3394 files changed, 214673 insertions, 66263 deletions

diff --git a/drivers/Makefile b/drivers/Makefile
index 24cd47014657..a6abd7a856c6 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -76,7 +76,7 @@ obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/
 obj-$(CONFIG_NUBUS)		+= nubus/
 obj-y				+= macintosh/
 obj-$(CONFIG_IDE)		+= ide/
-obj-$(CONFIG_SCSI)		+= scsi/
+obj-y				+= scsi/
 obj-y				+= nvme/
 obj-$(CONFIG_ATA)		+= ata/
 obj-$(CONFIG_TARGET_CORE)	+= target/
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index b533eeb6139d..4a46344bf0e3 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -5,11 +5,10 @@
 
 menuconfig ACPI
 	bool "ACPI (Advanced Configuration and Power Interface) Support"
-	depends on !IA64_HP_SIM
-	depends on IA64 || X86 || ARM64
+	depends on ARCH_SUPPORTS_ACPI
 	depends on PCI
 	select PNP
-	default y if (IA64 || X86)
+	default y if X86
 	help
 	  Advanced Configuration and Power Interface (ACPI) support for 
 	  Linux requires an ACPI-compliant platform (hardware/firmware),
@@ -41,6 +40,9 @@ menuconfig ACPI
 	  <http://www.acpi.info>
 	  <http://www.uefi.org/acpi/specs>
 
+config ARCH_SUPPORTS_ACPI
+	bool
+
 if ACPI
 
 config ACPI_LEGACY_TABLES_LOOKUP
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index 51c386bf230d..c5367bf5487f 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -165,7 +165,6 @@ struct acpi_namespace_node {
 #define ANOBJ_EVALUATED                 0x20	/* Set on first evaluation of node */
 #define ANOBJ_ALLOCATED_BUFFER          0x40	/* Method AML buffer is dynamic (install_method) */
 
-#define IMPLICIT_EXTERNAL               0x02	/* iASL only: This object created implicitly via External */
 #define ANOBJ_IS_EXTERNAL               0x08	/* iASL only: This object created via External() */
 #define ANOBJ_METHOD_NO_RETVAL          0x10	/* iASL only: Method has no return value */
 #define ANOBJ_METHOD_SOME_NO_RETVAL     0x20	/* iASL only: Method has at least one return value */
diff --git a/drivers/acpi/acpica/nsaccess.c b/drivers/acpi/acpica/nsaccess.c
index 220a718fbce9..83a593e2155d 100644
--- a/drivers/acpi/acpica/nsaccess.c
+++ b/drivers/acpi/acpica/nsaccess.c
@@ -613,13 +613,6 @@ acpi_ns_lookup(union acpi_generic_state *scope_info,
 		/* Special handling for the last segment (num_segments == 0) */
 
 		else {
-#ifdef ACPI_ASL_COMPILER
-			if (!acpi_gbl_disasm_flag
-			    && (this_node->flags & ANOBJ_IS_EXTERNAL)) {
-				this_node->flags &= ~IMPLICIT_EXTERNAL;
-			}
-#endif
-
 			/*
 			 * Sanity typecheck of the target object:
 			 *
diff --git a/drivers/acpi/acpica/nssearch.c b/drivers/acpi/acpica/nssearch.c
index e9c9a63bb6a4..f594ab75a5fe 100644
--- a/drivers/acpi/acpica/nssearch.c
+++ b/drivers/acpi/acpica/nssearch.c
@@ -381,7 +381,6 @@ acpi_ns_search_and_enter(u32 target_name,
 	if (flags & ACPI_NS_EXTERNAL ||
 	    (walk_state && walk_state->opcode == AML_SCOPE_OP)) {
 		new_node->flags |= ANOBJ_IS_EXTERNAL;
-		new_node->flags |= IMPLICIT_EXTERNAL;
 	}
 #endif
 
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 7a3a541046ed..08f26db2da7e 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -947,6 +947,24 @@ static int nc_dma_get_range(struct device *dev, u64 *size)
 	return 0;
 }
 
+static int rc_dma_get_range(struct device *dev, u64 *size)
+{
+	struct acpi_iort_node *node;
+	struct acpi_iort_root_complex *rc;
+
+	node = iort_scan_node(ACPI_IORT_NODE_PCI_ROOT_COMPLEX,
+			      iort_match_node_callback, dev);
+	if (!node || node->revision < 1)
+		return -ENODEV;
+
+	rc = (struct acpi_iort_root_complex *)node->node_data;
+
+	*size = rc->memory_address_limit >= 64 ? U64_MAX :
+			1ULL<<rc->memory_address_limit;
+
+	return 0;
+}
+
 /**
  * iort_dma_setup() - Set-up device DMA parameters.
  *
@@ -960,25 +978,28 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 	int ret, msb;
 
 	/*
-	 * Set default coherent_dma_mask to 32 bit.  Drivers are expected to
-	 * setup the correct supported mask.
+	 * If @dev is expected to be DMA-capable then the bus code that created
+	 * it should have initialised its dma_mask pointer by this point. For
+	 * now, we'll continue the legacy behaviour of coercing it to the
+	 * coherent mask if not, but we'll no longer do so quietly.
 	 */
-	if (!dev->coherent_dma_mask)
-		dev->coherent_dma_mask = DMA_BIT_MASK(32);
-
-	/*
-	 * Set it to coherent_dma_mask by default if the architecture
-	 * code has not set it.
-	 */
-	if (!dev->dma_mask)
+	if (!dev->dma_mask) {
+		dev_warn(dev, "DMA mask not set\n");
 		dev->dma_mask = &dev->coherent_dma_mask;
+	}
 
-	size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
+	if (dev->coherent_dma_mask)
+		size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
+	else
+		size = 1ULL << 32;
 
-	if (dev_is_pci(dev))
+	if (dev_is_pci(dev)) {
 		ret = acpi_dma_get_range(dev, &dmaaddr, &offset, &size);
-	else
+		if (ret == -ENODEV)
+			ret = rc_dma_get_range(dev, &size);
+	} else {
 		ret = nc_dma_get_range(dev, &size);
+	}
 
 	if (!ret) {
 		msb = fls64(dmaaddr + size - 1);
@@ -993,6 +1014,7 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 		 * Limit coherent and dma mask based on size
 		 * retrieved from firmware.
 		 */
+		dev->bus_dma_mask = mask;
 		dev->coherent_dma_mask = mask;
 		*dev->dma_mask = mask;
 	}
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index d79ad844c78f..cb97b6105f52 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -23,18 +23,18 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/async.h>
+#include <linux/delay.h>
+#include <linux/dmi.h>
+#include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/jiffies.h>
-#include <linux/async.h>
-#include <linux/dmi.h>
-#include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/suspend.h>
+#include <linux/types.h>
+
 #include <asm/unaligned.h>
 
 #ifdef CONFIG_ACPI_PROCFS_POWER
@@ -364,6 +364,20 @@ static enum power_supply_property energy_battery_props[] = {
 	POWER_SUPPLY_PROP_SERIAL_NUMBER,
 };
 
+static enum power_supply_property energy_battery_full_cap_broken_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_CYCLE_COUNT,
+	POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_POWER_NOW,
+	POWER_SUPPLY_PROP_ENERGY_NOW,
+	POWER_SUPPLY_PROP_MODEL_NAME,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+	POWER_SUPPLY_PROP_SERIAL_NUMBER,
+};
+
 /* --------------------------------------------------------------------------
                                Battery Management
    -------------------------------------------------------------------------- */
@@ -577,8 +591,7 @@ static int acpi_battery_get_state(struct acpi_battery *battery)
 		battery->rate_now != ACPI_BATTERY_VALUE_UNKNOWN &&
 		(s16)(battery->rate_now) < 0) {
 		battery->rate_now = abs((s16)battery->rate_now);
-		printk_once(KERN_WARNING FW_BUG
-			    "battery: (dis)charge rate invalid.\n");
+		pr_warn_once(FW_BUG "battery: (dis)charge rate invalid.\n");
 	}
 
 	if (test_bit(ACPI_BATTERY_QUIRK_PERCENTAGE_CAPACITY, &battery->flags)
@@ -799,6 +812,11 @@ static int sysfs_add_battery(struct acpi_battery *battery)
 		battery->bat_desc.properties = charge_battery_props;
 		battery->bat_desc.num_properties =
 			ARRAY_SIZE(charge_battery_props);
+	} else if (battery->full_charge_capacity == 0) {
+		battery->bat_desc.properties =
+			energy_battery_full_cap_broken_props;
+		battery->bat_desc.num_properties =
+			ARRAY_SIZE(energy_battery_full_cap_broken_props);
 	} else {
 		battery->bat_desc.properties = energy_battery_props;
 		battery->bat_desc.num_properties =
@@ -918,10 +936,11 @@ static void acpi_battery_quirks(struct acpi_battery *battery)
 
 static int acpi_battery_update(struct acpi_battery *battery, bool resume)
 {
-	int result, old_present = acpi_battery_present(battery);
-	result = acpi_battery_get_status(battery);
+	int result = acpi_battery_get_status(battery);
+
 	if (result)
 		return result;
+
 	if (!acpi_battery_present(battery)) {
 		sysfs_remove_battery(battery);
 		battery->update_time = 0;
@@ -931,8 +950,7 @@ static int acpi_battery_update(struct acpi_battery *battery, bool resume)
 	if (resume)
 		return 0;
 
-	if (!battery->update_time ||
-	    old_present != acpi_battery_present(battery)) {
+	if (!battery->update_time) {
 		result = acpi_battery_get_info(battery);
 		if (result)
 			return result;
@@ -1021,7 +1039,7 @@ static int acpi_battery_info_proc_show(struct seq_file *seq, void *offset)
 			   acpi_battery_units(battery));
 
 	seq_printf(seq, "battery technology:      %srechargeable\n",
-		   (!battery->technology)?"non-":"");
+		   battery->technology ? "" : "non-");
 
 	if (battery->design_voltage == ACPI_BATTERY_VALUE_UNKNOWN)
 		seq_printf(seq, "design voltage:          unknown\n");
@@ -1112,11 +1130,12 @@ static int acpi_battery_alarm_proc_show(struct seq_file *seq, void *offset)
 		goto end;
 	}
 	seq_printf(seq, "alarm:                   ");
-	if (!battery->alarm)
-		seq_printf(seq, "unsupported\n");
-	else
+	if (battery->alarm) {
 		seq_printf(seq, "%u %sh\n", battery->alarm,
 				acpi_battery_units(battery));
+	} else {
+		seq_printf(seq, "unsupported\n");
+	}
       end:
 	if (result)
 		seq_printf(seq, "ERROR: Unable to read battery alarm\n");
@@ -1149,9 +1168,9 @@ static ssize_t acpi_battery_write_alarm(struct file *file,
 	}
 	result = acpi_battery_set_alarm(battery);
       end:
-	if (!result)
-		return count;
-	return result;
+	if (result)
+		return result;
+	return count;
 }
 
 static int acpi_battery_alarm_proc_open(struct inode *inode, struct file *file)
@@ -1170,8 +1189,7 @@ static const struct file_operations acpi_battery_alarm_fops = {
 
 static int acpi_battery_add_fs(struct acpi_device *device)
 {
-	printk(KERN_WARNING PREFIX "Deprecated procfs I/F for battery is loaded,"
-			" please retry with CONFIG_ACPI_PROCFS_POWER cleared\n");
+	pr_warning(PREFIX "Deprecated procfs I/F for battery is loaded, please retry with CONFIG_ACPI_PROCFS_POWER cleared\n");
 	if (!acpi_device_dir(device)) {
 		acpi_device_dir(device) = proc_mkdir(acpi_device_bid(device),
 						     acpi_battery_dir);
@@ -1247,7 +1265,9 @@ static int battery_notify(struct notifier_block *nb,
 		if (!acpi_battery_present(battery))
 			return 0;
 
-		if (!battery->bat) {
+		if (battery->bat) {
+			acpi_battery_refresh(battery);
+		} else {
 			result = acpi_battery_get_info(battery);
 			if (result)
 				return result;
@@ -1255,8 +1275,7 @@ static int battery_notify(struct notifier_block *nb,
 			result = sysfs_add_battery(battery);
 			if (result)
 				return result;
-		} else
-			acpi_battery_refresh(battery);
+		}
 
 		acpi_battery_init_alarm(battery);
 		acpi_battery_get_state(battery);
@@ -1398,7 +1417,7 @@ static int acpi_battery_add(struct acpi_device *device)
 	}
 #endif
 
-	printk(KERN_INFO PREFIX "%s Slot [%s] (battery %s)\n",
+	pr_info(PREFIX "%s Slot [%s] (battery %s)\n",
 		ACPI_BATTERY_DEVICE_NAME, acpi_device_bid(device),
 		device->status.battery_present ? "present" : "absent");
 
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 84b4a62018eb..292088fcc624 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -66,37 +66,10 @@ static int set_copy_dsdt(const struct dmi_system_id *id)
 	return 0;
 }
 #endif
-static int set_gbl_term_list(const struct dmi_system_id *id)
-{
-	acpi_gbl_execute_tables_as_methods = 1;
-	return 0;
-}
 
-static const struct dmi_system_id acpi_quirks_dmi_table[] __initconst = {
-	/*
-	 * Touchpad on Dell XPS 9570/Precision M5530 doesn't work under I2C
-	 * mode.
-	 * https://bugzilla.kernel.org/show_bug.cgi?id=198515
-	 */
-	{
-		.callback = set_gbl_term_list,
-		.ident = "Dell Precision M5530",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Precision M5530"),
-		},
-	},
-	{
-		.callback = set_gbl_term_list,
-		.ident = "Dell XPS 15 9570",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "XPS 15 9570"),
-		},
-	},
+static const struct dmi_system_id dsdt_dmi_table[] __initconst = {
 	/*
 	 * Invoke DSDT corruption work-around on all Toshiba Satellite.
-	 * DSDT will be copied to memory.
 	 * https://bugzilla.kernel.org/show_bug.cgi?id=14679
 	 */
 	{
@@ -110,7 +83,7 @@ static const struct dmi_system_id acpi_quirks_dmi_table[] __initconst = {
 	{}
 };
 #else
-static const struct dmi_system_id acpi_quirks_dmi_table[] __initconst = {
+static const struct dmi_system_id dsdt_dmi_table[] __initconst = {
 	{}
 };
 #endif
@@ -962,7 +935,7 @@ static int acpi_device_probe(struct device *dev)
 	return 0;
 }
 
-static int acpi_device_remove(struct device * dev)
+static int acpi_device_remove(struct device *dev)
 {
 	struct acpi_device *acpi_dev = to_acpi_device(dev);
 	struct acpi_driver *acpi_drv = acpi_dev->driver;
@@ -1060,8 +1033,11 @@ void __init acpi_early_init(void)
 
 	acpi_permanent_mmap = true;
 
-	/* Check machine-specific quirks */
-	dmi_check_system(acpi_quirks_dmi_table);
+	/*
+	 * If the machine falls into the DMI check table,
+	 * DSDT will be copied to memory
+	 */
+	dmi_check_system(dsdt_dmi_table);
 
 	status = acpi_reallocate_root_table();
 	if (ACPI_FAILURE(status)) {
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 2345a5ee2dbb..a19ff3977ac4 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -21,6 +21,7 @@
 
 #define pr_fmt(fmt) "ACPI: button: " fmt
 
+#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -235,9 +236,6 @@ static int acpi_lid_notify_state(struct acpi_device *device, int state)
 		button->last_time = ktime_get();
 	}
 
-	if (state)
-		acpi_pm_wakeup_event(&device->dev);
-
 	ret = blocking_notifier_call_chain(&acpi_lid_notifier, state, device);
 	if (ret == NOTIFY_DONE)
 		ret = blocking_notifier_call_chain(&acpi_lid_notifier, state,
@@ -252,7 +250,8 @@ static int acpi_lid_notify_state(struct acpi_device *device, int state)
 	return ret;
 }
 
-static int acpi_button_state_seq_show(struct seq_file *seq, void *offset)
+static int __maybe_unused acpi_button_state_seq_show(struct seq_file *seq,
+						     void *offset)
 {
 	struct acpi_device *device = seq->private;
 	int state;
@@ -366,7 +365,8 @@ int acpi_lid_open(void)
 }
 EXPORT_SYMBOL(acpi_lid_open);
 
-static int acpi_lid_update_state(struct acpi_device *device)
+static int acpi_lid_update_state(struct acpi_device *device,
+				 bool signal_wakeup)
 {
 	int state;
 
@@ -374,6 +374,9 @@ static int acpi_lid_update_state(struct acpi_device *device)
 	if (state < 0)
 		return state;
 
+	if (state && signal_wakeup)
+		acpi_pm_wakeup_event(&device->dev);
+
 	return acpi_lid_notify_state(device, state);
 }
 
@@ -384,7 +387,7 @@ static void acpi_lid_initialize_state(struct acpi_device *device)
 		(void)acpi_lid_notify_state(device, 1);
 		break;
 	case ACPI_BUTTON_LID_INIT_METHOD:
-		(void)acpi_lid_update_state(device);
+		(void)acpi_lid_update_state(device, false);
 		break;
 	case ACPI_BUTTON_LID_INIT_IGNORE:
 	default:
@@ -409,7 +412,7 @@ static void acpi_button_notify(struct acpi_device *device, u32 event)
 			users = button->input->users;
 			mutex_unlock(&button->input->mutex);
 			if (users)
-				acpi_lid_update_state(device);
+				acpi_lid_update_state(device, true);
 		} else {
 			int keycode;
 
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 917f77f4cb55..d4e5610e09c5 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -2045,6 +2045,20 @@ static const struct dmi_system_id acpi_ec_no_wakeup[] = {
 			DMI_MATCH(DMI_PRODUCT_FAMILY, "Thinkpad X1 Carbon 6th"),
 		},
 	},
+	{
+		.ident = "ThinkPad X1 Carbon 6th",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Carbon 6th"),
+		},
+	},
+	{
+		.ident = "ThinkPad X1 Yoga 3rd",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Yoga 3rd"),
+		},
+	},
 	{ },
 };
 
diff --git a/drivers/acpi/osi.c b/drivers/acpi/osi.c
index 8a8f43568510..b2a16ed7e81a 100644
--- a/drivers/acpi/osi.c
+++ b/drivers/acpi/osi.c
@@ -66,6 +66,14 @@ osi_setup_entries[OSI_STRING_ENTRIES_MAX] __initdata = {
 	 * be removed if both new and old graphics cards are supported.
 	 */
 	{"Linux-Dell-Video", true},
+	/*
+	 * Linux-Lenovo-NV-HDMI-Audio is used by BIOS to power on NVidia's HDMI
+	 * audio device which is turned off for power-saving in Windows OS.
+	 * This power management feature observed on some Lenovo Thinkpad
+	 * systems which will not be able to output audio via HDMI without
+	 * a BIOS workaround.
+	 */
+	{"Linux-Lenovo-NV-HDMI-Audio", true},
 };
 
 static u32 acpi_osi_handler(acpi_string interface, u32 supported)
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 5815356ea6ad..693cf05b0cc4 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -542,6 +542,23 @@ static int acpi_data_get_property_array(const struct acpi_device_data *data,
 	return 0;
 }
 
+static struct fwnode_handle *
+acpi_fwnode_get_named_child_node(const struct fwnode_handle *fwnode,
+				 const char *childname)
+{
+	struct fwnode_handle *child;
+
+	/*
+	 * Find first matching named child node of this fwnode.
+	 * For ACPI this will be a data only sub-node.
+	 */
+	fwnode_for_each_child_node(fwnode, child)
+		if (acpi_data_node_match(child, childname))
+			return child;
+
+	return NULL;
+}
+
 /**
  * __acpi_node_get_property_reference - returns handle to the referenced object
  * @fwnode: Firmware node to get the property from
@@ -579,7 +596,7 @@ static int acpi_data_get_property_array(const struct acpi_device_data *data,
  */
 int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 	const char *propname, size_t index, size_t num_args,
-	struct acpi_reference_args *args)
+	struct fwnode_reference_args *args)
 {
 	const union acpi_object *element, *end;
 	const union acpi_object *obj;
@@ -607,7 +624,7 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 		if (ret)
 			return ret == -ENODEV ? -EINVAL : ret;
 
-		args->adev = device;
+		args->fwnode = acpi_fwnode_handle(device);
 		args->nargs = 0;
 		return 0;
 	}
@@ -633,6 +650,8 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 		u32 nargs, i;
 
 		if (element->type == ACPI_TYPE_LOCAL_REFERENCE) {
+			struct fwnode_handle *ref_fwnode;
+
 			ret = acpi_bus_get_device(element->reference.handle,
 						  &device);
 			if (ret)
@@ -641,6 +660,19 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 			nargs = 0;
 			element++;
 
+			/*
+			 * Find the referred data extension node under the
+			 * referred device node.
+			 */
+			for (ref_fwnode = acpi_fwnode_handle(device);
+			     element < end && element->type == ACPI_TYPE_STRING;
+			     element++) {
+				ref_fwnode = acpi_fwnode_get_named_child_node(
+					ref_fwnode, element->string.pointer);
+				if (!ref_fwnode)
+					return -EINVAL;
+			}
+
 			/* assume following integer elements are all args */
 			for (i = 0; element + i < end && i < num_args; i++) {
 				int type = element[i].type;
@@ -653,11 +685,11 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 					return -EINVAL;
 			}
 
-			if (nargs > MAX_ACPI_REFERENCE_ARGS)
+			if (nargs > NR_FWNODE_REFERENCE_ARGS)
 				return -EINVAL;
 
 			if (idx == index) {
-				args->adev = device;
+				args->fwnode = ref_fwnode;
 				args->nargs = nargs;
 				for (i = 0; i < nargs; i++)
 					args->args[i] = element[i].integer.value;
@@ -995,16 +1027,36 @@ struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode)
 	return NULL;
 }
 
+/*
+ * Return true if the node is an ACPI graph node. Called on either ports
+ * or endpoints.
+ */
+static bool is_acpi_graph_node(struct fwnode_handle *fwnode,
+			       const char *str)
+{
+	unsigned int len = strlen(str);
+	const char *name;
+
+	if (!len || !is_acpi_data_node(fwnode))
+		return false;
+
+	name = to_acpi_data_node(fwnode)->name;
+
+	return (fwnode_property_present(fwnode, "reg") &&
+		!strncmp(name, str, len) && name[len] == '@') ||
+		fwnode_property_present(fwnode, str);
+}
+
 /**
  * acpi_graph_get_next_endpoint - Get next endpoint ACPI firmware node
  * @fwnode: Pointer to the parent firmware node
  * @prev: Previous endpoint node or %NULL to get the first
  *
  * Looks up next endpoint ACPI firmware node below a given @fwnode. Returns
- * %NULL if there is no next endpoint, ERR_PTR() in case of error. In case
- * of success the next endpoint is returned.
+ * %NULL if there is no next endpoint or in case of error. In case of success
+ * the next endpoint is returned.
  */
-struct fwnode_handle *acpi_graph_get_next_endpoint(
+static struct fwnode_handle *acpi_graph_get_next_endpoint(
 	const struct fwnode_handle *fwnode, struct fwnode_handle *prev)
 {
 	struct fwnode_handle *port = NULL;
@@ -1013,8 +1065,14 @@ struct fwnode_handle *acpi_graph_get_next_endpoint(
 	if (!prev) {
 		do {
 			port = fwnode_get_next_child_node(fwnode, port);
-			/* Ports must have port property */
-			if (fwnode_property_present(port, "port"))
+			/*
+			 * The names of the port nodes begin with "port@"
+			 * followed by the number of the port node and they also
+			 * have a "reg" property that also has the number of the
+			 * port node. For compatibility reasons a node is also
+			 * recognised as a port node from the "port" property.
+			 */
+			if (is_acpi_graph_node(port, "port"))
 				break;
 		} while (port);
 	} else {
@@ -1029,15 +1087,19 @@ struct fwnode_handle *acpi_graph_get_next_endpoint(
 		port = fwnode_get_next_child_node(fwnode, port);
 		if (!port)
 			break;
-		if (fwnode_property_present(port, "port"))
+		if (is_acpi_graph_node(port, "port"))
 			endpoint = fwnode_get_next_child_node(port, NULL);
 	}
 
-	if (endpoint) {
-		/* Endpoints must have "endpoint" property */
-		if (!fwnode_property_present(endpoint, "endpoint"))
-			return ERR_PTR(-EPROTO);
-	}
+	/*
+	 * The names of the endpoint nodes begin with "endpoint@" followed by
+	 * the number of the endpoint node and they also have a "reg" property
+	 * that also has the number of the endpoint node. For compatibility
+	 * reasons a node is also recognised as an endpoint node from the
+	 * "endpoint" property.
+	 */
+	if (!is_acpi_graph_node(endpoint, "endpoint"))
+		return NULL;
 
 	return endpoint;
 }
@@ -1074,65 +1136,42 @@ static struct fwnode_handle *acpi_graph_get_child_prop_value(
 /**
  * acpi_graph_get_remote_enpoint - Parses and returns remote end of an endpoint
  * @fwnode: Endpoint firmware node pointing to a remote device
- * @parent: Firmware node of remote port parent is filled here if not %NULL
- * @port: Firmware node of remote port is filled here if not %NULL
  * @endpoint: Firmware node of remote endpoint is filled here if not %NULL
  *
- * Function parses remote end of ACPI firmware remote endpoint and fills in
- * fields requested by the caller. Returns %0 in case of success and
- * negative errno otherwise.
+ * Returns the remote endpoint corresponding to @__fwnode. NULL on error.
  */
-int acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode,
-				   struct fwnode_handle **parent,
-				   struct fwnode_handle **port,
-				   struct fwnode_handle **endpoint)
+static struct fwnode_handle *
+acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode)
 {
 	struct fwnode_handle *fwnode;
 	unsigned int port_nr, endpoint_nr;
-	struct acpi_reference_args args;
+	struct fwnode_reference_args args;
 	int ret;
 
 	memset(&args, 0, sizeof(args));
 	ret = acpi_node_get_property_reference(__fwnode, "remote-endpoint", 0,
 					       &args);
 	if (ret)
-		return ret;
+		return NULL;
+
+	/* Direct endpoint reference? */
+	if (!is_acpi_device_node(args.fwnode))
+		return args.nargs ? NULL : args.fwnode;
 
 	/*
 	 * Always require two arguments with the reference: port and
 	 * endpoint indices.
 	 */
 	if (args.nargs != 2)
-		return -EPROTO;
+		return NULL;
 
-	fwnode = acpi_fwnode_handle(args.adev);
+	fwnode = args.fwnode;
 	port_nr = args.args[0];
 	endpoint_nr = args.args[1];
 
-	if (parent)
-		*parent = fwnode;
-
-	if (!port && !endpoint)
-		return 0;
-
 	fwnode = acpi_graph_get_child_prop_value(fwnode, "port", port_nr);
-	if (!fwnode)
-		return -EPROTO;
-
-	if (port)
-		*port = fwnode;
-
-	if (!endpoint)
-		return 0;
 
-	fwnode = acpi_graph_get_child_prop_value(fwnode, "endpoint",
-						 endpoint_nr);
-	if (!fwnode)
-		return -EPROTO;
-
-	*endpoint = fwnode;
-
-	return 0;
+	return acpi_graph_get_child_prop_value(fwnode, "endpoint", endpoint_nr);
 }
 
 static bool acpi_fwnode_device_is_available(const struct fwnode_handle *fwnode)
@@ -1186,70 +1225,14 @@ acpi_fwnode_property_read_string_array(const struct fwnode_handle *fwnode,
 				   val, nval);
 }
 
-static struct fwnode_handle *
-acpi_fwnode_get_named_child_node(const struct fwnode_handle *fwnode,
-				 const char *childname)
-{
-	struct fwnode_handle *child;
-
-	/*
-	 * Find first matching named child node of this fwnode.
-	 * For ACPI this will be a data only sub-node.
-	 */
-	fwnode_for_each_child_node(fwnode, child)
-		if (acpi_data_node_match(child, childname))
-			return child;
-
-	return NULL;
-}
-
 static int
 acpi_fwnode_get_reference_args(const struct fwnode_handle *fwnode,
 			       const char *prop, const char *nargs_prop,
 			       unsigned int args_count, unsigned int index,
 			       struct fwnode_reference_args *args)
 {
-	struct acpi_reference_args acpi_args;
-	unsigned int i;
-	int ret;
-
-	ret = __acpi_node_get_property_reference(fwnode, prop, index,
-						 args_count, &acpi_args);
-	if (ret < 0)
-		return ret;
-	if (!args)
-		return 0;
-
-	args->nargs = acpi_args.nargs;
-	args->fwnode = acpi_fwnode_handle(acpi_args.adev);
-
-	for (i = 0; i < NR_FWNODE_REFERENCE_ARGS; i++)
-		args->args[i] = i < acpi_args.nargs ? acpi_args.args[i] : 0;
-
-	return 0;
-}
-
-static struct fwnode_handle *
-acpi_fwnode_graph_get_next_endpoint(const struct fwnode_handle *fwnode,
-				    struct fwnode_handle *prev)
-{
-	struct fwnode_handle *endpoint;
-
-	endpoint = acpi_graph_get_next_endpoint(fwnode, prev);
-	if (IS_ERR(endpoint))
-		return NULL;
-
-	return endpoint;
-}
-
-static struct fwnode_handle *
-acpi_fwnode_graph_get_remote_endpoint(const struct fwnode_handle *fwnode)
-{
-	struct fwnode_handle *endpoint = NULL;
-
-	acpi_graph_get_remote_endpoint(fwnode, NULL, NULL, &endpoint);
-
-	return endpoint;
+	return __acpi_node_get_property_reference(fwnode, prop, index,
+						  args_count, args);
 }
 
 static struct fwnode_handle *
@@ -1265,8 +1248,10 @@ static int acpi_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode,
 
 	endpoint->local_fwnode = fwnode;
 
-	fwnode_property_read_u32(port_fwnode, "port", &endpoint->port);
-	fwnode_property_read_u32(fwnode, "endpoint", &endpoint->id);
+	if (fwnode_property_read_u32(port_fwnode, "reg", &endpoint->port))
+		fwnode_property_read_u32(port_fwnode, "port", &endpoint->port);
+	if (fwnode_property_read_u32(fwnode, "reg", &endpoint->id))
+		fwnode_property_read_u32(fwnode, "endpoint", &endpoint->id);
 
 	return 0;
 }
@@ -1292,9 +1277,9 @@ acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode,
 		.get_named_child_node = acpi_fwnode_get_named_child_node, \
 		.get_reference_args = acpi_fwnode_get_reference_args,	\
 		.graph_get_next_endpoint =				\
-			acpi_fwnode_graph_get_next_endpoint,		\
+			acpi_graph_get_next_endpoint,			\
 		.graph_get_remote_endpoint =				\
-			acpi_fwnode_graph_get_remote_endpoint,		\
+			acpi_graph_get_remote_endpoint,			\
 		.graph_get_port_parent = acpi_fwnode_get_parent,	\
 		.graph_parse_endpoint = acpi_fwnode_graph_parse_endpoint, \
 	};								\
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 970dd87d347c..e1b6231cfa1c 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1528,7 +1528,7 @@ static int acpi_check_serial_bus_slave(struct acpi_resource *ares, void *data)
 static bool acpi_is_indirect_io_slave(struct acpi_device *device)
 {
 	struct acpi_device *parent = device->parent;
-	const struct acpi_device_id indirect_io_hosts[] = {
+	static const struct acpi_device_id indirect_io_hosts[] = {
 		{"HISI0191", 0},
 		{}
 	};
@@ -1540,6 +1540,18 @@ static bool acpi_device_enumeration_by_parent(struct acpi_device *device)
 {
 	struct list_head resource_list;
 	bool is_serial_bus_slave = false;
+	/*
+	 * These devices have multiple I2cSerialBus resources and an i2c-client
+	 * must be instantiated for each, each with its own i2c_device_id.
+	 * Normally we only instantiate an i2c-client for the first resource,
+	 * using the ACPI HID as id. These special cases are handled by the
+	 * drivers/platform/x86/i2c-multi-instantiate.c driver, which knows
+	 * which i2c_device_id to use for each resource.
+	 */
+	static const struct acpi_device_id i2c_multi_instantiate_ids[] = {
+		{"BSG1160", },
+		{}
+	};
 
 	if (acpi_is_indirect_io_slave(device))
 		return true;
@@ -1551,6 +1563,10 @@ static bool acpi_device_enumeration_by_parent(struct acpi_device *device)
 	     fwnode_property_present(&device->fwnode, "baud")))
 		return true;
 
+	/* Instantiate a pdev for the i2c-multi-instantiate drv to bind to */
+	if (!acpi_match_device_ids(device, i2c_multi_instantiate_ids))
+		return false;
+
 	INIT_LIST_HEAD(&resource_list);
 	acpi_dev_get_resources(device, &resource_list,
 			       acpi_check_serial_bus_slave,
@@ -1612,7 +1628,8 @@ static int acpi_add_single_object(struct acpi_device **child,
 	 * Note this must be done before the get power-/wakeup_dev-flags calls.
 	 */
 	if (type == ACPI_BUS_TYPE_DEVICE)
-		acpi_bus_get_status(device);
+		if (acpi_bus_get_status(device) < 0)
+			acpi_set_device_status(device, 0);
 
 	acpi_bus_get_power_flags(device);
 	acpi_bus_get_wakeup_device_flags(device);
@@ -1690,7 +1707,7 @@ static int acpi_bus_type_and_status(acpi_handle handle, int *type,
 		 * acpi_add_single_object updates this once we've an acpi_device
 		 * so that acpi_bus_get_status' quirk handling can be used.
 		 */
-		*sta = 0;
+		*sta = ACPI_STA_DEFAULT;
 		break;
 	case ACPI_TYPE_PROCESSOR:
 		*type = ACPI_BUS_TYPE_PROCESSOR;
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 5d0486f1cfcd..754d59f95500 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -338,6 +338,14 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "K54HR"),
 		},
 	},
+	{
+	.callback = init_nvs_save_s3,
+	.ident = "Asus 1025C",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "1025C"),
+		},
+	},
 	/*
 	 * https://bugzilla.kernel.org/show_bug.cgi?id=189431
 	 * Lenovo G50-45 is a platform later than 2012, but needs nvs memory
@@ -718,9 +726,6 @@ static const struct acpi_device_id lps0_device_ids[] = {
 #define ACPI_LPS0_ENTRY		5
 #define ACPI_LPS0_EXIT		6
 
-#define ACPI_LPS0_SCREEN_MASK	((1 << ACPI_LPS0_SCREEN_OFF) | (1 << ACPI_LPS0_SCREEN_ON))
-#define ACPI_LPS0_PLATFORM_MASK	((1 << ACPI_LPS0_ENTRY) | (1 << ACPI_LPS0_EXIT))
-
 static acpi_handle lps0_device_handle;
 static guid_t lps0_dsm_guid;
 static char lps0_dsm_func_mask;
@@ -924,17 +929,14 @@ static int lps0_device_attach(struct acpi_device *adev,
 	if (out_obj && out_obj->type == ACPI_TYPE_BUFFER) {
 		char bitmask = *(char *)out_obj->buffer.pointer;
 
-		if ((bitmask & ACPI_LPS0_PLATFORM_MASK) == ACPI_LPS0_PLATFORM_MASK ||
-		    (bitmask & ACPI_LPS0_SCREEN_MASK) == ACPI_LPS0_SCREEN_MASK) {
-			lps0_dsm_func_mask = bitmask;
-			lps0_device_handle = adev->handle;
-			/*
-			 * Use suspend-to-idle by default if the default
-			 * suspend mode was not set from the command line.
-			 */
-			if (mem_sleep_default > PM_SUSPEND_MEM)
-				mem_sleep_current = PM_SUSPEND_TO_IDLE;
-		}
+		lps0_dsm_func_mask = bitmask;
+		lps0_device_handle = adev->handle;
+		/*
+		 * Use suspend-to-idle by default if the default
+		 * suspend mode was not set from the command line.
+		 */
+		if (mem_sleep_default > PM_SUSPEND_MEM)
+			mem_sleep_current = PM_SUSPEND_TO_IDLE;
 
 		acpi_handle_debug(adev->handle, "_DSM function mask: 0x%x\n",
 				  bitmask);
diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c
index ec5b0f190231..06c31ec3cc70 100644
--- a/drivers/acpi/x86/utils.c
+++ b/drivers/acpi/x86/utils.c
@@ -62,14 +62,20 @@ static const struct always_present_id always_present_ids[] = {
 	 */
 	ENTRY("INT0002", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT), {}),
 	/*
-	 * On the Dell Venue 11 Pro 7130 the DSDT hides the touchscreen ACPI
-	 * device until a certain time after _SB.PCI0.GFX0.LCD.LCD1._ON gets
-	 * called has passed *and* _STA has been called at least 3 times since.
+	 * On the Dell Venue 11 Pro 7130 and 7139, the DSDT hides
+	 * the touchscreen ACPI device until a certain time
+	 * after _SB.PCI0.GFX0.LCD.LCD1._ON gets called has passed
+	 * *and* _STA has been called at least 3 times since.
 	 */
 	ENTRY("SYNA7500", "1", ICPU(INTEL_FAM6_HASWELL_ULT), {
 		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 		DMI_MATCH(DMI_PRODUCT_NAME, "Venue 11 Pro 7130"),
 	      }),
+	ENTRY("SYNA7500", "1", ICPU(INTEL_FAM6_HASWELL_ULT), {
+		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Venue 11 Pro 7139"),
+	      }),
+
 	/*
 	 * The GPD win BIOS dated 20170221 has disabled the accelerometer, the
 	 * drivers sometimes cause crashes under Windows and this is how the
@@ -103,13 +109,9 @@ static const struct always_present_id always_present_ids[] = {
 
 bool acpi_device_always_present(struct acpi_device *adev)
 {
-	u32 *status = (u32 *)&adev->status;
-	u32 old_status = *status;
 	bool ret = false;
 	unsigned int i;
 
-	/* acpi_match_device_ids checks status, so set it to default */
-	*status = ACPI_STA_DEFAULT;
 	for (i = 0; i < ARRAY_SIZE(always_present_ids); i++) {
 		if (acpi_match_device_ids(adev, always_present_ids[i].hid))
 			continue;
@@ -125,15 +127,9 @@ bool acpi_device_always_present(struct acpi_device *adev)
 		    !dmi_check_system(always_present_ids[i].dmi_ids))
 			continue;
 
-		if (old_status != ACPI_STA_DEFAULT) /* Log only once */
-			dev_info(&adev->dev,
-				 "Device [%s] is in always present list\n",
-				 adev->pnp.bus_id);
-
 		ret = true;
 		break;
 	}
-	*status = old_status;
 
 	return ret;
 }
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index cc71c63df381..984b37647b2f 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -6424,6 +6424,7 @@ void ata_host_init(struct ata_host *host, struct device *dev,
 	host->n_tags = ATA_MAX_QUEUE;
 	host->dev = dev;
 	host->ops = ops;
+	kref_init(&host->kref);
 }
 
 void __ata_port_probe(struct ata_port *ap)
@@ -7391,3 +7392,5 @@ EXPORT_SYMBOL_GPL(ata_cable_80wire);
 EXPORT_SYMBOL_GPL(ata_cable_unknown);
 EXPORT_SYMBOL_GPL(ata_cable_ignore);
 EXPORT_SYMBOL_GPL(ata_cable_sata);
+EXPORT_SYMBOL_GPL(ata_host_get);
+EXPORT_SYMBOL_GPL(ata_host_put);
\ No newline at end of file
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index aad1b01447de..8e270962b2f3 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -597,8 +597,9 @@ static int ata_get_identity(struct ata_port *ap, struct scsi_device *sdev,
 int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg)
 {
 	int rc = 0;
+	u8 sensebuf[SCSI_SENSE_BUFFERSIZE];
 	u8 scsi_cmd[MAX_COMMAND_SIZE];
-	u8 args[4], *argbuf = NULL, *sensebuf = NULL;
+	u8 args[4], *argbuf = NULL;
 	int argsize = 0;
 	enum dma_data_direction data_dir;
 	struct scsi_sense_hdr sshdr;
@@ -610,10 +611,7 @@ int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg)
 	if (copy_from_user(args, arg, sizeof(args)))
 		return -EFAULT;
 
-	sensebuf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_NOIO);
-	if (!sensebuf)
-		return -ENOMEM;
-
+	memset(sensebuf, 0, sizeof(sensebuf));
 	memset(scsi_cmd, 0, sizeof(scsi_cmd));
 
 	if (args[3]) {
@@ -685,7 +683,6 @@ int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg)
 	 && copy_to_user(arg + sizeof(args), argbuf, argsize))
 		rc = -EFAULT;
 error:
-	kfree(sensebuf);
 	kfree(argbuf);
 	return rc;
 }
@@ -704,8 +701,9 @@ error:
 int ata_task_ioctl(struct scsi_device *scsidev, void __user *arg)
 {
 	int rc = 0;
+	u8 sensebuf[SCSI_SENSE_BUFFERSIZE];
 	u8 scsi_cmd[MAX_COMMAND_SIZE];
-	u8 args[7], *sensebuf = NULL;
+	u8 args[7];
 	struct scsi_sense_hdr sshdr;
 	int cmd_result;
 
@@ -715,10 +713,7 @@ int ata_task_ioctl(struct scsi_device *scsidev, void __user *arg)
 	if (copy_from_user(args, arg, sizeof(args)))
 		return -EFAULT;
 
-	sensebuf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_NOIO);
-	if (!sensebuf)
-		return -ENOMEM;
-
+	memset(sensebuf, 0, sizeof(sensebuf));
 	memset(scsi_cmd, 0, sizeof(scsi_cmd));
 	scsi_cmd[0]  = ATA_16;
 	scsi_cmd[1]  = (3 << 1); /* Non-data */
@@ -769,7 +764,6 @@ int ata_task_ioctl(struct scsi_device *scsidev, void __user *arg)
 	}
 
  error:
-	kfree(sensebuf);
 	return rc;
 }
 
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index 9e21c49cf6be..f953cb4bb1ba 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -100,8 +100,6 @@ extern int ata_port_probe(struct ata_port *ap);
 extern void __ata_port_probe(struct ata_port *ap);
 extern unsigned int ata_read_log_page(struct ata_device *dev, u8 log,
 				      u8 page, void *buf, unsigned int sectors);
-extern void ata_host_get(struct ata_host *host);
-extern void ata_host_put(struct ata_host *host);
 
 #define to_ata_port(d) container_of(d, struct ata_port, tdev)
 
diff --git a/drivers/ata/pata_pxa.c b/drivers/ata/pata_pxa.c
index f6c46e9a4dc0..e8b6a2e464c9 100644
--- a/drivers/ata/pata_pxa.c
+++ b/drivers/ata/pata_pxa.c
@@ -25,7 +25,6 @@
 #include <linux/libata.h>
 #include <linux/platform_device.h>
 #include <linux/dmaengine.h>
-#include <linux/dma/pxa-dma.h>
 #include <linux/gpio.h>
 #include <linux/slab.h>
 #include <linux/completion.h>
@@ -180,8 +179,6 @@ static int pxa_ata_probe(struct platform_device *pdev)
 	struct resource *irq_res;
 	struct pata_pxa_pdata *pdata = dev_get_platdata(&pdev->dev);
 	struct dma_slave_config	config;
-	dma_cap_mask_t mask;
-	struct pxad_param param;
 	int ret = 0;
 
 	/*
@@ -278,10 +275,6 @@ static int pxa_ata_probe(struct platform_device *pdev)
 
 	ap->private_data = data;
 
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_SLAVE, mask);
-	param.prio = PXAD_PRIO_LOWEST;
-	param.drcmr = pdata->dma_dreq;
 	memset(&config, 0, sizeof(config));
 	config.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
 	config.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
@@ -294,8 +287,7 @@ static int pxa_ata_probe(struct platform_device *pdev)
 	 * Request the DMA channel
 	 */
 	data->dma_chan =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &param, &pdev->dev, "data");
+		dma_request_slave_channel(&pdev->dev, "data");
 	if (!data->dma_chan)
 		return -EBUSY;
 	ret = dmaengine_slave_config(data->dma_chan, &config);
diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c
index 2c288d1f42bb..e89146ddede6 100644
--- a/drivers/atm/zatm.c
+++ b/drivers/atm/zatm.c
@@ -1385,14 +1385,12 @@ static void zatm_close(struct atm_vcc *vcc)
 
 static int zatm_open(struct atm_vcc *vcc)
 {
-	struct zatm_dev *zatm_dev;
 	struct zatm_vcc *zatm_vcc;
 	short vpi = vcc->vpi;
 	int vci = vcc->vci;
 	int error;
 
 	DPRINTK(">zatm_open\n");
-	zatm_dev = ZATM_DEV(vcc->dev);
 	if (!test_bit(ATM_VF_PARTIAL,&vcc->flags))
 		vcc->dev_data = NULL;
 	if (vci != ATM_VPI_UNSPEC && vpi != ATM_VCI_UNSPEC)
diff --git a/drivers/auxdisplay/arm-charlcd.c b/drivers/auxdisplay/arm-charlcd.c
index 296fb30dfa00..dea031484cc4 100644
--- a/drivers/auxdisplay/arm-charlcd.c
+++ b/drivers/auxdisplay/arm-charlcd.c
@@ -331,8 +331,7 @@ out_no_resource:
 
 static int charlcd_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct charlcd *lcd = platform_get_drvdata(pdev);
+	struct charlcd *lcd = dev_get_drvdata(dev);
 
 	/* Power the display off */
 	charlcd_4bit_command(lcd, HD_DISPCTRL);
@@ -341,8 +340,7 @@ static int charlcd_suspend(struct device *dev)
 
 static int charlcd_resume(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct charlcd *lcd = platform_get_drvdata(pdev);
+	struct charlcd *lcd = dev_get_drvdata(dev);
 
 	/* Turn the display back on */
 	charlcd_4bit_command(lcd, HD_DISPCTRL | HD_DISPCTRL_ON);
diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c
index 8673fc2b9eb8..81c22d20d9d9 100644
--- a/drivers/auxdisplay/charlcd.c
+++ b/drivers/auxdisplay/charlcd.c
@@ -99,10 +99,7 @@ static atomic_t charlcd_available = ATOMIC_INIT(1);
 /* sleeps that many milliseconds with a reschedule */
 static void long_sleep(int ms)
 {
-	if (in_interrupt())
-		mdelay(ms);
-	else
-		schedule_timeout_interruptible(msecs_to_jiffies(ms));
+	schedule_timeout_interruptible(msecs_to_jiffies(ms));
 }
 
 /* turn the backlight on or off */
diff --git a/drivers/base/core.c b/drivers/base/core.c
index df3e1a44707a..7fbd281cfd5d 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -178,10 +178,10 @@ void device_pm_move_to_tail(struct device *dev)
  * of the link.  If DL_FLAG_PM_RUNTIME is not set, DL_FLAG_RPM_ACTIVE will be
  * ignored.
  *
- * If the DL_FLAG_AUTOREMOVE is set, the link will be removed automatically
- * when the consumer device driver unbinds from it.  The combination of both
- * DL_FLAG_AUTOREMOVE and DL_FLAG_STATELESS set is invalid and will cause NULL
- * to be returned.
+ * If the DL_FLAG_AUTOREMOVE_CONSUMER is set, the link will be removed
+ * automatically when the consumer device driver unbinds from it.
+ * The combination of both DL_FLAG_AUTOREMOVE_CONSUMER and DL_FLAG_STATELESS
+ * set is invalid and will cause NULL to be returned.
  *
  * A side effect of the link creation is re-ordering of dpm_list and the
  * devices_kset list by moving the consumer device and all devices depending
@@ -198,7 +198,8 @@ struct device_link *device_link_add(struct device *consumer,
 	struct device_link *link;
 
 	if (!consumer || !supplier ||
-	    ((flags & DL_FLAG_STATELESS) && (flags & DL_FLAG_AUTOREMOVE)))
+	    ((flags & DL_FLAG_STATELESS) &&
+	     (flags & DL_FLAG_AUTOREMOVE_CONSUMER)))
 		return NULL;
 
 	device_links_write_lock();
@@ -372,6 +373,36 @@ void device_link_del(struct device_link *link)
 }
 EXPORT_SYMBOL_GPL(device_link_del);
 
+/**
+ * device_link_remove - remove a link between two devices.
+ * @consumer: Consumer end of the link.
+ * @supplier: Supplier end of the link.
+ *
+ * The caller must ensure proper synchronization of this function with runtime
+ * PM.
+ */
+void device_link_remove(void *consumer, struct device *supplier)
+{
+	struct device_link *link;
+
+	if (WARN_ON(consumer == supplier))
+		return;
+
+	device_links_write_lock();
+	device_pm_lock();
+
+	list_for_each_entry(link, &supplier->links.consumers, s_node) {
+		if (link->consumer == consumer) {
+			kref_put(&link->kref, __device_link_del);
+			break;
+		}
+	}
+
+	device_pm_unlock();
+	device_links_write_unlock();
+}
+EXPORT_SYMBOL_GPL(device_link_remove);
+
 static void device_links_missing_supplier(struct device *dev)
 {
 	struct device_link *link;
@@ -479,7 +510,7 @@ static void __device_links_no_driver(struct device *dev)
 		if (link->flags & DL_FLAG_STATELESS)
 			continue;
 
-		if (link->flags & DL_FLAG_AUTOREMOVE)
+		if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER)
 			kref_put(&link->kref, __device_link_del);
 		else if (link->status != DL_STATE_SUPPLIER_UNBIND)
 			WRITE_ONCE(link->status, DL_STATE_AVAILABLE);
@@ -515,8 +546,18 @@ void device_links_driver_cleanup(struct device *dev)
 		if (link->flags & DL_FLAG_STATELESS)
 			continue;
 
-		WARN_ON(link->flags & DL_FLAG_AUTOREMOVE);
+		WARN_ON(link->flags & DL_FLAG_AUTOREMOVE_CONSUMER);
 		WARN_ON(link->status != DL_STATE_SUPPLIER_UNBIND);
+
+		/*
+		 * autoremove the links between this @dev and its consumer
+		 * devices that are not active, i.e. where the link state
+		 * has moved to DL_STATE_SUPPLIER_UNBIND.
+		 */
+		if (link->status == DL_STATE_SUPPLIER_UNBIND &&
+		    link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER)
+			kref_put(&link->kref, __device_link_del);
+
 		WRITE_ONCE(link->status, DL_STATE_DORMANT);
 	}
 
@@ -866,10 +907,19 @@ static const void *device_namespace(struct kobject *kobj)
 	return ns;
 }
 
+static void device_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid)
+{
+	struct device *dev = kobj_to_dev(kobj);
+
+	if (dev->class && dev->class->get_ownership)
+		dev->class->get_ownership(dev, uid, gid);
+}
+
 static struct kobj_type device_ktype = {
 	.release	= device_release,
 	.sysfs_ops	= &dev_sysfs_ops,
 	.namespace	= device_namespace,
+	.get_ownership	= device_get_ownership,
 };
 
 
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 30cc9c877ebb..eb9443d5bae1 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -540,16 +540,24 @@ ssize_t __weak cpu_show_spec_store_bypass(struct device *dev,
 	return sprintf(buf, "Not affected\n");
 }
 
+ssize_t __weak cpu_show_l1tf(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "Not affected\n");
+}
+
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
 static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
 static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL);
+static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
 	&dev_attr_spectre_v1.attr,
 	&dev_attr_spectre_v2.attr,
 	&dev_attr_spec_store_bypass.attr,
+	&dev_attr_l1tf.attr,
 	NULL
 };
 
diff --git a/drivers/base/firmware_loader/fallback.c b/drivers/base/firmware_loader/fallback.c
index 7f732744f0d3..202324291542 100644
--- a/drivers/base/firmware_loader/fallback.c
+++ b/drivers/base/firmware_loader/fallback.c
@@ -651,6 +651,8 @@ static bool fw_force_sysfs_fallback(enum fw_opt opt_flags)
 
 static bool fw_run_sysfs_fallback(enum fw_opt opt_flags)
 {
+	int ret;
+
 	if (fw_fallback_config.ignore_sysfs_fallback) {
 		pr_info_once("Ignoring firmware sysfs fallback due to sysctl knob\n");
 		return false;
@@ -659,6 +661,11 @@ static bool fw_run_sysfs_fallback(enum fw_opt opt_flags)
 	if ((opt_flags & FW_OPT_NOFALLBACK))
 		return false;
 
+	/* Also permit LSMs and IMA to fail firmware sysfs fallback */
+	ret = security_kernel_load_data(LOADING_FIRMWARE);
+	if (ret < 0)
+		return ret;
+
 	return fw_force_sysfs_fallback(opt_flags);
 }
 
diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
index df41b4780b3b..b413951c6abc 100644
--- a/drivers/base/power/common.c
+++ b/drivers/base/power/common.c
@@ -153,6 +153,23 @@ struct device *dev_pm_domain_attach_by_id(struct device *dev,
 EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_id);
 
 /**
+ * dev_pm_domain_attach_by_name - Associate a device with one of its PM domains.
+ * @dev: The device used to lookup the PM domain.
+ * @name: The name of the PM domain.
+ *
+ * For a detailed function description, see dev_pm_domain_attach_by_id().
+ */
+struct device *dev_pm_domain_attach_by_name(struct device *dev,
+					    char *name)
+{
+	if (dev->pm_domain)
+		return ERR_PTR(-EEXIST);
+
+	return genpd_dev_pm_attach_by_name(dev, name);
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_name);
+
+/**
  * dev_pm_domain_detach - Detach a device from its PM domain.
  * @dev: Device to detach.
  * @power_off: Used to indicate whether we should power off the device.
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 9e8484189034..79bdca70a81a 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -2374,6 +2374,30 @@ struct device *genpd_dev_pm_attach_by_id(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(genpd_dev_pm_attach_by_id);
 
+/**
+ * genpd_dev_pm_attach_by_name - Associate a device with one of its PM domains.
+ * @dev: The device used to lookup the PM domain.
+ * @name: The name of the PM domain.
+ *
+ * Parse device's OF node to find a PM domain specifier using the
+ * power-domain-names DT property. For further description see
+ * genpd_dev_pm_attach_by_id().
+ */
+struct device *genpd_dev_pm_attach_by_name(struct device *dev, char *name)
+{
+	int index;
+
+	if (!dev->of_node)
+		return NULL;
+
+	index = of_property_match_string(dev->of_node, "power-domain-names",
+					 name);
+	if (index < 0)
+		return NULL;
+
+	return genpd_dev_pm_attach_by_id(dev, index);
+}
+
 static const struct of_device_id idle_state_match[] = {
 	{ .compatible = "domain-idle-state", },
 	{ }
diff --git a/drivers/base/regmap/Kconfig b/drivers/base/regmap/Kconfig
index aff34c0c2a3e..6ad5ef48b61e 100644
--- a/drivers/base/regmap/Kconfig
+++ b/drivers/base/regmap/Kconfig
@@ -45,3 +45,7 @@ config REGMAP_IRQ
 config REGMAP_SOUNDWIRE
 	tristate
 	depends on SOUNDWIRE_BUS
+
+config REGMAP_SCCB
+	tristate
+	depends on I2C
diff --git a/drivers/base/regmap/Makefile b/drivers/base/regmap/Makefile
index 5ed0023fabda..f5b4e8851d00 100644
--- a/drivers/base/regmap/Makefile
+++ b/drivers/base/regmap/Makefile
@@ -15,3 +15,4 @@ obj-$(CONFIG_REGMAP_MMIO) += regmap-mmio.o
 obj-$(CONFIG_REGMAP_IRQ) += regmap-irq.o
 obj-$(CONFIG_REGMAP_W1) += regmap-w1.o
 obj-$(CONFIG_REGMAP_SOUNDWIRE) += regmap-sdw.o
+obj-$(CONFIG_REGMAP_SCCB) += regmap-sccb.o
diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index 53785e0e297a..a6bf34d6394e 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -94,10 +94,12 @@ struct regmap {
 	bool (*readable_reg)(struct device *dev, unsigned int reg);
 	bool (*volatile_reg)(struct device *dev, unsigned int reg);
 	bool (*precious_reg)(struct device *dev, unsigned int reg);
+	bool (*readable_noinc_reg)(struct device *dev, unsigned int reg);
 	const struct regmap_access_table *wr_table;
 	const struct regmap_access_table *rd_table;
 	const struct regmap_access_table *volatile_table;
 	const struct regmap_access_table *precious_table;
+	const struct regmap_access_table *rd_noinc_table;
 
 	int (*reg_read)(void *context, unsigned int reg, unsigned int *val);
 	int (*reg_write)(void *context, unsigned int reg, unsigned int val);
@@ -181,6 +183,7 @@ bool regmap_writeable(struct regmap *map, unsigned int reg);
 bool regmap_readable(struct regmap *map, unsigned int reg);
 bool regmap_volatile(struct regmap *map, unsigned int reg);
 bool regmap_precious(struct regmap *map, unsigned int reg);
+bool regmap_readable_noinc(struct regmap *map, unsigned int reg);
 
 int _regmap_write(struct regmap *map, unsigned int reg,
 		  unsigned int val);
diff --git a/drivers/base/regmap/regmap-sccb.c b/drivers/base/regmap/regmap-sccb.c
new file mode 100644
index 000000000000..597042e2d009
--- /dev/null
+++ b/drivers/base/regmap/regmap-sccb.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0
+// Register map access API - SCCB support
+
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+
+#include "internal.h"
+
+/**
+ * sccb_is_available - Check if the adapter supports SCCB protocol
+ * @adap: I2C adapter
+ *
+ * Return true if the I2C adapter is capable of using SCCB helper functions,
+ * false otherwise.
+ */
+static bool sccb_is_available(struct i2c_adapter *adap)
+{
+	u32 needed_funcs = I2C_FUNC_SMBUS_BYTE | I2C_FUNC_SMBUS_WRITE_BYTE_DATA;
+
+	/*
+	 * If we ever want support for hardware doing SCCB natively, we will
+	 * introduce a sccb_xfer() callback to struct i2c_algorithm and check
+	 * for it here.
+	 */
+
+	return (i2c_get_functionality(adap) & needed_funcs) == needed_funcs;
+}
+
+/**
+ * regmap_sccb_read - Read data from SCCB slave device
+ * @context: Device that will be interacted with
+ * @reg: Register to be read from
+ * @val: Pointer to store read value
+ *
+ * This executes the 2-phase write transmission cycle that is followed by a
+ * 2-phase read transmission cycle, returning negative errno else zero on
+ * success.
+ */
+static int regmap_sccb_read(void *context, unsigned int reg, unsigned int *val)
+{
+	struct device *dev = context;
+	struct i2c_client *i2c = to_i2c_client(dev);
+	int ret;
+	union i2c_smbus_data data;
+
+	i2c_lock_bus(i2c->adapter, I2C_LOCK_SEGMENT);
+
+	ret = __i2c_smbus_xfer(i2c->adapter, i2c->addr, i2c->flags,
+			       I2C_SMBUS_WRITE, reg, I2C_SMBUS_BYTE, NULL);
+	if (ret < 0)
+		goto out;
+
+	ret = __i2c_smbus_xfer(i2c->adapter, i2c->addr, i2c->flags,
+			       I2C_SMBUS_READ, 0, I2C_SMBUS_BYTE, &data);
+	if (ret < 0)
+		goto out;
+
+	*val = data.byte;
+out:
+	i2c_unlock_bus(i2c->adapter, I2C_LOCK_SEGMENT);
+
+	return ret;
+}
+
+/**
+ * regmap_sccb_write - Write data to SCCB slave device
+ * @context: Device that will be interacted with
+ * @reg: Register to write to
+ * @val: Value to be written
+ *
+ * This executes the SCCB 3-phase write transmission cycle, returning negative
+ * errno else zero on success.
+ */
+static int regmap_sccb_write(void *context, unsigned int reg, unsigned int val)
+{
+	struct device *dev = context;
+	struct i2c_client *i2c = to_i2c_client(dev);
+
+	return i2c_smbus_write_byte_data(i2c, reg, val);
+}
+
+static struct regmap_bus regmap_sccb_bus = {
+	.reg_write = regmap_sccb_write,
+	.reg_read = regmap_sccb_read,
+};
+
+static const struct regmap_bus *regmap_get_sccb_bus(struct i2c_client *i2c,
+					const struct regmap_config *config)
+{
+	if (config->val_bits == 8 && config->reg_bits == 8 &&
+			sccb_is_available(i2c->adapter))
+		return &regmap_sccb_bus;
+
+	return ERR_PTR(-ENOTSUPP);
+}
+
+struct regmap *__regmap_init_sccb(struct i2c_client *i2c,
+				  const struct regmap_config *config,
+				  struct lock_class_key *lock_key,
+				  const char *lock_name)
+{
+	const struct regmap_bus *bus = regmap_get_sccb_bus(i2c, config);
+
+	if (IS_ERR(bus))
+		return ERR_CAST(bus);
+
+	return __regmap_init(&i2c->dev, bus, &i2c->dev, config,
+			     lock_key, lock_name);
+}
+EXPORT_SYMBOL_GPL(__regmap_init_sccb);
+
+struct regmap *__devm_regmap_init_sccb(struct i2c_client *i2c,
+				       const struct regmap_config *config,
+				       struct lock_class_key *lock_key,
+				       const char *lock_name)
+{
+	const struct regmap_bus *bus = regmap_get_sccb_bus(i2c, config);
+
+	if (IS_ERR(bus))
+		return ERR_CAST(bus);
+
+	return __devm_regmap_init(&i2c->dev, bus, &i2c->dev, config,
+				  lock_key, lock_name);
+}
+EXPORT_SYMBOL_GPL(__devm_regmap_init_sccb);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/base/regmap/regmap-slimbus.c b/drivers/base/regmap/regmap-slimbus.c
index 91d501eda8a9..0968059f1ef5 100644
--- a/drivers/base/regmap/regmap-slimbus.c
+++ b/drivers/base/regmap/regmap-slimbus.c
@@ -7,33 +7,24 @@
 
 #include "internal.h"
 
-static int regmap_slimbus_byte_reg_read(void *context, unsigned int reg,
-					unsigned int *val)
+static int regmap_slimbus_write(void *context, const void *data, size_t count)
 {
 	struct slim_device *sdev = context;
-	int v;
 
-	v = slim_readb(sdev, reg);
-
-	if (v < 0)
-		return v;
-
-	*val = v;
-
-	return 0;
+	return slim_write(sdev, *(u16 *)data, count - 2, (u8 *)data + 2);
 }
 
-static int regmap_slimbus_byte_reg_write(void *context, unsigned int reg,
-					 unsigned int val)
+static int regmap_slimbus_read(void *context, const void *reg, size_t reg_size,
+			       void *val, size_t val_size)
 {
 	struct slim_device *sdev = context;
 
-	return slim_writeb(sdev, reg, val);
+	return slim_read(sdev, *(u16 *)reg, val_size, val);
 }
 
 static struct regmap_bus regmap_slimbus_bus = {
-	.reg_write = regmap_slimbus_byte_reg_write,
-	.reg_read = regmap_slimbus_byte_reg_read,
+	.write = regmap_slimbus_write,
+	.read = regmap_slimbus_read,
 	.reg_format_endian_default = REGMAP_ENDIAN_LITTLE,
 	.val_format_endian_default = REGMAP_ENDIAN_LITTLE,
 };
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 3bc84885eb91..0360a90ad6b6 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -168,6 +168,17 @@ bool regmap_precious(struct regmap *map, unsigned int reg)
 	return false;
 }
 
+bool regmap_readable_noinc(struct regmap *map, unsigned int reg)
+{
+	if (map->readable_noinc_reg)
+		return map->readable_noinc_reg(map->dev, reg);
+
+	if (map->rd_noinc_table)
+		return regmap_check_range_table(map, reg, map->rd_noinc_table);
+
+	return true;
+}
+
 static bool regmap_volatile_range(struct regmap *map, unsigned int reg,
 	size_t num)
 {
@@ -766,10 +777,12 @@ struct regmap *__regmap_init(struct device *dev,
 	map->rd_table = config->rd_table;
 	map->volatile_table = config->volatile_table;
 	map->precious_table = config->precious_table;
+	map->rd_noinc_table = config->rd_noinc_table;
 	map->writeable_reg = config->writeable_reg;
 	map->readable_reg = config->readable_reg;
 	map->volatile_reg = config->volatile_reg;
 	map->precious_reg = config->precious_reg;
+	map->readable_noinc_reg = config->readable_noinc_reg;
 	map->cache_type = config->cache_type;
 
 	spin_lock_init(&map->async_lock);
@@ -1285,6 +1298,7 @@ int regmap_reinit_cache(struct regmap *map, const struct regmap_config *config)
 	map->readable_reg = config->readable_reg;
 	map->volatile_reg = config->volatile_reg;
 	map->precious_reg = config->precious_reg;
+	map->readable_noinc_reg = config->readable_noinc_reg;
 	map->cache_type = config->cache_type;
 
 	regmap_debugfs_init(map, config->name);
@@ -2564,7 +2578,70 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
 EXPORT_SYMBOL_GPL(regmap_raw_read);
 
 /**
- * regmap_field_read() - Read a value to a single register field
+ * regmap_noinc_read(): Read data from a register without incrementing the
+ *			register number
+ *
+ * @map: Register map to read from
+ * @reg: Register to read from
+ * @val: Pointer to data buffer
+ * @val_len: Length of output buffer in bytes.
+ *
+ * The regmap API usually assumes that bulk bus read operations will read a
+ * range of registers. Some devices have certain registers for which a read
+ * operation read will read from an internal FIFO.
+ *
+ * The target register must be volatile but registers after it can be
+ * completely unrelated cacheable registers.
+ *
+ * This will attempt multiple reads as required to read val_len bytes.
+ *
+ * A value of zero will be returned on success, a negative errno will be
+ * returned in error cases.
+ */
+int regmap_noinc_read(struct regmap *map, unsigned int reg,
+		      void *val, size_t val_len)
+{
+	size_t read_len;
+	int ret;
+
+	if (!map->bus)
+		return -EINVAL;
+	if (!map->bus->read)
+		return -ENOTSUPP;
+	if (val_len % map->format.val_bytes)
+		return -EINVAL;
+	if (!IS_ALIGNED(reg, map->reg_stride))
+		return -EINVAL;
+	if (val_len == 0)
+		return -EINVAL;
+
+	map->lock(map->lock_arg);
+
+	if (!regmap_volatile(map, reg) || !regmap_readable_noinc(map, reg)) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	while (val_len) {
+		if (map->max_raw_read && map->max_raw_read < val_len)
+			read_len = map->max_raw_read;
+		else
+			read_len = val_len;
+		ret = _regmap_raw_read(map, reg, val, read_len);
+		if (ret)
+			goto out_unlock;
+		val = ((u8 *)val) + read_len;
+		val_len -= read_len;
+	}
+
+out_unlock:
+	map->unlock(map->lock_arg);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(regmap_noinc_read);
+
+/**
+ * regmap_field_read(): Read a value to a single register field
  *
  * @field: Register field to read from
  * @val: Pointer to store read value
diff --git a/drivers/bcma/Kconfig b/drivers/bcma/Kconfig
index cb0f1aad20b7..b9558ff20830 100644
--- a/drivers/bcma/Kconfig
+++ b/drivers/bcma/Kconfig
@@ -30,6 +30,7 @@ config BCMA_HOST_PCI
 
 config BCMA_HOST_SOC
 	bool "Support for BCMA in a SoC"
+	depends on HAS_IOMEM
 	help
 	  Host interface for a Broadcom AIX bus directly mapped into
 	  the memory. This only works with the Broadcom SoCs from the
@@ -61,7 +62,7 @@ config BCMA_DRIVER_PCI_HOSTMODE
 
 config BCMA_DRIVER_MIPS
 	bool "BCMA Broadcom MIPS core driver"
-	depends on MIPS
+	depends on MIPS || COMPILE_TEST
 	help
 	  Driver for the Broadcom MIPS core attached to Broadcom specific
 	  Advanced Microcontroller Bus.
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index f6518067aa7d..f99e5c883368 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -21,6 +21,7 @@
 #define DAC960_DriverDate			"21 Aug 2007"
 
 
+#include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/miscdevice.h>
@@ -6426,7 +6427,7 @@ static bool DAC960_V2_ExecuteUserCommand(DAC960_Controller_T *Controller,
   return true;
 }
 
-static int dac960_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused dac960_proc_show(struct seq_file *m, void *v)
 {
   unsigned char *StatusMessage = "OK\n";
   int ControllerNumber;
@@ -6446,14 +6447,16 @@ static int dac960_proc_show(struct seq_file *m, void *v)
   return 0;
 }
 
-static int dac960_initial_status_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused dac960_initial_status_proc_show(struct seq_file *m,
+							  void *v)
 {
 	DAC960_Controller_T *Controller = (DAC960_Controller_T *)m->private;
 	seq_printf(m, "%.*s", Controller->InitialStatusLength, Controller->CombinedStatusBuffer);
 	return 0;
 }
 
-static int dac960_current_status_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused dac960_current_status_proc_show(struct seq_file *m,
+							  void *v)
 {
   DAC960_Controller_T *Controller = (DAC960_Controller_T *) m->private;
   unsigned char *StatusMessage =
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index ad9b687a236a..d4913516823f 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -74,12 +74,12 @@ config AMIGA_Z2RAM
 
 config CDROM
 	tristate
+	select BLK_SCSI_REQUEST
 
 config GDROM
 	tristate "SEGA Dreamcast GD-ROM drive"
 	depends on SH_DREAMCAST
 	select CDROM
-	select BLK_SCSI_REQUEST # only for the generic cdrom code
 	help
 	  A standard SEGA Dreamcast comes with a modified CD ROM drive called a
 	  "GD-ROM" by SEGA to signify it is capable of reading special disks
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index dc061158b403..8566b188368b 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -36,8 +36,11 @@ obj-$(CONFIG_BLK_DEV_RBD)     += rbd.o
 obj-$(CONFIG_BLK_DEV_PCIESSD_MTIP32XX)	+= mtip32xx/
 
 obj-$(CONFIG_BLK_DEV_RSXX) += rsxx/
-obj-$(CONFIG_BLK_DEV_NULL_BLK)	+= null_blk.o
 obj-$(CONFIG_ZRAM) += zram/
 
+obj-$(CONFIG_BLK_DEV_NULL_BLK)	+= null_blk.o
+null_blk-objs	:= null_blk_main.o
+null_blk-$(CONFIG_BLK_DEV_ZONED) += null_blk_zoned.o
+
 skd-y		:= skd_main.o
 swim_mod-y	:= swim.o swim_asm.o
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 096882e54095..136dc507d020 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -1137,6 +1137,7 @@ noskb:		if (buf)
 			break;
 		}
 		bvcpy(skb, f->buf->bio, f->iter, n);
+		/* fall through */
 	case ATA_CMD_PIO_WRITE:
 	case ATA_CMD_PIO_WRITE_EXT:
 		spin_lock_irq(&d->lock);
diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
index 697f735b07a4..41060e9cedf2 100644
--- a/drivers/block/aoe/aoedev.c
+++ b/drivers/block/aoe/aoedev.c
@@ -284,8 +284,8 @@ freedev(struct aoedev *d)
 	e = t + d->ntargets;
 	for (; t < e && *t; t++)
 		freetgt(d, *t);
-	if (d->bufpool)
-		mempool_destroy(d->bufpool);
+
+	mempool_destroy(d->bufpool);
 	skbpoolfree(d);
 	minor_free(d->sysminor);
 
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index bb976598ee43..df8103dd40ac 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -254,20 +254,20 @@ static void copy_from_brd(void *dst, struct brd_device *brd,
  * Process a single bvec of a bio.
  */
 static int brd_do_bvec(struct brd_device *brd, struct page *page,
-			unsigned int len, unsigned int off, bool is_write,
+			unsigned int len, unsigned int off, unsigned int op,
 			sector_t sector)
 {
 	void *mem;
 	int err = 0;
 
-	if (is_write) {
+	if (op_is_write(op)) {
 		err = copy_to_brd_setup(brd, sector, len);
 		if (err)
 			goto out;
 	}
 
 	mem = kmap_atomic(page);
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		copy_from_brd(mem + off, brd, sector, len);
 		flush_dcache_page(page);
 	} else {
@@ -296,7 +296,7 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 		int err;
 
 		err = brd_do_bvec(brd, bvec.bv_page, len, bvec.bv_offset,
-					op_is_write(bio_op(bio)), sector);
+				  bio_op(bio), sector);
 		if (err)
 			goto io_error;
 		sector += len >> SECTOR_SHIFT;
@@ -310,15 +310,15 @@ io_error:
 }
 
 static int brd_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, bool is_write)
+		       struct page *page, unsigned int op)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	int err;
 
 	if (PageTransHuge(page))
 		return -ENOTSUPP;
-	err = brd_do_bvec(brd, page, PAGE_SIZE, 0, is_write, sector);
-	page_endio(page, is_write, err);
+	err = brd_do_bvec(brd, page, PAGE_SIZE, 0, op, sector);
+	page_endio(page, op_is_write(op), err);
 	return err;
 }
 
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index bc4ed2ed40a2..e35a234b0a8f 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -55,12 +55,10 @@
 # define __protected_by(x)       __attribute__((require_context(x,1,999,"rdwr")))
 # define __protected_read_by(x)  __attribute__((require_context(x,1,999,"read")))
 # define __protected_write_by(x) __attribute__((require_context(x,1,999,"write")))
-# define __must_hold(x)       __attribute__((context(x,1,1), require_context(x,1,999,"call")))
 #else
 # define __protected_by(x)
 # define __protected_read_by(x)
 # define __protected_write_by(x)
-# define __must_hold(x)
 #endif
 
 /* shared module parameters, defined in drbd_main.c */
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index a80809bd3057..ef8212a4b73e 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2103,14 +2103,10 @@ static void drbd_destroy_mempools(void)
 	mempool_exit(&drbd_md_io_page_pool);
 	mempool_exit(&drbd_ee_mempool);
 	mempool_exit(&drbd_request_mempool);
-	if (drbd_ee_cache)
-		kmem_cache_destroy(drbd_ee_cache);
-	if (drbd_request_cache)
-		kmem_cache_destroy(drbd_request_cache);
-	if (drbd_bm_ext_cache)
-		kmem_cache_destroy(drbd_bm_ext_cache);
-	if (drbd_al_ext_cache)
-		kmem_cache_destroy(drbd_al_ext_cache);
+	kmem_cache_destroy(drbd_ee_cache);
+	kmem_cache_destroy(drbd_request_cache);
+	kmem_cache_destroy(drbd_bm_ext_cache);
+	kmem_cache_destroy(drbd_al_ext_cache);
 
 	drbd_ee_cache        = NULL;
 	drbd_request_cache   = NULL;
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index be9450f5ad1c..75f6b47169e6 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -2674,8 +2674,7 @@ bool drbd_rs_c_min_rate_throttle(struct drbd_device *device)
 	if (c_min_rate == 0)
 		return false;
 
-	curr_events = (int)part_stat_read(&disk->part0, sectors[0]) +
-		      (int)part_stat_read(&disk->part0, sectors[1]) -
+	curr_events = (int)part_stat_read_accum(&disk->part0, sectors) -
 			atomic_read(&device->rs_sect_ev);
 
 	if (atomic_read(&device->ap_actlog_cnt)
@@ -2790,6 +2789,7 @@ static int receive_DataRequest(struct drbd_connection *connection, struct packet
 		   then we would do something smarter here than reading
 		   the block... */
 		peer_req->flags |= EE_RS_THIN_REQ;
+		/* fall through */
 	case P_RS_DATA_REQUEST:
 		peer_req->w.cb = w_e_end_rsdata_req;
 		fault_type = DRBD_FAULT_RS_RD;
@@ -2968,6 +2968,7 @@ static int drbd_asb_recover_0p(struct drbd_peer_device *peer_device) __must_hold
 		/* Else fall through to one of the other strategies... */
 		drbd_warn(device, "Discard younger/older primary did not find a decision\n"
 		     "Using discard-least-changes instead\n");
+		/* fall through */
 	case ASB_DISCARD_ZERO_CHG:
 		if (ch_peer == 0 && ch_self == 0) {
 			rv = test_bit(RESOLVE_CONFLICTS, &peer_device->connection->flags)
@@ -2979,6 +2980,7 @@ static int drbd_asb_recover_0p(struct drbd_peer_device *peer_device) __must_hold
 		}
 		if (after_sb_0p == ASB_DISCARD_ZERO_CHG)
 			break;
+		/* else: fall through */
 	case ASB_DISCARD_LEAST_CHG:
 		if	(ch_self < ch_peer)
 			rv = -1;
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index d146fedc38bb..19cac36e9737 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -38,7 +38,7 @@ static void _drbd_start_io_acct(struct drbd_device *device, struct drbd_request
 {
 	struct request_queue *q = device->rq_queue;
 
-	generic_start_io_acct(q, bio_data_dir(req->master_bio),
+	generic_start_io_acct(q, bio_op(req->master_bio),
 				req->i.size >> 9, &device->vdisk->part0);
 }
 
@@ -47,7 +47,7 @@ static void _drbd_end_io_acct(struct drbd_device *device, struct drbd_request *r
 {
 	struct request_queue *q = device->rq_queue;
 
-	generic_end_io_acct(q, bio_data_dir(req->master_bio),
+	generic_end_io_acct(q, bio_op(req->master_bio),
 			    &device->vdisk->part0, req->start_jif);
 }
 
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 5e793dd7adfb..b8f77e83d456 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -1690,9 +1690,7 @@ void drbd_rs_controller_reset(struct drbd_device *device)
 	atomic_set(&device->rs_sect_in, 0);
 	atomic_set(&device->rs_sect_ev, 0);
 	device->rs_in_flight = 0;
-	device->rs_last_events =
-		(int)part_stat_read(&disk->part0, sectors[0]) +
-		(int)part_stat_read(&disk->part0, sectors[1]);
+	device->rs_last_events = (int)part_stat_read_accum(&disk->part0, sectors);
 
 	/* Updating the RCU protected object in place is necessary since
 	   this function gets called from atomic context.
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 8871b5044d9e..48f622728ce6 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -1461,7 +1461,6 @@ static void setup_rw_floppy(void)
 	int i;
 	int r;
 	int flags;
-	int dflags;
 	unsigned long ready_date;
 	void (*function)(void);
 
@@ -1485,8 +1484,6 @@ static void setup_rw_floppy(void)
 		if (fd_wait_for_completion(ready_date, function))
 			return;
 	}
-	dflags = DRS->flags;
-
 	if ((flags & FD_RAW_READ) || (flags & FD_RAW_WRITE))
 		setup_DMA();
 
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 4cb1d1be3cfb..ea9debf59b22 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -690,7 +690,6 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 			  unsigned int arg)
 {
 	struct file	*file, *old_file;
-	struct inode	*inode;
 	int		error;
 
 	error = -ENXIO;
@@ -711,7 +710,6 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	if (error)
 		goto out_putf;
 
-	inode = file->f_mapping->host;
 	old_file = lo->lo_backing_file;
 
 	error = -EINVAL;
@@ -1611,6 +1609,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
 	case LOOP_GET_STATUS64:
 	case LOOP_SET_STATUS64:
 		arg = (unsigned long) compat_ptr(arg);
+		/* fall through */
 	case LOOP_SET_FD:
 	case LOOP_CHANGE_FD:
 	case LOOP_SET_BLOCK_SIZE:
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index c73626decb46..db253cd5b32a 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -2575,8 +2575,7 @@ static int mtip_hw_debugfs_init(struct driver_data *dd)
 
 static void mtip_hw_debugfs_exit(struct driver_data *dd)
 {
-	if (dd->dfs_node)
-		debugfs_remove_recursive(dd->dfs_node);
+	debugfs_remove_recursive(dd->dfs_node);
 }
 
 /*
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 3fb95c8d9fd8..3863c00372bb 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1633,7 +1633,7 @@ static int find_free_cb(int id, void *ptr, void *data)
 }
 
 /* Netlink interface. */
-static struct nla_policy nbd_attr_policy[NBD_ATTR_MAX + 1] = {
+static const struct nla_policy nbd_attr_policy[NBD_ATTR_MAX + 1] = {
 	[NBD_ATTR_INDEX]		=	{ .type = NLA_U32 },
 	[NBD_ATTR_SIZE_BYTES]		=	{ .type = NLA_U64 },
 	[NBD_ATTR_BLOCK_SIZE_BYTES]	=	{ .type = NLA_U64 },
@@ -1645,14 +1645,14 @@ static struct nla_policy nbd_attr_policy[NBD_ATTR_MAX + 1] = {
 	[NBD_ATTR_DEVICE_LIST]		=	{ .type = NLA_NESTED},
 };
 
-static struct nla_policy nbd_sock_policy[NBD_SOCK_MAX + 1] = {
+static const struct nla_policy nbd_sock_policy[NBD_SOCK_MAX + 1] = {
 	[NBD_SOCK_FD]			=	{ .type = NLA_U32 },
 };
 
 /* We don't use this right now since we don't parse the incoming list, but we
  * still want it here so userspace knows what to expect.
  */
-static struct nla_policy __attribute__((unused))
+static const struct nla_policy __attribute__((unused))
 nbd_device_policy[NBD_DEVICE_ATTR_MAX + 1] = {
 	[NBD_DEVICE_INDEX]		=	{ .type = NLA_U32 },
 	[NBD_DEVICE_CONNECTED]		=	{ .type = NLA_U8 },
diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h
new file mode 100644
index 000000000000..d81781f22dba
--- /dev/null
+++ b/drivers/block/null_blk.h
@@ -0,0 +1,108 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BLK_NULL_BLK_H
+#define __BLK_NULL_BLK_H
+
+#include <linux/blkdev.h>
+#include <linux/slab.h>
+#include <linux/blk-mq.h>
+#include <linux/hrtimer.h>
+#include <linux/configfs.h>
+#include <linux/badblocks.h>
+#include <linux/fault-inject.h>
+
+struct nullb_cmd {
+	struct list_head list;
+	struct llist_node ll_list;
+	struct __call_single_data csd;
+	struct request *rq;
+	struct bio *bio;
+	unsigned int tag;
+	blk_status_t error;
+	struct nullb_queue *nq;
+	struct hrtimer timer;
+};
+
+struct nullb_queue {
+	unsigned long *tag_map;
+	wait_queue_head_t wait;
+	unsigned int queue_depth;
+	struct nullb_device *dev;
+	unsigned int requeue_selection;
+
+	struct nullb_cmd *cmds;
+};
+
+struct nullb_device {
+	struct nullb *nullb;
+	struct config_item item;
+	struct radix_tree_root data; /* data stored in the disk */
+	struct radix_tree_root cache; /* disk cache data */
+	unsigned long flags; /* device flags */
+	unsigned int curr_cache;
+	struct badblocks badblocks;
+
+	unsigned int nr_zones;
+	struct blk_zone *zones;
+	sector_t zone_size_sects;
+
+	unsigned long size; /* device size in MB */
+	unsigned long completion_nsec; /* time in ns to complete a request */
+	unsigned long cache_size; /* disk cache size in MB */
+	unsigned long zone_size; /* zone size in MB if device is zoned */
+	unsigned int submit_queues; /* number of submission queues */
+	unsigned int home_node; /* home node for the device */
+	unsigned int queue_mode; /* block interface */
+	unsigned int blocksize; /* block size */
+	unsigned int irqmode; /* IRQ completion handler */
+	unsigned int hw_queue_depth; /* queue depth */
+	unsigned int index; /* index of the disk, only valid with a disk */
+	unsigned int mbps; /* Bandwidth throttle cap (in MB/s) */
+	bool blocking; /* blocking blk-mq device */
+	bool use_per_node_hctx; /* use per-node allocation for hardware context */
+	bool power; /* power on/off the device */
+	bool memory_backed; /* if data is stored in memory */
+	bool discard; /* if support discard */
+	bool zoned; /* if device is zoned */
+};
+
+struct nullb {
+	struct nullb_device *dev;
+	struct list_head list;
+	unsigned int index;
+	struct request_queue *q;
+	struct gendisk *disk;
+	struct blk_mq_tag_set *tag_set;
+	struct blk_mq_tag_set __tag_set;
+	unsigned int queue_depth;
+	atomic_long_t cur_bytes;
+	struct hrtimer bw_timer;
+	unsigned long cache_flush_pos;
+	spinlock_t lock;
+
+	struct nullb_queue *queues;
+	unsigned int nr_queues;
+	char disk_name[DISK_NAME_LEN];
+};
+
+#ifdef CONFIG_BLK_DEV_ZONED
+int null_zone_init(struct nullb_device *dev);
+void null_zone_exit(struct nullb_device *dev);
+blk_status_t null_zone_report(struct nullb *nullb,
+					    struct nullb_cmd *cmd);
+void null_zone_write(struct nullb_cmd *cmd);
+void null_zone_reset(struct nullb_cmd *cmd);
+#else
+static inline int null_zone_init(struct nullb_device *dev)
+{
+	return -EINVAL;
+}
+static inline void null_zone_exit(struct nullb_device *dev) {}
+static inline blk_status_t null_zone_report(struct nullb *nullb,
+					    struct nullb_cmd *cmd)
+{
+	return BLK_STS_NOTSUPP;
+}
+static inline void null_zone_write(struct nullb_cmd *cmd) {}
+static inline void null_zone_reset(struct nullb_cmd *cmd) {}
+#endif /* CONFIG_BLK_DEV_ZONED */
+#endif /* __NULL_BLK_H */
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk_main.c
index 042c778e5a4e..6127e3ff7b4b 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk_main.c
@@ -7,14 +7,8 @@
 #include <linux/moduleparam.h>
 #include <linux/sched.h>
 #include <linux/fs.h>
-#include <linux/blkdev.h>
 #include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/blk-mq.h>
-#include <linux/hrtimer.h>
-#include <linux/configfs.h>
-#include <linux/badblocks.h>
-#include <linux/fault-inject.h>
+#include "null_blk.h"
 
 #define PAGE_SECTORS_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
 #define PAGE_SECTORS		(1 << PAGE_SECTORS_SHIFT)
@@ -35,28 +29,6 @@ static inline u64 mb_per_tick(int mbps)
 	return (1 << 20) / TICKS_PER_SEC * ((u64) mbps);
 }
 
-struct nullb_cmd {
-	struct list_head list;
-	struct llist_node ll_list;
-	struct __call_single_data csd;
-	struct request *rq;
-	struct bio *bio;
-	unsigned int tag;
-	blk_status_t error;
-	struct nullb_queue *nq;
-	struct hrtimer timer;
-};
-
-struct nullb_queue {
-	unsigned long *tag_map;
-	wait_queue_head_t wait;
-	unsigned int queue_depth;
-	struct nullb_device *dev;
-	unsigned int requeue_selection;
-
-	struct nullb_cmd *cmds;
-};
-
 /*
  * Status flags for nullb_device.
  *
@@ -92,52 +64,6 @@ struct nullb_page {
 #define NULLB_PAGE_LOCK (MAP_SZ - 1)
 #define NULLB_PAGE_FREE (MAP_SZ - 2)
 
-struct nullb_device {
-	struct nullb *nullb;
-	struct config_item item;
-	struct radix_tree_root data; /* data stored in the disk */
-	struct radix_tree_root cache; /* disk cache data */
-	unsigned long flags; /* device flags */
-	unsigned int curr_cache;
-	struct badblocks badblocks;
-
-	unsigned long size; /* device size in MB */
-	unsigned long completion_nsec; /* time in ns to complete a request */
-	unsigned long cache_size; /* disk cache size in MB */
-	unsigned int submit_queues; /* number of submission queues */
-	unsigned int home_node; /* home node for the device */
-	unsigned int queue_mode; /* block interface */
-	unsigned int blocksize; /* block size */
-	unsigned int irqmode; /* IRQ completion handler */
-	unsigned int hw_queue_depth; /* queue depth */
-	unsigned int index; /* index of the disk, only valid with a disk */
-	unsigned int mbps; /* Bandwidth throttle cap (in MB/s) */
-	bool blocking; /* blocking blk-mq device */
-	bool use_per_node_hctx; /* use per-node allocation for hardware context */
-	bool power; /* power on/off the device */
-	bool memory_backed; /* if data is stored in memory */
-	bool discard; /* if support discard */
-};
-
-struct nullb {
-	struct nullb_device *dev;
-	struct list_head list;
-	unsigned int index;
-	struct request_queue *q;
-	struct gendisk *disk;
-	struct blk_mq_tag_set *tag_set;
-	struct blk_mq_tag_set __tag_set;
-	unsigned int queue_depth;
-	atomic_long_t cur_bytes;
-	struct hrtimer bw_timer;
-	unsigned long cache_flush_pos;
-	spinlock_t lock;
-
-	struct nullb_queue *queues;
-	unsigned int nr_queues;
-	char disk_name[DISK_NAME_LEN];
-};
-
 static LIST_HEAD(nullb_list);
 static struct mutex lock;
 static int null_major;
@@ -254,6 +180,14 @@ static bool g_use_per_node_hctx;
 module_param_named(use_per_node_hctx, g_use_per_node_hctx, bool, 0444);
 MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false");
 
+static bool g_zoned;
+module_param_named(zoned, g_zoned, bool, S_IRUGO);
+MODULE_PARM_DESC(zoned, "Make device as a host-managed zoned block device. Default: false");
+
+static unsigned long g_zone_size = 256;
+module_param_named(zone_size, g_zone_size, ulong, S_IRUGO);
+MODULE_PARM_DESC(zone_size, "Zone size in MB when block device is zoned. Must be power-of-two: Default: 256");
+
 static struct nullb_device *null_alloc_dev(void);
 static void null_free_dev(struct nullb_device *dev);
 static void null_del_dev(struct nullb *nullb);
@@ -357,6 +291,8 @@ NULLB_DEVICE_ATTR(memory_backed, bool);
 NULLB_DEVICE_ATTR(discard, bool);
 NULLB_DEVICE_ATTR(mbps, uint);
 NULLB_DEVICE_ATTR(cache_size, ulong);
+NULLB_DEVICE_ATTR(zoned, bool);
+NULLB_DEVICE_ATTR(zone_size, ulong);
 
 static ssize_t nullb_device_power_show(struct config_item *item, char *page)
 {
@@ -390,6 +326,7 @@ static ssize_t nullb_device_power_store(struct config_item *item,
 		null_del_dev(dev->nullb);
 		mutex_unlock(&lock);
 		clear_bit(NULLB_DEV_FL_UP, &dev->flags);
+		clear_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags);
 	}
 
 	return count;
@@ -468,6 +405,8 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_mbps,
 	&nullb_device_attr_cache_size,
 	&nullb_device_attr_badblocks,
+	&nullb_device_attr_zoned,
+	&nullb_device_attr_zone_size,
 	NULL,
 };
 
@@ -520,7 +459,7 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item)
 
 static ssize_t memb_group_features_show(struct config_item *item, char *page)
 {
-	return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks\n");
+	return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -579,6 +518,8 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->hw_queue_depth = g_hw_queue_depth;
 	dev->blocking = g_blocking;
 	dev->use_per_node_hctx = g_use_per_node_hctx;
+	dev->zoned = g_zoned;
+	dev->zone_size = g_zone_size;
 	return dev;
 }
 
@@ -587,6 +528,7 @@ static void null_free_dev(struct nullb_device *dev)
 	if (!dev)
 		return;
 
+	null_zone_exit(dev);
 	badblocks_exit(&dev->badblocks);
 	kfree(dev);
 }
@@ -862,7 +804,9 @@ static struct nullb_page *null_lookup_page(struct nullb *nullb,
 }
 
 static struct nullb_page *null_insert_page(struct nullb *nullb,
-	sector_t sector, bool ignore_cache)
+					   sector_t sector, bool ignore_cache)
+	__releases(&nullb->lock)
+	__acquires(&nullb->lock)
 {
 	u64 idx;
 	struct nullb_page *t_page;
@@ -1219,6 +1163,11 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd)
 	struct nullb *nullb = dev->nullb;
 	int err = 0;
 
+	if (req_op(cmd->rq) == REQ_OP_ZONE_REPORT) {
+		cmd->error = null_zone_report(nullb, cmd);
+		goto out;
+	}
+
 	if (test_bit(NULLB_DEV_FL_THROTTLED, &dev->flags)) {
 		struct request *rq = cmd->rq;
 
@@ -1283,6 +1232,13 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd)
 		}
 	}
 	cmd->error = errno_to_blk_status(err);
+
+	if (!cmd->error && dev->zoned) {
+		if (req_op(cmd->rq) == REQ_OP_WRITE)
+			null_zone_write(cmd);
+		else if (req_op(cmd->rq) == REQ_OP_ZONE_RESET)
+			null_zone_reset(cmd);
+	}
 out:
 	/* Complete IO by inline, softirq or timer */
 	switch (dev->irqmode) {
@@ -1810,6 +1766,15 @@ static int null_add_dev(struct nullb_device *dev)
 		blk_queue_flush_queueable(nullb->q, true);
 	}
 
+	if (dev->zoned) {
+		rv = null_zone_init(dev);
+		if (rv)
+			goto out_cleanup_blk_queue;
+
+		blk_queue_chunk_sectors(nullb->q, dev->zone_size_sects);
+		nullb->q->limits.zoned = BLK_ZONED_HM;
+	}
+
 	nullb->q->queuedata = nullb;
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, nullb->q);
@@ -1828,13 +1793,16 @@ static int null_add_dev(struct nullb_device *dev)
 
 	rv = null_gendisk_register(nullb);
 	if (rv)
-		goto out_cleanup_blk_queue;
+		goto out_cleanup_zone;
 
 	mutex_lock(&lock);
 	list_add_tail(&nullb->list, &nullb_list);
 	mutex_unlock(&lock);
 
 	return 0;
+out_cleanup_zone:
+	if (dev->zoned)
+		null_zone_exit(dev);
 out_cleanup_blk_queue:
 	blk_cleanup_queue(nullb->q);
 out_cleanup_tags:
@@ -1861,6 +1829,11 @@ static int __init null_init(void)
 		g_bs = PAGE_SIZE;
 	}
 
+	if (!is_power_of_2(g_zone_size)) {
+		pr_err("null_blk: zone_size must be power-of-two\n");
+		return -EINVAL;
+	}
+
 	if (g_queue_mode == NULL_Q_MQ && g_use_per_node_hctx) {
 		if (g_submit_queues != nr_online_nodes) {
 			pr_warn("null_blk: submit_queues param is set to %u.\n",
diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c
new file mode 100644
index 000000000000..a979ca00d7be
--- /dev/null
+++ b/drivers/block/null_blk_zoned.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/vmalloc.h>
+#include "null_blk.h"
+
+/* zone_size in MBs to sectors. */
+#define ZONE_SIZE_SHIFT		11
+
+static inline unsigned int null_zone_no(struct nullb_device *dev, sector_t sect)
+{
+	return sect >> ilog2(dev->zone_size_sects);
+}
+
+int null_zone_init(struct nullb_device *dev)
+{
+	sector_t dev_size = (sector_t)dev->size * 1024 * 1024;
+	sector_t sector = 0;
+	unsigned int i;
+
+	if (!is_power_of_2(dev->zone_size)) {
+		pr_err("null_blk: zone_size must be power-of-two\n");
+		return -EINVAL;
+	}
+
+	dev->zone_size_sects = dev->zone_size << ZONE_SIZE_SHIFT;
+	dev->nr_zones = dev_size >>
+				(SECTOR_SHIFT + ilog2(dev->zone_size_sects));
+	dev->zones = kvmalloc_array(dev->nr_zones, sizeof(struct blk_zone),
+			GFP_KERNEL | __GFP_ZERO);
+	if (!dev->zones)
+		return -ENOMEM;
+
+	for (i = 0; i < dev->nr_zones; i++) {
+		struct blk_zone *zone = &dev->zones[i];
+
+		zone->start = zone->wp = sector;
+		zone->len = dev->zone_size_sects;
+		zone->type = BLK_ZONE_TYPE_SEQWRITE_REQ;
+		zone->cond = BLK_ZONE_COND_EMPTY;
+
+		sector += dev->zone_size_sects;
+	}
+
+	return 0;
+}
+
+void null_zone_exit(struct nullb_device *dev)
+{
+	kvfree(dev->zones);
+}
+
+static void null_zone_fill_rq(struct nullb_device *dev, struct request *rq,
+			      unsigned int zno, unsigned int nr_zones)
+{
+	struct blk_zone_report_hdr *hdr = NULL;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
+	void *addr;
+	unsigned int zones_to_cpy;
+
+	bio_for_each_segment(bvec, rq->bio, iter) {
+		addr = kmap_atomic(bvec.bv_page);
+
+		zones_to_cpy = bvec.bv_len / sizeof(struct blk_zone);
+
+		if (!hdr) {
+			hdr = (struct blk_zone_report_hdr *)addr;
+			hdr->nr_zones = nr_zones;
+			zones_to_cpy--;
+			addr += sizeof(struct blk_zone_report_hdr);
+		}
+
+		zones_to_cpy = min_t(unsigned int, zones_to_cpy, nr_zones);
+
+		memcpy(addr, &dev->zones[zno],
+				zones_to_cpy * sizeof(struct blk_zone));
+
+		kunmap_atomic(addr);
+
+		nr_zones -= zones_to_cpy;
+		zno += zones_to_cpy;
+
+		if (!nr_zones)
+			break;
+	}
+}
+
+blk_status_t null_zone_report(struct nullb *nullb,
+				     struct nullb_cmd *cmd)
+{
+	struct nullb_device *dev = nullb->dev;
+	struct request *rq = cmd->rq;
+	unsigned int zno = null_zone_no(dev, blk_rq_pos(rq));
+	unsigned int nr_zones = dev->nr_zones - zno;
+	unsigned int max_zones = (blk_rq_bytes(rq) /
+					sizeof(struct blk_zone)) - 1;
+
+	nr_zones = min_t(unsigned int, nr_zones, max_zones);
+
+	null_zone_fill_rq(nullb->dev, rq, zno, nr_zones);
+
+	return BLK_STS_OK;
+}
+
+void null_zone_write(struct nullb_cmd *cmd)
+{
+	struct nullb_device *dev = cmd->nq->dev;
+	struct request *rq = cmd->rq;
+	sector_t sector = blk_rq_pos(rq);
+	unsigned int rq_sectors = blk_rq_sectors(rq);
+	unsigned int zno = null_zone_no(dev, sector);
+	struct blk_zone *zone = &dev->zones[zno];
+
+	switch (zone->cond) {
+	case BLK_ZONE_COND_FULL:
+		/* Cannot write to a full zone */
+		cmd->error = BLK_STS_IOERR;
+		break;
+	case BLK_ZONE_COND_EMPTY:
+	case BLK_ZONE_COND_IMP_OPEN:
+		/* Writes must be at the write pointer position */
+		if (blk_rq_pos(rq) != zone->wp) {
+			cmd->error = BLK_STS_IOERR;
+			break;
+		}
+
+		if (zone->cond == BLK_ZONE_COND_EMPTY)
+			zone->cond = BLK_ZONE_COND_IMP_OPEN;
+
+		zone->wp += rq_sectors;
+		if (zone->wp == zone->start + zone->len)
+			zone->cond = BLK_ZONE_COND_FULL;
+		break;
+	default:
+		/* Invalid zone condition */
+		cmd->error = BLK_STS_IOERR;
+		break;
+	}
+}
+
+void null_zone_reset(struct nullb_cmd *cmd)
+{
+	struct nullb_device *dev = cmd->nq->dev;
+	struct request *rq = cmd->rq;
+	unsigned int zno = null_zone_no(dev, blk_rq_pos(rq));
+	struct blk_zone *zone = &dev->zones[zno];
+
+	zone->cond = BLK_ZONE_COND_EMPTY;
+	zone->wp = zone->start;
+}
diff --git a/drivers/block/paride/bpck.c b/drivers/block/paride/bpck.c
index 4f27e7392e38..f5f63ca2889d 100644
--- a/drivers/block/paride/bpck.c
+++ b/drivers/block/paride/bpck.c
@@ -347,7 +347,7 @@ static int bpck_test_proto( PIA *pi, char * scratch, int verbose )
 
 static void bpck_read_eeprom ( PIA *pi, char * buf )
 
-{       int i,j,k,n,p,v,f, om, od;
+{       int i, j, k, p, v, f, om, od;
 
 	bpck_force_spp(pi);
 
@@ -356,7 +356,6 @@ static void bpck_read_eeprom ( PIA *pi, char * buf )
 
 	bpck_connect(pi);
 	
-	n = 0;
 	WR(4,0);
 	for (i=0;i<64;i++) {
 	    WR(6,8);  
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 8961b190e256..7cf947586fe4 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -426,6 +426,7 @@ static void run_fsm(void)
 				pd_claimed = 1;
 				if (!pi_schedule_claimed(pi_current, run_fsm))
 					return;
+				/* fall through */
 			case 1:
 				pd_claimed = 2;
 				pi_current->proto->connect(pi_current);
@@ -445,6 +446,7 @@ static void run_fsm(void)
 				spin_unlock_irqrestore(&pd_lock, saved_flags);
 				if (stop)
 					return;
+				/* fall through */
 			case Hold:
 				schedule_fsm();
 				return;
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index b3f83cd96f33..e285413d4a75 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -67,7 +67,7 @@
 #include <scsi/scsi.h>
 #include <linux/debugfs.h>
 #include <linux/device.h>
-
+#include <linux/nospec.h>
 #include <linux/uaccess.h>
 
 #define DRIVER_NAME	"pktcdvd"
@@ -748,13 +748,13 @@ static const char *sense_key_string(__u8 index)
 static void pkt_dump_sense(struct pktcdvd_device *pd,
 			   struct packet_command *cgc)
 {
-	struct request_sense *sense = cgc->sense;
+	struct scsi_sense_hdr *sshdr = cgc->sshdr;
 
-	if (sense)
+	if (sshdr)
 		pkt_err(pd, "%*ph - sense %02x.%02x.%02x (%s)\n",
 			CDROM_PACKET_SIZE, cgc->cmd,
-			sense->sense_key, sense->asc, sense->ascq,
-			sense_key_string(sense->sense_key));
+			sshdr->sense_key, sshdr->asc, sshdr->ascq,
+			sense_key_string(sshdr->sense_key));
 	else
 		pkt_err(pd, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd);
 }
@@ -787,18 +787,19 @@ static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd,
 				unsigned write_speed, unsigned read_speed)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	int ret;
 
 	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.cmd[0] = GPCMD_SET_SPEED;
 	cgc.cmd[2] = (read_speed >> 8) & 0xff;
 	cgc.cmd[3] = read_speed & 0xff;
 	cgc.cmd[4] = (write_speed >> 8) & 0xff;
 	cgc.cmd[5] = write_speed & 0xff;
 
-	if ((ret = pkt_generic_packet(pd, &cgc)))
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
 		pkt_dump_sense(pd, &cgc);
 
 	return ret;
@@ -1562,7 +1563,8 @@ static int pkt_get_disc_info(struct pktcdvd_device *pd, disc_information *di)
 	cgc.cmd[8] = cgc.buflen = 2;
 	cgc.quiet = 1;
 
-	if ((ret = pkt_generic_packet(pd, &cgc)))
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
 		return ret;
 
 	/* not all drives have the same disc_info length, so requeue
@@ -1591,7 +1593,8 @@ static int pkt_get_track_info(struct pktcdvd_device *pd, __u16 track, __u8 type,
 	cgc.cmd[8] = 8;
 	cgc.quiet = 1;
 
-	if ((ret = pkt_generic_packet(pd, &cgc)))
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
 		return ret;
 
 	cgc.buflen = be16_to_cpu(ti->track_information_length) +
@@ -1612,17 +1615,20 @@ static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd,
 	__u32 last_track;
 	int ret = -1;
 
-	if ((ret = pkt_get_disc_info(pd, &di)))
+	ret = pkt_get_disc_info(pd, &di);
+	if (ret)
 		return ret;
 
 	last_track = (di.last_track_msb << 8) | di.last_track_lsb;
-	if ((ret = pkt_get_track_info(pd, last_track, 1, &ti)))
+	ret = pkt_get_track_info(pd, last_track, 1, &ti);
+	if (ret)
 		return ret;
 
 	/* if this track is blank, try the previous. */
 	if (ti.blank) {
 		last_track--;
-		if ((ret = pkt_get_track_info(pd, last_track, 1, &ti)))
+		ret = pkt_get_track_info(pd, last_track, 1, &ti);
+		if (ret)
 			return ret;
 	}
 
@@ -1645,7 +1651,7 @@ static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd,
 static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	write_param_page *wp;
 	char buffer[128];
 	int ret, size;
@@ -1656,8 +1662,9 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 
 	memset(buffer, 0, sizeof(buffer));
 	init_cdrom_command(&cgc, buffer, sizeof(*wp), CGC_DATA_READ);
-	cgc.sense = &sense;
-	if ((ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0))) {
+	cgc.sshdr = &sshdr;
+	ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
+	if (ret) {
 		pkt_dump_sense(pd, &cgc);
 		return ret;
 	}
@@ -1671,8 +1678,9 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 	 * now get it all
 	 */
 	init_cdrom_command(&cgc, buffer, size, CGC_DATA_READ);
-	cgc.sense = &sense;
-	if ((ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0))) {
+	cgc.sshdr = &sshdr;
+	ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
+	if (ret) {
 		pkt_dump_sense(pd, &cgc);
 		return ret;
 	}
@@ -1714,7 +1722,8 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 	wp->packet_size = cpu_to_be32(pd->settings.size >> 2);
 
 	cgc.buflen = cgc.cmd[8] = size;
-	if ((ret = pkt_mode_select(pd, &cgc))) {
+	ret = pkt_mode_select(pd, &cgc);
+	if (ret) {
 		pkt_dump_sense(pd, &cgc);
 		return ret;
 	}
@@ -1819,7 +1828,8 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd)
 	memset(&di, 0, sizeof(disc_information));
 	memset(&ti, 0, sizeof(track_information));
 
-	if ((ret = pkt_get_disc_info(pd, &di))) {
+	ret = pkt_get_disc_info(pd, &di);
+	if (ret) {
 		pkt_err(pd, "failed get_disc\n");
 		return ret;
 	}
@@ -1830,7 +1840,8 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd)
 	pd->type = di.erasable ? PACKET_CDRW : PACKET_CDR;
 
 	track = 1; /* (di.last_track_msb << 8) | di.last_track_lsb; */
-	if ((ret = pkt_get_track_info(pd, track, 1, &ti))) {
+	ret = pkt_get_track_info(pd, track, 1, &ti);
+	if (ret) {
 		pkt_err(pd, "failed get_track\n");
 		return ret;
 	}
@@ -1905,12 +1916,12 @@ static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd,
 						int set)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	unsigned char buf[64];
 	int ret;
 
 	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.buflen = pd->mode_offset + 12;
 
 	/*
@@ -1918,7 +1929,8 @@ static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd,
 	 */
 	cgc.quiet = 1;
 
-	if ((ret = pkt_mode_sense(pd, &cgc, GPMODE_WCACHING_PAGE, 0)))
+	ret = pkt_mode_sense(pd, &cgc, GPMODE_WCACHING_PAGE, 0);
+	if (ret)
 		return ret;
 
 	buf[pd->mode_offset + 10] |= (!!set << 2);
@@ -1950,14 +1962,14 @@ static noinline_for_stack int pkt_get_max_speed(struct pktcdvd_device *pd,
 						unsigned *write_speed)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	unsigned char buf[256+18];
 	unsigned char *cap_buf;
 	int ret, offset;
 
 	cap_buf = &buf[sizeof(struct mode_page_header) + pd->mode_offset];
 	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_UNKNOWN);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 
 	ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0);
 	if (ret) {
@@ -2011,13 +2023,13 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
 						unsigned *speed)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	unsigned char buf[64];
 	unsigned int size, st, sp;
 	int ret;
 
 	init_cdrom_command(&cgc, buf, 2, CGC_DATA_READ);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
 	cgc.cmd[1] = 2;
 	cgc.cmd[2] = 4; /* READ ATIP */
@@ -2032,7 +2044,7 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
 		size = sizeof(buf);
 
 	init_cdrom_command(&cgc, buf, size, CGC_DATA_READ);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
 	cgc.cmd[1] = 2;
 	cgc.cmd[2] = 4;
@@ -2083,17 +2095,18 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
 static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	int ret;
 
 	pkt_dbg(2, pd, "Performing OPC\n");
 
 	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.timeout = 60*HZ;
 	cgc.cmd[0] = GPCMD_SEND_OPC;
 	cgc.cmd[1] = 1;
-	if ((ret = pkt_generic_packet(pd, &cgc)))
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
 		pkt_dump_sense(pd, &cgc);
 	return ret;
 }
@@ -2103,19 +2116,22 @@ static int pkt_open_write(struct pktcdvd_device *pd)
 	int ret;
 	unsigned int write_speed, media_write_speed, read_speed;
 
-	if ((ret = pkt_probe_settings(pd))) {
+	ret = pkt_probe_settings(pd);
+	if (ret) {
 		pkt_dbg(2, pd, "failed probe\n");
 		return ret;
 	}
 
-	if ((ret = pkt_set_write_settings(pd))) {
+	ret = pkt_set_write_settings(pd);
+	if (ret) {
 		pkt_dbg(1, pd, "failed saving write settings\n");
 		return -EIO;
 	}
 
 	pkt_write_caching(pd, USE_WCACHING);
 
-	if ((ret = pkt_get_max_speed(pd, &write_speed)))
+	ret = pkt_get_max_speed(pd, &write_speed);
+	if (ret)
 		write_speed = 16 * 177;
 	switch (pd->mmc3_profile) {
 		case 0x13: /* DVD-RW */
@@ -2124,7 +2140,8 @@ static int pkt_open_write(struct pktcdvd_device *pd)
 			pkt_dbg(1, pd, "write speed %ukB/s\n", write_speed);
 			break;
 		default:
-			if ((ret = pkt_media_speed(pd, &media_write_speed)))
+			ret = pkt_media_speed(pd, &media_write_speed);
+			if (ret)
 				media_write_speed = 16;
 			write_speed = min(write_speed, media_write_speed * 177);
 			pkt_dbg(1, pd, "write speed %ux\n", write_speed / 176);
@@ -2132,14 +2149,16 @@ static int pkt_open_write(struct pktcdvd_device *pd)
 	}
 	read_speed = write_speed;
 
-	if ((ret = pkt_set_speed(pd, write_speed, read_speed))) {
+	ret = pkt_set_speed(pd, write_speed, read_speed);
+	if (ret) {
 		pkt_dbg(1, pd, "couldn't set write speed\n");
 		return -EIO;
 	}
 	pd->write_speed = write_speed;
 	pd->read_speed = read_speed;
 
-	if ((ret = pkt_perform_opc(pd))) {
+	ret = pkt_perform_opc(pd);
+	if (ret) {
 		pkt_dbg(1, pd, "Optimum Power Calibration failed\n");
 	}
 
@@ -2161,10 +2180,12 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 	 * so bdget() can't fail.
 	 */
 	bdget(pd->bdev->bd_dev);
-	if ((ret = blkdev_get(pd->bdev, FMODE_READ | FMODE_EXCL, pd)))
+	ret = blkdev_get(pd->bdev, FMODE_READ | FMODE_EXCL, pd);
+	if (ret)
 		goto out;
 
-	if ((ret = pkt_get_last_written(pd, &lba))) {
+	ret = pkt_get_last_written(pd, &lba);
+	if (ret) {
 		pkt_err(pd, "pkt_get_last_written failed\n");
 		goto out_putdev;
 	}
@@ -2175,7 +2196,8 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 
 	q = bdev_get_queue(pd->bdev);
 	if (write) {
-		if ((ret = pkt_open_write(pd)))
+		ret = pkt_open_write(pd);
+		if (ret)
 			goto out_putdev;
 		/*
 		 * Some CDRW drives can not handle writes larger than one packet,
@@ -2190,7 +2212,8 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 		clear_bit(PACKET_WRITABLE, &pd->flags);
 	}
 
-	if ((ret = pkt_set_segment_merging(pd, q)))
+	ret = pkt_set_segment_merging(pd, q);
+	if (ret)
 		goto out_putdev;
 
 	if (write) {
@@ -2231,6 +2254,8 @@ static struct pktcdvd_device *pkt_find_dev_from_minor(unsigned int dev_minor)
 {
 	if (dev_minor >= MAX_WRITERS)
 		return NULL;
+
+	dev_minor = array_index_nospec(dev_minor, MAX_WRITERS);
 	return pkt_devs[dev_minor];
 }
 
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index fa0729c1e776..d81c653b9bf6 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -61,7 +61,7 @@ static int atomic_inc_return_safe(atomic_t *v)
 {
 	unsigned int counter;
 
-	counter = (unsigned int)__atomic_add_unless(v, 1, 0);
+	counter = (unsigned int)atomic_fetch_add_unless(v, 1, 0);
 	if (counter <= (unsigned int)INT_MAX)
 		return (int)counter;
 
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index dddb3f2490b6..1a92f9e65937 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -112,7 +112,7 @@ static const struct block_device_operations rsxx_fops = {
 
 static void disk_stats_start(struct rsxx_cardinfo *card, struct bio *bio)
 {
-	generic_start_io_acct(card->queue, bio_data_dir(bio), bio_sectors(bio),
+	generic_start_io_acct(card->queue, bio_op(bio), bio_sectors(bio),
 			     &card->gendisk->part0);
 }
 
@@ -120,8 +120,8 @@ static void disk_stats_complete(struct rsxx_cardinfo *card,
 				struct bio *bio,
 				unsigned long start_time)
 {
-	generic_end_io_acct(card->queue, bio_data_dir(bio),
-				&card->gendisk->part0, start_time);
+	generic_end_io_acct(card->queue, bio_op(bio),
+			    &card->gendisk->part0, start_time);
 }
 
 static void bio_dma_done_cb(struct rsxx_cardinfo *card,
diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c
index bc7aea6d7b7c..87b9e7fbf062 100644
--- a/drivers/block/skd_main.c
+++ b/drivers/block/skd_main.c
@@ -657,8 +657,8 @@ static bool skd_preop_sg_list(struct skd_device *skdev,
 
 	if (unlikely(skdev->dbg_level > 1)) {
 		dev_dbg(&skdev->pdev->dev,
-			"skreq=%x sksg_list=%p sksg_dma=%llx\n",
-			skreq->id, skreq->sksg_list, skreq->sksg_dma_address);
+			"skreq=%x sksg_list=%p sksg_dma=%pad\n",
+			skreq->id, skreq->sksg_list, &skreq->sksg_dma_address);
 		for (i = 0; i < n_sg; i++) {
 			struct fit_sg_descriptor *sgd = &skreq->sksg_list[i];
 
@@ -1190,8 +1190,8 @@ static void skd_send_fitmsg(struct skd_device *skdev,
 {
 	u64 qcmd;
 
-	dev_dbg(&skdev->pdev->dev, "dma address 0x%llx, busy=%d\n",
-		skmsg->mb_dma_address, skd_in_flight(skdev));
+	dev_dbg(&skdev->pdev->dev, "dma address %pad, busy=%d\n",
+		&skmsg->mb_dma_address, skd_in_flight(skdev));
 	dev_dbg(&skdev->pdev->dev, "msg_buf %p\n", skmsg->msg_buf);
 
 	qcmd = skmsg->mb_dma_address;
@@ -1250,9 +1250,9 @@ static void skd_send_special_fitmsg(struct skd_device *skdev,
 		}
 
 		dev_dbg(&skdev->pdev->dev,
-			"skspcl=%p id=%04x sksg_list=%p sksg_dma=%llx\n",
+			"skspcl=%p id=%04x sksg_list=%p sksg_dma=%pad\n",
 			skspcl, skspcl->req.id, skspcl->req.sksg_list,
-			skspcl->req.sksg_dma_address);
+			&skspcl->req.sksg_dma_address);
 		for (i = 0; i < skspcl->req.n_sg; i++) {
 			struct fit_sg_descriptor *sgd =
 				&skspcl->req.sksg_list[i];
@@ -2685,8 +2685,8 @@ static int skd_cons_skmsg(struct skd_device *skdev)
 
 		WARN(((uintptr_t)skmsg->msg_buf | skmsg->mb_dma_address) &
 		     (FIT_QCMD_ALIGN - 1),
-		     "not aligned: msg_buf %p mb_dma_address %#llx\n",
-		     skmsg->msg_buf, skmsg->mb_dma_address);
+		     "not aligned: msg_buf %p mb_dma_address %pad\n",
+		     skmsg->msg_buf, &skmsg->mb_dma_address);
 		memset(skmsg->msg_buf, 0, SKD_N_FITMSG_BYTES);
 	}
 
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index b5cedccb5d7d..8986adab9bf5 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -251,14 +251,9 @@ static DEFINE_SPINLOCK(minor_lock);
 #define GRANTS_PER_INDIRECT_FRAME \
 	(XEN_PAGE_SIZE / sizeof(struct blkif_request_segment))
 
-#define PSEGS_PER_INDIRECT_FRAME	\
-	(GRANTS_INDIRECT_FRAME / GRANTS_PSEGS)
-
 #define INDIRECT_GREFS(_grants)		\
 	DIV_ROUND_UP(_grants, GRANTS_PER_INDIRECT_FRAME)
 
-#define GREFS(_psegs)	((_psegs) * GRANTS_PER_PSEG)
-
 static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo);
 static void blkfront_gather_backend_features(struct blkfront_info *info);
 static int negotiate_mq(struct blkfront_info *info);
@@ -1441,7 +1436,7 @@ static bool blkif_completion(unsigned long *id,
 
 		/* Wait the second response if not yet here. */
 		if (s2->status == REQ_WAITING)
-			return 0;
+			return false;
 
 		bret->status = blkif_get_final_status(s->status,
 						      s2->status);
@@ -1542,7 +1537,7 @@ static bool blkif_completion(unsigned long *id,
 		}
 	}
 
-	return 1;
+	return true;
 }
 
 static irqreturn_t blkif_interrupt(int irq, void *dev_id)
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index a390c6d4f72d..c7acf74253a1 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1287,17 +1287,16 @@ static void zram_bio_discard(struct zram *zram, u32 index,
  * Returns 1 if IO request was successfully submitted.
  */
 static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
-			int offset, bool is_write, struct bio *bio)
+			int offset, unsigned int op, struct bio *bio)
 {
 	unsigned long start_time = jiffies;
-	int rw_acct = is_write ? REQ_OP_WRITE : REQ_OP_READ;
 	struct request_queue *q = zram->disk->queue;
 	int ret;
 
-	generic_start_io_acct(q, rw_acct, bvec->bv_len >> SECTOR_SHIFT,
+	generic_start_io_acct(q, op, bvec->bv_len >> SECTOR_SHIFT,
 			&zram->disk->part0);
 
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		atomic64_inc(&zram->stats.num_reads);
 		ret = zram_bvec_read(zram, bvec, index, offset, bio);
 		flush_dcache_page(bvec->bv_page);
@@ -1306,14 +1305,14 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
 		ret = zram_bvec_write(zram, bvec, index, offset, bio);
 	}
 
-	generic_end_io_acct(q, rw_acct, &zram->disk->part0, start_time);
+	generic_end_io_acct(q, op, &zram->disk->part0, start_time);
 
 	zram_slot_lock(zram, index);
 	zram_accessed(zram, index);
 	zram_slot_unlock(zram, index);
 
 	if (unlikely(ret < 0)) {
-		if (!is_write)
+		if (!op_is_write(op))
 			atomic64_inc(&zram->stats.failed_reads);
 		else
 			atomic64_inc(&zram->stats.failed_writes);
@@ -1351,7 +1350,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 			bv.bv_len = min_t(unsigned int, PAGE_SIZE - offset,
 							unwritten);
 			if (zram_bvec_rw(zram, &bv, index, offset,
-					op_is_write(bio_op(bio)), bio) < 0)
+					 bio_op(bio), bio) < 0)
 				goto out;
 
 			bv.bv_offset += bv.bv_len;
@@ -1403,7 +1402,7 @@ static void zram_slot_free_notify(struct block_device *bdev,
 }
 
 static int zram_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, bool is_write)
+		       struct page *page, unsigned int op)
 {
 	int offset, ret;
 	u32 index;
@@ -1427,7 +1426,7 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector,
 	bv.bv_len = PAGE_SIZE;
 	bv.bv_offset = 0;
 
-	ret = zram_bvec_rw(zram, &bv, index, offset, is_write, NULL);
+	ret = zram_bvec_rw(zram, &bv, index, offset, op, NULL);
 out:
 	/*
 	 * If I/O fails, just return error(ie, non-zero) without
@@ -1442,7 +1441,7 @@ out:
 
 	switch (ret) {
 	case 0:
-		page_endio(page, is_write, 0);
+		page_endio(page, op_is_write(op), 0);
 		break;
 	case 1:
 		ret = 0;
diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig
index f3c643a0473c..2df11cc08a46 100644
--- a/drivers/bluetooth/Kconfig
+++ b/drivers/bluetooth/Kconfig
@@ -159,6 +159,7 @@ config BT_HCIUART_LL
 config BT_HCIUART_3WIRE
 	bool "Three-wire UART (H5) protocol support"
 	depends on BT_HCIUART
+	depends on BT_HCIUART_SERDEV
 	help
 	  The HCI Three-wire UART Transport Layer makes it possible to
 	  user the Bluetooth HCI over a serial port interface. The HCI
@@ -194,6 +195,19 @@ config BT_HCIUART_BCM
 
 	  Say Y here to compile support for Broadcom protocol.
 
+config BT_HCIUART_RTL
+	bool "Realtek protocol support"
+	depends on BT_HCIUART
+	depends on BT_HCIUART_SERDEV
+	depends on GPIOLIB
+	select BT_HCIUART_3WIRE
+	select BT_RTL
+	help
+	  The Realtek protocol support enables Bluetooth HCI over 3-Wire
+	  serial port internface for Realtek Bluetooth controllers.
+
+	  Say Y here to compile support for Realtek protocol.
+
 config BT_HCIUART_QCA
 	bool "Qualcomm Atheros protocol support"
 	depends on BT_HCIUART
@@ -364,6 +378,17 @@ config BT_WILINK
 	  Say Y here to compile support for Texas Instrument's WiLink7 driver
 	  into the kernel or say M to compile it as module (btwilink).
 
+config BT_MTKUART
+	tristate "MediaTek HCI UART driver"
+	depends on SERIAL_DEV_BUS
+	help
+	  MediaTek Bluetooth HCI UART driver.
+	  This driver is required if you want to use MediaTek Bluetooth
+	  with serial interface.
+
+	  Say Y here to compile support for MediaTek Bluetooth UART devices
+	  into the kernel or say M to compile it as module (btmtkuart).
+
 config BT_QCOMSMD
 	tristate "Qualcomm SMD based HCI support"
 	depends on RPMSG || (COMPILE_TEST && RPMSG=n)
diff --git a/drivers/bluetooth/Makefile b/drivers/bluetooth/Makefile
index ec16c55eb6e9..b7e393cfc1e3 100644
--- a/drivers/bluetooth/Makefile
+++ b/drivers/bluetooth/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_BT_ATH3K)		+= ath3k.o
 obj-$(CONFIG_BT_MRVL)		+= btmrvl.o
 obj-$(CONFIG_BT_MRVL_SDIO)	+= btmrvl_sdio.o
 obj-$(CONFIG_BT_WILINK)		+= btwilink.o
+obj-$(CONFIG_BT_MTKUART)	+= btmtkuart.o
 obj-$(CONFIG_BT_QCOMSMD)	+= btqcomsmd.o
 obj-$(CONFIG_BT_BCM)		+= btbcm.o
 obj-$(CONFIG_BT_RTL)		+= btrtl.o
diff --git a/drivers/bluetooth/bfusb.c b/drivers/bluetooth/bfusb.c
index ab090a313a5f..0588639b899a 100644
--- a/drivers/bluetooth/bfusb.c
+++ b/drivers/bluetooth/bfusb.c
@@ -490,7 +490,7 @@ static int bfusb_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 	count = skb->len;
 
 	/* Max HCI frame size seems to be 1511 + 1 */
-	nskb = bt_skb_alloc(count + 32, GFP_ATOMIC);
+	nskb = bt_skb_alloc(count + 32, GFP_KERNEL);
 	if (!nskb) {
 		BT_ERR("Can't allocate memory for new packet");
 		return -ENOMEM;
diff --git a/drivers/bluetooth/bluecard_cs.c b/drivers/bluetooth/bluecard_cs.c
index 82437a69f99c..cc6e56223656 100644
--- a/drivers/bluetooth/bluecard_cs.c
+++ b/drivers/bluetooth/bluecard_cs.c
@@ -565,7 +565,7 @@ static int bluecard_hci_set_baud_rate(struct hci_dev *hdev, int baud)
 	/* Ericsson baud rate command */
 	unsigned char cmd[] = { HCI_COMMAND_PKT, 0x09, 0xfc, 0x01, 0x03 };
 
-	skb = bt_skb_alloc(HCI_MAX_FRAME_SIZE, GFP_ATOMIC);
+	skb = bt_skb_alloc(HCI_MAX_FRAME_SIZE, GFP_KERNEL);
 	if (!skb) {
 		BT_ERR("Can't allocate mem for new packet");
 		return -1;
diff --git a/drivers/bluetooth/bpa10x.c b/drivers/bluetooth/bpa10x.c
index c6f7cc57db14..d1c2adf08576 100644
--- a/drivers/bluetooth/bpa10x.c
+++ b/drivers/bluetooth/bpa10x.c
@@ -289,7 +289,7 @@ static int bpa10x_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 
 	skb->dev = (void *) hdev;
 
-	urb = usb_alloc_urb(0, GFP_ATOMIC);
+	urb = usb_alloc_urb(0, GFP_KERNEL);
 	if (!urb)
 		return -ENOMEM;
 
@@ -298,7 +298,7 @@ static int bpa10x_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 
 	switch (hci_skb_pkt_type(skb)) {
 	case HCI_COMMAND_PKT:
-		dr = kmalloc(sizeof(*dr), GFP_ATOMIC);
+		dr = kmalloc(sizeof(*dr), GFP_KERNEL);
 		if (!dr) {
 			usb_free_urb(urb);
 			return -ENOMEM;
@@ -343,7 +343,7 @@ static int bpa10x_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 
 	usb_anchor_urb(urb, &data->tx_anchor);
 
-	err = usb_submit_urb(urb, GFP_ATOMIC);
+	err = usb_submit_urb(urb, GFP_KERNEL);
 	if (err < 0) {
 		bt_dev_err(hdev, "urb %p submission failed", urb);
 		kfree(urb->setup_packet);
diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c
index 888bac49a87b..fb3d03928460 100644
--- a/drivers/bluetooth/btmrvl_sdio.c
+++ b/drivers/bluetooth/btmrvl_sdio.c
@@ -718,7 +718,7 @@ static int btmrvl_sdio_card_to_host(struct btmrvl_private *priv)
 	}
 
 	/* Allocate buffer */
-	skb = bt_skb_alloc(num_blocks * blksz + BTSDIO_DMA_ALIGN, GFP_ATOMIC);
+	skb = bt_skb_alloc(num_blocks * blksz + BTSDIO_DMA_ALIGN, GFP_KERNEL);
 	if (!skb) {
 		BT_ERR("No free skb");
 		ret = -ENOMEM;
diff --git a/drivers/bluetooth/btmtkuart.c b/drivers/bluetooth/btmtkuart.c
new file mode 100644
index 000000000000..ed2a5c7cb77f
--- /dev/null
+++ b/drivers/bluetooth/btmtkuart.c
@@ -0,0 +1,629 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 MediaTek Inc.
+
+/*
+ * Bluetooth support for MediaTek serial devices
+ *
+ * Author: Sean Wang <sean.wang@mediatek.com>
+ *
+ */
+
+#include <asm/unaligned.h>
+#include <linux/atomic.h>
+#include <linux/clk.h>
+#include <linux/firmware.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/pm_runtime.h>
+#include <linux/serdev.h>
+#include <linux/skbuff.h>
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+
+#include "h4_recv.h"
+
+#define VERSION "0.1"
+
+#define FIRMWARE_MT7622		"mediatek/mt7622pr2h.bin"
+
+#define MTK_STP_TLR_SIZE	2
+
+#define BTMTKUART_TX_STATE_ACTIVE	1
+#define BTMTKUART_TX_STATE_WAKEUP	2
+#define BTMTKUART_TX_WAIT_VND_EVT	3
+
+enum {
+	MTK_WMT_PATCH_DWNLD = 0x1,
+	MTK_WMT_FUNC_CTRL = 0x6,
+	MTK_WMT_RST = 0x7
+};
+
+struct mtk_stp_hdr {
+	u8	prefix;
+	__be16	dlen;
+	u8	cs;
+} __packed;
+
+struct mtk_wmt_hdr {
+	u8	dir;
+	u8	op;
+	__le16	dlen;
+	u8	flag;
+} __packed;
+
+struct mtk_hci_wmt_cmd {
+	struct mtk_wmt_hdr hdr;
+	u8 data[256];
+} __packed;
+
+struct btmtkuart_dev {
+	struct hci_dev *hdev;
+	struct serdev_device *serdev;
+	struct clk *clk;
+
+	struct work_struct tx_work;
+	unsigned long tx_state;
+	struct sk_buff_head txq;
+
+	struct sk_buff *rx_skb;
+
+	u8	stp_pad[6];
+	u8	stp_cursor;
+	u16	stp_dlen;
+};
+
+static int mtk_hci_wmt_sync(struct hci_dev *hdev, u8 op, u8 flag, u16 plen,
+			    const void *param)
+{
+	struct btmtkuart_dev *bdev = hci_get_drvdata(hdev);
+	struct mtk_hci_wmt_cmd wc;
+	struct mtk_wmt_hdr *hdr;
+	u32 hlen;
+	int err;
+
+	hlen = sizeof(*hdr) + plen;
+	if (hlen > 255)
+		return -EINVAL;
+
+	hdr = (struct mtk_wmt_hdr *)&wc;
+	hdr->dir = 1;
+	hdr->op = op;
+	hdr->dlen = cpu_to_le16(plen + 1);
+	hdr->flag = flag;
+	memcpy(wc.data, param, plen);
+
+	set_bit(BTMTKUART_TX_WAIT_VND_EVT, &bdev->tx_state);
+
+	err = __hci_cmd_send(hdev, 0xfc6f, hlen, &wc);
+	if (err < 0) {
+		clear_bit(BTMTKUART_TX_WAIT_VND_EVT, &bdev->tx_state);
+		return err;
+	}
+
+	/* The vendor specific WMT commands are all answered by a vendor
+	 * specific event and will not have the Command Status or Command
+	 * Complete as with usual HCI command flow control.
+	 *
+	 * After sending the command, wait for BTMTKUART_TX_WAIT_VND_EVT
+	 * state to be cleared. The driver speicfic event receive routine
+	 * will clear that state and with that indicate completion of the
+	 * WMT command.
+	 */
+	err = wait_on_bit_timeout(&bdev->tx_state, BTMTKUART_TX_WAIT_VND_EVT,
+				  TASK_INTERRUPTIBLE, HCI_INIT_TIMEOUT);
+	if (err == -EINTR) {
+		bt_dev_err(hdev, "Execution of wmt command interrupted");
+		return err;
+	}
+
+	if (err) {
+		bt_dev_err(hdev, "Execution of wmt command timed out");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+static int mtk_setup_fw(struct hci_dev *hdev)
+{
+	const struct firmware *fw;
+	const u8 *fw_ptr;
+	size_t fw_size;
+	int err, dlen;
+	u8 flag;
+
+	err = request_firmware(&fw, FIRMWARE_MT7622, &hdev->dev);
+	if (err < 0) {
+		bt_dev_err(hdev, "Failed to load firmware file (%d)", err);
+		return err;
+	}
+
+	fw_ptr = fw->data;
+	fw_size = fw->size;
+
+	/* The size of patch header is 30 bytes, should be skip */
+	if (fw_size < 30)
+		return -EINVAL;
+
+	fw_size -= 30;
+	fw_ptr += 30;
+	flag = 1;
+
+	while (fw_size > 0) {
+		dlen = min_t(int, 250, fw_size);
+
+		/* Tell device the position in sequence */
+		if (fw_size - dlen <= 0)
+			flag = 3;
+		else if (fw_size < fw->size - 30)
+			flag = 2;
+
+		err = mtk_hci_wmt_sync(hdev, MTK_WMT_PATCH_DWNLD, flag, dlen,
+				       fw_ptr);
+		if (err < 0) {
+			bt_dev_err(hdev, "Failed to send wmt patch dwnld (%d)",
+				   err);
+			break;
+		}
+
+		fw_size -= dlen;
+		fw_ptr += dlen;
+	}
+
+	release_firmware(fw);
+
+	return err;
+}
+
+static int btmtkuart_recv_event(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct btmtkuart_dev *bdev = hci_get_drvdata(hdev);
+	struct hci_event_hdr *hdr = (void *)skb->data;
+	int err;
+
+	/* Fix up the vendor event id with 0xff for vendor specific instead
+	 * of 0xe4 so that event send via monitoring socket can be parsed
+	 * properly.
+	 */
+	if (hdr->evt == 0xe4)
+		hdr->evt = HCI_EV_VENDOR;
+
+	err = hci_recv_frame(hdev, skb);
+
+	if (hdr->evt == HCI_EV_VENDOR) {
+		if (test_and_clear_bit(BTMTKUART_TX_WAIT_VND_EVT,
+				       &bdev->tx_state)) {
+			/* Barrier to sync with other CPUs */
+			smp_mb__after_atomic();
+			wake_up_bit(&bdev->tx_state, BTMTKUART_TX_WAIT_VND_EVT);
+		}
+	}
+
+	return err;
+}
+
+static const struct h4_recv_pkt mtk_recv_pkts[] = {
+	{ H4_RECV_ACL,      .recv = hci_recv_frame },
+	{ H4_RECV_SCO,      .recv = hci_recv_frame },
+	{ H4_RECV_EVENT,    .recv = btmtkuart_recv_event },
+};
+
+static void btmtkuart_tx_work(struct work_struct *work)
+{
+	struct btmtkuart_dev *bdev = container_of(work, struct btmtkuart_dev,
+						   tx_work);
+	struct serdev_device *serdev = bdev->serdev;
+	struct hci_dev *hdev = bdev->hdev;
+
+	while (1) {
+		clear_bit(BTMTKUART_TX_STATE_WAKEUP, &bdev->tx_state);
+
+		while (1) {
+			struct sk_buff *skb = skb_dequeue(&bdev->txq);
+			int len;
+
+			if (!skb)
+				break;
+
+			len = serdev_device_write_buf(serdev, skb->data,
+						      skb->len);
+			hdev->stat.byte_tx += len;
+
+			skb_pull(skb, len);
+			if (skb->len > 0) {
+				skb_queue_head(&bdev->txq, skb);
+				break;
+			}
+
+			switch (hci_skb_pkt_type(skb)) {
+			case HCI_COMMAND_PKT:
+				hdev->stat.cmd_tx++;
+				break;
+			case HCI_ACLDATA_PKT:
+				hdev->stat.acl_tx++;
+				break;
+			case HCI_SCODATA_PKT:
+				hdev->stat.sco_tx++;
+				break;
+			}
+
+			kfree_skb(skb);
+		}
+
+		if (!test_bit(BTMTKUART_TX_STATE_WAKEUP, &bdev->tx_state))
+			break;
+	}
+
+	clear_bit(BTMTKUART_TX_STATE_ACTIVE, &bdev->tx_state);
+}
+
+static void btmtkuart_tx_wakeup(struct btmtkuart_dev *bdev)
+{
+	if (test_and_set_bit(BTMTKUART_TX_STATE_ACTIVE, &bdev->tx_state))
+		set_bit(BTMTKUART_TX_STATE_WAKEUP, &bdev->tx_state);
+
+	schedule_work(&bdev->tx_work);
+}
+
+static const unsigned char *
+mtk_stp_split(struct btmtkuart_dev *bdev, const unsigned char *data, int count,
+	      int *sz_h4)
+{
+	struct mtk_stp_hdr *shdr;
+
+	/* The cursor is reset when all the data of STP is consumed out */
+	if (!bdev->stp_dlen && bdev->stp_cursor >= 6)
+		bdev->stp_cursor = 0;
+
+	/* Filling pad until all STP info is obtained */
+	while (bdev->stp_cursor < 6 && count > 0) {
+		bdev->stp_pad[bdev->stp_cursor] = *data;
+		bdev->stp_cursor++;
+		data++;
+		count--;
+	}
+
+	/* Retrieve STP info and have a sanity check */
+	if (!bdev->stp_dlen && bdev->stp_cursor >= 6) {
+		shdr = (struct mtk_stp_hdr *)&bdev->stp_pad[2];
+		bdev->stp_dlen = be16_to_cpu(shdr->dlen) & 0x0fff;
+
+		/* Resync STP when unexpected data is being read */
+		if (shdr->prefix != 0x80 || bdev->stp_dlen > 2048) {
+			bt_dev_err(bdev->hdev, "stp format unexpect (%d, %d)",
+				   shdr->prefix, bdev->stp_dlen);
+			bdev->stp_cursor = 2;
+			bdev->stp_dlen = 0;
+		}
+	}
+
+	/* Directly quit when there's no data found for H4 can process */
+	if (count <= 0)
+		return NULL;
+
+	/* Tranlate to how much the size of data H4 can handle so far */
+	*sz_h4 = min_t(int, count, bdev->stp_dlen);
+
+	/* Update the remaining size of STP packet */
+	bdev->stp_dlen -= *sz_h4;
+
+	/* Data points to STP payload which can be handled by H4 */
+	return data;
+}
+
+static int btmtkuart_recv(struct hci_dev *hdev, const u8 *data, size_t count)
+{
+	struct btmtkuart_dev *bdev = hci_get_drvdata(hdev);
+	const unsigned char *p_left = data, *p_h4;
+	int sz_left = count, sz_h4, adv;
+	int err;
+
+	while (sz_left > 0) {
+		/*  The serial data received from MT7622 BT controller is
+		 *  at all time padded around with the STP header and tailer.
+		 *
+		 *  A full STP packet is looking like
+		 *   -----------------------------------
+		 *  | STP header  |  H:4   | STP tailer |
+		 *   -----------------------------------
+		 *  but it doesn't guarantee to contain a full H:4 packet which
+		 *  means that it's possible for multiple STP packets forms a
+		 *  full H:4 packet that means extra STP header + length doesn't
+		 *  indicate a full H:4 frame, things can fragment. Whose length
+		 *  recorded in STP header just shows up the most length the
+		 *  H:4 engine can handle currently.
+		 */
+
+		p_h4 = mtk_stp_split(bdev, p_left, sz_left, &sz_h4);
+		if (!p_h4)
+			break;
+
+		adv = p_h4 - p_left;
+		sz_left -= adv;
+		p_left += adv;
+
+		bdev->rx_skb = h4_recv_buf(bdev->hdev, bdev->rx_skb, p_h4,
+					   sz_h4, mtk_recv_pkts,
+					   ARRAY_SIZE(mtk_recv_pkts));
+		if (IS_ERR(bdev->rx_skb)) {
+			err = PTR_ERR(bdev->rx_skb);
+			bt_dev_err(bdev->hdev,
+				   "Frame reassembly failed (%d)", err);
+			bdev->rx_skb = NULL;
+			return err;
+		}
+
+		sz_left -= sz_h4;
+		p_left += sz_h4;
+	}
+
+	return 0;
+}
+
+static int btmtkuart_receive_buf(struct serdev_device *serdev, const u8 *data,
+				 size_t count)
+{
+	struct btmtkuart_dev *bdev = serdev_device_get_drvdata(serdev);
+	int err;
+
+	err = btmtkuart_recv(bdev->hdev, data, count);
+	if (err < 0)
+		return err;
+
+	bdev->hdev->stat.byte_rx += count;
+
+	return count;
+}
+
+static void btmtkuart_write_wakeup(struct serdev_device *serdev)
+{
+	struct btmtkuart_dev *bdev = serdev_device_get_drvdata(serdev);
+
+	btmtkuart_tx_wakeup(bdev);
+}
+
+static const struct serdev_device_ops btmtkuart_client_ops = {
+	.receive_buf = btmtkuart_receive_buf,
+	.write_wakeup = btmtkuart_write_wakeup,
+};
+
+static int btmtkuart_open(struct hci_dev *hdev)
+{
+	struct btmtkuart_dev *bdev = hci_get_drvdata(hdev);
+	struct device *dev;
+	int err;
+
+	err = serdev_device_open(bdev->serdev);
+	if (err) {
+		bt_dev_err(hdev, "Unable to open UART device %s",
+			   dev_name(&bdev->serdev->dev));
+		goto err_open;
+	}
+
+	bdev->stp_cursor = 2;
+	bdev->stp_dlen = 0;
+
+	dev = &bdev->serdev->dev;
+
+	/* Enable the power domain and clock the device requires */
+	pm_runtime_enable(dev);
+	err = pm_runtime_get_sync(dev);
+	if (err < 0) {
+		pm_runtime_put_noidle(dev);
+		goto err_disable_rpm;
+	}
+
+	err = clk_prepare_enable(bdev->clk);
+	if (err < 0)
+		goto err_put_rpm;
+
+	return 0;
+
+err_put_rpm:
+	pm_runtime_put_sync(dev);
+err_disable_rpm:
+	pm_runtime_disable(dev);
+err_open:
+	return err;
+}
+
+static int btmtkuart_close(struct hci_dev *hdev)
+{
+	struct btmtkuart_dev *bdev = hci_get_drvdata(hdev);
+	struct device *dev = &bdev->serdev->dev;
+
+	/* Shutdown the clock and power domain the device requires */
+	clk_disable_unprepare(bdev->clk);
+	pm_runtime_put_sync(dev);
+	pm_runtime_disable(dev);
+
+	serdev_device_close(bdev->serdev);
+
+	return 0;
+}
+
+static int btmtkuart_flush(struct hci_dev *hdev)
+{
+	struct btmtkuart_dev *bdev = hci_get_drvdata(hdev);
+
+	/* Flush any pending characters */
+	serdev_device_write_flush(bdev->serdev);
+	skb_queue_purge(&bdev->txq);
+
+	cancel_work_sync(&bdev->tx_work);
+
+	kfree_skb(bdev->rx_skb);
+	bdev->rx_skb = NULL;
+
+	bdev->stp_cursor = 2;
+	bdev->stp_dlen = 0;
+
+	return 0;
+}
+
+static int btmtkuart_setup(struct hci_dev *hdev)
+{
+	u8 param = 0x1;
+	int err = 0;
+
+	/* Setup a firmware which the device definitely requires */
+	err = mtk_setup_fw(hdev);
+	if (err < 0)
+		return err;
+
+	/* Activate function the firmware providing to */
+	err = mtk_hci_wmt_sync(hdev, MTK_WMT_RST, 0x4, 0, 0);
+	if (err < 0) {
+		bt_dev_err(hdev, "Failed to send wmt rst (%d)", err);
+		return err;
+	}
+
+	/* Enable Bluetooth protocol */
+	err = mtk_hci_wmt_sync(hdev, MTK_WMT_FUNC_CTRL, 0x0, sizeof(param),
+			       &param);
+	if (err < 0) {
+		bt_dev_err(hdev, "Failed to send wmt func ctrl (%d)", err);
+		return err;
+	}
+
+	return 0;
+}
+
+static int btmtkuart_shutdown(struct hci_dev *hdev)
+{
+	u8 param = 0x0;
+	int err;
+
+	/* Disable the device */
+	err = mtk_hci_wmt_sync(hdev, MTK_WMT_FUNC_CTRL, 0x0, sizeof(param),
+			       &param);
+	if (err < 0) {
+		bt_dev_err(hdev, "Failed to send wmt func ctrl (%d)", err);
+		return err;
+	}
+
+	return 0;
+}
+
+static int btmtkuart_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct btmtkuart_dev *bdev = hci_get_drvdata(hdev);
+	struct mtk_stp_hdr *shdr;
+	int err, dlen, type = 0;
+
+	/* Prepend skb with frame type */
+	memcpy(skb_push(skb, 1), &hci_skb_pkt_type(skb), 1);
+
+	/* Make sure that there is enough rooms for STP header and trailer */
+	if (unlikely(skb_headroom(skb) < sizeof(*shdr)) ||
+	    (skb_tailroom(skb) < MTK_STP_TLR_SIZE)) {
+		err = pskb_expand_head(skb, sizeof(*shdr), MTK_STP_TLR_SIZE,
+				       GFP_ATOMIC);
+		if (err < 0)
+			return err;
+	}
+
+	/* Add the STP header */
+	dlen = skb->len;
+	shdr = skb_push(skb, sizeof(*shdr));
+	shdr->prefix = 0x80;
+	shdr->dlen = cpu_to_be16((dlen & 0x0fff) | (type << 12));
+	shdr->cs = 0;		/* MT7622 doesn't care about checksum value */
+
+	/* Add the STP trailer */
+	skb_put_zero(skb, MTK_STP_TLR_SIZE);
+
+	skb_queue_tail(&bdev->txq, skb);
+
+	btmtkuart_tx_wakeup(bdev);
+	return 0;
+}
+
+static int btmtkuart_probe(struct serdev_device *serdev)
+{
+	struct btmtkuart_dev *bdev;
+	struct hci_dev *hdev;
+
+	bdev = devm_kzalloc(&serdev->dev, sizeof(*bdev), GFP_KERNEL);
+	if (!bdev)
+		return -ENOMEM;
+
+	bdev->clk = devm_clk_get(&serdev->dev, "ref");
+	if (IS_ERR(bdev->clk))
+		return PTR_ERR(bdev->clk);
+
+	bdev->serdev = serdev;
+	serdev_device_set_drvdata(serdev, bdev);
+
+	serdev_device_set_client_ops(serdev, &btmtkuart_client_ops);
+
+	INIT_WORK(&bdev->tx_work, btmtkuart_tx_work);
+	skb_queue_head_init(&bdev->txq);
+
+	/* Initialize and register HCI device */
+	hdev = hci_alloc_dev();
+	if (!hdev) {
+		dev_err(&serdev->dev, "Can't allocate HCI device\n");
+		return -ENOMEM;
+	}
+
+	bdev->hdev = hdev;
+
+	hdev->bus = HCI_UART;
+	hci_set_drvdata(hdev, bdev);
+
+	hdev->open     = btmtkuart_open;
+	hdev->close    = btmtkuart_close;
+	hdev->flush    = btmtkuart_flush;
+	hdev->setup    = btmtkuart_setup;
+	hdev->shutdown = btmtkuart_shutdown;
+	hdev->send     = btmtkuart_send_frame;
+	SET_HCIDEV_DEV(hdev, &serdev->dev);
+
+	hdev->manufacturer = 70;
+	set_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks);
+
+	if (hci_register_dev(hdev) < 0) {
+		dev_err(&serdev->dev, "Can't register HCI device\n");
+		hci_free_dev(hdev);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static void btmtkuart_remove(struct serdev_device *serdev)
+{
+	struct btmtkuart_dev *bdev = serdev_device_get_drvdata(serdev);
+	struct hci_dev *hdev = bdev->hdev;
+
+	hci_unregister_dev(hdev);
+	hci_free_dev(hdev);
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id mtk_of_match_table[] = {
+	{ .compatible = "mediatek,mt7622-bluetooth"},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, mtk_of_match_table);
+#endif
+
+static struct serdev_device_driver btmtkuart_driver = {
+	.probe = btmtkuart_probe,
+	.remove = btmtkuart_remove,
+	.driver = {
+		.name = "btmtkuart",
+		.of_match_table = of_match_ptr(mtk_of_match_table),
+	},
+};
+
+module_serdev_device_driver(btmtkuart_driver);
+
+MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
+MODULE_DESCRIPTION("MediaTek Bluetooth Serial driver ver " VERSION);
+MODULE_VERSION(VERSION);
+MODULE_LICENSE("GPL");
+MODULE_FIRMWARE(FIRMWARE_MT7622);
diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index 8219816c54a0..ec9e03a6b778 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -27,7 +27,7 @@
 
 #define VERSION "0.1"
 
-static int rome_patch_ver_req(struct hci_dev *hdev, u32 *rome_version)
+int qca_read_soc_version(struct hci_dev *hdev, u32 *soc_version)
 {
 	struct sk_buff *skb;
 	struct edl_event_hdr *edl;
@@ -35,36 +35,35 @@ static int rome_patch_ver_req(struct hci_dev *hdev, u32 *rome_version)
 	char cmd;
 	int err = 0;
 
-	BT_DBG("%s: ROME Patch Version Request", hdev->name);
+	bt_dev_dbg(hdev, "QCA Version Request");
 
 	cmd = EDL_PATCH_VER_REQ_CMD;
 	skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, EDL_PATCH_CMD_LEN,
-				&cmd, HCI_VENDOR_PKT, HCI_INIT_TIMEOUT);
+				&cmd, HCI_EV_VENDOR, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
-		BT_ERR("%s: Failed to read version of ROME (%d)", hdev->name,
-		       err);
+		bt_dev_err(hdev, "Reading QCA version information failed (%d)",
+			   err);
 		return err;
 	}
 
 	if (skb->len != sizeof(*edl) + sizeof(*ver)) {
-		BT_ERR("%s: Version size mismatch len %d", hdev->name,
-		       skb->len);
+		bt_dev_err(hdev, "QCA Version size mismatch len %d", skb->len);
 		err = -EILSEQ;
 		goto out;
 	}
 
 	edl = (struct edl_event_hdr *)(skb->data);
 	if (!edl) {
-		BT_ERR("%s: TLV with no header", hdev->name);
+		bt_dev_err(hdev, "QCA TLV with no header");
 		err = -EILSEQ;
 		goto out;
 	}
 
 	if (edl->cresp != EDL_CMD_REQ_RES_EVT ||
 	    edl->rtype != EDL_APP_VER_RES_EVT) {
-		BT_ERR("%s: Wrong packet received %d %d", hdev->name,
-		       edl->cresp, edl->rtype);
+		bt_dev_err(hdev, "QCA Wrong packet received %d %d", edl->cresp,
+			   edl->rtype);
 		err = -EIO;
 		goto out;
 	}
@@ -76,30 +75,35 @@ static int rome_patch_ver_req(struct hci_dev *hdev, u32 *rome_version)
 	BT_DBG("%s: ROM    :0x%08x", hdev->name, le16_to_cpu(ver->rome_ver));
 	BT_DBG("%s: SOC    :0x%08x", hdev->name, le32_to_cpu(ver->soc_id));
 
-	/* ROME chipset version can be decided by patch and SoC
+	/* QCA chipset version can be decided by patch and SoC
 	 * version, combination with upper 2 bytes from SoC
 	 * and lower 2 bytes from patch will be used.
 	 */
-	*rome_version = (le32_to_cpu(ver->soc_id) << 16) |
+	*soc_version = (le32_to_cpu(ver->soc_id) << 16) |
 			(le16_to_cpu(ver->rome_ver) & 0x0000ffff);
+	if (*soc_version == 0)
+		err = -EILSEQ;
 
 out:
 	kfree_skb(skb);
+	if (err)
+		bt_dev_err(hdev, "QCA Failed to get version (%d)", err);
 
 	return err;
 }
+EXPORT_SYMBOL_GPL(qca_read_soc_version);
 
-static int rome_reset(struct hci_dev *hdev)
+static int qca_send_reset(struct hci_dev *hdev)
 {
 	struct sk_buff *skb;
 	int err;
 
-	BT_DBG("%s: ROME HCI_RESET", hdev->name);
+	bt_dev_dbg(hdev, "QCA HCI_RESET");
 
 	skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
-		BT_ERR("%s: Reset failed (%d)", hdev->name, err);
+		bt_dev_err(hdev, "QCA Reset failed (%d)", err);
 		return err;
 	}
 
@@ -108,7 +112,7 @@ static int rome_reset(struct hci_dev *hdev)
 	return 0;
 }
 
-static void rome_tlv_check_data(struct rome_config *config,
+static void qca_tlv_check_data(struct rome_config *config,
 				const struct firmware *fw)
 {
 	const u8 *data;
@@ -207,7 +211,7 @@ static void rome_tlv_check_data(struct rome_config *config,
 	}
 }
 
-static int rome_tlv_send_segment(struct hci_dev *hdev, int seg_size,
+static int qca_tlv_send_segment(struct hci_dev *hdev, int seg_size,
 				 const u8 *data, enum rome_tlv_dnld_mode mode)
 {
 	struct sk_buff *skb;
@@ -225,22 +229,22 @@ static int rome_tlv_send_segment(struct hci_dev *hdev, int seg_size,
 				      cmd);
 
 	skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, seg_size + 2, cmd,
-				HCI_VENDOR_PKT, HCI_INIT_TIMEOUT);
+				HCI_EV_VENDOR, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
-		BT_ERR("%s: Failed to send TLV segment (%d)", hdev->name, err);
+		bt_dev_err(hdev, "QCA Failed to send TLV segment (%d)", err);
 		return err;
 	}
 
 	if (skb->len != sizeof(*edl) + sizeof(*tlv_resp)) {
-		BT_ERR("%s: TLV response size mismatch", hdev->name);
+		bt_dev_err(hdev, "QCA TLV response size mismatch");
 		err = -EILSEQ;
 		goto out;
 	}
 
 	edl = (struct edl_event_hdr *)(skb->data);
 	if (!edl) {
-		BT_ERR("%s: TLV with no header", hdev->name);
+		bt_dev_err(hdev, "TLV with no header");
 		err = -EILSEQ;
 		goto out;
 	}
@@ -249,8 +253,8 @@ static int rome_tlv_send_segment(struct hci_dev *hdev, int seg_size,
 
 	if (edl->cresp != EDL_CMD_REQ_RES_EVT ||
 	    edl->rtype != EDL_TVL_DNLD_RES_EVT || tlv_resp->result != 0x00) {
-		BT_ERR("%s: TLV with error stat 0x%x rtype 0x%x (0x%x)",
-		       hdev->name, edl->cresp, edl->rtype, tlv_resp->result);
+		bt_dev_err(hdev, "QCA TLV with error stat 0x%x rtype 0x%x (0x%x)",
+			   edl->cresp, edl->rtype, tlv_resp->result);
 		err = -EIO;
 	}
 
@@ -260,23 +264,23 @@ out:
 	return err;
 }
 
-static int rome_download_firmware(struct hci_dev *hdev,
+static int qca_download_firmware(struct hci_dev *hdev,
 				  struct rome_config *config)
 {
 	const struct firmware *fw;
 	const u8 *segment;
 	int ret, remain, i = 0;
 
-	bt_dev_info(hdev, "ROME Downloading %s", config->fwname);
+	bt_dev_info(hdev, "QCA Downloading %s", config->fwname);
 
 	ret = request_firmware(&fw, config->fwname, &hdev->dev);
 	if (ret) {
-		BT_ERR("%s: Failed to request file: %s (%d)", hdev->name,
-		       config->fwname, ret);
+		bt_dev_err(hdev, "QCA Failed to request file: %s (%d)",
+			   config->fwname, ret);
 		return ret;
 	}
 
-	rome_tlv_check_data(config, fw);
+	qca_tlv_check_data(config, fw);
 
 	segment = fw->data;
 	remain = fw->size;
@@ -290,7 +294,7 @@ static int rome_download_firmware(struct hci_dev *hdev,
 		if (!remain || segsize < MAX_SIZE_PER_TLV_SEGMENT)
 			config->dnld_mode = ROME_SKIP_EVT_NONE;
 
-		ret = rome_tlv_send_segment(hdev, segsize, segment,
+		ret = qca_tlv_send_segment(hdev, segsize, segment,
 					    config->dnld_mode);
 		if (ret)
 			break;
@@ -314,11 +318,10 @@ int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr)
 	cmd[2] = sizeof(bdaddr_t);	/* size */
 	memcpy(cmd + 3, bdaddr, sizeof(bdaddr_t));
 	skb = __hci_cmd_sync_ev(hdev, EDL_NVM_ACCESS_OPCODE, sizeof(cmd), cmd,
-				HCI_VENDOR_PKT, HCI_INIT_TIMEOUT);
+				HCI_EV_VENDOR, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
-		BT_ERR("%s: Change address command failed (%d)",
-		       hdev->name, err);
+		bt_dev_err(hdev, "QCA Change address command failed (%d)", err);
 		return err;
 	}
 
@@ -328,57 +331,65 @@ int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr)
 }
 EXPORT_SYMBOL_GPL(qca_set_bdaddr_rome);
 
-int qca_uart_setup_rome(struct hci_dev *hdev, uint8_t baudrate)
+int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
+		   enum qca_btsoc_type soc_type, u32 soc_ver)
 {
-	u32 rome_ver = 0;
 	struct rome_config config;
 	int err;
+	u8 rom_ver;
 
-	BT_DBG("%s: ROME setup on UART", hdev->name);
+	bt_dev_dbg(hdev, "QCA setup on UART");
 
 	config.user_baud_rate = baudrate;
 
-	/* Get ROME version information */
-	err = rome_patch_ver_req(hdev, &rome_ver);
-	if (err < 0 || rome_ver == 0) {
-		BT_ERR("%s: Failed to get version 0x%x", hdev->name, err);
-		return err;
-	}
-
-	bt_dev_info(hdev, "ROME controller version 0x%08x", rome_ver);
-
 	/* Download rampatch file */
 	config.type = TLV_TYPE_PATCH;
-	snprintf(config.fwname, sizeof(config.fwname), "qca/rampatch_%08x.bin",
-		 rome_ver);
-	err = rome_download_firmware(hdev, &config);
+	if (soc_type == QCA_WCN3990) {
+		/* Firmware files to download are based on ROM version.
+		 * ROM version is derived from last two bytes of soc_ver.
+		 */
+		rom_ver = ((soc_ver & 0x00000f00) >> 0x04) |
+			    (soc_ver & 0x0000000f);
+		snprintf(config.fwname, sizeof(config.fwname),
+			 "qca/crbtfw%02x.tlv", rom_ver);
+	} else {
+		snprintf(config.fwname, sizeof(config.fwname),
+			 "qca/rampatch_%08x.bin", soc_ver);
+	}
+
+	err = qca_download_firmware(hdev, &config);
 	if (err < 0) {
-		BT_ERR("%s: Failed to download patch (%d)", hdev->name, err);
+		bt_dev_err(hdev, "QCA Failed to download patch (%d)", err);
 		return err;
 	}
 
 	/* Download NVM configuration */
 	config.type = TLV_TYPE_NVM;
-	snprintf(config.fwname, sizeof(config.fwname), "qca/nvm_%08x.bin",
-		 rome_ver);
-	err = rome_download_firmware(hdev, &config);
+	if (soc_type == QCA_WCN3990)
+		snprintf(config.fwname, sizeof(config.fwname),
+			 "qca/crnv%02x.bin", rom_ver);
+	else
+		snprintf(config.fwname, sizeof(config.fwname),
+			 "qca/nvm_%08x.bin", soc_ver);
+
+	err = qca_download_firmware(hdev, &config);
 	if (err < 0) {
-		BT_ERR("%s: Failed to download NVM (%d)", hdev->name, err);
+		bt_dev_err(hdev, "QCA Failed to download NVM (%d)", err);
 		return err;
 	}
 
 	/* Perform HCI reset */
-	err = rome_reset(hdev);
+	err = qca_send_reset(hdev);
 	if (err < 0) {
-		BT_ERR("%s: Failed to run HCI_RESET (%d)", hdev->name, err);
+		bt_dev_err(hdev, "QCA Failed to run HCI_RESET (%d)", err);
 		return err;
 	}
 
-	bt_dev_info(hdev, "ROME setup on UART is completed");
+	bt_dev_info(hdev, "QCA setup on UART is completed");
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(qca_uart_setup_rome);
+EXPORT_SYMBOL_GPL(qca_uart_setup);
 
 MODULE_AUTHOR("Ben Young Tae Kim <ytkim@qca.qualcomm.com>");
 MODULE_DESCRIPTION("Bluetooth support for Qualcomm Atheros family ver " VERSION);
diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h
index 13d77fd873b6..0c01f375fe83 100644
--- a/drivers/bluetooth/btqca.h
+++ b/drivers/bluetooth/btqca.h
@@ -37,6 +37,9 @@
 #define EDL_TAG_ID_HCI			(17)
 #define EDL_TAG_ID_DEEP_SLEEP		(27)
 
+#define QCA_WCN3990_POWERON_PULSE	0xFC
+#define QCA_WCN3990_POWEROFF_PULSE	0xC0
+
 enum qca_bardrate {
 	QCA_BAUDRATE_115200 	= 0,
 	QCA_BAUDRATE_57600,
@@ -124,10 +127,19 @@ struct tlv_type_hdr {
 	__u8   data[0];
 } __packed;
 
+enum qca_btsoc_type {
+	QCA_INVALID = -1,
+	QCA_AR3002,
+	QCA_ROME,
+	QCA_WCN3990
+};
+
 #if IS_ENABLED(CONFIG_BT_QCA)
 
 int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr);
-int qca_uart_setup_rome(struct hci_dev *hdev, uint8_t baudrate);
+int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
+		   enum qca_btsoc_type soc_type, u32 soc_ver);
+int qca_read_soc_version(struct hci_dev *hdev, u32 *soc_version);
 
 #else
 
@@ -136,7 +148,13 @@ static inline int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdad
 	return -EOPNOTSUPP;
 }
 
-static inline int qca_uart_setup_rome(struct hci_dev *hdev, int speed)
+static inline int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
+				 enum qca_btsoc_type soc_type, u32 soc_ver)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int qca_read_soc_version(struct hci_dev *hdev, u32 *soc_version)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index 437f080deaab..7f9ea8e4c1b2 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -34,9 +34,12 @@
 #define RTL_ROM_LMP_8821A	0x8821
 #define RTL_ROM_LMP_8761A	0x8761
 #define RTL_ROM_LMP_8822B	0x8822
+#define RTL_CONFIG_MAGIC	0x8723ab55
 
 #define IC_MATCH_FL_LMPSUBV	(1 << 0)
 #define IC_MATCH_FL_HCIREV	(1 << 1)
+#define IC_MATCH_FL_HCIVER	(1 << 2)
+#define IC_MATCH_FL_HCIBUS	(1 << 3)
 #define IC_INFO(lmps, hcir) \
 	.match_flags = IC_MATCH_FL_LMPSUBV | IC_MATCH_FL_HCIREV, \
 	.lmp_subver = (lmps), \
@@ -46,49 +49,130 @@ struct id_table {
 	__u16 match_flags;
 	__u16 lmp_subver;
 	__u16 hci_rev;
+	__u8 hci_ver;
+	__u8 hci_bus;
 	bool config_needed;
+	bool has_rom_version;
 	char *fw_name;
 	char *cfg_name;
 };
 
+struct btrtl_device_info {
+	const struct id_table *ic_info;
+	u8 rom_version;
+	u8 *fw_data;
+	int fw_len;
+	u8 *cfg_data;
+	int cfg_len;
+};
+
 static const struct id_table ic_id_table[] = {
+	{ IC_MATCH_FL_LMPSUBV, RTL_ROM_LMP_8723A, 0x0,
+	  .config_needed = false,
+	  .has_rom_version = false,
+	  .fw_name = "rtl_bt/rtl8723a_fw.bin",
+	  .cfg_name = NULL },
+
+	{ IC_MATCH_FL_LMPSUBV, RTL_ROM_LMP_3499, 0x0,
+	  .config_needed = false,
+	  .has_rom_version = false,
+	  .fw_name = "rtl_bt/rtl8723a_fw.bin",
+	  .cfg_name = NULL },
+
+	/* 8723BS */
+	{ .match_flags = IC_MATCH_FL_LMPSUBV | IC_MATCH_FL_HCIREV |
+			 IC_MATCH_FL_HCIVER | IC_MATCH_FL_HCIBUS,
+	  .lmp_subver = RTL_ROM_LMP_8723B,
+	  .hci_rev = 0xb,
+	  .hci_ver = 6,
+	  .hci_bus = HCI_UART,
+	  .config_needed = true,
+	  .has_rom_version = true,
+	  .fw_name  = "rtl_bt/rtl8723bs_fw.bin",
+	  .cfg_name = "rtl_bt/rtl8723bs_config" },
+
 	/* 8723B */
 	{ IC_INFO(RTL_ROM_LMP_8723B, 0xb),
 	  .config_needed = false,
+	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8723b_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8723b_config.bin" },
+	  .cfg_name = "rtl_bt/rtl8723b_config" },
 
 	/* 8723D */
 	{ IC_INFO(RTL_ROM_LMP_8723B, 0xd),
 	  .config_needed = true,
+	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8723d_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8723d_config.bin" },
+	  .cfg_name = "rtl_bt/rtl8723d_config" },
+
+	/* 8723DS */
+	{ .match_flags = IC_MATCH_FL_LMPSUBV | IC_MATCH_FL_HCIREV |
+			 IC_MATCH_FL_HCIVER | IC_MATCH_FL_HCIBUS,
+	  .lmp_subver = RTL_ROM_LMP_8723B,
+	  .hci_rev = 0xd,
+	  .hci_ver = 8,
+	  .hci_bus = HCI_UART,
+	  .config_needed = true,
+	  .has_rom_version = true,
+	  .fw_name  = "rtl_bt/rtl8723ds_fw.bin",
+	  .cfg_name = "rtl_bt/rtl8723ds_config" },
 
 	/* 8821A */
 	{ IC_INFO(RTL_ROM_LMP_8821A, 0xa),
 	  .config_needed = false,
+	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8821a_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8821a_config.bin" },
+	  .cfg_name = "rtl_bt/rtl8821a_config" },
 
 	/* 8821C */
 	{ IC_INFO(RTL_ROM_LMP_8821A, 0xc),
 	  .config_needed = false,
+	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8821c_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8821c_config.bin" },
+	  .cfg_name = "rtl_bt/rtl8821c_config" },
 
 	/* 8761A */
 	{ IC_MATCH_FL_LMPSUBV, RTL_ROM_LMP_8761A, 0x0,
 	  .config_needed = false,
+	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8761a_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8761a_config.bin" },
+	  .cfg_name = "rtl_bt/rtl8761a_config" },
 
 	/* 8822B */
 	{ IC_INFO(RTL_ROM_LMP_8822B, 0xb),
 	  .config_needed = true,
+	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8822b_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8822b_config.bin" },
+	  .cfg_name = "rtl_bt/rtl8822b_config" },
 	};
 
+static const struct id_table *btrtl_match_ic(u16 lmp_subver, u16 hci_rev,
+					     u8 hci_ver, u8 hci_bus)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ic_id_table); i++) {
+		if ((ic_id_table[i].match_flags & IC_MATCH_FL_LMPSUBV) &&
+		    (ic_id_table[i].lmp_subver != lmp_subver))
+			continue;
+		if ((ic_id_table[i].match_flags & IC_MATCH_FL_HCIREV) &&
+		    (ic_id_table[i].hci_rev != hci_rev))
+			continue;
+		if ((ic_id_table[i].match_flags & IC_MATCH_FL_HCIVER) &&
+		    (ic_id_table[i].hci_ver != hci_ver))
+			continue;
+		if ((ic_id_table[i].match_flags & IC_MATCH_FL_HCIBUS) &&
+		    (ic_id_table[i].hci_bus != hci_bus))
+			continue;
+
+		break;
+	}
+	if (i >= ARRAY_SIZE(ic_id_table))
+		return NULL;
+
+	return &ic_id_table[i];
+}
+
 static int rtl_read_rom_version(struct hci_dev *hdev, u8 *version)
 {
 	struct rtl_rom_version_evt *rom_version;
@@ -97,20 +181,20 @@ static int rtl_read_rom_version(struct hci_dev *hdev, u8 *version)
 	/* Read RTL ROM version command */
 	skb = __hci_cmd_sync(hdev, 0xfc6d, 0, NULL, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
-		BT_ERR("%s: Read ROM version failed (%ld)",
-		       hdev->name, PTR_ERR(skb));
+		rtl_dev_err(hdev, "Read ROM version failed (%ld)\n",
+			    PTR_ERR(skb));
 		return PTR_ERR(skb);
 	}
 
 	if (skb->len != sizeof(*rom_version)) {
-		BT_ERR("%s: RTL version event length mismatch", hdev->name);
+		rtl_dev_err(hdev, "RTL version event length mismatch\n");
 		kfree_skb(skb);
 		return -EIO;
 	}
 
 	rom_version = (struct rtl_rom_version_evt *)skb->data;
-	bt_dev_info(hdev, "rom_version status=%x version=%x",
-		    rom_version->status, rom_version->version);
+	rtl_dev_info(hdev, "rom_version status=%x version=%x\n",
+		     rom_version->status, rom_version->version);
 
 	*version = rom_version->version;
 
@@ -118,16 +202,16 @@ static int rtl_read_rom_version(struct hci_dev *hdev, u8 *version)
 	return 0;
 }
 
-static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver,
-				const struct firmware *fw,
+static int rtlbt_parse_firmware(struct hci_dev *hdev,
+				struct btrtl_device_info *btrtl_dev,
 				unsigned char **_buf)
 {
 	const u8 extension_sig[] = { 0x51, 0x04, 0xfd, 0x77 };
 	struct rtl_epatch_header *epatch_info;
 	unsigned char *buf;
-	int i, ret, len;
+	int i, len;
 	size_t min_size;
-	u8 opcode, length, data, rom_version = 0;
+	u8 opcode, length, data;
 	int project_id = -1;
 	const unsigned char *fwptr, *chip_id_base;
 	const unsigned char *patch_length_base, *patch_offset_base;
@@ -146,17 +230,13 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver,
 		{ RTL_ROM_LMP_8821A, 10 },	/* 8821C */
 	};
 
-	ret = rtl_read_rom_version(hdev, &rom_version);
-	if (ret)
-		return ret;
-
 	min_size = sizeof(struct rtl_epatch_header) + sizeof(extension_sig) + 3;
-	if (fw->size < min_size)
+	if (btrtl_dev->fw_len < min_size)
 		return -EINVAL;
 
-	fwptr = fw->data + fw->size - sizeof(extension_sig);
+	fwptr = btrtl_dev->fw_data + btrtl_dev->fw_len - sizeof(extension_sig);
 	if (memcmp(fwptr, extension_sig, sizeof(extension_sig)) != 0) {
-		BT_ERR("%s: extension section signature mismatch", hdev->name);
+		rtl_dev_err(hdev, "extension section signature mismatch\n");
 		return -EINVAL;
 	}
 
@@ -166,7 +246,7 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver,
 	 * Once we have that, we double-check that that project_id is suitable
 	 * for the hardware we are working with.
 	 */
-	while (fwptr >= fw->data + (sizeof(struct rtl_epatch_header) + 3)) {
+	while (fwptr >= btrtl_dev->fw_data + (sizeof(*epatch_info) + 3)) {
 		opcode = *--fwptr;
 		length = *--fwptr;
 		data = *--fwptr;
@@ -177,8 +257,7 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver,
 			break;
 
 		if (length == 0) {
-			BT_ERR("%s: found instruction with length 0",
-			       hdev->name);
+			rtl_dev_err(hdev, "found instruction with length 0\n");
 			return -EINVAL;
 		}
 
@@ -191,7 +270,7 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver,
 	}
 
 	if (project_id < 0) {
-		BT_ERR("%s: failed to find version instruction", hdev->name);
+		rtl_dev_err(hdev, "failed to find version instruction\n");
 		return -EINVAL;
 	}
 
@@ -202,19 +281,21 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver,
 	}
 
 	if (i >= ARRAY_SIZE(project_id_to_lmp_subver)) {
-		BT_ERR("%s: unknown project id %d", hdev->name, project_id);
+		rtl_dev_err(hdev, "unknown project id %d\n", project_id);
 		return -EINVAL;
 	}
 
-	if (lmp_subver != project_id_to_lmp_subver[i].lmp_subver) {
-		BT_ERR("%s: firmware is for %x but this is a %x", hdev->name,
-		       project_id_to_lmp_subver[i].lmp_subver, lmp_subver);
+	if (btrtl_dev->ic_info->lmp_subver !=
+				project_id_to_lmp_subver[i].lmp_subver) {
+		rtl_dev_err(hdev, "firmware is for %x but this is a %x\n",
+			    project_id_to_lmp_subver[i].lmp_subver,
+			    btrtl_dev->ic_info->lmp_subver);
 		return -EINVAL;
 	}
 
-	epatch_info = (struct rtl_epatch_header *)fw->data;
+	epatch_info = (struct rtl_epatch_header *)btrtl_dev->fw_data;
 	if (memcmp(epatch_info->signature, RTL_EPATCH_SIGNATURE, 8) != 0) {
-		BT_ERR("%s: bad EPATCH signature", hdev->name);
+		rtl_dev_err(hdev, "bad EPATCH signature\n");
 		return -EINVAL;
 	}
 
@@ -229,16 +310,16 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver,
 	 * Find the right patch for this chip.
 	 */
 	min_size += 8 * num_patches;
-	if (fw->size < min_size)
+	if (btrtl_dev->fw_len < min_size)
 		return -EINVAL;
 
-	chip_id_base = fw->data + sizeof(struct rtl_epatch_header);
+	chip_id_base = btrtl_dev->fw_data + sizeof(struct rtl_epatch_header);
 	patch_length_base = chip_id_base + (sizeof(u16) * num_patches);
 	patch_offset_base = patch_length_base + (sizeof(u16) * num_patches);
 	for (i = 0; i < num_patches; i++) {
 		u16 chip_id = get_unaligned_le16(chip_id_base +
 						 (i * sizeof(u16)));
-		if (chip_id == rom_version + 1) {
+		if (chip_id == btrtl_dev->rom_version + 1) {
 			patch_length = get_unaligned_le16(patch_length_base +
 							  (i * sizeof(u16)));
 			patch_offset = get_unaligned_le32(patch_offset_base +
@@ -248,21 +329,22 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver,
 	}
 
 	if (!patch_offset) {
-		BT_ERR("%s: didn't find patch for chip id %d",
-		       hdev->name, rom_version);
+		rtl_dev_err(hdev, "didn't find patch for chip id %d",
+			    btrtl_dev->rom_version);
 		return -EINVAL;
 	}
 
 	BT_DBG("length=%x offset=%x index %d", patch_length, patch_offset, i);
 	min_size = patch_offset + patch_length;
-	if (fw->size < min_size)
+	if (btrtl_dev->fw_len < min_size)
 		return -EINVAL;
 
 	/* Copy the firmware into a new buffer and write the version at
 	 * the end.
 	 */
 	len = patch_length;
-	buf = kmemdup(fw->data + patch_offset, patch_length, GFP_KERNEL);
+	buf = kmemdup(btrtl_dev->fw_data + patch_offset, patch_length,
+		      GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
@@ -301,15 +383,14 @@ static int rtl_download_firmware(struct hci_dev *hdev,
 		skb = __hci_cmd_sync(hdev, 0xfc20, frag_len + 1, dl_cmd,
 				     HCI_INIT_TIMEOUT);
 		if (IS_ERR(skb)) {
-			BT_ERR("%s: download fw command failed (%ld)",
-			       hdev->name, PTR_ERR(skb));
+			rtl_dev_err(hdev, "download fw command failed (%ld)\n",
+				    PTR_ERR(skb));
 			ret = -PTR_ERR(skb);
 			goto out;
 		}
 
 		if (skb->len != sizeof(struct rtl_download_response)) {
-			BT_ERR("%s: download fw event length mismatch",
-			       hdev->name);
+			rtl_dev_err(hdev, "download fw event length mismatch\n");
 			kfree_skb(skb);
 			ret = -EIO;
 			goto out;
@@ -324,12 +405,12 @@ out:
 	return ret;
 }
 
-static int rtl_load_config(struct hci_dev *hdev, const char *name, u8 **buff)
+static int rtl_load_file(struct hci_dev *hdev, const char *name, u8 **buff)
 {
 	const struct firmware *fw;
 	int ret;
 
-	bt_dev_info(hdev, "rtl: loading %s", name);
+	rtl_dev_info(hdev, "rtl: loading %s\n", name);
 	ret = request_firmware(&fw, name, &hdev->dev);
 	if (ret < 0)
 		return ret;
@@ -343,96 +424,37 @@ static int rtl_load_config(struct hci_dev *hdev, const char *name, u8 **buff)
 	return ret;
 }
 
-static int btrtl_setup_rtl8723a(struct hci_dev *hdev)
+static int btrtl_setup_rtl8723a(struct hci_dev *hdev,
+				struct btrtl_device_info *btrtl_dev)
 {
-	const struct firmware *fw;
-	int ret;
-
-	bt_dev_info(hdev, "rtl: loading rtl_bt/rtl8723a_fw.bin");
-	ret = request_firmware(&fw, "rtl_bt/rtl8723a_fw.bin", &hdev->dev);
-	if (ret < 0) {
-		BT_ERR("%s: Failed to load rtl_bt/rtl8723a_fw.bin", hdev->name);
-		return ret;
-	}
-
-	if (fw->size < 8) {
-		ret = -EINVAL;
-		goto out;
-	}
+	if (btrtl_dev->fw_len < 8)
+		return -EINVAL;
 
 	/* Check that the firmware doesn't have the epatch signature
 	 * (which is only for RTL8723B and newer).
 	 */
-	if (!memcmp(fw->data, RTL_EPATCH_SIGNATURE, 8)) {
-		BT_ERR("%s: unexpected EPATCH signature!", hdev->name);
-		ret = -EINVAL;
-		goto out;
+	if (!memcmp(btrtl_dev->fw_data, RTL_EPATCH_SIGNATURE, 8)) {
+		rtl_dev_err(hdev, "unexpected EPATCH signature!\n");
+		return -EINVAL;
 	}
 
-	ret = rtl_download_firmware(hdev, fw->data, fw->size);
-
-out:
-	release_firmware(fw);
-	return ret;
+	return rtl_download_firmware(hdev, btrtl_dev->fw_data,
+				     btrtl_dev->fw_len);
 }
 
-static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 hci_rev,
-				u16 lmp_subver)
+static int btrtl_setup_rtl8723b(struct hci_dev *hdev,
+				struct btrtl_device_info *btrtl_dev)
 {
 	unsigned char *fw_data = NULL;
-	const struct firmware *fw;
 	int ret;
-	int cfg_sz;
-	u8 *cfg_buff = NULL;
 	u8 *tbuff;
-	char *cfg_name = NULL;
-	char *fw_name = NULL;
-	int i;
 
-	for (i = 0; i < ARRAY_SIZE(ic_id_table); i++) {
-		if ((ic_id_table[i].match_flags & IC_MATCH_FL_LMPSUBV) &&
-		    (ic_id_table[i].lmp_subver != lmp_subver))
-			continue;
-		if ((ic_id_table[i].match_flags & IC_MATCH_FL_HCIREV) &&
-		    (ic_id_table[i].hci_rev != hci_rev))
-			continue;
-
-		break;
-	}
-
-	if (i >= ARRAY_SIZE(ic_id_table)) {
-		BT_ERR("%s: unknown IC info, lmp subver %04x, hci rev %04x",
-		       hdev->name, lmp_subver, hci_rev);
-		return -EINVAL;
-	}
-
-	cfg_name = ic_id_table[i].cfg_name;
-
-	if (cfg_name) {
-		cfg_sz = rtl_load_config(hdev, cfg_name, &cfg_buff);
-		if (cfg_sz < 0) {
-			cfg_sz = 0;
-			if (ic_id_table[i].config_needed)
-				BT_ERR("Necessary config file %s not found\n",
-				       cfg_name);
-		}
-	} else
-		cfg_sz = 0;
-
-	fw_name = ic_id_table[i].fw_name;
-	bt_dev_info(hdev, "rtl: loading %s", fw_name);
-	ret = request_firmware(&fw, fw_name, &hdev->dev);
-	if (ret < 0) {
-		BT_ERR("%s: Failed to load %s", hdev->name, fw_name);
-		goto err_req_fw;
-	}
-
-	ret = rtlbt_parse_firmware(hdev, lmp_subver, fw, &fw_data);
+	ret = rtlbt_parse_firmware(hdev, btrtl_dev, &fw_data);
 	if (ret < 0)
 		goto out;
 
-	if (cfg_sz) {
-		tbuff = kzalloc(ret + cfg_sz, GFP_KERNEL);
+	if (btrtl_dev->cfg_len > 0) {
+		tbuff = kzalloc(ret + btrtl_dev->cfg_len, GFP_KERNEL);
 		if (!tbuff) {
 			ret = -ENOMEM;
 			goto out;
@@ -441,22 +463,18 @@ static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 hci_rev,
 		memcpy(tbuff, fw_data, ret);
 		kfree(fw_data);
 
-		memcpy(tbuff + ret, cfg_buff, cfg_sz);
-		ret += cfg_sz;
+		memcpy(tbuff + ret, btrtl_dev->cfg_data, btrtl_dev->cfg_len);
+		ret += btrtl_dev->cfg_len;
 
 		fw_data = tbuff;
 	}
 
-	bt_dev_info(hdev, "cfg_sz %d, total size %d", cfg_sz, ret);
+	rtl_dev_info(hdev, "cfg_sz %d, total sz %d\n", btrtl_dev->cfg_len, ret);
 
 	ret = rtl_download_firmware(hdev, fw_data, ret);
 
 out:
-	release_firmware(fw);
 	kfree(fw_data);
-err_req_fw:
-	if (cfg_sz)
-		kfree(cfg_buff);
 	return ret;
 }
 
@@ -467,14 +485,13 @@ static struct sk_buff *btrtl_read_local_version(struct hci_dev *hdev)
 	skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_VERSION, 0, NULL,
 			     HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
-		BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION failed (%ld)",
-		       hdev->name, PTR_ERR(skb));
+		rtl_dev_err(hdev, "HCI_OP_READ_LOCAL_VERSION failed (%ld)\n",
+			    PTR_ERR(skb));
 		return skb;
 	}
 
 	if (skb->len != sizeof(struct hci_rp_read_local_version)) {
-		BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION event length mismatch",
-		       hdev->name);
+		rtl_dev_err(hdev, "HCI_OP_READ_LOCAL_VERSION event length mismatch\n");
 		kfree_skb(skb);
 		return ERR_PTR(-EIO);
 	}
@@ -482,49 +499,264 @@ static struct sk_buff *btrtl_read_local_version(struct hci_dev *hdev)
 	return skb;
 }
 
-int btrtl_setup_realtek(struct hci_dev *hdev)
+void btrtl_free(struct btrtl_device_info *btrtl_dev)
 {
+	kfree(btrtl_dev->fw_data);
+	kfree(btrtl_dev->cfg_data);
+	kfree(btrtl_dev);
+}
+EXPORT_SYMBOL_GPL(btrtl_free);
+
+struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev,
+					   const char *postfix)
+{
+	struct btrtl_device_info *btrtl_dev;
 	struct sk_buff *skb;
 	struct hci_rp_read_local_version *resp;
+	char cfg_name[40];
 	u16 hci_rev, lmp_subver;
+	u8 hci_ver;
+	int ret;
+
+	btrtl_dev = kzalloc(sizeof(*btrtl_dev), GFP_KERNEL);
+	if (!btrtl_dev) {
+		ret = -ENOMEM;
+		goto err_alloc;
+	}
 
 	skb = btrtl_read_local_version(hdev);
-	if (IS_ERR(skb))
-		return -PTR_ERR(skb);
+	if (IS_ERR(skb)) {
+		ret = PTR_ERR(skb);
+		goto err_free;
+	}
 
 	resp = (struct hci_rp_read_local_version *)skb->data;
-	bt_dev_info(hdev, "rtl: examining hci_ver=%02x hci_rev=%04x "
-		    "lmp_ver=%02x lmp_subver=%04x",
-		    resp->hci_ver, resp->hci_rev,
-		    resp->lmp_ver, resp->lmp_subver);
+	rtl_dev_info(hdev, "rtl: examining hci_ver=%02x hci_rev=%04x lmp_ver=%02x lmp_subver=%04x\n",
+		     resp->hci_ver, resp->hci_rev,
+		     resp->lmp_ver, resp->lmp_subver);
 
+	hci_ver = resp->hci_ver;
 	hci_rev = le16_to_cpu(resp->hci_rev);
 	lmp_subver = le16_to_cpu(resp->lmp_subver);
 	kfree_skb(skb);
 
+	btrtl_dev->ic_info = btrtl_match_ic(lmp_subver, hci_rev, hci_ver,
+					    hdev->bus);
+
+	if (!btrtl_dev->ic_info) {
+		rtl_dev_err(hdev, "rtl: unknown IC info, lmp subver %04x, hci rev %04x, hci ver %04x",
+			    lmp_subver, hci_rev, hci_ver);
+		ret = -EINVAL;
+		goto err_free;
+	}
+
+	if (btrtl_dev->ic_info->has_rom_version) {
+		ret = rtl_read_rom_version(hdev, &btrtl_dev->rom_version);
+		if (ret)
+			goto err_free;
+	}
+
+	btrtl_dev->fw_len = rtl_load_file(hdev, btrtl_dev->ic_info->fw_name,
+					  &btrtl_dev->fw_data);
+	if (btrtl_dev->fw_len < 0) {
+		rtl_dev_err(hdev, "firmware file %s not found\n",
+			    btrtl_dev->ic_info->fw_name);
+		ret = btrtl_dev->fw_len;
+		goto err_free;
+	}
+
+	if (btrtl_dev->ic_info->cfg_name) {
+		if (postfix) {
+			snprintf(cfg_name, sizeof(cfg_name), "%s-%s.bin",
+				 btrtl_dev->ic_info->cfg_name, postfix);
+		} else {
+			snprintf(cfg_name, sizeof(cfg_name), "%s.bin",
+				 btrtl_dev->ic_info->cfg_name);
+		}
+		btrtl_dev->cfg_len = rtl_load_file(hdev, cfg_name,
+						   &btrtl_dev->cfg_data);
+		if (btrtl_dev->ic_info->config_needed &&
+		    btrtl_dev->cfg_len <= 0) {
+			rtl_dev_err(hdev, "mandatory config file %s not found\n",
+				    btrtl_dev->ic_info->cfg_name);
+			ret = btrtl_dev->cfg_len;
+			goto err_free;
+		}
+	}
+
+	return btrtl_dev;
+
+err_free:
+	btrtl_free(btrtl_dev);
+err_alloc:
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(btrtl_initialize);
+
+int btrtl_download_firmware(struct hci_dev *hdev,
+			    struct btrtl_device_info *btrtl_dev)
+{
 	/* Match a set of subver values that correspond to stock firmware,
 	 * which is not compatible with standard btusb.
 	 * If matched, upload an alternative firmware that does conform to
 	 * standard btusb. Once that firmware is uploaded, the subver changes
 	 * to a different value.
 	 */
-	switch (lmp_subver) {
+	switch (btrtl_dev->ic_info->lmp_subver) {
 	case RTL_ROM_LMP_8723A:
 	case RTL_ROM_LMP_3499:
-		return btrtl_setup_rtl8723a(hdev);
+		return btrtl_setup_rtl8723a(hdev, btrtl_dev);
 	case RTL_ROM_LMP_8723B:
 	case RTL_ROM_LMP_8821A:
 	case RTL_ROM_LMP_8761A:
 	case RTL_ROM_LMP_8822B:
-		return btrtl_setup_rtl8723b(hdev, hci_rev, lmp_subver);
+		return btrtl_setup_rtl8723b(hdev, btrtl_dev);
 	default:
-		bt_dev_info(hdev, "rtl: assuming no firmware upload needed");
+		rtl_dev_info(hdev, "rtl: assuming no firmware upload needed\n");
 		return 0;
 	}
 }
+EXPORT_SYMBOL_GPL(btrtl_download_firmware);
+
+int btrtl_setup_realtek(struct hci_dev *hdev)
+{
+	struct btrtl_device_info *btrtl_dev;
+	int ret;
+
+	btrtl_dev = btrtl_initialize(hdev, NULL);
+	if (IS_ERR(btrtl_dev))
+		return PTR_ERR(btrtl_dev);
+
+	ret = btrtl_download_firmware(hdev, btrtl_dev);
+
+	btrtl_free(btrtl_dev);
+
+	return ret;
+}
 EXPORT_SYMBOL_GPL(btrtl_setup_realtek);
 
+static unsigned int btrtl_convert_baudrate(u32 device_baudrate)
+{
+	switch (device_baudrate) {
+	case 0x0252a00a:
+		return 230400;
+
+	case 0x05f75004:
+		return 921600;
+
+	case 0x00005004:
+		return 1000000;
+
+	case 0x04928002:
+	case 0x01128002:
+		return 1500000;
+
+	case 0x00005002:
+		return 2000000;
+
+	case 0x0000b001:
+		return 2500000;
+
+	case 0x04928001:
+		return 3000000;
+
+	case 0x052a6001:
+		return 3500000;
+
+	case 0x00005001:
+		return 4000000;
+
+	case 0x0252c014:
+	default:
+		return 115200;
+	}
+}
+
+int btrtl_get_uart_settings(struct hci_dev *hdev,
+			    struct btrtl_device_info *btrtl_dev,
+			    unsigned int *controller_baudrate,
+			    u32 *device_baudrate, bool *flow_control)
+{
+	struct rtl_vendor_config *config;
+	struct rtl_vendor_config_entry *entry;
+	int i, total_data_len;
+	bool found = false;
+
+	total_data_len = btrtl_dev->cfg_len - sizeof(*config);
+	if (total_data_len <= 0) {
+		rtl_dev_warn(hdev, "no config loaded\n");
+		return -EINVAL;
+	}
+
+	config = (struct rtl_vendor_config *)btrtl_dev->cfg_data;
+	if (le32_to_cpu(config->signature) != RTL_CONFIG_MAGIC) {
+		rtl_dev_err(hdev, "invalid config magic\n");
+		return -EINVAL;
+	}
+
+	if (total_data_len < le16_to_cpu(config->total_len)) {
+		rtl_dev_err(hdev, "config is too short\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < total_data_len; ) {
+		entry = ((void *)config->entry) + i;
+
+		switch (le16_to_cpu(entry->offset)) {
+		case 0xc:
+			if (entry->len < sizeof(*device_baudrate)) {
+				rtl_dev_err(hdev, "invalid UART config entry\n");
+				return -EINVAL;
+			}
+
+			*device_baudrate = get_unaligned_le32(entry->data);
+			*controller_baudrate = btrtl_convert_baudrate(
+							*device_baudrate);
+
+			if (entry->len >= 13)
+				*flow_control = !!(entry->data[12] & BIT(2));
+			else
+				*flow_control = false;
+
+			found = true;
+			break;
+
+		default:
+			rtl_dev_dbg(hdev, "skipping config entry 0x%x (len %u)\n",
+				   le16_to_cpu(entry->offset), entry->len);
+			break;
+		};
+
+		i += sizeof(*entry) + entry->len;
+	}
+
+	if (!found) {
+		rtl_dev_err(hdev, "no UART config entry found\n");
+		return -ENOENT;
+	}
+
+	rtl_dev_dbg(hdev, "device baudrate = 0x%08x\n", *device_baudrate);
+	rtl_dev_dbg(hdev, "controller baudrate = %u\n", *controller_baudrate);
+	rtl_dev_dbg(hdev, "flow control %d\n", *flow_control);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(btrtl_get_uart_settings);
+
 MODULE_AUTHOR("Daniel Drake <drake@endlessm.com>");
 MODULE_DESCRIPTION("Bluetooth support for Realtek devices ver " VERSION);
 MODULE_VERSION(VERSION);
 MODULE_LICENSE("GPL");
+MODULE_FIRMWARE("rtl_bt/rtl8723a_fw.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8723b_fw.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8723b_config.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8723bs_fw.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8723bs_config.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8723ds_fw.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8723ds_config.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8761a_fw.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8761a_config.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8821a_fw.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8821a_config.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8822b_fw.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8822b_config.bin");
diff --git a/drivers/bluetooth/btrtl.h b/drivers/bluetooth/btrtl.h
index 38ffe4890cd1..f5e36f3993a8 100644
--- a/drivers/bluetooth/btrtl.h
+++ b/drivers/bluetooth/btrtl.h
@@ -17,6 +17,13 @@
 
 #define RTL_FRAG_LEN 252
 
+#define rtl_dev_err(dev, fmt, ...) bt_dev_err(dev, "RTL: " fmt, ##__VA_ARGS__)
+#define rtl_dev_warn(dev, fmt, ...) bt_dev_warn(dev, "RTL: " fmt, ##__VA_ARGS__)
+#define rtl_dev_info(dev, fmt, ...) bt_dev_info(dev, "RTL: " fmt, ##__VA_ARGS__)
+#define rtl_dev_dbg(dev, fmt, ...) bt_dev_dbg(dev, "RTL: " fmt, ##__VA_ARGS__)
+
+struct btrtl_device_info;
+
 struct rtl_download_cmd {
 	__u8 index;
 	__u8 data[RTL_FRAG_LEN];
@@ -38,15 +45,61 @@ struct rtl_epatch_header {
 	__le16 num_patches;
 } __packed;
 
+struct rtl_vendor_config_entry {
+	__le16 offset;
+	__u8 len;
+	__u8 data[0];
+} __packed;
+
+struct rtl_vendor_config {
+	__le32 signature;
+	__le16 total_len;
+	struct rtl_vendor_config_entry entry[0];
+} __packed;
+
 #if IS_ENABLED(CONFIG_BT_RTL)
 
+struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev,
+					   const char *postfix);
+void btrtl_free(struct btrtl_device_info *btrtl_dev);
+int btrtl_download_firmware(struct hci_dev *hdev,
+			    struct btrtl_device_info *btrtl_dev);
 int btrtl_setup_realtek(struct hci_dev *hdev);
+int btrtl_get_uart_settings(struct hci_dev *hdev,
+			    struct btrtl_device_info *btrtl_dev,
+			    unsigned int *controller_baudrate,
+			    u32 *device_baudrate, bool *flow_control);
 
 #else
 
+static inline struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev,
+							 const char *postfix)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline void btrtl_free(struct btrtl_device_info *btrtl_dev)
+{
+}
+
+static inline int btrtl_download_firmware(struct hci_dev *hdev,
+					  struct btrtl_device_info *btrtl_dev)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int btrtl_setup_realtek(struct hci_dev *hdev)
 {
 	return -EOPNOTSUPP;
 }
 
+static inline int btrtl_get_uart_settings(struct hci_dev *hdev,
+					  struct btrtl_device_info *btrtl_dev,
+					  unsigned int *controller_baudrate,
+					  u32 *device_baudrate,
+					  bool *flow_control)
+{
+	return -ENOENT;
+}
+
 #endif
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index f73a27ea28cc..cd2e5cf14ea5 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -374,6 +374,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x7392, 0xa611), .driver_info = BTUSB_REALTEK },
 
 	/* Additional Realtek 8723DE Bluetooth devices */
+	{ USB_DEVICE(0x0bda, 0xb009), .driver_info = BTUSB_REALTEK },
 	{ USB_DEVICE(0x2ff8, 0xb011), .driver_info = BTUSB_REALTEK },
 
 	/* Additional Realtek 8821AE Bluetooth devices */
@@ -509,9 +510,10 @@ static inline void btusb_free_frags(struct btusb_data *data)
 static int btusb_recv_intr(struct btusb_data *data, void *buffer, int count)
 {
 	struct sk_buff *skb;
+	unsigned long flags;
 	int err = 0;
 
-	spin_lock(&data->rxlock);
+	spin_lock_irqsave(&data->rxlock, flags);
 	skb = data->evt_skb;
 
 	while (count) {
@@ -556,7 +558,7 @@ static int btusb_recv_intr(struct btusb_data *data, void *buffer, int count)
 	}
 
 	data->evt_skb = skb;
-	spin_unlock(&data->rxlock);
+	spin_unlock_irqrestore(&data->rxlock, flags);
 
 	return err;
 }
@@ -564,9 +566,10 @@ static int btusb_recv_intr(struct btusb_data *data, void *buffer, int count)
 static int btusb_recv_bulk(struct btusb_data *data, void *buffer, int count)
 {
 	struct sk_buff *skb;
+	unsigned long flags;
 	int err = 0;
 
-	spin_lock(&data->rxlock);
+	spin_lock_irqsave(&data->rxlock, flags);
 	skb = data->acl_skb;
 
 	while (count) {
@@ -613,7 +616,7 @@ static int btusb_recv_bulk(struct btusb_data *data, void *buffer, int count)
 	}
 
 	data->acl_skb = skb;
-	spin_unlock(&data->rxlock);
+	spin_unlock_irqrestore(&data->rxlock, flags);
 
 	return err;
 }
@@ -621,9 +624,10 @@ static int btusb_recv_bulk(struct btusb_data *data, void *buffer, int count)
 static int btusb_recv_isoc(struct btusb_data *data, void *buffer, int count)
 {
 	struct sk_buff *skb;
+	unsigned long flags;
 	int err = 0;
 
-	spin_lock(&data->rxlock);
+	spin_lock_irqsave(&data->rxlock, flags);
 	skb = data->sco_skb;
 
 	while (count) {
@@ -668,7 +672,7 @@ static int btusb_recv_isoc(struct btusb_data *data, void *buffer, int count)
 	}
 
 	data->sco_skb = skb;
-	spin_unlock(&data->rxlock);
+	spin_unlock_irqrestore(&data->rxlock, flags);
 
 	return err;
 }
@@ -1066,6 +1070,7 @@ static void btusb_tx_complete(struct urb *urb)
 	struct sk_buff *skb = urb->context;
 	struct hci_dev *hdev = (struct hci_dev *)skb->dev;
 	struct btusb_data *data = hci_get_drvdata(hdev);
+	unsigned long flags;
 
 	BT_DBG("%s urb %p status %d count %d", hdev->name, urb, urb->status,
 	       urb->actual_length);
@@ -1079,9 +1084,9 @@ static void btusb_tx_complete(struct urb *urb)
 		hdev->stat.err_tx++;
 
 done:
-	spin_lock(&data->txlock);
+	spin_lock_irqsave(&data->txlock, flags);
 	data->tx_in_flight--;
-	spin_unlock(&data->txlock);
+	spin_unlock_irqrestore(&data->txlock, flags);
 
 	kfree(urb->setup_packet);
 
@@ -1593,13 +1598,13 @@ static const struct firmware *btusb_setup_intel_get_fw(struct hci_dev *hdev,
 	ret = request_firmware(&fw, fwname, &hdev->dev);
 	if (ret < 0) {
 		if (ret == -EINVAL) {
-			BT_ERR("%s Intel firmware file request failed (%d)",
-			       hdev->name, ret);
+			bt_dev_err(hdev, "Intel firmware file request failed (%d)",
+				   ret);
 			return NULL;
 		}
 
-		BT_ERR("%s failed to open Intel firmware file: %s(%d)",
-		       hdev->name, fwname, ret);
+		bt_dev_err(hdev, "failed to open Intel firmware file: %s (%d)",
+			   fwname, ret);
 
 		/* If the correct firmware patch file is not found, use the
 		 * default firmware patch file instead
@@ -1607,8 +1612,8 @@ static const struct firmware *btusb_setup_intel_get_fw(struct hci_dev *hdev,
 		snprintf(fwname, sizeof(fwname), "intel/ibt-hw-%x.%x.bseq",
 			 ver->hw_platform, ver->hw_variant);
 		if (request_firmware(&fw, fwname, &hdev->dev) < 0) {
-			BT_ERR("%s failed to open default Intel fw file: %s",
-			       hdev->name, fwname);
+			bt_dev_err(hdev, "failed to open default fw file: %s",
+				   fwname);
 			return NULL;
 		}
 	}
@@ -1637,7 +1642,7 @@ static int btusb_setup_intel_patching(struct hci_dev *hdev,
 	 * process.
 	 */
 	if (remain > HCI_COMMAND_HDR_SIZE && *fw_ptr[0] != 0x01) {
-		BT_ERR("%s Intel fw corrupted: invalid cmd read", hdev->name);
+		bt_dev_err(hdev, "Intel fw corrupted: invalid cmd read");
 		return -EINVAL;
 	}
 	(*fw_ptr)++;
@@ -1651,7 +1656,7 @@ static int btusb_setup_intel_patching(struct hci_dev *hdev,
 	 * of command parameter. If not, the firmware file is corrupted.
 	 */
 	if (remain < cmd->plen) {
-		BT_ERR("%s Intel fw corrupted: invalid cmd len", hdev->name);
+		bt_dev_err(hdev, "Intel fw corrupted: invalid cmd len");
 		return -EFAULT;
 	}
 
@@ -1684,8 +1689,7 @@ static int btusb_setup_intel_patching(struct hci_dev *hdev,
 		remain -= sizeof(*evt);
 
 		if (remain < evt->plen) {
-			BT_ERR("%s Intel fw corrupted: invalid evt len",
-			       hdev->name);
+			bt_dev_err(hdev, "Intel fw corrupted: invalid evt len");
 			return -EFAULT;
 		}
 
@@ -1699,15 +1703,15 @@ static int btusb_setup_intel_patching(struct hci_dev *hdev,
 	 * file is corrupted.
 	 */
 	if (!evt || !evt_param || remain < 0) {
-		BT_ERR("%s Intel fw corrupted: invalid evt read", hdev->name);
+		bt_dev_err(hdev, "Intel fw corrupted: invalid evt read");
 		return -EFAULT;
 	}
 
 	skb = __hci_cmd_sync_ev(hdev, le16_to_cpu(cmd->opcode), cmd->plen,
 				cmd_param, evt->evt, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
-		BT_ERR("%s sending Intel patch command (0x%4.4x) failed (%ld)",
-		       hdev->name, cmd->opcode, PTR_ERR(skb));
+		bt_dev_err(hdev, "sending Intel patch command (0x%4.4x) failed (%ld)",
+			   cmd->opcode, PTR_ERR(skb));
 		return PTR_ERR(skb);
 	}
 
@@ -1716,15 +1720,15 @@ static int btusb_setup_intel_patching(struct hci_dev *hdev,
 	 * the contents of the event.
 	 */
 	if (skb->len != evt->plen) {
-		BT_ERR("%s mismatch event length (opcode 0x%4.4x)", hdev->name,
-		       le16_to_cpu(cmd->opcode));
+		bt_dev_err(hdev, "mismatch event length (opcode 0x%4.4x)",
+			   le16_to_cpu(cmd->opcode));
 		kfree_skb(skb);
 		return -EFAULT;
 	}
 
 	if (memcmp(skb->data, evt_param, evt->plen)) {
-		BT_ERR("%s mismatch event parameter (opcode 0x%4.4x)",
-		       hdev->name, le16_to_cpu(cmd->opcode));
+		bt_dev_err(hdev, "mismatch event parameter (opcode 0x%4.4x)",
+			   le16_to_cpu(cmd->opcode));
 		kfree_skb(skb);
 		return -EFAULT;
 	}
@@ -1753,8 +1757,8 @@ static int btusb_setup_intel(struct hci_dev *hdev)
 	 */
 	skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
-		BT_ERR("%s sending initial HCI reset command failed (%ld)",
-		       hdev->name, PTR_ERR(skb));
+		bt_dev_err(hdev, "sending initial HCI reset command failed (%ld)",
+			   PTR_ERR(skb));
 		return PTR_ERR(skb);
 	}
 	kfree_skb(skb);
@@ -1890,7 +1894,7 @@ static int inject_cmd_complete(struct hci_dev *hdev, __u16 opcode)
 	struct hci_event_hdr *hdr;
 	struct hci_ev_cmd_complete *evt;
 
-	skb = bt_skb_alloc(sizeof(*hdr) + sizeof(*evt) + 1, GFP_ATOMIC);
+	skb = bt_skb_alloc(sizeof(*hdr) + sizeof(*evt) + 1, GFP_KERNEL);
 	if (!skb)
 		return -ENOMEM;
 
@@ -2084,8 +2088,8 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	 * for now only accept this single value.
 	 */
 	if (ver.hw_platform != 0x37) {
-		BT_ERR("%s: Unsupported Intel hardware platform (%u)",
-		       hdev->name, ver.hw_platform);
+		bt_dev_err(hdev, "Unsupported Intel hardware platform (%u)",
+			   ver.hw_platform);
 		return -EINVAL;
 	}
 
@@ -2104,8 +2108,8 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	case 0x14:	/* QnJ, IcP */
 		break;
 	default:
-		BT_ERR("%s: Unsupported Intel hardware variant (%u)",
-		       hdev->name, ver.hw_variant);
+		bt_dev_err(hdev, "Unsupported Intel hardware variant (%u)",
+			   ver.hw_variant);
 		return -EINVAL;
 	}
 
@@ -2134,8 +2138,8 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	 * choice is to return an error and abort the device initialization.
 	 */
 	if (ver.fw_variant != 0x06) {
-		BT_ERR("%s: Unsupported Intel firmware variant (%u)",
-		       hdev->name, ver.fw_variant);
+		bt_dev_err(hdev, "Unsupported Intel firmware variant (%u)",
+			   ver.fw_variant);
 		return -ENODEV;
 	}
 
@@ -2151,8 +2155,8 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	 * that this bootloader does not send them, then abort the setup.
 	 */
 	if (params.limited_cce != 0x00) {
-		BT_ERR("%s: Unsupported Intel firmware loading method (%u)",
-		       hdev->name, params.limited_cce);
+		bt_dev_err(hdev, "Unsupported Intel firmware loading method (%u)",
+			   params.limited_cce);
 		return -EINVAL;
 	}
 
@@ -2202,14 +2206,13 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 			 le16_to_cpu(ver.fw_revision));
 		break;
 	default:
-		BT_ERR("%s: Unsupported Intel firmware naming", hdev->name);
+		bt_dev_err(hdev, "Unsupported Intel firmware naming");
 		return -EINVAL;
 	}
 
 	err = request_firmware(&fw, fwname, &hdev->dev);
 	if (err < 0) {
-		BT_ERR("%s: Failed to load Intel firmware file (%d)",
-		       hdev->name, err);
+		bt_dev_err(hdev, "Failed to load Intel firmware file (%d)", err);
 		return err;
 	}
 
@@ -2235,13 +2238,13 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 			 le16_to_cpu(ver.fw_revision));
 		break;
 	default:
-		BT_ERR("%s: Unsupported Intel firmware naming", hdev->name);
+		bt_dev_err(hdev, "Unsupported Intel firmware naming");
 		return -EINVAL;
 	}
 
 	if (fw->size < 644) {
-		BT_ERR("%s: Invalid size of firmware file (%zu)",
-		       hdev->name, fw->size);
+		bt_dev_err(hdev, "Invalid size of firmware file (%zu)",
+			   fw->size);
 		err = -EBADF;
 		goto done;
 	}
@@ -2272,18 +2275,18 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 				  TASK_INTERRUPTIBLE,
 				  msecs_to_jiffies(5000));
 	if (err == -EINTR) {
-		BT_ERR("%s: Firmware loading interrupted", hdev->name);
+		bt_dev_err(hdev, "Firmware loading interrupted");
 		goto done;
 	}
 
 	if (err) {
-		BT_ERR("%s: Firmware loading timeout", hdev->name);
+		bt_dev_err(hdev, "Firmware loading timeout");
 		err = -ETIMEDOUT;
 		goto done;
 	}
 
 	if (test_bit(BTUSB_FIRMWARE_FAILED, &data->flags)) {
-		BT_ERR("%s: Firmware loading failed", hdev->name);
+		bt_dev_err(hdev, "Firmware loading failed");
 		err = -ENOEXEC;
 		goto done;
 	}
@@ -2322,12 +2325,12 @@ done:
 				  msecs_to_jiffies(1000));
 
 	if (err == -EINTR) {
-		BT_ERR("%s: Device boot interrupted", hdev->name);
+		bt_dev_err(hdev, "Device boot interrupted");
 		return -EINTR;
 	}
 
 	if (err) {
-		BT_ERR("%s: Device boot timeout", hdev->name);
+		bt_dev_err(hdev, "Device boot timeout");
 		return -ETIMEDOUT;
 	}
 
@@ -2364,6 +2367,22 @@ static int btusb_shutdown_intel(struct hci_dev *hdev)
 	struct sk_buff *skb;
 	long ret;
 
+	/* In the shutdown sequence where Bluetooth is turned off followed
+	 * by WiFi being turned off, turning WiFi back on causes issue with
+	 * the RF calibration.
+	 *
+	 * To ensure that any RF activity has been stopped, issue HCI Reset
+	 * command to clear all ongoing activity including advertising,
+	 * scanning etc.
+	 */
+	skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		ret = PTR_ERR(skb);
+		bt_dev_err(hdev, "HCI reset during shutdown failed");
+		return ret;
+	}
+	kfree_skb(skb);
+
 	/* Some platforms have an issue with BT LED when the interface is
 	 * down or BT radio is turned off, which takes 5 seconds to BT LED
 	 * goes off. This command turns off the BT LED immediately.
@@ -2371,8 +2390,7 @@ static int btusb_shutdown_intel(struct hci_dev *hdev)
 	skb = __hci_cmd_sync(hdev, 0xfc3f, 0, NULL, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		ret = PTR_ERR(skb);
-		BT_ERR("%s: turning off Intel device LED failed (%ld)",
-		       hdev->name, ret);
+		bt_dev_err(hdev, "turning off Intel device LED failed");
 		return ret;
 	}
 	kfree_skb(skb);
diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index 6a8d0d06aba7..8eede1197cd2 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -21,13 +21,18 @@
  *
  */
 
-#include <linux/kernel.h>
+#include <linux/acpi.h>
 #include <linux/errno.h>
+#include <linux/gpio/consumer.h>
+#include <linux/kernel.h>
+#include <linux/mod_devicetable.h>
+#include <linux/serdev.h>
 #include <linux/skbuff.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
 
+#include "btrtl.h"
 #include "hci_uart.h"
 
 #define HCI_3WIRE_ACK_PKT	0
@@ -65,6 +70,9 @@ enum {
 };
 
 struct h5 {
+	/* Must be the first member, hci_serdev.c expects this. */
+	struct hci_uart		serdev_hu;
+
 	struct sk_buff_head	unack;		/* Unack'ed packets queue */
 	struct sk_buff_head	rel;		/* Reliable packets queue */
 	struct sk_buff_head	unrel;		/* Unreliable packets queue */
@@ -95,6 +103,19 @@ struct h5 {
 		H5_SLEEPING,
 		H5_WAKING_UP,
 	} sleep;
+
+	const struct h5_vnd *vnd;
+	const char *id;
+
+	struct gpio_desc *enable_gpio;
+	struct gpio_desc *device_wake_gpio;
+};
+
+struct h5_vnd {
+	int (*setup)(struct h5 *h5);
+	void (*open)(struct h5 *h5);
+	void (*close)(struct h5 *h5);
+	const struct acpi_gpio_mapping *acpi_gpio_map;
 };
 
 static void h5_reset_rx(struct h5 *h5);
@@ -193,9 +214,13 @@ static int h5_open(struct hci_uart *hu)
 
 	BT_DBG("hu %p", hu);
 
-	h5 = kzalloc(sizeof(*h5), GFP_KERNEL);
-	if (!h5)
-		return -ENOMEM;
+	if (hu->serdev) {
+		h5 = serdev_device_get_drvdata(hu->serdev);
+	} else {
+		h5 = kzalloc(sizeof(*h5), GFP_KERNEL);
+		if (!h5)
+			return -ENOMEM;
+	}
 
 	hu->priv = h5;
 	h5->hu = hu;
@@ -210,6 +235,9 @@ static int h5_open(struct hci_uart *hu)
 
 	h5->tx_win = H5_TX_WIN_MAX;
 
+	if (h5->vnd && h5->vnd->open)
+		h5->vnd->open(h5);
+
 	set_bit(HCI_UART_INIT_PENDING, &hu->hdev_flags);
 
 	/* Send initial sync request */
@@ -229,7 +257,21 @@ static int h5_close(struct hci_uart *hu)
 	skb_queue_purge(&h5->rel);
 	skb_queue_purge(&h5->unrel);
 
-	kfree(h5);
+	if (h5->vnd && h5->vnd->close)
+		h5->vnd->close(h5);
+
+	if (!hu->serdev)
+		kfree(h5);
+
+	return 0;
+}
+
+static int h5_setup(struct hci_uart *hu)
+{
+	struct h5 *h5 = hu->priv;
+
+	if (h5->vnd && h5->vnd->setup)
+		return h5->vnd->setup(h5);
 
 	return 0;
 }
@@ -744,18 +786,172 @@ static const struct hci_uart_proto h5p = {
 	.name		= "Three-wire (H5)",
 	.open		= h5_open,
 	.close		= h5_close,
+	.setup		= h5_setup,
 	.recv		= h5_recv,
 	.enqueue	= h5_enqueue,
 	.dequeue	= h5_dequeue,
 	.flush		= h5_flush,
 };
 
+static int h5_serdev_probe(struct serdev_device *serdev)
+{
+	const struct acpi_device_id *match;
+	struct device *dev = &serdev->dev;
+	struct h5 *h5;
+
+	h5 = devm_kzalloc(dev, sizeof(*h5), GFP_KERNEL);
+	if (!h5)
+		return -ENOMEM;
+
+	set_bit(HCI_UART_RESET_ON_INIT, &h5->serdev_hu.flags);
+
+	h5->hu = &h5->serdev_hu;
+	h5->serdev_hu.serdev = serdev;
+	serdev_device_set_drvdata(serdev, h5);
+
+	if (has_acpi_companion(dev)) {
+		match = acpi_match_device(dev->driver->acpi_match_table, dev);
+		if (!match)
+			return -ENODEV;
+
+		h5->vnd = (const struct h5_vnd *)match->driver_data;
+		h5->id  = (char *)match->id;
+
+		if (h5->vnd->acpi_gpio_map)
+			devm_acpi_dev_add_driver_gpios(dev,
+						       h5->vnd->acpi_gpio_map);
+	}
+
+	h5->enable_gpio = devm_gpiod_get_optional(dev, "enable", GPIOD_OUT_LOW);
+	if (IS_ERR(h5->enable_gpio))
+		return PTR_ERR(h5->enable_gpio);
+
+	h5->device_wake_gpio = devm_gpiod_get_optional(dev, "device-wake",
+						       GPIOD_OUT_LOW);
+	if (IS_ERR(h5->device_wake_gpio))
+		return PTR_ERR(h5->device_wake_gpio);
+
+	return hci_uart_register_device(&h5->serdev_hu, &h5p);
+}
+
+static void h5_serdev_remove(struct serdev_device *serdev)
+{
+	struct h5 *h5 = serdev_device_get_drvdata(serdev);
+
+	hci_uart_unregister_device(&h5->serdev_hu);
+}
+
+#ifdef CONFIG_BT_HCIUART_RTL
+static int h5_btrtl_setup(struct h5 *h5)
+{
+	struct btrtl_device_info *btrtl_dev;
+	struct sk_buff *skb;
+	__le32 baudrate_data;
+	u32 device_baudrate;
+	unsigned int controller_baudrate;
+	bool flow_control;
+	int err;
+
+	btrtl_dev = btrtl_initialize(h5->hu->hdev, h5->id);
+	if (IS_ERR(btrtl_dev))
+		return PTR_ERR(btrtl_dev);
+
+	err = btrtl_get_uart_settings(h5->hu->hdev, btrtl_dev,
+				      &controller_baudrate, &device_baudrate,
+				      &flow_control);
+	if (err)
+		goto out_free;
+
+	baudrate_data = cpu_to_le32(device_baudrate);
+	skb = __hci_cmd_sync(h5->hu->hdev, 0xfc17, sizeof(baudrate_data),
+			     &baudrate_data, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		rtl_dev_err(h5->hu->hdev, "set baud rate command failed\n");
+		err = PTR_ERR(skb);
+		goto out_free;
+	} else {
+		kfree_skb(skb);
+	}
+	/* Give the device some time to set up the new baudrate. */
+	usleep_range(10000, 20000);
+
+	serdev_device_set_baudrate(h5->hu->serdev, controller_baudrate);
+	serdev_device_set_flow_control(h5->hu->serdev, flow_control);
+
+	err = btrtl_download_firmware(h5->hu->hdev, btrtl_dev);
+	/* Give the device some time before the hci-core sends it a reset */
+	usleep_range(10000, 20000);
+
+out_free:
+	btrtl_free(btrtl_dev);
+
+	return err;
+}
+
+static void h5_btrtl_open(struct h5 *h5)
+{
+	/* Devices always start with these fixed parameters */
+	serdev_device_set_flow_control(h5->hu->serdev, false);
+	serdev_device_set_parity(h5->hu->serdev, SERDEV_PARITY_EVEN);
+	serdev_device_set_baudrate(h5->hu->serdev, 115200);
+
+	/* The controller needs up to 500ms to wakeup */
+	gpiod_set_value_cansleep(h5->enable_gpio, 1);
+	gpiod_set_value_cansleep(h5->device_wake_gpio, 1);
+	msleep(500);
+}
+
+static void h5_btrtl_close(struct h5 *h5)
+{
+	gpiod_set_value_cansleep(h5->device_wake_gpio, 0);
+	gpiod_set_value_cansleep(h5->enable_gpio, 0);
+}
+
+static const struct acpi_gpio_params btrtl_device_wake_gpios = { 0, 0, false };
+static const struct acpi_gpio_params btrtl_enable_gpios = { 1, 0, false };
+static const struct acpi_gpio_params btrtl_host_wake_gpios = { 2, 0, false };
+static const struct acpi_gpio_mapping acpi_btrtl_gpios[] = {
+	{ "device-wake-gpios", &btrtl_device_wake_gpios, 1 },
+	{ "enable-gpios", &btrtl_enable_gpios, 1 },
+	{ "host-wake-gpios", &btrtl_host_wake_gpios, 1 },
+	{},
+};
+
+static struct h5_vnd rtl_vnd = {
+	.setup		= h5_btrtl_setup,
+	.open		= h5_btrtl_open,
+	.close		= h5_btrtl_close,
+	.acpi_gpio_map	= acpi_btrtl_gpios,
+};
+#endif
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id h5_acpi_match[] = {
+#ifdef CONFIG_BT_HCIUART_RTL
+	{ "OBDA8723", (kernel_ulong_t)&rtl_vnd },
+#endif
+	{ },
+};
+MODULE_DEVICE_TABLE(acpi, h5_acpi_match);
+#endif
+
+static struct serdev_device_driver h5_serdev_driver = {
+	.probe = h5_serdev_probe,
+	.remove = h5_serdev_remove,
+	.driver = {
+		.name = "hci_uart_h5",
+		.acpi_match_table = ACPI_PTR(h5_acpi_match),
+	},
+};
+
 int __init h5_init(void)
 {
+	serdev_device_driver_register(&h5_serdev_driver);
 	return hci_uart_register_proto(&h5p);
 }
 
 int __exit h5_deinit(void)
 {
+	serdev_device_driver_unregister(&h5_serdev_driver);
 	return hci_uart_unregister_proto(&h5p);
 }
diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c
index 7c166e3b308b..46ace321bf60 100644
--- a/drivers/bluetooth/hci_intel.c
+++ b/drivers/bluetooth/hci_intel.c
@@ -458,7 +458,7 @@ static int inject_cmd_complete(struct hci_dev *hdev, __u16 opcode)
 	struct hci_event_hdr *hdr;
 	struct hci_ev_cmd_complete *evt;
 
-	skb = bt_skb_alloc(sizeof(*hdr) + sizeof(*evt) + 1, GFP_ATOMIC);
+	skb = bt_skb_alloc(sizeof(*hdr) + sizeof(*evt) + 1, GFP_KERNEL);
 	if (!skb)
 		return -ENOMEM;
 
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 51790dd02afb..e182f6019f68 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -5,7 +5,7 @@
  *  protocol extension to H4.
  *
  *  Copyright (C) 2007 Texas Instruments, Inc.
- *  Copyright (c) 2010, 2012 The Linux Foundation. All rights reserved.
+ *  Copyright (c) 2010, 2012, 2018 The Linux Foundation. All rights reserved.
  *
  *  Acknowledgements:
  *  This file is based on hci_ll.c, which was...
@@ -31,9 +31,14 @@
 #include <linux/kernel.h>
 #include <linux/clk.h>
 #include <linux/debugfs.h>
+#include <linux/delay.h>
+#include <linux/device.h>
 #include <linux/gpio/consumer.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
 #include <linux/serdev.h>
 
 #include <net/bluetooth/bluetooth.h>
@@ -119,12 +124,51 @@ struct qca_data {
 	u64 votes_off;
 };
 
+enum qca_speed_type {
+	QCA_INIT_SPEED = 1,
+	QCA_OPER_SPEED
+};
+
+/*
+ * Voltage regulator information required for configuring the
+ * QCA Bluetooth chipset
+ */
+struct qca_vreg {
+	const char *name;
+	unsigned int min_uV;
+	unsigned int max_uV;
+	unsigned int load_uA;
+};
+
+struct qca_vreg_data {
+	enum qca_btsoc_type soc_type;
+	struct qca_vreg *vregs;
+	size_t num_vregs;
+};
+
+/*
+ * Platform data for the QCA Bluetooth power driver.
+ */
+struct qca_power {
+	struct device *dev;
+	const struct qca_vreg_data *vreg_data;
+	struct regulator_bulk_data *vreg_bulk;
+	bool vregs_on;
+};
+
 struct qca_serdev {
 	struct hci_uart	 serdev_hu;
 	struct gpio_desc *bt_en;
 	struct clk	 *susclk;
+	enum qca_btsoc_type btsoc_type;
+	struct qca_power *bt_power;
+	u32 init_speed;
+	u32 oper_speed;
 };
 
+static int qca_power_setup(struct hci_uart *hu, bool on);
+static void qca_power_shutdown(struct hci_dev *hdev);
+
 static void __serial_clock_on(struct tty_struct *tty)
 {
 	/* TODO: Some chipset requires to enable UART clock on client
@@ -402,10 +446,11 @@ static int qca_open(struct hci_uart *hu)
 {
 	struct qca_serdev *qcadev;
 	struct qca_data *qca;
+	int ret;
 
 	BT_DBG("hu %p qca_open", hu);
 
-	qca = kzalloc(sizeof(struct qca_data), GFP_ATOMIC);
+	qca = kzalloc(sizeof(struct qca_data), GFP_KERNEL);
 	if (!qca)
 		return -ENOMEM;
 
@@ -453,19 +498,32 @@ static int qca_open(struct hci_uart *hu)
 
 	hu->priv = qca;
 
-	timer_setup(&qca->wake_retrans_timer, hci_ibs_wake_retrans_timeout, 0);
-	qca->wake_retrans = IBS_WAKE_RETRANS_TIMEOUT_MS;
-
-	timer_setup(&qca->tx_idle_timer, hci_ibs_tx_idle_timeout, 0);
-	qca->tx_idle_delay = IBS_TX_IDLE_TIMEOUT_MS;
-
 	if (hu->serdev) {
 		serdev_device_open(hu->serdev);
 
 		qcadev = serdev_device_get_drvdata(hu->serdev);
-		gpiod_set_value_cansleep(qcadev->bt_en, 1);
+		if (qcadev->btsoc_type != QCA_WCN3990) {
+			gpiod_set_value_cansleep(qcadev->bt_en, 1);
+		} else {
+			hu->init_speed = qcadev->init_speed;
+			hu->oper_speed = qcadev->oper_speed;
+			ret = qca_power_setup(hu, true);
+			if (ret) {
+				destroy_workqueue(qca->workqueue);
+				kfree_skb(qca->rx_skb);
+				hu->priv = NULL;
+				kfree(qca);
+				return ret;
+			}
+		}
 	}
 
+	timer_setup(&qca->wake_retrans_timer, hci_ibs_wake_retrans_timeout, 0);
+	qca->wake_retrans = IBS_WAKE_RETRANS_TIMEOUT_MS;
+
+	timer_setup(&qca->tx_idle_timer, hci_ibs_tx_idle_timeout, 0);
+	qca->tx_idle_delay = IBS_TX_IDLE_TIMEOUT_MS;
+
 	BT_DBG("HCI_UART_QCA open, tx_idle_delay=%u, wake_retrans=%u",
 	       qca->tx_idle_delay, qca->wake_retrans);
 
@@ -549,10 +607,13 @@ static int qca_close(struct hci_uart *hu)
 	qca->hu = NULL;
 
 	if (hu->serdev) {
-		serdev_device_close(hu->serdev);
-
 		qcadev = serdev_device_get_drvdata(hu->serdev);
-		gpiod_set_value_cansleep(qcadev->bt_en, 0);
+		if (qcadev->btsoc_type == QCA_WCN3990)
+			qca_power_shutdown(hu->hdev);
+		else
+			gpiod_set_value_cansleep(qcadev->bt_en, 0);
+
+		serdev_device_close(hu->serdev);
 	}
 
 	kfree_skb(qca->rx_skb);
@@ -872,6 +933,8 @@ static uint8_t qca_get_baudrate_value(int speed)
 		return QCA_BAUDRATE_2000000;
 	case 3000000:
 		return QCA_BAUDRATE_3000000;
+	case 3200000:
+		return QCA_BAUDRATE_3200000;
 	case 3500000:
 		return QCA_BAUDRATE_3500000;
 	default:
@@ -884,19 +947,27 @@ static int qca_set_baudrate(struct hci_dev *hdev, uint8_t baudrate)
 	struct hci_uart *hu = hci_get_drvdata(hdev);
 	struct qca_data *qca = hu->priv;
 	struct sk_buff *skb;
+	struct qca_serdev *qcadev;
 	u8 cmd[] = { 0x01, 0x48, 0xFC, 0x01, 0x00 };
 
-	if (baudrate > QCA_BAUDRATE_3000000)
+	if (baudrate > QCA_BAUDRATE_3200000)
 		return -EINVAL;
 
 	cmd[4] = baudrate;
 
-	skb = bt_skb_alloc(sizeof(cmd), GFP_ATOMIC);
+	skb = bt_skb_alloc(sizeof(cmd), GFP_KERNEL);
 	if (!skb) {
 		bt_dev_err(hdev, "Failed to allocate baudrate packet");
 		return -ENOMEM;
 	}
 
+	/* Disabling hardware flow control is mandatory while
+	 * sending change baudrate request to wcn3990 SoC.
+	 */
+	qcadev = serdev_device_get_drvdata(hu->serdev);
+	if (qcadev->btsoc_type == QCA_WCN3990)
+		hci_uart_set_flow_control(hu, true);
+
 	/* Assign commands to change baudrate and packet type. */
 	skb_put_data(skb, cmd, sizeof(cmd));
 	hci_skb_pkt_type(skb) = HCI_COMMAND_PKT;
@@ -912,6 +983,9 @@ static int qca_set_baudrate(struct hci_dev *hdev, uint8_t baudrate)
 	schedule_timeout(msecs_to_jiffies(BAUDRATE_SETTLE_TIMEOUT_MS));
 	set_current_state(TASK_RUNNING);
 
+	if (qcadev->btsoc_type == QCA_WCN3990)
+		hci_uart_set_flow_control(hu, false);
+
 	return 0;
 }
 
@@ -923,50 +997,195 @@ static inline void host_set_baudrate(struct hci_uart *hu, unsigned int speed)
 		hci_uart_set_baudrate(hu, speed);
 }
 
+static int qca_send_power_pulse(struct hci_dev *hdev, u8 cmd)
+{
+	struct hci_uart *hu = hci_get_drvdata(hdev);
+	struct qca_data *qca = hu->priv;
+	struct sk_buff *skb;
+
+	/* These power pulses are single byte command which are sent
+	 * at required baudrate to wcn3990. On wcn3990, we have an external
+	 * circuit at Tx pin which decodes the pulse sent at specific baudrate.
+	 * For example, wcn3990 supports RF COEX antenna for both Wi-Fi/BT
+	 * and also we use the same power inputs to turn on and off for
+	 * Wi-Fi/BT. Powering up the power sources will not enable BT, until
+	 * we send a power on pulse at 115200 bps. This algorithm will help to
+	 * save power. Disabling hardware flow control is mandatory while
+	 * sending power pulses to SoC.
+	 */
+	bt_dev_dbg(hdev, "sending power pulse %02x to SoC", cmd);
+
+	skb = bt_skb_alloc(sizeof(cmd), GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	hci_uart_set_flow_control(hu, true);
+
+	skb_put_u8(skb, cmd);
+	hci_skb_pkt_type(skb) = HCI_COMMAND_PKT;
+
+	skb_queue_tail(&qca->txq, skb);
+	hci_uart_tx_wakeup(hu);
+
+	/* Wait for 100 uS for SoC to settle down */
+	usleep_range(100, 200);
+	hci_uart_set_flow_control(hu, false);
+
+	return 0;
+}
+
+static unsigned int qca_get_speed(struct hci_uart *hu,
+				  enum qca_speed_type speed_type)
+{
+	unsigned int speed = 0;
+
+	if (speed_type == QCA_INIT_SPEED) {
+		if (hu->init_speed)
+			speed = hu->init_speed;
+		else if (hu->proto->init_speed)
+			speed = hu->proto->init_speed;
+	} else {
+		if (hu->oper_speed)
+			speed = hu->oper_speed;
+		else if (hu->proto->oper_speed)
+			speed = hu->proto->oper_speed;
+	}
+
+	return speed;
+}
+
+static int qca_check_speeds(struct hci_uart *hu)
+{
+	struct qca_serdev *qcadev;
+
+	qcadev = serdev_device_get_drvdata(hu->serdev);
+	if (qcadev->btsoc_type == QCA_WCN3990) {
+		if (!qca_get_speed(hu, QCA_INIT_SPEED) &&
+		    !qca_get_speed(hu, QCA_OPER_SPEED))
+			return -EINVAL;
+	} else {
+		if (!qca_get_speed(hu, QCA_INIT_SPEED) ||
+		    !qca_get_speed(hu, QCA_OPER_SPEED))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int qca_set_speed(struct hci_uart *hu, enum qca_speed_type speed_type)
+{
+	unsigned int speed, qca_baudrate;
+	int ret;
+
+	if (speed_type == QCA_INIT_SPEED) {
+		speed = qca_get_speed(hu, QCA_INIT_SPEED);
+		if (speed)
+			host_set_baudrate(hu, speed);
+	} else {
+		speed = qca_get_speed(hu, QCA_OPER_SPEED);
+		if (!speed)
+			return 0;
+
+		qca_baudrate = qca_get_baudrate_value(speed);
+		bt_dev_dbg(hu->hdev, "Set UART speed to %d", speed);
+		ret = qca_set_baudrate(hu->hdev, qca_baudrate);
+		if (ret)
+			return ret;
+
+		host_set_baudrate(hu, speed);
+	}
+
+	return 0;
+}
+
+static int qca_wcn3990_init(struct hci_uart *hu)
+{
+	struct hci_dev *hdev = hu->hdev;
+	int ret;
+
+	/* Forcefully enable wcn3990 to enter in to boot mode. */
+	host_set_baudrate(hu, 2400);
+	ret = qca_send_power_pulse(hdev, QCA_WCN3990_POWEROFF_PULSE);
+	if (ret)
+		return ret;
+
+	qca_set_speed(hu, QCA_INIT_SPEED);
+	ret = qca_send_power_pulse(hdev, QCA_WCN3990_POWERON_PULSE);
+	if (ret)
+		return ret;
+
+	/* Wait for 100 ms for SoC to boot */
+	msleep(100);
+
+	/* Now the device is in ready state to communicate with host.
+	 * To sync host with device we need to reopen port.
+	 * Without this, we will have RTS and CTS synchronization
+	 * issues.
+	 */
+	serdev_device_close(hu->serdev);
+	ret = serdev_device_open(hu->serdev);
+	if (ret) {
+		bt_dev_err(hu->hdev, "failed to open port");
+		return ret;
+	}
+
+	hci_uart_set_flow_control(hu, false);
+
+	return 0;
+}
+
 static int qca_setup(struct hci_uart *hu)
 {
 	struct hci_dev *hdev = hu->hdev;
 	struct qca_data *qca = hu->priv;
 	unsigned int speed, qca_baudrate = QCA_BAUDRATE_115200;
+	struct qca_serdev *qcadev;
 	int ret;
+	int soc_ver = 0;
+
+	qcadev = serdev_device_get_drvdata(hu->serdev);
 
-	bt_dev_info(hdev, "ROME setup");
+	ret = qca_check_speeds(hu);
+	if (ret)
+		return ret;
 
 	/* Patch downloading has to be done without IBS mode */
 	clear_bit(STATE_IN_BAND_SLEEP_ENABLED, &qca->flags);
 
-	/* Setup initial baudrate */
-	speed = 0;
-	if (hu->init_speed)
-		speed = hu->init_speed;
-	else if (hu->proto->init_speed)
-		speed = hu->proto->init_speed;
+	if (qcadev->btsoc_type == QCA_WCN3990) {
+		bt_dev_info(hdev, "setting up wcn3990");
+		ret = qca_wcn3990_init(hu);
+		if (ret)
+			return ret;
 
-	if (speed)
-		host_set_baudrate(hu, speed);
+		ret = qca_read_soc_version(hdev, &soc_ver);
+		if (ret)
+			return ret;
+	} else {
+		bt_dev_info(hdev, "ROME setup");
+		qca_set_speed(hu, QCA_INIT_SPEED);
+	}
 
 	/* Setup user speed if needed */
-	speed = 0;
-	if (hu->oper_speed)
-		speed = hu->oper_speed;
-	else if (hu->proto->oper_speed)
-		speed = hu->proto->oper_speed;
-
+	speed = qca_get_speed(hu, QCA_OPER_SPEED);
 	if (speed) {
+		ret = qca_set_speed(hu, QCA_OPER_SPEED);
+		if (ret)
+			return ret;
+
 		qca_baudrate = qca_get_baudrate_value(speed);
+	}
 
-		bt_dev_info(hdev, "Set UART speed to %d", speed);
-		ret = qca_set_baudrate(hdev, qca_baudrate);
-		if (ret) {
-			bt_dev_err(hdev, "Failed to change the baud rate (%d)",
-				   ret);
+	if (qcadev->btsoc_type != QCA_WCN3990) {
+		/* Get QCA version information */
+		ret = qca_read_soc_version(hdev, &soc_ver);
+		if (ret)
 			return ret;
-		}
-		host_set_baudrate(hu, speed);
 	}
 
+	bt_dev_info(hdev, "QCA controller version 0x%08x", soc_ver);
 	/* Setup patch / NVM configurations */
-	ret = qca_uart_setup_rome(hdev, qca_baudrate);
+	ret = qca_uart_setup(hdev, qca_baudrate, qcadev->btsoc_type, soc_ver);
 	if (!ret) {
 		set_bit(STATE_IN_BAND_SLEEP_ENABLED, &qca->flags);
 		qca_debugfs_init(hdev);
@@ -1002,9 +1221,123 @@ static struct hci_uart_proto qca_proto = {
 	.dequeue	= qca_dequeue,
 };
 
+static const struct qca_vreg_data qca_soc_data = {
+	.soc_type = QCA_WCN3990,
+	.vregs = (struct qca_vreg []) {
+		{ "vddio",   1800000, 1900000,  15000  },
+		{ "vddxo",   1800000, 1900000,  80000  },
+		{ "vddrf",   1300000, 1350000,  300000 },
+		{ "vddch0",  3300000, 3400000,  450000 },
+	},
+	.num_vregs = 4,
+};
+
+static void qca_power_shutdown(struct hci_dev *hdev)
+{
+	struct hci_uart *hu = hci_get_drvdata(hdev);
+
+	host_set_baudrate(hu, 2400);
+	qca_send_power_pulse(hdev, QCA_WCN3990_POWEROFF_PULSE);
+	qca_power_setup(hu, false);
+}
+
+static int qca_enable_regulator(struct qca_vreg vregs,
+				struct regulator *regulator)
+{
+	int ret;
+
+	ret = regulator_set_voltage(regulator, vregs.min_uV,
+				    vregs.max_uV);
+	if (ret)
+		return ret;
+
+	if (vregs.load_uA)
+		ret = regulator_set_load(regulator,
+					 vregs.load_uA);
+
+	if (ret)
+		return ret;
+
+	return regulator_enable(regulator);
+
+}
+
+static void qca_disable_regulator(struct qca_vreg vregs,
+				  struct regulator *regulator)
+{
+	regulator_disable(regulator);
+	regulator_set_voltage(regulator, 0, vregs.max_uV);
+	if (vregs.load_uA)
+		regulator_set_load(regulator, 0);
+
+}
+
+static int qca_power_setup(struct hci_uart *hu, bool on)
+{
+	struct qca_vreg *vregs;
+	struct regulator_bulk_data *vreg_bulk;
+	struct qca_serdev *qcadev;
+	int i, num_vregs, ret = 0;
+
+	qcadev = serdev_device_get_drvdata(hu->serdev);
+	if (!qcadev || !qcadev->bt_power || !qcadev->bt_power->vreg_data ||
+	    !qcadev->bt_power->vreg_bulk)
+		return -EINVAL;
+
+	vregs = qcadev->bt_power->vreg_data->vregs;
+	vreg_bulk = qcadev->bt_power->vreg_bulk;
+	num_vregs = qcadev->bt_power->vreg_data->num_vregs;
+	BT_DBG("on: %d", on);
+	if (on && !qcadev->bt_power->vregs_on) {
+		for (i = 0; i < num_vregs; i++) {
+			ret = qca_enable_regulator(vregs[i],
+						   vreg_bulk[i].consumer);
+			if (ret)
+				break;
+		}
+
+		if (ret) {
+			BT_ERR("failed to enable regulator:%s", vregs[i].name);
+			/* turn off regulators which are enabled */
+			for (i = i - 1; i >= 0; i--)
+				qca_disable_regulator(vregs[i],
+						      vreg_bulk[i].consumer);
+		} else {
+			qcadev->bt_power->vregs_on = true;
+		}
+	} else if (!on && qcadev->bt_power->vregs_on) {
+		/* turn off regulator in reverse order */
+		i = qcadev->bt_power->vreg_data->num_vregs - 1;
+		for ( ; i >= 0; i--)
+			qca_disable_regulator(vregs[i], vreg_bulk[i].consumer);
+
+		qcadev->bt_power->vregs_on = false;
+	}
+
+	return ret;
+}
+
+static int qca_init_regulators(struct qca_power *qca,
+				const struct qca_vreg *vregs, size_t num_vregs)
+{
+	int i;
+
+	qca->vreg_bulk = devm_kzalloc(qca->dev, num_vregs *
+				      sizeof(struct regulator_bulk_data),
+				      GFP_KERNEL);
+	if (!qca->vreg_bulk)
+		return -ENOMEM;
+
+	for (i = 0; i < num_vregs; i++)
+		qca->vreg_bulk[i].supply = vregs[i].name;
+
+	return devm_regulator_bulk_get(qca->dev, num_vregs, qca->vreg_bulk);
+}
+
 static int qca_serdev_probe(struct serdev_device *serdev)
 {
 	struct qca_serdev *qcadev;
+	const struct qca_vreg_data *data;
 	int err;
 
 	qcadev = devm_kzalloc(&serdev->dev, sizeof(*qcadev), GFP_KERNEL);
@@ -1012,47 +1345,84 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 		return -ENOMEM;
 
 	qcadev->serdev_hu.serdev = serdev;
+	data = of_device_get_match_data(&serdev->dev);
 	serdev_device_set_drvdata(serdev, qcadev);
+	if (data && data->soc_type == QCA_WCN3990) {
+		qcadev->btsoc_type = QCA_WCN3990;
+		qcadev->bt_power = devm_kzalloc(&serdev->dev,
+						sizeof(struct qca_power),
+						GFP_KERNEL);
+		if (!qcadev->bt_power)
+			return -ENOMEM;
+
+		qcadev->bt_power->dev = &serdev->dev;
+		qcadev->bt_power->vreg_data = data;
+		err = qca_init_regulators(qcadev->bt_power, data->vregs,
+					  data->num_vregs);
+		if (err) {
+			BT_ERR("Failed to init regulators:%d", err);
+			goto out;
+		}
 
-	qcadev->bt_en = devm_gpiod_get(&serdev->dev, "enable",
-				       GPIOD_OUT_LOW);
-	if (IS_ERR(qcadev->bt_en)) {
-		dev_err(&serdev->dev, "failed to acquire enable gpio\n");
-		return PTR_ERR(qcadev->bt_en);
-	}
+		qcadev->bt_power->vregs_on = false;
 
-	qcadev->susclk = devm_clk_get(&serdev->dev, NULL);
-	if (IS_ERR(qcadev->susclk)) {
-		dev_err(&serdev->dev, "failed to acquire clk\n");
-		return PTR_ERR(qcadev->susclk);
-	}
+		device_property_read_u32(&serdev->dev, "max-speed",
+					 &qcadev->oper_speed);
+		if (!qcadev->oper_speed)
+			BT_DBG("UART will pick default operating speed");
 
-	err = clk_set_rate(qcadev->susclk, SUSCLK_RATE_32KHZ);
-	if (err)
-		return err;
+		err = hci_uart_register_device(&qcadev->serdev_hu, &qca_proto);
+		if (err) {
+			BT_ERR("wcn3990 serdev registration failed");
+			goto out;
+		}
+	} else {
+		qcadev->btsoc_type = QCA_ROME;
+		qcadev->bt_en = devm_gpiod_get(&serdev->dev, "enable",
+					       GPIOD_OUT_LOW);
+		if (IS_ERR(qcadev->bt_en)) {
+			dev_err(&serdev->dev, "failed to acquire enable gpio\n");
+			return PTR_ERR(qcadev->bt_en);
+		}
 
-	err = clk_prepare_enable(qcadev->susclk);
-	if (err)
-		return err;
+		qcadev->susclk = devm_clk_get(&serdev->dev, NULL);
+		if (IS_ERR(qcadev->susclk)) {
+			dev_err(&serdev->dev, "failed to acquire clk\n");
+			return PTR_ERR(qcadev->susclk);
+		}
 
-	err = hci_uart_register_device(&qcadev->serdev_hu, &qca_proto);
-	if (err)
-		clk_disable_unprepare(qcadev->susclk);
+		err = clk_set_rate(qcadev->susclk, SUSCLK_RATE_32KHZ);
+		if (err)
+			return err;
+
+		err = clk_prepare_enable(qcadev->susclk);
+		if (err)
+			return err;
+
+		err = hci_uart_register_device(&qcadev->serdev_hu, &qca_proto);
+		if (err)
+			clk_disable_unprepare(qcadev->susclk);
+	}
+
+out:	return err;
 
-	return err;
 }
 
 static void qca_serdev_remove(struct serdev_device *serdev)
 {
 	struct qca_serdev *qcadev = serdev_device_get_drvdata(serdev);
 
-	hci_uart_unregister_device(&qcadev->serdev_hu);
+	if (qcadev->btsoc_type == QCA_WCN3990)
+		qca_power_shutdown(qcadev->serdev_hu.hdev);
+	else
+		clk_disable_unprepare(qcadev->susclk);
 
-	clk_disable_unprepare(qcadev->susclk);
+	hci_uart_unregister_device(&qcadev->serdev_hu);
 }
 
 static const struct of_device_id qca_bluetooth_of_match[] = {
 	{ .compatible = "qcom,qca6174-bt" },
+	{ .compatible = "qcom,wcn3990-bt", .data = &qca_soc_data},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, qca_bluetooth_of_match);
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index a78b8e7085e9..113fc6edb2b0 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -282,6 +282,7 @@
 #include <linux/blkdev.h>
 #include <linux/times.h>
 #include <linux/uaccess.h>
+#include <scsi/scsi_common.h>
 #include <scsi/scsi_request.h>
 
 /* used to tell the module to turn on full debugging messages */
@@ -345,10 +346,10 @@ static LIST_HEAD(cdrom_list);
 int cdrom_dummy_generic_packet(struct cdrom_device_info *cdi,
 			       struct packet_command *cgc)
 {
-	if (cgc->sense) {
-		cgc->sense->sense_key = 0x05;
-		cgc->sense->asc = 0x20;
-		cgc->sense->ascq = 0x00;
+	if (cgc->sshdr) {
+		cgc->sshdr->sense_key = 0x05;
+		cgc->sshdr->asc = 0x20;
+		cgc->sshdr->ascq = 0x00;
 	}
 
 	cgc->stat = -EIO;
@@ -2222,9 +2223,12 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 
 		blk_execute_rq(q, cdi->disk, rq, 0);
 		if (scsi_req(rq)->result) {
-			struct request_sense *s = req->sense;
+			struct scsi_sense_hdr sshdr;
+
 			ret = -EIO;
-			cdi->last_sense = s->sense_key;
+			scsi_normalize_sense(req->sense, req->sense_len,
+					     &sshdr);
+			cdi->last_sense = sshdr.sense_key;
 		}
 
 		if (blk_rq_unmap_user(bio))
@@ -2943,7 +2947,7 @@ static noinline int mmc_ioctl_cdrom_read_data(struct cdrom_device_info *cdi,
 					      struct packet_command *cgc,
 					      int cmd)
 {
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	struct cdrom_msf msf;
 	int blocksize = 0, format = 0, lba;
 	int ret;
@@ -2971,13 +2975,13 @@ static noinline int mmc_ioctl_cdrom_read_data(struct cdrom_device_info *cdi,
 	if (cgc->buffer == NULL)
 		return -ENOMEM;
 
-	memset(&sense, 0, sizeof(sense));
-	cgc->sense = &sense;
+	memset(&sshdr, 0, sizeof(sshdr));
+	cgc->sshdr = &sshdr;
 	cgc->data_direction = CGC_DATA_READ;
 	ret = cdrom_read_block(cdi, cgc, lba, 1, format, blocksize);
-	if (ret && sense.sense_key == 0x05 &&
-	    sense.asc == 0x20 &&
-	    sense.ascq == 0x00) {
+	if (ret && sshdr.sense_key == 0x05 &&
+	    sshdr.asc == 0x20 &&
+	    sshdr.ascq == 0x00) {
 		/*
 		 * SCSI-II devices are not required to support
 		 * READ_CD, so let's try switching block size
@@ -2986,7 +2990,7 @@ static noinline int mmc_ioctl_cdrom_read_data(struct cdrom_device_info *cdi,
 		ret = cdrom_switch_blocksize(cdi, blocksize);
 		if (ret)
 			goto out;
-		cgc->sense = NULL;
+		cgc->sshdr = NULL;
 		ret = cdrom_read_cd(cdi, cgc, lba, blocksize, 1);
 		ret |= cdrom_switch_blocksize(cdi, blocksize);
 	}
diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
index 212f447938ae..ce277ee0a28a 100644
--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@@ -554,3 +554,17 @@ config ADI
 
 endmenu
 
+config RANDOM_TRUST_CPU
+	bool "Trust the CPU manufacturer to initialize Linux's CRNG"
+	depends on X86 || S390 || PPC
+	default n
+	help
+	Assume that CPU manufacturer (e.g., Intel or AMD for RDSEED or
+	RDRAND, IBM for the S390 and Power PC architectures) is trustworthy
+	for the purposes of initializing Linux's CRNG.  Since this is not
+	something that can be independently audited, this amounts to trusting
+	that CPU manufacturer (perhaps with the insistence or mandate
+	of a Nation State's intelligence or law enforcement agencies)
+	has not installed a hidden back door to compromise the CPU's
+	random number generation facilities.
+
diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig
index c34b257d852d..dac895dc01b9 100644
--- a/drivers/char/hw_random/Kconfig
+++ b/drivers/char/hw_random/Kconfig
@@ -307,19 +307,6 @@ config HW_RANDOM_HISI
 
 	  If unsure, say Y.
 
-config HW_RANDOM_MSM
-	tristate "Qualcomm SoCs Random Number Generator support"
-	depends on HW_RANDOM && ARCH_QCOM
-	default HW_RANDOM
-	---help---
-	  This driver provides kernel-side support for the Random Number
-	  Generator hardware found on Qualcomm SoCs.
-
-	  To compile this driver as a module, choose M here. the
-	  module will be called msm-rng.
-
-	  If unsure, say Y.
-
 config HW_RANDOM_ST
 	tristate "ST Microelectronics HW Random Number Generator support"
 	depends on HW_RANDOM && ARCH_STI
diff --git a/drivers/char/hw_random/Makefile b/drivers/char/hw_random/Makefile
index 533e913c93d1..e35ec3ce3a20 100644
--- a/drivers/char/hw_random/Makefile
+++ b/drivers/char/hw_random/Makefile
@@ -29,7 +29,6 @@ obj-$(CONFIG_HW_RANDOM_POWERNV) += powernv-rng.o
 obj-$(CONFIG_HW_RANDOM_HISI)	+= hisi-rng.o
 obj-$(CONFIG_HW_RANDOM_BCM2835) += bcm2835-rng.o
 obj-$(CONFIG_HW_RANDOM_IPROC_RNG200) += iproc-rng200.o
-obj-$(CONFIG_HW_RANDOM_MSM) += msm-rng.o
 obj-$(CONFIG_HW_RANDOM_ST) += st-rng.o
 obj-$(CONFIG_HW_RANDOM_XGENE) += xgene-rng.o
 obj-$(CONFIG_HW_RANDOM_STM32) += stm32-rng.o
diff --git a/drivers/char/hw_random/msm-rng.c b/drivers/char/hw_random/msm-rng.c
deleted file mode 100644
index 841fee845ec9..000000000000
--- a/drivers/char/hw_random/msm-rng.c
+++ /dev/null
@@ -1,183 +0,0 @@
-/*
- * Copyright (c) 2011-2013, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/hw_random.h>
-#include <linux/io.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
-
-/* Device specific register offsets */
-#define PRNG_DATA_OUT		0x0000
-#define PRNG_STATUS		0x0004
-#define PRNG_LFSR_CFG		0x0100
-#define PRNG_CONFIG		0x0104
-
-/* Device specific register masks and config values */
-#define PRNG_LFSR_CFG_MASK	0x0000ffff
-#define PRNG_LFSR_CFG_CLOCKS	0x0000dddd
-#define PRNG_CONFIG_HW_ENABLE	BIT(1)
-#define PRNG_STATUS_DATA_AVAIL	BIT(0)
-
-#define MAX_HW_FIFO_DEPTH	16
-#define MAX_HW_FIFO_SIZE	(MAX_HW_FIFO_DEPTH * 4)
-#define WORD_SZ			4
-
-struct msm_rng {
-	void __iomem *base;
-	struct clk *clk;
-	struct hwrng hwrng;
-};
-
-#define to_msm_rng(p)	container_of(p, struct msm_rng, hwrng)
-
-static int msm_rng_enable(struct hwrng *hwrng, int enable)
-{
-	struct msm_rng *rng = to_msm_rng(hwrng);
-	u32 val;
-	int ret;
-
-	ret = clk_prepare_enable(rng->clk);
-	if (ret)
-		return ret;
-
-	if (enable) {
-		/* Enable PRNG only if it is not already enabled */
-		val = readl_relaxed(rng->base + PRNG_CONFIG);
-		if (val & PRNG_CONFIG_HW_ENABLE)
-			goto already_enabled;
-
-		val = readl_relaxed(rng->base + PRNG_LFSR_CFG);
-		val &= ~PRNG_LFSR_CFG_MASK;
-		val |= PRNG_LFSR_CFG_CLOCKS;
-		writel(val, rng->base + PRNG_LFSR_CFG);
-
-		val = readl_relaxed(rng->base + PRNG_CONFIG);
-		val |= PRNG_CONFIG_HW_ENABLE;
-		writel(val, rng->base + PRNG_CONFIG);
-	} else {
-		val = readl_relaxed(rng->base + PRNG_CONFIG);
-		val &= ~PRNG_CONFIG_HW_ENABLE;
-		writel(val, rng->base + PRNG_CONFIG);
-	}
-
-already_enabled:
-	clk_disable_unprepare(rng->clk);
-	return 0;
-}
-
-static int msm_rng_read(struct hwrng *hwrng, void *data, size_t max, bool wait)
-{
-	struct msm_rng *rng = to_msm_rng(hwrng);
-	size_t currsize = 0;
-	u32 *retdata = data;
-	size_t maxsize;
-	int ret;
-	u32 val;
-
-	/* calculate max size bytes to transfer back to caller */
-	maxsize = min_t(size_t, MAX_HW_FIFO_SIZE, max);
-
-	ret = clk_prepare_enable(rng->clk);
-	if (ret)
-		return ret;
-
-	/* read random data from hardware */
-	do {
-		val = readl_relaxed(rng->base + PRNG_STATUS);
-		if (!(val & PRNG_STATUS_DATA_AVAIL))
-			break;
-
-		val = readl_relaxed(rng->base + PRNG_DATA_OUT);
-		if (!val)
-			break;
-
-		*retdata++ = val;
-		currsize += WORD_SZ;
-
-		/* make sure we stay on 32bit boundary */
-		if ((maxsize - currsize) < WORD_SZ)
-			break;
-	} while (currsize < maxsize);
-
-	clk_disable_unprepare(rng->clk);
-
-	return currsize;
-}
-
-static int msm_rng_init(struct hwrng *hwrng)
-{
-	return msm_rng_enable(hwrng, 1);
-}
-
-static void msm_rng_cleanup(struct hwrng *hwrng)
-{
-	msm_rng_enable(hwrng, 0);
-}
-
-static int msm_rng_probe(struct platform_device *pdev)
-{
-	struct resource *res;
-	struct msm_rng *rng;
-	int ret;
-
-	rng = devm_kzalloc(&pdev->dev, sizeof(*rng), GFP_KERNEL);
-	if (!rng)
-		return -ENOMEM;
-
-	platform_set_drvdata(pdev, rng);
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	rng->base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(rng->base))
-		return PTR_ERR(rng->base);
-
-	rng->clk = devm_clk_get(&pdev->dev, "core");
-	if (IS_ERR(rng->clk))
-		return PTR_ERR(rng->clk);
-
-	rng->hwrng.name = KBUILD_MODNAME,
-	rng->hwrng.init = msm_rng_init,
-	rng->hwrng.cleanup = msm_rng_cleanup,
-	rng->hwrng.read = msm_rng_read,
-
-	ret = devm_hwrng_register(&pdev->dev, &rng->hwrng);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to register hwrng\n");
-		return ret;
-	}
-
-	return 0;
-}
-
-static const struct of_device_id msm_rng_of_match[] = {
-	{ .compatible = "qcom,prng", },
-	{}
-};
-MODULE_DEVICE_TABLE(of, msm_rng_of_match);
-
-static struct platform_driver msm_rng_driver = {
-	.probe = msm_rng_probe,
-	.driver = {
-		.name = KBUILD_MODNAME,
-		.of_match_table = of_match_ptr(msm_rng_of_match),
-	}
-};
-module_platform_driver(msm_rng_driver);
-
-MODULE_ALIAS("platform:" KBUILD_MODNAME);
-MODULE_AUTHOR("The Linux Foundation");
-MODULE_DESCRIPTION("Qualcomm MSM random number generator driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/char/random.c b/drivers/char/random.c
index bd449ad52442..bf5f99fc36f1 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -782,6 +782,7 @@ static void invalidate_batched_entropy(void);
 static void crng_initialize(struct crng_state *crng)
 {
 	int		i;
+	int		arch_init = 1;
 	unsigned long	rv;
 
 	memcpy(&crng->state[0], "expand 32-byte k", 16);
@@ -792,10 +793,18 @@ static void crng_initialize(struct crng_state *crng)
 		_get_random_bytes(&crng->state[4], sizeof(__u32) * 12);
 	for (i = 4; i < 16; i++) {
 		if (!arch_get_random_seed_long(&rv) &&
-		    !arch_get_random_long(&rv))
+		    !arch_get_random_long(&rv)) {
 			rv = random_get_entropy();
+			arch_init = 0;
+		}
 		crng->state[i] ^= rv;
 	}
+#ifdef CONFIG_RANDOM_TRUST_CPU
+	if (arch_init) {
+		crng_init = 2;
+		pr_notice("random: crng done (trusting CPU's manufacturer)\n");
+	}
+#endif
 	crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1;
 }
 
@@ -1122,8 +1131,6 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
 	} sample;
 	long delta, delta2, delta3;
 
-	preempt_disable();
-
 	sample.jiffies = jiffies;
 	sample.cycles = random_get_entropy();
 	sample.num = num;
@@ -1161,8 +1168,6 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
 	 * and limit entropy entimate to 12 bits.
 	 */
 	credit_entropy_bits(r, min_t(int, fls(delta>>1), 11));
-
-	preempt_enable();
 }
 
 void add_input_randomness(unsigned int type, unsigned int code,
@@ -1659,6 +1664,21 @@ int wait_for_random_bytes(void)
 EXPORT_SYMBOL(wait_for_random_bytes);
 
 /*
+ * Returns whether or not the urandom pool has been seeded and thus guaranteed
+ * to supply cryptographically secure random numbers. This applies to: the
+ * /dev/urandom device, the get_random_bytes function, and the get_random_{u32,
+ * ,u64,int,long} family of functions.
+ *
+ * Returns: true if the urandom pool has been seeded.
+ *          false if the urandom pool has not been seeded.
+ */
+bool rng_is_initialized(void)
+{
+	return crng_ready();
+}
+EXPORT_SYMBOL(rng_is_initialized);
+
+/*
  * Add a callback function that will be invoked when the nonblocking
  * pool is initialised.
  *
@@ -1725,30 +1745,31 @@ EXPORT_SYMBOL(del_random_ready_callback);
  * key known by the NSA).  So it's useful if we need the speed, but
  * only if we're willing to trust the hardware manufacturer not to
  * have put in a back door.
+ *
+ * Return number of bytes filled in.
  */
-void get_random_bytes_arch(void *buf, int nbytes)
+int __must_check get_random_bytes_arch(void *buf, int nbytes)
 {
+	int left = nbytes;
 	char *p = buf;
 
-	trace_get_random_bytes_arch(nbytes, _RET_IP_);
-	while (nbytes) {
+	trace_get_random_bytes_arch(left, _RET_IP_);
+	while (left) {
 		unsigned long v;
-		int chunk = min(nbytes, (int)sizeof(unsigned long));
+		int chunk = min_t(int, left, sizeof(unsigned long));
 
 		if (!arch_get_random_long(&v))
 			break;
-		
+
 		memcpy(p, &v, chunk);
 		p += chunk;
-		nbytes -= chunk;
+		left -= chunk;
 	}
 
-	if (nbytes)
-		get_random_bytes(p, nbytes);
+	return nbytes - left;
 }
 EXPORT_SYMBOL(get_random_bytes_arch);
 
-
 /*
  * init_std_data - initialize pool with system data
  *
diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c
index 0a62c19937b6..46caadca916a 100644
--- a/drivers/char/tpm/tpm-chip.c
+++ b/drivers/char/tpm/tpm-chip.c
@@ -81,42 +81,66 @@ void tpm_put_ops(struct tpm_chip *chip)
 EXPORT_SYMBOL_GPL(tpm_put_ops);
 
 /**
- * tpm_chip_find_get() - find and reserve a TPM chip
+ * tpm_default_chip() - find a TPM chip and get a reference to it
+ */
+struct tpm_chip *tpm_default_chip(void)
+{
+	struct tpm_chip *chip, *res = NULL;
+	int chip_num = 0;
+	int chip_prev;
+
+	mutex_lock(&idr_lock);
+
+	do {
+		chip_prev = chip_num;
+		chip = idr_get_next(&dev_nums_idr, &chip_num);
+		if (chip) {
+			get_device(&chip->dev);
+			res = chip;
+			break;
+		}
+	} while (chip_prev != chip_num);
+
+	mutex_unlock(&idr_lock);
+
+	return res;
+}
+EXPORT_SYMBOL_GPL(tpm_default_chip);
+
+/**
+ * tpm_find_get_ops() - find and reserve a TPM chip
  * @chip:	a &struct tpm_chip instance, %NULL for the default chip
  *
  * Finds a TPM chip and reserves its class device and operations. The chip must
- * be released with tpm_chip_put_ops() after use.
+ * be released with tpm_put_ops() after use.
+ * This function is for internal use only. It supports existing TPM callers
+ * by accepting NULL, but those callers should be converted to pass in a chip
+ * directly.
  *
  * Return:
  * A reserved &struct tpm_chip instance.
  * %NULL if a chip is not found.
  * %NULL if the chip is not available.
  */
-struct tpm_chip *tpm_chip_find_get(struct tpm_chip *chip)
+struct tpm_chip *tpm_find_get_ops(struct tpm_chip *chip)
 {
-	struct tpm_chip *res = NULL;
-	int chip_num = 0;
-	int chip_prev;
-
-	mutex_lock(&idr_lock);
+	int rc;
 
-	if (!chip) {
-		do {
-			chip_prev = chip_num;
-			chip = idr_get_next(&dev_nums_idr, &chip_num);
-			if (chip && !tpm_try_get_ops(chip)) {
-				res = chip;
-				break;
-			}
-		} while (chip_prev != chip_num);
-	} else {
+	if (chip) {
 		if (!tpm_try_get_ops(chip))
-			res = chip;
+			return chip;
+		return NULL;
 	}
 
-	mutex_unlock(&idr_lock);
-
-	return res;
+	chip = tpm_default_chip();
+	if (!chip)
+		return NULL;
+	rc = tpm_try_get_ops(chip);
+	/* release additional reference we got from tpm_default_chip() */
+	put_device(&chip->dev);
+	if (rc)
+		return NULL;
+	return chip;
 }
 
 /**
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index e32f6e85dc6d..1a803b0cf980 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -29,7 +29,6 @@
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/freezer.h>
-#include <linux/pm_runtime.h>
 #include <linux/tpm_eventlog.h>
 
 #include "tpm.h"
@@ -369,10 +368,13 @@ err_len:
 	return -EINVAL;
 }
 
-static int tpm_request_locality(struct tpm_chip *chip)
+static int tpm_request_locality(struct tpm_chip *chip, unsigned int flags)
 {
 	int rc;
 
+	if (flags & TPM_TRANSMIT_NESTED)
+		return 0;
+
 	if (!chip->ops->request_locality)
 		return 0;
 
@@ -385,10 +387,13 @@ static int tpm_request_locality(struct tpm_chip *chip)
 	return 0;
 }
 
-static void tpm_relinquish_locality(struct tpm_chip *chip)
+static void tpm_relinquish_locality(struct tpm_chip *chip, unsigned int flags)
 {
 	int rc;
 
+	if (flags & TPM_TRANSMIT_NESTED)
+		return;
+
 	if (!chip->ops->relinquish_locality)
 		return;
 
@@ -399,6 +404,28 @@ static void tpm_relinquish_locality(struct tpm_chip *chip)
 	chip->locality = -1;
 }
 
+static int tpm_cmd_ready(struct tpm_chip *chip, unsigned int flags)
+{
+	if (flags & TPM_TRANSMIT_NESTED)
+		return 0;
+
+	if (!chip->ops->cmd_ready)
+		return 0;
+
+	return chip->ops->cmd_ready(chip);
+}
+
+static int tpm_go_idle(struct tpm_chip *chip, unsigned int flags)
+{
+	if (flags & TPM_TRANSMIT_NESTED)
+		return 0;
+
+	if (!chip->ops->go_idle)
+		return 0;
+
+	return chip->ops->go_idle(chip);
+}
+
 static ssize_t tpm_try_transmit(struct tpm_chip *chip,
 				struct tpm_space *space,
 				u8 *buf, size_t bufsiz,
@@ -423,7 +450,7 @@ static ssize_t tpm_try_transmit(struct tpm_chip *chip,
 		header->tag = cpu_to_be16(TPM2_ST_NO_SESSIONS);
 		header->return_code = cpu_to_be32(TPM2_RC_COMMAND_CODE |
 						  TSS2_RESMGR_TPM_RC_LAYER);
-		return bufsiz;
+		return sizeof(*header);
 	}
 
 	if (bufsiz > TPM_BUFSIZE)
@@ -439,24 +466,24 @@ static ssize_t tpm_try_transmit(struct tpm_chip *chip,
 		return -E2BIG;
 	}
 
-	if (!(flags & TPM_TRANSMIT_UNLOCKED))
+	if (!(flags & TPM_TRANSMIT_UNLOCKED) && !(flags & TPM_TRANSMIT_NESTED))
 		mutex_lock(&chip->tpm_mutex);
 
-
 	if (chip->ops->clk_enable != NULL)
 		chip->ops->clk_enable(chip, true);
 
 	/* Store the decision as chip->locality will be changed. */
 	need_locality = chip->locality == -1;
 
-	if (!(flags & TPM_TRANSMIT_RAW) && need_locality) {
-		rc = tpm_request_locality(chip);
+	if (need_locality) {
+		rc = tpm_request_locality(chip, flags);
 		if (rc < 0)
 			goto out_no_locality;
 	}
 
-	if (chip->dev.parent)
-		pm_runtime_get_sync(chip->dev.parent);
+	rc = tpm_cmd_ready(chip, flags);
+	if (rc)
+		goto out;
 
 	rc = tpm2_prepare_space(chip, space, ordinal, buf);
 	if (rc)
@@ -516,19 +543,22 @@ out_recv:
 	}
 
 	rc = tpm2_commit_space(chip, space, ordinal, buf, &len);
+	if (rc)
+		dev_err(&chip->dev, "tpm2_commit_space: error %d\n", rc);
 
 out:
-	if (chip->dev.parent)
-		pm_runtime_put_sync(chip->dev.parent);
+	rc = tpm_go_idle(chip, flags);
+	if (rc)
+		goto out;
 
 	if (need_locality)
-		tpm_relinquish_locality(chip);
+		tpm_relinquish_locality(chip, flags);
 
 out_no_locality:
 	if (chip->ops->clk_enable != NULL)
 		chip->ops->clk_enable(chip, false);
 
-	if (!(flags & TPM_TRANSMIT_UNLOCKED))
+	if (!(flags & TPM_TRANSMIT_UNLOCKED) && !(flags & TPM_TRANSMIT_NESTED))
 		mutex_unlock(&chip->tpm_mutex);
 	return rc ? rc : len;
 }
@@ -930,7 +960,7 @@ int tpm_is_tpm2(struct tpm_chip *chip)
 {
 	int rc;
 
-	chip = tpm_chip_find_get(chip);
+	chip = tpm_find_get_ops(chip);
 	if (!chip)
 		return -ENODEV;
 
@@ -954,7 +984,7 @@ int tpm_pcr_read(struct tpm_chip *chip, int pcr_idx, u8 *res_buf)
 {
 	int rc;
 
-	chip = tpm_chip_find_get(chip);
+	chip = tpm_find_get_ops(chip);
 	if (!chip)
 		return -ENODEV;
 	if (chip->flags & TPM_CHIP_FLAG_TPM2)
@@ -1013,7 +1043,7 @@ int tpm_pcr_extend(struct tpm_chip *chip, int pcr_idx, const u8 *hash)
 	u32 count = 0;
 	int i;
 
-	chip = tpm_chip_find_get(chip);
+	chip = tpm_find_get_ops(chip);
 	if (!chip)
 		return -ENODEV;
 
@@ -1142,7 +1172,7 @@ int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen)
 {
 	int rc;
 
-	chip = tpm_chip_find_get(chip);
+	chip = tpm_find_get_ops(chip);
 	if (!chip)
 		return -ENODEV;
 
@@ -1262,7 +1292,7 @@ int tpm_get_random(struct tpm_chip *chip, u8 *out, size_t max)
 	if (!out || !num_bytes || max > TPM_MAX_RNG_DATA)
 		return -EINVAL;
 
-	chip = tpm_chip_find_get(chip);
+	chip = tpm_find_get_ops(chip);
 	if (!chip)
 		return -ENODEV;
 
@@ -1324,7 +1354,7 @@ int tpm_seal_trusted(struct tpm_chip *chip, struct trusted_key_payload *payload,
 {
 	int rc;
 
-	chip = tpm_chip_find_get(chip);
+	chip = tpm_find_get_ops(chip);
 	if (!chip || !(chip->flags & TPM_CHIP_FLAG_TPM2))
 		return -ENODEV;
 
@@ -1352,7 +1382,7 @@ int tpm_unseal_trusted(struct tpm_chip *chip,
 {
 	int rc;
 
-	chip = tpm_chip_find_get(chip);
+	chip = tpm_find_get_ops(chip);
 	if (!chip || !(chip->flags & TPM_CHIP_FLAG_TPM2))
 		return -ENODEV;
 
diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index 4426649e431c..f3501d05264f 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -424,23 +424,24 @@ struct tpm_buf {
 	u8 *data;
 };
 
-static inline int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal)
+static inline void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal)
 {
 	struct tpm_input_header *head;
+	head = (struct tpm_input_header *)buf->data;
+	head->tag = cpu_to_be16(tag);
+	head->length = cpu_to_be32(sizeof(*head));
+	head->ordinal = cpu_to_be32(ordinal);
+}
 
+static inline int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal)
+{
 	buf->data_page = alloc_page(GFP_HIGHUSER);
 	if (!buf->data_page)
 		return -ENOMEM;
 
 	buf->flags = 0;
 	buf->data = kmap(buf->data_page);
-
-	head = (struct tpm_input_header *) buf->data;
-
-	head->tag = cpu_to_be16(tag);
-	head->length = cpu_to_be32(sizeof(*head));
-	head->ordinal = cpu_to_be32(ordinal);
-
+	tpm_buf_reset(buf, tag, ordinal);
 	return 0;
 }
 
@@ -511,9 +512,17 @@ extern const struct file_operations tpm_fops;
 extern const struct file_operations tpmrm_fops;
 extern struct idr dev_nums_idr;
 
+/**
+ * enum tpm_transmit_flags - flags for tpm_transmit()
+ *
+ * @TPM_TRANSMIT_UNLOCKED:	do not lock the chip
+ * @TPM_TRANSMIT_NESTED:	discard setup steps (power management,
+ *				locality) including locking (i.e. implicit
+ *				UNLOCKED)
+ */
 enum tpm_transmit_flags {
 	TPM_TRANSMIT_UNLOCKED	= BIT(0),
-	TPM_TRANSMIT_RAW	= BIT(1),
+	TPM_TRANSMIT_NESTED      = BIT(1),
 };
 
 ssize_t tpm_transmit(struct tpm_chip *chip, struct tpm_space *space,
@@ -538,7 +547,7 @@ static inline void tpm_msleep(unsigned int delay_msec)
 		     delay_msec * 1000);
 };
 
-struct tpm_chip *tpm_chip_find_get(struct tpm_chip *chip);
+struct tpm_chip *tpm_find_get_ops(struct tpm_chip *chip);
 __must_check int tpm_try_get_ops(struct tpm_chip *chip);
 void tpm_put_ops(struct tpm_chip *chip);
 
@@ -569,7 +578,7 @@ static inline u32 tpm2_rc_value(u32 rc)
 int tpm2_pcr_read(struct tpm_chip *chip, int pcr_idx, u8 *res_buf);
 int tpm2_pcr_extend(struct tpm_chip *chip, int pcr_idx, u32 count,
 		    struct tpm2_digest *digests);
-int tpm2_get_random(struct tpm_chip *chip, u8 *out, size_t max);
+int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max);
 void tpm2_flush_context_cmd(struct tpm_chip *chip, u32 handle,
 			    unsigned int flags);
 int tpm2_seal_trusted(struct tpm_chip *chip,
diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c
index d31b09099216..c31b490bd41d 100644
--- a/drivers/char/tpm/tpm2-cmd.c
+++ b/drivers/char/tpm/tpm2-cmd.c
@@ -27,46 +27,6 @@ enum tpm2_session_attributes {
 	TPM2_SA_CONTINUE_SESSION	= BIT(0),
 };
 
-struct tpm2_startup_in {
-	__be16	startup_type;
-} __packed;
-
-struct tpm2_get_tpm_pt_in {
-	__be32	cap_id;
-	__be32	property_id;
-	__be32	property_cnt;
-} __packed;
-
-struct tpm2_get_tpm_pt_out {
-	u8	more_data;
-	__be32	subcap_id;
-	__be32	property_cnt;
-	__be32	property_id;
-	__be32	value;
-} __packed;
-
-struct tpm2_get_random_in {
-	__be16	size;
-} __packed;
-
-struct tpm2_get_random_out {
-	__be16	size;
-	u8	buffer[TPM_MAX_RNG_DATA];
-} __packed;
-
-union tpm2_cmd_params {
-	struct	tpm2_startup_in		startup_in;
-	struct	tpm2_get_tpm_pt_in	get_tpm_pt_in;
-	struct	tpm2_get_tpm_pt_out	get_tpm_pt_out;
-	struct	tpm2_get_random_in	getrandom_in;
-	struct	tpm2_get_random_out	getrandom_out;
-};
-
-struct tpm2_cmd {
-	tpm_cmd_header		header;
-	union tpm2_cmd_params	params;
-} __packed;
-
 struct tpm2_hash {
 	unsigned int crypto_id;
 	unsigned int tpm_id;
@@ -321,82 +281,72 @@ int tpm2_pcr_extend(struct tpm_chip *chip, int pcr_idx, u32 count,
 }
 
 
-#define TPM2_GETRANDOM_IN_SIZE \
-	(sizeof(struct tpm_input_header) + \
-	 sizeof(struct tpm2_get_random_in))
-
-static const struct tpm_input_header tpm2_getrandom_header = {
-	.tag = cpu_to_be16(TPM2_ST_NO_SESSIONS),
-	.length = cpu_to_be32(TPM2_GETRANDOM_IN_SIZE),
-	.ordinal = cpu_to_be32(TPM2_CC_GET_RANDOM)
-};
+struct tpm2_get_random_out {
+	__be16 size;
+	u8 buffer[TPM_MAX_RNG_DATA];
+} __packed;
 
 /**
  * tpm2_get_random() - get random bytes from the TPM RNG
  *
- * @chip: TPM chip to use
- * @out: destination buffer for the random bytes
- * @max: the max number of bytes to write to @out
+ * @chip:	a &tpm_chip instance
+ * @dest:	destination buffer
+ * @max:	the max number of random bytes to pull
  *
  * Return:
- *    Size of the output buffer, or -EIO on error.
+ *   size of the buffer on success,
+ *   -errno otherwise
  */
-int tpm2_get_random(struct tpm_chip *chip, u8 *out, size_t max)
+int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max)
 {
-	struct tpm2_cmd cmd;
-	u32 recd, rlength;
-	u32 num_bytes;
+	struct tpm2_get_random_out *out;
+	struct tpm_buf buf;
+	u32 recd;
+	u32 num_bytes = max;
 	int err;
 	int total = 0;
 	int retries = 5;
-	u8 *dest = out;
+	u8 *dest_ptr = dest;
 
-	num_bytes = min_t(u32, max, sizeof(cmd.params.getrandom_out.buffer));
-
-	if (!out || !num_bytes ||
-	    max > sizeof(cmd.params.getrandom_out.buffer))
+	if (!num_bytes || max > TPM_MAX_RNG_DATA)
 		return -EINVAL;
 
-	do {
-		cmd.header.in = tpm2_getrandom_header;
-		cmd.params.getrandom_in.size = cpu_to_be16(num_bytes);
+	err = tpm_buf_init(&buf, 0, 0);
+	if (err)
+		return err;
 
-		err = tpm_transmit_cmd(chip, NULL, &cmd, sizeof(cmd),
+	do {
+		tpm_buf_reset(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_GET_RANDOM);
+		tpm_buf_append_u16(&buf, num_bytes);
+		err = tpm_transmit_cmd(chip, NULL, buf.data, PAGE_SIZE,
 				       offsetof(struct tpm2_get_random_out,
 						buffer),
 				       0, "attempting get random");
 		if (err)
-			break;
+			goto out;
 
-		recd = min_t(u32, be16_to_cpu(cmd.params.getrandom_out.size),
-			     num_bytes);
-		rlength = be32_to_cpu(cmd.header.out.length);
-		if (rlength < offsetof(struct tpm2_get_random_out, buffer) +
-			      recd)
-			return -EFAULT;
-		memcpy(dest, cmd.params.getrandom_out.buffer, recd);
+		out = (struct tpm2_get_random_out *)
+			&buf.data[TPM_HEADER_SIZE];
+		recd = min_t(u32, be16_to_cpu(out->size), num_bytes);
+		if (tpm_buf_length(&buf) <
+		    offsetof(struct tpm2_get_random_out, buffer) + recd) {
+			err = -EFAULT;
+			goto out;
+		}
+		memcpy(dest_ptr, out->buffer, recd);
 
-		dest += recd;
+		dest_ptr += recd;
 		total += recd;
 		num_bytes -= recd;
 	} while (retries-- && total < max);
 
+	tpm_buf_destroy(&buf);
 	return total ? total : -EIO;
+out:
+	tpm_buf_destroy(&buf);
+	return err;
 }
 
-#define TPM2_GET_TPM_PT_IN_SIZE \
-	(sizeof(struct tpm_input_header) + \
-	 sizeof(struct tpm2_get_tpm_pt_in))
-
-#define TPM2_GET_TPM_PT_OUT_BODY_SIZE \
-	 sizeof(struct tpm2_get_tpm_pt_out)
-
-static const struct tpm_input_header tpm2_get_tpm_pt_header = {
-	.tag = cpu_to_be16(TPM2_ST_NO_SESSIONS),
-	.length = cpu_to_be32(TPM2_GET_TPM_PT_IN_SIZE),
-	.ordinal = cpu_to_be32(TPM2_CC_GET_CAPABILITY)
-};
-
 /**
  * tpm2_flush_context_cmd() - execute a TPM2_FlushContext command
  * @chip: TPM chip to use
@@ -471,7 +421,7 @@ int tpm2_seal_trusted(struct tpm_chip *chip,
 {
 	unsigned int blob_len;
 	struct tpm_buf buf;
-	u32 hash, rlength;
+	u32 hash;
 	int i;
 	int rc;
 
@@ -546,8 +496,7 @@ int tpm2_seal_trusted(struct tpm_chip *chip,
 		rc = -E2BIG;
 		goto out;
 	}
-	rlength = be32_to_cpu(((struct tpm2_cmd *)&buf)->header.out.length);
-	if (rlength < TPM_HEADER_SIZE + 4 + blob_len) {
+	if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 4 + blob_len) {
 		rc = -EFAULT;
 		goto out;
 	}
@@ -657,7 +606,6 @@ static int tpm2_unseal_cmd(struct tpm_chip *chip,
 	u16 data_len;
 	u8 *data;
 	int rc;
-	u32 rlength;
 
 	rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_UNSEAL);
 	if (rc)
@@ -685,9 +633,7 @@ static int tpm2_unseal_cmd(struct tpm_chip *chip,
 			goto out;
 		}
 
-		rlength = be32_to_cpu(((struct tpm2_cmd *)&buf)
-					->header.out.length);
-		if (rlength < TPM_HEADER_SIZE + 6 + data_len) {
+		if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 6 + data_len) {
 			rc = -EFAULT;
 			goto out;
 		}
@@ -733,69 +679,71 @@ out:
 	return rc;
 }
 
+struct tpm2_get_cap_out {
+	u8 more_data;
+	__be32 subcap_id;
+	__be32 property_cnt;
+	__be32 property_id;
+	__be32 value;
+} __packed;
+
 /**
  * tpm2_get_tpm_pt() - get value of a TPM_CAP_TPM_PROPERTIES type property
- * @chip:		TPM chip to use.
+ * @chip:		a &tpm_chip instance
  * @property_id:	property ID.
  * @value:		output variable.
  * @desc:		passed to tpm_transmit_cmd()
  *
- * Return: Same as with tpm_transmit_cmd.
+ * Return:
+ *   0 on success,
+ *   -errno or a TPM return code otherwise
  */
 ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id,  u32 *value,
 			const char *desc)
 {
-	struct tpm2_cmd cmd;
+	struct tpm2_get_cap_out *out;
+	struct tpm_buf buf;
 	int rc;
 
-	cmd.header.in = tpm2_get_tpm_pt_header;
-	cmd.params.get_tpm_pt_in.cap_id = cpu_to_be32(TPM2_CAP_TPM_PROPERTIES);
-	cmd.params.get_tpm_pt_in.property_id = cpu_to_be32(property_id);
-	cmd.params.get_tpm_pt_in.property_cnt = cpu_to_be32(1);
-
-	rc = tpm_transmit_cmd(chip, NULL, &cmd, sizeof(cmd),
-			      TPM2_GET_TPM_PT_OUT_BODY_SIZE, 0, desc);
-	if (!rc)
-		*value = be32_to_cpu(cmd.params.get_tpm_pt_out.value);
-
+	rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_GET_CAPABILITY);
+	if (rc)
+		return rc;
+	tpm_buf_append_u32(&buf, TPM2_CAP_TPM_PROPERTIES);
+	tpm_buf_append_u32(&buf, property_id);
+	tpm_buf_append_u32(&buf, 1);
+	rc = tpm_transmit_cmd(chip, NULL, buf.data, PAGE_SIZE, 0, 0, NULL);
+	if (!rc) {
+		out = (struct tpm2_get_cap_out *)
+			&buf.data[TPM_HEADER_SIZE];
+		*value = be32_to_cpu(out->value);
+	}
+	tpm_buf_destroy(&buf);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(tpm2_get_tpm_pt);
 
-#define TPM2_SHUTDOWN_IN_SIZE \
-	(sizeof(struct tpm_input_header) + \
-	 sizeof(struct tpm2_startup_in))
-
-static const struct tpm_input_header tpm2_shutdown_header = {
-	.tag = cpu_to_be16(TPM2_ST_NO_SESSIONS),
-	.length = cpu_to_be32(TPM2_SHUTDOWN_IN_SIZE),
-	.ordinal = cpu_to_be32(TPM2_CC_SHUTDOWN)
-};
-
 /**
- * tpm2_shutdown() - send shutdown command to the TPM chip
+ * tpm2_shutdown() - send a TPM shutdown command
+ *
+ * Sends a TPM shutdown command. The shutdown command is used in call
+ * sites where the system is going down. If it fails, there is not much
+ * that can be done except print an error message.
  *
- * @chip:		TPM chip to use.
- * @shutdown_type:	shutdown type. The value is either
- *			TPM_SU_CLEAR or TPM_SU_STATE.
+ * @chip:		a &tpm_chip instance
+ * @shutdown_type:	TPM_SU_CLEAR or TPM_SU_STATE.
  */
 void tpm2_shutdown(struct tpm_chip *chip, u16 shutdown_type)
 {
-	struct tpm2_cmd cmd;
+	struct tpm_buf buf;
 	int rc;
 
-	cmd.header.in = tpm2_shutdown_header;
-	cmd.params.startup_in.startup_type = cpu_to_be16(shutdown_type);
-
-	rc = tpm_transmit_cmd(chip, NULL, &cmd, sizeof(cmd), 0, 0,
-			      "stopping the TPM");
-
-	/* In places where shutdown command is sent there's no much we can do
-	 * except print the error code on a system failure.
-	 */
-	if (rc < 0 && rc != -EPIPE)
-		dev_warn(&chip->dev, "transmit returned %d while stopping the TPM",
-			 rc);
+	rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_SHUTDOWN);
+	if (rc)
+		return;
+	tpm_buf_append_u16(&buf, shutdown_type);
+	tpm_transmit_cmd(chip, NULL, buf.data, PAGE_SIZE, 0, 0,
+			 "stopping the TPM");
+	tpm_buf_destroy(&buf);
 }
 
 /*
@@ -863,31 +811,37 @@ static int tpm2_do_selftest(struct tpm_chip *chip)
 }
 
 /**
- * tpm2_probe() - probe TPM 2.0
- * @chip: TPM chip to use
+ * tpm2_probe() - probe for the TPM 2.0 protocol
+ * @chip:	a &tpm_chip instance
  *
- * Return: < 0 error and 0 on success.
+ * Send an idempotent TPM 2.0 command and see whether there is TPM2 chip in the
+ * other end based on the response tag. The flag TPM_CHIP_FLAG_TPM2 is set by
+ * this function if this is the case.
  *
- * Send idempotent TPM 2.0 command and see whether TPM 2.0 chip replied based on
- * the reply tag.
+ * Return:
+ *   0 on success,
+ *   -errno otherwise
  */
 int tpm2_probe(struct tpm_chip *chip)
 {
-	struct tpm2_cmd cmd;
+	struct tpm_output_header *out;
+	struct tpm_buf buf;
 	int rc;
 
-	cmd.header.in = tpm2_get_tpm_pt_header;
-	cmd.params.get_tpm_pt_in.cap_id = cpu_to_be32(TPM2_CAP_TPM_PROPERTIES);
-	cmd.params.get_tpm_pt_in.property_id = cpu_to_be32(0x100);
-	cmd.params.get_tpm_pt_in.property_cnt = cpu_to_be32(1);
-
-	rc = tpm_transmit_cmd(chip, NULL, &cmd, sizeof(cmd), 0, 0, NULL);
-	if (rc <  0)
+	rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_GET_CAPABILITY);
+	if (rc)
 		return rc;
-
-	if (be16_to_cpu(cmd.header.out.tag) == TPM2_ST_NO_SESSIONS)
-		chip->flags |= TPM_CHIP_FLAG_TPM2;
-
+	tpm_buf_append_u32(&buf, TPM2_CAP_TPM_PROPERTIES);
+	tpm_buf_append_u32(&buf, TPM_PT_TOTAL_COMMANDS);
+	tpm_buf_append_u32(&buf, 1);
+	rc = tpm_transmit_cmd(chip, NULL, buf.data, PAGE_SIZE, 0, 0, NULL);
+	/* We ignore TPM return codes on purpose. */
+	if (rc >=  0) {
+		out = (struct tpm_output_header *)buf.data;
+		if (be16_to_cpu(out->tag) == TPM2_ST_NO_SESSIONS)
+			chip->flags |= TPM_CHIP_FLAG_TPM2;
+	}
+	tpm_buf_destroy(&buf);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(tpm2_probe);
diff --git a/drivers/char/tpm/tpm2-space.c b/drivers/char/tpm/tpm2-space.c
index 6122d3276f72..d2e101b32482 100644
--- a/drivers/char/tpm/tpm2-space.c
+++ b/drivers/char/tpm/tpm2-space.c
@@ -39,7 +39,7 @@ static void tpm2_flush_sessions(struct tpm_chip *chip, struct tpm_space *space)
 	for (i = 0; i < ARRAY_SIZE(space->session_tbl); i++) {
 		if (space->session_tbl[i])
 			tpm2_flush_context_cmd(chip, space->session_tbl[i],
-					       TPM_TRANSMIT_UNLOCKED);
+					       TPM_TRANSMIT_NESTED);
 	}
 }
 
@@ -84,7 +84,7 @@ static int tpm2_load_context(struct tpm_chip *chip, u8 *buf,
 	tpm_buf_append(&tbuf, &buf[*offset], body_size);
 
 	rc = tpm_transmit_cmd(chip, NULL, tbuf.data, PAGE_SIZE, 4,
-			      TPM_TRANSMIT_UNLOCKED, NULL);
+			      TPM_TRANSMIT_NESTED, NULL);
 	if (rc < 0) {
 		dev_warn(&chip->dev, "%s: failed with a system error %d\n",
 			 __func__, rc);
@@ -133,7 +133,7 @@ static int tpm2_save_context(struct tpm_chip *chip, u32 handle, u8 *buf,
 	tpm_buf_append_u32(&tbuf, handle);
 
 	rc = tpm_transmit_cmd(chip, NULL, tbuf.data, PAGE_SIZE, 0,
-			      TPM_TRANSMIT_UNLOCKED, NULL);
+			      TPM_TRANSMIT_NESTED, NULL);
 	if (rc < 0) {
 		dev_warn(&chip->dev, "%s: failed with a system error %d\n",
 			 __func__, rc);
@@ -170,7 +170,7 @@ static void tpm2_flush_space(struct tpm_chip *chip)
 	for (i = 0; i < ARRAY_SIZE(space->context_tbl); i++)
 		if (space->context_tbl[i] && ~space->context_tbl[i])
 			tpm2_flush_context_cmd(chip, space->context_tbl[i],
-					       TPM_TRANSMIT_UNLOCKED);
+					       TPM_TRANSMIT_NESTED);
 
 	tpm2_flush_sessions(chip, space);
 }
@@ -377,7 +377,7 @@ static int tpm2_map_response_header(struct tpm_chip *chip, u32 cc, u8 *rsp,
 
 	return 0;
 out_no_slots:
-	tpm2_flush_context_cmd(chip, phandle, TPM_TRANSMIT_UNLOCKED);
+	tpm2_flush_context_cmd(chip, phandle, TPM_TRANSMIT_NESTED);
 	dev_warn(&chip->dev, "%s: out of slots for 0x%08X\n", __func__,
 		 phandle);
 	return -ENOMEM;
@@ -465,7 +465,7 @@ static int tpm2_save_space(struct tpm_chip *chip)
 			return rc;
 
 		tpm2_flush_context_cmd(chip, space->context_tbl[i],
-				       TPM_TRANSMIT_UNLOCKED);
+				       TPM_TRANSMIT_NESTED);
 		space->context_tbl[i] = ~0;
 	}
 
diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c
index 34fbc6cb097b..36952ef98f90 100644
--- a/drivers/char/tpm/tpm_crb.c
+++ b/drivers/char/tpm/tpm_crb.c
@@ -132,7 +132,7 @@ static bool crb_wait_for_reg_32(u32 __iomem *reg, u32 mask, u32 value,
 }
 
 /**
- * crb_go_idle - request tpm crb device to go the idle state
+ * __crb_go_idle - request tpm crb device to go the idle state
  *
  * @dev:  crb device
  * @priv: crb private data
@@ -147,7 +147,7 @@ static bool crb_wait_for_reg_32(u32 __iomem *reg, u32 mask, u32 value,
  *
  * Return: 0 always
  */
-static int crb_go_idle(struct device *dev, struct crb_priv *priv)
+static int __crb_go_idle(struct device *dev, struct crb_priv *priv)
 {
 	if ((priv->sm == ACPI_TPM2_START_METHOD) ||
 	    (priv->sm == ACPI_TPM2_COMMAND_BUFFER_WITH_START_METHOD) ||
@@ -163,11 +163,20 @@ static int crb_go_idle(struct device *dev, struct crb_priv *priv)
 		dev_warn(dev, "goIdle timed out\n");
 		return -ETIME;
 	}
+
 	return 0;
 }
 
+static int crb_go_idle(struct tpm_chip *chip)
+{
+	struct device *dev = &chip->dev;
+	struct crb_priv *priv = dev_get_drvdata(dev);
+
+	return __crb_go_idle(dev, priv);
+}
+
 /**
- * crb_cmd_ready - request tpm crb device to enter ready state
+ * __crb_cmd_ready - request tpm crb device to enter ready state
  *
  * @dev:  crb device
  * @priv: crb private data
@@ -181,7 +190,7 @@ static int crb_go_idle(struct device *dev, struct crb_priv *priv)
  *
  * Return: 0 on success -ETIME on timeout;
  */
-static int crb_cmd_ready(struct device *dev, struct crb_priv *priv)
+static int __crb_cmd_ready(struct device *dev, struct crb_priv *priv)
 {
 	if ((priv->sm == ACPI_TPM2_START_METHOD) ||
 	    (priv->sm == ACPI_TPM2_COMMAND_BUFFER_WITH_START_METHOD) ||
@@ -200,6 +209,14 @@ static int crb_cmd_ready(struct device *dev, struct crb_priv *priv)
 	return 0;
 }
 
+static int crb_cmd_ready(struct tpm_chip *chip)
+{
+	struct device *dev = &chip->dev;
+	struct crb_priv *priv = dev_get_drvdata(dev);
+
+	return __crb_cmd_ready(dev, priv);
+}
+
 static int __crb_request_locality(struct device *dev,
 				  struct crb_priv *priv, int loc)
 {
@@ -401,6 +418,8 @@ static const struct tpm_class_ops tpm_crb = {
 	.send = crb_send,
 	.cancel = crb_cancel,
 	.req_canceled = crb_req_canceled,
+	.go_idle  = crb_go_idle,
+	.cmd_ready = crb_cmd_ready,
 	.request_locality = crb_request_locality,
 	.relinquish_locality = crb_relinquish_locality,
 	.req_complete_mask = CRB_DRV_STS_COMPLETE,
@@ -520,7 +539,7 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv,
 	 * PTT HW bug w/a: wake up the device to access
 	 * possibly not retained registers.
 	 */
-	ret = crb_cmd_ready(dev, priv);
+	ret = __crb_cmd_ready(dev, priv);
 	if (ret)
 		goto out_relinquish_locality;
 
@@ -565,7 +584,7 @@ out:
 	if (!ret)
 		priv->cmd_size = cmd_size;
 
-	crb_go_idle(dev, priv);
+	__crb_go_idle(dev, priv);
 
 out_relinquish_locality:
 
@@ -628,32 +647,7 @@ static int crb_acpi_add(struct acpi_device *device)
 	chip->acpi_dev_handle = device->handle;
 	chip->flags = TPM_CHIP_FLAG_TPM2;
 
-	rc = __crb_request_locality(dev, priv, 0);
-	if (rc)
-		return rc;
-
-	rc  = crb_cmd_ready(dev, priv);
-	if (rc)
-		goto out;
-
-	pm_runtime_get_noresume(dev);
-	pm_runtime_set_active(dev);
-	pm_runtime_enable(dev);
-
-	rc = tpm_chip_register(chip);
-	if (rc) {
-		crb_go_idle(dev, priv);
-		pm_runtime_put_noidle(dev);
-		pm_runtime_disable(dev);
-		goto out;
-	}
-
-	pm_runtime_put_sync(dev);
-
-out:
-	__crb_relinquish_locality(dev, priv, 0);
-
-	return rc;
+	return tpm_chip_register(chip);
 }
 
 static int crb_acpi_remove(struct acpi_device *device)
@@ -663,52 +657,11 @@ static int crb_acpi_remove(struct acpi_device *device)
 
 	tpm_chip_unregister(chip);
 
-	pm_runtime_disable(dev);
-
 	return 0;
 }
 
-static int __maybe_unused crb_pm_runtime_suspend(struct device *dev)
-{
-	struct tpm_chip *chip = dev_get_drvdata(dev);
-	struct crb_priv *priv = dev_get_drvdata(&chip->dev);
-
-	return crb_go_idle(dev, priv);
-}
-
-static int __maybe_unused crb_pm_runtime_resume(struct device *dev)
-{
-	struct tpm_chip *chip = dev_get_drvdata(dev);
-	struct crb_priv *priv = dev_get_drvdata(&chip->dev);
-
-	return crb_cmd_ready(dev, priv);
-}
-
-static int __maybe_unused crb_pm_suspend(struct device *dev)
-{
-	int ret;
-
-	ret = tpm_pm_suspend(dev);
-	if (ret)
-		return ret;
-
-	return crb_pm_runtime_suspend(dev);
-}
-
-static int __maybe_unused crb_pm_resume(struct device *dev)
-{
-	int ret;
-
-	ret = crb_pm_runtime_resume(dev);
-	if (ret)
-		return ret;
-
-	return tpm_pm_resume(dev);
-}
-
 static const struct dev_pm_ops crb_pm = {
-	SET_SYSTEM_SLEEP_PM_OPS(crb_pm_suspend, crb_pm_resume)
-	SET_RUNTIME_PM_OPS(crb_pm_runtime_suspend, crb_pm_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(tpm_pm_suspend, tpm_pm_resume)
 };
 
 static const struct acpi_device_id crb_device_ids[] = {
diff --git a/drivers/char/tpm/tpm_i2c_infineon.c b/drivers/char/tpm/tpm_i2c_infineon.c
index 6116cd05e228..9086edc9066b 100644
--- a/drivers/char/tpm/tpm_i2c_infineon.c
+++ b/drivers/char/tpm/tpm_i2c_infineon.c
@@ -117,7 +117,7 @@ static int iic_tpm_read(u8 addr, u8 *buffer, size_t len)
 	/* Lock the adapter for the duration of the whole sequence. */
 	if (!tpm_dev.client->adapter->algo->master_xfer)
 		return -EOPNOTSUPP;
-	i2c_lock_adapter(tpm_dev.client->adapter);
+	i2c_lock_bus(tpm_dev.client->adapter, I2C_LOCK_SEGMENT);
 
 	if (tpm_dev.chip_type == SLB9645) {
 		/* use a combined read for newer chips
@@ -192,7 +192,7 @@ static int iic_tpm_read(u8 addr, u8 *buffer, size_t len)
 	}
 
 out:
-	i2c_unlock_adapter(tpm_dev.client->adapter);
+	i2c_unlock_bus(tpm_dev.client->adapter, I2C_LOCK_SEGMENT);
 	/* take care of 'guard time' */
 	usleep_range(SLEEP_DURATION_LOW, SLEEP_DURATION_HI);
 
@@ -224,7 +224,7 @@ static int iic_tpm_write_generic(u8 addr, u8 *buffer, size_t len,
 
 	if (!tpm_dev.client->adapter->algo->master_xfer)
 		return -EOPNOTSUPP;
-	i2c_lock_adapter(tpm_dev.client->adapter);
+	i2c_lock_bus(tpm_dev.client->adapter, I2C_LOCK_SEGMENT);
 
 	/* prepend the 'register address' to the buffer */
 	tpm_dev.buf[0] = addr;
@@ -243,7 +243,7 @@ static int iic_tpm_write_generic(u8 addr, u8 *buffer, size_t len,
 		usleep_range(sleep_low, sleep_hi);
 	}
 
-	i2c_unlock_adapter(tpm_dev.client->adapter);
+	i2c_unlock_bus(tpm_dev.client->adapter, I2C_LOCK_SEGMENT);
 	/* take care of 'guard time' */
 	usleep_range(SLEEP_DURATION_LOW, SLEEP_DURATION_HI);
 
diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index 8b46aaa9e049..d2345d9fd7b5 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -875,6 +875,8 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
 	chip->acpi_dev_handle = acpi_dev_handle;
 #endif
 
+	chip->hwrng.quality = priv->rng_quality;
+
 	/* Maximum timeouts */
 	chip->timeout_a = msecs_to_jiffies(TIS_TIMEOUT_A_MAX);
 	chip->timeout_b = msecs_to_jiffies(TIS_TIMEOUT_B_MAX);
diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h
index f6e1dbe212a7..f48125f1e6e0 100644
--- a/drivers/char/tpm/tpm_tis_core.h
+++ b/drivers/char/tpm/tpm_tis_core.h
@@ -99,6 +99,7 @@ struct tpm_tis_data {
 	wait_queue_head_t int_queue;
 	wait_queue_head_t read_queue;
 	const struct tpm_tis_phy_ops *phy_ops;
+	unsigned short rng_quality;
 };
 
 struct tpm_tis_phy_ops {
diff --git a/drivers/char/tpm/tpm_tis_spi.c b/drivers/char/tpm/tpm_tis_spi.c
index 424ff2fde1f2..9914f6973463 100644
--- a/drivers/char/tpm/tpm_tis_spi.c
+++ b/drivers/char/tpm/tpm_tis_spi.c
@@ -199,6 +199,7 @@ static const struct tpm_tis_phy_ops tpm_spi_phy_ops = {
 static int tpm_tis_spi_probe(struct spi_device *dev)
 {
 	struct tpm_tis_spi_phy *phy;
+	int irq;
 
 	phy = devm_kzalloc(&dev->dev, sizeof(struct tpm_tis_spi_phy),
 			   GFP_KERNEL);
@@ -211,7 +212,13 @@ static int tpm_tis_spi_probe(struct spi_device *dev)
 	if (!phy->iobuf)
 		return -ENOMEM;
 
-	return tpm_tis_core_init(&dev->dev, &phy->priv, -1, &tpm_spi_phy_ops,
+	/* If the SPI device has an IRQ then use that */
+	if (dev->irq > 0)
+		irq = dev->irq;
+	else
+		irq = -1;
+
+	return tpm_tis_core_init(&dev->dev, &phy->priv, irq, &tpm_spi_phy_ops,
 				 NULL);
 }
 
diff --git a/drivers/char/tpm/tpm_vtpm_proxy.c b/drivers/char/tpm/tpm_vtpm_proxy.c
index e4f79f920450..87a0ce47f201 100644
--- a/drivers/char/tpm/tpm_vtpm_proxy.c
+++ b/drivers/char/tpm/tpm_vtpm_proxy.c
@@ -418,7 +418,7 @@ static int vtpm_proxy_request_locality(struct tpm_chip *chip, int locality)
 	proxy_dev->state |= STATE_DRIVER_COMMAND;
 
 	rc = tpm_transmit_cmd(chip, NULL, buf.data, tpm_buf_length(&buf), 0,
-			      TPM_TRANSMIT_UNLOCKED | TPM_TRANSMIT_RAW,
+			      TPM_TRANSMIT_NESTED,
 			      "attempting to set locality");
 
 	proxy_dev->state &= ~STATE_DRIVER_COMMAND;
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 721572a8c429..292056bbb30e 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -45,6 +45,12 @@ config COMMON_CLK_MAX77686
 	  This driver supports Maxim 77620/77686/77802 crystal oscillator
 	  clock.
 
+config COMMON_CLK_MAX9485
+	tristate "Maxim 9485 Programmable Clock Generator"
+	depends on I2C
+	help
+	  This driver supports Maxim 9485 Programmable Audio Clock Generator
+
 config COMMON_CLK_RK808
 	tristate "Clock driver for RK805/RK808/RK818"
 	depends on MFD_RK808
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index 0bb25dd009d1..a84c5573cabe 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -31,6 +31,7 @@ obj-$(CONFIG_COMMON_CLK_ASPEED)		+= clk-aspeed.o
 obj-$(CONFIG_ARCH_HIGHBANK)		+= clk-highbank.o
 obj-$(CONFIG_CLK_HSDK)			+= clk-hsdk-pll.o
 obj-$(CONFIG_COMMON_CLK_MAX77686)	+= clk-max77686.o
+obj-$(CONFIG_COMMON_CLK_MAX9485)	+= clk-max9485.o
 obj-$(CONFIG_ARCH_MOXART)		+= clk-moxart.o
 obj-$(CONFIG_ARCH_NOMADIK)		+= clk-nomadik.o
 obj-$(CONFIG_ARCH_NPCM7XX)	    	+= clk-npcm7xx.o
diff --git a/drivers/clk/actions/Kconfig b/drivers/clk/actions/Kconfig
index 8854adb37847..dc38c85a4833 100644
--- a/drivers/clk/actions/Kconfig
+++ b/drivers/clk/actions/Kconfig
@@ -1,14 +1,21 @@
 config CLK_ACTIONS
 	bool "Clock driver for Actions Semi SoCs"
 	depends on ARCH_ACTIONS || COMPILE_TEST
+	select REGMAP_MMIO
 	default ARCH_ACTIONS
 
 if CLK_ACTIONS
 
 # SoC Drivers
 
+config CLK_OWL_S700
+	bool "Support for the Actions Semi OWL S700 clocks"
+	depends on (ARM64 && ARCH_ACTIONS) || COMPILE_TEST
+	default ARM64 && ARCH_ACTIONS
+
 config CLK_OWL_S900
 	bool "Support for the Actions Semi OWL S900 clocks"
 	depends on (ARM64 && ARCH_ACTIONS) || COMPILE_TEST
 	default ARM64 && ARCH_ACTIONS
+
 endif
diff --git a/drivers/clk/actions/Makefile b/drivers/clk/actions/Makefile
index 76e431434d10..78c17d56f991 100644
--- a/drivers/clk/actions/Makefile
+++ b/drivers/clk/actions/Makefile
@@ -9,4 +9,5 @@ clk-owl-y			+= owl-composite.o
 clk-owl-y			+= owl-pll.o
 
 # SoC support
+obj-$(CONFIG_CLK_OWL_S700)	+= owl-s700.o
 obj-$(CONFIG_CLK_OWL_S900)	+= owl-s900.o
diff --git a/drivers/clk/actions/owl-s700.c b/drivers/clk/actions/owl-s700.c
new file mode 100644
index 000000000000..5e9531392ee5
--- /dev/null
+++ b/drivers/clk/actions/owl-s700.c
@@ -0,0 +1,606 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Actions Semi S700 clock driver
+ *
+ * Copyright (c) 2014 Actions Semi Inc.
+ * Author: David Liu <liuwei@actions-semi.com>
+ *
+ * Author: Pathiban Nallathambi <pn@denx.de>
+ * Author: Saravanan Sekar <sravanhome@gmail.com>
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/platform_device.h>
+
+#include "owl-common.h"
+#include "owl-composite.h"
+#include "owl-divider.h"
+#include "owl-factor.h"
+#include "owl-fixed-factor.h"
+#include "owl-gate.h"
+#include "owl-mux.h"
+#include "owl-pll.h"
+
+#include <dt-bindings/clock/actions,s700-cmu.h>
+
+#define CMU_COREPLL		(0x0000)
+#define CMU_DEVPLL		(0x0004)
+#define CMU_DDRPLL		(0x0008)
+#define CMU_NANDPLL		(0x000C)
+#define CMU_DISPLAYPLL		(0x0010)
+#define CMU_AUDIOPLL		(0x0014)
+#define CMU_TVOUTPLL		(0x0018)
+#define CMU_BUSCLK		(0x001C)
+#define CMU_SENSORCLK		(0x0020)
+#define CMU_LCDCLK		(0x0024)
+#define CMU_DSIPLLCLK		(0x0028)
+#define CMU_CSICLK		(0x002C)
+#define CMU_DECLK		(0x0030)
+#define CMU_SICLK		(0x0034)
+#define CMU_BUSCLK1		(0x0038)
+#define CMU_HDECLK		(0x003C)
+#define CMU_VDECLK		(0x0040)
+#define CMU_VCECLK		(0x0044)
+#define CMU_NANDCCLK		(0x004C)
+#define CMU_SD0CLK		(0x0050)
+#define CMU_SD1CLK		(0x0054)
+#define CMU_SD2CLK		(0x0058)
+#define CMU_UART0CLK		(0x005C)
+#define CMU_UART1CLK		(0x0060)
+#define CMU_UART2CLK		(0x0064)
+#define CMU_UART3CLK		(0x0068)
+#define CMU_UART4CLK		(0x006C)
+#define CMU_UART5CLK		(0x0070)
+#define CMU_UART6CLK		(0x0074)
+#define CMU_PWM0CLK		(0x0078)
+#define CMU_PWM1CLK		(0x007C)
+#define CMU_PWM2CLK		(0x0080)
+#define CMU_PWM3CLK		(0x0084)
+#define CMU_PWM4CLK		(0x0088)
+#define CMU_PWM5CLK		(0x008C)
+#define CMU_GPU3DCLK		(0x0090)
+#define CMU_CORECTL		(0x009C)
+#define CMU_DEVCLKEN0		(0x00A0)
+#define CMU_DEVCLKEN1		(0x00A4)
+#define CMU_DEVRST0		(0x00A8)
+#define CMU_DEVRST1		(0x00AC)
+#define CMU_USBPLL		(0x00B0)
+#define CMU_ETHERNETPLL		(0x00B4)
+#define CMU_CVBSPLL		(0x00B8)
+#define CMU_SSTSCLK		(0x00C0)
+
+static struct clk_pll_table clk_audio_pll_table[] = {
+	{0, 45158400}, {1, 49152000},
+	{0, 0},
+};
+
+static struct clk_pll_table clk_cvbs_pll_table[] = {
+	{27, 29 * 12000000}, {28, 30 * 12000000}, {29, 31 * 12000000},
+	{30, 32 * 12000000}, {31, 33 * 12000000}, {32, 34 * 12000000},
+	{33, 35 * 12000000}, {34, 36 * 12000000}, {35, 37 * 12000000},
+	{36, 38 * 12000000}, {37, 39 * 12000000}, {38, 40 * 12000000},
+	{39, 41 * 12000000}, {40, 42 * 12000000}, {41, 43 * 12000000},
+	{42, 44 * 12000000}, {43, 45 * 12000000}, {0, 0},
+};
+
+/* pll clocks */
+static OWL_PLL_NO_PARENT(clk_core_pll,   "core_pll", CMU_COREPLL, 12000000, 9, 0, 8,  4, 174, NULL, CLK_IGNORE_UNUSED);
+static OWL_PLL_NO_PARENT(clk_dev_pll,    "dev_pll", CMU_DEVPLL,  6000000, 8, 0, 8, 8, 126, NULL, CLK_IGNORE_UNUSED);
+static OWL_PLL_NO_PARENT(clk_ddr_pll,    "ddr_pll", CMU_DDRPLL, 6000000, 8, 0, 8,  2,  180, NULL, CLK_IGNORE_UNUSED);
+static OWL_PLL_NO_PARENT(clk_nand_pll,   "nand_pll", CMU_NANDPLL,  6000000, 8, 0, 8,  2, 86, NULL, CLK_IGNORE_UNUSED);
+static OWL_PLL_NO_PARENT(clk_display_pll, "display_pll", CMU_DISPLAYPLL, 6000000, 8, 0, 8, 2, 140, NULL, CLK_IGNORE_UNUSED);
+static OWL_PLL_NO_PARENT(clk_cvbs_pll, "cvbs_pll", CMU_CVBSPLL, 0, 8, 0, 8, 27, 43, clk_cvbs_pll_table, CLK_IGNORE_UNUSED);
+static OWL_PLL_NO_PARENT(clk_audio_pll,  "audio_pll", CMU_AUDIOPLL, 0, 4, 0, 1, 0, 0, clk_audio_pll_table, CLK_IGNORE_UNUSED);
+static OWL_PLL_NO_PARENT(clk_ethernet_pll, "ethernet_pll", CMU_ETHERNETPLL, 500000000, 0, 0, 0, 0, 0, NULL, CLK_IGNORE_UNUSED);
+
+static const char *cpu_clk_mux_p[] = {"losc", "hosc", "core_pll", "noc1_clk_div"};
+static const char *dev_clk_p[] = { "hosc", "dev_pll"};
+static const char *noc_clk_mux_p[] = { "dev_clk", "display_pll", "nand_pll", "ddr_pll", "cvbs_pll"};
+
+static const char *csi_clk_mux_p[] = { "display_pll", "dev_clk"};
+static const char *de_clk_mux_p[] = { "display_pll", "dev_clk"};
+static const char *hde_clk_mux_p[] = { "dev_clk", "display_pll", "nand_pll", "ddr_pll"};
+static const char *nand_clk_mux_p[] = { "nand_pll", "display_pll", "dev_clk", "ddr_pll"};
+static const char *sd_clk_mux_p[] = { "dev_clk", "nand_pll", };
+static const char *uart_clk_mux_p[] = { "hosc", "dev_pll"};
+static const char *pwm_clk_mux_p[] = { "losc", "hosc"};
+static const char *gpu_clk_mux_p[] = { "dev_clk", "display_pll", "nand_pll", "ddr_clk", "cvbs_pll"};
+static const char *lcd_clk_mux_p[] = { "display_pll", "dev_clk" };
+static const char *i2s_clk_mux_p[] = { "audio_pll" };
+static const char *sensor_clk_mux_p[] = { "hosc", "si"};
+
+/* mux clocks */
+static OWL_MUX(clk_cpu, "cpu_clk", cpu_clk_mux_p,  CMU_BUSCLK, 0, 2, CLK_SET_RATE_PARENT);
+static OWL_MUX(clk_dev, "dev_clk", dev_clk_p, CMU_DEVPLL, 12, 1, CLK_SET_RATE_PARENT);
+static OWL_MUX(clk_noc0_clk_mux, "noc0_clk_mux", noc_clk_mux_p, CMU_BUSCLK, 4, 3, CLK_SET_RATE_PARENT);
+static OWL_MUX(clk_noc1_clk_mux, "noc1_clk_mux", noc_clk_mux_p, CMU_BUSCLK1, 4, 3, CLK_SET_RATE_PARENT);
+static OWL_MUX(clk_hp_clk_mux, "hp_clk_mux", noc_clk_mux_p, CMU_BUSCLK1, 8, 3, CLK_SET_RATE_PARENT);
+
+static struct clk_factor_table sd_factor_table[] = {
+	/* bit0 ~ 4 */
+	{0, 1, 1}, {1, 1, 2}, {2, 1, 3}, {3, 1, 4},
+	{4, 1, 5}, {5, 1, 6}, {6, 1, 7}, {7, 1, 8},
+	{8, 1, 9}, {9, 1, 10}, {10, 1, 11}, {11, 1, 12},
+	{12, 1, 13}, {13, 1, 14}, {14, 1, 15}, {15, 1, 16},
+	{16, 1, 17}, {17, 1, 18}, {18, 1, 19}, {19, 1, 20},
+	{20, 1, 21}, {21, 1, 22}, {22, 1, 23}, {23, 1, 24},
+	{24, 1, 25}, {25, 1, 26},
+
+	/* bit8: /128 */
+	{256, 1, 1 * 128}, {257, 1, 2 * 128}, {258, 1, 3 * 128}, {259, 1, 4 * 128},
+	{260, 1, 5 * 128}, {261, 1, 6 * 128}, {262, 1, 7 * 128}, {263, 1, 8 * 128},
+	{264, 1, 9 * 128}, {265, 1, 10 * 128}, {266, 1, 11 * 128}, {267, 1, 12 * 128},
+	{268, 1, 13 * 128}, {269, 1, 14 * 128}, {270, 1, 15 * 128}, {271, 1, 16 * 128},
+	{272, 1, 17 * 128}, {273, 1, 18 * 128}, {274, 1, 19 * 128}, {275, 1, 20 * 128},
+	{276, 1, 21 * 128}, {277, 1, 22 * 128}, {278, 1, 23 * 128}, {279, 1, 24 * 128},
+	{280, 1, 25 * 128}, {281, 1, 26 * 128},
+
+	{0, 0},
+};
+
+static struct clk_factor_table lcd_factor_table[] = {
+	/* bit0 ~ 3 */
+	{0, 1, 1}, {1, 1, 2}, {2, 1, 3}, {3, 1, 4},
+	{4, 1, 5}, {5, 1, 6}, {6, 1, 7}, {7, 1, 8},
+	{8, 1, 9}, {9, 1, 10}, {10, 1, 11}, {11, 1, 12},
+
+	/* bit8: /7 */
+	{256, 1, 1 * 7}, {257, 1, 2 * 7}, {258, 1, 3 * 7}, {259, 1, 4 * 7},
+	{260, 1, 5 * 7}, {261, 1, 6 * 7}, {262, 1, 7 * 7}, {263, 1, 8 * 7},
+	{264, 1, 9 * 7}, {265, 1, 10 * 7}, {266, 1, 11 * 7}, {267, 1, 12 * 7},
+	{0, 0},
+};
+
+static struct clk_div_table hdmia_div_table[] = {
+	{0, 1},   {1, 2},   {2, 3},   {3, 4},
+	{4, 6},   {5, 8},   {6, 12},  {7, 16},
+	{8, 24},
+	{0, 0},
+};
+
+static struct clk_div_table rmii_div_table[] = {
+	{0, 4},   {1, 10},
+};
+
+/* divider clocks */
+static OWL_DIVIDER(clk_noc0, "noc0_clk", "noc0_clk_mux", CMU_BUSCLK, 16, 2, NULL, 0, 0);
+static OWL_DIVIDER(clk_noc1, "noc1_clk", "noc1_clk_mux", CMU_BUSCLK1, 16, 2, NULL, 0, 0);
+static OWL_DIVIDER(clk_noc1_clk_div, "noc1_clk_div", "noc1_clk", CMU_BUSCLK1, 20, 1, NULL, 0, 0);
+static OWL_DIVIDER(clk_hp_clk_div, "hp_clk_div", "hp_clk_mux", CMU_BUSCLK1, 12, 2, NULL, 0, 0);
+static OWL_DIVIDER(clk_ahb, "ahb_clk", "hp_clk_div", CMU_BUSCLK1, 2, 2, NULL, 0, 0);
+static OWL_DIVIDER(clk_apb, "apb_clk", "ahb_clk", CMU_BUSCLK1, 14, 2, NULL, 0, 0);
+static OWL_DIVIDER(clk_sensor0, "sensor0", "sensor_src", CMU_SENSORCLK, 0, 4, NULL, 0, 0);
+static OWL_DIVIDER(clk_sensor1, "sensor1", "sensor_src", CMU_SENSORCLK, 8, 4, NULL, 0, 0);
+static OWL_DIVIDER(clk_rmii_ref, "rmii_ref", "ethernet_pll", CMU_ETHERNETPLL, 2, 1, rmii_div_table, 0, 0);
+
+static struct clk_factor_table de_factor_table[] = {
+	{0, 1, 1}, {1, 2, 3}, {2, 1, 2}, {3, 2, 5},
+	{4, 1, 3}, {5, 1, 4}, {6, 1, 6}, {7, 1, 8},
+	{8, 1, 12}, {0, 0, 0},
+};
+
+static struct clk_factor_table hde_factor_table[] = {
+	{0, 1, 1}, {1, 2, 3}, {2, 1, 2}, {3, 2, 5},
+	{4, 1, 3}, {5, 1, 4}, {6, 1, 6}, {7, 1, 8},
+	{0, 0, 0},
+};
+
+/* gate clocks */
+static OWL_GATE(clk_gpio, "gpio", "apb_clk", CMU_DEVCLKEN1, 25, 0, 0);
+static OWL_GATE(clk_dmac, "dmac", "hp_clk_div", CMU_DEVCLKEN0, 17, 0, 0);
+static OWL_GATE(clk_timer, "timer", "hosc", CMU_DEVCLKEN1, 22, 0, 0);
+static OWL_GATE_NO_PARENT(clk_dsi, "dsi_clk", CMU_DEVCLKEN0, 2, 0, 0);
+static OWL_GATE_NO_PARENT(clk_tvout, "tvout_clk", CMU_DEVCLKEN0, 3, 0, 0);
+static OWL_GATE_NO_PARENT(clk_hdmi_dev, "hdmi_dev", CMU_DEVCLKEN0, 5, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb3_480mpll0, "usb3_480mpll0", CMU_USBPLL, 3, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb3_480mphy0, "usb3_480mphy0", CMU_USBPLL, 2, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb3_5gphy, "usb3_5gphy", CMU_USBPLL, 1, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb3_cce, "usb3_cce", CMU_DEVCLKEN0, 25, 0, 0);
+static OWL_GATE(clk_i2c0, "i2c0", "hosc", CMU_DEVCLKEN1, 0, 0, 0);
+static OWL_GATE(clk_i2c1, "i2c1", "hosc", CMU_DEVCLKEN1, 1, 0, 0);
+static OWL_GATE(clk_i2c2, "i2c2", "hosc", CMU_DEVCLKEN1, 2, 0, 0);
+static OWL_GATE(clk_i2c3, "i2c3", "hosc", CMU_DEVCLKEN1, 3, 0, 0);
+static OWL_GATE(clk_spi0, "spi0", "ahb_clk", CMU_DEVCLKEN1, 4, 0, 0);
+static OWL_GATE(clk_spi1, "spi1", "ahb_clk", CMU_DEVCLKEN1, 5, 0, 0);
+static OWL_GATE(clk_spi2, "spi2", "ahb_clk", CMU_DEVCLKEN1, 6, 0, 0);
+static OWL_GATE(clk_spi3, "spi3", "ahb_clk", CMU_DEVCLKEN1, 7, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb2h0_pllen, "usbh0_pllen", CMU_USBPLL, 12, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb2h0_phy, "usbh0_phy", CMU_USBPLL, 10, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb2h0_cce, "usbh0_cce", CMU_DEVCLKEN0, 26, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb2h1_pllen, "usbh1_pllen", CMU_USBPLL, 13, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb2h1_phy, "usbh1_phy", CMU_USBPLL, 11, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb2h1_cce, "usbh1_cce", CMU_DEVCLKEN0, 27, 0, 0);
+static OWL_GATE_NO_PARENT(clk_irc_switch, "irc_switch", CMU_DEVCLKEN1, 15, 0, 0);
+
+/* composite clocks */
+
+static OWL_COMP_DIV(clk_csi, "csi", csi_clk_mux_p,
+			OWL_MUX_HW(CMU_CSICLK, 4, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 13, 0),
+			OWL_DIVIDER_HW(CMU_CSICLK, 0, 4, 0, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_si, "si", csi_clk_mux_p,
+			OWL_MUX_HW(CMU_SICLK, 4, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 14,  0),
+			OWL_DIVIDER_HW(CMU_SICLK, 0, 4, 0, NULL),
+			0);
+
+static OWL_COMP_FACTOR(clk_de, "de", de_clk_mux_p,
+			OWL_MUX_HW(CMU_DECLK, 12, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 0,  0),
+			OWL_FACTOR_HW(CMU_DECLK, 0, 3, 0, de_factor_table),
+			0);
+
+static OWL_COMP_FACTOR(clk_hde, "hde", hde_clk_mux_p,
+			OWL_MUX_HW(CMU_HDECLK, 4, 2),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 9, 0),
+			OWL_FACTOR_HW(CMU_HDECLK, 0, 3, 0, hde_factor_table),
+			0);
+
+static OWL_COMP_FACTOR(clk_vde, "vde", hde_clk_mux_p,
+			OWL_MUX_HW(CMU_VDECLK, 4, 2),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 10,  0),
+			OWL_FACTOR_HW(CMU_VDECLK, 0, 3, 0, hde_factor_table),
+			0);
+
+static OWL_COMP_FACTOR(clk_vce, "vce", hde_clk_mux_p,
+			OWL_MUX_HW(CMU_VCECLK, 4, 2),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 11, 0),
+			OWL_FACTOR_HW(CMU_VCECLK, 0, 3, 0, hde_factor_table),
+			0);
+
+static OWL_COMP_DIV(clk_nand, "nand", nand_clk_mux_p,
+			OWL_MUX_HW(CMU_NANDCCLK, 8, 2),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 21, 0),
+			OWL_DIVIDER_HW(CMU_NANDCCLK, 0, 3, 0, NULL),
+			CLK_SET_RATE_PARENT);
+
+static OWL_COMP_FACTOR(clk_sd0, "sd0", sd_clk_mux_p,
+			OWL_MUX_HW(CMU_SD0CLK, 9, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 22, 0),
+			OWL_FACTOR_HW(CMU_SD0CLK, 0, 9, 0, sd_factor_table),
+			0);
+
+static OWL_COMP_FACTOR(clk_sd1, "sd1", sd_clk_mux_p,
+			OWL_MUX_HW(CMU_SD1CLK, 9, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 23, 0),
+			OWL_FACTOR_HW(CMU_SD1CLK, 0, 9, 0, sd_factor_table),
+			0);
+
+static OWL_COMP_FACTOR(clk_sd2, "sd2", sd_clk_mux_p,
+			OWL_MUX_HW(CMU_SD2CLK, 9, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 24, 0),
+			OWL_FACTOR_HW(CMU_SD2CLK, 0, 9, 0, sd_factor_table),
+			0);
+
+static OWL_COMP_DIV(clk_uart0, "uart0", uart_clk_mux_p,
+			OWL_MUX_HW(CMU_UART0CLK, 16, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 8, 0),
+			OWL_DIVIDER_HW(CMU_UART0CLK, 0, 9, CLK_DIVIDER_ROUND_CLOSEST, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_uart1, "uart1", uart_clk_mux_p,
+			OWL_MUX_HW(CMU_UART1CLK, 16, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 9, 0),
+			OWL_DIVIDER_HW(CMU_UART1CLK, 0, 9, CLK_DIVIDER_ROUND_CLOSEST, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_uart2, "uart2", uart_clk_mux_p,
+			OWL_MUX_HW(CMU_UART2CLK, 16, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 10, 0),
+			OWL_DIVIDER_HW(CMU_UART2CLK, 0, 9,  CLK_DIVIDER_ROUND_CLOSEST, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_uart3, "uart3", uart_clk_mux_p,
+			OWL_MUX_HW(CMU_UART3CLK, 16, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 11, 0),
+			OWL_DIVIDER_HW(CMU_UART3CLK, 0, 9,  CLK_DIVIDER_ROUND_CLOSEST, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_uart4, "uart4", uart_clk_mux_p,
+			OWL_MUX_HW(CMU_UART4CLK, 16, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 12, 0),
+			OWL_DIVIDER_HW(CMU_UART4CLK, 0, 9,  CLK_DIVIDER_ROUND_CLOSEST, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_uart5, "uart5", uart_clk_mux_p,
+			OWL_MUX_HW(CMU_UART5CLK, 16, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 13, 0),
+			OWL_DIVIDER_HW(CMU_UART5CLK, 0, 9,  CLK_DIVIDER_ROUND_CLOSEST, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_uart6, "uart6", uart_clk_mux_p,
+			OWL_MUX_HW(CMU_UART6CLK, 16, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 14, 0),
+			OWL_DIVIDER_HW(CMU_UART6CLK, 0, 9,  CLK_DIVIDER_ROUND_CLOSEST, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_pwm0, "pwm0", pwm_clk_mux_p,
+			OWL_MUX_HW(CMU_PWM0CLK, 12, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 16, 0),
+			OWL_DIVIDER_HW(CMU_PWM0CLK, 0, 10, 0, NULL),
+			CLK_IGNORE_UNUSED);
+
+static OWL_COMP_DIV(clk_pwm1, "pwm1", pwm_clk_mux_p,
+			OWL_MUX_HW(CMU_PWM1CLK, 12, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 17, 0),
+			OWL_DIVIDER_HW(CMU_PWM1CLK, 0, 10, 0, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_pwm2, "pwm2", pwm_clk_mux_p,
+			OWL_MUX_HW(CMU_PWM2CLK, 12, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 18, 0),
+			OWL_DIVIDER_HW(CMU_PWM2CLK, 0, 10, 0, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_pwm3, "pwm3", pwm_clk_mux_p,
+			OWL_MUX_HW(CMU_PWM3CLK, 12, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 19, 0),
+			OWL_DIVIDER_HW(CMU_PWM3CLK, 0, 10, 0, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_pwm4, "pwm4", pwm_clk_mux_p,
+			OWL_MUX_HW(CMU_PWM4CLK, 12, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 20, 0),
+			OWL_DIVIDER_HW(CMU_PWM4CLK, 0, 10, 0, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_pwm5, "pwm5", pwm_clk_mux_p,
+			OWL_MUX_HW(CMU_PWM5CLK, 12, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 21, 0),
+			OWL_DIVIDER_HW(CMU_PWM5CLK, 0, 10, 0, NULL),
+			0);
+
+static OWL_COMP_FACTOR(clk_gpu3d, "gpu3d", gpu_clk_mux_p,
+			OWL_MUX_HW(CMU_GPU3DCLK, 4, 3),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 8, 0),
+			OWL_FACTOR_HW(CMU_GPU3DCLK, 0, 3, 0, hde_factor_table),
+			0);
+
+static OWL_COMP_FACTOR(clk_lcd, "lcd", lcd_clk_mux_p,
+			OWL_MUX_HW(CMU_LCDCLK, 12, 2),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 1, 0),
+			OWL_FACTOR_HW(CMU_LCDCLK, 0, 9, 0, lcd_factor_table),
+			0);
+
+static OWL_COMP_DIV(clk_hdmi_audio, "hdmia", i2s_clk_mux_p,
+			OWL_MUX_HW(CMU_AUDIOPLL, 24, 1), /*CMU_AUDIOPLL 24,1 unused*/
+			OWL_GATE_HW(CMU_DEVCLKEN1, 28, 0),
+			OWL_DIVIDER_HW(CMU_AUDIOPLL, 24, 4, 0, hdmia_div_table),
+			0);
+
+static OWL_COMP_DIV(clk_i2srx, "i2srx", i2s_clk_mux_p,
+			OWL_MUX_HW(CMU_AUDIOPLL, 24, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 27, 0),
+			OWL_DIVIDER_HW(CMU_AUDIOPLL, 20, 4, 0, hdmia_div_table),
+			0);
+
+static OWL_COMP_DIV(clk_i2stx, "i2stx", i2s_clk_mux_p,
+			OWL_MUX_HW(CMU_AUDIOPLL, 24, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 26, 0),
+			OWL_DIVIDER_HW(CMU_AUDIOPLL, 16, 4, 0, hdmia_div_table),
+			0);
+
+/* for bluetooth pcm communication */
+static OWL_COMP_FIXED_FACTOR(clk_pcm1, "pcm1", "audio_pll",
+			OWL_GATE_HW(CMU_DEVCLKEN1, 31, 0),
+			1, 2, 0);
+
+static OWL_COMP_DIV(clk_sensor_src, "sensor_src", sensor_clk_mux_p,
+			OWL_MUX_HW(CMU_SENSORCLK, 4, 1),
+			{0},
+			OWL_DIVIDER_HW(CMU_SENSORCLK, 5, 2, 0, NULL),
+			0);
+
+static OWL_COMP_FIXED_FACTOR(clk_ethernet, "ethernet", "ethernet_pll",
+			OWL_GATE_HW(CMU_DEVCLKEN1, 23, 0),
+			1, 20, 0);
+
+static OWL_COMP_DIV_FIXED(clk_thermal_sensor, "thermal_sensor", "hosc",
+				OWL_GATE_HW(CMU_DEVCLKEN0, 31, 0),
+				OWL_DIVIDER_HW(CMU_SSTSCLK, 20, 10, 0, NULL),
+				0);
+
+static struct owl_clk_common *s700_clks[] = {
+	&clk_core_pll.common,
+	&clk_dev_pll.common,
+	&clk_ddr_pll.common,
+	&clk_nand_pll.common,
+	&clk_display_pll.common,
+	&clk_cvbs_pll .common,
+	&clk_audio_pll.common,
+	&clk_ethernet_pll.common,
+	&clk_cpu.common,
+	&clk_dev.common,
+	&clk_ahb.common,
+	&clk_apb.common,
+	&clk_dmac.common,
+	&clk_noc0_clk_mux.common,
+	&clk_noc1_clk_mux.common,
+	&clk_hp_clk_mux.common,
+	&clk_hp_clk_div.common,
+	&clk_noc1_clk_div.common,
+	&clk_noc0.common,
+	&clk_noc1.common,
+	&clk_sensor_src.common,
+	&clk_gpio.common,
+	&clk_timer.common,
+	&clk_dsi.common,
+	&clk_csi.common,
+	&clk_si.common,
+	&clk_de.common,
+	&clk_hde.common,
+	&clk_vde.common,
+	&clk_vce.common,
+	&clk_nand.common,
+	&clk_sd0.common,
+	&clk_sd1.common,
+	&clk_sd2.common,
+	&clk_uart0.common,
+	&clk_uart1.common,
+	&clk_uart2.common,
+	&clk_uart3.common,
+	&clk_uart4.common,
+	&clk_uart5.common,
+	&clk_uart6.common,
+	&clk_pwm0.common,
+	&clk_pwm1.common,
+	&clk_pwm2.common,
+	&clk_pwm3.common,
+	&clk_pwm4.common,
+	&clk_pwm5.common,
+	&clk_gpu3d.common,
+	&clk_i2c0.common,
+	&clk_i2c1.common,
+	&clk_i2c2.common,
+	&clk_i2c3.common,
+	&clk_spi0.common,
+	&clk_spi1.common,
+	&clk_spi2.common,
+	&clk_spi3.common,
+	&clk_usb3_480mpll0.common,
+	&clk_usb3_480mphy0.common,
+	&clk_usb3_5gphy.common,
+	&clk_usb3_cce.common,
+	&clk_lcd.common,
+	&clk_hdmi_audio.common,
+	&clk_i2srx.common,
+	&clk_i2stx.common,
+	&clk_sensor0.common,
+	&clk_sensor1.common,
+	&clk_hdmi_dev.common,
+	&clk_ethernet.common,
+	&clk_rmii_ref.common,
+	&clk_usb2h0_pllen.common,
+	&clk_usb2h0_phy.common,
+	&clk_usb2h0_cce.common,
+	&clk_usb2h1_pllen.common,
+	&clk_usb2h1_phy.common,
+	&clk_usb2h1_cce.common,
+	&clk_tvout.common,
+	&clk_thermal_sensor.common,
+	&clk_irc_switch.common,
+	&clk_pcm1.common,
+};
+
+static struct clk_hw_onecell_data s700_hw_clks = {
+	.hws    = {
+			[CLK_CORE_PLL]				= &clk_core_pll.common.hw,
+			[CLK_DEV_PLL]				= &clk_dev_pll.common.hw,
+			[CLK_DDR_PLL]				= &clk_ddr_pll.common.hw,
+			[CLK_NAND_PLL]				= &clk_nand_pll.common.hw,
+			[CLK_DISPLAY_PLL]			= &clk_display_pll.common.hw,
+			[CLK_CVBS_PLL]				= &clk_cvbs_pll .common.hw,
+			[CLK_AUDIO_PLL]				= &clk_audio_pll.common.hw,
+			[CLK_ETHERNET_PLL]			= &clk_ethernet_pll.common.hw,
+			[CLK_CPU]				= &clk_cpu.common.hw,
+			[CLK_DEV]				= &clk_dev.common.hw,
+			[CLK_AHB]				= &clk_ahb.common.hw,
+			[CLK_APB]				= &clk_apb.common.hw,
+			[CLK_DMAC]				= &clk_dmac.common.hw,
+			[CLK_NOC0_CLK_MUX]			= &clk_noc0_clk_mux.common.hw,
+			[CLK_NOC1_CLK_MUX]			= &clk_noc1_clk_mux.common.hw,
+			[CLK_HP_CLK_MUX]			= &clk_hp_clk_mux.common.hw,
+			[CLK_HP_CLK_DIV]			= &clk_hp_clk_div.common.hw,
+			[CLK_NOC1_CLK_DIV]			= &clk_noc1_clk_div.common.hw,
+			[CLK_NOC0]				= &clk_noc0.common.hw,
+			[CLK_NOC1]				= &clk_noc1.common.hw,
+			[CLK_SENOR_SRC]				= &clk_sensor_src.common.hw,
+			[CLK_GPIO]				= &clk_gpio.common.hw,
+			[CLK_TIMER]				= &clk_timer.common.hw,
+			[CLK_DSI]				= &clk_dsi.common.hw,
+			[CLK_CSI]				= &clk_csi.common.hw,
+			[CLK_SI]				= &clk_si.common.hw,
+			[CLK_DE]				= &clk_de.common.hw,
+			[CLK_HDE]				= &clk_hde.common.hw,
+			[CLK_VDE]				= &clk_vde.common.hw,
+			[CLK_VCE]				= &clk_vce.common.hw,
+			[CLK_NAND]				= &clk_nand.common.hw,
+			[CLK_SD0]				= &clk_sd0.common.hw,
+			[CLK_SD1]				= &clk_sd1.common.hw,
+			[CLK_SD2]				= &clk_sd2.common.hw,
+			[CLK_UART0]				= &clk_uart0.common.hw,
+			[CLK_UART1]				= &clk_uart1.common.hw,
+			[CLK_UART2]				= &clk_uart2.common.hw,
+			[CLK_UART3]				= &clk_uart3.common.hw,
+			[CLK_UART4]				= &clk_uart4.common.hw,
+			[CLK_UART5]				= &clk_uart5.common.hw,
+			[CLK_UART6]				= &clk_uart6.common.hw,
+			[CLK_PWM0]				= &clk_pwm0.common.hw,
+			[CLK_PWM1]				= &clk_pwm1.common.hw,
+			[CLK_PWM2]				= &clk_pwm2.common.hw,
+			[CLK_PWM3]				= &clk_pwm3.common.hw,
+			[CLK_PWM4]				= &clk_pwm4.common.hw,
+			[CLK_PWM5]				= &clk_pwm5.common.hw,
+			[CLK_GPU3D]				= &clk_gpu3d.common.hw,
+			[CLK_I2C0]				= &clk_i2c0.common.hw,
+			[CLK_I2C1]				= &clk_i2c1.common.hw,
+			[CLK_I2C2]				= &clk_i2c2.common.hw,
+			[CLK_I2C3]				= &clk_i2c3.common.hw,
+			[CLK_SPI0]				= &clk_spi0.common.hw,
+			[CLK_SPI1]				= &clk_spi1.common.hw,
+			[CLK_SPI2]				= &clk_spi2.common.hw,
+			[CLK_SPI3]				= &clk_spi3.common.hw,
+			[CLK_USB3_480MPLL0]			= &clk_usb3_480mpll0.common.hw,
+			[CLK_USB3_480MPHY0]			= &clk_usb3_480mphy0.common.hw,
+			[CLK_USB3_5GPHY]			= &clk_usb3_5gphy.common.hw,
+			[CLK_USB3_CCE]				= &clk_usb3_cce.common.hw,
+			[CLK_LCD]				= &clk_lcd.common.hw,
+			[CLK_HDMI_AUDIO]			= &clk_hdmi_audio.common.hw,
+			[CLK_I2SRX]				= &clk_i2srx.common.hw,
+			[CLK_I2STX]				= &clk_i2stx.common.hw,
+			[CLK_SENSOR0]				= &clk_sensor0.common.hw,
+			[CLK_SENSOR1]				= &clk_sensor1.common.hw,
+			[CLK_HDMI_DEV]				= &clk_hdmi_dev.common.hw,
+			[CLK_ETHERNET]				= &clk_ethernet.common.hw,
+			[CLK_RMII_REF]				= &clk_rmii_ref.common.hw,
+			[CLK_USB2H0_PLLEN]			= &clk_usb2h0_pllen.common.hw,
+			[CLK_USB2H0_PHY]			= &clk_usb2h0_phy.common.hw,
+			[CLK_USB2H0_CCE]			= &clk_usb2h0_cce.common.hw,
+			[CLK_USB2H1_PLLEN]			= &clk_usb2h1_pllen.common.hw,
+			[CLK_USB2H1_PHY]			= &clk_usb2h1_phy.common.hw,
+			[CLK_USB2H1_CCE]			= &clk_usb2h1_cce.common.hw,
+			[CLK_TVOUT]				= &clk_tvout.common.hw,
+			[CLK_THERMAL_SENSOR]			= &clk_thermal_sensor.common.hw,
+			[CLK_IRC_SWITCH]			= &clk_irc_switch.common.hw,
+			[CLK_PCM1]				= &clk_pcm1.common.hw,
+		},
+		.num    = CLK_NR_CLKS,
+};
+
+static const struct owl_clk_desc s700_clk_desc = {
+	.clks       = s700_clks,
+	.num_clks   = ARRAY_SIZE(s700_clks),
+
+	.hw_clks    = &s700_hw_clks,
+};
+
+static int s700_clk_probe(struct platform_device *pdev)
+{
+	const struct owl_clk_desc *desc;
+
+	desc = &s700_clk_desc;
+	owl_clk_regmap_init(pdev, desc);
+
+	return owl_clk_probe(&pdev->dev, desc->hw_clks);
+}
+
+static const struct of_device_id s700_clk_of_match[] = {
+	{ .compatible = "actions,s700-cmu", },
+	{ /* sentinel */ }
+};
+
+static struct platform_driver s700_clk_driver = {
+	.probe = s700_clk_probe,
+	.driver = {
+		.name = "s700-cmu",
+		.of_match_table = s700_clk_of_match
+	},
+};
+
+static int __init s700_clk_init(void)
+{
+	return platform_driver_register(&s700_clk_driver);
+}
+core_initcall(s700_clk_init);
diff --git a/drivers/clk/at91/Makefile b/drivers/clk/at91/Makefile
index 082596f37c1d..facc169ebb68 100644
--- a/drivers/clk/at91/Makefile
+++ b/drivers/clk/at91/Makefile
@@ -13,3 +13,4 @@ obj-$(CONFIG_HAVE_AT91_USB_CLK)		+= clk-usb.o
 obj-$(CONFIG_HAVE_AT91_SMD)		+= clk-smd.o
 obj-$(CONFIG_HAVE_AT91_H32MX)		+= clk-h32mx.o
 obj-$(CONFIG_HAVE_AT91_GENERATED_CLK)	+= clk-generated.o
+obj-$(CONFIG_HAVE_AT91_I2S_MUX_CLK)	+= clk-i2s-mux.o
diff --git a/drivers/clk/at91/clk-i2s-mux.c b/drivers/clk/at91/clk-i2s-mux.c
new file mode 100644
index 000000000000..f0c3c3079f04
--- /dev/null
+++ b/drivers/clk/at91/clk-i2s-mux.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2018 Microchip Technology Inc,
+ *                     Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
+ *
+ *
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/of.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+#include <soc/at91/atmel-sfr.h>
+
+#define	I2S_BUS_NR	2
+
+struct clk_i2s_mux {
+	struct clk_hw hw;
+	struct regmap *regmap;
+	u8 bus_id;
+};
+
+#define to_clk_i2s_mux(hw) container_of(hw, struct clk_i2s_mux, hw)
+
+static u8 clk_i2s_mux_get_parent(struct clk_hw *hw)
+{
+	struct clk_i2s_mux *mux = to_clk_i2s_mux(hw);
+	u32 val;
+
+	regmap_read(mux->regmap, AT91_SFR_I2SCLKSEL, &val);
+
+	return (val & BIT(mux->bus_id)) >> mux->bus_id;
+}
+
+static int clk_i2s_mux_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct clk_i2s_mux *mux = to_clk_i2s_mux(hw);
+
+	return regmap_update_bits(mux->regmap, AT91_SFR_I2SCLKSEL,
+				  BIT(mux->bus_id), index << mux->bus_id);
+}
+
+static const struct clk_ops clk_i2s_mux_ops = {
+	.get_parent = clk_i2s_mux_get_parent,
+	.set_parent = clk_i2s_mux_set_parent,
+	.determine_rate = __clk_mux_determine_rate,
+};
+
+static struct clk_hw * __init
+at91_clk_i2s_mux_register(struct regmap *regmap, const char *name,
+			  const char * const *parent_names,
+			  unsigned int num_parents, u8 bus_id)
+{
+	struct clk_init_data init = {};
+	struct clk_i2s_mux *i2s_ck;
+	int ret;
+
+	i2s_ck = kzalloc(sizeof(*i2s_ck), GFP_KERNEL);
+	if (!i2s_ck)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = name;
+	init.ops = &clk_i2s_mux_ops;
+	init.parent_names = parent_names;
+	init.num_parents = num_parents;
+
+	i2s_ck->hw.init = &init;
+	i2s_ck->bus_id = bus_id;
+	i2s_ck->regmap = regmap;
+
+	ret = clk_hw_register(NULL, &i2s_ck->hw);
+	if (ret) {
+		kfree(i2s_ck);
+		return ERR_PTR(ret);
+	}
+
+	return &i2s_ck->hw;
+}
+
+static void __init of_sama5d2_clk_i2s_mux_setup(struct device_node *np)
+{
+	struct regmap *regmap_sfr;
+	u8 bus_id;
+	const char *parent_names[2];
+	struct device_node *i2s_mux_np;
+	struct clk_hw *hw;
+	int ret;
+
+	regmap_sfr = syscon_regmap_lookup_by_compatible("atmel,sama5d2-sfr");
+	if (IS_ERR(regmap_sfr))
+		return;
+
+	for_each_child_of_node(np, i2s_mux_np) {
+		if (of_property_read_u8(i2s_mux_np, "reg", &bus_id))
+			continue;
+
+		if (bus_id > I2S_BUS_NR)
+			continue;
+
+		ret = of_clk_parent_fill(i2s_mux_np, parent_names, 2);
+		if (ret != 2)
+			continue;
+
+		hw = at91_clk_i2s_mux_register(regmap_sfr, i2s_mux_np->name,
+					       parent_names, 2, bus_id);
+		if (IS_ERR(hw))
+			continue;
+
+		of_clk_add_hw_provider(i2s_mux_np, of_clk_hw_simple_get, hw);
+	}
+}
+
+CLK_OF_DECLARE(sama5d2_clk_i2s_mux, "atmel,sama5d2-clk-i2s-mux",
+	       of_sama5d2_clk_i2s_mux_setup);
diff --git a/drivers/clk/clk-aspeed.c b/drivers/clk/clk-aspeed.c
index 7b70a074095d..596136793fc4 100644
--- a/drivers/clk/clk-aspeed.c
+++ b/drivers/clk/clk-aspeed.c
@@ -109,7 +109,7 @@ static const struct aspeed_gate_data aspeed_gates[] = {
 	[ASPEED_CLK_GATE_RSACLK] =	{ 24, -1, "rsaclk-gate",	NULL,	0 }, /* RSA */
 	[ASPEED_CLK_GATE_UART3CLK] =	{ 25, -1, "uart3clk-gate",	"uart",	0 }, /* UART3 */
 	[ASPEED_CLK_GATE_UART4CLK] =	{ 26, -1, "uart4clk-gate",	"uart",	0 }, /* UART4 */
-	[ASPEED_CLK_GATE_SDCLKCLK] =	{ 27, 16, "sdclk-gate",		NULL,	0 }, /* SDIO/SD */
+	[ASPEED_CLK_GATE_SDCLK] =	{ 27, 16, "sdclk-gate",		NULL,	0 }, /* SDIO/SD */
 	[ASPEED_CLK_GATE_LHCCLK] =	{ 28, -1, "lhclk-gate",		"lhclk", 0 }, /* LPC master/LPC+ */
 };
 
diff --git a/drivers/clk/clk-cs2000-cp.c b/drivers/clk/clk-cs2000-cp.c
index a2f8c42e527a..92bc4aca0f95 100644
--- a/drivers/clk/clk-cs2000-cp.c
+++ b/drivers/clk/clk-cs2000-cp.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * CS2000  --  CIRRUS LOGIC Fractional-N Clock Synthesizer & Clock Multiplier
  *
  * Copyright (C) 2015 Renesas Electronics Corporation
  * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/clk-provider.h>
 #include <linux/delay.h>
diff --git a/drivers/clk/clk-fixed-factor.c b/drivers/clk/clk-fixed-factor.c
index a5d402de5584..20724abd38bd 100644
--- a/drivers/clk/clk-fixed-factor.c
+++ b/drivers/clk/clk-fixed-factor.c
@@ -177,8 +177,15 @@ static struct clk *_of_fixed_factor_clk_setup(struct device_node *node)
 
 	clk = clk_register_fixed_factor(NULL, clk_name, parent_name, flags,
 					mult, div);
-	if (IS_ERR(clk))
+	if (IS_ERR(clk)) {
+		/*
+		 * If parent clock is not registered, registration would fail.
+		 * Clear OF_POPULATED flag so that clock registration can be
+		 * attempted again from probe function.
+		 */
+		of_node_clear_flag(node, OF_POPULATED);
 		return clk;
+	}
 
 	ret = of_clk_add_provider(node, of_clk_src_simple_get, clk);
 	if (ret) {
diff --git a/drivers/clk/clk-max9485.c b/drivers/clk/clk-max9485.c
new file mode 100644
index 000000000000..5e80f3d090f3
--- /dev/null
+++ b/drivers/clk/clk-max9485.c
@@ -0,0 +1,387 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/regulator/consumer.h>
+
+#include <dt-bindings/clock/maxim,max9485.h>
+
+#define MAX9485_NUM_CLKS 4
+
+/* This chip has only one register of 8 bit width. */
+
+#define MAX9485_FS_12KHZ	(0 << 0)
+#define MAX9485_FS_32KHZ	(1 << 0)
+#define MAX9485_FS_44_1KHZ	(2 << 0)
+#define MAX9485_FS_48KHZ	(3 << 0)
+
+#define MAX9485_SCALE_256	(0 << 2)
+#define MAX9485_SCALE_384	(1 << 2)
+#define MAX9485_SCALE_768	(2 << 2)
+
+#define MAX9485_DOUBLE		BIT(4)
+#define MAX9485_CLKOUT1_ENABLE	BIT(5)
+#define MAX9485_CLKOUT2_ENABLE	BIT(6)
+#define MAX9485_MCLK_ENABLE	BIT(7)
+#define MAX9485_FREQ_MASK	0x1f
+
+struct max9485_rate {
+	unsigned long out;
+	u8 reg_value;
+};
+
+/*
+ * Ordered by frequency. For frequency the hardware can generate with
+ * multiple settings, the one with lowest jitter is listed first.
+ */
+static const struct max9485_rate max9485_rates[] = {
+	{  3072000, MAX9485_FS_12KHZ   | MAX9485_SCALE_256 },
+	{  4608000, MAX9485_FS_12KHZ   | MAX9485_SCALE_384 },
+	{  8192000, MAX9485_FS_32KHZ   | MAX9485_SCALE_256 },
+	{  9126000, MAX9485_FS_12KHZ   | MAX9485_SCALE_768 },
+	{ 11289600, MAX9485_FS_44_1KHZ | MAX9485_SCALE_256 },
+	{ 12288000, MAX9485_FS_48KHZ   | MAX9485_SCALE_256 },
+	{ 12288000, MAX9485_FS_32KHZ   | MAX9485_SCALE_384 },
+	{ 16384000, MAX9485_FS_32KHZ   | MAX9485_SCALE_256 | MAX9485_DOUBLE },
+	{ 16934400, MAX9485_FS_44_1KHZ | MAX9485_SCALE_384 },
+	{ 18384000, MAX9485_FS_48KHZ   | MAX9485_SCALE_384 },
+	{ 22579200, MAX9485_FS_44_1KHZ | MAX9485_SCALE_256 | MAX9485_DOUBLE },
+	{ 24576000, MAX9485_FS_48KHZ   | MAX9485_SCALE_256 | MAX9485_DOUBLE },
+	{ 24576000, MAX9485_FS_32KHZ   | MAX9485_SCALE_384 | MAX9485_DOUBLE },
+	{ 24576000, MAX9485_FS_32KHZ   | MAX9485_SCALE_768 },
+	{ 33868800, MAX9485_FS_44_1KHZ | MAX9485_SCALE_384 | MAX9485_DOUBLE },
+	{ 33868800, MAX9485_FS_44_1KHZ | MAX9485_SCALE_768 },
+	{ 36864000, MAX9485_FS_48KHZ   | MAX9485_SCALE_384 | MAX9485_DOUBLE },
+	{ 36864000, MAX9485_FS_48KHZ   | MAX9485_SCALE_768 },
+	{ 49152000, MAX9485_FS_32KHZ   | MAX9485_SCALE_768 | MAX9485_DOUBLE },
+	{ 67737600, MAX9485_FS_44_1KHZ | MAX9485_SCALE_768 | MAX9485_DOUBLE },
+	{ 73728000, MAX9485_FS_48KHZ   | MAX9485_SCALE_768 | MAX9485_DOUBLE },
+	{ } /* sentinel */
+};
+
+struct max9485_driver_data;
+
+struct max9485_clk_hw {
+	struct clk_hw hw;
+	struct clk_init_data init;
+	u8 enable_bit;
+	struct max9485_driver_data *drvdata;
+};
+
+struct max9485_driver_data {
+	struct clk *xclk;
+	struct i2c_client *client;
+	u8 reg_value;
+	struct regulator *supply;
+	struct gpio_desc *reset_gpio;
+	struct max9485_clk_hw hw[MAX9485_NUM_CLKS];
+};
+
+static inline struct max9485_clk_hw *to_max9485_clk(struct clk_hw *hw)
+{
+	return container_of(hw, struct max9485_clk_hw, hw);
+}
+
+static int max9485_update_bits(struct max9485_driver_data *drvdata,
+			       u8 mask, u8 value)
+{
+	int ret;
+
+	drvdata->reg_value &= ~mask;
+	drvdata->reg_value |= value;
+
+	dev_dbg(&drvdata->client->dev,
+		"updating mask 0x%02x value 0x%02x -> 0x%02x\n",
+		mask, value, drvdata->reg_value);
+
+	ret = i2c_master_send(drvdata->client,
+			      &drvdata->reg_value,
+			      sizeof(drvdata->reg_value));
+
+	return ret < 0 ? ret : 0;
+}
+
+static int max9485_clk_prepare(struct clk_hw *hw)
+{
+	struct max9485_clk_hw *clk_hw = to_max9485_clk(hw);
+
+	return max9485_update_bits(clk_hw->drvdata,
+				   clk_hw->enable_bit,
+				   clk_hw->enable_bit);
+}
+
+static void max9485_clk_unprepare(struct clk_hw *hw)
+{
+	struct max9485_clk_hw *clk_hw = to_max9485_clk(hw);
+
+	max9485_update_bits(clk_hw->drvdata, clk_hw->enable_bit, 0);
+}
+
+/*
+ * CLKOUT - configurable clock output
+ */
+static int max9485_clkout_set_rate(struct clk_hw *hw, unsigned long rate,
+				   unsigned long parent_rate)
+{
+	struct max9485_clk_hw *clk_hw = to_max9485_clk(hw);
+	const struct max9485_rate *entry;
+
+	for (entry = max9485_rates; entry->out != 0; entry++)
+		if (entry->out == rate)
+			break;
+
+	if (entry->out == 0)
+		return -EINVAL;
+
+	return max9485_update_bits(clk_hw->drvdata,
+				   MAX9485_FREQ_MASK,
+				   entry->reg_value);
+}
+
+static unsigned long max9485_clkout_recalc_rate(struct clk_hw *hw,
+						unsigned long parent_rate)
+{
+	struct max9485_clk_hw *clk_hw = to_max9485_clk(hw);
+	struct max9485_driver_data *drvdata = clk_hw->drvdata;
+	u8 val = drvdata->reg_value & MAX9485_FREQ_MASK;
+	const struct max9485_rate *entry;
+
+	for (entry = max9485_rates; entry->out != 0; entry++)
+		if (val == entry->reg_value)
+			return entry->out;
+
+	return 0;
+}
+
+static long max9485_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
+				      unsigned long *parent_rate)
+{
+	const struct max9485_rate *curr, *prev = NULL;
+
+	for (curr = max9485_rates; curr->out != 0; curr++) {
+		/* Exact matches */
+		if (curr->out == rate)
+			return rate;
+
+		/*
+		 * Find the first entry that has a frequency higher than the
+		 * requested one.
+		 */
+		if (curr->out > rate) {
+			unsigned int mid;
+
+			/*
+			 * If this is the first entry, clamp the value to the
+			 * lowest possible frequency.
+			 */
+			if (!prev)
+				return curr->out;
+
+			/*
+			 * Otherwise, determine whether the previous entry or
+			 * current one is closer.
+			 */
+			mid = prev->out + ((curr->out - prev->out) / 2);
+
+			return (mid > rate) ? prev->out : curr->out;
+		}
+
+		prev = curr;
+	}
+
+	/* If the last entry was still too high, clamp the value */
+	return prev->out;
+}
+
+struct max9485_clk {
+	const char *name;
+	int parent_index;
+	const struct clk_ops ops;
+	u8 enable_bit;
+};
+
+static const struct max9485_clk max9485_clks[MAX9485_NUM_CLKS] = {
+	[MAX9485_MCLKOUT] = {
+		.name = "mclkout",
+		.parent_index = -1,
+		.enable_bit = MAX9485_MCLK_ENABLE,
+		.ops = {
+			.prepare	= max9485_clk_prepare,
+			.unprepare	= max9485_clk_unprepare,
+		},
+	},
+	[MAX9485_CLKOUT] = {
+		.name = "clkout",
+		.parent_index = -1,
+		.ops = {
+			.set_rate	= max9485_clkout_set_rate,
+			.round_rate	= max9485_clkout_round_rate,
+			.recalc_rate	= max9485_clkout_recalc_rate,
+		},
+	},
+	[MAX9485_CLKOUT1] = {
+		.name = "clkout1",
+		.parent_index = MAX9485_CLKOUT,
+		.enable_bit = MAX9485_CLKOUT1_ENABLE,
+		.ops = {
+			.prepare	= max9485_clk_prepare,
+			.unprepare	= max9485_clk_unprepare,
+		},
+	},
+	[MAX9485_CLKOUT2] = {
+		.name = "clkout2",
+		.parent_index = MAX9485_CLKOUT,
+		.enable_bit = MAX9485_CLKOUT2_ENABLE,
+		.ops = {
+			.prepare	= max9485_clk_prepare,
+			.unprepare	= max9485_clk_unprepare,
+		},
+	},
+};
+
+static struct clk_hw *
+max9485_of_clk_get(struct of_phandle_args *clkspec, void *data)
+{
+	struct max9485_driver_data *drvdata = data;
+	unsigned int idx = clkspec->args[0];
+
+	return &drvdata->hw[idx].hw;
+}
+
+static int max9485_i2c_probe(struct i2c_client *client,
+			     const struct i2c_device_id *id)
+{
+	struct max9485_driver_data *drvdata;
+	struct device *dev = &client->dev;
+	const char *xclk_name;
+	int i, ret;
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	drvdata->xclk = devm_clk_get(dev, "xclk");
+	if (IS_ERR(drvdata->xclk))
+		return PTR_ERR(drvdata->xclk);
+
+	xclk_name = __clk_get_name(drvdata->xclk);
+
+	drvdata->supply = devm_regulator_get(dev, "vdd");
+	if (IS_ERR(drvdata->supply))
+		return PTR_ERR(drvdata->supply);
+
+	ret = regulator_enable(drvdata->supply);
+	if (ret < 0)
+		return ret;
+
+	drvdata->reset_gpio =
+		devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(drvdata->reset_gpio))
+		return PTR_ERR(drvdata->reset_gpio);
+
+	i2c_set_clientdata(client, drvdata);
+	drvdata->client = client;
+
+	ret = i2c_master_recv(drvdata->client, &drvdata->reg_value,
+			      sizeof(drvdata->reg_value));
+	if (ret < 0) {
+		dev_warn(dev, "Unable to read device register: %d\n", ret);
+		return ret;
+	}
+
+	for (i = 0; i < MAX9485_NUM_CLKS; i++) {
+		int parent_index = max9485_clks[i].parent_index;
+		const char *name;
+
+		if (of_property_read_string_index(dev->of_node,
+						  "clock-output-names",
+						  i, &name) == 0) {
+			drvdata->hw[i].init.name = name;
+		} else {
+			drvdata->hw[i].init.name = max9485_clks[i].name;
+		}
+
+		drvdata->hw[i].init.ops = &max9485_clks[i].ops;
+		drvdata->hw[i].init.num_parents = 1;
+		drvdata->hw[i].init.flags = 0;
+
+		if (parent_index > 0) {
+			drvdata->hw[i].init.parent_names =
+				&drvdata->hw[parent_index].init.name;
+			drvdata->hw[i].init.flags |= CLK_SET_RATE_PARENT;
+		} else {
+			drvdata->hw[i].init.parent_names = &xclk_name;
+		}
+
+		drvdata->hw[i].enable_bit = max9485_clks[i].enable_bit;
+		drvdata->hw[i].hw.init = &drvdata->hw[i].init;
+		drvdata->hw[i].drvdata = drvdata;
+
+		ret = devm_clk_hw_register(dev, &drvdata->hw[i].hw);
+		if (ret < 0)
+			return ret;
+	}
+
+	return devm_of_clk_add_hw_provider(dev, max9485_of_clk_get, drvdata);
+}
+
+static int __maybe_unused max9485_suspend(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct max9485_driver_data *drvdata = i2c_get_clientdata(client);
+
+	gpiod_set_value_cansleep(drvdata->reset_gpio, 0);
+
+	return 0;
+}
+
+static int __maybe_unused max9485_resume(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct max9485_driver_data *drvdata = i2c_get_clientdata(client);
+	int ret;
+
+	gpiod_set_value_cansleep(drvdata->reset_gpio, 1);
+
+	ret = i2c_master_send(client, &drvdata->reg_value,
+			      sizeof(drvdata->reg_value));
+
+	return ret < 0 ? ret : 0;
+}
+
+static const struct dev_pm_ops max9485_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(max9485_suspend, max9485_resume)
+};
+
+static const struct of_device_id max9485_dt_ids[] = {
+	{ .compatible = "maxim,max9485", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, max9485_dt_ids);
+
+static const struct i2c_device_id max9485_i2c_ids[] = {
+	{ .name = "max9485", },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, max9485_i2c_ids);
+
+static struct i2c_driver max9485_driver = {
+	.driver = {
+		.name		= "max9485",
+		.pm		= &max9485_pm_ops,
+		.of_match_table	= max9485_dt_ids,
+	},
+	.probe = max9485_i2c_probe,
+	.id_table = max9485_i2c_ids,
+};
+module_i2c_driver(max9485_driver);
+
+MODULE_AUTHOR("Daniel Mack <daniel@zonque.org>");
+MODULE_DESCRIPTION("MAX9485 Programmable Audio Clock Generator");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/clk-scmi.c b/drivers/clk/clk-scmi.c
index bb2a6f2f5516..a985bf5e1ac6 100644
--- a/drivers/clk/clk-scmi.c
+++ b/drivers/clk/clk-scmi.c
@@ -38,7 +38,6 @@ static unsigned long scmi_clk_recalc_rate(struct clk_hw *hw,
 static long scmi_clk_round_rate(struct clk_hw *hw, unsigned long rate,
 				unsigned long *parent_rate)
 {
-	int step;
 	u64 fmin, fmax, ftmp;
 	struct scmi_clk *clk = to_scmi_clk(hw);
 
@@ -60,9 +59,9 @@ static long scmi_clk_round_rate(struct clk_hw *hw, unsigned long rate,
 
 	ftmp = rate - fmin;
 	ftmp += clk->info->range.step_size - 1; /* to round up */
-	step = do_div(ftmp, clk->info->range.step_size);
+	do_div(ftmp, clk->info->range.step_size);
 
-	return step * clk->info->range.step_size + fmin;
+	return ftmp * clk->info->range.step_size + fmin;
 }
 
 static int scmi_clk_set_rate(struct clk_hw *hw, unsigned long rate,
diff --git a/drivers/clk/clk-si514.c b/drivers/clk/clk-si514.c
index 09b6718956bd..153b3a2b5857 100644
--- a/drivers/clk/clk-si514.c
+++ b/drivers/clk/clk-si514.c
@@ -74,6 +74,33 @@ static int si514_enable_output(struct clk_si514 *data, bool enable)
 		SI514_CONTROL_OE, enable ? SI514_CONTROL_OE : 0);
 }
 
+static int si514_prepare(struct clk_hw *hw)
+{
+	struct clk_si514 *data = to_clk_si514(hw);
+
+	return si514_enable_output(data, true);
+}
+
+static void si514_unprepare(struct clk_hw *hw)
+{
+	struct clk_si514 *data = to_clk_si514(hw);
+
+	si514_enable_output(data, false);
+}
+
+static int si514_is_prepared(struct clk_hw *hw)
+{
+	struct clk_si514 *data = to_clk_si514(hw);
+	unsigned int val;
+	int err;
+
+	err = regmap_read(data->regmap, SI514_REG_CONTROL, &val);
+	if (err < 0)
+		return err;
+
+	return !!(val & SI514_CONTROL_OE);
+}
+
 /* Retrieve clock multiplier and dividers from hardware */
 static int si514_get_muldiv(struct clk_si514 *data,
 	struct clk_si514_muldiv *settings)
@@ -235,12 +262,17 @@ static int si514_set_rate(struct clk_hw *hw, unsigned long rate,
 {
 	struct clk_si514 *data = to_clk_si514(hw);
 	struct clk_si514_muldiv settings;
+	unsigned int old_oe_state;
 	int err;
 
 	err = si514_calc_muldiv(&settings, rate);
 	if (err)
 		return err;
 
+	err = regmap_read(data->regmap, SI514_REG_CONTROL, &old_oe_state);
+	if (err)
+		return err;
+
 	si514_enable_output(data, false);
 
 	err = si514_set_muldiv(data, &settings);
@@ -255,12 +287,16 @@ static int si514_set_rate(struct clk_hw *hw, unsigned long rate,
 	/* Applying a new frequency can take up to 10ms */
 	usleep_range(10000, 12000);
 
-	si514_enable_output(data, true);
+	if (old_oe_state & SI514_CONTROL_OE)
+		si514_enable_output(data, true);
 
 	return err;
 }
 
 static const struct clk_ops si514_clk_ops = {
+	.prepare = si514_prepare,
+	.unprepare = si514_unprepare,
+	.is_prepared = si514_is_prepared,
 	.recalc_rate = si514_recalc_rate,
 	.round_rate = si514_round_rate,
 	.set_rate = si514_set_rate,
diff --git a/drivers/clk/clk-si544.c b/drivers/clk/clk-si544.c
index 1e2a3b8f9454..64e607f3232a 100644
--- a/drivers/clk/clk-si544.c
+++ b/drivers/clk/clk-si544.c
@@ -86,6 +86,33 @@ static int si544_enable_output(struct clk_si544 *data, bool enable)
 		SI544_OE_STATE_ODC_OE, enable ? SI544_OE_STATE_ODC_OE : 0);
 }
 
+static int si544_prepare(struct clk_hw *hw)
+{
+	struct clk_si544 *data = to_clk_si544(hw);
+
+	return si544_enable_output(data, true);
+}
+
+static void si544_unprepare(struct clk_hw *hw)
+{
+	struct clk_si544 *data = to_clk_si544(hw);
+
+	si544_enable_output(data, false);
+}
+
+static int si544_is_prepared(struct clk_hw *hw)
+{
+	struct clk_si544 *data = to_clk_si544(hw);
+	unsigned int val;
+	int err;
+
+	err = regmap_read(data->regmap, SI544_REG_OE_STATE, &val);
+	if (err < 0)
+		return err;
+
+	return !!(val & SI544_OE_STATE_ODC_OE);
+}
+
 /* Retrieve clock multiplier and dividers from hardware */
 static int si544_get_muldiv(struct clk_si544 *data,
 	struct clk_si544_muldiv *settings)
@@ -273,6 +300,7 @@ static int si544_set_rate(struct clk_hw *hw, unsigned long rate,
 {
 	struct clk_si544 *data = to_clk_si544(hw);
 	struct clk_si544_muldiv settings;
+	unsigned int old_oe_state;
 	int err;
 
 	if (!is_valid_frequency(data, rate))
@@ -282,6 +310,10 @@ static int si544_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (err)
 		return err;
 
+	err = regmap_read(data->regmap, SI544_REG_OE_STATE, &old_oe_state);
+	if (err)
+		return err;
+
 	si544_enable_output(data, false);
 
 	/* Allow FCAL for this frequency update */
@@ -303,12 +335,16 @@ static int si544_set_rate(struct clk_hw *hw, unsigned long rate,
 	/* Applying a new frequency can take up to 10ms */
 	usleep_range(10000, 12000);
 
-	si544_enable_output(data, true);
+	if (old_oe_state & SI544_OE_STATE_ODC_OE)
+		si544_enable_output(data, true);
 
 	return err;
 }
 
 static const struct clk_ops si544_clk_ops = {
+	.prepare = si544_prepare,
+	.unprepare = si544_unprepare,
+	.is_prepared = si544_is_prepared,
 	.recalc_rate = si544_recalc_rate,
 	.round_rate = si544_round_rate,
 	.set_rate = si544_set_rate,
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index e2ed078abd90..d31055ae6ec6 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -67,6 +67,7 @@ struct clk_core {
 	unsigned long		max_rate;
 	unsigned long		accuracy;
 	int			phase;
+	struct clk_duty		duty;
 	struct hlist_head	children;
 	struct hlist_node	child_node;
 	struct hlist_head	clks;
@@ -690,6 +691,9 @@ static void clk_core_unprepare(struct clk_core *core)
 	    "Unpreparing critical %s\n", core->name))
 		return;
 
+	if (core->flags & CLK_SET_RATE_GATE)
+		clk_core_rate_unprotect(core);
+
 	if (--core->prepare_count > 0)
 		return;
 
@@ -764,6 +768,16 @@ static int clk_core_prepare(struct clk_core *core)
 
 	core->prepare_count++;
 
+	/*
+	 * CLK_SET_RATE_GATE is a special case of clock protection
+	 * Instead of a consumer claiming exclusive rate control, it is
+	 * actually the provider which prevents any consumer from making any
+	 * operation which could result in a rate change or rate glitch while
+	 * the clock is prepared.
+	 */
+	if (core->flags & CLK_SET_RATE_GATE)
+		clk_core_rate_protect(core);
+
 	return 0;
 unprepare:
 	clk_core_unprepare(core->parent);
@@ -1887,9 +1901,6 @@ static int clk_core_set_rate_nolock(struct clk_core *core,
 	if (clk_core_rate_is_protected(core))
 		return -EBUSY;
 
-	if ((core->flags & CLK_SET_RATE_GATE) && core->prepare_count)
-		return -EBUSY;
-
 	/* calculate new rates and get the topmost changed clock */
 	top = clk_calc_new_rates(core, req_rate);
 	if (!top)
@@ -2401,6 +2412,172 @@ int clk_get_phase(struct clk *clk)
 }
 EXPORT_SYMBOL_GPL(clk_get_phase);
 
+static void clk_core_reset_duty_cycle_nolock(struct clk_core *core)
+{
+	/* Assume a default value of 50% */
+	core->duty.num = 1;
+	core->duty.den = 2;
+}
+
+static int clk_core_update_duty_cycle_parent_nolock(struct clk_core *core);
+
+static int clk_core_update_duty_cycle_nolock(struct clk_core *core)
+{
+	struct clk_duty *duty = &core->duty;
+	int ret = 0;
+
+	if (!core->ops->get_duty_cycle)
+		return clk_core_update_duty_cycle_parent_nolock(core);
+
+	ret = core->ops->get_duty_cycle(core->hw, duty);
+	if (ret)
+		goto reset;
+
+	/* Don't trust the clock provider too much */
+	if (duty->den == 0 || duty->num > duty->den) {
+		ret = -EINVAL;
+		goto reset;
+	}
+
+	return 0;
+
+reset:
+	clk_core_reset_duty_cycle_nolock(core);
+	return ret;
+}
+
+static int clk_core_update_duty_cycle_parent_nolock(struct clk_core *core)
+{
+	int ret = 0;
+
+	if (core->parent &&
+	    core->flags & CLK_DUTY_CYCLE_PARENT) {
+		ret = clk_core_update_duty_cycle_nolock(core->parent);
+		memcpy(&core->duty, &core->parent->duty, sizeof(core->duty));
+	} else {
+		clk_core_reset_duty_cycle_nolock(core);
+	}
+
+	return ret;
+}
+
+static int clk_core_set_duty_cycle_parent_nolock(struct clk_core *core,
+						 struct clk_duty *duty);
+
+static int clk_core_set_duty_cycle_nolock(struct clk_core *core,
+					  struct clk_duty *duty)
+{
+	int ret;
+
+	lockdep_assert_held(&prepare_lock);
+
+	if (clk_core_rate_is_protected(core))
+		return -EBUSY;
+
+	trace_clk_set_duty_cycle(core, duty);
+
+	if (!core->ops->set_duty_cycle)
+		return clk_core_set_duty_cycle_parent_nolock(core, duty);
+
+	ret = core->ops->set_duty_cycle(core->hw, duty);
+	if (!ret)
+		memcpy(&core->duty, duty, sizeof(*duty));
+
+	trace_clk_set_duty_cycle_complete(core, duty);
+
+	return ret;
+}
+
+static int clk_core_set_duty_cycle_parent_nolock(struct clk_core *core,
+						 struct clk_duty *duty)
+{
+	int ret = 0;
+
+	if (core->parent &&
+	    core->flags & (CLK_DUTY_CYCLE_PARENT | CLK_SET_RATE_PARENT)) {
+		ret = clk_core_set_duty_cycle_nolock(core->parent, duty);
+		memcpy(&core->duty, &core->parent->duty, sizeof(core->duty));
+	}
+
+	return ret;
+}
+
+/**
+ * clk_set_duty_cycle - adjust the duty cycle ratio of a clock signal
+ * @clk: clock signal source
+ * @num: numerator of the duty cycle ratio to be applied
+ * @den: denominator of the duty cycle ratio to be applied
+ *
+ * Apply the duty cycle ratio if the ratio is valid and the clock can
+ * perform this operation
+ *
+ * Returns (0) on success, a negative errno otherwise.
+ */
+int clk_set_duty_cycle(struct clk *clk, unsigned int num, unsigned int den)
+{
+	int ret;
+	struct clk_duty duty;
+
+	if (!clk)
+		return 0;
+
+	/* sanity check the ratio */
+	if (den == 0 || num > den)
+		return -EINVAL;
+
+	duty.num = num;
+	duty.den = den;
+
+	clk_prepare_lock();
+
+	if (clk->exclusive_count)
+		clk_core_rate_unprotect(clk->core);
+
+	ret = clk_core_set_duty_cycle_nolock(clk->core, &duty);
+
+	if (clk->exclusive_count)
+		clk_core_rate_protect(clk->core);
+
+	clk_prepare_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(clk_set_duty_cycle);
+
+static int clk_core_get_scaled_duty_cycle(struct clk_core *core,
+					  unsigned int scale)
+{
+	struct clk_duty *duty = &core->duty;
+	int ret;
+
+	clk_prepare_lock();
+
+	ret = clk_core_update_duty_cycle_nolock(core);
+	if (!ret)
+		ret = mult_frac(scale, duty->num, duty->den);
+
+	clk_prepare_unlock();
+
+	return ret;
+}
+
+/**
+ * clk_get_scaled_duty_cycle - return the duty cycle ratio of a clock signal
+ * @clk: clock signal source
+ * @scale: scaling factor to be applied to represent the ratio as an integer
+ *
+ * Returns the duty cycle ratio of a clock node multiplied by the provided
+ * scaling factor, or negative errno on error.
+ */
+int clk_get_scaled_duty_cycle(struct clk *clk, unsigned int scale)
+{
+	if (!clk)
+		return 0;
+
+	return clk_core_get_scaled_duty_cycle(clk->core, scale);
+}
+EXPORT_SYMBOL_GPL(clk_get_scaled_duty_cycle);
+
 /**
  * clk_is_match - check if two clk's point to the same hardware clock
  * @p: clk compared against q
@@ -2454,12 +2631,13 @@ static void clk_summary_show_one(struct seq_file *s, struct clk_core *c,
 	if (!c)
 		return;
 
-	seq_printf(s, "%*s%-*s %7d %8d %8d %11lu %10lu %-3d\n",
+	seq_printf(s, "%*s%-*s %7d %8d %8d %11lu %10lu %5d %6d\n",
 		   level * 3 + 1, "",
 		   30 - level * 3, c->name,
 		   c->enable_count, c->prepare_count, c->protect_count,
 		   clk_core_get_rate(c), clk_core_get_accuracy(c),
-		   clk_core_get_phase(c));
+		   clk_core_get_phase(c),
+		   clk_core_get_scaled_duty_cycle(c, 100000));
 }
 
 static void clk_summary_show_subtree(struct seq_file *s, struct clk_core *c,
@@ -2481,9 +2659,9 @@ static int clk_summary_show(struct seq_file *s, void *data)
 	struct clk_core *c;
 	struct hlist_head **lists = (struct hlist_head **)s->private;
 
-	seq_puts(s, "                                 enable  prepare  protect                               \n");
-	seq_puts(s, "   clock                          count    count    count        rate   accuracy   phase\n");
-	seq_puts(s, "----------------------------------------------------------------------------------------\n");
+	seq_puts(s, "                                 enable  prepare  protect                                duty\n");
+	seq_puts(s, "   clock                          count    count    count        rate   accuracy phase  cycle\n");
+	seq_puts(s, "---------------------------------------------------------------------------------------------\n");
 
 	clk_prepare_lock();
 
@@ -2510,6 +2688,8 @@ static void clk_dump_one(struct seq_file *s, struct clk_core *c, int level)
 	seq_printf(s, "\"rate\": %lu,", clk_core_get_rate(c));
 	seq_printf(s, "\"accuracy\": %lu,", clk_core_get_accuracy(c));
 	seq_printf(s, "\"phase\": %d", clk_core_get_phase(c));
+	seq_printf(s, "\"duty_cycle\": %u",
+		   clk_core_get_scaled_duty_cycle(c, 100000));
 }
 
 static void clk_dump_subtree(struct seq_file *s, struct clk_core *c, int level)
@@ -2571,6 +2751,7 @@ static const struct {
 	ENTRY(CLK_SET_RATE_UNGATE),
 	ENTRY(CLK_IS_CRITICAL),
 	ENTRY(CLK_OPS_PARENT_ENABLE),
+	ENTRY(CLK_DUTY_CYCLE_PARENT),
 #undef ENTRY
 };
 
@@ -2609,6 +2790,17 @@ static int possible_parents_show(struct seq_file *s, void *data)
 }
 DEFINE_SHOW_ATTRIBUTE(possible_parents);
 
+static int clk_duty_cycle_show(struct seq_file *s, void *data)
+{
+	struct clk_core *core = s->private;
+	struct clk_duty *duty = &core->duty;
+
+	seq_printf(s, "%u/%u\n", duty->num, duty->den);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(clk_duty_cycle);
+
 static void clk_debug_create_one(struct clk_core *core, struct dentry *pdentry)
 {
 	struct dentry *root;
@@ -2627,6 +2819,8 @@ static void clk_debug_create_one(struct clk_core *core, struct dentry *pdentry)
 	debugfs_create_u32("clk_enable_count", 0444, root, &core->enable_count);
 	debugfs_create_u32("clk_protect_count", 0444, root, &core->protect_count);
 	debugfs_create_u32("clk_notifier_count", 0444, root, &core->notifier_count);
+	debugfs_create_file("clk_duty_cycle", 0444, root, core,
+			    &clk_duty_cycle_fops);
 
 	if (core->num_parents > 1)
 		debugfs_create_file("clk_possible_parents", 0444, root, core,
@@ -2845,6 +3039,11 @@ static int __clk_core_init(struct clk_core *core)
 		core->phase = 0;
 
 	/*
+	 * Set clk's duty cycle.
+	 */
+	clk_core_update_duty_cycle_nolock(core);
+
+	/*
 	 * Set clk's rate.  The preferred method is to use .recalc_rate.  For
 	 * simple clocks and lazy developers the default fallback is to use the
 	 * parent's rate.  If a clock doesn't have a parent (or is orphaned)
@@ -2933,6 +3132,7 @@ struct clk *__clk_create_clk(struct clk_hw *hw, const char *dev_id,
 	return clk;
 }
 
+/* keep in sync with __clk_put */
 void __clk_free_clk(struct clk *clk)
 {
 	clk_prepare_lock();
@@ -3312,6 +3512,7 @@ int __clk_get(struct clk *clk)
 	return 1;
 }
 
+/* keep in sync with __clk_free_clk */
 void __clk_put(struct clk *clk)
 {
 	struct module *owner;
@@ -3345,6 +3546,7 @@ void __clk_put(struct clk *clk)
 
 	module_put(owner);
 
+	kfree_const(clk->con_id);
 	kfree(clk);
 }
 
diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c
index 7513411140b6..9ab3db8b3988 100644
--- a/drivers/clk/clkdev.c
+++ b/drivers/clk/clkdev.c
@@ -35,9 +35,6 @@ static struct clk *__of_clk_get(struct device_node *np, int index,
 	struct clk *clk;
 	int rc;
 
-	if (index < 0)
-		return ERR_PTR(-EINVAL);
-
 	rc = of_parse_phandle_with_args(np, "clocks", "#clock-cells", index,
 					&clkspec);
 	if (rc)
@@ -199,7 +196,7 @@ struct clk *clk_get(struct device *dev, const char *con_id)
 	const char *dev_id = dev ? dev_name(dev) : NULL;
 	struct clk *clk;
 
-	if (dev) {
+	if (dev && dev->of_node) {
 		clk = __of_clk_get_by_name(dev->of_node, dev_id, con_id);
 		if (!IS_ERR(clk) || PTR_ERR(clk) == -EPROBE_DEFER)
 			return clk;
diff --git a/drivers/clk/imx/clk-imx51-imx53.c b/drivers/clk/imx/clk-imx51-imx53.c
index caa8bd40692c..fc8e782d817b 100644
--- a/drivers/clk/imx/clk-imx51-imx53.c
+++ b/drivers/clk/imx/clk-imx51-imx53.c
@@ -16,6 +16,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/sizes.h>
 #include <soc/imx/revision.h>
 #include <dt-bindings/clock/imx5-clock.h>
 
@@ -175,13 +176,13 @@ static void __init mx5_clocks_common_init(void __iomem *ccm_base)
 	clk[IMX5_CLK_PER_ROOT]		= imx_clk_mux("per_root", MXC_CCM_CBCMR, 0, 1,
 						per_root_sel, ARRAY_SIZE(per_root_sel));
 	clk[IMX5_CLK_AHB]		= imx_clk_divider("ahb", "main_bus", MXC_CCM_CBCDR, 10, 3);
-	clk[IMX5_CLK_AHB_MAX]		= imx_clk_gate2("ahb_max", "ahb", MXC_CCM_CCGR0, 28);
-	clk[IMX5_CLK_AIPS_TZ1]		= imx_clk_gate2("aips_tz1", "ahb", MXC_CCM_CCGR0, 24);
-	clk[IMX5_CLK_AIPS_TZ2]		= imx_clk_gate2("aips_tz2", "ahb", MXC_CCM_CCGR0, 26);
-	clk[IMX5_CLK_TMAX1]		= imx_clk_gate2("tmax1", "ahb", MXC_CCM_CCGR1, 0);
-	clk[IMX5_CLK_TMAX2]		= imx_clk_gate2("tmax2", "ahb", MXC_CCM_CCGR1, 2);
-	clk[IMX5_CLK_TMAX3]		= imx_clk_gate2("tmax3", "ahb", MXC_CCM_CCGR1, 4);
-	clk[IMX5_CLK_SPBA]		= imx_clk_gate2("spba", "ipg", MXC_CCM_CCGR5, 0);
+	clk[IMX5_CLK_AHB_MAX]		= imx_clk_gate2_flags("ahb_max", "ahb", MXC_CCM_CCGR0, 28, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_AIPS_TZ1]		= imx_clk_gate2_flags("aips_tz1", "ahb", MXC_CCM_CCGR0, 24, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_AIPS_TZ2]		= imx_clk_gate2_flags("aips_tz2", "ahb", MXC_CCM_CCGR0, 26, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_TMAX1]		= imx_clk_gate2_flags("tmax1", "ahb", MXC_CCM_CCGR1, 0, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_TMAX2]		= imx_clk_gate2_flags("tmax2", "ahb", MXC_CCM_CCGR1, 2, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_TMAX3]		= imx_clk_gate2_flags("tmax3", "ahb", MXC_CCM_CCGR1, 4, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_SPBA]		= imx_clk_gate2_flags("spba", "ipg", MXC_CCM_CCGR5, 0, CLK_IS_CRITICAL);
 	clk[IMX5_CLK_IPG]		= imx_clk_divider("ipg", "ahb", MXC_CCM_CBCDR, 8, 2);
 	clk[IMX5_CLK_AXI_A]		= imx_clk_divider("axi_a", "main_bus", MXC_CCM_CBCDR, 16, 3);
 	clk[IMX5_CLK_AXI_B]		= imx_clk_divider("axi_b", "main_bus", MXC_CCM_CBCDR, 19, 3);
@@ -252,8 +253,8 @@ static void __init mx5_clocks_common_init(void __iomem *ccm_base)
 	clk[IMX5_CLK_ECSPI2_PER_GATE]	= imx_clk_gate2("ecspi2_per_gate", "ecspi_podf", MXC_CCM_CCGR4, 24);
 	clk[IMX5_CLK_CSPI_IPG_GATE]	= imx_clk_gate2("cspi_ipg_gate", "ipg", MXC_CCM_CCGR4, 26);
 	clk[IMX5_CLK_SDMA_GATE]		= imx_clk_gate2("sdma_gate", "ipg", MXC_CCM_CCGR4, 30);
-	clk[IMX5_CLK_EMI_FAST_GATE]	= imx_clk_gate2("emi_fast_gate", "dummy", MXC_CCM_CCGR5, 14);
-	clk[IMX5_CLK_EMI_SLOW_GATE]	= imx_clk_gate2("emi_slow_gate", "emi_slow_podf", MXC_CCM_CCGR5, 16);
+	clk[IMX5_CLK_EMI_FAST_GATE]	= imx_clk_gate2_flags("emi_fast_gate", "dummy", MXC_CCM_CCGR5, 14, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_EMI_SLOW_GATE]	= imx_clk_gate2_flags("emi_slow_gate", "emi_slow_podf", MXC_CCM_CCGR5, 16, CLK_IS_CRITICAL);
 	clk[IMX5_CLK_IPU_SEL]		= imx_clk_mux("ipu_sel", MXC_CCM_CBCMR, 6, 2, ipu_sel, ARRAY_SIZE(ipu_sel));
 	clk[IMX5_CLK_IPU_GATE]		= imx_clk_gate2("ipu_gate", "ipu_sel", MXC_CCM_CCGR5, 10);
 	clk[IMX5_CLK_NFC_GATE]		= imx_clk_gate2("nfc_gate", "nfc_podf", MXC_CCM_CCGR5, 20);
@@ -267,7 +268,7 @@ static void __init mx5_clocks_common_init(void __iomem *ccm_base)
 	clk[IMX5_CLK_VPU_SEL]		= imx_clk_mux("vpu_sel", MXC_CCM_CBCMR, 14, 2, vpu_sel, ARRAY_SIZE(vpu_sel));
 	clk[IMX5_CLK_VPU_GATE]		= imx_clk_gate2("vpu_gate", "vpu_sel", MXC_CCM_CCGR5, 6);
 	clk[IMX5_CLK_VPU_REFERENCE_GATE] = imx_clk_gate2("vpu_reference_gate", "osc", MXC_CCM_CCGR5, 8);
-	clk[IMX5_CLK_GPC_DVFS]		= imx_clk_gate2("gpc_dvfs", "dummy", MXC_CCM_CCGR5, 24);
+	clk[IMX5_CLK_GPC_DVFS]		= imx_clk_gate2_flags("gpc_dvfs", "dummy", MXC_CCM_CCGR5, 24, CLK_IS_CRITICAL);
 
 	clk[IMX5_CLK_SSI_APM]		= imx_clk_mux("ssi_apm", MXC_CCM_CSCMR1, 8, 2, ssi_apm_sels, ARRAY_SIZE(ssi_apm_sels));
 	clk[IMX5_CLK_SSI1_ROOT_SEL]	= imx_clk_mux("ssi1_root_sel", MXC_CCM_CSCMR1, 14, 2, ssi_clk_sels, ARRAY_SIZE(ssi_clk_sels));
@@ -316,21 +317,6 @@ static void __init mx5_clocks_common_init(void __iomem *ccm_base)
 
 	/* move usb phy clk to 24MHz */
 	clk_set_parent(clk[IMX5_CLK_USB_PHY_SEL], clk[IMX5_CLK_OSC]);
-
-	clk_prepare_enable(clk[IMX5_CLK_GPC_DVFS]);
-	clk_prepare_enable(clk[IMX5_CLK_AHB_MAX]); /* esdhc3 */
-	clk_prepare_enable(clk[IMX5_CLK_AIPS_TZ1]);
-	clk_prepare_enable(clk[IMX5_CLK_AIPS_TZ2]); /* fec */
-	clk_prepare_enable(clk[IMX5_CLK_SPBA]);
-	clk_prepare_enable(clk[IMX5_CLK_EMI_FAST_GATE]); /* fec */
-	clk_prepare_enable(clk[IMX5_CLK_EMI_SLOW_GATE]); /* eim */
-	clk_prepare_enable(clk[IMX5_CLK_MIPI_HSC1_GATE]);
-	clk_prepare_enable(clk[IMX5_CLK_MIPI_HSC2_GATE]);
-	clk_prepare_enable(clk[IMX5_CLK_MIPI_ESC_GATE]);
-	clk_prepare_enable(clk[IMX5_CLK_MIPI_HSP_GATE]);
-	clk_prepare_enable(clk[IMX5_CLK_TMAX1]);
-	clk_prepare_enable(clk[IMX5_CLK_TMAX2]); /* esdhc2, fec */
-	clk_prepare_enable(clk[IMX5_CLK_TMAX3]); /* esdhc1, esdhc4 */
 }
 
 static void __init mx50_clocks_init(struct device_node *np)
@@ -442,10 +428,10 @@ static void __init mx51_clocks_init(struct device_node *np)
 	clk[IMX5_CLK_ESDHC4_PER_GATE]	= imx_clk_gate2("esdhc4_per_gate", "esdhc_d_sel", MXC_CCM_CCGR3, 14);
 	clk[IMX5_CLK_USB_PHY_GATE]	= imx_clk_gate2("usb_phy_gate", "usb_phy_sel", MXC_CCM_CCGR2, 0);
 	clk[IMX5_CLK_HSI2C_GATE]	= imx_clk_gate2("hsi2c_gate", "ipg", MXC_CCM_CCGR1, 22);
-	clk[IMX5_CLK_MIPI_HSC1_GATE]	= imx_clk_gate2("mipi_hsc1_gate", "ipg", MXC_CCM_CCGR4, 6);
-	clk[IMX5_CLK_MIPI_HSC2_GATE]	= imx_clk_gate2("mipi_hsc2_gate", "ipg", MXC_CCM_CCGR4, 8);
-	clk[IMX5_CLK_MIPI_ESC_GATE]	= imx_clk_gate2("mipi_esc_gate", "ipg", MXC_CCM_CCGR4, 10);
-	clk[IMX5_CLK_MIPI_HSP_GATE]	= imx_clk_gate2("mipi_hsp_gate", "ipg", MXC_CCM_CCGR4, 12);
+	clk[IMX5_CLK_MIPI_HSC1_GATE]	= imx_clk_gate2_flags("mipi_hsc1_gate", "ipg", MXC_CCM_CCGR4, 6, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_MIPI_HSC2_GATE]	= imx_clk_gate2_flags("mipi_hsc2_gate", "ipg", MXC_CCM_CCGR4, 8, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_MIPI_ESC_GATE]	= imx_clk_gate2_flags("mipi_esc_gate", "ipg", MXC_CCM_CCGR4, 10, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_MIPI_HSP_GATE]	= imx_clk_gate2_flags("mipi_hsp_gate", "ipg", MXC_CCM_CCGR4, 12, CLK_IS_CRITICAL);
 	clk[IMX5_CLK_SPDIF_XTAL_SEL]	= imx_clk_mux("spdif_xtal_sel", MXC_CCM_CSCMR1, 2, 2,
 						mx51_spdif_xtal_sel, ARRAY_SIZE(mx51_spdif_xtal_sel));
 	clk[IMX5_CLK_SPDIF1_SEL]	= imx_clk_mux("spdif1_sel", MXC_CCM_CSCMR2, 2, 2,
diff --git a/drivers/clk/imx/clk-imx6q.c b/drivers/clk/imx/clk-imx6q.c
index b9ea7037e193..8c7c2fcb8d94 100644
--- a/drivers/clk/imx/clk-imx6q.c
+++ b/drivers/clk/imx/clk-imx6q.c
@@ -65,7 +65,7 @@ static const char *ipg_per_sels[] = { "ipg", "osc", };
 static const char *ecspi_sels[] = { "pll3_60m", "osc", };
 static const char *can_sels[] = { "pll3_60m", "osc", "pll3_80m", };
 static const char *cko1_sels[]	= { "pll3_usb_otg", "pll2_bus", "pll1_sys", "pll5_video_div",
-				    "dummy", "axi", "enfc", "ipu1_di0", "ipu1_di1", "ipu2_di0",
+				    "video_27m", "axi", "enfc", "ipu1_di0", "ipu1_di1", "ipu2_di0",
 				    "ipu2_di1", "ahb", "ipg", "ipg_per", "ckil", "pll4_audio_div", };
 static const char *cko2_sels[] = {
 	"mmdc_ch0_axi", "mmdc_ch1_axi", "usdhc4", "usdhc1",
@@ -96,12 +96,6 @@ static const char *pll7_bypass_sels[] = { "pll7", "pll7_bypass_src", };
 static struct clk *clk[IMX6QDL_CLK_END];
 static struct clk_onecell_data clk_data;
 
-static unsigned int const clks_init_on[] __initconst = {
-	IMX6QDL_CLK_MMDC_CH0_AXI,
-	IMX6QDL_CLK_ROM,
-	IMX6QDL_CLK_ARM,
-};
-
 static struct clk_div_table clk_enet_ref_table[] = {
 	{ .val = 0, .div = 20, },
 	{ .val = 1, .div = 10, },
@@ -417,7 +411,6 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 {
 	struct device_node *np;
 	void __iomem *anatop_base, *base;
-	int i;
 	int ret;
 
 	clk[IMX6QDL_CLK_DUMMY] = imx_clk_fixed("dummy", 0);
@@ -794,7 +787,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 		clk[IMX6QDL_CLK_MLB] = imx_clk_gate2("mlb",            "mlb_podf",   base + 0x74, 18);
 	else
 		clk[IMX6QDL_CLK_MLB] = imx_clk_gate2("mlb",            "axi",               base + 0x74, 18);
-	clk[IMX6QDL_CLK_MMDC_CH0_AXI] = imx_clk_gate2("mmdc_ch0_axi",  "mmdc_ch0_axi_podf", base + 0x74, 20);
+	clk[IMX6QDL_CLK_MMDC_CH0_AXI] = imx_clk_gate2_flags("mmdc_ch0_axi",  "mmdc_ch0_axi_podf", base + 0x74, 20, CLK_IS_CRITICAL);
 	clk[IMX6QDL_CLK_MMDC_CH1_AXI] = imx_clk_gate2("mmdc_ch1_axi",  "mmdc_ch1_axi_podf", base + 0x74, 22);
 	clk[IMX6QDL_CLK_OCRAM]        = imx_clk_gate2("ocram",         "ahb",               base + 0x74, 28);
 	clk[IMX6QDL_CLK_OPENVG_AXI]   = imx_clk_gate2("openvg_axi",    "axi",               base + 0x74, 30);
@@ -808,7 +801,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk[IMX6QDL_CLK_GPMI_BCH]     = imx_clk_gate2("gpmi_bch",      "usdhc4",            base + 0x78, 26);
 	clk[IMX6QDL_CLK_GPMI_IO]      = imx_clk_gate2("gpmi_io",       "enfc",              base + 0x78, 28);
 	clk[IMX6QDL_CLK_GPMI_APB]     = imx_clk_gate2("gpmi_apb",      "usdhc3",            base + 0x78, 30);
-	clk[IMX6QDL_CLK_ROM]          = imx_clk_gate2("rom",           "ahb",               base + 0x7c, 0);
+	clk[IMX6QDL_CLK_ROM]          = imx_clk_gate2_flags("rom",     "ahb",               base + 0x7c, 0, CLK_IS_CRITICAL);
 	clk[IMX6QDL_CLK_SATA]         = imx_clk_gate2("sata",          "ahb",               base + 0x7c, 4);
 	clk[IMX6QDL_CLK_SDMA]         = imx_clk_gate2("sdma",          "ahb",               base + 0x7c, 6);
 	clk[IMX6QDL_CLK_SPBA]         = imx_clk_gate2("spba",          "ipg",               base + 0x7c, 12);
@@ -878,9 +871,6 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	 */
 	clk_set_parent(clk[IMX6QDL_CLK_ENFC_SEL], clk[IMX6QDL_CLK_PLL2_PFD2_396M]);
 
-	for (i = 0; i < ARRAY_SIZE(clks_init_on); i++)
-		clk_prepare_enable(clk[clks_init_on[i]]);
-
 	if (IS_ENABLED(CONFIG_USB_MXS_PHY)) {
 		clk_prepare_enable(clk[IMX6QDL_CLK_USBPHY1_GATE]);
 		clk_prepare_enable(clk[IMX6QDL_CLK_USBPHY2_GATE]);
diff --git a/drivers/clk/imx/clk-imx6sl.c b/drivers/clk/imx/clk-imx6sl.c
index 66b1dd1cfad0..eb6bcbf345a3 100644
--- a/drivers/clk/imx/clk-imx6sl.c
+++ b/drivers/clk/imx/clk-imx6sl.c
@@ -104,10 +104,6 @@ static struct clk_onecell_data clk_data;
 static void __iomem *ccm_base;
 static void __iomem *anatop_base;
 
-static const u32 clks_init_on[] __initconst = {
-	IMX6SL_CLK_IPG, IMX6SL_CLK_ARM, IMX6SL_CLK_MMDC_ROOT,
-};
-
 /*
  * ERR005311 CCM: After exit from WAIT mode, unwanted interrupt(s) taken
  *           during WAIT mode entry process could cause cache memory
@@ -195,7 +191,6 @@ static void __init imx6sl_clocks_init(struct device_node *ccm_node)
 {
 	struct device_node *np;
 	void __iomem *base;
-	int i;
 	int ret;
 
 	clks[IMX6SL_CLK_DUMMY] = imx_clk_fixed("dummy", 0);
@@ -426,13 +421,6 @@ static void __init imx6sl_clocks_init(struct device_node *ccm_node)
 		pr_warn("%s: failed to set AHB clock rate %d!\n",
 			__func__, ret);
 
-	/*
-	 * Make sure those always on clocks are enabled to maintain the correct
-	 * usecount and enabling/disabling of parent PLLs.
-	 */
-	for (i = 0; i < ARRAY_SIZE(clks_init_on); i++)
-		clk_prepare_enable(clks[clks_init_on[i]]);
-
 	if (IS_ENABLED(CONFIG_USB_MXS_PHY)) {
 		clk_prepare_enable(clks[IMX6SL_CLK_USBPHY1_GATE]);
 		clk_prepare_enable(clks[IMX6SL_CLK_USBPHY2_GATE]);
diff --git a/drivers/clk/imx/clk-imx6sll.c b/drivers/clk/imx/clk-imx6sll.c
index 3651c77fbabe..52379ee49aec 100644
--- a/drivers/clk/imx/clk-imx6sll.c
+++ b/drivers/clk/imx/clk-imx6sll.c
@@ -92,6 +92,7 @@ static void __init imx6sll_clocks_init(struct device_node *ccm_node)
 
 	np = of_find_compatible_node(NULL, NULL, "fsl,imx6sll-anatop");
 	base = of_iomap(np, 0);
+	of_node_put(np);
 	WARN_ON(!base);
 
 	/* Do not bypass PLLs initially */
@@ -253,6 +254,7 @@ static void __init imx6sll_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SLL_CLK_DCP]		= imx_clk_gate2("dcp", "ahb", base + 0x68, 10);
 	clks[IMX6SLL_CLK_UART2_IPG]	= imx_clk_gate2("uart2_ipg", "ipg", base + 0x68, 28);
 	clks[IMX6SLL_CLK_UART2_SERIAL]	= imx_clk_gate2("uart2_serial",	"uart_podf", base + 0x68, 28);
+	clks[IMX6SLL_CLK_GPIO2]		= imx_clk_gate2("gpio2", "ipg", base + 0x68, 30);
 
 	/* CCGR1 */
 	clks[IMX6SLL_CLK_ECSPI1]	= imx_clk_gate2("ecspi1",	"ecspi_podf", base + 0x6c, 0);
@@ -267,13 +269,17 @@ static void __init imx6sll_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SLL_CLK_GPT_SERIAL]	= imx_clk_gate2("gpt1_serial",	"perclk", base + 0x6c, 22);
 	clks[IMX6SLL_CLK_UART4_IPG]	= imx_clk_gate2("uart4_ipg",	"ipg", base + 0x6c, 24);
 	clks[IMX6SLL_CLK_UART4_SERIAL]	= imx_clk_gate2("uart4_serail",	"uart_podf", base + 0x6c, 24);
+	clks[IMX6SLL_CLK_GPIO1]		= imx_clk_gate2("gpio1",	"ipg", base + 0x6c, 26);
+	clks[IMX6SLL_CLK_GPIO5]		= imx_clk_gate2("gpio5",	"ipg", base + 0x6c, 30);
 
 	/* CCGR2 */
+	clks[IMX6SLL_CLK_GPIO6]		= imx_clk_gate2("gpio6",	"ipg",    base + 0x70, 0);
 	clks[IMX6SLL_CLK_CSI]		= imx_clk_gate2("csi",		"axi",    base + 0x70,	2);
 	clks[IMX6SLL_CLK_I2C1]		= imx_clk_gate2("i2c1",		"perclk", base + 0x70,	6);
 	clks[IMX6SLL_CLK_I2C2]		= imx_clk_gate2("i2c2",		"perclk", base + 0x70,	8);
 	clks[IMX6SLL_CLK_I2C3]		= imx_clk_gate2("i2c3",		"perclk", base + 0x70,	10);
 	clks[IMX6SLL_CLK_OCOTP]		= imx_clk_gate2("ocotp",	"ipg",    base + 0x70,	12);
+	clks[IMX6SLL_CLK_GPIO3]		= imx_clk_gate2("gpio3",	"ipg",    base + 0x70,	26);
 	clks[IMX6SLL_CLK_LCDIF_APB]	= imx_clk_gate2("lcdif_apb",	"axi",    base + 0x70,	28);
 	clks[IMX6SLL_CLK_PXP]		= imx_clk_gate2("pxp",		"axi",    base + 0x70,	30);
 
@@ -283,6 +289,7 @@ static void __init imx6sll_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SLL_CLK_EPDC_AXI]	= imx_clk_gate2("epdc_aclk",	"axi",		base + 0x74, 4);
 	clks[IMX6SLL_CLK_EPDC_PIX]	= imx_clk_gate2("epdc_pix",	"epdc_podf",	base + 0x74, 4);
 	clks[IMX6SLL_CLK_LCDIF_PIX]	= imx_clk_gate2("lcdif_pix",	"lcdif_podf",	base + 0x74, 10);
+	clks[IMX6SLL_CLK_GPIO4]		= imx_clk_gate2("gpio4",	"ipg",		base + 0x74, 12);
 	clks[IMX6SLL_CLK_WDOG1]		= imx_clk_gate2("wdog1",	"ipg",		base + 0x74, 16);
 	clks[IMX6SLL_CLK_MMDC_P0_FAST]	= imx_clk_gate_flags("mmdc_p0_fast", "mmdc_podf",  base + 0x74,	20, CLK_IS_CRITICAL);
 	clks[IMX6SLL_CLK_MMDC_P0_IPG]	= imx_clk_gate2_flags("mmdc_p0_ipg", "ipg",	   base + 0x74,	24, CLK_IS_CRITICAL);
diff --git a/drivers/clk/imx/clk-imx6sx.c b/drivers/clk/imx/clk-imx6sx.c
index 10c771b91ef6..d9f2890ffe62 100644
--- a/drivers/clk/imx/clk-imx6sx.c
+++ b/drivers/clk/imx/clk-imx6sx.c
@@ -92,14 +92,6 @@ static const char *pll7_bypass_sels[] = { "pll7", "pll7_bypass_src", };
 static struct clk *clks[IMX6SX_CLK_CLK_END];
 static struct clk_onecell_data clk_data;
 
-static int const clks_init_on[] __initconst = {
-	IMX6SX_CLK_AIPS_TZ1, IMX6SX_CLK_AIPS_TZ2, IMX6SX_CLK_AIPS_TZ3,
-	IMX6SX_CLK_IPMUX1, IMX6SX_CLK_IPMUX2, IMX6SX_CLK_IPMUX3,
-	IMX6SX_CLK_WAKEUP, IMX6SX_CLK_MMDC_P0_FAST, IMX6SX_CLK_MMDC_P0_IPG,
-	IMX6SX_CLK_ROM, IMX6SX_CLK_ARM, IMX6SX_CLK_IPG, IMX6SX_CLK_OCRAM,
-	IMX6SX_CLK_PER2_MAIN, IMX6SX_CLK_PERCLK, IMX6SX_CLK_TZASC1,
-};
-
 static const struct clk_div_table clk_enet_ref_table[] = {
 	{ .val = 0, .div = 20, },
 	{ .val = 1, .div = 10, },
@@ -142,7 +134,6 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 {
 	struct device_node *np;
 	void __iomem *base;
-	int i;
 
 	clks[IMX6SX_CLK_DUMMY] = imx_clk_fixed("dummy", 0);
 
@@ -332,7 +323,7 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SX_CLK_QSPI1_PODF]         = imx_clk_divider("qspi1_podf",     "qspi1_sel",         base + 0x1c, 26,   3);
 	clks[IMX6SX_CLK_EIM_SLOW_PODF]      = imx_clk_divider("eim_slow_podf",  "eim_slow_sel",      base + 0x1c, 23,   3);
 	clks[IMX6SX_CLK_LCDIF2_PODF]        = imx_clk_divider("lcdif2_podf",    "lcdif2_pred",       base + 0x1c, 20,   3);
-	clks[IMX6SX_CLK_PERCLK]             = imx_clk_divider("perclk",         "perclk_sel",        base + 0x1c, 0,    6);
+	clks[IMX6SX_CLK_PERCLK]             = imx_clk_divider_flags("perclk", "perclk_sel", base + 0x1c, 0, 6, CLK_IS_CRITICAL);
 	clks[IMX6SX_CLK_VID_PODF]           = imx_clk_divider("vid_podf",       "vid_sel",           base + 0x20, 24,   2);
 	clks[IMX6SX_CLK_CAN_PODF]           = imx_clk_divider("can_podf",       "can_sel",           base + 0x20, 2,    6);
 	clks[IMX6SX_CLK_USDHC4_PODF]        = imx_clk_divider("usdhc4_podf",    "usdhc4_sel",        base + 0x24, 22,   3);
@@ -380,8 +371,8 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 
 	/*                                            name             parent_name          reg         shift */
 	/* CCGR0 */
-	clks[IMX6SX_CLK_AIPS_TZ1]     = imx_clk_gate2("aips_tz1",      "ahb",               base + 0x68, 0);
-	clks[IMX6SX_CLK_AIPS_TZ2]     = imx_clk_gate2("aips_tz2",      "ahb",               base + 0x68, 2);
+	clks[IMX6SX_CLK_AIPS_TZ1]     = imx_clk_gate2_flags("aips_tz1", "ahb", base + 0x68, 0, CLK_IS_CRITICAL);
+	clks[IMX6SX_CLK_AIPS_TZ2]     = imx_clk_gate2_flags("aips_tz2", "ahb", base + 0x68, 2, CLK_IS_CRITICAL);
 	clks[IMX6SX_CLK_APBH_DMA]     = imx_clk_gate2("apbh_dma",      "usdhc3",            base + 0x68, 4);
 	clks[IMX6SX_CLK_ASRC_MEM]     = imx_clk_gate2_shared("asrc_mem", "ahb",             base + 0x68, 6, &share_count_asrc);
 	clks[IMX6SX_CLK_ASRC_IPG]     = imx_clk_gate2_shared("asrc_ipg", "ahb",             base + 0x68, 6, &share_count_asrc);
@@ -394,7 +385,7 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SX_CLK_CAN2_SERIAL]  = imx_clk_gate2("can2_serial",   "can_podf",          base + 0x68, 20);
 	clks[IMX6SX_CLK_DCIC1]        = imx_clk_gate2("dcic1",         "display_podf",      base + 0x68, 24);
 	clks[IMX6SX_CLK_DCIC2]        = imx_clk_gate2("dcic2",         "display_podf",      base + 0x68, 26);
-	clks[IMX6SX_CLK_AIPS_TZ3]     = imx_clk_gate2("aips_tz3",      "ahb",               base + 0x68, 30);
+	clks[IMX6SX_CLK_AIPS_TZ3]     = imx_clk_gate2_flags("aips_tz3", "ahb", base + 0x68, 30, CLK_IS_CRITICAL);
 
 	/* CCGR1 */
 	clks[IMX6SX_CLK_ECSPI1]       = imx_clk_gate2("ecspi1",        "ecspi_podf",        base + 0x6c, 0);
@@ -407,10 +398,11 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SX_CLK_ESAI_EXTAL]   = imx_clk_gate2_shared("esai_extal", "esai_podf",     base + 0x6c, 16, &share_count_esai);
 	clks[IMX6SX_CLK_ESAI_IPG]     = imx_clk_gate2_shared("esai_ipg",   "ahb",           base + 0x6c, 16, &share_count_esai);
 	clks[IMX6SX_CLK_ESAI_MEM]     = imx_clk_gate2_shared("esai_mem",   "ahb",           base + 0x6c, 16, &share_count_esai);
-	clks[IMX6SX_CLK_WAKEUP]       = imx_clk_gate2("wakeup",        "ipg",               base + 0x6c, 18);
+	clks[IMX6SX_CLK_WAKEUP]       = imx_clk_gate2_flags("wakeup", "ipg", base + 0x6c, 18, CLK_IS_CRITICAL);
 	clks[IMX6SX_CLK_GPT_BUS]      = imx_clk_gate2("gpt_bus",       "perclk",            base + 0x6c, 20);
 	clks[IMX6SX_CLK_GPT_SERIAL]   = imx_clk_gate2("gpt_serial",    "perclk",            base + 0x6c, 22);
 	clks[IMX6SX_CLK_GPU]          = imx_clk_gate2("gpu",           "gpu_core_podf",     base + 0x6c, 26);
+	clks[IMX6SX_CLK_OCRAM_S]      = imx_clk_gate2("ocram_s",       "ahb",               base + 0x6c, 28);
 	clks[IMX6SX_CLK_CANFD]        = imx_clk_gate2("canfd",         "can_podf",          base + 0x6c, 30);
 
 	/* CCGR2 */
@@ -420,10 +412,10 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SX_CLK_I2C3]         = imx_clk_gate2("i2c3",          "perclk",            base + 0x70, 10);
 	clks[IMX6SX_CLK_OCOTP]        = imx_clk_gate2("ocotp",         "ipg",               base + 0x70, 12);
 	clks[IMX6SX_CLK_IOMUXC]       = imx_clk_gate2("iomuxc",        "lcdif1_podf",       base + 0x70, 14);
-	clks[IMX6SX_CLK_IPMUX1]       = imx_clk_gate2("ipmux1",        "ahb",               base + 0x70, 16);
-	clks[IMX6SX_CLK_IPMUX2]       = imx_clk_gate2("ipmux2",        "ahb",               base + 0x70, 18);
-	clks[IMX6SX_CLK_IPMUX3]       = imx_clk_gate2("ipmux3",        "ahb",               base + 0x70, 20);
-	clks[IMX6SX_CLK_TZASC1]       = imx_clk_gate2("tzasc1",        "mmdc_podf",         base + 0x70, 22);
+	clks[IMX6SX_CLK_IPMUX1]       = imx_clk_gate2_flags("ipmux1", "ahb", base + 0x70, 16, CLK_IS_CRITICAL);
+	clks[IMX6SX_CLK_IPMUX2]       = imx_clk_gate2_flags("ipmux2", "ahb", base + 0x70, 18, CLK_IS_CRITICAL);
+	clks[IMX6SX_CLK_IPMUX3]       = imx_clk_gate2_flags("ipmux3", "ahb", base + 0x70, 20, CLK_IS_CRITICAL);
+	clks[IMX6SX_CLK_TZASC1]       = imx_clk_gate2_flags("tzasc1", "mmdc_podf", base + 0x70, 22, CLK_IS_CRITICAL);
 	clks[IMX6SX_CLK_LCDIF_APB]    = imx_clk_gate2("lcdif_apb",     "display_podf",      base + 0x70, 28);
 	clks[IMX6SX_CLK_PXP_AXI]      = imx_clk_gate2("pxp_axi",       "display_podf",      base + 0x70, 30);
 
@@ -437,15 +429,15 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SX_CLK_LDB_DI0]      = imx_clk_gate2("ldb_di0",       "ldb_di0_div_sel",   base + 0x74, 12);
 	clks[IMX6SX_CLK_QSPI1]        = imx_clk_gate2("qspi1",         "qspi1_podf",        base + 0x74, 14);
 	clks[IMX6SX_CLK_MLB]          = imx_clk_gate2("mlb",           "ahb",               base + 0x74, 18);
-	clks[IMX6SX_CLK_MMDC_P0_FAST] = imx_clk_gate2("mmdc_p0_fast",  "mmdc_podf",         base + 0x74, 20);
-	clks[IMX6SX_CLK_MMDC_P0_IPG]  = imx_clk_gate2("mmdc_p0_ipg",   "ipg",               base + 0x74, 24);
-	clks[IMX6SX_CLK_OCRAM]        = imx_clk_gate2("ocram",         "ocram_podf",        base + 0x74, 28);
+	clks[IMX6SX_CLK_MMDC_P0_FAST] = imx_clk_gate2_flags("mmdc_p0_fast", "mmdc_podf", base + 0x74, 20, CLK_IS_CRITICAL);
+	clks[IMX6SX_CLK_MMDC_P0_IPG]  = imx_clk_gate2_flags("mmdc_p0_ipg", "ipg", base + 0x74, 24, CLK_IS_CRITICAL);
+	clks[IMX6SX_CLK_OCRAM]        = imx_clk_gate2_flags("ocram", "ocram_podf", base + 0x74, 28, CLK_IS_CRITICAL);
 
 	/* CCGR4 */
 	clks[IMX6SX_CLK_PCIE_AXI]     = imx_clk_gate2("pcie_axi",      "display_podf",      base + 0x78, 0);
 	clks[IMX6SX_CLK_QSPI2]        = imx_clk_gate2("qspi2",         "qspi2_podf",        base + 0x78, 10);
 	clks[IMX6SX_CLK_PER1_BCH]     = imx_clk_gate2("per1_bch",      "usdhc3",            base + 0x78, 12);
-	clks[IMX6SX_CLK_PER2_MAIN]    = imx_clk_gate2("per2_main",     "ahb",               base + 0x78, 14);
+	clks[IMX6SX_CLK_PER2_MAIN]    = imx_clk_gate2_flags("per2_main", "ahb", base + 0x78, 14, CLK_IS_CRITICAL);
 	clks[IMX6SX_CLK_PWM1]         = imx_clk_gate2("pwm1",          "perclk",            base + 0x78, 16);
 	clks[IMX6SX_CLK_PWM2]         = imx_clk_gate2("pwm2",          "perclk",            base + 0x78, 18);
 	clks[IMX6SX_CLK_PWM3]         = imx_clk_gate2("pwm3",          "perclk",            base + 0x78, 20);
@@ -456,7 +448,7 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SX_CLK_GPMI_APB]     = imx_clk_gate2("gpmi_apb",      "usdhc3",            base + 0x78, 30);
 
 	/* CCGR5 */
-	clks[IMX6SX_CLK_ROM]          = imx_clk_gate2("rom",           "ahb",               base + 0x7c, 0);
+	clks[IMX6SX_CLK_ROM]          = imx_clk_gate2_flags("rom", "ahb", base + 0x7c, 0, CLK_IS_CRITICAL);
 	clks[IMX6SX_CLK_SDMA]         = imx_clk_gate2("sdma",          "ahb",               base + 0x7c, 6);
 	clks[IMX6SX_CLK_SPBA]         = imx_clk_gate2("spba",          "ipg",               base + 0x7c, 12);
 	clks[IMX6SX_CLK_AUDIO]        = imx_clk_gate2_shared("audio",  "audio_podf",        base + 0x7c, 14, &share_count_audio);
@@ -502,9 +494,6 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	clk_data.clk_num = ARRAY_SIZE(clks);
 	of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data);
 
-	for (i = 0; i < ARRAY_SIZE(clks_init_on); i++)
-		clk_prepare_enable(clks[clks_init_on[i]]);
-
 	if (IS_ENABLED(CONFIG_USB_MXS_PHY)) {
 		clk_prepare_enable(clks[IMX6SX_CLK_USBPHY1_GATE]);
 		clk_prepare_enable(clks[IMX6SX_CLK_USBPHY2_GATE]);
diff --git a/drivers/clk/imx/clk-imx6ul.c b/drivers/clk/imx/clk-imx6ul.c
index ba563ba50b40..361b43f9742e 100644
--- a/drivers/clk/imx/clk-imx6ul.c
+++ b/drivers/clk/imx/clk-imx6ul.c
@@ -79,12 +79,6 @@ static const char *cko_sels[] = { "cko1", "cko2", };
 static struct clk *clks[IMX6UL_CLK_END];
 static struct clk_onecell_data clk_data;
 
-static int const clks_init_on[] __initconst = {
-	IMX6UL_CLK_AIPSTZ1, IMX6UL_CLK_AIPSTZ2,
-	IMX6UL_CLK_AXI, IMX6UL_CLK_ARM, IMX6UL_CLK_ROM,
-	IMX6UL_CLK_MMDC_P0_FAST, IMX6UL_CLK_MMDC_P0_IPG,
-};
-
 static const struct clk_div_table clk_enet_ref_table[] = {
 	{ .val = 0, .div = 20, },
 	{ .val = 1, .div = 10, },
@@ -129,7 +123,6 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 {
 	struct device_node *np;
 	void __iomem *base;
-	int i;
 
 	clks[IMX6UL_CLK_DUMMY] = imx_clk_fixed("dummy", 0);
 
@@ -142,6 +135,7 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 
 	np = of_find_compatible_node(NULL, NULL, "fsl,imx6ul-anatop");
 	base = of_iomap(np, 0);
+	of_node_put(np);
 	WARN_ON(!base);
 
 	clks[IMX6UL_PLL1_BYPASS_SRC] = imx_clk_mux("pll1_bypass_src", base + 0x00, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
@@ -336,8 +330,8 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 	clks[IMX6UL_CLK_AHB]		= imx_clk_busy_divider("ahb",	    "periph",	base +  0x14, 10, 3,  base + 0x48, 1);
 
 	/* CCGR0 */
-	clks[IMX6UL_CLK_AIPSTZ1]	= imx_clk_gate2("aips_tz1",	"ahb",		base + 0x68,	0);
-	clks[IMX6UL_CLK_AIPSTZ2]	= imx_clk_gate2("aips_tz2",	"ahb",		base + 0x68,	2);
+	clks[IMX6UL_CLK_AIPSTZ1]	= imx_clk_gate2_flags("aips_tz1", "ahb", base + 0x68, 0, CLK_IS_CRITICAL);
+	clks[IMX6UL_CLK_AIPSTZ2]	= imx_clk_gate2_flags("aips_tz2", "ahb", base + 0x68, 2, CLK_IS_CRITICAL);
 	clks[IMX6UL_CLK_APBHDMA]	= imx_clk_gate2("apbh_dma",	"bch_podf",	base + 0x68,	4);
 	clks[IMX6UL_CLK_ASRC_IPG]	= imx_clk_gate2_shared("asrc_ipg",	"ahb",	base + 0x68,	6, &share_count_asrc);
 	clks[IMX6UL_CLK_ASRC_MEM]	= imx_clk_gate2_shared("asrc_mem",	"ahb",	base + 0x68,	6, &share_count_asrc);
@@ -360,6 +354,7 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 	clks[IMX6UL_CLK_UART2_SERIAL]	= imx_clk_gate2("uart2_serial",	"uart_podf",	base + 0x68,	28);
 	if (clk_on_imx6ull())
 		clks[IMX6UL_CLK_AIPSTZ3]	= imx_clk_gate2("aips_tz3",	"ahb",		 base + 0x80,	18);
+	clks[IMX6UL_CLK_GPIO2]		= imx_clk_gate2("gpio2",	"ipg",		base + 0x68,	30);
 
 	/* CCGR1 */
 	clks[IMX6UL_CLK_ECSPI1]		= imx_clk_gate2("ecspi1",	"ecspi_podf",	base + 0x6c,	0);
@@ -376,6 +371,8 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 	clks[IMX6UL_CLK_GPT1_SERIAL]	= imx_clk_gate2("gpt1_serial",	"perclk",	base + 0x6c,	22);
 	clks[IMX6UL_CLK_UART4_IPG]	= imx_clk_gate2("uart4_ipg",	"ipg",		base + 0x6c,	24);
 	clks[IMX6UL_CLK_UART4_SERIAL]	= imx_clk_gate2("uart4_serial",	"uart_podf",	base + 0x6c,	24);
+	clks[IMX6UL_CLK_GPIO1]		= imx_clk_gate2("gpio1",	"ipg",		base + 0x6c,	26);
+	clks[IMX6UL_CLK_GPIO5]		= imx_clk_gate2("gpio5",	"ipg",		base + 0x6c,	30);
 
 	/* CCGR2 */
 	if (clk_on_imx6ull()) {
@@ -389,6 +386,7 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 	clks[IMX6UL_CLK_I2C3]		= imx_clk_gate2("i2c3",		"perclk",	base + 0x70,	10);
 	clks[IMX6UL_CLK_OCOTP]		= imx_clk_gate2("ocotp",	"ipg",		base + 0x70,	12);
 	clks[IMX6UL_CLK_IOMUXC]		= imx_clk_gate2("iomuxc",	"lcdif_podf",	base + 0x70,	14);
+	clks[IMX6UL_CLK_GPIO3]		= imx_clk_gate2("gpio3",	"ipg",		base + 0x70,	26);
 	clks[IMX6UL_CLK_LCDIF_APB]	= imx_clk_gate2("lcdif_apb",	"axi",		base + 0x70,	28);
 	clks[IMX6UL_CLK_PXP]		= imx_clk_gate2("pxp",		"axi",		base + 0x70,	30);
 
@@ -405,11 +403,12 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 	clks[IMX6UL_CLK_UART6_IPG]	= imx_clk_gate2("uart6_ipg",	"ipg",		base + 0x74,	6);
 	clks[IMX6UL_CLK_UART6_SERIAL]	= imx_clk_gate2("uart6_serial",	"uart_podf",	base + 0x74,	6);
 	clks[IMX6UL_CLK_LCDIF_PIX]	= imx_clk_gate2("lcdif_pix",	"lcdif_podf",	base + 0x74,	10);
+	clks[IMX6UL_CLK_GPIO4]		= imx_clk_gate2("gpio4",	"ipg",		base + 0x74,	12);
 	clks[IMX6UL_CLK_QSPI]		= imx_clk_gate2("qspi1",	"qspi1_podf",	base + 0x74,	14);
 	clks[IMX6UL_CLK_WDOG1]		= imx_clk_gate2("wdog1",	"ipg",		base + 0x74,	16);
-	clks[IMX6UL_CLK_MMDC_P0_FAST]	= imx_clk_gate("mmdc_p0_fast", "mmdc_podf", base + 0x74,	20);
-	clks[IMX6UL_CLK_MMDC_P0_IPG]	= imx_clk_gate2("mmdc_p0_ipg",	"ipg",		base + 0x74,	24);
-	clks[IMX6UL_CLK_AXI]		= imx_clk_gate("axi",	"axi_podf",	base + 0x74,	28);
+	clks[IMX6UL_CLK_MMDC_P0_FAST]	= imx_clk_gate_flags("mmdc_p0_fast", "mmdc_podf", base + 0x74,	20, CLK_IS_CRITICAL);
+	clks[IMX6UL_CLK_MMDC_P0_IPG]	= imx_clk_gate2_flags("mmdc_p0_ipg",	"ipg",		base + 0x74,	24, CLK_IS_CRITICAL);
+	clks[IMX6UL_CLK_AXI]		= imx_clk_gate_flags("axi",	"axi_podf",	base + 0x74,	28, CLK_IS_CRITICAL);
 
 	/* CCGR4 */
 	clks[IMX6UL_CLK_PER_BCH]	= imx_clk_gate2("per_bch",	"bch_podf",	base + 0x78,	12);
@@ -423,7 +422,7 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 	clks[IMX6UL_CLK_GPMI_APB]	= imx_clk_gate2("gpmi_apb",	"bch_podf",	base + 0x78,	30);
 
 	/* CCGR5 */
-	clks[IMX6UL_CLK_ROM]		= imx_clk_gate2("rom",		"ahb",		base + 0x7c,	0);
+	clks[IMX6UL_CLK_ROM]		= imx_clk_gate2_flags("rom",	"ahb",		base + 0x7c,	0,	CLK_IS_CRITICAL);
 	clks[IMX6UL_CLK_SDMA]		= imx_clk_gate2("sdma",		"ahb",		base + 0x7c,	6);
 	clks[IMX6UL_CLK_KPP]		= imx_clk_gate2("kpp",		"ipg",		base + 0x7c,	8);
 	clks[IMX6UL_CLK_WDOG2]		= imx_clk_gate2("wdog2",	"ipg",		base + 0x7c,	10);
@@ -497,10 +496,6 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 	clk_set_rate(clks[IMX6UL_CLK_ENET2_REF], 50000000);
 	clk_set_rate(clks[IMX6UL_CLK_CSI], 24000000);
 
-	/* keep all the clks on just for bringup */
-	for (i = 0; i < ARRAY_SIZE(clks_init_on); i++)
-		clk_prepare_enable(clks[clks_init_on[i]]);
-
 	if (clk_on_imx6ull())
 		clk_prepare_enable(clks[IMX6UL_CLK_AIPSTZ3]);
 
diff --git a/drivers/clk/imx/clk-imx7d.c b/drivers/clk/imx/clk-imx7d.c
index 27217a7ea17e..881b772c4ac9 100644
--- a/drivers/clk/imx/clk-imx7d.c
+++ b/drivers/clk/imx/clk-imx7d.c
@@ -797,6 +797,7 @@ static void __init imx7d_clocks_init(struct device_node *ccm_node)
 	clks[IMX7D_DRAM_ALT_ROOT_CLK] = imx_clk_gate4("dram_alt_root_clk", "dram_alt_post_div", base + 0x4130, 0);
 	clks[IMX7D_OCOTP_CLK] = imx_clk_gate4("ocotp_clk", "ipg_root_clk", base + 0x4230, 0);
 	clks[IMX7D_SNVS_CLK] = imx_clk_gate4("snvs_clk", "ipg_root_clk", base + 0x4250, 0);
+	clks[IMX7D_MU_ROOT_CLK] = imx_clk_gate4("mu_root_clk", "ipg_root_clk", base + 0x4270, 0);
 	clks[IMX7D_CAAM_CLK] = imx_clk_gate4("caam_clk", "ipg_root_clk", base + 0x4240, 0);
 	clks[IMX7D_USB_HSIC_ROOT_CLK] = imx_clk_gate4("usb_hsic_root_clk", "usb_hsic_post_div", base + 0x4690, 0);
 	clks[IMX7D_SDMA_CORE_CLK] = imx_clk_gate4("sdma_root_clk", "ahb_root_clk", base + 0x4480, 0);
diff --git a/drivers/clk/ingenic/jz4740-cgu.c b/drivers/clk/ingenic/jz4740-cgu.c
index 32fcc75f6f77..4479c102e899 100644
--- a/drivers/clk/ingenic/jz4740-cgu.c
+++ b/drivers/clk/ingenic/jz4740-cgu.c
@@ -134,7 +134,7 @@ static const struct ingenic_cgu_clk_info jz4740_cgu_clocks[] = {
 		"i2s", CGU_CLK_MUX | CGU_CLK_DIV | CGU_CLK_GATE,
 		.parents = { JZ4740_CLK_EXT, JZ4740_CLK_PLL_HALF, -1, -1 },
 		.mux = { CGU_REG_CPCCR, 31, 1 },
-		.div = { CGU_REG_I2SCDR, 0, 1, 8, -1, -1, -1 },
+		.div = { CGU_REG_I2SCDR, 0, 1, 9, -1, -1, -1 },
 		.gate = { CGU_REG_CLKGR, 6 },
 	},
 
@@ -161,7 +161,7 @@ static const struct ingenic_cgu_clk_info jz4740_cgu_clocks[] = {
 	},
 
 	[JZ4740_CLK_UDC] = {
-		"udc", CGU_CLK_MUX | CGU_CLK_DIV,
+		"udc", CGU_CLK_MUX | CGU_CLK_DIV | CGU_CLK_GATE,
 		.parents = { JZ4740_CLK_EXT, JZ4740_CLK_PLL_HALF, -1, -1 },
 		.mux = { CGU_REG_CPCCR, 29, 1 },
 		.div = { CGU_REG_CPCCR, 23, 1, 6, -1, -1, -1 },
diff --git a/drivers/clk/meson/Kconfig b/drivers/clk/meson/Kconfig
index 815659eebea3..efaa70f682b4 100644
--- a/drivers/clk/meson/Kconfig
+++ b/drivers/clk/meson/Kconfig
@@ -1,13 +1,19 @@
 config COMMON_CLK_AMLOGIC
 	bool
-	depends on OF
 	depends on ARCH_MESON || COMPILE_TEST
+	select COMMON_CLK_REGMAP_MESON
+
+config COMMON_CLK_AMLOGIC_AUDIO
+	bool
+	depends on ARCH_MESON || COMPILE_TEST
+	select COMMON_CLK_AMLOGIC
 
 config COMMON_CLK_MESON_AO
 	bool
 	depends on OF
 	depends on ARCH_MESON || COMPILE_TEST
 	select COMMON_CLK_REGMAP_MESON
+	select RESET_CONTROLLER
 
 config COMMON_CLK_REGMAP_MESON
 	bool
@@ -15,9 +21,8 @@ config COMMON_CLK_REGMAP_MESON
 
 config COMMON_CLK_MESON8B
 	bool
-	depends on COMMON_CLK_AMLOGIC
+	select COMMON_CLK_AMLOGIC
 	select RESET_CONTROLLER
-	select COMMON_CLK_REGMAP_MESON
 	help
 	  Support for the clock controller on AmLogic S802 (Meson8),
 	  S805 (Meson8b) and S812 (Meson8m2) devices. Say Y if you
@@ -25,10 +30,8 @@ config COMMON_CLK_MESON8B
 
 config COMMON_CLK_GXBB
 	bool
-	depends on COMMON_CLK_AMLOGIC
-	select RESET_CONTROLLER
+	select COMMON_CLK_AMLOGIC
 	select COMMON_CLK_MESON_AO
-	select COMMON_CLK_REGMAP_MESON
 	select MFD_SYSCON
 	help
 	  Support for the clock controller on AmLogic S905 devices, aka gxbb.
@@ -36,11 +39,18 @@ config COMMON_CLK_GXBB
 
 config COMMON_CLK_AXG
 	bool
-	depends on COMMON_CLK_AMLOGIC
-	select RESET_CONTROLLER
+	select COMMON_CLK_AMLOGIC
 	select COMMON_CLK_MESON_AO
-	select COMMON_CLK_REGMAP_MESON
 	select MFD_SYSCON
 	help
 	  Support for the clock controller on AmLogic A113D devices, aka axg.
 	  Say Y if you want peripherals and CPU frequency scaling to work.
+
+config COMMON_CLK_AXG_AUDIO
+	tristate "Meson AXG Audio Clock Controller Driver"
+	depends on COMMON_CLK_AXG
+	select COMMON_CLK_AMLOGIC_AUDIO
+	select MFD_SYSCON
+	help
+	  Support for the audio clock controller on AmLogic A113D devices,
+	  aka axg, Say Y if you want audio subsystem to work.
diff --git a/drivers/clk/meson/Makefile b/drivers/clk/meson/Makefile
index d0d13aeb369a..72ec8c40d848 100644
--- a/drivers/clk/meson/Makefile
+++ b/drivers/clk/meson/Makefile
@@ -2,9 +2,11 @@
 # Makefile for Meson specific clk
 #
 
-obj-$(CONFIG_COMMON_CLK_AMLOGIC) += clk-pll.o clk-mpll.o clk-audio-divider.o
+obj-$(CONFIG_COMMON_CLK_AMLOGIC) += clk-pll.o clk-mpll.o clk-phase.o
+obj-$(CONFIG_COMMON_CLK_AMLOGIC_AUDIO)	+= clk-triphase.o sclk-div.o
 obj-$(CONFIG_COMMON_CLK_MESON_AO) += meson-aoclk.o
 obj-$(CONFIG_COMMON_CLK_MESON8B) += meson8b.o
 obj-$(CONFIG_COMMON_CLK_GXBB)	 += gxbb.o gxbb-aoclk.o gxbb-aoclk-32k.o
 obj-$(CONFIG_COMMON_CLK_AXG)	 += axg.o axg-aoclk.o
+obj-$(CONFIG_COMMON_CLK_AXG_AUDIO)	+= axg-audio.o
 obj-$(CONFIG_COMMON_CLK_REGMAP_MESON)	+= clk-regmap.o
diff --git a/drivers/clk/meson/axg-audio.c b/drivers/clk/meson/axg-audio.c
new file mode 100644
index 000000000000..a0ed41e73bde
--- /dev/null
+++ b/drivers/clk/meson/axg-audio.c
@@ -0,0 +1,845 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2018 BayLibre, SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/init.h>
+#include <linux/of_device.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/reset.h>
+#include <linux/slab.h>
+
+#include "clkc-audio.h"
+#include "axg-audio.h"
+
+#define AXG_MST_IN_COUNT	8
+#define AXG_SLV_SCLK_COUNT	10
+#define AXG_SLV_LRCLK_COUNT	10
+
+#define AXG_AUD_GATE(_name, _reg, _bit, _pname, _iflags)		\
+struct clk_regmap axg_##_name = {					\
+	.data = &(struct clk_regmap_gate_data){				\
+		.offset = (_reg),					\
+		.bit_idx = (_bit),					\
+	},								\
+	.hw.init = &(struct clk_init_data) {				\
+		.name = "axg_"#_name,					\
+		.ops = &clk_regmap_gate_ops,				\
+		.parent_names = (const char *[]){ _pname },		\
+		.num_parents = 1,					\
+		.flags = CLK_DUTY_CYCLE_PARENT | (_iflags),		\
+	},								\
+}
+
+#define AXG_AUD_MUX(_name, _reg, _mask, _shift, _dflags, _pnames, _iflags) \
+struct clk_regmap axg_##_name = {					\
+	.data = &(struct clk_regmap_mux_data){				\
+		.offset = (_reg),					\
+		.mask = (_mask),					\
+		.shift = (_shift),					\
+		.flags = (_dflags),					\
+	},								\
+	.hw.init = &(struct clk_init_data){				\
+		.name = "axg_"#_name,					\
+		.ops = &clk_regmap_mux_ops,				\
+		.parent_names = (_pnames),				\
+		.num_parents = ARRAY_SIZE(_pnames),			\
+		.flags = CLK_DUTY_CYCLE_PARENT | (_iflags),		\
+	},								\
+}
+
+#define AXG_AUD_DIV(_name, _reg, _shift, _width, _dflags, _pname, _iflags) \
+struct clk_regmap axg_##_name = {					\
+	.data = &(struct clk_regmap_div_data){				\
+		.offset = (_reg),					\
+		.shift = (_shift),					\
+		.width = (_width),					\
+		.flags = (_dflags),					\
+	},								\
+	.hw.init = &(struct clk_init_data){				\
+		.name = "axg_"#_name,					\
+		.ops = &clk_regmap_divider_ops,				\
+		.parent_names = (const char *[]) { _pname },		\
+		.num_parents = 1,					\
+		.flags = (_iflags),					\
+	},								\
+}
+
+#define AXG_PCLK_GATE(_name, _bit)				\
+	AXG_AUD_GATE(_name, AUDIO_CLK_GATE_EN, _bit, "axg_audio_pclk", 0)
+
+/* Audio peripheral clocks */
+static AXG_PCLK_GATE(ddr_arb,	   0);
+static AXG_PCLK_GATE(pdm,	   1);
+static AXG_PCLK_GATE(tdmin_a,	   2);
+static AXG_PCLK_GATE(tdmin_b,	   3);
+static AXG_PCLK_GATE(tdmin_c,	   4);
+static AXG_PCLK_GATE(tdmin_lb,	   5);
+static AXG_PCLK_GATE(tdmout_a,	   6);
+static AXG_PCLK_GATE(tdmout_b,	   7);
+static AXG_PCLK_GATE(tdmout_c,	   8);
+static AXG_PCLK_GATE(frddr_a,	   9);
+static AXG_PCLK_GATE(frddr_b,	   10);
+static AXG_PCLK_GATE(frddr_c,	   11);
+static AXG_PCLK_GATE(toddr_a,	   12);
+static AXG_PCLK_GATE(toddr_b,	   13);
+static AXG_PCLK_GATE(toddr_c,	   14);
+static AXG_PCLK_GATE(loopback,	   15);
+static AXG_PCLK_GATE(spdifin,	   16);
+static AXG_PCLK_GATE(spdifout,	   17);
+static AXG_PCLK_GATE(resample,	   18);
+static AXG_PCLK_GATE(power_detect, 19);
+
+/* Audio Master Clocks */
+static const char * const mst_mux_parent_names[] = {
+	"axg_mst_in0", "axg_mst_in1", "axg_mst_in2", "axg_mst_in3",
+	"axg_mst_in4", "axg_mst_in5", "axg_mst_in6", "axg_mst_in7",
+};
+
+#define AXG_MST_MCLK_MUX(_name, _reg)					\
+	AXG_AUD_MUX(_name##_sel, _reg, 0x7, 24, CLK_MUX_ROUND_CLOSEST, \
+		    mst_mux_parent_names, CLK_SET_RATE_PARENT)
+
+static AXG_MST_MCLK_MUX(mst_a_mclk,   AUDIO_MCLK_A_CTRL);
+static AXG_MST_MCLK_MUX(mst_b_mclk,   AUDIO_MCLK_B_CTRL);
+static AXG_MST_MCLK_MUX(mst_c_mclk,   AUDIO_MCLK_C_CTRL);
+static AXG_MST_MCLK_MUX(mst_d_mclk,   AUDIO_MCLK_D_CTRL);
+static AXG_MST_MCLK_MUX(mst_e_mclk,   AUDIO_MCLK_E_CTRL);
+static AXG_MST_MCLK_MUX(mst_f_mclk,   AUDIO_MCLK_F_CTRL);
+static AXG_MST_MCLK_MUX(spdifout_clk, AUDIO_CLK_SPDIFOUT_CTRL);
+static AXG_MST_MCLK_MUX(spdifin_clk,  AUDIO_CLK_SPDIFIN_CTRL);
+static AXG_MST_MCLK_MUX(pdm_dclk,     AUDIO_CLK_PDMIN_CTRL0);
+static AXG_MST_MCLK_MUX(pdm_sysclk,   AUDIO_CLK_PDMIN_CTRL1);
+
+#define AXG_MST_MCLK_DIV(_name, _reg)					\
+	AXG_AUD_DIV(_name##_div, _reg, 0, 16, CLK_DIVIDER_ROUND_CLOSEST, \
+		    "axg_"#_name"_sel", CLK_SET_RATE_PARENT)		\
+
+static AXG_MST_MCLK_DIV(mst_a_mclk,   AUDIO_MCLK_A_CTRL);
+static AXG_MST_MCLK_DIV(mst_b_mclk,   AUDIO_MCLK_B_CTRL);
+static AXG_MST_MCLK_DIV(mst_c_mclk,   AUDIO_MCLK_C_CTRL);
+static AXG_MST_MCLK_DIV(mst_d_mclk,   AUDIO_MCLK_D_CTRL);
+static AXG_MST_MCLK_DIV(mst_e_mclk,   AUDIO_MCLK_E_CTRL);
+static AXG_MST_MCLK_DIV(mst_f_mclk,   AUDIO_MCLK_F_CTRL);
+static AXG_MST_MCLK_DIV(spdifout_clk, AUDIO_CLK_SPDIFOUT_CTRL);
+static AXG_MST_MCLK_DIV(spdifin_clk,  AUDIO_CLK_SPDIFIN_CTRL);
+static AXG_MST_MCLK_DIV(pdm_dclk,     AUDIO_CLK_PDMIN_CTRL0);
+static AXG_MST_MCLK_DIV(pdm_sysclk,   AUDIO_CLK_PDMIN_CTRL1);
+
+#define AXG_MST_MCLK_GATE(_name, _reg)					\
+	AXG_AUD_GATE(_name, _reg, 31,  "axg_"#_name"_div",		\
+		     CLK_SET_RATE_PARENT)
+
+static AXG_MST_MCLK_GATE(mst_a_mclk,   AUDIO_MCLK_A_CTRL);
+static AXG_MST_MCLK_GATE(mst_b_mclk,   AUDIO_MCLK_B_CTRL);
+static AXG_MST_MCLK_GATE(mst_c_mclk,   AUDIO_MCLK_C_CTRL);
+static AXG_MST_MCLK_GATE(mst_d_mclk,   AUDIO_MCLK_D_CTRL);
+static AXG_MST_MCLK_GATE(mst_e_mclk,   AUDIO_MCLK_E_CTRL);
+static AXG_MST_MCLK_GATE(mst_f_mclk,   AUDIO_MCLK_F_CTRL);
+static AXG_MST_MCLK_GATE(spdifout_clk, AUDIO_CLK_SPDIFOUT_CTRL);
+static AXG_MST_MCLK_GATE(spdifin_clk,  AUDIO_CLK_SPDIFIN_CTRL);
+static AXG_MST_MCLK_GATE(pdm_dclk,     AUDIO_CLK_PDMIN_CTRL0);
+static AXG_MST_MCLK_GATE(pdm_sysclk,   AUDIO_CLK_PDMIN_CTRL1);
+
+/* Sample Clocks */
+#define AXG_MST_SCLK_PRE_EN(_name, _reg)			\
+	AXG_AUD_GATE(mst_##_name##_sclk_pre_en, _reg, 31,	\
+		     "axg_mst_"#_name"_mclk", 0)
+
+static AXG_MST_SCLK_PRE_EN(a, AUDIO_MST_A_SCLK_CTRL0);
+static AXG_MST_SCLK_PRE_EN(b, AUDIO_MST_B_SCLK_CTRL0);
+static AXG_MST_SCLK_PRE_EN(c, AUDIO_MST_C_SCLK_CTRL0);
+static AXG_MST_SCLK_PRE_EN(d, AUDIO_MST_D_SCLK_CTRL0);
+static AXG_MST_SCLK_PRE_EN(e, AUDIO_MST_E_SCLK_CTRL0);
+static AXG_MST_SCLK_PRE_EN(f, AUDIO_MST_F_SCLK_CTRL0);
+
+#define AXG_AUD_SCLK_DIV(_name, _reg, _div_shift, _div_width,		\
+			 _hi_shift, _hi_width, _pname, _iflags)		\
+struct clk_regmap axg_##_name = {					\
+	.data = &(struct meson_sclk_div_data) {				\
+		.div = {						\
+			.reg_off = (_reg),				\
+			.shift   = (_div_shift),			\
+			.width   = (_div_width),			\
+		},							\
+		.hi = {							\
+			.reg_off = (_reg),				\
+			.shift   = (_hi_shift),				\
+			.width   = (_hi_width),				\
+		},							\
+	},								\
+	.hw.init = &(struct clk_init_data) {				\
+		.name = "axg_"#_name,					\
+		.ops = &meson_sclk_div_ops,				\
+		.parent_names = (const char *[]) { _pname },		\
+		.num_parents = 1,					\
+		.flags = (_iflags),					\
+	},								\
+}
+
+#define AXG_MST_SCLK_DIV(_name, _reg)					\
+	AXG_AUD_SCLK_DIV(mst_##_name##_sclk_div, _reg, 20, 10, 0, 0,	\
+			 "axg_mst_"#_name"_sclk_pre_en",		\
+			 CLK_SET_RATE_PARENT)
+
+static AXG_MST_SCLK_DIV(a, AUDIO_MST_A_SCLK_CTRL0);
+static AXG_MST_SCLK_DIV(b, AUDIO_MST_B_SCLK_CTRL0);
+static AXG_MST_SCLK_DIV(c, AUDIO_MST_C_SCLK_CTRL0);
+static AXG_MST_SCLK_DIV(d, AUDIO_MST_D_SCLK_CTRL0);
+static AXG_MST_SCLK_DIV(e, AUDIO_MST_E_SCLK_CTRL0);
+static AXG_MST_SCLK_DIV(f, AUDIO_MST_F_SCLK_CTRL0);
+
+#define AXG_MST_SCLK_POST_EN(_name, _reg)				\
+	AXG_AUD_GATE(mst_##_name##_sclk_post_en, _reg, 30,		\
+		     "axg_mst_"#_name"_sclk_div", CLK_SET_RATE_PARENT)
+
+static AXG_MST_SCLK_POST_EN(a, AUDIO_MST_A_SCLK_CTRL0);
+static AXG_MST_SCLK_POST_EN(b, AUDIO_MST_B_SCLK_CTRL0);
+static AXG_MST_SCLK_POST_EN(c, AUDIO_MST_C_SCLK_CTRL0);
+static AXG_MST_SCLK_POST_EN(d, AUDIO_MST_D_SCLK_CTRL0);
+static AXG_MST_SCLK_POST_EN(e, AUDIO_MST_E_SCLK_CTRL0);
+static AXG_MST_SCLK_POST_EN(f, AUDIO_MST_F_SCLK_CTRL0);
+
+#define AXG_AUD_TRIPHASE(_name, _reg, _width, _shift0, _shift1, _shift2, \
+			 _pname, _iflags)				\
+struct clk_regmap axg_##_name = {					\
+	.data = &(struct meson_clk_triphase_data) {			\
+		.ph0 = {						\
+			.reg_off = (_reg),				\
+			.shift   = (_shift0),				\
+			.width   = (_width),				\
+		},							\
+		.ph1 = {						\
+			.reg_off = (_reg),				\
+			.shift   = (_shift1),				\
+			.width   = (_width),				\
+		},							\
+		.ph2 = {						\
+			.reg_off = (_reg),				\
+			.shift   = (_shift2),				\
+			.width   = (_width),				\
+		},							\
+	},								\
+	.hw.init = &(struct clk_init_data) {				\
+		.name = "axg_"#_name,					\
+		.ops = &meson_clk_triphase_ops,				\
+		.parent_names = (const char *[]) { _pname },		\
+		.num_parents = 1,					\
+		.flags = CLK_DUTY_CYCLE_PARENT | (_iflags),		\
+	},								\
+}
+
+#define AXG_MST_SCLK(_name, _reg)					\
+	AXG_AUD_TRIPHASE(mst_##_name##_sclk, _reg, 1, 0, 2, 4,		\
+			 "axg_mst_"#_name"_sclk_post_en", CLK_SET_RATE_PARENT)
+
+static AXG_MST_SCLK(a, AUDIO_MST_A_SCLK_CTRL1);
+static AXG_MST_SCLK(b, AUDIO_MST_B_SCLK_CTRL1);
+static AXG_MST_SCLK(c, AUDIO_MST_C_SCLK_CTRL1);
+static AXG_MST_SCLK(d, AUDIO_MST_D_SCLK_CTRL1);
+static AXG_MST_SCLK(e, AUDIO_MST_E_SCLK_CTRL1);
+static AXG_MST_SCLK(f, AUDIO_MST_F_SCLK_CTRL1);
+
+#define AXG_MST_LRCLK_DIV(_name, _reg)					\
+	AXG_AUD_SCLK_DIV(mst_##_name##_lrclk_div, _reg, 0, 10, 10, 10,	\
+		    "axg_mst_"#_name"_sclk_post_en", 0)			\
+
+static AXG_MST_LRCLK_DIV(a, AUDIO_MST_A_SCLK_CTRL0);
+static AXG_MST_LRCLK_DIV(b, AUDIO_MST_B_SCLK_CTRL0);
+static AXG_MST_LRCLK_DIV(c, AUDIO_MST_C_SCLK_CTRL0);
+static AXG_MST_LRCLK_DIV(d, AUDIO_MST_D_SCLK_CTRL0);
+static AXG_MST_LRCLK_DIV(e, AUDIO_MST_E_SCLK_CTRL0);
+static AXG_MST_LRCLK_DIV(f, AUDIO_MST_F_SCLK_CTRL0);
+
+#define AXG_MST_LRCLK(_name, _reg)					\
+	AXG_AUD_TRIPHASE(mst_##_name##_lrclk, _reg, 1, 1, 3, 5,		\
+			 "axg_mst_"#_name"_lrclk_div", CLK_SET_RATE_PARENT)
+
+static AXG_MST_LRCLK(a, AUDIO_MST_A_SCLK_CTRL1);
+static AXG_MST_LRCLK(b, AUDIO_MST_B_SCLK_CTRL1);
+static AXG_MST_LRCLK(c, AUDIO_MST_C_SCLK_CTRL1);
+static AXG_MST_LRCLK(d, AUDIO_MST_D_SCLK_CTRL1);
+static AXG_MST_LRCLK(e, AUDIO_MST_E_SCLK_CTRL1);
+static AXG_MST_LRCLK(f, AUDIO_MST_F_SCLK_CTRL1);
+
+static const char * const tdm_sclk_parent_names[] = {
+	"axg_mst_a_sclk", "axg_mst_b_sclk", "axg_mst_c_sclk",
+	"axg_mst_d_sclk", "axg_mst_e_sclk", "axg_mst_f_sclk",
+	"axg_slv_sclk0", "axg_slv_sclk1", "axg_slv_sclk2",
+	"axg_slv_sclk3", "axg_slv_sclk4", "axg_slv_sclk5",
+	"axg_slv_sclk6", "axg_slv_sclk7", "axg_slv_sclk8",
+	"axg_slv_sclk9"
+};
+
+#define AXG_TDM_SCLK_MUX(_name, _reg)				\
+	AXG_AUD_MUX(tdm##_name##_sclk_sel, _reg, 0xf, 24,	\
+		    CLK_MUX_ROUND_CLOSEST,			\
+		    tdm_sclk_parent_names, 0)
+
+static AXG_TDM_SCLK_MUX(in_a,  AUDIO_CLK_TDMIN_A_CTRL);
+static AXG_TDM_SCLK_MUX(in_b,  AUDIO_CLK_TDMIN_B_CTRL);
+static AXG_TDM_SCLK_MUX(in_c,  AUDIO_CLK_TDMIN_C_CTRL);
+static AXG_TDM_SCLK_MUX(in_lb, AUDIO_CLK_TDMIN_LB_CTRL);
+static AXG_TDM_SCLK_MUX(out_a, AUDIO_CLK_TDMOUT_A_CTRL);
+static AXG_TDM_SCLK_MUX(out_b, AUDIO_CLK_TDMOUT_B_CTRL);
+static AXG_TDM_SCLK_MUX(out_c, AUDIO_CLK_TDMOUT_C_CTRL);
+
+#define AXG_TDM_SCLK_PRE_EN(_name, _reg)				\
+	AXG_AUD_GATE(tdm##_name##_sclk_pre_en, _reg, 31,		\
+		     "axg_tdm"#_name"_sclk_sel", CLK_SET_RATE_PARENT)
+
+static AXG_TDM_SCLK_PRE_EN(in_a,  AUDIO_CLK_TDMIN_A_CTRL);
+static AXG_TDM_SCLK_PRE_EN(in_b,  AUDIO_CLK_TDMIN_B_CTRL);
+static AXG_TDM_SCLK_PRE_EN(in_c,  AUDIO_CLK_TDMIN_C_CTRL);
+static AXG_TDM_SCLK_PRE_EN(in_lb, AUDIO_CLK_TDMIN_LB_CTRL);
+static AXG_TDM_SCLK_PRE_EN(out_a, AUDIO_CLK_TDMOUT_A_CTRL);
+static AXG_TDM_SCLK_PRE_EN(out_b, AUDIO_CLK_TDMOUT_B_CTRL);
+static AXG_TDM_SCLK_PRE_EN(out_c, AUDIO_CLK_TDMOUT_C_CTRL);
+
+#define AXG_TDM_SCLK_POST_EN(_name, _reg)				\
+	AXG_AUD_GATE(tdm##_name##_sclk_post_en, _reg, 30,		\
+		     "axg_tdm"#_name"_sclk_pre_en", CLK_SET_RATE_PARENT)
+
+static AXG_TDM_SCLK_POST_EN(in_a,  AUDIO_CLK_TDMIN_A_CTRL);
+static AXG_TDM_SCLK_POST_EN(in_b,  AUDIO_CLK_TDMIN_B_CTRL);
+static AXG_TDM_SCLK_POST_EN(in_c,  AUDIO_CLK_TDMIN_C_CTRL);
+static AXG_TDM_SCLK_POST_EN(in_lb, AUDIO_CLK_TDMIN_LB_CTRL);
+static AXG_TDM_SCLK_POST_EN(out_a, AUDIO_CLK_TDMOUT_A_CTRL);
+static AXG_TDM_SCLK_POST_EN(out_b, AUDIO_CLK_TDMOUT_B_CTRL);
+static AXG_TDM_SCLK_POST_EN(out_c, AUDIO_CLK_TDMOUT_C_CTRL);
+
+#define AXG_TDM_SCLK(_name, _reg)					\
+	struct clk_regmap axg_tdm##_name##_sclk = {			\
+	.data = &(struct meson_clk_phase_data) {			\
+		.ph = {							\
+			.reg_off = (_reg),				\
+			.shift   = 29,					\
+			.width   = 1,					\
+		},							\
+	},								\
+	.hw.init = &(struct clk_init_data) {				\
+		.name = "axg_tdm"#_name"_sclk",				\
+		.ops = &meson_clk_phase_ops,				\
+		.parent_names = (const char *[])			\
+		{ "axg_tdm"#_name"_sclk_post_en" },			\
+		.num_parents = 1,					\
+		.flags = CLK_DUTY_CYCLE_PARENT | CLK_SET_RATE_PARENT,	\
+	},								\
+}
+
+static AXG_TDM_SCLK(in_a,  AUDIO_CLK_TDMIN_A_CTRL);
+static AXG_TDM_SCLK(in_b,  AUDIO_CLK_TDMIN_B_CTRL);
+static AXG_TDM_SCLK(in_c,  AUDIO_CLK_TDMIN_C_CTRL);
+static AXG_TDM_SCLK(in_lb, AUDIO_CLK_TDMIN_LB_CTRL);
+static AXG_TDM_SCLK(out_a, AUDIO_CLK_TDMOUT_A_CTRL);
+static AXG_TDM_SCLK(out_b, AUDIO_CLK_TDMOUT_B_CTRL);
+static AXG_TDM_SCLK(out_c, AUDIO_CLK_TDMOUT_C_CTRL);
+
+static const char * const tdm_lrclk_parent_names[] = {
+	"axg_mst_a_lrclk", "axg_mst_b_lrclk", "axg_mst_c_lrclk",
+	"axg_mst_d_lrclk", "axg_mst_e_lrclk", "axg_mst_f_lrclk",
+	"axg_slv_lrclk0", "axg_slv_lrclk1", "axg_slv_lrclk2",
+	"axg_slv_lrclk3", "axg_slv_lrclk4", "axg_slv_lrclk5",
+	"axg_slv_lrclk6", "axg_slv_lrclk7", "axg_slv_lrclk8",
+	"axg_slv_lrclk9"
+};
+
+#define AXG_TDM_LRLCK(_name, _reg)		       \
+	AXG_AUD_MUX(tdm##_name##_lrclk, _reg, 0xf, 20, \
+		    CLK_MUX_ROUND_CLOSEST,	       \
+		    tdm_lrclk_parent_names, 0)
+
+static AXG_TDM_LRLCK(in_a,  AUDIO_CLK_TDMIN_A_CTRL);
+static AXG_TDM_LRLCK(in_b,  AUDIO_CLK_TDMIN_B_CTRL);
+static AXG_TDM_LRLCK(in_c,  AUDIO_CLK_TDMIN_C_CTRL);
+static AXG_TDM_LRLCK(in_lb, AUDIO_CLK_TDMIN_LB_CTRL);
+static AXG_TDM_LRLCK(out_a, AUDIO_CLK_TDMOUT_A_CTRL);
+static AXG_TDM_LRLCK(out_b, AUDIO_CLK_TDMOUT_B_CTRL);
+static AXG_TDM_LRLCK(out_c, AUDIO_CLK_TDMOUT_C_CTRL);
+
+/*
+ * Array of all clocks provided by this provider
+ * The input clocks of the controller will be populated at runtime
+ */
+static struct clk_hw_onecell_data axg_audio_hw_onecell_data = {
+	.hws = {
+		[AUD_CLKID_DDR_ARB]		= &axg_ddr_arb.hw,
+		[AUD_CLKID_PDM]			= &axg_pdm.hw,
+		[AUD_CLKID_TDMIN_A]		= &axg_tdmin_a.hw,
+		[AUD_CLKID_TDMIN_B]		= &axg_tdmin_b.hw,
+		[AUD_CLKID_TDMIN_C]		= &axg_tdmin_c.hw,
+		[AUD_CLKID_TDMIN_LB]		= &axg_tdmin_lb.hw,
+		[AUD_CLKID_TDMOUT_A]		= &axg_tdmout_a.hw,
+		[AUD_CLKID_TDMOUT_B]		= &axg_tdmout_b.hw,
+		[AUD_CLKID_TDMOUT_C]		= &axg_tdmout_c.hw,
+		[AUD_CLKID_FRDDR_A]		= &axg_frddr_a.hw,
+		[AUD_CLKID_FRDDR_B]		= &axg_frddr_b.hw,
+		[AUD_CLKID_FRDDR_C]		= &axg_frddr_c.hw,
+		[AUD_CLKID_TODDR_A]		= &axg_toddr_a.hw,
+		[AUD_CLKID_TODDR_B]		= &axg_toddr_b.hw,
+		[AUD_CLKID_TODDR_C]		= &axg_toddr_c.hw,
+		[AUD_CLKID_LOOPBACK]		= &axg_loopback.hw,
+		[AUD_CLKID_SPDIFIN]		= &axg_spdifin.hw,
+		[AUD_CLKID_SPDIFOUT]		= &axg_spdifout.hw,
+		[AUD_CLKID_RESAMPLE]		= &axg_resample.hw,
+		[AUD_CLKID_POWER_DETECT]	= &axg_power_detect.hw,
+		[AUD_CLKID_MST_A_MCLK_SEL]	= &axg_mst_a_mclk_sel.hw,
+		[AUD_CLKID_MST_B_MCLK_SEL]	= &axg_mst_b_mclk_sel.hw,
+		[AUD_CLKID_MST_C_MCLK_SEL]	= &axg_mst_c_mclk_sel.hw,
+		[AUD_CLKID_MST_D_MCLK_SEL]	= &axg_mst_d_mclk_sel.hw,
+		[AUD_CLKID_MST_E_MCLK_SEL]	= &axg_mst_e_mclk_sel.hw,
+		[AUD_CLKID_MST_F_MCLK_SEL]	= &axg_mst_f_mclk_sel.hw,
+		[AUD_CLKID_MST_A_MCLK_DIV]	= &axg_mst_a_mclk_div.hw,
+		[AUD_CLKID_MST_B_MCLK_DIV]	= &axg_mst_b_mclk_div.hw,
+		[AUD_CLKID_MST_C_MCLK_DIV]	= &axg_mst_c_mclk_div.hw,
+		[AUD_CLKID_MST_D_MCLK_DIV]	= &axg_mst_d_mclk_div.hw,
+		[AUD_CLKID_MST_E_MCLK_DIV]	= &axg_mst_e_mclk_div.hw,
+		[AUD_CLKID_MST_F_MCLK_DIV]	= &axg_mst_f_mclk_div.hw,
+		[AUD_CLKID_MST_A_MCLK]		= &axg_mst_a_mclk.hw,
+		[AUD_CLKID_MST_B_MCLK]		= &axg_mst_b_mclk.hw,
+		[AUD_CLKID_MST_C_MCLK]		= &axg_mst_c_mclk.hw,
+		[AUD_CLKID_MST_D_MCLK]		= &axg_mst_d_mclk.hw,
+		[AUD_CLKID_MST_E_MCLK]		= &axg_mst_e_mclk.hw,
+		[AUD_CLKID_MST_F_MCLK]		= &axg_mst_f_mclk.hw,
+		[AUD_CLKID_SPDIFOUT_CLK_SEL]	= &axg_spdifout_clk_sel.hw,
+		[AUD_CLKID_SPDIFOUT_CLK_DIV]	= &axg_spdifout_clk_div.hw,
+		[AUD_CLKID_SPDIFOUT_CLK]	= &axg_spdifout_clk.hw,
+		[AUD_CLKID_SPDIFIN_CLK_SEL]	= &axg_spdifin_clk_sel.hw,
+		[AUD_CLKID_SPDIFIN_CLK_DIV]	= &axg_spdifin_clk_div.hw,
+		[AUD_CLKID_SPDIFIN_CLK]		= &axg_spdifin_clk.hw,
+		[AUD_CLKID_PDM_DCLK_SEL]	= &axg_pdm_dclk_sel.hw,
+		[AUD_CLKID_PDM_DCLK_DIV]	= &axg_pdm_dclk_div.hw,
+		[AUD_CLKID_PDM_DCLK]		= &axg_pdm_dclk.hw,
+		[AUD_CLKID_PDM_SYSCLK_SEL]	= &axg_pdm_sysclk_sel.hw,
+		[AUD_CLKID_PDM_SYSCLK_DIV]	= &axg_pdm_sysclk_div.hw,
+		[AUD_CLKID_PDM_SYSCLK]		= &axg_pdm_sysclk.hw,
+		[AUD_CLKID_MST_A_SCLK_PRE_EN]	= &axg_mst_a_sclk_pre_en.hw,
+		[AUD_CLKID_MST_B_SCLK_PRE_EN]	= &axg_mst_b_sclk_pre_en.hw,
+		[AUD_CLKID_MST_C_SCLK_PRE_EN]	= &axg_mst_c_sclk_pre_en.hw,
+		[AUD_CLKID_MST_D_SCLK_PRE_EN]	= &axg_mst_d_sclk_pre_en.hw,
+		[AUD_CLKID_MST_E_SCLK_PRE_EN]	= &axg_mst_e_sclk_pre_en.hw,
+		[AUD_CLKID_MST_F_SCLK_PRE_EN]	= &axg_mst_f_sclk_pre_en.hw,
+		[AUD_CLKID_MST_A_SCLK_DIV]	= &axg_mst_a_sclk_div.hw,
+		[AUD_CLKID_MST_B_SCLK_DIV]	= &axg_mst_b_sclk_div.hw,
+		[AUD_CLKID_MST_C_SCLK_DIV]	= &axg_mst_c_sclk_div.hw,
+		[AUD_CLKID_MST_D_SCLK_DIV]	= &axg_mst_d_sclk_div.hw,
+		[AUD_CLKID_MST_E_SCLK_DIV]	= &axg_mst_e_sclk_div.hw,
+		[AUD_CLKID_MST_F_SCLK_DIV]	= &axg_mst_f_sclk_div.hw,
+		[AUD_CLKID_MST_A_SCLK_POST_EN]	= &axg_mst_a_sclk_post_en.hw,
+		[AUD_CLKID_MST_B_SCLK_POST_EN]	= &axg_mst_b_sclk_post_en.hw,
+		[AUD_CLKID_MST_C_SCLK_POST_EN]	= &axg_mst_c_sclk_post_en.hw,
+		[AUD_CLKID_MST_D_SCLK_POST_EN]	= &axg_mst_d_sclk_post_en.hw,
+		[AUD_CLKID_MST_E_SCLK_POST_EN]	= &axg_mst_e_sclk_post_en.hw,
+		[AUD_CLKID_MST_F_SCLK_POST_EN]	= &axg_mst_f_sclk_post_en.hw,
+		[AUD_CLKID_MST_A_SCLK]		= &axg_mst_a_sclk.hw,
+		[AUD_CLKID_MST_B_SCLK]		= &axg_mst_b_sclk.hw,
+		[AUD_CLKID_MST_C_SCLK]		= &axg_mst_c_sclk.hw,
+		[AUD_CLKID_MST_D_SCLK]		= &axg_mst_d_sclk.hw,
+		[AUD_CLKID_MST_E_SCLK]		= &axg_mst_e_sclk.hw,
+		[AUD_CLKID_MST_F_SCLK]		= &axg_mst_f_sclk.hw,
+		[AUD_CLKID_MST_A_LRCLK_DIV]	= &axg_mst_a_lrclk_div.hw,
+		[AUD_CLKID_MST_B_LRCLK_DIV]	= &axg_mst_b_lrclk_div.hw,
+		[AUD_CLKID_MST_C_LRCLK_DIV]	= &axg_mst_c_lrclk_div.hw,
+		[AUD_CLKID_MST_D_LRCLK_DIV]	= &axg_mst_d_lrclk_div.hw,
+		[AUD_CLKID_MST_E_LRCLK_DIV]	= &axg_mst_e_lrclk_div.hw,
+		[AUD_CLKID_MST_F_LRCLK_DIV]	= &axg_mst_f_lrclk_div.hw,
+		[AUD_CLKID_MST_A_LRCLK]		= &axg_mst_a_lrclk.hw,
+		[AUD_CLKID_MST_B_LRCLK]		= &axg_mst_b_lrclk.hw,
+		[AUD_CLKID_MST_C_LRCLK]		= &axg_mst_c_lrclk.hw,
+		[AUD_CLKID_MST_D_LRCLK]		= &axg_mst_d_lrclk.hw,
+		[AUD_CLKID_MST_E_LRCLK]		= &axg_mst_e_lrclk.hw,
+		[AUD_CLKID_MST_F_LRCLK]		= &axg_mst_f_lrclk.hw,
+		[AUD_CLKID_TDMIN_A_SCLK_SEL]	= &axg_tdmin_a_sclk_sel.hw,
+		[AUD_CLKID_TDMIN_B_SCLK_SEL]	= &axg_tdmin_b_sclk_sel.hw,
+		[AUD_CLKID_TDMIN_C_SCLK_SEL]	= &axg_tdmin_c_sclk_sel.hw,
+		[AUD_CLKID_TDMIN_LB_SCLK_SEL]	= &axg_tdmin_lb_sclk_sel.hw,
+		[AUD_CLKID_TDMOUT_A_SCLK_SEL]	= &axg_tdmout_a_sclk_sel.hw,
+		[AUD_CLKID_TDMOUT_B_SCLK_SEL]	= &axg_tdmout_b_sclk_sel.hw,
+		[AUD_CLKID_TDMOUT_C_SCLK_SEL]	= &axg_tdmout_c_sclk_sel.hw,
+		[AUD_CLKID_TDMIN_A_SCLK_PRE_EN]	= &axg_tdmin_a_sclk_pre_en.hw,
+		[AUD_CLKID_TDMIN_B_SCLK_PRE_EN]	= &axg_tdmin_b_sclk_pre_en.hw,
+		[AUD_CLKID_TDMIN_C_SCLK_PRE_EN]	= &axg_tdmin_c_sclk_pre_en.hw,
+		[AUD_CLKID_TDMIN_LB_SCLK_PRE_EN] = &axg_tdmin_lb_sclk_pre_en.hw,
+		[AUD_CLKID_TDMOUT_A_SCLK_PRE_EN] = &axg_tdmout_a_sclk_pre_en.hw,
+		[AUD_CLKID_TDMOUT_B_SCLK_PRE_EN] = &axg_tdmout_b_sclk_pre_en.hw,
+		[AUD_CLKID_TDMOUT_C_SCLK_PRE_EN] = &axg_tdmout_c_sclk_pre_en.hw,
+		[AUD_CLKID_TDMIN_A_SCLK_POST_EN] = &axg_tdmin_a_sclk_post_en.hw,
+		[AUD_CLKID_TDMIN_B_SCLK_POST_EN] = &axg_tdmin_b_sclk_post_en.hw,
+		[AUD_CLKID_TDMIN_C_SCLK_POST_EN] = &axg_tdmin_c_sclk_post_en.hw,
+		[AUD_CLKID_TDMIN_LB_SCLK_POST_EN] = &axg_tdmin_lb_sclk_post_en.hw,
+		[AUD_CLKID_TDMOUT_A_SCLK_POST_EN] = &axg_tdmout_a_sclk_post_en.hw,
+		[AUD_CLKID_TDMOUT_B_SCLK_POST_EN] = &axg_tdmout_b_sclk_post_en.hw,
+		[AUD_CLKID_TDMOUT_C_SCLK_POST_EN] = &axg_tdmout_c_sclk_post_en.hw,
+		[AUD_CLKID_TDMIN_A_SCLK]	= &axg_tdmin_a_sclk.hw,
+		[AUD_CLKID_TDMIN_B_SCLK]	= &axg_tdmin_b_sclk.hw,
+		[AUD_CLKID_TDMIN_C_SCLK]	= &axg_tdmin_c_sclk.hw,
+		[AUD_CLKID_TDMIN_LB_SCLK]	= &axg_tdmin_lb_sclk.hw,
+		[AUD_CLKID_TDMOUT_A_SCLK]	= &axg_tdmout_a_sclk.hw,
+		[AUD_CLKID_TDMOUT_B_SCLK]	= &axg_tdmout_b_sclk.hw,
+		[AUD_CLKID_TDMOUT_C_SCLK]	= &axg_tdmout_c_sclk.hw,
+		[AUD_CLKID_TDMIN_A_LRCLK]	= &axg_tdmin_a_lrclk.hw,
+		[AUD_CLKID_TDMIN_B_LRCLK]	= &axg_tdmin_b_lrclk.hw,
+		[AUD_CLKID_TDMIN_C_LRCLK]	= &axg_tdmin_c_lrclk.hw,
+		[AUD_CLKID_TDMIN_LB_LRCLK]	= &axg_tdmin_lb_lrclk.hw,
+		[AUD_CLKID_TDMOUT_A_LRCLK]	= &axg_tdmout_a_lrclk.hw,
+		[AUD_CLKID_TDMOUT_B_LRCLK]	= &axg_tdmout_b_lrclk.hw,
+		[AUD_CLKID_TDMOUT_C_LRCLK]	= &axg_tdmout_c_lrclk.hw,
+		[NR_CLKS] = NULL,
+	},
+	.num = NR_CLKS,
+};
+
+/* Convenience table to populate regmap in .probe() */
+static struct clk_regmap *const axg_audio_clk_regmaps[] = {
+	&axg_ddr_arb,
+	&axg_pdm,
+	&axg_tdmin_a,
+	&axg_tdmin_b,
+	&axg_tdmin_c,
+	&axg_tdmin_lb,
+	&axg_tdmout_a,
+	&axg_tdmout_b,
+	&axg_tdmout_c,
+	&axg_frddr_a,
+	&axg_frddr_b,
+	&axg_frddr_c,
+	&axg_toddr_a,
+	&axg_toddr_b,
+	&axg_toddr_c,
+	&axg_loopback,
+	&axg_spdifin,
+	&axg_spdifout,
+	&axg_resample,
+	&axg_power_detect,
+	&axg_mst_a_mclk_sel,
+	&axg_mst_b_mclk_sel,
+	&axg_mst_c_mclk_sel,
+	&axg_mst_d_mclk_sel,
+	&axg_mst_e_mclk_sel,
+	&axg_mst_f_mclk_sel,
+	&axg_mst_a_mclk_div,
+	&axg_mst_b_mclk_div,
+	&axg_mst_c_mclk_div,
+	&axg_mst_d_mclk_div,
+	&axg_mst_e_mclk_div,
+	&axg_mst_f_mclk_div,
+	&axg_mst_a_mclk,
+	&axg_mst_b_mclk,
+	&axg_mst_c_mclk,
+	&axg_mst_d_mclk,
+	&axg_mst_e_mclk,
+	&axg_mst_f_mclk,
+	&axg_spdifout_clk_sel,
+	&axg_spdifout_clk_div,
+	&axg_spdifout_clk,
+	&axg_spdifin_clk_sel,
+	&axg_spdifin_clk_div,
+	&axg_spdifin_clk,
+	&axg_pdm_dclk_sel,
+	&axg_pdm_dclk_div,
+	&axg_pdm_dclk,
+	&axg_pdm_sysclk_sel,
+	&axg_pdm_sysclk_div,
+	&axg_pdm_sysclk,
+	&axg_mst_a_sclk_pre_en,
+	&axg_mst_b_sclk_pre_en,
+	&axg_mst_c_sclk_pre_en,
+	&axg_mst_d_sclk_pre_en,
+	&axg_mst_e_sclk_pre_en,
+	&axg_mst_f_sclk_pre_en,
+	&axg_mst_a_sclk_div,
+	&axg_mst_b_sclk_div,
+	&axg_mst_c_sclk_div,
+	&axg_mst_d_sclk_div,
+	&axg_mst_e_sclk_div,
+	&axg_mst_f_sclk_div,
+	&axg_mst_a_sclk_post_en,
+	&axg_mst_b_sclk_post_en,
+	&axg_mst_c_sclk_post_en,
+	&axg_mst_d_sclk_post_en,
+	&axg_mst_e_sclk_post_en,
+	&axg_mst_f_sclk_post_en,
+	&axg_mst_a_sclk,
+	&axg_mst_b_sclk,
+	&axg_mst_c_sclk,
+	&axg_mst_d_sclk,
+	&axg_mst_e_sclk,
+	&axg_mst_f_sclk,
+	&axg_mst_a_lrclk_div,
+	&axg_mst_b_lrclk_div,
+	&axg_mst_c_lrclk_div,
+	&axg_mst_d_lrclk_div,
+	&axg_mst_e_lrclk_div,
+	&axg_mst_f_lrclk_div,
+	&axg_mst_a_lrclk,
+	&axg_mst_b_lrclk,
+	&axg_mst_c_lrclk,
+	&axg_mst_d_lrclk,
+	&axg_mst_e_lrclk,
+	&axg_mst_f_lrclk,
+	&axg_tdmin_a_sclk_sel,
+	&axg_tdmin_b_sclk_sel,
+	&axg_tdmin_c_sclk_sel,
+	&axg_tdmin_lb_sclk_sel,
+	&axg_tdmout_a_sclk_sel,
+	&axg_tdmout_b_sclk_sel,
+	&axg_tdmout_c_sclk_sel,
+	&axg_tdmin_a_sclk_pre_en,
+	&axg_tdmin_b_sclk_pre_en,
+	&axg_tdmin_c_sclk_pre_en,
+	&axg_tdmin_lb_sclk_pre_en,
+	&axg_tdmout_a_sclk_pre_en,
+	&axg_tdmout_b_sclk_pre_en,
+	&axg_tdmout_c_sclk_pre_en,
+	&axg_tdmin_a_sclk_post_en,
+	&axg_tdmin_b_sclk_post_en,
+	&axg_tdmin_c_sclk_post_en,
+	&axg_tdmin_lb_sclk_post_en,
+	&axg_tdmout_a_sclk_post_en,
+	&axg_tdmout_b_sclk_post_en,
+	&axg_tdmout_c_sclk_post_en,
+	&axg_tdmin_a_sclk,
+	&axg_tdmin_b_sclk,
+	&axg_tdmin_c_sclk,
+	&axg_tdmin_lb_sclk,
+	&axg_tdmout_a_sclk,
+	&axg_tdmout_b_sclk,
+	&axg_tdmout_c_sclk,
+	&axg_tdmin_a_lrclk,
+	&axg_tdmin_b_lrclk,
+	&axg_tdmin_c_lrclk,
+	&axg_tdmin_lb_lrclk,
+	&axg_tdmout_a_lrclk,
+	&axg_tdmout_b_lrclk,
+	&axg_tdmout_c_lrclk,
+};
+
+static struct clk *devm_clk_get_enable(struct device *dev, char *id)
+{
+	struct clk *clk;
+	int ret;
+
+	clk = devm_clk_get(dev, id);
+	if (IS_ERR(clk)) {
+		if (PTR_ERR(clk) != -EPROBE_DEFER)
+			dev_err(dev, "failed to get %s", id);
+		return clk;
+	}
+
+	ret = clk_prepare_enable(clk);
+	if (ret) {
+		dev_err(dev, "failed to enable %s", id);
+		return ERR_PTR(ret);
+	}
+
+	ret = devm_add_action_or_reset(dev,
+				       (void(*)(void *))clk_disable_unprepare,
+				       clk);
+	if (ret) {
+		dev_err(dev, "failed to add reset action on %s", id);
+		return ERR_PTR(ret);
+	}
+
+	return clk;
+}
+
+static const struct clk_ops axg_clk_no_ops = {};
+
+static struct clk_hw *axg_clk_hw_register_bypass(struct device *dev,
+						 const char *name,
+						 const char *parent_name)
+{
+	struct clk_hw *hw;
+	struct clk_init_data init;
+	char *clk_name;
+	int ret;
+
+	hw = devm_kzalloc(dev, sizeof(*hw), GFP_KERNEL);
+	if (!hw)
+		return ERR_PTR(-ENOMEM);
+
+	clk_name = kasprintf(GFP_KERNEL, "axg_%s", name);
+	if (!clk_name)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = clk_name;
+	init.ops = &axg_clk_no_ops;
+	init.flags = 0;
+	init.parent_names = parent_name ? &parent_name : NULL;
+	init.num_parents = parent_name ? 1 : 0;
+	hw->init = &init;
+
+	ret = devm_clk_hw_register(dev, hw);
+	kfree(clk_name);
+
+	return ret ? ERR_PTR(ret) : hw;
+}
+
+static int axg_register_clk_hw_input(struct device *dev,
+				     const char *name,
+				     unsigned int clkid)
+{
+	struct clk *parent_clk = devm_clk_get(dev, name);
+	struct clk_hw *hw = NULL;
+
+	if (IS_ERR(parent_clk)) {
+		int err = PTR_ERR(parent_clk);
+
+		/* It is ok if an input clock is missing */
+		if (err == -ENOENT) {
+			dev_dbg(dev, "%s not provided", name);
+		} else {
+			if (err != -EPROBE_DEFER)
+				dev_err(dev, "failed to get %s clock", name);
+			return err;
+		}
+	} else {
+		hw = axg_clk_hw_register_bypass(dev, name,
+						__clk_get_name(parent_clk));
+	}
+
+	if (IS_ERR(hw)) {
+		dev_err(dev, "failed to register %s clock", name);
+		return PTR_ERR(hw);
+	}
+
+	axg_audio_hw_onecell_data.hws[clkid] = hw;
+	return 0;
+}
+
+static int axg_register_clk_hw_inputs(struct device *dev,
+				      const char *basename,
+				      unsigned int count,
+				      unsigned int clkid)
+{
+	char *name;
+	int i, ret;
+
+	for (i = 0; i < count; i++) {
+		name = kasprintf(GFP_KERNEL, "%s%d", basename, i);
+		if (!name)
+			return -ENOMEM;
+
+		ret = axg_register_clk_hw_input(dev, name, clkid + i);
+		kfree(name);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static const struct regmap_config axg_audio_regmap_cfg = {
+	.reg_bits	= 32,
+	.val_bits	= 32,
+	.reg_stride	= 4,
+	.max_register	= AUDIO_CLK_PDMIN_CTRL1,
+};
+
+static int axg_audio_clkc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct regmap *map;
+	struct resource *res;
+	void __iomem *regs;
+	struct clk *clk;
+	struct clk_hw *hw;
+	int ret, i;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
+
+	map = devm_regmap_init_mmio(dev, regs, &axg_audio_regmap_cfg);
+	if (IS_ERR(map)) {
+		dev_err(dev, "failed to init regmap: %ld\n", PTR_ERR(map));
+		return PTR_ERR(map);
+	}
+
+	/* Get the mandatory peripheral clock */
+	clk = devm_clk_get_enable(dev, "pclk");
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	ret = device_reset(dev);
+	if (ret) {
+		dev_err(dev, "failed to reset device\n");
+		return ret;
+	}
+
+	/* Register the peripheral input clock */
+	hw = axg_clk_hw_register_bypass(dev, "audio_pclk",
+					__clk_get_name(clk));
+	if (IS_ERR(hw))
+		return PTR_ERR(hw);
+
+	axg_audio_hw_onecell_data.hws[AUD_CLKID_PCLK] = hw;
+
+	/* Register optional input master clocks */
+	ret = axg_register_clk_hw_inputs(dev, "mst_in",
+					 AXG_MST_IN_COUNT,
+					 AUD_CLKID_MST0);
+	if (ret)
+		return ret;
+
+	/* Register optional input slave sclks */
+	ret = axg_register_clk_hw_inputs(dev, "slv_sclk",
+					 AXG_SLV_SCLK_COUNT,
+					 AUD_CLKID_SLV_SCLK0);
+	if (ret)
+		return ret;
+
+	/* Register optional input slave lrclks */
+	ret = axg_register_clk_hw_inputs(dev, "slv_lrclk",
+					 AXG_SLV_LRCLK_COUNT,
+					 AUD_CLKID_SLV_LRCLK0);
+	if (ret)
+		return ret;
+
+	/* Populate regmap for the regmap backed clocks */
+	for (i = 0; i < ARRAY_SIZE(axg_audio_clk_regmaps); i++)
+		axg_audio_clk_regmaps[i]->map = map;
+
+	/* Take care to skip the registered input clocks */
+	for (i = AUD_CLKID_DDR_ARB; i < axg_audio_hw_onecell_data.num; i++) {
+		hw = axg_audio_hw_onecell_data.hws[i];
+		/* array might be sparse */
+		if (!hw)
+			continue;
+
+		ret = devm_clk_hw_register(dev, hw);
+		if (ret) {
+			dev_err(dev, "failed to register clock %s\n",
+				hw->init->name);
+			return ret;
+		}
+	}
+
+	return devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get,
+					   &axg_audio_hw_onecell_data);
+}
+
+static const struct of_device_id clkc_match_table[] = {
+	{ .compatible = "amlogic,axg-audio-clkc" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, clkc_match_table);
+
+static struct platform_driver axg_audio_driver = {
+	.probe		= axg_audio_clkc_probe,
+	.driver		= {
+		.name	= "axg-audio-clkc",
+		.of_match_table = clkc_match_table,
+	},
+};
+module_platform_driver(axg_audio_driver);
+
+MODULE_DESCRIPTION("Amlogic A113x Audio Clock driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/meson/axg-audio.h b/drivers/clk/meson/axg-audio.h
new file mode 100644
index 000000000000..7191b39c9d65
--- /dev/null
+++ b/drivers/clk/meson/axg-audio.h
@@ -0,0 +1,127 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * Copyright (c) 2018 BayLibre, SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ */
+
+#ifndef __AXG_AUDIO_CLKC_H
+#define __AXG_AUDIO_CLKC_H
+
+/*
+ * Audio Clock  register offsets
+ *
+ * Register offsets from the datasheet must be multiplied by 4 before
+ * to get the right offset
+ */
+#define AUDIO_CLK_GATE_EN	0x000
+#define AUDIO_MCLK_A_CTRL	0x004
+#define AUDIO_MCLK_B_CTRL	0x008
+#define AUDIO_MCLK_C_CTRL	0x00C
+#define AUDIO_MCLK_D_CTRL	0x010
+#define AUDIO_MCLK_E_CTRL	0x014
+#define AUDIO_MCLK_F_CTRL	0x018
+#define AUDIO_MST_A_SCLK_CTRL0	0x040
+#define AUDIO_MST_A_SCLK_CTRL1	0x044
+#define AUDIO_MST_B_SCLK_CTRL0	0x048
+#define AUDIO_MST_B_SCLK_CTRL1	0x04C
+#define AUDIO_MST_C_SCLK_CTRL0	0x050
+#define AUDIO_MST_C_SCLK_CTRL1	0x054
+#define AUDIO_MST_D_SCLK_CTRL0	0x058
+#define AUDIO_MST_D_SCLK_CTRL1	0x05C
+#define AUDIO_MST_E_SCLK_CTRL0	0x060
+#define AUDIO_MST_E_SCLK_CTRL1	0x064
+#define AUDIO_MST_F_SCLK_CTRL0	0x068
+#define AUDIO_MST_F_SCLK_CTRL1	0x06C
+#define AUDIO_CLK_TDMIN_A_CTRL	0x080
+#define AUDIO_CLK_TDMIN_B_CTRL	0x084
+#define AUDIO_CLK_TDMIN_C_CTRL	0x088
+#define AUDIO_CLK_TDMIN_LB_CTRL 0x08C
+#define AUDIO_CLK_TDMOUT_A_CTRL 0x090
+#define AUDIO_CLK_TDMOUT_B_CTRL 0x094
+#define AUDIO_CLK_TDMOUT_C_CTRL 0x098
+#define AUDIO_CLK_SPDIFIN_CTRL	0x09C
+#define AUDIO_CLK_SPDIFOUT_CTRL 0x0A0
+#define AUDIO_CLK_RESAMPLE_CTRL 0x0A4
+#define AUDIO_CLK_LOCKER_CTRL	0x0A8
+#define AUDIO_CLK_PDMIN_CTRL0	0x0AC
+#define AUDIO_CLK_PDMIN_CTRL1	0x0B0
+
+/*
+ * CLKID index values
+ * These indices are entirely contrived and do not map onto the hardware.
+ */
+
+#define AUD_CLKID_PCLK			0
+#define AUD_CLKID_MST0			1
+#define AUD_CLKID_MST1			2
+#define AUD_CLKID_MST2			3
+#define AUD_CLKID_MST3			4
+#define AUD_CLKID_MST4			5
+#define AUD_CLKID_MST5			6
+#define AUD_CLKID_MST6			7
+#define AUD_CLKID_MST7			8
+#define AUD_CLKID_MST_A_MCLK_SEL	59
+#define AUD_CLKID_MST_B_MCLK_SEL	60
+#define AUD_CLKID_MST_C_MCLK_SEL	61
+#define AUD_CLKID_MST_D_MCLK_SEL	62
+#define AUD_CLKID_MST_E_MCLK_SEL	63
+#define AUD_CLKID_MST_F_MCLK_SEL	64
+#define AUD_CLKID_MST_A_MCLK_DIV	65
+#define AUD_CLKID_MST_B_MCLK_DIV	66
+#define AUD_CLKID_MST_C_MCLK_DIV	67
+#define AUD_CLKID_MST_D_MCLK_DIV	68
+#define AUD_CLKID_MST_E_MCLK_DIV	69
+#define AUD_CLKID_MST_F_MCLK_DIV	70
+#define AUD_CLKID_SPDIFOUT_CLK_SEL	71
+#define AUD_CLKID_SPDIFOUT_CLK_DIV	72
+#define AUD_CLKID_SPDIFIN_CLK_SEL	73
+#define AUD_CLKID_SPDIFIN_CLK_DIV	74
+#define AUD_CLKID_PDM_DCLK_SEL		75
+#define AUD_CLKID_PDM_DCLK_DIV		76
+#define AUD_CLKID_PDM_SYSCLK_SEL	77
+#define AUD_CLKID_PDM_SYSCLK_DIV	78
+#define AUD_CLKID_MST_A_SCLK_PRE_EN	92
+#define AUD_CLKID_MST_B_SCLK_PRE_EN	93
+#define AUD_CLKID_MST_C_SCLK_PRE_EN	94
+#define AUD_CLKID_MST_D_SCLK_PRE_EN	95
+#define AUD_CLKID_MST_E_SCLK_PRE_EN	96
+#define AUD_CLKID_MST_F_SCLK_PRE_EN	97
+#define AUD_CLKID_MST_A_SCLK_DIV	98
+#define AUD_CLKID_MST_B_SCLK_DIV	99
+#define AUD_CLKID_MST_C_SCLK_DIV	100
+#define AUD_CLKID_MST_D_SCLK_DIV	101
+#define AUD_CLKID_MST_E_SCLK_DIV	102
+#define AUD_CLKID_MST_F_SCLK_DIV	103
+#define AUD_CLKID_MST_A_SCLK_POST_EN	104
+#define AUD_CLKID_MST_B_SCLK_POST_EN	105
+#define AUD_CLKID_MST_C_SCLK_POST_EN	106
+#define AUD_CLKID_MST_D_SCLK_POST_EN	107
+#define AUD_CLKID_MST_E_SCLK_POST_EN	108
+#define AUD_CLKID_MST_F_SCLK_POST_EN	109
+#define AUD_CLKID_MST_A_LRCLK_DIV	110
+#define AUD_CLKID_MST_B_LRCLK_DIV	111
+#define AUD_CLKID_MST_C_LRCLK_DIV	112
+#define AUD_CLKID_MST_D_LRCLK_DIV	113
+#define AUD_CLKID_MST_E_LRCLK_DIV	114
+#define AUD_CLKID_MST_F_LRCLK_DIV	115
+#define AUD_CLKID_TDMIN_A_SCLK_PRE_EN	137
+#define AUD_CLKID_TDMIN_B_SCLK_PRE_EN	138
+#define AUD_CLKID_TDMIN_C_SCLK_PRE_EN	139
+#define AUD_CLKID_TDMIN_LB_SCLK_PRE_EN	140
+#define AUD_CLKID_TDMOUT_A_SCLK_PRE_EN	141
+#define AUD_CLKID_TDMOUT_B_SCLK_PRE_EN	142
+#define AUD_CLKID_TDMOUT_C_SCLK_PRE_EN	143
+#define AUD_CLKID_TDMIN_A_SCLK_POST_EN	144
+#define AUD_CLKID_TDMIN_B_SCLK_POST_EN	145
+#define AUD_CLKID_TDMIN_C_SCLK_POST_EN	146
+#define AUD_CLKID_TDMIN_LB_SCLK_POST_EN	147
+#define AUD_CLKID_TDMOUT_A_SCLK_POST_EN	148
+#define AUD_CLKID_TDMOUT_B_SCLK_POST_EN	149
+#define AUD_CLKID_TDMOUT_C_SCLK_POST_EN	150
+
+/* include the CLKIDs which are part of the DT bindings */
+#include <dt-bindings/clock/axg-audio-clkc.h>
+
+#define NR_CLKS	151
+
+#endif /*__AXG_AUDIO_CLKC_H */
diff --git a/drivers/clk/meson/axg.c b/drivers/clk/meson/axg.c
index bd4dbc696b88..00ce62ad6416 100644
--- a/drivers/clk/meson/axg.c
+++ b/drivers/clk/meson/axg.c
@@ -12,7 +12,6 @@
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/init.h>
-#include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/mfd/syscon.h>
 #include <linux/platform_device.h>
@@ -626,6 +625,137 @@ static struct clk_regmap axg_mpll3 = {
 	},
 };
 
+static const struct pll_rate_table axg_pcie_pll_rate_table[] = {
+	{
+		.rate	= 100000000,
+		.m	= 200,
+		.n	= 3,
+		.od	= 1,
+		.od2	= 3,
+	},
+	{ /* sentinel */ },
+};
+
+static const struct reg_sequence axg_pcie_init_regs[] = {
+	{ .reg = HHI_PCIE_PLL_CNTL,	.def = 0x400106c8 },
+	{ .reg = HHI_PCIE_PLL_CNTL1,	.def = 0x0084a2aa },
+	{ .reg = HHI_PCIE_PLL_CNTL2,	.def = 0xb75020be },
+	{ .reg = HHI_PCIE_PLL_CNTL3,	.def = 0x0a47488e },
+	{ .reg = HHI_PCIE_PLL_CNTL4,	.def = 0xc000004d },
+	{ .reg = HHI_PCIE_PLL_CNTL5,	.def = 0x00078000 },
+	{ .reg = HHI_PCIE_PLL_CNTL6,	.def = 0x002323c6 },
+};
+
+static struct clk_regmap axg_pcie_pll = {
+	.data = &(struct meson_clk_pll_data){
+		.m = {
+			.reg_off = HHI_PCIE_PLL_CNTL,
+			.shift   = 0,
+			.width   = 9,
+		},
+		.n = {
+			.reg_off = HHI_PCIE_PLL_CNTL,
+			.shift   = 9,
+			.width   = 5,
+		},
+		.od = {
+			.reg_off = HHI_PCIE_PLL_CNTL,
+			.shift   = 16,
+			.width   = 2,
+		},
+		.od2 = {
+			.reg_off = HHI_PCIE_PLL_CNTL6,
+			.shift   = 6,
+			.width   = 2,
+		},
+		.frac = {
+			.reg_off = HHI_PCIE_PLL_CNTL1,
+			.shift   = 0,
+			.width   = 12,
+		},
+		.l = {
+			.reg_off = HHI_PCIE_PLL_CNTL,
+			.shift   = 31,
+			.width   = 1,
+		},
+		.rst = {
+			.reg_off = HHI_PCIE_PLL_CNTL,
+			.shift   = 29,
+			.width   = 1,
+		},
+		.table = axg_pcie_pll_rate_table,
+		.init_regs = axg_pcie_init_regs,
+		.init_count = ARRAY_SIZE(axg_pcie_init_regs),
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "pcie_pll",
+		.ops = &meson_clk_pll_ops,
+		.parent_names = (const char *[]){ "xtal" },
+		.num_parents = 1,
+	},
+};
+
+static struct clk_regmap axg_pcie_mux = {
+	.data = &(struct clk_regmap_mux_data){
+		.offset = HHI_PCIE_PLL_CNTL6,
+		.mask = 0x1,
+		.shift = 2,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "pcie_mux",
+		.ops = &clk_regmap_mux_ops,
+		.parent_names = (const char *[]){ "mpll3", "pcie_pll" },
+		.num_parents = 2,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_regmap axg_pcie_ref = {
+	.data = &(struct clk_regmap_mux_data){
+		.offset = HHI_PCIE_PLL_CNTL6,
+		.mask = 0x1,
+		.shift = 1,
+		/* skip the parent 0, reserved for debug */
+		.table = (u32[]){ 1 },
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "pcie_ref",
+		.ops = &clk_regmap_mux_ops,
+		.parent_names = (const char *[]){ "pcie_mux" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_regmap axg_pcie_cml_en0 = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_PCIE_PLL_CNTL6,
+		.bit_idx = 4,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "pcie_cml_en0",
+		.ops = &clk_regmap_gate_ops,
+		.parent_names = (const char *[]){ "pcie_ref" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+
+	},
+};
+
+static struct clk_regmap axg_pcie_cml_en1 = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_PCIE_PLL_CNTL6,
+		.bit_idx = 3,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "pcie_cml_en1",
+		.ops = &clk_regmap_gate_ops,
+		.parent_names = (const char *[]){ "pcie_ref" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
 static u32 mux_table_clk81[]	= { 0, 2, 3, 4, 5, 6, 7 };
 static const char * const clk81_parent_names[] = {
 	"xtal", "fclk_div7", "mpll1", "mpll2", "fclk_div4",
@@ -779,6 +909,63 @@ static struct clk_regmap axg_sd_emmc_c_clk0 = {
 	},
 };
 
+static u32 mux_table_gen_clk[]	= { 0, 4, 5, 6, 7, 8,
+				    9, 10, 11, 13, 14, };
+static const char * const gen_clk_parent_names[] = {
+	"xtal", "hifi_pll", "mpll0", "mpll1", "mpll2", "mpll3",
+	"fclk_div4", "fclk_div3", "fclk_div5", "fclk_div7", "gp0_pll",
+};
+
+static struct clk_regmap axg_gen_clk_sel = {
+	.data = &(struct clk_regmap_mux_data){
+		.offset = HHI_GEN_CLK_CNTL,
+		.mask = 0xf,
+		.shift = 12,
+		.table = mux_table_gen_clk,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "gen_clk_sel",
+		.ops = &clk_regmap_mux_ops,
+		/*
+		 * bits 15:12 selects from 14 possible parents:
+		 * xtal, [rtc_oscin_i], [sys_cpu_div16], [ddr_dpll_pt],
+		 * hifi_pll, mpll0, mpll1, mpll2, mpll3, fdiv4,
+		 * fdiv3, fdiv5, [cts_msr_clk], fdiv7, gp0_pll
+		 */
+		.parent_names = gen_clk_parent_names,
+		.num_parents = ARRAY_SIZE(gen_clk_parent_names),
+	},
+};
+
+static struct clk_regmap axg_gen_clk_div = {
+	.data = &(struct clk_regmap_div_data){
+		.offset = HHI_GEN_CLK_CNTL,
+		.shift = 0,
+		.width = 11,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "gen_clk_div",
+		.ops = &clk_regmap_divider_ops,
+		.parent_names = (const char *[]){ "gen_clk_sel" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_regmap axg_gen_clk = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_GEN_CLK_CNTL,
+		.bit_idx = 7,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "gen_clk",
+		.ops = &clk_regmap_gate_ops,
+		.parent_names = (const char *[]){ "gen_clk_div" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
 /* Everything Else (EE) domain gates */
 static MESON_GATE(axg_ddr, HHI_GCLK_MPEG0, 0);
 static MESON_GATE(axg_audio_locker, HHI_GCLK_MPEG0, 2);
@@ -821,6 +1008,7 @@ static MESON_GATE(axg_mmc_pclk, HHI_GCLK_MPEG2, 11);
 static MESON_GATE(axg_vpu_intr, HHI_GCLK_MPEG2, 25);
 static MESON_GATE(axg_sec_ahb_ahb3_bridge, HHI_GCLK_MPEG2, 26);
 static MESON_GATE(axg_gic, HHI_GCLK_MPEG2, 30);
+static MESON_GATE(axg_mipi_enable, HHI_MIPI_CNTL0, 29);
 
 /* Always On (AO) domain gates */
 
@@ -910,6 +1098,15 @@ static struct clk_hw_onecell_data axg_hw_onecell_data = {
 		[CLKID_FCLK_DIV4_DIV]		= &axg_fclk_div4_div.hw,
 		[CLKID_FCLK_DIV5_DIV]		= &axg_fclk_div5_div.hw,
 		[CLKID_FCLK_DIV7_DIV]		= &axg_fclk_div7_div.hw,
+		[CLKID_PCIE_PLL]		= &axg_pcie_pll.hw,
+		[CLKID_PCIE_MUX]		= &axg_pcie_mux.hw,
+		[CLKID_PCIE_REF]		= &axg_pcie_ref.hw,
+		[CLKID_PCIE_CML_EN0]		= &axg_pcie_cml_en0.hw,
+		[CLKID_PCIE_CML_EN1]		= &axg_pcie_cml_en1.hw,
+		[CLKID_MIPI_ENABLE]		= &axg_mipi_enable.hw,
+		[CLKID_GEN_CLK_SEL]		= &axg_gen_clk_sel.hw,
+		[CLKID_GEN_CLK_DIV]		= &axg_gen_clk_div.hw,
+		[CLKID_GEN_CLK]			= &axg_gen_clk.hw,
 		[NR_CLKS]			= NULL,
 	},
 	.num = NR_CLKS,
@@ -988,6 +1185,15 @@ static struct clk_regmap *const axg_clk_regmaps[] = {
 	&axg_fclk_div4,
 	&axg_fclk_div5,
 	&axg_fclk_div7,
+	&axg_pcie_pll,
+	&axg_pcie_mux,
+	&axg_pcie_ref,
+	&axg_pcie_cml_en0,
+	&axg_pcie_cml_en1,
+	&axg_mipi_enable,
+	&axg_gen_clk_sel,
+	&axg_gen_clk_div,
+	&axg_gen_clk,
 };
 
 static const struct of_device_id clkc_match_table[] = {
@@ -995,49 +1201,17 @@ static const struct of_device_id clkc_match_table[] = {
 	{}
 };
 
-static const struct regmap_config clkc_regmap_config = {
-	.reg_bits       = 32,
-	.val_bits       = 32,
-	.reg_stride     = 4,
-};
-
 static int axg_clkc_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct resource *res;
-	void __iomem *clk_base = NULL;
 	struct regmap *map;
 	int ret, i;
 
 	/* Get the hhi system controller node if available */
 	map = syscon_node_to_regmap(of_get_parent(dev->of_node));
 	if (IS_ERR(map)) {
-		dev_err(dev,
-			"failed to get HHI regmap - Trying obsolete regs\n");
-
-		/*
-		 * FIXME: HHI registers should be accessed through
-		 * the appropriate system controller. This is required because
-		 * there is more than just clocks in this register space
-		 *
-		 * This fallback method is only provided temporarily until
-		 * all the platform DTs are properly using the syscon node
-		 */
-		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-		if (!res)
-			return -EINVAL;
-
-
-		clk_base = devm_ioremap(dev, res->start, resource_size(res));
-		if (!clk_base) {
-			dev_err(dev, "Unable to map clk base\n");
-			return -ENXIO;
-		}
-
-		map = devm_regmap_init_mmio(dev, clk_base,
-					    &clkc_regmap_config);
-		if (IS_ERR(map))
-			return PTR_ERR(map);
+		dev_err(dev, "failed to get HHI regmap\n");
+		return PTR_ERR(map);
 	}
 
 	/* Populate regmap for the regmap backed clocks */
diff --git a/drivers/clk/meson/axg.h b/drivers/clk/meson/axg.h
index b421df6a7ea0..1d04144a1b2c 100644
--- a/drivers/clk/meson/axg.h
+++ b/drivers/clk/meson/axg.h
@@ -16,6 +16,7 @@
  * Register offsets from the data sheet must be multiplied by 4 before
  * adding them to the base address to get the right value.
  */
+#define HHI_MIPI_CNTL0			0x00
 #define HHI_GP0_PLL_CNTL		0x40
 #define HHI_GP0_PLL_CNTL2		0x44
 #define HHI_GP0_PLL_CNTL3		0x48
@@ -127,8 +128,13 @@
 #define CLKID_FCLK_DIV4_DIV			73
 #define CLKID_FCLK_DIV5_DIV			74
 #define CLKID_FCLK_DIV7_DIV			75
+#define CLKID_PCIE_PLL				76
+#define CLKID_PCIE_MUX				77
+#define CLKID_PCIE_REF				78
+#define CLKID_GEN_CLK_SEL			82
+#define CLKID_GEN_CLK_DIV			83
 
-#define NR_CLKS					76
+#define NR_CLKS					85
 
 /* include the CLKIDs that have been made part of the DT binding */
 #include <dt-bindings/clock/axg-clkc.h>
diff --git a/drivers/clk/meson/clk-audio-divider.c b/drivers/clk/meson/clk-audio-divider.c
deleted file mode 100644
index e4cf96ba704e..000000000000
--- a/drivers/clk/meson/clk-audio-divider.c
+++ /dev/null
@@ -1,110 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (c) 2017 AmLogic, Inc.
- * Author: Jerome Brunet <jbrunet@baylibre.com>
- */
-
-/*
- * i2s master clock divider: The algorithm of the generic clk-divider used with
- * a very precise clock parent such as the mpll tends to select a low divider
- * factor. This gives poor results with this particular divider, especially with
- * high frequencies (> 100 MHz)
- *
- * This driver try to select the maximum possible divider with the rate the
- * upstream clock can provide.
- */
-
-#include <linux/clk-provider.h>
-#include "clkc.h"
-
-static inline struct meson_clk_audio_div_data *
-meson_clk_audio_div_data(struct clk_regmap *clk)
-{
-	return (struct meson_clk_audio_div_data *)clk->data;
-}
-
-static int _div_round(unsigned long parent_rate, unsigned long rate,
-		      unsigned long flags)
-{
-	if (flags & CLK_DIVIDER_ROUND_CLOSEST)
-		return DIV_ROUND_CLOSEST_ULL((u64)parent_rate, rate);
-
-	return DIV_ROUND_UP_ULL((u64)parent_rate, rate);
-}
-
-static int _get_val(unsigned long parent_rate, unsigned long rate)
-{
-	return DIV_ROUND_UP_ULL((u64)parent_rate, rate) - 1;
-}
-
-static int _valid_divider(unsigned int width, int divider)
-{
-	int max_divider = 1 << width;
-
-	return clamp(divider, 1, max_divider);
-}
-
-static unsigned long audio_divider_recalc_rate(struct clk_hw *hw,
-					       unsigned long parent_rate)
-{
-	struct clk_regmap *clk = to_clk_regmap(hw);
-	struct meson_clk_audio_div_data *adiv = meson_clk_audio_div_data(clk);
-	unsigned long divider;
-
-	divider = meson_parm_read(clk->map, &adiv->div) + 1;
-
-	return DIV_ROUND_UP_ULL((u64)parent_rate, divider);
-}
-
-static long audio_divider_round_rate(struct clk_hw *hw,
-				     unsigned long rate,
-				     unsigned long *parent_rate)
-{
-	struct clk_regmap *clk = to_clk_regmap(hw);
-	struct meson_clk_audio_div_data *adiv = meson_clk_audio_div_data(clk);
-	unsigned long max_prate;
-	int divider;
-
-	if (!(clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT)) {
-		divider = _div_round(*parent_rate, rate, adiv->flags);
-		divider = _valid_divider(adiv->div.width, divider);
-		return DIV_ROUND_UP_ULL((u64)*parent_rate, divider);
-	}
-
-	/* Get the maximum parent rate */
-	max_prate = clk_hw_round_rate(clk_hw_get_parent(hw), ULONG_MAX);
-
-	/* Get the corresponding rounded down divider */
-	divider = max_prate / rate;
-	divider = _valid_divider(adiv->div.width, divider);
-
-	/* Get actual rate of the parent */
-	*parent_rate = clk_hw_round_rate(clk_hw_get_parent(hw),
-					 divider * rate);
-
-	return DIV_ROUND_UP_ULL((u64)*parent_rate, divider);
-}
-
-static int audio_divider_set_rate(struct clk_hw *hw,
-				  unsigned long rate,
-				  unsigned long parent_rate)
-{
-	struct clk_regmap *clk = to_clk_regmap(hw);
-	struct meson_clk_audio_div_data *adiv = meson_clk_audio_div_data(clk);
-	int val = _get_val(parent_rate, rate);
-
-	meson_parm_write(clk->map, &adiv->div, val);
-
-	return 0;
-}
-
-const struct clk_ops meson_clk_audio_divider_ro_ops = {
-	.recalc_rate	= audio_divider_recalc_rate,
-	.round_rate	= audio_divider_round_rate,
-};
-
-const struct clk_ops meson_clk_audio_divider_ops = {
-	.recalc_rate	= audio_divider_recalc_rate,
-	.round_rate	= audio_divider_round_rate,
-	.set_rate	= audio_divider_set_rate,
-};
diff --git a/drivers/clk/meson/clk-phase.c b/drivers/clk/meson/clk-phase.c
new file mode 100644
index 000000000000..cba43748ce3d
--- /dev/null
+++ b/drivers/clk/meson/clk-phase.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2018 BayLibre, SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ */
+
+#include <linux/clk-provider.h>
+#include "clkc.h"
+
+#define phase_step(_width) (360 / (1 << (_width)))
+
+static inline struct meson_clk_phase_data *
+meson_clk_phase_data(struct clk_regmap *clk)
+{
+	return (struct meson_clk_phase_data *)clk->data;
+}
+
+int meson_clk_degrees_from_val(unsigned int val, unsigned int width)
+{
+	return phase_step(width) * val;
+}
+EXPORT_SYMBOL_GPL(meson_clk_degrees_from_val);
+
+unsigned int meson_clk_degrees_to_val(int degrees, unsigned int width)
+{
+	unsigned int val = DIV_ROUND_CLOSEST(degrees, phase_step(width));
+
+	/*
+	 * This last calculation is here for cases when degrees is rounded
+	 * to 360, in which case val == (1 << width).
+	 */
+	return val % (1 << width);
+}
+EXPORT_SYMBOL_GPL(meson_clk_degrees_to_val);
+
+static int meson_clk_phase_get_phase(struct clk_hw *hw)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_clk_phase_data *phase = meson_clk_phase_data(clk);
+	unsigned int val;
+
+	val = meson_parm_read(clk->map, &phase->ph);
+
+	return meson_clk_degrees_from_val(val, phase->ph.width);
+}
+
+static int meson_clk_phase_set_phase(struct clk_hw *hw, int degrees)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_clk_phase_data *phase = meson_clk_phase_data(clk);
+	unsigned int val;
+
+	val = meson_clk_degrees_to_val(degrees, phase->ph.width);
+	meson_parm_write(clk->map, &phase->ph, val);
+
+	return 0;
+}
+
+const struct clk_ops meson_clk_phase_ops = {
+	.get_phase	= meson_clk_phase_get_phase,
+	.set_phase	= meson_clk_phase_set_phase,
+};
+EXPORT_SYMBOL_GPL(meson_clk_phase_ops);
diff --git a/drivers/clk/meson/clk-triphase.c b/drivers/clk/meson/clk-triphase.c
new file mode 100644
index 000000000000..4a59936251e5
--- /dev/null
+++ b/drivers/clk/meson/clk-triphase.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2018 BayLibre, SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ */
+
+#include <linux/clk-provider.h>
+#include "clkc-audio.h"
+
+/*
+ * This is a special clock for the audio controller.
+ * The phase of mst_sclk clock output can be controlled independently
+ * for the outside world (ph0), the tdmout (ph1) and tdmin (ph2).
+ * Controlling these 3 phases as just one makes things simpler and
+ * give the same clock view to all the element on the i2s bus.
+ * If necessary, we can still control the phase in the tdm block
+ * which makes these independent control redundant.
+ */
+static inline struct meson_clk_triphase_data *
+meson_clk_triphase_data(struct clk_regmap *clk)
+{
+	return (struct meson_clk_triphase_data *)clk->data;
+}
+
+static void meson_clk_triphase_sync(struct clk_hw *hw)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_clk_triphase_data *tph = meson_clk_triphase_data(clk);
+	unsigned int val;
+
+	/* Get phase 0 and sync it to phase 1 and 2 */
+	val = meson_parm_read(clk->map, &tph->ph0);
+	meson_parm_write(clk->map, &tph->ph1, val);
+	meson_parm_write(clk->map, &tph->ph2, val);
+}
+
+static int meson_clk_triphase_get_phase(struct clk_hw *hw)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_clk_triphase_data *tph = meson_clk_triphase_data(clk);
+	unsigned int val;
+
+	/* Phase are in sync, reading phase 0 is enough */
+	val = meson_parm_read(clk->map, &tph->ph0);
+
+	return meson_clk_degrees_from_val(val, tph->ph0.width);
+}
+
+static int meson_clk_triphase_set_phase(struct clk_hw *hw, int degrees)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_clk_triphase_data *tph = meson_clk_triphase_data(clk);
+	unsigned int val;
+
+	val = meson_clk_degrees_to_val(degrees, tph->ph0.width);
+	meson_parm_write(clk->map, &tph->ph0, val);
+	meson_parm_write(clk->map, &tph->ph1, val);
+	meson_parm_write(clk->map, &tph->ph2, val);
+
+	return 0;
+}
+
+const struct clk_ops meson_clk_triphase_ops = {
+	.init		= meson_clk_triphase_sync,
+	.get_phase	= meson_clk_triphase_get_phase,
+	.set_phase	= meson_clk_triphase_set_phase,
+};
+EXPORT_SYMBOL_GPL(meson_clk_triphase_ops);
diff --git a/drivers/clk/meson/clkc-audio.h b/drivers/clk/meson/clkc-audio.h
new file mode 100644
index 000000000000..0a7c157ebf81
--- /dev/null
+++ b/drivers/clk/meson/clkc-audio.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2018 BayLibre, SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ */
+
+#ifndef __MESON_CLKC_AUDIO_H
+#define __MESON_CLKC_AUDIO_H
+
+#include "clkc.h"
+
+struct meson_clk_triphase_data {
+	struct parm ph0;
+	struct parm ph1;
+	struct parm ph2;
+};
+
+struct meson_sclk_div_data {
+	struct parm div;
+	struct parm hi;
+	unsigned int cached_div;
+	struct clk_duty cached_duty;
+};
+
+extern const struct clk_ops meson_clk_triphase_ops;
+extern const struct clk_ops meson_sclk_div_ops;
+
+#endif /* __MESON_CLKC_AUDIO_H */
diff --git a/drivers/clk/meson/clkc.h b/drivers/clk/meson/clkc.h
index 2fb084330ee9..24cec16b6038 100644
--- a/drivers/clk/meson/clkc.h
+++ b/drivers/clk/meson/clkc.h
@@ -91,11 +91,13 @@ struct meson_clk_mpll_data {
 
 #define CLK_MESON_MPLL_ROUND_CLOSEST	BIT(0)
 
-struct meson_clk_audio_div_data {
-	struct parm div;
-	u8 flags;
+struct meson_clk_phase_data {
+	struct parm ph;
 };
 
+int meson_clk_degrees_from_val(unsigned int val, unsigned int width);
+unsigned int meson_clk_degrees_to_val(int degrees, unsigned int width);
+
 #define MESON_GATE(_name, _reg, _bit)					\
 struct clk_regmap _name = {						\
 	.data = &(struct clk_regmap_gate_data){				\
@@ -117,7 +119,6 @@ extern const struct clk_ops meson_clk_pll_ops;
 extern const struct clk_ops meson_clk_cpu_ops;
 extern const struct clk_ops meson_clk_mpll_ro_ops;
 extern const struct clk_ops meson_clk_mpll_ops;
-extern const struct clk_ops meson_clk_audio_divider_ro_ops;
-extern const struct clk_ops meson_clk_audio_divider_ops;
+extern const struct clk_ops meson_clk_phase_ops;
 
 #endif /* __CLKC_H */
diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c
index 177fffb9ebef..86d3ae58e84c 100644
--- a/drivers/clk/meson/gxbb.c
+++ b/drivers/clk/meson/gxbb.c
@@ -7,7 +7,6 @@
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/init.h>
-#include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/mfd/syscon.h>
 #include <linux/platform_device.h>
@@ -971,28 +970,26 @@ static struct clk_regmap gxbb_cts_amclk_sel = {
 		.mask = 0x3,
 		.shift = 9,
 		.table = (u32[]){ 1, 2, 3 },
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cts_amclk_sel",
 		.ops = &clk_regmap_mux_ops,
 		.parent_names = (const char *[]){ "mpll0", "mpll1", "mpll2" },
 		.num_parents = 3,
-		.flags = CLK_SET_RATE_PARENT,
 	},
 };
 
 static struct clk_regmap gxbb_cts_amclk_div = {
-	.data = &(struct meson_clk_audio_div_data){
-		.div = {
-			.reg_off = HHI_AUD_CLK_CNTL,
-			.shift   = 0,
-			.width   = 8,
-		},
+	.data = &(struct clk_regmap_div_data) {
+		.offset = HHI_AUD_CLK_CNTL,
+		.shift = 0,
+		.width = 8,
 		.flags = CLK_DIVIDER_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cts_amclk_div",
-		.ops = &meson_clk_audio_divider_ops,
+		.ops = &clk_regmap_divider_ops,
 		.parent_names = (const char *[]){ "cts_amclk_sel" },
 		.num_parents = 1,
 		.flags = CLK_SET_RATE_PARENT,
@@ -1019,13 +1016,13 @@ static struct clk_regmap gxbb_cts_mclk_i958_sel = {
 		.mask = 0x3,
 		.shift = 25,
 		.table = (u32[]){ 1, 2, 3 },
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data) {
 		.name = "cts_mclk_i958_sel",
 		.ops = &clk_regmap_mux_ops,
 		.parent_names = (const char *[]){ "mpll0", "mpll1", "mpll2" },
 		.num_parents = 3,
-		.flags = CLK_SET_RATE_PARENT,
 	},
 };
 
@@ -1627,6 +1624,63 @@ static struct clk_regmap gxbb_vdec_hevc = {
 	},
 };
 
+static u32 mux_table_gen_clk[]	= { 0, 4, 5, 6, 7, 8,
+				    9, 10, 11, 13, 14, };
+static const char * const gen_clk_parent_names[] = {
+	"xtal", "vdec_1", "vdec_hevc", "mpll0", "mpll1", "mpll2",
+	"fclk_div4", "fclk_div3", "fclk_div5", "fclk_div7", "gp0_pll",
+};
+
+static struct clk_regmap gxbb_gen_clk_sel = {
+	.data = &(struct clk_regmap_mux_data){
+		.offset = HHI_GEN_CLK_CNTL,
+		.mask = 0xf,
+		.shift = 12,
+		.table = mux_table_gen_clk,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "gen_clk_sel",
+		.ops = &clk_regmap_mux_ops,
+		/*
+		 * bits 15:12 selects from 14 possible parents:
+		 * xtal, [rtc_oscin_i], [sys_cpu_div16], [ddr_dpll_pt],
+		 * vid_pll, vid2_pll (hevc), mpll0, mpll1, mpll2, fdiv4,
+		 * fdiv3, fdiv5, [cts_msr_clk], fdiv7, gp0_pll
+		 */
+		.parent_names = gen_clk_parent_names,
+		.num_parents = ARRAY_SIZE(gen_clk_parent_names),
+	},
+};
+
+static struct clk_regmap gxbb_gen_clk_div = {
+	.data = &(struct clk_regmap_div_data){
+		.offset = HHI_GEN_CLK_CNTL,
+		.shift = 0,
+		.width = 11,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "gen_clk_div",
+		.ops = &clk_regmap_divider_ops,
+		.parent_names = (const char *[]){ "gen_clk_sel" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_regmap gxbb_gen_clk = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_GEN_CLK_CNTL,
+		.bit_idx = 7,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "gen_clk",
+		.ops = &clk_regmap_gate_ops,
+		.parent_names = (const char *[]){ "gen_clk_div" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
 /* Everything Else (EE) domain gates */
 static MESON_GATE(gxbb_ddr, HHI_GCLK_MPEG0, 0);
 static MESON_GATE(gxbb_dos, HHI_GCLK_MPEG0, 1);
@@ -1876,6 +1930,9 @@ static struct clk_hw_onecell_data gxbb_hw_onecell_data = {
 		[CLKID_VDEC_HEVC_SEL]	    = &gxbb_vdec_hevc_sel.hw,
 		[CLKID_VDEC_HEVC_DIV]	    = &gxbb_vdec_hevc_div.hw,
 		[CLKID_VDEC_HEVC]	    = &gxbb_vdec_hevc.hw,
+		[CLKID_GEN_CLK_SEL]	    = &gxbb_gen_clk_sel.hw,
+		[CLKID_GEN_CLK_DIV]	    = &gxbb_gen_clk_div.hw,
+		[CLKID_GEN_CLK]		    = &gxbb_gen_clk.hw,
 		[NR_CLKS]		    = NULL,
 	},
 	.num = NR_CLKS,
@@ -2038,6 +2095,9 @@ static struct clk_hw_onecell_data gxl_hw_onecell_data = {
 		[CLKID_VDEC_HEVC_SEL]	    = &gxbb_vdec_hevc_sel.hw,
 		[CLKID_VDEC_HEVC_DIV]	    = &gxbb_vdec_hevc_div.hw,
 		[CLKID_VDEC_HEVC]	    = &gxbb_vdec_hevc.hw,
+		[CLKID_GEN_CLK_SEL]	    = &gxbb_gen_clk_sel.hw,
+		[CLKID_GEN_CLK_DIV]	    = &gxbb_gen_clk_div.hw,
+		[CLKID_GEN_CLK]		    = &gxbb_gen_clk.hw,
 		[NR_CLKS]		    = NULL,
 	},
 	.num = NR_CLKS,
@@ -2202,6 +2262,9 @@ static struct clk_regmap *const gx_clk_regmaps[] = {
 	&gxbb_vdec_hevc_sel,
 	&gxbb_vdec_hevc_div,
 	&gxbb_vdec_hevc,
+	&gxbb_gen_clk_sel,
+	&gxbb_gen_clk_div,
+	&gxbb_gen_clk,
 };
 
 struct clkc_data {
@@ -2228,17 +2291,9 @@ static const struct of_device_id clkc_match_table[] = {
 	{},
 };
 
-static const struct regmap_config clkc_regmap_config = {
-	.reg_bits       = 32,
-	.val_bits       = 32,
-	.reg_stride     = 4,
-};
-
 static int gxbb_clkc_probe(struct platform_device *pdev)
 {
 	const struct clkc_data *clkc_data;
-	struct resource *res;
-	void __iomem *clk_base;
 	struct regmap *map;
 	int ret, i;
 	struct device *dev = &pdev->dev;
@@ -2250,31 +2305,8 @@ static int gxbb_clkc_probe(struct platform_device *pdev)
 	/* Get the hhi system controller node if available */
 	map = syscon_node_to_regmap(of_get_parent(dev->of_node));
 	if (IS_ERR(map)) {
-		dev_err(dev,
-			"failed to get HHI regmap - Trying obsolete regs\n");
-
-		/*
-		 * FIXME: HHI registers should be accessed through
-		 * the appropriate system controller. This is required because
-		 * there is more than just clocks in this register space
-		 *
-		 * This fallback method is only provided temporarily until
-		 * all the platform DTs are properly using the syscon node
-		 */
-		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-		if (!res)
-			return -EINVAL;
-
-		clk_base = devm_ioremap(dev, res->start, resource_size(res));
-		if (!clk_base) {
-			dev_err(dev, "Unable to map clk base\n");
-			return -ENXIO;
-		}
-
-		map = devm_regmap_init_mmio(dev, clk_base,
-					    &clkc_regmap_config);
-		if (IS_ERR(map))
-			return PTR_ERR(map);
+		dev_err(dev, "failed to get HHI regmap\n");
+		return PTR_ERR(map);
 	}
 
 	/* Populate regmap for the common regmap backed clocks */
diff --git a/drivers/clk/meson/gxbb.h b/drivers/clk/meson/gxbb.h
index ec1a812bf1fd..20dfb1daf5b8 100644
--- a/drivers/clk/meson/gxbb.h
+++ b/drivers/clk/meson/gxbb.h
@@ -66,7 +66,6 @@
 #define HHI_USB_CLK_CNTL		0x220 /* 0x88 offset in data sheet */
 #define HHI_32K_CLK_CNTL		0x224 /* 0x89 offset in data sheet */
 #define HHI_GEN_CLK_CNTL		0x228 /* 0x8a offset in data sheet */
-#define HHI_GEN_CLK_CNTL		0x228 /* 0x8a offset in data sheet */
 
 #define HHI_PCM_CLK_CNTL		0x258 /* 0x96 offset in data sheet */
 #define HHI_NAND_CLK_CNTL		0x25C /* 0x97 offset in data sheet */
@@ -158,8 +157,10 @@
 #define CLKID_VDEC_1_DIV	  152
 #define CLKID_VDEC_HEVC_SEL	  154
 #define CLKID_VDEC_HEVC_DIV	  155
+#define CLKID_GEN_CLK_SEL	  157
+#define CLKID_GEN_CLK_DIV	  158
 
-#define NR_CLKS			  157
+#define NR_CLKS			  160
 
 /* include the CLKIDs that have been made part of the DT binding */
 #include <dt-bindings/clock/gxbb-clkc.h>
diff --git a/drivers/clk/meson/sclk-div.c b/drivers/clk/meson/sclk-div.c
new file mode 100644
index 000000000000..bc64019b8eeb
--- /dev/null
+++ b/drivers/clk/meson/sclk-div.c
@@ -0,0 +1,243 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2018 BayLibre, SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ *
+ * Sample clock generator divider:
+ * This HW divider gates with value 0 but is otherwise a zero based divider:
+ *
+ * val >= 1
+ * divider = val + 1
+ *
+ * The duty cycle may also be set for the LR clock variant. The duty cycle
+ * ratio is:
+ *
+ * hi = [0 - val]
+ * duty_cycle = (1 + hi) / (1 + val)
+ */
+
+#include "clkc-audio.h"
+
+static inline struct meson_sclk_div_data *
+meson_sclk_div_data(struct clk_regmap *clk)
+{
+	return (struct meson_sclk_div_data *)clk->data;
+}
+
+static int sclk_div_maxval(struct meson_sclk_div_data *sclk)
+{
+	return (1 << sclk->div.width) - 1;
+}
+
+static int sclk_div_maxdiv(struct meson_sclk_div_data *sclk)
+{
+	return sclk_div_maxval(sclk) + 1;
+}
+
+static int sclk_div_getdiv(struct clk_hw *hw, unsigned long rate,
+			   unsigned long prate, int maxdiv)
+{
+	int div = DIV_ROUND_CLOSEST_ULL((u64)prate, rate);
+
+	return clamp(div, 2, maxdiv);
+}
+
+static int sclk_div_bestdiv(struct clk_hw *hw, unsigned long rate,
+			    unsigned long *prate,
+			    struct meson_sclk_div_data *sclk)
+{
+	struct clk_hw *parent = clk_hw_get_parent(hw);
+	int bestdiv = 0, i;
+	unsigned long maxdiv, now, parent_now;
+	unsigned long best = 0, best_parent = 0;
+
+	if (!rate)
+		rate = 1;
+
+	maxdiv = sclk_div_maxdiv(sclk);
+
+	if (!(clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT))
+		return sclk_div_getdiv(hw, rate, *prate, maxdiv);
+
+	/*
+	 * The maximum divider we can use without overflowing
+	 * unsigned long in rate * i below
+	 */
+	maxdiv = min(ULONG_MAX / rate, maxdiv);
+
+	for (i = 2; i <= maxdiv; i++) {
+		/*
+		 * It's the most ideal case if the requested rate can be
+		 * divided from parent clock without needing to change
+		 * parent rate, so return the divider immediately.
+		 */
+		if (rate * i == *prate)
+			return i;
+
+		parent_now = clk_hw_round_rate(parent, rate * i);
+		now = DIV_ROUND_UP_ULL((u64)parent_now, i);
+
+		if (abs(rate - now) < abs(rate - best)) {
+			bestdiv = i;
+			best = now;
+			best_parent = parent_now;
+		}
+	}
+
+	if (!bestdiv)
+		bestdiv = sclk_div_maxdiv(sclk);
+	else
+		*prate = best_parent;
+
+	return bestdiv;
+}
+
+static long sclk_div_round_rate(struct clk_hw *hw, unsigned long rate,
+				unsigned long *prate)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_sclk_div_data *sclk = meson_sclk_div_data(clk);
+	int div;
+
+	div = sclk_div_bestdiv(hw, rate, prate, sclk);
+
+	return DIV_ROUND_UP_ULL((u64)*prate, div);
+}
+
+static void sclk_apply_ratio(struct clk_regmap *clk,
+			     struct meson_sclk_div_data *sclk)
+{
+	unsigned int hi = DIV_ROUND_CLOSEST(sclk->cached_div *
+					    sclk->cached_duty.num,
+					    sclk->cached_duty.den);
+
+	if (hi)
+		hi -= 1;
+
+	meson_parm_write(clk->map, &sclk->hi, hi);
+}
+
+static int sclk_div_set_duty_cycle(struct clk_hw *hw,
+				   struct clk_duty *duty)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_sclk_div_data *sclk = meson_sclk_div_data(clk);
+
+	if (MESON_PARM_APPLICABLE(&sclk->hi)) {
+		memcpy(&sclk->cached_duty, duty, sizeof(*duty));
+		sclk_apply_ratio(clk, sclk);
+	}
+
+	return 0;
+}
+
+static int sclk_div_get_duty_cycle(struct clk_hw *hw,
+				   struct clk_duty *duty)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_sclk_div_data *sclk = meson_sclk_div_data(clk);
+	int hi;
+
+	if (!MESON_PARM_APPLICABLE(&sclk->hi)) {
+		duty->num = 1;
+		duty->den = 2;
+		return 0;
+	}
+
+	hi = meson_parm_read(clk->map, &sclk->hi);
+	duty->num = hi + 1;
+	duty->den = sclk->cached_div;
+	return 0;
+}
+
+static void sclk_apply_divider(struct clk_regmap *clk,
+			       struct meson_sclk_div_data *sclk)
+{
+	if (MESON_PARM_APPLICABLE(&sclk->hi))
+		sclk_apply_ratio(clk, sclk);
+
+	meson_parm_write(clk->map, &sclk->div, sclk->cached_div - 1);
+}
+
+static int sclk_div_set_rate(struct clk_hw *hw, unsigned long rate,
+			     unsigned long prate)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_sclk_div_data *sclk = meson_sclk_div_data(clk);
+	unsigned long maxdiv = sclk_div_maxdiv(sclk);
+
+	sclk->cached_div = sclk_div_getdiv(hw, rate, prate, maxdiv);
+
+	if (clk_hw_is_enabled(hw))
+		sclk_apply_divider(clk, sclk);
+
+	return 0;
+}
+
+static unsigned long sclk_div_recalc_rate(struct clk_hw *hw,
+					  unsigned long prate)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_sclk_div_data *sclk = meson_sclk_div_data(clk);
+
+	return DIV_ROUND_UP_ULL((u64)prate, sclk->cached_div);
+}
+
+static int sclk_div_enable(struct clk_hw *hw)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_sclk_div_data *sclk = meson_sclk_div_data(clk);
+
+	sclk_apply_divider(clk, sclk);
+
+	return 0;
+}
+
+static void sclk_div_disable(struct clk_hw *hw)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_sclk_div_data *sclk = meson_sclk_div_data(clk);
+
+	meson_parm_write(clk->map, &sclk->div, 0);
+}
+
+static int sclk_div_is_enabled(struct clk_hw *hw)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_sclk_div_data *sclk = meson_sclk_div_data(clk);
+
+	if (meson_parm_read(clk->map, &sclk->div))
+		return 1;
+
+	return 0;
+}
+
+static void sclk_div_init(struct clk_hw *hw)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_sclk_div_data *sclk = meson_sclk_div_data(clk);
+	unsigned int val;
+
+	val = meson_parm_read(clk->map, &sclk->div);
+
+	/* if the divider is initially disabled, assume max */
+	if (!val)
+		sclk->cached_div = sclk_div_maxdiv(sclk);
+	else
+		sclk->cached_div = val + 1;
+
+	sclk_div_get_duty_cycle(hw, &sclk->cached_duty);
+}
+
+const struct clk_ops meson_sclk_div_ops = {
+	.recalc_rate	= sclk_div_recalc_rate,
+	.round_rate	= sclk_div_round_rate,
+	.set_rate	= sclk_div_set_rate,
+	.enable		= sclk_div_enable,
+	.disable	= sclk_div_disable,
+	.is_enabled	= sclk_div_is_enabled,
+	.get_duty_cycle	= sclk_div_get_duty_cycle,
+	.set_duty_cycle = sclk_div_set_duty_cycle,
+	.init		= sclk_div_init,
+};
+EXPORT_SYMBOL_GPL(meson_sclk_div_ops);
diff --git a/drivers/clk/mvebu/armada-37xx-periph.c b/drivers/clk/mvebu/armada-37xx-periph.c
index 44e4e27eddad..499f5962c8b0 100644
--- a/drivers/clk/mvebu/armada-37xx-periph.c
+++ b/drivers/clk/mvebu/armada-37xx-periph.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Marvell Armada 37xx SoC Peripheral clocks
  *
@@ -5,10 +6,6 @@
  *
  * Gregory CLEMENT <gregory.clement@free-electrons.com>
  *
- * This file is licensed under the terms of the GNU General Public
- * License version 2 or later. This program is licensed "as is"
- * without any warranty of any kind, whether express or implied.
- *
  * Most of the peripheral clocks can be modelled like this:
  *             _____    _______    _______
  * TBG-A-P  --|     |  |       |  |       |   ______
@@ -419,7 +416,6 @@ static unsigned int armada_3700_pm_dvfs_get_cpu_parent(struct regmap *base)
 static u8 clk_pm_cpu_get_parent(struct clk_hw *hw)
 {
 	struct clk_pm_cpu *pm_cpu = to_clk_pm_cpu(hw);
-	int num_parents = clk_hw_get_num_parents(hw);
 	u32 val;
 
 	if (armada_3700_pm_dvfs_is_enabled(pm_cpu->nb_pm_base)) {
@@ -429,9 +425,6 @@ static u8 clk_pm_cpu_get_parent(struct clk_hw *hw)
 		val &= pm_cpu->mask_mux;
 	}
 
-	if (val >= num_parents)
-		return -EINVAL;
-
 	return val;
 }
 
diff --git a/drivers/clk/pxa/clk-pxa25x.c b/drivers/clk/pxa/clk-pxa25x.c
index 6416c1f8e632..e88f8e01fe3a 100644
--- a/drivers/clk/pxa/clk-pxa25x.c
+++ b/drivers/clk/pxa/clk-pxa25x.c
@@ -292,8 +292,10 @@ static void __init pxa25x_register_plls(void)
 {
 	clk_register_fixed_rate(NULL, "osc_3_6864mhz", NULL,
 				CLK_GET_RATE_NOCACHE, 3686400);
-	clk_register_fixed_rate(NULL, "osc_32_768khz", NULL,
-				CLK_GET_RATE_NOCACHE, 32768);
+	clkdev_pxa_register(CLK_OSC32k768, "osc_32_768khz", NULL,
+			    clk_register_fixed_rate(NULL, "osc_32_768khz", NULL,
+						    CLK_GET_RATE_NOCACHE,
+						    32768));
 	clk_register_fixed_rate(NULL, "clk_dummy", NULL, 0, 0);
 	clk_register_fixed_factor(NULL, "ppll_95_85mhz", "osc_3_6864mhz",
 				  0, 26, 1);
diff --git a/drivers/clk/pxa/clk-pxa27x.c b/drivers/clk/pxa/clk-pxa27x.c
index 25a30194d27a..d40b63e7bbce 100644
--- a/drivers/clk/pxa/clk-pxa27x.c
+++ b/drivers/clk/pxa/clk-pxa27x.c
@@ -314,9 +314,10 @@ static void __init pxa27x_register_plls(void)
 	clk_register_fixed_rate(NULL, "osc_13mhz", NULL,
 				CLK_GET_RATE_NOCACHE,
 				13 * MHz);
-	clk_register_fixed_rate(NULL, "osc_32_768khz", NULL,
-				CLK_GET_RATE_NOCACHE,
-				32768 * KHz);
+	clkdev_pxa_register(CLK_OSC32k768, "osc_32_768khz", NULL,
+			    clk_register_fixed_rate(NULL, "osc_32_768khz", NULL,
+						    CLK_GET_RATE_NOCACHE,
+						    32768 * KHz));
 	clk_register_fixed_rate(NULL, "clk_dummy", NULL, 0, 0);
 	clk_register_fixed_factor(NULL, "ppll_312mhz", "osc_13mhz", 0, 24, 1);
 }
diff --git a/drivers/clk/pxa/clk-pxa3xx.c b/drivers/clk/pxa/clk-pxa3xx.c
index 2d126df2bccd..7aa120c3bd08 100644
--- a/drivers/clk/pxa/clk-pxa3xx.c
+++ b/drivers/clk/pxa/clk-pxa3xx.c
@@ -286,9 +286,10 @@ static void __init pxa3xx_register_plls(void)
 	clk_register_fixed_rate(NULL, "osc_13mhz", NULL,
 				CLK_GET_RATE_NOCACHE,
 				13 * MHz);
-	clk_register_fixed_rate(NULL, "osc_32_768khz", NULL,
-				CLK_GET_RATE_NOCACHE,
-				32768);
+	clkdev_pxa_register(CLK_OSC32k768, "osc_32_768khz", NULL,
+			    clk_register_fixed_rate(NULL, "osc_32_768khz", NULL,
+						    CLK_GET_RATE_NOCACHE,
+						    32768));
 	clk_register_fixed_rate(NULL, "ring_osc_120mhz", NULL,
 				CLK_GET_RATE_NOCACHE,
 				120 * MHz);
diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig
index 9c3480dcc38a..064768699fe7 100644
--- a/drivers/clk/qcom/Kconfig
+++ b/drivers/clk/qcom/Kconfig
@@ -59,6 +59,15 @@ config QCOM_CLK_SMD_RPM
 	  Say Y if you want to support the clocks exposed by the RPM on
 	  platforms such as apq8016, apq8084, msm8974 etc.
 
+config QCOM_CLK_RPMH
+	tristate "RPMh Clock Driver"
+	depends on COMMON_CLK_QCOM && QCOM_RPMH
+	help
+	 RPMh manages shared resources on some Qualcomm Technologies, Inc.
+	 SoCs. It accepts requests from other hardware subsystems via RSC.
+	 Say Y if you want to support the clocks exposed by RPMh on
+	 platforms such as SDM845.
+
 config APQ_GCC_8084
 	tristate "APQ8084 Global Clock Controller"
 	select QCOM_GDSC
@@ -245,6 +254,16 @@ config SDM_VIDEOCC_845
 	  Say Y if you want to support video devices and functionality such as
 	  video encode and decode.
 
+config SDM_DISPCC_845
+	tristate "SDM845 Display Clock Controller"
+	select SDM_GCC_845
+	depends on COMMON_CLK_QCOM
+	help
+	  Support for the display clock controller on Qualcomm Technologies, Inc
+	  SDM845 devices.
+	  Say Y if you want to support display devices and functionality such as
+	  splash screen.
+
 config SPMI_PMIC_CLKDIV
 	tristate "SPMI PMIC clkdiv Support"
 	depends on (COMMON_CLK_QCOM && SPMI) || COMPILE_TEST
diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile
index 762c01137c2f..21a45035930d 100644
--- a/drivers/clk/qcom/Makefile
+++ b/drivers/clk/qcom/Makefile
@@ -37,7 +37,9 @@ obj-$(CONFIG_MSM_MMCC_8996) += mmcc-msm8996.o
 obj-$(CONFIG_QCOM_A53PLL) += a53-pll.o
 obj-$(CONFIG_QCOM_CLK_APCS_MSM8916) += apcs-msm8916.o
 obj-$(CONFIG_QCOM_CLK_RPM) += clk-rpm.o
+obj-$(CONFIG_QCOM_CLK_RPMH) += clk-rpmh.o
 obj-$(CONFIG_QCOM_CLK_SMD_RPM) += clk-smd-rpm.o
+obj-$(CONFIG_SDM_DISPCC_845) += dispcc-sdm845.o
 obj-$(CONFIG_SDM_GCC_845) += gcc-sdm845.o
 obj-$(CONFIG_SDM_VIDEOCC_845) += videocc-sdm845.o
 obj-$(CONFIG_SPMI_PMIC_CLKDIV) += clk-spmi-pmic-div.o
diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c
index 3c49a60072f1..a91d97cecbad 100644
--- a/drivers/clk/qcom/clk-alpha-pll.c
+++ b/drivers/clk/qcom/clk-alpha-pll.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2015, 2018, The Linux Foundation. All rights reserved.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/clk/qcom/clk-alpha-pll.h b/drivers/clk/qcom/clk-alpha-pll.h
index f981b486c468..66755f0f84fc 100644
--- a/drivers/clk/qcom/clk-alpha-pll.h
+++ b/drivers/clk/qcom/clk-alpha-pll.h
@@ -1,15 +1,5 @@
-/*
- * Copyright (c) 2015, 2018, The Linux Foundation. All rights reserved.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2015, 2018, The Linux Foundation. All rights reserved. */
 
 #ifndef __QCOM_CLK_ALPHA_PLL_H__
 #define __QCOM_CLK_ALPHA_PLL_H__
diff --git a/drivers/clk/qcom/clk-branch.c b/drivers/clk/qcom/clk-branch.c
index c58c5538b1b6..bc2205c450b6 100644
--- a/drivers/clk/qcom/clk-branch.c
+++ b/drivers/clk/qcom/clk-branch.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2013, The Linux Foundation. All rights reserved.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/clk/qcom/clk-branch.h b/drivers/clk/qcom/clk-branch.h
index 1702efb1c511..b3561e0a3984 100644
--- a/drivers/clk/qcom/clk-branch.h
+++ b/drivers/clk/qcom/clk-branch.h
@@ -1,15 +1,5 @@
-/*
- * Copyright (c) 2013, The Linux Foundation. All rights reserved.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2013, The Linux Foundation. All rights reserved. */
 
 #ifndef __QCOM_CLK_BRANCH_H__
 #define __QCOM_CLK_BRANCH_H__
diff --git a/drivers/clk/qcom/clk-rcg.h b/drivers/clk/qcom/clk-rcg.h
index b209a2fe86b9..dbd5a9e83554 100644
--- a/drivers/clk/qcom/clk-rcg.h
+++ b/drivers/clk/qcom/clk-rcg.h
@@ -7,6 +7,8 @@
 #include <linux/clk-provider.h>
 #include "clk-regmap.h"
 
+#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
+
 struct freq_tbl {
 	unsigned long freq;
 	u8 src;
diff --git a/drivers/clk/qcom/clk-regmap.c b/drivers/clk/qcom/clk-regmap.c
index 1c856d330733..ce80db27ccf2 100644
--- a/drivers/clk/qcom/clk-regmap.c
+++ b/drivers/clk/qcom/clk-regmap.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2014, The Linux Foundation. All rights reserved.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/device.h>
diff --git a/drivers/clk/qcom/clk-regmap.h b/drivers/clk/qcom/clk-regmap.h
index 90d95cd11ec6..6cfc1bccb255 100644
--- a/drivers/clk/qcom/clk-regmap.h
+++ b/drivers/clk/qcom/clk-regmap.h
@@ -1,15 +1,5 @@
-/*
- * Copyright (c) 2014, The Linux Foundation. All rights reserved.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2014, The Linux Foundation. All rights reserved. */
 
 #ifndef __QCOM_CLK_REGMAP_H__
 #define __QCOM_CLK_REGMAP_H__
diff --git a/drivers/clk/qcom/clk-rpmh.c b/drivers/clk/qcom/clk-rpmh.c
new file mode 100644
index 000000000000..9f4fc7773fb2
--- /dev/null
+++ b/drivers/clk/qcom/clk-rpmh.c
@@ -0,0 +1,329 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <soc/qcom/cmd-db.h>
+#include <soc/qcom/rpmh.h>
+
+#include <dt-bindings/clock/qcom,rpmh.h>
+
+#define CLK_RPMH_ARC_EN_OFFSET		0
+#define CLK_RPMH_VRM_EN_OFFSET		4
+
+/**
+ * struct clk_rpmh - individual rpmh clock data structure
+ * @hw:			handle between common and hardware-specific interfaces
+ * @res_name:		resource name for the rpmh clock
+ * @div:		clock divider to compute the clock rate
+ * @res_addr:		base address of the rpmh resource within the RPMh
+ * @res_on_val:		rpmh clock enable value
+ * @state:		rpmh clock requested state
+ * @aggr_state:		rpmh clock aggregated state
+ * @last_sent_aggr_state: rpmh clock last aggr state sent to RPMh
+ * @valid_state_mask:	mask to determine the state of the rpmh clock
+ * @dev:		device to which it is attached
+ * @peer:		pointer to the clock rpmh sibling
+ */
+struct clk_rpmh {
+	struct clk_hw hw;
+	const char *res_name;
+	u8 div;
+	u32 res_addr;
+	u32 res_on_val;
+	u32 state;
+	u32 aggr_state;
+	u32 last_sent_aggr_state;
+	u32 valid_state_mask;
+	struct device *dev;
+	struct clk_rpmh *peer;
+};
+
+struct clk_rpmh_desc {
+	struct clk_hw **clks;
+	size_t num_clks;
+};
+
+static DEFINE_MUTEX(rpmh_clk_lock);
+
+#define __DEFINE_CLK_RPMH(_platform, _name, _name_active, _res_name,	\
+			  _res_en_offset, _res_on, _div)		\
+	static struct clk_rpmh _platform##_##_name_active;		\
+	static struct clk_rpmh _platform##_##_name = {			\
+		.res_name = _res_name,					\
+		.res_addr = _res_en_offset,				\
+		.res_on_val = _res_on,					\
+		.div = _div,						\
+		.peer = &_platform##_##_name_active,			\
+		.valid_state_mask = (BIT(RPMH_WAKE_ONLY_STATE) |	\
+				      BIT(RPMH_ACTIVE_ONLY_STATE) |	\
+				      BIT(RPMH_SLEEP_STATE)),		\
+		.hw.init = &(struct clk_init_data){			\
+			.ops = &clk_rpmh_ops,				\
+			.name = #_name,					\
+			.parent_names = (const char *[]){ "xo_board" },	\
+			.num_parents = 1,				\
+		},							\
+	};								\
+	static struct clk_rpmh _platform##_##_name_active = {		\
+		.res_name = _res_name,					\
+		.res_addr = _res_en_offset,				\
+		.res_on_val = _res_on,					\
+		.div = _div,						\
+		.peer = &_platform##_##_name,				\
+		.valid_state_mask = (BIT(RPMH_WAKE_ONLY_STATE) |	\
+					BIT(RPMH_ACTIVE_ONLY_STATE)),	\
+		.hw.init = &(struct clk_init_data){			\
+			.ops = &clk_rpmh_ops,				\
+			.name = #_name_active,				\
+			.parent_names = (const char *[]){ "xo_board" },	\
+			.num_parents = 1,				\
+		},							\
+	}
+
+#define DEFINE_CLK_RPMH_ARC(_platform, _name, _name_active, _res_name,	\
+			    _res_on, _div)				\
+	__DEFINE_CLK_RPMH(_platform, _name, _name_active, _res_name,	\
+			  CLK_RPMH_ARC_EN_OFFSET, _res_on, _div)
+
+#define DEFINE_CLK_RPMH_VRM(_platform, _name, _name_active, _res_name,	\
+				_div)					\
+	__DEFINE_CLK_RPMH(_platform, _name, _name_active, _res_name,	\
+			  CLK_RPMH_VRM_EN_OFFSET, 1, _div)
+
+static inline struct clk_rpmh *to_clk_rpmh(struct clk_hw *_hw)
+{
+	return container_of(_hw, struct clk_rpmh, hw);
+}
+
+static inline bool has_state_changed(struct clk_rpmh *c, u32 state)
+{
+	return (c->last_sent_aggr_state & BIT(state))
+		!= (c->aggr_state & BIT(state));
+}
+
+static int clk_rpmh_send_aggregate_command(struct clk_rpmh *c)
+{
+	struct tcs_cmd cmd = { 0 };
+	u32 cmd_state, on_val;
+	enum rpmh_state state = RPMH_SLEEP_STATE;
+	int ret;
+
+	cmd.addr = c->res_addr;
+	cmd_state = c->aggr_state;
+	on_val = c->res_on_val;
+
+	for (; state <= RPMH_ACTIVE_ONLY_STATE; state++) {
+		if (has_state_changed(c, state)) {
+			if (cmd_state & BIT(state))
+				cmd.data = on_val;
+
+			ret = rpmh_write_async(c->dev, state, &cmd, 1);
+			if (ret) {
+				dev_err(c->dev, "set %s state of %s failed: (%d)\n",
+					!state ? "sleep" :
+					state == RPMH_WAKE_ONLY_STATE	?
+					"wake" : "active", c->res_name, ret);
+				return ret;
+			}
+		}
+	}
+
+	c->last_sent_aggr_state = c->aggr_state;
+	c->peer->last_sent_aggr_state =  c->last_sent_aggr_state;
+
+	return 0;
+}
+
+/*
+ * Update state and aggregate state values based on enable value.
+ */
+static int clk_rpmh_aggregate_state_send_command(struct clk_rpmh *c,
+						bool enable)
+{
+	int ret;
+
+	/* Nothing required to be done if already off or on */
+	if (enable == c->state)
+		return 0;
+
+	c->state = enable ? c->valid_state_mask : 0;
+	c->aggr_state = c->state | c->peer->state;
+	c->peer->aggr_state = c->aggr_state;
+
+	ret = clk_rpmh_send_aggregate_command(c);
+	if (!ret)
+		return 0;
+
+	if (ret && enable)
+		c->state = 0;
+	else if (ret)
+		c->state = c->valid_state_mask;
+
+	WARN(1, "clk: %s failed to %s\n", c->res_name,
+	     enable ? "enable" : "disable");
+	return ret;
+}
+
+static int clk_rpmh_prepare(struct clk_hw *hw)
+{
+	struct clk_rpmh *c = to_clk_rpmh(hw);
+	int ret = 0;
+
+	mutex_lock(&rpmh_clk_lock);
+	ret = clk_rpmh_aggregate_state_send_command(c, true);
+	mutex_unlock(&rpmh_clk_lock);
+
+	return ret;
+};
+
+static void clk_rpmh_unprepare(struct clk_hw *hw)
+{
+	struct clk_rpmh *c = to_clk_rpmh(hw);
+
+	mutex_lock(&rpmh_clk_lock);
+	clk_rpmh_aggregate_state_send_command(c, false);
+	mutex_unlock(&rpmh_clk_lock);
+};
+
+static unsigned long clk_rpmh_recalc_rate(struct clk_hw *hw,
+					unsigned long prate)
+{
+	struct clk_rpmh *r = to_clk_rpmh(hw);
+
+	/*
+	 * RPMh clocks have a fixed rate. Return static rate.
+	 */
+	return prate / r->div;
+}
+
+static const struct clk_ops clk_rpmh_ops = {
+	.prepare	= clk_rpmh_prepare,
+	.unprepare	= clk_rpmh_unprepare,
+	.recalc_rate	= clk_rpmh_recalc_rate,
+};
+
+/* Resource name must match resource id present in cmd-db. */
+DEFINE_CLK_RPMH_ARC(sdm845, bi_tcxo, bi_tcxo_ao, "xo.lvl", 0x3, 2);
+DEFINE_CLK_RPMH_VRM(sdm845, ln_bb_clk2, ln_bb_clk2_ao, "lnbclka2", 2);
+DEFINE_CLK_RPMH_VRM(sdm845, ln_bb_clk3, ln_bb_clk3_ao, "lnbclka3", 2);
+DEFINE_CLK_RPMH_VRM(sdm845, rf_clk1, rf_clk1_ao, "rfclka1", 1);
+DEFINE_CLK_RPMH_VRM(sdm845, rf_clk2, rf_clk2_ao, "rfclka2", 1);
+DEFINE_CLK_RPMH_VRM(sdm845, rf_clk3, rf_clk3_ao, "rfclka3", 1);
+
+static struct clk_hw *sdm845_rpmh_clocks[] = {
+	[RPMH_CXO_CLK]		= &sdm845_bi_tcxo.hw,
+	[RPMH_CXO_CLK_A]	= &sdm845_bi_tcxo_ao.hw,
+	[RPMH_LN_BB_CLK2]	= &sdm845_ln_bb_clk2.hw,
+	[RPMH_LN_BB_CLK2_A]	= &sdm845_ln_bb_clk2_ao.hw,
+	[RPMH_LN_BB_CLK3]	= &sdm845_ln_bb_clk3.hw,
+	[RPMH_LN_BB_CLK3_A]	= &sdm845_ln_bb_clk3_ao.hw,
+	[RPMH_RF_CLK1]		= &sdm845_rf_clk1.hw,
+	[RPMH_RF_CLK1_A]	= &sdm845_rf_clk1_ao.hw,
+	[RPMH_RF_CLK2]		= &sdm845_rf_clk2.hw,
+	[RPMH_RF_CLK2_A]	= &sdm845_rf_clk2_ao.hw,
+	[RPMH_RF_CLK3]		= &sdm845_rf_clk3.hw,
+	[RPMH_RF_CLK3_A]	= &sdm845_rf_clk3_ao.hw,
+};
+
+static const struct clk_rpmh_desc clk_rpmh_sdm845 = {
+	.clks = sdm845_rpmh_clocks,
+	.num_clks = ARRAY_SIZE(sdm845_rpmh_clocks),
+};
+
+static struct clk_hw *of_clk_rpmh_hw_get(struct of_phandle_args *clkspec,
+					 void *data)
+{
+	struct clk_rpmh_desc *rpmh = data;
+	unsigned int idx = clkspec->args[0];
+
+	if (idx >= rpmh->num_clks) {
+		pr_err("%s: invalid index %u\n", __func__, idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return rpmh->clks[idx];
+}
+
+static int clk_rpmh_probe(struct platform_device *pdev)
+{
+	struct clk_hw **hw_clks;
+	struct clk_rpmh *rpmh_clk;
+	const struct clk_rpmh_desc *desc;
+	int ret, i;
+
+	desc = of_device_get_match_data(&pdev->dev);
+	if (!desc)
+		return -ENODEV;
+
+	hw_clks = desc->clks;
+
+	for (i = 0; i < desc->num_clks; i++) {
+		u32 res_addr;
+
+		rpmh_clk = to_clk_rpmh(hw_clks[i]);
+		res_addr = cmd_db_read_addr(rpmh_clk->res_name);
+		if (!res_addr) {
+			dev_err(&pdev->dev, "missing RPMh resource address for %s\n",
+				rpmh_clk->res_name);
+			return -ENODEV;
+		}
+		rpmh_clk->res_addr += res_addr;
+		rpmh_clk->dev = &pdev->dev;
+
+		ret = devm_clk_hw_register(&pdev->dev, hw_clks[i]);
+		if (ret) {
+			dev_err(&pdev->dev, "failed to register %s\n",
+				hw_clks[i]->init->name);
+			return ret;
+		}
+	}
+
+	/* typecast to silence compiler warning */
+	ret = devm_of_clk_add_hw_provider(&pdev->dev, of_clk_rpmh_hw_get,
+					  (void *)desc);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to add clock provider\n");
+		return ret;
+	}
+
+	dev_dbg(&pdev->dev, "Registered RPMh clocks\n");
+
+	return 0;
+}
+
+static const struct of_device_id clk_rpmh_match_table[] = {
+	{ .compatible = "qcom,sdm845-rpmh-clk", .data = &clk_rpmh_sdm845},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, clk_rpmh_match_table);
+
+static struct platform_driver clk_rpmh_driver = {
+	.probe		= clk_rpmh_probe,
+	.driver		= {
+		.name	= "clk-rpmh",
+		.of_match_table = clk_rpmh_match_table,
+	},
+};
+
+static int __init clk_rpmh_init(void)
+{
+	return platform_driver_register(&clk_rpmh_driver);
+}
+subsys_initcall(clk_rpmh_init);
+
+static void __exit clk_rpmh_exit(void)
+{
+	platform_driver_unregister(&clk_rpmh_driver);
+}
+module_exit(clk_rpmh_exit);
+
+MODULE_DESCRIPTION("QCOM RPMh Clock Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/qcom/common.c b/drivers/clk/qcom/common.c
index 39ce64c2783b..db9b2471ac40 100644
--- a/drivers/clk/qcom/common.c
+++ b/drivers/clk/qcom/common.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2013-2014, The Linux Foundation. All rights reserved.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/export.h>
diff --git a/drivers/clk/qcom/common.h b/drivers/clk/qcom/common.h
index 00196ee15e73..4aa33ee70bae 100644
--- a/drivers/clk/qcom/common.h
+++ b/drivers/clk/qcom/common.h
@@ -1,15 +1,6 @@
-/*
- * Copyright (c) 2014, The Linux Foundation. All rights reserved.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2014, The Linux Foundation. All rights reserved. */
+
 #ifndef __QCOM_CLK_COMMON_H__
 #define __QCOM_CLK_COMMON_H__
 
diff --git a/drivers/clk/qcom/dispcc-sdm845.c b/drivers/clk/qcom/dispcc-sdm845.c
new file mode 100644
index 000000000000..0cc4909b5dbe
--- /dev/null
+++ b/drivers/clk/qcom/dispcc-sdm845.c
@@ -0,0 +1,685 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/reset-controller.h>
+
+#include <dt-bindings/clock/qcom,dispcc-sdm845.h>
+
+#include "clk-alpha-pll.h"
+#include "clk-branch.h"
+#include "clk-rcg.h"
+#include "clk-regmap-divider.h"
+#include "common.h"
+#include "gdsc.h"
+#include "reset.h"
+
+enum {
+	P_BI_TCXO,
+	P_CORE_BI_PLL_TEST_SE,
+	P_DISP_CC_PLL0_OUT_MAIN,
+	P_DSI0_PHY_PLL_OUT_BYTECLK,
+	P_DSI0_PHY_PLL_OUT_DSICLK,
+	P_DSI1_PHY_PLL_OUT_BYTECLK,
+	P_DSI1_PHY_PLL_OUT_DSICLK,
+	P_GPLL0_OUT_MAIN,
+	P_GPLL0_OUT_MAIN_DIV,
+};
+
+static const struct parent_map disp_cc_parent_map_0[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_DSI0_PHY_PLL_OUT_BYTECLK, 1 },
+	{ P_DSI1_PHY_PLL_OUT_BYTECLK, 2 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const char * const disp_cc_parent_names_0[] = {
+	"bi_tcxo",
+	"dsi0_phy_pll_out_byteclk",
+	"dsi1_phy_pll_out_byteclk",
+	"core_bi_pll_test_se",
+};
+
+static const struct parent_map disp_cc_parent_map_2[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const char * const disp_cc_parent_names_2[] = {
+	"bi_tcxo",
+	"core_bi_pll_test_se",
+};
+
+static const struct parent_map disp_cc_parent_map_3[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_DISP_CC_PLL0_OUT_MAIN, 1 },
+	{ P_GPLL0_OUT_MAIN, 4 },
+	{ P_GPLL0_OUT_MAIN_DIV, 5 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const char * const disp_cc_parent_names_3[] = {
+	"bi_tcxo",
+	"disp_cc_pll0",
+	"gcc_disp_gpll0_clk_src",
+	"gcc_disp_gpll0_div_clk_src",
+	"core_bi_pll_test_se",
+};
+
+static const struct parent_map disp_cc_parent_map_4[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_DSI0_PHY_PLL_OUT_DSICLK, 1 },
+	{ P_DSI1_PHY_PLL_OUT_DSICLK, 2 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const char * const disp_cc_parent_names_4[] = {
+	"bi_tcxo",
+	"dsi0_phy_pll_out_dsiclk",
+	"dsi1_phy_pll_out_dsiclk",
+	"core_bi_pll_test_se",
+};
+
+static struct clk_alpha_pll disp_cc_pll0 = {
+	.offset = 0x0,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_pll0",
+			.parent_names = (const char *[]){ "bi_tcxo" },
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_fabia_ops,
+		},
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_rcg2 disp_cc_mdss_byte0_clk_src = {
+	.cmd_rcgr = 0x20d0,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_0,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_byte0_clk_src",
+		.parent_names = disp_cc_parent_names_0,
+		.num_parents = 4,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_byte2_ops,
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_rcg2 disp_cc_mdss_byte1_clk_src = {
+	.cmd_rcgr = 0x20ec,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_0,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_byte1_clk_src",
+		.parent_names = disp_cc_parent_names_0,
+		.num_parents = 4,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_byte2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_disp_cc_mdss_esc0_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 disp_cc_mdss_esc0_clk_src = {
+	.cmd_rcgr = 0x2108,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_0,
+	.freq_tbl = ftbl_disp_cc_mdss_esc0_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_esc0_clk_src",
+		.parent_names = disp_cc_parent_names_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 disp_cc_mdss_esc1_clk_src = {
+	.cmd_rcgr = 0x2120,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_0,
+	.freq_tbl = ftbl_disp_cc_mdss_esc0_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_esc1_clk_src",
+		.parent_names = disp_cc_parent_names_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_disp_cc_mdss_mdp_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(85714286, P_GPLL0_OUT_MAIN, 7, 0, 0),
+	F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0),
+	F(150000000, P_GPLL0_OUT_MAIN, 4, 0, 0),
+	F(171428571, P_GPLL0_OUT_MAIN, 3.5, 0, 0),
+	F(200000000, P_GPLL0_OUT_MAIN, 3, 0, 0),
+	F(300000000, P_GPLL0_OUT_MAIN, 2, 0, 0),
+	F(344000000, P_DISP_CC_PLL0_OUT_MAIN, 2.5, 0, 0),
+	F(430000000, P_DISP_CC_PLL0_OUT_MAIN, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 disp_cc_mdss_mdp_clk_src = {
+	.cmd_rcgr = 0x2088,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_3,
+	.freq_tbl = ftbl_disp_cc_mdss_mdp_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_mdp_clk_src",
+		.parent_names = disp_cc_parent_names_3,
+		.num_parents = 5,
+		.ops = &clk_rcg2_shared_ops,
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_rcg2 disp_cc_mdss_pclk0_clk_src = {
+	.cmd_rcgr = 0x2058,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_4,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_pclk0_clk_src",
+		.parent_names = disp_cc_parent_names_4,
+		.num_parents = 4,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_pixel_ops,
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_rcg2 disp_cc_mdss_pclk1_clk_src = {
+	.cmd_rcgr = 0x2070,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_4,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_pclk1_clk_src",
+		.parent_names = disp_cc_parent_names_4,
+		.num_parents = 4,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_pixel_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_disp_cc_mdss_rot_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(171428571, P_GPLL0_OUT_MAIN, 3.5, 0, 0),
+	F(300000000, P_GPLL0_OUT_MAIN, 2, 0, 0),
+	F(344000000, P_DISP_CC_PLL0_OUT_MAIN, 2.5, 0, 0),
+	F(430000000, P_DISP_CC_PLL0_OUT_MAIN, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 disp_cc_mdss_rot_clk_src = {
+	.cmd_rcgr = 0x20a0,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_3,
+	.freq_tbl = ftbl_disp_cc_mdss_rot_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_rot_clk_src",
+		.parent_names = disp_cc_parent_names_3,
+		.num_parents = 5,
+		.ops = &clk_rcg2_shared_ops,
+	},
+};
+
+static struct clk_rcg2 disp_cc_mdss_vsync_clk_src = {
+	.cmd_rcgr = 0x20b8,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_2,
+	.freq_tbl = ftbl_disp_cc_mdss_esc0_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_vsync_clk_src",
+		.parent_names = disp_cc_parent_names_2,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_branch disp_cc_mdss_ahb_clk = {
+	.halt_reg = 0x4004,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x4004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_axi_clk = {
+	.halt_reg = 0x4008,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x4008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_branch disp_cc_mdss_byte0_clk = {
+	.halt_reg = 0x2028,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2028,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_byte0_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_byte0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_regmap_div disp_cc_mdss_byte0_div_clk_src = {
+	.reg = 0x20e8,
+	.shift = 0,
+	.width = 2,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_byte0_div_clk_src",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_byte0_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+		},
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_branch disp_cc_mdss_byte0_intf_clk = {
+	.halt_reg = 0x202c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x202c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_byte0_intf_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_byte0_div_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_branch disp_cc_mdss_byte1_clk = {
+	.halt_reg = 0x2030,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2030,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_byte1_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_byte1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_regmap_div disp_cc_mdss_byte1_div_clk_src = {
+	.reg = 0x2104,
+	.shift = 0,
+	.width = 2,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_byte1_div_clk_src",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_byte1_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+		},
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_branch disp_cc_mdss_byte1_intf_clk = {
+	.halt_reg = 0x2034,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2034,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_byte1_intf_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_byte1_div_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_esc0_clk = {
+	.halt_reg = 0x2038,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2038,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_esc0_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_esc0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_esc1_clk = {
+	.halt_reg = 0x203c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x203c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_esc1_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_esc1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_mdp_clk = {
+	.halt_reg = 0x200c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x200c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_mdp_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_mdp_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_mdp_lut_clk = {
+	.halt_reg = 0x201c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x201c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_mdp_lut_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_mdp_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_branch disp_cc_mdss_pclk0_clk = {
+	.halt_reg = 0x2004,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_pclk0_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_pclk0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_branch disp_cc_mdss_pclk1_clk = {
+	.halt_reg = 0x2008,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_pclk1_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_pclk1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_rot_clk = {
+	.halt_reg = 0x2014,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2014,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_rot_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_rot_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_rscc_ahb_clk = {
+	.halt_reg = 0x5004,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x5004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_rscc_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_rscc_vsync_clk = {
+	.halt_reg = 0x5008,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x5008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_rscc_vsync_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_vsync_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_vsync_clk = {
+	.halt_reg = 0x2024,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2024,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_vsync_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_vsync_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct gdsc mdss_gdsc = {
+	.gdscr = 0x3000,
+	.pd = {
+		.name = "mdss_gdsc",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+	.flags = HW_CTRL | POLL_CFG_GDSCR,
+};
+
+static struct clk_regmap *disp_cc_sdm845_clocks[] = {
+	[DISP_CC_MDSS_AHB_CLK] = &disp_cc_mdss_ahb_clk.clkr,
+	[DISP_CC_MDSS_AXI_CLK] = &disp_cc_mdss_axi_clk.clkr,
+	[DISP_CC_MDSS_BYTE0_CLK] = &disp_cc_mdss_byte0_clk.clkr,
+	[DISP_CC_MDSS_BYTE0_CLK_SRC] = &disp_cc_mdss_byte0_clk_src.clkr,
+	[DISP_CC_MDSS_BYTE0_INTF_CLK] = &disp_cc_mdss_byte0_intf_clk.clkr,
+	[DISP_CC_MDSS_BYTE0_DIV_CLK_SRC] =
+					&disp_cc_mdss_byte0_div_clk_src.clkr,
+	[DISP_CC_MDSS_BYTE1_CLK] = &disp_cc_mdss_byte1_clk.clkr,
+	[DISP_CC_MDSS_BYTE1_CLK_SRC] = &disp_cc_mdss_byte1_clk_src.clkr,
+	[DISP_CC_MDSS_BYTE1_INTF_CLK] = &disp_cc_mdss_byte1_intf_clk.clkr,
+	[DISP_CC_MDSS_BYTE1_DIV_CLK_SRC] =
+					&disp_cc_mdss_byte1_div_clk_src.clkr,
+	[DISP_CC_MDSS_ESC0_CLK] = &disp_cc_mdss_esc0_clk.clkr,
+	[DISP_CC_MDSS_ESC0_CLK_SRC] = &disp_cc_mdss_esc0_clk_src.clkr,
+	[DISP_CC_MDSS_ESC1_CLK] = &disp_cc_mdss_esc1_clk.clkr,
+	[DISP_CC_MDSS_ESC1_CLK_SRC] = &disp_cc_mdss_esc1_clk_src.clkr,
+	[DISP_CC_MDSS_MDP_CLK] = &disp_cc_mdss_mdp_clk.clkr,
+	[DISP_CC_MDSS_MDP_CLK_SRC] = &disp_cc_mdss_mdp_clk_src.clkr,
+	[DISP_CC_MDSS_MDP_LUT_CLK] = &disp_cc_mdss_mdp_lut_clk.clkr,
+	[DISP_CC_MDSS_PCLK0_CLK] = &disp_cc_mdss_pclk0_clk.clkr,
+	[DISP_CC_MDSS_PCLK0_CLK_SRC] = &disp_cc_mdss_pclk0_clk_src.clkr,
+	[DISP_CC_MDSS_PCLK1_CLK] = &disp_cc_mdss_pclk1_clk.clkr,
+	[DISP_CC_MDSS_PCLK1_CLK_SRC] = &disp_cc_mdss_pclk1_clk_src.clkr,
+	[DISP_CC_MDSS_ROT_CLK] = &disp_cc_mdss_rot_clk.clkr,
+	[DISP_CC_MDSS_ROT_CLK_SRC] = &disp_cc_mdss_rot_clk_src.clkr,
+	[DISP_CC_MDSS_RSCC_AHB_CLK] = &disp_cc_mdss_rscc_ahb_clk.clkr,
+	[DISP_CC_MDSS_RSCC_VSYNC_CLK] = &disp_cc_mdss_rscc_vsync_clk.clkr,
+	[DISP_CC_MDSS_VSYNC_CLK] = &disp_cc_mdss_vsync_clk.clkr,
+	[DISP_CC_MDSS_VSYNC_CLK_SRC] = &disp_cc_mdss_vsync_clk_src.clkr,
+	[DISP_CC_PLL0] = &disp_cc_pll0.clkr,
+};
+
+static const struct qcom_reset_map disp_cc_sdm845_resets[] = {
+	[DISP_CC_MDSS_RSCC_BCR] = { 0x5000 },
+};
+
+static struct gdsc *disp_cc_sdm845_gdscs[] = {
+	[MDSS_GDSC] = &mdss_gdsc,
+};
+
+static const struct regmap_config disp_cc_sdm845_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= 0x10000,
+	.fast_io	= true,
+};
+
+static const struct qcom_cc_desc disp_cc_sdm845_desc = {
+	.config = &disp_cc_sdm845_regmap_config,
+	.clks = disp_cc_sdm845_clocks,
+	.num_clks = ARRAY_SIZE(disp_cc_sdm845_clocks),
+	.resets = disp_cc_sdm845_resets,
+	.num_resets = ARRAY_SIZE(disp_cc_sdm845_resets),
+	.gdscs = disp_cc_sdm845_gdscs,
+	.num_gdscs = ARRAY_SIZE(disp_cc_sdm845_gdscs),
+};
+
+static const struct of_device_id disp_cc_sdm845_match_table[] = {
+	{ .compatible = "qcom,sdm845-dispcc" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, disp_cc_sdm845_match_table);
+
+static int disp_cc_sdm845_probe(struct platform_device *pdev)
+{
+	struct regmap *regmap;
+	struct alpha_pll_config disp_cc_pll0_config = {};
+
+	regmap = qcom_cc_map(pdev, &disp_cc_sdm845_desc);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	disp_cc_pll0_config.l = 0x2c;
+	disp_cc_pll0_config.alpha = 0xcaaa;
+
+	clk_fabia_pll_configure(&disp_cc_pll0, regmap, &disp_cc_pll0_config);
+
+	/* Enable hardware clock gating for DSI and MDP clocks */
+	regmap_update_bits(regmap, 0x8000, 0x7f0, 0x7f0);
+
+	return qcom_cc_really_probe(pdev, &disp_cc_sdm845_desc, regmap);
+}
+
+static struct platform_driver disp_cc_sdm845_driver = {
+	.probe		= disp_cc_sdm845_probe,
+	.driver		= {
+		.name	= "disp_cc-sdm845",
+		.of_match_table = disp_cc_sdm845_match_table,
+	},
+};
+
+static int __init disp_cc_sdm845_init(void)
+{
+	return platform_driver_register(&disp_cc_sdm845_driver);
+}
+subsys_initcall(disp_cc_sdm845_init);
+
+static void __exit disp_cc_sdm845_exit(void)
+{
+	platform_driver_unregister(&disp_cc_sdm845_driver);
+}
+module_exit(disp_cc_sdm845_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("QTI DISPCC SDM845 Driver");
diff --git a/drivers/clk/qcom/gcc-apq8084.c b/drivers/clk/qcom/gcc-apq8084.c
index 486d9610355c..9c99a71ea71e 100644
--- a/drivers/clk/qcom/gcc-apq8084.c
+++ b/drivers/clk/qcom/gcc-apq8084.c
@@ -106,8 +106,6 @@ static const char * const gcc_xo_pcie_sleep[] = {
 	"sleep_clk_src",
 };
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 static struct clk_pll gpll0 = {
 	.l_reg = 0x0004,
 	.m_reg = 0x0008,
diff --git a/drivers/clk/qcom/gcc-ipq4019.c b/drivers/clk/qcom/gcc-ipq4019.c
index 46cb256b4aa2..8902ad42ba87 100644
--- a/drivers/clk/qcom/gcc-ipq4019.c
+++ b/drivers/clk/qcom/gcc-ipq4019.c
@@ -179,8 +179,6 @@ static const char * const gcc_xo_ddr_500_200[] = {
 	"ddrpllapss",
 };
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 static const struct freq_tbl ftbl_gcc_audio_pwm_clk[] = {
 	F(48000000, P_XO, 1, 0, 0),
 	F(200000000, P_FEPLL200, 1, 0, 0),
diff --git a/drivers/clk/qcom/gcc-ipq806x.c b/drivers/clk/qcom/gcc-ipq806x.c
index 28eb200d0f1e..5f61225657ab 100644
--- a/drivers/clk/qcom/gcc-ipq806x.c
+++ b/drivers/clk/qcom/gcc-ipq806x.c
@@ -1220,7 +1220,6 @@ static struct clk_rcg sdc1_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1269,7 +1268,6 @@ static struct clk_rcg sdc3_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1353,7 +1351,6 @@ static struct clk_rcg tsif_ref_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
diff --git a/drivers/clk/qcom/gcc-ipq8074.c b/drivers/clk/qcom/gcc-ipq8074.c
index 0462f4a8c932..505c6263141d 100644
--- a/drivers/clk/qcom/gcc-ipq8074.c
+++ b/drivers/clk/qcom/gcc-ipq8074.c
@@ -32,8 +32,6 @@
 #include "clk-regmap-mux.h"
 #include "reset.h"
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 enum {
 	P_XO,
 	P_GPLL0,
diff --git a/drivers/clk/qcom/gcc-mdm9615.c b/drivers/clk/qcom/gcc-mdm9615.c
index b99dd406e907..849046fbed6d 100644
--- a/drivers/clk/qcom/gcc-mdm9615.c
+++ b/drivers/clk/qcom/gcc-mdm9615.c
@@ -947,7 +947,6 @@ static struct clk_rcg sdc1_src = {
 			.parent_names = gcc_cxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -996,7 +995,6 @@ static struct clk_rcg sdc2_src = {
 			.parent_names = gcc_cxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
diff --git a/drivers/clk/qcom/gcc-msm8660.c b/drivers/clk/qcom/gcc-msm8660.c
index c347a0d44bc8..7e930e25c79f 100644
--- a/drivers/clk/qcom/gcc-msm8660.c
+++ b/drivers/clk/qcom/gcc-msm8660.c
@@ -1558,7 +1558,6 @@ static struct clk_rcg sdc1_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1607,7 +1606,6 @@ static struct clk_rcg sdc2_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1656,7 +1654,6 @@ static struct clk_rcg sdc3_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1705,7 +1702,6 @@ static struct clk_rcg sdc4_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1754,7 +1750,6 @@ static struct clk_rcg sdc5_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
diff --git a/drivers/clk/qcom/gcc-msm8916.c b/drivers/clk/qcom/gcc-msm8916.c
index d6c7f50ba86a..ac2b0aa1e8b5 100644
--- a/drivers/clk/qcom/gcc-msm8916.c
+++ b/drivers/clk/qcom/gcc-msm8916.c
@@ -264,8 +264,6 @@ static const char * const gcc_xo_gpll1_emclk_sleep[] = {
 	"sleep_clk",
 };
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 static struct clk_pll gpll0 = {
 	.l_reg = 0x21004,
 	.m_reg = 0x21008,
diff --git a/drivers/clk/qcom/gcc-msm8960.c b/drivers/clk/qcom/gcc-msm8960.c
index eb551c75fba6..fd495e0471bb 100644
--- a/drivers/clk/qcom/gcc-msm8960.c
+++ b/drivers/clk/qcom/gcc-msm8960.c
@@ -1628,7 +1628,6 @@ static struct clk_rcg sdc1_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1677,7 +1676,6 @@ static struct clk_rcg sdc2_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1726,7 +1724,6 @@ static struct clk_rcg sdc3_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1775,7 +1772,6 @@ static struct clk_rcg sdc4_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1824,7 +1820,6 @@ static struct clk_rcg sdc5_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
diff --git a/drivers/clk/qcom/gcc-msm8974.c b/drivers/clk/qcom/gcc-msm8974.c
index 348e30da4f18..08e2900d172c 100644
--- a/drivers/clk/qcom/gcc-msm8974.c
+++ b/drivers/clk/qcom/gcc-msm8974.c
@@ -62,8 +62,6 @@ static const char * const gcc_xo_gpll0_gpll4[] = {
 	"gpll4_vote",
 };
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 static struct clk_pll gpll0 = {
 	.l_reg = 0x0004,
 	.m_reg = 0x0008,
diff --git a/drivers/clk/qcom/gcc-msm8994.c b/drivers/clk/qcom/gcc-msm8994.c
index 1e38efc37180..53f0f369a33e 100644
--- a/drivers/clk/qcom/gcc-msm8994.c
+++ b/drivers/clk/qcom/gcc-msm8994.c
@@ -57,8 +57,6 @@ static const char * const gcc_xo_gpll0_gpll4[] = {
 	"gpll4",
 };
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 static struct clk_fixed_factor xo = {
 	.mult = 1,
 	.div = 1,
diff --git a/drivers/clk/qcom/gcc-msm8996.c b/drivers/clk/qcom/gcc-msm8996.c
index ff8d66fd94e6..9a3290fdd01b 100644
--- a/drivers/clk/qcom/gcc-msm8996.c
+++ b/drivers/clk/qcom/gcc-msm8996.c
@@ -32,8 +32,6 @@
 #include "reset.h"
 #include "gdsc.h"
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 enum {
 	P_XO,
 	P_GPLL0,
diff --git a/drivers/clk/qcom/gcc-msm8998.c b/drivers/clk/qcom/gcc-msm8998.c
index 78d87f5c7098..9f0ae403d5f5 100644
--- a/drivers/clk/qcom/gcc-msm8998.c
+++ b/drivers/clk/qcom/gcc-msm8998.c
@@ -25,8 +25,6 @@
 #include "reset.h"
 #include "gdsc.h"
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 enum {
 	P_AUD_REF_CLK,
 	P_CORE_BI_PLL_TEST_SE,
diff --git a/drivers/clk/qcom/gcc-sdm845.c b/drivers/clk/qcom/gcc-sdm845.c
index e78e6f5b99fc..fa1a196350f1 100644
--- a/drivers/clk/qcom/gcc-sdm845.c
+++ b/drivers/clk/qcom/gcc-sdm845.c
@@ -25,8 +25,6 @@
 #include "gdsc.h"
 #include "reset.h"
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 enum {
 	P_BI_TCXO,
 	P_AUD_REF_CLK,
@@ -1103,6 +1101,7 @@ static struct clk_branch gcc_camera_ahb_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_camera_ahb_clk",
+			.flags = CLK_IS_CRITICAL,
 			.ops = &clk_branch2_ops,
 		},
 	},
@@ -1129,6 +1128,7 @@ static struct clk_branch gcc_camera_xo_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_camera_xo_clk",
+			.flags = CLK_IS_CRITICAL,
 			.ops = &clk_branch2_ops,
 		},
 	},
@@ -1270,6 +1270,7 @@ static struct clk_branch gcc_disp_ahb_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_disp_ahb_clk",
+			.flags = CLK_IS_CRITICAL,
 			.ops = &clk_branch2_ops,
 		},
 	},
@@ -1328,6 +1329,7 @@ static struct clk_branch gcc_disp_xo_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_disp_xo_clk",
+			.flags = CLK_IS_CRITICAL,
 			.ops = &clk_branch2_ops,
 		},
 	},
@@ -1397,6 +1399,7 @@ static struct clk_branch gcc_gpu_cfg_ahb_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_gpu_cfg_ahb_clk",
+			.flags = CLK_IS_CRITICAL,
 			.ops = &clk_branch2_ops,
 		},
 	},
@@ -2985,6 +2988,7 @@ static struct clk_branch gcc_video_ahb_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_video_ahb_clk",
+			.flags = CLK_IS_CRITICAL,
 			.ops = &clk_branch2_ops,
 		},
 	},
@@ -3011,6 +3015,7 @@ static struct clk_branch gcc_video_xo_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_video_xo_clk",
+			.flags = CLK_IS_CRITICAL,
 			.ops = &clk_branch2_ops,
 		},
 	},
@@ -3049,6 +3054,36 @@ static struct clk_branch gcc_vs_ctrl_clk = {
 	},
 };
 
+static struct clk_branch gcc_cpuss_dvm_bus_clk = {
+	.halt_reg = 0x48190,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x48190,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_cpuss_dvm_bus_clk",
+			.flags = CLK_IS_CRITICAL,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_cpuss_gnoc_clk = {
+	.halt_reg = 0x48004,
+	.halt_check = BRANCH_HALT_VOTED,
+	.hwcg_reg = 0x48004,
+	.hwcg_bit = 1,
+	.clkr = {
+		.enable_reg = 0x52004,
+		.enable_mask = BIT(22),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_cpuss_gnoc_clk",
+			.flags = CLK_IS_CRITICAL,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct gdsc pcie_0_gdsc = {
 	.gdscr = 0x6b004,
 	.pd = {
@@ -3344,6 +3379,8 @@ static struct clk_regmap *gcc_sdm845_clocks[] = {
 	[GPLL0] = &gpll0.clkr,
 	[GPLL0_OUT_EVEN] = &gpll0_out_even.clkr,
 	[GPLL4] = &gpll4.clkr,
+	[GCC_CPUSS_DVM_BUS_CLK] = &gcc_cpuss_dvm_bus_clk.clkr,
+	[GCC_CPUSS_GNOC_CLK] = &gcc_cpuss_gnoc_clk.clkr,
 };
 
 static const struct qcom_reset_map gcc_sdm845_resets[] = {
@@ -3433,10 +3470,6 @@ static int gcc_sdm845_probe(struct platform_device *pdev)
 	regmap_update_bits(regmap, 0x09ffc, 0x3, 0x3);
 	regmap_update_bits(regmap, 0x71028, 0x3, 0x3);
 
-	/* Enable CPUSS clocks */
-	regmap_update_bits(regmap, 0x48190, BIT(0), 0x1);
-	regmap_update_bits(regmap, 0x52004, BIT(22), 0x1);
-
 	return qcom_cc_really_probe(pdev, &gcc_sdm845_desc, regmap);
 }
 
diff --git a/drivers/clk/qcom/mmcc-apq8084.c b/drivers/clk/qcom/mmcc-apq8084.c
index 30777f9f1a43..4ce1d7c88377 100644
--- a/drivers/clk/qcom/mmcc-apq8084.c
+++ b/drivers/clk/qcom/mmcc-apq8084.c
@@ -219,8 +219,6 @@ static const char * const mmcc_xo_mmpll0_1_4_gpll1_0_sleep[] = {
 	"sleep_clk_src",
 };
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 static struct clk_pll mmpll0 = {
 	.l_reg = 0x0004,
 	.m_reg = 0x0008,
diff --git a/drivers/clk/qcom/mmcc-msm8974.c b/drivers/clk/qcom/mmcc-msm8974.c
index 715e7cd94125..91818516c3e0 100644
--- a/drivers/clk/qcom/mmcc-msm8974.c
+++ b/drivers/clk/qcom/mmcc-msm8974.c
@@ -184,8 +184,6 @@ static const char * const mmcc_xo_dsibyte_hdmi_edp_gpll0[] = {
 	"dsi1pllbyte",
 };
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 static struct clk_pll mmpll0 = {
 	.l_reg = 0x0004,
 	.m_reg = 0x0008,
diff --git a/drivers/clk/qcom/mmcc-msm8996.c b/drivers/clk/qcom/mmcc-msm8996.c
index 4b20d1b67a1b..7d4ee109435c 100644
--- a/drivers/clk/qcom/mmcc-msm8996.c
+++ b/drivers/clk/qcom/mmcc-msm8996.c
@@ -34,8 +34,6 @@
 #include "reset.h"
 #include "gdsc.h"
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 enum {
 	P_XO,
 	P_MMPLL0,
diff --git a/drivers/clk/qcom/videocc-sdm845.c b/drivers/clk/qcom/videocc-sdm845.c
index 9073b7a710ac..5d6a7724a194 100644
--- a/drivers/clk/qcom/videocc-sdm845.c
+++ b/drivers/clk/qcom/videocc-sdm845.c
@@ -18,8 +18,6 @@
 #include "clk-pll.h"
 #include "gdsc.h"
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 enum {
 	P_BI_TCXO,
 	P_CORE_BI_PLL_TEST_SE,
diff --git a/drivers/clk/renesas/Kconfig b/drivers/clk/renesas/Kconfig
index f9ba71311727..9022bbe1297e 100644
--- a/drivers/clk/renesas/Kconfig
+++ b/drivers/clk/renesas/Kconfig
@@ -21,6 +21,7 @@ config CLK_RENESAS
 	select CLK_R8A77980 if ARCH_R8A77980
 	select CLK_R8A77990 if ARCH_R8A77990
 	select CLK_R8A77995 if ARCH_R8A77995
+	select CLK_R9A06G032 if ARCH_R9A06G032
 	select CLK_SH73A0 if ARCH_SH73A0
 
 if CLK_RENESAS
@@ -125,6 +126,11 @@ config CLK_R8A77995
 	bool "R-Car D3 clock support" if COMPILE_TEST
 	select CLK_RCAR_GEN3_CPG
 
+config CLK_R9A06G032
+	bool "Renesas R9A06G032 clock driver"
+	help
+	  This is a driver for R9A06G032 clocks
+
 config CLK_SH73A0
 	bool "SH-Mobile AG5 clock support" if COMPILE_TEST
 	select CLK_RENESAS_CPG_MSTP
diff --git a/drivers/clk/renesas/Makefile b/drivers/clk/renesas/Makefile
index fe5bac9215e5..e4aa3d6143d2 100644
--- a/drivers/clk/renesas/Makefile
+++ b/drivers/clk/renesas/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_CLK_R8A77970)		+= r8a77970-cpg-mssr.o
 obj-$(CONFIG_CLK_R8A77980)		+= r8a77980-cpg-mssr.o
 obj-$(CONFIG_CLK_R8A77990)		+= r8a77990-cpg-mssr.o
 obj-$(CONFIG_CLK_R8A77995)		+= r8a77995-cpg-mssr.o
+obj-$(CONFIG_CLK_R9A06G032)		+= r9a06g032-clocks.o
 obj-$(CONFIG_CLK_SH73A0)		+= clk-sh73a0.o
 
 # Family
diff --git a/drivers/clk/renesas/r8a7795-cpg-mssr.c b/drivers/clk/renesas/r8a7795-cpg-mssr.c
index 775b0ceaa337..a85dd50e8911 100644
--- a/drivers/clk/renesas/r8a7795-cpg-mssr.c
+++ b/drivers/clk/renesas/r8a7795-cpg-mssr.c
@@ -103,6 +103,7 @@ static struct cpg_core_clk r8a7795_core_clks[] __initdata = {
 	DEF_GEN3_SD("sd3",      R8A7795_CLK_SD3,   CLK_SDSRC,     0x26c),
 
 	DEF_FIXED("cl",         R8A7795_CLK_CL,    CLK_PLL1_DIV2, 48, 1),
+	DEF_FIXED("cr",         R8A7795_CLK_CR,    CLK_PLL1_DIV4,  2, 1),
 	DEF_FIXED("cp",         R8A7795_CLK_CP,    CLK_EXTAL,      2, 1),
 
 	DEF_DIV6P1("canfd",     R8A7795_CLK_CANFD, CLK_PLL1_DIV4, 0x244),
@@ -132,6 +133,7 @@ static struct mssr_mod_clk r8a7795_mod_clks[] __initdata = {
 	DEF_MOD("sys-dmac2",		 217,	R8A7795_CLK_S0D3),
 	DEF_MOD("sys-dmac1",		 218,	R8A7795_CLK_S0D3),
 	DEF_MOD("sys-dmac0",		 219,	R8A7795_CLK_S0D3),
+	DEF_MOD("sceg-pub",		 229,	R8A7795_CLK_CR),
 	DEF_MOD("cmt3",			 300,	R8A7795_CLK_R),
 	DEF_MOD("cmt2",			 301,	R8A7795_CLK_R),
 	DEF_MOD("cmt1",			 302,	R8A7795_CLK_R),
diff --git a/drivers/clk/renesas/r9a06g032-clocks.c b/drivers/clk/renesas/r9a06g032-clocks.c
new file mode 100644
index 000000000000..a0b6ecdc63dd
--- /dev/null
+++ b/drivers/clk/renesas/r9a06g032-clocks.c
@@ -0,0 +1,893 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * R9A09G032 clock driver
+ *
+ * Copyright (C) 2018 Renesas Electronics Europe Limited
+ *
+ * Michel Pollet <michel.pollet@bp.renesas.com>, <buserror@gmail.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/math64.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <dt-bindings/clock/r9a06g032-sysctrl.h>
+
+struct r9a06g032_gate {
+	u16 gate, reset, ready, midle,
+		scon, mirack, mistat;
+};
+
+/* This is used to describe a clock for instantiation */
+struct r9a06g032_clkdesc {
+	const char *name;
+	uint32_t type: 3;
+	uint32_t index: 8;
+	uint32_t source : 8; /* source index + 1 (0 == none) */
+	/* these are used to populate the bitsel struct */
+	union {
+		struct r9a06g032_gate gate;
+		/* for dividers */
+		struct {
+			unsigned int div_min : 10, div_max : 10, reg: 10;
+			u16 div_table[4];
+		};
+		/* For fixed-factor ones */
+		struct {
+			u16 div, mul;
+		};
+		unsigned int factor;
+		unsigned int frequency;
+		/* for dual gate */
+		struct {
+			uint16_t group : 1, index: 3;
+			u16 sel, g1, r1, g2, r2;
+		} dual;
+	};
+} __packed;
+
+#define I_GATE(_clk, _rst, _rdy, _midle, _scon, _mirack, _mistat) \
+	{ .gate = _clk, .reset = _rst, \
+		.ready = _rdy, .midle = _midle, \
+		.scon = _scon, .mirack = _mirack, .mistat = _mistat }
+#define D_GATE(_idx, _n, _src, ...) \
+	{ .type = K_GATE, .index = R9A06G032_##_idx, \
+		.source = 1 + R9A06G032_##_src, .name = _n, \
+		.gate = I_GATE(__VA_ARGS__), }
+#define D_ROOT(_idx, _n, _mul, _div) \
+	{ .type = K_FFC, .index = R9A06G032_##_idx, .name = _n, \
+		.div = _div, .mul = _mul }
+#define D_FFC(_idx, _n, _src, _div) \
+	{ .type = K_FFC, .index = R9A06G032_##_idx, \
+		.source = 1 + R9A06G032_##_src, .name = _n, \
+		.div = _div, .mul = 1}
+#define D_DIV(_idx, _n, _src, _reg, _min, _max, ...) \
+	{ .type = K_DIV, .index = R9A06G032_##_idx, \
+		.source = 1 + R9A06G032_##_src, .name = _n, \
+		.reg = _reg, .div_min = _min, .div_max = _max, \
+		.div_table = { __VA_ARGS__ } }
+#define D_UGATE(_idx, _n, _src, _g, _gi, _g1, _r1, _g2, _r2) \
+	{ .type = K_DUALGATE, .index = R9A06G032_##_idx, \
+		.source = 1 + R9A06G032_##_src, .name = _n, \
+		.dual = { .group = _g, .index = _gi, \
+			.g1 = _g1, .r1 = _r1, .g2 = _g2, .r2 = _r2 }, }
+
+enum { K_GATE = 0, K_FFC, K_DIV, K_BITSEL, K_DUALGATE };
+
+/* Internal clock IDs */
+#define R9A06G032_CLKOUT		0
+#define R9A06G032_CLKOUT_D10		2
+#define R9A06G032_CLKOUT_D16		3
+#define R9A06G032_CLKOUT_D160		4
+#define R9A06G032_CLKOUT_D1OR2		5
+#define R9A06G032_CLKOUT_D20		6
+#define R9A06G032_CLKOUT_D40		7
+#define R9A06G032_CLKOUT_D5		8
+#define R9A06G032_CLKOUT_D8		9
+#define R9A06G032_DIV_ADC		10
+#define R9A06G032_DIV_I2C		11
+#define R9A06G032_DIV_NAND		12
+#define R9A06G032_DIV_P1_PG		13
+#define R9A06G032_DIV_P2_PG		14
+#define R9A06G032_DIV_P3_PG		15
+#define R9A06G032_DIV_P4_PG		16
+#define R9A06G032_DIV_P5_PG		17
+#define R9A06G032_DIV_P6_PG		18
+#define R9A06G032_DIV_QSPI0		19
+#define R9A06G032_DIV_QSPI1		20
+#define R9A06G032_DIV_REF_SYNC		21
+#define R9A06G032_DIV_SDIO0		22
+#define R9A06G032_DIV_SDIO1		23
+#define R9A06G032_DIV_SWITCH		24
+#define R9A06G032_DIV_UART		25
+#define R9A06G032_DIV_MOTOR		64
+#define R9A06G032_CLK_DDRPHY_PLLCLK_D4	78
+#define R9A06G032_CLK_ECAT100_D4	79
+#define R9A06G032_CLK_HSR100_D2		80
+#define R9A06G032_CLK_REF_SYNC_D4	81
+#define R9A06G032_CLK_REF_SYNC_D8	82
+#define R9A06G032_CLK_SERCOS100_D2	83
+#define R9A06G032_DIV_CA7		84
+
+#define R9A06G032_UART_GROUP_012	154
+#define R9A06G032_UART_GROUP_34567	155
+
+#define R9A06G032_CLOCK_COUNT		(R9A06G032_UART_GROUP_34567 + 1)
+
+static const struct r9a06g032_clkdesc r9a06g032_clocks[] __initconst = {
+	D_ROOT(CLKOUT, "clkout", 25, 1),
+	D_ROOT(CLK_PLL_USB, "clk_pll_usb", 12, 10),
+	D_FFC(CLKOUT_D10, "clkout_d10", CLKOUT, 10),
+	D_FFC(CLKOUT_D16, "clkout_d16", CLKOUT, 16),
+	D_FFC(CLKOUT_D160, "clkout_d160", CLKOUT, 160),
+	D_DIV(CLKOUT_D1OR2, "clkout_d1or2", CLKOUT, 0, 1, 2),
+	D_FFC(CLKOUT_D20, "clkout_d20", CLKOUT, 20),
+	D_FFC(CLKOUT_D40, "clkout_d40", CLKOUT, 40),
+	D_FFC(CLKOUT_D5, "clkout_d5", CLKOUT, 5),
+	D_FFC(CLKOUT_D8, "clkout_d8", CLKOUT, 8),
+	D_DIV(DIV_ADC, "div_adc", CLKOUT, 77, 50, 250),
+	D_DIV(DIV_I2C, "div_i2c", CLKOUT, 78, 12, 16),
+	D_DIV(DIV_NAND, "div_nand", CLKOUT, 82, 12, 32),
+	D_DIV(DIV_P1_PG, "div_p1_pg", CLKOUT, 68, 12, 200),
+	D_DIV(DIV_P2_PG, "div_p2_pg", CLKOUT, 62, 12, 128),
+	D_DIV(DIV_P3_PG, "div_p3_pg", CLKOUT, 64, 8, 128),
+	D_DIV(DIV_P4_PG, "div_p4_pg", CLKOUT, 66, 8, 128),
+	D_DIV(DIV_P5_PG, "div_p5_pg", CLKOUT, 71, 10, 40),
+	D_DIV(DIV_P6_PG, "div_p6_pg", CLKOUT, 18, 12, 64),
+	D_DIV(DIV_QSPI0, "div_qspi0", CLKOUT, 73, 3, 7),
+	D_DIV(DIV_QSPI1, "div_qspi1", CLKOUT, 25, 3, 7),
+	D_DIV(DIV_REF_SYNC, "div_ref_sync", CLKOUT, 56, 2, 16, 2, 4, 8, 16),
+	D_DIV(DIV_SDIO0, "div_sdio0", CLKOUT, 74, 20, 128),
+	D_DIV(DIV_SDIO1, "div_sdio1", CLKOUT, 75, 20, 128),
+	D_DIV(DIV_SWITCH, "div_switch", CLKOUT, 37, 5, 40),
+	D_DIV(DIV_UART, "div_uart", CLKOUT, 79, 12, 128),
+	D_GATE(CLK_25_PG4, "clk_25_pg4", CLKOUT_D40, 0x749, 0x74a, 0x74b, 0, 0xae3, 0, 0),
+	D_GATE(CLK_25_PG5, "clk_25_pg5", CLKOUT_D40, 0x74c, 0x74d, 0x74e, 0, 0xae4, 0, 0),
+	D_GATE(CLK_25_PG6, "clk_25_pg6", CLKOUT_D40, 0x74f, 0x750, 0x751, 0, 0xae5, 0, 0),
+	D_GATE(CLK_25_PG7, "clk_25_pg7", CLKOUT_D40, 0x752, 0x753, 0x754, 0, 0xae6, 0, 0),
+	D_GATE(CLK_25_PG8, "clk_25_pg8", CLKOUT_D40, 0x755, 0x756, 0x757, 0, 0xae7, 0, 0),
+	D_GATE(CLK_ADC, "clk_adc", DIV_ADC, 0x1ea, 0x1eb, 0, 0, 0, 0, 0),
+	D_GATE(CLK_ECAT100, "clk_ecat100", CLKOUT_D10, 0x405, 0, 0, 0, 0, 0, 0),
+	D_GATE(CLK_HSR100, "clk_hsr100", CLKOUT_D10, 0x483, 0, 0, 0, 0, 0, 0),
+	D_GATE(CLK_I2C0, "clk_i2c0", DIV_I2C, 0x1e6, 0x1e7, 0, 0, 0, 0, 0),
+	D_GATE(CLK_I2C1, "clk_i2c1", DIV_I2C, 0x1e8, 0x1e9, 0, 0, 0, 0, 0),
+	D_GATE(CLK_MII_REF, "clk_mii_ref", CLKOUT_D40, 0x342, 0, 0, 0, 0, 0, 0),
+	D_GATE(CLK_NAND, "clk_nand", DIV_NAND, 0x284, 0x285, 0, 0, 0, 0, 0),
+	D_GATE(CLK_NOUSBP2_PG6, "clk_nousbp2_pg6", DIV_P2_PG, 0x774, 0x775, 0, 0, 0, 0, 0),
+	D_GATE(CLK_P1_PG2, "clk_p1_pg2", DIV_P1_PG, 0x862, 0x863, 0, 0, 0, 0, 0),
+	D_GATE(CLK_P1_PG3, "clk_p1_pg3", DIV_P1_PG, 0x864, 0x865, 0, 0, 0, 0, 0),
+	D_GATE(CLK_P1_PG4, "clk_p1_pg4", DIV_P1_PG, 0x866, 0x867, 0, 0, 0, 0, 0),
+	D_GATE(CLK_P4_PG3, "clk_p4_pg3", DIV_P4_PG, 0x824, 0x825, 0, 0, 0, 0, 0),
+	D_GATE(CLK_P4_PG4, "clk_p4_pg4", DIV_P4_PG, 0x826, 0x827, 0, 0, 0, 0, 0),
+	D_GATE(CLK_P6_PG1, "clk_p6_pg1", DIV_P6_PG, 0x8a0, 0x8a1, 0x8a2, 0, 0xb60, 0, 0),
+	D_GATE(CLK_P6_PG2, "clk_p6_pg2", DIV_P6_PG, 0x8a3, 0x8a4, 0x8a5, 0, 0xb61, 0, 0),
+	D_GATE(CLK_P6_PG3, "clk_p6_pg3", DIV_P6_PG, 0x8a6, 0x8a7, 0x8a8, 0, 0xb62, 0, 0),
+	D_GATE(CLK_P6_PG4, "clk_p6_pg4", DIV_P6_PG, 0x8a9, 0x8aa, 0x8ab, 0, 0xb63, 0, 0),
+	D_GATE(CLK_QSPI0, "clk_qspi0", DIV_QSPI0, 0x2a4, 0x2a5, 0, 0, 0, 0, 0),
+	D_GATE(CLK_QSPI1, "clk_qspi1", DIV_QSPI1, 0x484, 0x485, 0, 0, 0, 0, 0),
+	D_GATE(CLK_RGMII_REF, "clk_rgmii_ref", CLKOUT_D8, 0x340, 0, 0, 0, 0, 0, 0),
+	D_GATE(CLK_RMII_REF, "clk_rmii_ref", CLKOUT_D20, 0x341, 0, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SDIO0, "clk_sdio0", DIV_SDIO0, 0x64, 0, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SDIO1, "clk_sdio1", DIV_SDIO1, 0x644, 0, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SERCOS100, "clk_sercos100", CLKOUT_D10, 0x425, 0, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SLCD, "clk_slcd", DIV_P1_PG, 0x860, 0x861, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SPI0, "clk_spi0", DIV_P3_PG, 0x7e0, 0x7e1, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SPI1, "clk_spi1", DIV_P3_PG, 0x7e2, 0x7e3, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SPI2, "clk_spi2", DIV_P3_PG, 0x7e4, 0x7e5, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SPI3, "clk_spi3", DIV_P3_PG, 0x7e6, 0x7e7, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SPI4, "clk_spi4", DIV_P4_PG, 0x820, 0x821, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SPI5, "clk_spi5", DIV_P4_PG, 0x822, 0x823, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SWITCH, "clk_switch", DIV_SWITCH, 0x982, 0x983, 0, 0, 0, 0, 0),
+	D_DIV(DIV_MOTOR, "div_motor", CLKOUT_D5, 84, 2, 8),
+	D_GATE(HCLK_ECAT125, "hclk_ecat125", CLKOUT_D8, 0x400, 0x401, 0, 0x402, 0, 0x440, 0x441),
+	D_GATE(HCLK_PINCONFIG, "hclk_pinconfig", CLKOUT_D40, 0x740, 0x741, 0x742, 0, 0xae0, 0, 0),
+	D_GATE(HCLK_SERCOS, "hclk_sercos", CLKOUT_D10, 0x420, 0x422, 0, 0x421, 0, 0x460, 0x461),
+	D_GATE(HCLK_SGPIO2, "hclk_sgpio2", DIV_P5_PG, 0x8c3, 0x8c4, 0x8c5, 0, 0xb41, 0, 0),
+	D_GATE(HCLK_SGPIO3, "hclk_sgpio3", DIV_P5_PG, 0x8c6, 0x8c7, 0x8c8, 0, 0xb42, 0, 0),
+	D_GATE(HCLK_SGPIO4, "hclk_sgpio4", DIV_P5_PG, 0x8c9, 0x8ca, 0x8cb, 0, 0xb43, 0, 0),
+	D_GATE(HCLK_TIMER0, "hclk_timer0", CLKOUT_D40, 0x743, 0x744, 0x745, 0, 0xae1, 0, 0),
+	D_GATE(HCLK_TIMER1, "hclk_timer1", CLKOUT_D40, 0x746, 0x747, 0x748, 0, 0xae2, 0, 0),
+	D_GATE(HCLK_USBF, "hclk_usbf", CLKOUT_D8, 0xe3, 0, 0, 0xe4, 0, 0x102, 0x103),
+	D_GATE(HCLK_USBH, "hclk_usbh", CLKOUT_D8, 0xe0, 0xe1, 0, 0xe2, 0, 0x100, 0x101),
+	D_GATE(HCLK_USBPM, "hclk_usbpm", CLKOUT_D8, 0xe5, 0, 0, 0, 0, 0, 0),
+	D_GATE(CLK_48_PG_F, "clk_48_pg_f", CLK_48, 0x78c, 0x78d, 0, 0x78e, 0, 0xb04, 0xb05),
+	D_GATE(CLK_48_PG4, "clk_48_pg4", CLK_48, 0x789, 0x78a, 0x78b, 0, 0xb03, 0, 0),
+	D_FFC(CLK_DDRPHY_PLLCLK_D4, "clk_ddrphy_pllclk_d4", CLK_DDRPHY_PLLCLK, 4),
+	D_FFC(CLK_ECAT100_D4, "clk_ecat100_d4", CLK_ECAT100, 4),
+	D_FFC(CLK_HSR100_D2, "clk_hsr100_d2", CLK_HSR100, 2),
+	D_FFC(CLK_REF_SYNC_D4, "clk_ref_sync_d4", CLK_REF_SYNC, 4),
+	D_FFC(CLK_REF_SYNC_D8, "clk_ref_sync_d8", CLK_REF_SYNC, 8),
+	D_FFC(CLK_SERCOS100_D2, "clk_sercos100_d2", CLK_SERCOS100, 2),
+	D_DIV(DIV_CA7, "div_ca7", CLK_REF_SYNC, 57, 1, 4, 1, 2, 4),
+	D_GATE(HCLK_CAN0, "hclk_can0", CLK_48, 0x783, 0x784, 0x785, 0, 0xb01, 0, 0),
+	D_GATE(HCLK_CAN1, "hclk_can1", CLK_48, 0x786, 0x787, 0x788, 0, 0xb02, 0, 0),
+	D_GATE(HCLK_DELTASIGMA, "hclk_deltasigma", DIV_MOTOR, 0x1ef, 0x1f0, 0x1f1, 0, 0, 0, 0),
+	D_GATE(HCLK_PWMPTO, "hclk_pwmpto", DIV_MOTOR, 0x1ec, 0x1ed, 0x1ee, 0, 0, 0, 0),
+	D_GATE(HCLK_RSV, "hclk_rsv", CLK_48, 0x780, 0x781, 0x782, 0, 0xb00, 0, 0),
+	D_GATE(HCLK_SGPIO0, "hclk_sgpio0", DIV_MOTOR, 0x1e0, 0x1e1, 0x1e2, 0, 0, 0, 0),
+	D_GATE(HCLK_SGPIO1, "hclk_sgpio1", DIV_MOTOR, 0x1e3, 0x1e4, 0x1e5, 0, 0, 0, 0),
+	D_DIV(RTOS_MDC, "rtos_mdc", CLK_REF_SYNC, 100, 80, 640, 80, 160, 320, 640),
+	D_GATE(CLK_CM3, "clk_cm3", CLK_REF_SYNC_D4, 0xba0, 0xba1, 0, 0xba2, 0, 0xbc0, 0xbc1),
+	D_GATE(CLK_DDRC, "clk_ddrc", CLK_DDRPHY_PLLCLK_D4, 0x323, 0x324, 0, 0, 0, 0, 0),
+	D_GATE(CLK_ECAT25, "clk_ecat25", CLK_ECAT100_D4, 0x403, 0x404, 0, 0, 0, 0, 0),
+	D_GATE(CLK_HSR50, "clk_hsr50", CLK_HSR100_D2, 0x484, 0x485, 0, 0, 0, 0, 0),
+	D_GATE(CLK_HW_RTOS, "clk_hw_rtos", CLK_REF_SYNC_D4, 0xc60, 0xc61, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SERCOS50, "clk_sercos50", CLK_SERCOS100_D2, 0x424, 0x423, 0, 0, 0, 0, 0),
+	D_GATE(HCLK_ADC, "hclk_adc", CLK_REF_SYNC_D8, 0x1af, 0x1b0, 0x1b1, 0, 0, 0, 0),
+	D_GATE(HCLK_CM3, "hclk_cm3", CLK_REF_SYNC_D4, 0xc20, 0xc21, 0xc22, 0, 0, 0, 0),
+	D_GATE(HCLK_CRYPTO_EIP150, "hclk_crypto_eip150", CLK_REF_SYNC_D4, 0x123, 0x124, 0x125, 0, 0x142, 0, 0),
+	D_GATE(HCLK_CRYPTO_EIP93, "hclk_crypto_eip93", CLK_REF_SYNC_D4, 0x120, 0x121, 0, 0x122, 0, 0x140, 0x141),
+	D_GATE(HCLK_DDRC, "hclk_ddrc", CLK_REF_SYNC_D4, 0x320, 0x322, 0, 0x321, 0, 0x3a0, 0x3a1),
+	D_GATE(HCLK_DMA0, "hclk_dma0", CLK_REF_SYNC_D4, 0x260, 0x261, 0x262, 0x263, 0x2c0, 0x2c1, 0x2c2),
+	D_GATE(HCLK_DMA1, "hclk_dma1", CLK_REF_SYNC_D4, 0x264, 0x265, 0x266, 0x267, 0x2c3, 0x2c4, 0x2c5),
+	D_GATE(HCLK_GMAC0, "hclk_gmac0", CLK_REF_SYNC_D4, 0x360, 0x361, 0x362, 0x363, 0x3c0, 0x3c1, 0x3c2),
+	D_GATE(HCLK_GMAC1, "hclk_gmac1", CLK_REF_SYNC_D4, 0x380, 0x381, 0x382, 0x383, 0x3e0, 0x3e1, 0x3e2),
+	D_GATE(HCLK_GPIO0, "hclk_gpio0", CLK_REF_SYNC_D4, 0x212, 0x213, 0x214, 0, 0, 0, 0),
+	D_GATE(HCLK_GPIO1, "hclk_gpio1", CLK_REF_SYNC_D4, 0x215, 0x216, 0x217, 0, 0, 0, 0),
+	D_GATE(HCLK_GPIO2, "hclk_gpio2", CLK_REF_SYNC_D4, 0x229, 0x22a, 0x22b, 0, 0, 0, 0),
+	D_GATE(HCLK_HSR, "hclk_hsr", CLK_HSR100_D2, 0x480, 0x482, 0, 0x481, 0, 0x4c0, 0x4c1),
+	D_GATE(HCLK_I2C0, "hclk_i2c0", CLK_REF_SYNC_D8, 0x1a9, 0x1aa, 0x1ab, 0, 0, 0, 0),
+	D_GATE(HCLK_I2C1, "hclk_i2c1", CLK_REF_SYNC_D8, 0x1ac, 0x1ad, 0x1ae, 0, 0, 0, 0),
+	D_GATE(HCLK_LCD, "hclk_lcd", CLK_REF_SYNC_D4, 0x7a0, 0x7a1, 0x7a2, 0, 0xb20, 0, 0),
+	D_GATE(HCLK_MSEBI_M, "hclk_msebi_m", CLK_REF_SYNC_D4, 0x164, 0x165, 0x166, 0, 0x183, 0, 0),
+	D_GATE(HCLK_MSEBI_S, "hclk_msebi_s", CLK_REF_SYNC_D4, 0x160, 0x161, 0x162, 0x163, 0x180, 0x181, 0x182),
+	D_GATE(HCLK_NAND, "hclk_nand", CLK_REF_SYNC_D4, 0x280, 0x281, 0x282, 0x283, 0x2e0, 0x2e1, 0x2e2),
+	D_GATE(HCLK_PG_I, "hclk_pg_i", CLK_REF_SYNC_D4, 0x7ac, 0x7ad, 0, 0x7ae, 0, 0xb24, 0xb25),
+	D_GATE(HCLK_PG19, "hclk_pg19", CLK_REF_SYNC_D4, 0x22c, 0x22d, 0x22e, 0, 0, 0, 0),
+	D_GATE(HCLK_PG20, "hclk_pg20", CLK_REF_SYNC_D4, 0x22f, 0x230, 0x231, 0, 0, 0, 0),
+	D_GATE(HCLK_PG3, "hclk_pg3", CLK_REF_SYNC_D4, 0x7a6, 0x7a7, 0x7a8, 0, 0xb22, 0, 0),
+	D_GATE(HCLK_PG4, "hclk_pg4", CLK_REF_SYNC_D4, 0x7a9, 0x7aa, 0x7ab, 0, 0xb23, 0, 0),
+	D_GATE(HCLK_QSPI0, "hclk_qspi0", CLK_REF_SYNC_D4, 0x2a0, 0x2a1, 0x2a2, 0x2a3, 0x300, 0x301, 0x302),
+	D_GATE(HCLK_QSPI1, "hclk_qspi1", CLK_REF_SYNC_D4, 0x480, 0x481, 0x482, 0x483, 0x4c0, 0x4c1, 0x4c2),
+	D_GATE(HCLK_ROM, "hclk_rom", CLK_REF_SYNC_D4, 0xaa0, 0xaa1, 0xaa2, 0, 0xb80, 0, 0),
+	D_GATE(HCLK_RTC, "hclk_rtc", CLK_REF_SYNC_D8, 0xa00, 0, 0, 0, 0, 0, 0),
+	D_GATE(HCLK_SDIO0, "hclk_sdio0", CLK_REF_SYNC_D4, 0x60, 0x61, 0x62, 0x63, 0x80, 0x81, 0x82),
+	D_GATE(HCLK_SDIO1, "hclk_sdio1", CLK_REF_SYNC_D4, 0x640, 0x641, 0x642, 0x643, 0x660, 0x661, 0x662),
+	D_GATE(HCLK_SEMAP, "hclk_semap", CLK_REF_SYNC_D4, 0x7a3, 0x7a4, 0x7a5, 0, 0xb21, 0, 0),
+	D_GATE(HCLK_SPI0, "hclk_spi0", CLK_REF_SYNC_D4, 0x200, 0x201, 0x202, 0, 0, 0, 0),
+	D_GATE(HCLK_SPI1, "hclk_spi1", CLK_REF_SYNC_D4, 0x203, 0x204, 0x205, 0, 0, 0, 0),
+	D_GATE(HCLK_SPI2, "hclk_spi2", CLK_REF_SYNC_D4, 0x206, 0x207, 0x208, 0, 0, 0, 0),
+	D_GATE(HCLK_SPI3, "hclk_spi3", CLK_REF_SYNC_D4, 0x209, 0x20a, 0x20b, 0, 0, 0, 0),
+	D_GATE(HCLK_SPI4, "hclk_spi4", CLK_REF_SYNC_D4, 0x20c, 0x20d, 0x20e, 0, 0, 0, 0),
+	D_GATE(HCLK_SPI5, "hclk_spi5", CLK_REF_SYNC_D4, 0x20f, 0x210, 0x211, 0, 0, 0, 0),
+	D_GATE(HCLK_SWITCH, "hclk_switch", CLK_REF_SYNC_D4, 0x980, 0, 0x981, 0, 0, 0, 0),
+	D_GATE(HCLK_SWITCH_RG, "hclk_switch_rg", CLK_REF_SYNC_D4, 0xc40, 0xc41, 0xc42, 0, 0, 0, 0),
+	D_GATE(HCLK_UART0, "hclk_uart0", CLK_REF_SYNC_D8, 0x1a0, 0x1a1, 0x1a2, 0, 0, 0, 0),
+	D_GATE(HCLK_UART1, "hclk_uart1", CLK_REF_SYNC_D8, 0x1a3, 0x1a4, 0x1a5, 0, 0, 0, 0),
+	D_GATE(HCLK_UART2, "hclk_uart2", CLK_REF_SYNC_D8, 0x1a6, 0x1a7, 0x1a8, 0, 0, 0, 0),
+	D_GATE(HCLK_UART3, "hclk_uart3", CLK_REF_SYNC_D4, 0x218, 0x219, 0x21a, 0, 0, 0, 0),
+	D_GATE(HCLK_UART4, "hclk_uart4", CLK_REF_SYNC_D4, 0x21b, 0x21c, 0x21d, 0, 0, 0, 0),
+	D_GATE(HCLK_UART5, "hclk_uart5", CLK_REF_SYNC_D4, 0x220, 0x221, 0x222, 0, 0, 0, 0),
+	D_GATE(HCLK_UART6, "hclk_uart6", CLK_REF_SYNC_D4, 0x223, 0x224, 0x225, 0, 0, 0, 0),
+	D_GATE(HCLK_UART7, "hclk_uart7", CLK_REF_SYNC_D4, 0x226, 0x227, 0x228, 0, 0, 0, 0),
+	/*
+	 * These are not hardware clocks, but are needed to handle the special
+	 * case where we have a 'selector bit' that doesn't just change the
+	 * parent for a clock, but also the gate it's suposed to use.
+	 */
+	{
+		.index = R9A06G032_UART_GROUP_012,
+		.name = "uart_group_012",
+		.type = K_BITSEL,
+		.source = 1 + R9A06G032_DIV_UART,
+		/* R9A06G032_SYSCTRL_REG_PWRCTRL_PG1_PR2 */
+		.dual.sel = ((0xec / 4) << 5) | 24,
+		.dual.group = 0,
+	},
+	{
+		.index = R9A06G032_UART_GROUP_34567,
+		.name = "uart_group_34567",
+		.type = K_BITSEL,
+		.source = 1 + R9A06G032_DIV_P2_PG,
+		/* R9A06G032_SYSCTRL_REG_PWRCTRL_PG0_0 */
+		.dual.sel = ((0x34 / 4) << 5) | 30,
+		.dual.group = 1,
+	},
+	D_UGATE(CLK_UART0, "clk_uart0", UART_GROUP_012, 0, 0, 0x1b2, 0x1b3, 0x1b4, 0x1b5),
+	D_UGATE(CLK_UART1, "clk_uart1", UART_GROUP_012, 0, 1, 0x1b6, 0x1b7, 0x1b8, 0x1b9),
+	D_UGATE(CLK_UART2, "clk_uart2", UART_GROUP_012, 0, 2, 0x1ba, 0x1bb, 0x1bc, 0x1bd),
+	D_UGATE(CLK_UART3, "clk_uart3", UART_GROUP_34567, 1, 0, 0x760, 0x761, 0x762, 0x763),
+	D_UGATE(CLK_UART4, "clk_uart4", UART_GROUP_34567, 1, 1, 0x764, 0x765, 0x766, 0x767),
+	D_UGATE(CLK_UART5, "clk_uart5", UART_GROUP_34567, 1, 2, 0x768, 0x769, 0x76a, 0x76b),
+	D_UGATE(CLK_UART6, "clk_uart6", UART_GROUP_34567, 1, 3, 0x76c, 0x76d, 0x76e, 0x76f),
+	D_UGATE(CLK_UART7, "clk_uart7", UART_GROUP_34567, 1, 4, 0x770, 0x771, 0x772, 0x773),
+};
+
+struct r9a06g032_priv {
+	struct clk_onecell_data data;
+	spinlock_t lock; /* protects concurent access to gates */
+	void __iomem *reg;
+};
+
+/* register/bit pairs are encoded as an uint16_t */
+static void
+clk_rdesc_set(struct r9a06g032_priv *clocks,
+	      u16 one, unsigned int on)
+{
+	u32 __iomem *reg = clocks->reg + (4 * (one >> 5));
+	u32 val = readl(reg);
+
+	val = (val & ~(1U << (one & 0x1f))) | ((!!on) << (one & 0x1f));
+	writel(val, reg);
+}
+
+static int
+clk_rdesc_get(struct r9a06g032_priv *clocks,
+	      uint16_t one)
+{
+	u32 __iomem *reg = clocks->reg + (4 * (one >> 5));
+	u32 val = readl(reg);
+
+	return !!(val & (1U << (one & 0x1f)));
+}
+
+/*
+ * This implements the R9A09G032 clock gate 'driver'. We cannot use the system's
+ * clock gate framework as the gates on the R9A09G032 have a special enabling
+ * sequence, therefore we use this little proxy.
+ */
+struct r9a06g032_clk_gate {
+	struct clk_hw hw;
+	struct r9a06g032_priv *clocks;
+	u16 index;
+
+	struct r9a06g032_gate gate;
+};
+
+#define to_r9a06g032_gate(_hw) container_of(_hw, struct r9a06g032_clk_gate, hw)
+
+static void
+r9a06g032_clk_gate_set(struct r9a06g032_priv *clocks,
+		       struct r9a06g032_gate *g, int on)
+{
+	unsigned long flags;
+
+	WARN_ON(!g->gate);
+
+	spin_lock_irqsave(&clocks->lock, flags);
+	clk_rdesc_set(clocks, g->gate, on);
+	/* De-assert reset */
+	if (g->reset)
+		clk_rdesc_set(clocks, g->reset, 1);
+	spin_unlock_irqrestore(&clocks->lock, flags);
+
+	/* Hardware manual recommends 5us delay after enabling clock & reset */
+	udelay(5);
+
+	/* If the peripheral is memory mapped (i.e. an AXI slave), there is an
+	 * associated SLVRDY bit in the System Controller that needs to be set
+	 * so that the FlexWAY bus fabric passes on the read/write requests.
+	 */
+	if (g->ready || g->midle) {
+		spin_lock_irqsave(&clocks->lock, flags);
+		if (g->ready)
+			clk_rdesc_set(clocks, g->ready, on);
+		/* Clear 'Master Idle Request' bit */
+		if (g->midle)
+			clk_rdesc_set(clocks, g->midle, !on);
+		spin_unlock_irqrestore(&clocks->lock, flags);
+	}
+	/* Note: We don't wait for FlexWAY Socket Connection signal */
+}
+
+static int r9a06g032_clk_gate_enable(struct clk_hw *hw)
+{
+	struct r9a06g032_clk_gate *g = to_r9a06g032_gate(hw);
+
+	r9a06g032_clk_gate_set(g->clocks, &g->gate, 1);
+	return 0;
+}
+
+static void r9a06g032_clk_gate_disable(struct clk_hw *hw)
+{
+	struct r9a06g032_clk_gate *g = to_r9a06g032_gate(hw);
+
+	r9a06g032_clk_gate_set(g->clocks, &g->gate, 0);
+}
+
+static int r9a06g032_clk_gate_is_enabled(struct clk_hw *hw)
+{
+	struct r9a06g032_clk_gate *g = to_r9a06g032_gate(hw);
+
+	/* if clock is in reset, the gate might be on, and still not 'be' on */
+	if (g->gate.reset && !clk_rdesc_get(g->clocks, g->gate.reset))
+		return 0;
+
+	return clk_rdesc_get(g->clocks, g->gate.gate);
+}
+
+static const struct clk_ops r9a06g032_clk_gate_ops = {
+	.enable = r9a06g032_clk_gate_enable,
+	.disable = r9a06g032_clk_gate_disable,
+	.is_enabled = r9a06g032_clk_gate_is_enabled,
+};
+
+static struct clk *
+r9a06g032_register_gate(struct r9a06g032_priv *clocks,
+			const char *parent_name,
+			const struct r9a06g032_clkdesc *desc)
+{
+	struct clk *clk;
+	struct r9a06g032_clk_gate *g;
+	struct clk_init_data init;
+
+	g = kzalloc(sizeof(*g), GFP_KERNEL);
+	if (!g)
+		return NULL;
+
+	init.name = desc->name;
+	init.ops = &r9a06g032_clk_gate_ops;
+	init.flags = CLK_IS_BASIC | CLK_SET_RATE_PARENT;
+	init.parent_names = parent_name ? &parent_name : NULL;
+	init.num_parents = parent_name ? 1 : 0;
+
+	g->clocks = clocks;
+	g->index = desc->index;
+	g->gate = desc->gate;
+	g->hw.init = &init;
+
+	/*
+	 * important here, some clocks are already in use by the CM3, we
+	 * have to assume they are not Linux's to play with and try to disable
+	 * at the end of the boot!
+	 */
+	if (r9a06g032_clk_gate_is_enabled(&g->hw)) {
+		init.flags |= CLK_IS_CRITICAL;
+		pr_debug("%s was enabled, making read-only\n", desc->name);
+	}
+
+	clk = clk_register(NULL, &g->hw);
+	if (IS_ERR(clk)) {
+		kfree(g);
+		return NULL;
+	}
+	return clk;
+}
+
+struct r9a06g032_clk_div {
+	struct clk_hw hw;
+	struct r9a06g032_priv *clocks;
+	u16 index;
+	u16 reg;
+	u16 min, max;
+	u8 table_size;
+	u16 table[8];	/* we know there are no more than 8 */
+};
+
+#define to_r9a06g032_div(_hw) \
+		container_of(_hw, struct r9a06g032_clk_div, hw)
+
+static unsigned long
+r9a06g032_div_recalc_rate(struct clk_hw *hw,
+			  unsigned long parent_rate)
+{
+	struct r9a06g032_clk_div *clk = to_r9a06g032_div(hw);
+	u32 __iomem *reg = clk->clocks->reg + (4 * clk->reg);
+	u32 div = readl(reg);
+
+	if (div < clk->min)
+		div = clk->min;
+	else if (div > clk->max)
+		div = clk->max;
+	return DIV_ROUND_UP(parent_rate, div);
+}
+
+/*
+ * Attempts to find a value that is in range of min,max,
+ * and if a table of set dividers was specified for this
+ * register, try to find the fixed divider that is the closest
+ * to the target frequency
+ */
+static long
+r9a06g032_div_clamp_div(struct r9a06g032_clk_div *clk,
+			unsigned long rate, unsigned long prate)
+{
+	/* + 1 to cope with rates that have the remainder dropped */
+	u32 div = DIV_ROUND_UP(prate, rate + 1);
+	int i;
+
+	if (div <= clk->min)
+		return clk->min;
+	if (div >= clk->max)
+		return clk->max;
+
+	for (i = 0; clk->table_size && i < clk->table_size - 1; i++) {
+		if (div >= clk->table[i] && div <= clk->table[i + 1]) {
+			unsigned long m = rate -
+				DIV_ROUND_UP(prate, clk->table[i]);
+			unsigned long p =
+				DIV_ROUND_UP(prate, clk->table[i + 1]) -
+				rate;
+			/*
+			 * select the divider that generates
+			 * the value closest to the ideal frequency
+			 */
+			div = p >= m ? clk->table[i] : clk->table[i + 1];
+			return div;
+		}
+	}
+	return div;
+}
+
+static long
+r9a06g032_div_round_rate(struct clk_hw *hw,
+			 unsigned long rate, unsigned long *prate)
+{
+	struct r9a06g032_clk_div *clk = to_r9a06g032_div(hw);
+	u32 div = DIV_ROUND_UP(*prate, rate);
+
+	pr_devel("%s %pC %ld (prate %ld) (wanted div %u)\n", __func__,
+		 hw->clk, rate, *prate, div);
+	pr_devel("   min %d (%ld) max %d (%ld)\n",
+		 clk->min, DIV_ROUND_UP(*prate, clk->min),
+		clk->max, DIV_ROUND_UP(*prate, clk->max));
+
+	div = r9a06g032_div_clamp_div(clk, rate, *prate);
+	/*
+	 * this is a hack. Currently the serial driver asks for a clock rate
+	 * that is 16 times the baud rate -- and that is wildly outside the
+	 * range of the UART divider, somehow there is no provision for that
+	 * case of 'let the divider as is if outside range'.
+	 * The serial driver *shouldn't* play with these clocks anyway, there's
+	 * several uarts attached to this divider, and changing this impacts
+	 * everyone.
+	 */
+	if (clk->index == R9A06G032_DIV_UART) {
+		pr_devel("%s div uart hack!\n", __func__);
+		return clk_get_rate(hw->clk);
+	}
+	pr_devel("%s %pC %ld / %u = %ld\n", __func__, hw->clk,
+		 *prate, div, DIV_ROUND_UP(*prate, div));
+	return DIV_ROUND_UP(*prate, div);
+}
+
+static int
+r9a06g032_div_set_rate(struct clk_hw *hw,
+		       unsigned long rate, unsigned long parent_rate)
+{
+	struct r9a06g032_clk_div *clk = to_r9a06g032_div(hw);
+	/* + 1 to cope with rates that have the remainder dropped */
+	u32 div = DIV_ROUND_UP(parent_rate, rate + 1);
+	u32 __iomem *reg = clk->clocks->reg + (4 * clk->reg);
+
+	pr_devel("%s %pC rate %ld parent %ld div %d\n", __func__, hw->clk,
+		 rate, parent_rate, div);
+
+	/*
+	 * Need to write the bit 31 with the divider value to
+	 * latch it. Technically we should wait until it has been
+	 * cleared too.
+	 * TODO: Find whether this callback is sleepable, in case
+	 * the hardware /does/ require some sort of spinloop here.
+	 */
+	writel(div | BIT(31), reg);
+
+	return 0;
+}
+
+static const struct clk_ops r9a06g032_clk_div_ops = {
+	.recalc_rate = r9a06g032_div_recalc_rate,
+	.round_rate = r9a06g032_div_round_rate,
+	.set_rate = r9a06g032_div_set_rate,
+};
+
+static struct clk *
+r9a06g032_register_div(struct r9a06g032_priv *clocks,
+		       const char *parent_name,
+		       const struct r9a06g032_clkdesc *desc)
+{
+	struct r9a06g032_clk_div *div;
+	struct clk *clk;
+	struct clk_init_data init;
+	unsigned int i;
+
+	div = kzalloc(sizeof(*div), GFP_KERNEL);
+	if (!div)
+		return NULL;
+
+	init.name = desc->name;
+	init.ops = &r9a06g032_clk_div_ops;
+	init.flags = CLK_IS_BASIC | CLK_SET_RATE_PARENT;
+	init.parent_names = parent_name ? &parent_name : NULL;
+	init.num_parents = parent_name ? 1 : 0;
+
+	div->clocks = clocks;
+	div->index = desc->index;
+	div->reg = desc->reg;
+	div->hw.init = &init;
+	div->min = desc->div_min;
+	div->max = desc->div_max;
+	/* populate (optional) divider table fixed values */
+	for (i = 0; i < ARRAY_SIZE(div->table) &&
+	     i < ARRAY_SIZE(desc->div_table) && desc->div_table[i]; i++) {
+		div->table[div->table_size++] = desc->div_table[i];
+	}
+
+	clk = clk_register(NULL, &div->hw);
+	if (IS_ERR(clk)) {
+		kfree(div);
+		return NULL;
+	}
+	return clk;
+}
+
+/*
+ * This clock provider handles the case of the R9A06G032 where you have
+ * peripherals that have two potential clock source and two gates, one for
+ * each of the clock source - the used clock source (for all sub clocks)
+ * is selected by a single bit.
+ * That single bit affects all sub-clocks, and therefore needs to change the
+ * active gate (and turn the others off) and force a recalculation of the rates.
+ *
+ * This implements two clock providers, one 'bitselect' that
+ * handles the switch between both parents, and another 'dualgate'
+ * that knows which gate to poke at, depending on the parent's bit position.
+ */
+struct r9a06g032_clk_bitsel {
+	struct clk_hw	hw;
+	struct r9a06g032_priv *clocks;
+	u16 index;
+	u16 selector;		/* selector register + bit */
+};
+
+#define to_clk_bitselect(_hw) \
+		container_of(_hw, struct r9a06g032_clk_bitsel, hw)
+
+static u8 r9a06g032_clk_mux_get_parent(struct clk_hw *hw)
+{
+	struct r9a06g032_clk_bitsel *set = to_clk_bitselect(hw);
+
+	return clk_rdesc_get(set->clocks, set->selector);
+}
+
+static int r9a06g032_clk_mux_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct r9a06g032_clk_bitsel *set = to_clk_bitselect(hw);
+
+	/* a single bit in the register selects one of two parent clocks */
+	clk_rdesc_set(set->clocks, set->selector, !!index);
+
+	return 0;
+}
+
+static const struct clk_ops clk_bitselect_ops = {
+	.get_parent = r9a06g032_clk_mux_get_parent,
+	.set_parent = r9a06g032_clk_mux_set_parent,
+};
+
+static struct clk *
+r9a06g032_register_bitsel(struct r9a06g032_priv *clocks,
+			  const char *parent_name,
+			  const struct r9a06g032_clkdesc *desc)
+{
+	struct clk *clk;
+	struct r9a06g032_clk_bitsel *g;
+	struct clk_init_data init;
+	const char *names[2];
+
+	/* allocate the gate */
+	g = kzalloc(sizeof(*g), GFP_KERNEL);
+	if (!g)
+		return NULL;
+
+	names[0] = parent_name;
+	names[1] = "clk_pll_usb";
+
+	init.name = desc->name;
+	init.ops = &clk_bitselect_ops;
+	init.flags = CLK_IS_BASIC | CLK_SET_RATE_PARENT;
+	init.parent_names = names;
+	init.num_parents = 2;
+
+	g->clocks = clocks;
+	g->index = desc->index;
+	g->selector = desc->dual.sel;
+	g->hw.init = &init;
+
+	clk = clk_register(NULL, &g->hw);
+	if (IS_ERR(clk)) {
+		kfree(g);
+		return NULL;
+	}
+	return clk;
+}
+
+struct r9a06g032_clk_dualgate {
+	struct clk_hw	hw;
+	struct r9a06g032_priv *clocks;
+	u16 index;
+	u16 selector;		/* selector register + bit */
+	struct r9a06g032_gate gate[2];
+};
+
+#define to_clk_dualgate(_hw) \
+		container_of(_hw, struct r9a06g032_clk_dualgate, hw)
+
+static int
+r9a06g032_clk_dualgate_setenable(struct r9a06g032_clk_dualgate *g, int enable)
+{
+	u8 sel_bit = clk_rdesc_get(g->clocks, g->selector);
+
+	/* we always turn off the 'other' gate, regardless */
+	r9a06g032_clk_gate_set(g->clocks, &g->gate[!sel_bit], 0);
+	r9a06g032_clk_gate_set(g->clocks, &g->gate[sel_bit], enable);
+
+	return 0;
+}
+
+static int r9a06g032_clk_dualgate_enable(struct clk_hw *hw)
+{
+	struct r9a06g032_clk_dualgate *gate = to_clk_dualgate(hw);
+
+	r9a06g032_clk_dualgate_setenable(gate, 1);
+
+	return 0;
+}
+
+static void r9a06g032_clk_dualgate_disable(struct clk_hw *hw)
+{
+	struct r9a06g032_clk_dualgate *gate = to_clk_dualgate(hw);
+
+	r9a06g032_clk_dualgate_setenable(gate, 0);
+}
+
+static int r9a06g032_clk_dualgate_is_enabled(struct clk_hw *hw)
+{
+	struct r9a06g032_clk_dualgate *g = to_clk_dualgate(hw);
+	u8 sel_bit = clk_rdesc_get(g->clocks, g->selector);
+
+	return clk_rdesc_get(g->clocks, g->gate[sel_bit].gate);
+}
+
+static const struct clk_ops r9a06g032_clk_dualgate_ops = {
+	.enable = r9a06g032_clk_dualgate_enable,
+	.disable = r9a06g032_clk_dualgate_disable,
+	.is_enabled = r9a06g032_clk_dualgate_is_enabled,
+};
+
+static struct clk *
+r9a06g032_register_dualgate(struct r9a06g032_priv *clocks,
+			    const char *parent_name,
+			    const struct r9a06g032_clkdesc *desc,
+			    uint16_t sel)
+{
+	struct r9a06g032_clk_dualgate *g;
+	struct clk *clk;
+	struct clk_init_data init;
+
+	/* allocate the gate */
+	g = kzalloc(sizeof(*g), GFP_KERNEL);
+	if (!g)
+		return NULL;
+	g->clocks = clocks;
+	g->index = desc->index;
+	g->selector = sel;
+	g->gate[0].gate = desc->dual.g1;
+	g->gate[0].reset = desc->dual.r1;
+	g->gate[1].gate = desc->dual.g2;
+	g->gate[1].reset = desc->dual.r2;
+
+	init.name = desc->name;
+	init.ops = &r9a06g032_clk_dualgate_ops;
+	init.flags = CLK_IS_BASIC | CLK_SET_RATE_PARENT;
+	init.parent_names = &parent_name;
+	init.num_parents = 1;
+	g->hw.init = &init;
+	/*
+	 * important here, some clocks are already in use by the CM3, we
+	 * have to assume they are not Linux's to play with and try to disable
+	 * at the end of the boot!
+	 */
+	if (r9a06g032_clk_dualgate_is_enabled(&g->hw)) {
+		init.flags |= CLK_IS_CRITICAL;
+		pr_debug("%s was enabled, making read-only\n", desc->name);
+	}
+
+	clk = clk_register(NULL, &g->hw);
+	if (IS_ERR(clk)) {
+		kfree(g);
+		return NULL;
+	}
+	return clk;
+}
+
+static void r9a06g032_clocks_del_clk_provider(void *data)
+{
+	of_clk_del_provider(data);
+}
+
+static int __init r9a06g032_clocks_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct r9a06g032_priv *clocks;
+	struct clk **clks;
+	struct clk *mclk;
+	unsigned int i;
+	u16 uart_group_sel[2];
+	int error;
+
+	clocks = devm_kzalloc(dev, sizeof(*clocks), GFP_KERNEL);
+	clks = devm_kcalloc(dev, R9A06G032_CLOCK_COUNT, sizeof(struct clk *),
+			    GFP_KERNEL);
+	if (!clocks || !clks)
+		return -ENOMEM;
+
+	spin_lock_init(&clocks->lock);
+
+	clocks->data.clks = clks;
+	clocks->data.clk_num = R9A06G032_CLOCK_COUNT;
+
+	mclk = devm_clk_get(dev, "mclk");
+	if (IS_ERR(mclk))
+		return PTR_ERR(mclk);
+
+	clocks->reg = of_iomap(np, 0);
+	if (WARN_ON(!clocks->reg))
+		return -ENOMEM;
+	for (i = 0; i < ARRAY_SIZE(r9a06g032_clocks); ++i) {
+		const struct r9a06g032_clkdesc *d = &r9a06g032_clocks[i];
+		const char *parent_name = d->source ?
+			__clk_get_name(clocks->data.clks[d->source - 1]) :
+			__clk_get_name(mclk);
+		struct clk *clk = NULL;
+
+		switch (d->type) {
+		case K_FFC:
+			clk = clk_register_fixed_factor(NULL, d->name,
+							parent_name, 0,
+							d->mul, d->div);
+			break;
+		case K_GATE:
+			clk = r9a06g032_register_gate(clocks, parent_name, d);
+			break;
+		case K_DIV:
+			clk = r9a06g032_register_div(clocks, parent_name, d);
+			break;
+		case K_BITSEL:
+			/* keep that selector register around */
+			uart_group_sel[d->dual.group] = d->dual.sel;
+			clk = r9a06g032_register_bitsel(clocks, parent_name, d);
+			break;
+		case K_DUALGATE:
+			clk = r9a06g032_register_dualgate(clocks, parent_name,
+							  d,
+							  uart_group_sel[d->dual.group]);
+			break;
+		}
+		clocks->data.clks[d->index] = clk;
+	}
+	error = of_clk_add_provider(np, of_clk_src_onecell_get, &clocks->data);
+	if (error)
+		return error;
+
+	return devm_add_action_or_reset(dev,
+					r9a06g032_clocks_del_clk_provider, np);
+}
+
+static const struct of_device_id r9a06g032_match[] = {
+	{ .compatible = "renesas,r9a06g032-sysctrl" },
+	{ }
+};
+
+static struct platform_driver r9a06g032_clock_driver = {
+	.driver		= {
+		.name	= "renesas,r9a06g032-sysctrl",
+		.of_match_table = r9a06g032_match,
+	},
+};
+
+static int __init r9a06g032_clocks_init(void)
+{
+	return platform_driver_probe(&r9a06g032_clock_driver,
+			r9a06g032_clocks_probe);
+}
+
+subsys_initcall(r9a06g032_clocks_init);
diff --git a/drivers/clk/rockchip/Makefile b/drivers/clk/rockchip/Makefile
index 98e7b9429b83..ff35ab463a6f 100644
--- a/drivers/clk/rockchip/Makefile
+++ b/drivers/clk/rockchip/Makefile
@@ -6,12 +6,14 @@
 obj-y	+= clk.o
 obj-y	+= clk-pll.o
 obj-y	+= clk-cpu.o
+obj-y	+= clk-half-divider.o
 obj-y	+= clk-inverter.o
 obj-y	+= clk-mmc-phase.o
 obj-y	+= clk-muxgrf.o
 obj-y	+= clk-ddr.o
 obj-$(CONFIG_RESET_CONTROLLER)	+= softrst.o
 
+obj-y	+= clk-px30.o
 obj-y	+= clk-rv1108.o
 obj-y	+= clk-rk3036.o
 obj-y	+= clk-rk3128.o
diff --git a/drivers/clk/rockchip/clk-half-divider.c b/drivers/clk/rockchip/clk-half-divider.c
new file mode 100644
index 000000000000..b8da6e799423
--- /dev/null
+++ b/drivers/clk/rockchip/clk-half-divider.c
@@ -0,0 +1,227 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 Fuzhou Rockchip Electronics Co., Ltd
+ */
+
+#include <linux/slab.h>
+#include <linux/clk-provider.h>
+#include "clk.h"
+
+#define div_mask(width)	((1 << (width)) - 1)
+
+static bool _is_best_half_div(unsigned long rate, unsigned long now,
+			      unsigned long best, unsigned long flags)
+{
+	if (flags & CLK_DIVIDER_ROUND_CLOSEST)
+		return abs(rate - now) < abs(rate - best);
+
+	return now <= rate && now > best;
+}
+
+static unsigned long clk_half_divider_recalc_rate(struct clk_hw *hw,
+						  unsigned long parent_rate)
+{
+	struct clk_divider *divider = to_clk_divider(hw);
+	unsigned int val;
+
+	val = clk_readl(divider->reg) >> divider->shift;
+	val &= div_mask(divider->width);
+	val = val * 2 + 3;
+
+	return DIV_ROUND_UP_ULL(((u64)parent_rate * 2), val);
+}
+
+static int clk_half_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
+				    unsigned long *best_parent_rate, u8 width,
+				    unsigned long flags)
+{
+	unsigned int i, bestdiv = 0;
+	unsigned long parent_rate, best = 0, now, maxdiv;
+	unsigned long parent_rate_saved = *best_parent_rate;
+
+	if (!rate)
+		rate = 1;
+
+	maxdiv = div_mask(width);
+
+	if (!(clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT)) {
+		parent_rate = *best_parent_rate;
+		bestdiv = DIV_ROUND_UP_ULL(((u64)parent_rate * 2), rate);
+		if (bestdiv < 3)
+			bestdiv = 0;
+		else
+			bestdiv = (bestdiv - 3) / 2;
+		bestdiv = bestdiv > maxdiv ? maxdiv : bestdiv;
+		return bestdiv;
+	}
+
+	/*
+	 * The maximum divider we can use without overflowing
+	 * unsigned long in rate * i below
+	 */
+	maxdiv = min(ULONG_MAX / rate, maxdiv);
+
+	for (i = 0; i <= maxdiv; i++) {
+		if (((u64)rate * (i * 2 + 3)) == ((u64)parent_rate_saved * 2)) {
+			/*
+			 * It's the most ideal case if the requested rate can be
+			 * divided from parent clock without needing to change
+			 * parent rate, so return the divider immediately.
+			 */
+			*best_parent_rate = parent_rate_saved;
+			return i;
+		}
+		parent_rate = clk_hw_round_rate(clk_hw_get_parent(hw),
+						((u64)rate * (i * 2 + 3)) / 2);
+		now = DIV_ROUND_UP_ULL(((u64)parent_rate * 2),
+				       (i * 2 + 3));
+
+		if (_is_best_half_div(rate, now, best, flags)) {
+			bestdiv = i;
+			best = now;
+			*best_parent_rate = parent_rate;
+		}
+	}
+
+	if (!bestdiv) {
+		bestdiv = div_mask(width);
+		*best_parent_rate = clk_hw_round_rate(clk_hw_get_parent(hw), 1);
+	}
+
+	return bestdiv;
+}
+
+static long clk_half_divider_round_rate(struct clk_hw *hw, unsigned long rate,
+					unsigned long *prate)
+{
+	struct clk_divider *divider = to_clk_divider(hw);
+	int div;
+
+	div = clk_half_divider_bestdiv(hw, rate, prate,
+				       divider->width,
+				       divider->flags);
+
+	return DIV_ROUND_UP_ULL(((u64)*prate * 2), div * 2 + 3);
+}
+
+static int clk_half_divider_set_rate(struct clk_hw *hw, unsigned long rate,
+				     unsigned long parent_rate)
+{
+	struct clk_divider *divider = to_clk_divider(hw);
+	unsigned int value;
+	unsigned long flags = 0;
+	u32 val;
+
+	value = DIV_ROUND_UP_ULL(((u64)parent_rate * 2), rate);
+	value = (value - 3) / 2;
+	value =  min_t(unsigned int, value, div_mask(divider->width));
+
+	if (divider->lock)
+		spin_lock_irqsave(divider->lock, flags);
+	else
+		__acquire(divider->lock);
+
+	if (divider->flags & CLK_DIVIDER_HIWORD_MASK) {
+		val = div_mask(divider->width) << (divider->shift + 16);
+	} else {
+		val = clk_readl(divider->reg);
+		val &= ~(div_mask(divider->width) << divider->shift);
+	}
+	val |= value << divider->shift;
+	clk_writel(val, divider->reg);
+
+	if (divider->lock)
+		spin_unlock_irqrestore(divider->lock, flags);
+	else
+		__release(divider->lock);
+
+	return 0;
+}
+
+const struct clk_ops clk_half_divider_ops = {
+	.recalc_rate = clk_half_divider_recalc_rate,
+	.round_rate = clk_half_divider_round_rate,
+	.set_rate = clk_half_divider_set_rate,
+};
+EXPORT_SYMBOL_GPL(clk_half_divider_ops);
+
+/**
+ * Register a clock branch.
+ * Most clock branches have a form like
+ *
+ * src1 --|--\
+ *        |M |--[GATE]-[DIV]-
+ * src2 --|--/
+ *
+ * sometimes without one of those components.
+ */
+struct clk *rockchip_clk_register_halfdiv(const char *name,
+					  const char *const *parent_names,
+					  u8 num_parents, void __iomem *base,
+					  int muxdiv_offset, u8 mux_shift,
+					  u8 mux_width, u8 mux_flags,
+					  u8 div_shift, u8 div_width,
+					  u8 div_flags, int gate_offset,
+					  u8 gate_shift, u8 gate_flags,
+					  unsigned long flags,
+					  spinlock_t *lock)
+{
+	struct clk *clk;
+	struct clk_mux *mux = NULL;
+	struct clk_gate *gate = NULL;
+	struct clk_divider *div = NULL;
+	const struct clk_ops *mux_ops = NULL, *div_ops = NULL,
+			     *gate_ops = NULL;
+
+	if (num_parents > 1) {
+		mux = kzalloc(sizeof(*mux), GFP_KERNEL);
+		if (!mux)
+			return ERR_PTR(-ENOMEM);
+
+		mux->reg = base + muxdiv_offset;
+		mux->shift = mux_shift;
+		mux->mask = BIT(mux_width) - 1;
+		mux->flags = mux_flags;
+		mux->lock = lock;
+		mux_ops = (mux_flags & CLK_MUX_READ_ONLY) ? &clk_mux_ro_ops
+							: &clk_mux_ops;
+	}
+
+	if (gate_offset >= 0) {
+		gate = kzalloc(sizeof(*gate), GFP_KERNEL);
+		if (!gate)
+			goto err_gate;
+
+		gate->flags = gate_flags;
+		gate->reg = base + gate_offset;
+		gate->bit_idx = gate_shift;
+		gate->lock = lock;
+		gate_ops = &clk_gate_ops;
+	}
+
+	if (div_width > 0) {
+		div = kzalloc(sizeof(*div), GFP_KERNEL);
+		if (!div)
+			goto err_div;
+
+		div->flags = div_flags;
+		div->reg = base + muxdiv_offset;
+		div->shift = div_shift;
+		div->width = div_width;
+		div->lock = lock;
+		div_ops = &clk_half_divider_ops;
+	}
+
+	clk = clk_register_composite(NULL, name, parent_names, num_parents,
+				     mux ? &mux->hw : NULL, mux_ops,
+				     div ? &div->hw : NULL, div_ops,
+				     gate ? &gate->hw : NULL, gate_ops,
+				     flags);
+
+	return clk;
+err_div:
+	kfree(gate);
+err_gate:
+	kfree(mux);
+	return ERR_PTR(-ENOMEM);
+}
diff --git a/drivers/clk/rockchip/clk-px30.c b/drivers/clk/rockchip/clk-px30.c
new file mode 100644
index 000000000000..601a77f1af78
--- /dev/null
+++ b/drivers/clk/rockchip/clk-px30.c
@@ -0,0 +1,1039 @@
+/*
+ * Copyright (c) 2018 Rockchip Electronics Co. Ltd.
+ * Author: Elaine Zhang<zhangqing@rock-chips.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/syscore_ops.h>
+#include <dt-bindings/clock/px30-cru.h>
+#include "clk.h"
+
+#define PX30_GRF_SOC_STATUS0		0x480
+
+enum px30_plls {
+	apll, dpll, cpll, npll, apll_b_h, apll_b_l,
+};
+
+enum px30_pmu_plls {
+	gpll,
+};
+
+static struct rockchip_pll_rate_table px30_pll_rates[] = {
+	/* _mhz, _refdiv, _fbdiv, _postdiv1, _postdiv2, _dsmpd, _frac */
+	RK3036_PLL_RATE(1608000000, 1, 67, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1584000000, 1, 66, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1560000000, 1, 65, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1536000000, 1, 64, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1512000000, 1, 63, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1488000000, 1, 62, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1464000000, 1, 61, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1440000000, 1, 60, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1416000000, 1, 59, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1392000000, 1, 58, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1368000000, 1, 57, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1344000000, 1, 56, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1320000000, 1, 55, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1296000000, 1, 54, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1272000000, 1, 53, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1248000000, 1, 52, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1200000000, 1, 50, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1188000000, 2, 99, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1104000000, 1, 46, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1100000000, 12, 550, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1008000000, 1, 84, 2, 1, 1, 0),
+	RK3036_PLL_RATE(1000000000, 6, 500, 2, 1, 1, 0),
+	RK3036_PLL_RATE(984000000, 1, 82, 2, 1, 1, 0),
+	RK3036_PLL_RATE(960000000, 1, 80, 2, 1, 1, 0),
+	RK3036_PLL_RATE(936000000, 1, 78, 2, 1, 1, 0),
+	RK3036_PLL_RATE(912000000, 1, 76, 2, 1, 1, 0),
+	RK3036_PLL_RATE(900000000, 4, 300, 2, 1, 1, 0),
+	RK3036_PLL_RATE(888000000, 1, 74, 2, 1, 1, 0),
+	RK3036_PLL_RATE(864000000, 1, 72, 2, 1, 1, 0),
+	RK3036_PLL_RATE(840000000, 1, 70, 2, 1, 1, 0),
+	RK3036_PLL_RATE(816000000, 1, 68, 2, 1, 1, 0),
+	RK3036_PLL_RATE(800000000, 6, 400, 2, 1, 1, 0),
+	RK3036_PLL_RATE(700000000, 6, 350, 2, 1, 1, 0),
+	RK3036_PLL_RATE(696000000, 1, 58, 2, 1, 1, 0),
+	RK3036_PLL_RATE(624000000, 1, 52, 2, 1, 1, 0),
+	RK3036_PLL_RATE(600000000, 1, 75, 3, 1, 1, 0),
+	RK3036_PLL_RATE(594000000, 2, 99, 2, 1, 1, 0),
+	RK3036_PLL_RATE(504000000, 1, 63, 3, 1, 1, 0),
+	RK3036_PLL_RATE(500000000, 6, 250, 2, 1, 1, 0),
+	RK3036_PLL_RATE(408000000, 1, 68, 2, 2, 1, 0),
+	RK3036_PLL_RATE(312000000, 1, 52, 2, 2, 1, 0),
+	RK3036_PLL_RATE(216000000, 1, 72, 4, 2, 1, 0),
+	RK3036_PLL_RATE(96000000, 1, 64, 4, 4, 1, 0),
+	{ /* sentinel */ },
+};
+
+#define PX30_DIV_ACLKM_MASK		0x7
+#define PX30_DIV_ACLKM_SHIFT		12
+#define PX30_DIV_PCLK_DBG_MASK	0xf
+#define PX30_DIV_PCLK_DBG_SHIFT	8
+
+#define PX30_CLKSEL0(_aclk_core, _pclk_dbg)				\
+{									\
+	.reg = PX30_CLKSEL_CON(0),					\
+	.val = HIWORD_UPDATE(_aclk_core, PX30_DIV_ACLKM_MASK,		\
+			     PX30_DIV_ACLKM_SHIFT) |			\
+	       HIWORD_UPDATE(_pclk_dbg, PX30_DIV_PCLK_DBG_MASK,	\
+			     PX30_DIV_PCLK_DBG_SHIFT),		\
+}
+
+#define PX30_CPUCLK_RATE(_prate, _aclk_core, _pclk_dbg)		\
+{									\
+	.prate = _prate,						\
+	.divs = {							\
+		PX30_CLKSEL0(_aclk_core, _pclk_dbg),			\
+	},								\
+}
+
+static struct rockchip_cpuclk_rate_table px30_cpuclk_rates[] __initdata = {
+	PX30_CPUCLK_RATE(1608000000, 1, 7),
+	PX30_CPUCLK_RATE(1584000000, 1, 7),
+	PX30_CPUCLK_RATE(1560000000, 1, 7),
+	PX30_CPUCLK_RATE(1536000000, 1, 7),
+	PX30_CPUCLK_RATE(1512000000, 1, 7),
+	PX30_CPUCLK_RATE(1488000000, 1, 5),
+	PX30_CPUCLK_RATE(1464000000, 1, 5),
+	PX30_CPUCLK_RATE(1440000000, 1, 5),
+	PX30_CPUCLK_RATE(1416000000, 1, 5),
+	PX30_CPUCLK_RATE(1392000000, 1, 5),
+	PX30_CPUCLK_RATE(1368000000, 1, 5),
+	PX30_CPUCLK_RATE(1344000000, 1, 5),
+	PX30_CPUCLK_RATE(1320000000, 1, 5),
+	PX30_CPUCLK_RATE(1296000000, 1, 5),
+	PX30_CPUCLK_RATE(1272000000, 1, 5),
+	PX30_CPUCLK_RATE(1248000000, 1, 5),
+	PX30_CPUCLK_RATE(1224000000, 1, 5),
+	PX30_CPUCLK_RATE(1200000000, 1, 5),
+	PX30_CPUCLK_RATE(1104000000, 1, 5),
+	PX30_CPUCLK_RATE(1008000000, 1, 5),
+	PX30_CPUCLK_RATE(912000000, 1, 5),
+	PX30_CPUCLK_RATE(816000000, 1, 3),
+	PX30_CPUCLK_RATE(696000000, 1, 3),
+	PX30_CPUCLK_RATE(600000000, 1, 3),
+	PX30_CPUCLK_RATE(408000000, 1, 1),
+	PX30_CPUCLK_RATE(312000000, 1, 1),
+	PX30_CPUCLK_RATE(216000000,  1, 1),
+	PX30_CPUCLK_RATE(96000000, 1, 1),
+};
+
+static const struct rockchip_cpuclk_reg_data px30_cpuclk_data = {
+	.core_reg = PX30_CLKSEL_CON(0),
+	.div_core_shift = 0,
+	.div_core_mask = 0xf,
+	.mux_core_alt = 1,
+	.mux_core_main = 0,
+	.mux_core_shift = 7,
+	.mux_core_mask = 0x1,
+};
+
+PNAME(mux_pll_p)		= { "xin24m"};
+PNAME(mux_usb480m_p)		= { "xin24m", "usb480m_phy", "clk_rtc32k_pmu" };
+PNAME(mux_armclk_p)		= { "apll_core", "gpll_core" };
+PNAME(mux_ddrphy_p)		= { "dpll_ddr", "gpll_ddr" };
+PNAME(mux_ddrstdby_p)		= { "clk_ddrphy1x", "clk_stdby_2wrap" };
+PNAME(mux_4plls_p)		= { "gpll", "dummy_cpll", "usb480m", "npll" };
+PNAME(mux_cpll_npll_p)		= { "cpll", "npll" };
+PNAME(mux_npll_cpll_p)		= { "npll", "cpll" };
+PNAME(mux_gpll_cpll_p)		= { "gpll", "dummy_cpll" };
+PNAME(mux_gpll_npll_p)		= { "gpll", "npll" };
+PNAME(mux_gpll_xin24m_p)		= { "gpll", "xin24m"};
+PNAME(mux_gpll_cpll_npll_p)		= { "gpll", "dummy_cpll", "npll" };
+PNAME(mux_gpll_cpll_npll_xin24m_p)	= { "gpll", "dummy_cpll", "npll", "xin24m" };
+PNAME(mux_gpll_xin24m_npll_p)		= { "gpll", "xin24m", "npll"};
+PNAME(mux_pdm_p)		= { "clk_pdm_src", "clk_pdm_frac" };
+PNAME(mux_i2s0_tx_p)		= { "clk_i2s0_tx_src", "clk_i2s0_tx_frac", "mclk_i2s0_tx_in", "xin12m"};
+PNAME(mux_i2s0_rx_p)		= { "clk_i2s0_rx_src", "clk_i2s0_rx_frac", "mclk_i2s0_rx_in", "xin12m"};
+PNAME(mux_i2s1_p)		= { "clk_i2s1_src", "clk_i2s1_frac", "i2s1_clkin", "xin12m"};
+PNAME(mux_i2s2_p)		= { "clk_i2s2_src", "clk_i2s2_frac", "i2s2_clkin", "xin12m"};
+PNAME(mux_i2s0_tx_out_p)	= { "clk_i2s0_tx", "xin12m", "clk_i2s0_rx"};
+PNAME(mux_i2s0_rx_out_p)	= { "clk_i2s0_rx", "xin12m", "clk_i2s0_tx"};
+PNAME(mux_i2s1_out_p)		= { "clk_i2s1", "xin12m"};
+PNAME(mux_i2s2_out_p)		= { "clk_i2s2", "xin12m"};
+PNAME(mux_i2s0_tx_rx_p)		= { "clk_i2s0_tx_mux", "clk_i2s0_rx_mux"};
+PNAME(mux_i2s0_rx_tx_p)		= { "clk_i2s0_rx_mux", "clk_i2s0_tx_mux"};
+PNAME(mux_uart_src_p)		= { "gpll", "xin24m", "usb480m", "npll" };
+PNAME(mux_uart1_p)		= { "clk_uart1_src", "clk_uart1_np5", "clk_uart1_frac" };
+PNAME(mux_uart2_p)		= { "clk_uart2_src", "clk_uart2_np5", "clk_uart2_frac" };
+PNAME(mux_uart3_p)		= { "clk_uart3_src", "clk_uart3_np5", "clk_uart3_frac" };
+PNAME(mux_uart4_p)		= { "clk_uart4_src", "clk_uart4_np5", "clk_uart4_frac" };
+PNAME(mux_uart5_p)		= { "clk_uart5_src", "clk_uart5_np5", "clk_uart5_frac" };
+PNAME(mux_cif_out_p)		= { "xin24m", "dummy_cpll", "npll", "usb480m" };
+PNAME(mux_dclk_vopb_p)		= { "dclk_vopb_src", "dclk_vopb_frac", "xin24m" };
+PNAME(mux_dclk_vopl_p)		= { "dclk_vopl_src", "dclk_vopl_frac", "xin24m" };
+PNAME(mux_gmac_p)		= { "clk_gmac_src", "gmac_clkin" };
+PNAME(mux_gmac_rmii_sel_p)	= { "clk_gmac_rx_tx_div20", "clk_gmac_rx_tx_div2" };
+PNAME(mux_rtc32k_pmu_p)		= { "xin32k", "pmu_pvtm_32k", "clk_rtc32k_frac", };
+PNAME(mux_wifi_pmu_p)		= { "xin24m", "clk_wifi_pmu_src" };
+PNAME(mux_uart0_pmu_p)		= { "clk_uart0_pmu_src", "clk_uart0_np5", "clk_uart0_frac" };
+PNAME(mux_usbphy_ref_p)		= { "xin24m", "clk_ref24m_pmu" };
+PNAME(mux_mipidsiphy_ref_p)	= { "xin24m", "clk_ref24m_pmu" };
+PNAME(mux_gpu_p)		= { "clk_gpu_div", "clk_gpu_np5" };
+
+static struct rockchip_pll_clock px30_pll_clks[] __initdata = {
+	[apll] = PLL(pll_rk3328, PLL_APLL, "apll", mux_pll_p,
+		     0, PX30_PLL_CON(0),
+		     PX30_MODE_CON, 0, 0, 0, px30_pll_rates),
+	[dpll] = PLL(pll_rk3328, PLL_DPLL, "dpll", mux_pll_p,
+		     0, PX30_PLL_CON(8),
+		     PX30_MODE_CON, 4, 1, 0, NULL),
+	[cpll] = PLL(pll_rk3328, PLL_CPLL, "cpll", mux_pll_p,
+		     0, PX30_PLL_CON(16),
+		     PX30_MODE_CON, 2, 2, 0, px30_pll_rates),
+	[npll] = PLL(pll_rk3328, PLL_NPLL, "npll", mux_pll_p,
+		     0, PX30_PLL_CON(24),
+		     PX30_MODE_CON, 6, 4, 0, px30_pll_rates),
+};
+
+static struct rockchip_pll_clock px30_pmu_pll_clks[] __initdata = {
+	[gpll] = PLL(pll_rk3328, PLL_GPLL, "gpll",  mux_pll_p, 0, PX30_PMU_PLL_CON(0),
+		     PX30_PMU_MODE, 0, 3, 0, px30_pll_rates),
+};
+
+#define MFLAGS CLK_MUX_HIWORD_MASK
+#define DFLAGS CLK_DIVIDER_HIWORD_MASK
+#define GFLAGS (CLK_GATE_HIWORD_MASK | CLK_GATE_SET_TO_DISABLE)
+
+static struct rockchip_clk_branch px30_pdm_fracmux __initdata =
+	MUX(0, "clk_pdm_mux", mux_pdm_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(26), 15, 1, MFLAGS);
+
+static struct rockchip_clk_branch px30_i2s0_tx_fracmux __initdata =
+	MUX(0, "clk_i2s0_tx_mux", mux_i2s0_tx_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(28), 10, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_i2s0_rx_fracmux __initdata =
+	MUX(0, "clk_i2s0_rx_mux", mux_i2s0_rx_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(58), 10, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_i2s1_fracmux __initdata =
+	MUX(0, "clk_i2s1_mux", mux_i2s1_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(30), 10, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_i2s2_fracmux __initdata =
+	MUX(0, "clk_i2s2_mux", mux_i2s2_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(32), 10, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_uart1_fracmux __initdata =
+	MUX(0, "clk_uart1_mux", mux_uart1_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(35), 14, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_uart2_fracmux __initdata =
+	MUX(0, "clk_uart2_mux", mux_uart2_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(38), 14, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_uart3_fracmux __initdata =
+	MUX(0, "clk_uart3_mux", mux_uart3_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(41), 14, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_uart4_fracmux __initdata =
+	MUX(0, "clk_uart4_mux", mux_uart4_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(44), 14, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_uart5_fracmux __initdata =
+	MUX(0, "clk_uart5_mux", mux_uart5_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(47), 14, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_dclk_vopb_fracmux __initdata =
+	MUX(0, "dclk_vopb_mux", mux_dclk_vopb_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(5), 14, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_dclk_vopl_fracmux __initdata =
+	MUX(0, "dclk_vopl_mux", mux_dclk_vopl_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(8), 14, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_rtc32k_pmu_fracmux __initdata =
+	MUX(SCLK_RTC32K_PMU, "clk_rtc32k_pmu", mux_rtc32k_pmu_p, CLK_SET_RATE_PARENT,
+			PX30_PMU_CLKSEL_CON(0), 14, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_uart0_pmu_fracmux __initdata =
+	MUX(0, "clk_uart0_pmu_mux", mux_uart0_pmu_p, CLK_SET_RATE_PARENT,
+			PX30_PMU_CLKSEL_CON(4), 14, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_clk_branches[] __initdata = {
+	/*
+	 * Clock-Architecture Diagram 1
+	 */
+
+	MUX(USB480M, "usb480m", mux_usb480m_p, CLK_SET_RATE_PARENT,
+			PX30_MODE_CON, 8, 2, MFLAGS),
+	FACTOR(0, "xin12m", "xin24m", 0, 1, 2),
+
+	/*
+	 * Clock-Architecture Diagram 3
+	 */
+
+	/* PD_CORE */
+	GATE(0, "apll_core", "apll", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 0, GFLAGS),
+	GATE(0, "gpll_core", "gpll", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 0, GFLAGS),
+	COMPOSITE_NOMUX(0, "pclk_dbg", "armclk", CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(0), 8, 4, DFLAGS | CLK_DIVIDER_READ_ONLY,
+			PX30_CLKGATE_CON(0), 2, GFLAGS),
+	COMPOSITE_NOMUX(0, "aclk_core", "armclk", CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(0), 12, 3, DFLAGS | CLK_DIVIDER_READ_ONLY,
+			PX30_CLKGATE_CON(0), 1, GFLAGS),
+	GATE(0, "aclk_core_niu", "aclk_core", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 4, GFLAGS),
+	GATE(0, "aclk_core_prf", "aclk_core", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(17), 5, GFLAGS),
+	GATE(0, "pclk_dbg_niu", "pclk_dbg", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 5, GFLAGS),
+	GATE(0, "pclk_core_dbg", "pclk_dbg", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 6, GFLAGS),
+	GATE(0, "pclk_core_grf", "pclk_dbg", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(17), 6, GFLAGS),
+
+	GATE(0, "clk_jtag", "jtag_clkin", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 3, GFLAGS),
+	GATE(SCLK_PVTM, "clk_pvtm", "xin24m", 0,
+			PX30_CLKGATE_CON(17), 4, GFLAGS),
+
+	/* PD_GPU */
+	COMPOSITE_NODIV(0, "clk_gpu_src", mux_4plls_p, 0,
+			PX30_CLKSEL_CON(1), 6, 2, MFLAGS,
+			PX30_CLKGATE_CON(0), 8, GFLAGS),
+	COMPOSITE_NOMUX(0, "clk_gpu_div", "clk_gpu_src", 0,
+			PX30_CLKSEL_CON(1), 0, 4, DFLAGS,
+			PX30_CLKGATE_CON(0), 12, GFLAGS),
+	COMPOSITE_NOMUX_HALFDIV(0, "clk_gpu_np5", "clk_gpu_src", 0,
+			PX30_CLKSEL_CON(1), 8, 4, DFLAGS,
+			PX30_CLKGATE_CON(0), 9, GFLAGS),
+	COMPOSITE_NODIV(SCLK_GPU, "clk_gpu", mux_gpu_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(1), 15, 1, MFLAGS,
+			PX30_CLKGATE_CON(0), 10, GFLAGS),
+	COMPOSITE_NOMUX(0, "aclk_gpu", "clk_gpu", CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(1), 13, 2, DFLAGS,
+			PX30_CLKGATE_CON(17), 10, GFLAGS),
+	GATE(0, "aclk_gpu_niu", "aclk_gpu", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 11, GFLAGS),
+	GATE(0, "aclk_gpu_prf", "aclk_gpu", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(17), 8, GFLAGS),
+	GATE(0, "pclk_gpu_grf", "aclk_gpu", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(17), 9, GFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 4
+	 */
+
+	/* PD_DDR */
+	GATE(0, "dpll_ddr", "dpll", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 7, GFLAGS),
+	GATE(0, "gpll_ddr", "gpll", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 13, GFLAGS),
+	COMPOSITE_NOGATE(SCLK_DDRCLK, "sclk_ddrc", mux_ddrphy_p, CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(2), 7, 1, MFLAGS, 0, 3, DFLAGS | CLK_DIVIDER_POWER_OF_TWO),
+	COMPOSITE_NOGATE(0, "clk_ddrphy4x", mux_ddrphy_p, CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(2), 7, 1, MFLAGS, 0, 3, DFLAGS),
+	FACTOR_GATE(0, "clk_ddrphy1x", "clk_ddrphy4x", CLK_IGNORE_UNUSED, 1, 4,
+			PX30_CLKGATE_CON(0), 14, GFLAGS),
+	FACTOR_GATE(0, "clk_stdby_2wrap", "clk_ddrphy4x", CLK_IGNORE_UNUSED, 1, 4,
+			PX30_CLKGATE_CON(1), 0, GFLAGS),
+	COMPOSITE_NODIV(0, "clk_ddrstdby", mux_ddrstdby_p, CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(2), 4, 1, MFLAGS,
+			PX30_CLKGATE_CON(1), 13, GFLAGS),
+	GATE(0, "aclk_split", "clk_ddrphy1x", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 15, GFLAGS),
+	GATE(0, "clk_msch", "clk_ddrphy1x", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 8, GFLAGS),
+	GATE(0, "aclk_ddrc", "clk_ddrphy1x", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 5, GFLAGS),
+	GATE(0, "clk_core_ddrc", "clk_ddrphy1x", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 6, GFLAGS),
+	GATE(0, "aclk_cmd_buff", "clk_ddrphy1x", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 6, GFLAGS),
+	GATE(0, "clk_ddrmon", "clk_ddrphy1x", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 11, GFLAGS),
+
+	GATE(0, "clk_ddrmon_timer", "xin24m", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 15, GFLAGS),
+
+	COMPOSITE_NOMUX(PCLK_DDR, "pclk_ddr", "gpll", CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(2), 8, 5, DFLAGS,
+			PX30_CLKGATE_CON(1), 1, GFLAGS),
+	GATE(0, "pclk_ddrmon", "pclk_ddr", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 10, GFLAGS),
+	GATE(0, "pclk_ddrc", "pclk_ddr", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 7, GFLAGS),
+	GATE(0, "pclk_msch", "pclk_ddr", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 9, GFLAGS),
+	GATE(0, "pclk_stdby", "pclk_ddr", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 12, GFLAGS),
+	GATE(0, "pclk_ddr_grf", "pclk_ddr", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 14, GFLAGS),
+	GATE(0, "pclk_cmdbuff", "pclk_ddr", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 3, GFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 5
+	 */
+
+	/* PD_VI */
+	COMPOSITE(ACLK_VI_PRE, "aclk_vi_pre", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(11), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(4), 8, GFLAGS),
+	COMPOSITE_NOMUX(HCLK_VI_PRE, "hclk_vi_pre", "aclk_vi_pre", 0,
+			PX30_CLKSEL_CON(11), 8, 4, DFLAGS,
+			PX30_CLKGATE_CON(4), 12, GFLAGS),
+	COMPOSITE(SCLK_ISP, "clk_isp", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(12), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(4), 9, GFLAGS),
+	COMPOSITE(SCLK_CIF_OUT, "clk_cif_out", mux_cif_out_p, 0,
+			PX30_CLKSEL_CON(13), 6, 2, MFLAGS, 0, 6, DFLAGS,
+			PX30_CLKGATE_CON(4), 11, GFLAGS),
+	GATE(PCLK_ISP, "pclkin_isp", "ext_pclkin", 0,
+			PX30_CLKGATE_CON(4), 13, GFLAGS),
+	GATE(PCLK_CIF, "pclkin_cif", "ext_pclkin", 0,
+			PX30_CLKGATE_CON(4), 14, GFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 6
+	 */
+
+	/* PD_VO */
+	COMPOSITE(ACLK_VO_PRE, "aclk_vo_pre", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(3), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(2), 0, GFLAGS),
+	COMPOSITE_NOMUX(HCLK_VO_PRE, "hclk_vo_pre", "aclk_vo_pre", 0,
+			PX30_CLKSEL_CON(3), 8, 4, DFLAGS,
+			PX30_CLKGATE_CON(2), 12, GFLAGS),
+	COMPOSITE_NOMUX(PCLK_VO_PRE, "pclk_vo_pre", "aclk_vo_pre", 0,
+			PX30_CLKSEL_CON(3), 12, 4, DFLAGS,
+			PX30_CLKGATE_CON(2), 13, GFLAGS),
+	COMPOSITE(SCLK_RGA_CORE, "clk_rga_core", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(4), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(2), 1, GFLAGS),
+
+	COMPOSITE(SCLK_VOPB_PWM, "clk_vopb_pwm", mux_gpll_xin24m_p, 0,
+			PX30_CLKSEL_CON(7), 7, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(2), 5, GFLAGS),
+	COMPOSITE(0, "dclk_vopb_src", mux_cpll_npll_p, CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
+			PX30_CLKSEL_CON(5), 11, 1, MFLAGS, 0, 8, DFLAGS,
+			PX30_CLKGATE_CON(2), 2, GFLAGS),
+	COMPOSITE_FRACMUX(0, "dclk_vopb_frac", "dclk_vopb_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(6), 0,
+			PX30_CLKGATE_CON(2), 3, GFLAGS,
+			&px30_dclk_vopb_fracmux),
+	GATE(DCLK_VOPB, "dclk_vopb", "dclk_vopb_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(2), 4, GFLAGS),
+	COMPOSITE(0, "dclk_vopl_src", mux_npll_cpll_p, 0,
+			PX30_CLKSEL_CON(8), 11, 1, MFLAGS, 0, 8, DFLAGS,
+			PX30_CLKGATE_CON(2), 6, GFLAGS),
+	COMPOSITE_FRACMUX(0, "dclk_vopl_frac", "dclk_vopl_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(9), 0,
+			PX30_CLKGATE_CON(2), 7, GFLAGS,
+			&px30_dclk_vopl_fracmux),
+	GATE(DCLK_VOPL, "dclk_vopl", "dclk_vopl_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(2), 8, GFLAGS),
+
+	/* PD_VPU */
+	COMPOSITE(0, "aclk_vpu_pre", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(10), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(4), 0, GFLAGS),
+	COMPOSITE_NOMUX(0, "hclk_vpu_pre", "aclk_vpu_pre", 0,
+			PX30_CLKSEL_CON(10), 8, 4, DFLAGS,
+			PX30_CLKGATE_CON(4), 2, GFLAGS),
+	COMPOSITE(SCLK_CORE_VPU, "sclk_core_vpu", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(13), 14, 2, MFLAGS, 8, 5, DFLAGS,
+			PX30_CLKGATE_CON(4), 1, GFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 7
+	 */
+
+	COMPOSITE_NODIV(ACLK_PERI_SRC, "aclk_peri_src", mux_gpll_cpll_p, 0,
+			PX30_CLKSEL_CON(14), 15, 1, MFLAGS,
+			PX30_CLKGATE_CON(5), 7, GFLAGS),
+	COMPOSITE_NOMUX(ACLK_PERI_PRE, "aclk_peri_pre", "aclk_peri_src", CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(14), 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(5), 8, GFLAGS),
+	DIV(HCLK_PERI_PRE, "hclk_peri_pre", "aclk_peri_src", CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(14), 8, 5, DFLAGS),
+
+	/* PD_MMC_NAND */
+	GATE(HCLK_MMC_NAND, "hclk_mmc_nand", "hclk_peri_pre", 0,
+			PX30_CLKGATE_CON(6), 0, GFLAGS),
+	COMPOSITE(SCLK_NANDC, "clk_nandc", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(15), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(5), 13, GFLAGS),
+
+	COMPOSITE(SCLK_SDIO, "clk_sdio", mux_gpll_cpll_npll_xin24m_p, 0,
+			PX30_CLKSEL_CON(18), 14, 2, MFLAGS, 0, 8, DFLAGS,
+			PX30_CLKGATE_CON(6), 3, GFLAGS),
+
+	COMPOSITE(SCLK_EMMC, "clk_emmc", mux_gpll_cpll_npll_xin24m_p, 0,
+			PX30_CLKSEL_CON(20), 14, 2, MFLAGS, 0, 8, DFLAGS,
+			PX30_CLKGATE_CON(6), 6, GFLAGS),
+
+	COMPOSITE(SCLK_SFC, "clk_sfc", mux_gpll_cpll_p, 0,
+			PX30_CLKSEL_CON(22), 7, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(6), 7, GFLAGS),
+
+	MMC(SCLK_SDMMC_DRV, "sdmmc_drv", "clk_sdmmc",
+	    PX30_SDMMC_CON0, 1),
+	MMC(SCLK_SDMMC_SAMPLE, "sdmmc_sample", "clk_sdmmc",
+	    PX30_SDMMC_CON1, 1),
+
+	MMC(SCLK_SDIO_DRV, "sdio_drv", "clk_sdio",
+	    PX30_SDIO_CON0, 1),
+	MMC(SCLK_SDIO_SAMPLE, "sdio_sample", "clk_sdio",
+	    PX30_SDIO_CON1, 1),
+
+	MMC(SCLK_EMMC_DRV, "emmc_drv", "clk_emmc",
+	    PX30_EMMC_CON0, 1),
+	MMC(SCLK_EMMC_SAMPLE, "emmc_sample", "clk_emmc",
+	    PX30_EMMC_CON1, 1),
+
+	/* PD_SDCARD */
+	GATE(0, "hclk_sdmmc_pre", "hclk_peri_pre", 0,
+			PX30_CLKGATE_CON(6), 12, GFLAGS),
+	COMPOSITE(SCLK_SDMMC, "clk_sdmmc", mux_gpll_cpll_npll_xin24m_p, 0,
+			PX30_CLKSEL_CON(16), 14, 2, MFLAGS, 0, 8, DFLAGS,
+			PX30_CLKGATE_CON(6), 15, GFLAGS),
+
+	/* PD_USB */
+	GATE(HCLK_USB, "hclk_usb", "hclk_peri_pre", 0,
+			PX30_CLKGATE_CON(7), 2, GFLAGS),
+	GATE(SCLK_OTG_ADP, "clk_otg_adp", "clk_rtc32k_pmu", 0,
+			PX30_CLKGATE_CON(7), 3, GFLAGS),
+
+	/* PD_GMAC */
+	COMPOSITE(SCLK_GMAC_SRC, "clk_gmac_src", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(22), 14, 2, MFLAGS, 8, 5, DFLAGS,
+			PX30_CLKGATE_CON(7), 11, GFLAGS),
+	MUX(SCLK_GMAC, "clk_gmac", mux_gmac_p,  CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(23), 6, 1, MFLAGS),
+	GATE(SCLK_MAC_REF, "clk_mac_ref", "clk_gmac", 0,
+			PX30_CLKGATE_CON(7), 15, GFLAGS),
+	GATE(SCLK_GMAC_RX_TX, "clk_gmac_rx_tx", "clk_gmac", 0,
+			PX30_CLKGATE_CON(7), 13, GFLAGS),
+	FACTOR(0, "clk_gmac_rx_tx_div2", "clk_gmac_rx_tx", 0, 1, 2),
+	FACTOR(0, "clk_gmac_rx_tx_div20", "clk_gmac_rx_tx", 0, 1, 20),
+	MUX(SCLK_GMAC_RMII, "clk_gmac_rmii_sel", mux_gmac_rmii_sel_p,  CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(23), 7, 1, MFLAGS),
+
+	GATE(0, "aclk_gmac_pre", "aclk_peri_pre", 0,
+			PX30_CLKGATE_CON(7), 10, GFLAGS),
+	COMPOSITE_NOMUX(0, "pclk_gmac_pre", "aclk_gmac_pre", 0,
+			PX30_CLKSEL_CON(23), 0, 4, DFLAGS,
+			PX30_CLKGATE_CON(7), 12, GFLAGS),
+
+	COMPOSITE(SCLK_MAC_OUT, "clk_mac_out", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(12), 14, 2, MFLAGS, 8, 5, DFLAGS,
+			PX30_CLKGATE_CON(8), 5, GFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 8
+	 */
+
+	/* PD_BUS */
+	COMPOSITE_NODIV(ACLK_BUS_SRC, "aclk_bus_src", mux_gpll_cpll_p, CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(23), 15, 1, MFLAGS,
+			PX30_CLKGATE_CON(8), 6, GFLAGS),
+	COMPOSITE_NOMUX(HCLK_BUS_PRE, "hclk_bus_pre", "aclk_bus_src", CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(24), 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(8), 8, GFLAGS),
+	COMPOSITE_NOMUX(ACLK_BUS_PRE, "aclk_bus_pre", "aclk_bus_src", CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(23), 8, 5, DFLAGS,
+			PX30_CLKGATE_CON(8), 7, GFLAGS),
+	COMPOSITE_NOMUX(PCLK_BUS_PRE, "pclk_bus_pre", "aclk_bus_pre", CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(24), 8, 2, DFLAGS,
+			PX30_CLKGATE_CON(8), 9, GFLAGS),
+	GATE(0, "pclk_top_pre", "pclk_bus_pre", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(8), 10, GFLAGS),
+
+	COMPOSITE(0, "clk_pdm_src", mux_gpll_xin24m_npll_p, 0,
+			PX30_CLKSEL_CON(26), 8, 2, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(9), 9, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_pdm_frac", "clk_pdm_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(27), 0,
+			PX30_CLKGATE_CON(9), 10, GFLAGS,
+			&px30_pdm_fracmux),
+	GATE(SCLK_PDM, "clk_pdm", "clk_pdm_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(9), 11, GFLAGS),
+
+	COMPOSITE(0, "clk_i2s0_tx_src", mux_gpll_npll_p, 0,
+			PX30_CLKSEL_CON(28), 8, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(9), 12, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_i2s0_tx_frac", "clk_i2s0_tx_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(29), 0,
+			PX30_CLKGATE_CON(9), 13, GFLAGS,
+			&px30_i2s0_tx_fracmux),
+	COMPOSITE_NODIV(SCLK_I2S0_TX, "clk_i2s0_tx", mux_i2s0_tx_rx_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(28), 12, 1, MFLAGS,
+			PX30_CLKGATE_CON(9), 14, GFLAGS),
+	COMPOSITE_NODIV(0, "clk_i2s0_tx_out_pre", mux_i2s0_tx_out_p, 0,
+			PX30_CLKSEL_CON(28), 14, 2, MFLAGS,
+			PX30_CLKGATE_CON(9), 15, GFLAGS),
+	GATE(SCLK_I2S0_TX_OUT, "clk_i2s0_tx_out", "clk_i2s0_tx_out_pre", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(10), 8, CLK_GATE_HIWORD_MASK),
+
+	COMPOSITE(0, "clk_i2s0_rx_src", mux_gpll_npll_p, 0,
+			PX30_CLKSEL_CON(58), 8, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(17), 0, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_i2s0_rx_frac", "clk_i2s0_rx_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(59), 0,
+			PX30_CLKGATE_CON(17), 1, GFLAGS,
+			&px30_i2s0_rx_fracmux),
+	COMPOSITE_NODIV(SCLK_I2S0_RX, "clk_i2s0_rx", mux_i2s0_rx_tx_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(58), 12, 1, MFLAGS,
+			PX30_CLKGATE_CON(17), 2, GFLAGS),
+	COMPOSITE_NODIV(0, "clk_i2s0_rx_out_pre", mux_i2s0_rx_out_p, 0,
+			PX30_CLKSEL_CON(58), 14, 2, MFLAGS,
+			PX30_CLKGATE_CON(17), 3, GFLAGS),
+	GATE(SCLK_I2S0_RX_OUT, "clk_i2s0_rx_out", "clk_i2s0_rx_out_pre", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(10), 11, CLK_GATE_HIWORD_MASK),
+
+	COMPOSITE(0, "clk_i2s1_src", mux_gpll_npll_p, 0,
+			PX30_CLKSEL_CON(30), 8, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(10), 0, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_i2s1_frac", "clk_i2s1_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(31), 0,
+			PX30_CLKGATE_CON(10), 1, GFLAGS,
+			&px30_i2s1_fracmux),
+	GATE(SCLK_I2S1, "clk_i2s1", "clk_i2s1_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(10), 2, GFLAGS),
+	COMPOSITE_NODIV(0, "clk_i2s1_out_pre", mux_i2s1_out_p, 0,
+			PX30_CLKSEL_CON(30), 15, 1, MFLAGS,
+			PX30_CLKGATE_CON(10), 3, GFLAGS),
+	GATE(SCLK_I2S1_OUT, "clk_i2s1_out", "clk_i2s1_out_pre", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(10), 9, CLK_GATE_HIWORD_MASK),
+
+	COMPOSITE(0, "clk_i2s2_src", mux_gpll_npll_p, 0,
+			PX30_CLKSEL_CON(32), 8, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(10), 4, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_i2s2_frac", "clk_i2s2_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(33), 0,
+			PX30_CLKGATE_CON(10), 5, GFLAGS,
+			&px30_i2s2_fracmux),
+	GATE(SCLK_I2S2, "clk_i2s2", "clk_i2s2_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(10), 6, GFLAGS),
+	COMPOSITE_NODIV(0, "clk_i2s2_out_pre", mux_i2s2_out_p, 0,
+			PX30_CLKSEL_CON(32), 15, 1, MFLAGS,
+			PX30_CLKGATE_CON(10), 7, GFLAGS),
+	GATE(SCLK_I2S2_OUT, "clk_i2s2_out", "clk_i2s2_out_pre", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(10), 10, CLK_GATE_HIWORD_MASK),
+
+	COMPOSITE(SCLK_UART1_SRC, "clk_uart1_src", mux_uart_src_p, CLK_SET_RATE_NO_REPARENT,
+			PX30_CLKSEL_CON(34), 14, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(10), 12, GFLAGS),
+	COMPOSITE_NOMUX_HALFDIV(0, "clk_uart1_np5", "clk_uart1_src", 0,
+			PX30_CLKSEL_CON(35), 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(10), 13, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_uart1_frac", "clk_uart1_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(36), 0,
+			PX30_CLKGATE_CON(10), 14, GFLAGS,
+			&px30_uart1_fracmux),
+	GATE(SCLK_UART1, "clk_uart1", "clk_uart1_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(10), 15, GFLAGS),
+
+	COMPOSITE(SCLK_UART2_SRC, "clk_uart2_src", mux_uart_src_p, 0,
+			PX30_CLKSEL_CON(37), 14, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(11), 0, GFLAGS),
+	COMPOSITE_NOMUX_HALFDIV(0, "clk_uart2_np5", "clk_uart2_src", 0,
+			PX30_CLKSEL_CON(38), 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(11), 1, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_uart2_frac", "clk_uart2_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(39), 0,
+			PX30_CLKGATE_CON(11), 2, GFLAGS,
+			&px30_uart2_fracmux),
+	GATE(SCLK_UART2, "clk_uart2", "clk_uart2_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(11), 3, GFLAGS),
+
+	COMPOSITE(0, "clk_uart3_src", mux_uart_src_p, 0,
+			PX30_CLKSEL_CON(40), 14, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(11), 4, GFLAGS),
+	COMPOSITE_NOMUX_HALFDIV(0, "clk_uart3_np5", "clk_uart3_src", 0,
+			PX30_CLKSEL_CON(41), 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(11), 5, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_uart3_frac", "clk_uart3_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(42), 0,
+			PX30_CLKGATE_CON(11), 6, GFLAGS,
+			&px30_uart3_fracmux),
+	GATE(SCLK_UART3, "clk_uart3", "clk_uart3_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(11), 7, GFLAGS),
+
+	COMPOSITE(0, "clk_uart4_src", mux_uart_src_p, 0,
+			PX30_CLKSEL_CON(43), 14, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(11), 8, GFLAGS),
+	COMPOSITE_NOMUX_HALFDIV(0, "clk_uart4_np5", "clk_uart4_src", 0,
+			PX30_CLKSEL_CON(44), 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(11), 9, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_uart4_frac", "clk_uart4_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(45), 0,
+			PX30_CLKGATE_CON(11), 10, GFLAGS,
+			&px30_uart4_fracmux),
+	GATE(SCLK_UART4, "clk_uart4", "clk_uart4_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(11), 11, GFLAGS),
+
+	COMPOSITE(0, "clk_uart5_src", mux_uart_src_p, 0,
+			PX30_CLKSEL_CON(46), 14, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(11), 12, GFLAGS),
+	COMPOSITE_NOMUX_HALFDIV(0, "clk_uart5_np5", "clk_uart5_src", 0,
+			PX30_CLKSEL_CON(47), 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(11), 13, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_uart5_frac", "clk_uart5_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(48), 0,
+			PX30_CLKGATE_CON(11), 14, GFLAGS,
+			&px30_uart5_fracmux),
+	GATE(SCLK_UART5, "clk_uart5", "clk_uart5_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(11), 15, GFLAGS),
+
+	COMPOSITE(SCLK_I2C0, "clk_i2c0", mux_gpll_xin24m_p, 0,
+			PX30_CLKSEL_CON(49), 7, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(12), 0, GFLAGS),
+	COMPOSITE(SCLK_I2C1, "clk_i2c1", mux_gpll_xin24m_p, 0,
+			PX30_CLKSEL_CON(49), 15, 1, MFLAGS, 8, 7, DFLAGS,
+			PX30_CLKGATE_CON(12), 1, GFLAGS),
+	COMPOSITE(SCLK_I2C2, "clk_i2c2", mux_gpll_xin24m_p, 0,
+			PX30_CLKSEL_CON(50), 7, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(12), 2, GFLAGS),
+	COMPOSITE(SCLK_I2C3, "clk_i2c3", mux_gpll_xin24m_p, 0,
+			PX30_CLKSEL_CON(50), 15, 1, MFLAGS, 8, 7, DFLAGS,
+			PX30_CLKGATE_CON(12), 3, GFLAGS),
+	COMPOSITE(SCLK_PWM0, "clk_pwm0", mux_gpll_xin24m_p, 0,
+			PX30_CLKSEL_CON(52), 7, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(12), 5, GFLAGS),
+	COMPOSITE(SCLK_PWM1, "clk_pwm1", mux_gpll_xin24m_p, 0,
+			PX30_CLKSEL_CON(52), 15, 1, MFLAGS, 8, 7, DFLAGS,
+			PX30_CLKGATE_CON(12), 6, GFLAGS),
+	COMPOSITE(SCLK_SPI0, "clk_spi0", mux_gpll_xin24m_p, 0,
+			PX30_CLKSEL_CON(53), 7, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(12), 7, GFLAGS),
+	COMPOSITE(SCLK_SPI1, "clk_spi1", mux_gpll_xin24m_p, 0,
+			PX30_CLKSEL_CON(53), 15, 1, MFLAGS, 8, 7, DFLAGS,
+			PX30_CLKGATE_CON(12), 8, GFLAGS),
+
+	GATE(SCLK_TIMER0, "sclk_timer0", "xin24m", 0,
+			PX30_CLKGATE_CON(13), 0, GFLAGS),
+	GATE(SCLK_TIMER1, "sclk_timer1", "xin24m", 0,
+			PX30_CLKGATE_CON(13), 1, GFLAGS),
+	GATE(SCLK_TIMER2, "sclk_timer2", "xin24m", 0,
+			PX30_CLKGATE_CON(13), 2, GFLAGS),
+	GATE(SCLK_TIMER3, "sclk_timer3", "xin24m", 0,
+			PX30_CLKGATE_CON(13), 3, GFLAGS),
+	GATE(SCLK_TIMER4, "sclk_timer4", "xin24m", 0,
+			PX30_CLKGATE_CON(13), 4, GFLAGS),
+	GATE(SCLK_TIMER5, "sclk_timer5", "xin24m", 0,
+			PX30_CLKGATE_CON(13), 5, GFLAGS),
+
+	COMPOSITE_NOMUX(SCLK_TSADC, "clk_tsadc", "xin24m", 0,
+			PX30_CLKSEL_CON(54), 0, 11, DFLAGS,
+			PX30_CLKGATE_CON(12), 9, GFLAGS),
+	COMPOSITE_NOMUX(SCLK_SARADC, "clk_saradc", "xin24m", 0,
+			PX30_CLKSEL_CON(55), 0, 11, DFLAGS,
+			PX30_CLKGATE_CON(12), 10, GFLAGS),
+	COMPOSITE_NOMUX(SCLK_OTP, "clk_otp", "xin24m", 0,
+			PX30_CLKSEL_CON(56), 0, 3, DFLAGS,
+			PX30_CLKGATE_CON(12), 11, GFLAGS),
+	COMPOSITE_NOMUX(SCLK_OTP_USR, "clk_otp_usr", "clk_otp", 0,
+			PX30_CLKSEL_CON(56), 4, 2, DFLAGS,
+			PX30_CLKGATE_CON(13), 6, GFLAGS),
+
+	GATE(0, "clk_cpu_boost", "xin24m", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(12), 12, GFLAGS),
+
+	/* PD_CRYPTO */
+	GATE(0, "aclk_crypto_pre", "aclk_bus_pre", 0,
+			PX30_CLKGATE_CON(8), 12, GFLAGS),
+	GATE(0, "hclk_crypto_pre", "hclk_bus_pre", 0,
+			PX30_CLKGATE_CON(8), 13, GFLAGS),
+	COMPOSITE(SCLK_CRYPTO, "clk_crypto", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(25), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(8), 14, GFLAGS),
+	COMPOSITE(SCLK_CRYPTO_APK, "clk_crypto_apk", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(25), 14, 2, MFLAGS, 8, 5, DFLAGS,
+			PX30_CLKGATE_CON(8), 15, GFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 9
+	 */
+
+	/* PD_BUS_TOP */
+	GATE(0, "pclk_top_niu", "pclk_top_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(16), 0, GFLAGS),
+	GATE(0, "pclk_top_cru", "pclk_top_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(16), 1, GFLAGS),
+	GATE(PCLK_OTP_PHY, "pclk_otp_phy", "pclk_top_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(16), 2, GFLAGS),
+	GATE(0, "pclk_ddrphy", "pclk_top_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(16), 3, GFLAGS),
+	GATE(PCLK_MIPIDSIPHY, "pclk_mipidsiphy", "pclk_top_pre", 0, PX30_CLKGATE_CON(16), 4, GFLAGS),
+	GATE(PCLK_MIPICSIPHY, "pclk_mipicsiphy", "pclk_top_pre", 0, PX30_CLKGATE_CON(16), 5, GFLAGS),
+	GATE(PCLK_USB_GRF, "pclk_usb_grf", "pclk_top_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(16), 6, GFLAGS),
+	GATE(0, "pclk_cpu_hoost", "pclk_top_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(16), 7, GFLAGS),
+
+	/* PD_VI */
+	GATE(0, "aclk_vi_niu", "aclk_vi_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(4), 15, GFLAGS),
+	GATE(ACLK_CIF, "aclk_cif", "aclk_vi_pre", 0, PX30_CLKGATE_CON(5), 1, GFLAGS),
+	GATE(ACLK_ISP, "aclk_isp", "aclk_vi_pre", 0, PX30_CLKGATE_CON(5), 3, GFLAGS),
+	GATE(0, "hclk_vi_niu", "hclk_vi_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(5), 0, GFLAGS),
+	GATE(HCLK_CIF, "hclk_cif", "hclk_vi_pre", 0, PX30_CLKGATE_CON(5), 2, GFLAGS),
+	GATE(HCLK_ISP, "hclk_isp", "hclk_vi_pre", 0, PX30_CLKGATE_CON(5), 4, GFLAGS),
+
+	/* PD_VO */
+	GATE(0, "aclk_vo_niu", "aclk_vo_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(3), 0, GFLAGS),
+	GATE(ACLK_VOPB, "aclk_vopb", "aclk_vo_pre", 0, PX30_CLKGATE_CON(3), 3, GFLAGS),
+	GATE(ACLK_RGA, "aclk_rga", "aclk_vo_pre", 0, PX30_CLKGATE_CON(3), 7, GFLAGS),
+	GATE(ACLK_VOPL, "aclk_vopl", "aclk_vo_pre", 0, PX30_CLKGATE_CON(3), 5, GFLAGS),
+
+	GATE(0, "hclk_vo_niu", "hclk_vo_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(3), 1, GFLAGS),
+	GATE(HCLK_VOPB, "hclk_vopb", "hclk_vo_pre", 0, PX30_CLKGATE_CON(3), 4, GFLAGS),
+	GATE(HCLK_RGA, "hclk_rga", "hclk_vo_pre", 0, PX30_CLKGATE_CON(3), 8, GFLAGS),
+	GATE(HCLK_VOPL, "hclk_vopl", "hclk_vo_pre", 0, PX30_CLKGATE_CON(3), 6, GFLAGS),
+
+	GATE(0, "pclk_vo_niu", "pclk_vo_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(3), 2, GFLAGS),
+	GATE(PCLK_MIPI_DSI, "pclk_mipi_dsi", "pclk_vo_pre", 0, PX30_CLKGATE_CON(3), 9, GFLAGS),
+
+	/* PD_BUS */
+	GATE(0, "aclk_bus_niu", "aclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(13), 8, GFLAGS),
+	GATE(0, "aclk_intmem", "aclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(13), 11, GFLAGS),
+	GATE(ACLK_GIC, "aclk_gic", "aclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(13), 12, GFLAGS),
+	GATE(ACLK_DCF, "aclk_dcf", "aclk_bus_pre", 0, PX30_CLKGATE_CON(13), 15, GFLAGS),
+
+	GATE(0, "hclk_bus_niu", "hclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(13), 9, GFLAGS),
+	GATE(0, "hclk_rom", "hclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(13), 14, GFLAGS),
+	GATE(HCLK_PDM, "hclk_pdm", "hclk_bus_pre", 0, PX30_CLKGATE_CON(14), 1, GFLAGS),
+	GATE(HCLK_I2S0, "hclk_i2s0", "hclk_bus_pre", 0, PX30_CLKGATE_CON(14), 2, GFLAGS),
+	GATE(HCLK_I2S1, "hclk_i2s1", "hclk_bus_pre", 0, PX30_CLKGATE_CON(14), 3, GFLAGS),
+	GATE(HCLK_I2S2, "hclk_i2s2", "hclk_bus_pre", 0, PX30_CLKGATE_CON(14), 4, GFLAGS),
+
+	GATE(0, "pclk_bus_niu", "pclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(13), 10, GFLAGS),
+	GATE(PCLK_DCF, "pclk_dcf", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 0, GFLAGS),
+	GATE(PCLK_UART1, "pclk_uart1", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 5, GFLAGS),
+	GATE(PCLK_UART2, "pclk_uart2", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 6, GFLAGS),
+	GATE(PCLK_UART3, "pclk_uart3", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 7, GFLAGS),
+	GATE(PCLK_UART4, "pclk_uart4", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 8, GFLAGS),
+	GATE(PCLK_UART5, "pclk_uart5", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 9, GFLAGS),
+	GATE(PCLK_I2C0, "pclk_i2c0", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 10, GFLAGS),
+	GATE(PCLK_I2C1, "pclk_i2c1", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 11, GFLAGS),
+	GATE(PCLK_I2C2, "pclk_i2c2", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 12, GFLAGS),
+	GATE(PCLK_I2C3, "pclk_i2c3", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 13, GFLAGS),
+	GATE(PCLK_I2C4, "pclk_i2c4", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 14, GFLAGS),
+	GATE(PCLK_PWM0, "pclk_pwm0", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 15, GFLAGS),
+	GATE(PCLK_PWM1, "pclk_pwm1", "pclk_bus_pre", 0, PX30_CLKGATE_CON(15), 0, GFLAGS),
+	GATE(PCLK_SPI0, "pclk_spi0", "pclk_bus_pre", 0, PX30_CLKGATE_CON(15), 1, GFLAGS),
+	GATE(PCLK_SPI1, "pclk_spi1", "pclk_bus_pre", 0, PX30_CLKGATE_CON(15), 2, GFLAGS),
+	GATE(PCLK_SARADC, "pclk_saradc", "pclk_bus_pre", 0, PX30_CLKGATE_CON(15), 3, GFLAGS),
+	GATE(PCLK_TSADC, "pclk_tsadc", "pclk_bus_pre", 0, PX30_CLKGATE_CON(15), 4, GFLAGS),
+	GATE(PCLK_TIMER, "pclk_timer", "pclk_bus_pre", 0, PX30_CLKGATE_CON(15), 5, GFLAGS),
+	GATE(PCLK_OTP_NS, "pclk_otp_ns", "pclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(15), 6, GFLAGS),
+	GATE(PCLK_WDT_NS, "pclk_wdt_ns", "pclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(15), 7, GFLAGS),
+	GATE(PCLK_GPIO1, "pclk_gpio1", "pclk_bus_pre", 0, PX30_CLKGATE_CON(15), 8, GFLAGS),
+	GATE(PCLK_GPIO2, "pclk_gpio2", "pclk_bus_pre", 0, PX30_CLKGATE_CON(15), 9, GFLAGS),
+	GATE(PCLK_GPIO3, "pclk_gpio3", "pclk_bus_pre", 0, PX30_CLKGATE_CON(15), 10, GFLAGS),
+	GATE(0, "pclk_grf", "pclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(15), 11, GFLAGS),
+	GATE(0, "pclk_sgrf", "pclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(15), 12, GFLAGS),
+
+	/* PD_VPU */
+	GATE(0, "hclk_vpu_niu", "hclk_vpu_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(4), 7, GFLAGS),
+	GATE(HCLK_VPU, "hclk_vpu", "hclk_vpu_pre", 0, PX30_CLKGATE_CON(4), 6, GFLAGS),
+	GATE(0, "aclk_vpu_niu", "aclk_vpu_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(4), 5, GFLAGS),
+	GATE(ACLK_VPU, "aclk_vpu", "aclk_vpu_pre", 0, PX30_CLKGATE_CON(4), 4, GFLAGS),
+
+	/* PD_CRYPTO */
+	GATE(0, "hclk_crypto_niu", "hclk_crypto_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(9), 3, GFLAGS),
+	GATE(HCLK_CRYPTO, "hclk_crypto", "hclk_crypto_pre", 0, PX30_CLKGATE_CON(9), 5, GFLAGS),
+	GATE(0, "aclk_crypto_niu", "aclk_crypto_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(9), 2, GFLAGS),
+	GATE(ACLK_CRYPTO, "aclk_crypto", "aclk_crypto_pre", 0, PX30_CLKGATE_CON(9), 4, GFLAGS),
+
+	/* PD_SDCARD */
+	GATE(0, "hclk_sdmmc_niu", "hclk_sdmmc_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(7), 0, GFLAGS),
+	GATE(HCLK_SDMMC, "hclk_sdmmc", "hclk_sdmmc_pre", 0, PX30_CLKGATE_CON(7), 1, GFLAGS),
+
+	/* PD_PERI */
+	GATE(0, "aclk_peri_niu", "aclk_peri_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(5), 9, GFLAGS),
+
+	/* PD_MMC_NAND */
+	GATE(HCLK_NANDC, "hclk_nandc", "hclk_mmc_nand", 0, PX30_CLKGATE_CON(5), 15, GFLAGS),
+	GATE(0, "hclk_mmc_nand_niu", "hclk_mmc_nand", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(6), 8, GFLAGS),
+	GATE(HCLK_SDIO, "hclk_sdio", "hclk_mmc_nand", 0, PX30_CLKGATE_CON(6), 9, GFLAGS),
+	GATE(HCLK_EMMC, "hclk_emmc", "hclk_mmc_nand", 0, PX30_CLKGATE_CON(6), 10, GFLAGS),
+	GATE(HCLK_SFC, "hclk_sfc", "hclk_mmc_nand", 0, PX30_CLKGATE_CON(6), 11, GFLAGS),
+
+	/* PD_USB */
+	GATE(0, "hclk_usb_niu", "hclk_usb", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(7), 4, GFLAGS),
+	GATE(HCLK_OTG, "hclk_otg", "hclk_usb", 0, PX30_CLKGATE_CON(7), 5, GFLAGS),
+	GATE(HCLK_HOST, "hclk_host", "hclk_usb", 0, PX30_CLKGATE_CON(7), 6, GFLAGS),
+	GATE(HCLK_HOST_ARB, "hclk_host_arb", "hclk_usb", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(7), 8, GFLAGS),
+
+	/* PD_GMAC */
+	GATE(0, "aclk_gmac_niu", "aclk_gmac_pre", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(8), 0, GFLAGS),
+	GATE(ACLK_GMAC, "aclk_gmac", "aclk_gmac_pre", 0,
+			PX30_CLKGATE_CON(8), 2, GFLAGS),
+	GATE(0, "pclk_gmac_niu", "pclk_gmac_pre", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(8), 1, GFLAGS),
+	GATE(PCLK_GMAC, "pclk_gmac", "pclk_gmac_pre", 0,
+			PX30_CLKGATE_CON(8), 3, GFLAGS),
+};
+
+static struct rockchip_clk_branch px30_clk_pmu_branches[] __initdata = {
+	/*
+	 * Clock-Architecture Diagram 2
+	 */
+
+	COMPOSITE_FRACMUX(0, "clk_rtc32k_frac", "xin24m", CLK_IGNORE_UNUSED,
+			PX30_PMU_CLKSEL_CON(1), 0,
+			PX30_PMU_CLKGATE_CON(0), 13, GFLAGS,
+			&px30_rtc32k_pmu_fracmux),
+
+	COMPOSITE_NOMUX(XIN24M_DIV, "xin24m_div", "xin24m", CLK_IGNORE_UNUSED,
+			PX30_PMU_CLKSEL_CON(0), 8, 5, DFLAGS,
+			PX30_PMU_CLKGATE_CON(0), 12, GFLAGS),
+
+	COMPOSITE_NOMUX(0, "clk_wifi_pmu_src", "gpll", 0,
+			PX30_PMU_CLKSEL_CON(2), 8, 6, DFLAGS,
+			PX30_PMU_CLKGATE_CON(0), 14, GFLAGS),
+	COMPOSITE_NODIV(SCLK_WIFI_PMU, "clk_wifi_pmu", mux_wifi_pmu_p, CLK_SET_RATE_PARENT,
+			PX30_PMU_CLKSEL_CON(2), 15, 1, MFLAGS,
+			PX30_PMU_CLKGATE_CON(0), 15, GFLAGS),
+
+	COMPOSITE(0, "clk_uart0_pmu_src", mux_uart_src_p, 0,
+			PX30_PMU_CLKSEL_CON(3), 14, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_PMU_CLKGATE_CON(1), 0, GFLAGS),
+	COMPOSITE_NOMUX_HALFDIV(0, "clk_uart0_np5", "clk_uart0_pmu_src", 0,
+			PX30_PMU_CLKSEL_CON(4), 0, 5, DFLAGS,
+			PX30_PMU_CLKGATE_CON(1), 1, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_uart0_frac", "clk_uart0_pmu_src", CLK_SET_RATE_PARENT,
+			PX30_PMU_CLKSEL_CON(5), 0,
+			PX30_PMU_CLKGATE_CON(1), 2, GFLAGS,
+			&px30_uart0_pmu_fracmux),
+	GATE(SCLK_UART0_PMU, "clk_uart0_pmu", "clk_uart0_pmu_mux", CLK_SET_RATE_PARENT,
+			PX30_PMU_CLKGATE_CON(1), 3, GFLAGS),
+
+	GATE(SCLK_PVTM_PMU, "clk_pvtm_pmu", "xin24m", 0,
+			PX30_PMU_CLKGATE_CON(1), 4, GFLAGS),
+
+	COMPOSITE_NOMUX(PCLK_PMU_PRE, "pclk_pmu_pre", "gpll", 0,
+			PX30_PMU_CLKSEL_CON(0), 0, 5, DFLAGS,
+			PX30_PMU_CLKGATE_CON(0), 0, GFLAGS),
+
+	COMPOSITE_NOMUX(SCLK_REF24M_PMU, "clk_ref24m_pmu", "gpll", 0,
+			PX30_PMU_CLKSEL_CON(2), 0, 6, DFLAGS,
+			PX30_PMU_CLKGATE_CON(1), 8, GFLAGS),
+	COMPOSITE_NODIV(SCLK_USBPHY_REF, "clk_usbphy_ref", mux_usbphy_ref_p, CLK_SET_RATE_PARENT,
+			PX30_PMU_CLKSEL_CON(2), 6, 1, MFLAGS,
+			PX30_PMU_CLKGATE_CON(1), 9, GFLAGS),
+	COMPOSITE_NODIV(SCLK_MIPIDSIPHY_REF, "clk_mipidsiphy_ref", mux_mipidsiphy_ref_p, CLK_SET_RATE_PARENT,
+			PX30_PMU_CLKSEL_CON(2), 7, 1, MFLAGS,
+			PX30_PMU_CLKGATE_CON(1), 10, GFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 9
+	 */
+
+	/* PD_PMU */
+	GATE(0, "pclk_pmu_niu", "pclk_pmu_pre", CLK_IGNORE_UNUSED, PX30_PMU_CLKGATE_CON(0), 1, GFLAGS),
+	GATE(0, "pclk_pmu_sgrf", "pclk_pmu_pre", CLK_IGNORE_UNUSED, PX30_PMU_CLKGATE_CON(0), 2, GFLAGS),
+	GATE(0, "pclk_pmu_grf", "pclk_pmu_pre", CLK_IGNORE_UNUSED, PX30_PMU_CLKGATE_CON(0), 3, GFLAGS),
+	GATE(0, "pclk_pmu", "pclk_pmu_pre", CLK_IGNORE_UNUSED, PX30_PMU_CLKGATE_CON(0), 4, GFLAGS),
+	GATE(0, "pclk_pmu_mem", "pclk_pmu_pre", CLK_IGNORE_UNUSED, PX30_PMU_CLKGATE_CON(0), 5, GFLAGS),
+	GATE(PCLK_GPIO0_PMU, "pclk_gpio0_pmu", "pclk_pmu_pre", 0, PX30_PMU_CLKGATE_CON(0), 6, GFLAGS),
+	GATE(PCLK_UART0_PMU, "pclk_uart0_pmu", "pclk_pmu_pre", 0, PX30_PMU_CLKGATE_CON(0), 7, GFLAGS),
+	GATE(0, "pclk_cru_pmu", "pclk_pmu_pre", CLK_IGNORE_UNUSED, PX30_PMU_CLKGATE_CON(0), 8, GFLAGS),
+};
+
+static const char *const px30_pmucru_critical_clocks[] __initconst = {
+	"aclk_bus_pre",
+	"pclk_bus_pre",
+	"hclk_bus_pre",
+	"aclk_peri_pre",
+	"hclk_peri_pre",
+	"aclk_gpu_niu",
+	"pclk_top_pre",
+	"pclk_pmu_pre",
+	"hclk_usb_niu",
+	"pll_npll",
+	"usb480m",
+	"clk_uart2",
+	"pclk_uart2",
+};
+
+static void __init px30_clk_init(struct device_node *np)
+{
+	struct rockchip_clk_provider *ctx;
+	void __iomem *reg_base;
+	struct clk *clk;
+
+	reg_base = of_iomap(np, 0);
+	if (!reg_base) {
+		pr_err("%s: could not map cru region\n", __func__);
+		return;
+	}
+
+	ctx = rockchip_clk_init(np, reg_base, CLK_NR_CLKS);
+	if (IS_ERR(ctx)) {
+		pr_err("%s: rockchip clk init failed\n", __func__);
+		iounmap(reg_base);
+		return;
+	}
+
+	/* aclk_dmac is controlled by sgrf_soc_con1[11]. */
+	clk = clk_register_fixed_factor(NULL, "aclk_dmac", "aclk_bus_pre", 0, 1, 1);
+	if (IS_ERR(clk))
+		pr_warn("%s: could not register clock aclk_dmac: %ld\n",
+			__func__, PTR_ERR(clk));
+	else
+		rockchip_clk_add_lookup(ctx, clk, ACLK_DMAC);
+
+	rockchip_clk_register_plls(ctx, px30_pll_clks,
+				   ARRAY_SIZE(px30_pll_clks),
+				   PX30_GRF_SOC_STATUS0);
+	rockchip_clk_register_branches(ctx, px30_clk_branches,
+				       ARRAY_SIZE(px30_clk_branches));
+
+	rockchip_clk_register_armclk(ctx, ARMCLK, "armclk",
+				     mux_armclk_p, ARRAY_SIZE(mux_armclk_p),
+				     &px30_cpuclk_data, px30_cpuclk_rates,
+				     ARRAY_SIZE(px30_cpuclk_rates));
+
+	rockchip_register_softrst(np, 12, reg_base + PX30_SOFTRST_CON(0),
+				  ROCKCHIP_SOFTRST_HIWORD_MASK);
+
+	rockchip_register_restart_notifier(ctx, PX30_GLB_SRST_FST, NULL);
+
+	rockchip_clk_of_add_provider(np, ctx);
+}
+CLK_OF_DECLARE(px30_cru, "rockchip,px30-cru", px30_clk_init);
+
+static void __init px30_pmu_clk_init(struct device_node *np)
+{
+	struct rockchip_clk_provider *ctx;
+	void __iomem *reg_base;
+
+	reg_base = of_iomap(np, 0);
+	if (!reg_base) {
+		pr_err("%s: could not map cru pmu region\n", __func__);
+		return;
+	}
+
+	ctx = rockchip_clk_init(np, reg_base, CLKPMU_NR_CLKS);
+	if (IS_ERR(ctx)) {
+		pr_err("%s: rockchip pmu clk init failed\n", __func__);
+		return;
+	}
+
+	rockchip_clk_register_plls(ctx, px30_pmu_pll_clks,
+				   ARRAY_SIZE(px30_pmu_pll_clks), PX30_GRF_SOC_STATUS0);
+
+	rockchip_clk_register_branches(ctx, px30_clk_pmu_branches,
+				       ARRAY_SIZE(px30_clk_pmu_branches));
+
+	rockchip_clk_protect_critical(px30_pmucru_critical_clocks,
+				      ARRAY_SIZE(px30_pmucru_critical_clocks));
+
+	rockchip_clk_of_add_provider(np, ctx);
+}
+CLK_OF_DECLARE(px30_cru_pmu, "rockchip,px30-pmucru", px30_pmu_clk_init);
diff --git a/drivers/clk/rockchip/clk-rk3399.c b/drivers/clk/rockchip/clk-rk3399.c
index bca10d618f0a..5a628148f3f0 100644
--- a/drivers/clk/rockchip/clk-rk3399.c
+++ b/drivers/clk/rockchip/clk-rk3399.c
@@ -631,7 +631,7 @@ static struct rockchip_clk_branch rk3399_clk_branches[] __initdata = {
 	MUX(0, "clk_i2sout_src", mux_i2sch_p, CLK_SET_RATE_PARENT,
 			RK3399_CLKSEL_CON(31), 0, 2, MFLAGS),
 	COMPOSITE_NODIV(SCLK_I2S_8CH_OUT, "clk_i2sout", mux_i2sout_p, CLK_SET_RATE_PARENT,
-			RK3399_CLKSEL_CON(30), 8, 2, MFLAGS,
+			RK3399_CLKSEL_CON(31), 2, 1, MFLAGS,
 			RK3399_CLKGATE_CON(8), 12, GFLAGS),
 
 	/* uart */
@@ -1523,6 +1523,7 @@ static const char *const rk3399_pmucru_critical_clocks[] __initconst = {
 	"pclk_pmu_src",
 	"fclk_cm0s_src_pmu",
 	"clk_timer_src_pmu",
+	"pclk_rkpwm_pmu",
 };
 
 static void __init rk3399_clk_init(struct device_node *np)
diff --git a/drivers/clk/rockchip/clk.c b/drivers/clk/rockchip/clk.c
index 326b3fa44f5d..c3ad92965823 100644
--- a/drivers/clk/rockchip/clk.c
+++ b/drivers/clk/rockchip/clk.c
@@ -492,6 +492,16 @@ void __init rockchip_clk_register_branches(
 				list->gate_flags, flags, list->child,
 				&ctx->lock);
 			break;
+		case branch_half_divider:
+			clk = rockchip_clk_register_halfdiv(list->name,
+				list->parent_names, list->num_parents,
+				ctx->reg_base, list->muxdiv_offset,
+				list->mux_shift, list->mux_width,
+				list->mux_flags, list->div_shift,
+				list->div_width, list->div_flags,
+				list->gate_offset, list->gate_shift,
+				list->gate_flags, flags, &ctx->lock);
+			break;
 		case branch_gate:
 			flags |= CLK_SET_RATE_PARENT;
 
diff --git a/drivers/clk/rockchip/clk.h b/drivers/clk/rockchip/clk.h
index ef601dded32c..6b53fff4cc96 100644
--- a/drivers/clk/rockchip/clk.h
+++ b/drivers/clk/rockchip/clk.h
@@ -34,7 +34,46 @@ struct clk;
 #define HIWORD_UPDATE(val, mask, shift) \
 		((val) << (shift) | (mask) << ((shift) + 16))
 
-/* register positions shared by RV1108, RK2928, RK3036, RK3066, RK3188 and RK3228 */
+/* register positions shared by PX30, RV1108, RK2928, RK3036, RK3066, RK3188 and RK3228 */
+#define BOOST_PLL_H_CON(x)		((x) * 0x4)
+#define BOOST_CLK_CON			0x0008
+#define BOOST_BOOST_CON			0x000c
+#define BOOST_SWITCH_CNT		0x0010
+#define BOOST_HIGH_PERF_CNT0		0x0014
+#define BOOST_HIGH_PERF_CNT1		0x0018
+#define BOOST_STATIS_THRESHOLD		0x001c
+#define BOOST_SHORT_SWITCH_CNT		0x0020
+#define BOOST_SWITCH_THRESHOLD		0x0024
+#define BOOST_FSM_STATUS		0x0028
+#define BOOST_PLL_L_CON(x)		((x) * 0x4 + 0x2c)
+#define BOOST_RECOVERY_MASK		0x1
+#define BOOST_RECOVERY_SHIFT		1
+#define BOOST_SW_CTRL_MASK		0x1
+#define BOOST_SW_CTRL_SHIFT		2
+#define BOOST_LOW_FREQ_EN_MASK		0x1
+#define BOOST_LOW_FREQ_EN_SHIFT		3
+#define BOOST_BUSY_STATE		BIT(8)
+
+#define PX30_PLL_CON(x)			((x) * 0x4)
+#define PX30_CLKSEL_CON(x)		((x) * 0x4 + 0x100)
+#define PX30_CLKGATE_CON(x)		((x) * 0x4 + 0x200)
+#define PX30_GLB_SRST_FST		0xb8
+#define PX30_GLB_SRST_SND		0xbc
+#define PX30_SOFTRST_CON(x)		((x) * 0x4 + 0x300)
+#define PX30_MODE_CON			0xa0
+#define PX30_MISC_CON			0xa4
+#define PX30_SDMMC_CON0			0x380
+#define PX30_SDMMC_CON1			0x384
+#define PX30_SDIO_CON0			0x388
+#define PX30_SDIO_CON1			0x38c
+#define PX30_EMMC_CON0			0x390
+#define PX30_EMMC_CON1			0x394
+
+#define PX30_PMU_PLL_CON(x)		((x) * 0x4)
+#define PX30_PMU_CLKSEL_CON(x)		((x) * 0x4 + 0x40)
+#define PX30_PMU_CLKGATE_CON(x)		((x) * 0x4 + 0x80)
+#define PX30_PMU_MODE			0x0020
+
 #define RV1108_PLL_CON(x)		((x) * 0x4)
 #define RV1108_CLKSEL_CON(x)		((x) * 0x4 + 0x60)
 #define RV1108_CLKGATE_CON(x)		((x) * 0x4 + 0x120)
@@ -354,6 +393,7 @@ enum rockchip_clk_branch_type {
 	branch_inverter,
 	branch_factor,
 	branch_ddrclk,
+	branch_half_divider,
 };
 
 struct rockchip_clk_branch {
@@ -684,6 +724,79 @@ struct rockchip_clk_branch {
 		.gate_flags	= gf,				\
 	}
 
+#define COMPOSITE_HALFDIV(_id, cname, pnames, f, mo, ms, mw, mf, ds, dw,\
+			  df, go, gs, gf)				\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_half_divider,		\
+		.name		= cname,			\
+		.parent_names	= pnames,			\
+		.num_parents	= ARRAY_SIZE(pnames),		\
+		.flags		= f,				\
+		.muxdiv_offset	= mo,				\
+		.mux_shift	= ms,				\
+		.mux_width	= mw,				\
+		.mux_flags	= mf,				\
+		.div_shift	= ds,				\
+		.div_width	= dw,				\
+		.div_flags	= df,				\
+		.gate_offset	= go,				\
+		.gate_shift	= gs,				\
+		.gate_flags	= gf,				\
+	}
+
+#define COMPOSITE_NOGATE_HALFDIV(_id, cname, pnames, f, mo, ms, mw, mf,	\
+				 ds, dw, df)				\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_half_divider,		\
+		.name		= cname,			\
+		.parent_names	= pnames,			\
+		.num_parents	= ARRAY_SIZE(pnames),		\
+		.flags		= f,				\
+		.muxdiv_offset	= mo,				\
+		.mux_shift	= ms,				\
+		.mux_width	= mw,				\
+		.mux_flags	= mf,				\
+		.div_shift	= ds,				\
+		.div_width	= dw,				\
+		.div_flags	= df,				\
+		.gate_offset	= -1,				\
+	}
+
+#define COMPOSITE_NOMUX_HALFDIV(_id, cname, pname, f, mo, ds, dw, df,	\
+			go, gs, gf)				\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_half_divider,		\
+		.name		= cname,			\
+		.parent_names	= (const char *[]){ pname },	\
+		.num_parents	= 1,				\
+		.flags		= f,				\
+		.muxdiv_offset	= mo,				\
+		.div_shift	= ds,				\
+		.div_width	= dw,				\
+		.div_flags	= df,				\
+		.gate_offset	= go,				\
+		.gate_shift	= gs,				\
+		.gate_flags	= gf,				\
+	}
+
+#define DIV_HALF(_id, cname, pname, f, o, s, w, df)			\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_half_divider,		\
+		.name		= cname,			\
+		.parent_names	= (const char *[]){ pname },	\
+		.num_parents	= 1,				\
+		.flags		= f,				\
+		.muxdiv_offset	= o,				\
+		.div_shift	= s,				\
+		.div_width	= w,				\
+		.div_flags	= df,				\
+		.gate_offset	= -1,				\
+	}
+
 struct rockchip_clk_provider *rockchip_clk_init(struct device_node *np,
 			void __iomem *base, unsigned long nr_clks);
 void rockchip_clk_of_add_provider(struct device_node *np,
@@ -708,6 +821,17 @@ void rockchip_register_restart_notifier(struct rockchip_clk_provider *ctx,
 
 #define ROCKCHIP_SOFTRST_HIWORD_MASK	BIT(0)
 
+struct clk *rockchip_clk_register_halfdiv(const char *name,
+					  const char *const *parent_names,
+					  u8 num_parents, void __iomem *base,
+					  int muxdiv_offset, u8 mux_shift,
+					  u8 mux_width, u8 mux_flags,
+					  u8 div_shift, u8 div_width,
+					  u8 div_flags, int gate_offset,
+					  u8 gate_shift, u8 gate_flags,
+					  unsigned long flags,
+					  spinlock_t *lock);
+
 #ifdef CONFIG_RESET_CONTROLLER
 void rockchip_register_softrst(struct device_node *np,
 			       unsigned int num_regs,
diff --git a/drivers/clk/samsung/clk-exynos4412-isp.c b/drivers/clk/samsung/clk-exynos4412-isp.c
index d5f1ccb36300..cfaa057035ad 100644
--- a/drivers/clk/samsung/clk-exynos4412-isp.c
+++ b/drivers/clk/samsung/clk-exynos4412-isp.c
@@ -37,8 +37,6 @@ static const unsigned long exynos4x12_clk_isp_save[] __initconst = {
 	E4X12_GATE_ISP1,
 };
 
-PNAME(mout_user_aclk400_mcuisp_p4x12) = { "fin_pll", "div_aclk400_mcuisp", };
-
 static struct samsung_div_clock exynos4x12_isp_div_clks[] = {
 	DIV(CLK_ISP_DIV_ISP0, "div_isp0", "aclk200", E4X12_DIV_ISP0, 0, 3),
 	DIV(CLK_ISP_DIV_ISP1, "div_isp1", "aclk200", E4X12_DIV_ISP0, 4, 3),
diff --git a/drivers/clk/socfpga/clk-s10.c b/drivers/clk/socfpga/clk-s10.c
index 72714633e39c..5b238fc314ac 100644
--- a/drivers/clk/socfpga/clk-s10.c
+++ b/drivers/clk/socfpga/clk-s10.c
@@ -28,7 +28,7 @@ static const char * const emaca_free_mux[] = {"peri_emaca_clk", "boot_clk"};
 static const char * const emacb_free_mux[] = {"peri_emacb_clk", "boot_clk"};
 static const char * const emac_ptp_free_mux[] = {"peri_emac_ptp_clk", "boot_clk"};
 static const char * const gpio_db_free_mux[] = {"peri_gpio_db_clk", "boot_clk"};
-static const char * const sdmmc_free_mux[] = {"peri_sdmmc_clk", "boot_clk"};
+static const char * const sdmmc_free_mux[] = {"main_sdmmc_clk", "boot_clk"};
 static const char * const s2f_usr1_free_mux[] = {"peri_s2f_usr1_clk", "boot_clk"};
 static const char * const psi_ref_free_mux[] = {"peri_psi_ref_clk", "boot_clk"};
 static const char * const mpu_mux[] = { "mpu_free_clk", "boot_clk",};
@@ -37,6 +37,11 @@ static const char * const s2f_usr0_mux[] = {"f2s_free_clk", "boot_clk"};
 static const char * const emac_mux[] = {"emaca_free_clk", "emacb_free_clk"};
 static const char * const noc_mux[] = {"noc_free_clk", "boot_clk"};
 
+static const char * const mpu_free_mux[] = {"main_mpu_base_clk",
+					    "peri_mpu_base_clk",
+					    "osc1", "cb_intosc_hs_div2_clk",
+					    "f2s_free_clk"};
+
 /* clocks in AO (always on) controller */
 static const struct stratix10_pll_clock s10_pll_clks[] = {
 	{ STRATIX10_BOOT_CLK, "boot_clk", boot_mux, ARRAY_SIZE(boot_mux), 0,
@@ -57,7 +62,7 @@ static const struct stratix10_perip_c_clock s10_main_perip_c_clks[] = {
 };
 
 static const struct stratix10_perip_cnt_clock s10_main_perip_cnt_clks[] = {
-	{ STRATIX10_MPU_FREE_CLK, "mpu_free_clk", NULL, cntr_mux, ARRAY_SIZE(cntr_mux),
+	{ STRATIX10_MPU_FREE_CLK, "mpu_free_clk", NULL, mpu_free_mux, ARRAY_SIZE(mpu_free_mux),
 	   0, 0x48, 0, 0, 0},
 	{ STRATIX10_NOC_FREE_CLK, "noc_free_clk", NULL, noc_free_mux, ARRAY_SIZE(noc_free_mux),
 	  0, 0x4C, 0, 0, 0},
diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-de2.c b/drivers/clk/sunxi-ng/ccu-sun8i-de2.c
index 468d1abaf0ee..bae5ee67a797 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-de2.c
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-de2.c
@@ -289,16 +289,13 @@ static const struct of_device_id sunxi_de2_clk_ids[] = {
 		.data = &sun8i_v3s_de2_clk_desc,
 	},
 	{
+		.compatible = "allwinner,sun50i-a64-de2-clk",
+		.data = &sun50i_a64_de2_clk_desc,
+	},
+	{
 		.compatible = "allwinner,sun50i-h5-de2-clk",
 		.data = &sun50i_a64_de2_clk_desc,
 	},
-	/*
-	 * The Allwinner A64 SoC needs some bit to be poke in syscon to make
-	 * DE2 really working.
-	 * So there's currently no A64 compatible here.
-	 * H5 shares the same reset line with A64, so here H5 is using the
-	 * clock description of A64.
-	 */
 	{ }
 };
 
diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-r40.c b/drivers/clk/sunxi-ng/ccu-sun8i-r40.c
index 65ba6455feb7..0f388f6944d5 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-r40.c
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-r40.c
@@ -66,17 +66,18 @@ static SUNXI_CCU_NM_WITH_GATE_LOCK(pll_audio_base_clk, "pll-audio-base",
 				   CLK_SET_RATE_UNGATE);
 
 /* TODO: The result of N/M is required to be in [8, 25] range. */
-static SUNXI_CCU_NM_WITH_FRAC_GATE_LOCK(pll_video0_clk, "pll-video0",
-					"osc24M", 0x0010,
-					8, 7,		/* N */
-					0, 4,		/* M */
-					BIT(24),	/* frac enable */
-					BIT(25),	/* frac select */
-					270000000,	/* frac rate 0 */
-					297000000,	/* frac rate 1 */
-					BIT(31),	/* gate */
-					BIT(28),	/* lock */
-					CLK_SET_RATE_UNGATE);
+static SUNXI_CCU_NM_WITH_FRAC_GATE_LOCK_MIN(pll_video0_clk, "pll-video0",
+					    "osc24M", 0x0010,
+					    192000000,	/* Minimum rate */
+					    8, 7,	/* N */
+					    0, 4,	/* M */
+					    BIT(24),	/* frac enable */
+					    BIT(25),	/* frac select */
+					    270000000,	/* frac rate 0 */
+					    297000000,	/* frac rate 1 */
+					    BIT(31),	/* gate */
+					    BIT(28),	/* lock */
+					    CLK_SET_RATE_UNGATE);
 
 /* TODO: The result of N/M is required to be in [8, 25] range. */
 static SUNXI_CCU_NM_WITH_FRAC_GATE_LOCK(pll_ve_clk, "pll-ve",
@@ -152,17 +153,18 @@ static struct ccu_nk pll_periph1_clk = {
 };
 
 /* TODO: The result of N/M is required to be in [8, 25] range. */
-static SUNXI_CCU_NM_WITH_FRAC_GATE_LOCK(pll_video1_clk, "pll-video1",
-					"osc24M", 0x030,
-					8, 7,		/* N */
-					0, 4,		/* M */
-					BIT(24),	/* frac enable */
-					BIT(25),	/* frac select */
-					270000000,	/* frac rate 0 */
-					297000000,	/* frac rate 1 */
-					BIT(31),	/* gate */
-					BIT(28),	/* lock */
-					CLK_SET_RATE_UNGATE);
+static SUNXI_CCU_NM_WITH_FRAC_GATE_LOCK_MIN(pll_video1_clk, "pll-video1",
+					    "osc24M", 0x030,
+					    192000000,	/* Minimum rate */
+					    8, 7,	/* N */
+					    0, 4,	/* M */
+					    BIT(24),	/* frac enable */
+					    BIT(25),	/* frac select */
+					    270000000,	/* frac rate 0 */
+					    297000000,	/* frac rate 1 */
+					    BIT(31),	/* gate */
+					    BIT(28),	/* lock */
+					    CLK_SET_RATE_UNGATE);
 
 static struct ccu_nkm pll_sata_clk = {
 	.enable		= BIT(31),
@@ -654,7 +656,8 @@ static SUNXI_CCU_GATE(dram_deinterlace_clk,	"dram-deinterlace",	"dram",
 
 static const char * const de_parents[] = { "pll-periph0-2x", "pll-de" };
 static SUNXI_CCU_M_WITH_MUX_GATE(de_clk, "de", de_parents,
-				 0x104, 0, 4, 24, 3, BIT(31), 0);
+				 0x104, 0, 4, 24, 3, BIT(31),
+				 CLK_SET_RATE_PARENT);
 static SUNXI_CCU_M_WITH_MUX_GATE(mp_clk, "mp", de_parents,
 				 0x108, 0, 4, 24, 3, BIT(31), 0);
 
@@ -666,9 +669,11 @@ static SUNXI_CCU_MUX_WITH_GATE(tcon_lcd0_clk, "tcon-lcd0", tcon_parents,
 static SUNXI_CCU_MUX_WITH_GATE(tcon_lcd1_clk, "tcon-lcd1", tcon_parents,
 			       0x114, 24, 3, BIT(31), CLK_SET_RATE_PARENT);
 static SUNXI_CCU_M_WITH_MUX_GATE(tcon_tv0_clk, "tcon-tv0", tcon_parents,
-				 0x118, 0, 4, 24, 3, BIT(31), 0);
+				 0x118, 0, 4, 24, 3, BIT(31),
+				 CLK_SET_RATE_PARENT);
 static SUNXI_CCU_M_WITH_MUX_GATE(tcon_tv1_clk, "tcon-tv1", tcon_parents,
-				 0x11c, 0, 4, 24, 3, BIT(31), 0);
+				 0x11c, 0, 4, 24, 3, BIT(31),
+				 CLK_SET_RATE_PARENT);
 
 static const char * const deinterlace_parents[] = { "pll-periph0",
 						    "pll-periph1" };
@@ -698,7 +703,8 @@ static SUNXI_CCU_GATE(avs_clk,		"avs",		"osc24M",
 
 static const char * const hdmi_parents[] = { "pll-video0", "pll-video1" };
 static SUNXI_CCU_M_WITH_MUX_GATE(hdmi_clk, "hdmi", hdmi_parents,
-				 0x150, 0, 4, 24, 2, BIT(31), 0);
+				 0x150, 0, 4, 24, 2, BIT(31),
+				 CLK_SET_RATE_PARENT);
 
 static SUNXI_CCU_GATE(hdmi_slow_clk,	"hdmi-slow",	"osc24M",
 		      0x154, BIT(31), 0);
diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-r40.h b/drivers/clk/sunxi-ng/ccu-sun8i-r40.h
index 0db8e1e97af8..db2a1243f9ff 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-r40.h
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-r40.h
@@ -25,7 +25,9 @@
 #define CLK_PLL_AUDIO_2X	4
 #define CLK_PLL_AUDIO_4X	5
 #define CLK_PLL_AUDIO_8X	6
-#define CLK_PLL_VIDEO0		7
+
+/* PLL_VIDEO0 is exported */
+
 #define CLK_PLL_VIDEO0_2X	8
 #define CLK_PLL_VE		9
 #define CLK_PLL_DDR0		10
@@ -34,7 +36,9 @@
 #define CLK_PLL_PERIPH0_2X	13
 #define CLK_PLL_PERIPH1		14
 #define CLK_PLL_PERIPH1_2X	15
-#define CLK_PLL_VIDEO1		16
+
+/* PLL_VIDEO1 is exported */
+
 #define CLK_PLL_VIDEO1_2X	17
 #define CLK_PLL_SATA		18
 #define CLK_PLL_SATA_OUT	19
diff --git a/drivers/clk/tegra/Makefile b/drivers/clk/tegra/Makefile
index b71692391bd6..6507acc843c7 100644
--- a/drivers/clk/tegra/Makefile
+++ b/drivers/clk/tegra/Makefile
@@ -8,6 +8,7 @@ obj-y					+= clk-periph-fixed.o
 obj-y					+= clk-periph-gate.o
 obj-y					+= clk-pll.o
 obj-y					+= clk-pll-out.o
+obj-y					+= clk-sdmmc-mux.o
 obj-y					+= clk-super.o
 obj-y					+= clk-tegra-audio.o
 obj-y					+= clk-tegra-periph.o
@@ -24,3 +25,4 @@ obj-$(CONFIG_ARCH_TEGRA_132_SOC)	+= clk-tegra124.o
 obj-y					+= cvb.o
 obj-$(CONFIG_ARCH_TEGRA_210_SOC)	+= clk-tegra210.o
 obj-$(CONFIG_CLK_TEGRA_BPMP)		+= clk-bpmp.o
+obj-y					+= clk-utils.o
diff --git a/drivers/clk/tegra/clk-bpmp.c b/drivers/clk/tegra/clk-bpmp.c
index a896692b74ec..01dada561c10 100644
--- a/drivers/clk/tegra/clk-bpmp.c
+++ b/drivers/clk/tegra/clk-bpmp.c
@@ -586,9 +586,15 @@ static struct clk_hw *tegra_bpmp_clk_of_xlate(struct of_phandle_args *clkspec,
 	unsigned int id = clkspec->args[0], i;
 	struct tegra_bpmp *bpmp = data;
 
-	for (i = 0; i < bpmp->num_clocks; i++)
-		if (bpmp->clocks[i]->id == id)
-			return &bpmp->clocks[i]->hw;
+	for (i = 0; i < bpmp->num_clocks; i++) {
+		struct tegra_bpmp_clk *clk = bpmp->clocks[i];
+
+		if (!clk)
+			continue;
+
+		if (clk->id == id)
+			return &clk->hw;
+	}
 
 	return NULL;
 }
diff --git a/drivers/clk/tegra/clk-divider.c b/drivers/clk/tegra/clk-divider.c
index 16e0aee14773..205fe8ff63f0 100644
--- a/drivers/clk/tegra/clk-divider.c
+++ b/drivers/clk/tegra/clk-divider.c
@@ -32,35 +32,15 @@
 static int get_div(struct tegra_clk_frac_div *divider, unsigned long rate,
 		   unsigned long parent_rate)
 {
-	u64 divider_ux1 = parent_rate;
-	u8 flags = divider->flags;
-	int mul;
-
-	if (!rate)
-		return 0;
-
-	mul = get_mul(divider);
-
-	if (!(flags & TEGRA_DIVIDER_INT))
-		divider_ux1 *= mul;
-
-	if (flags & TEGRA_DIVIDER_ROUND_UP)
-		divider_ux1 += rate - 1;
-
-	do_div(divider_ux1, rate);
-
-	if (flags & TEGRA_DIVIDER_INT)
-		divider_ux1 *= mul;
+	int div;
 
-	divider_ux1 -= mul;
+	div = div_frac_get(rate, parent_rate, divider->width,
+			   divider->frac_width, divider->flags);
 
-	if ((s64)divider_ux1 < 0)
+	if (div < 0)
 		return 0;
 
-	if (divider_ux1 > get_max_div(divider))
-		return get_max_div(divider);
-
-	return divider_ux1;
+	return div;
 }
 
 static unsigned long clk_frac_div_recalc_rate(struct clk_hw *hw,
@@ -194,6 +174,7 @@ static const struct clk_div_table mc_div_table[] = {
 struct clk *tegra_clk_register_mc(const char *name, const char *parent_name,
 				  void __iomem *reg, spinlock_t *lock)
 {
-	return clk_register_divider_table(NULL, name, parent_name, 0, reg,
-					  16, 1, 0, mc_div_table, lock);
+	return clk_register_divider_table(NULL, name, parent_name,
+					  CLK_IS_CRITICAL, reg, 16, 1, 0,
+					  mc_div_table, lock);
 }
diff --git a/drivers/clk/tegra/clk-emc.c b/drivers/clk/tegra/clk-emc.c
index 5234acd30e89..0621a3a82ea6 100644
--- a/drivers/clk/tegra/clk-emc.c
+++ b/drivers/clk/tegra/clk-emc.c
@@ -132,7 +132,7 @@ static int emc_determine_rate(struct clk_hw *hw, struct clk_rate_request *req)
 		timing = tegra->timings + i;
 
 		if (timing->rate > req->max_rate) {
-			i = min(i, 1);
+			i = max(i, 1);
 			req->rate = tegra->timings[i - 1].rate;
 			return 0;
 		}
diff --git a/drivers/clk/tegra/clk-id.h b/drivers/clk/tegra/clk-id.h
index b616e33c5255..de466b4446da 100644
--- a/drivers/clk/tegra/clk-id.h
+++ b/drivers/clk/tegra/clk-id.h
@@ -227,13 +227,11 @@ enum clk_id {
 	tegra_clk_sdmmc1_9,
 	tegra_clk_sdmmc2,
 	tegra_clk_sdmmc2_8,
-	tegra_clk_sdmmc2_9,
 	tegra_clk_sdmmc3,
 	tegra_clk_sdmmc3_8,
 	tegra_clk_sdmmc3_9,
 	tegra_clk_sdmmc4,
 	tegra_clk_sdmmc4_8,
-	tegra_clk_sdmmc4_9,
 	tegra_clk_se,
 	tegra_clk_soc_therm,
 	tegra_clk_soc_therm_8,
diff --git a/drivers/clk/tegra/clk-sdmmc-mux.c b/drivers/clk/tegra/clk-sdmmc-mux.c
new file mode 100644
index 000000000000..473d418533cb
--- /dev/null
+++ b/drivers/clk/tegra/clk-sdmmc-mux.c
@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 NVIDIA CORPORATION.  All rights reserved.
+ *
+ * based on clk-mux.c
+ *
+ * Copyright (C) 2011 Sascha Hauer, Pengutronix <s.hauer@pengutronix.de>
+ * Copyright (C) 2011 Richard Zhao, Linaro <richard.zhao@linaro.org>
+ * Copyright (C) 2011-2012 Mike Turquette, Linaro Ltd <mturquette@linaro.org>
+ *
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/err.h>
+#include <linux/types.h>
+
+#include "clk.h"
+
+#define DIV_MASK GENMASK(7, 0)
+#define MUX_SHIFT 29
+#define MUX_MASK GENMASK(MUX_SHIFT + 2, MUX_SHIFT)
+#define SDMMC_MUL 2
+
+#define get_max_div(d) DIV_MASK
+#define get_div_field(val) ((val) & DIV_MASK)
+#define get_mux_field(val) (((val) & MUX_MASK) >> MUX_SHIFT)
+
+static const char * const mux_sdmmc_parents[] = {
+	"pll_p", "pll_c4_out2", "pll_c4_out0", "pll_c4_out1", "clk_m"
+};
+
+static const u8 mux_lj_idx[] = {
+	[0] = 0, [1] = 1, [2] = 2, [3] = 5, [4] = 6
+};
+
+static const u8 mux_non_lj_idx[] = {
+	[0] = 0, [1] = 3, [2] = 7, [3] = 4, [4] = 6
+};
+
+static u8 clk_sdmmc_mux_get_parent(struct clk_hw *hw)
+{
+	struct tegra_sdmmc_mux *sdmmc_mux = to_clk_sdmmc_mux(hw);
+	int num_parents, i;
+	u32 src, val;
+	const u8 *mux_idx;
+
+	num_parents = clk_hw_get_num_parents(hw);
+
+	val = readl_relaxed(sdmmc_mux->reg);
+	src = get_mux_field(val);
+	if (get_div_field(val))
+		mux_idx = mux_non_lj_idx;
+	else
+		mux_idx = mux_lj_idx;
+
+	for (i = 0; i < num_parents; i++) {
+		if (mux_idx[i] == src)
+			return i;
+	}
+
+	WARN(1, "Unknown parent selector %d\n", src);
+
+	return 0;
+}
+
+static int clk_sdmmc_mux_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct tegra_sdmmc_mux *sdmmc_mux = to_clk_sdmmc_mux(hw);
+	u32 val;
+
+
+	val = readl_relaxed(sdmmc_mux->reg);
+	if (get_div_field(val))
+		index = mux_non_lj_idx[index];
+	else
+		index = mux_lj_idx[index];
+
+	val &= ~MUX_MASK;
+	val |= index << MUX_SHIFT;
+
+	writel(val, sdmmc_mux->reg);
+
+	return 0;
+}
+
+static unsigned long clk_sdmmc_mux_recalc_rate(struct clk_hw *hw,
+					       unsigned long parent_rate)
+{
+	struct tegra_sdmmc_mux *sdmmc_mux = to_clk_sdmmc_mux(hw);
+	u32 val;
+	int div;
+	u64 rate = parent_rate;
+
+	val = readl_relaxed(sdmmc_mux->reg);
+	div = get_div_field(val);
+
+	div += SDMMC_MUL;
+
+	rate *= SDMMC_MUL;
+	rate += div - 1;
+	do_div(rate, div);
+
+	return rate;
+}
+
+static int clk_sdmmc_mux_determine_rate(struct clk_hw *hw,
+					struct clk_rate_request *req)
+{
+	struct tegra_sdmmc_mux *sdmmc_mux = to_clk_sdmmc_mux(hw);
+	int div;
+	unsigned long output_rate = req->best_parent_rate;
+
+	req->rate = max(req->rate, req->min_rate);
+	req->rate = min(req->rate, req->max_rate);
+
+	if (!req->rate)
+		return output_rate;
+
+	div = div_frac_get(req->rate, output_rate, 8, 1, sdmmc_mux->div_flags);
+	if (div < 0)
+		div = 0;
+
+	if (sdmmc_mux->div_flags & TEGRA_DIVIDER_ROUND_UP)
+		req->rate =  DIV_ROUND_UP(output_rate * SDMMC_MUL,
+					  div + SDMMC_MUL);
+	else
+		req->rate =  output_rate * SDMMC_MUL / (div + SDMMC_MUL);
+
+	return 0;
+}
+
+static int clk_sdmmc_mux_set_rate(struct clk_hw *hw, unsigned long rate,
+				  unsigned long parent_rate)
+{
+	struct tegra_sdmmc_mux *sdmmc_mux = to_clk_sdmmc_mux(hw);
+	int div;
+	unsigned long flags = 0;
+	u32 val;
+	u8 src;
+
+	div = div_frac_get(rate, parent_rate, 8, 1, sdmmc_mux->div_flags);
+	if (div < 0)
+		return div;
+
+	if (sdmmc_mux->lock)
+		spin_lock_irqsave(sdmmc_mux->lock, flags);
+
+	src = clk_sdmmc_mux_get_parent(hw);
+	if (div)
+		src = mux_non_lj_idx[src];
+	else
+		src = mux_lj_idx[src];
+
+	val = src << MUX_SHIFT;
+	val |= div;
+	writel(val, sdmmc_mux->reg);
+	fence_udelay(2, sdmmc_mux->reg);
+
+	if (sdmmc_mux->lock)
+		spin_unlock_irqrestore(sdmmc_mux->lock, flags);
+
+	return 0;
+}
+
+static int clk_sdmmc_mux_is_enabled(struct clk_hw *hw)
+{
+	struct tegra_sdmmc_mux *sdmmc_mux = to_clk_sdmmc_mux(hw);
+	const struct clk_ops *gate_ops = sdmmc_mux->gate_ops;
+	struct clk_hw *gate_hw = &sdmmc_mux->gate.hw;
+
+	__clk_hw_set_clk(gate_hw, hw);
+
+	return gate_ops->is_enabled(gate_hw);
+}
+
+static int clk_sdmmc_mux_enable(struct clk_hw *hw)
+{
+	struct tegra_sdmmc_mux *sdmmc_mux = to_clk_sdmmc_mux(hw);
+	const struct clk_ops *gate_ops = sdmmc_mux->gate_ops;
+	struct clk_hw *gate_hw = &sdmmc_mux->gate.hw;
+
+	__clk_hw_set_clk(gate_hw, hw);
+
+	return gate_ops->enable(gate_hw);
+}
+
+static void clk_sdmmc_mux_disable(struct clk_hw *hw)
+{
+	struct tegra_sdmmc_mux *sdmmc_mux = to_clk_sdmmc_mux(hw);
+	const struct clk_ops *gate_ops = sdmmc_mux->gate_ops;
+	struct clk_hw *gate_hw = &sdmmc_mux->gate.hw;
+
+	gate_ops->disable(gate_hw);
+}
+
+static const struct clk_ops tegra_clk_sdmmc_mux_ops = {
+	.get_parent = clk_sdmmc_mux_get_parent,
+	.set_parent = clk_sdmmc_mux_set_parent,
+	.determine_rate = clk_sdmmc_mux_determine_rate,
+	.recalc_rate = clk_sdmmc_mux_recalc_rate,
+	.set_rate = clk_sdmmc_mux_set_rate,
+	.is_enabled = clk_sdmmc_mux_is_enabled,
+	.enable = clk_sdmmc_mux_enable,
+	.disable = clk_sdmmc_mux_disable,
+};
+
+struct clk *tegra_clk_register_sdmmc_mux_div(const char *name,
+	void __iomem *clk_base, u32 offset, u32 clk_num, u8 div_flags,
+	unsigned long flags, void *lock)
+{
+	struct clk *clk;
+	struct clk_init_data init;
+	const struct tegra_clk_periph_regs *bank;
+	struct tegra_sdmmc_mux *sdmmc_mux;
+
+	init.ops = &tegra_clk_sdmmc_mux_ops;
+	init.name = name;
+	init.flags = flags;
+	init.parent_names = mux_sdmmc_parents;
+	init.num_parents = ARRAY_SIZE(mux_sdmmc_parents);
+
+	bank = get_reg_bank(clk_num);
+	if (!bank)
+		return ERR_PTR(-EINVAL);
+
+	sdmmc_mux = kzalloc(sizeof(*sdmmc_mux), GFP_KERNEL);
+	if (!sdmmc_mux)
+		return ERR_PTR(-ENOMEM);
+
+	/* Data in .init is copied by clk_register(), so stack variable OK */
+	sdmmc_mux->hw.init = &init;
+	sdmmc_mux->reg = clk_base + offset;
+	sdmmc_mux->lock = lock;
+	sdmmc_mux->gate.clk_base = clk_base;
+	sdmmc_mux->gate.regs = bank;
+	sdmmc_mux->gate.enable_refcnt = periph_clk_enb_refcnt;
+	sdmmc_mux->gate.clk_num = clk_num;
+	sdmmc_mux->gate.flags = TEGRA_PERIPH_ON_APB;
+	sdmmc_mux->div_flags = div_flags;
+	sdmmc_mux->gate_ops = &tegra_clk_periph_gate_ops;
+
+	clk = clk_register(NULL, &sdmmc_mux->hw);
+	if (IS_ERR(clk)) {
+		kfree(sdmmc_mux);
+		return clk;
+	}
+
+	sdmmc_mux->gate.hw.clk = clk;
+
+	return clk;
+}
diff --git a/drivers/clk/tegra/clk-tegra-periph.c b/drivers/clk/tegra/clk-tegra-periph.c
index 2acba2986bc6..38c4eb28c8bf 100644
--- a/drivers/clk/tegra/clk-tegra-periph.c
+++ b/drivers/clk/tegra/clk-tegra-periph.c
@@ -451,15 +451,6 @@ static u32 mux_pllp_pllc4_out2_pllc4_out1_clkm_pllc4_out0_idx[] = {
 	[0] = 0, [1] = 3, [2] = 4, [3] = 6, [4] = 7,
 };
 
-static const char *mux_pllp_clkm_pllc4_out2_out1_out0_lj[] = {
-	"pll_p",
-	"pll_c4_out2", "pll_c4_out0",	/* LJ input */
-	"pll_c4_out2", "pll_c4_out1",
-	"pll_c4_out1",			/* LJ input */
-	"clk_m", "pll_c4_out0"
-};
-#define mux_pllp_clkm_pllc4_out2_out1_out0_lj_idx NULL
-
 static const char *mux_pllp_pllc2_c_c3_clkm[] = {
 	"pll_p", "pll_c2", "pll_c", "pll_c3", "clk_m"
 };
@@ -686,9 +677,7 @@ static struct tegra_periph_init_data periph_clks[] = {
 	MUX("sdmmc3", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_SDMMC3, 69, TEGRA_PERIPH_ON_APB, tegra_clk_sdmmc3),
 	MUX("sdmmc4", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_SDMMC4, 15, TEGRA_PERIPH_ON_APB, tegra_clk_sdmmc4),
 	MUX8("sdmmc1", mux_pllp_pllc4_out2_pllc4_out1_clkm_pllc4_out0, CLK_SOURCE_SDMMC1, 14, TEGRA_PERIPH_ON_APB, tegra_clk_sdmmc1_9),
-	MUX8("sdmmc2", mux_pllp_clkm_pllc4_out2_out1_out0_lj, CLK_SOURCE_SDMMC2, 9, TEGRA_PERIPH_ON_APB, tegra_clk_sdmmc2_9),
 	MUX8("sdmmc3", mux_pllp_pllc4_out2_pllc4_out1_clkm_pllc4_out0, CLK_SOURCE_SDMMC3, 69, TEGRA_PERIPH_ON_APB, tegra_clk_sdmmc3_9),
-	MUX8("sdmmc4", mux_pllp_clkm_pllc4_out2_out1_out0_lj, CLK_SOURCE_SDMMC4, 15, TEGRA_PERIPH_ON_APB, tegra_clk_sdmmc4_9),
 	MUX("la", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_LA, 76, TEGRA_PERIPH_ON_APB, tegra_clk_la),
 	MUX("trace", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_TRACE, 77, TEGRA_PERIPH_ON_APB, tegra_clk_trace),
 	MUX("owr", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_OWR, 71, TEGRA_PERIPH_ON_APB, tegra_clk_owr),
diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c
index 0c69c7970950..b6cf28ca2ed2 100644
--- a/drivers/clk/tegra/clk-tegra124.c
+++ b/drivers/clk/tegra/clk-tegra124.c
@@ -1267,7 +1267,7 @@ static struct tegra_clk_init_table common_init_table[] __initdata = {
 	{ TEGRA124_CLK_I2S2, TEGRA124_CLK_PLL_A_OUT0, 11289600, 0 },
 	{ TEGRA124_CLK_I2S3, TEGRA124_CLK_PLL_A_OUT0, 11289600, 0 },
 	{ TEGRA124_CLK_I2S4, TEGRA124_CLK_PLL_A_OUT0, 11289600, 0 },
-	{ TEGRA124_CLK_VDE, TEGRA124_CLK_CLK_MAX, 600000000, 0 },
+	{ TEGRA124_CLK_VDE, TEGRA124_CLK_PLL_C3, 600000000, 0 },
 	{ TEGRA124_CLK_HOST1X, TEGRA124_CLK_PLL_P, 136000000, 1 },
 	{ TEGRA124_CLK_DSIALP, TEGRA124_CLK_PLL_P, 68000000, 0 },
 	{ TEGRA124_CLK_DSIBLP, TEGRA124_CLK_PLL_P, 68000000, 0 },
@@ -1290,6 +1290,7 @@ static struct tegra_clk_init_table common_init_table[] __initdata = {
 	{ TEGRA124_CLK_MSELECT, TEGRA124_CLK_CLK_MAX, 0, 1 },
 	{ TEGRA124_CLK_CSITE, TEGRA124_CLK_CLK_MAX, 0, 1 },
 	{ TEGRA124_CLK_TSENSOR, TEGRA124_CLK_CLK_M, 400000, 0 },
+	{ TEGRA124_CLK_VIC03, TEGRA124_CLK_PLL_C3, 0, 0 },
 	/* must be the last entry */
 	{ TEGRA124_CLK_CLK_MAX, TEGRA124_CLK_CLK_MAX, 0, 0 },
 };
diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c
index 5435d01c636a..9eb1cb14fce1 100644
--- a/drivers/clk/tegra/clk-tegra210.c
+++ b/drivers/clk/tegra/clk-tegra210.c
@@ -44,6 +44,8 @@
 #define CLK_SOURCE_EMC 0x19c
 #define CLK_SOURCE_SOR1 0x410
 #define CLK_SOURCE_LA 0x1f8
+#define CLK_SOURCE_SDMMC2 0x154
+#define CLK_SOURCE_SDMMC4 0x164
 
 #define PLLC_BASE 0x80
 #define PLLC_OUT 0x84
@@ -2286,11 +2288,9 @@ static struct tegra_clk tegra210_clks[tegra_clk_max] __initdata = {
 	[tegra_clk_rtc] = { .dt_id = TEGRA210_CLK_RTC, .present = true },
 	[tegra_clk_timer] = { .dt_id = TEGRA210_CLK_TIMER, .present = true },
 	[tegra_clk_uarta_8] = { .dt_id = TEGRA210_CLK_UARTA, .present = true },
-	[tegra_clk_sdmmc2_9] = { .dt_id = TEGRA210_CLK_SDMMC2, .present = true },
 	[tegra_clk_i2s1] = { .dt_id = TEGRA210_CLK_I2S1, .present = true },
 	[tegra_clk_i2c1] = { .dt_id = TEGRA210_CLK_I2C1, .present = true },
 	[tegra_clk_sdmmc1_9] = { .dt_id = TEGRA210_CLK_SDMMC1, .present = true },
-	[tegra_clk_sdmmc4_9] = { .dt_id = TEGRA210_CLK_SDMMC4, .present = true },
 	[tegra_clk_pwm] = { .dt_id = TEGRA210_CLK_PWM, .present = true },
 	[tegra_clk_i2s2] = { .dt_id = TEGRA210_CLK_I2S2, .present = true },
 	[tegra_clk_usbd] = { .dt_id = TEGRA210_CLK_USBD, .present = true },
@@ -3030,6 +3030,16 @@ static __init void tegra210_periph_clk_init(void __iomem *clk_base,
 				0, NULL);
 	clks[TEGRA210_CLK_ACLK] = clk;
 
+	clk = tegra_clk_register_sdmmc_mux_div("sdmmc2", clk_base,
+					    CLK_SOURCE_SDMMC2, 9,
+					    TEGRA_DIVIDER_ROUND_UP, 0, NULL);
+	clks[TEGRA210_CLK_SDMMC2] = clk;
+
+	clk = tegra_clk_register_sdmmc_mux_div("sdmmc4", clk_base,
+					    CLK_SOURCE_SDMMC4, 15,
+					    TEGRA_DIVIDER_ROUND_UP, 0, NULL);
+	clks[TEGRA210_CLK_SDMMC4] = clk;
+
 	for (i = 0; i < ARRAY_SIZE(tegra210_periph); i++) {
 		struct tegra_periph_init_data *init = &tegra210_periph[i];
 		struct clk **clkp;
diff --git a/drivers/clk/tegra/clk-utils.c b/drivers/clk/tegra/clk-utils.c
new file mode 100644
index 000000000000..1a5daae4e501
--- /dev/null
+++ b/drivers/clk/tegra/clk-utils.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018, NVIDIA CORPORATION.  All rights reserved.
+ */
+
+#include <asm/div64.h>
+
+#include "clk.h"
+
+#define div_mask(w) ((1 << (w)) - 1)
+
+int div_frac_get(unsigned long rate, unsigned parent_rate, u8 width,
+		 u8 frac_width, u8 flags)
+{
+	u64 divider_ux1 = parent_rate;
+	int mul;
+
+	if (!rate)
+		return 0;
+
+	mul = 1 << frac_width;
+
+	if (!(flags & TEGRA_DIVIDER_INT))
+		divider_ux1 *= mul;
+
+	if (flags & TEGRA_DIVIDER_ROUND_UP)
+		divider_ux1 += rate - 1;
+
+	do_div(divider_ux1, rate);
+
+	if (flags & TEGRA_DIVIDER_INT)
+		divider_ux1 *= mul;
+
+	if (divider_ux1 < mul)
+		return 0;
+
+	divider_ux1 -= mul;
+
+	if (divider_ux1 > div_mask(width))
+		return div_mask(width);
+
+	return divider_ux1;
+}
diff --git a/drivers/clk/tegra/clk.h b/drivers/clk/tegra/clk.h
index e1f88463b600..d2c3a010f8e9 100644
--- a/drivers/clk/tegra/clk.h
+++ b/drivers/clk/tegra/clk.h
@@ -19,6 +19,7 @@
 
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
+#include <linux/delay.h>
 
 /**
  * struct tegra_clk_sync_source - external clock source from codec
@@ -705,6 +706,32 @@ struct clk *tegra_clk_register_super_clk(const char *name,
 		const char * const *parent_names, u8 num_parents,
 		unsigned long flags, void __iomem *reg, u8 clk_super_flags,
 		spinlock_t *lock);
+
+/**
+ * struct tegra_sdmmc_mux - switch divider with Low Jitter inputs for SDMMC
+ *
+ * @hw:		handle between common and hardware-specific interfaces
+ * @reg:	register controlling mux and divider
+ * @flags:	hardware-specific flags
+ * @lock:	optional register lock
+ * @gate:	gate clock
+ * @gate_ops:	gate clock ops
+ */
+struct tegra_sdmmc_mux {
+	struct clk_hw		hw;
+	void __iomem		*reg;
+	spinlock_t		*lock;
+	const struct clk_ops	*gate_ops;
+	struct tegra_clk_periph_gate	gate;
+	u8			div_flags;
+};
+
+#define to_clk_sdmmc_mux(_hw) container_of(_hw, struct tegra_sdmmc_mux, hw)
+
+struct clk *tegra_clk_register_sdmmc_mux_div(const char *name,
+		void __iomem *clk_base, u32 offset, u32 clk_num, u8 div_flags,
+		unsigned long flags, void *lock);
+
 /**
  * struct clk_init_table - clock initialization table
  * @clk_id:	clock id as mentioned in device tree bindings
@@ -811,6 +838,9 @@ extern tegra_clk_apply_init_table_func tegra_clk_apply_init_table;
 int tegra_pll_wait_for_lock(struct tegra_clk_pll *pll);
 u16 tegra_pll_get_fixed_mdiv(struct clk_hw *hw, unsigned long input_rate);
 int tegra_pll_p_div_to_hw(struct tegra_clk_pll *pll, u8 p_div);
+int div_frac_get(unsigned long rate, unsigned parent_rate, u8 width,
+		 u8 frac_width, u8 flags);
+
 
 /* Combined read fence with delay */
 #define fence_udelay(delay, reg)	\
diff --git a/drivers/clk/uniphier/clk-uniphier-peri.c b/drivers/clk/uniphier/clk-uniphier-peri.c
index 521c80e9a06f..89b3ac378b3f 100644
--- a/drivers/clk/uniphier/clk-uniphier-peri.c
+++ b/drivers/clk/uniphier/clk-uniphier-peri.c
@@ -27,6 +27,12 @@
 #define UNIPHIER_PERI_CLK_FI2C(idx, ch)					\
 	UNIPHIER_CLK_GATE("i2c" #ch, (idx), "i2c", 0x24, 24 + (ch))
 
+#define UNIPHIER_PERI_CLK_SCSSI(idx)					\
+	UNIPHIER_CLK_GATE("scssi", (idx), "spi", 0x20, 17)
+
+#define UNIPHIER_PERI_CLK_MCSSI(idx)					\
+	UNIPHIER_CLK_GATE("mcssi", (idx), "spi", 0x24, 14)
+
 const struct uniphier_clk_data uniphier_ld4_peri_clk_data[] = {
 	UNIPHIER_PERI_CLK_UART(0, 0),
 	UNIPHIER_PERI_CLK_UART(1, 1),
@@ -38,6 +44,7 @@ const struct uniphier_clk_data uniphier_ld4_peri_clk_data[] = {
 	UNIPHIER_PERI_CLK_I2C(6, 2),
 	UNIPHIER_PERI_CLK_I2C(7, 3),
 	UNIPHIER_PERI_CLK_I2C(8, 4),
+	UNIPHIER_PERI_CLK_SCSSI(11),
 	{ /* sentinel */ }
 };
 
@@ -53,5 +60,7 @@ const struct uniphier_clk_data uniphier_pro4_peri_clk_data[] = {
 	UNIPHIER_PERI_CLK_FI2C(8, 4),
 	UNIPHIER_PERI_CLK_FI2C(9, 5),
 	UNIPHIER_PERI_CLK_FI2C(10, 6),
+	UNIPHIER_PERI_CLK_SCSSI(11),
+	UNIPHIER_PERI_CLK_MCSSI(12),
 	{ /* sentinel */ }
 };
diff --git a/drivers/clk/uniphier/clk-uniphier-sys.c b/drivers/clk/uniphier/clk-uniphier-sys.c
index 4f5ff9fa11fd..2bb5a8570adc 100644
--- a/drivers/clk/uniphier/clk-uniphier-sys.c
+++ b/drivers/clk/uniphier/clk-uniphier-sys.c
@@ -29,18 +29,20 @@
 	UNIPHIER_CLK_FACTOR("sd-200m", -1, "spll", 1, 10),		\
 	UNIPHIER_CLK_FACTOR("sd-133m", -1, "spll", 1, 15)
 
-/* Denali driver requires clk_x rate (clk: 50MHz, clk_x & ecc_clk: 200MHz) */
 #define UNIPHIER_LD4_SYS_CLK_NAND(idx)					\
-	UNIPHIER_CLK_FACTOR("nand-200m", -1, "spll", 1, 8),		\
-	UNIPHIER_CLK_GATE("nand", (idx), "nand-200m", 0x2104, 2)
+	UNIPHIER_CLK_FACTOR("nand-50m", -1, "spll", 1, 32),		\
+	UNIPHIER_CLK_GATE("nand", (idx), "nand-50m", 0x2104, 2)
 
 #define UNIPHIER_PRO5_SYS_CLK_NAND(idx)					\
-	UNIPHIER_CLK_FACTOR("nand-200m", -1, "spll", 1, 12),		\
-	UNIPHIER_CLK_GATE("nand", (idx), "nand-200m", 0x2104, 2)
+	UNIPHIER_CLK_FACTOR("nand-50m", -1, "spll", 1, 48),		\
+	UNIPHIER_CLK_GATE("nand", (idx), "nand-50m", 0x2104, 2)
 
 #define UNIPHIER_LD11_SYS_CLK_NAND(idx)					\
-	UNIPHIER_CLK_FACTOR("nand-200m", -1, "spll", 1, 10),		\
-	UNIPHIER_CLK_GATE("nand", (idx), "nand-200m", 0x210c, 0)
+	UNIPHIER_CLK_FACTOR("nand-50m", -1, "spll", 1, 40),		\
+	UNIPHIER_CLK_GATE("nand", (idx), "nand-50m", 0x210c, 0)
+
+#define UNIPHIER_SYS_CLK_NAND_4X(idx)					\
+	UNIPHIER_CLK_FACTOR("nand-4x", (idx), "nand", 4, 1)
 
 #define UNIPHIER_LD11_SYS_CLK_EMMC(idx)					\
 	UNIPHIER_CLK_GATE("emmc", (idx), NULL, 0x210c, 2)
@@ -93,7 +95,9 @@ const struct uniphier_clk_data uniphier_ld4_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("vpll27a", -1, "ref", 5625, 512),	/* 270 MHz */
 	UNIPHIER_CLK_FACTOR("uart", 0, "a2pll", 1, 16),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 16),
+	UNIPHIER_CLK_FACTOR("spi", -1, "spll", 1, 32),
 	UNIPHIER_LD4_SYS_CLK_NAND(2),
+	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_LD4_SYS_CLK_SD,
 	UNIPHIER_CLK_FACTOR("usb2", -1, "upll", 1, 12),
 	UNIPHIER_LD4_SYS_CLK_STDMAC(8),			/* Ether, HSC, MIO */
@@ -108,7 +112,9 @@ const struct uniphier_clk_data uniphier_pro4_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("gpll", -1, "ref", 10, 1),		/* 250 MHz */
 	UNIPHIER_CLK_FACTOR("uart", 0, "a2pll", 1, 8),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 32),
+	UNIPHIER_CLK_FACTOR("spi", 1, "spll", 1, 32),
 	UNIPHIER_LD4_SYS_CLK_NAND(2),
+	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_LD4_SYS_CLK_SD,
 	UNIPHIER_CLK_FACTOR("usb2", -1, "upll", 1, 12),
 	UNIPHIER_PRO4_SYS_CLK_ETHER(6),
@@ -118,6 +124,9 @@ const struct uniphier_clk_data uniphier_pro4_sys_clk_data[] = {
 	UNIPHIER_PRO4_SYS_CLK_GIO(12),			/* Ether, SATA, USB3 */
 	UNIPHIER_PRO4_SYS_CLK_USB3(14, 0),
 	UNIPHIER_PRO4_SYS_CLK_USB3(15, 1),
+	UNIPHIER_CLK_FACTOR("usb30-hsphy0", 16, "upll", 1, 12),
+	UNIPHIER_CLK_FACTOR("usb30-ssphy0", 17, "ref", 1, 1),
+	UNIPHIER_CLK_FACTOR("usb31-ssphy0", 20, "ref", 1, 1),
 	UNIPHIER_CLK_GATE("sata0", 28, NULL, 0x2104, 18),
 	UNIPHIER_CLK_GATE("sata1", 29, NULL, 0x2104, 19),
 	UNIPHIER_PRO4_SYS_CLK_AIO(40),
@@ -130,7 +139,9 @@ const struct uniphier_clk_data uniphier_sld8_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("vpll27a", -1, "ref", 270, 25),	/* 270 MHz */
 	UNIPHIER_CLK_FACTOR("uart", 0, "spll", 1, 20),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 16),
+	UNIPHIER_CLK_FACTOR("spi", -1, "spll", 1, 32),
 	UNIPHIER_LD4_SYS_CLK_NAND(2),
+	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_LD4_SYS_CLK_SD,
 	UNIPHIER_CLK_FACTOR("usb2", -1, "upll", 1, 12),
 	UNIPHIER_LD4_SYS_CLK_STDMAC(8),			/* Ether, HSC, MIO */
@@ -143,7 +154,9 @@ const struct uniphier_clk_data uniphier_pro5_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("dapll2", -1, "dapll1", 144, 125),	/* 2949.12 MHz */
 	UNIPHIER_CLK_FACTOR("uart", 0, "dapll2", 1, 40),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 48),
+	UNIPHIER_CLK_FACTOR("spi", -1, "spll", 1, 48),
 	UNIPHIER_PRO5_SYS_CLK_NAND(2),
+	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_PRO5_SYS_CLK_SD,
 	UNIPHIER_LD4_SYS_CLK_STDMAC(8),				/* HSC */
 	UNIPHIER_PRO4_SYS_CLK_GIO(12),				/* PCIe, USB3 */
@@ -158,7 +171,9 @@ const struct uniphier_clk_data uniphier_pxs2_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("spll", -1, "ref", 96, 1),		/* 2400 MHz */
 	UNIPHIER_CLK_FACTOR("uart", 0, "spll", 1, 27),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 48),
+	UNIPHIER_CLK_FACTOR("spi", -1, "spll", 1, 48),
 	UNIPHIER_PRO5_SYS_CLK_NAND(2),
+	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_PRO5_SYS_CLK_SD,
 	UNIPHIER_PRO4_SYS_CLK_ETHER(6),
 	UNIPHIER_LD4_SYS_CLK_STDMAC(8),				/* HSC, RLE */
@@ -166,8 +181,11 @@ const struct uniphier_clk_data uniphier_pxs2_sys_clk_data[] = {
 	UNIPHIER_PRO4_SYS_CLK_USB3(14, 0),
 	UNIPHIER_PRO4_SYS_CLK_USB3(15, 1),
 	/* The document mentions 0x2104 bit 18, but not functional */
-	UNIPHIER_CLK_GATE("usb30-phy", 16, NULL, 0x2104, 19),
-	UNIPHIER_CLK_GATE("usb31-phy", 20, NULL, 0x2104, 20),
+	UNIPHIER_CLK_GATE("usb30-hsphy0", 16, NULL, 0x2104, 19),
+	UNIPHIER_CLK_FACTOR("usb30-ssphy0", 17, "ref", 1, 1),
+	UNIPHIER_CLK_FACTOR("usb30-ssphy1", 18, "ref", 1, 1),
+	UNIPHIER_CLK_GATE("usb31-hsphy0", 20, NULL, 0x2104, 20),
+	UNIPHIER_CLK_FACTOR("usb31-ssphy0", 21, "ref", 1, 1),
 	UNIPHIER_CLK_GATE("sata0", 28, NULL, 0x2104, 22),
 	UNIPHIER_PRO5_SYS_CLK_AIO(40),
 	{ /* sentinel */ }
@@ -180,7 +198,9 @@ const struct uniphier_clk_data uniphier_ld11_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("vspll", -1, "ref", 80, 1),		/* 2000 MHz */
 	UNIPHIER_CLK_FACTOR("uart", 0, "spll", 1, 34),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 40),
+	UNIPHIER_CLK_FACTOR("spi", -1, "spll", 1, 40),
 	UNIPHIER_LD11_SYS_CLK_NAND(2),
+	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_LD11_SYS_CLK_EMMC(4),
 	/* Index 5 reserved for eMMC PHY */
 	UNIPHIER_LD11_SYS_CLK_ETHER(6),
@@ -213,7 +233,9 @@ const struct uniphier_clk_data uniphier_ld20_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("vppll", -1, "ref", 504, 5),	/* 2520 MHz */
 	UNIPHIER_CLK_FACTOR("uart", 0, "spll", 1, 34),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 40),
+	UNIPHIER_CLK_FACTOR("spi", -1, "spll", 1, 40),
 	UNIPHIER_LD11_SYS_CLK_NAND(2),
+	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_LD11_SYS_CLK_EMMC(4),
 	/* Index 5 reserved for eMMC PHY */
 	UNIPHIER_LD20_SYS_CLK_SD,
@@ -226,8 +248,10 @@ const struct uniphier_clk_data uniphier_ld20_sys_clk_data[] = {
 	 * We do not use bit 15 here.
 	 */
 	UNIPHIER_CLK_GATE("usb30", 14, NULL, 0x210c, 14),
-	UNIPHIER_CLK_GATE("usb30-phy0", 16, NULL, 0x210c, 12),
-	UNIPHIER_CLK_GATE("usb30-phy1", 17, NULL, 0x210c, 13),
+	UNIPHIER_CLK_GATE("usb30-hsphy0", 16, NULL, 0x210c, 12),
+	UNIPHIER_CLK_GATE("usb30-hsphy1", 17, NULL, 0x210c, 13),
+	UNIPHIER_CLK_FACTOR("usb30-ssphy0", 18, "ref", 1, 1),
+	UNIPHIER_CLK_FACTOR("usb30-ssphy1", 19, "ref", 1, 1),
 	UNIPHIER_CLK_GATE("pcie", 24, NULL, 0x210c, 4),
 	UNIPHIER_LD11_SYS_CLK_AIO(40),
 	UNIPHIER_LD11_SYS_CLK_EVEA(41),
@@ -254,19 +278,21 @@ const struct uniphier_clk_data uniphier_pxs3_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("s2pll", -1, "ref", 88, 1),		/* IPP: 2400 MHz */
 	UNIPHIER_CLK_FACTOR("uart", 0, "spll", 1, 34),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 40),
+	UNIPHIER_CLK_FACTOR("spi", -1, "spll", 1, 40),
 	UNIPHIER_LD20_SYS_CLK_SD,
 	UNIPHIER_LD11_SYS_CLK_NAND(2),
+	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_LD11_SYS_CLK_EMMC(4),
 	UNIPHIER_CLK_GATE("ether0", 6, NULL, 0x210c, 9),
 	UNIPHIER_CLK_GATE("ether1", 7, NULL, 0x210c, 10),
 	UNIPHIER_CLK_GATE("usb30", 12, NULL, 0x210c, 4),	/* =GIO0 */
 	UNIPHIER_CLK_GATE("usb31-0", 13, NULL, 0x210c, 5),	/* =GIO1 */
 	UNIPHIER_CLK_GATE("usb31-1", 14, NULL, 0x210c, 6),	/* =GIO1-1 */
-	UNIPHIER_CLK_GATE("usb30-phy0", 16, NULL, 0x210c, 16),
-	UNIPHIER_CLK_GATE("usb30-phy1", 17, NULL, 0x210c, 18),
-	UNIPHIER_CLK_GATE("usb30-phy2", 18, NULL, 0x210c, 20),
-	UNIPHIER_CLK_GATE("usb31-phy0", 20, NULL, 0x210c, 17),
-	UNIPHIER_CLK_GATE("usb31-phy1", 21, NULL, 0x210c, 19),
+	UNIPHIER_CLK_GATE("usb30-hsphy0", 16, NULL, 0x210c, 16),
+	UNIPHIER_CLK_GATE("usb30-ssphy0", 17, NULL, 0x210c, 18),
+	UNIPHIER_CLK_GATE("usb30-ssphy1", 18, NULL, 0x210c, 20),
+	UNIPHIER_CLK_GATE("usb31-hsphy0", 20, NULL, 0x210c, 17),
+	UNIPHIER_CLK_GATE("usb31-ssphy0", 21, NULL, 0x210c, 19),
 	UNIPHIER_CLK_GATE("pcie", 24, NULL, 0x210c, 3),
 	UNIPHIER_CLK_GATE("sata0", 28, NULL, 0x210c, 7),
 	UNIPHIER_CLK_GATE("sata1", 29, NULL, 0x210c, 8),
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index 00caf37e52f9..c070cc7992e9 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -49,7 +49,7 @@ obj-$(CONFIG_CLKSRC_SAMSUNG_PWM)	+= samsung_pwm_timer.o
 obj-$(CONFIG_FSL_FTM_TIMER)	+= fsl_ftm_timer.o
 obj-$(CONFIG_VF_PIT_TIMER)	+= vf_pit_timer.o
 obj-$(CONFIG_CLKSRC_QCOM)	+= qcom-timer.o
-obj-$(CONFIG_MTK_TIMER)		+= mtk_timer.o
+obj-$(CONFIG_MTK_TIMER)		+= timer-mediatek.o
 obj-$(CONFIG_CLKSRC_PISTACHIO)	+= time-pistachio.o
 obj-$(CONFIG_CLKSRC_TI_32K)	+= timer-ti-32k.o
 obj-$(CONFIG_CLKSRC_NPS)	+= timer-nps.o
diff --git a/drivers/clocksource/mtk_timer.c b/drivers/clocksource/mtk_timer.c
deleted file mode 100644
index f9b724fd9950..000000000000
--- a/drivers/clocksource/mtk_timer.c
+++ /dev/null
@@ -1,268 +0,0 @@
-/*
- * Mediatek SoCs General-Purpose Timer handling.
- *
- * Copyright (C) 2014 Matthias Brugger
- *
- * Matthias Brugger <matthias.bgg@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
-
-#include <linux/clk.h>
-#include <linux/clockchips.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/irqreturn.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/sched_clock.h>
-#include <linux/slab.h>
-
-#define GPT_IRQ_EN_REG		0x00
-#define GPT_IRQ_ENABLE(val)	BIT((val) - 1)
-#define GPT_IRQ_ACK_REG		0x08
-#define GPT_IRQ_ACK(val)	BIT((val) - 1)
-
-#define TIMER_CTRL_REG(val)	(0x10 * (val))
-#define TIMER_CTRL_OP(val)	(((val) & 0x3) << 4)
-#define TIMER_CTRL_OP_ONESHOT	(0)
-#define TIMER_CTRL_OP_REPEAT	(1)
-#define TIMER_CTRL_OP_FREERUN	(3)
-#define TIMER_CTRL_CLEAR	(2)
-#define TIMER_CTRL_ENABLE	(1)
-#define TIMER_CTRL_DISABLE	(0)
-
-#define TIMER_CLK_REG(val)	(0x04 + (0x10 * (val)))
-#define TIMER_CLK_SRC(val)	(((val) & 0x1) << 4)
-#define TIMER_CLK_SRC_SYS13M	(0)
-#define TIMER_CLK_SRC_RTC32K	(1)
-#define TIMER_CLK_DIV1		(0x0)
-#define TIMER_CLK_DIV2		(0x1)
-
-#define TIMER_CNT_REG(val)	(0x08 + (0x10 * (val)))
-#define TIMER_CMP_REG(val)	(0x0C + (0x10 * (val)))
-
-#define GPT_CLK_EVT	1
-#define GPT_CLK_SRC	2
-
-struct mtk_clock_event_device {
-	void __iomem *gpt_base;
-	u32 ticks_per_jiffy;
-	struct clock_event_device dev;
-};
-
-static void __iomem *gpt_sched_reg __read_mostly;
-
-static u64 notrace mtk_read_sched_clock(void)
-{
-	return readl_relaxed(gpt_sched_reg);
-}
-
-static inline struct mtk_clock_event_device *to_mtk_clk(
-				struct clock_event_device *c)
-{
-	return container_of(c, struct mtk_clock_event_device, dev);
-}
-
-static void mtk_clkevt_time_stop(struct mtk_clock_event_device *evt, u8 timer)
-{
-	u32 val;
-
-	val = readl(evt->gpt_base + TIMER_CTRL_REG(timer));
-	writel(val & ~TIMER_CTRL_ENABLE, evt->gpt_base +
-			TIMER_CTRL_REG(timer));
-}
-
-static void mtk_clkevt_time_setup(struct mtk_clock_event_device *evt,
-				unsigned long delay, u8 timer)
-{
-	writel(delay, evt->gpt_base + TIMER_CMP_REG(timer));
-}
-
-static void mtk_clkevt_time_start(struct mtk_clock_event_device *evt,
-		bool periodic, u8 timer)
-{
-	u32 val;
-
-	/* Acknowledge interrupt */
-	writel(GPT_IRQ_ACK(timer), evt->gpt_base + GPT_IRQ_ACK_REG);
-
-	val = readl(evt->gpt_base + TIMER_CTRL_REG(timer));
-
-	/* Clear 2 bit timer operation mode field */
-	val &= ~TIMER_CTRL_OP(0x3);
-
-	if (periodic)
-		val |= TIMER_CTRL_OP(TIMER_CTRL_OP_REPEAT);
-	else
-		val |= TIMER_CTRL_OP(TIMER_CTRL_OP_ONESHOT);
-
-	writel(val | TIMER_CTRL_ENABLE | TIMER_CTRL_CLEAR,
-	       evt->gpt_base + TIMER_CTRL_REG(timer));
-}
-
-static int mtk_clkevt_shutdown(struct clock_event_device *clk)
-{
-	mtk_clkevt_time_stop(to_mtk_clk(clk), GPT_CLK_EVT);
-	return 0;
-}
-
-static int mtk_clkevt_set_periodic(struct clock_event_device *clk)
-{
-	struct mtk_clock_event_device *evt = to_mtk_clk(clk);
-
-	mtk_clkevt_time_stop(evt, GPT_CLK_EVT);
-	mtk_clkevt_time_setup(evt, evt->ticks_per_jiffy, GPT_CLK_EVT);
-	mtk_clkevt_time_start(evt, true, GPT_CLK_EVT);
-	return 0;
-}
-
-static int mtk_clkevt_next_event(unsigned long event,
-				   struct clock_event_device *clk)
-{
-	struct mtk_clock_event_device *evt = to_mtk_clk(clk);
-
-	mtk_clkevt_time_stop(evt, GPT_CLK_EVT);
-	mtk_clkevt_time_setup(evt, event, GPT_CLK_EVT);
-	mtk_clkevt_time_start(evt, false, GPT_CLK_EVT);
-
-	return 0;
-}
-
-static irqreturn_t mtk_timer_interrupt(int irq, void *dev_id)
-{
-	struct mtk_clock_event_device *evt = dev_id;
-
-	/* Acknowledge timer0 irq */
-	writel(GPT_IRQ_ACK(GPT_CLK_EVT), evt->gpt_base + GPT_IRQ_ACK_REG);
-	evt->dev.event_handler(&evt->dev);
-
-	return IRQ_HANDLED;
-}
-
-static void
-__init mtk_timer_setup(struct mtk_clock_event_device *evt, u8 timer, u8 option)
-{
-	writel(TIMER_CTRL_CLEAR | TIMER_CTRL_DISABLE,
-		evt->gpt_base + TIMER_CTRL_REG(timer));
-
-	writel(TIMER_CLK_SRC(TIMER_CLK_SRC_SYS13M) | TIMER_CLK_DIV1,
-			evt->gpt_base + TIMER_CLK_REG(timer));
-
-	writel(0x0, evt->gpt_base + TIMER_CMP_REG(timer));
-
-	writel(TIMER_CTRL_OP(option) | TIMER_CTRL_ENABLE,
-			evt->gpt_base + TIMER_CTRL_REG(timer));
-}
-
-static void mtk_timer_enable_irq(struct mtk_clock_event_device *evt, u8 timer)
-{
-	u32 val;
-
-	/* Disable all interrupts */
-	writel(0x0, evt->gpt_base + GPT_IRQ_EN_REG);
-
-	/* Acknowledge all spurious pending interrupts */
-	writel(0x3f, evt->gpt_base + GPT_IRQ_ACK_REG);
-
-	val = readl(evt->gpt_base + GPT_IRQ_EN_REG);
-	writel(val | GPT_IRQ_ENABLE(timer),
-			evt->gpt_base + GPT_IRQ_EN_REG);
-}
-
-static int __init mtk_timer_init(struct device_node *node)
-{
-	struct mtk_clock_event_device *evt;
-	struct resource res;
-	unsigned long rate = 0;
-	struct clk *clk;
-
-	evt = kzalloc(sizeof(*evt), GFP_KERNEL);
-	if (!evt)
-		return -ENOMEM;
-
-	evt->dev.name = "mtk_tick";
-	evt->dev.rating = 300;
-	evt->dev.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
-	evt->dev.set_state_shutdown = mtk_clkevt_shutdown;
-	evt->dev.set_state_periodic = mtk_clkevt_set_periodic;
-	evt->dev.set_state_oneshot = mtk_clkevt_shutdown;
-	evt->dev.tick_resume = mtk_clkevt_shutdown;
-	evt->dev.set_next_event = mtk_clkevt_next_event;
-	evt->dev.cpumask = cpu_possible_mask;
-
-	evt->gpt_base = of_io_request_and_map(node, 0, "mtk-timer");
-	if (IS_ERR(evt->gpt_base)) {
-		pr_err("Can't get resource\n");
-		goto err_kzalloc;
-	}
-
-	evt->dev.irq = irq_of_parse_and_map(node, 0);
-	if (evt->dev.irq <= 0) {
-		pr_err("Can't parse IRQ\n");
-		goto err_mem;
-	}
-
-	clk = of_clk_get(node, 0);
-	if (IS_ERR(clk)) {
-		pr_err("Can't get timer clock\n");
-		goto err_irq;
-	}
-
-	if (clk_prepare_enable(clk)) {
-		pr_err("Can't prepare clock\n");
-		goto err_clk_put;
-	}
-	rate = clk_get_rate(clk);
-
-	if (request_irq(evt->dev.irq, mtk_timer_interrupt,
-			IRQF_TIMER | IRQF_IRQPOLL, "mtk_timer", evt)) {
-		pr_err("failed to setup irq %d\n", evt->dev.irq);
-		goto err_clk_disable;
-	}
-
-	evt->ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
-
-	/* Configure clock source */
-	mtk_timer_setup(evt, GPT_CLK_SRC, TIMER_CTRL_OP_FREERUN);
-	clocksource_mmio_init(evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC),
-			node->name, rate, 300, 32, clocksource_mmio_readl_up);
-	gpt_sched_reg = evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC);
-	sched_clock_register(mtk_read_sched_clock, 32, rate);
-
-	/* Configure clock event */
-	mtk_timer_setup(evt, GPT_CLK_EVT, TIMER_CTRL_OP_REPEAT);
-	clockevents_config_and_register(&evt->dev, rate, 0x3,
-					0xffffffff);
-
-	mtk_timer_enable_irq(evt, GPT_CLK_EVT);
-
-	return 0;
-
-err_clk_disable:
-	clk_disable_unprepare(clk);
-err_clk_put:
-	clk_put(clk);
-err_irq:
-	irq_dispose_mapping(evt->dev.irq);
-err_mem:
-	iounmap(evt->gpt_base);
-	of_address_to_resource(node, 0, &res);
-	release_mem_region(res.start, resource_size(&res));
-err_kzalloc:
-	kfree(evt);
-
-	return -EINVAL;
-}
-TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_timer_init);
diff --git a/drivers/clocksource/tegra20_timer.c b/drivers/clocksource/tegra20_timer.c
index c337a8100a7b..aa624885e0e2 100644
--- a/drivers/clocksource/tegra20_timer.c
+++ b/drivers/clocksource/tegra20_timer.c
@@ -230,7 +230,7 @@ static int __init tegra20_init_timer(struct device_node *np)
 		return ret;
 	}
 
-	tegra_clockevent.cpumask = cpu_all_mask;
+	tegra_clockevent.cpumask = cpu_possible_mask;
 	tegra_clockevent.irq = tegra_timer_irq.irq;
 	clockevents_config_and_register(&tegra_clockevent, 1000000,
 					0x1, 0x1fffffff);
@@ -259,6 +259,6 @@ static int __init tegra20_init_rtc(struct device_node *np)
 	else
 		clk_prepare_enable(clk);
 
-	return register_persistent_clock(NULL, tegra_read_persistent_clock64);
+	return register_persistent_clock(tegra_read_persistent_clock64);
 }
 TIMER_OF_DECLARE(tegra20_rtc, "nvidia,tegra20-rtc", tegra20_init_rtc);
diff --git a/drivers/clocksource/timer-atcpit100.c b/drivers/clocksource/timer-atcpit100.c
index 5e23d7b4a722..b4bd2f5b801d 100644
--- a/drivers/clocksource/timer-atcpit100.c
+++ b/drivers/clocksource/timer-atcpit100.c
@@ -185,7 +185,7 @@ static struct timer_of to = {
 		.set_state_oneshot = atcpit100_clkevt_set_oneshot,
 		.tick_resume = atcpit100_clkevt_shutdown,
 		.set_next_event = atcpit100_clkevt_next_event,
-		.cpumask = cpu_all_mask,
+		.cpumask = cpu_possible_mask,
 	},
 
 	.of_irq = {
diff --git a/drivers/clocksource/timer-keystone.c b/drivers/clocksource/timer-keystone.c
index 0eee03250cfc..f5b2eda30bf3 100644
--- a/drivers/clocksource/timer-keystone.c
+++ b/drivers/clocksource/timer-keystone.c
@@ -211,7 +211,7 @@ static int __init keystone_timer_init(struct device_node *np)
 	event_dev->set_state_shutdown = keystone_shutdown;
 	event_dev->set_state_periodic = keystone_set_periodic;
 	event_dev->set_state_oneshot = keystone_shutdown;
-	event_dev->cpumask = cpu_all_mask;
+	event_dev->cpumask = cpu_possible_mask;
 	event_dev->owner = THIS_MODULE;
 	event_dev->name = TIMER_NAME;
 	event_dev->irq = irq;
diff --git a/drivers/clocksource/timer-mediatek.c b/drivers/clocksource/timer-mediatek.c
new file mode 100644
index 000000000000..eb10321f8517
--- /dev/null
+++ b/drivers/clocksource/timer-mediatek.c
@@ -0,0 +1,328 @@
+/*
+ * Mediatek SoCs General-Purpose Timer handling.
+ *
+ * Copyright (C) 2014 Matthias Brugger
+ *
+ * Matthias Brugger <matthias.bgg@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/interrupt.h>
+#include <linux/irqreturn.h>
+#include <linux/sched_clock.h>
+#include <linux/slab.h>
+#include "timer-of.h"
+
+#define TIMER_CLK_EVT           (1)
+#define TIMER_CLK_SRC           (2)
+
+#define TIMER_SYNC_TICKS        (3)
+
+/* gpt */
+#define GPT_IRQ_EN_REG          0x00
+#define GPT_IRQ_ENABLE(val)     BIT((val) - 1)
+#define GPT_IRQ_ACK_REG	        0x08
+#define GPT_IRQ_ACK(val)        BIT((val) - 1)
+
+#define GPT_CTRL_REG(val)       (0x10 * (val))
+#define GPT_CTRL_OP(val)        (((val) & 0x3) << 4)
+#define GPT_CTRL_OP_ONESHOT     (0)
+#define GPT_CTRL_OP_REPEAT      (1)
+#define GPT_CTRL_OP_FREERUN     (3)
+#define GPT_CTRL_CLEAR          (2)
+#define GPT_CTRL_ENABLE         (1)
+#define GPT_CTRL_DISABLE        (0)
+
+#define GPT_CLK_REG(val)        (0x04 + (0x10 * (val)))
+#define GPT_CLK_SRC(val)        (((val) & 0x1) << 4)
+#define GPT_CLK_SRC_SYS13M      (0)
+#define GPT_CLK_SRC_RTC32K      (1)
+#define GPT_CLK_DIV1            (0x0)
+#define GPT_CLK_DIV2            (0x1)
+
+#define GPT_CNT_REG(val)        (0x08 + (0x10 * (val)))
+#define GPT_CMP_REG(val)        (0x0C + (0x10 * (val)))
+
+/* system timer */
+#define SYST_BASE               (0x40)
+
+#define SYST_CON                (SYST_BASE + 0x0)
+#define SYST_VAL                (SYST_BASE + 0x4)
+
+#define SYST_CON_REG(to)        (timer_of_base(to) + SYST_CON)
+#define SYST_VAL_REG(to)        (timer_of_base(to) + SYST_VAL)
+
+/*
+ * SYST_CON_EN: Clock enable. Shall be set to
+ *   - Start timer countdown.
+ *   - Allow timeout ticks being updated.
+ *   - Allow changing interrupt functions.
+ *
+ * SYST_CON_IRQ_EN: Set to allow interrupt.
+ *
+ * SYST_CON_IRQ_CLR: Set to clear interrupt.
+ */
+#define SYST_CON_EN              BIT(0)
+#define SYST_CON_IRQ_EN          BIT(1)
+#define SYST_CON_IRQ_CLR         BIT(4)
+
+static void __iomem *gpt_sched_reg __read_mostly;
+
+static void mtk_syst_ack_irq(struct timer_of *to)
+{
+	/* Clear and disable interrupt */
+	writel(SYST_CON_IRQ_CLR | SYST_CON_EN, SYST_CON_REG(to));
+}
+
+static irqreturn_t mtk_syst_handler(int irq, void *dev_id)
+{
+	struct clock_event_device *clkevt = dev_id;
+	struct timer_of *to = to_timer_of(clkevt);
+
+	mtk_syst_ack_irq(to);
+	clkevt->event_handler(clkevt);
+
+	return IRQ_HANDLED;
+}
+
+static int mtk_syst_clkevt_next_event(unsigned long ticks,
+				      struct clock_event_device *clkevt)
+{
+	struct timer_of *to = to_timer_of(clkevt);
+
+	/* Enable clock to allow timeout tick update later */
+	writel(SYST_CON_EN, SYST_CON_REG(to));
+
+	/*
+	 * Write new timeout ticks. Timer shall start countdown
+	 * after timeout ticks are updated.
+	 */
+	writel(ticks, SYST_VAL_REG(to));
+
+	/* Enable interrupt */
+	writel(SYST_CON_EN | SYST_CON_IRQ_EN, SYST_CON_REG(to));
+
+	return 0;
+}
+
+static int mtk_syst_clkevt_shutdown(struct clock_event_device *clkevt)
+{
+	/* Disable timer */
+	writel(0, SYST_CON_REG(to_timer_of(clkevt)));
+
+	return 0;
+}
+
+static int mtk_syst_clkevt_resume(struct clock_event_device *clkevt)
+{
+	return mtk_syst_clkevt_shutdown(clkevt);
+}
+
+static int mtk_syst_clkevt_oneshot(struct clock_event_device *clkevt)
+{
+	return 0;
+}
+
+static u64 notrace mtk_gpt_read_sched_clock(void)
+{
+	return readl_relaxed(gpt_sched_reg);
+}
+
+static void mtk_gpt_clkevt_time_stop(struct timer_of *to, u8 timer)
+{
+	u32 val;
+
+	val = readl(timer_of_base(to) + GPT_CTRL_REG(timer));
+	writel(val & ~GPT_CTRL_ENABLE, timer_of_base(to) +
+	       GPT_CTRL_REG(timer));
+}
+
+static void mtk_gpt_clkevt_time_setup(struct timer_of *to,
+				      unsigned long delay, u8 timer)
+{
+	writel(delay, timer_of_base(to) + GPT_CMP_REG(timer));
+}
+
+static void mtk_gpt_clkevt_time_start(struct timer_of *to,
+				      bool periodic, u8 timer)
+{
+	u32 val;
+
+	/* Acknowledge interrupt */
+	writel(GPT_IRQ_ACK(timer), timer_of_base(to) + GPT_IRQ_ACK_REG);
+
+	val = readl(timer_of_base(to) + GPT_CTRL_REG(timer));
+
+	/* Clear 2 bit timer operation mode field */
+	val &= ~GPT_CTRL_OP(0x3);
+
+	if (periodic)
+		val |= GPT_CTRL_OP(GPT_CTRL_OP_REPEAT);
+	else
+		val |= GPT_CTRL_OP(GPT_CTRL_OP_ONESHOT);
+
+	writel(val | GPT_CTRL_ENABLE | GPT_CTRL_CLEAR,
+	       timer_of_base(to) + GPT_CTRL_REG(timer));
+}
+
+static int mtk_gpt_clkevt_shutdown(struct clock_event_device *clk)
+{
+	mtk_gpt_clkevt_time_stop(to_timer_of(clk), TIMER_CLK_EVT);
+
+	return 0;
+}
+
+static int mtk_gpt_clkevt_set_periodic(struct clock_event_device *clk)
+{
+	struct timer_of *to = to_timer_of(clk);
+
+	mtk_gpt_clkevt_time_stop(to, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_setup(to, to->of_clk.period, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_start(to, true, TIMER_CLK_EVT);
+
+	return 0;
+}
+
+static int mtk_gpt_clkevt_next_event(unsigned long event,
+				     struct clock_event_device *clk)
+{
+	struct timer_of *to = to_timer_of(clk);
+
+	mtk_gpt_clkevt_time_stop(to, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_setup(to, event, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_start(to, false, TIMER_CLK_EVT);
+
+	return 0;
+}
+
+static irqreturn_t mtk_gpt_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *clkevt = (struct clock_event_device *)dev_id;
+	struct timer_of *to = to_timer_of(clkevt);
+
+	/* Acknowledge timer0 irq */
+	writel(GPT_IRQ_ACK(TIMER_CLK_EVT), timer_of_base(to) + GPT_IRQ_ACK_REG);
+	clkevt->event_handler(clkevt);
+
+	return IRQ_HANDLED;
+}
+
+static void
+__init mtk_gpt_setup(struct timer_of *to, u8 timer, u8 option)
+{
+	writel(GPT_CTRL_CLEAR | GPT_CTRL_DISABLE,
+	       timer_of_base(to) + GPT_CTRL_REG(timer));
+
+	writel(GPT_CLK_SRC(GPT_CLK_SRC_SYS13M) | GPT_CLK_DIV1,
+	       timer_of_base(to) + GPT_CLK_REG(timer));
+
+	writel(0x0, timer_of_base(to) + GPT_CMP_REG(timer));
+
+	writel(GPT_CTRL_OP(option) | GPT_CTRL_ENABLE,
+	       timer_of_base(to) + GPT_CTRL_REG(timer));
+}
+
+static void mtk_gpt_enable_irq(struct timer_of *to, u8 timer)
+{
+	u32 val;
+
+	/* Disable all interrupts */
+	writel(0x0, timer_of_base(to) + GPT_IRQ_EN_REG);
+
+	/* Acknowledge all spurious pending interrupts */
+	writel(0x3f, timer_of_base(to) + GPT_IRQ_ACK_REG);
+
+	val = readl(timer_of_base(to) + GPT_IRQ_EN_REG);
+	writel(val | GPT_IRQ_ENABLE(timer),
+	       timer_of_base(to) + GPT_IRQ_EN_REG);
+}
+
+static struct timer_of to = {
+	.flags = TIMER_OF_IRQ | TIMER_OF_BASE | TIMER_OF_CLOCK,
+
+	.clkevt = {
+		.name = "mtk-clkevt",
+		.rating = 300,
+		.cpumask = cpu_possible_mask,
+	},
+
+	.of_irq = {
+		.flags = IRQF_TIMER | IRQF_IRQPOLL,
+	},
+};
+
+static int __init mtk_syst_init(struct device_node *node)
+{
+	int ret;
+
+	to.clkevt.features = CLOCK_EVT_FEAT_DYNIRQ | CLOCK_EVT_FEAT_ONESHOT;
+	to.clkevt.set_state_shutdown = mtk_syst_clkevt_shutdown;
+	to.clkevt.set_state_oneshot = mtk_syst_clkevt_oneshot;
+	to.clkevt.tick_resume = mtk_syst_clkevt_resume;
+	to.clkevt.set_next_event = mtk_syst_clkevt_next_event;
+	to.of_irq.handler = mtk_syst_handler;
+
+	ret = timer_of_init(node, &to);
+	if (ret)
+		goto err;
+
+	clockevents_config_and_register(&to.clkevt, timer_of_rate(&to),
+					TIMER_SYNC_TICKS, 0xffffffff);
+
+	return 0;
+err:
+	timer_of_cleanup(&to);
+	return ret;
+}
+
+static int __init mtk_gpt_init(struct device_node *node)
+{
+	int ret;
+
+	to.clkevt.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
+	to.clkevt.set_state_shutdown = mtk_gpt_clkevt_shutdown;
+	to.clkevt.set_state_periodic = mtk_gpt_clkevt_set_periodic;
+	to.clkevt.set_state_oneshot = mtk_gpt_clkevt_shutdown;
+	to.clkevt.tick_resume = mtk_gpt_clkevt_shutdown;
+	to.clkevt.set_next_event = mtk_gpt_clkevt_next_event;
+	to.of_irq.handler = mtk_gpt_interrupt;
+
+	ret = timer_of_init(node, &to);
+	if (ret)
+		goto err;
+
+	/* Configure clock source */
+	mtk_gpt_setup(&to, TIMER_CLK_SRC, GPT_CTRL_OP_FREERUN);
+	clocksource_mmio_init(timer_of_base(&to) + GPT_CNT_REG(TIMER_CLK_SRC),
+			      node->name, timer_of_rate(&to), 300, 32,
+			      clocksource_mmio_readl_up);
+	gpt_sched_reg = timer_of_base(&to) + GPT_CNT_REG(TIMER_CLK_SRC);
+	sched_clock_register(mtk_gpt_read_sched_clock, 32, timer_of_rate(&to));
+
+	/* Configure clock event */
+	mtk_gpt_setup(&to, TIMER_CLK_EVT, GPT_CTRL_OP_REPEAT);
+	clockevents_config_and_register(&to.clkevt, timer_of_rate(&to),
+					TIMER_SYNC_TICKS, 0xffffffff);
+
+	mtk_gpt_enable_irq(&to, TIMER_CLK_EVT);
+
+	return 0;
+err:
+	timer_of_cleanup(&to);
+	return ret;
+}
+TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_gpt_init);
+TIMER_OF_DECLARE(mtk_mt6765, "mediatek,mt6765-timer", mtk_syst_init);
diff --git a/drivers/clocksource/timer-sprd.c b/drivers/clocksource/timer-sprd.c
index ef9ebeafb3ed..430cb99d8d79 100644
--- a/drivers/clocksource/timer-sprd.c
+++ b/drivers/clocksource/timer-sprd.c
@@ -156,4 +156,54 @@ static int __init sprd_timer_init(struct device_node *np)
 	return 0;
 }
 
+static struct timer_of suspend_to = {
+	.flags = TIMER_OF_BASE | TIMER_OF_CLOCK,
+};
+
+static u64 sprd_suspend_timer_read(struct clocksource *cs)
+{
+	return ~(u64)readl_relaxed(timer_of_base(&suspend_to) +
+				   TIMER_VALUE_SHDW_LO) & cs->mask;
+}
+
+static int sprd_suspend_timer_enable(struct clocksource *cs)
+{
+	sprd_timer_update_counter(timer_of_base(&suspend_to),
+				  TIMER_VALUE_LO_MASK);
+	sprd_timer_enable(timer_of_base(&suspend_to), TIMER_CTL_PERIOD_MODE);
+
+	return 0;
+}
+
+static void sprd_suspend_timer_disable(struct clocksource *cs)
+{
+	sprd_timer_disable(timer_of_base(&suspend_to));
+}
+
+static struct clocksource suspend_clocksource = {
+	.name	= "sprd_suspend_timer",
+	.rating	= 200,
+	.read	= sprd_suspend_timer_read,
+	.enable = sprd_suspend_timer_enable,
+	.disable = sprd_suspend_timer_disable,
+	.mask	= CLOCKSOURCE_MASK(32),
+	.flags	= CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_SUSPEND_NONSTOP,
+};
+
+static int __init sprd_suspend_timer_init(struct device_node *np)
+{
+	int ret;
+
+	ret = timer_of_init(np, &suspend_to);
+	if (ret)
+		return ret;
+
+	clocksource_register_hz(&suspend_clocksource,
+				timer_of_rate(&suspend_to));
+
+	return 0;
+}
+
 TIMER_OF_DECLARE(sc9860_timer, "sprd,sc9860-timer", sprd_timer_init);
+TIMER_OF_DECLARE(sc9860_persistent_timer, "sprd,sc9860-suspend-timer",
+		 sprd_suspend_timer_init);
diff --git a/drivers/clocksource/timer-ti-32k.c b/drivers/clocksource/timer-ti-32k.c
index 880a861ab3c8..29e2e1a78a43 100644
--- a/drivers/clocksource/timer-ti-32k.c
+++ b/drivers/clocksource/timer-ti-32k.c
@@ -78,8 +78,7 @@ static struct ti_32k ti_32k_timer = {
 		.rating		= 250,
 		.read		= ti_32k_read_cycles,
 		.mask		= CLOCKSOURCE_MASK(32),
-		.flags		= CLOCK_SOURCE_IS_CONTINUOUS |
-				CLOCK_SOURCE_SUSPEND_NONSTOP,
+		.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 	},
 };
 
diff --git a/drivers/clocksource/zevio-timer.c b/drivers/clocksource/zevio-timer.c
index a6a0338eea77..f74689334f7c 100644
--- a/drivers/clocksource/zevio-timer.c
+++ b/drivers/clocksource/zevio-timer.c
@@ -162,7 +162,7 @@ static int __init zevio_timer_add(struct device_node *node)
 		timer->clkevt.set_state_oneshot = zevio_timer_set_oneshot;
 		timer->clkevt.tick_resume	= zevio_timer_set_oneshot;
 		timer->clkevt.rating		= 200;
-		timer->clkevt.cpumask		= cpu_all_mask;
+		timer->clkevt.cpumask		= cpu_possible_mask;
 		timer->clkevt.features		= CLOCK_EVT_FEAT_ONESHOT;
 		timer->clkevt.irq		= irqnr;
 
diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index e718b8c69a56..eeb7d31cbda5 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -19,6 +19,7 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/list.h>
@@ -239,7 +240,7 @@ void cn_del_callback(struct cb_id *id)
 }
 EXPORT_SYMBOL_GPL(cn_del_callback);
 
-static int cn_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused cn_proc_show(struct seq_file *m, void *v)
 {
 	struct cn_queue_dev *dev = cdev.cbdev;
 	struct cn_callback_entry *cbq;
diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c
index 739da90ff3f6..75491fc841a6 100644
--- a/drivers/cpufreq/armada-37xx-cpufreq.c
+++ b/drivers/cpufreq/armada-37xx-cpufreq.c
@@ -51,6 +51,16 @@
 #define  ARMADA_37XX_DVFS_LOAD_2	2
 #define  ARMADA_37XX_DVFS_LOAD_3	3
 
+/* AVS register set */
+#define ARMADA_37XX_AVS_CTL0		0x0
+#define	 ARMADA_37XX_AVS_ENABLE		BIT(30)
+#define	 ARMADA_37XX_AVS_HIGH_VDD_LIMIT	16
+#define	 ARMADA_37XX_AVS_LOW_VDD_LIMIT	22
+#define	 ARMADA_37XX_AVS_VDD_MASK	0x3F
+#define ARMADA_37XX_AVS_CTL2		0x8
+#define	 ARMADA_37XX_AVS_LOW_VDD_EN	BIT(6)
+#define ARMADA_37XX_AVS_VSET(x)	    (0x1C + 4 * (x))
+
 /*
  * On Armada 37xx the Power management manages 4 level of CPU load,
  * each level can be associated with a CPU clock source, a CPU
@@ -58,6 +68,17 @@
  */
 #define LOAD_LEVEL_NR	4
 
+#define MIN_VOLT_MV 1000
+
+/*  AVS value for the corresponding voltage (in mV) */
+static int avs_map[] = {
+	747, 758, 770, 782, 793, 805, 817, 828, 840, 852, 863, 875, 887, 898,
+	910, 922, 933, 945, 957, 968, 980, 992, 1003, 1015, 1027, 1038, 1050,
+	1062, 1073, 1085, 1097, 1108, 1120, 1132, 1143, 1155, 1167, 1178, 1190,
+	1202, 1213, 1225, 1237, 1248, 1260, 1272, 1283, 1295, 1307, 1318, 1330,
+	1342
+};
+
 struct armada37xx_cpufreq_state {
 	struct regmap *regmap;
 	u32 nb_l0l1;
@@ -71,6 +92,7 @@ static struct armada37xx_cpufreq_state *armada37xx_cpufreq_state;
 struct armada_37xx_dvfs {
 	u32 cpu_freq_max;
 	u8 divider[LOAD_LEVEL_NR];
+	u32 avs[LOAD_LEVEL_NR];
 };
 
 static struct armada_37xx_dvfs armada_37xx_dvfs[] = {
@@ -148,6 +170,128 @@ static void __init armada37xx_cpufreq_dvfs_setup(struct regmap *base,
 	clk_set_parent(clk, parent);
 }
 
+/*
+ * Find out the armada 37x supported AVS value whose voltage value is
+ * the round-up closest to the target voltage value.
+ */
+static u32 armada_37xx_avs_val_match(int target_vm)
+{
+	u32 avs;
+
+	/* Find out the round-up closest supported voltage value */
+	for (avs = 0; avs < ARRAY_SIZE(avs_map); avs++)
+		if (avs_map[avs] >= target_vm)
+			break;
+
+	/*
+	 * If all supported voltages are smaller than target one,
+	 * choose the largest supported voltage
+	 */
+	if (avs == ARRAY_SIZE(avs_map))
+		avs = ARRAY_SIZE(avs_map) - 1;
+
+	return avs;
+}
+
+/*
+ * For Armada 37xx soc, L0(VSET0) VDD AVS value is set to SVC revision
+ * value or a default value when SVC is not supported.
+ * - L0 can be read out from the register of AVS_CTRL_0 and L0 voltage
+ *   can be got from the mapping table of avs_map.
+ * - L1 voltage should be about 100mv smaller than L0 voltage
+ * - L2 & L3 voltage should be about 150mv smaller than L0 voltage.
+ * This function calculates L1 & L2 & L3 AVS values dynamically based
+ * on L0 voltage and fill all AVS values to the AVS value table.
+ */
+static void __init armada37xx_cpufreq_avs_configure(struct regmap *base,
+						struct armada_37xx_dvfs *dvfs)
+{
+	unsigned int target_vm;
+	int load_level = 0;
+	u32 l0_vdd_min;
+
+	if (base == NULL)
+		return;
+
+	/* Get L0 VDD min value */
+	regmap_read(base, ARMADA_37XX_AVS_CTL0, &l0_vdd_min);
+	l0_vdd_min = (l0_vdd_min >> ARMADA_37XX_AVS_LOW_VDD_LIMIT) &
+		ARMADA_37XX_AVS_VDD_MASK;
+	if (l0_vdd_min >= ARRAY_SIZE(avs_map))  {
+		pr_err("L0 VDD MIN %d is not correct.\n", l0_vdd_min);
+		return;
+	}
+	dvfs->avs[0] = l0_vdd_min;
+
+	if (avs_map[l0_vdd_min] <= MIN_VOLT_MV) {
+		/*
+		 * If L0 voltage is smaller than 1000mv, then all VDD sets
+		 * use L0 voltage;
+		 */
+		u32 avs_min = armada_37xx_avs_val_match(MIN_VOLT_MV);
+
+		for (load_level = 1; load_level < LOAD_LEVEL_NR; load_level++)
+			dvfs->avs[load_level] = avs_min;
+
+		return;
+	}
+
+	/*
+	 * L1 voltage is equal to L0 voltage - 100mv and it must be
+	 * larger than 1000mv
+	 */
+
+	target_vm = avs_map[l0_vdd_min] - 100;
+	target_vm = target_vm > MIN_VOLT_MV ? target_vm : MIN_VOLT_MV;
+	dvfs->avs[1] = armada_37xx_avs_val_match(target_vm);
+
+	/*
+	 * L2 & L3 voltage is equal to L0 voltage - 150mv and it must
+	 * be larger than 1000mv
+	 */
+	target_vm = avs_map[l0_vdd_min] - 150;
+	target_vm = target_vm > MIN_VOLT_MV ? target_vm : MIN_VOLT_MV;
+	dvfs->avs[2] = dvfs->avs[3] = armada_37xx_avs_val_match(target_vm);
+}
+
+static void __init armada37xx_cpufreq_avs_setup(struct regmap *base,
+						struct armada_37xx_dvfs *dvfs)
+{
+	unsigned int avs_val = 0, freq;
+	int load_level = 0;
+
+	if (base == NULL)
+		return;
+
+	/* Disable AVS before the configuration */
+	regmap_update_bits(base, ARMADA_37XX_AVS_CTL0,
+			   ARMADA_37XX_AVS_ENABLE, 0);
+
+
+	/* Enable low voltage mode */
+	regmap_update_bits(base, ARMADA_37XX_AVS_CTL2,
+			   ARMADA_37XX_AVS_LOW_VDD_EN,
+			   ARMADA_37XX_AVS_LOW_VDD_EN);
+
+
+	for (load_level = 1; load_level < LOAD_LEVEL_NR; load_level++) {
+		freq = dvfs->cpu_freq_max / dvfs->divider[load_level];
+
+		avs_val = dvfs->avs[load_level];
+		regmap_update_bits(base, ARMADA_37XX_AVS_VSET(load_level-1),
+		    ARMADA_37XX_AVS_VDD_MASK << ARMADA_37XX_AVS_HIGH_VDD_LIMIT |
+		    ARMADA_37XX_AVS_VDD_MASK << ARMADA_37XX_AVS_LOW_VDD_LIMIT,
+		    avs_val << ARMADA_37XX_AVS_HIGH_VDD_LIMIT |
+		    avs_val << ARMADA_37XX_AVS_LOW_VDD_LIMIT);
+	}
+
+	/* Enable AVS after the configuration */
+	regmap_update_bits(base, ARMADA_37XX_AVS_CTL0,
+			   ARMADA_37XX_AVS_ENABLE,
+			   ARMADA_37XX_AVS_ENABLE);
+
+}
+
 static void armada37xx_cpufreq_disable_dvfs(struct regmap *base)
 {
 	unsigned int reg = ARMADA_37XX_NB_DYN_MOD,
@@ -216,7 +360,7 @@ static int __init armada37xx_cpufreq_driver_init(void)
 	struct platform_device *pdev;
 	unsigned long freq;
 	unsigned int cur_frequency;
-	struct regmap *nb_pm_base;
+	struct regmap *nb_pm_base, *avs_base;
 	struct device *cpu_dev;
 	int load_lvl, ret;
 	struct clk *clk;
@@ -227,6 +371,14 @@ static int __init armada37xx_cpufreq_driver_init(void)
 	if (IS_ERR(nb_pm_base))
 		return -ENODEV;
 
+	avs_base =
+		syscon_regmap_lookup_by_compatible("marvell,armada-3700-avs");
+
+	/* if AVS is not present don't use it but still try to setup dvfs */
+	if (IS_ERR(avs_base)) {
+		pr_info("Syscon failed for Adapting Voltage Scaling: skip it\n");
+		avs_base = NULL;
+	}
 	/* Before doing any configuration on the DVFS first, disable it */
 	armada37xx_cpufreq_disable_dvfs(nb_pm_base);
 
@@ -270,16 +422,21 @@ static int __init armada37xx_cpufreq_driver_init(void)
 
 	armada37xx_cpufreq_state->regmap = nb_pm_base;
 
+	armada37xx_cpufreq_avs_configure(avs_base, dvfs);
+	armada37xx_cpufreq_avs_setup(avs_base, dvfs);
+
 	armada37xx_cpufreq_dvfs_setup(nb_pm_base, clk, dvfs->divider);
 	clk_put(clk);
 
 	for (load_lvl = ARMADA_37XX_DVFS_LOAD_0; load_lvl < LOAD_LEVEL_NR;
 	     load_lvl++) {
+		unsigned long u_volt = avs_map[dvfs->avs[load_lvl]] * 1000;
 		freq = cur_frequency / dvfs->divider[load_lvl];
-
-		ret = dev_pm_opp_add(cpu_dev, freq, 0);
+		ret = dev_pm_opp_add(cpu_dev, freq, u_volt);
 		if (ret)
 			goto remove_opp;
+
+
 	}
 
 	/* Now that everything is setup, enable the DVFS at hardware level */
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index a9d3eec32795..30f302149730 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -296,10 +296,62 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	return ret;
 }
 
+static inline u64 get_delta(u64 t1, u64 t0)
+{
+	if (t1 > t0 || t0 > ~(u32)0)
+		return t1 - t0;
+
+	return (u32)t1 - (u32)t0;
+}
+
+static int cppc_get_rate_from_fbctrs(struct cppc_cpudata *cpu,
+				     struct cppc_perf_fb_ctrs fb_ctrs_t0,
+				     struct cppc_perf_fb_ctrs fb_ctrs_t1)
+{
+	u64 delta_reference, delta_delivered;
+	u64 reference_perf, delivered_perf;
+
+	reference_perf = fb_ctrs_t0.reference_perf;
+
+	delta_reference = get_delta(fb_ctrs_t1.reference,
+				    fb_ctrs_t0.reference);
+	delta_delivered = get_delta(fb_ctrs_t1.delivered,
+				    fb_ctrs_t0.delivered);
+
+	/* Check to avoid divide-by zero */
+	if (delta_reference || delta_delivered)
+		delivered_perf = (reference_perf * delta_delivered) /
+					delta_reference;
+	else
+		delivered_perf = cpu->perf_ctrls.desired_perf;
+
+	return cppc_cpufreq_perf_to_khz(cpu, delivered_perf);
+}
+
+static unsigned int cppc_cpufreq_get_rate(unsigned int cpunum)
+{
+	struct cppc_perf_fb_ctrs fb_ctrs_t0 = {0}, fb_ctrs_t1 = {0};
+	struct cppc_cpudata *cpu = all_cpu_data[cpunum];
+	int ret;
+
+	ret = cppc_get_perf_ctrs(cpunum, &fb_ctrs_t0);
+	if (ret)
+		return ret;
+
+	udelay(2); /* 2usec delay between sampling */
+
+	ret = cppc_get_perf_ctrs(cpunum, &fb_ctrs_t1);
+	if (ret)
+		return ret;
+
+	return cppc_get_rate_from_fbctrs(cpu, fb_ctrs_t0, fb_ctrs_t1);
+}
+
 static struct cpufreq_driver cppc_cpufreq_driver = {
 	.flags = CPUFREQ_CONST_LOOPS,
 	.verify = cppc_verify_policy,
 	.target = cppc_cpufreq_set_target,
+	.get = cppc_cpufreq_get_rate,
 	.init = cppc_cpufreq_cpu_init,
 	.stop_cpu = cppc_cpufreq_stop_cpu,
 	.name = "cppc_cpufreq",
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index b0dfd3222013..f53fb41efb7b 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -923,7 +923,12 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 	struct freq_attr *fattr = to_attr(attr);
 	ssize_t ret = -EINVAL;
 
-	cpus_read_lock();
+	/*
+	 * cpus_read_trylock() is used here to work around a circular lock
+	 * dependency problem with respect to the cpufreq_register_driver().
+	 */
+	if (!cpus_read_trylock())
+		return -EBUSY;
 
 	if (cpu_online(policy->cpu)) {
 		down_write(&policy->rwsem);
@@ -2236,6 +2241,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 
 	policy->min = new_policy->min;
 	policy->max = new_policy->max;
+	trace_cpu_frequency_limits(policy);
 
 	policy->cached_target_freq = UINT_MAX;
 
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index 8b3c2a79ad6c..b2ff423ad7f8 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -9,6 +9,7 @@
 #include <linux/clk.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
+#include <linux/cpu_cooling.h>
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -50,6 +51,7 @@ static struct clk_bulk_data clks[] = {
 };
 
 static struct device *cpu_dev;
+static struct thermal_cooling_device *cdev;
 static bool free_opp;
 static struct cpufreq_frequency_table *freq_table;
 static unsigned int max_freq;
@@ -191,6 +193,16 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index)
 	return 0;
 }
 
+static void imx6q_cpufreq_ready(struct cpufreq_policy *policy)
+{
+	cdev = of_cpufreq_cooling_register(policy);
+
+	if (!cdev)
+		dev_err(cpu_dev,
+			"running cpufreq without cooling device: %ld\n",
+			PTR_ERR(cdev));
+}
+
 static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
 {
 	int ret;
@@ -202,13 +214,22 @@ static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
 	return ret;
 }
 
+static int imx6q_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	cpufreq_cooling_unregister(cdev);
+
+	return 0;
+}
+
 static struct cpufreq_driver imx6q_cpufreq_driver = {
 	.flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK,
 	.verify = cpufreq_generic_frequency_table_verify,
 	.target_index = imx6q_set_target,
 	.get = cpufreq_generic_get,
 	.init = imx6q_cpufreq_init,
+	.exit = imx6q_cpufreq_exit,
 	.name = "imx6q-cpufreq",
+	.ready = imx6q_cpufreq_ready,
 	.attr = cpufreq_generic_attr,
 	.suspend = cpufreq_generic_suspend,
 };
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index d4ed0022b0dd..b6a1aadaff9f 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -670,21 +670,18 @@ static ssize_t store_energy_performance_preference(
 {
 	struct cpudata *cpu_data = all_cpu_data[policy->cpu];
 	char str_preference[21];
-	int ret, i = 0;
+	int ret;
 
 	ret = sscanf(buf, "%20s", str_preference);
 	if (ret != 1)
 		return -EINVAL;
 
-	while (energy_perf_strings[i] != NULL) {
-		if (!strcmp(str_preference, energy_perf_strings[i])) {
-			intel_pstate_set_energy_pref_index(cpu_data, i);
-			return count;
-		}
-		++i;
-	}
+	ret = match_string(energy_perf_strings, -1, str_preference);
+	if (ret < 0)
+		return ret;
 
-	return -EINVAL;
+	intel_pstate_set_energy_pref_index(cpu_data, ret);
+	return count;
 }
 
 static ssize_t show_energy_performance_preference(
@@ -2011,7 +2008,8 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 static void intel_pstate_adjust_policy_max(struct cpufreq_policy *policy,
 					 struct cpudata *cpu)
 {
-	if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
+	if (!hwp_active &&
+	    cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
 	    policy->max < policy->cpuinfo.max_freq &&
 	    policy->max > cpu->pstate.max_freq) {
 		pr_debug("policy->max > max non turbo frequency\n");
@@ -2085,6 +2083,15 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
 			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
 	policy->cpuinfo.max_freq *= cpu->pstate.scaling;
 
+	if (hwp_active) {
+		unsigned int max_freq;
+
+		max_freq = global.turbo_disabled ?
+			cpu->pstate.max_freq : cpu->pstate.turbo_freq;
+		if (max_freq < policy->cpuinfo.max_freq)
+			policy->cpuinfo.max_freq = max_freq;
+	}
+
 	intel_pstate_init_acpi_perf_limits(policy);
 
 	policy->fast_switch_possible = true;
diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c
index 0c56c9759672..099a849396f6 100644
--- a/drivers/cpufreq/pcc-cpufreq.c
+++ b/drivers/cpufreq/pcc-cpufreq.c
@@ -593,6 +593,15 @@ static int __init pcc_cpufreq_init(void)
 		return ret;
 	}
 
+	if (num_present_cpus() > 4) {
+		pcc_cpufreq_driver.flags |= CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING;
+		pr_err("%s: Too many CPUs, dynamic performance scaling disabled\n",
+		       __func__);
+		pr_err("%s: Try to enable another scaling driver through BIOS settings\n",
+		       __func__);
+		pr_err("%s: and complain to the system vendor\n", __func__);
+	}
+
 	ret = cpufreq_register_driver(&pcc_cpufreq_driver);
 
 	return ret;
diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c
index efc9a7ae4857..a1830fa25fc5 100644
--- a/drivers/cpufreq/qcom-cpufreq-kryo.c
+++ b/drivers/cpufreq/qcom-cpufreq-kryo.c
@@ -109,8 +109,9 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
 	speedbin_nvmem = of_nvmem_cell_get(np, NULL);
 	of_node_put(np);
 	if (IS_ERR(speedbin_nvmem)) {
-		dev_err(cpu_dev, "Could not get nvmem cell: %ld\n",
-			PTR_ERR(speedbin_nvmem));
+		if (PTR_ERR(speedbin_nvmem) != -EPROBE_DEFER)
+			dev_err(cpu_dev, "Could not get nvmem cell: %ld\n",
+				PTR_ERR(speedbin_nvmem));
 		return PTR_ERR(speedbin_nvmem);
 	}
 
diff --git a/drivers/cpuidle/cpuidle-arm.c b/drivers/cpuidle/cpuidle-arm.c
index e07bc7ace774..073557f433eb 100644
--- a/drivers/cpuidle/cpuidle-arm.c
+++ b/drivers/cpuidle/cpuidle-arm.c
@@ -105,7 +105,8 @@ static int __init arm_idle_init_cpu(int cpu)
 
 	ret = cpuidle_register_driver(drv);
 	if (ret) {
-		pr_err("Failed to register cpuidle driver\n");
+		if (ret != -EBUSY)
+			pr_err("Failed to register cpuidle driver\n");
 		goto out_kfree_drv;
 	}
 
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 43cccf6aff61..a8c4ce07fc9d 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -585,6 +585,17 @@ config CRYPTO_DEV_QCE
 	  hardware. To compile this driver as a module, choose M here. The
 	  module will be called qcrypto.
 
+config CRYPTO_DEV_QCOM_RNG
+	tristate "Qualcomm Random Number Generator Driver"
+	depends on ARCH_QCOM || COMPILE_TEST
+	select CRYPTO_RNG
+	help
+	  This driver provides support for the Random Number
+	  Generator hardware found on Qualcomm SoCs.
+
+	  To compile this driver as a module, choose M here. The
+          module will be called qcom-rng. If unsure, say N.
+
 config CRYPTO_DEV_VMX
 	bool "Support for VMX cryptographic acceleration instructions"
 	depends on PPC64 && VSX
@@ -689,8 +700,10 @@ config CRYPTO_DEV_SAFEXCEL
 	select CRYPTO_AES
 	select CRYPTO_AUTHENC
 	select CRYPTO_BLKCIPHER
+	select CRYPTO_DES
 	select CRYPTO_HASH
 	select CRYPTO_HMAC
+	select CRYPTO_MD5
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
 	select CRYPTO_SHA512
@@ -746,4 +759,6 @@ config CRYPTO_DEV_CCREE
 	  cryptographic operations on the system REE.
 	  If unsure say Y.
 
+source "drivers/crypto/hisilicon/Kconfig"
+
 endif # CRYPTO_HW
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index 7ae87b4f6c8d..c23396f32c8a 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -33,6 +33,7 @@ obj-$(CONFIG_CRYPTO_DEV_PICOXCELL) += picoxcell_crypto.o
 obj-$(CONFIG_CRYPTO_DEV_PPC4XX) += amcc/
 obj-$(CONFIG_CRYPTO_DEV_QAT) += qat/
 obj-$(CONFIG_CRYPTO_DEV_QCE) += qce/
+obj-$(CONFIG_CRYPTO_DEV_QCOM_RNG) += qcom-rng.o
 obj-$(CONFIG_CRYPTO_DEV_ROCKCHIP) += rockchip/
 obj-$(CONFIG_CRYPTO_DEV_S5P) += s5p-sss.o
 obj-$(CONFIG_CRYPTO_DEV_SAHARA) += sahara.o
@@ -45,3 +46,4 @@ obj-$(CONFIG_CRYPTO_DEV_VMX) += vmx/
 obj-$(CONFIG_CRYPTO_DEV_BCM_SPU) += bcm/
 obj-$(CONFIG_CRYPTO_DEV_SAFEXCEL) += inside-secure/
 obj-$(CONFIG_CRYPTO_DEV_ARTPEC6) += axis/
+obj-y += hisilicon/
diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c
index 05981ccd9901..6eaec9ba0f68 100644
--- a/drivers/crypto/amcc/crypto4xx_core.c
+++ b/drivers/crypto/amcc/crypto4xx_core.c
@@ -1132,8 +1132,7 @@ static struct crypto4xx_alg_common crypto4xx_alg[] = {
 			.cra_name = "cbc(aes)",
 			.cra_driver_name = "cbc-aes-ppc4xx",
 			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct crypto4xx_ctx),
@@ -1153,8 +1152,7 @@ static struct crypto4xx_alg_common crypto4xx_alg[] = {
 			.cra_name = "cfb(aes)",
 			.cra_driver_name = "cfb-aes-ppc4xx",
 			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct crypto4xx_ctx),
@@ -1174,8 +1172,7 @@ static struct crypto4xx_alg_common crypto4xx_alg[] = {
 			.cra_name = "ctr(aes)",
 			.cra_driver_name = "ctr-aes-ppc4xx",
 			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				CRYPTO_ALG_NEED_FALLBACK |
+			.cra_flags = CRYPTO_ALG_NEED_FALLBACK |
 				CRYPTO_ALG_ASYNC |
 				CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
@@ -1196,8 +1193,7 @@ static struct crypto4xx_alg_common crypto4xx_alg[] = {
 			.cra_name = "rfc3686(ctr(aes))",
 			.cra_driver_name = "rfc3686-ctr-aes-ppc4xx",
 			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct crypto4xx_ctx),
@@ -1217,8 +1213,7 @@ static struct crypto4xx_alg_common crypto4xx_alg[] = {
 			.cra_name = "ecb(aes)",
 			.cra_driver_name = "ecb-aes-ppc4xx",
 			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct crypto4xx_ctx),
@@ -1237,8 +1232,7 @@ static struct crypto4xx_alg_common crypto4xx_alg[] = {
 			.cra_name = "ofb(aes)",
 			.cra_driver_name = "ofb-aes-ppc4xx",
 			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct crypto4xx_ctx),
diff --git a/drivers/crypto/atmel-ecc.c b/drivers/crypto/atmel-ecc.c
index e66f18a0ddd0..74f083f45e97 100644
--- a/drivers/crypto/atmel-ecc.c
+++ b/drivers/crypto/atmel-ecc.c
@@ -186,7 +186,10 @@ static int atmel_ecc_init_ecdh_cmd(struct atmel_ecc_cmd *cmd,
 	 * always be the same. Use a macro for the key size to avoid unnecessary
 	 * computations.
 	 */
-	copied = sg_copy_to_buffer(pubkey, 1, cmd->data, ATMEL_ECC_PUBKEY_SIZE);
+	copied = sg_copy_to_buffer(pubkey,
+				   sg_nents_for_len(pubkey,
+						    ATMEL_ECC_PUBKEY_SIZE),
+				   cmd->data, ATMEL_ECC_PUBKEY_SIZE);
 	if (copied != ATMEL_ECC_PUBKEY_SIZE)
 		return -EINVAL;
 
@@ -268,15 +271,17 @@ static void atmel_ecdh_done(struct atmel_ecc_work_data *work_data, void *areq,
 	struct kpp_request *req = areq;
 	struct atmel_ecdh_ctx *ctx = work_data->ctx;
 	struct atmel_ecc_cmd *cmd = &work_data->cmd;
-	size_t copied;
-	size_t n_sz = ctx->n_sz;
+	size_t copied, n_sz;
 
 	if (status)
 		goto free_work_data;
 
+	/* might want less than we've got */
+	n_sz = min_t(size_t, ctx->n_sz, req->dst_len);
+
 	/* copy the shared secret */
-	copied = sg_copy_from_buffer(req->dst, 1, &cmd->data[RSP_DATA_IDX],
-				     n_sz);
+	copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst, n_sz),
+				     &cmd->data[RSP_DATA_IDX], n_sz);
 	if (copied != n_sz)
 		status = -EINVAL;
 
@@ -440,7 +445,7 @@ static int atmel_ecdh_generate_public_key(struct kpp_request *req)
 {
 	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
 	struct atmel_ecdh_ctx *ctx = kpp_tfm_ctx(tfm);
-	size_t copied;
+	size_t copied, nbytes;
 	int ret = 0;
 
 	if (ctx->do_fallback) {
@@ -448,10 +453,14 @@ static int atmel_ecdh_generate_public_key(struct kpp_request *req)
 		return crypto_kpp_generate_public_key(req);
 	}
 
+	/* might want less than we've got */
+	nbytes = min_t(size_t, ATMEL_ECC_PUBKEY_SIZE, req->dst_len);
+
 	/* public key was saved at private key generation */
-	copied = sg_copy_from_buffer(req->dst, 1, ctx->public_key,
-				     ATMEL_ECC_PUBKEY_SIZE);
-	if (copied != ATMEL_ECC_PUBKEY_SIZE)
+	copied = sg_copy_from_buffer(req->dst,
+				     sg_nents_for_len(req->dst, nbytes),
+				     ctx->public_key, nbytes);
+	if (copied != nbytes)
 		ret = -EINVAL;
 
 	return ret;
@@ -470,6 +479,10 @@ static int atmel_ecdh_compute_shared_secret(struct kpp_request *req)
 		return crypto_kpp_compute_shared_secret(req);
 	}
 
+	/* must have exactly two points to be on the curve */
+	if (req->src_len != ATMEL_ECC_PUBKEY_SIZE)
+		return -EINVAL;
+
 	gfp = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ? GFP_KERNEL :
 							     GFP_ATOMIC;
 
@@ -554,10 +567,6 @@ static int atmel_ecdh_init_tfm(struct crypto_kpp *tfm)
 	}
 
 	crypto_kpp_set_flags(fallback, crypto_kpp_get_flags(tfm));
-
-	dev_info(&ctx->client->dev, "Using '%s' as fallback implementation.\n",
-		 crypto_tfm_alg_driver_name(crypto_kpp_tfm(fallback)));
-
 	ctx->fallback = fallback;
 
 	return 0;
diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c
index 4d43081120db..8a19df2fba6a 100644
--- a/drivers/crypto/atmel-sha.c
+++ b/drivers/crypto/atmel-sha.c
@@ -2316,9 +2316,7 @@ struct atmel_sha_authenc_ctx *atmel_sha_authenc_spawn(unsigned long mode)
 		goto error;
 	}
 
-	tfm = crypto_alloc_ahash(name,
-				 CRYPTO_ALG_TYPE_AHASH,
-				 CRYPTO_ALG_TYPE_AHASH_MASK);
+	tfm = crypto_alloc_ahash(name, 0, 0);
 	if (IS_ERR(tfm)) {
 		err = PTR_ERR(tfm);
 		goto error;
diff --git a/drivers/crypto/axis/artpec6_crypto.c b/drivers/crypto/axis/artpec6_crypto.c
index 0fb8bbf41a8d..7f07a5085e9b 100644
--- a/drivers/crypto/axis/artpec6_crypto.c
+++ b/drivers/crypto/axis/artpec6_crypto.c
@@ -2704,7 +2704,7 @@ static struct ahash_alg hash_algos[] = {
 			.cra_name = "sha1",
 			.cra_driver_name = "artpec-sha1",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = SHA1_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct artpec6_hashalg_context),
 			.cra_alignmask = 3,
@@ -2727,7 +2727,7 @@ static struct ahash_alg hash_algos[] = {
 			.cra_name = "sha256",
 			.cra_driver_name = "artpec-sha256",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = SHA256_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct artpec6_hashalg_context),
 			.cra_alignmask = 3,
@@ -2751,7 +2751,7 @@ static struct ahash_alg hash_algos[] = {
 			.cra_name = "hmac(sha256)",
 			.cra_driver_name = "artpec-hmac-sha256",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = SHA256_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct artpec6_hashalg_context),
 			.cra_alignmask = 3,
@@ -2777,7 +2777,7 @@ static struct ahash_alg artpec7_hash_algos[] = {
 			.cra_name = "sha384",
 			.cra_driver_name = "artpec-sha384",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = SHA384_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct artpec6_hashalg_context),
 			.cra_alignmask = 3,
@@ -2801,7 +2801,7 @@ static struct ahash_alg artpec7_hash_algos[] = {
 			.cra_name = "hmac(sha384)",
 			.cra_driver_name = "artpec-hmac-sha384",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = SHA384_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct artpec6_hashalg_context),
 			.cra_alignmask = 3,
@@ -2824,7 +2824,7 @@ static struct ahash_alg artpec7_hash_algos[] = {
 			.cra_name = "sha512",
 			.cra_driver_name = "artpec-sha512",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = SHA512_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct artpec6_hashalg_context),
 			.cra_alignmask = 3,
@@ -2848,7 +2848,7 @@ static struct ahash_alg artpec7_hash_algos[] = {
 			.cra_name = "hmac(sha512)",
 			.cra_driver_name = "artpec-hmac-sha512",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = SHA512_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct artpec6_hashalg_context),
 			.cra_alignmask = 3,
@@ -2867,8 +2867,7 @@ static struct skcipher_alg crypto_algos[] = {
 			.cra_name = "ecb(aes)",
 			.cra_driver_name = "artpec6-ecb-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				     CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct artpec6_cryptotfm_context),
 			.cra_alignmask = 3,
@@ -2888,8 +2887,7 @@ static struct skcipher_alg crypto_algos[] = {
 			.cra_name = "ctr(aes)",
 			.cra_driver_name = "artpec6-ctr-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				     CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				     CRYPTO_ALG_NEED_FALLBACK,
 			.cra_blocksize = 1,
 			.cra_ctxsize = sizeof(struct artpec6_cryptotfm_context),
@@ -2911,8 +2909,7 @@ static struct skcipher_alg crypto_algos[] = {
 			.cra_name = "cbc(aes)",
 			.cra_driver_name = "artpec6-cbc-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				     CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct artpec6_cryptotfm_context),
 			.cra_alignmask = 3,
@@ -2933,8 +2930,7 @@ static struct skcipher_alg crypto_algos[] = {
 			.cra_name = "xts(aes)",
 			.cra_driver_name = "artpec6-xts-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				     CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = 1,
 			.cra_ctxsize = sizeof(struct artpec6_cryptotfm_context),
 			.cra_alignmask = 3,
@@ -2964,7 +2960,7 @@ static struct aead_alg aead_algos[] = {
 			.cra_name = "gcm(aes)",
 			.cra_driver_name = "artpec-gcm-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				     CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = 1,
 			.cra_ctxsize = sizeof(struct artpec6_cryptotfm_context),
diff --git a/drivers/crypto/bcm/cipher.c b/drivers/crypto/bcm/cipher.c
index 309c67c7012f..2d1f1db9f807 100644
--- a/drivers/crypto/bcm/cipher.c
+++ b/drivers/crypto/bcm/cipher.c
@@ -3914,8 +3914,7 @@ static struct iproc_alg_s driver_algs[] = {
 				    .cra_name = "md5",
 				    .cra_driver_name = "md5-iproc",
 				    .cra_blocksize = MD5_BLOCK_WORDS * 4,
-				    .cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				    .cra_flags = CRYPTO_ALG_ASYNC,
 				}
 		      },
 	 .cipher_info = {
@@ -4649,8 +4648,7 @@ static int spu_register_ahash(struct iproc_alg_s *driver_alg)
 	hash->halg.base.cra_ctxsize = sizeof(struct iproc_ctx_s);
 	hash->halg.base.cra_init = ahash_cra_init;
 	hash->halg.base.cra_exit = generic_cra_exit;
-	hash->halg.base.cra_type = &crypto_ahash_type;
-	hash->halg.base.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC;
+	hash->halg.base.cra_flags = CRYPTO_ALG_ASYNC;
 	hash->halg.statesize = sizeof(struct spu_hash_export_s);
 
 	if (driver_alg->auth_info.mode != HASH_MODE_HMAC) {
@@ -4691,7 +4689,7 @@ static int spu_register_aead(struct iproc_alg_s *driver_alg)
 	aead->base.cra_ctxsize = sizeof(struct iproc_ctx_s);
 	INIT_LIST_HEAD(&aead->base.cra_list);
 
-	aead->base.cra_flags |= CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC;
+	aead->base.cra_flags |= CRYPTO_ALG_ASYNC;
 	/* setkey set in alg initialization */
 	aead->setauthsize = aead_setauthsize;
 	aead->encrypt = aead_encrypt;
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 0beb28196e20..43975ab5f09c 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -1846,8 +1846,7 @@ caam_hash_alloc(struct caam_hash_template *template,
 	alg->cra_priority = CAAM_CRA_PRIORITY;
 	alg->cra_blocksize = template->blocksize;
 	alg->cra_alignmask = 0;
-	alg->cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_TYPE_AHASH;
-	alg->cra_type = &crypto_ahash_type;
+	alg->cra_flags = CRYPTO_ALG_ASYNC;
 
 	t_alg->alg_type = template->alg_type;
 
diff --git a/drivers/crypto/cavium/cpt/cptvf_algs.c b/drivers/crypto/cavium/cpt/cptvf_algs.c
index df21d996db7e..600336d169a9 100644
--- a/drivers/crypto/cavium/cpt/cptvf_algs.c
+++ b/drivers/crypto/cavium/cpt/cptvf_algs.c
@@ -351,7 +351,7 @@ static int cvm_enc_dec_init(struct crypto_tfm *tfm)
 	return 0;
 }
 
-struct crypto_alg algs[] = { {
+static struct crypto_alg algs[] = { {
 	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize = AES_BLOCK_SIZE,
 	.cra_ctxsize = sizeof(struct cvm_enc_ctx),
diff --git a/drivers/crypto/cavium/nitrox/nitrox_lib.c b/drivers/crypto/cavium/nitrox/nitrox_lib.c
index 4fdc921ba611..ebe267379ac9 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_lib.c
+++ b/drivers/crypto/cavium/nitrox/nitrox_lib.c
@@ -148,7 +148,7 @@ void *crypto_alloc_context(struct nitrox_device *ndev)
 	void *vaddr;
 	dma_addr_t dma;
 
-	vaddr = dma_pool_alloc(ndev->ctx_pool, (GFP_ATOMIC | __GFP_ZERO), &dma);
+	vaddr = dma_pool_alloc(ndev->ctx_pool, (GFP_KERNEL | __GFP_ZERO), &dma);
 	if (!vaddr)
 		return NULL;
 
diff --git a/drivers/crypto/ccp/ccp-crypto-aes-cmac.c b/drivers/crypto/ccp/ccp-crypto-aes-cmac.c
index 26687f318de6..3c6fe57f91f8 100644
--- a/drivers/crypto/ccp/ccp-crypto-aes-cmac.c
+++ b/drivers/crypto/ccp/ccp-crypto-aes-cmac.c
@@ -399,13 +399,12 @@ int ccp_register_aes_cmac_algs(struct list_head *head)
 	base = &halg->base;
 	snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "cmac(aes)");
 	snprintf(base->cra_driver_name, CRYPTO_MAX_ALG_NAME, "cmac-aes-ccp");
-	base->cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC |
+	base->cra_flags = CRYPTO_ALG_ASYNC |
 			  CRYPTO_ALG_KERN_DRIVER_ONLY |
 			  CRYPTO_ALG_NEED_FALLBACK;
 	base->cra_blocksize = AES_BLOCK_SIZE;
 	base->cra_ctxsize = sizeof(struct ccp_ctx);
 	base->cra_priority = CCP_CRA_PRIORITY;
-	base->cra_type = &crypto_ahash_type;
 	base->cra_init = ccp_aes_cmac_cra_init;
 	base->cra_exit = ccp_aes_cmac_cra_exit;
 	base->cra_module = THIS_MODULE;
diff --git a/drivers/crypto/ccp/ccp-crypto-sha.c b/drivers/crypto/ccp/ccp-crypto-sha.c
index 871c9628a2ee..2ca64bb57d2e 100644
--- a/drivers/crypto/ccp/ccp-crypto-sha.c
+++ b/drivers/crypto/ccp/ccp-crypto-sha.c
@@ -497,13 +497,12 @@ static int ccp_register_sha_alg(struct list_head *head,
 	snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "%s", def->name);
 	snprintf(base->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 		 def->drv_name);
-	base->cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC |
+	base->cra_flags = CRYPTO_ALG_ASYNC |
 			  CRYPTO_ALG_KERN_DRIVER_ONLY |
 			  CRYPTO_ALG_NEED_FALLBACK;
 	base->cra_blocksize = def->block_size;
 	base->cra_ctxsize = sizeof(struct ccp_ctx);
 	base->cra_priority = CCP_CRA_PRIORITY;
-	base->cra_type = &crypto_ahash_type;
 	base->cra_init = ccp_sha_cra_init;
 	base->cra_exit = ccp_sha_cra_exit;
 	base->cra_module = THIS_MODULE;
diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c
index ff478d826d7d..218739b961fe 100644
--- a/drivers/crypto/ccp/psp-dev.c
+++ b/drivers/crypto/ccp/psp-dev.c
@@ -62,14 +62,14 @@ static irqreturn_t psp_irq_handler(int irq, void *data)
 	int reg;
 
 	/* Read the interrupt status: */
-	status = ioread32(psp->io_regs + PSP_P2CMSG_INTSTS);
+	status = ioread32(psp->io_regs + psp->vdata->intsts_reg);
 
 	/* Check if it is command completion: */
-	if (!(status & BIT(PSP_CMD_COMPLETE_REG)))
+	if (!(status & PSP_CMD_COMPLETE))
 		goto done;
 
 	/* Check if it is SEV command completion: */
-	reg = ioread32(psp->io_regs + PSP_CMDRESP);
+	reg = ioread32(psp->io_regs + psp->vdata->cmdresp_reg);
 	if (reg & PSP_CMDRESP_RESP) {
 		psp->sev_int_rcvd = 1;
 		wake_up(&psp->sev_int_queue);
@@ -77,17 +77,15 @@ static irqreturn_t psp_irq_handler(int irq, void *data)
 
 done:
 	/* Clear the interrupt status by writing the same value we read. */
-	iowrite32(status, psp->io_regs + PSP_P2CMSG_INTSTS);
+	iowrite32(status, psp->io_regs + psp->vdata->intsts_reg);
 
 	return IRQ_HANDLED;
 }
 
 static void sev_wait_cmd_ioc(struct psp_device *psp, unsigned int *reg)
 {
-	psp->sev_int_rcvd = 0;
-
 	wait_event(psp->sev_int_queue, psp->sev_int_rcvd);
-	*reg = ioread32(psp->io_regs + PSP_CMDRESP);
+	*reg = ioread32(psp->io_regs + psp->vdata->cmdresp_reg);
 }
 
 static int sev_cmd_buffer_len(int cmd)
@@ -145,13 +143,15 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret)
 	print_hex_dump_debug("(in):  ", DUMP_PREFIX_OFFSET, 16, 2, data,
 			     sev_cmd_buffer_len(cmd), false);
 
-	iowrite32(phys_lsb, psp->io_regs + PSP_CMDBUFF_ADDR_LO);
-	iowrite32(phys_msb, psp->io_regs + PSP_CMDBUFF_ADDR_HI);
+	iowrite32(phys_lsb, psp->io_regs + psp->vdata->cmdbuff_addr_lo_reg);
+	iowrite32(phys_msb, psp->io_regs + psp->vdata->cmdbuff_addr_hi_reg);
+
+	psp->sev_int_rcvd = 0;
 
 	reg = cmd;
 	reg <<= PSP_CMDRESP_CMD_SHIFT;
 	reg |= PSP_CMDRESP_IOC;
-	iowrite32(reg, psp->io_regs + PSP_CMDRESP);
+	iowrite32(reg, psp->io_regs + psp->vdata->cmdresp_reg);
 
 	/* wait for command completion */
 	sev_wait_cmd_ioc(psp, &reg);
@@ -789,7 +789,7 @@ static int sev_misc_init(struct psp_device *psp)
 static int sev_init(struct psp_device *psp)
 {
 	/* Check if device supports SEV feature */
-	if (!(ioread32(psp->io_regs + PSP_FEATURE_REG) & 1)) {
+	if (!(ioread32(psp->io_regs + psp->vdata->feature_reg) & 1)) {
 		dev_dbg(psp->dev, "device does not support SEV\n");
 		return 1;
 	}
@@ -817,11 +817,11 @@ int psp_dev_init(struct sp_device *sp)
 		goto e_err;
 	}
 
-	psp->io_regs = sp->io_map + psp->vdata->offset;
+	psp->io_regs = sp->io_map;
 
 	/* Disable and clear interrupts until ready */
-	iowrite32(0, psp->io_regs + PSP_P2CMSG_INTEN);
-	iowrite32(-1, psp->io_regs + PSP_P2CMSG_INTSTS);
+	iowrite32(0, psp->io_regs + psp->vdata->inten_reg);
+	iowrite32(-1, psp->io_regs + psp->vdata->intsts_reg);
 
 	/* Request an irq */
 	ret = sp_request_psp_irq(psp->sp, psp_irq_handler, psp->name, psp);
@@ -838,7 +838,9 @@ int psp_dev_init(struct sp_device *sp)
 		sp->set_psp_master_device(sp);
 
 	/* Enable interrupt */
-	iowrite32(-1, psp->io_regs + PSP_P2CMSG_INTEN);
+	iowrite32(-1, psp->io_regs + psp->vdata->inten_reg);
+
+	dev_notice(dev, "psp enabled\n");
 
 	return 0;
 
@@ -856,6 +858,9 @@ void psp_dev_destroy(struct sp_device *sp)
 {
 	struct psp_device *psp = sp->psp_data;
 
+	if (!psp)
+		return;
+
 	if (psp->sev_misc)
 		kref_put(&misc_dev->refcount, sev_exit);
 
diff --git a/drivers/crypto/ccp/psp-dev.h b/drivers/crypto/ccp/psp-dev.h
index c7e9098a233c..8b53a9674ecb 100644
--- a/drivers/crypto/ccp/psp-dev.h
+++ b/drivers/crypto/ccp/psp-dev.h
@@ -30,24 +30,7 @@
 
 #include "sp-dev.h"
 
-#define PSP_C2PMSG(_num)		((_num) << 2)
-#define PSP_CMDRESP			PSP_C2PMSG(32)
-#define PSP_CMDBUFF_ADDR_LO		PSP_C2PMSG(56)
-#define PSP_CMDBUFF_ADDR_HI             PSP_C2PMSG(57)
-#define PSP_FEATURE_REG			PSP_C2PMSG(63)
-
-#define PSP_P2CMSG(_num)		((_num) << 2)
-#define PSP_CMD_COMPLETE_REG		1
-#define PSP_CMD_COMPLETE		PSP_P2CMSG(PSP_CMD_COMPLETE_REG)
-
-#define PSP_P2CMSG_INTEN		0x0110
-#define PSP_P2CMSG_INTSTS		0x0114
-
-#define PSP_C2PMSG_ATTR_0		0x0118
-#define PSP_C2PMSG_ATTR_1		0x011c
-#define PSP_C2PMSG_ATTR_2		0x0120
-#define PSP_C2PMSG_ATTR_3		0x0124
-#define PSP_P2CMSG_ATTR_0		0x0128
+#define PSP_CMD_COMPLETE		BIT(1)
 
 #define PSP_CMDRESP_CMD_SHIFT		16
 #define PSP_CMDRESP_IOC			BIT(0)
diff --git a/drivers/crypto/ccp/sp-dev.h b/drivers/crypto/ccp/sp-dev.h
index acb197b66ced..14398cad1625 100644
--- a/drivers/crypto/ccp/sp-dev.h
+++ b/drivers/crypto/ccp/sp-dev.h
@@ -44,7 +44,12 @@ struct ccp_vdata {
 };
 
 struct psp_vdata {
-	const unsigned int offset;
+	const unsigned int cmdresp_reg;
+	const unsigned int cmdbuff_addr_lo_reg;
+	const unsigned int cmdbuff_addr_hi_reg;
+	const unsigned int feature_reg;
+	const unsigned int inten_reg;
+	const unsigned int intsts_reg;
 };
 
 /* Structure to hold SP device data */
diff --git a/drivers/crypto/ccp/sp-pci.c b/drivers/crypto/ccp/sp-pci.c
index f5f43c50698a..7da93e9bebed 100644
--- a/drivers/crypto/ccp/sp-pci.c
+++ b/drivers/crypto/ccp/sp-pci.c
@@ -269,38 +269,62 @@ static int sp_pci_resume(struct pci_dev *pdev)
 #endif
 
 #ifdef CONFIG_CRYPTO_DEV_SP_PSP
-static const struct psp_vdata psp_entry = {
-	.offset = 0x10500,
+static const struct psp_vdata pspv1 = {
+	.cmdresp_reg		= 0x10580,
+	.cmdbuff_addr_lo_reg	= 0x105e0,
+	.cmdbuff_addr_hi_reg	= 0x105e4,
+	.feature_reg		= 0x105fc,
+	.inten_reg		= 0x10610,
+	.intsts_reg		= 0x10614,
+};
+
+static const struct psp_vdata pspv2 = {
+	.cmdresp_reg		= 0x10980,
+	.cmdbuff_addr_lo_reg	= 0x109e0,
+	.cmdbuff_addr_hi_reg	= 0x109e4,
+	.feature_reg		= 0x109fc,
+	.inten_reg		= 0x10690,
+	.intsts_reg		= 0x10694,
 };
 #endif
 
 static const struct sp_dev_vdata dev_vdata[] = {
-	{
+	{	/* 0 */
 		.bar = 2,
 #ifdef CONFIG_CRYPTO_DEV_SP_CCP
 		.ccp_vdata = &ccpv3,
 #endif
 	},
-	{
+	{	/* 1 */
 		.bar = 2,
 #ifdef CONFIG_CRYPTO_DEV_SP_CCP
 		.ccp_vdata = &ccpv5a,
 #endif
 #ifdef CONFIG_CRYPTO_DEV_SP_PSP
-		.psp_vdata = &psp_entry
+		.psp_vdata = &pspv1,
 #endif
 	},
-	{
+	{	/* 2 */
 		.bar = 2,
 #ifdef CONFIG_CRYPTO_DEV_SP_CCP
 		.ccp_vdata = &ccpv5b,
 #endif
 	},
+	{	/* 3 */
+		.bar = 2,
+#ifdef CONFIG_CRYPTO_DEV_SP_CCP
+		.ccp_vdata = &ccpv5a,
+#endif
+#ifdef CONFIG_CRYPTO_DEV_SP_PSP
+		.psp_vdata = &pspv2,
+#endif
+	},
 };
 static const struct pci_device_id sp_pci_table[] = {
 	{ PCI_VDEVICE(AMD, 0x1537), (kernel_ulong_t)&dev_vdata[0] },
 	{ PCI_VDEVICE(AMD, 0x1456), (kernel_ulong_t)&dev_vdata[1] },
 	{ PCI_VDEVICE(AMD, 0x1468), (kernel_ulong_t)&dev_vdata[2] },
+	{ PCI_VDEVICE(AMD, 0x1486), (kernel_ulong_t)&dev_vdata[3] },
 	/* Last entry must be zero */
 	{ 0, }
 };
diff --git a/drivers/crypto/ccree/cc_aead.c b/drivers/crypto/ccree/cc_aead.c
index 03f4b9fce556..01b82b82f8b8 100644
--- a/drivers/crypto/ccree/cc_aead.c
+++ b/drivers/crypto/ccree/cc_aead.c
@@ -2344,7 +2344,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "authenc(hmac(sha1),cbc(aes))",
 		.driver_name = "authenc-hmac-sha1-cbc-aes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_aead_setauthsize,
@@ -2364,7 +2363,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "authenc(hmac(sha1),cbc(des3_ede))",
 		.driver_name = "authenc-hmac-sha1-cbc-des3-ccree",
 		.blocksize = DES3_EDE_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_aead_setauthsize,
@@ -2384,7 +2382,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "authenc(hmac(sha256),cbc(aes))",
 		.driver_name = "authenc-hmac-sha256-cbc-aes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_aead_setauthsize,
@@ -2404,7 +2401,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "authenc(hmac(sha256),cbc(des3_ede))",
 		.driver_name = "authenc-hmac-sha256-cbc-des3-ccree",
 		.blocksize = DES3_EDE_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_aead_setauthsize,
@@ -2424,7 +2420,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "authenc(xcbc(aes),cbc(aes))",
 		.driver_name = "authenc-xcbc-aes-cbc-aes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_aead_setauthsize,
@@ -2444,7 +2439,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "authenc(hmac(sha1),rfc3686(ctr(aes)))",
 		.driver_name = "authenc-hmac-sha1-rfc3686-ctr-aes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_aead_setauthsize,
@@ -2464,7 +2458,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "authenc(hmac(sha256),rfc3686(ctr(aes)))",
 		.driver_name = "authenc-hmac-sha256-rfc3686-ctr-aes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_aead_setauthsize,
@@ -2484,7 +2477,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "authenc(xcbc(aes),rfc3686(ctr(aes)))",
 		.driver_name = "authenc-xcbc-aes-rfc3686-ctr-aes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_aead_setauthsize,
@@ -2504,7 +2496,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "ccm(aes)",
 		.driver_name = "ccm-aes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_ccm_setauthsize,
@@ -2524,7 +2515,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "rfc4309(ccm(aes))",
 		.driver_name = "rfc4309-ccm-aes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_rfc4309_ccm_setkey,
 			.setauthsize = cc_rfc4309_ccm_setauthsize,
@@ -2544,7 +2534,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "gcm(aes)",
 		.driver_name = "gcm-aes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_gcm_setauthsize,
@@ -2564,7 +2553,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "rfc4106(gcm(aes))",
 		.driver_name = "rfc4106-gcm-aes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_rfc4106_gcm_setkey,
 			.setauthsize = cc_rfc4106_gcm_setauthsize,
@@ -2584,7 +2572,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "rfc4543(gcm(aes))",
 		.driver_name = "rfc4543-gcm-aes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_rfc4543_gcm_setkey,
 			.setauthsize = cc_rfc4543_gcm_setauthsize,
@@ -2621,8 +2608,7 @@ static struct cc_crypto_alg *cc_create_aead_alg(struct cc_alg_template *tmpl,
 	alg->base.cra_priority = CC_CRA_PRIO;
 
 	alg->base.cra_ctxsize = sizeof(struct cc_aead_ctx);
-	alg->base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY |
-			 tmpl->type;
+	alg->base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY;
 	alg->init = cc_aead_init;
 	alg->exit = cc_aead_exit;
 
diff --git a/drivers/crypto/ccree/cc_buffer_mgr.c b/drivers/crypto/ccree/cc_buffer_mgr.c
index b32577477b4c..dd948e1df9e5 100644
--- a/drivers/crypto/ccree/cc_buffer_mgr.c
+++ b/drivers/crypto/ccree/cc_buffer_mgr.c
@@ -454,9 +454,7 @@ void cc_unmap_cipher_request(struct device *dev, void *ctx,
 		dev_dbg(dev, "Unmapped iv: iv_dma_addr=%pad iv_size=%u\n",
 			&req_ctx->gen_ctx.iv_dma_addr, ivsize);
 		dma_unmap_single(dev, req_ctx->gen_ctx.iv_dma_addr,
-				 ivsize,
-				 req_ctx->is_giv ? DMA_BIDIRECTIONAL :
-				 DMA_TO_DEVICE);
+				 ivsize, DMA_TO_DEVICE);
 	}
 	/* Release pool */
 	if (req_ctx->dma_buf_type == CC_DMA_BUF_MLLI &&
@@ -498,9 +496,7 @@ int cc_map_cipher_request(struct cc_drvdata *drvdata, void *ctx,
 		dump_byte_array("iv", (u8 *)info, ivsize);
 		req_ctx->gen_ctx.iv_dma_addr =
 			dma_map_single(dev, (void *)info,
-				       ivsize,
-				       req_ctx->is_giv ? DMA_BIDIRECTIONAL :
-				       DMA_TO_DEVICE);
+				       ivsize, DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, req_ctx->gen_ctx.iv_dma_addr)) {
 			dev_err(dev, "Mapping iv %u B at va=%pK for DMA failed\n",
 				ivsize, info);
diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c
index d2810c183b73..7623b29911af 100644
--- a/drivers/crypto/ccree/cc_cipher.c
+++ b/drivers/crypto/ccree/cc_cipher.c
@@ -19,8 +19,6 @@
 
 #define template_skcipher	template_u.skcipher
 
-#define CC_MIN_AES_XTS_SIZE 0x10
-#define CC_MAX_AES_XTS_SIZE 0x2000
 struct cc_cipher_handle {
 	struct list_head alg_list;
 };
@@ -98,8 +96,7 @@ static int validate_data_size(struct cc_cipher_ctx *ctx_p,
 	case S_DIN_to_AES:
 		switch (ctx_p->cipher_mode) {
 		case DRV_CIPHER_XTS:
-			if (size >= CC_MIN_AES_XTS_SIZE &&
-			    size <= CC_MAX_AES_XTS_SIZE &&
+			if (size >= AES_BLOCK_SIZE &&
 			    IS_ALIGNED(size, AES_BLOCK_SIZE))
 				return 0;
 			break;
@@ -593,34 +590,82 @@ static void cc_setup_cipher_data(struct crypto_tfm *tfm,
 	}
 }
 
+/*
+ * Update a CTR-AES 128 bit counter
+ */
+static void cc_update_ctr(u8 *ctr, unsigned int increment)
+{
+	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
+	    IS_ALIGNED((unsigned long)ctr, 8)) {
+
+		__be64 *high_be = (__be64 *)ctr;
+		__be64 *low_be = high_be + 1;
+		u64 orig_low = __be64_to_cpu(*low_be);
+		u64 new_low = orig_low + (u64)increment;
+
+		*low_be = __cpu_to_be64(new_low);
+
+		if (new_low < orig_low)
+			*high_be = __cpu_to_be64(__be64_to_cpu(*high_be) + 1);
+	} else {
+		u8 *pos = (ctr + AES_BLOCK_SIZE);
+		u8 val;
+		unsigned int size;
+
+		for (; increment; increment--)
+			for (size = AES_BLOCK_SIZE; size; size--) {
+				val = *--pos + 1;
+				*pos = val;
+				if (val)
+					break;
+			}
+	}
+}
+
 static void cc_cipher_complete(struct device *dev, void *cc_req, int err)
 {
 	struct skcipher_request *req = (struct skcipher_request *)cc_req;
 	struct scatterlist *dst = req->dst;
 	struct scatterlist *src = req->src;
 	struct cipher_req_ctx *req_ctx = skcipher_request_ctx(req);
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	unsigned int ivsize = crypto_skcipher_ivsize(tfm);
+	struct crypto_skcipher *sk_tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(sk_tfm);
+	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
+	unsigned int ivsize = crypto_skcipher_ivsize(sk_tfm);
+	unsigned int len;
 
-	cc_unmap_cipher_request(dev, req_ctx, ivsize, src, dst);
-	kzfree(req_ctx->iv);
+	switch (ctx_p->cipher_mode) {
+	case DRV_CIPHER_CBC:
+		/*
+		 * The crypto API expects us to set the req->iv to the last
+		 * ciphertext block. For encrypt, simply copy from the result.
+		 * For decrypt, we must copy from a saved buffer since this
+		 * could be an in-place decryption operation and the src is
+		 * lost by this point.
+		 */
+		if (req_ctx->gen_ctx.op_type == DRV_CRYPTO_DIRECTION_DECRYPT)  {
+			memcpy(req->iv, req_ctx->backup_info, ivsize);
+			kzfree(req_ctx->backup_info);
+		} else if (!err) {
+			len = req->cryptlen - ivsize;
+			scatterwalk_map_and_copy(req->iv, req->dst, len,
+						 ivsize, 0);
+		}
+		break;
 
-	/*
-	 * The crypto API expects us to set the req->iv to the last
-	 * ciphertext block. For encrypt, simply copy from the result.
-	 * For decrypt, we must copy from a saved buffer since this
-	 * could be an in-place decryption operation and the src is
-	 * lost by this point.
-	 */
-	if (req_ctx->gen_ctx.op_type == DRV_CRYPTO_DIRECTION_DECRYPT)  {
-		memcpy(req->iv, req_ctx->backup_info, ivsize);
-		kzfree(req_ctx->backup_info);
-	} else if (!err) {
-		scatterwalk_map_and_copy(req->iv, req->dst,
-					 (req->cryptlen - ivsize),
-					 ivsize, 0);
+	case DRV_CIPHER_CTR:
+		/* Compute the counter of the last block */
+		len = ALIGN(req->cryptlen, AES_BLOCK_SIZE) / AES_BLOCK_SIZE;
+		cc_update_ctr((u8 *)req->iv, len);
+		break;
+
+	default:
+		break;
 	}
 
+	cc_unmap_cipher_request(dev, req_ctx, ivsize, src, dst);
+	kzfree(req_ctx->iv);
+
 	skcipher_request_complete(req, err);
 }
 
@@ -639,7 +684,7 @@ static int cc_cipher_process(struct skcipher_request *req,
 	struct device *dev = drvdata_to_dev(ctx_p->drvdata);
 	struct cc_hw_desc desc[MAX_ABLKCIPHER_SEQ_LEN];
 	struct cc_crypto_req cc_req = {};
-	int rc, cts_restore_flag = 0;
+	int rc;
 	unsigned int seq_len = 0;
 	gfp_t flags = cc_gfp_flags(&req->base);
 
@@ -671,23 +716,10 @@ static int cc_cipher_process(struct skcipher_request *req,
 		goto exit_process;
 	}
 
-	/*For CTS in case of data size aligned to 16 use CBC mode*/
-	if (((nbytes % AES_BLOCK_SIZE) == 0) &&
-	    ctx_p->cipher_mode == DRV_CIPHER_CBC_CTS) {
-		ctx_p->cipher_mode = DRV_CIPHER_CBC;
-		cts_restore_flag = 1;
-	}
-
 	/* Setup request structure */
 	cc_req.user_cb = (void *)cc_cipher_complete;
 	cc_req.user_arg = (void *)req;
 
-#ifdef ENABLE_CYCLE_COUNT
-	cc_req.op_type = (direction == DRV_CRYPTO_DIRECTION_DECRYPT) ?
-		STAT_OP_TYPE_DECODE : STAT_OP_TYPE_ENCODE;
-
-#endif
-
 	/* Setup request context */
 	req_ctx->gen_ctx.op_type = direction;
 
@@ -708,14 +740,6 @@ static int cc_cipher_process(struct skcipher_request *req,
 	cc_setup_cipher_data(tfm, req_ctx, dst, src, nbytes, req, desc,
 			     &seq_len);
 
-	/* do we need to generate IV? */
-	if (req_ctx->is_giv) {
-		cc_req.ivgen_dma_addr[0] = req_ctx->gen_ctx.iv_dma_addr;
-		cc_req.ivgen_dma_addr_len = 1;
-		/* set the IV size (8/16 B long)*/
-		cc_req.ivgen_size = ivsize;
-	}
-
 	/* STAT_PHASE_3: Lock HW and push sequence */
 
 	rc = cc_send_request(ctx_p->drvdata, &cc_req, desc, seq_len,
@@ -728,9 +752,6 @@ static int cc_cipher_process(struct skcipher_request *req,
 	}
 
 exit_process:
-	if (cts_restore_flag)
-		ctx_p->cipher_mode = DRV_CIPHER_CBC_CTS;
-
 	if (rc != -EINPROGRESS && rc != -EBUSY) {
 		kzfree(req_ctx->backup_info);
 		kzfree(req_ctx->iv);
@@ -743,8 +764,7 @@ static int cc_cipher_encrypt(struct skcipher_request *req)
 {
 	struct cipher_req_ctx *req_ctx = skcipher_request_ctx(req);
 
-	req_ctx->is_giv = false;
-	req_ctx->backup_info = NULL;
+	memset(req_ctx, 0, sizeof(*req_ctx));
 
 	return cc_cipher_process(req, DRV_CRYPTO_DIRECTION_ENCRYPT);
 }
@@ -752,21 +772,28 @@ static int cc_cipher_encrypt(struct skcipher_request *req)
 static int cc_cipher_decrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *sk_tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(sk_tfm);
+	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
 	struct cipher_req_ctx *req_ctx = skcipher_request_ctx(req);
 	unsigned int ivsize = crypto_skcipher_ivsize(sk_tfm);
 	gfp_t flags = cc_gfp_flags(&req->base);
+	unsigned int len;
 
-	/*
-	 * Allocate and save the last IV sized bytes of the source, which will
-	 * be lost in case of in-place decryption and might be needed for CTS.
-	 */
-	req_ctx->backup_info = kmalloc(ivsize, flags);
-	if (!req_ctx->backup_info)
-		return -ENOMEM;
+	memset(req_ctx, 0, sizeof(*req_ctx));
+
+	if (ctx_p->cipher_mode == DRV_CIPHER_CBC) {
+
+		/* Allocate and save the last IV sized bytes of the source,
+		 * which will be lost in case of in-place decryption.
+		 */
+		req_ctx->backup_info = kzalloc(ivsize, flags);
+		if (!req_ctx->backup_info)
+			return -ENOMEM;
 
-	scatterwalk_map_and_copy(req_ctx->backup_info, req->src,
-				 (req->cryptlen - ivsize), ivsize, 0);
-	req_ctx->is_giv = false;
+		len = req->cryptlen - ivsize;
+		scatterwalk_map_and_copy(req_ctx->backup_info, req->src, len,
+					 ivsize, 0);
+	}
 
 	return cc_cipher_process(req, DRV_CRYPTO_DIRECTION_DECRYPT);
 }
@@ -927,7 +954,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "ecb(paes)",
 		.driver_name = "ecb-paes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_sethkey,
 			.encrypt = cc_cipher_encrypt,
@@ -944,7 +970,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "cbc(paes)",
 		.driver_name = "cbc-paes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_sethkey,
 			.encrypt = cc_cipher_encrypt,
@@ -961,7 +986,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "ofb(paes)",
 		.driver_name = "ofb-paes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_sethkey,
 			.encrypt = cc_cipher_encrypt,
@@ -975,10 +999,9 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.min_hw_rev = CC_HW_REV_712,
 	},
 	{
-		.name = "cts1(cbc(paes))",
-		.driver_name = "cts1-cbc-paes-ccree",
+		.name = "cts(cbc(paes))",
+		.driver_name = "cts-cbc-paes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_sethkey,
 			.encrypt = cc_cipher_encrypt,
@@ -995,7 +1018,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "ctr(paes)",
 		.driver_name = "ctr-paes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_sethkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1162,7 +1184,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "ecb(aes)",
 		.driver_name = "ecb-aes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_setkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1179,7 +1200,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "cbc(aes)",
 		.driver_name = "cbc-aes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_setkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1196,7 +1216,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "ofb(aes)",
 		.driver_name = "ofb-aes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_setkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1210,10 +1229,9 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.min_hw_rev = CC_HW_REV_630,
 	},
 	{
-		.name = "cts1(cbc(aes))",
-		.driver_name = "cts1-cbc-aes-ccree",
+		.name = "cts(cbc(aes))",
+		.driver_name = "cts-cbc-aes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_setkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1230,7 +1248,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "ctr(aes)",
 		.driver_name = "ctr-aes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_setkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1247,7 +1264,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "cbc(des3_ede)",
 		.driver_name = "cbc-3des-ccree",
 		.blocksize = DES3_EDE_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_setkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1264,7 +1280,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "ecb(des3_ede)",
 		.driver_name = "ecb-3des-ccree",
 		.blocksize = DES3_EDE_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_setkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1281,7 +1296,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "cbc(des)",
 		.driver_name = "cbc-des-ccree",
 		.blocksize = DES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_setkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1298,7 +1312,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "ecb(des)",
 		.driver_name = "ecb-des-ccree",
 		.blocksize = DES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_setkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1338,8 +1351,7 @@ static struct cc_crypto_alg *cc_create_alg(const struct cc_alg_template *tmpl,
 
 	alg->base.cra_init = cc_cipher_init;
 	alg->base.cra_exit = cc_cipher_exit;
-	alg->base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY |
-				CRYPTO_ALG_TYPE_SKCIPHER;
+	alg->base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY;
 
 	t_alg->cipher_mode = tmpl->cipher_mode;
 	t_alg->flow_mode = tmpl->flow_mode;
diff --git a/drivers/crypto/ccree/cc_cipher.h b/drivers/crypto/ccree/cc_cipher.h
index 68444cfa936b..4dbc0a1e6d5c 100644
--- a/drivers/crypto/ccree/cc_cipher.h
+++ b/drivers/crypto/ccree/cc_cipher.h
@@ -22,7 +22,6 @@ struct cipher_req_ctx {
 	u32 out_mlli_nents;
 	u8 *backup_info; /*store iv for generated IV flow*/
 	u8 *iv;
-	bool is_giv;
 	struct mlli_params mlli_params;
 };
 
diff --git a/drivers/crypto/ccree/cc_driver.c b/drivers/crypto/ccree/cc_driver.c
index bd974fef05e4..1ff229c2aeab 100644
--- a/drivers/crypto/ccree/cc_driver.c
+++ b/drivers/crypto/ccree/cc_driver.c
@@ -131,8 +131,8 @@ static irqreturn_t cc_isr(int irq, void *dev_id)
 	}
 
 	if (irr) {
-		dev_dbg(dev, "IRR includes unknown cause bits (0x%08X)\n",
-			irr);
+		dev_dbg_ratelimited(dev, "IRR includes unknown cause bits (0x%08X)\n",
+				    irr);
 		/* Just warning */
 	}
 
diff --git a/drivers/crypto/ccree/cc_driver.h b/drivers/crypto/ccree/cc_driver.h
index 95f82b2d1e70..d608a4faf662 100644
--- a/drivers/crypto/ccree/cc_driver.h
+++ b/drivers/crypto/ccree/cc_driver.h
@@ -148,7 +148,6 @@ struct cc_alg_template {
 	char name[CRYPTO_MAX_ALG_NAME];
 	char driver_name[CRYPTO_MAX_ALG_NAME];
 	unsigned int blocksize;
-	u32 type;
 	union {
 		struct skcipher_alg skcipher;
 		struct aead_alg aead;
diff --git a/drivers/crypto/ccree/cc_hash.c b/drivers/crypto/ccree/cc_hash.c
index 96ff777474d7..b9313306c36f 100644
--- a/drivers/crypto/ccree/cc_hash.c
+++ b/drivers/crypto/ccree/cc_hash.c
@@ -602,66 +602,7 @@ static int cc_hash_update(struct ahash_request *req)
 	return rc;
 }
 
-static int cc_hash_finup(struct ahash_request *req)
-{
-	struct ahash_req_ctx *state = ahash_request_ctx(req);
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct cc_hash_ctx *ctx = crypto_ahash_ctx(tfm);
-	u32 digestsize = crypto_ahash_digestsize(tfm);
-	struct scatterlist *src = req->src;
-	unsigned int nbytes = req->nbytes;
-	u8 *result = req->result;
-	struct device *dev = drvdata_to_dev(ctx->drvdata);
-	bool is_hmac = ctx->is_hmac;
-	struct cc_crypto_req cc_req = {};
-	struct cc_hw_desc desc[CC_MAX_HASH_SEQ_LEN];
-	unsigned int idx = 0;
-	int rc;
-	gfp_t flags = cc_gfp_flags(&req->base);
-
-	dev_dbg(dev, "===== %s-finup (%d) ====\n", is_hmac ? "hmac" : "hash",
-		nbytes);
-
-	if (cc_map_req(dev, state, ctx)) {
-		dev_err(dev, "map_ahash_source() failed\n");
-		return -EINVAL;
-	}
-
-	if (cc_map_hash_request_final(ctx->drvdata, state, src, nbytes, 1,
-				      flags)) {
-		dev_err(dev, "map_ahash_request_final() failed\n");
-		cc_unmap_req(dev, state, ctx);
-		return -ENOMEM;
-	}
-	if (cc_map_result(dev, state, digestsize)) {
-		dev_err(dev, "map_ahash_digest() failed\n");
-		cc_unmap_hash_request(dev, state, src, true);
-		cc_unmap_req(dev, state, ctx);
-		return -ENOMEM;
-	}
-
-	/* Setup request structure */
-	cc_req.user_cb = cc_hash_complete;
-	cc_req.user_arg = req;
-
-	idx = cc_restore_hash(desc, ctx, state, idx);
-
-	if (is_hmac)
-		idx = cc_fin_hmac(desc, req, idx);
-
-	idx = cc_fin_result(desc, req, idx);
-
-	rc = cc_send_request(ctx->drvdata, &cc_req, desc, idx, &req->base);
-	if (rc != -EINPROGRESS && rc != -EBUSY) {
-		dev_err(dev, "send_request() failed (rc=%d)\n", rc);
-		cc_unmap_hash_request(dev, state, src, true);
-		cc_unmap_result(dev, state, digestsize, result);
-		cc_unmap_req(dev, state, ctx);
-	}
-	return rc;
-}
-
-static int cc_hash_final(struct ahash_request *req)
+static int cc_do_finup(struct ahash_request *req, bool update)
 {
 	struct ahash_req_ctx *state = ahash_request_ctx(req);
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
@@ -678,21 +619,20 @@ static int cc_hash_final(struct ahash_request *req)
 	int rc;
 	gfp_t flags = cc_gfp_flags(&req->base);
 
-	dev_dbg(dev, "===== %s-final (%d) ====\n", is_hmac ? "hmac" : "hash",
-		nbytes);
+	dev_dbg(dev, "===== %s-%s (%d) ====\n", is_hmac ? "hmac" : "hash",
+		update ? "finup" : "final", nbytes);
 
 	if (cc_map_req(dev, state, ctx)) {
 		dev_err(dev, "map_ahash_source() failed\n");
 		return -EINVAL;
 	}
 
-	if (cc_map_hash_request_final(ctx->drvdata, state, src, nbytes, 0,
+	if (cc_map_hash_request_final(ctx->drvdata, state, src, nbytes, update,
 				      flags)) {
 		dev_err(dev, "map_ahash_request_final() failed\n");
 		cc_unmap_req(dev, state, ctx);
 		return -ENOMEM;
 	}
-
 	if (cc_map_result(dev, state, digestsize)) {
 		dev_err(dev, "map_ahash_digest() failed\n");
 		cc_unmap_hash_request(dev, state, src, true);
@@ -706,7 +646,7 @@ static int cc_hash_final(struct ahash_request *req)
 
 	idx = cc_restore_hash(desc, ctx, state, idx);
 
-	/* "DO-PAD" must be enabled only when writing current length to HW */
+	/* Pad the hash */
 	hw_desc_init(&desc[idx]);
 	set_cipher_do(&desc[idx], DO_PAD);
 	set_cipher_mode(&desc[idx], ctx->hw_mode);
@@ -731,6 +671,17 @@ static int cc_hash_final(struct ahash_request *req)
 	return rc;
 }
 
+static int cc_hash_finup(struct ahash_request *req)
+{
+	return cc_do_finup(req, true);
+}
+
+
+static int cc_hash_final(struct ahash_request *req)
+{
+	return cc_do_finup(req, false);
+}
+
 static int cc_hash_init(struct ahash_request *req)
 {
 	struct ahash_req_ctx *state = ahash_request_ctx(req);
@@ -1813,9 +1764,7 @@ static struct cc_hash_alg *cc_alloc_hash_alg(struct cc_hash_template *template,
 	alg->cra_exit = cc_cra_exit;
 
 	alg->cra_init = cc_cra_init;
-	alg->cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_TYPE_AHASH |
-			CRYPTO_ALG_KERN_DRIVER_ONLY;
-	alg->cra_type = &crypto_ahash_type;
+	alg->cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY;
 
 	t_crypto_alg->hash_mode = template->hash_mode;
 	t_crypto_alg->hw_mode = template->hw_mode;
diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c
index b916c4eb608c..5c539af8ed60 100644
--- a/drivers/crypto/chelsio/chcr_algo.c
+++ b/drivers/crypto/chelsio/chcr_algo.c
@@ -4203,7 +4203,6 @@ static int chcr_unregister_alg(void)
 #define SZ_AHASH_CTX sizeof(struct chcr_context)
 #define SZ_AHASH_H_CTX (sizeof(struct chcr_context) + sizeof(struct hmac_ctx))
 #define SZ_AHASH_REQ_CTX sizeof(struct chcr_ahash_req_ctx)
-#define AHASH_CRA_FLAGS (CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC)
 
 /*
  *	chcr_register_alg - Register crypto algorithms with kernel framework.
@@ -4237,8 +4236,7 @@ static int chcr_register_alg(void)
 			break;
 		case CRYPTO_ALG_TYPE_AEAD:
 			driver_algs[i].alg.aead.base.cra_flags =
-				CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC |
-				CRYPTO_ALG_NEED_FALLBACK;
+				CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK;
 			driver_algs[i].alg.aead.encrypt = chcr_aead_encrypt;
 			driver_algs[i].alg.aead.decrypt = chcr_aead_decrypt;
 			driver_algs[i].alg.aead.init = chcr_aead_cra_init;
@@ -4258,10 +4256,9 @@ static int chcr_register_alg(void)
 			a_hash->halg.statesize = SZ_AHASH_REQ_CTX;
 			a_hash->halg.base.cra_priority = CHCR_CRA_PRIORITY;
 			a_hash->halg.base.cra_module = THIS_MODULE;
-			a_hash->halg.base.cra_flags = AHASH_CRA_FLAGS;
+			a_hash->halg.base.cra_flags = CRYPTO_ALG_ASYNC;
 			a_hash->halg.base.cra_alignmask = 0;
 			a_hash->halg.base.cra_exit = NULL;
-			a_hash->halg.base.cra_type = &crypto_ahash_type;
 
 			if (driver_algs[i].type == CRYPTO_ALG_TYPE_HMAC) {
 				a_hash->halg.base.cra_init = chcr_hmac_cra_init;
diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.c b/drivers/crypto/chelsio/chtls/chtls_cm.c
index 2bb6f0380758..0997e166ea57 100644
--- a/drivers/crypto/chelsio/chtls/chtls_cm.c
+++ b/drivers/crypto/chelsio/chtls/chtls_cm.c
@@ -1673,7 +1673,7 @@ static void chtls_timewait(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	tp->rcv_nxt++;
-	tp->rx_opt.ts_recent_stamp = get_seconds();
+	tp->rx_opt.ts_recent_stamp = ktime_get_seconds();
 	tp->srtt_us = 0;
 	tcp_time_wait(sk, TCP_TIME_WAIT, 0);
 }
diff --git a/drivers/crypto/chelsio/chtls/chtls_hw.c b/drivers/crypto/chelsio/chtls/chtls_hw.c
index 55d50140f9e5..490960755864 100644
--- a/drivers/crypto/chelsio/chtls/chtls_hw.c
+++ b/drivers/crypto/chelsio/chtls/chtls_hw.c
@@ -97,7 +97,7 @@ static int chtls_set_tcb_field(struct sock *sk, u16 word, u64 mask, u64 val)
 int chtls_set_tcb_tflag(struct sock *sk, unsigned int bit_pos, int val)
 {
 	return chtls_set_tcb_field(sk, 1, 1ULL << bit_pos,
-				   val << bit_pos);
+				   (u64)val << bit_pos);
 }
 
 static int chtls_set_tcb_keyid(struct sock *sk, int keyid)
diff --git a/drivers/crypto/hisilicon/Kconfig b/drivers/crypto/hisilicon/Kconfig
new file mode 100644
index 000000000000..8ca9c503bcb0
--- /dev/null
+++ b/drivers/crypto/hisilicon/Kconfig
@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0
+
+config CRYPTO_DEV_HISI_SEC
+	tristate "Support for Hisilicon SEC crypto block cipher accelerator"
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_ALGAPI
+	select SG_SPLIT
+	depends on ARM64 || COMPILE_TEST
+	depends on HAS_IOMEM
+	help
+	  Support for Hisilicon SEC Engine in Hip06 and Hip07
+
+	  To compile this as a module, choose M here: the module
+	  will be called hisi_sec.
diff --git a/drivers/crypto/hisilicon/Makefile b/drivers/crypto/hisilicon/Makefile
new file mode 100644
index 000000000000..463f46ace182
--- /dev/null
+++ b/drivers/crypto/hisilicon/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_CRYPTO_DEV_HISI_SEC) += sec/
diff --git a/drivers/crypto/hisilicon/sec/Makefile b/drivers/crypto/hisilicon/sec/Makefile
new file mode 100644
index 000000000000..a55b698e0c27
--- /dev/null
+++ b/drivers/crypto/hisilicon/sec/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_CRYPTO_DEV_HISI_SEC) += hisi_sec.o
+hisi_sec-y = sec_algs.o sec_drv.o
diff --git a/drivers/crypto/hisilicon/sec/sec_algs.c b/drivers/crypto/hisilicon/sec/sec_algs.c
new file mode 100644
index 000000000000..f7d6d690116e
--- /dev/null
+++ b/drivers/crypto/hisilicon/sec/sec_algs.c
@@ -0,0 +1,1122 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2016-2017 Hisilicon Limited. */
+#include <linux/crypto.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <crypto/des.h>
+#include <crypto/skcipher.h>
+#include <crypto/xts.h>
+#include <crypto/internal/skcipher.h>
+
+#include "sec_drv.h"
+
+#define SEC_MAX_CIPHER_KEY		64
+#define SEC_REQ_LIMIT SZ_32M
+
+struct sec_c_alg_cfg {
+	unsigned c_alg		: 3;
+	unsigned c_mode		: 3;
+	unsigned key_len	: 2;
+	unsigned c_width	: 2;
+};
+
+static const struct sec_c_alg_cfg sec_c_alg_cfgs[] =  {
+	[SEC_C_DES_ECB_64] = {
+		.c_alg = SEC_C_ALG_DES,
+		.c_mode = SEC_C_MODE_ECB,
+		.key_len = SEC_KEY_LEN_DES,
+	},
+	[SEC_C_DES_CBC_64] = {
+		.c_alg = SEC_C_ALG_DES,
+		.c_mode = SEC_C_MODE_CBC,
+		.key_len = SEC_KEY_LEN_DES,
+	},
+	[SEC_C_3DES_ECB_192_3KEY] = {
+		.c_alg = SEC_C_ALG_3DES,
+		.c_mode = SEC_C_MODE_ECB,
+		.key_len = SEC_KEY_LEN_3DES_3_KEY,
+	},
+	[SEC_C_3DES_ECB_192_2KEY] = {
+		.c_alg = SEC_C_ALG_3DES,
+		.c_mode = SEC_C_MODE_ECB,
+		.key_len = SEC_KEY_LEN_3DES_2_KEY,
+	},
+	[SEC_C_3DES_CBC_192_3KEY] = {
+		.c_alg = SEC_C_ALG_3DES,
+		.c_mode = SEC_C_MODE_CBC,
+		.key_len = SEC_KEY_LEN_3DES_3_KEY,
+	},
+	[SEC_C_3DES_CBC_192_2KEY] = {
+		.c_alg = SEC_C_ALG_3DES,
+		.c_mode = SEC_C_MODE_CBC,
+		.key_len = SEC_KEY_LEN_3DES_2_KEY,
+	},
+	[SEC_C_AES_ECB_128] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_ECB,
+		.key_len = SEC_KEY_LEN_AES_128,
+	},
+	[SEC_C_AES_ECB_192] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_ECB,
+		.key_len = SEC_KEY_LEN_AES_192,
+	},
+	[SEC_C_AES_ECB_256] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_ECB,
+		.key_len = SEC_KEY_LEN_AES_256,
+	},
+	[SEC_C_AES_CBC_128] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_CBC,
+		.key_len = SEC_KEY_LEN_AES_128,
+	},
+	[SEC_C_AES_CBC_192] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_CBC,
+		.key_len = SEC_KEY_LEN_AES_192,
+	},
+	[SEC_C_AES_CBC_256] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_CBC,
+		.key_len = SEC_KEY_LEN_AES_256,
+	},
+	[SEC_C_AES_CTR_128] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_CTR,
+		.key_len = SEC_KEY_LEN_AES_128,
+	},
+	[SEC_C_AES_CTR_192] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_CTR,
+		.key_len = SEC_KEY_LEN_AES_192,
+	},
+	[SEC_C_AES_CTR_256] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_CTR,
+		.key_len = SEC_KEY_LEN_AES_256,
+	},
+	[SEC_C_AES_XTS_128] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_XTS,
+		.key_len = SEC_KEY_LEN_AES_128,
+	},
+	[SEC_C_AES_XTS_256] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_XTS,
+		.key_len = SEC_KEY_LEN_AES_256,
+	},
+	[SEC_C_NULL] = {
+	},
+};
+
+/*
+ * Mutex used to ensure safe operation of reference count of
+ * alg providers
+ */
+static DEFINE_MUTEX(algs_lock);
+static unsigned int active_devs;
+
+static void sec_alg_skcipher_init_template(struct sec_alg_tfm_ctx *ctx,
+					   struct sec_bd_info *req,
+					   enum sec_cipher_alg alg)
+{
+	const struct sec_c_alg_cfg *cfg = &sec_c_alg_cfgs[alg];
+
+	memset(req, 0, sizeof(*req));
+	req->w0 |= cfg->c_mode << SEC_BD_W0_C_MODE_S;
+	req->w1 |= cfg->c_alg << SEC_BD_W1_C_ALG_S;
+	req->w3 |= cfg->key_len << SEC_BD_W3_C_KEY_LEN_S;
+	req->w0 |= cfg->c_width << SEC_BD_W0_C_WIDTH_S;
+
+	req->cipher_key_addr_lo = lower_32_bits(ctx->pkey);
+	req->cipher_key_addr_hi = upper_32_bits(ctx->pkey);
+}
+
+static void sec_alg_skcipher_init_context(struct crypto_skcipher *atfm,
+					  const u8 *key,
+					  unsigned int keylen,
+					  enum sec_cipher_alg alg)
+{
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(atfm);
+	struct sec_alg_tfm_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ctx->cipher_alg = alg;
+	memcpy(ctx->key, key, keylen);
+	sec_alg_skcipher_init_template(ctx, &ctx->req_template,
+				       ctx->cipher_alg);
+}
+
+static int sec_alloc_and_fill_hw_sgl(struct sec_hw_sgl **sec_sgl,
+				     dma_addr_t *psec_sgl,
+				     struct scatterlist *sgl,
+				     int count,
+				     struct sec_dev_info *info)
+{
+	struct sec_hw_sgl *sgl_current = NULL;
+	struct sec_hw_sgl *sgl_next;
+	dma_addr_t sgl_next_dma;
+	struct scatterlist *sg;
+	int ret, sge_index, i;
+
+	if (!count)
+		return -EINVAL;
+
+	for_each_sg(sgl, sg, count, i) {
+		sge_index = i % SEC_MAX_SGE_NUM;
+		if (sge_index == 0) {
+			sgl_next = dma_pool_zalloc(info->hw_sgl_pool,
+						   GFP_KERNEL, &sgl_next_dma);
+			if (!sgl_next) {
+				ret = -ENOMEM;
+				goto err_free_hw_sgls;
+			}
+
+			if (!sgl_current) { /* First one */
+				*psec_sgl = sgl_next_dma;
+				*sec_sgl = sgl_next;
+			} else { /* Chained */
+				sgl_current->entry_sum_in_sgl = SEC_MAX_SGE_NUM;
+				sgl_current->next_sgl = sgl_next_dma;
+				sgl_current->next = sgl_next;
+			}
+			sgl_current = sgl_next;
+		}
+		sgl_current->sge_entries[sge_index].buf = sg_dma_address(sg);
+		sgl_current->sge_entries[sge_index].len = sg_dma_len(sg);
+		sgl_current->data_bytes_in_sgl += sg_dma_len(sg);
+	}
+	sgl_current->entry_sum_in_sgl = count % SEC_MAX_SGE_NUM;
+	sgl_current->next_sgl = 0;
+	(*sec_sgl)->entry_sum_in_chain = count;
+
+	return 0;
+
+err_free_hw_sgls:
+	sgl_current = *sec_sgl;
+	while (sgl_current) {
+		sgl_next = sgl_current->next;
+		dma_pool_free(info->hw_sgl_pool, sgl_current,
+			      sgl_current->next_sgl);
+		sgl_current = sgl_next;
+	}
+	*psec_sgl = 0;
+
+	return ret;
+}
+
+static void sec_free_hw_sgl(struct sec_hw_sgl *hw_sgl,
+			    dma_addr_t psec_sgl, struct sec_dev_info *info)
+{
+	struct sec_hw_sgl *sgl_current, *sgl_next;
+
+	if (!hw_sgl)
+		return;
+	sgl_current = hw_sgl;
+	while (sgl_current->next) {
+		sgl_next = sgl_current->next;
+		dma_pool_free(info->hw_sgl_pool, sgl_current,
+			      sgl_current->next_sgl);
+		sgl_current = sgl_next;
+	}
+	dma_pool_free(info->hw_sgl_pool, hw_sgl, psec_sgl);
+}
+
+static int sec_alg_skcipher_setkey(struct crypto_skcipher *tfm,
+				   const u8 *key, unsigned int keylen,
+				   enum sec_cipher_alg alg)
+{
+	struct sec_alg_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct device *dev = ctx->queue->dev_info->dev;
+
+	mutex_lock(&ctx->lock);
+	if (ctx->key) {
+		/* rekeying */
+		memset(ctx->key, 0, SEC_MAX_CIPHER_KEY);
+	} else {
+		/* new key */
+		ctx->key = dma_zalloc_coherent(dev, SEC_MAX_CIPHER_KEY,
+					       &ctx->pkey, GFP_KERNEL);
+		if (!ctx->key) {
+			mutex_unlock(&ctx->lock);
+			return -ENOMEM;
+		}
+	}
+	mutex_unlock(&ctx->lock);
+	sec_alg_skcipher_init_context(tfm, key, keylen, alg);
+
+	return 0;
+}
+
+static int sec_alg_skcipher_setkey_aes_ecb(struct crypto_skcipher *tfm,
+					   const u8 *key, unsigned int keylen)
+{
+	enum sec_cipher_alg alg;
+
+	switch (keylen) {
+	case AES_KEYSIZE_128:
+		alg = SEC_C_AES_ECB_128;
+		break;
+	case AES_KEYSIZE_192:
+		alg = SEC_C_AES_ECB_192;
+		break;
+	case AES_KEYSIZE_256:
+		alg = SEC_C_AES_ECB_256;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return sec_alg_skcipher_setkey(tfm, key, keylen, alg);
+}
+
+static int sec_alg_skcipher_setkey_aes_cbc(struct crypto_skcipher *tfm,
+					   const u8 *key, unsigned int keylen)
+{
+	enum sec_cipher_alg alg;
+
+	switch (keylen) {
+	case AES_KEYSIZE_128:
+		alg = SEC_C_AES_CBC_128;
+		break;
+	case AES_KEYSIZE_192:
+		alg = SEC_C_AES_CBC_192;
+		break;
+	case AES_KEYSIZE_256:
+		alg = SEC_C_AES_CBC_256;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return sec_alg_skcipher_setkey(tfm, key, keylen, alg);
+}
+
+static int sec_alg_skcipher_setkey_aes_ctr(struct crypto_skcipher *tfm,
+					   const u8 *key, unsigned int keylen)
+{
+	enum sec_cipher_alg alg;
+
+	switch (keylen) {
+	case AES_KEYSIZE_128:
+		alg = SEC_C_AES_CTR_128;
+		break;
+	case AES_KEYSIZE_192:
+		alg = SEC_C_AES_CTR_192;
+		break;
+	case AES_KEYSIZE_256:
+		alg = SEC_C_AES_CTR_256;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return sec_alg_skcipher_setkey(tfm, key, keylen, alg);
+}
+
+static int sec_alg_skcipher_setkey_aes_xts(struct crypto_skcipher *tfm,
+					   const u8 *key, unsigned int keylen)
+{
+	enum sec_cipher_alg alg;
+	int ret;
+
+	ret = xts_verify_key(tfm, key, keylen);
+	if (ret)
+		return ret;
+
+	switch (keylen) {
+	case AES_KEYSIZE_128 * 2:
+		alg = SEC_C_AES_XTS_128;
+		break;
+	case AES_KEYSIZE_256 * 2:
+		alg = SEC_C_AES_XTS_256;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return sec_alg_skcipher_setkey(tfm, key, keylen, alg);
+}
+
+static int sec_alg_skcipher_setkey_des_ecb(struct crypto_skcipher *tfm,
+					   const u8 *key, unsigned int keylen)
+{
+	if (keylen != DES_KEY_SIZE)
+		return -EINVAL;
+
+	return sec_alg_skcipher_setkey(tfm, key, keylen, SEC_C_DES_ECB_64);
+}
+
+static int sec_alg_skcipher_setkey_des_cbc(struct crypto_skcipher *tfm,
+					   const u8 *key, unsigned int keylen)
+{
+	if (keylen != DES_KEY_SIZE)
+		return -EINVAL;
+
+	return sec_alg_skcipher_setkey(tfm, key, keylen, SEC_C_DES_CBC_64);
+}
+
+static int sec_alg_skcipher_setkey_3des_ecb(struct crypto_skcipher *tfm,
+					    const u8 *key, unsigned int keylen)
+{
+	if (keylen != DES_KEY_SIZE * 3)
+		return -EINVAL;
+
+	return sec_alg_skcipher_setkey(tfm, key, keylen,
+				       SEC_C_3DES_ECB_192_3KEY);
+}
+
+static int sec_alg_skcipher_setkey_3des_cbc(struct crypto_skcipher *tfm,
+					    const u8 *key, unsigned int keylen)
+{
+	if (keylen != DES3_EDE_KEY_SIZE)
+		return -EINVAL;
+
+	return sec_alg_skcipher_setkey(tfm, key, keylen,
+				       SEC_C_3DES_CBC_192_3KEY);
+}
+
+static void sec_alg_free_el(struct sec_request_el *el,
+			    struct sec_dev_info *info)
+{
+	sec_free_hw_sgl(el->out, el->dma_out, info);
+	sec_free_hw_sgl(el->in, el->dma_in, info);
+	kfree(el->sgl_in);
+	kfree(el->sgl_out);
+	kfree(el);
+}
+
+/* queuelock must be held */
+static int sec_send_request(struct sec_request *sec_req, struct sec_queue *queue)
+{
+	struct sec_request_el *el, *temp;
+	int ret = 0;
+
+	mutex_lock(&sec_req->lock);
+	list_for_each_entry_safe(el, temp, &sec_req->elements, head) {
+		/*
+		 * Add to hardware queue only under following circumstances
+		 * 1) Software and hardware queue empty so no chain dependencies
+		 * 2) No dependencies as new IV - (check software queue empty
+		 *    to maintain order)
+		 * 3) No dependencies because the mode does no chaining.
+		 *
+		 * In other cases first insert onto the software queue which
+		 * is then emptied as requests complete
+		 */
+		if (!queue->havesoftqueue ||
+		    (kfifo_is_empty(&queue->softqueue) &&
+		     sec_queue_empty(queue))) {
+			ret = sec_queue_send(queue, &el->req, sec_req);
+			if (ret == -EAGAIN) {
+				/* Wait unti we can send then try again */
+				/* DEAD if here - should not happen */
+				ret = -EBUSY;
+				goto err_unlock;
+			}
+		} else {
+			kfifo_put(&queue->softqueue, el);
+		}
+	}
+err_unlock:
+	mutex_unlock(&sec_req->lock);
+
+	return ret;
+}
+
+static void sec_skcipher_alg_callback(struct sec_bd_info *sec_resp,
+				      struct crypto_async_request *req_base)
+{
+	struct skcipher_request *skreq = container_of(req_base,
+						      struct skcipher_request,
+						      base);
+	struct sec_request *sec_req = skcipher_request_ctx(skreq);
+	struct sec_request *backlog_req;
+	struct sec_request_el *sec_req_el, *nextrequest;
+	struct sec_alg_tfm_ctx *ctx = sec_req->tfm_ctx;
+	struct crypto_skcipher *atfm = crypto_skcipher_reqtfm(skreq);
+	struct device *dev = ctx->queue->dev_info->dev;
+	int icv_or_skey_en, ret;
+	bool done;
+
+	sec_req_el = list_first_entry(&sec_req->elements, struct sec_request_el,
+				      head);
+	icv_or_skey_en = (sec_resp->w0 & SEC_BD_W0_ICV_OR_SKEY_EN_M) >>
+		SEC_BD_W0_ICV_OR_SKEY_EN_S;
+	if (sec_resp->w1 & SEC_BD_W1_BD_INVALID || icv_or_skey_en == 3) {
+		dev_err(dev, "Got an invalid answer %lu %d\n",
+			sec_resp->w1 & SEC_BD_W1_BD_INVALID,
+			icv_or_skey_en);
+		sec_req->err = -EINVAL;
+		/*
+		 * We need to muddle on to avoid getting stuck with elements
+		 * on the queue. Error will be reported so requester so
+		 * it should be able to handle appropriately.
+		 */
+	}
+
+	mutex_lock(&ctx->queue->queuelock);
+	/* Put the IV in place for chained cases */
+	switch (ctx->cipher_alg) {
+	case SEC_C_AES_CBC_128:
+	case SEC_C_AES_CBC_192:
+	case SEC_C_AES_CBC_256:
+		if (sec_req_el->req.w0 & SEC_BD_W0_DE)
+			sg_pcopy_to_buffer(sec_req_el->sgl_out,
+					   sg_nents(sec_req_el->sgl_out),
+					   skreq->iv,
+					   crypto_skcipher_ivsize(atfm),
+					   sec_req_el->el_length -
+					   crypto_skcipher_ivsize(atfm));
+		else
+			sg_pcopy_to_buffer(sec_req_el->sgl_in,
+					   sg_nents(sec_req_el->sgl_in),
+					   skreq->iv,
+					   crypto_skcipher_ivsize(atfm),
+					   sec_req_el->el_length -
+					   crypto_skcipher_ivsize(atfm));
+		/* No need to sync to the device as coherent DMA */
+		break;
+	case SEC_C_AES_CTR_128:
+	case SEC_C_AES_CTR_192:
+	case SEC_C_AES_CTR_256:
+		crypto_inc(skreq->iv, 16);
+		break;
+	default:
+		/* Do not update */
+		break;
+	}
+
+	if (ctx->queue->havesoftqueue &&
+	    !kfifo_is_empty(&ctx->queue->softqueue) &&
+	    sec_queue_empty(ctx->queue)) {
+		ret = kfifo_get(&ctx->queue->softqueue, &nextrequest);
+		if (ret <= 0)
+			dev_err(dev,
+				"Error getting next element from kfifo %d\n",
+				ret);
+		else
+			/* We know there is space so this cannot fail */
+			sec_queue_send(ctx->queue, &nextrequest->req,
+				       nextrequest->sec_req);
+	} else if (!list_empty(&ctx->backlog)) {
+		/* Need to verify there is room first */
+		backlog_req = list_first_entry(&ctx->backlog,
+					       typeof(*backlog_req),
+					       backlog_head);
+		if (sec_queue_can_enqueue(ctx->queue,
+		    backlog_req->num_elements) ||
+		    (ctx->queue->havesoftqueue &&
+		     kfifo_avail(&ctx->queue->softqueue) >
+		     backlog_req->num_elements)) {
+			sec_send_request(backlog_req, ctx->queue);
+			backlog_req->req_base->complete(backlog_req->req_base,
+							-EINPROGRESS);
+			list_del(&backlog_req->backlog_head);
+		}
+	}
+	mutex_unlock(&ctx->queue->queuelock);
+
+	mutex_lock(&sec_req->lock);
+	list_del(&sec_req_el->head);
+	mutex_unlock(&sec_req->lock);
+	sec_alg_free_el(sec_req_el, ctx->queue->dev_info);
+
+	/*
+	 * Request is done.
+	 * The dance is needed as the lock is freed in the completion
+	 */
+	mutex_lock(&sec_req->lock);
+	done = list_empty(&sec_req->elements);
+	mutex_unlock(&sec_req->lock);
+	if (done) {
+		if (crypto_skcipher_ivsize(atfm)) {
+			dma_unmap_single(dev, sec_req->dma_iv,
+					 crypto_skcipher_ivsize(atfm),
+					 DMA_TO_DEVICE);
+		}
+		dma_unmap_sg(dev, skreq->src, sec_req->len_in,
+			     DMA_BIDIRECTIONAL);
+		if (skreq->src != skreq->dst)
+			dma_unmap_sg(dev, skreq->dst, sec_req->len_out,
+				     DMA_BIDIRECTIONAL);
+		skreq->base.complete(&skreq->base, sec_req->err);
+	}
+}
+
+void sec_alg_callback(struct sec_bd_info *resp, void *shadow)
+{
+	struct sec_request *sec_req = shadow;
+
+	sec_req->cb(resp, sec_req->req_base);
+}
+
+static int sec_alg_alloc_and_calc_split_sizes(int length, size_t **split_sizes,
+					      int *steps)
+{
+	size_t *sizes;
+	int i;
+
+	/* Split into suitable sized blocks */
+	*steps = roundup(length, SEC_REQ_LIMIT) / SEC_REQ_LIMIT;
+	sizes = kcalloc(*steps, sizeof(*sizes), GFP_KERNEL);
+	if (!sizes)
+		return -ENOMEM;
+
+	for (i = 0; i < *steps - 1; i++)
+		sizes[i] = SEC_REQ_LIMIT;
+	sizes[*steps - 1] = length - SEC_REQ_LIMIT * (*steps - 1);
+	*split_sizes = sizes;
+
+	return 0;
+}
+
+static int sec_map_and_split_sg(struct scatterlist *sgl, size_t *split_sizes,
+				int steps, struct scatterlist ***splits,
+				int **splits_nents,
+				int sgl_len_in,
+				struct device *dev)
+{
+	int ret, count;
+
+	count = dma_map_sg(dev, sgl, sgl_len_in, DMA_BIDIRECTIONAL);
+	if (!count)
+		return -EINVAL;
+
+	*splits = kcalloc(steps, sizeof(struct scatterlist *), GFP_KERNEL);
+	if (!*splits) {
+		ret = -ENOMEM;
+		goto err_unmap_sg;
+	}
+	*splits_nents = kcalloc(steps, sizeof(int), GFP_KERNEL);
+	if (!*splits_nents) {
+		ret = -ENOMEM;
+		goto err_free_splits;
+	}
+
+	/* output the scatter list before and after this */
+	ret = sg_split(sgl, count, 0, steps, split_sizes,
+		       *splits, *splits_nents, GFP_KERNEL);
+	if (ret) {
+		ret = -ENOMEM;
+		goto err_free_splits_nents;
+	}
+
+	return 0;
+
+err_free_splits_nents:
+	kfree(*splits_nents);
+err_free_splits:
+	kfree(*splits);
+err_unmap_sg:
+	dma_unmap_sg(dev, sgl, sgl_len_in, DMA_BIDIRECTIONAL);
+
+	return ret;
+}
+
+/*
+ * Reverses the sec_map_and_split_sg call for messages not yet added to
+ * the queues.
+ */
+static void sec_unmap_sg_on_err(struct scatterlist *sgl, int steps,
+				struct scatterlist **splits, int *splits_nents,
+				int sgl_len_in, struct device *dev)
+{
+	int i;
+
+	for (i = 0; i < steps; i++)
+		kfree(splits[i]);
+	kfree(splits_nents);
+	kfree(splits);
+
+	dma_unmap_sg(dev, sgl, sgl_len_in, DMA_BIDIRECTIONAL);
+}
+
+static struct sec_request_el
+*sec_alg_alloc_and_fill_el(struct sec_bd_info *template, int encrypt,
+			   int el_size, bool different_dest,
+			   struct scatterlist *sgl_in, int n_ents_in,
+			   struct scatterlist *sgl_out, int n_ents_out,
+			   struct sec_dev_info *info)
+{
+	struct sec_request_el *el;
+	struct sec_bd_info *req;
+	int ret;
+
+	el = kzalloc(sizeof(*el), GFP_KERNEL);
+	if (!el)
+		return ERR_PTR(-ENOMEM);
+	el->el_length = el_size;
+	req = &el->req;
+	memcpy(req, template, sizeof(*req));
+
+	req->w0 &= ~SEC_BD_W0_CIPHER_M;
+	if (encrypt)
+		req->w0 |= SEC_CIPHER_ENCRYPT << SEC_BD_W0_CIPHER_S;
+	else
+		req->w0 |= SEC_CIPHER_DECRYPT << SEC_BD_W0_CIPHER_S;
+
+	req->w0 &= ~SEC_BD_W0_C_GRAN_SIZE_19_16_M;
+	req->w0 |= ((el_size >> 16) << SEC_BD_W0_C_GRAN_SIZE_19_16_S) &
+		SEC_BD_W0_C_GRAN_SIZE_19_16_M;
+
+	req->w0 &= ~SEC_BD_W0_C_GRAN_SIZE_21_20_M;
+	req->w0 |= ((el_size >> 20) << SEC_BD_W0_C_GRAN_SIZE_21_20_S) &
+		SEC_BD_W0_C_GRAN_SIZE_21_20_M;
+
+	/* Writing whole u32 so no need to take care of masking */
+	req->w2 = ((1 << SEC_BD_W2_GRAN_NUM_S) & SEC_BD_W2_GRAN_NUM_M) |
+		((el_size << SEC_BD_W2_C_GRAN_SIZE_15_0_S) &
+		 SEC_BD_W2_C_GRAN_SIZE_15_0_M);
+
+	req->w3 &= ~SEC_BD_W3_CIPHER_LEN_OFFSET_M;
+	req->w1 |= SEC_BD_W1_ADDR_TYPE;
+
+	el->sgl_in = sgl_in;
+
+	ret = sec_alloc_and_fill_hw_sgl(&el->in, &el->dma_in, el->sgl_in,
+					n_ents_in, info);
+	if (ret)
+		goto err_free_el;
+
+	req->data_addr_lo = lower_32_bits(el->dma_in);
+	req->data_addr_hi = upper_32_bits(el->dma_in);
+
+	if (different_dest) {
+		el->sgl_out = sgl_out;
+		ret = sec_alloc_and_fill_hw_sgl(&el->out, &el->dma_out,
+						el->sgl_out,
+						n_ents_out, info);
+		if (ret)
+			goto err_free_hw_sgl_in;
+
+		req->w0 |= SEC_BD_W0_DE;
+		req->cipher_destin_addr_lo = lower_32_bits(el->dma_out);
+		req->cipher_destin_addr_hi = upper_32_bits(el->dma_out);
+
+	} else {
+		req->w0 &= ~SEC_BD_W0_DE;
+		req->cipher_destin_addr_lo = lower_32_bits(el->dma_in);
+		req->cipher_destin_addr_hi = upper_32_bits(el->dma_in);
+	}
+
+	return el;
+
+err_free_hw_sgl_in:
+	sec_free_hw_sgl(el->in, el->dma_in, info);
+err_free_el:
+	kfree(el);
+
+	return ERR_PTR(ret);
+}
+
+static int sec_alg_skcipher_crypto(struct skcipher_request *skreq,
+				   bool encrypt)
+{
+	struct crypto_skcipher *atfm = crypto_skcipher_reqtfm(skreq);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(atfm);
+	struct sec_alg_tfm_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct sec_queue *queue = ctx->queue;
+	struct sec_request *sec_req = skcipher_request_ctx(skreq);
+	struct sec_dev_info *info = queue->dev_info;
+	int i, ret, steps;
+	size_t *split_sizes;
+	struct scatterlist **splits_in;
+	struct scatterlist **splits_out = NULL;
+	int *splits_in_nents;
+	int *splits_out_nents = NULL;
+	struct sec_request_el *el, *temp;
+
+	mutex_init(&sec_req->lock);
+	sec_req->req_base = &skreq->base;
+	sec_req->err = 0;
+	/* SGL mapping out here to allow us to break it up as necessary */
+	sec_req->len_in = sg_nents(skreq->src);
+
+	ret = sec_alg_alloc_and_calc_split_sizes(skreq->cryptlen, &split_sizes,
+						 &steps);
+	if (ret)
+		return ret;
+	sec_req->num_elements = steps;
+	ret = sec_map_and_split_sg(skreq->src, split_sizes, steps, &splits_in,
+				   &splits_in_nents, sec_req->len_in,
+				   info->dev);
+	if (ret)
+		goto err_free_split_sizes;
+
+	if (skreq->src != skreq->dst) {
+		sec_req->len_out = sg_nents(skreq->dst);
+		ret = sec_map_and_split_sg(skreq->dst, split_sizes, steps,
+					   &splits_out, &splits_out_nents,
+					   sec_req->len_out, info->dev);
+		if (ret)
+			goto err_unmap_in_sg;
+	}
+	/* Shared info stored in seq_req - applies to all BDs */
+	sec_req->tfm_ctx = ctx;
+	sec_req->cb = sec_skcipher_alg_callback;
+	INIT_LIST_HEAD(&sec_req->elements);
+
+	/*
+	 * Future optimization.
+	 * In the chaining case we can't use a dma pool bounce buffer
+	 * but in the case where we know there is no chaining we can
+	 */
+	if (crypto_skcipher_ivsize(atfm)) {
+		sec_req->dma_iv = dma_map_single(info->dev, skreq->iv,
+						 crypto_skcipher_ivsize(atfm),
+						 DMA_TO_DEVICE);
+		if (dma_mapping_error(info->dev, sec_req->dma_iv)) {
+			ret = -ENOMEM;
+			goto err_unmap_out_sg;
+		}
+	}
+
+	/* Set them all up then queue - cleaner error handling. */
+	for (i = 0; i < steps; i++) {
+		el = sec_alg_alloc_and_fill_el(&ctx->req_template,
+					       encrypt ? 1 : 0,
+					       split_sizes[i],
+					       skreq->src != skreq->dst,
+					       splits_in[i], splits_in_nents[i],
+					       splits_out[i],
+					       splits_out_nents[i], info);
+		if (IS_ERR(el)) {
+			ret = PTR_ERR(el);
+			goto err_free_elements;
+		}
+		el->req.cipher_iv_addr_lo = lower_32_bits(sec_req->dma_iv);
+		el->req.cipher_iv_addr_hi = upper_32_bits(sec_req->dma_iv);
+		el->sec_req = sec_req;
+		list_add_tail(&el->head, &sec_req->elements);
+	}
+
+	/*
+	 * Only attempt to queue if the whole lot can fit in the queue -
+	 * we can't successfully cleanup after a partial queing so this
+	 * must succeed or fail atomically.
+	 *
+	 * Big hammer test of both software and hardware queues - could be
+	 * more refined but this is unlikely to happen so no need.
+	 */
+
+	/* Cleanup - all elements in pointer arrays have been coppied */
+	kfree(splits_in_nents);
+	kfree(splits_in);
+	kfree(splits_out_nents);
+	kfree(splits_out);
+	kfree(split_sizes);
+
+	/* Grab a big lock for a long time to avoid concurrency issues */
+	mutex_lock(&queue->queuelock);
+
+	/*
+	 * Can go on to queue if we have space in either:
+	 * 1) The hardware queue and no software queue
+	 * 2) The software queue
+	 * AND there is nothing in the backlog.  If there is backlog we
+	 * have to only queue to the backlog queue and return busy.
+	 */
+	if ((!sec_queue_can_enqueue(queue, steps) &&
+	     (!queue->havesoftqueue ||
+	      kfifo_avail(&queue->softqueue) > steps)) ||
+	    !list_empty(&ctx->backlog)) {
+		if ((skreq->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG)) {
+			list_add_tail(&sec_req->backlog_head, &ctx->backlog);
+			mutex_unlock(&queue->queuelock);
+			return -EBUSY;
+		}
+
+		ret = -EBUSY;
+		mutex_unlock(&queue->queuelock);
+		goto err_free_elements;
+	}
+	ret = sec_send_request(sec_req, queue);
+	mutex_unlock(&queue->queuelock);
+	if (ret)
+		goto err_free_elements;
+
+	return -EINPROGRESS;
+
+err_free_elements:
+	list_for_each_entry_safe(el, temp, &sec_req->elements, head) {
+		list_del(&el->head);
+		sec_alg_free_el(el, info);
+	}
+	if (crypto_skcipher_ivsize(atfm))
+		dma_unmap_single(info->dev, sec_req->dma_iv,
+				 crypto_skcipher_ivsize(atfm),
+				 DMA_BIDIRECTIONAL);
+err_unmap_out_sg:
+	if (skreq->src != skreq->dst)
+		sec_unmap_sg_on_err(skreq->dst, steps, splits_out,
+				    splits_out_nents, sec_req->len_out,
+				    info->dev);
+err_unmap_in_sg:
+	sec_unmap_sg_on_err(skreq->src, steps, splits_in, splits_in_nents,
+			    sec_req->len_in, info->dev);
+err_free_split_sizes:
+	kfree(split_sizes);
+
+	return ret;
+}
+
+static int sec_alg_skcipher_encrypt(struct skcipher_request *req)
+{
+	return sec_alg_skcipher_crypto(req, true);
+}
+
+static int sec_alg_skcipher_decrypt(struct skcipher_request *req)
+{
+	return sec_alg_skcipher_crypto(req, false);
+}
+
+static int sec_alg_skcipher_init(struct crypto_skcipher *tfm)
+{
+	struct sec_alg_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	mutex_init(&ctx->lock);
+	INIT_LIST_HEAD(&ctx->backlog);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct sec_request));
+
+	ctx->queue = sec_queue_alloc_start_safe();
+	if (IS_ERR(ctx->queue))
+		return PTR_ERR(ctx->queue);
+
+	mutex_init(&ctx->queue->queuelock);
+	ctx->queue->havesoftqueue = false;
+
+	return 0;
+}
+
+static void sec_alg_skcipher_exit(struct crypto_skcipher *tfm)
+{
+	struct sec_alg_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct device *dev = ctx->queue->dev_info->dev;
+
+	if (ctx->key) {
+		memzero_explicit(ctx->key, SEC_MAX_CIPHER_KEY);
+		dma_free_coherent(dev, SEC_MAX_CIPHER_KEY, ctx->key,
+				  ctx->pkey);
+	}
+	sec_queue_stop_release(ctx->queue);
+}
+
+static int sec_alg_skcipher_init_with_queue(struct crypto_skcipher *tfm)
+{
+	struct sec_alg_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int ret;
+
+	ret = sec_alg_skcipher_init(tfm);
+	if (ret)
+		return ret;
+
+	INIT_KFIFO(ctx->queue->softqueue);
+	ret = kfifo_alloc(&ctx->queue->softqueue, 512, GFP_KERNEL);
+	if (ret) {
+		sec_alg_skcipher_exit(tfm);
+		return ret;
+	}
+	ctx->queue->havesoftqueue = true;
+
+	return 0;
+}
+
+static void sec_alg_skcipher_exit_with_queue(struct crypto_skcipher *tfm)
+{
+	struct sec_alg_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	kfifo_free(&ctx->queue->softqueue);
+	sec_alg_skcipher_exit(tfm);
+}
+
+static struct skcipher_alg sec_algs[] = {
+	{
+		.base = {
+			.cra_name = "ecb(aes)",
+			.cra_driver_name = "hisi_sec_aes_ecb",
+			.cra_priority = 4001,
+			.cra_flags = CRYPTO_ALG_ASYNC,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct sec_alg_tfm_ctx),
+			.cra_alignmask = 0,
+			.cra_module = THIS_MODULE,
+		},
+		.init = sec_alg_skcipher_init,
+		.exit = sec_alg_skcipher_exit,
+		.setkey = sec_alg_skcipher_setkey_aes_ecb,
+		.decrypt = sec_alg_skcipher_decrypt,
+		.encrypt = sec_alg_skcipher_encrypt,
+		.min_keysize = AES_MIN_KEY_SIZE,
+		.max_keysize = AES_MAX_KEY_SIZE,
+		.ivsize = 0,
+	}, {
+		.base = {
+			.cra_name = "cbc(aes)",
+			.cra_driver_name = "hisi_sec_aes_cbc",
+			.cra_priority = 4001,
+			.cra_flags = CRYPTO_ALG_ASYNC,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct sec_alg_tfm_ctx),
+			.cra_alignmask = 0,
+			.cra_module = THIS_MODULE,
+		},
+		.init = sec_alg_skcipher_init_with_queue,
+		.exit = sec_alg_skcipher_exit_with_queue,
+		.setkey = sec_alg_skcipher_setkey_aes_cbc,
+		.decrypt = sec_alg_skcipher_decrypt,
+		.encrypt = sec_alg_skcipher_encrypt,
+		.min_keysize = AES_MIN_KEY_SIZE,
+		.max_keysize = AES_MAX_KEY_SIZE,
+		.ivsize = AES_BLOCK_SIZE,
+	}, {
+		.base = {
+			.cra_name = "ctr(aes)",
+			.cra_driver_name = "hisi_sec_aes_ctr",
+			.cra_priority = 4001,
+			.cra_flags = CRYPTO_ALG_ASYNC,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct sec_alg_tfm_ctx),
+			.cra_alignmask = 0,
+			.cra_module = THIS_MODULE,
+		},
+		.init = sec_alg_skcipher_init_with_queue,
+		.exit = sec_alg_skcipher_exit_with_queue,
+		.setkey = sec_alg_skcipher_setkey_aes_ctr,
+		.decrypt = sec_alg_skcipher_decrypt,
+		.encrypt = sec_alg_skcipher_encrypt,
+		.min_keysize = AES_MIN_KEY_SIZE,
+		.max_keysize = AES_MAX_KEY_SIZE,
+		.ivsize = AES_BLOCK_SIZE,
+	}, {
+		.base = {
+			.cra_name = "xts(aes)",
+			.cra_driver_name = "hisi_sec_aes_xts",
+			.cra_priority = 4001,
+			.cra_flags = CRYPTO_ALG_ASYNC,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct sec_alg_tfm_ctx),
+			.cra_alignmask = 0,
+			.cra_module = THIS_MODULE,
+		},
+		.init = sec_alg_skcipher_init,
+		.exit = sec_alg_skcipher_exit,
+		.setkey = sec_alg_skcipher_setkey_aes_xts,
+		.decrypt = sec_alg_skcipher_decrypt,
+		.encrypt = sec_alg_skcipher_encrypt,
+		.min_keysize = 2 * AES_MIN_KEY_SIZE,
+		.max_keysize = 2 * AES_MAX_KEY_SIZE,
+		.ivsize = AES_BLOCK_SIZE,
+	}, {
+	/* Unable to find any test vectors so untested */
+		.base = {
+			.cra_name = "ecb(des)",
+			.cra_driver_name = "hisi_sec_des_ecb",
+			.cra_priority = 4001,
+			.cra_flags = CRYPTO_ALG_ASYNC,
+			.cra_blocksize = DES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct sec_alg_tfm_ctx),
+			.cra_alignmask = 0,
+			.cra_module = THIS_MODULE,
+		},
+		.init = sec_alg_skcipher_init,
+		.exit = sec_alg_skcipher_exit,
+		.setkey = sec_alg_skcipher_setkey_des_ecb,
+		.decrypt = sec_alg_skcipher_decrypt,
+		.encrypt = sec_alg_skcipher_encrypt,
+		.min_keysize = DES_KEY_SIZE,
+		.max_keysize = DES_KEY_SIZE,
+		.ivsize = 0,
+	}, {
+		.base = {
+			.cra_name = "cbc(des)",
+			.cra_driver_name = "hisi_sec_des_cbc",
+			.cra_priority = 4001,
+			.cra_flags = CRYPTO_ALG_ASYNC,
+			.cra_blocksize = DES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct sec_alg_tfm_ctx),
+			.cra_alignmask = 0,
+			.cra_module = THIS_MODULE,
+		},
+		.init = sec_alg_skcipher_init_with_queue,
+		.exit = sec_alg_skcipher_exit_with_queue,
+		.setkey = sec_alg_skcipher_setkey_des_cbc,
+		.decrypt = sec_alg_skcipher_decrypt,
+		.encrypt = sec_alg_skcipher_encrypt,
+		.min_keysize = DES_KEY_SIZE,
+		.max_keysize = DES_KEY_SIZE,
+		.ivsize = DES_BLOCK_SIZE,
+	}, {
+		.base = {
+			.cra_name = "cbc(des3_ede)",
+			.cra_driver_name = "hisi_sec_3des_cbc",
+			.cra_priority = 4001,
+			.cra_flags = CRYPTO_ALG_ASYNC,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct sec_alg_tfm_ctx),
+			.cra_alignmask = 0,
+			.cra_module = THIS_MODULE,
+		},
+		.init = sec_alg_skcipher_init_with_queue,
+		.exit = sec_alg_skcipher_exit_with_queue,
+		.setkey = sec_alg_skcipher_setkey_3des_cbc,
+		.decrypt = sec_alg_skcipher_decrypt,
+		.encrypt = sec_alg_skcipher_encrypt,
+		.min_keysize = DES3_EDE_KEY_SIZE,
+		.max_keysize = DES3_EDE_KEY_SIZE,
+		.ivsize = DES3_EDE_BLOCK_SIZE,
+	}, {
+		.base = {
+			.cra_name = "ecb(des3_ede)",
+			.cra_driver_name = "hisi_sec_3des_ecb",
+			.cra_priority = 4001,
+			.cra_flags = CRYPTO_ALG_ASYNC,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct sec_alg_tfm_ctx),
+			.cra_alignmask = 0,
+			.cra_module = THIS_MODULE,
+		},
+		.init = sec_alg_skcipher_init,
+		.exit = sec_alg_skcipher_exit,
+		.setkey = sec_alg_skcipher_setkey_3des_ecb,
+		.decrypt = sec_alg_skcipher_decrypt,
+		.encrypt = sec_alg_skcipher_encrypt,
+		.min_keysize = DES3_EDE_KEY_SIZE,
+		.max_keysize = DES3_EDE_KEY_SIZE,
+		.ivsize = 0,
+	}
+};
+
+int sec_algs_register(void)
+{
+	int ret = 0;
+
+	mutex_lock(&algs_lock);
+	if (++active_devs != 1)
+		goto unlock;
+
+	ret = crypto_register_skciphers(sec_algs, ARRAY_SIZE(sec_algs));
+	if (ret)
+		--active_devs;
+unlock:
+	mutex_unlock(&algs_lock);
+
+	return ret;
+}
+
+void sec_algs_unregister(void)
+{
+	mutex_lock(&algs_lock);
+	if (--active_devs != 0)
+		goto unlock;
+	crypto_unregister_skciphers(sec_algs, ARRAY_SIZE(sec_algs));
+
+unlock:
+	mutex_unlock(&algs_lock);
+}
diff --git a/drivers/crypto/hisilicon/sec/sec_drv.c b/drivers/crypto/hisilicon/sec/sec_drv.c
new file mode 100644
index 000000000000..c1ee4e7bf996
--- /dev/null
+++ b/drivers/crypto/hisilicon/sec/sec_drv.c
@@ -0,0 +1,1323 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Driver for the Hisilicon SEC units found on Hip06 Hip07
+ *
+ * Copyright (c) 2016-2017 Hisilicon Limited.
+ */
+#include <linux/acpi.h>
+#include <linux/atomic.h>
+#include <linux/delay.h>
+#include <linux/dma-direction.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/io.h>
+#include <linux/iommu.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqreturn.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "sec_drv.h"
+
+#define SEC_QUEUE_AR_FROCE_ALLOC			0
+#define SEC_QUEUE_AR_FROCE_NOALLOC			1
+#define SEC_QUEUE_AR_FROCE_DIS				2
+
+#define SEC_QUEUE_AW_FROCE_ALLOC			0
+#define SEC_QUEUE_AW_FROCE_NOALLOC			1
+#define SEC_QUEUE_AW_FROCE_DIS				2
+
+/* SEC_ALGSUB registers */
+#define SEC_ALGSUB_CLK_EN_REG				0x03b8
+#define SEC_ALGSUB_CLK_DIS_REG				0x03bc
+#define SEC_ALGSUB_CLK_ST_REG				0x535c
+#define SEC_ALGSUB_RST_REQ_REG				0x0aa8
+#define SEC_ALGSUB_RST_DREQ_REG				0x0aac
+#define SEC_ALGSUB_RST_ST_REG				0x5a54
+#define   SEC_ALGSUB_RST_ST_IS_RST			BIT(0)
+
+#define SEC_ALGSUB_BUILD_RST_REQ_REG			0x0ab8
+#define SEC_ALGSUB_BUILD_RST_DREQ_REG			0x0abc
+#define SEC_ALGSUB_BUILD_RST_ST_REG			0x5a5c
+#define   SEC_ALGSUB_BUILD_RST_ST_IS_RST		BIT(0)
+
+#define SEC_SAA_BASE					0x00001000UL
+
+/* SEC_SAA registers */
+#define SEC_SAA_CTRL_REG(x)	((x) * SEC_SAA_ADDR_SIZE)
+#define   SEC_SAA_CTRL_GET_QM_EN			BIT(0)
+
+#define SEC_ST_INTMSK1_REG				0x0200
+#define SEC_ST_RINT1_REG				0x0400
+#define SEC_ST_INTSTS1_REG				0x0600
+#define SEC_BD_MNG_STAT_REG				0x0800
+#define SEC_PARSING_STAT_REG				0x0804
+#define SEC_LOAD_TIME_OUT_CNT_REG			0x0808
+#define SEC_CORE_WORK_TIME_OUT_CNT_REG			0x080c
+#define SEC_BACK_TIME_OUT_CNT_REG			0x0810
+#define SEC_BD1_PARSING_RD_TIME_OUT_CNT_REG		0x0814
+#define SEC_BD1_PARSING_WR_TIME_OUT_CNT_REG		0x0818
+#define SEC_BD2_PARSING_RD_TIME_OUT_CNT_REG		0x081c
+#define SEC_BD2_PARSING_WR_TIME_OUT_CNT_REG		0x0820
+#define SEC_SAA_ACC_REG					0x083c
+#define SEC_BD_NUM_CNT_IN_SEC_REG			0x0858
+#define SEC_LOAD_WORK_TIME_CNT_REG			0x0860
+#define SEC_CORE_WORK_WORK_TIME_CNT_REG			0x0864
+#define SEC_BACK_WORK_TIME_CNT_REG			0x0868
+#define SEC_SAA_IDLE_TIME_CNT_REG			0x086c
+#define SEC_SAA_CLK_CNT_REG				0x0870
+
+/* SEC_COMMON registers */
+#define SEC_CLK_EN_REG					0x0000
+#define SEC_CTRL_REG					0x0004
+
+#define SEC_COMMON_CNT_CLR_CE_REG			0x0008
+#define   SEC_COMMON_CNT_CLR_CE_CLEAR			BIT(0)
+#define   SEC_COMMON_CNT_CLR_CE_SNAP_EN			BIT(1)
+
+#define SEC_SECURE_CTRL_REG				0x000c
+#define SEC_AXI_CACHE_CFG_REG				0x0010
+#define SEC_AXI_QOS_CFG_REG				0x0014
+#define SEC_IPV4_MASK_TABLE_REG				0x0020
+#define SEC_IPV6_MASK_TABLE_X_REG(x)	(0x0024 + (x) * 4)
+#define SEC_FSM_MAX_CNT_REG				0x0064
+
+#define SEC_CTRL2_REG					0x0068
+#define   SEC_CTRL2_DATA_AXI_RD_OTSD_CFG_M		GENMASK(3, 0)
+#define   SEC_CTRL2_DATA_AXI_RD_OTSD_CFG_S		0
+#define   SEC_CTRL2_DATA_AXI_WR_OTSD_CFG_M		GENMASK(6, 4)
+#define   SEC_CTRL2_DATA_AXI_WR_OTSD_CFG_S		4
+#define   SEC_CTRL2_CLK_GATE_EN				BIT(7)
+#define   SEC_CTRL2_ENDIAN_BD				BIT(8)
+#define   SEC_CTRL2_ENDIAN_BD_TYPE			BIT(9)
+
+#define SEC_CNT_PRECISION_CFG_REG			0x006c
+#define SEC_DEBUG_BD_CFG_REG				0x0070
+#define   SEC_DEBUG_BD_CFG_WB_NORMAL			BIT(0)
+#define   SEC_DEBUG_BD_CFG_WB_EN			BIT(1)
+
+#define SEC_Q_SIGHT_SEL					0x0074
+#define SEC_Q_SIGHT_HIS_CLR				0x0078
+#define SEC_Q_VMID_CFG_REG(q)		(0x0100 + (q) * 4)
+#define SEC_Q_WEIGHT_CFG_REG(q)		(0x200 + (q) * 4)
+#define SEC_STAT_CLR_REG				0x0a00
+#define SEC_SAA_IDLE_CNT_CLR_REG			0x0a04
+#define SEC_QM_CPL_Q_IDBUF_DFX_CFG_REG			0x0b00
+#define SEC_QM_CPL_Q_IDBUF_DFX_RESULT_REG		0x0b04
+#define SEC_QM_BD_DFX_CFG_REG				0x0b08
+#define SEC_QM_BD_DFX_RESULT_REG			0x0b0c
+#define SEC_QM_BDID_DFX_RESULT_REG			0x0b10
+#define SEC_QM_BD_DFIFO_STATUS_REG			0x0b14
+#define SEC_QM_BD_DFX_CFG2_REG				0x0b1c
+#define SEC_QM_BD_DFX_RESULT2_REG			0x0b20
+#define SEC_QM_BD_IDFIFO_STATUS_REG			0x0b18
+#define SEC_QM_BD_DFIFO_STATUS2_REG			0x0b28
+#define SEC_QM_BD_IDFIFO_STATUS2_REG			0x0b2c
+
+#define SEC_HASH_IPV4_MASK				0xfff00000
+#define SEC_MAX_SAA_NUM					0xa
+#define SEC_SAA_ADDR_SIZE				0x1000
+
+#define SEC_Q_INIT_REG					0x0
+#define   SEC_Q_INIT_WO_STAT_CLEAR			0x2
+#define   SEC_Q_INIT_AND_STAT_CLEAR			0x3
+
+#define SEC_Q_CFG_REG					0x8
+#define   SEC_Q_CFG_REORDER				BIT(0)
+
+#define SEC_Q_PROC_NUM_CFG_REG				0x10
+#define SEC_QUEUE_ENB_REG				0x18
+
+#define SEC_Q_DEPTH_CFG_REG				0x50
+#define   SEC_Q_DEPTH_CFG_DEPTH_M			GENMASK(11, 0)
+#define   SEC_Q_DEPTH_CFG_DEPTH_S			0
+
+#define SEC_Q_BASE_HADDR_REG				0x54
+#define SEC_Q_BASE_LADDR_REG				0x58
+#define SEC_Q_WR_PTR_REG				0x5c
+#define SEC_Q_OUTORDER_BASE_HADDR_REG			0x60
+#define SEC_Q_OUTORDER_BASE_LADDR_REG			0x64
+#define SEC_Q_OUTORDER_RD_PTR_REG			0x68
+#define SEC_Q_OT_TH_REG					0x6c
+
+#define SEC_Q_ARUSER_CFG_REG				0x70
+#define   SEC_Q_ARUSER_CFG_FA				BIT(0)
+#define   SEC_Q_ARUSER_CFG_FNA				BIT(1)
+#define   SEC_Q_ARUSER_CFG_RINVLD			BIT(2)
+#define   SEC_Q_ARUSER_CFG_PKG				BIT(3)
+
+#define SEC_Q_AWUSER_CFG_REG				0x74
+#define   SEC_Q_AWUSER_CFG_FA				BIT(0)
+#define   SEC_Q_AWUSER_CFG_FNA				BIT(1)
+#define   SEC_Q_AWUSER_CFG_PKG				BIT(2)
+
+#define SEC_Q_ERR_BASE_HADDR_REG			0x7c
+#define SEC_Q_ERR_BASE_LADDR_REG			0x80
+#define SEC_Q_CFG_VF_NUM_REG				0x84
+#define SEC_Q_SOFT_PROC_PTR_REG				0x88
+#define SEC_Q_FAIL_INT_MSK_REG				0x300
+#define SEC_Q_FLOW_INT_MKS_REG				0x304
+#define SEC_Q_FAIL_RINT_REG				0x400
+#define SEC_Q_FLOW_RINT_REG				0x404
+#define SEC_Q_FAIL_INT_STATUS_REG			0x500
+#define SEC_Q_FLOW_INT_STATUS_REG			0x504
+#define SEC_Q_STATUS_REG				0x600
+#define SEC_Q_RD_PTR_REG				0x604
+#define SEC_Q_PRO_PTR_REG				0x608
+#define SEC_Q_OUTORDER_WR_PTR_REG			0x60c
+#define SEC_Q_OT_CNT_STATUS_REG				0x610
+#define SEC_Q_INORDER_BD_NUM_ST_REG			0x650
+#define SEC_Q_INORDER_GET_FLAG_ST_REG			0x654
+#define SEC_Q_INORDER_ADD_FLAG_ST_REG			0x658
+#define SEC_Q_INORDER_TASK_INT_NUM_LEFT_ST_REG		0x65c
+#define SEC_Q_RD_DONE_PTR_REG				0x660
+#define SEC_Q_CPL_Q_BD_NUM_ST_REG			0x700
+#define SEC_Q_CPL_Q_PTR_ST_REG				0x704
+#define SEC_Q_CPL_Q_H_ADDR_ST_REG			0x708
+#define SEC_Q_CPL_Q_L_ADDR_ST_REG			0x70c
+#define SEC_Q_CPL_TASK_INT_NUM_LEFT_ST_REG		0x710
+#define SEC_Q_WRR_ID_CHECK_REG				0x714
+#define SEC_Q_CPLQ_FULL_CHECK_REG			0x718
+#define SEC_Q_SUCCESS_BD_CNT_REG			0x800
+#define SEC_Q_FAIL_BD_CNT_REG				0x804
+#define SEC_Q_GET_BD_CNT_REG				0x808
+#define SEC_Q_IVLD_CNT_REG				0x80c
+#define SEC_Q_BD_PROC_GET_CNT_REG			0x810
+#define SEC_Q_BD_PROC_DONE_CNT_REG			0x814
+#define SEC_Q_LAT_CLR_REG				0x850
+#define SEC_Q_PKT_LAT_MAX_REG				0x854
+#define SEC_Q_PKT_LAT_AVG_REG				0x858
+#define SEC_Q_PKT_LAT_MIN_REG				0x85c
+#define SEC_Q_ID_CLR_CFG_REG				0x900
+#define SEC_Q_1ST_BD_ERR_ID_REG				0x904
+#define SEC_Q_1ST_AUTH_FAIL_ID_REG			0x908
+#define SEC_Q_1ST_RD_ERR_ID_REG				0x90c
+#define SEC_Q_1ST_ECC2_ERR_ID_REG			0x910
+#define SEC_Q_1ST_IVLD_ID_REG				0x914
+#define SEC_Q_1ST_BD_WR_ERR_ID_REG			0x918
+#define SEC_Q_1ST_ERR_BD_WR_ERR_ID_REG			0x91c
+#define SEC_Q_1ST_BD_MAC_WR_ERR_ID_REG			0x920
+
+struct sec_debug_bd_info {
+#define SEC_DEBUG_BD_INFO_SOFT_ERR_CHECK_M	GENMASK(22, 0)
+	u32 soft_err_check;
+#define SEC_DEBUG_BD_INFO_HARD_ERR_CHECK_M	GENMASK(9, 0)
+	u32 hard_err_check;
+	u32 icv_mac1st_word;
+#define SEC_DEBUG_BD_INFO_GET_ID_M		GENMASK(19, 0)
+	u32 sec_get_id;
+	/* W4---W15 */
+	u32 reserv_left[12];
+};
+
+struct sec_out_bd_info	{
+#define SEC_OUT_BD_INFO_Q_ID_M			GENMASK(11, 0)
+#define SEC_OUT_BD_INFO_ECC_2BIT_ERR		BIT(14)
+	u16 data;
+};
+
+#define SEC_MAX_DEVICES				8
+static struct sec_dev_info *sec_devices[SEC_MAX_DEVICES];
+static DEFINE_MUTEX(sec_id_lock);
+
+static int sec_queue_map_io(struct sec_queue *queue)
+{
+	struct device *dev = queue->dev_info->dev;
+	struct resource *res;
+
+	res = platform_get_resource(to_platform_device(dev),
+				    IORESOURCE_MEM,
+				    2 + queue->queue_id);
+	if (!res) {
+		dev_err(dev, "Failed to get queue %d memory resource\n",
+			queue->queue_id);
+		return -ENOMEM;
+	}
+	queue->regs = ioremap(res->start, resource_size(res));
+	if (!queue->regs)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void sec_queue_unmap_io(struct sec_queue *queue)
+{
+	 iounmap(queue->regs);
+}
+
+static int sec_queue_ar_pkgattr(struct sec_queue *queue, u32 ar_pkg)
+{
+	void __iomem *addr = queue->regs +  SEC_Q_ARUSER_CFG_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	if (ar_pkg)
+		regval |= SEC_Q_ARUSER_CFG_PKG;
+	else
+		regval &= ~SEC_Q_ARUSER_CFG_PKG;
+	writel_relaxed(regval, addr);
+
+	return 0;
+}
+
+static int sec_queue_aw_pkgattr(struct sec_queue *queue, u32 aw_pkg)
+{
+	void __iomem *addr = queue->regs + SEC_Q_AWUSER_CFG_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	regval |= SEC_Q_AWUSER_CFG_PKG;
+	writel_relaxed(regval, addr);
+
+	return 0;
+}
+
+static int sec_clk_en(struct sec_dev_info *info)
+{
+	void __iomem *base = info->regs[SEC_COMMON];
+	u32 i = 0;
+
+	writel_relaxed(0x7, base + SEC_ALGSUB_CLK_EN_REG);
+	do {
+		usleep_range(1000, 10000);
+		if ((readl_relaxed(base + SEC_ALGSUB_CLK_ST_REG) & 0x7) == 0x7)
+			return 0;
+		i++;
+	} while (i < 10);
+	dev_err(info->dev, "sec clock enable fail!\n");
+
+	return -EIO;
+}
+
+static int sec_clk_dis(struct sec_dev_info *info)
+{
+	void __iomem *base = info->regs[SEC_COMMON];
+	u32 i = 0;
+
+	writel_relaxed(0x7, base + SEC_ALGSUB_CLK_DIS_REG);
+	do {
+		usleep_range(1000, 10000);
+		if ((readl_relaxed(base + SEC_ALGSUB_CLK_ST_REG) & 0x7) == 0)
+			return 0;
+		i++;
+	} while (i < 10);
+	dev_err(info->dev, "sec clock disable fail!\n");
+
+	return -EIO;
+}
+
+static int sec_reset_whole_module(struct sec_dev_info *info)
+{
+	void __iomem *base = info->regs[SEC_COMMON];
+	bool is_reset, b_is_reset;
+	u32 i = 0;
+
+	writel_relaxed(1, base + SEC_ALGSUB_RST_REQ_REG);
+	writel_relaxed(1, base + SEC_ALGSUB_BUILD_RST_REQ_REG);
+	while (1) {
+		usleep_range(1000, 10000);
+		is_reset = readl_relaxed(base + SEC_ALGSUB_RST_ST_REG) &
+			SEC_ALGSUB_RST_ST_IS_RST;
+		b_is_reset = readl_relaxed(base + SEC_ALGSUB_BUILD_RST_ST_REG) &
+			SEC_ALGSUB_BUILD_RST_ST_IS_RST;
+		if (is_reset && b_is_reset)
+			break;
+		i++;
+		if (i > 10) {
+			dev_err(info->dev, "Reset req failed\n");
+			return -EIO;
+		}
+	}
+
+	i = 0;
+	writel_relaxed(1, base + SEC_ALGSUB_RST_DREQ_REG);
+	writel_relaxed(1, base + SEC_ALGSUB_BUILD_RST_DREQ_REG);
+	while (1) {
+		usleep_range(1000, 10000);
+		is_reset = readl_relaxed(base + SEC_ALGSUB_RST_ST_REG) &
+			SEC_ALGSUB_RST_ST_IS_RST;
+		b_is_reset = readl_relaxed(base + SEC_ALGSUB_BUILD_RST_ST_REG) &
+			SEC_ALGSUB_BUILD_RST_ST_IS_RST;
+		if (!is_reset && !b_is_reset)
+			break;
+
+		i++;
+		if (i > 10) {
+			dev_err(info->dev, "Reset dreq failed\n");
+			return -EIO;
+		}
+	}
+
+	return 0;
+}
+
+static void sec_bd_endian_little(struct sec_dev_info *info)
+{
+	void __iomem *addr = info->regs[SEC_SAA] + SEC_CTRL2_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	regval &= ~(SEC_CTRL2_ENDIAN_BD | SEC_CTRL2_ENDIAN_BD_TYPE);
+	writel_relaxed(regval, addr);
+}
+
+/*
+ * sec_cache_config - configure optimum cache placement
+ */
+static void sec_cache_config(struct sec_dev_info *info)
+{
+	struct iommu_domain *domain;
+	void __iomem *addr = info->regs[SEC_SAA] + SEC_CTRL_REG;
+
+	domain = iommu_get_domain_for_dev(info->dev);
+
+	/* Check that translation is occurring */
+	if (domain && (domain->type & __IOMMU_DOMAIN_PAGING))
+		writel_relaxed(0x44cf9e, addr);
+	else
+		writel_relaxed(0x4cfd9, addr);
+}
+
+static void sec_data_axiwr_otsd_cfg(struct sec_dev_info *info, u32 cfg)
+{
+	void __iomem *addr = info->regs[SEC_SAA] + SEC_CTRL2_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	regval &= ~SEC_CTRL2_DATA_AXI_WR_OTSD_CFG_M;
+	regval |= (cfg << SEC_CTRL2_DATA_AXI_WR_OTSD_CFG_S) &
+		SEC_CTRL2_DATA_AXI_WR_OTSD_CFG_M;
+	writel_relaxed(regval, addr);
+}
+
+static void sec_data_axird_otsd_cfg(struct sec_dev_info *info, u32 cfg)
+{
+	void __iomem *addr = info->regs[SEC_SAA] + SEC_CTRL2_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	regval &= ~SEC_CTRL2_DATA_AXI_RD_OTSD_CFG_M;
+	regval |= (cfg << SEC_CTRL2_DATA_AXI_RD_OTSD_CFG_S) &
+		SEC_CTRL2_DATA_AXI_RD_OTSD_CFG_M;
+	writel_relaxed(regval, addr);
+}
+
+static void sec_clk_gate_en(struct sec_dev_info *info, bool clkgate)
+{
+	void __iomem *addr = info->regs[SEC_SAA] + SEC_CTRL2_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	if (clkgate)
+		regval |= SEC_CTRL2_CLK_GATE_EN;
+	else
+		regval &= ~SEC_CTRL2_CLK_GATE_EN;
+	writel_relaxed(regval, addr);
+}
+
+static void sec_comm_cnt_cfg(struct sec_dev_info *info, bool clr_ce)
+{
+	void __iomem *addr = info->regs[SEC_SAA] + SEC_COMMON_CNT_CLR_CE_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	if (clr_ce)
+		regval |= SEC_COMMON_CNT_CLR_CE_CLEAR;
+	else
+		regval &= ~SEC_COMMON_CNT_CLR_CE_CLEAR;
+	writel_relaxed(regval, addr);
+}
+
+static void sec_commsnap_en(struct sec_dev_info *info, bool snap_en)
+{
+	void __iomem *addr = info->regs[SEC_SAA] + SEC_COMMON_CNT_CLR_CE_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	if (snap_en)
+		regval |= SEC_COMMON_CNT_CLR_CE_SNAP_EN;
+	else
+		regval &= ~SEC_COMMON_CNT_CLR_CE_SNAP_EN;
+	writel_relaxed(regval, addr);
+}
+
+static void sec_ipv6_hashmask(struct sec_dev_info *info, u32 hash_mask[])
+{
+	void __iomem *base = info->regs[SEC_SAA];
+	int i;
+
+	for (i = 0; i < 10; i++)
+		writel_relaxed(hash_mask[0],
+			       base + SEC_IPV6_MASK_TABLE_X_REG(i));
+}
+
+static int sec_ipv4_hashmask(struct sec_dev_info *info, u32 hash_mask)
+{
+	if (hash_mask & SEC_HASH_IPV4_MASK) {
+		dev_err(info->dev, "Sec Ipv4 Hash Mask Input Error!\n ");
+		return -EINVAL;
+	}
+
+	writel_relaxed(hash_mask,
+		       info->regs[SEC_SAA] + SEC_IPV4_MASK_TABLE_REG);
+
+	return 0;
+}
+
+static void sec_set_dbg_bd_cfg(struct sec_dev_info *info, u32 cfg)
+{
+	void __iomem *addr = info->regs[SEC_SAA] + SEC_DEBUG_BD_CFG_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	/* Always disable write back of normal bd */
+	regval &= ~SEC_DEBUG_BD_CFG_WB_NORMAL;
+
+	if (cfg)
+		regval &= ~SEC_DEBUG_BD_CFG_WB_EN;
+	else
+		regval |= SEC_DEBUG_BD_CFG_WB_EN;
+
+	writel_relaxed(regval, addr);
+}
+
+static void sec_saa_getqm_en(struct sec_dev_info *info, u32 saa_indx, u32 en)
+{
+	void __iomem *addr = info->regs[SEC_SAA] + SEC_SAA_BASE +
+		SEC_SAA_CTRL_REG(saa_indx);
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	if (en)
+		regval |= SEC_SAA_CTRL_GET_QM_EN;
+	else
+		regval &= ~SEC_SAA_CTRL_GET_QM_EN;
+	writel_relaxed(regval, addr);
+}
+
+static void sec_saa_int_mask(struct sec_dev_info *info, u32 saa_indx,
+			     u32 saa_int_mask)
+{
+	writel_relaxed(saa_int_mask,
+		       info->regs[SEC_SAA] + SEC_SAA_BASE + SEC_ST_INTMSK1_REG +
+		       saa_indx * SEC_SAA_ADDR_SIZE);
+}
+
+static void sec_streamid(struct sec_dev_info *info, int i)
+{
+	#define SEC_SID 0x600
+	#define SEC_VMID 0
+
+	writel_relaxed((SEC_VMID | ((SEC_SID & 0xffff) << 8)),
+		       info->regs[SEC_SAA] + SEC_Q_VMID_CFG_REG(i));
+}
+
+static void sec_queue_ar_alloc(struct sec_queue *queue, u32 alloc)
+{
+	void __iomem *addr = queue->regs + SEC_Q_ARUSER_CFG_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	if (alloc == SEC_QUEUE_AR_FROCE_ALLOC) {
+		regval |= SEC_Q_ARUSER_CFG_FA;
+		regval &= ~SEC_Q_ARUSER_CFG_FNA;
+	} else {
+		regval &= ~SEC_Q_ARUSER_CFG_FA;
+		regval |= SEC_Q_ARUSER_CFG_FNA;
+	}
+
+	writel_relaxed(regval, addr);
+}
+
+static void sec_queue_aw_alloc(struct sec_queue *queue, u32 alloc)
+{
+	void __iomem *addr = queue->regs + SEC_Q_AWUSER_CFG_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	if (alloc == SEC_QUEUE_AW_FROCE_ALLOC) {
+		regval |= SEC_Q_AWUSER_CFG_FA;
+		regval &= ~SEC_Q_AWUSER_CFG_FNA;
+	} else {
+		regval &= ~SEC_Q_AWUSER_CFG_FA;
+		regval |= SEC_Q_AWUSER_CFG_FNA;
+	}
+
+	writel_relaxed(regval, addr);
+}
+
+static void sec_queue_reorder(struct sec_queue *queue, bool reorder)
+{
+	void __iomem *base = queue->regs;
+	u32 regval;
+
+	regval = readl_relaxed(base + SEC_Q_CFG_REG);
+	if (reorder)
+		regval |= SEC_Q_CFG_REORDER;
+	else
+		regval &= ~SEC_Q_CFG_REORDER;
+	writel_relaxed(regval, base + SEC_Q_CFG_REG);
+}
+
+static void sec_queue_depth(struct sec_queue *queue, u32 depth)
+{
+	void __iomem *addr = queue->regs + SEC_Q_DEPTH_CFG_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	regval &= ~SEC_Q_DEPTH_CFG_DEPTH_M;
+	regval |= (depth << SEC_Q_DEPTH_CFG_DEPTH_S) & SEC_Q_DEPTH_CFG_DEPTH_M;
+
+	writel_relaxed(regval, addr);
+}
+
+static void sec_queue_cmdbase_addr(struct sec_queue *queue, u64 addr)
+{
+	writel_relaxed(upper_32_bits(addr), queue->regs + SEC_Q_BASE_HADDR_REG);
+	writel_relaxed(lower_32_bits(addr), queue->regs + SEC_Q_BASE_LADDR_REG);
+}
+
+static void sec_queue_outorder_addr(struct sec_queue *queue, u64 addr)
+{
+	writel_relaxed(upper_32_bits(addr),
+		       queue->regs + SEC_Q_OUTORDER_BASE_HADDR_REG);
+	writel_relaxed(lower_32_bits(addr),
+		       queue->regs + SEC_Q_OUTORDER_BASE_LADDR_REG);
+}
+
+static void sec_queue_errbase_addr(struct sec_queue *queue, u64 addr)
+{
+	writel_relaxed(upper_32_bits(addr),
+		       queue->regs + SEC_Q_ERR_BASE_HADDR_REG);
+	writel_relaxed(lower_32_bits(addr),
+		       queue->regs + SEC_Q_ERR_BASE_LADDR_REG);
+}
+
+static void sec_queue_irq_disable(struct sec_queue *queue)
+{
+	writel_relaxed((u32)~0, queue->regs + SEC_Q_FLOW_INT_MKS_REG);
+}
+
+static void sec_queue_irq_enable(struct sec_queue *queue)
+{
+	writel_relaxed(0, queue->regs + SEC_Q_FLOW_INT_MKS_REG);
+}
+
+static void sec_queue_abn_irq_disable(struct sec_queue *queue)
+{
+	writel_relaxed((u32)~0, queue->regs + SEC_Q_FAIL_INT_MSK_REG);
+}
+
+static void sec_queue_stop(struct sec_queue *queue)
+{
+	disable_irq(queue->task_irq);
+	sec_queue_irq_disable(queue);
+	writel_relaxed(0x0, queue->regs + SEC_QUEUE_ENB_REG);
+}
+
+static void sec_queue_start(struct sec_queue *queue)
+{
+	sec_queue_irq_enable(queue);
+	enable_irq(queue->task_irq);
+	queue->expected = 0;
+	writel_relaxed(SEC_Q_INIT_AND_STAT_CLEAR, queue->regs + SEC_Q_INIT_REG);
+	writel_relaxed(0x1, queue->regs + SEC_QUEUE_ENB_REG);
+}
+
+static struct sec_queue *sec_alloc_queue(struct sec_dev_info *info)
+{
+	int i;
+
+	mutex_lock(&info->dev_lock);
+
+	/* Get the first idle queue in SEC device */
+	for (i = 0; i < SEC_Q_NUM; i++)
+		if (!info->queues[i].in_use) {
+			info->queues[i].in_use = true;
+			info->queues_in_use++;
+			mutex_unlock(&info->dev_lock);
+
+			return &info->queues[i];
+		}
+	mutex_unlock(&info->dev_lock);
+
+	return ERR_PTR(-ENODEV);
+}
+
+static int sec_queue_free(struct sec_queue *queue)
+{
+	struct sec_dev_info *info = queue->dev_info;
+
+	if (queue->queue_id >= SEC_Q_NUM) {
+		dev_err(info->dev, "No queue %d\n", queue->queue_id);
+		return -ENODEV;
+	}
+
+	if (!queue->in_use) {
+		dev_err(info->dev, "Queue %d is idle\n", queue->queue_id);
+		return -ENODEV;
+	}
+
+	mutex_lock(&info->dev_lock);
+	queue->in_use = false;
+	info->queues_in_use--;
+	mutex_unlock(&info->dev_lock);
+
+	return 0;
+}
+
+static irqreturn_t sec_isr_handle_th(int irq, void *q)
+{
+	sec_queue_irq_disable(q);
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t sec_isr_handle(int irq, void *q)
+{
+	struct sec_queue *queue = q;
+	struct sec_queue_ring_cmd *msg_ring = &queue->ring_cmd;
+	struct sec_queue_ring_cq *cq_ring = &queue->ring_cq;
+	struct sec_out_bd_info *outorder_msg;
+	struct sec_bd_info *msg;
+	u32 ooo_read, ooo_write;
+	void __iomem *base = queue->regs;
+	int q_id;
+
+	ooo_read = readl(base + SEC_Q_OUTORDER_RD_PTR_REG);
+	ooo_write = readl(base + SEC_Q_OUTORDER_WR_PTR_REG);
+	outorder_msg = cq_ring->vaddr + ooo_read;
+	q_id = outorder_msg->data & SEC_OUT_BD_INFO_Q_ID_M;
+	msg = msg_ring->vaddr + q_id;
+
+	while ((ooo_write != ooo_read) && msg->w0 & SEC_BD_W0_DONE) {
+		/*
+		 * Must be before callback otherwise blocks adding other chained
+		 * elements
+		 */
+		set_bit(q_id, queue->unprocessed);
+		if (q_id == queue->expected)
+			while (test_bit(queue->expected, queue->unprocessed)) {
+				clear_bit(queue->expected, queue->unprocessed);
+				msg = msg_ring->vaddr + queue->expected;
+				msg->w0 &= ~SEC_BD_W0_DONE;
+				msg_ring->callback(msg,
+						queue->shadow[queue->expected]);
+				queue->shadow[queue->expected] = NULL;
+				queue->expected = (queue->expected + 1) %
+					SEC_QUEUE_LEN;
+				atomic_dec(&msg_ring->used);
+			}
+
+		ooo_read = (ooo_read + 1) % SEC_QUEUE_LEN;
+		writel(ooo_read, base + SEC_Q_OUTORDER_RD_PTR_REG);
+		ooo_write = readl(base + SEC_Q_OUTORDER_WR_PTR_REG);
+		outorder_msg = cq_ring->vaddr + ooo_read;
+		q_id = outorder_msg->data & SEC_OUT_BD_INFO_Q_ID_M;
+		msg = msg_ring->vaddr + q_id;
+	}
+
+	sec_queue_irq_enable(queue);
+
+	return IRQ_HANDLED;
+}
+
+static int sec_queue_irq_init(struct sec_queue *queue)
+{
+	struct sec_dev_info *info = queue->dev_info;
+	int irq = queue->task_irq;
+	int ret;
+
+	ret = request_threaded_irq(irq, sec_isr_handle_th, sec_isr_handle,
+				   IRQF_TRIGGER_RISING, queue->name, queue);
+	if (ret) {
+		dev_err(info->dev, "request irq(%d) failed %d\n", irq, ret);
+		return ret;
+	}
+	disable_irq(irq);
+
+	return 0;
+}
+
+static int sec_queue_irq_uninit(struct sec_queue *queue)
+{
+	free_irq(queue->task_irq, queue);
+
+	return 0;
+}
+
+static struct sec_dev_info *sec_device_get(void)
+{
+	struct sec_dev_info *sec_dev = NULL;
+	struct sec_dev_info *this_sec_dev;
+	int least_busy_n = SEC_Q_NUM + 1;
+	int i;
+
+	/* Find which one is least busy and use that first */
+	for (i = 0; i < SEC_MAX_DEVICES; i++) {
+		this_sec_dev = sec_devices[i];
+		if (this_sec_dev &&
+		    this_sec_dev->queues_in_use < least_busy_n) {
+			least_busy_n = this_sec_dev->queues_in_use;
+			sec_dev = this_sec_dev;
+		}
+	}
+
+	return sec_dev;
+}
+
+static struct sec_queue *sec_queue_alloc_start(struct sec_dev_info *info)
+{
+	struct sec_queue *queue;
+
+	queue = sec_alloc_queue(info);
+	if (IS_ERR(queue)) {
+		dev_err(info->dev, "alloc sec queue failed! %ld\n",
+			PTR_ERR(queue));
+		return queue;
+	}
+
+	sec_queue_start(queue);
+
+	return queue;
+}
+
+/**
+ * sec_queue_alloc_start_safe - get a hw queue from appropriate instance
+ *
+ * This function does extremely simplistic load balancing. It does not take into
+ * account NUMA locality of the accelerator, or which cpu has requested the
+ * queue.  Future work may focus on optimizing this in order to improve full
+ * machine throughput.
+ */
+struct sec_queue *sec_queue_alloc_start_safe(void)
+{
+	struct sec_dev_info *info;
+	struct sec_queue *queue = ERR_PTR(-ENODEV);
+
+	mutex_lock(&sec_id_lock);
+	info = sec_device_get();
+	if (!info)
+		goto unlock;
+
+	queue = sec_queue_alloc_start(info);
+
+unlock:
+	mutex_unlock(&sec_id_lock);
+
+	return queue;
+}
+
+/**
+ * sec_queue_stop_release() - free up a hw queue for reuse
+ * @queue: The queue we are done with.
+ *
+ * This will stop the current queue, terminanting any transactions
+ * that are inflight an return it to the pool of available hw queuess
+ */
+int sec_queue_stop_release(struct sec_queue *queue)
+{
+	struct device *dev = queue->dev_info->dev;
+	int ret;
+
+	sec_queue_stop(queue);
+
+	ret = sec_queue_free(queue);
+	if (ret)
+		dev_err(dev, "Releasing queue failed %d\n", ret);
+
+	return ret;
+}
+
+/**
+ * sec_queue_empty() - Is this hardware queue currently empty.
+ *
+ * We need to know if we have an empty queue for some of the chaining modes
+ * as if it is not empty we may need to hold the message in a software queue
+ * until the hw queue is drained.
+ */
+bool sec_queue_empty(struct sec_queue *queue)
+{
+	struct sec_queue_ring_cmd *msg_ring = &queue->ring_cmd;
+
+	return !atomic_read(&msg_ring->used);
+}
+
+/**
+ * sec_queue_send() - queue up a single operation in the hw queue
+ * @queue: The queue in which to put the message
+ * @msg: The message
+ * @ctx: Context to be put in the shadow array and passed back to cb on result.
+ *
+ * This function will return -EAGAIN if the queue is currently full.
+ */
+int sec_queue_send(struct sec_queue *queue, struct sec_bd_info *msg, void *ctx)
+{
+	struct sec_queue_ring_cmd *msg_ring = &queue->ring_cmd;
+	void __iomem *base = queue->regs;
+	u32 write, read;
+
+	mutex_lock(&msg_ring->lock);
+	read = readl(base + SEC_Q_RD_PTR_REG);
+	write = readl(base + SEC_Q_WR_PTR_REG);
+	if (write == read && atomic_read(&msg_ring->used) == SEC_QUEUE_LEN) {
+		mutex_unlock(&msg_ring->lock);
+		return -EAGAIN;
+	}
+	memcpy(msg_ring->vaddr + write, msg, sizeof(*msg));
+	queue->shadow[write] = ctx;
+	write = (write + 1) % SEC_QUEUE_LEN;
+
+	/* Ensure content updated before queue advance */
+	wmb();
+	writel(write, base + SEC_Q_WR_PTR_REG);
+
+	atomic_inc(&msg_ring->used);
+	mutex_unlock(&msg_ring->lock);
+
+	return 0;
+}
+
+bool sec_queue_can_enqueue(struct sec_queue *queue, int num)
+{
+	struct sec_queue_ring_cmd *msg_ring = &queue->ring_cmd;
+
+	return SEC_QUEUE_LEN - atomic_read(&msg_ring->used) >= num;
+}
+
+static void sec_queue_hw_init(struct sec_queue *queue)
+{
+	sec_queue_ar_alloc(queue, SEC_QUEUE_AR_FROCE_NOALLOC);
+	sec_queue_aw_alloc(queue, SEC_QUEUE_AR_FROCE_NOALLOC);
+	sec_queue_ar_pkgattr(queue, 1);
+	sec_queue_aw_pkgattr(queue, 1);
+
+	/* Enable out of order queue */
+	sec_queue_reorder(queue, true);
+
+	/* Interrupt after a single complete element */
+	writel_relaxed(1, queue->regs + SEC_Q_PROC_NUM_CFG_REG);
+
+	sec_queue_depth(queue, SEC_QUEUE_LEN - 1);
+
+	sec_queue_cmdbase_addr(queue, queue->ring_cmd.paddr);
+
+	sec_queue_outorder_addr(queue, queue->ring_cq.paddr);
+
+	sec_queue_errbase_addr(queue, queue->ring_db.paddr);
+
+	writel_relaxed(0x100, queue->regs + SEC_Q_OT_TH_REG);
+
+	sec_queue_abn_irq_disable(queue);
+	sec_queue_irq_disable(queue);
+	writel_relaxed(SEC_Q_INIT_AND_STAT_CLEAR, queue->regs + SEC_Q_INIT_REG);
+}
+
+static int sec_hw_init(struct sec_dev_info *info)
+{
+	struct iommu_domain *domain;
+	u32 sec_ipv4_mask = 0;
+	u32 sec_ipv6_mask[10] = {};
+	u32 i, ret;
+
+	domain = iommu_get_domain_for_dev(info->dev);
+
+	/*
+	 * Enable all available processing unit clocks.
+	 * Only the first cluster is usable with translations.
+	 */
+	if (domain && (domain->type & __IOMMU_DOMAIN_PAGING))
+		info->num_saas = 5;
+
+	else
+		info->num_saas = 10;
+
+	writel_relaxed(GENMASK(info->num_saas - 1, 0),
+		       info->regs[SEC_SAA] + SEC_CLK_EN_REG);
+
+	/* 32 bit little endian */
+	sec_bd_endian_little(info);
+
+	sec_cache_config(info);
+
+	/* Data axi port write and read outstanding config as per datasheet */
+	sec_data_axiwr_otsd_cfg(info, 0x7);
+	sec_data_axird_otsd_cfg(info, 0x7);
+
+	/* Enable clock gating */
+	sec_clk_gate_en(info, true);
+
+	/* Set CNT_CYC register not read clear */
+	sec_comm_cnt_cfg(info, false);
+
+	/* Enable CNT_CYC */
+	sec_commsnap_en(info, false);
+
+	writel_relaxed((u32)~0, info->regs[SEC_SAA] + SEC_FSM_MAX_CNT_REG);
+
+	ret = sec_ipv4_hashmask(info, sec_ipv4_mask);
+	if (ret) {
+		dev_err(info->dev, "Failed to set ipv4 hashmask %d\n", ret);
+		return -EIO;
+	}
+
+	sec_ipv6_hashmask(info, sec_ipv6_mask);
+
+	/*  do not use debug bd */
+	sec_set_dbg_bd_cfg(info, 0);
+
+	if (domain && (domain->type & __IOMMU_DOMAIN_PAGING)) {
+		for (i = 0; i < SEC_Q_NUM; i++) {
+			sec_streamid(info, i);
+			/* Same QoS for all queues */
+			writel_relaxed(0x3f,
+				       info->regs[SEC_SAA] +
+				       SEC_Q_WEIGHT_CFG_REG(i));
+		}
+	}
+
+	for (i = 0; i < info->num_saas; i++) {
+		sec_saa_getqm_en(info, i, 1);
+		sec_saa_int_mask(info, i, 0);
+	}
+
+	return 0;
+}
+
+static void sec_hw_exit(struct sec_dev_info *info)
+{
+	int i;
+
+	for (i = 0; i < SEC_MAX_SAA_NUM; i++) {
+		sec_saa_int_mask(info, i, (u32)~0);
+		sec_saa_getqm_en(info, i, 0);
+	}
+}
+
+static void sec_queue_base_init(struct sec_dev_info *info,
+				struct sec_queue *queue, int queue_id)
+{
+	queue->dev_info = info;
+	queue->queue_id = queue_id;
+	snprintf(queue->name, sizeof(queue->name),
+		 "%s_%d", dev_name(info->dev), queue->queue_id);
+}
+
+static int sec_map_io(struct sec_dev_info *info, struct platform_device *pdev)
+{
+	struct resource *res;
+	int i;
+
+	for (i = 0; i < SEC_NUM_ADDR_REGIONS; i++) {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, i);
+
+		if (!res) {
+			dev_err(info->dev, "Memory resource %d not found\n", i);
+			return -EINVAL;
+		}
+
+		info->regs[i] = devm_ioremap(info->dev, res->start,
+					     resource_size(res));
+		if (!info->regs[i]) {
+			dev_err(info->dev,
+				"Memory resource %d could not be remapped\n",
+				i);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int sec_base_init(struct sec_dev_info *info,
+			 struct platform_device *pdev)
+{
+	int ret;
+
+	ret = sec_map_io(info, pdev);
+	if (ret)
+		return ret;
+
+	ret = sec_clk_en(info);
+	if (ret)
+		return ret;
+
+	ret = sec_reset_whole_module(info);
+	if (ret)
+		goto sec_clk_disable;
+
+	ret = sec_hw_init(info);
+	if (ret)
+		goto sec_clk_disable;
+
+	return 0;
+
+sec_clk_disable:
+	sec_clk_dis(info);
+
+	return ret;
+}
+
+static void sec_base_exit(struct sec_dev_info *info)
+{
+	sec_hw_exit(info);
+	sec_clk_dis(info);
+}
+
+#define SEC_Q_CMD_SIZE \
+	round_up(SEC_QUEUE_LEN * sizeof(struct sec_bd_info), PAGE_SIZE)
+#define SEC_Q_CQ_SIZE \
+	round_up(SEC_QUEUE_LEN * sizeof(struct sec_out_bd_info), PAGE_SIZE)
+#define SEC_Q_DB_SIZE \
+	round_up(SEC_QUEUE_LEN * sizeof(struct sec_debug_bd_info), PAGE_SIZE)
+
+static int sec_queue_res_cfg(struct sec_queue *queue)
+{
+	struct device *dev = queue->dev_info->dev;
+	struct sec_queue_ring_cmd *ring_cmd = &queue->ring_cmd;
+	struct sec_queue_ring_cq *ring_cq = &queue->ring_cq;
+	struct sec_queue_ring_db *ring_db = &queue->ring_db;
+	int ret;
+
+	ring_cmd->vaddr = dma_zalloc_coherent(dev, SEC_Q_CMD_SIZE,
+					      &ring_cmd->paddr,
+					      GFP_KERNEL);
+	if (!ring_cmd->vaddr)
+		return -ENOMEM;
+
+	atomic_set(&ring_cmd->used, 0);
+	mutex_init(&ring_cmd->lock);
+	ring_cmd->callback = sec_alg_callback;
+
+	ring_cq->vaddr = dma_zalloc_coherent(dev, SEC_Q_CQ_SIZE,
+					     &ring_cq->paddr,
+					     GFP_KERNEL);
+	if (!ring_cq->vaddr) {
+		ret = -ENOMEM;
+		goto err_free_ring_cmd;
+	}
+
+	ring_db->vaddr = dma_zalloc_coherent(dev, SEC_Q_DB_SIZE,
+					     &ring_db->paddr,
+					     GFP_KERNEL);
+	if (!ring_db->vaddr) {
+		ret = -ENOMEM;
+		goto err_free_ring_cq;
+	}
+	queue->task_irq = platform_get_irq(to_platform_device(dev),
+					   queue->queue_id * 2 + 1);
+	if (queue->task_irq <= 0) {
+		ret = -EINVAL;
+		goto err_free_ring_db;
+	}
+
+	return 0;
+
+err_free_ring_db:
+	dma_free_coherent(dev, SEC_Q_DB_SIZE, queue->ring_db.vaddr,
+			  queue->ring_db.paddr);
+err_free_ring_cq:
+	dma_free_coherent(dev, SEC_Q_CQ_SIZE, queue->ring_cq.vaddr,
+			  queue->ring_cq.paddr);
+err_free_ring_cmd:
+	dma_free_coherent(dev, SEC_Q_CMD_SIZE, queue->ring_cmd.vaddr,
+			  queue->ring_cmd.paddr);
+
+	return ret;
+}
+
+static void sec_queue_free_ring_pages(struct sec_queue *queue)
+{
+	struct device *dev = queue->dev_info->dev;
+
+	dma_free_coherent(dev, SEC_Q_DB_SIZE, queue->ring_db.vaddr,
+			  queue->ring_db.paddr);
+	dma_free_coherent(dev, SEC_Q_CQ_SIZE, queue->ring_cq.vaddr,
+			  queue->ring_cq.paddr);
+	dma_free_coherent(dev, SEC_Q_CMD_SIZE, queue->ring_cmd.vaddr,
+			  queue->ring_cmd.paddr);
+}
+
+static int sec_queue_config(struct sec_dev_info *info, struct sec_queue *queue,
+			    int queue_id)
+{
+	int ret;
+
+	sec_queue_base_init(info, queue, queue_id);
+
+	ret = sec_queue_res_cfg(queue);
+	if (ret)
+		return ret;
+
+	ret = sec_queue_map_io(queue);
+	if (ret) {
+		dev_err(info->dev, "Queue map failed %d\n", ret);
+		sec_queue_free_ring_pages(queue);
+		return ret;
+	}
+
+	sec_queue_hw_init(queue);
+
+	return 0;
+}
+
+static void sec_queue_unconfig(struct sec_dev_info *info,
+			       struct sec_queue *queue)
+{
+	sec_queue_unmap_io(queue);
+	sec_queue_free_ring_pages(queue);
+}
+
+static int sec_id_alloc(struct sec_dev_info *info)
+{
+	int ret = 0;
+	int i;
+
+	mutex_lock(&sec_id_lock);
+
+	for (i = 0; i < SEC_MAX_DEVICES; i++)
+		if (!sec_devices[i])
+			break;
+	if (i == SEC_MAX_DEVICES) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+	info->sec_id = i;
+	sec_devices[info->sec_id] = info;
+
+unlock:
+	mutex_unlock(&sec_id_lock);
+
+	return ret;
+}
+
+static void sec_id_free(struct sec_dev_info *info)
+{
+	mutex_lock(&sec_id_lock);
+	sec_devices[info->sec_id] = NULL;
+	mutex_unlock(&sec_id_lock);
+}
+
+static int sec_probe(struct platform_device *pdev)
+{
+	struct sec_dev_info *info;
+	struct device *dev = &pdev->dev;
+	int i, j;
+	int ret;
+
+	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
+	if (ret) {
+		dev_err(dev, "Failed to set 64 bit dma mask %d", ret);
+		return -ENODEV;
+	}
+
+	info = devm_kzalloc(dev, (sizeof(*info)), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->dev = dev;
+	mutex_init(&info->dev_lock);
+
+	info->hw_sgl_pool = dmam_pool_create("sgl", dev,
+					     sizeof(struct sec_hw_sgl), 64, 0);
+	if (!info->hw_sgl_pool) {
+		dev_err(dev, "Failed to create sec sgl dma pool\n");
+		return -ENOMEM;
+	}
+
+	ret = sec_base_init(info, pdev);
+	if (ret) {
+		dev_err(dev, "Base initialization fail! %d\n", ret);
+		return ret;
+	}
+
+	for (i = 0; i < SEC_Q_NUM; i++) {
+		ret = sec_queue_config(info, &info->queues[i], i);
+		if (ret)
+			goto queues_unconfig;
+
+		ret = sec_queue_irq_init(&info->queues[i]);
+		if (ret) {
+			sec_queue_unconfig(info, &info->queues[i]);
+			goto queues_unconfig;
+		}
+	}
+
+	ret = sec_algs_register();
+	if (ret) {
+		dev_err(dev, "Failed to register algorithms with crypto %d\n",
+			ret);
+		goto queues_unconfig;
+	}
+
+	platform_set_drvdata(pdev, info);
+
+	ret = sec_id_alloc(info);
+	if (ret)
+		goto algs_unregister;
+
+	return 0;
+
+algs_unregister:
+	sec_algs_unregister();
+queues_unconfig:
+	for (j = i - 1; j >= 0; j--) {
+		sec_queue_irq_uninit(&info->queues[j]);
+		sec_queue_unconfig(info, &info->queues[j]);
+	}
+	sec_base_exit(info);
+
+	return ret;
+}
+
+static int sec_remove(struct platform_device *pdev)
+{
+	struct sec_dev_info *info = platform_get_drvdata(pdev);
+	int i;
+
+	/* Unexpose as soon as possible, reuse during remove is fine */
+	sec_id_free(info);
+
+	sec_algs_unregister();
+
+	for (i = 0; i < SEC_Q_NUM; i++) {
+		sec_queue_irq_uninit(&info->queues[i]);
+		sec_queue_unconfig(info, &info->queues[i]);
+	}
+
+	sec_base_exit(info);
+
+	return 0;
+}
+
+static const __maybe_unused struct of_device_id sec_match[] = {
+	{ .compatible = "hisilicon,hip06-sec" },
+	{ .compatible = "hisilicon,hip07-sec" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, sec_match);
+
+static const __maybe_unused struct acpi_device_id sec_acpi_match[] = {
+	{ "HISI02C1", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, sec_acpi_match);
+
+static struct platform_driver sec_driver = {
+	.probe = sec_probe,
+	.remove = sec_remove,
+	.driver = {
+		.name = "hisi_sec_platform_driver",
+		.of_match_table = sec_match,
+		.acpi_match_table = ACPI_PTR(sec_acpi_match),
+	},
+};
+module_platform_driver(sec_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Hisilicon Security Accelerators");
+MODULE_AUTHOR("Zaibo Xu <xuzaibo@huawei.com");
+MODULE_AUTHOR("Jonathan Cameron <jonathan.cameron@huawei.com>");
diff --git a/drivers/crypto/hisilicon/sec/sec_drv.h b/drivers/crypto/hisilicon/sec/sec_drv.h
new file mode 100644
index 000000000000..2d2f186674ba
--- /dev/null
+++ b/drivers/crypto/hisilicon/sec/sec_drv.h
@@ -0,0 +1,428 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2016-2017 Hisilicon Limited. */
+
+#ifndef _SEC_DRV_H_
+#define _SEC_DRV_H_
+
+#include <crypto/algapi.h>
+#include <linux/kfifo.h>
+
+#define SEC_MAX_SGE_NUM			64
+#define SEC_HW_RING_NUM			3
+
+#define SEC_CMD_RING			0
+#define SEC_OUTORDER_RING		1
+#define SEC_DBG_RING			2
+
+/* A reasonable length to balance memory use against flexibility */
+#define SEC_QUEUE_LEN			512
+
+#define SEC_MAX_SGE_NUM   64
+
+struct sec_bd_info {
+#define SEC_BD_W0_T_LEN_M			GENMASK(4, 0)
+#define SEC_BD_W0_T_LEN_S			0
+
+#define SEC_BD_W0_C_WIDTH_M			GENMASK(6, 5)
+#define SEC_BD_W0_C_WIDTH_S			5
+#define   SEC_C_WIDTH_AES_128BIT		0
+#define   SEC_C_WIDTH_AES_8BIT		1
+#define   SEC_C_WIDTH_AES_1BIT		2
+#define   SEC_C_WIDTH_DES_64BIT		0
+#define   SEC_C_WIDTH_DES_8BIT		1
+#define   SEC_C_WIDTH_DES_1BIT		2
+
+#define SEC_BD_W0_C_MODE_M			GENMASK(9, 7)
+#define SEC_BD_W0_C_MODE_S			7
+#define   SEC_C_MODE_ECB			0
+#define   SEC_C_MODE_CBC			1
+#define   SEC_C_MODE_CTR			4
+#define   SEC_C_MODE_CCM			5
+#define   SEC_C_MODE_GCM			6
+#define   SEC_C_MODE_XTS			7
+
+#define SEC_BD_W0_SEQ				BIT(10)
+#define SEC_BD_W0_DE				BIT(11)
+#define SEC_BD_W0_DAT_SKIP_M			GENMASK(13, 12)
+#define SEC_BD_W0_DAT_SKIP_S			12
+#define SEC_BD_W0_C_GRAN_SIZE_19_16_M		GENMASK(17, 14)
+#define SEC_BD_W0_C_GRAN_SIZE_19_16_S		14
+
+#define SEC_BD_W0_CIPHER_M			GENMASK(19, 18)
+#define SEC_BD_W0_CIPHER_S			18
+#define   SEC_CIPHER_NULL			0
+#define   SEC_CIPHER_ENCRYPT			1
+#define   SEC_CIPHER_DECRYPT			2
+
+#define SEC_BD_W0_AUTH_M			GENMASK(21, 20)
+#define SEC_BD_W0_AUTH_S			20
+#define   SEC_AUTH_NULL				0
+#define   SEC_AUTH_MAC				1
+#define   SEC_AUTH_VERIF			2
+
+#define SEC_BD_W0_AI_GEN			BIT(22)
+#define SEC_BD_W0_CI_GEN			BIT(23)
+#define SEC_BD_W0_NO_HPAD			BIT(24)
+#define SEC_BD_W0_HM_M				GENMASK(26, 25)
+#define SEC_BD_W0_HM_S				25
+#define SEC_BD_W0_ICV_OR_SKEY_EN_M		GENMASK(28, 27)
+#define SEC_BD_W0_ICV_OR_SKEY_EN_S		27
+
+/* Multi purpose field - gran size bits for send, flag for recv */
+#define SEC_BD_W0_FLAG_M			GENMASK(30, 29)
+#define SEC_BD_W0_C_GRAN_SIZE_21_20_M		GENMASK(30, 29)
+#define SEC_BD_W0_FLAG_S			29
+#define SEC_BD_W0_C_GRAN_SIZE_21_20_S		29
+
+#define SEC_BD_W0_DONE				BIT(31)
+	u32 w0;
+
+#define SEC_BD_W1_AUTH_GRAN_SIZE_M		GENMASK(21, 0)
+#define SEC_BD_W1_AUTH_GRAN_SIZE_S		0
+#define SEC_BD_W1_M_KEY_EN			BIT(22)
+#define SEC_BD_W1_BD_INVALID			BIT(23)
+#define SEC_BD_W1_ADDR_TYPE			BIT(24)
+
+#define SEC_BD_W1_A_ALG_M			GENMASK(28, 25)
+#define SEC_BD_W1_A_ALG_S			25
+#define   SEC_A_ALG_SHA1			0
+#define   SEC_A_ALG_SHA256			1
+#define   SEC_A_ALG_MD5				2
+#define   SEC_A_ALG_SHA224			3
+#define   SEC_A_ALG_HMAC_SHA1			8
+#define   SEC_A_ALG_HMAC_SHA224			10
+#define   SEC_A_ALG_HMAC_SHA256			11
+#define   SEC_A_ALG_HMAC_MD5			12
+#define   SEC_A_ALG_AES_XCBC			13
+#define   SEC_A_ALG_AES_CMAC			14
+
+#define SEC_BD_W1_C_ALG_M			GENMASK(31, 29)
+#define SEC_BD_W1_C_ALG_S			29
+#define   SEC_C_ALG_DES				0
+#define   SEC_C_ALG_3DES			1
+#define   SEC_C_ALG_AES				2
+
+	u32 w1;
+
+#define SEC_BD_W2_C_GRAN_SIZE_15_0_M		GENMASK(15, 0)
+#define SEC_BD_W2_C_GRAN_SIZE_15_0_S		0
+#define SEC_BD_W2_GRAN_NUM_M			GENMASK(31, 16)
+#define SEC_BD_W2_GRAN_NUM_S			16
+	u32 w2;
+
+#define SEC_BD_W3_AUTH_LEN_OFFSET_M		GENMASK(9, 0)
+#define SEC_BD_W3_AUTH_LEN_OFFSET_S		0
+#define SEC_BD_W3_CIPHER_LEN_OFFSET_M		GENMASK(19, 10)
+#define SEC_BD_W3_CIPHER_LEN_OFFSET_S		10
+#define SEC_BD_W3_MAC_LEN_M			GENMASK(24, 20)
+#define SEC_BD_W3_MAC_LEN_S			20
+#define SEC_BD_W3_A_KEY_LEN_M			GENMASK(29, 25)
+#define SEC_BD_W3_A_KEY_LEN_S			25
+#define SEC_BD_W3_C_KEY_LEN_M			GENMASK(31, 30)
+#define SEC_BD_W3_C_KEY_LEN_S			30
+#define   SEC_KEY_LEN_AES_128			0
+#define   SEC_KEY_LEN_AES_192			1
+#define   SEC_KEY_LEN_AES_256			2
+#define   SEC_KEY_LEN_DES			1
+#define   SEC_KEY_LEN_3DES_3_KEY		1
+#define   SEC_KEY_LEN_3DES_2_KEY		3
+	u32 w3;
+
+	/* W4,5 */
+	union {
+		u32 authkey_addr_lo;
+		u32 authiv_addr_lo;
+	};
+	union {
+		u32 authkey_addr_hi;
+		u32 authiv_addr_hi;
+	};
+
+	/* W6,7 */
+	u32 cipher_key_addr_lo;
+	u32 cipher_key_addr_hi;
+
+	/* W8,9 */
+	u32 cipher_iv_addr_lo;
+	u32 cipher_iv_addr_hi;
+
+	/* W10,11 */
+	u32 data_addr_lo;
+	u32 data_addr_hi;
+
+	/* W12,13 */
+	u32 mac_addr_lo;
+	u32 mac_addr_hi;
+
+	/* W14,15 */
+	u32 cipher_destin_addr_lo;
+	u32 cipher_destin_addr_hi;
+};
+
+enum sec_mem_region {
+	SEC_COMMON = 0,
+	SEC_SAA,
+	SEC_NUM_ADDR_REGIONS
+};
+
+#define SEC_NAME_SIZE				64
+#define SEC_Q_NUM				16
+
+
+/**
+ * struct sec_queue_ring_cmd - store information about a SEC HW cmd ring
+ * @used: Local counter used to cheaply establish if the ring is empty.
+ * @lock: Protect against simultaneous adjusting of the read and write pointers.
+ * @vaddr: Virtual address for the ram pages used for the ring.
+ * @paddr: Physical address of the dma mapped region of ram used for the ring.
+ * @callback: Callback function called on a ring element completing.
+ */
+struct sec_queue_ring_cmd {
+	atomic_t used;
+	struct mutex lock;
+	struct sec_bd_info *vaddr;
+	dma_addr_t paddr;
+	void (*callback)(struct sec_bd_info *resp, void *ctx);
+};
+
+struct sec_debug_bd_info;
+struct sec_queue_ring_db {
+	struct sec_debug_bd_info *vaddr;
+	dma_addr_t paddr;
+};
+
+struct sec_out_bd_info;
+struct sec_queue_ring_cq {
+	struct sec_out_bd_info *vaddr;
+	dma_addr_t paddr;
+};
+
+struct sec_dev_info;
+
+enum sec_cipher_alg {
+	SEC_C_DES_ECB_64,
+	SEC_C_DES_CBC_64,
+
+	SEC_C_3DES_ECB_192_3KEY,
+	SEC_C_3DES_ECB_192_2KEY,
+
+	SEC_C_3DES_CBC_192_3KEY,
+	SEC_C_3DES_CBC_192_2KEY,
+
+	SEC_C_AES_ECB_128,
+	SEC_C_AES_ECB_192,
+	SEC_C_AES_ECB_256,
+
+	SEC_C_AES_CBC_128,
+	SEC_C_AES_CBC_192,
+	SEC_C_AES_CBC_256,
+
+	SEC_C_AES_CTR_128,
+	SEC_C_AES_CTR_192,
+	SEC_C_AES_CTR_256,
+
+	SEC_C_AES_XTS_128,
+	SEC_C_AES_XTS_256,
+
+	SEC_C_NULL,
+};
+
+/**
+ * struct sec_alg_tfm_ctx - hardware specific tranformation context
+ * @cipher_alg: Cipher algorithm enabled include encryption mode.
+ * @key: Key storage if required.
+ * @pkey: DMA address for the key storage.
+ * @req_template: Request template to save time on setup.
+ * @queue: The hardware queue associated with this tfm context.
+ * @lock: Protect key and pkey to ensure they are consistent
+ * @auth_buf: Current context buffer for auth operations.
+ * @backlog: The backlog queue used for cases where our buffers aren't
+ * large enough.
+ */
+struct sec_alg_tfm_ctx {
+	enum sec_cipher_alg cipher_alg;
+	u8 *key;
+	dma_addr_t pkey;
+	struct sec_bd_info req_template;
+	struct sec_queue *queue;
+	struct mutex lock;
+	u8 *auth_buf;
+	struct list_head backlog;
+};
+
+/**
+ * struct sec_request - data associate with a single crypto request
+ * @elements: List of subparts of this request (hardware size restriction)
+ * @num_elements: The number of subparts (used as an optimization)
+ * @lock: Protect elements of this structure against concurrent change.
+ * @tfm_ctx: hardware specific context.
+ * @len_in: length of in sgl from upper layers
+ * @len_out: length of out sgl from upper layers
+ * @dma_iv: initialization vector - phsyical address
+ * @err: store used to track errors across subelements of this request.
+ * @req_base: pointer to base element of associate crypto context.
+ * This is needed to allow shared handling skcipher, ahash etc.
+ * @cb: completion callback.
+ * @backlog_head: list head to allow backlog maintenance.
+ *
+ * The hardware is limited in the maximum size of data that it can
+ * process from a single BD.  Typically this is fairly large (32MB)
+ * but still requires the complexity of splitting the incoming
+ * skreq up into a number of elements complete with appropriate
+ * iv chaining.
+ */
+struct sec_request {
+	struct list_head elements;
+	int num_elements;
+	struct mutex lock;
+	struct sec_alg_tfm_ctx *tfm_ctx;
+	int len_in;
+	int len_out;
+	dma_addr_t dma_iv;
+	int err;
+	struct crypto_async_request *req_base;
+	void (*cb)(struct sec_bd_info *resp, struct crypto_async_request *req);
+	struct list_head backlog_head;
+};
+
+/**
+ * struct sec_request_el - A subpart of a request.
+ * @head: allow us to attach this to the list in the sec_request
+ * @req: hardware block descriptor corresponding to this request subpart
+ * @in: hardware sgl for input - virtual address
+ * @dma_in: hardware sgl for input - physical address
+ * @sgl_in: scatterlist for this request subpart
+ * @out: hardware sgl for output - virtual address
+ * @dma_out: hardware sgl for output - physical address
+ * @sgl_out: scatterlist for this request subpart
+ * @sec_req: The request which this subpart forms a part of
+ * @el_length: Number of bytes in this subpart. Needed to locate
+ * last ivsize chunk for iv chaining.
+ */
+struct sec_request_el {
+	struct list_head head;
+	struct sec_bd_info req;
+	struct sec_hw_sgl *in;
+	dma_addr_t dma_in;
+	struct scatterlist *sgl_in;
+	struct sec_hw_sgl *out;
+	dma_addr_t dma_out;
+	struct scatterlist *sgl_out;
+	struct sec_request *sec_req;
+	size_t el_length;
+};
+
+/**
+ * struct sec_queue - All the information about a HW queue
+ * @dev_info: The parent SEC device to which this queue belongs.
+ * @task_irq: Completion interrupt for the queue.
+ * @name: Human readable queue description also used as irq name.
+ * @ring: The several HW rings associated with one queue.
+ * @regs: The iomapped device registers
+ * @queue_id: Index of the queue used for naming and resource selection.
+ * @in_use: Flag to say if the queue is in use.
+ * @expected: The next expected element to finish assuming we were in order.
+ * @uprocessed: A bitmap to track which OoO elements are done but not handled.
+ * @softqueue: A software queue used when chaining requirements prevent direct
+ *   use of the hardware queues.
+ * @havesoftqueue: A flag to say we have a queues - as we may need one for the
+ *   current mode.
+ * @queuelock: Protect the soft queue from concurrent changes to avoid some
+ *   potential loss of data races.
+ * @shadow: Pointers back to the shadow copy of the hardware ring element
+ *   need because we can't store any context reference in the bd element.
+ */
+struct sec_queue {
+	struct sec_dev_info *dev_info;
+	int task_irq;
+	char name[SEC_NAME_SIZE];
+	struct sec_queue_ring_cmd ring_cmd;
+	struct sec_queue_ring_cq ring_cq;
+	struct sec_queue_ring_db ring_db;
+	void __iomem *regs;
+	u32 queue_id;
+	bool in_use;
+	int expected;
+
+	DECLARE_BITMAP(unprocessed, SEC_QUEUE_LEN);
+	DECLARE_KFIFO_PTR(softqueue, typeof(struct sec_request_el *));
+	bool havesoftqueue;
+	struct mutex queuelock;
+	void *shadow[SEC_QUEUE_LEN];
+};
+
+/**
+ * struct sec_hw_sge: Track each of the 64 element SEC HW SGL entries
+ * @buf: The IOV dma address for this entry.
+ * @len: Length of this IOV.
+ * @pad: Reserved space.
+ */
+struct sec_hw_sge {
+	dma_addr_t buf;
+	unsigned int len;
+	unsigned int pad;
+};
+
+/**
+ * struct sec_hw_sgl: One hardware SGL entry.
+ * @next_sgl: The next entry if we need to chain dma address. Null if last.
+ * @entry_sum_in_chain: The full count of SGEs - only matters for first SGL.
+ * @entry_sum_in_sgl: The number of SGEs in this SGL element.
+ * @flag: Unused in skciphers.
+ * @serial_num: Unsued in skciphers.
+ * @cpuid: Currently unused.
+ * @data_bytes_in_sgl: Count of bytes from all SGEs in this SGL.
+ * @next: Virtual address used to stash the next sgl - useful in completion.
+ * @reserved: A reserved field not currently used.
+ * @sge_entries: The (up to) 64 Scatter Gather Entries, representing IOVs.
+ * @node: Currently unused.
+ */
+struct sec_hw_sgl {
+	dma_addr_t next_sgl;
+	u16 entry_sum_in_chain;
+	u16 entry_sum_in_sgl;
+	u32 flag;
+	u64 serial_num;
+	u32 cpuid;
+	u32 data_bytes_in_sgl;
+	struct sec_hw_sgl *next;
+	u64 reserved;
+	struct sec_hw_sge  sge_entries[SEC_MAX_SGE_NUM];
+	u8 node[16];
+};
+
+struct dma_pool;
+
+/**
+ * struct sec_dev_info: The full SEC unit comprising queues and processors.
+ * @sec_id: Index used to track which SEC this is when more than one is present.
+ * @num_saas: The number of backed processors enabled.
+ * @regs: iomapped register regions shared by whole SEC unit.
+ * @dev_lock: Protects concurrent queue allocation / freeing for the SEC.
+ * @queues: The 16 queues that this SEC instance provides.
+ * @dev: Device pointer.
+ * @hw_sgl_pool: DMA pool used to mimise mapping for the scatter gather lists.
+ */
+struct sec_dev_info {
+	int sec_id;
+	int num_saas;
+	void __iomem *regs[SEC_NUM_ADDR_REGIONS];
+	struct mutex dev_lock;
+	int queues_in_use;
+	struct sec_queue queues[SEC_Q_NUM];
+	struct device *dev;
+	struct dma_pool *hw_sgl_pool;
+};
+
+int sec_queue_send(struct sec_queue *queue, struct sec_bd_info *msg, void *ctx);
+bool sec_queue_can_enqueue(struct sec_queue *queue, int num);
+int sec_queue_stop_release(struct sec_queue *queue);
+struct sec_queue *sec_queue_alloc_start_safe(void);
+bool sec_queue_empty(struct sec_queue *queue);
+
+/* Algorithm specific elements from sec_algs.c */
+void sec_alg_callback(struct sec_bd_info *resp, void *ctx);
+int sec_algs_register(void);
+void sec_algs_unregister(void);
+
+#endif /* _SEC_DRV_H_ */
diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 4e86f864a952..7e71043457a6 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2017 Marvell
  *
  * Antoine Tenart <antoine.tenart@free-electrons.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 
 #include <linux/clk.h>
@@ -33,7 +30,19 @@ MODULE_PARM_DESC(max_rings, "Maximum number of rings to use.");
 static void eip197_trc_cache_init(struct safexcel_crypto_priv *priv)
 {
 	u32 val, htable_offset;
-	int i;
+	int i, cs_rc_max, cs_ht_wc, cs_trc_rec_wc, cs_trc_lg_rec_wc;
+
+	if (priv->version == EIP197B) {
+		cs_rc_max = EIP197B_CS_RC_MAX;
+		cs_ht_wc = EIP197B_CS_HT_WC;
+		cs_trc_rec_wc = EIP197B_CS_TRC_REC_WC;
+		cs_trc_lg_rec_wc = EIP197B_CS_TRC_LG_REC_WC;
+	} else {
+		cs_rc_max = EIP197D_CS_RC_MAX;
+		cs_ht_wc = EIP197D_CS_HT_WC;
+		cs_trc_rec_wc = EIP197D_CS_TRC_REC_WC;
+		cs_trc_lg_rec_wc = EIP197D_CS_TRC_LG_REC_WC;
+	}
 
 	/* Enable the record cache memory access */
 	val = readl(priv->base + EIP197_CS_RAM_CTRL);
@@ -54,7 +63,7 @@ static void eip197_trc_cache_init(struct safexcel_crypto_priv *priv)
 	writel(val, priv->base + EIP197_TRC_PARAMS);
 
 	/* Clear all records */
-	for (i = 0; i < EIP197_CS_RC_MAX; i++) {
+	for (i = 0; i < cs_rc_max; i++) {
 		u32 val, offset = EIP197_CLASSIFICATION_RAMS + i * EIP197_CS_RC_SIZE;
 
 		writel(EIP197_CS_RC_NEXT(EIP197_RC_NULL) |
@@ -64,14 +73,14 @@ static void eip197_trc_cache_init(struct safexcel_crypto_priv *priv)
 		val = EIP197_CS_RC_NEXT(i+1) | EIP197_CS_RC_PREV(i-1);
 		if (i == 0)
 			val |= EIP197_CS_RC_PREV(EIP197_RC_NULL);
-		else if (i == EIP197_CS_RC_MAX - 1)
+		else if (i == cs_rc_max - 1)
 			val |= EIP197_CS_RC_NEXT(EIP197_RC_NULL);
 		writel(val, priv->base + offset + sizeof(u32));
 	}
 
 	/* Clear the hash table entries */
-	htable_offset = EIP197_CS_RC_MAX * EIP197_CS_RC_SIZE;
-	for (i = 0; i < 64; i++)
+	htable_offset = cs_rc_max * EIP197_CS_RC_SIZE;
+	for (i = 0; i < cs_ht_wc; i++)
 		writel(GENMASK(29, 0),
 		       priv->base + EIP197_CLASSIFICATION_RAMS + htable_offset + i * sizeof(u32));
 
@@ -82,23 +91,23 @@ static void eip197_trc_cache_init(struct safexcel_crypto_priv *priv)
 
 	/* Write head and tail pointers of the record free chain */
 	val = EIP197_TRC_FREECHAIN_HEAD_PTR(0) |
-	      EIP197_TRC_FREECHAIN_TAIL_PTR(EIP197_CS_RC_MAX - 1);
+	      EIP197_TRC_FREECHAIN_TAIL_PTR(cs_rc_max - 1);
 	writel(val, priv->base + EIP197_TRC_FREECHAIN);
 
 	/* Configure the record cache #1 */
-	val = EIP197_TRC_PARAMS2_RC_SZ_SMALL(EIP197_CS_TRC_REC_WC) |
-	      EIP197_TRC_PARAMS2_HTABLE_PTR(EIP197_CS_RC_MAX);
+	val = EIP197_TRC_PARAMS2_RC_SZ_SMALL(cs_trc_rec_wc) |
+	      EIP197_TRC_PARAMS2_HTABLE_PTR(cs_rc_max);
 	writel(val, priv->base + EIP197_TRC_PARAMS2);
 
 	/* Configure the record cache #2 */
-	val = EIP197_TRC_PARAMS_RC_SZ_LARGE(EIP197_CS_TRC_LG_REC_WC) |
+	val = EIP197_TRC_PARAMS_RC_SZ_LARGE(cs_trc_lg_rec_wc) |
 	      EIP197_TRC_PARAMS_BLK_TIMER_SPEED(1) |
 	      EIP197_TRC_PARAMS_HTABLE_SZ(2);
 	writel(val, priv->base + EIP197_TRC_PARAMS);
 }
 
 static void eip197_write_firmware(struct safexcel_crypto_priv *priv,
-				  const struct firmware *fw, u32 ctrl,
+				  const struct firmware *fw, int pe, u32 ctrl,
 				  u32 prog_en)
 {
 	const u32 *data = (const u32 *)fw->data;
@@ -112,7 +121,7 @@ static void eip197_write_firmware(struct safexcel_crypto_priv *priv,
 	       EIP197_PE(priv) + ctrl);
 
 	/* Enable access to the program memory */
-	writel(prog_en, EIP197_PE(priv) + EIP197_PE_ICE_RAM_CTRL);
+	writel(prog_en, EIP197_PE(priv) + EIP197_PE_ICE_RAM_CTRL(pe));
 
 	/* Write the firmware */
 	for (i = 0; i < fw->size / sizeof(u32); i++)
@@ -120,7 +129,7 @@ static void eip197_write_firmware(struct safexcel_crypto_priv *priv,
 		       priv->base + EIP197_CLASSIFICATION_RAMS + i * sizeof(u32));
 
 	/* Disable access to the program memory */
-	writel(0, EIP197_PE(priv) + EIP197_PE_ICE_RAM_CTRL);
+	writel(0, EIP197_PE(priv) + EIP197_PE_ICE_RAM_CTRL(pe));
 
 	/* Release engine from reset */
 	val = readl(EIP197_PE(priv) + ctrl);
@@ -132,35 +141,62 @@ static int eip197_load_firmwares(struct safexcel_crypto_priv *priv)
 {
 	const char *fw_name[] = {"ifpp.bin", "ipue.bin"};
 	const struct firmware *fw[FW_NB];
-	int i, j, ret = 0;
+	char fw_path[31], *dir = NULL;
+	int i, j, ret = 0, pe;
 	u32 val;
 
+	switch (priv->version) {
+	case EIP197B:
+		dir = "eip197b";
+		break;
+	case EIP197D:
+		dir = "eip197d";
+		break;
+	default:
+		/* No firmware is required */
+		return 0;
+	}
+
 	for (i = 0; i < FW_NB; i++) {
-		ret = request_firmware(&fw[i], fw_name[i], priv->dev);
+		snprintf(fw_path, 31, "inside-secure/%s/%s", dir, fw_name[i]);
+		ret = request_firmware(&fw[i], fw_path, priv->dev);
 		if (ret) {
-			dev_err(priv->dev,
-				"Failed to request firmware %s (%d)\n",
-				fw_name[i], ret);
-			goto release_fw;
-		}
-	 }
-
-	/* Clear the scratchpad memory */
-	val = readl(EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_CTRL);
-	val |= EIP197_PE_ICE_SCRATCH_CTRL_CHANGE_TIMER |
-	       EIP197_PE_ICE_SCRATCH_CTRL_TIMER_EN |
-	       EIP197_PE_ICE_SCRATCH_CTRL_SCRATCH_ACCESS |
-	       EIP197_PE_ICE_SCRATCH_CTRL_CHANGE_ACCESS;
-	writel(val, EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_CTRL);
+			if (priv->version != EIP197B)
+				goto release_fw;
 
-	memset_io(EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_RAM, 0,
-		  EIP197_NUM_OF_SCRATCH_BLOCKS * sizeof(u32));
-
-	eip197_write_firmware(priv, fw[FW_IFPP], EIP197_PE_ICE_FPP_CTRL,
-			      EIP197_PE_ICE_RAM_CTRL_FPP_PROG_EN);
+			/* Fallback to the old firmware location for the
+			 * EIP197b.
+			 */
+			ret = request_firmware(&fw[i], fw_name[i], priv->dev);
+			if (ret) {
+				dev_err(priv->dev,
+					"Failed to request firmware %s (%d)\n",
+					fw_name[i], ret);
+				goto release_fw;
+			}
+		}
+	}
 
-	eip197_write_firmware(priv, fw[FW_IPUE], EIP197_PE_ICE_PUE_CTRL,
-			      EIP197_PE_ICE_RAM_CTRL_PUE_PROG_EN);
+	for (pe = 0; pe < priv->config.pes; pe++) {
+		/* Clear the scratchpad memory */
+		val = readl(EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_CTRL(pe));
+		val |= EIP197_PE_ICE_SCRATCH_CTRL_CHANGE_TIMER |
+		       EIP197_PE_ICE_SCRATCH_CTRL_TIMER_EN |
+		       EIP197_PE_ICE_SCRATCH_CTRL_SCRATCH_ACCESS |
+		       EIP197_PE_ICE_SCRATCH_CTRL_CHANGE_ACCESS;
+		writel(val, EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_CTRL(pe));
+
+		memset_io(EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_RAM(pe), 0,
+			  EIP197_NUM_OF_SCRATCH_BLOCKS * sizeof(u32));
+
+		eip197_write_firmware(priv, fw[FW_IFPP], pe,
+				      EIP197_PE_ICE_FPP_CTRL(pe),
+				      EIP197_PE_ICE_RAM_CTRL_FPP_PROG_EN);
+
+		eip197_write_firmware(priv, fw[FW_IPUE], pe,
+				      EIP197_PE_ICE_PUE_CTRL(pe),
+				      EIP197_PE_ICE_RAM_CTRL_PUE_PROG_EN);
+	}
 
 release_fw:
 	for (j = 0; j < i; j++)
@@ -256,7 +292,7 @@ static int safexcel_hw_setup_rdesc_rings(struct safexcel_crypto_priv *priv)
 static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 {
 	u32 version, val;
-	int i, ret;
+	int i, ret, pe;
 
 	/* Determine endianess and configure byte swap */
 	version = readl(EIP197_HIA_AIC(priv) + EIP197_HIA_VERSION);
@@ -267,6 +303,10 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 	else if (((version >> 16) & 0xffff) == EIP197_HIA_VERSION_LE)
 		val |= (EIP197_MST_CTRL_NO_BYTE_SWAP >> 24);
 
+	/* For EIP197 set maximum number of TX commands to 2^5 = 32 */
+	if (priv->version == EIP197B || priv->version == EIP197D)
+		val |= EIP197_MST_CTRL_TX_MAX_CMD(5);
+
 	writel(val, EIP197_HIA_AIC(priv) + EIP197_HIA_MST_CTRL);
 
 	/* Configure wr/rd cache values */
@@ -282,82 +322,94 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 	/* Clear any pending interrupt */
 	writel(GENMASK(31, 0), EIP197_HIA_AIC_G(priv) + EIP197_HIA_AIC_G_ACK);
 
-	/* Data Fetch Engine configuration */
-
-	/* Reset all DFE threads */
-	writel(EIP197_DxE_THR_CTRL_RESET_PE,
-	       EIP197_HIA_DFE_THR(priv) + EIP197_HIA_DFE_THR_CTRL);
-
-	if (priv->version == EIP197) {
-		/* Reset HIA input interface arbiter */
-		writel(EIP197_HIA_RA_PE_CTRL_RESET,
-		       EIP197_HIA_AIC(priv) + EIP197_HIA_RA_PE_CTRL);
-	}
-
-	/* DMA transfer size to use */
-	val = EIP197_HIA_DFE_CFG_DIS_DEBUG;
-	val |= EIP197_HIA_DxE_CFG_MIN_DATA_SIZE(5) | EIP197_HIA_DxE_CFG_MAX_DATA_SIZE(9);
-	val |= EIP197_HIA_DxE_CFG_MIN_CTRL_SIZE(5) | EIP197_HIA_DxE_CFG_MAX_CTRL_SIZE(7);
-	val |= EIP197_HIA_DxE_CFG_DATA_CACHE_CTRL(RD_CACHE_3BITS);
-	val |= EIP197_HIA_DxE_CFG_CTRL_CACHE_CTRL(RD_CACHE_3BITS);
-	writel(val, EIP197_HIA_DFE(priv) + EIP197_HIA_DFE_CFG);
-
-	/* Leave the DFE threads reset state */
-	writel(0, EIP197_HIA_DFE_THR(priv) + EIP197_HIA_DFE_THR_CTRL);
-
-	/* Configure the procesing engine thresholds */
-	writel(EIP197_PE_IN_xBUF_THRES_MIN(5) | EIP197_PE_IN_xBUF_THRES_MAX(9),
-	       EIP197_PE(priv) + EIP197_PE_IN_DBUF_THRES);
-	writel(EIP197_PE_IN_xBUF_THRES_MIN(5) | EIP197_PE_IN_xBUF_THRES_MAX(7),
-	       EIP197_PE(priv) + EIP197_PE_IN_TBUF_THRES);
-
-	if (priv->version == EIP197) {
-		/* enable HIA input interface arbiter and rings */
-		writel(EIP197_HIA_RA_PE_CTRL_EN |
-		       GENMASK(priv->config.rings - 1, 0),
-		       EIP197_HIA_AIC(priv) + EIP197_HIA_RA_PE_CTRL);
-	}
-
-	/* Data Store Engine configuration */
-
-	/* Reset all DSE threads */
-	writel(EIP197_DxE_THR_CTRL_RESET_PE,
-	       EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_CTRL);
-
-	/* Wait for all DSE threads to complete */
-	while ((readl(EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_STAT) &
-		GENMASK(15, 12)) != GENMASK(15, 12))
-		;
-
-	/* DMA transfer size to use */
-	val = EIP197_HIA_DSE_CFG_DIS_DEBUG;
-	val |= EIP197_HIA_DxE_CFG_MIN_DATA_SIZE(7) | EIP197_HIA_DxE_CFG_MAX_DATA_SIZE(8);
-	val |= EIP197_HIA_DxE_CFG_DATA_CACHE_CTRL(WR_CACHE_3BITS);
-	val |= EIP197_HIA_DSE_CFG_ALWAYS_BUFFERABLE;
-	/* FIXME: instability issues can occur for EIP97 but disabling it impact
-	 * performances.
-	 */
-	if (priv->version == EIP197)
-		val |= EIP197_HIA_DSE_CFG_EN_SINGLE_WR;
-	writel(val, EIP197_HIA_DSE(priv) + EIP197_HIA_DSE_CFG);
+	/* Processing Engine configuration */
+	for (pe = 0; pe < priv->config.pes; pe++) {
+		/* Data Fetch Engine configuration */
 
-	/* Leave the DSE threads reset state */
-	writel(0, EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_CTRL);
+		/* Reset all DFE threads */
+		writel(EIP197_DxE_THR_CTRL_RESET_PE,
+		       EIP197_HIA_DFE_THR(priv) + EIP197_HIA_DFE_THR_CTRL(pe));
 
-	/* Configure the procesing engine thresholds */
-	writel(EIP197_PE_OUT_DBUF_THRES_MIN(7) | EIP197_PE_OUT_DBUF_THRES_MAX(8),
-	       EIP197_PE(priv) + EIP197_PE_OUT_DBUF_THRES);
+		if (priv->version == EIP197B || priv->version == EIP197D) {
+			/* Reset HIA input interface arbiter */
+			writel(EIP197_HIA_RA_PE_CTRL_RESET,
+			       EIP197_HIA_AIC(priv) + EIP197_HIA_RA_PE_CTRL(pe));
+		}
 
-	/* Processing Engine configuration */
+		/* DMA transfer size to use */
+		val = EIP197_HIA_DFE_CFG_DIS_DEBUG;
+		val |= EIP197_HIA_DxE_CFG_MIN_DATA_SIZE(6) |
+		       EIP197_HIA_DxE_CFG_MAX_DATA_SIZE(9);
+		val |= EIP197_HIA_DxE_CFG_MIN_CTRL_SIZE(6) |
+		       EIP197_HIA_DxE_CFG_MAX_CTRL_SIZE(7);
+		val |= EIP197_HIA_DxE_CFG_DATA_CACHE_CTRL(RD_CACHE_3BITS);
+		val |= EIP197_HIA_DxE_CFG_CTRL_CACHE_CTRL(RD_CACHE_3BITS);
+		writel(val, EIP197_HIA_DFE(priv) + EIP197_HIA_DFE_CFG(pe));
+
+		/* Leave the DFE threads reset state */
+		writel(0, EIP197_HIA_DFE_THR(priv) + EIP197_HIA_DFE_THR_CTRL(pe));
+
+		/* Configure the processing engine thresholds */
+		writel(EIP197_PE_IN_xBUF_THRES_MIN(6) |
+		       EIP197_PE_IN_xBUF_THRES_MAX(9),
+		       EIP197_PE(priv) + EIP197_PE_IN_DBUF_THRES(pe));
+		writel(EIP197_PE_IN_xBUF_THRES_MIN(6) |
+		       EIP197_PE_IN_xBUF_THRES_MAX(7),
+		       EIP197_PE(priv) + EIP197_PE_IN_TBUF_THRES(pe));
+
+		if (priv->version == EIP197B || priv->version == EIP197D) {
+			/* enable HIA input interface arbiter and rings */
+			writel(EIP197_HIA_RA_PE_CTRL_EN |
+			       GENMASK(priv->config.rings - 1, 0),
+			       EIP197_HIA_AIC(priv) + EIP197_HIA_RA_PE_CTRL(pe));
+		}
 
-	/* H/W capabilities selection */
-	val = EIP197_FUNCTION_RSVD;
-	val |= EIP197_PROTOCOL_ENCRYPT_ONLY | EIP197_PROTOCOL_HASH_ONLY;
-	val |= EIP197_PROTOCOL_ENCRYPT_HASH | EIP197_PROTOCOL_HASH_DECRYPT;
-	val |= EIP197_ALG_AES_ECB | EIP197_ALG_AES_CBC;
-	val |= EIP197_ALG_SHA1 | EIP197_ALG_HMAC_SHA1;
-	val |= EIP197_ALG_SHA2 | EIP197_ALG_HMAC_SHA2;
-	writel(val, EIP197_PE(priv) + EIP197_PE_EIP96_FUNCTION_EN);
+		/* Data Store Engine configuration */
+
+		/* Reset all DSE threads */
+		writel(EIP197_DxE_THR_CTRL_RESET_PE,
+		       EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_CTRL(pe));
+
+		/* Wait for all DSE threads to complete */
+		while ((readl(EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_STAT(pe)) &
+			GENMASK(15, 12)) != GENMASK(15, 12))
+			;
+
+		/* DMA transfer size to use */
+		val = EIP197_HIA_DSE_CFG_DIS_DEBUG;
+		val |= EIP197_HIA_DxE_CFG_MIN_DATA_SIZE(7) |
+		       EIP197_HIA_DxE_CFG_MAX_DATA_SIZE(8);
+		val |= EIP197_HIA_DxE_CFG_DATA_CACHE_CTRL(WR_CACHE_3BITS);
+		val |= EIP197_HIA_DSE_CFG_ALWAYS_BUFFERABLE;
+		/* FIXME: instability issues can occur for EIP97 but disabling it impact
+		 * performances.
+		 */
+		if (priv->version == EIP197B || priv->version == EIP197D)
+			val |= EIP197_HIA_DSE_CFG_EN_SINGLE_WR;
+		writel(val, EIP197_HIA_DSE(priv) + EIP197_HIA_DSE_CFG(pe));
+
+		/* Leave the DSE threads reset state */
+		writel(0, EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_CTRL(pe));
+
+		/* Configure the procesing engine thresholds */
+		writel(EIP197_PE_OUT_DBUF_THRES_MIN(7) |
+		       EIP197_PE_OUT_DBUF_THRES_MAX(8),
+		       EIP197_PE(priv) + EIP197_PE_OUT_DBUF_THRES(pe));
+
+		/* Processing Engine configuration */
+
+		/* H/W capabilities selection */
+		val = EIP197_FUNCTION_RSVD;
+		val |= EIP197_PROTOCOL_ENCRYPT_ONLY | EIP197_PROTOCOL_HASH_ONLY;
+		val |= EIP197_PROTOCOL_ENCRYPT_HASH | EIP197_PROTOCOL_HASH_DECRYPT;
+		val |= EIP197_ALG_DES_ECB | EIP197_ALG_DES_CBC;
+		val |= EIP197_ALG_3DES_ECB | EIP197_ALG_3DES_CBC;
+		val |= EIP197_ALG_AES_ECB | EIP197_ALG_AES_CBC;
+		val |= EIP197_ALG_MD5 | EIP197_ALG_HMAC_MD5;
+		val |= EIP197_ALG_SHA1 | EIP197_ALG_HMAC_SHA1;
+		val |= EIP197_ALG_SHA2 | EIP197_ALG_HMAC_SHA2;
+		writel(val, EIP197_PE(priv) + EIP197_PE_EIP96_FUNCTION_EN(pe));
+	}
 
 	/* Command Descriptor Rings prepare */
 	for (i = 0; i < priv->config.rings; i++) {
@@ -408,18 +460,20 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 		       EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_RING_SIZE);
 	}
 
-	/* Enable command descriptor rings */
-	writel(EIP197_DxE_THR_CTRL_EN | GENMASK(priv->config.rings - 1, 0),
-	       EIP197_HIA_DFE_THR(priv) + EIP197_HIA_DFE_THR_CTRL);
+	for (pe = 0; pe < priv->config.pes; pe++) {
+		/* Enable command descriptor rings */
+		writel(EIP197_DxE_THR_CTRL_EN | GENMASK(priv->config.rings - 1, 0),
+		       EIP197_HIA_DFE_THR(priv) + EIP197_HIA_DFE_THR_CTRL(pe));
 
-	/* Enable result descriptor rings */
-	writel(EIP197_DxE_THR_CTRL_EN | GENMASK(priv->config.rings - 1, 0),
-	       EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_CTRL);
+		/* Enable result descriptor rings */
+		writel(EIP197_DxE_THR_CTRL_EN | GENMASK(priv->config.rings - 1, 0),
+		       EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_CTRL(pe));
+	}
 
 	/* Clear any HIA interrupt */
 	writel(GENMASK(30, 20), EIP197_HIA_AIC_G(priv) + EIP197_HIA_AIC_G_ACK);
 
-	if (priv->version == EIP197) {
+	if (priv->version == EIP197B || priv->version == EIP197D) {
 		eip197_trc_cache_init(priv);
 
 		ret = eip197_load_firmwares(priv);
@@ -452,7 +506,6 @@ void safexcel_dequeue(struct safexcel_crypto_priv *priv, int ring)
 {
 	struct crypto_async_request *req, *backlog;
 	struct safexcel_context *ctx;
-	struct safexcel_request *request;
 	int ret, nreq = 0, cdesc = 0, rdesc = 0, commands, results;
 
 	/* If a request wasn't properly dequeued because of a lack of resources,
@@ -476,16 +529,10 @@ void safexcel_dequeue(struct safexcel_crypto_priv *priv, int ring)
 		}
 
 handle_req:
-		request = kzalloc(sizeof(*request), EIP197_GFP_FLAGS(*req));
-		if (!request)
-			goto request_failed;
-
 		ctx = crypto_tfm_ctx(req->tfm);
-		ret = ctx->send(req, ring, request, &commands, &results);
-		if (ret) {
-			kfree(request);
+		ret = ctx->send(req, ring, &commands, &results);
+		if (ret)
 			goto request_failed;
-		}
 
 		if (backlog)
 			backlog->complete(backlog, -EINPROGRESS);
@@ -494,14 +541,8 @@ handle_req:
 		 * to the engine because the input data was cached, continue to
 		 * dequeue other requests as this is valid and not an error.
 		 */
-		if (!commands && !results) {
-			kfree(request);
+		if (!commands && !results)
 			continue;
-		}
-
-		spin_lock_bh(&priv->ring[ring].egress_lock);
-		list_add_tail(&request->list, &priv->ring[ring].list);
-		spin_unlock_bh(&priv->ring[ring].egress_lock);
 
 		cdesc += commands;
 		rdesc += results;
@@ -519,7 +560,7 @@ finalize:
 	if (!nreq)
 		return;
 
-	spin_lock_bh(&priv->ring[ring].egress_lock);
+	spin_lock_bh(&priv->ring[ring].lock);
 
 	priv->ring[ring].requests += nreq;
 
@@ -528,7 +569,7 @@ finalize:
 		priv->ring[ring].busy = true;
 	}
 
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
+	spin_unlock_bh(&priv->ring[ring].lock);
 
 	/* let the RDR know we have pending descriptors */
 	writel((rdesc * priv->config.rd_offset) << 2,
@@ -560,6 +601,24 @@ inline int safexcel_rdesc_check_errors(struct safexcel_crypto_priv *priv,
 	return -EINVAL;
 }
 
+inline void safexcel_rdr_req_set(struct safexcel_crypto_priv *priv,
+				 int ring,
+				 struct safexcel_result_desc *rdesc,
+				 struct crypto_async_request *req)
+{
+	int i = safexcel_ring_rdr_rdesc_index(priv, ring, rdesc);
+
+	priv->ring[ring].rdr_req[i] = req;
+}
+
+inline struct crypto_async_request *
+safexcel_rdr_req_get(struct safexcel_crypto_priv *priv, int ring)
+{
+	int i = safexcel_ring_first_rdr_index(priv, ring);
+
+	return priv->ring[ring].rdr_req[i];
+}
+
 void safexcel_complete(struct safexcel_crypto_priv *priv, int ring)
 {
 	struct safexcel_command_desc *cdesc;
@@ -588,21 +647,16 @@ void safexcel_inv_complete(struct crypto_async_request *req, int error)
 
 int safexcel_invalidate_cache(struct crypto_async_request *async,
 			      struct safexcel_crypto_priv *priv,
-			      dma_addr_t ctxr_dma, int ring,
-			      struct safexcel_request *request)
+			      dma_addr_t ctxr_dma, int ring)
 {
 	struct safexcel_command_desc *cdesc;
 	struct safexcel_result_desc *rdesc;
 	int ret = 0;
 
-	spin_lock_bh(&priv->ring[ring].egress_lock);
-
 	/* Prepare command descriptor */
 	cdesc = safexcel_add_cdesc(priv, ring, true, true, 0, 0, 0, ctxr_dma);
-	if (IS_ERR(cdesc)) {
-		ret = PTR_ERR(cdesc);
-		goto unlock;
-	}
+	if (IS_ERR(cdesc))
+		return PTR_ERR(cdesc);
 
 	cdesc->control_data.type = EIP197_TYPE_EXTENDED;
 	cdesc->control_data.options = 0;
@@ -617,21 +671,20 @@ int safexcel_invalidate_cache(struct crypto_async_request *async,
 		goto cdesc_rollback;
 	}
 
-	request->req = async;
-	goto unlock;
+	safexcel_rdr_req_set(priv, ring, rdesc, async);
+
+	return ret;
 
 cdesc_rollback:
 	safexcel_ring_rollback_wptr(priv, &priv->ring[ring].cdr);
 
-unlock:
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
 	return ret;
 }
 
 static inline void safexcel_handle_result_descriptor(struct safexcel_crypto_priv *priv,
 						     int ring)
 {
-	struct safexcel_request *sreq;
+	struct crypto_async_request *req;
 	struct safexcel_context *ctx;
 	int ret, i, nreq, ndesc, tot_descs, handled = 0;
 	bool should_complete;
@@ -646,28 +699,22 @@ handle_results:
 		goto requests_left;
 
 	for (i = 0; i < nreq; i++) {
-		spin_lock_bh(&priv->ring[ring].egress_lock);
-		sreq = list_first_entry(&priv->ring[ring].list,
-					struct safexcel_request, list);
-		list_del(&sreq->list);
-		spin_unlock_bh(&priv->ring[ring].egress_lock);
-
-		ctx = crypto_tfm_ctx(sreq->req->tfm);
-		ndesc = ctx->handle_result(priv, ring, sreq->req,
+		req = safexcel_rdr_req_get(priv, ring);
+
+		ctx = crypto_tfm_ctx(req->tfm);
+		ndesc = ctx->handle_result(priv, ring, req,
 					   &should_complete, &ret);
 		if (ndesc < 0) {
-			kfree(sreq);
 			dev_err(priv->dev, "failed to handle result (%d)", ndesc);
 			goto acknowledge;
 		}
 
 		if (should_complete) {
 			local_bh_disable();
-			sreq->req->complete(sreq->req, ret);
+			req->complete(req, ret);
 			local_bh_enable();
 		}
 
-		kfree(sreq);
 		tot_descs += ndesc;
 		handled++;
 	}
@@ -686,7 +733,7 @@ acknowledge:
 		goto handle_results;
 
 requests_left:
-	spin_lock_bh(&priv->ring[ring].egress_lock);
+	spin_lock_bh(&priv->ring[ring].lock);
 
 	priv->ring[ring].requests -= handled;
 	safexcel_try_push_requests(priv, ring);
@@ -694,7 +741,7 @@ requests_left:
 	if (!priv->ring[ring].requests)
 		priv->ring[ring].busy = false;
 
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
+	spin_unlock_bh(&priv->ring[ring].lock);
 }
 
 static void safexcel_dequeue_work(struct work_struct *work)
@@ -785,17 +832,29 @@ static int safexcel_request_ring_irq(struct platform_device *pdev, const char *n
 }
 
 static struct safexcel_alg_template *safexcel_algs[] = {
+	&safexcel_alg_ecb_des,
+	&safexcel_alg_cbc_des,
+	&safexcel_alg_ecb_des3_ede,
+	&safexcel_alg_cbc_des3_ede,
 	&safexcel_alg_ecb_aes,
 	&safexcel_alg_cbc_aes,
+	&safexcel_alg_md5,
 	&safexcel_alg_sha1,
 	&safexcel_alg_sha224,
 	&safexcel_alg_sha256,
+	&safexcel_alg_sha384,
+	&safexcel_alg_sha512,
+	&safexcel_alg_hmac_md5,
 	&safexcel_alg_hmac_sha1,
 	&safexcel_alg_hmac_sha224,
 	&safexcel_alg_hmac_sha256,
+	&safexcel_alg_hmac_sha384,
+	&safexcel_alg_hmac_sha512,
 	&safexcel_alg_authenc_hmac_sha1_cbc_aes,
 	&safexcel_alg_authenc_hmac_sha224_cbc_aes,
 	&safexcel_alg_authenc_hmac_sha256_cbc_aes,
+	&safexcel_alg_authenc_hmac_sha384_cbc_aes,
+	&safexcel_alg_authenc_hmac_sha512_cbc_aes,
 };
 
 static int safexcel_register_algorithms(struct safexcel_crypto_priv *priv)
@@ -805,6 +864,9 @@ static int safexcel_register_algorithms(struct safexcel_crypto_priv *priv)
 	for (i = 0; i < ARRAY_SIZE(safexcel_algs); i++) {
 		safexcel_algs[i]->priv = priv;
 
+		if (!(safexcel_algs[i]->engines & priv->version))
+			continue;
+
 		if (safexcel_algs[i]->type == SAFEXCEL_ALG_TYPE_SKCIPHER)
 			ret = crypto_register_skcipher(&safexcel_algs[i]->alg.skcipher);
 		else if (safexcel_algs[i]->type == SAFEXCEL_ALG_TYPE_AEAD)
@@ -820,6 +882,9 @@ static int safexcel_register_algorithms(struct safexcel_crypto_priv *priv)
 
 fail:
 	for (j = 0; j < i; j++) {
+		if (!(safexcel_algs[j]->engines & priv->version))
+			continue;
+
 		if (safexcel_algs[j]->type == SAFEXCEL_ALG_TYPE_SKCIPHER)
 			crypto_unregister_skcipher(&safexcel_algs[j]->alg.skcipher);
 		else if (safexcel_algs[j]->type == SAFEXCEL_ALG_TYPE_AEAD)
@@ -836,6 +901,9 @@ static void safexcel_unregister_algorithms(struct safexcel_crypto_priv *priv)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(safexcel_algs); i++) {
+		if (!(safexcel_algs[i]->engines & priv->version))
+			continue;
+
 		if (safexcel_algs[i]->type == SAFEXCEL_ALG_TYPE_SKCIPHER)
 			crypto_unregister_skcipher(&safexcel_algs[i]->alg.skcipher);
 		else if (safexcel_algs[i]->type == SAFEXCEL_ALG_TYPE_AEAD)
@@ -847,9 +915,21 @@ static void safexcel_unregister_algorithms(struct safexcel_crypto_priv *priv)
 
 static void safexcel_configure(struct safexcel_crypto_priv *priv)
 {
-	u32 val, mask;
+	u32 val, mask = 0;
 
 	val = readl(EIP197_HIA_AIC_G(priv) + EIP197_HIA_OPTIONS);
+
+	/* Read number of PEs from the engine */
+	switch (priv->version) {
+	case EIP197B:
+	case EIP197D:
+		mask = EIP197_N_PES_MASK;
+		break;
+	default:
+		mask = EIP97_N_PES_MASK;
+	}
+	priv->config.pes = (val >> EIP197_N_PES_OFFSET) & mask;
+
 	val = (val & GENMASK(27, 25)) >> 25;
 	mask = BIT(val) - 1;
 
@@ -867,7 +947,9 @@ static void safexcel_init_register_offsets(struct safexcel_crypto_priv *priv)
 {
 	struct safexcel_register_offsets *offsets = &priv->offsets;
 
-	if (priv->version == EIP197) {
+	switch (priv->version) {
+	case EIP197B:
+	case EIP197D:
 		offsets->hia_aic	= EIP197_HIA_AIC_BASE;
 		offsets->hia_aic_g	= EIP197_HIA_AIC_G_BASE;
 		offsets->hia_aic_r	= EIP197_HIA_AIC_R_BASE;
@@ -878,7 +960,8 @@ static void safexcel_init_register_offsets(struct safexcel_crypto_priv *priv)
 		offsets->hia_dse_thr	= EIP197_HIA_DSE_THR_BASE;
 		offsets->hia_gen_cfg	= EIP197_HIA_GEN_CFG_BASE;
 		offsets->pe		= EIP197_PE_BASE;
-	} else {
+		break;
+	case EIP97IES:
 		offsets->hia_aic	= EIP97_HIA_AIC_BASE;
 		offsets->hia_aic_g	= EIP97_HIA_AIC_G_BASE;
 		offsets->hia_aic_r	= EIP97_HIA_AIC_R_BASE;
@@ -889,6 +972,7 @@ static void safexcel_init_register_offsets(struct safexcel_crypto_priv *priv)
 		offsets->hia_dse_thr	= EIP97_HIA_DSE_THR_BASE;
 		offsets->hia_gen_cfg	= EIP97_HIA_GEN_CFG_BASE;
 		offsets->pe		= EIP97_PE_BASE;
+		break;
 	}
 }
 
@@ -906,6 +990,9 @@ static int safexcel_probe(struct platform_device *pdev)
 	priv->dev = dev;
 	priv->version = (enum safexcel_eip_version)of_device_get_match_data(dev);
 
+	if (priv->version == EIP197B || priv->version == EIP197D)
+		priv->flags |= EIP197_TRC_CACHE;
+
 	safexcel_init_register_offsets(priv);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -957,6 +1044,13 @@ static int safexcel_probe(struct platform_device *pdev)
 
 	safexcel_configure(priv);
 
+	priv->ring = devm_kzalloc(dev, priv->config.rings * sizeof(*priv->ring),
+				  GFP_KERNEL);
+	if (!priv->ring) {
+		ret = -ENOMEM;
+		goto err_reg_clk;
+	}
+
 	for (i = 0; i < priv->config.rings; i++) {
 		char irq_name[6] = {0}; /* "ringX\0" */
 		char wq_name[9] = {0}; /* "wq_ringX\0" */
@@ -969,6 +1063,14 @@ static int safexcel_probe(struct platform_device *pdev)
 		if (ret)
 			goto err_reg_clk;
 
+		priv->ring[i].rdr_req = devm_kzalloc(dev,
+			sizeof(priv->ring[i].rdr_req) * EIP197_DEFAULT_RING_SIZE,
+			GFP_KERNEL);
+		if (!priv->ring[i].rdr_req) {
+			ret = -ENOMEM;
+			goto err_reg_clk;
+		}
+
 		ring_irq = devm_kzalloc(dev, sizeof(*ring_irq), GFP_KERNEL);
 		if (!ring_irq) {
 			ret = -ENOMEM;
@@ -1004,9 +1106,7 @@ static int safexcel_probe(struct platform_device *pdev)
 		crypto_init_queue(&priv->ring[i].queue,
 				  EIP197_DEFAULT_RING_SIZE);
 
-		INIT_LIST_HEAD(&priv->ring[i].list);
 		spin_lock_init(&priv->ring[i].lock);
-		spin_lock_init(&priv->ring[i].egress_lock);
 		spin_lock_init(&priv->ring[i].queue_lock);
 	}
 
@@ -1034,6 +1134,24 @@ err_core_clk:
 	return ret;
 }
 
+static void safexcel_hw_reset_rings(struct safexcel_crypto_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->config.rings; i++) {
+		/* clear any pending interrupt */
+		writel(GENMASK(5, 0), EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_STAT);
+		writel(GENMASK(7, 0), EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_STAT);
+
+		/* Reset the CDR base address */
+		writel(0, EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_RING_BASE_ADDR_LO);
+		writel(0, EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_RING_BASE_ADDR_HI);
+
+		/* Reset the RDR base address */
+		writel(0, EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_RING_BASE_ADDR_LO);
+		writel(0, EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_RING_BASE_ADDR_HI);
+	}
+}
 
 static int safexcel_remove(struct platform_device *pdev)
 {
@@ -1041,6 +1159,8 @@ static int safexcel_remove(struct platform_device *pdev)
 	int i;
 
 	safexcel_unregister_algorithms(priv);
+	safexcel_hw_reset_rings(priv);
+
 	clk_disable_unprepare(priv->clk);
 
 	for (i = 0; i < priv->config.rings; i++)
@@ -1051,12 +1171,26 @@ static int safexcel_remove(struct platform_device *pdev)
 
 static const struct of_device_id safexcel_of_match_table[] = {
 	{
+		.compatible = "inside-secure,safexcel-eip97ies",
+		.data = (void *)EIP97IES,
+	},
+	{
+		.compatible = "inside-secure,safexcel-eip197b",
+		.data = (void *)EIP197B,
+	},
+	{
+		.compatible = "inside-secure,safexcel-eip197d",
+		.data = (void *)EIP197D,
+	},
+	{
+		/* Deprecated. Kept for backward compatibility. */
 		.compatible = "inside-secure,safexcel-eip97",
-		.data = (void *)EIP97,
+		.data = (void *)EIP97IES,
 	},
 	{
+		/* Deprecated. Kept for backward compatibility. */
 		.compatible = "inside-secure,safexcel-eip197",
-		.data = (void *)EIP197,
+		.data = (void *)EIP197B,
 	},
 	{},
 };
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 8b3ee9b59f53..65624a81f0fd 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2017 Marvell
  *
  * Antoine Tenart <antoine.tenart@free-electrons.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 
 #ifndef __SAFEXCEL_H__
@@ -95,13 +92,13 @@
 #define EIP197_HIA_xDR_STAT			0x003c
 
 /* register offsets */
-#define EIP197_HIA_DFE_CFG			0x0000
-#define EIP197_HIA_DFE_THR_CTRL			0x0000
-#define EIP197_HIA_DFE_THR_STAT			0x0004
-#define EIP197_HIA_DSE_CFG			0x0000
-#define EIP197_HIA_DSE_THR_CTRL			0x0000
-#define EIP197_HIA_DSE_THR_STAT			0x0004
-#define EIP197_HIA_RA_PE_CTRL			0x0010
+#define EIP197_HIA_DFE_CFG(n)			(0x0000 + (128 * (n)))
+#define EIP197_HIA_DFE_THR_CTRL(n)		(0x0000 + (128 * (n)))
+#define EIP197_HIA_DFE_THR_STAT(n)		(0x0004 + (128 * (n)))
+#define EIP197_HIA_DSE_CFG(n)			(0x0000 + (128 * (n)))
+#define EIP197_HIA_DSE_THR_CTRL(n)		(0x0000 + (128 * (n)))
+#define EIP197_HIA_DSE_THR_STAT(n)		(0x0004 + (128 * (n)))
+#define EIP197_HIA_RA_PE_CTRL(n)		(0x0010 + (8   * (n)))
 #define EIP197_HIA_RA_PE_STAT			0x0014
 #define EIP197_HIA_AIC_R_OFF(r)			((r) * 0x1000)
 #define EIP197_HIA_AIC_R_ENABLE_CTRL(r)		(0xe008 - EIP197_HIA_AIC_R_OFF(r))
@@ -114,18 +111,18 @@
 #define EIP197_HIA_MST_CTRL			0xfff4
 #define EIP197_HIA_OPTIONS			0xfff8
 #define EIP197_HIA_VERSION			0xfffc
-#define EIP197_PE_IN_DBUF_THRES			0x0000
-#define EIP197_PE_IN_TBUF_THRES			0x0100
-#define EIP197_PE_ICE_SCRATCH_RAM		0x0800
-#define EIP197_PE_ICE_PUE_CTRL			0x0c80
-#define EIP197_PE_ICE_SCRATCH_CTRL		0x0d04
-#define EIP197_PE_ICE_FPP_CTRL			0x0d80
-#define EIP197_PE_ICE_RAM_CTRL			0x0ff0
-#define EIP197_PE_EIP96_FUNCTION_EN		0x1004
-#define EIP197_PE_EIP96_CONTEXT_CTRL		0x1008
-#define EIP197_PE_EIP96_CONTEXT_STAT		0x100c
-#define EIP197_PE_OUT_DBUF_THRES		0x1c00
-#define EIP197_PE_OUT_TBUF_THRES		0x1d00
+#define EIP197_PE_IN_DBUF_THRES(n)		(0x0000 + (0x2000 * (n)))
+#define EIP197_PE_IN_TBUF_THRES(n)		(0x0100 + (0x2000 * (n)))
+#define EIP197_PE_ICE_SCRATCH_RAM(n)		(0x0800 + (0x2000 * (n)))
+#define EIP197_PE_ICE_PUE_CTRL(n)		(0x0c80 + (0x2000 * (n)))
+#define EIP197_PE_ICE_SCRATCH_CTRL(n)		(0x0d04 + (0x2000 * (n)))
+#define EIP197_PE_ICE_FPP_CTRL(n)		(0x0d80 + (0x2000 * (n)))
+#define EIP197_PE_ICE_RAM_CTRL(n)		(0x0ff0 + (0x2000 * (n)))
+#define EIP197_PE_EIP96_FUNCTION_EN(n)		(0x1004 + (0x2000 * (n)))
+#define EIP197_PE_EIP96_CONTEXT_CTRL(n)		(0x1008 + (0x2000 * (n)))
+#define EIP197_PE_EIP96_CONTEXT_STAT(n)		(0x100c + (0x2000 * (n)))
+#define EIP197_PE_OUT_DBUF_THRES(n)		(0x1c00 + (0x2000 * (n)))
+#define EIP197_PE_OUT_TBUF_THRES(n)		(0x1d00 + (0x2000 * (n)))
 #define EIP197_MST_CTRL				0xfff4
 
 /* EIP197-specific registers, no indirection */
@@ -184,6 +181,11 @@
 #define EIP197_HIA_RA_PE_CTRL_RESET		BIT(31)
 #define EIP197_HIA_RA_PE_CTRL_EN		BIT(30)
 
+/* EIP197_HIA_OPTIONS */
+#define EIP197_N_PES_OFFSET			4
+#define EIP197_N_PES_MASK			GENMASK(4, 0)
+#define EIP97_N_PES_MASK			GENMASK(2, 0)
+
 /* EIP197_HIA_AIC_R_ENABLE_CTRL */
 #define EIP197_CDR_IRQ(n)			BIT((n) * 2)
 #define EIP197_RDR_IRQ(n)			BIT((n) * 2 + 1)
@@ -217,6 +219,7 @@
 #define WR_CACHE_4BITS				(WR_CACHE_3BITS << 1 | BIT(0))
 #define EIP197_MST_CTRL_RD_CACHE(n)		(((n) & 0xf) << 0)
 #define EIP197_MST_CTRL_WD_CACHE(n)		(((n) & 0xf) << 4)
+#define EIP197_MST_CTRL_TX_MAX_CMD(n)		(((n) & 0xf) << 20)
 #define EIP197_MST_CTRL_BYTE_SWAP		BIT(24)
 #define EIP197_MST_CTRL_NO_BYTE_SWAP		BIT(25)
 
@@ -287,7 +290,7 @@ struct safexcel_context_record {
 	u32 control0;
 	u32 control1;
 
-	__le32 data[24];
+	__le32 data[40];
 } __packed;
 
 /* control0 */
@@ -305,14 +308,19 @@ struct safexcel_context_record {
 #define CONTEXT_CONTROL_NO_FINISH_HASH		BIT(5)
 #define CONTEXT_CONTROL_SIZE(n)			((n) << 8)
 #define CONTEXT_CONTROL_KEY_EN			BIT(16)
+#define CONTEXT_CONTROL_CRYPTO_ALG_DES		(0x0 << 17)
+#define CONTEXT_CONTROL_CRYPTO_ALG_3DES		(0x2 << 17)
 #define CONTEXT_CONTROL_CRYPTO_ALG_AES128	(0x5 << 17)
 #define CONTEXT_CONTROL_CRYPTO_ALG_AES192	(0x6 << 17)
 #define CONTEXT_CONTROL_CRYPTO_ALG_AES256	(0x7 << 17)
 #define CONTEXT_CONTROL_DIGEST_PRECOMPUTED	(0x1 << 21)
 #define CONTEXT_CONTROL_DIGEST_HMAC		(0x3 << 21)
+#define CONTEXT_CONTROL_CRYPTO_ALG_MD5		(0x0 << 23)
 #define CONTEXT_CONTROL_CRYPTO_ALG_SHA1		(0x2 << 23)
 #define CONTEXT_CONTROL_CRYPTO_ALG_SHA224	(0x4 << 23)
 #define CONTEXT_CONTROL_CRYPTO_ALG_SHA256	(0x3 << 23)
+#define CONTEXT_CONTROL_CRYPTO_ALG_SHA384	(0x6 << 23)
+#define CONTEXT_CONTROL_CRYPTO_ALG_SHA512	(0x5 << 23)
 #define CONTEXT_CONTROL_INV_FR			(0x5 << 24)
 #define CONTEXT_CONTROL_INV_TR			(0x6 << 24)
 
@@ -327,6 +335,11 @@ struct safexcel_context_record {
 #define CONTEXT_CONTROL_COUNTER_MODE		BIT(10)
 #define CONTEXT_CONTROL_HASH_STORE		BIT(19)
 
+/* The hash counter given to the engine in the context has a granularity of
+ * 64 bits.
+ */
+#define EIP197_COUNTER_BLOCK_SIZE		64
+
 /* EIP197_CS_RAM_CTRL */
 #define EIP197_TRC_ENABLE_0			BIT(4)
 #define EIP197_TRC_ENABLE_1			BIT(5)
@@ -349,13 +362,19 @@ struct safexcel_context_record {
 #define EIP197_TRC_PARAMS2_RC_SZ_SMALL(n)	((n) << 18)
 
 /* Cache helpers */
-#define EIP197_CS_RC_MAX			52
+#define EIP197B_CS_RC_MAX			52
+#define EIP197D_CS_RC_MAX			96
 #define EIP197_CS_RC_SIZE			(4 * sizeof(u32))
 #define EIP197_CS_RC_NEXT(x)			(x)
 #define EIP197_CS_RC_PREV(x)			((x) << 10)
 #define EIP197_RC_NULL				0x3ff
-#define EIP197_CS_TRC_REC_WC			59
-#define EIP197_CS_TRC_LG_REC_WC			73
+#define EIP197B_CS_TRC_REC_WC			59
+#define EIP197D_CS_TRC_REC_WC			64
+#define EIP197B_CS_TRC_LG_REC_WC		73
+#define EIP197D_CS_TRC_LG_REC_WC		80
+#define EIP197B_CS_HT_WC			64
+#define EIP197D_CS_HT_WC			256
+
 
 /* Result data */
 struct result_data_desc {
@@ -450,6 +469,7 @@ struct safexcel_control_data_desc {
 #define EIP197_OPTION_MAGIC_VALUE	BIT(0)
 #define EIP197_OPTION_64BIT_CTX		BIT(1)
 #define EIP197_OPTION_CTX_CTRL_IN_CMD	BIT(8)
+#define EIP197_OPTION_2_TOKEN_IV_CMD	GENMASK(11, 10)
 #define EIP197_OPTION_4_TOKEN_IV_CMD	GENMASK(11, 9)
 
 #define EIP197_TYPE_EXTENDED		0x3
@@ -480,7 +500,7 @@ enum eip197_fw {
 	FW_NB
 };
 
-struct safexcel_ring {
+struct safexcel_desc_ring {
 	void *base;
 	void *base_end;
 	dma_addr_t base_dma;
@@ -489,8 +509,7 @@ struct safexcel_ring {
 	void *write;
 	void *read;
 
-	/* number of elements used in the ring */
-	unsigned nr;
+	/* descriptor element offset */
 	unsigned offset;
 };
 
@@ -500,12 +519,8 @@ enum safexcel_alg_type {
 	SAFEXCEL_ALG_TYPE_AHASH,
 };
 
-struct safexcel_request {
-	struct list_head list;
-	struct crypto_async_request *req;
-};
-
 struct safexcel_config {
+	u32 pes;
 	u32 rings;
 
 	u32 cd_size;
@@ -521,9 +536,40 @@ struct safexcel_work_data {
 	int ring;
 };
 
+struct safexcel_ring {
+	spinlock_t lock;
+
+	struct workqueue_struct *workqueue;
+	struct safexcel_work_data work_data;
+
+	/* command/result rings */
+	struct safexcel_desc_ring cdr;
+	struct safexcel_desc_ring rdr;
+
+	/* result ring crypto API request */
+	struct crypto_async_request **rdr_req;
+
+	/* queue */
+	struct crypto_queue queue;
+	spinlock_t queue_lock;
+
+	/* Number of requests in the engine. */
+	int requests;
+
+	/* The ring is currently handling at least one request */
+	bool busy;
+
+	/* Store for current requests when bailing out of the dequeueing
+	 * function when no enough resources are available.
+	 */
+	struct crypto_async_request *req;
+	struct crypto_async_request *backlog;
+};
+
 enum safexcel_eip_version {
-	EIP97,
-	EIP197,
+	EIP97IES = BIT(0),
+	EIP197B  = BIT(1),
+	EIP197D  = BIT(2),
 };
 
 struct safexcel_register_offsets {
@@ -539,6 +585,10 @@ struct safexcel_register_offsets {
 	u32 pe;
 };
 
+enum safexcel_flags {
+	EIP197_TRC_CACHE = BIT(0),
+};
+
 struct safexcel_crypto_priv {
 	void __iomem *base;
 	struct device *dev;
@@ -548,46 +598,19 @@ struct safexcel_crypto_priv {
 
 	enum safexcel_eip_version version;
 	struct safexcel_register_offsets offsets;
+	u32 flags;
 
 	/* context DMA pool */
 	struct dma_pool *context_pool;
 
 	atomic_t ring_used;
 
-	struct {
-		spinlock_t lock;
-		spinlock_t egress_lock;
-
-		struct list_head list;
-		struct workqueue_struct *workqueue;
-		struct safexcel_work_data work_data;
-
-		/* command/result rings */
-		struct safexcel_ring cdr;
-		struct safexcel_ring rdr;
-
-		/* queue */
-		struct crypto_queue queue;
-		spinlock_t queue_lock;
-
-		/* Number of requests in the engine. */
-		int requests;
-
-		/* The ring is currently handling at least one request */
-		bool busy;
-
-		/* Store for current requests when bailing out of the dequeueing
-		 * function when no enough resources are available.
-		 */
-		struct crypto_async_request *req;
-		struct crypto_async_request *backlog;
-	} ring[EIP197_MAX_RINGS];
+	struct safexcel_ring *ring;
 };
 
 struct safexcel_context {
 	int (*send)(struct crypto_async_request *req, int ring,
-		    struct safexcel_request *request, int *commands,
-		    int *results);
+		    int *commands, int *results);
 	int (*handle_result)(struct safexcel_crypto_priv *priv, int ring,
 			     struct crypto_async_request *req, bool *complete,
 			     int *ret);
@@ -600,13 +623,13 @@ struct safexcel_context {
 };
 
 struct safexcel_ahash_export_state {
-	u64 len;
-	u64 processed;
+	u64 len[2];
+	u64 processed[2];
 
 	u32 digest;
 
-	u32 state[SHA256_DIGEST_SIZE / sizeof(u32)];
-	u8 cache[SHA256_BLOCK_SIZE];
+	u32 state[SHA512_DIGEST_SIZE / sizeof(u32)];
+	u8 cache[SHA512_BLOCK_SIZE];
 };
 
 /*
@@ -617,6 +640,7 @@ struct safexcel_ahash_export_state {
 struct safexcel_alg_template {
 	struct safexcel_crypto_priv *priv;
 	enum safexcel_alg_type type;
+	u32 engines;
 	union {
 		struct skcipher_alg skcipher;
 		struct aead_alg aead;
@@ -635,16 +659,16 @@ int safexcel_rdesc_check_errors(struct safexcel_crypto_priv *priv,
 void safexcel_complete(struct safexcel_crypto_priv *priv, int ring);
 int safexcel_invalidate_cache(struct crypto_async_request *async,
 			      struct safexcel_crypto_priv *priv,
-			      dma_addr_t ctxr_dma, int ring,
-			      struct safexcel_request *request);
+			      dma_addr_t ctxr_dma, int ring);
 int safexcel_init_ring_descriptors(struct safexcel_crypto_priv *priv,
-				   struct safexcel_ring *cdr,
-				   struct safexcel_ring *rdr);
+				   struct safexcel_desc_ring *cdr,
+				   struct safexcel_desc_ring *rdr);
 int safexcel_select_ring(struct safexcel_crypto_priv *priv);
 void *safexcel_ring_next_rptr(struct safexcel_crypto_priv *priv,
-			      struct safexcel_ring *ring);
+			      struct safexcel_desc_ring *ring);
+void *safexcel_ring_first_rptr(struct safexcel_crypto_priv *priv, int  ring);
 void safexcel_ring_rollback_wptr(struct safexcel_crypto_priv *priv,
-				 struct safexcel_ring *ring);
+				 struct safexcel_desc_ring *ring);
 struct safexcel_command_desc *safexcel_add_cdesc(struct safexcel_crypto_priv *priv,
 						 int ring_id,
 						 bool first, bool last,
@@ -655,21 +679,44 @@ struct safexcel_result_desc *safexcel_add_rdesc(struct safexcel_crypto_priv *pri
 						 int ring_id,
 						bool first, bool last,
 						dma_addr_t data, u32 len);
+int safexcel_ring_first_rdr_index(struct safexcel_crypto_priv *priv,
+				  int ring);
+int safexcel_ring_rdr_rdesc_index(struct safexcel_crypto_priv *priv,
+				  int ring,
+				  struct safexcel_result_desc *rdesc);
+void safexcel_rdr_req_set(struct safexcel_crypto_priv *priv,
+			  int ring,
+			  struct safexcel_result_desc *rdesc,
+			  struct crypto_async_request *req);
+inline struct crypto_async_request *
+safexcel_rdr_req_get(struct safexcel_crypto_priv *priv, int ring);
 void safexcel_inv_complete(struct crypto_async_request *req, int error);
 int safexcel_hmac_setkey(const char *alg, const u8 *key, unsigned int keylen,
 			 void *istate, void *ostate);
 
 /* available algorithms */
+extern struct safexcel_alg_template safexcel_alg_ecb_des;
+extern struct safexcel_alg_template safexcel_alg_cbc_des;
+extern struct safexcel_alg_template safexcel_alg_ecb_des3_ede;
+extern struct safexcel_alg_template safexcel_alg_cbc_des3_ede;
 extern struct safexcel_alg_template safexcel_alg_ecb_aes;
 extern struct safexcel_alg_template safexcel_alg_cbc_aes;
+extern struct safexcel_alg_template safexcel_alg_md5;
 extern struct safexcel_alg_template safexcel_alg_sha1;
 extern struct safexcel_alg_template safexcel_alg_sha224;
 extern struct safexcel_alg_template safexcel_alg_sha256;
+extern struct safexcel_alg_template safexcel_alg_sha384;
+extern struct safexcel_alg_template safexcel_alg_sha512;
+extern struct safexcel_alg_template safexcel_alg_hmac_md5;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha1;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha224;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha256;
+extern struct safexcel_alg_template safexcel_alg_hmac_sha384;
+extern struct safexcel_alg_template safexcel_alg_hmac_sha512;
 extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_cbc_aes;
 extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha224_cbc_aes;
 extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha256_cbc_aes;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha384_cbc_aes;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha512_cbc_aes;
 
 #endif
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index 6bb60fda2043..3aef1d43e435 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2017 Marvell
  *
  * Antoine Tenart <antoine.tenart@free-electrons.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 
 #include <linux/device.h>
@@ -15,6 +12,7 @@
 #include <crypto/aead.h>
 #include <crypto/aes.h>
 #include <crypto/authenc.h>
+#include <crypto/des.h>
 #include <crypto/sha.h>
 #include <crypto/skcipher.h>
 #include <crypto/internal/aead.h>
@@ -27,21 +25,28 @@ enum safexcel_cipher_direction {
 	SAFEXCEL_DECRYPT,
 };
 
+enum safexcel_cipher_alg {
+	SAFEXCEL_DES,
+	SAFEXCEL_3DES,
+	SAFEXCEL_AES,
+};
+
 struct safexcel_cipher_ctx {
 	struct safexcel_context base;
 	struct safexcel_crypto_priv *priv;
 
 	u32 mode;
+	enum safexcel_cipher_alg alg;
 	bool aead;
 
 	__le32 key[8];
 	unsigned int key_len;
 
 	/* All the below is AEAD specific */
-	u32 alg;
+	u32 hash_alg;
 	u32 state_sz;
-	u32 ipad[SHA256_DIGEST_SIZE / sizeof(u32)];
-	u32 opad[SHA256_DIGEST_SIZE / sizeof(u32)];
+	u32 ipad[SHA512_DIGEST_SIZE / sizeof(u32)];
+	u32 opad[SHA512_DIGEST_SIZE / sizeof(u32)];
 };
 
 struct safexcel_cipher_req {
@@ -57,10 +62,24 @@ static void safexcel_skcipher_token(struct safexcel_cipher_ctx *ctx, u8 *iv,
 	unsigned offset = 0;
 
 	if (ctx->mode == CONTEXT_CONTROL_CRYPTO_MODE_CBC) {
-		offset = AES_BLOCK_SIZE / sizeof(u32);
-		memcpy(cdesc->control_data.token, iv, AES_BLOCK_SIZE);
+		switch (ctx->alg) {
+		case SAFEXCEL_DES:
+			offset = DES_BLOCK_SIZE / sizeof(u32);
+			memcpy(cdesc->control_data.token, iv, DES_BLOCK_SIZE);
+			cdesc->control_data.options |= EIP197_OPTION_2_TOKEN_IV_CMD;
+			break;
+		case SAFEXCEL_3DES:
+			offset = DES3_EDE_BLOCK_SIZE / sizeof(u32);
+			memcpy(cdesc->control_data.token, iv, DES3_EDE_BLOCK_SIZE);
+			cdesc->control_data.options |= EIP197_OPTION_2_TOKEN_IV_CMD;
+			break;
 
-		cdesc->control_data.options |= EIP197_OPTION_4_TOKEN_IV_CMD;
+		case SAFEXCEL_AES:
+			offset = AES_BLOCK_SIZE / sizeof(u32);
+			memcpy(cdesc->control_data.token, iv, AES_BLOCK_SIZE);
+			cdesc->control_data.options |= EIP197_OPTION_4_TOKEN_IV_CMD;
+			break;
+		}
 	}
 
 	token = (struct safexcel_token *)(cdesc->control_data.token + offset);
@@ -145,7 +164,7 @@ static int safexcel_skcipher_aes_setkey(struct crypto_skcipher *ctfm,
 		return ret;
 	}
 
-	if (priv->version == EIP197 && ctx->base.ctxr_dma) {
+	if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr_dma) {
 		for (i = 0; i < len / sizeof(u32); i++) {
 			if (ctx->key[i] != cpu_to_le32(aes.key_enc[i])) {
 				ctx->base.needs_inv = true;
@@ -179,12 +198,12 @@ static int safexcel_aead_aes_setkey(struct crypto_aead *ctfm, const u8 *key,
 		goto badkey;
 
 	/* Encryption key */
-	if (priv->version == EIP197 && ctx->base.ctxr_dma &&
+	if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr_dma &&
 	    memcmp(ctx->key, keys.enckey, keys.enckeylen))
 		ctx->base.needs_inv = true;
 
 	/* Auth key */
-	switch (ctx->alg) {
+	switch (ctx->hash_alg) {
 	case CONTEXT_CONTROL_CRYPTO_ALG_SHA1:
 		if (safexcel_hmac_setkey("safexcel-sha1", keys.authkey,
 					 keys.authkeylen, &istate, &ostate))
@@ -200,6 +219,16 @@ static int safexcel_aead_aes_setkey(struct crypto_aead *ctfm, const u8 *key,
 					 keys.authkeylen, &istate, &ostate))
 			goto badkey;
 		break;
+	case CONTEXT_CONTROL_CRYPTO_ALG_SHA384:
+		if (safexcel_hmac_setkey("safexcel-sha384", keys.authkey,
+					 keys.authkeylen, &istate, &ostate))
+			goto badkey;
+		break;
+	case CONTEXT_CONTROL_CRYPTO_ALG_SHA512:
+		if (safexcel_hmac_setkey("safexcel-sha512", keys.authkey,
+					 keys.authkeylen, &istate, &ostate))
+			goto badkey;
+		break;
 	default:
 		dev_err(priv->dev, "aead: unsupported hash algorithm\n");
 		goto badkey;
@@ -208,7 +237,7 @@ static int safexcel_aead_aes_setkey(struct crypto_aead *ctfm, const u8 *key,
 	crypto_aead_set_flags(ctfm, crypto_aead_get_flags(ctfm) &
 				    CRYPTO_TFM_RES_MASK);
 
-	if (priv->version == EIP197 && ctx->base.ctxr_dma &&
+	if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr_dma &&
 	    (memcmp(ctx->ipad, istate.state, ctx->state_sz) ||
 	     memcmp(ctx->opad, ostate.state, ctx->state_sz)))
 		ctx->base.needs_inv = true;
@@ -258,22 +287,28 @@ static int safexcel_context_control(struct safexcel_cipher_ctx *ctx,
 
 	if (ctx->aead)
 		cdesc->control_data.control0 |= CONTEXT_CONTROL_DIGEST_HMAC |
-						ctx->alg;
-
-	switch (ctx->key_len) {
-	case AES_KEYSIZE_128:
-		cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_AES128;
-		break;
-	case AES_KEYSIZE_192:
-		cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_AES192;
-		break;
-	case AES_KEYSIZE_256:
-		cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_AES256;
-		break;
-	default:
-		dev_err(priv->dev, "aes keysize not supported: %u\n",
-			ctx->key_len);
-		return -EINVAL;
+						ctx->hash_alg;
+
+	if (ctx->alg == SAFEXCEL_DES) {
+		cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_DES;
+	} else if (ctx->alg == SAFEXCEL_3DES) {
+		cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_3DES;
+	} else if (ctx->alg == SAFEXCEL_AES) {
+		switch (ctx->key_len) {
+		case AES_KEYSIZE_128:
+			cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_AES128;
+			break;
+		case AES_KEYSIZE_192:
+			cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_AES192;
+			break;
+		case AES_KEYSIZE_256:
+			cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_AES256;
+			break;
+		default:
+			dev_err(priv->dev, "aes keysize not supported: %u\n",
+				ctx->key_len);
+			return -EINVAL;
+		}
 	}
 
 	ctrl_size = ctx->key_len / sizeof(u32);
@@ -298,7 +333,6 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 
 	*ret = 0;
 
-	spin_lock_bh(&priv->ring[ring].egress_lock);
 	do {
 		rdesc = safexcel_ring_next_rptr(priv, &priv->ring[ring].rdr);
 		if (IS_ERR(rdesc)) {
@@ -315,7 +349,6 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 	} while (!rdesc->last_seg);
 
 	safexcel_complete(priv, ring);
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
 
 	if (src == dst) {
 		dma_unmap_sg(priv->dev, src,
@@ -335,8 +368,7 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 	return ndesc;
 }
 
-static int safexcel_aes_send(struct crypto_async_request *base, int ring,
-			     struct safexcel_request *request,
+static int safexcel_send_req(struct crypto_async_request *base, int ring,
 			     struct safexcel_cipher_req *sreq,
 			     struct scatterlist *src, struct scatterlist *dst,
 			     unsigned int cryptlen, unsigned int assoclen,
@@ -346,7 +378,7 @@ static int safexcel_aes_send(struct crypto_async_request *base, int ring,
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(base->tfm);
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	struct safexcel_command_desc *cdesc;
-	struct safexcel_result_desc *rdesc;
+	struct safexcel_result_desc *rdesc, *first_rdesc = NULL;
 	struct scatterlist *sg;
 	unsigned int totlen = cryptlen + assoclen;
 	int nr_src, nr_dst, n_cdesc = 0, n_rdesc = 0, queued = totlen;
@@ -386,8 +418,6 @@ static int safexcel_aes_send(struct crypto_async_request *base, int ring,
 		       ctx->opad, ctx->state_sz);
 	}
 
-	spin_lock_bh(&priv->ring[ring].egress_lock);
-
 	/* command descriptors */
 	for_each_sg(src, sg, nr_src, i) {
 		int len = sg_dma_len(sg);
@@ -434,12 +464,12 @@ static int safexcel_aes_send(struct crypto_async_request *base, int ring,
 			ret = PTR_ERR(rdesc);
 			goto rdesc_rollback;
 		}
+		if (first)
+			first_rdesc = rdesc;
 		n_rdesc++;
 	}
 
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
-
-	request->req = base;
+	safexcel_rdr_req_set(priv, ring, first_rdesc, base);
 
 	*commands = n_cdesc;
 	*results = n_rdesc;
@@ -452,8 +482,6 @@ cdesc_rollback:
 	for (i = 0; i < n_cdesc; i++)
 		safexcel_ring_rollback_wptr(priv, &priv->ring[ring].cdr);
 
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
-
 	if (src == dst) {
 		dma_unmap_sg(priv->dev, src,
 			     sg_nents_for_len(src, totlen),
@@ -481,7 +509,6 @@ static int safexcel_handle_inv_result(struct safexcel_crypto_priv *priv,
 
 	*ret = 0;
 
-	spin_lock_bh(&priv->ring[ring].egress_lock);
 	do {
 		rdesc = safexcel_ring_next_rptr(priv, &priv->ring[ring].rdr);
 		if (IS_ERR(rdesc)) {
@@ -491,17 +518,13 @@ static int safexcel_handle_inv_result(struct safexcel_crypto_priv *priv,
 			break;
 		}
 
-		if (rdesc->result_data.error_code) {
-			dev_err(priv->dev, "cipher: invalidate: result descriptor error (%d)\n",
-				rdesc->result_data.error_code);
-			*ret = -EIO;
-		}
+		if (likely(!*ret))
+			*ret = safexcel_rdesc_check_errors(priv, rdesc);
 
 		ndesc++;
 	} while (!rdesc->last_seg);
 
 	safexcel_complete(priv, ring);
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
 
 	if (ctx->base.exit_inv) {
 		dma_pool_free(priv->context_pool, ctx->base.ctxr,
@@ -577,15 +600,13 @@ static int safexcel_aead_handle_result(struct safexcel_crypto_priv *priv,
 }
 
 static int safexcel_cipher_send_inv(struct crypto_async_request *base,
-				    int ring, struct safexcel_request *request,
-				    int *commands, int *results)
+				    int ring, int *commands, int *results)
 {
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(base->tfm);
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	int ret;
 
-	ret = safexcel_invalidate_cache(base, priv, ctx->base.ctxr_dma, ring,
-					request);
+	ret = safexcel_invalidate_cache(base, priv, ctx->base.ctxr_dma, ring);
 	if (unlikely(ret))
 		return ret;
 
@@ -596,7 +617,6 @@ static int safexcel_cipher_send_inv(struct crypto_async_request *base,
 }
 
 static int safexcel_skcipher_send(struct crypto_async_request *async, int ring,
-				  struct safexcel_request *request,
 				  int *commands, int *results)
 {
 	struct skcipher_request *req = skcipher_request_cast(async);
@@ -605,21 +625,19 @@ static int safexcel_skcipher_send(struct crypto_async_request *async, int ring,
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	int ret;
 
-	BUG_ON(priv->version == EIP97 && sreq->needs_inv);
+	BUG_ON(!(priv->flags & EIP197_TRC_CACHE) && sreq->needs_inv);
 
 	if (sreq->needs_inv)
-		ret = safexcel_cipher_send_inv(async, ring, request, commands,
-					       results);
+		ret = safexcel_cipher_send_inv(async, ring, commands, results);
 	else
-		ret = safexcel_aes_send(async, ring, request, sreq, req->src,
+		ret = safexcel_send_req(async, ring, sreq, req->src,
 					req->dst, req->cryptlen, 0, 0, req->iv,
 					commands, results);
 	return ret;
 }
 
 static int safexcel_aead_send(struct crypto_async_request *async, int ring,
-			      struct safexcel_request *request, int *commands,
-			      int *results)
+			      int *commands, int *results)
 {
 	struct aead_request *req = aead_request_cast(async);
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
@@ -628,14 +646,13 @@ static int safexcel_aead_send(struct crypto_async_request *async, int ring,
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	int ret;
 
-	BUG_ON(priv->version == EIP97 && sreq->needs_inv);
+	BUG_ON(!(priv->flags & EIP197_TRC_CACHE) && sreq->needs_inv);
 
 	if (sreq->needs_inv)
-		ret = safexcel_cipher_send_inv(async, ring, request, commands,
-					       results);
+		ret = safexcel_cipher_send_inv(async, ring, commands, results);
 	else
-		ret = safexcel_aes_send(async, ring, request, sreq, req->src,
-					req->dst, req->cryptlen, req->assoclen,
+		ret = safexcel_send_req(async, ring, sreq, req->src, req->dst,
+					req->cryptlen, req->assoclen,
 					crypto_aead_authsize(tfm), req->iv,
 					commands, results);
 	return ret;
@@ -705,9 +722,10 @@ static int safexcel_aead_exit_inv(struct crypto_tfm *tfm)
 	return safexcel_cipher_exit_inv(tfm, &req->base, sreq, &result);
 }
 
-static int safexcel_aes(struct crypto_async_request *base,
+static int safexcel_queue_req(struct crypto_async_request *base,
 			struct safexcel_cipher_req *sreq,
-			enum safexcel_cipher_direction dir, u32 mode)
+			enum safexcel_cipher_direction dir, u32 mode,
+			enum safexcel_cipher_alg alg)
 {
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(base->tfm);
 	struct safexcel_crypto_priv *priv = ctx->priv;
@@ -715,10 +733,11 @@ static int safexcel_aes(struct crypto_async_request *base,
 
 	sreq->needs_inv = false;
 	sreq->direction = dir;
+	ctx->alg = alg;
 	ctx->mode = mode;
 
 	if (ctx->base.ctxr) {
-		if (priv->version == EIP197 && ctx->base.needs_inv) {
+		if (priv->flags & EIP197_TRC_CACHE && ctx->base.needs_inv) {
 			sreq->needs_inv = true;
 			ctx->base.needs_inv = false;
 		}
@@ -745,14 +764,16 @@ static int safexcel_aes(struct crypto_async_request *base,
 
 static int safexcel_ecb_aes_encrypt(struct skcipher_request *req)
 {
-	return safexcel_aes(&req->base, skcipher_request_ctx(req),
-			    SAFEXCEL_ENCRYPT, CONTEXT_CONTROL_CRYPTO_MODE_ECB);
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_ENCRYPT, CONTEXT_CONTROL_CRYPTO_MODE_ECB,
+			SAFEXCEL_AES);
 }
 
 static int safexcel_ecb_aes_decrypt(struct skcipher_request *req)
 {
-	return safexcel_aes(&req->base, skcipher_request_ctx(req),
-			    SAFEXCEL_DECRYPT, CONTEXT_CONTROL_CRYPTO_MODE_ECB);
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_DECRYPT, CONTEXT_CONTROL_CRYPTO_MODE_ECB,
+			SAFEXCEL_AES);
 }
 
 static int safexcel_skcipher_cra_init(struct crypto_tfm *tfm)
@@ -795,7 +816,7 @@ static void safexcel_skcipher_cra_exit(struct crypto_tfm *tfm)
 	if (safexcel_cipher_cra_exit(tfm))
 		return;
 
-	if (priv->version == EIP197) {
+	if (priv->flags & EIP197_TRC_CACHE) {
 		ret = safexcel_skcipher_exit_inv(tfm);
 		if (ret)
 			dev_warn(priv->dev, "skcipher: invalidation error %d\n",
@@ -815,7 +836,7 @@ static void safexcel_aead_cra_exit(struct crypto_tfm *tfm)
 	if (safexcel_cipher_cra_exit(tfm))
 		return;
 
-	if (priv->version == EIP197) {
+	if (priv->flags & EIP197_TRC_CACHE) {
 		ret = safexcel_aead_exit_inv(tfm);
 		if (ret)
 			dev_warn(priv->dev, "aead: invalidation error %d\n",
@@ -828,6 +849,7 @@ static void safexcel_aead_cra_exit(struct crypto_tfm *tfm)
 
 struct safexcel_alg_template safexcel_alg_ecb_aes = {
 	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.skcipher = {
 		.setkey = safexcel_skcipher_aes_setkey,
 		.encrypt = safexcel_ecb_aes_encrypt,
@@ -838,7 +860,7 @@ struct safexcel_alg_template safexcel_alg_ecb_aes = {
 			.cra_name = "ecb(aes)",
 			.cra_driver_name = "safexcel-ecb-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				     CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
@@ -852,18 +874,21 @@ struct safexcel_alg_template safexcel_alg_ecb_aes = {
 
 static int safexcel_cbc_aes_encrypt(struct skcipher_request *req)
 {
-	return safexcel_aes(&req->base, skcipher_request_ctx(req),
-			    SAFEXCEL_ENCRYPT, CONTEXT_CONTROL_CRYPTO_MODE_CBC);
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_ENCRYPT, CONTEXT_CONTROL_CRYPTO_MODE_CBC,
+			SAFEXCEL_AES);
 }
 
 static int safexcel_cbc_aes_decrypt(struct skcipher_request *req)
 {
-	return safexcel_aes(&req->base, skcipher_request_ctx(req),
-			    SAFEXCEL_DECRYPT, CONTEXT_CONTROL_CRYPTO_MODE_CBC);
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_DECRYPT, CONTEXT_CONTROL_CRYPTO_MODE_CBC,
+			SAFEXCEL_AES);
 }
 
 struct safexcel_alg_template safexcel_alg_cbc_aes = {
 	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.skcipher = {
 		.setkey = safexcel_skcipher_aes_setkey,
 		.encrypt = safexcel_cbc_aes_encrypt,
@@ -875,7 +900,7 @@ struct safexcel_alg_template safexcel_alg_cbc_aes = {
 			.cra_name = "cbc(aes)",
 			.cra_driver_name = "safexcel-cbc-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				     CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
@@ -887,20 +912,234 @@ struct safexcel_alg_template safexcel_alg_cbc_aes = {
 	},
 };
 
+static int safexcel_cbc_des_encrypt(struct skcipher_request *req)
+{
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_ENCRYPT, CONTEXT_CONTROL_CRYPTO_MODE_CBC,
+			SAFEXCEL_DES);
+}
+
+static int safexcel_cbc_des_decrypt(struct skcipher_request *req)
+{
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_DECRYPT, CONTEXT_CONTROL_CRYPTO_MODE_CBC,
+			SAFEXCEL_DES);
+}
+
+static int safexcel_des_setkey(struct crypto_skcipher *ctfm, const u8 *key,
+			       unsigned int len)
+{
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(ctfm);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	u32 tmp[DES_EXPKEY_WORDS];
+	int ret;
+
+	if (len != DES_KEY_SIZE) {
+		crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	ret = des_ekey(tmp, key);
+	if (!ret && (tfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY)) {
+		tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY;
+		return -EINVAL;
+	}
+
+	/* if context exits and key changed, need to invalidate it */
+	if (ctx->base.ctxr_dma)
+		if (memcmp(ctx->key, key, len))
+			ctx->base.needs_inv = true;
+
+	memcpy(ctx->key, key, len);
+	ctx->key_len = len;
+
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_cbc_des = {
+	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.engines = EIP97IES | EIP197B | EIP197D,
+	.alg.skcipher = {
+		.setkey = safexcel_des_setkey,
+		.encrypt = safexcel_cbc_des_encrypt,
+		.decrypt = safexcel_cbc_des_decrypt,
+		.min_keysize = DES_KEY_SIZE,
+		.max_keysize = DES_KEY_SIZE,
+		.ivsize = DES_BLOCK_SIZE,
+		.base = {
+			.cra_name = "cbc(des)",
+			.cra_driver_name = "safexcel-cbc-des",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = DES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_skcipher_cra_init,
+			.cra_exit = safexcel_skcipher_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_ecb_des_encrypt(struct skcipher_request *req)
+{
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_ENCRYPT, CONTEXT_CONTROL_CRYPTO_MODE_ECB,
+			SAFEXCEL_DES);
+}
+
+static int safexcel_ecb_des_decrypt(struct skcipher_request *req)
+{
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_DECRYPT, CONTEXT_CONTROL_CRYPTO_MODE_ECB,
+			SAFEXCEL_DES);
+}
+
+struct safexcel_alg_template safexcel_alg_ecb_des = {
+	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.engines = EIP97IES | EIP197B | EIP197D,
+	.alg.skcipher = {
+		.setkey = safexcel_des_setkey,
+		.encrypt = safexcel_ecb_des_encrypt,
+		.decrypt = safexcel_ecb_des_decrypt,
+		.min_keysize = DES_KEY_SIZE,
+		.max_keysize = DES_KEY_SIZE,
+		.ivsize = DES_BLOCK_SIZE,
+		.base = {
+			.cra_name = "ecb(des)",
+			.cra_driver_name = "safexcel-ecb-des",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = DES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_skcipher_cra_init,
+			.cra_exit = safexcel_skcipher_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_cbc_des3_ede_encrypt(struct skcipher_request *req)
+{
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_ENCRYPT, CONTEXT_CONTROL_CRYPTO_MODE_CBC,
+			SAFEXCEL_3DES);
+}
+
+static int safexcel_cbc_des3_ede_decrypt(struct skcipher_request *req)
+{
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_DECRYPT, CONTEXT_CONTROL_CRYPTO_MODE_CBC,
+			SAFEXCEL_3DES);
+}
+
+static int safexcel_des3_ede_setkey(struct crypto_skcipher *ctfm,
+				   const u8 *key, unsigned int len)
+{
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(ctfm);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (len != DES3_EDE_KEY_SIZE) {
+		crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	/* if context exits and key changed, need to invalidate it */
+	if (ctx->base.ctxr_dma) {
+		if (memcmp(ctx->key, key, len))
+			ctx->base.needs_inv = true;
+	}
+
+	memcpy(ctx->key, key, len);
+
+	ctx->key_len = len;
+
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_cbc_des3_ede = {
+	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.engines = EIP97IES | EIP197B | EIP197D,
+	.alg.skcipher = {
+		.setkey = safexcel_des3_ede_setkey,
+		.encrypt = safexcel_cbc_des3_ede_encrypt,
+		.decrypt = safexcel_cbc_des3_ede_decrypt,
+		.min_keysize = DES3_EDE_KEY_SIZE,
+		.max_keysize = DES3_EDE_KEY_SIZE,
+		.ivsize = DES3_EDE_BLOCK_SIZE,
+		.base = {
+			.cra_name = "cbc(des3_ede)",
+			.cra_driver_name = "safexcel-cbc-des3_ede",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_skcipher_cra_init,
+			.cra_exit = safexcel_skcipher_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_ecb_des3_ede_encrypt(struct skcipher_request *req)
+{
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_ENCRYPT, CONTEXT_CONTROL_CRYPTO_MODE_ECB,
+			SAFEXCEL_3DES);
+}
+
+static int safexcel_ecb_des3_ede_decrypt(struct skcipher_request *req)
+{
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_DECRYPT, CONTEXT_CONTROL_CRYPTO_MODE_ECB,
+			SAFEXCEL_3DES);
+}
+
+struct safexcel_alg_template safexcel_alg_ecb_des3_ede = {
+	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.engines = EIP97IES | EIP197B | EIP197D,
+	.alg.skcipher = {
+		.setkey = safexcel_des3_ede_setkey,
+		.encrypt = safexcel_ecb_des3_ede_encrypt,
+		.decrypt = safexcel_ecb_des3_ede_decrypt,
+		.min_keysize = DES3_EDE_KEY_SIZE,
+		.max_keysize = DES3_EDE_KEY_SIZE,
+		.ivsize = DES3_EDE_BLOCK_SIZE,
+		.base = {
+			.cra_name = "ecb(des3_ede)",
+			.cra_driver_name = "safexcel-ecb-des3_ede",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_skcipher_cra_init,
+			.cra_exit = safexcel_skcipher_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
 static int safexcel_aead_encrypt(struct aead_request *req)
 {
 	struct safexcel_cipher_req *creq = aead_request_ctx(req);
 
-	return safexcel_aes(&req->base, creq, SAFEXCEL_ENCRYPT,
-			    CONTEXT_CONTROL_CRYPTO_MODE_CBC);
+	return safexcel_queue_req(&req->base, creq, SAFEXCEL_ENCRYPT,
+			CONTEXT_CONTROL_CRYPTO_MODE_CBC, SAFEXCEL_AES);
 }
 
 static int safexcel_aead_decrypt(struct aead_request *req)
 {
 	struct safexcel_cipher_req *creq = aead_request_ctx(req);
 
-	return safexcel_aes(&req->base, creq, SAFEXCEL_DECRYPT,
-			    CONTEXT_CONTROL_CRYPTO_MODE_CBC);
+	return safexcel_queue_req(&req->base, creq, SAFEXCEL_DECRYPT,
+			CONTEXT_CONTROL_CRYPTO_MODE_CBC, SAFEXCEL_AES);
 }
 
 static int safexcel_aead_cra_init(struct crypto_tfm *tfm)
@@ -926,13 +1165,14 @@ static int safexcel_aead_sha1_cra_init(struct crypto_tfm *tfm)
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	safexcel_aead_cra_init(tfm);
-	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA1;
+	ctx->hash_alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA1;
 	ctx->state_sz = SHA1_DIGEST_SIZE;
 	return 0;
 }
 
 struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_cbc_aes = {
 	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.aead = {
 		.setkey = safexcel_aead_aes_setkey,
 		.encrypt = safexcel_aead_encrypt,
@@ -943,7 +1183,7 @@ struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_cbc_aes = {
 			.cra_name = "authenc(hmac(sha1),cbc(aes))",
 			.cra_driver_name = "safexcel-authenc-hmac-sha1-cbc-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				     CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
@@ -960,13 +1200,14 @@ static int safexcel_aead_sha256_cra_init(struct crypto_tfm *tfm)
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	safexcel_aead_cra_init(tfm);
-	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA256;
+	ctx->hash_alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA256;
 	ctx->state_sz = SHA256_DIGEST_SIZE;
 	return 0;
 }
 
 struct safexcel_alg_template safexcel_alg_authenc_hmac_sha256_cbc_aes = {
 	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.aead = {
 		.setkey = safexcel_aead_aes_setkey,
 		.encrypt = safexcel_aead_encrypt,
@@ -977,7 +1218,7 @@ struct safexcel_alg_template safexcel_alg_authenc_hmac_sha256_cbc_aes = {
 			.cra_name = "authenc(hmac(sha256),cbc(aes))",
 			.cra_driver_name = "safexcel-authenc-hmac-sha256-cbc-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				     CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
@@ -994,13 +1235,14 @@ static int safexcel_aead_sha224_cra_init(struct crypto_tfm *tfm)
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	safexcel_aead_cra_init(tfm);
-	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA224;
+	ctx->hash_alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA224;
 	ctx->state_sz = SHA256_DIGEST_SIZE;
 	return 0;
 }
 
 struct safexcel_alg_template safexcel_alg_authenc_hmac_sha224_cbc_aes = {
 	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.aead = {
 		.setkey = safexcel_aead_aes_setkey,
 		.encrypt = safexcel_aead_encrypt,
@@ -1011,7 +1253,7 @@ struct safexcel_alg_template safexcel_alg_authenc_hmac_sha224_cbc_aes = {
 			.cra_name = "authenc(hmac(sha224),cbc(aes))",
 			.cra_driver_name = "safexcel-authenc-hmac-sha224-cbc-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				     CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
@@ -1022,3 +1264,73 @@ struct safexcel_alg_template safexcel_alg_authenc_hmac_sha224_cbc_aes = {
 		},
 	},
 };
+
+static int safexcel_aead_sha512_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_cra_init(tfm);
+	ctx->hash_alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA512;
+	ctx->state_sz = SHA512_DIGEST_SIZE;
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sha512_cbc_aes = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.engines = EIP97IES | EIP197B | EIP197D,
+	.alg.aead = {
+		.setkey = safexcel_aead_aes_setkey,
+		.encrypt = safexcel_aead_encrypt,
+		.decrypt = safexcel_aead_decrypt,
+		.ivsize = AES_BLOCK_SIZE,
+		.maxauthsize = SHA512_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sha512),cbc(aes))",
+			.cra_driver_name = "safexcel-authenc-hmac-sha512-cbc-aes",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sha512_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_aead_sha384_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_cra_init(tfm);
+	ctx->hash_alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA384;
+	ctx->state_sz = SHA512_DIGEST_SIZE;
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sha384_cbc_aes = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.engines = EIP97IES | EIP197B | EIP197D,
+	.alg.aead = {
+		.setkey = safexcel_aead_aes_setkey,
+		.encrypt = safexcel_aead_encrypt,
+		.decrypt = safexcel_aead_decrypt,
+		.ivsize = AES_BLOCK_SIZE,
+		.maxauthsize = SHA384_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sha384),cbc(aes))",
+			.cra_driver_name = "safexcel-authenc-hmac-sha384-cbc-aes",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sha384_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index c77b0e1655a8..ac9282c1a5ec 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -1,14 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2017 Marvell
  *
  * Antoine Tenart <antoine.tenart@free-electrons.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 
 #include <crypto/hmac.h>
+#include <crypto/md5.h>
 #include <crypto/sha.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
@@ -22,8 +20,8 @@ struct safexcel_ahash_ctx {
 
 	u32 alg;
 
-	u32 ipad[SHA256_DIGEST_SIZE / sizeof(u32)];
-	u32 opad[SHA256_DIGEST_SIZE / sizeof(u32)];
+	u32 ipad[SHA512_DIGEST_SIZE / sizeof(u32)];
+	u32 opad[SHA512_DIGEST_SIZE / sizeof(u32)];
 };
 
 struct safexcel_ahash_req {
@@ -38,18 +36,26 @@ struct safexcel_ahash_req {
 	u32 digest;
 
 	u8 state_sz;    /* expected sate size, only set once */
-	u32 state[SHA256_DIGEST_SIZE / sizeof(u32)] __aligned(sizeof(u32));
+	u32 state[SHA512_DIGEST_SIZE / sizeof(u32)] __aligned(sizeof(u32));
 
-	u64 len;
-	u64 processed;
+	u64 len[2];
+	u64 processed[2];
 
-	u8 cache[SHA256_BLOCK_SIZE] __aligned(sizeof(u32));
+	u8 cache[SHA512_BLOCK_SIZE] __aligned(sizeof(u32));
 	dma_addr_t cache_dma;
 	unsigned int cache_sz;
 
-	u8 cache_next[SHA256_BLOCK_SIZE] __aligned(sizeof(u32));
+	u8 cache_next[SHA512_BLOCK_SIZE] __aligned(sizeof(u32));
 };
 
+static inline u64 safexcel_queued_len(struct safexcel_ahash_req *req)
+{
+	if (req->len[1] > req->processed[1])
+		return 0xffffffff - (req->len[0] - req->processed[0]);
+
+	return req->len[0] - req->processed[0];
+}
+
 static void safexcel_hash_token(struct safexcel_command_desc *cdesc,
 				u32 input_length, u32 result_length)
 {
@@ -72,9 +78,9 @@ static void safexcel_hash_token(struct safexcel_command_desc *cdesc,
 static void safexcel_context_control(struct safexcel_ahash_ctx *ctx,
 				     struct safexcel_ahash_req *req,
 				     struct safexcel_command_desc *cdesc,
-				     unsigned int digestsize,
-				     unsigned int blocksize)
+				     unsigned int digestsize)
 {
+	struct safexcel_crypto_priv *priv = ctx->priv;
 	int i;
 
 	cdesc->control_data.control0 |= CONTEXT_CONTROL_TYPE_HASH_OUT;
@@ -82,12 +88,17 @@ static void safexcel_context_control(struct safexcel_ahash_ctx *ctx,
 	cdesc->control_data.control0 |= req->digest;
 
 	if (req->digest == CONTEXT_CONTROL_DIGEST_PRECOMPUTED) {
-		if (req->processed) {
-			if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA1)
+		if (req->processed[0] || req->processed[1]) {
+			if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_MD5)
+				cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(5);
+			else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA1)
 				cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(6);
 			else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA224 ||
 				 ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA256)
 				cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(9);
+			else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA384 ||
+				 ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA512)
+				cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(17);
 
 			cdesc->control_data.control1 |= CONTEXT_CONTROL_DIGEST_CNT;
 		} else {
@@ -102,12 +113,28 @@ static void safexcel_context_control(struct safexcel_ahash_ctx *ctx,
 		 * fields. Do this now as we need it to setup the first command
 		 * descriptor.
 		 */
-		if (req->processed) {
+		if (req->processed[0] || req->processed[1]) {
 			for (i = 0; i < digestsize / sizeof(u32); i++)
 				ctx->base.ctxr->data[i] = cpu_to_le32(req->state[i]);
 
-			if (req->finish)
-				ctx->base.ctxr->data[i] = cpu_to_le32(req->processed / blocksize);
+			if (req->finish) {
+				u64 count = req->processed[0] / EIP197_COUNTER_BLOCK_SIZE;
+				count += ((0xffffffff / EIP197_COUNTER_BLOCK_SIZE) *
+					  req->processed[1]);
+
+				/* This is a haredware limitation, as the
+				 * counter must fit into an u32. This represents
+				 * a farily big amount of input data, so we
+				 * shouldn't see this.
+				 */
+				if (unlikely(count & 0xffff0000)) {
+					dev_warn(priv->dev,
+						 "Input data is too big\n");
+					return;
+				}
+
+				ctx->base.ctxr->data[i] = cpu_to_le32(count);
+			}
 		}
 	} else if (req->digest == CONTEXT_CONTROL_DIGEST_HMAC) {
 		cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(2 * req->state_sz / sizeof(u32));
@@ -126,11 +153,10 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 	struct ahash_request *areq = ahash_request_cast(async);
 	struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq);
 	struct safexcel_ahash_req *sreq = ahash_request_ctx(areq);
-	int cache_len;
+	u64 cache_len;
 
 	*ret = 0;
 
-	spin_lock_bh(&priv->ring[ring].egress_lock);
 	rdesc = safexcel_ring_next_rptr(priv, &priv->ring[ring].rdr);
 	if (IS_ERR(rdesc)) {
 		dev_err(priv->dev,
@@ -141,7 +167,6 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 	}
 
 	safexcel_complete(priv, ring);
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
 
 	if (sreq->nents) {
 		dma_unmap_sg(priv->dev, areq->src, sreq->nents, DMA_TO_DEVICE);
@@ -164,7 +189,7 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 		memcpy(areq->result, sreq->state,
 		       crypto_ahash_digestsize(ahash));
 
-	cache_len = sreq->len - sreq->processed;
+	cache_len = safexcel_queued_len(sreq);
 	if (cache_len)
 		memcpy(sreq->cache, sreq->cache_next, cache_len);
 
@@ -174,7 +199,6 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 }
 
 static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
-				   struct safexcel_request *request,
 				   int *commands, int *results)
 {
 	struct ahash_request *areq = ahash_request_cast(async);
@@ -185,9 +209,10 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
 	struct safexcel_command_desc *cdesc, *first_cdesc = NULL;
 	struct safexcel_result_desc *rdesc;
 	struct scatterlist *sg;
-	int i, queued, len, cache_len, extra, n_cdesc = 0, ret = 0;
+	int i, extra, n_cdesc = 0, ret = 0;
+	u64 queued, len, cache_len;
 
-	queued = len = req->len - req->processed;
+	queued = len = safexcel_queued_len(req);
 	if (queued <= crypto_ahash_blocksize(ahash))
 		cache_len = queued;
 	else
@@ -220,16 +245,12 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
 		}
 	}
 
-	spin_lock_bh(&priv->ring[ring].egress_lock);
-
 	/* Add a command descriptor for the cached data, if any */
 	if (cache_len) {
 		req->cache_dma = dma_map_single(priv->dev, req->cache,
 						cache_len, DMA_TO_DEVICE);
-		if (dma_mapping_error(priv->dev, req->cache_dma)) {
-			spin_unlock_bh(&priv->ring[ring].egress_lock);
+		if (dma_mapping_error(priv->dev, req->cache_dma))
 			return -EINVAL;
-		}
 
 		req->cache_sz = cache_len;
 		first_cdesc = safexcel_add_cdesc(priv, ring, 1,
@@ -260,7 +281,7 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
 		int sglen = sg_dma_len(sg);
 
 		/* Do not overflow the request */
-		if (queued - sglen < 0)
+		if (queued < sglen)
 			sglen = queued;
 
 		cdesc = safexcel_add_cdesc(priv, ring, !n_cdesc,
@@ -282,8 +303,7 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
 
 send_command:
 	/* Setup the context options */
-	safexcel_context_control(ctx, req, first_cdesc, req->state_sz,
-				 crypto_ahash_blocksize(ahash));
+	safexcel_context_control(ctx, req, first_cdesc, req->state_sz);
 
 	/* Add the token */
 	safexcel_hash_token(first_cdesc, len, req->state_sz);
@@ -303,10 +323,11 @@ send_command:
 		goto unmap_result;
 	}
 
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
+	safexcel_rdr_req_set(priv, ring, rdesc, &areq->base);
 
-	req->processed += len;
-	request->req = &areq->base;
+	req->processed[0] += len;
+	if (req->processed[0] < len)
+		req->processed[1]++;
 
 	*commands = n_cdesc;
 	*results = 1;
@@ -327,7 +348,6 @@ unmap_cache:
 		req->cache_sz = 0;
 	}
 
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
 	return ret;
 }
 
@@ -335,16 +355,18 @@ static inline bool safexcel_ahash_needs_inv_get(struct ahash_request *areq)
 {
 	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
 	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
-	struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq);
 	unsigned int state_w_sz = req->state_sz / sizeof(u32);
+	u64 processed;
 	int i;
 
+	processed = req->processed[0] / EIP197_COUNTER_BLOCK_SIZE;
+	processed += (0xffffffff / EIP197_COUNTER_BLOCK_SIZE) * req->processed[1];
+
 	for (i = 0; i < state_w_sz; i++)
 		if (ctx->base.ctxr->data[i] != cpu_to_le32(req->state[i]))
 			return true;
 
-	if (ctx->base.ctxr->data[state_w_sz] !=
-	    cpu_to_le32(req->processed / crypto_ahash_blocksize(ahash)))
+	if (ctx->base.ctxr->data[state_w_sz] != cpu_to_le32(processed))
 		return true;
 
 	return false;
@@ -363,21 +385,16 @@ static int safexcel_handle_inv_result(struct safexcel_crypto_priv *priv,
 
 	*ret = 0;
 
-	spin_lock_bh(&priv->ring[ring].egress_lock);
 	rdesc = safexcel_ring_next_rptr(priv, &priv->ring[ring].rdr);
 	if (IS_ERR(rdesc)) {
 		dev_err(priv->dev,
 			"hash: invalidate: could not retrieve the result descriptor\n");
 		*ret = PTR_ERR(rdesc);
-	} else if (rdesc->result_data.error_code) {
-		dev_err(priv->dev,
-			"hash: invalidate: result descriptor error (%d)\n",
-			rdesc->result_data.error_code);
-		*ret = -EINVAL;
+	} else {
+		*ret = safexcel_rdesc_check_errors(priv, rdesc);
 	}
 
 	safexcel_complete(priv, ring);
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
 
 	if (ctx->base.exit_inv) {
 		dma_pool_free(priv->context_pool, ctx->base.ctxr,
@@ -413,7 +430,7 @@ static int safexcel_handle_result(struct safexcel_crypto_priv *priv, int ring,
 	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
 	int err;
 
-	BUG_ON(priv->version == EIP97 && req->needs_inv);
+	BUG_ON(!(priv->flags & EIP197_TRC_CACHE) && req->needs_inv);
 
 	if (req->needs_inv) {
 		req->needs_inv = false;
@@ -428,15 +445,14 @@ static int safexcel_handle_result(struct safexcel_crypto_priv *priv, int ring,
 }
 
 static int safexcel_ahash_send_inv(struct crypto_async_request *async,
-				   int ring, struct safexcel_request *request,
-				   int *commands, int *results)
+				   int ring, int *commands, int *results)
 {
 	struct ahash_request *areq = ahash_request_cast(async);
 	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
 	int ret;
 
 	ret = safexcel_invalidate_cache(async, ctx->priv,
-					ctx->base.ctxr_dma, ring, request);
+					ctx->base.ctxr_dma, ring);
 	if (unlikely(ret))
 		return ret;
 
@@ -447,19 +463,17 @@ static int safexcel_ahash_send_inv(struct crypto_async_request *async,
 }
 
 static int safexcel_ahash_send(struct crypto_async_request *async,
-			       int ring, struct safexcel_request *request,
-			       int *commands, int *results)
+			       int ring, int *commands, int *results)
 {
 	struct ahash_request *areq = ahash_request_cast(async);
 	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
 	int ret;
 
 	if (req->needs_inv)
-		ret = safexcel_ahash_send_inv(async, ring, request,
-					      commands, results);
+		ret = safexcel_ahash_send_inv(async, ring, commands, results);
 	else
-		ret = safexcel_ahash_send_req(async, ring, request,
-					      commands, results);
+		ret = safexcel_ahash_send_req(async, ring, commands, results);
+
 	return ret;
 }
 
@@ -509,17 +523,17 @@ static int safexcel_ahash_cache(struct ahash_request *areq)
 {
 	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
 	struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq);
-	int queued, cache_len;
+	u64 queued, cache_len;
 
-	/* cache_len: everyting accepted by the driver but not sent yet,
-	 * tot sz handled by update() - last req sz - tot sz handled by send()
-	 */
-	cache_len = req->len - areq->nbytes - req->processed;
 	/* queued: everything accepted by the driver which will be handled by
 	 * the next send() calls.
 	 * tot sz handled by update() - tot sz handled by send()
 	 */
-	queued = req->len - req->processed;
+	queued = safexcel_queued_len(req);
+	/* cache_len: everything accepted by the driver but not sent yet,
+	 * tot sz handled by update() - last req sz - tot sz handled by send()
+	 */
+	cache_len = queued - areq->nbytes;
 
 	/*
 	 * In case there isn't enough bytes to proceed (less than a
@@ -546,8 +560,8 @@ static int safexcel_ahash_enqueue(struct ahash_request *areq)
 	req->needs_inv = false;
 
 	if (ctx->base.ctxr) {
-		if (priv->version == EIP197 &&
-		    !ctx->base.needs_inv && req->processed &&
+		if (priv->flags & EIP197_TRC_CACHE && !ctx->base.needs_inv &&
+		    (req->processed[0] || req->processed[1]) &&
 		    req->digest == CONTEXT_CONTROL_DIGEST_PRECOMPUTED)
 			/* We're still setting needs_inv here, even though it is
 			 * cleared right away, because the needs_inv flag can be
@@ -590,7 +604,9 @@ static int safexcel_ahash_update(struct ahash_request *areq)
 	if (!areq->nbytes)
 		return 0;
 
-	req->len += areq->nbytes;
+	req->len[0] += areq->nbytes;
+	if (req->len[0] < areq->nbytes)
+		req->len[1]++;
 
 	safexcel_ahash_cache(areq);
 
@@ -605,7 +621,7 @@ static int safexcel_ahash_update(struct ahash_request *areq)
 		return safexcel_ahash_enqueue(areq);
 
 	if (!req->last_req &&
-	    req->len - req->processed > crypto_ahash_blocksize(ahash))
+	    safexcel_queued_len(req) > crypto_ahash_blocksize(ahash))
 		return safexcel_ahash_enqueue(areq);
 
 	return 0;
@@ -620,8 +636,11 @@ static int safexcel_ahash_final(struct ahash_request *areq)
 	req->finish = true;
 
 	/* If we have an overall 0 length request */
-	if (!(req->len + areq->nbytes)) {
-		if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA1)
+	if (!req->len[0] && !req->len[1] && !areq->nbytes) {
+		if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_MD5)
+			memcpy(areq->result, md5_zero_message_hash,
+			       MD5_DIGEST_SIZE);
+		else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA1)
 			memcpy(areq->result, sha1_zero_message_hash,
 			       SHA1_DIGEST_SIZE);
 		else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA224)
@@ -630,6 +649,12 @@ static int safexcel_ahash_final(struct ahash_request *areq)
 		else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA256)
 			memcpy(areq->result, sha256_zero_message_hash,
 			       SHA256_DIGEST_SIZE);
+		else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA384)
+			memcpy(areq->result, sha384_zero_message_hash,
+			       SHA384_DIGEST_SIZE);
+		else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA512)
+			memcpy(areq->result, sha512_zero_message_hash,
+			       SHA512_DIGEST_SIZE);
 
 		return 0;
 	}
@@ -654,8 +679,10 @@ static int safexcel_ahash_export(struct ahash_request *areq, void *out)
 	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
 	struct safexcel_ahash_export_state *export = out;
 
-	export->len = req->len;
-	export->processed = req->processed;
+	export->len[0] = req->len[0];
+	export->len[1] = req->len[1];
+	export->processed[0] = req->processed[0];
+	export->processed[1] = req->processed[1];
 
 	export->digest = req->digest;
 
@@ -676,8 +703,10 @@ static int safexcel_ahash_import(struct ahash_request *areq, const void *in)
 	if (ret)
 		return ret;
 
-	req->len = export->len;
-	req->processed = export->processed;
+	req->len[0] = export->len[0];
+	req->len[1] = export->len[1];
+	req->processed[0] = export->processed[0];
+	req->processed[1] = export->processed[1];
 
 	req->digest = export->digest;
 
@@ -743,7 +772,7 @@ static void safexcel_ahash_cra_exit(struct crypto_tfm *tfm)
 	if (!ctx->base.ctxr)
 		return;
 
-	if (priv->version == EIP197) {
+	if (priv->flags & EIP197_TRC_CACHE) {
 		ret = safexcel_ahash_exit_inv(tfm);
 		if (ret)
 			dev_warn(priv->dev, "hash: invalidation error %d\n", ret);
@@ -755,6 +784,7 @@ static void safexcel_ahash_cra_exit(struct crypto_tfm *tfm)
 
 struct safexcel_alg_template safexcel_alg_sha1 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.ahash = {
 		.init = safexcel_sha1_init,
 		.update = safexcel_ahash_update,
@@ -908,8 +938,7 @@ int safexcel_hmac_setkey(const char *alg, const u8 *key, unsigned int keylen,
 	u8 *ipad, *opad;
 	int ret;
 
-	tfm = crypto_alloc_ahash(alg, CRYPTO_ALG_TYPE_AHASH,
-				 CRYPTO_ALG_TYPE_AHASH_MASK);
+	tfm = crypto_alloc_ahash(alg, 0, 0);
 	if (IS_ERR(tfm))
 		return PTR_ERR(tfm);
 
@@ -963,7 +992,7 @@ static int safexcel_hmac_alg_setkey(struct crypto_ahash *tfm, const u8 *key,
 	if (ret)
 		return ret;
 
-	if (priv->version == EIP197 && ctx->base.ctxr) {
+	if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr) {
 		for (i = 0; i < state_sz / sizeof(u32); i++) {
 			if (ctx->ipad[i] != le32_to_cpu(istate.state[i]) ||
 			    ctx->opad[i] != le32_to_cpu(ostate.state[i])) {
@@ -988,6 +1017,7 @@ static int safexcel_hmac_sha1_setkey(struct crypto_ahash *tfm, const u8 *key,
 
 struct safexcel_alg_template safexcel_alg_hmac_sha1 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.ahash = {
 		.init = safexcel_hmac_sha1_init,
 		.update = safexcel_ahash_update,
@@ -1051,6 +1081,7 @@ static int safexcel_sha256_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_sha256 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.ahash = {
 		.init = safexcel_sha256_init,
 		.update = safexcel_ahash_update,
@@ -1113,6 +1144,7 @@ static int safexcel_sha224_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_sha224 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.ahash = {
 		.init = safexcel_sha224_init,
 		.update = safexcel_ahash_update,
@@ -1168,6 +1200,7 @@ static int safexcel_hmac_sha224_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_hmac_sha224 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.ahash = {
 		.init = safexcel_hmac_sha224_init,
 		.update = safexcel_ahash_update,
@@ -1224,6 +1257,7 @@ static int safexcel_hmac_sha256_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_hmac_sha256 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.ahash = {
 		.init = safexcel_hmac_sha256_init,
 		.update = safexcel_ahash_update,
@@ -1251,3 +1285,375 @@ struct safexcel_alg_template safexcel_alg_hmac_sha256 = {
 		},
 	},
 };
+
+static int safexcel_sha512_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	req->state[0] = lower_32_bits(SHA512_H0);
+	req->state[1] = upper_32_bits(SHA512_H0);
+	req->state[2] = lower_32_bits(SHA512_H1);
+	req->state[3] = upper_32_bits(SHA512_H1);
+	req->state[4] = lower_32_bits(SHA512_H2);
+	req->state[5] = upper_32_bits(SHA512_H2);
+	req->state[6] = lower_32_bits(SHA512_H3);
+	req->state[7] = upper_32_bits(SHA512_H3);
+	req->state[8] = lower_32_bits(SHA512_H4);
+	req->state[9] = upper_32_bits(SHA512_H4);
+	req->state[10] = lower_32_bits(SHA512_H5);
+	req->state[11] = upper_32_bits(SHA512_H5);
+	req->state[12] = lower_32_bits(SHA512_H6);
+	req->state[13] = upper_32_bits(SHA512_H6);
+	req->state[14] = lower_32_bits(SHA512_H7);
+	req->state[15] = upper_32_bits(SHA512_H7);
+
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA512;
+	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
+	req->state_sz = SHA512_DIGEST_SIZE;
+
+	return 0;
+}
+
+static int safexcel_sha512_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_sha512_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_sha512 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B | EIP197D,
+	.alg.ahash = {
+		.init = safexcel_sha512_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_sha512_digest,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = SHA512_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "sha512",
+				.cra_driver_name = "safexcel-sha512",
+				.cra_priority = 300,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = SHA512_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_sha384_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	req->state[0] = lower_32_bits(SHA384_H0);
+	req->state[1] = upper_32_bits(SHA384_H0);
+	req->state[2] = lower_32_bits(SHA384_H1);
+	req->state[3] = upper_32_bits(SHA384_H1);
+	req->state[4] = lower_32_bits(SHA384_H2);
+	req->state[5] = upper_32_bits(SHA384_H2);
+	req->state[6] = lower_32_bits(SHA384_H3);
+	req->state[7] = upper_32_bits(SHA384_H3);
+	req->state[8] = lower_32_bits(SHA384_H4);
+	req->state[9] = upper_32_bits(SHA384_H4);
+	req->state[10] = lower_32_bits(SHA384_H5);
+	req->state[11] = upper_32_bits(SHA384_H5);
+	req->state[12] = lower_32_bits(SHA384_H6);
+	req->state[13] = upper_32_bits(SHA384_H6);
+	req->state[14] = lower_32_bits(SHA384_H7);
+	req->state[15] = upper_32_bits(SHA384_H7);
+
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA384;
+	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
+	req->state_sz = SHA512_DIGEST_SIZE;
+
+	return 0;
+}
+
+static int safexcel_sha384_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_sha384_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_sha384 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B | EIP197D,
+	.alg.ahash = {
+		.init = safexcel_sha384_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_sha384_digest,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = SHA384_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "sha384",
+				.cra_driver_name = "safexcel-sha384",
+				.cra_priority = 300,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = SHA384_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_hmac_sha512_setkey(struct crypto_ahash *tfm, const u8 *key,
+				       unsigned int keylen)
+{
+	return safexcel_hmac_alg_setkey(tfm, key, keylen, "safexcel-sha512",
+					SHA512_DIGEST_SIZE);
+}
+
+static int safexcel_hmac_sha512_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	safexcel_sha512_init(areq);
+	req->digest = CONTEXT_CONTROL_DIGEST_HMAC;
+	return 0;
+}
+
+static int safexcel_hmac_sha512_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_hmac_sha512_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_hmac_sha512 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B | EIP197D,
+	.alg.ahash = {
+		.init = safexcel_hmac_sha512_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_hmac_sha512_digest,
+		.setkey = safexcel_hmac_sha512_setkey,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = SHA512_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "hmac(sha512)",
+				.cra_driver_name = "safexcel-hmac-sha512",
+				.cra_priority = 300,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = SHA512_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_hmac_sha384_setkey(struct crypto_ahash *tfm, const u8 *key,
+				       unsigned int keylen)
+{
+	return safexcel_hmac_alg_setkey(tfm, key, keylen, "safexcel-sha384",
+					SHA512_DIGEST_SIZE);
+}
+
+static int safexcel_hmac_sha384_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	safexcel_sha384_init(areq);
+	req->digest = CONTEXT_CONTROL_DIGEST_HMAC;
+	return 0;
+}
+
+static int safexcel_hmac_sha384_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_hmac_sha384_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_hmac_sha384 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B | EIP197D,
+	.alg.ahash = {
+		.init = safexcel_hmac_sha384_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_hmac_sha384_digest,
+		.setkey = safexcel_hmac_sha384_setkey,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = SHA384_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "hmac(sha384)",
+				.cra_driver_name = "safexcel-hmac-sha384",
+				.cra_priority = 300,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = SHA384_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_md5_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	req->state[0] = MD5_H0;
+	req->state[1] = MD5_H1;
+	req->state[2] = MD5_H2;
+	req->state[3] = MD5_H3;
+
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_MD5;
+	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
+	req->state_sz = MD5_DIGEST_SIZE;
+
+	return 0;
+}
+
+static int safexcel_md5_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_md5_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_md5 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B | EIP197D,
+	.alg.ahash = {
+		.init = safexcel_md5_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_md5_digest,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = MD5_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "md5",
+				.cra_driver_name = "safexcel-md5",
+				.cra_priority = 300,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_hmac_md5_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	safexcel_md5_init(areq);
+	req->digest = CONTEXT_CONTROL_DIGEST_HMAC;
+	return 0;
+}
+
+static int safexcel_hmac_md5_setkey(struct crypto_ahash *tfm, const u8 *key,
+				     unsigned int keylen)
+{
+	return safexcel_hmac_alg_setkey(tfm, key, keylen, "safexcel-md5",
+					MD5_DIGEST_SIZE);
+}
+
+static int safexcel_hmac_md5_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_hmac_md5_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_hmac_md5 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B | EIP197D,
+	.alg.ahash = {
+		.init = safexcel_hmac_md5_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_hmac_md5_digest,
+		.setkey = safexcel_hmac_md5_setkey,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = MD5_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "hmac(md5)",
+				.cra_driver_name = "safexcel-hmac-md5",
+				.cra_priority = 300,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
diff --git a/drivers/crypto/inside-secure/safexcel_ring.c b/drivers/crypto/inside-secure/safexcel_ring.c
index c9d2a8716b5b..eb75fa684876 100644
--- a/drivers/crypto/inside-secure/safexcel_ring.c
+++ b/drivers/crypto/inside-secure/safexcel_ring.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2017 Marvell
  *
  * Antoine Tenart <antoine.tenart@free-electrons.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 
 #include <linux/dma-mapping.h>
@@ -14,8 +11,8 @@
 #include "safexcel.h"
 
 int safexcel_init_ring_descriptors(struct safexcel_crypto_priv *priv,
-				   struct safexcel_ring *cdr,
-				   struct safexcel_ring *rdr)
+				   struct safexcel_desc_ring *cdr,
+				   struct safexcel_desc_ring *rdr)
 {
 	cdr->offset = sizeof(u32) * priv->config.cd_offset;
 	cdr->base = dmam_alloc_coherent(priv->dev,
@@ -24,7 +21,7 @@ int safexcel_init_ring_descriptors(struct safexcel_crypto_priv *priv,
 	if (!cdr->base)
 		return -ENOMEM;
 	cdr->write = cdr->base;
-	cdr->base_end = cdr->base + cdr->offset * EIP197_DEFAULT_RING_SIZE;
+	cdr->base_end = cdr->base + cdr->offset * (EIP197_DEFAULT_RING_SIZE - 1);
 	cdr->read = cdr->base;
 
 	rdr->offset = sizeof(u32) * priv->config.rd_offset;
@@ -34,7 +31,7 @@ int safexcel_init_ring_descriptors(struct safexcel_crypto_priv *priv,
 	if (!rdr->base)
 		return -ENOMEM;
 	rdr->write = rdr->base;
-	rdr->base_end = rdr->base + rdr->offset * EIP197_DEFAULT_RING_SIZE;
+	rdr->base_end = rdr->base + rdr->offset  * (EIP197_DEFAULT_RING_SIZE - 1);
 	rdr->read = rdr->base;
 
 	return 0;
@@ -46,49 +43,73 @@ inline int safexcel_select_ring(struct safexcel_crypto_priv *priv)
 }
 
 static void *safexcel_ring_next_wptr(struct safexcel_crypto_priv *priv,
-				     struct safexcel_ring *ring)
+				     struct safexcel_desc_ring *ring)
 {
 	void *ptr = ring->write;
 
-	if (ring->nr == EIP197_DEFAULT_RING_SIZE - 1)
+	if ((ring->write == ring->read - ring->offset) ||
+	    (ring->read == ring->base && ring->write == ring->base_end))
 		return ERR_PTR(-ENOMEM);
 
-	ring->write += ring->offset;
 	if (ring->write == ring->base_end)
 		ring->write = ring->base;
+	else
+		ring->write += ring->offset;
 
-	ring->nr++;
 	return ptr;
 }
 
 void *safexcel_ring_next_rptr(struct safexcel_crypto_priv *priv,
-			      struct safexcel_ring *ring)
+			      struct safexcel_desc_ring *ring)
 {
 	void *ptr = ring->read;
 
-	if (!ring->nr)
+	if (ring->write == ring->read)
 		return ERR_PTR(-ENOENT);
 
-	ring->read += ring->offset;
 	if (ring->read == ring->base_end)
 		ring->read = ring->base;
+	else
+		ring->read += ring->offset;
 
-	ring->nr--;
 	return ptr;
 }
 
+inline void *safexcel_ring_curr_rptr(struct safexcel_crypto_priv *priv,
+				     int ring)
+{
+	struct safexcel_desc_ring *rdr = &priv->ring[ring].rdr;
+
+	return rdr->read;
+}
+
+inline int safexcel_ring_first_rdr_index(struct safexcel_crypto_priv *priv,
+					 int ring)
+{
+	struct safexcel_desc_ring *rdr = &priv->ring[ring].rdr;
+
+	return (rdr->read - rdr->base) / rdr->offset;
+}
+
+inline int safexcel_ring_rdr_rdesc_index(struct safexcel_crypto_priv *priv,
+					 int ring,
+					 struct safexcel_result_desc *rdesc)
+{
+	struct safexcel_desc_ring *rdr = &priv->ring[ring].rdr;
+
+	return ((void *)rdesc - rdr->base) / rdr->offset;
+}
+
 void safexcel_ring_rollback_wptr(struct safexcel_crypto_priv *priv,
-				 struct safexcel_ring *ring)
+				 struct safexcel_desc_ring *ring)
 {
-	if (!ring->nr)
+	if (ring->write == ring->read)
 		return;
 
 	if (ring->write == ring->base)
-		ring->write = ring->base_end - ring->offset;
+		ring->write = ring->base_end;
 	else
 		ring->write -= ring->offset;
-
-	ring->nr--;
 }
 
 struct safexcel_command_desc *safexcel_add_cdesc(struct safexcel_crypto_priv *priv,
diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c
index e34d80b6b7e5..99ff54cc8a15 100644
--- a/drivers/crypto/marvell/hash.c
+++ b/drivers/crypto/marvell/hash.c
@@ -1183,8 +1183,7 @@ static int mv_cesa_ahmac_setkey(const char *hash_alg_name,
 	u8 *opad;
 	int ret;
 
-	tfm = crypto_alloc_ahash(hash_alg_name, CRYPTO_ALG_TYPE_AHASH,
-				 CRYPTO_ALG_TYPE_AHASH_MASK);
+	tfm = crypto_alloc_ahash(hash_alg_name, 0, 0);
 	if (IS_ERR(tfm))
 		return PTR_ERR(tfm);
 
diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c
index ab6235b7ff22..55f34cfc43ff 100644
--- a/drivers/crypto/n2_core.c
+++ b/drivers/crypto/n2_core.c
@@ -1487,8 +1487,7 @@ static int __n2_register_one_ahash(const struct n2_hash_tmpl *tmpl)
 	snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "%s", tmpl->name);
 	snprintf(base->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s-n2", tmpl->name);
 	base->cra_priority = N2_CRA_PRIORITY;
-	base->cra_flags = CRYPTO_ALG_TYPE_AHASH |
-			  CRYPTO_ALG_KERN_DRIVER_ONLY |
+	base->cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY |
 			  CRYPTO_ALG_NEED_FALLBACK;
 	base->cra_blocksize = tmpl->block_size;
 	base->cra_ctxsize = sizeof(struct n2_hash_ctx);
diff --git a/drivers/crypto/nx/nx-aes-xcbc.c b/drivers/crypto/nx/nx-aes-xcbc.c
index c2f7d4befb55..ad3358e74f5c 100644
--- a/drivers/crypto/nx/nx-aes-xcbc.c
+++ b/drivers/crypto/nx/nx-aes-xcbc.c
@@ -386,7 +386,6 @@ struct shash_alg nx_shash_aes_xcbc_alg = {
 		.cra_name        = "xcbc(aes)",
 		.cra_driver_name = "xcbc-aes-nx",
 		.cra_priority    = 300,
-		.cra_flags       = CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize   = AES_BLOCK_SIZE,
 		.cra_module      = THIS_MODULE,
 		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
diff --git a/drivers/crypto/nx/nx-sha256.c b/drivers/crypto/nx/nx-sha256.c
index becb738c897b..a6764af83c6d 100644
--- a/drivers/crypto/nx/nx-sha256.c
+++ b/drivers/crypto/nx/nx-sha256.c
@@ -288,7 +288,6 @@ struct shash_alg nx_shash_sha256_alg = {
 		.cra_name        = "sha256",
 		.cra_driver_name = "sha256-nx",
 		.cra_priority    = 300,
-		.cra_flags       = CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize   = SHA256_BLOCK_SIZE,
 		.cra_module      = THIS_MODULE,
 		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
diff --git a/drivers/crypto/nx/nx-sha512.c b/drivers/crypto/nx/nx-sha512.c
index b6e183d58d73..92956bc6e45e 100644
--- a/drivers/crypto/nx/nx-sha512.c
+++ b/drivers/crypto/nx/nx-sha512.c
@@ -294,7 +294,6 @@ struct shash_alg nx_shash_sha512_alg = {
 		.cra_name        = "sha512",
 		.cra_driver_name = "sha512-nx",
 		.cra_priority    = 300,
-		.cra_flags       = CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize   = SHA512_BLOCK_SIZE,
 		.cra_module      = THIS_MODULE,
 		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c
index d1a1c74fb56a..0641185bd82f 100644
--- a/drivers/crypto/omap-sham.c
+++ b/drivers/crypto/omap-sham.c
@@ -1464,8 +1464,7 @@ static struct ahash_alg algs_sha1_md5[] = {
 		.cra_name		= "sha1",
 		.cra_driver_name	= "omap-sha1",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_KERN_DRIVER_ONLY |
+		.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA1_BLOCK_SIZE,
@@ -1487,8 +1486,7 @@ static struct ahash_alg algs_sha1_md5[] = {
 		.cra_name		= "md5",
 		.cra_driver_name	= "omap-md5",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_KERN_DRIVER_ONLY |
+		.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA1_BLOCK_SIZE,
@@ -1511,8 +1509,7 @@ static struct ahash_alg algs_sha1_md5[] = {
 		.cra_name		= "hmac(sha1)",
 		.cra_driver_name	= "omap-hmac-sha1",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_KERN_DRIVER_ONLY |
+		.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA1_BLOCK_SIZE,
@@ -1536,8 +1533,7 @@ static struct ahash_alg algs_sha1_md5[] = {
 		.cra_name		= "hmac(md5)",
 		.cra_driver_name	= "omap-hmac-md5",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_KERN_DRIVER_ONLY |
+		.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA1_BLOCK_SIZE,
@@ -1564,8 +1560,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 		.cra_name		= "sha224",
 		.cra_driver_name	= "omap-sha224",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA224_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct omap_sham_ctx),
@@ -1586,8 +1581,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 		.cra_name		= "sha256",
 		.cra_driver_name	= "omap-sha256",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA256_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct omap_sham_ctx),
@@ -1609,8 +1603,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 		.cra_name		= "hmac(sha224)",
 		.cra_driver_name	= "omap-hmac-sha224",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA224_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct omap_sham_ctx) +
@@ -1633,8 +1626,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 		.cra_name		= "hmac(sha256)",
 		.cra_driver_name	= "omap-hmac-sha256",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA256_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct omap_sham_ctx) +
@@ -1659,8 +1651,7 @@ static struct ahash_alg algs_sha384_sha512[] = {
 		.cra_name		= "sha384",
 		.cra_driver_name	= "omap-sha384",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA384_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct omap_sham_ctx),
@@ -1681,8 +1672,7 @@ static struct ahash_alg algs_sha384_sha512[] = {
 		.cra_name		= "sha512",
 		.cra_driver_name	= "omap-sha512",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA512_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct omap_sham_ctx),
@@ -1704,8 +1694,7 @@ static struct ahash_alg algs_sha384_sha512[] = {
 		.cra_name		= "hmac(sha384)",
 		.cra_driver_name	= "omap-hmac-sha384",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA384_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct omap_sham_ctx) +
@@ -1728,8 +1717,7 @@ static struct ahash_alg algs_sha384_sha512[] = {
 		.cra_name		= "hmac(sha512)",
 		.cra_driver_name	= "omap-hmac-sha512",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA512_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct omap_sham_ctx) +
diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c
index d32c79328876..21e5cae0a1e0 100644
--- a/drivers/crypto/padlock-sha.c
+++ b/drivers/crypto/padlock-sha.c
@@ -247,8 +247,7 @@ static struct shash_alg sha1_alg = {
 		.cra_name		=	"sha1",
 		.cra_driver_name	=	"sha1-padlock",
 		.cra_priority		=	PADLOCK_CRA_PRIORITY,
-		.cra_flags		=	CRYPTO_ALG_TYPE_SHASH |
-						CRYPTO_ALG_NEED_FALLBACK,
+		.cra_flags		=	CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		=	SHA1_BLOCK_SIZE,
 		.cra_ctxsize		=	sizeof(struct padlock_sha_ctx),
 		.cra_module		=	THIS_MODULE,
@@ -271,8 +270,7 @@ static struct shash_alg sha256_alg = {
 		.cra_name		=	"sha256",
 		.cra_driver_name	=	"sha256-padlock",
 		.cra_priority		=	PADLOCK_CRA_PRIORITY,
-		.cra_flags		=	CRYPTO_ALG_TYPE_SHASH |
-						CRYPTO_ALG_NEED_FALLBACK,
+		.cra_flags		=	CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		=	SHA256_BLOCK_SIZE,
 		.cra_ctxsize		=	sizeof(struct padlock_sha_ctx),
 		.cra_module		=	THIS_MODULE,
@@ -484,7 +482,6 @@ static struct shash_alg sha1_alg_nano = {
 		.cra_name		=	"sha1",
 		.cra_driver_name	=	"sha1-padlock-nano",
 		.cra_priority		=	PADLOCK_CRA_PRIORITY,
-		.cra_flags		=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		=	SHA1_BLOCK_SIZE,
 		.cra_module		=	THIS_MODULE,
 	}
@@ -503,7 +500,6 @@ static struct shash_alg sha256_alg_nano = {
 		.cra_name		=	"sha256",
 		.cra_driver_name	=	"sha256-padlock-nano",
 		.cra_priority		=	PADLOCK_CRA_PRIORITY,
-		.cra_flags		=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		=	SHA256_BLOCK_SIZE,
 		.cra_module		=	THIS_MODULE,
 	}
diff --git a/drivers/crypto/qat/qat_common/adf_aer.c b/drivers/crypto/qat/qat_common/adf_aer.c
index da8a2d3b5e9a..9225d060e18f 100644
--- a/drivers/crypto/qat/qat_common/adf_aer.c
+++ b/drivers/crypto/qat/qat_common/adf_aer.c
@@ -163,7 +163,7 @@ static int adf_dev_aer_schedule_reset(struct adf_accel_dev *accel_dev,
 		return 0;
 
 	set_bit(ADF_STATUS_RESTARTING, &accel_dev->status);
-	reset_data = kzalloc(sizeof(*reset_data), GFP_ATOMIC);
+	reset_data = kzalloc(sizeof(*reset_data), GFP_KERNEL);
 	if (!reset_data)
 		return -ENOMEM;
 	reset_data->accel_dev = accel_dev;
diff --git a/drivers/crypto/qce/sha.c b/drivers/crypto/qce/sha.c
index 53227d70d397..d8a5db11b7ea 100644
--- a/drivers/crypto/qce/sha.c
+++ b/drivers/crypto/qce/sha.c
@@ -378,8 +378,7 @@ static int qce_ahash_hmac_setkey(struct crypto_ahash *tfm, const u8 *key,
 	else
 		return -EINVAL;
 
-	ahash_tfm = crypto_alloc_ahash(alg_name, CRYPTO_ALG_TYPE_AHASH,
-				       CRYPTO_ALG_TYPE_AHASH_MASK);
+	ahash_tfm = crypto_alloc_ahash(alg_name, 0, 0);
 	if (IS_ERR(ahash_tfm))
 		return PTR_ERR(ahash_tfm);
 
diff --git a/drivers/crypto/qcom-rng.c b/drivers/crypto/qcom-rng.c
new file mode 100644
index 000000000000..e54249ccc009
--- /dev/null
+++ b/drivers/crypto/qcom-rng.c
@@ -0,0 +1,229 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2017-18 Linaro Limited
+//
+// Based on msm-rng.c and downstream driver
+
+#include <crypto/internal/rng.h>
+#include <linux/acpi.h>
+#include <linux/clk.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+/* Device specific register offsets */
+#define PRNG_DATA_OUT		0x0000
+#define PRNG_STATUS		0x0004
+#define PRNG_LFSR_CFG		0x0100
+#define PRNG_CONFIG		0x0104
+
+/* Device specific register masks and config values */
+#define PRNG_LFSR_CFG_MASK	0x0000ffff
+#define PRNG_LFSR_CFG_CLOCKS	0x0000dddd
+#define PRNG_CONFIG_HW_ENABLE	BIT(1)
+#define PRNG_STATUS_DATA_AVAIL	BIT(0)
+
+#define WORD_SZ			4
+
+struct qcom_rng {
+	struct mutex lock;
+	void __iomem *base;
+	struct clk *clk;
+	unsigned int skip_init;
+};
+
+struct qcom_rng_ctx {
+	struct qcom_rng *rng;
+};
+
+static struct qcom_rng *qcom_rng_dev;
+
+static int qcom_rng_read(struct qcom_rng *rng, u8 *data, unsigned int max)
+{
+	unsigned int currsize = 0;
+	u32 val;
+
+	/* read random data from hardware */
+	do {
+		val = readl_relaxed(rng->base + PRNG_STATUS);
+		if (!(val & PRNG_STATUS_DATA_AVAIL))
+			break;
+
+		val = readl_relaxed(rng->base + PRNG_DATA_OUT);
+		if (!val)
+			break;
+
+		if ((max - currsize) >= WORD_SZ) {
+			memcpy(data, &val, WORD_SZ);
+			data += WORD_SZ;
+			currsize += WORD_SZ;
+		} else {
+			/* copy only remaining bytes */
+			memcpy(data, &val, max - currsize);
+			break;
+		}
+	} while (currsize < max);
+
+	return currsize;
+}
+
+static int qcom_rng_generate(struct crypto_rng *tfm,
+			     const u8 *src, unsigned int slen,
+			     u8 *dstn, unsigned int dlen)
+{
+	struct qcom_rng_ctx *ctx = crypto_rng_ctx(tfm);
+	struct qcom_rng *rng = ctx->rng;
+	int ret;
+
+	ret = clk_prepare_enable(rng->clk);
+	if (ret)
+		return ret;
+
+	mutex_lock(&rng->lock);
+
+	ret = qcom_rng_read(rng, dstn, dlen);
+
+	mutex_unlock(&rng->lock);
+	clk_disable_unprepare(rng->clk);
+
+	return 0;
+}
+
+static int qcom_rng_seed(struct crypto_rng *tfm, const u8 *seed,
+			 unsigned int slen)
+{
+	return 0;
+}
+
+static int qcom_rng_enable(struct qcom_rng *rng)
+{
+	u32 val;
+	int ret;
+
+	ret = clk_prepare_enable(rng->clk);
+	if (ret)
+		return ret;
+
+	/* Enable PRNG only if it is not already enabled */
+	val = readl_relaxed(rng->base + PRNG_CONFIG);
+	if (val & PRNG_CONFIG_HW_ENABLE)
+		goto already_enabled;
+
+	val = readl_relaxed(rng->base + PRNG_LFSR_CFG);
+	val &= ~PRNG_LFSR_CFG_MASK;
+	val |= PRNG_LFSR_CFG_CLOCKS;
+	writel(val, rng->base + PRNG_LFSR_CFG);
+
+	val = readl_relaxed(rng->base + PRNG_CONFIG);
+	val |= PRNG_CONFIG_HW_ENABLE;
+	writel(val, rng->base + PRNG_CONFIG);
+
+already_enabled:
+	clk_disable_unprepare(rng->clk);
+
+	return 0;
+}
+
+static int qcom_rng_init(struct crypto_tfm *tfm)
+{
+	struct qcom_rng_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ctx->rng = qcom_rng_dev;
+
+	if (!ctx->rng->skip_init)
+		return qcom_rng_enable(ctx->rng);
+
+	return 0;
+}
+
+static struct rng_alg qcom_rng_alg = {
+	.generate	= qcom_rng_generate,
+	.seed		= qcom_rng_seed,
+	.seedsize	= 0,
+	.base		= {
+		.cra_name		= "stdrng",
+		.cra_driver_name	= "qcom-rng",
+		.cra_flags		= CRYPTO_ALG_TYPE_RNG,
+		.cra_priority		= 300,
+		.cra_ctxsize		= sizeof(struct qcom_rng_ctx),
+		.cra_module		= THIS_MODULE,
+		.cra_init		= qcom_rng_init,
+	}
+};
+
+static int qcom_rng_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+	struct qcom_rng *rng;
+	int ret;
+
+	rng = devm_kzalloc(&pdev->dev, sizeof(*rng), GFP_KERNEL);
+	if (!rng)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, rng);
+	mutex_init(&rng->lock);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	rng->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(rng->base))
+		return PTR_ERR(rng->base);
+
+	/* ACPI systems have clk already on, so skip clk_get */
+	if (!has_acpi_companion(&pdev->dev)) {
+		rng->clk = devm_clk_get(&pdev->dev, "core");
+		if (IS_ERR(rng->clk))
+			return PTR_ERR(rng->clk);
+	}
+
+
+	rng->skip_init = (unsigned long)device_get_match_data(&pdev->dev);
+
+	qcom_rng_dev = rng;
+	ret = crypto_register_rng(&qcom_rng_alg);
+	if (ret) {
+		dev_err(&pdev->dev, "Register crypto rng failed: %d\n", ret);
+		qcom_rng_dev = NULL;
+	}
+
+	return ret;
+}
+
+static int qcom_rng_remove(struct platform_device *pdev)
+{
+	crypto_unregister_rng(&qcom_rng_alg);
+
+	qcom_rng_dev = NULL;
+
+	return 0;
+}
+
+#if IS_ENABLED(CONFIG_ACPI)
+static const struct acpi_device_id qcom_rng_acpi_match[] = {
+	{ .id = "QCOM8160", .driver_data = 1 },
+	{}
+};
+MODULE_DEVICE_TABLE(acpi, qcom_rng_acpi_match);
+#endif
+
+static const struct of_device_id qcom_rng_of_match[] = {
+	{ .compatible = "qcom,prng", .data = (void *)0},
+	{ .compatible = "qcom,prng-ee", .data = (void *)1},
+	{}
+};
+MODULE_DEVICE_TABLE(of, qcom_rng_of_match);
+
+static struct platform_driver qcom_rng_driver = {
+	.probe = qcom_rng_probe,
+	.remove =  qcom_rng_remove,
+	.driver = {
+		.name = KBUILD_MODNAME,
+		.of_match_table = of_match_ptr(qcom_rng_of_match),
+		.acpi_match_table = ACPI_PTR(qcom_rng_acpi_match),
+	}
+};
+module_platform_driver(qcom_rng_driver);
+
+MODULE_ALIAS("platform:" KBUILD_MODNAME);
+MODULE_DESCRIPTION("Qualcomm random number generator driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c
index bf7163042569..faa282074e5a 100644
--- a/drivers/crypto/s5p-sss.c
+++ b/drivers/crypto/s5p-sss.c
@@ -1765,8 +1765,7 @@ static struct ahash_alg algs_sha1_md5_sha256[] = {
 		.cra_name		= "sha1",
 		.cra_driver_name	= "exynos-sha1",
 		.cra_priority		= 100,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-					  CRYPTO_ALG_KERN_DRIVER_ONLY |
+		.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
 					  CRYPTO_ALG_ASYNC |
 					  CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= HASH_BLOCK_SIZE,
@@ -1791,8 +1790,7 @@ static struct ahash_alg algs_sha1_md5_sha256[] = {
 		.cra_name		= "md5",
 		.cra_driver_name	= "exynos-md5",
 		.cra_priority		= 100,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-					  CRYPTO_ALG_KERN_DRIVER_ONLY |
+		.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
 					  CRYPTO_ALG_ASYNC |
 					  CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= HASH_BLOCK_SIZE,
@@ -1817,8 +1815,7 @@ static struct ahash_alg algs_sha1_md5_sha256[] = {
 		.cra_name		= "sha256",
 		.cra_driver_name	= "exynos-sha256",
 		.cra_priority		= 100,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-					  CRYPTO_ALG_KERN_DRIVER_ONLY |
+		.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
 					  CRYPTO_ALG_ASYNC |
 					  CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= HASH_BLOCK_SIZE,
diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index 0f2245e1af2b..e7540a5b8197 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -1253,8 +1253,7 @@ static struct ahash_alg sha_v3_algs[] = {
 		.cra_name		= "sha1",
 		.cra_driver_name	= "sahara-sha1",
 		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA1_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct sahara_ctx),
@@ -1280,8 +1279,7 @@ static struct ahash_alg sha_v4_algs[] = {
 		.cra_name		= "sha256",
 		.cra_driver_name	= "sahara-sha256",
 		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA256_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct sahara_ctx),
@@ -1351,7 +1349,7 @@ err_sha_v4_algs:
 
 err_sha_v3_algs:
 	for (j = 0; j < k; j++)
-		crypto_unregister_ahash(&sha_v4_algs[j]);
+		crypto_unregister_ahash(&sha_v3_algs[j]);
 
 err_aes_algs:
 	for (j = 0; j < i; j++)
@@ -1367,7 +1365,7 @@ static void sahara_unregister_algs(struct sahara_dev *dev)
 	for (i = 0; i < ARRAY_SIZE(aes_algs); i++)
 		crypto_unregister_alg(&aes_algs[i]);
 
-	for (i = 0; i < ARRAY_SIZE(sha_v4_algs); i++)
+	for (i = 0; i < ARRAY_SIZE(sha_v3_algs); i++)
 		crypto_unregister_ahash(&sha_v3_algs[i]);
 
 	if (dev->version > SAHARA_VERSION_3)
diff --git a/drivers/crypto/stm32/stm32-cryp.c b/drivers/crypto/stm32/stm32-cryp.c
index c5d3efc54a4f..23b0b7bd64c7 100644
--- a/drivers/crypto/stm32/stm32-cryp.c
+++ b/drivers/crypto/stm32/stm32-cryp.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/reset.h>
 
 #include <crypto/aes.h>
@@ -105,6 +106,7 @@
 #define GCM_CTR_INIT            2
 #define _walked_in              (cryp->in_walk.offset - cryp->in_sg->offset)
 #define _walked_out             (cryp->out_walk.offset - cryp->out_sg->offset)
+#define CRYP_AUTOSUSPEND_DELAY	50
 
 struct stm32_cryp_caps {
 	bool                    swap_final;
@@ -519,6 +521,8 @@ static int stm32_cryp_hw_init(struct stm32_cryp *cryp)
 	int ret;
 	u32 cfg, hw_mode;
 
+	pm_runtime_get_sync(cryp->dev);
+
 	/* Disable interrupt */
 	stm32_cryp_write(cryp, CRYP_IMSCR, 0);
 
@@ -638,6 +642,9 @@ static void stm32_cryp_finish_req(struct stm32_cryp *cryp, int err)
 		free_pages((unsigned long)buf_out, pages);
 	}
 
+	pm_runtime_mark_last_busy(cryp->dev);
+	pm_runtime_put_autosuspend(cryp->dev);
+
 	if (is_gcm(cryp) || is_ccm(cryp)) {
 		crypto_finalize_aead_request(cryp->engine, cryp->areq, err);
 		cryp->areq = NULL;
@@ -1969,6 +1976,13 @@ static int stm32_cryp_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	pm_runtime_set_autosuspend_delay(dev, CRYP_AUTOSUSPEND_DELAY);
+	pm_runtime_use_autosuspend(dev);
+
+	pm_runtime_get_noresume(dev);
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+
 	rst = devm_reset_control_get(dev, NULL);
 	if (!IS_ERR(rst)) {
 		reset_control_assert(rst);
@@ -2008,6 +2022,8 @@ static int stm32_cryp_probe(struct platform_device *pdev)
 
 	dev_info(dev, "Initialized\n");
 
+	pm_runtime_put_sync(dev);
+
 	return 0;
 
 err_aead_algs:
@@ -2020,6 +2036,11 @@ err_engine1:
 	list_del(&cryp->list);
 	spin_unlock(&cryp_list.lock);
 
+	pm_runtime_disable(dev);
+	pm_runtime_put_noidle(dev);
+	pm_runtime_disable(dev);
+	pm_runtime_put_noidle(dev);
+
 	clk_disable_unprepare(cryp->clk);
 
 	return ret;
@@ -2028,10 +2049,15 @@ err_engine1:
 static int stm32_cryp_remove(struct platform_device *pdev)
 {
 	struct stm32_cryp *cryp = platform_get_drvdata(pdev);
+	int ret;
 
 	if (!cryp)
 		return -ENODEV;
 
+	ret = pm_runtime_get_sync(cryp->dev);
+	if (ret < 0)
+		return ret;
+
 	crypto_unregister_aeads(aead_algs, ARRAY_SIZE(aead_algs));
 	crypto_unregister_algs(crypto_algs, ARRAY_SIZE(crypto_algs));
 
@@ -2041,16 +2067,52 @@ static int stm32_cryp_remove(struct platform_device *pdev)
 	list_del(&cryp->list);
 	spin_unlock(&cryp_list.lock);
 
+	pm_runtime_disable(cryp->dev);
+	pm_runtime_put_noidle(cryp->dev);
+
+	clk_disable_unprepare(cryp->clk);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int stm32_cryp_runtime_suspend(struct device *dev)
+{
+	struct stm32_cryp *cryp = dev_get_drvdata(dev);
+
 	clk_disable_unprepare(cryp->clk);
 
 	return 0;
 }
 
+static int stm32_cryp_runtime_resume(struct device *dev)
+{
+	struct stm32_cryp *cryp = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(cryp->clk);
+	if (ret) {
+		dev_err(cryp->dev, "Failed to prepare_enable clock\n");
+		return ret;
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops stm32_cryp_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+	SET_RUNTIME_PM_OPS(stm32_cryp_runtime_suspend,
+			   stm32_cryp_runtime_resume, NULL)
+};
+
 static struct platform_driver stm32_cryp_driver = {
 	.probe  = stm32_cryp_probe,
 	.remove = stm32_cryp_remove,
 	.driver = {
 		.name           = DRIVER_NAME,
+		.pm		= &stm32_cryp_pm_ops,
 		.of_match_table = stm32_dt_ids,
 	},
 };
diff --git a/drivers/crypto/stm32/stm32-hash.c b/drivers/crypto/stm32/stm32-hash.c
index cdc96f1bb917..590d7352837e 100644
--- a/drivers/crypto/stm32/stm32-hash.c
+++ b/drivers/crypto/stm32/stm32-hash.c
@@ -31,6 +31,7 @@
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/reset.h>
 
 #include <crypto/engine.h>
@@ -121,6 +122,8 @@ enum stm32_hash_data_format {
 #define HASH_QUEUE_LENGTH		16
 #define HASH_DMA_THRESHOLD		50
 
+#define HASH_AUTOSUSPEND_DELAY		50
+
 struct stm32_hash_ctx {
 	struct crypto_engine_ctx enginectx;
 	struct stm32_hash_dev	*hdev;
@@ -814,12 +817,17 @@ static void stm32_hash_finish_req(struct ahash_request *req, int err)
 		rctx->flags |= HASH_FLAGS_ERRORS;
 	}
 
+	pm_runtime_mark_last_busy(hdev->dev);
+	pm_runtime_put_autosuspend(hdev->dev);
+
 	crypto_finalize_hash_request(hdev->engine, req, err);
 }
 
 static int stm32_hash_hw_init(struct stm32_hash_dev *hdev,
 			      struct stm32_hash_request_ctx *rctx)
 {
+	pm_runtime_get_sync(hdev->dev);
+
 	if (!(HASH_FLAGS_INIT & hdev->flags)) {
 		stm32_hash_write(hdev, HASH_CR, HASH_CR_INIT);
 		stm32_hash_write(hdev, HASH_STR, 0);
@@ -967,6 +975,8 @@ static int stm32_hash_export(struct ahash_request *req, void *out)
 	u32 *preg;
 	unsigned int i;
 
+	pm_runtime_get_sync(hdev->dev);
+
 	while (!(stm32_hash_read(hdev, HASH_SR) & HASH_SR_DATA_INPUT_READY))
 		cpu_relax();
 
@@ -982,6 +992,9 @@ static int stm32_hash_export(struct ahash_request *req, void *out)
 	for (i = 0; i < HASH_CSR_REGISTER_NUMBER; i++)
 		*preg++ = stm32_hash_read(hdev, HASH_CSR(i));
 
+	pm_runtime_mark_last_busy(hdev->dev);
+	pm_runtime_put_autosuspend(hdev->dev);
+
 	memcpy(out, rctx, sizeof(*rctx));
 
 	return 0;
@@ -1000,6 +1013,8 @@ static int stm32_hash_import(struct ahash_request *req, const void *in)
 
 	preg = rctx->hw_context;
 
+	pm_runtime_get_sync(hdev->dev);
+
 	stm32_hash_write(hdev, HASH_IMR, *preg++);
 	stm32_hash_write(hdev, HASH_STR, *preg++);
 	stm32_hash_write(hdev, HASH_CR, *preg);
@@ -1009,6 +1024,9 @@ static int stm32_hash_import(struct ahash_request *req, const void *in)
 	for (i = 0; i < HASH_CSR_REGISTER_NUMBER; i++)
 		stm32_hash_write(hdev, HASH_CSR(i), *preg++);
 
+	pm_runtime_mark_last_busy(hdev->dev);
+	pm_runtime_put_autosuspend(hdev->dev);
+
 	kfree(rctx->hw_context);
 
 	return 0;
@@ -1132,8 +1150,7 @@ static struct ahash_alg algs_md5_sha1[] = {
 				.cra_name = "md5",
 				.cra_driver_name = "stm32-md5",
 				.cra_priority = 200,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					CRYPTO_ALG_ASYNC |
+				.cra_flags = CRYPTO_ALG_ASYNC |
 					CRYPTO_ALG_KERN_DRIVER_ONLY,
 				.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct stm32_hash_ctx),
@@ -1159,8 +1176,7 @@ static struct ahash_alg algs_md5_sha1[] = {
 				.cra_name = "hmac(md5)",
 				.cra_driver_name = "stm32-hmac-md5",
 				.cra_priority = 200,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					CRYPTO_ALG_ASYNC |
+				.cra_flags = CRYPTO_ALG_ASYNC |
 					CRYPTO_ALG_KERN_DRIVER_ONLY,
 				.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct stm32_hash_ctx),
@@ -1185,8 +1201,7 @@ static struct ahash_alg algs_md5_sha1[] = {
 				.cra_name = "sha1",
 				.cra_driver_name = "stm32-sha1",
 				.cra_priority = 200,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					CRYPTO_ALG_ASYNC |
+				.cra_flags = CRYPTO_ALG_ASYNC |
 					CRYPTO_ALG_KERN_DRIVER_ONLY,
 				.cra_blocksize = SHA1_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct stm32_hash_ctx),
@@ -1212,8 +1227,7 @@ static struct ahash_alg algs_md5_sha1[] = {
 				.cra_name = "hmac(sha1)",
 				.cra_driver_name = "stm32-hmac-sha1",
 				.cra_priority = 200,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					CRYPTO_ALG_ASYNC |
+				.cra_flags = CRYPTO_ALG_ASYNC |
 					CRYPTO_ALG_KERN_DRIVER_ONLY,
 				.cra_blocksize = SHA1_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct stm32_hash_ctx),
@@ -1241,8 +1255,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 				.cra_name = "sha224",
 				.cra_driver_name = "stm32-sha224",
 				.cra_priority = 200,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					CRYPTO_ALG_ASYNC |
+				.cra_flags = CRYPTO_ALG_ASYNC |
 					CRYPTO_ALG_KERN_DRIVER_ONLY,
 				.cra_blocksize = SHA224_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct stm32_hash_ctx),
@@ -1268,8 +1281,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 				.cra_name = "hmac(sha224)",
 				.cra_driver_name = "stm32-hmac-sha224",
 				.cra_priority = 200,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					CRYPTO_ALG_ASYNC |
+				.cra_flags = CRYPTO_ALG_ASYNC |
 					CRYPTO_ALG_KERN_DRIVER_ONLY,
 				.cra_blocksize = SHA224_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct stm32_hash_ctx),
@@ -1294,8 +1306,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 				.cra_name = "sha256",
 				.cra_driver_name = "stm32-sha256",
 				.cra_priority = 200,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					CRYPTO_ALG_ASYNC |
+				.cra_flags = CRYPTO_ALG_ASYNC |
 					CRYPTO_ALG_KERN_DRIVER_ONLY,
 				.cra_blocksize = SHA256_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct stm32_hash_ctx),
@@ -1321,8 +1332,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 				.cra_name = "hmac(sha256)",
 				.cra_driver_name = "stm32-hmac-sha256",
 				.cra_priority = 200,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					CRYPTO_ALG_ASYNC |
+				.cra_flags = CRYPTO_ALG_ASYNC |
 					CRYPTO_ALG_KERN_DRIVER_ONLY,
 				.cra_blocksize = SHA256_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct stm32_hash_ctx),
@@ -1482,6 +1492,13 @@ static int stm32_hash_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	pm_runtime_set_autosuspend_delay(dev, HASH_AUTOSUSPEND_DELAY);
+	pm_runtime_use_autosuspend(dev);
+
+	pm_runtime_get_noresume(dev);
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+
 	hdev->rst = devm_reset_control_get(&pdev->dev, NULL);
 	if (!IS_ERR(hdev->rst)) {
 		reset_control_assert(hdev->rst);
@@ -1522,6 +1539,8 @@ static int stm32_hash_probe(struct platform_device *pdev)
 	dev_info(dev, "Init HASH done HW ver %x DMA mode %u\n",
 		 stm32_hash_read(hdev, HASH_VER), hdev->dma_mode);
 
+	pm_runtime_put_sync(dev);
+
 	return 0;
 
 err_algs:
@@ -1535,6 +1554,9 @@ err_engine:
 	if (hdev->dma_lch)
 		dma_release_channel(hdev->dma_lch);
 
+	pm_runtime_disable(dev);
+	pm_runtime_put_noidle(dev);
+
 	clk_disable_unprepare(hdev->clk);
 
 	return ret;
@@ -1543,11 +1565,16 @@ err_engine:
 static int stm32_hash_remove(struct platform_device *pdev)
 {
 	static struct stm32_hash_dev *hdev;
+	int ret;
 
 	hdev = platform_get_drvdata(pdev);
 	if (!hdev)
 		return -ENODEV;
 
+	ret = pm_runtime_get_sync(hdev->dev);
+	if (ret < 0)
+		return ret;
+
 	stm32_hash_unregister_algs(hdev);
 
 	crypto_engine_exit(hdev->engine);
@@ -1559,16 +1586,52 @@ static int stm32_hash_remove(struct platform_device *pdev)
 	if (hdev->dma_lch)
 		dma_release_channel(hdev->dma_lch);
 
+	pm_runtime_disable(hdev->dev);
+	pm_runtime_put_noidle(hdev->dev);
+
 	clk_disable_unprepare(hdev->clk);
 
 	return 0;
 }
 
+#ifdef CONFIG_PM
+static int stm32_hash_runtime_suspend(struct device *dev)
+{
+	struct stm32_hash_dev *hdev = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(hdev->clk);
+
+	return 0;
+}
+
+static int stm32_hash_runtime_resume(struct device *dev)
+{
+	struct stm32_hash_dev *hdev = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(hdev->clk);
+	if (ret) {
+		dev_err(hdev->dev, "Failed to prepare_enable clock\n");
+		return ret;
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops stm32_hash_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+	SET_RUNTIME_PM_OPS(stm32_hash_runtime_suspend,
+			   stm32_hash_runtime_resume, NULL)
+};
+
 static struct platform_driver stm32_hash_driver = {
 	.probe		= stm32_hash_probe,
 	.remove		= stm32_hash_remove,
 	.driver		= {
 		.name	= "stm32-hash",
+		.pm = &stm32_hash_pm_ops,
 		.of_match_table	= stm32_hash_of_match,
 	}
 };
diff --git a/drivers/crypto/stm32/stm32_crc32.c b/drivers/crypto/stm32/stm32_crc32.c
index 8f09b8430893..5f3242a246fc 100644
--- a/drivers/crypto/stm32/stm32_crc32.c
+++ b/drivers/crypto/stm32/stm32_crc32.c
@@ -6,8 +6,10 @@
 
 #include <linux/bitrev.h>
 #include <linux/clk.h>
+#include <linux/crc32poly.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 
 #include <crypto/internal/hash.h>
 
@@ -28,9 +30,7 @@
 #define CRC_CR_REVERSE          (BIT(7) | BIT(6) | BIT(5))
 #define CRC_INIT_DEFAULT        0xFFFFFFFF
 
-/* Polynomial reversed */
-#define POLY_CRC32              0xEDB88320
-#define POLY_CRC32C             0x82F63B78
+#define CRC_AUTOSUSPEND_DELAY	50
 
 struct stm32_crc {
 	struct list_head list;
@@ -66,7 +66,7 @@ static int stm32_crc32_cra_init(struct crypto_tfm *tfm)
 	struct stm32_crc_ctx *mctx = crypto_tfm_ctx(tfm);
 
 	mctx->key = CRC_INIT_DEFAULT;
-	mctx->poly = POLY_CRC32;
+	mctx->poly = CRC32_POLY_LE;
 	return 0;
 }
 
@@ -75,7 +75,7 @@ static int stm32_crc32c_cra_init(struct crypto_tfm *tfm)
 	struct stm32_crc_ctx *mctx = crypto_tfm_ctx(tfm);
 
 	mctx->key = CRC_INIT_DEFAULT;
-	mctx->poly = POLY_CRC32C;
+	mctx->poly = CRC32C_POLY_LE;
 	return 0;
 }
 
@@ -106,6 +106,8 @@ static int stm32_crc_init(struct shash_desc *desc)
 	}
 	spin_unlock_bh(&crc_list.lock);
 
+	pm_runtime_get_sync(ctx->crc->dev);
+
 	/* Reset, set key, poly and configure in bit reverse mode */
 	writel_relaxed(bitrev32(mctx->key), ctx->crc->regs + CRC_INIT);
 	writel_relaxed(bitrev32(mctx->poly), ctx->crc->regs + CRC_POL);
@@ -115,6 +117,9 @@ static int stm32_crc_init(struct shash_desc *desc)
 	ctx->partial = readl_relaxed(ctx->crc->regs + CRC_DR);
 	ctx->crc->nb_pending_bytes = 0;
 
+	pm_runtime_mark_last_busy(ctx->crc->dev);
+	pm_runtime_put_autosuspend(ctx->crc->dev);
+
 	return 0;
 }
 
@@ -126,6 +131,8 @@ static int stm32_crc_update(struct shash_desc *desc, const u8 *d8,
 	u32 *d32;
 	unsigned int i;
 
+	pm_runtime_get_sync(crc->dev);
+
 	if (unlikely(crc->nb_pending_bytes)) {
 		while (crc->nb_pending_bytes != sizeof(u32) && length) {
 			/* Fill in pending data */
@@ -149,6 +156,9 @@ static int stm32_crc_update(struct shash_desc *desc, const u8 *d8,
 	/* Store partial result */
 	ctx->partial = readl_relaxed(crc->regs + CRC_DR);
 
+	pm_runtime_mark_last_busy(crc->dev);
+	pm_runtime_put_autosuspend(crc->dev);
+
 	/* Check for pending data (non 32 bits) */
 	length &= 3;
 	if (likely(!length))
@@ -174,7 +184,7 @@ static int stm32_crc_final(struct shash_desc *desc, u8 *out)
 	struct stm32_crc_ctx *mctx = crypto_shash_ctx(desc->tfm);
 
 	/* Send computed CRC */
-	put_unaligned_le32(mctx->poly == POLY_CRC32C ?
+	put_unaligned_le32(mctx->poly == CRC32C_POLY_LE ?
 			   ~ctx->partial : ctx->partial, out);
 
 	return 0;
@@ -272,6 +282,13 @@ static int stm32_crc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	pm_runtime_set_autosuspend_delay(dev, CRC_AUTOSUSPEND_DELAY);
+	pm_runtime_use_autosuspend(dev);
+
+	pm_runtime_get_noresume(dev);
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+
 	platform_set_drvdata(pdev, crc);
 
 	spin_lock(&crc_list.lock);
@@ -287,12 +304,18 @@ static int stm32_crc_probe(struct platform_device *pdev)
 
 	dev_info(dev, "Initialized\n");
 
+	pm_runtime_put_sync(dev);
+
 	return 0;
 }
 
 static int stm32_crc_remove(struct platform_device *pdev)
 {
 	struct stm32_crc *crc = platform_get_drvdata(pdev);
+	int ret = pm_runtime_get_sync(crc->dev);
+
+	if (ret < 0)
+		return ret;
 
 	spin_lock(&crc_list.lock);
 	list_del(&crc->list);
@@ -300,11 +323,46 @@ static int stm32_crc_remove(struct platform_device *pdev)
 
 	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
 
+	pm_runtime_disable(crc->dev);
+	pm_runtime_put_noidle(crc->dev);
+
+	clk_disable_unprepare(crc->clk);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int stm32_crc_runtime_suspend(struct device *dev)
+{
+	struct stm32_crc *crc = dev_get_drvdata(dev);
+
 	clk_disable_unprepare(crc->clk);
 
 	return 0;
 }
 
+static int stm32_crc_runtime_resume(struct device *dev)
+{
+	struct stm32_crc *crc = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(crc->clk);
+	if (ret) {
+		dev_err(crc->dev, "Failed to prepare_enable clock\n");
+		return ret;
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops stm32_crc_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+	SET_RUNTIME_PM_OPS(stm32_crc_runtime_suspend,
+			   stm32_crc_runtime_resume, NULL)
+};
+
 static const struct of_device_id stm32_dt_ids[] = {
 	{ .compatible = "st,stm32f7-crc", },
 	{},
@@ -316,6 +374,7 @@ static struct platform_driver stm32_crc_driver = {
 	.remove = stm32_crc_remove,
 	.driver = {
 		.name           = DRIVER_NAME,
+		.pm		= &stm32_crc_pm_ops,
 		.of_match_table = stm32_dt_ids,
 	},
 };
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-core.c b/drivers/crypto/sunxi-ss/sun4i-ss-core.c
index a81d89b3b7d8..89adf9e0fed2 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-core.c
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-core.c
@@ -45,11 +45,9 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 				.cra_driver_name = "md5-sun4i-ss",
 				.cra_priority = 300,
 				.cra_alignmask = 3,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH,
 				.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 				.cra_module = THIS_MODULE,
-				.cra_type = &crypto_ahash_type,
 				.cra_init = sun4i_hash_crainit
 			}
 		}
@@ -73,11 +71,9 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 				.cra_driver_name = "sha1-sun4i-ss",
 				.cra_priority = 300,
 				.cra_alignmask = 3,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH,
 				.cra_blocksize = SHA1_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 				.cra_module = THIS_MODULE,
-				.cra_type = &crypto_ahash_type,
 				.cra_init = sun4i_hash_crainit
 			}
 		}
@@ -96,8 +92,7 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 			.cra_driver_name = "cbc-aes-sun4i-ss",
 			.cra_priority = 300,
 			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_ctxsize = sizeof(struct sun4i_tfm_ctx),
 			.cra_module = THIS_MODULE,
 			.cra_alignmask = 3,
@@ -118,8 +113,7 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 			.cra_driver_name = "ecb-aes-sun4i-ss",
 			.cra_priority = 300,
 			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_ctxsize = sizeof(struct sun4i_tfm_ctx),
 			.cra_module = THIS_MODULE,
 			.cra_alignmask = 3,
@@ -140,8 +134,7 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 			.cra_driver_name = "cbc-des-sun4i-ss",
 			.cra_priority = 300,
 			.cra_blocksize = DES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 			.cra_module = THIS_MODULE,
 			.cra_alignmask = 3,
@@ -161,8 +154,7 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 			.cra_driver_name = "ecb-des-sun4i-ss",
 			.cra_priority = 300,
 			.cra_blocksize = DES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 			.cra_module = THIS_MODULE,
 			.cra_alignmask = 3,
@@ -183,8 +175,7 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 			.cra_driver_name = "cbc-des3-sun4i-ss",
 			.cra_priority = 300,
 			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 			.cra_module = THIS_MODULE,
 			.cra_alignmask = 3,
@@ -205,7 +196,6 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 			.cra_driver_name = "ecb-des3-sun4i-ss",
 			.cra_priority = 300,
 			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER,
 			.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 			.cra_module = THIS_MODULE,
 			.cra_alignmask = 3,
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index cf14f099ce4a..6988012deca4 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -2822,8 +2822,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "md5",
 				.cra_driver_name = "md5-talitos",
 				.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2838,8 +2837,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "sha1",
 				.cra_driver_name = "sha1-talitos",
 				.cra_blocksize = SHA1_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2854,8 +2852,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "sha224",
 				.cra_driver_name = "sha224-talitos",
 				.cra_blocksize = SHA224_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2870,8 +2867,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "sha256",
 				.cra_driver_name = "sha256-talitos",
 				.cra_blocksize = SHA256_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2886,8 +2882,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "sha384",
 				.cra_driver_name = "sha384-talitos",
 				.cra_blocksize = SHA384_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2902,8 +2897,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "sha512",
 				.cra_driver_name = "sha512-talitos",
 				.cra_blocksize = SHA512_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2918,8 +2912,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "hmac(md5)",
 				.cra_driver_name = "hmac-md5-talitos",
 				.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2934,8 +2927,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "hmac(sha1)",
 				.cra_driver_name = "hmac-sha1-talitos",
 				.cra_blocksize = SHA1_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2950,8 +2942,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "hmac(sha224)",
 				.cra_driver_name = "hmac-sha224-talitos",
 				.cra_blocksize = SHA224_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2966,8 +2957,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "hmac(sha256)",
 				.cra_driver_name = "hmac-sha256-talitos",
 				.cra_blocksize = SHA256_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2982,8 +2972,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "hmac(sha384)",
 				.cra_driver_name = "hmac-sha384-talitos",
 				.cra_blocksize = SHA384_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2998,8 +2987,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "hmac(sha512)",
 				.cra_driver_name = "hmac-sha512-talitos",
 				.cra_blocksize = SHA512_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -3186,7 +3174,6 @@ static struct talitos_crypto_alg *talitos_alg_alloc(struct device *dev,
 		alg = &t_alg->algt.alg.hash.halg.base;
 		alg->cra_init = talitos_cra_init_ahash;
 		alg->cra_exit = talitos_cra_exit;
-		alg->cra_type = &crypto_ahash_type;
 		t_alg->algt.alg.hash.init = ahash_init;
 		t_alg->algt.alg.hash.update = ahash_update;
 		t_alg->algt.alg.hash.final = ahash_final;
diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c
index 2d0a677bcc76..daf4fed0df8c 100644
--- a/drivers/crypto/ux500/hash/hash_core.c
+++ b/drivers/crypto/ux500/hash/hash_core.c
@@ -1524,8 +1524,7 @@ static struct hash_algo_template hash_algs[] = {
 			.halg.base = {
 				.cra_name = "sha1",
 				.cra_driver_name = "sha1-ux500",
-				.cra_flags = (CRYPTO_ALG_TYPE_AHASH |
-					      CRYPTO_ALG_ASYNC),
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA1_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct hash_ctx),
 				.cra_init = hash_cra_init,
@@ -1548,11 +1547,9 @@ static struct hash_algo_template hash_algs[] = {
 			.halg.base = {
 				.cra_name = "sha256",
 				.cra_driver_name = "sha256-ux500",
-				.cra_flags = (CRYPTO_ALG_TYPE_AHASH |
-					      CRYPTO_ALG_ASYNC),
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA256_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct hash_ctx),
-				.cra_type = &crypto_ahash_type,
 				.cra_init = hash_cra_init,
 				.cra_module = THIS_MODULE,
 			}
@@ -1574,11 +1571,9 @@ static struct hash_algo_template hash_algs[] = {
 			.halg.base = {
 				.cra_name = "hmac(sha1)",
 				.cra_driver_name = "hmac-sha1-ux500",
-				.cra_flags = (CRYPTO_ALG_TYPE_AHASH |
-					      CRYPTO_ALG_ASYNC),
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA1_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct hash_ctx),
-				.cra_type = &crypto_ahash_type,
 				.cra_init = hash_cra_init,
 				.cra_module = THIS_MODULE,
 			}
@@ -1600,11 +1595,9 @@ static struct hash_algo_template hash_algs[] = {
 			.halg.base = {
 				.cra_name = "hmac(sha256)",
 				.cra_driver_name = "hmac-sha256-ux500",
-				.cra_flags = (CRYPTO_ALG_TYPE_AHASH |
-					      CRYPTO_ALG_ASYNC),
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA256_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct hash_ctx),
-				.cra_type = &crypto_ahash_type,
 				.cra_init = hash_cra_init,
 				.cra_module = THIS_MODULE,
 			}
diff --git a/drivers/crypto/virtio/virtio_crypto_algs.c b/drivers/crypto/virtio/virtio_crypto_algs.c
index af6a908dfa7a..2c573d1aaa64 100644
--- a/drivers/crypto/virtio/virtio_crypto_algs.c
+++ b/drivers/crypto/virtio/virtio_crypto_algs.c
@@ -49,12 +49,18 @@ struct virtio_crypto_sym_request {
 	bool encrypt;
 };
 
+struct virtio_crypto_algo {
+	uint32_t algonum;
+	uint32_t service;
+	unsigned int active_devs;
+	struct crypto_alg algo;
+};
+
 /*
  * The algs_lock protects the below global virtio_crypto_active_devs
  * and crypto algorithms registion.
  */
 static DEFINE_MUTEX(algs_lock);
-static unsigned int virtio_crypto_active_devs;
 static void virtio_crypto_ablkcipher_finalize_req(
 	struct virtio_crypto_sym_request *vc_sym_req,
 	struct ablkcipher_request *req,
@@ -312,15 +318,21 @@ static int virtio_crypto_ablkcipher_setkey(struct crypto_ablkcipher *tfm,
 					 unsigned int keylen)
 {
 	struct virtio_crypto_ablkcipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	uint32_t alg;
 	int ret;
 
+	ret = virtio_crypto_alg_validate_key(keylen, &alg);
+	if (ret)
+		return ret;
+
 	if (!ctx->vcrypto) {
 		/* New key */
 		int node = virtio_crypto_get_current_node();
 		struct virtio_crypto *vcrypto =
-				      virtcrypto_get_dev_node(node);
+				      virtcrypto_get_dev_node(node,
+				      VIRTIO_CRYPTO_SERVICE_CIPHER, alg);
 		if (!vcrypto) {
-			pr_err("virtio_crypto: Could not find a virtio device in the system\n");
+			pr_err("virtio_crypto: Could not find a virtio device in the system or unsupported algo\n");
 			return -ENODEV;
 		}
 
@@ -371,12 +383,12 @@ __virtio_crypto_ablkcipher_do_req(struct virtio_crypto_sym_request *vc_sym_req,
 
 	/* Why 3?  outhdr + iv + inhdr */
 	sg_total = src_nents + dst_nents + 3;
-	sgs = kcalloc_node(sg_total, sizeof(*sgs), GFP_ATOMIC,
+	sgs = kcalloc_node(sg_total, sizeof(*sgs), GFP_KERNEL,
 				dev_to_node(&vcrypto->vdev->dev));
 	if (!sgs)
 		return -ENOMEM;
 
-	req_data = kzalloc_node(sizeof(*req_data), GFP_ATOMIC,
+	req_data = kzalloc_node(sizeof(*req_data), GFP_KERNEL,
 				dev_to_node(&vcrypto->vdev->dev));
 	if (!req_data) {
 		kfree(sgs);
@@ -571,57 +583,85 @@ static void virtio_crypto_ablkcipher_finalize_req(
 	virtcrypto_clear_request(&vc_sym_req->base);
 }
 
-static struct crypto_alg virtio_crypto_algs[] = { {
-	.cra_name = "cbc(aes)",
-	.cra_driver_name = "virtio_crypto_aes_cbc",
-	.cra_priority = 150,
-	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize = AES_BLOCK_SIZE,
-	.cra_ctxsize  = sizeof(struct virtio_crypto_ablkcipher_ctx),
-	.cra_alignmask = 0,
-	.cra_module = THIS_MODULE,
-	.cra_type = &crypto_ablkcipher_type,
-	.cra_init = virtio_crypto_ablkcipher_init,
-	.cra_exit = virtio_crypto_ablkcipher_exit,
-	.cra_u = {
-	   .ablkcipher = {
-			.setkey = virtio_crypto_ablkcipher_setkey,
-			.decrypt = virtio_crypto_ablkcipher_decrypt,
-			.encrypt = virtio_crypto_ablkcipher_encrypt,
-			.min_keysize = AES_MIN_KEY_SIZE,
-			.max_keysize = AES_MAX_KEY_SIZE,
-			.ivsize = AES_BLOCK_SIZE,
+static struct virtio_crypto_algo virtio_crypto_algs[] = { {
+	.algonum = VIRTIO_CRYPTO_CIPHER_AES_CBC,
+	.service = VIRTIO_CRYPTO_SERVICE_CIPHER,
+	.algo = {
+		.cra_name = "cbc(aes)",
+		.cra_driver_name = "virtio_crypto_aes_cbc",
+		.cra_priority = 150,
+		.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+		.cra_blocksize = AES_BLOCK_SIZE,
+		.cra_ctxsize  = sizeof(struct virtio_crypto_ablkcipher_ctx),
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+		.cra_type = &crypto_ablkcipher_type,
+		.cra_init = virtio_crypto_ablkcipher_init,
+		.cra_exit = virtio_crypto_ablkcipher_exit,
+		.cra_u = {
+			.ablkcipher = {
+				.setkey = virtio_crypto_ablkcipher_setkey,
+				.decrypt = virtio_crypto_ablkcipher_decrypt,
+				.encrypt = virtio_crypto_ablkcipher_encrypt,
+				.min_keysize = AES_MIN_KEY_SIZE,
+				.max_keysize = AES_MAX_KEY_SIZE,
+				.ivsize = AES_BLOCK_SIZE,
+			},
 		},
 	},
 } };
 
-int virtio_crypto_algs_register(void)
+int virtio_crypto_algs_register(struct virtio_crypto *vcrypto)
 {
 	int ret = 0;
+	int i = 0;
 
 	mutex_lock(&algs_lock);
-	if (++virtio_crypto_active_devs != 1)
-		goto unlock;
 
-	ret = crypto_register_algs(virtio_crypto_algs,
-			ARRAY_SIZE(virtio_crypto_algs));
-	if (ret)
-		virtio_crypto_active_devs--;
+	for (i = 0; i < ARRAY_SIZE(virtio_crypto_algs); i++) {
+
+		uint32_t service = virtio_crypto_algs[i].service;
+		uint32_t algonum = virtio_crypto_algs[i].algonum;
+
+		if (!virtcrypto_algo_is_supported(vcrypto, service, algonum))
+			continue;
+
+		if (virtio_crypto_algs[i].active_devs == 0) {
+			ret = crypto_register_alg(&virtio_crypto_algs[i].algo);
+			if (ret)
+				goto unlock;
+		}
+
+		virtio_crypto_algs[i].active_devs++;
+		dev_info(&vcrypto->vdev->dev, "Registered algo %s\n",
+			 virtio_crypto_algs[i].algo.cra_name);
+	}
 
 unlock:
 	mutex_unlock(&algs_lock);
 	return ret;
 }
 
-void virtio_crypto_algs_unregister(void)
+void virtio_crypto_algs_unregister(struct virtio_crypto *vcrypto)
 {
+	int i = 0;
+
 	mutex_lock(&algs_lock);
-	if (--virtio_crypto_active_devs != 0)
-		goto unlock;
 
-	crypto_unregister_algs(virtio_crypto_algs,
-			ARRAY_SIZE(virtio_crypto_algs));
+	for (i = 0; i < ARRAY_SIZE(virtio_crypto_algs); i++) {
+
+		uint32_t service = virtio_crypto_algs[i].service;
+		uint32_t algonum = virtio_crypto_algs[i].algonum;
+
+		if (virtio_crypto_algs[i].active_devs == 0 ||
+		    !virtcrypto_algo_is_supported(vcrypto, service, algonum))
+			continue;
+
+		if (virtio_crypto_algs[i].active_devs == 1)
+			crypto_unregister_alg(&virtio_crypto_algs[i].algo);
+
+		virtio_crypto_algs[i].active_devs--;
+	}
 
-unlock:
 	mutex_unlock(&algs_lock);
 }
diff --git a/drivers/crypto/virtio/virtio_crypto_common.h b/drivers/crypto/virtio/virtio_crypto_common.h
index 66501a5a2b7b..63ef7f7924ea 100644
--- a/drivers/crypto/virtio/virtio_crypto_common.h
+++ b/drivers/crypto/virtio/virtio_crypto_common.h
@@ -55,6 +55,20 @@ struct virtio_crypto {
 	/* Number of queue currently used by the driver */
 	u32 curr_queue;
 
+	/*
+	 * Specifies the services mask which the device support,
+	 * see VIRTIO_CRYPTO_SERVICE_*
+	 */
+	u32 crypto_services;
+
+	/* Detailed algorithms mask */
+	u32 cipher_algo_l;
+	u32 cipher_algo_h;
+	u32 hash_algo;
+	u32 mac_algo_l;
+	u32 mac_algo_h;
+	u32 aead_algo;
+
 	/* Maximum length of cipher key */
 	u32 max_cipher_key_len;
 	/* Maximum length of authenticated key */
@@ -102,7 +116,12 @@ int virtcrypto_dev_in_use(struct virtio_crypto *vcrypto_dev);
 int virtcrypto_dev_get(struct virtio_crypto *vcrypto_dev);
 void virtcrypto_dev_put(struct virtio_crypto *vcrypto_dev);
 int virtcrypto_dev_started(struct virtio_crypto *vcrypto_dev);
-struct virtio_crypto *virtcrypto_get_dev_node(int node);
+bool virtcrypto_algo_is_supported(struct virtio_crypto *vcrypto_dev,
+				  uint32_t service,
+				  uint32_t algo);
+struct virtio_crypto *virtcrypto_get_dev_node(int node,
+					      uint32_t service,
+					      uint32_t algo);
 int virtcrypto_dev_start(struct virtio_crypto *vcrypto);
 void virtcrypto_dev_stop(struct virtio_crypto *vcrypto);
 int virtio_crypto_ablkcipher_crypt_req(
@@ -122,7 +141,7 @@ static inline int virtio_crypto_get_current_node(void)
 	return node;
 }
 
-int virtio_crypto_algs_register(void);
-void virtio_crypto_algs_unregister(void);
+int virtio_crypto_algs_register(struct virtio_crypto *vcrypto);
+void virtio_crypto_algs_unregister(struct virtio_crypto *vcrypto);
 
 #endif /* _VIRTIO_CRYPTO_COMMON_H */
diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c
index 83326986c113..3c9e120287af 100644
--- a/drivers/crypto/virtio/virtio_crypto_core.c
+++ b/drivers/crypto/virtio/virtio_crypto_core.c
@@ -146,7 +146,7 @@ static void virtcrypto_clean_affinity(struct virtio_crypto *vi, long hcpu)
 
 	if (vi->affinity_hint_set) {
 		for (i = 0; i < vi->max_data_queues; i++)
-			virtqueue_set_affinity(vi->data_vq[i].vq, -1);
+			virtqueue_set_affinity(vi->data_vq[i].vq, NULL);
 
 		vi->affinity_hint_set = false;
 	}
@@ -173,7 +173,7 @@ static void virtcrypto_set_affinity(struct virtio_crypto *vcrypto)
 	 *
 	 */
 	for_each_online_cpu(cpu) {
-		virtqueue_set_affinity(vcrypto->data_vq[i].vq, cpu);
+		virtqueue_set_affinity(vcrypto->data_vq[i].vq, cpumask_of(cpu));
 		if (++i >= vcrypto->max_data_queues)
 			break;
 	}
@@ -303,6 +303,13 @@ static int virtcrypto_probe(struct virtio_device *vdev)
 	u32 max_data_queues = 0, max_cipher_key_len = 0;
 	u32 max_auth_key_len = 0;
 	u64 max_size = 0;
+	u32 cipher_algo_l = 0;
+	u32 cipher_algo_h = 0;
+	u32 hash_algo = 0;
+	u32 mac_algo_l = 0;
+	u32 mac_algo_h = 0;
+	u32 aead_algo = 0;
+	u32 crypto_services = 0;
 
 	if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1))
 		return -ENODEV;
@@ -339,6 +346,20 @@ static int virtcrypto_probe(struct virtio_device *vdev)
 		max_auth_key_len, &max_auth_key_len);
 	virtio_cread(vdev, struct virtio_crypto_config,
 		max_size, &max_size);
+	virtio_cread(vdev, struct virtio_crypto_config,
+		crypto_services, &crypto_services);
+	virtio_cread(vdev, struct virtio_crypto_config,
+		cipher_algo_l, &cipher_algo_l);
+	virtio_cread(vdev, struct virtio_crypto_config,
+		cipher_algo_h, &cipher_algo_h);
+	virtio_cread(vdev, struct virtio_crypto_config,
+		hash_algo, &hash_algo);
+	virtio_cread(vdev, struct virtio_crypto_config,
+		mac_algo_l, &mac_algo_l);
+	virtio_cread(vdev, struct virtio_crypto_config,
+		mac_algo_h, &mac_algo_h);
+	virtio_cread(vdev, struct virtio_crypto_config,
+		aead_algo, &aead_algo);
 
 	/* Add virtio crypto device to global table */
 	err = virtcrypto_devmgr_add_dev(vcrypto);
@@ -358,6 +379,14 @@ static int virtcrypto_probe(struct virtio_device *vdev)
 	vcrypto->max_cipher_key_len = max_cipher_key_len;
 	vcrypto->max_auth_key_len = max_auth_key_len;
 	vcrypto->max_size = max_size;
+	vcrypto->crypto_services = crypto_services;
+	vcrypto->cipher_algo_l = cipher_algo_l;
+	vcrypto->cipher_algo_h = cipher_algo_h;
+	vcrypto->mac_algo_l = mac_algo_l;
+	vcrypto->mac_algo_h = mac_algo_h;
+	vcrypto->hash_algo = hash_algo;
+	vcrypto->aead_algo = aead_algo;
+
 
 	dev_info(&vdev->dev,
 		"max_queues: %u, max_cipher_key_len: %u, max_auth_key_len: %u, max_size 0x%llx\n",
diff --git a/drivers/crypto/virtio/virtio_crypto_mgr.c b/drivers/crypto/virtio/virtio_crypto_mgr.c
index a69ff71de2c4..d70de3a4f7d7 100644
--- a/drivers/crypto/virtio/virtio_crypto_mgr.c
+++ b/drivers/crypto/virtio/virtio_crypto_mgr.c
@@ -181,14 +181,20 @@ int virtcrypto_dev_started(struct virtio_crypto *vcrypto_dev)
 /*
  * virtcrypto_get_dev_node() - Get vcrypto_dev on the node.
  * @node:  Node id the driver works.
+ * @service: Crypto service that needs to be supported by the
+ *	      dev
+ * @algo: The algorithm number that needs to be supported by the
+ *	  dev
  *
- * Function returns the virtio crypto device used fewest on the node.
+ * Function returns the virtio crypto device used fewest on the node,
+ * and supports the given crypto service and algorithm.
  *
  * To be used by virtio crypto device specific drivers.
  *
  * Return: pointer to vcrypto_dev or NULL if not found.
  */
-struct virtio_crypto *virtcrypto_get_dev_node(int node)
+struct virtio_crypto *virtcrypto_get_dev_node(int node, uint32_t service,
+					      uint32_t algo)
 {
 	struct virtio_crypto *vcrypto_dev = NULL, *tmp_dev;
 	unsigned long best = ~0;
@@ -199,7 +205,8 @@ struct virtio_crypto *virtcrypto_get_dev_node(int node)
 
 		if ((node == dev_to_node(&tmp_dev->vdev->dev) ||
 		     dev_to_node(&tmp_dev->vdev->dev) < 0) &&
-		    virtcrypto_dev_started(tmp_dev)) {
+		    virtcrypto_dev_started(tmp_dev) &&
+		    virtcrypto_algo_is_supported(tmp_dev, service, algo)) {
 			ctr = atomic_read(&tmp_dev->ref_count);
 			if (best > ctr) {
 				vcrypto_dev = tmp_dev;
@@ -214,7 +221,9 @@ struct virtio_crypto *virtcrypto_get_dev_node(int node)
 		/* Get any started device */
 		list_for_each_entry(tmp_dev,
 				virtcrypto_devmgr_get_head(), list) {
-			if (virtcrypto_dev_started(tmp_dev)) {
+			if (virtcrypto_dev_started(tmp_dev) &&
+			    virtcrypto_algo_is_supported(tmp_dev,
+			    service, algo)) {
 				vcrypto_dev = tmp_dev;
 				break;
 			}
@@ -240,7 +249,7 @@ struct virtio_crypto *virtcrypto_get_dev_node(int node)
  */
 int virtcrypto_dev_start(struct virtio_crypto *vcrypto)
 {
-	if (virtio_crypto_algs_register()) {
+	if (virtio_crypto_algs_register(vcrypto)) {
 		pr_err("virtio_crypto: Failed to register crypto algs\n");
 		return -EFAULT;
 	}
@@ -260,5 +269,65 @@ int virtcrypto_dev_start(struct virtio_crypto *vcrypto)
  */
 void virtcrypto_dev_stop(struct virtio_crypto *vcrypto)
 {
-	virtio_crypto_algs_unregister();
+	virtio_crypto_algs_unregister(vcrypto);
+}
+
+/*
+ * vcrypto_algo_is_supported()
+ * @vcrypto: Pointer to virtio crypto device.
+ * @service: The bit number for service validate.
+ *	      See VIRTIO_CRYPTO_SERVICE_*
+ * @algo : The bit number for the algorithm to validate.
+ *
+ *
+ * Validate if the virtio crypto device supports a service and
+ * algo.
+ *
+ * Return true if device supports a service and algo.
+ */
+
+bool virtcrypto_algo_is_supported(struct virtio_crypto *vcrypto,
+				  uint32_t service,
+				  uint32_t algo)
+{
+	uint32_t service_mask = 1u << service;
+	uint32_t algo_mask = 0;
+	bool low = true;
+
+	if (algo > 31) {
+		algo -= 32;
+		low = false;
+	}
+
+	if (!(vcrypto->crypto_services & service_mask))
+		return false;
+
+	switch (service) {
+	case VIRTIO_CRYPTO_SERVICE_CIPHER:
+		if (low)
+			algo_mask = vcrypto->cipher_algo_l;
+		else
+			algo_mask = vcrypto->cipher_algo_h;
+		break;
+
+	case VIRTIO_CRYPTO_SERVICE_HASH:
+		algo_mask = vcrypto->hash_algo;
+		break;
+
+	case VIRTIO_CRYPTO_SERVICE_MAC:
+		if (low)
+			algo_mask = vcrypto->mac_algo_l;
+		else
+			algo_mask = vcrypto->mac_algo_h;
+		break;
+
+	case VIRTIO_CRYPTO_SERVICE_AEAD:
+		algo_mask = vcrypto->aead_algo;
+		break;
+	}
+
+	if (!(algo_mask & (1u << algo)))
+		return false;
+
+	return true;
 }
diff --git a/drivers/crypto/vmx/ghash.c b/drivers/crypto/vmx/ghash.c
index 1c4b5b889fba..dd8b8716467a 100644
--- a/drivers/crypto/vmx/ghash.c
+++ b/drivers/crypto/vmx/ghash.c
@@ -215,7 +215,7 @@ struct shash_alg p8_ghash_alg = {
 		 .cra_name = "ghash",
 		 .cra_driver_name = "p8_ghash",
 		 .cra_priority = 1000,
-		 .cra_flags = CRYPTO_ALG_TYPE_SHASH | CRYPTO_ALG_NEED_FALLBACK,
+		 .cra_flags = CRYPTO_ALG_NEED_FALLBACK,
 		 .cra_blocksize = GHASH_BLOCK_SIZE,
 		 .cra_ctxsize = sizeof(struct p8_ghash_ctx),
 		 .cra_module = THIS_MODULE,
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 0b5b3abe054e..4c49bb1330b5 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -604,28 +604,29 @@ struct devfreq *devfreq_add_device(struct device *dev,
 		mutex_lock(&devfreq->lock);
 	}
 
-	devfreq->min_freq = find_available_min_freq(devfreq);
-	if (!devfreq->min_freq) {
+	devfreq->scaling_min_freq = find_available_min_freq(devfreq);
+	if (!devfreq->scaling_min_freq) {
 		mutex_unlock(&devfreq->lock);
 		err = -EINVAL;
 		goto err_dev;
 	}
-	devfreq->scaling_min_freq = devfreq->min_freq;
+	devfreq->min_freq = devfreq->scaling_min_freq;
 
-	devfreq->max_freq = find_available_max_freq(devfreq);
-	if (!devfreq->max_freq) {
+	devfreq->scaling_max_freq = find_available_max_freq(devfreq);
+	if (!devfreq->scaling_max_freq) {
 		mutex_unlock(&devfreq->lock);
 		err = -EINVAL;
 		goto err_dev;
 	}
-	devfreq->scaling_max_freq = devfreq->max_freq;
+	devfreq->max_freq = devfreq->scaling_max_freq;
 
 	dev_set_name(&devfreq->dev, "devfreq%d",
 				atomic_inc_return(&devfreq_no));
 	err = device_register(&devfreq->dev);
 	if (err) {
 		mutex_unlock(&devfreq->lock);
-		goto err_dev;
+		put_device(&devfreq->dev);
+		goto err_out;
 	}
 
 	devfreq->trans_table =
@@ -672,6 +673,7 @@ err_init:
 	mutex_unlock(&devfreq_list_lock);
 
 	device_unregister(&devfreq->dev);
+	devfreq = NULL;
 err_dev:
 	if (devfreq)
 		kfree(devfreq);
diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c
index 3cd6a184fe7c..a9c64f0d3284 100644
--- a/drivers/devfreq/event/exynos-ppmu.c
+++ b/drivers/devfreq/event/exynos-ppmu.c
@@ -627,11 +627,9 @@ static int exynos_ppmu_probe(struct platform_device *pdev)
 
 	size = sizeof(struct devfreq_event_dev *) * info->num_events;
 	info->edev = devm_kzalloc(&pdev->dev, size, GFP_KERNEL);
-	if (!info->edev) {
-		dev_err(&pdev->dev,
-			"failed to allocate memory devfreq-event devices\n");
+	if (!info->edev)
 		return -ENOMEM;
-	}
+
 	edev = info->edev;
 	platform_set_drvdata(pdev, info);
 
diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c
index 5dfbfa3cc878..e795ad2b3f6b 100644
--- a/drivers/devfreq/rk3399_dmc.c
+++ b/drivers/devfreq/rk3399_dmc.c
@@ -68,15 +68,6 @@ struct rk3399_dmcfreq {
 	struct devfreq_event_dev *edev;
 	struct mutex lock;
 	struct dram_timing timing;
-
-	/*
-	 * DDR Converser of Frequency (DCF) is used to implement DDR frequency
-	 * conversion without the participation of CPU, we will implement and
-	 * control it in arm trust firmware.
-	 */
-	wait_queue_head_t	wait_dcf_queue;
-	int irq;
-	int wait_dcf_flag;
 	struct regulator *vdd_center;
 	unsigned long rate, target_rate;
 	unsigned long volt, target_volt;
@@ -112,31 +103,22 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 		err = regulator_set_voltage(dmcfreq->vdd_center, target_volt,
 					    target_volt);
 		if (err) {
-			dev_err(dev, "Cannot to set voltage %lu uV\n",
+			dev_err(dev, "Cannot set voltage %lu uV\n",
 				target_volt);
 			goto out;
 		}
 	}
-	dmcfreq->wait_dcf_flag = 1;
 
 	err = clk_set_rate(dmcfreq->dmc_clk, target_rate);
 	if (err) {
-		dev_err(dev, "Cannot to set frequency %lu (%d)\n",
-			target_rate, err);
+		dev_err(dev, "Cannot set frequency %lu (%d)\n", target_rate,
+			err);
 		regulator_set_voltage(dmcfreq->vdd_center, dmcfreq->volt,
 				      dmcfreq->volt);
 		goto out;
 	}
 
 	/*
-	 * Wait until bcf irq happen, it means freq scaling finish in
-	 * arm trust firmware, use 100ms as timeout time.
-	 */
-	if (!wait_event_timeout(dmcfreq->wait_dcf_queue,
-				!dmcfreq->wait_dcf_flag, HZ / 10))
-		dev_warn(dev, "Timeout waiting for dcf interrupt\n");
-
-	/*
 	 * Check the dpll rate,
 	 * There only two result we will get,
 	 * 1. Ddr frequency scaling fail, we still get the old rate.
@@ -146,8 +128,8 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 
 	/* If get the incorrect rate, set voltage to old value. */
 	if (dmcfreq->rate != target_rate) {
-		dev_err(dev, "Get wrong ddr frequency, Request frequency %lu,\
-			Current frequency %lu\n", target_rate, dmcfreq->rate);
+		dev_err(dev, "Got wrong frequency, Request %lu, Current %lu\n",
+			target_rate, dmcfreq->rate);
 		regulator_set_voltage(dmcfreq->vdd_center, dmcfreq->volt,
 				      dmcfreq->volt);
 		goto out;
@@ -155,7 +137,7 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 		err = regulator_set_voltage(dmcfreq->vdd_center, target_volt,
 					    target_volt);
 	if (err)
-		dev_err(dev, "Cannot to set vol %lu uV\n", target_volt);
+		dev_err(dev, "Cannot set voltage %lu uV\n", target_volt);
 
 	dmcfreq->rate = target_rate;
 	dmcfreq->volt = target_volt;
@@ -241,22 +223,6 @@ static __maybe_unused int rk3399_dmcfreq_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(rk3399_dmcfreq_pm, rk3399_dmcfreq_suspend,
 			 rk3399_dmcfreq_resume);
 
-static irqreturn_t rk3399_dmc_irq(int irq, void *dev_id)
-{
-	struct rk3399_dmcfreq *dmcfreq = dev_id;
-	struct arm_smccc_res res;
-
-	dmcfreq->wait_dcf_flag = 0;
-	wake_up(&dmcfreq->wait_dcf_queue);
-
-	/* Clear the DCF interrupt */
-	arm_smccc_smc(ROCKCHIP_SIP_DRAM_FREQ, 0, 0,
-		      ROCKCHIP_SIP_CONFIG_DRAM_CLR_IRQ,
-		      0, 0, 0, 0, &res);
-
-	return IRQ_HANDLED;
-}
-
 static int of_get_ddr_timings(struct dram_timing *timing,
 			      struct device_node *np)
 {
@@ -330,16 +296,10 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct device_node *np = pdev->dev.of_node;
 	struct rk3399_dmcfreq *data;
-	int ret, irq, index, size;
+	int ret, index, size;
 	uint32_t *timing;
 	struct dev_pm_opp *opp;
 
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev,
-			"Cannot get the dmc interrupt resource: %d\n", irq);
-		return irq;
-	}
 	data = devm_kzalloc(dev, sizeof(struct rk3399_dmcfreq), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
@@ -348,27 +308,22 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 
 	data->vdd_center = devm_regulator_get(dev, "center");
 	if (IS_ERR(data->vdd_center)) {
+		if (PTR_ERR(data->vdd_center) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+
 		dev_err(dev, "Cannot get the regulator \"center\"\n");
 		return PTR_ERR(data->vdd_center);
 	}
 
 	data->dmc_clk = devm_clk_get(dev, "dmc_clk");
 	if (IS_ERR(data->dmc_clk)) {
+		if (PTR_ERR(data->dmc_clk) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+
 		dev_err(dev, "Cannot get the clk dmc_clk\n");
 		return PTR_ERR(data->dmc_clk);
 	};
 
-	data->irq = irq;
-	ret = devm_request_irq(dev, irq, rk3399_dmc_irq, 0,
-			       dev_name(dev), data);
-	if (ret) {
-		dev_err(dev, "Failed to request dmc irq: %d\n", ret);
-		return ret;
-	}
-
-	init_waitqueue_head(&data->wait_dcf_queue);
-	data->wait_dcf_flag = 0;
-
 	data->edev = devfreq_event_get_edev_by_phandle(dev, 0);
 	if (IS_ERR(data->edev))
 		return -EPROBE_DEFER;
@@ -420,8 +375,10 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 	data->rate = clk_get_rate(data->dmc_clk);
 
 	opp = devfreq_recommended_opp(dev, &data->rate, 0);
-	if (IS_ERR(opp))
-		return PTR_ERR(opp);
+	if (IS_ERR(opp)) {
+		ret = PTR_ERR(opp);
+		goto err_free_opp;
+	}
 
 	data->rate = dev_pm_opp_get_freq(opp);
 	data->volt = dev_pm_opp_get_voltage(opp);
@@ -433,14 +390,34 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 					   &rk3399_devfreq_dmc_profile,
 					   DEVFREQ_GOV_SIMPLE_ONDEMAND,
 					   &data->ondemand_data);
-	if (IS_ERR(data->devfreq))
-		return PTR_ERR(data->devfreq);
+	if (IS_ERR(data->devfreq)) {
+		ret = PTR_ERR(data->devfreq);
+		goto err_free_opp;
+	}
+
 	devm_devfreq_register_opp_notifier(dev, data->devfreq);
 
 	data->dev = dev;
 	platform_set_drvdata(pdev, data);
 
 	return 0;
+
+err_free_opp:
+	dev_pm_opp_of_remove_table(&pdev->dev);
+	return ret;
+}
+
+static int rk3399_dmcfreq_remove(struct platform_device *pdev)
+{
+	struct rk3399_dmcfreq *dmcfreq = dev_get_drvdata(&pdev->dev);
+
+	/*
+	 * Before remove the opp table we need to unregister the opp notifier.
+	 */
+	devm_devfreq_unregister_opp_notifier(dmcfreq->dev, dmcfreq->devfreq);
+	dev_pm_opp_of_remove_table(dmcfreq->dev);
+
+	return 0;
 }
 
 static const struct of_device_id rk3399dmc_devfreq_of_match[] = {
@@ -451,6 +428,7 @@ MODULE_DEVICE_TABLE(of, rk3399dmc_devfreq_of_match);
 
 static struct platform_driver rk3399_dmcfreq_driver = {
 	.probe	= rk3399_dmcfreq_probe,
+	.remove = rk3399_dmcfreq_remove,
 	.driver = {
 		.name	= "rk3399-dmc-freq",
 		.pm	= &rk3399_dmcfreq_pm,
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index d78d5fc173dc..13884474d158 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -405,7 +405,6 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
 			  || !exp_info->ops->map_dma_buf
 			  || !exp_info->ops->unmap_dma_buf
 			  || !exp_info->ops->release
-			  || !exp_info->ops->map_atomic
 			  || !exp_info->ops->map
 			  || !exp_info->ops->mmap)) {
 		return ERR_PTR(-EINVAL);
@@ -568,7 +567,7 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
 	mutex_lock(&dmabuf->lock);
 
 	if (dmabuf->ops->attach) {
-		ret = dmabuf->ops->attach(dmabuf, dev, attach);
+		ret = dmabuf->ops->attach(dmabuf, attach);
 		if (ret)
 			goto err_attach;
 	}
@@ -687,26 +686,14 @@ EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment);
  *      void \*dma_buf_kmap(struct dma_buf \*, unsigned long);
  *      void dma_buf_kunmap(struct dma_buf \*, unsigned long, void \*);
  *
- *   There are also atomic variants of these interfaces. Like for kmap they
- *   facilitate non-blocking fast-paths. Neither the importer nor the exporter
- *   (in the callback) is allowed to block when using these.
- *
- *   Interfaces::
- *      void \*dma_buf_kmap_atomic(struct dma_buf \*, unsigned long);
- *      void dma_buf_kunmap_atomic(struct dma_buf \*, unsigned long, void \*);
- *
- *   For importers all the restrictions of using kmap apply, like the limited
- *   supply of kmap_atomic slots. Hence an importer shall only hold onto at
- *   max 2 atomic dma_buf kmaps at the same time (in any given process context).
+ *   Implementing the functions is optional for exporters and for importers all
+ *   the restrictions of using kmap apply.
  *
  *   dma_buf kmap calls outside of the range specified in begin_cpu_access are
  *   undefined. If the range is not PAGE_SIZE aligned, kmap needs to succeed on
  *   the partial chunks at the beginning and end but may return stale or bogus
  *   data outside of the range (in these partial chunks).
  *
- *   Note that these calls need to always succeed. The exporter needs to
- *   complete any preparations that might fail in begin_cpu_access.
- *
  *   For some cases the overhead of kmap can be too high, a vmap interface
  *   is introduced. This interface should be used very carefully, as vmalloc
  *   space is a limited resources on many architectures.
@@ -860,41 +847,6 @@ int dma_buf_end_cpu_access(struct dma_buf *dmabuf,
 EXPORT_SYMBOL_GPL(dma_buf_end_cpu_access);
 
 /**
- * dma_buf_kmap_atomic - Map a page of the buffer object into kernel address
- * space. The same restrictions as for kmap_atomic and friends apply.
- * @dmabuf:	[in]	buffer to map page from.
- * @page_num:	[in]	page in PAGE_SIZE units to map.
- *
- * This call must always succeed, any necessary preparations that might fail
- * need to be done in begin_cpu_access.
- */
-void *dma_buf_kmap_atomic(struct dma_buf *dmabuf, unsigned long page_num)
-{
-	WARN_ON(!dmabuf);
-
-	return dmabuf->ops->map_atomic(dmabuf, page_num);
-}
-EXPORT_SYMBOL_GPL(dma_buf_kmap_atomic);
-
-/**
- * dma_buf_kunmap_atomic - Unmap a page obtained by dma_buf_kmap_atomic.
- * @dmabuf:	[in]	buffer to unmap page from.
- * @page_num:	[in]	page in PAGE_SIZE units to unmap.
- * @vaddr:	[in]	kernel space pointer obtained from dma_buf_kmap_atomic.
- *
- * This call must always succeed.
- */
-void dma_buf_kunmap_atomic(struct dma_buf *dmabuf, unsigned long page_num,
-			   void *vaddr)
-{
-	WARN_ON(!dmabuf);
-
-	if (dmabuf->ops->unmap_atomic)
-		dmabuf->ops->unmap_atomic(dmabuf, page_num, vaddr);
-}
-EXPORT_SYMBOL_GPL(dma_buf_kunmap_atomic);
-
-/**
  * dma_buf_kmap - Map a page of the buffer object into kernel address space. The
  * same restrictions as for kmap and friends apply.
  * @dmabuf:	[in]	buffer to map page from.
@@ -907,6 +859,8 @@ void *dma_buf_kmap(struct dma_buf *dmabuf, unsigned long page_num)
 {
 	WARN_ON(!dmabuf);
 
+	if (!dmabuf->ops->map)
+		return NULL;
 	return dmabuf->ops->map(dmabuf, page_num);
 }
 EXPORT_SYMBOL_GPL(dma_buf_kmap);
diff --git a/drivers/dma-buf/dma-fence-array.c b/drivers/dma-buf/dma-fence-array.c
index dd1edfb27b61..a8c254497251 100644
--- a/drivers/dma-buf/dma-fence-array.c
+++ b/drivers/dma-buf/dma-fence-array.c
@@ -104,7 +104,6 @@ const struct dma_fence_ops dma_fence_array_ops = {
 	.get_timeline_name = dma_fence_array_get_timeline_name,
 	.enable_signaling = dma_fence_array_enable_signaling,
 	.signaled = dma_fence_array_signaled,
-	.wait = dma_fence_default_wait,
 	.release = dma_fence_array_release,
 };
 EXPORT_SYMBOL(dma_fence_array_ops);
diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c
index 4edb9fd3cf47..1551ca7df394 100644
--- a/drivers/dma-buf/dma-fence.c
+++ b/drivers/dma-buf/dma-fence.c
@@ -39,11 +39,42 @@ EXPORT_TRACEPOINT_SYMBOL(dma_fence_enable_signal);
 static atomic64_t dma_fence_context_counter = ATOMIC64_INIT(0);
 
 /**
+ * DOC: DMA fences overview
+ *
+ * DMA fences, represented by &struct dma_fence, are the kernel internal
+ * synchronization primitive for DMA operations like GPU rendering, video
+ * encoding/decoding, or displaying buffers on a screen.
+ *
+ * A fence is initialized using dma_fence_init() and completed using
+ * dma_fence_signal(). Fences are associated with a context, allocated through
+ * dma_fence_context_alloc(), and all fences on the same context are
+ * fully ordered.
+ *
+ * Since the purposes of fences is to facilitate cross-device and
+ * cross-application synchronization, there's multiple ways to use one:
+ *
+ * - Individual fences can be exposed as a &sync_file, accessed as a file
+ *   descriptor from userspace, created by calling sync_file_create(). This is
+ *   called explicit fencing, since userspace passes around explicit
+ *   synchronization points.
+ *
+ * - Some subsystems also have their own explicit fencing primitives, like
+ *   &drm_syncobj. Compared to &sync_file, a &drm_syncobj allows the underlying
+ *   fence to be updated.
+ *
+ * - Then there's also implicit fencing, where the synchronization points are
+ *   implicitly passed around as part of shared &dma_buf instances. Such
+ *   implicit fences are stored in &struct reservation_object through the
+ *   &dma_buf.resv pointer.
+ */
+
+/**
  * dma_fence_context_alloc - allocate an array of fence contexts
- * @num:	[in]	amount of contexts to allocate
+ * @num: amount of contexts to allocate
  *
- * This function will return the first index of the number of fences allocated.
- * The fence context is used for setting fence->context to a unique number.
+ * This function will return the first index of the number of fence contexts
+ * allocated.  The fence context is used for setting &dma_fence.context to a
+ * unique number by passing the context to dma_fence_init().
  */
 u64 dma_fence_context_alloc(unsigned num)
 {
@@ -59,10 +90,14 @@ EXPORT_SYMBOL(dma_fence_context_alloc);
  * Signal completion for software callbacks on a fence, this will unblock
  * dma_fence_wait() calls and run all the callbacks added with
  * dma_fence_add_callback(). Can be called multiple times, but since a fence
- * can only go from unsignaled to signaled state, it will only be effective
- * the first time.
+ * can only go from the unsignaled to the signaled state and not back, it will
+ * only be effective the first time.
  *
- * Unlike dma_fence_signal, this function must be called with fence->lock held.
+ * Unlike dma_fence_signal(), this function must be called with &dma_fence.lock
+ * held.
+ *
+ * Returns 0 on success and a negative error value when @fence has been
+ * signalled already.
  */
 int dma_fence_signal_locked(struct dma_fence *fence)
 {
@@ -102,8 +137,11 @@ EXPORT_SYMBOL(dma_fence_signal_locked);
  * Signal completion for software callbacks on a fence, this will unblock
  * dma_fence_wait() calls and run all the callbacks added with
  * dma_fence_add_callback(). Can be called multiple times, but since a fence
- * can only go from unsignaled to signaled state, it will only be effective
- * the first time.
+ * can only go from the unsignaled to the signaled state and not back, it will
+ * only be effective the first time.
+ *
+ * Returns 0 on success and a negative error value when @fence has been
+ * signalled already.
  */
 int dma_fence_signal(struct dma_fence *fence)
 {
@@ -136,9 +174,9 @@ EXPORT_SYMBOL(dma_fence_signal);
 /**
  * dma_fence_wait_timeout - sleep until the fence gets signaled
  * or until timeout elapses
- * @fence:	[in]	the fence to wait on
- * @intr:	[in]	if true, do an interruptible wait
- * @timeout:	[in]	timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT
+ * @fence: the fence to wait on
+ * @intr: if true, do an interruptible wait
+ * @timeout: timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT
  *
  * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or the
  * remaining timeout in jiffies on success. Other error values may be
@@ -148,6 +186,8 @@ EXPORT_SYMBOL(dma_fence_signal);
  * directly or indirectly (buf-mgr between reservation and committing)
  * holds a reference to the fence, otherwise the fence might be
  * freed before return, resulting in undefined behavior.
+ *
+ * See also dma_fence_wait() and dma_fence_wait_any_timeout().
  */
 signed long
 dma_fence_wait_timeout(struct dma_fence *fence, bool intr, signed long timeout)
@@ -158,12 +198,22 @@ dma_fence_wait_timeout(struct dma_fence *fence, bool intr, signed long timeout)
 		return -EINVAL;
 
 	trace_dma_fence_wait_start(fence);
-	ret = fence->ops->wait(fence, intr, timeout);
+	if (fence->ops->wait)
+		ret = fence->ops->wait(fence, intr, timeout);
+	else
+		ret = dma_fence_default_wait(fence, intr, timeout);
 	trace_dma_fence_wait_end(fence);
 	return ret;
 }
 EXPORT_SYMBOL(dma_fence_wait_timeout);
 
+/**
+ * dma_fence_release - default relese function for fences
+ * @kref: &dma_fence.recfount
+ *
+ * This is the default release functions for &dma_fence. Drivers shouldn't call
+ * this directly, but instead call dma_fence_put().
+ */
 void dma_fence_release(struct kref *kref)
 {
 	struct dma_fence *fence =
@@ -181,6 +231,13 @@ void dma_fence_release(struct kref *kref)
 }
 EXPORT_SYMBOL(dma_fence_release);
 
+/**
+ * dma_fence_free - default release function for &dma_fence.
+ * @fence: fence to release
+ *
+ * This is the default implementation for &dma_fence_ops.release. It calls
+ * kfree_rcu() on @fence.
+ */
 void dma_fence_free(struct dma_fence *fence)
 {
 	kfree_rcu(fence, rcu);
@@ -189,10 +246,11 @@ EXPORT_SYMBOL(dma_fence_free);
 
 /**
  * dma_fence_enable_sw_signaling - enable signaling on fence
- * @fence:	[in]	the fence to enable
+ * @fence: the fence to enable
  *
- * this will request for sw signaling to be enabled, to make the fence
- * complete as soon as possible
+ * This will request for sw signaling to be enabled, to make the fence
+ * complete as soon as possible. This calls &dma_fence_ops.enable_signaling
+ * internally.
  */
 void dma_fence_enable_sw_signaling(struct dma_fence *fence)
 {
@@ -200,7 +258,8 @@ void dma_fence_enable_sw_signaling(struct dma_fence *fence)
 
 	if (!test_and_set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
 			      &fence->flags) &&
-	    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
+	    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags) &&
+	    fence->ops->enable_signaling) {
 		trace_dma_fence_enable_signal(fence);
 
 		spin_lock_irqsave(fence->lock, flags);
@@ -216,24 +275,24 @@ EXPORT_SYMBOL(dma_fence_enable_sw_signaling);
 /**
  * dma_fence_add_callback - add a callback to be called when the fence
  * is signaled
- * @fence:	[in]	the fence to wait on
- * @cb:		[in]	the callback to register
- * @func:	[in]	the function to call
+ * @fence: the fence to wait on
+ * @cb: the callback to register
+ * @func: the function to call
  *
- * cb will be initialized by dma_fence_add_callback, no initialization
+ * @cb will be initialized by dma_fence_add_callback(), no initialization
  * by the caller is required. Any number of callbacks can be registered
  * to a fence, but a callback can only be registered to one fence at a time.
  *
  * Note that the callback can be called from an atomic context.  If
  * fence is already signaled, this function will return -ENOENT (and
- * *not* call the callback)
+ * *not* call the callback).
  *
  * Add a software callback to the fence. Same restrictions apply to
- * refcount as it does to dma_fence_wait, however the caller doesn't need to
- * keep a refcount to fence afterwards: when software access is enabled,
- * the creator of the fence is required to keep the fence alive until
- * after it signals with dma_fence_signal. The callback itself can be called
- * from irq context.
+ * refcount as it does to dma_fence_wait(), however the caller doesn't need to
+ * keep a refcount to fence afterward dma_fence_add_callback() has returned:
+ * when software access is enabled, the creator of the fence is required to keep
+ * the fence alive until after it signals with dma_fence_signal(). The callback
+ * itself can be called from irq context.
  *
  * Returns 0 in case of success, -ENOENT if the fence is already signaled
  * and -EINVAL in case of error.
@@ -260,7 +319,7 @@ int dma_fence_add_callback(struct dma_fence *fence, struct dma_fence_cb *cb,
 
 	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
 		ret = -ENOENT;
-	else if (!was_set) {
+	else if (!was_set && fence->ops->enable_signaling) {
 		trace_dma_fence_enable_signal(fence);
 
 		if (!fence->ops->enable_signaling(fence)) {
@@ -282,7 +341,7 @@ EXPORT_SYMBOL(dma_fence_add_callback);
 
 /**
  * dma_fence_get_status - returns the status upon completion
- * @fence: [in]	the dma_fence to query
+ * @fence: the dma_fence to query
  *
  * This wraps dma_fence_get_status_locked() to return the error status
  * condition on a signaled fence. See dma_fence_get_status_locked() for more
@@ -307,8 +366,8 @@ EXPORT_SYMBOL(dma_fence_get_status);
 
 /**
  * dma_fence_remove_callback - remove a callback from the signaling list
- * @fence:	[in]	the fence to wait on
- * @cb:		[in]	the callback to remove
+ * @fence: the fence to wait on
+ * @cb: the callback to remove
  *
  * Remove a previously queued callback from the fence. This function returns
  * true if the callback is successfully removed, or false if the fence has
@@ -319,6 +378,9 @@ EXPORT_SYMBOL(dma_fence_get_status);
  * doing, since deadlocks and race conditions could occur all too easily. For
  * this reason, it should only ever be done on hardware lockup recovery,
  * with a reference held to the fence.
+ *
+ * Behaviour is undefined if @cb has not been added to @fence using
+ * dma_fence_add_callback() beforehand.
  */
 bool
 dma_fence_remove_callback(struct dma_fence *fence, struct dma_fence_cb *cb)
@@ -355,9 +417,9 @@ dma_fence_default_wait_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
 /**
  * dma_fence_default_wait - default sleep until the fence gets signaled
  * or until timeout elapses
- * @fence:	[in]	the fence to wait on
- * @intr:	[in]	if true, do an interruptible wait
- * @timeout:	[in]	timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT
+ * @fence: the fence to wait on
+ * @intr: if true, do an interruptible wait
+ * @timeout: timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT
  *
  * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or the
  * remaining timeout in jiffies on success. If timeout is zero the value one is
@@ -388,7 +450,7 @@ dma_fence_default_wait(struct dma_fence *fence, bool intr, signed long timeout)
 	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
 		goto out;
 
-	if (!was_set) {
+	if (!was_set && fence->ops->enable_signaling) {
 		trace_dma_fence_enable_signal(fence);
 
 		if (!fence->ops->enable_signaling(fence)) {
@@ -450,12 +512,12 @@ dma_fence_test_signaled_any(struct dma_fence **fences, uint32_t count,
 /**
  * dma_fence_wait_any_timeout - sleep until any fence gets signaled
  * or until timeout elapses
- * @fences:	[in]	array of fences to wait on
- * @count:	[in]	number of fences to wait on
- * @intr:	[in]	if true, do an interruptible wait
- * @timeout:	[in]	timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT
- * @idx:       [out]	the first signaled fence index, meaningful only on
- *			positive return
+ * @fences: array of fences to wait on
+ * @count: number of fences to wait on
+ * @intr: if true, do an interruptible wait
+ * @timeout: timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT
+ * @idx: used to store the first signaled fence index, meaningful only on
+ *	positive return
  *
  * Returns -EINVAL on custom fence wait implementation, -ERESTARTSYS if
  * interrupted, 0 if the wait timed out, or the remaining timeout in jiffies
@@ -464,6 +526,8 @@ dma_fence_test_signaled_any(struct dma_fence **fences, uint32_t count,
  * Synchronous waits for the first fence in the array to be signaled. The
  * caller needs to hold a reference to all fences in the array, otherwise a
  * fence might be freed before return, resulting in undefined behavior.
+ *
+ * See also dma_fence_wait() and dma_fence_wait_timeout().
  */
 signed long
 dma_fence_wait_any_timeout(struct dma_fence **fences, uint32_t count,
@@ -496,11 +560,6 @@ dma_fence_wait_any_timeout(struct dma_fence **fences, uint32_t count,
 	for (i = 0; i < count; ++i) {
 		struct dma_fence *fence = fences[i];
 
-		if (fence->ops->wait != dma_fence_default_wait) {
-			ret = -EINVAL;
-			goto fence_rm_cb;
-		}
-
 		cb[i].task = current;
 		if (dma_fence_add_callback(fence, &cb[i].base,
 					   dma_fence_default_wait_cb)) {
@@ -541,27 +600,25 @@ EXPORT_SYMBOL(dma_fence_wait_any_timeout);
 
 /**
  * dma_fence_init - Initialize a custom fence.
- * @fence:	[in]	the fence to initialize
- * @ops:	[in]	the dma_fence_ops for operations on this fence
- * @lock:	[in]	the irqsafe spinlock to use for locking this fence
- * @context:	[in]	the execution context this fence is run on
- * @seqno:	[in]	a linear increasing sequence number for this context
+ * @fence: the fence to initialize
+ * @ops: the dma_fence_ops for operations on this fence
+ * @lock: the irqsafe spinlock to use for locking this fence
+ * @context: the execution context this fence is run on
+ * @seqno: a linear increasing sequence number for this context
  *
  * Initializes an allocated fence, the caller doesn't have to keep its
  * refcount after committing with this fence, but it will need to hold a
- * refcount again if dma_fence_ops.enable_signaling gets called. This can
- * be used for other implementing other types of fence.
+ * refcount again if &dma_fence_ops.enable_signaling gets called.
  *
  * context and seqno are used for easy comparison between fences, allowing
- * to check which fence is later by simply using dma_fence_later.
+ * to check which fence is later by simply using dma_fence_later().
  */
 void
 dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops,
 	       spinlock_t *lock, u64 context, unsigned seqno)
 {
 	BUG_ON(!lock);
-	BUG_ON(!ops || !ops->wait || !ops->enable_signaling ||
-	       !ops->get_driver_name || !ops->get_timeline_name);
+	BUG_ON(!ops || !ops->get_driver_name || !ops->get_timeline_name);
 
 	kref_init(&fence->refcount);
 	fence->ops = ops;
diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c
index 314eb1071cce..6c95f61a32e7 100644
--- a/drivers/dma-buf/reservation.c
+++ b/drivers/dma-buf/reservation.c
@@ -46,7 +46,7 @@
  * write-side updates.
  */
 
-DEFINE_WW_CLASS(reservation_ww_class);
+DEFINE_WD_CLASS(reservation_ww_class);
 EXPORT_SYMBOL(reservation_ww_class);
 
 struct lock_class_key reservation_seqcount_class;
@@ -141,6 +141,7 @@ reservation_object_add_shared_inplace(struct reservation_object *obj,
 	if (signaled) {
 		RCU_INIT_POINTER(fobj->shared[signaled_idx], fence);
 	} else {
+		BUG_ON(fobj->shared_count >= fobj->shared_max);
 		RCU_INIT_POINTER(fobj->shared[fobj->shared_count], fence);
 		fobj->shared_count++;
 	}
@@ -230,10 +231,9 @@ void reservation_object_add_shared_fence(struct reservation_object *obj,
 	old = reservation_object_get_list(obj);
 	obj->staged = NULL;
 
-	if (!fobj) {
-		BUG_ON(old->shared_count >= old->shared_max);
+	if (!fobj)
 		reservation_object_add_shared_inplace(obj, old, fence);
-	} else
+	else
 		reservation_object_add_shared_replace(obj, old, fobj, fence);
 }
 EXPORT_SYMBOL(reservation_object_add_shared_fence);
diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c
index 3d78ca89a605..53c1d6d36a64 100644
--- a/drivers/dma-buf/sw_sync.c
+++ b/drivers/dma-buf/sw_sync.c
@@ -188,7 +188,6 @@ static const struct dma_fence_ops timeline_fence_ops = {
 	.get_timeline_name = timeline_fence_get_timeline_name,
 	.enable_signaling = timeline_fence_enable_signaling,
 	.signaled = timeline_fence_signaled,
-	.wait = dma_fence_default_wait,
 	.release = timeline_fence_release,
 	.fence_value_str = timeline_fence_value_str,
 	.timeline_value_str = timeline_fence_timeline_value_str,
diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c
index b53fb618bbf6..b31c28b67ad3 100644
--- a/drivers/dma/pxa_dma.c
+++ b/drivers/dma/pxa_dma.c
@@ -179,6 +179,8 @@ static unsigned int pxad_drcmr(unsigned int line)
 	return 0x1000 + line * 4;
 }
 
+bool pxad_filter_fn(struct dma_chan *chan, void *param);
+
 /*
  * Debug fs
  */
@@ -760,6 +762,8 @@ static void pxad_free_chan_resources(struct dma_chan *dchan)
 	dma_pool_destroy(chan->desc_pool);
 	chan->desc_pool = NULL;
 
+	chan->drcmr = U32_MAX;
+	chan->prio = PXAD_PRIO_LOWEST;
 }
 
 static void pxad_free_desc(struct virt_dma_desc *vd)
@@ -1384,6 +1388,9 @@ static int pxad_init_dmadev(struct platform_device *op,
 		c = devm_kzalloc(&op->dev, sizeof(*c), GFP_KERNEL);
 		if (!c)
 			return -ENOMEM;
+
+		c->drcmr = U32_MAX;
+		c->prio = PXAD_PRIO_LOWEST;
 		c->vc.desc_free = pxad_free_desc;
 		vchan_init(&c->vc, &pdev->slave);
 		init_waitqueue_head(&c->wq_state);
@@ -1396,9 +1403,10 @@ static int pxad_probe(struct platform_device *op)
 {
 	struct pxad_device *pdev;
 	const struct of_device_id *of_id;
+	const struct dma_slave_map *slave_map = NULL;
 	struct mmp_dma_platdata *pdata = dev_get_platdata(&op->dev);
 	struct resource *iores;
-	int ret, dma_channels = 0, nb_requestors = 0;
+	int ret, dma_channels = 0, nb_requestors = 0, slave_map_cnt = 0;
 	const enum dma_slave_buswidth widths =
 		DMA_SLAVE_BUSWIDTH_1_BYTE   | DMA_SLAVE_BUSWIDTH_2_BYTES |
 		DMA_SLAVE_BUSWIDTH_4_BYTES;
@@ -1429,6 +1437,8 @@ static int pxad_probe(struct platform_device *op)
 	} else if (pdata && pdata->dma_channels) {
 		dma_channels = pdata->dma_channels;
 		nb_requestors = pdata->nb_requestors;
+		slave_map = pdata->slave_map;
+		slave_map_cnt = pdata->slave_map_cnt;
 	} else {
 		dma_channels = 32;	/* default 32 channel */
 	}
@@ -1440,6 +1450,9 @@ static int pxad_probe(struct platform_device *op)
 	pdev->slave.device_prep_dma_memcpy = pxad_prep_memcpy;
 	pdev->slave.device_prep_slave_sg = pxad_prep_slave_sg;
 	pdev->slave.device_prep_dma_cyclic = pxad_prep_dma_cyclic;
+	pdev->slave.filter.map = slave_map;
+	pdev->slave.filter.mapcnt = slave_map_cnt;
+	pdev->slave.filter.fn = pxad_filter_fn;
 
 	pdev->slave.copy_align = PDMA_ALIGNMENT;
 	pdev->slave.src_addr_widths = widths;
diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c
index d0d5c4dbe097..5762c3c383f2 100644
--- a/drivers/edac/altera_edac.c
+++ b/drivers/edac/altera_edac.c
@@ -730,7 +730,8 @@ static int altr_s10_sdram_probe(struct platform_device *pdev)
 			 S10_DDR0_IRQ_MASK)) {
 		edac_printk(KERN_ERR, EDAC_MC,
 			    "Error clearing SDRAM ECC count\n");
-		return -ENODEV;
+		ret = -ENODEV;
+		goto err2;
 	}
 
 	if (regmap_update_bits(drvdata->mc_vbase, priv->ecc_irq_en_offset,
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index 7481955160a4..20374b8248f0 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -1075,14 +1075,14 @@ int __init edac_mc_sysfs_init(void)
 
 	err = device_add(mci_pdev);
 	if (err < 0)
-		goto out_dev_free;
+		goto out_put_device;
 
 	edac_dbg(0, "device %s created\n", dev_name(mci_pdev));
 
 	return 0;
 
- out_dev_free:
-	kfree(mci_pdev);
+ out_put_device:
+	put_device(mci_pdev);
  out:
 	return err;
 }
diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index 8ed4dd9c571b..8e120bf60624 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -1177,15 +1177,14 @@ static int i7core_create_sysfs_devices(struct mem_ctl_info *mci)
 
 	rc = device_add(pvt->addrmatch_dev);
 	if (rc < 0)
-		return rc;
+		goto err_put_addrmatch;
 
 	if (!pvt->is_registered) {
 		pvt->chancounts_dev = kzalloc(sizeof(*pvt->chancounts_dev),
 					      GFP_KERNEL);
 		if (!pvt->chancounts_dev) {
-			put_device(pvt->addrmatch_dev);
-			device_del(pvt->addrmatch_dev);
-			return -ENOMEM;
+			rc = -ENOMEM;
+			goto err_del_addrmatch;
 		}
 
 		pvt->chancounts_dev->type = &all_channel_counts_type;
@@ -1199,9 +1198,18 @@ static int i7core_create_sysfs_devices(struct mem_ctl_info *mci)
 
 		rc = device_add(pvt->chancounts_dev);
 		if (rc < 0)
-			return rc;
+			goto err_put_chancounts;
 	}
 	return 0;
+
+err_put_chancounts:
+	put_device(pvt->chancounts_dev);
+err_del_addrmatch:
+	device_del(pvt->addrmatch_dev);
+err_put_addrmatch:
+	put_device(pvt->addrmatch_dev);
+
+	return rc;
 }
 
 static void i7core_delete_sysfs_devices(struct mem_ctl_info *mci)
@@ -1211,11 +1219,11 @@ static void i7core_delete_sysfs_devices(struct mem_ctl_info *mci)
 	edac_dbg(1, "\n");
 
 	if (!pvt->is_registered) {
-		put_device(pvt->chancounts_dev);
 		device_del(pvt->chancounts_dev);
+		put_device(pvt->chancounts_dev);
 	}
-	put_device(pvt->addrmatch_dev);
 	device_del(pvt->addrmatch_dev);
+	put_device(pvt->addrmatch_dev);
 }
 
 /****************************************************************************
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 4a89c8093307..07726fb00321 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -352,6 +352,7 @@ struct pci_id_table {
 
 struct sbridge_dev {
 	struct list_head	list;
+	int			seg;
 	u8			bus, mc;
 	u8			node_id, source_id;
 	struct pci_dev		**pdev;
@@ -729,7 +730,8 @@ static inline int numcol(u32 mtr)
 	return 1 << cols;
 }
 
-static struct sbridge_dev *get_sbridge_dev(u8 bus, enum domain dom, int multi_bus,
+static struct sbridge_dev *get_sbridge_dev(int seg, u8 bus, enum domain dom,
+					   int multi_bus,
 					   struct sbridge_dev *prev)
 {
 	struct sbridge_dev *sbridge_dev;
@@ -747,14 +749,15 @@ static struct sbridge_dev *get_sbridge_dev(u8 bus, enum domain dom, int multi_bu
 				      : sbridge_edac_list.next, struct sbridge_dev, list);
 
 	list_for_each_entry_from(sbridge_dev, &sbridge_edac_list, list) {
-		if (sbridge_dev->bus == bus && (dom == SOCK || dom == sbridge_dev->dom))
+		if ((sbridge_dev->seg == seg) && (sbridge_dev->bus == bus) &&
+				(dom == SOCK || dom == sbridge_dev->dom))
 			return sbridge_dev;
 	}
 
 	return NULL;
 }
 
-static struct sbridge_dev *alloc_sbridge_dev(u8 bus, enum domain dom,
+static struct sbridge_dev *alloc_sbridge_dev(int seg, u8 bus, enum domain dom,
 					     const struct pci_id_table *table)
 {
 	struct sbridge_dev *sbridge_dev;
@@ -771,6 +774,7 @@ static struct sbridge_dev *alloc_sbridge_dev(u8 bus, enum domain dom,
 		return NULL;
 	}
 
+	sbridge_dev->seg = seg;
 	sbridge_dev->bus = bus;
 	sbridge_dev->dom = dom;
 	sbridge_dev->n_devs = table->n_devs_per_imc;
@@ -2246,6 +2250,7 @@ static int sbridge_get_onedevice(struct pci_dev **prev,
 	struct sbridge_dev *sbridge_dev = NULL;
 	const struct pci_id_descr *dev_descr = &table->descr[devno];
 	struct pci_dev *pdev = NULL;
+	int seg = 0;
 	u8 bus = 0;
 	int i = 0;
 
@@ -2276,10 +2281,12 @@ static int sbridge_get_onedevice(struct pci_dev **prev,
 		/* End of list, leave */
 		return -ENODEV;
 	}
+	seg = pci_domain_nr(pdev->bus);
 	bus = pdev->bus->number;
 
 next_imc:
-	sbridge_dev = get_sbridge_dev(bus, dev_descr->dom, multi_bus, sbridge_dev);
+	sbridge_dev = get_sbridge_dev(seg, bus, dev_descr->dom,
+				      multi_bus, sbridge_dev);
 	if (!sbridge_dev) {
 		/* If the HA1 wasn't found, don't create EDAC second memory controller */
 		if (dev_descr->dom == IMC1 && devno != 1) {
@@ -2292,7 +2299,7 @@ next_imc:
 		if (dev_descr->dom == SOCK)
 			goto out_imc;
 
-		sbridge_dev = alloc_sbridge_dev(bus, dev_descr->dom, table);
+		sbridge_dev = alloc_sbridge_dev(seg, bus, dev_descr->dom, table);
 		if (!sbridge_dev) {
 			pci_dev_put(pdev);
 			return -ENOMEM;
diff --git a/drivers/edac/thunderx_edac.c b/drivers/edac/thunderx_edac.c
index 4803c6468bab..c009d94f40c5 100644
--- a/drivers/edac/thunderx_edac.c
+++ b/drivers/edac/thunderx_edac.c
@@ -408,26 +408,29 @@ static ssize_t thunderx_lmc_inject_ecc_write(struct file *file,
 					     size_t count, loff_t *ppos)
 {
 	struct thunderx_lmc *lmc = file->private_data;
-
 	unsigned int cline_size = cache_line_size();
-
-	u8 tmp[cline_size];
+	u8 *tmp;
 	void __iomem *addr;
 	unsigned int offs, timeout = 100000;
 
 	atomic_set(&lmc->ecc_int, 0);
 
 	lmc->mem = alloc_pages_node(lmc->node, GFP_KERNEL, 0);
-
 	if (!lmc->mem)
 		return -ENOMEM;
 
+	tmp = kmalloc(cline_size, GFP_KERNEL);
+	if (!tmp) {
+		__free_pages(lmc->mem, 0);
+		return -ENOMEM;
+	}
+
 	addr = page_address(lmc->mem);
 
 	while (!atomic_read(&lmc->ecc_int) && timeout--) {
 		stop_machine(inject_ecc_fn, lmc, NULL);
 
-		for (offs = 0; offs < PAGE_SIZE; offs += sizeof(tmp)) {
+		for (offs = 0; offs < PAGE_SIZE; offs += cline_size) {
 			/*
 			 * Do a load from the previously rigged location
 			 * This should generate an error interrupt.
@@ -437,6 +440,7 @@ static ssize_t thunderx_lmc_inject_ecc_write(struct file *file,
 		}
 	}
 
+	kfree(tmp);
 	__free_pages(lmc->mem, 0);
 
 	return count;
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 781a4a337557..d8e159feb573 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -87,6 +87,18 @@ config EFI_RUNTIME_WRAPPERS
 config EFI_ARMSTUB
 	bool
 
+config EFI_ARMSTUB_DTB_LOADER
+	bool "Enable the DTB loader"
+	depends on EFI_ARMSTUB
+	help
+	  Select this config option to add support for the dtb= command
+	  line parameter, allowing a device tree blob to be loaded into
+	  memory from the EFI System Partition by the stub.
+
+	  The device tree is typically provided by the platform or by
+	  the bootloader, so this option is mostly for development
+	  purposes only.
+
 config EFI_BOOTLOADER_CONTROL
 	tristate "EFI Bootloader Control"
 	depends on EFI_VARS
diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c
index b5214c143fee..388a929baf95 100644
--- a/drivers/firmware/efi/arm-init.c
+++ b/drivers/firmware/efi/arm-init.c
@@ -259,7 +259,6 @@ void __init efi_init(void)
 
 	reserve_regions();
 	efi_esrt_init();
-	efi_memmap_unmap();
 
 	memblock_reserve(params.mmap & PAGE_MASK,
 			 PAGE_ALIGN(params.mmap_size +
diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
index 5889cbea60b8..922cfb813109 100644
--- a/drivers/firmware/efi/arm-runtime.c
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -110,11 +110,20 @@ static int __init arm_enable_runtime_services(void)
 {
 	u64 mapsize;
 
-	if (!efi_enabled(EFI_BOOT)) {
+	if (!efi_enabled(EFI_BOOT) || !efi_enabled(EFI_MEMMAP)) {
 		pr_info("EFI services will not be available.\n");
 		return 0;
 	}
 
+	efi_memmap_unmap();
+
+	mapsize = efi.memmap.desc_size * efi.memmap.nr_map;
+
+	if (efi_memmap_init_late(efi.memmap.phys_map, mapsize)) {
+		pr_err("Failed to remap EFI memory map\n");
+		return 0;
+	}
+
 	if (efi_runtime_disabled()) {
 		pr_info("EFI runtime services will be disabled.\n");
 		return 0;
@@ -127,13 +136,6 @@ static int __init arm_enable_runtime_services(void)
 
 	pr_info("Remapping and enabling EFI services.\n");
 
-	mapsize = efi.memmap.desc_size * efi.memmap.nr_map;
-
-	if (efi_memmap_init_late(efi.memmap.phys_map, mapsize)) {
-		pr_err("Failed to remap EFI memory map\n");
-		return -ENOMEM;
-	}
-
 	if (!efi_virtmap_init()) {
 		pr_err("UEFI virtual mapping missing or invalid -- runtime services will not be available\n");
 		return -ENOMEM;
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 3bf0dca378a6..a7902fccdcfa 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -48,8 +48,21 @@ u64 cper_next_record_id(void)
 {
 	static atomic64_t seq;
 
-	if (!atomic64_read(&seq))
-		atomic64_set(&seq, ((u64)get_seconds()) << 32);
+	if (!atomic64_read(&seq)) {
+		time64_t time = ktime_get_real_seconds();
+
+		/*
+		 * This code is unlikely to still be needed in year 2106,
+		 * but just in case, let's use a few more bits for timestamps
+		 * after y2038 to be sure they keep increasing monotonically
+		 * for the next few hundred years...
+		 */
+		if (time < 0x80000000)
+			atomic64_set(&seq, (ktime_get_real_seconds()) << 32);
+		else
+			atomic64_set(&seq, 0x8000000000000000ull |
+					   ktime_get_real_seconds() << 24);
+	}
 
 	return atomic64_inc_return(&seq);
 }
@@ -459,7 +472,7 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata
 		else
 			goto err_section_too_small;
 #if defined(CONFIG_ARM64) || defined(CONFIG_ARM)
-	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PROC_ARM)) {
+	} else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
 		struct cper_sec_proc_arm *arm_err = acpi_hest_get_payload(gdata);
 
 		printk("%ssection_type: ARM processor error\n", newpfx);
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 232f4915223b..2a29dd9c986d 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -82,8 +82,11 @@ struct mm_struct efi_mm = {
 	.mmap_sem		= __RWSEM_INITIALIZER(efi_mm.mmap_sem),
 	.page_table_lock	= __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock),
 	.mmlist			= LIST_HEAD_INIT(efi_mm.mmlist),
+	.cpu_bitmap		= { [BITS_TO_LONGS(NR_CPUS)] = 0},
 };
 
+struct workqueue_struct *efi_rts_wq;
+
 static bool disable_runtime;
 static int __init setup_noefi(char *arg)
 {
@@ -337,6 +340,18 @@ static int __init efisubsys_init(void)
 	if (!efi_enabled(EFI_BOOT))
 		return 0;
 
+	/*
+	 * Since we process only one efi_runtime_service() at a time, an
+	 * ordered workqueue (which creates only one execution context)
+	 * should suffice all our needs.
+	 */
+	efi_rts_wq = alloc_ordered_workqueue("efi_rts_wq", 0);
+	if (!efi_rts_wq) {
+		pr_err("Creating efi_rts_wq failed, EFI runtime services disabled.\n");
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+		return 0;
+	}
+
 	/* We register the efi directory at /sys/firmware/efi */
 	efi_kobj = kobject_create_and_add("efi", firmware_kobj);
 	if (!efi_kobj) {
@@ -388,7 +403,7 @@ subsys_initcall(efisubsys_init);
  * and if so, populate the supplied memory descriptor with the appropriate
  * data.
  */
-int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
+int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
 {
 	efi_memory_desc_t *md;
 
@@ -406,12 +421,6 @@ int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
 		u64 size;
 		u64 end;
 
-		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
-		    md->type != EFI_BOOT_SERVICES_DATA &&
-		    md->type != EFI_RUNTIME_SERVICES_DATA) {
-			continue;
-		}
-
 		size = md->num_pages << EFI_PAGE_SHIFT;
 		end = md->phys_addr + size;
 		if (phys_addr >= md->phys_addr && phys_addr < end) {
diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
index 1ab80e06e7c5..5d06bd247d07 100644
--- a/drivers/firmware/efi/esrt.c
+++ b/drivers/firmware/efi/esrt.c
@@ -250,7 +250,10 @@ void __init efi_esrt_init(void)
 		return;
 
 	rc = efi_mem_desc_lookup(efi.esrt, &md);
-	if (rc < 0) {
+	if (rc < 0 ||
+	    (!(md.attribute & EFI_MEMORY_RUNTIME) &&
+	     md.type != EFI_BOOT_SERVICES_DATA &&
+	     md.type != EFI_RUNTIME_SERVICES_DATA)) {
 		pr_warn("ESRT header is not in the memory map.\n");
 		return;
 	}
@@ -326,7 +329,8 @@ void __init efi_esrt_init(void)
 
 	end = esrt_data + size;
 	pr_info("Reserving ESRT space from %pa to %pa.\n", &esrt_data, &end);
-	efi_mem_reserve(esrt_data, esrt_data_size);
+	if (md.type == EFI_BOOT_SERVICES_DATA)
+		efi_mem_reserve(esrt_data, esrt_data_size);
 
 	pr_debug("esrt-init: loaded.\n");
 }
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index a34e9290a699..88c322d7c71e 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -11,7 +11,10 @@ cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ -O2 \
 				   -fPIC -fno-strict-aliasing -mno-red-zone \
 				   -mno-mmx -mno-sse -fshort-wchar
 
-cflags-$(CONFIG_ARM64)		:= $(subst -pg,,$(KBUILD_CFLAGS)) -fpie
+# arm64 uses the full KBUILD_CFLAGS so it's necessary to explicitly
+# disable the stackleak plugin
+cflags-$(CONFIG_ARM64)		:= $(subst -pg,,$(KBUILD_CFLAGS)) -fpie \
+				   $(DISABLE_STACKLEAK_PLUGIN)
 cflags-$(CONFIG_ARM)		:= $(subst -pg,,$(KBUILD_CFLAGS)) \
 				   -fno-builtin -fpic -mno-single-pic-base
 
@@ -20,7 +23,7 @@ cflags-$(CONFIG_EFI_ARMSTUB)	+= -I$(srctree)/scripts/dtc/libfdt
 KBUILD_CFLAGS			:= $(cflags-y) -DDISABLE_BRANCH_PROFILING \
 				   -D__NO_FORTIFY \
 				   $(call cc-option,-ffreestanding) \
-				   $(call cc-option,-fno-stack-protector)
+				   $(call cc-option,-fno-stack-protector) \
 
 GCOV_PROFILE			:= n
 KASAN_SANITIZE			:= n
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index 01a9d78ee415..6920033de6d4 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -40,31 +40,6 @@
 
 static u64 virtmap_base = EFI_RT_VIRTUAL_BASE;
 
-efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
-			     void *__image, void **__fh)
-{
-	efi_file_io_interface_t *io;
-	efi_loaded_image_t *image = __image;
-	efi_file_handle_t *fh;
-	efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
-	efi_status_t status;
-	void *handle = (void *)(unsigned long)image->device_handle;
-
-	status = sys_table_arg->boottime->handle_protocol(handle,
-				 &fs_proto, (void **)&io);
-	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table_arg, "Failed to handle fs_proto\n");
-		return status;
-	}
-
-	status = io->open_volume(io, &fh);
-	if (status != EFI_SUCCESS)
-		efi_printk(sys_table_arg, "Failed to open volume\n");
-
-	*__fh = fh;
-	return status;
-}
-
 void efi_char16_printk(efi_system_table_t *sys_table_arg,
 			      efi_char16_t *str)
 {
@@ -202,9 +177,10 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
 	 * 'dtb=' unless UEFI Secure Boot is disabled.  We assume that secure
 	 * boot is enabled if we can't determine its state.
 	 */
-	if (secure_boot != efi_secureboot_mode_disabled &&
-	    strstr(cmdline_ptr, "dtb=")) {
-		pr_efi(sys_table, "Ignoring DTB from command line.\n");
+	if (!IS_ENABLED(CONFIG_EFI_ARMSTUB_DTB_LOADER) ||
+	     secure_boot != efi_secureboot_mode_disabled) {
+		if (strstr(cmdline_ptr, "dtb="))
+			pr_efi(sys_table, "Ignoring DTB from command line.\n");
 	} else {
 		status = handle_cmdline_files(sys_table, image, cmdline_ptr,
 					      "dtb=",
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index 50a9cab5a834..e94975f4655b 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -413,6 +413,34 @@ static efi_status_t efi_file_close(void *handle)
 	return efi_call_proto(efi_file_handle, close, handle);
 }
 
+static efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
+				    efi_loaded_image_t *image,
+				    efi_file_handle_t **__fh)
+{
+	efi_file_io_interface_t *io;
+	efi_file_handle_t *fh;
+	efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
+	efi_status_t status;
+	void *handle = (void *)(unsigned long)efi_table_attr(efi_loaded_image,
+							     device_handle,
+							     image);
+
+	status = efi_call_early(handle_protocol, handle,
+				&fs_proto, (void **)&io);
+	if (status != EFI_SUCCESS) {
+		efi_printk(sys_table_arg, "Failed to handle fs_proto\n");
+		return status;
+	}
+
+	status = efi_call_proto(efi_file_io_interface, open_volume, io, &fh);
+	if (status != EFI_SUCCESS)
+		efi_printk(sys_table_arg, "Failed to open volume\n");
+	else
+		*__fh = fh;
+
+	return status;
+}
+
 /*
  * Parse the ASCII string 'cmdline' for EFI options, denoted by the efi=
  * option, e.g. efi=nochunk.
@@ -563,8 +591,7 @@ efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg,
 
 		/* Only open the volume once. */
 		if (!i) {
-			status = efi_open_volume(sys_table_arg, image,
-						 (void **)&fh);
+			status = efi_open_volume(sys_table_arg, image, &fh);
 			if (status != EFI_SUCCESS)
 				goto free_files;
 		}
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index f59564b72ddc..32799cf039ef 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -36,9 +36,6 @@ extern int __pure is_quiet(void);
 
 void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
 
-efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image,
-			     void **__fh);
-
 unsigned long get_dram_base(efi_system_table_t *sys_table_arg);
 
 efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c
index ae54870b2788..aa66cbf23512 100644
--- a/drivers/firmware/efi/runtime-wrappers.c
+++ b/drivers/firmware/efi/runtime-wrappers.c
@@ -1,6 +1,15 @@
 /*
  * runtime-wrappers.c - Runtime Services function call wrappers
  *
+ * Implementation summary:
+ * -----------------------
+ * 1. When user/kernel thread requests to execute efi_runtime_service(),
+ * enqueue work to efi_rts_wq.
+ * 2. Caller thread waits for completion until the work is finished
+ * because it's dependent on the return status and execution of
+ * efi_runtime_service().
+ * For instance, get_variable() and get_next_variable().
+ *
  * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
  *
  * Split off from arch/x86/platform/efi/efi.c
@@ -22,6 +31,9 @@
 #include <linux/mutex.h>
 #include <linux/semaphore.h>
 #include <linux/stringify.h>
+#include <linux/workqueue.h>
+#include <linux/completion.h>
+
 #include <asm/efi.h>
 
 /*
@@ -33,6 +45,76 @@
 #define __efi_call_virt(f, args...) \
 	__efi_call_virt_pointer(efi.systab->runtime, f, args)
 
+/* efi_runtime_service() function identifiers */
+enum efi_rts_ids {
+	GET_TIME,
+	SET_TIME,
+	GET_WAKEUP_TIME,
+	SET_WAKEUP_TIME,
+	GET_VARIABLE,
+	GET_NEXT_VARIABLE,
+	SET_VARIABLE,
+	QUERY_VARIABLE_INFO,
+	GET_NEXT_HIGH_MONO_COUNT,
+	UPDATE_CAPSULE,
+	QUERY_CAPSULE_CAPS,
+};
+
+/*
+ * efi_runtime_work:	Details of EFI Runtime Service work
+ * @arg<1-5>:		EFI Runtime Service function arguments
+ * @status:		Status of executing EFI Runtime Service
+ * @efi_rts_id:		EFI Runtime Service function identifier
+ * @efi_rts_comp:	Struct used for handling completions
+ */
+struct efi_runtime_work {
+	void *arg1;
+	void *arg2;
+	void *arg3;
+	void *arg4;
+	void *arg5;
+	efi_status_t status;
+	struct work_struct work;
+	enum efi_rts_ids efi_rts_id;
+	struct completion efi_rts_comp;
+};
+
+/*
+ * efi_queue_work:	Queue efi_runtime_service() and wait until it's done
+ * @rts:		efi_runtime_service() function identifier
+ * @rts_arg<1-5>:	efi_runtime_service() function arguments
+ *
+ * Accesses to efi_runtime_services() are serialized by a binary
+ * semaphore (efi_runtime_lock) and caller waits until the work is
+ * finished, hence _only_ one work is queued at a time and the caller
+ * thread waits for completion.
+ */
+#define efi_queue_work(_rts, _arg1, _arg2, _arg3, _arg4, _arg5)		\
+({									\
+	struct efi_runtime_work efi_rts_work;				\
+	efi_rts_work.status = EFI_ABORTED;				\
+									\
+	init_completion(&efi_rts_work.efi_rts_comp);			\
+	INIT_WORK_ONSTACK(&efi_rts_work.work, efi_call_rts);		\
+	efi_rts_work.arg1 = _arg1;					\
+	efi_rts_work.arg2 = _arg2;					\
+	efi_rts_work.arg3 = _arg3;					\
+	efi_rts_work.arg4 = _arg4;					\
+	efi_rts_work.arg5 = _arg5;					\
+	efi_rts_work.efi_rts_id = _rts;					\
+									\
+	/*								\
+	 * queue_work() returns 0 if work was already on queue,         \
+	 * _ideally_ this should never happen.                          \
+	 */								\
+	if (queue_work(efi_rts_wq, &efi_rts_work.work))			\
+		wait_for_completion(&efi_rts_work.efi_rts_comp);	\
+	else								\
+		pr_err("Failed to queue work to efi_rts_wq.\n");	\
+									\
+	efi_rts_work.status;						\
+})
+
 void efi_call_virt_check_flags(unsigned long flags, const char *call)
 {
 	unsigned long cur_flags, mismatch;
@@ -90,13 +172,98 @@ void efi_call_virt_check_flags(unsigned long flags, const char *call)
  */
 static DEFINE_SEMAPHORE(efi_runtime_lock);
 
+/*
+ * Calls the appropriate efi_runtime_service() with the appropriate
+ * arguments.
+ *
+ * Semantics followed by efi_call_rts() to understand efi_runtime_work:
+ * 1. If argument was a pointer, recast it from void pointer to original
+ * pointer type.
+ * 2. If argument was a value, recast it from void pointer to original
+ * pointer type and dereference it.
+ */
+static void efi_call_rts(struct work_struct *work)
+{
+	struct efi_runtime_work *efi_rts_work;
+	void *arg1, *arg2, *arg3, *arg4, *arg5;
+	efi_status_t status = EFI_NOT_FOUND;
+
+	efi_rts_work = container_of(work, struct efi_runtime_work, work);
+	arg1 = efi_rts_work->arg1;
+	arg2 = efi_rts_work->arg2;
+	arg3 = efi_rts_work->arg3;
+	arg4 = efi_rts_work->arg4;
+	arg5 = efi_rts_work->arg5;
+
+	switch (efi_rts_work->efi_rts_id) {
+	case GET_TIME:
+		status = efi_call_virt(get_time, (efi_time_t *)arg1,
+				       (efi_time_cap_t *)arg2);
+		break;
+	case SET_TIME:
+		status = efi_call_virt(set_time, (efi_time_t *)arg1);
+		break;
+	case GET_WAKEUP_TIME:
+		status = efi_call_virt(get_wakeup_time, (efi_bool_t *)arg1,
+				       (efi_bool_t *)arg2, (efi_time_t *)arg3);
+		break;
+	case SET_WAKEUP_TIME:
+		status = efi_call_virt(set_wakeup_time, *(efi_bool_t *)arg1,
+				       (efi_time_t *)arg2);
+		break;
+	case GET_VARIABLE:
+		status = efi_call_virt(get_variable, (efi_char16_t *)arg1,
+				       (efi_guid_t *)arg2, (u32 *)arg3,
+				       (unsigned long *)arg4, (void *)arg5);
+		break;
+	case GET_NEXT_VARIABLE:
+		status = efi_call_virt(get_next_variable, (unsigned long *)arg1,
+				       (efi_char16_t *)arg2,
+				       (efi_guid_t *)arg3);
+		break;
+	case SET_VARIABLE:
+		status = efi_call_virt(set_variable, (efi_char16_t *)arg1,
+				       (efi_guid_t *)arg2, *(u32 *)arg3,
+				       *(unsigned long *)arg4, (void *)arg5);
+		break;
+	case QUERY_VARIABLE_INFO:
+		status = efi_call_virt(query_variable_info, *(u32 *)arg1,
+				       (u64 *)arg2, (u64 *)arg3, (u64 *)arg4);
+		break;
+	case GET_NEXT_HIGH_MONO_COUNT:
+		status = efi_call_virt(get_next_high_mono_count, (u32 *)arg1);
+		break;
+	case UPDATE_CAPSULE:
+		status = efi_call_virt(update_capsule,
+				       (efi_capsule_header_t **)arg1,
+				       *(unsigned long *)arg2,
+				       *(unsigned long *)arg3);
+		break;
+	case QUERY_CAPSULE_CAPS:
+		status = efi_call_virt(query_capsule_caps,
+				       (efi_capsule_header_t **)arg1,
+				       *(unsigned long *)arg2, (u64 *)arg3,
+				       (int *)arg4);
+		break;
+	default:
+		/*
+		 * Ideally, we should never reach here because a caller of this
+		 * function should have put the right efi_runtime_service()
+		 * function identifier into efi_rts_work->efi_rts_id
+		 */
+		pr_err("Requested executing invalid EFI Runtime Service.\n");
+	}
+	efi_rts_work->status = status;
+	complete(&efi_rts_work->efi_rts_comp);
+}
+
 static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 {
 	efi_status_t status;
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_time, tm, tc);
+	status = efi_queue_work(GET_TIME, tm, tc, NULL, NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -107,7 +274,7 @@ static efi_status_t virt_efi_set_time(efi_time_t *tm)
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(set_time, tm);
+	status = efi_queue_work(SET_TIME, tm, NULL, NULL, NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -120,7 +287,8 @@ static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_wakeup_time, enabled, pending, tm);
+	status = efi_queue_work(GET_WAKEUP_TIME, enabled, pending, tm, NULL,
+				NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -131,7 +299,8 @@ static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(set_wakeup_time, enabled, tm);
+	status = efi_queue_work(SET_WAKEUP_TIME, &enabled, tm, NULL, NULL,
+				NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -146,8 +315,8 @@ static efi_status_t virt_efi_get_variable(efi_char16_t *name,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_variable, name, vendor, attr, data_size,
-			       data);
+	status = efi_queue_work(GET_VARIABLE, name, vendor, attr, data_size,
+				data);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -160,7 +329,8 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_next_variable, name_size, name, vendor);
+	status = efi_queue_work(GET_NEXT_VARIABLE, name_size, name, vendor,
+				NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -175,8 +345,8 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(set_variable, name, vendor, attr, data_size,
-			       data);
+	status = efi_queue_work(SET_VARIABLE, name, vendor, &attr, &data_size,
+				data);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -210,8 +380,8 @@ static efi_status_t virt_efi_query_variable_info(u32 attr,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(query_variable_info, attr, storage_space,
-			       remaining_space, max_variable_size);
+	status = efi_queue_work(QUERY_VARIABLE_INFO, &attr, storage_space,
+				remaining_space, max_variable_size, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -242,7 +412,8 @@ static efi_status_t virt_efi_get_next_high_mono_count(u32 *count)
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_next_high_mono_count, count);
+	status = efi_queue_work(GET_NEXT_HIGH_MONO_COUNT, count, NULL, NULL,
+				NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -272,7 +443,8 @@ static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(update_capsule, capsules, count, sg_list);
+	status = efi_queue_work(UPDATE_CAPSULE, capsules, &count, &sg_list,
+				NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -289,8 +461,8 @@ static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(query_capsule_caps, capsules, count, max_size,
-			       reset_type);
+	status = efi_queue_work(QUERY_CAPSULE_CAPS, capsules, &count,
+				max_size, reset_type, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c
index 14fedbeca724..039e0f91dba8 100644
--- a/drivers/firmware/qemu_fw_cfg.c
+++ b/drivers/firmware/qemu_fw_cfg.c
@@ -28,6 +28,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/mod_devicetable.h>
 #include <linux/platform_device.h>
 #include <linux/acpi.h>
 #include <linux/slab.h>
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 71c0ab46f216..f7a0f576f918 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -359,6 +359,15 @@ config GPIO_MPC8XXX
 	  Say Y here if you're going to use hardware that connects to the
 	  MPC512x/831x/834x/837x/8572/8610/QorIQ GPIOs.
 
+config GPIO_MT7621
+	bool "Mediatek MT7621 GPIO Support"
+	depends on SOC_MT7620 || SOC_MT7621 || COMPILE_TEST
+	depends on OF_GPIO
+	select GPIO_GENERIC
+	select GPIOLIB_IRQCHIP
+	help
+	  Say yes here to support the Mediatek MT7621 SoC GPIO device
+
 config GPIO_MVEBU
 	def_bool y
 	depends on PLAT_ORION || ARCH_MVEBU
@@ -684,7 +693,8 @@ config GPIO_IT87
 	  Say yes here to support GPIO functionality of IT87xx Super I/O chips.
 
 	  This driver is tested with ITE IT8728 and IT8732 Super I/O chips, and
-	  supports the IT8761E, IT8620E and IT8628E Super I/O chip as well.
+	  supports the IT8761E, IT8613, IT8620E, and IT8628E Super I/O chips as
+	  well.
 
 	  To compile this driver as a module, choose M here: the module will
 	  be called gpio_it87
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index 1324c8f966a7..fc77989371be 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -88,6 +88,7 @@ obj-$(CONFIG_GPIO_MOCKUP)      += gpio-mockup.o
 obj-$(CONFIG_GPIO_MPC5200)	+= gpio-mpc5200.o
 obj-$(CONFIG_GPIO_MPC8XXX)	+= gpio-mpc8xxx.o
 obj-$(CONFIG_GPIO_MSIC)		+= gpio-msic.o
+obj-$(CONFIG_GPIO_MT7621)		+= gpio-mt7621.o
 obj-$(CONFIG_GPIO_MVEBU)        += gpio-mvebu.o
 obj-$(CONFIG_GPIO_MXC)		+= gpio-mxc.o
 obj-$(CONFIG_GPIO_MXS)		+= gpio-mxs.o
diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c
index b31ae16170e7..2342e154029b 100644
--- a/drivers/gpio/gpio-aspeed.c
+++ b/drivers/gpio/gpio-aspeed.c
@@ -12,6 +12,7 @@
 #include <asm/div64.h>
 #include <linux/clk.h>
 #include <linux/gpio/driver.h>
+#include <linux/gpio/aspeed.h>
 #include <linux/hashtable.h>
 #include <linux/init.h>
 #include <linux/io.h>
@@ -22,6 +23,15 @@
 #include <linux/spinlock.h>
 #include <linux/string.h>
 
+/*
+ * These two headers aren't meant to be used by GPIO drivers. We need
+ * them in order to access gpio_chip_hwgpio() which we need to implement
+ * the aspeed specific API which allows the coprocessor to request
+ * access to some GPIOs and to arbitrate between coprocessor and ARM.
+ */
+#include <linux/gpio/consumer.h>
+#include "gpiolib.h"
+
 struct aspeed_bank_props {
 	unsigned int bank;
 	u32 input;
@@ -56,83 +66,130 @@ struct aspeed_gpio {
 	struct clk *clk;
 
 	u32 *dcache;
+	u8 *cf_copro_bankmap;
 };
 
 struct aspeed_gpio_bank {
-	uint16_t	val_regs;
+	uint16_t	val_regs;	/* +0: Rd: read input value, Wr: set write latch
+					 * +4: Rd/Wr: Direction (0=in, 1=out)
+					 */
+	uint16_t	rdata_reg;	/*     Rd: read write latch, Wr: <none>  */
 	uint16_t	irq_regs;
 	uint16_t	debounce_regs;
 	uint16_t	tolerance_regs;
+	uint16_t	cmdsrc_regs;
 	const char	names[4][3];
 };
 
+/*
+ * Note: The "value" register returns the input value sampled on the
+ *       line even when the GPIO is configured as an output. Since
+ *       that input goes through synchronizers, writing, then reading
+ *       back may not return the written value right away.
+ *
+ *       The "rdata" register returns the content of the write latch
+ *       and thus can be used to read back what was last written
+ *       reliably.
+ */
+
 static const int debounce_timers[4] = { 0x00, 0x50, 0x54, 0x58 };
 
+static const struct aspeed_gpio_copro_ops *copro_ops;
+static void *copro_data;
+
 static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 	{
 		.val_regs = 0x0000,
+		.rdata_reg = 0x00c0,
 		.irq_regs = 0x0008,
 		.debounce_regs = 0x0040,
 		.tolerance_regs = 0x001c,
+		.cmdsrc_regs = 0x0060,
 		.names = { "A", "B", "C", "D" },
 	},
 	{
 		.val_regs = 0x0020,
+		.rdata_reg = 0x00c4,
 		.irq_regs = 0x0028,
 		.debounce_regs = 0x0048,
 		.tolerance_regs = 0x003c,
+		.cmdsrc_regs = 0x0068,
 		.names = { "E", "F", "G", "H" },
 	},
 	{
 		.val_regs = 0x0070,
+		.rdata_reg = 0x00c8,
 		.irq_regs = 0x0098,
 		.debounce_regs = 0x00b0,
 		.tolerance_regs = 0x00ac,
+		.cmdsrc_regs = 0x0090,
 		.names = { "I", "J", "K", "L" },
 	},
 	{
 		.val_regs = 0x0078,
+		.rdata_reg = 0x00cc,
 		.irq_regs = 0x00e8,
 		.debounce_regs = 0x0100,
 		.tolerance_regs = 0x00fc,
+		.cmdsrc_regs = 0x00e0,
 		.names = { "M", "N", "O", "P" },
 	},
 	{
 		.val_regs = 0x0080,
+		.rdata_reg = 0x00d0,
 		.irq_regs = 0x0118,
 		.debounce_regs = 0x0130,
 		.tolerance_regs = 0x012c,
+		.cmdsrc_regs = 0x0110,
 		.names = { "Q", "R", "S", "T" },
 	},
 	{
 		.val_regs = 0x0088,
+		.rdata_reg = 0x00d4,
 		.irq_regs = 0x0148,
 		.debounce_regs = 0x0160,
 		.tolerance_regs = 0x015c,
+		.cmdsrc_regs = 0x0140,
 		.names = { "U", "V", "W", "X" },
 	},
 	{
 		.val_regs = 0x01E0,
+		.rdata_reg = 0x00d8,
 		.irq_regs = 0x0178,
 		.debounce_regs = 0x0190,
 		.tolerance_regs = 0x018c,
+		.cmdsrc_regs = 0x0170,
 		.names = { "Y", "Z", "AA", "AB" },
 	},
 	{
 		.val_regs = 0x01e8,
+		.rdata_reg = 0x00dc,
 		.irq_regs = 0x01a8,
 		.debounce_regs = 0x01c0,
 		.tolerance_regs = 0x01bc,
+		.cmdsrc_regs = 0x01a0,
 		.names = { "AC", "", "", "" },
 	},
 };
 
-#define GPIO_BANK(x)	((x) >> 5)
-#define GPIO_OFFSET(x)	((x) & 0x1f)
-#define GPIO_BIT(x)	BIT(GPIO_OFFSET(x))
+enum aspeed_gpio_reg {
+	reg_val,
+	reg_rdata,
+	reg_dir,
+	reg_irq_enable,
+	reg_irq_type0,
+	reg_irq_type1,
+	reg_irq_type2,
+	reg_irq_status,
+	reg_debounce_sel1,
+	reg_debounce_sel2,
+	reg_tolerance,
+	reg_cmdsrc0,
+	reg_cmdsrc1,
+};
 
-#define GPIO_DATA	0x00
-#define GPIO_DIR	0x04
+#define GPIO_VAL_VALUE	0x00
+#define GPIO_VAL_DIR	0x04
 
 #define GPIO_IRQ_ENABLE	0x00
 #define GPIO_IRQ_TYPE0	0x04
@@ -143,6 +200,53 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 #define GPIO_DEBOUNCE_SEL1 0x00
 #define GPIO_DEBOUNCE_SEL2 0x04
 
+#define GPIO_CMDSRC_0	0x00
+#define GPIO_CMDSRC_1	0x04
+#define  GPIO_CMDSRC_ARM		0
+#define  GPIO_CMDSRC_LPC		1
+#define  GPIO_CMDSRC_COLDFIRE		2
+#define  GPIO_CMDSRC_RESERVED		3
+
+/* This will be resolved at compile time */
+static inline void __iomem *bank_reg(struct aspeed_gpio *gpio,
+				     const struct aspeed_gpio_bank *bank,
+				     const enum aspeed_gpio_reg reg)
+{
+	switch (reg) {
+	case reg_val:
+		return gpio->base + bank->val_regs + GPIO_VAL_VALUE;
+	case reg_rdata:
+		return gpio->base + bank->rdata_reg;
+	case reg_dir:
+		return gpio->base + bank->val_regs + GPIO_VAL_DIR;
+	case reg_irq_enable:
+		return gpio->base + bank->irq_regs + GPIO_IRQ_ENABLE;
+	case reg_irq_type0:
+		return gpio->base + bank->irq_regs + GPIO_IRQ_TYPE0;
+	case reg_irq_type1:
+		return gpio->base + bank->irq_regs + GPIO_IRQ_TYPE1;
+	case reg_irq_type2:
+		return gpio->base + bank->irq_regs + GPIO_IRQ_TYPE2;
+	case reg_irq_status:
+		return gpio->base + bank->irq_regs + GPIO_IRQ_STATUS;
+	case reg_debounce_sel1:
+		return gpio->base + bank->debounce_regs + GPIO_DEBOUNCE_SEL1;
+	case reg_debounce_sel2:
+		return gpio->base + bank->debounce_regs + GPIO_DEBOUNCE_SEL2;
+	case reg_tolerance:
+		return gpio->base + bank->tolerance_regs;
+	case reg_cmdsrc0:
+		return gpio->base + bank->cmdsrc_regs + GPIO_CMDSRC_0;
+	case reg_cmdsrc1:
+		return gpio->base + bank->cmdsrc_regs + GPIO_CMDSRC_1;
+	}
+	BUG();
+}
+
+#define GPIO_BANK(x)	((x) >> 5)
+#define GPIO_OFFSET(x)	((x) & 0x1f)
+#define GPIO_BIT(x)	BIT(GPIO_OFFSET(x))
+
 #define _GPIO_SET_DEBOUNCE(t, o, i) ((!!((t) & BIT(i))) << GPIO_OFFSET(o))
 #define GPIO_SET_DEBOUNCE1(t, o) _GPIO_SET_DEBOUNCE(t, o, 1)
 #define GPIO_SET_DEBOUNCE2(t, o) _GPIO_SET_DEBOUNCE(t, o, 0)
@@ -201,18 +305,80 @@ static inline bool have_output(struct aspeed_gpio *gpio, unsigned int offset)
 	return !props || (props->output & GPIO_BIT(offset));
 }
 
-static void __iomem *bank_val_reg(struct aspeed_gpio *gpio,
-		const struct aspeed_gpio_bank *bank,
-		unsigned int reg)
+static void aspeed_gpio_change_cmd_source(struct aspeed_gpio *gpio,
+					  const struct aspeed_gpio_bank *bank,
+					  int bindex, int cmdsrc)
 {
-	return gpio->base + bank->val_regs + reg;
+	void __iomem *c0 = bank_reg(gpio, bank, reg_cmdsrc0);
+	void __iomem *c1 = bank_reg(gpio, bank, reg_cmdsrc1);
+	u32 bit, reg;
+
+	/*
+	 * Each register controls 4 banks, so take the bottom 2
+	 * bits of the bank index, and use them to select the
+	 * right control bit (0, 8, 16 or 24).
+	 */
+	bit = BIT((bindex & 3) << 3);
+
+	/* Source 1 first to avoid illegal 11 combination */
+	reg = ioread32(c1);
+	if (cmdsrc & 2)
+		reg |= bit;
+	else
+		reg &= ~bit;
+	iowrite32(reg, c1);
+
+	/* Then Source 0 */
+	reg = ioread32(c0);
+	if (cmdsrc & 1)
+		reg |= bit;
+	else
+		reg &= ~bit;
+	iowrite32(reg, c0);
 }
 
-static void __iomem *bank_irq_reg(struct aspeed_gpio *gpio,
-		const struct aspeed_gpio_bank *bank,
-		unsigned int reg)
+static bool aspeed_gpio_copro_request(struct aspeed_gpio *gpio,
+				      unsigned int offset)
 {
-	return gpio->base + bank->irq_regs + reg;
+	const struct aspeed_gpio_bank *bank = to_bank(offset);
+
+	if (!copro_ops || !gpio->cf_copro_bankmap)
+		return false;
+	if (!gpio->cf_copro_bankmap[offset >> 3])
+		return false;
+	if (!copro_ops->request_access)
+		return false;
+
+	/* Pause the coprocessor */
+	copro_ops->request_access(copro_data);
+
+	/* Change command source back to ARM */
+	aspeed_gpio_change_cmd_source(gpio, bank, offset >> 3, GPIO_CMDSRC_ARM);
+
+	/* Update cache */
+	gpio->dcache[GPIO_BANK(offset)] = ioread32(bank_reg(gpio, bank, reg_rdata));
+
+	return true;
+}
+
+static void aspeed_gpio_copro_release(struct aspeed_gpio *gpio,
+				      unsigned int offset)
+{
+	const struct aspeed_gpio_bank *bank = to_bank(offset);
+
+	if (!copro_ops || !gpio->cf_copro_bankmap)
+		return;
+	if (!gpio->cf_copro_bankmap[offset >> 3])
+		return;
+	if (!copro_ops->release_access)
+		return;
+
+	/* Change command source back to ColdFire */
+	aspeed_gpio_change_cmd_source(gpio, bank, offset >> 3,
+				      GPIO_CMDSRC_COLDFIRE);
+
+	/* Restart the coprocessor */
+	copro_ops->release_access(copro_data);
 }
 
 static int aspeed_gpio_get(struct gpio_chip *gc, unsigned int offset)
@@ -220,8 +386,7 @@ static int aspeed_gpio_get(struct gpio_chip *gc, unsigned int offset)
 	struct aspeed_gpio *gpio = gpiochip_get_data(gc);
 	const struct aspeed_gpio_bank *bank = to_bank(offset);
 
-	return !!(ioread32(bank_val_reg(gpio, bank, GPIO_DATA))
-			& GPIO_BIT(offset));
+	return !!(ioread32(bank_reg(gpio, bank, reg_val)) & GPIO_BIT(offset));
 }
 
 static void __aspeed_gpio_set(struct gpio_chip *gc, unsigned int offset,
@@ -232,7 +397,7 @@ static void __aspeed_gpio_set(struct gpio_chip *gc, unsigned int offset,
 	void __iomem *addr;
 	u32 reg;
 
-	addr = bank_val_reg(gpio, bank, GPIO_DATA);
+	addr = bank_reg(gpio, bank, reg_val);
 	reg = gpio->dcache[GPIO_BANK(offset)];
 
 	if (val)
@@ -249,11 +414,15 @@ static void aspeed_gpio_set(struct gpio_chip *gc, unsigned int offset,
 {
 	struct aspeed_gpio *gpio = gpiochip_get_data(gc);
 	unsigned long flags;
+	bool copro;
 
 	spin_lock_irqsave(&gpio->lock, flags);
+	copro = aspeed_gpio_copro_request(gpio, offset);
 
 	__aspeed_gpio_set(gc, offset, val);
 
+	if (copro)
+		aspeed_gpio_copro_release(gpio, offset);
 	spin_unlock_irqrestore(&gpio->lock, flags);
 }
 
@@ -261,7 +430,9 @@ static int aspeed_gpio_dir_in(struct gpio_chip *gc, unsigned int offset)
 {
 	struct aspeed_gpio *gpio = gpiochip_get_data(gc);
 	const struct aspeed_gpio_bank *bank = to_bank(offset);
+	void __iomem *addr = bank_reg(gpio, bank, reg_dir);
 	unsigned long flags;
+	bool copro;
 	u32 reg;
 
 	if (!have_input(gpio, offset))
@@ -269,8 +440,13 @@ static int aspeed_gpio_dir_in(struct gpio_chip *gc, unsigned int offset)
 
 	spin_lock_irqsave(&gpio->lock, flags);
 
-	reg = ioread32(bank_val_reg(gpio, bank, GPIO_DIR));
-	iowrite32(reg & ~GPIO_BIT(offset), bank_val_reg(gpio, bank, GPIO_DIR));
+	reg = ioread32(addr);
+	reg &= ~GPIO_BIT(offset);
+
+	copro = aspeed_gpio_copro_request(gpio, offset);
+	iowrite32(reg, addr);
+	if (copro)
+		aspeed_gpio_copro_release(gpio, offset);
 
 	spin_unlock_irqrestore(&gpio->lock, flags);
 
@@ -282,7 +458,9 @@ static int aspeed_gpio_dir_out(struct gpio_chip *gc,
 {
 	struct aspeed_gpio *gpio = gpiochip_get_data(gc);
 	const struct aspeed_gpio_bank *bank = to_bank(offset);
+	void __iomem *addr = bank_reg(gpio, bank, reg_dir);
 	unsigned long flags;
+	bool copro;
 	u32 reg;
 
 	if (!have_output(gpio, offset))
@@ -290,10 +468,15 @@ static int aspeed_gpio_dir_out(struct gpio_chip *gc,
 
 	spin_lock_irqsave(&gpio->lock, flags);
 
+	reg = ioread32(addr);
+	reg |= GPIO_BIT(offset);
+
+	copro = aspeed_gpio_copro_request(gpio, offset);
 	__aspeed_gpio_set(gc, offset, val);
-	reg = ioread32(bank_val_reg(gpio, bank, GPIO_DIR));
-	iowrite32(reg | GPIO_BIT(offset), bank_val_reg(gpio, bank, GPIO_DIR));
+	iowrite32(reg, addr);
 
+	if (copro)
+		aspeed_gpio_copro_release(gpio, offset);
 	spin_unlock_irqrestore(&gpio->lock, flags);
 
 	return 0;
@@ -314,7 +497,7 @@ static int aspeed_gpio_get_direction(struct gpio_chip *gc, unsigned int offset)
 
 	spin_lock_irqsave(&gpio->lock, flags);
 
-	val = ioread32(bank_val_reg(gpio, bank, GPIO_DIR)) & GPIO_BIT(offset);
+	val = ioread32(bank_reg(gpio, bank, reg_dir)) & GPIO_BIT(offset);
 
 	spin_unlock_irqrestore(&gpio->lock, flags);
 
@@ -323,24 +506,23 @@ static int aspeed_gpio_get_direction(struct gpio_chip *gc, unsigned int offset)
 }
 
 static inline int irqd_to_aspeed_gpio_data(struct irq_data *d,
-		struct aspeed_gpio **gpio,
-		const struct aspeed_gpio_bank **bank,
-		u32 *bit)
+					   struct aspeed_gpio **gpio,
+					   const struct aspeed_gpio_bank **bank,
+					   u32 *bit, int *offset)
 {
-	int offset;
 	struct aspeed_gpio *internal;
 
-	offset = irqd_to_hwirq(d);
+	*offset = irqd_to_hwirq(d);
 
 	internal = irq_data_get_irq_chip_data(d);
 
 	/* This might be a bit of a questionable place to check */
-	if (!have_irq(internal, offset))
+	if (!have_irq(internal, *offset))
 		return -ENOTSUPP;
 
 	*gpio = internal;
-	*bank = to_bank(offset);
-	*bit = GPIO_BIT(offset);
+	*bank = to_bank(*offset);
+	*bit = GPIO_BIT(*offset);
 
 	return 0;
 }
@@ -351,17 +533,23 @@ static void aspeed_gpio_irq_ack(struct irq_data *d)
 	struct aspeed_gpio *gpio;
 	unsigned long flags;
 	void __iomem *status_addr;
+	int rc, offset;
+	bool copro;
 	u32 bit;
-	int rc;
 
-	rc = irqd_to_aspeed_gpio_data(d, &gpio, &bank, &bit);
+	rc = irqd_to_aspeed_gpio_data(d, &gpio, &bank, &bit, &offset);
 	if (rc)
 		return;
 
-	status_addr = bank_irq_reg(gpio, bank, GPIO_IRQ_STATUS);
+	status_addr = bank_reg(gpio, bank, reg_irq_status);
 
 	spin_lock_irqsave(&gpio->lock, flags);
+	copro = aspeed_gpio_copro_request(gpio, offset);
+
 	iowrite32(bit, status_addr);
+
+	if (copro)
+		aspeed_gpio_copro_release(gpio, offset);
 	spin_unlock_irqrestore(&gpio->lock, flags);
 }
 
@@ -372,15 +560,17 @@ static void aspeed_gpio_irq_set_mask(struct irq_data *d, bool set)
 	unsigned long flags;
 	u32 reg, bit;
 	void __iomem *addr;
-	int rc;
+	int rc, offset;
+	bool copro;
 
-	rc = irqd_to_aspeed_gpio_data(d, &gpio, &bank, &bit);
+	rc = irqd_to_aspeed_gpio_data(d, &gpio, &bank, &bit, &offset);
 	if (rc)
 		return;
 
-	addr = bank_irq_reg(gpio, bank, GPIO_IRQ_ENABLE);
+	addr = bank_reg(gpio, bank, reg_irq_enable);
 
 	spin_lock_irqsave(&gpio->lock, flags);
+	copro = aspeed_gpio_copro_request(gpio, offset);
 
 	reg = ioread32(addr);
 	if (set)
@@ -389,6 +579,8 @@ static void aspeed_gpio_irq_set_mask(struct irq_data *d, bool set)
 		reg &= ~bit;
 	iowrite32(reg, addr);
 
+	if (copro)
+		aspeed_gpio_copro_release(gpio, offset);
 	spin_unlock_irqrestore(&gpio->lock, flags);
 }
 
@@ -413,9 +605,10 @@ static int aspeed_gpio_set_type(struct irq_data *d, unsigned int type)
 	struct aspeed_gpio *gpio;
 	unsigned long flags;
 	void __iomem *addr;
-	int rc;
+	int rc, offset;
+	bool copro;
 
-	rc = irqd_to_aspeed_gpio_data(d, &gpio, &bank, &bit);
+	rc = irqd_to_aspeed_gpio_data(d, &gpio, &bank, &bit, &offset);
 	if (rc)
 		return -EINVAL;
 
@@ -441,22 +634,25 @@ static int aspeed_gpio_set_type(struct irq_data *d, unsigned int type)
 	}
 
 	spin_lock_irqsave(&gpio->lock, flags);
+	copro = aspeed_gpio_copro_request(gpio, offset);
 
-	addr = bank_irq_reg(gpio, bank, GPIO_IRQ_TYPE0);
+	addr = bank_reg(gpio, bank, reg_irq_type0);
 	reg = ioread32(addr);
 	reg = (reg & ~bit) | type0;
 	iowrite32(reg, addr);
 
-	addr = bank_irq_reg(gpio, bank, GPIO_IRQ_TYPE1);
+	addr = bank_reg(gpio, bank, reg_irq_type1);
 	reg = ioread32(addr);
 	reg = (reg & ~bit) | type1;
 	iowrite32(reg, addr);
 
-	addr = bank_irq_reg(gpio, bank, GPIO_IRQ_TYPE2);
+	addr = bank_reg(gpio, bank, reg_irq_type2);
 	reg = ioread32(addr);
 	reg = (reg & ~bit) | type2;
 	iowrite32(reg, addr);
 
+	if (copro)
+		aspeed_gpio_copro_release(gpio, offset);
 	spin_unlock_irqrestore(&gpio->lock, flags);
 
 	irq_set_handler_locked(d, handler);
@@ -477,7 +673,7 @@ static void aspeed_gpio_irq_handler(struct irq_desc *desc)
 	for (i = 0; i < ARRAY_SIZE(aspeed_gpio_banks); i++) {
 		const struct aspeed_gpio_bank *bank = &aspeed_gpio_banks[i];
 
-		reg = ioread32(bank_irq_reg(data, bank, GPIO_IRQ_STATUS));
+		reg = ioread32(bank_reg(data, bank, reg_irq_status));
 
 		for_each_set_bit(p, &reg, 32) {
 			girq = irq_find_mapping(gc->irq.domain, i * 32 + p);
@@ -549,21 +745,27 @@ static int aspeed_gpio_reset_tolerance(struct gpio_chip *chip,
 					unsigned int offset, bool enable)
 {
 	struct aspeed_gpio *gpio = gpiochip_get_data(chip);
-	const struct aspeed_gpio_bank *bank;
 	unsigned long flags;
+	void __iomem *treg;
+	bool copro;
 	u32 val;
 
-	bank = to_bank(offset);
+	treg = bank_reg(gpio, to_bank(offset), reg_tolerance);
 
 	spin_lock_irqsave(&gpio->lock, flags);
-	val = readl(gpio->base + bank->tolerance_regs);
+	copro = aspeed_gpio_copro_request(gpio, offset);
+
+	val = readl(treg);
 
 	if (enable)
 		val |= GPIO_BIT(offset);
 	else
 		val &= ~GPIO_BIT(offset);
 
-	writel(val, gpio->base + bank->tolerance_regs);
+	writel(val, treg);
+
+	if (copro)
+		aspeed_gpio_copro_release(gpio, offset);
 	spin_unlock_irqrestore(&gpio->lock, flags);
 
 	return 0;
@@ -582,13 +784,6 @@ static void aspeed_gpio_free(struct gpio_chip *chip, unsigned int offset)
 	pinctrl_gpio_free(chip->base + offset);
 }
 
-static inline void __iomem *bank_debounce_reg(struct aspeed_gpio *gpio,
-		const struct aspeed_gpio_bank *bank,
-		unsigned int reg)
-{
-	return gpio->base + bank->debounce_regs + reg;
-}
-
 static int usecs_to_cycles(struct aspeed_gpio *gpio, unsigned long usecs,
 		u32 *cycles)
 {
@@ -666,11 +861,14 @@ static void configure_timer(struct aspeed_gpio *gpio, unsigned int offset,
 	void __iomem *addr;
 	u32 val;
 
-	addr = bank_debounce_reg(gpio, bank, GPIO_DEBOUNCE_SEL1);
+	/* Note: Debounce timer isn't under control of the command
+	 * source registers, so no need to sync with the coprocessor
+	 */
+	addr = bank_reg(gpio, bank, reg_debounce_sel1);
 	val = ioread32(addr);
 	iowrite32((val & ~mask) | GPIO_SET_DEBOUNCE1(timer, offset), addr);
 
-	addr = bank_debounce_reg(gpio, bank, GPIO_DEBOUNCE_SEL2);
+	addr = bank_reg(gpio, bank, reg_debounce_sel2);
 	val = ioread32(addr);
 	iowrite32((val & ~mask) | GPIO_SET_DEBOUNCE2(timer, offset), addr);
 }
@@ -812,6 +1010,111 @@ static int aspeed_gpio_set_config(struct gpio_chip *chip, unsigned int offset,
 	return -ENOTSUPP;
 }
 
+/**
+ * aspeed_gpio_copro_set_ops - Sets the callbacks used for handhsaking with
+ *                             the coprocessor for shared GPIO banks
+ * @ops: The callbacks
+ * @data: Pointer passed back to the callbacks
+ */
+int aspeed_gpio_copro_set_ops(const struct aspeed_gpio_copro_ops *ops, void *data)
+{
+	copro_data = data;
+	copro_ops = ops;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(aspeed_gpio_copro_set_ops);
+
+/**
+ * aspeed_gpio_copro_grab_gpio - Mark a GPIO used by the coprocessor. The entire
+ *                               bank gets marked and any access from the ARM will
+ *                               result in handshaking via callbacks.
+ * @desc: The GPIO to be marked
+ * @vreg_offset: If non-NULL, returns the value register offset in the GPIO space
+ * @dreg_offset: If non-NULL, returns the data latch register offset in the GPIO space
+ * @bit: If non-NULL, returns the bit number of the GPIO in the registers
+ */
+int aspeed_gpio_copro_grab_gpio(struct gpio_desc *desc,
+				u16 *vreg_offset, u16 *dreg_offset, u8 *bit)
+{
+	struct gpio_chip *chip = gpiod_to_chip(desc);
+	struct aspeed_gpio *gpio = gpiochip_get_data(chip);
+	int rc = 0, bindex, offset = gpio_chip_hwgpio(desc);
+	const struct aspeed_gpio_bank *bank = to_bank(offset);
+	unsigned long flags;
+
+	if (!gpio->cf_copro_bankmap)
+		gpio->cf_copro_bankmap = kzalloc(gpio->config->nr_gpios >> 3, GFP_KERNEL);
+	if (!gpio->cf_copro_bankmap)
+		return -ENOMEM;
+	if (offset < 0 || offset > gpio->config->nr_gpios)
+		return -EINVAL;
+	bindex = offset >> 3;
+
+	spin_lock_irqsave(&gpio->lock, flags);
+
+	/* Sanity check, this shouldn't happen */
+	if (gpio->cf_copro_bankmap[bindex] == 0xff) {
+		rc = -EIO;
+		goto bail;
+	}
+	gpio->cf_copro_bankmap[bindex]++;
+
+	/* Switch command source */
+	if (gpio->cf_copro_bankmap[bindex] == 1)
+		aspeed_gpio_change_cmd_source(gpio, bank, bindex,
+					      GPIO_CMDSRC_COLDFIRE);
+
+	if (vreg_offset)
+		*vreg_offset = bank->val_regs;
+	if (dreg_offset)
+		*dreg_offset = bank->rdata_reg;
+	if (bit)
+		*bit = GPIO_OFFSET(offset);
+ bail:
+	spin_unlock_irqrestore(&gpio->lock, flags);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(aspeed_gpio_copro_grab_gpio);
+
+/**
+ * aspeed_gpio_copro_release_gpio - Unmark a GPIO used by the coprocessor.
+ * @desc: The GPIO to be marked
+ */
+int aspeed_gpio_copro_release_gpio(struct gpio_desc *desc)
+{
+	struct gpio_chip *chip = gpiod_to_chip(desc);
+	struct aspeed_gpio *gpio = gpiochip_get_data(chip);
+	int rc = 0, bindex, offset = gpio_chip_hwgpio(desc);
+	const struct aspeed_gpio_bank *bank = to_bank(offset);
+	unsigned long flags;
+
+	if (!gpio->cf_copro_bankmap)
+		return -ENXIO;
+
+	if (offset < 0 || offset > gpio->config->nr_gpios)
+		return -EINVAL;
+	bindex = offset >> 3;
+
+	spin_lock_irqsave(&gpio->lock, flags);
+
+	/* Sanity check, this shouldn't happen */
+	if (gpio->cf_copro_bankmap[bindex] == 0) {
+		rc = -EIO;
+		goto bail;
+	}
+	gpio->cf_copro_bankmap[bindex]--;
+
+	/* Switch command source */
+	if (gpio->cf_copro_bankmap[bindex] == 0)
+		aspeed_gpio_change_cmd_source(gpio, bank, bindex,
+					      GPIO_CMDSRC_ARM);
+ bail:
+	spin_unlock_irqrestore(&gpio->lock, flags);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(aspeed_gpio_copro_release_gpio);
+
 /*
  * Any banks not specified in a struct aspeed_bank_props array are assumed to
  * have the properties:
@@ -902,11 +1205,18 @@ static int __init aspeed_gpio_probe(struct platform_device *pdev)
 	if (!gpio->dcache)
 		return -ENOMEM;
 
-	/* Populate it with initial values read from the HW */
+	/*
+	 * Populate it with initial values read from the HW and switch
+	 * all command sources to the ARM by default
+	 */
 	for (i = 0; i < banks; i++) {
 		const struct aspeed_gpio_bank *bank = &aspeed_gpio_banks[i];
-		gpio->dcache[i] = ioread32(gpio->base + bank->val_regs +
-					   GPIO_DATA);
+		void __iomem *addr = bank_reg(gpio, bank, reg_rdata);
+		gpio->dcache[i] = ioread32(addr);
+		aspeed_gpio_change_cmd_source(gpio, bank, 0, GPIO_CMDSRC_ARM);
+		aspeed_gpio_change_cmd_source(gpio, bank, 1, GPIO_CMDSRC_ARM);
+		aspeed_gpio_change_cmd_source(gpio, bank, 2, GPIO_CMDSRC_ARM);
+		aspeed_gpio_change_cmd_source(gpio, bank, 3, GPIO_CMDSRC_ARM);
 	}
 
 	rc = devm_gpiochip_add_data(&pdev->dev, &gpio->chip, gpio);
diff --git a/drivers/gpio/gpio-ath79.c b/drivers/gpio/gpio-ath79.c
index 684e9d6d6623..0a553d676042 100644
--- a/drivers/gpio/gpio-ath79.c
+++ b/drivers/gpio/gpio-ath79.c
@@ -51,7 +51,7 @@ static u32 ath79_gpio_read(struct ath79_gpio_ctrl *ctrl, unsigned reg)
 static void ath79_gpio_write(struct ath79_gpio_ctrl *ctrl,
 			unsigned reg, u32 val)
 {
-	return writel(val, ctrl->base + reg);
+	writel(val, ctrl->base + reg);
 }
 
 static bool ath79_gpio_update_bits(
diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c
index 00272fa7cc4f..d0707fc23afd 100644
--- a/drivers/gpio/gpio-bcm-kona.c
+++ b/drivers/gpio/gpio-bcm-kona.c
@@ -485,12 +485,14 @@ static void bcm_kona_gpio_irq_handler(struct irq_desc *desc)
 static int bcm_kona_gpio_irq_reqres(struct irq_data *d)
 {
 	struct bcm_kona_gpio *kona_gpio = irq_data_get_irq_chip_data(d);
+	int ret;
 
-	if (gpiochip_lock_as_irq(&kona_gpio->gpio_chip, d->hwirq)) {
+	ret = gpiochip_lock_as_irq(&kona_gpio->gpio_chip, d->hwirq);
+	if (ret) {
 		dev_err(kona_gpio->gpio_chip.parent,
 			"unable to lock HW IRQ %lu for IRQ\n",
 			d->hwirq);
-		return -EINVAL;
+		return ret;
 	}
 	return 0;
 }
diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c
index 035a454eca43..a5ece8ea79bc 100644
--- a/drivers/gpio/gpio-davinci.c
+++ b/drivers/gpio/gpio-davinci.c
@@ -167,8 +167,8 @@ of_err:
 static int davinci_gpio_probe(struct platform_device *pdev)
 {
 	static int ctrl_num, bank_base;
-	int gpio, bank, ret = 0;
-	unsigned ngpio, nbank;
+	int gpio, bank, i, ret = 0;
+	unsigned int ngpio, nbank, nirq;
 	struct davinci_gpio_controller *chips;
 	struct davinci_gpio_platform_data *pdata;
 	struct device *dev = &pdev->dev;
@@ -197,6 +197,16 @@ static int davinci_gpio_probe(struct platform_device *pdev)
 	if (WARN_ON(ARCH_NR_GPIOS < ngpio))
 		ngpio = ARCH_NR_GPIOS;
 
+	/*
+	 * If there are unbanked interrupts then the number of
+	 * interrupts is equal to number of gpios else all are banked so
+	 * number of interrupts is equal to number of banks(each with 16 gpios)
+	 */
+	if (pdata->gpio_unbanked)
+		nirq = pdata->gpio_unbanked;
+	else
+		nirq = DIV_ROUND_UP(ngpio, 16);
+
 	nbank = DIV_ROUND_UP(ngpio, 32);
 	chips = devm_kcalloc(dev,
 			     nbank, sizeof(struct davinci_gpio_controller),
@@ -209,6 +219,15 @@ static int davinci_gpio_probe(struct platform_device *pdev)
 	if (IS_ERR(gpio_base))
 		return PTR_ERR(gpio_base);
 
+	for (i = 0; i < nirq; i++) {
+		chips->irqs[i] = platform_get_irq(pdev, i);
+		if (chips->irqs[i] < 0) {
+			dev_info(dev, "IRQ not populated, err = %d\n",
+				 chips->irqs[i]);
+			return chips->irqs[i];
+		}
+	}
+
 	snprintf(label, MAX_LABEL_SIZE, "davinci_gpio.%d", ctrl_num++);
 	chips->chip.label = devm_kstrdup(dev, label, GFP_KERNEL);
 		if (!chips->chip.label)
@@ -377,7 +396,7 @@ static int gpio_to_irq_unbanked(struct gpio_chip *chip, unsigned offset)
 	 * can provide direct-mapped IRQs to AINTC (up to 32 GPIOs).
 	 */
 	if (offset < d->gpio_unbanked)
-		return d->base_irq + offset;
+		return d->irqs[offset];
 	else
 		return -ENODEV;
 }
@@ -386,11 +405,18 @@ static int gpio_irq_type_unbanked(struct irq_data *data, unsigned trigger)
 {
 	struct davinci_gpio_controller *d;
 	struct davinci_gpio_regs __iomem *g;
-	u32 mask;
+	u32 mask, i;
 
 	d = (struct davinci_gpio_controller *)irq_data_get_irq_handler_data(data);
 	g = (struct davinci_gpio_regs __iomem *)d->regs[0];
-	mask = __gpio_mask(data->irq - d->base_irq);
+	for (i = 0; i < MAX_INT_PER_BANK; i++)
+		if (data->irq == d->irqs[i])
+			break;
+
+	if (i == MAX_INT_PER_BANK)
+		return -EINVAL;
+
+	mask = __gpio_mask(i);
 
 	if (trigger & ~(IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING))
 		return -EINVAL;
@@ -459,9 +485,8 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev)
 	int		ret;
 	struct clk	*clk;
 	u32		binten = 0;
-	unsigned	ngpio, bank_irq;
+	unsigned	ngpio;
 	struct device *dev = &pdev->dev;
-	struct resource	*res;
 	struct davinci_gpio_controller *chips = platform_get_drvdata(pdev);
 	struct davinci_gpio_platform_data *pdata = dev->platform_data;
 	struct davinci_gpio_regs __iomem *g;
@@ -481,24 +506,13 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev)
 		gpio_get_irq_chip = (gpio_get_irq_chip_cb_t)match->data;
 
 	ngpio = pdata->ngpio;
-	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (!res) {
-		dev_err(dev, "Invalid IRQ resource\n");
-		return -EBUSY;
-	}
-
-	bank_irq = res->start;
-
-	if (!bank_irq) {
-		dev_err(dev, "Invalid IRQ resource\n");
-		return -ENODEV;
-	}
 
 	clk = devm_clk_get(dev, "gpio");
 	if (IS_ERR(clk)) {
 		dev_err(dev, "Error %ld getting gpio clock\n", PTR_ERR(clk));
 		return PTR_ERR(clk);
 	}
+
 	ret = clk_prepare_enable(clk);
 	if (ret)
 		return ret;
@@ -538,12 +552,11 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev)
 	if (pdata->gpio_unbanked) {
 		/* pass "bank 0" GPIO IRQs to AINTC */
 		chips->chip.to_irq = gpio_to_irq_unbanked;
-		chips->base_irq = bank_irq;
 		chips->gpio_unbanked = pdata->gpio_unbanked;
 		binten = GENMASK(pdata->gpio_unbanked / 16, 0);
 
 		/* AINTC handles mask/unmask; GPIO handles triggering */
-		irq = bank_irq;
+		irq = chips->irqs[0];
 		irq_chip = gpio_get_irq_chip(irq);
 		irq_chip->name = "GPIO-AINTC";
 		irq_chip->irq_set_type = gpio_irq_type_unbanked;
@@ -554,10 +567,11 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev)
 		writel_relaxed(~0, &g->set_rising);
 
 		/* set the direct IRQs up to use that irqchip */
-		for (gpio = 0; gpio < pdata->gpio_unbanked; gpio++, irq++) {
-			irq_set_chip(irq, irq_chip);
-			irq_set_handler_data(irq, chips);
-			irq_set_status_flags(irq, IRQ_TYPE_EDGE_BOTH);
+		for (gpio = 0; gpio < pdata->gpio_unbanked; gpio++) {
+			irq_set_chip(chips->irqs[gpio], irq_chip);
+			irq_set_handler_data(chips->irqs[gpio], chips);
+			irq_set_status_flags(chips->irqs[gpio],
+					     IRQ_TYPE_EDGE_BOTH);
 		}
 
 		goto done;
@@ -567,7 +581,7 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev)
 	 * Or, AINTC can handle IRQs for banks of 16 GPIO IRQs, which we
 	 * then chain through our own handler.
 	 */
-	for (gpio = 0, bank = 0; gpio < ngpio; bank++, bank_irq++, gpio += 16) {
+	for (gpio = 0, bank = 0; gpio < ngpio; bank++, gpio += 16) {
 		/* disabled by default, enabled only as needed
 		 * There are register sets for 32 GPIOs. 2 banks of 16
 		 * GPIOs are covered by each set of registers hence divide by 2
@@ -594,8 +608,8 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev)
 		irqdata->bank_num = bank;
 		irqdata->chip = chips;
 
-		irq_set_chained_handler_and_data(bank_irq, gpio_irq_handler,
-						 irqdata);
+		irq_set_chained_handler_and_data(chips->irqs[bank],
+						 gpio_irq_handler, irqdata);
 
 		binten |= BIT(bank);
 	}
diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c
index 7a2de3de6571..28da700f5f52 100644
--- a/drivers/gpio/gpio-dwapb.c
+++ b/drivers/gpio/gpio-dwapb.c
@@ -255,11 +255,13 @@ static int dwapb_irq_reqres(struct irq_data *d)
 	struct irq_chip_generic *igc = irq_data_get_irq_chip_data(d);
 	struct dwapb_gpio *gpio = igc->private;
 	struct gpio_chip *gc = &gpio->ports[0].gc;
+	int ret;
 
-	if (gpiochip_lock_as_irq(gc, irqd_to_hwirq(d))) {
+	ret = gpiochip_lock_as_irq(gc, irqd_to_hwirq(d));
+	if (ret) {
 		dev_err(gpio->dev, "unable to lock HW IRQ %lu for IRQ\n",
 			irqd_to_hwirq(d));
-		return -EINVAL;
+		return ret;
 	}
 	return 0;
 }
diff --git a/drivers/gpio/gpio-em.c b/drivers/gpio/gpio-em.c
index 2b466b80e70a..982e699a5b81 100644
--- a/drivers/gpio/gpio-em.c
+++ b/drivers/gpio/gpio-em.c
@@ -101,12 +101,14 @@ static void em_gio_irq_enable(struct irq_data *d)
 static int em_gio_irq_reqres(struct irq_data *d)
 {
 	struct em_gio_priv *p = irq_data_get_irq_chip_data(d);
+	int ret;
 
-	if (gpiochip_lock_as_irq(&p->gpio_chip, irqd_to_hwirq(d))) {
+	ret = gpiochip_lock_as_irq(&p->gpio_chip, irqd_to_hwirq(d));
+	if (ret) {
 		dev_err(p->gpio_chip.parent,
 			"unable to lock HW IRQ %lu for IRQ\n",
 			irqd_to_hwirq(d));
-		return -EINVAL;
+		return ret;
 	}
 	return 0;
 }
diff --git a/drivers/gpio/gpio-it87.c b/drivers/gpio/gpio-it87.c
index 7cad14d3f127..389ecd8b7d26 100644
--- a/drivers/gpio/gpio-it87.c
+++ b/drivers/gpio/gpio-it87.c
@@ -35,12 +35,15 @@
 
 /* Chip Id numbers */
 #define NO_DEV_ID	0xffff
+#define IT8613_ID	0x8613
 #define IT8620_ID	0x8620
 #define IT8628_ID	0x8628
+#define IT8718_ID       0x8718
 #define IT8728_ID	0x8728
 #define IT8732_ID	0x8732
 #define IT8761_ID	0x8761
 #define IT8772_ID	0x8772
+#define IT8786_ID	0x8786
 
 /* IO Ports */
 #define REG		0x2e
@@ -306,6 +309,14 @@ static int __init it87_gpio_init(void)
 	it87_gpio->chip = it87_template_chip;
 
 	switch (chip_type) {
+	case IT8613_ID:
+		gpio_ba_reg = 0x62;
+		it87_gpio->io_size = 8;  /* it8613 only needs 6, use 8 for alignment */
+		it87_gpio->output_base = 0xc8;
+		it87_gpio->simple_base = 0xc0;
+		it87_gpio->simple_size = 6;
+		it87_gpio->chip.ngpio = 64;  /* has 48, use 64 for convenient calc */
+		break;
 	case IT8620_ID:
 	case IT8628_ID:
 		gpio_ba_reg = 0x62;
@@ -314,9 +325,11 @@ static int __init it87_gpio_init(void)
 		it87_gpio->simple_size = 0;
 		it87_gpio->chip.ngpio = 64;
 		break;
+	case IT8718_ID:
 	case IT8728_ID:
 	case IT8732_ID:
 	case IT8772_ID:
+	case IT8786_ID:
 		gpio_ba_reg = 0x62;
 		it87_gpio->io_size = 8;
 		it87_gpio->output_base = 0xc8;
diff --git a/drivers/gpio/gpio-max732x.c b/drivers/gpio/gpio-max732x.c
index 9d8bcc69f245..f03cb0ba7726 100644
--- a/drivers/gpio/gpio-max732x.c
+++ b/drivers/gpio/gpio-max732x.c
@@ -653,6 +653,12 @@ static int max732x_probe(struct i2c_client *client,
 		chip->client_group_a = client;
 		if (nr_port > 8) {
 			c = i2c_new_dummy(client->adapter, addr_b);
+			if (!c) {
+				dev_err(&client->dev,
+					"Failed to allocate I2C device\n");
+				ret = -ENODEV;
+				goto out_failed;
+			}
 			chip->client_group_b = chip->client_dummy = c;
 		}
 		break;
@@ -660,6 +666,12 @@ static int max732x_probe(struct i2c_client *client,
 		chip->client_group_b = client;
 		if (nr_port > 8) {
 			c = i2c_new_dummy(client->adapter, addr_a);
+			if (!c) {
+				dev_err(&client->dev,
+					"Failed to allocate I2C device\n");
+				ret = -ENODEV;
+				goto out_failed;
+			}
 			chip->client_group_a = chip->client_dummy = c;
 		}
 		break;
diff --git a/drivers/gpio/gpio-menz127.c b/drivers/gpio/gpio-menz127.c
index e1037582e34d..b2635326546e 100644
--- a/drivers/gpio/gpio-menz127.c
+++ b/drivers/gpio/gpio-menz127.c
@@ -56,9 +56,9 @@ static int men_z127_debounce(struct gpio_chip *gc, unsigned gpio,
 		rnd = fls(debounce) - 1;
 
 		if (rnd && (debounce & BIT(rnd - 1)))
-			debounce = round_up(debounce, MEN_Z127_DB_MIN_US);
+			debounce = roundup(debounce, MEN_Z127_DB_MIN_US);
 		else
-			debounce = round_down(debounce, MEN_Z127_DB_MIN_US);
+			debounce = rounddown(debounce, MEN_Z127_DB_MIN_US);
 
 		if (debounce > MEN_Z127_DB_MAX_US)
 			debounce = MEN_Z127_DB_MAX_US;
diff --git a/drivers/gpio/gpio-ml-ioh.c b/drivers/gpio/gpio-ml-ioh.c
index b23d9a36be1f..51c7d1b84c2e 100644
--- a/drivers/gpio/gpio-ml-ioh.c
+++ b/drivers/gpio/gpio-ml-ioh.c
@@ -496,9 +496,10 @@ static int ioh_gpio_probe(struct pci_dev *pdev,
 	return 0;
 
 err_gpiochip_add:
+	chip = chip_save;
 	while (--i >= 0) {
-		chip--;
 		gpiochip_remove(&chip->gpio);
+		chip++;
 	}
 	kfree(chip_save);
 
diff --git a/drivers/gpio/gpio-mmio.c b/drivers/gpio/gpio-mmio.c
index 7b14d6280e44..935292a30c99 100644
--- a/drivers/gpio/gpio-mmio.c
+++ b/drivers/gpio/gpio-mmio.c
@@ -136,8 +136,20 @@ static unsigned long bgpio_line2mask(struct gpio_chip *gc, unsigned int line)
 static int bgpio_get_set(struct gpio_chip *gc, unsigned int gpio)
 {
 	unsigned long pinmask = bgpio_line2mask(gc, gpio);
+	bool dir = !!(gc->bgpio_dir & pinmask);
 
-	if (gc->bgpio_dir & pinmask)
+	/*
+	 * If the direction is OUT we read the value from the SET
+	 * register, and if the direction is IN we read the value
+	 * from the DAT register.
+	 *
+	 * If the direction bits are inverted, naturally this gets
+	 * inverted too.
+	 */
+	if (gc->bgpio_dir_inverted)
+		dir = !dir;
+
+	if (dir)
 		return !!(gc->read_reg(gc->reg_set) & pinmask);
 	else
 		return !!(gc->read_reg(gc->reg_dat) & pinmask);
@@ -157,8 +169,13 @@ static int bgpio_get_set_multiple(struct gpio_chip *gc, unsigned long *mask,
 	*bits &= ~*mask;
 
 	/* Exploit the fact that we know which directions are set */
-	set_mask = *mask & gc->bgpio_dir;
-	get_mask = *mask & ~gc->bgpio_dir;
+	if (gc->bgpio_dir_inverted) {
+		set_mask = *mask & ~gc->bgpio_dir;
+		get_mask = *mask & gc->bgpio_dir;
+	} else {
+		set_mask = *mask & gc->bgpio_dir;
+		get_mask = *mask & ~gc->bgpio_dir;
+	}
 
 	if (set_mask)
 		*bits |= gc->read_reg(gc->reg_set) & set_mask;
@@ -359,7 +376,10 @@ static int bgpio_dir_in(struct gpio_chip *gc, unsigned int gpio)
 
 	spin_lock_irqsave(&gc->bgpio_lock, flags);
 
-	gc->bgpio_dir &= ~bgpio_line2mask(gc, gpio);
+	if (gc->bgpio_dir_inverted)
+		gc->bgpio_dir |= bgpio_line2mask(gc, gpio);
+	else
+		gc->bgpio_dir &= ~bgpio_line2mask(gc, gpio);
 	gc->write_reg(gc->reg_dir, gc->bgpio_dir);
 
 	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
@@ -370,7 +390,10 @@ static int bgpio_dir_in(struct gpio_chip *gc, unsigned int gpio)
 static int bgpio_get_dir(struct gpio_chip *gc, unsigned int gpio)
 {
 	/* Return 0 if output, 1 of input */
-	return !(gc->read_reg(gc->reg_dir) & bgpio_line2mask(gc, gpio));
+	if (gc->bgpio_dir_inverted)
+		return !!(gc->read_reg(gc->reg_dir) & bgpio_line2mask(gc, gpio));
+	else
+		return !(gc->read_reg(gc->reg_dir) & bgpio_line2mask(gc, gpio));
 }
 
 static int bgpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
@@ -381,37 +404,10 @@ static int bgpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 
 	spin_lock_irqsave(&gc->bgpio_lock, flags);
 
-	gc->bgpio_dir |= bgpio_line2mask(gc, gpio);
-	gc->write_reg(gc->reg_dir, gc->bgpio_dir);
-
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
-
-	return 0;
-}
-
-static int bgpio_dir_in_inv(struct gpio_chip *gc, unsigned int gpio)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
-
-	gc->bgpio_dir |= bgpio_line2mask(gc, gpio);
-	gc->write_reg(gc->reg_dir, gc->bgpio_dir);
-
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
-
-	return 0;
-}
-
-static int bgpio_dir_out_inv(struct gpio_chip *gc, unsigned int gpio, int val)
-{
-	unsigned long flags;
-
-	gc->set(gc, gpio, val);
-
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
-
-	gc->bgpio_dir &= ~bgpio_line2mask(gc, gpio);
+	if (gc->bgpio_dir_inverted)
+		gc->bgpio_dir &= ~bgpio_line2mask(gc, gpio);
+	else
+		gc->bgpio_dir |= bgpio_line2mask(gc, gpio);
 	gc->write_reg(gc->reg_dir, gc->bgpio_dir);
 
 	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
@@ -419,12 +415,6 @@ static int bgpio_dir_out_inv(struct gpio_chip *gc, unsigned int gpio, int val)
 	return 0;
 }
 
-static int bgpio_get_dir_inv(struct gpio_chip *gc, unsigned int gpio)
-{
-	/* Return 0 if output, 1 if input */
-	return !!(gc->read_reg(gc->reg_dir) & bgpio_line2mask(gc, gpio));
-}
-
 static int bgpio_setup_accessors(struct device *dev,
 				 struct gpio_chip *gc,
 				 bool byte_be)
@@ -560,9 +550,10 @@ static int bgpio_setup_direction(struct gpio_chip *gc,
 		gc->get_direction = bgpio_get_dir;
 	} else if (dirin) {
 		gc->reg_dir = dirin;
-		gc->direction_output = bgpio_dir_out_inv;
-		gc->direction_input = bgpio_dir_in_inv;
-		gc->get_direction = bgpio_get_dir_inv;
+		gc->direction_output = bgpio_dir_out;
+		gc->direction_input = bgpio_dir_in;
+		gc->get_direction = bgpio_get_dir;
+		gc->bgpio_dir_inverted = true;
 	} else {
 		if (flags & BGPIOF_NO_OUTPUT)
 			gc->direction_output = bgpio_dir_out_err;
@@ -582,6 +573,33 @@ static int bgpio_request(struct gpio_chip *chip, unsigned gpio_pin)
 	return -EINVAL;
 }
 
+/**
+ * bgpio_init() - Initialize generic GPIO accessor functions
+ * @gc: the GPIO chip to set up
+ * @dev: the parent device of the new GPIO chip (compulsory)
+ * @sz: the size (width) of the MMIO registers in bytes, typically 1, 2 or 4
+ * @dat: MMIO address for the register to READ the value of the GPIO lines, it
+ *	is expected that a 1 in the corresponding bit in this register means the
+ *	line is asserted
+ * @set: MMIO address for the register to SET the value of the GPIO lines, it is
+ *	expected that we write the line with 1 in this register to drive the GPIO line
+ *	high.
+ * @clr: MMIO address for the register to CLEAR the value of the GPIO lines, it is
+ *	expected that we write the line with 1 in this register to drive the GPIO line
+ *	low. It is allowed to leave this address as NULL, in that case the SET register
+ *	will be assumed to also clear the GPIO lines, by actively writing the line
+ *	with 0.
+ * @dirout: MMIO address for the register to set the line as OUTPUT. It is assumed
+ *	that setting a line to 1 in this register will turn that line into an
+ *	output line. Conversely, setting the line to 0 will turn that line into
+ *	an input. Either this or @dirin can be defined, but never both.
+ * @dirin: MMIO address for the register to set this line as INPUT. It is assumed
+ *	that setting a line to 1 in this register will turn that line into an
+ *	input line. Conversely, setting the line to 0 will turn that line into
+ *	an output. Either this or @dirout can be defined, but never both.
+ * @flags: Different flags that will affect the behaviour of the device, such as
+ *	endianness etc.
+ */
 int bgpio_init(struct gpio_chip *gc, struct device *dev,
 	       unsigned long sz, void __iomem *dat, void __iomem *set,
 	       void __iomem *clr, void __iomem *dirout, void __iomem *dirin,
diff --git a/drivers/gpio/gpio-mt7621.c b/drivers/gpio/gpio-mt7621.c
new file mode 100644
index 000000000000..d72af6f6cdbd
--- /dev/null
+++ b/drivers/gpio/gpio-mt7621.c
@@ -0,0 +1,332 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2009-2011 Gabor Juhos <juhosg@openwrt.org>
+ * Copyright (C) 2013 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/err.h>
+#include <linux/gpio/driver.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+
+#define MTK_BANK_CNT	3
+#define MTK_BANK_WIDTH	32
+
+#define GPIO_BANK_STRIDE	0x04
+#define GPIO_REG_CTRL		0x00
+#define GPIO_REG_POL		0x10
+#define GPIO_REG_DATA		0x20
+#define GPIO_REG_DSET		0x30
+#define GPIO_REG_DCLR		0x40
+#define GPIO_REG_REDGE		0x50
+#define GPIO_REG_FEDGE		0x60
+#define GPIO_REG_HLVL		0x70
+#define GPIO_REG_LLVL		0x80
+#define GPIO_REG_STAT		0x90
+#define GPIO_REG_EDGE		0xA0
+
+struct mtk_gc {
+	struct gpio_chip chip;
+	spinlock_t lock;
+	int bank;
+	u32 rising;
+	u32 falling;
+	u32 hlevel;
+	u32 llevel;
+};
+
+/**
+ * struct mtk - state container for
+ * data of the platform driver. It is 3
+ * separate gpio-chip each one with its
+ * own irq_chip.
+ * @dev: device instance
+ * @base: memory base address
+ * @gpio_irq: irq number from the device tree
+ * @gc_map: array of the gpio chips
+ */
+struct mtk {
+	struct device *dev;
+	void __iomem *base;
+	int gpio_irq;
+	struct mtk_gc gc_map[MTK_BANK_CNT];
+};
+
+static inline struct mtk_gc *
+to_mediatek_gpio(struct gpio_chip *chip)
+{
+	return container_of(chip, struct mtk_gc, chip);
+}
+
+static inline void
+mtk_gpio_w32(struct mtk_gc *rg, u32 offset, u32 val)
+{
+	struct gpio_chip *gc = &rg->chip;
+	struct mtk *mtk = gpiochip_get_data(gc);
+
+	offset = (rg->bank * GPIO_BANK_STRIDE) + offset;
+	gc->write_reg(mtk->base + offset, val);
+}
+
+static inline u32
+mtk_gpio_r32(struct mtk_gc *rg, u32 offset)
+{
+	struct gpio_chip *gc = &rg->chip;
+	struct mtk *mtk = gpiochip_get_data(gc);
+
+	offset = (rg->bank * GPIO_BANK_STRIDE) + offset;
+	return gc->read_reg(mtk->base + offset);
+}
+
+static irqreturn_t
+mediatek_gpio_irq_handler(int irq, void *data)
+{
+	struct gpio_chip *gc = data;
+	struct mtk_gc *rg = to_mediatek_gpio(gc);
+	irqreturn_t ret = IRQ_NONE;
+	unsigned long pending;
+	int bit;
+
+	pending = mtk_gpio_r32(rg, GPIO_REG_STAT);
+
+	for_each_set_bit(bit, &pending, MTK_BANK_WIDTH) {
+		u32 map = irq_find_mapping(gc->irq.domain, bit);
+
+		generic_handle_irq(map);
+		mtk_gpio_w32(rg, GPIO_REG_STAT, BIT(bit));
+		ret |= IRQ_HANDLED;
+	}
+
+	return ret;
+}
+
+static void
+mediatek_gpio_irq_unmask(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct mtk_gc *rg = to_mediatek_gpio(gc);
+	int pin = d->hwirq;
+	unsigned long flags;
+	u32 rise, fall, high, low;
+
+	spin_lock_irqsave(&rg->lock, flags);
+	rise = mtk_gpio_r32(rg, GPIO_REG_REDGE);
+	fall = mtk_gpio_r32(rg, GPIO_REG_FEDGE);
+	high = mtk_gpio_r32(rg, GPIO_REG_HLVL);
+	low = mtk_gpio_r32(rg, GPIO_REG_LLVL);
+	mtk_gpio_w32(rg, GPIO_REG_REDGE, rise | (BIT(pin) & rg->rising));
+	mtk_gpio_w32(rg, GPIO_REG_FEDGE, fall | (BIT(pin) & rg->falling));
+	mtk_gpio_w32(rg, GPIO_REG_HLVL, high | (BIT(pin) & rg->hlevel));
+	mtk_gpio_w32(rg, GPIO_REG_LLVL, low | (BIT(pin) & rg->llevel));
+	spin_unlock_irqrestore(&rg->lock, flags);
+}
+
+static void
+mediatek_gpio_irq_mask(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct mtk_gc *rg = to_mediatek_gpio(gc);
+	int pin = d->hwirq;
+	unsigned long flags;
+	u32 rise, fall, high, low;
+
+	spin_lock_irqsave(&rg->lock, flags);
+	rise = mtk_gpio_r32(rg, GPIO_REG_REDGE);
+	fall = mtk_gpio_r32(rg, GPIO_REG_FEDGE);
+	high = mtk_gpio_r32(rg, GPIO_REG_HLVL);
+	low = mtk_gpio_r32(rg, GPIO_REG_LLVL);
+	mtk_gpio_w32(rg, GPIO_REG_FEDGE, fall & ~BIT(pin));
+	mtk_gpio_w32(rg, GPIO_REG_REDGE, rise & ~BIT(pin));
+	mtk_gpio_w32(rg, GPIO_REG_HLVL, high & ~BIT(pin));
+	mtk_gpio_w32(rg, GPIO_REG_LLVL, low & ~BIT(pin));
+	spin_unlock_irqrestore(&rg->lock, flags);
+}
+
+static int
+mediatek_gpio_irq_type(struct irq_data *d, unsigned int type)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct mtk_gc *rg = to_mediatek_gpio(gc);
+	int pin = d->hwirq;
+	u32 mask = BIT(pin);
+
+	if (type == IRQ_TYPE_PROBE) {
+		if ((rg->rising | rg->falling |
+		     rg->hlevel | rg->llevel) & mask)
+			return 0;
+
+		type = IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING;
+	}
+
+	rg->rising &= ~mask;
+	rg->falling &= ~mask;
+	rg->hlevel &= ~mask;
+	rg->llevel &= ~mask;
+
+	switch (type & IRQ_TYPE_SENSE_MASK) {
+	case IRQ_TYPE_EDGE_BOTH:
+		rg->rising |= mask;
+		rg->falling |= mask;
+		break;
+	case IRQ_TYPE_EDGE_RISING:
+		rg->rising |= mask;
+		break;
+	case IRQ_TYPE_EDGE_FALLING:
+		rg->falling |= mask;
+		break;
+	case IRQ_TYPE_LEVEL_HIGH:
+		rg->hlevel |= mask;
+		break;
+	case IRQ_TYPE_LEVEL_LOW:
+		rg->llevel |= mask;
+		break;
+	}
+
+	return 0;
+}
+
+static struct irq_chip mediatek_gpio_irq_chip = {
+	.irq_unmask		= mediatek_gpio_irq_unmask,
+	.irq_mask		= mediatek_gpio_irq_mask,
+	.irq_mask_ack		= mediatek_gpio_irq_mask,
+	.irq_set_type		= mediatek_gpio_irq_type,
+};
+
+static int
+mediatek_gpio_xlate(struct gpio_chip *chip,
+		    const struct of_phandle_args *spec, u32 *flags)
+{
+	int gpio = spec->args[0];
+	struct mtk_gc *rg = to_mediatek_gpio(chip);
+
+	if (rg->bank != gpio / MTK_BANK_WIDTH)
+		return -EINVAL;
+
+	if (flags)
+		*flags = spec->args[1];
+
+	return gpio % MTK_BANK_WIDTH;
+}
+
+static int
+mediatek_gpio_bank_probe(struct device *dev,
+			 struct device_node *node, int bank)
+{
+	struct mtk *mtk = dev_get_drvdata(dev);
+	struct mtk_gc *rg;
+	void __iomem *dat, *set, *ctrl, *diro;
+	int ret;
+
+	rg = &mtk->gc_map[bank];
+	memset(rg, 0, sizeof(*rg));
+
+	spin_lock_init(&rg->lock);
+	rg->chip.of_node = node;
+	rg->bank = bank;
+
+	dat = mtk->base + GPIO_REG_DATA + (rg->bank * GPIO_BANK_STRIDE);
+	set = mtk->base + GPIO_REG_DSET + (rg->bank * GPIO_BANK_STRIDE);
+	ctrl = mtk->base + GPIO_REG_DCLR + (rg->bank * GPIO_BANK_STRIDE);
+	diro = mtk->base + GPIO_REG_CTRL + (rg->bank * GPIO_BANK_STRIDE);
+
+	ret = bgpio_init(&rg->chip, dev, 4,
+			 dat, set, ctrl, diro, NULL, 0);
+	if (ret) {
+		dev_err(dev, "bgpio_init() failed\n");
+		return ret;
+	}
+
+	rg->chip.of_gpio_n_cells = 2;
+	rg->chip.of_xlate = mediatek_gpio_xlate;
+	rg->chip.label = devm_kasprintf(dev, GFP_KERNEL, "%s-bank%d",
+					dev_name(dev), bank);
+
+	ret = devm_gpiochip_add_data(dev, &rg->chip, mtk);
+	if (ret < 0) {
+		dev_err(dev, "Could not register gpio %d, ret=%d\n",
+			rg->chip.ngpio, ret);
+		return ret;
+	}
+
+	if (mtk->gpio_irq) {
+		/*
+		 * Manually request the irq here instead of passing
+		 * a flow-handler to gpiochip_set_chained_irqchip,
+		 * because the irq is shared.
+		 */
+		ret = devm_request_irq(dev, mtk->gpio_irq,
+				       mediatek_gpio_irq_handler, IRQF_SHARED,
+				       rg->chip.label, &rg->chip);
+
+		if (ret) {
+			dev_err(dev, "Error requesting IRQ %d: %d\n",
+				mtk->gpio_irq, ret);
+			return ret;
+		}
+
+		ret = gpiochip_irqchip_add(&rg->chip, &mediatek_gpio_irq_chip,
+					   0, handle_simple_irq, IRQ_TYPE_NONE);
+		if (ret) {
+			dev_err(dev, "failed to add gpiochip_irqchip\n");
+			return ret;
+		}
+
+		gpiochip_set_chained_irqchip(&rg->chip, &mediatek_gpio_irq_chip,
+					     mtk->gpio_irq, NULL);
+	}
+
+	/* set polarity to low for all gpios */
+	mtk_gpio_w32(rg, GPIO_REG_POL, 0);
+
+	dev_info(dev, "registering %d gpios\n", rg->chip.ngpio);
+
+	return 0;
+}
+
+static int
+mediatek_gpio_probe(struct platform_device *pdev)
+{
+	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct mtk *mtk;
+	int i;
+
+	mtk = devm_kzalloc(dev, sizeof(*mtk), GFP_KERNEL);
+	if (!mtk)
+		return -ENOMEM;
+
+	mtk->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(mtk->base))
+		return PTR_ERR(mtk->base);
+
+	mtk->gpio_irq = irq_of_parse_and_map(np, 0);
+	mtk->dev = dev;
+	platform_set_drvdata(pdev, mtk);
+	mediatek_gpio_irq_chip.name = dev_name(dev);
+
+	for (i = 0; i < MTK_BANK_CNT; i++)
+		mediatek_gpio_bank_probe(dev, np, i);
+
+	return 0;
+}
+
+static const struct of_device_id mediatek_gpio_match[] = {
+	{ .compatible = "mediatek,mt7621-gpio" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, mediatek_gpio_match);
+
+static struct platform_driver mediatek_gpio_driver = {
+	.probe = mediatek_gpio_probe,
+	.driver = {
+		.name = "mt7621_gpio",
+		.of_match_table = mediatek_gpio_match,
+	},
+};
+
+builtin_platform_driver(mediatek_gpio_driver);
diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c
index 2f2829966d4c..995cf0b9e0b1 100644
--- a/drivers/gpio/gpio-mxc.c
+++ b/drivers/gpio/gpio-mxc.c
@@ -45,6 +45,15 @@ struct mxc_gpio_hwdata {
 	unsigned fall_edge;
 };
 
+struct mxc_gpio_reg_saved {
+	u32 icr1;
+	u32 icr2;
+	u32 imr;
+	u32 gdir;
+	u32 edge_sel;
+	u32 dr;
+};
+
 struct mxc_gpio_port {
 	struct list_head node;
 	void __iomem *base;
@@ -55,6 +64,8 @@ struct mxc_gpio_port {
 	struct gpio_chip gc;
 	struct device *dev;
 	u32 both_edges;
+	struct mxc_gpio_reg_saved gpio_saved_reg;
+	bool power_off;
 };
 
 static struct mxc_gpio_hwdata imx1_imx21_gpio_hwdata = {
@@ -143,6 +154,7 @@ static const struct of_device_id mxc_gpio_dt_ids[] = {
 	{ .compatible = "fsl,imx21-gpio", .data = &mxc_gpio_devtype[IMX21_GPIO], },
 	{ .compatible = "fsl,imx31-gpio", .data = &mxc_gpio_devtype[IMX31_GPIO], },
 	{ .compatible = "fsl,imx35-gpio", .data = &mxc_gpio_devtype[IMX35_GPIO], },
+	{ .compatible = "fsl,imx7d-gpio", .data = &mxc_gpio_devtype[IMX35_GPIO], },
 	{ /* sentinel */ }
 };
 
@@ -434,6 +446,9 @@ static int mxc_gpio_probe(struct platform_device *pdev)
 		return err;
 	}
 
+	if (of_device_is_compatible(np, "fsl,imx7d-gpio"))
+		port->power_off = true;
+
 	/* disable the interrupt and clear the status */
 	writel(0, port->base + GPIO_IMR);
 	writel(~0, port->base + GPIO_ISR);
@@ -497,6 +512,8 @@ static int mxc_gpio_probe(struct platform_device *pdev)
 
 	list_add_tail(&port->node, &mxc_gpio_ports);
 
+	platform_set_drvdata(pdev, port);
+
 	return 0;
 
 out_irqdomain_remove:
@@ -507,11 +524,67 @@ out_bgio:
 	return err;
 }
 
+static void mxc_gpio_save_regs(struct mxc_gpio_port *port)
+{
+	if (!port->power_off)
+		return;
+
+	port->gpio_saved_reg.icr1 = readl(port->base + GPIO_ICR1);
+	port->gpio_saved_reg.icr2 = readl(port->base + GPIO_ICR2);
+	port->gpio_saved_reg.imr = readl(port->base + GPIO_IMR);
+	port->gpio_saved_reg.gdir = readl(port->base + GPIO_GDIR);
+	port->gpio_saved_reg.edge_sel = readl(port->base + GPIO_EDGE_SEL);
+	port->gpio_saved_reg.dr = readl(port->base + GPIO_DR);
+}
+
+static void mxc_gpio_restore_regs(struct mxc_gpio_port *port)
+{
+	if (!port->power_off)
+		return;
+
+	writel(port->gpio_saved_reg.icr1, port->base + GPIO_ICR1);
+	writel(port->gpio_saved_reg.icr2, port->base + GPIO_ICR2);
+	writel(port->gpio_saved_reg.imr, port->base + GPIO_IMR);
+	writel(port->gpio_saved_reg.gdir, port->base + GPIO_GDIR);
+	writel(port->gpio_saved_reg.edge_sel, port->base + GPIO_EDGE_SEL);
+	writel(port->gpio_saved_reg.dr, port->base + GPIO_DR);
+}
+
+static int __maybe_unused mxc_gpio_noirq_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct mxc_gpio_port *port = platform_get_drvdata(pdev);
+
+	mxc_gpio_save_regs(port);
+	clk_disable_unprepare(port->clk);
+
+	return 0;
+}
+
+static int __maybe_unused mxc_gpio_noirq_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct mxc_gpio_port *port = platform_get_drvdata(pdev);
+	int ret;
+
+	ret = clk_prepare_enable(port->clk);
+	if (ret)
+		return ret;
+	mxc_gpio_restore_regs(port);
+
+	return 0;
+}
+
+static const struct dev_pm_ops mxc_gpio_dev_pm_ops = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(mxc_gpio_noirq_suspend, mxc_gpio_noirq_resume)
+};
+
 static struct platform_driver mxc_gpio_driver = {
 	.driver		= {
 		.name	= "gpio-mxc",
 		.of_match_table = mxc_gpio_dt_ids,
 		.suppress_bind_attrs = true,
+		.pm = &mxc_gpio_dev_pm_ops,
 	},
 	.probe		= mxc_gpio_probe,
 	.id_table	= mxc_gpio_devtype,
diff --git a/drivers/gpio/gpio-mxs.c b/drivers/gpio/gpio-mxs.c
index e2831ee70cdc..df30490da820 100644
--- a/drivers/gpio/gpio-mxs.c
+++ b/drivers/gpio/gpio-mxs.c
@@ -126,8 +126,7 @@ static int mxs_gpio_set_irq_type(struct irq_data *d, unsigned int type)
 	else
 		writel(pin_mask, pin_addr + MXS_CLR);
 
-	writel(pin_mask,
-	       port->base + PINCTRL_IRQSTAT(port) + MXS_CLR);
+	writel(pin_mask, port->base + PINCTRL_IRQSTAT(port) + MXS_CLR);
 
 	return 0;
 }
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index d1afedf4dcbf..e81008678a38 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -77,6 +77,8 @@ struct gpio_bank {
 	bool workaround_enabled;
 
 	void (*set_dataout)(struct gpio_bank *bank, unsigned gpio, int enable);
+	void (*set_dataout_multiple)(struct gpio_bank *bank,
+				     unsigned long *mask, unsigned long *bits);
 	int (*get_context_loss_count)(struct device *dev);
 
 	struct omap_gpio_reg_offs *regs;
@@ -161,6 +163,51 @@ static int omap_get_gpio_dataout(struct gpio_bank *bank, int offset)
 	return (readl_relaxed(reg) & (BIT(offset))) != 0;
 }
 
+/* set multiple data out values using dedicate set/clear register */
+static void omap_set_gpio_dataout_reg_multiple(struct gpio_bank *bank,
+					       unsigned long *mask,
+					       unsigned long *bits)
+{
+	void __iomem *reg = bank->base;
+	u32 l;
+
+	l = *bits & *mask;
+	writel_relaxed(l, reg + bank->regs->set_dataout);
+	bank->context.dataout |= l;
+
+	l = ~*bits & *mask;
+	writel_relaxed(l, reg + bank->regs->clr_dataout);
+	bank->context.dataout &= ~l;
+}
+
+/* set multiple data out values using mask register */
+static void omap_set_gpio_dataout_mask_multiple(struct gpio_bank *bank,
+						unsigned long *mask,
+						unsigned long *bits)
+{
+	void __iomem *reg = bank->base + bank->regs->dataout;
+	u32 l = (readl_relaxed(reg) & ~*mask) | (*bits & *mask);
+
+	writel_relaxed(l, reg);
+	bank->context.dataout = l;
+}
+
+static unsigned long omap_get_gpio_datain_multiple(struct gpio_bank *bank,
+					      unsigned long *mask)
+{
+	void __iomem *reg = bank->base + bank->regs->datain;
+
+	return readl_relaxed(reg) & *mask;
+}
+
+static unsigned long omap_get_gpio_dataout_multiple(struct gpio_bank *bank,
+					       unsigned long *mask)
+{
+	void __iomem *reg = bank->base + bank->regs->dataout;
+
+	return readl_relaxed(reg) & *mask;
+}
+
 static inline void omap_gpio_rmw(void __iomem *base, u32 reg, u32 mask, bool set)
 {
 	int l = readl_relaxed(base + reg);
@@ -968,6 +1015,26 @@ static int omap_gpio_output(struct gpio_chip *chip, unsigned offset, int value)
 	return 0;
 }
 
+static int omap_gpio_get_multiple(struct gpio_chip *chip, unsigned long *mask,
+				  unsigned long *bits)
+{
+	struct gpio_bank *bank = gpiochip_get_data(chip);
+	void __iomem *reg = bank->base + bank->regs->direction;
+	unsigned long in = readl_relaxed(reg), l;
+
+	*bits = 0;
+
+	l = in & *mask;
+	if (l)
+		*bits |= omap_get_gpio_datain_multiple(bank, &l);
+
+	l = ~in & *mask;
+	if (l)
+		*bits |= omap_get_gpio_dataout_multiple(bank, &l);
+
+	return 0;
+}
+
 static int omap_gpio_debounce(struct gpio_chip *chip, unsigned offset,
 			      unsigned debounce)
 {
@@ -1012,6 +1079,17 @@ static void omap_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
 	raw_spin_unlock_irqrestore(&bank->lock, flags);
 }
 
+static void omap_gpio_set_multiple(struct gpio_chip *chip, unsigned long *mask,
+				   unsigned long *bits)
+{
+	struct gpio_bank *bank = gpiochip_get_data(chip);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&bank->lock, flags);
+	bank->set_dataout_multiple(bank, mask, bits);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
+}
+
 /*---------------------------------------------------------------------*/
 
 static void omap_gpio_show_rev(struct gpio_bank *bank)
@@ -1073,9 +1151,11 @@ static int omap_gpio_chip_init(struct gpio_bank *bank, struct irq_chip *irqc)
 	bank->chip.get_direction = omap_gpio_get_direction;
 	bank->chip.direction_input = omap_gpio_input;
 	bank->chip.get = omap_gpio_get;
+	bank->chip.get_multiple = omap_gpio_get_multiple;
 	bank->chip.direction_output = omap_gpio_output;
 	bank->chip.set_config = omap_gpio_set_config;
 	bank->chip.set = omap_gpio_set;
+	bank->chip.set_multiple = omap_gpio_set_multiple;
 	if (bank->is_mpuio) {
 		bank->chip.label = "mpuio";
 		if (bank->regs->wkup_en)
@@ -1209,10 +1289,14 @@ static int omap_gpio_probe(struct platform_device *pdev)
 				pdata->get_context_loss_count;
 	}
 
-	if (bank->regs->set_dataout && bank->regs->clr_dataout)
+	if (bank->regs->set_dataout && bank->regs->clr_dataout) {
 		bank->set_dataout = omap_set_gpio_dataout_reg;
-	else
+		bank->set_dataout_multiple = omap_set_gpio_dataout_reg_multiple;
+	} else {
 		bank->set_dataout = omap_set_gpio_dataout_mask;
+		bank->set_dataout_multiple =
+				omap_set_gpio_dataout_mask_multiple;
+	}
 
 	raw_spin_lock_init(&bank->lock);
 	raw_spin_lock_init(&bank->wa_lock);
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index c55ad157e820..023a32cfac42 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -708,7 +708,7 @@ static int pca953x_irq_setup(struct pca953x_chip *chip,
 {
 	struct i2c_client *client = chip->client;
 
-	if (irq_base != -1 && (chip->driver_data & PCA_INT))
+	if (client->irq && irq_base != -1 && (chip->driver_data & PCA_INT))
 		dev_warn(&client->dev, "interrupt support not compiled in\n");
 
 	return 0;
diff --git a/drivers/gpio/gpio-pisosr.c b/drivers/gpio/gpio-pisosr.c
index f5545049c187..f809a5a8e9eb 100644
--- a/drivers/gpio/gpio-pisosr.c
+++ b/drivers/gpio/gpio-pisosr.c
@@ -12,6 +12,8 @@
  * GNU General Public License version 2 for more details.
  */
 
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
 #include <linux/gpio/driver.h>
@@ -90,6 +92,25 @@ static int pisosr_gpio_get(struct gpio_chip *chip, unsigned offset)
 	return (gpio->buffer[offset / 8] >> (offset % 8)) & 0x1;
 }
 
+static int pisosr_gpio_get_multiple(struct gpio_chip *chip,
+				    unsigned long *mask, unsigned long *bits)
+{
+	struct pisosr_gpio *gpio = gpiochip_get_data(chip);
+	unsigned int nbytes = DIV_ROUND_UP(chip->ngpio, 8);
+	unsigned int i, j;
+
+	pisosr_gpio_refresh(gpio);
+
+	bitmap_zero(bits, chip->ngpio);
+	for (i = 0; i < nbytes; i++) {
+		j = i / sizeof(unsigned long);
+		bits[j] |= ((unsigned long) gpio->buffer[i])
+			   << (8 * (i % sizeof(unsigned long)));
+	}
+
+	return 0;
+}
+
 static const struct gpio_chip template_chip = {
 	.label			= "pisosr-gpio",
 	.owner			= THIS_MODULE,
@@ -97,6 +118,7 @@ static const struct gpio_chip template_chip = {
 	.direction_input	= pisosr_gpio_direction_input,
 	.direction_output	= pisosr_gpio_direction_output,
 	.get			= pisosr_gpio_get,
+	.get_multiple		= pisosr_gpio_get_multiple,
 	.base			= -1,
 	.ngpio			= DEFAULT_NGPIO,
 	.can_sleep		= true,
diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c
index 1e66f808051c..c18712dabf93 100644
--- a/drivers/gpio/gpio-pxa.c
+++ b/drivers/gpio/gpio-pxa.c
@@ -241,6 +241,17 @@ int pxa_irq_to_gpio(int irq)
 	return irq_gpio0;
 }
 
+static bool pxa_gpio_has_pinctrl(void)
+{
+	switch (gpio_type) {
+	case PXA3XX_GPIO:
+		return false;
+
+	default:
+		return true;
+	}
+}
+
 static int pxa_gpio_to_irq(struct gpio_chip *chip, unsigned offset)
 {
 	struct pxa_gpio_chip *pchip = chip_to_pxachip(chip);
@@ -255,9 +266,11 @@ static int pxa_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
 	unsigned long flags;
 	int ret;
 
-	ret = pinctrl_gpio_direction_input(chip->base + offset);
-	if (!ret)
-		return 0;
+	if (pxa_gpio_has_pinctrl()) {
+		ret = pinctrl_gpio_direction_input(chip->base + offset);
+		if (!ret)
+			return 0;
+	}
 
 	spin_lock_irqsave(&gpio_lock, flags);
 
@@ -282,9 +295,11 @@ static int pxa_gpio_direction_output(struct gpio_chip *chip,
 
 	writel_relaxed(mask, base + (value ? GPSR_OFFSET : GPCR_OFFSET));
 
-	ret = pinctrl_gpio_direction_output(chip->base + offset);
-	if (ret)
-		return ret;
+	if (pxa_gpio_has_pinctrl()) {
+		ret = pinctrl_gpio_direction_output(chip->base + offset);
+		if (ret)
+			return ret;
+	}
 
 	spin_lock_irqsave(&gpio_lock, flags);
 
@@ -348,8 +363,12 @@ static int pxa_init_gpio_chip(struct pxa_gpio_chip *pchip, int ngpio,
 	pchip->chip.set = pxa_gpio_set;
 	pchip->chip.to_irq = pxa_gpio_to_irq;
 	pchip->chip.ngpio = ngpio;
-	pchip->chip.request = gpiochip_generic_request;
-	pchip->chip.free = gpiochip_generic_free;
+
+	if (pxa_gpio_has_pinctrl()) {
+		pchip->chip.request = gpiochip_generic_request;
+		pchip->chip.free = gpiochip_generic_free;
+	}
+
 #ifdef CONFIG_OF_GPIO
 	pchip->chip.of_node = np;
 	pchip->chip.of_xlate = pxa_gpio_of_xlate;
@@ -607,7 +626,7 @@ static int pxa_gpio_probe(struct platform_device *pdev)
 	struct pxa_gpio_platform_data *info;
 	void __iomem *gpio_reg_base;
 	int gpio, ret;
-	int irq0 = 0, irq1 = 0, irq_mux, gpio_offset = 0;
+	int irq0 = 0, irq1 = 0, irq_mux;
 
 	pchip = devm_kzalloc(&pdev->dev, sizeof(*pchip), GFP_KERNEL);
 	if (!pchip)
@@ -646,14 +665,13 @@ static int pxa_gpio_probe(struct platform_device *pdev)
 	pchip->irq0 = irq0;
 	pchip->irq1 = irq1;
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -EINVAL;
 	gpio_reg_base = devm_ioremap(&pdev->dev, res->start,
 				     resource_size(res));
 	if (!gpio_reg_base)
 		return -EINVAL;
 
-	if (irq0 > 0)
-		gpio_offset = 2;
-
 	clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(clk)) {
 		dev_err(&pdev->dev, "Error %ld to get gpio clock\n",
diff --git a/drivers/gpio/gpio-rc5t583.c b/drivers/gpio/gpio-rc5t583.c
index 3b4dc1a9a68d..a499c633a6c5 100644
--- a/drivers/gpio/gpio-rc5t583.c
+++ b/drivers/gpio/gpio-rc5t583.c
@@ -25,7 +25,7 @@
 #include <linux/slab.h>
 #include <linux/platform_device.h>
 #include <linux/device.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/mfd/rc5t583.h>
 
 struct rc5t583_gpio {
diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index 350390c0b290..55cc61086d99 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -15,7 +15,7 @@
  */
 
 #include <linux/err.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -278,6 +278,13 @@ static void gpio_rcar_free(struct gpio_chip *chip, unsigned offset)
 	pm_runtime_put(&p->pdev->dev);
 }
 
+static int gpio_rcar_get_direction(struct gpio_chip *chip, unsigned int offset)
+{
+	struct gpio_rcar_priv *p = gpiochip_get_data(chip);
+
+	return !(gpio_rcar_read(p, INOUTSEL) & BIT(offset));
+}
+
 static int gpio_rcar_direction_input(struct gpio_chip *chip, unsigned offset)
 {
 	gpio_rcar_config_general_input_output_mode(chip, offset, false);
@@ -461,6 +468,7 @@ static int gpio_rcar_probe(struct platform_device *pdev)
 	gpio_chip = &p->gpio_chip;
 	gpio_chip->request = gpio_rcar_request;
 	gpio_chip->free = gpio_rcar_free;
+	gpio_chip->get_direction = gpio_rcar_get_direction;
 	gpio_chip->direction_input = gpio_rcar_direction_input;
 	gpio_chip->get = gpio_rcar_get;
 	gpio_chip->direction_output = gpio_rcar_direction_output;
diff --git a/drivers/gpio/gpio-rdc321x.c b/drivers/gpio/gpio-rdc321x.c
index cbf0f9e6465b..2938217566d3 100644
--- a/drivers/gpio/gpio-rdc321x.c
+++ b/drivers/gpio/gpio-rdc321x.c
@@ -25,7 +25,7 @@
 #include <linux/spinlock.h>
 #include <linux/platform_device.h>
 #include <linux/pci.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/mfd/rdc321x.h>
 #include <linux/slab.h>
 
diff --git a/drivers/gpio/gpio-sa1100.c b/drivers/gpio/gpio-sa1100.c
index 249f433aa62d..986eb3b231ac 100644
--- a/drivers/gpio/gpio-sa1100.c
+++ b/drivers/gpio/gpio-sa1100.c
@@ -7,7 +7,7 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/io.h>
diff --git a/drivers/gpio/gpio-sch.c b/drivers/gpio/gpio-sch.c
index 545004445846..e9878f6ede67 100644
--- a/drivers/gpio/gpio-sch.c
+++ b/drivers/gpio/gpio-sch.c
@@ -26,8 +26,7 @@
 #include <linux/acpi.h>
 #include <linux/platform_device.h>
 #include <linux/pci_ids.h>
-
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 
 #define GEN	0x00
 #define GIO	0x04
@@ -138,6 +137,13 @@ static int sch_gpio_direction_out(struct gpio_chip *gc, unsigned gpio_num,
 	return 0;
 }
 
+static int sch_gpio_get_direction(struct gpio_chip *gc, unsigned gpio_num)
+{
+	struct sch_gpio *sch = gpiochip_get_data(gc);
+
+	return sch_gpio_reg_get(sch, gpio_num, GIO);
+}
+
 static const struct gpio_chip sch_gpio_chip = {
 	.label			= "sch_gpio",
 	.owner			= THIS_MODULE,
@@ -145,6 +151,7 @@ static const struct gpio_chip sch_gpio_chip = {
 	.get			= sch_gpio_get,
 	.direction_output	= sch_gpio_direction_out,
 	.set			= sch_gpio_set,
+	.get_direction		= sch_gpio_get_direction,
 };
 
 static int sch_gpio_probe(struct platform_device *pdev)
diff --git a/drivers/gpio/gpio-sch311x.c b/drivers/gpio/gpio-sch311x.c
index b96990c262a1..5497f0a88cf0 100644
--- a/drivers/gpio/gpio-sch311x.c
+++ b/drivers/gpio/gpio-sch311x.c
@@ -17,16 +17,15 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/bitops.h>
 #include <linux/io.h>
 
 #define DRV_NAME			"gpio-sch311x"
 
-#define SCH311X_GPIO_CONF_OUT		0x00
-#define SCH311X_GPIO_CONF_IN		0x01
-#define SCH311X_GPIO_CONF_INVERT	0x02
-#define SCH311X_GPIO_CONF_OPEN_DRAIN	0x80
+#define SCH311X_GPIO_CONF_DIR		BIT(0)
+#define SCH311X_GPIO_CONF_INVERT	BIT(1)
+#define SCH311X_GPIO_CONF_OPEN_DRAIN	BIT(7)
 
 #define SIO_CONFIG_KEY_ENTER		0x55
 #define SIO_CONFIG_KEY_EXIT		0xaa
@@ -163,7 +162,7 @@ static void sch311x_gpio_free(struct gpio_chip *chip, unsigned offset)
 static int sch311x_gpio_get(struct gpio_chip *chip, unsigned offset)
 {
 	struct sch311x_gpio_block *block = gpiochip_get_data(chip);
-	unsigned char data;
+	u8 data;
 
 	spin_lock(&block->lock);
 	data = inb(block->runtime_reg + block->data_reg);
@@ -175,7 +174,7 @@ static int sch311x_gpio_get(struct gpio_chip *chip, unsigned offset)
 static void __sch311x_gpio_set(struct sch311x_gpio_block *block,
 			       unsigned offset, int value)
 {
-	unsigned char data = inb(block->runtime_reg + block->data_reg);
+	u8 data = inb(block->runtime_reg + block->data_reg);
 	if (value)
 		data |= BIT(offset);
 	else
@@ -196,10 +195,12 @@ static void sch311x_gpio_set(struct gpio_chip *chip, unsigned offset,
 static int sch311x_gpio_direction_in(struct gpio_chip *chip, unsigned offset)
 {
 	struct sch311x_gpio_block *block = gpiochip_get_data(chip);
+	u8 data;
 
 	spin_lock(&block->lock);
-	outb(SCH311X_GPIO_CONF_IN, block->runtime_reg +
-	     block->config_regs[offset]);
+	data = inb(block->runtime_reg + block->config_regs[offset]);
+	data |= SCH311X_GPIO_CONF_DIR;
+	outb(data, block->runtime_reg + block->config_regs[offset]);
 	spin_unlock(&block->lock);
 
 	return 0;
@@ -209,18 +210,59 @@ static int sch311x_gpio_direction_out(struct gpio_chip *chip, unsigned offset,
 				      int value)
 {
 	struct sch311x_gpio_block *block = gpiochip_get_data(chip);
+	u8 data;
 
 	spin_lock(&block->lock);
 
-	outb(SCH311X_GPIO_CONF_OUT, block->runtime_reg +
-	     block->config_regs[offset]);
-
+	data = inb(block->runtime_reg + block->config_regs[offset]);
+	data &= ~SCH311X_GPIO_CONF_DIR;
+	outb(data, block->runtime_reg + block->config_regs[offset]);
 	__sch311x_gpio_set(block, offset, value);
 
 	spin_unlock(&block->lock);
 	return 0;
 }
 
+static int sch311x_gpio_get_direction(struct gpio_chip *chip, unsigned offset)
+{
+	struct sch311x_gpio_block *block = gpiochip_get_data(chip);
+	u8 data;
+
+	spin_lock(&block->lock);
+	data = inb(block->runtime_reg + block->config_regs[offset]);
+	spin_unlock(&block->lock);
+
+	return !!(data & SCH311X_GPIO_CONF_DIR);
+}
+
+static int sch311x_gpio_set_config(struct gpio_chip *chip, unsigned offset,
+				   unsigned long config)
+{
+	struct sch311x_gpio_block *block = gpiochip_get_data(chip);
+	enum pin_config_param param = pinconf_to_config_param(config);
+	u8 data;
+
+	switch (param) {
+	case PIN_CONFIG_DRIVE_OPEN_DRAIN:
+		spin_lock(&block->lock);
+		data = inb(block->runtime_reg + block->config_regs[offset]);
+		data |= SCH311X_GPIO_CONF_OPEN_DRAIN;
+		outb(data, block->runtime_reg + block->config_regs[offset]);
+		spin_unlock(&block->lock);
+		return 0;
+	case PIN_CONFIG_DRIVE_PUSH_PULL:
+		spin_lock(&block->lock);
+		data = inb(block->runtime_reg + block->config_regs[offset]);
+		data &= ~SCH311X_GPIO_CONF_OPEN_DRAIN;
+		outb(data, block->runtime_reg + block->config_regs[offset]);
+		spin_unlock(&block->lock);
+		return 0;
+	default:
+		break;
+	}
+	return -ENOTSUPP;
+}
+
 static int sch311x_gpio_probe(struct platform_device *pdev)
 {
 	struct sch311x_pdev_data *pdata = dev_get_platdata(&pdev->dev);
@@ -253,6 +295,8 @@ static int sch311x_gpio_probe(struct platform_device *pdev)
 		block->chip.free = sch311x_gpio_free;
 		block->chip.direction_input = sch311x_gpio_direction_in;
 		block->chip.direction_output = sch311x_gpio_direction_out;
+		block->chip.get_direction = sch311x_gpio_get_direction;
+		block->chip.set_config = sch311x_gpio_set_config;
 		block->chip.get = sch311x_gpio_get;
 		block->chip.set = sch311x_gpio_set;
 		block->chip.ngpio = 8;
@@ -309,7 +353,7 @@ static int __init sch311x_detect(int sio_config_port, unsigned short *addr)
 {
 	int err = 0, reg;
 	unsigned short base_addr;
-	unsigned char dev_id;
+	u8 dev_id;
 
 	err = sch311x_sio_enter(sio_config_port);
 	if (err)
diff --git a/drivers/gpio/gpio-spear-spics.c b/drivers/gpio/gpio-spear-spics.c
index 22267479ba68..ee3039f091f4 100644
--- a/drivers/gpio/gpio-spear-spics.c
+++ b/drivers/gpio/gpio-spear-spics.c
@@ -10,7 +10,7 @@
  */
 
 #include <linux/err.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/io.h>
 #include <linux/init.h>
 #include <linux/of.h>
diff --git a/drivers/gpio/gpio-sta2x11.c b/drivers/gpio/gpio-sta2x11.c
index 407359da08f9..2283c869ad5d 100644
--- a/drivers/gpio/gpio-sta2x11.c
+++ b/drivers/gpio/gpio-sta2x11.c
@@ -23,7 +23,8 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
+#include <linux/bitops.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/pci.h>
@@ -58,16 +59,6 @@ struct gsta_gpio {
 	unsigned			irq_type[GSTA_NR_GPIO];
 };
 
-static inline struct gsta_regs __iomem *__regs(struct gsta_gpio *chip, int nr)
-{
-	return chip->regs[nr / GSTA_GPIO_PER_BLOCK];
-}
-
-static inline u32 __bit(int nr)
-{
-	return 1U << (nr % GSTA_GPIO_PER_BLOCK);
-}
-
 /*
  * gpio methods
  */
@@ -75,8 +66,8 @@ static inline u32 __bit(int nr)
 static void gsta_gpio_set(struct gpio_chip *gpio, unsigned nr, int val)
 {
 	struct gsta_gpio *chip = gpiochip_get_data(gpio);
-	struct gsta_regs __iomem *regs = __regs(chip, nr);
-	u32 bit = __bit(nr);
+	struct gsta_regs __iomem *regs = chip->regs[nr / GSTA_GPIO_PER_BLOCK];
+	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 
 	if (val)
 		writel(bit, &regs->dats);
@@ -87,8 +78,8 @@ static void gsta_gpio_set(struct gpio_chip *gpio, unsigned nr, int val)
 static int gsta_gpio_get(struct gpio_chip *gpio, unsigned nr)
 {
 	struct gsta_gpio *chip = gpiochip_get_data(gpio);
-	struct gsta_regs __iomem *regs = __regs(chip, nr);
-	u32 bit = __bit(nr);
+	struct gsta_regs __iomem *regs = chip->regs[nr / GSTA_GPIO_PER_BLOCK];
+	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 
 	return !!(readl(&regs->dat) & bit);
 }
@@ -97,8 +88,8 @@ static int gsta_gpio_direction_output(struct gpio_chip *gpio, unsigned nr,
 				      int val)
 {
 	struct gsta_gpio *chip = gpiochip_get_data(gpio);
-	struct gsta_regs __iomem *regs = __regs(chip, nr);
-	u32 bit = __bit(nr);
+	struct gsta_regs __iomem *regs = chip->regs[nr / GSTA_GPIO_PER_BLOCK];
+	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 
 	writel(bit, &regs->dirs);
 	/* Data register after direction, otherwise pullup/down is selected */
@@ -112,8 +103,8 @@ static int gsta_gpio_direction_output(struct gpio_chip *gpio, unsigned nr,
 static int gsta_gpio_direction_input(struct gpio_chip *gpio, unsigned nr)
 {
 	struct gsta_gpio *chip = gpiochip_get_data(gpio);
-	struct gsta_regs __iomem *regs = __regs(chip, nr);
-	u32 bit = __bit(nr);
+	struct gsta_regs __iomem *regs = chip->regs[nr / GSTA_GPIO_PER_BLOCK];
+	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 
 	writel(bit, &regs->dirc);
 	return 0;
@@ -165,9 +156,9 @@ static void gsta_gpio_setup(struct gsta_gpio *chip) /* called from probe */
  */
 static void gsta_set_config(struct gsta_gpio *chip, int nr, unsigned cfg)
 {
-	struct gsta_regs __iomem *regs = __regs(chip, nr);
+	struct gsta_regs __iomem *regs = chip->regs[nr / GSTA_GPIO_PER_BLOCK];
 	unsigned long flags;
-	u32 bit = __bit(nr);
+	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 	u32 val;
 	int err = 0;
 
@@ -234,8 +225,8 @@ static void gsta_irq_disable(struct irq_data *data)
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
 	struct gsta_gpio *chip = gc->private;
 	int nr = data->irq - chip->irq_base;
-	struct gsta_regs __iomem *regs = __regs(chip, nr);
-	u32 bit = __bit(nr);
+	struct gsta_regs __iomem *regs = chip->regs[nr / GSTA_GPIO_PER_BLOCK];
+	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 	u32 val;
 	unsigned long flags;
 
@@ -257,8 +248,8 @@ static void gsta_irq_enable(struct irq_data *data)
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
 	struct gsta_gpio *chip = gc->private;
 	int nr = data->irq - chip->irq_base;
-	struct gsta_regs __iomem *regs = __regs(chip, nr);
-	u32 bit = __bit(nr);
+	struct gsta_regs __iomem *regs = chip->regs[nr / GSTA_GPIO_PER_BLOCK];
+	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 	u32 val;
 	int type;
 	unsigned long flags;
diff --git a/drivers/gpio/gpio-stmpe.c b/drivers/gpio/gpio-stmpe.c
index 8d6a5a7e612d..65a2315f1673 100644
--- a/drivers/gpio/gpio-stmpe.c
+++ b/drivers/gpio/gpio-stmpe.c
@@ -8,7 +8,7 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/interrupt.h>
 #include <linux/of.h>
 #include <linux/mfd/stmpe.h>
diff --git a/drivers/gpio/gpio-stp-xway.c b/drivers/gpio/gpio-stp-xway.c
index c07385b71403..19972084c45b 100644
--- a/drivers/gpio/gpio-stp-xway.c
+++ b/drivers/gpio/gpio-stp-xway.c
@@ -13,9 +13,8 @@
 #include <linux/types.h>
 #include <linux/of_platform.h>
 #include <linux/mutex.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/io.h>
-#include <linux/of_gpio.h>
 #include <linux/clk.h>
 #include <linux/err.h>
 
@@ -91,6 +90,20 @@ struct xway_stp {
 };
 
 /**
+ * xway_stp_get() - gpio_chip->get - get gpios.
+ * @gc:     Pointer to gpio_chip device structure.
+ * @gpio:   GPIO signal number.
+ *
+ * Gets the shadow value.
+ */
+static int xway_stp_get(struct gpio_chip *gc, unsigned int gpio)
+{
+	struct xway_stp *chip = gpiochip_get_data(gc);
+
+	return (xway_stp_r32(chip->virt, XWAY_STP_CPU0) & BIT(gpio));
+}
+
+/**
  * xway_stp_set() - gpio_chip->set - set gpios.
  * @gc:     Pointer to gpio_chip device structure.
  * @gpio:   GPIO signal number.
@@ -215,6 +228,7 @@ static int xway_stp_probe(struct platform_device *pdev)
 	chip->gc.parent = &pdev->dev;
 	chip->gc.label = "stp-xway";
 	chip->gc.direction_output = xway_stp_dir_out;
+	chip->gc.get = xway_stp_get;
 	chip->gc.set = xway_stp_set;
 	chip->gc.request = xway_stp_request;
 	chip->gc.base = -1;
diff --git a/drivers/gpio/gpio-syscon.c b/drivers/gpio/gpio-syscon.c
index 8b0a69c5ba88..87c18a544513 100644
--- a/drivers/gpio/gpio-syscon.c
+++ b/drivers/gpio/gpio-syscon.c
@@ -10,7 +10,7 @@
  */
 
 #include <linux/err.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
@@ -135,6 +135,33 @@ static const struct syscon_gpio_data clps711x_mctrl_gpio = {
 	.dat_bit_offset	= 0x40 * 8 + 8,
 };
 
+static void rockchip_gpio_set(struct gpio_chip *chip, unsigned int offset,
+			      int val)
+{
+	struct syscon_gpio_priv *priv = gpiochip_get_data(chip);
+	unsigned int offs;
+	u8 bit;
+	u32 data;
+	int ret;
+
+	offs = priv->dreg_offset + priv->data->dat_bit_offset + offset;
+	bit = offs % SYSCON_REG_BITS;
+	data = (val ? BIT(bit) : 0) | BIT(bit + 16);
+	ret = regmap_write(priv->syscon,
+			   (offs / SYSCON_REG_BITS) * SYSCON_REG_SIZE,
+			   data);
+	if (ret < 0)
+		dev_err(chip->parent, "gpio write failed ret(%d)\n", ret);
+}
+
+static const struct syscon_gpio_data rockchip_rk3328_gpio_mute = {
+	/* RK3328 GPIO_MUTE is an output only pin at GRF_SOC_CON10[1] */
+	.flags		= GPIO_SYSCON_FEAT_OUT,
+	.bit_count	= 1,
+	.dat_bit_offset = 0x0428 * 8 + 1,
+	.set		= rockchip_gpio_set,
+};
+
 #define KEYSTONE_LOCK_BIT BIT(0)
 
 static void keystone_gpio_set(struct gpio_chip *chip, unsigned offset, int val)
@@ -175,6 +202,10 @@ static const struct of_device_id syscon_gpio_ids[] = {
 		.compatible	= "ti,keystone-dsp-gpio",
 		.data		= &keystone_dsp_gpio,
 	},
+	{
+		.compatible	= "rockchip,rk3328-grf-gpio",
+		.data		= &rockchip_rk3328_gpio_mute,
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, syscon_gpio_ids);
diff --git a/drivers/gpio/gpio-tb10x.c b/drivers/gpio/gpio-tb10x.c
index ac6f2a9841e5..a12cd0b5c972 100644
--- a/drivers/gpio/gpio-tb10x.c
+++ b/drivers/gpio/gpio-tb10x.c
@@ -22,7 +22,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/slab.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
@@ -30,7 +30,6 @@
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
-#include <linux/of_gpio.h>
 #include <linux/spinlock.h>
 #include <linux/bitops.h>
 #include <linux/pinctrl/consumer.h>
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index 94396caaca75..47dbd19751d0 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -22,7 +22,7 @@
 #include <linux/irq.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/module.h>
@@ -207,7 +207,7 @@ static int tegra_gpio_get_direction(struct gpio_chip *chip,
 
 	oe = tegra_gpio_readl(tgi, GPIO_OE(tgi, offset));
 
-	return (oe & pin_mask) ? GPIOF_DIR_OUT : GPIOF_DIR_IN;
+	return !(oe & pin_mask);
 }
 
 static int tegra_gpio_set_debounce(struct gpio_chip *chip, unsigned int offset,
@@ -323,13 +323,6 @@ static int tegra_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 		return -EINVAL;
 	}
 
-	ret = gpiochip_lock_as_irq(&tgi->gc, gpio);
-	if (ret) {
-		dev_err(tgi->dev,
-			"unable to lock Tegra GPIO %u as IRQ\n", gpio);
-		return ret;
-	}
-
 	spin_lock_irqsave(&bank->lvl_lock[port], flags);
 
 	val = tegra_gpio_readl(tgi, GPIO_INT_LVL(tgi, gpio));
@@ -342,6 +335,14 @@ static int tegra_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 	tegra_gpio_mask_write(tgi, GPIO_MSK_OE(tgi, gpio), gpio, 0);
 	tegra_gpio_enable(tgi, gpio);
 
+	ret = gpiochip_lock_as_irq(&tgi->gc, gpio);
+	if (ret) {
+		dev_err(tgi->dev,
+			"unable to lock Tegra GPIO %u as IRQ\n", gpio);
+		tegra_gpio_disable(tgi, gpio);
+		return ret;
+	}
+
 	if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
 		irq_set_handler_locked(d, handle_level_irq);
 	else if (type & (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING))
@@ -550,13 +551,6 @@ static const struct dev_pm_ops tegra_gpio_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(tegra_gpio_suspend, tegra_gpio_resume)
 };
 
-/*
- * This lock class tells lockdep that GPIO irqs are in a different category
- * than their parents, so it won't report false recursion.
- */
-static struct lock_class_key gpio_lock_class;
-static struct lock_class_key gpio_request_class;
-
 static int tegra_gpio_probe(struct platform_device *pdev)
 {
 	struct tegra_gpio_info *tgi;
@@ -661,8 +655,6 @@ static int tegra_gpio_probe(struct platform_device *pdev)
 
 		bank = &tgi->bank_info[GPIO_BANK(gpio)];
 
-		irq_set_lockdep_class(irq, &gpio_lock_class,
-				      &gpio_request_class);
 		irq_set_chip_data(irq, bank);
 		irq_set_chip_and_handler(irq, &tgi->ic, handle_simple_irq);
 	}
@@ -720,4 +712,4 @@ static int __init tegra_gpio_init(void)
 {
 	return platform_driver_register(&tegra_gpio_driver);
 }
-postcore_initcall(tegra_gpio_init);
+subsys_initcall(tegra_gpio_init);
diff --git a/drivers/gpio/gpio-tegra186.c b/drivers/gpio/gpio-tegra186.c
index 7f1aa4c21e0d..9d0292c8a199 100644
--- a/drivers/gpio/gpio-tegra186.c
+++ b/drivers/gpio/gpio-tegra186.c
@@ -16,6 +16,7 @@
 #include <linux/platform_device.h>
 
 #include <dt-bindings/gpio/tegra186-gpio.h>
+#include <dt-bindings/gpio/tegra194-gpio.h>
 
 #define TEGRA186_GPIO_ENABLE_CONFIG 0x00
 #define  TEGRA186_GPIO_ENABLE_CONFIG_ENABLE BIT(0)
@@ -593,6 +594,73 @@ static const struct tegra_gpio_soc tegra186_aon_soc = {
 	.name = "tegra186-gpio-aon",
 };
 
+#define TEGRA194_MAIN_GPIO_PORT(port, base, count, controller)	\
+	[TEGRA194_MAIN_GPIO_PORT_##port] = {			\
+		.name = #port,					\
+		.offset = base,					\
+		.pins = count,					\
+		.irq = controller,				\
+	}
+
+static const struct tegra_gpio_port tegra194_main_ports[] = {
+	TEGRA194_MAIN_GPIO_PORT( A, 0x1400, 8, 1),
+	TEGRA194_MAIN_GPIO_PORT( B, 0x4e00, 2, 4),
+	TEGRA194_MAIN_GPIO_PORT( C, 0x4600, 8, 4),
+	TEGRA194_MAIN_GPIO_PORT( D, 0x4800, 4, 4),
+	TEGRA194_MAIN_GPIO_PORT( E, 0x4a00, 8, 4),
+	TEGRA194_MAIN_GPIO_PORT( F, 0x4c00, 6, 4),
+	TEGRA194_MAIN_GPIO_PORT( G, 0x4000, 8, 4),
+	TEGRA194_MAIN_GPIO_PORT( H, 0x4200, 8, 4),
+	TEGRA194_MAIN_GPIO_PORT( I, 0x4400, 5, 4),
+	TEGRA194_MAIN_GPIO_PORT( J, 0x5200, 6, 5),
+	TEGRA194_MAIN_GPIO_PORT( K, 0x3000, 8, 3),
+	TEGRA194_MAIN_GPIO_PORT( L, 0x3200, 4, 3),
+	TEGRA194_MAIN_GPIO_PORT( M, 0x2600, 8, 2),
+	TEGRA194_MAIN_GPIO_PORT( N, 0x2800, 3, 2),
+	TEGRA194_MAIN_GPIO_PORT( O, 0x5000, 6, 5),
+	TEGRA194_MAIN_GPIO_PORT( P, 0x2a00, 8, 2),
+	TEGRA194_MAIN_GPIO_PORT( Q, 0x2c00, 8, 2),
+	TEGRA194_MAIN_GPIO_PORT( R, 0x2e00, 6, 2),
+	TEGRA194_MAIN_GPIO_PORT( S, 0x3600, 8, 3),
+	TEGRA194_MAIN_GPIO_PORT( T, 0x3800, 8, 3),
+	TEGRA194_MAIN_GPIO_PORT( U, 0x3a00, 1, 3),
+	TEGRA194_MAIN_GPIO_PORT( V, 0x1000, 8, 1),
+	TEGRA194_MAIN_GPIO_PORT( W, 0x1200, 2, 1),
+	TEGRA194_MAIN_GPIO_PORT( X, 0x2000, 8, 2),
+	TEGRA194_MAIN_GPIO_PORT( Y, 0x2200, 8, 2),
+	TEGRA194_MAIN_GPIO_PORT( Z, 0x2400, 8, 2),
+	TEGRA194_MAIN_GPIO_PORT(FF, 0x3400, 2, 3),
+	TEGRA194_MAIN_GPIO_PORT(GG, 0x0000, 2, 0)
+};
+
+static const struct tegra_gpio_soc tegra194_main_soc = {
+	.num_ports = ARRAY_SIZE(tegra194_main_ports),
+	.ports = tegra194_main_ports,
+	.name = "tegra194-gpio",
+};
+
+#define TEGRA194_AON_GPIO_PORT(port, base, count, controller)	\
+	[TEGRA194_AON_GPIO_PORT_##port] = {			\
+		.name = #port,					\
+		.offset = base,					\
+		.pins = count,					\
+		.irq = controller,				\
+	}
+
+static const struct tegra_gpio_port tegra194_aon_ports[] = {
+	TEGRA194_AON_GPIO_PORT(AA, 0x0600, 8, 0),
+	TEGRA194_AON_GPIO_PORT(BB, 0x0800, 4, 0),
+	TEGRA194_AON_GPIO_PORT(CC, 0x0200, 8, 0),
+	TEGRA194_AON_GPIO_PORT(DD, 0x0400, 3, 0),
+	TEGRA194_AON_GPIO_PORT(EE, 0x0000, 7, 0)
+};
+
+static const struct tegra_gpio_soc tegra194_aon_soc = {
+	.num_ports = ARRAY_SIZE(tegra194_aon_ports),
+	.ports = tegra194_aon_ports,
+	.name = "tegra194-gpio-aon",
+};
+
 static const struct of_device_id tegra186_gpio_of_match[] = {
 	{
 		.compatible = "nvidia,tegra186-gpio",
@@ -601,6 +669,12 @@ static const struct of_device_id tegra186_gpio_of_match[] = {
 		.compatible = "nvidia,tegra186-gpio-aon",
 		.data = &tegra186_aon_soc
 	}, {
+		.compatible = "nvidia,tegra194-gpio",
+		.data = &tegra194_main_soc
+	}, {
+		.compatible = "nvidia,tegra194-gpio-aon",
+		.data = &tegra194_aon_soc
+	}, {
 		/* sentinel */
 	}
 };
diff --git a/drivers/gpio/gpio-timberdale.c b/drivers/gpio/gpio-timberdale.c
index 6520a8475910..314e300d6ba3 100644
--- a/drivers/gpio/gpio-timberdale.c
+++ b/drivers/gpio/gpio-timberdale.c
@@ -22,7 +22,7 @@
  */
 
 #include <linux/init.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/platform_device.h>
 #include <linux/irq.h>
 #include <linux/io.h>
diff --git a/drivers/gpio/gpio-uniphier.c b/drivers/gpio/gpio-uniphier.c
index 58faeb1cef63..7fdac9060979 100644
--- a/drivers/gpio/gpio-uniphier.c
+++ b/drivers/gpio/gpio-uniphier.c
@@ -310,8 +310,7 @@ static int uniphier_gpio_irq_domain_activate(struct irq_domain *domain,
 	struct uniphier_gpio_priv *priv = domain->host_data;
 	struct gpio_chip *chip = &priv->chip;
 
-	gpiochip_lock_as_irq(chip, data->hwirq + UNIPHIER_GPIO_IRQ_OFFSET);
-	return 0;
+	return gpiochip_lock_as_irq(chip, data->hwirq + UNIPHIER_GPIO_IRQ_OFFSET);
 }
 
 static void uniphier_gpio_irq_domain_deactivate(struct irq_domain *domain,
diff --git a/drivers/gpio/gpio-vr41xx.c b/drivers/gpio/gpio-vr41xx.c
index ac8deb01f6f6..027699cec911 100644
--- a/drivers/gpio/gpio-vr41xx.c
+++ b/drivers/gpio/gpio-vr41xx.c
@@ -138,10 +138,16 @@ static void unmask_giuint_low(struct irq_data *d)
 
 static unsigned int startup_giuint(struct irq_data *data)
 {
-	if (gpiochip_lock_as_irq(&vr41xx_gpio_chip, data->hwirq))
+	int ret;
+
+	ret = gpiochip_lock_as_irq(&vr41xx_gpio_chip, irqd_to_hwirq(data));
+	if (ret) {
 		dev_err(vr41xx_gpio_chip.parent,
 			"unable to lock HW IRQ %lu for IRQ\n",
 			data->hwirq);
+		return ret;
+	}
+
 	/* Satisfy the .enable semantics by unmasking the line */
 	unmask_giuint_low(data);
 	return 0;
diff --git a/drivers/gpio/gpio-xgene-sb.c b/drivers/gpio/gpio-xgene-sb.c
index acd59113e08b..2eb76f35aa7e 100644
--- a/drivers/gpio/gpio-xgene-sb.c
+++ b/drivers/gpio/gpio-xgene-sb.c
@@ -143,12 +143,14 @@ static int xgene_gpio_sb_domain_activate(struct irq_domain *d,
 {
 	struct xgene_gpio_sb *priv = d->host_data;
 	u32 gpio = HWIRQ_TO_GPIO(priv, irq_data->hwirq);
+	int ret;
 
-	if (gpiochip_lock_as_irq(&priv->gc, gpio)) {
+	ret = gpiochip_lock_as_irq(&priv->gc, gpio);
+	if (ret) {
 		dev_err(priv->gc.parent,
 		"Unable to configure XGene GPIO standby pin %d as IRQ\n",
 				gpio);
-		return -ENOSPC;
+		return ret;
 	}
 
 	xgene_gpio_set_bit(&priv->gc, priv->regs + MPA_GPIO_SEL_LO,
diff --git a/drivers/gpio/gpio-xilinx.c b/drivers/gpio/gpio-xilinx.c
index e8ec0e33a0a9..8f24478cc18b 100644
--- a/drivers/gpio/gpio-xilinx.c
+++ b/drivers/gpio/gpio-xilinx.c
@@ -20,7 +20,7 @@
 #include <linux/of_platform.h>
 #include <linux/of_gpio.h>
 #include <linux/io.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/slab.h>
 
 /* Register Offset Definitions */
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index addd9fecc198..c48ed9d89ff5 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -389,7 +389,7 @@ EXPORT_SYMBOL_GPL(devm_acpi_dev_remove_driver_gpios);
 
 static bool acpi_get_driver_gpio_data(struct acpi_device *adev,
 				      const char *name, int index,
-				      struct acpi_reference_args *args,
+				      struct fwnode_reference_args *args,
 				      unsigned int *quirks)
 {
 	const struct acpi_gpio_mapping *gm;
@@ -401,7 +401,7 @@ static bool acpi_get_driver_gpio_data(struct acpi_device *adev,
 		if (!strcmp(name, gm->name) && gm->data && index < gm->size) {
 			const struct acpi_gpio_params *par = gm->data + index;
 
-			args->adev = adev;
+			args->fwnode = acpi_fwnode_handle(adev);
 			args->args[0] = par->crs_entry_index;
 			args->args[1] = par->line_index;
 			args->args[2] = par->active_low;
@@ -564,7 +564,7 @@ static int acpi_gpio_property_lookup(struct fwnode_handle *fwnode,
 				     const char *propname, int index,
 				     struct acpi_gpio_lookup *lookup)
 {
-	struct acpi_reference_args args;
+	struct fwnode_reference_args args;
 	unsigned int quirks = 0;
 	int ret;
 
@@ -585,6 +585,8 @@ static int acpi_gpio_property_lookup(struct fwnode_handle *fwnode,
 	 * The property was found and resolved, so need to lookup the GPIO based
 	 * on returned args.
 	 */
+	if (!to_acpi_device_node(args.fwnode))
+		return -EINVAL;
 	if (args.nargs != 3)
 		return -EPROTO;
 
@@ -592,8 +594,9 @@ static int acpi_gpio_property_lookup(struct fwnode_handle *fwnode,
 	lookup->pin_index = args.args[1];
 	lookup->active_low = !!args.args[2];
 
-	lookup->info.adev = args.adev;
+	lookup->info.adev = to_acpi_device_node(args.fwnode);
 	lookup->info.quirks = quirks;
+
 	return 0;
 }
 
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 53a14ee8ad6d..a4f1157d6aa0 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -621,9 +621,6 @@ int of_gpiochip_add(struct gpio_chip *chip)
 {
 	int status;
 
-	if ((!chip->of_node) && (chip->parent))
-		chip->of_node = chip->parent->of_node;
-
 	if (!chip->of_node)
 		return 0;
 
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index e11a3bb03820..e8f8a1999393 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -431,7 +431,7 @@ static long linehandle_ioctl(struct file *filep, unsigned int cmd,
 	int i;
 
 	if (cmd == GPIOHANDLE_GET_LINE_VALUES_IOCTL) {
-		/* TODO: check if descriptors are really input */
+		/* NOTE: It's ok to read values of output lines. */
 		int ret = gpiod_get_array_value_complex(false,
 							true,
 							lh->numdescs,
@@ -449,7 +449,13 @@ static long linehandle_ioctl(struct file *filep, unsigned int cmd,
 
 		return 0;
 	} else if (cmd == GPIOHANDLE_SET_LINE_VALUES_IOCTL) {
-		/* TODO: check if descriptors are really output */
+		/*
+		 * All line descriptors were created at once with the same
+		 * flags so just check if the first one is really output.
+		 */
+		if (!test_bit(FLAG_IS_OUT, &lh->descs[0]->flags))
+			return -EPERM;
+
 		if (copy_from_user(&ghd, ip, sizeof(ghd)))
 			return -EFAULT;
 
@@ -1256,6 +1262,8 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,
 	/* If the gpiochip has an assigned OF node this takes precedence */
 	if (chip->of_node)
 		gdev->dev.of_node = chip->of_node;
+	else
+		chip->of_node = gdev->dev.of_node;
 #endif
 
 	gdev->id = ida_simple_get(&gpio_ida, 0, 0, GFP_KERNEL);
@@ -1408,9 +1416,9 @@ err_free_descs:
 err_free_gdev:
 	ida_simple_remove(&gpio_ida, gdev->id);
 	/* failures here can mean systems won't boot... */
-	pr_err("%s: GPIOs %d..%d (%s) failed to register\n", __func__,
+	pr_err("%s: GPIOs %d..%d (%s) failed to register, %d\n", __func__,
 	       gdev->base, gdev->base + gdev->ngpio - 1,
-	       chip->label ? : "generic");
+	       chip->label ? : "generic", status);
 	kfree(gdev);
 	return status;
 }
@@ -1664,8 +1672,7 @@ static void gpiochip_set_cascaded_irqchip(struct gpio_chip *gpiochip,
 	if (parent_handler) {
 		if (gpiochip->can_sleep) {
 			chip_err(gpiochip,
-				 "you cannot have chained interrupts on a "
-				 "chip that may sleep\n");
+				 "you cannot have chained interrupts on a chip that may sleep\n");
 			return;
 		}
 		/*
@@ -1800,16 +1807,18 @@ static const struct irq_domain_ops gpiochip_domain_ops = {
 static int gpiochip_irq_reqres(struct irq_data *d)
 {
 	struct gpio_chip *chip = irq_data_get_irq_chip_data(d);
+	int ret;
 
 	if (!try_module_get(chip->gpiodev->owner))
 		return -ENODEV;
 
-	if (gpiochip_lock_as_irq(chip, d->hwirq)) {
+	ret = gpiochip_lock_as_irq(chip, d->hwirq);
+	if (ret) {
 		chip_err(chip,
 			"unable to lock HW IRQ %lu for IRQ\n",
 			d->hwirq);
 		module_put(chip->gpiodev->owner);
-		return -EINVAL;
+		return ret;
 	}
 	return 0;
 }
@@ -1850,8 +1859,7 @@ static int gpiochip_add_irqchip(struct gpio_chip *gpiochip,
 		return 0;
 
 	if (gpiochip->irq.parent_handler && gpiochip->can_sleep) {
-		chip_err(gpiochip, "you cannot have chained interrupts on a "
-			 "chip that may sleep\n");
+		chip_err(gpiochip, "you cannot have chained interrupts on a chip that may sleep\n");
 		return -EINVAL;
 	}
 
@@ -2259,6 +2267,7 @@ static int gpiod_request_commit(struct gpio_desc *desc, const char *label)
 	struct gpio_chip	*chip = desc->gdev->chip;
 	int			status;
 	unsigned long		flags;
+	unsigned		offset;
 
 	spin_lock_irqsave(&gpio_lock, flags);
 
@@ -2277,7 +2286,11 @@ static int gpiod_request_commit(struct gpio_desc *desc, const char *label)
 	if (chip->request) {
 		/* chip->request may sleep */
 		spin_unlock_irqrestore(&gpio_lock, flags);
-		status = chip->request(chip, gpio_chip_hwgpio(desc));
+		offset = gpio_chip_hwgpio(desc);
+		if (gpiochip_line_is_valid(chip, offset))
+			status = chip->request(chip, offset);
+		else
+			status = -EINVAL;
 		spin_lock_irqsave(&gpio_lock, flags);
 
 		if (status < 0) {
@@ -3194,6 +3207,19 @@ int gpiod_cansleep(const struct gpio_desc *desc)
 EXPORT_SYMBOL_GPL(gpiod_cansleep);
 
 /**
+ * gpiod_set_consumer_name() - set the consumer name for the descriptor
+ * @desc: gpio to set the consumer name on
+ * @name: the new consumer name
+ */
+void gpiod_set_consumer_name(struct gpio_desc *desc, const char *name)
+{
+	VALIDATE_DESC_VOID(desc);
+	/* Just overwrite whatever the previous name was */
+	desc->label = name;
+}
+EXPORT_SYMBOL_GPL(gpiod_set_consumer_name);
+
+/**
  * gpiod_to_irq() - return the IRQ corresponding to a GPIO
  * @desc: gpio whose IRQ will be returned (already requested)
  *
@@ -3249,18 +3275,19 @@ int gpiochip_lock_as_irq(struct gpio_chip *chip, unsigned int offset)
 	 * behind our back
 	 */
 	if (!chip->can_sleep && chip->get_direction) {
-		int dir = chip->get_direction(chip, offset);
+		int dir = gpiod_get_direction(desc);
 
-		if (dir)
-			clear_bit(FLAG_IS_OUT, &desc->flags);
-		else
-			set_bit(FLAG_IS_OUT, &desc->flags);
+		if (dir < 0) {
+			chip_err(chip, "%s: cannot get GPIO direction\n",
+				 __func__);
+			return dir;
+		}
 	}
 
 	if (test_bit(FLAG_IS_OUT, &desc->flags)) {
 		chip_err(chip,
-			  "%s: tried to flag a GPIO set as output for IRQ\n",
-			  __func__);
+			 "%s: tried to flag a GPIO set as output for IRQ\n",
+			 __func__);
 		return -EIO;
 	}
 
@@ -3639,9 +3666,16 @@ static struct gpio_desc *gpiod_find(struct device *dev, const char *con_id,
 		chip = find_chip_by_name(p->chip_label);
 
 		if (!chip) {
-			dev_err(dev, "cannot find GPIO chip %s\n",
-				p->chip_label);
-			return ERR_PTR(-ENODEV);
+			/*
+			 * As the lookup table indicates a chip with
+			 * p->chip_label should exist, assume it may
+			 * still appear later and let the interested
+			 * consumer be probed again or let the Deferred
+			 * Probe infrastructure handle the error.
+			 */
+			dev_warn(dev, "cannot find GPIO chip %s, deferring\n",
+				 p->chip_label);
+			return ERR_PTR(-EPROBE_DEFER);
 		}
 
 		if (chip->ngpio <= p->chip_hwnum) {
@@ -4215,7 +4249,7 @@ static int __init gpiolib_dev_init(void)
 	int ret;
 
 	/* Register GPIO sysfs bus */
-	ret  = bus_register(&gpio_bus_type);
+	ret = bus_register(&gpio_bus_type);
 	if (ret < 0) {
 		pr_err("gpiolib: could not register GPIO bus type\n");
 		return ret;
@@ -4259,9 +4293,7 @@ static void gpiolib_dbg_show(struct seq_file *s, struct gpio_device *gdev)
 		seq_printf(s, " gpio-%-3d (%-20.20s|%-20.20s) %s %s %s",
 			gpio, gdesc->name ? gdesc->name : "", gdesc->label,
 			is_out ? "out" : "in ",
-			chip->get
-				? (chip->get(chip, i) ? "hi" : "lo")
-				: "?  ",
+			chip->get ? (chip->get(chip, i) ? "hi" : "lo") : "?  ",
 			is_irq ? "IRQ" : "   ");
 		seq_printf(s, "\n");
 	}
diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h
index 1a8e20363861..a7e49fef73d4 100644
--- a/drivers/gpio/gpiolib.h
+++ b/drivers/gpio/gpiolib.h
@@ -92,7 +92,7 @@ struct acpi_gpio_info {
 };
 
 /* gpio suffixes used for ACPI and device tree lookup */
-static const char * const gpio_suffixes[] = { "gpios", "gpio" };
+static __maybe_unused const char * const gpio_suffixes[] = { "gpios", "gpio" };
 
 #ifdef CONFIG_OF_GPIO
 struct gpio_desc *of_find_gpio(struct device *dev,
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 2a72d2feb76d..cb88528e7b10 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -122,6 +122,16 @@ config DRM_LOAD_EDID_FIRMWARE
 	  default case is N. Details and instructions how to build your own
 	  EDID data are given in Documentation/EDID/HOWTO.txt.
 
+config DRM_DP_CEC
+	bool "Enable DisplayPort CEC-Tunneling-over-AUX HDMI support"
+	select CEC_CORE
+	help
+	  Choose this option if you want to enable HDMI CEC support for
+	  DisplayPort/USB-C to HDMI adapters.
+
+	  Note: not all adapters support this feature, and even for those
+	  that do support this they often do not hook up the CEC pin.
+
 config DRM_TTM
 	tristate
 	depends on DRM && MMU
@@ -213,6 +223,17 @@ config DRM_VGEM
 	  as used by Mesa's software renderer for enhanced performance.
 	  If M is selected the module will be called vgem.
 
+config DRM_VKMS
+	tristate "Virtual KMS (EXPERIMENTAL)"
+	depends on DRM
+	select DRM_KMS_HELPER
+	default n
+	help
+	  Virtual Kernel Mode-Setting (VKMS) is used for testing or for
+	  running GPU in a headless machines. Choose this option to get
+	  a VKMS.
+
+	  If M is selected the module will be called vkms.
 
 source "drivers/gpu/drm/exynos/Kconfig"
 
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index ef9f3dab287f..a6771cef85e2 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -18,7 +18,7 @@ drm-y       :=	drm_auth.o drm_bufs.o drm_cache.o \
 		drm_encoder.o drm_mode_object.o drm_property.o \
 		drm_plane.o drm_color_mgmt.o drm_print.o \
 		drm_dumb_buffers.o drm_mode_config.o drm_vblank.o \
-		drm_syncobj.o drm_lease.o
+		drm_syncobj.o drm_lease.o drm_writeback.o drm_client.o
 
 drm-$(CONFIG_DRM_LIB_RANDOM) += lib/drm_random.o
 drm-$(CONFIG_DRM_VM) += drm_vm.o
@@ -41,6 +41,7 @@ drm_kms_helper-$(CONFIG_DRM_PANEL_BRIDGE) += bridge/panel.o
 drm_kms_helper-$(CONFIG_DRM_FBDEV_EMULATION) += drm_fb_helper.o
 drm_kms_helper-$(CONFIG_DRM_KMS_CMA_HELPER) += drm_fb_cma_helper.o
 drm_kms_helper-$(CONFIG_DRM_DP_AUX_CHARDEV) += drm_dp_aux_dev.o
+drm_kms_helper-$(CONFIG_DRM_DP_CEC) += drm_dp_cec.o
 
 obj-$(CONFIG_DRM_KMS_HELPER) += drm_kms_helper.o
 obj-$(CONFIG_DRM_DEBUG_SELFTEST) += selftests/
@@ -69,6 +70,7 @@ obj-$(CONFIG_DRM_SAVAGE)+= savage/
 obj-$(CONFIG_DRM_VMWGFX)+= vmwgfx/
 obj-$(CONFIG_DRM_VIA)	+=via/
 obj-$(CONFIG_DRM_VGEM)	+= vgem/
+obj-$(CONFIG_DRM_VKMS)	+= vkms/
 obj-$(CONFIG_DRM_NOUVEAU) +=nouveau/
 obj-$(CONFIG_DRM_EXYNOS) +=exynos/
 obj-$(CONFIG_DRM_ROCKCHIP) +=rockchip/
diff --git a/drivers/gpu/drm/amd/amdgpu/ObjectID.h b/drivers/gpu/drm/amd/amdgpu/ObjectID.h
index 06192698bd96..5b393622f592 100644
--- a/drivers/gpu/drm/amd/amdgpu/ObjectID.h
+++ b/drivers/gpu/drm/amd/amdgpu/ObjectID.h
@@ -136,6 +136,7 @@
 #define GENERIC_OBJECT_ID_PX2_NON_DRIVABLE        0x02
 #define GENERIC_OBJECT_ID_MXM_OPM                 0x03
 #define GENERIC_OBJECT_ID_STEREO_PIN              0x04        //This object could show up from Misc Object table, it follows ATOM_OBJECT format, and contains one ATOM_OBJECT_GPIO_CNTL_RECORD for the stereo pin
+#define GENERIC_OBJECT_ID_BRACKET_LAYOUT          0x05
 
 /****************************************************/
 /* Graphics Object ENUM ID Definition               */
@@ -714,6 +715,13 @@
                                                  GRAPH_OBJECT_ENUM_ID1 << ENUM_ID_SHIFT |\
                                                  GENERIC_OBJECT_ID_STEREO_PIN << OBJECT_ID_SHIFT)
 
+#define GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID1    (GRAPH_OBJECT_TYPE_GENERIC << OBJECT_TYPE_SHIFT |\
+                                                 GRAPH_OBJECT_ENUM_ID1 << ENUM_ID_SHIFT |\
+                                                 GENERIC_OBJECT_ID_BRACKET_LAYOUT << OBJECT_ID_SHIFT)
+
+#define GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID2    (GRAPH_OBJECT_TYPE_GENERIC << OBJECT_TYPE_SHIFT |\
+                                                 GRAPH_OBJECT_ENUM_ID2 << ENUM_ID_SHIFT |\
+                                                 GENERIC_OBJECT_ID_BRACKET_LAYOUT << OBJECT_ID_SHIFT)
 /****************************************************/
 /* Object Cap definition - Shared with BIOS         */
 /****************************************************/
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 7dcbac8af9a7..447c4c7a36d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -73,6 +73,8 @@
 #include "amdgpu_virt.h"
 #include "amdgpu_gart.h"
 #include "amdgpu_debugfs.h"
+#include "amdgpu_job.h"
+#include "amdgpu_bo_list.h"
 
 /*
  * Modules parameters.
@@ -105,11 +107,8 @@ extern int amdgpu_vm_fault_stop;
 extern int amdgpu_vm_debug;
 extern int amdgpu_vm_update_mode;
 extern int amdgpu_dc;
-extern int amdgpu_dc_log;
 extern int amdgpu_sched_jobs;
 extern int amdgpu_sched_hw_submission;
-extern int amdgpu_no_evict;
-extern int amdgpu_direct_gma_size;
 extern uint amdgpu_pcie_gen_cap;
 extern uint amdgpu_pcie_lane_cap;
 extern uint amdgpu_cg_mask;
@@ -600,17 +599,6 @@ struct amdgpu_ib {
 
 extern const struct drm_sched_backend_ops amdgpu_sched_ops;
 
-int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
-		     struct amdgpu_job **job, struct amdgpu_vm *vm);
-int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size,
-			     struct amdgpu_job **job);
-
-void amdgpu_job_free_resources(struct amdgpu_job *job);
-void amdgpu_job_free(struct amdgpu_job *job);
-int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
-		      struct drm_sched_entity *entity, void *owner,
-		      struct dma_fence **f);
-
 /*
  * Queue manager
  */
@@ -684,8 +672,8 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 int amdgpu_ctx_wait_prev_fence(struct amdgpu_ctx *ctx, unsigned ring_id);
 
 void amdgpu_ctx_mgr_init(struct amdgpu_ctx_mgr *mgr);
-void amdgpu_ctx_mgr_entity_cleanup(struct amdgpu_ctx_mgr *mgr);
 void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr);
+void amdgpu_ctx_mgr_entity_flush(struct amdgpu_ctx_mgr *mgr);
 void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr);
 
 
@@ -703,37 +691,6 @@ struct amdgpu_fpriv {
 };
 
 /*
- * residency list
- */
-struct amdgpu_bo_list_entry {
-	struct amdgpu_bo		*robj;
-	struct ttm_validate_buffer	tv;
-	struct amdgpu_bo_va		*bo_va;
-	uint32_t			priority;
-	struct page			**user_pages;
-	int				user_invalidated;
-};
-
-struct amdgpu_bo_list {
-	struct mutex lock;
-	struct rcu_head rhead;
-	struct kref refcount;
-	struct amdgpu_bo *gds_obj;
-	struct amdgpu_bo *gws_obj;
-	struct amdgpu_bo *oa_obj;
-	unsigned first_userptr;
-	unsigned num_entries;
-	struct amdgpu_bo_list_entry *array;
-};
-
-struct amdgpu_bo_list *
-amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id);
-void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
-			     struct list_head *validated);
-void amdgpu_bo_list_put(struct amdgpu_bo_list *list);
-void amdgpu_bo_list_free(struct amdgpu_bo_list *list);
-
-/*
  * GFX stuff
  */
 #include "clearstate_defs.h"
@@ -931,6 +888,11 @@ struct amdgpu_ngg {
 	bool			init;
 };
 
+struct sq_work {
+	struct work_struct	work;
+	unsigned ih_data;
+};
+
 struct amdgpu_gfx {
 	struct mutex			gpu_clock_mutex;
 	struct amdgpu_gfx_config	config;
@@ -969,6 +931,10 @@ struct amdgpu_gfx {
 	struct amdgpu_irq_src		eop_irq;
 	struct amdgpu_irq_src		priv_reg_irq;
 	struct amdgpu_irq_src		priv_inst_irq;
+	struct amdgpu_irq_src		cp_ecc_error_irq;
+	struct amdgpu_irq_src		sq_irq;
+	struct sq_work			sq_work;
+
 	/* gfx status */
 	uint32_t			gfx_current_status;
 	/* ce ram size*/
@@ -1020,6 +986,7 @@ struct amdgpu_cs_parser {
 
 	/* scheduler job object */
 	struct amdgpu_job	*job;
+	struct amdgpu_ring	*ring;
 
 	/* buffer objects */
 	struct ww_acquire_ctx		ticket;
@@ -1041,40 +1008,6 @@ struct amdgpu_cs_parser {
 	struct drm_syncobj **post_dep_syncobjs;
 };
 
-#define AMDGPU_PREAMBLE_IB_PRESENT          (1 << 0) /* bit set means command submit involves a preamble IB */
-#define AMDGPU_PREAMBLE_IB_PRESENT_FIRST    (1 << 1) /* bit set means preamble IB is first presented in belonging context */
-#define AMDGPU_HAVE_CTX_SWITCH              (1 << 2) /* bit set means context switch occured */
-
-struct amdgpu_job {
-	struct drm_sched_job    base;
-	struct amdgpu_device	*adev;
-	struct amdgpu_vm	*vm;
-	struct amdgpu_ring	*ring;
-	struct amdgpu_sync	sync;
-	struct amdgpu_sync	sched_sync;
-	struct amdgpu_ib	*ibs;
-	struct dma_fence	*fence; /* the hw fence */
-	uint32_t		preamble_status;
-	uint32_t		num_ibs;
-	void			*owner;
-	uint64_t		fence_ctx; /* the fence_context this job uses */
-	bool                    vm_needs_flush;
-	uint64_t		vm_pd_addr;
-	unsigned		vmid;
-	unsigned		pasid;
-	uint32_t		gds_base, gds_size;
-	uint32_t		gws_base, gws_size;
-	uint32_t		oa_base, oa_size;
-	uint32_t		vram_lost_counter;
-
-	/* user fence handling */
-	uint64_t		uf_addr;
-	uint64_t		uf_sequence;
-
-};
-#define to_amdgpu_job(sched_job)		\
-		container_of((sched_job), struct amdgpu_job, base)
-
 static inline u32 amdgpu_get_ib_value(struct amdgpu_cs_parser *p,
 				      uint32_t ib_idx, int idx)
 {
@@ -1389,6 +1322,7 @@ enum amd_hw_ip_block_type {
 	PWR_HWIP,
 	NBIF_HWIP,
 	THM_HWIP,
+	CLK_HWIP,
 	MAX_HWIP
 };
 
@@ -1579,9 +1513,9 @@ struct amdgpu_device {
 	DECLARE_HASHTABLE(mn_hash, 7);
 
 	/* tracking pinned memory */
-	u64 vram_pin_size;
-	u64 invisible_pin_size;
-	u64 gart_pin_size;
+	atomic64_t vram_pin_size;
+	atomic64_t visible_pin_size;
+	atomic64_t gart_pin_size;
 
 	/* amdkfd interface */
 	struct kfd_dev          *kfd;
@@ -1776,6 +1710,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_vm_write_pte(adev, ib, pe, value, count, incr) ((adev)->vm_manager.vm_pte_funcs->write_pte((ib), (pe), (value), (count), (incr)))
 #define amdgpu_vm_set_pte_pde(adev, ib, pe, addr, count, incr, flags) ((adev)->vm_manager.vm_pte_funcs->set_pte_pde((ib), (pe), (addr), (count), (incr), (flags)))
 #define amdgpu_ring_parse_cs(r, p, ib) ((r)->funcs->parse_cs((p), (ib)))
+#define amdgpu_ring_patch_cs_in_place(r, p, ib) ((r)->funcs->patch_cs_in_place((p), (ib)))
 #define amdgpu_ring_test_ring(r) (r)->funcs->test_ring((r))
 #define amdgpu_ring_test_ib(r, t) (r)->funcs->test_ib((r), (t))
 #define amdgpu_ring_get_rptr(r) (r)->funcs->get_rptr((r))
@@ -1829,8 +1764,6 @@ void amdgpu_display_update_priority(struct amdgpu_device *adev);
 
 void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev, u64 num_bytes,
 				  u64 num_vis_bytes);
-void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain);
-bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo);
 void amdgpu_device_vram_location(struct amdgpu_device *adev,
 				 struct amdgpu_gmc *mc, u64 base);
 void amdgpu_device_gart_location(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 0d8c3fc6eace..353993218f21 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -364,7 +364,6 @@ static int amdgpu_atif_handler(struct amdgpu_device *adev,
 			       struct acpi_bus_event *event)
 {
 	struct amdgpu_atif *atif = adev->atif;
-	struct atif_sbios_requests req;
 	int count;
 
 	DRM_DEBUG_DRIVER("event, device_class = %s, type = %#x\n",
@@ -379,42 +378,48 @@ static int amdgpu_atif_handler(struct amdgpu_device *adev,
 		/* Not our event */
 		return NOTIFY_DONE;
 
-	/* Check pending SBIOS requests */
-	count = amdgpu_atif_get_sbios_requests(atif, &req);
+	if (atif->functions.sbios_requests) {
+		struct atif_sbios_requests req;
 
-	if (count <= 0)
-		return NOTIFY_DONE;
+		/* Check pending SBIOS requests */
+		count = amdgpu_atif_get_sbios_requests(atif, &req);
+
+		if (count <= 0)
+			return NOTIFY_DONE;
 
-	DRM_DEBUG_DRIVER("ATIF: %d pending SBIOS requests\n", count);
+		DRM_DEBUG_DRIVER("ATIF: %d pending SBIOS requests\n", count);
 
-	if (req.pending & ATIF_PANEL_BRIGHTNESS_CHANGE_REQUEST) {
-		struct amdgpu_encoder *enc = atif->encoder_for_bl;
+		/* todo: add DC handling */
+		if ((req.pending & ATIF_PANEL_BRIGHTNESS_CHANGE_REQUEST) &&
+		    !amdgpu_device_has_dc_support(adev)) {
+			struct amdgpu_encoder *enc = atif->encoder_for_bl;
 
-		if (enc) {
-			struct amdgpu_encoder_atom_dig *dig = enc->enc_priv;
+			if (enc) {
+				struct amdgpu_encoder_atom_dig *dig = enc->enc_priv;
 
-			DRM_DEBUG_DRIVER("Changing brightness to %d\n",
-					req.backlight_level);
+				DRM_DEBUG_DRIVER("Changing brightness to %d\n",
+						 req.backlight_level);
 
-			amdgpu_display_backlight_set_level(adev, enc, req.backlight_level);
+				amdgpu_display_backlight_set_level(adev, enc, req.backlight_level);
 
 #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) || defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE)
-			backlight_force_update(dig->bl_dev,
-					       BACKLIGHT_UPDATE_HOTKEY);
+				backlight_force_update(dig->bl_dev,
+						       BACKLIGHT_UPDATE_HOTKEY);
 #endif
+			}
 		}
-	}
-	if (req.pending & ATIF_DGPU_DISPLAY_EVENT) {
-		if ((adev->flags & AMD_IS_PX) &&
-		    amdgpu_atpx_dgpu_req_power_for_displays()) {
-			pm_runtime_get_sync(adev->ddev->dev);
-			/* Just fire off a uevent and let userspace tell us what to do */
-			drm_helper_hpd_irq_event(adev->ddev);
-			pm_runtime_mark_last_busy(adev->ddev->dev);
-			pm_runtime_put_autosuspend(adev->ddev->dev);
+		if (req.pending & ATIF_DGPU_DISPLAY_EVENT) {
+			if ((adev->flags & AMD_IS_PX) &&
+			    amdgpu_atpx_dgpu_req_power_for_displays()) {
+				pm_runtime_get_sync(adev->ddev->dev);
+				/* Just fire off a uevent and let userspace tell us what to do */
+				drm_helper_hpd_irq_event(adev->ddev);
+				pm_runtime_mark_last_busy(adev->ddev->dev);
+				pm_runtime_put_autosuspend(adev->ddev->dev);
+			}
 		}
+		/* TODO: check other events */
 	}
-	/* TODO: check other events */
 
 	/* We've handled the event, stop the notifier chain. The ACPI interface
 	 * overloads ACPI_VIDEO_NOTIFY_PROBE, we don't want to send that to
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 305143fcc1ce..f8bbbb3a9504 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -243,6 +243,33 @@ int amdgpu_amdkfd_resume(struct amdgpu_device *adev)
 	return r;
 }
 
+int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (adev->kfd)
+		r = kgd2kfd->pre_reset(adev->kfd);
+
+	return r;
+}
+
+int amdgpu_amdkfd_post_reset(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (adev->kfd)
+		r = kgd2kfd->post_reset(adev->kfd);
+
+	return r;
+}
+
+void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+
+	amdgpu_device_gpu_recover(adev, NULL, false);
+}
+
 int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 			void **mem_obj, uint64_t *gpu_addr,
 			void **cpu_ptr)
@@ -251,7 +278,6 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 	struct amdgpu_bo *bo = NULL;
 	struct amdgpu_bo_param bp;
 	int r;
-	uint64_t gpu_addr_tmp = 0;
 	void *cpu_ptr_tmp = NULL;
 
 	memset(&bp, 0, sizeof(bp));
@@ -275,13 +301,18 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 		goto allocate_mem_reserve_bo_failed;
 	}
 
-	r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT,
-				&gpu_addr_tmp);
+	r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
 	if (r) {
 		dev_err(adev->dev, "(%d) failed to pin bo for amdkfd\n", r);
 		goto allocate_mem_pin_bo_failed;
 	}
 
+	r = amdgpu_ttm_alloc_gart(&bo->tbo);
+	if (r) {
+		dev_err(adev->dev, "%p bind failed\n", bo);
+		goto allocate_mem_kmap_bo_failed;
+	}
+
 	r = amdgpu_bo_kmap(bo, &cpu_ptr_tmp);
 	if (r) {
 		dev_err(adev->dev,
@@ -290,7 +321,7 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 	}
 
 	*mem_obj = bo;
-	*gpu_addr = gpu_addr_tmp;
+	*gpu_addr = amdgpu_bo_gpu_offset(bo);
 	*cpu_ptr = cpu_ptr_tmp;
 
 	amdgpu_bo_unreserve(bo);
@@ -457,6 +488,14 @@ err:
 	return ret;
 }
 
+void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+
+	amdgpu_dpm_switch_power_profile(adev,
+					PP_SMC_POWER_PROFILE_COMPUTE, !idle);
+}
+
 bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid)
 {
 	if (adev->kfd) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index a8418a3f4e9d..2f379c183ed2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -119,6 +119,7 @@ int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem, struct mm_struct *mm);
 int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
 				uint32_t vmid, uint64_t gpu_addr,
 				uint32_t *ib_cmd, uint32_t ib_len);
+void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle);
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void);
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void);
@@ -126,6 +127,12 @@ struct kfd2kgd_calls *amdgpu_amdkfd_gfx_9_0_get_functions(void);
 
 bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid);
 
+int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev);
+
+int amdgpu_amdkfd_post_reset(struct amdgpu_device *adev);
+
+void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd);
+
 /* Shared API */
 int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 			void **mem_obj, uint64_t *gpu_addr,
@@ -183,6 +190,9 @@ int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_dev *kgd,
 int amdgpu_amdkfd_gpuvm_restore_process_bos(void *process_info,
 					    struct dma_fence **ef);
 
+int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd,
+					      struct kfd_vm_fault_info *info);
+
 void amdgpu_amdkfd_gpuvm_init_mem_limits(void);
 void amdgpu_amdkfd_unreserve_system_memory_limit(struct amdgpu_bo *bo);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c
index 2c14025e5e76..574c1181ae9a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c
@@ -173,7 +173,5 @@ static const struct dma_fence_ops amdkfd_fence_ops = {
 	.get_driver_name = amdkfd_fence_get_driver_name,
 	.get_timeline_name = amdkfd_fence_get_timeline_name,
 	.enable_signaling = amdkfd_fence_enable_signaling,
-	.signaled = NULL,
-	.wait = dma_fence_default_wait,
 	.release = amdkfd_fence_release,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index ea79908dac4c..ea3f698aef5e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -145,6 +145,7 @@ static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
 		uint32_t page_table_base);
 static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid);
 static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid);
+static uint32_t read_vmid_from_vmfault_reg(struct kgd_dev *kgd);
 
 /* Because of REG_GET_FIELD() being used, we put this function in the
  * asic specific file.
@@ -216,6 +217,10 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.invalidate_tlbs = invalidate_tlbs,
 	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.submit_ib = amdgpu_amdkfd_submit_ib,
+	.get_vm_fault_info = amdgpu_amdkfd_gpuvm_get_vm_fault_info,
+	.read_vmid_from_vmfault_reg = read_vmid_from_vmfault_reg,
+	.gpu_recover = amdgpu_amdkfd_gpu_reset,
+	.set_compute_idle = amdgpu_amdkfd_set_compute_idle
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void)
@@ -571,6 +576,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	unsigned long flags, end_jiffies;
 	int retry;
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	acquire_queue(kgd, pipe_id, queue_id);
 	WREG32(mmCP_HQD_PQ_DOORBELL_CONTROL, 0);
 
@@ -882,6 +890,9 @@ static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
 	int vmid;
 	unsigned int tmp;
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	for (vmid = 0; vmid < 16; vmid++) {
 		if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid))
 			continue;
@@ -911,3 +922,19 @@ static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid)
 	RREG32(mmVM_INVALIDATE_RESPONSE);
 	return 0;
 }
+
+ /**
+  * read_vmid_from_vmfault_reg - read vmid from register
+  *
+  * adev: amdgpu_device pointer
+  * @vmid: vmid pointer
+  * read vmid from register (CIK).
+  */
+static uint32_t read_vmid_from_vmfault_reg(struct kgd_dev *kgd)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+
+	uint32_t status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS);
+
+	return REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS, VMID);
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index 19dd665e7307..f6e53e9352bd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -176,6 +176,9 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.invalidate_tlbs = invalidate_tlbs,
 	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.submit_ib = amdgpu_amdkfd_submit_ib,
+	.get_vm_fault_info = amdgpu_amdkfd_gpuvm_get_vm_fault_info,
+	.gpu_recover = amdgpu_amdkfd_gpu_reset,
+	.set_compute_idle = amdgpu_amdkfd_set_compute_idle
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void)
@@ -568,6 +571,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	int retry;
 	struct vi_mqd *m = get_mqd(mqd);
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	acquire_queue(kgd, pipe_id, queue_id);
 
 	if (m->cp_hqd_vmid == 0)
@@ -844,6 +850,9 @@ static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
 	int vmid;
 	unsigned int tmp;
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	for (vmid = 0; vmid < 16; vmid++) {
 		if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid))
 			continue;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index 1db60aa5b7f0..8efedfcb9dfc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -213,6 +213,8 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.invalidate_tlbs = invalidate_tlbs,
 	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.submit_ib = amdgpu_amdkfd_submit_ib,
+	.gpu_recover = amdgpu_amdkfd_gpu_reset,
+	.set_compute_idle = amdgpu_amdkfd_set_compute_idle
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_9_0_get_functions(void)
@@ -679,6 +681,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	uint32_t temp;
 	struct v9_mqd *m = get_mqd(mqd);
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	acquire_queue(kgd, pipe_id, queue_id);
 
 	if (m->cp_hqd_vmid == 0)
@@ -866,6 +871,9 @@ static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
 	int vmid;
 	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	if (ring->ready)
 		return invalidate_tlbs_with_kiq(adev, pasid);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index ff8fd75f7ca5..8a707d8bbb1c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -334,7 +334,7 @@ static int amdgpu_amdkfd_bo_validate(struct amdgpu_bo *bo, uint32_t domain,
 		 "Called with userptr BO"))
 		return -EINVAL;
 
-	amdgpu_ttm_placement_from_domain(bo, domain);
+	amdgpu_bo_placement_from_domain(bo, domain);
 
 	ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	if (ret)
@@ -622,7 +622,7 @@ static int init_user_pages(struct kgd_mem *mem, struct mm_struct *mm,
 		pr_err("%s: Failed to reserve BO\n", __func__);
 		goto release_out;
 	}
-	amdgpu_ttm_placement_from_domain(bo, mem->domain);
+	amdgpu_bo_placement_from_domain(bo, mem->domain);
 	ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	if (ret)
 		pr_err("%s: failed to validate BO\n", __func__);
@@ -1587,7 +1587,7 @@ int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_dev *kgd,
 		goto bo_reserve_failed;
 	}
 
-	ret = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT, NULL);
+	ret = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
 	if (ret) {
 		pr_err("Failed to pin bo. ret %d\n", ret);
 		goto pin_failed;
@@ -1621,6 +1621,20 @@ bo_reserve_failed:
 	return ret;
 }
 
+int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd,
+					      struct kfd_vm_fault_info *mem)
+{
+	struct amdgpu_device *adev;
+
+	adev = (struct amdgpu_device *)kgd;
+	if (atomic_read(&adev->gmc.vm_fault_info_updated) == 1) {
+		*mem = *adev->gmc.vm_fault_info;
+		mb();
+		atomic_set(&adev->gmc.vm_fault_info_updated, 0);
+	}
+	return 0;
+}
+
 /* Evict a userptr BO by stopping the queues if necessary
  *
  * Runs in MMU notifier, may be in RECLAIM_FS context. This means it
@@ -1680,7 +1694,7 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
 
 		if (amdgpu_bo_reserve(bo, true))
 			return -EAGAIN;
-		amdgpu_ttm_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_CPU);
+		amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_CPU);
 		ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		amdgpu_bo_unreserve(bo);
 		if (ret) {
@@ -1824,7 +1838,7 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info)
 		if (mem->user_pages[0]) {
 			amdgpu_ttm_tt_set_user_pages(bo->tbo.ttm,
 						     mem->user_pages);
-			amdgpu_ttm_placement_from_domain(bo, mem->domain);
+			amdgpu_bo_placement_from_domain(bo, mem->domain);
 			ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 			if (ret) {
 				pr_err("%s: failed to validate BO\n", __func__);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
index ca8bf1c9a98e..a028661d9e20 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
@@ -32,7 +32,7 @@ struct amdgpu_atpx_functions {
 	bool switch_start;
 	bool switch_end;
 	bool disp_connectors_mapping;
-	bool disp_detetion_ports;
+	bool disp_detection_ports;
 };
 
 struct amdgpu_atpx {
@@ -162,7 +162,7 @@ static void amdgpu_atpx_parse_functions(struct amdgpu_atpx_functions *f, u32 mas
 	f->switch_start = mask & ATPX_GRAPHICS_DEVICE_SWITCH_START_NOTIFICATION_SUPPORTED;
 	f->switch_end = mask & ATPX_GRAPHICS_DEVICE_SWITCH_END_NOTIFICATION_SUPPORTED;
 	f->disp_connectors_mapping = mask & ATPX_GET_DISPLAY_CONNECTORS_MAPPING_SUPPORTED;
-	f->disp_detetion_ports = mask & ATPX_GET_DISPLAY_DETECTION_PORTS_SUPPORTED;
+	f->disp_detection_ports = mask & ATPX_GET_DISPLAY_DETECTION_PORTS_SUPPORTED;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
index 19cfff31f2e1..3079ea8523c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
@@ -95,11 +95,17 @@ static void amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size,
 	r = amdgpu_bo_reserve(sobj, false);
 	if (unlikely(r != 0))
 		goto out_cleanup;
-	r = amdgpu_bo_pin(sobj, sdomain, &saddr);
+	r = amdgpu_bo_pin(sobj, sdomain);
+	if (r) {
+		amdgpu_bo_unreserve(sobj);
+		goto out_cleanup;
+	}
+	r = amdgpu_ttm_alloc_gart(&sobj->tbo);
 	amdgpu_bo_unreserve(sobj);
 	if (r) {
 		goto out_cleanup;
 	}
+	saddr = amdgpu_bo_gpu_offset(sobj);
 	bp.domain = ddomain;
 	r = amdgpu_bo_create(adev, &bp, &dobj);
 	if (r) {
@@ -108,11 +114,17 @@ static void amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size,
 	r = amdgpu_bo_reserve(dobj, false);
 	if (unlikely(r != 0))
 		goto out_cleanup;
-	r = amdgpu_bo_pin(dobj, ddomain, &daddr);
+	r = amdgpu_bo_pin(dobj, ddomain);
+	if (r) {
+		amdgpu_bo_unreserve(sobj);
+		goto out_cleanup;
+	}
+	r = amdgpu_ttm_alloc_gart(&dobj->tbo);
 	amdgpu_bo_unreserve(dobj);
 	if (r) {
 		goto out_cleanup;
 	}
+	daddr = amdgpu_bo_gpu_offset(dobj);
 
 	if (adev->mman.buffer_funcs) {
 		time = amdgpu_benchmark_do_move(adev, size, saddr, daddr, n);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 92be7f6de197..d472a2c8399f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -35,92 +35,53 @@
 #define AMDGPU_BO_LIST_MAX_PRIORITY	32u
 #define AMDGPU_BO_LIST_NUM_BUCKETS	(AMDGPU_BO_LIST_MAX_PRIORITY + 1)
 
-static int amdgpu_bo_list_set(struct amdgpu_device *adev,
-				     struct drm_file *filp,
-				     struct amdgpu_bo_list *list,
-				     struct drm_amdgpu_bo_list_entry *info,
-				     unsigned num_entries);
+static void amdgpu_bo_list_free_rcu(struct rcu_head *rcu)
+{
+	struct amdgpu_bo_list *list = container_of(rcu, struct amdgpu_bo_list,
+						   rhead);
+
+	kvfree(list);
+}
 
-static void amdgpu_bo_list_release_rcu(struct kref *ref)
+static void amdgpu_bo_list_free(struct kref *ref)
 {
-	unsigned i;
 	struct amdgpu_bo_list *list = container_of(ref, struct amdgpu_bo_list,
 						   refcount);
+	struct amdgpu_bo_list_entry *e;
 
-	for (i = 0; i < list->num_entries; ++i)
-		amdgpu_bo_unref(&list->array[i].robj);
+	amdgpu_bo_list_for_each_entry(e, list)
+		amdgpu_bo_unref(&e->robj);
 
-	mutex_destroy(&list->lock);
-	kvfree(list->array);
-	kfree_rcu(list, rhead);
+	call_rcu(&list->rhead, amdgpu_bo_list_free_rcu);
 }
 
-static int amdgpu_bo_list_create(struct amdgpu_device *adev,
-				 struct drm_file *filp,
-				 struct drm_amdgpu_bo_list_entry *info,
-				 unsigned num_entries,
-				 int *id)
+int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp,
+			  struct drm_amdgpu_bo_list_entry *info,
+			  unsigned num_entries, struct amdgpu_bo_list **result)
 {
-	int r;
-	struct amdgpu_fpriv *fpriv = filp->driver_priv;
+	unsigned last_entry = 0, first_userptr = num_entries;
+	struct amdgpu_bo_list_entry *array;
 	struct amdgpu_bo_list *list;
+	uint64_t total_size = 0;
+	size_t size;
+	unsigned i;
+	int r;
+
+	if (num_entries > SIZE_MAX / sizeof(struct amdgpu_bo_list_entry))
+		return -EINVAL;
 
-	list = kzalloc(sizeof(struct amdgpu_bo_list), GFP_KERNEL);
+	size = sizeof(struct amdgpu_bo_list);
+	size += num_entries * sizeof(struct amdgpu_bo_list_entry);
+	list = kvmalloc(size, GFP_KERNEL);
 	if (!list)
 		return -ENOMEM;
 
-	/* initialize bo list*/
-	mutex_init(&list->lock);
 	kref_init(&list->refcount);
-	r = amdgpu_bo_list_set(adev, filp, list, info, num_entries);
-	if (r) {
-		kfree(list);
-		return r;
-	}
-
-	/* idr alloc should be called only after initialization of bo list. */
-	mutex_lock(&fpriv->bo_list_lock);
-	r = idr_alloc(&fpriv->bo_list_handles, list, 1, 0, GFP_KERNEL);
-	mutex_unlock(&fpriv->bo_list_lock);
-	if (r < 0) {
-		amdgpu_bo_list_free(list);
-		return r;
-	}
-	*id = r;
-
-	return 0;
-}
-
-static void amdgpu_bo_list_destroy(struct amdgpu_fpriv *fpriv, int id)
-{
-	struct amdgpu_bo_list *list;
-
-	mutex_lock(&fpriv->bo_list_lock);
-	list = idr_remove(&fpriv->bo_list_handles, id);
-	mutex_unlock(&fpriv->bo_list_lock);
-	if (list)
-		kref_put(&list->refcount, amdgpu_bo_list_release_rcu);
-}
-
-static int amdgpu_bo_list_set(struct amdgpu_device *adev,
-				     struct drm_file *filp,
-				     struct amdgpu_bo_list *list,
-				     struct drm_amdgpu_bo_list_entry *info,
-				     unsigned num_entries)
-{
-	struct amdgpu_bo_list_entry *array;
-	struct amdgpu_bo *gds_obj = adev->gds.gds_gfx_bo;
-	struct amdgpu_bo *gws_obj = adev->gds.gws_gfx_bo;
-	struct amdgpu_bo *oa_obj = adev->gds.oa_gfx_bo;
-
-	unsigned last_entry = 0, first_userptr = num_entries;
-	unsigned i;
-	int r;
-	unsigned long total_size = 0;
+	list->gds_obj = adev->gds.gds_gfx_bo;
+	list->gws_obj = adev->gds.gws_gfx_bo;
+	list->oa_obj = adev->gds.oa_gfx_bo;
 
-	array = kvmalloc_array(num_entries, sizeof(struct amdgpu_bo_list_entry), GFP_KERNEL);
-	if (!array)
-		return -ENOMEM;
+	array = amdgpu_bo_list_array_entry(list, 0);
 	memset(array, 0, num_entries * sizeof(struct amdgpu_bo_list_entry));
 
 	for (i = 0; i < num_entries; ++i) {
@@ -157,59 +118,56 @@ static int amdgpu_bo_list_set(struct amdgpu_device *adev,
 		entry->tv.shared = !entry->robj->prime_shared_count;
 
 		if (entry->robj->preferred_domains == AMDGPU_GEM_DOMAIN_GDS)
-			gds_obj = entry->robj;
+			list->gds_obj = entry->robj;
 		if (entry->robj->preferred_domains == AMDGPU_GEM_DOMAIN_GWS)
-			gws_obj = entry->robj;
+			list->gws_obj = entry->robj;
 		if (entry->robj->preferred_domains == AMDGPU_GEM_DOMAIN_OA)
-			oa_obj = entry->robj;
+			list->oa_obj = entry->robj;
 
 		total_size += amdgpu_bo_size(entry->robj);
 		trace_amdgpu_bo_list_set(list, entry->robj);
 	}
 
-	for (i = 0; i < list->num_entries; ++i)
-		amdgpu_bo_unref(&list->array[i].robj);
-
-	kvfree(list->array);
-
-	list->gds_obj = gds_obj;
-	list->gws_obj = gws_obj;
-	list->oa_obj = oa_obj;
 	list->first_userptr = first_userptr;
-	list->array = array;
 	list->num_entries = num_entries;
 
 	trace_amdgpu_cs_bo_status(list->num_entries, total_size);
+
+	*result = list;
 	return 0;
 
 error_free:
 	while (i--)
 		amdgpu_bo_unref(&array[i].robj);
-	kvfree(array);
+	kvfree(list);
 	return r;
+
 }
 
-struct amdgpu_bo_list *
-amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id)
+static void amdgpu_bo_list_destroy(struct amdgpu_fpriv *fpriv, int id)
 {
-	struct amdgpu_bo_list *result;
+	struct amdgpu_bo_list *list;
+
+	mutex_lock(&fpriv->bo_list_lock);
+	list = idr_remove(&fpriv->bo_list_handles, id);
+	mutex_unlock(&fpriv->bo_list_lock);
+	if (list)
+		kref_put(&list->refcount, amdgpu_bo_list_free);
+}
 
+int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id,
+		       struct amdgpu_bo_list **result)
+{
 	rcu_read_lock();
-	result = idr_find(&fpriv->bo_list_handles, id);
+	*result = idr_find(&fpriv->bo_list_handles, id);
 
-	if (result) {
-		if (kref_get_unless_zero(&result->refcount)) {
-			rcu_read_unlock();
-			mutex_lock(&result->lock);
-		} else {
-			rcu_read_unlock();
-			result = NULL;
-		}
-	} else {
+	if (*result && kref_get_unless_zero(&(*result)->refcount)) {
 		rcu_read_unlock();
+		return 0;
 	}
 
-	return result;
+	rcu_read_unlock();
+	return -ENOENT;
 }
 
 void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
@@ -220,6 +178,7 @@ void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
 	 * concatenated in descending order.
 	 */
 	struct list_head bucket[AMDGPU_BO_LIST_NUM_BUCKETS];
+	struct amdgpu_bo_list_entry *e;
 	unsigned i;
 
 	for (i = 0; i < AMDGPU_BO_LIST_NUM_BUCKETS; i++)
@@ -230,14 +189,13 @@ void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
 	 * in the list, the sort mustn't change the ordering of buffers
 	 * with the same priority, i.e. it must be stable.
 	 */
-	for (i = 0; i < list->num_entries; i++) {
-		unsigned priority = list->array[i].priority;
+	amdgpu_bo_list_for_each_entry(e, list) {
+		unsigned priority = e->priority;
 
-		if (!list->array[i].robj->parent)
-			list_add_tail(&list->array[i].tv.head,
-				      &bucket[priority]);
+		if (!e->robj->parent)
+			list_add_tail(&e->tv.head, &bucket[priority]);
 
-		list->array[i].user_pages = NULL;
+		e->user_pages = NULL;
 	}
 
 	/* Connect the sorted buckets in the output list. */
@@ -247,71 +205,82 @@ void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
 
 void amdgpu_bo_list_put(struct amdgpu_bo_list *list)
 {
-	mutex_unlock(&list->lock);
-	kref_put(&list->refcount, amdgpu_bo_list_release_rcu);
-}
-
-void amdgpu_bo_list_free(struct amdgpu_bo_list *list)
-{
-	unsigned i;
-
-	for (i = 0; i < list->num_entries; ++i)
-		amdgpu_bo_unref(&list->array[i].robj);
-
-	mutex_destroy(&list->lock);
-	kvfree(list->array);
-	kfree(list);
+	kref_put(&list->refcount, amdgpu_bo_list_free);
 }
 
-int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
-				struct drm_file *filp)
+int amdgpu_bo_create_list_entry_array(struct drm_amdgpu_bo_list_in *in,
+				      struct drm_amdgpu_bo_list_entry **info_param)
 {
+	const void __user *uptr = u64_to_user_ptr(in->bo_info_ptr);
 	const uint32_t info_size = sizeof(struct drm_amdgpu_bo_list_entry);
-
-	struct amdgpu_device *adev = dev->dev_private;
-	struct amdgpu_fpriv *fpriv = filp->driver_priv;
-	union drm_amdgpu_bo_list *args = data;
-	uint32_t handle = args->in.list_handle;
-	const void __user *uptr = u64_to_user_ptr(args->in.bo_info_ptr);
-
 	struct drm_amdgpu_bo_list_entry *info;
-	struct amdgpu_bo_list *list;
-
 	int r;
 
-	info = kvmalloc_array(args->in.bo_number,
-			     sizeof(struct drm_amdgpu_bo_list_entry), GFP_KERNEL);
+	info = kvmalloc_array(in->bo_number, info_size, GFP_KERNEL);
 	if (!info)
 		return -ENOMEM;
 
 	/* copy the handle array from userspace to a kernel buffer */
 	r = -EFAULT;
-	if (likely(info_size == args->in.bo_info_size)) {
-		unsigned long bytes = args->in.bo_number *
-			args->in.bo_info_size;
+	if (likely(info_size == in->bo_info_size)) {
+		unsigned long bytes = in->bo_number *
+			in->bo_info_size;
 
 		if (copy_from_user(info, uptr, bytes))
 			goto error_free;
 
 	} else {
-		unsigned long bytes = min(args->in.bo_info_size, info_size);
+		unsigned long bytes = min(in->bo_info_size, info_size);
 		unsigned i;
 
-		memset(info, 0, args->in.bo_number * info_size);
-		for (i = 0; i < args->in.bo_number; ++i) {
+		memset(info, 0, in->bo_number * info_size);
+		for (i = 0; i < in->bo_number; ++i) {
 			if (copy_from_user(&info[i], uptr, bytes))
 				goto error_free;
 
-			uptr += args->in.bo_info_size;
+			uptr += in->bo_info_size;
 		}
 	}
 
+	*info_param = info;
+	return 0;
+
+error_free:
+	kvfree(info);
+	return r;
+}
+
+int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
+				struct drm_file *filp)
+{
+	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_fpriv *fpriv = filp->driver_priv;
+	union drm_amdgpu_bo_list *args = data;
+	uint32_t handle = args->in.list_handle;
+	struct drm_amdgpu_bo_list_entry *info = NULL;
+	struct amdgpu_bo_list *list, *old;
+	int r;
+
+	r = amdgpu_bo_create_list_entry_array(&args->in, &info);
+	if (r)
+		goto error_free;
+
 	switch (args->in.operation) {
 	case AMDGPU_BO_LIST_OP_CREATE:
 		r = amdgpu_bo_list_create(adev, filp, info, args->in.bo_number,
-					  &handle);
+					  &list);
 		if (r)
 			goto error_free;
+
+		mutex_lock(&fpriv->bo_list_lock);
+		r = idr_alloc(&fpriv->bo_list_handles, list, 1, 0, GFP_KERNEL);
+		mutex_unlock(&fpriv->bo_list_lock);
+		if (r < 0) {
+			amdgpu_bo_list_put(list);
+			return r;
+		}
+
+		handle = r;
 		break;
 
 	case AMDGPU_BO_LIST_OP_DESTROY:
@@ -320,17 +289,22 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 		break;
 
 	case AMDGPU_BO_LIST_OP_UPDATE:
-		r = -ENOENT;
-		list = amdgpu_bo_list_get(fpriv, handle);
-		if (!list)
+		r = amdgpu_bo_list_create(adev, filp, info, args->in.bo_number,
+					  &list);
+		if (r)
 			goto error_free;
 
-		r = amdgpu_bo_list_set(adev, filp, list, info,
-					      args->in.bo_number);
-		amdgpu_bo_list_put(list);
-		if (r)
+		mutex_lock(&fpriv->bo_list_lock);
+		old = idr_replace(&fpriv->bo_list_handles, list, handle);
+		mutex_unlock(&fpriv->bo_list_lock);
+
+		if (IS_ERR(old)) {
+			amdgpu_bo_list_put(list);
+			r = PTR_ERR(old);
 			goto error_free;
+		}
 
+		amdgpu_bo_list_put(old);
 		break;
 
 	default:
@@ -345,6 +319,7 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 	return 0;
 
 error_free:
-	kvfree(info);
+	if (info)
+		kvfree(info);
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
new file mode 100644
index 000000000000..61b089768e1c
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
@@ -0,0 +1,85 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef __AMDGPU_BO_LIST_H__
+#define __AMDGPU_BO_LIST_H__
+
+#include <drm/ttm/ttm_execbuf_util.h>
+#include <drm/amdgpu_drm.h>
+
+struct amdgpu_device;
+struct amdgpu_bo;
+struct amdgpu_bo_va;
+struct amdgpu_fpriv;
+
+struct amdgpu_bo_list_entry {
+	struct amdgpu_bo		*robj;
+	struct ttm_validate_buffer	tv;
+	struct amdgpu_bo_va		*bo_va;
+	uint32_t			priority;
+	struct page			**user_pages;
+	int				user_invalidated;
+};
+
+struct amdgpu_bo_list {
+	struct rcu_head rhead;
+	struct kref refcount;
+	struct amdgpu_bo *gds_obj;
+	struct amdgpu_bo *gws_obj;
+	struct amdgpu_bo *oa_obj;
+	unsigned first_userptr;
+	unsigned num_entries;
+};
+
+int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id,
+		       struct amdgpu_bo_list **result);
+void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
+			     struct list_head *validated);
+void amdgpu_bo_list_put(struct amdgpu_bo_list *list);
+int amdgpu_bo_create_list_entry_array(struct drm_amdgpu_bo_list_in *in,
+				      struct drm_amdgpu_bo_list_entry **info_param);
+
+int amdgpu_bo_list_create(struct amdgpu_device *adev,
+				 struct drm_file *filp,
+				 struct drm_amdgpu_bo_list_entry *info,
+				 unsigned num_entries,
+				 struct amdgpu_bo_list **list);
+
+static inline struct amdgpu_bo_list_entry *
+amdgpu_bo_list_array_entry(struct amdgpu_bo_list *list, unsigned index)
+{
+	struct amdgpu_bo_list_entry *array = (void *)&list[1];
+
+	return &array[index];
+}
+
+#define amdgpu_bo_list_for_each_entry(e, list) \
+	for (e = amdgpu_bo_list_array_entry(list, 0); \
+	     e != amdgpu_bo_list_array_entry(list, (list)->num_entries); \
+	     ++e)
+
+#define amdgpu_bo_list_for_each_userptr_entry(e, list) \
+	for (e = amdgpu_bo_list_array_entry(list, (list)->first_userptr); \
+	     e != amdgpu_bo_list_array_entry(list, (list)->num_entries); \
+	     ++e)
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index e950730f1933..693ec5ea4950 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -314,17 +314,17 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device,
 					(adev->pdev->revision == 0x81) ||
 					(adev->pdev->device == 0x665f)) {
 					info->is_kicker = true;
-					strcpy(fw_name, "radeon/bonaire_k_smc.bin");
+					strcpy(fw_name, "amdgpu/bonaire_k_smc.bin");
 				} else {
-					strcpy(fw_name, "radeon/bonaire_smc.bin");
+					strcpy(fw_name, "amdgpu/bonaire_smc.bin");
 				}
 				break;
 			case CHIP_HAWAII:
 				if (adev->pdev->revision == 0x80) {
 					info->is_kicker = true;
-					strcpy(fw_name, "radeon/hawaii_k_smc.bin");
+					strcpy(fw_name, "amdgpu/hawaii_k_smc.bin");
 				} else {
-					strcpy(fw_name, "radeon/hawaii_smc.bin");
+					strcpy(fw_name, "amdgpu/hawaii_smc.bin");
 				}
 				break;
 			case CHIP_TOPAZ:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 8e66851eb427..c770d73352a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -212,30 +212,21 @@ static void
 amdgpu_connector_update_scratch_regs(struct drm_connector *connector,
 				      enum drm_connector_status status)
 {
-	struct drm_encoder *best_encoder = NULL;
-	struct drm_encoder *encoder = NULL;
+	struct drm_encoder *best_encoder;
+	struct drm_encoder *encoder;
 	const struct drm_connector_helper_funcs *connector_funcs = connector->helper_private;
 	bool connected;
 	int i;
 
 	best_encoder = connector_funcs->best_encoder(connector);
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL,
-					connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if ((encoder == best_encoder) && (status == connector_status_connected))
 			connected = true;
 		else
 			connected = false;
 
 		amdgpu_atombios_encoder_set_bios_scratch_regs(connector, encoder, connected);
-
 	}
 }
 
@@ -246,17 +237,11 @@ amdgpu_connector_find_encoder(struct drm_connector *connector,
 	struct drm_encoder *encoder;
 	int i;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-		encoder = drm_encoder_find(connector->dev, NULL,
-					connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if (encoder->encoder_type == encoder_type)
 			return encoder;
 	}
+
 	return NULL;
 }
 
@@ -349,22 +334,24 @@ static int amdgpu_connector_ddc_get_modes(struct drm_connector *connector)
 	int ret;
 
 	if (amdgpu_connector->edid) {
-		drm_mode_connector_update_edid_property(connector, amdgpu_connector->edid);
+		drm_connector_update_edid_property(connector, amdgpu_connector->edid);
 		ret = drm_add_edid_modes(connector, amdgpu_connector->edid);
 		return ret;
 	}
-	drm_mode_connector_update_edid_property(connector, NULL);
+	drm_connector_update_edid_property(connector, NULL);
 	return 0;
 }
 
 static struct drm_encoder *
 amdgpu_connector_best_single_encoder(struct drm_connector *connector)
 {
-	int enc_id = connector->encoder_ids[0];
+	struct drm_encoder *encoder;
+	int i;
+
+	/* pick the first one */
+	drm_connector_for_each_possible_encoder(connector, encoder, i)
+		return encoder;
 
-	/* pick the encoder ids */
-	if (enc_id)
-		return drm_encoder_find(connector->dev, NULL, enc_id);
 	return NULL;
 }
 
@@ -985,9 +972,8 @@ amdgpu_connector_dvi_detect(struct drm_connector *connector, bool force)
 	struct drm_device *dev = connector->dev;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
-	struct drm_encoder *encoder = NULL;
 	const struct drm_encoder_helper_funcs *encoder_funcs;
-	int i, r;
+	int r;
 	enum drm_connector_status ret = connector_status_disconnected;
 	bool dret = false, broken_edid = false;
 
@@ -1077,14 +1063,10 @@ amdgpu_connector_dvi_detect(struct drm_connector *connector, bool force)
 
 	/* find analog encoder */
 	if (amdgpu_connector->dac_load_detect) {
-		for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-			if (connector->encoder_ids[i] == 0)
-				break;
-
-			encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-			if (!encoder)
-				continue;
+		struct drm_encoder *encoder;
+		int i;
 
+		drm_connector_for_each_possible_encoder(connector, encoder, i) {
 			if (encoder->encoder_type != DRM_MODE_ENCODER_DAC &&
 			    encoder->encoder_type != DRM_MODE_ENCODER_TVDAC)
 				continue;
@@ -1132,18 +1114,11 @@ exit:
 static struct drm_encoder *
 amdgpu_connector_dvi_encoder(struct drm_connector *connector)
 {
-	int enc_id = connector->encoder_ids[0];
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 	struct drm_encoder *encoder;
 	int i;
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
 
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if (amdgpu_connector->use_digital == true) {
 			if (encoder->encoder_type == DRM_MODE_ENCODER_TMDS)
 				return encoder;
@@ -1158,8 +1133,9 @@ amdgpu_connector_dvi_encoder(struct drm_connector *connector)
 
 	/* then check use digitial */
 	/* pick the first one */
-	if (enc_id)
-		return drm_encoder_find(connector->dev, NULL, enc_id);
+	drm_connector_for_each_possible_encoder(connector, encoder, i)
+		return encoder;
+
 	return NULL;
 }
 
@@ -1296,15 +1272,7 @@ u16 amdgpu_connector_encoder_get_dp_bridge_encoder_id(struct drm_connector *conn
 	struct amdgpu_encoder *amdgpu_encoder;
 	int i;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL,
-					connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		amdgpu_encoder = to_amdgpu_encoder(encoder);
 
 		switch (amdgpu_encoder->encoder_id) {
@@ -1326,14 +1294,7 @@ static bool amdgpu_connector_encoder_is_hbr2(struct drm_connector *connector)
 	int i;
 	bool found = false;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-		encoder = drm_encoder_find(connector->dev, NULL,
-					connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		amdgpu_encoder = to_amdgpu_encoder(encoder);
 		if (amdgpu_encoder->caps & ATOM_ENCODER_CAP_RECORD_HBR2)
 			found = true;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 9c85a90be293..502b94fb116a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -31,6 +31,7 @@
 #include <drm/drm_syncobj.h>
 #include "amdgpu.h"
 #include "amdgpu_trace.h"
+#include "amdgpu_gmc.h"
 
 static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p,
 				      struct drm_amdgpu_cs_chunk_fence *data,
@@ -65,11 +66,35 @@ static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p,
 	return 0;
 }
 
-static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
+static int amdgpu_cs_bo_handles_chunk(struct amdgpu_cs_parser *p,
+				      struct drm_amdgpu_bo_list_in *data)
+{
+	int r;
+	struct drm_amdgpu_bo_list_entry *info = NULL;
+
+	r = amdgpu_bo_create_list_entry_array(data, &info);
+	if (r)
+		return r;
+
+	r = amdgpu_bo_list_create(p->adev, p->filp, info, data->bo_number,
+				  &p->bo_list);
+	if (r)
+		goto error_free;
+
+	kvfree(info);
+	return 0;
+
+error_free:
+	if (info)
+		kvfree(info);
+
+	return r;
+}
+
+static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs *cs)
 {
 	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
 	struct amdgpu_vm *vm = &fpriv->vm;
-	union drm_amdgpu_cs *cs = data;
 	uint64_t *chunk_array_user;
 	uint64_t *chunk_array;
 	unsigned size, num_ibs = 0;
@@ -163,6 +188,19 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 
 			break;
 
+		case AMDGPU_CHUNK_ID_BO_HANDLES:
+			size = sizeof(struct drm_amdgpu_bo_list_in);
+			if (p->chunks[i].length_dw * sizeof(uint32_t) < size) {
+				ret = -EINVAL;
+				goto free_partial_kdata;
+			}
+
+			ret = amdgpu_cs_bo_handles_chunk(p, p->chunks[i].kdata);
+			if (ret)
+				goto free_partial_kdata;
+
+			break;
+
 		case AMDGPU_CHUNK_ID_DEPENDENCIES:
 		case AMDGPU_CHUNK_ID_SYNCOBJ_IN:
 		case AMDGPU_CHUNK_ID_SYNCOBJ_OUT:
@@ -186,6 +224,10 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 	if (p->uf_entry.robj)
 		p->job->uf_addr = uf_offset;
 	kfree(chunk_array);
+
+	/* Use this opportunity to fill in task info for the vm */
+	amdgpu_vm_set_task_info(vm);
+
 	return 0;
 
 free_all_kdata:
@@ -257,7 +299,7 @@ static void amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev,
 		return;
 	}
 
-	total_vram = adev->gmc.real_vram_size - adev->vram_pin_size;
+	total_vram = adev->gmc.real_vram_size - atomic64_read(&adev->vram_pin_size);
 	used_vram = amdgpu_vram_mgr_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
 	free_vram = used_vram >= total_vram ? 0 : total_vram - used_vram;
 
@@ -302,7 +344,7 @@ static void amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev,
 	*max_bytes = us_to_bytes(adev, adev->mm_stats.accum_us);
 
 	/* Do the same for visible VRAM if half of it is free */
-	if (adev->gmc.visible_vram_size < adev->gmc.real_vram_size) {
+	if (!amdgpu_gmc_vram_full_visible(&adev->gmc)) {
 		u64 total_vis_vram = adev->gmc.visible_vram_size;
 		u64 used_vis_vram =
 			amdgpu_vram_mgr_vis_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
@@ -359,7 +401,7 @@ static int amdgpu_cs_bo_validate(struct amdgpu_cs_parser *p,
 	 * to move it. Don't move anything if the threshold is zero.
 	 */
 	if (p->bytes_moved < p->bytes_moved_threshold) {
-		if (adev->gmc.visible_vram_size < adev->gmc.real_vram_size &&
+		if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
 		    (bo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED)) {
 			/* And don't move a CPU_ACCESS_REQUIRED BO to limited
 			 * visible VRAM if we've depleted our allowance to do
@@ -377,11 +419,11 @@ static int amdgpu_cs_bo_validate(struct amdgpu_cs_parser *p,
 	}
 
 retry:
-	amdgpu_ttm_placement_from_domain(bo, domain);
+	amdgpu_bo_placement_from_domain(bo, domain);
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 
 	p->bytes_moved += ctx.bytes_moved;
-	if (adev->gmc.visible_vram_size < adev->gmc.real_vram_size &&
+	if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
 	    amdgpu_bo_in_cpu_visible_vram(bo))
 		p->bytes_moved_vis += ctx.bytes_moved;
 
@@ -434,9 +476,9 @@ static bool amdgpu_cs_try_evict(struct amdgpu_cs_parser *p,
 
 		/* Good we can try to move this BO somewhere else */
 		update_bytes_moved_vis =
-			adev->gmc.visible_vram_size < adev->gmc.real_vram_size &&
-			amdgpu_bo_in_cpu_visible_vram(bo);
-		amdgpu_ttm_placement_from_domain(bo, other);
+				!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
+				amdgpu_bo_in_cpu_visible_vram(bo);
+		amdgpu_bo_placement_from_domain(bo, other);
 		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		p->bytes_moved += ctx.bytes_moved;
 		if (update_bytes_moved_vis)
@@ -490,8 +532,8 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
 		/* Check if we have user pages and nobody bound the BO already */
 		if (amdgpu_ttm_tt_userptr_needs_pages(bo->tbo.ttm) &&
 		    lobj->user_pages) {
-			amdgpu_ttm_placement_from_domain(bo,
-							 AMDGPU_GEM_DOMAIN_CPU);
+			amdgpu_bo_placement_from_domain(bo,
+							AMDGPU_GEM_DOMAIN_CPU);
 			r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 			if (r)
 				return r;
@@ -519,23 +561,38 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 				union drm_amdgpu_cs *cs)
 {
 	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
+	struct amdgpu_vm *vm = &fpriv->vm;
 	struct amdgpu_bo_list_entry *e;
 	struct list_head duplicates;
-	unsigned i, tries = 10;
 	struct amdgpu_bo *gds;
 	struct amdgpu_bo *gws;
 	struct amdgpu_bo *oa;
+	unsigned tries = 10;
 	int r;
 
 	INIT_LIST_HEAD(&p->validated);
 
-	p->bo_list = amdgpu_bo_list_get(fpriv, cs->in.bo_list_handle);
-	if (p->bo_list) {
-		amdgpu_bo_list_get_list(p->bo_list, &p->validated);
-		if (p->bo_list->first_userptr != p->bo_list->num_entries)
-			p->mn = amdgpu_mn_get(p->adev, AMDGPU_MN_TYPE_GFX);
+	/* p->bo_list could already be assigned if AMDGPU_CHUNK_ID_BO_HANDLES is present */
+	if (cs->in.bo_list_handle) {
+		if (p->bo_list)
+			return -EINVAL;
+
+		r = amdgpu_bo_list_get(fpriv, cs->in.bo_list_handle,
+				       &p->bo_list);
+		if (r)
+			return r;
+	} else if (!p->bo_list) {
+		/* Create a empty bo_list when no handle is provided */
+		r = amdgpu_bo_list_create(p->adev, p->filp, NULL, 0,
+					  &p->bo_list);
+		if (r)
+			return r;
 	}
 
+	amdgpu_bo_list_get_list(p->bo_list, &p->validated);
+	if (p->bo_list->first_userptr != p->bo_list->num_entries)
+		p->mn = amdgpu_mn_get(p->adev, AMDGPU_MN_TYPE_GFX);
+
 	INIT_LIST_HEAD(&duplicates);
 	amdgpu_vm_get_pd_bo(&fpriv->vm, &p->validated, &p->vm_pd);
 
@@ -544,7 +601,6 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 
 	while (1) {
 		struct list_head need_pages;
-		unsigned i;
 
 		r = ttm_eu_reserve_buffers(&p->ticket, &p->validated, true,
 					   &duplicates);
@@ -554,17 +610,9 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 			goto error_free_pages;
 		}
 
-		/* Without a BO list we don't have userptr BOs */
-		if (!p->bo_list)
-			break;
-
 		INIT_LIST_HEAD(&need_pages);
-		for (i = p->bo_list->first_userptr;
-		     i < p->bo_list->num_entries; ++i) {
-			struct amdgpu_bo *bo;
-
-			e = &p->bo_list->array[i];
-			bo = e->robj;
+		amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) {
+			struct amdgpu_bo *bo = e->robj;
 
 			if (amdgpu_ttm_tt_userptr_invalidated(bo->tbo.ttm,
 				 &e->user_invalidated) && e->user_pages) {
@@ -656,23 +704,12 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	amdgpu_cs_report_moved_bytes(p->adev, p->bytes_moved,
 				     p->bytes_moved_vis);
 
-	if (p->bo_list) {
-		struct amdgpu_vm *vm = &fpriv->vm;
-		unsigned i;
+	gds = p->bo_list->gds_obj;
+	gws = p->bo_list->gws_obj;
+	oa = p->bo_list->oa_obj;
 
-		gds = p->bo_list->gds_obj;
-		gws = p->bo_list->gws_obj;
-		oa = p->bo_list->oa_obj;
-		for (i = 0; i < p->bo_list->num_entries; i++) {
-			struct amdgpu_bo *bo = p->bo_list->array[i].robj;
-
-			p->bo_list->array[i].bo_va = amdgpu_vm_bo_find(vm, bo);
-		}
-	} else {
-		gds = p->adev->gds.gds_gfx_bo;
-		gws = p->adev->gds.gws_gfx_bo;
-		oa = p->adev->gds.oa_gfx_bo;
-	}
+	amdgpu_bo_list_for_each_entry(e, p->bo_list)
+		e->bo_va = amdgpu_vm_bo_find(vm, e->robj);
 
 	if (gds) {
 		p->job->gds_base = amdgpu_bo_gpu_offset(gds);
@@ -700,18 +737,13 @@ error_validate:
 
 error_free_pages:
 
-	if (p->bo_list) {
-		for (i = p->bo_list->first_userptr;
-		     i < p->bo_list->num_entries; ++i) {
-			e = &p->bo_list->array[i];
-
-			if (!e->user_pages)
-				continue;
+	amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) {
+		if (!e->user_pages)
+			continue;
 
-			release_pages(e->user_pages,
-				      e->robj->tbo.ttm->num_pages);
-			kvfree(e->user_pages);
-		}
+		release_pages(e->user_pages,
+			      e->robj->tbo.ttm->num_pages);
+		kvfree(e->user_pages);
 	}
 
 	return r;
@@ -773,12 +805,13 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error,
 
 static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
 {
-	struct amdgpu_device *adev = p->adev;
 	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
+	struct amdgpu_device *adev = p->adev;
 	struct amdgpu_vm *vm = &fpriv->vm;
+	struct amdgpu_bo_list_entry *e;
 	struct amdgpu_bo_va *bo_va;
 	struct amdgpu_bo *bo;
-	int i, r;
+	int r;
 
 	r = amdgpu_vm_clear_freed(adev, vm, NULL);
 	if (r)
@@ -808,29 +841,26 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
 			return r;
 	}
 
-	if (p->bo_list) {
-		for (i = 0; i < p->bo_list->num_entries; i++) {
-			struct dma_fence *f;
-
-			/* ignore duplicates */
-			bo = p->bo_list->array[i].robj;
-			if (!bo)
-				continue;
+	amdgpu_bo_list_for_each_entry(e, p->bo_list) {
+		struct dma_fence *f;
 
-			bo_va = p->bo_list->array[i].bo_va;
-			if (bo_va == NULL)
-				continue;
+		/* ignore duplicates */
+		bo = e->robj;
+		if (!bo)
+			continue;
 
-			r = amdgpu_vm_bo_update(adev, bo_va, false);
-			if (r)
-				return r;
+		bo_va = e->bo_va;
+		if (bo_va == NULL)
+			continue;
 
-			f = bo_va->last_pt_update;
-			r = amdgpu_sync_fence(adev, &p->job->sync, f, false);
-			if (r)
-				return r;
-		}
+		r = amdgpu_vm_bo_update(adev, bo_va, false);
+		if (r)
+			return r;
 
+		f = bo_va->last_pt_update;
+		r = amdgpu_sync_fence(adev, &p->job->sync, f, false);
+		if (r)
+			return r;
 	}
 
 	r = amdgpu_vm_handle_moved(adev, vm);
@@ -845,15 +875,14 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
 	if (r)
 		return r;
 
-	if (amdgpu_vm_debug && p->bo_list) {
+	if (amdgpu_vm_debug) {
 		/* Invalidate all BOs to test for userspace bugs */
-		for (i = 0; i < p->bo_list->num_entries; i++) {
+		amdgpu_bo_list_for_each_entry(e, p->bo_list) {
 			/* ignore duplicates */
-			bo = p->bo_list->array[i].robj;
-			if (!bo)
+			if (!e->robj)
 				continue;
 
-			amdgpu_vm_bo_invalidate(adev, bo, false);
+			amdgpu_vm_bo_invalidate(adev, e->robj, false);
 		}
 	}
 
@@ -865,11 +894,11 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 {
 	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
 	struct amdgpu_vm *vm = &fpriv->vm;
-	struct amdgpu_ring *ring = p->job->ring;
+	struct amdgpu_ring *ring = p->ring;
 	int r;
 
 	/* Only for UVD/VCE VM emulation */
-	if (p->job->ring->funcs->parse_cs) {
+	if (p->ring->funcs->parse_cs || p->ring->funcs->patch_cs_in_place) {
 		unsigned i, j;
 
 		for (i = 0, j = 0; i < p->nchunks && j < p->job->num_ibs; i++) {
@@ -910,12 +939,20 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 			offset = m->start * AMDGPU_GPU_PAGE_SIZE;
 			kptr += va_start - offset;
 
-			memcpy(ib->ptr, kptr, chunk_ib->ib_bytes);
-			amdgpu_bo_kunmap(aobj);
-
-			r = amdgpu_ring_parse_cs(ring, p, j);
-			if (r)
-				return r;
+			if (p->ring->funcs->parse_cs) {
+				memcpy(ib->ptr, kptr, chunk_ib->ib_bytes);
+				amdgpu_bo_kunmap(aobj);
+
+				r = amdgpu_ring_parse_cs(ring, p, j);
+				if (r)
+					return r;
+			} else {
+				ib->ptr = (uint32_t *)kptr;
+				r = amdgpu_ring_patch_cs_in_place(ring, p, j);
+				amdgpu_bo_kunmap(aobj);
+				if (r)
+					return r;
+			}
 
 			j++;
 		}
@@ -983,10 +1020,10 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
 			}
 		}
 
-		if (parser->job->ring && parser->job->ring != ring)
+		if (parser->ring && parser->ring != ring)
 			return -EINVAL;
 
-		parser->job->ring = ring;
+		parser->ring = ring;
 
 		r =  amdgpu_ib_get(adev, vm,
 					ring->funcs->parse_cs ? chunk_ib->ib_bytes : 0,
@@ -1005,11 +1042,11 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
 
 	/* UVD & VCE fw doesn't support user fences */
 	if (parser->job->uf_addr && (
-	    parser->job->ring->funcs->type == AMDGPU_RING_TYPE_UVD ||
-	    parser->job->ring->funcs->type == AMDGPU_RING_TYPE_VCE))
+	    parser->ring->funcs->type == AMDGPU_RING_TYPE_UVD ||
+	    parser->ring->funcs->type == AMDGPU_RING_TYPE_VCE))
 		return -EINVAL;
 
-	return amdgpu_ctx_wait_prev_fence(parser->ctx, parser->job->ring->idx);
+	return amdgpu_ctx_wait_prev_fence(parser->ctx, parser->ring->idx);
 }
 
 static int amdgpu_cs_process_fence_dep(struct amdgpu_cs_parser *p,
@@ -1160,31 +1197,30 @@ static void amdgpu_cs_post_dependencies(struct amdgpu_cs_parser *p)
 static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 			    union drm_amdgpu_cs *cs)
 {
-	struct amdgpu_ring *ring = p->job->ring;
+	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
+	struct amdgpu_ring *ring = p->ring;
 	struct drm_sched_entity *entity = &p->ctx->rings[ring->idx].entity;
+	enum drm_sched_priority priority;
+	struct amdgpu_bo_list_entry *e;
 	struct amdgpu_job *job;
-	unsigned i;
 	uint64_t seq;
 
 	int r;
 
 	amdgpu_mn_lock(p->mn);
-	if (p->bo_list) {
-		for (i = p->bo_list->first_userptr;
-		     i < p->bo_list->num_entries; ++i) {
-			struct amdgpu_bo *bo = p->bo_list->array[i].robj;
-
-			if (amdgpu_ttm_tt_userptr_needs_pages(bo->tbo.ttm)) {
-				amdgpu_mn_unlock(p->mn);
-				return -ERESTARTSYS;
-			}
+	amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) {
+		struct amdgpu_bo *bo = e->robj;
+
+		if (amdgpu_ttm_tt_userptr_needs_pages(bo->tbo.ttm)) {
+			amdgpu_mn_unlock(p->mn);
+			return -ERESTARTSYS;
 		}
 	}
 
 	job = p->job;
 	p->job = NULL;
 
-	r = drm_sched_job_init(&job->base, &ring->sched, entity, p->filp);
+	r = drm_sched_job_init(&job->base, entity, p->filp);
 	if (r) {
 		amdgpu_job_free(job);
 		amdgpu_mn_unlock(p->mn);
@@ -1192,7 +1228,6 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	}
 
 	job->owner = p->filp;
-	job->fence_ctx = entity->fence_context;
 	p->fence = dma_fence_get(&job->base.s_fence->finished);
 
 	r = amdgpu_ctx_add_fence(p->ctx, ring, p->fence, &seq);
@@ -1210,11 +1245,15 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	job->uf_sequence = seq;
 
 	amdgpu_job_free_resources(job);
-	amdgpu_ring_priority_get(job->ring, job->base.s_priority);
 
 	trace_amdgpu_cs_ioctl(job);
+	amdgpu_vm_bo_trace_cs(&fpriv->vm, &p->ticket);
+	priority = job->base.s_priority;
 	drm_sched_entity_push_job(&job->base, entity);
 
+	ring = to_amdgpu_ring(entity->rq->sched);
+	amdgpu_ring_priority_get(ring, priority);
+
 	ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence);
 	amdgpu_mn_unlock(p->mn);
 
@@ -1605,7 +1644,7 @@ int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser,
 
 	if (!((*bo)->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)) {
 		(*bo)->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
-		amdgpu_ttm_placement_from_domain(*bo, (*bo)->allowed_domains);
+		amdgpu_bo_placement_from_domain(*bo, (*bo)->allowed_domains);
 		r = ttm_bo_validate(&(*bo)->tbo, &(*bo)->placement, &ctx);
 		if (r)
 			return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index c5bb36275e93..df6965761046 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -90,8 +90,8 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 		if (ring == &adev->gfx.kiq.ring)
 			continue;
 
-		r = drm_sched_entity_init(&ring->sched, &ctx->rings[i].entity,
-					  rq, &ctx->guilty);
+		r = drm_sched_entity_init(&ctx->rings[i].entity,
+					  &rq, 1, &ctx->guilty);
 		if (r)
 			goto failed;
 	}
@@ -104,8 +104,7 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 
 failed:
 	for (j = 0; j < i; j++)
-		drm_sched_entity_fini(&adev->rings[j]->sched,
-				      &ctx->rings[j].entity);
+		drm_sched_entity_destroy(&ctx->rings[j].entity);
 	kfree(ctx->fences);
 	ctx->fences = NULL;
 	return r;
@@ -178,8 +177,7 @@ static void amdgpu_ctx_do_release(struct kref *ref)
 		if (ctx->adev->rings[i] == &ctx->adev->gfx.kiq.ring)
 			continue;
 
-		drm_sched_entity_fini(&ctx->adev->rings[i]->sched,
-			&ctx->rings[i].entity);
+		drm_sched_entity_destroy(&ctx->rings[i].entity);
 	}
 
 	amdgpu_ctx_fini(ref);
@@ -444,34 +442,36 @@ void amdgpu_ctx_mgr_init(struct amdgpu_ctx_mgr *mgr)
 	idr_init(&mgr->ctx_handles);
 }
 
-void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr)
+void amdgpu_ctx_mgr_entity_flush(struct amdgpu_ctx_mgr *mgr)
 {
 	struct amdgpu_ctx *ctx;
 	struct idr *idp;
 	uint32_t id, i;
+	long max_wait = MAX_WAIT_SCHED_ENTITY_Q_EMPTY;
 
 	idp = &mgr->ctx_handles;
 
+	mutex_lock(&mgr->lock);
 	idr_for_each_entry(idp, ctx, id) {
 
-		if (!ctx->adev)
+		if (!ctx->adev) {
+			mutex_unlock(&mgr->lock);
 			return;
+		}
 
 		for (i = 0; i < ctx->adev->num_rings; i++) {
 
 			if (ctx->adev->rings[i] == &ctx->adev->gfx.kiq.ring)
 				continue;
 
-			if (kref_read(&ctx->refcount) == 1)
-				drm_sched_entity_do_release(&ctx->adev->rings[i]->sched,
-						  &ctx->rings[i].entity);
-			else
-				DRM_ERROR("ctx %p is still alive\n", ctx);
+			max_wait = drm_sched_entity_flush(&ctx->rings[i].entity,
+							  max_wait);
 		}
 	}
+	mutex_unlock(&mgr->lock);
 }
 
-void amdgpu_ctx_mgr_entity_cleanup(struct amdgpu_ctx_mgr *mgr)
+void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr)
 {
 	struct amdgpu_ctx *ctx;
 	struct idr *idp;
@@ -490,8 +490,7 @@ void amdgpu_ctx_mgr_entity_cleanup(struct amdgpu_ctx_mgr *mgr)
 				continue;
 
 			if (kref_read(&ctx->refcount) == 1)
-				drm_sched_entity_cleanup(&ctx->adev->rings[i]->sched,
-					&ctx->rings[i].entity);
+				drm_sched_entity_fini(&ctx->rings[i].entity);
 			else
 				DRM_ERROR("ctx %p is still alive\n", ctx);
 		}
@@ -504,7 +503,7 @@ void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr)
 	struct idr *idp;
 	uint32_t id;
 
-	amdgpu_ctx_mgr_entity_cleanup(mgr);
+	amdgpu_ctx_mgr_entity_fini(mgr);
 
 	idp = &mgr->ctx_handles;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 2c5f093e79e3..1e66dfd0e39c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -25,6 +25,7 @@
  *          Alex Deucher
  *          Jerome Glisse
  */
+#include <linux/power_supply.h>
 #include <linux/kthread.h>
 #include <linux/console.h>
 #include <linux/slab.h>
@@ -675,17 +676,15 @@ void amdgpu_device_vram_location(struct amdgpu_device *adev,
 }
 
 /**
- * amdgpu_device_gart_location - try to find GTT location
+ * amdgpu_device_gart_location - try to find GART location
  *
  * @adev: amdgpu device structure holding all necessary informations
  * @mc: memory controller structure holding memory informations
  *
- * Function will place try to place GTT before or after VRAM.
+ * Function will place try to place GART before or after VRAM.
  *
- * If GTT size is bigger than space left then we ajust GTT size.
+ * If GART size is bigger than space left then we ajust GART size.
  * Thus function will never fails.
- *
- * FIXME: when reducing GTT size align new size on power of 2.
  */
 void amdgpu_device_gart_location(struct amdgpu_device *adev,
 				 struct amdgpu_gmc *mc)
@@ -698,13 +697,13 @@ void amdgpu_device_gart_location(struct amdgpu_device *adev,
 	size_bf = mc->vram_start;
 	if (size_bf > size_af) {
 		if (mc->gart_size > size_bf) {
-			dev_warn(adev->dev, "limiting GTT\n");
+			dev_warn(adev->dev, "limiting GART\n");
 			mc->gart_size = size_bf;
 		}
 		mc->gart_start = 0;
 	} else {
 		if (mc->gart_size > size_af) {
-			dev_warn(adev->dev, "limiting GTT\n");
+			dev_warn(adev->dev, "limiting GART\n");
 			mc->gart_size = size_af;
 		}
 		/* VCE doesn't like it when BOs cross a 4GB segment, so align
@@ -713,7 +712,7 @@ void amdgpu_device_gart_location(struct amdgpu_device *adev,
 		mc->gart_start = ALIGN(mc->vram_end + 1, 0x100000000ULL);
 	}
 	mc->gart_end = mc->gart_start + mc->gart_size - 1;
-	dev_info(adev->dev, "GTT: %lluM 0x%016llX - 0x%016llX\n",
+	dev_info(adev->dev, "GART: %lluM 0x%016llX - 0x%016llX\n",
 			mc->gart_size >> 20, mc->gart_start, mc->gart_end);
 }
 
@@ -1077,7 +1076,7 @@ static const struct vga_switcheroo_client_ops amdgpu_switcheroo_ops = {
 /**
  * amdgpu_device_ip_set_clockgating_state - set the CG state
  *
- * @adev: amdgpu_device pointer
+ * @dev: amdgpu_device pointer
  * @block_type: Type of hardware IP (SMU, GFX, UVD, etc.)
  * @state: clockgating state (gate or ungate)
  *
@@ -1111,7 +1110,7 @@ int amdgpu_device_ip_set_clockgating_state(void *dev,
 /**
  * amdgpu_device_ip_set_powergating_state - set the PG state
  *
- * @adev: amdgpu_device pointer
+ * @dev: amdgpu_device pointer
  * @block_type: Type of hardware IP (SMU, GFX, UVD, etc.)
  * @state: powergating state (gate or ungate)
  *
@@ -1222,7 +1221,7 @@ bool amdgpu_device_ip_is_idle(struct amdgpu_device *adev,
  * amdgpu_device_ip_get_ip_block - get a hw IP pointer
  *
  * @adev: amdgpu_device pointer
- * @block_type: Type of hardware IP (SMU, GFX, UVD, etc.)
+ * @type: Type of hardware IP (SMU, GFX, UVD, etc.)
  *
  * Returns a pointer to the hardware IP block structure
  * if it exists for the asic, otherwise NULL.
@@ -1708,10 +1707,6 @@ static int amdgpu_device_ip_late_set_cg_state(struct amdgpu_device *adev)
 	if (amdgpu_emu_mode == 1)
 		return 0;
 
-	r = amdgpu_ib_ring_tests(adev);
-	if (r)
-		DRM_ERROR("ib ring test failed (%d).\n", r);
-
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_blocks[i].status.valid)
 			continue;
@@ -1731,17 +1726,34 @@ static int amdgpu_device_ip_late_set_cg_state(struct amdgpu_device *adev)
 		}
 	}
 
-	if (adev->powerplay.pp_feature & PP_GFXOFF_MASK) {
-		/* enable gfx powergating */
-		amdgpu_device_ip_set_powergating_state(adev,
-						       AMD_IP_BLOCK_TYPE_GFX,
-						       AMD_PG_STATE_GATE);
-		/* enable gfxoff */
-		amdgpu_device_ip_set_powergating_state(adev,
-						       AMD_IP_BLOCK_TYPE_SMC,
-						       AMD_PG_STATE_GATE);
-	}
+	return 0;
+}
 
+static int amdgpu_device_ip_late_set_pg_state(struct amdgpu_device *adev)
+{
+	int i = 0, r;
+
+	if (amdgpu_emu_mode == 1)
+		return 0;
+
+	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_blocks[i].status.valid)
+			continue;
+		/* skip CG for VCE/UVD, it's handled specially */
+		if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD &&
+		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE &&
+		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCN &&
+		    adev->ip_blocks[i].version->funcs->set_powergating_state) {
+			/* enable powergating to save power */
+			r = adev->ip_blocks[i].version->funcs->set_powergating_state((void *)adev,
+										     AMD_PG_STATE_GATE);
+			if (r) {
+				DRM_ERROR("set_powergating_state(gate) of IP block <%s> failed %d\n",
+					  adev->ip_blocks[i].version->funcs->name, r);
+				return r;
+			}
+		}
+	}
 	return 0;
 }
 
@@ -1775,6 +1787,9 @@ static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
 		}
 	}
 
+	amdgpu_device_ip_late_set_cg_state(adev);
+	amdgpu_device_ip_late_set_pg_state(adev);
+
 	queue_delayed_work(system_wq, &adev->late_init_work,
 			   msecs_to_jiffies(AMDGPU_RESUME_MS));
 
@@ -1813,6 +1828,8 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 					  adev->ip_blocks[i].version->funcs->name, r);
 				return r;
 			}
+			if (adev->powerplay.pp_funcs->set_powergating_by_smu)
+				amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, false);
 			r = adev->ip_blocks[i].version->funcs->hw_fini((void *)adev);
 			/* XXX handle errors */
 			if (r) {
@@ -1901,11 +1918,15 @@ static void amdgpu_device_ip_late_init_func_handler(struct work_struct *work)
 {
 	struct amdgpu_device *adev =
 		container_of(work, struct amdgpu_device, late_init_work.work);
-	amdgpu_device_ip_late_set_cg_state(adev);
+	int r;
+
+	r = amdgpu_ib_ring_tests(adev);
+	if (r)
+		DRM_ERROR("ib ring test failed (%d).\n", r);
 }
 
 /**
- * amdgpu_device_ip_suspend - run suspend for hardware IPs
+ * amdgpu_device_ip_suspend_phase1 - run suspend for hardware IPs (phase 1)
  *
  * @adev: amdgpu_device pointer
  *
@@ -1915,18 +1936,60 @@ static void amdgpu_device_ip_late_init_func_handler(struct work_struct *work)
  * in each IP into a state suitable for suspend.
  * Returns 0 on success, negative error code on failure.
  */
-int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
+static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev)
 {
 	int i, r;
 
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_request_full_gpu(adev, false);
 
-	/* ungate SMC block powergating */
-	if (adev->powerplay.pp_feature & PP_GFXOFF_MASK)
-		amdgpu_device_ip_set_powergating_state(adev,
-						       AMD_IP_BLOCK_TYPE_SMC,
-						       AMD_CG_STATE_UNGATE);
+	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
+		if (!adev->ip_blocks[i].status.valid)
+			continue;
+		/* displays are handled separately */
+		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_DCE) {
+			/* ungate blocks so that suspend can properly shut them down */
+			if (adev->ip_blocks[i].version->funcs->set_clockgating_state) {
+				r = adev->ip_blocks[i].version->funcs->set_clockgating_state((void *)adev,
+											     AMD_CG_STATE_UNGATE);
+				if (r) {
+					DRM_ERROR("set_clockgating_state(ungate) of IP block <%s> failed %d\n",
+						  adev->ip_blocks[i].version->funcs->name, r);
+				}
+			}
+			/* XXX handle errors */
+			r = adev->ip_blocks[i].version->funcs->suspend(adev);
+			/* XXX handle errors */
+			if (r) {
+				DRM_ERROR("suspend of IP block <%s> failed %d\n",
+					  adev->ip_blocks[i].version->funcs->name, r);
+			}
+		}
+	}
+
+	if (amdgpu_sriov_vf(adev))
+		amdgpu_virt_release_full_gpu(adev, false);
+
+	return 0;
+}
+
+/**
+ * amdgpu_device_ip_suspend_phase2 - run suspend for hardware IPs (phase 2)
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Main suspend function for hardware IPs.  The list of all the hardware
+ * IPs that make up the asic is walked, clockgating is disabled and the
+ * suspend callbacks are run.  suspend puts the hardware and software state
+ * in each IP into a state suitable for suspend.
+ * Returns 0 on success, negative error code on failure.
+ */
+static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
+{
+	int i, r;
+
+	if (amdgpu_sriov_vf(adev))
+		amdgpu_virt_request_full_gpu(adev, false);
 
 	/* ungate SMC block first */
 	r = amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_SMC,
@@ -1935,9 +1998,16 @@ int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
 		DRM_ERROR("set_clockgating_state(ungate) SMC failed %d\n", r);
 	}
 
+	/* call smu to disable gfx off feature first when suspend */
+	if (adev->powerplay.pp_funcs->set_powergating_by_smu)
+		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, false);
+
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.valid)
 			continue;
+		/* displays are handled in phase1 */
+		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_DCE)
+			continue;
 		/* ungate blocks so that suspend can properly shut them down */
 		if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_SMC &&
 			adev->ip_blocks[i].version->funcs->set_clockgating_state) {
@@ -1963,6 +2033,29 @@ int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
 	return 0;
 }
 
+/**
+ * amdgpu_device_ip_suspend - run suspend for hardware IPs
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Main suspend function for hardware IPs.  The list of all the hardware
+ * IPs that make up the asic is walked, clockgating is disabled and the
+ * suspend callbacks are run.  suspend puts the hardware and software state
+ * in each IP into a state suitable for suspend.
+ * Returns 0 on success, negative error code on failure.
+ */
+int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
+{
+	int r;
+
+	r = amdgpu_device_ip_suspend_phase1(adev);
+	if (r)
+		return r;
+	r = amdgpu_device_ip_suspend_phase2(adev);
+
+	return r;
+}
+
 static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev)
 {
 	int i, r;
@@ -1985,7 +2078,7 @@ static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev)
 				continue;
 
 			r = block->version->funcs->hw_init(adev);
-			DRM_INFO("RE-INIT: %s %s\n", block->version->funcs->name, r?"failed":"successed");
+			DRM_INFO("RE-INIT: %s %s\n", block->version->funcs->name, r?"failed":"succeeded");
 			if (r)
 				return r;
 		}
@@ -2020,7 +2113,7 @@ static int amdgpu_device_ip_reinit_late_sriov(struct amdgpu_device *adev)
 				continue;
 
 			r = block->version->funcs->hw_init(adev);
-			DRM_INFO("RE-INIT: %s %s\n", block->version->funcs->name, r?"failed":"successed");
+			DRM_INFO("RE-INIT: %s %s\n", block->version->funcs->name, r?"failed":"succeeded");
 			if (r)
 				return r;
 		}
@@ -2181,7 +2274,7 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
 	case CHIP_VEGA20:
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case CHIP_RAVEN:
 #endif
 		return amdgpu_dc != 0;
@@ -2210,7 +2303,7 @@ bool amdgpu_device_has_dc_support(struct amdgpu_device *adev)
  * amdgpu_device_init - initialize the driver
  *
  * @adev: amdgpu_device pointer
- * @pdev: drm dev pointer
+ * @ddev: drm dev pointer
  * @pdev: pci dev pointer
  * @flags: driver flags
  *
@@ -2301,6 +2394,8 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	INIT_DELAYED_WORK(&adev->late_init_work,
 			  amdgpu_device_ip_late_init_func_handler);
 
+	adev->pm.ac_power = power_supply_is_system_supplied() > 0 ? true : false;
+
 	/* Registers mapping */
 	/* TODO: block userspace mapping of io register */
 	if (adev->asic_type >= CHIP_BONAIRE) {
@@ -2581,8 +2676,9 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 /**
  * amdgpu_device_suspend - initiate device suspend
  *
- * @pdev: drm dev pointer
- * @state: suspend state
+ * @dev: drm dev pointer
+ * @suspend: suspend state
+ * @fbcon : notify the fbdev of suspend
  *
  * Puts the hw in the suspend state (all asics).
  * Returns 0 for success or an error on failure.
@@ -2606,6 +2702,9 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 
 	drm_kms_helper_poll_disable(dev);
 
+	if (fbcon)
+		amdgpu_fbdev_set_suspend(adev, 1);
+
 	if (!amdgpu_device_has_dc_support(adev)) {
 		/* turn off display hw */
 		drm_modeset_lock_all(dev);
@@ -2613,44 +2712,46 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
 		}
 		drm_modeset_unlock_all(dev);
-	}
-
-	amdgpu_amdkfd_suspend(adev);
-
-	/* unpin the front buffers and cursors */
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
-		struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-		struct drm_framebuffer *fb = crtc->primary->fb;
-		struct amdgpu_bo *robj;
-
-		if (amdgpu_crtc->cursor_bo) {
-			struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
-			r = amdgpu_bo_reserve(aobj, true);
-			if (r == 0) {
-				amdgpu_bo_unpin(aobj);
-				amdgpu_bo_unreserve(aobj);
+			/* unpin the front buffers and cursors */
+		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+			struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+			struct drm_framebuffer *fb = crtc->primary->fb;
+			struct amdgpu_bo *robj;
+
+			if (amdgpu_crtc->cursor_bo) {
+				struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
+				r = amdgpu_bo_reserve(aobj, true);
+				if (r == 0) {
+					amdgpu_bo_unpin(aobj);
+					amdgpu_bo_unreserve(aobj);
+				}
 			}
-		}
 
-		if (fb == NULL || fb->obj[0] == NULL) {
-			continue;
-		}
-		robj = gem_to_amdgpu_bo(fb->obj[0]);
-		/* don't unpin kernel fb objects */
-		if (!amdgpu_fbdev_robj_is_fb(adev, robj)) {
-			r = amdgpu_bo_reserve(robj, true);
-			if (r == 0) {
-				amdgpu_bo_unpin(robj);
-				amdgpu_bo_unreserve(robj);
+			if (fb == NULL || fb->obj[0] == NULL) {
+				continue;
+			}
+			robj = gem_to_amdgpu_bo(fb->obj[0]);
+			/* don't unpin kernel fb objects */
+			if (!amdgpu_fbdev_robj_is_fb(adev, robj)) {
+				r = amdgpu_bo_reserve(robj, true);
+				if (r == 0) {
+					amdgpu_bo_unpin(robj);
+					amdgpu_bo_unreserve(robj);
+				}
 			}
 		}
 	}
+
+	amdgpu_amdkfd_suspend(adev);
+
+	r = amdgpu_device_ip_suspend_phase1(adev);
+
 	/* evict vram memory */
 	amdgpu_bo_evict_vram(adev);
 
 	amdgpu_fence_driver_suspend(adev);
 
-	r = amdgpu_device_ip_suspend(adev);
+	r = amdgpu_device_ip_suspend_phase2(adev);
 
 	/* evict remaining vram memory
 	 * This second call to evict vram is to evict the gart page table
@@ -2669,18 +2770,15 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 			DRM_ERROR("amdgpu asic reset failed\n");
 	}
 
-	if (fbcon) {
-		console_lock();
-		amdgpu_fbdev_set_suspend(adev, 1);
-		console_unlock();
-	}
 	return 0;
 }
 
 /**
  * amdgpu_device_resume - initiate device resume
  *
- * @pdev: drm dev pointer
+ * @dev: drm dev pointer
+ * @resume: resume state
+ * @fbcon : notify the fbdev of resume
  *
  * Bring the hw back to operating state (all asics).
  * Returns 0 for success or an error on failure.
@@ -2696,15 +2794,12 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
-	if (fbcon)
-		console_lock();
-
 	if (resume) {
 		pci_set_power_state(dev->pdev, PCI_D0);
 		pci_restore_state(dev->pdev);
 		r = pci_enable_device(dev->pdev);
 		if (r)
-			goto unlock;
+			return r;
 	}
 
 	/* post card */
@@ -2717,29 +2812,30 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 	r = amdgpu_device_ip_resume(adev);
 	if (r) {
 		DRM_ERROR("amdgpu_device_ip_resume failed (%d).\n", r);
-		goto unlock;
+		return r;
 	}
 	amdgpu_fence_driver_resume(adev);
 
 
 	r = amdgpu_device_ip_late_init(adev);
 	if (r)
-		goto unlock;
-
-	/* pin cursors */
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
-		struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-
-		if (amdgpu_crtc->cursor_bo) {
-			struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
-			r = amdgpu_bo_reserve(aobj, true);
-			if (r == 0) {
-				r = amdgpu_bo_pin(aobj,
-						  AMDGPU_GEM_DOMAIN_VRAM,
-						  &amdgpu_crtc->cursor_addr);
-				if (r != 0)
-					DRM_ERROR("Failed to pin cursor BO (%d)\n", r);
-				amdgpu_bo_unreserve(aobj);
+		return r;
+
+	if (!amdgpu_device_has_dc_support(adev)) {
+		/* pin cursors */
+		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+			struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+
+			if (amdgpu_crtc->cursor_bo) {
+				struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
+				r = amdgpu_bo_reserve(aobj, true);
+				if (r == 0) {
+					r = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
+					if (r != 0)
+						DRM_ERROR("Failed to pin cursor BO (%d)\n", r);
+					amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
+					amdgpu_bo_unreserve(aobj);
+				}
 			}
 		}
 	}
@@ -2763,6 +2859,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 			}
 			drm_modeset_unlock_all(dev);
 		}
+		amdgpu_fbdev_set_suspend(adev, 0);
 	}
 
 	drm_kms_helper_poll_enable(dev);
@@ -2786,15 +2883,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 #ifdef CONFIG_PM
 	dev->dev->power.disable_depth--;
 #endif
-
-	if (fbcon)
-		amdgpu_fbdev_set_suspend(adev, 0);
-
-unlock:
-	if (fbcon)
-		console_unlock();
-
-	return r;
+	return 0;
 }
 
 /**
@@ -3019,7 +3108,7 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)
 	long tmo;
 
 	if (amdgpu_sriov_runtime(adev))
-		tmo = msecs_to_jiffies(amdgpu_lockup_timeout);
+		tmo = msecs_to_jiffies(8000);
 	else
 		tmo = msecs_to_jiffies(100);
 
@@ -3071,7 +3160,7 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)
  * @adev: amdgpu device pointer
  *
  * attempt to do soft-reset or full-reset and reinitialize Asic
- * return 0 means successed otherwise failed
+ * return 0 means succeeded otherwise failed
  */
 static int amdgpu_device_reset(struct amdgpu_device *adev)
 {
@@ -3146,9 +3235,10 @@ out:
  * amdgpu_device_reset_sriov - reset ASIC for SR-IOV vf
  *
  * @adev: amdgpu device pointer
+ * @from_hypervisor: request from hypervisor
  *
  * do VF FLR and reinitialize Asic
- * return 0 means successed otherwise failed
+ * return 0 means succeeded otherwise failed
  */
 static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 				     bool from_hypervisor)
@@ -3193,7 +3283,7 @@ error:
  *
  * @adev: amdgpu device pointer
  * @job: which job trigger hang
- * @force forces reset regardless of amdgpu_gpu_recovery
+ * @force: forces reset regardless of amdgpu_gpu_recovery
  *
  * Attempt to reset the GPU if it has hung (all asics).
  * Returns 0 for success or an error on failure.
@@ -3220,6 +3310,9 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	atomic_inc(&adev->gpu_reset_counter);
 	adev->in_gpu_reset = 1;
 
+	/* Block kfd */
+	amdgpu_amdkfd_pre_reset(adev);
+
 	/* block TTM */
 	resched = ttm_bo_lock_delayed_workqueue(&adev->mman.bdev);
 
@@ -3232,10 +3325,10 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
 		kthread_park(ring->sched.thread);
 
-		if (job && job->ring->idx != i)
+		if (job && job->base.sched == &ring->sched)
 			continue;
 
-		drm_sched_hw_job_reset(&ring->sched, &job->base);
+		drm_sched_hw_job_reset(&ring->sched, job ? &job->base : NULL);
 
 		/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
 		amdgpu_fence_driver_force_completion(ring);
@@ -3256,7 +3349,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		 * or all rings (in the case @job is NULL)
 		 * after above amdgpu_reset accomplished
 		 */
-		if ((!job || job->ring->idx == i) && !r)
+		if ((!job || job->base.sched == &ring->sched) && !r)
 			drm_sched_job_recovery(&ring->sched);
 
 		kthread_unpark(ring->sched.thread);
@@ -3273,9 +3366,11 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		dev_info(adev->dev, "GPU reset(%d) failed\n", atomic_read(&adev->gpu_reset_counter));
 		amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0, r);
 	} else {
-		dev_info(adev->dev, "GPU reset(%d) successed!\n",atomic_read(&adev->gpu_reset_counter));
+		dev_info(adev->dev, "GPU reset(%d) succeeded!\n",atomic_read(&adev->gpu_reset_counter));
 	}
 
+	/*unlock kfd */
+	amdgpu_amdkfd_post_reset(adev);
 	amdgpu_vf_error_trans_all(adev);
 	adev->in_gpu_reset = 0;
 	mutex_unlock(&adev->lock_reset);
@@ -3293,8 +3388,9 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
  */
 static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 {
-	u32 mask;
-	int ret;
+	struct pci_dev *pdev;
+	enum pci_bus_speed speed_cap;
+	enum pcie_link_width link_width;
 
 	if (amdgpu_pcie_gen_cap)
 		adev->pm.pcie_gen_mask = amdgpu_pcie_gen_cap;
@@ -3312,27 +3408,61 @@ static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 	}
 
 	if (adev->pm.pcie_gen_mask == 0) {
-		ret = drm_pcie_get_speed_cap_mask(adev->ddev, &mask);
-		if (!ret) {
-			adev->pm.pcie_gen_mask = (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+		/* asic caps */
+		pdev = adev->pdev;
+		speed_cap = pcie_get_speed_cap(pdev);
+		if (speed_cap == PCI_SPEED_UNKNOWN) {
+			adev->pm.pcie_gen_mask |= (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
 						  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 |
 						  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3);
-
-			if (mask & DRM_PCIE_SPEED_25)
-				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1;
-			if (mask & DRM_PCIE_SPEED_50)
-				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2;
-			if (mask & DRM_PCIE_SPEED_80)
-				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3;
 		} else {
-			adev->pm.pcie_gen_mask = AMDGPU_DEFAULT_PCIE_GEN_MASK;
+			if (speed_cap == PCIE_SPEED_16_0GT)
+				adev->pm.pcie_gen_mask |= (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+							  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 |
+							  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3 |
+							  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN4);
+			else if (speed_cap == PCIE_SPEED_8_0GT)
+				adev->pm.pcie_gen_mask |= (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+							  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 |
+							  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3);
+			else if (speed_cap == PCIE_SPEED_5_0GT)
+				adev->pm.pcie_gen_mask |= (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+							  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2);
+			else
+				adev->pm.pcie_gen_mask |= CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1;
+		}
+		/* platform caps */
+		pdev = adev->ddev->pdev->bus->self;
+		speed_cap = pcie_get_speed_cap(pdev);
+		if (speed_cap == PCI_SPEED_UNKNOWN) {
+			adev->pm.pcie_gen_mask |= (CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+						   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2);
+		} else {
+			if (speed_cap == PCIE_SPEED_16_0GT)
+				adev->pm.pcie_gen_mask |= (CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+							   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2 |
+							   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3 |
+							   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4);
+			else if (speed_cap == PCIE_SPEED_8_0GT)
+				adev->pm.pcie_gen_mask |= (CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+							   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2 |
+							   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3);
+			else if (speed_cap == PCIE_SPEED_5_0GT)
+				adev->pm.pcie_gen_mask |= (CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+							   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2);
+			else
+				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1;
+
 		}
 	}
 	if (adev->pm.pcie_mlw_mask == 0) {
-		ret = drm_pcie_get_max_link_width(adev->ddev, &mask);
-		if (!ret) {
-			switch (mask) {
-			case 32:
+		pdev = adev->ddev->pdev->bus->self;
+		link_width = pcie_get_width_cap(pdev);
+		if (link_width == PCIE_LNK_WIDTH_UNKNOWN) {
+			adev->pm.pcie_mlw_mask |= AMDGPU_DEFAULT_PCIE_MLW_MASK;
+		} else {
+			switch (link_width) {
+			case PCIE_LNK_X32:
 				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
@@ -3341,7 +3471,7 @@ static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
-			case 16:
+			case PCIE_LNK_X16:
 				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
@@ -3349,36 +3479,34 @@ static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
-			case 12:
+			case PCIE_LNK_X12:
 				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
-			case 8:
+			case PCIE_LNK_X8:
 				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
-			case 4:
+			case PCIE_LNK_X4:
 				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
-			case 2:
+			case PCIE_LNK_X2:
 				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
-			case 1:
+			case PCIE_LNK_X1:
 				adev->pm.pcie_mlw_mask = CAIL_PCIE_LINK_WIDTH_SUPPORT_X1;
 				break;
 			default:
 				break;
 			}
-		} else {
-			adev->pm.pcie_mlw_mask = AMDGPU_DEFAULT_PCIE_MLW_MASK;
 		}
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 76ee8e04ff11..6748cd7fc129 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -157,7 +157,6 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc,
 	struct amdgpu_bo *new_abo;
 	unsigned long flags;
 	u64 tiling_flags;
-	u64 base;
 	int i, r;
 
 	work = kzalloc(sizeof *work, GFP_KERNEL);
@@ -189,12 +188,18 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc,
 		goto cleanup;
 	}
 
-	r = amdgpu_bo_pin(new_abo, amdgpu_display_supported_domains(adev), &base);
+	r = amdgpu_bo_pin(new_abo, amdgpu_display_supported_domains(adev));
 	if (unlikely(r != 0)) {
 		DRM_ERROR("failed to pin new abo buffer before flip\n");
 		goto unreserve;
 	}
 
+	r = amdgpu_ttm_alloc_gart(&new_abo->tbo);
+	if (unlikely(r != 0)) {
+		DRM_ERROR("%p bind failed\n", new_abo);
+		goto unpin;
+	}
+
 	r = reservation_object_get_fences_rcu(new_abo->tbo.resv, &work->excl,
 					      &work->shared_count,
 					      &work->shared);
@@ -206,7 +211,7 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc,
 	amdgpu_bo_get_tiling_flags(new_abo, &tiling_flags);
 	amdgpu_bo_unreserve(new_abo);
 
-	work->base = base;
+	work->base = amdgpu_bo_gpu_offset(new_abo);
 	work->target_vblank = target - (uint32_t)drm_crtc_vblank_count(crtc) +
 		amdgpu_get_vblank_counter_kms(dev, work->crtc_id);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
index 77ad59ade85c..1c4595562f8f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
@@ -28,6 +28,7 @@
 #include "amdgpu_i2c.h"
 #include "amdgpu_dpm.h"
 #include "atom.h"
+#include "amd_pcie.h"
 
 void amdgpu_dpm_print_class_info(u32 class, u32 class2)
 {
@@ -936,9 +937,11 @@ enum amdgpu_pcie_gen amdgpu_get_pcie_gen_support(struct amdgpu_device *adev,
 	case AMDGPU_PCIE_GEN3:
 		return AMDGPU_PCIE_GEN3;
 	default:
-		if ((sys_mask & DRM_PCIE_SPEED_80) && (default_gen == AMDGPU_PCIE_GEN3))
+		if ((sys_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) &&
+		    (default_gen == AMDGPU_PCIE_GEN3))
 			return AMDGPU_PCIE_GEN3;
-		else if ((sys_mask & DRM_PCIE_SPEED_50) && (default_gen == AMDGPU_PCIE_GEN2))
+		else if ((sys_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2) &&
+			 (default_gen == AMDGPU_PCIE_GEN2))
 			return AMDGPU_PCIE_GEN2;
 		else
 			return AMDGPU_PCIE_GEN1;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
index dd6203a0a6b7..ff24e1cc5b65 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
@@ -287,12 +287,6 @@ enum amdgpu_pcie_gen {
 #define amdgpu_dpm_force_performance_level(adev, l) \
 		((adev)->powerplay.pp_funcs->force_performance_level((adev)->powerplay.pp_handle, (l)))
 
-#define amdgpu_dpm_powergate_uvd(adev, g) \
-		((adev)->powerplay.pp_funcs->powergate_uvd((adev)->powerplay.pp_handle, (g)))
-
-#define amdgpu_dpm_powergate_vce(adev, g) \
-		((adev)->powerplay.pp_funcs->powergate_vce((adev)->powerplay.pp_handle, (g)))
-
 #define amdgpu_dpm_get_current_power_state(adev) \
 		((adev)->powerplay.pp_funcs->get_current_power_state((adev)->powerplay.pp_handle))
 
@@ -347,6 +341,10 @@ enum amdgpu_pcie_gen {
 		((adev)->powerplay.pp_funcs->set_clockgating_by_smu(\
 			(adev)->powerplay.pp_handle, msg_id))
 
+#define amdgpu_dpm_set_powergating_by_smu(adev, block_type, gate) \
+		((adev)->powerplay.pp_funcs->set_powergating_by_smu(\
+			(adev)->powerplay.pp_handle, block_type, gate))
+
 #define amdgpu_dpm_get_power_profile_mode(adev, buf) \
 		((adev)->powerplay.pp_funcs->get_power_profile_mode(\
 			(adev)->powerplay.pp_handle, buf))
@@ -359,10 +357,6 @@ enum amdgpu_pcie_gen {
 		((adev)->powerplay.pp_funcs->odn_edit_dpm_table(\
 			(adev)->powerplay.pp_handle, type, parameter, size))
 
-#define amdgpu_dpm_set_mmhub_powergating_by_smu(adev) \
-		((adev)->powerplay.pp_funcs->set_mmhub_powergating_by_smu( \
-		(adev)->powerplay.pp_handle))
-
 struct amdgpu_dpm {
 	struct amdgpu_ps        *ps;
 	/* number of valid power states */
@@ -402,7 +396,6 @@ struct amdgpu_dpm {
 	u32 tdp_adjustment;
 	u16 load_line_slope;
 	bool power_control;
-	bool ac_power;
 	/* special states active */
 	bool                    thermal_active;
 	bool                    uvd_active;
@@ -439,6 +432,7 @@ struct amdgpu_pm {
 	struct amd_pp_display_configuration pm_display_cfg;/* set by dc */
 	uint32_t                smu_prv_buffer_size;
 	struct amdgpu_bo        *smu_prv_buffer;
+	bool ac_power;
 };
 
 #define R600_SSTU_DFLT                               0
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index b0bf2f24da48..8843a06360fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1,10 +1,3 @@
-/**
- * \file amdgpu_drv.c
- * AMD Amdgpu driver
- *
- * \author Gareth Hughes <gareth@valinux.com>
- */
-
 /*
  * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California.
  * All Rights Reserved.
@@ -76,9 +69,10 @@
  * - 3.24.0 - Add high priority compute support for gfx9
  * - 3.25.0 - Add support for sensor query info (stable pstate sclk/mclk).
  * - 3.26.0 - GFX9: Process AMDGPU_IB_FLAG_TC_WB_NOT_INVALIDATE.
+ * - 3.27.0 - Add new chunk to to AMDGPU_CS to enable BO_LIST creation.
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	26
+#define KMS_DRIVER_MINOR	27
 #define KMS_DRIVER_PATCHLEVEL	0
 
 int amdgpu_vram_limit = 0;
@@ -110,11 +104,8 @@ int amdgpu_vram_page_split = 512;
 int amdgpu_vm_update_mode = -1;
 int amdgpu_exp_hw_support = 0;
 int amdgpu_dc = -1;
-int amdgpu_dc_log = 0;
 int amdgpu_sched_jobs = 32;
 int amdgpu_sched_hw_submission = 2;
-int amdgpu_no_evict = 0;
-int amdgpu_direct_gma_size = 0;
 uint amdgpu_pcie_gen_cap = 0;
 uint amdgpu_pcie_lane_cap = 0;
 uint amdgpu_cg_mask = 0xffffffff;
@@ -122,7 +113,8 @@ uint amdgpu_pg_mask = 0xffffffff;
 uint amdgpu_sdma_phase_quantum = 32;
 char *amdgpu_disable_cu = NULL;
 char *amdgpu_virtual_display = NULL;
-uint amdgpu_pp_feature_mask = 0xffff3fff; /* gfxoff (bit 15) disabled by default */
+/* OverDrive(bit 14),gfxoff(bit 15),stutter mode(bit 17) disabled by default*/
+uint amdgpu_pp_feature_mask = 0xfffd3fff;
 int amdgpu_ngg = 0;
 int amdgpu_prim_buf_per_se = 0;
 int amdgpu_pos_buf_per_se = 0;
@@ -135,163 +127,368 @@ int amdgpu_gpu_recovery = -1; /* auto */
 int amdgpu_emu_mode = 0;
 uint amdgpu_smu_memory_pool_size = 0;
 
+/**
+ * DOC: vramlimit (int)
+ * Restrict the total amount of VRAM in MiB for testing.  The default is 0 (Use full VRAM).
+ */
 MODULE_PARM_DESC(vramlimit, "Restrict VRAM for testing, in megabytes");
 module_param_named(vramlimit, amdgpu_vram_limit, int, 0600);
 
+/**
+ * DOC: vis_vramlimit (int)
+ * Restrict the amount of CPU visible VRAM in MiB for testing.  The default is 0 (Use full CPU visible VRAM).
+ */
 MODULE_PARM_DESC(vis_vramlimit, "Restrict visible VRAM for testing, in megabytes");
 module_param_named(vis_vramlimit, amdgpu_vis_vram_limit, int, 0444);
 
+/**
+ * DOC: gartsize (uint)
+ * Restrict the size of GART in Mib (32, 64, etc.) for testing. The default is -1 (The size depends on asic).
+ */
 MODULE_PARM_DESC(gartsize, "Size of GART to setup in megabytes (32, 64, etc., -1=auto)");
 module_param_named(gartsize, amdgpu_gart_size, uint, 0600);
 
+/**
+ * DOC: gttsize (int)
+ * Restrict the size of GTT domain in MiB for testing. The default is -1 (It's VRAM size if 3GB < VRAM < 3/4 RAM,
+ * otherwise 3/4 RAM size).
+ */
 MODULE_PARM_DESC(gttsize, "Size of the GTT domain in megabytes (-1 = auto)");
 module_param_named(gttsize, amdgpu_gtt_size, int, 0600);
 
+/**
+ * DOC: moverate (int)
+ * Set maximum buffer migration rate in MB/s. The default is -1 (8 MB/s).
+ */
 MODULE_PARM_DESC(moverate, "Maximum buffer migration rate in MB/s. (32, 64, etc., -1=auto, 0=1=disabled)");
 module_param_named(moverate, amdgpu_moverate, int, 0600);
 
+/**
+ * DOC: benchmark (int)
+ * Run benchmarks. The default is 0 (Skip benchmarks).
+ */
 MODULE_PARM_DESC(benchmark, "Run benchmark");
 module_param_named(benchmark, amdgpu_benchmarking, int, 0444);
 
+/**
+ * DOC: test (int)
+ * Test BO GTT->VRAM and VRAM->GTT GPU copies. The default is 0 (Skip test, only set 1 to run test).
+ */
 MODULE_PARM_DESC(test, "Run tests");
 module_param_named(test, amdgpu_testing, int, 0444);
 
+/**
+ * DOC: audio (int)
+ * Set HDMI/DPAudio. Only affects non-DC display handling. The default is -1 (Enabled), set 0 to disabled it.
+ */
 MODULE_PARM_DESC(audio, "Audio enable (-1 = auto, 0 = disable, 1 = enable)");
 module_param_named(audio, amdgpu_audio, int, 0444);
 
+/**
+ * DOC: disp_priority (int)
+ * Set display Priority (1 = normal, 2 = high). Only affects non-DC display handling. The default is 0 (auto).
+ */
 MODULE_PARM_DESC(disp_priority, "Display Priority (0 = auto, 1 = normal, 2 = high)");
 module_param_named(disp_priority, amdgpu_disp_priority, int, 0444);
 
+/**
+ * DOC: hw_i2c (int)
+ * To enable hw i2c engine. Only affects non-DC display handling. The default is 0 (Disabled).
+ */
 MODULE_PARM_DESC(hw_i2c, "hw i2c engine enable (0 = disable)");
 module_param_named(hw_i2c, amdgpu_hw_i2c, int, 0444);
 
+/**
+ * DOC: pcie_gen2 (int)
+ * To disable PCIE Gen2/3 mode (0 = disable, 1 = enable). The default is -1 (auto, enabled).
+ */
 MODULE_PARM_DESC(pcie_gen2, "PCIE Gen2 mode (-1 = auto, 0 = disable, 1 = enable)");
 module_param_named(pcie_gen2, amdgpu_pcie_gen2, int, 0444);
 
+/**
+ * DOC: msi (int)
+ * To disable Message Signaled Interrupts (MSI) functionality (1 = enable, 0 = disable). The default is -1 (auto, enabled).
+ */
 MODULE_PARM_DESC(msi, "MSI support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(msi, amdgpu_msi, int, 0444);
 
+/**
+ * DOC: lockup_timeout (int)
+ * Set GPU scheduler timeout value in ms. Value 0 is invalidated, will be adjusted to 10000.
+ * Negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET). The default is 10000.
+ */
 MODULE_PARM_DESC(lockup_timeout, "GPU lockup timeout in ms > 0 (default 10000)");
 module_param_named(lockup_timeout, amdgpu_lockup_timeout, int, 0444);
 
+/**
+ * DOC: dpm (int)
+ * Override for dynamic power management setting (1 = enable, 0 = disable). The default is -1 (auto).
+ */
 MODULE_PARM_DESC(dpm, "DPM support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(dpm, amdgpu_dpm, int, 0444);
 
+/**
+ * DOC: fw_load_type (int)
+ * Set different firmware loading type for debugging (0 = direct, 1 = SMU, 2 = PSP). The default is -1 (auto).
+ */
 MODULE_PARM_DESC(fw_load_type, "firmware loading type (0 = direct, 1 = SMU, 2 = PSP, -1 = auto)");
 module_param_named(fw_load_type, amdgpu_fw_load_type, int, 0444);
 
+/**
+ * DOC: aspm (int)
+ * To disable ASPM (1 = enable, 0 = disable). The default is -1 (auto, enabled).
+ */
 MODULE_PARM_DESC(aspm, "ASPM support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(aspm, amdgpu_aspm, int, 0444);
 
+/**
+ * DOC: runpm (int)
+ * Override for runtime power management control for dGPUs in PX/HG laptops. The amdgpu driver can dynamically power down
+ * the dGPU on PX/HG laptops when it is idle. The default is -1 (auto enable). Setting the value to 0 disables this functionality.
+ */
 MODULE_PARM_DESC(runpm, "PX runtime pm (1 = force enable, 0 = disable, -1 = PX only default)");
 module_param_named(runpm, amdgpu_runtime_pm, int, 0444);
 
+/**
+ * DOC: ip_block_mask (uint)
+ * Override what IP blocks are enabled on the GPU. Each GPU is a collection of IP blocks (gfx, display, video, etc.).
+ * Use this parameter to disable specific blocks. Note that the IP blocks do not have a fixed index. Some asics may not have
+ * some IPs or may include multiple instances of an IP so the ordering various from asic to asic. See the driver output in
+ * the kernel log for the list of IPs on the asic. The default is 0xffffffff (enable all blocks on a device).
+ */
 MODULE_PARM_DESC(ip_block_mask, "IP Block Mask (all blocks enabled (default))");
 module_param_named(ip_block_mask, amdgpu_ip_block_mask, uint, 0444);
 
+/**
+ * DOC: bapm (int)
+ * Bidirectional Application Power Management (BAPM) used to dynamically share TDP between CPU and GPU. Set value 0 to disable it.
+ * The default -1 (auto, enabled)
+ */
 MODULE_PARM_DESC(bapm, "BAPM support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(bapm, amdgpu_bapm, int, 0444);
 
+/**
+ * DOC: deep_color (int)
+ * Set 1 to enable Deep Color support. Only affects non-DC display handling. The default is 0 (disabled).
+ */
 MODULE_PARM_DESC(deep_color, "Deep Color support (1 = enable, 0 = disable (default))");
 module_param_named(deep_color, amdgpu_deep_color, int, 0444);
 
+/**
+ * DOC: vm_size (int)
+ * Override the size of the GPU's per client virtual address space in GiB.  The default is -1 (automatic for each asic).
+ */
 MODULE_PARM_DESC(vm_size, "VM address space size in gigabytes (default 64GB)");
 module_param_named(vm_size, amdgpu_vm_size, int, 0444);
 
+/**
+ * DOC: vm_fragment_size (int)
+ * Override VM fragment size in bits (4, 5, etc. 4 = 64K, 9 = 2M). The default is -1 (automatic for each asic).
+ */
 MODULE_PARM_DESC(vm_fragment_size, "VM fragment size in bits (4, 5, etc. 4 = 64K (default), Max 9 = 2M)");
 module_param_named(vm_fragment_size, amdgpu_vm_fragment_size, int, 0444);
 
+/**
+ * DOC: vm_block_size (int)
+ * Override VM page table size in bits (default depending on vm_size and hw setup). The default is -1 (automatic for each asic).
+ */
 MODULE_PARM_DESC(vm_block_size, "VM page table size in bits (default depending on vm_size)");
 module_param_named(vm_block_size, amdgpu_vm_block_size, int, 0444);
 
+/**
+ * DOC: vm_fault_stop (int)
+ * Stop on VM fault for debugging (0 = never, 1 = print first, 2 = always). The default is 0 (No stop).
+ */
 MODULE_PARM_DESC(vm_fault_stop, "Stop on VM fault (0 = never (default), 1 = print first, 2 = always)");
 module_param_named(vm_fault_stop, amdgpu_vm_fault_stop, int, 0444);
 
+/**
+ * DOC: vm_debug (int)
+ * Debug VM handling (0 = disabled, 1 = enabled). The default is 0 (Disabled).
+ */
 MODULE_PARM_DESC(vm_debug, "Debug VM handling (0 = disabled (default), 1 = enabled)");
 module_param_named(vm_debug, amdgpu_vm_debug, int, 0644);
 
+/**
+ * DOC: vm_update_mode (int)
+ * Override VM update mode. VM updated by using CPU (0 = never, 1 = Graphics only, 2 = Compute only, 3 = Both). The default
+ * is -1 (Only in large BAR(LB) systems Compute VM tables will be updated by CPU, otherwise 0, never).
+ */
 MODULE_PARM_DESC(vm_update_mode, "VM update using CPU (0 = never (default except for large BAR(LB)), 1 = Graphics only, 2 = Compute only (default for LB), 3 = Both");
 module_param_named(vm_update_mode, amdgpu_vm_update_mode, int, 0444);
 
+/**
+ * DOC: vram_page_split (int)
+ * Override the number of pages after we split VRAM allocations (default 512, -1 = disable). The default is 512.
+ */
 MODULE_PARM_DESC(vram_page_split, "Number of pages after we split VRAM allocations (default 512, -1 = disable)");
 module_param_named(vram_page_split, amdgpu_vram_page_split, int, 0444);
 
+/**
+ * DOC: exp_hw_support (int)
+ * Enable experimental hw support (1 = enable). The default is 0 (disabled).
+ */
 MODULE_PARM_DESC(exp_hw_support, "experimental hw support (1 = enable, 0 = disable (default))");
 module_param_named(exp_hw_support, amdgpu_exp_hw_support, int, 0444);
 
+/**
+ * DOC: dc (int)
+ * Disable/Enable Display Core driver for debugging (1 = enable, 0 = disable). The default is -1 (automatic for each asic).
+ */
 MODULE_PARM_DESC(dc, "Display Core driver (1 = enable, 0 = disable, -1 = auto (default))");
 module_param_named(dc, amdgpu_dc, int, 0444);
 
-MODULE_PARM_DESC(dc_log, "Display Core Log Level (0 = minimal (default), 1 = chatty");
-module_param_named(dc_log, amdgpu_dc_log, int, 0444);
-
+/**
+ * DOC: sched_jobs (int)
+ * Override the max number of jobs supported in the sw queue. The default is 32.
+ */
 MODULE_PARM_DESC(sched_jobs, "the max number of jobs supported in the sw queue (default 32)");
 module_param_named(sched_jobs, amdgpu_sched_jobs, int, 0444);
 
+/**
+ * DOC: sched_hw_submission (int)
+ * Override the max number of HW submissions. The default is 2.
+ */
 MODULE_PARM_DESC(sched_hw_submission, "the max number of HW submissions (default 2)");
 module_param_named(sched_hw_submission, amdgpu_sched_hw_submission, int, 0444);
 
+/**
+ * DOC: ppfeaturemask (uint)
+ * Override power features enabled. See enum PP_FEATURE_MASK in drivers/gpu/drm/amd/include/amd_shared.h.
+ * The default is the current set of stable power features.
+ */
 MODULE_PARM_DESC(ppfeaturemask, "all power features enabled (default))");
 module_param_named(ppfeaturemask, amdgpu_pp_feature_mask, uint, 0444);
 
-MODULE_PARM_DESC(no_evict, "Support pinning request from user space (1 = enable, 0 = disable (default))");
-module_param_named(no_evict, amdgpu_no_evict, int, 0444);
-
-MODULE_PARM_DESC(direct_gma_size, "Direct GMA size in megabytes (max 96MB)");
-module_param_named(direct_gma_size, amdgpu_direct_gma_size, int, 0444);
-
+/**
+ * DOC: pcie_gen_cap (uint)
+ * Override PCIE gen speed capabilities. See the CAIL flags in drivers/gpu/drm/amd/include/amd_pcie.h.
+ * The default is 0 (automatic for each asic).
+ */
 MODULE_PARM_DESC(pcie_gen_cap, "PCIE Gen Caps (0: autodetect (default))");
 module_param_named(pcie_gen_cap, amdgpu_pcie_gen_cap, uint, 0444);
 
+/**
+ * DOC: pcie_lane_cap (uint)
+ * Override PCIE lanes capabilities. See the CAIL flags in drivers/gpu/drm/amd/include/amd_pcie.h.
+ * The default is 0 (automatic for each asic).
+ */
 MODULE_PARM_DESC(pcie_lane_cap, "PCIE Lane Caps (0: autodetect (default))");
 module_param_named(pcie_lane_cap, amdgpu_pcie_lane_cap, uint, 0444);
 
+/**
+ * DOC: cg_mask (uint)
+ * Override Clockgating features enabled on GPU (0 = disable clock gating). See the AMD_CG_SUPPORT flags in
+ * drivers/gpu/drm/amd/include/amd_shared.h. The default is 0xffffffff (all enabled).
+ */
 MODULE_PARM_DESC(cg_mask, "Clockgating flags mask (0 = disable clock gating)");
 module_param_named(cg_mask, amdgpu_cg_mask, uint, 0444);
 
+/**
+ * DOC: pg_mask (uint)
+ * Override Powergating features enabled on GPU (0 = disable power gating). See the AMD_PG_SUPPORT flags in
+ * drivers/gpu/drm/amd/include/amd_shared.h. The default is 0xffffffff (all enabled).
+ */
 MODULE_PARM_DESC(pg_mask, "Powergating flags mask (0 = disable power gating)");
 module_param_named(pg_mask, amdgpu_pg_mask, uint, 0444);
 
+/**
+ * DOC: sdma_phase_quantum (uint)
+ * Override SDMA context switch phase quantum (x 1K GPU clock cycles, 0 = no change). The default is 32.
+ */
 MODULE_PARM_DESC(sdma_phase_quantum, "SDMA context switch phase quantum (x 1K GPU clock cycles, 0 = no change (default 32))");
 module_param_named(sdma_phase_quantum, amdgpu_sdma_phase_quantum, uint, 0444);
 
+/**
+ * DOC: disable_cu (charp)
+ * Set to disable CUs (It's set like se.sh.cu,...). The default is NULL.
+ */
 MODULE_PARM_DESC(disable_cu, "Disable CUs (se.sh.cu,...)");
 module_param_named(disable_cu, amdgpu_disable_cu, charp, 0444);
 
+/**
+ * DOC: virtual_display (charp)
+ * Set to enable virtual display feature. This feature provides a virtual display hardware on headless boards
+ * or in virtualized environments. It will be set like xxxx:xx:xx.x,x;xxxx:xx:xx.x,x. It's the pci address of
+ * the device, plus the number of crtcs to expose. E.g., 0000:26:00.0,4 would enable 4 virtual crtcs on the pci
+ * device at 26:00.0. The default is NULL.
+ */
 MODULE_PARM_DESC(virtual_display,
 		 "Enable virtual display feature (the virtual_display will be set like xxxx:xx:xx.x,x;xxxx:xx:xx.x,x)");
 module_param_named(virtual_display, amdgpu_virtual_display, charp, 0444);
 
+/**
+ * DOC: ngg (int)
+ * Set to enable Next Generation Graphics (1 = enable). The default is 0 (disabled).
+ */
 MODULE_PARM_DESC(ngg, "Next Generation Graphics (1 = enable, 0 = disable(default depending on gfx))");
 module_param_named(ngg, amdgpu_ngg, int, 0444);
 
+/**
+ * DOC: prim_buf_per_se (int)
+ * Override the size of Primitive Buffer per Shader Engine in Byte. The default is 0 (depending on gfx).
+ */
 MODULE_PARM_DESC(prim_buf_per_se, "the size of Primitive Buffer per Shader Engine (default depending on gfx)");
 module_param_named(prim_buf_per_se, amdgpu_prim_buf_per_se, int, 0444);
 
+/**
+ * DOC: pos_buf_per_se (int)
+ * Override the size of Position Buffer per Shader Engine in Byte. The default is 0 (depending on gfx).
+ */
 MODULE_PARM_DESC(pos_buf_per_se, "the size of Position Buffer per Shader Engine (default depending on gfx)");
 module_param_named(pos_buf_per_se, amdgpu_pos_buf_per_se, int, 0444);
 
+/**
+ * DOC: cntl_sb_buf_per_se (int)
+ * Override the size of Control Sideband per Shader Engine in Byte. The default is 0 (depending on gfx).
+ */
 MODULE_PARM_DESC(cntl_sb_buf_per_se, "the size of Control Sideband per Shader Engine (default depending on gfx)");
 module_param_named(cntl_sb_buf_per_se, amdgpu_cntl_sb_buf_per_se, int, 0444);
 
+/**
+ * DOC: param_buf_per_se (int)
+ * Override the size of Off-Chip Pramater Cache per Shader Engine in Byte. The default is 0 (depending on gfx).
+ */
 MODULE_PARM_DESC(param_buf_per_se, "the size of Off-Chip Pramater Cache per Shader Engine (default depending on gfx)");
 module_param_named(param_buf_per_se, amdgpu_param_buf_per_se, int, 0444);
 
+/**
+ * DOC: job_hang_limit (int)
+ * Set how much time allow a job hang and not drop it. The default is 0.
+ */
 MODULE_PARM_DESC(job_hang_limit, "how much time allow a job hang and not drop it (default 0)");
 module_param_named(job_hang_limit, amdgpu_job_hang_limit, int ,0444);
 
+/**
+ * DOC: lbpw (int)
+ * Override Load Balancing Per Watt (LBPW) support (1 = enable, 0 = disable). The default is -1 (auto, enabled).
+ */
 MODULE_PARM_DESC(lbpw, "Load Balancing Per Watt (LBPW) support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(lbpw, amdgpu_lbpw, int, 0444);
 
 MODULE_PARM_DESC(compute_multipipe, "Force compute queues to be spread across pipes (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(compute_multipipe, amdgpu_compute_multipipe, int, 0444);
 
+/**
+ * DOC: gpu_recovery (int)
+ * Set to enable GPU recovery mechanism (1 = enable, 0 = disable). The default is -1 (auto, disabled except SRIOV).
+ */
 MODULE_PARM_DESC(gpu_recovery, "Enable GPU recovery mechanism, (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(gpu_recovery, amdgpu_gpu_recovery, int, 0444);
 
+/**
+ * DOC: emu_mode (int)
+ * Set value 1 to enable emulation mode. This is only needed when running on an emulator. The default is 0 (disabled).
+ */
 MODULE_PARM_DESC(emu_mode, "Emulation mode, (1 = enable, 0 = disable)");
 module_param_named(emu_mode, amdgpu_emu_mode, int, 0444);
 
+/**
+ * DOC: si_support (int)
+ * Set SI support driver. This parameter works after set config CONFIG_DRM_AMDGPU_SI. For SI asic, when radeon driver is enabled,
+ * set value 0 to use radeon driver, while set value 1 to use amdgpu driver. The default is using radeon driver when it available,
+ * otherwise using amdgpu driver.
+ */
 #ifdef CONFIG_DRM_AMDGPU_SI
 
 #if defined(CONFIG_DRM_RADEON) || defined(CONFIG_DRM_RADEON_MODULE)
@@ -305,6 +502,12 @@ MODULE_PARM_DESC(si_support, "SI support (1 = enabled (default), 0 = disabled)")
 module_param_named(si_support, amdgpu_si_support, int, 0444);
 #endif
 
+/**
+ * DOC: cik_support (int)
+ * Set CIK support driver. This parameter works after set config CONFIG_DRM_AMDGPU_CIK. For CIK asic, when radeon driver is enabled,
+ * set value 0 to use radeon driver, while set value 1 to use amdgpu driver. The default is using radeon driver when it available,
+ * otherwise using amdgpu driver.
+ */
 #ifdef CONFIG_DRM_AMDGPU_CIK
 
 #if defined(CONFIG_DRM_RADEON) || defined(CONFIG_DRM_RADEON_MODULE)
@@ -318,6 +521,11 @@ MODULE_PARM_DESC(cik_support, "CIK support (1 = enabled (default), 0 = disabled)
 module_param_named(cik_support, amdgpu_cik_support, int, 0444);
 #endif
 
+/**
+ * DOC: smu_memory_pool_size (uint)
+ * It is used to reserve gtt for smu debug usage, setting value 0 to disable it. The actual size is value * 256MiB.
+ * E.g. 0x1 = 256Mbyte, 0x2 = 512Mbyte, 0x4 = 1 Gbyte, 0x8 = 2GByte. The default is 0 (disabled).
+ */
 MODULE_PARM_DESC(smu_memory_pool_size,
 	"reserve gtt for smu debug usage, 0 = disable,"
 		"0x1 = 256Mbyte, 0x2 = 512Mbyte, 0x4 = 1 Gbyte, 0x8 = 2GByte");
@@ -664,7 +872,7 @@ retry_init:
 err_pci:
 	pci_disable_device(pdev);
 err_free:
-	drm_dev_unref(dev);
+	drm_dev_put(dev);
 	return ret;
 }
 
@@ -674,7 +882,7 @@ amdgpu_pci_remove(struct pci_dev *pdev)
 	struct drm_device *dev = pci_get_drvdata(pdev);
 
 	drm_dev_unregister(dev);
-	drm_dev_unref(dev);
+	drm_dev_put(dev);
 	pci_disable_device(pdev);
 	pci_set_drvdata(pdev, NULL);
 }
@@ -855,9 +1063,21 @@ static const struct dev_pm_ops amdgpu_pm_ops = {
 	.runtime_idle = amdgpu_pmops_runtime_idle,
 };
 
+static int amdgpu_flush(struct file *f, fl_owner_t id)
+{
+	struct drm_file *file_priv = f->private_data;
+	struct amdgpu_fpriv *fpriv = file_priv->driver_priv;
+
+	amdgpu_ctx_mgr_entity_flush(&fpriv->ctx_mgr);
+
+	return 0;
+}
+
+
 static const struct file_operations amdgpu_driver_kms_fops = {
 	.owner = THIS_MODULE,
 	.open = drm_open,
+	.flush = amdgpu_flush,
 	.release = drm_release,
 	.unlocked_ioctl = amdgpu_drm_ioctl,
 	.mmap = amdgpu_mmap,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c
index 94138abe093b..ae8fac34f7a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c
@@ -46,7 +46,7 @@ amdgpu_link_encoder_connector(struct drm_device *dev)
 		list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
 			amdgpu_encoder = to_amdgpu_encoder(encoder);
 			if (amdgpu_encoder->devices & amdgpu_connector->devices) {
-				drm_mode_connector_attach_encoder(connector, encoder);
+				drm_connector_attach_encoder(connector, encoder);
 				if (amdgpu_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) {
 					amdgpu_atombios_encoder_init_backlight(amdgpu_encoder, connector);
 					adev->mode_info.bl_encoder = amdgpu_encoder;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index bc5fd8ebab5d..69c5d22f29bd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -146,7 +146,7 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev,
 				       AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
 				       AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS |
 				       AMDGPU_GEM_CREATE_VRAM_CLEARED,
-				       true, NULL, &gobj);
+				       ttm_bo_type_kernel, NULL, &gobj);
 	if (ret) {
 		pr_err("failed to allocate framebuffer (%d)\n", aligned_size);
 		return -ENOMEM;
@@ -168,11 +168,19 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev,
 	}
 
 
-	ret = amdgpu_bo_pin(abo, domain, NULL);
+	ret = amdgpu_bo_pin(abo, domain);
 	if (ret) {
 		amdgpu_bo_unreserve(abo);
 		goto out_unref;
 	}
+
+	ret = amdgpu_ttm_alloc_gart(&abo->tbo);
+	if (ret) {
+		amdgpu_bo_unreserve(abo);
+		dev_err(adev->dev, "%p bind failed\n", abo);
+		goto out_unref;
+	}
+
 	ret = amdgpu_bo_kmap(abo, NULL);
 	amdgpu_bo_unreserve(abo);
 	if (ret) {
@@ -365,8 +373,8 @@ void amdgpu_fbdev_fini(struct amdgpu_device *adev)
 void amdgpu_fbdev_set_suspend(struct amdgpu_device *adev, int state)
 {
 	if (adev->mode_info.rfbdev)
-		drm_fb_helper_set_suspend(&adev->mode_info.rfbdev->helper,
-			state);
+		drm_fb_helper_set_suspend_unlocked(&adev->mode_info.rfbdev->helper,
+						   state);
 }
 
 int amdgpu_fbdev_total_size(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index e74d620d9699..7056925eb386 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -646,7 +646,6 @@ static const struct dma_fence_ops amdgpu_fence_ops = {
 	.get_driver_name = amdgpu_fence_get_driver_name,
 	.get_timeline_name = amdgpu_fence_get_timeline_name,
 	.enable_signaling = amdgpu_fence_enable_signaling,
-	.wait = dma_fence_default_wait,
 	.release = amdgpu_fence_release,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index dd11b7313ca0..a54d5655a191 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -143,14 +143,12 @@ int amdgpu_gart_table_vram_alloc(struct amdgpu_device *adev)
  */
 int amdgpu_gart_table_vram_pin(struct amdgpu_device *adev)
 {
-	uint64_t gpu_addr;
 	int r;
 
 	r = amdgpu_bo_reserve(adev->gart.robj, false);
 	if (unlikely(r != 0))
 		return r;
-	r = amdgpu_bo_pin(adev->gart.robj,
-				AMDGPU_GEM_DOMAIN_VRAM, &gpu_addr);
+	r = amdgpu_bo_pin(adev->gart.robj, AMDGPU_GEM_DOMAIN_VRAM);
 	if (r) {
 		amdgpu_bo_unreserve(adev->gart.robj);
 		return r;
@@ -159,7 +157,7 @@ int amdgpu_gart_table_vram_pin(struct amdgpu_device *adev)
 	if (r)
 		amdgpu_bo_unpin(adev->gart.robj);
 	amdgpu_bo_unreserve(adev->gart.robj);
-	adev->gart.table_addr = gpu_addr;
+	adev->gart.table_addr = amdgpu_bo_gpu_offset(adev->gart.robj);
 	return r;
 }
 
@@ -234,7 +232,7 @@ int amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
 	}
 
 	t = offset / AMDGPU_GPU_PAGE_SIZE;
-	p = t / (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+	p = t / AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 	for (i = 0; i < pages; i++, p++) {
 #ifdef CONFIG_DRM_AMDGPU_GART_DEBUGFS
 		adev->gart.pages[p] = NULL;
@@ -243,7 +241,7 @@ int amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
 		if (!adev->gart.ptr)
 			continue;
 
-		for (j = 0; j < (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE); j++, t++) {
+		for (j = 0; j < AMDGPU_GPU_PAGES_IN_CPU_PAGE; j++, t++) {
 			amdgpu_gmc_set_pte_pde(adev, adev->gart.ptr,
 					       t, page_base, flags);
 			page_base += AMDGPU_GPU_PAGE_SIZE;
@@ -282,7 +280,7 @@ int amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset,
 
 	for (i = 0; i < pages; i++) {
 		page_base = dma_addr[i];
-		for (j = 0; j < (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE); j++, t++) {
+		for (j = 0; j < AMDGPU_GPU_PAGES_IN_CPU_PAGE; j++, t++) {
 			amdgpu_gmc_set_pte_pde(adev, dst, t, page_base, flags);
 			page_base += AMDGPU_GPU_PAGE_SIZE;
 		}
@@ -319,7 +317,7 @@ int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
 
 #ifdef CONFIG_DRM_AMDGPU_GART_DEBUGFS
 	t = offset / AMDGPU_GPU_PAGE_SIZE;
-	p = t / (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+	p = t / AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 	for (i = 0; i < pages; i++, p++)
 		adev->gart.pages[p] = pagelist ? pagelist[i] : NULL;
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
index 456295c00291..9f9e9dc87da1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
@@ -37,6 +37,8 @@ struct amdgpu_bo;
 #define AMDGPU_GPU_PAGE_SHIFT 12
 #define AMDGPU_GPU_PAGE_ALIGN(a) (((a) + AMDGPU_GPU_PAGE_MASK) & ~AMDGPU_GPU_PAGE_MASK)
 
+#define AMDGPU_GPU_PAGES_IN_CPU_PAGE (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE)
+
 struct amdgpu_gart {
 	u64				table_addr;
 	struct amdgpu_bo		*robj;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 5fb156a01774..71792d820ae0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -265,7 +265,7 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
 
 	r = amdgpu_gem_object_create(adev, size, args->in.alignment,
 				     (u32)(0xffffffff & args->in.domains),
-				     flags, false, resv, &gobj);
+				     flags, ttm_bo_type_device, resv, &gobj);
 	if (flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID) {
 		if (!r) {
 			struct amdgpu_bo *abo = gem_to_amdgpu_bo(gobj);
@@ -317,7 +317,7 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
 
 	/* create a gem object to contain this object in */
 	r = amdgpu_gem_object_create(adev, args->size, 0, AMDGPU_GEM_DOMAIN_CPU,
-				     0, 0, NULL, &gobj);
+				     0, ttm_bo_type_device, NULL, &gobj);
 	if (r)
 		return r;
 
@@ -344,7 +344,7 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
 		if (r)
 			goto free_pages;
 
-		amdgpu_ttm_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
+		amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
 		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		amdgpu_bo_unreserve(bo);
 		if (r)
@@ -510,7 +510,6 @@ out:
  * @adev: amdgpu_device pointer
  * @vm: vm to update
  * @bo_va: bo_va to update
- * @list: validation list
  * @operation: map, unmap or clear
  *
  * Update the bo_va directly after setting its address. Errors are not
@@ -519,7 +518,6 @@ out:
 static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
 				    struct amdgpu_vm *vm,
 				    struct amdgpu_bo_va *bo_va,
-				    struct list_head *list,
 				    uint32_t operation)
 {
 	int r;
@@ -612,7 +610,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 			return -ENOENT;
 		abo = gem_to_amdgpu_bo(gobj);
 		tv.bo = &abo->tbo;
-		tv.shared = false;
+		tv.shared = !!(abo->flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID);
 		list_add(&tv.head, &list);
 	} else {
 		gobj = NULL;
@@ -673,7 +671,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 		break;
 	}
 	if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE) && !amdgpu_vm_debug)
-		amdgpu_gem_va_update_vm(adev, &fpriv->vm, bo_va, &list,
+		amdgpu_gem_va_update_vm(adev, &fpriv->vm, bo_va,
 					args->operation);
 
 error_backoff:
@@ -768,7 +766,7 @@ int amdgpu_mode_dumb_create(struct drm_file *file_priv,
 				amdgpu_display_supported_domains(adev));
 	r = amdgpu_gem_object_create(adev, args->size, 0, domain,
 				     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-				     false, NULL, &gobj);
+				     ttm_bo_type_device, NULL, &gobj);
 	if (r)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index 893c2490b783..bb5a47a45790 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -105,8 +105,25 @@ struct amdgpu_gmc {
 	/* protects concurrent invalidation */
 	spinlock_t		invalidate_lock;
 	bool			translate_further;
+	struct kfd_vm_fault_info *vm_fault_info;
+	atomic_t		vm_fault_info_updated;
 
 	const struct amdgpu_gmc_funcs	*gmc_funcs;
 };
 
+/**
+ * amdgpu_gmc_vram_full_visible - Check if full VRAM is visible through the BAR
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Returns:
+ * True if full VRAM is visible through the BAR
+ */
+static inline bool amdgpu_gmc_vram_full_visible(struct amdgpu_gmc *gmc)
+{
+	WARN_ON(gmc->real_vram_size < gmc->visible_vram_size);
+
+	return (gmc->real_vram_size == gmc->visible_vram_size);
+}
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 7aaa263ad8c7..5518e623fed2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -139,7 +139,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	/* ring tests don't use a job */
 	if (job) {
 		vm = job->vm;
-		fence_ctx = job->fence_ctx;
+		fence_ctx = job->base.s_fence->scheduled.context;
 	} else {
 		vm = NULL;
 		fence_ctx = 0;
@@ -353,7 +353,8 @@ int amdgpu_ib_ring_tests(struct amdgpu_device *adev)
 			ring->funcs->type == AMDGPU_RING_TYPE_VCE ||
 			ring->funcs->type == AMDGPU_RING_TYPE_UVD_ENC ||
 			ring->funcs->type == AMDGPU_RING_TYPE_VCN_DEC ||
-			ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC)
+			ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC ||
+			ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG)
 			tmo = tmo_mm;
 		else
 			tmo = tmo_gfx;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index a1c78f90eadf..3a072a7a39f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -578,11 +578,6 @@ void amdgpu_vmid_mgr_init(struct amdgpu_device *adev)
 			list_add_tail(&id_mgr->ids[j].list, &id_mgr->ids_lru);
 		}
 	}
-
-	adev->vm_manager.fence_context =
-		dma_fence_context_alloc(AMDGPU_MAX_RINGS);
-	for (i = 0; i < AMDGPU_MAX_RINGS; ++i)
-		adev->vm_manager.seqno[i] = 0;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 3a5ca462abf0..1abf5b5bac9e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -25,6 +25,23 @@
  *          Alex Deucher
  *          Jerome Glisse
  */
+
+/**
+ * DOC: Interrupt Handling
+ *
+ * Interrupts generated within GPU hardware raise interrupt requests that are
+ * passed to amdgpu IRQ handler which is responsible for detecting source and
+ * type of the interrupt and dispatching matching handlers. If handling an
+ * interrupt requires calling kernel functions that may sleep processing is
+ * dispatched to work handlers.
+ *
+ * If MSI functionality is not disabled by module parameter then MSI
+ * support will be enabled.
+ *
+ * For GPU interrupt sources that may be driven by another driver, IRQ domain
+ * support is used (with mapping between virtual and hardware IRQs).
+ */
+
 #include <linux/irq.h>
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
@@ -43,19 +60,21 @@
 
 #define AMDGPU_WAIT_IDLE_TIMEOUT 200
 
-/*
- * Handle hotplug events outside the interrupt handler proper.
- */
 /**
- * amdgpu_hotplug_work_func - display hotplug work handler
+ * amdgpu_hotplug_work_func - work handler for display hotplug event
  *
- * @work: work struct
+ * @work: work struct pointer
  *
- * This is the hot plug event work handler (all asics).
- * The work gets scheduled from the irq handler if there
- * was a hot plug interrupt.  It walks the connector table
- * and calls the hotplug handler for each one, then sends
- * a drm hotplug event to alert userspace.
+ * This is the hotplug event work handler (all ASICs).
+ * The work gets scheduled from the IRQ handler if there
+ * was a hotplug interrupt.  It walks through the connector table
+ * and calls hotplug handler for each connector. After this, it sends
+ * a DRM hotplug event to alert userspace.
+ *
+ * This design approach is required in order to defer hotplug event handling
+ * from the IRQ handler to a work handler because hotplug handler has to use
+ * mutexes which cannot be locked in an IRQ handler (since &mutex_lock may
+ * sleep).
  */
 static void amdgpu_hotplug_work_func(struct work_struct *work)
 {
@@ -74,13 +93,12 @@ static void amdgpu_hotplug_work_func(struct work_struct *work)
 }
 
 /**
- * amdgpu_irq_reset_work_func - execute gpu reset
+ * amdgpu_irq_reset_work_func - execute GPU reset
  *
- * @work: work struct
+ * @work: work struct pointer
  *
- * Execute scheduled gpu reset (cayman+).
- * This function is called when the irq handler
- * thinks we need a gpu reset.
+ * Execute scheduled GPU reset (Cayman+).
+ * This function is called when the IRQ handler thinks we need a GPU reset.
  */
 static void amdgpu_irq_reset_work_func(struct work_struct *work)
 {
@@ -91,7 +109,13 @@ static void amdgpu_irq_reset_work_func(struct work_struct *work)
 		amdgpu_device_gpu_recover(adev, NULL, false);
 }
 
-/* Disable *all* interrupts */
+/**
+ * amdgpu_irq_disable_all - disable *all* interrupts
+ *
+ * @adev: amdgpu device pointer
+ *
+ * Disable all types of interrupts from all sources.
+ */
 void amdgpu_irq_disable_all(struct amdgpu_device *adev)
 {
 	unsigned long irqflags;
@@ -123,11 +147,15 @@ void amdgpu_irq_disable_all(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_irq_handler - irq handler
+ * amdgpu_irq_handler - IRQ handler
+ *
+ * @irq: IRQ number (unused)
+ * @arg: pointer to DRM device
  *
- * @int irq, void *arg: args
+ * IRQ handler for amdgpu driver (all ASICs).
  *
- * This is the irq handler for the amdgpu driver (all asics).
+ * Returns:
+ * result of handling the IRQ, as defined by &irqreturn_t
  */
 irqreturn_t amdgpu_irq_handler(int irq, void *arg)
 {
@@ -142,18 +170,18 @@ irqreturn_t amdgpu_irq_handler(int irq, void *arg)
 }
 
 /**
- * amdgpu_msi_ok - asic specific msi checks
+ * amdgpu_msi_ok - check whether MSI functionality is enabled
  *
- * @adev: amdgpu device pointer
+ * @adev: amdgpu device pointer (unused)
+ *
+ * Checks whether MSI functionality has been disabled via module parameter
+ * (all ASICs).
  *
- * Handles asic specific MSI checks to determine if
- * MSIs should be enabled on a particular chip (all asics).
- * Returns true if MSIs should be enabled, false if MSIs
- * should not be enabled.
+ * Returns:
+ * *true* if MSIs are allowed to be enabled or *false* otherwise
  */
 static bool amdgpu_msi_ok(struct amdgpu_device *adev)
 {
-	/* force MSI on */
 	if (amdgpu_msi == 1)
 		return true;
 	else if (amdgpu_msi == 0)
@@ -163,12 +191,15 @@ static bool amdgpu_msi_ok(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_irq_init - init driver interrupt info
+ * amdgpu_irq_init - initialize interrupt handling
  *
  * @adev: amdgpu device pointer
  *
- * Sets up the work irq handlers, vblank init, MSIs, etc. (all asics).
- * Returns 0 for success, error for failure.
+ * Sets up work functions for hotplug and reset interrupts, enables MSI
+ * functionality, initializes vblank, hotplug and reset interrupt handling.
+ *
+ * Returns:
+ * 0 on success or error code on failure
  */
 int amdgpu_irq_init(struct amdgpu_device *adev)
 {
@@ -176,7 +207,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 
 	spin_lock_init(&adev->irq.lock);
 
-	/* enable msi */
+	/* Enable MSI if not disabled by module parameter */
 	adev->irq.msi_enabled = false;
 
 	if (amdgpu_msi_ok(adev)) {
@@ -189,7 +220,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 
 	if (!amdgpu_device_has_dc_support(adev)) {
 		if (!adev->enable_virtual_display)
-			/* Disable vblank irqs aggressively for power-saving */
+			/* Disable vblank IRQs aggressively for power-saving */
 			/* XXX: can this be enabled for DC? */
 			adev->ddev->vblank_disable_immediate = true;
 
@@ -197,7 +228,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 		if (r)
 			return r;
 
-		/* pre DCE11 */
+		/* Pre-DCE11 */
 		INIT_WORK(&adev->hotplug_work,
 				amdgpu_hotplug_work_func);
 	}
@@ -220,11 +251,13 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_irq_fini - tear down driver interrupt info
+ * amdgpu_irq_fini - shut down interrupt handling
  *
  * @adev: amdgpu device pointer
  *
- * Tears down the work irq handlers, vblank handlers, MSIs, etc. (all asics).
+ * Tears down work functions for hotplug and reset interrupts, disables MSI
+ * functionality, shuts down vblank, hotplug and reset interrupt handling,
+ * turns off interrupts from all sources (all ASICs).
  */
 void amdgpu_irq_fini(struct amdgpu_device *adev)
 {
@@ -264,12 +297,17 @@ void amdgpu_irq_fini(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_irq_add_id - register irq source
+ * amdgpu_irq_add_id - register IRQ source
  *
  * @adev: amdgpu device pointer
- * @src_id: source id for this source
- * @source: irq source
+ * @client_id: client id
+ * @src_id: source id
+ * @source: IRQ source pointer
+ *
+ * Registers IRQ source on a client.
  *
+ * Returns:
+ * 0 on success or error code otherwise
  */
 int amdgpu_irq_add_id(struct amdgpu_device *adev,
 		      unsigned client_id, unsigned src_id,
@@ -312,12 +350,12 @@ int amdgpu_irq_add_id(struct amdgpu_device *adev,
 }
 
 /**
- * amdgpu_irq_dispatch - dispatch irq to IP blocks
+ * amdgpu_irq_dispatch - dispatch IRQ to IP blocks
  *
  * @adev: amdgpu device pointer
- * @entry: interrupt vector
+ * @entry: interrupt vector pointer
  *
- * Dispatches the irq to the different IP blocks
+ * Dispatches IRQ to IP blocks.
  */
 void amdgpu_irq_dispatch(struct amdgpu_device *adev,
 			 struct amdgpu_iv_entry *entry)
@@ -361,13 +399,13 @@ void amdgpu_irq_dispatch(struct amdgpu_device *adev,
 }
 
 /**
- * amdgpu_irq_update - update hw interrupt state
+ * amdgpu_irq_update - update hardware interrupt state
  *
  * @adev: amdgpu device pointer
- * @src: interrupt src you want to enable
- * @type: type of interrupt you want to update
+ * @src: interrupt source pointer
+ * @type: type of interrupt
  *
- * Updates the interrupt state for a specific src (all asics).
+ * Updates interrupt state for the specific source (all ASICs).
  */
 int amdgpu_irq_update(struct amdgpu_device *adev,
 			     struct amdgpu_irq_src *src, unsigned type)
@@ -378,7 +416,7 @@ int amdgpu_irq_update(struct amdgpu_device *adev,
 
 	spin_lock_irqsave(&adev->irq.lock, irqflags);
 
-	/* we need to determine after taking the lock, otherwise
+	/* We need to determine after taking the lock, otherwise
 	   we might disable just enabled interrupts again */
 	if (amdgpu_irq_enabled(adev, src, type))
 		state = AMDGPU_IRQ_STATE_ENABLE;
@@ -390,6 +428,14 @@ int amdgpu_irq_update(struct amdgpu_device *adev,
 	return r;
 }
 
+/**
+ * amdgpu_irq_gpu_reset_resume_helper - update interrupt states on all sources
+ *
+ * @adev: amdgpu device pointer
+ *
+ * Updates state of all types of interrupts on all sources on resume after
+ * reset.
+ */
 void amdgpu_irq_gpu_reset_resume_helper(struct amdgpu_device *adev)
 {
 	int i, j, k;
@@ -413,10 +459,13 @@ void amdgpu_irq_gpu_reset_resume_helper(struct amdgpu_device *adev)
  * amdgpu_irq_get - enable interrupt
  *
  * @adev: amdgpu device pointer
- * @src: interrupt src you want to enable
- * @type: type of interrupt you want to enable
+ * @src: interrupt source pointer
+ * @type: type of interrupt
  *
- * Enables the interrupt type for a specific src (all asics).
+ * Enables specified type of interrupt on the specified source (all ASICs).
+ *
+ * Returns:
+ * 0 on success or error code otherwise
  */
 int amdgpu_irq_get(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 		   unsigned type)
@@ -440,10 +489,13 @@ int amdgpu_irq_get(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
  * amdgpu_irq_put - disable interrupt
  *
  * @adev: amdgpu device pointer
- * @src: interrupt src you want to disable
- * @type: type of interrupt you want to disable
+ * @src: interrupt source pointer
+ * @type: type of interrupt
+ *
+ * Enables specified type of interrupt on the specified source (all ASICs).
  *
- * Disables the interrupt type for a specific src (all asics).
+ * Returns:
+ * 0 on success or error code otherwise
  */
 int amdgpu_irq_put(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 		   unsigned type)
@@ -464,12 +516,17 @@ int amdgpu_irq_put(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 }
 
 /**
- * amdgpu_irq_enabled - test if irq is enabled or not
+ * amdgpu_irq_enabled - check whether interrupt is enabled or not
  *
  * @adev: amdgpu device pointer
- * @idx: interrupt src you want to test
+ * @src: interrupt source pointer
+ * @type: type of interrupt
  *
- * Tests if the given interrupt source is enabled or not
+ * Checks whether the given type of interrupt is enabled on the given source.
+ *
+ * Returns:
+ * *true* if interrupt is enabled, *false* if interrupt is disabled or on
+ * invalid parameters
  */
 bool amdgpu_irq_enabled(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 			unsigned type)
@@ -486,7 +543,7 @@ bool amdgpu_irq_enabled(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 	return !!atomic_read(&src->enabled_types[type]);
 }
 
-/* gen irq */
+/* XXX: Generic IRQ handling */
 static void amdgpu_irq_mask(struct irq_data *irqd)
 {
 	/* XXX */
@@ -497,12 +554,26 @@ static void amdgpu_irq_unmask(struct irq_data *irqd)
 	/* XXX */
 }
 
+/* amdgpu hardware interrupt chip descriptor */
 static struct irq_chip amdgpu_irq_chip = {
 	.name = "amdgpu-ih",
 	.irq_mask = amdgpu_irq_mask,
 	.irq_unmask = amdgpu_irq_unmask,
 };
 
+/**
+ * amdgpu_irqdomain_map - create mapping between virtual and hardware IRQ numbers
+ *
+ * @d: amdgpu IRQ domain pointer (unused)
+ * @irq: virtual IRQ number
+ * @hwirq: hardware irq number
+ *
+ * Current implementation assigns simple interrupt handler to the given virtual
+ * IRQ.
+ *
+ * Returns:
+ * 0 on success or error code otherwise
+ */
 static int amdgpu_irqdomain_map(struct irq_domain *d,
 				unsigned int irq, irq_hw_number_t hwirq)
 {
@@ -514,17 +585,21 @@ static int amdgpu_irqdomain_map(struct irq_domain *d,
 	return 0;
 }
 
+/* Implementation of methods for amdgpu IRQ domain */
 static const struct irq_domain_ops amdgpu_hw_irqdomain_ops = {
 	.map = amdgpu_irqdomain_map,
 };
 
 /**
- * amdgpu_irq_add_domain - create a linear irq domain
+ * amdgpu_irq_add_domain - create a linear IRQ domain
  *
  * @adev: amdgpu device pointer
  *
- * Create an irq domain for GPU interrupt sources
+ * Creates an IRQ domain for GPU interrupt sources
  * that may be driven by another driver (e.g., ACP).
+ *
+ * Returns:
+ * 0 on success or error code otherwise
  */
 int amdgpu_irq_add_domain(struct amdgpu_device *adev)
 {
@@ -539,11 +614,11 @@ int amdgpu_irq_add_domain(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_irq_remove_domain - remove the irq domain
+ * amdgpu_irq_remove_domain - remove the IRQ domain
  *
  * @adev: amdgpu device pointer
  *
- * Remove the irq domain for GPU interrupt sources
+ * Removes the IRQ domain for GPU interrupt sources
  * that may be driven by another driver (e.g., ACP).
  */
 void amdgpu_irq_remove_domain(struct amdgpu_device *adev)
@@ -555,16 +630,17 @@ void amdgpu_irq_remove_domain(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_irq_create_mapping - create a mapping between a domain irq and a
- *                             Linux irq
+ * amdgpu_irq_create_mapping - create mapping between domain Linux IRQs
  *
  * @adev: amdgpu device pointer
  * @src_id: IH source id
  *
- * Create a mapping between a domain irq (GPU IH src id) and a Linux irq
+ * Creates mapping between a domain IRQ (GPU IH src id) and a Linux IRQ
  * Use this for components that generate a GPU interrupt, but are driven
  * by a different driver (e.g., ACP).
- * Returns the Linux irq.
+ *
+ * Returns:
+ * Linux IRQ
  */
 unsigned amdgpu_irq_create_mapping(struct amdgpu_device *adev, unsigned src_id)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 2bd56760c744..391e2f7c03aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -30,14 +30,14 @@
 
 static void amdgpu_job_timedout(struct drm_sched_job *s_job)
 {
-	struct amdgpu_job *job = container_of(s_job, struct amdgpu_job, base);
+	struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched);
+	struct amdgpu_job *job = to_amdgpu_job(s_job);
 
-	DRM_ERROR("ring %s timeout, last signaled seq=%u, last emitted seq=%u\n",
-		  job->base.sched->name,
-		  atomic_read(&job->ring->fence_drv.last_seq),
-		  job->ring->fence_drv.sync_seq);
+	DRM_ERROR("ring %s timeout, signaled seq=%u, emitted seq=%u\n",
+		  job->base.sched->name, atomic_read(&ring->fence_drv.last_seq),
+		  ring->fence_drv.sync_seq);
 
-	amdgpu_device_gpu_recover(job->adev, job, false);
+	amdgpu_device_gpu_recover(ring->adev, job, false);
 }
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
@@ -54,7 +54,11 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
 	if (!*job)
 		return -ENOMEM;
 
-	(*job)->adev = adev;
+	/*
+	 * Initialize the scheduler to at least some ring so that we always
+	 * have a pointer to adev.
+	 */
+	(*job)->base.sched = &adev->rings[0]->sched;
 	(*job)->vm = vm;
 	(*job)->ibs = (void *)&(*job)[1];
 	(*job)->num_ibs = num_ibs;
@@ -86,6 +90,7 @@ int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size,
 
 void amdgpu_job_free_resources(struct amdgpu_job *job)
 {
+	struct amdgpu_ring *ring = to_amdgpu_ring(job->base.sched);
 	struct dma_fence *f;
 	unsigned i;
 
@@ -93,14 +98,15 @@ void amdgpu_job_free_resources(struct amdgpu_job *job)
 	f = job->base.s_fence ? &job->base.s_fence->finished : job->fence;
 
 	for (i = 0; i < job->num_ibs; ++i)
-		amdgpu_ib_free(job->adev, &job->ibs[i], f);
+		amdgpu_ib_free(ring->adev, &job->ibs[i], f);
 }
 
 static void amdgpu_job_free_cb(struct drm_sched_job *s_job)
 {
-	struct amdgpu_job *job = container_of(s_job, struct amdgpu_job, base);
+	struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched);
+	struct amdgpu_job *job = to_amdgpu_job(s_job);
 
-	amdgpu_ring_priority_put(job->ring, s_job->s_priority);
+	amdgpu_ring_priority_put(ring, s_job->s_priority);
 	dma_fence_put(job->fence);
 	amdgpu_sync_free(&job->sync);
 	amdgpu_sync_free(&job->sched_sync);
@@ -117,50 +123,68 @@ void amdgpu_job_free(struct amdgpu_job *job)
 	kfree(job);
 }
 
-int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
-		      struct drm_sched_entity *entity, void *owner,
-		      struct dma_fence **f)
+int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
+		      void *owner, struct dma_fence **f)
 {
+	enum drm_sched_priority priority;
+	struct amdgpu_ring *ring;
 	int r;
-	job->ring = ring;
 
 	if (!f)
 		return -EINVAL;
 
-	r = drm_sched_job_init(&job->base, &ring->sched, entity, owner);
+	r = drm_sched_job_init(&job->base, entity, owner);
 	if (r)
 		return r;
 
 	job->owner = owner;
-	job->fence_ctx = entity->fence_context;
 	*f = dma_fence_get(&job->base.s_fence->finished);
 	amdgpu_job_free_resources(job);
-	amdgpu_ring_priority_get(job->ring, job->base.s_priority);
+	priority = job->base.s_priority;
 	drm_sched_entity_push_job(&job->base, entity);
 
+	ring = to_amdgpu_ring(entity->rq->sched);
+	amdgpu_ring_priority_get(ring, priority);
+
+	return 0;
+}
+
+int amdgpu_job_submit_direct(struct amdgpu_job *job, struct amdgpu_ring *ring,
+			     struct dma_fence **fence)
+{
+	int r;
+
+	job->base.sched = &ring->sched;
+	r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs, NULL, fence);
+	job->fence = dma_fence_get(*fence);
+	if (r)
+		return r;
+
+	amdgpu_job_free(job);
 	return 0;
 }
 
 static struct dma_fence *amdgpu_job_dependency(struct drm_sched_job *sched_job,
 					       struct drm_sched_entity *s_entity)
 {
+	struct amdgpu_ring *ring = to_amdgpu_ring(s_entity->rq->sched);
 	struct amdgpu_job *job = to_amdgpu_job(sched_job);
 	struct amdgpu_vm *vm = job->vm;
+	struct dma_fence *fence;
 	bool explicit = false;
 	int r;
-	struct dma_fence *fence = amdgpu_sync_get_fence(&job->sync, &explicit);
 
+	fence = amdgpu_sync_get_fence(&job->sync, &explicit);
 	if (fence && explicit) {
 		if (drm_sched_dependency_optimized(fence, s_entity)) {
-			r = amdgpu_sync_fence(job->adev, &job->sched_sync, fence, false);
+			r = amdgpu_sync_fence(ring->adev, &job->sched_sync,
+					      fence, false);
 			if (r)
-				DRM_ERROR("Error adding fence to sync (%d)\n", r);
+				DRM_ERROR("Error adding fence (%d)\n", r);
 		}
 	}
 
 	while (fence == NULL && vm && !job->vmid) {
-		struct amdgpu_ring *ring = job->ring;
-
 		r = amdgpu_vmid_grab(vm, ring, &job->sync,
 				     &job->base.s_fence->finished,
 				     job);
@@ -175,30 +199,25 @@ static struct dma_fence *amdgpu_job_dependency(struct drm_sched_job *sched_job,
 
 static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 {
+	struct amdgpu_ring *ring = to_amdgpu_ring(sched_job->sched);
 	struct dma_fence *fence = NULL, *finished;
-	struct amdgpu_device *adev;
 	struct amdgpu_job *job;
 	int r;
 
-	if (!sched_job) {
-		DRM_ERROR("job is null\n");
-		return NULL;
-	}
 	job = to_amdgpu_job(sched_job);
 	finished = &job->base.s_fence->finished;
-	adev = job->adev;
 
 	BUG_ON(amdgpu_sync_peek_fence(&job->sync, NULL));
 
 	trace_amdgpu_sched_run_job(job);
 
-	if (job->vram_lost_counter != atomic_read(&adev->vram_lost_counter))
+	if (job->vram_lost_counter != atomic_read(&ring->adev->vram_lost_counter))
 		dma_fence_set_error(finished, -ECANCELED);/* skip IB as well if VRAM lost */
 
 	if (finished->error < 0) {
 		DRM_INFO("Skip scheduling IBs!\n");
 	} else {
-		r = amdgpu_ib_schedule(job->ring, job->num_ibs, job->ibs, job,
+		r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs, job,
 				       &fence);
 		if (r)
 			DRM_ERROR("Error scheduling IBs (%d)\n", r);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
new file mode 100644
index 000000000000..57cfe78a262b
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -0,0 +1,74 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef __AMDGPU_JOB_H__
+#define __AMDGPU_JOB_H__
+
+/* bit set means command submit involves a preamble IB */
+#define AMDGPU_PREAMBLE_IB_PRESENT          (1 << 0)
+/* bit set means preamble IB is first presented in belonging context */
+#define AMDGPU_PREAMBLE_IB_PRESENT_FIRST    (1 << 1)
+/* bit set means context switch occured */
+#define AMDGPU_HAVE_CTX_SWITCH              (1 << 2)
+
+#define to_amdgpu_job(sched_job)		\
+		container_of((sched_job), struct amdgpu_job, base)
+
+struct amdgpu_fence;
+
+struct amdgpu_job {
+	struct drm_sched_job    base;
+	struct amdgpu_vm	*vm;
+	struct amdgpu_sync	sync;
+	struct amdgpu_sync	sched_sync;
+	struct amdgpu_ib	*ibs;
+	struct dma_fence	*fence; /* the hw fence */
+	uint32_t		preamble_status;
+	uint32_t		num_ibs;
+	void			*owner;
+	bool                    vm_needs_flush;
+	uint64_t		vm_pd_addr;
+	unsigned		vmid;
+	unsigned		pasid;
+	uint32_t		gds_base, gds_size;
+	uint32_t		gws_base, gws_size;
+	uint32_t		oa_base, oa_size;
+	uint32_t		vram_lost_counter;
+
+	/* user fence handling */
+	uint64_t		uf_addr;
+	uint64_t		uf_sequence;
+
+};
+
+int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
+		     struct amdgpu_job **job, struct amdgpu_vm *vm);
+int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size,
+			     struct amdgpu_job **job);
+
+void amdgpu_job_free_resources(struct amdgpu_job *job);
+void amdgpu_job_free(struct amdgpu_job *job);
+int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
+		      void *owner, struct dma_fence **f);
+int amdgpu_job_submit_direct(struct amdgpu_job *job, struct amdgpu_ring *ring,
+			     struct dma_fence **fence);
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 91517b166a3b..bd98cc5fb97b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -328,61 +328,71 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		case AMDGPU_HW_IP_GFX:
 			type = AMD_IP_BLOCK_TYPE_GFX;
 			for (i = 0; i < adev->gfx.num_gfx_rings; i++)
-				ring_mask |= ((adev->gfx.gfx_ring[i].ready ? 1 : 0) << i);
-			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
-			ib_size_alignment = 8;
+				ring_mask |= adev->gfx.gfx_ring[i].ready << i;
+			ib_start_alignment = 32;
+			ib_size_alignment = 32;
 			break;
 		case AMDGPU_HW_IP_COMPUTE:
 			type = AMD_IP_BLOCK_TYPE_GFX;
 			for (i = 0; i < adev->gfx.num_compute_rings; i++)
-				ring_mask |= ((adev->gfx.compute_ring[i].ready ? 1 : 0) << i);
-			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
-			ib_size_alignment = 8;
+				ring_mask |= adev->gfx.compute_ring[i].ready << i;
+			ib_start_alignment = 32;
+			ib_size_alignment = 32;
 			break;
 		case AMDGPU_HW_IP_DMA:
 			type = AMD_IP_BLOCK_TYPE_SDMA;
 			for (i = 0; i < adev->sdma.num_instances; i++)
-				ring_mask |= ((adev->sdma.instance[i].ring.ready ? 1 : 0) << i);
-			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
-			ib_size_alignment = 1;
+				ring_mask |= adev->sdma.instance[i].ring.ready << i;
+			ib_start_alignment = 256;
+			ib_size_alignment = 4;
 			break;
 		case AMDGPU_HW_IP_UVD:
 			type = AMD_IP_BLOCK_TYPE_UVD;
-			for (i = 0; i < adev->uvd.num_uvd_inst; i++)
-				ring_mask |= ((adev->uvd.inst[i].ring.ready ? 1 : 0) << i);
-			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
-			ib_size_alignment = 16;
+			for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
+				if (adev->uvd.harvest_config & (1 << i))
+					continue;
+				ring_mask |= adev->uvd.inst[i].ring.ready;
+			}
+			ib_start_alignment = 64;
+			ib_size_alignment = 64;
 			break;
 		case AMDGPU_HW_IP_VCE:
 			type = AMD_IP_BLOCK_TYPE_VCE;
 			for (i = 0; i < adev->vce.num_rings; i++)
-				ring_mask |= ((adev->vce.ring[i].ready ? 1 : 0) << i);
-			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
+				ring_mask |= adev->vce.ring[i].ready << i;
+			ib_start_alignment = 4;
 			ib_size_alignment = 1;
 			break;
 		case AMDGPU_HW_IP_UVD_ENC:
 			type = AMD_IP_BLOCK_TYPE_UVD;
-			for (i = 0; i < adev->uvd.num_uvd_inst; i++)
+			for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
+				if (adev->uvd.harvest_config & (1 << i))
+					continue;
 				for (j = 0; j < adev->uvd.num_enc_rings; j++)
-					ring_mask |=
-					((adev->uvd.inst[i].ring_enc[j].ready ? 1 : 0) <<
-					(j + i * adev->uvd.num_enc_rings));
-			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
-			ib_size_alignment = 1;
+					ring_mask |= adev->uvd.inst[i].ring_enc[j].ready << j;
+			}
+			ib_start_alignment = 64;
+			ib_size_alignment = 64;
 			break;
 		case AMDGPU_HW_IP_VCN_DEC:
 			type = AMD_IP_BLOCK_TYPE_VCN;
-			ring_mask = adev->vcn.ring_dec.ready ? 1 : 0;
-			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
+			ring_mask = adev->vcn.ring_dec.ready;
+			ib_start_alignment = 16;
 			ib_size_alignment = 16;
 			break;
 		case AMDGPU_HW_IP_VCN_ENC:
 			type = AMD_IP_BLOCK_TYPE_VCN;
 			for (i = 0; i < adev->vcn.num_enc_rings; i++)
-				ring_mask |= ((adev->vcn.ring_enc[i].ready ? 1 : 0) << i);
-			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
+				ring_mask |= adev->vcn.ring_enc[i].ready << i;
+			ib_start_alignment = 64;
 			ib_size_alignment = 1;
 			break;
+		case AMDGPU_HW_IP_VCN_JPEG:
+			type = AMD_IP_BLOCK_TYPE_VCN;
+			ring_mask = adev->vcn.ring_jpeg.ready;
+			ib_start_alignment = 16;
+			ib_size_alignment = 16;
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -427,6 +437,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			break;
 		case AMDGPU_HW_IP_VCN_DEC:
 		case AMDGPU_HW_IP_VCN_ENC:
+		case AMDGPU_HW_IP_VCN_JPEG:
 			type = AMD_IP_BLOCK_TYPE_VCN;
 			break;
 		default:
@@ -494,13 +505,13 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 	case AMDGPU_INFO_VRAM_GTT: {
 		struct drm_amdgpu_info_vram_gtt vram_gtt;
 
-		vram_gtt.vram_size = adev->gmc.real_vram_size;
-		vram_gtt.vram_size -= adev->vram_pin_size;
-		vram_gtt.vram_cpu_accessible_size = adev->gmc.visible_vram_size;
-		vram_gtt.vram_cpu_accessible_size -= (adev->vram_pin_size - adev->invisible_pin_size);
+		vram_gtt.vram_size = adev->gmc.real_vram_size -
+			atomic64_read(&adev->vram_pin_size);
+		vram_gtt.vram_cpu_accessible_size = adev->gmc.visible_vram_size -
+			atomic64_read(&adev->visible_pin_size);
 		vram_gtt.gtt_size = adev->mman.bdev.man[TTM_PL_TT].size;
 		vram_gtt.gtt_size *= PAGE_SIZE;
-		vram_gtt.gtt_size -= adev->gart_pin_size;
+		vram_gtt.gtt_size -= atomic64_read(&adev->gart_pin_size);
 		return copy_to_user(out, &vram_gtt,
 				    min((size_t)size, sizeof(vram_gtt))) ? -EFAULT : 0;
 	}
@@ -509,17 +520,16 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 
 		memset(&mem, 0, sizeof(mem));
 		mem.vram.total_heap_size = adev->gmc.real_vram_size;
-		mem.vram.usable_heap_size =
-			adev->gmc.real_vram_size - adev->vram_pin_size;
+		mem.vram.usable_heap_size = adev->gmc.real_vram_size -
+			atomic64_read(&adev->vram_pin_size);
 		mem.vram.heap_usage =
 			amdgpu_vram_mgr_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
 		mem.vram.max_allocation = mem.vram.usable_heap_size * 3 / 4;
 
 		mem.cpu_accessible_vram.total_heap_size =
 			adev->gmc.visible_vram_size;
-		mem.cpu_accessible_vram.usable_heap_size =
-			adev->gmc.visible_vram_size -
-			(adev->vram_pin_size - adev->invisible_pin_size);
+		mem.cpu_accessible_vram.usable_heap_size = adev->gmc.visible_vram_size -
+			atomic64_read(&adev->visible_pin_size);
 		mem.cpu_accessible_vram.heap_usage =
 			amdgpu_vram_mgr_vis_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
 		mem.cpu_accessible_vram.max_allocation =
@@ -527,8 +537,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 
 		mem.gtt.total_heap_size = adev->mman.bdev.man[TTM_PL_TT].size;
 		mem.gtt.total_heap_size *= PAGE_SIZE;
-		mem.gtt.usable_heap_size = mem.gtt.total_heap_size
-			- adev->gart_pin_size;
+		mem.gtt.usable_heap_size = mem.gtt.total_heap_size -
+			atomic64_read(&adev->gart_pin_size);
 		mem.gtt.heap_usage =
 			amdgpu_gtt_mgr_usage(&adev->mman.bdev.man[TTM_PL_TT]);
 		mem.gtt.max_allocation = mem.gtt.usable_heap_size * 3 / 4;
@@ -930,7 +940,6 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
 		return;
 
 	pm_runtime_get_sync(dev->dev);
-	amdgpu_ctx_mgr_entity_fini(&fpriv->ctx_mgr);
 
 	if (adev->asic_type != CHIP_RAVEN) {
 		amdgpu_uvd_free_handles(adev, file_priv);
@@ -958,7 +967,7 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
 	amdgpu_bo_unref(&pd);
 
 	idr_for_each_entry(&fpriv->bo_list_handles, list, handle)
-		amdgpu_bo_list_free(list);
+		amdgpu_bo_list_put(list);
 
 	idr_destroy(&fpriv->bo_list_handles);
 	mutex_destroy(&fpriv->bo_list_lock);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index 83e344fbb50a..a365ea2383d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -28,6 +28,21 @@
  *    Christian König <christian.koenig@amd.com>
  */
 
+/**
+ * DOC: MMU Notifier
+ *
+ * For coherent userptr handling registers an MMU notifier to inform the driver
+ * about updates on the page tables of a process.
+ *
+ * When somebody tries to invalidate the page tables we block the update until
+ * all operations on the pages in question are completed, then those pages are
+ * marked as accessed and also dirty if it wasn't a read only access.
+ *
+ * New command submissions using the userptrs in question are delayed until all
+ * page table invalidation are completed and we once more see a coherent process
+ * address space.
+ */
+
 #include <linux/firmware.h>
 #include <linux/module.h>
 #include <linux/mmu_notifier.h>
@@ -38,6 +53,22 @@
 #include "amdgpu.h"
 #include "amdgpu_amdkfd.h"
 
+/**
+ * struct amdgpu_mn
+ *
+ * @adev: amdgpu device pointer
+ * @mm: process address space
+ * @mn: MMU notifier structure
+ * @type: type of MMU notifier
+ * @work: destruction work item
+ * @node: hash table node to find structure by adev and mn
+ * @lock: rw semaphore protecting the notifier nodes
+ * @objects: interval tree containing amdgpu_mn_nodes
+ * @read_lock: mutex for recursive locking of @lock
+ * @recursion: depth of recursion
+ *
+ * Data for each amdgpu device and process address space.
+ */
 struct amdgpu_mn {
 	/* constant after initialisation */
 	struct amdgpu_device	*adev;
@@ -58,13 +89,21 @@ struct amdgpu_mn {
 	atomic_t		recursion;
 };
 
+/**
+ * struct amdgpu_mn_node
+ *
+ * @it: interval node defining start-last of the affected address range
+ * @bos: list of all BOs in the affected address range
+ *
+ * Manages all BOs which are affected of a certain range of address space.
+ */
 struct amdgpu_mn_node {
 	struct interval_tree_node	it;
 	struct list_head		bos;
 };
 
 /**
- * amdgpu_mn_destroy - destroy the rmn
+ * amdgpu_mn_destroy - destroy the MMU notifier
  *
  * @work: previously sheduled work item
  *
@@ -72,47 +111,50 @@ struct amdgpu_mn_node {
  */
 static void amdgpu_mn_destroy(struct work_struct *work)
 {
-	struct amdgpu_mn *rmn = container_of(work, struct amdgpu_mn, work);
-	struct amdgpu_device *adev = rmn->adev;
+	struct amdgpu_mn *amn = container_of(work, struct amdgpu_mn, work);
+	struct amdgpu_device *adev = amn->adev;
 	struct amdgpu_mn_node *node, *next_node;
 	struct amdgpu_bo *bo, *next_bo;
 
 	mutex_lock(&adev->mn_lock);
-	down_write(&rmn->lock);
-	hash_del(&rmn->node);
+	down_write(&amn->lock);
+	hash_del(&amn->node);
 	rbtree_postorder_for_each_entry_safe(node, next_node,
-					     &rmn->objects.rb_root, it.rb) {
+					     &amn->objects.rb_root, it.rb) {
 		list_for_each_entry_safe(bo, next_bo, &node->bos, mn_list) {
 			bo->mn = NULL;
 			list_del_init(&bo->mn_list);
 		}
 		kfree(node);
 	}
-	up_write(&rmn->lock);
+	up_write(&amn->lock);
 	mutex_unlock(&adev->mn_lock);
-	mmu_notifier_unregister_no_release(&rmn->mn, rmn->mm);
-	kfree(rmn);
+	mmu_notifier_unregister_no_release(&amn->mn, amn->mm);
+	kfree(amn);
 }
 
 /**
  * amdgpu_mn_release - callback to notify about mm destruction
  *
  * @mn: our notifier
- * @mn: the mm this callback is about
+ * @mm: the mm this callback is about
  *
  * Shedule a work item to lazy destroy our notifier.
  */
 static void amdgpu_mn_release(struct mmu_notifier *mn,
 			      struct mm_struct *mm)
 {
-	struct amdgpu_mn *rmn = container_of(mn, struct amdgpu_mn, mn);
-	INIT_WORK(&rmn->work, amdgpu_mn_destroy);
-	schedule_work(&rmn->work);
+	struct amdgpu_mn *amn = container_of(mn, struct amdgpu_mn, mn);
+
+	INIT_WORK(&amn->work, amdgpu_mn_destroy);
+	schedule_work(&amn->work);
 }
 
 
 /**
- * amdgpu_mn_lock - take the write side lock for this mn
+ * amdgpu_mn_lock - take the write side lock for this notifier
+ *
+ * @mn: our notifier
  */
 void amdgpu_mn_lock(struct amdgpu_mn *mn)
 {
@@ -121,7 +163,9 @@ void amdgpu_mn_lock(struct amdgpu_mn *mn)
 }
 
 /**
- * amdgpu_mn_unlock - drop the write side lock for this mn
+ * amdgpu_mn_unlock - drop the write side lock for this notifier
+ *
+ * @mn: our notifier
  */
 void amdgpu_mn_unlock(struct amdgpu_mn *mn)
 {
@@ -130,40 +174,38 @@ void amdgpu_mn_unlock(struct amdgpu_mn *mn)
 }
 
 /**
- * amdgpu_mn_read_lock - take the rmn read lock
- *
- * @rmn: our notifier
+ * amdgpu_mn_read_lock - take the read side lock for this notifier
  *
- * Take the rmn read side lock.
+ * @amn: our notifier
  */
-static void amdgpu_mn_read_lock(struct amdgpu_mn *rmn)
+static void amdgpu_mn_read_lock(struct amdgpu_mn *amn)
 {
-	mutex_lock(&rmn->read_lock);
-	if (atomic_inc_return(&rmn->recursion) == 1)
-		down_read_non_owner(&rmn->lock);
-	mutex_unlock(&rmn->read_lock);
+	mutex_lock(&amn->read_lock);
+	if (atomic_inc_return(&amn->recursion) == 1)
+		down_read_non_owner(&amn->lock);
+	mutex_unlock(&amn->read_lock);
 }
 
 /**
- * amdgpu_mn_read_unlock - drop the rmn read lock
+ * amdgpu_mn_read_unlock - drop the read side lock for this notifier
  *
- * @rmn: our notifier
- *
- * Drop the rmn read side lock.
+ * @amn: our notifier
  */
-static void amdgpu_mn_read_unlock(struct amdgpu_mn *rmn)
+static void amdgpu_mn_read_unlock(struct amdgpu_mn *amn)
 {
-	if (atomic_dec_return(&rmn->recursion) == 0)
-		up_read_non_owner(&rmn->lock);
+	if (atomic_dec_return(&amn->recursion) == 0)
+		up_read_non_owner(&amn->lock);
 }
 
 /**
  * amdgpu_mn_invalidate_node - unmap all BOs of a node
  *
  * @node: the node with the BOs to unmap
+ * @start: start of address range affected
+ * @end: end of address range affected
  *
- * We block for all BOs and unmap them by move them
- * into system domain again.
+ * Block for operations on BOs to finish and mark pages as accessed and
+ * potentially dirty.
  */
 static void amdgpu_mn_invalidate_node(struct amdgpu_mn_node *node,
 				      unsigned long start,
@@ -190,27 +232,27 @@ static void amdgpu_mn_invalidate_node(struct amdgpu_mn_node *node,
  * amdgpu_mn_invalidate_range_start_gfx - callback to notify about mm change
  *
  * @mn: our notifier
- * @mn: the mm this callback is about
+ * @mm: the mm this callback is about
  * @start: start of updated range
  * @end: end of updated range
  *
- * We block for all BOs between start and end to be idle and
- * unmap them by move them into system domain again.
+ * Block for operations on BOs to finish and mark pages as accessed and
+ * potentially dirty.
  */
 static void amdgpu_mn_invalidate_range_start_gfx(struct mmu_notifier *mn,
 						 struct mm_struct *mm,
 						 unsigned long start,
 						 unsigned long end)
 {
-	struct amdgpu_mn *rmn = container_of(mn, struct amdgpu_mn, mn);
+	struct amdgpu_mn *amn = container_of(mn, struct amdgpu_mn, mn);
 	struct interval_tree_node *it;
 
 	/* notification is exclusive, but interval is inclusive */
 	end -= 1;
 
-	amdgpu_mn_read_lock(rmn);
+	amdgpu_mn_read_lock(amn);
 
-	it = interval_tree_iter_first(&rmn->objects, start, end);
+	it = interval_tree_iter_first(&amn->objects, start, end);
 	while (it) {
 		struct amdgpu_mn_node *node;
 
@@ -225,7 +267,7 @@ static void amdgpu_mn_invalidate_range_start_gfx(struct mmu_notifier *mn,
  * amdgpu_mn_invalidate_range_start_hsa - callback to notify about mm change
  *
  * @mn: our notifier
- * @mn: the mm this callback is about
+ * @mm: the mm this callback is about
  * @start: start of updated range
  * @end: end of updated range
  *
@@ -238,15 +280,15 @@ static void amdgpu_mn_invalidate_range_start_hsa(struct mmu_notifier *mn,
 						 unsigned long start,
 						 unsigned long end)
 {
-	struct amdgpu_mn *rmn = container_of(mn, struct amdgpu_mn, mn);
+	struct amdgpu_mn *amn = container_of(mn, struct amdgpu_mn, mn);
 	struct interval_tree_node *it;
 
 	/* notification is exclusive, but interval is inclusive */
 	end -= 1;
 
-	amdgpu_mn_read_lock(rmn);
+	amdgpu_mn_read_lock(amn);
 
-	it = interval_tree_iter_first(&rmn->objects, start, end);
+	it = interval_tree_iter_first(&amn->objects, start, end);
 	while (it) {
 		struct amdgpu_mn_node *node;
 		struct amdgpu_bo *bo;
@@ -268,7 +310,7 @@ static void amdgpu_mn_invalidate_range_start_hsa(struct mmu_notifier *mn,
  * amdgpu_mn_invalidate_range_end - callback to notify about mm change
  *
  * @mn: our notifier
- * @mn: the mm this callback is about
+ * @mm: the mm this callback is about
  * @start: start of updated range
  * @end: end of updated range
  *
@@ -279,9 +321,9 @@ static void amdgpu_mn_invalidate_range_end(struct mmu_notifier *mn,
 					   unsigned long start,
 					   unsigned long end)
 {
-	struct amdgpu_mn *rmn = container_of(mn, struct amdgpu_mn, mn);
+	struct amdgpu_mn *amn = container_of(mn, struct amdgpu_mn, mn);
 
-	amdgpu_mn_read_unlock(rmn);
+	amdgpu_mn_read_unlock(amn);
 }
 
 static const struct mmu_notifier_ops amdgpu_mn_ops[] = {
@@ -315,7 +357,7 @@ struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev,
 				enum amdgpu_mn_type type)
 {
 	struct mm_struct *mm = current->mm;
-	struct amdgpu_mn *rmn;
+	struct amdgpu_mn *amn;
 	unsigned long key = AMDGPU_MN_KEY(mm, type);
 	int r;
 
@@ -325,41 +367,41 @@ struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev,
 		return ERR_PTR(-EINTR);
 	}
 
-	hash_for_each_possible(adev->mn_hash, rmn, node, key)
-		if (AMDGPU_MN_KEY(rmn->mm, rmn->type) == key)
+	hash_for_each_possible(adev->mn_hash, amn, node, key)
+		if (AMDGPU_MN_KEY(amn->mm, amn->type) == key)
 			goto release_locks;
 
-	rmn = kzalloc(sizeof(*rmn), GFP_KERNEL);
-	if (!rmn) {
-		rmn = ERR_PTR(-ENOMEM);
+	amn = kzalloc(sizeof(*amn), GFP_KERNEL);
+	if (!amn) {
+		amn = ERR_PTR(-ENOMEM);
 		goto release_locks;
 	}
 
-	rmn->adev = adev;
-	rmn->mm = mm;
-	init_rwsem(&rmn->lock);
-	rmn->type = type;
-	rmn->mn.ops = &amdgpu_mn_ops[type];
-	rmn->objects = RB_ROOT_CACHED;
-	mutex_init(&rmn->read_lock);
-	atomic_set(&rmn->recursion, 0);
+	amn->adev = adev;
+	amn->mm = mm;
+	init_rwsem(&amn->lock);
+	amn->type = type;
+	amn->mn.ops = &amdgpu_mn_ops[type];
+	amn->objects = RB_ROOT_CACHED;
+	mutex_init(&amn->read_lock);
+	atomic_set(&amn->recursion, 0);
 
-	r = __mmu_notifier_register(&rmn->mn, mm);
+	r = __mmu_notifier_register(&amn->mn, mm);
 	if (r)
-		goto free_rmn;
+		goto free_amn;
 
-	hash_add(adev->mn_hash, &rmn->node, AMDGPU_MN_KEY(mm, type));
+	hash_add(adev->mn_hash, &amn->node, AMDGPU_MN_KEY(mm, type));
 
 release_locks:
 	up_write(&mm->mmap_sem);
 	mutex_unlock(&adev->mn_lock);
 
-	return rmn;
+	return amn;
 
-free_rmn:
+free_amn:
 	up_write(&mm->mmap_sem);
 	mutex_unlock(&adev->mn_lock);
-	kfree(rmn);
+	kfree(amn);
 
 	return ERR_PTR(r);
 }
@@ -379,14 +421,14 @@ int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	enum amdgpu_mn_type type =
 		bo->kfd_bo ? AMDGPU_MN_TYPE_HSA : AMDGPU_MN_TYPE_GFX;
-	struct amdgpu_mn *rmn;
+	struct amdgpu_mn *amn;
 	struct amdgpu_mn_node *node = NULL, *new_node;
 	struct list_head bos;
 	struct interval_tree_node *it;
 
-	rmn = amdgpu_mn_get(adev, type);
-	if (IS_ERR(rmn))
-		return PTR_ERR(rmn);
+	amn = amdgpu_mn_get(adev, type);
+	if (IS_ERR(amn))
+		return PTR_ERR(amn);
 
 	new_node = kmalloc(sizeof(*new_node), GFP_KERNEL);
 	if (!new_node)
@@ -394,12 +436,12 @@ int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
 
 	INIT_LIST_HEAD(&bos);
 
-	down_write(&rmn->lock);
+	down_write(&amn->lock);
 
-	while ((it = interval_tree_iter_first(&rmn->objects, addr, end))) {
+	while ((it = interval_tree_iter_first(&amn->objects, addr, end))) {
 		kfree(node);
 		node = container_of(it, struct amdgpu_mn_node, it);
-		interval_tree_remove(&node->it, &rmn->objects);
+		interval_tree_remove(&node->it, &amn->objects);
 		addr = min(it->start, addr);
 		end = max(it->last, end);
 		list_splice(&node->bos, &bos);
@@ -410,7 +452,7 @@ int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
 	else
 		kfree(new_node);
 
-	bo->mn = rmn;
+	bo->mn = amn;
 
 	node->it.start = addr;
 	node->it.last = end;
@@ -418,9 +460,9 @@ int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
 	list_splice(&bos, &node->bos);
 	list_add(&bo->mn_list, &node->bos);
 
-	interval_tree_insert(&node->it, &rmn->objects);
+	interval_tree_insert(&node->it, &amn->objects);
 
-	up_write(&rmn->lock);
+	up_write(&amn->lock);
 
 	return 0;
 }
@@ -435,18 +477,18 @@ int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
 void amdgpu_mn_unregister(struct amdgpu_bo *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	struct amdgpu_mn *rmn;
+	struct amdgpu_mn *amn;
 	struct list_head *head;
 
 	mutex_lock(&adev->mn_lock);
 
-	rmn = bo->mn;
-	if (rmn == NULL) {
+	amn = bo->mn;
+	if (amn == NULL) {
 		mutex_unlock(&adev->mn_lock);
 		return;
 	}
 
-	down_write(&rmn->lock);
+	down_write(&amn->lock);
 
 	/* save the next list entry for later */
 	head = bo->mn_list.next;
@@ -456,12 +498,13 @@ void amdgpu_mn_unregister(struct amdgpu_bo *bo)
 
 	if (list_empty(head)) {
 		struct amdgpu_mn_node *node;
+
 		node = container_of(head, struct amdgpu_mn_node, bos);
-		interval_tree_remove(&node->it, &rmn->objects);
+		interval_tree_remove(&node->it, &amn->objects);
 		kfree(node);
 	}
 
-	up_write(&rmn->lock);
+	up_write(&amn->lock);
 	mutex_unlock(&adev->mn_lock);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 3526efa8960e..b0e14a3d54ef 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -38,7 +38,20 @@
 #include "amdgpu_trace.h"
 #include "amdgpu_amdkfd.h"
 
-static bool amdgpu_need_backup(struct amdgpu_device *adev)
+/**
+ * DOC: amdgpu_object
+ *
+ * This defines the interfaces to operate on an &amdgpu_bo buffer object which
+ * represents memory used by driver (VRAM, system memory, etc.). The driver
+ * provides DRM/GEM APIs to userspace. DRM/GEM APIs then use these interfaces
+ * to create/destroy/set buffer object which are then managed by the kernel TTM
+ * memory manager.
+ * The interfaces are also used internally by kernel clients, including gfx,
+ * uvd, etc. for kernel managed allocations used by the GPU.
+ *
+ */
+
+static bool amdgpu_bo_need_backup(struct amdgpu_device *adev)
 {
 	if (adev->flags & AMD_IS_APU)
 		return false;
@@ -50,11 +63,35 @@ static bool amdgpu_need_backup(struct amdgpu_device *adev)
 	return true;
 }
 
-static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
+/**
+ * amdgpu_bo_subtract_pin_size - Remove BO from pin_size accounting
+ *
+ * @bo: &amdgpu_bo buffer object
+ *
+ * This function is called when a BO stops being pinned, and updates the
+ * &amdgpu_device pin_size values accordingly.
+ */
+static void amdgpu_bo_subtract_pin_size(struct amdgpu_bo *bo)
+{
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+
+	if (bo->tbo.mem.mem_type == TTM_PL_VRAM) {
+		atomic64_sub(amdgpu_bo_size(bo), &adev->vram_pin_size);
+		atomic64_sub(amdgpu_vram_mgr_bo_visible_size(bo),
+			     &adev->visible_pin_size);
+	} else if (bo->tbo.mem.mem_type == TTM_PL_TT) {
+		atomic64_sub(amdgpu_bo_size(bo), &adev->gart_pin_size);
+	}
+}
+
+static void amdgpu_bo_destroy(struct ttm_buffer_object *tbo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev);
 	struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo);
 
+	if (bo->pin_count > 0)
+		amdgpu_bo_subtract_pin_size(bo);
+
 	if (bo->kfd_bo)
 		amdgpu_amdkfd_unreserve_system_memory_limit(bo);
 
@@ -73,14 +110,32 @@ static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
 	kfree(bo);
 }
 
-bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo)
+/**
+ * amdgpu_bo_is_amdgpu_bo - check if the buffer object is an &amdgpu_bo
+ * @bo: buffer object to be checked
+ *
+ * Uses destroy function associated with the object to determine if this is
+ * an &amdgpu_bo.
+ *
+ * Returns:
+ * true if the object belongs to &amdgpu_bo, false if not.
+ */
+bool amdgpu_bo_is_amdgpu_bo(struct ttm_buffer_object *bo)
 {
-	if (bo->destroy == &amdgpu_ttm_bo_destroy)
+	if (bo->destroy == &amdgpu_bo_destroy)
 		return true;
 	return false;
 }
 
-void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
+/**
+ * amdgpu_bo_placement_from_domain - set buffer's placement
+ * @abo: &amdgpu_bo buffer object whose placement is to be set
+ * @domain: requested domain
+ *
+ * Sets buffer's placement according to requested domain and the buffer's
+ * flags.
+ */
+void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(abo->tbo.bdev);
 	struct ttm_placement *placement = &abo->placement;
@@ -161,6 +216,8 @@ void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 		c++;
 	}
 
+	BUG_ON(c >= AMDGPU_BO_MAX_PLACEMENTS);
+
 	placement->num_placement = c;
 	placement->placement = places;
 
@@ -184,7 +241,8 @@ void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
  *
  * Note: For bo_ptr new BO is only created if bo_ptr points to NULL.
  *
- * Returns 0 on success, negative error code otherwise.
+ * Returns:
+ * 0 on success, negative error code otherwise.
  */
 int amdgpu_bo_create_reserved(struct amdgpu_device *adev,
 			      unsigned long size, int align,
@@ -220,22 +278,33 @@ int amdgpu_bo_create_reserved(struct amdgpu_device *adev,
 		goto error_free;
 	}
 
-	r = amdgpu_bo_pin(*bo_ptr, domain, gpu_addr);
+	r = amdgpu_bo_pin(*bo_ptr, domain);
 	if (r) {
 		dev_err(adev->dev, "(%d) kernel bo pin failed\n", r);
 		goto error_unreserve;
 	}
 
+	r = amdgpu_ttm_alloc_gart(&(*bo_ptr)->tbo);
+	if (r) {
+		dev_err(adev->dev, "%p bind failed\n", *bo_ptr);
+		goto error_unpin;
+	}
+
+	if (gpu_addr)
+		*gpu_addr = amdgpu_bo_gpu_offset(*bo_ptr);
+
 	if (cpu_addr) {
 		r = amdgpu_bo_kmap(*bo_ptr, cpu_addr);
 		if (r) {
 			dev_err(adev->dev, "(%d) kernel bo map failed\n", r);
-			goto error_unreserve;
+			goto error_unpin;
 		}
 	}
 
 	return 0;
 
+error_unpin:
+	amdgpu_bo_unpin(*bo_ptr);
 error_unreserve:
 	amdgpu_bo_unreserve(*bo_ptr);
 
@@ -261,7 +330,8 @@ error_free:
  *
  * Note: For bo_ptr new BO is only created if bo_ptr points to NULL.
  *
- * Returns 0 on success, negative error code otherwise.
+ * Returns:
+ * 0 on success, negative error code otherwise.
  */
 int amdgpu_bo_create_kernel(struct amdgpu_device *adev,
 			    unsigned long size, int align,
@@ -285,6 +355,8 @@ int amdgpu_bo_create_kernel(struct amdgpu_device *adev,
  * amdgpu_bo_free_kernel - free BO for kernel use
  *
  * @bo: amdgpu BO to free
+ * @gpu_addr: pointer to where the BO's GPU memory space address was stored
+ * @cpu_addr: pointer to where the BO's CPU memory space address was stored
  *
  * unmaps and unpin a BO for kernel internal use.
  */
@@ -418,17 +490,17 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 #endif
 
 	bo->tbo.bdev = &adev->mman.bdev;
-	amdgpu_ttm_placement_from_domain(bo, bp->domain);
+	amdgpu_bo_placement_from_domain(bo, bp->domain);
 	if (bp->type == ttm_bo_type_kernel)
 		bo->tbo.priority = 1;
 
 	r = ttm_bo_init_reserved(&adev->mman.bdev, &bo->tbo, size, bp->type,
 				 &bo->placement, page_align, &ctx, acc_size,
-				 NULL, bp->resv, &amdgpu_ttm_bo_destroy);
+				 NULL, bp->resv, &amdgpu_bo_destroy);
 	if (unlikely(r != 0))
 		return r;
 
-	if (adev->gmc.visible_vram_size < adev->gmc.real_vram_size &&
+	if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
 	    bo->tbo.mem.mem_type == TTM_PL_VRAM &&
 	    bo->tbo.mem.start < adev->gmc.visible_vram_size >> PAGE_SHIFT)
 		amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved,
@@ -498,6 +570,20 @@ static int amdgpu_bo_create_shadow(struct amdgpu_device *adev,
 	return r;
 }
 
+/**
+ * amdgpu_bo_create - create an &amdgpu_bo buffer object
+ * @adev: amdgpu device object
+ * @bp: parameters to be used for the buffer object
+ * @bo_ptr: pointer to the buffer object pointer
+ *
+ * Creates an &amdgpu_bo buffer object; and if requested, also creates a
+ * shadow object.
+ * Shadow object is used to backup the original buffer object, and is always
+ * in GTT.
+ *
+ * Returns:
+ * 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_create(struct amdgpu_device *adev,
 		     struct amdgpu_bo_param *bp,
 		     struct amdgpu_bo **bo_ptr)
@@ -510,7 +596,7 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
-	if ((flags & AMDGPU_GEM_CREATE_SHADOW) && amdgpu_need_backup(adev)) {
+	if ((flags & AMDGPU_GEM_CREATE_SHADOW) && amdgpu_bo_need_backup(adev)) {
 		if (!bp->resv)
 			WARN_ON(reservation_object_lock((*bo_ptr)->tbo.resv,
 							NULL));
@@ -527,6 +613,21 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 	return r;
 }
 
+/**
+ * amdgpu_bo_backup_to_shadow - Backs up an &amdgpu_bo buffer object
+ * @adev: amdgpu device object
+ * @ring: amdgpu_ring for the engine handling the buffer operations
+ * @bo: &amdgpu_bo buffer to be backed up
+ * @resv: reservation object with embedded fence
+ * @fence: dma_fence associated with the operation
+ * @direct: whether to submit the job directly
+ *
+ * Copies an &amdgpu_bo buffer object to its shadow object.
+ * Not used for now.
+ *
+ * Returns:
+ * 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_backup_to_shadow(struct amdgpu_device *adev,
 			       struct amdgpu_ring *ring,
 			       struct amdgpu_bo *bo,
@@ -559,6 +660,18 @@ err:
 	return r;
 }
 
+/**
+ * amdgpu_bo_validate - validate an &amdgpu_bo buffer object
+ * @bo: pointer to the buffer object
+ *
+ * Sets placement according to domain; and changes placement and caching
+ * policy of the buffer object according to the placement.
+ * This is used for validating shadow bos.  It calls ttm_bo_validate() to
+ * make sure the buffer is resident where it needs to be.
+ *
+ * Returns:
+ * 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_validate(struct amdgpu_bo *bo)
 {
 	struct ttm_operation_ctx ctx = { false, false };
@@ -571,7 +684,7 @@ int amdgpu_bo_validate(struct amdgpu_bo *bo)
 	domain = bo->preferred_domains;
 
 retry:
-	amdgpu_ttm_placement_from_domain(bo, domain);
+	amdgpu_bo_placement_from_domain(bo, domain);
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	if (unlikely(r == -ENOMEM) && domain != bo->allowed_domains) {
 		domain = bo->allowed_domains;
@@ -581,6 +694,22 @@ retry:
 	return r;
 }
 
+/**
+ * amdgpu_bo_restore_from_shadow - restore an &amdgpu_bo buffer object
+ * @adev: amdgpu device object
+ * @ring: amdgpu_ring for the engine handling the buffer operations
+ * @bo: &amdgpu_bo buffer to be restored
+ * @resv: reservation object with embedded fence
+ * @fence: dma_fence associated with the operation
+ * @direct: whether to submit the job directly
+ *
+ * Copies a buffer object's shadow content back to the object.
+ * This is used for recovering a buffer from its shadow in case of a gpu
+ * reset where vram context may be lost.
+ *
+ * Returns:
+ * 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_restore_from_shadow(struct amdgpu_device *adev,
 				  struct amdgpu_ring *ring,
 				  struct amdgpu_bo *bo,
@@ -613,6 +742,17 @@ err:
 	return r;
 }
 
+/**
+ * amdgpu_bo_kmap - map an &amdgpu_bo buffer object
+ * @bo: &amdgpu_bo buffer object to be mapped
+ * @ptr: kernel virtual address to be returned
+ *
+ * Calls ttm_bo_kmap() to set up the kernel virtual mapping; calls
+ * amdgpu_bo_kptr() to get the kernel virtual address.
+ *
+ * Returns:
+ * 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr)
 {
 	void *kptr;
@@ -643,6 +783,15 @@ int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr)
 	return 0;
 }
 
+/**
+ * amdgpu_bo_kptr - returns a kernel virtual address of the buffer object
+ * @bo: &amdgpu_bo buffer object
+ *
+ * Calls ttm_kmap_obj_virtual() to get the kernel virtual address
+ *
+ * Returns:
+ * the virtual address of a buffer object area.
+ */
 void *amdgpu_bo_kptr(struct amdgpu_bo *bo)
 {
 	bool is_iomem;
@@ -650,21 +799,42 @@ void *amdgpu_bo_kptr(struct amdgpu_bo *bo)
 	return ttm_kmap_obj_virtual(&bo->kmap, &is_iomem);
 }
 
+/**
+ * amdgpu_bo_kunmap - unmap an &amdgpu_bo buffer object
+ * @bo: &amdgpu_bo buffer object to be unmapped
+ *
+ * Unmaps a kernel map set up by amdgpu_bo_kmap().
+ */
 void amdgpu_bo_kunmap(struct amdgpu_bo *bo)
 {
 	if (bo->kmap.bo)
 		ttm_bo_kunmap(&bo->kmap);
 }
 
+/**
+ * amdgpu_bo_ref - reference an &amdgpu_bo buffer object
+ * @bo: &amdgpu_bo buffer object
+ *
+ * References the contained &ttm_buffer_object.
+ *
+ * Returns:
+ * a refcounted pointer to the &amdgpu_bo buffer object.
+ */
 struct amdgpu_bo *amdgpu_bo_ref(struct amdgpu_bo *bo)
 {
 	if (bo == NULL)
 		return NULL;
 
-	ttm_bo_reference(&bo->tbo);
+	ttm_bo_get(&bo->tbo);
 	return bo;
 }
 
+/**
+ * amdgpu_bo_unref - unreference an &amdgpu_bo buffer object
+ * @bo: &amdgpu_bo buffer object
+ *
+ * Unreferences the contained &ttm_buffer_object and clear the pointer
+ */
 void amdgpu_bo_unref(struct amdgpu_bo **bo)
 {
 	struct ttm_buffer_object *tbo;
@@ -673,14 +843,34 @@ void amdgpu_bo_unref(struct amdgpu_bo **bo)
 		return;
 
 	tbo = &((*bo)->tbo);
-	ttm_bo_unref(&tbo);
-	if (tbo == NULL)
-		*bo = NULL;
+	ttm_bo_put(tbo);
+	*bo = NULL;
 }
 
+/**
+ * amdgpu_bo_pin_restricted - pin an &amdgpu_bo buffer object
+ * @bo: &amdgpu_bo buffer object to be pinned
+ * @domain: domain to be pinned to
+ * @min_offset: the start of requested address range
+ * @max_offset: the end of requested address range
+ *
+ * Pins the buffer object according to requested domain and address range. If
+ * the memory is unbound gart memory, binds the pages into gart table. Adjusts
+ * pin_count and pin_size accordingly.
+ *
+ * Pinning means to lock pages in memory along with keeping them at a fixed
+ * offset. It is required when a buffer can not be moved, for example, when
+ * a display buffer is being scanned out.
+ *
+ * Compared with amdgpu_bo_pin(), this function gives more flexibility on
+ * where to pin a buffer if there are specific restrictions on where a buffer
+ * must be located.
+ *
+ * Returns:
+ * 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
-			     u64 min_offset, u64 max_offset,
-			     u64 *gpu_addr)
+			     u64 min_offset, u64 max_offset)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	struct ttm_operation_ctx ctx = { false, false };
@@ -712,8 +902,6 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 			return -EINVAL;
 
 		bo->pin_count++;
-		if (gpu_addr)
-			*gpu_addr = amdgpu_bo_gpu_offset(bo);
 
 		if (max_offset != 0) {
 			u64 domain_start = bo->tbo.bdev->man[mem_type].gpu_offset;
@@ -728,7 +916,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 	/* force to pin into visible video ram */
 	if (!(bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS))
 		bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
-	amdgpu_ttm_placement_from_domain(bo, domain);
+	amdgpu_bo_placement_from_domain(bo, domain);
 	for (i = 0; i < bo->placement.num_placement; i++) {
 		unsigned fpfn, lpfn;
 
@@ -749,33 +937,48 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 		goto error;
 	}
 
-	r = amdgpu_ttm_alloc_gart(&bo->tbo);
-	if (unlikely(r)) {
-		dev_err(adev->dev, "%p bind failed\n", bo);
-		goto error;
-	}
-
 	bo->pin_count = 1;
-	if (gpu_addr != NULL)
-		*gpu_addr = amdgpu_bo_gpu_offset(bo);
 
 	domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type);
 	if (domain == AMDGPU_GEM_DOMAIN_VRAM) {
-		adev->vram_pin_size += amdgpu_bo_size(bo);
-		adev->invisible_pin_size += amdgpu_vram_mgr_bo_invisible_size(bo);
+		atomic64_add(amdgpu_bo_size(bo), &adev->vram_pin_size);
+		atomic64_add(amdgpu_vram_mgr_bo_visible_size(bo),
+			     &adev->visible_pin_size);
 	} else if (domain == AMDGPU_GEM_DOMAIN_GTT) {
-		adev->gart_pin_size += amdgpu_bo_size(bo);
+		atomic64_add(amdgpu_bo_size(bo), &adev->gart_pin_size);
 	}
 
 error:
 	return r;
 }
 
-int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain, u64 *gpu_addr)
+/**
+ * amdgpu_bo_pin - pin an &amdgpu_bo buffer object
+ * @bo: &amdgpu_bo buffer object to be pinned
+ * @domain: domain to be pinned to
+ *
+ * A simple wrapper to amdgpu_bo_pin_restricted().
+ * Provides a simpler API for buffers that do not have any strict restrictions
+ * on where a buffer must be located.
+ *
+ * Returns:
+ * 0 for success or a negative error code on failure.
+ */
+int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain)
 {
-	return amdgpu_bo_pin_restricted(bo, domain, 0, 0, gpu_addr);
+	return amdgpu_bo_pin_restricted(bo, domain, 0, 0);
 }
 
+/**
+ * amdgpu_bo_unpin - unpin an &amdgpu_bo buffer object
+ * @bo: &amdgpu_bo buffer object to be unpinned
+ *
+ * Decreases the pin_count, and clears the flags if pin_count reaches 0.
+ * Changes placement and pin size accordingly.
+ *
+ * Returns:
+ * 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_unpin(struct amdgpu_bo *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
@@ -790,12 +993,7 @@ int amdgpu_bo_unpin(struct amdgpu_bo *bo)
 	if (bo->pin_count)
 		return 0;
 
-	if (bo->tbo.mem.mem_type == TTM_PL_VRAM) {
-		adev->vram_pin_size -= amdgpu_bo_size(bo);
-		adev->invisible_pin_size -= amdgpu_vram_mgr_bo_invisible_size(bo);
-	} else if (bo->tbo.mem.mem_type == TTM_PL_TT) {
-		adev->gart_pin_size -= amdgpu_bo_size(bo);
-	}
+	amdgpu_bo_subtract_pin_size(bo);
 
 	for (i = 0; i < bo->placement.num_placement; i++) {
 		bo->placements[i].lpfn = 0;
@@ -808,6 +1006,16 @@ int amdgpu_bo_unpin(struct amdgpu_bo *bo)
 	return r;
 }
 
+/**
+ * amdgpu_bo_evict_vram - evict VRAM buffers
+ * @adev: amdgpu device object
+ *
+ * Evicts all VRAM buffers on the lru list of the memory type.
+ * Mainly used for evicting vram at suspend time.
+ *
+ * Returns:
+ * 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_evict_vram(struct amdgpu_device *adev)
 {
 	/* late 2.6.33 fix IGP hibernate - we need pm ops to do this correct */
@@ -830,6 +1038,15 @@ static const char *amdgpu_vram_names[] = {
 	"DDR4",
 };
 
+/**
+ * amdgpu_bo_init - initialize memory manager
+ * @adev: amdgpu device object
+ *
+ * Calls amdgpu_ttm_init() to initialize amdgpu memory manager.
+ *
+ * Returns:
+ * 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_init(struct amdgpu_device *adev)
 {
 	/* reserve PAT memory space to WC for VRAM */
@@ -847,6 +1064,16 @@ int amdgpu_bo_init(struct amdgpu_device *adev)
 	return amdgpu_ttm_init(adev);
 }
 
+/**
+ * amdgpu_bo_late_init - late init
+ * @adev: amdgpu device object
+ *
+ * Calls amdgpu_ttm_late_init() to free resources used earlier during
+ * initialization.
+ *
+ * Returns:
+ * 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_late_init(struct amdgpu_device *adev)
 {
 	amdgpu_ttm_late_init(adev);
@@ -854,6 +1081,12 @@ int amdgpu_bo_late_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+/**
+ * amdgpu_bo_fini - tear down memory manager
+ * @adev: amdgpu device object
+ *
+ * Reverses amdgpu_bo_init() to tear down memory manager.
+ */
 void amdgpu_bo_fini(struct amdgpu_device *adev)
 {
 	amdgpu_ttm_fini(adev);
@@ -861,12 +1094,33 @@ void amdgpu_bo_fini(struct amdgpu_device *adev)
 	arch_io_free_memtype_wc(adev->gmc.aper_base, adev->gmc.aper_size);
 }
 
+/**
+ * amdgpu_bo_fbdev_mmap - mmap fbdev memory
+ * @bo: &amdgpu_bo buffer object
+ * @vma: vma as input from the fbdev mmap method
+ *
+ * Calls ttm_fbdev_mmap() to mmap fbdev memory if it is backed by a bo.
+ *
+ * Returns:
+ * 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_fbdev_mmap(struct amdgpu_bo *bo,
 			     struct vm_area_struct *vma)
 {
 	return ttm_fbdev_mmap(vma, &bo->tbo);
 }
 
+/**
+ * amdgpu_bo_set_tiling_flags - set tiling flags
+ * @bo: &amdgpu_bo buffer object
+ * @tiling_flags: new flags
+ *
+ * Sets buffer object's tiling flags with the new one. Used by GEM ioctl or
+ * kernel driver to set the tiling flags on a buffer.
+ *
+ * Returns:
+ * 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_set_tiling_flags(struct amdgpu_bo *bo, u64 tiling_flags)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
@@ -879,6 +1133,14 @@ int amdgpu_bo_set_tiling_flags(struct amdgpu_bo *bo, u64 tiling_flags)
 	return 0;
 }
 
+/**
+ * amdgpu_bo_get_tiling_flags - get tiling flags
+ * @bo: &amdgpu_bo buffer object
+ * @tiling_flags: returned flags
+ *
+ * Gets buffer object's tiling flags. Used by GEM ioctl or kernel driver to
+ * set the tiling flags on a buffer.
+ */
 void amdgpu_bo_get_tiling_flags(struct amdgpu_bo *bo, u64 *tiling_flags)
 {
 	lockdep_assert_held(&bo->tbo.resv->lock.base);
@@ -887,6 +1149,19 @@ void amdgpu_bo_get_tiling_flags(struct amdgpu_bo *bo, u64 *tiling_flags)
 		*tiling_flags = bo->tiling_flags;
 }
 
+/**
+ * amdgpu_bo_set_metadata - set metadata
+ * @bo: &amdgpu_bo buffer object
+ * @metadata: new metadata
+ * @metadata_size: size of the new metadata
+ * @flags: flags of the new metadata
+ *
+ * Sets buffer object's metadata, its size and flags.
+ * Used via GEM ioctl.
+ *
+ * Returns:
+ * 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata,
 			    uint32_t metadata_size, uint64_t flags)
 {
@@ -916,6 +1191,21 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata,
 	return 0;
 }
 
+/**
+ * amdgpu_bo_get_metadata - get metadata
+ * @bo: &amdgpu_bo buffer object
+ * @buffer: returned metadata
+ * @buffer_size: size of the buffer
+ * @metadata_size: size of the returned metadata
+ * @flags: flags of the returned metadata
+ *
+ * Gets buffer object's metadata, its size and flags. buffer_size shall not be
+ * less than metadata_size.
+ * Used via GEM ioctl.
+ *
+ * Returns:
+ * 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
 			   size_t buffer_size, uint32_t *metadata_size,
 			   uint64_t *flags)
@@ -939,6 +1229,16 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
 	return 0;
 }
 
+/**
+ * amdgpu_bo_move_notify - notification about a memory move
+ * @bo: pointer to a buffer object
+ * @evict: if this move is evicting the buffer from the graphics address space
+ * @new_mem: new information of the bufer object
+ *
+ * Marks the corresponding &amdgpu_bo buffer object as invalid, also performs
+ * bookkeeping.
+ * TTM driver callback which is called when ttm moves a buffer.
+ */
 void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 			   bool evict,
 			   struct ttm_mem_reg *new_mem)
@@ -947,7 +1247,7 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 	struct amdgpu_bo *abo;
 	struct ttm_mem_reg *old_mem = &bo->mem;
 
-	if (!amdgpu_ttm_bo_is_amdgpu_bo(bo))
+	if (!amdgpu_bo_is_amdgpu_bo(bo))
 		return;
 
 	abo = ttm_to_amdgpu_bo(bo);
@@ -964,9 +1264,20 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 		return;
 
 	/* move_notify is called before move happens */
-	trace_amdgpu_ttm_bo_move(abo, new_mem->mem_type, old_mem->mem_type);
+	trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type);
 }
 
+/**
+ * amdgpu_bo_fault_reserve_notify - notification about a memory fault
+ * @bo: pointer to a buffer object
+ *
+ * Notifies the driver we are taking a fault on this BO and have reserved it,
+ * also performs bookkeeping.
+ * TTM driver callback for dealing with vm faults.
+ *
+ * Returns:
+ * 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
@@ -975,7 +1286,7 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 	unsigned long offset, size;
 	int r;
 
-	if (!amdgpu_ttm_bo_is_amdgpu_bo(bo))
+	if (!amdgpu_bo_is_amdgpu_bo(bo))
 		return 0;
 
 	abo = ttm_to_amdgpu_bo(bo);
@@ -997,8 +1308,8 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 
 	/* hurrah the memory is not visible ! */
 	atomic64_inc(&adev->num_vram_cpu_page_faults);
-	amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM |
-					 AMDGPU_GEM_DOMAIN_GTT);
+	amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM |
+					AMDGPU_GEM_DOMAIN_GTT);
 
 	/* Avoid costly evictions; only set GTT as a busy placement */
 	abo->placement.num_busy_placement = 1;
@@ -1040,10 +1351,11 @@ void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence,
  * amdgpu_bo_gpu_offset - return GPU offset of bo
  * @bo:	amdgpu object for which we query the offset
  *
- * Returns current GPU offset of the object.
- *
  * Note: object should either be pinned or reserved when calling this
  * function, it might be useful to add check for this for debugging.
+ *
+ * Returns:
+ * current GPU offset of the object.
  */
 u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo)
 {
@@ -1059,6 +1371,14 @@ u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo)
 	return bo->tbo.offset;
 }
 
+/**
+ * amdgpu_bo_get_preferred_pin_domain - get preferred domain for scanout
+ * @adev: amdgpu device object
+ * @domain: allowed :ref:`memory domains <amdgpu_memory_domains>`
+ *
+ * Returns:
+ * Which of the allowed domains is preferred for pinning the BO for scanout.
+ */
 uint32_t amdgpu_bo_get_preferred_pin_domain(struct amdgpu_device *adev,
 					    uint32_t domain)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 731748033878..18945dd6982d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -32,6 +32,7 @@
 #include "amdgpu.h"
 
 #define AMDGPU_BO_INVALID_OFFSET	LONG_MAX
+#define AMDGPU_BO_MAX_PLACEMENTS	3
 
 struct amdgpu_bo_param {
 	unsigned long			size;
@@ -77,7 +78,7 @@ struct amdgpu_bo {
 	/* Protected by tbo.reserved */
 	u32				preferred_domains;
 	u32				allowed_domains;
-	struct ttm_place		placements[AMDGPU_GEM_DOMAIN_MAX + 1];
+	struct ttm_place		placements[AMDGPU_BO_MAX_PLACEMENTS];
 	struct ttm_placement		placement;
 	struct ttm_buffer_object	tbo;
 	struct ttm_bo_kmap_obj		kmap;
@@ -234,6 +235,9 @@ static inline bool amdgpu_bo_explicit_sync(struct amdgpu_bo *bo)
 	return bo->flags & AMDGPU_GEM_CREATE_EXPLICIT_SYNC;
 }
 
+bool amdgpu_bo_is_amdgpu_bo(struct ttm_buffer_object *bo);
+void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain);
+
 int amdgpu_bo_create(struct amdgpu_device *adev,
 		     struct amdgpu_bo_param *bp,
 		     struct amdgpu_bo **bo_ptr);
@@ -252,10 +256,9 @@ void *amdgpu_bo_kptr(struct amdgpu_bo *bo);
 void amdgpu_bo_kunmap(struct amdgpu_bo *bo);
 struct amdgpu_bo *amdgpu_bo_ref(struct amdgpu_bo *bo);
 void amdgpu_bo_unref(struct amdgpu_bo **bo);
-int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain, u64 *gpu_addr);
+int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain);
 int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
-			     u64 min_offset, u64 max_offset,
-			     u64 *gpu_addr);
+			     u64 min_offset, u64 max_offset);
 int amdgpu_bo_unpin(struct amdgpu_bo *bo);
 int amdgpu_bo_evict_vram(struct amdgpu_device *adev);
 int amdgpu_bo_init(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index fc818b4d849c..8f98629fbe59 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -31,7 +31,7 @@
 #include <linux/power_supply.h>
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
-
+#include <linux/nospec.h>
 
 static int amdgpu_debugfs_pm_init(struct amdgpu_device *adev);
 
@@ -68,11 +68,11 @@ void amdgpu_pm_acpi_event_handler(struct amdgpu_device *adev)
 	if (adev->pm.dpm_enabled) {
 		mutex_lock(&adev->pm.mutex);
 		if (power_supply_is_system_supplied() > 0)
-			adev->pm.dpm.ac_power = true;
+			adev->pm.ac_power = true;
 		else
-			adev->pm.dpm.ac_power = false;
+			adev->pm.ac_power = false;
 		if (adev->powerplay.pp_funcs->enable_bapm)
-			amdgpu_dpm_enable_bapm(adev, adev->pm.dpm.ac_power);
+			amdgpu_dpm_enable_bapm(adev, adev->pm.ac_power);
 		mutex_unlock(&adev->pm.mutex);
 	}
 }
@@ -80,12 +80,15 @@ void amdgpu_pm_acpi_event_handler(struct amdgpu_device *adev)
 /**
  * DOC: power_dpm_state
  *
- * This is a legacy interface and is only provided for backwards compatibility.
- * The amdgpu driver provides a sysfs API for adjusting certain power
- * related parameters.  The file power_dpm_state is used for this.
+ * The power_dpm_state file is a legacy interface and is only provided for
+ * backwards compatibility. The amdgpu driver provides a sysfs API for adjusting
+ * certain power related parameters.  The file power_dpm_state is used for this.
  * It accepts the following arguments:
+ *
  * - battery
+ *
  * - balanced
+ *
  * - performance
  *
  * battery
@@ -169,14 +172,21 @@ fail:
  * The amdgpu driver provides a sysfs API for adjusting certain power
  * related parameters.  The file power_dpm_force_performance_level is
  * used for this.  It accepts the following arguments:
+ *
  * - auto
+ *
  * - low
+ *
  * - high
+ *
  * - manual
- * - GPU fan
+ *
  * - profile_standard
+ *
  * - profile_min_sclk
+ *
  * - profile_min_mclk
+ *
  * - profile_peak
  *
  * auto
@@ -393,6 +403,7 @@ static ssize_t amdgpu_set_pp_force_state(struct device *dev,
 			count = -EINVAL;
 			goto fail;
 		}
+		idx = array_index_nospec(idx, ARRAY_SIZE(data.states));
 
 		amdgpu_dpm_get_pp_num_states(adev, &data);
 		state = data.states[idx];
@@ -463,8 +474,11 @@ static ssize_t amdgpu_set_pp_table(struct device *dev,
  * this.
  *
  * Reading the file will display:
+ *
  * - a list of engine clock levels and voltages labeled OD_SCLK
+ *
  * - a list of memory clock levels and voltages labeled OD_MCLK
+ *
  * - a list of valid ranges for sclk, mclk, and voltage labeled OD_RANGE
  *
  * To manually adjust these settings, first select manual using
@@ -593,40 +607,59 @@ static ssize_t amdgpu_get_pp_dpm_sclk(struct device *dev,
 		return snprintf(buf, PAGE_SIZE, "\n");
 }
 
-static ssize_t amdgpu_set_pp_dpm_sclk(struct device *dev,
-		struct device_attribute *attr,
-		const char *buf,
-		size_t count)
+/*
+ * Worst case: 32 bits individually specified, in octal at 12 characters
+ * per line (+1 for \n).
+ */
+#define AMDGPU_MASK_BUF_MAX	(32 * 13)
+
+static ssize_t amdgpu_read_mask(const char *buf, size_t count, uint32_t *mask)
 {
-	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
 	int ret;
 	long level;
-	uint32_t mask = 0;
 	char *sub_str = NULL;
 	char *tmp;
-	char buf_cpy[count];
+	char buf_cpy[AMDGPU_MASK_BUF_MAX + 1];
 	const char delimiter[3] = {' ', '\n', '\0'};
+	size_t bytes;
 
-	memcpy(buf_cpy, buf, count+1);
+	*mask = 0;
+
+	bytes = min(count, sizeof(buf_cpy) - 1);
+	memcpy(buf_cpy, buf, bytes);
+	buf_cpy[bytes] = '\0';
 	tmp = buf_cpy;
 	while (tmp[0]) {
-		sub_str =  strsep(&tmp, delimiter);
+		sub_str = strsep(&tmp, delimiter);
 		if (strlen(sub_str)) {
 			ret = kstrtol(sub_str, 0, &level);
-
-			if (ret) {
-				count = -EINVAL;
-				goto fail;
-			}
-			mask |= 1 << level;
+			if (ret)
+				return -EINVAL;
+			*mask |= 1 << level;
 		} else
 			break;
 	}
+
+	return 0;
+}
+
+static ssize_t amdgpu_set_pp_dpm_sclk(struct device *dev,
+		struct device_attribute *attr,
+		const char *buf,
+		size_t count)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = ddev->dev_private;
+	int ret;
+	uint32_t mask = 0;
+
+	ret = amdgpu_read_mask(buf, count, &mask);
+	if (ret)
+		return ret;
+
 	if (adev->powerplay.pp_funcs->force_clock_level)
 		amdgpu_dpm_force_clock_level(adev, PP_SCLK, mask);
 
-fail:
 	return count;
 }
 
@@ -651,32 +684,15 @@ static ssize_t amdgpu_set_pp_dpm_mclk(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	int ret;
-	long level;
 	uint32_t mask = 0;
-	char *sub_str = NULL;
-	char *tmp;
-	char buf_cpy[count];
-	const char delimiter[3] = {' ', '\n', '\0'};
 
-	memcpy(buf_cpy, buf, count+1);
-	tmp = buf_cpy;
-	while (tmp[0]) {
-		sub_str =  strsep(&tmp, delimiter);
-		if (strlen(sub_str)) {
-			ret = kstrtol(sub_str, 0, &level);
+	ret = amdgpu_read_mask(buf, count, &mask);
+	if (ret)
+		return ret;
 
-			if (ret) {
-				count = -EINVAL;
-				goto fail;
-			}
-			mask |= 1 << level;
-		} else
-			break;
-	}
 	if (adev->powerplay.pp_funcs->force_clock_level)
 		amdgpu_dpm_force_clock_level(adev, PP_MCLK, mask);
 
-fail:
 	return count;
 }
 
@@ -701,33 +717,15 @@ static ssize_t amdgpu_set_pp_dpm_pcie(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	int ret;
-	long level;
 	uint32_t mask = 0;
-	char *sub_str = NULL;
-	char *tmp;
-	char buf_cpy[count];
-	const char delimiter[3] = {' ', '\n', '\0'};
 
-	memcpy(buf_cpy, buf, count+1);
-	tmp = buf_cpy;
-
-	while (tmp[0]) {
-		sub_str =  strsep(&tmp, delimiter);
-		if (strlen(sub_str)) {
-			ret = kstrtol(sub_str, 0, &level);
+	ret = amdgpu_read_mask(buf, count, &mask);
+	if (ret)
+		return ret;
 
-			if (ret) {
-				count = -EINVAL;
-				goto fail;
-			}
-			mask |= 1 << level;
-		} else
-			break;
-	}
 	if (adev->powerplay.pp_funcs->force_clock_level)
 		amdgpu_dpm_force_clock_level(adev, PP_PCIE, mask);
 
-fail:
 	return count;
 }
 
@@ -905,6 +903,36 @@ fail:
 	return -EINVAL;
 }
 
+/**
+ * DOC: busy_percent
+ *
+ * The amdgpu driver provides a sysfs API for reading how busy the GPU
+ * is as a percentage.  The file gpu_busy_percent is used for this.
+ * The SMU firmware computes a percentage of load based on the
+ * aggregate activity level in the IP cores.
+ */
+static ssize_t amdgpu_get_busy_percent(struct device *dev,
+		struct device_attribute *attr,
+		char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = ddev->dev_private;
+	int r, value, size = sizeof(value);
+
+	/* sanity check PP is enabled */
+	if (!(adev->powerplay.pp_funcs &&
+	      adev->powerplay.pp_funcs->read_sensor))
+		return -EINVAL;
+
+	/* read the IP busy sensor */
+	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_LOAD,
+				   (void *)&value, &size);
+	if (r)
+		return r;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", value);
+}
+
 static DEVICE_ATTR(power_dpm_state, S_IRUGO | S_IWUSR, amdgpu_get_dpm_state, amdgpu_set_dpm_state);
 static DEVICE_ATTR(power_dpm_force_performance_level, S_IRUGO | S_IWUSR,
 		   amdgpu_get_dpm_forced_performance_level,
@@ -938,6 +966,8 @@ static DEVICE_ATTR(pp_power_profile_mode, S_IRUGO | S_IWUSR,
 static DEVICE_ATTR(pp_od_clk_voltage, S_IRUGO | S_IWUSR,
 		amdgpu_get_pp_od_clk_voltage,
 		amdgpu_set_pp_od_clk_voltage);
+static DEVICE_ATTR(gpu_busy_percent, S_IRUGO,
+		amdgpu_get_busy_percent, NULL);
 
 static ssize_t amdgpu_hwmon_show_temp(struct device *dev,
 				      struct device_attribute *attr,
@@ -1156,7 +1186,7 @@ static ssize_t amdgpu_hwmon_show_vddnb(struct device *dev,
 	int r, size = sizeof(vddnb);
 
 	/* only APUs have vddnb */
-	if  (adev->flags & AMD_IS_APU)
+	if  (!(adev->flags & AMD_IS_APU))
 		return -EINVAL;
 
 	/* Can't get voltage when the card is off */
@@ -1285,35 +1315,51 @@ static ssize_t amdgpu_hwmon_set_power_cap(struct device *dev,
  * DOC: hwmon
  *
  * The amdgpu driver exposes the following sensor interfaces:
+ *
  * - GPU temperature (via the on-die sensor)
+ *
  * - GPU voltage
+ *
  * - Northbridge voltage (APUs only)
+ *
  * - GPU power
+ *
  * - GPU fan
  *
  * hwmon interfaces for GPU temperature:
+ *
  * - temp1_input: the on die GPU temperature in millidegrees Celsius
+ *
  * - temp1_crit: temperature critical max value in millidegrees Celsius
+ *
  * - temp1_crit_hyst: temperature hysteresis for critical limit in millidegrees Celsius
  *
  * hwmon interfaces for GPU voltage:
+ *
  * - in0_input: the voltage on the GPU in millivolts
+ *
  * - in1_input: the voltage on the Northbridge in millivolts
  *
  * hwmon interfaces for GPU power:
+ *
  * - power1_average: average power used by the GPU in microWatts
+ *
  * - power1_cap_min: minimum cap supported in microWatts
+ *
  * - power1_cap_max: maximum cap supported in microWatts
+ *
  * - power1_cap: selected power cap in microWatts
  *
  * hwmon interfaces for GPU fan:
+ *
  * - pwm1: pulse width modulation fan level (0-255)
- * - pwm1_enable: pulse width modulation fan control method
- *                0: no fan speed control
- *                1: manual fan speed control using pwm interface
- *                2: automatic fan speed control
+ *
+ * - pwm1_enable: pulse width modulation fan control method (0: no fan speed control, 1: manual fan speed control using pwm interface, 2: automatic fan speed control)
+ *
  * - pwm1_min: pulse width modulation fan control minimum level (0)
+ *
  * - pwm1_max: pulse width modulation fan control maximum level (255)
+ *
  * - fan1_input: fan speed in RPM
  *
  * You can use hwmon tools like sensors to view this information on your system.
@@ -1668,10 +1714,10 @@ static void amdgpu_dpm_change_power_state_locked(struct amdgpu_device *adev)
 
 void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable)
 {
-	if (adev->powerplay.pp_funcs->powergate_uvd) {
+	if (adev->powerplay.pp_funcs->set_powergating_by_smu) {
 		/* enable/disable UVD */
 		mutex_lock(&adev->pm.mutex);
-		amdgpu_dpm_powergate_uvd(adev, !enable);
+		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_UVD, !enable);
 		mutex_unlock(&adev->pm.mutex);
 	} else {
 		if (enable) {
@@ -1690,10 +1736,10 @@ void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable)
 
 void amdgpu_dpm_enable_vce(struct amdgpu_device *adev, bool enable)
 {
-	if (adev->powerplay.pp_funcs->powergate_vce) {
+	if (adev->powerplay.pp_funcs->set_powergating_by_smu) {
 		/* enable/disable VCE */
 		mutex_lock(&adev->pm.mutex);
-		amdgpu_dpm_powergate_vce(adev, !enable);
+		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_VCE, !enable);
 		mutex_unlock(&adev->pm.mutex);
 	} else {
 		if (enable) {
@@ -1825,6 +1871,13 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev)
 				"pp_od_clk_voltage\n");
 		return ret;
 	}
+	ret = device_create_file(adev->dev,
+			&dev_attr_gpu_busy_percent);
+	if (ret) {
+		DRM_ERROR("failed to create device file	"
+				"gpu_busy_level\n");
+		return ret;
+	}
 	ret = amdgpu_debugfs_pm_init(adev);
 	if (ret) {
 		DRM_ERROR("Failed to register debugfs file for dpm!\n");
@@ -1860,6 +1913,7 @@ void amdgpu_pm_sysfs_fini(struct amdgpu_device *adev)
 			&dev_attr_pp_power_profile_mode);
 	device_remove_file(adev->dev,
 			&dev_attr_pp_od_clk_voltage);
+	device_remove_file(adev->dev, &dev_attr_gpu_busy_percent);
 }
 
 void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
@@ -1878,6 +1932,14 @@ void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
 			amdgpu_fence_wait_empty(ring);
 	}
 
+	mutex_lock(&adev->pm.mutex);
+	/* update battery/ac status */
+	if (power_supply_is_system_supplied() > 0)
+		adev->pm.ac_power = true;
+	else
+		adev->pm.ac_power = false;
+	mutex_unlock(&adev->pm.mutex);
+
 	if (adev->powerplay.pp_funcs->dispatch_tasks) {
 		if (!amdgpu_device_has_dc_support(adev)) {
 			mutex_lock(&adev->pm.mutex);
@@ -1898,14 +1960,7 @@ void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
 	} else {
 		mutex_lock(&adev->pm.mutex);
 		amdgpu_dpm_get_active_displays(adev);
-		/* update battery/ac status */
-		if (power_supply_is_system_supplied() > 0)
-			adev->pm.dpm.ac_power = true;
-		else
-			adev->pm.dpm.ac_power = false;
-
 		amdgpu_dpm_change_power_state_locked(adev);
-
 		mutex_unlock(&adev->pm.mutex);
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index 4683626b065f..1c5d97f4b4dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -23,6 +23,14 @@
  *
  * Authors: Alex Deucher
  */
+
+/**
+ * DOC: PRIME Buffer Sharing
+ *
+ * The following callback implementations are used for :ref:`sharing GEM buffer
+ * objects between different devices via PRIME <prime_buffer_sharing>`.
+ */
+
 #include <drm/drmP.h>
 
 #include "amdgpu.h"
@@ -32,6 +40,14 @@
 
 static const struct dma_buf_ops amdgpu_dmabuf_ops;
 
+/**
+ * amdgpu_gem_prime_get_sg_table - &drm_driver.gem_prime_get_sg_table
+ * implementation
+ * @obj: GEM buffer object
+ *
+ * Returns:
+ * A scatter/gather table for the pinned pages of the buffer object's memory.
+ */
 struct sg_table *amdgpu_gem_prime_get_sg_table(struct drm_gem_object *obj)
 {
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
@@ -40,6 +56,15 @@ struct sg_table *amdgpu_gem_prime_get_sg_table(struct drm_gem_object *obj)
 	return drm_prime_pages_to_sg(bo->tbo.ttm->pages, npages);
 }
 
+/**
+ * amdgpu_gem_prime_vmap - &dma_buf_ops.vmap implementation
+ * @obj: GEM buffer object
+ *
+ * Sets up an in-kernel virtual mapping of the buffer object's memory.
+ *
+ * Returns:
+ * The virtual address of the mapping or an error pointer.
+ */
 void *amdgpu_gem_prime_vmap(struct drm_gem_object *obj)
 {
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
@@ -53,6 +78,13 @@ void *amdgpu_gem_prime_vmap(struct drm_gem_object *obj)
 	return bo->dma_buf_vmap.virtual;
 }
 
+/**
+ * amdgpu_gem_prime_vunmap - &dma_buf_ops.vunmap implementation
+ * @obj: GEM buffer object
+ * @vaddr: virtual address (unused)
+ *
+ * Tears down the in-kernel virtual mapping of the buffer object's memory.
+ */
 void amdgpu_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
 {
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
@@ -60,6 +92,17 @@ void amdgpu_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
 	ttm_bo_kunmap(&bo->dma_buf_vmap);
 }
 
+/**
+ * amdgpu_gem_prime_mmap - &drm_driver.gem_prime_mmap implementation
+ * @obj: GEM buffer object
+ * @vma: virtual memory area
+ *
+ * Sets up a userspace mapping of the buffer object's memory in the given
+ * virtual memory area.
+ *
+ * Returns:
+ * 0 on success or negative error code.
+ */
 int amdgpu_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
 {
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
@@ -94,6 +137,19 @@ int amdgpu_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma
 	return ret;
 }
 
+/**
+ * amdgpu_gem_prime_import_sg_table - &drm_driver.gem_prime_import_sg_table
+ * implementation
+ * @dev: DRM device
+ * @attach: DMA-buf attachment
+ * @sg: Scatter/gather table
+ *
+ * Import shared DMA buffer memory exported by another device.
+ *
+ * Returns:
+ * A new GEM buffer object of the given DRM device, representing the memory
+ * described by the given DMA-buf attachment and scatter/gather table.
+ */
 struct drm_gem_object *
 amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
 				 struct dma_buf_attachment *attach,
@@ -132,8 +188,19 @@ error:
 	return ERR_PTR(ret);
 }
 
+/**
+ * amdgpu_gem_map_attach - &dma_buf_ops.attach implementation
+ * @dma_buf: shared DMA buffer
+ * @attach: DMA-buf attachment
+ *
+ * Makes sure that the shared DMA buffer can be accessed by the target device.
+ * For now, simply pins it to the GTT domain, where it should be accessible by
+ * all DMA devices.
+ *
+ * Returns:
+ * 0 on success or negative error code.
+ */
 static int amdgpu_gem_map_attach(struct dma_buf *dma_buf,
-				 struct device *target_dev,
 				 struct dma_buf_attachment *attach)
 {
 	struct drm_gem_object *obj = dma_buf->priv;
@@ -141,7 +208,7 @@ static int amdgpu_gem_map_attach(struct dma_buf *dma_buf,
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	long r;
 
-	r = drm_gem_map_attach(dma_buf, target_dev, attach);
+	r = drm_gem_map_attach(dma_buf, attach);
 	if (r)
 		return r;
 
@@ -165,7 +232,7 @@ static int amdgpu_gem_map_attach(struct dma_buf *dma_buf,
 	}
 
 	/* pin buffer into GTT */
-	r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT, NULL);
+	r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
 	if (r)
 		goto error_unreserve;
 
@@ -181,6 +248,14 @@ error_detach:
 	return r;
 }
 
+/**
+ * amdgpu_gem_map_detach - &dma_buf_ops.detach implementation
+ * @dma_buf: shared DMA buffer
+ * @attach: DMA-buf attachment
+ *
+ * This is called when a shared DMA buffer no longer needs to be accessible by
+ * the other device. For now, simply unpins the buffer from GTT.
+ */
 static void amdgpu_gem_map_detach(struct dma_buf *dma_buf,
 				  struct dma_buf_attachment *attach)
 {
@@ -202,6 +277,13 @@ error:
 	drm_gem_map_detach(dma_buf, attach);
 }
 
+/**
+ * amdgpu_gem_prime_res_obj - &drm_driver.gem_prime_res_obj implementation
+ * @obj: GEM buffer object
+ *
+ * Returns:
+ * The buffer object's reservation object.
+ */
 struct reservation_object *amdgpu_gem_prime_res_obj(struct drm_gem_object *obj)
 {
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
@@ -209,6 +291,18 @@ struct reservation_object *amdgpu_gem_prime_res_obj(struct drm_gem_object *obj)
 	return bo->tbo.resv;
 }
 
+/**
+ * amdgpu_gem_begin_cpu_access - &dma_buf_ops.begin_cpu_access implementation
+ * @dma_buf: shared DMA buffer
+ * @direction: direction of DMA transfer
+ *
+ * This is called before CPU access to the shared DMA buffer's memory. If it's
+ * a read access, the buffer is moved to the GTT domain if possible, for optimal
+ * CPU read performance.
+ *
+ * Returns:
+ * 0 on success or negative error code.
+ */
 static int amdgpu_gem_begin_cpu_access(struct dma_buf *dma_buf,
 				       enum dma_data_direction direction)
 {
@@ -229,7 +323,7 @@ static int amdgpu_gem_begin_cpu_access(struct dma_buf *dma_buf,
 		return ret;
 
 	if (!bo->pin_count && (bo->allowed_domains & AMDGPU_GEM_DOMAIN_GTT)) {
-		amdgpu_ttm_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
+		amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
 		ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	}
 
@@ -245,14 +339,24 @@ static const struct dma_buf_ops amdgpu_dmabuf_ops = {
 	.release = drm_gem_dmabuf_release,
 	.begin_cpu_access = amdgpu_gem_begin_cpu_access,
 	.map = drm_gem_dmabuf_kmap,
-	.map_atomic = drm_gem_dmabuf_kmap_atomic,
 	.unmap = drm_gem_dmabuf_kunmap,
-	.unmap_atomic = drm_gem_dmabuf_kunmap_atomic,
 	.mmap = drm_gem_dmabuf_mmap,
 	.vmap = drm_gem_dmabuf_vmap,
 	.vunmap = drm_gem_dmabuf_vunmap,
 };
 
+/**
+ * amdgpu_gem_prime_export - &drm_driver.gem_prime_export implementation
+ * @dev: DRM device
+ * @gobj: GEM buffer object
+ * @flags: flags like DRM_CLOEXEC and DRM_RDWR
+ *
+ * The main work is done by the &drm_gem_prime_export helper, which in turn
+ * uses &amdgpu_gem_prime_res_obj.
+ *
+ * Returns:
+ * Shared DMA buffer representing the GEM buffer object from the given device.
+ */
 struct dma_buf *amdgpu_gem_prime_export(struct drm_device *dev,
 					struct drm_gem_object *gobj,
 					int flags)
@@ -273,6 +377,17 @@ struct dma_buf *amdgpu_gem_prime_export(struct drm_device *dev,
 	return buf;
 }
 
+/**
+ * amdgpu_gem_prime_import - &drm_driver.gem_prime_import implementation
+ * @dev: DRM device
+ * @dma_buf: Shared DMA buffer
+ *
+ * The main work is done by the &drm_gem_prime_import helper, which in turn
+ * uses &amdgpu_gem_prime_import_sg_table.
+ *
+ * Returns:
+ * GEM buffer object representing the shared DMA buffer for the given device.
+ */
 struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev,
 					    struct dma_buf *dma_buf)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
index 8af16e81c7d4..a172bba32b45 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
@@ -66,8 +66,6 @@ static int amdgpu_identity_map(struct amdgpu_device *adev,
 			       u32 ring,
 			       struct amdgpu_ring **out_ring)
 {
-	u32 instance;
-
 	switch (mapper->hw_ip) {
 	case AMDGPU_HW_IP_GFX:
 		*out_ring = &adev->gfx.gfx_ring[ring];
@@ -79,16 +77,13 @@ static int amdgpu_identity_map(struct amdgpu_device *adev,
 		*out_ring = &adev->sdma.instance[ring].ring;
 		break;
 	case AMDGPU_HW_IP_UVD:
-		instance = ring;
-		*out_ring = &adev->uvd.inst[instance].ring;
+		*out_ring = &adev->uvd.inst[0].ring;
 		break;
 	case AMDGPU_HW_IP_VCE:
 		*out_ring = &adev->vce.ring[ring];
 		break;
 	case AMDGPU_HW_IP_UVD_ENC:
-		instance = ring / adev->uvd.num_enc_rings;
-		*out_ring =
-		&adev->uvd.inst[instance].ring_enc[ring%adev->uvd.num_enc_rings];
+		*out_ring = &adev->uvd.inst[0].ring_enc[ring];
 		break;
 	case AMDGPU_HW_IP_VCN_DEC:
 		*out_ring = &adev->vcn.ring_dec;
@@ -96,6 +91,9 @@ static int amdgpu_identity_map(struct amdgpu_device *adev,
 	case AMDGPU_HW_IP_VCN_ENC:
 		*out_ring = &adev->vcn.ring_enc[ring];
 		break;
+	case AMDGPU_HW_IP_VCN_JPEG:
+		*out_ring = &adev->vcn.ring_jpeg;
+		break;
 	default:
 		*out_ring = NULL;
 		DRM_ERROR("unknown HW IP type: %d\n", mapper->hw_ip);
@@ -216,7 +214,7 @@ int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
 			 u32 hw_ip, u32 instance, u32 ring,
 			 struct amdgpu_ring **out_ring)
 {
-	int r, ip_num_rings;
+	int i, r, ip_num_rings = 0;
 	struct amdgpu_queue_mapper *mapper = &mgr->mapper[hw_ip];
 
 	if (!adev || !mgr || !out_ring)
@@ -245,14 +243,21 @@ int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
 		ip_num_rings = adev->sdma.num_instances;
 		break;
 	case AMDGPU_HW_IP_UVD:
-		ip_num_rings = adev->uvd.num_uvd_inst;
+		for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
+			if (!(adev->uvd.harvest_config & (1 << i)))
+				ip_num_rings++;
+		}
 		break;
 	case AMDGPU_HW_IP_VCE:
 		ip_num_rings = adev->vce.num_rings;
 		break;
 	case AMDGPU_HW_IP_UVD_ENC:
+		for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
+			if (!(adev->uvd.harvest_config & (1 << i)))
+				ip_num_rings++;
+		}
 		ip_num_rings =
-			adev->uvd.num_enc_rings * adev->uvd.num_uvd_inst;
+			adev->uvd.num_enc_rings * ip_num_rings;
 		break;
 	case AMDGPU_HW_IP_VCN_DEC:
 		ip_num_rings = 1;
@@ -260,6 +265,9 @@ int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
 	case AMDGPU_HW_IP_VCN_ENC:
 		ip_num_rings = adev->vcn.num_enc_rings;
 		break;
+	case AMDGPU_HW_IP_VCN_JPEG:
+		ip_num_rings = 1;
+		break;
 	default:
 		DRM_DEBUG("unknown ip type: %d\n", hw_ip);
 		return -EINVAL;
@@ -287,6 +295,7 @@ int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
 	case AMDGPU_HW_IP_UVD_ENC:
 	case AMDGPU_HW_IP_VCN_DEC:
 	case AMDGPU_HW_IP_VCN_ENC:
+	case AMDGPU_HW_IP_VCN_JPEG:
 		r = amdgpu_identity_map(adev, mapper, ring, out_ring);
 		break;
 	case AMDGPU_HW_IP_DMA:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index c6850b629d0e..93794a85f83d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -211,7 +211,8 @@ void amdgpu_ring_priority_get(struct amdgpu_ring *ring,
 	if (!ring->funcs->set_priority)
 		return;
 
-	atomic_inc(&ring->num_jobs[priority]);
+	if (atomic_inc_return(&ring->num_jobs[priority]) <= 0)
+		return;
 
 	mutex_lock(&ring->priority_mutex);
 	if (priority <= ring->priority)
@@ -304,7 +305,7 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 		0xffffffffffffffff : ring->buf_mask;
 	/* Allocate ring buffer */
 	if (ring->ring_obj == NULL) {
-		r = amdgpu_bo_create_kernel(adev, ring->ring_size, PAGE_SIZE,
+		r = amdgpu_bo_create_kernel(adev, ring->ring_size + ring->funcs->extra_dw, PAGE_SIZE,
 					    AMDGPU_GEM_DOMAIN_GTT,
 					    &ring->ring_obj,
 					    &ring->gpu_addr,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 1513124c5659..d242b9a51e90 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -44,6 +44,8 @@
 #define AMDGPU_FENCE_FLAG_INT           (1 << 1)
 #define AMDGPU_FENCE_FLAG_TC_WB_ONLY    (1 << 2)
 
+#define to_amdgpu_ring(s) container_of((s), struct amdgpu_ring, sched)
+
 enum amdgpu_ring_type {
 	AMDGPU_RING_TYPE_GFX,
 	AMDGPU_RING_TYPE_COMPUTE,
@@ -53,7 +55,8 @@ enum amdgpu_ring_type {
 	AMDGPU_RING_TYPE_KIQ,
 	AMDGPU_RING_TYPE_UVD_ENC,
 	AMDGPU_RING_TYPE_VCN_DEC,
-	AMDGPU_RING_TYPE_VCN_ENC
+	AMDGPU_RING_TYPE_VCN_ENC,
+	AMDGPU_RING_TYPE_VCN_JPEG
 };
 
 struct amdgpu_device;
@@ -112,6 +115,7 @@ struct amdgpu_ring_funcs {
 	u32			nop;
 	bool			support_64bit_ptrs;
 	unsigned		vmhub;
+	unsigned		extra_dw;
 
 	/* ring read/write ptr handling */
 	u64 (*get_rptr)(struct amdgpu_ring *ring);
@@ -119,6 +123,7 @@ struct amdgpu_ring_funcs {
 	void (*set_wptr)(struct amdgpu_ring *ring);
 	/* validating and patching of IBs */
 	int (*parse_cs)(struct amdgpu_cs_parser *p, uint32_t ib_idx);
+	int (*patch_cs_in_place)(struct amdgpu_cs_parser *p, uint32_t ib_idx);
 	/* constants to calculate how many DW are needed for an emit */
 	unsigned emit_frame_size;
 	unsigned emit_ib_size;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
index e3878256743a..8904e62dca7a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /*
  * Copyright 2009 VMware, Inc.
  *
@@ -75,11 +76,12 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
 	r = amdgpu_bo_reserve(vram_obj, false);
 	if (unlikely(r != 0))
 		goto out_unref;
-	r = amdgpu_bo_pin(vram_obj, AMDGPU_GEM_DOMAIN_VRAM, &vram_addr);
+	r = amdgpu_bo_pin(vram_obj, AMDGPU_GEM_DOMAIN_VRAM);
 	if (r) {
 		DRM_ERROR("Failed to pin VRAM object\n");
 		goto out_unres;
 	}
+	vram_addr = amdgpu_bo_gpu_offset(vram_obj);
 	for (i = 0; i < n; i++) {
 		void *gtt_map, *vram_map;
 		void **gart_start, **gart_end;
@@ -96,11 +98,17 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
 		r = amdgpu_bo_reserve(gtt_obj[i], false);
 		if (unlikely(r != 0))
 			goto out_lclean_unref;
-		r = amdgpu_bo_pin(gtt_obj[i], AMDGPU_GEM_DOMAIN_GTT, &gart_addr);
+		r = amdgpu_bo_pin(gtt_obj[i], AMDGPU_GEM_DOMAIN_GTT);
 		if (r) {
 			DRM_ERROR("Failed to pin GTT object %d\n", i);
 			goto out_lclean_unres;
 		}
+		r = amdgpu_ttm_alloc_gart(&gtt_obj[i]->tbo);
+		if (r) {
+			DRM_ERROR("%p bind failed\n", gtt_obj[i]);
+			goto out_lclean_unpin;
+		}
+		gart_addr = amdgpu_bo_gpu_offset(gtt_obj[i]);
 
 		r = amdgpu_bo_kmap(gtt_obj[i], &gtt_map);
 		if (r) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index e96e26d3f3b0..7206a0025b17 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -150,10 +150,10 @@ TRACE_EVENT(amdgpu_cs,
 
 	    TP_fast_assign(
 			   __entry->bo_list = p->bo_list;
-			   __entry->ring = p->job->ring->idx;
+			   __entry->ring = p->ring->idx;
 			   __entry->dw = p->job->ibs[i].length_dw;
 			   __entry->fences = amdgpu_fence_count_emitted(
-				p->job->ring);
+				p->ring);
 			   ),
 	    TP_printk("bo_list=%p, ring=%u, dw=%u, fences=%u",
 		      __entry->bo_list, __entry->ring, __entry->dw,
@@ -178,7 +178,7 @@ TRACE_EVENT(amdgpu_cs_ioctl,
 			   __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
 			   __entry->context = job->base.s_fence->finished.context;
 			   __entry->seqno = job->base.s_fence->finished.seqno;
-			   __entry->ring_name = job->ring->name;
+			   __entry->ring_name = to_amdgpu_ring(job->base.sched)->name;
 			   __entry->num_ibs = job->num_ibs;
 			   ),
 	    TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u",
@@ -203,7 +203,7 @@ TRACE_EVENT(amdgpu_sched_run_job,
 			   __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
 			   __entry->context = job->base.s_fence->finished.context;
 			   __entry->seqno = job->base.s_fence->finished.seqno;
-			   __entry->ring_name = job->ring->name;
+			   __entry->ring_name = to_amdgpu_ring(job->base.sched)->name;
 			   __entry->num_ibs = job->num_ibs;
 			   ),
 	    TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u",
@@ -314,6 +314,11 @@ DEFINE_EVENT(amdgpu_vm_mapping, amdgpu_vm_bo_mapping,
 	    TP_ARGS(mapping)
 );
 
+DEFINE_EVENT(amdgpu_vm_mapping, amdgpu_vm_bo_cs,
+	    TP_PROTO(struct amdgpu_bo_va_mapping *mapping),
+	    TP_ARGS(mapping)
+);
+
 TRACE_EVENT(amdgpu_vm_set_ptes,
 	    TP_PROTO(uint64_t pe, uint64_t addr, unsigned count,
 		     uint32_t incr, uint64_t flags),
@@ -436,7 +441,7 @@ TRACE_EVENT(amdgpu_cs_bo_status,
 			__entry->total_bo, __entry->total_size)
 );
 
-TRACE_EVENT(amdgpu_ttm_bo_move,
+TRACE_EVENT(amdgpu_bo_move,
 	    TP_PROTO(struct amdgpu_bo* bo, uint32_t new_placement, uint32_t old_placement),
 	    TP_ARGS(bo, new_placement, old_placement),
 	    TP_STRUCT__entry(
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index e93a0a237dc3..fcf421263fd9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -92,11 +92,9 @@ static void amdgpu_ttm_mem_global_release(struct drm_global_reference *ref)
 }
 
 /**
- * amdgpu_ttm_global_init - Initialize global TTM memory reference
- * 							structures.
+ * amdgpu_ttm_global_init - Initialize global TTM memory reference structures.
  *
- * @adev:  	AMDGPU device for which the global structures need to be
- *			registered.
+ * @adev: AMDGPU device for which the global structures need to be registered.
  *
  * This is called as part of the AMDGPU ttm init from amdgpu_ttm_init()
  * during bring up.
@@ -104,8 +102,6 @@ static void amdgpu_ttm_mem_global_release(struct drm_global_reference *ref)
 static int amdgpu_ttm_global_init(struct amdgpu_device *adev)
 {
 	struct drm_global_reference *global_ref;
-	struct amdgpu_ring *ring;
-	struct drm_sched_rq *rq;
 	int r;
 
 	/* ensure reference is false in case init fails */
@@ -138,21 +134,10 @@ static int amdgpu_ttm_global_init(struct amdgpu_device *adev)
 
 	mutex_init(&adev->mman.gtt_window_lock);
 
-	ring = adev->mman.buffer_funcs_ring;
-	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL];
-	r = drm_sched_entity_init(&ring->sched, &adev->mman.entity,
-				  rq, NULL);
-	if (r) {
-		DRM_ERROR("Failed setting up TTM BO move run queue.\n");
-		goto error_entity;
-	}
-
 	adev->mman.mem_global_referenced = true;
 
 	return 0;
 
-error_entity:
-	drm_global_item_unref(&adev->mman.bo_global_ref.ref);
 error_bo:
 	drm_global_item_unref(&adev->mman.mem_global_ref);
 error_mem:
@@ -162,8 +147,6 @@ error_mem:
 static void amdgpu_ttm_global_fini(struct amdgpu_device *adev)
 {
 	if (adev->mman.mem_global_referenced) {
-		drm_sched_entity_fini(adev->mman.entity.sched,
-				      &adev->mman.entity);
 		mutex_destroy(&adev->mman.gtt_window_lock);
 		drm_global_item_unref(&adev->mman.bo_global_ref.ref);
 		drm_global_item_unref(&adev->mman.mem_global_ref);
@@ -177,13 +160,12 @@ static int amdgpu_invalidate_caches(struct ttm_bo_device *bdev, uint32_t flags)
 }
 
 /**
- * amdgpu_init_mem_type - 	Initialize a memory manager for a specific
- * 							type of memory request.
+ * amdgpu_init_mem_type - Initialize a memory manager for a specific type of
+ * memory request.
  *
- * @bdev:	The TTM BO device object (contains a reference to
- * 			amdgpu_device)
- * @type:	The type of memory requested
- * @man:
+ * @bdev: The TTM BO device object (contains a reference to amdgpu_device)
+ * @type: The type of memory requested
+ * @man: The memory type manager for each domain
  *
  * This is called by ttm_bo_init_mm() when a buffer object is being
  * initialized.
@@ -263,7 +245,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 	}
 
 	/* Object isn't an AMDGPU object so ignore */
-	if (!amdgpu_ttm_bo_is_amdgpu_bo(bo)) {
+	if (!amdgpu_bo_is_amdgpu_bo(bo)) {
 		placement->placement = &placements;
 		placement->busy_placement = &placements;
 		placement->num_placement = 1;
@@ -276,8 +258,8 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 	case TTM_PL_VRAM:
 		if (!adev->mman.buffer_funcs_enabled) {
 			/* Move to system memory */
-			amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_CPU);
-		} else if (adev->gmc.visible_vram_size < adev->gmc.real_vram_size &&
+			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_CPU);
+		} else if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
 			   !(abo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) &&
 			   amdgpu_bo_in_cpu_visible_vram(abo)) {
 
@@ -286,7 +268,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 			 * BO will be evicted to GTT rather than causing other
 			 * BOs to be evicted from VRAM
 			 */
-			amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM |
+			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM |
 							 AMDGPU_GEM_DOMAIN_GTT);
 			abo->placements[0].fpfn = adev->gmc.visible_vram_size >> PAGE_SHIFT;
 			abo->placements[0].lpfn = 0;
@@ -294,12 +276,12 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 			abo->placement.num_busy_placement = 1;
 		} else {
 			/* Move to GTT memory */
-			amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_GTT);
+			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_GTT);
 		}
 		break;
 	case TTM_PL_TT:
 	default:
-		amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_CPU);
+		amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_CPU);
 	}
 	*placement = abo->placement;
 }
@@ -307,8 +289,8 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 /**
  * amdgpu_verify_access - Verify access for a mmap call
  *
- * @bo:		The buffer object to map
- * @filp:	The file pointer from the process performing the mmap
+ * @bo:	The buffer object to map
+ * @filp: The file pointer from the process performing the mmap
  *
  * This is called by ttm_bo_mmap() to verify whether a process
  * has the right to mmap a BO to their process space.
@@ -333,11 +315,10 @@ static int amdgpu_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 /**
  * amdgpu_move_null - Register memory for a buffer object
  *
- * @bo:			The bo to assign the memory to
- * @new_mem:	The memory to be assigned.
+ * @bo: The bo to assign the memory to
+ * @new_mem: The memory to be assigned.
  *
- * Assign the memory from new_mem to the memory of the buffer object
- * bo.
+ * Assign the memory from new_mem to the memory of the buffer object bo.
  */
 static void amdgpu_move_null(struct ttm_buffer_object *bo,
 			     struct ttm_mem_reg *new_mem)
@@ -350,8 +331,12 @@ static void amdgpu_move_null(struct ttm_buffer_object *bo,
 }
 
 /**
- * amdgpu_mm_node_addr -	Compute the GPU relative offset of a GTT
- * 							buffer.
+ * amdgpu_mm_node_addr - Compute the GPU relative offset of a GTT buffer.
+ *
+ * @bo: The bo to assign the memory to.
+ * @mm_node: Memory manager node for drm allocator.
+ * @mem: The region where the bo resides.
+ *
  */
 static uint64_t amdgpu_mm_node_addr(struct ttm_buffer_object *bo,
 				    struct drm_mm_node *mm_node,
@@ -367,10 +352,12 @@ static uint64_t amdgpu_mm_node_addr(struct ttm_buffer_object *bo,
 }
 
 /**
- * amdgpu_find_mm_node -	Helper function finds the drm_mm_node
- *  						corresponding to @offset. It also modifies
- * 							the offset to be within the drm_mm_node
- * 							returned
+ * amdgpu_find_mm_node - Helper function finds the drm_mm_node corresponding to
+ * @offset. It also modifies the offset to be within the drm_mm_node returned
+ *
+ * @mem: The region where the bo resides.
+ * @offset: The offset that drm_mm_node is used for finding.
+ *
  */
 static struct drm_mm_node *amdgpu_find_mm_node(struct ttm_mem_reg *mem,
 					       unsigned long *offset)
@@ -512,8 +499,8 @@ error:
 /**
  * amdgpu_move_blit - Copy an entire buffer to another buffer
  *
- * This is a helper called by amdgpu_bo_move() and
- * amdgpu_move_vram_ram() to help move buffers to and from VRAM.
+ * This is a helper called by amdgpu_bo_move() and amdgpu_move_vram_ram() to
+ * help move buffers to and from VRAM.
  */
 static int amdgpu_move_blit(struct ttm_buffer_object *bo,
 			    bool evict, bool no_wait_gpu,
@@ -595,7 +582,7 @@ static int amdgpu_move_vram_ram(struct ttm_buffer_object *bo, bool evict,
 	}
 
 	/* blit VRAM to GTT */
-	r = amdgpu_move_blit(bo, true, ctx->no_wait_gpu, &tmp_mem, old_mem);
+	r = amdgpu_move_blit(bo, evict, ctx->no_wait_gpu, &tmp_mem, old_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
@@ -647,7 +634,7 @@ static int amdgpu_move_ram_vram(struct ttm_buffer_object *bo, bool evict,
 	}
 
 	/* copy to VRAM */
-	r = amdgpu_move_blit(bo, true, ctx->no_wait_gpu, new_mem, old_mem);
+	r = amdgpu_move_blit(bo, evict, ctx->no_wait_gpu, new_mem, old_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
@@ -809,8 +796,8 @@ struct amdgpu_ttm_tt {
 };
 
 /**
- * amdgpu_ttm_tt_get_user_pages - 	Pin pages of memory pointed to
- * 									by a USERPTR pointer to memory
+ * amdgpu_ttm_tt_get_user_pages - Pin pages of memory pointed to by a USERPTR
+ * pointer to memory
  *
  * Called by amdgpu_gem_userptr_ioctl() and amdgpu_cs_parser_bos().
  * This provides a wrapper around the get_user_pages() call to provide
@@ -833,8 +820,10 @@ int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages)
 	down_read(&mm->mmap_sem);
 
 	if (gtt->userflags & AMDGPU_GEM_USERPTR_ANONONLY) {
-		/* check that we only use anonymous memory
-		   to prevent problems with writeback */
+		/*
+		 * check that we only use anonymous memory to prevent problems
+		 * with writeback
+		 */
 		unsigned long end = gtt->userptr + ttm->num_pages * PAGE_SIZE;
 		struct vm_area_struct *vma;
 
@@ -885,10 +874,9 @@ release_pages:
 }
 
 /**
- * amdgpu_ttm_tt_set_user_pages - 	Copy pages in, putting old pages
- * 									as necessary.
+ * amdgpu_ttm_tt_set_user_pages - Copy pages in, putting old pages as necessary.
  *
- * Called by amdgpu_cs_list_validate().  This creates the page list
+ * Called by amdgpu_cs_list_validate(). This creates the page list
  * that backs user memory and will ultimately be mapped into the device
  * address space.
  */
@@ -930,8 +918,7 @@ void amdgpu_ttm_tt_mark_user_pages(struct ttm_tt *ttm)
 }
 
 /**
- * amdgpu_ttm_tt_pin_userptr - 	prepare the sg table with the
- * 								user pages
+ * amdgpu_ttm_tt_pin_userptr - 	prepare the sg table with the user pages
  *
  * Called by amdgpu_ttm_backend_bind()
  **/
@@ -1310,8 +1297,8 @@ static void amdgpu_ttm_tt_unpopulate(struct ttm_tt *ttm)
 }
 
 /**
- * amdgpu_ttm_tt_set_userptr -	Initialize userptr GTT ttm_tt
- * 								for the current task
+ * amdgpu_ttm_tt_set_userptr - Initialize userptr GTT ttm_tt for the current
+ * task
  *
  * @ttm: The ttm_tt object to bind this userptr object to
  * @addr:  The address in the current tasks VM space to use
@@ -1361,9 +1348,8 @@ struct mm_struct *amdgpu_ttm_tt_get_usermm(struct ttm_tt *ttm)
 }
 
 /**
- * amdgpu_ttm_tt_affect_userptr -	Determine if a ttm_tt object lays
- * 									inside an address range for the
- * 									current task.
+ * amdgpu_ttm_tt_affect_userptr - Determine if a ttm_tt object lays inside an
+ * address range for the current task.
  *
  */
 bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
@@ -1401,8 +1387,7 @@ bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
 }
 
 /**
- * amdgpu_ttm_tt_userptr_invalidated -	Has the ttm_tt object been
- * 										invalidated?
+ * amdgpu_ttm_tt_userptr_invalidated - Has the ttm_tt object been invalidated?
  */
 bool amdgpu_ttm_tt_userptr_invalidated(struct ttm_tt *ttm,
 				       int *last_invalidated)
@@ -1415,10 +1400,8 @@ bool amdgpu_ttm_tt_userptr_invalidated(struct ttm_tt *ttm,
 }
 
 /**
- * amdgpu_ttm_tt_userptr_needs_pages -	Have the pages backing this
- * 										ttm_tt object been invalidated
- * 										since the last time they've
- * 										been set?
+ * amdgpu_ttm_tt_userptr_needs_pages - Have the pages backing this ttm_tt object
+ * been invalidated since the last time they've been set?
  */
 bool amdgpu_ttm_tt_userptr_needs_pages(struct ttm_tt *ttm)
 {
@@ -1474,13 +1457,12 @@ uint64_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm,
 }
 
 /**
- * amdgpu_ttm_bo_eviction_valuable -	Check to see if we can evict
- * 										a buffer object.
+ * amdgpu_ttm_bo_eviction_valuable - Check to see if we can evict a buffer
+ * object.
  *
- * Return true if eviction is sensible.  Called by
- * ttm_mem_evict_first() on behalf of ttm_bo_mem_force_space()
- * which tries to evict buffer objects until it can find space
- * for a new object and by ttm_bo_force_list_clean() which is
+ * Return true if eviction is sensible. Called by ttm_mem_evict_first() on
+ * behalf of ttm_bo_mem_force_space() which tries to evict buffer objects until
+ * it can find space for a new object and by ttm_bo_force_list_clean() which is
  * used to clean out a memory space.
  */
 static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo,
@@ -1530,8 +1512,7 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo,
 }
 
 /**
- * amdgpu_ttm_access_memory -	Read or Write memory that backs a
- * 								buffer object.
+ * amdgpu_ttm_access_memory - Read or Write memory that backs a buffer object.
  *
  * @bo:  The buffer object to read/write
  * @offset:  Offset into buffer object
@@ -1695,7 +1676,7 @@ static int amdgpu_ttm_fw_reserve_vram_init(struct amdgpu_device *adev)
 			AMDGPU_GEM_DOMAIN_VRAM,
 			adev->fw_vram_usage.start_offset,
 			(adev->fw_vram_usage.start_offset +
-			adev->fw_vram_usage.size), NULL);
+			adev->fw_vram_usage.size));
 		if (r)
 			goto error_pin;
 		r = amdgpu_bo_kmap(adev->fw_vram_usage.reserved_bo,
@@ -1719,8 +1700,8 @@ error_create:
 	return r;
 }
 /**
- * amdgpu_ttm_init -	Init the memory management (ttm) as well as
- * 						various gtt/vram related fields.
+ * amdgpu_ttm_init - Init the memory management (ttm) as well as various
+ * gtt/vram related fields.
  *
  * This initializes all of the memory space pools that the TTM layer
  * will need such as the GTT space (system memory mapped to the device),
@@ -1871,8 +1852,7 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_ttm_late_init -	Handle any late initialization for
- * 							amdgpu_ttm
+ * amdgpu_ttm_late_init - Handle any late initialization for amdgpu_ttm
  */
 void amdgpu_ttm_late_init(struct amdgpu_device *adev)
 {
@@ -1921,10 +1901,30 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 {
 	struct ttm_mem_type_manager *man = &adev->mman.bdev.man[TTM_PL_VRAM];
 	uint64_t size;
+	int r;
 
-	if (!adev->mman.initialized || adev->in_gpu_reset)
+	if (!adev->mman.initialized || adev->in_gpu_reset ||
+	    adev->mman.buffer_funcs_enabled == enable)
 		return;
 
+	if (enable) {
+		struct amdgpu_ring *ring;
+		struct drm_sched_rq *rq;
+
+		ring = adev->mman.buffer_funcs_ring;
+		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+		r = drm_sched_entity_init(&adev->mman.entity, &rq, 1, NULL);
+		if (r) {
+			DRM_ERROR("Failed setting up TTM BO move entity (%d)\n",
+				  r);
+			return;
+		}
+	} else {
+		drm_sched_entity_destroy(&adev->mman.entity);
+		dma_fence_put(man->move);
+		man->move = NULL;
+	}
+
 	/* this just adjusts TTM size idea, which sets lpfn to the correct value */
 	if (enable)
 		size = adev->gmc.real_vram_size;
@@ -2002,7 +2002,7 @@ static int amdgpu_map_buffer(struct ttm_buffer_object *bo,
 	if (r)
 		goto error_free;
 
-	r = amdgpu_job_submit(job, ring, &adev->mman.entity,
+	r = amdgpu_job_submit(job, &adev->mman.entity,
 			      AMDGPU_FENCE_OWNER_UNDEFINED, &fence);
 	if (r)
 		goto error_free;
@@ -2071,24 +2071,19 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
 
 	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
 	WARN_ON(job->ibs[0].length_dw > num_dw);
-	if (direct_submit) {
-		r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs,
-				       NULL, fence);
-		job->fence = dma_fence_get(*fence);
-		if (r)
-			DRM_ERROR("Error scheduling IBs (%d)\n", r);
-		amdgpu_job_free(job);
-	} else {
-		r = amdgpu_job_submit(job, ring, &adev->mman.entity,
+	if (direct_submit)
+		r = amdgpu_job_submit_direct(job, ring, fence);
+	else
+		r = amdgpu_job_submit(job, &adev->mman.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, fence);
-		if (r)
-			goto error_free;
-	}
+	if (r)
+		goto error_free;
 
 	return r;
 
 error_free:
 	amdgpu_job_free(job);
+	DRM_ERROR("Error scheduling IBs (%d)\n", r);
 	return r;
 }
 
@@ -2171,7 +2166,7 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo,
 
 	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
 	WARN_ON(job->ibs[0].length_dw > num_dw);
-	r = amdgpu_job_submit(job, ring, &adev->mman.entity,
+	r = amdgpu_job_submit(job, &adev->mman.entity,
 			      AMDGPU_FENCE_OWNER_UNDEFINED, fence);
 	if (r)
 		goto error_free;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index e5da4654b630..8b3cc6687769 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -73,7 +73,7 @@ bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_mem_reg *mem);
 uint64_t amdgpu_gtt_mgr_usage(struct ttm_mem_type_manager *man);
 int amdgpu_gtt_mgr_recover(struct ttm_mem_type_manager *man);
 
-u64 amdgpu_vram_mgr_bo_invisible_size(struct amdgpu_bo *bo);
+u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo);
 uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man);
 uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_mem_type_manager *man);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 3ff08e326838..632fa5980ff4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -53,11 +53,11 @@
 
 /* Firmware Names */
 #ifdef CONFIG_DRM_AMDGPU_CIK
-#define FIRMWARE_BONAIRE	"radeon/bonaire_uvd.bin"
-#define FIRMWARE_KABINI	"radeon/kabini_uvd.bin"
-#define FIRMWARE_KAVERI	"radeon/kaveri_uvd.bin"
-#define FIRMWARE_HAWAII	"radeon/hawaii_uvd.bin"
-#define FIRMWARE_MULLINS	"radeon/mullins_uvd.bin"
+#define FIRMWARE_BONAIRE	"amdgpu/bonaire_uvd.bin"
+#define FIRMWARE_KABINI	"amdgpu/kabini_uvd.bin"
+#define FIRMWARE_KAVERI	"amdgpu/kaveri_uvd.bin"
+#define FIRMWARE_HAWAII	"amdgpu/hawaii_uvd.bin"
+#define FIRMWARE_MULLINS	"amdgpu/mullins_uvd.bin"
 #endif
 #define FIRMWARE_TONGA		"amdgpu/tonga_uvd.bin"
 #define FIRMWARE_CARRIZO	"amdgpu/carrizo_uvd.bin"
@@ -127,7 +127,7 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 	unsigned long bo_size;
 	const char *fw_name;
 	const struct common_firmware_header *hdr;
-	unsigned version_major, version_minor, family_id;
+	unsigned family_id;
 	int i, j, r;
 
 	INIT_DELAYED_WORK(&adev->uvd.idle_work, amdgpu_uvd_idle_work_handler);
@@ -208,29 +208,46 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 
 	hdr = (const struct common_firmware_header *)adev->uvd.fw->data;
 	family_id = le32_to_cpu(hdr->ucode_version) & 0xff;
-	version_major = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xff;
-	version_minor = (le32_to_cpu(hdr->ucode_version) >> 8) & 0xff;
-	DRM_INFO("Found UVD firmware Version: %hu.%hu Family ID: %hu\n",
-		version_major, version_minor, family_id);
-
-	/*
-	 * Limit the number of UVD handles depending on microcode major
-	 * and minor versions. The firmware version which has 40 UVD
-	 * instances support is 1.80. So all subsequent versions should
-	 * also have the same support.
-	 */
-	if ((version_major > 0x01) ||
-	    ((version_major == 0x01) && (version_minor >= 0x50)))
-		adev->uvd.max_handles = AMDGPU_MAX_UVD_HANDLES;
 
-	adev->uvd.fw_version = ((version_major << 24) | (version_minor << 16) |
-				(family_id << 8));
+	if (adev->asic_type < CHIP_VEGA20) {
+		unsigned version_major, version_minor;
 
-	if ((adev->asic_type == CHIP_POLARIS10 ||
-	     adev->asic_type == CHIP_POLARIS11) &&
-	    (adev->uvd.fw_version < FW_1_66_16))
-		DRM_ERROR("POLARIS10/11 UVD firmware version %hu.%hu is too old.\n",
-			  version_major, version_minor);
+		version_major = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xff;
+		version_minor = (le32_to_cpu(hdr->ucode_version) >> 8) & 0xff;
+		DRM_INFO("Found UVD firmware Version: %hu.%hu Family ID: %hu\n",
+			version_major, version_minor, family_id);
+
+		/*
+		 * Limit the number of UVD handles depending on microcode major
+		 * and minor versions. The firmware version which has 40 UVD
+		 * instances support is 1.80. So all subsequent versions should
+		 * also have the same support.
+		 */
+		if ((version_major > 0x01) ||
+		    ((version_major == 0x01) && (version_minor >= 0x50)))
+			adev->uvd.max_handles = AMDGPU_MAX_UVD_HANDLES;
+
+		adev->uvd.fw_version = ((version_major << 24) | (version_minor << 16) |
+					(family_id << 8));
+
+		if ((adev->asic_type == CHIP_POLARIS10 ||
+		     adev->asic_type == CHIP_POLARIS11) &&
+		    (adev->uvd.fw_version < FW_1_66_16))
+			DRM_ERROR("POLARIS10/11 UVD firmware version %hu.%hu is too old.\n",
+				  version_major, version_minor);
+	} else {
+		unsigned int enc_major, enc_minor, dec_minor;
+
+		dec_minor = (le32_to_cpu(hdr->ucode_version) >> 8) & 0xff;
+		enc_minor = (le32_to_cpu(hdr->ucode_version) >> 24) & 0x3f;
+		enc_major = (le32_to_cpu(hdr->ucode_version) >> 30) & 0x3;
+		DRM_INFO("Found UVD firmware ENC: %hu.%hu DEC: .%hu Family ID: %hu\n",
+			enc_major, enc_minor, dec_minor, family_id);
+
+		adev->uvd.max_handles = AMDGPU_MAX_UVD_HANDLES;
+
+		adev->uvd.fw_version = le32_to_cpu(hdr->ucode_version);
+	}
 
 	bo_size = AMDGPU_UVD_STACK_SIZE + AMDGPU_UVD_HEAP_SIZE
 		  +  AMDGPU_UVD_SESSION_SIZE * adev->uvd.max_handles;
@@ -238,7 +255,8 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 		bo_size += AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8);
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
-
+		if (adev->uvd.harvest_config & (1 << j))
+			continue;
 		r = amdgpu_bo_create_kernel(adev, bo_size, PAGE_SIZE,
 					    AMDGPU_GEM_DOMAIN_VRAM, &adev->uvd.inst[j].vcpu_bo,
 					    &adev->uvd.inst[j].gpu_addr, &adev->uvd.inst[j].cpu_addr);
@@ -246,21 +264,20 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 			dev_err(adev->dev, "(%d) failed to allocate UVD bo\n", r);
 			return r;
 		}
+	}
 
-		ring = &adev->uvd.inst[j].ring;
-		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-		r = drm_sched_entity_init(&ring->sched, &adev->uvd.inst[j].entity,
-					  rq, NULL);
-		if (r != 0) {
-			DRM_ERROR("Failed setting up UVD(%d) run queue.\n", j);
-			return r;
-		}
-
-		for (i = 0; i < adev->uvd.max_handles; ++i) {
-			atomic_set(&adev->uvd.inst[j].handles[i], 0);
-			adev->uvd.inst[j].filp[i] = NULL;
-		}
+	ring = &adev->uvd.inst[0].ring;
+	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
+	r = drm_sched_entity_init(&adev->uvd.entity, &rq, 1, NULL);
+	if (r) {
+		DRM_ERROR("Failed setting up UVD kernel entity.\n");
+		return r;
+	}
+	for (i = 0; i < adev->uvd.max_handles; ++i) {
+		atomic_set(&adev->uvd.handles[i], 0);
+		adev->uvd.filp[i] = NULL;
 	}
+
 	/* from uvd v5.0 HW addressing capacity increased to 64 bits */
 	if (!amdgpu_device_ip_block_version_cmp(adev, AMD_IP_BLOCK_TYPE_UVD, 5, 0))
 		adev->uvd.address_64_bit = true;
@@ -289,11 +306,13 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev)
 {
 	int i, j;
 
+	drm_sched_entity_destroy(&adev->uvd.entity);
+
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
+		if (adev->uvd.harvest_config & (1 << j))
+			continue;
 		kfree(adev->uvd.inst[j].saved_bo);
 
-		drm_sched_entity_fini(&adev->uvd.inst[j].ring.sched, &adev->uvd.inst[j].entity);
-
 		amdgpu_bo_free_kernel(&adev->uvd.inst[j].vcpu_bo,
 				      &adev->uvd.inst[j].gpu_addr,
 				      (void **)&adev->uvd.inst[j].cpu_addr);
@@ -316,20 +335,22 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev)
 
 	cancel_delayed_work_sync(&adev->uvd.idle_work);
 
+	/* only valid for physical mode */
+	if (adev->asic_type < CHIP_POLARIS10) {
+		for (i = 0; i < adev->uvd.max_handles; ++i)
+			if (atomic_read(&adev->uvd.handles[i]))
+				break;
+
+		if (i == adev->uvd.max_handles)
+			return 0;
+	}
+
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
+		if (adev->uvd.harvest_config & (1 << j))
+			continue;
 		if (adev->uvd.inst[j].vcpu_bo == NULL)
 			continue;
 
-		/* only valid for physical mode */
-		if (adev->asic_type < CHIP_POLARIS10) {
-			for (i = 0; i < adev->uvd.max_handles; ++i)
-				if (atomic_read(&adev->uvd.inst[j].handles[i]))
-					break;
-
-			if (i == adev->uvd.max_handles)
-				continue;
-		}
-
 		size = amdgpu_bo_size(adev->uvd.inst[j].vcpu_bo);
 		ptr = adev->uvd.inst[j].cpu_addr;
 
@@ -349,6 +370,8 @@ int amdgpu_uvd_resume(struct amdgpu_device *adev)
 	int i;
 
 	for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
+		if (adev->uvd.harvest_config & (1 << i))
+			continue;
 		if (adev->uvd.inst[i].vcpu_bo == NULL)
 			return -EINVAL;
 
@@ -381,30 +404,27 @@ int amdgpu_uvd_resume(struct amdgpu_device *adev)
 
 void amdgpu_uvd_free_handles(struct amdgpu_device *adev, struct drm_file *filp)
 {
-	struct amdgpu_ring *ring;
-	int i, j, r;
-
-	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
-		ring = &adev->uvd.inst[j].ring;
+	struct amdgpu_ring *ring = &adev->uvd.inst[0].ring;
+	int i, r;
 
-		for (i = 0; i < adev->uvd.max_handles; ++i) {
-			uint32_t handle = atomic_read(&adev->uvd.inst[j].handles[i]);
-			if (handle != 0 && adev->uvd.inst[j].filp[i] == filp) {
-				struct dma_fence *fence;
-
-				r = amdgpu_uvd_get_destroy_msg(ring, handle,
-							       false, &fence);
-				if (r) {
-					DRM_ERROR("Error destroying UVD(%d) %d!\n", j, r);
-					continue;
-				}
+	for (i = 0; i < adev->uvd.max_handles; ++i) {
+		uint32_t handle = atomic_read(&adev->uvd.handles[i]);
 
-				dma_fence_wait(fence, false);
-				dma_fence_put(fence);
+		if (handle != 0 && adev->uvd.filp[i] == filp) {
+			struct dma_fence *fence;
 
-				adev->uvd.inst[j].filp[i] = NULL;
-				atomic_set(&adev->uvd.inst[j].handles[i], 0);
+			r = amdgpu_uvd_get_destroy_msg(ring, handle, false,
+						       &fence);
+			if (r) {
+				DRM_ERROR("Error destroying UVD %d!\n", r);
+				continue;
 			}
+
+			dma_fence_wait(fence, false);
+			dma_fence_put(fence);
+
+			adev->uvd.filp[i] = NULL;
+			atomic_set(&adev->uvd.handles[i], 0);
 		}
 	}
 }
@@ -459,7 +479,7 @@ static int amdgpu_uvd_cs_pass1(struct amdgpu_uvd_cs_ctx *ctx)
 		if (cmd == 0x0 || cmd == 0x3) {
 			/* yes, force it into VRAM */
 			uint32_t domain = AMDGPU_GEM_DOMAIN_VRAM;
-			amdgpu_ttm_placement_from_domain(bo, domain);
+			amdgpu_bo_placement_from_domain(bo, domain);
 		}
 		amdgpu_uvd_force_into_uvd_segment(bo);
 
@@ -679,16 +699,15 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 	void *ptr;
 	long r;
 	int i;
-	uint32_t ip_instance = ctx->parser->job->ring->me;
 
 	if (offset & 0x3F) {
-		DRM_ERROR("UVD(%d) messages must be 64 byte aligned!\n", ip_instance);
+		DRM_ERROR("UVD messages must be 64 byte aligned!\n");
 		return -EINVAL;
 	}
 
 	r = amdgpu_bo_kmap(bo, &ptr);
 	if (r) {
-		DRM_ERROR("Failed mapping the UVD(%d) message (%ld)!\n", ip_instance, r);
+		DRM_ERROR("Failed mapping the UVD) message (%ld)!\n", r);
 		return r;
 	}
 
@@ -698,7 +717,7 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 	handle = msg[2];
 
 	if (handle == 0) {
-		DRM_ERROR("Invalid UVD(%d) handle!\n", ip_instance);
+		DRM_ERROR("Invalid UVD handle!\n");
 		return -EINVAL;
 	}
 
@@ -709,18 +728,19 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 
 		/* try to alloc a new handle */
 		for (i = 0; i < adev->uvd.max_handles; ++i) {
-			if (atomic_read(&adev->uvd.inst[ip_instance].handles[i]) == handle) {
-				DRM_ERROR("(%d)Handle 0x%x already in use!\n", ip_instance, handle);
+			if (atomic_read(&adev->uvd.handles[i]) == handle) {
+				DRM_ERROR(")Handle 0x%x already in use!\n",
+					  handle);
 				return -EINVAL;
 			}
 
-			if (!atomic_cmpxchg(&adev->uvd.inst[ip_instance].handles[i], 0, handle)) {
-				adev->uvd.inst[ip_instance].filp[i] = ctx->parser->filp;
+			if (!atomic_cmpxchg(&adev->uvd.handles[i], 0, handle)) {
+				adev->uvd.filp[i] = ctx->parser->filp;
 				return 0;
 			}
 		}
 
-		DRM_ERROR("No more free UVD(%d) handles!\n", ip_instance);
+		DRM_ERROR("No more free UVD handles!\n");
 		return -ENOSPC;
 
 	case 1:
@@ -732,27 +752,27 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 
 		/* validate the handle */
 		for (i = 0; i < adev->uvd.max_handles; ++i) {
-			if (atomic_read(&adev->uvd.inst[ip_instance].handles[i]) == handle) {
-				if (adev->uvd.inst[ip_instance].filp[i] != ctx->parser->filp) {
-					DRM_ERROR("UVD(%d) handle collision detected!\n", ip_instance);
+			if (atomic_read(&adev->uvd.handles[i]) == handle) {
+				if (adev->uvd.filp[i] != ctx->parser->filp) {
+					DRM_ERROR("UVD handle collision detected!\n");
 					return -EINVAL;
 				}
 				return 0;
 			}
 		}
 
-		DRM_ERROR("Invalid UVD(%d) handle 0x%x!\n", ip_instance, handle);
+		DRM_ERROR("Invalid UVD handle 0x%x!\n", handle);
 		return -ENOENT;
 
 	case 2:
 		/* it's a destroy msg, free the handle */
 		for (i = 0; i < adev->uvd.max_handles; ++i)
-			atomic_cmpxchg(&adev->uvd.inst[ip_instance].handles[i], handle, 0);
+			atomic_cmpxchg(&adev->uvd.handles[i], handle, 0);
 		amdgpu_bo_kunmap(bo);
 		return 0;
 
 	default:
-		DRM_ERROR("Illegal UVD(%d) message type (%d)!\n", ip_instance, msg_type);
+		DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type);
 		return -EINVAL;
 	}
 	BUG();
@@ -1000,7 +1020,7 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 	if (!ring->adev->uvd.address_64_bit) {
 		struct ttm_operation_ctx ctx = { true, false };
 
-		amdgpu_ttm_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_VRAM);
+		amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_VRAM);
 		amdgpu_uvd_force_into_uvd_segment(bo);
 		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		if (r)
@@ -1045,19 +1065,16 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 		if (r < 0)
 			goto err_free;
 
-		r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-		job->fence = dma_fence_get(f);
+		r = amdgpu_job_submit_direct(job, ring, &f);
 		if (r)
 			goto err_free;
-
-		amdgpu_job_free(job);
 	} else {
 		r = amdgpu_sync_resv(adev, &job->sync, bo->tbo.resv,
 				     AMDGPU_FENCE_OWNER_UNDEFINED, false);
 		if (r)
 			goto err_free;
 
-		r = amdgpu_job_submit(job, ring, &adev->uvd.inst[ring->me].entity,
+		r = amdgpu_job_submit(job, &adev->uvd.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
 		if (r)
 			goto err_free;
@@ -1149,6 +1166,8 @@ static void amdgpu_uvd_idle_work_handler(struct work_struct *work)
 	unsigned fences = 0, i, j;
 
 	for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
+		if (adev->uvd.harvest_config & (1 << i))
+			continue;
 		fences += amdgpu_fence_count_emitted(&adev->uvd.inst[i].ring);
 		for (j = 0; j < adev->uvd.num_enc_rings; ++j) {
 			fences += amdgpu_fence_count_emitted(&adev->uvd.inst[i].ring_enc[j]);
@@ -1259,7 +1278,7 @@ uint32_t amdgpu_uvd_used_handles(struct amdgpu_device *adev)
 		 * necessarily linear. So we need to count
 		 * all non-zero handles.
 		 */
-		if (atomic_read(&adev->uvd.inst->handles[i]))
+		if (atomic_read(&adev->uvd.handles[i]))
 			used_handles++;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
index 8b23a1b00c76..33c5f806f925 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
@@ -42,26 +42,29 @@ struct amdgpu_uvd_inst {
 	void			*cpu_addr;
 	uint64_t		gpu_addr;
 	void			*saved_bo;
-	atomic_t		handles[AMDGPU_MAX_UVD_HANDLES];
-	struct drm_file		*filp[AMDGPU_MAX_UVD_HANDLES];
 	struct amdgpu_ring	ring;
 	struct amdgpu_ring	ring_enc[AMDGPU_MAX_UVD_ENC_RINGS];
 	struct amdgpu_irq_src	irq;
-	struct drm_sched_entity entity;
-	struct drm_sched_entity entity_enc;
 	uint32_t                srbm_soft_reset;
 };
 
+#define AMDGPU_UVD_HARVEST_UVD0 (1 << 0)
+#define AMDGPU_UVD_HARVEST_UVD1 (1 << 1)
+
 struct amdgpu_uvd {
 	const struct firmware	*fw;	/* UVD firmware */
 	unsigned		fw_version;
 	unsigned		max_handles;
 	unsigned		num_enc_rings;
-	uint8_t		num_uvd_inst;
+	uint8_t			num_uvd_inst;
 	bool			address_64_bit;
 	bool			use_ctx_buf;
-	struct amdgpu_uvd_inst		inst[AMDGPU_MAX_UVD_INSTANCES];
+	struct amdgpu_uvd_inst	inst[AMDGPU_MAX_UVD_INSTANCES];
+	struct drm_file		*filp[AMDGPU_MAX_UVD_HANDLES];
+	atomic_t		handles[AMDGPU_MAX_UVD_HANDLES];
+	struct drm_sched_entity entity;
 	struct delayed_work	idle_work;
+	unsigned		harvest_config;
 };
 
 int amdgpu_uvd_sw_init(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 23d960ec1cf2..b6ab4f5350c8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -40,11 +40,11 @@
 
 /* Firmware Names */
 #ifdef CONFIG_DRM_AMDGPU_CIK
-#define FIRMWARE_BONAIRE	"radeon/bonaire_vce.bin"
-#define FIRMWARE_KABINI	"radeon/kabini_vce.bin"
-#define FIRMWARE_KAVERI	"radeon/kaveri_vce.bin"
-#define FIRMWARE_HAWAII	"radeon/hawaii_vce.bin"
-#define FIRMWARE_MULLINS	"radeon/mullins_vce.bin"
+#define FIRMWARE_BONAIRE	"amdgpu/bonaire_vce.bin"
+#define FIRMWARE_KABINI	"amdgpu/kabini_vce.bin"
+#define FIRMWARE_KAVERI	"amdgpu/kaveri_vce.bin"
+#define FIRMWARE_HAWAII	"amdgpu/hawaii_vce.bin"
+#define FIRMWARE_MULLINS	"amdgpu/mullins_vce.bin"
 #endif
 #define FIRMWARE_TONGA		"amdgpu/tonga_vce.bin"
 #define FIRMWARE_CARRIZO	"amdgpu/carrizo_vce.bin"
@@ -190,8 +190,7 @@ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size)
 
 	ring = &adev->vce.ring[0];
 	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-	r = drm_sched_entity_init(&ring->sched, &adev->vce.entity,
-				  rq, NULL);
+	r = drm_sched_entity_init(&adev->vce.entity, &rq, 1, NULL);
 	if (r != 0) {
 		DRM_ERROR("Failed setting up VCE run queue.\n");
 		return r;
@@ -222,7 +221,7 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev)
 	if (adev->vce.vcpu_bo == NULL)
 		return 0;
 
-	drm_sched_entity_fini(&adev->vce.ring[0].sched, &adev->vce.entity);
+	drm_sched_entity_destroy(&adev->vce.entity);
 
 	amdgpu_bo_free_kernel(&adev->vce.vcpu_bo, &adev->vce.gpu_addr,
 		(void **)&adev->vce.cpu_addr);
@@ -470,12 +469,10 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err;
 
-	amdgpu_job_free(job);
 	if (fence)
 		*fence = dma_fence_get(f);
 	dma_fence_put(f);
@@ -532,19 +529,13 @@ int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (direct) {
-		r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-		job->fence = dma_fence_get(f);
-		if (r)
-			goto err;
-
-		amdgpu_job_free(job);
-	} else {
-		r = amdgpu_job_submit(job, ring, &ring->adev->vce.entity,
+	if (direct)
+		r = amdgpu_job_submit_direct(job, ring, &f);
+	else
+		r = amdgpu_job_submit(job, &ring->adev->vce.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
-		if (r)
-			goto err;
-	}
+	if (r)
+		goto err;
 
 	if (fence)
 		*fence = dma_fence_get(f);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 1b4ad9b2a755..798648a19710 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -140,6 +140,8 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
 	for (i = 0; i < adev->vcn.num_enc_rings; ++i)
 		amdgpu_ring_fini(&adev->vcn.ring_enc[i]);
 
+	amdgpu_ring_fini(&adev->vcn.ring_jpeg);
+
 	release_firmware(adev->vcn.fw);
 
 	return 0;
@@ -209,6 +211,8 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
 		fences += amdgpu_fence_count_emitted(&adev->vcn.ring_enc[i]);
 	}
 
+	fences += amdgpu_fence_count_emitted(&adev->vcn.ring_jpeg);
+
 	if (fences == 0) {
 		if (adev->pm.dpm_enabled)
 			amdgpu_dpm_enable_uvd(adev, false);
@@ -225,7 +229,7 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 	bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work);
 
-	if (set_clocks && adev->pm.dpm_enabled) {
+	if (set_clocks) {
 		if (adev->pm.dpm_enabled)
 			amdgpu_dpm_enable_uvd(adev, true);
 		else
@@ -304,13 +308,10 @@ static int amdgpu_vcn_dec_send_msg(struct amdgpu_ring *ring,
 	}
 	ib->length_dw = 16;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err_free;
 
-	amdgpu_job_free(job);
-
 	amdgpu_bo_fence(bo, f, false);
 	amdgpu_bo_unreserve(bo);
 	amdgpu_bo_unref(&bo);
@@ -495,12 +496,10 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err;
 
-	amdgpu_job_free(job);
 	if (fence)
 		*fence = dma_fence_get(f);
 	dma_fence_put(f);
@@ -549,12 +548,10 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err;
 
-	amdgpu_job_free(job);
 	if (fence)
 		*fence = dma_fence_get(f);
 	dma_fence_put(f);
@@ -597,3 +594,127 @@ error:
 	dma_fence_put(fence);
 	return r;
 }
+
+int amdgpu_vcn_jpeg_ring_test_ring(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t tmp = 0;
+	unsigned i;
+	int r;
+
+	WREG32(SOC15_REG_OFFSET(UVD, 0, mmUVD_CONTEXT_ID), 0xCAFEDEAD);
+	r = amdgpu_ring_alloc(ring, 3);
+
+	if (r) {
+		DRM_ERROR("amdgpu: cp failed to lock ring %d (%d).\n",
+				  ring->idx, r);
+		return r;
+	}
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_CONTEXT_ID), 0, 0, 0));
+	amdgpu_ring_write(ring, 0xDEADBEEF);
+	amdgpu_ring_commit(ring);
+
+	for (i = 0; i < adev->usec_timeout; i++) {
+		tmp = RREG32(SOC15_REG_OFFSET(UVD, 0, mmUVD_CONTEXT_ID));
+		if (tmp == 0xDEADBEEF)
+			break;
+		DRM_UDELAY(1);
+	}
+
+	if (i < adev->usec_timeout) {
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n",
+				  ring->idx, i);
+	} else {
+		DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
+				  ring->idx, tmp);
+		r = -EINVAL;
+	}
+
+	return r;
+}
+
+static int amdgpu_vcn_jpeg_set_reg(struct amdgpu_ring *ring, uint32_t handle,
+		struct dma_fence **fence)
+{
+	struct amdgpu_device *adev = ring->adev;
+	struct amdgpu_job *job;
+	struct amdgpu_ib *ib;
+	struct dma_fence *f = NULL;
+	const unsigned ib_size_dw = 16;
+	int i, r;
+
+	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
+	if (r)
+		return r;
+
+	ib = &job->ibs[0];
+
+	ib->ptr[0] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_PITCH), 0, 0, PACKETJ_TYPE0);
+	ib->ptr[1] = 0xDEADBEEF;
+	for (i = 2; i < 16; i += 2) {
+		ib->ptr[i] = PACKETJ(0, 0, 0, PACKETJ_TYPE6);
+		ib->ptr[i+1] = 0;
+	}
+	ib->length_dw = 16;
+
+	r = amdgpu_job_submit_direct(job, ring, &f);
+	if (r)
+		goto err;
+
+	if (fence)
+		*fence = dma_fence_get(f);
+	dma_fence_put(f);
+
+	return 0;
+
+err:
+	amdgpu_job_free(job);
+	return r;
+}
+
+int amdgpu_vcn_jpeg_ring_test_ib(struct amdgpu_ring *ring, long timeout)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t tmp = 0;
+	unsigned i;
+	struct dma_fence *fence = NULL;
+	long r = 0;
+
+	r = amdgpu_vcn_jpeg_set_reg(ring, 1, &fence);
+	if (r) {
+		DRM_ERROR("amdgpu: failed to set jpeg register (%ld).\n", r);
+		goto error;
+	}
+
+	r = dma_fence_wait_timeout(fence, false, timeout);
+	if (r == 0) {
+		DRM_ERROR("amdgpu: IB test timed out.\n");
+		r = -ETIMEDOUT;
+		goto error;
+	} else if (r < 0) {
+		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
+		goto error;
+	} else
+		r = 0;
+
+	for (i = 0; i < adev->usec_timeout; i++) {
+		tmp = RREG32(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_PITCH));
+		if (tmp == 0xDEADBEEF)
+			break;
+		DRM_UDELAY(1);
+	}
+
+	if (i < adev->usec_timeout)
+		DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
+	else {
+		DRM_ERROR("ib test failed (0x%08X)\n", tmp);
+		r = -EINVAL;
+	}
+
+	dma_fence_put(fence);
+
+error:
+	return r;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index 773010b9ff15..0b0b8638d73f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -66,6 +66,7 @@ struct amdgpu_vcn {
 	const struct firmware	*fw;	/* VCN firmware */
 	struct amdgpu_ring	ring_dec;
 	struct amdgpu_ring	ring_enc[AMDGPU_VCN_MAX_ENC_RINGS];
+	struct amdgpu_ring	ring_jpeg;
 	struct amdgpu_irq_src	irq;
 	unsigned		num_enc_rings;
 };
@@ -83,4 +84,7 @@ int amdgpu_vcn_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout);
 int amdgpu_vcn_enc_ring_test_ring(struct amdgpu_ring *ring);
 int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout);
 
+int amdgpu_vcn_jpeg_ring_test_ring(struct amdgpu_ring *ring);
+int amdgpu_vcn_jpeg_ring_test_ib(struct amdgpu_ring *ring, long timeout);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index fdcb498f6d19..ece0ac703e27 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -33,9 +33,11 @@
 #include "amdgpu.h"
 #include "amdgpu_trace.h"
 #include "amdgpu_amdkfd.h"
+#include "amdgpu_gmc.h"
 
-/*
- * GPUVM
+/**
+ * DOC: GPUVM
+ *
  * GPUVM is similar to the legacy gart on older asics, however
  * rather than there being a single global gart table
  * for the entire GPU, there are multiple VM page tables active
@@ -63,37 +65,84 @@ INTERVAL_TREE_DEFINE(struct amdgpu_bo_va_mapping, rb, uint64_t, __subtree_last,
 #undef START
 #undef LAST
 
-/* Local structure. Encapsulate some VM table update parameters to reduce
+/**
+ * struct amdgpu_pte_update_params - Local structure
+ *
+ * Encapsulate some VM table update parameters to reduce
  * the number of function parameters
+ *
  */
 struct amdgpu_pte_update_params {
-	/* amdgpu device we do this update for */
+
+	/**
+	 * @adev: amdgpu device we do this update for
+	 */
 	struct amdgpu_device *adev;
-	/* optional amdgpu_vm we do this update for */
+
+	/**
+	 * @vm: optional amdgpu_vm we do this update for
+	 */
 	struct amdgpu_vm *vm;
-	/* address where to copy page table entries from */
+
+	/**
+	 * @src: address where to copy page table entries from
+	 */
 	uint64_t src;
-	/* indirect buffer to fill with commands */
+
+	/**
+	 * @ib: indirect buffer to fill with commands
+	 */
 	struct amdgpu_ib *ib;
-	/* Function which actually does the update */
+
+	/**
+	 * @func: Function which actually does the update
+	 */
 	void (*func)(struct amdgpu_pte_update_params *params,
 		     struct amdgpu_bo *bo, uint64_t pe,
 		     uint64_t addr, unsigned count, uint32_t incr,
 		     uint64_t flags);
-	/* The next two are used during VM update by CPU
-	 *  DMA addresses to use for mapping
-	 *  Kernel pointer of PD/PT BO that needs to be updated
+	/**
+	 * @pages_addr:
+	 *
+	 * DMA addresses to use for mapping, used during VM update by CPU
 	 */
 	dma_addr_t *pages_addr;
+
+	/**
+	 * @kptr:
+	 *
+	 * Kernel pointer of PD/PT BO that needs to be updated,
+	 * used during VM update by CPU
+	 */
 	void *kptr;
 };
 
-/* Helper to disable partial resident texture feature from a fence callback */
+/**
+ * struct amdgpu_prt_cb - Helper to disable partial resident texture feature from a fence callback
+ */
 struct amdgpu_prt_cb {
+
+	/**
+	 * @adev: amdgpu device
+	 */
 	struct amdgpu_device *adev;
+
+	/**
+	 * @cb: callback
+	 */
 	struct dma_fence_cb cb;
 };
 
+/**
+ * amdgpu_vm_bo_base_init - Adds bo to the list of bos associated with the vm
+ *
+ * @base: base structure for tracking BO usage in a VM
+ * @vm: vm to which bo is to be added
+ * @bo: amdgpu buffer object
+ *
+ * Initialize a bo_va_base structure and add it to the appropriate lists
+ *
+ */
 static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base,
 				   struct amdgpu_vm *vm,
 				   struct amdgpu_bo *bo)
@@ -129,8 +178,10 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base,
  * amdgpu_vm_level_shift - return the addr shift for each level
  *
  * @adev: amdgpu_device pointer
+ * @level: VMPT level
  *
- * Returns the number of bits the pfn needs to be right shifted for a level.
+ * Returns:
+ * The number of bits the pfn needs to be right shifted for a level.
  */
 static unsigned amdgpu_vm_level_shift(struct amdgpu_device *adev,
 				      unsigned level)
@@ -158,8 +209,10 @@ static unsigned amdgpu_vm_level_shift(struct amdgpu_device *adev,
  * amdgpu_vm_num_entries - return the number of entries in a PD/PT
  *
  * @adev: amdgpu_device pointer
+ * @level: VMPT level
  *
- * Calculate the number of entries in a page directory or page table.
+ * Returns:
+ * The number of entries in a page directory or page table.
  */
 static unsigned amdgpu_vm_num_entries(struct amdgpu_device *adev,
 				      unsigned level)
@@ -182,8 +235,10 @@ static unsigned amdgpu_vm_num_entries(struct amdgpu_device *adev,
  * amdgpu_vm_bo_size - returns the size of the BOs in bytes
  *
  * @adev: amdgpu_device pointer
+ * @level: VMPT level
  *
- * Calculate the size of the BO for a page directory or page table in bytes.
+ * Returns:
+ * The size of the BO for a page directory or page table in bytes.
  */
 static unsigned amdgpu_vm_bo_size(struct amdgpu_device *adev, unsigned level)
 {
@@ -221,6 +276,9 @@ void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
  * @param: parameter for the validation callback
  *
  * Validate the page table BOs on command submission if neccessary.
+ *
+ * Returns:
+ * Validation result.
  */
 int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			      int (*validate)(void *p, struct amdgpu_bo *bo),
@@ -276,6 +334,9 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
  * @vm: VM to check
  *
  * Check if all VM PDs/PTs are ready for updates
+ *
+ * Returns:
+ * True if eviction list is empty.
  */
 bool amdgpu_vm_ready(struct amdgpu_vm *vm)
 {
@@ -286,10 +347,15 @@ bool amdgpu_vm_ready(struct amdgpu_vm *vm)
  * amdgpu_vm_clear_bo - initially clear the PDs/PTs
  *
  * @adev: amdgpu_device pointer
+ * @vm: VM to clear BO from
  * @bo: BO to clear
  * @level: level this BO is at
+ * @pte_support_ats: indicate ATS support from PTE
  *
  * Root PD needs to be reserved when calling this.
+ *
+ * Returns:
+ * 0 on success, errno otherwise.
  */
 static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
 			      struct amdgpu_vm *vm, struct amdgpu_bo *bo,
@@ -321,7 +387,7 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
 		ats_entries = 0;
 	}
 
-	ring = container_of(vm->entity.sched, struct amdgpu_ring, sched);
+	ring = container_of(vm->entity.rq->sched, struct amdgpu_ring, sched);
 
 	r = reservation_object_reserve_shared(bo->tbo.resv);
 	if (r)
@@ -359,8 +425,8 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
 	if (r)
 		goto error_free;
 
-	r = amdgpu_job_submit(job, ring, &vm->entity,
-			      AMDGPU_FENCE_OWNER_UNDEFINED, &fence);
+	r = amdgpu_job_submit(job, &vm->entity, AMDGPU_FENCE_OWNER_UNDEFINED,
+			      &fence);
 	if (r)
 		goto error_free;
 
@@ -385,10 +451,16 @@ error:
  *
  * @adev: amdgpu_device pointer
  * @vm: requested vm
+ * @parent: parent PT
  * @saddr: start of the address range
  * @eaddr: end of the address range
+ * @level: VMPT level
+ * @ats: indicate ATS support from PTE
  *
  * Make sure the page directories and page tables are allocated
+ *
+ * Returns:
+ * 0 on success, errno otherwise.
  */
 static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev,
 				  struct amdgpu_vm *vm,
@@ -423,11 +495,12 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev,
 	eaddr = eaddr & ((1 << shift) - 1);
 
 	flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
+	if (vm->root.base.bo->shadow)
+		flags |= AMDGPU_GEM_CREATE_SHADOW;
 	if (vm->use_cpu_for_update)
 		flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
 	else
-		flags |= (AMDGPU_GEM_CREATE_NO_CPU_ACCESS |
-				AMDGPU_GEM_CREATE_SHADOW);
+		flags |= AMDGPU_GEM_CREATE_NO_CPU_ACCESS;
 
 	/* walk over the address space and allocate the page tables */
 	for (pt_idx = from; pt_idx <= to; ++pt_idx) {
@@ -496,6 +569,9 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev,
  * @size: Size from start address we need.
  *
  * Make sure the page tables are allocated.
+ *
+ * Returns:
+ * 0 on success, errno otherwise.
  */
 int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,
 			struct amdgpu_vm *vm,
@@ -561,6 +637,15 @@ void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev)
 	}
 }
 
+/**
+ * amdgpu_vm_need_pipeline_sync - Check if pipe sync is needed for job.
+ *
+ * @ring: ring on which the job will be submitted
+ * @job: job to submit
+ *
+ * Returns:
+ * True if sync is needed.
+ */
 bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
 				  struct amdgpu_job *job)
 {
@@ -588,19 +673,17 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
 	return vm_flush_needed || gds_switch_needed;
 }
 
-static bool amdgpu_vm_is_large_bar(struct amdgpu_device *adev)
-{
-	return (adev->gmc.real_vram_size == adev->gmc.visible_vram_size);
-}
-
 /**
  * amdgpu_vm_flush - hardware flush the vm
  *
  * @ring: ring to use for flush
- * @vmid: vmid number to use
- * @pd_addr: address of the page directory
+ * @job:  related job
+ * @need_pipe_sync: is pipe sync needed
  *
  * Emit a VM flush when it is necessary.
+ *
+ * Returns:
+ * 0 on success, errno otherwise.
  */
 int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_pipe_sync)
 {
@@ -708,6 +791,9 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_
  * Returns the found bo_va or NULL if none is found
  *
  * Object has to be reserved!
+ *
+ * Returns:
+ * Found bo_va or NULL.
  */
 struct amdgpu_bo_va *amdgpu_vm_bo_find(struct amdgpu_vm *vm,
 				       struct amdgpu_bo *bo)
@@ -789,7 +875,10 @@ static void amdgpu_vm_do_copy_ptes(struct amdgpu_pte_update_params *params,
  * @addr: the unmapped addr
  *
  * Look up the physical address of the page that the pte resolves
- * to and return the pointer for the page table entry.
+ * to.
+ *
+ * Returns:
+ * The pointer for the page table entry.
  */
 static uint64_t amdgpu_vm_map_gart(const dma_addr_t *pages_addr, uint64_t addr)
 {
@@ -842,6 +931,17 @@ static void amdgpu_vm_cpu_set_ptes(struct amdgpu_pte_update_params *params,
 	}
 }
 
+
+/**
+ * amdgpu_vm_wait_pd - Wait for PT BOs to be free.
+ *
+ * @adev: amdgpu_device pointer
+ * @vm: related vm
+ * @owner: fence owner
+ *
+ * Returns:
+ * 0 on success, errno otherwise.
+ */
 static int amdgpu_vm_wait_pd(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			     void *owner)
 {
@@ -895,7 +995,10 @@ static void amdgpu_vm_update_pde(struct amdgpu_pte_update_params *params,
 /*
  * amdgpu_vm_invalidate_level - mark all PD levels as invalid
  *
+ * @adev: amdgpu_device pointer
+ * @vm: related vm
  * @parent: parent PD
+ * @level: VMPT level
  *
  * Mark all PD level as invalid after an error.
  */
@@ -930,7 +1033,9 @@ static void amdgpu_vm_invalidate_level(struct amdgpu_device *adev,
  * @vm: requested vm
  *
  * Makes sure all directories are up to date.
- * Returns 0 for success, error for failure.
+ *
+ * Returns:
+ * 0 for success, error for failure.
  */
 int amdgpu_vm_update_directories(struct amdgpu_device *adev,
 				 struct amdgpu_vm *vm)
@@ -980,7 +1085,7 @@ restart:
 					   struct amdgpu_vm_bo_base,
 					   vm_status);
 		bo_base->moved = false;
-		list_move(&bo_base->vm_status, &vm->idle);
+		list_del_init(&bo_base->vm_status);
 
 		bo = bo_base->bo->parent;
 		if (!bo)
@@ -1009,15 +1114,15 @@ restart:
 		struct amdgpu_ring *ring;
 		struct dma_fence *fence;
 
-		ring = container_of(vm->entity.sched, struct amdgpu_ring,
+		ring = container_of(vm->entity.rq->sched, struct amdgpu_ring,
 				    sched);
 
 		amdgpu_ring_pad_ib(ring, params.ib);
 		amdgpu_sync_resv(adev, &job->sync, root->tbo.resv,
 				 AMDGPU_FENCE_OWNER_VM, false);
 		WARN_ON(params.ib->length_dw > ndw);
-		r = amdgpu_job_submit(job, ring, &vm->entity,
-				      AMDGPU_FENCE_OWNER_VM, &fence);
+		r = amdgpu_job_submit(job, &vm->entity, AMDGPU_FENCE_OWNER_VM,
+				      &fence);
 		if (r)
 			goto error;
 
@@ -1117,14 +1222,15 @@ static void amdgpu_vm_handle_huge_pages(struct amdgpu_pte_update_params *p,
  * amdgpu_vm_update_ptes - make sure that page tables are valid
  *
  * @params: see amdgpu_pte_update_params definition
- * @vm: requested vm
  * @start: start of GPU address range
  * @end: end of GPU address range
  * @dst: destination address to map to, the next dst inside the function
  * @flags: mapping flags
  *
  * Update the page tables in the range @start - @end.
- * Returns 0 for success, -EINVAL for failure.
+ *
+ * Returns:
+ * 0 for success, -EINVAL for failure.
  */
 static int amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params,
 				  uint64_t start, uint64_t end,
@@ -1178,7 +1284,9 @@ static int amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params,
  * @end: last PTE to handle
  * @dst: addr those PTEs should point to
  * @flags: hw mapping flags
- * Returns 0 for success, -EINVAL for failure.
+ *
+ * Returns:
+ * 0 for success, -EINVAL for failure.
  */
 static int amdgpu_vm_frag_ptes(struct amdgpu_pte_update_params	*params,
 				uint64_t start, uint64_t end,
@@ -1250,7 +1358,9 @@ static int amdgpu_vm_frag_ptes(struct amdgpu_pte_update_params	*params,
  * @fence: optional resulting fence
  *
  * Fill in the page table entries between @start and @last.
- * Returns 0 for success, -EINVAL for failure.
+ *
+ * Returns:
+ * 0 for success, -EINVAL for failure.
  */
 static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 				       struct dma_fence *exclusive,
@@ -1294,7 +1404,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 					   addr, flags);
 	}
 
-	ring = container_of(vm->entity.sched, struct amdgpu_ring, sched);
+	ring = container_of(vm->entity.rq->sched, struct amdgpu_ring, sched);
 
 	nptes = last - start + 1;
 
@@ -1326,7 +1436,10 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 		ndw += ncmds * 10;
 
 		/* extra commands for begin/end fragments */
-		ndw += 2 * 10 * adev->vm_manager.fragment_size;
+		if (vm->root.base.bo->shadow)
+		        ndw += 2 * 10 * adev->vm_manager.fragment_size * 2;
+		else
+		        ndw += 2 * 10 * adev->vm_manager.fragment_size;
 
 		params.func = amdgpu_vm_do_set_ptes;
 	}
@@ -1373,8 +1486,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 
 	amdgpu_ring_pad_ib(ring, params.ib);
 	WARN_ON(params.ib->length_dw > ndw);
-	r = amdgpu_job_submit(job, ring, &vm->entity,
-			      AMDGPU_FENCE_OWNER_VM, &f);
+	r = amdgpu_job_submit(job, &vm->entity, AMDGPU_FENCE_OWNER_VM, &f);
 	if (r)
 		goto error_free;
 
@@ -1402,7 +1514,9 @@ error_free:
  *
  * Split the mapping into smaller chunks so that each update fits
  * into a SDMA IB.
- * Returns 0 for success, -EINVAL for failure.
+ *
+ * Returns:
+ * 0 for success, -EINVAL for failure.
  */
 static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 				      struct dma_fence *exclusive,
@@ -1455,7 +1569,7 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 		if (nodes) {
 			addr = nodes->start << PAGE_SHIFT;
 			max_entries = (nodes->size - pfn) *
-				(PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+				AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 		} else {
 			addr = 0;
 			max_entries = S64_MAX;
@@ -1466,7 +1580,7 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 
 			max_entries = min(max_entries, 16ull * 1024ull);
 			for (count = 1;
-			     count < max_entries / (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+			     count < max_entries / AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 			     ++count) {
 				uint64_t idx = pfn + count;
 
@@ -1480,7 +1594,7 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 				dma_addr = pages_addr;
 			} else {
 				addr = pages_addr[pfn];
-				max_entries = count * (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+				max_entries = count * AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 			}
 
 		} else if (flags & AMDGPU_PTE_VALID) {
@@ -1495,7 +1609,7 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 		if (r)
 			return r;
 
-		pfn += (last - start + 1) / (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+		pfn += (last - start + 1) / AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 		if (nodes && nodes->size == pfn) {
 			pfn = 0;
 			++nodes;
@@ -1515,7 +1629,9 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
  * @clear: if true clear the entries
  *
  * Fill in the page table entries for @bo_va.
- * Returns 0 for success, -EINVAL for failure.
+ *
+ * Returns:
+ * 0 for success, -EINVAL for failure.
  */
 int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 			struct amdgpu_bo_va *bo_va,
@@ -1531,18 +1647,17 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 	uint64_t flags;
 	int r;
 
-	if (clear || !bo_va->base.bo) {
+	if (clear || !bo) {
 		mem = NULL;
 		nodes = NULL;
 		exclusive = NULL;
 	} else {
 		struct ttm_dma_tt *ttm;
 
-		mem = &bo_va->base.bo->tbo.mem;
+		mem = &bo->tbo.mem;
 		nodes = mem->mm_node;
 		if (mem->mem_type == TTM_PL_TT) {
-			ttm = container_of(bo_va->base.bo->tbo.ttm,
-					   struct ttm_dma_tt, ttm);
+			ttm = container_of(bo->tbo.ttm, struct ttm_dma_tt, ttm);
 			pages_addr = ttm->dma_address;
 		}
 		exclusive = reservation_object_get_excl(bo->tbo.resv);
@@ -1610,6 +1725,8 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 
 /**
  * amdgpu_vm_update_prt_state - update the global PRT state
+ *
+ * @adev: amdgpu_device pointer
  */
 static void amdgpu_vm_update_prt_state(struct amdgpu_device *adev)
 {
@@ -1624,6 +1741,8 @@ static void amdgpu_vm_update_prt_state(struct amdgpu_device *adev)
 
 /**
  * amdgpu_vm_prt_get - add a PRT user
+ *
+ * @adev: amdgpu_device pointer
  */
 static void amdgpu_vm_prt_get(struct amdgpu_device *adev)
 {
@@ -1636,6 +1755,8 @@ static void amdgpu_vm_prt_get(struct amdgpu_device *adev)
 
 /**
  * amdgpu_vm_prt_put - drop a PRT user
+ *
+ * @adev: amdgpu_device pointer
  */
 static void amdgpu_vm_prt_put(struct amdgpu_device *adev)
 {
@@ -1645,6 +1766,9 @@ static void amdgpu_vm_prt_put(struct amdgpu_device *adev)
 
 /**
  * amdgpu_vm_prt_cb - callback for updating the PRT status
+ *
+ * @fence: fence for the callback
+ * @_cb: the callback function
  */
 static void amdgpu_vm_prt_cb(struct dma_fence *fence, struct dma_fence_cb *_cb)
 {
@@ -1656,6 +1780,9 @@ static void amdgpu_vm_prt_cb(struct dma_fence *fence, struct dma_fence_cb *_cb)
 
 /**
  * amdgpu_vm_add_prt_cb - add callback for updating the PRT status
+ *
+ * @adev: amdgpu_device pointer
+ * @fence: fence for the callback
  */
 static void amdgpu_vm_add_prt_cb(struct amdgpu_device *adev,
 				 struct dma_fence *fence)
@@ -1747,9 +1874,11 @@ static void amdgpu_vm_prt_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
  * or if an error occurred)
  *
  * Make sure all freed BOs are cleared in the PT.
- * Returns 0 for success.
- *
  * PTs have to be reserved and mutex must be locked!
+ *
+ * Returns:
+ * 0 for success.
+ *
  */
 int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
 			  struct amdgpu_vm *vm,
@@ -1794,10 +1923,11 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
  *
  * @adev: amdgpu_device pointer
  * @vm: requested vm
- * @sync: sync object to add fences to
  *
  * Make sure all BOs which are moved are updated in the PTs.
- * Returns 0 for success.
+ *
+ * Returns:
+ * 0 for success.
  *
  * PTs have to be reserved!
  */
@@ -1852,7 +1982,9 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
  *
  * Add @bo into the requested vm.
  * Add @bo to the list of bos associated with the vm
- * Returns newly added bo_va or NULL for failure
+ *
+ * Returns:
+ * Newly added bo_va or NULL for failure
  *
  * Object has to be reserved!
  */
@@ -1915,10 +2047,13 @@ static void amdgpu_vm_bo_insert_map(struct amdgpu_device *adev,
  * @bo_va: bo_va to store the address
  * @saddr: where to map the BO
  * @offset: requested offset in the BO
+ * @size: BO size in bytes
  * @flags: attributes of pages (read/write/valid/etc.)
  *
  * Add a mapping of the BO at the specefied addr into the VM.
- * Returns 0 for success, error for failure.
+ *
+ * Returns:
+ * 0 for success, error for failure.
  *
  * Object has to be reserved and unreserved outside!
  */
@@ -1976,11 +2111,14 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
  * @bo_va: bo_va to store the address
  * @saddr: where to map the BO
  * @offset: requested offset in the BO
+ * @size: BO size in bytes
  * @flags: attributes of pages (read/write/valid/etc.)
  *
  * Add a mapping of the BO at the specefied addr into the VM. Replace existing
  * mappings as we do so.
- * Returns 0 for success, error for failure.
+ *
+ * Returns:
+ * 0 for success, error for failure.
  *
  * Object has to be reserved and unreserved outside!
  */
@@ -2037,7 +2175,9 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev,
  * @saddr: where to the BO is mapped
  *
  * Remove a mapping of the BO at the specefied addr from the VM.
- * Returns 0 for success, error for failure.
+ *
+ * Returns:
+ * 0 for success, error for failure.
  *
  * Object has to be reserved and unreserved outside!
  */
@@ -2091,7 +2231,9 @@ int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
  * @size: size of the range
  *
  * Remove all mappings in a range, split them as appropriate.
- * Returns 0 for success, error for failure.
+ *
+ * Returns:
+ * 0 for success, error for failure.
  */
 int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev,
 				struct amdgpu_vm *vm,
@@ -2188,8 +2330,13 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev,
  * amdgpu_vm_bo_lookup_mapping - find mapping by address
  *
  * @vm: the requested VM
+ * @addr: the address
  *
  * Find a mapping by it's address.
+ *
+ * Returns:
+ * The amdgpu_bo_va_mapping matching for addr or NULL
+ *
  */
 struct amdgpu_bo_va_mapping *amdgpu_vm_bo_lookup_mapping(struct amdgpu_vm *vm,
 							 uint64_t addr)
@@ -2198,6 +2345,35 @@ struct amdgpu_bo_va_mapping *amdgpu_vm_bo_lookup_mapping(struct amdgpu_vm *vm,
 }
 
 /**
+ * amdgpu_vm_bo_trace_cs - trace all reserved mappings
+ *
+ * @vm: the requested vm
+ * @ticket: CS ticket
+ *
+ * Trace all mappings of BOs reserved during a command submission.
+ */
+void amdgpu_vm_bo_trace_cs(struct amdgpu_vm *vm, struct ww_acquire_ctx *ticket)
+{
+	struct amdgpu_bo_va_mapping *mapping;
+
+	if (!trace_amdgpu_vm_bo_cs_enabled())
+		return;
+
+	for (mapping = amdgpu_vm_it_iter_first(&vm->va, 0, U64_MAX); mapping;
+	     mapping = amdgpu_vm_it_iter_next(mapping, 0, U64_MAX)) {
+		if (mapping->bo_va && mapping->bo_va->base.bo) {
+			struct amdgpu_bo *bo;
+
+			bo = mapping->bo_va->base.bo;
+			if (READ_ONCE(bo->tbo.resv->lock.ctx) != ticket)
+				continue;
+		}
+
+		trace_amdgpu_vm_bo_cs(mapping);
+	}
+}
+
+/**
  * amdgpu_vm_bo_rmv - remove a bo to a specific vm
  *
  * @adev: amdgpu_device pointer
@@ -2241,8 +2417,8 @@ void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
  * amdgpu_vm_bo_invalidate - mark the bo as invalid
  *
  * @adev: amdgpu_device pointer
- * @vm: requested vm
  * @bo: amdgpu buffer object
+ * @evicted: is the BO evicted
  *
  * Mark @bo as invalid.
  */
@@ -2282,6 +2458,14 @@ void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
 	}
 }
 
+/**
+ * amdgpu_vm_get_block_size - calculate VM page table size as power of two
+ *
+ * @vm_size: VM size
+ *
+ * Returns:
+ * VM page table as power of two
+ */
 static uint32_t amdgpu_vm_get_block_size(uint64_t vm_size)
 {
 	/* Total bits covered by PD + PTs */
@@ -2300,6 +2484,10 @@ static uint32_t amdgpu_vm_get_block_size(uint64_t vm_size)
  *
  * @adev: amdgpu_device pointer
  * @vm_size: the default vm size if it's set auto
+ * @fragment_size_default: Default PTE fragment size
+ * @max_level: max VMPT level
+ * @max_bits: max address space size in bits
+ *
  */
 void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t vm_size,
 			   uint32_t fragment_size_default, unsigned max_level,
@@ -2367,8 +2555,12 @@ void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t vm_size,
  * @adev: amdgpu_device pointer
  * @vm: requested vm
  * @vm_context: Indicates if it GFX or Compute context
+ * @pasid: Process address space identifier
  *
  * Init @vm fields.
+ *
+ * Returns:
+ * 0 for success, error for failure.
  */
 int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		   int vm_context, unsigned int pasid)
@@ -2400,8 +2592,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	ring_instance %= adev->vm_manager.vm_pte_num_rings;
 	ring = adev->vm_manager.vm_pte_rings[ring_instance];
 	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL];
-	r = drm_sched_entity_init(&ring->sched, &vm->entity,
-				  rq, NULL);
+	r = drm_sched_entity_init(&vm->entity, &rq, 1, NULL);
 	if (r)
 		return r;
 
@@ -2419,14 +2610,14 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	}
 	DRM_DEBUG_DRIVER("VM update mode is %s\n",
 			 vm->use_cpu_for_update ? "CPU" : "SDMA");
-	WARN_ONCE((vm->use_cpu_for_update & !amdgpu_vm_is_large_bar(adev)),
+	WARN_ONCE((vm->use_cpu_for_update & !amdgpu_gmc_vram_full_visible(&adev->gmc)),
 		  "CPU update of VM recommended only for large BAR system\n");
 	vm->last_update = NULL;
 
 	flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
 	if (vm->use_cpu_for_update)
 		flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
-	else
+	else if (vm_context != AMDGPU_VM_CONTEXT_COMPUTE)
 		flags |= AMDGPU_GEM_CREATE_SHADOW;
 
 	size = amdgpu_vm_bo_size(adev, adev->vm_manager.root_level);
@@ -2481,7 +2672,7 @@ error_free_root:
 	vm->root.base.bo = NULL;
 
 error_free_sched_entity:
-	drm_sched_entity_fini(&ring->sched, &vm->entity);
+	drm_sched_entity_destroy(&vm->entity);
 
 	return r;
 }
@@ -2489,6 +2680,9 @@ error_free_sched_entity:
 /**
  * amdgpu_vm_make_compute - Turn a GFX VM into a compute VM
  *
+ * @adev: amdgpu_device pointer
+ * @vm: requested vm
+ *
  * This only works on GFX VMs that don't have any BOs added and no
  * page tables allocated yet.
  *
@@ -2498,10 +2692,10 @@ error_free_sched_entity:
  * - pasid (old PASID is released, because compute manages its own PASIDs)
  *
  * Reinitializes the page directory to reflect the changed ATS
- * setting. May leave behind an unused shadow BO for the page
- * directory when switching from SDMA updates to CPU updates.
+ * setting.
  *
- * Returns 0 for success, -errno for errors.
+ * Returns:
+ * 0 for success, -errno for errors.
  */
 int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 {
@@ -2535,7 +2729,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	vm->pte_support_ats = pte_support_ats;
 	DRM_DEBUG_DRIVER("VM update mode is %s\n",
 			 vm->use_cpu_for_update ? "CPU" : "SDMA");
-	WARN_ONCE((vm->use_cpu_for_update & !amdgpu_vm_is_large_bar(adev)),
+	WARN_ONCE((vm->use_cpu_for_update & !amdgpu_gmc_vram_full_visible(&adev->gmc)),
 		  "CPU update of VM recommended only for large BAR system\n");
 
 	if (vm->pasid) {
@@ -2548,6 +2742,9 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		vm->pasid = 0;
 	}
 
+	/* Free the shadow bo for compute VM */
+	amdgpu_bo_unref(&vm->root.base.bo->shadow);
+
 error:
 	amdgpu_bo_unreserve(vm->root.base.bo);
 	return r;
@@ -2614,7 +2811,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
 	}
 
-	drm_sched_entity_fini(vm->entity.sched, &vm->entity);
+	drm_sched_entity_destroy(&vm->entity);
 
 	if (!RB_EMPTY_ROOT(&vm->va.rb_root)) {
 		dev_err(adev->dev, "still active bo inside vm\n");
@@ -2656,8 +2853,10 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
  * @adev: amdgpu_device pointer
  * @pasid: PASID do identify the VM
  *
- * This function is expected to be called in interrupt context. Returns
- * true if there was fault credit, false otherwise
+ * This function is expected to be called in interrupt context.
+ *
+ * Returns:
+ * True if there was fault credit, false otherwise
  */
 bool amdgpu_vm_pasid_fault_credit(struct amdgpu_device *adev,
 				  unsigned int pasid)
@@ -2711,7 +2910,7 @@ void amdgpu_vm_manager_init(struct amdgpu_device *adev)
 	 */
 #ifdef CONFIG_X86_64
 	if (amdgpu_vm_update_mode == -1) {
-		if (amdgpu_vm_is_large_bar(adev))
+		if (amdgpu_gmc_vram_full_visible(&adev->gmc))
 			adev->vm_manager.vm_update_mode =
 				AMDGPU_VM_USE_CPU_FOR_COMPUTE;
 		else
@@ -2741,6 +2940,16 @@ void amdgpu_vm_manager_fini(struct amdgpu_device *adev)
 	amdgpu_vmid_mgr_fini(adev);
 }
 
+/**
+ * amdgpu_vm_ioctl - Manages VMID reservation for vm hubs.
+ *
+ * @dev: drm device pointer
+ * @data: drm_amdgpu_vm
+ * @filp: drm file pointer
+ *
+ * Returns:
+ * 0 for success, -errno for errors.
+ */
 int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 {
 	union drm_amdgpu_vm *args = data;
@@ -2764,3 +2973,42 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 
 	return 0;
 }
+
+/**
+ * amdgpu_vm_get_task_info - Extracts task info for a PASID.
+ *
+ * @dev: drm device pointer
+ * @pasid: PASID identifier for VM
+ * @task_info: task_info to fill.
+ */
+void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
+			 struct amdgpu_task_info *task_info)
+{
+	struct amdgpu_vm *vm;
+
+	spin_lock(&adev->vm_manager.pasid_lock);
+
+	vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
+	if (vm)
+		*task_info = vm->task_info;
+
+	spin_unlock(&adev->vm_manager.pasid_lock);
+}
+
+/**
+ * amdgpu_vm_set_task_info - Sets VMs task info.
+ *
+ * @vm: vm for which to set the info
+ */
+void amdgpu_vm_set_task_info(struct amdgpu_vm *vm)
+{
+	if (!vm->task_info.pid) {
+		vm->task_info.pid = current->pid;
+		get_task_comm(vm->task_info.task_name, current);
+
+		if (current->group_leader->mm == current->mm) {
+			vm->task_info.tgid = current->group_leader->pid;
+			get_task_comm(vm->task_info.process_name, current->group_leader);
+		}
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 061b99a18cb8..67a15d439ac0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -164,6 +164,14 @@ struct amdgpu_vm_pt {
 #define AMDGPU_VM_FAULT_PASID(fault) ((u64)(fault) >> 48)
 #define AMDGPU_VM_FAULT_ADDR(fault)  ((u64)(fault) & 0xfffffffff000ULL)
 
+
+struct amdgpu_task_info {
+	char	process_name[TASK_COMM_LEN];
+	char	task_name[TASK_COMM_LEN];
+	pid_t	pid;
+	pid_t	tgid;
+};
+
 struct amdgpu_vm {
 	/* tree of virtual addresses mapped */
 	struct rb_root_cached	va;
@@ -215,6 +223,9 @@ struct amdgpu_vm {
 
 	/* Valid while the PD is reserved or fenced */
 	uint64_t		pd_phys_addr;
+
+	/* Some basic info about the task */
+	struct amdgpu_task_info task_info;
 };
 
 struct amdgpu_vm_manager {
@@ -307,6 +318,7 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev,
 				uint64_t saddr, uint64_t size);
 struct amdgpu_bo_va_mapping *amdgpu_vm_bo_lookup_mapping(struct amdgpu_vm *vm,
 							 uint64_t addr);
+void amdgpu_vm_bo_trace_cs(struct amdgpu_vm *vm, struct ww_acquire_ctx *ticket);
 void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
 		      struct amdgpu_bo_va *bo_va);
 void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t vm_size,
@@ -317,4 +329,9 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
 				  struct amdgpu_job *job);
 void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev);
 
+void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
+			 struct amdgpu_task_info *task_info);
+
+void amdgpu_vm_set_task_info(struct amdgpu_vm *vm);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index b6333f92ba45..9cfa8a9ada92 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -97,33 +97,29 @@ static u64 amdgpu_vram_mgr_vis_size(struct amdgpu_device *adev,
 }
 
 /**
- * amdgpu_vram_mgr_bo_invisible_size - CPU invisible BO size
+ * amdgpu_vram_mgr_bo_visible_size - CPU visible BO size
  *
  * @bo: &amdgpu_bo buffer object (must be in VRAM)
  *
  * Returns:
- * How much of the given &amdgpu_bo buffer object lies in CPU invisible VRAM.
+ * How much of the given &amdgpu_bo buffer object lies in CPU visible VRAM.
  */
-u64 amdgpu_vram_mgr_bo_invisible_size(struct amdgpu_bo *bo)
+u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	struct ttm_mem_reg *mem = &bo->tbo.mem;
 	struct drm_mm_node *nodes = mem->mm_node;
 	unsigned pages = mem->num_pages;
-	u64 usage = 0;
+	u64 usage;
 
-	if (adev->gmc.visible_vram_size == adev->gmc.real_vram_size)
-		return 0;
+	if (amdgpu_gmc_vram_full_visible(&adev->gmc))
+		return amdgpu_bo_size(bo);
 
 	if (mem->start >= adev->gmc.visible_vram_size >> PAGE_SHIFT)
-		return amdgpu_bo_size(bo);
+		return 0;
 
-	while (nodes && pages) {
-		usage += nodes->size << PAGE_SHIFT;
-		usage -= amdgpu_vram_mgr_vis_size(adev, nodes);
-		pages -= nodes->size;
-		++nodes;
-	}
+	for (usage = 0; nodes && pages; pages -= nodes->size, nodes++)
+		usage += amdgpu_vram_mgr_vis_size(adev, nodes);
 
 	return usage;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index 7fbad2f5f0bd..d2469453dca2 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -49,10 +49,10 @@
 #include "gmc/gmc_7_1_d.h"
 #include "gmc/gmc_7_1_sh_mask.h"
 
-MODULE_FIRMWARE("radeon/bonaire_smc.bin");
-MODULE_FIRMWARE("radeon/bonaire_k_smc.bin");
-MODULE_FIRMWARE("radeon/hawaii_smc.bin");
-MODULE_FIRMWARE("radeon/hawaii_k_smc.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_smc.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_k_smc.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_smc.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_k_smc.bin");
 
 #define MC_CG_ARB_FREQ_F0           0x0a
 #define MC_CG_ARB_FREQ_F1           0x0b
@@ -951,12 +951,12 @@ static void ci_apply_state_adjust_rules(struct amdgpu_device *adev,
 	else
 		pi->battery_state = false;
 
-	if (adev->pm.dpm.ac_power)
+	if (adev->pm.ac_power)
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
 	else
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_dc;
 
-	if (adev->pm.dpm.ac_power == false) {
+	if (adev->pm.ac_power == false) {
 		for (i = 0; i < ps->performance_level_count; i++) {
 			if (ps->performance_levels[i].mclk > max_limits->mclk)
 				ps->performance_levels[i].mclk = max_limits->mclk;
@@ -4078,7 +4078,7 @@ static int ci_enable_uvd_dpm(struct amdgpu_device *adev, bool enable)
 	const struct amdgpu_clock_and_voltage_limits *max_limits;
 	int i;
 
-	if (adev->pm.dpm.ac_power)
+	if (adev->pm.ac_power)
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
 	else
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_dc;
@@ -4127,7 +4127,7 @@ static int ci_enable_vce_dpm(struct amdgpu_device *adev, bool enable)
 	const struct amdgpu_clock_and_voltage_limits *max_limits;
 	int i;
 
-	if (adev->pm.dpm.ac_power)
+	if (adev->pm.ac_power)
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
 	else
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_dc;
@@ -4160,7 +4160,7 @@ static int ci_enable_samu_dpm(struct amdgpu_device *adev, bool enable)
 	const struct amdgpu_clock_and_voltage_limits *max_limits;
 	int i;
 
-	if (adev->pm.dpm.ac_power)
+	if (adev->pm.ac_power)
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
 	else
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_dc;
@@ -4191,7 +4191,7 @@ static int ci_enable_acp_dpm(struct amdgpu_device *adev, bool enable)
 	const struct amdgpu_clock_and_voltage_limits *max_limits;
 	int i;
 
-	if (adev->pm.dpm.ac_power)
+	if (adev->pm.ac_power)
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
 	else
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_dc;
@@ -5815,7 +5815,7 @@ static int ci_dpm_init_microcode(struct amdgpu_device *adev)
 	default: BUG();
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_smc.bin", chip_name);
 	err = request_firmware(&adev->pm.fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -5846,8 +5846,7 @@ static int ci_dpm_init(struct amdgpu_device *adev)
 	adev->pm.dpm.priv = pi;
 
 	pi->sys_pcie_mask =
-		(adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_MASK) >>
-		CAIL_PCIE_LINK_SPEED_SUPPORT_SHIFT;
+		adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_MASK;
 
 	pi->force_pcie_gen = AMDGPU_PCIE_GEN_INVALID;
 
@@ -6767,6 +6766,19 @@ static int ci_dpm_read_sensor(void *handle, int idx,
 	}
 }
 
+static int ci_set_powergating_by_smu(void *handle,
+				uint32_t block_type, bool gate)
+{
+	switch (block_type) {
+	case AMD_IP_BLOCK_TYPE_UVD:
+		ci_dpm_powergate_uvd(handle, gate);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
 static const struct amd_ip_funcs ci_dpm_ip_funcs = {
 	.name = "ci_dpm",
 	.early_init = ci_dpm_early_init,
@@ -6804,7 +6816,7 @@ static const struct amd_pm_funcs ci_dpm_funcs = {
 	.debugfs_print_current_performance_level = &ci_dpm_debugfs_print_current_performance_level,
 	.force_performance_level = &ci_dpm_force_performance_level,
 	.vblank_too_short = &ci_dpm_vblank_too_short,
-	.powergate_uvd = &ci_dpm_powergate_uvd,
+	.set_powergating_by_smu = &ci_set_powergating_by_smu,
 	.set_fan_control_mode = &ci_dpm_set_fan_control_mode,
 	.get_fan_control_mode = &ci_dpm_get_fan_control_mode,
 	.set_fan_speed_percent = &ci_dpm_set_fan_speed_percent,
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 8ff4c60d1b59..78ab939ae5d8 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1476,7 +1476,7 @@ static void cik_pcie_gen3_enable(struct amdgpu_device *adev)
 				tmp |= PCIE_LC_CNTL4__LC_REDO_EQ_MASK;
 				WREG32_PCIE(ixPCIE_LC_CNTL4, tmp);
 
-				mdelay(100);
+				msleep(100);
 
 				/* linkctl */
 				pci_read_config_word(root, bridge_pos + PCI_EXP_LNKCTL, &tmp16);
@@ -2003,9 +2003,9 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gmc_v7_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &cik_ih_ip_block);
 		if (amdgpu_dpm == -1)
-			amdgpu_device_ip_block_add(adev, &ci_smu_ip_block);
-		else
 			amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
+		else
+			amdgpu_device_ip_block_add(adev, &ci_smu_ip_block);
 		if (adev->enable_virtual_display)
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
@@ -2024,9 +2024,9 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gmc_v7_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &cik_ih_ip_block);
 		if (amdgpu_dpm == -1)
-			amdgpu_device_ip_block_add(adev, &ci_smu_ip_block);
-		else
 			amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
+		else
+			amdgpu_device_ip_block_add(adev, &ci_smu_ip_block);
 		if (adev->enable_virtual_display)
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index a7576255cc30..d0fa2aac2388 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -54,16 +54,16 @@ static void cik_sdma_set_buffer_funcs(struct amdgpu_device *adev);
 static void cik_sdma_set_vm_pte_funcs(struct amdgpu_device *adev);
 static int cik_sdma_soft_reset(void *handle);
 
-MODULE_FIRMWARE("radeon/bonaire_sdma.bin");
-MODULE_FIRMWARE("radeon/bonaire_sdma1.bin");
-MODULE_FIRMWARE("radeon/hawaii_sdma.bin");
-MODULE_FIRMWARE("radeon/hawaii_sdma1.bin");
-MODULE_FIRMWARE("radeon/kaveri_sdma.bin");
-MODULE_FIRMWARE("radeon/kaveri_sdma1.bin");
-MODULE_FIRMWARE("radeon/kabini_sdma.bin");
-MODULE_FIRMWARE("radeon/kabini_sdma1.bin");
-MODULE_FIRMWARE("radeon/mullins_sdma.bin");
-MODULE_FIRMWARE("radeon/mullins_sdma1.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_sdma.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_sdma1.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_sdma.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_sdma1.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_sdma.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_sdma1.bin");
+MODULE_FIRMWARE("amdgpu/kabini_sdma.bin");
+MODULE_FIRMWARE("amdgpu/kabini_sdma1.bin");
+MODULE_FIRMWARE("amdgpu/mullins_sdma.bin");
+MODULE_FIRMWARE("amdgpu/mullins_sdma1.bin");
 
 u32 amdgpu_cik_gpu_check_soft_reset(struct amdgpu_device *adev);
 
@@ -132,9 +132,9 @@ static int cik_sdma_init_microcode(struct amdgpu_device *adev)
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		if (i == 0)
-			snprintf(fw_name, sizeof(fw_name), "radeon/%s_sdma.bin", chip_name);
+			snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma.bin", chip_name);
 		else
-			snprintf(fw_name, sizeof(fw_name), "radeon/%s_sdma1.bin", chip_name);
+			snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma1.bin", chip_name);
 		err = request_firmware(&adev->sdma.instance[i].fw, fw_name, adev->dev);
 		if (err)
 			goto out;
@@ -177,9 +177,8 @@ static uint64_t cik_sdma_ring_get_rptr(struct amdgpu_ring *ring)
 static uint64_t cik_sdma_ring_get_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	u32 me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
 
-	return (RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me]) & 0x3fffc) >> 2;
+	return (RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[ring->me]) & 0x3fffc) >> 2;
 }
 
 /**
@@ -192,9 +191,8 @@ static uint64_t cik_sdma_ring_get_wptr(struct amdgpu_ring *ring)
 static void cik_sdma_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	u32 me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
 
-	WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me],
+	WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[ring->me],
 		       	(lower_32_bits(ring->wptr) << 2) & 0x3fffc);
 }
 
@@ -248,7 +246,7 @@ static void cik_sdma_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 			  SDMA_POLL_REG_MEM_EXTRA_FUNC(3)); /* == */
 	u32 ref_and_mask;
 
-	if (ring == &ring->adev->sdma.instance[0].ring)
+	if (ring->me == 0)
 		ref_and_mask = GPU_HDP_FLUSH_DONE__SDMA0_MASK;
 	else
 		ref_and_mask = GPU_HDP_FLUSH_DONE__SDMA1_MASK;
@@ -1290,8 +1288,10 @@ static void cik_sdma_set_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->sdma.num_instances; i++)
+	for (i = 0; i < adev->sdma.num_instances; i++) {
 		adev->sdma.instance[i].ring.funcs = &cik_sdma_ring_funcs;
+		adev->sdma.instance[i].ring.me = i;
+	}
 }
 
 static const struct amdgpu_irq_src_funcs cik_sdma_trap_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index ada241bfeee9..308f9f238bc1 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -41,6 +41,8 @@
 #include "gmc/gmc_8_1_d.h"
 #include "gmc/gmc_8_1_sh_mask.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 static void dce_v10_0_set_display_funcs(struct amdgpu_device *adev);
 static void dce_v10_0_set_irq_funcs(struct amdgpu_device *adev);
 
@@ -1855,15 +1857,14 @@ static int dce_v10_0_crtc_do_set_base(struct drm_crtc *crtc,
 	if (unlikely(r != 0))
 		return r;
 
-	if (atomic) {
-		fb_location = amdgpu_bo_gpu_offset(abo);
-	} else {
-		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM, &fb_location);
+	if (!atomic) {
+		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM);
 		if (unlikely(r != 0)) {
 			amdgpu_bo_unreserve(abo);
 			return -EINVAL;
 		}
 	}
+	fb_location = amdgpu_bo_gpu_offset(abo);
 
 	amdgpu_bo_get_tiling_flags(abo, &tiling_flags);
 	amdgpu_bo_unreserve(abo);
@@ -2370,13 +2371,14 @@ static int dce_v10_0_crtc_cursor_set2(struct drm_crtc *crtc,
 		return ret;
 	}
 
-	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM, &amdgpu_crtc->cursor_addr);
+	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
 	amdgpu_bo_unreserve(aobj);
 	if (ret) {
 		DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret);
 		drm_gem_object_put_unlocked(obj);
 		return ret;
 	}
+	amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
 
 	dce_v10_0_lock_cursor(crtc, true);
 
@@ -2737,14 +2739,14 @@ static int dce_v10_0_sw_init(void *handle)
 			return r;
 	}
 
-	for (i = 8; i < 20; i += 2) {
+	for (i = VISLANDS30_IV_SRCID_D1_GRPH_PFLIP; i < 20; i += 2) {
 		r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, i, &adev->pageflip_irq);
 		if (r)
 			return r;
 	}
 
 	/* HPD hotplug */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 42, &adev->hpd_irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_HOTPLUG_DETECT_A, &adev->hpd_irq);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index a5b96eac3033..76dfb76f7900 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -41,6 +41,8 @@
 #include "gmc/gmc_8_1_d.h"
 #include "gmc/gmc_8_1_sh_mask.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 static void dce_v11_0_set_display_funcs(struct amdgpu_device *adev);
 static void dce_v11_0_set_irq_funcs(struct amdgpu_device *adev);
 
@@ -1897,15 +1899,14 @@ static int dce_v11_0_crtc_do_set_base(struct drm_crtc *crtc,
 	if (unlikely(r != 0))
 		return r;
 
-	if (atomic) {
-		fb_location = amdgpu_bo_gpu_offset(abo);
-	} else {
-		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM, &fb_location);
+	if (!atomic) {
+		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM);
 		if (unlikely(r != 0)) {
 			amdgpu_bo_unreserve(abo);
 			return -EINVAL;
 		}
 	}
+	fb_location = amdgpu_bo_gpu_offset(abo);
 
 	amdgpu_bo_get_tiling_flags(abo, &tiling_flags);
 	amdgpu_bo_unreserve(abo);
@@ -2449,13 +2450,14 @@ static int dce_v11_0_crtc_cursor_set2(struct drm_crtc *crtc,
 		return ret;
 	}
 
-	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM, &amdgpu_crtc->cursor_addr);
+	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
 	amdgpu_bo_unreserve(aobj);
 	if (ret) {
 		DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret);
 		drm_gem_object_put_unlocked(obj);
 		return ret;
 	}
+	amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
 
 	dce_v11_0_lock_cursor(crtc, true);
 
@@ -2858,14 +2860,14 @@ static int dce_v11_0_sw_init(void *handle)
 			return r;
 	}
 
-	for (i = 8; i < 20; i += 2) {
+	for (i = VISLANDS30_IV_SRCID_D1_GRPH_PFLIP; i < 20; i += 2) {
 		r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, i, &adev->pageflip_irq);
 		if (r)
 			return r;
 	}
 
 	/* HPD hotplug */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 42, &adev->hpd_irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_HOTPLUG_DETECT_A, &adev->hpd_irq);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index 394cc1e8fe20..c9adc627305d 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -1811,15 +1811,14 @@ static int dce_v6_0_crtc_do_set_base(struct drm_crtc *crtc,
 	if (unlikely(r != 0))
 		return r;
 
-	if (atomic) {
-		fb_location = amdgpu_bo_gpu_offset(abo);
-	} else {
-		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM, &fb_location);
+	if (!atomic) {
+		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM);
 		if (unlikely(r != 0)) {
 			amdgpu_bo_unreserve(abo);
 			return -EINVAL;
 		}
 	}
+	fb_location = amdgpu_bo_gpu_offset(abo);
 
 	amdgpu_bo_get_tiling_flags(abo, &tiling_flags);
 	amdgpu_bo_unreserve(abo);
@@ -2263,13 +2262,14 @@ static int dce_v6_0_crtc_cursor_set2(struct drm_crtc *crtc,
 		return ret;
 	}
 
-	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM, &amdgpu_crtc->cursor_addr);
+	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
 	amdgpu_bo_unreserve(aobj);
 	if (ret) {
 		DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret);
 		drm_gem_object_put_unlocked(obj);
 		return ret;
 	}
+	amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
 
 	dce_v6_0_lock_cursor(crtc, true);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index c9b9ab8f1b05..50cd03beac7d 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -1786,15 +1786,14 @@ static int dce_v8_0_crtc_do_set_base(struct drm_crtc *crtc,
 	if (unlikely(r != 0))
 		return r;
 
-	if (atomic) {
-		fb_location = amdgpu_bo_gpu_offset(abo);
-	} else {
-		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM, &fb_location);
+	if (!atomic) {
+		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM);
 		if (unlikely(r != 0)) {
 			amdgpu_bo_unreserve(abo);
 			return -EINVAL;
 		}
 	}
+	fb_location = amdgpu_bo_gpu_offset(abo);
 
 	amdgpu_bo_get_tiling_flags(abo, &tiling_flags);
 	amdgpu_bo_unreserve(abo);
@@ -2274,13 +2273,14 @@ static int dce_v8_0_crtc_cursor_set2(struct drm_crtc *crtc,
 		return ret;
 	}
 
-	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM, &amdgpu_crtc->cursor_addr);
+	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
 	amdgpu_bo_unreserve(aobj);
 	if (ret) {
 		DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret);
 		drm_gem_object_put_unlocked(obj);
 		return ret;
 	}
+	amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
 
 	dce_v8_0_lock_cursor(crtc, true);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
index dbf2ccd0c744..15257634a53a 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
@@ -36,6 +36,7 @@
 #include "dce_v10_0.h"
 #include "dce_v11_0.h"
 #include "dce_virtual.h"
+#include "ivsrcid/ivsrcid_vislands30.h"
 
 #define DCE_VIRTUAL_VBLANK_PERIOD 16666666
 
@@ -269,25 +270,18 @@ static int dce_virtual_early_init(void *handle)
 static struct drm_encoder *
 dce_virtual_encoder(struct drm_connector *connector)
 {
-	int enc_id = connector->encoder_ids[0];
 	struct drm_encoder *encoder;
 	int i;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if (encoder->encoder_type == DRM_MODE_ENCODER_VIRTUAL)
 			return encoder;
 	}
 
 	/* pick the first one */
-	if (enc_id)
-		return drm_encoder_find(connector->dev, NULL, enc_id);
+	drm_connector_for_each_possible_encoder(connector, encoder, i)
+		return encoder;
+
 	return NULL;
 }
 
@@ -378,7 +372,7 @@ static int dce_virtual_sw_init(void *handle)
 	int r, i;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 229, &adev->crtc_irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SMU_DISP_TIMER2_TRIGGER, &adev->crtc_irq);
 	if (r)
 		return r;
 
@@ -634,7 +628,7 @@ static int dce_virtual_connector_encoder_init(struct amdgpu_device *adev,
 	drm_connector_register(connector);
 
 	/* link them */
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index cd6bf291a853..de184a886057 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -44,30 +44,30 @@ static void gfx_v6_0_set_ring_funcs(struct amdgpu_device *adev);
 static void gfx_v6_0_set_irq_funcs(struct amdgpu_device *adev);
 static void gfx_v6_0_get_cu_info(struct amdgpu_device *adev);
 
-MODULE_FIRMWARE("radeon/tahiti_pfp.bin");
-MODULE_FIRMWARE("radeon/tahiti_me.bin");
-MODULE_FIRMWARE("radeon/tahiti_ce.bin");
-MODULE_FIRMWARE("radeon/tahiti_rlc.bin");
-
-MODULE_FIRMWARE("radeon/pitcairn_pfp.bin");
-MODULE_FIRMWARE("radeon/pitcairn_me.bin");
-MODULE_FIRMWARE("radeon/pitcairn_ce.bin");
-MODULE_FIRMWARE("radeon/pitcairn_rlc.bin");
-
-MODULE_FIRMWARE("radeon/verde_pfp.bin");
-MODULE_FIRMWARE("radeon/verde_me.bin");
-MODULE_FIRMWARE("radeon/verde_ce.bin");
-MODULE_FIRMWARE("radeon/verde_rlc.bin");
-
-MODULE_FIRMWARE("radeon/oland_pfp.bin");
-MODULE_FIRMWARE("radeon/oland_me.bin");
-MODULE_FIRMWARE("radeon/oland_ce.bin");
-MODULE_FIRMWARE("radeon/oland_rlc.bin");
-
-MODULE_FIRMWARE("radeon/hainan_pfp.bin");
-MODULE_FIRMWARE("radeon/hainan_me.bin");
-MODULE_FIRMWARE("radeon/hainan_ce.bin");
-MODULE_FIRMWARE("radeon/hainan_rlc.bin");
+MODULE_FIRMWARE("amdgpu/tahiti_pfp.bin");
+MODULE_FIRMWARE("amdgpu/tahiti_me.bin");
+MODULE_FIRMWARE("amdgpu/tahiti_ce.bin");
+MODULE_FIRMWARE("amdgpu/tahiti_rlc.bin");
+
+MODULE_FIRMWARE("amdgpu/pitcairn_pfp.bin");
+MODULE_FIRMWARE("amdgpu/pitcairn_me.bin");
+MODULE_FIRMWARE("amdgpu/pitcairn_ce.bin");
+MODULE_FIRMWARE("amdgpu/pitcairn_rlc.bin");
+
+MODULE_FIRMWARE("amdgpu/verde_pfp.bin");
+MODULE_FIRMWARE("amdgpu/verde_me.bin");
+MODULE_FIRMWARE("amdgpu/verde_ce.bin");
+MODULE_FIRMWARE("amdgpu/verde_rlc.bin");
+
+MODULE_FIRMWARE("amdgpu/oland_pfp.bin");
+MODULE_FIRMWARE("amdgpu/oland_me.bin");
+MODULE_FIRMWARE("amdgpu/oland_ce.bin");
+MODULE_FIRMWARE("amdgpu/oland_rlc.bin");
+
+MODULE_FIRMWARE("amdgpu/hainan_pfp.bin");
+MODULE_FIRMWARE("amdgpu/hainan_me.bin");
+MODULE_FIRMWARE("amdgpu/hainan_ce.bin");
+MODULE_FIRMWARE("amdgpu/hainan_rlc.bin");
 
 static u32 gfx_v6_0_get_csb_size(struct amdgpu_device *adev);
 static void gfx_v6_0_get_csb_buffer(struct amdgpu_device *adev, volatile u32 *buffer);
@@ -335,7 +335,7 @@ static int gfx_v6_0_init_microcode(struct amdgpu_device *adev)
 	default: BUG();
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_pfp.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", chip_name);
 	err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -346,7 +346,7 @@ static int gfx_v6_0_init_microcode(struct amdgpu_device *adev)
 	adev->gfx.pfp_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
 	adev->gfx.pfp_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_me.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name);
 	err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -357,7 +357,7 @@ static int gfx_v6_0_init_microcode(struct amdgpu_device *adev)
 	adev->gfx.me_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
 	adev->gfx.me_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_ce.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name);
 	err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -368,7 +368,7 @@ static int gfx_v6_0_init_microcode(struct amdgpu_device *adev)
 	adev->gfx.ce_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
 	adev->gfx.ce_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_rlc.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name);
 	err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 42b6144c1fd5..95452c5a9df6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -57,36 +57,36 @@ static void gfx_v7_0_set_ring_funcs(struct amdgpu_device *adev);
 static void gfx_v7_0_set_irq_funcs(struct amdgpu_device *adev);
 static void gfx_v7_0_set_gds_init(struct amdgpu_device *adev);
 
-MODULE_FIRMWARE("radeon/bonaire_pfp.bin");
-MODULE_FIRMWARE("radeon/bonaire_me.bin");
-MODULE_FIRMWARE("radeon/bonaire_ce.bin");
-MODULE_FIRMWARE("radeon/bonaire_rlc.bin");
-MODULE_FIRMWARE("radeon/bonaire_mec.bin");
-
-MODULE_FIRMWARE("radeon/hawaii_pfp.bin");
-MODULE_FIRMWARE("radeon/hawaii_me.bin");
-MODULE_FIRMWARE("radeon/hawaii_ce.bin");
-MODULE_FIRMWARE("radeon/hawaii_rlc.bin");
-MODULE_FIRMWARE("radeon/hawaii_mec.bin");
-
-MODULE_FIRMWARE("radeon/kaveri_pfp.bin");
-MODULE_FIRMWARE("radeon/kaveri_me.bin");
-MODULE_FIRMWARE("radeon/kaveri_ce.bin");
-MODULE_FIRMWARE("radeon/kaveri_rlc.bin");
-MODULE_FIRMWARE("radeon/kaveri_mec.bin");
-MODULE_FIRMWARE("radeon/kaveri_mec2.bin");
-
-MODULE_FIRMWARE("radeon/kabini_pfp.bin");
-MODULE_FIRMWARE("radeon/kabini_me.bin");
-MODULE_FIRMWARE("radeon/kabini_ce.bin");
-MODULE_FIRMWARE("radeon/kabini_rlc.bin");
-MODULE_FIRMWARE("radeon/kabini_mec.bin");
-
-MODULE_FIRMWARE("radeon/mullins_pfp.bin");
-MODULE_FIRMWARE("radeon/mullins_me.bin");
-MODULE_FIRMWARE("radeon/mullins_ce.bin");
-MODULE_FIRMWARE("radeon/mullins_rlc.bin");
-MODULE_FIRMWARE("radeon/mullins_mec.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_pfp.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_me.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_ce.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_rlc.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_mec.bin");
+
+MODULE_FIRMWARE("amdgpu/hawaii_pfp.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_me.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_ce.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_rlc.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_mec.bin");
+
+MODULE_FIRMWARE("amdgpu/kaveri_pfp.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_me.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_ce.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_rlc.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_mec.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_mec2.bin");
+
+MODULE_FIRMWARE("amdgpu/kabini_pfp.bin");
+MODULE_FIRMWARE("amdgpu/kabini_me.bin");
+MODULE_FIRMWARE("amdgpu/kabini_ce.bin");
+MODULE_FIRMWARE("amdgpu/kabini_rlc.bin");
+MODULE_FIRMWARE("amdgpu/kabini_mec.bin");
+
+MODULE_FIRMWARE("amdgpu/mullins_pfp.bin");
+MODULE_FIRMWARE("amdgpu/mullins_me.bin");
+MODULE_FIRMWARE("amdgpu/mullins_ce.bin");
+MODULE_FIRMWARE("amdgpu/mullins_rlc.bin");
+MODULE_FIRMWARE("amdgpu/mullins_mec.bin");
 
 static const struct amdgpu_gds_reg_offset amdgpu_gds_reg_offset[] =
 {
@@ -925,7 +925,7 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev)
 	default: BUG();
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_pfp.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", chip_name);
 	err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -933,7 +933,7 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev)
 	if (err)
 		goto out;
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_me.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name);
 	err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -941,7 +941,7 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev)
 	if (err)
 		goto out;
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_ce.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name);
 	err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -949,7 +949,7 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev)
 	if (err)
 		goto out;
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_mec.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", chip_name);
 	err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -958,7 +958,7 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev)
 		goto out;
 
 	if (adev->asic_type == CHIP_KAVERI) {
-		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mec2.bin", chip_name);
+		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name);
 		err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev);
 		if (err)
 			goto out;
@@ -967,7 +967,7 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev)
 			goto out;
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_rlc.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name);
 	err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 818874b13c99..5cd45210113f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -51,6 +51,8 @@
 
 #include "smu/smu_7_1_3_d.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 #define GFX8_NUM_GFX_RINGS     1
 #define GFX8_MEC_HPD_SIZE 2048
 
@@ -704,6 +706,17 @@ static const u32 stoney_mgcg_cgcg_init[] =
 	mmCGTS_SM_CTRL_REG, 0xffffffff, 0x96940200,
 };
 
+
+static const char * const sq_edc_source_names[] = {
+	"SQ_EDC_INFO_SOURCE_INVALID: No EDC error has occurred",
+	"SQ_EDC_INFO_SOURCE_INST: EDC source is Instruction Fetch",
+	"SQ_EDC_INFO_SOURCE_SGPR: EDC source is SGPR or SQC data return",
+	"SQ_EDC_INFO_SOURCE_VGPR: EDC source is VGPR",
+	"SQ_EDC_INFO_SOURCE_LDS: EDC source is LDS",
+	"SQ_EDC_INFO_SOURCE_GDS: EDC source is GDS",
+	"SQ_EDC_INFO_SOURCE_TA: EDC source is TA",
+};
+
 static void gfx_v8_0_set_ring_funcs(struct amdgpu_device *adev);
 static void gfx_v8_0_set_irq_funcs(struct amdgpu_device *adev);
 static void gfx_v8_0_set_gds_init(struct amdgpu_device *adev);
@@ -866,26 +879,32 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_ib ib;
 	struct dma_fence *f = NULL;
-	uint32_t scratch;
-	uint32_t tmp = 0;
+
+	unsigned int index;
+	uint64_t gpu_addr;
+	uint32_t tmp;
 	long r;
 
-	r = amdgpu_gfx_scratch_get(adev, &scratch);
+	r = amdgpu_device_wb_get(adev, &index);
 	if (r) {
-		DRM_ERROR("amdgpu: failed to get scratch reg (%ld).\n", r);
+		dev_err(adev->dev, "(%ld) failed to allocate wb slot\n", r);
 		return r;
 	}
-	WREG32(scratch, 0xCAFEDEAD);
+
+	gpu_addr = adev->wb.gpu_addr + (index * 4);
+	adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD);
 	memset(&ib, 0, sizeof(ib));
-	r = amdgpu_ib_get(adev, NULL, 256, &ib);
+	r = amdgpu_ib_get(adev, NULL, 16, &ib);
 	if (r) {
 		DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r);
 		goto err1;
 	}
-	ib.ptr[0] = PACKET3(PACKET3_SET_UCONFIG_REG, 1);
-	ib.ptr[1] = ((scratch - PACKET3_SET_UCONFIG_REG_START));
-	ib.ptr[2] = 0xDEADBEEF;
-	ib.length_dw = 3;
+	ib.ptr[0] = PACKET3(PACKET3_WRITE_DATA, 3);
+	ib.ptr[1] = WRITE_DATA_DST_SEL(5) | WR_CONFIRM;
+	ib.ptr[2] = lower_32_bits(gpu_addr);
+	ib.ptr[3] = upper_32_bits(gpu_addr);
+	ib.ptr[4] = 0xDEADBEEF;
+	ib.length_dw = 5;
 
 	r = amdgpu_ib_schedule(ring, 1, &ib, NULL, &f);
 	if (r)
@@ -900,20 +919,21 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
 		goto err2;
 	}
-	tmp = RREG32(scratch);
+
+	tmp = adev->wb.wb[index];
 	if (tmp == 0xDEADBEEF) {
 		DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
 		r = 0;
 	} else {
-		DRM_ERROR("amdgpu: ib test failed (scratch(0x%04X)=0x%08X)\n",
-			  scratch, tmp);
+		DRM_ERROR("ib test on ring %d failed\n", ring->idx);
 		r = -EINVAL;
 	}
+
 err2:
 	amdgpu_ib_free(adev, &ib, NULL);
 	dma_fence_put(f);
 err1:
-	amdgpu_gfx_scratch_free(adev, scratch);
+	amdgpu_device_wb_free(adev, index);
 	return r;
 }
 
@@ -1999,6 +2019,8 @@ static int gfx_v8_0_compute_ring_init(struct amdgpu_device *adev, int ring_id,
 	return 0;
 }
 
+static void gfx_v8_0_sq_irq_work_func(struct work_struct *work);
+
 static int gfx_v8_0_sw_init(void *handle)
 {
 	int i, j, k, r, ring_id;
@@ -2027,27 +2049,43 @@ static int gfx_v8_0_sw_init(void *handle)
 	adev->gfx.mec.num_queue_per_pipe = 8;
 
 	/* KIQ event */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 178, &adev->gfx.kiq.irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_CP_INT_IB2, &adev->gfx.kiq.irq);
 	if (r)
 		return r;
 
 	/* EOP Event */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 181, &adev->gfx.eop_irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_CP_END_OF_PIPE, &adev->gfx.eop_irq);
 	if (r)
 		return r;
 
 	/* Privileged reg */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 184,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_CP_PRIV_REG_FAULT,
 			      &adev->gfx.priv_reg_irq);
 	if (r)
 		return r;
 
 	/* Privileged inst */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 185,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_CP_PRIV_INSTR_FAULT,
 			      &adev->gfx.priv_inst_irq);
 	if (r)
 		return r;
 
+	/* Add CP EDC/ECC irq  */
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_CP_ECC_ERROR,
+			      &adev->gfx.cp_ecc_error_irq);
+	if (r)
+		return r;
+
+	/* SQ interrupts. */
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SQ_INTERRUPT_MSG,
+			      &adev->gfx.sq_irq);
+	if (r) {
+		DRM_ERROR("amdgpu_irq_add() for SQ failed: %d\n", r);
+		return r;
+	}
+
+	INIT_WORK(&adev->gfx.sq_work.work, gfx_v8_0_sq_irq_work_func);
+
 	adev->gfx.gfx_current_status = AMDGPU_GFX_NORMAL_MODE;
 
 	gfx_v8_0_scratch_init(adev);
@@ -5111,6 +5149,10 @@ static int gfx_v8_0_hw_fini(void *handle)
 	amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0);
 
+	amdgpu_irq_put(adev, &adev->gfx.cp_ecc_error_irq, 0);
+
+	amdgpu_irq_put(adev, &adev->gfx.sq_irq, 0);
+
 	/* disable KCQ to avoid CPC touch memory not valid anymore */
 	for (i = 0; i < adev->gfx.num_compute_rings; i++)
 		gfx_v8_0_kcq_disable(&adev->gfx.kiq.ring, &adev->gfx.compute_ring[i]);
@@ -5542,9 +5584,19 @@ static int gfx_v8_0_late_init(void *handle)
 	if (r)
 		return r;
 
-	amdgpu_device_ip_set_powergating_state(adev,
-					       AMD_IP_BLOCK_TYPE_GFX,
-					       AMD_PG_STATE_GATE);
+	r = amdgpu_irq_get(adev, &adev->gfx.cp_ecc_error_irq, 0);
+	if (r) {
+		DRM_ERROR("amdgpu_irq_get() failed to get IRQ for EDC, r: %d.\n", r);
+		return r;
+	}
+
+	r = amdgpu_irq_get(adev, &adev->gfx.sq_irq, 0);
+	if (r) {
+		DRM_ERROR(
+			"amdgpu_irq_get() failed to get IRQ for SQ, r: %d.\n",
+			r);
+		return r;
+	}
 
 	return 0;
 }
@@ -5552,14 +5604,12 @@ static int gfx_v8_0_late_init(void *handle)
 static void gfx_v8_0_enable_gfx_static_mg_power_gating(struct amdgpu_device *adev,
 						       bool enable)
 {
-	if ((adev->asic_type == CHIP_POLARIS11) ||
+	if (((adev->asic_type == CHIP_POLARIS11) ||
 	    (adev->asic_type == CHIP_POLARIS12) ||
-	    (adev->asic_type == CHIP_VEGAM))
+	    (adev->asic_type == CHIP_VEGAM)) &&
+	    adev->powerplay.pp_funcs->set_powergating_by_smu)
 		/* Send msg to SMU via Powerplay */
-		amdgpu_device_ip_set_powergating_state(adev,
-						       AMD_IP_BLOCK_TYPE_SMC,
-						       enable ?
-						       AMD_PG_STATE_GATE : AMD_PG_STATE_UNGATE);
+		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, enable);
 
 	WREG32_FIELD(RLC_PG_CNTL, STATIC_PER_CU_PG_ENABLE, enable ? 1 : 0);
 }
@@ -6787,6 +6837,77 @@ static int gfx_v8_0_set_eop_interrupt_state(struct amdgpu_device *adev,
 	return 0;
 }
 
+static int gfx_v8_0_set_cp_ecc_int_state(struct amdgpu_device *adev,
+					 struct amdgpu_irq_src *source,
+					 unsigned int type,
+					 enum amdgpu_interrupt_state state)
+{
+	int enable_flag;
+
+	switch (state) {
+	case AMDGPU_IRQ_STATE_DISABLE:
+		enable_flag = 0;
+		break;
+
+	case AMDGPU_IRQ_STATE_ENABLE:
+		enable_flag = 1;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	WREG32_FIELD(CP_INT_CNTL, CP_ECC_ERROR_INT_ENABLE, enable_flag);
+	WREG32_FIELD(CP_INT_CNTL_RING0, CP_ECC_ERROR_INT_ENABLE, enable_flag);
+	WREG32_FIELD(CP_INT_CNTL_RING1, CP_ECC_ERROR_INT_ENABLE, enable_flag);
+	WREG32_FIELD(CP_INT_CNTL_RING2, CP_ECC_ERROR_INT_ENABLE, enable_flag);
+	WREG32_FIELD(CPC_INT_CNTL, CP_ECC_ERROR_INT_ENABLE, enable_flag);
+	WREG32_FIELD(CP_ME1_PIPE0_INT_CNTL, CP_ECC_ERROR_INT_ENABLE,
+		     enable_flag);
+	WREG32_FIELD(CP_ME1_PIPE1_INT_CNTL, CP_ECC_ERROR_INT_ENABLE,
+		     enable_flag);
+	WREG32_FIELD(CP_ME1_PIPE2_INT_CNTL, CP_ECC_ERROR_INT_ENABLE,
+		     enable_flag);
+	WREG32_FIELD(CP_ME1_PIPE3_INT_CNTL, CP_ECC_ERROR_INT_ENABLE,
+		     enable_flag);
+	WREG32_FIELD(CP_ME2_PIPE0_INT_CNTL, CP_ECC_ERROR_INT_ENABLE,
+		     enable_flag);
+	WREG32_FIELD(CP_ME2_PIPE1_INT_CNTL, CP_ECC_ERROR_INT_ENABLE,
+		     enable_flag);
+	WREG32_FIELD(CP_ME2_PIPE2_INT_CNTL, CP_ECC_ERROR_INT_ENABLE,
+		     enable_flag);
+	WREG32_FIELD(CP_ME2_PIPE3_INT_CNTL, CP_ECC_ERROR_INT_ENABLE,
+		     enable_flag);
+
+	return 0;
+}
+
+static int gfx_v8_0_set_sq_int_state(struct amdgpu_device *adev,
+				     struct amdgpu_irq_src *source,
+				     unsigned int type,
+				     enum amdgpu_interrupt_state state)
+{
+	int enable_flag;
+
+	switch (state) {
+	case AMDGPU_IRQ_STATE_DISABLE:
+		enable_flag = 1;
+		break;
+
+	case AMDGPU_IRQ_STATE_ENABLE:
+		enable_flag = 0;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	WREG32_FIELD(SQ_INTERRUPT_MSG_CTRL, STALL,
+		     enable_flag);
+
+	return 0;
+}
+
 static int gfx_v8_0_eop_irq(struct amdgpu_device *adev,
 			    struct amdgpu_irq_src *source,
 			    struct amdgpu_iv_entry *entry)
@@ -6837,6 +6958,114 @@ static int gfx_v8_0_priv_inst_irq(struct amdgpu_device *adev,
 	return 0;
 }
 
+static int gfx_v8_0_cp_ecc_error_irq(struct amdgpu_device *adev,
+				     struct amdgpu_irq_src *source,
+				     struct amdgpu_iv_entry *entry)
+{
+	DRM_ERROR("CP EDC/ECC error detected.");
+	return 0;
+}
+
+static void gfx_v8_0_parse_sq_irq(struct amdgpu_device *adev, unsigned ih_data)
+{
+	u32 enc, se_id, sh_id, cu_id;
+	char type[20];
+	int sq_edc_source = -1;
+
+	enc = REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_CMN, ENCODING);
+	se_id = REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_CMN, SE_ID);
+
+	switch (enc) {
+		case 0:
+			DRM_INFO("SQ general purpose intr detected:"
+					"se_id %d, immed_overflow %d, host_reg_overflow %d,"
+					"host_cmd_overflow %d, cmd_timestamp %d,"
+					"reg_timestamp %d, thread_trace_buff_full %d,"
+					"wlt %d, thread_trace %d.\n",
+					se_id,
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, IMMED_OVERFLOW),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, HOST_REG_OVERFLOW),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, HOST_CMD_OVERFLOW),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, CMD_TIMESTAMP),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, REG_TIMESTAMP),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, THREAD_TRACE_BUF_FULL),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, WLT),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, THREAD_TRACE)
+					);
+			break;
+		case 1:
+		case 2:
+
+			cu_id = REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, CU_ID);
+			sh_id = REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, SH_ID);
+
+			/*
+			 * This function can be called either directly from ISR
+			 * or from BH in which case we can access SQ_EDC_INFO
+			 * instance
+			 */
+			if (in_task()) {
+				mutex_lock(&adev->grbm_idx_mutex);
+				gfx_v8_0_select_se_sh(adev, se_id, sh_id, cu_id);
+
+				sq_edc_source = REG_GET_FIELD(RREG32(mmSQ_EDC_INFO), SQ_EDC_INFO, SOURCE);
+
+				gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
+				mutex_unlock(&adev->grbm_idx_mutex);
+			}
+
+			if (enc == 1)
+				sprintf(type, "instruction intr");
+			else
+				sprintf(type, "EDC/ECC error");
+
+			DRM_INFO(
+				"SQ %s detected: "
+					"se_id %d, sh_id %d, cu_id %d, simd_id %d, wave_id %d, vm_id %d "
+					"trap %s, sq_ed_info.source %s.\n",
+					type, se_id, sh_id, cu_id,
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, SIMD_ID),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, WAVE_ID),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, VM_ID),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, PRIV) ? "true" : "false",
+					(sq_edc_source != -1) ? sq_edc_source_names[sq_edc_source] : "unavailable"
+				);
+			break;
+		default:
+			DRM_ERROR("SQ invalid encoding type\n.");
+	}
+}
+
+static void gfx_v8_0_sq_irq_work_func(struct work_struct *work)
+{
+
+	struct amdgpu_device *adev = container_of(work, struct amdgpu_device, gfx.sq_work.work);
+	struct sq_work *sq_work = container_of(work, struct sq_work, work);
+
+	gfx_v8_0_parse_sq_irq(adev, sq_work->ih_data);
+}
+
+static int gfx_v8_0_sq_irq(struct amdgpu_device *adev,
+			   struct amdgpu_irq_src *source,
+			   struct amdgpu_iv_entry *entry)
+{
+	unsigned ih_data = entry->src_data[0];
+
+	/*
+	 * Try to submit work so SQ_EDC_INFO can be accessed from
+	 * BH. If previous work submission hasn't finished yet
+	 * just print whatever info is possible directly from the ISR.
+	 */
+	if (work_pending(&adev->gfx.sq_work.work)) {
+		gfx_v8_0_parse_sq_irq(adev, ih_data);
+	} else {
+		adev->gfx.sq_work.ih_data = ih_data;
+		schedule_work(&adev->gfx.sq_work.work);
+	}
+
+	return 0;
+}
+
 static int gfx_v8_0_kiq_set_interrupt_state(struct amdgpu_device *adev,
 					    struct amdgpu_irq_src *src,
 					    unsigned int type,
@@ -7037,6 +7266,16 @@ static const struct amdgpu_irq_src_funcs gfx_v8_0_kiq_irq_funcs = {
 	.process = gfx_v8_0_kiq_irq,
 };
 
+static const struct amdgpu_irq_src_funcs gfx_v8_0_cp_ecc_error_irq_funcs = {
+	.set = gfx_v8_0_set_cp_ecc_int_state,
+	.process = gfx_v8_0_cp_ecc_error_irq,
+};
+
+static const struct amdgpu_irq_src_funcs gfx_v8_0_sq_irq_funcs = {
+	.set = gfx_v8_0_set_sq_int_state,
+	.process = gfx_v8_0_sq_irq,
+};
+
 static void gfx_v8_0_set_irq_funcs(struct amdgpu_device *adev)
 {
 	adev->gfx.eop_irq.num_types = AMDGPU_CP_IRQ_LAST;
@@ -7050,6 +7289,12 @@ static void gfx_v8_0_set_irq_funcs(struct amdgpu_device *adev)
 
 	adev->gfx.kiq.irq.num_types = AMDGPU_CP_KIQ_IRQ_LAST;
 	adev->gfx.kiq.irq.funcs = &gfx_v8_0_kiq_irq_funcs;
+
+	adev->gfx.cp_ecc_error_irq.num_types = 1;
+	adev->gfx.cp_ecc_error_irq.funcs = &gfx_v8_0_cp_ecc_error_irq_funcs;
+
+	adev->gfx.sq_irq.num_types = 1;
+	adev->gfx.sq_irq.funcs = &gfx_v8_0_sq_irq_funcs;
 }
 
 static void gfx_v8_0_set_rlc_funcs(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index a69153435ea7..ef00d14f8645 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -38,6 +38,8 @@
 #include "clearstate_gfx9.h"
 #include "v9_structs.h"
 
+#include "ivsrcid/gfx/irqsrcs_gfx_9_0.h"
+
 #define GFX9_NUM_GFX_RINGS     1
 #define GFX9_MEC_HPD_SIZE 2048
 #define RLCG_UCODE_LOADING_START_ADDRESS 0x00002000L
@@ -102,11 +104,22 @@ static const struct soc15_reg_golden golden_settings_gc_9_0_vg10[] =
 {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL, 0x0000f000, 0x00012107),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_3, 0x30000000, 0x10000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPC_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPF_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPG_UTCL1_CNTL, 0x08000000, 0x08000080),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0xffff77ff, 0x2a114042),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG_READ, 0xffff77ff, 0x2a114042),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmIA_UTCL1_CNTL, 0x08000000, 0x08000080),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_1, 0x00008000, 0x00048000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_GPM_UTCL1_CNTL_0, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_GPM_UTCL1_CNTL_1, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_GPM_UTCL1_CNTL_2, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_PREWALKER_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_SPM_UTCL1_CNTL, 0x08000000, 0x08000080),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRMI_UTCL1_CNTL2, 0x00030000, 0x00020000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTD_CNTL, 0x00001800, 0x00000800)
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1, 0x0000000f, 0x01000107),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTD_CNTL, 0x00001800, 0x00000800),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmWD_UTCL1_CNTL, 0x08000000, 0x08000080)
 };
 
 static const struct soc15_reg_golden golden_settings_gc_9_0_vg20[] =
@@ -648,7 +661,10 @@ static int gfx_v9_0_init_microcode(struct amdgpu_device *adev)
 		adev->firmware.fw_size +=
 			ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
 
-		if (adev->gfx.rlc.is_rlc_v2_1) {
+		if (adev->gfx.rlc.is_rlc_v2_1 &&
+		    adev->gfx.rlc.save_restore_list_cntl_size_bytes &&
+		    adev->gfx.rlc.save_restore_list_gpm_size_bytes &&
+		    adev->gfx.rlc.save_restore_list_srm_size_bytes) {
 			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL];
 			info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL;
 			info->fw = adev->gfx.rlc_fw;
@@ -943,6 +959,7 @@ static int gfx_v9_0_rlc_init(struct amdgpu_device *adev)
 		dst_ptr = adev->gfx.rlc.cs_ptr;
 		gfx_v9_0_get_csb_buffer(adev, dst_ptr);
 		amdgpu_bo_kunmap(adev->gfx.rlc.clear_state_obj);
+		amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj);
 		amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
 	}
 
@@ -971,6 +988,39 @@ static int gfx_v9_0_rlc_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+static int gfx_v9_0_csb_vram_pin(struct amdgpu_device *adev)
+{
+	int r;
+
+	r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false);
+	if (unlikely(r != 0))
+		return r;
+
+	r = amdgpu_bo_pin(adev->gfx.rlc.clear_state_obj,
+			AMDGPU_GEM_DOMAIN_VRAM);
+	if (!r)
+		adev->gfx.rlc.clear_state_gpu_addr =
+			amdgpu_bo_gpu_offset(adev->gfx.rlc.clear_state_obj);
+
+	amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
+
+	return r;
+}
+
+static void gfx_v9_0_csb_vram_unpin(struct amdgpu_device *adev)
+{
+	int r;
+
+	if (!adev->gfx.rlc.clear_state_obj)
+		return;
+
+	r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, true);
+	if (likely(r == 0)) {
+		amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj);
+		amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
+	}
+}
+
 static void gfx_v9_0_mec_fini(struct amdgpu_device *adev)
 {
 	amdgpu_bo_free_kernel(&adev->gfx.mec.hpd_eop_obj, NULL, NULL);
@@ -1451,23 +1501,23 @@ static int gfx_v9_0_sw_init(void *handle)
 	adev->gfx.mec.num_queue_per_pipe = 8;
 
 	/* KIQ event */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, 178, &adev->gfx.kiq.irq);
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, GFX_9_0__SRCID__CP_IB2_INTERRUPT_PKT, &adev->gfx.kiq.irq);
 	if (r)
 		return r;
 
 	/* EOP Event */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, 181, &adev->gfx.eop_irq);
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, GFX_9_0__SRCID__CP_EOP_INTERRUPT, &adev->gfx.eop_irq);
 	if (r)
 		return r;
 
 	/* Privileged reg */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, 184,
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, GFX_9_0__SRCID__CP_PRIV_REG_FAULT,
 			      &adev->gfx.priv_reg_irq);
 	if (r)
 		return r;
 
 	/* Privileged inst */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, 185,
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, GFX_9_0__SRCID__CP_PRIV_INSTR_FAULT,
 			      &adev->gfx.priv_inst_irq);
 	if (r)
 		return r;
@@ -2148,8 +2198,16 @@ static void gfx_v9_0_enable_gfx_dynamic_mg_power_gating(struct amdgpu_device *ad
 
 static void gfx_v9_0_init_pg(struct amdgpu_device *adev)
 {
-	if (!adev->gfx.rlc.is_rlc_v2_1)
-		return;
+	gfx_v9_0_init_csb(adev);
+
+	/*
+	 * Rlc save restore list is workable since v2_1.
+	 * And it's needed by gfxoff feature.
+	 */
+	if (adev->gfx.rlc.is_rlc_v2_1) {
+		gfx_v9_1_init_rlc_save_restore_list(adev);
+		gfx_v9_0_enable_save_restore_machine(adev);
+	}
 
 	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
 			      AMD_PG_SUPPORT_GFX_SMG |
@@ -2157,10 +2215,6 @@ static void gfx_v9_0_init_pg(struct amdgpu_device *adev)
 			      AMD_PG_SUPPORT_CP |
 			      AMD_PG_SUPPORT_GDS |
 			      AMD_PG_SUPPORT_RLC_SMU_HS)) {
-		gfx_v9_0_init_csb(adev);
-		gfx_v9_1_init_rlc_save_restore_list(adev);
-		gfx_v9_0_enable_save_restore_machine(adev);
-
 		WREG32(mmRLC_JUMP_TABLE_RESTORE,
 		       adev->gfx.rlc.cp_table_gpu_addr >> 8);
 		gfx_v9_0_init_gfx_power_gating(adev);
@@ -2252,9 +2306,6 @@ static int gfx_v9_0_rlc_resume(struct amdgpu_device *adev)
 	/* disable CG */
 	WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL, 0);
 
-	/* disable PG */
-	WREG32_SOC15(GC, 0, mmRLC_PG_CNTL, 0);
-
 	gfx_v9_0_rlc_reset(adev);
 
 	gfx_v9_0_init_pg(adev);
@@ -3116,6 +3167,10 @@ static int gfx_v9_0_hw_init(void *handle)
 
 	gfx_v9_0_gpu_init(adev);
 
+	r = gfx_v9_0_csb_vram_pin(adev);
+	if (r)
+		return r;
+
 	r = gfx_v9_0_rlc_resume(adev);
 	if (r)
 		return r;
@@ -3224,6 +3279,8 @@ static int gfx_v9_0_hw_fini(void *handle)
 	gfx_v9_0_cp_enable(adev, false);
 	gfx_v9_0_rlc_stop(adev);
 
+	gfx_v9_0_csb_vram_unpin(adev);
+
 	return 0;
 }
 
@@ -3433,7 +3490,7 @@ static void gfx_v9_0_enter_rlc_safe_mode(struct amdgpu_device *adev)
 
 		/* wait for RLC_SAFE_MODE */
 		for (i = 0; i < adev->usec_timeout; i++) {
-			if (!REG_GET_FIELD(SOC15_REG_OFFSET(GC, 0, mmRLC_SAFE_MODE), RLC_SAFE_MODE, CMD))
+			if (!REG_GET_FIELD(RREG32_SOC15(GC, 0, mmRLC_SAFE_MODE), RLC_SAFE_MODE, CMD))
 				break;
 			udelay(1);
 		}
@@ -3510,8 +3567,11 @@ static void gfx_v9_0_update_medium_grain_clock_gating(struct amdgpu_device *adev
 	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) {
 		/* 1 - RLC_CGTT_MGCG_OVERRIDE */
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE);
-		data &= ~(RLC_CGTT_MGCG_OVERRIDE__CPF_CGTT_SCLK_OVERRIDE_MASK |
-			  RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK |
+
+		if (adev->asic_type != CHIP_VEGA12)
+			data &= ~RLC_CGTT_MGCG_OVERRIDE__CPF_CGTT_SCLK_OVERRIDE_MASK;
+
+		data &= ~(RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK |
 			  RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE_MASK |
 			  RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK);
 
@@ -3541,11 +3601,15 @@ static void gfx_v9_0_update_medium_grain_clock_gating(struct amdgpu_device *adev
 	} else {
 		/* 1 - MGCG_OVERRIDE */
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE);
-		data |= (RLC_CGTT_MGCG_OVERRIDE__CPF_CGTT_SCLK_OVERRIDE_MASK |
-			 RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE_MASK |
+
+		if (adev->asic_type != CHIP_VEGA12)
+			data |= RLC_CGTT_MGCG_OVERRIDE__CPF_CGTT_SCLK_OVERRIDE_MASK;
+
+		data |= (RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE_MASK |
 			 RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK |
 			 RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE_MASK |
 			 RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK);
+
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data);
 
@@ -3581,9 +3645,11 @@ static void gfx_v9_0_update_3d_clock_gating(struct amdgpu_device *adev,
 		/* update CGCG and CGLS override bits */
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data);
-		/* enable 3Dcgcg FSM(0x0020003f) */
+
+		/* enable 3Dcgcg FSM(0x0000363f) */
 		def = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL_3D);
-		data = (0x2000 << RLC_CGCG_CGLS_CTRL_3D__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
+
+		data = (0x36 << RLC_CGCG_CGLS_CTRL_3D__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
 			RLC_CGCG_CGLS_CTRL_3D__CGCG_EN_MASK;
 		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGLS)
 			data |= (0x000F << RLC_CGCG_CGLS_CTRL_3D__CGLS_REP_COMPANSAT_DELAY__SHIFT) |
@@ -3630,9 +3696,10 @@ static void gfx_v9_0_update_coarse_grain_clock_gating(struct amdgpu_device *adev
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data);
 
-		/* enable cgcg FSM(0x0020003F) */
+		/* enable cgcg FSM(0x0000363F) */
 		def = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL);
-		data = (0x2000 << RLC_CGCG_CGLS_CTRL__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
+
+		data = (0x36 << RLC_CGCG_CGLS_CTRL__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
 			RLC_CGCG_CGLS_CTRL__CGCG_EN_MASK;
 		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGLS)
 			data |= (0x000F << RLC_CGCG_CGLS_CTRL__CGLS_REP_COMPANSAT_DELAY__SHIFT) |
@@ -3714,6 +3781,15 @@ static int gfx_v9_0_set_powergating_state(void *handle,
 
 		/* update mgcg state */
 		gfx_v9_0_update_gfx_mg_power_gating(adev, enable);
+
+		/* set gfx off through smu */
+		if (enable && adev->powerplay.pp_funcs->set_powergating_by_smu)
+			amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, true);
+		break;
+	case CHIP_VEGA12:
+		/* set gfx off through smu */
+		if (enable && adev->powerplay.pp_funcs->set_powergating_by_smu)
+			amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, true);
 		break;
 	default:
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 79f9ac29019b..75317f283c69 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -41,11 +41,11 @@ static void gmc_v6_0_set_gmc_funcs(struct amdgpu_device *adev);
 static void gmc_v6_0_set_irq_funcs(struct amdgpu_device *adev);
 static int gmc_v6_0_wait_for_idle(void *handle);
 
-MODULE_FIRMWARE("radeon/tahiti_mc.bin");
-MODULE_FIRMWARE("radeon/pitcairn_mc.bin");
-MODULE_FIRMWARE("radeon/verde_mc.bin");
-MODULE_FIRMWARE("radeon/oland_mc.bin");
-MODULE_FIRMWARE("radeon/si58_mc.bin");
+MODULE_FIRMWARE("amdgpu/tahiti_mc.bin");
+MODULE_FIRMWARE("amdgpu/pitcairn_mc.bin");
+MODULE_FIRMWARE("amdgpu/verde_mc.bin");
+MODULE_FIRMWARE("amdgpu/oland_mc.bin");
+MODULE_FIRMWARE("amdgpu/si58_mc.bin");
 
 #define MC_SEQ_MISC0__MT__MASK   0xf0000000
 #define MC_SEQ_MISC0__MT__GDDR1  0x10000000
@@ -134,9 +134,9 @@ static int gmc_v6_0_init_microcode(struct amdgpu_device *adev)
 		is_58_fw = true;
 
 	if (is_58_fw)
-		snprintf(fw_name, sizeof(fw_name), "radeon/si58_mc.bin");
+		snprintf(fw_name, sizeof(fw_name), "amdgpu/si58_mc.bin");
 	else
-		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
+		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mc.bin", chip_name);
 	err = request_firmware(&adev->gmc.fw, fw_name, adev->dev);
 	if (err)
 		goto out;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 7147bfe25a23..36dc367c4b45 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -28,6 +28,7 @@
 #include "cik.h"
 #include "gmc_v7_0.h"
 #include "amdgpu_ucode.h"
+#include "amdgpu_amdkfd.h"
 
 #include "bif/bif_4_1_d.h"
 #include "bif/bif_4_1_sh_mask.h"
@@ -43,12 +44,14 @@
 
 #include "amdgpu_atombios.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 static void gmc_v7_0_set_gmc_funcs(struct amdgpu_device *adev);
 static void gmc_v7_0_set_irq_funcs(struct amdgpu_device *adev);
 static int gmc_v7_0_wait_for_idle(void *handle);
 
-MODULE_FIRMWARE("radeon/bonaire_mc.bin");
-MODULE_FIRMWARE("radeon/hawaii_mc.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_mc.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_mc.bin");
 MODULE_FIRMWARE("amdgpu/topaz_mc.bin");
 
 static const u32 golden_settings_iceland_a11[] =
@@ -147,10 +150,7 @@ static int gmc_v7_0_init_microcode(struct amdgpu_device *adev)
 	default: BUG();
 	}
 
-	if (adev->asic_type == CHIP_TOPAZ)
-		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mc.bin", chip_name);
-	else
-		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mc.bin", chip_name);
 
 	err = request_firmware(&adev->gmc.fw, fw_name, adev->dev);
 	if (err)
@@ -999,11 +999,11 @@ static int gmc_v7_0_sw_init(void *handle)
 		adev->gmc.vram_type = gmc_v7_0_convert_vram_type(tmp);
 	}
 
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 146, &adev->gmc.vm_fault);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_GFX_PAGE_INV_FAULT, &adev->gmc.vm_fault);
 	if (r)
 		return r;
 
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 147, &adev->gmc.vm_fault);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_GFX_MEM_PROT_FAULT, &adev->gmc.vm_fault);
 	if (r)
 		return r;
 
@@ -1079,6 +1079,12 @@ static int gmc_v7_0_sw_init(void *handle)
 		adev->vm_manager.vram_base_offset = 0;
 	}
 
+	adev->gmc.vm_fault_info = kmalloc(sizeof(struct kfd_vm_fault_info),
+					GFP_KERNEL);
+	if (!adev->gmc.vm_fault_info)
+		return -ENOMEM;
+	atomic_set(&adev->gmc.vm_fault_info_updated, 0);
+
 	return 0;
 }
 
@@ -1088,6 +1094,7 @@ static int gmc_v7_0_sw_fini(void *handle)
 
 	amdgpu_gem_force_release(adev);
 	amdgpu_vm_manager_fini(adev);
+	kfree(adev->gmc.vm_fault_info);
 	gmc_v7_0_gart_fini(adev);
 	amdgpu_bo_fini(adev);
 	release_firmware(adev->gmc.fw);
@@ -1277,7 +1284,7 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_irq_src *source,
 				      struct amdgpu_iv_entry *entry)
 {
-	u32 addr, status, mc_client;
+	u32 addr, status, mc_client, vmid;
 
 	addr = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_ADDR);
 	status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS);
@@ -1302,6 +1309,29 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev,
 					 entry->pasid);
 	}
 
+	vmid = REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+			     VMID);
+	if (amdgpu_amdkfd_is_kfd_vmid(adev, vmid)
+		&& !atomic_read(&adev->gmc.vm_fault_info_updated)) {
+		struct kfd_vm_fault_info *info = adev->gmc.vm_fault_info;
+		u32 protections = REG_GET_FIELD(status,
+					VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					PROTECTIONS);
+
+		info->vmid = vmid;
+		info->mc_id = REG_GET_FIELD(status,
+					    VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					    MEMORY_CLIENT_ID);
+		info->status = status;
+		info->page_addr = addr;
+		info->prot_valid = protections & 0x7 ? true : false;
+		info->prot_read = protections & 0x8 ? true : false;
+		info->prot_write = protections & 0x10 ? true : false;
+		info->prot_exec = protections & 0x20 ? true : false;
+		mb();
+		atomic_set(&adev->gmc.vm_fault_info_updated, 1);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 1edbe6b477b5..70fc97b59b4f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -26,6 +26,7 @@
 #include "amdgpu.h"
 #include "gmc_v8_0.h"
 #include "amdgpu_ucode.h"
+#include "amdgpu_amdkfd.h"
 
 #include "gmc/gmc_8_1_d.h"
 #include "gmc/gmc_8_1_sh_mask.h"
@@ -44,6 +45,7 @@
 
 #include "amdgpu_atombios.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
 
 static void gmc_v8_0_set_gmc_funcs(struct amdgpu_device *adev);
 static void gmc_v8_0_set_irq_funcs(struct amdgpu_device *adev);
@@ -1101,11 +1103,11 @@ static int gmc_v8_0_sw_init(void *handle)
 		adev->gmc.vram_type = gmc_v8_0_convert_vram_type(tmp);
 	}
 
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 146, &adev->gmc.vm_fault);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_GFX_PAGE_INV_FAULT, &adev->gmc.vm_fault);
 	if (r)
 		return r;
 
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 147, &adev->gmc.vm_fault);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_GFX_MEM_PROT_FAULT, &adev->gmc.vm_fault);
 	if (r)
 		return r;
 
@@ -1181,6 +1183,12 @@ static int gmc_v8_0_sw_init(void *handle)
 		adev->vm_manager.vram_base_offset = 0;
 	}
 
+	adev->gmc.vm_fault_info = kmalloc(sizeof(struct kfd_vm_fault_info),
+					GFP_KERNEL);
+	if (!adev->gmc.vm_fault_info)
+		return -ENOMEM;
+	atomic_set(&adev->gmc.vm_fault_info_updated, 0);
+
 	return 0;
 }
 
@@ -1190,6 +1198,7 @@ static int gmc_v8_0_sw_fini(void *handle)
 
 	amdgpu_gem_force_release(adev);
 	amdgpu_vm_manager_fini(adev);
+	kfree(adev->gmc.vm_fault_info);
 	gmc_v8_0_gart_fini(adev);
 	amdgpu_bo_fini(adev);
 	release_firmware(adev->gmc.fw);
@@ -1425,7 +1434,7 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_irq_src *source,
 				      struct amdgpu_iv_entry *entry)
 {
-	u32 addr, status, mc_client;
+	u32 addr, status, mc_client, vmid;
 
 	if (amdgpu_sriov_vf(adev)) {
 		dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
@@ -1447,8 +1456,13 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev,
 		gmc_v8_0_set_fault_enable_default(adev, false);
 
 	if (printk_ratelimit()) {
-		dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
-			entry->src_id, entry->src_data[0]);
+		struct amdgpu_task_info task_info = { 0 };
+
+		amdgpu_vm_get_task_info(adev, entry->pasid, &task_info);
+
+		dev_err(adev->dev, "GPU fault detected: %d 0x%08x for process %s pid %d thread %s pid %d\n",
+			entry->src_id, entry->src_data[0], task_info.process_name,
+			task_info.tgid, task_info.task_name, task_info.pid);
 		dev_err(adev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x%08X\n",
 			addr);
 		dev_err(adev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
@@ -1457,6 +1471,29 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev,
 					 entry->pasid);
 	}
 
+	vmid = REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+			     VMID);
+	if (amdgpu_amdkfd_is_kfd_vmid(adev, vmid)
+		&& !atomic_read(&adev->gmc.vm_fault_info_updated)) {
+		struct kfd_vm_fault_info *info = adev->gmc.vm_fault_info;
+		u32 protections = REG_GET_FIELD(status,
+					VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					PROTECTIONS);
+
+		info->vmid = vmid;
+		info->mc_id = REG_GET_FIELD(status,
+					    VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					    MEMORY_CLIENT_ID);
+		info->status = status;
+		info->page_addr = addr;
+		info->prot_valid = protections & 0x7 ? true : false;
+		info->prot_read = protections & 0x8 ? true : false;
+		info->prot_write = protections & 0x10 ? true : false;
+		info->prot_exec = protections & 0x20 ? true : false;
+		mb();
+		atomic_set(&adev->gmc.vm_fault_info_updated, 1);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 3c0a85d4e4ab..399a5db27649 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -43,6 +43,8 @@
 #include "gfxhub_v1_0.h"
 #include "mmhub_v1_0.h"
 
+#include "ivsrcid/vmc/irqsrcs_vmc_1_0.h"
+
 /* add these here since we already include dce12 headers and these are for DCN */
 #define mmHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION                                                          0x055d
 #define mmHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION_BASE_IDX                                                 2
@@ -257,12 +259,17 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 	}
 
 	if (printk_ratelimit()) {
+		struct amdgpu_task_info task_info = { 0 };
+
+		amdgpu_vm_get_task_info(adev, entry->pasid, &task_info);
+
 		dev_err(adev->dev,
-			"[%s] VMC page fault (src_id:%u ring:%u vmid:%u pasid:%u)\n",
+			"[%s] VMC page fault (src_id:%u ring:%u vmid:%u pasid:%u, for process %s pid %d thread %s pid %d\n)\n",
 			entry->vmid_src ? "mmhub" : "gfxhub",
 			entry->src_id, entry->ring_id, entry->vmid,
-			entry->pasid);
-		dev_err(adev->dev, "  at page 0x%016llx from %d\n",
+			entry->pasid, task_info.process_name, task_info.tgid,
+			task_info.task_name, task_info.pid);
+		dev_err(adev->dev, "  at address 0x%016llx from %d\n",
 			addr, entry->client_id);
 		if (!amdgpu_sriov_vf(adev))
 			dev_err(adev->dev,
@@ -872,9 +879,9 @@ static int gmc_v9_0_sw_init(void *handle)
 	}
 
 	/* This interrupt is VMC page fault.*/
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VMC, 0,
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VMC, VMC_1_0__SRCID__VM_FAULT,
 				&adev->gmc.vm_fault);
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_UTCL2, 0,
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_UTCL2, UTCL2_1_0__SRCID__FAULT,
 				&adev->gmc.vm_fault);
 
 	if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
index 7a1e77c93bf1..3f57f6463dc8 100644
--- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
@@ -1921,7 +1921,7 @@ static int kv_dpm_set_power_state(void *handle)
 	int ret;
 
 	if (pi->bapm_enable) {
-		ret = amdgpu_kv_smc_bapm_enable(adev, adev->pm.dpm.ac_power);
+		ret = amdgpu_kv_smc_bapm_enable(adev, adev->pm.ac_power);
 		if (ret) {
 			DRM_ERROR("amdgpu_kv_smc_bapm_enable failed\n");
 			return ret;
@@ -3306,6 +3306,19 @@ static int kv_dpm_read_sensor(void *handle, int idx,
 	}
 }
 
+static int kv_set_powergating_by_smu(void *handle,
+				uint32_t block_type, bool gate)
+{
+	switch (block_type) {
+	case AMD_IP_BLOCK_TYPE_UVD:
+		kv_dpm_powergate_uvd(handle, gate);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
 static const struct amd_ip_funcs kv_dpm_ip_funcs = {
 	.name = "kv_dpm",
 	.early_init = kv_dpm_early_init,
@@ -3342,7 +3355,7 @@ static const struct amd_pm_funcs kv_dpm_funcs = {
 	.print_power_state = &kv_dpm_print_power_state,
 	.debugfs_print_current_performance_level = &kv_dpm_debugfs_print_current_performance_level,
 	.force_performance_level = &kv_dpm_force_performance_level,
-	.powergate_uvd = &kv_dpm_powergate_uvd,
+	.set_powergating_by_smu = kv_set_powergating_by_smu,
 	.enable_bapm = &kv_dpm_enable_bapm,
 	.get_vce_clock_state = amdgpu_get_vce_clock_state,
 	.check_state_equal = kv_check_state_equal,
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index 3d53c4413f13..e70a0d4d6db4 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -471,8 +471,8 @@ void mmhub_v1_0_update_power_gating(struct amdgpu_device *adev,
 						RENG_EXECUTE_ON_REG_UPDATE, 1);
 		WREG32_SOC15(MMHUB, 0, mmPCTL1_RENG_EXECUTE, pctl1_reng_execute);
 
-		if (adev->powerplay.pp_funcs->set_mmhub_powergating_by_smu)
-			amdgpu_dpm_set_mmhub_powergating_by_smu(adev);
+		if (adev->powerplay.pp_funcs->set_powergating_by_smu)
+			amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GMC, true);
 
 	} else {
 		pctl0_reng_execute = REG_SET_FIELD(pctl0_reng_execute,
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index c7190c39c4f5..15ae4bc9c072 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -44,6 +44,8 @@
 
 #include "iceland_sdma_pkt_open.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 static void sdma_v2_4_set_ring_funcs(struct amdgpu_device *adev);
 static void sdma_v2_4_set_buffer_funcs(struct amdgpu_device *adev);
 static void sdma_v2_4_set_vm_pte_funcs(struct amdgpu_device *adev);
@@ -202,8 +204,7 @@ static uint64_t sdma_v2_4_ring_get_rptr(struct amdgpu_ring *ring)
 static uint64_t sdma_v2_4_ring_get_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
-	u32 wptr = RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me]) >> 2;
+	u32 wptr = RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[ring->me]) >> 2;
 
 	return wptr;
 }
@@ -218,9 +219,8 @@ static uint64_t sdma_v2_4_ring_get_wptr(struct amdgpu_ring *ring)
 static void sdma_v2_4_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
 
-	WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], lower_32_bits(ring->wptr) << 2);
+	WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[ring->me], lower_32_bits(ring->wptr) << 2);
 }
 
 static void sdma_v2_4_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
@@ -273,7 +273,7 @@ static void sdma_v2_4_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 {
 	u32 ref_and_mask = 0;
 
-	if (ring == &ring->adev->sdma.instance[0].ring)
+	if (ring->me == 0)
 		ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA0, 1);
 	else
 		ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA1, 1);
@@ -898,7 +898,7 @@ static int sdma_v2_4_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* SDMA trap event */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 224,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SDMA_TRAP,
 			      &adev->sdma.trap_irq);
 	if (r)
 		return r;
@@ -910,7 +910,7 @@ static int sdma_v2_4_sw_init(void *handle)
 		return r;
 
 	/* SDMA Privileged inst */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 247,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SDMA_SRBM_WRITE,
 			      &adev->sdma.illegal_inst_irq);
 	if (r)
 		return r;
@@ -1213,8 +1213,10 @@ static void sdma_v2_4_set_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->sdma.num_instances; i++)
+	for (i = 0; i < adev->sdma.num_instances; i++) {
 		adev->sdma.instance[i].ring.funcs = &sdma_v2_4_ring_funcs;
+		adev->sdma.instance[i].ring.me = i;
+	}
 }
 
 static const struct amdgpu_irq_src_funcs sdma_v2_4_trap_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index aa9ab299fd32..1e07ff274d73 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -44,6 +44,8 @@
 
 #include "tonga_sdma_pkt_open.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 static void sdma_v3_0_set_ring_funcs(struct amdgpu_device *adev);
 static void sdma_v3_0_set_buffer_funcs(struct amdgpu_device *adev);
 static void sdma_v3_0_set_vm_pte_funcs(struct amdgpu_device *adev);
@@ -365,9 +367,7 @@ static uint64_t sdma_v3_0_ring_get_wptr(struct amdgpu_ring *ring)
 		/* XXX check if swapping is necessary on BE */
 		wptr = ring->adev->wb.wb[ring->wptr_offs] >> 2;
 	} else {
-		int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
-
-		wptr = RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me]) >> 2;
+		wptr = RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[ring->me]) >> 2;
 	}
 
 	return wptr;
@@ -394,9 +394,7 @@ static void sdma_v3_0_ring_set_wptr(struct amdgpu_ring *ring)
 
 		WRITE_ONCE(*wb, (lower_32_bits(ring->wptr) << 2));
 	} else {
-		int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
-
-		WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], lower_32_bits(ring->wptr) << 2);
+		WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[ring->me], lower_32_bits(ring->wptr) << 2);
 	}
 }
 
@@ -450,7 +448,7 @@ static void sdma_v3_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 {
 	u32 ref_and_mask = 0;
 
-	if (ring == &ring->adev->sdma.instance[0].ring)
+	if (ring->me == 0)
 		ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA0, 1);
 	else
 		ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA1, 1);
@@ -1179,7 +1177,7 @@ static int sdma_v3_0_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* SDMA trap event */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 224,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SDMA_TRAP,
 			      &adev->sdma.trap_irq);
 	if (r)
 		return r;
@@ -1191,7 +1189,7 @@ static int sdma_v3_0_sw_init(void *handle)
 		return r;
 
 	/* SDMA Privileged inst */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 247,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SDMA_SRBM_WRITE,
 			      &adev->sdma.illegal_inst_irq);
 	if (r)
 		return r;
@@ -1655,8 +1653,10 @@ static void sdma_v3_0_set_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->sdma.num_instances; i++)
+	for (i = 0; i < adev->sdma.num_instances; i++) {
 		adev->sdma.instance[i].ring.funcs = &sdma_v3_0_ring_funcs;
+		adev->sdma.instance[i].ring.me = i;
+	}
 }
 
 static const struct amdgpu_irq_src_funcs sdma_v3_0_trap_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index ca53b3fba422..e7ca4623cfb9 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -38,6 +38,9 @@
 #include "soc15.h"
 #include "vega10_sdma_pkt_open.h"
 
+#include "ivsrcid/sdma0/irqsrcs_sdma0_4_0.h"
+#include "ivsrcid/sdma1/irqsrcs_sdma1_4_0.h"
+
 MODULE_FIRMWARE("amdgpu/vega10_sdma.bin");
 MODULE_FIRMWARE("amdgpu/vega10_sdma1.bin");
 MODULE_FIRMWARE("amdgpu/vega12_sdma.bin");
@@ -296,13 +299,12 @@ static uint64_t sdma_v4_0_ring_get_wptr(struct amdgpu_ring *ring)
 		DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", wptr);
 	} else {
 		u32 lowbit, highbit;
-		int me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
 
-		lowbit = RREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR)) >> 2;
-		highbit = RREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR_HI)) >> 2;
+		lowbit = RREG32(sdma_v4_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR)) >> 2;
+		highbit = RREG32(sdma_v4_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI)) >> 2;
 
 		DRM_DEBUG("wptr [%i]high== 0x%08x low==0x%08x\n",
-				me, highbit, lowbit);
+				ring->me, highbit, lowbit);
 		wptr = highbit;
 		wptr = wptr << 32;
 		wptr |= lowbit;
@@ -339,17 +341,15 @@ static void sdma_v4_0_ring_set_wptr(struct amdgpu_ring *ring)
 				ring->doorbell_index, ring->wptr << 2);
 		WDOORBELL64(ring->doorbell_index, ring->wptr << 2);
 	} else {
-		int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
-
 		DRM_DEBUG("Not using doorbell -- "
 				"mmSDMA%i_GFX_RB_WPTR == 0x%08x "
 				"mmSDMA%i_GFX_RB_WPTR_HI == 0x%08x\n",
-				me,
+				ring->me,
 				lower_32_bits(ring->wptr << 2),
-				me,
+				ring->me,
 				upper_32_bits(ring->wptr << 2));
-		WREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR), lower_32_bits(ring->wptr << 2));
-		WREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR_HI), upper_32_bits(ring->wptr << 2));
+		WREG32(sdma_v4_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR), lower_32_bits(ring->wptr << 2));
+		WREG32(sdma_v4_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI), upper_32_bits(ring->wptr << 2));
 	}
 }
 
@@ -430,7 +430,7 @@ static void sdma_v4_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 	u32 ref_and_mask = 0;
 	const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio_funcs->hdp_flush_reg;
 
-	if (ring == &ring->adev->sdma.instance[0].ring)
+	if (ring->me == 0)
 		ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0;
 	else
 		ref_and_mask = nbio_hf_reg->ref_and_mask_sdma1;
@@ -1228,13 +1228,13 @@ static int sdma_v4_0_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* SDMA trap event */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_SDMA0, 224,
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_SDMA0, SDMA0_4_0__SRCID__SDMA_TRAP,
 			      &adev->sdma.trap_irq);
 	if (r)
 		return r;
 
 	/* SDMA trap event */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_SDMA1, 224,
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_SDMA1, SDMA1_4_0__SRCID__SDMA_TRAP,
 			      &adev->sdma.trap_irq);
 	if (r)
 		return r;
@@ -1651,8 +1651,10 @@ static void sdma_v4_0_set_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->sdma.num_instances; i++)
+	for (i = 0; i < adev->sdma.num_instances; i++) {
 		adev->sdma.instance[i].ring.funcs = &sdma_v4_0_ring_funcs;
+		adev->sdma.instance[i].ring.me = i;
+	}
 }
 
 static const struct amdgpu_irq_src_funcs sdma_v4_0_trap_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index 5c97a3671726..db327b412562 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
@@ -56,16 +56,16 @@
 
 #define BIOS_SCRATCH_4                                    0x5cd
 
-MODULE_FIRMWARE("radeon/tahiti_smc.bin");
-MODULE_FIRMWARE("radeon/pitcairn_smc.bin");
-MODULE_FIRMWARE("radeon/pitcairn_k_smc.bin");
-MODULE_FIRMWARE("radeon/verde_smc.bin");
-MODULE_FIRMWARE("radeon/verde_k_smc.bin");
-MODULE_FIRMWARE("radeon/oland_smc.bin");
-MODULE_FIRMWARE("radeon/oland_k_smc.bin");
-MODULE_FIRMWARE("radeon/hainan_smc.bin");
-MODULE_FIRMWARE("radeon/hainan_k_smc.bin");
-MODULE_FIRMWARE("radeon/banks_k_2_smc.bin");
+MODULE_FIRMWARE("amdgpu/tahiti_smc.bin");
+MODULE_FIRMWARE("amdgpu/pitcairn_smc.bin");
+MODULE_FIRMWARE("amdgpu/pitcairn_k_smc.bin");
+MODULE_FIRMWARE("amdgpu/verde_smc.bin");
+MODULE_FIRMWARE("amdgpu/verde_k_smc.bin");
+MODULE_FIRMWARE("amdgpu/oland_smc.bin");
+MODULE_FIRMWARE("amdgpu/oland_k_smc.bin");
+MODULE_FIRMWARE("amdgpu/hainan_smc.bin");
+MODULE_FIRMWARE("amdgpu/hainan_k_smc.bin");
+MODULE_FIRMWARE("amdgpu/banks_k_2_smc.bin");
 
 static const struct amd_pm_funcs si_dpm_funcs;
 
@@ -3480,7 +3480,7 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev,
 		disable_sclk_switching = true;
 	}
 
-	if (adev->pm.dpm.ac_power)
+	if (adev->pm.ac_power)
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
 	else
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_dc;
@@ -3489,7 +3489,7 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev,
 		if (ps->performance_levels[i].vddc > ps->performance_levels[i+1].vddc)
 			ps->performance_levels[i].vddc = ps->performance_levels[i+1].vddc;
 	}
-	if (adev->pm.dpm.ac_power == false) {
+	if (adev->pm.ac_power == false) {
 		for (i = 0; i < ps->performance_level_count; i++) {
 			if (ps->performance_levels[i].mclk > max_limits->mclk)
 				ps->performance_levels[i].mclk = max_limits->mclk;
@@ -7318,8 +7318,7 @@ static int si_dpm_init(struct amdgpu_device *adev)
 	pi = &eg_pi->rv7xx;
 
 	si_pi->sys_pcie_mask =
-		(adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_MASK) >>
-		CAIL_PCIE_LINK_SPEED_SUPPORT_SHIFT;
+		adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_MASK;
 	si_pi->force_pcie_gen = AMDGPU_PCIE_GEN_INVALID;
 	si_pi->boot_pcie_gen = si_get_current_pcie_speed(adev);
 
@@ -7667,7 +7666,7 @@ static int si_dpm_init_microcode(struct amdgpu_device *adev)
 	default: BUG();
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_smc.bin", chip_name);
 	err = request_firmware(&adev->pm.fw, fw_name, adev->dev);
 	if (err)
 		goto out;
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15d.h b/drivers/gpu/drm/amd/amdgpu/soc15d.h
index 8dc29107228f..edfe50821cd9 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15d.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15d.h
@@ -53,6 +53,29 @@
 
 #define PACKET3_COMPUTE(op, n) (PACKET3(op, n) | 1 << 1)
 
+#define	PACKETJ_CONDITION_CHECK0	0
+#define	PACKETJ_CONDITION_CHECK1	1
+#define	PACKETJ_CONDITION_CHECK2	2
+#define	PACKETJ_CONDITION_CHECK3	3
+#define	PACKETJ_CONDITION_CHECK4	4
+#define	PACKETJ_CONDITION_CHECK5	5
+#define	PACKETJ_CONDITION_CHECK6	6
+#define	PACKETJ_CONDITION_CHECK7	7
+
+#define	PACKETJ_TYPE0	0
+#define	PACKETJ_TYPE1	1
+#define	PACKETJ_TYPE2	2
+#define	PACKETJ_TYPE3	3
+#define	PACKETJ_TYPE4	4
+#define	PACKETJ_TYPE5	5
+#define	PACKETJ_TYPE6	6
+#define	PACKETJ_TYPE7	7
+
+#define PACKETJ(reg, r, cond, type)	((reg & 0x3FFFF) |			\
+			 ((r & 0x3F) << 18) |			\
+			 ((cond & 0xF) << 24) |				\
+			 ((type & 0xF) << 28))
+
 /* Packet 3 types */
 #define	PACKET3_NOP					0x10
 #define	PACKET3_SET_BASE				0x11
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index 341ee6d55ce8..aeaa1ca46a99 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
@@ -35,6 +35,7 @@
 #include "vi.h"
 #include "smu/smu_7_1_2_d.h"
 #include "smu/smu_7_1_2_sh_mask.h"
+#include "ivsrcid/ivsrcid_vislands30.h"
 
 static void uvd_v5_0_set_ring_funcs(struct amdgpu_device *adev);
 static void uvd_v5_0_set_irq_funcs(struct amdgpu_device *adev);
@@ -104,7 +105,7 @@ static int uvd_v5_0_sw_init(void *handle)
 	int r;
 
 	/* UVD TRAP */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 124, &adev->uvd.inst->irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_UVD_SYSTEM_MESSAGE, &adev->uvd.inst->irq);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index bfddf97dd13e..598dbeaba636 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -36,6 +36,7 @@
 #include "bif/bif_5_1_d.h"
 #include "gmc/gmc_8_1_d.h"
 #include "vi.h"
+#include "ivsrcid/ivsrcid_vislands30.h"
 
 /* Polaris10/11/12 firmware version */
 #define FW_1_130_16 ((1 << 24) | (130 << 16) | (16 << 8))
@@ -247,12 +248,10 @@ static int uvd_v6_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err;
 
-	amdgpu_job_free(job);
 	if (fence)
 		*fence = dma_fence_get(f);
 	dma_fence_put(f);
@@ -311,19 +310,13 @@ static int uvd_v6_0_enc_get_destroy_msg(struct amdgpu_ring *ring,
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (direct) {
-		r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-		job->fence = dma_fence_get(f);
-		if (r)
-			goto err;
-
-		amdgpu_job_free(job);
-	} else {
-		r = amdgpu_job_submit(job, ring, &ring->adev->vce.entity,
+	if (direct)
+		r = amdgpu_job_submit_direct(job, ring, &f);
+	else
+		r = amdgpu_job_submit(job, &ring->adev->vce.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
-		if (r)
-			goto err;
-	}
+	if (r)
+		goto err;
 
 	if (fence)
 		*fence = dma_fence_get(f);
@@ -400,14 +393,14 @@ static int uvd_v6_0_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* UVD TRAP */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 124, &adev->uvd.inst->irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_UVD_SYSTEM_MESSAGE, &adev->uvd.inst->irq);
 	if (r)
 		return r;
 
 	/* UVD ENC TRAP */
 	if (uvd_v6_0_enc_support(adev)) {
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
-			r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, i + 119, &adev->uvd.inst->irq);
+			r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, i + VISLANDS30_IV_SRCID_UVD_ENC_GEN_PURP, &adev->uvd.inst->irq);
 			if (r)
 				return r;
 		}
@@ -425,16 +418,6 @@ static int uvd_v6_0_sw_init(void *handle)
 		adev->uvd.num_enc_rings = 0;
 
 		DRM_INFO("UVD ENC is disabled\n");
-	} else {
-		struct drm_sched_rq *rq;
-		ring = &adev->uvd.inst->ring_enc[0];
-		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-		r = drm_sched_entity_init(&ring->sched, &adev->uvd.inst->entity_enc,
-					  rq, NULL);
-		if (r) {
-			DRM_ERROR("Failed setting up UVD ENC run queue.\n");
-			return r;
-		}
 	}
 
 	r = amdgpu_uvd_resume(adev);
@@ -470,8 +453,6 @@ static int uvd_v6_0_sw_fini(void *handle)
 		return r;
 
 	if (uvd_v6_0_enc_support(adev)) {
-		drm_sched_entity_fini(&adev->uvd.inst->ring_enc[0].sched, &adev->uvd.inst->entity_enc);
-
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i)
 			amdgpu_ring_fini(&adev->uvd.inst->ring_enc[i]);
 	}
@@ -1569,7 +1550,6 @@ static const struct amdgpu_ring_funcs uvd_v6_0_ring_phys_funcs = {
 static const struct amdgpu_ring_funcs uvd_v6_0_ring_vm_funcs = {
 	.type = AMDGPU_RING_TYPE_UVD,
 	.align_mask = 0xf,
-	.nop = PACKET0(mmUVD_NO_OP, 0),
 	.support_64bit_ptrs = false,
 	.get_rptr = uvd_v6_0_ring_get_rptr,
 	.get_wptr = uvd_v6_0_ring_get_wptr,
@@ -1587,7 +1567,7 @@ static const struct amdgpu_ring_funcs uvd_v6_0_ring_vm_funcs = {
 	.emit_hdp_flush = uvd_v6_0_ring_emit_hdp_flush,
 	.test_ring = uvd_v6_0_ring_test_ring,
 	.test_ib = amdgpu_uvd_ring_test_ib,
-	.insert_nop = amdgpu_ring_insert_nop,
+	.insert_nop = uvd_v6_0_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.begin_use = amdgpu_uvd_ring_begin_use,
 	.end_use = amdgpu_uvd_ring_end_use,
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index 57d32f21b3a6..5fab3560a71d 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -39,6 +39,13 @@
 #include "hdp/hdp_4_0_offset.h"
 #include "mmhub/mmhub_1_0_offset.h"
 #include "mmhub/mmhub_1_0_sh_mask.h"
+#include "ivsrcid/uvd/irqsrcs_uvd_7_0.h"
+
+#define mmUVD_PG0_CC_UVD_HARVESTING                                                                    0x00c7
+#define mmUVD_PG0_CC_UVD_HARVESTING_BASE_IDX                                                           1
+//UVD_PG0_CC_UVD_HARVESTING
+#define UVD_PG0_CC_UVD_HARVESTING__UVD_DISABLE__SHIFT                                                         0x1
+#define UVD_PG0_CC_UVD_HARVESTING__UVD_DISABLE_MASK                                                           0x00000002L
 
 #define UVD7_MAX_HW_INSTANCES_VEGA20			2
 
@@ -249,12 +256,10 @@ static int uvd_v7_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err;
 
-	amdgpu_job_free(job);
 	if (fence)
 		*fence = dma_fence_get(f);
 	dma_fence_put(f);
@@ -312,19 +317,13 @@ int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (direct) {
-		r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-		job->fence = dma_fence_get(f);
-		if (r)
-			goto err;
-
-		amdgpu_job_free(job);
-	} else {
-		r = amdgpu_job_submit(job, ring, &ring->adev->vce.entity,
+	if (direct)
+		r = amdgpu_job_submit_direct(job, ring, &f);
+	else
+		r = amdgpu_job_submit(job, &ring->adev->vce.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
-		if (r)
-			goto err;
-	}
+	if (r)
+		goto err;
 
 	if (fence)
 		*fence = dma_fence_get(f);
@@ -377,10 +376,25 @@ error:
 static int uvd_v7_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	if (adev->asic_type == CHIP_VEGA20)
+
+	if (adev->asic_type == CHIP_VEGA20) {
+		u32 harvest;
+		int i;
+
 		adev->uvd.num_uvd_inst = UVD7_MAX_HW_INSTANCES_VEGA20;
-	else
+		for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
+			harvest = RREG32_SOC15(UVD, i, mmUVD_PG0_CC_UVD_HARVESTING);
+			if (harvest & UVD_PG0_CC_UVD_HARVESTING__UVD_DISABLE_MASK) {
+				adev->uvd.harvest_config |= 1 << i;
+			}
+		}
+		if (adev->uvd.harvest_config == (AMDGPU_UVD_HARVEST_UVD0 |
+						 AMDGPU_UVD_HARVEST_UVD1))
+			/* both instances are harvested, disable the block */
+			return -ENOENT;
+	} else {
 		adev->uvd.num_uvd_inst = 1;
+	}
 
 	if (amdgpu_sriov_vf(adev))
 		adev->uvd.num_enc_rings = 1;
@@ -396,19 +410,20 @@ static int uvd_v7_0_early_init(void *handle)
 static int uvd_v7_0_sw_init(void *handle)
 {
 	struct amdgpu_ring *ring;
-	struct drm_sched_rq *rq;
 	int i, j, r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
+		if (adev->uvd.harvest_config & (1 << j))
+			continue;
 		/* UVD TRAP */
-		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_uvds[j], 124, &adev->uvd.inst[j].irq);
+		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_uvds[j], UVD_7_0__SRCID__UVD_SYSTEM_MESSAGE_INTERRUPT, &adev->uvd.inst[j].irq);
 		if (r)
 			return r;
 
 		/* UVD ENC TRAP */
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
-			r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_uvds[j], i + 119, &adev->uvd.inst[j].irq);
+			r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_uvds[j], i + UVD_7_0__SRCID__UVD_ENC_GEN_PURP, &adev->uvd.inst[j].irq);
 			if (r)
 				return r;
 		}
@@ -428,22 +443,13 @@ static int uvd_v7_0_sw_init(void *handle)
 		DRM_INFO("PSP loading UVD firmware\n");
 	}
 
-	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
-		ring = &adev->uvd.inst[j].ring_enc[0];
-		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-		r = drm_sched_entity_init(&ring->sched, &adev->uvd.inst[j].entity_enc,
-					  rq, NULL);
-		if (r) {
-			DRM_ERROR("(%d)Failed setting up UVD ENC run queue.\n", j);
-			return r;
-		}
-	}
-
 	r = amdgpu_uvd_resume(adev);
 	if (r)
 		return r;
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
+		if (adev->uvd.harvest_config & (1 << j))
+			continue;
 		if (!amdgpu_sriov_vf(adev)) {
 			ring = &adev->uvd.inst[j].ring;
 			sprintf(ring->name, "uvd<%d>", j);
@@ -491,8 +497,8 @@ static int uvd_v7_0_sw_fini(void *handle)
 		return r;
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
-		drm_sched_entity_fini(&adev->uvd.inst[j].ring_enc[0].sched, &adev->uvd.inst[j].entity_enc);
-
+		if (adev->uvd.harvest_config & (1 << j))
+			continue;
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i)
 			amdgpu_ring_fini(&adev->uvd.inst[j].ring_enc[i]);
 	}
@@ -521,6 +527,8 @@ static int uvd_v7_0_hw_init(void *handle)
 		goto done;
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
+		if (adev->uvd.harvest_config & (1 << j))
+			continue;
 		ring = &adev->uvd.inst[j].ring;
 
 		if (!amdgpu_sriov_vf(adev)) {
@@ -600,8 +608,11 @@ static int uvd_v7_0_hw_fini(void *handle)
 		DRM_DEBUG("For SRIOV client, shouldn't do anything.\n");
 	}
 
-	for (i = 0; i < adev->uvd.num_uvd_inst; ++i)
+	for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
+		if (adev->uvd.harvest_config & (1 << i))
+			continue;
 		adev->uvd.inst[i].ring.ready = false;
+	}
 
 	return 0;
 }
@@ -644,6 +655,8 @@ static void uvd_v7_0_mc_resume(struct amdgpu_device *adev)
 	int i;
 
 	for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
+		if (adev->uvd.harvest_config & (1 << i))
+			continue;
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
 			WREG32_SOC15(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
 				lower_32_bits(adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].mc_addr));
@@ -716,6 +729,8 @@ static int uvd_v7_0_mmsch_start(struct amdgpu_device *adev,
 	WREG32_SOC15(VCE, 0, mmVCE_MMSCH_VF_MAILBOX_RESP, 0);
 
 	for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
+		if (adev->uvd.harvest_config & (1 << i))
+			continue;
 		WDOORBELL32(adev->uvd.inst[i].ring_enc[0].doorbell_index, 0);
 		adev->wb.wb[adev->uvd.inst[i].ring_enc[0].wptr_offs] = 0;
 		adev->uvd.inst[i].ring_enc[0].wptr = 0;
@@ -772,6 +787,8 @@ static int uvd_v7_0_sriov_start(struct amdgpu_device *adev)
 		init_table += header->uvd_table_offset;
 
 		for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
+			if (adev->uvd.harvest_config & (1 << i))
+				continue;
 			ring = &adev->uvd.inst[i].ring;
 			ring->wptr = 0;
 			size = AMDGPU_GPU_PAGE_ALIGN(adev->uvd.fw->size + 4);
@@ -911,6 +928,8 @@ static int uvd_v7_0_start(struct amdgpu_device *adev)
 	int i, j, k, r;
 
 	for (k = 0; k < adev->uvd.num_uvd_inst; ++k) {
+		if (adev->uvd.harvest_config & (1 << k))
+			continue;
 		/* disable DPG */
 		WREG32_P(SOC15_REG_OFFSET(UVD, k, mmUVD_POWER_STATUS), 0,
 				~UVD_POWER_STATUS__UVD_PG_MODE_MASK);
@@ -923,6 +942,8 @@ static int uvd_v7_0_start(struct amdgpu_device *adev)
 	uvd_v7_0_mc_resume(adev);
 
 	for (k = 0; k < adev->uvd.num_uvd_inst; ++k) {
+		if (adev->uvd.harvest_config & (1 << k))
+			continue;
 		ring = &adev->uvd.inst[k].ring;
 		/* disable clock gating */
 		WREG32_P(SOC15_REG_OFFSET(UVD, k, mmUVD_CGC_CTRL), 0,
@@ -1090,6 +1111,8 @@ static void uvd_v7_0_stop(struct amdgpu_device *adev)
 	uint8_t i = 0;
 
 	for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
+		if (adev->uvd.harvest_config & (1 << i))
+			continue;
 		/* force RBC into idle state */
 		WREG32_SOC15(UVD, i, mmUVD_RBC_RB_CNTL, 0x11010101);
 
@@ -1227,6 +1250,34 @@ static int uvd_v7_0_ring_test_ring(struct amdgpu_ring *ring)
 }
 
 /**
+ * uvd_v7_0_ring_patch_cs_in_place - Patch the IB for command submission.
+ *
+ * @p: the CS parser with the IBs
+ * @ib_idx: which IB to patch
+ *
+ */
+static int uvd_v7_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p,
+					   uint32_t ib_idx)
+{
+	struct amdgpu_ib *ib = &p->job->ibs[ib_idx];
+	unsigned i;
+
+	/* No patching necessary for the first instance */
+	if (!p->ring->me)
+		return 0;
+
+	for (i = 0; i < ib->length_dw; i += 2) {
+		uint32_t reg = amdgpu_get_ib_value(p, ib_idx, i);
+
+		reg -= p->adev->reg_offset[UVD_HWIP][0][1];
+		reg += p->adev->reg_offset[UVD_HWIP][1][1];
+
+		amdgpu_set_ib_value(p, ib_idx, i, reg);
+	}
+	return 0;
+}
+
+/**
  * uvd_v7_0_ring_emit_ib - execute indirect buffer
  *
  * @ring: amdgpu_ring pointer
@@ -1718,6 +1769,7 @@ static const struct amdgpu_ring_funcs uvd_v7_0_ring_vm_funcs = {
 	.get_rptr = uvd_v7_0_ring_get_rptr,
 	.get_wptr = uvd_v7_0_ring_get_wptr,
 	.set_wptr = uvd_v7_0_ring_set_wptr,
+	.patch_cs_in_place = uvd_v7_0_ring_patch_cs_in_place,
 	.emit_frame_size =
 		6 + /* hdp invalidate */
 		SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
@@ -1777,6 +1829,8 @@ static void uvd_v7_0_set_ring_funcs(struct amdgpu_device *adev)
 	int i;
 
 	for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
+		if (adev->uvd.harvest_config & (1 << i))
+			continue;
 		adev->uvd.inst[i].ring.funcs = &uvd_v7_0_ring_vm_funcs;
 		adev->uvd.inst[i].ring.me = i;
 		DRM_INFO("UVD(%d) is enabled in VM mode\n", i);
@@ -1788,6 +1842,8 @@ static void uvd_v7_0_set_enc_ring_funcs(struct amdgpu_device *adev)
 	int i, j;
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
+		if (adev->uvd.harvest_config & (1 << j))
+			continue;
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
 			adev->uvd.inst[j].ring_enc[i].funcs = &uvd_v7_0_enc_ring_vm_funcs;
 			adev->uvd.inst[j].ring_enc[i].me = j;
@@ -1807,6 +1863,8 @@ static void uvd_v7_0_set_irq_funcs(struct amdgpu_device *adev)
 	int i;
 
 	for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
+		if (adev->uvd.harvest_config & (1 << i))
+			continue;
 		adev->uvd.inst[i].irq.num_types = adev->uvd.num_enc_rings + 1;
 		adev->uvd.inst[i].irq.funcs = &uvd_v7_0_irq_funcs;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
index 47f70827195b..d48e877b682e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
@@ -56,7 +56,7 @@ static uint64_t vce_v2_0_ring_get_rptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		return RREG32(mmVCE_RB_RPTR);
 	else
 		return RREG32(mmVCE_RB_RPTR2);
@@ -73,7 +73,7 @@ static uint64_t vce_v2_0_ring_get_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		return RREG32(mmVCE_RB_WPTR);
 	else
 		return RREG32(mmVCE_RB_WPTR2);
@@ -90,7 +90,7 @@ static void vce_v2_0_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
 	else
 		WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
@@ -627,8 +627,10 @@ static void vce_v2_0_set_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->vce.num_rings; i++)
+	for (i = 0; i < adev->vce.num_rings; i++) {
 		adev->vce.ring[i].funcs = &vce_v2_0_ring_funcs;
+		adev->vce.ring[i].me = i;
+	}
 }
 
 static const struct amdgpu_irq_src_funcs vce_v2_0_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index a71b97519cc0..cc6ce6cc03f4 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -39,6 +39,7 @@
 #include "smu/smu_7_1_2_sh_mask.h"
 #include "gca/gfx_8_0_d.h"
 #include "gca/gfx_8_0_sh_mask.h"
+#include "ivsrcid/ivsrcid_vislands30.h"
 
 
 #define GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT	0x04
@@ -86,9 +87,9 @@ static uint64_t vce_v3_0_ring_get_rptr(struct amdgpu_ring *ring)
 	else if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0)
 		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		v = RREG32(mmVCE_RB_RPTR);
-	else if (ring == &adev->vce.ring[1])
+	else if (ring->me == 1)
 		v = RREG32(mmVCE_RB_RPTR2);
 	else
 		v = RREG32(mmVCE_RB_RPTR3);
@@ -118,9 +119,9 @@ static uint64_t vce_v3_0_ring_get_wptr(struct amdgpu_ring *ring)
 	else if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0)
 		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		v = RREG32(mmVCE_RB_WPTR);
-	else if (ring == &adev->vce.ring[1])
+	else if (ring->me == 1)
 		v = RREG32(mmVCE_RB_WPTR2);
 	else
 		v = RREG32(mmVCE_RB_WPTR3);
@@ -149,9 +150,9 @@ static void vce_v3_0_ring_set_wptr(struct amdgpu_ring *ring)
 	else if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0)
 		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
-	else if (ring == &adev->vce.ring[1])
+	else if (ring->me == 1)
 		WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
 	else
 		WREG32(mmVCE_RB_WPTR3, lower_32_bits(ring->wptr));
@@ -422,7 +423,7 @@ static int vce_v3_0_sw_init(void *handle)
 	int r, i;
 
 	/* VCE */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 167, &adev->vce.irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_VCE_TRAP, &adev->vce.irq);
 	if (r)
 		return r;
 
@@ -942,12 +943,16 @@ static void vce_v3_0_set_ring_funcs(struct amdgpu_device *adev)
 	int i;
 
 	if (adev->asic_type >= CHIP_STONEY) {
-		for (i = 0; i < adev->vce.num_rings; i++)
+		for (i = 0; i < adev->vce.num_rings; i++) {
 			adev->vce.ring[i].funcs = &vce_v3_0_ring_vm_funcs;
+			adev->vce.ring[i].me = i;
+		}
 		DRM_INFO("VCE enabled in VM mode\n");
 	} else {
-		for (i = 0; i < adev->vce.num_rings; i++)
+		for (i = 0; i < adev->vce.num_rings; i++) {
 			adev->vce.ring[i].funcs = &vce_v3_0_ring_phys_funcs;
+			adev->vce.ring[i].me = i;
+		}
 		DRM_INFO("VCE enabled in physical mode\n");
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
index 8fd1b742985a..65f8860169e9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
@@ -39,6 +39,8 @@
 #include "mmhub/mmhub_1_0_offset.h"
 #include "mmhub/mmhub_1_0_sh_mask.h"
 
+#include "ivsrcid/vce/irqsrcs_vce_4_0.h"
+
 #define VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK	0x02
 
 #define VCE_V4_0_FW_SIZE	(384 * 1024)
@@ -60,9 +62,9 @@ static uint64_t vce_v4_0_ring_get_rptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		return RREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_RPTR));
-	else if (ring == &adev->vce.ring[1])
+	else if (ring->me == 1)
 		return RREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_RPTR2));
 	else
 		return RREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_RPTR3));
@@ -82,9 +84,9 @@ static uint64_t vce_v4_0_ring_get_wptr(struct amdgpu_ring *ring)
 	if (ring->use_doorbell)
 		return adev->wb.wb[ring->wptr_offs];
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		return RREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_WPTR));
-	else if (ring == &adev->vce.ring[1])
+	else if (ring->me == 1)
 		return RREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_WPTR2));
 	else
 		return RREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_WPTR3));
@@ -108,10 +110,10 @@ static void vce_v4_0_ring_set_wptr(struct amdgpu_ring *ring)
 		return;
 	}
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		WREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_WPTR),
 			lower_32_bits(ring->wptr));
-	else if (ring == &adev->vce.ring[1])
+	else if (ring->me == 1)
 		WREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_WPTR2),
 			lower_32_bits(ring->wptr));
 	else
@@ -1088,8 +1090,10 @@ static void vce_v4_0_set_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->vce.num_rings; i++)
+	for (i = 0; i < adev->vce.num_rings; i++) {
 		adev->vce.ring[i].funcs = &vce_v4_0_ring_vm_funcs;
+		adev->vce.ring[i].me = i;
+	}
 	DRM_INFO("VCE enabled in VM mode\n");
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 29684c3ea4ef..2ce91a748c40 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -35,10 +35,14 @@
 #include "mmhub/mmhub_9_1_offset.h"
 #include "mmhub/mmhub_9_1_sh_mask.h"
 
+#include "ivsrcid/vcn/irqsrcs_vcn_1_0.h"
+
 static int vcn_v1_0_stop(struct amdgpu_device *adev);
 static void vcn_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v1_0_set_enc_ring_funcs(struct amdgpu_device *adev);
+static void vcn_v1_0_set_jpeg_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v1_0_set_irq_funcs(struct amdgpu_device *adev);
+static void vcn_v1_0_jpeg_ring_set_patch_ring(struct amdgpu_ring *ring, uint32_t ptr);
 
 /**
  * vcn_v1_0_early_init - set function pointers
@@ -55,6 +59,7 @@ static int vcn_v1_0_early_init(void *handle)
 
 	vcn_v1_0_set_dec_ring_funcs(adev);
 	vcn_v1_0_set_enc_ring_funcs(adev);
+	vcn_v1_0_set_jpeg_ring_funcs(adev);
 	vcn_v1_0_set_irq_funcs(adev);
 
 	return 0;
@@ -74,18 +79,23 @@ static int vcn_v1_0_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* VCN DEC TRAP */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, 124, &adev->vcn.irq);
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, VCN_1_0__SRCID__UVD_SYSTEM_MESSAGE_INTERRUPT, &adev->vcn.irq);
 	if (r)
 		return r;
 
 	/* VCN ENC TRAP */
 	for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
-		r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, i + 119,
+		r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, i + VCN_1_0__SRCID__UVD_ENC_GENERAL_PURPOSE,
 					&adev->vcn.irq);
 		if (r)
 			return r;
 	}
 
+	/* VCN JPEG TRAP */
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, 126, &adev->vcn.irq);
+	if (r)
+		return r;
+
 	r = amdgpu_vcn_sw_init(adev);
 	if (r)
 		return r;
@@ -108,6 +118,12 @@ static int vcn_v1_0_sw_init(void *handle)
 			return r;
 	}
 
+	ring = &adev->vcn.ring_jpeg;
+	sprintf(ring->name, "vcn_jpeg");
+	r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.irq, 0);
+	if (r)
+		return r;
+
 	return r;
 }
 
@@ -162,6 +178,14 @@ static int vcn_v1_0_hw_init(void *handle)
 		}
 	}
 
+	ring = &adev->vcn.ring_jpeg;
+	ring->ready = true;
+	r = amdgpu_ring_test_ring(ring);
+	if (r) {
+		ring->ready = false;
+		goto done;
+	}
+
 done:
 	if (!r)
 		DRM_INFO("VCN decode and encode initialized successfully.\n");
@@ -578,12 +602,12 @@ static int vcn_v1_0_start(struct amdgpu_device *adev)
 	/* disable byte swapping */
 	lmi_swap_cntl = 0;
 
-	vcn_v1_0_mc_resume(adev);
-
 	vcn_1_0_disable_static_power_gating(adev);
 	/* disable clock gating */
 	vcn_v1_0_disable_clock_gating(adev);
 
+	vcn_v1_0_mc_resume(adev);
+
 	/* disable interupt */
 	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_MASTINT_EN), 0,
 			~UVD_MASTINT_EN__VCPU_EN_MASK);
@@ -729,6 +753,22 @@ static int vcn_v1_0_start(struct amdgpu_device *adev)
 	WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
 	WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE2, ring->ring_size / 4);
 
+	ring = &adev->vcn.ring_jpeg;
+	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_VMID, 0);
+	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, (0x00000001L | 0x00000002L));
+	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW, lower_32_bits(ring->gpu_addr));
+	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH, upper_32_bits(ring->gpu_addr));
+	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_RPTR, 0);
+	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR, 0);
+	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, 0x00000002L);
+
+	/* initialize wptr */
+	ring->wptr = RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
+
+	/* copy patch commands to the jpeg ring */
+	vcn_v1_0_jpeg_ring_set_patch_ring(ring,
+		(ring->wptr + ring->max_dw * amdgpu_sched_hw_submission));
+
 	return 0;
 }
 
@@ -1126,6 +1166,383 @@ static void vcn_v1_0_enc_ring_emit_wreg(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, val);
 }
 
+
+/**
+ * vcn_v1_0_jpeg_ring_get_rptr - get read pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware read pointer
+ */
+static uint64_t vcn_v1_0_jpeg_ring_get_rptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	return RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_RPTR);
+}
+
+/**
+ * vcn_v1_0_jpeg_ring_get_wptr - get write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware write pointer
+ */
+static uint64_t vcn_v1_0_jpeg_ring_get_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	return RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
+}
+
+/**
+ * vcn_v1_0_jpeg_ring_set_wptr - set write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Commits the write pointer to the hardware
+ */
+static void vcn_v1_0_jpeg_ring_set_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
+}
+
+/**
+ * vcn_v1_0_jpeg_ring_insert_start - insert a start command
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Write a start command to the ring.
+ */
+static void vcn_v1_0_jpeg_ring_insert_start(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x68e04);
+
+	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x80010000);
+}
+
+/**
+ * vcn_v1_0_jpeg_ring_insert_end - insert a end command
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Write a end command to the ring.
+ */
+static void vcn_v1_0_jpeg_ring_insert_end(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x68e04);
+
+	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x00010000);
+}
+
+/**
+ * vcn_v1_0_jpeg_ring_emit_fence - emit an fence & trap command
+ *
+ * @ring: amdgpu_ring pointer
+ * @fence: fence to emit
+ *
+ * Write a fence and a trap command to the ring.
+ */
+static void vcn_v1_0_jpeg_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
+				     unsigned flags)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_DATA0), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, seq);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_DATA1), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, seq);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_CMD), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x8);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_CMD), 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE4));
+	amdgpu_ring_write(ring, 0);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x01400200);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, seq);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(0, 0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE2));
+	amdgpu_ring_write(ring, 0xffffffff);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x3fbc);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(0, 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x1);
+}
+
+/**
+ * vcn_v1_0_jpeg_ring_emit_ib - execute indirect buffer
+ *
+ * @ring: amdgpu_ring pointer
+ * @ib: indirect buffer to execute
+ *
+ * Write ring commands to execute the indirect buffer.
+ */
+static void vcn_v1_0_jpeg_ring_emit_ib(struct amdgpu_ring *ring,
+				  struct amdgpu_ib *ib,
+				  unsigned vmid, bool ctx_switch)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_IB_VMID), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JPEG_VMID), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_IB_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_IB_SIZE), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, ib->length_dw);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(ring->gpu_addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(ring->gpu_addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(0, 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE2));
+	amdgpu_ring_write(ring, 0);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x01400200);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x2);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_STATUS), 0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE3));
+	amdgpu_ring_write(ring, 0x2);
+}
+
+static void vcn_v1_0_jpeg_ring_emit_reg_wait(struct amdgpu_ring *ring,
+					    uint32_t reg, uint32_t val,
+					    uint32_t mask)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t reg_offset = (reg << 2);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x01400200);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, val);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
+		((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring,
+			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3));
+	} else {
+		amdgpu_ring_write(ring, reg_offset);
+		amdgpu_ring_write(ring,
+			PACKETJ(0, 0, 0, PACKETJ_TYPE3));
+	}
+	amdgpu_ring_write(ring, mask);
+}
+
+static void vcn_v1_0_jpeg_ring_emit_vm_flush(struct amdgpu_ring *ring,
+		unsigned vmid, uint64_t pd_addr)
+{
+	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
+	uint32_t data0, data1, mask;
+
+	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
+
+	/* wait for register write */
+	data0 = hub->ctx0_ptb_addr_lo32 + vmid * 2;
+	data1 = lower_32_bits(pd_addr);
+	mask = 0xffffffff;
+	vcn_v1_0_jpeg_ring_emit_reg_wait(ring, data0, data1, mask);
+}
+
+static void vcn_v1_0_jpeg_ring_emit_wreg(struct amdgpu_ring *ring,
+					uint32_t reg, uint32_t val)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t reg_offset = (reg << 2);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
+			((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring,
+			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0));
+	} else {
+		amdgpu_ring_write(ring, reg_offset);
+		amdgpu_ring_write(ring,
+			PACKETJ(0, 0, 0, PACKETJ_TYPE0));
+	}
+	amdgpu_ring_write(ring, val);
+}
+
+static void vcn_v1_0_jpeg_ring_nop(struct amdgpu_ring *ring, uint32_t count)
+{
+	int i;
+
+	WARN_ON(ring->wptr % 2 || count % 2);
+
+	for (i = 0; i < count / 2; i++) {
+		amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE6));
+		amdgpu_ring_write(ring, 0);
+	}
+}
+
+static void vcn_v1_0_jpeg_ring_patch_wreg(struct amdgpu_ring *ring, uint32_t *ptr, uint32_t reg_offset, uint32_t val)
+{
+	struct amdgpu_device *adev = ring->adev;
+	ring->ring[(*ptr)++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0);
+	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
+		((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
+		ring->ring[(*ptr)++] = 0;
+		ring->ring[(*ptr)++] = PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0);
+	} else {
+		ring->ring[(*ptr)++] = reg_offset;
+		ring->ring[(*ptr)++] = PACKETJ(0, 0, 0, PACKETJ_TYPE0);
+	}
+	ring->ring[(*ptr)++] = val;
+}
+
+static void vcn_v1_0_jpeg_ring_set_patch_ring(struct amdgpu_ring *ring, uint32_t ptr)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	uint32_t reg, reg_offset, val, mask, i;
+
+	// 1st: program mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW
+	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW);
+	reg_offset = (reg << 2);
+	val = lower_32_bits(ring->gpu_addr);
+	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	// 2nd: program mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH
+	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH);
+	reg_offset = (reg << 2);
+	val = upper_32_bits(ring->gpu_addr);
+	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	// 3rd to 5th: issue MEM_READ commands
+	for (i = 0; i <= 2; i++) {
+		ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE2);
+		ring->ring[ptr++] = 0;
+	}
+
+	// 6th: program mmUVD_JRBC_RB_CNTL register to enable NO_FETCH and RPTR write ability
+	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_CNTL);
+	reg_offset = (reg << 2);
+	val = 0x13;
+	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	// 7th: program mmUVD_JRBC_RB_REF_DATA
+	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA);
+	reg_offset = (reg << 2);
+	val = 0x1;
+	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	// 8th: issue conditional register read mmUVD_JRBC_RB_CNTL
+	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_CNTL);
+	reg_offset = (reg << 2);
+	val = 0x1;
+	mask = 0x1;
+
+	ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0);
+	ring->ring[ptr++] = 0x01400200;
+	ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0);
+	ring->ring[ptr++] = val;
+	ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0);
+	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
+		((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
+		ring->ring[ptr++] = 0;
+		ring->ring[ptr++] = PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3);
+	} else {
+		ring->ring[ptr++] = reg_offset;
+		ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE3);
+	}
+	ring->ring[ptr++] = mask;
+
+	//9th to 21st: insert no-op
+	for (i = 0; i <= 12; i++) {
+		ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE6);
+		ring->ring[ptr++] = 0;
+	}
+
+	//22nd: reset mmUVD_JRBC_RB_RPTR
+	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_RPTR);
+	reg_offset = (reg << 2);
+	val = 0;
+	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	//23rd: program mmUVD_JRBC_RB_CNTL to disable no_fetch
+	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_CNTL);
+	reg_offset = (reg << 2);
+	val = 0x12;
+	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
+}
+
 static int vcn_v1_0_set_interrupt_state(struct amdgpu_device *adev,
 					struct amdgpu_irq_src *source,
 					unsigned type,
@@ -1150,6 +1567,9 @@ static int vcn_v1_0_process_interrupt(struct amdgpu_device *adev,
 	case 120:
 		amdgpu_fence_process(&adev->vcn.ring_enc[1]);
 		break;
+	case 126:
+		amdgpu_fence_process(&adev->vcn.ring_jpeg);
+		break;
 	default:
 		DRM_ERROR("Unhandled interrupt: %d %d\n",
 			  entry->src_id, entry->src_data[0]);
@@ -1273,6 +1693,39 @@ static const struct amdgpu_ring_funcs vcn_v1_0_enc_ring_vm_funcs = {
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };
 
+static const struct amdgpu_ring_funcs vcn_v1_0_jpeg_ring_vm_funcs = {
+	.type = AMDGPU_RING_TYPE_VCN_JPEG,
+	.align_mask = 0xf,
+	.nop = PACKET0(0x81ff, 0),
+	.support_64bit_ptrs = false,
+	.vmhub = AMDGPU_MMHUB,
+	.extra_dw = 64,
+	.get_rptr = vcn_v1_0_jpeg_ring_get_rptr,
+	.get_wptr = vcn_v1_0_jpeg_ring_get_wptr,
+	.set_wptr = vcn_v1_0_jpeg_ring_set_wptr,
+	.emit_frame_size =
+		6 + 6 + /* hdp invalidate / flush */
+		SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
+		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
+		8 + /* vcn_v1_0_dec_ring_emit_vm_flush */
+		14 + 14 + /* vcn_v1_0_dec_ring_emit_fence x2 vm fence */
+		6,
+	.emit_ib_size = 22, /* vcn_v1_0_dec_ring_emit_ib */
+	.emit_ib = vcn_v1_0_jpeg_ring_emit_ib,
+	.emit_fence = vcn_v1_0_jpeg_ring_emit_fence,
+	.emit_vm_flush = vcn_v1_0_jpeg_ring_emit_vm_flush,
+	.test_ring = amdgpu_vcn_jpeg_ring_test_ring,
+	.test_ib = amdgpu_vcn_jpeg_ring_test_ib,
+	.insert_nop = vcn_v1_0_jpeg_ring_nop,
+	.insert_start = vcn_v1_0_jpeg_ring_insert_start,
+	.insert_end = vcn_v1_0_jpeg_ring_insert_end,
+	.pad_ib = amdgpu_ring_generic_pad_ib,
+	.begin_use = amdgpu_vcn_ring_begin_use,
+	.end_use = amdgpu_vcn_ring_end_use,
+	.emit_wreg = vcn_v1_0_jpeg_ring_emit_wreg,
+	.emit_reg_wait = vcn_v1_0_jpeg_ring_emit_reg_wait,
+};
+
 static void vcn_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev)
 {
 	adev->vcn.ring_dec.funcs = &vcn_v1_0_dec_ring_vm_funcs;
@@ -1289,6 +1742,12 @@ static void vcn_v1_0_set_enc_ring_funcs(struct amdgpu_device *adev)
 	DRM_INFO("VCN encode is enabled in VM mode\n");
 }
 
+static void vcn_v1_0_set_jpeg_ring_funcs(struct amdgpu_device *adev)
+{
+	adev->vcn.ring_jpeg.funcs = &vcn_v1_0_jpeg_ring_vm_funcs;
+	DRM_INFO("VCN jpeg decode is enabled in VM mode\n");
+}
+
 static const struct amdgpu_irq_src_funcs vcn_v1_0_irq_funcs = {
 	.set = vcn_v1_0_set_interrupt_state,
 	.process = vcn_v1_0_process_interrupt,
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c b/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c
index 45aafca7f315..c5c9b2bc190d 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c
@@ -51,6 +51,7 @@ int vega10_reg_base_init(struct amdgpu_device *adev)
 		adev->reg_offset[PWR_HWIP][i] = (uint32_t *)(&(PWR_BASE.instance[i]));
 		adev->reg_offset[NBIF_HWIP][i] = (uint32_t *)(&(NBIF_BASE.instance[i]));
 		adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i]));
+		adev->reg_offset[CLK_HWIP][i] = (uint32_t *)(&(CLK_BASE.instance[i]));
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 4ac1288ab7df..42c8ad105b05 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1363,11 +1363,11 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
 
 	if (adev->cg_flags & (AMD_CG_SUPPORT_MC_LS | AMD_CG_SUPPORT_MC_MGCG)) {
 		if (adev->cg_flags & AMD_CG_SUPPORT_MC_LS) {
-			pp_support_state = AMD_CG_SUPPORT_MC_LS;
+			pp_support_state = PP_STATE_SUPPORT_LS;
 			pp_state = PP_STATE_LS;
 		}
 		if (adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG) {
-			pp_support_state |= AMD_CG_SUPPORT_MC_MGCG;
+			pp_support_state |= PP_STATE_SUPPORT_CG;
 			pp_state |= PP_STATE_CG;
 		}
 		if (state == AMD_CG_STATE_UNGATE)
@@ -1382,11 +1382,11 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
 
 	if (adev->cg_flags & (AMD_CG_SUPPORT_SDMA_LS | AMD_CG_SUPPORT_SDMA_MGCG)) {
 		if (adev->cg_flags & AMD_CG_SUPPORT_SDMA_LS) {
-			pp_support_state = AMD_CG_SUPPORT_SDMA_LS;
+			pp_support_state = PP_STATE_SUPPORT_LS;
 			pp_state = PP_STATE_LS;
 		}
 		if (adev->cg_flags & AMD_CG_SUPPORT_SDMA_MGCG) {
-			pp_support_state |= AMD_CG_SUPPORT_SDMA_MGCG;
+			pp_support_state |= PP_STATE_SUPPORT_CG;
 			pp_state |= PP_STATE_CG;
 		}
 		if (state == AMD_CG_STATE_UNGATE)
@@ -1401,11 +1401,11 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
 
 	if (adev->cg_flags & (AMD_CG_SUPPORT_HDP_LS | AMD_CG_SUPPORT_HDP_MGCG)) {
 		if (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS) {
-			pp_support_state = AMD_CG_SUPPORT_HDP_LS;
+			pp_support_state = PP_STATE_SUPPORT_LS;
 			pp_state = PP_STATE_LS;
 		}
 		if (adev->cg_flags & AMD_CG_SUPPORT_HDP_MGCG) {
-			pp_support_state |= AMD_CG_SUPPORT_HDP_MGCG;
+			pp_support_state |= PP_STATE_SUPPORT_CG;
 			pp_state |= PP_STATE_CG;
 		}
 		if (state == AMD_CG_STATE_UNGATE)
diff --git a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
index 49df6c791cfc..5d2475d5392c 100644
--- a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
@@ -25,12 +25,39 @@
 #include "cik_int.h"
 
 static bool cik_event_interrupt_isr(struct kfd_dev *dev,
-					const uint32_t *ih_ring_entry)
+					const uint32_t *ih_ring_entry,
+					uint32_t *patched_ihre,
+					bool *patched_flag)
 {
 	const struct cik_ih_ring_entry *ihre =
 			(const struct cik_ih_ring_entry *)ih_ring_entry;
+	const struct kfd2kgd_calls *f2g = dev->kfd2kgd;
 	unsigned int vmid, pasid;
 
+	/* This workaround is due to HW/FW limitation on Hawaii that
+	 * VMID and PASID are not written into ih_ring_entry
+	 */
+	if ((ihre->source_id == CIK_INTSRC_GFX_PAGE_INV_FAULT ||
+		ihre->source_id == CIK_INTSRC_GFX_MEM_PROT_FAULT) &&
+		dev->device_info->asic_family == CHIP_HAWAII) {
+		struct cik_ih_ring_entry *tmp_ihre =
+			(struct cik_ih_ring_entry *)patched_ihre;
+
+		*patched_flag = true;
+		*tmp_ihre = *ihre;
+
+		vmid = f2g->read_vmid_from_vmfault_reg(dev->kgd);
+		pasid = f2g->get_atc_vmid_pasid_mapping_pasid(dev->kgd, vmid);
+
+		tmp_ihre->ring_id &= 0x000000ff;
+		tmp_ihre->ring_id |= vmid << 8;
+		tmp_ihre->ring_id |= pasid << 16;
+
+		return (pasid != 0) &&
+			vmid >= dev->vm_info.first_vmid_kfd &&
+			vmid <= dev->vm_info.last_vmid_kfd;
+	}
+
 	/* Only handle interrupts from KFD VMIDs */
 	vmid  = (ihre->ring_id & 0x0000ff00) >> 8;
 	if (vmid < dev->vm_info.first_vmid_kfd ||
@@ -48,18 +75,19 @@ static bool cik_event_interrupt_isr(struct kfd_dev *dev,
 	return ihre->source_id == CIK_INTSRC_CP_END_OF_PIPE ||
 		ihre->source_id == CIK_INTSRC_SDMA_TRAP ||
 		ihre->source_id == CIK_INTSRC_SQ_INTERRUPT_MSG ||
-		ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE;
+		ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE ||
+		ihre->source_id == CIK_INTSRC_GFX_PAGE_INV_FAULT ||
+		ihre->source_id == CIK_INTSRC_GFX_MEM_PROT_FAULT;
 }
 
 static void cik_event_interrupt_wq(struct kfd_dev *dev,
 					const uint32_t *ih_ring_entry)
 {
-	unsigned int pasid;
 	const struct cik_ih_ring_entry *ihre =
 			(const struct cik_ih_ring_entry *)ih_ring_entry;
 	uint32_t context_id = ihre->data & 0xfffffff;
-
-	pasid = (ihre->ring_id & 0xffff0000) >> 16;
+	unsigned int vmid  = (ihre->ring_id & 0x0000ff00) >> 8;
+	unsigned int pasid = (ihre->ring_id & 0xffff0000) >> 16;
 
 	if (pasid == 0)
 		return;
@@ -72,6 +100,22 @@ static void cik_event_interrupt_wq(struct kfd_dev *dev,
 		kfd_signal_event_interrupt(pasid, context_id & 0xff, 8);
 	else if (ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE)
 		kfd_signal_hw_exception_event(pasid);
+	else if (ihre->source_id == CIK_INTSRC_GFX_PAGE_INV_FAULT ||
+		ihre->source_id == CIK_INTSRC_GFX_MEM_PROT_FAULT) {
+		struct kfd_vm_fault_info info;
+
+		kfd_process_vm_fault(dev->dqm, pasid);
+
+		memset(&info, 0, sizeof(info));
+		dev->kfd2kgd->get_vm_fault_info(dev->kgd, &info);
+		if (!info.page_addr && !info.status)
+			return;
+
+		if (info.vmid == vmid)
+			kfd_signal_vm_fault_event(dev, pasid, &info);
+		else
+			kfd_signal_vm_fault_event(dev, pasid, NULL);
+	}
 }
 
 const struct kfd_event_interrupt_class event_interrupt_class_cik = {
diff --git a/drivers/gpu/drm/amd/amdkfd/cik_int.h b/drivers/gpu/drm/amd/amdkfd/cik_int.h
index 109298b9d507..76f8677a7926 100644
--- a/drivers/gpu/drm/amd/amdkfd/cik_int.h
+++ b/drivers/gpu/drm/amd/amdkfd/cik_int.h
@@ -20,8 +20,8 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 
-#ifndef HSA_RADEON_CIK_INT_H_INCLUDED
-#define HSA_RADEON_CIK_INT_H_INCLUDED
+#ifndef CIK_INT_H_INCLUDED
+#define CIK_INT_H_INCLUDED
 
 #include <linux/types.h>
 
@@ -34,9 +34,10 @@ struct cik_ih_ring_entry {
 
 #define CIK_INTSRC_CP_END_OF_PIPE	0xB5
 #define CIK_INTSRC_CP_BAD_OPCODE	0xB7
-#define CIK_INTSRC_DEQUEUE_COMPLETE	0xC6
 #define CIK_INTSRC_SDMA_TRAP		0xE0
 #define CIK_INTSRC_SQ_INTERRUPT_MSG	0xEF
+#define CIK_INTSRC_GFX_PAGE_INV_FAULT	0x92
+#define CIK_INTSRC_GFX_MEM_PROT_FAULT	0x93
 
 #endif
 
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
index f68aef02fc1f..3621efbd5759 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -21,18 +21,21 @@
  */
 
 static const uint32_t cwsr_trap_gfx8_hex[] = {
-	0xbf820001, 0xbf820125,
+	0xbf820001, 0xbf82012b,
 	0xb8f4f802, 0x89748674,
 	0xb8f5f803, 0x8675ff75,
-	0x00000400, 0xbf850011,
+	0x00000400, 0xbf850017,
 	0xc00a1e37, 0x00000000,
 	0xbf8c007f, 0x87777978,
-	0xbf840002, 0xb974f802,
-	0xbe801d78, 0xb8f5f803,
-	0x8675ff75, 0x000001ff,
-	0xbf850002, 0x80708470,
-	0x82718071, 0x8671ff71,
-	0x0000ffff, 0xb974f802,
+	0xbf840005, 0x8f728374,
+	0xb972e0c2, 0xbf800002,
+	0xb9740002, 0xbe801d78,
+	0xb8f5f803, 0x8675ff75,
+	0x000001ff, 0xbf850002,
+	0x80708470, 0x82718071,
+	0x8671ff71, 0x0000ffff,
+	0x8f728374, 0xb972e0c2,
+	0xbf800002, 0xb9740002,
 	0xbe801f70, 0xb8f5f803,
 	0x8675ff75, 0x00000100,
 	0xbf840006, 0xbefa0080,
@@ -168,7 +171,7 @@ static const uint32_t cwsr_trap_gfx8_hex[] = {
 	0x807c847c, 0x806eff6e,
 	0x00000400, 0xbf0a757c,
 	0xbf85ffef, 0xbf9c0000,
-	0xbf8200ca, 0xbef8007e,
+	0xbf8200cd, 0xbef8007e,
 	0x8679ff7f, 0x0000ffff,
 	0x8779ff79, 0x00040000,
 	0xbefa0080, 0xbefb00ff,
@@ -268,16 +271,18 @@ static const uint32_t cwsr_trap_gfx8_hex[] = {
 	0x8f739773, 0xb976f807,
 	0x8671ff71, 0x0000ffff,
 	0x86fe7e7e, 0x86ea6a6a,
-	0xb974f802, 0xbf8a0000,
-	0x95807370, 0xbf810000,
+	0x8f768374, 0xb976e0c2,
+	0xbf800002, 0xb9740002,
+	0xbf8a0000, 0x95807370,
+	0xbf810000, 0x00000000,
 };
 
 
 static const uint32_t cwsr_trap_gfx9_hex[] = {
-	0xbf820001, 0xbf82015a,
+	0xbf820001, 0xbf82015d,
 	0xb8f8f802, 0x89788678,
 	0xb8f1f803, 0x866eff71,
-	0x00000400, 0xbf850034,
+	0x00000400, 0xbf850037,
 	0x866eff71, 0x00000800,
 	0xbf850003, 0x866eff71,
 	0x00000100, 0xbf840008,
@@ -303,258 +308,261 @@ static const uint32_t cwsr_trap_gfx9_hex[] = {
 	0x8f6e8b77, 0x866eff6e,
 	0x001f8000, 0xb96ef807,
 	0x86fe7e7e, 0x86ea6a6a,
-	0xb978f802, 0xbe801f6c,
-	0x866dff6d, 0x0000ffff,
-	0xbef00080, 0xb9700283,
-	0xb8f02407, 0x8e709c70,
-	0x876d706d, 0xb8f003c7,
-	0x8e709b70, 0x876d706d,
-	0xb8f0f807, 0x8670ff70,
-	0x00007fff, 0xb970f807,
-	0xbeee007e, 0xbeef007f,
-	0xbefe0180, 0xbf900004,
-	0x87708478, 0xb970f802,
-	0xbf8e0002, 0xbf88fffe,
-	0xb8f02a05, 0x80708170,
-	0x8e708a70, 0xb8f11605,
-	0x80718171, 0x8e718671,
-	0x80707170, 0x80707e70,
-	0x8271807f, 0x8671ff71,
-	0x0000ffff, 0xc0471cb8,
-	0x00000040, 0xbf8cc07f,
-	0xc04b1d38, 0x00000048,
-	0xbf8cc07f, 0xc0431e78,
-	0x00000058, 0xbf8cc07f,
-	0xc0471eb8, 0x0000005c,
-	0xbf8cc07f, 0xbef4007e,
-	0x8675ff7f, 0x0000ffff,
-	0x8775ff75, 0x00040000,
-	0xbef60080, 0xbef700ff,
-	0x00807fac, 0x8670ff7f,
-	0x08000000, 0x8f708370,
-	0x87777077, 0x8670ff7f,
-	0x70000000, 0x8f708170,
-	0x87777077, 0xbefb007c,
-	0xbefa0080, 0xb8fa2a05,
-	0x807a817a, 0x8e7a8a7a,
-	0xb8f01605, 0x80708170,
-	0x8e708670, 0x807a707a,
-	0xbef60084, 0xbef600ff,
-	0x01000000, 0xbefe007c,
-	0xbefc007a, 0xc0611efa,
-	0x0000007c, 0xbf8cc07f,
-	0x807a847a, 0xbefc007e,
+	0x8f6e8378, 0xb96ee0c2,
+	0xbf800002, 0xb9780002,
+	0xbe801f6c, 0x866dff6d,
+	0x0000ffff, 0xbef00080,
+	0xb9700283, 0xb8f02407,
+	0x8e709c70, 0x876d706d,
+	0xb8f003c7, 0x8e709b70,
+	0x876d706d, 0xb8f0f807,
+	0x8670ff70, 0x00007fff,
+	0xb970f807, 0xbeee007e,
+	0xbeef007f, 0xbefe0180,
+	0xbf900004, 0x87708478,
+	0xb970f802, 0xbf8e0002,
+	0xbf88fffe, 0xb8f02a05,
+	0x80708170, 0x8e708a70,
+	0xb8f11605, 0x80718171,
+	0x8e718671, 0x80707170,
+	0x80707e70, 0x8271807f,
+	0x8671ff71, 0x0000ffff,
+	0xc0471cb8, 0x00000040,
+	0xbf8cc07f, 0xc04b1d38,
+	0x00000048, 0xbf8cc07f,
+	0xc0431e78, 0x00000058,
+	0xbf8cc07f, 0xc0471eb8,
+	0x0000005c, 0xbf8cc07f,
+	0xbef4007e, 0x8675ff7f,
+	0x0000ffff, 0x8775ff75,
+	0x00040000, 0xbef60080,
+	0xbef700ff, 0x00807fac,
+	0x8670ff7f, 0x08000000,
+	0x8f708370, 0x87777077,
+	0x8670ff7f, 0x70000000,
+	0x8f708170, 0x87777077,
+	0xbefb007c, 0xbefa0080,
+	0xb8fa2a05, 0x807a817a,
+	0x8e7a8a7a, 0xb8f01605,
+	0x80708170, 0x8e708670,
+	0x807a707a, 0xbef60084,
+	0xbef600ff, 0x01000000,
 	0xbefe007c, 0xbefc007a,
-	0xc0611b3a, 0x0000007c,
+	0xc0611efa, 0x0000007c,
 	0xbf8cc07f, 0x807a847a,
 	0xbefc007e, 0xbefe007c,
-	0xbefc007a, 0xc0611b7a,
+	0xbefc007a, 0xc0611b3a,
 	0x0000007c, 0xbf8cc07f,
 	0x807a847a, 0xbefc007e,
 	0xbefe007c, 0xbefc007a,
-	0xc0611bba, 0x0000007c,
+	0xc0611b7a, 0x0000007c,
 	0xbf8cc07f, 0x807a847a,
 	0xbefc007e, 0xbefe007c,
-	0xbefc007a, 0xc0611bfa,
+	0xbefc007a, 0xc0611bba,
 	0x0000007c, 0xbf8cc07f,
 	0x807a847a, 0xbefc007e,
 	0xbefe007c, 0xbefc007a,
-	0xc0611e3a, 0x0000007c,
-	0xbf8cc07f, 0x807a847a,
-	0xbefc007e, 0xb8f1f803,
-	0xbefe007c, 0xbefc007a,
-	0xc0611c7a, 0x0000007c,
+	0xc0611bfa, 0x0000007c,
 	0xbf8cc07f, 0x807a847a,
 	0xbefc007e, 0xbefe007c,
-	0xbefc007a, 0xc0611a3a,
+	0xbefc007a, 0xc0611e3a,
+	0x0000007c, 0xbf8cc07f,
+	0x807a847a, 0xbefc007e,
+	0xb8f1f803, 0xbefe007c,
+	0xbefc007a, 0xc0611c7a,
 	0x0000007c, 0xbf8cc07f,
 	0x807a847a, 0xbefc007e,
 	0xbefe007c, 0xbefc007a,
-	0xc0611a7a, 0x0000007c,
-	0xbf8cc07f, 0x807a847a,
-	0xbefc007e, 0xb8fbf801,
-	0xbefe007c, 0xbefc007a,
-	0xc0611efa, 0x0000007c,
+	0xc0611a3a, 0x0000007c,
 	0xbf8cc07f, 0x807a847a,
-	0xbefc007e, 0x8670ff7f,
-	0x04000000, 0xbeef0080,
-	0x876f6f70, 0xb8fa2a05,
+	0xbefc007e, 0xbefe007c,
+	0xbefc007a, 0xc0611a7a,
+	0x0000007c, 0xbf8cc07f,
+	0x807a847a, 0xbefc007e,
+	0xb8fbf801, 0xbefe007c,
+	0xbefc007a, 0xc0611efa,
+	0x0000007c, 0xbf8cc07f,
+	0x807a847a, 0xbefc007e,
+	0x8670ff7f, 0x04000000,
+	0xbeef0080, 0x876f6f70,
+	0xb8fa2a05, 0x807a817a,
+	0x8e7a8a7a, 0xb8f11605,
+	0x80718171, 0x8e718471,
+	0x8e768271, 0xbef600ff,
+	0x01000000, 0xbef20174,
+	0x80747a74, 0x82758075,
+	0xbefc0080, 0xbf800000,
+	0xbe802b00, 0xbe822b02,
+	0xbe842b04, 0xbe862b06,
+	0xbe882b08, 0xbe8a2b0a,
+	0xbe8c2b0c, 0xbe8e2b0e,
+	0xc06b003a, 0x00000000,
+	0xbf8cc07f, 0xc06b013a,
+	0x00000010, 0xbf8cc07f,
+	0xc06b023a, 0x00000020,
+	0xbf8cc07f, 0xc06b033a,
+	0x00000030, 0xbf8cc07f,
+	0x8074c074, 0x82758075,
+	0x807c907c, 0xbf0a717c,
+	0xbf85ffe7, 0xbef40172,
+	0xbefa0080, 0xbefe00c1,
+	0xbeff00c1, 0xbee80080,
+	0xbee90080, 0xbef600ff,
+	0x01000000, 0xe0724000,
+	0x7a1d0000, 0xe0724100,
+	0x7a1d0100, 0xe0724200,
+	0x7a1d0200, 0xe0724300,
+	0x7a1d0300, 0xbefe00c1,
+	0xbeff00c1, 0xb8f14306,
+	0x8671c171, 0xbf84002c,
+	0xbf8a0000, 0x8670ff6f,
+	0x04000000, 0xbf840028,
+	0x8e718671, 0x8e718271,
+	0xbef60071, 0xb8fa2a05,
 	0x807a817a, 0x8e7a8a7a,
-	0xb8f11605, 0x80718171,
-	0x8e718471, 0x8e768271,
+	0xb8f01605, 0x80708170,
+	0x8e708670, 0x807a707a,
+	0x807aff7a, 0x00000080,
 	0xbef600ff, 0x01000000,
-	0xbef20174, 0x80747a74,
-	0x82758075, 0xbefc0080,
-	0xbf800000, 0xbe802b00,
-	0xbe822b02, 0xbe842b04,
-	0xbe862b06, 0xbe882b08,
-	0xbe8a2b0a, 0xbe8c2b0c,
-	0xbe8e2b0e, 0xc06b003a,
-	0x00000000, 0xbf8cc07f,
-	0xc06b013a, 0x00000010,
-	0xbf8cc07f, 0xc06b023a,
-	0x00000020, 0xbf8cc07f,
-	0xc06b033a, 0x00000030,
-	0xbf8cc07f, 0x8074c074,
-	0x82758075, 0x807c907c,
-	0xbf0a717c, 0xbf85ffe7,
-	0xbef40172, 0xbefa0080,
+	0xbefc0080, 0xd28c0002,
+	0x000100c1, 0xd28d0003,
+	0x000204c1, 0xd1060002,
+	0x00011103, 0x7e0602ff,
+	0x00000200, 0xbefc00ff,
+	0x00010000, 0xbe800077,
+	0x8677ff77, 0xff7fffff,
+	0x8777ff77, 0x00058000,
+	0xd8ec0000, 0x00000002,
+	0xbf8cc07f, 0xe0765000,
+	0x7a1d0002, 0x68040702,
+	0xd0c9006a, 0x0000e302,
+	0xbf87fff7, 0xbef70000,
+	0xbefa00ff, 0x00000400,
 	0xbefe00c1, 0xbeff00c1,
-	0xbee80080, 0xbee90080,
+	0xb8f12a05, 0x80718171,
+	0x8e718271, 0x8e768871,
 	0xbef600ff, 0x01000000,
+	0xbefc0084, 0xbf0a717c,
+	0xbf840015, 0xbf11017c,
+	0x8071ff71, 0x00001000,
+	0x7e000300, 0x7e020301,
+	0x7e040302, 0x7e060303,
 	0xe0724000, 0x7a1d0000,
 	0xe0724100, 0x7a1d0100,
 	0xe0724200, 0x7a1d0200,
 	0xe0724300, 0x7a1d0300,
+	0x807c847c, 0x807aff7a,
+	0x00000400, 0xbf0a717c,
+	0xbf85ffef, 0xbf9c0000,
+	0xbf8200dc, 0xbef4007e,
+	0x8675ff7f, 0x0000ffff,
+	0x8775ff75, 0x00040000,
+	0xbef60080, 0xbef700ff,
+	0x00807fac, 0x866eff7f,
+	0x08000000, 0x8f6e836e,
+	0x87776e77, 0x866eff7f,
+	0x70000000, 0x8f6e816e,
+	0x87776e77, 0x866eff7f,
+	0x04000000, 0xbf84001e,
 	0xbefe00c1, 0xbeff00c1,
-	0xb8f14306, 0x8671c171,
-	0xbf84002c, 0xbf8a0000,
-	0x8670ff6f, 0x04000000,
-	0xbf840028, 0x8e718671,
-	0x8e718271, 0xbef60071,
-	0xb8fa2a05, 0x807a817a,
-	0x8e7a8a7a, 0xb8f01605,
-	0x80708170, 0x8e708670,
-	0x807a707a, 0x807aff7a,
+	0xb8ef4306, 0x866fc16f,
+	0xbf840019, 0x8e6f866f,
+	0x8e6f826f, 0xbef6006f,
+	0xb8f82a05, 0x80788178,
+	0x8e788a78, 0xb8ee1605,
+	0x806e816e, 0x8e6e866e,
+	0x80786e78, 0x8078ff78,
 	0x00000080, 0xbef600ff,
 	0x01000000, 0xbefc0080,
-	0xd28c0002, 0x000100c1,
-	0xd28d0003, 0x000204c1,
-	0xd1060002, 0x00011103,
-	0x7e0602ff, 0x00000200,
-	0xbefc00ff, 0x00010000,
-	0xbe800077, 0x8677ff77,
-	0xff7fffff, 0x8777ff77,
-	0x00058000, 0xd8ec0000,
-	0x00000002, 0xbf8cc07f,
-	0xe0765000, 0x7a1d0002,
-	0x68040702, 0xd0c9006a,
-	0x0000e302, 0xbf87fff7,
-	0xbef70000, 0xbefa00ff,
-	0x00000400, 0xbefe00c1,
-	0xbeff00c1, 0xb8f12a05,
-	0x80718171, 0x8e718271,
-	0x8e768871, 0xbef600ff,
-	0x01000000, 0xbefc0084,
-	0xbf0a717c, 0xbf840015,
-	0xbf11017c, 0x8071ff71,
-	0x00001000, 0x7e000300,
+	0xe0510000, 0x781d0000,
+	0xe0510100, 0x781d0000,
+	0x807cff7c, 0x00000200,
+	0x8078ff78, 0x00000200,
+	0xbf0a6f7c, 0xbf85fff6,
+	0xbef80080, 0xbefe00c1,
+	0xbeff00c1, 0xb8ef2a05,
+	0x806f816f, 0x8e6f826f,
+	0x8e76886f, 0xbef600ff,
+	0x01000000, 0xbeee0078,
+	0x8078ff78, 0x00000400,
+	0xbefc0084, 0xbf11087c,
+	0x806fff6f, 0x00008000,
+	0xe0524000, 0x781d0000,
+	0xe0524100, 0x781d0100,
+	0xe0524200, 0x781d0200,
+	0xe0524300, 0x781d0300,
+	0xbf8c0f70, 0x7e000300,
 	0x7e020301, 0x7e040302,
-	0x7e060303, 0xe0724000,
-	0x7a1d0000, 0xe0724100,
-	0x7a1d0100, 0xe0724200,
-	0x7a1d0200, 0xe0724300,
-	0x7a1d0300, 0x807c847c,
-	0x807aff7a, 0x00000400,
-	0xbf0a717c, 0xbf85ffef,
-	0xbf9c0000, 0xbf8200d9,
-	0xbef4007e, 0x8675ff7f,
-	0x0000ffff, 0x8775ff75,
-	0x00040000, 0xbef60080,
-	0xbef700ff, 0x00807fac,
-	0x866eff7f, 0x08000000,
-	0x8f6e836e, 0x87776e77,
-	0x866eff7f, 0x70000000,
-	0x8f6e816e, 0x87776e77,
-	0x866eff7f, 0x04000000,
-	0xbf84001e, 0xbefe00c1,
-	0xbeff00c1, 0xb8ef4306,
-	0x866fc16f, 0xbf840019,
-	0x8e6f866f, 0x8e6f826f,
-	0xbef6006f, 0xb8f82a05,
+	0x7e060303, 0x807c847c,
+	0x8078ff78, 0x00000400,
+	0xbf0a6f7c, 0xbf85ffee,
+	0xbf9c0000, 0xe0524000,
+	0x6e1d0000, 0xe0524100,
+	0x6e1d0100, 0xe0524200,
+	0x6e1d0200, 0xe0524300,
+	0x6e1d0300, 0xb8f82a05,
 	0x80788178, 0x8e788a78,
 	0xb8ee1605, 0x806e816e,
 	0x8e6e866e, 0x80786e78,
-	0x8078ff78, 0x00000080,
-	0xbef600ff, 0x01000000,
-	0xbefc0080, 0xe0510000,
-	0x781d0000, 0xe0510100,
-	0x781d0000, 0x807cff7c,
-	0x00000200, 0x8078ff78,
-	0x00000200, 0xbf0a6f7c,
-	0xbf85fff6, 0xbef80080,
-	0xbefe00c1, 0xbeff00c1,
-	0xb8ef2a05, 0x806f816f,
-	0x8e6f826f, 0x8e76886f,
-	0xbef600ff, 0x01000000,
-	0xbeee0078, 0x8078ff78,
-	0x00000400, 0xbefc0084,
-	0xbf11087c, 0x806fff6f,
-	0x00008000, 0xe0524000,
-	0x781d0000, 0xe0524100,
-	0x781d0100, 0xe0524200,
-	0x781d0200, 0xe0524300,
-	0x781d0300, 0xbf8c0f70,
-	0x7e000300, 0x7e020301,
-	0x7e040302, 0x7e060303,
-	0x807c847c, 0x8078ff78,
-	0x00000400, 0xbf0a6f7c,
-	0xbf85ffee, 0xbf9c0000,
-	0xe0524000, 0x6e1d0000,
-	0xe0524100, 0x6e1d0100,
-	0xe0524200, 0x6e1d0200,
-	0xe0524300, 0x6e1d0300,
+	0x80f8c078, 0xb8ef1605,
+	0x806f816f, 0x8e6f846f,
+	0x8e76826f, 0xbef600ff,
+	0x01000000, 0xbefc006f,
+	0xc031003a, 0x00000078,
+	0x80f8c078, 0xbf8cc07f,
+	0x80fc907c, 0xbf800000,
+	0xbe802d00, 0xbe822d02,
+	0xbe842d04, 0xbe862d06,
+	0xbe882d08, 0xbe8a2d0a,
+	0xbe8c2d0c, 0xbe8e2d0e,
+	0xbf06807c, 0xbf84fff0,
 	0xb8f82a05, 0x80788178,
 	0x8e788a78, 0xb8ee1605,
 	0x806e816e, 0x8e6e866e,
-	0x80786e78, 0x80f8c078,
-	0xb8ef1605, 0x806f816f,
-	0x8e6f846f, 0x8e76826f,
+	0x80786e78, 0xbef60084,
 	0xbef600ff, 0x01000000,
-	0xbefc006f, 0xc031003a,
-	0x00000078, 0x80f8c078,
-	0xbf8cc07f, 0x80fc907c,
-	0xbf800000, 0xbe802d00,
-	0xbe822d02, 0xbe842d04,
-	0xbe862d06, 0xbe882d08,
-	0xbe8a2d0a, 0xbe8c2d0c,
-	0xbe8e2d0e, 0xbf06807c,
-	0xbf84fff0, 0xb8f82a05,
-	0x80788178, 0x8e788a78,
-	0xb8ee1605, 0x806e816e,
-	0x8e6e866e, 0x80786e78,
-	0xbef60084, 0xbef600ff,
-	0x01000000, 0xc0211bfa,
+	0xc0211bfa, 0x00000078,
+	0x80788478, 0xc0211b3a,
 	0x00000078, 0x80788478,
-	0xc0211b3a, 0x00000078,
-	0x80788478, 0xc0211b7a,
+	0xc0211b7a, 0x00000078,
+	0x80788478, 0xc0211eba,
 	0x00000078, 0x80788478,
-	0xc0211eba, 0x00000078,
-	0x80788478, 0xc0211efa,
+	0xc0211efa, 0x00000078,
+	0x80788478, 0xc0211c3a,
 	0x00000078, 0x80788478,
-	0xc0211c3a, 0x00000078,
-	0x80788478, 0xc0211c7a,
+	0xc0211c7a, 0x00000078,
+	0x80788478, 0xc0211a3a,
 	0x00000078, 0x80788478,
-	0xc0211a3a, 0x00000078,
-	0x80788478, 0xc0211a7a,
+	0xc0211a7a, 0x00000078,
+	0x80788478, 0xc0211cfa,
 	0x00000078, 0x80788478,
-	0xc0211cfa, 0x00000078,
-	0x80788478, 0xbf8cc07f,
-	0xbefc006f, 0xbefe007a,
-	0xbeff007b, 0x866f71ff,
-	0x000003ff, 0xb96f4803,
-	0x866f71ff, 0xfffff800,
-	0x8f6f8b6f, 0xb96fa2c3,
-	0xb973f801, 0xb8ee2a05,
-	0x806e816e, 0x8e6e8a6e,
-	0xb8ef1605, 0x806f816f,
-	0x8e6f866f, 0x806e6f6e,
-	0x806e746e, 0x826f8075,
-	0x866fff6f, 0x0000ffff,
-	0xc0071cb7, 0x00000040,
-	0xc00b1d37, 0x00000048,
-	0xc0031e77, 0x00000058,
-	0xc0071eb7, 0x0000005c,
-	0xbf8cc07f, 0x866fff6d,
-	0xf0000000, 0x8f6f9c6f,
-	0x8e6f906f, 0xbeee0080,
-	0x876e6f6e, 0x866fff6d,
-	0x08000000, 0x8f6f9b6f,
-	0x8e6f8f6f, 0x876e6f6e,
-	0x866fff70, 0x00800000,
-	0x8f6f976f, 0xb96ef807,
-	0x866dff6d, 0x0000ffff,
-	0x86fe7e7e, 0x86ea6a6a,
-	0xb970f802, 0xbf8a0000,
+	0xbf8cc07f, 0xbefc006f,
+	0xbefe007a, 0xbeff007b,
+	0x866f71ff, 0x000003ff,
+	0xb96f4803, 0x866f71ff,
+	0xfffff800, 0x8f6f8b6f,
+	0xb96fa2c3, 0xb973f801,
+	0xb8ee2a05, 0x806e816e,
+	0x8e6e8a6e, 0xb8ef1605,
+	0x806f816f, 0x8e6f866f,
+	0x806e6f6e, 0x806e746e,
+	0x826f8075, 0x866fff6f,
+	0x0000ffff, 0xc0071cb7,
+	0x00000040, 0xc00b1d37,
+	0x00000048, 0xc0031e77,
+	0x00000058, 0xc0071eb7,
+	0x0000005c, 0xbf8cc07f,
+	0x866fff6d, 0xf0000000,
+	0x8f6f9c6f, 0x8e6f906f,
+	0xbeee0080, 0x876e6f6e,
+	0x866fff6d, 0x08000000,
+	0x8f6f9b6f, 0x8e6f8f6f,
+	0x876e6f6e, 0x866fff70,
+	0x00800000, 0x8f6f976f,
+	0xb96ef807, 0x866dff6d,
+	0x0000ffff, 0x86fe7e7e,
+	0x86ea6a6a, 0x8f6e8370,
+	0xb96ee0c2, 0xbf800002,
+	0xb9700002, 0xbf8a0000,
 	0x95806f6c, 0xbf810000,
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm
index a2a04bb64096..abe1a5da29fb 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm
@@ -103,6 +103,10 @@ var SQ_WAVE_STATUS_INST_ATC_SHIFT  = 23
 var SQ_WAVE_STATUS_INST_ATC_MASK   = 0x00800000
 var SQ_WAVE_STATUS_SPI_PRIO_SHIFT  = 1
 var SQ_WAVE_STATUS_SPI_PRIO_MASK   = 0x00000006
+var SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT   = 0
+var SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE    = 1
+var SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT  = 3
+var SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE   = 29
 
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT    = 12
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE     = 9
@@ -251,7 +255,7 @@ if (!EMU_RUN_HACK)
     s_waitcnt lgkmcnt(0)
     s_or_b32        ttmp7, ttmp8, ttmp9
     s_cbranch_scc0  L_NO_NEXT_TRAP //next level trap handler not been set
-    s_setreg_b32    hwreg(HW_REG_STATUS), s_save_status //restore HW status(SCC)
+    set_status_without_spi_prio(s_save_status, ttmp2) //restore HW status(SCC)
     s_setpc_b64     [ttmp8,ttmp9] //jump to next level trap handler
 
 L_NO_NEXT_TRAP:
@@ -262,7 +266,7 @@ L_NO_NEXT_TRAP:
     s_addc_u32  ttmp1, ttmp1, 0
 L_EXCP_CASE:
     s_and_b32   ttmp1, ttmp1, 0xFFFF
-    s_setreg_b32    hwreg(HW_REG_STATUS), s_save_status //restore HW status(SCC)
+    set_status_without_spi_prio(s_save_status, ttmp2) //restore HW status(SCC)
     s_rfe_b64       [ttmp0, ttmp1]
 end
     // *********        End handling of non-CWSR traps   *******************
@@ -1053,7 +1057,7 @@ end
     s_and_b32 s_restore_pc_hi, s_restore_pc_hi, 0x0000ffff      //pc[47:32]        //Do it here in order not to affect STATUS
     s_and_b64    exec, exec, exec  // Restore STATUS.EXECZ, not writable by s_setreg_b32
     s_and_b64    vcc, vcc, vcc  // Restore STATUS.VCCZ, not writable by s_setreg_b32
-    s_setreg_b32    hwreg(HW_REG_STATUS),   s_restore_status     // SCC is included, which is changed by previous salu
+    set_status_without_spi_prio(s_restore_status, s_restore_tmp) // SCC is included, which is changed by previous salu
 
     s_barrier                                                   //barrier to ensure the readiness of LDS before access attempts from any other wave in the same TG //FIXME not performance-optimal at this time
 
@@ -1134,3 +1138,11 @@ end
 function get_hwreg_size_bytes
     return 128 //HWREG size 128 bytes
 end
+
+function set_status_without_spi_prio(status, tmp)
+    // Do not restore STATUS.SPI_PRIO since scheduler may have raised it.
+    s_lshr_b32      tmp, status, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT
+    s_setreg_b32    hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE), tmp
+    s_nop           0x2 // avoid S_SETREG => S_SETREG hazard
+    s_setreg_b32    hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE), status
+end
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
index 998be96be736..0bb9c577b3a2 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
@@ -103,6 +103,10 @@ var SQ_WAVE_STATUS_INST_ATC_MASK   = 0x00800000
 var SQ_WAVE_STATUS_SPI_PRIO_SHIFT  = 1
 var SQ_WAVE_STATUS_SPI_PRIO_MASK   = 0x00000006
 var SQ_WAVE_STATUS_HALT_MASK       = 0x2000
+var SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT   = 0
+var SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE    = 1
+var SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT  = 3
+var SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE   = 29
 
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT	= 12
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE	= 9
@@ -317,7 +321,7 @@ L_EXCP_CASE:
     // Restore SQ_WAVE_STATUS.
     s_and_b64       exec, exec, exec // Restore STATUS.EXECZ, not writable by s_setreg_b32
     s_and_b64       vcc, vcc, vcc    // Restore STATUS.VCCZ, not writable by s_setreg_b32
-    s_setreg_b32    hwreg(HW_REG_STATUS), s_save_status
+    set_status_without_spi_prio(s_save_status, ttmp2)
 
     s_rfe_b64       [ttmp0, ttmp1]
 end
@@ -1120,7 +1124,7 @@ end
     s_and_b32 s_restore_pc_hi, s_restore_pc_hi, 0x0000ffff	//pc[47:32]	   //Do it here in order not to affect STATUS
     s_and_b64	 exec, exec, exec  // Restore STATUS.EXECZ, not writable by s_setreg_b32
     s_and_b64	 vcc, vcc, vcc	// Restore STATUS.VCCZ, not writable by s_setreg_b32
-    s_setreg_b32    hwreg(HW_REG_STATUS),   s_restore_status	 // SCC is included, which is changed by previous salu
+    set_status_without_spi_prio(s_restore_status, s_restore_tmp) // SCC is included, which is changed by previous salu
 
     s_barrier							//barrier to ensure the readiness of LDS before access attempts from any other wave in the same TG //FIXME not performance-optimal at this time
 
@@ -1212,3 +1216,11 @@ function ack_sqc_store_workaround
         s_waitcnt lgkmcnt(0)
     end
 end
+
+function set_status_without_spi_prio(status, tmp)
+    // Do not restore STATUS.SPI_PRIO since scheduler may have raised it.
+    s_lshr_b32      tmp, status, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT
+    s_setreg_b32    hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE), tmp
+    s_nop           0x2 // avoid S_SETREG => S_SETREG hazard
+    s_setreg_b32    hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE), status
+end
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index f64c5551cdba..297b36c26a05 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -122,6 +122,9 @@ static int kfd_open(struct inode *inode, struct file *filep)
 	if (IS_ERR(process))
 		return PTR_ERR(process);
 
+	if (kfd_is_locked())
+		return -EAGAIN;
+
 	dev_dbg(kfd_device, "process %d opened, compat mode (32 bit) - %d\n",
 		process->pasid, process->is_32bit_user_mode);
 
@@ -389,6 +392,61 @@ static int kfd_ioctl_update_queue(struct file *filp, struct kfd_process *p,
 	return retval;
 }
 
+static int kfd_ioctl_set_cu_mask(struct file *filp, struct kfd_process *p,
+					void *data)
+{
+	int retval;
+	const int max_num_cus = 1024;
+	struct kfd_ioctl_set_cu_mask_args *args = data;
+	struct queue_properties properties;
+	uint32_t __user *cu_mask_ptr = (uint32_t __user *)args->cu_mask_ptr;
+	size_t cu_mask_size = sizeof(uint32_t) * (args->num_cu_mask / 32);
+
+	if ((args->num_cu_mask % 32) != 0) {
+		pr_debug("num_cu_mask 0x%x must be a multiple of 32",
+				args->num_cu_mask);
+		return -EINVAL;
+	}
+
+	properties.cu_mask_count = args->num_cu_mask;
+	if (properties.cu_mask_count == 0) {
+		pr_debug("CU mask cannot be 0");
+		return -EINVAL;
+	}
+
+	/* To prevent an unreasonably large CU mask size, set an arbitrary
+	 * limit of max_num_cus bits.  We can then just drop any CU mask bits
+	 * past max_num_cus bits and just use the first max_num_cus bits.
+	 */
+	if (properties.cu_mask_count > max_num_cus) {
+		pr_debug("CU mask cannot be greater than 1024 bits");
+		properties.cu_mask_count = max_num_cus;
+		cu_mask_size = sizeof(uint32_t) * (max_num_cus/32);
+	}
+
+	properties.cu_mask = kzalloc(cu_mask_size, GFP_KERNEL);
+	if (!properties.cu_mask)
+		return -ENOMEM;
+
+	retval = copy_from_user(properties.cu_mask, cu_mask_ptr, cu_mask_size);
+	if (retval) {
+		pr_debug("Could not copy CU mask from userspace");
+		kfree(properties.cu_mask);
+		return -EFAULT;
+	}
+
+	mutex_lock(&p->mutex);
+
+	retval = pqm_set_cu_mask(&p->pqm, args->queue_id, &properties);
+
+	mutex_unlock(&p->mutex);
+
+	if (retval)
+		kfree(properties.cu_mask);
+
+	return retval;
+}
+
 static int kfd_ioctl_set_memory_policy(struct file *filep,
 					struct kfd_process *p, void *data)
 {
@@ -754,7 +812,6 @@ static int kfd_ioctl_get_clock_counters(struct file *filep,
 {
 	struct kfd_ioctl_get_clock_counters_args *args = data;
 	struct kfd_dev *dev;
-	struct timespec64 time;
 
 	dev = kfd_device_by_id(args->gpu_id);
 	if (dev)
@@ -766,11 +823,8 @@ static int kfd_ioctl_get_clock_counters(struct file *filep,
 		args->gpu_clock_counter = 0;
 
 	/* No access to rdtsc. Using raw monotonic time */
-	getrawmonotonic64(&time);
-	args->cpu_clock_counter = (uint64_t)timespec64_to_ns(&time);
-
-	get_monotonic_boottime64(&time);
-	args->system_clock_counter = (uint64_t)timespec64_to_ns(&time);
+	args->cpu_clock_counter = ktime_get_raw_ns();
+	args->system_clock_counter = ktime_get_boot_ns();
 
 	/* Since the counter is in nano-seconds we use 1GHz frequency */
 	args->system_clock_freq = 1000000000;
@@ -1558,6 +1612,9 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = {
 	AMDKFD_IOCTL_DEF(AMDKFD_IOC_UNMAP_MEMORY_FROM_GPU,
 			kfd_ioctl_unmap_memory_from_gpu, 0),
 
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_SET_CU_MASK,
+			kfd_ioctl_set_cu_mask, 0),
+
 };
 
 #define AMDKFD_CORE_IOCTL_COUNT	ARRAY_SIZE(amdkfd_ioctls)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index 296b3f230280..ee4996029a86 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -189,6 +189,21 @@ static int kfd_parse_subtype_cu(struct crat_subtype_computeunit *cu,
 	return 0;
 }
 
+static struct kfd_mem_properties *
+find_subtype_mem(uint32_t heap_type, uint32_t flags, uint32_t width,
+		struct kfd_topology_device *dev)
+{
+	struct kfd_mem_properties *props;
+
+	list_for_each_entry(props, &dev->mem_props, list) {
+		if (props->heap_type == heap_type
+				&& props->flags == flags
+				&& props->width == width)
+			return props;
+	}
+
+	return NULL;
+}
 /* kfd_parse_subtype_mem - parse memory subtypes and attach it to correct
  * topology device present in the device_list
  */
@@ -197,36 +212,56 @@ static int kfd_parse_subtype_mem(struct crat_subtype_memory *mem,
 {
 	struct kfd_mem_properties *props;
 	struct kfd_topology_device *dev;
+	uint32_t heap_type;
+	uint64_t size_in_bytes;
+	uint32_t flags = 0;
+	uint32_t width;
 
 	pr_debug("Found memory entry in CRAT table with proximity_domain=%d\n",
 			mem->proximity_domain);
 	list_for_each_entry(dev, device_list, list) {
 		if (mem->proximity_domain == dev->proximity_domain) {
-			props = kfd_alloc_struct(props);
-			if (!props)
-				return -ENOMEM;
-
 			/* We're on GPU node */
 			if (dev->node_props.cpu_cores_count == 0) {
 				/* APU */
 				if (mem->visibility_type == 0)
-					props->heap_type =
+					heap_type =
 						HSA_MEM_HEAP_TYPE_FB_PRIVATE;
 				/* dGPU */
 				else
-					props->heap_type = mem->visibility_type;
+					heap_type = mem->visibility_type;
 			} else
-				props->heap_type = HSA_MEM_HEAP_TYPE_SYSTEM;
+				heap_type = HSA_MEM_HEAP_TYPE_SYSTEM;
 
 			if (mem->flags & CRAT_MEM_FLAGS_HOT_PLUGGABLE)
-				props->flags |= HSA_MEM_FLAGS_HOT_PLUGGABLE;
+				flags |= HSA_MEM_FLAGS_HOT_PLUGGABLE;
 			if (mem->flags & CRAT_MEM_FLAGS_NON_VOLATILE)
-				props->flags |= HSA_MEM_FLAGS_NON_VOLATILE;
+				flags |= HSA_MEM_FLAGS_NON_VOLATILE;
 
-			props->size_in_bytes =
+			size_in_bytes =
 				((uint64_t)mem->length_high << 32) +
 							mem->length_low;
-			props->width = mem->width;
+			width = mem->width;
+
+			/* Multiple banks of the same type are aggregated into
+			 * one. User mode doesn't care about multiple physical
+			 * memory segments. It's managed as a single virtual
+			 * heap for user mode.
+			 */
+			props = find_subtype_mem(heap_type, flags, width, dev);
+			if (props) {
+				props->size_in_bytes += size_in_bytes;
+				break;
+			}
+
+			props = kfd_alloc_struct(props);
+			if (!props)
+				return -ENOMEM;
+
+			props->heap_type = heap_type;
+			props->flags = flags;
+			props->size_in_bytes = size_in_bytes;
+			props->width = width;
 
 			dev->node_props.mem_banks_count++;
 			list_add_tail(&props->list, &dev->mem_props);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
index afb26f205d29..a3441b0e385b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
@@ -38,7 +38,6 @@
 #include "kfd_dbgmgr.h"
 #include "kfd_dbgdev.h"
 #include "kfd_device_queue_manager.h"
-#include "../../radeon/cik_reg.h"
 
 static void dbgdev_address_watch_disable_nodiq(struct kfd_dev *dev)
 {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h
index 03424c20920c..0619c777b47e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h
@@ -60,6 +60,9 @@ enum {
 	SH_REG_SIZE = SH_REG_END - SH_REG_BASE
 };
 
+/* SQ_CMD definitions */
+#define SQ_CMD						0x8DEC
+
 enum SQ_IND_CMD_CMD {
 	SQ_IND_CMD_CMD_NULL = 0x00000000,
 	SQ_IND_CMD_CMD_HALT = 0x00000001,
@@ -190,4 +193,38 @@ union ULARGE_INTEGER {
 void kfd_dbgdev_init(struct kfd_dbgdev *pdbgdev, struct kfd_dev *pdev,
 			enum DBGDEV_TYPE type);
 
+union TCP_WATCH_CNTL_BITS {
+	struct {
+		uint32_t mask:24;
+		uint32_t vmid:4;
+		uint32_t atc:1;
+		uint32_t mode:2;
+		uint32_t valid:1;
+	} bitfields, bits;
+	uint32_t u32All;
+	signed int i32All;
+	float f32All;
+};
+
+enum {
+	ADDRESS_WATCH_REG_CNTL_ATC_BIT = 0x10000000UL,
+	ADDRESS_WATCH_REG_CNTL_DEFAULT_MASK = 0x00FFFFFF,
+	ADDRESS_WATCH_REG_ADDLOW_MASK_EXTENSION = 0x03000000,
+	/* extend the mask to 26 bits in order to match the low address field */
+	ADDRESS_WATCH_REG_ADDLOW_SHIFT = 6,
+	ADDRESS_WATCH_REG_ADDHIGH_MASK = 0xFFFF
+};
+
+enum {
+	MAX_TRAPID = 8,		/* 3 bits in the bitfield. */
+	MAX_WATCH_ADDRESSES = 4
+};
+
+enum {
+	ADDRESS_WATCH_REG_ADDR_HI = 0,
+	ADDRESS_WATCH_REG_ADDR_LO,
+	ADDRESS_WATCH_REG_CNTL,
+	ADDRESS_WATCH_REG_MAX
+};
+
 #endif	/* KFD_DBGDEV_H_ */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
index 4bd6ebfaf425..ab37d36d9cd6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
@@ -21,6 +21,8 @@
  */
 
 #include <linux/debugfs.h>
+#include <linux/uaccess.h>
+
 #include "kfd_priv.h"
 
 static struct dentry *debugfs_root;
@@ -32,6 +34,38 @@ static int kfd_debugfs_open(struct inode *inode, struct file *file)
 	return single_open(file, show, NULL);
 }
 
+static ssize_t kfd_debugfs_hang_hws_write(struct file *file,
+	const char __user *user_buf, size_t size, loff_t *ppos)
+{
+	struct kfd_dev *dev;
+	char tmp[16];
+	uint32_t gpu_id;
+	int ret = -EINVAL;
+
+	memset(tmp, 0, 16);
+	if (size >= 16) {
+		pr_err("Invalid input for gpu id.\n");
+		goto out;
+	}
+	if (copy_from_user(tmp, user_buf, size)) {
+		ret = -EFAULT;
+		goto out;
+	}
+	if (kstrtoint(tmp, 10, &gpu_id)) {
+		pr_err("Invalid input for gpu id.\n");
+		goto out;
+	}
+	dev = kfd_device_by_id(gpu_id);
+	if (dev) {
+		kfd_debugfs_hang_hws(dev);
+		ret = size;
+	} else
+		pr_err("Cannot find device %d.\n", gpu_id);
+
+out:
+	return ret;
+}
+
 static const struct file_operations kfd_debugfs_fops = {
 	.owner = THIS_MODULE,
 	.open = kfd_debugfs_open,
@@ -40,6 +74,15 @@ static const struct file_operations kfd_debugfs_fops = {
 	.release = single_release,
 };
 
+static const struct file_operations kfd_debugfs_hang_hws_fops = {
+	.owner = THIS_MODULE,
+	.open = kfd_debugfs_open,
+	.read = seq_read,
+	.write = kfd_debugfs_hang_hws_write,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
 void kfd_debugfs_init(void)
 {
 	struct dentry *ent;
@@ -65,6 +108,11 @@ void kfd_debugfs_init(void)
 	ent = debugfs_create_file("rls", S_IFREG | 0444, debugfs_root,
 				  kfd_debugfs_rls_by_device,
 				  &kfd_debugfs_fops);
+
+	ent = debugfs_create_file("hang_hws", S_IFREG | 0644, debugfs_root,
+				  NULL,
+				  &kfd_debugfs_hang_hws_fops);
+
 	if (!ent)
 		pr_warn("Failed to create rls in kfd debugfs\n");
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 7ee6cec2c060..1b048715ab8a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -30,7 +30,13 @@
 #include "kfd_iommu.h"
 
 #define MQD_SIZE_ALIGNED 768
-static atomic_t kfd_device_suspended = ATOMIC_INIT(0);
+
+/*
+ * kfd_locked is used to lock the kfd driver during suspend or reset
+ * once locked, kfd driver will stop any further GPU execution.
+ * create process (open) will return -EAGAIN.
+ */
+static atomic_t kfd_locked = ATOMIC_INIT(0);
 
 #ifdef KFD_SUPPORT_IOMMU_V2
 static const struct kfd_device_info kaveri_device_info = {
@@ -46,6 +52,7 @@ static const struct kfd_device_info kaveri_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = true,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info carrizo_device_info = {
@@ -61,6 +68,22 @@ static const struct kfd_device_info carrizo_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = true,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
+};
+
+static const struct kfd_device_info raven_device_info = {
+	.asic_family = CHIP_RAVEN,
+	.max_pasid_bits = 16,
+	.max_no_of_hqd  = 24,
+	.doorbell_size  = 8,
+	.ih_ring_entry_size = 8 * sizeof(uint32_t),
+	.event_interrupt_class = &event_interrupt_class_v9,
+	.num_of_watch_points = 4,
+	.mqd_size_aligned = MQD_SIZE_ALIGNED,
+	.supports_cwsr = true,
+	.needs_iommu_device = true,
+	.needs_pci_atomics = true,
+	.num_sdma_engines = 1,
 };
 #endif
 
@@ -77,6 +100,7 @@ static const struct kfd_device_info hawaii_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info tonga_device_info = {
@@ -91,6 +115,7 @@ static const struct kfd_device_info tonga_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info tonga_vf_device_info = {
@@ -105,6 +130,7 @@ static const struct kfd_device_info tonga_vf_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info fiji_device_info = {
@@ -119,6 +145,7 @@ static const struct kfd_device_info fiji_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info fiji_vf_device_info = {
@@ -133,6 +160,7 @@ static const struct kfd_device_info fiji_vf_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 
@@ -148,6 +176,7 @@ static const struct kfd_device_info polaris10_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info polaris10_vf_device_info = {
@@ -162,6 +191,7 @@ static const struct kfd_device_info polaris10_vf_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info polaris11_device_info = {
@@ -176,6 +206,7 @@ static const struct kfd_device_info polaris11_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info vega10_device_info = {
@@ -190,6 +221,7 @@ static const struct kfd_device_info vega10_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info vega10_vf_device_info = {
@@ -204,6 +236,7 @@ static const struct kfd_device_info vega10_vf_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 
@@ -241,6 +274,7 @@ static const struct kfd_deviceid supported_devices[] = {
 	{ 0x9875, &carrizo_device_info },	/* Carrizo */
 	{ 0x9876, &carrizo_device_info },	/* Carrizo */
 	{ 0x9877, &carrizo_device_info },	/* Carrizo */
+	{ 0x15DD, &raven_device_info },		/* Raven */
 #endif
 	{ 0x67A0, &hawaii_device_info },	/* Hawaii */
 	{ 0x67A1, &hawaii_device_info },	/* Hawaii */
@@ -514,13 +548,54 @@ void kgd2kfd_device_exit(struct kfd_dev *kfd)
 	kfree(kfd);
 }
 
+int kgd2kfd_pre_reset(struct kfd_dev *kfd)
+{
+	if (!kfd->init_complete)
+		return 0;
+	kgd2kfd_suspend(kfd);
+
+	/* hold dqm->lock to prevent further execution*/
+	dqm_lock(kfd->dqm);
+
+	kfd_signal_reset_event(kfd);
+	return 0;
+}
+
+/*
+ * Fix me. KFD won't be able to resume existing process for now.
+ * We will keep all existing process in a evicted state and
+ * wait the process to be terminated.
+ */
+
+int kgd2kfd_post_reset(struct kfd_dev *kfd)
+{
+	int ret, count;
+
+	if (!kfd->init_complete)
+		return 0;
+
+	dqm_unlock(kfd->dqm);
+
+	ret = kfd_resume(kfd);
+	if (ret)
+		return ret;
+	count = atomic_dec_return(&kfd_locked);
+	WARN_ONCE(count != 0, "KFD reset ref. error");
+	return 0;
+}
+
+bool kfd_is_locked(void)
+{
+	return  (atomic_read(&kfd_locked) > 0);
+}
+
 void kgd2kfd_suspend(struct kfd_dev *kfd)
 {
 	if (!kfd->init_complete)
 		return;
 
 	/* For first KFD device suspend all the KFD processes */
-	if (atomic_inc_return(&kfd_device_suspended) == 1)
+	if (atomic_inc_return(&kfd_locked) == 1)
 		kfd_suspend_all_processes();
 
 	kfd->dqm->ops.stop(kfd->dqm);
@@ -539,7 +614,7 @@ int kgd2kfd_resume(struct kfd_dev *kfd)
 	if (ret)
 		return ret;
 
-	count = atomic_dec_return(&kfd_device_suspended);
+	count = atomic_dec_return(&kfd_locked);
 	WARN_ONCE(count < 0, "KFD suspend / resume ref. error");
 	if (count == 0)
 		ret = kfd_resume_all_processes();
@@ -577,14 +652,24 @@ dqm_start_error:
 /* This is called directly from KGD at ISR. */
 void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
 {
+	uint32_t patched_ihre[KFD_MAX_RING_ENTRY_SIZE];
+	bool is_patched = false;
+
 	if (!kfd->init_complete)
 		return;
 
+	if (kfd->device_info->ih_ring_entry_size > sizeof(patched_ihre)) {
+		dev_err_once(kfd_device, "Ring entry too small\n");
+		return;
+	}
+
 	spin_lock(&kfd->interrupt_lock);
 
 	if (kfd->interrupts_active
-	    && interrupt_is_wanted(kfd, ih_ring_entry)
-	    && enqueue_ih_ring_entry(kfd, ih_ring_entry))
+	    && interrupt_is_wanted(kfd, ih_ring_entry,
+				   patched_ihre, &is_patched)
+	    && enqueue_ih_ring_entry(kfd,
+				     is_patched ? patched_ihre : ih_ring_entry))
 		queue_work(kfd->ih_wq, &kfd->interrupt_work);
 
 	spin_unlock(&kfd->interrupt_lock);
@@ -739,8 +824,8 @@ int kfd_gtt_sa_allocate(struct kfd_dev *kfd, unsigned int size,
 	if (size > kfd->gtt_sa_num_of_chunks * kfd->gtt_sa_chunk_size)
 		return -ENOMEM;
 
-	*mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_NOIO);
-	if ((*mem_obj) == NULL)
+	*mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_KERNEL);
+	if (!(*mem_obj))
 		return -ENOMEM;
 
 	pr_debug("Allocated mem_obj = %p for size = %d\n", *mem_obj, size);
@@ -857,3 +942,26 @@ int kfd_gtt_sa_free(struct kfd_dev *kfd, struct kfd_mem_obj *mem_obj)
 	kfree(mem_obj);
 	return 0;
 }
+
+#if defined(CONFIG_DEBUG_FS)
+
+/* This function will send a package to HIQ to hang the HWS
+ * which will trigger a GPU reset and bring the HWS back to normal state
+ */
+int kfd_debugfs_hang_hws(struct kfd_dev *dev)
+{
+	int r = 0;
+
+	if (dev->dqm->sched_policy != KFD_SCHED_POLICY_HWS) {
+		pr_err("HWS is not enabled");
+		return -EINVAL;
+	}
+
+	r = pm_debugfs_hang_hws(&dev->dqm->packets);
+	if (!r)
+		r = dqm_debugfs_execute_queues(dev->dqm);
+
+	return r;
+}
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 668ad07ebe1f..ec0d62a16e53 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -61,6 +61,8 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
 static void deallocate_sdma_queue(struct device_queue_manager *dqm,
 				unsigned int sdma_queue_id);
 
+static void kfd_process_hw_exception(struct work_struct *work);
+
 static inline
 enum KFD_MQD_TYPE get_mqd_type_from_queue_type(enum kfd_queue_type type)
 {
@@ -99,6 +101,17 @@ unsigned int get_pipes_per_mec(struct device_queue_manager *dqm)
 	return dqm->dev->shared_resources.num_pipe_per_mec;
 }
 
+static unsigned int get_num_sdma_engines(struct device_queue_manager *dqm)
+{
+	return dqm->dev->device_info->num_sdma_engines;
+}
+
+unsigned int get_num_sdma_queues(struct device_queue_manager *dqm)
+{
+	return dqm->dev->device_info->num_sdma_engines
+			* KFD_SDMA_QUEUES_PER_ENGINE;
+}
+
 void program_sh_mem_settings(struct device_queue_manager *dqm,
 					struct qcm_process_device *qpd)
 {
@@ -240,7 +253,7 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
 
 	print_queue(q);
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	if (dqm->total_queue_count >= max_num_of_queues_per_device) {
 		pr_warn("Can't create new usermode queue because %d queues were already created\n",
@@ -297,7 +310,7 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
 			dqm->total_queue_count);
 
 out_unlock:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -346,10 +359,10 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 					struct qcm_process_device *qpd)
 {
 	int retval;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 
-	mqd = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_COMPUTE);
-	if (!mqd)
+	mqd_mgr = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_COMPUTE);
+	if (!mqd_mgr)
 		return -ENOMEM;
 
 	retval = allocate_hqd(dqm, q);
@@ -360,7 +373,7 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 	if (retval)
 		goto out_deallocate_hqd;
 
-	retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj,
+	retval = mqd_mgr->init_mqd(mqd_mgr, &q->mqd, &q->mqd_mem_obj,
 				&q->gart_mqd_addr, &q->properties);
 	if (retval)
 		goto out_deallocate_doorbell;
@@ -374,15 +387,15 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 	if (!q->properties.is_active)
 		return 0;
 
-	retval = mqd->load_mqd(mqd, q->mqd, q->pipe, q->queue, &q->properties,
-			       q->process->mm);
+	retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue,
+			&q->properties, q->process->mm);
 	if (retval)
 		goto out_uninit_mqd;
 
 	return 0;
 
 out_uninit_mqd:
-	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+	mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
 out_deallocate_doorbell:
 	deallocate_doorbell(qpd, q);
 out_deallocate_hqd:
@@ -399,11 +412,11 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm,
 				struct queue *q)
 {
 	int retval;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 
-	mqd = dqm->ops.get_mqd_manager(dqm,
+	mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 		get_mqd_type_from_queue_type(q->properties.type));
-	if (!mqd)
+	if (!mqd_mgr)
 		return -ENOMEM;
 
 	if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE) {
@@ -420,14 +433,14 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm,
 
 	deallocate_doorbell(qpd, q);
 
-	retval = mqd->destroy_mqd(mqd, q->mqd,
+	retval = mqd_mgr->destroy_mqd(mqd_mgr, q->mqd,
 				KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
 				KFD_UNMAP_LATENCY_MS,
 				q->pipe, q->queue);
 	if (retval == -ETIME)
 		qpd->reset_wavefronts = true;
 
-	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+	mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
 
 	list_del(&q->list);
 	if (list_empty(&qpd->queues_list)) {
@@ -457,9 +470,9 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm,
 {
 	int retval;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	retval = destroy_queue_nocpsch_locked(dqm, qpd, q);
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 
 	return retval;
 }
@@ -467,19 +480,19 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm,
 static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 {
 	int retval;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 	struct kfd_process_device *pdd;
 	bool prev_active = false;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	pdd = kfd_get_process_device_data(q->device, q->process);
 	if (!pdd) {
 		retval = -ENODEV;
 		goto out_unlock;
 	}
-	mqd = dqm->ops.get_mqd_manager(dqm,
+	mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
-	if (!mqd) {
+	if (!mqd_mgr) {
 		retval = -ENOMEM;
 		goto out_unlock;
 	}
@@ -506,7 +519,7 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 	} else if (prev_active &&
 		   (q->properties.type == KFD_QUEUE_TYPE_COMPUTE ||
 		    q->properties.type == KFD_QUEUE_TYPE_SDMA)) {
-		retval = mqd->destroy_mqd(mqd, q->mqd,
+		retval = mqd_mgr->destroy_mqd(mqd_mgr, q->mqd,
 				KFD_PREEMPT_TYPE_WAVEFRONT_DRAIN,
 				KFD_UNMAP_LATENCY_MS, q->pipe, q->queue);
 		if (retval) {
@@ -515,7 +528,7 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 		}
 	}
 
-	retval = mqd->update_mqd(mqd, q->mqd, &q->properties);
+	retval = mqd_mgr->update_mqd(mqd_mgr, q->mqd, &q->properties);
 
 	/*
 	 * check active state vs. the previous state and modify
@@ -533,44 +546,44 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 	else if (q->properties.is_active &&
 		 (q->properties.type == KFD_QUEUE_TYPE_COMPUTE ||
 		  q->properties.type == KFD_QUEUE_TYPE_SDMA))
-		retval = mqd->load_mqd(mqd, q->mqd, q->pipe, q->queue,
+		retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue,
 				       &q->properties, q->process->mm);
 
 out_unlock:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
 static struct mqd_manager *get_mqd_manager(
 		struct device_queue_manager *dqm, enum KFD_MQD_TYPE type)
 {
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 
 	if (WARN_ON(type >= KFD_MQD_TYPE_MAX))
 		return NULL;
 
 	pr_debug("mqd type %d\n", type);
 
-	mqd = dqm->mqds[type];
-	if (!mqd) {
-		mqd = mqd_manager_init(type, dqm->dev);
-		if (!mqd)
+	mqd_mgr = dqm->mqd_mgrs[type];
+	if (!mqd_mgr) {
+		mqd_mgr = mqd_manager_init(type, dqm->dev);
+		if (!mqd_mgr)
 			pr_err("mqd manager is NULL");
-		dqm->mqds[type] = mqd;
+		dqm->mqd_mgrs[type] = mqd_mgr;
 	}
 
-	return mqd;
+	return mqd_mgr;
 }
 
 static int evict_process_queues_nocpsch(struct device_queue_manager *dqm,
 					struct qcm_process_device *qpd)
 {
 	struct queue *q;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 	struct kfd_process_device *pdd;
 	int retval = 0;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	if (qpd->evicted++ > 0) /* already evicted, do nothing */
 		goto out;
 
@@ -582,16 +595,16 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm,
 	list_for_each_entry(q, &qpd->queues_list, list) {
 		if (!q->properties.is_active)
 			continue;
-		mqd = dqm->ops.get_mqd_manager(dqm,
+		mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
-		if (!mqd) { /* should not be here */
+		if (!mqd_mgr) { /* should not be here */
 			pr_err("Cannot evict queue, mqd mgr is NULL\n");
 			retval = -ENOMEM;
 			goto out;
 		}
 		q->properties.is_evicted = true;
 		q->properties.is_active = false;
-		retval = mqd->destroy_mqd(mqd, q->mqd,
+		retval = mqd_mgr->destroy_mqd(mqd_mgr, q->mqd,
 				KFD_PREEMPT_TYPE_WAVEFRONT_DRAIN,
 				KFD_UNMAP_LATENCY_MS, q->pipe, q->queue);
 		if (retval)
@@ -600,7 +613,7 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm,
 	}
 
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -611,7 +624,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm,
 	struct kfd_process_device *pdd;
 	int retval = 0;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	if (qpd->evicted++ > 0) /* already evicted, do nothing */
 		goto out;
 
@@ -633,7 +646,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm,
 				KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
 
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -641,7 +654,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 					  struct qcm_process_device *qpd)
 {
 	struct queue *q;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 	struct kfd_process_device *pdd;
 	uint32_t pd_base;
 	int retval = 0;
@@ -650,7 +663,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 	/* Retrieve PD base */
 	pd_base = dqm->dev->kfd2kgd->get_process_page_dir(pdd->vm);
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	if (WARN_ON_ONCE(!qpd->evicted)) /* already restored, do nothing */
 		goto out;
 	if (qpd->evicted > 1) { /* ref count still > 0, decrement & quit */
@@ -677,16 +690,16 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 	list_for_each_entry(q, &qpd->queues_list, list) {
 		if (!q->properties.is_evicted)
 			continue;
-		mqd = dqm->ops.get_mqd_manager(dqm,
+		mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
-		if (!mqd) { /* should not be here */
+		if (!mqd_mgr) { /* should not be here */
 			pr_err("Cannot restore queue, mqd mgr is NULL\n");
 			retval = -ENOMEM;
 			goto out;
 		}
 		q->properties.is_evicted = false;
 		q->properties.is_active = true;
-		retval = mqd->load_mqd(mqd, q->mqd, q->pipe,
+		retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe,
 				       q->queue, &q->properties,
 				       q->process->mm);
 		if (retval)
@@ -695,7 +708,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 	}
 	qpd->evicted = 0;
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -711,7 +724,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm,
 	/* Retrieve PD base */
 	pd_base = dqm->dev->kfd2kgd->get_process_page_dir(pdd->vm);
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	if (WARN_ON_ONCE(!qpd->evicted)) /* already restored, do nothing */
 		goto out;
 	if (qpd->evicted > 1) { /* ref count still > 0, decrement & quit */
@@ -739,7 +752,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm,
 	if (!retval)
 		qpd->evicted = 0;
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -761,7 +774,7 @@ static int register_process(struct device_queue_manager *dqm,
 	/* Retrieve PD base */
 	pd_base = dqm->dev->kfd2kgd->get_process_page_dir(pdd->vm);
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	list_add(&n->list, &dqm->queues);
 
 	/* Update PD Base in QPD */
@@ -769,9 +782,10 @@ static int register_process(struct device_queue_manager *dqm,
 
 	retval = dqm->asic_ops.update_qpd(dqm, qpd);
 
-	dqm->processes_count++;
+	if (dqm->processes_count++ == 0)
+		dqm->dev->kfd2kgd->set_compute_idle(dqm->dev->kgd, false);
 
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 
 	return retval;
 }
@@ -786,20 +800,22 @@ static int unregister_process(struct device_queue_manager *dqm,
 			list_empty(&qpd->queues_list) ? "empty" : "not empty");
 
 	retval = 0;
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	list_for_each_entry_safe(cur, next, &dqm->queues, list) {
 		if (qpd == cur->qpd) {
 			list_del(&cur->list);
 			kfree(cur);
-			dqm->processes_count--;
+			if (--dqm->processes_count == 0)
+				dqm->dev->kfd2kgd->set_compute_idle(
+					dqm->dev->kgd, true);
 			goto out;
 		}
 	}
 	/* qpd not found in dqm list */
 	retval = 1;
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -838,7 +854,7 @@ static int initialize_nocpsch(struct device_queue_manager *dqm)
 	if (!dqm->allocated_queues)
 		return -ENOMEM;
 
-	mutex_init(&dqm->lock);
+	mutex_init(&dqm->lock_hidden);
 	INIT_LIST_HEAD(&dqm->queues);
 	dqm->queue_count = dqm->next_pipe_to_allocate = 0;
 	dqm->sdma_queue_count = 0;
@@ -853,7 +869,7 @@ static int initialize_nocpsch(struct device_queue_manager *dqm)
 	}
 
 	dqm->vmid_bitmap = (1 << dqm->dev->vm_info.vmid_num_kfd) - 1;
-	dqm->sdma_bitmap = (1 << CIK_SDMA_QUEUES) - 1;
+	dqm->sdma_bitmap = (1 << get_num_sdma_queues(dqm)) - 1;
 
 	return 0;
 }
@@ -866,8 +882,8 @@ static void uninitialize(struct device_queue_manager *dqm)
 
 	kfree(dqm->allocated_queues);
 	for (i = 0 ; i < KFD_MQD_TYPE_MAX ; i++)
-		kfree(dqm->mqds[i]);
-	mutex_destroy(&dqm->lock);
+		kfree(dqm->mqd_mgrs[i]);
+	mutex_destroy(&dqm->lock_hidden);
 	kfd_gtt_sa_free(dqm->dev, dqm->pipeline_mem);
 }
 
@@ -901,7 +917,7 @@ static int allocate_sdma_queue(struct device_queue_manager *dqm,
 static void deallocate_sdma_queue(struct device_queue_manager *dqm,
 				unsigned int sdma_queue_id)
 {
-	if (sdma_queue_id >= CIK_SDMA_QUEUES)
+	if (sdma_queue_id >= get_num_sdma_queues(dqm))
 		return;
 	dqm->sdma_bitmap |= (1 << sdma_queue_id);
 }
@@ -910,19 +926,19 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
 					struct queue *q,
 					struct qcm_process_device *qpd)
 {
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 	int retval;
 
-	mqd = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_SDMA);
-	if (!mqd)
+	mqd_mgr = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_SDMA);
+	if (!mqd_mgr)
 		return -ENOMEM;
 
 	retval = allocate_sdma_queue(dqm, &q->sdma_id);
 	if (retval)
 		return retval;
 
-	q->properties.sdma_queue_id = q->sdma_id / CIK_SDMA_QUEUES_PER_ENGINE;
-	q->properties.sdma_engine_id = q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE;
+	q->properties.sdma_queue_id = q->sdma_id / get_num_sdma_engines(dqm);
+	q->properties.sdma_engine_id = q->sdma_id % get_num_sdma_engines(dqm);
 
 	retval = allocate_doorbell(qpd, q);
 	if (retval)
@@ -933,19 +949,20 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
 	pr_debug("SDMA engine id: %d\n", q->properties.sdma_engine_id);
 
 	dqm->asic_ops.init_sdma_vm(dqm, q, qpd);
-	retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj,
+	retval = mqd_mgr->init_mqd(mqd_mgr, &q->mqd, &q->mqd_mem_obj,
 				&q->gart_mqd_addr, &q->properties);
 	if (retval)
 		goto out_deallocate_doorbell;
 
-	retval = mqd->load_mqd(mqd, q->mqd, 0, 0, &q->properties, NULL);
+	retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, 0, 0, &q->properties,
+				NULL);
 	if (retval)
 		goto out_uninit_mqd;
 
 	return 0;
 
 out_uninit_mqd:
-	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+	mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
 out_deallocate_doorbell:
 	deallocate_doorbell(qpd, q);
 out_deallocate_sdma_queue:
@@ -1003,12 +1020,14 @@ static int initialize_cpsch(struct device_queue_manager *dqm)
 {
 	pr_debug("num of pipes: %d\n", get_pipes_per_mec(dqm));
 
-	mutex_init(&dqm->lock);
+	mutex_init(&dqm->lock_hidden);
 	INIT_LIST_HEAD(&dqm->queues);
 	dqm->queue_count = dqm->processes_count = 0;
 	dqm->sdma_queue_count = 0;
 	dqm->active_runlist = false;
-	dqm->sdma_bitmap = (1 << CIK_SDMA_QUEUES) - 1;
+	dqm->sdma_bitmap = (1 << get_num_sdma_queues(dqm)) - 1;
+
+	INIT_WORK(&dqm->hw_exception_work, kfd_process_hw_exception);
 
 	return 0;
 }
@@ -1041,9 +1060,11 @@ static int start_cpsch(struct device_queue_manager *dqm)
 
 	init_interrupts(dqm);
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
+	/* clear hang status when driver try to start the hw scheduler */
+	dqm->is_hws_hang = false;
 	execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 
 	return 0;
 fail_allocate_vidmem:
@@ -1055,9 +1076,9 @@ fail_packet_manager_init:
 
 static int stop_cpsch(struct device_queue_manager *dqm)
 {
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 
 	kfd_gtt_sa_free(dqm->dev, dqm->fence_mem);
 	pm_uninit(&dqm->packets);
@@ -1069,11 +1090,11 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm,
 					struct kernel_queue *kq,
 					struct qcm_process_device *qpd)
 {
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	if (dqm->total_queue_count >= max_num_of_queues_per_device) {
 		pr_warn("Can't create new kernel queue because %d queues were already created\n",
 				dqm->total_queue_count);
-		mutex_unlock(&dqm->lock);
+		dqm_unlock(dqm);
 		return -EPERM;
 	}
 
@@ -1089,7 +1110,7 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm,
 	dqm->queue_count++;
 	qpd->is_debug = true;
 	execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 
 	return 0;
 }
@@ -1098,7 +1119,7 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
 					struct kernel_queue *kq,
 					struct qcm_process_device *qpd)
 {
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	list_del(&kq->list);
 	dqm->queue_count--;
 	qpd->is_debug = false;
@@ -1110,18 +1131,18 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
 	dqm->total_queue_count--;
 	pr_debug("Total of %d queues are accountable so far\n",
 			dqm->total_queue_count);
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 }
 
 static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 			struct qcm_process_device *qpd)
 {
 	int retval;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 
 	retval = 0;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	if (dqm->total_queue_count >= max_num_of_queues_per_device) {
 		pr_warn("Can't create new usermode queue because %d queues were already created\n",
@@ -1135,19 +1156,19 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 		if (retval)
 			goto out_unlock;
 		q->properties.sdma_queue_id =
-			q->sdma_id / CIK_SDMA_QUEUES_PER_ENGINE;
+			q->sdma_id / get_num_sdma_engines(dqm);
 		q->properties.sdma_engine_id =
-			q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE;
+			q->sdma_id % get_num_sdma_engines(dqm);
 	}
 
 	retval = allocate_doorbell(qpd, q);
 	if (retval)
 		goto out_deallocate_sdma_queue;
 
-	mqd = dqm->ops.get_mqd_manager(dqm,
+	mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
 
-	if (!mqd) {
+	if (!mqd_mgr) {
 		retval = -ENOMEM;
 		goto out_deallocate_doorbell;
 	}
@@ -1164,7 +1185,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 
 	q->properties.tba_addr = qpd->tba_addr;
 	q->properties.tma_addr = qpd->tma_addr;
-	retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj,
+	retval = mqd_mgr->init_mqd(mqd_mgr, &q->mqd, &q->mqd_mem_obj,
 				&q->gart_mqd_addr, &q->properties);
 	if (retval)
 		goto out_deallocate_doorbell;
@@ -1188,7 +1209,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 	pr_debug("Total of %d queues are accountable so far\n",
 			dqm->total_queue_count);
 
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 
 out_deallocate_doorbell:
@@ -1197,7 +1218,8 @@ out_deallocate_sdma_queue:
 	if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
 		deallocate_sdma_queue(dqm, q->sdma_id);
 out_unlock:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
+
 	return retval;
 }
 
@@ -1210,6 +1232,13 @@ int amdkfd_fence_wait_timeout(unsigned int *fence_addr,
 	while (*fence_addr != fence_value) {
 		if (time_after(jiffies, end_jiffies)) {
 			pr_err("qcm fence wait loop timeout expired\n");
+			/* In HWS case, this is used to halt the driver thread
+			 * in order not to mess up CP states before doing
+			 * scandumps for FW debugging.
+			 */
+			while (halt_if_hws_hang)
+				schedule();
+
 			return -ETIME;
 		}
 		schedule();
@@ -1254,6 +1283,8 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
 {
 	int retval = 0;
 
+	if (dqm->is_hws_hang)
+		return -EIO;
 	if (!dqm->active_runlist)
 		return retval;
 
@@ -1292,9 +1323,13 @@ static int execute_queues_cpsch(struct device_queue_manager *dqm,
 {
 	int retval;
 
+	if (dqm->is_hws_hang)
+		return -EIO;
 	retval = unmap_queues_cpsch(dqm, filter, filter_param);
 	if (retval) {
 		pr_err("The cp might be in an unrecoverable state due to an unsuccessful queues preemption\n");
+		dqm->is_hws_hang = true;
+		schedule_work(&dqm->hw_exception_work);
 		return retval;
 	}
 
@@ -1306,7 +1341,7 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 				struct queue *q)
 {
 	int retval;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 	bool preempt_all_queues;
 
 	preempt_all_queues = false;
@@ -1314,7 +1349,7 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 	retval = 0;
 
 	/* remove queue from list to prevent rescheduling after preemption */
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	if (qpd->is_debug) {
 		/*
@@ -1326,9 +1361,9 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 
 	}
 
-	mqd = dqm->ops.get_mqd_manager(dqm,
+	mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
-	if (!mqd) {
+	if (!mqd_mgr) {
 		retval = -ENOMEM;
 		goto failed;
 	}
@@ -1350,7 +1385,7 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 			qpd->reset_wavefronts = true;
 	}
 
-	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+	mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
 
 	/*
 	 * Unconditionally decrement this counter, regardless of the queue's
@@ -1360,14 +1395,14 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 	pr_debug("Total of %d queues are accountable so far\n",
 			dqm->total_queue_count);
 
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 
 	return retval;
 
 failed:
 failed_try_destroy_debugged_queue:
 
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -1391,7 +1426,7 @@ static bool set_cache_memory_policy(struct device_queue_manager *dqm,
 	if (!dqm->asic_ops.set_cache_memory_policy)
 		return retval;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	if (alternate_aperture_size == 0) {
 		/* base > limit disables APE1 */
@@ -1437,7 +1472,7 @@ static bool set_cache_memory_policy(struct device_queue_manager *dqm,
 		qpd->sh_mem_ape1_limit);
 
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -1468,7 +1503,7 @@ static int process_termination_nocpsch(struct device_queue_manager *dqm,
 	struct device_process_node *cur, *next_dpn;
 	int retval = 0;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	/* Clear all user mode queues */
 	list_for_each_entry_safe(q, next, &qpd->queues_list, list) {
@@ -1489,7 +1524,7 @@ static int process_termination_nocpsch(struct device_queue_manager *dqm,
 		}
 	}
 
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -1500,14 +1535,14 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
 	int retval;
 	struct queue *q, *next;
 	struct kernel_queue *kq, *kq_next;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 	struct device_process_node *cur, *next_dpn;
 	enum kfd_unmap_queues_filter filter =
 		KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES;
 
 	retval = 0;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	/* Clean all kernel queues */
 	list_for_each_entry_safe(kq, kq_next, &qpd->priv_queue_list, list) {
@@ -1542,7 +1577,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
 	}
 
 	retval = execute_queues_cpsch(dqm, filter, 0);
-	if (retval || qpd->reset_wavefronts) {
+	if ((!dqm->is_hws_hang) && (retval || qpd->reset_wavefronts)) {
 		pr_warn("Resetting wave fronts (cpsch) on dev %p\n", dqm->dev);
 		dbgdev_wave_reset_wavefronts(dqm->dev, qpd->pqm->process);
 		qpd->reset_wavefronts = false;
@@ -1550,19 +1585,19 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
 
 	/* lastly, free mqd resources */
 	list_for_each_entry_safe(q, next, &qpd->queues_list, list) {
-		mqd = dqm->ops.get_mqd_manager(dqm,
+		mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
-		if (!mqd) {
+		if (!mqd_mgr) {
 			retval = -ENOMEM;
 			goto out;
 		}
 		list_del(&q->list);
 		qpd->queue_count--;
-		mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+		mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
 	}
 
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -1683,6 +1718,30 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm)
 	kfree(dqm);
 }
 
+int kfd_process_vm_fault(struct device_queue_manager *dqm,
+			 unsigned int pasid)
+{
+	struct kfd_process_device *pdd;
+	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);
+	int ret = 0;
+
+	if (!p)
+		return -EINVAL;
+	pdd = kfd_get_process_device_data(dqm->dev, p);
+	if (pdd)
+		ret = dqm->ops.evict_process_queues(dqm, &pdd->qpd);
+	kfd_unref_process(p);
+
+	return ret;
+}
+
+static void kfd_process_hw_exception(struct work_struct *work)
+{
+	struct device_queue_manager *dqm = container_of(work,
+			struct device_queue_manager, hw_exception_work);
+	dqm->dev->kfd2kgd->gpu_recover(dqm->dev->kgd);
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
 static void seq_reg_dump(struct seq_file *m,
@@ -1746,8 +1805,8 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data)
 		}
 	}
 
-	for (pipe = 0; pipe < CIK_SDMA_ENGINE_NUM; pipe++) {
-		for (queue = 0; queue < CIK_SDMA_QUEUES_PER_ENGINE; queue++) {
+	for (pipe = 0; pipe < get_num_sdma_engines(dqm); pipe++) {
+		for (queue = 0; queue < KFD_SDMA_QUEUES_PER_ENGINE; queue++) {
 			r = dqm->dev->kfd2kgd->hqd_sdma_dump(
 				dqm->dev->kgd, pipe, queue, &dump, &n_regs);
 			if (r)
@@ -1764,4 +1823,16 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data)
 	return r;
 }
 
+int dqm_debugfs_execute_queues(struct device_queue_manager *dqm)
+{
+	int r = 0;
+
+	dqm_lock(dqm);
+	dqm->active_runlist = true;
+	r = execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
+	dqm_unlock(dqm);
+
+	return r;
+}
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index 59a6b1956932..00da3169a004 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -26,15 +26,14 @@
 
 #include <linux/rwsem.h>
 #include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/sched/mm.h>
 #include "kfd_priv.h"
 #include "kfd_mqd_manager.h"
 
 #define KFD_UNMAP_LATENCY_MS			(4000)
 #define QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS (2 * KFD_UNMAP_LATENCY_MS + 1000)
-
-#define CIK_SDMA_QUEUES				(4)
-#define CIK_SDMA_QUEUES_PER_ENGINE		(2)
-#define CIK_SDMA_ENGINE_NUM			(2)
+#define KFD_SDMA_QUEUES_PER_ENGINE		(2)
 
 struct device_process_node {
 	struct qcm_process_device *qpd;
@@ -170,11 +169,12 @@ struct device_queue_manager {
 	struct device_queue_manager_ops ops;
 	struct device_queue_manager_asic_ops asic_ops;
 
-	struct mqd_manager	*mqds[KFD_MQD_TYPE_MAX];
+	struct mqd_manager	*mqd_mgrs[KFD_MQD_TYPE_MAX];
 	struct packet_manager	packets;
 	struct kfd_dev		*dev;
-	struct mutex		lock;
+	struct mutex		lock_hidden; /* use dqm_lock/unlock(dqm) */
 	struct list_head	queues;
+	unsigned int		saved_flags;
 	unsigned int		processes_count;
 	unsigned int		queue_count;
 	unsigned int		sdma_queue_count;
@@ -190,6 +190,10 @@ struct device_queue_manager {
 	struct kfd_mem_obj	*fence_mem;
 	bool			active_runlist;
 	int			sched_policy;
+
+	/* hw exception  */
+	bool			is_hws_hang;
+	struct work_struct	hw_exception_work;
 };
 
 void device_queue_manager_init_cik(
@@ -207,6 +211,7 @@ void program_sh_mem_settings(struct device_queue_manager *dqm,
 unsigned int get_queues_num(struct device_queue_manager *dqm);
 unsigned int get_queues_per_pipe(struct device_queue_manager *dqm);
 unsigned int get_pipes_per_mec(struct device_queue_manager *dqm);
+unsigned int get_num_sdma_queues(struct device_queue_manager *dqm);
 
 static inline unsigned int get_sh_mem_bases_32(struct kfd_process_device *pdd)
 {
@@ -219,4 +224,19 @@ get_sh_mem_bases_nybble_64(struct kfd_process_device *pdd)
 	return (pdd->lds_base >> 60) & 0x0E;
 }
 
+/* The DQM lock can be taken in MMU notifiers. Make sure no reclaim-FS
+ * happens while holding this lock anywhere to prevent deadlocks when
+ * an MMU notifier runs in reclaim-FS context.
+ */
+static inline void dqm_lock(struct device_queue_manager *dqm)
+{
+	mutex_lock(&dqm->lock_hidden);
+	dqm->saved_flags = memalloc_nofs_save();
+}
+static inline void dqm_unlock(struct device_queue_manager *dqm)
+{
+	memalloc_nofs_restore(dqm->saved_flags);
+	mutex_unlock(&dqm->lock_hidden);
+}
+
 #endif /* KFD_DEVICE_QUEUE_MANAGER_H_ */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
index 79e5bcf6367c..417515332c35 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
@@ -60,7 +60,7 @@ static int update_qpd_v9(struct device_queue_manager *dqm,
 		qpd->sh_mem_config =
 				SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
 					SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT;
-		if (vega10_noretry &&
+		if (noretry &&
 		    !dqm->dev->device_info->needs_iommu_device)
 			qpd->sh_mem_config |=
 				1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
index c3744d89352c..ebe79bf00145 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
@@ -188,9 +188,9 @@ void __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd,
 	*doorbell_off = kfd->doorbell_id_offset + inx;
 
 	pr_debug("Get kernel queue doorbell\n"
-			 "     doorbell offset   == 0x%08X\n"
-			 "     kernel address    == %p\n",
-		*doorbell_off, (kfd->doorbell_kernel_ptr + inx));
+			"     doorbell offset   == 0x%08X\n"
+			"     doorbell index    == 0x%x\n",
+		*doorbell_off, inx);
 
 	return kfd->doorbell_kernel_ptr + inx;
 }
@@ -199,7 +199,8 @@ void kfd_release_kernel_doorbell(struct kfd_dev *kfd, u32 __iomem *db_addr)
 {
 	unsigned int inx;
 
-	inx = (unsigned int)(db_addr - kfd->doorbell_kernel_ptr);
+	inx = (unsigned int)(db_addr - kfd->doorbell_kernel_ptr)
+		* sizeof(u32) / kfd->device_info->doorbell_size;
 
 	mutex_lock(&kfd->doorbell_mutex);
 	__clear_bit(inx, kfd->doorbell_available_index);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 5562e94e786a..e9f0e0a1b41c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -850,6 +850,13 @@ static void lookup_events_by_type_and_signal(struct kfd_process *p,
 				ev->memory_exception_data = *ev_data;
 		}
 
+	if (type == KFD_EVENT_TYPE_MEMORY) {
+		dev_warn(kfd_device,
+			"Sending SIGSEGV to HSA Process with PID %d ",
+				p->lead_thread->pid);
+		send_sig(SIGSEGV, p->lead_thread, 0);
+	}
+
 	/* Send SIGTERM no event of type "type" has been found*/
 	if (send_signal) {
 		if (send_sigterm) {
@@ -904,34 +911,41 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
 	memory_exception_data.failure.NotPresent = 1;
 	memory_exception_data.failure.NoExecute = 0;
 	memory_exception_data.failure.ReadOnly = 0;
-	if (vma) {
-		if (vma->vm_start > address) {
-			memory_exception_data.failure.NotPresent = 1;
-			memory_exception_data.failure.NoExecute = 0;
+	if (vma && address >= vma->vm_start) {
+		memory_exception_data.failure.NotPresent = 0;
+
+		if (is_write_requested && !(vma->vm_flags & VM_WRITE))
+			memory_exception_data.failure.ReadOnly = 1;
+		else
 			memory_exception_data.failure.ReadOnly = 0;
-		} else {
-			memory_exception_data.failure.NotPresent = 0;
-			if (is_write_requested && !(vma->vm_flags & VM_WRITE))
-				memory_exception_data.failure.ReadOnly = 1;
-			else
-				memory_exception_data.failure.ReadOnly = 0;
-			if (is_execute_requested && !(vma->vm_flags & VM_EXEC))
-				memory_exception_data.failure.NoExecute = 1;
-			else
-				memory_exception_data.failure.NoExecute = 0;
-		}
+
+		if (is_execute_requested && !(vma->vm_flags & VM_EXEC))
+			memory_exception_data.failure.NoExecute = 1;
+		else
+			memory_exception_data.failure.NoExecute = 0;
 	}
 
 	up_read(&mm->mmap_sem);
 	mmput(mm);
 
-	mutex_lock(&p->event_mutex);
+	pr_debug("notpresent %d, noexecute %d, readonly %d\n",
+			memory_exception_data.failure.NotPresent,
+			memory_exception_data.failure.NoExecute,
+			memory_exception_data.failure.ReadOnly);
 
-	/* Lookup events by type and signal them */
-	lookup_events_by_type_and_signal(p, KFD_EVENT_TYPE_MEMORY,
-			&memory_exception_data);
+	/* Workaround on Raven to not kill the process when memory is freed
+	 * before IOMMU is able to finish processing all the excessive PPRs
+	 */
+	if (dev->device_info->asic_family != CHIP_RAVEN) {
+		mutex_lock(&p->event_mutex);
+
+		/* Lookup events by type and signal them */
+		lookup_events_by_type_and_signal(p, KFD_EVENT_TYPE_MEMORY,
+				&memory_exception_data);
+
+		mutex_unlock(&p->event_mutex);
+	}
 
-	mutex_unlock(&p->event_mutex);
 	kfd_unref_process(p);
 }
 #endif /* KFD_SUPPORT_IOMMU_V2 */
@@ -956,3 +970,67 @@ void kfd_signal_hw_exception_event(unsigned int pasid)
 	mutex_unlock(&p->event_mutex);
 	kfd_unref_process(p);
 }
+
+void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
+				struct kfd_vm_fault_info *info)
+{
+	struct kfd_event *ev;
+	uint32_t id;
+	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);
+	struct kfd_hsa_memory_exception_data memory_exception_data;
+
+	if (!p)
+		return; /* Presumably process exited. */
+	memset(&memory_exception_data, 0, sizeof(memory_exception_data));
+	memory_exception_data.gpu_id = dev->id;
+	memory_exception_data.failure.imprecise = 1;
+	/* Set failure reason */
+	if (info) {
+		memory_exception_data.va = (info->page_addr) << PAGE_SHIFT;
+		memory_exception_data.failure.NotPresent =
+			info->prot_valid ? 1 : 0;
+		memory_exception_data.failure.NoExecute =
+			info->prot_exec ? 1 : 0;
+		memory_exception_data.failure.ReadOnly =
+			info->prot_write ? 1 : 0;
+		memory_exception_data.failure.imprecise = 0;
+	}
+	mutex_lock(&p->event_mutex);
+
+	id = KFD_FIRST_NONSIGNAL_EVENT_ID;
+	idr_for_each_entry_continue(&p->event_idr, ev, id)
+		if (ev->type == KFD_EVENT_TYPE_MEMORY) {
+			ev->memory_exception_data = memory_exception_data;
+			set_event(ev);
+		}
+
+	mutex_unlock(&p->event_mutex);
+	kfd_unref_process(p);
+}
+
+void kfd_signal_reset_event(struct kfd_dev *dev)
+{
+	struct kfd_hsa_hw_exception_data hw_exception_data;
+	struct kfd_process *p;
+	struct kfd_event *ev;
+	unsigned int temp;
+	uint32_t id, idx;
+
+	/* Whole gpu reset caused by GPU hang and memory is lost */
+	memset(&hw_exception_data, 0, sizeof(hw_exception_data));
+	hw_exception_data.gpu_id = dev->id;
+	hw_exception_data.memory_lost = 1;
+
+	idx = srcu_read_lock(&kfd_processes_srcu);
+	hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) {
+		mutex_lock(&p->event_mutex);
+		id = KFD_FIRST_NONSIGNAL_EVENT_ID;
+		idr_for_each_entry_continue(&p->event_idr, ev, id)
+			if (ev->type == KFD_EVENT_TYPE_HW_EXCEPTION) {
+				ev->hw_exception_data = hw_exception_data;
+				set_event(ev);
+			}
+		mutex_unlock(&p->event_mutex);
+	}
+	srcu_read_unlock(&kfd_processes_srcu, idx);
+}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_events.h
index abca5bfebbff..c7ac6c73af86 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.h
@@ -66,6 +66,7 @@ struct kfd_event {
 	/* type specific data */
 	union {
 		struct kfd_hsa_memory_exception_data memory_exception_data;
+		struct kfd_hsa_hw_exception_data hw_exception_data;
 	};
 };
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
index 37029baa3346..f836897bbf58 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
@@ -26,7 +26,9 @@
 
 
 static bool event_interrupt_isr_v9(struct kfd_dev *dev,
-					const uint32_t *ih_ring_entry)
+					const uint32_t *ih_ring_entry,
+					uint32_t *patched_ihre,
+					bool *patched_flag)
 {
 	uint16_t source_id, client_id, pasid, vmid;
 	const uint32_t *data = ih_ring_entry;
@@ -57,7 +59,9 @@ static bool event_interrupt_isr_v9(struct kfd_dev *dev,
 	return source_id == SOC15_INTSRC_CP_END_OF_PIPE ||
 		source_id == SOC15_INTSRC_SDMA_TRAP ||
 		source_id == SOC15_INTSRC_SQ_INTERRUPT_MSG ||
-		source_id == SOC15_INTSRC_CP_BAD_OPCODE;
+		source_id == SOC15_INTSRC_CP_BAD_OPCODE ||
+		client_id == SOC15_IH_CLIENTID_VMC ||
+		client_id == SOC15_IH_CLIENTID_UTCL2;
 }
 
 static void event_interrupt_wq_v9(struct kfd_dev *dev,
@@ -82,7 +86,19 @@ static void event_interrupt_wq_v9(struct kfd_dev *dev,
 		kfd_signal_hw_exception_event(pasid);
 	else if (client_id == SOC15_IH_CLIENTID_VMC ||
 		 client_id == SOC15_IH_CLIENTID_UTCL2) {
-		/* TODO */
+		struct kfd_vm_fault_info info = {0};
+		uint16_t ring_id = SOC15_RING_ID_FROM_IH_ENTRY(ih_ring_entry);
+
+		info.vmid = vmid;
+		info.mc_id = client_id;
+		info.page_addr = ih_ring_entry[4] |
+			(uint64_t)(ih_ring_entry[5] & 0xf) << 32;
+		info.prot_valid = ring_id & 0x08;
+		info.prot_read  = ring_id & 0x10;
+		info.prot_write = ring_id & 0x20;
+
+		kfd_process_vm_fault(dev->dqm, pasid);
+		kfd_signal_vm_fault_event(dev, pasid, &info);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
index db6d9336b80d..c56ac47cd318 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
@@ -151,13 +151,15 @@ static void interrupt_wq(struct work_struct *work)
 								ih_ring_entry);
 }
 
-bool interrupt_is_wanted(struct kfd_dev *dev, const uint32_t *ih_ring_entry)
+bool interrupt_is_wanted(struct kfd_dev *dev,
+			const uint32_t *ih_ring_entry,
+			uint32_t *patched_ihre, bool *flag)
 {
 	/* integer and bitwise OR so there is no boolean short-circuiting */
 	unsigned int wanted = 0;
 
 	wanted |= dev->device_info->event_interrupt_class->interrupt_isr(dev,
-								ih_ring_entry);
+					 ih_ring_entry, patched_ihre, flag);
 
 	return wanted != 0;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
index c71817963eea..7a61f38c09e6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
@@ -190,7 +190,7 @@ static int iommu_invalid_ppr_cb(struct pci_dev *pdev, int pasid,
 {
 	struct kfd_dev *dev;
 
-	dev_warn(kfd_device,
+	dev_warn_ratelimited(kfd_device,
 			"Invalid PPR device %x:%x.%x pasid %d address 0x%lX flags 0x%X",
 			PCI_BUS_NUM(pdev->devfn),
 			PCI_SLOT(pdev->devfn),
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
index 476951d8c91c..9f84b4d9fb88 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
@@ -59,7 +59,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 	switch (type) {
 	case KFD_QUEUE_TYPE_DIQ:
 	case KFD_QUEUE_TYPE_HIQ:
-		kq->mqd = dev->dqm->ops.get_mqd_manager(dev->dqm,
+		kq->mqd_mgr = dev->dqm->ops.get_mqd_manager(dev->dqm,
 						KFD_MQD_TYPE_HIQ);
 		break;
 	default:
@@ -67,7 +67,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 		return false;
 	}
 
-	if (!kq->mqd)
+	if (!kq->mqd_mgr)
 		return false;
 
 	prop.doorbell_ptr = kfd_get_kernel_doorbell(dev, &prop.doorbell_off);
@@ -123,6 +123,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 	prop.write_ptr = (uint32_t *) kq->wptr_gpu_addr;
 	prop.eop_ring_buffer_address = kq->eop_gpu_addr;
 	prop.eop_ring_buffer_size = PAGE_SIZE;
+	prop.cu_mask = NULL;
 
 	if (init_queue(&kq->queue, &prop) != 0)
 		goto err_init_queue;
@@ -130,7 +131,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 	kq->queue->device = dev;
 	kq->queue->process = kfd_get_process(current);
 
-	retval = kq->mqd->init_mqd(kq->mqd, &kq->queue->mqd,
+	retval = kq->mqd_mgr->init_mqd(kq->mqd_mgr, &kq->queue->mqd,
 					&kq->queue->mqd_mem_obj,
 					&kq->queue->gart_mqd_addr,
 					&kq->queue->properties);
@@ -142,9 +143,9 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 		pr_debug("Assigning hiq to hqd\n");
 		kq->queue->pipe = KFD_CIK_HIQ_PIPE;
 		kq->queue->queue = KFD_CIK_HIQ_QUEUE;
-		kq->mqd->load_mqd(kq->mqd, kq->queue->mqd, kq->queue->pipe,
-				  kq->queue->queue, &kq->queue->properties,
-				  NULL);
+		kq->mqd_mgr->load_mqd(kq->mqd_mgr, kq->queue->mqd,
+				kq->queue->pipe, kq->queue->queue,
+				&kq->queue->properties, NULL);
 	} else {
 		/* allocate fence for DIQ */
 
@@ -182,7 +183,7 @@ err_get_kernel_doorbell:
 static void uninitialize(struct kernel_queue *kq)
 {
 	if (kq->queue->properties.type == KFD_QUEUE_TYPE_HIQ)
-		kq->mqd->destroy_mqd(kq->mqd,
+		kq->mqd_mgr->destroy_mqd(kq->mqd_mgr,
 					kq->queue->mqd,
 					KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
 					KFD_UNMAP_LATENCY_MS,
@@ -191,7 +192,8 @@ static void uninitialize(struct kernel_queue *kq)
 	else if (kq->queue->properties.type == KFD_QUEUE_TYPE_DIQ)
 		kfd_gtt_sa_free(kq->dev, kq->fence_mem_obj);
 
-	kq->mqd->uninit_mqd(kq->mqd, kq->queue->mqd, kq->queue->mqd_mem_obj);
+	kq->mqd_mgr->uninit_mqd(kq->mqd_mgr, kq->queue->mqd,
+				kq->queue->mqd_mem_obj);
 
 	kfd_gtt_sa_free(kq->dev, kq->rptr_mem);
 	kfd_gtt_sa_free(kq->dev, kq->wptr_mem);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h
index 97aff2041a5d..a7116a939029 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h
@@ -70,7 +70,7 @@ struct kernel_queue {
 
 	/* data */
 	struct kfd_dev		*dev;
-	struct mqd_manager	*mqd;
+	struct mqd_manager	*mqd_mgr;
 	struct queue		*queue;
 	uint64_t		pending_wptr64;
 	uint32_t		pending_wptr;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
index 76bf2dc8aec4..6e1f5c7c2d4b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
@@ -47,6 +47,8 @@ static const struct kgd2kfd_calls kgd2kfd = {
 	.resume_mm	= kgd2kfd_resume_mm,
 	.schedule_evict_and_restore_process =
 			  kgd2kfd_schedule_evict_and_restore_process,
+	.pre_reset	= kgd2kfd_pre_reset,
+	.post_reset	= kgd2kfd_post_reset,
 };
 
 int sched_policy = KFD_SCHED_POLICY_HWS;
@@ -61,7 +63,7 @@ MODULE_PARM_DESC(hws_max_conc_proc,
 
 int cwsr_enable = 1;
 module_param(cwsr_enable, int, 0444);
-MODULE_PARM_DESC(cwsr_enable, "CWSR enable (0 = Off, 1 = On (Default))");
+MODULE_PARM_DESC(cwsr_enable, "CWSR enable (0 = off, 1 = on (default))");
 
 int max_num_of_queues_per_device = KFD_MAX_NUM_OF_QUEUES_PER_DEVICE_DEFAULT;
 module_param(max_num_of_queues_per_device, int, 0444);
@@ -83,13 +85,19 @@ module_param(ignore_crat, int, 0444);
 MODULE_PARM_DESC(ignore_crat,
 	"Ignore CRAT table during KFD initialization (0 = use CRAT (default), 1 = ignore CRAT)");
 
-int vega10_noretry;
-module_param_named(noretry, vega10_noretry, int, 0644);
+int noretry;
+module_param(noretry, int, 0644);
 MODULE_PARM_DESC(noretry,
-	"Set sh_mem_config.retry_disable on Vega10 (0 = retry enabled (default), 1 = retry disabled)");
+	"Set sh_mem_config.retry_disable on GFXv9+ dGPUs (0 = retry enabled (default), 1 = retry disabled)");
+
+int halt_if_hws_hang;
+module_param(halt_if_hws_hang, int, 0644);
+MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (default), 1 = on)");
+
 
 static int amdkfd_init_completed;
 
+
 int kgd2kfd_init(unsigned int interface_version,
 		const struct kgd2kfd_calls **g2f)
 {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
index 4b8eb506642b..3bc25ab84f34 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
@@ -21,7 +21,7 @@
  *
  */
 
-#include "kfd_priv.h"
+#include "kfd_mqd_manager.h"
 
 struct mqd_manager *mqd_manager_init(enum KFD_MQD_TYPE type,
 					struct kfd_dev *dev)
@@ -48,3 +48,42 @@ struct mqd_manager *mqd_manager_init(enum KFD_MQD_TYPE type,
 
 	return NULL;
 }
+
+void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
+		const uint32_t *cu_mask, uint32_t cu_mask_count,
+		uint32_t *se_mask)
+{
+	struct kfd_cu_info cu_info;
+	uint32_t cu_per_sh[4] = {0};
+	int i, se, cu = 0;
+
+	mm->dev->kfd2kgd->get_cu_info(mm->dev->kgd, &cu_info);
+
+	if (cu_mask_count > cu_info.cu_active_number)
+		cu_mask_count = cu_info.cu_active_number;
+
+	for (se = 0; se < cu_info.num_shader_engines; se++)
+		for (i = 0; i < 4; i++)
+			cu_per_sh[se] += hweight32(cu_info.cu_bitmap[se][i]);
+
+	/* Symmetrically map cu_mask to all SEs:
+	 * cu_mask[0] bit0 -> se_mask[0] bit0;
+	 * cu_mask[0] bit1 -> se_mask[1] bit0;
+	 * ... (if # SE is 4)
+	 * cu_mask[0] bit4 -> se_mask[0] bit1;
+	 * ...
+	 */
+	se = 0;
+	for (i = 0; i < cu_mask_count; i++) {
+		if (cu_mask[i / 32] & (1 << (i % 32)))
+			se_mask[se] |= 1 << cu;
+
+		do {
+			se++;
+			if (se == cu_info.num_shader_engines) {
+				se = 0;
+				cu++;
+			}
+		} while (cu >= cu_per_sh[se] && cu < 32);
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
index 8972bcfbf701..4e84052d4e21 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
@@ -93,4 +93,8 @@ struct mqd_manager {
 	struct kfd_dev	*dev;
 };
 
+void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
+		const uint32_t *cu_mask, uint32_t cu_mask_count,
+		uint32_t *se_mask);
+
 #endif /* KFD_MQD_MANAGER_H_ */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
index 06eaa218eba6..47243165a082 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
@@ -41,6 +41,31 @@ static inline struct cik_sdma_rlc_registers *get_sdma_mqd(void *mqd)
 	return (struct cik_sdma_rlc_registers *)mqd;
 }
 
+static void update_cu_mask(struct mqd_manager *mm, void *mqd,
+			struct queue_properties *q)
+{
+	struct cik_mqd *m;
+	uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */
+
+	if (q->cu_mask_count == 0)
+		return;
+
+	mqd_symmetrically_map_cu_mask(mm,
+		q->cu_mask, q->cu_mask_count, se_mask);
+
+	m = get_mqd(mqd);
+	m->compute_static_thread_mgmt_se0 = se_mask[0];
+	m->compute_static_thread_mgmt_se1 = se_mask[1];
+	m->compute_static_thread_mgmt_se2 = se_mask[2];
+	m->compute_static_thread_mgmt_se3 = se_mask[3];
+
+	pr_debug("Update cu mask to %#x %#x %#x %#x\n",
+		m->compute_static_thread_mgmt_se0,
+		m->compute_static_thread_mgmt_se1,
+		m->compute_static_thread_mgmt_se2,
+		m->compute_static_thread_mgmt_se3);
+}
+
 static int init_mqd(struct mqd_manager *mm, void **mqd,
 		struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr,
 		struct queue_properties *q)
@@ -196,6 +221,8 @@ static int __update_mqd(struct mqd_manager *mm, void *mqd,
 	if (q->format == KFD_QUEUE_FORMAT_AQL)
 		m->cp_hqd_pq_control |= NO_UPDATE_RPTR;
 
+	update_cu_mask(mm, mqd, q);
+
 	q->is_active = (q->queue_size > 0 &&
 			q->queue_address != 0 &&
 			q->queue_percent > 0 &&
@@ -408,7 +435,7 @@ struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type,
 	if (WARN_ON(type >= KFD_MQD_TYPE_MAX))
 		return NULL;
 
-	mqd = kzalloc(sizeof(*mqd), GFP_NOIO);
+	mqd = kzalloc(sizeof(*mqd), GFP_KERNEL);
 	if (!mqd)
 		return NULL;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index 684054ff02cd..f5fc3675f21e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -41,6 +41,31 @@ static inline struct v9_sdma_mqd *get_sdma_mqd(void *mqd)
 	return (struct v9_sdma_mqd *)mqd;
 }
 
+static void update_cu_mask(struct mqd_manager *mm, void *mqd,
+			struct queue_properties *q)
+{
+	struct v9_mqd *m;
+	uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */
+
+	if (q->cu_mask_count == 0)
+		return;
+
+	mqd_symmetrically_map_cu_mask(mm,
+		q->cu_mask, q->cu_mask_count, se_mask);
+
+	m = get_mqd(mqd);
+	m->compute_static_thread_mgmt_se0 = se_mask[0];
+	m->compute_static_thread_mgmt_se1 = se_mask[1];
+	m->compute_static_thread_mgmt_se2 = se_mask[2];
+	m->compute_static_thread_mgmt_se3 = se_mask[3];
+
+	pr_debug("update cu mask to %#x %#x %#x %#x\n",
+		m->compute_static_thread_mgmt_se0,
+		m->compute_static_thread_mgmt_se1,
+		m->compute_static_thread_mgmt_se2,
+		m->compute_static_thread_mgmt_se3);
+}
+
 static int init_mqd(struct mqd_manager *mm, void **mqd,
 			struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr,
 			struct queue_properties *q)
@@ -55,7 +80,7 @@ static int init_mqd(struct mqd_manager *mm, void **mqd,
 	 * instead of sub-allocation function.
 	 */
 	if (kfd->cwsr_enabled && (q->type == KFD_QUEUE_TYPE_COMPUTE)) {
-		*mqd_mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_NOIO);
+		*mqd_mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_KERNEL);
 		if (!*mqd_mem_obj)
 			return -ENOMEM;
 		retval = kfd->kfd2kgd->init_gtt_mem_allocation(kfd->kgd,
@@ -198,6 +223,8 @@ static int update_mqd(struct mqd_manager *mm, void *mqd,
 	if (mm->dev->cwsr_enabled && q->ctx_save_restore_area_address)
 		m->cp_hqd_ctx_save_control = 0;
 
+	update_cu_mask(mm, mqd, q);
+
 	q->is_active = (q->queue_size > 0 &&
 			q->queue_address != 0 &&
 			q->queue_percent > 0 &&
@@ -393,7 +420,7 @@ struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type,
 	if (WARN_ON(type >= KFD_MQD_TYPE_MAX))
 		return NULL;
 
-	mqd = kzalloc(sizeof(*mqd), GFP_NOIO);
+	mqd = kzalloc(sizeof(*mqd), GFP_KERNEL);
 	if (!mqd)
 		return NULL;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
index 481307b8b4db..b81fda3754da 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
@@ -43,6 +43,31 @@ static inline struct vi_sdma_mqd *get_sdma_mqd(void *mqd)
 	return (struct vi_sdma_mqd *)mqd;
 }
 
+static void update_cu_mask(struct mqd_manager *mm, void *mqd,
+			struct queue_properties *q)
+{
+	struct vi_mqd *m;
+	uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */
+
+	if (q->cu_mask_count == 0)
+		return;
+
+	mqd_symmetrically_map_cu_mask(mm,
+		q->cu_mask, q->cu_mask_count, se_mask);
+
+	m = get_mqd(mqd);
+	m->compute_static_thread_mgmt_se0 = se_mask[0];
+	m->compute_static_thread_mgmt_se1 = se_mask[1];
+	m->compute_static_thread_mgmt_se2 = se_mask[2];
+	m->compute_static_thread_mgmt_se3 = se_mask[3];
+
+	pr_debug("Update cu mask to %#x %#x %#x %#x\n",
+		m->compute_static_thread_mgmt_se0,
+		m->compute_static_thread_mgmt_se1,
+		m->compute_static_thread_mgmt_se2,
+		m->compute_static_thread_mgmt_se3);
+}
+
 static int init_mqd(struct mqd_manager *mm, void **mqd,
 			struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr,
 			struct queue_properties *q)
@@ -196,6 +221,8 @@ static int __update_mqd(struct mqd_manager *mm, void *mqd,
 			atc_bit << CP_HQD_CTX_SAVE_CONTROL__ATC__SHIFT |
 			mtype << CP_HQD_CTX_SAVE_CONTROL__MTYPE__SHIFT;
 
+	update_cu_mask(mm, mqd, q);
+
 	q->is_active = (q->queue_size > 0 &&
 			q->queue_address != 0 &&
 			q->queue_percent > 0 &&
@@ -394,7 +421,7 @@ struct mqd_manager *mqd_manager_init_vi(enum KFD_MQD_TYPE type,
 	if (WARN_ON(type >= KFD_MQD_TYPE_MAX))
 		return NULL;
 
-	mqd = kzalloc(sizeof(*mqd), GFP_NOIO);
+	mqd = kzalloc(sizeof(*mqd), GFP_KERNEL);
 	if (!mqd)
 		return NULL;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
index c317feb43f69..1092631765cb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
@@ -418,4 +418,30 @@ out:
 	return 0;
 }
 
+int pm_debugfs_hang_hws(struct packet_manager *pm)
+{
+	uint32_t *buffer, size;
+	int r = 0;
+
+	size = pm->pmf->query_status_size;
+	mutex_lock(&pm->lock);
+	pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+			size / sizeof(uint32_t), (unsigned int **)&buffer);
+	if (!buffer) {
+		pr_err("Failed to allocate buffer on kernel queue\n");
+		r = -ENOMEM;
+		goto out;
+	}
+	memset(buffer, 0x55, size);
+	pm->priv_queue->ops.submit_packet(pm->priv_queue);
+
+	pr_info("Submitting %x %x %x %x %x %x %x to HIQ to hang the HWS.",
+		buffer[0], buffer[1], buffer[2], buffer[3],
+		buffer[4], buffer[5], buffer[6]);
+out:
+	mutex_unlock(&pm->lock);
+	return r;
+}
+
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 5e3990bb4c4b..f971710f1c91 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -73,7 +73,7 @@
 
 /*
  * When working with cp scheduler we should assign the HIQ manually or via
- * the radeon driver to a fixed hqd slot, here are the fixed HIQ hqd slot
+ * the amdgpu driver to a fixed hqd slot, here are the fixed HIQ hqd slot
  * definitions for Kaveri. In Kaveri only the first ME queues participates
  * in the cp scheduling taking that in mind we set the HIQ slot in the
  * second ME.
@@ -142,7 +142,12 @@ extern int ignore_crat;
 /*
  * Set sh_mem_config.retry_disable on Vega10
  */
-extern int vega10_noretry;
+extern int noretry;
+
+/*
+ * Halt if HWS hang is detected
+ */
+extern int halt_if_hws_hang;
 
 /**
  * enum kfd_sched_policy
@@ -180,9 +185,10 @@ enum cache_policy {
 
 struct kfd_event_interrupt_class {
 	bool (*interrupt_isr)(struct kfd_dev *dev,
-				const uint32_t *ih_ring_entry);
+			const uint32_t *ih_ring_entry, uint32_t *patched_ihre,
+			bool *patched_flag);
 	void (*interrupt_wq)(struct kfd_dev *dev,
-				const uint32_t *ih_ring_entry);
+			const uint32_t *ih_ring_entry);
 };
 
 struct kfd_device_info {
@@ -197,6 +203,7 @@ struct kfd_device_info {
 	bool supports_cwsr;
 	bool needs_iommu_device;
 	bool needs_pci_atomics;
+	unsigned int num_sdma_engines;
 };
 
 struct kfd_mem_obj {
@@ -415,6 +422,9 @@ struct queue_properties {
 	uint32_t ctl_stack_size;
 	uint64_t tba_addr;
 	uint64_t tma_addr;
+	/* Relevant for CU */
+	uint32_t cu_mask_count; /* Must be a multiple of 32 */
+	uint32_t *cu_mask;
 };
 
 /**
@@ -806,12 +816,18 @@ int kfd_interrupt_init(struct kfd_dev *dev);
 void kfd_interrupt_exit(struct kfd_dev *dev);
 void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry);
 bool enqueue_ih_ring_entry(struct kfd_dev *kfd,	const void *ih_ring_entry);
-bool interrupt_is_wanted(struct kfd_dev *dev, const uint32_t *ih_ring_entry);
+bool interrupt_is_wanted(struct kfd_dev *dev,
+				const uint32_t *ih_ring_entry,
+				uint32_t *patched_ihre, bool *flag);
 
 /* Power Management */
 void kgd2kfd_suspend(struct kfd_dev *kfd);
 int kgd2kfd_resume(struct kfd_dev *kfd);
 
+/* GPU reset */
+int kgd2kfd_pre_reset(struct kfd_dev *kfd);
+int kgd2kfd_post_reset(struct kfd_dev *kfd);
+
 /* amdkfd Apertures */
 int kfd_init_apertures(struct kfd_process *process);
 
@@ -838,6 +854,7 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm);
 struct kernel_queue *kernel_queue_init(struct kfd_dev *dev,
 					enum kfd_queue_type type);
 void kernel_queue_uninit(struct kernel_queue *kq);
+int kfd_process_vm_fault(struct device_queue_manager *dqm, unsigned int pasid);
 
 /* Process Queue Manager */
 struct process_queue_node {
@@ -858,6 +875,8 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid);
 int pqm_update_queue(struct process_queue_manager *pqm, unsigned int qid,
 			struct queue_properties *p);
+int pqm_set_cu_mask(struct process_queue_manager *pqm, unsigned int qid,
+			struct queue_properties *p);
 struct kernel_queue *pqm_get_kernel_queue(struct process_queue_manager *pqm,
 						unsigned int qid);
 
@@ -964,10 +983,17 @@ int kfd_event_create(struct file *devkfd, struct kfd_process *p,
 		     uint64_t *event_page_offset, uint32_t *event_slot_index);
 int kfd_event_destroy(struct kfd_process *p, uint32_t event_id);
 
+void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
+				struct kfd_vm_fault_info *info);
+
+void kfd_signal_reset_event(struct kfd_dev *dev);
+
 void kfd_flush_tlb(struct kfd_process_device *pdd);
 
 int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p);
 
+bool kfd_is_locked(void);
+
 /* Debugfs */
 #if defined(CONFIG_DEBUG_FS)
 
@@ -980,6 +1006,10 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data);
 int kfd_debugfs_rls_by_device(struct seq_file *m, void *data);
 int pm_debugfs_runlist(struct seq_file *m, void *data);
 
+int kfd_debugfs_hang_hws(struct kfd_dev *dev);
+int pm_debugfs_hang_hws(struct packet_manager *pm);
+int dqm_debugfs_execute_queues(struct device_queue_manager *dqm);
+
 #else
 
 static inline void kfd_debugfs_init(void) {}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 1d80b4f7c681..4694386cc623 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -244,6 +244,8 @@ struct kfd_process *kfd_get_process(const struct task_struct *thread)
 		return ERR_PTR(-EINVAL);
 
 	process = find_process(thread);
+	if (!process)
+		return ERR_PTR(-EINVAL);
 
 	return process;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index d65ce0436b31..c8cad9c078ae 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -186,8 +186,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 
 	switch (type) {
 	case KFD_QUEUE_TYPE_SDMA:
-		if (dev->dqm->queue_count >=
-			CIK_SDMA_QUEUES_PER_ENGINE * CIK_SDMA_ENGINE_NUM) {
+		if (dev->dqm->queue_count >= get_num_sdma_queues(dev->dqm)) {
 			pr_err("Over-subscription is not allowed for SDMA.\n");
 			retval = -EPERM;
 			goto err_create_queue;
@@ -209,7 +208,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 		     KFD_SCHED_POLICY_HWS_NO_OVERSUBSCRIPTION) &&
 		((dev->dqm->processes_count >= dev->vm_info.vmid_num_kfd) ||
 		(dev->dqm->queue_count >= get_queues_num(dev->dqm)))) {
-			pr_err("Over-subscription is not allowed in radeon_kfd.sched_policy == 1\n");
+			pr_debug("Over-subscription is not allowed when amdkfd.sched_policy == 1\n");
 			retval = -EPERM;
 			goto err_create_queue;
 		}
@@ -326,6 +325,8 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
 			if (retval != -ETIME)
 				goto err_destroy_queue;
 		}
+		kfree(pqn->q->properties.cu_mask);
+		pqn->q->properties.cu_mask = NULL;
 		uninit_queue(pqn->q);
 	}
 
@@ -366,6 +367,34 @@ int pqm_update_queue(struct process_queue_manager *pqm, unsigned int qid,
 	return 0;
 }
 
+int pqm_set_cu_mask(struct process_queue_manager *pqm, unsigned int qid,
+			struct queue_properties *p)
+{
+	int retval;
+	struct process_queue_node *pqn;
+
+	pqn = get_queue_by_qid(pqm, qid);
+	if (!pqn) {
+		pr_debug("No queue %d exists for update operation\n", qid);
+		return -EFAULT;
+	}
+
+	/* Free the old CU mask memory if it is already allocated, then
+	 * allocate memory for the new CU mask.
+	 */
+	kfree(pqn->q->properties.cu_mask);
+
+	pqn->q->properties.cu_mask_count = p->cu_mask_count;
+	pqn->q->properties.cu_mask = p->cu_mask;
+
+	retval = pqn->q->device->dqm->ops.update_queue(pqn->q->device->dqm,
+							pqn->q);
+	if (retval != 0)
+		return retval;
+
+	return 0;
+}
+
 struct kernel_queue *pqm_get_kernel_queue(
 					struct process_queue_manager *pqm,
 					unsigned int qid)
@@ -387,7 +416,7 @@ int pqm_debugfs_mqds(struct seq_file *m, void *data)
 	struct process_queue_node *pqn;
 	struct queue *q;
 	enum KFD_MQD_TYPE mqd_type;
-	struct mqd_manager *mqd_manager;
+	struct mqd_manager *mqd_mgr;
 	int r = 0;
 
 	list_for_each_entry(pqn, &pqm->queues, process_queue_list) {
@@ -410,11 +439,11 @@ int pqm_debugfs_mqds(struct seq_file *m, void *data)
 					   q->properties.type, q->device->id);
 				continue;
 			}
-			mqd_manager = q->device->dqm->ops.get_mqd_manager(
+			mqd_mgr = q->device->dqm->ops.get_mqd_manager(
 				q->device->dqm, mqd_type);
 		} else if (pqn->kq) {
 			q = pqn->kq->queue;
-			mqd_manager = pqn->kq->mqd;
+			mqd_mgr = pqn->kq->mqd_mgr;
 			switch (q->properties.type) {
 			case KFD_QUEUE_TYPE_DIQ:
 				seq_printf(m, "  DIQ on device %x\n",
@@ -434,7 +463,7 @@ int pqm_debugfs_mqds(struct seq_file *m, void *data)
 			continue;
 		}
 
-		r = mqd_manager->debugfs_show_mqd(m, q->mqd);
+		r = mqd_mgr->debugfs_show_mqd(m, q->mqd);
 		if (r != 0)
 			break;
 	}
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index d5d4586e6176..325083b0297e 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -9,23 +9,6 @@ config DRM_AMD_DC
 	  support for AMDGPU. This adds required support for Vega and
 	  Raven ASICs.
 
-config DRM_AMD_DC_FBC
-	bool "AMD FBC - Enable Frame Buffer Compression"
-	depends on DRM_AMD_DC
-	help
-	  Choose this option if you want to use frame buffer compression
-	  support.
-	  This is a power optimisation feature, check its availability
-	  on your hardware before enabling this option.
-
-
-config DRM_AMD_DC_DCN1_0
-	bool "DCN 1.0 Raven family"
-	depends on DRM_AMD_DC && X86
-	help
-	  Choose this option if you want to have
-	  RV family for display engine
-
 config DEBUG_KERNEL_DC
 	bool "Enable kgdb break in DC"
 	depends on DRM_AMD_DC
diff --git a/drivers/gpu/drm/amd/display/TODO b/drivers/gpu/drm/amd/display/TODO
index 357d59648401..a8a6c106e8c7 100644
--- a/drivers/gpu/drm/amd/display/TODO
+++ b/drivers/gpu/drm/amd/display/TODO
@@ -97,10 +97,10 @@ share it with drivers. But that's a very long term goal, and by far not just an
 issue with DC - other drivers, especially around DP sink handling, are equally
 guilty.
 
-19. The DC logger is still a rather sore thing, but I know that the DRM_DEBUG
-stuff just isn't up to the challenges either. We need to figure out something
-that integrates better with DRM and linux debug printing, while not being
-useless with filtering output. dynamic debug printing might be an option.
+19. DONE - The DC logger is still a rather sore thing, but I know that the
+DRM_DEBUG stuff just isn't up to the challenges either. We need to figure out
+something that integrates better with DRM and linux debug printing, while not
+being useless with filtering output. dynamic debug printing might be an option.
 
 20. Use kernel i2c device to program HDMI retimer. Some boards have an HDMI
 retimer that we need to program to pass PHY compliance. Currently that's
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
index af16973f2c41..94911871eb9b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
@@ -28,11 +28,11 @@
 AMDGPUDM = amdgpu_dm.o amdgpu_dm_irq.o amdgpu_dm_mst_types.o amdgpu_dm_color.o
 
 ifneq ($(CONFIG_DRM_AMD_DC),)
-AMDGPUDM += amdgpu_dm_services.o amdgpu_dm_helpers.o
+AMDGPUDM += amdgpu_dm_services.o amdgpu_dm_helpers.o amdgpu_dm_pp_smu.o
 endif
 
 ifneq ($(CONFIG_DEBUG_FS),)
-AMDGPUDM += amdgpu_dm_crc.o
+AMDGPUDM += amdgpu_dm_crc.o amdgpu_dm_debugfs.o
 endif
 
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/dc
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 770c6b24be0b..34f34823bab5 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -39,6 +39,9 @@
 #include "dm_helpers.h"
 #include "dm_services_types.h"
 #include "amdgpu_dm_mst_types.h"
+#if defined(CONFIG_DEBUG_FS)
+#include "amdgpu_dm_debugfs.h"
+#endif
 
 #include "ivsrcid/ivsrcid_vislands30.h"
 
@@ -57,7 +60,7 @@
 
 #include "modules/inc/mod_freesync.h"
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "ivsrcid/irqsrcs_dcn_1_0.h"
 
 #include "dcn/dcn_1_0_offset.h"
@@ -347,7 +350,6 @@ static void hotplug_notify_work_func(struct work_struct *work)
 	drm_kms_helper_hotplug_event(dev);
 }
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 /* Allocate memory for FBC compressed data  */
 static void amdgpu_dm_fbc_init(struct drm_connector *connector)
 {
@@ -388,7 +390,6 @@ static void amdgpu_dm_fbc_init(struct drm_connector *connector)
 	}
 
 }
-#endif
 
 
 /* Init display KMS
@@ -902,14 +903,14 @@ amdgpu_dm_update_connector_after_detect(struct amdgpu_dm_connector *aconnector)
 				(struct edid *) sink->dc_edid.raw_edid;
 
 
-			drm_mode_connector_update_edid_property(connector,
+			drm_connector_update_edid_property(connector,
 					aconnector->edid);
 		}
 		amdgpu_dm_add_sink_to_freesync_module(connector, aconnector->edid);
 
 	} else {
 		amdgpu_dm_remove_sink_from_freesync_module(connector);
-		drm_mode_connector_update_edid_property(connector, NULL);
+		drm_connector_update_edid_property(connector, NULL);
 		aconnector->num_modes = 0;
 		aconnector->dc_sink = NULL;
 		aconnector->edid = NULL;
@@ -1040,7 +1041,7 @@ static void handle_hpd_rx_irq(void *param)
 	if (dc_link->type != dc_connection_mst_branch)
 		mutex_lock(&aconnector->hpd_lock);
 
-	if (dc_link_handle_hpd_rx_irq(dc_link, NULL) &&
+	if (dc_link_handle_hpd_rx_irq(dc_link, NULL, NULL) &&
 			!is_mst_root_connector) {
 		/* Downstream Port status changed. */
 		if (dc_link_detect(dc_link, DETECT_REASON_HPDRX)) {
@@ -1191,7 +1192,7 @@ static int dce110_register_irq_handlers(struct amdgpu_device *adev)
 	return 0;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 /* Register IRQ sources and initialize IRQ callbacks */
 static int dcn10_register_irq_handlers(struct amdgpu_device *adev)
 {
@@ -1319,7 +1320,12 @@ static int amdgpu_dm_backlight_update_status(struct backlight_device *bd)
 
 static int amdgpu_dm_backlight_get_brightness(struct backlight_device *bd)
 {
-	return bd->props.brightness;
+	struct amdgpu_display_manager *dm = bl_get_data(bd);
+	int ret = dc_link_get_backlight_level(dm->backlight_link);
+
+	if (ret == DC_ERROR_UNEXPECTED)
+		return bd->props.brightness;
+	return ret;
 }
 
 static const struct backlight_ops amdgpu_dm_backlight_ops = {
@@ -1334,6 +1340,7 @@ amdgpu_dm_register_backlight_device(struct amdgpu_display_manager *dm)
 	struct backlight_properties props = { 0 };
 
 	props.max_brightness = AMDGPU_MAX_BL_LEVEL;
+	props.brightness = AMDGPU_MAX_BL_LEVEL;
 	props.type = BACKLIGHT_RAW;
 
 	snprintf(bl_name, sizeof(bl_name), "amdgpu_bl%d",
@@ -1525,16 +1532,12 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 			goto fail;
 		}
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case CHIP_RAVEN:
 		if (dcn10_register_irq_handlers(dm->adev)) {
 			DRM_ERROR("DM: Failed to initialize IRQ\n");
 			goto fail;
 		}
-		/*
-		 * Temporary disable until pplib/smu interaction is implemented
-		 */
-		dm->dc->debug.disable_stutter = true;
 		break;
 #endif
 	default:
@@ -1542,6 +1545,9 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 		goto fail;
 	}
 
+	if (adev->asic_type != CHIP_CARRIZO && adev->asic_type != CHIP_STONEY)
+		dm->dc->debug.disable_stutter = amdgpu_pp_feature_mask & PP_STUTTER_MODE ? false : true;
+
 	return 0;
 fail:
 	kfree(aencoder);
@@ -1573,18 +1579,6 @@ static void dm_bandwidth_update(struct amdgpu_device *adev)
 	/* TODO: implement later */
 }
 
-static void dm_set_backlight_level(struct amdgpu_encoder *amdgpu_encoder,
-				     u8 level)
-{
-	/* TODO: translate amdgpu_encoder to display_index and call DAL */
-}
-
-static u8 dm_get_backlight_level(struct amdgpu_encoder *amdgpu_encoder)
-{
-	/* TODO: translate amdgpu_encoder to display_index and call DAL */
-	return 0;
-}
-
 static int amdgpu_notify_freesync(struct drm_device *dev, void *data,
 				struct drm_file *filp)
 {
@@ -1613,10 +1607,8 @@ static int amdgpu_notify_freesync(struct drm_device *dev, void *data,
 static const struct amdgpu_display_funcs dm_display_funcs = {
 	.bandwidth_update = dm_bandwidth_update, /* called unconditionally */
 	.vblank_get_counter = dm_vblank_get_counter,/* called unconditionally */
-	.backlight_set_level =
-		dm_set_backlight_level,/* called unconditionally */
-	.backlight_get_level =
-		dm_get_backlight_level,/* called unconditionally */
+	.backlight_set_level = NULL, /* never called for DC */
+	.backlight_get_level = NULL, /* never called for DC */
 	.hpd_sense = NULL,/* called unconditionally */
 	.hpd_set_polarity = NULL, /* called unconditionally */
 	.hpd_get_gpio_reg = NULL, /* VBIOS parsing. DAL does it. */
@@ -1724,7 +1716,7 @@ static int dm_early_init(void *handle)
 		adev->mode_info.num_dig = 6;
 		adev->mode_info.plane_type = dm_plane_type_default;
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case CHIP_RAVEN:
 		adev->mode_info.num_crtc = 4;
 		adev->mode_info.num_hpd = 4;
@@ -2123,13 +2115,8 @@ convert_color_depth_from_display_info(const struct drm_connector *connector)
 static enum dc_aspect_ratio
 get_aspect_ratio(const struct drm_display_mode *mode_in)
 {
-	int32_t width = mode_in->crtc_hdisplay * 9;
-	int32_t height = mode_in->crtc_vdisplay * 16;
-
-	if ((width - height) < 10 && (width - height) > -10)
-		return ASPECT_RATIO_16_9;
-	else
-		return ASPECT_RATIO_4_3;
+	/* 1-1 mapping, since both enums follow the HDMI spec. */
+	return (enum dc_aspect_ratio) mode_in->picture_aspect_ratio;
 }
 
 static enum dc_color_space
@@ -3093,15 +3080,25 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane,
 	else
 		domain = AMDGPU_GEM_DOMAIN_VRAM;
 
-	r = amdgpu_bo_pin(rbo, domain, &afb->address);
-	amdgpu_bo_unreserve(rbo);
-
+	r = amdgpu_bo_pin(rbo, domain);
 	if (unlikely(r != 0)) {
 		if (r != -ERESTARTSYS)
 			DRM_ERROR("Failed to pin framebuffer with error %d\n", r);
+		amdgpu_bo_unreserve(rbo);
 		return r;
 	}
 
+	r = amdgpu_ttm_alloc_gart(&rbo->tbo);
+	if (unlikely(r != 0)) {
+		amdgpu_bo_unpin(rbo);
+		amdgpu_bo_unreserve(rbo);
+		DRM_ERROR("%p bind failed\n", rbo);
+		return r;
+	}
+	amdgpu_bo_unreserve(rbo);
+
+	afb->address = amdgpu_bo_gpu_offset(rbo);
+
 	amdgpu_bo_ref(rbo);
 
 	if (dm_plane_state_new->dc_state &&
@@ -3471,12 +3468,15 @@ static int amdgpu_dm_connector_get_modes(struct drm_connector *connector)
 	struct edid *edid = amdgpu_dm_connector->edid;
 
 	encoder = helper->best_encoder(connector);
-	amdgpu_dm_connector_ddc_get_modes(connector, edid);
-	amdgpu_dm_connector_add_common_modes(encoder, connector);
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
+	if (!edid || !drm_edid_is_valid(edid)) {
+		drm_add_modes_noedid(connector, 640, 480);
+	} else {
+		amdgpu_dm_connector_ddc_get_modes(connector, edid);
+		amdgpu_dm_connector_add_common_modes(encoder, connector);
+	}
 	amdgpu_dm_fbc_init(connector);
-#endif
+
 	return amdgpu_dm_connector->num_modes;
 }
 
@@ -3495,7 +3495,6 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm,
 	aconnector->base.stereo_allowed = false;
 	aconnector->base.dpms = DRM_MODE_DPMS_OFF;
 	aconnector->hpd.hpd = AMDGPU_HPD_NONE; /* not used */
-
 	mutex_init(&aconnector->hpd_lock);
 
 	/* configure support HPD hot plug connector_>polled default value is 0
@@ -3504,9 +3503,13 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm,
 	switch (connector_type) {
 	case DRM_MODE_CONNECTOR_HDMIA:
 		aconnector->base.polled = DRM_CONNECTOR_POLL_HPD;
+		aconnector->base.ycbcr_420_allowed =
+			link->link_enc->features.ycbcr420_supported ? true : false;
 		break;
 	case DRM_MODE_CONNECTOR_DisplayPort:
 		aconnector->base.polled = DRM_CONNECTOR_POLL_HPD;
+		aconnector->base.ycbcr_420_allowed =
+			link->link_enc->features.ycbcr420_supported ? true : false;
 		break;
 	case DRM_MODE_CONNECTOR_DVID:
 		aconnector->base.polled = DRM_CONNECTOR_POLL_HPD;
@@ -3659,10 +3662,17 @@ static int amdgpu_dm_connector_init(struct amdgpu_display_manager *dm,
 		link,
 		link_index);
 
-	drm_mode_connector_attach_encoder(
+	drm_connector_attach_encoder(
 		&aconnector->base, &aencoder->base);
 
 	drm_connector_register(&aconnector->base);
+#if defined(CONFIG_DEBUG_FS)
+	res = connector_debugfs_init(aconnector);
+	if (res) {
+		DRM_ERROR("Failed to create debugfs for connector");
+		goto out_free;
+	}
+#endif
 
 	if (connector_type == DRM_MODE_CONNECTOR_DisplayPort
 		|| connector_type == DRM_MODE_CONNECTOR_eDP)
@@ -3959,8 +3969,6 @@ static void amdgpu_dm_do_flip(struct drm_crtc *crtc,
 
 	/* Flip */
 	spin_lock_irqsave(&crtc->dev->event_lock, flags);
-	/* update crtc fb */
-	crtc->primary->fb = fb;
 
 	WARN_ON(acrtc->pflip_status != AMDGPU_FLIP_NONE);
 	WARN_ON(!acrtc_state->stream);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index d5aa89ad5571..a29dc35954c9 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -72,13 +72,11 @@ struct irq_list_head {
 	struct work_struct work;
 };
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 struct dm_comressor_info {
 	void *cpu_addr;
 	struct amdgpu_bo *bo_ptr;
 	uint64_t gpu_addr;
 };
-#endif
 
 
 struct amdgpu_display_manager {
@@ -129,9 +127,8 @@ struct amdgpu_display_manager {
 	 * Caches device atomic state for suspend/resume
 	 */
 	struct drm_atomic_state *cached_state;
-#if defined(CONFIG_DRM_AMD_DC_FBC)
+
 	struct dm_comressor_info compressor;
-#endif
 };
 
 struct amdgpu_dm_connector {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
index b329393307e5..326f6fb7e0bc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
@@ -231,18 +231,21 @@ void amdgpu_dm_set_ctm(struct dm_crtc_state *crtc)
  * preparation for hardware commit. If no lut is specified by user, we default
  * to SRGB degamma.
  *
- * Currently, we only support degamma bypass, or preprogrammed SRGB degamma.
- * Programmable degamma is not supported, and an attempt to do so will return
- * -EINVAL.
+ * We support degamma bypass, predefined SRGB, and custom degamma
  *
  * RETURNS:
- * 0 on success, -EINVAL if custom degamma curve is given.
+ * 0 on success
+ * -EINVAL if crtc_state has a degamma_lut of invalid size
+ * -ENOMEM if gamma allocation fails
  */
 int amdgpu_dm_set_degamma_lut(struct drm_crtc_state *crtc_state,
 			      struct dc_plane_state *dc_plane_state)
 {
 	struct drm_property_blob *blob = crtc_state->degamma_lut;
 	struct drm_color_lut *lut;
+	uint32_t lut_size;
+	struct dc_gamma *gamma;
+	bool ret;
 
 	if (!blob) {
 		/* Default to SRGB */
@@ -258,11 +261,30 @@ int amdgpu_dm_set_degamma_lut(struct drm_crtc_state *crtc_state,
 		return 0;
 	}
 
-	/* Otherwise, assume SRGB, since programmable degamma is not
-	 * supported.
-	 */
-	dc_plane_state->in_transfer_func->type = TF_TYPE_PREDEFINED;
-	dc_plane_state->in_transfer_func->tf = TRANSFER_FUNCTION_SRGB;
-	return -EINVAL;
+	gamma = dc_create_gamma();
+	if (!gamma)
+		return -ENOMEM;
+
+	lut_size = blob->length / sizeof(struct drm_color_lut);
+	gamma->num_entries = lut_size;
+	if (gamma->num_entries == MAX_COLOR_LUT_ENTRIES)
+		gamma->type = GAMMA_CUSTOM;
+	else {
+		dc_gamma_release(&gamma);
+		return -EINVAL;
+	}
+
+	__drm_lut_to_dc_gamma(lut, gamma, false);
+
+	dc_plane_state->in_transfer_func->type = TF_TYPE_DISTRIBUTED_POINTS;
+	ret = mod_color_calculate_degamma_params(dc_plane_state->in_transfer_func, gamma, true);
+	dc_gamma_release(&gamma);
+	if (!ret) {
+		dc_plane_state->in_transfer_func->type = TF_TYPE_BYPASS;
+		DRM_ERROR("Out of memory when calculating degamma params\n");
+		return -ENOMEM;
+	}
+
+	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
new file mode 100644
index 000000000000..0d9e410ca01e
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -0,0 +1,722 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include <linux/debugfs.h>
+
+#include "dc.h"
+#include "amdgpu.h"
+#include "amdgpu_dm.h"
+#include "amdgpu_dm_debugfs.h"
+
+/* function description
+ * get/ set DP configuration: lane_count, link_rate, spread_spectrum
+ *
+ * valid lane count value: 1, 2, 4
+ * valid link rate value:
+ * 06h = 1.62Gbps per lane
+ * 0Ah = 2.7Gbps per lane
+ * 0Ch = 3.24Gbps per lane
+ * 14h = 5.4Gbps per lane
+ * 1Eh = 8.1Gbps per lane
+ *
+ * debugfs is located at /sys/kernel/debug/dri/0/DP-x/link_settings
+ *
+ * --- to get dp configuration
+ *
+ * cat link_settings
+ *
+ * It will list current, verified, reported, preferred dp configuration.
+ * current -- for current video mode
+ * verified --- maximum configuration which pass link training
+ * reported --- DP rx report caps (DPCD register offset 0, 1 2)
+ * preferred --- user force settings
+ *
+ * --- set (or force) dp configuration
+ *
+ * echo <lane_count>  <link_rate> > link_settings
+ *
+ * for example, to force to  2 lane, 2.7GHz,
+ * echo 4 0xa > link_settings
+ *
+ * spread_spectrum could not be changed dynamically.
+ *
+ * in case invalid lane count, link rate are force, no hw programming will be
+ * done. please check link settings after force operation to see if HW get
+ * programming.
+ *
+ * cat link_settings
+ *
+ * check current and preferred settings.
+ *
+ */
+static ssize_t dp_link_settings_read(struct file *f, char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	struct amdgpu_dm_connector *connector = file_inode(f)->i_private;
+	struct dc_link *link = connector->dc_link;
+	char *rd_buf = NULL;
+	char *rd_buf_ptr = NULL;
+	const uint32_t rd_buf_size = 100;
+	uint32_t result = 0;
+	uint8_t str_len = 0;
+	int r;
+
+	if (*pos & 3 || size & 3)
+		return -EINVAL;
+
+	rd_buf = kcalloc(rd_buf_size, sizeof(char), GFP_KERNEL);
+	if (!rd_buf)
+		return 0;
+
+	rd_buf_ptr = rd_buf;
+
+	str_len = strlen("Current:  %d  %d  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Current:  %d  %d  %d  ",
+			link->cur_link_settings.lane_count,
+			link->cur_link_settings.link_rate,
+			link->cur_link_settings.link_spread);
+	rd_buf_ptr += str_len;
+
+	str_len = strlen("Verified:  %d  %d  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Verified:  %d  %d  %d  ",
+			link->verified_link_cap.lane_count,
+			link->verified_link_cap.link_rate,
+			link->verified_link_cap.link_spread);
+	rd_buf_ptr += str_len;
+
+	str_len = strlen("Reported:  %d  %d  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Reported:  %d  %d  %d  ",
+			link->reported_link_cap.lane_count,
+			link->reported_link_cap.link_rate,
+			link->reported_link_cap.link_spread);
+	rd_buf_ptr += str_len;
+
+	str_len = strlen("Preferred:  %d  %d  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Preferred:  %d  %d  %d\n",
+			link->preferred_link_setting.lane_count,
+			link->preferred_link_setting.link_rate,
+			link->preferred_link_setting.link_spread);
+
+	while (size) {
+		if (*pos >= rd_buf_size)
+			break;
+
+		r = put_user(*(rd_buf + result), buf);
+		if (r)
+			return r; /* r = -EFAULT */
+
+		buf += 1;
+		size -= 1;
+		*pos += 1;
+		result += 1;
+	}
+
+	kfree(rd_buf);
+	return result;
+}
+
+static ssize_t dp_link_settings_write(struct file *f, const char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	struct amdgpu_dm_connector *connector = file_inode(f)->i_private;
+	struct dc_link *link = connector->dc_link;
+	struct dc *dc = (struct dc *)link->dc;
+	struct dc_link_settings prefer_link_settings;
+	char *wr_buf = NULL;
+	char *wr_buf_ptr = NULL;
+	const uint32_t wr_buf_size = 40;
+	int r;
+	int bytes_from_user;
+	char *sub_str;
+	/* 0: lane_count; 1: link_rate */
+	uint8_t param_index = 0;
+	long param[2];
+	const char delimiter[3] = {' ', '\n', '\0'};
+	bool valid_input = false;
+
+	if (size == 0)
+		return -EINVAL;
+
+	wr_buf = kcalloc(wr_buf_size, sizeof(char), GFP_KERNEL);
+	if (!wr_buf)
+		return -EINVAL;
+	wr_buf_ptr = wr_buf;
+
+	r = copy_from_user(wr_buf_ptr, buf, wr_buf_size);
+
+	/* r is bytes not be copied */
+	if (r >= wr_buf_size) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("user data not read\n");
+		return -EINVAL;
+	}
+
+	bytes_from_user = wr_buf_size - r;
+
+	while (isspace(*wr_buf_ptr))
+		wr_buf_ptr++;
+
+	while ((*wr_buf_ptr != '\0') && (param_index < 2)) {
+
+		sub_str = strsep(&wr_buf_ptr, delimiter);
+
+		r = kstrtol(sub_str, 16, &param[param_index]);
+
+		if (r)
+			DRM_DEBUG_DRIVER("string to int convert error code: %d\n", r);
+
+		param_index++;
+		while (isspace(*wr_buf_ptr))
+			wr_buf_ptr++;
+	}
+
+	switch (param[0]) {
+	case LANE_COUNT_ONE:
+	case LANE_COUNT_TWO:
+	case LANE_COUNT_FOUR:
+		valid_input = true;
+		break;
+	default:
+		break;
+	}
+
+	switch (param[1]) {
+	case LINK_RATE_LOW:
+	case LINK_RATE_HIGH:
+	case LINK_RATE_RBR2:
+	case LINK_RATE_HIGH2:
+	case LINK_RATE_HIGH3:
+		valid_input = true;
+		break;
+	default:
+		break;
+	}
+
+	if (!valid_input) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("Invalid Input value No HW will be programmed\n");
+		return bytes_from_user;
+	}
+
+	/* save user force lane_count, link_rate to preferred settings
+	 * spread spectrum will not be changed
+	 */
+	prefer_link_settings.link_spread = link->cur_link_settings.link_spread;
+	prefer_link_settings.lane_count = param[0];
+	prefer_link_settings.link_rate = param[1];
+
+	dc_link_set_preferred_link_settings(dc, &prefer_link_settings, link);
+
+	kfree(wr_buf);
+	return bytes_from_user;
+}
+
+/* function: get current DP PHY settings: voltage swing, pre-emphasis,
+ * post-cursor2 (defined by VESA DP specification)
+ *
+ * valid values
+ * voltage swing: 0,1,2,3
+ * pre-emphasis : 0,1,2,3
+ * post cursor2 : 0,1,2,3
+ *
+ *
+ * how to use this debugfs
+ *
+ * debugfs is located at /sys/kernel/debug/dri/0/DP-x
+ *
+ * there will be directories, like DP-1, DP-2,DP-3, etc. for DP display
+ *
+ * To figure out which DP-x is the display for DP to be check,
+ * cd DP-x
+ * ls -ll
+ * There should be debugfs file, like link_settings, phy_settings.
+ * cat link_settings
+ * from lane_count, link_rate to figure which DP-x is for display to be worked
+ * on
+ *
+ * To get current DP PHY settings,
+ * cat phy_settings
+ *
+ * To change DP PHY settings,
+ * echo <voltage_swing> <pre-emphasis> <post_cursor2> > phy_settings
+ * for examle, to change voltage swing to 2, pre-emphasis to 3, post_cursor2 to
+ * 0,
+ * echo 2 3 0 > phy_settings
+ *
+ * To check if change be applied, get current phy settings by
+ * cat phy_settings
+ *
+ * In case invalid values are set by user, like
+ * echo 1 4 0 > phy_settings
+ *
+ * HW will NOT be programmed by these settings.
+ * cat phy_settings will show the previous valid settings.
+ */
+static ssize_t dp_phy_settings_read(struct file *f, char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	struct amdgpu_dm_connector *connector = file_inode(f)->i_private;
+	struct dc_link *link = connector->dc_link;
+	char *rd_buf = NULL;
+	const uint32_t rd_buf_size = 20;
+	uint32_t result = 0;
+	int r;
+
+	if (*pos & 3 || size & 3)
+		return -EINVAL;
+
+	rd_buf = kcalloc(rd_buf_size, sizeof(char), GFP_KERNEL);
+	if (!rd_buf)
+		return -EINVAL;
+
+	snprintf(rd_buf, rd_buf_size, "  %d  %d  %d  ",
+			link->cur_lane_setting.VOLTAGE_SWING,
+			link->cur_lane_setting.PRE_EMPHASIS,
+			link->cur_lane_setting.POST_CURSOR2);
+
+	while (size) {
+		if (*pos >= rd_buf_size)
+			break;
+
+		r = put_user((*(rd_buf + result)), buf);
+		if (r)
+			return r; /* r = -EFAULT */
+
+		buf += 1;
+		size -= 1;
+		*pos += 1;
+		result += 1;
+	}
+
+	kfree(rd_buf);
+	return result;
+}
+
+static ssize_t dp_phy_settings_write(struct file *f, const char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	struct amdgpu_dm_connector *connector = file_inode(f)->i_private;
+	struct dc_link *link = connector->dc_link;
+	struct dc *dc = (struct dc *)link->dc;
+	char *wr_buf = NULL;
+	char *wr_buf_ptr = NULL;
+	uint32_t wr_buf_size = 40;
+	int r;
+	int bytes_from_user;
+	char *sub_str;
+	uint8_t param_index = 0;
+	long param[3];
+	const char delimiter[3] = {' ', '\n', '\0'};
+	bool use_prefer_link_setting;
+	struct link_training_settings link_lane_settings;
+
+	if (size == 0)
+		return 0;
+
+	wr_buf = kcalloc(wr_buf_size, sizeof(char), GFP_KERNEL);
+	if (!wr_buf)
+		return 0;
+	wr_buf_ptr = wr_buf;
+
+	r = copy_from_user(wr_buf_ptr, buf, wr_buf_size);
+
+	/* r is bytes not be copied */
+	if (r >= wr_buf_size) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("user data not be read\n");
+		return 0;
+	}
+
+	bytes_from_user = wr_buf_size - r;
+
+	while (isspace(*wr_buf_ptr))
+		wr_buf_ptr++;
+
+	while ((*wr_buf_ptr != '\0') && (param_index < 3)) {
+
+		sub_str = strsep(&wr_buf_ptr, delimiter);
+
+		r = kstrtol(sub_str, 16, &param[param_index]);
+
+		if (r)
+			DRM_DEBUG_DRIVER("string to int convert error code: %d\n", r);
+
+		param_index++;
+		while (isspace(*wr_buf_ptr))
+			wr_buf_ptr++;
+	}
+
+	if ((param[0] > VOLTAGE_SWING_MAX_LEVEL) ||
+			(param[1] > PRE_EMPHASIS_MAX_LEVEL) ||
+			(param[2] > POST_CURSOR2_MAX_LEVEL)) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("Invalid Input No HW will be programmed\n");
+		return bytes_from_user;
+	}
+
+	/* get link settings: lane count, link rate */
+	use_prefer_link_setting =
+		((link->preferred_link_setting.link_rate != LINK_RATE_UNKNOWN) &&
+		(link->test_pattern_enabled));
+
+	memset(&link_lane_settings, 0, sizeof(link_lane_settings));
+
+	if (use_prefer_link_setting) {
+		link_lane_settings.link_settings.lane_count =
+				link->preferred_link_setting.lane_count;
+		link_lane_settings.link_settings.link_rate =
+				link->preferred_link_setting.link_rate;
+		link_lane_settings.link_settings.link_spread =
+				link->preferred_link_setting.link_spread;
+	} else {
+		link_lane_settings.link_settings.lane_count =
+				link->cur_link_settings.lane_count;
+		link_lane_settings.link_settings.link_rate =
+				link->cur_link_settings.link_rate;
+		link_lane_settings.link_settings.link_spread =
+				link->cur_link_settings.link_spread;
+	}
+
+	/* apply phy settings from user */
+	for (r = 0; r < link_lane_settings.link_settings.lane_count; r++) {
+		link_lane_settings.lane_settings[r].VOLTAGE_SWING =
+				(enum dc_voltage_swing) (param[0]);
+		link_lane_settings.lane_settings[r].PRE_EMPHASIS =
+				(enum dc_pre_emphasis) (param[1]);
+		link_lane_settings.lane_settings[r].POST_CURSOR2 =
+				(enum dc_post_cursor2) (param[2]);
+	}
+
+	/* program ASIC registers and DPCD registers */
+	dc_link_set_drive_settings(dc, &link_lane_settings, link);
+
+	kfree(wr_buf);
+	return bytes_from_user;
+}
+
+/* function description
+ *
+ * set PHY layer or Link layer test pattern
+ * PHY test pattern is used for PHY SI check.
+ * Link layer test will not affect PHY SI.
+ *
+ * Reset Test Pattern:
+ * 0 = DP_TEST_PATTERN_VIDEO_MODE
+ *
+ * PHY test pattern supported:
+ * 1 = DP_TEST_PATTERN_D102
+ * 2 = DP_TEST_PATTERN_SYMBOL_ERROR
+ * 3 = DP_TEST_PATTERN_PRBS7
+ * 4 = DP_TEST_PATTERN_80BIT_CUSTOM
+ * 5 = DP_TEST_PATTERN_CP2520_1
+ * 6 = DP_TEST_PATTERN_CP2520_2 = DP_TEST_PATTERN_HBR2_COMPLIANCE_EYE
+ * 7 = DP_TEST_PATTERN_CP2520_3
+ *
+ * DP PHY Link Training Patterns
+ * 8 = DP_TEST_PATTERN_TRAINING_PATTERN1
+ * 9 = DP_TEST_PATTERN_TRAINING_PATTERN2
+ * a = DP_TEST_PATTERN_TRAINING_PATTERN3
+ * b = DP_TEST_PATTERN_TRAINING_PATTERN4
+ *
+ * DP Link Layer Test pattern
+ * c = DP_TEST_PATTERN_COLOR_SQUARES
+ * d = DP_TEST_PATTERN_COLOR_SQUARES_CEA
+ * e = DP_TEST_PATTERN_VERTICAL_BARS
+ * f = DP_TEST_PATTERN_HORIZONTAL_BARS
+ * 10= DP_TEST_PATTERN_COLOR_RAMP
+ *
+ * debugfs phy_test_pattern is located at /syskernel/debug/dri/0/DP-x
+ *
+ * --- set test pattern
+ * echo <test pattern #> > test_pattern
+ *
+ * If test pattern # is not supported, NO HW programming will be done.
+ * for DP_TEST_PATTERN_80BIT_CUSTOM, it needs extra 10 bytes of data
+ * for the user pattern. input 10 bytes data are separated by space
+ *
+ * echo 0x4 0x11 0x22 0x33 0x44 0x55 0x66 0x77 0x88 0x99 0xaa > test_pattern
+ *
+ * --- reset test pattern
+ * echo 0 > test_pattern
+ *
+ * --- HPD detection is disabled when set PHY test pattern
+ *
+ * when PHY test pattern (pattern # within [1,7]) is set, HPD pin of HW ASIC
+ * is disable. User could unplug DP display from DP connected and plug scope to
+ * check test pattern PHY SI.
+ * If there is need unplug scope and plug DP display back, do steps below:
+ * echo 0 > phy_test_pattern
+ * unplug scope
+ * plug DP display.
+ *
+ * "echo 0 > phy_test_pattern" will re-enable HPD pin again so that video sw
+ * driver could detect "unplug scope" and "plug DP display"
+ */
+static ssize_t dp_phy_test_pattern_debugfs_write(struct file *f, const char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	struct amdgpu_dm_connector *connector = file_inode(f)->i_private;
+	struct dc_link *link = connector->dc_link;
+	char *wr_buf = NULL;
+	char *wr_buf_ptr = NULL;
+	uint32_t wr_buf_size = 100;
+	uint32_t wr_buf_count = 0;
+	int r;
+	int bytes_from_user;
+	char *sub_str = NULL;
+	uint8_t param_index = 0;
+	uint8_t param_nums = 0;
+	long param[11] = {0x0};
+	const char delimiter[3] = {' ', '\n', '\0'};
+	enum dp_test_pattern test_pattern = DP_TEST_PATTERN_UNSUPPORTED;
+	bool disable_hpd = false;
+	bool valid_test_pattern = false;
+	/* init with defalut 80bit custom pattern */
+	uint8_t custom_pattern[10] = {
+			0x1f, 0x7c, 0xf0, 0xc1, 0x07,
+			0x1f, 0x7c, 0xf0, 0xc1, 0x07
+			};
+	struct dc_link_settings prefer_link_settings = {LANE_COUNT_UNKNOWN,
+			LINK_RATE_UNKNOWN, LINK_SPREAD_DISABLED};
+	struct dc_link_settings cur_link_settings = {LANE_COUNT_UNKNOWN,
+			LINK_RATE_UNKNOWN, LINK_SPREAD_DISABLED};
+	struct link_training_settings link_training_settings;
+	int i;
+
+	if (size == 0)
+		return 0;
+
+	wr_buf = kcalloc(wr_buf_size, sizeof(char), GFP_KERNEL);
+	if (!wr_buf)
+		return 0;
+	wr_buf_ptr = wr_buf;
+
+	r = copy_from_user(wr_buf_ptr, buf, wr_buf_size);
+
+	/* r is bytes not be copied */
+	if (r >= wr_buf_size) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("user data not be read\n");
+		return 0;
+	}
+
+	bytes_from_user = wr_buf_size - r;
+
+	/* check number of parameters. isspace could not differ space and \n */
+	while ((*wr_buf_ptr != 0xa) && (wr_buf_count < wr_buf_size)) {
+		/* skip space*/
+		while (isspace(*wr_buf_ptr) && (wr_buf_count < wr_buf_size)) {
+			wr_buf_ptr++;
+			wr_buf_count++;
+			}
+
+		if (wr_buf_count == wr_buf_size)
+			break;
+
+		/* skip non-space*/
+		while ((!isspace(*wr_buf_ptr)) && (wr_buf_count < wr_buf_size)) {
+			wr_buf_ptr++;
+			wr_buf_count++;
+			}
+
+		param_nums++;
+
+		if (wr_buf_count == wr_buf_size)
+			break;
+	}
+
+	/* max 11 parameters */
+	if (param_nums > 11)
+		param_nums = 11;
+
+	wr_buf_ptr = wr_buf; /* reset buf pinter */
+	wr_buf_count = 0; /* number of char already checked */
+
+	while (isspace(*wr_buf_ptr) && (wr_buf_count < wr_buf_size)) {
+		wr_buf_ptr++;
+		wr_buf_count++;
+	}
+
+	while (param_index < param_nums) {
+		/* after strsep, wr_buf_ptr will be moved to after space */
+		sub_str = strsep(&wr_buf_ptr, delimiter);
+
+		r = kstrtol(sub_str, 16, &param[param_index]);
+
+		if (r)
+			DRM_DEBUG_DRIVER("string to int convert error code: %d\n", r);
+
+		param_index++;
+	}
+
+	test_pattern = param[0];
+
+	switch (test_pattern) {
+	case DP_TEST_PATTERN_VIDEO_MODE:
+	case DP_TEST_PATTERN_COLOR_SQUARES:
+	case DP_TEST_PATTERN_COLOR_SQUARES_CEA:
+	case DP_TEST_PATTERN_VERTICAL_BARS:
+	case DP_TEST_PATTERN_HORIZONTAL_BARS:
+	case DP_TEST_PATTERN_COLOR_RAMP:
+		valid_test_pattern = true;
+		break;
+
+	case DP_TEST_PATTERN_D102:
+	case DP_TEST_PATTERN_SYMBOL_ERROR:
+	case DP_TEST_PATTERN_PRBS7:
+	case DP_TEST_PATTERN_80BIT_CUSTOM:
+	case DP_TEST_PATTERN_HBR2_COMPLIANCE_EYE:
+	case DP_TEST_PATTERN_TRAINING_PATTERN4:
+		disable_hpd = true;
+		valid_test_pattern = true;
+		break;
+
+	default:
+		valid_test_pattern = false;
+		test_pattern = DP_TEST_PATTERN_UNSUPPORTED;
+		break;
+	}
+
+	if (!valid_test_pattern) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("Invalid Test Pattern Parameters\n");
+		return bytes_from_user;
+	}
+
+	if (test_pattern == DP_TEST_PATTERN_80BIT_CUSTOM) {
+		for (i = 0; i < 10; i++) {
+			if ((uint8_t) param[i + 1] != 0x0)
+				break;
+		}
+
+		if (i < 10) {
+			/* not use default value */
+			for (i = 0; i < 10; i++)
+				custom_pattern[i] = (uint8_t) param[i + 1];
+		}
+	}
+
+	/* Usage: set DP physical test pattern using debugfs with normal DP
+	 * panel. Then plug out DP panel and connect a scope to measure
+	 * For normal video mode and test pattern generated from CRCT,
+	 * they are visibile to user. So do not disable HPD.
+	 * Video Mode is also set to clear the test pattern, so enable HPD
+	 * because it might have been disabled after a test pattern was set.
+	 * AUX depends on HPD * sequence dependent, do not move!
+	 */
+	if (!disable_hpd)
+		dc_link_enable_hpd(link);
+
+	prefer_link_settings.lane_count = link->verified_link_cap.lane_count;
+	prefer_link_settings.link_rate = link->verified_link_cap.link_rate;
+	prefer_link_settings.link_spread = link->verified_link_cap.link_spread;
+
+	cur_link_settings.lane_count = link->cur_link_settings.lane_count;
+	cur_link_settings.link_rate = link->cur_link_settings.link_rate;
+	cur_link_settings.link_spread = link->cur_link_settings.link_spread;
+
+	link_training_settings.link_settings = cur_link_settings;
+
+
+	if (test_pattern != DP_TEST_PATTERN_VIDEO_MODE) {
+		if (prefer_link_settings.lane_count != LANE_COUNT_UNKNOWN &&
+			prefer_link_settings.link_rate !=  LINK_RATE_UNKNOWN &&
+			(prefer_link_settings.lane_count != cur_link_settings.lane_count ||
+			prefer_link_settings.link_rate != cur_link_settings.link_rate))
+			link_training_settings.link_settings = prefer_link_settings;
+	}
+
+	for (i = 0; i < (unsigned int)(link_training_settings.link_settings.lane_count); i++)
+		link_training_settings.lane_settings[i] = link->cur_lane_setting;
+
+	dc_link_set_test_pattern(
+		link,
+		test_pattern,
+		&link_training_settings,
+		custom_pattern,
+		10);
+
+	/* Usage: Set DP physical test pattern using AMDDP with normal DP panel
+	 * Then plug out DP panel and connect a scope to measure DP PHY signal.
+	 * Need disable interrupt to avoid SW driver disable DP output. This is
+	 * done after the test pattern is set.
+	 */
+	if (valid_test_pattern && disable_hpd)
+		dc_link_disable_hpd(link);
+
+	kfree(wr_buf);
+
+	return bytes_from_user;
+}
+
+static const struct file_operations dp_link_settings_debugfs_fops = {
+	.owner = THIS_MODULE,
+	.read = dp_link_settings_read,
+	.write = dp_link_settings_write,
+	.llseek = default_llseek
+};
+
+static const struct file_operations dp_phy_settings_debugfs_fop = {
+	.owner = THIS_MODULE,
+	.read = dp_phy_settings_read,
+	.write = dp_phy_settings_write,
+	.llseek = default_llseek
+};
+
+static const struct file_operations dp_phy_test_pattern_fops = {
+	.owner = THIS_MODULE,
+	.write = dp_phy_test_pattern_debugfs_write,
+	.llseek = default_llseek
+};
+
+static const struct {
+	char *name;
+	const struct file_operations *fops;
+} dp_debugfs_entries[] = {
+		{"link_settings", &dp_link_settings_debugfs_fops},
+		{"phy_settings", &dp_phy_settings_debugfs_fop},
+		{"test_pattern", &dp_phy_test_pattern_fops}
+};
+
+int connector_debugfs_init(struct amdgpu_dm_connector *connector)
+{
+	int i;
+	struct dentry *ent, *dir = connector->base.debugfs_entry;
+
+	if (connector->base.connector_type == DRM_MODE_CONNECTOR_DisplayPort) {
+		for (i = 0; i < ARRAY_SIZE(dp_debugfs_entries); i++) {
+			ent = debugfs_create_file(dp_debugfs_entries[i].name,
+						  0644,
+						  dir,
+						  connector,
+						  dp_debugfs_entries[i].fops);
+			if (IS_ERR(ent))
+				return PTR_ERR(ent);
+		}
+	}
+
+	return 0;
+}
+
diff --git a/drivers/gpu/drm/amd/powerplay/inc/pp_power_source.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.h
index b43315cc5d58..d9ed1b2aa811 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/pp_power_source.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.h
@@ -1,5 +1,5 @@
 /*
- * Copyright 2015 Advanced Micro Devices, Inc.
+ * Copyright 2018 Advanced Micro Devices, Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -19,18 +19,16 @@
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  *
+ * Authors: AMD
+ *
  */
 
-#ifndef PP_POWERSOURCE_H
-#define PP_POWERSOURCE_H
+#ifndef __AMDGPU_DM_DEBUGFS_H__
+#define __AMDGPU_DM_DEBUGFS_H__
 
-enum pp_power_source {
-	PP_PowerSource_AC = 0,
-	PP_PowerSource_DC,
-	PP_PowerSource_LimitedPower,
-	PP_PowerSource_LimitedPower_2,
-	PP_PowerSource_Max
-};
+#include "amdgpu.h"
+#include "amdgpu_dm.h"
 
+int connector_debugfs_init(struct amdgpu_dm_connector *connector);
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index ec304b1a5973..8403b6a9a77b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -169,6 +169,11 @@ static void get_payload_table(
 	mutex_unlock(&mst_mgr->payload_lock);
 }
 
+void dm_helpers_dp_update_branch_info(
+	struct dc_context *ctx,
+	const struct dc_link *link)
+{}
+
 /*
  * Writes payload allocation table in immediate downstream device.
  */
@@ -454,6 +459,22 @@ bool dm_helpers_submit_i2c(
 	return result;
 }
 
+bool dm_helpers_is_dp_sink_present(struct dc_link *link)
+{
+	bool dp_sink_present;
+	struct amdgpu_dm_connector *aconnector = link->priv;
+
+	if (!aconnector) {
+		BUG_ON("Failed to found connector for link!");
+		return true;
+	}
+
+	mutex_lock(&aconnector->dm_dp_aux.aux.hw_mutex);
+	dp_sink_present = dc_link_is_dp_sink_present(link);
+	mutex_unlock(&aconnector->dm_dp_aux.aux.hw_mutex);
+	return dp_sink_present;
+}
+
 enum dc_edid_status dm_helpers_read_local_edid(
 		struct dc_context *ctx,
 		struct dc_link *link,
@@ -497,6 +518,34 @@ enum dc_edid_status dm_helpers_read_local_edid(
 		DRM_ERROR("EDID err: %d, on connector: %s",
 				edid_status,
 				aconnector->base.name);
+	if (link->aux_mode) {
+		union test_request test_request = { {0} };
+		union test_response test_response = { {0} };
+
+		dm_helpers_dp_read_dpcd(ctx,
+					link,
+					DP_TEST_REQUEST,
+					&test_request.raw,
+					sizeof(union test_request));
+
+		if (!test_request.bits.EDID_READ)
+			return edid_status;
+
+		test_response.bits.EDID_CHECKSUM_WRITE = 1;
+
+		dm_helpers_dp_write_dpcd(ctx,
+					link,
+					DP_TEST_EDID_CHECKSUM,
+					&sink->dc_edid.raw_edid[sink->dc_edid.length-1],
+					1);
+
+		dm_helpers_dp_write_dpcd(ctx,
+					link,
+					DP_TEST_RESPONSE,
+					&test_response.raw,
+					sizeof(test_response));
+
+	}
 
 	return edid_status;
 }
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index ace9ad578ca0..9a300732ba37 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -80,53 +80,72 @@ static void log_dpcd(uint8_t type,
 static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 				  struct drm_dp_aux_msg *msg)
 {
-	enum i2c_mot_mode mot = (msg->request & DP_AUX_I2C_MOT) ?
-		I2C_MOT_TRUE : I2C_MOT_FALSE;
-	enum ddc_result res;
-	ssize_t read_bytes;
+	ssize_t result = 0;
+	enum i2caux_transaction_action action;
+	enum aux_transaction_type type;
 
 	if (WARN_ON(msg->size > 16))
 		return -E2BIG;
 
 	switch (msg->request & ~DP_AUX_I2C_MOT) {
 	case DP_AUX_NATIVE_READ:
-		read_bytes = dal_ddc_service_read_dpcd_data(
-				TO_DM_AUX(aux)->ddc_service,
-				false,
-				I2C_MOT_UNDEF,
-				msg->address,
-				msg->buffer,
-				msg->size);
-		return read_bytes;
+		type = AUX_TRANSACTION_TYPE_DP;
+		action = I2CAUX_TRANSACTION_ACTION_DP_READ;
+
+		result = dc_link_aux_transfer(TO_DM_AUX(aux)->ddc_service,
+					      msg->address,
+					      &msg->reply,
+					      msg->buffer,
+					      msg->size,
+					      type,
+					      action);
+		break;
 	case DP_AUX_NATIVE_WRITE:
-		res = dal_ddc_service_write_dpcd_data(
-				TO_DM_AUX(aux)->ddc_service,
-				false,
-				I2C_MOT_UNDEF,
-				msg->address,
-				msg->buffer,
-				msg->size);
+		type = AUX_TRANSACTION_TYPE_DP;
+		action = I2CAUX_TRANSACTION_ACTION_DP_WRITE;
+
+		dc_link_aux_transfer(TO_DM_AUX(aux)->ddc_service,
+				     msg->address,
+				     &msg->reply,
+				     msg->buffer,
+				     msg->size,
+				     type,
+				     action);
+		result = msg->size;
 		break;
 	case DP_AUX_I2C_READ:
-		read_bytes = dal_ddc_service_read_dpcd_data(
-				TO_DM_AUX(aux)->ddc_service,
-				true,
-				mot,
-				msg->address,
-				msg->buffer,
-				msg->size);
-		return read_bytes;
+		type = AUX_TRANSACTION_TYPE_I2C;
+		if (msg->request & DP_AUX_I2C_MOT)
+			action = I2CAUX_TRANSACTION_ACTION_I2C_READ_MOT;
+		else
+			action = I2CAUX_TRANSACTION_ACTION_I2C_READ;
+
+		result = dc_link_aux_transfer(TO_DM_AUX(aux)->ddc_service,
+					      msg->address,
+					      &msg->reply,
+					      msg->buffer,
+					      msg->size,
+					      type,
+					      action);
+		break;
 	case DP_AUX_I2C_WRITE:
-		res = dal_ddc_service_write_dpcd_data(
-				TO_DM_AUX(aux)->ddc_service,
-				true,
-				mot,
-				msg->address,
-				msg->buffer,
-				msg->size);
+		type = AUX_TRANSACTION_TYPE_I2C;
+		if (msg->request & DP_AUX_I2C_MOT)
+			action = I2CAUX_TRANSACTION_ACTION_I2C_WRITE_MOT;
+		else
+			action = I2CAUX_TRANSACTION_ACTION_I2C_WRITE;
+
+		dc_link_aux_transfer(TO_DM_AUX(aux)->ddc_service,
+				     msg->address,
+				     &msg->reply,
+				     msg->buffer,
+				     msg->size,
+				     type,
+				     action);
+		result = msg->size;
 		break;
 	default:
-		return 0;
+		return -EINVAL;
 	}
 
 #ifdef TRACE_DPCD
@@ -137,7 +156,10 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 		 r == DDC_RESULT_SUCESSFULL);
 #endif
 
-	return msg->size;
+	if (result < 0) /* DC doesn't know about kernel error codes */
+		result = -EIO;
+
+	return result;
 }
 
 static enum drm_connector_status
@@ -229,7 +251,7 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector)
 		edid = drm_dp_mst_get_edid(connector, &aconnector->mst_port->mst_mgr, aconnector->port);
 
 		if (!edid) {
-			drm_mode_connector_update_edid_property(
+			drm_connector_update_edid_property(
 				&aconnector->base,
 				NULL);
 			return ret;
@@ -257,7 +279,7 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector)
 					connector, aconnector->edid);
 	}
 
-	drm_mode_connector_update_edid_property(
+	drm_connector_update_edid_property(
 					&aconnector->base, aconnector->edid);
 
 	ret = drm_add_edid_modes(connector, aconnector->edid);
@@ -341,7 +363,7 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 						aconnector, connector->base.id, aconnector->mst_port);
 
 			aconnector->port = port;
-			drm_mode_connector_set_path_property(connector, pathprop);
+			drm_connector_set_path_property(connector, pathprop);
 
 			drm_connector_list_iter_end(&conn_iter);
 			aconnector->mst_connected = true;
@@ -389,7 +411,7 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 		dev->mode_config.tile_property,
 		0);
 
-	drm_mode_connector_set_path_property(connector, pathprop);
+	drm_connector_set_path_property(connector, pathprop);
 
 	/*
 	 * Initialize connector state before adding the connectror to drm and
@@ -437,7 +459,7 @@ static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr)
 static void dm_dp_mst_link_status_reset(struct drm_connector *connector)
 {
 	mutex_lock(&connector->dev->mode_config.mutex);
-	drm_mode_connector_set_link_status_property(connector, DRM_MODE_LINK_STATUS_BAD);
+	drm_connector_set_link_status_property(connector, DRM_MODE_LINK_STATUS_BAD);
 	mutex_unlock(&connector->dev->mode_config.mutex);
 }
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
new file mode 100644
index 000000000000..fbe878ae1e8c
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -0,0 +1,562 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ */
+#include <linux/string.h>
+#include <linux/acpi.h>
+
+#include <drm/drmP.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/amdgpu_drm.h>
+#include "dm_services.h"
+#include "amdgpu.h"
+#include "amdgpu_dm.h"
+#include "amdgpu_dm_irq.h"
+#include "amdgpu_pm.h"
+#include "dm_pp_smu.h"
+
+
+bool dm_pp_apply_display_requirements(
+		const struct dc_context *ctx,
+		const struct dm_pp_display_configuration *pp_display_cfg)
+{
+	struct amdgpu_device *adev = ctx->driver_context;
+	int i;
+
+	if (adev->pm.dpm_enabled) {
+
+		memset(&adev->pm.pm_display_cfg, 0,
+				sizeof(adev->pm.pm_display_cfg));
+
+		adev->pm.pm_display_cfg.cpu_cc6_disable =
+			pp_display_cfg->cpu_cc6_disable;
+
+		adev->pm.pm_display_cfg.cpu_pstate_disable =
+			pp_display_cfg->cpu_pstate_disable;
+
+		adev->pm.pm_display_cfg.cpu_pstate_separation_time =
+			pp_display_cfg->cpu_pstate_separation_time;
+
+		adev->pm.pm_display_cfg.nb_pstate_switch_disable =
+			pp_display_cfg->nb_pstate_switch_disable;
+
+		adev->pm.pm_display_cfg.num_display =
+				pp_display_cfg->display_count;
+		adev->pm.pm_display_cfg.num_path_including_non_display =
+				pp_display_cfg->display_count;
+
+		adev->pm.pm_display_cfg.min_core_set_clock =
+				pp_display_cfg->min_engine_clock_khz/10;
+		adev->pm.pm_display_cfg.min_core_set_clock_in_sr =
+				pp_display_cfg->min_engine_clock_deep_sleep_khz/10;
+		adev->pm.pm_display_cfg.min_mem_set_clock =
+				pp_display_cfg->min_memory_clock_khz/10;
+
+		adev->pm.pm_display_cfg.min_dcef_deep_sleep_set_clk =
+				pp_display_cfg->min_engine_clock_deep_sleep_khz/10;
+		adev->pm.pm_display_cfg.min_dcef_set_clk =
+				pp_display_cfg->min_dcfclock_khz/10;
+
+		adev->pm.pm_display_cfg.multi_monitor_in_sync =
+				pp_display_cfg->all_displays_in_sync;
+		adev->pm.pm_display_cfg.min_vblank_time =
+				pp_display_cfg->avail_mclk_switch_time_us;
+
+		adev->pm.pm_display_cfg.display_clk =
+				pp_display_cfg->disp_clk_khz/10;
+
+		adev->pm.pm_display_cfg.dce_tolerable_mclk_in_active_latency =
+				pp_display_cfg->avail_mclk_switch_time_in_disp_active_us;
+
+		adev->pm.pm_display_cfg.crtc_index = pp_display_cfg->crtc_index;
+		adev->pm.pm_display_cfg.line_time_in_us =
+				pp_display_cfg->line_time_in_us;
+
+		adev->pm.pm_display_cfg.vrefresh = pp_display_cfg->disp_configs[0].v_refresh;
+		adev->pm.pm_display_cfg.crossfire_display_index = -1;
+		adev->pm.pm_display_cfg.min_bus_bandwidth = 0;
+
+		for (i = 0; i < pp_display_cfg->display_count; i++) {
+			const struct dm_pp_single_disp_config *dc_cfg =
+						&pp_display_cfg->disp_configs[i];
+			adev->pm.pm_display_cfg.displays[i].controller_id = dc_cfg->pipe_idx + 1;
+		}
+
+		/* TODO: complete implementation of
+		 * pp_display_configuration_change().
+		 * Follow example of:
+		 * PHM_StoreDALConfigurationData - powerplay\hwmgr\hardwaremanager.c
+		 * PP_IRI_DisplayConfigurationChange - powerplay\eventmgr\iri.c */
+		if (adev->powerplay.pp_funcs->display_configuration_change)
+			adev->powerplay.pp_funcs->display_configuration_change(
+				adev->powerplay.pp_handle,
+				&adev->pm.pm_display_cfg);
+
+		/* TODO: replace by a separate call to 'apply display cfg'? */
+		amdgpu_pm_compute_clocks(adev);
+	}
+
+	return true;
+}
+
+static void get_default_clock_levels(
+		enum dm_pp_clock_type clk_type,
+		struct dm_pp_clock_levels *clks)
+{
+	uint32_t disp_clks_in_khz[6] = {
+			300000, 400000, 496560, 626090, 685720, 757900 };
+	uint32_t sclks_in_khz[6] = {
+			300000, 360000, 423530, 514290, 626090, 720000 };
+	uint32_t mclks_in_khz[2] = { 333000, 800000 };
+
+	switch (clk_type) {
+	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
+		clks->num_levels = 6;
+		memmove(clks->clocks_in_khz, disp_clks_in_khz,
+				sizeof(disp_clks_in_khz));
+		break;
+	case DM_PP_CLOCK_TYPE_ENGINE_CLK:
+		clks->num_levels = 6;
+		memmove(clks->clocks_in_khz, sclks_in_khz,
+				sizeof(sclks_in_khz));
+		break;
+	case DM_PP_CLOCK_TYPE_MEMORY_CLK:
+		clks->num_levels = 2;
+		memmove(clks->clocks_in_khz, mclks_in_khz,
+				sizeof(mclks_in_khz));
+		break;
+	default:
+		clks->num_levels = 0;
+		break;
+	}
+}
+
+static enum amd_pp_clock_type dc_to_pp_clock_type(
+		enum dm_pp_clock_type dm_pp_clk_type)
+{
+	enum amd_pp_clock_type amd_pp_clk_type = 0;
+
+	switch (dm_pp_clk_type) {
+	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
+		amd_pp_clk_type = amd_pp_disp_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_ENGINE_CLK:
+		amd_pp_clk_type = amd_pp_sys_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_MEMORY_CLK:
+		amd_pp_clk_type = amd_pp_mem_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_DCEFCLK:
+		amd_pp_clk_type  = amd_pp_dcef_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_DCFCLK:
+		amd_pp_clk_type = amd_pp_dcf_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_PIXELCLK:
+		amd_pp_clk_type = amd_pp_pixel_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_FCLK:
+		amd_pp_clk_type = amd_pp_f_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
+		amd_pp_clk_type = amd_pp_phy_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_DPPCLK:
+		amd_pp_clk_type = amd_pp_dpp_clock;
+		break;
+	default:
+		DRM_ERROR("DM_PPLIB: invalid clock type: %d!\n",
+				dm_pp_clk_type);
+		break;
+	}
+
+	return amd_pp_clk_type;
+}
+
+static enum dm_pp_clocks_state pp_to_dc_powerlevel_state(
+			enum PP_DAL_POWERLEVEL max_clocks_state)
+{
+	switch (max_clocks_state) {
+	case PP_DAL_POWERLEVEL_0:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_0;
+	case PP_DAL_POWERLEVEL_1:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_1;
+	case PP_DAL_POWERLEVEL_2:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_2;
+	case PP_DAL_POWERLEVEL_3:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_3;
+	case PP_DAL_POWERLEVEL_4:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_4;
+	case PP_DAL_POWERLEVEL_5:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_5;
+	case PP_DAL_POWERLEVEL_6:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_6;
+	case PP_DAL_POWERLEVEL_7:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_7;
+	default:
+		DRM_ERROR("DM_PPLIB: invalid powerlevel state: %d!\n",
+				max_clocks_state);
+		return DM_PP_CLOCKS_STATE_INVALID;
+	}
+}
+
+static void pp_to_dc_clock_levels(
+		const struct amd_pp_clocks *pp_clks,
+		struct dm_pp_clock_levels *dc_clks,
+		enum dm_pp_clock_type dc_clk_type)
+{
+	uint32_t i;
+
+	if (pp_clks->count > DM_PP_MAX_CLOCK_LEVELS) {
+		DRM_INFO("DM_PPLIB: Warning: %s clock: number of levels %d exceeds maximum of %d!\n",
+				DC_DECODE_PP_CLOCK_TYPE(dc_clk_type),
+				pp_clks->count,
+				DM_PP_MAX_CLOCK_LEVELS);
+
+		dc_clks->num_levels = DM_PP_MAX_CLOCK_LEVELS;
+	} else
+		dc_clks->num_levels = pp_clks->count;
+
+	DRM_INFO("DM_PPLIB: values for %s clock\n",
+			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
+
+	for (i = 0; i < dc_clks->num_levels; i++) {
+		DRM_INFO("DM_PPLIB:\t %d\n", pp_clks->clock[i]);
+		dc_clks->clocks_in_khz[i] = pp_clks->clock[i];
+	}
+}
+
+static void pp_to_dc_clock_levels_with_latency(
+		const struct pp_clock_levels_with_latency *pp_clks,
+		struct dm_pp_clock_levels_with_latency *clk_level_info,
+		enum dm_pp_clock_type dc_clk_type)
+{
+	uint32_t i;
+
+	if (pp_clks->num_levels > DM_PP_MAX_CLOCK_LEVELS) {
+		DRM_INFO("DM_PPLIB: Warning: %s clock: number of levels %d exceeds maximum of %d!\n",
+				DC_DECODE_PP_CLOCK_TYPE(dc_clk_type),
+				pp_clks->num_levels,
+				DM_PP_MAX_CLOCK_LEVELS);
+
+		clk_level_info->num_levels = DM_PP_MAX_CLOCK_LEVELS;
+	} else
+		clk_level_info->num_levels = pp_clks->num_levels;
+
+	DRM_DEBUG("DM_PPLIB: values for %s clock\n",
+			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
+
+	for (i = 0; i < clk_level_info->num_levels; i++) {
+		DRM_DEBUG("DM_PPLIB:\t %d in kHz\n", pp_clks->data[i].clocks_in_khz);
+		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz;
+		clk_level_info->data[i].latency_in_us = pp_clks->data[i].latency_in_us;
+	}
+}
+
+static void pp_to_dc_clock_levels_with_voltage(
+		const struct pp_clock_levels_with_voltage *pp_clks,
+		struct dm_pp_clock_levels_with_voltage *clk_level_info,
+		enum dm_pp_clock_type dc_clk_type)
+{
+	uint32_t i;
+
+	if (pp_clks->num_levels > DM_PP_MAX_CLOCK_LEVELS) {
+		DRM_INFO("DM_PPLIB: Warning: %s clock: number of levels %d exceeds maximum of %d!\n",
+				DC_DECODE_PP_CLOCK_TYPE(dc_clk_type),
+				pp_clks->num_levels,
+				DM_PP_MAX_CLOCK_LEVELS);
+
+		clk_level_info->num_levels = DM_PP_MAX_CLOCK_LEVELS;
+	} else
+		clk_level_info->num_levels = pp_clks->num_levels;
+
+	DRM_INFO("DM_PPLIB: values for %s clock\n",
+			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
+
+	for (i = 0; i < clk_level_info->num_levels; i++) {
+		DRM_INFO("DM_PPLIB:\t %d in kHz\n", pp_clks->data[i].clocks_in_khz);
+		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz;
+		clk_level_info->data[i].voltage_in_mv = pp_clks->data[i].voltage_in_mv;
+	}
+}
+
+bool dm_pp_get_clock_levels_by_type(
+		const struct dc_context *ctx,
+		enum dm_pp_clock_type clk_type,
+		struct dm_pp_clock_levels *dc_clks)
+{
+	struct amdgpu_device *adev = ctx->driver_context;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct amd_pp_clocks pp_clks = { 0 };
+	struct amd_pp_simple_clock_info validation_clks = { 0 };
+	uint32_t i;
+
+	if (adev->powerplay.pp_funcs->get_clock_by_type) {
+		if (adev->powerplay.pp_funcs->get_clock_by_type(pp_handle,
+			dc_to_pp_clock_type(clk_type), &pp_clks)) {
+		/* Error in pplib. Provide default values. */
+			get_default_clock_levels(clk_type, dc_clks);
+			return true;
+		}
+	}
+
+	pp_to_dc_clock_levels(&pp_clks, dc_clks, clk_type);
+
+	if (adev->powerplay.pp_funcs->get_display_mode_validation_clocks) {
+		if (adev->powerplay.pp_funcs->get_display_mode_validation_clocks(
+						pp_handle, &validation_clks)) {
+			/* Error in pplib. Provide default values. */
+			DRM_INFO("DM_PPLIB: Warning: using default validation clocks!\n");
+			validation_clks.engine_max_clock = 72000;
+			validation_clks.memory_max_clock = 80000;
+			validation_clks.level = 0;
+		}
+	}
+
+	DRM_INFO("DM_PPLIB: Validation clocks:\n");
+	DRM_INFO("DM_PPLIB:    engine_max_clock: %d\n",
+			validation_clks.engine_max_clock);
+	DRM_INFO("DM_PPLIB:    memory_max_clock: %d\n",
+			validation_clks.memory_max_clock);
+	DRM_INFO("DM_PPLIB:    level           : %d\n",
+			validation_clks.level);
+
+	/* Translate 10 kHz to kHz. */
+	validation_clks.engine_max_clock *= 10;
+	validation_clks.memory_max_clock *= 10;
+
+	/* Determine the highest non-boosted level from the Validation Clocks */
+	if (clk_type == DM_PP_CLOCK_TYPE_ENGINE_CLK) {
+		for (i = 0; i < dc_clks->num_levels; i++) {
+			if (dc_clks->clocks_in_khz[i] > validation_clks.engine_max_clock) {
+				/* This clock is higher the validation clock.
+				 * Than means the previous one is the highest
+				 * non-boosted one. */
+				DRM_INFO("DM_PPLIB: reducing engine clock level from %d to %d\n",
+						dc_clks->num_levels, i);
+				dc_clks->num_levels = i > 0 ? i : 1;
+				break;
+			}
+		}
+	} else if (clk_type == DM_PP_CLOCK_TYPE_MEMORY_CLK) {
+		for (i = 0; i < dc_clks->num_levels; i++) {
+			if (dc_clks->clocks_in_khz[i] > validation_clks.memory_max_clock) {
+				DRM_INFO("DM_PPLIB: reducing memory clock level from %d to %d\n",
+						dc_clks->num_levels, i);
+				dc_clks->num_levels = i > 0 ? i : 1;
+				break;
+			}
+		}
+	}
+
+	return true;
+}
+
+bool dm_pp_get_clock_levels_by_type_with_latency(
+	const struct dc_context *ctx,
+	enum dm_pp_clock_type clk_type,
+	struct dm_pp_clock_levels_with_latency *clk_level_info)
+{
+	struct amdgpu_device *adev = ctx->driver_context;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct pp_clock_levels_with_latency pp_clks = { 0 };
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+	if (!pp_funcs || !pp_funcs->get_clock_by_type_with_latency)
+		return false;
+
+	if (pp_funcs->get_clock_by_type_with_latency(pp_handle,
+						     dc_to_pp_clock_type(clk_type),
+						     &pp_clks))
+		return false;
+
+	pp_to_dc_clock_levels_with_latency(&pp_clks, clk_level_info, clk_type);
+
+	return true;
+}
+
+bool dm_pp_get_clock_levels_by_type_with_voltage(
+	const struct dc_context *ctx,
+	enum dm_pp_clock_type clk_type,
+	struct dm_pp_clock_levels_with_voltage *clk_level_info)
+{
+	struct amdgpu_device *adev = ctx->driver_context;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct pp_clock_levels_with_voltage pp_clk_info = {0};
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+	if (pp_funcs->get_clock_by_type_with_voltage(pp_handle,
+						     dc_to_pp_clock_type(clk_type),
+						     &pp_clk_info))
+		return false;
+
+	pp_to_dc_clock_levels_with_voltage(&pp_clk_info, clk_level_info, clk_type);
+
+	return true;
+}
+
+bool dm_pp_notify_wm_clock_changes(
+	const struct dc_context *ctx,
+	struct dm_pp_wm_sets_with_clock_ranges *wm_with_clock_ranges)
+{
+	/* TODO: to be implemented */
+	return false;
+}
+
+bool dm_pp_apply_power_level_change_request(
+	const struct dc_context *ctx,
+	struct dm_pp_power_level_change_request *level_change_req)
+{
+	/* TODO: to be implemented */
+	return false;
+}
+
+bool dm_pp_apply_clock_for_voltage_request(
+	const struct dc_context *ctx,
+	struct dm_pp_clock_for_voltage_req *clock_for_voltage_req)
+{
+	struct amdgpu_device *adev = ctx->driver_context;
+	struct pp_display_clock_request pp_clock_request = {0};
+	int ret = 0;
+
+	pp_clock_request.clock_type = dc_to_pp_clock_type(clock_for_voltage_req->clk_type);
+	pp_clock_request.clock_freq_in_khz = clock_for_voltage_req->clocks_in_khz;
+
+	if (!pp_clock_request.clock_type)
+		return false;
+
+	if (adev->powerplay.pp_funcs->display_clock_voltage_request)
+		ret = adev->powerplay.pp_funcs->display_clock_voltage_request(
+			adev->powerplay.pp_handle,
+			&pp_clock_request);
+	if (ret)
+		return false;
+	return true;
+}
+
+bool dm_pp_get_static_clocks(
+	const struct dc_context *ctx,
+	struct dm_pp_static_clock_info *static_clk_info)
+{
+	struct amdgpu_device *adev = ctx->driver_context;
+	struct amd_pp_clock_info pp_clk_info = {0};
+	int ret = 0;
+
+	if (adev->powerplay.pp_funcs->get_current_clocks)
+		ret = adev->powerplay.pp_funcs->get_current_clocks(
+			adev->powerplay.pp_handle,
+			&pp_clk_info);
+	if (ret)
+		return false;
+
+	static_clk_info->max_clocks_state = pp_to_dc_powerlevel_state(pp_clk_info.max_clocks_state);
+	static_clk_info->max_mclk_khz = pp_clk_info.max_memory_clock * 10;
+	static_clk_info->max_sclk_khz = pp_clk_info.max_engine_clock * 10;
+
+	return true;
+}
+
+void pp_rv_set_display_requirement(struct pp_smu *pp,
+		struct pp_smu_display_requirement_rv *req)
+{
+	struct dc_context *ctx = pp->ctx;
+	struct amdgpu_device *adev = ctx->driver_context;
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+	if (!pp_funcs || !pp_funcs->display_configuration_changed)
+		return;
+
+	amdgpu_dpm_display_configuration_changed(adev);
+}
+
+void pp_rv_set_wm_ranges(struct pp_smu *pp,
+		struct pp_smu_wm_range_sets *ranges)
+{
+	struct dc_context *ctx = pp->ctx;
+	struct amdgpu_device *adev = ctx->driver_context;
+	void *pp_handle = adev->powerplay.pp_handle;
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	struct dm_pp_wm_sets_with_clock_ranges_soc15 wm_with_clock_ranges;
+	struct dm_pp_clock_range_for_dmif_wm_set_soc15 *wm_dce_clocks = wm_with_clock_ranges.wm_dmif_clocks_ranges;
+	struct dm_pp_clock_range_for_mcif_wm_set_soc15 *wm_soc_clocks = wm_with_clock_ranges.wm_mcif_clocks_ranges;
+	int32_t i;
+
+	wm_with_clock_ranges.num_wm_dmif_sets = ranges->num_reader_wm_sets;
+	wm_with_clock_ranges.num_wm_mcif_sets = ranges->num_writer_wm_sets;
+
+	for (i = 0; i < wm_with_clock_ranges.num_wm_dmif_sets; i++) {
+		if (ranges->reader_wm_sets[i].wm_inst > 3)
+			wm_dce_clocks[i].wm_set_id = WM_SET_A;
+		else
+			wm_dce_clocks[i].wm_set_id =
+					ranges->reader_wm_sets[i].wm_inst;
+		wm_dce_clocks[i].wm_max_dcfclk_clk_in_khz =
+				ranges->reader_wm_sets[i].max_drain_clk_khz;
+		wm_dce_clocks[i].wm_min_dcfclk_clk_in_khz =
+				ranges->reader_wm_sets[i].min_drain_clk_khz;
+		wm_dce_clocks[i].wm_max_mem_clk_in_khz =
+				ranges->reader_wm_sets[i].max_fill_clk_khz;
+		wm_dce_clocks[i].wm_min_mem_clk_in_khz =
+				ranges->reader_wm_sets[i].min_fill_clk_khz;
+	}
+
+	for (i = 0; i < wm_with_clock_ranges.num_wm_mcif_sets; i++) {
+		if (ranges->writer_wm_sets[i].wm_inst > 3)
+			wm_soc_clocks[i].wm_set_id = WM_SET_A;
+		else
+			wm_soc_clocks[i].wm_set_id =
+					ranges->writer_wm_sets[i].wm_inst;
+		wm_soc_clocks[i].wm_max_socclk_clk_in_khz =
+				ranges->writer_wm_sets[i].max_fill_clk_khz;
+		wm_soc_clocks[i].wm_min_socclk_clk_in_khz =
+				ranges->writer_wm_sets[i].min_fill_clk_khz;
+		wm_soc_clocks[i].wm_max_mem_clk_in_khz =
+				ranges->writer_wm_sets[i].max_drain_clk_khz;
+		wm_soc_clocks[i].wm_min_mem_clk_in_khz =
+				ranges->writer_wm_sets[i].min_drain_clk_khz;
+	}
+
+	pp_funcs->set_watermarks_for_clocks_ranges(pp_handle, &wm_with_clock_ranges);
+}
+
+void pp_rv_set_pme_wa_enable(struct pp_smu *pp)
+{
+	struct dc_context *ctx = pp->ctx;
+	struct amdgpu_device *adev = ctx->driver_context;
+	void *pp_handle = adev->powerplay.pp_handle;
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+	if (!pp_funcs || !pp_funcs->notify_smu_enable_pwe)
+		return;
+
+	pp_funcs->notify_smu_enable_pwe(pp_handle);
+}
+
+void dm_pp_get_funcs_rv(
+		struct dc_context *ctx,
+		struct pp_smu_funcs_rv *funcs)
+{
+	funcs->pp_smu.ctx = ctx;
+	funcs->set_display_requirement = pp_rv_set_display_requirement;
+	funcs->set_wm_ranges = pp_rv_set_wm_ranges;
+	funcs->set_pme_wa_enable = pp_rv_set_pme_wa_enable;
+}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
index 5a2e952c5bea..516795342dd2 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
@@ -35,13 +35,7 @@
 #include "amdgpu_dm_irq.h"
 #include "amdgpu_pm.h"
 
-unsigned long long dm_get_timestamp(struct dc_context *ctx)
-{
-	struct timespec64 time;
 
-	getrawmonotonic64(&time);
-	return timespec64_to_ns(&time);
-}
 
 unsigned long long dm_get_elapse_time_in_ns(struct dc_context *ctx,
 		unsigned long long current_time_stamp,
@@ -80,327 +74,3 @@ bool dm_read_persistent_data(struct dc_context *ctx,
 
 /**** power component interfaces ****/
 
-bool dm_pp_apply_display_requirements(
-		const struct dc_context *ctx,
-		const struct dm_pp_display_configuration *pp_display_cfg)
-{
-	struct amdgpu_device *adev = ctx->driver_context;
-
-	if (adev->pm.dpm_enabled) {
-
-		memset(&adev->pm.pm_display_cfg, 0,
-				sizeof(adev->pm.pm_display_cfg));
-
-		adev->pm.pm_display_cfg.cpu_cc6_disable =
-			pp_display_cfg->cpu_cc6_disable;
-
-		adev->pm.pm_display_cfg.cpu_pstate_disable =
-			pp_display_cfg->cpu_pstate_disable;
-
-		adev->pm.pm_display_cfg.cpu_pstate_separation_time =
-			pp_display_cfg->cpu_pstate_separation_time;
-
-		adev->pm.pm_display_cfg.nb_pstate_switch_disable =
-			pp_display_cfg->nb_pstate_switch_disable;
-
-		adev->pm.pm_display_cfg.num_display =
-				pp_display_cfg->display_count;
-		adev->pm.pm_display_cfg.num_path_including_non_display =
-				pp_display_cfg->display_count;
-
-		adev->pm.pm_display_cfg.min_core_set_clock =
-				pp_display_cfg->min_engine_clock_khz/10;
-		adev->pm.pm_display_cfg.min_core_set_clock_in_sr =
-				pp_display_cfg->min_engine_clock_deep_sleep_khz/10;
-		adev->pm.pm_display_cfg.min_mem_set_clock =
-				pp_display_cfg->min_memory_clock_khz/10;
-
-		adev->pm.pm_display_cfg.multi_monitor_in_sync =
-				pp_display_cfg->all_displays_in_sync;
-		adev->pm.pm_display_cfg.min_vblank_time =
-				pp_display_cfg->avail_mclk_switch_time_us;
-
-		adev->pm.pm_display_cfg.display_clk =
-				pp_display_cfg->disp_clk_khz/10;
-
-		adev->pm.pm_display_cfg.dce_tolerable_mclk_in_active_latency =
-				pp_display_cfg->avail_mclk_switch_time_in_disp_active_us;
-
-		adev->pm.pm_display_cfg.crtc_index = pp_display_cfg->crtc_index;
-		adev->pm.pm_display_cfg.line_time_in_us =
-				pp_display_cfg->line_time_in_us;
-
-		adev->pm.pm_display_cfg.vrefresh = pp_display_cfg->disp_configs[0].v_refresh;
-		adev->pm.pm_display_cfg.crossfire_display_index = -1;
-		adev->pm.pm_display_cfg.min_bus_bandwidth = 0;
-
-		/* TODO: complete implementation of
-		 * pp_display_configuration_change().
-		 * Follow example of:
-		 * PHM_StoreDALConfigurationData - powerplay\hwmgr\hardwaremanager.c
-		 * PP_IRI_DisplayConfigurationChange - powerplay\eventmgr\iri.c */
-		if (adev->powerplay.pp_funcs->display_configuration_change)
-			adev->powerplay.pp_funcs->display_configuration_change(
-				adev->powerplay.pp_handle,
-				&adev->pm.pm_display_cfg);
-
-		/* TODO: replace by a separate call to 'apply display cfg'? */
-		amdgpu_pm_compute_clocks(adev);
-	}
-
-	return true;
-}
-
-static void get_default_clock_levels(
-		enum dm_pp_clock_type clk_type,
-		struct dm_pp_clock_levels *clks)
-{
-	uint32_t disp_clks_in_khz[6] = {
-			300000, 400000, 496560, 626090, 685720, 757900 };
-	uint32_t sclks_in_khz[6] = {
-			300000, 360000, 423530, 514290, 626090, 720000 };
-	uint32_t mclks_in_khz[2] = { 333000, 800000 };
-
-	switch (clk_type) {
-	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-		clks->num_levels = 6;
-		memmove(clks->clocks_in_khz, disp_clks_in_khz,
-				sizeof(disp_clks_in_khz));
-		break;
-	case DM_PP_CLOCK_TYPE_ENGINE_CLK:
-		clks->num_levels = 6;
-		memmove(clks->clocks_in_khz, sclks_in_khz,
-				sizeof(sclks_in_khz));
-		break;
-	case DM_PP_CLOCK_TYPE_MEMORY_CLK:
-		clks->num_levels = 2;
-		memmove(clks->clocks_in_khz, mclks_in_khz,
-				sizeof(mclks_in_khz));
-		break;
-	default:
-		clks->num_levels = 0;
-		break;
-	}
-}
-
-static enum amd_pp_clock_type dc_to_pp_clock_type(
-		enum dm_pp_clock_type dm_pp_clk_type)
-{
-	enum amd_pp_clock_type amd_pp_clk_type = 0;
-
-	switch (dm_pp_clk_type) {
-	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-		amd_pp_clk_type = amd_pp_disp_clock;
-		break;
-	case DM_PP_CLOCK_TYPE_ENGINE_CLK:
-		amd_pp_clk_type = amd_pp_sys_clock;
-		break;
-	case DM_PP_CLOCK_TYPE_MEMORY_CLK:
-		amd_pp_clk_type = amd_pp_mem_clock;
-		break;
-	default:
-		DRM_ERROR("DM_PPLIB: invalid clock type: %d!\n",
-				dm_pp_clk_type);
-		break;
-	}
-
-	return amd_pp_clk_type;
-}
-
-static void pp_to_dc_clock_levels(
-		const struct amd_pp_clocks *pp_clks,
-		struct dm_pp_clock_levels *dc_clks,
-		enum dm_pp_clock_type dc_clk_type)
-{
-	uint32_t i;
-
-	if (pp_clks->count > DM_PP_MAX_CLOCK_LEVELS) {
-		DRM_INFO("DM_PPLIB: Warning: %s clock: number of levels %d exceeds maximum of %d!\n",
-				DC_DECODE_PP_CLOCK_TYPE(dc_clk_type),
-				pp_clks->count,
-				DM_PP_MAX_CLOCK_LEVELS);
-
-		dc_clks->num_levels = DM_PP_MAX_CLOCK_LEVELS;
-	} else
-		dc_clks->num_levels = pp_clks->count;
-
-	DRM_INFO("DM_PPLIB: values for %s clock\n",
-			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
-
-	for (i = 0; i < dc_clks->num_levels; i++) {
-		DRM_INFO("DM_PPLIB:\t %d\n", pp_clks->clock[i]);
-		/* translate 10kHz to kHz */
-		dc_clks->clocks_in_khz[i] = pp_clks->clock[i] * 10;
-	}
-}
-
-static void pp_to_dc_clock_levels_with_latency(
-		const struct pp_clock_levels_with_latency *pp_clks,
-		struct dm_pp_clock_levels_with_latency *clk_level_info,
-		enum dm_pp_clock_type dc_clk_type)
-{
-	uint32_t i;
-
-	if (pp_clks->num_levels > DM_PP_MAX_CLOCK_LEVELS) {
-		DRM_INFO("DM_PPLIB: Warning: %s clock: number of levels %d exceeds maximum of %d!\n",
-				DC_DECODE_PP_CLOCK_TYPE(dc_clk_type),
-				pp_clks->num_levels,
-				DM_PP_MAX_CLOCK_LEVELS);
-
-		clk_level_info->num_levels = DM_PP_MAX_CLOCK_LEVELS;
-	} else
-		clk_level_info->num_levels = pp_clks->num_levels;
-
-	DRM_DEBUG("DM_PPLIB: values for %s clock\n",
-			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
-
-	for (i = 0; i < clk_level_info->num_levels; i++) {
-		DRM_DEBUG("DM_PPLIB:\t %d in 10kHz\n", pp_clks->data[i].clocks_in_khz);
-		/* translate 10kHz to kHz */
-		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz * 10;
-		clk_level_info->data[i].latency_in_us = pp_clks->data[i].latency_in_us;
-	}
-}
-
-bool dm_pp_get_clock_levels_by_type(
-		const struct dc_context *ctx,
-		enum dm_pp_clock_type clk_type,
-		struct dm_pp_clock_levels *dc_clks)
-{
-	struct amdgpu_device *adev = ctx->driver_context;
-	void *pp_handle = adev->powerplay.pp_handle;
-	struct amd_pp_clocks pp_clks = { 0 };
-	struct amd_pp_simple_clock_info validation_clks = { 0 };
-	uint32_t i;
-
-	if (adev->powerplay.pp_funcs->get_clock_by_type) {
-		if (adev->powerplay.pp_funcs->get_clock_by_type(pp_handle,
-			dc_to_pp_clock_type(clk_type), &pp_clks)) {
-		/* Error in pplib. Provide default values. */
-			get_default_clock_levels(clk_type, dc_clks);
-			return true;
-		}
-	}
-
-	pp_to_dc_clock_levels(&pp_clks, dc_clks, clk_type);
-
-	if (adev->powerplay.pp_funcs->get_display_mode_validation_clocks) {
-		if (adev->powerplay.pp_funcs->get_display_mode_validation_clocks(
-						pp_handle, &validation_clks)) {
-			/* Error in pplib. Provide default values. */
-			DRM_INFO("DM_PPLIB: Warning: using default validation clocks!\n");
-			validation_clks.engine_max_clock = 72000;
-			validation_clks.memory_max_clock = 80000;
-			validation_clks.level = 0;
-		}
-	}
-
-	DRM_INFO("DM_PPLIB: Validation clocks:\n");
-	DRM_INFO("DM_PPLIB:    engine_max_clock: %d\n",
-			validation_clks.engine_max_clock);
-	DRM_INFO("DM_PPLIB:    memory_max_clock: %d\n",
-			validation_clks.memory_max_clock);
-	DRM_INFO("DM_PPLIB:    level           : %d\n",
-			validation_clks.level);
-
-	/* Translate 10 kHz to kHz. */
-	validation_clks.engine_max_clock *= 10;
-	validation_clks.memory_max_clock *= 10;
-
-	/* Determine the highest non-boosted level from the Validation Clocks */
-	if (clk_type == DM_PP_CLOCK_TYPE_ENGINE_CLK) {
-		for (i = 0; i < dc_clks->num_levels; i++) {
-			if (dc_clks->clocks_in_khz[i] > validation_clks.engine_max_clock) {
-				/* This clock is higher the validation clock.
-				 * Than means the previous one is the highest
-				 * non-boosted one. */
-				DRM_INFO("DM_PPLIB: reducing engine clock level from %d to %d\n",
-						dc_clks->num_levels, i);
-				dc_clks->num_levels = i > 0 ? i : 1;
-				break;
-			}
-		}
-	} else if (clk_type == DM_PP_CLOCK_TYPE_MEMORY_CLK) {
-		for (i = 0; i < dc_clks->num_levels; i++) {
-			if (dc_clks->clocks_in_khz[i] > validation_clks.memory_max_clock) {
-				DRM_INFO("DM_PPLIB: reducing memory clock level from %d to %d\n",
-						dc_clks->num_levels, i);
-				dc_clks->num_levels = i > 0 ? i : 1;
-				break;
-			}
-		}
-	}
-
-	return true;
-}
-
-bool dm_pp_get_clock_levels_by_type_with_latency(
-	const struct dc_context *ctx,
-	enum dm_pp_clock_type clk_type,
-	struct dm_pp_clock_levels_with_latency *clk_level_info)
-{
-	struct amdgpu_device *adev = ctx->driver_context;
-	void *pp_handle = adev->powerplay.pp_handle;
-	struct pp_clock_levels_with_latency pp_clks = { 0 };
-	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
-
-	if (!pp_funcs || !pp_funcs->get_clock_by_type_with_latency)
-		return false;
-
-	if (pp_funcs->get_clock_by_type_with_latency(pp_handle,
-						     dc_to_pp_clock_type(clk_type),
-						     &pp_clks))
-		return false;
-
-	pp_to_dc_clock_levels_with_latency(&pp_clks, clk_level_info, clk_type);
-
-	return true;
-}
-
-bool dm_pp_get_clock_levels_by_type_with_voltage(
-	const struct dc_context *ctx,
-	enum dm_pp_clock_type clk_type,
-	struct dm_pp_clock_levels_with_voltage *clk_level_info)
-{
-	/* TODO: to be implemented */
-	return false;
-}
-
-bool dm_pp_notify_wm_clock_changes(
-	const struct dc_context *ctx,
-	struct dm_pp_wm_sets_with_clock_ranges *wm_with_clock_ranges)
-{
-	/* TODO: to be implemented */
-	return false;
-}
-
-bool dm_pp_apply_power_level_change_request(
-	const struct dc_context *ctx,
-	struct dm_pp_power_level_change_request *level_change_req)
-{
-	/* TODO: to be implemented */
-	return false;
-}
-
-bool dm_pp_apply_clock_for_voltage_request(
-	const struct dc_context *ctx,
-	struct dm_pp_clock_for_voltage_req *clock_for_voltage_req)
-{
-	/* TODO: to be implemented */
-	return false;
-}
-
-bool dm_pp_get_static_clocks(
-	const struct dc_context *ctx,
-	struct dm_pp_static_clock_info *static_clk_info)
-{
-	/* TODO: to be implemented */
-	return false;
-}
-
-void dm_pp_get_funcs_rv(
-		struct dc_context *ctx,
-		struct pp_smu_funcs_rv *funcs)
-{}
-
-/**** end of power component interfaces ****/
diff --git a/drivers/gpu/drm/amd/display/dc/Makefile b/drivers/gpu/drm/amd/display/dc/Makefile
index aed538a4d1ba..532a515fda9a 100644
--- a/drivers/gpu/drm/amd/display/dc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/Makefile
@@ -25,7 +25,7 @@
 
 DC_LIBS = basics bios calcs dce gpio i2caux irq virtual
 
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_X86
 DC_LIBS += dcn10 dml
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/basics/Makefile b/drivers/gpu/drm/amd/display/dc/basics/Makefile
index b49ea96b5dae..a50a76471107 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/basics/Makefile
@@ -25,7 +25,7 @@
 # subcomponents.
 
 BASICS = conversion.o fixpt31_32.o \
-	logger.o log_helpers.o vector.o
+	log_helpers.o vector.o
 
 AMD_DAL_BASICS = $(addprefix $(AMDDALPATH)/dc/basics/,$(BASICS))
 
diff --git a/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c b/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c
index 021451549ff7..26583f346c39 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c
@@ -28,75 +28,12 @@
 #include "include/logger_interface.h"
 #include "dm_helpers.h"
 
-#define NUM_ELEMENTS(a) (sizeof(a) / sizeof((a)[0]))
-
-struct dc_signal_type_info {
-	enum signal_type type;
-	char name[MAX_NAME_LEN];
-};
-
-static const struct dc_signal_type_info signal_type_info_tbl[] = {
-		{SIGNAL_TYPE_NONE,             "NC"},
-		{SIGNAL_TYPE_DVI_SINGLE_LINK,  "DVI"},
-		{SIGNAL_TYPE_DVI_DUAL_LINK,    "DDVI"},
-		{SIGNAL_TYPE_HDMI_TYPE_A,      "HDMIA"},
-		{SIGNAL_TYPE_LVDS,             "LVDS"},
-		{SIGNAL_TYPE_RGB,              "VGA"},
-		{SIGNAL_TYPE_DISPLAY_PORT,     "DP"},
-		{SIGNAL_TYPE_DISPLAY_PORT_MST, "MST"},
-		{SIGNAL_TYPE_EDP,              "eDP"},
-		{SIGNAL_TYPE_VIRTUAL,          "Virtual"}
-};
-
-void dc_conn_log(struct dc_context *ctx,
-		const struct dc_link *link,
-		uint8_t *hex_data,
-		int hex_data_count,
-		enum dc_log_type event,
-		const char *msg,
-		...)
+void dc_conn_log_hex_linux(const uint8_t *hex_data, int hex_data_count)
 {
 	int i;
-	va_list args;
-	struct log_entry entry = { 0 };
-	enum signal_type signal;
-
-	if (link->local_sink)
-		signal = link->local_sink->sink_signal;
-	else
-		signal = link->connector_signal;
-
-	if (link->type == dc_connection_mst_branch)
-		signal = SIGNAL_TYPE_DISPLAY_PORT_MST;
-
-	dm_logger_open(ctx->logger, &entry, event);
-
-	for (i = 0; i < NUM_ELEMENTS(signal_type_info_tbl); i++)
-		if (signal == signal_type_info_tbl[i].type)
-			break;
-
-	if (i == NUM_ELEMENTS(signal_type_info_tbl))
-		goto fail;
-
-	dm_logger_append(&entry, "[%s][ConnIdx:%d] ",
-			signal_type_info_tbl[i].name,
-			link->link_index);
-
-	va_start(args, msg);
-	dm_logger_append_va(&entry, msg, args);
-
-	if (entry.buf_offset > 0 &&
-	    entry.buf[entry.buf_offset - 1] == '\n')
-		entry.buf_offset--;
 
 	if (hex_data)
 		for (i = 0; i < hex_data_count; i++)
-			dm_logger_append(&entry, "%2.2X ", hex_data[i]);
-
-	dm_logger_append(&entry, "^\n");
-
-fail:
-	dm_logger_close(&entry);
-
-	va_end(args);
+			DC_LOG_DEBUG("%2.2X ", hex_data[i]);
 }
+
diff --git a/drivers/gpu/drm/amd/display/dc/basics/logger.c b/drivers/gpu/drm/amd/display/dc/basics/logger.c
deleted file mode 100644
index 0866874ae8c6..000000000000
--- a/drivers/gpu/drm/amd/display/dc/basics/logger.c
+++ /dev/null
@@ -1,405 +0,0 @@
-/*
- * Copyright 2012-15 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: AMD
- *
- */
-#include "dm_services.h"
-#include "include/logger_interface.h"
-#include "logger.h"
-
-
-#define NUM_ELEMENTS(a) (sizeof(a) / sizeof((a)[0]))
-
-static const struct dc_log_type_info log_type_info_tbl[] = {
-		{LOG_ERROR,                 "Error"},
-		{LOG_WARNING,               "Warning"},
-		{LOG_DEBUG,		    "Debug"},
-		{LOG_DC,                    "DC_Interface"},
-		{LOG_SURFACE,               "Surface"},
-		{LOG_HW_HOTPLUG,            "HW_Hotplug"},
-		{LOG_HW_LINK_TRAINING,      "HW_LKTN"},
-		{LOG_HW_SET_MODE,           "HW_Mode"},
-		{LOG_HW_RESUME_S3,          "HW_Resume"},
-		{LOG_HW_AUDIO,              "HW_Audio"},
-		{LOG_HW_HPD_IRQ,            "HW_HPDIRQ"},
-		{LOG_MST,                   "MST"},
-		{LOG_SCALER,                "Scaler"},
-		{LOG_BIOS,                  "BIOS"},
-		{LOG_BANDWIDTH_CALCS,       "BWCalcs"},
-		{LOG_BANDWIDTH_VALIDATION,  "BWValidation"},
-		{LOG_I2C_AUX,               "I2C_AUX"},
-		{LOG_SYNC,                  "Sync"},
-		{LOG_BACKLIGHT,             "Backlight"},
-		{LOG_FEATURE_OVERRIDE,      "Override"},
-		{LOG_DETECTION_EDID_PARSER, "Edid"},
-		{LOG_DETECTION_DP_CAPS,     "DP_Caps"},
-		{LOG_RESOURCE,              "Resource"},
-		{LOG_DML,                   "DML"},
-		{LOG_EVENT_MODE_SET,        "Mode"},
-		{LOG_EVENT_DETECTION,       "Detect"},
-		{LOG_EVENT_LINK_TRAINING,   "LKTN"},
-		{LOG_EVENT_LINK_LOSS,       "LinkLoss"},
-		{LOG_EVENT_UNDERFLOW,       "Underflow"},
-		{LOG_IF_TRACE,              "InterfaceTrace"},
-		{LOG_DTN,                   "DTN"},
-		{LOG_DISPLAYSTATS,          "DisplayStats"}
-};
-
-
-/* ----------- Object init and destruction ----------- */
-static bool construct(struct dc_context *ctx, struct dal_logger *logger,
-		      uint32_t log_mask)
-{
-	/* malloc buffer and init offsets */
-	logger->log_buffer_size = DAL_LOGGER_BUFFER_MAX_SIZE;
-	logger->log_buffer = kcalloc(logger->log_buffer_size, sizeof(char),
-				     GFP_KERNEL);
-	if (!logger->log_buffer)
-		return false;
-
-	/* Initialize both offsets to start of buffer (empty) */
-	logger->buffer_read_offset = 0;
-	logger->buffer_write_offset = 0;
-
-	logger->open_count = 0;
-
-	logger->flags.bits.ENABLE_CONSOLE = 1;
-	logger->flags.bits.ENABLE_BUFFER = 0;
-
-	logger->ctx = ctx;
-
-	logger->mask = log_mask;
-
-	return true;
-}
-
-static void destruct(struct dal_logger *logger)
-{
-	if (logger->log_buffer) {
-		kfree(logger->log_buffer);
-		logger->log_buffer = NULL;
-	}
-}
-
-struct dal_logger *dal_logger_create(struct dc_context *ctx, uint32_t log_mask)
-{
-	/* malloc struct */
-	struct dal_logger *logger = kzalloc(sizeof(struct dal_logger),
-					    GFP_KERNEL);
-
-	if (!logger)
-		return NULL;
-	if (!construct(ctx, logger, log_mask)) {
-		kfree(logger);
-		return NULL;
-	}
-
-	return logger;
-}
-
-uint32_t dal_logger_destroy(struct dal_logger **logger)
-{
-	if (logger == NULL || *logger == NULL)
-		return 1;
-	destruct(*logger);
-	kfree(*logger);
-	*logger = NULL;
-
-	return 0;
-}
-
-/* ------------------------------------------------------------------------ */
-
-
-static bool dal_logger_should_log(
-	struct dal_logger *logger,
-	enum dc_log_type log_type)
-{
-	if (logger->mask & (1 << log_type))
-		return true;
-
-	return false;
-}
-
-static void log_to_debug_console(struct log_entry *entry)
-{
-	struct dal_logger *logger = entry->logger;
-
-	if (logger->flags.bits.ENABLE_CONSOLE == 0)
-		return;
-
-	if (entry->buf_offset) {
-		switch (entry->type) {
-		case LOG_ERROR:
-			dm_error("%s", entry->buf);
-			break;
-		default:
-			dm_output_to_console("%s", entry->buf);
-			break;
-		}
-	}
-}
-
-/* Print everything unread existing in log_buffer to debug console*/
-void dm_logger_flush_buffer(struct dal_logger *logger, bool should_warn)
-{
-	char *string_start = &logger->log_buffer[logger->buffer_read_offset];
-
-	if (should_warn)
-		dm_output_to_console(
-			"---------------- FLUSHING LOG BUFFER ----------------\n");
-	while (logger->buffer_read_offset < logger->buffer_write_offset) {
-
-		if (logger->log_buffer[logger->buffer_read_offset] == '\0') {
-			dm_output_to_console("%s", string_start);
-			string_start = logger->log_buffer + logger->buffer_read_offset + 1;
-		}
-		logger->buffer_read_offset++;
-	}
-	if (should_warn)
-		dm_output_to_console(
-			"-------------- END FLUSHING LOG BUFFER --------------\n\n");
-}
-
-static void log_to_internal_buffer(struct log_entry *entry)
-{
-
-	uint32_t size = entry->buf_offset;
-	struct dal_logger *logger = entry->logger;
-
-	if (logger->flags.bits.ENABLE_BUFFER == 0)
-		return;
-
-	if (logger->log_buffer == NULL)
-		return;
-
-	if (size > 0 && size < logger->log_buffer_size) {
-
-		int buffer_space = logger->log_buffer_size -
-				logger->buffer_write_offset;
-
-		if (logger->buffer_write_offset == logger->buffer_read_offset) {
-			/* Buffer is empty, start writing at beginning */
-			buffer_space = logger->log_buffer_size;
-			logger->buffer_write_offset = 0;
-			logger->buffer_read_offset = 0;
-		}
-
-		if (buffer_space > size) {
-			/* No wrap around, copy 'size' bytes
-			 * from 'entry->buf' to 'log_buffer'
-			 */
-			memmove(logger->log_buffer +
-					logger->buffer_write_offset,
-					entry->buf, size);
-			logger->buffer_write_offset += size;
-
-		} else {
-			/* Not enough room remaining, we should flush
-			 * existing logs */
-
-			/* Flush existing unread logs to console */
-			dm_logger_flush_buffer(logger, true);
-
-			/* Start writing to beginning of buffer */
-			memmove(logger->log_buffer, entry->buf, size);
-			logger->buffer_write_offset = size;
-			logger->buffer_read_offset = 0;
-		}
-
-	}
-}
-
-static void log_heading(struct log_entry *entry)
-{
-	int j;
-
-	for (j = 0; j < NUM_ELEMENTS(log_type_info_tbl); j++) {
-
-		const struct dc_log_type_info *info = &log_type_info_tbl[j];
-
-		if (info->type == entry->type)
-			dm_logger_append(entry, "[%s]\t", info->name);
-	}
-}
-
-static void append_entry(
-		struct log_entry *entry,
-		char *buffer,
-		uint32_t buf_size)
-{
-	if (!entry->buf ||
-		entry->buf_offset + buf_size > entry->max_buf_bytes
-	) {
-		BREAK_TO_DEBUGGER();
-		return;
-	}
-
-	/* Todo: check if off by 1 byte due to \0 anywhere */
-	memmove(entry->buf + entry->buf_offset, buffer, buf_size);
-	entry->buf_offset += buf_size;
-}
-
-/* ------------------------------------------------------------------------ */
-
-/* Warning: Be careful that 'msg' is null terminated and the total size is
- * less than DAL_LOGGER_BUFFER_MAX_LOG_LINE_SIZE (256) including '\0'
- */
-void dm_logger_write(
-	struct dal_logger *logger,
-	enum dc_log_type log_type,
-	const char *msg,
-	...)
-{
-	if (logger && dal_logger_should_log(logger, log_type)) {
-		uint32_t size;
-		va_list args;
-		char buffer[LOG_MAX_LINE_SIZE];
-		struct log_entry entry;
-
-		va_start(args, msg);
-
-		entry.logger = logger;
-
-		entry.buf = buffer;
-
-		entry.buf_offset = 0;
-		entry.max_buf_bytes = DAL_LOGGER_BUFFER_MAX_SIZE * sizeof(char);
-
-		entry.type = log_type;
-
-		log_heading(&entry);
-
-		size = dm_log_to_buffer(
-			buffer, LOG_MAX_LINE_SIZE - 1, msg, args);
-
-		buffer[entry.buf_offset + size] = '\0';
-		entry.buf_offset += size + 1;
-
-		/* --Flush log_entry buffer-- */
-		/* print to kernel console */
-		log_to_debug_console(&entry);
-		/* log internally for dsat */
-		log_to_internal_buffer(&entry);
-
-		va_end(args);
-	}
-}
-
-/* Same as dm_logger_write, except without open() and close(), which must
- * be done separately.
- */
-void dm_logger_append(
-	struct log_entry *entry,
-	const char *msg,
-	...)
-{
-	va_list args;
-
-	va_start(args, msg);
-	dm_logger_append_va(entry, msg, args);
-	va_end(args);
-}
-
-void dm_logger_append_va(
-	struct log_entry *entry,
-	const char *msg,
-	va_list args)
-{
-	struct dal_logger *logger;
-
-	if (!entry) {
-		BREAK_TO_DEBUGGER();
-		return;
-	}
-
-	logger = entry->logger;
-
-	if (logger && logger->open_count > 0 &&
-		dal_logger_should_log(logger, entry->type)) {
-
-		uint32_t size;
-		char buffer[LOG_MAX_LINE_SIZE];
-
-		size = dm_log_to_buffer(
-			buffer, LOG_MAX_LINE_SIZE, msg, args);
-
-		if (size < LOG_MAX_LINE_SIZE - 1) {
-			append_entry(entry, buffer, size);
-		} else {
-			append_entry(entry, "LOG_ERROR, line too long\n", 27);
-		}
-	}
-}
-
-void dm_logger_open(
-		struct dal_logger *logger,
-		struct log_entry *entry, /* out */
-		enum dc_log_type log_type)
-{
-	if (!entry) {
-		BREAK_TO_DEBUGGER();
-		return;
-	}
-
-	entry->type = log_type;
-	entry->logger = logger;
-
-	entry->buf = kzalloc(DAL_LOGGER_BUFFER_MAX_SIZE,
-			     GFP_KERNEL);
-
-	entry->buf_offset = 0;
-	entry->max_buf_bytes = DAL_LOGGER_BUFFER_MAX_SIZE * sizeof(char);
-
-	logger->open_count++;
-
-	log_heading(entry);
-}
-
-void dm_logger_close(struct log_entry *entry)
-{
-	struct dal_logger *logger = entry->logger;
-
-	if (logger && logger->open_count > 0) {
-		logger->open_count--;
-	} else {
-		BREAK_TO_DEBUGGER();
-		goto cleanup;
-	}
-
-	/* --Flush log_entry buffer-- */
-	/* print to kernel console */
-	log_to_debug_console(entry);
-	/* log internally for dsat */
-	log_to_internal_buffer(entry);
-
-	/* TODO: Write end heading */
-
-cleanup:
-	if (entry->buf) {
-		kfree(entry->buf);
-		entry->buf = NULL;
-		entry->buf_offset = 0;
-		entry->max_buf_bytes = 0;
-	}
-}
-
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
index c7f0b27e457e..be8a2494355a 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
@@ -3762,6 +3762,200 @@ static struct integrated_info *bios_parser_create_integrated_info(
 	return NULL;
 }
 
+enum bp_result update_slot_layout_info(
+	struct dc_bios *dcb,
+	unsigned int i,
+	struct slot_layout_info *slot_layout_info,
+	unsigned int record_offset)
+{
+	unsigned int j;
+	struct bios_parser *bp;
+	ATOM_BRACKET_LAYOUT_RECORD *record;
+	ATOM_COMMON_RECORD_HEADER *record_header;
+	enum bp_result result = BP_RESULT_NORECORD;
+
+	bp = BP_FROM_DCB(dcb);
+	record = NULL;
+	record_header = NULL;
+
+	for (;;) {
+
+		record_header = (ATOM_COMMON_RECORD_HEADER *)
+			GET_IMAGE(ATOM_COMMON_RECORD_HEADER, record_offset);
+		if (record_header == NULL) {
+			result = BP_RESULT_BADBIOSTABLE;
+			break;
+		}
+
+		/* the end of the list */
+		if (record_header->ucRecordType == 0xff ||
+			record_header->ucRecordSize == 0)	{
+			break;
+		}
+
+		if (record_header->ucRecordType ==
+			ATOM_BRACKET_LAYOUT_RECORD_TYPE &&
+			sizeof(ATOM_BRACKET_LAYOUT_RECORD)
+			<= record_header->ucRecordSize) {
+			record = (ATOM_BRACKET_LAYOUT_RECORD *)
+				(record_header);
+			result = BP_RESULT_OK;
+			break;
+		}
+
+		record_offset += record_header->ucRecordSize;
+	}
+
+	/* return if the record not found */
+	if (result != BP_RESULT_OK)
+		return result;
+
+	/* get slot sizes */
+	slot_layout_info->length = record->ucLength;
+	slot_layout_info->width = record->ucWidth;
+
+	/* get info for each connector in the slot */
+	slot_layout_info->num_of_connectors = record->ucConnNum;
+	for (j = 0; j < slot_layout_info->num_of_connectors; ++j) {
+		slot_layout_info->connectors[j].connector_type =
+			(enum connector_layout_type)
+			(record->asConnInfo[j].ucConnectorType);
+		switch (record->asConnInfo[j].ucConnectorType) {
+		case CONNECTOR_TYPE_DVI_D:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_DVI_D;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_DVI;
+			break;
+
+		case CONNECTOR_TYPE_HDMI:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_HDMI;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_HDMI;
+			break;
+
+		case CONNECTOR_TYPE_DISPLAY_PORT:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_DP;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_DP;
+			break;
+
+		case CONNECTOR_TYPE_MINI_DISPLAY_PORT:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_MINI_DP;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_MINI_DP;
+			break;
+
+		default:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_UNKNOWN;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_UNKNOWN;
+		}
+
+		slot_layout_info->connectors[j].position =
+			record->asConnInfo[j].ucPosition;
+		slot_layout_info->connectors[j].connector_id =
+			object_id_from_bios_object_id(
+				record->asConnInfo[j].usConnectorObjectId);
+	}
+	return result;
+}
+
+
+enum bp_result get_bracket_layout_record(
+	struct dc_bios *dcb,
+	unsigned int bracket_layout_id,
+	struct slot_layout_info *slot_layout_info)
+{
+	unsigned int i;
+	unsigned int record_offset;
+	struct bios_parser *bp;
+	enum bp_result result;
+	ATOM_OBJECT *object;
+	ATOM_OBJECT_TABLE *object_table;
+	unsigned int genericTableOffset;
+
+	bp = BP_FROM_DCB(dcb);
+	object = NULL;
+	if (slot_layout_info == NULL) {
+		DC_LOG_DETECTION_EDID_PARSER("Invalid slot_layout_info\n");
+		return BP_RESULT_BADINPUT;
+	}
+
+
+	genericTableOffset = bp->object_info_tbl_offset +
+		bp->object_info_tbl.v1_3->usMiscObjectTableOffset;
+	object_table = (ATOM_OBJECT_TABLE *)
+		GET_IMAGE(ATOM_OBJECT_TABLE, genericTableOffset);
+	if (!object_table)
+		return BP_RESULT_FAILURE;
+
+	result = BP_RESULT_NORECORD;
+	for (i = 0; i < object_table->ucNumberOfObjects; ++i) {
+
+		if (bracket_layout_id ==
+			object_table->asObjects[i].usObjectID) {
+
+			object = &object_table->asObjects[i];
+			record_offset = object->usRecordOffset +
+				bp->object_info_tbl_offset;
+
+			result = update_slot_layout_info(dcb, i,
+				slot_layout_info, record_offset);
+			break;
+		}
+	}
+	return result;
+}
+
+static enum bp_result bios_get_board_layout_info(
+	struct dc_bios *dcb,
+	struct board_layout_info *board_layout_info)
+{
+	unsigned int i;
+	struct bios_parser *bp;
+	enum bp_result record_result;
+
+	const unsigned int slot_index_to_vbios_id[MAX_BOARD_SLOTS] = {
+		GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID1,
+		GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID2,
+		0, 0
+	};
+
+	bp = BP_FROM_DCB(dcb);
+	if (board_layout_info == NULL) {
+		DC_LOG_DETECTION_EDID_PARSER("Invalid board_layout_info\n");
+		return BP_RESULT_BADINPUT;
+	}
+
+	board_layout_info->num_of_slots = 0;
+
+	for (i = 0; i < MAX_BOARD_SLOTS; ++i) {
+		record_result = get_bracket_layout_record(dcb,
+			slot_index_to_vbios_id[i],
+			&board_layout_info->slots[i]);
+
+		if (record_result == BP_RESULT_NORECORD && i > 0)
+			break; /* no more slots present in bios */
+		else if (record_result != BP_RESULT_OK)
+			return record_result;  /* fail */
+
+		++board_layout_info->num_of_slots;
+	}
+
+	/* all data is valid */
+	board_layout_info->is_number_of_slots_valid = 1;
+	board_layout_info->is_slots_size_valid = 1;
+	board_layout_info->is_connector_offsets_valid = 1;
+	board_layout_info->is_connector_lengths_valid = 1;
+
+	return BP_RESULT_OK;
+}
+
 /******************************************************************************/
 
 static const struct dc_vbios_funcs vbios_funcs = {
@@ -3836,6 +4030,8 @@ static const struct dc_vbios_funcs vbios_funcs = {
 	.post_init = bios_parser_post_init,  /* patch vbios table for mxm module by reading i2c */
 
 	.bios_parser_destroy = bios_parser_destroy,
+
+	.get_board_layout_info = bios_get_board_layout_info,
 };
 
 static bool bios_parser_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index b8cef7af3c4a..eab007e1793c 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -43,6 +43,29 @@
 #include "bios_parser_interface.h"
 
 #include "bios_parser_common.h"
+
+/* Temporarily add in defines until ObjectID.h patch is updated in a few days */
+#ifndef GENERIC_OBJECT_ID_BRACKET_LAYOUT
+#define GENERIC_OBJECT_ID_BRACKET_LAYOUT          0x05
+#endif /* GENERIC_OBJECT_ID_BRACKET_LAYOUT */
+
+#ifndef GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID1
+#define GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID1	\
+	(GRAPH_OBJECT_TYPE_GENERIC << OBJECT_TYPE_SHIFT |\
+	GRAPH_OBJECT_ENUM_ID1 << ENUM_ID_SHIFT |\
+	GENERIC_OBJECT_ID_BRACKET_LAYOUT << OBJECT_ID_SHIFT)
+#endif /* GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID1 */
+
+#ifndef GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID2
+#define GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID2	\
+	(GRAPH_OBJECT_TYPE_GENERIC << OBJECT_TYPE_SHIFT |\
+	GRAPH_OBJECT_ENUM_ID2 << ENUM_ID_SHIFT |\
+	GENERIC_OBJECT_ID_BRACKET_LAYOUT << OBJECT_ID_SHIFT)
+#endif /* GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID2 */
+
+#define DC_LOGGER \
+	bp->base.ctx->logger
+
 #define LAST_RECORD_TYPE 0xff
 #define SMU9_SYSPLL0_ID  0
 
@@ -86,7 +109,6 @@ static struct atom_encoder_caps_record *get_encoder_cap_record(
 
 #define DATA_TABLES(table) (bp->master_data_tbl->listOfdatatables.table)
 
-
 static void destruct(struct bios_parser *bp)
 {
 	kfree(bp->base.bios_local_image);
@@ -656,7 +678,7 @@ static enum bp_result bios_parser_get_gpio_pin_info(
 		return BP_RESULT_BADBIOSTABLE;
 
 	if (sizeof(struct atom_common_table_header) +
-			sizeof(struct atom_gpio_pin_lut_v2_1)
+			sizeof(struct atom_gpio_pin_assignment)
 			> le16_to_cpu(header->table_header.structuresize))
 		return BP_RESULT_BADBIOSTABLE;
 
@@ -1854,6 +1876,198 @@ static struct integrated_info *bios_parser_create_integrated_info(
 	return NULL;
 }
 
+static enum bp_result update_slot_layout_info(
+	struct dc_bios *dcb,
+	unsigned int i,
+	struct slot_layout_info *slot_layout_info)
+{
+	unsigned int record_offset;
+	unsigned int j;
+	struct atom_display_object_path_v2 *object;
+	struct atom_bracket_layout_record *record;
+	struct atom_common_record_header *record_header;
+	enum bp_result result;
+	struct bios_parser *bp;
+	struct object_info_table *tbl;
+	struct display_object_info_table_v1_4 *v1_4;
+
+	record = NULL;
+	record_header = NULL;
+	result = BP_RESULT_NORECORD;
+
+	bp = BP_FROM_DCB(dcb);
+	tbl = &bp->object_info_tbl;
+	v1_4 = tbl->v1_4;
+
+	object = &v1_4->display_path[i];
+	record_offset = (unsigned int)
+		(object->disp_recordoffset) +
+		(unsigned int)(bp->object_info_tbl_offset);
+
+	for (;;) {
+
+		record_header = (struct atom_common_record_header *)
+			GET_IMAGE(struct atom_common_record_header,
+			record_offset);
+		if (record_header == NULL) {
+			result = BP_RESULT_BADBIOSTABLE;
+			break;
+		}
+
+		/* the end of the list */
+		if (record_header->record_type == 0xff ||
+			record_header->record_size == 0)	{
+			break;
+		}
+
+		if (record_header->record_type ==
+			ATOM_BRACKET_LAYOUT_RECORD_TYPE &&
+			sizeof(struct atom_bracket_layout_record)
+			<= record_header->record_size) {
+			record = (struct atom_bracket_layout_record *)
+				(record_header);
+			result = BP_RESULT_OK;
+			break;
+		}
+
+		record_offset += record_header->record_size;
+	}
+
+	/* return if the record not found */
+	if (result != BP_RESULT_OK)
+		return result;
+
+	/* get slot sizes */
+	slot_layout_info->length = record->bracketlen;
+	slot_layout_info->width = record->bracketwidth;
+
+	/* get info for each connector in the slot */
+	slot_layout_info->num_of_connectors = record->conn_num;
+	for (j = 0; j < slot_layout_info->num_of_connectors; ++j) {
+		slot_layout_info->connectors[j].connector_type =
+			(enum connector_layout_type)
+			(record->conn_info[j].connector_type);
+		switch (record->conn_info[j].connector_type) {
+		case CONNECTOR_TYPE_DVI_D:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_DVI_D;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_DVI;
+			break;
+
+		case CONNECTOR_TYPE_HDMI:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_HDMI;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_HDMI;
+			break;
+
+		case CONNECTOR_TYPE_DISPLAY_PORT:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_DP;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_DP;
+			break;
+
+		case CONNECTOR_TYPE_MINI_DISPLAY_PORT:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_MINI_DP;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_MINI_DP;
+			break;
+
+		default:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_UNKNOWN;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_UNKNOWN;
+		}
+
+		slot_layout_info->connectors[j].position =
+			record->conn_info[j].position;
+		slot_layout_info->connectors[j].connector_id =
+			object_id_from_bios_object_id(
+				record->conn_info[j].connectorobjid);
+	}
+	return result;
+}
+
+
+static enum bp_result get_bracket_layout_record(
+	struct dc_bios *dcb,
+	unsigned int bracket_layout_id,
+	struct slot_layout_info *slot_layout_info)
+{
+	unsigned int i;
+	struct bios_parser *bp = BP_FROM_DCB(dcb);
+	enum bp_result result;
+	struct object_info_table *tbl;
+	struct display_object_info_table_v1_4 *v1_4;
+
+	if (slot_layout_info == NULL) {
+		DC_LOG_DETECTION_EDID_PARSER("Invalid slot_layout_info\n");
+		return BP_RESULT_BADINPUT;
+	}
+	tbl = &bp->object_info_tbl;
+	v1_4 = tbl->v1_4;
+
+	result = BP_RESULT_NORECORD;
+	for (i = 0; i < v1_4->number_of_path; ++i)	{
+
+		if (bracket_layout_id ==
+			v1_4->display_path[i].display_objid) {
+			result = update_slot_layout_info(dcb, i,
+				slot_layout_info);
+			break;
+		}
+	}
+	return result;
+}
+
+static enum bp_result bios_get_board_layout_info(
+	struct dc_bios *dcb,
+	struct board_layout_info *board_layout_info)
+{
+	unsigned int i;
+	struct bios_parser *bp;
+	enum bp_result record_result;
+
+	const unsigned int slot_index_to_vbios_id[MAX_BOARD_SLOTS] = {
+		GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID1,
+		GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID2,
+		0, 0
+	};
+
+	bp = BP_FROM_DCB(dcb);
+	if (board_layout_info == NULL) {
+		DC_LOG_DETECTION_EDID_PARSER("Invalid board_layout_info\n");
+		return BP_RESULT_BADINPUT;
+	}
+
+	board_layout_info->num_of_slots = 0;
+
+	for (i = 0; i < MAX_BOARD_SLOTS; ++i) {
+		record_result = get_bracket_layout_record(dcb,
+			slot_index_to_vbios_id[i],
+			&board_layout_info->slots[i]);
+
+		if (record_result == BP_RESULT_NORECORD && i > 0)
+			break; /* no more slots present in bios */
+		else if (record_result != BP_RESULT_OK)
+			return record_result;  /* fail */
+
+		++board_layout_info->num_of_slots;
+	}
+
+	/* all data is valid */
+	board_layout_info->is_number_of_slots_valid = 1;
+	board_layout_info->is_slots_size_valid = 1;
+	board_layout_info->is_connector_offsets_valid = 1;
+	board_layout_info->is_connector_lengths_valid = 1;
+
+	return BP_RESULT_OK;
+}
+
 static const struct dc_vbios_funcs vbios_funcs = {
 	.get_connectors_number = bios_parser_get_connectors_number,
 
@@ -1925,6 +2139,8 @@ static const struct dc_vbios_funcs vbios_funcs = {
 	.bios_parser_destroy = firmware_parser_destroy,
 
 	.get_smu_clock_info = bios_parser_get_smu_clock_info,
+
+	.get_board_layout_info = bios_get_board_layout_info,
 };
 
 static bool bios_parser_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table.c b/drivers/gpu/drm/amd/display/dc/bios/command_table.c
index 651e1fd4622f..a558bfaa0c46 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table.c
@@ -808,6 +808,24 @@ static enum bp_result transmitter_control_v1_5(
 	 * (=1: 8bpp, =1.25: 10bpp, =1.5:12bpp, =2: 16bpp)
 	 * LVDS mode: usPixelClock = pixel clock
 	 */
+	if  (cntl->signal == SIGNAL_TYPE_HDMI_TYPE_A) {
+		switch (cntl->color_depth) {
+		case COLOR_DEPTH_101010:
+			params.usSymClock =
+				cpu_to_le16((le16_to_cpu(params.usSymClock) * 30) / 24);
+			break;
+		case COLOR_DEPTH_121212:
+			params.usSymClock =
+				cpu_to_le16((le16_to_cpu(params.usSymClock) * 36) / 24);
+			break;
+		case COLOR_DEPTH_161616:
+			params.usSymClock =
+				cpu_to_le16((le16_to_cpu(params.usSymClock) * 48) / 24);
+			break;
+		default:
+			break;
+		}
+	}
 
 	if (EXEC_BIOS_CMD_TABLE(UNIPHYTransmitterControl, params))
 		result = BP_RESULT_OK;
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
index 752b08a42d3e..2b5dc499a35e 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
@@ -59,36 +59,7 @@
 	bios_cmd_table_para_revision(bp->base.ctx->driver_context, \
 			GET_INDEX_INTO_MASTER_TABLE(command, fname))
 
-static void init_dig_encoder_control(struct bios_parser *bp);
-static void init_transmitter_control(struct bios_parser *bp);
-static void init_set_pixel_clock(struct bios_parser *bp);
 
-static void init_set_crtc_timing(struct bios_parser *bp);
-
-static void init_select_crtc_source(struct bios_parser *bp);
-static void init_enable_crtc(struct bios_parser *bp);
-
-static void init_external_encoder_control(struct bios_parser *bp);
-static void init_enable_disp_power_gating(struct bios_parser *bp);
-static void init_set_dce_clock(struct bios_parser *bp);
-static void init_get_smu_clock_info(struct bios_parser *bp);
-
-void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp)
-{
-	init_dig_encoder_control(bp);
-	init_transmitter_control(bp);
-	init_set_pixel_clock(bp);
-
-	init_set_crtc_timing(bp);
-
-	init_select_crtc_source(bp);
-	init_enable_crtc(bp);
-
-	init_external_encoder_control(bp);
-	init_enable_disp_power_gating(bp);
-	init_set_dce_clock(bp);
-	init_get_smu_clock_info(bp);
-}
 
 static uint32_t bios_cmd_table_para_revision(void *dev,
 					     uint32_t index)
@@ -829,3 +800,20 @@ static unsigned int get_smu_clock_info_v3_1(struct bios_parser *bp, uint8_t id)
 	return 0;
 }
 
+void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp)
+{
+	init_dig_encoder_control(bp);
+	init_transmitter_control(bp);
+	init_set_pixel_clock(bp);
+
+	init_set_crtc_timing(bp);
+
+	init_select_crtc_source(bp);
+	init_enable_crtc(bp);
+
+	init_external_encoder_control(bp);
+	init_enable_disp_power_gating(bp);
+	init_set_dce_clock(bp);
+	init_get_smu_clock_info(bp);
+
+}
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
index bbbcef566c55..770ff89ba7e1 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
@@ -55,7 +55,7 @@ bool dal_bios_parser_init_cmd_tbl_helper2(
 	case DCE_VERSION_11_22:
 		*h = dal_cmd_tbl_helper_dce112_get_table2();
 		return true;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 		*h = dal_cmd_tbl_helper_dce112_get_table2();
 		return true;
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/Makefile b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
index 95f332ee3e7e..416500e51b8d 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
@@ -38,7 +38,7 @@ CFLAGS_dcn_calc_math.o := $(calcs_ccflags) -Wno-tautological-compare
 
 BW_CALCS = dce_calcs.o bw_fixed.o custom_float.o
 
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_X86
 BW_CALCS += dcn_calcs.o dcn_calc_math.o dcn_calc_auto.o
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/calcs_logger.h b/drivers/gpu/drm/amd/display/dc/calcs/calcs_logger.h
index fc3f98fb09ea..62435bfc274d 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/calcs_logger.h
+++ b/drivers/gpu/drm/amd/display/dc/calcs/calcs_logger.h
@@ -25,10 +25,9 @@
 
 #ifndef _CALCS_CALCS_LOGGER_H_
 #define _CALCS_CALCS_LOGGER_H_
-#define DC_LOGGER \
-	logger
+#define DC_LOGGER ctx->logger
 
-static void print_bw_calcs_dceip(struct dal_logger *logger, const struct bw_calcs_dceip *dceip)
+static void print_bw_calcs_dceip(struct dc_context *ctx, const struct bw_calcs_dceip *dceip)
 {
 
 	DC_LOG_BANDWIDTH_CALCS("#####################################################################");
@@ -122,7 +121,7 @@ static void print_bw_calcs_dceip(struct dal_logger *logger, const struct bw_calc
 
 }
 
-static void print_bw_calcs_vbios(struct dal_logger *logger, const struct bw_calcs_vbios *vbios)
+static void print_bw_calcs_vbios(struct dc_context *ctx, const struct bw_calcs_vbios *vbios)
 {
 
 	DC_LOG_BANDWIDTH_CALCS("#####################################################################");
@@ -181,7 +180,7 @@ static void print_bw_calcs_vbios(struct dal_logger *logger, const struct bw_calc
 
 }
 
-static void print_bw_calcs_data(struct dal_logger *logger, struct bw_calcs_data *data)
+static void print_bw_calcs_data(struct dc_context *ctx, struct bw_calcs_data *data)
 {
 
 	int i, j, k;
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
index 2c4e8f0cb2dc..160d11a15eac 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
@@ -3010,9 +3010,9 @@ bool bw_calcs(struct dc_context *ctx,
 		struct bw_fixed low_yclk = vbios->low_yclk;
 
 		if (ctx->dc->debug.bandwidth_calcs_trace) {
-			print_bw_calcs_dceip(ctx->logger, dceip);
-			print_bw_calcs_vbios(ctx->logger, vbios);
-			print_bw_calcs_data(ctx->logger, data);
+			print_bw_calcs_dceip(ctx, dceip);
+			print_bw_calcs_vbios(ctx, vbios);
+			print_bw_calcs_data(ctx, data);
 		}
 		calculate_bandwidth(dceip, vbios, data);
 
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index 49a4ea45466d..bd039322f697 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -31,6 +31,8 @@
 
 #include "resource.h"
 #include "dcn10/dcn10_resource.h"
+#include "dcn10/dcn10_hubbub.h"
+
 #include "dcn_calc_math.h"
 
 #define DC_LOGGER \
@@ -248,7 +250,24 @@ static void pipe_ctx_to_e2e_pipe_params (
 	else if (pipe->bottom_pipe != NULL && pipe->bottom_pipe->plane_state == pipe->plane_state)
 		input->src.is_hsplit = true;
 
-	input->src.dcc                 = pipe->plane_state->dcc.enable;
+	if (pipe->plane_res.dpp->ctx->dc->debug.optimized_watermark) {
+		/*
+		 * this method requires us to always re-calculate watermark when dcc change
+		 * between flip.
+		 */
+		input->src.dcc = pipe->plane_state->dcc.enable ? 1 : 0;
+	} else {
+		/*
+		 * allow us to disable dcc on the fly without re-calculating WM
+		 *
+		 * extra overhead for DCC is quite small.  for 1080p WM without
+		 * DCC is only 0.417us lower (urgent goes from 6.979us to 6.562us)
+		 */
+		unsigned int bpe;
+
+		input->src.dcc = pipe->plane_res.dpp->ctx->dc->res_pool->hubbub->funcs->
+			dcc_support_pixel_format(pipe->plane_state->format, &bpe) ? 1 : 0;
+	}
 	input->src.dcc_rate            = 1;
 	input->src.meta_pitch          = pipe->plane_state->dcc.grph.meta_pitch;
 	input->src.source_scan         = dm_horz;
@@ -423,6 +442,10 @@ static void dcn_bw_calc_rq_dlg_ttu(
 	int total_flip_bytes = 0;
 	int i;
 
+	memset(dlg_regs, 0, sizeof(*dlg_regs));
+	memset(ttu_regs, 0, sizeof(*ttu_regs));
+	memset(rq_regs, 0, sizeof(*rq_regs));
+
 	for (i = 0; i < number_of_planes; i++) {
 		total_active_bw += v->read_bandwidth[i];
 		total_prefetch_bw += v->prefetch_bandwidth[i];
@@ -501,6 +524,7 @@ static void split_stream_across_pipes(
 	resource_build_scaling_params(secondary_pipe);
 }
 
+#if 0
 static void calc_wm_sets_and_perf_params(
 		struct dc_state *context,
 		struct dcn_bw_internal_vars *v)
@@ -582,6 +606,7 @@ static void calc_wm_sets_and_perf_params(
 	if (v->voltage_level >= 3)
 		context->bw.dcn.watermarks.d = context->bw.dcn.watermarks.a;
 }
+#endif
 
 static bool dcn_bw_apply_registry_override(struct dc *dc)
 {
@@ -651,7 +676,7 @@ static void hack_force_pipe_split(struct dcn_bw_internal_vars *v,
 }
 
 static void hack_bounding_box(struct dcn_bw_internal_vars *v,
-		struct dc_debug *dbg,
+		struct dc_debug_options *dbg,
 		struct dc_state *context)
 {
 	if (dbg->pipe_split_policy == MPC_SPLIT_AVOID)
@@ -883,7 +908,26 @@ bool dcn_validate_bandwidth(
 				ASSERT(pipe->plane_res.scl_data.ratios.vert.value != dc_fixpt_one.value
 					|| v->scaler_rec_out_width[input_idx] == v->viewport_height[input_idx]);
 			}
-			v->dcc_enable[input_idx] = pipe->plane_state->dcc.enable ? dcn_bw_yes : dcn_bw_no;
+
+			if (dc->debug.optimized_watermark) {
+				/*
+				 * this method requires us to always re-calculate watermark when dcc change
+				 * between flip.
+				 */
+				v->dcc_enable[input_idx] = pipe->plane_state->dcc.enable ? dcn_bw_yes : dcn_bw_no;
+			} else {
+				/*
+				 * allow us to disable dcc on the fly without re-calculating WM
+				 *
+				 * extra overhead for DCC is quite small.  for 1080p WM without
+				 * DCC is only 0.417us lower (urgent goes from 6.979us to 6.562us)
+				 */
+				unsigned int bpe;
+
+				v->dcc_enable[input_idx] = dc->res_pool->hubbub->funcs->dcc_support_pixel_format(
+						pipe->plane_state->format, &bpe) ? dcn_bw_yes : dcn_bw_no;
+			}
+
 			v->source_pixel_format[input_idx] = tl_pixel_format_to_bw_defs(
 					pipe->plane_state->format);
 			v->source_surface_mode[input_idx] = tl_sw_mode_to_bw_defs(
@@ -976,43 +1020,60 @@ bool dcn_validate_bandwidth(
 				bw_consumed = v->fabric_and_dram_bandwidth;
 
 		display_pipe_configuration(v);
-		calc_wm_sets_and_perf_params(context, v);
-		context->bw.dcn.calc_clk.fclk_khz = (int)(bw_consumed * 1000000 /
+		/*calc_wm_sets_and_perf_params(context, v);*/
+		/* Only 1 set is used by dcn since no noticeable
+		 * performance improvement was measured and due to hw bug DEGVIDCN10-254
+		 */
+		dispclkdppclkdcfclk_deep_sleep_prefetch_parameters_watermarks_and_performance_calculation(v);
+
+		context->bw.dcn.watermarks.a.cstate_pstate.cstate_exit_ns =
+			v->stutter_exit_watermark * 1000;
+		context->bw.dcn.watermarks.a.cstate_pstate.cstate_enter_plus_exit_ns =
+				v->stutter_enter_plus_exit_watermark * 1000;
+		context->bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns =
+				v->dram_clock_change_watermark * 1000;
+		context->bw.dcn.watermarks.a.pte_meta_urgent_ns = v->ptemeta_urgent_watermark * 1000;
+		context->bw.dcn.watermarks.a.urgent_ns = v->urgent_watermark * 1000;
+		context->bw.dcn.watermarks.b = context->bw.dcn.watermarks.a;
+		context->bw.dcn.watermarks.c = context->bw.dcn.watermarks.a;
+		context->bw.dcn.watermarks.d = context->bw.dcn.watermarks.a;
+
+		context->bw.dcn.clk.fclk_khz = (int)(bw_consumed * 1000000 /
 				(ddr4_dram_factor_single_Channel * v->number_of_channels));
 		if (bw_consumed == v->fabric_and_dram_bandwidth_vmin0p65) {
-			context->bw.dcn.calc_clk.fclk_khz = (int)(bw_consumed * 1000000 / 32);
+			context->bw.dcn.clk.fclk_khz = (int)(bw_consumed * 1000000 / 32);
 		}
 
-		context->bw.dcn.calc_clk.dcfclk_deep_sleep_khz = (int)(v->dcf_clk_deep_sleep * 1000);
-		context->bw.dcn.calc_clk.dcfclk_khz = (int)(v->dcfclk * 1000);
+		context->bw.dcn.clk.dcfclk_deep_sleep_khz = (int)(v->dcf_clk_deep_sleep * 1000);
+		context->bw.dcn.clk.dcfclk_khz = (int)(v->dcfclk * 1000);
 
-		context->bw.dcn.calc_clk.dispclk_khz = (int)(v->dispclk * 1000);
+		context->bw.dcn.clk.dispclk_khz = (int)(v->dispclk * 1000);
 		if (dc->debug.max_disp_clk == true)
-			context->bw.dcn.calc_clk.dispclk_khz = (int)(dc->dcn_soc->max_dispclk_vmax0p9 * 1000);
+			context->bw.dcn.clk.dispclk_khz = (int)(dc->dcn_soc->max_dispclk_vmax0p9 * 1000);
 
-		if (context->bw.dcn.calc_clk.dispclk_khz <
+		if (context->bw.dcn.clk.dispclk_khz <
 				dc->debug.min_disp_clk_khz) {
-			context->bw.dcn.calc_clk.dispclk_khz =
+			context->bw.dcn.clk.dispclk_khz =
 					dc->debug.min_disp_clk_khz;
 		}
 
-		context->bw.dcn.calc_clk.dppclk_khz = context->bw.dcn.calc_clk.dispclk_khz / v->dispclk_dppclk_ratio;
-
+		context->bw.dcn.clk.dppclk_khz = context->bw.dcn.clk.dispclk_khz / v->dispclk_dppclk_ratio;
+		context->bw.dcn.clk.phyclk_khz = v->phyclk_per_state[v->voltage_level];
 		switch (v->voltage_level) {
 		case 0:
-			context->bw.dcn.calc_clk.max_supported_dppclk_khz =
+			context->bw.dcn.clk.max_supported_dppclk_khz =
 					(int)(dc->dcn_soc->max_dppclk_vmin0p65 * 1000);
 			break;
 		case 1:
-			context->bw.dcn.calc_clk.max_supported_dppclk_khz =
+			context->bw.dcn.clk.max_supported_dppclk_khz =
 					(int)(dc->dcn_soc->max_dppclk_vmid0p72 * 1000);
 			break;
 		case 2:
-			context->bw.dcn.calc_clk.max_supported_dppclk_khz =
+			context->bw.dcn.clk.max_supported_dppclk_khz =
 					(int)(dc->dcn_soc->max_dppclk_vnom0p8 * 1000);
 			break;
 		default:
-			context->bw.dcn.calc_clk.max_supported_dppclk_khz =
+			context->bw.dcn.clk.max_supported_dppclk_khz =
 					(int)(dc->dcn_soc->max_dppclk_vmax0p9 * 1000);
 			break;
 		}
@@ -1225,27 +1286,27 @@ static unsigned int dcn_find_normalized_clock_vdd_Level(
 
 unsigned int dcn_find_dcfclk_suits_all(
 	const struct dc *dc,
-	struct clocks_value *clocks)
+	struct dc_clocks *clocks)
 {
 	unsigned vdd_level, vdd_level_temp;
 	unsigned dcf_clk;
 
 	/*find a common supported voltage level*/
 	vdd_level = dcn_find_normalized_clock_vdd_Level(
-		dc, DM_PP_CLOCK_TYPE_DISPLAY_CLK, clocks->dispclk_in_khz);
+		dc, DM_PP_CLOCK_TYPE_DISPLAY_CLK, clocks->dispclk_khz);
 	vdd_level_temp = dcn_find_normalized_clock_vdd_Level(
-		dc, DM_PP_CLOCK_TYPE_DISPLAYPHYCLK, clocks->phyclk_in_khz);
+		dc, DM_PP_CLOCK_TYPE_DISPLAYPHYCLK, clocks->phyclk_khz);
 
 	vdd_level = dcn_bw_max(vdd_level, vdd_level_temp);
 	vdd_level_temp = dcn_find_normalized_clock_vdd_Level(
-		dc, DM_PP_CLOCK_TYPE_DPPCLK, clocks->dppclk_in_khz);
+		dc, DM_PP_CLOCK_TYPE_DPPCLK, clocks->dppclk_khz);
 	vdd_level = dcn_bw_max(vdd_level, vdd_level_temp);
 
 	vdd_level_temp = dcn_find_normalized_clock_vdd_Level(
-		dc, DM_PP_CLOCK_TYPE_MEMORY_CLK, clocks->dcfclock_in_khz);
+		dc, DM_PP_CLOCK_TYPE_MEMORY_CLK, clocks->fclk_khz);
 	vdd_level = dcn_bw_max(vdd_level, vdd_level_temp);
 	vdd_level_temp = dcn_find_normalized_clock_vdd_Level(
-		dc, DM_PP_CLOCK_TYPE_DCFCLK, clocks->dcfclock_in_khz);
+		dc, DM_PP_CLOCK_TYPE_DCFCLK, clocks->dcfclk_khz);
 
 	/*find that level conresponding dcfclk*/
 	vdd_level = dcn_bw_max(vdd_level, vdd_level_temp);
@@ -1331,21 +1392,14 @@ void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc)
 {
 	struct pp_smu_funcs_rv *pp = dc->res_pool->pp_smu;
 	struct pp_smu_wm_range_sets ranges = {0};
-	int max_fclk_khz, nom_fclk_khz, mid_fclk_khz, min_fclk_khz;
-	int max_dcfclk_khz, min_dcfclk_khz;
-	int socclk_khz;
+	int min_fclk_khz, min_dcfclk_khz, socclk_khz;
 	const int overdrive = 5000000; /* 5 GHz to cover Overdrive */
-	unsigned factor = (ddr4_dram_factor_single_Channel * dc->dcn_soc->number_of_channels);
 
 	if (!pp->set_wm_ranges)
 		return;
 
 	kernel_fpu_begin();
-	max_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 * 1000000 / factor;
-	nom_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 * 1000000 / factor;
-	mid_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 * 1000000 / factor;
 	min_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 * 1000000 / 32;
-	max_dcfclk_khz = dc->dcn_soc->dcfclkv_max0p9 * 1000;
 	min_dcfclk_khz = dc->dcn_soc->dcfclkv_min0p65 * 1000;
 	socclk_khz = dc->dcn_soc->socclk * 1000;
 	kernel_fpu_end();
@@ -1353,105 +1407,46 @@ void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc)
 	/* Now notify PPLib/SMU about which Watermarks sets they should select
 	 * depending on DPM state they are in. And update BW MGR GFX Engine and
 	 * Memory clock member variables for Watermarks calculations for each
-	 * Watermark Set
+	 * Watermark Set. Only one watermark set for dcn1 due to hw bug DEGVIDCN10-254.
 	 */
 	/* SOCCLK does not affect anytihng but writeback for DCN so for now we dont
 	 * care what the value is, hence min to overdrive level
 	 */
-	ranges.num_reader_wm_sets = WM_COUNT;
-	ranges.num_writer_wm_sets = WM_COUNT;
+	ranges.num_reader_wm_sets = WM_SET_COUNT;
+	ranges.num_writer_wm_sets = WM_SET_COUNT;
 	ranges.reader_wm_sets[0].wm_inst = WM_A;
 	ranges.reader_wm_sets[0].min_drain_clk_khz = min_dcfclk_khz;
-	ranges.reader_wm_sets[0].max_drain_clk_khz = max_dcfclk_khz;
+	ranges.reader_wm_sets[0].max_drain_clk_khz = overdrive;
 	ranges.reader_wm_sets[0].min_fill_clk_khz = min_fclk_khz;
-	ranges.reader_wm_sets[0].max_fill_clk_khz = min_fclk_khz;
+	ranges.reader_wm_sets[0].max_fill_clk_khz = overdrive;
 	ranges.writer_wm_sets[0].wm_inst = WM_A;
 	ranges.writer_wm_sets[0].min_fill_clk_khz = socclk_khz;
 	ranges.writer_wm_sets[0].max_fill_clk_khz = overdrive;
 	ranges.writer_wm_sets[0].min_drain_clk_khz = min_fclk_khz;
-	ranges.writer_wm_sets[0].max_drain_clk_khz = min_fclk_khz;
-
-	ranges.reader_wm_sets[1].wm_inst = WM_B;
-	ranges.reader_wm_sets[1].min_drain_clk_khz = min_fclk_khz;
-	ranges.reader_wm_sets[1].max_drain_clk_khz = max_dcfclk_khz;
-	ranges.reader_wm_sets[1].min_fill_clk_khz = mid_fclk_khz;
-	ranges.reader_wm_sets[1].max_fill_clk_khz = mid_fclk_khz;
-	ranges.writer_wm_sets[1].wm_inst = WM_B;
-	ranges.writer_wm_sets[1].min_fill_clk_khz = socclk_khz;
-	ranges.writer_wm_sets[1].max_fill_clk_khz = overdrive;
-	ranges.writer_wm_sets[1].min_drain_clk_khz = mid_fclk_khz;
-	ranges.writer_wm_sets[1].max_drain_clk_khz = mid_fclk_khz;
-
-
-	ranges.reader_wm_sets[2].wm_inst = WM_C;
-	ranges.reader_wm_sets[2].min_drain_clk_khz = min_fclk_khz;
-	ranges.reader_wm_sets[2].max_drain_clk_khz = max_dcfclk_khz;
-	ranges.reader_wm_sets[2].min_fill_clk_khz = nom_fclk_khz;
-	ranges.reader_wm_sets[2].max_fill_clk_khz = nom_fclk_khz;
-	ranges.writer_wm_sets[2].wm_inst = WM_C;
-	ranges.writer_wm_sets[2].min_fill_clk_khz = socclk_khz;
-	ranges.writer_wm_sets[2].max_fill_clk_khz = overdrive;
-	ranges.writer_wm_sets[2].min_drain_clk_khz = nom_fclk_khz;
-	ranges.writer_wm_sets[2].max_drain_clk_khz = nom_fclk_khz;
-
-	ranges.reader_wm_sets[3].wm_inst = WM_D;
-	ranges.reader_wm_sets[3].min_drain_clk_khz = min_fclk_khz;
-	ranges.reader_wm_sets[3].max_drain_clk_khz = max_dcfclk_khz;
-	ranges.reader_wm_sets[3].min_fill_clk_khz = max_fclk_khz;
-	ranges.reader_wm_sets[3].max_fill_clk_khz = max_fclk_khz;
-	ranges.writer_wm_sets[3].wm_inst = WM_D;
-	ranges.writer_wm_sets[3].min_fill_clk_khz = socclk_khz;
-	ranges.writer_wm_sets[3].max_fill_clk_khz = overdrive;
-	ranges.writer_wm_sets[3].min_drain_clk_khz = max_fclk_khz;
-	ranges.writer_wm_sets[3].max_drain_clk_khz = max_fclk_khz;
+	ranges.writer_wm_sets[0].max_drain_clk_khz = overdrive;
 
 	if (dc->debug.pplib_wm_report_mode == WM_REPORT_OVERRIDE) {
 		ranges.reader_wm_sets[0].wm_inst = WM_A;
 		ranges.reader_wm_sets[0].min_drain_clk_khz = 300000;
-		ranges.reader_wm_sets[0].max_drain_clk_khz = 654000;
+		ranges.reader_wm_sets[0].max_drain_clk_khz = 5000000;
 		ranges.reader_wm_sets[0].min_fill_clk_khz = 800000;
-		ranges.reader_wm_sets[0].max_fill_clk_khz = 800000;
+		ranges.reader_wm_sets[0].max_fill_clk_khz = 5000000;
 		ranges.writer_wm_sets[0].wm_inst = WM_A;
 		ranges.writer_wm_sets[0].min_fill_clk_khz = 200000;
-		ranges.writer_wm_sets[0].max_fill_clk_khz = 757000;
+		ranges.writer_wm_sets[0].max_fill_clk_khz = 5000000;
 		ranges.writer_wm_sets[0].min_drain_clk_khz = 800000;
-		ranges.writer_wm_sets[0].max_drain_clk_khz = 800000;
-
-		ranges.reader_wm_sets[1].wm_inst = WM_B;
-		ranges.reader_wm_sets[1].min_drain_clk_khz = 300000;
-		ranges.reader_wm_sets[1].max_drain_clk_khz = 654000;
-		ranges.reader_wm_sets[1].min_fill_clk_khz = 933000;
-		ranges.reader_wm_sets[1].max_fill_clk_khz = 933000;
-		ranges.writer_wm_sets[1].wm_inst = WM_B;
-		ranges.writer_wm_sets[1].min_fill_clk_khz = 200000;
-		ranges.writer_wm_sets[1].max_fill_clk_khz = 757000;
-		ranges.writer_wm_sets[1].min_drain_clk_khz = 933000;
-		ranges.writer_wm_sets[1].max_drain_clk_khz = 933000;
-
-
-		ranges.reader_wm_sets[2].wm_inst = WM_C;
-		ranges.reader_wm_sets[2].min_drain_clk_khz = 300000;
-		ranges.reader_wm_sets[2].max_drain_clk_khz = 654000;
-		ranges.reader_wm_sets[2].min_fill_clk_khz = 1067000;
-		ranges.reader_wm_sets[2].max_fill_clk_khz = 1067000;
-		ranges.writer_wm_sets[2].wm_inst = WM_C;
-		ranges.writer_wm_sets[2].min_fill_clk_khz = 200000;
-		ranges.writer_wm_sets[2].max_fill_clk_khz = 757000;
-		ranges.writer_wm_sets[2].min_drain_clk_khz = 1067000;
-		ranges.writer_wm_sets[2].max_drain_clk_khz = 1067000;
-
-		ranges.reader_wm_sets[3].wm_inst = WM_D;
-		ranges.reader_wm_sets[3].min_drain_clk_khz = 300000;
-		ranges.reader_wm_sets[3].max_drain_clk_khz = 654000;
-		ranges.reader_wm_sets[3].min_fill_clk_khz = 1200000;
-		ranges.reader_wm_sets[3].max_fill_clk_khz = 1200000;
-		ranges.writer_wm_sets[3].wm_inst = WM_D;
-		ranges.writer_wm_sets[3].min_fill_clk_khz = 200000;
-		ranges.writer_wm_sets[3].max_fill_clk_khz = 757000;
-		ranges.writer_wm_sets[3].min_drain_clk_khz = 1200000;
-		ranges.writer_wm_sets[3].max_drain_clk_khz = 1200000;
+		ranges.writer_wm_sets[0].max_drain_clk_khz = 5000000;
 	}
 
+	ranges.reader_wm_sets[1] = ranges.writer_wm_sets[0];
+	ranges.reader_wm_sets[1].wm_inst = WM_B;
+
+	ranges.reader_wm_sets[2] = ranges.writer_wm_sets[0];
+	ranges.reader_wm_sets[2].wm_inst = WM_C;
+
+	ranges.reader_wm_sets[3] = ranges.writer_wm_sets[0];
+	ranges.reader_wm_sets[3].wm_inst = WM_D;
+
 	/* Notify PP Lib/SMU which Watermarks to use for which clock ranges */
 	pp->set_wm_ranges(&pp->pp_smu, &ranges);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 644b2187507b..733ac224e7fd 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -169,6 +169,22 @@ failed_alloc:
 	return false;
 }
 
+/**
+ *****************************************************************************
+ *  Function: dc_stream_adjust_vmin_vmax
+ *
+ *  @brief
+ *     Looks up the pipe context of dc_stream_state and updates the
+ *     vertical_total_min and vertical_total_max of the DRR, Dynamic Refresh
+ *     Rate, which is a power-saving feature that targets reducing panel
+ *     refresh rate while the screen is static
+ *
+ *  @param [in] dc: dc reference
+ *  @param [in] stream: Initial dc stream state
+ *  @param [in] adjust: Updated parameters for vertical_total_min and
+ *  vertical_total_max
+ *****************************************************************************
+ */
 bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 		struct dc_stream_state **streams, int num_streams,
 		int vmin, int vmax)
@@ -368,6 +384,71 @@ void dc_stream_set_static_screen_events(struct dc *dc,
 	dc->hwss.set_static_screen_control(pipes_affected, num_pipes_affected, events);
 }
 
+void dc_link_set_drive_settings(struct dc *dc,
+				struct link_training_settings *lt_settings,
+				const struct dc_link *link)
+{
+
+	int i;
+
+	for (i = 0; i < dc->link_count; i++) {
+		if (dc->links[i] == link)
+			break;
+	}
+
+	if (i >= dc->link_count)
+		ASSERT_CRITICAL(false);
+
+	dc_link_dp_set_drive_settings(dc->links[i], lt_settings);
+}
+
+void dc_link_perform_link_training(struct dc *dc,
+				   struct dc_link_settings *link_setting,
+				   bool skip_video_pattern)
+{
+	int i;
+
+	for (i = 0; i < dc->link_count; i++)
+		dc_link_dp_perform_link_training(
+			dc->links[i],
+			link_setting,
+			skip_video_pattern);
+}
+
+void dc_link_set_preferred_link_settings(struct dc *dc,
+					 struct dc_link_settings *link_setting,
+					 struct dc_link *link)
+{
+	link->preferred_link_setting = *link_setting;
+	dp_retrain_link_dp_test(link, link_setting, false);
+}
+
+void dc_link_enable_hpd(const struct dc_link *link)
+{
+	dc_link_dp_enable_hpd(link);
+}
+
+void dc_link_disable_hpd(const struct dc_link *link)
+{
+	dc_link_dp_disable_hpd(link);
+}
+
+
+void dc_link_set_test_pattern(struct dc_link *link,
+			      enum dp_test_pattern test_pattern,
+			      const struct link_training_settings *p_link_settings,
+			      const unsigned char *p_custom_pattern,
+			      unsigned int cust_pattern_size)
+{
+	if (link != NULL)
+		dc_link_dp_set_test_pattern(
+			link,
+			test_pattern,
+			p_link_settings,
+			p_custom_pattern,
+			cust_pattern_size);
+}
+
 static void destruct(struct dc *dc)
 {
 	dc_release_state(dc->current_state);
@@ -386,9 +467,6 @@ static void destruct(struct dc *dc)
 	if (dc->ctx->created_bios)
 		dal_bios_parser_destroy(&dc->ctx->dc_bios);
 
-	if (dc->ctx->logger)
-		dal_logger_destroy(&dc->ctx->logger);
-
 	kfree(dc->ctx);
 	dc->ctx = NULL;
 
@@ -398,7 +476,7 @@ static void destruct(struct dc *dc)
 	kfree(dc->bw_dceip);
 	dc->bw_dceip = NULL;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 	kfree(dc->dcn_soc);
 	dc->dcn_soc = NULL;
 
@@ -411,11 +489,10 @@ static void destruct(struct dc *dc)
 static bool construct(struct dc *dc,
 		const struct dc_init_data *init_params)
 {
-	struct dal_logger *logger;
 	struct dc_context *dc_ctx;
 	struct bw_calcs_dceip *dc_dceip;
 	struct bw_calcs_vbios *dc_vbios;
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 	struct dcn_soc_bounding_box *dcn_soc;
 	struct dcn_ip_params *dcn_ip;
 #endif
@@ -437,7 +514,7 @@ static bool construct(struct dc *dc,
 	}
 
 	dc->bw_vbios = dc_vbios;
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 	dcn_soc = kzalloc(sizeof(*dcn_soc), GFP_KERNEL);
 	if (!dcn_soc) {
 		dm_error("%s: failed to create dcn_soc\n", __func__);
@@ -465,6 +542,7 @@ static bool construct(struct dc *dc,
 	dc_ctx->driver_context = init_params->driver;
 	dc_ctx->dc = dc;
 	dc_ctx->asic_id = init_params->asic_id;
+	dc_ctx->dc_sink_id_count = 0;
 	dc->ctx = dc_ctx;
 
 	dc->current_state = dc_create_state();
@@ -475,14 +553,7 @@ static bool construct(struct dc *dc,
 	}
 
 	/* Create logger */
-	logger = dal_logger_create(dc_ctx, init_params->log_mask);
 
-	if (!logger) {
-		/* can *not* call logger. call base driver 'print error' */
-		dm_error("%s: failed to create Logger!\n", __func__);
-		goto fail;
-	}
-	dc_ctx->logger = logger;
 	dc_ctx->dce_environment = init_params->dce_environment;
 
 	dc_version = resource_parse_asic_id(init_params->asic_id);
@@ -901,9 +972,7 @@ bool dc_commit_state(struct dc *dc, struct dc_state *context)
 	for (i = 0; i < context->stream_count; i++) {
 		struct dc_stream_state *stream = context->streams[i];
 
-		dc_stream_log(stream,
-				dc->ctx->logger,
-				LOG_DC);
+		dc_stream_log(dc, stream);
 	}
 
 	result = dc_commit_state_no_check(dc, context);
@@ -927,12 +996,7 @@ bool dc_post_update_surfaces_to_stream(struct dc *dc)
 
 	dc->optimized_required = false;
 
-	/* 3rd param should be true, temp w/a for RV*/
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
-	dc->hwss.set_bandwidth(dc, context, dc->ctx->dce_version < DCN_VERSION_1_0);
-#else
 	dc->hwss.set_bandwidth(dc, context, true);
-#endif
 	return true;
 }
 
@@ -1548,7 +1612,7 @@ struct dc_sink *dc_link_add_remote_sink(
 	struct dc_sink *dc_sink;
 	enum dc_edid_status edid_status;
 
-	if (len > MAX_EDID_BUFFER_SIZE) {
+	if (len > DC_MAX_EDID_BUFFER_SIZE) {
 		dm_error("Max EDID buffer size breached!\n");
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_debug.c b/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
index 267c76766dea..caece7c13bc6 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
@@ -348,23 +348,23 @@ void context_clock_trace(
 		struct dc *dc,
 		struct dc_state *context)
 {
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	DC_LOGGER_INIT(dc->ctx->logger);
 	CLOCK_TRACE("Current: dispclk_khz:%d  max_dppclk_khz:%d  dcfclk_khz:%d\n"
 			"dcfclk_deep_sleep_khz:%d  fclk_khz:%d  socclk_khz:%d\n",
-			context->bw.dcn.calc_clk.dispclk_khz,
-			context->bw.dcn.calc_clk.dppclk_khz,
-			context->bw.dcn.calc_clk.dcfclk_khz,
-			context->bw.dcn.calc_clk.dcfclk_deep_sleep_khz,
-			context->bw.dcn.calc_clk.fclk_khz,
-			context->bw.dcn.calc_clk.socclk_khz);
+			context->bw.dcn.clk.dispclk_khz,
+			context->bw.dcn.clk.dppclk_khz,
+			context->bw.dcn.clk.dcfclk_khz,
+			context->bw.dcn.clk.dcfclk_deep_sleep_khz,
+			context->bw.dcn.clk.fclk_khz,
+			context->bw.dcn.clk.socclk_khz);
 	CLOCK_TRACE("Calculated: dispclk_khz:%d  max_dppclk_khz:%d  dcfclk_khz:%d\n"
 			"dcfclk_deep_sleep_khz:%d  fclk_khz:%d  socclk_khz:%d\n",
-			context->bw.dcn.calc_clk.dispclk_khz,
-			context->bw.dcn.calc_clk.dppclk_khz,
-			context->bw.dcn.calc_clk.dcfclk_khz,
-			context->bw.dcn.calc_clk.dcfclk_deep_sleep_khz,
-			context->bw.dcn.calc_clk.fclk_khz,
-			context->bw.dcn.calc_clk.socclk_khz);
+			context->bw.dcn.clk.dispclk_khz,
+			context->bw.dcn.clk.dppclk_khz,
+			context->bw.dcn.clk.dcfclk_khz,
+			context->bw.dcn.clk.dcfclk_deep_sleep_khz,
+			context->bw.dcn.clk.fclk_khz,
+			context->bw.dcn.clk.socclk_khz);
 #endif
 }
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 2fa521812d23..a38e7ad36a7e 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -33,6 +33,7 @@
 #include "dc_link_dp.h"
 #include "dc_link_ddc.h"
 #include "link_hwss.h"
+#include "opp.h"
 
 #include "link_encoder.h"
 #include "hw_sequencer.h"
@@ -59,7 +60,14 @@
 
 enum {
 	LINK_RATE_REF_FREQ_IN_MHZ = 27,
-	PEAK_FACTOR_X1000 = 1006
+	PEAK_FACTOR_X1000 = 1006,
+	/*
+	* Some receivers fail to train on first try and are good
+	* on subsequent tries. 2 retries should be plenty. If we
+	* don't have a successful training then we don't expect to
+	* ever get one.
+	*/
+	LINK_TRAINING_MAX_VERIFY_RETRY = 2
 };
 
 /*******************************************************************************
@@ -312,7 +320,7 @@ static enum signal_type get_basic_signal_type(
  * @brief
  * Check whether there is a dongle on DP connector
  */
-static bool is_dp_sink_present(struct dc_link *link)
+bool dc_link_is_dp_sink_present(struct dc_link *link)
 {
 	enum gpio_result gpio_result;
 	uint32_t clock_pin = 0;
@@ -405,7 +413,7 @@ static enum signal_type link_detect_sink(
 			 * we assume signal is DVI; it could be corrected
 			 * to HDMI after dongle detection
 			 */
-			if (!is_dp_sink_present(link))
+			if (!dm_helpers_is_dp_sink_present(link))
 				result = SIGNAL_TYPE_DVI_SINGLE_LINK;
 		}
 	}
@@ -497,6 +505,10 @@ static bool detect_dp(
 			sink_caps->signal = SIGNAL_TYPE_DISPLAY_PORT_MST;
 			link->type = dc_connection_mst_branch;
 
+			dal_ddc_service_set_transaction_type(
+							link->ddc,
+							sink_caps->transaction_type);
+
 			/*
 			 * This call will initiate MST topology discovery. Which
 			 * will detect MST ports and add new DRM connector DRM
@@ -524,6 +536,10 @@ static bool detect_dp(
 			if (reason == DETECT_REASON_BOOT)
 				boot = true;
 
+			dm_helpers_dp_update_branch_info(
+				link->ctx,
+				link);
+
 			if (!dm_helpers_dp_mst_start_top_mgr(
 				link->ctx,
 				link, boot)) {
@@ -728,6 +744,18 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 			break;
 		case EDID_NO_RESPONSE:
 			DC_LOG_ERROR("No EDID read.\n");
+
+			/*
+			 * Abort detection for non-DP connectors if we have
+			 * no EDID
+			 *
+			 * DP needs to report as connected if HDP is high
+			 * even if we have no EDID in order to go to
+			 * fail-safe mode
+			 */
+			if (dc_is_hdmi_signal(link->connector_signal) ||
+			    dc_is_dvi_signal(link->connector_signal))
+				return false;
 		default:
 			break;
 		}
@@ -736,30 +764,41 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 		if ((prev_sink != NULL) && ((edid_status == EDID_THE_SAME) || (edid_status == EDID_OK)))
 			same_edid = is_same_edid(&prev_sink->dc_edid, &sink->dc_edid);
 
-		// If both edid and dpcd are the same, then discard new sink and revert back to original sink
-		if ((same_edid) && (same_dpcd)) {
-			link_disconnect_remap(prev_sink, link);
-			sink = prev_sink;
-			prev_sink = NULL;
-		} else {
-			if (link->connector_signal == SIGNAL_TYPE_DISPLAY_PORT &&
-					sink_caps.transaction_type ==
-						DDC_TRANSACTION_TYPE_I2C_OVER_AUX) {
-				/*
-				 * TODO debug why Dell 2413 doesn't like
-				 *  two link trainings
-				 */
+		if (link->connector_signal == SIGNAL_TYPE_DISPLAY_PORT &&
+			sink_caps.transaction_type == DDC_TRANSACTION_TYPE_I2C_OVER_AUX &&
+			reason != DETECT_REASON_HPDRX) {
+			/*
+			 * TODO debug why Dell 2413 doesn't like
+			 *  two link trainings
+			 */
+
+			/* deal with non-mst cases */
+			for (i = 0; i < LINK_TRAINING_MAX_VERIFY_RETRY; i++) {
+				int fail_count = 0;
+
+				dp_verify_link_cap(link,
+						  &link->reported_link_cap,
+						  &fail_count);
 
-				/* deal with non-mst cases */
-				dp_hbr_verify_link_cap(link, &link->reported_link_cap);
+				if (fail_count == 0)
+					break;
 			}
 
-			/* HDMI-DVI Dongle */
-			if (sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A &&
-					!sink->edid_caps.edid_hdmi)
-				sink->sink_signal = SIGNAL_TYPE_DVI_SINGLE_LINK;
+		} else {
+			// If edid is the same, then discard new sink and revert back to original sink
+			if (same_edid) {
+				link_disconnect_remap(prev_sink, link);
+				sink = prev_sink;
+				prev_sink = NULL;
+
+			}
 		}
 
+		/* HDMI-DVI Dongle */
+		if (sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A &&
+				!sink->edid_caps.edid_hdmi)
+			sink->sink_signal = SIGNAL_TYPE_DVI_SINGLE_LINK;
+
 		/* Connectivity log: detection */
 		for (i = 0; i < sink->dc_edid.length / EDID_BLOCK_SIZE; i++) {
 			CONN_DATA_DETECT(link,
@@ -1000,6 +1039,9 @@ static bool construct(
 
 	link->link_id = bios->funcs->get_connector_id(bios, init_params->connector_index);
 
+	if (dc_ctx->dc_bios->integrated_info)
+		link->dp_ss_off = !!dc_ctx->dc_bios->integrated_info->dp_ss_control;
+
 	if (link->link_id.type != OBJECT_TYPE_CONNECTOR) {
 		dm_error("%s: Invalid Connector ObjectID from Adapter Service for connector index:%d! type %d expected %d\n",
 			 __func__, init_params->connector_index,
@@ -1284,29 +1326,15 @@ static enum dc_status enable_link_dp(
 		max_link_rate = LINK_RATE_HIGH3;
 
 	if (link_settings.link_rate == max_link_rate) {
-		if (state->dis_clk->funcs->set_min_clocks_state) {
-			if (state->dis_clk->cur_min_clks_state < DM_PP_CLOCKS_STATE_NOMINAL)
-				state->dis_clk->funcs->set_min_clocks_state(
-					state->dis_clk, DM_PP_CLOCKS_STATE_NOMINAL);
-		} else {
-			uint32_t dp_phyclk_in_khz;
-			const struct clocks_value clocks_value =
-					state->dis_clk->cur_clocks_value;
-
-			/* 27mhz = 27000000hz= 27000khz */
-			dp_phyclk_in_khz = link_settings.link_rate * 27000;
-
-			if (((clocks_value.max_non_dp_phyclk_in_khz != 0) &&
-				(dp_phyclk_in_khz > clocks_value.max_non_dp_phyclk_in_khz)) ||
-				(dp_phyclk_in_khz > clocks_value.max_dp_phyclk_in_khz)) {
-				state->dis_clk->funcs->apply_clock_voltage_request(
-						state->dis_clk,
-						DM_PP_CLOCK_TYPE_DISPLAYPHYCLK,
-						dp_phyclk_in_khz,
-						false,
-						true);
-			}
-		}
+		struct dc_clocks clocks = state->bw.dcn.clk;
+
+		/* dce/dcn compat, do not update dispclk */
+		clocks.dispclk_khz = 0;
+		/* 27mhz = 27000000hz= 27000khz */
+		clocks.phyclk_khz = link_settings.link_rate * 27000;
+
+		state->dis_clk->funcs->update_clocks(
+				state->dis_clk, &clocks, false);
 	}
 
 	dp_enable_link_phy(
@@ -1861,28 +1889,6 @@ static enum dc_status enable_link(
 		break;
 	}
 
-	if (pipe_ctx->stream_res.audio && status == DC_OK) {
-		struct dc *core_dc = pipe_ctx->stream->ctx->dc;
-		/* notify audio driver for audio modes of monitor */
-		struct pp_smu_funcs_rv *pp_smu = core_dc->res_pool->pp_smu;
-		unsigned int i, num_audio = 1;
-		for (i = 0; i < MAX_PIPES; i++) {
-			/*current_state not updated yet*/
-			if (core_dc->current_state->res_ctx.pipe_ctx[i].stream_res.audio != NULL)
-				num_audio++;
-		}
-
-		pipe_ctx->stream_res.audio->funcs->az_enable(pipe_ctx->stream_res.audio);
-
-		if (num_audio == 1 && pp_smu != NULL && pp_smu->set_pme_wa_enable != NULL)
-			/*this is the first audio. apply the PME w/a in order to wake AZ from D3*/
-			pp_smu->set_pme_wa_enable(&pp_smu->pp_smu);
-		/* un-mute audio */
-		/* TODO: audio should be per stream rather than per link */
-		pipe_ctx->stream_res.stream_enc->funcs->audio_mute_control(
-			pipe_ctx->stream_res.stream_enc, false);
-	}
-
 	return status;
 }
 
@@ -2023,6 +2029,15 @@ enum dc_status dc_link_validate_mode_timing(
 	return DC_OK;
 }
 
+int dc_link_get_backlight_level(const struct dc_link *link)
+{
+	struct abm *abm = link->ctx->dc->res_pool->abm;
+
+	if (abm == NULL || abm->funcs->get_current_backlight_8_bit == NULL)
+		return DC_ERROR_UNEXPECTED;
+
+	return (int) abm->funcs->get_current_backlight_8_bit(abm);
+}
 
 bool dc_link_set_backlight_level(const struct dc_link *link, uint32_t level,
 		uint32_t frame_ramp, const struct dc_stream_state *stream)
@@ -2415,10 +2430,13 @@ void core_link_enable_stream(
 			}
 	}
 
+	core_dc->hwss.enable_audio_stream(pipe_ctx);
+
 	/* turn off otg test pattern if enable */
-	pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
-			CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
-			COLOR_DEPTH_UNDEFINED);
+	if (pipe_ctx->stream_res.tg->funcs->set_test_pattern)
+		pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
+				CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
+				COLOR_DEPTH_UNDEFINED);
 
 	core_dc->hwss.enable_stream(pipe_ctx);
 
@@ -2453,6 +2471,22 @@ void core_link_set_avmute(struct pipe_ctx *pipe_ctx, bool enable)
 	core_dc->hwss.set_avmute(pipe_ctx, enable);
 }
 
+/**
+ *****************************************************************************
+ *  Function: dc_link_enable_hpd_filter
+ *
+ *  @brief
+ *     If enable is true, programs HPD filter on associated HPD line using
+ *     delay_on_disconnect/delay_on_connect values dependent on
+ *     link->connector_signal
+ *
+ *     If enable is false, programs HPD filter on associated HPD line with no
+ *     delays on connect or disconnect
+ *
+ *  @param [in] link: pointer to the dc link
+ *  @param [in] enable: boolean specifying whether to enable hbd
+ *****************************************************************************
+ */
 void dc_link_enable_hpd_filter(struct dc_link *link, bool enable)
 {
 	struct gpio *hpd;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
index 49c2face1e7a..8def0d9fa0ff 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
@@ -33,6 +33,7 @@
 #include "include/vector.h"
 #include "core_types.h"
 #include "dc_link_ddc.h"
+#include "aux_engine.h"
 
 #define AUX_POWER_UP_WA_DELAY 500
 #define I2C_OVER_AUX_DEFER_WA_DELAY 70
@@ -629,79 +630,61 @@ bool dal_ddc_service_query_ddc_data(
 	return ret;
 }
 
-ssize_t dal_ddc_service_read_dpcd_data(
-	struct ddc_service *ddc,
-	bool i2c,
-	enum i2c_mot_mode mot,
-	uint32_t address,
-	uint8_t *data,
-	uint32_t len)
+int dc_link_aux_transfer(struct ddc_service *ddc,
+			     unsigned int address,
+			     uint8_t *reply,
+			     void *buffer,
+			     unsigned int size,
+			     enum aux_transaction_type type,
+			     enum i2caux_transaction_action action)
 {
-	struct aux_payload read_payload = {
-		.i2c_over_aux = i2c,
-		.write = false,
-		.address = address,
-		.length = len,
-		.data = data,
-	};
-	struct aux_command command = {
-		.payloads = &read_payload,
-		.number_of_payloads = 1,
-		.defer_delay = 0,
-		.max_defer_write_retry = 0,
-		.mot = mot
-	};
-
-	if (len > DEFAULT_AUX_MAX_DATA_SIZE) {
-		BREAK_TO_DEBUGGER();
-		return DDC_RESULT_FAILED_INVALID_OPERATION;
-	}
+	struct ddc *ddc_pin = ddc->ddc_pin;
+	struct aux_engine *aux_engine;
+	enum aux_channel_operation_result operation_result;
+	struct aux_request_transaction_data aux_req;
+	struct aux_reply_transaction_data aux_rep;
+	uint8_t returned_bytes = 0;
+	int res = -1;
+	uint32_t status;
 
-	if (dal_i2caux_submit_aux_command(
-		ddc->ctx->i2caux,
-		ddc->ddc_pin,
-		&command)) {
-		return (ssize_t)command.payloads->length;
-	}
+	memset(&aux_req, 0, sizeof(aux_req));
+	memset(&aux_rep, 0, sizeof(aux_rep));
 
-	return DDC_RESULT_FAILED_OPERATION;
-}
+	aux_engine = ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en];
+	aux_engine->funcs->acquire(aux_engine, ddc_pin);
 
-enum ddc_result dal_ddc_service_write_dpcd_data(
-	struct ddc_service *ddc,
-	bool i2c,
-	enum i2c_mot_mode mot,
-	uint32_t address,
-	const uint8_t *data,
-	uint32_t len)
-{
-	struct aux_payload write_payload = {
-		.i2c_over_aux = i2c,
-		.write = true,
-		.address = address,
-		.length = len,
-		.data = (uint8_t *)data,
-	};
-	struct aux_command command = {
-		.payloads = &write_payload,
-		.number_of_payloads = 1,
-		.defer_delay = 0,
-		.max_defer_write_retry = 0,
-		.mot = mot
-	};
-
-	if (len > DEFAULT_AUX_MAX_DATA_SIZE) {
-		BREAK_TO_DEBUGGER();
-		return DDC_RESULT_FAILED_INVALID_OPERATION;
-	}
+	aux_req.type = type;
+	aux_req.action = action;
+
+	aux_req.address = address;
+	aux_req.delay = 0;
+	aux_req.length = size;
+	aux_req.data = buffer;
 
-	if (dal_i2caux_submit_aux_command(
-		ddc->ctx->i2caux,
-		ddc->ddc_pin,
-		&command))
-		return DDC_RESULT_SUCESSFULL;
+	aux_engine->funcs->submit_channel_request(aux_engine, &aux_req);
+	operation_result = aux_engine->funcs->get_channel_status(aux_engine, &returned_bytes);
 
-	return DDC_RESULT_FAILED_OPERATION;
+	switch (operation_result) {
+	case AUX_CHANNEL_OPERATION_SUCCEEDED:
+		res = returned_bytes;
+
+		if (res <= size && res >= 0)
+			res = aux_engine->funcs->read_channel_reply(aux_engine, size,
+								buffer, reply,
+								&status);
+
+		break;
+	case AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON:
+		res = 0;
+		break;
+	case AUX_CHANNEL_OPERATION_FAILED_REASON_UNKNOWN:
+	case AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY:
+	case AUX_CHANNEL_OPERATION_FAILED_TIMEOUT:
+		res = -1;
+		break;
+	}
+	aux_engine->funcs->release_engine(aux_engine);
+	return res;
 }
 
 /*test only function*/
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index bdd121485cbc..a7553b6d59c2 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -3,6 +3,7 @@
 #include "dc.h"
 #include "dc_link_dp.h"
 #include "dm_helpers.h"
+#include "opp.h"
 
 #include "inc/core_types.h"
 #include "link_hwss.h"
@@ -38,7 +39,7 @@ static bool decide_fallback_link_setting(
 		struct dc_link_settings initial_link_settings,
 		struct dc_link_settings *current_link_setting,
 		enum link_training_result training_result);
-static struct dc_link_settings get_common_supported_link_settings (
+static struct dc_link_settings get_common_supported_link_settings(
 		struct dc_link_settings link_setting_a,
 		struct dc_link_settings link_setting_b);
 
@@ -93,8 +94,8 @@ static void dpcd_set_link_settings(
 	uint8_t rate = (uint8_t)
 	(lt_settings->link_settings.link_rate);
 
-	union down_spread_ctrl downspread = {{0}};
-	union lane_count_set lane_count_set = {{0}};
+	union down_spread_ctrl downspread = { {0} };
+	union lane_count_set lane_count_set = { {0} };
 	uint8_t link_set_buffer[2];
 
 	downspread.raw = (uint8_t)
@@ -164,11 +165,11 @@ static void dpcd_set_lt_pattern_and_lane_settings(
 	const struct link_training_settings *lt_settings,
 	enum hw_dp_training_pattern pattern)
 {
-	union dpcd_training_lane dpcd_lane[LANE_COUNT_DP_MAX] = {{{0}}};
+	union dpcd_training_lane dpcd_lane[LANE_COUNT_DP_MAX] = { { {0} } };
 	const uint32_t dpcd_base_lt_offset =
 	DP_TRAINING_PATTERN_SET;
 	uint8_t dpcd_lt_buffer[5] = {0};
-	union dpcd_training_pattern dpcd_pattern = {{0}};
+	union dpcd_training_pattern dpcd_pattern = { {0} };
 	uint32_t lane;
 	uint32_t size_in_bytes;
 	bool edp_workaround = false; /* TODO link_prop.INTERNAL */
@@ -232,7 +233,7 @@ static void dpcd_set_lt_pattern_and_lane_settings(
 			link,
 			DP_TRAINING_PATTERN_SET,
 			&dpcd_pattern.raw,
-			sizeof(dpcd_pattern.raw) );
+			sizeof(dpcd_pattern.raw));
 
 		core_link_write_dpcd(
 			link,
@@ -246,7 +247,7 @@ static void dpcd_set_lt_pattern_and_lane_settings(
 				link,
 				dpcd_base_lt_offset,
 				dpcd_lt_buffer,
-				size_in_bytes + sizeof(dpcd_pattern.raw) );
+				size_in_bytes + sizeof(dpcd_pattern.raw));
 
 	link->cur_lane_setting = lt_settings->lane_settings[0];
 }
@@ -428,8 +429,8 @@ static void get_lane_status_and_drive_settings(
 	struct link_training_settings *req_settings)
 {
 	uint8_t dpcd_buf[6] = {0};
-	union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = {{{0}}};
-	struct link_training_settings request_settings = {{0}};
+	union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = { { {0} } };
+	struct link_training_settings request_settings = { {0} };
 	uint32_t lane;
 
 	memset(req_settings, '\0', sizeof(struct link_training_settings));
@@ -651,7 +652,7 @@ static bool perform_post_lt_adj_req_sequence(
 
 			if (req_drv_setting_changed) {
 				update_drive_settings(
-					lt_settings,req_settings);
+					lt_settings, req_settings);
 
 				dc_link_dp_set_drive_settings(link,
 						lt_settings);
@@ -724,8 +725,8 @@ static enum link_training_result perform_channel_equalization_sequence(
 	enum hw_dp_training_pattern hw_tr_pattern;
 	uint32_t retries_ch_eq;
 	enum dc_lane_count lane_count = lt_settings->link_settings.lane_count;
-	union lane_align_status_updated dpcd_lane_status_updated = {{0}};
-	union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = {{{0}}};
+	union lane_align_status_updated dpcd_lane_status_updated = { {0} };
+	union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = { { {0} } };
 
 	hw_tr_pattern = get_supported_tp(link);
 
@@ -952,7 +953,10 @@ enum link_training_result dc_link_dp_perform_link_training(
 	 * LINK_SPREAD_05_DOWNSPREAD_30KHZ :
 	 * LINK_SPREAD_DISABLED;
 	 */
-	lt_settings.link_settings.link_spread = LINK_SPREAD_05_DOWNSPREAD_30KHZ;
+	if (link->dp_ss_off)
+		lt_settings.link_settings.link_spread = LINK_SPREAD_DISABLED;
+	else
+		lt_settings.link_settings.link_spread = LINK_SPREAD_05_DOWNSPREAD_30KHZ;
 
 	/* 1. set link rate, lane count and spread*/
 	dpcd_set_link_settings(link, &lt_settings);
@@ -1027,6 +1031,9 @@ enum link_training_result dc_link_dp_perform_link_training(
 			lt_settings.lane_settings[0].VOLTAGE_SWING,
 			lt_settings.lane_settings[0].PRE_EMPHASIS);
 
+	if (status != LINK_TRAINING_SUCCESS)
+		link->ctx->dc->debug_data.ltFailCount++;
+
 	return status;
 }
 
@@ -1082,9 +1089,10 @@ static struct dc_link_settings get_max_link_cap(struct dc_link *link)
 	return max_link_cap;
 }
 
-bool dp_hbr_verify_link_cap(
+bool dp_verify_link_cap(
 	struct dc_link *link,
-	struct dc_link_settings *known_limit_link_setting)
+	struct dc_link_settings *known_limit_link_setting,
+	int *fail_count)
 {
 	struct dc_link_settings max_link_cap = {0};
 	struct dc_link_settings cur_link_setting = {0};
@@ -1097,6 +1105,11 @@ bool dp_hbr_verify_link_cap(
 	enum clock_source_id dp_cs_id = CLOCK_SOURCE_ID_EXTERNAL;
 	enum link_training_result status;
 
+	if (link->dc->debug.skip_detection_link_training) {
+		link->verified_link_cap = *known_limit_link_setting;
+		return true;
+	}
+
 	success = false;
 	skip_link_training = false;
 
@@ -1151,6 +1164,8 @@ bool dp_hbr_verify_link_cap(
 							skip_video_pattern);
 			if (status == LINK_TRAINING_SUCCESS)
 				success = true;
+			else
+				(*fail_count)++;
 		}
 
 		if (success)
@@ -1182,7 +1197,7 @@ bool dp_hbr_verify_link_cap(
 	return success;
 }
 
-static struct dc_link_settings get_common_supported_link_settings (
+static struct dc_link_settings get_common_supported_link_settings(
 		struct dc_link_settings link_setting_a,
 		struct dc_link_settings link_setting_b)
 {
@@ -1428,6 +1443,7 @@ static uint32_t bandwidth_in_kbps_from_link_settings(
 
 	uint32_t lane_count  = link_setting->lane_count;
 	uint32_t kbps = link_rate_in_kbps;
+
 	kbps *= lane_count;
 	kbps *= 8;   /* 8 bits per byte*/
 
@@ -1445,9 +1461,9 @@ bool dp_validate_mode_timing(
 	const struct dc_link_settings *link_setting;
 
 	/*always DP fail safe mode*/
-	if (timing->pix_clk_khz == (uint32_t)25175 &&
-		timing->h_addressable == (uint32_t)640 &&
-		timing->v_addressable == (uint32_t)480)
+	if (timing->pix_clk_khz == (uint32_t) 25175 &&
+		timing->h_addressable == (uint32_t) 640 &&
+		timing->v_addressable == (uint32_t) 480)
 		return true;
 
 	/* We always use verified link settings */
@@ -1647,22 +1663,26 @@ static enum dc_status read_hpd_rx_irq_data(
 			irq_data->raw,
 			sizeof(union hpd_irq_data));
 	else {
-		/* Read 2 bytes at this location,... */
+		/* Read 14 bytes in a single read and then copy only the required fields.
+		 * This is more efficient than doing it in two separate AUX reads. */
+
+		uint8_t tmp[DP_SINK_STATUS_ESI - DP_SINK_COUNT_ESI + 1];
+
 		retval = core_link_read_dpcd(
 			link,
 			DP_SINK_COUNT_ESI,
-			irq_data->raw,
-			2);
+			tmp,
+			sizeof(tmp));
 
 		if (retval != DC_OK)
 			return retval;
 
-		/* ... then read remaining 4 at the other location */
-		retval = core_link_read_dpcd(
-			link,
-			DP_LANE0_1_STATUS_ESI,
-			&irq_data->raw[2],
-			4);
+		irq_data->bytes.sink_cnt.raw = tmp[DP_SINK_COUNT_ESI - DP_SINK_COUNT_ESI];
+		irq_data->bytes.device_service_irq.raw = tmp[DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0 - DP_SINK_COUNT_ESI];
+		irq_data->bytes.lane01_status.raw = tmp[DP_LANE0_1_STATUS_ESI - DP_SINK_COUNT_ESI];
+		irq_data->bytes.lane23_status.raw = tmp[DP_LANE2_3_STATUS_ESI - DP_SINK_COUNT_ESI];
+		irq_data->bytes.lane_status_updated.raw = tmp[DP_LANE_ALIGN_STATUS_UPDATED_ESI - DP_SINK_COUNT_ESI];
+		irq_data->bytes.sink_status.raw = tmp[DP_SINK_STATUS_ESI - DP_SINK_COUNT_ESI];
 	}
 
 	return retval;
@@ -1989,12 +2009,16 @@ static void handle_automated_test(struct dc_link *link)
 			sizeof(test_response));
 }
 
-bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd_irq_dpcd_data)
+bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd_irq_dpcd_data, bool *out_link_loss)
 {
-	union hpd_irq_data hpd_irq_dpcd_data = {{{{0}}}};
+	union hpd_irq_data hpd_irq_dpcd_data = { { { {0} } } };
 	union device_service_irq device_service_clear = { { 0 } };
-	enum dc_status result = DDC_RESULT_UNKNOWN;
+	enum dc_status result;
+
 	bool status = false;
+
+	if (out_link_loss)
+		*out_link_loss = false;
 	/* For use cases related to down stream connection status change,
 	 * PSR and device auto test, refer to function handle_sst_hpd_irq
 	 * in DAL2.1*/
@@ -2069,6 +2093,8 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd
 			true, LINK_TRAINING_ATTEMPTS);
 
 		status = false;
+		if (out_link_loss)
+			*out_link_loss = true;
 	}
 
 	if (link->type == dc_connection_active_dongle &&
@@ -2255,6 +2281,11 @@ static void get_active_converter_info(
 
 		link->dpcd_caps.branch_hw_revision =
 			dp_hw_fw_revision.ieee_hw_rev;
+
+		memmove(
+			link->dpcd_caps.branch_fw_revision,
+			dp_hw_fw_revision.ieee_fw_rev,
+			sizeof(dp_hw_fw_revision.ieee_fw_rev));
 	}
 }
 
@@ -2303,12 +2334,14 @@ static bool retrieve_link_cap(struct dc_link *link)
 {
 	uint8_t dpcd_data[DP_ADAPTER_CAP - DP_DPCD_REV + 1];
 
+	struct dp_device_vendor_id sink_id;
 	union down_stream_port_count down_strm_port_count;
 	union edp_configuration_cap edp_config_cap;
 	union dp_downstream_port_present ds_port = { 0 };
 	enum dc_status status = DC_ERROR_UNEXPECTED;
 	uint32_t read_dpcd_retry_cnt = 3;
 	int i;
+	struct dp_sink_hw_fw_revision dp_hw_fw_revision;
 
 	memset(dpcd_data, '\0', sizeof(dpcd_data));
 	memset(&down_strm_port_count,
@@ -2389,6 +2422,36 @@ static bool retrieve_link_cap(struct dc_link *link)
 			&link->dpcd_caps.sink_count.raw,
 			sizeof(link->dpcd_caps.sink_count.raw));
 
+	/* read sink ieee oui */
+	core_link_read_dpcd(link,
+			DP_SINK_OUI,
+			(uint8_t *)(&sink_id),
+			sizeof(sink_id));
+
+	link->dpcd_caps.sink_dev_id =
+			(sink_id.ieee_oui[0] << 16) +
+			(sink_id.ieee_oui[1] << 8) +
+			(sink_id.ieee_oui[2]);
+
+	memmove(
+		link->dpcd_caps.sink_dev_id_str,
+		sink_id.ieee_device_id,
+		sizeof(sink_id.ieee_device_id));
+
+	core_link_read_dpcd(
+		link,
+		DP_SINK_HW_REVISION_START,
+		(uint8_t *)&dp_hw_fw_revision,
+		sizeof(dp_hw_fw_revision));
+
+	link->dpcd_caps.sink_hw_revision =
+		dp_hw_fw_revision.ieee_hw_rev;
+
+	memmove(
+		link->dpcd_caps.sink_fw_revision,
+		dp_hw_fw_revision.ieee_fw_rev,
+		sizeof(dp_hw_fw_revision.ieee_fw_rev));
+
 	/* Connectivity log: detection */
 	CONN_DATA_DETECT(link, dpcd_data, sizeof(dpcd_data), "Rx Caps: ");
 
@@ -2493,8 +2556,8 @@ static void set_crtc_test_pattern(struct dc_link *link,
 		pipe_ctx->stream->bit_depth_params = params;
 		pipe_ctx->stream_res.opp->funcs->
 			opp_program_bit_depth_reduction(pipe_ctx->stream_res.opp, &params);
-
-		pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
+		if (pipe_ctx->stream_res.tg->funcs->set_test_pattern)
+			pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
 				controller_test_pattern, color_depth);
 	}
 	break;
@@ -2506,8 +2569,8 @@ static void set_crtc_test_pattern(struct dc_link *link,
 		pipe_ctx->stream->bit_depth_params = params;
 		pipe_ctx->stream_res.opp->funcs->
 			opp_program_bit_depth_reduction(pipe_ctx->stream_res.opp, &params);
-
-		pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
+		if (pipe_ctx->stream_res.tg->funcs->set_test_pattern)
+			pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
 				CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
 				color_depth);
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 751f3ac9d921..4ca41d6e3bcf 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -41,7 +41,7 @@
 #include "dce100/dce100_resource.h"
 #include "dce110/dce110_resource.h"
 #include "dce112/dce112_resource.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "dcn10/dcn10_resource.h"
 #endif
 #include "dce120/dce120_resource.h"
@@ -85,7 +85,7 @@ enum dce_version resource_parse_asic_id(struct hw_asic_id asic_id)
 	case FAMILY_AI:
 		dc_version = DCE_VERSION_12_0;
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case FAMILY_RV:
 		dc_version = DCN_VERSION_1_0;
 		break;
@@ -136,7 +136,7 @@ struct resource_pool *dc_create_resource_pool(
 			num_virtual_links, dc);
 		break;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 		res_pool = dcn10_create_resource_pool(
 				num_virtual_links, dc);
@@ -330,6 +330,9 @@ bool resource_are_streams_timing_synchronizable(
 				!= stream2->timing.pix_clk_khz)
 		return false;
 
+	if (stream1->clamping.c_depth != stream2->clamping.c_depth)
+		return false;
+
 	if (stream1->phy_pix_clk != stream2->phy_pix_clk
 			&& (!dc_is_dp_signal(stream1->signal)
 			|| !dc_is_dp_signal(stream2->signal)))
@@ -337,6 +340,20 @@ bool resource_are_streams_timing_synchronizable(
 
 	return true;
 }
+static bool is_dp_and_hdmi_sharable(
+		struct dc_stream_state *stream1,
+		struct dc_stream_state *stream2)
+{
+	if (stream1->ctx->dc->caps.disable_dp_clk_share)
+		return false;
+
+	if (stream1->clamping.c_depth != COLOR_DEPTH_888 ||
+	    stream2->clamping.c_depth != COLOR_DEPTH_888)
+	return false;
+
+	return true;
+
+}
 
 static bool is_sharable_clk_src(
 	const struct pipe_ctx *pipe_with_clk_src,
@@ -348,7 +365,10 @@ static bool is_sharable_clk_src(
 	if (pipe_with_clk_src->stream->signal == SIGNAL_TYPE_VIRTUAL)
 		return false;
 
-	if (dc_is_dp_signal(pipe_with_clk_src->stream->signal))
+	if (dc_is_dp_signal(pipe_with_clk_src->stream->signal) ||
+		(dc_is_dp_signal(pipe->stream->signal) &&
+		!is_dp_and_hdmi_sharable(pipe_with_clk_src->stream,
+				     pipe->stream)))
 		return false;
 
 	if (dc_is_hdmi_signal(pipe_with_clk_src->stream->signal)
@@ -522,13 +542,12 @@ static void calculate_viewport(struct pipe_ctx *pipe_ctx)
 	}
 }
 
-static void calculate_recout(struct pipe_ctx *pipe_ctx, struct view *recout_skip)
+static void calculate_recout(struct pipe_ctx *pipe_ctx, struct rect *recout_full)
 {
 	const struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 	const struct dc_stream_state *stream = pipe_ctx->stream;
 	struct rect surf_src = plane_state->src_rect;
 	struct rect surf_clip = plane_state->clip_rect;
-	int recout_full_x, recout_full_y;
 	bool pri_split = pipe_ctx->bottom_pipe &&
 			pipe_ctx->bottom_pipe->plane_state == pipe_ctx->plane_state;
 	bool sec_split = pipe_ctx->top_pipe &&
@@ -597,20 +616,22 @@ static void calculate_recout(struct pipe_ctx *pipe_ctx, struct view *recout_skip
 		}
 	}
 	/* Unclipped recout offset = stream dst offset + ((surf dst offset - stream surf_src offset)
-	 * 				* 1/ stream scaling ratio) - (surf surf_src offset * 1/ full scl
-	 * 				ratio)
+	 *			* 1/ stream scaling ratio) - (surf surf_src offset * 1/ full scl
+	 *			ratio)
 	 */
-	recout_full_x = stream->dst.x + (plane_state->dst_rect.x - stream->src.x)
+	recout_full->x = stream->dst.x + (plane_state->dst_rect.x - stream->src.x)
 					* stream->dst.width / stream->src.width -
 			surf_src.x * plane_state->dst_rect.width / surf_src.width
 					* stream->dst.width / stream->src.width;
-	recout_full_y = stream->dst.y + (plane_state->dst_rect.y - stream->src.y)
+	recout_full->y = stream->dst.y + (plane_state->dst_rect.y - stream->src.y)
 					* stream->dst.height / stream->src.height -
 			surf_src.y * plane_state->dst_rect.height / surf_src.height
 					* stream->dst.height / stream->src.height;
 
-	recout_skip->width = pipe_ctx->plane_res.scl_data.recout.x - recout_full_x;
-	recout_skip->height = pipe_ctx->plane_res.scl_data.recout.y - recout_full_y;
+	recout_full->width = plane_state->dst_rect.width
+					* stream->dst.width / stream->src.width;
+	recout_full->height = plane_state->dst_rect.height
+					* stream->dst.height / stream->src.height;
 }
 
 static void calculate_scaling_ratios(struct pipe_ctx *pipe_ctx)
@@ -662,7 +683,7 @@ static void calculate_scaling_ratios(struct pipe_ctx *pipe_ctx)
 			pipe_ctx->plane_res.scl_data.ratios.vert_c, 19);
 }
 
-static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *recout_skip)
+static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct rect *recout_full)
 {
 	struct scaler_data *data = &pipe_ctx->plane_res.scl_data;
 	struct rect src = pipe_ctx->plane_state->src_rect;
@@ -680,15 +701,14 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *r
 		flip_vert_scan_dir = true;
 	else if (pipe_ctx->plane_state->rotation == ROTATION_ANGLE_270)
 		flip_horz_scan_dir = true;
-	if (pipe_ctx->plane_state->horizontal_mirror)
-		flip_horz_scan_dir = !flip_horz_scan_dir;
 
 	if (pipe_ctx->plane_state->rotation == ROTATION_ANGLE_90 ||
 			pipe_ctx->plane_state->rotation == ROTATION_ANGLE_270) {
 		rect_swap_helper(&src);
 		rect_swap_helper(&data->viewport_c);
 		rect_swap_helper(&data->viewport);
-	}
+	} else if (pipe_ctx->plane_state->horizontal_mirror)
+			flip_horz_scan_dir = !flip_horz_scan_dir;
 
 	/*
 	 * Init calculated according to formula:
@@ -708,127 +728,286 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *r
 	data->inits.v_c = dc_fixpt_truncate(dc_fixpt_add(data->inits.v_c, dc_fixpt_div_int(
 			dc_fixpt_add_int(data->ratios.vert_c, data->taps.v_taps_c + 1), 2)), 19);
 
+	if (!flip_horz_scan_dir) {
+		/* Adjust for viewport end clip-off */
+		if ((data->viewport.x + data->viewport.width) < (src.x + src.width)) {
+			int vp_clip = src.x + src.width - data->viewport.width - data->viewport.x;
+			int int_part = dc_fixpt_floor(
+					dc_fixpt_sub(data->inits.h, data->ratios.horz));
 
+			int_part = int_part > 0 ? int_part : 0;
+			data->viewport.width += int_part < vp_clip ? int_part : vp_clip;
+		}
+		if ((data->viewport_c.x + data->viewport_c.width) < (src.x + src.width) / vpc_div) {
+			int vp_clip = (src.x + src.width) / vpc_div -
+					data->viewport_c.width - data->viewport_c.x;
+			int int_part = dc_fixpt_floor(
+					dc_fixpt_sub(data->inits.h_c, data->ratios.horz_c));
+
+			int_part = int_part > 0 ? int_part : 0;
+			data->viewport_c.width += int_part < vp_clip ? int_part : vp_clip;
+		}
+
+		/* Adjust for non-0 viewport offset */
+		if (data->viewport.x) {
+			int int_part;
+
+			data->inits.h = dc_fixpt_add(data->inits.h, dc_fixpt_mul_int(
+					data->ratios.horz, data->recout.x - recout_full->x));
+			int_part = dc_fixpt_floor(data->inits.h) - data->viewport.x;
+			if (int_part < data->taps.h_taps) {
+				int int_adj = data->viewport.x >= (data->taps.h_taps - int_part) ?
+							(data->taps.h_taps - int_part) : data->viewport.x;
+				data->viewport.x -= int_adj;
+				data->viewport.width += int_adj;
+				int_part += int_adj;
+			} else if (int_part > data->taps.h_taps) {
+				data->viewport.x += int_part - data->taps.h_taps;
+				data->viewport.width -= int_part - data->taps.h_taps;
+				int_part = data->taps.h_taps;
+			}
+			data->inits.h.value &= 0xffffffff;
+			data->inits.h = dc_fixpt_add_int(data->inits.h, int_part);
+		}
 
-	/* Adjust for viewport end clip-off */
-	if ((data->viewport.x + data->viewport.width) < (src.x + src.width) && !flip_horz_scan_dir) {
-		int vp_clip = src.x + src.width - data->viewport.width - data->viewport.x;
-		int int_part = dc_fixpt_floor(
-				dc_fixpt_sub(data->inits.h, data->ratios.horz));
-
-		int_part = int_part > 0 ? int_part : 0;
-		data->viewport.width += int_part < vp_clip ? int_part : vp_clip;
-	}
-	if ((data->viewport.y + data->viewport.height) < (src.y + src.height) && !flip_vert_scan_dir) {
-		int vp_clip = src.y + src.height - data->viewport.height - data->viewport.y;
-		int int_part = dc_fixpt_floor(
-				dc_fixpt_sub(data->inits.v, data->ratios.vert));
-
-		int_part = int_part > 0 ? int_part : 0;
-		data->viewport.height += int_part < vp_clip ? int_part : vp_clip;
-	}
-	if ((data->viewport_c.x + data->viewport_c.width) < (src.x + src.width) / vpc_div && !flip_horz_scan_dir) {
-		int vp_clip = (src.x + src.width) / vpc_div -
-				data->viewport_c.width - data->viewport_c.x;
-		int int_part = dc_fixpt_floor(
-				dc_fixpt_sub(data->inits.h_c, data->ratios.horz_c));
-
-		int_part = int_part > 0 ? int_part : 0;
-		data->viewport_c.width += int_part < vp_clip ? int_part : vp_clip;
-	}
-	if ((data->viewport_c.y + data->viewport_c.height) < (src.y + src.height) / vpc_div && !flip_vert_scan_dir) {
-		int vp_clip = (src.y + src.height) / vpc_div -
-				data->viewport_c.height - data->viewport_c.y;
-		int int_part = dc_fixpt_floor(
-				dc_fixpt_sub(data->inits.v_c, data->ratios.vert_c));
-
-		int_part = int_part > 0 ? int_part : 0;
-		data->viewport_c.height += int_part < vp_clip ? int_part : vp_clip;
-	}
-
-	/* Adjust for non-0 viewport offset */
-	if (data->viewport.x && !flip_horz_scan_dir) {
-		int int_part;
-
-		data->inits.h = dc_fixpt_add(data->inits.h, dc_fixpt_mul_int(
-				data->ratios.horz, recout_skip->width));
-		int_part = dc_fixpt_floor(data->inits.h) - data->viewport.x;
-		if (int_part < data->taps.h_taps) {
-			int int_adj = data->viewport.x >= (data->taps.h_taps - int_part) ?
-						(data->taps.h_taps - int_part) : data->viewport.x;
-			data->viewport.x -= int_adj;
-			data->viewport.width += int_adj;
-			int_part += int_adj;
-		} else if (int_part > data->taps.h_taps) {
-			data->viewport.x += int_part - data->taps.h_taps;
-			data->viewport.width -= int_part - data->taps.h_taps;
-			int_part = data->taps.h_taps;
+		if (data->viewport_c.x) {
+			int int_part;
+
+			data->inits.h_c = dc_fixpt_add(data->inits.h_c, dc_fixpt_mul_int(
+					data->ratios.horz_c, data->recout.x - recout_full->x));
+			int_part = dc_fixpt_floor(data->inits.h_c) - data->viewport_c.x;
+			if (int_part < data->taps.h_taps_c) {
+				int int_adj = data->viewport_c.x >= (data->taps.h_taps_c - int_part) ?
+						(data->taps.h_taps_c - int_part) : data->viewport_c.x;
+				data->viewport_c.x -= int_adj;
+				data->viewport_c.width += int_adj;
+				int_part += int_adj;
+			} else if (int_part > data->taps.h_taps_c) {
+				data->viewport_c.x += int_part - data->taps.h_taps_c;
+				data->viewport_c.width -= int_part - data->taps.h_taps_c;
+				int_part = data->taps.h_taps_c;
+			}
+			data->inits.h_c.value &= 0xffffffff;
+			data->inits.h_c = dc_fixpt_add_int(data->inits.h_c, int_part);
 		}
-		data->inits.h.value &= 0xffffffff;
-		data->inits.h = dc_fixpt_add_int(data->inits.h, int_part);
-	}
-
-	if (data->viewport_c.x && !flip_horz_scan_dir) {
-		int int_part;
-
-		data->inits.h_c = dc_fixpt_add(data->inits.h_c, dc_fixpt_mul_int(
-				data->ratios.horz_c, recout_skip->width));
-		int_part = dc_fixpt_floor(data->inits.h_c) - data->viewport_c.x;
-		if (int_part < data->taps.h_taps_c) {
-			int int_adj = data->viewport_c.x >= (data->taps.h_taps_c - int_part) ?
-					(data->taps.h_taps_c - int_part) : data->viewport_c.x;
-			data->viewport_c.x -= int_adj;
-			data->viewport_c.width += int_adj;
-			int_part += int_adj;
-		} else if (int_part > data->taps.h_taps_c) {
-			data->viewport_c.x += int_part - data->taps.h_taps_c;
-			data->viewport_c.width -= int_part - data->taps.h_taps_c;
-			int_part = data->taps.h_taps_c;
+	} else {
+		/* Adjust for non-0 viewport offset */
+		if (data->viewport.x) {
+			int int_part = dc_fixpt_floor(
+					dc_fixpt_sub(data->inits.h, data->ratios.horz));
+
+			int_part = int_part > 0 ? int_part : 0;
+			data->viewport.width += int_part < data->viewport.x ? int_part : data->viewport.x;
+			data->viewport.x -= int_part < data->viewport.x ? int_part : data->viewport.x;
 		}
-		data->inits.h_c.value &= 0xffffffff;
-		data->inits.h_c = dc_fixpt_add_int(data->inits.h_c, int_part);
-	}
-
-	if (data->viewport.y && !flip_vert_scan_dir) {
-		int int_part;
-
-		data->inits.v = dc_fixpt_add(data->inits.v, dc_fixpt_mul_int(
-				data->ratios.vert, recout_skip->height));
-		int_part = dc_fixpt_floor(data->inits.v) - data->viewport.y;
-		if (int_part < data->taps.v_taps) {
-			int int_adj = data->viewport.y >= (data->taps.v_taps - int_part) ?
-						(data->taps.v_taps - int_part) : data->viewport.y;
-			data->viewport.y -= int_adj;
-			data->viewport.height += int_adj;
-			int_part += int_adj;
-		} else if (int_part > data->taps.v_taps) {
-			data->viewport.y += int_part - data->taps.v_taps;
-			data->viewport.height -= int_part - data->taps.v_taps;
-			int_part = data->taps.v_taps;
+		if (data->viewport_c.x) {
+			int int_part = dc_fixpt_floor(
+					dc_fixpt_sub(data->inits.h_c, data->ratios.horz_c));
+
+			int_part = int_part > 0 ? int_part : 0;
+			data->viewport_c.width += int_part < data->viewport_c.x ? int_part : data->viewport_c.x;
+			data->viewport_c.x -= int_part < data->viewport_c.x ? int_part : data->viewport_c.x;
 		}
-		data->inits.v.value &= 0xffffffff;
-		data->inits.v = dc_fixpt_add_int(data->inits.v, int_part);
-	}
-
-	if (data->viewport_c.y && !flip_vert_scan_dir) {
-		int int_part;
-
-		data->inits.v_c = dc_fixpt_add(data->inits.v_c, dc_fixpt_mul_int(
-				data->ratios.vert_c, recout_skip->height));
-		int_part = dc_fixpt_floor(data->inits.v_c) - data->viewport_c.y;
-		if (int_part < data->taps.v_taps_c) {
-			int int_adj = data->viewport_c.y >= (data->taps.v_taps_c - int_part) ?
-					(data->taps.v_taps_c - int_part) : data->viewport_c.y;
-			data->viewport_c.y -= int_adj;
-			data->viewport_c.height += int_adj;
-			int_part += int_adj;
-		} else if (int_part > data->taps.v_taps_c) {
-			data->viewport_c.y += int_part - data->taps.v_taps_c;
-			data->viewport_c.height -= int_part - data->taps.v_taps_c;
-			int_part = data->taps.v_taps_c;
+
+		/* Adjust for viewport end clip-off */
+		if ((data->viewport.x + data->viewport.width) < (src.x + src.width)) {
+			int int_part;
+			int end_offset = src.x + src.width
+					- data->viewport.x - data->viewport.width;
+
+			/*
+			 * this is init if vp had no offset, keep in mind this is from the
+			 * right side of vp due to scan direction
+			 */
+			data->inits.h = dc_fixpt_add(data->inits.h, dc_fixpt_mul_int(
+					data->ratios.horz, data->recout.x - recout_full->x));
+			/*
+			 * this is the difference between first pixel of viewport available to read
+			 * and init position, takning into account scan direction
+			 */
+			int_part = dc_fixpt_floor(data->inits.h) - end_offset;
+			if (int_part < data->taps.h_taps) {
+				int int_adj = end_offset >= (data->taps.h_taps - int_part) ?
+							(data->taps.h_taps - int_part) : end_offset;
+				data->viewport.width += int_adj;
+				int_part += int_adj;
+			} else if (int_part > data->taps.h_taps) {
+				data->viewport.width += int_part - data->taps.h_taps;
+				int_part = data->taps.h_taps;
+			}
+			data->inits.h.value &= 0xffffffff;
+			data->inits.h = dc_fixpt_add_int(data->inits.h, int_part);
+		}
+
+		if ((data->viewport_c.x + data->viewport_c.width) < (src.x + src.width) / vpc_div) {
+			int int_part;
+			int end_offset = (src.x + src.width) / vpc_div
+					- data->viewport_c.x - data->viewport_c.width;
+
+			/*
+			 * this is init if vp had no offset, keep in mind this is from the
+			 * right side of vp due to scan direction
+			 */
+			data->inits.h_c = dc_fixpt_add(data->inits.h_c, dc_fixpt_mul_int(
+					data->ratios.horz_c, data->recout.x - recout_full->x));
+			/*
+			 * this is the difference between first pixel of viewport available to read
+			 * and init position, takning into account scan direction
+			 */
+			int_part = dc_fixpt_floor(data->inits.h_c) - end_offset;
+			if (int_part < data->taps.h_taps_c) {
+				int int_adj = end_offset >= (data->taps.h_taps_c - int_part) ?
+							(data->taps.h_taps_c - int_part) : end_offset;
+				data->viewport_c.width += int_adj;
+				int_part += int_adj;
+			} else if (int_part > data->taps.h_taps_c) {
+				data->viewport_c.width += int_part - data->taps.h_taps_c;
+				int_part = data->taps.h_taps_c;
+			}
+			data->inits.h_c.value &= 0xffffffff;
+			data->inits.h_c = dc_fixpt_add_int(data->inits.h_c, int_part);
+		}
+
+	}
+	if (!flip_vert_scan_dir) {
+		/* Adjust for viewport end clip-off */
+		if ((data->viewport.y + data->viewport.height) < (src.y + src.height)) {
+			int vp_clip = src.y + src.height - data->viewport.height - data->viewport.y;
+			int int_part = dc_fixpt_floor(
+					dc_fixpt_sub(data->inits.v, data->ratios.vert));
+
+			int_part = int_part > 0 ? int_part : 0;
+			data->viewport.height += int_part < vp_clip ? int_part : vp_clip;
+		}
+		if ((data->viewport_c.y + data->viewport_c.height) < (src.y + src.height) / vpc_div) {
+			int vp_clip = (src.y + src.height) / vpc_div -
+					data->viewport_c.height - data->viewport_c.y;
+			int int_part = dc_fixpt_floor(
+					dc_fixpt_sub(data->inits.v_c, data->ratios.vert_c));
+
+			int_part = int_part > 0 ? int_part : 0;
+			data->viewport_c.height += int_part < vp_clip ? int_part : vp_clip;
+		}
+
+		/* Adjust for non-0 viewport offset */
+		if (data->viewport.y) {
+			int int_part;
+
+			data->inits.v = dc_fixpt_add(data->inits.v, dc_fixpt_mul_int(
+					data->ratios.vert, data->recout.y - recout_full->y));
+			int_part = dc_fixpt_floor(data->inits.v) - data->viewport.y;
+			if (int_part < data->taps.v_taps) {
+				int int_adj = data->viewport.y >= (data->taps.v_taps - int_part) ?
+							(data->taps.v_taps - int_part) : data->viewport.y;
+				data->viewport.y -= int_adj;
+				data->viewport.height += int_adj;
+				int_part += int_adj;
+			} else if (int_part > data->taps.v_taps) {
+				data->viewport.y += int_part - data->taps.v_taps;
+				data->viewport.height -= int_part - data->taps.v_taps;
+				int_part = data->taps.v_taps;
+			}
+			data->inits.v.value &= 0xffffffff;
+			data->inits.v = dc_fixpt_add_int(data->inits.v, int_part);
+		}
+
+		if (data->viewport_c.y) {
+			int int_part;
+
+			data->inits.v_c = dc_fixpt_add(data->inits.v_c, dc_fixpt_mul_int(
+					data->ratios.vert_c, data->recout.y - recout_full->y));
+			int_part = dc_fixpt_floor(data->inits.v_c) - data->viewport_c.y;
+			if (int_part < data->taps.v_taps_c) {
+				int int_adj = data->viewport_c.y >= (data->taps.v_taps_c - int_part) ?
+						(data->taps.v_taps_c - int_part) : data->viewport_c.y;
+				data->viewport_c.y -= int_adj;
+				data->viewport_c.height += int_adj;
+				int_part += int_adj;
+			} else if (int_part > data->taps.v_taps_c) {
+				data->viewport_c.y += int_part - data->taps.v_taps_c;
+				data->viewport_c.height -= int_part - data->taps.v_taps_c;
+				int_part = data->taps.v_taps_c;
+			}
+			data->inits.v_c.value &= 0xffffffff;
+			data->inits.v_c = dc_fixpt_add_int(data->inits.v_c, int_part);
+		}
+	} else {
+		/* Adjust for non-0 viewport offset */
+		if (data->viewport.y) {
+			int int_part = dc_fixpt_floor(
+					dc_fixpt_sub(data->inits.v, data->ratios.vert));
+
+			int_part = int_part > 0 ? int_part : 0;
+			data->viewport.height += int_part < data->viewport.y ? int_part : data->viewport.y;
+			data->viewport.y -= int_part < data->viewport.y ? int_part : data->viewport.y;
+		}
+		if (data->viewport_c.y) {
+			int int_part = dc_fixpt_floor(
+					dc_fixpt_sub(data->inits.v_c, data->ratios.vert_c));
+
+			int_part = int_part > 0 ? int_part : 0;
+			data->viewport_c.height += int_part < data->viewport_c.y ? int_part : data->viewport_c.y;
+			data->viewport_c.y -= int_part < data->viewport_c.y ? int_part : data->viewport_c.y;
+		}
+
+		/* Adjust for viewport end clip-off */
+		if ((data->viewport.y + data->viewport.height) < (src.y + src.height)) {
+			int int_part;
+			int end_offset = src.y + src.height
+					- data->viewport.y - data->viewport.height;
+
+			/*
+			 * this is init if vp had no offset, keep in mind this is from the
+			 * right side of vp due to scan direction
+			 */
+			data->inits.v = dc_fixpt_add(data->inits.v, dc_fixpt_mul_int(
+					data->ratios.vert, data->recout.y - recout_full->y));
+			/*
+			 * this is the difference between first pixel of viewport available to read
+			 * and init position, taking into account scan direction
+			 */
+			int_part = dc_fixpt_floor(data->inits.v) - end_offset;
+			if (int_part < data->taps.v_taps) {
+				int int_adj = end_offset >= (data->taps.v_taps - int_part) ?
+							(data->taps.v_taps - int_part) : end_offset;
+				data->viewport.height += int_adj;
+				int_part += int_adj;
+			} else if (int_part > data->taps.v_taps) {
+				data->viewport.height += int_part - data->taps.v_taps;
+				int_part = data->taps.v_taps;
+			}
+			data->inits.v.value &= 0xffffffff;
+			data->inits.v = dc_fixpt_add_int(data->inits.v, int_part);
+		}
+
+		if ((data->viewport_c.y + data->viewport_c.height) < (src.y + src.height) / vpc_div) {
+			int int_part;
+			int end_offset = (src.y + src.height) / vpc_div
+					- data->viewport_c.y - data->viewport_c.height;
+
+			/*
+			 * this is init if vp had no offset, keep in mind this is from the
+			 * right side of vp due to scan direction
+			 */
+			data->inits.v_c = dc_fixpt_add(data->inits.v_c, dc_fixpt_mul_int(
+					data->ratios.vert_c, data->recout.y - recout_full->y));
+			/*
+			 * this is the difference between first pixel of viewport available to read
+			 * and init position, taking into account scan direction
+			 */
+			int_part = dc_fixpt_floor(data->inits.v_c) - end_offset;
+			if (int_part < data->taps.v_taps_c) {
+				int int_adj = end_offset >= (data->taps.v_taps_c - int_part) ?
+							(data->taps.v_taps_c - int_part) : end_offset;
+				data->viewport_c.height += int_adj;
+				int_part += int_adj;
+			} else if (int_part > data->taps.v_taps_c) {
+				data->viewport_c.height += int_part - data->taps.v_taps_c;
+				int_part = data->taps.v_taps_c;
+			}
+			data->inits.v_c.value &= 0xffffffff;
+			data->inits.v_c = dc_fixpt_add_int(data->inits.v_c, int_part);
 		}
-		data->inits.v_c.value &= 0xffffffff;
-		data->inits.v_c = dc_fixpt_add_int(data->inits.v_c, int_part);
 	}
 
 	/* Interlaced inits based on final vert inits */
@@ -846,7 +1025,7 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 {
 	const struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 	struct dc_crtc_timing *timing = &pipe_ctx->stream->timing;
-	struct view recout_skip = { 0 };
+	struct rect recout_full = { 0 };
 	bool res = false;
 	DC_LOGGER_INIT(pipe_ctx->stream->ctx->logger);
 	/* Important: scaling ratio calculation requires pixel format,
@@ -866,7 +1045,7 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	if (pipe_ctx->plane_res.scl_data.viewport.height < 16 || pipe_ctx->plane_res.scl_data.viewport.width < 16)
 		return false;
 
-	calculate_recout(pipe_ctx, &recout_skip);
+	calculate_recout(pipe_ctx, &recout_full);
 
 	/**
 	 * Setting line buffer pixel depth to 24bpp yields banding
@@ -910,7 +1089,7 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 
 	if (res)
 		/* May need to re-check lb size after this in some obscure scenario */
-		calculate_inits_and_adj_vp(pipe_ctx, &recout_skip);
+		calculate_inits_and_adj_vp(pipe_ctx, &recout_full);
 
 	DC_LOG_SCALER(
 				"%s: Viewport:\nheight:%d width:%d x:%d "
@@ -1054,7 +1233,7 @@ static struct pipe_ctx *acquire_free_pipe_for_stream(
 
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 static int acquire_first_split_pipe(
 		struct resource_context *res_ctx,
 		const struct resource_pool *pool,
@@ -1125,7 +1304,7 @@ bool dc_add_plane_to_context(
 
 	free_pipe = acquire_free_pipe_for_stream(context, pool, stream);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	if (!free_pipe) {
 		int pipe_idx = acquire_first_split_pipe(&context->res_ctx, pool, stream);
 		if (pipe_idx >= 0)
@@ -1546,8 +1725,8 @@ enum dc_status dc_add_stream_to_ctx(
 	struct dc_context *dc_ctx = dc->ctx;
 	enum dc_status res;
 
-	if (new_ctx->stream_count >= dc->res_pool->pipe_count) {
-		DC_ERROR("Max streams reached, can add stream %p !\n", stream);
+	if (new_ctx->stream_count >= dc->res_pool->timing_generator_count) {
+		DC_ERROR("Max streams reached, can't add stream %p !\n", stream);
 		return DC_ERROR_UNEXPECTED;
 	}
 
@@ -1723,7 +1902,7 @@ enum dc_status resource_map_pool_resources(
 	/* acquire new resources */
 	pipe_idx = acquire_first_free_pipe(&context->res_ctx, pool, stream);
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 	if (pipe_idx < 0)
 		pipe_idx = acquire_first_split_pipe(&context->res_ctx, pool, stream);
 #endif
@@ -1789,7 +1968,7 @@ void dc_resource_state_construct(
 		const struct dc *dc,
 		struct dc_state *dst_ctx)
 {
-	dst_ctx->dis_clk = dc->res_pool->display_clock;
+	dst_ctx->dis_clk = dc->res_pool->dccg;
 }
 
 enum dc_status dc_validate_global_state(
@@ -2347,7 +2526,8 @@ static void set_hdr_static_info_packet(
 {
 	/* HDR Static Metadata info packet for HDR10 */
 
-	if (!stream->hdr_static_metadata.valid)
+	if (!stream->hdr_static_metadata.valid ||
+			stream->use_dynamic_meta)
 		return;
 
 	*info_packet = stream->hdr_static_metadata;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_sink.c b/drivers/gpu/drm/amd/display/dc/core/dc_sink.c
index 25fae38409ab..9971b515c3eb 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_sink.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_sink.c
@@ -53,6 +53,10 @@ static bool construct(struct dc_sink *sink, const struct dc_sink_init_data *init
 	sink->dongle_max_pix_clk = init_params->dongle_max_pix_clk;
 	sink->converter_disable_audio = init_params->converter_disable_audio;
 	sink->dc_container_id = NULL;
+	sink->sink_id = init_params->link->ctx->dc_sink_id_count;
+	// increment dc_sink_id_count because we don't want two sinks with same ID
+	// unless they are actually the same
+	init_params->link->ctx->dc_sink_id_count++;
 
 	return true;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index 3732a1de9d6c..fdcc8ab19bf3 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -30,6 +30,8 @@
 #include "ipp.h"
 #include "timing_generator.h"
 
+#define DC_LOGGER dc->ctx->logger
+
 /*******************************************************************************
  * Private functions
  ******************************************************************************/
@@ -212,6 +214,8 @@ bool dc_stream_set_cursor_attributes(
 		}
 
 		core_dc->hwss.set_cursor_attribute(pipe_ctx);
+		if (core_dc->hwss.set_cursor_sdr_white_level)
+			core_dc->hwss.set_cursor_sdr_white_level(pipe_ctx);
 	}
 
 	if (pipe_to_program)
@@ -317,16 +321,10 @@ bool dc_stream_get_scanoutpos(const struct dc_stream_state *stream,
 	return ret;
 }
 
-
-void dc_stream_log(
-	const struct dc_stream_state *stream,
-	struct dal_logger *dm_logger,
-	enum dc_log_type log_type)
+void dc_stream_log(const struct dc *dc, const struct dc_stream_state *stream)
 {
-
-	dm_logger_write(dm_logger,
-			log_type,
-			"core_stream 0x%x: src: %d, %d, %d, %d; dst: %d, %d, %d, %d, colorSpace:%d\n",
+	DC_LOG_DC(
+			"core_stream 0x%p: src: %d, %d, %d, %d; dst: %d, %d, %d, %d, colorSpace:%d\n",
 			stream,
 			stream->src.x,
 			stream->src.y,
@@ -337,21 +335,18 @@ void dc_stream_log(
 			stream->dst.width,
 			stream->dst.height,
 			stream->output_color_space);
-	dm_logger_write(dm_logger,
-			log_type,
+	DC_LOG_DC(
 			"\tpix_clk_khz: %d, h_total: %d, v_total: %d, pixelencoder:%d, displaycolorDepth:%d\n",
 			stream->timing.pix_clk_khz,
 			stream->timing.h_total,
 			stream->timing.v_total,
 			stream->timing.pixel_encoding,
 			stream->timing.display_color_depth);
-	dm_logger_write(dm_logger,
-			log_type,
+	DC_LOG_DC(
 			"\tsink name: %s, serial: %d\n",
 			stream->sink->edid_caps.display_name,
 			stream->sink->edid_caps.serial_number);
-	dm_logger_write(dm_logger,
-			log_type,
+	DC_LOG_DC(
 			"\tlink: %d\n",
 			stream->sink->link->link_index);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
index 68a71adeb12e..8fb3aefd195c 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
@@ -84,6 +84,17 @@ struct dc_plane_state *dc_create_plane_state(struct dc *dc)
 	return plane_state;
 }
 
+/**
+ *****************************************************************************
+ *  Function: dc_plane_get_status
+ *
+ *  @brief
+ *     Looks up the pipe context of plane_state and updates the pending status
+ *     of the pipe context. Then returns plane_state->status
+ *
+ *  @param [in] plane_state: pointer to the plane_state to get the status of
+ *****************************************************************************
+ */
 const struct dc_plane_status *dc_plane_get_status(
 		const struct dc_plane_state *plane_state)
 {
@@ -181,7 +192,7 @@ void dc_transfer_func_release(struct dc_transfer_func *tf)
 	kref_put(&tf->refcount, dc_transfer_func_free);
 }
 
-struct dc_transfer_func *dc_create_transfer_func()
+struct dc_transfer_func *dc_create_transfer_func(void)
 {
 	struct dc_transfer_func *tf = kvzalloc(sizeof(*tf), GFP_KERNEL);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 53c71296f3dd..e2f033d420a0 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -38,7 +38,7 @@
 #include "inc/compressor.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.1.44"
+#define DC_VER "3.1.59"
 
 #define MAX_SURFACES 3
 #define MAX_STREAMS 6
@@ -68,6 +68,7 @@ struct dc_caps {
 	uint32_t max_planes;
 	uint32_t max_downscale_ratio;
 	uint32_t i2c_speed_in_khz;
+	uint32_t dmdata_alloc_size;
 	unsigned int max_cursor_size;
 	unsigned int max_video_width;
 	int linear_pitch_alignment;
@@ -77,6 +78,8 @@ struct dc_caps {
 	bool dual_link_dvi;
 	bool post_blend_color_processing;
 	bool force_dp_tps4_for_cp2520;
+	bool disable_dp_clk_share;
+	bool psp_setup_panel_mode;
 };
 
 struct dc_dcc_surface_param {
@@ -169,6 +172,12 @@ struct dc_config {
 	bool disable_disp_pll_sharing;
 };
 
+enum visual_confirm {
+	VISUAL_CONFIRM_DISABLE = 0,
+	VISUAL_CONFIRM_SURFACE = 1,
+	VISUAL_CONFIRM_HDR = 2,
+};
+
 enum dcc_option {
 	DCC_ENABLE = 0,
 	DCC_DISABLE = 1,
@@ -186,6 +195,10 @@ enum wm_report_mode {
 	WM_REPORT_OVERRIDE = 1,
 };
 
+/*
+ * For any clocks that may differ per pipe
+ * only the max is stored in this structure
+ */
 struct dc_clocks {
 	int dispclk_khz;
 	int max_supported_dppclk_khz;
@@ -194,10 +207,11 @@ struct dc_clocks {
 	int socclk_khz;
 	int dcfclk_deep_sleep_khz;
 	int fclk_khz;
+	int phyclk_khz;
 };
 
-struct dc_debug {
-	bool surface_visual_confirm;
+struct dc_debug_options {
+	enum visual_confirm visual_confirm;
 	bool sanity_checks;
 	bool max_disp_clk;
 	bool surface_trace;
@@ -228,6 +242,7 @@ struct dc_debug {
 	int urgent_latency_ns;
 	int percent_of_ideal_drambw;
 	int dram_clock_change_latency_ns;
+	bool optimized_watermark;
 	int always_scale;
 	bool disable_pplib_clock_request;
 	bool disable_clock_gate;
@@ -243,8 +258,19 @@ struct dc_debug {
 	bool always_use_regamma;
 	bool p010_mpo_support;
 	bool recovery_enabled;
+	bool avoid_vbios_exec_table;
+	bool scl_reset_length10;
+	bool hdmi20_disable;
+	bool skip_detection_link_training;
+};
 
+struct dc_debug_data {
+	uint32_t ltFailCount;
+	uint32_t i2cErrorCount;
+	uint32_t auxErrorCount;
 };
+
+
 struct dc_state;
 struct resource_pool;
 struct dce_hwseq;
@@ -253,8 +279,7 @@ struct dc {
 	struct dc_caps caps;
 	struct dc_cap_funcs cap_funcs;
 	struct dc_config config;
-	struct dc_debug debug;
-
+	struct dc_debug_options debug;
 	struct dc_context *ctx;
 
 	uint8_t link_count;
@@ -269,7 +294,7 @@ struct dc {
 	/* Inputs into BW and WM calculations. */
 	struct bw_calcs_dceip *bw_dceip;
 	struct bw_calcs_vbios *bw_vbios;
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 	struct dcn_soc_bounding_box *dcn_soc;
 	struct dcn_ip_params *dcn_ip;
 	struct display_mode_lib dml;
@@ -289,9 +314,9 @@ struct dc {
 	bool apply_edp_fast_boot_optimization;
 
 	/* FBC compressor */
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 	struct compressor *fbc_compressor;
-#endif
+
+	struct dc_debug_data debug_data;
 };
 
 enum frame_buffer_mode {
@@ -359,6 +384,7 @@ enum dc_transfer_func_type {
 	TF_TYPE_PREDEFINED,
 	TF_TYPE_DISTRIBUTED_POINTS,
 	TF_TYPE_BYPASS,
+	TF_TYPE_HWPWL
 };
 
 struct dc_transfer_func_distributed_points {
@@ -378,16 +404,22 @@ enum dc_transfer_func_predefined {
 	TRANSFER_FUNCTION_PQ,
 	TRANSFER_FUNCTION_LINEAR,
 	TRANSFER_FUNCTION_UNITY,
+	TRANSFER_FUNCTION_HLG,
+	TRANSFER_FUNCTION_HLG12,
+	TRANSFER_FUNCTION_GAMMA22
 };
 
 struct dc_transfer_func {
 	struct kref refcount;
-	struct dc_transfer_func_distributed_points tf_pts;
 	enum dc_transfer_func_type type;
 	enum dc_transfer_func_predefined tf;
 	/* FP16 1.0 reference level in nits, default is 80 nits, only for PQ*/
 	uint32_t sdr_ref_white_level;
 	struct dc_context *ctx;
+	union {
+		struct pwl_params pwl;
+		struct dc_transfer_func_distributed_points tf_pts;
+	};
 };
 
 /*
@@ -617,9 +649,14 @@ struct dpcd_caps {
 	struct dc_dongle_caps dongle_caps;
 
 	uint32_t sink_dev_id;
+	int8_t sink_dev_id_str[6];
+	int8_t sink_hw_revision;
+	int8_t sink_fw_revision[2];
+
 	uint32_t branch_dev_id;
 	int8_t branch_dev_name[6];
 	int8_t branch_hw_revision;
+	int8_t branch_fw_revision[2];
 
 	bool allow_invalid_MSA_timing_param;
 	bool panel_mode_edp;
@@ -662,9 +699,13 @@ struct dc_sink {
 	struct dc_link *link;
 	struct dc_context *ctx;
 
+	uint32_t sink_id;
+
 	/* private to dc_sink.c */
+	// refcount must be the last member in dc_sink, since we want the
+	// sink structure to be logically cloneable up to (but not including)
+	// refcount
 	struct kref refcount;
-
 };
 
 void dc_sink_retain(struct dc_sink *sink);
diff --git a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h
index d9b84ec7954c..90082bab71f0 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h
@@ -198,6 +198,10 @@ struct dc_vbios_funcs {
 	void (*post_init)(struct dc_bios *bios);
 
 	void (*bios_parser_destroy)(struct dc_bios **dcb);
+
+	enum bp_result (*get_board_layout_info)(
+		struct dc_bios *dcb,
+		struct board_layout_info *board_layout_info);
 };
 
 struct bios_registers {
diff --git a/drivers/gpu/drm/amd/display/dc/dc_ddc_types.h b/drivers/gpu/drm/amd/display/dc/dc_ddc_types.h
index e1affeb5cc51..05c8c31d8b31 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_ddc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_ddc_types.h
@@ -25,6 +25,65 @@
 #ifndef DC_DDC_TYPES_H_
 #define DC_DDC_TYPES_H_
 
+enum aux_transaction_type {
+	AUX_TRANSACTION_TYPE_DP,
+	AUX_TRANSACTION_TYPE_I2C
+};
+
+
+enum i2caux_transaction_action {
+	I2CAUX_TRANSACTION_ACTION_I2C_WRITE = 0x00,
+	I2CAUX_TRANSACTION_ACTION_I2C_READ = 0x10,
+	I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST = 0x20,
+
+	I2CAUX_TRANSACTION_ACTION_I2C_WRITE_MOT = 0x40,
+	I2CAUX_TRANSACTION_ACTION_I2C_READ_MOT = 0x50,
+	I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST_MOT = 0x60,
+
+	I2CAUX_TRANSACTION_ACTION_DP_WRITE = 0x80,
+	I2CAUX_TRANSACTION_ACTION_DP_READ = 0x90
+};
+
+enum aux_channel_operation_result {
+	AUX_CHANNEL_OPERATION_SUCCEEDED,
+	AUX_CHANNEL_OPERATION_FAILED_REASON_UNKNOWN,
+	AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY,
+	AUX_CHANNEL_OPERATION_FAILED_TIMEOUT,
+	AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON
+};
+
+
+struct aux_request_transaction_data {
+	enum aux_transaction_type type;
+	enum i2caux_transaction_action action;
+	/* 20-bit AUX channel transaction address */
+	uint32_t address;
+	/* delay, in 100-microsecond units */
+	uint8_t delay;
+	uint32_t length;
+	uint8_t *data;
+};
+
+enum aux_transaction_reply {
+	AUX_TRANSACTION_REPLY_AUX_ACK = 0x00,
+	AUX_TRANSACTION_REPLY_AUX_NACK = 0x01,
+	AUX_TRANSACTION_REPLY_AUX_DEFER = 0x02,
+
+	AUX_TRANSACTION_REPLY_I2C_ACK = 0x00,
+	AUX_TRANSACTION_REPLY_I2C_NACK = 0x10,
+	AUX_TRANSACTION_REPLY_I2C_DEFER = 0x20,
+
+	AUX_TRANSACTION_REPLY_HPD_DISCON = 0x40,
+
+	AUX_TRANSACTION_REPLY_INVALID = 0xFF
+};
+
+struct aux_reply_transaction_data {
+	enum aux_transaction_reply status;
+	uint32_t length;
+	uint8_t *data;
+};
+
 struct i2c_payload {
 	bool write;
 	uint8_t address;
@@ -109,7 +168,7 @@ struct ddc_service {
 
 	uint32_t address;
 	uint32_t edid_buf_len;
-	uint8_t edid_buf[MAX_EDID_BUFFER_SIZE];
+	uint8_t edid_buf[DC_MAX_EDID_BUFFER_SIZE];
 };
 
 #endif /* DC_DDC_TYPES_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
index 90bccd5ccaa2..da93ab43f2d8 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
@@ -430,7 +430,7 @@ union test_request {
 	struct {
 	uint8_t LINK_TRAINING         :1;
 	uint8_t LINK_TEST_PATTRN      :1;
-	uint8_t EDID_REAT             :1;
+	uint8_t EDID_READ             :1;
 	uint8_t PHY_TEST_PATTERN      :1;
 	uint8_t AUDIO_TEST_PATTERN    :1;
 	uint8_t RESERVED              :1;
@@ -443,7 +443,8 @@ union test_response {
 	struct {
 		uint8_t ACK         :1;
 		uint8_t NO_ACK      :1;
-		uint8_t RESERVED    :6;
+		uint8_t EDID_CHECKSUM_WRITE:1;
+		uint8_t RESERVED    :5;
 	} bits;
 	uint8_t raw;
 };
diff --git a/drivers/gpu/drm/amd/display/dc/dc_helper.c b/drivers/gpu/drm/amd/display/dc/dc_helper.c
index bd0fda0ceb91..e68077e65565 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_helper.c
@@ -255,3 +255,54 @@ uint32_t generic_reg_wait(const struct dc_context *ctx,
 
 	return reg_val;
 }
+
+void generic_write_indirect_reg(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index, uint32_t data)
+{
+	dm_write_reg(ctx, addr_index, index);
+	dm_write_reg(ctx, addr_data, data);
+}
+
+uint32_t generic_read_indirect_reg(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index)
+{
+	uint32_t value = 0;
+
+	dm_write_reg(ctx, addr_index, index);
+	value = dm_read_reg(ctx, addr_data);
+
+	return value;
+}
+
+
+uint32_t generic_indirect_reg_update_ex(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index, uint32_t reg_val, int n,
+		uint8_t shift1, uint32_t mask1, uint32_t field_value1,
+		...)
+{
+	uint32_t shift, mask, field_value;
+	int i = 1;
+
+	va_list ap;
+
+	va_start(ap, field_value1);
+
+	reg_val = set_reg_field_value_ex(reg_val, field_value1, mask1, shift1);
+
+	while (i < n) {
+		shift = va_arg(ap, uint32_t);
+		mask = va_arg(ap, uint32_t);
+		field_value = va_arg(ap, uint32_t);
+
+		reg_val = set_reg_field_value_ex(reg_val, field_value, mask, shift);
+		i++;
+	}
+
+	generic_write_indirect_reg(ctx, addr_index, addr_data, index, reg_val);
+	va_end(ap);
+
+	return reg_val;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
index b1f70579d61b..b789cb2b354b 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -192,13 +192,14 @@ enum surface_pixel_format {
 	/*swaped & float*/
 	SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F,
 	/*grow graphics here if necessary */
-
+	SURFACE_PIXEL_FORMAT_VIDEO_AYCrCb8888,
 	SURFACE_PIXEL_FORMAT_VIDEO_BEGIN,
 	SURFACE_PIXEL_FORMAT_VIDEO_420_YCbCr =
 		SURFACE_PIXEL_FORMAT_VIDEO_BEGIN,
 	SURFACE_PIXEL_FORMAT_VIDEO_420_YCrCb,
 	SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCbCr,
 	SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCrCb,
+		SURFACE_PIXEL_FORMAT_SUBSAMPLE_END,
 	SURFACE_PIXEL_FORMAT_INVALID
 
 	/*grow 444 video here if necessary */
@@ -403,9 +404,11 @@ struct dc_cursor_position {
 struct dc_cursor_mi_param {
 	unsigned int pixel_clk_khz;
 	unsigned int ref_clk_khz;
-	unsigned int viewport_x_start;
-	unsigned int viewport_width;
+	struct rect viewport;
 	struct fixed31_32 h_scale_ratio;
+	struct fixed31_32 v_scale_ratio;
+	enum dc_rotation_angle rotation;
+	bool mirror;
 };
 
 /* IPP related types */
@@ -414,6 +417,7 @@ enum {
 	GAMMA_RGB_256_ENTRIES = 256,
 	GAMMA_RGB_FLOAT_1024_ENTRIES = 1024,
 	GAMMA_CS_TFM_1D_ENTRIES = 4096,
+	GAMMA_CUSTOM_ENTRIES = 4096,
 	GAMMA_MAX_ENTRIES = 4096
 };
 
@@ -421,6 +425,7 @@ enum dc_gamma_type {
 	GAMMA_RGB_256 = 1,
 	GAMMA_RGB_FLOAT_1024 = 2,
 	GAMMA_CS_TFM_1D = 3,
+	GAMMA_CUSTOM = 4,
 };
 
 struct dc_csc_transform {
@@ -489,6 +494,7 @@ struct dc_cursor_attributes {
 	uint32_t height;
 
 	enum dc_cursor_color_format color_format;
+	uint32_t sdr_white_level; // for boosting (SDR) cursor in HDR mode
 
 	/* In case we support HW Cursor rotation in the future */
 	enum dc_rotation_angle rotation_angle;
@@ -496,6 +502,11 @@ struct dc_cursor_attributes {
 	union dc_cursor_attribute_flags attribute_flags;
 };
 
+struct dpp_cursor_attributes {
+	int bias;
+	int scale;
+};
+
 /* OPP */
 
 enum dc_color_space {
@@ -567,25 +578,25 @@ struct scaling_taps {
 };
 
 enum dc_timing_standard {
-	TIMING_STANDARD_UNDEFINED,
-	TIMING_STANDARD_DMT,
-	TIMING_STANDARD_GTF,
-	TIMING_STANDARD_CVT,
-	TIMING_STANDARD_CVT_RB,
-	TIMING_STANDARD_CEA770,
-	TIMING_STANDARD_CEA861,
-	TIMING_STANDARD_HDMI,
-	TIMING_STANDARD_TV_NTSC,
-	TIMING_STANDARD_TV_NTSC_J,
-	TIMING_STANDARD_TV_PAL,
-	TIMING_STANDARD_TV_PAL_M,
-	TIMING_STANDARD_TV_PAL_CN,
-	TIMING_STANDARD_TV_SECAM,
-	TIMING_STANDARD_EXPLICIT,
+	DC_TIMING_STANDARD_UNDEFINED,
+	DC_TIMING_STANDARD_DMT,
+	DC_TIMING_STANDARD_GTF,
+	DC_TIMING_STANDARD_CVT,
+	DC_TIMING_STANDARD_CVT_RB,
+	DC_TIMING_STANDARD_CEA770,
+	DC_TIMING_STANDARD_CEA861,
+	DC_TIMING_STANDARD_HDMI,
+	DC_TIMING_STANDARD_TV_NTSC,
+	DC_TIMING_STANDARD_TV_NTSC_J,
+	DC_TIMING_STANDARD_TV_PAL,
+	DC_TIMING_STANDARD_TV_PAL_M,
+	DC_TIMING_STANDARD_TV_PAL_CN,
+	DC_TIMING_STANDARD_TV_SECAM,
+	DC_TIMING_STANDARD_EXPLICIT,
 	/*!< For explicit timings from EDID, VBIOS, etc.*/
-	TIMING_STANDARD_USER_OVERRIDE,
+	DC_TIMING_STANDARD_USER_OVERRIDE,
 	/*!< For mode timing override by user*/
-	TIMING_STANDARD_MAX
+	DC_TIMING_STANDARD_MAX
 };
 
 enum dc_color_depth {
diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h
index 8a716baa1203..d43cefbc43d3 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_link.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_link.h
@@ -73,6 +73,7 @@ struct dc_link {
 	enum dc_irq_source irq_source_hpd;
 	enum dc_irq_source irq_source_hpd_rx;/* aka DP Short Pulse  */
 	bool is_hpd_filter_disabled;
+	bool dp_ss_off;
 
 	/* caps is the same as reported_link_cap. link_traing use
 	 * reported_link_cap. Will clean up.  TODO
@@ -141,6 +142,8 @@ static inline struct dc_link *dc_get_link_at_index(struct dc *dc, uint32_t link_
 bool dc_link_set_backlight_level(const struct dc_link *dc_link, uint32_t level,
 		uint32_t frame_ramp, const struct dc_stream_state *stream);
 
+int dc_link_get_backlight_level(const struct dc_link *dc_link);
+
 bool dc_link_set_abm_disable(const struct dc_link *dc_link);
 
 bool dc_link_set_psr_enable(const struct dc_link *dc_link, bool enable, bool wait);
@@ -172,7 +175,7 @@ bool dc_link_detect(struct dc_link *dc_link, enum dc_detect_reason reason);
  * false - no change in Downstream port status. No further action required
  * from DM. */
 bool dc_link_handle_hpd_rx_irq(struct dc_link *dc_link,
-		union hpd_irq_data *hpd_irq_dpcd_data);
+		union hpd_irq_data *hpd_irq_dpcd_data, bool *out_link_loss);
 
 struct dc_sink_init_data;
 
@@ -210,10 +213,29 @@ bool dc_link_dp_set_test_pattern(
 
 void dc_link_enable_hpd_filter(struct dc_link *link, bool enable);
 
+bool dc_link_is_dp_sink_present(struct dc_link *link);
+
 /*
  * DPCD access interfaces
  */
 
+void dc_link_set_drive_settings(struct dc *dc,
+				struct link_training_settings *lt_settings,
+				const struct dc_link *link);
+void dc_link_perform_link_training(struct dc *dc,
+				   struct dc_link_settings *link_setting,
+				   bool skip_video_pattern);
+void dc_link_set_preferred_link_settings(struct dc *dc,
+					 struct dc_link_settings *link_setting,
+					 struct dc_link *link);
+void dc_link_enable_hpd(const struct dc_link *link);
+void dc_link_disable_hpd(const struct dc_link *link);
+void dc_link_set_test_pattern(struct dc_link *link,
+			enum dp_test_pattern test_pattern,
+			const struct link_training_settings *p_link_settings,
+			const unsigned char *p_custom_pattern,
+			unsigned int cust_pattern_size);
+
 bool dc_submit_i2c(
 		struct dc *dc,
 		uint32_t link_index,
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index d7e6d53bb383..cbfe418006cb 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -59,6 +59,9 @@ struct dc_stream_state {
 	struct freesync_context freesync_ctx;
 
 	struct dc_info_packet hdr_static_metadata;
+	PHYSICAL_ADDRESS_LOC dmdata_address;
+	bool   use_dynamic_meta;
+
 	struct dc_transfer_func *out_transfer_func;
 	struct colorspace_transform gamut_remap_matrix;
 	struct dc_csc_transform csc_color_matrix;
@@ -97,6 +100,7 @@ struct dc_stream_state {
 
 	struct dc_cursor_attributes cursor_attributes;
 	struct dc_cursor_position cursor_position;
+	uint32_t sdr_white_level; // for boosting (SDR) cursor in HDR mode
 
 	/* from stream struct */
 	struct kref refcount;
@@ -144,10 +148,7 @@ void dc_commit_updates_for_stream(struct dc *dc,
 /*
  * Log the current stream state.
  */
-void dc_stream_log(
-	const struct dc_stream_state *stream,
-	struct dal_logger *dc_logger,
-	enum dc_log_type log_type);
+void dc_stream_log(const struct dc *dc, const struct dc_stream_state *stream);
 
 uint8_t dc_get_current_stream_count(struct dc *dc);
 struct dc_stream_state *dc_get_stream_at_index(struct dc *dc, uint8_t i);
@@ -255,6 +256,7 @@ bool dc_stream_set_cursor_position(
 	struct dc_stream_state *stream,
 	const struct dc_cursor_position *position);
 
+
 bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 				struct dc_stream_state **stream,
 				int num_streams,
@@ -299,9 +301,4 @@ bool dc_stream_get_crtc_position(struct dc *dc,
 				 unsigned int *v_pos,
 				 unsigned int *nom_v_pos);
 
-void dc_stream_set_static_screen_events(struct dc *dc,
-					struct dc_stream_state **stream,
-					int num_streams,
-					const struct dc_static_screen_events *events);
-
 #endif /* DC_STREAM_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 76df2534c4a4..8c6eb78b0c3b 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -77,8 +77,6 @@ struct dc_context {
 	struct dc *dc;
 
 	void *driver_context; /* e.g. amdgpu_device */
-
-	struct dal_logger *logger;
 	void *cgs_device;
 
 	enum dce_environment dce_environment;
@@ -92,13 +90,12 @@ struct dc_context {
 	bool created_bios;
 	struct gpio_service *gpio_service;
 	struct i2caux *i2caux;
-#if defined(CONFIG_DRM_AMD_DC_FBC)
+	uint32_t dc_sink_id_count;
 	uint64_t fbc_gpu_addr;
-#endif
 };
 
 
-#define MAX_EDID_BUFFER_SIZE 512
+#define DC_MAX_EDID_BUFFER_SIZE 512
 #define EDID_BLOCK_SIZE 128
 #define MAX_SURFACE_NUM 4
 #define NUM_PIXEL_FORMATS 10
@@ -137,13 +134,13 @@ enum plane_stereo_format {
  */
 
 enum dc_edid_connector_type {
-	EDID_CONNECTOR_UNKNOWN = 0,
-	EDID_CONNECTOR_ANALOG = 1,
-	EDID_CONNECTOR_DIGITAL = 10,
-	EDID_CONNECTOR_DVI = 11,
-	EDID_CONNECTOR_HDMIA = 12,
-	EDID_CONNECTOR_MDDI = 14,
-	EDID_CONNECTOR_DISPLAYPORT = 15
+	DC_EDID_CONNECTOR_UNKNOWN = 0,
+	DC_EDID_CONNECTOR_ANALOG = 1,
+	DC_EDID_CONNECTOR_DIGITAL = 10,
+	DC_EDID_CONNECTOR_DVI = 11,
+	DC_EDID_CONNECTOR_HDMIA = 12,
+	DC_EDID_CONNECTOR_MDDI = 14,
+	DC_EDID_CONNECTOR_DISPLAYPORT = 15
 };
 
 enum dc_edid_status {
@@ -169,7 +166,7 @@ struct dc_cea_audio_mode {
 
 struct dc_edid {
 	uint32_t length;
-	uint8_t raw_edid[MAX_EDID_BUFFER_SIZE];
+	uint8_t raw_edid[DC_MAX_EDID_BUFFER_SIZE];
 };
 
 /* When speaker location data block is not available, DEFAULT_SPEAKER_LOCATION
@@ -195,6 +192,7 @@ union display_content_support {
 
 struct dc_panel_patch {
 	unsigned int dppowerup_delay;
+	unsigned int extra_t12_ms;
 };
 
 struct dc_edid_caps {
diff --git a/drivers/gpu/drm/amd/display/dc/dce/Makefile b/drivers/gpu/drm/amd/display/dc/dce/Makefile
index 11401fd8e535..825537bd4545 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce/Makefile
@@ -28,7 +28,7 @@
 
 DCE = dce_audio.o dce_stream_encoder.o dce_link_encoder.o dce_hwseq.o \
 dce_mem_input.o dce_clock_source.o dce_scl_filters.o dce_transform.o \
-dce_clocks.o dce_opp.o dce_dmcu.o dce_abm.o dce_ipp.o
+dce_clocks.o dce_opp.o dce_dmcu.o dce_abm.o dce_ipp.o dce_aux.o
 
 
 AMD_DAL_DCE = $(addprefix $(AMDDALPATH)/dc/dce/,$(DCE))
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
new file mode 100644
index 000000000000..3f5b2e6f7553
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
@@ -0,0 +1,937 @@
+/*
+ * Copyright 2012-15 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dm_services.h"
+#include "dce_aux.h"
+#include "dce/dce_11_0_sh_mask.h"
+
+#define CTX \
+	aux110->base.ctx
+#define REG(reg_name)\
+	(aux110->regs->reg_name)
+
+#define DC_LOGGER \
+	engine->ctx->logger
+
+#include "reg_helper.h"
+
+#define FROM_AUX_ENGINE(ptr) \
+	container_of((ptr), struct aux_engine_dce110, base)
+
+#define FROM_ENGINE(ptr) \
+	FROM_AUX_ENGINE(container_of((ptr), struct aux_engine, base))
+
+#define FROM_AUX_ENGINE_ENGINE(ptr) \
+	container_of((ptr), struct aux_engine, base)
+enum {
+	AUX_INVALID_REPLY_RETRY_COUNTER = 1,
+	AUX_TIMED_OUT_RETRY_COUNTER = 2,
+	AUX_DEFER_RETRY_COUNTER = 6
+};
+static void release_engine(
+	struct aux_engine *engine)
+{
+	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
+
+	dal_ddc_close(engine->ddc);
+
+	engine->ddc = NULL;
+
+	REG_UPDATE(AUX_ARB_CONTROL, AUX_SW_DONE_USING_AUX_REG, 1);
+}
+
+#define SW_CAN_ACCESS_AUX 1
+#define DMCU_CAN_ACCESS_AUX 2
+
+static bool is_engine_available(
+	struct aux_engine *engine)
+{
+	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
+
+	uint32_t value = REG_READ(AUX_ARB_CONTROL);
+	uint32_t field = get_reg_field_value(
+			value,
+			AUX_ARB_CONTROL,
+			AUX_REG_RW_CNTL_STATUS);
+
+	return (field != DMCU_CAN_ACCESS_AUX);
+}
+static bool acquire_engine(
+	struct aux_engine *engine)
+{
+	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
+
+	uint32_t value = REG_READ(AUX_ARB_CONTROL);
+	uint32_t field = get_reg_field_value(
+			value,
+			AUX_ARB_CONTROL,
+			AUX_REG_RW_CNTL_STATUS);
+	if (field == DMCU_CAN_ACCESS_AUX)
+		return false;
+	/* enable AUX before request SW to access AUX */
+	value = REG_READ(AUX_CONTROL);
+	field = get_reg_field_value(value,
+				AUX_CONTROL,
+				AUX_EN);
+
+	if (field == 0) {
+		set_reg_field_value(
+				value,
+				1,
+				AUX_CONTROL,
+				AUX_EN);
+
+		if (REG(AUX_RESET_MASK)) {
+			/*DP_AUX block as part of the enable sequence*/
+			set_reg_field_value(
+				value,
+				1,
+				AUX_CONTROL,
+				AUX_RESET);
+		}
+
+		REG_WRITE(AUX_CONTROL, value);
+
+		if (REG(AUX_RESET_MASK)) {
+			/*poll HW to make sure reset it done*/
+
+			REG_WAIT(AUX_CONTROL, AUX_RESET_DONE, 1,
+					1, 11);
+
+			set_reg_field_value(
+				value,
+				0,
+				AUX_CONTROL,
+				AUX_RESET);
+
+			REG_WRITE(AUX_CONTROL, value);
+
+			REG_WAIT(AUX_CONTROL, AUX_RESET_DONE, 0,
+					1, 11);
+		}
+	} /*if (field)*/
+
+	/* request SW to access AUX */
+	REG_UPDATE(AUX_ARB_CONTROL, AUX_SW_USE_AUX_REG_REQ, 1);
+
+	value = REG_READ(AUX_ARB_CONTROL);
+	field = get_reg_field_value(
+			value,
+			AUX_ARB_CONTROL,
+			AUX_REG_RW_CNTL_STATUS);
+
+	return (field == SW_CAN_ACCESS_AUX);
+}
+
+#define COMPOSE_AUX_SW_DATA_16_20(command, address) \
+	((command) | ((0xF0000 & (address)) >> 16))
+
+#define COMPOSE_AUX_SW_DATA_8_15(address) \
+	((0xFF00 & (address)) >> 8)
+
+#define COMPOSE_AUX_SW_DATA_0_7(address) \
+	(0xFF & (address))
+
+static void submit_channel_request(
+	struct aux_engine *engine,
+	struct aux_request_transaction_data *request)
+{
+	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
+	uint32_t value;
+	uint32_t length;
+
+	bool is_write =
+		((request->type == AUX_TRANSACTION_TYPE_DP) &&
+		 (request->action == I2CAUX_TRANSACTION_ACTION_DP_WRITE)) ||
+		((request->type == AUX_TRANSACTION_TYPE_I2C) &&
+		((request->action == I2CAUX_TRANSACTION_ACTION_I2C_WRITE) ||
+		 (request->action == I2CAUX_TRANSACTION_ACTION_I2C_WRITE_MOT)));
+	if (REG(AUXN_IMPCAL)) {
+		/* clear_aux_error */
+		REG_UPDATE_SEQ(AUXN_IMPCAL, AUXN_CALOUT_ERROR_AK,
+				1,
+				0);
+
+		REG_UPDATE_SEQ(AUXP_IMPCAL, AUXP_CALOUT_ERROR_AK,
+				1,
+				0);
+
+		/* force_default_calibrate */
+		REG_UPDATE_1BY1_2(AUXN_IMPCAL,
+				AUXN_IMPCAL_ENABLE, 1,
+				AUXN_IMPCAL_OVERRIDE_ENABLE, 0);
+
+		/* bug? why AUXN update EN and OVERRIDE_EN 1 by 1 while AUX P toggles OVERRIDE? */
+
+		REG_UPDATE_SEQ(AUXP_IMPCAL, AUXP_IMPCAL_OVERRIDE_ENABLE,
+				1,
+				0);
+	}
+	/* set the delay and the number of bytes to write */
+
+	/* The length include
+	 * the 4 bit header and the 20 bit address
+	 * (that is 3 byte).
+	 * If the requested length is non zero this means
+	 * an addition byte specifying the length is required.
+	 */
+
+	length = request->length ? 4 : 3;
+	if (is_write)
+		length += request->length;
+
+	REG_UPDATE_2(AUX_SW_CONTROL,
+			AUX_SW_START_DELAY, request->delay,
+			AUX_SW_WR_BYTES, length);
+
+	/* program action and address and payload data (if 'is_write') */
+	value = REG_UPDATE_4(AUX_SW_DATA,
+			AUX_SW_INDEX, 0,
+			AUX_SW_DATA_RW, 0,
+			AUX_SW_AUTOINCREMENT_DISABLE, 1,
+			AUX_SW_DATA, COMPOSE_AUX_SW_DATA_16_20(request->action, request->address));
+
+	value = REG_SET_2(AUX_SW_DATA, value,
+			AUX_SW_AUTOINCREMENT_DISABLE, 0,
+			AUX_SW_DATA, COMPOSE_AUX_SW_DATA_8_15(request->address));
+
+	value = REG_SET(AUX_SW_DATA, value,
+			AUX_SW_DATA, COMPOSE_AUX_SW_DATA_0_7(request->address));
+
+	if (request->length) {
+		value = REG_SET(AUX_SW_DATA, value,
+				AUX_SW_DATA, request->length - 1);
+	}
+
+	if (is_write) {
+		/* Load the HW buffer with the Data to be sent.
+		 * This is relevant for write operation.
+		 * For read, the data recived data will be
+		 * processed in process_channel_reply().
+		 */
+		uint32_t i = 0;
+
+		while (i < request->length) {
+			value = REG_SET(AUX_SW_DATA, value,
+					AUX_SW_DATA, request->data[i]);
+
+			++i;
+		}
+	}
+
+	REG_UPDATE(AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, 1);
+	REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 0,
+				10, aux110->timeout_period/10);
+	REG_UPDATE(AUX_SW_CONTROL, AUX_SW_GO, 1);
+}
+
+static int read_channel_reply(struct aux_engine *engine, uint32_t size,
+			      uint8_t *buffer, uint8_t *reply_result,
+			      uint32_t *sw_status)
+{
+	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
+	uint32_t bytes_replied;
+	uint32_t reply_result_32;
+
+	*sw_status = REG_GET(AUX_SW_STATUS, AUX_SW_REPLY_BYTE_COUNT,
+			     &bytes_replied);
+
+	/* In case HPD is LOW, exit AUX transaction */
+	if ((*sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK))
+		return -1;
+
+	/* Need at least the status byte */
+	if (!bytes_replied)
+		return -1;
+
+	REG_UPDATE_1BY1_3(AUX_SW_DATA,
+			  AUX_SW_INDEX, 0,
+			  AUX_SW_AUTOINCREMENT_DISABLE, 1,
+			  AUX_SW_DATA_RW, 1);
+
+	REG_GET(AUX_SW_DATA, AUX_SW_DATA, &reply_result_32);
+	reply_result_32 = reply_result_32 >> 4;
+	*reply_result = (uint8_t)reply_result_32;
+
+	if (reply_result_32 == 0) { /* ACK */
+		uint32_t i = 0;
+
+		/* First byte was already used to get the command status */
+		--bytes_replied;
+
+		/* Do not overflow buffer */
+		if (bytes_replied > size)
+			return -1;
+
+		while (i < bytes_replied) {
+			uint32_t aux_sw_data_val;
+
+			REG_GET(AUX_SW_DATA, AUX_SW_DATA, &aux_sw_data_val);
+			buffer[i] = aux_sw_data_val;
+			++i;
+		}
+
+		return i;
+	}
+
+	return 0;
+}
+
+static void process_channel_reply(
+	struct aux_engine *engine,
+	struct aux_reply_transaction_data *reply)
+{
+	int bytes_replied;
+	uint8_t reply_result;
+	uint32_t sw_status;
+
+	bytes_replied = read_channel_reply(engine, reply->length, reply->data,
+					   &reply_result, &sw_status);
+
+	/* in case HPD is LOW, exit AUX transaction */
+	if ((sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
+		reply->status = AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON;
+		return;
+	}
+
+	if (bytes_replied < 0) {
+		/* Need to handle an error case...
+		 * Hopefully, upper layer function won't call this function if
+		 * the number of bytes in the reply was 0, because there was
+		 * surely an error that was asserted that should have been
+		 * handled for hot plug case, this could happens
+		 */
+		if (!(sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
+			reply->status = AUX_TRANSACTION_REPLY_INVALID;
+			ASSERT_CRITICAL(false);
+			return;
+		}
+	} else {
+
+		switch (reply_result) {
+		case 0: /* ACK */
+			reply->status = AUX_TRANSACTION_REPLY_AUX_ACK;
+		break;
+		case 1: /* NACK */
+			reply->status = AUX_TRANSACTION_REPLY_AUX_NACK;
+		break;
+		case 2: /* DEFER */
+			reply->status = AUX_TRANSACTION_REPLY_AUX_DEFER;
+		break;
+		case 4: /* AUX ACK / I2C NACK */
+			reply->status = AUX_TRANSACTION_REPLY_I2C_NACK;
+		break;
+		case 8: /* AUX ACK / I2C DEFER */
+			reply->status = AUX_TRANSACTION_REPLY_I2C_DEFER;
+		break;
+		default:
+			reply->status = AUX_TRANSACTION_REPLY_INVALID;
+		}
+	}
+}
+
+static enum aux_channel_operation_result get_channel_status(
+	struct aux_engine *engine,
+	uint8_t *returned_bytes)
+{
+	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
+
+	uint32_t value;
+
+	if (returned_bytes == NULL) {
+		/*caller pass NULL pointer*/
+		ASSERT_CRITICAL(false);
+		return AUX_CHANNEL_OPERATION_FAILED_REASON_UNKNOWN;
+	}
+	*returned_bytes = 0;
+
+	/* poll to make sure that SW_DONE is asserted */
+	value = REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 1,
+				10, aux110->timeout_period/10);
+
+	/* in case HPD is LOW, exit AUX transaction */
+	if ((value & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK))
+		return AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON;
+
+	/* Note that the following bits are set in 'status.bits'
+	 * during CTS 4.2.1.2 (FW 3.3.1):
+	 * AUX_SW_RX_MIN_COUNT_VIOL, AUX_SW_RX_INVALID_STOP,
+	 * AUX_SW_RX_RECV_NO_DET, AUX_SW_RX_RECV_INVALID_H.
+	 *
+	 * AUX_SW_RX_MIN_COUNT_VIOL is an internal,
+	 * HW debugging bit and should be ignored.
+	 */
+	if (value & AUX_SW_STATUS__AUX_SW_DONE_MASK) {
+		if ((value & AUX_SW_STATUS__AUX_SW_RX_TIMEOUT_STATE_MASK) ||
+			(value & AUX_SW_STATUS__AUX_SW_RX_TIMEOUT_MASK))
+			return AUX_CHANNEL_OPERATION_FAILED_TIMEOUT;
+
+		else if ((value & AUX_SW_STATUS__AUX_SW_RX_INVALID_STOP_MASK) ||
+			(value & AUX_SW_STATUS__AUX_SW_RX_RECV_NO_DET_MASK) ||
+			(value &
+				AUX_SW_STATUS__AUX_SW_RX_RECV_INVALID_H_MASK) ||
+			(value & AUX_SW_STATUS__AUX_SW_RX_RECV_INVALID_L_MASK))
+			return AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY;
+
+		*returned_bytes = get_reg_field_value(value,
+				AUX_SW_STATUS,
+				AUX_SW_REPLY_BYTE_COUNT);
+
+		if (*returned_bytes == 0)
+			return
+			AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY;
+		else {
+			*returned_bytes -= 1;
+			return AUX_CHANNEL_OPERATION_SUCCEEDED;
+		}
+	} else {
+		/*time_elapsed >= aux_engine->timeout_period
+		 *  AUX_SW_STATUS__AUX_SW_HPD_DISCON = at this point
+		 */
+		ASSERT_CRITICAL(false);
+		return AUX_CHANNEL_OPERATION_FAILED_TIMEOUT;
+	}
+}
+static void process_read_reply(
+	struct aux_engine *engine,
+	struct read_command_context *ctx)
+{
+	engine->funcs->process_channel_reply(engine, &ctx->reply);
+
+	switch (ctx->reply.status) {
+	case AUX_TRANSACTION_REPLY_AUX_ACK:
+		ctx->defer_retry_aux = 0;
+		if (ctx->returned_byte > ctx->current_read_length) {
+			ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
+			ctx->operation_succeeded = false;
+		} else if (ctx->returned_byte < ctx->current_read_length) {
+			ctx->current_read_length -= ctx->returned_byte;
+
+			ctx->offset += ctx->returned_byte;
+
+			++ctx->invalid_reply_retry_aux_on_ack;
+
+			if (ctx->invalid_reply_retry_aux_on_ack >
+				AUX_INVALID_REPLY_RETRY_COUNTER) {
+				ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
+				ctx->operation_succeeded = false;
+			}
+		} else {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_SUCCEEDED;
+			ctx->transaction_complete = true;
+			ctx->operation_succeeded = true;
+		}
+	break;
+	case AUX_TRANSACTION_REPLY_AUX_NACK:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_NACK;
+		ctx->operation_succeeded = false;
+	break;
+	case AUX_TRANSACTION_REPLY_AUX_DEFER:
+		++ctx->defer_retry_aux;
+
+		if (ctx->defer_retry_aux > AUX_DEFER_RETRY_COUNTER) {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+			ctx->operation_succeeded = false;
+		}
+	break;
+	case AUX_TRANSACTION_REPLY_I2C_DEFER:
+		ctx->defer_retry_aux = 0;
+
+		++ctx->defer_retry_i2c;
+
+		if (ctx->defer_retry_i2c > AUX_DEFER_RETRY_COUNTER) {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+			ctx->operation_succeeded = false;
+		}
+	break;
+	case AUX_TRANSACTION_REPLY_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
+	default:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
+		ctx->operation_succeeded = false;
+	}
+}
+static void process_read_request(
+	struct aux_engine *engine,
+	struct read_command_context *ctx)
+{
+	enum aux_channel_operation_result operation_result;
+
+	engine->funcs->submit_channel_request(engine, &ctx->request);
+
+	operation_result = engine->funcs->get_channel_status(
+		engine, &ctx->returned_byte);
+
+	switch (operation_result) {
+	case AUX_CHANNEL_OPERATION_SUCCEEDED:
+		if (ctx->returned_byte > ctx->current_read_length) {
+			ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
+			ctx->operation_succeeded = false;
+		} else {
+			ctx->timed_out_retry_aux = 0;
+			ctx->invalid_reply_retry_aux = 0;
+
+			ctx->reply.length = ctx->returned_byte;
+			ctx->reply.data = ctx->buffer;
+
+			process_read_reply(engine, ctx);
+		}
+	break;
+	case AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY:
+		++ctx->invalid_reply_retry_aux;
+
+		if (ctx->invalid_reply_retry_aux >
+			AUX_INVALID_REPLY_RETRY_COUNTER) {
+			ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
+			ctx->operation_succeeded = false;
+		} else
+			udelay(400);
+	break;
+	case AUX_CHANNEL_OPERATION_FAILED_TIMEOUT:
+		++ctx->timed_out_retry_aux;
+
+		if (ctx->timed_out_retry_aux > AUX_TIMED_OUT_RETRY_COUNTER) {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+			ctx->operation_succeeded = false;
+		} else {
+			/* DP 1.2a, table 2-58:
+			 * "S3: AUX Request CMD PENDING:
+			 * retry 3 times, with 400usec wait on each"
+			 * The HW timeout is set to 550usec,
+			 * so we should not wait here
+			 */
+		}
+	break;
+	case AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
+	default:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
+		ctx->operation_succeeded = false;
+	}
+}
+static bool read_command(
+	struct aux_engine *engine,
+	struct i2caux_transaction_request *request,
+	bool middle_of_transaction)
+{
+	struct read_command_context ctx;
+
+	ctx.buffer = request->payload.data;
+	ctx.current_read_length = request->payload.length;
+	ctx.offset = 0;
+	ctx.timed_out_retry_aux = 0;
+	ctx.invalid_reply_retry_aux = 0;
+	ctx.defer_retry_aux = 0;
+	ctx.defer_retry_i2c = 0;
+	ctx.invalid_reply_retry_aux_on_ack = 0;
+	ctx.transaction_complete = false;
+	ctx.operation_succeeded = true;
+
+	if (request->payload.address_space ==
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_DPCD) {
+		ctx.request.type = AUX_TRANSACTION_TYPE_DP;
+		ctx.request.action = I2CAUX_TRANSACTION_ACTION_DP_READ;
+		ctx.request.address = request->payload.address;
+	} else if (request->payload.address_space ==
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_I2C) {
+		ctx.request.type = AUX_TRANSACTION_TYPE_I2C;
+		ctx.request.action = middle_of_transaction ?
+			I2CAUX_TRANSACTION_ACTION_I2C_READ_MOT :
+			I2CAUX_TRANSACTION_ACTION_I2C_READ;
+		ctx.request.address = request->payload.address >> 1;
+	} else {
+		/* in DAL2, there was no return in such case */
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+
+	ctx.request.delay = 0;
+
+	do {
+		memset(ctx.buffer + ctx.offset, 0, ctx.current_read_length);
+
+		ctx.request.data = ctx.buffer + ctx.offset;
+		ctx.request.length = ctx.current_read_length;
+
+		process_read_request(engine, &ctx);
+
+		request->status = ctx.status;
+
+		if (ctx.operation_succeeded && !ctx.transaction_complete)
+			if (ctx.request.type == AUX_TRANSACTION_TYPE_I2C)
+				msleep(engine->delay);
+	} while (ctx.operation_succeeded && !ctx.transaction_complete);
+
+	if (request->payload.address_space ==
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_DPCD) {
+		DC_LOG_I2C_AUX("READ: addr:0x%x  value:0x%x Result:%d",
+				request->payload.address,
+				request->payload.data[0],
+				ctx.operation_succeeded);
+	}
+
+	return ctx.operation_succeeded;
+}
+
+static void process_write_reply(
+	struct aux_engine *engine,
+	struct write_command_context *ctx)
+{
+	engine->funcs->process_channel_reply(engine, &ctx->reply);
+
+	switch (ctx->reply.status) {
+	case AUX_TRANSACTION_REPLY_AUX_ACK:
+		ctx->operation_succeeded = true;
+
+		if (ctx->returned_byte) {
+			ctx->request.action = ctx->mot ?
+			I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST_MOT :
+			I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST;
+
+			ctx->current_write_length = 0;
+
+			++ctx->ack_m_retry;
+
+			if (ctx->ack_m_retry > AUX_DEFER_RETRY_COUNTER) {
+				ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+				ctx->operation_succeeded = false;
+			} else
+				udelay(300);
+		} else {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_SUCCEEDED;
+			ctx->defer_retry_aux = 0;
+			ctx->ack_m_retry = 0;
+			ctx->transaction_complete = true;
+		}
+	break;
+	case AUX_TRANSACTION_REPLY_AUX_NACK:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_NACK;
+		ctx->operation_succeeded = false;
+	break;
+	case AUX_TRANSACTION_REPLY_AUX_DEFER:
+		++ctx->defer_retry_aux;
+
+		if (ctx->defer_retry_aux > ctx->max_defer_retry) {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+			ctx->operation_succeeded = false;
+		}
+	break;
+	case AUX_TRANSACTION_REPLY_I2C_DEFER:
+		ctx->defer_retry_aux = 0;
+		ctx->current_write_length = 0;
+
+		ctx->request.action = ctx->mot ?
+			I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST_MOT :
+			I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST;
+
+		++ctx->defer_retry_i2c;
+
+		if (ctx->defer_retry_i2c > ctx->max_defer_retry) {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+			ctx->operation_succeeded = false;
+		}
+	break;
+	case AUX_TRANSACTION_REPLY_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
+	default:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
+		ctx->operation_succeeded = false;
+	}
+}
+static void process_write_request(
+	struct aux_engine *engine,
+	struct write_command_context *ctx)
+{
+	enum aux_channel_operation_result operation_result;
+
+	engine->funcs->submit_channel_request(engine, &ctx->request);
+
+	operation_result = engine->funcs->get_channel_status(
+		engine, &ctx->returned_byte);
+
+	switch (operation_result) {
+	case AUX_CHANNEL_OPERATION_SUCCEEDED:
+		ctx->timed_out_retry_aux = 0;
+		ctx->invalid_reply_retry_aux = 0;
+
+		ctx->reply.length = ctx->returned_byte;
+		ctx->reply.data = ctx->reply_data;
+
+		process_write_reply(engine, ctx);
+	break;
+	case AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY:
+		++ctx->invalid_reply_retry_aux;
+
+		if (ctx->invalid_reply_retry_aux >
+			AUX_INVALID_REPLY_RETRY_COUNTER) {
+			ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
+			ctx->operation_succeeded = false;
+		} else
+			udelay(400);
+	break;
+	case AUX_CHANNEL_OPERATION_FAILED_TIMEOUT:
+		++ctx->timed_out_retry_aux;
+
+		if (ctx->timed_out_retry_aux > AUX_TIMED_OUT_RETRY_COUNTER) {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+			ctx->operation_succeeded = false;
+		} else {
+			/* DP 1.2a, table 2-58:
+			 * "S3: AUX Request CMD PENDING:
+			 * retry 3 times, with 400usec wait on each"
+			 * The HW timeout is set to 550usec,
+			 * so we should not wait here
+			 */
+		}
+	break;
+	case AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
+	default:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
+		ctx->operation_succeeded = false;
+	}
+}
+static bool write_command(
+	struct aux_engine *engine,
+	struct i2caux_transaction_request *request,
+	bool middle_of_transaction)
+{
+	struct write_command_context ctx;
+
+	ctx.mot = middle_of_transaction;
+	ctx.buffer = request->payload.data;
+	ctx.current_write_length = request->payload.length;
+	ctx.timed_out_retry_aux = 0;
+	ctx.invalid_reply_retry_aux = 0;
+	ctx.defer_retry_aux = 0;
+	ctx.defer_retry_i2c = 0;
+	ctx.ack_m_retry = 0;
+	ctx.transaction_complete = false;
+	ctx.operation_succeeded = true;
+
+	if (request->payload.address_space ==
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_DPCD) {
+		ctx.request.type = AUX_TRANSACTION_TYPE_DP;
+		ctx.request.action = I2CAUX_TRANSACTION_ACTION_DP_WRITE;
+		ctx.request.address = request->payload.address;
+	} else if (request->payload.address_space ==
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_I2C) {
+		ctx.request.type = AUX_TRANSACTION_TYPE_I2C;
+		ctx.request.action = middle_of_transaction ?
+			I2CAUX_TRANSACTION_ACTION_I2C_WRITE_MOT :
+			I2CAUX_TRANSACTION_ACTION_I2C_WRITE;
+		ctx.request.address = request->payload.address >> 1;
+	} else {
+		/* in DAL2, there was no return in such case */
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+
+	ctx.request.delay = 0;
+
+	ctx.max_defer_retry =
+		(engine->max_defer_write_retry > AUX_DEFER_RETRY_COUNTER) ?
+			engine->max_defer_write_retry : AUX_DEFER_RETRY_COUNTER;
+
+	do {
+		ctx.request.data = ctx.buffer;
+		ctx.request.length = ctx.current_write_length;
+
+		process_write_request(engine, &ctx);
+
+		request->status = ctx.status;
+
+		if (ctx.operation_succeeded && !ctx.transaction_complete)
+			if (ctx.request.type == AUX_TRANSACTION_TYPE_I2C)
+				msleep(engine->delay);
+	} while (ctx.operation_succeeded && !ctx.transaction_complete);
+
+	if (request->payload.address_space ==
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_DPCD) {
+		DC_LOG_I2C_AUX("WRITE: addr:0x%x  value:0x%x Result:%d",
+				request->payload.address,
+				request->payload.data[0],
+				ctx.operation_succeeded);
+	}
+
+	return ctx.operation_succeeded;
+}
+static bool end_of_transaction_command(
+	struct aux_engine *engine,
+	struct i2caux_transaction_request *request)
+{
+	struct i2caux_transaction_request dummy_request;
+	uint8_t dummy_data;
+
+	/* [tcheng] We only need to send the stop (read with MOT = 0)
+	 * for I2C-over-Aux, not native AUX
+	 */
+
+	if (request->payload.address_space !=
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_I2C)
+		return false;
+
+	dummy_request.operation = request->operation;
+	dummy_request.payload.address_space = request->payload.address_space;
+	dummy_request.payload.address = request->payload.address;
+
+	/*
+	 * Add a dummy byte due to some receiver quirk
+	 * where one byte is sent along with MOT = 0.
+	 * Ideally this should be 0.
+	 */
+
+	dummy_request.payload.length = 0;
+	dummy_request.payload.data = &dummy_data;
+
+	if (request->operation == I2CAUX_TRANSACTION_READ)
+		return read_command(engine, &dummy_request, false);
+	else
+		return write_command(engine, &dummy_request, false);
+
+	/* according Syed, it does not need now DoDummyMOT */
+}
+static bool submit_request(
+	struct aux_engine *engine,
+	struct i2caux_transaction_request *request,
+	bool middle_of_transaction)
+{
+
+	bool result;
+	bool mot_used = true;
+
+	switch (request->operation) {
+	case I2CAUX_TRANSACTION_READ:
+		result = read_command(engine, request, mot_used);
+	break;
+	case I2CAUX_TRANSACTION_WRITE:
+		result = write_command(engine, request, mot_used);
+	break;
+	default:
+		result = false;
+	}
+
+	/* [tcheng]
+	 * need to send stop for the last transaction to free up the AUX
+	 * if the above command fails, this would be the last transaction
+	 */
+
+	if (!middle_of_transaction || !result)
+		end_of_transaction_command(engine, request);
+
+	/* mask AUX interrupt */
+
+	return result;
+}
+enum i2caux_engine_type get_engine_type(
+		const struct aux_engine *engine)
+{
+	return I2CAUX_ENGINE_TYPE_AUX;
+}
+
+static bool acquire(
+	struct aux_engine *engine,
+	struct ddc *ddc)
+{
+
+	enum gpio_result result;
+
+	if (engine->funcs->is_engine_available) {
+		/*check whether SW could use the engine*/
+		if (!engine->funcs->is_engine_available(engine))
+			return false;
+	}
+
+	result = dal_ddc_open(ddc, GPIO_MODE_HARDWARE,
+		GPIO_DDC_CONFIG_TYPE_MODE_AUX);
+
+	if (result != GPIO_RESULT_OK)
+		return false;
+
+	if (!engine->funcs->acquire_engine(engine)) {
+		dal_ddc_close(ddc);
+		return false;
+	}
+
+	engine->ddc = ddc;
+
+	return true;
+}
+
+static const struct aux_engine_funcs aux_engine_funcs = {
+	.acquire_engine = acquire_engine,
+	.submit_channel_request = submit_channel_request,
+	.process_channel_reply = process_channel_reply,
+	.read_channel_reply = read_channel_reply,
+	.get_channel_status = get_channel_status,
+	.is_engine_available = is_engine_available,
+	.release_engine = release_engine,
+	.destroy_engine = dce110_engine_destroy,
+	.submit_request = submit_request,
+	.get_engine_type = get_engine_type,
+	.acquire = acquire,
+};
+
+void dce110_engine_destroy(struct aux_engine **engine)
+{
+
+	struct aux_engine_dce110 *engine110 = FROM_AUX_ENGINE(*engine);
+
+	kfree(engine110);
+	*engine = NULL;
+
+}
+struct aux_engine *dce110_aux_engine_construct(struct aux_engine_dce110 *aux_engine110,
+		struct dc_context *ctx,
+		uint32_t inst,
+		uint32_t timeout_period,
+		const struct dce110_aux_registers *regs)
+{
+	aux_engine110->base.ddc = NULL;
+	aux_engine110->base.ctx = ctx;
+	aux_engine110->base.delay = 0;
+	aux_engine110->base.max_defer_write_retry = 0;
+	aux_engine110->base.funcs = &aux_engine_funcs;
+	aux_engine110->base.inst = inst;
+	aux_engine110->timeout_period = timeout_period;
+	aux_engine110->regs = regs;
+
+	return &aux_engine110->base;
+}
+
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
new file mode 100644
index 000000000000..f7caab85dc80
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
@@ -0,0 +1,111 @@
+/*
+ * Copyright 2012-15 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DAL_AUX_ENGINE_DCE110_H__
+#define __DAL_AUX_ENGINE_DCE110_H__
+#include "aux_engine.h"
+
+#define AUX_COMMON_REG_LIST(id)\
+	SRI(AUX_CONTROL, DP_AUX, id), \
+	SRI(AUX_ARB_CONTROL, DP_AUX, id), \
+	SRI(AUX_SW_DATA, DP_AUX, id), \
+	SRI(AUX_SW_CONTROL, DP_AUX, id), \
+	SRI(AUX_INTERRUPT_CONTROL, DP_AUX, id), \
+	SRI(AUX_SW_STATUS, DP_AUX, id), \
+	SR(AUXN_IMPCAL), \
+	SR(AUXP_IMPCAL)
+
+struct dce110_aux_registers {
+	uint32_t AUX_CONTROL;
+	uint32_t AUX_ARB_CONTROL;
+	uint32_t AUX_SW_DATA;
+	uint32_t AUX_SW_CONTROL;
+	uint32_t AUX_INTERRUPT_CONTROL;
+	uint32_t AUX_SW_STATUS;
+	uint32_t AUXN_IMPCAL;
+	uint32_t AUXP_IMPCAL;
+
+	uint32_t AUX_RESET_MASK;
+};
+
+enum {	/* This is the timeout as defined in DP 1.2a,
+	 * 2.3.4 "Detailed uPacket TX AUX CH State Description".
+	 */
+	AUX_TIMEOUT_PERIOD = 400,
+
+	/* Ideally, the SW timeout should be just above 550usec
+	 * which is programmed in HW.
+	 * But the SW timeout of 600usec is not reliable,
+	 * because on some systems, delay_in_microseconds()
+	 * returns faster than it should.
+	 * EPR #379763: by trial-and-error on different systems,
+	 * 700usec is the minimum reliable SW timeout for polling
+	 * the AUX_SW_STATUS.AUX_SW_DONE bit.
+	 * This timeout expires *only* when there is
+	 * AUX Error or AUX Timeout conditions - not during normal operation.
+	 * During normal operation, AUX_SW_STATUS.AUX_SW_DONE bit is set
+	 * at most within ~240usec. That means,
+	 * increasing this timeout will not affect normal operation,
+	 * and we'll timeout after
+	 * SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD = 1600usec.
+	 * This timeout is especially important for
+	 * resume from S3 and CTS.
+	 */
+	SW_AUX_TIMEOUT_PERIOD_MULTIPLIER = 4
+};
+struct aux_engine_dce110 {
+	struct aux_engine base;
+	const struct dce110_aux_registers *regs;
+	struct {
+		uint32_t aux_control;
+		uint32_t aux_arb_control;
+		uint32_t aux_sw_data;
+		uint32_t aux_sw_control;
+		uint32_t aux_interrupt_control;
+		uint32_t aux_sw_status;
+	} addr;
+	uint32_t timeout_period;
+};
+
+struct aux_engine_dce110_init_data {
+	uint32_t engine_id;
+	uint32_t timeout_period;
+	struct dc_context *ctx;
+	const struct dce110_aux_registers *regs;
+};
+
+struct aux_engine *dce110_aux_engine_construct(
+		struct aux_engine_dce110 *aux_engine110,
+		struct dc_context *ctx,
+		uint32_t inst,
+		uint32_t timeout_period,
+		const struct dce110_aux_registers *regs);
+
+void dce110_engine_destroy(struct aux_engine **engine);
+
+bool dce110_aux_engine_acquire(
+	struct aux_engine *aux_engine,
+	struct ddc *ddc);
+#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
index 88b09dd758ba..439dcf3b596c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
@@ -133,7 +133,7 @@ static bool calculate_fb_and_fractional_fb_divider(
 	uint64_t feedback_divider;
 
 	feedback_divider =
-		(uint64_t)(target_pix_clk_khz * ref_divider * post_divider);
+		(uint64_t)target_pix_clk_khz * ref_divider * post_divider;
 	feedback_divider *= 10;
 	/* additional factor, since we divide by 10 afterwards */
 	feedback_divider *= (uint64_t)(calc_pll_cs->fract_fb_divider_factor);
@@ -145,8 +145,8 @@ static bool calculate_fb_and_fractional_fb_divider(
  * of fractional feedback decimal point and the fractional FB Divider precision
  * is 2 then the equation becomes (ullfeedbackDivider + 5*100) / (10*100))*/
 
-	feedback_divider += (uint64_t)
-			(5 * calc_pll_cs->fract_fb_divider_precision_factor);
+	feedback_divider += 5ULL *
+			    calc_pll_cs->fract_fb_divider_precision_factor;
 	feedback_divider =
 		div_u64(feedback_divider,
 			calc_pll_cs->fract_fb_divider_precision_factor * 10);
@@ -203,8 +203,8 @@ static bool calc_fb_divider_checking_tolerance(
 			&fract_feedback_divider);
 
 	/*Actual calculated value*/
-	actual_calc_clk_khz = (uint64_t)(feedback_divider *
-					calc_pll_cs->fract_fb_divider_factor) +
+	actual_calc_clk_khz = (uint64_t)feedback_divider *
+					calc_pll_cs->fract_fb_divider_factor +
 							fract_feedback_divider;
 	actual_calc_clk_khz *= calc_pll_cs->ref_freq_khz;
 	actual_calc_clk_khz =
@@ -592,7 +592,7 @@ static uint32_t dce110_get_pix_clk_dividers(
 	case DCE_VERSION_11_2:
 	case DCE_VERSION_11_22:
 	case DCE_VERSION_12_0:
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 #endif
 
@@ -909,7 +909,7 @@ static bool dce110_program_pix_clk(
 	struct dce110_clk_src *clk_src = TO_DCE110_CLK_SRC(clock_source);
 	struct bp_pixel_clock_parameters bp_pc_params = {0};
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	if (IS_FPGA_MAXIMUS_DC(clock_source->ctx->dce_environment)) {
 		unsigned int inst = pix_clk_params->controller_id - CONTROLLER_ID_D0;
 		unsigned dp_dto_ref_kHz = 700000;
@@ -982,7 +982,7 @@ static bool dce110_program_pix_clk(
 	case DCE_VERSION_11_2:
 	case DCE_VERSION_11_22:
 	case DCE_VERSION_12_0:
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h
index c45e2f76189e..801bb65707b3 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h
@@ -55,7 +55,7 @@
 	CS_SF(PHYPLLA_PIXCLK_RESYNC_CNTL, PHYPLLA_DCCG_DEEP_COLOR_CNTL, mask_sh),\
 	CS_SF(PHYPLLA_PIXCLK_RESYNC_CNTL, PHYPLLA_PIXCLK_DOUBLE_RATE_ENABLE, mask_sh)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 
 #define CS_COMMON_REG_LIST_DCN1_0(index, pllid) \
 		SRI(PIXCLK_RESYNC_CNTL, PHYPLL, pllid),\
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index 8a581c67bf2d..684da3db7568 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -30,7 +30,7 @@
 #include "bios_parser_interface.h"
 #include "dc.h"
 #include "dmcu.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "dcn_calcs.h"
 #endif
 #include "core_types.h"
@@ -38,7 +38,7 @@
 #include "dal_asic_id.h"
 
 #define TO_DCE_CLOCKS(clocks)\
-	container_of(clocks, struct dce_disp_clk, base)
+	container_of(clocks, struct dce_dccg, base)
 
 #define REG(reg) \
 	(clk_dce->regs->reg)
@@ -101,99 +101,78 @@ static const struct state_dependent_clocks dce120_max_clks_by_state[] = {
 /*ClocksStatePerformance*/
 { .display_clk_khz = 1133000, .pixel_clk_khz = 600000 } };
 
-/* Starting point for each divider range.*/
-enum dce_divider_range_start {
-	DIVIDER_RANGE_01_START = 200, /* 2.00*/
-	DIVIDER_RANGE_02_START = 1600, /* 16.00*/
-	DIVIDER_RANGE_03_START = 3200, /* 32.00*/
-	DIVIDER_RANGE_SCALE_FACTOR = 100 /* Results are scaled up by 100.*/
+/* Starting DID for each range */
+enum dentist_base_divider_id {
+	DENTIST_BASE_DID_1 = 0x08,
+	DENTIST_BASE_DID_2 = 0x40,
+	DENTIST_BASE_DID_3 = 0x60,
+	DENTIST_MAX_DID    = 0x80
 };
 
-/* Ranges for divider identifiers (Divider ID or DID)
- mmDENTIST_DISPCLK_CNTL.DENTIST_DISPCLK_WDIVIDER*/
-enum dce_divider_id_register_setting {
-	DIVIDER_RANGE_01_BASE_DIVIDER_ID = 0X08,
-	DIVIDER_RANGE_02_BASE_DIVIDER_ID = 0X40,
-	DIVIDER_RANGE_03_BASE_DIVIDER_ID = 0X60,
-	DIVIDER_RANGE_MAX_DIVIDER_ID = 0X80
+/* Starting point and step size for each divider range.*/
+enum dentist_divider_range {
+	DENTIST_DIVIDER_RANGE_1_START = 8,   /* 2.00  */
+	DENTIST_DIVIDER_RANGE_1_STEP  = 1,   /* 0.25  */
+	DENTIST_DIVIDER_RANGE_2_START = 64,  /* 16.00 */
+	DENTIST_DIVIDER_RANGE_2_STEP  = 2,   /* 0.50  */
+	DENTIST_DIVIDER_RANGE_3_START = 128, /* 32.00 */
+	DENTIST_DIVIDER_RANGE_3_STEP  = 4,   /* 1.00  */
+	DENTIST_DIVIDER_RANGE_SCALE_FACTOR = 4
 };
 
-/* Step size between each divider within a range.
- Incrementing the DENTIST_DISPCLK_WDIVIDER by one
- will increment the divider by this much.*/
-enum dce_divider_range_step_size {
-	DIVIDER_RANGE_01_STEP_SIZE = 25, /* 0.25*/
-	DIVIDER_RANGE_02_STEP_SIZE = 50, /* 0.50*/
-	DIVIDER_RANGE_03_STEP_SIZE = 100 /* 1.00 */
-};
-
-static bool dce_divider_range_construct(
-	struct dce_divider_range *div_range,
-	int range_start,
-	int range_step,
-	int did_min,
-	int did_max)
+static int dentist_get_divider_from_did(int did)
 {
-	div_range->div_range_start = range_start;
-	div_range->div_range_step = range_step;
-	div_range->did_min = did_min;
-	div_range->did_max = did_max;
-
-	if (div_range->div_range_step == 0) {
-		div_range->div_range_step = 1;
-		/*div_range_step cannot be zero*/
-		BREAK_TO_DEBUGGER();
+	if (did < DENTIST_BASE_DID_1)
+		did = DENTIST_BASE_DID_1;
+	if (did > DENTIST_MAX_DID)
+		did = DENTIST_MAX_DID;
+
+	if (did < DENTIST_BASE_DID_2) {
+		return DENTIST_DIVIDER_RANGE_1_START + DENTIST_DIVIDER_RANGE_1_STEP
+							* (did - DENTIST_BASE_DID_1);
+	} else if (did < DENTIST_BASE_DID_3) {
+		return DENTIST_DIVIDER_RANGE_2_START + DENTIST_DIVIDER_RANGE_2_STEP
+							* (did - DENTIST_BASE_DID_2);
+	} else {
+		return DENTIST_DIVIDER_RANGE_3_START + DENTIST_DIVIDER_RANGE_3_STEP
+							* (did - DENTIST_BASE_DID_3);
 	}
-	/* Calculate this based on the other inputs.*/
-	/* See DividerRange.h for explanation of */
-	/* the relationship between divider id (DID) and a divider.*/
-	/* Number of Divider IDs = (Maximum Divider ID - Minimum Divider ID)*/
-	/* Maximum divider identified in this range =
-	 * (Number of Divider IDs)*Step size between dividers
-	 *  + The start of this range.*/
-	div_range->div_range_end = (did_max - did_min) * range_step
-		+ range_start;
-	return true;
-}
-
-static int dce_divider_range_calc_divider(
-	struct dce_divider_range *div_range,
-	int did)
-{
-	/* Is this DID within our range?*/
-	if ((did < div_range->did_min) || (did >= div_range->did_max))
-		return INVALID_DIVIDER;
-
-	return ((did - div_range->did_min) * div_range->div_range_step)
-			+ div_range->div_range_start;
-
 }
 
-static int dce_divider_range_get_divider(
-	struct dce_divider_range *div_range,
-	int ranges_num,
-	int did)
+/* SW will adjust DP REF Clock average value for all purposes
+ * (DP DTO / DP Audio DTO and DP GTC)
+ if clock is spread for all cases:
+ -if SS enabled on DP Ref clock and HW de-spreading enabled with SW
+ calculations for DS_INCR/DS_MODULO (this is planned to be default case)
+ -if SS enabled on DP Ref clock and HW de-spreading enabled with HW
+ calculations (not planned to be used, but average clock should still
+ be valid)
+ -if SS enabled on DP Ref clock and HW de-spreading disabled
+ (should not be case with CIK) then SW should program all rates
+ generated according to average value (case as with previous ASICs)
+  */
+static int dccg_adjust_dp_ref_freq_for_ss(struct dce_dccg *clk_dce, int dp_ref_clk_khz)
 {
-	int div = INVALID_DIVIDER;
-	int i;
+	if (clk_dce->ss_on_dprefclk && clk_dce->dprefclk_ss_divider != 0) {
+		struct fixed31_32 ss_percentage = dc_fixpt_div_int(
+				dc_fixpt_from_fraction(clk_dce->dprefclk_ss_percentage,
+							clk_dce->dprefclk_ss_divider), 200);
+		struct fixed31_32 adj_dp_ref_clk_khz;
 
-	for (i = 0; i < ranges_num; i++) {
-		/* Calculate divider with given divider ID*/
-		div = dce_divider_range_calc_divider(&div_range[i], did);
-		/* Found a valid return divider*/
-		if (div != INVALID_DIVIDER)
-			break;
+		ss_percentage = dc_fixpt_sub(dc_fixpt_one, ss_percentage);
+		adj_dp_ref_clk_khz = dc_fixpt_mul_int(ss_percentage, dp_ref_clk_khz);
+		dp_ref_clk_khz = dc_fixpt_floor(adj_dp_ref_clk_khz);
 	}
-	return div;
+	return dp_ref_clk_khz;
 }
 
-static int dce_clocks_get_dp_ref_freq(struct display_clock *clk)
+static int dce_get_dp_ref_freq_khz(struct dccg *clk)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(clk);
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
 	int dprefclk_wdivider;
 	int dprefclk_src_sel;
 	int dp_ref_clk_khz = 600000;
-	int target_div = INVALID_DIVIDER;
+	int target_div;
 
 	/* ASSERT DP Reference Clock source is from DFS*/
 	REG_GET(DPREFCLK_CNTL, DPREFCLK_SRC_SEL, &dprefclk_src_sel);
@@ -204,80 +183,27 @@ static int dce_clocks_get_dp_ref_freq(struct display_clock *clk)
 	REG_GET(DENTIST_DISPCLK_CNTL, DENTIST_DPREFCLK_WDIVIDER, &dprefclk_wdivider);
 
 	/* Convert DENTIST_DPREFCLK_WDIVIDERto actual divider*/
-	target_div = dce_divider_range_get_divider(
-			clk_dce->divider_ranges,
-			DIVIDER_RANGE_MAX,
-			dprefclk_wdivider);
-
-	if (target_div != INVALID_DIVIDER) {
-		/* Calculate the current DFS clock, in kHz.*/
-		dp_ref_clk_khz = (DIVIDER_RANGE_SCALE_FACTOR
-			* clk_dce->dentist_vco_freq_khz) / target_div;
-	}
+	target_div = dentist_get_divider_from_did(dprefclk_wdivider);
 
-	/* SW will adjust DP REF Clock average value for all purposes
-	 * (DP DTO / DP Audio DTO and DP GTC)
-	 if clock is spread for all cases:
-	 -if SS enabled on DP Ref clock and HW de-spreading enabled with SW
-	 calculations for DS_INCR/DS_MODULO (this is planned to be default case)
-	 -if SS enabled on DP Ref clock and HW de-spreading enabled with HW
-	 calculations (not planned to be used, but average clock should still
-	 be valid)
-	 -if SS enabled on DP Ref clock and HW de-spreading disabled
-	 (should not be case with CIK) then SW should program all rates
-	 generated according to average value (case as with previous ASICs)
-	  */
-	if (clk_dce->ss_on_dprefclk && clk_dce->dprefclk_ss_divider != 0) {
-		struct fixed31_32 ss_percentage = dc_fixpt_div_int(
-				dc_fixpt_from_fraction(
-						clk_dce->dprefclk_ss_percentage,
-						clk_dce->dprefclk_ss_divider), 200);
-		struct fixed31_32 adj_dp_ref_clk_khz;
+	/* Calculate the current DFS clock, in kHz.*/
+	dp_ref_clk_khz = (DENTIST_DIVIDER_RANGE_SCALE_FACTOR
+		* clk_dce->dentist_vco_freq_khz) / target_div;
 
-		ss_percentage = dc_fixpt_sub(dc_fixpt_one,
-								ss_percentage);
-		adj_dp_ref_clk_khz =
-			dc_fixpt_mul_int(
-				ss_percentage,
-				dp_ref_clk_khz);
-		dp_ref_clk_khz = dc_fixpt_floor(adj_dp_ref_clk_khz);
-	}
-
-	return dp_ref_clk_khz;
+	return dccg_adjust_dp_ref_freq_for_ss(clk_dce, dp_ref_clk_khz);
 }
 
-/* TODO: This is DCN DPREFCLK: it could be program by DENTIST by VBIOS
- * or CLK0_CLK11 by SMU. For DCE120, it is wlays 600Mhz. Will re-visit
- * clock implementation
- */
-static int dce_clocks_get_dp_ref_freq_wrkaround(struct display_clock *clk)
+static int dce12_get_dp_ref_freq_khz(struct dccg *clk)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(clk);
-	int dp_ref_clk_khz = 600000;
-
-	if (clk_dce->ss_on_dprefclk && clk_dce->dprefclk_ss_divider != 0) {
-		struct fixed31_32 ss_percentage = dc_fixpt_div_int(
-				dc_fixpt_from_fraction(
-						clk_dce->dprefclk_ss_percentage,
-						clk_dce->dprefclk_ss_divider), 200);
-		struct fixed31_32 adj_dp_ref_clk_khz;
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
 
-		ss_percentage = dc_fixpt_sub(dc_fixpt_one,
-								ss_percentage);
-		adj_dp_ref_clk_khz =
-			dc_fixpt_mul_int(
-				ss_percentage,
-				dp_ref_clk_khz);
-		dp_ref_clk_khz = dc_fixpt_floor(adj_dp_ref_clk_khz);
-	}
-
-	return dp_ref_clk_khz;
+	return dccg_adjust_dp_ref_freq_for_ss(clk_dce, 600000);
 }
+
 static enum dm_pp_clocks_state dce_get_required_clocks_state(
-	struct display_clock *clk,
-	struct state_dependent_clocks *req_clocks)
+	struct dccg *clk,
+	struct dc_clocks *req_clocks)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(clk);
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
 	int i;
 	enum dm_pp_clocks_state low_req_clk;
 
@@ -286,53 +212,30 @@ static enum dm_pp_clocks_state dce_get_required_clocks_state(
 	 * all required clocks
 	 */
 	for (i = clk->max_clks_state; i >= DM_PP_CLOCKS_STATE_ULTRA_LOW; i--)
-		if (req_clocks->display_clk_khz >
+		if (req_clocks->dispclk_khz >
 				clk_dce->max_clks_by_state[i].display_clk_khz
-			|| req_clocks->pixel_clk_khz >
+			|| req_clocks->phyclk_khz >
 				clk_dce->max_clks_by_state[i].pixel_clk_khz)
 			break;
 
 	low_req_clk = i + 1;
 	if (low_req_clk > clk->max_clks_state) {
-		DC_LOG_WARNING("%s: clocks unsupported disp_clk %d pix_clk %d",
-				__func__,
-				req_clocks->display_clk_khz,
-				req_clocks->pixel_clk_khz);
-		low_req_clk = DM_PP_CLOCKS_STATE_INVALID;
+		/* set max clock state for high phyclock, invalid on exceeding display clock */
+		if (clk_dce->max_clks_by_state[clk->max_clks_state].display_clk_khz
+				< req_clocks->dispclk_khz)
+			low_req_clk = DM_PP_CLOCKS_STATE_INVALID;
+		else
+			low_req_clk = clk->max_clks_state;
 	}
 
 	return low_req_clk;
 }
 
-static bool dce_clock_set_min_clocks_state(
-	struct display_clock *clk,
-	enum dm_pp_clocks_state clocks_state)
-{
-	struct dm_pp_power_level_change_request level_change_req = {
-			clocks_state };
-
-	if (clocks_state > clk->max_clks_state) {
-		/*Requested state exceeds max supported state.*/
-		DC_LOG_WARNING("Requested state exceeds max supported state");
-		return false;
-	} else if (clocks_state == clk->cur_min_clks_state) {
-		/*if we're trying to set the same state, we can just return
-		 * since nothing needs to be done*/
-		return true;
-	}
-
-	/* get max clock state from PPLIB */
-	if (dm_pp_apply_power_level_change_request(clk->ctx, &level_change_req))
-		clk->cur_min_clks_state = clocks_state;
-
-	return true;
-}
-
 static int dce_set_clock(
-	struct display_clock *clk,
+	struct dccg *clk,
 	int requested_clk_khz)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(clk);
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
 	struct bp_pixel_clock_parameters pxl_clk_params = { 0 };
 	struct dc_bios *bp = clk->ctx->dc_bios;
 	int actual_clock = requested_clk_khz;
@@ -364,10 +267,10 @@ static int dce_set_clock(
 }
 
 static int dce_psr_set_clock(
-	struct display_clock *clk,
+	struct dccg *clk,
 	int requested_clk_khz)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(clk);
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
 	struct dc_context *ctx = clk_dce->base.ctx;
 	struct dc *core_dc = ctx->dc;
 	struct dmcu *dmcu = core_dc->res_pool->dmcu;
@@ -380,10 +283,10 @@ static int dce_psr_set_clock(
 }
 
 static int dce112_set_clock(
-	struct display_clock *clk,
+	struct dccg *clk,
 	int requested_clk_khz)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(clk);
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
 	struct bp_set_dce_clock_parameters dce_clk_params;
 	struct dc_bios *bp = clk->ctx->dc_bios;
 	struct dc *core_dc = clk->ctx->dc;
@@ -432,9 +335,9 @@ static int dce112_set_clock(
 	return actual_clock;
 }
 
-static void dce_clock_read_integrated_info(struct dce_disp_clk *clk_dce)
+static void dce_clock_read_integrated_info(struct dce_dccg *clk_dce)
 {
-	struct dc_debug *debug = &clk_dce->base.ctx->dc->debug;
+	struct dc_debug_options *debug = &clk_dce->base.ctx->dc->debug;
 	struct dc_bios *bp = clk_dce->base.ctx->dc_bios;
 	struct integrated_info info = { { { 0 } } };
 	struct dc_firmware_info fw_info = { { 0 } };
@@ -488,11 +391,9 @@ static void dce_clock_read_integrated_info(struct dce_disp_clk *clk_dce)
 	if (!debug->disable_dfs_bypass && bp->integrated_info)
 		if (bp->integrated_info->gpu_cap_info & DFS_BYPASS_ENABLE)
 			clk_dce->dfs_bypass_enabled = true;
-
-	clk_dce->use_max_disp_clk = debug->max_disp_clk;
 }
 
-static void dce_clock_read_ss_info(struct dce_disp_clk *clk_dce)
+static void dce_clock_read_ss_info(struct dce_dccg *clk_dce)
 {
 	struct dc_bios *bp = clk_dce->base.ctx->dc_bios;
 	int ss_info_num = bp->funcs->get_ss_entry_number(
@@ -548,139 +449,265 @@ static void dce_clock_read_ss_info(struct dce_disp_clk *clk_dce)
 	}
 }
 
-static bool dce_apply_clock_voltage_request(
-	struct display_clock *clk,
-	enum dm_pp_clock_type clocks_type,
-	int clocks_in_khz,
-	bool pre_mode_set,
-	bool update_dp_phyclk)
+static inline bool should_set_clock(bool safe_to_lower, int calc_clk, int cur_clk)
+{
+	return ((safe_to_lower && calc_clk < cur_clk) || calc_clk > cur_clk);
+}
+
+static void dce12_update_clocks(struct dccg *dccg,
+			struct dc_clocks *new_clocks,
+			bool safe_to_lower)
 {
-	bool send_request = false;
 	struct dm_pp_clock_for_voltage_req clock_voltage_req = {0};
 
-	switch (clocks_type) {
-	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-	case DM_PP_CLOCK_TYPE_PIXELCLK:
-	case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
-		break;
-	default:
-		BREAK_TO_DEBUGGER();
-		return false;
+	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, dccg->clks.dispclk_khz)) {
+		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DISPLAY_CLK;
+		clock_voltage_req.clocks_in_khz = new_clocks->dispclk_khz;
+		new_clocks->dispclk_khz = dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);
+		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
+
+		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
 	}
 
-	clock_voltage_req.clk_type = clocks_type;
-	clock_voltage_req.clocks_in_khz = clocks_in_khz;
-
-	/* to pplib */
-	if (pre_mode_set) {
-		switch (clocks_type) {
-		case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-			if (clocks_in_khz > clk->cur_clocks_value.dispclk_in_khz) {
-				clk->cur_clocks_value.dispclk_notify_pplib_done = true;
-				send_request = true;
-			} else
-				clk->cur_clocks_value.dispclk_notify_pplib_done = false;
-			/* no matter incrase or decrase clock, update current clock value */
-			clk->cur_clocks_value.dispclk_in_khz = clocks_in_khz;
-			break;
-		case DM_PP_CLOCK_TYPE_PIXELCLK:
-			if (clocks_in_khz > clk->cur_clocks_value.max_pixelclk_in_khz) {
-				clk->cur_clocks_value.pixelclk_notify_pplib_done = true;
-				send_request = true;
-			} else
-				clk->cur_clocks_value.pixelclk_notify_pplib_done = false;
-			/* no matter incrase or decrase clock, update current clock value */
-			clk->cur_clocks_value.max_pixelclk_in_khz = clocks_in_khz;
-			break;
-		case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
-			if (clocks_in_khz > clk->cur_clocks_value.max_non_dp_phyclk_in_khz) {
-				clk->cur_clocks_value.phyclk_notigy_pplib_done = true;
-				send_request = true;
-			} else
-				clk->cur_clocks_value.phyclk_notigy_pplib_done = false;
-			/* no matter incrase or decrase clock, update current clock value */
-			clk->cur_clocks_value.max_non_dp_phyclk_in_khz = clocks_in_khz;
-			break;
-		default:
-			ASSERT(0);
-			break;
-		}
+	if (should_set_clock(safe_to_lower, new_clocks->phyclk_khz, dccg->clks.phyclk_khz)) {
+		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DISPLAYPHYCLK;
+		clock_voltage_req.clocks_in_khz = new_clocks->phyclk_khz;
+		dccg->clks.phyclk_khz = new_clocks->phyclk_khz;
+
+		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
+	}
+}
+
+#ifdef CONFIG_X86
+static int dcn1_determine_dppclk_threshold(struct dccg *dccg, struct dc_clocks *new_clocks)
+{
+	bool request_dpp_div = new_clocks->dispclk_khz > new_clocks->dppclk_khz;
+	bool dispclk_increase = new_clocks->dispclk_khz > dccg->clks.dispclk_khz;
+	int disp_clk_threshold = new_clocks->max_supported_dppclk_khz;
+	bool cur_dpp_div = dccg->clks.dispclk_khz > dccg->clks.dppclk_khz;
+
+	/* increase clock, looking for div is 0 for current, request div is 1*/
+	if (dispclk_increase) {
+		/* already divided by 2, no need to reach target clk with 2 steps*/
+		if (cur_dpp_div)
+			return new_clocks->dispclk_khz;
+
+		/* request disp clk is lower than maximum supported dpp clk,
+		 * no need to reach target clk with two steps.
+		 */
+		if (new_clocks->dispclk_khz <= disp_clk_threshold)
+			return new_clocks->dispclk_khz;
+
+		/* target dpp clk not request divided by 2, still within threshold */
+		if (!request_dpp_div)
+			return new_clocks->dispclk_khz;
 
 	} else {
-		switch (clocks_type) {
-		case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-			if (!clk->cur_clocks_value.dispclk_notify_pplib_done)
-				send_request = true;
-			break;
-		case DM_PP_CLOCK_TYPE_PIXELCLK:
-			if (!clk->cur_clocks_value.pixelclk_notify_pplib_done)
-				send_request = true;
-			break;
-		case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
-			if (!clk->cur_clocks_value.phyclk_notigy_pplib_done)
-				send_request = true;
-			break;
-		default:
-			ASSERT(0);
-			break;
-		}
+		/* decrease clock, looking for current dppclk divided by 2,
+		 * request dppclk not divided by 2.
+		 */
+
+		/* current dpp clk not divided by 2, no need to ramp*/
+		if (!cur_dpp_div)
+			return new_clocks->dispclk_khz;
+
+		/* current disp clk is lower than current maximum dpp clk,
+		 * no need to ramp
+		 */
+		if (dccg->clks.dispclk_khz <= disp_clk_threshold)
+			return new_clocks->dispclk_khz;
+
+		/* request dpp clk need to be divided by 2 */
+		if (request_dpp_div)
+			return new_clocks->dispclk_khz;
 	}
-	if (send_request) {
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
-		if (clk->ctx->dce_version >= DCN_VERSION_1_0) {
-			struct dc *core_dc = clk->ctx->dc;
-			/*use dcfclk request voltage*/
-			clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
-			clock_voltage_req.clocks_in_khz =
-				dcn_find_dcfclk_suits_all(core_dc, &clk->cur_clocks_value);
-		}
+
+	return disp_clk_threshold;
+}
+
+static void dcn1_ramp_up_dispclk_with_dpp(struct dccg *dccg, struct dc_clocks *new_clocks)
+{
+	struct dc *dc = dccg->ctx->dc;
+	int dispclk_to_dpp_threshold = dcn1_determine_dppclk_threshold(dccg, new_clocks);
+	bool request_dpp_div = new_clocks->dispclk_khz > new_clocks->dppclk_khz;
+	int i;
+
+	/* set disp clk to dpp clk threshold */
+	dccg->funcs->set_dispclk(dccg, dispclk_to_dpp_threshold);
+
+	/* update request dpp clk division option */
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
+
+		if (!pipe_ctx->plane_state)
+			continue;
+
+		pipe_ctx->plane_res.dpp->funcs->dpp_dppclk_control(
+				pipe_ctx->plane_res.dpp,
+				request_dpp_div,
+				true);
+	}
+
+	/* If target clk not same as dppclk threshold, set to target clock */
+	if (dispclk_to_dpp_threshold != new_clocks->dispclk_khz)
+		dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);
+
+	dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
+	dccg->clks.dppclk_khz = new_clocks->dppclk_khz;
+	dccg->clks.max_supported_dppclk_khz = new_clocks->max_supported_dppclk_khz;
+}
+
+static void dcn1_update_clocks(struct dccg *dccg,
+			struct dc_clocks *new_clocks,
+			bool safe_to_lower)
+{
+	struct dc *dc = dccg->ctx->dc;
+	struct pp_smu_display_requirement_rv *smu_req_cur =
+			&dc->res_pool->pp_smu_req;
+	struct pp_smu_display_requirement_rv smu_req = *smu_req_cur;
+	struct pp_smu_funcs_rv *pp_smu = dc->res_pool->pp_smu;
+	struct dm_pp_clock_for_voltage_req clock_voltage_req = {0};
+	bool send_request_to_increase = false;
+	bool send_request_to_lower = false;
+
+	if (new_clocks->phyclk_khz)
+		smu_req.display_count = 1;
+	else
+		smu_req.display_count = 0;
+
+	if (new_clocks->dispclk_khz > dccg->clks.dispclk_khz
+			|| new_clocks->phyclk_khz > dccg->clks.phyclk_khz
+			|| new_clocks->fclk_khz > dccg->clks.fclk_khz
+			|| new_clocks->dcfclk_khz > dccg->clks.dcfclk_khz)
+		send_request_to_increase = true;
+
+	if (should_set_clock(safe_to_lower, new_clocks->phyclk_khz, dccg->clks.phyclk_khz)) {
+		dccg->clks.phyclk_khz = new_clocks->phyclk_khz;
+
+		send_request_to_lower = true;
+	}
+
+	if (should_set_clock(safe_to_lower, new_clocks->fclk_khz, dccg->clks.fclk_khz)) {
+		dccg->clks.fclk_khz = new_clocks->fclk_khz;
+		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_FCLK;
+		clock_voltage_req.clocks_in_khz = new_clocks->fclk_khz;
+		smu_req.hard_min_fclk_khz = new_clocks->fclk_khz;
+
+		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
+		send_request_to_lower = true;
+	}
+
+	if (should_set_clock(safe_to_lower, new_clocks->dcfclk_khz, dccg->clks.dcfclk_khz)) {
+		dccg->clks.dcfclk_khz = new_clocks->dcfclk_khz;
+		smu_req.hard_min_dcefclk_khz = new_clocks->dcfclk_khz;
+
+		send_request_to_lower = true;
+	}
+
+	if (should_set_clock(safe_to_lower,
+			new_clocks->dcfclk_deep_sleep_khz, dccg->clks.dcfclk_deep_sleep_khz)) {
+		dccg->clks.dcfclk_deep_sleep_khz = new_clocks->dcfclk_deep_sleep_khz;
+		smu_req.min_deep_sleep_dcefclk_mhz = new_clocks->dcfclk_deep_sleep_khz;
+
+		send_request_to_lower = true;
+	}
+
+	/* make sure dcf clk is before dpp clk to
+	 * make sure we have enough voltage to run dpp clk
+	 */
+	if (send_request_to_increase) {
+		/*use dcfclk to request voltage*/
+		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
+		clock_voltage_req.clocks_in_khz = dcn_find_dcfclk_suits_all(dc, new_clocks);
+		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
+		if (pp_smu->set_display_requirement)
+			pp_smu->set_display_requirement(&pp_smu->pp_smu, &smu_req);
+	}
+
+	/* dcn1 dppclk is tied to dispclk */
+	/* program dispclk on = as a w/a for sleep resume clock ramping issues */
+	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, dccg->clks.dispclk_khz)
+			|| new_clocks->dispclk_khz == dccg->clks.dispclk_khz) {
+		dcn1_ramp_up_dispclk_with_dpp(dccg, new_clocks);
+		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
+
+		send_request_to_lower = true;
+	}
+
+	if (!send_request_to_increase && send_request_to_lower) {
+		/*use dcfclk to request voltage*/
+		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
+		clock_voltage_req.clocks_in_khz = dcn_find_dcfclk_suits_all(dc, new_clocks);
+		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
+		if (pp_smu->set_display_requirement)
+			pp_smu->set_display_requirement(&pp_smu->pp_smu, &smu_req);
+	}
+
+
+	*smu_req_cur = smu_req;
+}
 #endif
-		dm_pp_apply_clock_for_voltage_request(
-			clk->ctx, &clock_voltage_req);
+
+static void dce_update_clocks(struct dccg *dccg,
+			struct dc_clocks *new_clocks,
+			bool safe_to_lower)
+{
+	struct dm_pp_power_level_change_request level_change_req;
+
+	level_change_req.power_level = dce_get_required_clocks_state(dccg, new_clocks);
+	/* get max clock state from PPLIB */
+	if ((level_change_req.power_level < dccg->cur_min_clks_state && safe_to_lower)
+			|| level_change_req.power_level > dccg->cur_min_clks_state) {
+		if (dm_pp_apply_power_level_change_request(dccg->ctx, &level_change_req))
+			dccg->cur_min_clks_state = level_change_req.power_level;
 	}
-	if (update_dp_phyclk && (clocks_in_khz >
-	clk->cur_clocks_value.max_dp_phyclk_in_khz))
-		clk->cur_clocks_value.max_dp_phyclk_in_khz = clocks_in_khz;
 
-	return true;
+	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, dccg->clks.dispclk_khz)) {
+		new_clocks->dispclk_khz = dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);
+		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
+	}
 }
 
+#ifdef CONFIG_X86
+static const struct display_clock_funcs dcn1_funcs = {
+	.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
+	.set_dispclk = dce112_set_clock,
+	.update_clocks = dcn1_update_clocks
+};
+#endif
 
 static const struct display_clock_funcs dce120_funcs = {
-	.get_dp_ref_clk_frequency = dce_clocks_get_dp_ref_freq_wrkaround,
-	.apply_clock_voltage_request = dce_apply_clock_voltage_request,
-	.set_clock = dce112_set_clock
+	.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
+	.set_dispclk = dce112_set_clock,
+	.update_clocks = dce12_update_clocks
 };
 
 static const struct display_clock_funcs dce112_funcs = {
-	.get_dp_ref_clk_frequency = dce_clocks_get_dp_ref_freq,
-	.get_required_clocks_state = dce_get_required_clocks_state,
-	.set_min_clocks_state = dce_clock_set_min_clocks_state,
-	.set_clock = dce112_set_clock
+	.get_dp_ref_clk_frequency = dce_get_dp_ref_freq_khz,
+	.set_dispclk = dce112_set_clock,
+	.update_clocks = dce_update_clocks
 };
 
 static const struct display_clock_funcs dce110_funcs = {
-	.get_dp_ref_clk_frequency = dce_clocks_get_dp_ref_freq,
-	.get_required_clocks_state = dce_get_required_clocks_state,
-	.set_min_clocks_state = dce_clock_set_min_clocks_state,
-	.set_clock = dce_psr_set_clock
+	.get_dp_ref_clk_frequency = dce_get_dp_ref_freq_khz,
+	.set_dispclk = dce_psr_set_clock,
+	.update_clocks = dce_update_clocks
 };
 
 static const struct display_clock_funcs dce_funcs = {
-	.get_dp_ref_clk_frequency = dce_clocks_get_dp_ref_freq,
-	.get_required_clocks_state = dce_get_required_clocks_state,
-	.set_min_clocks_state = dce_clock_set_min_clocks_state,
-	.set_clock = dce_set_clock
+	.get_dp_ref_clk_frequency = dce_get_dp_ref_freq_khz,
+	.set_dispclk = dce_set_clock,
+	.update_clocks = dce_update_clocks
 };
 
-static void dce_disp_clk_construct(
-	struct dce_disp_clk *clk_dce,
+static void dce_dccg_construct(
+	struct dce_dccg *clk_dce,
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask)
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask)
 {
-	struct display_clock *base = &clk_dce->base;
+	struct dccg *base = &clk_dce->base;
 
 	base->ctx = ctx;
 	base->funcs = &dce_funcs;
@@ -700,34 +727,15 @@ static void dce_disp_clk_construct(
 
 	dce_clock_read_integrated_info(clk_dce);
 	dce_clock_read_ss_info(clk_dce);
-
-	dce_divider_range_construct(
-		&clk_dce->divider_ranges[DIVIDER_RANGE_01],
-		DIVIDER_RANGE_01_START,
-		DIVIDER_RANGE_01_STEP_SIZE,
-		DIVIDER_RANGE_01_BASE_DIVIDER_ID,
-		DIVIDER_RANGE_02_BASE_DIVIDER_ID);
-	dce_divider_range_construct(
-		&clk_dce->divider_ranges[DIVIDER_RANGE_02],
-		DIVIDER_RANGE_02_START,
-		DIVIDER_RANGE_02_STEP_SIZE,
-		DIVIDER_RANGE_02_BASE_DIVIDER_ID,
-		DIVIDER_RANGE_03_BASE_DIVIDER_ID);
-	dce_divider_range_construct(
-		&clk_dce->divider_ranges[DIVIDER_RANGE_03],
-		DIVIDER_RANGE_03_START,
-		DIVIDER_RANGE_03_STEP_SIZE,
-		DIVIDER_RANGE_03_BASE_DIVIDER_ID,
-		DIVIDER_RANGE_MAX_DIVIDER_ID);
 }
 
-struct display_clock *dce_disp_clk_create(
+struct dccg *dce_dccg_create(
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask)
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask)
 {
-	struct dce_disp_clk *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
+	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
 
 	if (clk_dce == NULL) {
 		BREAK_TO_DEBUGGER();
@@ -738,19 +746,19 @@ struct display_clock *dce_disp_clk_create(
 		dce80_max_clks_by_state,
 		sizeof(dce80_max_clks_by_state));
 
-	dce_disp_clk_construct(
+	dce_dccg_construct(
 		clk_dce, ctx, regs, clk_shift, clk_mask);
 
 	return &clk_dce->base;
 }
 
-struct display_clock *dce110_disp_clk_create(
+struct dccg *dce110_dccg_create(
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask)
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask)
 {
-	struct dce_disp_clk *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
+	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
 
 	if (clk_dce == NULL) {
 		BREAK_TO_DEBUGGER();
@@ -761,7 +769,7 @@ struct display_clock *dce110_disp_clk_create(
 		dce110_max_clks_by_state,
 		sizeof(dce110_max_clks_by_state));
 
-	dce_disp_clk_construct(
+	dce_dccg_construct(
 		clk_dce, ctx, regs, clk_shift, clk_mask);
 
 	clk_dce->base.funcs = &dce110_funcs;
@@ -769,13 +777,13 @@ struct display_clock *dce110_disp_clk_create(
 	return &clk_dce->base;
 }
 
-struct display_clock *dce112_disp_clk_create(
+struct dccg *dce112_dccg_create(
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask)
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask)
 {
-	struct dce_disp_clk *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
+	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
 
 	if (clk_dce == NULL) {
 		BREAK_TO_DEBUGGER();
@@ -786,7 +794,7 @@ struct display_clock *dce112_disp_clk_create(
 		dce112_max_clks_by_state,
 		sizeof(dce112_max_clks_by_state));
 
-	dce_disp_clk_construct(
+	dce_dccg_construct(
 		clk_dce, ctx, regs, clk_shift, clk_mask);
 
 	clk_dce->base.funcs = &dce112_funcs;
@@ -794,10 +802,9 @@ struct display_clock *dce112_disp_clk_create(
 	return &clk_dce->base;
 }
 
-struct display_clock *dce120_disp_clk_create(struct dc_context *ctx)
+struct dccg *dce120_dccg_create(struct dc_context *ctx)
 {
-	struct dce_disp_clk *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
-	struct dm_pp_clock_levels_with_voltage clk_level_info = {0};
+	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
 
 	if (clk_dce == NULL) {
 		BREAK_TO_DEBUGGER();
@@ -808,28 +815,59 @@ struct display_clock *dce120_disp_clk_create(struct dc_context *ctx)
 		dce120_max_clks_by_state,
 		sizeof(dce120_max_clks_by_state));
 
-	dce_disp_clk_construct(
+	dce_dccg_construct(
 		clk_dce, ctx, NULL, NULL, NULL);
 
 	clk_dce->base.funcs = &dce120_funcs;
 
-	/* new in dce120 */
-	if (!ctx->dc->debug.disable_pplib_clock_request  &&
-			dm_pp_get_clock_levels_by_type_with_voltage(
-			ctx, DM_PP_CLOCK_TYPE_DISPLAY_CLK, &clk_level_info)
-						&& clk_level_info.num_levels)
-		clk_dce->max_displ_clk_in_khz =
-			clk_level_info.data[clk_level_info.num_levels - 1].clocks_in_khz;
-	else
-		clk_dce->max_displ_clk_in_khz = 1133000;
+	return &clk_dce->base;
+}
+
+#ifdef CONFIG_X86
+struct dccg *dcn1_dccg_create(struct dc_context *ctx)
+{
+	struct dc_debug_options *debug = &ctx->dc->debug;
+	struct dc_bios *bp = ctx->dc_bios;
+	struct dc_firmware_info fw_info = { { 0 } };
+	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
+
+	if (clk_dce == NULL) {
+		BREAK_TO_DEBUGGER();
+		return NULL;
+	}
+
+	clk_dce->base.ctx = ctx;
+	clk_dce->base.funcs = &dcn1_funcs;
+
+	clk_dce->dfs_bypass_disp_clk = 0;
+
+	clk_dce->dprefclk_ss_percentage = 0;
+	clk_dce->dprefclk_ss_divider = 1000;
+	clk_dce->ss_on_dprefclk = false;
+
+	if (bp->integrated_info)
+		clk_dce->dentist_vco_freq_khz = bp->integrated_info->dentist_vco_freq;
+	if (clk_dce->dentist_vco_freq_khz == 0) {
+		bp->funcs->get_firmware_info(bp, &fw_info);
+		clk_dce->dentist_vco_freq_khz = fw_info.smu_gpu_pll_output_freq;
+		if (clk_dce->dentist_vco_freq_khz == 0)
+			clk_dce->dentist_vco_freq_khz = 3600000;
+	}
+
+	if (!debug->disable_dfs_bypass && bp->integrated_info)
+		if (bp->integrated_info->gpu_cap_info & DFS_BYPASS_ENABLE)
+			clk_dce->dfs_bypass_enabled = true;
+
+	dce_clock_read_ss_info(clk_dce);
 
 	return &clk_dce->base;
 }
+#endif
 
-void dce_disp_clk_destroy(struct display_clock **disp_clk)
+void dce_dccg_destroy(struct dccg **dccg)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(*disp_clk);
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(*dccg);
 
 	kfree(clk_dce);
-	*disp_clk = NULL;
+	*dccg = NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
index 0e717e0dc8f0..e5e44adc6c27 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
@@ -33,6 +33,9 @@
 	.DPREFCLK_CNTL = mmDPREFCLK_CNTL, \
 	.DENTIST_DISPCLK_CNTL = mmDENTIST_DISPCLK_CNTL
 
+#define CLK_COMMON_REG_LIST_DCN_BASE() \
+	SR(DENTIST_DISPCLK_CNTL)
+
 #define CLK_SF(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
 
@@ -40,58 +43,37 @@
 	CLK_SF(DPREFCLK_CNTL, DPREFCLK_SRC_SEL, mask_sh), \
 	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DPREFCLK_WDIVIDER, mask_sh)
 
+#define CLK_COMMON_MASK_SH_LIST_DCN_COMMON_BASE(mask_sh) \
+	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, mask_sh),\
+	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, mask_sh)
+
 #define CLK_REG_FIELD_LIST(type) \
 	type DPREFCLK_SRC_SEL; \
-	type DENTIST_DPREFCLK_WDIVIDER;
+	type DENTIST_DPREFCLK_WDIVIDER; \
+	type DENTIST_DISPCLK_WDIVIDER; \
+	type DENTIST_DISPCLK_CHG_DONE;
 
-struct dce_disp_clk_shift {
+struct dccg_shift {
 	CLK_REG_FIELD_LIST(uint8_t)
 };
 
-struct dce_disp_clk_mask {
+struct dccg_mask {
 	CLK_REG_FIELD_LIST(uint32_t)
 };
 
-struct dce_disp_clk_registers {
+struct dccg_registers {
 	uint32_t DPREFCLK_CNTL;
 	uint32_t DENTIST_DISPCLK_CNTL;
 };
 
-/* Array identifiers and count for the divider ranges.*/
-enum dce_divider_range_count {
-	DIVIDER_RANGE_01 = 0,
-	DIVIDER_RANGE_02,
-	DIVIDER_RANGE_03,
-	DIVIDER_RANGE_MAX /* == 3*/
-};
-
-enum dce_divider_error_types {
-	INVALID_DID = 0,
-	INVALID_DIVIDER = 1
-};
-
-struct dce_divider_range {
-	int div_range_start;
-	/* The end of this range of dividers.*/
-	int div_range_end;
-	/* The distance between each divider in this range.*/
-	int div_range_step;
-	/* The divider id for the lowest divider.*/
-	int did_min;
-	/* The divider id for the highest divider.*/
-	int did_max;
-};
-
-struct dce_disp_clk {
-	struct display_clock base;
-	const struct dce_disp_clk_registers *regs;
-	const struct dce_disp_clk_shift *clk_shift;
-	const struct dce_disp_clk_mask *clk_mask;
+struct dce_dccg {
+	struct dccg base;
+	const struct dccg_registers *regs;
+	const struct dccg_shift *clk_shift;
+	const struct dccg_mask *clk_mask;
 
 	struct state_dependent_clocks max_clks_by_state[DM_PP_CLOCKS_MAX_STATES];
-	struct dce_divider_range divider_ranges[DIVIDER_RANGE_MAX];
 
-	bool use_max_disp_clk;
 	int dentist_vco_freq_khz;
 
 	/* Cache the status of DFS-bypass feature*/
@@ -106,32 +88,33 @@ struct dce_disp_clk {
 	int dprefclk_ss_percentage;
 	/* DPREFCLK SS percentage Divider (100 or 1000) */
 	int dprefclk_ss_divider;
-
-	/* max disp_clk from PPLIB for max validation display clock*/
-	int max_displ_clk_in_khz;
 };
 
 
-struct display_clock *dce_disp_clk_create(
+struct dccg *dce_dccg_create(
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask);
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask);
 
-struct display_clock *dce110_disp_clk_create(
+struct dccg *dce110_dccg_create(
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask);
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask);
 
-struct display_clock *dce112_disp_clk_create(
+struct dccg *dce112_dccg_create(
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask);
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask);
+
+struct dccg *dce120_dccg_create(struct dc_context *ctx);
 
-struct display_clock *dce120_disp_clk_create(struct dc_context *ctx);
+#ifdef CONFIG_X86
+struct dccg *dcn1_dccg_create(struct dc_context *ctx);
+#endif
 
-void dce_disp_clk_destroy(struct display_clock **disp_clk);
+void dce_dccg_destroy(struct dccg **dccg);
 
 #endif /* _DCE_CLOCKS_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
index a576b8bbb3cd..ca7989e4932b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
@@ -150,7 +150,7 @@ static void dce_dmcu_set_psr_enable(struct dmcu *dmcu, bool enable, bool wait)
 	}
 }
 
-static void dce_dmcu_setup_psr(struct dmcu *dmcu,
+static bool dce_dmcu_setup_psr(struct dmcu *dmcu,
 		struct dc_link *link,
 		struct psr_context *psr_context)
 {
@@ -261,6 +261,8 @@ static void dce_dmcu_setup_psr(struct dmcu *dmcu,
 
 	/* notifyDMCUMsg */
 	REG_UPDATE(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 1);
+
+	return true;
 }
 
 static bool dce_is_dmcu_initialized(struct dmcu *dmcu)
@@ -314,7 +316,7 @@ static void dce_get_psr_wait_loop(
 	return;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 static void dcn10_get_dmcu_state(struct dmcu *dmcu)
 {
 	struct dce_dmcu *dmcu_dce = TO_DCE_DMCU(dmcu);
@@ -545,24 +547,25 @@ static void dcn10_dmcu_set_psr_enable(struct dmcu *dmcu, bool enable, bool wait)
 	 *  least a few frames. Should never hit the max retry assert below.
 	 */
 	if (wait == true) {
-	for (retryCount = 0; retryCount <= 1000; retryCount++) {
-		dcn10_get_dmcu_psr_state(dmcu, &psr_state);
-		if (enable) {
-			if (psr_state != 0)
-				break;
-		} else {
-			if (psr_state == 0)
-				break;
+		for (retryCount = 0; retryCount <= 1000; retryCount++) {
+			dcn10_get_dmcu_psr_state(dmcu, &psr_state);
+			if (enable) {
+				if (psr_state != 0)
+					break;
+			} else {
+				if (psr_state == 0)
+					break;
+			}
+			udelay(500);
 		}
-		udelay(500);
-	}
 
-	/* assert if max retry hit */
-	ASSERT(retryCount <= 1000);
+		/* assert if max retry hit */
+		if (retryCount >= 1000)
+			ASSERT(0);
 	}
 }
 
-static void dcn10_dmcu_setup_psr(struct dmcu *dmcu,
+static bool dcn10_dmcu_setup_psr(struct dmcu *dmcu,
 		struct dc_link *link,
 		struct psr_context *psr_context)
 {
@@ -577,7 +580,7 @@ static void dcn10_dmcu_setup_psr(struct dmcu *dmcu,
 
 	/* If microcontroller is not running, do nothing */
 	if (dmcu->dmcu_state != DMCU_RUNNING)
-		return;
+		return false;
 
 	link->link_enc->funcs->psr_program_dp_dphy_fast_training(link->link_enc,
 			psr_context->psrExitLinkTrainingRequired);
@@ -677,6 +680,11 @@ static void dcn10_dmcu_setup_psr(struct dmcu *dmcu,
 
 	/* notifyDMCUMsg */
 	REG_UPDATE(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 1);
+
+	/* waitDMCUReadyForCmd */
+	REG_WAIT(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 0, 1, 10000);
+
+	return true;
 }
 
 static void dcn10_psr_wait_loop(
@@ -735,7 +743,7 @@ static const struct dmcu_funcs dce_funcs = {
 	.is_dmcu_initialized = dce_is_dmcu_initialized
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 static const struct dmcu_funcs dcn10_funcs = {
 	.dmcu_init = dcn10_dmcu_init,
 	.load_iram = dcn10_dmcu_load_iram,
@@ -787,7 +795,7 @@ struct dmcu *dce_dmcu_create(
 	return &dmcu_dce->base;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 struct dmcu *dcn10_dmcu_create(
 	struct dc_context *ctx,
 	const struct dce_dmcu_registers *regs,
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
index 057b8afd74bc..64dc75378541 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
@@ -147,6 +147,7 @@
 	SR(DCCG_GATE_DISABLE_CNTL2), \
 	SR(DCFCLK_CNTL),\
 	SR(DCFCLK_CNTL), \
+	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL), \
 	/* todo:  get these from GVM instead of reading registers ourselves */\
 	MMHUB_SR(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32),\
 	MMHUB_SR(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32),\
@@ -249,7 +250,6 @@ struct dce_hwseq_registers {
 	uint32_t DISPCLK_FREQ_CHANGE_CNTL;
 	uint32_t RBBMIF_TIMEOUT_DIS;
 	uint32_t RBBMIF_TIMEOUT_DIS_2;
-	uint32_t DENTIST_DISPCLK_CNTL;
 	uint32_t DCHUBBUB_CRC_CTRL;
 	uint32_t DPP_TOP0_DPP_CRC_CTRL;
 	uint32_t DPP_TOP0_DPP_CRC_VAL_R_G;
@@ -276,6 +276,8 @@ struct dce_hwseq_registers {
 	uint32_t MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB;
 	uint32_t MC_VM_SYSTEM_APERTURE_LOW_ADDR;
 	uint32_t MC_VM_SYSTEM_APERTURE_HIGH_ADDR;
+	uint32_t AZALIA_AUDIO_DTO;
+	uint32_t AZALIA_CONTROLLER_CLOCK_GATING;
 };
  /* set field name */
 #define HWS_SF(blk_name, reg_name, field_name, post_fix)\
@@ -362,7 +364,8 @@ struct dce_hwseq_registers {
 	HWSEQ_PIXEL_RATE_MASK_SH_LIST(mask_sh, OTG0_),\
 	HWS_SF1(OTG0_, PHYPLL_PIXEL_RATE_CNTL, PHYPLL_PIXEL_RATE_SOURCE, mask_sh), \
 	HWS_SF(, DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_ENABLE, mask_sh), \
-	HWS_SF(, DCFCLK_CNTL, DCFCLK_GATE_DIS, mask_sh)
+	HWS_SF(, DCFCLK_CNTL, DCFCLK_GATE_DIS, mask_sh), \
+	HWS_SF(, DC_MEM_GLOBAL_PWR_REQ_CNTL, DC_MEM_GLOBAL_PWR_REQ_DIS, mask_sh)
 
 #define HWSEQ_DCN1_MASK_SH_LIST(mask_sh)\
 	HWSEQ_DCN_MASK_SH_LIST(mask_sh), \
@@ -496,14 +499,13 @@ struct dce_hwseq_registers {
 	type DOMAIN7_PGFSM_PWR_STATUS; \
 	type DCFCLK_GATE_DIS; \
 	type DCHUBBUB_GLOBAL_TIMER_REFDIV; \
-	type DENTIST_DPPCLK_WDIVIDER; \
-	type DENTIST_DISPCLK_WDIVIDER; \
 	type VGA_TEST_ENABLE; \
 	type VGA_TEST_RENDER_START; \
 	type D1VGA_MODE_ENABLE; \
 	type D2VGA_MODE_ENABLE; \
 	type D3VGA_MODE_ENABLE; \
-	type D4VGA_MODE_ENABLE;
+	type D4VGA_MODE_ENABLE; \
+	type AZALIA_AUDIO_DTO_MODULE;
 
 struct dce_hwseq_shift {
 	HWSEQ_REG_FIELD_LIST(uint8_t)
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
index dbe3b26b6d9e..752b3d62e793 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
@@ -256,6 +256,11 @@ static void setup_panel_mode(
 	enum dp_panel_mode panel_mode)
 {
 	uint32_t value;
+	struct dc_context *ctx = enc110->base.ctx;
+
+	/* if psp set panel mode, dal should be program it */
+	if (ctx->dc->caps.psp_setup_panel_mode)
+		return;
 
 	ASSERT(REG(DP_DPHY_INTERNAL_CTRL));
 	value = REG_READ(DP_DPHY_INTERNAL_CTRL);
@@ -646,6 +651,9 @@ static bool dce110_link_encoder_validate_hdmi_output(
 	if (!enc110->base.features.flags.bits.HDMI_6GB_EN &&
 		adjusted_pix_clk_khz >= 300000)
 		return false;
+	if (enc110->base.ctx->dc->debug.hdmi20_disable &&
+		crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+		return false;
 	return true;
 }
 
@@ -773,6 +781,9 @@ void dce110_link_encoder_construct(
 				__func__,
 				result);
 	}
+	if (enc110->base.ctx->dc->debug.hdmi20_disable) {
+		enc110->base.features.flags.bits.HDMI_6GB_EN = 0;
+	}
 }
 
 bool dce110_link_encoder_validate_output_with_stream(
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
index bae752332a9f..85686d917636 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
@@ -729,7 +729,7 @@ static bool dce_mi_program_surface_flip_and_addr(
 	return true;
 }
 
-static struct mem_input_funcs dce_mi_funcs = {
+static const struct mem_input_funcs dce_mi_funcs = {
 	.mem_input_program_display_marks = dce_mi_program_display_marks,
 	.allocate_mem_input = dce_mi_allocate_dmif,
 	.free_mem_input = dce_mi_free_dmif,
@@ -741,7 +741,7 @@ static struct mem_input_funcs dce_mi_funcs = {
 	.mem_input_is_flip_pending = dce_mi_is_flip_pending
 };
 
-static struct mem_input_funcs dce112_mi_funcs = {
+static const struct mem_input_funcs dce112_mi_funcs = {
 	.mem_input_program_display_marks = dce112_mi_program_display_marks,
 	.allocate_mem_input = dce_mi_allocate_dmif,
 	.free_mem_input = dce_mi_free_dmif,
@@ -753,7 +753,7 @@ static struct mem_input_funcs dce112_mi_funcs = {
 	.mem_input_is_flip_pending = dce_mi_is_flip_pending
 };
 
-static struct mem_input_funcs dce120_mi_funcs = {
+static const struct mem_input_funcs dce120_mi_funcs = {
 	.mem_input_program_display_marks = dce120_mi_program_display_marks,
 	.allocate_mem_input = dce_mi_allocate_dmif,
 	.free_mem_input = dce_mi_free_dmif,
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
index c0e813c7ddd4..b139b4017820 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
@@ -135,7 +135,7 @@ static void dce110_update_generic_info_packet(
 			AFMT_GENERIC0_UPDATE, (packet_index == 0),
 			AFMT_GENERIC2_UPDATE, (packet_index == 2));
 	}
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	if (REG(AFMT_VBI_PACKET_CONTROL1)) {
 		switch (packet_index) {
 		case 0:
@@ -229,7 +229,7 @@ static void dce110_update_hdmi_info_packet(
 				HDMI_GENERIC1_SEND, send,
 				HDMI_GENERIC1_LINE, line);
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case 4:
 		if (REG(HDMI_GENERIC_PACKET_CONTROL2))
 			REG_UPDATE_3(HDMI_GENERIC_PACKET_CONTROL2,
@@ -274,7 +274,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 	struct dc_crtc_timing *crtc_timing,
 	enum dc_color_space output_color_space)
 {
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	uint32_t h_active_start;
 	uint32_t v_active_start;
 	uint32_t misc0 = 0;
@@ -289,11 +289,6 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 
 	struct dce110_stream_encoder *enc110 = DCE110STRENC_FROM_STRENC(enc);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
-	if (REG(DP_DB_CNTL))
-		REG_UPDATE(DP_DB_CNTL, DP_DB_DISABLE, 1);
-#endif
-
 	/* set pixel encoding */
 	switch (crtc_timing->pixel_encoding) {
 	case PIXEL_ENCODING_YCBCR422:
@@ -322,7 +317,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 		if (enc110->se_mask->DP_VID_M_DOUBLE_VALUE_EN)
 			REG_UPDATE(DP_VID_TIMING, DP_VID_M_DOUBLE_VALUE_EN, 1);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 		if (enc110->se_mask->DP_VID_N_MUL)
 			REG_UPDATE(DP_VID_TIMING, DP_VID_N_MUL, 1);
 #endif
@@ -333,7 +328,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 		break;
 	}
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	if (REG(DP_MSA_MISC))
 		misc1 = REG_READ(DP_MSA_MISC);
 #endif
@@ -367,7 +362,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 	/* set dynamic range and YCbCr range */
 
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	switch (crtc_timing->display_color_depth) {
 	case COLOR_DEPTH_666:
 		colorimetry_bpc = 0;
@@ -446,7 +441,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 				DP_DYN_RANGE, dynamic_range_rgb,
 				DP_YCBCR_RANGE, dynamic_range_ycbcr);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 		if (REG(DP_MSA_COLORIMETRY))
 			REG_SET(DP_MSA_COLORIMETRY, 0, DP_MSA_MISC0, misc0);
 
@@ -481,7 +476,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 				crtc_timing->v_front_porch;
 
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 		/* start at begining of left border */
 		if (REG(DP_MSA_TIMING_PARAM2))
 			REG_SET_2(DP_MSA_TIMING_PARAM2, 0,
@@ -756,7 +751,7 @@ static void dce110_stream_encoder_update_hdmi_info_packets(
 		dce110_update_hdmi_info_packet(enc110, 3, &info_frame->hdrsmd);
 	}
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	if (enc110->se_mask->HDMI_DB_DISABLE) {
 		/* for bring up, disable dp double  TODO */
 		if (REG(HDMI_DB_CONTROL))
@@ -794,7 +789,7 @@ static void dce110_stream_encoder_stop_hdmi_info_packets(
 		HDMI_GENERIC1_LINE, 0,
 		HDMI_GENERIC1_SEND, 0);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	/* stop generic packets 2 & 3 on HDMI */
 	if (REG(HDMI_GENERIC_PACKET_CONTROL2))
 		REG_SET_6(HDMI_GENERIC_PACKET_CONTROL2, 0,
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
index a02e719d7794..ab63d0d0304c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
@@ -155,7 +155,7 @@ static void program_overscan(
 	int overscan_bottom = data->v_active
 			- data->recout.y - data->recout.height;
 
-	if (xfm_dce->base.ctx->dc->debug.surface_visual_confirm) {
+	if (xfm_dce->base.ctx->dc->debug.visual_confirm != VISUAL_CONFIRM_DISABLE) {
 		overscan_bottom += 2;
 		overscan_right += 2;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
index 41f83ecd7469..74c05e878807 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
@@ -125,17 +125,50 @@ static void dce100_pplib_apply_display_requirements(
 	dc->prev_display_config = *pp_display_cfg;
 }
 
+/* unit: in_khz before mode set, get pixel clock from context. ASIC register
+ * may not be programmed yet
+ */
+static uint32_t get_max_pixel_clock_for_all_paths(
+	struct dc *dc,
+	struct dc_state *context)
+{
+	uint32_t max_pix_clk = 0;
+	int i;
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+		if (pipe_ctx->stream == NULL)
+			continue;
+
+		/* do not check under lay */
+		if (pipe_ctx->top_pipe)
+			continue;
+
+		if (pipe_ctx->stream_res.pix_clk_params.requested_pix_clk > max_pix_clk)
+			max_pix_clk =
+				pipe_ctx->stream_res.pix_clk_params.requested_pix_clk;
+	}
+	return max_pix_clk;
+}
+
 void dce100_set_bandwidth(
 		struct dc *dc,
 		struct dc_state *context,
 		bool decrease_allowed)
 {
-	if (decrease_allowed || context->bw.dce.dispclk_khz > dc->current_state->bw.dce.dispclk_khz) {
-		dc->res_pool->display_clock->funcs->set_clock(
-				dc->res_pool->display_clock,
-				context->bw.dce.dispclk_khz * 115 / 100);
-		dc->current_state->bw.dce.dispclk_khz = context->bw.dce.dispclk_khz;
-	}
+	struct dc_clocks req_clks;
+
+	req_clks.dispclk_khz = context->bw.dce.dispclk_khz * 115 / 100;
+	req_clks.phyclk_khz = get_max_pixel_clock_for_all_paths(dc, context);
+
+	dce110_set_safe_displaymarks(&context->res_ctx, dc->res_pool);
+
+	dc->res_pool->dccg->funcs->update_clocks(
+			dc->res_pool->dccg,
+			&req_clks,
+			decrease_allowed);
+
 	dce100_pplib_apply_display_requirements(dc, context);
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
index 344dd2e69e7c..3f76e6019546 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -52,6 +52,7 @@
 #include "dce/dce_10_0_sh_mask.h"
 
 #include "dce/dce_dmcu.h"
+#include "dce/dce_aux.h"
 #include "dce/dce_abm.h"
 
 #ifndef mmMC_HUB_RDREQ_DMIF_LIMIT
@@ -135,15 +136,15 @@ static const struct dce110_timing_generator_offsets dce100_tg_offsets[] = {
 	.reg_name = mm ## block ## id ## _ ## reg_name
 
 
-static const struct dce_disp_clk_registers disp_clk_regs = {
+static const struct dccg_registers disp_clk_regs = {
 		CLK_COMMON_REG_LIST_DCE_BASE()
 };
 
-static const struct dce_disp_clk_shift disp_clk_shift = {
+static const struct dccg_shift disp_clk_shift = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(__SHIFT)
 };
 
-static const struct dce_disp_clk_mask disp_clk_mask = {
+static const struct dccg_mask disp_clk_mask = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(_MASK)
 };
 
@@ -279,7 +280,20 @@ static const struct dce_opp_shift opp_shift = {
 static const struct dce_opp_mask opp_mask = {
 	OPP_COMMON_MASK_SH_LIST_DCE_100(_MASK)
 };
+#define aux_engine_regs(id)\
+[id] = {\
+	AUX_COMMON_REG_LIST(id), \
+	.AUX_RESET_MASK = 0 \
+}
 
+static const struct dce110_aux_registers aux_engine_regs[] = {
+		aux_engine_regs(0),
+		aux_engine_regs(1),
+		aux_engine_regs(2),
+		aux_engine_regs(3),
+		aux_engine_regs(4),
+		aux_engine_regs(5)
+};
 
 #define audio_regs(id)\
 [id] = {\
@@ -572,6 +586,23 @@ struct output_pixel_processor *dce100_opp_create(
 	return &opp->base;
 }
 
+struct aux_engine *dce100_aux_engine_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct aux_engine_dce110 *aux_engine =
+		kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL);
+
+	if (!aux_engine)
+		return NULL;
+
+	dce110_aux_engine_construct(aux_engine, ctx, inst,
+				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
+				    &aux_engine_regs[inst]);
+
+	return &aux_engine->base;
+}
+
 struct clock_source *dce100_clock_source_create(
 	struct dc_context *ctx,
 	struct dc_bios *bios,
@@ -624,6 +655,10 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+
+		if (pool->base.engines[i] != NULL)
+			dce110_engine_destroy(&pool->base.engines[i]);
+
 	}
 
 	for (i = 0; i < pool->base.stream_enc_count; i++) {
@@ -644,8 +679,8 @@ static void destruct(struct dce110_resource_pool *pool)
 			dce_aud_destroy(&pool->base.audios[i]);
 	}
 
-	if (pool->base.display_clock != NULL)
-		dce_disp_clk_destroy(&pool->base.display_clock);
+	if (pool->base.dccg != NULL)
+		dce_dccg_destroy(&pool->base.dccg);
 
 	if (pool->base.abm != NULL)
 				dce_abm_destroy(&pool->base.abm);
@@ -830,11 +865,11 @@ static bool construct(
 		}
 	}
 
-	pool->base.display_clock = dce_disp_clk_create(ctx,
+	pool->base.dccg = dce_dccg_create(ctx,
 			&disp_clk_regs,
 			&disp_clk_shift,
 			&disp_clk_mask);
-	if (pool->base.display_clock == NULL) {
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto res_create_fail;
@@ -864,7 +899,7 @@ static bool construct(
 	 * max_clock_state
 	 */
 	if (dm_pp_get_static_clocks(ctx, &static_clk_info))
-		pool->base.display_clock->max_clks_state =
+		pool->base.dccg->max_clks_state =
 					static_clk_info.max_clocks_state;
 	{
 		struct irq_service_init_data init_data;
@@ -884,7 +919,7 @@ static bool construct(
 	dc->caps.i2c_speed_in_khz = 40;
 	dc->caps.max_cursor_size = 128;
 	dc->caps.dual_link_dvi = true;
-
+	dc->caps.disable_dp_clk_share = true;
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		pool->base.timing_generators[i] =
 			dce100_timing_generator_create(
@@ -928,6 +963,13 @@ static bool construct(
 				"DC: failed to create output pixel processor!\n");
 			goto res_create_fail;
 		}
+		pool->base.engines[i] = dce100_aux_engine_create(ctx, i);
+		if (pool->base.engines[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create aux engine!!\n");
+			goto res_create_fail;
+		}
 	}
 
 	dc->caps.max_planes =  pool->base.pipe_count;
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c
index e2994d337044..1f7f25013217 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c
@@ -143,7 +143,7 @@ static void wait_for_fbc_state_changed(
 	struct dce110_compressor *cp110,
 	bool enabled)
 {
-	uint8_t counter = 0;
+	uint32_t counter = 0;
 	uint32_t addr = mmFBC_STATUS;
 	uint32_t value;
 
@@ -158,7 +158,7 @@ static void wait_for_fbc_state_changed(
 		counter++;
 	}
 
-	if (counter == 10) {
+	if (counter == 1000) {
 		DC_LOG_WARNING("%s: wait counter exceeded, changes to HW not applied",
 			__func__);
 	} else {
@@ -551,9 +551,7 @@ void dce110_compressor_construct(struct dce110_compressor *compressor,
 	compressor->base.lpt_channels_num = 0;
 	compressor->base.attached_inst = 0;
 	compressor->base.is_enabled = false;
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 	compressor->base.funcs = &dce110_compressor_funcs;
 
-#endif
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index c29052b6da5a..1d98e3678b04 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -34,9 +34,7 @@
 #include "dce/dce_hwseq.h"
 #include "gpio_service_interface.h"
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 #include "dce110_compressor.h"
-#endif
 
 #include "bios/bios_parser_helper.h"
 #include "timing_generator.h"
@@ -667,16 +665,25 @@ static enum dc_status bios_parser_crtc_source_select(
 
 void dce110_update_info_frame(struct pipe_ctx *pipe_ctx)
 {
+	bool is_hdmi;
+	bool is_dp;
+
 	ASSERT(pipe_ctx->stream);
 
 	if (pipe_ctx->stream_res.stream_enc == NULL)
 		return;  /* this is not root pipe */
 
-	if (dc_is_hdmi_signal(pipe_ctx->stream->signal))
+	is_hdmi = dc_is_hdmi_signal(pipe_ctx->stream->signal);
+	is_dp = dc_is_dp_signal(pipe_ctx->stream->signal);
+
+	if (!is_hdmi && !is_dp)
+		return;
+
+	if (is_hdmi)
 		pipe_ctx->stream_res.stream_enc->funcs->update_hdmi_info_packets(
 			pipe_ctx->stream_res.stream_enc,
 			&pipe_ctx->stream_res.encoder_info_frame);
-	else if (dc_is_dp_signal(pipe_ctx->stream->signal))
+	else
 		pipe_ctx->stream_res.stream_enc->funcs->update_dp_info_packets(
 			pipe_ctx->stream_res.stream_enc,
 			&pipe_ctx->stream_res.encoder_info_frame);
@@ -857,17 +864,22 @@ void hwss_edp_power_control(
 		if (power_up) {
 			unsigned long long current_ts = dm_get_timestamp(ctx);
 			unsigned long long duration_in_ms =
-					dm_get_elapse_time_in_ns(
+					div64_u64(dm_get_elapse_time_in_ns(
 							ctx,
 							current_ts,
-							div64_u64(link->link_trace.time_stamp.edp_poweroff, 1000000));
+							link->link_trace.time_stamp.edp_poweroff), 1000000);
 			unsigned long long wait_time_ms = 0;
 
 			/* max 500ms from LCDVDD off to on */
+			unsigned long long edp_poweroff_time_ms = 500;
+
+			if (link->local_sink != NULL)
+				edp_poweroff_time_ms =
+						500 + link->local_sink->edid_caps.panel_patch.extra_t12_ms;
 			if (link->link_trace.time_stamp.edp_poweroff == 0)
-				wait_time_ms = 500;
-			else if (duration_in_ms < 500)
-				wait_time_ms = 500 - duration_in_ms;
+				wait_time_ms = edp_poweroff_time_ms;
+			else if (duration_in_ms < edp_poweroff_time_ms)
+				wait_time_ms = edp_poweroff_time_ms - duration_in_ms;
 
 			if (wait_time_ms) {
 				msleep(wait_time_ms);
@@ -972,19 +984,35 @@ void hwss_edp_backlight_control(
 		edp_receiver_ready_T9(link);
 }
 
-void dce110_disable_stream(struct pipe_ctx *pipe_ctx, int option)
+void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx)
 {
-	struct dc_stream_state *stream = pipe_ctx->stream;
-	struct dc_link *link = stream->sink->link;
-	struct dc *dc = pipe_ctx->stream->ctx->dc;
+	struct dc *core_dc = pipe_ctx->stream->ctx->dc;
+	/* notify audio driver for audio modes of monitor */
+	struct pp_smu_funcs_rv *pp_smu = core_dc->res_pool->pp_smu;
+	unsigned int i, num_audio = 1;
 
-	if (dc_is_hdmi_signal(pipe_ctx->stream->signal))
-		pipe_ctx->stream_res.stream_enc->funcs->stop_hdmi_info_packets(
-			pipe_ctx->stream_res.stream_enc);
+	if (pipe_ctx->stream_res.audio) {
+		for (i = 0; i < MAX_PIPES; i++) {
+			/*current_state not updated yet*/
+			if (core_dc->current_state->res_ctx.pipe_ctx[i].stream_res.audio != NULL)
+				num_audio++;
+		}
 
-	if (dc_is_dp_signal(pipe_ctx->stream->signal))
-		pipe_ctx->stream_res.stream_enc->funcs->stop_dp_info_packets(
-			pipe_ctx->stream_res.stream_enc);
+		pipe_ctx->stream_res.audio->funcs->az_enable(pipe_ctx->stream_res.audio);
+
+		if (num_audio == 1 && pp_smu != NULL && pp_smu->set_pme_wa_enable != NULL)
+			/*this is the first audio. apply the PME w/a in order to wake AZ from D3*/
+			pp_smu->set_pme_wa_enable(&pp_smu->pp_smu);
+		/* un-mute audio */
+		/* TODO: audio should be per stream rather than per link */
+		pipe_ctx->stream_res.stream_enc->funcs->audio_mute_control(
+			pipe_ctx->stream_res.stream_enc, false);
+	}
+}
+
+void dce110_disable_audio_stream(struct pipe_ctx *pipe_ctx, int option)
+{
+	struct dc *dc = pipe_ctx->stream->ctx->dc;
 
 	pipe_ctx->stream_res.stream_enc->funcs->audio_mute_control(
 			pipe_ctx->stream_res.stream_enc, true);
@@ -1015,7 +1043,23 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx, int option)
 		 * stream->stream_engine_id);
 		 */
 	}
+}
 
+void dce110_disable_stream(struct pipe_ctx *pipe_ctx, int option)
+{
+	struct dc_stream_state *stream = pipe_ctx->stream;
+	struct dc_link *link = stream->sink->link;
+	struct dc *dc = pipe_ctx->stream->ctx->dc;
+
+	if (dc_is_hdmi_signal(pipe_ctx->stream->signal))
+		pipe_ctx->stream_res.stream_enc->funcs->stop_hdmi_info_packets(
+			pipe_ctx->stream_res.stream_enc);
+
+	if (dc_is_dp_signal(pipe_ctx->stream->signal))
+		pipe_ctx->stream_res.stream_enc->funcs->stop_dp_info_packets(
+			pipe_ctx->stream_res.stream_enc);
+
+	dc->hwss.disable_audio_stream(pipe_ctx, option);
 
 	link->link_enc->funcs->connect_dig_be_to_fe(
 			link->link_enc,
@@ -1206,13 +1250,13 @@ static void program_scaler(const struct dc *dc,
 {
 	struct tg_color color = {0};
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	/* TOFPGA */
 	if (pipe_ctx->plane_res.xfm->funcs->transform_set_pixel_storage_depth == NULL)
 		return;
 #endif
 
-	if (dc->debug.surface_visual_confirm)
+	if (dc->debug.visual_confirm == VISUAL_CONFIRM_SURFACE)
 		get_surface_visual_confirm_color(pipe_ctx, &color);
 	else
 		color_space_to_black_color(dc,
@@ -1298,6 +1342,30 @@ static enum dc_status apply_single_controller_ctx_to_hw(
 	struct pipe_ctx *pipe_ctx_old = &dc->current_state->res_ctx.
 			pipe_ctx[pipe_ctx->pipe_idx];
 
+	if (pipe_ctx->stream_res.audio != NULL) {
+		struct audio_output audio_output;
+
+		build_audio_output(context, pipe_ctx, &audio_output);
+
+		if (dc_is_dp_signal(pipe_ctx->stream->signal))
+			pipe_ctx->stream_res.stream_enc->funcs->dp_audio_setup(
+					pipe_ctx->stream_res.stream_enc,
+					pipe_ctx->stream_res.audio->inst,
+					&pipe_ctx->stream->audio_info);
+		else
+			pipe_ctx->stream_res.stream_enc->funcs->hdmi_audio_setup(
+					pipe_ctx->stream_res.stream_enc,
+					pipe_ctx->stream_res.audio->inst,
+					&pipe_ctx->stream->audio_info,
+					&audio_output.crtc_info);
+
+		pipe_ctx->stream_res.audio->funcs->az_configure(
+				pipe_ctx->stream_res.audio,
+				pipe_ctx->stream->signal,
+				&audio_output.crtc_info,
+				&pipe_ctx->stream->audio_info);
+	}
+
 	/*  */
 	dc->hwss.enable_stream_timing(pipe_ctx, context, dc);
 
@@ -1412,7 +1480,7 @@ static void power_down_controllers(struct dc *dc)
 {
 	int i;
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+	for (i = 0; i < dc->res_pool->timing_generator_count; i++) {
 		dc->res_pool->timing_generators[i]->funcs->disable_crtc(
 				dc->res_pool->timing_generators[i]);
 	}
@@ -1441,10 +1509,8 @@ static void power_down_all_hw_blocks(struct dc *dc)
 
 	power_down_clock_sources(dc);
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 	if (dc->fbc_compressor)
 		dc->fbc_compressor->funcs->disable_fbc(dc->fbc_compressor);
-#endif
 }
 
 static void disable_vga_and_power_gate_all_controllers(
@@ -1454,12 +1520,13 @@ static void disable_vga_and_power_gate_all_controllers(
 	struct timing_generator *tg;
 	struct dc_context *ctx = dc->ctx;
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+	for (i = 0; i < dc->res_pool->timing_generator_count; i++) {
 		tg = dc->res_pool->timing_generators[i];
 
 		if (tg->funcs->disable_vga)
 			tg->funcs->disable_vga(tg);
-
+	}
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		/* Enable CLOCK gating for each pipe BEFORE controller
 		 * powergating. */
 		enable_display_pipe_clock_gating(ctx,
@@ -1602,7 +1669,7 @@ static void dce110_set_displaymarks(
 	}
 }
 
-static void set_safe_displaymarks(
+void dce110_set_safe_displaymarks(
 		struct resource_context *res_ctx,
 		const struct resource_pool *pool)
 {
@@ -1686,9 +1753,7 @@ static void set_static_screen_control(struct pipe_ctx **pipe_ctx,
 	if (events->force_trigger)
 		value |= 0x1;
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 	value |= 0x84;
-#endif
 
 	for (i = 0; i < num_pipes; i++)
 		pipe_ctx[i]->stream_res.tg->funcs->
@@ -1696,23 +1761,15 @@ static void set_static_screen_control(struct pipe_ctx **pipe_ctx,
 }
 
 /* unit: in_khz before mode set, get pixel clock from context. ASIC register
- * may not be programmed yet.
- * TODO: after mode set, pre_mode_set = false,
- * may read PLL register to get pixel clock
+ * may not be programmed yet
  */
 static uint32_t get_max_pixel_clock_for_all_paths(
 	struct dc *dc,
-	struct dc_state *context,
-	bool pre_mode_set)
+	struct dc_state *context)
 {
 	uint32_t max_pix_clk = 0;
 	int i;
 
-	if (!pre_mode_set) {
-		/* TODO: read ASIC register to get pixel clock */
-		ASSERT(0);
-	}
-
 	for (i = 0; i < MAX_PIPES; i++) {
 		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
 
@@ -1728,97 +1785,10 @@ static uint32_t get_max_pixel_clock_for_all_paths(
 				pipe_ctx->stream_res.pix_clk_params.requested_pix_clk;
 	}
 
-	if (max_pix_clk == 0)
-		ASSERT(0);
-
 	return max_pix_clk;
 }
 
 /*
- * Find clock state based on clock requested. if clock value is 0, simply
- * set clock state as requested without finding clock state by clock value
- */
-
-static void apply_min_clocks(
-	struct dc *dc,
-	struct dc_state *context,
-	enum dm_pp_clocks_state *clocks_state,
-	bool pre_mode_set)
-{
-	struct state_dependent_clocks req_clocks = {0};
-
-	if (!pre_mode_set) {
-		/* set clock_state without verification */
-		if (context->dis_clk->funcs->set_min_clocks_state) {
-			context->dis_clk->funcs->set_min_clocks_state(
-						context->dis_clk, *clocks_state);
-			return;
-		}
-
-		/* TODO: This is incorrect. Figure out how to fix. */
-		context->dis_clk->funcs->apply_clock_voltage_request(
-				context->dis_clk,
-				DM_PP_CLOCK_TYPE_DISPLAY_CLK,
-				context->dis_clk->cur_clocks_value.dispclk_in_khz,
-				pre_mode_set,
-				false);
-
-		context->dis_clk->funcs->apply_clock_voltage_request(
-				context->dis_clk,
-				DM_PP_CLOCK_TYPE_PIXELCLK,
-				context->dis_clk->cur_clocks_value.max_pixelclk_in_khz,
-				pre_mode_set,
-				false);
-
-		context->dis_clk->funcs->apply_clock_voltage_request(
-				context->dis_clk,
-				DM_PP_CLOCK_TYPE_DISPLAYPHYCLK,
-				context->dis_clk->cur_clocks_value.max_non_dp_phyclk_in_khz,
-				pre_mode_set,
-				false);
-		return;
-	}
-
-	/* get the required state based on state dependent clocks:
-	 * display clock and pixel clock
-	 */
-	req_clocks.display_clk_khz = context->bw.dce.dispclk_khz;
-
-	req_clocks.pixel_clk_khz = get_max_pixel_clock_for_all_paths(
-			dc, context, true);
-
-	if (context->dis_clk->funcs->get_required_clocks_state) {
-		*clocks_state = context->dis_clk->funcs->get_required_clocks_state(
-				context->dis_clk, &req_clocks);
-		context->dis_clk->funcs->set_min_clocks_state(
-			context->dis_clk, *clocks_state);
-	} else {
-		context->dis_clk->funcs->apply_clock_voltage_request(
-				context->dis_clk,
-				DM_PP_CLOCK_TYPE_DISPLAY_CLK,
-				req_clocks.display_clk_khz,
-				pre_mode_set,
-				false);
-
-		context->dis_clk->funcs->apply_clock_voltage_request(
-				context->dis_clk,
-				DM_PP_CLOCK_TYPE_PIXELCLK,
-				req_clocks.pixel_clk_khz,
-				pre_mode_set,
-				false);
-
-		context->dis_clk->funcs->apply_clock_voltage_request(
-				context->dis_clk,
-				DM_PP_CLOCK_TYPE_DISPLAYPHYCLK,
-				req_clocks.pixel_clk_khz,
-				pre_mode_set,
-				false);
-	}
-}
-
-#if defined(CONFIG_DRM_AMD_DC_FBC)
-
-/*
  *  Check if FBC can be enabled
  */
 static bool should_enable_fbc(struct dc *dc,
@@ -1896,7 +1866,6 @@ static void enable_fbc(struct dc *dc,
 		compr->funcs->enable_fbc(compr, &params);
 	}
 }
-#endif
 
 static void dce110_reset_hw_ctx_wrap(
 		struct dc *dc,
@@ -1949,97 +1918,12 @@ static void dce110_reset_hw_ctx_wrap(
 	}
 }
 
-
-enum dc_status dce110_apply_ctx_to_hw(
+static void dce110_setup_audio_dto(
 		struct dc *dc,
 		struct dc_state *context)
 {
-	struct dc_bios *dcb = dc->ctx->dc_bios;
-	enum dc_status status;
 	int i;
-	enum dm_pp_clocks_state clocks_state = DM_PP_CLOCKS_STATE_INVALID;
-
-	/* Reset old context */
-	/* look up the targets that have been removed since last commit */
-	dc->hwss.reset_hw_ctx_wrap(dc, context);
-
-	/* Skip applying if no targets */
-	if (context->stream_count <= 0)
-		return DC_OK;
-
-	/* Apply new context */
-	dcb->funcs->set_scratch_critical_state(dcb, true);
 
-	/* below is for real asic only */
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *pipe_ctx_old =
-					&dc->current_state->res_ctx.pipe_ctx[i];
-		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
-
-		if (pipe_ctx->stream == NULL || pipe_ctx->top_pipe)
-			continue;
-
-		if (pipe_ctx->stream == pipe_ctx_old->stream) {
-			if (pipe_ctx_old->clock_source != pipe_ctx->clock_source)
-				dce_crtc_switch_to_clk_src(dc->hwseq,
-						pipe_ctx->clock_source, i);
-			continue;
-		}
-
-		dc->hwss.enable_display_power_gating(
-				dc, i, dc->ctx->dc_bios,
-				PIPE_GATING_CONTROL_DISABLE);
-	}
-
-	set_safe_displaymarks(&context->res_ctx, dc->res_pool);
-
-#if defined(CONFIG_DRM_AMD_DC_FBC)
-	if (dc->fbc_compressor)
-		dc->fbc_compressor->funcs->disable_fbc(dc->fbc_compressor);
-#endif
-	/*TODO: when pplib works*/
-	apply_min_clocks(dc, context, &clocks_state, true);
-
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
-	if (dc->ctx->dce_version >= DCN_VERSION_1_0) {
-		if (context->bw.dcn.calc_clk.fclk_khz
-				> dc->current_state->bw.dcn.cur_clk.fclk_khz) {
-			struct dm_pp_clock_for_voltage_req clock;
-
-			clock.clk_type = DM_PP_CLOCK_TYPE_FCLK;
-			clock.clocks_in_khz = context->bw.dcn.calc_clk.fclk_khz;
-			dm_pp_apply_clock_for_voltage_request(dc->ctx, &clock);
-			dc->current_state->bw.dcn.cur_clk.fclk_khz = clock.clocks_in_khz;
-			context->bw.dcn.cur_clk.fclk_khz = clock.clocks_in_khz;
-		}
-		if (context->bw.dcn.calc_clk.dcfclk_khz
-				> dc->current_state->bw.dcn.cur_clk.dcfclk_khz) {
-			struct dm_pp_clock_for_voltage_req clock;
-
-			clock.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
-			clock.clocks_in_khz = context->bw.dcn.calc_clk.dcfclk_khz;
-			dm_pp_apply_clock_for_voltage_request(dc->ctx, &clock);
-			dc->current_state->bw.dcn.cur_clk.dcfclk_khz = clock.clocks_in_khz;
-			context->bw.dcn.cur_clk.dcfclk_khz = clock.clocks_in_khz;
-		}
-		if (context->bw.dcn.calc_clk.dispclk_khz
-				> dc->current_state->bw.dcn.cur_clk.dispclk_khz) {
-			dc->res_pool->display_clock->funcs->set_clock(
-					dc->res_pool->display_clock,
-					context->bw.dcn.calc_clk.dispclk_khz);
-			dc->current_state->bw.dcn.cur_clk.dispclk_khz =
-					context->bw.dcn.calc_clk.dispclk_khz;
-			context->bw.dcn.cur_clk.dispclk_khz =
-					context->bw.dcn.calc_clk.dispclk_khz;
-		}
-	} else
-#endif
-	if (context->bw.dce.dispclk_khz
-			> dc->current_state->bw.dce.dispclk_khz) {
-		dc->res_pool->display_clock->funcs->set_clock(
-				dc->res_pool->display_clock,
-				context->bw.dce.dispclk_khz * 115 / 100);
-	}
 	/* program audio wall clock. use HDMI as clock source if HDMI
 	 * audio active. Otherwise, use DP as clock source
 	 * first, loop to find any HDMI audio, if not, loop find DP audio
@@ -2113,6 +1997,52 @@ enum dc_status dce110_apply_ctx_to_hw(
 			}
 		}
 	}
+}
+
+enum dc_status dce110_apply_ctx_to_hw(
+		struct dc *dc,
+		struct dc_state *context)
+{
+	struct dc_bios *dcb = dc->ctx->dc_bios;
+	enum dc_status status;
+	int i;
+
+	/* Reset old context */
+	/* look up the targets that have been removed since last commit */
+	dc->hwss.reset_hw_ctx_wrap(dc, context);
+
+	/* Skip applying if no targets */
+	if (context->stream_count <= 0)
+		return DC_OK;
+
+	/* Apply new context */
+	dcb->funcs->set_scratch_critical_state(dcb, true);
+
+	/* below is for real asic only */
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe_ctx_old =
+					&dc->current_state->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+		if (pipe_ctx->stream == NULL || pipe_ctx->top_pipe)
+			continue;
+
+		if (pipe_ctx->stream == pipe_ctx_old->stream) {
+			if (pipe_ctx_old->clock_source != pipe_ctx->clock_source)
+				dce_crtc_switch_to_clk_src(dc->hwseq,
+						pipe_ctx->clock_source, i);
+			continue;
+		}
+
+		dc->hwss.enable_display_power_gating(
+				dc, i, dc->ctx->dc_bios,
+				PIPE_GATING_CONTROL_DISABLE);
+	}
+
+	if (dc->fbc_compressor)
+		dc->fbc_compressor->funcs->disable_fbc(dc->fbc_compressor);
+
+	dce110_setup_audio_dto(dc, context);
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe_ctx_old =
@@ -2131,31 +2061,6 @@ enum dc_status dce110_apply_ctx_to_hw(
 		if (pipe_ctx->top_pipe)
 			continue;
 
-		if (context->res_ctx.pipe_ctx[i].stream_res.audio != NULL) {
-
-			struct audio_output audio_output;
-
-			build_audio_output(context, pipe_ctx, &audio_output);
-
-			if (dc_is_dp_signal(pipe_ctx->stream->signal))
-				pipe_ctx->stream_res.stream_enc->funcs->dp_audio_setup(
-						pipe_ctx->stream_res.stream_enc,
-						pipe_ctx->stream_res.audio->inst,
-						&pipe_ctx->stream->audio_info);
-			else
-				pipe_ctx->stream_res.stream_enc->funcs->hdmi_audio_setup(
-						pipe_ctx->stream_res.stream_enc,
-						pipe_ctx->stream_res.audio->inst,
-						&pipe_ctx->stream->audio_info,
-						&audio_output.crtc_info);
-
-			pipe_ctx->stream_res.audio->funcs->az_configure(
-					pipe_ctx->stream_res.audio,
-					pipe_ctx->stream->signal,
-					&audio_output.crtc_info,
-					&pipe_ctx->stream->audio_info);
-		}
-
 		status = apply_single_controller_ctx_to_hw(
 				pipe_ctx,
 				context,
@@ -2165,17 +2070,11 @@ enum dc_status dce110_apply_ctx_to_hw(
 			return status;
 	}
 
-	/* to save power */
-	apply_min_clocks(dc, context, &clocks_state, false);
-
 	dcb->funcs->set_scratch_critical_state(dcb, false);
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 	if (dc->fbc_compressor)
 		enable_fbc(dc, context);
 
-#endif
-
 	return DC_OK;
 }
 
@@ -2490,10 +2389,9 @@ static void init_hw(struct dc *dc)
 		abm->funcs->init_backlight(abm);
 		abm->funcs->abm_init(abm);
 	}
-#if defined(CONFIG_DRM_AMD_DC_FBC)
+
 	if (dc->fbc_compressor)
 		dc->fbc_compressor->funcs->power_up_fbc(dc->fbc_compressor);
-#endif
 
 }
 
@@ -2632,7 +2530,7 @@ static void pplib_apply_display_requirements(
 	/* TODO: dce11.2*/
 	pp_display_cfg->avail_mclk_switch_time_in_disp_active_us = 0;
 
-	pp_display_cfg->disp_clk_khz = context->bw.dce.dispclk_khz;
+	pp_display_cfg->disp_clk_khz = dc->res_pool->dccg->clks.dispclk_khz;
 
 	dce110_fill_display_configs(context, pp_display_cfg);
 
@@ -2654,20 +2552,25 @@ static void pplib_apply_display_requirements(
 	dc->prev_display_config = *pp_display_cfg;
 }
 
-static void dce110_set_bandwidth(
+void dce110_set_bandwidth(
 		struct dc *dc,
 		struct dc_state *context,
 		bool decrease_allowed)
 {
-	dce110_set_displaymarks(dc, context);
+	struct dc_clocks req_clks;
 
-	if (decrease_allowed || context->bw.dce.dispclk_khz > dc->current_state->bw.dce.dispclk_khz) {
-		dc->res_pool->display_clock->funcs->set_clock(
-				dc->res_pool->display_clock,
-				context->bw.dce.dispclk_khz * 115 / 100);
-		dc->current_state->bw.dce.dispclk_khz = context->bw.dce.dispclk_khz;
-	}
+	req_clks.dispclk_khz = context->bw.dce.dispclk_khz;
+	req_clks.phyclk_khz = get_max_pixel_clock_for_all_paths(dc, context);
+
+	if (decrease_allowed)
+		dce110_set_displaymarks(dc, context);
+	else
+		dce110_set_safe_displaymarks(&context->res_ctx, dc->res_pool);
 
+	dc->res_pool->dccg->funcs->update_clocks(
+			dc->res_pool->dccg,
+			&req_clks,
+			decrease_allowed);
 	pplib_apply_display_requirements(dc, context);
 }
 
@@ -2679,9 +2582,7 @@ static void dce110_program_front_end_for_pipe(
 	struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 	struct xfm_grph_csc_adjustment adjust;
 	struct out_csc_color_matrix tbl_entry;
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 	unsigned int underlay_idx = dc->res_pool->underlay_pipe_index;
-#endif
 	unsigned int i;
 	DC_LOGGER_INIT();
 	memset(&tbl_entry, 0, sizeof(tbl_entry));
@@ -2722,7 +2623,6 @@ static void dce110_program_front_end_for_pipe(
 
 	program_scaler(dc, pipe_ctx);
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 	/* fbc not applicable on Underlay pipe */
 	if (dc->fbc_compressor && old_pipe->stream &&
 	    pipe_ctx->pipe_idx != underlay_idx) {
@@ -2731,7 +2631,6 @@ static void dce110_program_front_end_for_pipe(
 		else
 			enable_fbc(dc, dc->current_state);
 	}
-#endif
 
 	mi->funcs->mem_input_program_surface_config(
 			mi,
@@ -2907,9 +2806,11 @@ void dce110_set_cursor_position(struct pipe_ctx *pipe_ctx)
 	struct dc_cursor_mi_param param = {
 		.pixel_clk_khz = pipe_ctx->stream->timing.pix_clk_khz,
 		.ref_clk_khz = pipe_ctx->stream->ctx->dc->res_pool->ref_clock_inKhz,
-		.viewport_x_start = pipe_ctx->plane_res.scl_data.viewport.x,
-		.viewport_width = pipe_ctx->plane_res.scl_data.viewport.width,
-		.h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz
+		.viewport = pipe_ctx->plane_res.scl_data.viewport,
+		.h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz,
+		.v_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.vert,
+		.rotation = pipe_ctx->plane_state->rotation,
+		.mirror = pipe_ctx->plane_state->horizontal_mirror
 	};
 
 	if (pipe_ctx->plane_state->address.type
@@ -2968,6 +2869,8 @@ static const struct hw_sequencer_funcs dce110_funcs = {
 	.disable_stream = dce110_disable_stream,
 	.unblank_stream = dce110_unblank_stream,
 	.blank_stream = dce110_blank_stream,
+	.enable_audio_stream = dce110_enable_audio_stream,
+	.disable_audio_stream = dce110_disable_audio_stream,
 	.enable_display_pipe_clock_gating = enable_display_pipe_clock_gating,
 	.enable_display_power_gating = dce110_enable_display_power_gating,
 	.disable_plane = dce110_power_down_fe,
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
index 5d7e9f516827..e4c5db75c4c6 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
@@ -49,6 +49,10 @@ void dce110_unblank_stream(struct pipe_ctx *pipe_ctx,
 		struct dc_link_settings *link_settings);
 
 void dce110_blank_stream(struct pipe_ctx *pipe_ctx);
+
+void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx);
+void dce110_disable_audio_stream(struct pipe_ctx *pipe_ctx, int option);
+
 void dce110_update_info_frame(struct pipe_ctx *pipe_ctx);
 
 void dce110_set_avmute(struct pipe_ctx *pipe_ctx, bool enable);
@@ -56,10 +60,19 @@ void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context);
 
 void dce110_power_down(struct dc *dc);
 
+void dce110_set_safe_displaymarks(
+		struct resource_context *res_ctx,
+		const struct resource_pool *pool);
+
 void dce110_fill_display_configs(
 	const struct dc_state *context,
 	struct dm_pp_display_configuration *pp_display_cfg);
 
+void dce110_set_bandwidth(
+		struct dc *dc,
+		struct dc_state *context,
+		bool decrease_allowed);
+
 uint32_t dce110_get_min_vblank_time_us(const struct dc_state *context);
 
 void dp_receiver_power_ctrl(struct dc_link *link, bool on);
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c
index 0564c8e31252..9b9fc3d96c07 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c
@@ -1011,7 +1011,7 @@ void dce110_free_mem_input_v(
 {
 }
 
-static struct mem_input_funcs dce110_mem_input_v_funcs = {
+static const struct mem_input_funcs dce110_mem_input_v_funcs = {
 	.mem_input_program_display_marks =
 			dce_mem_input_v_program_display_marks,
 	.mem_input_program_chroma_display_marks =
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
index ee33786bdef6..e5e9e92521e9 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -49,14 +49,14 @@
 #include "dce/dce_clock_source.h"
 #include "dce/dce_hwseq.h"
 #include "dce110/dce110_hw_sequencer.h"
+#include "dce/dce_aux.h"
 #include "dce/dce_abm.h"
 #include "dce/dce_dmcu.h"
 
 #define DC_LOGGER \
 		dc->ctx->logger
-#if defined(CONFIG_DRM_AMD_DC_FBC)
+
 #include "dce110/dce110_compressor.h"
-#endif
 
 #include "reg_helper.h"
 
@@ -147,15 +147,15 @@ static const struct dce110_timing_generator_offsets dce110_tg_offsets[] = {
 #define SRI(reg_name, block, id)\
 	.reg_name = mm ## block ## id ## _ ## reg_name
 
-static const struct dce_disp_clk_registers disp_clk_regs = {
+static const struct dccg_registers disp_clk_regs = {
 		CLK_COMMON_REG_LIST_DCE_BASE()
 };
 
-static const struct dce_disp_clk_shift disp_clk_shift = {
+static const struct dccg_shift disp_clk_shift = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(__SHIFT)
 };
 
-static const struct dce_disp_clk_mask disp_clk_mask = {
+static const struct dccg_mask disp_clk_mask = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(_MASK)
 };
 
@@ -307,6 +307,21 @@ static const struct dce_opp_mask opp_mask = {
 	OPP_COMMON_MASK_SH_LIST_DCE_110(_MASK)
 };
 
+#define aux_engine_regs(id)\
+[id] = {\
+	AUX_COMMON_REG_LIST(id), \
+	.AUX_RESET_MASK = 0 \
+}
+
+static const struct dce110_aux_registers aux_engine_regs[] = {
+		aux_engine_regs(0),
+		aux_engine_regs(1),
+		aux_engine_regs(2),
+		aux_engine_regs(3),
+		aux_engine_regs(4),
+		aux_engine_regs(5)
+};
+
 #define audio_regs(id)\
 [id] = {\
 	AUD_COMMON_REG_LIST(id)\
@@ -589,6 +604,23 @@ static struct output_pixel_processor *dce110_opp_create(
 	return &opp->base;
 }
 
+struct aux_engine *dce110_aux_engine_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct aux_engine_dce110 *aux_engine =
+		kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL);
+
+	if (!aux_engine)
+		return NULL;
+
+	dce110_aux_engine_construct(aux_engine, ctx, inst,
+				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
+				    &aux_engine_regs[inst]);
+
+	return &aux_engine->base;
+}
+
 struct clock_source *dce110_clock_source_create(
 	struct dc_context *ctx,
 	struct dc_bios *bios,
@@ -652,6 +684,10 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+
+		if (pool->base.engines[i] != NULL)
+			dce110_engine_destroy(&pool->base.engines[i]);
+
 	}
 
 	for (i = 0; i < pool->base.stream_enc_count; i++) {
@@ -680,8 +716,8 @@ static void destruct(struct dce110_resource_pool *pool)
 	if (pool->base.dmcu != NULL)
 		dce_dmcu_destroy(&pool->base.dmcu);
 
-	if (pool->base.display_clock != NULL)
-		dce_disp_clk_destroy(&pool->base.display_clock);
+	if (pool->base.dccg != NULL)
+		dce_dccg_destroy(&pool->base.dccg);
 
 	if (pool->base.irqs != NULL) {
 		dal_irq_service_destroy(&pool->base.irqs);
@@ -795,43 +831,38 @@ static bool dce110_validate_bandwidth(
 
 	if (memcmp(&dc->current_state->bw.dce,
 			&context->bw.dce, sizeof(context->bw.dce))) {
-		struct log_entry log_entry;
-		dm_logger_open(
-			dc->ctx->logger,
-			&log_entry,
-			LOG_BANDWIDTH_CALCS);
-		dm_logger_append(&log_entry, "%s: finish,\n"
+
+		DC_LOG_BANDWIDTH_CALCS(
+			"%s: finish,\n"
+			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
+			"stutMark_b: %d stutMark_a: %d\n"
+			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
+			"stutMark_b: %d stutMark_a: %d\n"
 			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
-			"stutMark_b: %d stutMark_a: %d\n",
+			"stutMark_b: %d stutMark_a: %d stutter_mode_enable: %d\n"
+			"cstate: %d pstate: %d nbpstate: %d sync: %d dispclk: %d\n"
+			"sclk: %d sclk_sleep: %d yclk: %d blackout_recovery_time_us: %d\n"
+			,
 			__func__,
 			context->bw.dce.nbp_state_change_wm_ns[0].b_mark,
 			context->bw.dce.nbp_state_change_wm_ns[0].a_mark,
 			context->bw.dce.urgent_wm_ns[0].b_mark,
 			context->bw.dce.urgent_wm_ns[0].a_mark,
 			context->bw.dce.stutter_exit_wm_ns[0].b_mark,
-			context->bw.dce.stutter_exit_wm_ns[0].a_mark);
-		dm_logger_append(&log_entry,
-			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
-			"stutMark_b: %d stutMark_a: %d\n",
+			context->bw.dce.stutter_exit_wm_ns[0].a_mark,
 			context->bw.dce.nbp_state_change_wm_ns[1].b_mark,
 			context->bw.dce.nbp_state_change_wm_ns[1].a_mark,
 			context->bw.dce.urgent_wm_ns[1].b_mark,
 			context->bw.dce.urgent_wm_ns[1].a_mark,
 			context->bw.dce.stutter_exit_wm_ns[1].b_mark,
-			context->bw.dce.stutter_exit_wm_ns[1].a_mark);
-		dm_logger_append(&log_entry,
-			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
-			"stutMark_b: %d stutMark_a: %d stutter_mode_enable: %d\n",
+			context->bw.dce.stutter_exit_wm_ns[1].a_mark,
 			context->bw.dce.nbp_state_change_wm_ns[2].b_mark,
 			context->bw.dce.nbp_state_change_wm_ns[2].a_mark,
 			context->bw.dce.urgent_wm_ns[2].b_mark,
 			context->bw.dce.urgent_wm_ns[2].a_mark,
 			context->bw.dce.stutter_exit_wm_ns[2].b_mark,
 			context->bw.dce.stutter_exit_wm_ns[2].a_mark,
-			context->bw.dce.stutter_mode_enable);
-		dm_logger_append(&log_entry,
-			"cstate: %d pstate: %d nbpstate: %d sync: %d dispclk: %d\n"
-			"sclk: %d sclk_sleep: %d yclk: %d blackout_recovery_time_us: %d\n",
+			context->bw.dce.stutter_mode_enable,
 			context->bw.dce.cpuc_state_change_enable,
 			context->bw.dce.cpup_state_change_enable,
 			context->bw.dce.nbp_state_change_enable,
@@ -841,7 +872,6 @@ static bool dce110_validate_bandwidth(
 			context->bw.dce.sclk_deep_sleep_khz,
 			context->bw.dce.yclk_khz,
 			context->bw.dce.blackout_recovery_time_us);
-		dm_logger_close(&log_entry);
 	}
 	return result;
 }
@@ -1180,11 +1210,11 @@ static bool construct(
 		}
 	}
 
-	pool->base.display_clock = dce110_disp_clk_create(ctx,
+	pool->base.dccg = dce110_dccg_create(ctx,
 			&disp_clk_regs,
 			&disp_clk_shift,
 			&disp_clk_mask);
-	if (pool->base.display_clock == NULL) {
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto res_create_fail;
@@ -1214,7 +1244,7 @@ static bool construct(
 	 * max_clock_state
 	 */
 	if (dm_pp_get_static_clocks(ctx, &static_clk_info))
-		pool->base.display_clock->max_clks_state =
+		pool->base.dccg->max_clks_state =
 				static_clk_info.max_clocks_state;
 
 	{
@@ -1265,14 +1295,18 @@ static bool construct(
 				"DC: failed to create output pixel processor!\n");
 			goto res_create_fail;
 		}
+
+		pool->base.engines[i] = dce110_aux_engine_create(ctx, i);
+		if (pool->base.engines[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create aux engine!!\n");
+			goto res_create_fail;
+		}
 	}
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 	dc->fbc_compressor = dce110_compressor_create(ctx);
 
-
-
-#endif
 	if (!underlay_create(ctx, &pool->base))
 		goto res_create_fail;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_transform_v.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_transform_v.c
index a7dce060204f..aa8d6b10d2c3 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_transform_v.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_transform_v.c
@@ -235,7 +235,7 @@ static void program_overscan(
 	int overscan_right = data->h_active - data->recout.x - data->recout.width;
 	int overscan_bottom = data->v_active - data->recout.y - data->recout.height;
 
-	if (xfm_dce->base.ctx->dc->debug.surface_visual_confirm) {
+	if (xfm_dce->base.ctx->dc->debug.visual_confirm != VISUAL_CONFIRM_DISABLE) {
 		overscan_bottom += 2;
 		overscan_right += 2;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
index 00c0a1ef15eb..288129343c77 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -49,6 +49,7 @@
 #include "dce112/dce112_hw_sequencer.h"
 #include "dce/dce_abm.h"
 #include "dce/dce_dmcu.h"
+#include "dce/dce_aux.h"
 
 #include "reg_helper.h"
 
@@ -146,15 +147,15 @@ static const struct dce110_timing_generator_offsets dce112_tg_offsets[] = {
 	.reg_name = mm ## block ## id ## _ ## reg_name
 
 
-static const struct dce_disp_clk_registers disp_clk_regs = {
+static const struct dccg_registers disp_clk_regs = {
 		CLK_COMMON_REG_LIST_DCE_BASE()
 };
 
-static const struct dce_disp_clk_shift disp_clk_shift = {
+static const struct dccg_shift disp_clk_shift = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(__SHIFT)
 };
 
-static const struct dce_disp_clk_mask disp_clk_mask = {
+static const struct dccg_mask disp_clk_mask = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(_MASK)
 };
 
@@ -314,6 +315,21 @@ static const struct dce_opp_mask opp_mask = {
 	OPP_COMMON_MASK_SH_LIST_DCE_112(_MASK)
 };
 
+#define aux_engine_regs(id)\
+[id] = {\
+	AUX_COMMON_REG_LIST(id), \
+	.AUX_RESET_MASK = 0 \
+}
+
+static const struct dce110_aux_registers aux_engine_regs[] = {
+		aux_engine_regs(0),
+		aux_engine_regs(1),
+		aux_engine_regs(2),
+		aux_engine_regs(3),
+		aux_engine_regs(4),
+		aux_engine_regs(5)
+};
+
 #define audio_regs(id)\
 [id] = {\
 	AUD_COMMON_REG_LIST(id)\
@@ -588,6 +604,23 @@ struct output_pixel_processor *dce112_opp_create(
 	return &opp->base;
 }
 
+struct aux_engine *dce112_aux_engine_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct aux_engine_dce110 *aux_engine =
+		kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL);
+
+	if (!aux_engine)
+		return NULL;
+
+	dce110_aux_engine_construct(aux_engine, ctx, inst,
+				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
+				    &aux_engine_regs[inst]);
+
+	return &aux_engine->base;
+}
+
 struct clock_source *dce112_clock_source_create(
 	struct dc_context *ctx,
 	struct dc_bios *bios,
@@ -625,6 +658,9 @@ static void destruct(struct dce110_resource_pool *pool)
 		if (pool->base.opps[i] != NULL)
 			dce110_opp_destroy(&pool->base.opps[i]);
 
+		if (pool->base.engines[i] != NULL)
+			dce110_engine_destroy(&pool->base.engines[i]);
+
 		if (pool->base.transforms[i] != NULL)
 			dce112_transform_destroy(&pool->base.transforms[i]);
 
@@ -640,6 +676,7 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+
 	}
 
 	for (i = 0; i < pool->base.stream_enc_count; i++) {
@@ -668,8 +705,8 @@ static void destruct(struct dce110_resource_pool *pool)
 	if (pool->base.dmcu != NULL)
 		dce_dmcu_destroy(&pool->base.dmcu);
 
-	if (pool->base.display_clock != NULL)
-		dce_disp_clk_destroy(&pool->base.display_clock);
+	if (pool->base.dccg != NULL)
+		dce_dccg_destroy(&pool->base.dccg);
 
 	if (pool->base.irqs != NULL) {
 		dal_irq_service_destroy(&pool->base.irqs);
@@ -744,43 +781,38 @@ bool dce112_validate_bandwidth(
 
 	if (memcmp(&dc->current_state->bw.dce,
 			&context->bw.dce, sizeof(context->bw.dce))) {
-		struct log_entry log_entry;
-		dm_logger_open(
-			dc->ctx->logger,
-			&log_entry,
-			LOG_BANDWIDTH_CALCS);
-		dm_logger_append(&log_entry, "%s: finish,\n"
+
+		DC_LOG_BANDWIDTH_CALCS(
+			"%s: finish,\n"
+			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
+			"stutMark_b: %d stutMark_a: %d\n"
 			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
-			"stutMark_b: %d stutMark_a: %d\n",
+			"stutMark_b: %d stutMark_a: %d\n"
+			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
+			"stutMark_b: %d stutMark_a: %d stutter_mode_enable: %d\n"
+			"cstate: %d pstate: %d nbpstate: %d sync: %d dispclk: %d\n"
+			"sclk: %d sclk_sleep: %d yclk: %d blackout_recovery_time_us: %d\n"
+			,
 			__func__,
 			context->bw.dce.nbp_state_change_wm_ns[0].b_mark,
 			context->bw.dce.nbp_state_change_wm_ns[0].a_mark,
 			context->bw.dce.urgent_wm_ns[0].b_mark,
 			context->bw.dce.urgent_wm_ns[0].a_mark,
 			context->bw.dce.stutter_exit_wm_ns[0].b_mark,
-			context->bw.dce.stutter_exit_wm_ns[0].a_mark);
-		dm_logger_append(&log_entry,
-			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
-			"stutMark_b: %d stutMark_a: %d\n",
+			context->bw.dce.stutter_exit_wm_ns[0].a_mark,
 			context->bw.dce.nbp_state_change_wm_ns[1].b_mark,
 			context->bw.dce.nbp_state_change_wm_ns[1].a_mark,
 			context->bw.dce.urgent_wm_ns[1].b_mark,
 			context->bw.dce.urgent_wm_ns[1].a_mark,
 			context->bw.dce.stutter_exit_wm_ns[1].b_mark,
-			context->bw.dce.stutter_exit_wm_ns[1].a_mark);
-		dm_logger_append(&log_entry,
-			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
-			"stutMark_b: %d stutMark_a: %d stutter_mode_enable: %d\n",
+			context->bw.dce.stutter_exit_wm_ns[1].a_mark,
 			context->bw.dce.nbp_state_change_wm_ns[2].b_mark,
 			context->bw.dce.nbp_state_change_wm_ns[2].a_mark,
 			context->bw.dce.urgent_wm_ns[2].b_mark,
 			context->bw.dce.urgent_wm_ns[2].a_mark,
 			context->bw.dce.stutter_exit_wm_ns[2].b_mark,
 			context->bw.dce.stutter_exit_wm_ns[2].a_mark,
-			context->bw.dce.stutter_mode_enable);
-		dm_logger_append(&log_entry,
-			"cstate: %d pstate: %d nbpstate: %d sync: %d dispclk: %d\n"
-			"sclk: %d sclk_sleep: %d yclk: %d blackout_recovery_time_us: %d\n",
+			context->bw.dce.stutter_mode_enable,
 			context->bw.dce.cpuc_state_change_enable,
 			context->bw.dce.cpup_state_change_enable,
 			context->bw.dce.nbp_state_change_enable,
@@ -790,7 +822,6 @@ bool dce112_validate_bandwidth(
 			context->bw.dce.sclk_deep_sleep_khz,
 			context->bw.dce.yclk_khz,
 			context->bw.dce.blackout_recovery_time_us);
-		dm_logger_close(&log_entry);
 	}
 	return result;
 }
@@ -1000,7 +1031,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[0].wm_max_eng_clk_in_khz =
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz - 1;
-	clk_ranges.wm_clk_ranges[0].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[0].wm_min_mem_clk_in_khz =
 			mem_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[0].wm_max_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz - 1;
@@ -1010,7 +1041,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz;
 	/* 5 GHz instead of data[7].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[1].wm_max_eng_clk_in_khz = 5000000;
-	clk_ranges.wm_clk_ranges[1].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[1].wm_min_mem_clk_in_khz =
 			mem_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[1].wm_max_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz - 1;
@@ -1020,7 +1051,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[2].wm_max_eng_clk_in_khz =
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz - 1;
-	clk_ranges.wm_clk_ranges[2].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[2].wm_min_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz;
 	/* 5 GHz instead of data[2].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[2].wm_max_mem_clk_in_khz = 5000000;
@@ -1030,7 +1061,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz;
 	/* 5 GHz instead of data[7].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[3].wm_max_eng_clk_in_khz = 5000000;
-	clk_ranges.wm_clk_ranges[3].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[3].wm_min_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz;
 	/* 5 GHz instead of data[2].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[3].wm_max_mem_clk_in_khz = 5000000;
@@ -1124,11 +1155,11 @@ static bool construct(
 		}
 	}
 
-	pool->base.display_clock = dce112_disp_clk_create(ctx,
+	pool->base.dccg = dce112_dccg_create(ctx,
 			&disp_clk_regs,
 			&disp_clk_shift,
 			&disp_clk_mask);
-	if (pool->base.display_clock == NULL) {
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto res_create_fail;
@@ -1158,7 +1189,7 @@ static bool construct(
 	 * max_clock_state
 	 */
 	if (dm_pp_get_static_clocks(ctx, &static_clk_info))
-		pool->base.display_clock->max_clks_state =
+		pool->base.dccg->max_clks_state =
 				static_clk_info.max_clocks_state;
 
 	{
@@ -1214,6 +1245,13 @@ static bool construct(
 				"DC:failed to create output pixel processor!\n");
 			goto res_create_fail;
 		}
+		pool->base.engines[i] = dce112_aux_engine_create(ctx, i);
+		if (pool->base.engines[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create aux engine!!\n");
+			goto res_create_fail;
+		}
 	}
 
 	if (!resource_construct(num_virtual_links, dc, &pool->base,
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c
index e96ff86d2fc3..5853522a6182 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c
@@ -244,7 +244,16 @@ static void dce120_update_dchub(
 	dh_data->dchub_info_valid = false;
 }
 
+static void dce120_set_bandwidth(
+		struct dc *dc,
+		struct dc_state *context,
+		bool decrease_allowed)
+{
+	if (context->stream_count <= 0)
+		return;
 
+	dce110_set_bandwidth(dc, context, decrease_allowed);
+}
 
 void dce120_hw_sequencer_construct(struct dc *dc)
 {
@@ -254,5 +263,6 @@ void dce120_hw_sequencer_construct(struct dc *dc)
 	dce110_hw_sequencer_construct(dc);
 	dc->hwss.enable_display_power_gating = dce120_enable_display_power_gating;
 	dc->hwss.update_dchub = dce120_update_dchub;
+	dc->hwss.set_bandwidth = dce120_set_bandwidth;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
index 2d58daccc005..d43f37d99c7d 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
@@ -53,6 +53,7 @@
 #include "dce/dce_hwseq.h"
 #include "dce/dce_abm.h"
 #include "dce/dce_dmcu.h"
+#include "dce/dce_aux.h"
 
 #include "dce/dce_12_0_offset.h"
 #include "dce/dce_12_0_sh_mask.h"
@@ -297,6 +298,20 @@ static const struct dce_opp_shift opp_shift = {
 static const struct dce_opp_mask opp_mask = {
 	OPP_COMMON_MASK_SH_LIST_DCE_120(_MASK)
 };
+ #define aux_engine_regs(id)\
+[id] = {\
+	AUX_COMMON_REG_LIST(id), \
+	.AUX_RESET_MASK = 0 \
+}
+
+static const struct dce110_aux_registers aux_engine_regs[] = {
+		aux_engine_regs(0),
+		aux_engine_regs(1),
+		aux_engine_regs(2),
+		aux_engine_regs(3),
+		aux_engine_regs(4),
+		aux_engine_regs(5)
+};
 
 #define audio_regs(id)\
 [id] = {\
@@ -361,6 +376,22 @@ struct output_pixel_processor *dce120_opp_create(
 			     ctx, inst, &opp_regs[inst], &opp_shift, &opp_mask);
 	return &opp->base;
 }
+struct aux_engine *dce120_aux_engine_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct aux_engine_dce110 *aux_engine =
+		kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL);
+
+	if (!aux_engine)
+		return NULL;
+
+	dce110_aux_engine_construct(aux_engine, ctx, inst,
+				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
+				    &aux_engine_regs[inst]);
+
+	return &aux_engine->base;
+}
 
 static const struct bios_registers bios_regs = {
 	.BIOS_SCRATCH_6 = mmBIOS_SCRATCH_6 + NBIO_BASE(mmBIOS_SCRATCH_6_BASE_IDX)
@@ -373,7 +404,7 @@ static const struct resource_caps res_cap = {
 		.num_pll = 6,
 };
 
-static const struct dc_debug debug_defaults = {
+static const struct dc_debug_options debug_defaults = {
 		.disable_clock_gate = true,
 };
 
@@ -467,6 +498,10 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+
+		if (pool->base.engines[i] != NULL)
+			dce110_engine_destroy(&pool->base.engines[i]);
+
 	}
 
 	for (i = 0; i < pool->base.audio_count; i++) {
@@ -494,8 +529,8 @@ static void destruct(struct dce110_resource_pool *pool)
 	if (pool->base.dmcu != NULL)
 		dce_dmcu_destroy(&pool->base.dmcu);
 
-	if (pool->base.display_clock != NULL)
-		dce_disp_clk_destroy(&pool->base.display_clock);
+	if (pool->base.dccg != NULL)
+		dce_dccg_destroy(&pool->base.dccg);
 }
 
 static void read_dce_straps(
@@ -775,7 +810,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[0].wm_max_eng_clk_in_khz =
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz - 1;
-	clk_ranges.wm_clk_ranges[0].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[0].wm_min_mem_clk_in_khz =
 			mem_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[0].wm_max_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz - 1;
@@ -785,7 +820,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz;
 	/* 5 GHz instead of data[7].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[1].wm_max_eng_clk_in_khz = 5000000;
-	clk_ranges.wm_clk_ranges[1].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[1].wm_min_mem_clk_in_khz =
 			mem_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[1].wm_max_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz - 1;
@@ -795,7 +830,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[2].wm_max_eng_clk_in_khz =
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz - 1;
-	clk_ranges.wm_clk_ranges[2].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[2].wm_min_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz;
 	/* 5 GHz instead of data[2].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[2].wm_max_mem_clk_in_khz = 5000000;
@@ -805,7 +840,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz;
 	/* 5 GHz instead of data[7].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[3].wm_max_eng_clk_in_khz = 5000000;
-	clk_ranges.wm_clk_ranges[3].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[3].wm_min_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz;
 	/* 5 GHz instead of data[2].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[3].wm_max_mem_clk_in_khz = 5000000;
@@ -848,6 +883,7 @@ static bool construct(
 	dc->caps.i2c_speed_in_khz = 100;
 	dc->caps.max_cursor_size = 128;
 	dc->caps.dual_link_dvi = true;
+	dc->caps.psp_setup_panel_mode = true;
 
 	dc->debug = debug_defaults;
 
@@ -894,11 +930,11 @@ static bool construct(
 		}
 	}
 
-	pool->base.display_clock = dce120_disp_clk_create(ctx);
-	if (pool->base.display_clock == NULL) {
+	pool->base.dccg = dce120_dccg_create(ctx);
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
-		goto disp_clk_create_fail;
+		goto dccg_create_fail;
 	}
 
 	pool->base.dmcu = dce_dmcu_create(ctx,
@@ -984,6 +1020,13 @@ static bool construct(
 			dm_error(
 				"DC: failed to create output pixel processor!\n");
 		}
+		pool->base.engines[i] = dce120_aux_engine_create(ctx, i);
+				if (pool->base.engines[i] == NULL) {
+					BREAK_TO_DEBUGGER();
+					dm_error(
+						"DC:failed to create aux engine!!\n");
+					goto res_create_fail;
+				}
 
 		/* check next valid pipe */
 		j++;
@@ -1011,7 +1054,7 @@ static bool construct(
 
 irqs_create_fail:
 controller_create_fail:
-disp_clk_create_fail:
+dccg_create_fail:
 clk_src_create_fail:
 res_create_fail:
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
index 48a068964722..604c62969ead 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
@@ -54,6 +54,7 @@
 #include "reg_helper.h"
 
 #include "dce/dce_dmcu.h"
+#include "dce/dce_aux.h"
 #include "dce/dce_abm.h"
 /* TODO remove this include */
 
@@ -153,15 +154,15 @@ static const struct dce110_timing_generator_offsets dce80_tg_offsets[] = {
 	.reg_name = mm ## block ## id ## _ ## reg_name
 
 
-static const struct dce_disp_clk_registers disp_clk_regs = {
+static const struct dccg_registers disp_clk_regs = {
 		CLK_COMMON_REG_LIST_DCE_BASE()
 };
 
-static const struct dce_disp_clk_shift disp_clk_shift = {
+static const struct dccg_shift disp_clk_shift = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(__SHIFT)
 };
 
-static const struct dce_disp_clk_mask disp_clk_mask = {
+static const struct dccg_mask disp_clk_mask = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(_MASK)
 };
 
@@ -298,6 +299,21 @@ static const struct dce_opp_mask opp_mask = {
 	OPP_COMMON_MASK_SH_LIST_DCE_80(_MASK)
 };
 
+#define aux_engine_regs(id)\
+[id] = {\
+	AUX_COMMON_REG_LIST(id), \
+	.AUX_RESET_MASK = 0 \
+}
+
+static const struct dce110_aux_registers aux_engine_regs[] = {
+		aux_engine_regs(0),
+		aux_engine_regs(1),
+		aux_engine_regs(2),
+		aux_engine_regs(3),
+		aux_engine_regs(4),
+		aux_engine_regs(5)
+};
+
 #define audio_regs(id)\
 [id] = {\
 	AUD_COMMON_REG_LIST(id)\
@@ -448,6 +464,23 @@ static struct output_pixel_processor *dce80_opp_create(
 	return &opp->base;
 }
 
+struct aux_engine *dce80_aux_engine_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct aux_engine_dce110 *aux_engine =
+		kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL);
+
+	if (!aux_engine)
+		return NULL;
+
+	dce110_aux_engine_construct(aux_engine, ctx, inst,
+				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
+				    &aux_engine_regs[inst]);
+
+	return &aux_engine->base;
+}
+
 static struct stream_encoder *dce80_stream_encoder_create(
 	enum engine_id eng_id,
 	struct dc_context *ctx)
@@ -655,6 +688,9 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+
+		if (pool->base.engines[i] != NULL)
+			dce110_engine_destroy(&pool->base.engines[i]);
 	}
 
 	for (i = 0; i < pool->base.stream_enc_count; i++) {
@@ -683,8 +719,8 @@ static void destruct(struct dce110_resource_pool *pool)
 		}
 	}
 
-	if (pool->base.display_clock != NULL)
-		dce_disp_clk_destroy(&pool->base.display_clock);
+	if (pool->base.dccg != NULL)
+		dce_dccg_destroy(&pool->base.dccg);
 
 	if (pool->base.irqs != NULL) {
 		dal_irq_service_destroy(&pool->base.irqs);
@@ -822,11 +858,11 @@ static bool dce80_construct(
 		}
 	}
 
-	pool->base.display_clock = dce_disp_clk_create(ctx,
+	pool->base.dccg = dce_dccg_create(ctx,
 			&disp_clk_regs,
 			&disp_clk_shift,
 			&disp_clk_mask);
-	if (pool->base.display_clock == NULL) {
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto res_create_fail;
@@ -852,7 +888,7 @@ static bool dce80_construct(
 		goto res_create_fail;
 	}
 	if (dm_pp_get_static_clocks(ctx, &static_clk_info))
-		pool->base.display_clock->max_clks_state =
+		pool->base.dccg->max_clks_state =
 					static_clk_info.max_clocks_state;
 
 	{
@@ -899,9 +935,18 @@ static bool dce80_construct(
 			dm_error("DC: failed to create output pixel processor!\n");
 			goto res_create_fail;
 		}
+
+		pool->base.engines[i] = dce80_aux_engine_create(ctx, i);
+		if (pool->base.engines[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create aux engine!!\n");
+			goto res_create_fail;
+		}
 	}
 
 	dc->caps.max_planes =  pool->base.pipe_count;
+	dc->caps.disable_dp_clk_share = true;
 
 	if (!resource_construct(num_virtual_links, dc, &pool->base,
 			&res_create_funcs))
@@ -1006,11 +1051,11 @@ static bool dce81_construct(
 		}
 	}
 
-	pool->base.display_clock = dce_disp_clk_create(ctx,
+	pool->base.dccg = dce_dccg_create(ctx,
 			&disp_clk_regs,
 			&disp_clk_shift,
 			&disp_clk_mask);
-	if (pool->base.display_clock == NULL) {
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto res_create_fail;
@@ -1037,7 +1082,7 @@ static bool dce81_construct(
 	}
 
 	if (dm_pp_get_static_clocks(ctx, &static_clk_info))
-		pool->base.display_clock->max_clks_state =
+		pool->base.dccg->max_clks_state =
 					static_clk_info.max_clocks_state;
 
 	{
@@ -1087,6 +1132,7 @@ static bool dce81_construct(
 	}
 
 	dc->caps.max_planes =  pool->base.pipe_count;
+	dc->caps.disable_dp_clk_share = true;
 
 	if (!resource_construct(num_virtual_links, dc, &pool->base,
 			&res_create_funcs))
@@ -1187,11 +1233,11 @@ static bool dce83_construct(
 		}
 	}
 
-	pool->base.display_clock = dce_disp_clk_create(ctx,
+	pool->base.dccg = dce_dccg_create(ctx,
 			&disp_clk_regs,
 			&disp_clk_shift,
 			&disp_clk_mask);
-	if (pool->base.display_clock == NULL) {
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto res_create_fail;
@@ -1218,7 +1264,7 @@ static bool dce83_construct(
 	}
 
 	if (dm_pp_get_static_clocks(ctx, &static_clk_info))
-		pool->base.display_clock->max_clks_state =
+		pool->base.dccg->max_clks_state =
 					static_clk_info.max_clocks_state;
 
 	{
@@ -1268,6 +1314,7 @@ static bool dce83_construct(
 	}
 
 	dc->caps.max_planes =  pool->base.pipe_count;
+	dc->caps.disable_dp_clk_share = true;
 
 	if (!resource_construct(num_virtual_links, dc, &pool->base,
 			&res_create_funcs))
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
index c69fa4bfab0a..bf8b68f8db4f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
@@ -145,10 +145,10 @@ static bool dpp_get_optimal_number_of_taps(
 		pixel_width = scl_data->viewport.width;
 
 	/* Some ASICs does not support  FP16 scaling, so we reject modes require this*/
-	if (scl_data->viewport.width  != scl_data->h_active &&
-		scl_data->viewport.height != scl_data->v_active &&
+	if (scl_data->format == PIXEL_FORMAT_FP16 &&
 		dpp->caps->dscl_data_proc_format == DSCL_DATA_PRCESSING_FIXED_FORMAT &&
-		scl_data->format == PIXEL_FORMAT_FP16)
+		scl_data->ratios.horz.value != dc_fixpt_one.value &&
+		scl_data->ratios.vert.value != dc_fixpt_one.value)
 		return false;
 
 	if (scl_data->viewport.width > scl_data->h_active &&
@@ -445,10 +445,10 @@ void dpp1_set_cursor_position(
 		uint32_t width)
 {
 	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
-	int src_x_offset = pos->x - pos->x_hotspot - param->viewport_x_start;
+	int src_x_offset = pos->x - pos->x_hotspot - param->viewport.x;
 	uint32_t cur_en = pos->enable ? 1 : 0;
 
-	if (src_x_offset >= (int)param->viewport_width)
+	if (src_x_offset >= (int)param->viewport.width)
 		cur_en = 0;  /* not visible beyond right edge*/
 
 	if (src_x_offset + (int)width <= 0)
@@ -459,6 +459,18 @@ void dpp1_set_cursor_position(
 
 }
 
+void dpp1_cnv_set_optional_cursor_attributes(
+		struct dpp *dpp_base,
+		struct dpp_cursor_attributes *attr)
+{
+	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+
+	if (attr) {
+		REG_UPDATE(CURSOR0_FP_SCALE_BIAS,  CUR0_FP_BIAS,  attr->bias);
+		REG_UPDATE(CURSOR0_FP_SCALE_BIAS,  CUR0_FP_SCALE, attr->scale);
+	}
+}
+
 void dpp1_dppclk_control(
 		struct dpp *dpp_base,
 		bool dppclk_div,
@@ -499,6 +511,7 @@ static const struct dpp_funcs dcn10_dpp_funcs = {
 		.dpp_full_bypass		= dpp1_full_bypass,
 		.set_cursor_attributes = dpp1_set_cursor_attributes,
 		.set_cursor_position = dpp1_set_cursor_position,
+		.set_optional_cursor_attributes = dpp1_cnv_set_optional_cursor_attributes,
 		.dpp_dppclk_control = dpp1_dppclk_control,
 		.dpp_set_hdr_multiplier = dpp1_set_hdr_multiplier,
 };
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
index e862cafa6501..e2889e61b18c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
@@ -119,6 +119,7 @@
 	SRI(CURSOR0_CONTROL, CNVC_CUR, id), \
 	SRI(CURSOR0_COLOR0, CNVC_CUR, id), \
 	SRI(CURSOR0_COLOR1, CNVC_CUR, id), \
+	SRI(CURSOR0_FP_SCALE_BIAS, CNVC_CUR, id), \
 	SRI(DPP_CONTROL, DPP_TOP, id), \
 	SRI(CM_HDR_MULT_COEF, CM, id)
 
@@ -324,6 +325,8 @@
 	TF_SF(CNVC_CUR0_CURSOR0_CONTROL, CUR0_ENABLE, mask_sh), \
 	TF_SF(CNVC_CUR0_CURSOR0_COLOR0, CUR0_COLOR0, mask_sh), \
 	TF_SF(CNVC_CUR0_CURSOR0_COLOR1, CUR0_COLOR1, mask_sh), \
+	TF_SF(CNVC_CUR0_CURSOR0_FP_SCALE_BIAS, CUR0_FP_BIAS, mask_sh), \
+	TF_SF(CNVC_CUR0_CURSOR0_FP_SCALE_BIAS, CUR0_FP_SCALE, mask_sh), \
 	TF_SF(DPP_TOP0_DPP_CONTROL, DPP_CLOCK_ENABLE, mask_sh), \
 	TF_SF(CM0_CM_HDR_MULT_COEF, CM_HDR_MULT_COEF, mask_sh)
 
@@ -1076,7 +1079,9 @@
 	type CUR0_COLOR1; \
 	type DPPCLK_RATE_CONTROL; \
 	type DPP_CLOCK_ENABLE; \
-	type CM_HDR_MULT_COEF;
+	type CM_HDR_MULT_COEF; \
+	type CUR0_FP_BIAS; \
+	type CUR0_FP_SCALE;
 
 struct dcn_dpp_shift {
 	TF_REG_FIELD_LIST(uint8_t)
@@ -1329,7 +1334,8 @@ struct dcn_dpp_mask {
 	uint32_t CURSOR0_COLOR0; \
 	uint32_t CURSOR0_COLOR1; \
 	uint32_t DPP_CONTROL; \
-	uint32_t CM_HDR_MULT_COEF;
+	uint32_t CM_HDR_MULT_COEF; \
+	uint32_t CURSOR0_FP_SCALE_BIAS;
 
 struct dcn_dpp_registers {
 	DPP_COMMON_REG_VARIABLE_LIST
@@ -1370,6 +1376,10 @@ void dpp1_set_cursor_position(
 		const struct dc_cursor_mi_param *param,
 		uint32_t width);
 
+void dpp1_cnv_set_optional_cursor_attributes(
+			struct dpp *dpp_base,
+			struct dpp_cursor_attributes *attr);
+
 bool dpp1_dscl_is_lb_conf_valid(
 		int ceil_vratio,
 		int num_partitions,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
index f862fd148cca..4a863a5dab41 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
@@ -621,6 +621,10 @@ static void dpp1_dscl_set_manual_ratio_init(
 static void dpp1_dscl_set_recout(
 			struct dcn10_dpp *dpp, const struct rect *recout)
 {
+	int visual_confirm_on = 0;
+	if (dpp->base.ctx->dc->debug.visual_confirm != VISUAL_CONFIRM_DISABLE)
+		visual_confirm_on = 1;
+
 	REG_SET_2(RECOUT_START, 0,
 		/* First pixel of RECOUT */
 			 RECOUT_START_X, recout->x,
@@ -632,8 +636,7 @@ static void dpp1_dscl_set_recout(
 			 RECOUT_WIDTH, recout->width,
 		/* Number of RECOUT vertical lines */
 			 RECOUT_HEIGHT, recout->height
-			 - dpp->base.ctx->dc->debug.surface_visual_confirm * 4 *
-			 (dpp->base.inst + 1));
+			 - visual_confirm_on * 4 * (dpp->base.inst + 1));
 }
 
 /* Main function to program scaler and line buffer in manual scaling mode */
@@ -655,6 +658,12 @@ void dpp1_dscl_set_scaler_manual_scale(
 
 	dpp->scl_data = *scl_data;
 
+	/* Autocal off */
+	REG_SET_3(DSCL_AUTOCAL, 0,
+		AUTOCAL_MODE, AUTOCAL_MODE_OFF,
+		AUTOCAL_NUM_PIPE, 0,
+		AUTOCAL_PIPE_ID, 0);
+
 	/* Recout */
 	dpp1_dscl_set_recout(dpp, &scl_data->recout);
 
@@ -678,12 +687,6 @@ void dpp1_dscl_set_scaler_manual_scale(
 	if (dscl_mode == DSCL_MODE_SCALING_444_BYPASS)
 		return;
 
-	/* Autocal off */
-	REG_SET_3(DSCL_AUTOCAL, 0,
-		AUTOCAL_MODE, AUTOCAL_MODE_OFF,
-		AUTOCAL_NUM_PIPE, 0,
-		AUTOCAL_PIPE_ID, 0);
-
 	/* Black offsets */
 	if (ycbcr)
 		REG_SET_2(SCL_BLACK_OFFSET, 0,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
index 943143efbb82..1ea91e153d3a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
@@ -190,10 +190,17 @@ static uint32_t convert_and_clamp(
 }
 
 
+void hubbub1_wm_change_req_wa(struct hubbub *hubbub)
+{
+	REG_UPDATE_SEQ(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
+			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, 0, 1);
+}
+
 void hubbub1_program_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
-		unsigned int refclk_mhz)
+		unsigned int refclk_mhz,
+		bool safe_to_lower)
 {
 	uint32_t force_en = hubbub->ctx->dc->debug.disable_stutter ? 1 : 0;
 	/*
@@ -202,191 +209,259 @@ void hubbub1_program_watermarks(
 	 */
 	uint32_t prog_wm_value;
 
-	REG_UPDATE(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
-			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, 0);
 
 	/* Repeat for water mark set A, B, C and D. */
 	/* clock state A */
-	prog_wm_value = convert_and_clamp(watermarks->a.urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_A, prog_wm_value);
-
-	DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_A calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->a.urgent_ns, prog_wm_value);
+	if (safe_to_lower || watermarks->a.urgent_ns > hubbub->watermarks.a.urgent_ns) {
+		hubbub->watermarks.a.urgent_ns = watermarks->a.urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->a.urgent_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_A, prog_wm_value);
 
-	prog_wm_value = convert_and_clamp(watermarks->a.pte_meta_urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_A, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_A calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->a.pte_meta_urgent_ns, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_A calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->a.urgent_ns, prog_wm_value);
+	}
 
-	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A)) {
-		prog_wm_value = convert_and_clamp(
-				watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns,
+	if (safe_to_lower || watermarks->a.pte_meta_urgent_ns > hubbub->watermarks.a.pte_meta_urgent_ns) {
+		hubbub->watermarks.a.pte_meta_urgent_ns = watermarks->a.pte_meta_urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->a.pte_meta_urgent_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_ENTER_EXIT_WATERMARK_A calculated =%d\n"
+		REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_A, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_A calculated =%d\n"
 			"HW register value = 0x%x\n",
-			watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+			watermarks->a.pte_meta_urgent_ns, prog_wm_value);
+	}
+
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A)) {
+		if (safe_to_lower || watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns
+				> hubbub->watermarks.a.cstate_pstate.cstate_enter_plus_exit_ns) {
+			hubbub->watermarks.a.cstate_pstate.cstate_enter_plus_exit_ns =
+					watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_ENTER_EXIT_WATERMARK_A calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+		}
 
+		if (safe_to_lower || watermarks->a.cstate_pstate.cstate_exit_ns
+				> hubbub->watermarks.a.cstate_pstate.cstate_exit_ns) {
+			hubbub->watermarks.a.cstate_pstate.cstate_exit_ns =
+					watermarks->a.cstate_pstate.cstate_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->a.cstate_pstate.cstate_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_A, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_A calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->a.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		}
+	}
 
+	if (safe_to_lower || watermarks->a.cstate_pstate.pstate_change_ns
+			> hubbub->watermarks.a.cstate_pstate.pstate_change_ns) {
+		hubbub->watermarks.a.cstate_pstate.pstate_change_ns =
+				watermarks->a.cstate_pstate.pstate_change_ns;
 		prog_wm_value = convert_and_clamp(
-				watermarks->a.cstate_pstate.cstate_exit_ns,
+				watermarks->a.cstate_pstate.pstate_change_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_A, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_A calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->a.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_A calculated =%d\n"
+			"HW register value = 0x%x\n\n",
+			watermarks->a.cstate_pstate.pstate_change_ns, prog_wm_value);
 	}
 
-	prog_wm_value = convert_and_clamp(
-			watermarks->a.cstate_pstate.pstate_change_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_A calculated =%d\n"
-		"HW register value = 0x%x\n\n",
-		watermarks->a.cstate_pstate.pstate_change_ns, prog_wm_value);
-
-
 	/* clock state B */
-	prog_wm_value = convert_and_clamp(
-			watermarks->b.urgent_ns, refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_B, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_B calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->b.urgent_ns, prog_wm_value);
-
-
-	prog_wm_value = convert_and_clamp(
-			watermarks->b.pte_meta_urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_B, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_B calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->b.pte_meta_urgent_ns, prog_wm_value);
+	if (safe_to_lower || watermarks->b.urgent_ns > hubbub->watermarks.b.urgent_ns) {
+		hubbub->watermarks.b.urgent_ns = watermarks->b.urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->b.urgent_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_B, prog_wm_value);
 
+		DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_B calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->b.urgent_ns, prog_wm_value);
+	}
 
-	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B)) {
-		prog_wm_value = convert_and_clamp(
-				watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns,
+	if (safe_to_lower || watermarks->b.pte_meta_urgent_ns > hubbub->watermarks.b.pte_meta_urgent_ns) {
+		hubbub->watermarks.b.pte_meta_urgent_ns = watermarks->b.pte_meta_urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->b.pte_meta_urgent_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_ENTER_WATERMARK_B calculated =%d\n"
+		REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_B, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_B calculated =%d\n"
 			"HW register value = 0x%x\n",
-			watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+			watermarks->b.pte_meta_urgent_ns, prog_wm_value);
+	}
+
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B)) {
+		if (safe_to_lower || watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns
+				> hubbub->watermarks.b.cstate_pstate.cstate_enter_plus_exit_ns) {
+			hubbub->watermarks.b.cstate_pstate.cstate_enter_plus_exit_ns =
+					watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_ENTER_EXIT_WATERMARK_B calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+		}
 
+		if (safe_to_lower || watermarks->b.cstate_pstate.cstate_exit_ns
+				> hubbub->watermarks.b.cstate_pstate.cstate_exit_ns) {
+			hubbub->watermarks.b.cstate_pstate.cstate_exit_ns =
+					watermarks->b.cstate_pstate.cstate_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->b.cstate_pstate.cstate_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_B, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_B calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->b.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		}
+	}
 
+	if (safe_to_lower || watermarks->b.cstate_pstate.pstate_change_ns
+			> hubbub->watermarks.b.cstate_pstate.pstate_change_ns) {
+		hubbub->watermarks.b.cstate_pstate.pstate_change_ns =
+				watermarks->b.cstate_pstate.pstate_change_ns;
 		prog_wm_value = convert_and_clamp(
-				watermarks->b.cstate_pstate.cstate_exit_ns,
+				watermarks->b.cstate_pstate.pstate_change_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_B, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_B calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->b.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_B calculated =%d\n"
+			"HW register value = 0x%x\n\n",
+			watermarks->b.cstate_pstate.pstate_change_ns, prog_wm_value);
 	}
 
-	prog_wm_value = convert_and_clamp(
-			watermarks->b.cstate_pstate.pstate_change_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_B calculated =%d\n\n"
-		"HW register value = 0x%x\n",
-		watermarks->b.cstate_pstate.pstate_change_ns, prog_wm_value);
-
 	/* clock state C */
-	prog_wm_value = convert_and_clamp(
-			watermarks->c.urgent_ns, refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_C, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_C calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->c.urgent_ns, prog_wm_value);
-
-
-	prog_wm_value = convert_and_clamp(
-			watermarks->c.pte_meta_urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_C, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_C calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->c.pte_meta_urgent_ns, prog_wm_value);
+	if (safe_to_lower || watermarks->c.urgent_ns > hubbub->watermarks.c.urgent_ns) {
+		hubbub->watermarks.c.urgent_ns = watermarks->c.urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->c.urgent_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_C, prog_wm_value);
 
+		DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_C calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->c.urgent_ns, prog_wm_value);
+	}
 
-	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C)) {
-		prog_wm_value = convert_and_clamp(
-				watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns,
+	if (safe_to_lower || watermarks->c.pte_meta_urgent_ns > hubbub->watermarks.c.pte_meta_urgent_ns) {
+		hubbub->watermarks.c.pte_meta_urgent_ns = watermarks->c.pte_meta_urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->c.pte_meta_urgent_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_ENTER_WATERMARK_C calculated =%d\n"
+		REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_C, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_C calculated =%d\n"
 			"HW register value = 0x%x\n",
-			watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+			watermarks->c.pte_meta_urgent_ns, prog_wm_value);
+	}
 
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C)) {
+		if (safe_to_lower || watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns
+				> hubbub->watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns) {
+			hubbub->watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns =
+					watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_ENTER_EXIT_WATERMARK_C calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+		}
+
+		if (safe_to_lower || watermarks->c.cstate_pstate.cstate_exit_ns
+				> hubbub->watermarks.c.cstate_pstate.cstate_exit_ns) {
+			hubbub->watermarks.c.cstate_pstate.cstate_exit_ns =
+					watermarks->c.cstate_pstate.cstate_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->c.cstate_pstate.cstate_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_C, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_C calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->c.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		}
+	}
 
+	if (safe_to_lower || watermarks->c.cstate_pstate.pstate_change_ns
+			> hubbub->watermarks.c.cstate_pstate.pstate_change_ns) {
+		hubbub->watermarks.c.cstate_pstate.pstate_change_ns =
+				watermarks->c.cstate_pstate.pstate_change_ns;
 		prog_wm_value = convert_and_clamp(
-				watermarks->c.cstate_pstate.cstate_exit_ns,
+				watermarks->c.cstate_pstate.pstate_change_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_C, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_C calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->c.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_C calculated =%d\n"
+			"HW register value = 0x%x\n\n",
+			watermarks->c.cstate_pstate.pstate_change_ns, prog_wm_value);
 	}
 
-	prog_wm_value = convert_and_clamp(
-			watermarks->c.cstate_pstate.pstate_change_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_C calculated =%d\n\n"
-		"HW register value = 0x%x\n",
-		watermarks->c.cstate_pstate.pstate_change_ns, prog_wm_value);
-
 	/* clock state D */
-	prog_wm_value = convert_and_clamp(
-			watermarks->d.urgent_ns, refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_D, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_D calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->d.urgent_ns, prog_wm_value);
-
-	prog_wm_value = convert_and_clamp(
-			watermarks->d.pte_meta_urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_D, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_D calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->d.pte_meta_urgent_ns, prog_wm_value);
-
-
-	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D)) {
-		prog_wm_value = convert_and_clamp(
-				watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns,
+	if (safe_to_lower || watermarks->d.urgent_ns > hubbub->watermarks.d.urgent_ns) {
+		hubbub->watermarks.d.urgent_ns = watermarks->d.urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->d.urgent_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_ENTER_WATERMARK_D calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+		REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_D, prog_wm_value);
 
+		DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_D calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->d.urgent_ns, prog_wm_value);
+	}
 
-		prog_wm_value = convert_and_clamp(
-				watermarks->d.cstate_pstate.cstate_exit_ns,
+	if (safe_to_lower || watermarks->d.pte_meta_urgent_ns > hubbub->watermarks.d.pte_meta_urgent_ns) {
+		hubbub->watermarks.d.pte_meta_urgent_ns = watermarks->d.pte_meta_urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->d.pte_meta_urgent_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_D, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_D calculated =%d\n"
+		REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_D, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_D calculated =%d\n"
 			"HW register value = 0x%x\n",
-			watermarks->d.cstate_pstate.cstate_exit_ns, prog_wm_value);
+			watermarks->d.pte_meta_urgent_ns, prog_wm_value);
 	}
 
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D)) {
+		if (safe_to_lower || watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns
+				> hubbub->watermarks.d.cstate_pstate.cstate_enter_plus_exit_ns) {
+			hubbub->watermarks.d.cstate_pstate.cstate_enter_plus_exit_ns =
+					watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_ENTER_EXIT_WATERMARK_D calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+		}
 
-	prog_wm_value = convert_and_clamp(
-			watermarks->d.cstate_pstate.pstate_change_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_D calculated =%d\n"
-		"HW register value = 0x%x\n\n",
-		watermarks->d.cstate_pstate.pstate_change_ns, prog_wm_value);
+		if (safe_to_lower || watermarks->d.cstate_pstate.cstate_exit_ns
+				> hubbub->watermarks.d.cstate_pstate.cstate_exit_ns) {
+			hubbub->watermarks.d.cstate_pstate.cstate_exit_ns =
+					watermarks->d.cstate_pstate.cstate_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->d.cstate_pstate.cstate_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_D, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_D calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->d.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		}
+	}
 
-	REG_UPDATE(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
-			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, 1);
+	if (safe_to_lower || watermarks->d.cstate_pstate.pstate_change_ns
+			> hubbub->watermarks.d.cstate_pstate.pstate_change_ns) {
+		hubbub->watermarks.d.cstate_pstate.pstate_change_ns =
+				watermarks->d.cstate_pstate.pstate_change_ns;
+		prog_wm_value = convert_and_clamp(
+				watermarks->d.cstate_pstate.pstate_change_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_D calculated =%d\n"
+			"HW register value = 0x%x\n\n",
+			watermarks->d.cstate_pstate.pstate_change_ns, prog_wm_value);
+	}
 
 	REG_UPDATE(DCHUBBUB_ARB_SAT_LEVEL,
 			DCHUBBUB_ARB_SAT_LEVEL, 60 * refclk_mhz);
@@ -408,6 +483,11 @@ void hubbub1_update_dchub(
 	struct hubbub *hubbub,
 	struct dchub_init_data *dh_data)
 {
+	if (REG(DCHUBBUB_SDPIF_FB_TOP) == 0) {
+		ASSERT(false);
+		/*should not come here*/
+		return;
+	}
 	/* TODO: port code from dal2 */
 	switch (dh_data->fb_mode) {
 	case FRAME_BUFFER_MODE_ZFB_ONLY:
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
index 6315a0e6b0d6..d6e596eef4c5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
@@ -185,6 +185,7 @@ struct hubbub {
 	const struct dcn_hubbub_shift *shifts;
 	const struct dcn_hubbub_mask *masks;
 	unsigned int debug_test_index_pstate;
+	struct dcn_watermark_set watermarks;
 };
 
 void hubbub1_update_dchub(
@@ -194,10 +195,13 @@ void hubbub1_update_dchub(
 bool hubbub1_verify_allow_pstate_change_high(
 	struct hubbub *hubbub);
 
+void hubbub1_wm_change_req_wa(struct hubbub *hubbub);
+
 void hubbub1_program_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
-		unsigned int refclk_mhz);
+		unsigned int refclk_mhz,
+		bool safe_to_lower);
 
 void hubbub1_toggle_watermark_change_req(
 		struct hubbub *hubbub);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index c28085be39ff..2138cd3c5d1d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -152,21 +152,19 @@ void hubp1_program_tiling(
 			PIPE_ALIGNED, info->gfx9.pipe_aligned);
 }
 
-void hubp1_program_size_and_rotation(
+void hubp1_program_size(
 	struct hubp *hubp,
-	enum dc_rotation_angle rotation,
 	enum surface_pixel_format format,
 	const union plane_size *plane_size,
-	struct dc_plane_dcc_param *dcc,
-	bool horizontal_mirror)
+	struct dc_plane_dcc_param *dcc)
 {
 	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
-	uint32_t pitch, meta_pitch, pitch_c, meta_pitch_c, mirror;
+	uint32_t pitch, meta_pitch, pitch_c, meta_pitch_c;
 
 	/* Program data and meta surface pitch (calculation from addrlib)
 	 * 444 or 420 luma
 	 */
-	if (format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN) {
+	if (format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN && format < SURFACE_PIXEL_FORMAT_SUBSAMPLE_END) {
 		ASSERT(plane_size->video.chroma_pitch != 0);
 		/* Chroma pitch zero can cause system hang! */
 
@@ -192,13 +190,22 @@ void hubp1_program_size_and_rotation(
 	if (format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN)
 		REG_UPDATE_2(DCSURF_SURFACE_PITCH_C,
 			PITCH_C, pitch_c, META_PITCH_C, meta_pitch_c);
+}
+
+void hubp1_program_rotation(
+	struct hubp *hubp,
+	enum dc_rotation_angle rotation,
+	bool horizontal_mirror)
+{
+	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
+	uint32_t mirror;
+
 
 	if (horizontal_mirror)
 		mirror = 1;
 	else
 		mirror = 0;
 
-
 	/* Program rotation angle and horz mirror - no mirror */
 	if (rotation == ROTATION_ANGLE_0)
 		REG_UPDATE_2(DCSURF_SURFACE_CONFIG,
@@ -287,6 +294,10 @@ void hubp1_program_pixel_format(
 		REG_UPDATE(DCSURF_SURFACE_CONFIG,
 				SURFACE_PIXEL_FORMAT, 66);
 		break;
+	case SURFACE_PIXEL_FORMAT_VIDEO_AYCrCb8888:
+		REG_UPDATE(DCSURF_SURFACE_CONFIG,
+				SURFACE_PIXEL_FORMAT, 12);
+		break;
 	default:
 		BREAK_TO_DEBUGGER();
 		break;
@@ -450,9 +461,6 @@ bool hubp1_program_surface_flip_and_addr(
 
 	hubp->request_address = *address;
 
-	if (flip_immediate)
-		hubp->current_address = *address;
-
 	return true;
 }
 
@@ -481,8 +489,8 @@ void hubp1_program_surface_config(
 {
 	hubp1_dcc_control(hubp, dcc->enable, dcc->grph.independent_64b_blks);
 	hubp1_program_tiling(hubp, tiling_info, format);
-	hubp1_program_size_and_rotation(
-			hubp, rotation, format, plane_size, dcc, horizontal_mirror);
+	hubp1_program_size(hubp, format, plane_size, dcc);
+	hubp1_program_rotation(hubp, rotation, horizontal_mirror);
 	hubp1_program_pixel_format(hubp, format);
 }
 
@@ -688,7 +696,6 @@ bool hubp1_is_flip_pending(struct hubp *hubp)
 	if (earliest_inuse_address.grph.addr.quad_part != hubp->request_address.grph.addr.quad_part)
 		return true;
 
-	hubp->current_address = hubp->request_address;
 	return false;
 }
 
@@ -1061,9 +1068,11 @@ void hubp1_cursor_set_position(
 		const struct dc_cursor_mi_param *param)
 {
 	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
-	int src_x_offset = pos->x - pos->x_hotspot - param->viewport_x_start;
+	int src_x_offset = pos->x - pos->x_hotspot - param->viewport.x;
+	int x_hotspot = pos->x_hotspot;
+	int y_hotspot = pos->y_hotspot;
+	uint32_t dst_x_offset;
 	uint32_t cur_en = pos->enable ? 1 : 0;
-	uint32_t dst_x_offset = (src_x_offset >= 0) ? src_x_offset : 0;
 
 	/*
 	 * Guard aganst cursor_set_position() from being called with invalid
@@ -1075,6 +1084,18 @@ void hubp1_cursor_set_position(
 	if (hubp->curs_attr.address.quad_part == 0)
 		return;
 
+	if (param->rotation == ROTATION_ANGLE_90 || param->rotation == ROTATION_ANGLE_270) {
+		src_x_offset = pos->y - pos->y_hotspot - param->viewport.x;
+		y_hotspot = pos->x_hotspot;
+		x_hotspot = pos->y_hotspot;
+	}
+
+	if (param->mirror) {
+		x_hotspot = param->viewport.width - x_hotspot;
+		src_x_offset = param->viewport.x + param->viewport.width - src_x_offset;
+	}
+
+	dst_x_offset = (src_x_offset >= 0) ? src_x_offset : 0;
 	dst_x_offset *= param->ref_clk_khz;
 	dst_x_offset /= param->pixel_clk_khz;
 
@@ -1085,7 +1106,7 @@ void hubp1_cursor_set_position(
 				dc_fixpt_from_int(dst_x_offset),
 				param->h_scale_ratio));
 
-	if (src_x_offset >= (int)param->viewport_width)
+	if (src_x_offset >= (int)param->viewport.width)
 		cur_en = 0;  /* not visible beyond right edge*/
 
 	if (src_x_offset + (int)hubp->curs_attr.width <= 0)
@@ -1102,8 +1123,8 @@ void hubp1_cursor_set_position(
 			CURSOR_Y_POSITION, pos->y);
 
 	REG_SET_2(CURSOR_HOT_SPOT, 0,
-			CURSOR_HOT_SPOT_X, pos->x_hotspot,
-			CURSOR_HOT_SPOT_Y, pos->y_hotspot);
+			CURSOR_HOT_SPOT_X, x_hotspot,
+			CURSOR_HOT_SPOT_Y, y_hotspot);
 
 	REG_SET(CURSOR_DST_OFFSET, 0,
 			CURSOR_DST_X_OFFSET, dst_x_offset);
@@ -1125,7 +1146,7 @@ void hubp1_vtg_sel(struct hubp *hubp, uint32_t otg_inst)
 	REG_UPDATE(DCHUBP_CNTL, HUBP_VTG_SEL, otg_inst);
 }
 
-static struct hubp_funcs dcn10_hubp_funcs = {
+static const struct hubp_funcs dcn10_hubp_funcs = {
 	.hubp_program_surface_flip_and_addr =
 			hubp1_program_surface_flip_and_addr,
 	.hubp_program_surface_config =
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
index d901d5092969..f689feace82d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
@@ -268,8 +268,6 @@
 	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_PITCH, META_PITCH, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_PITCH_C, PITCH_C, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_PITCH_C, META_PITCH_C, mask_sh),\
-	HUBP_SF(HUBP0_DCSURF_SURFACE_CONFIG, ROTATION_ANGLE, mask_sh),\
-	HUBP_SF(HUBP0_DCSURF_SURFACE_CONFIG, H_MIRROR_EN, mask_sh),\
 	HUBP_SF(HUBP0_DCSURF_SURFACE_CONFIG, SURFACE_PIXEL_FORMAT, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_FLIP_CONTROL, SURFACE_FLIP_TYPE, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_FLIP_CONTROL, SURFACE_FLIP_PENDING, mask_sh),\
@@ -388,6 +386,8 @@
 #define HUBP_MASK_SH_LIST_DCN10(mask_sh)\
 	HUBP_MASK_SH_LIST_DCN(mask_sh),\
 	HUBP_MASK_SH_LIST_DCN_VM(mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_SURFACE_CONFIG, ROTATION_ANGLE, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_SURFACE_CONFIG, H_MIRROR_EN, mask_sh),\
 	HUBP_SF(HUBPREQ0_PREFETCH_SETTINS, DST_Y_PREFETCH, mask_sh),\
 	HUBP_SF(HUBPREQ0_PREFETCH_SETTINS, VRATIO_PREFETCH, mask_sh),\
 	HUBP_SF(HUBPREQ0_PREFETCH_SETTINS_C, VRATIO_PREFETCH_C, mask_sh),\
@@ -679,12 +679,15 @@ void hubp1_program_pixel_format(
 	struct hubp *hubp,
 	enum surface_pixel_format format);
 
-void hubp1_program_size_and_rotation(
+void hubp1_program_size(
 	struct hubp *hubp,
-	enum dc_rotation_angle rotation,
 	enum surface_pixel_format format,
 	const union plane_size *plane_size,
-	struct dc_plane_dcc_param *dcc,
+	struct dc_plane_dcc_param *dcc);
+
+void hubp1_program_rotation(
+	struct hubp *hubp,
+	enum dc_rotation_angle rotation,
 	bool horizontal_mirror);
 
 void hubp1_program_tiling(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index f8e0576af6e0..cfcc54f2ce65 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -337,13 +337,13 @@ void dcn10_log_hw_state(struct dc *dc)
 
 	DTN_INFO("\nCALCULATED Clocks: dcfclk_khz:%d  dcfclk_deep_sleep_khz:%d  dispclk_khz:%d\n"
 		"dppclk_khz:%d  max_supported_dppclk_khz:%d  fclk_khz:%d  socclk_khz:%d\n\n",
-			dc->current_state->bw.dcn.calc_clk.dcfclk_khz,
-			dc->current_state->bw.dcn.calc_clk.dcfclk_deep_sleep_khz,
-			dc->current_state->bw.dcn.calc_clk.dispclk_khz,
-			dc->current_state->bw.dcn.calc_clk.dppclk_khz,
-			dc->current_state->bw.dcn.calc_clk.max_supported_dppclk_khz,
-			dc->current_state->bw.dcn.calc_clk.fclk_khz,
-			dc->current_state->bw.dcn.calc_clk.socclk_khz);
+			dc->current_state->bw.dcn.clk.dcfclk_khz,
+			dc->current_state->bw.dcn.clk.dcfclk_deep_sleep_khz,
+			dc->current_state->bw.dcn.clk.dispclk_khz,
+			dc->current_state->bw.dcn.clk.dppclk_khz,
+			dc->current_state->bw.dcn.clk.max_supported_dppclk_khz,
+			dc->current_state->bw.dcn.clk.fclk_khz,
+			dc->current_state->bw.dcn.clk.socclk_khz);
 
 	log_mpc_crc(dc);
 
@@ -415,6 +415,8 @@ static void dpp_pg_control(
 
 	if (hws->ctx->dc->debug.disable_dpp_power_gate)
 		return;
+	if (REG(DOMAIN1_PG_CONFIG) == 0)
+		return;
 
 	switch (dpp_inst) {
 	case 0: /* DPP0 */
@@ -465,6 +467,8 @@ static void hubp_pg_control(
 
 	if (hws->ctx->dc->debug.disable_hubp_power_gate)
 		return;
+	if (REG(DOMAIN0_PG_CONFIG) == 0)
+		return;
 
 	switch (hubp_inst) {
 	case 0: /* DCHUBP0 */
@@ -719,19 +723,7 @@ static void reset_back_end_for_pipe(
 		if (!pipe_ctx->stream->dpms_off)
 			core_link_disable_stream(pipe_ctx, FREE_ACQUIRED_RESOURCE);
 		else if (pipe_ctx->stream_res.audio) {
-			/*
-			 * if stream is already disabled outside of commit streams path,
-			 * audio disable was skipped. Need to do it here
-			 */
-			pipe_ctx->stream_res.audio->funcs->az_disable(pipe_ctx->stream_res.audio);
-
-			if (dc->caps.dynamic_audio == true) {
-				/*we have to dynamic arbitrate the audio endpoints*/
-				pipe_ctx->stream_res.audio = NULL;
-				/*we free the resource, need reset is_audio_acquired*/
-				update_audio_usage(&dc->current_state->res_ctx, dc->res_pool, pipe_ctx->stream_res.audio, false);
-			}
-
+			dc->hwss.disable_audio_stream(pipe_ctx, FREE_ACQUIRED_RESOURCE);
 		}
 
 	}
@@ -842,7 +834,7 @@ static bool dcn10_hw_wa_force_recovery(struct dc *dc)
 }
 
 
-static void dcn10_verify_allow_pstate_change_high(struct dc *dc)
+void dcn10_verify_allow_pstate_change_high(struct dc *dc)
 {
 	static bool should_log_hw_state; /* prevent hw state log by default */
 
@@ -877,7 +869,8 @@ void hwss1_plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx)
 		return;
 
 	mpc->funcs->remove_mpcc(mpc, mpc_tree_params, mpcc_to_remove);
-	opp->mpcc_disconnect_pending[pipe_ctx->plane_res.mpcc_inst] = true;
+	if (opp != NULL)
+		opp->mpcc_disconnect_pending[pipe_ctx->plane_res.mpcc_inst] = true;
 
 	dc->optimized_required = true;
 
@@ -1022,7 +1015,7 @@ static void dcn10_init_hw(struct dc *dc)
 	/* Reset all MPCC muxes */
 	dc->res_pool->mpc->funcs->mpc_init(dc->res_pool->mpc);
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+	for (i = 0; i < dc->res_pool->timing_generator_count; i++) {
 		struct timing_generator *tg = dc->res_pool->timing_generators[i];
 		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
 		struct hubp *hubp = dc->res_pool->hubps[i];
@@ -1096,6 +1089,8 @@ static void dcn10_init_hw(struct dc *dc)
 	}
 
 	enable_power_gating_plane(dc->hwseq, true);
+
+	memset(&dc->res_pool->dccg->clks, 0, sizeof(dc->res_pool->dccg->clks));
 }
 
 static void reset_hw_ctx_wrap(
@@ -1164,12 +1159,19 @@ static void dcn10_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_c
 
 	if (plane_state == NULL)
 		return;
+
 	addr_patched = patch_address_for_sbs_tb_stereo(pipe_ctx, &addr);
+
 	pipe_ctx->plane_res.hubp->funcs->hubp_program_surface_flip_and_addr(
 			pipe_ctx->plane_res.hubp,
 			&plane_state->address,
 			plane_state->flip_immediate);
+
 	plane_state->status.requested_address = plane_state->address;
+
+	if (plane_state->flip_immediate)
+		plane_state->status.current_address = plane_state->address;
+
 	if (addr_patched)
 		pipe_ctx->plane_state->address.grph_stereo.left_addr = addr;
 }
@@ -1213,8 +1215,11 @@ static bool dcn10_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
 	} else if (tf->type == TF_TYPE_BYPASS) {
 		dpp_base->funcs->dpp_set_degamma(dpp_base, IPP_DEGAMMA_MODE_BYPASS);
 	} else {
-		/*TF_TYPE_DISTRIBUTED_POINTS*/
-		result = false;
+		cm_helper_translate_curve_to_degamma_hw_format(tf,
+					&dpp_base->degamma_params);
+		dpp_base->funcs->dpp_program_degamma_pwl(dpp_base,
+				&dpp_base->degamma_params);
+		result = true;
 	}
 
 	return result;
@@ -1355,10 +1360,11 @@ static void dcn10_enable_per_frame_crtc_position_reset(
 
 	DC_SYNC_INFO("Setting up\n");
 	for (i = 0; i < group_size; i++)
-		grouped_pipes[i]->stream_res.tg->funcs->enable_crtc_reset(
-				grouped_pipes[i]->stream_res.tg,
-				grouped_pipes[i]->stream->triggered_crtc_reset.event_source->status.primary_otg_inst,
-				&grouped_pipes[i]->stream->triggered_crtc_reset);
+		if (grouped_pipes[i]->stream_res.tg->funcs->enable_crtc_reset)
+			grouped_pipes[i]->stream_res.tg->funcs->enable_crtc_reset(
+					grouped_pipes[i]->stream_res.tg,
+					grouped_pipes[i]->stream->triggered_crtc_reset.event_source->status.primary_otg_inst,
+					&grouped_pipes[i]->stream->triggered_crtc_reset);
 
 	DC_SYNC_INFO("Waiting for trigger\n");
 
@@ -1774,6 +1780,43 @@ static void dcn10_get_surface_visual_confirm_color(
 	}
 }
 
+static void dcn10_get_hdr_visual_confirm_color(
+		struct pipe_ctx *pipe_ctx,
+		struct tg_color *color)
+{
+	uint32_t color_value = MAX_TG_COLOR_VALUE;
+
+	// Determine the overscan color based on the top-most (desktop) plane's context
+	struct pipe_ctx *top_pipe_ctx  = pipe_ctx;
+
+	while (top_pipe_ctx->top_pipe != NULL)
+		top_pipe_ctx = top_pipe_ctx->top_pipe;
+
+	switch (top_pipe_ctx->plane_res.scl_data.format) {
+	case PIXEL_FORMAT_ARGB2101010:
+		if (top_pipe_ctx->stream->out_transfer_func->tf == TRANSFER_FUNCTION_UNITY) {
+			/* HDR10, ARGB2101010 - set boarder color to red */
+			color->color_r_cr = color_value;
+		}
+		break;
+	case PIXEL_FORMAT_FP16:
+		if (top_pipe_ctx->stream->out_transfer_func->tf == TRANSFER_FUNCTION_PQ) {
+			/* HDR10, FP16 - set boarder color to blue */
+			color->color_b_cb = color_value;
+		} else if (top_pipe_ctx->stream->out_transfer_func->tf == TRANSFER_FUNCTION_GAMMA22) {
+			/* FreeSync 2 HDR - set boarder color to green */
+			color->color_g_y = color_value;
+		}
+		break;
+	default:
+		/* SDR - set boarder color to Gray */
+		color->color_r_cr = color_value/2;
+		color->color_b_cb = color_value/2;
+		color->color_g_y = color_value/2;
+		break;
+	}
+}
+
 static uint16_t fixed_point_to_int_frac(
 	struct fixed31_32 arg,
 	uint8_t integer_bits,
@@ -1854,11 +1897,10 @@ static void update_dpp(struct dpp *dpp, struct dc_plane_state *plane_state)
 		dpp->funcs->dpp_program_bias_and_scale(dpp, &bns_params);
 }
 
-
-static void update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
+static void dcn10_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
-	struct mpcc_blnd_cfg blnd_cfg;
+	struct mpcc_blnd_cfg blnd_cfg = {0};
 	bool per_pixel_alpha = pipe_ctx->plane_state->per_pixel_alpha && pipe_ctx->bottom_pipe;
 	int mpcc_id;
 	struct mpcc *new_mpcc;
@@ -1869,13 +1911,17 @@ static void update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 
 	/* TODO: proper fix once fpga works */
 
-	if (dc->debug.surface_visual_confirm)
+	if (dc->debug.visual_confirm == VISUAL_CONFIRM_HDR) {
+		dcn10_get_hdr_visual_confirm_color(
+				pipe_ctx, &blnd_cfg.black_color);
+	} else if (dc->debug.visual_confirm == VISUAL_CONFIRM_SURFACE) {
 		dcn10_get_surface_visual_confirm_color(
 				pipe_ctx, &blnd_cfg.black_color);
-	else
+	} else {
 		color_space_to_black_color(
-			dc, pipe_ctx->stream->output_color_space,
-			&blnd_cfg.black_color);
+				dc, pipe_ctx->stream->output_color_space,
+				&blnd_cfg.black_color);
+	}
 
 	if (per_pixel_alpha)
 		blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA;
@@ -1964,18 +2010,17 @@ static void update_dchubp_dpp(
 	 * divided by 2
 	 */
 	if (plane_state->update_flags.bits.full_update) {
-		bool should_divided_by_2 = context->bw.dcn.calc_clk.dppclk_khz <=
-				context->bw.dcn.cur_clk.dispclk_khz / 2;
+		bool should_divided_by_2 = context->bw.dcn.clk.dppclk_khz <=
+				dc->res_pool->dccg->clks.dispclk_khz / 2;
 
 		dpp->funcs->dpp_dppclk_control(
 				dpp,
 				should_divided_by_2,
 				true);
 
-		dc->current_state->bw.dcn.cur_clk.dppclk_khz =
-				should_divided_by_2 ?
-				context->bw.dcn.cur_clk.dispclk_khz / 2 :
-				context->bw.dcn.cur_clk.dispclk_khz;
+		dc->res_pool->dccg->clks.dppclk_khz = should_divided_by_2 ?
+						dc->res_pool->dccg->clks.dispclk_khz / 2 :
+							dc->res_pool->dccg->clks.dispclk_khz;
 	}
 
 	/* TODO: Need input parameter to tell current DCHUB pipe tie to which OTG
@@ -2001,7 +2046,7 @@ static void update_dchubp_dpp(
 
 	if (plane_state->update_flags.bits.full_update ||
 		plane_state->update_flags.bits.per_pixel_alpha_change)
-		update_mpcc(dc, pipe_ctx);
+		dc->hwss.update_mpcc(dc, pipe_ctx);
 
 	if (plane_state->update_flags.bits.full_update ||
 		plane_state->update_flags.bits.per_pixel_alpha_change ||
@@ -2063,12 +2108,13 @@ static void update_dchubp_dpp(
 
 static void dcn10_blank_pixel_data(
 		struct dc *dc,
-		struct stream_resource *stream_res,
-		struct dc_stream_state *stream,
+		struct pipe_ctx *pipe_ctx,
 		bool blank)
 {
 	enum dc_color_space color_space;
 	struct tg_color black_color = {0};
+	struct stream_resource *stream_res = &pipe_ctx->stream_res;
+	struct dc_stream_state *stream = pipe_ctx->stream;
 
 	/* program otg blank color */
 	color_space = stream->output_color_space;
@@ -2110,6 +2156,33 @@ static void set_hdr_multiplier(struct pipe_ctx *pipe_ctx)
 			pipe_ctx->plane_res.dpp, hw_mult);
 }
 
+void dcn10_program_pipe(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context)
+{
+	if (pipe_ctx->plane_state->update_flags.bits.full_update)
+		dcn10_enable_plane(dc, pipe_ctx, context);
+
+	update_dchubp_dpp(dc, pipe_ctx, context);
+
+	set_hdr_multiplier(pipe_ctx);
+
+	if (pipe_ctx->plane_state->update_flags.bits.full_update ||
+			pipe_ctx->plane_state->update_flags.bits.in_transfer_func_change ||
+			pipe_ctx->plane_state->update_flags.bits.gamma_change)
+		dc->hwss.set_input_transfer_func(pipe_ctx, pipe_ctx->plane_state);
+
+	/* dcn10_translate_regamma_to_hw_format takes 750us to finish
+	 * only do gamma programming for full update.
+	 * TODO: This can be further optimized/cleaned up
+	 * Always call this for now since it does memcmp inside before
+	 * doing heavy calculation and programming
+	 */
+	if (pipe_ctx->plane_state->update_flags.bits.full_update)
+		dc->hwss.set_output_transfer_func(pipe_ctx, pipe_ctx->stream);
+}
+
 static void program_all_pipe_in_tree(
 		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
@@ -2127,31 +2200,12 @@ static void program_all_pipe_in_tree(
 		pipe_ctx->stream_res.tg->funcs->program_global_sync(
 				pipe_ctx->stream_res.tg);
 
-		dc->hwss.blank_pixel_data(dc, &pipe_ctx->stream_res,
-				pipe_ctx->stream, blank);
+		dc->hwss.blank_pixel_data(dc, pipe_ctx, blank);
+
 	}
 
 	if (pipe_ctx->plane_state != NULL) {
-		if (pipe_ctx->plane_state->update_flags.bits.full_update)
-			dcn10_enable_plane(dc, pipe_ctx, context);
-
-		update_dchubp_dpp(dc, pipe_ctx, context);
-
-		set_hdr_multiplier(pipe_ctx);
-
-		if (pipe_ctx->plane_state->update_flags.bits.full_update ||
-				pipe_ctx->plane_state->update_flags.bits.in_transfer_func_change ||
-				pipe_ctx->plane_state->update_flags.bits.gamma_change)
-			dc->hwss.set_input_transfer_func(pipe_ctx, pipe_ctx->plane_state);
-
-		/* dcn10_translate_regamma_to_hw_format takes 750us to finish
-		 * only do gamma programming for full update.
-		 * TODO: This can be further optimized/cleaned up
-		 * Always call this for now since it does memcmp inside before
-		 * doing heavy calculation and programming
-		 */
-		if (pipe_ctx->plane_state->update_flags.bits.full_update)
-			dc->hwss.set_output_transfer_func(pipe_ctx, pipe_ctx->stream);
+		dcn10_program_pipe(dc, pipe_ctx, context);
 	}
 
 	if (pipe_ctx->bottom_pipe != NULL && pipe_ctx->bottom_pipe != pipe_ctx) {
@@ -2165,12 +2219,12 @@ static void dcn10_pplib_apply_display_requirements(
 {
 	struct dm_pp_display_configuration *pp_display_cfg = &context->pp_display_cfg;
 
-	pp_display_cfg->min_engine_clock_khz = context->bw.dcn.cur_clk.dcfclk_khz;
-	pp_display_cfg->min_memory_clock_khz = context->bw.dcn.cur_clk.fclk_khz;
-	pp_display_cfg->min_engine_clock_deep_sleep_khz = context->bw.dcn.cur_clk.dcfclk_deep_sleep_khz;
-	pp_display_cfg->min_dcfc_deep_sleep_clock_khz = context->bw.dcn.cur_clk.dcfclk_deep_sleep_khz;
-	pp_display_cfg->min_dcfclock_khz = context->bw.dcn.cur_clk.dcfclk_khz;
-	pp_display_cfg->disp_clk_khz = context->bw.dcn.cur_clk.dispclk_khz;
+	pp_display_cfg->min_engine_clock_khz = dc->res_pool->dccg->clks.dcfclk_khz;
+	pp_display_cfg->min_memory_clock_khz = dc->res_pool->dccg->clks.fclk_khz;
+	pp_display_cfg->min_engine_clock_deep_sleep_khz = dc->res_pool->dccg->clks.dcfclk_deep_sleep_khz;
+	pp_display_cfg->min_dcfc_deep_sleep_clock_khz = dc->res_pool->dccg->clks.dcfclk_deep_sleep_khz;
+	pp_display_cfg->min_dcfclock_khz = dc->res_pool->dccg->clks.dcfclk_khz;
+	pp_display_cfg->disp_clk_khz = dc->res_pool->dccg->clks.dispclk_khz;
 	dce110_fill_display_configs(context, pp_display_cfg);
 
 	if (memcmp(&dc->prev_display_config, pp_display_cfg, sizeof(
@@ -2232,8 +2286,6 @@ static void dcn10_apply_ctx_for_surface(
 	int i;
 	struct timing_generator *tg;
 	bool removed_pipe[4] = { false };
-	unsigned int ref_clk_mhz = dc->res_pool->ref_clock_inKhz/1000;
-	bool program_water_mark = false;
 	struct pipe_ctx *top_pipe_to_program =
 			find_top_pipe_for_stream(dc, context, stream);
 	DC_LOGGER_INIT(dc->ctx->logger);
@@ -2247,7 +2299,7 @@ static void dcn10_apply_ctx_for_surface(
 
 	if (num_planes == 0) {
 		/* OTG blank before remove all front end */
-		dc->hwss.blank_pixel_data(dc, &top_pipe_to_program->stream_res, top_pipe_to_program->stream, true);
+		dc->hwss.blank_pixel_data(dc, top_pipe_to_program, true);
 	}
 
 	/* Disconnect unused mpcc */
@@ -2278,11 +2330,10 @@ static void dcn10_apply_ctx_for_surface(
 			old_pipe_ctx->plane_state &&
 			old_pipe_ctx->stream_res.tg == tg) {
 
-			hwss1_plane_atomic_disconnect(dc, old_pipe_ctx);
+			dc->hwss.plane_atomic_disconnect(dc, old_pipe_ctx);
 			removed_pipe[i] = true;
 
-			DC_LOG_DC(
-					"Reset mpcc for pipe %d\n",
+			DC_LOG_DC("Reset mpcc for pipe %d\n",
 					old_pipe_ctx->pipe_idx);
 		}
 	}
@@ -2295,248 +2346,41 @@ static void dcn10_apply_ctx_for_surface(
 	if (num_planes == 0)
 		false_optc_underflow_wa(dc, stream, tg);
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *old_pipe_ctx =
-				&dc->current_state->res_ctx.pipe_ctx[i];
-		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
-
-		if (pipe_ctx->stream == stream &&
-				pipe_ctx->plane_state &&
-			pipe_ctx->plane_state->update_flags.bits.full_update)
-			program_water_mark = true;
-
+	for (i = 0; i < dc->res_pool->pipe_count; i++)
 		if (removed_pipe[i])
-			dcn10_disable_plane(dc, old_pipe_ctx);
-	}
-
-	if (program_water_mark) {
-		if (dc->debug.sanity_checks) {
-			/* pstate stuck check after watermark update */
-			dcn10_verify_allow_pstate_change_high(dc);
-		}
-
-		/* watermark is for all pipes */
-		hubbub1_program_watermarks(dc->res_pool->hubbub,
-				&context->bw.dcn.watermarks, ref_clk_mhz);
+			dcn10_disable_plane(dc, &dc->current_state->res_ctx.pipe_ctx[i]);
 
-		if (dc->debug.sanity_checks) {
-			/* pstate stuck check after watermark update */
-			dcn10_verify_allow_pstate_change_high(dc);
-		}
-	}
-/*	DC_LOG_BANDWIDTH_CALCS(dc->ctx->logger,
-			"\n============== Watermark parameters ==============\n"
-			"a.urgent_ns: %d \n"
-			"a.cstate_enter_plus_exit: %d \n"
-			"a.cstate_exit: %d \n"
-			"a.pstate_change: %d \n"
-			"a.pte_meta_urgent: %d \n"
-			"b.urgent_ns: %d \n"
-			"b.cstate_enter_plus_exit: %d \n"
-			"b.cstate_exit: %d \n"
-			"b.pstate_change: %d \n"
-			"b.pte_meta_urgent: %d \n",
-			context->bw.dcn.watermarks.a.urgent_ns,
-			context->bw.dcn.watermarks.a.cstate_pstate.cstate_enter_plus_exit_ns,
-			context->bw.dcn.watermarks.a.cstate_pstate.cstate_exit_ns,
-			context->bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns,
-			context->bw.dcn.watermarks.a.pte_meta_urgent_ns,
-			context->bw.dcn.watermarks.b.urgent_ns,
-			context->bw.dcn.watermarks.b.cstate_pstate.cstate_enter_plus_exit_ns,
-			context->bw.dcn.watermarks.b.cstate_pstate.cstate_exit_ns,
-			context->bw.dcn.watermarks.b.cstate_pstate.pstate_change_ns,
-			context->bw.dcn.watermarks.b.pte_meta_urgent_ns
-			);
-	DC_LOG_BANDWIDTH_CALCS(dc->ctx->logger,
-			"\nc.urgent_ns: %d \n"
-			"c.cstate_enter_plus_exit: %d \n"
-			"c.cstate_exit: %d \n"
-			"c.pstate_change: %d \n"
-			"c.pte_meta_urgent: %d \n"
-			"d.urgent_ns: %d \n"
-			"d.cstate_enter_plus_exit: %d \n"
-			"d.cstate_exit: %d \n"
-			"d.pstate_change: %d \n"
-			"d.pte_meta_urgent: %d \n"
-			"========================================================\n",
-			context->bw.dcn.watermarks.c.urgent_ns,
-			context->bw.dcn.watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns,
-			context->bw.dcn.watermarks.c.cstate_pstate.cstate_exit_ns,
-			context->bw.dcn.watermarks.c.cstate_pstate.pstate_change_ns,
-			context->bw.dcn.watermarks.c.pte_meta_urgent_ns,
-			context->bw.dcn.watermarks.d.urgent_ns,
-			context->bw.dcn.watermarks.d.cstate_pstate.cstate_enter_plus_exit_ns,
-			context->bw.dcn.watermarks.d.cstate_pstate.cstate_exit_ns,
-			context->bw.dcn.watermarks.d.cstate_pstate.pstate_change_ns,
-			context->bw.dcn.watermarks.d.pte_meta_urgent_ns
-			);
-*/
-}
-
-static inline bool should_set_clock(bool decrease_allowed, int calc_clk, int cur_clk)
-{
-	return ((decrease_allowed && calc_clk < cur_clk) || calc_clk > cur_clk);
-}
-
-static int determine_dppclk_threshold(struct dc *dc, struct dc_state *context)
-{
-	bool request_dpp_div = context->bw.dcn.calc_clk.dispclk_khz >
-			context->bw.dcn.calc_clk.dppclk_khz;
-	bool dispclk_increase = context->bw.dcn.calc_clk.dispclk_khz >
-			context->bw.dcn.cur_clk.dispclk_khz;
-	int disp_clk_threshold = context->bw.dcn.calc_clk.max_supported_dppclk_khz;
-	bool cur_dpp_div = context->bw.dcn.cur_clk.dispclk_khz >
-			context->bw.dcn.cur_clk.dppclk_khz;
-
-	/* increase clock, looking for div is 0 for current, request div is 1*/
-	if (dispclk_increase) {
-		/* already divided by 2, no need to reach target clk with 2 steps*/
-		if (cur_dpp_div)
-			return context->bw.dcn.calc_clk.dispclk_khz;
-
-		/* request disp clk is lower than maximum supported dpp clk,
-		 * no need to reach target clk with two steps.
-		 */
-		if (context->bw.dcn.calc_clk.dispclk_khz <= disp_clk_threshold)
-			return context->bw.dcn.calc_clk.dispclk_khz;
-
-		/* target dpp clk not request divided by 2, still within threshold */
-		if (!request_dpp_div)
-			return context->bw.dcn.calc_clk.dispclk_khz;
-
-	} else {
-		/* decrease clock, looking for current dppclk divided by 2,
-		 * request dppclk not divided by 2.
-		 */
-
-		/* current dpp clk not divided by 2, no need to ramp*/
-		if (!cur_dpp_div)
-			return context->bw.dcn.calc_clk.dispclk_khz;
-
-		/* current disp clk is lower than current maximum dpp clk,
-		 * no need to ramp
-		 */
-		if (context->bw.dcn.cur_clk.dispclk_khz <= disp_clk_threshold)
-			return context->bw.dcn.calc_clk.dispclk_khz;
-
-		/* request dpp clk need to be divided by 2 */
-		if (request_dpp_div)
-			return context->bw.dcn.calc_clk.dispclk_khz;
-	}
-
-	return disp_clk_threshold;
-}
-
-static void ramp_up_dispclk_with_dpp(struct dc *dc, struct dc_state *context)
-{
-	int i;
-	bool request_dpp_div = context->bw.dcn.calc_clk.dispclk_khz >
-				context->bw.dcn.calc_clk.dppclk_khz;
-
-	int dispclk_to_dpp_threshold = determine_dppclk_threshold(dc, context);
-
-	/* set disp clk to dpp clk threshold */
-	dc->res_pool->display_clock->funcs->set_clock(
-			dc->res_pool->display_clock,
-			dispclk_to_dpp_threshold);
-
-	/* update request dpp clk division option */
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
-
-		if (!pipe_ctx->plane_state)
-			continue;
-
-		pipe_ctx->plane_res.dpp->funcs->dpp_dppclk_control(
-				pipe_ctx->plane_res.dpp,
-				request_dpp_div,
-				true);
-	}
-
-	/* If target clk not same as dppclk threshold, set to target clock */
-	if (dispclk_to_dpp_threshold != context->bw.dcn.calc_clk.dispclk_khz) {
-		dc->res_pool->display_clock->funcs->set_clock(
-				dc->res_pool->display_clock,
-				context->bw.dcn.calc_clk.dispclk_khz);
-	}
-
-	context->bw.dcn.cur_clk.dispclk_khz =
-			context->bw.dcn.calc_clk.dispclk_khz;
-	context->bw.dcn.cur_clk.dppclk_khz =
-			context->bw.dcn.calc_clk.dppclk_khz;
-	context->bw.dcn.cur_clk.max_supported_dppclk_khz =
-			context->bw.dcn.calc_clk.max_supported_dppclk_khz;
+	if (dc->hwseq->wa.DEGVIDCN10_254)
+		hubbub1_wm_change_req_wa(dc->res_pool->hubbub);
 }
 
 static void dcn10_set_bandwidth(
 		struct dc *dc,
 		struct dc_state *context,
-		bool decrease_allowed)
+		bool safe_to_lower)
 {
-	struct pp_smu_display_requirement_rv *smu_req_cur =
-			&dc->res_pool->pp_smu_req;
-	struct pp_smu_display_requirement_rv smu_req = *smu_req_cur;
-	struct pp_smu_funcs_rv *pp_smu = dc->res_pool->pp_smu;
-
-	if (dc->debug.sanity_checks) {
+	if (dc->debug.sanity_checks)
 		dcn10_verify_allow_pstate_change_high(dc);
-	}
-
-	if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
-		return;
-
-	if (should_set_clock(
-			decrease_allowed,
-			context->bw.dcn.calc_clk.dcfclk_khz,
-			dc->current_state->bw.dcn.cur_clk.dcfclk_khz)) {
-		context->bw.dcn.cur_clk.dcfclk_khz =
-				context->bw.dcn.calc_clk.dcfclk_khz;
-		smu_req.hard_min_dcefclk_khz =
-				context->bw.dcn.calc_clk.dcfclk_khz;
-	}
-
-	if (should_set_clock(
-			decrease_allowed,
-			context->bw.dcn.calc_clk.dcfclk_deep_sleep_khz,
-			dc->current_state->bw.dcn.cur_clk.dcfclk_deep_sleep_khz)) {
-		context->bw.dcn.cur_clk.dcfclk_deep_sleep_khz =
-				context->bw.dcn.calc_clk.dcfclk_deep_sleep_khz;
-	}
-
-	if (should_set_clock(
-			decrease_allowed,
-			context->bw.dcn.calc_clk.fclk_khz,
-			dc->current_state->bw.dcn.cur_clk.fclk_khz)) {
-		context->bw.dcn.cur_clk.fclk_khz =
-				context->bw.dcn.calc_clk.fclk_khz;
-		smu_req.hard_min_fclk_khz = context->bw.dcn.calc_clk.fclk_khz;
-	}
-
-	smu_req.display_count = context->stream_count;
-
-	if (pp_smu->set_display_requirement)
-		pp_smu->set_display_requirement(&pp_smu->pp_smu, &smu_req);
 
-	*smu_req_cur = smu_req;
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
+		if (context->stream_count == 0)
+			context->bw.dcn.clk.phyclk_khz = 0;
 
-	/* make sure dcf clk is before dpp clk to
-	 * make sure we have enough voltage to run dpp clk
-	 */
-	if (should_set_clock(
-			decrease_allowed,
-			context->bw.dcn.calc_clk.dispclk_khz,
-			dc->current_state->bw.dcn.cur_clk.dispclk_khz)) {
+		dc->res_pool->dccg->funcs->update_clocks(
+				dc->res_pool->dccg,
+				&context->bw.dcn.clk,
+				safe_to_lower);
 
-		ramp_up_dispclk_with_dpp(dc, context);
+		dcn10_pplib_apply_display_requirements(dc, context);
 	}
 
-	dcn10_pplib_apply_display_requirements(dc, context);
+	hubbub1_program_watermarks(dc->res_pool->hubbub,
+			&context->bw.dcn.watermarks,
+			dc->res_pool->ref_clock_inKhz / 1000,
+			true);
 
-	if (dc->debug.sanity_checks) {
+	if (dc->debug.sanity_checks)
 		dcn10_verify_allow_pstate_change_high(dc);
-	}
-
-	/* need to fix this function.  not doing the right thing here */
 }
 
 static void set_drr(struct pipe_ctx **pipe_ctx,
@@ -2701,16 +2545,20 @@ static void dcn10_update_pending_status(struct pipe_ctx *pipe_ctx)
 {
 	struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 	struct timing_generator *tg = pipe_ctx->stream_res.tg;
+	bool flip_pending;
 
 	if (plane_state == NULL)
 		return;
 
-	plane_state->status.is_flip_pending =
-			pipe_ctx->plane_res.hubp->funcs->hubp_is_flip_pending(
+	flip_pending = pipe_ctx->plane_res.hubp->funcs->hubp_is_flip_pending(
 					pipe_ctx->plane_res.hubp);
 
-	plane_state->status.current_address = pipe_ctx->plane_res.hubp->current_address;
-	if (pipe_ctx->plane_res.hubp->current_address.type == PLN_ADDR_TYPE_GRPH_STEREO &&
+	plane_state->status.is_flip_pending = flip_pending;
+
+	if (!flip_pending)
+		plane_state->status.current_address = plane_state->status.requested_address;
+
+	if (plane_state->status.current_address.type == PLN_ADDR_TYPE_GRPH_STEREO &&
 			tg->funcs->is_stereo_left_eye) {
 		plane_state->status.is_right_eye =
 				!tg->funcs->is_stereo_left_eye(pipe_ctx->stream_res.tg);
@@ -2719,8 +2567,14 @@ static void dcn10_update_pending_status(struct pipe_ctx *pipe_ctx)
 
 static void dcn10_update_dchub(struct dce_hwseq *hws, struct dchub_init_data *dh_data)
 {
-	if (hws->ctx->dc->res_pool->hubbub != NULL)
-		hubbub1_update_dchub(hws->ctx->dc->res_pool->hubbub, dh_data);
+	if (hws->ctx->dc->res_pool->hubbub != NULL) {
+		struct hubp *hubp = hws->ctx->dc->res_pool->hubps[0];
+
+		if (hubp->funcs->hubp_update_dchub)
+			hubp->funcs->hubp_update_dchub(hubp, dh_data);
+		else
+			hubbub1_update_dchub(hws->ctx->dc->res_pool->hubbub, dh_data);
+	}
 }
 
 static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
@@ -2731,9 +2585,11 @@ static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 	struct dc_cursor_mi_param param = {
 		.pixel_clk_khz = pipe_ctx->stream->timing.pix_clk_khz,
 		.ref_clk_khz = pipe_ctx->stream->ctx->dc->res_pool->ref_clock_inKhz,
-		.viewport_x_start = pipe_ctx->plane_res.scl_data.viewport.x,
-		.viewport_width = pipe_ctx->plane_res.scl_data.viewport.width,
-		.h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz
+		.viewport = pipe_ctx->plane_res.scl_data.viewport,
+		.h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz,
+		.v_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.vert,
+		.rotation = pipe_ctx->plane_state->rotation,
+		.mirror = pipe_ctx->plane_state->horizontal_mirror
 	};
 
 	if (pipe_ctx->plane_state->address.type
@@ -2757,6 +2613,33 @@ static void dcn10_set_cursor_attribute(struct pipe_ctx *pipe_ctx)
 		pipe_ctx->plane_res.dpp, attributes->color_format);
 }
 
+static void dcn10_set_cursor_sdr_white_level(struct pipe_ctx *pipe_ctx)
+{
+	uint32_t sdr_white_level = pipe_ctx->stream->cursor_attributes.sdr_white_level;
+	struct fixed31_32 multiplier;
+	struct dpp_cursor_attributes opt_attr = { 0 };
+	uint32_t hw_scale = 0x3c00; // 1.0 default multiplier
+	struct custom_float_format fmt;
+
+	if (!pipe_ctx->plane_res.dpp->funcs->set_optional_cursor_attributes)
+		return;
+
+	fmt.exponenta_bits = 5;
+	fmt.mantissa_bits = 10;
+	fmt.sign = true;
+
+	if (sdr_white_level > 80) {
+		multiplier = dc_fixpt_from_fraction(sdr_white_level, 80);
+		convert_to_custom_float_format(multiplier, &fmt, &hw_scale);
+	}
+
+	opt_attr.scale = hw_scale;
+	opt_attr.bias = 0;
+
+	pipe_ctx->plane_res.dpp->funcs->set_optional_cursor_attributes(
+			pipe_ctx->plane_res.dpp, &opt_attr);
+}
+
 static const struct hw_sequencer_funcs dcn10_funcs = {
 	.program_gamut_remap = program_gamut_remap,
 	.program_csc_matrix = program_csc_matrix,
@@ -2764,7 +2647,9 @@ static const struct hw_sequencer_funcs dcn10_funcs = {
 	.apply_ctx_to_hw = dce110_apply_ctx_to_hw,
 	.apply_ctx_for_surface = dcn10_apply_ctx_for_surface,
 	.update_plane_addr = dcn10_update_plane_addr,
+	.plane_atomic_disconnect = hwss1_plane_atomic_disconnect,
 	.update_dchub = dcn10_update_dchub,
+	.update_mpcc = dcn10_update_mpcc,
 	.update_pending_status = dcn10_update_pending_status,
 	.set_input_transfer_func = dcn10_set_input_transfer_func,
 	.set_output_transfer_func = dcn10_set_output_transfer_func,
@@ -2778,6 +2663,8 @@ static const struct hw_sequencer_funcs dcn10_funcs = {
 	.disable_stream = dce110_disable_stream,
 	.unblank_stream = dce110_unblank_stream,
 	.blank_stream = dce110_blank_stream,
+	.enable_audio_stream = dce110_enable_audio_stream,
+	.disable_audio_stream = dce110_disable_audio_stream,
 	.enable_display_power_gating = dcn10_dummy_display_power_gating,
 	.disable_plane = dcn10_disable_plane,
 	.blank_pixel_data = dcn10_blank_pixel_data,
@@ -2800,7 +2687,8 @@ static const struct hw_sequencer_funcs dcn10_funcs = {
 	.edp_power_control = hwss_edp_power_control,
 	.edp_wait_for_hpd_ready = hwss_edp_wait_for_hpd_ready,
 	.set_cursor_position = dcn10_set_cursor_position,
-	.set_cursor_attribute = dcn10_set_cursor_attribute
+	.set_cursor_attribute = dcn10_set_cursor_attribute,
+	.set_cursor_sdr_white_level = dcn10_set_cursor_sdr_white_level
 };
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
index 44f734b73f9e..7139fb73e966 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
@@ -39,4 +39,11 @@ bool is_rgb_cspace(enum dc_color_space output_color_space);
 
 void hwss1_plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx);
 
+void dcn10_verify_allow_pstate_change_high(struct dc *dc);
+
+void dcn10_program_pipe(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context);
+
 #endif /* __DC_HWSS_DCN10_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
index 21fa40ac0786..6f675206a136 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
@@ -65,11 +65,6 @@ enum {
 	DP_MST_UPDATE_MAX_RETRY = 50
 };
 
-
-
-static void aux_initialize(struct dcn10_link_encoder *enc10);
-
-
 static const struct link_encoder_funcs dcn10_lnk_enc_funcs = {
 	.validate_output_with_stream =
 		dcn10_link_encoder_validate_output_with_stream,
@@ -445,12 +440,11 @@ static uint8_t get_frontend_source(
 	}
 }
 
-static void configure_encoder(
+void configure_encoder(
 	struct dcn10_link_encoder *enc10,
 	const struct dc_link_settings *link_settings)
 {
 	/* set number of lanes */
-
 	REG_SET(DP_CONFIG, 0,
 			DP_UDI_LANES, link_settings->lane_count - LANE_COUNT_ONE);
 
@@ -602,6 +596,9 @@ static bool dcn10_link_encoder_validate_hdmi_output(
 	if (!enc10->base.features.flags.bits.HDMI_6GB_EN &&
 		adjusted_pix_clk_khz >= 300000)
 		return false;
+	if (enc10->base.ctx->dc->debug.hdmi20_disable &&
+		crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+		return false;
 	return true;
 }
 
@@ -734,6 +731,9 @@ void dcn10_link_encoder_construct(
 				__func__,
 				result);
 	}
+	if (enc10->base.ctx->dc->debug.hdmi20_disable) {
+		enc10->base.features.flags.bits.HDMI_6GB_EN = 0;
+	}
 }
 
 bool dcn10_link_encoder_validate_output_with_stream(
@@ -812,7 +812,7 @@ void dcn10_link_encoder_hw_init(
 		ASSERT(result == BP_RESULT_OK);
 
 	}
-	aux_initialize(enc10);
+	dcn10_aux_initialize(enc10);
 
 	/* reinitialize HPD.
 	 * hpd_initialize() will pass DIG_FE id to HW context.
@@ -995,6 +995,8 @@ void dcn10_link_encoder_disable_output(
 
 	if (!dcn10_is_dig_enabled(enc)) {
 		/* OF_SKIP_POWER_DOWN_INACTIVE_ENCODER */
+	/*in DP_Alt_No_Connect case, we turn off the dig already,
+	after excuation the PHY w/a sequence, not allow touch PHY any more*/
 		return;
 	}
 	/* Power-down RX and disable GPU PHY should be paired.
@@ -1347,8 +1349,7 @@ void dcn10_link_encoder_disable_hpd(struct link_encoder *enc)
 				FN(reg, f1), v1,\
 				FN(reg, f2), v2)
 
-static void aux_initialize(
-	struct dcn10_link_encoder *enc10)
+void dcn10_aux_initialize(struct dcn10_link_encoder *enc10)
 {
 	enum hpd_source_id hpd_source = enc10->base.hpd_source;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
index 2a97cdb2cfbb..49ead12b2532 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
@@ -42,6 +42,7 @@
 #define LE_DCN_COMMON_REG_LIST(id) \
 	SRI(DIG_BE_CNTL, DIG, id), \
 	SRI(DIG_BE_EN_CNTL, DIG, id), \
+	SRI(TMDS_CTL_BITS, DIG, id), \
 	SRI(DP_CONFIG, DP, id), \
 	SRI(DP_DPHY_CNTL, DP, id), \
 	SRI(DP_DPHY_PRBS_CNTL, DP, id), \
@@ -64,6 +65,7 @@
 	SRI(DP_DPHY_INTERNAL_CTRL, DP, id), \
 	SRI(DP_DPHY_HBR2_PATTERN_CONTROL, DP, id)
 
+
 #define LE_DCN10_REG_LIST(id)\
 	LE_DCN_COMMON_REG_LIST(id)
 
@@ -100,6 +102,7 @@ struct dcn10_link_enc_registers {
 	uint32_t DP_DPHY_BS_SR_SWAP_CNTL;
 	uint32_t DP_DPHY_HBR2_PATTERN_CONTROL;
 	uint32_t DP_SEC_CNTL1;
+	uint32_t TMDS_CTL_BITS;
 };
 
 #define LE_SF(reg_name, field_name, post_fix)\
@@ -110,6 +113,7 @@ struct dcn10_link_enc_registers {
 	LE_SF(DIG0_DIG_BE_CNTL, DIG_HPD_SELECT, mask_sh),\
 	LE_SF(DIG0_DIG_BE_CNTL, DIG_MODE, mask_sh),\
 	LE_SF(DIG0_DIG_BE_CNTL, DIG_FE_SOURCE_SELECT, mask_sh),\
+	LE_SF(DIG0_TMDS_CTL_BITS, TMDS_CTL0, mask_sh), \
 	LE_SF(DP0_DP_DPHY_CNTL, DPHY_BYPASS, mask_sh),\
 	LE_SF(DP0_DP_DPHY_CNTL, DPHY_ATEST_SEL_LANE0, mask_sh),\
 	LE_SF(DP0_DP_DPHY_CNTL, DPHY_ATEST_SEL_LANE1, mask_sh),\
@@ -198,10 +202,11 @@ struct dcn10_link_enc_registers {
 	type DP_MSE_SAT_SLOT_COUNT3;\
 	type DP_MSE_SAT_UPDATE;\
 	type DP_MSE_16_MTP_KEEPOUT;\
+	type DC_HPD_EN;\
+	type TMDS_CTL0;\
 	type AUX_HPD_SEL;\
 	type AUX_LS_READ_EN;\
-	type AUX_RX_RECEIVE_WINDOW;\
-	type DC_HPD_EN
+	type AUX_RX_RECEIVE_WINDOW
 
 struct dcn10_link_enc_shift {
 	DCN_LINK_ENCODER_REG_FIELD_LIST(uint8_t);
@@ -266,6 +271,10 @@ void dcn10_link_encoder_setup(
 	struct link_encoder *enc,
 	enum signal_type signal);
 
+void configure_encoder(
+	struct dcn10_link_encoder *enc10,
+	const struct dc_link_settings *link_settings);
+
 /* enables TMDS PHY output */
 /* TODO: still need depth or just pass in adjusted pixel clock? */
 void dcn10_link_encoder_enable_tmds_output(
@@ -327,4 +336,6 @@ void dcn10_psr_program_secondary_packet(struct link_encoder *enc,
 
 bool dcn10_is_dig_enabled(struct link_encoder *enc);
 
+void dcn10_aux_initialize(struct dcn10_link_encoder *enc10);
+
 #endif /* __DC_LINK_ENCODER__DCN10_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
index 9ca51ae46de7..958994edf2c4 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
@@ -428,7 +428,7 @@ void mpc1_read_mpcc_state(
 			MPCC_BUSY, &s->busy);
 }
 
-const struct mpc_funcs dcn10_mpc_funcs = {
+static const struct mpc_funcs dcn10_mpc_funcs = {
 	.read_mpcc_state = mpc1_read_mpcc_state,
 	.insert_plane = mpc1_insert_plane,
 	.remove_mpcc = mpc1_remove_mpcc,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
index 77a1a9d541a4..ab958cff3b76 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
@@ -385,7 +385,7 @@ void opp1_destroy(struct output_pixel_processor **opp)
 	*opp = NULL;
 }
 
-static struct opp_funcs dcn10_opp_funcs = {
+static const struct opp_funcs dcn10_opp_funcs = {
 		.opp_set_dyn_expansion = opp1_set_dyn_expansion,
 		.opp_program_fmt = opp1_program_fmt,
 		.opp_program_bit_depth_reduction = opp1_program_bit_depth_reduction,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
index f2fbce0e3fc5..411f89218e01 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
@@ -1257,6 +1257,37 @@ void optc1_read_otg_state(struct optc *optc1,
 			OPTC_UNDERFLOW_OCCURRED_STATUS, &s->underflow_occurred_status);
 }
 
+bool optc1_get_otg_active_size(struct timing_generator *optc,
+		uint32_t *otg_active_width,
+		uint32_t *otg_active_height)
+{
+	uint32_t otg_enabled;
+	uint32_t v_blank_start;
+	uint32_t v_blank_end;
+	uint32_t h_blank_start;
+	uint32_t h_blank_end;
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
+
+
+	REG_GET(OTG_CONTROL,
+			OTG_MASTER_EN, &otg_enabled);
+
+	if (otg_enabled == 0)
+		return false;
+
+	REG_GET_2(OTG_V_BLANK_START_END,
+			OTG_V_BLANK_START, &v_blank_start,
+			OTG_V_BLANK_END, &v_blank_end);
+
+	REG_GET_2(OTG_H_BLANK_START_END,
+			OTG_H_BLANK_START, &h_blank_start,
+			OTG_H_BLANK_END, &h_blank_end);
+
+	*otg_active_width = v_blank_start - v_blank_end;
+	*otg_active_height = h_blank_start - h_blank_end;
+	return true;
+}
+
 void optc1_clear_optc_underflow(struct timing_generator *optc)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
@@ -1293,6 +1324,72 @@ bool optc1_is_optc_underflow_occurred(struct timing_generator *optc)
 	return (underflow_occurred == 1);
 }
 
+bool optc1_configure_crc(struct timing_generator *optc,
+			  const struct crc_params *params)
+{
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
+
+	/* Cannot configure crc on a CRTC that is disabled */
+	if (!optc1_is_tg_enabled(optc))
+		return false;
+
+	REG_WRITE(OTG_CRC_CNTL, 0);
+
+	if (!params->enable)
+		return true;
+
+	/* Program frame boundaries */
+	/* Window A x axis start and end. */
+	REG_UPDATE_2(OTG_CRC0_WINDOWA_X_CONTROL,
+			OTG_CRC0_WINDOWA_X_START, params->windowa_x_start,
+			OTG_CRC0_WINDOWA_X_END, params->windowa_x_end);
+
+	/* Window A y axis start and end. */
+	REG_UPDATE_2(OTG_CRC0_WINDOWA_Y_CONTROL,
+			OTG_CRC0_WINDOWA_Y_START, params->windowa_y_start,
+			OTG_CRC0_WINDOWA_Y_END, params->windowa_y_end);
+
+	/* Window B x axis start and end. */
+	REG_UPDATE_2(OTG_CRC0_WINDOWB_X_CONTROL,
+			OTG_CRC0_WINDOWB_X_START, params->windowb_x_start,
+			OTG_CRC0_WINDOWB_X_END, params->windowb_x_end);
+
+	/* Window B y axis start and end. */
+	REG_UPDATE_2(OTG_CRC0_WINDOWB_Y_CONTROL,
+			OTG_CRC0_WINDOWB_Y_START, params->windowb_y_start,
+			OTG_CRC0_WINDOWB_Y_END, params->windowb_y_end);
+
+	/* Set crc mode and selection, and enable. Only using CRC0*/
+	REG_UPDATE_3(OTG_CRC_CNTL,
+			OTG_CRC_CONT_EN, params->continuous_mode ? 1 : 0,
+			OTG_CRC0_SELECT, params->selection,
+			OTG_CRC_EN, 1);
+
+	return true;
+}
+
+bool optc1_get_crc(struct timing_generator *optc,
+		    uint32_t *r_cr, uint32_t *g_y, uint32_t *b_cb)
+{
+	uint32_t field = 0;
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
+
+	REG_GET(OTG_CRC_CNTL, OTG_CRC_EN, &field);
+
+	/* Early return if CRC is not enabled for this CRTC */
+	if (!field)
+		return false;
+
+	REG_GET_2(OTG_CRC0_DATA_RG,
+			CRC0_R_CR, r_cr,
+			CRC0_G_Y, g_y);
+
+	REG_GET(OTG_CRC0_DATA_B,
+			CRC0_B_CB, b_cb);
+
+	return true;
+}
+
 static const struct timing_generator_funcs dcn10_tg_funcs = {
 		.validate_timing = optc1_validate_timing,
 		.program_timing = optc1_program_timing,
@@ -1305,6 +1402,7 @@ static const struct timing_generator_funcs dcn10_tg_funcs = {
 		.get_position = optc1_get_position,
 		.get_frame_count = optc1_get_vblank_counter,
 		.get_scanoutpos = optc1_get_crtc_scanoutpos,
+		.get_otg_active_size = optc1_get_otg_active_size,
 		.set_early_control = optc1_set_early_control,
 		/* used by enable_timing_synchronization. Not need for FPGA */
 		.wait_for_state = optc1_wait_for_state,
@@ -1328,6 +1426,8 @@ static const struct timing_generator_funcs dcn10_tg_funcs = {
 		.is_tg_enabled = optc1_is_tg_enabled,
 		.is_optc_underflow_occurred = optc1_is_optc_underflow_occurred,
 		.clear_optc_underflow = optc1_clear_optc_underflow,
+		.get_crc = optc1_get_crc,
+		.configure_crc = optc1_configure_crc,
 };
 
 void dcn10_timing_generator_init(struct optc *optc1)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
index c62052f46460..c1b114209fe8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
@@ -75,7 +75,14 @@
 	SRI(CONTROL, VTG, inst),\
 	SRI(OTG_VERT_SYNC_CONTROL, OTG, inst),\
 	SRI(OTG_MASTER_UPDATE_MODE, OTG, inst),\
-	SRI(OTG_GSL_CONTROL, OTG, inst)
+	SRI(OTG_GSL_CONTROL, OTG, inst),\
+	SRI(OTG_CRC_CNTL, OTG, inst),\
+	SRI(OTG_CRC0_DATA_RG, OTG, inst),\
+	SRI(OTG_CRC0_DATA_B, OTG, inst),\
+	SRI(OTG_CRC0_WINDOWA_X_CONTROL, OTG, inst),\
+	SRI(OTG_CRC0_WINDOWA_Y_CONTROL, OTG, inst),\
+	SRI(OTG_CRC0_WINDOWB_X_CONTROL, OTG, inst),\
+	SRI(OTG_CRC0_WINDOWB_Y_CONTROL, OTG, inst)
 
 #define TG_COMMON_REG_LIST_DCN1_0(inst) \
 	TG_COMMON_REG_LIST_DCN(inst),\
@@ -138,6 +145,13 @@ struct dcn_optc_registers {
 	uint32_t OTG_GSL_WINDOW_X;
 	uint32_t OTG_GSL_WINDOW_Y;
 	uint32_t OTG_VUPDATE_KEEPOUT;
+	uint32_t OTG_CRC_CNTL;
+	uint32_t OTG_CRC0_DATA_RG;
+	uint32_t OTG_CRC0_DATA_B;
+	uint32_t OTG_CRC0_WINDOWA_X_CONTROL;
+	uint32_t OTG_CRC0_WINDOWA_Y_CONTROL;
+	uint32_t OTG_CRC0_WINDOWB_X_CONTROL;
+	uint32_t OTG_CRC0_WINDOWB_Y_CONTROL;
 };
 
 #define TG_COMMON_MASK_SH_LIST_DCN(mask_sh)\
@@ -232,7 +246,21 @@ struct dcn_optc_registers {
 	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL2_EN, mask_sh),\
 	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL_MASTER_EN, mask_sh),\
 	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL_FORCE_DELAY, mask_sh),\
-	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL_CHECK_ALL_FIELDS, mask_sh)
+	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL_CHECK_ALL_FIELDS, mask_sh),\
+	SF(OTG0_OTG_CRC_CNTL, OTG_CRC_CONT_EN, mask_sh),\
+	SF(OTG0_OTG_CRC_CNTL, OTG_CRC0_SELECT, mask_sh),\
+	SF(OTG0_OTG_CRC_CNTL, OTG_CRC_EN, mask_sh),\
+	SF(OTG0_OTG_CRC0_DATA_RG, CRC0_R_CR, mask_sh),\
+	SF(OTG0_OTG_CRC0_DATA_RG, CRC0_G_Y, mask_sh),\
+	SF(OTG0_OTG_CRC0_DATA_B, CRC0_B_CB, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWA_X_CONTROL, OTG_CRC0_WINDOWA_X_START, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWA_X_CONTROL, OTG_CRC0_WINDOWA_X_END, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWA_Y_CONTROL, OTG_CRC0_WINDOWA_Y_START, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWA_Y_CONTROL, OTG_CRC0_WINDOWA_Y_END, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWB_X_CONTROL, OTG_CRC0_WINDOWB_X_START, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWB_X_CONTROL, OTG_CRC0_WINDOWB_X_END, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWB_Y_CONTROL, OTG_CRC0_WINDOWB_Y_START, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWB_Y_CONTROL, OTG_CRC0_WINDOWB_Y_END, mask_sh)
 
 
 #define TG_COMMON_MASK_SH_LIST_DCN1_0(mask_sh)\
@@ -363,7 +391,22 @@ struct dcn_optc_registers {
 	type OTG_MASTER_UPDATE_LOCK_GSL_EN;\
 	type MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_START_OFFSET;\
 	type MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_END_OFFSET;\
-	type OTG_MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_EN;
+	type OTG_MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_EN;\
+	type OTG_CRC_CONT_EN;\
+	type OTG_CRC0_SELECT;\
+	type OTG_CRC_EN;\
+	type CRC0_R_CR;\
+	type CRC0_G_Y;\
+	type CRC0_B_CB;\
+	type OTG_CRC0_WINDOWA_X_START;\
+	type OTG_CRC0_WINDOWA_X_END;\
+	type OTG_CRC0_WINDOWA_Y_START;\
+	type OTG_CRC0_WINDOWA_Y_END;\
+	type OTG_CRC0_WINDOWB_X_START;\
+	type OTG_CRC0_WINDOWB_X_END;\
+	type OTG_CRC0_WINDOWB_Y_START;\
+	type OTG_CRC0_WINDOWB_Y_END;
+
 
 #define TG_REG_FIELD_LIST(type) \
 	TG_REG_FIELD_LIST_DCN1_0(type)
@@ -507,4 +550,19 @@ bool optc1_is_optc_underflow_occurred(struct timing_generator *optc);
 
 void optc1_set_blank_data_double_buffer(struct timing_generator *optc, bool enable);
 
+bool optc1_get_otg_active_size(struct timing_generator *optc,
+		uint32_t *otg_active_width,
+		uint32_t *otg_active_height);
+
+void optc1_enable_crtc_reset(
+		struct timing_generator *optc,
+		int source_tg_inst,
+		struct crtc_trigger_info *crtc_tp);
+
+bool optc1_configure_crc(struct timing_generator *optc,
+			  const struct crc_params *params);
+
+bool optc1_get_crc(struct timing_generator *optc,
+		    uint32_t *r_cr, uint32_t *g_y, uint32_t *b_cb);
+
 #endif /* __DC_TIMING_GENERATOR_DCN10_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 34dac84066a0..6b44ed3697a4 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -64,6 +64,69 @@
 #include "reg_helper.h"
 #include "dce/dce_abm.h"
 #include "dce/dce_dmcu.h"
+#include "dce/dce_aux.h"
+
+const struct _vcs_dpi_ip_params_st dcn1_0_ip = {
+	.rob_buffer_size_kbytes = 64,
+	.det_buffer_size_kbytes = 164,
+	.dpte_buffer_size_in_pte_reqs = 42,
+	.dpp_output_buffer_pixels = 2560,
+	.opp_output_buffer_lines = 1,
+	.pixel_chunk_size_kbytes = 8,
+	.pte_enable = 1,
+	.pte_chunk_size_kbytes = 2,
+	.meta_chunk_size_kbytes = 2,
+	.writeback_chunk_size_kbytes = 2,
+	.line_buffer_size_bits = 589824,
+	.max_line_buffer_lines = 12,
+	.IsLineBufferBppFixed = 0,
+	.LineBufferFixedBpp = -1,
+	.writeback_luma_buffer_size_kbytes = 12,
+	.writeback_chroma_buffer_size_kbytes = 8,
+	.max_num_dpp = 4,
+	.max_num_wb = 2,
+	.max_dchub_pscl_bw_pix_per_clk = 4,
+	.max_pscl_lb_bw_pix_per_clk = 2,
+	.max_lb_vscl_bw_pix_per_clk = 4,
+	.max_vscl_hscl_bw_pix_per_clk = 4,
+	.max_hscl_ratio = 4,
+	.max_vscl_ratio = 4,
+	.hscl_mults = 4,
+	.vscl_mults = 4,
+	.max_hscl_taps = 8,
+	.max_vscl_taps = 8,
+	.dispclk_ramp_margin_percent = 1,
+	.underscan_factor = 1.10,
+	.min_vblank_lines = 14,
+	.dppclk_delay_subtotal = 90,
+	.dispclk_delay_subtotal = 42,
+	.dcfclk_cstate_latency = 10,
+	.max_inter_dcn_tile_repeaters = 8,
+	.can_vstartup_lines_exceed_vsync_plus_back_porch_lines_minus_one = 0,
+	.bug_forcing_LC_req_same_size_fixed = 0,
+};
+
+const struct _vcs_dpi_soc_bounding_box_st dcn1_0_soc = {
+	.sr_exit_time_us = 9.0,
+	.sr_enter_plus_exit_time_us = 11.0,
+	.urgent_latency_us = 4.0,
+	.writeback_latency_us = 12.0,
+	.ideal_dram_bw_after_urgent_percent = 80.0,
+	.max_request_size_bytes = 256,
+	.downspread_percent = 0.5,
+	.dram_page_open_time_ns = 50.0,
+	.dram_rw_turnaround_time_ns = 17.5,
+	.dram_return_buffer_per_channel_bytes = 8192,
+	.round_trip_ping_latency_dcfclk_cycles = 128,
+	.urgent_out_of_order_return_per_channel_bytes = 256,
+	.channel_interleave_bytes = 256,
+	.num_banks = 8,
+	.num_chans = 2,
+	.vmm_page_size_bytes = 4096,
+	.dram_clock_change_latency_us = 17.0,
+	.writeback_dram_clock_change_latency_us = 23.0,
+	.return_bus_width_bytes = 64,
+};
 
 #ifndef mmDP0_DP_DPHY_INTERNAL_CTRL
 	#define mmDP0_DP_DPHY_INTERNAL_CTRL		0x210f
@@ -294,6 +357,21 @@ static const struct dcn10_opp_mask opp_mask = {
 		OPP_MASK_SH_LIST_DCN10(_MASK),
 };
 
+#define aux_engine_regs(id)\
+[id] = {\
+	AUX_COMMON_REG_LIST(id), \
+	.AUX_RESET_MASK = 0 \
+}
+
+static const struct dce110_aux_registers aux_engine_regs[] = {
+		aux_engine_regs(0),
+		aux_engine_regs(1),
+		aux_engine_regs(2),
+		aux_engine_regs(3),
+		aux_engine_regs(4),
+		aux_engine_regs(5)
+};
+
 #define tf_regs(id)\
 [id] = {\
 	TF_REG_LIST_DCN10(id),\
@@ -417,13 +495,14 @@ static const struct dce110_clk_src_mask cs_mask = {
 
 static const struct resource_caps res_cap = {
 		.num_timing_generator = 4,
+		.num_opp = 4,
 		.num_video_plane = 4,
 		.num_audio = 4,
 		.num_stream_encoder = 4,
 		.num_pll = 4,
 };
 
-static const struct dc_debug debug_defaults_drv = {
+static const struct dc_debug_options debug_defaults_drv = {
 		.sanity_checks = true,
 		.disable_dmcu = true,
 		.force_abm_enable = false,
@@ -436,7 +515,7 @@ static const struct dc_debug debug_defaults_drv = {
 		 */
 		.min_disp_clk_khz = 100000,
 
-		.disable_pplib_clock_request = true,
+		.disable_pplib_clock_request = false,
 		.disable_pplib_wm_range = false,
 		.pplib_wm_report_mode = WM_REPORT_DEFAULT,
 		.pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP,
@@ -451,7 +530,7 @@ static const struct dc_debug debug_defaults_drv = {
 		.max_downscale_src_width = 3840,
 };
 
-static const struct dc_debug debug_defaults_diags = {
+static const struct dc_debug_options debug_defaults_diags = {
 		.disable_dmcu = true,
 		.force_abm_enable = false,
 		.timing_trace = true,
@@ -515,6 +594,23 @@ static struct output_pixel_processor *dcn10_opp_create(
 	return &opp->base;
 }
 
+struct aux_engine *dcn10_aux_engine_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct aux_engine_dce110 *aux_engine =
+		kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL);
+
+	if (!aux_engine)
+		return NULL;
+
+	dce110_aux_engine_construct(aux_engine, ctx, inst,
+				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
+				    &aux_engine_regs[inst]);
+
+	return &aux_engine->base;
+}
+
 static struct mpc *dcn10_mpc_create(struct dc_context *ctx)
 {
 	struct dcn10_mpc *mpc10 = kzalloc(sizeof(struct dcn10_mpc),
@@ -680,6 +776,7 @@ static struct dce_hwseq *dcn10_hwseq_create(
 		hws->masks = &hwseq_mask;
 		hws->wa.DEGVIDCN10_253 = true;
 		hws->wa.false_optc_underflow = true;
+		hws->wa.DEGVIDCN10_254 = true;
 	}
 	return hws;
 }
@@ -762,6 +859,9 @@ static void destruct(struct dcn10_resource_pool *pool)
 			kfree(DCN10TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+
+		if (pool->base.engines[i] != NULL)
+			pool->base.engines[i]->funcs->destroy_engine(&pool->base.engines[i]);
 	}
 
 	for (i = 0; i < pool->base.stream_enc_count; i++)
@@ -790,8 +890,8 @@ static void destruct(struct dcn10_resource_pool *pool)
 	if (pool->base.dmcu != NULL)
 		dce_dmcu_destroy(&pool->base.dmcu);
 
-	if (pool->base.display_clock != NULL)
-		dce_disp_clk_destroy(&pool->base.display_clock);
+	if (pool->base.dccg != NULL)
+		dce_dccg_destroy(&pool->base.dccg);
 
 	kfree(pool->base.pp_smu);
 }
@@ -971,11 +1071,11 @@ static enum dc_status dcn10_validate_plane(const struct dc_plane_state *plane_st
 	return DC_OK;
 }
 
-static struct dc_cap_funcs cap_funcs = {
+static const struct dc_cap_funcs cap_funcs = {
 	.get_dcc_compression_cap = dcn10_get_dcc_compression_cap
 };
 
-static struct resource_funcs dcn10_res_pool_funcs = {
+static const struct resource_funcs dcn10_res_pool_funcs = {
 	.destroy = dcn10_destroy_resource_pool,
 	.link_enc_create = dcn10_link_encoder_create,
 	.validate_bandwidth = dcn_validate_bandwidth,
@@ -1072,8 +1172,8 @@ static bool construct(
 		}
 	}
 
-	pool->base.display_clock = dce120_disp_clk_create(ctx);
-	if (pool->base.display_clock == NULL) {
+	pool->base.dccg = dcn1_dccg_create(ctx);
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto fail;
@@ -1193,6 +1293,14 @@ static bool construct(
 			goto fail;
 		}
 
+		pool->base.engines[i] = dcn10_aux_engine_create(ctx, i);
+		if (pool->base.engines[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create aux engine!!\n");
+			goto fail;
+		}
+
 		/* check next valid pipe */
 		j++;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
index c928ee4cd382..6f9078f3c4d3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
@@ -257,20 +257,18 @@ void enc1_stream_encoder_dp_set_stream_attribute(
 	uint8_t colorimetry_bpc;
 	uint8_t dynamic_range_rgb = 0; /*full range*/
 	uint8_t dynamic_range_ycbcr = 1; /*bt709*/
+	uint8_t dp_pixel_encoding = 0;
+	uint8_t dp_component_depth = 0;
 
 	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
 
-	REG_UPDATE(DP_DB_CNTL, DP_DB_DISABLE, 1);
-
 	/* set pixel encoding */
 	switch (crtc_timing->pixel_encoding) {
 	case PIXEL_ENCODING_YCBCR422:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
-				DP_PIXEL_ENCODING_TYPE_YCBCR422);
+		dp_pixel_encoding = DP_PIXEL_ENCODING_TYPE_YCBCR422;
 		break;
 	case PIXEL_ENCODING_YCBCR444:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
-				DP_PIXEL_ENCODING_TYPE_YCBCR444);
+		dp_pixel_encoding = DP_PIXEL_ENCODING_TYPE_YCBCR444;
 
 		if (crtc_timing->flags.Y_ONLY)
 			if (crtc_timing->display_color_depth != COLOR_DEPTH_666)
@@ -278,8 +276,8 @@ void enc1_stream_encoder_dp_set_stream_attribute(
 				 * Color depth of Y-only could be
 				 * 8, 10, 12, 16 bits
 				 */
-				REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
-						DP_PIXEL_ENCODING_TYPE_Y_ONLY);
+				dp_pixel_encoding = DP_PIXEL_ENCODING_TYPE_Y_ONLY;
+
 		/* Note: DP_MSA_MISC1 bit 7 is the indicator
 		 * of Y-only mode.
 		 * This bit is set in HW if register
@@ -287,48 +285,55 @@ void enc1_stream_encoder_dp_set_stream_attribute(
 		 */
 		break;
 	case PIXEL_ENCODING_YCBCR420:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
-				DP_PIXEL_ENCODING_TYPE_YCBCR420);
+		dp_pixel_encoding = DP_PIXEL_ENCODING_TYPE_YCBCR420;
 		REG_UPDATE(DP_VID_TIMING, DP_VID_N_MUL, 1);
 		break;
 	default:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
-				DP_PIXEL_ENCODING_TYPE_RGB444);
+		dp_pixel_encoding = DP_PIXEL_ENCODING_TYPE_RGB444;
 		break;
 	}
 
 	misc1 = REG_READ(DP_MSA_MISC);
+	/* For YCbCr420 and BT2020 Colorimetry Formats, VSC SDP shall be used.
+	 * When MISC1, bit 6, is Set to 1, a Source device uses a VSC SDP to indicate the
+	 * Pixel Encoding/Colorimetry Format and that a Sink device shall ignore MISC1, bit 7,
+	 * and MISC0, bits 7:1 (MISC1, bit 7, and MISC0, bits 7:1, become "don't care").
+	 */
+	if ((crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR420) ||
+			(output_color_space == COLOR_SPACE_2020_YCBCR) ||
+			(output_color_space == COLOR_SPACE_2020_RGB_FULLRANGE) ||
+			(output_color_space == COLOR_SPACE_2020_RGB_LIMITEDRANGE))
+		misc1 = misc1 | 0x40;
+	else
+		misc1 = misc1 & ~0x40;
 
 	/* set color depth */
-
 	switch (crtc_timing->display_color_depth) {
 	case COLOR_DEPTH_666:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
-				0);
+		dp_component_depth = DP_COMPONENT_PIXEL_DEPTH_6BPC;
 		break;
 	case COLOR_DEPTH_888:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
-				DP_COMPONENT_PIXEL_DEPTH_8BPC);
+		dp_component_depth = DP_COMPONENT_PIXEL_DEPTH_8BPC;
 		break;
 	case COLOR_DEPTH_101010:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
-				DP_COMPONENT_PIXEL_DEPTH_10BPC);
-
+		dp_component_depth = DP_COMPONENT_PIXEL_DEPTH_10BPC;
 		break;
 	case COLOR_DEPTH_121212:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
-				DP_COMPONENT_PIXEL_DEPTH_12BPC);
+		dp_component_depth = DP_COMPONENT_PIXEL_DEPTH_12BPC;
 		break;
 	case COLOR_DEPTH_161616:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
-				DP_COMPONENT_PIXEL_DEPTH_16BPC);
+		dp_component_depth = DP_COMPONENT_PIXEL_DEPTH_16BPC;
 		break;
 	default:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
-				DP_COMPONENT_PIXEL_DEPTH_6BPC);
+		dp_component_depth = DP_COMPONENT_PIXEL_DEPTH_6BPC;
 		break;
 	}
 
+	/* Set DP pixel encoding and component depth */
+	REG_UPDATE_2(DP_PIXEL_FORMAT,
+			DP_PIXEL_ENCODING, dp_pixel_encoding,
+			DP_COMPONENT_DEPTH, dp_component_depth);
+
 	/* set dynamic range and YCbCr range */
 
 	switch (crtc_timing->display_color_depth) {
@@ -354,7 +359,6 @@ void enc1_stream_encoder_dp_set_stream_attribute(
 
 	switch (output_color_space) {
 	case COLOR_SPACE_SRGB:
-		misc0 = misc0 | 0x0;
 		misc1 = misc1 & ~0x80; /* bit7 = 0*/
 		dynamic_range_rgb = 0; /*full range*/
 		break;
@@ -1087,27 +1091,6 @@ static union audio_cea_channels speakers_to_channels(
 	return cea_channels;
 }
 
-static uint32_t calc_max_audio_packets_per_line(
-	const struct audio_crtc_info *crtc_info)
-{
-	uint32_t max_packets_per_line;
-
-	max_packets_per_line =
-		crtc_info->h_total - crtc_info->h_active;
-
-	if (crtc_info->pixel_repetition)
-		max_packets_per_line *= crtc_info->pixel_repetition;
-
-	/* for other hdmi features */
-	max_packets_per_line -= 58;
-	/* for Control Period */
-	max_packets_per_line -= 16;
-	/* Number of Audio Packets per Line */
-	max_packets_per_line /= 32;
-
-	return max_packets_per_line;
-}
-
 static void get_audio_clock_info(
 	enum dc_color_depth color_depth,
 	uint32_t crtc_pixel_clock_in_khz,
@@ -1201,16 +1184,9 @@ static void enc1_se_setup_hdmi_audio(
 	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
 
 	struct audio_clock_info audio_clock_info = {0};
-	uint32_t max_packets_per_line;
-
-	/* For now still do calculation, although this field is ignored when
-	 * above HDMI_PACKET_GEN_VERSION set to 1
-	 */
-	max_packets_per_line = calc_max_audio_packets_per_line(crtc_info);
 
 	/* HDMI_AUDIO_PACKET_CONTROL */
-	REG_UPDATE_2(HDMI_AUDIO_PACKET_CONTROL,
-			HDMI_AUDIO_PACKETS_PER_LINE, max_packets_per_line,
+	REG_UPDATE(HDMI_AUDIO_PACKET_CONTROL,
 			HDMI_AUDIO_DELAY_EN, 1);
 
 	/* AFMT_AUDIO_PACKET_CONTROL */
diff --git a/drivers/gpu/drm/amd/display/dc/dm_helpers.h b/drivers/gpu/drm/amd/display/dc/dm_helpers.h
index 034369fbb9e2..5d4527d03045 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_helpers.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_helpers.h
@@ -40,6 +40,14 @@ enum dc_edid_status dm_helpers_parse_edid_caps(
 	const struct dc_edid *edid,
 	struct dc_edid_caps *edid_caps);
 
+
+/*
+ * Update DP branch info
+ */
+void dm_helpers_dp_update_branch_info(
+		struct dc_context *ctx,
+		const struct dc_link *link);
+
 /*
  * Writes payload allocation table in immediate downstream device.
  */
@@ -103,6 +111,9 @@ bool dm_helpers_submit_i2c(
 		const struct dc_link *link,
 		struct i2c_command *cmd);
 
+bool dm_helpers_is_dp_sink_present(
+		struct dc_link *link);
+
 enum dc_edid_status dm_helpers_read_local_edid(
 		struct dc_context *ctx,
 		struct dc_link *link,
diff --git a/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h b/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h
index eac4bfe12257..58ed2055ef9f 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h
@@ -40,7 +40,7 @@ enum wm_set_id {
 	WM_B,
 	WM_C,
 	WM_D,
-	WM_COUNT,
+	WM_SET_COUNT,
 };
 
 struct pp_smu_wm_set_range {
@@ -53,10 +53,10 @@ struct pp_smu_wm_set_range {
 
 struct pp_smu_wm_range_sets {
 	uint32_t num_reader_wm_sets;
-	struct pp_smu_wm_set_range reader_wm_sets[WM_COUNT];
+	struct pp_smu_wm_set_range reader_wm_sets[WM_SET_COUNT];
 
 	uint32_t num_writer_wm_sets;
-	struct pp_smu_wm_set_range writer_wm_sets[WM_COUNT];
+	struct pp_smu_wm_set_range writer_wm_sets[WM_SET_COUNT];
 };
 
 struct pp_smu_display_requirement_rv {
diff --git a/drivers/gpu/drm/amd/display/dc/dm_services.h b/drivers/gpu/drm/amd/display/dc/dm_services.h
index 4ff9b2bba178..eb5ab3978e84 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_services.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_services.h
@@ -339,7 +339,10 @@ bool dm_dmcu_set_pipe(struct dc_context *ctx, unsigned int controller_id);
 #define dm_log_to_buffer(buffer, size, fmt, args)\
 	vsnprintf(buffer, size, fmt, args)
 
-unsigned long long dm_get_timestamp(struct dc_context *ctx);
+static inline unsigned long long dm_get_timestamp(struct dc_context *ctx)
+{
+	return ktime_get_raw_ns();
+}
 
 unsigned long long dm_get_elapse_time_in_ns(struct dc_context *ctx,
 		unsigned long long current_time_stamp,
diff --git a/drivers/gpu/drm/amd/display/dc/dm_services_types.h b/drivers/gpu/drm/amd/display/dc/dm_services_types.h
index ab8c77d4e6df..2b83f922ac02 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_services_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_services_types.h
@@ -137,7 +137,7 @@ struct dm_pp_clock_range_for_wm_set {
 	enum dm_pp_wm_set_id wm_set_id;
 	uint32_t wm_min_eng_clk_in_khz;
 	uint32_t wm_max_eng_clk_in_khz;
-	uint32_t wm_min_memg_clk_in_khz;
+	uint32_t wm_min_mem_clk_in_khz;
 	uint32_t wm_max_mem_clk_in_khz;
 };
 
@@ -150,7 +150,7 @@ struct dm_pp_clock_range_for_dmif_wm_set_soc15 {
 	enum dm_pp_wm_set_id wm_set_id;
 	uint32_t wm_min_dcfclk_clk_in_khz;
 	uint32_t wm_max_dcfclk_clk_in_khz;
-	uint32_t wm_min_memg_clk_in_khz;
+	uint32_t wm_min_mem_clk_in_khz;
 	uint32_t wm_max_mem_clk_in_khz;
 };
 
@@ -158,7 +158,7 @@ struct dm_pp_clock_range_for_mcif_wm_set_soc15 {
 	enum dm_pp_wm_set_id wm_set_id;
 	uint32_t wm_min_socclk_clk_in_khz;
 	uint32_t wm_max_socclk_clk_in_khz;
-	uint32_t wm_min_memg_clk_in_khz;
+	uint32_t wm_min_mem_clk_in_khz;
 	uint32_t wm_max_mem_clk_in_khz;
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index f83a608f93e9..d97ca6528f9d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -36,11 +36,10 @@ CFLAGS_display_mode_lib.o := $(dml_ccflags)
 CFLAGS_display_pipe_clocks.o := $(dml_ccflags)
 CFLAGS_dml1_display_rq_dlg_calc.o := $(dml_ccflags)
 CFLAGS_display_rq_dlg_helpers.o := $(dml_ccflags)
-CFLAGS_soc_bounding_box.o := $(dml_ccflags)
 CFLAGS_dml_common_defs.o := $(dml_ccflags)
 
 DML = display_mode_lib.o display_rq_dlg_helpers.o dml1_display_rq_dlg_calc.o \
-	  soc_bounding_box.o dml_common_defs.o
+	dml_common_defs.o
 
 AMD_DAL_DML = $(addprefix $(AMDDALPATH)/dc/dml/,$(DML))
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
index fd9d97aab071..dddeb0d4db8f 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
@@ -26,67 +26,8 @@
 #include "display_mode_lib.h"
 #include "dc_features.h"
 
-static const struct _vcs_dpi_ip_params_st dcn1_0_ip = {
-	.rob_buffer_size_kbytes = 64,
-	.det_buffer_size_kbytes = 164,
-	.dpte_buffer_size_in_pte_reqs = 42,
-	.dpp_output_buffer_pixels = 2560,
-	.opp_output_buffer_lines = 1,
-	.pixel_chunk_size_kbytes = 8,
-	.pte_enable = 1,
-	.pte_chunk_size_kbytes = 2,
-	.meta_chunk_size_kbytes = 2,
-	.writeback_chunk_size_kbytes = 2,
-	.line_buffer_size_bits = 589824,
-	.max_line_buffer_lines = 12,
-	.IsLineBufferBppFixed = 0,
-	.LineBufferFixedBpp = -1,
-	.writeback_luma_buffer_size_kbytes = 12,
-	.writeback_chroma_buffer_size_kbytes = 8,
-	.max_num_dpp = 4,
-	.max_num_wb = 2,
-	.max_dchub_pscl_bw_pix_per_clk = 4,
-	.max_pscl_lb_bw_pix_per_clk = 2,
-	.max_lb_vscl_bw_pix_per_clk = 4,
-	.max_vscl_hscl_bw_pix_per_clk = 4,
-	.max_hscl_ratio = 4,
-	.max_vscl_ratio = 4,
-	.hscl_mults = 4,
-	.vscl_mults = 4,
-	.max_hscl_taps = 8,
-	.max_vscl_taps = 8,
-	.dispclk_ramp_margin_percent = 1,
-	.underscan_factor = 1.10,
-	.min_vblank_lines = 14,
-	.dppclk_delay_subtotal = 90,
-	.dispclk_delay_subtotal = 42,
-	.dcfclk_cstate_latency = 10,
-	.max_inter_dcn_tile_repeaters = 8,
-	.can_vstartup_lines_exceed_vsync_plus_back_porch_lines_minus_one = 0,
-	.bug_forcing_LC_req_same_size_fixed = 0,
-};
-
-static const struct _vcs_dpi_soc_bounding_box_st dcn1_0_soc = {
-	.sr_exit_time_us = 9.0,
-	.sr_enter_plus_exit_time_us = 11.0,
-	.urgent_latency_us = 4.0,
-	.writeback_latency_us = 12.0,
-	.ideal_dram_bw_after_urgent_percent = 80.0,
-	.max_request_size_bytes = 256,
-	.downspread_percent = 0.5,
-	.dram_page_open_time_ns = 50.0,
-	.dram_rw_turnaround_time_ns = 17.5,
-	.dram_return_buffer_per_channel_bytes = 8192,
-	.round_trip_ping_latency_dcfclk_cycles = 128,
-	.urgent_out_of_order_return_per_channel_bytes = 256,
-	.channel_interleave_bytes = 256,
-	.num_banks = 8,
-	.num_chans = 2,
-	.vmm_page_size_bytes = 4096,
-	.dram_clock_change_latency_us = 17.0,
-	.writeback_dram_clock_change_latency_us = 23.0,
-	.return_bus_width_bytes = 64,
-};
+extern const struct _vcs_dpi_ip_params_st dcn1_0_ip;
+extern const struct _vcs_dpi_soc_bounding_box_st dcn1_0_soc;
 
 static void set_soc_bounding_box(struct _vcs_dpi_soc_bounding_box_st *soc, enum dml_project project)
 {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
index 3c2abcb8a1b0..635206248889 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
@@ -27,7 +27,6 @@
 
 
 #include "dml_common_defs.h"
-#include "soc_bounding_box.h"
 #include "dml1_display_rq_dlg_calc.h"
 
 enum dml_project {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
index 7fa0375939ae..cbafce649e33 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
@@ -64,10 +64,9 @@ struct _vcs_dpi_voltage_scaling_st {
 	double dscclk_mhz;
 	double dcfclk_mhz;
 	double socclk_mhz;
-	double dram_speed_mhz;
+	double dram_speed_mts;
 	double fabricclk_mhz;
 	double dispclk_mhz;
-	double dram_bw_per_chan_gbps;
 	double phyclk_mhz;
 	double dppclk_mhz;
 };
@@ -112,6 +111,8 @@ struct _vcs_dpi_soc_bounding_box_st {
 	double xfc_bus_transport_time_us;
 	double xfc_xbuf_latency_tolerance_us;
 	int use_urgent_burst_bw;
+	double max_hscl_ratio;
+	double max_vscl_ratio;
 	struct _vcs_dpi_voltage_scaling_st clock_limits[7];
 };
 
@@ -304,6 +305,7 @@ struct _vcs_dpi_display_pipe_dest_params_st {
 	unsigned char otg_inst;
 	unsigned char odm_split_cnt;
 	unsigned char odm_combine;
+	unsigned char use_maximum_vstartup;
 };
 
 struct _vcs_dpi_display_pipe_params_st {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.c b/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.c
deleted file mode 100644
index 324239c77958..000000000000
--- a/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.c
+++ /dev/null
@@ -1,79 +0,0 @@
-/*
- * Copyright 2017 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: AMD
- *
- */
-#include "soc_bounding_box.h"
-#include "display_mode_lib.h"
-#include "dc_features.h"
-
-#include "dml_inline_defs.h"
-
-/*
- * NOTE:
- *   This file is gcc-parseable HW gospel, coming straight from HW engineers.
- *
- * It doesn't adhere to Linux kernel style and sometimes will do things in odd
- * ways. Unless there is something clearly wrong with it the code should
- * remain as-is as it provides us with a guarantee from HW that it is correct.
- */
-
-void dml_socbb_set_latencies(soc_bounding_box_st *to_box, soc_bounding_box_st *from_box)
-{
-	to_box->dram_clock_change_latency_us = from_box->dram_clock_change_latency_us;
-	to_box->sr_exit_time_us = from_box->sr_exit_time_us;
-	to_box->sr_enter_plus_exit_time_us = from_box->sr_enter_plus_exit_time_us;
-	to_box->urgent_latency_us = from_box->urgent_latency_us;
-	to_box->writeback_latency_us = from_box->writeback_latency_us;
-}
-
-voltage_scaling_st dml_socbb_voltage_scaling(
-		const soc_bounding_box_st *soc,
-		enum voltage_state voltage)
-{
-	const voltage_scaling_st *voltage_state;
-	const voltage_scaling_st * const voltage_end = soc->clock_limits + DC__VOLTAGE_STATES;
-
-	for (voltage_state = soc->clock_limits;
-			voltage_state < voltage_end && voltage_state->state != voltage;
-			voltage_state++) {
-	}
-
-	if (voltage_state < voltage_end)
-		return *voltage_state;
-	return soc->clock_limits[DC__VOLTAGE_STATES - 1];
-}
-
-double dml_socbb_return_bw_mhz(soc_bounding_box_st *box, enum voltage_state voltage)
-{
-	double return_bw;
-
-	voltage_scaling_st state = dml_socbb_voltage_scaling(box, voltage);
-
-	return_bw = dml_min((double) box->return_bus_width_bytes * state.dcfclk_mhz,
-			state.dram_bw_per_chan_gbps * 1000.0 * (double) box->num_chans
-					* box->ideal_dram_bw_after_urgent_percent / 100.0);
-
-	return_bw = dml_min((double) box->return_bus_width_bytes * state.fabricclk_mhz, return_bw);
-
-	return return_bw;
-}
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/Makefile b/drivers/gpu/drm/amd/display/dc/gpio/Makefile
index 562ee189d780..b9d9930a4974 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/gpio/Makefile
@@ -61,7 +61,7 @@ AMD_DISPLAY_FILES += $(AMD_DAL_GPIO_DCE120)
 ###############################################################################
 # DCN 1x
 ###############################################################################
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_X86
 GPIO_DCN10 = hw_translate_dcn10.o hw_factory_dcn10.o
 
 AMD_DAL_GPIO_DCN10 = $(addprefix $(AMDDALPATH)/dc/gpio/dcn10/,$(GPIO_DCN10))
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/ddc_regs.h b/drivers/gpu/drm/amd/display/dc/gpio/ddc_regs.h
index 9c4a56c738c0..bf40725f982f 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/ddc_regs.h
+++ b/drivers/gpu/drm/amd/display/dc/gpio/ddc_regs.h
@@ -82,13 +82,16 @@
 	DDC_GPIO_I2C_REG_LIST(cd),\
 	.ddc_setup = 0
 
-#define DDC_MASK_SH_LIST(mask_sh) \
+#define DDC_MASK_SH_LIST_COMMON(mask_sh) \
 		SF_DDC(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_ENABLE, mask_sh),\
 		SF_DDC(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_EDID_DETECT_ENABLE, mask_sh),\
 		SF_DDC(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_EDID_DETECT_MODE, mask_sh),\
 		SF_DDC(DC_GPIO_DDC1_MASK, DC_GPIO_DDC1DATA_PD_EN, mask_sh),\
 		SF_DDC(DC_GPIO_DDC1_MASK, DC_GPIO_DDC1CLK_PD_EN, mask_sh),\
-		SF_DDC(DC_GPIO_DDC1_MASK, AUX_PAD1_MODE, mask_sh),\
+		SF_DDC(DC_GPIO_DDC1_MASK, AUX_PAD1_MODE, mask_sh)
+
+#define DDC_MASK_SH_LIST(mask_sh) \
+		DDC_MASK_SH_LIST_COMMON(mask_sh),\
 		SF_DDC(DC_GPIO_I2CPAD_MASK, DC_GPIO_SDA_PD_DIS, mask_sh),\
 		SF_DDC(DC_GPIO_I2CPAD_MASK, DC_GPIO_SCL_PD_DIS, mask_sh)
 
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c b/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c
index ab5483c0c502..f20161c5706d 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c
@@ -375,6 +375,7 @@ struct gpio *dal_gpio_create_irq(
 	case GPIO_ID_GPIO_PAD:
 	break;
 	default:
+		id = GPIO_ID_HPD;
 		ASSERT_CRITICAL(false);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
index 0caee3523017..83df779984e5 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
@@ -43,7 +43,7 @@
 #include "dce80/hw_factory_dce80.h"
 #include "dce110/hw_factory_dce110.h"
 #include "dce120/hw_factory_dce120.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "dcn10/hw_factory_dcn10.h"
 #endif
 
@@ -81,7 +81,7 @@ bool dal_hw_factory_init(
 	case DCE_VERSION_12_0:
 		dal_hw_factory_dce120_init(factory);
 		return true;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 		dal_hw_factory_dcn10_init(factory);
 		return true;
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
index 55c707488541..e7541310480b 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
@@ -43,7 +43,7 @@
 #include "dce80/hw_translate_dce80.h"
 #include "dce110/hw_translate_dce110.h"
 #include "dce120/hw_translate_dce120.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "dcn10/hw_translate_dcn10.h"
 #endif
 
@@ -78,7 +78,7 @@ bool dal_hw_translate_init(
 	case DCE_VERSION_12_0:
 		dal_hw_translate_dce120_init(translate);
 		return true;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 		dal_hw_translate_dcn10_init(translate);
 		return true;
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/Makefile b/drivers/gpu/drm/amd/display/dc/i2caux/Makefile
index 352885cb4d07..a851d07f0190 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/Makefile
@@ -71,7 +71,7 @@ AMD_DISPLAY_FILES += $(AMD_DAL_I2CAUX_DCE112)
 ###############################################################################
 # DCN 1.0 family
 ###############################################################################
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_X86
 I2CAUX_DCN1 = i2caux_dcn10.o
 
 AMD_DAL_I2CAUX_DCN1 = $(addprefix $(AMDDALPATH)/dc/i2caux/dcn10/,$(I2CAUX_DCN1))
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.c b/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.c
index bb526ad326e5..0afd2fa57bbe 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.c
@@ -128,8 +128,20 @@ static void process_read_reply(
 			ctx->status =
 				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
 			ctx->operation_succeeded = false;
+		} else if (ctx->returned_byte < ctx->current_read_length) {
+			ctx->current_read_length -= ctx->returned_byte;
+
+			ctx->offset += ctx->returned_byte;
+
+			++ctx->invalid_reply_retry_aux_on_ack;
+
+			if (ctx->invalid_reply_retry_aux_on_ack >
+				AUX_INVALID_REPLY_RETRY_COUNTER) {
+				ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
+				ctx->operation_succeeded = false;
+			}
 		} else {
-			ctx->current_read_length = ctx->returned_byte;
 			ctx->status = I2CAUX_TRANSACTION_STATUS_SUCCEEDED;
 			ctx->transaction_complete = true;
 			ctx->operation_succeeded = true;
@@ -157,6 +169,10 @@ static void process_read_reply(
 			ctx->operation_succeeded = false;
 		}
 	break;
+	case AUX_TRANSACTION_REPLY_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
 	default:
 		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
 		ctx->operation_succeeded = false;
@@ -215,6 +231,10 @@ static void process_read_request(
 			 * so we should not wait here */
 		}
 	break;
+	case AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
 	default:
 		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
 		ctx->operation_succeeded = false;
@@ -282,7 +302,6 @@ static bool read_command(
 				ctx.operation_succeeded);
 	}
 
-	request->payload.length = ctx.reply.length;
 	return ctx.operation_succeeded;
 }
 
@@ -370,6 +389,10 @@ static void process_write_reply(
 			ctx->operation_succeeded = false;
 		}
 	break;
+	case AUX_TRANSACTION_REPLY_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
 	default:
 		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
 		ctx->operation_succeeded = false;
@@ -422,6 +445,10 @@ static void process_write_request(
 			 * so we should not wait here */
 		}
 	break;
+	case AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
 	default:
 		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
 		ctx->operation_succeeded = false;
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h b/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h
index 8e71324ccb10..c33a2898d967 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h
@@ -26,46 +26,7 @@
 #ifndef __DAL_AUX_ENGINE_H__
 #define __DAL_AUX_ENGINE_H__
 
-enum aux_transaction_type {
-	AUX_TRANSACTION_TYPE_DP,
-	AUX_TRANSACTION_TYPE_I2C
-};
-
-struct aux_request_transaction_data {
-	enum aux_transaction_type type;
-	enum i2caux_transaction_action action;
-	/* 20-bit AUX channel transaction address */
-	uint32_t address;
-	/* delay, in 100-microsecond units */
-	uint8_t delay;
-	uint32_t length;
-	uint8_t *data;
-};
-
-enum aux_transaction_reply {
-	AUX_TRANSACTION_REPLY_AUX_ACK = 0x00,
-	AUX_TRANSACTION_REPLY_AUX_NACK = 0x01,
-	AUX_TRANSACTION_REPLY_AUX_DEFER = 0x02,
-
-	AUX_TRANSACTION_REPLY_I2C_ACK = 0x00,
-	AUX_TRANSACTION_REPLY_I2C_NACK = 0x10,
-	AUX_TRANSACTION_REPLY_I2C_DEFER = 0x20,
-
-	AUX_TRANSACTION_REPLY_INVALID = 0xFF
-};
-
-struct aux_reply_transaction_data {
-	enum aux_transaction_reply status;
-	uint32_t length;
-	uint8_t *data;
-};
-
-enum aux_channel_operation_result {
-	AUX_CHANNEL_OPERATION_SUCCEEDED,
-	AUX_CHANNEL_OPERATION_FAILED_REASON_UNKNOWN,
-	AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY,
-	AUX_CHANNEL_OPERATION_FAILED_TIMEOUT
-};
+#include "dc_ddc_types.h"
 
 struct aux_engine;
 
@@ -83,6 +44,12 @@ struct aux_engine_funcs {
 	void (*process_channel_reply)(
 		struct aux_engine *engine,
 		struct aux_reply_transaction_data *reply);
+	int (*read_channel_reply)(
+		struct aux_engine *engine,
+		uint32_t size,
+		uint8_t *buffer,
+		uint8_t *reply_result,
+		uint32_t *sw_status);
 	enum aux_channel_operation_result (*get_channel_status)(
 		struct aux_engine *engine,
 		uint8_t *returned_bytes);
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce100/i2caux_dce100.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce100/i2caux_dce100.c
index e8d3781deaed..8b704ab0471c 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce100/i2caux_dce100.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce100/i2caux_dce100.c
@@ -97,6 +97,7 @@ struct i2caux *dal_i2caux_dce100_create(
 
 	dal_i2caux_dce110_construct(i2caux_dce110,
 				    ctx,
+				    ARRAY_SIZE(dce100_aux_regs),
 				    dce100_aux_regs,
 				    dce100_hw_engine_regs,
 				    &i2c_shift,
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
index 5f47f6c007ac..ae5caa97caca 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
@@ -198,27 +198,27 @@ static void submit_channel_request(
 		((request->type == AUX_TRANSACTION_TYPE_I2C) &&
 		((request->action == I2CAUX_TRANSACTION_ACTION_I2C_WRITE) ||
 		 (request->action == I2CAUX_TRANSACTION_ACTION_I2C_WRITE_MOT)));
+	if (REG(AUXN_IMPCAL)) {
+		/* clear_aux_error */
+		REG_UPDATE_SEQ(AUXN_IMPCAL, AUXN_CALOUT_ERROR_AK,
+				1,
+				0);
 
-	/* clear_aux_error */
-	REG_UPDATE_SEQ(AUXN_IMPCAL, AUXN_CALOUT_ERROR_AK,
-			1,
-			0);
-
-	REG_UPDATE_SEQ(AUXP_IMPCAL, AUXP_CALOUT_ERROR_AK,
-			1,
-			0);
-
-	/* force_default_calibrate */
-	REG_UPDATE_1BY1_2(AUXN_IMPCAL,
-			AUXN_IMPCAL_ENABLE, 1,
-			AUXN_IMPCAL_OVERRIDE_ENABLE, 0);
+		REG_UPDATE_SEQ(AUXP_IMPCAL, AUXP_CALOUT_ERROR_AK,
+				1,
+				0);
 
-	/* bug? why AUXN update EN and OVERRIDE_EN 1 by 1 while AUX P toggles OVERRIDE? */
+		/* force_default_calibrate */
+		REG_UPDATE_1BY1_2(AUXN_IMPCAL,
+				AUXN_IMPCAL_ENABLE, 1,
+				AUXN_IMPCAL_OVERRIDE_ENABLE, 0);
 
-	REG_UPDATE_SEQ(AUXP_IMPCAL, AUXP_IMPCAL_OVERRIDE_ENABLE,
-			1,
-			0);
+		/* bug? why AUXN update EN and OVERRIDE_EN 1 by 1 while AUX P toggles OVERRIDE? */
 
+		REG_UPDATE_SEQ(AUXP_IMPCAL, AUXP_IMPCAL_OVERRIDE_ENABLE,
+				1,
+				0);
+	}
 	/* set the delay and the number of bytes to write */
 
 	/* The length include
@@ -275,55 +275,92 @@ static void submit_channel_request(
 	REG_UPDATE(AUX_SW_CONTROL, AUX_SW_GO, 1);
 }
 
-static void process_channel_reply(
-	struct aux_engine *engine,
-	struct aux_reply_transaction_data *reply)
+static int read_channel_reply(struct aux_engine *engine, uint32_t size,
+			      uint8_t *buffer, uint8_t *reply_result,
+			      uint32_t *sw_status)
 {
 	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
+	uint32_t bytes_replied;
+	uint32_t reply_result_32;
 
-	/* Need to do a read to get the number of bytes to process
-	 * Alternatively, this information can be passed -
-	 * but that causes coupling which isn't good either. */
+	*sw_status = REG_GET(AUX_SW_STATUS, AUX_SW_REPLY_BYTE_COUNT,
+			     &bytes_replied);
 
-	uint32_t bytes_replied;
-	uint32_t value;
+	/* In case HPD is LOW, exit AUX transaction */
+	if ((*sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK))
+		return -1;
 
-	value = REG_GET(AUX_SW_STATUS,
-			AUX_SW_REPLY_BYTE_COUNT, &bytes_replied);
+	/* Need at least the status byte */
+	if (!bytes_replied)
+		return -1;
 
-	if (bytes_replied) {
-		uint32_t reply_result;
+	REG_UPDATE_1BY1_3(AUX_SW_DATA,
+			  AUX_SW_INDEX, 0,
+			  AUX_SW_AUTOINCREMENT_DISABLE, 1,
+			  AUX_SW_DATA_RW, 1);
 
-		REG_UPDATE_1BY1_3(AUX_SW_DATA,
-				AUX_SW_INDEX, 0,
-				AUX_SW_AUTOINCREMENT_DISABLE, 1,
-				AUX_SW_DATA_RW, 1);
+	REG_GET(AUX_SW_DATA, AUX_SW_DATA, &reply_result_32);
+	reply_result_32 = reply_result_32 >> 4;
+	*reply_result = (uint8_t)reply_result_32;
 
-		REG_GET(AUX_SW_DATA,
-				AUX_SW_DATA, &reply_result);
+	if (reply_result_32 == 0) { /* ACK */
+		uint32_t i = 0;
 
-		reply_result = reply_result >> 4;
+		/* First byte was already used to get the command status */
+		--bytes_replied;
 
-		switch (reply_result) {
-		case 0: /* ACK */ {
-			uint32_t i = 0;
+		/* Do not overflow buffer */
+		if (bytes_replied > size)
+			return -1;
 
-			/* first byte was already used
-			 * to get the command status */
-			--bytes_replied;
+		while (i < bytes_replied) {
+			uint32_t aux_sw_data_val;
 
-			while (i < bytes_replied) {
-				uint32_t aux_sw_data_val;
+			REG_GET(AUX_SW_DATA, AUX_SW_DATA, &aux_sw_data_val);
+			buffer[i] = aux_sw_data_val;
+			++i;
+		}
 
-				REG_GET(AUX_SW_DATA,
-						AUX_SW_DATA, &aux_sw_data_val);
+		return i;
+	}
 
-				reply->data[i] = aux_sw_data_val;
-				++i;
-			}
+	return 0;
+}
 
-			reply->status = AUX_TRANSACTION_REPLY_AUX_ACK;
+static void process_channel_reply(
+	struct aux_engine *engine,
+	struct aux_reply_transaction_data *reply)
+{
+	int bytes_replied;
+	uint8_t reply_result;
+	uint32_t sw_status;
+
+	bytes_replied = read_channel_reply(engine, reply->length, reply->data,
+					   &reply_result, &sw_status);
+
+	/* in case HPD is LOW, exit AUX transaction */
+	if ((sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
+		reply->status = AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON;
+		return;
+	}
+
+	if (bytes_replied < 0) {
+		/* Need to handle an error case...
+		 * Hopefully, upper layer function won't call this function if
+		 * the number of bytes in the reply was 0, because there was
+		 * surely an error that was asserted that should have been
+		 * handled for hot plug case, this could happens
+		 */
+		if (!(sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
+			reply->status = AUX_TRANSACTION_REPLY_INVALID;
+			ASSERT_CRITICAL(false);
+			return;
 		}
+	} else {
+
+		switch (reply_result) {
+		case 0: /* ACK */
+			reply->status = AUX_TRANSACTION_REPLY_AUX_ACK;
 		break;
 		case 1: /* NACK */
 			reply->status = AUX_TRANSACTION_REPLY_AUX_NACK;
@@ -340,15 +377,6 @@ static void process_channel_reply(
 		default:
 			reply->status = AUX_TRANSACTION_REPLY_INVALID;
 		}
-	} else {
-		/* Need to handle an error case...
-		 * hopefully, upper layer function won't call this function
-		 * if the number of bytes in the reply was 0
-		 * because there was surely an error that was asserted
-		 * that should have been handled
-		 * for hot plug case, this could happens*/
-		if (!(value & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK))
-			ASSERT_CRITICAL(false);
 	}
 }
 
@@ -371,6 +399,10 @@ static enum aux_channel_operation_result get_channel_status(
 	value = REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 1,
 				10, aux110->timeout_period/10);
 
+	/* in case HPD is LOW, exit AUX transaction */
+	if ((value & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK))
+		return AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON;
+
 	/* Note that the following bits are set in 'status.bits'
 	 * during CTS 4.2.1.2 (FW 3.3.1):
 	 * AUX_SW_RX_MIN_COUNT_VIOL, AUX_SW_RX_INVALID_STOP,
@@ -402,10 +434,10 @@ static enum aux_channel_operation_result get_channel_status(
 			return AUX_CHANNEL_OPERATION_SUCCEEDED;
 		}
 	} else {
-		/*time_elapsed >= aux_engine->timeout_period */
-		if (!(value & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK))
-			ASSERT_CRITICAL(false);
-
+		/*time_elapsed >= aux_engine->timeout_period
+		 *  AUX_SW_STATUS__AUX_SW_HPD_DISCON = at this point
+		 */
+		ASSERT_CRITICAL(false);
 		return AUX_CHANNEL_OPERATION_FAILED_TIMEOUT;
 	}
 }
@@ -415,6 +447,7 @@ static const struct aux_engine_funcs aux_engine_funcs = {
 	.acquire_engine = acquire_engine,
 	.submit_channel_request = submit_channel_request,
 	.process_channel_reply = process_channel_reply,
+	.read_channel_reply = read_channel_reply,
 	.get_channel_status = get_channel_status,
 	.is_engine_available = is_engine_available,
 };
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.c
index b7256f595052..9cbe1a7a6bcb 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.c
@@ -62,12 +62,7 @@ enum dc_i2c_arbitration {
 	DC_I2C_ARBITRATION__DC_I2C_SW_PRIORITY_HIGH
 };
 
-enum {
-	/* No timeout in HW
-	 * (timeout implemented in SW by querying status) */
-	I2C_SETUP_TIME_LIMIT = 255,
-	I2C_HW_BUFFER_SIZE = 538
-};
+
 
 /*
  * @brief
@@ -152,6 +147,11 @@ static bool setup_engine(
 	struct i2c_engine *i2c_engine)
 {
 	struct i2c_hw_engine_dce110 *hw_engine = FROM_I2C_ENGINE(i2c_engine);
+	uint32_t i2c_setup_limit = I2C_SETUP_TIME_LIMIT_DCE;
+	uint32_t  reset_length = 0;
+
+	if (hw_engine->base.base.setup_limit != 0)
+		i2c_setup_limit = hw_engine->base.base.setup_limit;
 
 	/* Program pin select */
 	REG_UPDATE_6(
@@ -164,11 +164,15 @@ static bool setup_engine(
 			DC_I2C_DDC_SELECT, hw_engine->engine_id);
 
 	/* Program time limit */
-	REG_UPDATE_N(
-			SETUP, 2,
-			FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_TIME_LIMIT), I2C_SETUP_TIME_LIMIT,
-			FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_ENABLE), 1);
-
+	if (hw_engine->base.base.send_reset_length == 0) {
+		/*pre-dcn*/
+		REG_UPDATE_N(
+				SETUP, 2,
+				FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_TIME_LIMIT), i2c_setup_limit,
+				FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_ENABLE), 1);
+	} else {
+		reset_length = hw_engine->base.base.send_reset_length;
+	}
 	/* Program HW priority
 	 * set to High - interrupt software I2C at any time
 	 * Enable restart of SW I2C that was interrupted by HW
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.h b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.h
index 5bb04085f670..fea2946906ed 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.h
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.h
@@ -192,6 +192,7 @@ struct i2c_hw_engine_dce110 {
 	/* number of pending transactions (before GO) */
 	uint32_t transaction_count;
 	uint32_t engine_keep_power_up_count;
+	uint32_t i2_setup_time_limit;
 };
 
 struct i2c_hw_engine_dce110_create_arg {
@@ -207,4 +208,11 @@ struct i2c_hw_engine_dce110_create_arg {
 struct i2c_engine *dal_i2c_hw_engine_dce110_create(
 	const struct i2c_hw_engine_dce110_create_arg *arg);
 
+enum {
+	I2C_SETUP_TIME_LIMIT_DCE = 255,
+	I2C_SETUP_TIME_LIMIT_DCN = 3,
+	I2C_HW_BUFFER_SIZE = 538,
+	I2C_SEND_RESET_LENGTH_9 = 9,
+	I2C_SEND_RESET_LENGTH_10 = 10,
+};
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.c
index 2a047f8ca0e9..1d748ac1d6d6 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.c
@@ -43,6 +43,9 @@
 #include "i2c_sw_engine_dce110.h"
 #include "i2c_hw_engine_dce110.h"
 #include "aux_engine_dce110.h"
+#include "../../dc.h"
+#include "dc_types.h"
+
 
 /*
  * Post-requisites: headers required by this unit
@@ -199,6 +202,7 @@ static const struct dce110_i2c_hw_engine_mask i2c_mask = {
 void dal_i2caux_dce110_construct(
 	struct i2caux_dce110 *i2caux_dce110,
 	struct dc_context *ctx,
+	unsigned int num_i2caux_inst,
 	const struct dce110_aux_registers aux_regs[],
 	const struct dce110_i2c_hw_engine_registers i2c_hw_engine_regs[],
 	const struct dce110_i2c_hw_engine_shift *i2c_shift,
@@ -249,9 +253,22 @@ void dal_i2caux_dce110_construct(
 
 		base->i2c_hw_engines[line_id] =
 			dal_i2c_hw_engine_dce110_create(&hw_arg_dce110);
-
+		if (base->i2c_hw_engines[line_id] != NULL) {
+			switch (ctx->dce_version) {
+			case DCN_VERSION_1_0:
+				base->i2c_hw_engines[line_id]->setup_limit =
+					I2C_SETUP_TIME_LIMIT_DCN;
+				base->i2c_hw_engines[line_id]->send_reset_length  = 0;
+			break;
+			default:
+				base->i2c_hw_engines[line_id]->setup_limit =
+					I2C_SETUP_TIME_LIMIT_DCE;
+				base->i2c_hw_engines[line_id]->send_reset_length  = 0;
+				break;
+			}
+		}
 		++i;
-	} while (i < ARRAY_SIZE(hw_ddc_lines));
+	} while (i < num_i2caux_inst);
 
 	/* Create AUX engines for all lines which has assisted HW AUX
 	 * 'i' (loop counter) used as DDC/AUX engine_id */
@@ -272,7 +289,7 @@ void dal_i2caux_dce110_construct(
 			dal_aux_engine_dce110_create(&aux_init_data);
 
 		++i;
-	} while (i < ARRAY_SIZE(hw_aux_lines));
+	} while (i < num_i2caux_inst);
 
 	/*TODO Generic I2C SW and HW*/
 }
@@ -303,6 +320,7 @@ struct i2caux *dal_i2caux_dce110_create(
 
 	dal_i2caux_dce110_construct(i2caux_dce110,
 				    ctx,
+				    ARRAY_SIZE(dce110_aux_regs),
 				    dce110_aux_regs,
 				    i2c_hw_engine_regs,
 				    &i2c_shift,
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.h b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.h
index 1b1f71c60ac9..d3d8cc58666a 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.h
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.h
@@ -45,6 +45,7 @@ struct i2caux *dal_i2caux_dce110_create(
 void dal_i2caux_dce110_construct(
 	struct i2caux_dce110 *i2caux_dce110,
 	struct dc_context *ctx,
+	unsigned int num_i2caux_inst,
 	const struct dce110_aux_registers *aux_regs,
 	const struct dce110_i2c_hw_engine_registers *i2c_hw_engine_regs,
 	const struct dce110_i2c_hw_engine_shift *i2c_shift,
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce112/i2caux_dce112.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce112/i2caux_dce112.c
index dafc1a727f7f..a9db04738724 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce112/i2caux_dce112.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce112/i2caux_dce112.c
@@ -93,6 +93,7 @@ static void construct(
 {
 	dal_i2caux_dce110_construct(i2caux_dce110,
 				    ctx,
+				    ARRAY_SIZE(dce112_aux_regs),
 				    dce112_aux_regs,
 				    dce112_hw_engine_regs,
 				    &i2c_shift,
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce120/i2caux_dce120.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce120/i2caux_dce120.c
index 0e7b18260027..6a4f344c1db4 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce120/i2caux_dce120.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce120/i2caux_dce120.c
@@ -111,6 +111,7 @@ struct i2caux *dal_i2caux_dce120_create(
 
 	dal_i2caux_dce110_construct(i2caux_dce110,
 				    ctx,
+				    ARRAY_SIZE(dce120_aux_regs),
 				    dce120_aux_regs,
 				    dce120_hw_engine_regs,
 				    &i2c_shift,
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dcn10/i2caux_dcn10.c b/drivers/gpu/drm/amd/display/dc/i2caux/dcn10/i2caux_dcn10.c
index e44a8901f38b..a59c1f50c1e8 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dcn10/i2caux_dcn10.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dcn10/i2caux_dcn10.c
@@ -111,6 +111,7 @@ struct i2caux *dal_i2caux_dcn10_create(
 
 	dal_i2caux_dce110_construct(i2caux_dce110,
 				    ctx,
+				    ARRAY_SIZE(dcn10_aux_regs),
 				    dcn10_aux_regs,
 				    dcn10_hw_engine_regs,
 				    &i2c_shift,
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/engine.h b/drivers/gpu/drm/amd/display/dc/i2caux/engine.h
index 33de8a8834dc..b16fb1ff687d 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/engine.h
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/engine.h
@@ -26,6 +26,8 @@
 #ifndef __DAL_ENGINE_H__
 #define __DAL_ENGINE_H__
 
+#include "dc_ddc_types.h"
+
 enum i2caux_transaction_operation {
 	I2CAUX_TRANSACTION_READ,
 	I2CAUX_TRANSACTION_WRITE
@@ -53,7 +55,8 @@ enum i2caux_transaction_status {
 	I2CAUX_TRANSACTION_STATUS_FAILED_INCOMPLETE,
 	I2CAUX_TRANSACTION_STATUS_FAILED_OPERATION,
 	I2CAUX_TRANSACTION_STATUS_FAILED_INVALID_OPERATION,
-	I2CAUX_TRANSACTION_STATUS_FAILED_BUFFER_OVERFLOW
+	I2CAUX_TRANSACTION_STATUS_FAILED_BUFFER_OVERFLOW,
+	I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON
 };
 
 struct i2caux_transaction_request {
@@ -75,19 +78,6 @@ enum i2c_default_speed {
 	I2CAUX_DEFAULT_I2C_SW_SPEED = 50
 };
 
-enum i2caux_transaction_action {
-	I2CAUX_TRANSACTION_ACTION_I2C_WRITE = 0x00,
-	I2CAUX_TRANSACTION_ACTION_I2C_READ = 0x10,
-	I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST = 0x20,
-
-	I2CAUX_TRANSACTION_ACTION_I2C_WRITE_MOT = 0x40,
-	I2CAUX_TRANSACTION_ACTION_I2C_READ_MOT = 0x50,
-	I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST_MOT = 0x60,
-
-	I2CAUX_TRANSACTION_ACTION_DP_WRITE = 0x80,
-	I2CAUX_TRANSACTION_ACTION_DP_READ = 0x90
-};
-
 struct engine;
 
 struct engine_funcs {
@@ -106,6 +96,7 @@ struct engine_funcs {
 
 struct engine {
 	const struct engine_funcs *funcs;
+	uint32_t inst;
 	struct ddc *ddc;
 	struct dc_context *ctx;
 };
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/i2c_engine.h b/drivers/gpu/drm/amd/display/dc/i2caux/i2c_engine.h
index 58fc0f25eceb..ded6ea34b714 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/i2c_engine.h
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/i2c_engine.h
@@ -86,6 +86,8 @@ struct i2c_engine {
 	struct engine base;
 	const struct i2c_engine_funcs *funcs;
 	uint32_t timeout_delay;
+	uint32_t setup_limit;
+	uint32_t send_reset_length;
 };
 
 void dal_i2c_engine_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c b/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c
index 14dc8c94d862..f7ed355fc84f 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c
@@ -59,7 +59,7 @@
 
 #include "dce120/i2caux_dce120.h"
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "dcn10/i2caux_dcn10.h"
 #endif
 
@@ -91,7 +91,7 @@ struct i2caux *dal_i2caux_create(
 		return dal_i2caux_dce100_create(ctx);
 	case DCE_VERSION_12_0:
 		return dal_i2caux_dce120_create(ctx);
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 		return dal_i2caux_dcn10_create(ctx);
 #endif
@@ -254,7 +254,6 @@ bool dal_i2caux_submit_aux_command(
 			break;
 		}
 
-		cmd->payloads->length = request.payload.length;
 		++index_of_payload;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index a94942d4e66b..9f33306f9014 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -33,7 +33,7 @@
 #include "dc_bios_types.h"
 #include "mem_input.h"
 #include "hubp.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "mpc.h"
 #endif
 
@@ -138,7 +138,7 @@ struct resource_pool {
 	struct output_pixel_processor *opps[MAX_PIPES];
 	struct timing_generator *timing_generators[MAX_PIPES];
 	struct stream_encoder *stream_enc[MAX_PIPES * 2];
-
+	struct aux_engine *engines[MAX_PIPES];
 	struct hubbub *hubbub;
 	struct mpc *mpc;
 	struct pp_smu_funcs_rv *pp_smu;
@@ -162,7 +162,7 @@ struct resource_pool {
 	unsigned int audio_count;
 	struct audio_support audio_support;
 
-	struct display_clock *display_clock;
+	struct dccg *dccg;
 	struct irq_service *irqs;
 
 	struct abm *abm;
@@ -221,7 +221,7 @@ struct pipe_ctx {
 	struct pipe_ctx *top_pipe;
 	struct pipe_ctx *bottom_pipe;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 	struct _vcs_dpi_display_dlg_regs_st dlg_regs;
 	struct _vcs_dpi_display_ttu_regs_st ttu_regs;
 	struct _vcs_dpi_display_rq_regs_st rq_regs;
@@ -255,8 +255,7 @@ struct dce_bw_output {
 };
 
 struct dcn_bw_output {
-	struct dc_clocks cur_clk;
-	struct dc_clocks calc_clk;
+	struct dc_clocks clk;
 	struct dcn_watermark_set watermarks;
 };
 
@@ -277,11 +276,11 @@ struct dc_state {
 
 	/* Note: these are big structures, do *not* put on stack! */
 	struct dm_pp_display_configuration pp_display_cfg;
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 	struct dcn_bw_internal_vars dcn_bw_vars;
 #endif
 
-	struct display_clock *dis_clk;
+	struct dccg *dis_clk;
 
 	struct kref refcount;
 };
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
index 090b7a8dd67b..538b83303b86 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
@@ -102,21 +102,13 @@ bool dal_ddc_service_query_ddc_data(
 		uint8_t *read_buf,
 		uint32_t read_size);
 
-ssize_t dal_ddc_service_read_dpcd_data(
-		struct ddc_service *ddc,
-		bool i2c,
-		enum i2c_mot_mode mot,
-		uint32_t address,
-		uint8_t *data,
-		uint32_t len);
-
-enum ddc_result dal_ddc_service_write_dpcd_data(
-		struct ddc_service *ddc,
-		bool i2c,
-		enum i2c_mot_mode mot,
-		uint32_t address,
-		const uint8_t *data,
-		uint32_t len);
+int dc_link_aux_transfer(struct ddc_service *ddc,
+			     unsigned int address,
+			     uint8_t *reply,
+			     void *buffer,
+			     unsigned int size,
+			     enum aux_transaction_type type,
+			     enum i2caux_transaction_action action);
 
 void dal_ddc_service_write_scdc_data(
 		struct ddc_service *ddc_service,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
index 2f783c650084..a37255c757e0 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
@@ -33,9 +33,10 @@ struct dc_link;
 struct dc_stream_state;
 struct dc_link_settings;
 
-bool dp_hbr_verify_link_cap(
+bool dp_verify_link_cap(
 	struct dc_link *link,
-	struct dc_link_settings *known_limit_link_setting);
+	struct dc_link_settings *known_limit_link_setting,
+	int *fail_count);
 
 bool dp_validate_mode_timing(
 	struct dc_link *link,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h b/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h
index 132d18d4b293..ddbb673caa08 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h
@@ -625,7 +625,7 @@ bool dcn_validate_bandwidth(
 
 unsigned int dcn_find_dcfclk_suits_all(
 	const struct dc *dc,
-	struct clocks_value *clocks);
+	struct dc_clocks *clocks);
 
 void dcn_bw_update_from_pplib(struct dc *dc);
 void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/aux_engine.h b/drivers/gpu/drm/amd/display/dc/inc/hw/aux_engine.h
new file mode 100644
index 000000000000..e79cd4e92919
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/aux_engine.h
@@ -0,0 +1,180 @@
+/*
+ * Copyright 2012-15 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DAL_AUX_ENGINE_H__
+#define __DAL_AUX_ENGINE_H__
+
+#include "dc_ddc_types.h"
+#include "include/i2caux_interface.h"
+
+enum i2caux_transaction_operation {
+	I2CAUX_TRANSACTION_READ,
+	I2CAUX_TRANSACTION_WRITE
+};
+
+enum i2caux_transaction_address_space {
+	I2CAUX_TRANSACTION_ADDRESS_SPACE_I2C = 1,
+	I2CAUX_TRANSACTION_ADDRESS_SPACE_DPCD
+};
+
+struct i2caux_transaction_payload {
+	enum i2caux_transaction_address_space address_space;
+	uint32_t address;
+	uint32_t length;
+	uint8_t *data;
+};
+
+enum i2caux_transaction_status {
+	I2CAUX_TRANSACTION_STATUS_UNKNOWN = (-1L),
+	I2CAUX_TRANSACTION_STATUS_SUCCEEDED,
+	I2CAUX_TRANSACTION_STATUS_FAILED_CHANNEL_BUSY,
+	I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT,
+	I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR,
+	I2CAUX_TRANSACTION_STATUS_FAILED_NACK,
+	I2CAUX_TRANSACTION_STATUS_FAILED_INCOMPLETE,
+	I2CAUX_TRANSACTION_STATUS_FAILED_OPERATION,
+	I2CAUX_TRANSACTION_STATUS_FAILED_INVALID_OPERATION,
+	I2CAUX_TRANSACTION_STATUS_FAILED_BUFFER_OVERFLOW,
+	I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON
+};
+
+struct i2caux_transaction_request {
+	enum i2caux_transaction_operation operation;
+	struct i2caux_transaction_payload payload;
+	enum i2caux_transaction_status status;
+};
+
+enum i2caux_engine_type {
+	I2CAUX_ENGINE_TYPE_UNKNOWN = (-1L),
+	I2CAUX_ENGINE_TYPE_AUX,
+	I2CAUX_ENGINE_TYPE_I2C_DDC_HW,
+	I2CAUX_ENGINE_TYPE_I2C_GENERIC_HW,
+	I2CAUX_ENGINE_TYPE_I2C_SW
+};
+
+enum i2c_default_speed {
+	I2CAUX_DEFAULT_I2C_HW_SPEED = 50,
+	I2CAUX_DEFAULT_I2C_SW_SPEED = 50
+};
+
+union aux_config;
+
+struct aux_engine {
+	uint32_t inst;
+	struct ddc *ddc;
+	struct dc_context *ctx;
+	const struct aux_engine_funcs *funcs;
+	/* following values are expressed in milliseconds */
+	uint32_t delay;
+	uint32_t max_defer_write_retry;
+	bool acquire_reset;
+};
+
+struct read_command_context {
+	uint8_t *buffer;
+	uint32_t current_read_length;
+	uint32_t offset;
+	enum i2caux_transaction_status status;
+
+	struct aux_request_transaction_data request;
+	struct aux_reply_transaction_data reply;
+
+	uint8_t returned_byte;
+
+	uint32_t timed_out_retry_aux;
+	uint32_t invalid_reply_retry_aux;
+	uint32_t defer_retry_aux;
+	uint32_t defer_retry_i2c;
+	uint32_t invalid_reply_retry_aux_on_ack;
+
+	bool transaction_complete;
+	bool operation_succeeded;
+};
+
+struct write_command_context {
+	bool mot;
+
+	uint8_t *buffer;
+	uint32_t current_write_length;
+	enum i2caux_transaction_status status;
+
+	struct aux_request_transaction_data request;
+	struct aux_reply_transaction_data reply;
+
+	uint8_t returned_byte;
+
+	uint32_t timed_out_retry_aux;
+	uint32_t invalid_reply_retry_aux;
+	uint32_t defer_retry_aux;
+	uint32_t defer_retry_i2c;
+	uint32_t max_defer_retry;
+	uint32_t ack_m_retry;
+
+	uint8_t reply_data[DEFAULT_AUX_MAX_DATA_SIZE];
+
+	bool transaction_complete;
+	bool operation_succeeded;
+};
+
+
+struct aux_engine_funcs {
+	void (*destroy)(
+		struct aux_engine **ptr);
+	bool (*acquire_engine)(
+		struct aux_engine *engine);
+	void (*configure)(
+		struct aux_engine *engine,
+		union aux_config cfg);
+	void (*submit_channel_request)(
+		struct aux_engine *engine,
+		struct aux_request_transaction_data *request);
+	void (*process_channel_reply)(
+		struct aux_engine *engine,
+		struct aux_reply_transaction_data *reply);
+	int (*read_channel_reply)(
+		struct aux_engine *engine,
+		uint32_t size,
+		uint8_t *buffer,
+		uint8_t *reply_result,
+		uint32_t *sw_status);
+	enum aux_channel_operation_result (*get_channel_status)(
+		struct aux_engine *engine,
+		uint8_t *returned_bytes);
+	bool (*is_engine_available)(struct aux_engine *engine);
+	enum i2caux_engine_type (*get_engine_type)(
+		const struct aux_engine *engine);
+	bool (*acquire)(
+		struct aux_engine *engine,
+		struct ddc *ddc);
+	bool (*submit_request)(
+		struct aux_engine *engine,
+		struct i2caux_transaction_request *request,
+		bool middle_of_transaction);
+	void (*release_engine)(
+		struct aux_engine *engine);
+	void (*destroy_engine)(
+		struct aux_engine **engine);
+};
+#endif
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h b/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h
index f5f69cd81f6f..3c7ccb68ecdb 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h
@@ -27,23 +27,7 @@
 #define __DISPLAY_CLOCK_H__
 
 #include "dm_services_types.h"
-
-
-struct clocks_value {
-	int dispclk_in_khz;
-	int max_pixelclk_in_khz;
-	int max_non_dp_phyclk_in_khz;
-	int max_dp_phyclk_in_khz;
-	bool dispclk_notify_pplib_done;
-	bool pixelclk_notify_pplib_done;
-	bool phyclk_notigy_pplib_done;
-	int dcfclock_in_khz;
-	int dppclk_in_khz;
-	int mclk_in_khz;
-	int phyclk_in_khz;
-	int common_vdd_level;
-};
-
+#include "dc.h"
 
 /* Structure containing all state-dependent clocks
  * (dependent on "enum clocks_state") */
@@ -52,34 +36,23 @@ struct state_dependent_clocks {
 	int pixel_clk_khz;
 };
 
-struct display_clock {
+struct dccg {
 	struct dc_context *ctx;
 	const struct display_clock_funcs *funcs;
 
 	enum dm_pp_clocks_state max_clks_state;
 	enum dm_pp_clocks_state cur_min_clks_state;
-	struct clocks_value cur_clocks_value;
+	struct dc_clocks clks;
 };
 
 struct display_clock_funcs {
-	int (*set_clock)(struct display_clock *disp_clk,
+	void (*update_clocks)(struct dccg *dccg,
+			struct dc_clocks *new_clocks,
+			bool safe_to_lower);
+	int (*set_dispclk)(struct dccg *dccg,
 		int requested_clock_khz);
 
-	enum dm_pp_clocks_state (*get_required_clocks_state)(
-		struct display_clock *disp_clk,
-		struct state_dependent_clocks *req_clocks);
-
-	bool (*set_min_clocks_state)(struct display_clock *disp_clk,
-		enum dm_pp_clocks_state dm_pp_clocks_state);
-
-	int (*get_dp_ref_clk_frequency)(struct display_clock *disp_clk);
-
-	bool (*apply_clock_voltage_request)(
-		struct display_clock *disp_clk,
-		enum dm_pp_clock_type clocks_type,
-		int clocks_in_khz,
-		bool pre_mode_set,
-		bool update_dp_phyclk);
+	int (*get_dp_ref_clk_frequency)(struct dccg *dccg);
 };
 
 #endif /* __DISPLAY_CLOCK_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h
index de60f940030d..4550747fb61c 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h
@@ -48,7 +48,7 @@ struct dmcu_funcs {
 			const char *src,
 			unsigned int bytes);
 	void (*set_psr_enable)(struct dmcu *dmcu, bool enable, bool wait);
-	void (*setup_psr)(struct dmcu *dmcu,
+	bool (*setup_psr)(struct dmcu *dmcu,
 			struct dc_link *link,
 			struct psr_context *psr_context);
 	void (*get_psr_state)(struct dmcu *dmcu, uint32_t *psr_state);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
index 582458f028f8..74ad94b0e4f0 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
@@ -151,6 +151,9 @@ struct dpp_funcs {
 	void (*dpp_set_hdr_multiplier)(
 			struct dpp *dpp_base,
 			uint32_t multiplier);
+	void (*set_optional_cursor_attributes)(
+			struct dpp *dpp_base,
+			struct dpp_cursor_attributes *attr);
 
 	void (*dpp_dppclk_control)(
 			struct dpp *dpp_base,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
index 97df82cddf82..4f3f9e68ccfa 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
@@ -43,10 +43,9 @@ enum cursor_lines_per_chunk {
 };
 
 struct hubp {
-	struct hubp_funcs *funcs;
+	const struct hubp_funcs *funcs;
 	struct dc_context *ctx;
 	struct dc_plane_address request_address;
-	struct dc_plane_address current_address;
 	int inst;
 
 	/* run time states */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h
index 47f1dc5a43b7..da89c2edb07c 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h
@@ -64,7 +64,7 @@ struct stutter_modes {
 };
 
 struct mem_input {
-	struct mem_input_funcs *funcs;
+	const struct mem_input_funcs *funcs;
 	struct dc_context *ctx;
 	struct dc_plane_address request_address;
 	struct dc_plane_address current_address;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
index 69cb0a105300..af700c7dac50 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
@@ -156,6 +156,9 @@ struct timing_generator_funcs {
 		uint32_t *v_blank_end,
 		uint32_t *h_position,
 		uint32_t *v_position);
+	bool (*get_otg_active_size)(struct timing_generator *optc,
+			uint32_t *otg_active_width,
+			uint32_t *otg_active_height);
 	void (*set_early_control)(struct timing_generator *tg,
 							   uint32_t early_cntl);
 	void (*wait_for_state)(struct timing_generator *tg,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
index 63fc6c499789..a14ce4de80b2 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
@@ -44,6 +44,7 @@ struct dce_hwseq_wa {
 	bool blnd_crtc_trigger;
 	bool DEGVIDCN10_253;
 	bool false_optc_underflow;
+	bool DEGVIDCN10_254;
 };
 
 struct hwseq_wa_state {
@@ -101,10 +102,18 @@ struct hw_sequencer_funcs {
 		const struct dc *dc,
 		struct pipe_ctx *pipe_ctx);
 
+	void (*plane_atomic_disconnect)(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx);
+
 	void (*update_dchub)(
 		struct dce_hwseq *hws,
 		struct dchub_init_data *dh_data);
 
+	void (*update_mpcc)(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx);
+
 	void (*update_pending_status)(
 			struct pipe_ctx *pipe_ctx);
 
@@ -154,20 +163,24 @@ struct hw_sequencer_funcs {
 			struct dc_link_settings *link_settings);
 
 	void (*blank_stream)(struct pipe_ctx *pipe_ctx);
+
+	void (*enable_audio_stream)(struct pipe_ctx *pipe_ctx);
+
+	void (*disable_audio_stream)(struct pipe_ctx *pipe_ctx, int option);
+
 	void (*pipe_control_lock)(
 				struct dc *dc,
 				struct pipe_ctx *pipe,
 				bool lock);
 	void (*blank_pixel_data)(
 			struct dc *dc,
-			struct stream_resource *stream_res,
-			struct dc_stream_state *stream,
+			struct pipe_ctx *pipe_ctx,
 			bool blank);
 
 	void (*set_bandwidth)(
 			struct dc *dc,
 			struct dc_state *context,
-			bool decrease_allowed);
+			bool safe_to_lower);
 
 	void (*set_drr)(struct pipe_ctx **pipe_ctx, int num_pipes,
 			int vmin, int vmax);
@@ -210,6 +223,7 @@ struct hw_sequencer_funcs {
 
 	void (*set_cursor_position)(struct pipe_ctx *pipe);
 	void (*set_cursor_attribute)(struct pipe_ctx *pipe);
+	void (*set_cursor_sdr_white_level)(struct pipe_ctx *pipe);
 
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h b/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h
index 3306e7b0b3e3..cf5a84b9e27c 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h
@@ -445,4 +445,50 @@ uint32_t generic_reg_get8(const struct dc_context *ctx, uint32_t addr,
 		uint8_t shift6, uint32_t mask6, uint32_t *field_value6,
 		uint8_t shift7, uint32_t mask7, uint32_t *field_value7,
 		uint8_t shift8, uint32_t mask8, uint32_t *field_value8);
+
+
+/* indirect register access */
+
+#define IX_REG_SET_N(index_reg_name, data_reg_name, index, n, initial_val, ...)	\
+		generic_indirect_reg_update_ex(CTX, \
+				REG(index_reg_name), REG(data_reg_name), IND_REG(index), \
+				initial_val, \
+				n, __VA_ARGS__)
+
+#define IX_REG_SET_2(index_reg_name, data_reg_name, index, init_value, f1, v1, f2, v2)	\
+		IX_REG_SET_N(index_reg_name, data_reg_name, index, 2, init_value, \
+				FN(reg, f1), v1,\
+				FN(reg, f2), v2)
+
+
+#define IX_REG_READ(index_reg_name, data_reg_name, index) \
+		generic_read_indirect_reg(CTX, REG(index_reg_name), REG(data_reg_name), IND_REG(index))
+
+
+
+#define IX_REG_UPDATE_N(index_reg_name, data_reg_name, index, n, ...)	\
+		generic_indirect_reg_update_ex(CTX, \
+				REG(index_reg_name), REG(data_reg_name), IND_REG(index), \
+				IX_REG_READ(index_reg_name, data_reg_name, index), \
+				n, __VA_ARGS__)
+
+#define IX_REG_UPDATE_2(index_reg_name, data_reg_name, index, f1, v1, f2, v2)	\
+		IX_REG_UPDATE_N(index_reg_name, data_reg_name, index, 2,\
+				FN(reg, f1), v1,\
+				FN(reg, f2), v2)
+
+void generic_write_indirect_reg(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index, uint32_t data);
+
+uint32_t generic_read_indirect_reg(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index);
+
+uint32_t generic_indirect_reg_update_ex(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index, uint32_t reg_val, int n,
+		uint8_t shift1, uint32_t mask1, uint32_t field_value1,
+		...);
+
 #endif /* DRIVERS_GPU_DRM_AMD_DC_DEV_DC_INC_REG_HELPER_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h
index 640a647f4611..e92facbd038f 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/resource.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h
@@ -38,6 +38,7 @@ enum dce_version resource_parse_asic_id(
 
 struct resource_caps {
 	int num_timing_generator;
+	int num_opp;
 	int num_video_plane;
 	int num_audio;
 	int num_stream_encoder;
diff --git a/drivers/gpu/drm/amd/display/dc/irq/Makefile b/drivers/gpu/drm/amd/display/dc/irq/Makefile
index 498515aad4a5..a76ee600ecee 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/irq/Makefile
@@ -60,7 +60,7 @@ AMD_DISPLAY_FILES += $(AMD_DAL_IRQ_DCE12)
 ###############################################################################
 # DCN 1x
 ###############################################################################
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_X86
 IRQ_DCN1 = irq_service_dcn10.o
 
 AMD_DAL_IRQ_DCN1 = $(addprefix $(AMDDALPATH)/dc/irq/dcn10/,$(IRQ_DCN1))
diff --git a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
index dcdfa0f01551..ae3fd0a235ba 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
@@ -36,7 +36,7 @@
 #include "dce120/irq_service_dce120.h"
 
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "dcn10/irq_service_dcn10.h"
 #endif
 
@@ -78,7 +78,7 @@ const struct irq_source_info *find_irq_source_info(
 	struct irq_service *irq_service,
 	enum dc_irq_source source)
 {
-	if (source > DAL_IRQ_SOURCES_NUMBER || source < DC_IRQ_SOURCE_INVALID)
+	if (source >= DAL_IRQ_SOURCES_NUMBER || source < DC_IRQ_SOURCE_INVALID)
 		return NULL;
 
 	return &irq_service->info[source];
diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h
index a407892905af..c9fce9066ad8 100644
--- a/drivers/gpu/drm/amd/display/dc/os_types.h
+++ b/drivers/gpu/drm/amd/display/dc/os_types.h
@@ -48,7 +48,7 @@
 
 #define dm_error(fmt, ...) DRM_ERROR(fmt, ##__VA_ARGS__)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include <asm/fpu/api.h>
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/include/ddc_service_types.h b/drivers/gpu/drm/amd/display/include/ddc_service_types.h
index 019e7a095ea1..d968956a10cd 100644
--- a/drivers/gpu/drm/amd/display/include/ddc_service_types.h
+++ b/drivers/gpu/drm/amd/display/include/ddc_service_types.h
@@ -40,7 +40,8 @@ enum ddc_result {
 	DDC_RESULT_FAILED_INCOMPLETE,
 	DDC_RESULT_FAILED_OPERATION,
 	DDC_RESULT_FAILED_INVALID_OPERATION,
-	DDC_RESULT_FAILED_BUFFER_OVERFLOW
+	DDC_RESULT_FAILED_BUFFER_OVERFLOW,
+	DDC_RESULT_FAILED_HPD_DISCON
 };
 
 enum ddc_service_type {
diff --git a/drivers/gpu/drm/amd/display/include/dpcd_defs.h b/drivers/gpu/drm/amd/display/include/dpcd_defs.h
index d8e52e3b8e3c..1c66166d0a94 100644
--- a/drivers/gpu/drm/amd/display/include/dpcd_defs.h
+++ b/drivers/gpu/drm/amd/display/include/dpcd_defs.h
@@ -27,6 +27,9 @@
 #define __DAL_DPCD_DEFS_H__
 
 #include <drm/drm_dp_helper.h>
+#ifndef DP_SINK_HW_REVISION_START // can remove this once the define gets into linux drm_dp_helper.h
+#define DP_SINK_HW_REVISION_START 0x409
+#endif
 
 enum dpcd_revision {
 	DPCD_REV_10 = 0x10,
diff --git a/drivers/gpu/drm/amd/display/include/fixed31_32.h b/drivers/gpu/drm/amd/display/include/fixed31_32.h
index a981b3e99ab3..52a73332befb 100644
--- a/drivers/gpu/drm/amd/display/include/fixed31_32.h
+++ b/drivers/gpu/drm/amd/display/include/fixed31_32.h
@@ -26,6 +26,13 @@
 #ifndef __DAL_FIXED31_32_H__
 #define __DAL_FIXED31_32_H__
 
+#ifndef LLONG_MAX
+#define LLONG_MAX 9223372036854775807ll
+#endif
+#ifndef LLONG_MIN
+#define LLONG_MIN (-LLONG_MAX - 1ll)
+#endif
+
 #define FIXED31_32_BITS_PER_FRACTIONAL_PART 32
 #ifndef LLONG_MIN
 #define LLONG_MIN (1LL<<63)
diff --git a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h
index 36bbad594267..f312834fef50 100644
--- a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h
+++ b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h
@@ -395,6 +395,8 @@ struct integrated_info {
 	struct i2c_reg_info dp3_ext_hdmi_reg_settings[9];
 	unsigned char dp3_ext_hdmi_6g_reg_num;
 	struct i2c_reg_info dp3_ext_hdmi_6g_reg_settings[3];
+	/* V11 */
+	uint32_t dp_ss_control;
 };
 
 /**
diff --git a/drivers/gpu/drm/amd/display/include/grph_object_defs.h b/drivers/gpu/drm/amd/display/include/grph_object_defs.h
index 2941b882b0b6..58bb42ed85ca 100644
--- a/drivers/gpu/drm/amd/display/include/grph_object_defs.h
+++ b/drivers/gpu/drm/amd/display/include/grph_object_defs.h
@@ -37,6 +37,10 @@
  * ********************************************************************
  */
 
+#define MAX_CONNECTOR_NUMBER_PER_SLOT	(16)
+#define MAX_BOARD_SLOTS					(4)
+#define INVALID_CONNECTOR_INDEX			((unsigned int)(-1))
+
 /* HPD unit id - HW direct translation */
 enum hpd_source_id {
 	HPD_SOURCEID1 = 0,
@@ -136,5 +140,47 @@ enum sync_source {
 	SYNC_SOURCE_DUAL_GPU_PIN
 };
 
+/* connector sizes in millimeters - from BiosParserTypes.hpp */
+#define CONNECTOR_SIZE_DVI			40
+#define CONNECTOR_SIZE_VGA			32
+#define CONNECTOR_SIZE_HDMI			16
+#define CONNECTOR_SIZE_DP			16
+#define CONNECTOR_SIZE_MINI_DP			9
+#define CONNECTOR_SIZE_UNKNOWN			30
+
+enum connector_layout_type {
+	CONNECTOR_LAYOUT_TYPE_UNKNOWN,
+	CONNECTOR_LAYOUT_TYPE_DVI_D,
+	CONNECTOR_LAYOUT_TYPE_DVI_I,
+	CONNECTOR_LAYOUT_TYPE_VGA,
+	CONNECTOR_LAYOUT_TYPE_HDMI,
+	CONNECTOR_LAYOUT_TYPE_DP,
+	CONNECTOR_LAYOUT_TYPE_MINI_DP,
+};
+struct connector_layout_info {
+	struct graphics_object_id connector_id;
+	enum connector_layout_type connector_type;
+	unsigned int length;
+	unsigned int position;  /* offset in mm from right side of the board */
+};
+
+/* length and width in mm */
+struct slot_layout_info {
+	unsigned int length;
+	unsigned int width;
+	unsigned int num_of_connectors;
+	struct connector_layout_info connectors[MAX_CONNECTOR_NUMBER_PER_SLOT];
+};
+
+struct board_layout_info {
+	unsigned int num_of_slots;
 
+	/* indicates valid information in bracket layout structure. */
+	unsigned int is_number_of_slots_valid : 1;
+	unsigned int is_slots_size_valid : 1;
+	unsigned int is_connector_offsets_valid : 1;
+	unsigned int is_connector_lengths_valid : 1;
+
+	struct slot_layout_info slots[MAX_BOARD_SLOTS];
+};
 #endif
diff --git a/drivers/gpu/drm/amd/display/include/grph_object_id.h b/drivers/gpu/drm/amd/display/include/grph_object_id.h
index c4197432eb7c..33b3d755fe65 100644
--- a/drivers/gpu/drm/amd/display/include/grph_object_id.h
+++ b/drivers/gpu/drm/amd/display/include/grph_object_id.h
@@ -197,6 +197,11 @@ enum transmitter_color_depth {
 	TRANSMITTER_COLOR_DEPTH_48       /* 16 bits */
 };
 
+enum dp_alt_mode {
+	DP_Alt_mode__Unknown = 0,
+	DP_Alt_mode__Connect,
+	DP_Alt_mode__NoConnect,
+};
 /*
  *****************************************************************************
  * graphics_object_id struct
@@ -287,4 +292,15 @@ static inline enum engine_id dal_graphics_object_id_get_engine_id(
 		return (enum engine_id) id.id;
 	return ENGINE_ID_UNKNOWN;
 }
+
+static inline bool dal_graphics_object_id_equal(
+	struct graphics_object_id id_1,
+	struct graphics_object_id id_2)
+{
+	if ((id_1.id == id_2.id) && (id_1.enum_id == id_2.enum_id) &&
+		(id_1.type == id_2.type)) {
+		return true;
+	}
+	return false;
+}
 #endif
diff --git a/drivers/gpu/drm/amd/display/include/logger_interface.h b/drivers/gpu/drm/amd/display/include/logger_interface.h
index dc98d6d4b2bd..e3c79616682d 100644
--- a/drivers/gpu/drm/amd/display/include/logger_interface.h
+++ b/drivers/gpu/drm/amd/display/include/logger_interface.h
@@ -40,47 +40,7 @@ struct dc_state;
  *
  */
 
-struct dal_logger *dal_logger_create(struct dc_context *ctx, uint32_t log_mask);
-
-uint32_t dal_logger_destroy(struct dal_logger **logger);
-
-void dm_logger_flush_buffer(struct dal_logger *logger, bool should_warn);
-
-void dm_logger_write(
-		struct dal_logger *logger,
-		enum dc_log_type log_type,
-		const char *msg,
-		...);
-
-void dm_logger_append(
-		struct log_entry *entry,
-		const char *msg,
-		...);
-
-void dm_logger_append_va(
-		struct log_entry *entry,
-		const char *msg,
-		va_list args);
-
-void dm_logger_open(
-		struct dal_logger *logger,
-		struct log_entry *entry,
-		enum dc_log_type log_type);
-
-void dm_logger_close(struct log_entry *entry);
-
-void dc_conn_log(struct dc_context *ctx,
-		const struct dc_link *link,
-		uint8_t *hex_data,
-		int hex_data_count,
-		enum dc_log_type event,
-		const char *msg,
-		...);
-
-void logger_write(struct dal_logger *logger,
-		enum dc_log_type log_type,
-		const char *msg,
-		void *paralist);
+void dc_conn_log_hex_linux(const uint8_t *hex_data, int hex_data_count);
 
 void pre_surface_trace(
 		struct dc *dc,
@@ -106,28 +66,31 @@ void context_clock_trace(
  * marked by this macro.
  * Note that the message will be printed exactly once for every function
  * it is used in order to avoid repeating of the same message. */
+
 #define DAL_LOGGER_NOT_IMPL(fmt, ...) \
-{ \
-	static bool print_not_impl = true; \
-\
-	if (print_not_impl == true) { \
-		print_not_impl = false; \
-		dm_logger_write(ctx->logger, LOG_WARNING, \
-		"DAL_NOT_IMPL: " fmt, ##__VA_ARGS__); \
-	} \
-}
+	do { \
+		static bool print_not_impl = true; \
+		if (print_not_impl == true) { \
+			print_not_impl = false; \
+			DRM_WARN("DAL_NOT_IMPL: " fmt, ##__VA_ARGS__); \
+		} \
+	} while (0)
 
 /******************************************************************************
  * Convenience macros to save on typing.
  *****************************************************************************/
 
 #define DC_ERROR(...) \
-	dm_logger_write(dc_ctx->logger, LOG_ERROR, \
-		__VA_ARGS__)
+		do { \
+			(void)(dc_ctx); \
+			DC_LOG_ERROR(__VA_ARGS__); \
+		} while (0)
 
 #define DC_SYNC_INFO(...) \
-	dm_logger_write(dc_ctx->logger, LOG_SYNC, \
-		__VA_ARGS__)
+		do { \
+			(void)(dc_ctx); \
+			DC_LOG_SYNC(__VA_ARGS__); \
+		} while (0)
 
 /* Connectivity log format:
  * [time stamp]   [drm] [Major_minor] [connector name] message.....
@@ -137,20 +100,30 @@ void context_clock_trace(
  */
 
 #define CONN_DATA_DETECT(link, hex_data, hex_len, ...) \
-		dc_conn_log(link->ctx, link, hex_data, hex_len, \
-				LOG_EVENT_DETECTION, ##__VA_ARGS__)
+		do { \
+			(void)(link); \
+			dc_conn_log_hex_linux(hex_data, hex_len); \
+			DC_LOG_EVENT_DETECTION(__VA_ARGS__); \
+		} while (0)
 
 #define CONN_DATA_LINK_LOSS(link, hex_data, hex_len, ...) \
-		dc_conn_log(link->ctx, link, hex_data, hex_len, \
-				LOG_EVENT_LINK_LOSS, ##__VA_ARGS__)
+		do { \
+			(void)(link); \
+			dc_conn_log_hex_linux(hex_data, hex_len); \
+			DC_LOG_EVENT_LINK_LOSS(__VA_ARGS__); \
+		} while (0)
 
 #define CONN_MSG_LT(link, ...) \
-		dc_conn_log(link->ctx, link, NULL, 0, \
-				LOG_EVENT_LINK_TRAINING, ##__VA_ARGS__)
+		do { \
+			(void)(link); \
+			DC_LOG_EVENT_LINK_TRAINING(__VA_ARGS__); \
+		} while (0)
 
 #define CONN_MSG_MODE(link, ...) \
-		dc_conn_log(link->ctx, link, NULL, 0, \
-				LOG_EVENT_MODE_SET, ##__VA_ARGS__)
+		do { \
+			(void)(link); \
+			DC_LOG_EVENT_MODE_SET(__VA_ARGS__); \
+		} while (0)
 
 /*
  * Display Test Next logging
@@ -165,38 +138,21 @@ void context_clock_trace(
 	dm_dtn_log_end(dc_ctx)
 
 #define PERFORMANCE_TRACE_START() \
-	unsigned long long perf_trc_start_stmp = dm_get_timestamp(dc->ctx); \
-	unsigned long long perf_trc_start_log_msk = dc->ctx->logger->mask; \
-	unsigned int perf_trc_start_log_flags = dc->ctx->logger->flags.value; \
-	if (dc->debug.performance_trace) {\
-		dm_logger_flush_buffer(dc->ctx->logger, false);\
-		dc->ctx->logger->mask = 1<<LOG_PERF_TRACE;\
-		dc->ctx->logger->flags.bits.ENABLE_CONSOLE = 0;\
-		dc->ctx->logger->flags.bits.ENABLE_BUFFER = 1;\
-	}
-
-#define PERFORMANCE_TRACE_END() do {\
-	unsigned long long perf_trc_end_stmp = dm_get_timestamp(dc->ctx);\
-	if (dc->debug.performance_trace) {\
-		dm_logger_write(dc->ctx->logger, \
-				LOG_PERF_TRACE, \
-				"%s duration: %d ticks\n", __func__,\
+	unsigned long long perf_trc_start_stmp = dm_get_timestamp(dc->ctx)
+
+#define PERFORMANCE_TRACE_END() \
+	do { \
+		unsigned long long perf_trc_end_stmp = dm_get_timestamp(dc->ctx); \
+		if (dc->debug.performance_trace) { \
+			DC_LOG_PERF_TRACE("%s duration: %lld ticks\n", __func__, \
 				perf_trc_end_stmp - perf_trc_start_stmp); \
-		if (perf_trc_start_log_msk != 1<<LOG_PERF_TRACE) {\
-			dc->ctx->logger->mask = perf_trc_start_log_msk;\
-			dc->ctx->logger->flags.value = perf_trc_start_log_flags;\
-			dm_logger_flush_buffer(dc->ctx->logger, false);\
 		} \
-	} \
-} while (0)
+	} while (0)
 
-#define DISPLAY_STATS_BEGIN(entry) \
-	dm_logger_open(dc->ctx->logger, &entry, LOG_DISPLAYSTATS)
+#define DISPLAY_STATS_BEGIN(entry) (void)(entry)
 
-#define DISPLAY_STATS(msg, ...) \
-	dm_logger_append(&log_entry, msg, ##__VA_ARGS__)
+#define DISPLAY_STATS(msg, ...) DC_LOG_PERF_TRACE(msg, __VA_ARGS__)
 
-#define DISPLAY_STATS_END(entry) \
-	dm_logger_close(&entry)
+#define DISPLAY_STATS_END(entry) (void)(entry)
 
 #endif /* __DAL_LOGGER_INTERFACE_H__ */
diff --git a/drivers/gpu/drm/amd/display/include/logger_types.h b/drivers/gpu/drm/amd/display/include/logger_types.h
index 0a540b9897a6..ad3695e67b76 100644
--- a/drivers/gpu/drm/amd/display/include/logger_types.h
+++ b/drivers/gpu/drm/amd/display/include/logger_types.h
@@ -138,63 +138,4 @@ enum dc_log_type {
 		(1 << LOG_HW_AUDIO)| \
 		(1 << LOG_BANDWIDTH_CALCS)*/
 
-union logger_flags {
-	struct {
-		uint32_t ENABLE_CONSOLE:1; /* Print to console */
-		uint32_t ENABLE_BUFFER:1; /* Print to buffer */
-		uint32_t RESERVED:30;
-	} bits;
-	uint32_t value;
-};
-
-struct log_entry {
-	struct dal_logger *logger;
-	enum dc_log_type type;
-
-	char *buf;
-	uint32_t buf_offset;
-	uint32_t max_buf_bytes;
-};
-
-/**
-* Structure for enumerating log types
-*/
-struct dc_log_type_info {
-	enum dc_log_type type;
-	char name[MAX_NAME_LEN];
-};
-
-/* Structure for keeping track of offsets, buffer, etc */
-
-#define DAL_LOGGER_BUFFER_MAX_SIZE 2048
-
-/*Connectivity log needs to output EDID, which needs at lease 256x3 bytes,
- * change log line size to 896 to meet the request.
- */
-#define LOG_MAX_LINE_SIZE 896
-
-struct dal_logger {
-
-	/* How far into the circular buffer has been read by dsat
-	 * Read offset should never cross write offset. Write \0's to
-	 * read data just to be sure?
-	 */
-	uint32_t buffer_read_offset;
-
-	/* How far into the circular buffer we have written
-	 * Write offset should never cross read offset
-	 */
-	uint32_t buffer_write_offset;
-
-	uint32_t open_count;
-
-	char *log_buffer;	/* Pointer to malloc'ed buffer */
-	uint32_t log_buffer_size; /* Size of circular buffer */
-
-	uint32_t mask; /*array of masks for major elements*/
-
-	union logger_flags flags;
-	struct dc_context *ctx;
-};
-
 #endif /* __DAL_LOGGER_TYPES_H__ */
diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
index eee0dfad6962..bf29733958c3 100644
--- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
+++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
@@ -131,6 +131,63 @@ static void compute_de_pq(struct fixed31_32 in_x, struct fixed31_32 *out_y)
 			dc_fixpt_div(dc_fixpt_one, m1));
 
 }
+
+/*de gamma, none linear to linear*/
+static void compute_hlg_oetf(struct fixed31_32 in_x, bool is_light0_12, struct fixed31_32 *out_y)
+{
+	struct fixed31_32 a;
+	struct fixed31_32 b;
+	struct fixed31_32 c;
+	struct fixed31_32 threshold;
+	struct fixed31_32 reference_white_level;
+
+	a = dc_fixpt_from_fraction(17883277, 100000000);
+	if (is_light0_12) {
+		/*light 0-12*/
+		b = dc_fixpt_from_fraction(28466892, 100000000);
+		c = dc_fixpt_from_fraction(55991073, 100000000);
+		threshold = dc_fixpt_one;
+		reference_white_level = dc_fixpt_half;
+	} else {
+		/*light 0-1*/
+		b = dc_fixpt_from_fraction(2372241, 100000000);
+		c = dc_fixpt_add(dc_fixpt_one, dc_fixpt_from_fraction(429347, 100000000));
+		threshold = dc_fixpt_from_fraction(1, 12);
+		reference_white_level = dc_fixpt_pow(dc_fixpt_from_fraction(3, 1), dc_fixpt_half);
+	}
+	if (dc_fixpt_lt(threshold, in_x))
+		*out_y = dc_fixpt_add(c, dc_fixpt_mul(a, dc_fixpt_log(dc_fixpt_sub(in_x, b))));
+	else
+		*out_y = dc_fixpt_mul(dc_fixpt_pow(in_x, dc_fixpt_half), reference_white_level);
+}
+
+/*re gamma, linear to none linear*/
+static void compute_hlg_eotf(struct fixed31_32 in_x, bool is_light0_12, struct fixed31_32 *out_y)
+{
+	struct fixed31_32 a;
+	struct fixed31_32 b;
+	struct fixed31_32 c;
+	struct fixed31_32 reference_white_level;
+
+	a = dc_fixpt_from_fraction(17883277, 100000000);
+	if (is_light0_12) {
+		/*light 0-12*/
+		b = dc_fixpt_from_fraction(28466892, 100000000);
+		c = dc_fixpt_from_fraction(55991073, 100000000);
+		reference_white_level = dc_fixpt_from_fraction(4, 1);
+	} else {
+		/*light 0-1*/
+		b = dc_fixpt_from_fraction(2372241, 100000000);
+		c = dc_fixpt_add(dc_fixpt_one, dc_fixpt_from_fraction(429347, 100000000));
+		reference_white_level = dc_fixpt_from_fraction(1, 3);
+	}
+	if (dc_fixpt_lt(dc_fixpt_half, in_x))
+		*out_y = dc_fixpt_add(dc_fixpt_exp(dc_fixpt_div(dc_fixpt_sub(in_x, c), a)), b);
+	else
+		*out_y = dc_fixpt_mul(dc_fixpt_pow(in_x, dc_fixpt_from_fraction(2, 1)), reference_white_level);
+}
+
+
 /* one-time pre-compute PQ values - only for sdr_white_level 80 */
 void precompute_pq(void)
 {
@@ -691,6 +748,48 @@ static void build_degamma(struct pwl_float_data_ex *curve,
 	}
 }
 
+static void build_hlg_degamma(struct pwl_float_data_ex *degamma,
+		uint32_t hw_points_num,
+		const struct hw_x_point *coordinate_x, bool is_light0_12)
+{
+	uint32_t i;
+
+	struct pwl_float_data_ex *rgb = degamma;
+	const struct hw_x_point *coord_x = coordinate_x;
+
+	i = 0;
+
+	while (i != hw_points_num + 1) {
+		compute_hlg_oetf(coord_x->x, is_light0_12, &rgb->r);
+		rgb->g = rgb->r;
+		rgb->b = rgb->r;
+		++coord_x;
+		++rgb;
+		++i;
+	}
+}
+
+static void build_hlg_regamma(struct pwl_float_data_ex *regamma,
+		uint32_t hw_points_num,
+		const struct hw_x_point *coordinate_x, bool is_light0_12)
+{
+	uint32_t i;
+
+	struct pwl_float_data_ex *rgb = regamma;
+	const struct hw_x_point *coord_x = coordinate_x;
+
+	i = 0;
+
+	while (i != hw_points_num + 1) {
+		compute_hlg_eotf(coord_x->x, is_light0_12, &rgb->r);
+		rgb->g = rgb->r;
+		rgb->b = rgb->r;
+		++coord_x;
+		++rgb;
+		++i;
+	}
+}
+
 static void scale_gamma(struct pwl_float_data *pwl_rgb,
 		const struct dc_gamma *ramp,
 		struct dividers dividers)
@@ -898,7 +997,9 @@ static void scale_user_regamma_ramp(struct pwl_float_data *pwl_rgb,
  * norm_y = 4095*regamma_y, and index is just truncating to nearest integer
  * lut1 = lut1D[index], lut2 = lut1D[index+1]
  *
- *adjustedY is then linearly interpolating regamma Y between lut1 and lut2
+ * adjustedY is then linearly interpolating regamma Y between lut1 and lut2
+ *
+ * Custom degamma on Linux uses the same interpolation math, so is handled here
  */
 static void apply_lut_1d(
 		const struct dc_gamma *ramp,
@@ -919,7 +1020,7 @@ static void apply_lut_1d(
 	struct fixed31_32 delta_lut;
 	struct fixed31_32 delta_index;
 
-	if (ramp->type != GAMMA_CS_TFM_1D)
+	if (ramp->type != GAMMA_CS_TFM_1D && ramp->type != GAMMA_CUSTOM)
 		return; // this is not expected
 
 	for (i = 0; i < num_hw_points; i++) {
@@ -1537,7 +1638,9 @@ bool mod_color_calculate_degamma_params(struct dc_transfer_func *input_tf,
 	map_regamma_hw_to_x_user(ramp, coeff, rgb_user,
 			coordinates_x, axix_x, curve,
 			MAX_HW_POINTS, tf_pts,
-			mapUserRamp);
+			mapUserRamp && ramp->type != GAMMA_CUSTOM);
+	if (ramp->type == GAMMA_CUSTOM)
+		apply_lut_1d(ramp, MAX_HW_POINTS, tf_pts);
 
 	ret = true;
 
@@ -1622,6 +1725,25 @@ bool  mod_color_calculate_curve(enum dc_transfer_func_predefined trans,
 		ret = true;
 
 		kvfree(rgb_regamma);
+	} else if (trans == TRANSFER_FUNCTION_HLG ||
+		trans == TRANSFER_FUNCTION_HLG12) {
+		rgb_regamma = kvcalloc(MAX_HW_POINTS + _EXTRA_POINTS,
+				       sizeof(*rgb_regamma),
+				       GFP_KERNEL);
+		if (!rgb_regamma)
+			goto rgb_regamma_alloc_fail;
+
+		build_hlg_regamma(rgb_regamma,
+				MAX_HW_POINTS,
+				coordinates_x,
+				trans == TRANSFER_FUNCTION_HLG12 ? true:false);
+		for (i = 0; i <= MAX_HW_POINTS ; i++) {
+			points->red[i]    = rgb_regamma[i].r;
+			points->green[i]  = rgb_regamma[i].g;
+			points->blue[i]   = rgb_regamma[i].b;
+		}
+		ret = true;
+		kvfree(rgb_regamma);
 	}
 rgb_regamma_alloc_fail:
 	return ret;
@@ -1682,6 +1804,25 @@ bool  mod_color_calculate_degamma_curve(enum dc_transfer_func_predefined trans,
 		ret = true;
 
 		kvfree(rgb_degamma);
+	} else if (trans == TRANSFER_FUNCTION_HLG ||
+		trans == TRANSFER_FUNCTION_HLG12) {
+		rgb_degamma = kvcalloc(MAX_HW_POINTS + _EXTRA_POINTS,
+				       sizeof(*rgb_degamma),
+				       GFP_KERNEL);
+		if (!rgb_degamma)
+			goto rgb_degamma_alloc_fail;
+
+		build_hlg_degamma(rgb_degamma,
+				MAX_HW_POINTS,
+				coordinates_x,
+				trans == TRANSFER_FUNCTION_HLG12 ? true:false);
+		for (i = 0; i <= MAX_HW_POINTS ; i++) {
+			points->red[i]    = rgb_degamma[i].r;
+			points->green[i]  = rgb_degamma[i].g;
+			points->blue[i]   = rgb_degamma[i].b;
+		}
+		ret = true;
+		kvfree(rgb_degamma);
 	}
 	points->end_exponent = 0;
 	points->x_point_at_y1_red = 1;
diff --git a/drivers/gpu/drm/amd/display/modules/color/luts_1d.h b/drivers/gpu/drm/amd/display/modules/color/luts_1d.h
new file mode 100644
index 000000000000..66b1fad572ac
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/modules/color/luts_1d.h
@@ -0,0 +1,51 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+#ifndef LUTS_1D_H
+#define LUTS_1D_H
+
+#include "hw_shared.h"
+
+struct point_config {
+	uint32_t custom_float_x;
+	uint32_t custom_float_y;
+	uint32_t custom_float_slope;
+};
+
+struct lut_point {
+	uint32_t red;
+	uint32_t green;
+	uint32_t blue;
+	uint32_t delta_red;
+	uint32_t delta_green;
+	uint32_t delta_blue;
+};
+
+struct pwl_1dlut_parameter {
+	struct gamma_curve	arr_curve_points[34];
+	struct point_config	arr_points[2];
+	struct lut_point rgb_resulted[256];
+	uint32_t hw_points_num;
+};
+#endif // LUTS_1D_H
diff --git a/drivers/gpu/drm/amd/display/modules/stats/stats.c b/drivers/gpu/drm/amd/display/modules/stats/stats.c
index 710852ad03f3..3d4c1b1ab8c4 100644
--- a/drivers/gpu/drm/amd/display/modules/stats/stats.c
+++ b/drivers/gpu/drm/amd/display/modules/stats/stats.c
@@ -29,7 +29,7 @@
 #include "core_types.h"
 
 #define DAL_STATS_ENABLE_REGKEY			"DalStatsEnable"
-#define DAL_STATS_ENABLE_REGKEY_DEFAULT		0x00000001
+#define DAL_STATS_ENABLE_REGKEY_DEFAULT		0x00000000
 #define DAL_STATS_ENABLE_REGKEY_ENABLED		0x00000001
 
 #define DAL_STATS_ENTRIES_REGKEY		"DalStatsEntries"
@@ -238,7 +238,7 @@ void mod_stats_dump(struct mod_stats *mod_stats)
 	for (int i = 0; i < core_stats->entry_id; i++) {
 		if (event_index < core_stats->event_index &&
 				i == events[event_index].entry_id) {
-			DISPLAY_STATS("%s\n", events[event_index].event_string);
+			DISPLAY_STATS("==Event==%s\n", events[event_index].event_string);
 			event_index++;
 		} else if (time_index < core_stats->index &&
 				i == time[time_index].entry_id) {
diff --git a/drivers/gpu/drm/amd/include/amd_pcie.h b/drivers/gpu/drm/amd/include/amd_pcie.h
index 5eb895fd98bf..9cb9ceb4d74d 100644
--- a/drivers/gpu/drm/amd/include/amd_pcie.h
+++ b/drivers/gpu/drm/amd/include/amd_pcie.h
@@ -27,6 +27,7 @@
 #define CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1        0x00010000
 #define CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2        0x00020000
 #define CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3        0x00040000
+#define CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4        0x00080000
 #define CAIL_PCIE_LINK_SPEED_SUPPORT_MASK        0xFFFF0000
 #define CAIL_PCIE_LINK_SPEED_SUPPORT_SHIFT       16
 
@@ -34,6 +35,7 @@
 #define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1   0x00000001
 #define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2   0x00000002
 #define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3   0x00000004
+#define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN4   0x00000008
 #define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_MASK   0x0000FFFF
 #define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_SHIFT  0
 
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index b178176b72ac..265621d8945c 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -128,47 +128,57 @@ enum PP_FEATURE_MASK {
 	PP_OVERDRIVE_MASK = 0x4000,
 	PP_GFXOFF_MASK = 0x8000,
 	PP_ACG_MASK = 0x10000,
+	PP_STUTTER_MODE = 0x20000,
 };
 
+/**
+ * struct amd_ip_funcs - general hooks for managing amdgpu IP Blocks
+ */
 struct amd_ip_funcs {
-	/* Name of IP block */
+	/** @name: Name of IP block */
 	char *name;
-	/* sets up early driver state (pre sw_init), does not configure hw - Optional */
+	/**
+	 * @early_init:
+	 *
+	 * sets up early driver state (pre sw_init),
+	 * does not configure hw - Optional
+	 */
 	int (*early_init)(void *handle);
-	/* sets up late driver/hw state (post hw_init) - Optional */
+	/** @late_init: sets up late driver/hw state (post hw_init) - Optional */
 	int (*late_init)(void *handle);
-	/* sets up driver state, does not configure hw */
+	/** @sw_init: sets up driver state, does not configure hw */
 	int (*sw_init)(void *handle);
-	/* tears down driver state, does not configure hw */
+	/** @sw_fini: tears down driver state, does not configure hw */
 	int (*sw_fini)(void *handle);
-	/* sets up the hw state */
+	/** @hw_init: sets up the hw state */
 	int (*hw_init)(void *handle);
-	/* tears down the hw state */
+	/** @hw_fini: tears down the hw state */
 	int (*hw_fini)(void *handle);
+	/** @late_fini: final cleanup */
 	void (*late_fini)(void *handle);
-	/* handles IP specific hw/sw changes for suspend */
+	/** @suspend: handles IP specific hw/sw changes for suspend */
 	int (*suspend)(void *handle);
-	/* handles IP specific hw/sw changes for resume */
+	/** @resume: handles IP specific hw/sw changes for resume */
 	int (*resume)(void *handle);
-	/* returns current IP block idle status */
+	/** @is_idle: returns current IP block idle status */
 	bool (*is_idle)(void *handle);
-	/* poll for idle */
+	/** @wait_for_idle: poll for idle */
 	int (*wait_for_idle)(void *handle);
-	/* check soft reset the IP block */
+	/** @check_soft_reset: check soft reset the IP block */
 	bool (*check_soft_reset)(void *handle);
-	/* pre soft reset the IP block */
+	/** @pre_soft_reset: pre soft reset the IP block */
 	int (*pre_soft_reset)(void *handle);
-	/* soft reset the IP block */
+	/** @soft_reset: soft reset the IP block */
 	int (*soft_reset)(void *handle);
-	/* post soft reset the IP block */
+	/** @post_soft_reset: post soft reset the IP block */
 	int (*post_soft_reset)(void *handle);
-	/* enable/disable cg for the IP block */
+	/** @set_clockgating_state: enable/disable cg for the IP block */
 	int (*set_clockgating_state)(void *handle,
 				     enum amd_clockgating_state state);
-	/* enable/disable pg for the IP block */
+	/** @set_powergating_state: enable/disable pg for the IP block */
 	int (*set_powergating_state)(void *handle,
 				     enum amd_powergating_state state);
-	/* get current clockgating status */
+	/** @get_clockgating_state: get current clockgating status */
 	void (*get_clockgating_state)(void *handle, u32 *flags);
 };
 
diff --git a/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_1_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_1_0_offset.h
index 18a32477ed1d..fe0cbaade3c3 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_1_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_1_0_offset.h
@@ -89,6 +89,8 @@
 #define mmUVD_JPEG_RB_SIZE_BASE_IDX                                                                    1
 #define mmUVD_JPEG_ADDR_CONFIG                                                                         0x021f
 #define mmUVD_JPEG_ADDR_CONFIG_BASE_IDX                                                                1
+#define mmUVD_JPEG_PITCH                                                                               0x0222
+#define mmUVD_JPEG_PITCH_BASE_IDX                                                                      1
 #define mmUVD_JPEG_GPCOM_CMD                                                                           0x022c
 #define mmUVD_JPEG_GPCOM_CMD_BASE_IDX                                                                  1
 #define mmUVD_JPEG_GPCOM_DATA0                                                                         0x022d
@@ -203,6 +205,8 @@
 #define mmUVD_RB_WPTR4_BASE_IDX                                                                        1
 #define mmUVD_JRBC_RB_RPTR                                                                             0x0457
 #define mmUVD_JRBC_RB_RPTR_BASE_IDX                                                                    1
+#define mmUVD_LMI_JPEG_VMID                                                                            0x045d
+#define mmUVD_LMI_JPEG_VMID_BASE_IDX                                                                   1
 #define mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH                                                            0x045e
 #define mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH_BASE_IDX                                                   1
 #define mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW                                                             0x045f
@@ -231,6 +235,8 @@
 #define mmUVD_LMI_JRBC_IB_64BIT_BAR_HIGH_BASE_IDX                                                      1
 #define mmUVD_LMI_JRBC_IB_VMID                                                                         0x0507
 #define mmUVD_LMI_JRBC_IB_VMID_BASE_IDX                                                                1
+#define mmUVD_LMI_JRBC_RB_VMID                                                                         0x0508
+#define mmUVD_LMI_JRBC_RB_VMID_BASE_IDX                                                                1
 #define mmUVD_JRBC_RB_WPTR                                                                             0x0509
 #define mmUVD_JRBC_RB_WPTR_BASE_IDX                                                                    1
 #define mmUVD_JRBC_RB_CNTL                                                                             0x050a
@@ -239,6 +245,20 @@
 #define mmUVD_JRBC_IB_SIZE_BASE_IDX                                                                    1
 #define mmUVD_JRBC_LMI_SWAP_CNTL                                                                       0x050d
 #define mmUVD_JRBC_LMI_SWAP_CNTL_BASE_IDX                                                              1
+#define mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW                                                         0x050e
+#define mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW_BASE_IDX                                                1
+#define mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH                                                        0x050f
+#define mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH_BASE_IDX                                               1
+#define mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW                                                         0x0510
+#define mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW_BASE_IDX                                                1
+#define mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH                                                        0x0511
+#define mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH_BASE_IDX                                               1
+#define mmUVD_JRBC_RB_REF_DATA                                                                         0x0512
+#define mmUVD_JRBC_RB_REF_DATA_BASE_IDX                                                                1
+#define mmUVD_JRBC_RB_COND_RD_TIMER                                                                    0x0513
+#define mmUVD_JRBC_RB_COND_RD_TIMER_BASE_IDX                                                           1
+#define mmUVD_JRBC_EXTERNAL_REG_BASE                                                                   0x0517
+#define mmUVD_JRBC_EXTERNAL_REG_BASE_BASE_IDX                                                          1
 #define mmUVD_JRBC_SOFT_RESET                                                                          0x0519
 #define mmUVD_JRBC_SOFT_RESET_BASE_IDX                                                                 1
 #define mmUVD_JRBC_STATUS                                                                              0x051a
diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
index 33b4de4ad66e..4bc118df3bc4 100644
--- a/drivers/gpu/drm/amd/include/atomfirmware.h
+++ b/drivers/gpu/drm/amd/include/atomfirmware.h
@@ -1074,7 +1074,7 @@ struct atom_integrated_system_info_v1_11
   uint16_t  dpphy_override;                   // bit vector, enum of atom_sysinfo_dpphy_override_def
   uint16_t  lvds_misc;                        // enum of atom_sys_info_lvds_misc_def
   uint16_t  backlight_pwm_hz;                 // pwm frequency in hz
-  uint8_t   memorytype;                       // enum of atom_sys_mem_type
+  uint8_t   memorytype;                       // enum of atom_dmi_t17_mem_type_def, APU memory type indication.
   uint8_t   umachannelnumber;                 // number of memory channels
   uint8_t   pwr_on_digon_to_de;               /* all pwr sequence numbers below are in uint of 4ms */
   uint8_t   pwr_on_de_to_vary_bl;
@@ -1084,18 +1084,25 @@ struct atom_integrated_system_info_v1_11
   uint8_t   pwr_on_vary_bl_to_blon;
   uint8_t   pwr_down_bloff_to_vary_bloff;
   uint8_t   min_allowed_bl_level;
+  uint8_t   htc_hyst_limit;
+  uint8_t   htc_tmp_limit;
+  uint8_t   reserved1;
+  uint8_t   reserved2;
   struct atom_external_display_connection_info extdispconninfo;
   struct atom_14nm_dpphy_dvihdmi_tuningset dvi_tuningset;
   struct atom_14nm_dpphy_dvihdmi_tuningset hdmi_tuningset;
   struct atom_14nm_dpphy_dvihdmi_tuningset hdmi6g_tuningset;
-  struct atom_14nm_dpphy_dp_tuningset dp_tuningset;
-  struct atom_14nm_dpphy_dp_tuningset dp_hbr3_tuningset;
+  struct atom_14nm_dpphy_dp_tuningset dp_tuningset;        // rbr 1.62G dp tuning set
+  struct atom_14nm_dpphy_dp_tuningset dp_hbr3_tuningset;   // HBR3 dp tuning set
   struct atom_camera_data  camera_info;
   struct atom_hdmi_retimer_redriver_set dp0_retimer_set;   //for DP0
   struct atom_hdmi_retimer_redriver_set dp1_retimer_set;   //for DP1
   struct atom_hdmi_retimer_redriver_set dp2_retimer_set;   //for DP2
   struct atom_hdmi_retimer_redriver_set dp3_retimer_set;   //for DP3
-  uint32_t  reserved[108];
+  struct atom_14nm_dpphy_dp_tuningset dp_hbr_tuningset;    //hbr 2.7G dp tuning set
+  struct atom_14nm_dpphy_dp_tuningset dp_hbr2_tuningset;   //hbr2 5.4G dp turnig set
+  struct atom_14nm_dpphy_dp_tuningset edp_tuningset;       //edp tuning set
+  uint32_t  reserved[66];
 };
 
 
diff --git a/drivers/gpu/drm/amd/include/dm_pp_interface.h b/drivers/gpu/drm/amd/include/dm_pp_interface.h
index 7852952d1fde..1d93a0c574c9 100644
--- a/drivers/gpu/drm/amd/include/dm_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/dm_pp_interface.h
@@ -23,6 +23,8 @@
 #ifndef _DM_PP_INTERFACE_
 #define _DM_PP_INTERFACE_
 
+#include "dm_services_types.h"
+
 #define PP_MAX_CLOCK_LEVELS 16
 
 enum amd_pp_display_config_type{
@@ -189,39 +191,4 @@ struct pp_display_clock_request {
 	uint32_t clock_freq_in_khz;
 };
 
-#define PP_MAX_WM_SETS 4
-
-enum pp_wm_set_id {
-	DC_WM_SET_A = 0,
-	DC_WM_SET_B,
-	DC_WM_SET_C,
-	DC_WM_SET_D,
-	DC_WM_SET_INVALID = 0xffff,
-};
-
-struct pp_wm_set_with_dmif_clock_range_soc15 {
-	enum pp_wm_set_id wm_set_id;
-	uint32_t wm_min_dcefclk_in_khz;
-	uint32_t wm_max_dcefclk_in_khz;
-	uint32_t wm_min_memclk_in_khz;
-	uint32_t wm_max_memclk_in_khz;
-};
-
-struct pp_wm_set_with_mcif_clock_range_soc15 {
-	enum pp_wm_set_id wm_set_id;
-	uint32_t wm_min_socclk_in_khz;
-	uint32_t wm_max_socclk_in_khz;
-	uint32_t wm_min_memclk_in_khz;
-	uint32_t wm_max_memclk_in_khz;
-};
-
-struct pp_wm_sets_with_clock_ranges_soc15 {
-	uint32_t num_wm_sets_dmif;
-	uint32_t num_wm_sets_mcif;
-	struct pp_wm_set_with_dmif_clock_range_soc15
-		wm_sets_dmif[PP_MAX_WM_SETS];
-	struct pp_wm_set_with_mcif_clock_range_soc15
-		wm_sets_mcif[PP_MAX_WM_SETS];
-};
-
 #endif /* _DM_PP_INTERFACE_ */
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/gfx/irqsrcs_gfx_9_0.h b/drivers/gpu/drm/amd/include/ivsrcid/gfx/irqsrcs_gfx_9_0.h
new file mode 100644
index 000000000000..36306c57a2b4
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/gfx/irqsrcs_gfx_9_0.h
@@ -0,0 +1,55 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __IRQSRCS_GFX_9_0_H__
+#define __IRQSRCS_GFX_9_0_H__
+
+
+#define GFX_9_0__SRCID__CP_RB_INTERRUPT_PKT					176		/* B0 CP_INTERRUPT pkt in RB */
+#define GFX_9_0__SRCID__CP_IB1_INTERRUPT_PKT				177		/* B1 CP_INTERRUPT pkt in IB1 */
+#define GFX_9_0__SRCID__CP_IB2_INTERRUPT_PKT				178		/* B2 CP_INTERRUPT pkt in IB2 */
+#define GFX_9_0__SRCID__CP_PM4_PKT_RSVD_BIT_ERROR			180		/* B4 PM4 Pkt Rsvd Bits Error */
+#define GFX_9_0__SRCID__CP_EOP_INTERRUPT					181		/* B5 End-of-Pipe Interrupt */
+#define GFX_9_0__SRCID__CP_BAD_OPCODE_ERROR					183		/* B7 Bad Opcode Error */
+#define GFX_9_0__SRCID__CP_PRIV_REG_FAULT					184		/* B8 Privileged Register Fault */
+#define GFX_9_0__SRCID__CP_PRIV_INSTR_FAULT					185		/* B9 Privileged Instr Fault */
+#define GFX_9_0__SRCID__CP_WAIT_MEM_SEM_FAULT				186		/* BA Wait Memory Semaphore Fault (Synchronization Object Fault) */
+#define GFX_9_0__SRCID__CP_CTX_EMPTY_INTERRUPT				187		/* BB Context Empty Interrupt */
+#define GFX_9_0__SRCID__CP_CTX_BUSY_INTERRUPT				188		/* BC Context Busy Interrupt */
+#define GFX_9_0__SRCID__CP_ME_WAIT_REG_MEM_POLL_TIMEOUT		192		/* C0 CP.ME Wait_Reg_Mem Poll Timeout */
+#define GFX_9_0__SRCID__CP_SIG_INCOMPLETE					193		/* C1 "Surface Probe Fault Signal Incomplete" */
+#define GFX_9_0__SRCID__CP_PREEMPT_ACK					    194		/* C2 Preemption Ack-wledge */
+#define GFX_9_0__SRCID__CP_GPF					            195		/* C3 General Protection Fault (GPF) */
+#define GFX_9_0__SRCID__CP_GDS_ALLOC_ERROR					196		/* C4 GDS Alloc Error */
+#define GFX_9_0__SRCID__CP_ECC_ERROR					    197		/* C5 ECC  Error */
+#define GFX_9_0__SRCID__CP_COMPUTE_QUERY_STATUS             199     /* C7 Compute query status */
+#define GFX_9_0__SRCID__CP_VM_DOORBELL					    200		/* C8 Unattached VM Doorbell Received */
+#define GFX_9_0__SRCID__CP_FUE_ERROR					    201		/* C9 ECC FUE Error */
+#define GFX_9_0__SRCID__RLC_STRM_PERF_MONITOR_INTERRUPT		202		/* CA Streaming Perf Monitor Interrupt */
+#define GFX_9_0__SRCID__GRBM_RD_TIMEOUT_ERROR				232		/* E8 CRead timeout error */
+#define GFX_9_0__SRCID__GRBM_REG_GUI_IDLE					233		/* E9 Register GUI Idle */
+#define GFX_9_0__SRCID__SQ_INTERRUPT_ID					    239		/* EF SQ Interrupt (ttrace wrap, errors) */
+
+#endif /* __IRQSRCS_GFX_9_0_H__ */
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/ivsrcid_vislands30.h b/drivers/gpu/drm/amd/include/ivsrcid/ivsrcid_vislands30.h
index c6b6f97de9de..aaed7f59e0e2 100644
--- a/drivers/gpu/drm/amd/include/ivsrcid/ivsrcid_vislands30.h
+++ b/drivers/gpu/drm/amd/include/ivsrcid/ivsrcid_vislands30.h
@@ -198,4 +198,102 @@
 #define VISLANDS30_IV_SRCID_HPD_RX_F		                    42	    // 0x2a		
 #define VISLANDS30_IV_EXTID_HPD_RX_F                         11
 
+#define VISLANDS30_IV_SRCID_GPIO_19                            0x00000053  /* 83 */
+
+#define VISLANDS30_IV_SRCID_SRBM_READ_TIMEOUT_ERR              0x00000060  /* 96 */
+#define VISLANDS30_IV_SRCID_SRBM_CTX_SWITCH                    0x00000061  /* 97 */
+
+#define VISLANDS30_IV_SRBM_REG_ACCESS_ERROR                    0x00000062  /* 98 */
+
+
+#define VISLANDS30_IV_SRCID_UVD_ENC_GEN_PURP                   0x00000077  /* 119 */
+#define VISLANDS30_IV_SRCID_UVD_SYSTEM_MESSAGE                 0x0000007c  /* 124 */
+
+#define VISLANDS30_IV_SRCID_BIF_PF_VF_MSGBUF_VALID             0x00000087  /* 135 */
+
+#define VISLANDS30_IV_SRCID_BIF_VF_PF_MSGBUF_ACK               0x0000008a  /* 138 */
+
+#define VISLANDS30_IV_SRCID_SYS_PAGE_INV_FAULT                 0x0000008c  /* 140 */
+#define VISLANDS30_IV_SRCID_SYS_MEM_PROT_FAULT                 0x0000008d  /* 141 */
+
+#define VISLANDS30_IV_SRCID_SEM_PAGE_INV_FAULT                 0x00000090  /* 144 */
+#define VISLANDS30_IV_SRCID_SEM_MEM_PROT_FAULT                 0x00000091  /* 145 */
+
+#define VISLANDS30_IV_SRCID_GFX_PAGE_INV_FAULT                 0x00000092  /* 146 */
+#define VISLANDS30_IV_SRCID_GFX_MEM_PROT_FAULT                 0x00000093  /* 147 */
+
+#define VISLANDS30_IV_SRCID_ACP                                0x000000a2  /* 162 */
+
+#define VISLANDS30_IV_SRCID_VCE_TRAP                           0x000000a7  /* 167 */
+#define VISLANDS30_IV_EXTID_VCE_TRAP_GENERAL_PURPOSE           0
+#define VISLANDS30_IV_EXTID_VCE_TRAP_LOW_LATENCY               1
+#define VISLANDS30_IV_EXTID_VCE_TRAP_REAL_TIME                 2
+
+#define VISLANDS30_IV_SRCID_CP_INT_RB                          0x000000b0  /* 176 */
+#define VISLANDS30_IV_SRCID_CP_INT_IB1                         0x000000b1  /* 177 */
+#define VISLANDS30_IV_SRCID_CP_INT_IB2                         0x000000b2  /* 178 */
+#define VISLANDS30_IV_SRCID_CP_PM4_RES_BITS_ERR                0x000000b4  /* 180 */
+#define VISLANDS30_IV_SRCID_CP_END_OF_PIPE                     0x000000b5  /* 181 */
+#define VISLANDS30_IV_SRCID_CP_BAD_OPCODE                      0x000000b7  /* 183 */
+#define VISLANDS30_IV_SRCID_CP_PRIV_REG_FAULT                  0x000000b8  /* 184 */
+#define VISLANDS30_IV_SRCID_CP_PRIV_INSTR_FAULT                0x000000b9  /* 185 */
+#define VISLANDS30_IV_SRCID_CP_WAIT_MEM_SEM_FAULT              0x000000ba  /* 186 */
+#define VISLANDS30_IV_SRCID_CP_GUI_IDLE                        0x000000bb  /* 187 */
+#define VISLANDS30_IV_SRCID_CP_GUI_BUSY                        0x000000bc  /* 188 */
+
+#define VISLANDS30_IV_SRCID_CP_COMPUTE_QUERY_STATUS            0x000000bf  /* 191 */
+#define VISLANDS30_IV_SRCID_CP_ECC_ERROR                       0x000000c5  /* 197 */
+
+#define CARRIZO_IV_SRCID_CP_COMPUTE_QUERY_STATUS               0x000000c7  /* 199 */
+
+#define VISLANDS30_IV_SRCID_CP_WAIT_REG_MEM_POLL_TIMEOUT       0x000000c0  /* 192 */
+#define VISLANDS30_IV_SRCID_CP_SEM_SIG_INCOMPL                 0x000000c1  /* 193 */
+#define VISLANDS30_IV_SRCID_CP_PREEMPT_ACK                     0x000000c2  /* 194 */
+#define VISLANDS30_IV_SRCID_CP_GENERAL_PROT_FAULT              0x000000c3  /* 195 */
+#define VISLANDS30_IV_SRCID_CP_GDS_ALLOC_ERROR                 0x000000c4  /* 196 */
+#define VISLANDS30_IV_SRCID_CP_ECC_ERROR                       0x000000c5  /* 197 */
+
+#define VISLANDS30_IV_SRCID_RLC_STRM_PERF_MONITOR              0x000000ca  /* 202 */
+
+#define VISLANDS30_IV_SDMA_ATOMIC_SRC_ID                       0x000000da  /* 218 */
+
+#define VISLANDS30_IV_SRCID_SDMA_ECC_ERROR                     0x000000dc  /* 220 */
+
+#define VISLANDS30_IV_SRCID_SDMA_TRAP          	               0x000000e0  /* 224 */
+#define VISLANDS30_IV_SRCID_SDMA_SEM_INCOMPLETE                0x000000e1  /* 225 */
+#define VISLANDS30_IV_SRCID_SDMA_SEM_WAIT                      0x000000e2  /* 226 */
+
+
+#define VISLANDS30_IV_SRCID_SMU_DISP_TIMER2_TRIGGER            0x000000e5  /* 229 */
+
+#define VISLANDS30_IV_SRCID_CG_TSS_THERMAL_LOW_TO_HIGH         0x000000e6  /* 230 */
+#define VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW         0x000000e7  /* 231 */
+
+#define VISLANDS30_IV_SRCID_GRBM_READ_TIMEOUT_ERR              0x000000e8  /* 232 */
+#define VISLANDS30_IV_SRCID_GRBM_REG_GUI_IDLE                  0x000000e9  /* 233 */
+
+#define VISLANDS30_IV_SRCID_SQ_INTERRUPT_MSG                   0x000000ef  /* 239 */
+
+#define VISLANDS30_IV_SRCID_SDMA_PREEMPT                       0x000000f0  /* 240 */
+#define VISLANDS30_IV_SRCID_SDMA_VM_HOLE                       0x000000f2  /* 242 */
+#define VISLANDS30_IV_SRCID_SDMA_CTXEMPTY                      0x000000f3  /* 243 */
+#define VISLANDS30_IV_SRCID_SDMA_DOORBELL_INVALID              0x000000f4  /* 244 */
+#define VISLANDS30_IV_SRCID_SDMA_FROZEN                        0x000000f5  /* 245 */
+#define VISLANDS30_IV_SRCID_SDMA_POLL_TIMEOUT                  0x000000f6  /* 246 */
+#define VISLANDS30_IV_SRCID_SDMA_SRBM_WRITE                    0x000000f7  /* 247 */
+
+#define VISLANDS30_IV_SRCID_CG_THERMAL_TRIG                    0x000000f8  /* 248 */
+
+#define VISLANDS30_IV_SRCID_SMU_DISP_TIMER_TRIGGER             0x000000fd  /* 253 */
+
+/* These are not "real" source ids defined by HW */
+#define VISLANDS30_IV_SRCID_VM_CONTEXT_ALL                     0x00000100  /* 256 */
+#define VISLANDS30_IV_EXTID_VM_CONTEXT0_ALL                    0
+#define VISLANDS30_IV_EXTID_VM_CONTEXT1_ALL                    1
+
+
+/* IV Extended IDs */
+#define VISLANDS30_IV_EXTID_NONE                               0x00000000
+#define VISLANDS30_IV_EXTID_INVALID                            0xffffffff
+
 #endif // _IVSRCID_VISLANDS30_H_
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/sdma0/irqsrcs_sdma0_4_0.h b/drivers/gpu/drm/amd/include/ivsrcid/sdma0/irqsrcs_sdma0_4_0.h
new file mode 100644
index 000000000000..802413832fe8
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/sdma0/irqsrcs_sdma0_4_0.h
@@ -0,0 +1,50 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __IRQSRCS_SDMA0_4_0_H__
+#define __IRQSRCS_SDMA0_4_0_H__
+
+#define SDMA0_4_0__SRCID__SDMA_ATOMIC_RTN_DONE                         217             /* 0xD9 SDMA atomic*_rtn ops complete  */
+#define SDMA0_4_0__SRCID__SDMA_ATOMIC_TIMEOUT                          218             /* 0xDA SDMA atomic CMPSWAP loop timeout  */
+#define SDMA0_4_0__SRCID__SDMA_IB_PREEMPT                                      219             /* 0xDB sdma mid-command buffer preempt interrupt  */
+#define SDMA0_4_0__SRCID__SDMA_ECC                                             220             /* 0xDC ECC  Error  */
+#define SDMA0_4_0__SRCID__SDMA_PAGE_FAULT                                      221             /* 0xDD Page Fault Error from UTCL2 when nack=3  */
+#define SDMA0_4_0__SRCID__SDMA_PAGE_NULL                                       222             /* 0xDE Page Null from UTCL2 when nack=2  */
+#define SDMA0_4_0__SRCID__SDMA_XNACK                                       223         /* 0xDF Page retry  timeout after UTCL2 return nack=1  */
+#define SDMA0_4_0__SRCID__SDMA_TRAP                                            224             /* 0xE0 Trap  */
+#define SDMA0_4_0__SRCID__SDMA_SEM_INCOMPLETE_TIMEOUT          225             /* 0xE1 0xDAGPF (Sem incomplete timeout)  */
+#define SDMA0_4_0__SRCID__SDMA_SEM_WAIT_FAIL_TIMEOUT           226             /* 0xE2 Semaphore wait fail timeout  */
+#define SDMA0_4_0__SRCID__SDMA_SRAM_ECC                                            228         /* 0xE4 SRAM ECC Error  */
+#define SDMA0_4_0__SRCID__SDMA_PREEMPT                                     240         /* 0xF0 SDMA New Run List  */
+#define SDMA0_4_0__SRCID__SDMA_VM_HOLE                                     242         /* 0xF2 MC or SEM address in VM hole  */
+#define SDMA0_4_0__SRCID__SDMA_CTXEMPTY                                            243         /* 0xF3 Context Empty  */
+#define SDMA0_4_0__SRCID__SDMA_DOORBELL_INVALID                                244             /* 0xF4 Doorbell BE invalid  */
+#define SDMA0_4_0__SRCID__SDMA_FROZEN                                      245         /* 0xF5 SDMA Frozen  */
+#define SDMA0_4_0__SRCID__SDMA_POLL_TIMEOUT                                    246             /* 0xF6 SRBM read poll timeout  */
+#define SDMA0_4_0__SRCID__SDMA_SRBMWRITE                                       247             /* 0xF7 SRBM write Protection  */
+
+#endif /* __IRQSRCS_SDMA_4_0_H__ */
+
+
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/sdma1/irqsrcs_sdma1_4_0.h b/drivers/gpu/drm/amd/include/ivsrcid/sdma1/irqsrcs_sdma1_4_0.h
new file mode 100644
index 000000000000..d12a35619f9a
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/sdma1/irqsrcs_sdma1_4_0.h
@@ -0,0 +1,50 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __IRQSRCS_SDMA1_4_0_H__
+#define __IRQSRCS_SDMA1_4_0_H__
+
+#define SDMA1_4_0__SRCID__SDMA_ATOMIC_RTN_DONE                         217             /* 0xD9 SDMA atomic*_rtn ops complete  */
+#define SDMA1_4_0__SRCID__SDMA_ATOMIC_TIMEOUT                          218             /* 0xDA SDMA atomic CMPSWAP loop timeout  */
+#define SDMA1_4_0__SRCID__SDMA_IB_PREEMPT                                      219             /* 0xDB sdma mid-command buffer preempt interrupt  */
+#define SDMA1_4_0__SRCID__SDMA_ECC                                             220             /* 0xDC ECC  Error  */
+#define SDMA1_4_0__SRCID__SDMA_PAGE_FAULT                                      221             /* 0xDD Page Fault Error from UTCL2 when nack=3  */
+#define SDMA1_4_0__SRCID__SDMA_PAGE_NULL                                       222             /* 0xDE Page Null from UTCL2 when nack=2  */
+#define SDMA1_4_0__SRCID__SDMA_XNACK                                       223         /* 0xDF Page retry  timeout after UTCL2 return nack=1  */
+#define SDMA1_4_0__SRCID__SDMA_TRAP                                            224             /* 0xE0 Trap  */
+#define SDMA1_4_0__SRCID__SDMA_SEM_INCOMPLETE_TIMEOUT          225             /* 0xE1 0xDAGPF (Sem incomplete timeout)  */
+#define SDMA1_4_0__SRCID__SDMA_SEM_WAIT_FAIL_TIMEOUT           226             /* 0xE2 Semaphore wait fail timeout  */
+#define SDMA1_4_0__SRCID__SDMA_SRAM_ECC                                            228         /* 0xE4 SRAM ECC Error  */
+#define SDMA1_4_0__SRCID__SDMA_PREEMPT                                     240         /* 0xF0 SDMA New Run List  */
+#define SDMA1_4_0__SRCID__SDMA_VM_HOLE                                     242         /* 0xF2 MC or SEM address in VM hole  */
+#define SDMA1_4_0__SRCID__SDMA_CTXEMPTY                                            243         /* 0xF3 Context Empty  */
+#define SDMA1_4_0__SRCID__SDMA_DOORBELL_INVALID                                244             /* 0xF4 Doorbell BE invalid  */
+#define SDMA1_4_0__SRCID__SDMA_FROZEN                                      245         /* 0xF5 SDMA Frozen  */
+#define SDMA1_4_0__SRCID__SDMA_POLL_TIMEOUT                                    246             /* 0xF6 SRBM read poll timeout  */
+#define SDMA1_4_0__SRCID__SDMA_SRBMWRITE                                       247             /* 0xF7 SRBM write Protection  */
+
+#endif /* __IRQSRCS_SDMA1_4_0_H__ */
+
+
diff --git a/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.h b/drivers/gpu/drm/amd/include/ivsrcid/smuio/irqsrcs_smuio_9_0.h
index 7a65206a6d21..02bab4673cd4 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.h
+++ b/drivers/gpu/drm/amd/include/ivsrcid/smuio/irqsrcs_smuio_9_0.h
@@ -23,13 +23,10 @@
  *
  */
 
-#ifndef __SOC_BOUNDING_BOX_H__
-#define __SOC_BOUNDING_BOX_H__
+#ifndef __IRQSRCS_SMUIO_9_0_H__
+#define __IRQSRCS_SMUIO_9_0_H__
 
-#include "dml_common_defs.h"
+#define SMUIO_9_0__SRCID__SMUIO_GPIO19			83		/* GPIO19 interrupt  */
 
-void dml_socbb_set_latencies(soc_bounding_box_st *to_box, soc_bounding_box_st *from_box);
-voltage_scaling_st dml_socbb_voltage_scaling(const soc_bounding_box_st *box, enum voltage_state voltage);
-double dml_socbb_return_bw_mhz(soc_bounding_box_st *box, enum voltage_state voltage);
+#endif /* __IRQSRCS_SMUIO_9_0_H__ */
 
-#endif
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/thm/irqsrcs_thm_9_0.h b/drivers/gpu/drm/amd/include/ivsrcid/thm/irqsrcs_thm_9_0.h
new file mode 100644
index 000000000000..5218bc53fb2d
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/thm/irqsrcs_thm_9_0.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __IRQSRCS_THM_9_0_H__
+#define __IRQSRCS_THM_9_0_H__
+
+#define THM_9_0__SRCID__THM_DIG_THERM_L2H		0		/* ASIC_TEMP > CG_THERMAL_INT.DIG_THERM_INTH  */
+#define THM_9_0__SRCID__THM_DIG_THERM_H2L		1		/* ASIC_TEMP < CG_THERMAL_INT.DIG_THERM_INTL  */
+
+#endif /* __IRQSRCS_THM_9_0_H__ */
+
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/uvd/irqsrcs_uvd_7_0.h b/drivers/gpu/drm/amd/include/ivsrcid/uvd/irqsrcs_uvd_7_0.h
new file mode 100644
index 000000000000..fb041aee6c66
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/uvd/irqsrcs_uvd_7_0.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __IRQSRCS_UVD_7_0_H__
+#define __IRQSRCS_UVD_7_0_H__
+
+#define UVD_7_0__SRCID__UVD_ENC_GEN_PURP                119
+#define UVD_7_0__SRCID__UVD_ENC_LOW_LATENCY             120
+#define UVD_7_0__SRCID__UVD_SYSTEM_MESSAGE_INTERRUPT	124		/* UVD system message interrupt  */
+
+#endif /* __IRQSRCS_UVD_7_0_H__ */
+
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/vce/irqsrcs_vce_4_0.h b/drivers/gpu/drm/amd/include/ivsrcid/vce/irqsrcs_vce_4_0.h
new file mode 100644
index 000000000000..3440bab565af
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/vce/irqsrcs_vce_4_0.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __IRQSRCS_VCE_4_0_H__
+#define __IRQSRCS_VCE_4_0_H__
+
+#define VCE_4_0__CTXID__VCE_TRAP_GENERAL_PURPOSE               0
+#define VCE_4_0__CTXID__VCE_TRAP_LOW_LATENCY                   1
+#define VCE_4_0__CTXID__VCE_TRAP_REAL_TIME                     2
+
+#endif /* __IRQSRCS_VCE_4_0_H__ */
+
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/vcn/irqsrcs_vcn_1_0.h b/drivers/gpu/drm/amd/include/ivsrcid/vcn/irqsrcs_vcn_1_0.h
new file mode 100644
index 000000000000..e5951709bfc3
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/vcn/irqsrcs_vcn_1_0.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __IRQSRCS_VCN_1_0_H__
+#define __IRQSRCS_VCN_1_0_H__
+
+#define VCN_1_0__SRCID__UVD_ENC_GENERAL_PURPOSE                 119     /* 0x77 Encoder General Purpose  */
+#define VCN_1_0__SRCID__UVD_ENC_LOW_LATENCY                     120     /* 0x78 Encoder Low Latency  */
+#define VCN_1_0__SRCID__UVD_SYSTEM_MESSAGE_INTERRUPT	        124		/* 0x7c UVD system message interrupt  */
+
+#endif /* __IRQSRCS_VCN_1_0_H__ */
+
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/vmc/irqsrcs_vmc_1_0.h b/drivers/gpu/drm/amd/include/ivsrcid/vmc/irqsrcs_vmc_1_0.h
new file mode 100644
index 000000000000..d130936c9989
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/vmc/irqsrcs_vmc_1_0.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __IRQSRCS_VMC_1_0_H__
+#define __IRQSRCS_VMC_1_0_H__
+
+
+#define VMC_1_0__SRCID__VM_FAULT                            0
+#define VMC_1_0__SRCID__VM_CONTEXT0_ALL                     256
+#define VMC_1_0__SRCID__VM_CONTEXT1_ALL                     257
+
+#define UTCL2_1_0__SRCID__FAULT                             0       /* UTC L2 has encountered a fault or retry scenario */
+
+
+#endif /* __IRQSRCS_VMC_1_0_H__ */
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index 5733fbee07f7..14391b06080c 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -47,6 +47,17 @@ enum kfd_preempt_type {
 	KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
 };
 
+struct kfd_vm_fault_info {
+	uint64_t	page_addr;
+	uint32_t	vmid;
+	uint32_t	mc_id;
+	uint32_t	status;
+	bool		prot_valid;
+	bool		prot_read;
+	bool		prot_write;
+	bool		prot_exec;
+};
+
 struct kfd_cu_info {
 	uint32_t num_shader_engines;
 	uint32_t num_shader_arrays_per_engine;
@@ -259,6 +270,21 @@ struct tile_config {
  * IB to the corresponding ring (ring type). The IB is executed with the
  * specified VMID in a user mode context.
  *
+ * @get_vm_fault_info: Return information about a recent VM fault on
+ * GFXv7 and v8. If multiple VM faults occurred since the last call of
+ * this function, it will return information about the first of those
+ * faults. On GFXv9 VM fault information is fully contained in the IH
+ * packet and this function is not needed.
+ *
+ * @read_vmid_from_vmfault_reg: On Hawaii the VMID is not set in the
+ * IH ring entry. This function allows the KFD ISR to get the VMID
+ * from the fault status register as early as possible.
+ *
+ * @gpu_recover: let kgd reset gpu after kfd detect CPC hang
+ *
+ * @set_compute_idle: Indicates that compute is idle on a device. This
+ * can be used to change power profiles depending on compute activity.
+ *
  * This structure contains function pointers to services that the kgd driver
  * provides to amdkfd driver.
  *
@@ -374,6 +400,14 @@ struct kfd2kgd_calls {
 	int (*submit_ib)(struct kgd_dev *kgd, enum kgd_engine_type engine,
 			uint32_t vmid, uint64_t gpu_addr,
 			uint32_t *ib_cmd, uint32_t ib_len);
+
+	int (*get_vm_fault_info)(struct kgd_dev *kgd,
+			struct kfd_vm_fault_info *info);
+	uint32_t (*read_vmid_from_vmfault_reg)(struct kgd_dev *kgd);
+
+	void (*gpu_recover)(struct kgd_dev *kgd);
+
+	void (*set_compute_idle)(struct kgd_dev *kgd, bool idle);
 };
 
 /**
@@ -399,6 +433,10 @@ struct kfd2kgd_calls {
  * @schedule_evict_and_restore_process: Schedules work queue that will prepare
  * for safe eviction of KFD BOs that belong to the specified process.
  *
+ * @pre_reset: Notifies amdkfd that amdgpu about to reset the gpu
+ *
+ * @post_reset: Notify amdkfd that amgpu successfully reseted the gpu
+ *
  * This structure contains function callback pointers so the kgd driver
  * will notify to the amdkfd about certain status changes.
  *
@@ -417,6 +455,8 @@ struct kgd2kfd_calls {
 	int (*resume_mm)(struct mm_struct *mm);
 	int (*schedule_evict_and_restore_process)(struct mm_struct *mm,
 			struct dma_fence *fence);
+	int  (*pre_reset)(struct kfd_dev *kfd);
+	int  (*post_reset)(struct kfd_dev *kfd);
 };
 
 int kgd2kfd_init(unsigned interface_version,
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index 06f08f34a110..6a41b81c7325 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -192,7 +192,6 @@ struct amd_pp_simple_clock_info;
 struct amd_pp_display_configuration;
 struct amd_pp_clock_info;
 struct pp_display_clock_request;
-struct pp_wm_sets_with_clock_ranges_soc15;
 struct pp_clock_levels_with_voltage;
 struct pp_clock_levels_with_latency;
 struct amd_pp_clocks;
@@ -232,16 +231,19 @@ struct amd_pm_funcs {
 	void (*debugfs_print_current_performance_level)(void *handle, struct seq_file *m);
 	int (*switch_power_profile)(void *handle, enum PP_SMC_POWER_PROFILE type, bool en);
 /* export to amdgpu */
-	void (*powergate_uvd)(void *handle, bool gate);
-	void (*powergate_vce)(void *handle, bool gate);
 	struct amd_vce_state *(*get_vce_clock_state)(void *handle, u32 idx);
 	int (*dispatch_tasks)(void *handle, enum amd_pp_task task_id,
 			enum amd_pm_state_type *user_state);
 	int (*load_firmware)(void *handle);
 	int (*wait_for_fw_loading_complete)(void *handle);
+	int (*set_powergating_by_smu)(void *handle,
+				uint32_t block_type, bool gate);
 	int (*set_clockgating_by_smu)(void *handle, uint32_t msg_id);
 	int (*set_power_limit)(void *handle, uint32_t n);
 	int (*get_power_limit)(void *handle, uint32_t *limit, bool default_limit);
+	int (*get_power_profile_mode)(void *handle, char *buf);
+	int (*set_power_profile_mode)(void *handle, long *input, uint32_t size);
+	int (*odn_edit_dpm_table)(void *handle, uint32_t type, long *input, uint32_t size);
 /* export to DC */
 	u32 (*get_sclk)(void *handle, bool low);
 	u32 (*get_mclk)(void *handle, bool low);
@@ -261,15 +263,12 @@ struct amd_pm_funcs {
 		enum amd_pp_clock_type type,
 		struct pp_clock_levels_with_voltage *clocks);
 	int (*set_watermarks_for_clocks_ranges)(void *handle,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges);
+						void *clock_ranges);
 	int (*display_clock_voltage_request)(void *handle,
 				struct pp_display_clock_request *clock);
 	int (*get_display_mode_validation_clocks)(void *handle,
 		struct amd_pp_simple_clock_info *clocks);
-	int (*get_power_profile_mode)(void *handle, char *buf);
-	int (*set_power_profile_mode)(void *handle, long *input, uint32_t size);
-	int (*odn_edit_dpm_table)(void *handle, uint32_t type, long *input, uint32_t size);
-	int (*set_mmhub_powergating_by_smu)(void *handle);
+	int (*notify_smu_enable_pwe)(void *handle);
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index d567be49c31b..7a646f94b478 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -221,29 +221,7 @@ static int pp_sw_reset(void *handle)
 static int pp_set_powergating_state(void *handle,
 				    enum amd_powergating_state state)
 {
-	struct amdgpu_device *adev = handle;
-	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
-	int ret;
-
-	if (!hwmgr || !hwmgr->pm_en)
-		return 0;
-
-	if (hwmgr->hwmgr_func->gfx_off_control) {
-		/* Enable/disable GFX off through SMU */
-		ret = hwmgr->hwmgr_func->gfx_off_control(hwmgr,
-							 state == AMD_PG_STATE_GATE);
-		if (ret)
-			pr_err("gfx off control failed!\n");
-	}
-
-	if (hwmgr->hwmgr_func->enable_per_cu_power_gating == NULL) {
-		pr_debug("%s was not implemented.\n", __func__);
-		return 0;
-	}
-
-	/* Enable/disable GFX per cu powergating through SMU */
-	return hwmgr->hwmgr_func->enable_per_cu_power_gating(hwmgr,
-			state == AMD_PG_STATE_GATE);
+	return 0;
 }
 
 static int pp_suspend(void *handle)
@@ -1020,7 +998,7 @@ static int pp_get_display_power_level(void *handle,
 static int pp_get_current_clocks(void *handle,
 		struct amd_pp_clock_info *clocks)
 {
-	struct amd_pp_simple_clock_info simple_clocks;
+	struct amd_pp_simple_clock_info simple_clocks = { 0 };
 	struct pp_clock_info hw_clocks;
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
@@ -1056,7 +1034,10 @@ static int pp_get_current_clocks(void *handle,
 	clocks->max_engine_clock_in_sr = hw_clocks.max_eng_clk;
 	clocks->min_engine_clock_in_sr = hw_clocks.min_eng_clk;
 
-	clocks->max_clocks_state = simple_clocks.level;
+	if (simple_clocks.level == 0)
+		clocks->max_clocks_state = PP_DAL_POWERLEVEL_7;
+	else
+		clocks->max_clocks_state = simple_clocks.level;
 
 	if (0 == phm_get_current_shallow_sleep_clocks(hwmgr, &hwmgr->current_ps->hardware, &hw_clocks)) {
 		clocks->max_engine_clock_in_sr = hw_clocks.max_eng_clk;
@@ -1118,17 +1099,17 @@ static int pp_get_clock_by_type_with_voltage(void *handle,
 }
 
 static int pp_set_watermarks_for_clocks_ranges(void *handle,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+		void *clock_ranges)
 {
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	if (!hwmgr || !hwmgr->pm_en ||!wm_with_clock_ranges)
+	if (!hwmgr || !hwmgr->pm_en || !clock_ranges)
 		return -EINVAL;
 
 	mutex_lock(&hwmgr->smu_lock);
 	ret = phm_set_watermarks_for_clocks_ranges(hwmgr,
-			wm_with_clock_ranges);
+			clock_ranges);
 	mutex_unlock(&hwmgr->smu_lock);
 
 	return ret;
@@ -1159,6 +1140,8 @@ static int pp_get_display_mode_validation_clocks(void *handle,
 	if (!hwmgr || !hwmgr->pm_en ||!clocks)
 		return -EINVAL;
 
+	clocks->level = PP_DAL_POWERLEVEL_7;
+
 	mutex_lock(&hwmgr->smu_lock);
 
 	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_DynamicPatchPowerState))
@@ -1168,19 +1151,78 @@ static int pp_get_display_mode_validation_clocks(void *handle,
 	return ret;
 }
 
-static int pp_set_mmhub_powergating_by_smu(void *handle)
+static int pp_dpm_powergate_mmhub(void *handle)
 {
 	struct pp_hwmgr *hwmgr = handle;
 
 	if (!hwmgr || !hwmgr->pm_en)
 		return -EINVAL;
 
-	if (hwmgr->hwmgr_func->set_mmhub_powergating_by_smu == NULL) {
+	if (hwmgr->hwmgr_func->powergate_mmhub == NULL) {
+		pr_info("%s was not implemented.\n", __func__);
+		return 0;
+	}
+
+	return hwmgr->hwmgr_func->powergate_mmhub(hwmgr);
+}
+
+static int pp_dpm_powergate_gfx(void *handle, bool gate)
+{
+	struct pp_hwmgr *hwmgr = handle;
+
+	if (!hwmgr || !hwmgr->pm_en)
+		return 0;
+
+	if (hwmgr->hwmgr_func->powergate_gfx == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
 		return 0;
 	}
 
-	return hwmgr->hwmgr_func->set_mmhub_powergating_by_smu(hwmgr);
+	return hwmgr->hwmgr_func->powergate_gfx(hwmgr, gate);
+}
+
+static int pp_set_powergating_by_smu(void *handle,
+				uint32_t block_type, bool gate)
+{
+	int ret = 0;
+
+	switch (block_type) {
+	case AMD_IP_BLOCK_TYPE_UVD:
+	case AMD_IP_BLOCK_TYPE_VCN:
+		pp_dpm_powergate_uvd(handle, gate);
+		break;
+	case AMD_IP_BLOCK_TYPE_VCE:
+		pp_dpm_powergate_vce(handle, gate);
+		break;
+	case AMD_IP_BLOCK_TYPE_GMC:
+		pp_dpm_powergate_mmhub(handle);
+		break;
+	case AMD_IP_BLOCK_TYPE_GFX:
+		ret = pp_dpm_powergate_gfx(handle, gate);
+		break;
+	default:
+		break;
+	}
+	return ret;
+}
+
+static int pp_notify_smu_enable_pwe(void *handle)
+{
+	struct pp_hwmgr *hwmgr = handle;
+
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
+
+	if (hwmgr->hwmgr_func->smus_notify_pwe == NULL) {
+		pr_info("%s was not implemented.\n", __func__);
+		return -EINVAL;;
+	}
+
+	mutex_lock(&hwmgr->smu_lock);
+	hwmgr->hwmgr_func->smus_notify_pwe(hwmgr);
+	mutex_unlock(&hwmgr->smu_lock);
+
+	return 0;
 }
 
 static const struct amd_pm_funcs pp_dpm_funcs = {
@@ -1189,8 +1231,6 @@ static const struct amd_pm_funcs pp_dpm_funcs = {
 	.force_performance_level = pp_dpm_force_performance_level,
 	.get_performance_level = pp_dpm_get_performance_level,
 	.get_current_power_state = pp_dpm_get_current_power_state,
-	.powergate_vce = pp_dpm_powergate_vce,
-	.powergate_uvd = pp_dpm_powergate_uvd,
 	.dispatch_tasks = pp_dpm_dispatch_tasks,
 	.set_fan_control_mode = pp_dpm_set_fan_control_mode,
 	.get_fan_control_mode = pp_dpm_get_fan_control_mode,
@@ -1210,6 +1250,7 @@ static const struct amd_pm_funcs pp_dpm_funcs = {
 	.get_vce_clock_state = pp_dpm_get_vce_clock_state,
 	.switch_power_profile = pp_dpm_switch_power_profile,
 	.set_clockgating_by_smu = pp_set_clockgating_by_smu,
+	.set_powergating_by_smu = pp_set_powergating_by_smu,
 	.get_power_profile_mode = pp_get_power_profile_mode,
 	.set_power_profile_mode = pp_set_power_profile_mode,
 	.odn_edit_dpm_table = pp_odn_edit_dpm_table,
@@ -1227,5 +1268,5 @@ static const struct amd_pm_funcs pp_dpm_funcs = {
 	.set_watermarks_for_clocks_ranges = pp_set_watermarks_for_clocks_ranges,
 	.display_clock_voltage_request = pp_display_clock_voltage_request,
 	.get_display_mode_validation_clocks = pp_get_display_mode_validation_clocks,
-	.set_mmhub_powergating_by_smu = pp_set_mmhub_powergating_by_smu,
+	.notify_smu_enable_pwe = pp_notify_smu_enable_pwe,
 };
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
index a0bb921fac22..53207e76b0f3 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
@@ -435,7 +435,7 @@ int phm_get_clock_by_type_with_voltage(struct pp_hwmgr *hwmgr,
 }
 
 int phm_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+					void *clock_ranges)
 {
 	PHM_FUNC_CHECK(hwmgr);
 
@@ -443,7 +443,7 @@ int phm_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
 		return -EINVAL;
 
 	return hwmgr->hwmgr_func->set_watermarks_for_clocks_ranges(hwmgr,
-			wm_with_clock_ranges);
+								clock_ranges);
 }
 
 int phm_display_clock_voltage_request(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
index e63bc47dc715..8994aa5c8cf8 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
@@ -81,7 +81,6 @@ int hwmgr_early_init(struct pp_hwmgr *hwmgr)
 		return -EINVAL;
 
 	hwmgr->usec_timeout = AMD_MAX_USEC_TIMEOUT;
-	hwmgr->power_source = PP_PowerSource_AC;
 	hwmgr->pp_table_version = PP_TABLE_V1;
 	hwmgr->dpm_level = AMD_DPM_FORCED_LEVEL_AUTO;
 	hwmgr->request_dpm_level = AMD_DPM_FORCED_LEVEL_AUTO;
@@ -148,10 +147,10 @@ int hwmgr_early_init(struct pp_hwmgr *hwmgr)
 		smu7_init_function_pointers(hwmgr);
 		break;
 	case AMDGPU_FAMILY_AI:
-		hwmgr->feature_mask &= ~PP_GFXOFF_MASK;
 		switch (hwmgr->chip_id) {
 		case CHIP_VEGA10:
 		case CHIP_VEGA20:
+			hwmgr->feature_mask &= ~PP_GFXOFF_MASK;
 			hwmgr->smumgr_funcs = &vega10_smu_funcs;
 			vega10_hwmgr_init(hwmgr);
 			break;
@@ -236,6 +235,11 @@ int hwmgr_hw_init(struct pp_hwmgr *hwmgr)
 	ret = hwmgr->hwmgr_func->backend_init(hwmgr);
 	if (ret)
 		goto err1;
+ /* make sure dc limits are valid */
+	if ((hwmgr->dyn_state.max_clock_voltage_on_dc.sclk == 0) ||
+			(hwmgr->dyn_state.max_clock_voltage_on_dc.mclk == 0))
+			hwmgr->dyn_state.max_clock_voltage_on_dc =
+					hwmgr->dyn_state.max_clock_voltage_on_ac;
 
 	ret = psm_init_power_state_table(hwmgr);
 	if (ret)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
index 7047e29755c3..01dc46dc9c8a 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
@@ -1544,14 +1544,14 @@ void atomctrl_get_voltage_range(struct pp_hwmgr *hwmgr, uint32_t *max_vddc,
 		switch (hwmgr->chip_id) {
 		case CHIP_TONGA:
 		case CHIP_FIJI:
-			*max_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_3 *)profile)->ulMaxVddc/4);
-			*min_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_3 *)profile)->ulMinVddc/4);
+			*max_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_3 *)profile)->ulMaxVddc) / 4;
+			*min_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_3 *)profile)->ulMinVddc) / 4;
 			return;
 		case CHIP_POLARIS11:
 		case CHIP_POLARIS10:
 		case CHIP_POLARIS12:
-			*max_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_6 *)profile)->ulMaxVddc/100);
-			*min_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_6 *)profile)->ulMinVddc/100);
+			*max_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_6 *)profile)->ulMaxVddc) / 100;
+			*min_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_6 *)profile)->ulMinVddc) / 100;
 			return;
 		default:
 			break;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c b/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
index 35bd9870ab10..4e1fd5393845 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
@@ -183,10 +183,10 @@ static int get_vddc_lookup_table(
 					ATOM_Tonga_Voltage_Lookup_Record,
 					entries, vddc_lookup_pp_tables, i);
 		record->us_calculated = 0;
-		record->us_vdd = atom_record->usVdd;
-		record->us_cac_low = atom_record->usCACLow;
-		record->us_cac_mid = atom_record->usCACMid;
-		record->us_cac_high = atom_record->usCACHigh;
+		record->us_vdd = le16_to_cpu(atom_record->usVdd);
+		record->us_cac_low = le16_to_cpu(atom_record->usCACLow);
+		record->us_cac_mid = le16_to_cpu(atom_record->usCACMid);
+		record->us_cac_high = le16_to_cpu(atom_record->usCACHigh);
 	}
 
 	*lookup_table = table;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
index d4bc83e81389..a63e00653324 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
@@ -993,7 +993,7 @@ static int smu10_get_clock_by_type_with_latency(struct pp_hwmgr *hwmgr,
 
 	clocks->num_levels = 0;
 	for (i = 0; i < pclk_vol_table->count; i++) {
-		clocks->data[i].clocks_in_khz = pclk_vol_table->entries[i].clk;
+		clocks->data[i].clocks_in_khz = pclk_vol_table->entries[i].clk * 10;
 		clocks->data[i].latency_in_us = latency_required ?
 						smu10_get_mem_latency(hwmgr,
 						pclk_vol_table->entries[i].clk) :
@@ -1044,7 +1044,7 @@ static int smu10_get_clock_by_type_with_voltage(struct pp_hwmgr *hwmgr,
 
 	clocks->num_levels = 0;
 	for (i = 0; i < pclk_vol_table->count; i++) {
-		clocks->data[i].clocks_in_khz = pclk_vol_table->entries[i].clk;
+		clocks->data[i].clocks_in_khz = pclk_vol_table->entries[i].clk  * 10;
 		clocks->data[i].voltage_in_mv = pclk_vol_table->entries[i].vol;
 		clocks->num_levels++;
 	}
@@ -1108,9 +1108,10 @@ static int smu10_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 }
 
 static int smu10_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+		void *clock_ranges)
 {
 	struct smu10_hwmgr *data = hwmgr->backend;
+	struct dm_pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_ranges;
 	Watermarks_t *table = &(data->water_marks_table);
 	int result = 0;
 
@@ -1126,7 +1127,7 @@ static int smu10_smus_notify_pwe(struct pp_hwmgr *hwmgr)
 	return smum_send_msg_to_smc(hwmgr, PPSMC_MSG_SetRccPfcPmeRestoreRegister);
 }
 
-static int smu10_set_mmhub_powergating_by_smu(struct pp_hwmgr *hwmgr)
+static int smu10_powergate_mmhub(struct pp_hwmgr *hwmgr)
 {
 	return smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PowerGateMmHub);
 }
@@ -1182,10 +1183,11 @@ static const struct pp_hwmgr_func smu10_hwmgr_funcs = {
 	.asic_setup = smu10_setup_asic_task,
 	.power_state_set = smu10_set_power_state_tasks,
 	.dynamic_state_management_disable = smu10_disable_dpm_tasks,
-	.set_mmhub_powergating_by_smu = smu10_set_mmhub_powergating_by_smu,
+	.powergate_mmhub = smu10_powergate_mmhub,
 	.smus_notify_pwe = smu10_smus_notify_pwe,
 	.gfx_off_control = smu10_gfx_off_control,
 	.display_clock_voltage_request = smu10_display_clock_voltage_request,
+	.powergate_gfx = smu10_gfx_off_control,
 };
 
 int smu10_init_function_pointers(struct pp_hwmgr *hwmgr)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
index 6d72a5600917..683b29a99366 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
@@ -39,13 +39,6 @@ static int smu7_enable_disable_vce_dpm(struct pp_hwmgr *hwmgr, bool enable)
 			PPSMC_MSG_VCEDPM_Disable);
 }
 
-static int smu7_enable_disable_samu_dpm(struct pp_hwmgr *hwmgr, bool enable)
-{
-	return smum_send_msg_to_smc(hwmgr, enable ?
-			PPSMC_MSG_SAMUDPM_Enable :
-			PPSMC_MSG_SAMUDPM_Disable);
-}
-
 static int smu7_update_uvd_dpm(struct pp_hwmgr *hwmgr, bool bgate)
 {
 	if (!bgate)
@@ -60,13 +53,6 @@ static int smu7_update_vce_dpm(struct pp_hwmgr *hwmgr, bool bgate)
 	return smu7_enable_disable_vce_dpm(hwmgr, !bgate);
 }
 
-static int smu7_update_samu_dpm(struct pp_hwmgr *hwmgr, bool bgate)
-{
-	if (!bgate)
-		smum_update_smc_table(hwmgr, SMU_SAMU_TABLE);
-	return smu7_enable_disable_samu_dpm(hwmgr, !bgate);
-}
-
 int smu7_powerdown_uvd(struct pp_hwmgr *hwmgr)
 {
 	if (phm_cf_want_uvd_power_gating(hwmgr))
@@ -107,35 +93,15 @@ static int smu7_powerup_vce(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-static int smu7_powerdown_samu(struct pp_hwmgr *hwmgr)
-{
-	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
-			PHM_PlatformCaps_SamuPowerGating))
-		return smum_send_msg_to_smc(hwmgr,
-				PPSMC_MSG_SAMPowerOFF);
-	return 0;
-}
-
-static int smu7_powerup_samu(struct pp_hwmgr *hwmgr)
-{
-	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
-			PHM_PlatformCaps_SamuPowerGating))
-		return smum_send_msg_to_smc(hwmgr,
-				PPSMC_MSG_SAMPowerON);
-	return 0;
-}
-
 int smu7_disable_clock_power_gating(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
 
 	data->uvd_power_gated = false;
 	data->vce_power_gated = false;
-	data->samu_power_gated = false;
 
 	smu7_powerup_uvd(hwmgr);
 	smu7_powerup_vce(hwmgr);
-	smu7_powerup_samu(hwmgr);
 
 	return 0;
 }
@@ -195,26 +161,6 @@ void smu7_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate)
 	}
 }
 
-int smu7_powergate_samu(struct pp_hwmgr *hwmgr, bool bgate)
-{
-	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
-
-	if (data->samu_power_gated == bgate)
-		return 0;
-
-	data->samu_power_gated = bgate;
-
-	if (bgate) {
-		smu7_update_samu_dpm(hwmgr, true);
-		smu7_powerdown_samu(hwmgr);
-	} else {
-		smu7_powerup_samu(hwmgr);
-		smu7_update_samu_dpm(hwmgr, false);
-	}
-
-	return 0;
-}
-
 int smu7_update_clock_gatings(struct pp_hwmgr *hwmgr,
 					const uint32_t *msg_id)
 {
@@ -470,7 +416,7 @@ int smu7_update_clock_gatings(struct pp_hwmgr *hwmgr,
  * Powerplay will only control the static per CU Power Gating.
  * Dynamic per CU Power Gating will be done in gfx.
  */
-int smu7_enable_per_cu_power_gating(struct pp_hwmgr *hwmgr, bool enable)
+int smu7_powergate_gfx(struct pp_hwmgr *hwmgr, bool enable)
 {
 	struct amdgpu_device *adev = hwmgr->adev;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.h b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.h
index 1ddce023218a..fc8f8a6acc72 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.h
@@ -29,11 +29,10 @@
 void smu7_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate);
 void smu7_powergate_uvd(struct pp_hwmgr *hwmgr, bool bgate);
 int smu7_powerdown_uvd(struct pp_hwmgr *hwmgr);
-int smu7_powergate_samu(struct pp_hwmgr *hwmgr, bool bgate);
 int smu7_powergate_acp(struct pp_hwmgr *hwmgr, bool bgate);
 int smu7_disable_clock_power_gating(struct pp_hwmgr *hwmgr);
 int smu7_update_clock_gatings(struct pp_hwmgr *hwmgr,
 					const uint32_t *msg_id);
-int smu7_enable_per_cu_power_gating(struct pp_hwmgr *hwmgr, bool enable);
+int smu7_powergate_gfx(struct pp_hwmgr *hwmgr, bool enable);
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index f8e866ceda02..052e60dfaf9f 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -48,6 +48,8 @@
 #include "processpptables.h"
 #include "pp_thermal.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 #define MC_CG_ARB_FREQ_F0           0x0a
 #define MC_CG_ARB_FREQ_F1           0x0b
 #define MC_CG_ARB_FREQ_F2           0x0c
@@ -885,6 +887,60 @@ static void smu7_setup_voltage_range_from_vbios(struct pp_hwmgr *hwmgr)
 	data->odn_dpm_table.max_vddc = max_vddc;
 }
 
+static void smu7_check_dpm_table_updated(struct pp_hwmgr *hwmgr)
+{
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct smu7_odn_dpm_table *odn_table = &(data->odn_dpm_table);
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+	uint32_t i;
+
+	struct phm_ppt_v1_clock_voltage_dependency_table *dep_table;
+	struct phm_ppt_v1_clock_voltage_dependency_table *odn_dep_table;
+
+	if (table_info == NULL)
+		return;
+
+	for (i = 0; i < data->dpm_table.sclk_table.count; i++) {
+		if (odn_table->odn_core_clock_dpm_levels.entries[i].clock !=
+					data->dpm_table.sclk_table.dpm_levels[i].value) {
+			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_SCLK;
+			break;
+		}
+	}
+
+	for (i = 0; i < data->dpm_table.mclk_table.count; i++) {
+		if (odn_table->odn_memory_clock_dpm_levels.entries[i].clock !=
+					data->dpm_table.mclk_table.dpm_levels[i].value) {
+			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_MCLK;
+			break;
+		}
+	}
+
+	dep_table = table_info->vdd_dep_on_mclk;
+	odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dependency_on_mclk);
+
+	for (i = 0; i < dep_table->count; i++) {
+		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
+			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_MCLK;
+			return;
+		}
+	}
+
+	dep_table = table_info->vdd_dep_on_sclk;
+	odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dependency_on_sclk);
+	for (i = 0; i < dep_table->count; i++) {
+		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
+			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_SCLK;
+			return;
+		}
+	}
+	if (data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_VDDC) {
+		data->need_update_smu7_dpm_table &= ~DPMTABLE_OD_UPDATE_VDDC;
+		data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_SCLK | DPMTABLE_OD_UPDATE_MCLK;
+	}
+}
+
 static int smu7_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
@@ -904,10 +960,13 @@ static int smu7_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 
 	/* initialize ODN table */
 	if (hwmgr->od_enabled) {
-		smu7_setup_voltage_range_from_vbios(hwmgr);
-		smu7_odn_initial_default_setting(hwmgr);
+		if (data->odn_dpm_table.max_vddc) {
+			smu7_check_dpm_table_updated(hwmgr);
+		} else {
+			smu7_setup_voltage_range_from_vbios(hwmgr);
+			smu7_odn_initial_default_setting(hwmgr);
+		}
 	}
-
 	return 0;
 }
 
@@ -1521,7 +1580,7 @@ static void smu7_init_dpm_defaults(struct pp_hwmgr *hwmgr)
 	data->current_profile_setting.sclk_up_hyst = 0;
 	data->current_profile_setting.sclk_down_hyst = 100;
 	data->current_profile_setting.sclk_activity = SMU7_SCLK_TARGETACTIVITY_DFLT;
-	data->current_profile_setting.bupdate_sclk = 1;
+	data->current_profile_setting.bupdate_mclk = 1;
 	data->current_profile_setting.mclk_up_hyst = 0;
 	data->current_profile_setting.mclk_down_hyst = 100;
 	data->current_profile_setting.mclk_activity = SMU7_MCLK_TARGETACTIVITY_DFLT;
@@ -2820,7 +2879,7 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 				struct pp_power_state *request_ps,
 			const struct pp_power_state *current_ps)
 {
-
+	struct amdgpu_device *adev = hwmgr->adev;
 	struct smu7_power_state *smu7_ps =
 				cast_phw_smu7_power_state(&request_ps->hardware);
 	uint32_t sclk;
@@ -2843,12 +2902,12 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 				 "VI should always have 2 performance levels",
 				);
 
-	max_limits = (PP_PowerSource_AC == hwmgr->power_source) ?
+	max_limits = adev->pm.ac_power ?
 			&(hwmgr->dyn_state.max_clock_voltage_on_ac) :
 			&(hwmgr->dyn_state.max_clock_voltage_on_dc);
 
 	/* Cap clock DPM tables at DC MAX if it is in DC. */
-	if (PP_PowerSource_DC == hwmgr->power_source) {
+	if (!adev->pm.ac_power) {
 		for (i = 0; i < smu7_ps->performance_level_count; i++) {
 			if (smu7_ps->performance_levels[i].memory_clock > max_limits->mclk)
 				smu7_ps->performance_levels[i].memory_clock = max_limits->mclk;
@@ -3126,7 +3185,7 @@ static int smu7_get_pp_table_entry_callback_func_v1(struct pp_hwmgr *hwmgr,
 	performance_level->pcie_gen = get_pcie_gen_support(data->pcie_gen_cap,
 			state_entry->ucPCIEGenLow);
 	performance_level->pcie_lane = get_pcie_lane_support(data->pcie_lane_cap,
-			state_entry->ucPCIELaneHigh);
+			state_entry->ucPCIELaneLow);
 
 	performance_level = &(smu7_power_state->performance_levels
 			[smu7_power_state->performance_level_count++]);
@@ -3717,8 +3776,9 @@ static int smu7_trim_single_dpm_states(struct pp_hwmgr *hwmgr,
 	uint32_t i;
 
 	for (i = 0; i < dpm_table->count; i++) {
-		if ((dpm_table->dpm_levels[i].value < low_limit)
-		|| (dpm_table->dpm_levels[i].value > high_limit))
+	/*skip the trim if od is enabled*/
+		if (!hwmgr->od_enabled && (dpm_table->dpm_levels[i].value < low_limit
+			|| dpm_table->dpm_levels[i].value > high_limit))
 			dpm_table->dpm_levels[i].enabled = false;
 		else
 			dpm_table->dpm_levels[i].enabled = true;
@@ -3762,10 +3822,8 @@ static int smu7_generate_dpm_level_enable_mask(
 	const struct smu7_power_state *smu7_ps =
 			cast_const_phw_smu7_power_state(states->pnew_state);
 
-	/*skip the trim if od is enabled*/
-	if (!hwmgr->od_enabled)
-		result = smu7_trim_dpm_states(hwmgr, smu7_ps);
 
+	result = smu7_trim_dpm_states(hwmgr, smu7_ps);
 	if (result)
 		return result;
 
@@ -4049,17 +4107,17 @@ static int smu7_register_irq_handlers(struct pp_hwmgr *hwmgr)
 
 	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			AMDGPU_IH_CLIENTID_LEGACY,
-			230,
+			VISLANDS30_IV_SRCID_CG_TSS_THERMAL_LOW_TO_HIGH,
 			source);
 	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			AMDGPU_IH_CLIENTID_LEGACY,
-			231,
+			VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW,
 			source);
 
 	/* Register CTF(GPIO_19) interrupt */
 	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			AMDGPU_IH_CLIENTID_LEGACY,
-			83,
+			VISLANDS30_IV_SRCID_GPIO_19,
 			source);
 
 	return 0;
@@ -4244,7 +4302,6 @@ static int smu7_init_power_gate_state(struct pp_hwmgr *hwmgr)
 
 	data->uvd_power_gated = false;
 	data->vce_power_gated = false;
-	data->samu_power_gated = false;
 
 	return 0;
 }
@@ -4555,12 +4612,12 @@ static int smu7_get_sclks(struct pp_hwmgr *hwmgr, struct amd_pp_clocks *clocks)
 			return -EINVAL;
 		dep_sclk_table = table_info->vdd_dep_on_sclk;
 		for (i = 0; i < dep_sclk_table->count; i++)
-			clocks->clock[i] = dep_sclk_table->entries[i].clk;
+			clocks->clock[i] = dep_sclk_table->entries[i].clk * 10;
 		clocks->count = dep_sclk_table->count;
 	} else if (hwmgr->pp_table_version == PP_TABLE_V0) {
 		sclk_table = hwmgr->dyn_state.vddc_dependency_on_sclk;
 		for (i = 0; i < sclk_table->count; i++)
-			clocks->clock[i] = sclk_table->entries[i].clk;
+			clocks->clock[i] = sclk_table->entries[i].clk * 10;
 		clocks->count = sclk_table->count;
 	}
 
@@ -4592,7 +4649,7 @@ static int smu7_get_mclks(struct pp_hwmgr *hwmgr, struct amd_pp_clocks *clocks)
 			return -EINVAL;
 		dep_mclk_table = table_info->vdd_dep_on_mclk;
 		for (i = 0; i < dep_mclk_table->count; i++) {
-			clocks->clock[i] = dep_mclk_table->entries[i].clk;
+			clocks->clock[i] = dep_mclk_table->entries[i].clk * 10;
 			clocks->latency[i] = smu7_get_mem_latency(hwmgr,
 						dep_mclk_table->entries[i].clk);
 		}
@@ -4600,7 +4657,7 @@ static int smu7_get_mclks(struct pp_hwmgr *hwmgr, struct amd_pp_clocks *clocks)
 	} else if (hwmgr->pp_table_version == PP_TABLE_V0) {
 		mclk_table = hwmgr->dyn_state.vddc_dependency_on_mclk;
 		for (i = 0; i < mclk_table->count; i++)
-			clocks->clock[i] = mclk_table->entries[i].clk;
+			clocks->clock[i] = mclk_table->entries[i].clk * 10;
 		clocks->count = mclk_table->count;
 	}
 	return 0;
@@ -4739,60 +4796,6 @@ static bool smu7_check_clk_voltage_valid(struct pp_hwmgr *hwmgr,
 	return true;
 }
 
-static void smu7_check_dpm_table_updated(struct pp_hwmgr *hwmgr)
-{
-	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
-	struct smu7_odn_dpm_table *odn_table = &(data->odn_dpm_table);
-	struct phm_ppt_v1_information *table_info =
-			(struct phm_ppt_v1_information *)(hwmgr->pptable);
-	uint32_t i;
-
-	struct phm_ppt_v1_clock_voltage_dependency_table *dep_table;
-	struct phm_ppt_v1_clock_voltage_dependency_table *odn_dep_table;
-
-	if (table_info == NULL)
-		return;
-
-	for (i=0; i<data->dpm_table.sclk_table.count; i++) {
-		if (odn_table->odn_core_clock_dpm_levels.entries[i].clock !=
-					data->dpm_table.sclk_table.dpm_levels[i].value) {
-			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_SCLK;
-			break;
-		}
-	}
-
-	for (i=0; i<data->dpm_table.mclk_table.count; i++) {
-		if (odn_table->odn_memory_clock_dpm_levels.entries[i].clock !=
-					data->dpm_table.mclk_table.dpm_levels[i].value) {
-			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_MCLK;
-			break;
-		}
-	}
-
-	dep_table = table_info->vdd_dep_on_mclk;
-	odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dependency_on_mclk);
-
-	for (i=0; i < dep_table->count; i++) {
-		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
-			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_MCLK;
-			return;
-		}
-	}
-
-	dep_table = table_info->vdd_dep_on_sclk;
-	odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dependency_on_sclk);
-	for (i=0; i < dep_table->count; i++) {
-		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
-			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_SCLK;
-			return;
-		}
-	}
-	if (data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_VDDC) {
-		data->need_update_smu7_dpm_table &= ~DPMTABLE_OD_UPDATE_VDDC;
-		data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_SCLK | DPMTABLE_OD_UPDATE_MCLK;
-	}
-}
-
 static int smu7_odn_edit_dpm_table(struct pp_hwmgr *hwmgr,
 					enum PP_OD_DPM_TABLE_COMMAND type,
 					long *input, uint32_t size)
@@ -5043,7 +5046,7 @@ static const struct pp_hwmgr_func smu7_hwmgr_funcs = {
 	.get_fan_control_mode = smu7_get_fan_control_mode,
 	.force_clock_level = smu7_force_clock_level,
 	.print_clock_levels = smu7_print_clock_levels,
-	.enable_per_cu_power_gating = smu7_enable_per_cu_power_gating,
+	.powergate_gfx = smu7_powergate_gfx,
 	.get_sclk_od = smu7_get_sclk_od,
 	.set_sclk_od = smu7_set_sclk_od,
 	.get_mclk_od = smu7_get_mclk_od,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h
index c91e75db6a8e..3784ce6e50ab 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h
@@ -310,7 +310,6 @@ struct smu7_hwmgr {
 	/* ---- Power Gating States ---- */
 	bool                           uvd_power_gated;
 	bool                           vce_power_gated;
-	bool                           samu_power_gated;
 	bool                           need_long_memory_training;
 
 	/* Application power optimization parameters */
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c
index c952845833d7..5e19f5977eb1 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c
@@ -403,6 +403,49 @@ static const struct gpu_pt_config_reg DIDTConfig_Polaris12[] = {
 	{   ixDIDT_SQ_CTRL1,                   DIDT_SQ_CTRL1__MAX_POWER_MASK,                      DIDT_SQ_CTRL1__MAX_POWER__SHIFT,                    0xffff,     GPU_CONFIGREG_DIDT_IND },
 
 	{   ixDIDT_SQ_CTRL_OCP,                DIDT_SQ_CTRL_OCP__UNUSED_0_MASK,                    DIDT_SQ_CTRL_OCP__UNUSED_0__SHIFT,                  0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL_OCP,                DIDT_SQ_CTRL_OCP__OCP_MAX_POWER_MASK,               DIDT_SQ_CTRL_OCP__OCP_MAX_POWER__SHIFT,             0xffff,     GPU_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__MAX_POWER_DELTA_MASK,                DIDT_SQ_CTRL2__MAX_POWER_DELTA__SHIFT,              0x3853,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__UNUSED_0_MASK,                       DIDT_SQ_CTRL2__UNUSED_0__SHIFT,                     0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK,       DIDT_SQ_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT,     0x005a,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__UNUSED_1_MASK,                       DIDT_SQ_CTRL2__UNUSED_1__SHIFT,                     0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK,       DIDT_SQ_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT,     0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__UNUSED_2_MASK,                       DIDT_SQ_CTRL2__UNUSED_2__SHIFT,                     0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK,    DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT,  0x0001,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK,       DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT,     0x0001,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK,       DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT,     0x0001,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK,   DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT, 0x0ebb,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__UNUSED_0_MASK,                  DIDT_SQ_STALL_CTRL__UNUSED_0__SHIFT,                0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK,       DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT,     0x0001,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK,       DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT,     0x3853,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK,       DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT,     0x3153,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__UNUSED_0_MASK,                 DIDT_SQ_TUNING_CTRL__UNUSED_0__SHIFT,               0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_CTRL_EN_MASK,                   DIDT_SQ_CTRL0__DIDT_CTRL_EN__SHIFT,                 0x0001,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__USE_REF_CLOCK_MASK,                  DIDT_SQ_CTRL0__USE_REF_CLOCK__SHIFT,                0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__PHASE_OFFSET_MASK,                   DIDT_SQ_CTRL0__PHASE_OFFSET__SHIFT,                 0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_CTRL_RST_MASK,                  DIDT_SQ_CTRL0__DIDT_CTRL_RST__SHIFT,                0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK,           DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT,         0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK,     DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT,   0x0010,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK,     DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT,   0x0010,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__UNUSED_0_MASK,                       DIDT_SQ_CTRL0__UNUSED_0__SHIFT,                     0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT0_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT0__SHIFT,                  0x000a,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT1_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT1__SHIFT,                  0x0010,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT2_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT2__SHIFT,                  0x0017,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT3_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT3__SHIFT,                  0x002f,     GPU_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT4_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT4__SHIFT,                  0x0046,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT5_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT5__SHIFT,                  0x005d,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT6_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT6__SHIFT,                  0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT7_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT7__SHIFT,                  0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_CTRL1,                   DIDT_TD_CTRL1__MIN_POWER_MASK,                      DIDT_TD_CTRL1__MIN_POWER__SHIFT,                    0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL1,                   DIDT_TD_CTRL1__MAX_POWER_MASK,                      DIDT_TD_CTRL1__MAX_POWER__SHIFT,                    0xffff,     GPU_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_CTRL_OCP,                DIDT_TD_CTRL_OCP__UNUSED_0_MASK,                    DIDT_TD_CTRL_OCP__UNUSED_0__SHIFT,                  0x0000,     GPU_CONFIGREG_DIDT_IND },
 	{   ixDIDT_TD_CTRL_OCP,                DIDT_TD_CTRL_OCP__OCP_MAX_POWER_MASK,               DIDT_TD_CTRL_OCP__OCP_MAX_POWER__SHIFT,             0x00ff,     GPU_CONFIGREG_DIDT_IND },
 
 	{   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__MAX_POWER_DELTA_MASK,                DIDT_TD_CTRL2__MAX_POWER_DELTA__SHIFT,              0x3fff,     GPU_CONFIGREG_DIDT_IND },
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c
index 50690c72b2ea..0adfc5392cd3 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c
@@ -244,6 +244,7 @@ static int smu8_initialize_dpm_defaults(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+/* convert form 8bit vid to real voltage in mV*4 */
 static uint32_t smu8_convert_8Bit_index_to_voltage(
 			struct pp_hwmgr *hwmgr, uint16_t voltage)
 {
@@ -1604,17 +1605,17 @@ static int smu8_get_clock_by_type(struct pp_hwmgr *hwmgr, enum amd_pp_clock_type
 	switch (type) {
 	case amd_pp_disp_clock:
 		for (i = 0; i < clocks->count; i++)
-			clocks->clock[i] = data->sys_info.display_clock[i];
+			clocks->clock[i] = data->sys_info.display_clock[i] * 10;
 		break;
 	case amd_pp_sys_clock:
 		table = hwmgr->dyn_state.vddc_dependency_on_sclk;
 		for (i = 0; i < clocks->count; i++)
-			clocks->clock[i] = table->entries[i].clk;
+			clocks->clock[i] = table->entries[i].clk * 10;
 		break;
 	case amd_pp_mem_clock:
 		clocks->count = SMU8_NUM_NBPMEMORYCLOCK;
 		for (i = 0; i < clocks->count; i++)
-			clocks->clock[i] = data->sys_info.nbp_memory_clock[clocks->count - 1 - i];
+			clocks->clock[i] = data->sys_info.nbp_memory_clock[clocks->count - 1 - i] * 10;
 		break;
 	default:
 		return -1;
@@ -1702,13 +1703,13 @@ static int smu8_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 	case AMDGPU_PP_SENSOR_VDDNB:
 		tmp = (cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixSMUSVI_NB_CURRENTVID) &
 			CURRENT_NB_VID_MASK) >> CURRENT_NB_VID__SHIFT;
-		vddnb = smu8_convert_8Bit_index_to_voltage(hwmgr, tmp);
+		vddnb = smu8_convert_8Bit_index_to_voltage(hwmgr, tmp) / 4;
 		*((uint32_t *)value) = vddnb;
 		return 0;
 	case AMDGPU_PP_SENSOR_VDDGFX:
 		tmp = (cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixSMUSVI_GFX_CURRENTVID) &
 			CURRENT_GFX_VID_MASK) >> CURRENT_GFX_VID__SHIFT;
-		vddgfx = smu8_convert_8Bit_index_to_voltage(hwmgr, (u16)tmp);
+		vddgfx = smu8_convert_8Bit_index_to_voltage(hwmgr, (u16)tmp) / 4;
 		*((uint32_t *)value) = vddgfx;
 		return 0;
 	case AMDGPU_PP_SENSOR_UVD_VCLK:
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
index 93a3d022ba47..2aab1b475945 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
@@ -25,6 +25,9 @@
 #include "ppatomctrl.h"
 #include "ppsmc.h"
 #include "atom.h"
+#include "ivsrcid/thm/irqsrcs_thm_9_0.h"
+#include "ivsrcid/smuio/irqsrcs_smuio_9_0.h"
+#include "ivsrcid/ivsrcid_vislands30.h"
 
 uint8_t convert_to_vid(uint16_t vddc)
 {
@@ -543,17 +546,17 @@ int phm_irq_process(struct amdgpu_device *adev,
 	uint32_t src_id = entry->src_id;
 
 	if (client_id == AMDGPU_IH_CLIENTID_LEGACY) {
-		if (src_id == 230)
+		if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_LOW_TO_HIGH)
 			pr_warn("GPU over temperature range detected on PCIe %d:%d.%d!\n",
 						PCI_BUS_NUM(adev->pdev->devfn),
 						PCI_SLOT(adev->pdev->devfn),
 						PCI_FUNC(adev->pdev->devfn));
-		else if (src_id == 231)
+		else if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW)
 			pr_warn("GPU under temperature range detected on PCIe %d:%d.%d!\n",
 					PCI_BUS_NUM(adev->pdev->devfn),
 					PCI_SLOT(adev->pdev->devfn),
 					PCI_FUNC(adev->pdev->devfn));
-		else if (src_id == 83)
+		else if (src_id == VISLANDS30_IV_SRCID_GPIO_19)
 			pr_warn("GPU Critical Temperature Fault detected on PCIe %d:%d.%d!\n",
 					PCI_BUS_NUM(adev->pdev->devfn),
 					PCI_SLOT(adev->pdev->devfn),
@@ -594,17 +597,17 @@ int smu9_register_irq_handlers(struct pp_hwmgr *hwmgr)
 
 	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			SOC15_IH_CLIENTID_THM,
-			0,
+			THM_9_0__SRCID__THM_DIG_THERM_L2H,
 			source);
 	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			SOC15_IH_CLIENTID_THM,
-			1,
+			THM_9_0__SRCID__THM_DIG_THERM_H2L,
 			source);
 
 	/* Register CTF(GPIO_19) interrupt */
 	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			SOC15_IH_CLIENTID_ROM_SMUIO,
-			83,
+			SMUIO_9_0__SRCID__SMUIO_GPIO19,
 			source);
 
 	return 0;
@@ -652,7 +655,7 @@ int smu_get_voltage_dependency_table_ppt_v1(
 }
 
 int smu_set_watermarks_for_clocks_ranges(void *wt_table,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+		struct dm_pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
 {
 	uint32_t i;
 	struct watermarks *table = wt_table;
@@ -660,49 +663,49 @@ int smu_set_watermarks_for_clocks_ranges(void *wt_table,
 	if (!table || !wm_with_clock_ranges)
 		return -EINVAL;
 
-	if (wm_with_clock_ranges->num_wm_sets_dmif > 4 || wm_with_clock_ranges->num_wm_sets_mcif > 4)
+	if (wm_with_clock_ranges->num_wm_dmif_sets > 4 || wm_with_clock_ranges->num_wm_mcif_sets > 4)
 		return -EINVAL;
 
-	for (i = 0; i < wm_with_clock_ranges->num_wm_sets_dmif; i++) {
+	for (i = 0; i < wm_with_clock_ranges->num_wm_dmif_sets; i++) {
 		table->WatermarkRow[1][i].MinClock =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_dmif[i].wm_min_dcefclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_min_dcfclk_clk_in_khz) /
+			1000);
 		table->WatermarkRow[1][i].MaxClock =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_dmif[i].wm_max_dcefclk_in_khz) /
+			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_max_dcfclk_clk_in_khz) /
 			100);
 		table->WatermarkRow[1][i].MinUclk =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_dmif[i].wm_min_memclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_min_mem_clk_in_khz) /
+			1000);
 		table->WatermarkRow[1][i].MaxUclk =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_dmif[i].wm_max_memclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_max_mem_clk_in_khz) /
+			1000);
 		table->WatermarkRow[1][i].WmSetting = (uint8_t)
-				wm_with_clock_ranges->wm_sets_dmif[i].wm_set_id;
+				wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_set_id;
 	}
 
-	for (i = 0; i < wm_with_clock_ranges->num_wm_sets_mcif; i++) {
+	for (i = 0; i < wm_with_clock_ranges->num_wm_mcif_sets; i++) {
 		table->WatermarkRow[0][i].MinClock =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_mcif[i].wm_min_socclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_min_socclk_clk_in_khz) /
+			1000);
 		table->WatermarkRow[0][i].MaxClock =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_mcif[i].wm_max_socclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_max_socclk_clk_in_khz) /
+			1000);
 		table->WatermarkRow[0][i].MinUclk =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_mcif[i].wm_min_memclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_min_mem_clk_in_khz) /
+			1000);
 		table->WatermarkRow[0][i].MaxUclk =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_mcif[i].wm_max_memclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_max_mem_clk_in_khz) /
+			1000);
 		table->WatermarkRow[0][i].WmSetting = (uint8_t)
-				wm_with_clock_ranges->wm_sets_mcif[i].wm_set_id;
+				wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_set_id;
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h
index 916cc01e7652..5454289d5226 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h
@@ -107,7 +107,7 @@ int smu_get_voltage_dependency_table_ppt_v1(
 		struct phm_ppt_v1_clock_voltage_dependency_table *dep_table);
 
 int smu_set_watermarks_for_clocks_ranges(void *wt_table,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges);
+		struct dm_pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges);
 
 #define PHM_FIELD_SHIFT(reg, field) reg##__##field##__SHIFT
 #define PHM_FIELD_MASK(reg, field) reg##__##field##_MASK
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index 05e680d55dbb..fb86c24394ff 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -55,12 +55,6 @@
 
 static const uint32_t channel_number[] = {1, 2, 0, 4, 0, 8, 0, 16, 2};
 
-#define MEM_FREQ_LOW_LATENCY        25000
-#define MEM_FREQ_HIGH_LATENCY       80000
-#define MEM_LATENCY_HIGH            245
-#define MEM_LATENCY_LOW             35
-#define MEM_LATENCY_ERR             0xFFFF
-
 #define mmDF_CS_AON0_DramBaseAddress0                                                                  0x0044
 #define mmDF_CS_AON0_DramBaseAddress0_BASE_IDX                                                         0
 
@@ -295,7 +289,15 @@ static int vega10_odn_initial_default_setting(struct pp_hwmgr *hwmgr)
 	struct phm_ppt_v1_voltage_lookup_table *vddc_lookup_table;
 	struct phm_ppt_v1_clock_voltage_dependency_table *dep_table[3];
 	struct phm_ppt_v1_clock_voltage_dependency_table *od_table[3];
+	struct pp_atomfwctrl_avfs_parameters avfs_params = {0};
 	uint32_t i;
+	int result;
+
+	result = pp_atomfwctrl_get_avfs_information(hwmgr, &avfs_params);
+	if (!result) {
+		data->odn_dpm_table.max_vddc = avfs_params.ulMaxVddc;
+		data->odn_dpm_table.min_vddc = avfs_params.ulMinVddc;
+	}
 
 	od_lookup_table = &odn_table->vddc_lookup_table;
 	vddc_lookup_table = table_info->vddc_lookup_table;
@@ -2078,9 +2080,6 @@ static int vega10_populate_avfs_parameters(struct pp_hwmgr *hwmgr)
 	if (data->smu_features[GNLD_AVFS].supported) {
 		result = pp_atomfwctrl_get_avfs_information(hwmgr, &avfs_params);
 		if (!result) {
-			data->odn_dpm_table.max_vddc = avfs_params.ulMaxVddc;
-			data->odn_dpm_table.min_vddc = avfs_params.ulMinVddc;
-
 			pp_table->MinVoltageVid = (uint8_t)
 					convert_to_vid((uint16_t)(avfs_params.ulMinVddc));
 			pp_table->MaxVoltageVid = (uint8_t)
@@ -2414,6 +2413,40 @@ static int vega10_populate_and_upload_avfs_fuse_override(struct pp_hwmgr *hwmgr)
 	return result;
 }
 
+static void vega10_check_dpm_table_updated(struct pp_hwmgr *hwmgr)
+{
+	struct vega10_hwmgr *data = hwmgr->backend;
+	struct vega10_odn_dpm_table *odn_table = &(data->odn_dpm_table);
+	struct phm_ppt_v2_information *table_info = hwmgr->pptable;
+	struct phm_ppt_v1_clock_voltage_dependency_table *dep_table;
+	struct phm_ppt_v1_clock_voltage_dependency_table *odn_dep_table;
+	uint32_t i;
+
+	dep_table = table_info->vdd_dep_on_mclk;
+	odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dep_on_mclk);
+
+	for (i = 0; i < dep_table->count; i++) {
+		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
+			data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_MCLK;
+			return;
+		}
+	}
+
+	dep_table = table_info->vdd_dep_on_sclk;
+	odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dep_on_sclk);
+	for (i = 0; i < dep_table->count; i++) {
+		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
+			data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_SCLK;
+			return;
+		}
+	}
+
+	if (data->need_update_dpm_table & DPMTABLE_OD_UPDATE_VDDC) {
+		data->need_update_dpm_table &= ~DPMTABLE_OD_UPDATE_VDDC;
+		data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_SCLK | DPMTABLE_OD_UPDATE_MCLK;
+	}
+}
+
 /**
 * Initializes the SMC table and uploads it
 *
@@ -2430,6 +2463,7 @@ static int vega10_init_smc_table(struct pp_hwmgr *hwmgr)
 	PPTable_t *pp_table = &(data->smc_state_table.pp_table);
 	struct pp_atomfwctrl_voltage_table voltage_table;
 	struct pp_atomfwctrl_bios_boot_up_values boot_up_values;
+	struct vega10_odn_dpm_table *odn_table = &(data->odn_dpm_table);
 
 	result = vega10_setup_default_dpm_tables(hwmgr);
 	PP_ASSERT_WITH_CODE(!result,
@@ -2437,8 +2471,14 @@ static int vega10_init_smc_table(struct pp_hwmgr *hwmgr)
 			return result);
 
 	/* initialize ODN table */
-	if (hwmgr->od_enabled)
-		vega10_odn_initial_default_setting(hwmgr);
+	if (hwmgr->od_enabled) {
+		if (odn_table->max_vddc) {
+			data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_SCLK | DPMTABLE_OD_UPDATE_MCLK;
+			vega10_check_dpm_table_updated(hwmgr);
+		} else {
+			vega10_odn_initial_default_setting(hwmgr);
+		}
+	}
 
 	pp_atomfwctrl_get_voltage_table_v4(hwmgr, VOLTAGE_TYPE_VDDC,
 			VOLTAGE_OBJ_SVID2,  &voltage_table);
@@ -2861,11 +2901,6 @@ static int vega10_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 
 	vega10_enable_disable_PCC_limit_feature(hwmgr, true);
 
-	if ((hwmgr->smu_version == 0x001c2c00) ||
-			(hwmgr->smu_version == 0x001c2d00))
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-				PPSMC_MSG_UpdatePkgPwrPidAlpha, 1);
-
 	smum_send_msg_to_smc_with_parameter(hwmgr,
 		PPSMC_MSG_ConfigureTelemetry, data->config_telemetry);
 
@@ -3061,6 +3096,7 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 				struct pp_power_state  *request_ps,
 			const struct pp_power_state *current_ps)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	struct vega10_power_state *vega10_ps =
 				cast_phw_vega10_power_state(&request_ps->hardware);
 	uint32_t sclk;
@@ -3086,12 +3122,12 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 	if (vega10_ps->performance_level_count != 2)
 		pr_info("VI should always have 2 performance levels");
 
-	max_limits = (PP_PowerSource_AC == hwmgr->power_source) ?
+	max_limits = adev->pm.ac_power ?
 			&(hwmgr->dyn_state.max_clock_voltage_on_ac) :
 			&(hwmgr->dyn_state.max_clock_voltage_on_dc);
 
 	/* Cap clock DPM tables at DC MAX if it is in DC. */
-	if (PP_PowerSource_DC == hwmgr->power_source) {
+	if (!adev->pm.ac_power) {
 		for (i = 0; i < vega10_ps->performance_level_count; i++) {
 			if (vega10_ps->performance_levels[i].mem_clock >
 				max_limits->mclk)
@@ -3181,7 +3217,7 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 		/* Find the lowest MCLK frequency that is within
 		 * the tolerable latency defined in DAL
 		 */
-		latency = 0;
+		latency = hwmgr->display_config->dce_tolerable_mclk_in_active_latency;
 		for (i = 0; i < data->mclk_latency_table.count; i++) {
 			if ((data->mclk_latency_table.entries[i].latency <= latency) &&
 				(data->mclk_latency_table.entries[i].frequency >=
@@ -3223,10 +3259,25 @@ static int vega10_populate_and_upload_sclk_mclk_dpm_levels(
 {
 	int result = 0;
 	struct vega10_hwmgr *data = hwmgr->backend;
+	struct vega10_dpm_table *dpm_table = &data->dpm_table;
+	struct vega10_odn_dpm_table *odn_table = &data->odn_dpm_table;
+	struct vega10_odn_clock_voltage_dependency_table *odn_clk_table = &odn_table->vdd_dep_on_sclk;
+	int count;
 
 	if (!data->need_update_dpm_table)
 		return 0;
 
+	if (hwmgr->od_enabled && data->need_update_dpm_table & DPMTABLE_OD_UPDATE_SCLK) {
+		for (count = 0; count < dpm_table->gfx_table.count; count++)
+			dpm_table->gfx_table.dpm_levels[count].value = odn_clk_table->entries[count].clk;
+	}
+
+	odn_clk_table = &odn_table->vdd_dep_on_mclk;
+	if (hwmgr->od_enabled && data->need_update_dpm_table & DPMTABLE_OD_UPDATE_MCLK) {
+		for (count = 0; count < dpm_table->mem_table.count; count++)
+			dpm_table->mem_table.dpm_levels[count].value = odn_clk_table->entries[count].clk;
+	}
+
 	if (data->need_update_dpm_table &
 			(DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK + DPMTABLE_UPDATE_SOCCLK)) {
 		result = vega10_populate_all_graphic_levels(hwmgr);
@@ -3674,7 +3725,7 @@ static void vega10_notify_smc_display_change(struct pp_hwmgr *hwmgr,
 {
 	smum_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetUclkFastSwitch,
-			has_disp ? 0 : 1);
+			has_disp ? 1 : 0);
 }
 
 int vega10_display_clock_voltage_request(struct pp_hwmgr *hwmgr,
@@ -3749,7 +3800,9 @@ static int vega10_notify_smc_display_config_after_ps_adjustment(
 	uint32_t i;
 	struct pp_display_clock_request clock_req;
 
-	if (hwmgr->display_config->num_display > 1)
+	if ((hwmgr->display_config->num_display > 1) &&
+	     !hwmgr->display_config->multi_monitor_in_sync &&
+	     !hwmgr->display_config->nb_pstate_switch_disable)
 		vega10_notify_smc_display_change(hwmgr, false);
 	else
 		vega10_notify_smc_display_change(hwmgr, true);
@@ -3765,7 +3818,7 @@ static int vega10_notify_smc_display_config_after_ps_adjustment(
 
 	if (i < dpm_table->count) {
 		clock_req.clock_type = amd_pp_dcef_clock;
-		clock_req.clock_freq_in_khz = dpm_table->dpm_levels[i].value;
+		clock_req.clock_freq_in_khz = dpm_table->dpm_levels[i].value * 10;
 		if (!vega10_display_clock_voltage_request(hwmgr, &clock_req)) {
 			smum_send_msg_to_smc_with_parameter(
 					hwmgr, PPSMC_MSG_SetMinDeepSleepDcefclk,
@@ -4022,28 +4075,17 @@ static void vega10_get_sclks(struct pp_hwmgr *hwmgr,
 			table_info->vdd_dep_on_sclk;
 	uint32_t i;
 
+	clocks->num_levels = 0;
 	for (i = 0; i < dep_table->count; i++) {
 		if (dep_table->entries[i].clk) {
 			clocks->data[clocks->num_levels].clocks_in_khz =
-					dep_table->entries[i].clk;
+					dep_table->entries[i].clk * 10;
 			clocks->num_levels++;
 		}
 	}
 
 }
 
-static uint32_t vega10_get_mem_latency(struct pp_hwmgr *hwmgr,
-		uint32_t clock)
-{
-	if (clock >= MEM_FREQ_LOW_LATENCY &&
-			clock < MEM_FREQ_HIGH_LATENCY)
-		return MEM_LATENCY_HIGH;
-	else if (clock >= MEM_FREQ_HIGH_LATENCY)
-		return MEM_LATENCY_LOW;
-	else
-		return MEM_LATENCY_ERR;
-}
-
 static void vega10_get_memclocks(struct pp_hwmgr *hwmgr,
 		struct pp_clock_levels_with_latency *clocks)
 {
@@ -4052,26 +4094,22 @@ static void vega10_get_memclocks(struct pp_hwmgr *hwmgr,
 	struct phm_ppt_v1_clock_voltage_dependency_table *dep_table =
 			table_info->vdd_dep_on_mclk;
 	struct vega10_hwmgr *data = hwmgr->backend;
+	uint32_t j = 0;
 	uint32_t i;
 
-	clocks->num_levels = 0;
-	data->mclk_latency_table.count = 0;
-
 	for (i = 0; i < dep_table->count; i++) {
 		if (dep_table->entries[i].clk) {
-			clocks->data[clocks->num_levels].clocks_in_khz =
-			data->mclk_latency_table.entries
-			[data->mclk_latency_table.count].frequency =
-					dep_table->entries[i].clk;
-			clocks->data[clocks->num_levels].latency_in_us =
-			data->mclk_latency_table.entries
-			[data->mclk_latency_table.count].latency =
-					vega10_get_mem_latency(hwmgr,
-						dep_table->entries[i].clk);
-			clocks->num_levels++;
-			data->mclk_latency_table.count++;
+
+			clocks->data[j].clocks_in_khz =
+						dep_table->entries[i].clk * 10;
+			data->mclk_latency_table.entries[j].frequency =
+							dep_table->entries[i].clk;
+			clocks->data[j].latency_in_us =
+				data->mclk_latency_table.entries[j].latency = 25;
+			j++;
 		}
 	}
+	clocks->num_levels = data->mclk_latency_table.count = j;
 }
 
 static void vega10_get_dcefclocks(struct pp_hwmgr *hwmgr,
@@ -4084,7 +4122,7 @@ static void vega10_get_dcefclocks(struct pp_hwmgr *hwmgr,
 	uint32_t i;
 
 	for (i = 0; i < dep_table->count; i++) {
-		clocks->data[i].clocks_in_khz = dep_table->entries[i].clk;
+		clocks->data[i].clocks_in_khz = dep_table->entries[i].clk * 10;
 		clocks->data[i].latency_in_us = 0;
 		clocks->num_levels++;
 	}
@@ -4100,7 +4138,7 @@ static void vega10_get_socclocks(struct pp_hwmgr *hwmgr,
 	uint32_t i;
 
 	for (i = 0; i < dep_table->count; i++) {
-		clocks->data[i].clocks_in_khz = dep_table->entries[i].clk;
+		clocks->data[i].clocks_in_khz = dep_table->entries[i].clk * 10;
 		clocks->data[i].latency_in_us = 0;
 		clocks->num_levels++;
 	}
@@ -4160,7 +4198,7 @@ static int vega10_get_clock_by_type_with_voltage(struct pp_hwmgr *hwmgr,
 	}
 
 	for (i = 0; i < dep_table->count; i++) {
-		clocks->data[i].clocks_in_khz = dep_table->entries[i].clk;
+		clocks->data[i].clocks_in_khz = dep_table->entries[i].clk  * 10;
 		clocks->data[i].voltage_in_mv = (uint32_t)(table_info->vddc_lookup_table->
 				entries[dep_table->entries[i].vddInd].us_vdd);
 		clocks->num_levels++;
@@ -4173,9 +4211,10 @@ static int vega10_get_clock_by_type_with_voltage(struct pp_hwmgr *hwmgr,
 }
 
 static int vega10_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+							void *clock_range)
 {
 	struct vega10_hwmgr *data = hwmgr->backend;
+	struct dm_pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_range;
 	Watermarks_t *table = &(data->smc_state_table.water_marks_table);
 	int result = 0;
 
@@ -4695,40 +4734,6 @@ static bool vega10_check_clk_voltage_valid(struct pp_hwmgr *hwmgr,
 	return true;
 }
 
-static void vega10_check_dpm_table_updated(struct pp_hwmgr *hwmgr)
-{
-	struct vega10_hwmgr *data = hwmgr->backend;
-	struct vega10_odn_dpm_table *odn_table = &(data->odn_dpm_table);
-	struct phm_ppt_v2_information *table_info = hwmgr->pptable;
-	struct phm_ppt_v1_clock_voltage_dependency_table *dep_table;
-	struct phm_ppt_v1_clock_voltage_dependency_table *odn_dep_table;
-	uint32_t i;
-
-	dep_table = table_info->vdd_dep_on_mclk;
-	odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dep_on_mclk);
-
-	for (i = 0; i < dep_table->count; i++) {
-		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
-			data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_MCLK;
-			return;
-		}
-	}
-
-	dep_table = table_info->vdd_dep_on_sclk;
-	odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dep_on_sclk);
-	for (i = 0; i < dep_table->count; i++) {
-		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
-			data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_SCLK;
-			return;
-		}
-	}
-
-	if (data->need_update_dpm_table & DPMTABLE_OD_UPDATE_VDDC) {
-		data->need_update_dpm_table &= ~DPMTABLE_OD_UPDATE_VDDC;
-		data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_SCLK | DPMTABLE_OD_UPDATE_MCLK;
-	}
-}
-
 static void vega10_odn_update_soc_table(struct pp_hwmgr *hwmgr,
 						enum PP_OD_DPM_TABLE_COMMAND type)
 {
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h
index aadd6cbc7e85..339820da9e6a 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h
@@ -370,7 +370,6 @@ struct vega10_hwmgr {
 	/* ---- Power Gating States ---- */
 	bool                           uvd_power_gated;
 	bool                           vce_power_gated;
-	bool                           samu_power_gated;
 	bool                           need_long_memory_training;
 
 	/* Internal settings to apply the application power optimization parameters */
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index c98e5de777cd..0789d64246ca 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -423,6 +423,11 @@ static int vega12_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 			hwmgr->thermal_controller.advanceFanControlParameters.usFanPWMMinLimit *
 			hwmgr->thermal_controller.fanInfo.ulMaxRPM / 100;
 
+	if (hwmgr->feature_mask & PP_GFXOFF_MASK)
+		data->gfxoff_controlled_by_driver = true;
+	else
+		data->gfxoff_controlled_by_driver = false;
+
 	return result;
 }
 
@@ -454,43 +459,36 @@ static int vega12_setup_asic_task(struct pp_hwmgr *hwmgr)
  */
 static void vega12_init_dpm_state(struct vega12_dpm_state *dpm_state)
 {
-	dpm_state->soft_min_level = 0xff;
-	dpm_state->soft_max_level = 0xff;
-	dpm_state->hard_min_level = 0xff;
-	dpm_state->hard_max_level = 0xff;
+	dpm_state->soft_min_level = 0x0;
+	dpm_state->soft_max_level = 0xffff;
+	dpm_state->hard_min_level = 0x0;
+	dpm_state->hard_max_level = 0xffff;
 }
 
-static int vega12_get_number_dpm_level(struct pp_hwmgr *hwmgr,
-		PPCLK_e clkID, uint32_t *num_dpm_level)
+static int vega12_get_number_of_dpm_level(struct pp_hwmgr *hwmgr,
+		PPCLK_e clk_id, uint32_t *num_of_levels)
 {
-	int result;
-	/*
-	 * SMU expects the Clock ID to be in the top 16 bits.
-	 * Lower 16 bits specify the level however 0xFF is a
-	 * special argument the returns the total number of levels
-	 */
-	PP_ASSERT_WITH_CODE(smum_send_msg_to_smc_with_parameter(hwmgr,
-		PPSMC_MSG_GetDpmFreqByIndex, (clkID << 16 | 0xFF)) == 0,
-		"[GetNumberDpmLevel] Failed to get DPM levels from SMU for CLKID!",
-		return -EINVAL);
-
-	result = vega12_read_arg_from_smc(hwmgr, num_dpm_level);
+	int ret = 0;
 
-	PP_ASSERT_WITH_CODE(*num_dpm_level < MAX_REGULAR_DPM_NUMBER,
-		"[GetNumberDPMLevel] Number of DPM levels is greater than limit",
-		return -EINVAL);
+	ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+			PPSMC_MSG_GetDpmFreqByIndex,
+			(clk_id << 16 | 0xFF));
+	PP_ASSERT_WITH_CODE(!ret,
+			"[GetNumOfDpmLevel] failed to get dpm levels!",
+			return ret);
 
-	PP_ASSERT_WITH_CODE(*num_dpm_level != 0,
-		"[GetNumberDPMLevel] Number of CLK Levels is zero!",
-		return -EINVAL);
+	*num_of_levels = smum_get_argument(hwmgr);
+	PP_ASSERT_WITH_CODE(*num_of_levels > 0,
+			"[GetNumOfDpmLevel] number of clk levels is invalid!",
+			return -EINVAL);
 
-	return result;
+	return ret;
 }
 
 static int vega12_get_dpm_frequency_by_index(struct pp_hwmgr *hwmgr,
 		PPCLK_e clkID, uint32_t index, uint32_t *clock)
 {
-	int result;
+	int result = 0;
 
 	/*
 	 *SMU expects the Clock ID to be in the top 16 bits.
@@ -501,15 +499,36 @@ static int vega12_get_dpm_frequency_by_index(struct pp_hwmgr *hwmgr,
 		"[GetDpmFrequencyByIndex] Failed to get dpm frequency from SMU!",
 		return -EINVAL);
 
-	result = vega12_read_arg_from_smc(hwmgr, clock);
-
-	PP_ASSERT_WITH_CODE(*clock != 0,
-		"[GetDPMFrequencyByIndex] Failed to get dpm frequency by index.!",
-		return -EINVAL);
+	*clock = smum_get_argument(hwmgr);
 
 	return result;
 }
 
+static int vega12_setup_single_dpm_table(struct pp_hwmgr *hwmgr,
+		struct vega12_single_dpm_table *dpm_table, PPCLK_e clk_id)
+{
+	int ret = 0;
+	uint32_t i, num_of_levels, clk;
+
+	ret = vega12_get_number_of_dpm_level(hwmgr, clk_id, &num_of_levels);
+	PP_ASSERT_WITH_CODE(!ret,
+			"[SetupSingleDpmTable] failed to get clk levels!",
+			return ret);
+
+	dpm_table->count = num_of_levels;
+
+	for (i = 0; i < num_of_levels; i++) {
+		ret = vega12_get_dpm_frequency_by_index(hwmgr, clk_id, i, &clk);
+		PP_ASSERT_WITH_CODE(!ret,
+			"[SetupSingleDpmTable] failed to get clk of specific level!",
+			return ret);
+		dpm_table->dpm_levels[i].value = clk;
+		dpm_table->dpm_levels[i].enabled = true;
+	}
+
+	return ret;
+}
+
 /*
  * This function is to initialize all DPM state tables
  * for SMU based on the dependency table.
@@ -520,224 +539,136 @@ static int vega12_get_dpm_frequency_by_index(struct pp_hwmgr *hwmgr,
  */
 static int vega12_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 {
-	uint32_t num_levels, i, clock;
 
 	struct vega12_hwmgr *data =
 			(struct vega12_hwmgr *)(hwmgr->backend);
-
 	struct vega12_single_dpm_table *dpm_table;
+	int ret = 0;
 
 	memset(&data->dpm_table, 0, sizeof(data->dpm_table));
 
-	/* Initialize Sclk DPM and SOC DPM table based on allow Sclk values */
+	/* socclk */
 	dpm_table = &(data->dpm_table.soc_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr, PPCLK_SOCCLK,
-		&num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for SOCCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_SOCCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for SOCCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	if (data->smu_features[GNLD_DPM_SOCCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_SOCCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get socclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.soc_clock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* gfxclk */
 	dpm_table = &(data->dpm_table.gfx_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr, PPCLK_GFXCLK,
-		&num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for GFXCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_GFXCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for GFXCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	if (data->smu_features[GNLD_DPM_GFXCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_GFXCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get gfxclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.gfx_clock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
-	/* Initialize Mclk DPM table based on allow Mclk values */
-	dpm_table = &(data->dpm_table.mem_table);
 
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr, PPCLK_UCLK,
-		&num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for UCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_UCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for UCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	/* memclk */
+	dpm_table = &(data->dpm_table.mem_table);
+	if (data->smu_features[GNLD_DPM_UCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_UCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get memclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.mem_clock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* eclk */
 	dpm_table = &(data->dpm_table.eclk_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr, PPCLK_ECLK,
-		&num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for ECLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-		PPCLK_ECLK, i, &clock) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for ECLK!",
-		return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	if (data->smu_features[GNLD_DPM_VCE].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_ECLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get eclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.eclock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* vclk */
 	dpm_table = &(data->dpm_table.vclk_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr, PPCLK_VCLK,
-		&num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for VCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_VCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for VCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	if (data->smu_features[GNLD_DPM_UVD].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_VCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get vclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.vclock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* dclk */
 	dpm_table = &(data->dpm_table.dclk_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr, PPCLK_DCLK,
-		&num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for DCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_DCLK, i, &clock) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for DCLK!",
-		return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	if (data->smu_features[GNLD_DPM_UVD].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_DCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get dclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.dclock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
-	/* Assume there is no headless Vega12 for now */
+	/* dcefclk */
 	dpm_table = &(data->dpm_table.dcef_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr,
-		PPCLK_DCEFCLK, &num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for DCEFCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_DCEFCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for DCEFCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	if (data->smu_features[GNLD_DPM_DCEFCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_DCEFCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get dcefclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.dcef_clock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* pixclk */
 	dpm_table = &(data->dpm_table.pixel_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr,
-		PPCLK_PIXCLK, &num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for PIXCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_PIXCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for PIXCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
-	}
-
+	if (data->smu_features[GNLD_DPM_DCEFCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_PIXCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get pixclk dpm levels!",
+				return ret);
+	} else
+		dpm_table->count = 0;
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* dispclk */
 	dpm_table = &(data->dpm_table.display_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr,
-		PPCLK_DISPCLK, &num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for DISPCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_DISPCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for DISPCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
-	}
-
+	if (data->smu_features[GNLD_DPM_DCEFCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_DISPCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get dispclk dpm levels!",
+				return ret);
+	} else
+		dpm_table->count = 0;
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* phyclk */
 	dpm_table = &(data->dpm_table.phy_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr,
-		PPCLK_PHYCLK, &num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for PHYCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_PHYCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for PHYCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
-	}
-
+	if (data->smu_features[GNLD_DPM_DCEFCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_PHYCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get phyclk dpm levels!",
+				return ret);
+	} else
+		dpm_table->count = 0;
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
 	/* save a copy of the default DPM table */
@@ -848,6 +779,21 @@ static int vega12_set_allowed_featuresmask(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+static void vega12_init_powergate_state(struct pp_hwmgr *hwmgr)
+{
+	struct vega12_hwmgr *data =
+			(struct vega12_hwmgr *)(hwmgr->backend);
+
+	data->uvd_power_gated = true;
+	data->vce_power_gated = true;
+
+	if (data->smu_features[GNLD_DPM_UVD].enabled)
+		data->uvd_power_gated = false;
+
+	if (data->smu_features[GNLD_DPM_VCE].enabled)
+		data->vce_power_gated = false;
+}
+
 static int vega12_enable_all_smu_features(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_hwmgr *data =
@@ -866,12 +812,11 @@ static int vega12_enable_all_smu_features(struct pp_hwmgr *hwmgr)
 			enabled = (features_enabled & data->smu_features[i].smu_feature_bitmap) ? true : false;
 			data->smu_features[i].enabled = enabled;
 			data->smu_features[i].supported = enabled;
-			PP_ASSERT(
-				!data->smu_features[i].allowed || enabled,
-				"[EnableAllSMUFeatures] Enabled feature is different from allowed, expected disabled!");
 		}
 	}
 
+	vega12_init_powergate_state(hwmgr);
+
 	return 0;
 }
 
@@ -927,6 +872,48 @@ static int vega12_power_control_set_level(struct pp_hwmgr *hwmgr)
 	return result;
 }
 
+static int vega12_get_all_clock_ranges_helper(struct pp_hwmgr *hwmgr,
+		PPCLK_e clkid, struct vega12_clock_range *clock)
+{
+	/* AC Max */
+	PP_ASSERT_WITH_CODE(
+		smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetMaxDpmFreq, (clkid << 16)) == 0,
+		"[GetClockRanges] Failed to get max ac clock from SMC!",
+		return -EINVAL);
+	clock->ACMax = smum_get_argument(hwmgr);
+
+	/* AC Min */
+	PP_ASSERT_WITH_CODE(
+		smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetMinDpmFreq, (clkid << 16)) == 0,
+		"[GetClockRanges] Failed to get min ac clock from SMC!",
+		return -EINVAL);
+	clock->ACMin = smum_get_argument(hwmgr);
+
+	/* DC Max */
+	PP_ASSERT_WITH_CODE(
+		smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetDcModeMaxDpmFreq, (clkid << 16)) == 0,
+		"[GetClockRanges] Failed to get max dc clock from SMC!",
+		return -EINVAL);
+	clock->DCMax = smum_get_argument(hwmgr);
+
+	return 0;
+}
+
+static int vega12_get_all_clock_ranges(struct pp_hwmgr *hwmgr)
+{
+	struct vega12_hwmgr *data =
+			(struct vega12_hwmgr *)(hwmgr->backend);
+	uint32_t i;
+
+	for (i = 0; i < PPCLK_COUNT; i++)
+		PP_ASSERT_WITH_CODE(!vega12_get_all_clock_ranges_helper(hwmgr,
+					i, &(data->clk_range[i])),
+				"Failed to get clk range from SMC!",
+				return -EINVAL);
+
+	return 0;
+}
+
 static int vega12_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 {
 	int tmp_result, result = 0;
@@ -954,6 +941,11 @@ static int vega12_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 			"Failed to power control set level!",
 			result = tmp_result);
 
+	result = vega12_get_all_clock_ranges(hwmgr);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to get all clock ranges!",
+			return result);
+
 	result = vega12_odn_initialize_default_settings(hwmgr);
 	PP_ASSERT_WITH_CODE(!result,
 			"Failed to power control set level!",
@@ -982,76 +974,172 @@ static uint32_t vega12_find_lowest_dpm_level(
 			break;
 	}
 
+	if (i >= table->count) {
+		i = 0;
+		table->dpm_levels[i].enabled = true;
+	}
+
 	return i;
 }
 
 static uint32_t vega12_find_highest_dpm_level(
 		struct vega12_single_dpm_table *table)
 {
-	uint32_t i = 0;
+	int32_t i = 0;
+	PP_ASSERT_WITH_CODE(table->count <= MAX_REGULAR_DPM_NUMBER,
+			"[FindHighestDPMLevel] DPM Table has too many entries!",
+			return MAX_REGULAR_DPM_NUMBER - 1);
 
-	if (table->count <= MAX_REGULAR_DPM_NUMBER) {
-		for (i = table->count; i > 0; i--) {
-			if (table->dpm_levels[i - 1].enabled)
-				return i - 1;
-		}
-	} else {
-		pr_info("DPM Table Has Too Many Entries!");
-		return MAX_REGULAR_DPM_NUMBER - 1;
+	for (i = table->count - 1; i >= 0; i--) {
+		if (table->dpm_levels[i].enabled)
+			break;
 	}
 
-	return i;
+	if (i < 0) {
+		i = 0;
+		table->dpm_levels[i].enabled = true;
+	}
+
+	return (uint32_t)i;
 }
 
 static int vega12_upload_dpm_min_level(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_hwmgr *data = hwmgr->backend;
-	if (data->smc_state_table.gfx_boot_level !=
-			data->dpm_table.gfx_table.dpm_state.soft_min_level) {
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-			PPSMC_MSG_SetSoftMinByFreq,
-			PPCLK_GFXCLK<<16 | data->dpm_table.gfx_table.dpm_levels[data->smc_state_table.gfx_boot_level].value);
-		data->dpm_table.gfx_table.dpm_state.soft_min_level =
-				data->smc_state_table.gfx_boot_level;
+	uint32_t min_freq;
+	int ret = 0;
+
+	if (data->smu_features[GNLD_DPM_GFXCLK].enabled) {
+		min_freq = data->dpm_table.gfx_table.dpm_state.soft_min_level;
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMinByFreq,
+					(PPCLK_GFXCLK << 16) | (min_freq & 0xffff))),
+					"Failed to set soft min gfxclk !",
+					return ret);
 	}
 
-	if (data->smc_state_table.mem_boot_level !=
-			data->dpm_table.mem_table.dpm_state.soft_min_level) {
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-			PPSMC_MSG_SetSoftMinByFreq,
-			PPCLK_UCLK<<16 | data->dpm_table.mem_table.dpm_levels[data->smc_state_table.mem_boot_level].value);
-		data->dpm_table.mem_table.dpm_state.soft_min_level =
-				data->smc_state_table.mem_boot_level;
+	if (data->smu_features[GNLD_DPM_UCLK].enabled) {
+		min_freq = data->dpm_table.mem_table.dpm_state.soft_min_level;
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMinByFreq,
+					(PPCLK_UCLK << 16) | (min_freq & 0xffff))),
+					"Failed to set soft min memclk !",
+					return ret);
+
+		min_freq = data->dpm_table.mem_table.dpm_state.hard_min_level;
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetHardMinByFreq,
+					(PPCLK_UCLK << 16) | (min_freq & 0xffff))),
+					"Failed to set hard min memclk !",
+					return ret);
 	}
 
-	return 0;
+	if (data->smu_features[GNLD_DPM_UVD].enabled) {
+		min_freq = data->dpm_table.vclk_table.dpm_state.soft_min_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMinByFreq,
+					(PPCLK_VCLK << 16) | (min_freq & 0xffff))),
+					"Failed to set soft min vclk!",
+					return ret);
+
+		min_freq = data->dpm_table.dclk_table.dpm_state.soft_min_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMinByFreq,
+					(PPCLK_DCLK << 16) | (min_freq & 0xffff))),
+					"Failed to set soft min dclk!",
+					return ret);
+	}
+
+	if (data->smu_features[GNLD_DPM_VCE].enabled) {
+		min_freq = data->dpm_table.eclk_table.dpm_state.soft_min_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMinByFreq,
+					(PPCLK_ECLK << 16) | (min_freq & 0xffff))),
+					"Failed to set soft min eclk!",
+					return ret);
+	}
+
+	if (data->smu_features[GNLD_DPM_SOCCLK].enabled) {
+		min_freq = data->dpm_table.soc_table.dpm_state.soft_min_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMinByFreq,
+					(PPCLK_SOCCLK << 16) | (min_freq & 0xffff))),
+					"Failed to set soft min socclk!",
+					return ret);
+	}
+
+	return ret;
 
 }
 
 static int vega12_upload_dpm_max_level(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_hwmgr *data = hwmgr->backend;
-	if (data->smc_state_table.gfx_max_level !=
-		data->dpm_table.gfx_table.dpm_state.soft_max_level) {
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-			PPSMC_MSG_SetSoftMaxByFreq,
-			/* plus the vale by 1 to align the resolution */
-			PPCLK_GFXCLK<<16 | (data->dpm_table.gfx_table.dpm_levels[data->smc_state_table.gfx_max_level].value + 1));
-		data->dpm_table.gfx_table.dpm_state.soft_max_level =
-				data->smc_state_table.gfx_max_level;
+	uint32_t max_freq;
+	int ret = 0;
+
+	if (data->smu_features[GNLD_DPM_GFXCLK].enabled) {
+		max_freq = data->dpm_table.gfx_table.dpm_state.soft_max_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMaxByFreq,
+					(PPCLK_GFXCLK << 16) | (max_freq & 0xffff))),
+					"Failed to set soft max gfxclk!",
+					return ret);
 	}
 
-	if (data->smc_state_table.mem_max_level !=
-		data->dpm_table.mem_table.dpm_state.soft_max_level) {
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-			PPSMC_MSG_SetSoftMaxByFreq,
-			/* plus the vale by 1 to align the resolution */
-			PPCLK_UCLK<<16 | (data->dpm_table.mem_table.dpm_levels[data->smc_state_table.mem_max_level].value + 1));
-		data->dpm_table.mem_table.dpm_state.soft_max_level =
-				data->smc_state_table.mem_max_level;
+	if (data->smu_features[GNLD_DPM_UCLK].enabled) {
+		max_freq = data->dpm_table.mem_table.dpm_state.soft_max_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMaxByFreq,
+					(PPCLK_UCLK << 16) | (max_freq & 0xffff))),
+					"Failed to set soft max memclk!",
+					return ret);
 	}
 
-	return 0;
+	if (data->smu_features[GNLD_DPM_UVD].enabled) {
+		max_freq = data->dpm_table.vclk_table.dpm_state.soft_max_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMaxByFreq,
+					(PPCLK_VCLK << 16) | (max_freq & 0xffff))),
+					"Failed to set soft max vclk!",
+					return ret);
+
+		max_freq = data->dpm_table.dclk_table.dpm_state.soft_max_level;
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMaxByFreq,
+					(PPCLK_DCLK << 16) | (max_freq & 0xffff))),
+					"Failed to set soft max dclk!",
+					return ret);
+	}
+
+	if (data->smu_features[GNLD_DPM_VCE].enabled) {
+		max_freq = data->dpm_table.eclk_table.dpm_state.soft_max_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMaxByFreq,
+					(PPCLK_ECLK << 16) | (max_freq & 0xffff))),
+					"Failed to set soft max eclk!",
+					return ret);
+	}
+
+	if (data->smu_features[GNLD_DPM_SOCCLK].enabled) {
+		max_freq = data->dpm_table.soc_table.dpm_state.soft_max_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMaxByFreq,
+					(PPCLK_SOCCLK << 16) | (max_freq & 0xffff))),
+					"Failed to set soft max socclk!",
+					return ret);
+	}
+
+	return ret;
 }
 
 int vega12_enable_disable_vce_dpm(struct pp_hwmgr *hwmgr, bool enable)
@@ -1127,7 +1215,7 @@ static int vega12_get_gpu_power(struct pp_hwmgr *hwmgr, uint32_t *query)
 			"Failed to get current package power!",
 			return -EINVAL);
 
-	vega12_read_arg_from_smc(hwmgr, &value);
+	value = smum_get_argument(hwmgr);
 	/* power value is an integer */
 	*query = value << 8;
 #endif
@@ -1140,14 +1228,11 @@ static int vega12_get_current_gfx_clk_freq(struct pp_hwmgr *hwmgr, uint32_t *gfx
 
 	*gfx_freq = 0;
 
-	PP_ASSERT_WITH_CODE(
-			smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetDpmClockFreq, (PPCLK_GFXCLK << 16)) == 0,
+	PP_ASSERT_WITH_CODE(smum_send_msg_to_smc_with_parameter(hwmgr,
+			PPSMC_MSG_GetDpmClockFreq, (PPCLK_GFXCLK << 16)) == 0,
 			"[GetCurrentGfxClkFreq] Attempt to get Current GFXCLK Frequency Failed!",
-			return -1);
-	PP_ASSERT_WITH_CODE(
-			vega12_read_arg_from_smc(hwmgr, &gfx_clk) == 0,
-			"[GetCurrentGfxClkFreq] Attempt to read arg from SMC Failed",
-			return -1);
+			return -EINVAL);
+	gfx_clk = smum_get_argument(hwmgr);
 
 	*gfx_freq = gfx_clk * 100;
 
@@ -1163,11 +1248,8 @@ static int vega12_get_current_mclk_freq(struct pp_hwmgr *hwmgr, uint32_t *mclk_f
 	PP_ASSERT_WITH_CODE(
 			smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetDpmClockFreq, (PPCLK_UCLK << 16)) == 0,
 			"[GetCurrentMClkFreq] Attempt to get Current MCLK Frequency Failed!",
-			return -1);
-	PP_ASSERT_WITH_CODE(
-			vega12_read_arg_from_smc(hwmgr, &mem_clk) == 0,
-			"[GetCurrentMClkFreq] Attempt to read arg from SMC Failed",
-			return -1);
+			return -EINVAL);
+	mem_clk = smum_get_argument(hwmgr);
 
 	*mclk_freq = mem_clk * 100;
 
@@ -1184,16 +1266,12 @@ static int vega12_get_current_activity_percent(
 #if 0
 	ret = smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetAverageGfxActivity, 0);
 	if (!ret) {
-		ret = vega12_read_arg_from_smc(hwmgr, &current_activity);
-		if (!ret) {
-			if (current_activity > 100) {
-				PP_ASSERT(false,
-					"[GetCurrentActivityPercent] Activity Percentage Exceeds 100!");
-				current_activity = 100;
-			}
-		} else
+		current_activity = smum_get_argument(hwmgr);
+		if (current_activity > 100) {
 			PP_ASSERT(false,
-				"[GetCurrentActivityPercent] Attempt To Read Average Graphics Activity from SMU Failed!");
+				  "[GetCurrentActivityPercent] Activity Percentage Exceeds 100!");
+			current_activity = 100;
+		}
 	} else
 		PP_ASSERT(false,
 			"[GetCurrentActivityPercent] Attempt To Send Get Average Graphics Activity to SMU Failed!");
@@ -1256,7 +1334,7 @@ static int vega12_notify_smc_display_change(struct pp_hwmgr *hwmgr,
 	if (data->smu_features[GNLD_DPM_UCLK].enabled)
 		return smum_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetUclkFastSwitch,
-			has_disp ? 0 : 1);
+			has_disp ? 1 : 0);
 
 	return 0;
 }
@@ -1274,7 +1352,6 @@ int vega12_display_clock_voltage_request(struct pp_hwmgr *hwmgr,
 	if (data->smu_features[GNLD_DPM_DCEFCLK].enabled) {
 		switch (clk_type) {
 		case amd_pp_dcef_clock:
-			clk_freq = clock_req->clock_freq_in_khz / 100;
 			clk_select = PPCLK_DCEFCLK;
 			break;
 		case amd_pp_disp_clock:
@@ -1310,9 +1387,10 @@ static int vega12_notify_smc_display_config_after_ps_adjustment(
 			(struct vega12_hwmgr *)(hwmgr->backend);
 	struct PP_Clocks min_clocks = {0};
 	struct pp_display_clock_request clock_req;
-	uint32_t clk_request;
 
-	if (hwmgr->display_config->num_display > 1)
+	if ((hwmgr->display_config->num_display > 1) &&
+	     !hwmgr->display_config->multi_monitor_in_sync &&
+	     !hwmgr->display_config->nb_pstate_switch_disable)
 		vega12_notify_smc_display_change(hwmgr, false);
 	else
 		vega12_notify_smc_display_change(hwmgr, true);
@@ -1323,7 +1401,7 @@ static int vega12_notify_smc_display_config_after_ps_adjustment(
 
 	if (data->smu_features[GNLD_DPM_DCEFCLK].supported) {
 		clock_req.clock_type = amd_pp_dcef_clock;
-		clock_req.clock_freq_in_khz = min_clocks.dcefClock;
+		clock_req.clock_freq_in_khz = min_clocks.dcefClock/10;
 		if (!vega12_display_clock_voltage_request(hwmgr, &clock_req)) {
 			if (data->smu_features[GNLD_DS_DCEFCLK].supported)
 				PP_ASSERT_WITH_CODE(
@@ -1337,15 +1415,6 @@ static int vega12_notify_smc_display_config_after_ps_adjustment(
 		}
 	}
 
-	if (data->smu_features[GNLD_DPM_UCLK].enabled) {
-		clk_request = (PPCLK_UCLK << 16) | (min_clocks.memoryClock) / 100;
-		PP_ASSERT_WITH_CODE(
-			smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinByFreq, clk_request) == 0,
-			"[PhwVega12_NotifySMCDisplayConfigAfterPowerStateAdjustment] Attempt to set UCLK HardMin Failed!",
-			return -1);
-		data->dpm_table.mem_table.dpm_state.hard_min_level = min_clocks.memoryClock;
-	}
-
 	return 0;
 }
 
@@ -1354,12 +1423,19 @@ static int vega12_force_dpm_highest(struct pp_hwmgr *hwmgr)
 	struct vega12_hwmgr *data =
 			(struct vega12_hwmgr *)(hwmgr->backend);
 
-	data->smc_state_table.gfx_boot_level =
-	data->smc_state_table.gfx_max_level =
-			vega12_find_highest_dpm_level(&(data->dpm_table.gfx_table));
-	data->smc_state_table.mem_boot_level =
-	data->smc_state_table.mem_max_level =
-			vega12_find_highest_dpm_level(&(data->dpm_table.mem_table));
+	uint32_t soft_level;
+
+	soft_level = vega12_find_highest_dpm_level(&(data->dpm_table.gfx_table));
+
+	data->dpm_table.gfx_table.dpm_state.soft_min_level =
+		data->dpm_table.gfx_table.dpm_state.soft_max_level =
+		data->dpm_table.gfx_table.dpm_levels[soft_level].value;
+
+	soft_level = vega12_find_highest_dpm_level(&(data->dpm_table.mem_table));
+
+	data->dpm_table.mem_table.dpm_state.soft_min_level =
+		data->dpm_table.mem_table.dpm_state.soft_max_level =
+		data->dpm_table.mem_table.dpm_levels[soft_level].value;
 
 	PP_ASSERT_WITH_CODE(!vega12_upload_dpm_min_level(hwmgr),
 			"Failed to upload boot level to highest!",
@@ -1376,13 +1452,19 @@ static int vega12_force_dpm_lowest(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_hwmgr *data =
 			(struct vega12_hwmgr *)(hwmgr->backend);
+	uint32_t soft_level;
+
+	soft_level = vega12_find_lowest_dpm_level(&(data->dpm_table.gfx_table));
+
+	data->dpm_table.gfx_table.dpm_state.soft_min_level =
+		data->dpm_table.gfx_table.dpm_state.soft_max_level =
+		data->dpm_table.gfx_table.dpm_levels[soft_level].value;
 
-	data->smc_state_table.gfx_boot_level =
-	data->smc_state_table.gfx_max_level =
-			vega12_find_lowest_dpm_level(&(data->dpm_table.gfx_table));
-	data->smc_state_table.mem_boot_level =
-	data->smc_state_table.mem_max_level =
-			vega12_find_lowest_dpm_level(&(data->dpm_table.mem_table));
+	soft_level = vega12_find_lowest_dpm_level(&(data->dpm_table.mem_table));
+
+	data->dpm_table.mem_table.dpm_state.soft_min_level =
+		data->dpm_table.mem_table.dpm_state.soft_max_level =
+		data->dpm_table.mem_table.dpm_levels[soft_level].value;
 
 	PP_ASSERT_WITH_CODE(!vega12_upload_dpm_min_level(hwmgr),
 			"Failed to upload boot level to highest!",
@@ -1398,17 +1480,6 @@ static int vega12_force_dpm_lowest(struct pp_hwmgr *hwmgr)
 
 static int vega12_unforce_dpm_levels(struct pp_hwmgr *hwmgr)
 {
-	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
-
-	data->smc_state_table.gfx_boot_level =
-			vega12_find_lowest_dpm_level(&(data->dpm_table.gfx_table));
-	data->smc_state_table.gfx_max_level =
-			vega12_find_highest_dpm_level(&(data->dpm_table.gfx_table));
-	data->smc_state_table.mem_boot_level =
-			vega12_find_lowest_dpm_level(&(data->dpm_table.mem_table));
-	data->smc_state_table.mem_max_level =
-			vega12_find_highest_dpm_level(&(data->dpm_table.mem_table));
-
 	PP_ASSERT_WITH_CODE(!vega12_upload_dpm_min_level(hwmgr),
 			"Failed to upload DPM Bootup Levels!",
 			return -1);
@@ -1416,22 +1487,28 @@ static int vega12_unforce_dpm_levels(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE(!vega12_upload_dpm_max_level(hwmgr),
 			"Failed to upload DPM Max Levels!",
 			return -1);
+
 	return 0;
 }
 
-#if 0
 static int vega12_get_profiling_clk_mask(struct pp_hwmgr *hwmgr, enum amd_dpm_forced_level level,
 				uint32_t *sclk_mask, uint32_t *mclk_mask, uint32_t *soc_mask)
 {
-	struct phm_ppt_v2_information *table_info =
-			(struct phm_ppt_v2_information *)(hwmgr->pptable);
+	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
+	struct vega12_single_dpm_table *gfx_dpm_table = &(data->dpm_table.gfx_table);
+	struct vega12_single_dpm_table *mem_dpm_table = &(data->dpm_table.mem_table);
+	struct vega12_single_dpm_table *soc_dpm_table = &(data->dpm_table.soc_table);
 
-	if (table_info->vdd_dep_on_sclk->count > VEGA12_UMD_PSTATE_GFXCLK_LEVEL &&
-		table_info->vdd_dep_on_socclk->count > VEGA12_UMD_PSTATE_SOCCLK_LEVEL &&
-		table_info->vdd_dep_on_mclk->count > VEGA12_UMD_PSTATE_MCLK_LEVEL) {
+	*sclk_mask = 0;
+	*mclk_mask = 0;
+	*soc_mask  = 0;
+
+	if (gfx_dpm_table->count > VEGA12_UMD_PSTATE_GFXCLK_LEVEL &&
+	    mem_dpm_table->count > VEGA12_UMD_PSTATE_MCLK_LEVEL &&
+	    soc_dpm_table->count > VEGA12_UMD_PSTATE_SOCCLK_LEVEL) {
 		*sclk_mask = VEGA12_UMD_PSTATE_GFXCLK_LEVEL;
-		*soc_mask = VEGA12_UMD_PSTATE_SOCCLK_LEVEL;
 		*mclk_mask = VEGA12_UMD_PSTATE_MCLK_LEVEL;
+		*soc_mask  = VEGA12_UMD_PSTATE_SOCCLK_LEVEL;
 	}
 
 	if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK) {
@@ -1439,13 +1516,13 @@ static int vega12_get_profiling_clk_mask(struct pp_hwmgr *hwmgr, enum amd_dpm_fo
 	} else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK) {
 		*mclk_mask = 0;
 	} else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
-		*sclk_mask = table_info->vdd_dep_on_sclk->count - 1;
-		*soc_mask = table_info->vdd_dep_on_socclk->count - 1;
-		*mclk_mask = table_info->vdd_dep_on_mclk->count - 1;
+		*sclk_mask = gfx_dpm_table->count - 1;
+		*mclk_mask = mem_dpm_table->count - 1;
+		*soc_mask  = soc_dpm_table->count - 1;
 	}
+
 	return 0;
 }
-#endif
 
 static void vega12_set_fan_control_mode(struct pp_hwmgr *hwmgr, uint32_t mode)
 {
@@ -1469,11 +1546,9 @@ static int vega12_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 				enum amd_dpm_forced_level level)
 {
 	int ret = 0;
-#if 0
 	uint32_t sclk_mask = 0;
 	uint32_t mclk_mask = 0;
 	uint32_t soc_mask = 0;
-#endif
 
 	switch (level) {
 	case AMD_DPM_FORCED_LEVEL_HIGH:
@@ -1489,27 +1564,18 @@ static int vega12_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
 	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
 	case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
-#if 0
 		ret = vega12_get_profiling_clk_mask(hwmgr, level, &sclk_mask, &mclk_mask, &soc_mask);
 		if (ret)
 			return ret;
-		vega12_force_clock_level(hwmgr, PP_SCLK, 1<<sclk_mask);
-		vega12_force_clock_level(hwmgr, PP_MCLK, 1<<mclk_mask);
-#endif
+		vega12_force_clock_level(hwmgr, PP_SCLK, 1 << sclk_mask);
+		vega12_force_clock_level(hwmgr, PP_MCLK, 1 << mclk_mask);
 		break;
 	case AMD_DPM_FORCED_LEVEL_MANUAL:
 	case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT:
 	default:
 		break;
 	}
-#if 0
-	if (!ret) {
-		if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK && hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)
-			vega12_set_fan_control_mode(hwmgr, AMD_FAN_CTRL_NONE);
-		else if (level != AMD_DPM_FORCED_LEVEL_PROFILE_PEAK && hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)
-			vega12_set_fan_control_mode(hwmgr, AMD_FAN_CTRL_AUTO);
-	}
-#endif
+
 	return ret;
 }
 
@@ -1543,24 +1609,14 @@ static int vega12_get_clock_ranges(struct pp_hwmgr *hwmgr,
 		PPCLK_e clock_select,
 		bool max)
 {
-	int result;
-	*clock = 0;
+	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
 
-	if (max) {
-		 PP_ASSERT_WITH_CODE(
-			smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetMaxDpmFreq, (clock_select << 16)) == 0,
-			"[GetClockRanges] Failed to get max clock from SMC!",
-			return -1);
-		result = vega12_read_arg_from_smc(hwmgr, clock);
-	} else {
-		PP_ASSERT_WITH_CODE(
-			smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetMinDpmFreq, (clock_select << 16)) == 0,
-			"[GetClockRanges] Failed to get min clock from SMC!",
-			return -1);
-		result = vega12_read_arg_from_smc(hwmgr, clock);
-	}
+	if (max)
+		*clock = data->clk_range[clock_select].ACMax;
+	else
+		*clock = data->clk_range[clock_select].ACMin;
 
-	return result;
+	return 0;
 }
 
 static int vega12_get_sclks(struct pp_hwmgr *hwmgr,
@@ -1575,12 +1631,12 @@ static int vega12_get_sclks(struct pp_hwmgr *hwmgr,
 		return -1;
 
 	dpm_table = &(data->dpm_table.gfx_table);
-	ucount = (dpm_table->count > VG12_PSUEDO_NUM_GFXCLK_DPM_LEVELS) ?
-		VG12_PSUEDO_NUM_GFXCLK_DPM_LEVELS : dpm_table->count;
+	ucount = (dpm_table->count > MAX_NUM_CLOCKS) ?
+		MAX_NUM_CLOCKS : dpm_table->count;
 
 	for (i = 0; i < ucount; i++) {
 		clocks->data[i].clocks_in_khz =
-			dpm_table->dpm_levels[i].value * 100;
+			dpm_table->dpm_levels[i].value * 1000;
 
 		clocks->data[i].latency_in_us = 0;
 	}
@@ -1607,13 +1663,12 @@ static int vega12_get_memclocks(struct pp_hwmgr *hwmgr,
 		return -1;
 
 	dpm_table = &(data->dpm_table.mem_table);
-	ucount = (dpm_table->count > VG12_PSUEDO_NUM_UCLK_DPM_LEVELS) ?
-		VG12_PSUEDO_NUM_UCLK_DPM_LEVELS : dpm_table->count;
+	ucount = (dpm_table->count > MAX_NUM_CLOCKS) ?
+		MAX_NUM_CLOCKS : dpm_table->count;
 
 	for (i = 0; i < ucount; i++) {
-		clocks->data[i].clocks_in_khz =
-			dpm_table->dpm_levels[i].value * 100;
-
+		clocks->data[i].clocks_in_khz = dpm_table->dpm_levels[i].value * 1000;
+		data->mclk_latency_table.entries[i].frequency = dpm_table->dpm_levels[i].value * 100;
 		clocks->data[i].latency_in_us =
 			data->mclk_latency_table.entries[i].latency =
 			vega12_get_mem_latency(hwmgr, dpm_table->dpm_levels[i].value);
@@ -1637,12 +1692,12 @@ static int vega12_get_dcefclocks(struct pp_hwmgr *hwmgr,
 
 
 	dpm_table = &(data->dpm_table.dcef_table);
-	ucount = (dpm_table->count > VG12_PSUEDO_NUM_DCEFCLK_DPM_LEVELS) ?
-		VG12_PSUEDO_NUM_DCEFCLK_DPM_LEVELS : dpm_table->count;
+	ucount = (dpm_table->count > MAX_NUM_CLOCKS) ?
+		MAX_NUM_CLOCKS : dpm_table->count;
 
 	for (i = 0; i < ucount; i++) {
 		clocks->data[i].clocks_in_khz =
-			dpm_table->dpm_levels[i].value * 100;
+			dpm_table->dpm_levels[i].value * 1000;
 
 		clocks->data[i].latency_in_us = 0;
 	}
@@ -1665,12 +1720,12 @@ static int vega12_get_socclocks(struct pp_hwmgr *hwmgr,
 
 
 	dpm_table = &(data->dpm_table.soc_table);
-	ucount = (dpm_table->count > VG12_PSUEDO_NUM_SOCCLK_DPM_LEVELS) ?
-		VG12_PSUEDO_NUM_SOCCLK_DPM_LEVELS : dpm_table->count;
+	ucount = (dpm_table->count > MAX_NUM_CLOCKS) ?
+		MAX_NUM_CLOCKS : dpm_table->count;
 
 	for (i = 0; i < ucount; i++) {
 		clocks->data[i].clocks_in_khz =
-			dpm_table->dpm_levels[i].value * 100;
+			dpm_table->dpm_levels[i].value * 1000;
 
 		clocks->data[i].latency_in_us = 0;
 	}
@@ -1717,99 +1772,69 @@ static int vega12_get_clock_by_type_with_voltage(struct pp_hwmgr *hwmgr,
 }
 
 static int vega12_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+							void *clock_ranges)
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
 	Watermarks_t *table = &(data->smc_state_table.water_marks_table);
-	int result = 0;
-	uint32_t i;
+	struct dm_pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_ranges;
 
 	if (!data->registry_data.disable_water_mark &&
 			data->smu_features[GNLD_DPM_DCEFCLK].supported &&
 			data->smu_features[GNLD_DPM_SOCCLK].supported) {
-		for (i = 0; i < wm_with_clock_ranges->num_wm_sets_dmif; i++) {
-			table->WatermarkRow[WM_DCEFCLK][i].MinClock =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_dmif[i].wm_min_dcefclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_DCEFCLK][i].MaxClock =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_dmif[i].wm_max_dcefclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_DCEFCLK][i].MinUclk =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_dmif[i].wm_min_memclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_DCEFCLK][i].MaxUclk =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_dmif[i].wm_max_memclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_DCEFCLK][i].WmSetting = (uint8_t)
-					wm_with_clock_ranges->wm_sets_dmif[i].wm_set_id;
-		}
-
-		for (i = 0; i < wm_with_clock_ranges->num_wm_sets_mcif; i++) {
-			table->WatermarkRow[WM_SOCCLK][i].MinClock =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_mcif[i].wm_min_socclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_SOCCLK][i].MaxClock =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_mcif[i].wm_max_socclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_SOCCLK][i].MinUclk =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_mcif[i].wm_min_memclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_SOCCLK][i].MaxUclk =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_mcif[i].wm_max_memclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_SOCCLK][i].WmSetting = (uint8_t)
-					wm_with_clock_ranges->wm_sets_mcif[i].wm_set_id;
-		}
+		smu_set_watermarks_for_clocks_ranges(table, wm_with_clock_ranges);
 		data->water_marks_bitmap |= WaterMarksExist;
 		data->water_marks_bitmap &= ~WaterMarksLoaded;
 	}
 
-	return result;
+	return 0;
 }
 
 static int vega12_force_clock_level(struct pp_hwmgr *hwmgr,
 		enum pp_clock_type type, uint32_t mask)
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
-
-	if (hwmgr->request_dpm_level & (AMD_DPM_FORCED_LEVEL_AUTO |
-				AMD_DPM_FORCED_LEVEL_LOW |
-				AMD_DPM_FORCED_LEVEL_HIGH))
-		return -EINVAL;
+	uint32_t soft_min_level, soft_max_level;
+	int ret = 0;
 
 	switch (type) {
 	case PP_SCLK:
-		data->smc_state_table.gfx_boot_level = mask ? (ffs(mask) - 1) : 0;
-		data->smc_state_table.gfx_max_level = mask ? (fls(mask) - 1) : 0;
+		soft_min_level = mask ? (ffs(mask) - 1) : 0;
+		soft_max_level = mask ? (fls(mask) - 1) : 0;
+
+		data->dpm_table.gfx_table.dpm_state.soft_min_level =
+			data->dpm_table.gfx_table.dpm_levels[soft_min_level].value;
+		data->dpm_table.gfx_table.dpm_state.soft_max_level =
+			data->dpm_table.gfx_table.dpm_levels[soft_max_level].value;
 
-		PP_ASSERT_WITH_CODE(!vega12_upload_dpm_min_level(hwmgr),
+		ret = vega12_upload_dpm_min_level(hwmgr);
+		PP_ASSERT_WITH_CODE(!ret,
 			"Failed to upload boot level to lowest!",
-			return -EINVAL);
+			return ret);
 
-		PP_ASSERT_WITH_CODE(!vega12_upload_dpm_max_level(hwmgr),
+		ret = vega12_upload_dpm_max_level(hwmgr);
+		PP_ASSERT_WITH_CODE(!ret,
 			"Failed to upload dpm max level to highest!",
-			return -EINVAL);
+			return ret);
 		break;
 
 	case PP_MCLK:
-		data->smc_state_table.mem_boot_level = mask ? (ffs(mask) - 1) : 0;
-		data->smc_state_table.mem_max_level = mask ? (fls(mask) - 1) : 0;
+		soft_min_level = mask ? (ffs(mask) - 1) : 0;
+		soft_max_level = mask ? (fls(mask) - 1) : 0;
 
-		PP_ASSERT_WITH_CODE(!vega12_upload_dpm_min_level(hwmgr),
+		data->dpm_table.mem_table.dpm_state.soft_min_level =
+			data->dpm_table.mem_table.dpm_levels[soft_min_level].value;
+		data->dpm_table.mem_table.dpm_state.soft_max_level =
+			data->dpm_table.mem_table.dpm_levels[soft_max_level].value;
+
+		ret = vega12_upload_dpm_min_level(hwmgr);
+		PP_ASSERT_WITH_CODE(!ret,
 			"Failed to upload boot level to lowest!",
-			return -EINVAL);
+			return ret);
 
-		PP_ASSERT_WITH_CODE(!vega12_upload_dpm_max_level(hwmgr),
+		ret = vega12_upload_dpm_max_level(hwmgr);
+		PP_ASSERT_WITH_CODE(!ret,
 			"Failed to upload dpm max level to highest!",
-			return -EINVAL);
+			return ret);
 
 		break;
 
@@ -1842,8 +1867,8 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 				return -1);
 		for (i = 0; i < clocks.num_levels; i++)
 			size += sprintf(buf + size, "%d: %uMhz %s\n",
-				i, clocks.data[i].clocks_in_khz / 100,
-				(clocks.data[i].clocks_in_khz == now) ? "*" : "");
+				i, clocks.data[i].clocks_in_khz / 1000,
+				(clocks.data[i].clocks_in_khz / 1000 == now / 100) ? "*" : "");
 		break;
 
 	case PP_MCLK:
@@ -1858,8 +1883,8 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 				return -1);
 		for (i = 0; i < clocks.num_levels; i++)
 			size += sprintf(buf + size, "%d: %uMhz %s\n",
-				i, clocks.data[i].clocks_in_khz / 100,
-				(clocks.data[i].clocks_in_khz == now) ? "*" : "");
+				i, clocks.data[i].clocks_in_khz / 1000,
+				(clocks.data[i].clocks_in_khz / 1000 == now / 100) ? "*" : "");
 		break;
 
 	case PP_PCIE:
@@ -1871,6 +1896,205 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 	return size;
 }
 
+static int vega12_apply_clocks_adjust_rules(struct pp_hwmgr *hwmgr)
+{
+	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
+	struct vega12_single_dpm_table *dpm_table;
+	bool vblank_too_short = false;
+	bool disable_mclk_switching;
+	uint32_t i, latency;
+
+	disable_mclk_switching = ((1 < hwmgr->display_config->num_display) &&
+			          !hwmgr->display_config->multi_monitor_in_sync) ||
+			          vblank_too_short;
+	latency = hwmgr->display_config->dce_tolerable_mclk_in_active_latency;
+
+	/* gfxclk */
+	dpm_table = &(data->dpm_table.gfx_table);
+	dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+	dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.hard_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	if (PP_CAP(PHM_PlatformCaps_UMDPState)) {
+		if (VEGA12_UMD_PSTATE_GFXCLK_LEVEL < dpm_table->count) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_GFXCLK_LEVEL].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_GFXCLK_LEVEL].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[0].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		}
+	}
+
+	/* memclk */
+	dpm_table = &(data->dpm_table.mem_table);
+	dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+	dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.hard_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	if (PP_CAP(PHM_PlatformCaps_UMDPState)) {
+		if (VEGA12_UMD_PSTATE_MCLK_LEVEL < dpm_table->count) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_MCLK_LEVEL].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_MCLK_LEVEL].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[0].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		}
+	}
+
+	/* honour DAL's UCLK Hardmin */
+	if (dpm_table->dpm_state.hard_min_level < (hwmgr->display_config->min_mem_set_clock / 100))
+		dpm_table->dpm_state.hard_min_level = hwmgr->display_config->min_mem_set_clock / 100;
+
+	/* Hardmin is dependent on displayconfig */
+	if (disable_mclk_switching) {
+		dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		for (i = 0; i < data->mclk_latency_table.count - 1; i++) {
+			if (data->mclk_latency_table.entries[i].latency <= latency) {
+				if (dpm_table->dpm_levels[i].value >= (hwmgr->display_config->min_mem_set_clock / 100)) {
+					dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[i].value;
+					break;
+				}
+			}
+		}
+	}
+
+	if (hwmgr->display_config->nb_pstate_switch_disable)
+		dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	/* vclk */
+	dpm_table = &(data->dpm_table.vclk_table);
+	dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+	dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.hard_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	if (PP_CAP(PHM_PlatformCaps_UMDPState)) {
+		if (VEGA12_UMD_PSTATE_UVDCLK_LEVEL < dpm_table->count) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_UVDCLK_LEVEL].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_UVDCLK_LEVEL].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		}
+	}
+
+	/* dclk */
+	dpm_table = &(data->dpm_table.dclk_table);
+	dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+	dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.hard_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	if (PP_CAP(PHM_PlatformCaps_UMDPState)) {
+		if (VEGA12_UMD_PSTATE_UVDCLK_LEVEL < dpm_table->count) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_UVDCLK_LEVEL].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_UVDCLK_LEVEL].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		}
+	}
+
+	/* socclk */
+	dpm_table = &(data->dpm_table.soc_table);
+	dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+	dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.hard_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	if (PP_CAP(PHM_PlatformCaps_UMDPState)) {
+		if (VEGA12_UMD_PSTATE_SOCCLK_LEVEL < dpm_table->count) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_SOCCLK_LEVEL].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_SOCCLK_LEVEL].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		}
+	}
+
+	/* eclk */
+	dpm_table = &(data->dpm_table.eclk_table);
+	dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+	dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.hard_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	if (PP_CAP(PHM_PlatformCaps_UMDPState)) {
+		if (VEGA12_UMD_PSTATE_VCEMCLK_LEVEL < dpm_table->count) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_VCEMCLK_LEVEL].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_VCEMCLK_LEVEL].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		}
+	}
+
+	return 0;
+}
+
+static int vega12_set_uclk_to_highest_dpm_level(struct pp_hwmgr *hwmgr,
+		struct vega12_single_dpm_table *dpm_table)
+{
+	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
+	int ret = 0;
+
+	if (data->smu_features[GNLD_DPM_UCLK].enabled) {
+		PP_ASSERT_WITH_CODE(dpm_table->count > 0,
+				"[SetUclkToHightestDpmLevel] Dpm table has no entry!",
+				return -EINVAL);
+		PP_ASSERT_WITH_CODE(dpm_table->count <= NUM_UCLK_DPM_LEVELS,
+				"[SetUclkToHightestDpmLevel] Dpm table has too many entries!",
+				return -EINVAL);
+
+		dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+				PPSMC_MSG_SetHardMinByFreq,
+				(PPCLK_UCLK << 16 ) | dpm_table->dpm_state.hard_min_level)),
+				"[SetUclkToHightestDpmLevel] Set hard min uclk failed!",
+				return ret);
+	}
+
+	return ret;
+}
+
+static int vega12_pre_display_configuration_changed_task(struct pp_hwmgr *hwmgr)
+{
+	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
+	int ret = 0;
+
+	smum_send_msg_to_smc_with_parameter(hwmgr,
+			PPSMC_MSG_NumOfDisplays, 0);
+
+	ret = vega12_set_uclk_to_highest_dpm_level(hwmgr,
+			&data->dpm_table.mem_table);
+
+	return ret;
+}
+
 static int vega12_display_configuration_changed_task(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
@@ -1915,6 +2139,9 @@ static void vega12_power_gate_vce(struct pp_hwmgr *hwmgr, bool bgate)
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
 
+	if (data->vce_power_gated == bgate)
+		return;
+
 	data->vce_power_gated = bgate;
 	vega12_enable_disable_vce_dpm(hwmgr, !bgate);
 }
@@ -1923,6 +2150,9 @@ static void vega12_power_gate_uvd(struct pp_hwmgr *hwmgr, bool bgate)
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
 
+	if (data->uvd_power_gated == bgate)
+		return;
+
 	data->uvd_power_gated = bgate;
 	vega12_enable_disable_uvd_dpm(hwmgr, !bgate);
 }
@@ -2090,6 +2320,38 @@ static int vega12_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
+static int vega12_enable_gfx_off(struct pp_hwmgr *hwmgr)
+{
+	struct vega12_hwmgr *data =
+			(struct vega12_hwmgr *)(hwmgr->backend);
+	int ret = 0;
+
+	if (data->gfxoff_controlled_by_driver)
+		ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_AllowGfxOff);
+
+	return ret;
+}
+
+static int vega12_disable_gfx_off(struct pp_hwmgr *hwmgr)
+{
+	struct vega12_hwmgr *data =
+			(struct vega12_hwmgr *)(hwmgr->backend);
+	int ret = 0;
+
+	if (data->gfxoff_controlled_by_driver)
+		ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_DisallowGfxOff);
+
+	return ret;
+}
+
+static int vega12_gfx_off_control(struct pp_hwmgr *hwmgr, bool enable)
+{
+	if (enable)
+		return vega12_enable_gfx_off(hwmgr);
+	else
+		return vega12_disable_gfx_off(hwmgr);
+}
+
 static const struct pp_hwmgr_func vega12_hwmgr_funcs = {
 	.backend_init = vega12_hwmgr_backend_init,
 	.backend_fini = vega12_hwmgr_backend_fini,
@@ -2117,6 +2379,10 @@ static const struct pp_hwmgr_func vega12_hwmgr_funcs = {
 	.display_clock_voltage_request = vega12_display_clock_voltage_request,
 	.force_clock_level = vega12_force_clock_level,
 	.print_clock_levels = vega12_print_clock_levels,
+	.apply_clocks_adjust_rules =
+		vega12_apply_clocks_adjust_rules,
+	.pre_display_config_changed =
+		vega12_pre_display_configuration_changed_task,
 	.display_config_changed = vega12_display_configuration_changed_task,
 	.powergate_uvd = vega12_power_gate_uvd,
 	.powergate_vce = vega12_power_gate_vce,
@@ -2135,6 +2401,7 @@ static const struct pp_hwmgr_func vega12_hwmgr_funcs = {
 	.get_thermal_temperature_range = vega12_get_thermal_temperature_range,
 	.register_irq_handlers = smu9_register_irq_handlers,
 	.start_thermal_controller = vega12_start_thermal_controller,
+	.powergate_gfx = vega12_gfx_off_control,
 };
 
 int vega12_hwmgr_init(struct pp_hwmgr *hwmgr)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
index 49b38df8c7f2..b3e424d28994 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
@@ -304,6 +304,12 @@ struct vega12_odn_fan_table {
 	bool		force_fan_pwm;
 };
 
+struct vega12_clock_range {
+	uint32_t	ACMax;
+	uint32_t	ACMin;
+	uint32_t	DCMax;
+};
+
 struct vega12_hwmgr {
 	struct vega12_dpm_table          dpm_table;
 	struct vega12_dpm_table          golden_dpm_table;
@@ -385,6 +391,11 @@ struct vega12_hwmgr {
 	uint32_t                       smu_version;
 	struct smu_features            smu_features[GNLD_FEATURES_MAX];
 	struct vega12_smc_state_table  smc_state_table;
+
+	struct vega12_clock_range      clk_range[PPCLK_COUNT];
+
+	/* ---- Gfxoff ---- */
+	bool                           gfxoff_controlled_by_driver;
 };
 
 #define VEGA12_DPM2_NEAR_TDP_DEC                      10
@@ -435,6 +446,8 @@ struct vega12_hwmgr {
 #define VEGA12_UMD_PSTATE_GFXCLK_LEVEL         0x3
 #define VEGA12_UMD_PSTATE_SOCCLK_LEVEL         0x3
 #define VEGA12_UMD_PSTATE_MCLK_LEVEL           0x2
+#define VEGA12_UMD_PSTATE_UVDCLK_LEVEL         0x3
+#define VEGA12_UMD_PSTATE_VCEMCLK_LEVEL        0x3
 
 int vega12_enable_disable_vce_dpm(struct pp_hwmgr *hwmgr, bool enable);
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
index 29914700ee82..cb3a5b1737c8 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
@@ -224,11 +224,7 @@ static int append_vbios_pptable(struct pp_hwmgr *hwmgr, PPTable_t *ppsmc_pptable
 	ppsmc_pptable->AcgGfxclkSpreadPercent = smc_dpm_table.acggfxclkspreadpercent;
 	ppsmc_pptable->AcgGfxclkSpreadFreq = smc_dpm_table.acggfxclkspreadfreq;
 
-	/* 0xFFFF will disable the ACG feature */
-	if (!(hwmgr->feature_mask & PP_ACG_MASK)) {
-		ppsmc_pptable->AcgThresholdFreqHigh = 0xFFFF;
-		ppsmc_pptable->AcgThresholdFreqLow = 0xFFFF;
-	}
+	ppsmc_pptable->Vr2_I2C_address = smc_dpm_table.Vr2_I2C_address;
 
 	ppsmc_pptable->Vr2_I2C_address = smc_dpm_table.Vr2_I2C_address;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c
index cfd9e6ccb790..904eb2c9155b 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c
@@ -34,11 +34,9 @@ static int vega12_get_current_rpm(struct pp_hwmgr *hwmgr, uint32_t *current_rpm)
 	PP_ASSERT_WITH_CODE(!smum_send_msg_to_smc(hwmgr,
 				PPSMC_MSG_GetCurrentRpm),
 			"Attempt to get current RPM from SMC Failed!",
-			return -1);
-	PP_ASSERT_WITH_CODE(!vega12_read_arg_from_smc(hwmgr,
-			current_rpm),
-			"Attempt to read current RPM from SMC Failed!",
-			return -1);
+			return -EINVAL);
+	*current_rpm = smum_get_argument(hwmgr);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h b/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
index a202247c9894..429c9c4322da 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
@@ -455,7 +455,7 @@ extern int phm_get_clock_by_type_with_voltage(struct pp_hwmgr *hwmgr,
 		enum amd_pp_clock_type type,
 		struct pp_clock_levels_with_voltage *clocks);
 extern int phm_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges);
+						void *clock_ranges);
 extern int phm_display_clock_voltage_request(struct pp_hwmgr *hwmgr,
 		struct pp_display_clock_request *clock);
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index b99fb8ac822c..d3d96260f440 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
@@ -26,7 +26,6 @@
 #include <linux/seq_file.h>
 #include "amd_powerplay.h"
 #include "hardwaremanager.h"
-#include "pp_power_source.h"
 #include "hwmgr_ppt.h"
 #include "ppatomctrl.h"
 #include "hwmgr_ppt.h"
@@ -195,7 +194,7 @@ struct pp_smumgr_func {
 	int (*request_smu_load_fw)(struct pp_hwmgr  *hwmgr);
 	int (*request_smu_load_specific_fw)(struct pp_hwmgr  *hwmgr,
 					    uint32_t firmware);
-	int (*get_argument)(struct pp_hwmgr  *hwmgr);
+	uint32_t (*get_argument)(struct pp_hwmgr  *hwmgr);
 	int (*send_msg_to_smc)(struct pp_hwmgr  *hwmgr, uint16_t msg);
 	int (*send_msg_to_smc_with_parameter)(struct pp_hwmgr  *hwmgr,
 					  uint16_t msg, uint32_t parameter);
@@ -294,8 +293,7 @@ struct pp_hwmgr_func {
 	int (*get_clock_by_type_with_voltage)(struct pp_hwmgr *hwmgr,
 			enum amd_pp_clock_type type,
 			struct pp_clock_levels_with_voltage *clocks);
-	int (*set_watermarks_for_clocks_ranges)(struct pp_hwmgr *hwmgr,
-			struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges);
+	int (*set_watermarks_for_clocks_ranges)(struct pp_hwmgr *hwmgr, void *clock_ranges);
 	int (*display_clock_voltage_request)(struct pp_hwmgr *hwmgr,
 			struct pp_display_clock_request *clock);
 	int (*get_max_high_clocks)(struct pp_hwmgr *hwmgr, struct amd_pp_simple_clock_info *clocks);
@@ -303,7 +301,7 @@ struct pp_hwmgr_func {
 	int (*power_off_asic)(struct pp_hwmgr *hwmgr);
 	int (*force_clock_level)(struct pp_hwmgr *hwmgr, enum pp_clock_type type, uint32_t mask);
 	int (*print_clock_levels)(struct pp_hwmgr *hwmgr, enum pp_clock_type type, char *buf);
-	int (*enable_per_cu_power_gating)(struct pp_hwmgr *hwmgr, bool enable);
+	int (*powergate_gfx)(struct pp_hwmgr *hwmgr, bool enable);
 	int (*get_sclk_od)(struct pp_hwmgr *hwmgr);
 	int (*set_sclk_od)(struct pp_hwmgr *hwmgr, uint32_t value);
 	int (*get_mclk_od)(struct pp_hwmgr *hwmgr);
@@ -328,7 +326,7 @@ struct pp_hwmgr_func {
 					enum PP_OD_DPM_TABLE_COMMAND type,
 					long *input, uint32_t size);
 	int (*set_power_limit)(struct pp_hwmgr *hwmgr, uint32_t n);
-	int (*set_mmhub_powergating_by_smu)(struct pp_hwmgr *hwmgr);
+	int (*powergate_mmhub)(struct pp_hwmgr *hwmgr);
 	int (*smus_notify_pwe)(struct pp_hwmgr *hwmgr);
 };
 
@@ -741,7 +739,6 @@ struct pp_hwmgr {
 	const struct pp_table_func *pptable_func;
 
 	struct pp_power_state    *ps;
-	enum pp_power_source  power_source;
 	uint32_t num_ps;
 	struct pp_thermal_controller_info thermal_controller;
 	bool fan_ctrl_is_in_default_mode;
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h b/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
index 6c22ed9249bf..82550a8a3a3f 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
@@ -29,7 +29,6 @@
 enum SMU_TABLE {
 	SMU_UVD_TABLE = 0,
 	SMU_VCE_TABLE,
-	SMU_SAMU_TABLE,
 	SMU_BIF_TABLE,
 };
 
@@ -47,7 +46,6 @@ enum SMU_MEMBER {
 	UcodeLoadStatus,
 	UvdBootLevel,
 	VceBootLevel,
-	SamuBootLevel,
 	LowSclkInterruptThreshold,
 	DRAM_LOG_ADDR_H,
 	DRAM_LOG_ADDR_L,
@@ -82,7 +80,7 @@ enum SMU10_TABLE_ID {
 	SMU10_CLOCKTABLE,
 };
 
-extern int smum_get_argument(struct pp_hwmgr *hwmgr);
+extern uint32_t smum_get_argument(struct pp_hwmgr *hwmgr);
 
 extern int smum_download_powerplay_table(struct pp_hwmgr *hwmgr, void **table);
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h b/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
index b08526fd1619..b6ffd08784e7 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
@@ -412,10 +412,10 @@ typedef struct {
   QuadraticInt_t    ReservedEquation2;
   QuadraticInt_t    ReservedEquation3;
 
-	uint16_t     MinVoltageUlvGfx;
-	uint16_t     MinVoltageUlvSoc;
+  uint16_t     MinVoltageUlvGfx;
+  uint16_t     MinVoltageUlvSoc;
 
-	uint32_t     Reserved[14];
+  uint32_t     Reserved[14];
 
 
 
@@ -483,9 +483,9 @@ typedef struct {
   uint8_t      padding8_4;
 
 
-	uint8_t      PllGfxclkSpreadEnabled;
-	uint8_t      PllGfxclkSpreadPercent;
-	uint16_t     PllGfxclkSpreadFreq;
+  uint8_t      PllGfxclkSpreadEnabled;
+  uint8_t      PllGfxclkSpreadPercent;
+  uint16_t     PllGfxclkSpreadFreq;
 
   uint8_t      UclkSpreadEnabled;
   uint8_t      UclkSpreadPercent;
@@ -495,9 +495,9 @@ typedef struct {
   uint8_t      SocclkSpreadPercent;
   uint16_t     SocclkSpreadFreq;
 
-	uint8_t      AcgGfxclkSpreadEnabled;
-	uint8_t      AcgGfxclkSpreadPercent;
-	uint16_t     AcgGfxclkSpreadFreq;
+  uint8_t      AcgGfxclkSpreadEnabled;
+  uint8_t      AcgGfxclkSpreadPercent;
+  uint16_t     AcgGfxclkSpreadFreq;
 
   uint8_t      Vr2_I2C_address;
   uint8_t      padding_vr2[3];
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/Makefile b/drivers/gpu/drm/amd/powerplay/smumgr/Makefile
index 0a200406a1ec..8d557accaef2 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/Makefile
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/Makefile
@@ -26,7 +26,7 @@
 SMU_MGR = smumgr.o smu8_smumgr.o tonga_smumgr.o fiji_smumgr.o \
 	  polaris10_smumgr.o iceland_smumgr.o \
 	  smu7_smumgr.o vega10_smumgr.o smu10_smumgr.o ci_smumgr.o \
-	  vega12_smumgr.o vegam_smumgr.o
+	  vega12_smumgr.o vegam_smumgr.o smu9_smumgr.o
 
 AMD_PP_SMUMGR = $(addprefix $(AMD_PP_PATH)/smumgr/,$(SMU_MGR))
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
index 2d4ec8ac3a08..fbe3ef4ee45c 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
@@ -1614,37 +1614,6 @@ static int ci_populate_smc_acp_level(struct pp_hwmgr *hwmgr,
 	return result;
 }
 
-static int ci_populate_smc_samu_level(struct pp_hwmgr *hwmgr,
-					SMU7_Discrete_DpmTable *table)
-{
-	int result = -EINVAL;
-	uint8_t count;
-	struct pp_atomctrl_clock_dividers_vi dividers;
-	struct phm_samu_clock_voltage_dependency_table *samu_table =
-				hwmgr->dyn_state.samu_clock_voltage_dependency_table;
-
-	table->SamuBootLevel = 0;
-	table->SamuLevelCount = (uint8_t)(samu_table->count);
-
-	for (count = 0; count < table->SamuLevelCount; count++) {
-		table->SamuLevel[count].Frequency = samu_table->entries[count].samclk;
-		table->SamuLevel[count].MinVoltage = samu_table->entries[count].v * VOLTAGE_SCALE;
-		table->SamuLevel[count].MinPhases = 1;
-
-		/* retrieve divider value for VBIOS */
-		result = atomctrl_get_dfs_pll_dividers_vi(hwmgr,
-				table->SamuLevel[count].Frequency, &dividers);
-		PP_ASSERT_WITH_CODE((0 == result),
-				"can not find divide id for samu clock", return result);
-
-		table->SamuLevel[count].Divider = (uint8_t)dividers.pll_post_divider;
-
-		CONVERT_FROM_HOST_TO_SMC_UL(table->SamuLevel[count].Frequency);
-		CONVERT_FROM_HOST_TO_SMC_US(table->SamuLevel[count].MinVoltage);
-	}
-	return result;
-}
-
 static int ci_populate_memory_timing_parameters(
 		struct pp_hwmgr *hwmgr,
 		uint32_t engine_clock,
@@ -2026,10 +1995,6 @@ static int ci_init_smc_table(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE(0 == result,
 		"Failed to initialize ACP Level!", return result);
 
-	result = ci_populate_smc_samu_level(hwmgr, table);
-	PP_ASSERT_WITH_CODE(0 == result,
-		"Failed to initialize SAMU Level!", return result);
-
 	/* Since only the initial state is completely set up at this point (the other states are just copies of the boot state) we only */
 	/* need to populate the  ARB settings for the initial state. */
 	result = ci_program_memory_timing_parameters(hwmgr);
@@ -2881,6 +2846,89 @@ static int ci_update_dpm_settings(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
+static int ci_update_uvd_smc_table(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+	struct smu7_hwmgr *data = hwmgr->backend;
+	struct ci_smumgr *smu_data = hwmgr->smu_backend;
+	struct phm_uvd_clock_voltage_dependency_table *uvd_table =
+			hwmgr->dyn_state.uvd_clock_voltage_dependency_table;
+	uint32_t profile_mode_mask = AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD |
+					AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK |
+					AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK |
+					AMD_DPM_FORCED_LEVEL_PROFILE_PEAK;
+	uint32_t max_vddc = adev->pm.ac_power ? hwmgr->dyn_state.max_clock_voltage_on_ac.vddc :
+						hwmgr->dyn_state.max_clock_voltage_on_dc.vddc;
+	int32_t i;
+
+	if (PP_CAP(PHM_PlatformCaps_UVDDPM) || uvd_table->count <= 0)
+		smu_data->smc_state_table.UvdBootLevel = 0;
+	else
+		smu_data->smc_state_table.UvdBootLevel = uvd_table->count - 1;
+
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, DPM_TABLE_475,
+				UvdBootLevel, smu_data->smc_state_table.UvdBootLevel);
+
+	data->dpm_level_enable_mask.uvd_dpm_enable_mask = 0;
+
+	for (i = uvd_table->count - 1; i >= 0; i--) {
+		if (uvd_table->entries[i].v <= max_vddc)
+			data->dpm_level_enable_mask.uvd_dpm_enable_mask |= 1 << i;
+		if (hwmgr->dpm_level & profile_mode_mask || !PP_CAP(PHM_PlatformCaps_UVDDPM))
+			break;
+	}
+	ci_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_UVDDPM_SetEnabledMask,
+				data->dpm_level_enable_mask.uvd_dpm_enable_mask);
+
+	return 0;
+}
+
+static int ci_update_vce_smc_table(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+	struct smu7_hwmgr *data = hwmgr->backend;
+	struct phm_vce_clock_voltage_dependency_table *vce_table =
+			hwmgr->dyn_state.vce_clock_voltage_dependency_table;
+	uint32_t profile_mode_mask = AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD |
+					AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK |
+					AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK |
+					AMD_DPM_FORCED_LEVEL_PROFILE_PEAK;
+	uint32_t max_vddc = adev->pm.ac_power ? hwmgr->dyn_state.max_clock_voltage_on_ac.vddc :
+						hwmgr->dyn_state.max_clock_voltage_on_dc.vddc;
+	int32_t i;
+
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, DPM_TABLE_475,
+				VceBootLevel, 0); /* temp hard code to level 0, vce can set min evclk*/
+
+	data->dpm_level_enable_mask.vce_dpm_enable_mask = 0;
+
+	for (i = vce_table->count - 1; i >= 0; i--) {
+		if (vce_table->entries[i].v <= max_vddc)
+			data->dpm_level_enable_mask.vce_dpm_enable_mask |= 1 << i;
+		if (hwmgr->dpm_level & profile_mode_mask || !PP_CAP(PHM_PlatformCaps_VCEDPM))
+			break;
+	}
+	ci_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_VCEDPM_SetEnabledMask,
+				data->dpm_level_enable_mask.vce_dpm_enable_mask);
+
+	return 0;
+}
+
+static int ci_update_smc_table(struct pp_hwmgr *hwmgr, uint32_t type)
+{
+	switch (type) {
+	case SMU_UVD_TABLE:
+		ci_update_uvd_smc_table(hwmgr);
+		break;
+	case SMU_VCE_TABLE:
+		ci_update_vce_smc_table(hwmgr);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
 const struct pp_smumgr_func ci_smu_funcs = {
 	.smu_init = ci_smu_init,
 	.smu_fini = ci_smu_fini,
@@ -2903,4 +2951,5 @@ const struct pp_smumgr_func ci_smu_funcs = {
 	.initialize_mc_reg_table = ci_initialize_mc_reg_table,
 	.is_dpm_running = ci_is_dpm_running,
 	.update_dpm_settings = ci_update_dpm_settings,
+	.update_smc_table = ci_update_smc_table,
 };
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
index 53df9405f43a..18048f8e2f13 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
@@ -1503,44 +1503,6 @@ static int fiji_populate_smc_acp_level(struct pp_hwmgr *hwmgr,
 	return result;
 }
 
-static int fiji_populate_smc_samu_level(struct pp_hwmgr *hwmgr,
-		SMU73_Discrete_DpmTable *table)
-{
-	int result = -EINVAL;
-	uint8_t count;
-	struct pp_atomctrl_clock_dividers_vi dividers;
-	struct phm_ppt_v1_information *table_info =
-			(struct phm_ppt_v1_information *)(hwmgr->pptable);
-	struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
-			table_info->mm_dep_table;
-
-	table->SamuBootLevel = 0;
-	table->SamuLevelCount = (uint8_t)(mm_table->count);
-
-	for (count = 0; count < table->SamuLevelCount; count++) {
-		/* not sure whether we need evclk or not */
-		table->SamuLevel[count].MinVoltage = 0;
-		table->SamuLevel[count].Frequency = mm_table->entries[count].samclock;
-		table->SamuLevel[count].MinVoltage |= (mm_table->entries[count].vddc *
-				VOLTAGE_SCALE) << VDDC_SHIFT;
-		table->SamuLevel[count].MinVoltage |= ((mm_table->entries[count].vddc -
-				VDDC_VDDCI_DELTA) * VOLTAGE_SCALE) << VDDCI_SHIFT;
-		table->SamuLevel[count].MinVoltage |= 1 << PHASES_SHIFT;
-
-		/* retrieve divider value for VBIOS */
-		result = atomctrl_get_dfs_pll_dividers_vi(hwmgr,
-				table->SamuLevel[count].Frequency, &dividers);
-		PP_ASSERT_WITH_CODE((0 == result),
-				"can not find divide id for samu clock", return result);
-
-		table->SamuLevel[count].Divider = (uint8_t)dividers.pll_post_divider;
-
-		CONVERT_FROM_HOST_TO_SMC_UL(table->SamuLevel[count].Frequency);
-		CONVERT_FROM_HOST_TO_SMC_UL(table->SamuLevel[count].MinVoltage);
-	}
-	return result;
-}
-
 static int fiji_populate_memory_timing_parameters(struct pp_hwmgr *hwmgr,
 		int32_t eng_clock, int32_t mem_clock,
 		struct SMU73_Discrete_MCArbDramTimingTableEntry *arb_regs)
@@ -2028,10 +1990,6 @@ static int fiji_init_smc_table(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE(0 == result,
 			"Failed to initialize ACP Level!", return result);
 
-	result = fiji_populate_smc_samu_level(hwmgr, table);
-	PP_ASSERT_WITH_CODE(0 == result,
-			"Failed to initialize SAMU Level!", return result);
-
 	/* Since only the initial state is completely set up at this point
 	 * (the other states are just copies of the boot state) we only
 	 * need to populate the  ARB settings for the initial state.
@@ -2378,8 +2336,6 @@ static uint32_t fiji_get_offsetof(uint32_t type, uint32_t member)
 			return offsetof(SMU73_Discrete_DpmTable, UvdBootLevel);
 		case VceBootLevel:
 			return offsetof(SMU73_Discrete_DpmTable, VceBootLevel);
-		case SamuBootLevel:
-			return offsetof(SMU73_Discrete_DpmTable, SamuBootLevel);
 		case LowSclkInterruptThreshold:
 			return offsetof(SMU73_Discrete_DpmTable, LowSclkInterruptThreshold);
 		}
@@ -2478,33 +2434,6 @@ static int fiji_update_vce_smc_table(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-static int fiji_update_samu_smc_table(struct pp_hwmgr *hwmgr)
-{
-	struct fiji_smumgr *smu_data = (struct fiji_smumgr *)(hwmgr->smu_backend);
-	uint32_t mm_boot_level_offset, mm_boot_level_value;
-
-
-	smu_data->smc_state_table.SamuBootLevel = 0;
-	mm_boot_level_offset = smu_data->smu7_data.dpm_table_start +
-				offsetof(SMU73_Discrete_DpmTable, SamuBootLevel);
-
-	mm_boot_level_offset /= 4;
-	mm_boot_level_offset *= 4;
-	mm_boot_level_value = cgs_read_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC, mm_boot_level_offset);
-	mm_boot_level_value &= 0xFFFFFF00;
-	mm_boot_level_value |= smu_data->smc_state_table.SamuBootLevel << 0;
-	cgs_write_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC, mm_boot_level_offset, mm_boot_level_value);
-
-	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
-			PHM_PlatformCaps_StablePState))
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-				PPSMC_MSG_SAMUDPM_SetEnabledMask,
-				(uint32_t)(1 << smu_data->smc_state_table.SamuBootLevel));
-	return 0;
-}
-
 static int fiji_update_smc_table(struct pp_hwmgr *hwmgr, uint32_t type)
 {
 	switch (type) {
@@ -2514,9 +2443,6 @@ static int fiji_update_smc_table(struct pp_hwmgr *hwmgr, uint32_t type)
 	case SMU_VCE_TABLE:
 		fiji_update_vce_smc_table(hwmgr);
 		break;
-	case SMU_SAMU_TABLE:
-		fiji_update_samu_smc_table(hwmgr);
-		break;
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c
index 415f691c3fa9..9299b93aa09a 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c
@@ -1578,12 +1578,6 @@ static int iceland_populate_smc_acp_level(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
-static int iceland_populate_smc_samu_level(struct pp_hwmgr *hwmgr,
-	SMU71_Discrete_DpmTable *table)
-{
-	return 0;
-}
-
 static int iceland_populate_memory_timing_parameters(
 		struct pp_hwmgr *hwmgr,
 		uint32_t engine_clock,
@@ -1992,10 +1986,6 @@ static int iceland_init_smc_table(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE(0 == result,
 		"Failed to initialize ACP Level!", return result;);
 
-	result = iceland_populate_smc_samu_level(hwmgr, table);
-	PP_ASSERT_WITH_CODE(0 == result,
-		"Failed to initialize SAMU Level!", return result;);
-
 	/* Since only the initial state is completely set up at this point (the other states are just copies of the boot state) we only */
 	/* need to populate the  ARB settings for the initial state. */
 	result = iceland_program_memory_timing_parameters(hwmgr);
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
index a8c6524f07e4..1276f168ff68 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
@@ -1204,7 +1204,6 @@ static int polaris10_populate_smc_acpi_level(struct pp_hwmgr *hwmgr,
 			(struct phm_ppt_v1_information *)(hwmgr->pptable);
 	SMIO_Pattern vol_level;
 	uint32_t mvdd;
-	uint16_t us_mvdd;
 
 	table->ACPILevel.Flags &= ~PPSMC_SWSTATE_FLAG_DC;
 
@@ -1255,16 +1254,11 @@ static int polaris10_populate_smc_acpi_level(struct pp_hwmgr *hwmgr,
 			"in Clock Dependency Table",
 			);
 
-	us_mvdd = 0;
-	if ((SMU7_VOLTAGE_CONTROL_NONE == data->mvdd_control) ||
-			(data->mclk_dpm_key_disabled))
-		us_mvdd = data->vbios_boot_state.mvdd_bootup_value;
-	else {
-		if (!polaris10_populate_mvdd_value(hwmgr,
+	if (!((SMU7_VOLTAGE_CONTROL_NONE == data->mvdd_control) ||
+			(data->mclk_dpm_key_disabled)))
+		polaris10_populate_mvdd_value(hwmgr,
 				data->dpm_table.mclk_table.dpm_levels[0].value,
-				&vol_level))
-			us_mvdd = vol_level.Voltage;
-	}
+				&vol_level);
 
 	if (0 == polaris10_populate_mvdd_value(hwmgr, 0, &vol_level))
 		table->MemoryACPILevel.MinMvdd = PP_HOST_TO_SMC_UL(vol_level.Voltage);
@@ -1337,55 +1331,6 @@ static int polaris10_populate_smc_vce_level(struct pp_hwmgr *hwmgr,
 	return result;
 }
 
-
-static int polaris10_populate_smc_samu_level(struct pp_hwmgr *hwmgr,
-		SMU74_Discrete_DpmTable *table)
-{
-	int result = -EINVAL;
-	uint8_t count;
-	struct pp_atomctrl_clock_dividers_vi dividers;
-	struct phm_ppt_v1_information *table_info =
-			(struct phm_ppt_v1_information *)(hwmgr->pptable);
-	struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
-			table_info->mm_dep_table;
-	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
-	uint32_t vddci;
-
-	table->SamuBootLevel = 0;
-	table->SamuLevelCount = (uint8_t)(mm_table->count);
-
-	for (count = 0; count < table->SamuLevelCount; count++) {
-		/* not sure whether we need evclk or not */
-		table->SamuLevel[count].MinVoltage = 0;
-		table->SamuLevel[count].Frequency = mm_table->entries[count].samclock;
-		table->SamuLevel[count].MinVoltage |= (mm_table->entries[count].vddc *
-				VOLTAGE_SCALE) << VDDC_SHIFT;
-
-		if (SMU7_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control)
-			vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table),
-						mm_table->entries[count].vddc - VDDC_VDDCI_DELTA);
-		else if (SMU7_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control)
-			vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA;
-		else
-			vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT;
-
-		table->SamuLevel[count].MinVoltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
-		table->SamuLevel[count].MinVoltage |= 1 << PHASES_SHIFT;
-
-		/* retrieve divider value for VBIOS */
-		result = atomctrl_get_dfs_pll_dividers_vi(hwmgr,
-				table->SamuLevel[count].Frequency, &dividers);
-		PP_ASSERT_WITH_CODE((0 == result),
-				"can not find divide id for samu clock", return result);
-
-		table->SamuLevel[count].Divider = (uint8_t)dividers.pll_post_divider;
-
-		CONVERT_FROM_HOST_TO_SMC_UL(table->SamuLevel[count].Frequency);
-		CONVERT_FROM_HOST_TO_SMC_UL(table->SamuLevel[count].MinVoltage);
-	}
-	return result;
-}
-
 static int polaris10_populate_memory_timing_parameters(struct pp_hwmgr *hwmgr,
 		int32_t eng_clock, int32_t mem_clock,
 		SMU74_Discrete_MCArbDramTimingTableEntry *arb_regs)
@@ -1566,7 +1511,7 @@ static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
 	uint32_t ro, efuse, volt_without_cks, volt_with_cks, value, max, min;
 	struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(hwmgr->smu_backend);
 
-	uint8_t i, stretch_amount, stretch_amount2, volt_offset = 0;
+	uint8_t i, stretch_amount, volt_offset = 0;
 	struct phm_ppt_v1_information *table_info =
 			(struct phm_ppt_v1_information *)(hwmgr->pptable);
 	struct phm_ppt_v1_clock_voltage_dependency_table *sclk_table =
@@ -1617,11 +1562,7 @@ static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
 
 	smu_data->smc_state_table.LdoRefSel = (table_info->cac_dtp_table->ucCKS_LDO_REFSEL != 0) ? table_info->cac_dtp_table->ucCKS_LDO_REFSEL : 6;
 	/* Populate CKS Lookup Table */
-	if (stretch_amount == 1 || stretch_amount == 2 || stretch_amount == 5)
-		stretch_amount2 = 0;
-	else if (stretch_amount == 3 || stretch_amount == 4)
-		stretch_amount2 = 1;
-	else {
+	if (stretch_amount == 0 || stretch_amount > 5) {
 		phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
 				PHM_PlatformCaps_ClockStretcher);
 		PP_ASSERT_WITH_CODE(false,
@@ -1865,10 +1806,6 @@ static int polaris10_init_smc_table(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE(0 == result,
 			"Failed to initialize VCE Level!", return result);
 
-	result = polaris10_populate_smc_samu_level(hwmgr, table);
-	PP_ASSERT_WITH_CODE(0 == result,
-			"Failed to initialize SAMU Level!", return result);
-
 	/* Since only the initial state is completely set up at this point
 	 * (the other states are just copies of the boot state) we only
 	 * need to populate the  ARB settings for the initial state.
@@ -2222,34 +2159,6 @@ static int polaris10_update_vce_smc_table(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-static int polaris10_update_samu_smc_table(struct pp_hwmgr *hwmgr)
-{
-	struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(hwmgr->smu_backend);
-	uint32_t mm_boot_level_offset, mm_boot_level_value;
-
-
-	smu_data->smc_state_table.SamuBootLevel = 0;
-	mm_boot_level_offset = smu_data->smu7_data.dpm_table_start +
-				offsetof(SMU74_Discrete_DpmTable, SamuBootLevel);
-
-	mm_boot_level_offset /= 4;
-	mm_boot_level_offset *= 4;
-	mm_boot_level_value = cgs_read_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC, mm_boot_level_offset);
-	mm_boot_level_value &= 0xFFFFFF00;
-	mm_boot_level_value |= smu_data->smc_state_table.SamuBootLevel << 0;
-	cgs_write_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC, mm_boot_level_offset, mm_boot_level_value);
-
-	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
-			PHM_PlatformCaps_StablePState))
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-				PPSMC_MSG_SAMUDPM_SetEnabledMask,
-				(uint32_t)(1 << smu_data->smc_state_table.SamuBootLevel));
-	return 0;
-}
-
-
 static int polaris10_update_bif_smc_table(struct pp_hwmgr *hwmgr)
 {
 	struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(hwmgr->smu_backend);
@@ -2276,9 +2185,6 @@ static int polaris10_update_smc_table(struct pp_hwmgr *hwmgr, uint32_t type)
 	case SMU_VCE_TABLE:
 		polaris10_update_vce_smc_table(hwmgr);
 		break;
-	case SMU_SAMU_TABLE:
-		polaris10_update_samu_smc_table(hwmgr);
-		break;
 	case SMU_BIF_TABLE:
 		polaris10_update_bif_smc_table(hwmgr);
 	default:
@@ -2357,8 +2263,6 @@ static uint32_t polaris10_get_offsetof(uint32_t type, uint32_t member)
 			return offsetof(SMU74_Discrete_DpmTable, UvdBootLevel);
 		case VceBootLevel:
 			return offsetof(SMU74_Discrete_DpmTable, VceBootLevel);
-		case SamuBootLevel:
-			return offsetof(SMU74_Discrete_DpmTable, SamuBootLevel);
 		case LowSclkInterruptThreshold:
 			return offsetof(SMU74_Discrete_DpmTable, LowSclkInterruptThreshold);
 		}
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
index 0a563f6fe9ea..bb07d43f3874 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
@@ -68,7 +68,7 @@ static int smu10_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
-static int smu10_read_arg_from_smc(struct pp_hwmgr *hwmgr)
+static uint32_t smu10_read_arg_from_smc(struct pp_hwmgr *hwmgr)
 {
 	struct amdgpu_device *adev = hwmgr->adev;
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
index 9f407c48d4f0..a029e47c2319 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
@@ -379,9 +379,7 @@ int smu7_request_smu_load_fw(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_smumgr *smu_data = (struct smu7_smumgr *)(hwmgr->smu_backend);
 	uint32_t fw_to_load;
-	int result = 0;
-	struct SMU_DRAMData_TOC *toc;
-	uint32_t num_entries = 0;
+	int r = 0;
 
 	if (!hwmgr->reload_fw) {
 		pr_info("skip reloading...\n");
@@ -422,49 +420,62 @@ int smu7_request_smu_load_fw(struct pp_hwmgr *hwmgr)
 			   + UCODE_ID_CP_MEC_JT2_MASK;
 	}
 
-	toc = (struct SMU_DRAMData_TOC *)smu_data->header;
-	toc->structure_version = 1;
-
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_RLC_G, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_CE, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_PFP, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_ME, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_MEC, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_MEC_JT1, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_MEC_JT2, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_SDMA0, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_SDMA1, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	if (!hwmgr->not_vf)
-		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_MEC_STORAGE, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
+	if (!smu_data->toc) {
+		struct SMU_DRAMData_TOC *toc;
 
-	toc->num_entries = num_entries;
+		smu_data->toc = kzalloc(sizeof(struct SMU_DRAMData_TOC), GFP_KERNEL);
+		if (!smu_data->toc)
+			return -ENOMEM;
+		toc = smu_data->toc;
+		toc->num_entries = 0;
+		toc->structure_version = 1;
+
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_RLC_G, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_CP_CE, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_CP_PFP, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_CP_ME, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_CP_MEC, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_CP_MEC_JT1, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_CP_MEC_JT2, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_SDMA0, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_SDMA1, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		if (!hwmgr->not_vf)
+			PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_MEC_STORAGE, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+	}
+	memcpy_toio(smu_data->header_buffer.kaddr, smu_data->toc,
+		    sizeof(struct SMU_DRAMData_TOC));
 	smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_DRV_DRAM_ADDR_HI, upper_32_bits(smu_data->header_buffer.mc_addr));
 	smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_DRV_DRAM_ADDR_LO, lower_32_bits(smu_data->header_buffer.mc_addr));
 
 	if (smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_LoadUcodes, fw_to_load))
 		pr_err("Fail to Request SMU Load uCode");
 
-	return result;
+	return r;
+
+failed:
+	kfree(smu_data->toc);
+	smu_data->toc = NULL;
+	return r;
 }
 
 /* Check if the FW has been loaded, SMU will not return if loading has not finished. */
@@ -571,7 +582,6 @@ int smu7_setup_pwr_virus(struct pp_hwmgr *hwmgr)
 int smu7_init(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_smumgr *smu_data;
-	uint64_t mc_addr = 0;
 	int r;
 	/* Allocate memory for backend private data */
 	smu_data = (struct smu7_smumgr *)(hwmgr->smu_backend);
@@ -585,15 +595,12 @@ int smu7_init(struct pp_hwmgr *hwmgr)
 		PAGE_SIZE,
 		AMDGPU_GEM_DOMAIN_VRAM,
 		&smu_data->header_buffer.handle,
-		&mc_addr,
+		&smu_data->header_buffer.mc_addr,
 		&smu_data->header_buffer.kaddr);
 
 	if (r)
 		return -EINVAL;
 
-	smu_data->header = smu_data->header_buffer.kaddr;
-	smu_data->header_buffer.mc_addr = mc_addr;
-
 	if (!hwmgr->not_vf)
 		return 0;
 
@@ -603,7 +610,7 @@ int smu7_init(struct pp_hwmgr *hwmgr)
 		PAGE_SIZE,
 		AMDGPU_GEM_DOMAIN_VRAM,
 		&smu_data->smu_buffer.handle,
-		&mc_addr,
+		&smu_data->smu_buffer.mc_addr,
 		&smu_data->smu_buffer.kaddr);
 
 	if (r) {
@@ -612,7 +619,6 @@ int smu7_init(struct pp_hwmgr *hwmgr)
 					&smu_data->header_buffer.kaddr);
 		return -EINVAL;
 	}
-	smu_data->smu_buffer.mc_addr = mc_addr;
 
 	if (smum_is_hw_avfs_present(hwmgr))
 		hwmgr->avfs_supported = true;
@@ -634,6 +640,9 @@ int smu7_smu_fini(struct pp_hwmgr *hwmgr)
 					&smu_data->smu_buffer.mc_addr,
 					&smu_data->smu_buffer.kaddr);
 
+
+	kfree(smu_data->toc);
+	smu_data->toc = NULL;
 	kfree(hwmgr->smu_backend);
 	hwmgr->smu_backend = NULL;
 	return 0;
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h
index 39c9bfda0ab4..01f0538fba6b 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h
@@ -37,10 +37,9 @@ struct smu7_buffer_entry {
 };
 
 struct smu7_smumgr {
-	uint8_t *header;
-	uint8_t *mec_image;
 	struct smu7_buffer_entry smu_buffer;
 	struct smu7_buffer_entry header_buffer;
+	struct SMU_DRAMData_TOC *toc;
 
 	uint32_t                             soft_regs_start;
 	uint32_t                             dpm_table_start;
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c
index c861d3023474..f7e3bc22bb93 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c
@@ -52,10 +52,10 @@ static const enum smu8_scratch_entry firmware_list[] = {
 	SMU8_SCRATCH_ENTRY_UCODE_ID_RLC_G,
 };
 
-static int smu8_get_argument(struct pp_hwmgr *hwmgr)
+static uint32_t smu8_get_argument(struct pp_hwmgr *hwmgr)
 {
 	if (hwmgr == NULL || hwmgr->device == NULL)
-		return -EINVAL;
+		return 0;
 
 	return cgs_read_register(hwmgr->device,
 					mmSMU_MP1_SRBM2P_ARG_0);
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c
new file mode 100644
index 000000000000..079fc8e8f709
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c
@@ -0,0 +1,150 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include "smumgr.h"
+#include "vega10_inc.h"
+#include "soc15_common.h"
+#include "pp_debug.h"
+
+
+/* MP Apertures */
+#define MP0_Public                  0x03800000
+#define MP0_SRAM                    0x03900000
+#define MP1_Public                  0x03b00000
+#define MP1_SRAM                    0x03c00004
+
+#define smnMP1_FIRMWARE_FLAGS                                                                           0x3010028
+
+bool smu9_is_smc_ram_running(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t mp1_fw_flags;
+
+	WREG32_SOC15(NBIF, 0, mmPCIE_INDEX2,
+			(MP1_Public | (smnMP1_FIRMWARE_FLAGS & 0xffffffff)));
+
+	mp1_fw_flags = RREG32_SOC15(NBIF, 0, mmPCIE_DATA2);
+
+	if (mp1_fw_flags & MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK)
+		return true;
+
+	return false;
+}
+
+/*
+ * Check if SMC has responded to previous message.
+ *
+ * @param    smumgr  the address of the powerplay hardware manager.
+ * @return   TRUE    SMC has responded, FALSE otherwise.
+ */
+static uint32_t smu9_wait_for_response(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t reg;
+	uint32_t ret;
+
+	reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_90);
+
+	ret = phm_wait_for_register_unequal(hwmgr, reg,
+			0, MP1_C2PMSG_90__CONTENT_MASK);
+
+	if (ret)
+		pr_err("No response from smu\n");
+
+	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
+}
+
+/*
+ * Send a message to the SMC, and do not wait for its response.
+ * @param    smumgr  the address of the powerplay hardware manager.
+ * @param    msg the message to send.
+ * @return   Always return 0.
+ */
+static int smu9_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr,
+						uint16_t msg)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, msg);
+
+	return 0;
+}
+
+/*
+ * Send a message to the SMC, and wait for its response.
+ * @param    hwmgr  the address of the powerplay hardware manager.
+ * @param    msg the message to send.
+ * @return   Always return 0.
+ */
+int smu9_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t ret;
+
+	smu9_wait_for_response(hwmgr);
+
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
+
+	smu9_send_msg_to_smc_without_waiting(hwmgr, msg);
+
+	ret = smu9_wait_for_response(hwmgr);
+	if (ret != 1)
+		pr_err("Failed to send message: 0x%x, ret value: 0x%x\n", msg, ret);
+
+	return 0;
+}
+
+/*
+ * Send a message to the SMC with parameter
+ * @param    hwmgr:  the address of the powerplay hardware manager.
+ * @param    msg: the message to send.
+ * @param    parameter: the parameter to send
+ * @return   Always return 0.
+ */
+int smu9_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
+					uint16_t msg, uint32_t parameter)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t ret;
+
+	smu9_wait_for_response(hwmgr);
+
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
+
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82, parameter);
+
+	smu9_send_msg_to_smc_without_waiting(hwmgr, msg);
+
+	ret = smu9_wait_for_response(hwmgr);
+	if (ret != 1)
+		pr_err("Failed message: 0x%x, input parameter: 0x%x, error code: 0x%x\n", msg, parameter, ret);
+
+	return 0;
+}
+
+uint32_t smu9_get_argument(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
+}
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.h b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.h
new file mode 100644
index 000000000000..1462279ca128
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef _SMU9_SMUMANAGER_H_
+#define _SMU9_SMUMANAGER_H_
+
+bool smu9_is_smc_ram_running(struct pp_hwmgr *hwmgr);
+int smu9_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg);
+int smu9_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
+					uint16_t msg, uint32_t parameter);
+uint32_t smu9_get_argument(struct pp_hwmgr *hwmgr);
+
+#endif
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
index c9837935f0f5..99d5e4f98f49 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
@@ -96,7 +96,7 @@ int smum_process_firmware_header(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-int smum_get_argument(struct pp_hwmgr *hwmgr)
+uint32_t smum_get_argument(struct pp_hwmgr *hwmgr)
 {
 	if (NULL != hwmgr->smumgr_funcs->get_argument)
 		return hwmgr->smumgr_funcs->get_argument(hwmgr);
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
index 782b19fc2e70..7dabc6c456e1 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
@@ -1443,51 +1443,6 @@ static int tonga_populate_smc_acp_level(struct pp_hwmgr *hwmgr,
 	return result;
 }
 
-static int tonga_populate_smc_samu_level(struct pp_hwmgr *hwmgr,
-		SMU72_Discrete_DpmTable *table)
-{
-	int result = 0;
-	uint8_t count;
-	pp_atomctrl_clock_dividers_vi dividers;
-	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
-	struct phm_ppt_v1_information *pptable_info =
-			     (struct phm_ppt_v1_information *)(hwmgr->pptable);
-	phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
-						    pptable_info->mm_dep_table;
-
-	table->SamuBootLevel = 0;
-	table->SamuLevelCount = (uint8_t) (mm_table->count);
-
-	for (count = 0; count < table->SamuLevelCount; count++) {
-		/* not sure whether we need evclk or not */
-		table->SamuLevel[count].Frequency =
-			pptable_info->mm_dep_table->entries[count].samclock;
-		table->SamuLevel[count].MinVoltage.Vddc =
-			phm_get_voltage_index(pptable_info->vddc_lookup_table,
-				mm_table->entries[count].vddc);
-		table->SamuLevel[count].MinVoltage.VddGfx =
-			(data->vdd_gfx_control == SMU7_VOLTAGE_CONTROL_BY_SVID2) ?
-			phm_get_voltage_index(pptable_info->vddgfx_lookup_table,
-				mm_table->entries[count].vddgfx) : 0;
-		table->SamuLevel[count].MinVoltage.Vddci =
-			phm_get_voltage_id(&data->vddci_voltage_table,
-				mm_table->entries[count].vddc - VDDC_VDDCI_DELTA);
-		table->SamuLevel[count].MinVoltage.Phases = 1;
-
-		/* retrieve divider value for VBIOS */
-		result = atomctrl_get_dfs_pll_dividers_vi(hwmgr,
-					table->SamuLevel[count].Frequency, &dividers);
-		PP_ASSERT_WITH_CODE((!result),
-			"can not find divide id for samu clock", return result);
-
-		table->SamuLevel[count].Divider = (uint8_t)dividers.pll_post_divider;
-
-		CONVERT_FROM_HOST_TO_SMC_UL(table->SamuLevel[count].Frequency);
-	}
-
-	return result;
-}
-
 static int tonga_populate_memory_timing_parameters(
 		struct pp_hwmgr *hwmgr,
 		uint32_t engine_clock,
@@ -2323,10 +2278,6 @@ static int tonga_init_smc_table(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE(!result,
 		"Failed to initialize ACP Level !", return result);
 
-	result = tonga_populate_smc_samu_level(hwmgr, table);
-	PP_ASSERT_WITH_CODE(!result,
-		"Failed to initialize SAMU Level !", return result);
-
 	/* Since only the initial state is completely set up at this
 	* point (the other states are just copies of the boot state) we only
 	* need to populate the  ARB settings for the initial state.
@@ -2673,8 +2624,6 @@ static uint32_t tonga_get_offsetof(uint32_t type, uint32_t member)
 			return offsetof(SMU72_Discrete_DpmTable, UvdBootLevel);
 		case VceBootLevel:
 			return offsetof(SMU72_Discrete_DpmTable, VceBootLevel);
-		case SamuBootLevel:
-			return offsetof(SMU72_Discrete_DpmTable, SamuBootLevel);
 		case LowSclkInterruptThreshold:
 			return offsetof(SMU72_Discrete_DpmTable, LowSclkInterruptThreshold);
 		}
@@ -2773,32 +2722,6 @@ static int tonga_update_vce_smc_table(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-static int tonga_update_samu_smc_table(struct pp_hwmgr *hwmgr)
-{
-	struct tonga_smumgr *smu_data = (struct tonga_smumgr *)(hwmgr->smu_backend);
-	uint32_t mm_boot_level_offset, mm_boot_level_value;
-
-	smu_data->smc_state_table.SamuBootLevel = 0;
-	mm_boot_level_offset = smu_data->smu7_data.dpm_table_start +
-				offsetof(SMU72_Discrete_DpmTable, SamuBootLevel);
-
-	mm_boot_level_offset /= 4;
-	mm_boot_level_offset *= 4;
-	mm_boot_level_value = cgs_read_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC, mm_boot_level_offset);
-	mm_boot_level_value &= 0xFFFFFF00;
-	mm_boot_level_value |= smu_data->smc_state_table.SamuBootLevel << 0;
-	cgs_write_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC, mm_boot_level_offset, mm_boot_level_value);
-
-	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
-			PHM_PlatformCaps_StablePState))
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-				PPSMC_MSG_SAMUDPM_SetEnabledMask,
-				(uint32_t)(1 << smu_data->smc_state_table.SamuBootLevel));
-	return 0;
-}
-
 static int tonga_update_smc_table(struct pp_hwmgr *hwmgr, uint32_t type)
 {
 	switch (type) {
@@ -2808,9 +2731,6 @@ static int tonga_update_smc_table(struct pp_hwmgr *hwmgr, uint32_t type)
 	case SMU_VCE_TABLE:
 		tonga_update_vce_smc_table(hwmgr);
 		break;
-	case SMU_SAMU_TABLE:
-		tonga_update_samu_smc_table(hwmgr);
-		break;
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
index e84669c448a3..5d19115f410c 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
@@ -28,142 +28,11 @@
 #include "vega10_hwmgr.h"
 #include "vega10_ppsmc.h"
 #include "smu9_driver_if.h"
+#include "smu9_smumgr.h"
 #include "ppatomctrl.h"
 #include "pp_debug.h"
 
 
-#define AVFS_EN_MSB		1568
-#define AVFS_EN_LSB		1568
-
-/* Microcode file is stored in this buffer */
-#define BUFFER_SIZE                 80000
-#define MAX_STRING_SIZE             15
-#define BUFFER_SIZETWO              131072 /* 128 *1024 */
-
-/* MP Apertures */
-#define MP0_Public                  0x03800000
-#define MP0_SRAM                    0x03900000
-#define MP1_Public                  0x03b00000
-#define MP1_SRAM                    0x03c00004
-
-#define smnMP1_FIRMWARE_FLAGS                                                                           0x3010028
-#define smnMP0_FW_INTF                                                                                  0x3010104
-#define smnMP1_PUB_CTRL                                                                                 0x3010b14
-
-static bool vega10_is_smc_ram_running(struct pp_hwmgr *hwmgr)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t mp1_fw_flags;
-
-	WREG32_SOC15(NBIF, 0, mmPCIE_INDEX2,
-			(MP1_Public | (smnMP1_FIRMWARE_FLAGS & 0xffffffff)));
-
-	mp1_fw_flags = RREG32_SOC15(NBIF, 0, mmPCIE_DATA2);
-
-	if (mp1_fw_flags & MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK)
-		return true;
-
-	return false;
-}
-
-/*
- * Check if SMC has responded to previous message.
- *
- * @param    smumgr  the address of the powerplay hardware manager.
- * @return   TRUE    SMC has responded, FALSE otherwise.
- */
-static uint32_t vega10_wait_for_response(struct pp_hwmgr *hwmgr)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t reg;
-	uint32_t ret;
-
-	reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_90);
-
-	ret = phm_wait_for_register_unequal(hwmgr, reg,
-			0, MP1_C2PMSG_90__CONTENT_MASK);
-
-	if (ret)
-		pr_err("No response from smu\n");
-
-	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
-}
-
-/*
- * Send a message to the SMC, and do not wait for its response.
- * @param    smumgr  the address of the powerplay hardware manager.
- * @param    msg the message to send.
- * @return   Always return 0.
- */
-static int vega10_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr,
-		uint16_t msg)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, msg);
-
-	return 0;
-}
-
-/*
- * Send a message to the SMC, and wait for its response.
- * @param    hwmgr  the address of the powerplay hardware manager.
- * @param    msg the message to send.
- * @return   Always return 0.
- */
-static int vega10_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t ret;
-
-	vega10_wait_for_response(hwmgr);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
-
-	vega10_send_msg_to_smc_without_waiting(hwmgr, msg);
-
-	ret = vega10_wait_for_response(hwmgr);
-	if (ret != 1)
-		pr_err("Failed to send message: 0x%x, ret value: 0x%x\n", msg, ret);
-
-	return 0;
-}
-
-/*
- * Send a message to the SMC with parameter
- * @param    hwmgr:  the address of the powerplay hardware manager.
- * @param    msg: the message to send.
- * @param    parameter: the parameter to send
- * @return   Always return 0.
- */
-static int vega10_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
-		uint16_t msg, uint32_t parameter)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t ret;
-
-	vega10_wait_for_response(hwmgr);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82, parameter);
-
-	vega10_send_msg_to_smc_without_waiting(hwmgr, msg);
-
-	ret = vega10_wait_for_response(hwmgr);
-	if (ret != 1)
-		pr_err("Failed message: 0x%x, input parameter: 0x%x, error code: 0x%x\n", msg, parameter, ret);
-
-	return 0;
-}
-
-static int vega10_get_argument(struct pp_hwmgr *hwmgr)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
-}
-
 static int vega10_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 		uint8_t *table, int16_t table_id)
 {
@@ -175,13 +44,13 @@ static int vega10_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 			"Invalid SMU Table version!", return -EINVAL);
 	PP_ASSERT_WITH_CODE(priv->smu_tables.entry[table_id].size != 0,
 			"Invalid SMU Table Length!", return -EINVAL);
-	vega10_send_msg_to_smc_with_parameter(hwmgr,
+	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[table_id].mc_addr));
-	vega10_send_msg_to_smc_with_parameter(hwmgr,
+	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrLow,
 			lower_32_bits(priv->smu_tables.entry[table_id].mc_addr));
-	vega10_send_msg_to_smc_with_parameter(hwmgr,
+	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_TransferTableSmu2Dram,
 			priv->smu_tables.entry[table_id].table_id);
 
@@ -206,13 +75,13 @@ static int vega10_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 	memcpy(priv->smu_tables.entry[table_id].table, table,
 			priv->smu_tables.entry[table_id].size);
 
-	vega10_send_msg_to_smc_with_parameter(hwmgr,
+	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[table_id].mc_addr));
-	vega10_send_msg_to_smc_with_parameter(hwmgr,
+	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrLow,
 			lower_32_bits(priv->smu_tables.entry[table_id].mc_addr));
-	vega10_send_msg_to_smc_with_parameter(hwmgr,
+	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_TransferTableDram2Smu,
 			priv->smu_tables.entry[table_id].table_id);
 
@@ -225,8 +94,8 @@ static int vega10_get_smc_features(struct pp_hwmgr *hwmgr,
 	if (features_enabled == NULL)
 		return -EINVAL;
 
-	vega10_send_msg_to_smc(hwmgr, PPSMC_MSG_GetEnabledSmuFeatures);
-	*features_enabled = vega10_get_argument(hwmgr);
+	smu9_send_msg_to_smc(hwmgr, PPSMC_MSG_GetEnabledSmuFeatures);
+	*features_enabled = smu9_get_argument(hwmgr);
 
 	return 0;
 }
@@ -248,10 +117,10 @@ static int vega10_set_tools_address(struct pp_hwmgr *hwmgr)
 	struct vega10_smumgr *priv = hwmgr->smu_backend;
 
 	if (priv->smu_tables.entry[TOOLSTABLE].mc_addr) {
-		vega10_send_msg_to_smc_with_parameter(hwmgr,
+		smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_SetToolsDramAddrHigh,
 				upper_32_bits(priv->smu_tables.entry[TOOLSTABLE].mc_addr));
-		vega10_send_msg_to_smc_with_parameter(hwmgr,
+		smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_SetToolsDramAddrLow,
 				lower_32_bits(priv->smu_tables.entry[TOOLSTABLE].mc_addr));
 	}
@@ -265,11 +134,11 @@ static int vega10_verify_smc_interface(struct pp_hwmgr *hwmgr)
 	uint32_t dev_id;
 	uint32_t rev_id;
 
-	PP_ASSERT_WITH_CODE(!vega10_send_msg_to_smc(hwmgr,
+	PP_ASSERT_WITH_CODE(!smu9_send_msg_to_smc(hwmgr,
 			PPSMC_MSG_GetDriverIfVersion),
 			"Attempt to get SMC IF Version Number Failed!",
 			return -EINVAL);
-	smc_driver_if_version = vega10_get_argument(hwmgr);
+	smc_driver_if_version = smu9_get_argument(hwmgr);
 
 	dev_id = adev->pdev->device;
 	rev_id = adev->pdev->revision;
@@ -441,7 +310,7 @@ static int vega10_smu_fini(struct pp_hwmgr *hwmgr)
 
 static int vega10_start_smu(struct pp_hwmgr *hwmgr)
 {
-	if (!vega10_is_smc_ram_running(hwmgr))
+	if (!smu9_is_smc_ram_running(hwmgr))
 		return -EINVAL;
 
 	PP_ASSERT_WITH_CODE(!vega10_verify_smc_interface(hwmgr),
@@ -453,7 +322,8 @@ static int vega10_start_smu(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-static int vega10_smc_table_manager(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t table_id, bool rw)
+static int vega10_smc_table_manager(struct pp_hwmgr *hwmgr, uint8_t *table,
+				    uint16_t table_id, bool rw)
 {
 	int ret;
 
@@ -470,11 +340,11 @@ const struct pp_smumgr_func vega10_smu_funcs = {
 	.smu_fini = &vega10_smu_fini,
 	.start_smu = &vega10_start_smu,
 	.request_smu_load_specific_fw = NULL,
-	.send_msg_to_smc = &vega10_send_msg_to_smc,
-	.send_msg_to_smc_with_parameter = &vega10_send_msg_to_smc_with_parameter,
+	.send_msg_to_smc = &smu9_send_msg_to_smc,
+	.send_msg_to_smc_with_parameter = &smu9_send_msg_to_smc_with_parameter,
 	.download_pptable_settings = NULL,
 	.upload_pptable_settings = NULL,
 	.is_dpm_running = vega10_is_dpm_running,
-	.get_argument = vega10_get_argument,
+	.get_argument = smu9_get_argument,
 	.smc_table_manager = vega10_smc_table_manager,
 };
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
index 7d9b40e8b1bf..7f0e2109f40d 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
@@ -24,157 +24,14 @@
 #include "smumgr.h"
 #include "vega12_inc.h"
 #include "soc15_common.h"
+#include "smu9_smumgr.h"
 #include "vega12_smumgr.h"
 #include "vega12_ppsmc.h"
 #include "vega12/smu9_driver_if.h"
-
 #include "ppatomctrl.h"
 #include "pp_debug.h"
 
 
-/* MP Apertures */
-#define MP0_Public                  0x03800000
-#define MP0_SRAM                    0x03900000
-#define MP1_Public                  0x03b00000
-#define MP1_SRAM                    0x03c00004
-
-#define smnMP1_FIRMWARE_FLAGS                                                                           0x3010028
-#define smnMP0_FW_INTF                                                                                  0x3010104
-#define smnMP1_PUB_CTRL                                                                                 0x3010b14
-
-static bool vega12_is_smc_ram_running(struct pp_hwmgr *hwmgr)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t mp1_fw_flags;
-
-	WREG32_SOC15(NBIF, 0, mmPCIE_INDEX2,
-			(MP1_Public | (smnMP1_FIRMWARE_FLAGS & 0xffffffff)));
-
-	mp1_fw_flags = RREG32_SOC15(NBIF, 0, mmPCIE_DATA2);
-
-	if ((mp1_fw_flags & MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK) >>
-				MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED__SHIFT)
-		return true;
-
-	return false;
-}
-
-/*
- * Check if SMC has responded to previous message.
- *
- * @param    smumgr  the address of the powerplay hardware manager.
- * @return   TRUE    SMC has responded, FALSE otherwise.
- */
-static uint32_t vega12_wait_for_response(struct pp_hwmgr *hwmgr)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t reg;
-
-	reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_90);
-
-	phm_wait_for_register_unequal(hwmgr, reg,
-			0, MP1_C2PMSG_90__CONTENT_MASK);
-
-	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
-}
-
-/*
- * Send a message to the SMC, and do not wait for its response.
- * @param    smumgr  the address of the powerplay hardware manager.
- * @param    msg the message to send.
- * @return   Always return 0.
- */
-int vega12_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr,
-		uint16_t msg)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, msg);
-
-	return 0;
-}
-
-/*
- * Send a message to the SMC, and wait for its response.
- * @param    hwmgr  the address of the powerplay hardware manager.
- * @param    msg the message to send.
- * @return   Always return 0.
- */
-int vega12_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	vega12_wait_for_response(hwmgr);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
-
-	vega12_send_msg_to_smc_without_waiting(hwmgr, msg);
-
-	if (vega12_wait_for_response(hwmgr) != 1)
-		pr_err("Failed to send message: 0x%x\n", msg);
-
-	return 0;
-}
-
-/*
- * Send a message to the SMC with parameter
- * @param    hwmgr:  the address of the powerplay hardware manager.
- * @param    msg: the message to send.
- * @param    parameter: the parameter to send
- * @return   Always return 0.
- */
-int vega12_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
-		uint16_t msg, uint32_t parameter)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	vega12_wait_for_response(hwmgr);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82, parameter);
-
-	vega12_send_msg_to_smc_without_waiting(hwmgr, msg);
-
-	if (vega12_wait_for_response(hwmgr) != 1)
-		pr_err("Failed to send message: 0x%x\n", msg);
-
-	return 0;
-}
-
-
-/*
- * Send a message to the SMC with parameter, do not wait for response
- * @param    hwmgr:  the address of the powerplay hardware manager.
- * @param    msg: the message to send.
- * @param    parameter: the parameter to send
- * @return   The response that came from the SMC.
- */
-int vega12_send_msg_to_smc_with_parameter_without_waiting(
-		struct pp_hwmgr *hwmgr, uint16_t msg, uint32_t parameter)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, parameter);
-
-	return vega12_send_msg_to_smc_without_waiting(hwmgr, msg);
-}
-
-/*
- * Retrieve an argument from SMC.
- * @param    hwmgr  the address of the powerplay hardware manager.
- * @param    arg     pointer to store the argument from SMC.
- * @return   Always return 0.
- */
-int vega12_read_arg_from_smc(struct pp_hwmgr *hwmgr, uint32_t *arg)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	*arg = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
-
-	return 0;
-}
-
 /*
  * Copy table from SMC into driver FB
  * @param   hwmgr    the address of the HW manager
@@ -192,16 +49,16 @@ int vega12_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 			"Invalid SMU Table version!", return -EINVAL);
 	PP_ASSERT_WITH_CODE(priv->smu_tables.entry[table_id].size != 0,
 			"Invalid SMU Table Length!", return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[table_id].mc_addr)) == 0,
 			"[CopyTableFromSMC] Attempt to Set Dram Addr High Failed!", return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrLow,
 			lower_32_bits(priv->smu_tables.entry[table_id].mc_addr)) == 0,
 			"[CopyTableFromSMC] Attempt to Set Dram Addr Low Failed!",
 			return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_TransferTableSmu2Dram,
 			table_id) == 0,
 			"[CopyTableFromSMC] Attempt to Transfer Table From SMU Failed!",
@@ -234,17 +91,17 @@ int vega12_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 	memcpy(priv->smu_tables.entry[table_id].table, table,
 			priv->smu_tables.entry[table_id].size);
 
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[table_id].mc_addr)) == 0,
 			"[CopyTableToSMC] Attempt to Set Dram Addr High Failed!",
 			return -EINVAL;);
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrLow,
 			lower_32_bits(priv->smu_tables.entry[table_id].mc_addr)) == 0,
 			"[CopyTableToSMC] Attempt to Set Dram Addr Low Failed!",
 			return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_TransferTableDram2Smu,
 			table_id) == 0,
 			"[CopyTableToSMC] Attempt to Transfer Table To SMU Failed!",
@@ -262,20 +119,20 @@ int vega12_enable_smc_features(struct pp_hwmgr *hwmgr,
 	smu_features_high = (uint32_t)((feature_mask & SMU_FEATURES_HIGH_MASK) >> SMU_FEATURES_HIGH_SHIFT);
 
 	if (enable) {
-		PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+		PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_EnableSmuFeaturesLow, smu_features_low) == 0,
 				"[EnableDisableSMCFeatures] Attemp to enable SMU features Low failed!",
 				return -EINVAL);
-		PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+		PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_EnableSmuFeaturesHigh, smu_features_high) == 0,
 				"[EnableDisableSMCFeatures] Attemp to enable SMU features High failed!",
 				return -EINVAL);
 	} else {
-		PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+		PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_DisableSmuFeaturesLow, smu_features_low) == 0,
 				"[EnableDisableSMCFeatures] Attemp to disable SMU features Low failed!",
 				return -EINVAL);
-		PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+		PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_DisableSmuFeaturesHigh, smu_features_high) == 0,
 				"[EnableDisableSMCFeatures] Attemp to disable SMU features High failed!",
 				return -EINVAL);
@@ -292,22 +149,17 @@ int vega12_get_enabled_smc_features(struct pp_hwmgr *hwmgr,
 	if (features_enabled == NULL)
 		return -EINVAL;
 
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc(hwmgr,
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc(hwmgr,
 			PPSMC_MSG_GetEnabledSmuFeaturesLow) == 0,
 			"[GetEnabledSMCFeatures] Attemp to get SMU features Low failed!",
 			return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_read_arg_from_smc(hwmgr,
-			&smc_features_low) == 0,
-			"[GetEnabledSMCFeatures] Attemp to read SMU features Low argument failed!",
-			return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc(hwmgr,
+	smc_features_low = smu9_get_argument(hwmgr);
+
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc(hwmgr,
 			PPSMC_MSG_GetEnabledSmuFeaturesHigh) == 0,
 			"[GetEnabledSMCFeatures] Attemp to get SMU features High failed!",
 			return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_read_arg_from_smc(hwmgr,
-			&smc_features_high) == 0,
-			"[GetEnabledSMCFeatures] Attemp to read SMU features High argument failed!",
-			return -EINVAL);
+	smc_features_high = smu9_get_argument(hwmgr);
 
 	*features_enabled = ((((uint64_t)smc_features_low << SMU_FEATURES_LOW_SHIFT) & SMU_FEATURES_LOW_MASK) |
 			(((uint64_t)smc_features_high << SMU_FEATURES_HIGH_SHIFT) & SMU_FEATURES_HIGH_MASK));
@@ -333,39 +185,16 @@ static int vega12_set_tools_address(struct pp_hwmgr *hwmgr)
 			(struct vega12_smumgr *)(hwmgr->smu_backend);
 
 	if (priv->smu_tables.entry[TABLE_PMSTATUSLOG].mc_addr) {
-		if (!vega12_send_msg_to_smc_with_parameter(hwmgr,
+		if (!smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_SetToolsDramAddrHigh,
 				upper_32_bits(priv->smu_tables.entry[TABLE_PMSTATUSLOG].mc_addr)))
-			vega12_send_msg_to_smc_with_parameter(hwmgr,
+			smu9_send_msg_to_smc_with_parameter(hwmgr,
 					PPSMC_MSG_SetToolsDramAddrLow,
 					lower_32_bits(priv->smu_tables.entry[TABLE_PMSTATUSLOG].mc_addr));
 	}
 	return 0;
 }
 
-#if 0 /* tentatively remove */
-static int vega12_verify_smc_interface(struct pp_hwmgr *hwmgr)
-{
-	uint32_t smc_driver_if_version;
-
-	PP_ASSERT_WITH_CODE(!vega12_send_msg_to_smc(hwmgr,
-			PPSMC_MSG_GetDriverIfVersion),
-			"Attempt to get SMC IF Version Number Failed!",
-			return -EINVAL);
-	vega12_read_arg_from_smc(hwmgr, &smc_driver_if_version);
-
-	if (smc_driver_if_version != SMU9_DRIVER_IF_VERSION) {
-		pr_err("Your firmware(0x%x) doesn't match \
-			SMU9_DRIVER_IF_VERSION(0x%x). \
-			Please update your firmware!\n",
-			smc_driver_if_version, SMU9_DRIVER_IF_VERSION);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-#endif
-
 static int vega12_smu_init(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_smumgr *priv;
@@ -513,16 +342,10 @@ static int vega12_smu_fini(struct pp_hwmgr *hwmgr)
 
 static int vega12_start_smu(struct pp_hwmgr *hwmgr)
 {
-	PP_ASSERT_WITH_CODE(vega12_is_smc_ram_running(hwmgr),
+	PP_ASSERT_WITH_CODE(smu9_is_smc_ram_running(hwmgr),
 			"SMC is not running!",
 			return -EINVAL);
 
-#if 0 /* tentatively remove */
-	PP_ASSERT_WITH_CODE(!vega12_verify_smc_interface(hwmgr),
-			"Failed to verify SMC interface!",
-			return -EINVAL);
-#endif
-
 	vega12_set_tools_address(hwmgr);
 
 	return 0;
@@ -533,9 +356,10 @@ const struct pp_smumgr_func vega12_smu_funcs = {
 	.smu_fini = &vega12_smu_fini,
 	.start_smu = &vega12_start_smu,
 	.request_smu_load_specific_fw = NULL,
-	.send_msg_to_smc = &vega12_send_msg_to_smc,
-	.send_msg_to_smc_with_parameter = &vega12_send_msg_to_smc_with_parameter,
+	.send_msg_to_smc = &smu9_send_msg_to_smc,
+	.send_msg_to_smc_with_parameter = &smu9_send_msg_to_smc_with_parameter,
 	.download_pptable_settings = NULL,
 	.upload_pptable_settings = NULL,
 	.is_dpm_running = vega12_is_dpm_running,
+	.get_argument = smu9_get_argument,
 };
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.h b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.h
index 2810d387b611..b285cbc04019 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.h
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.h
@@ -48,7 +48,6 @@ struct vega12_smumgr {
 #define SMU_FEATURES_HIGH_MASK       0xFFFFFFFF00000000
 #define SMU_FEATURES_HIGH_SHIFT      32
 
-int vega12_read_arg_from_smc(struct pp_hwmgr *hwmgr, uint32_t *arg);
 int vega12_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 		uint8_t *table, int16_t table_id);
 int vega12_copy_table_to_smc(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
index 2de48959ac93..57420d7caa4e 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
@@ -393,34 +393,6 @@ static int vegam_update_vce_smc_table(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-static int vegam_update_samu_smc_table(struct pp_hwmgr *hwmgr)
-{
-	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
-	uint32_t mm_boot_level_offset, mm_boot_level_value;
-
-
-	smu_data->smc_state_table.SamuBootLevel = 0;
-	mm_boot_level_offset = smu_data->smu7_data.dpm_table_start +
-				offsetof(SMU75_Discrete_DpmTable, SamuBootLevel);
-
-	mm_boot_level_offset /= 4;
-	mm_boot_level_offset *= 4;
-	mm_boot_level_value = cgs_read_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC, mm_boot_level_offset);
-	mm_boot_level_value &= 0xFFFFFF00;
-	mm_boot_level_value |= smu_data->smc_state_table.SamuBootLevel << 0;
-	cgs_write_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC, mm_boot_level_offset, mm_boot_level_value);
-
-	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
-			PHM_PlatformCaps_StablePState))
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-				PPSMC_MSG_SAMUDPM_SetEnabledMask,
-				(uint32_t)(1 << smu_data->smc_state_table.SamuBootLevel));
-	return 0;
-}
-
-
 static int vegam_update_bif_smc_table(struct pp_hwmgr *hwmgr)
 {
 	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
@@ -447,9 +419,6 @@ static int vegam_update_smc_table(struct pp_hwmgr *hwmgr, uint32_t type)
 	case SMU_VCE_TABLE:
 		vegam_update_vce_smc_table(hwmgr);
 		break;
-	case SMU_SAMU_TABLE:
-		vegam_update_samu_smc_table(hwmgr);
-		break;
 	case SMU_BIF_TABLE:
 		vegam_update_bif_smc_table(hwmgr);
 		break;
@@ -1281,54 +1250,6 @@ static int vegam_populate_smc_vce_level(struct pp_hwmgr *hwmgr,
 	return result;
 }
 
-static int vegam_populate_smc_samu_level(struct pp_hwmgr *hwmgr,
-		SMU75_Discrete_DpmTable *table)
-{
-	int result = -EINVAL;
-	uint8_t count;
-	struct pp_atomctrl_clock_dividers_vi dividers;
-	struct phm_ppt_v1_information *table_info =
-			(struct phm_ppt_v1_information *)(hwmgr->pptable);
-	struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
-			table_info->mm_dep_table;
-	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
-	uint32_t vddci;
-
-	table->SamuBootLevel = 0;
-	table->SamuLevelCount = (uint8_t)(mm_table->count);
-
-	for (count = 0; count < table->SamuLevelCount; count++) {
-		/* not sure whether we need evclk or not */
-		table->SamuLevel[count].MinVoltage = 0;
-		table->SamuLevel[count].Frequency = mm_table->entries[count].samclock;
-		table->SamuLevel[count].MinVoltage |= (mm_table->entries[count].vddc *
-				VOLTAGE_SCALE) << VDDC_SHIFT;
-
-		if (SMU7_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control)
-			vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table),
-						mm_table->entries[count].vddc - VDDC_VDDCI_DELTA);
-		else if (SMU7_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control)
-			vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA;
-		else
-			vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT;
-
-		table->SamuLevel[count].MinVoltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
-		table->SamuLevel[count].MinVoltage |= 1 << PHASES_SHIFT;
-
-		/* retrieve divider value for VBIOS */
-		result = atomctrl_get_dfs_pll_dividers_vi(hwmgr,
-				table->SamuLevel[count].Frequency, &dividers);
-		PP_ASSERT_WITH_CODE((0 == result),
-				"can not find divide id for samu clock", return result);
-
-		table->SamuLevel[count].Divider = (uint8_t)dividers.pll_post_divider;
-
-		CONVERT_FROM_HOST_TO_SMC_UL(table->SamuLevel[count].Frequency);
-		CONVERT_FROM_HOST_TO_SMC_UL(table->SamuLevel[count].MinVoltage);
-	}
-	return result;
-}
-
 static int vegam_populate_memory_timing_parameters(struct pp_hwmgr *hwmgr,
 		int32_t eng_clock, int32_t mem_clock,
 		SMU75_Discrete_MCArbDramTimingTableEntry *arb_regs)
@@ -2062,10 +1983,6 @@ static int vegam_init_smc_table(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE(!result,
 			"Failed to initialize VCE Level!", return result);
 
-	result = vegam_populate_smc_samu_level(hwmgr, table);
-	PP_ASSERT_WITH_CODE(!result,
-			"Failed to initialize SAMU Level!", return result);
-
 	/* Since only the initial state is completely set up at this point
 	 * (the other states are just copies of the boot state) we only
 	 * need to populate the  ARB settings for the initial state.
@@ -2273,8 +2190,6 @@ static uint32_t vegam_get_offsetof(uint32_t type, uint32_t member)
 			return offsetof(SMU75_Discrete_DpmTable, UvdBootLevel);
 		case VceBootLevel:
 			return offsetof(SMU75_Discrete_DpmTable, VceBootLevel);
-		case SamuBootLevel:
-			return offsetof(SMU75_Discrete_DpmTable, SamuBootLevel);
 		case LowSclkInterruptThreshold:
 			return offsetof(SMU75_Discrete_DpmTable, LowSclkInterruptThreshold);
 		}
diff --git a/drivers/gpu/drm/arc/arcpgu_crtc.c b/drivers/gpu/drm/arc/arcpgu_crtc.c
index 16903dc7fe0d..965cda48dc13 100644
--- a/drivers/gpu/drm/arc/arcpgu_crtc.c
+++ b/drivers/gpu/drm/arc/arcpgu_crtc.c
@@ -136,9 +136,6 @@ static void arc_pgu_crtc_atomic_disable(struct drm_crtc *crtc,
 {
 	struct arcpgu_drm_private *arcpgu = crtc_to_arcpgu_priv(crtc);
 
-	if (!crtc->primary->fb)
-		return;
-
 	clk_disable_unprepare(arcpgu->clk);
 	arc_pgu_write(arcpgu, ARCPGU_REG_CTRL,
 			      arc_pgu_read(arcpgu, ARCPGU_REG_CTRL) &
@@ -189,7 +186,7 @@ static const struct drm_plane_helper_funcs arc_pgu_plane_helper_funcs = {
 
 static void arc_pgu_plane_destroy(struct drm_plane *plane)
 {
-	drm_plane_helper_disable(plane);
+	drm_plane_helper_disable(plane, NULL);
 	drm_plane_cleanup(plane);
 }
 
diff --git a/drivers/gpu/drm/arc/arcpgu_sim.c b/drivers/gpu/drm/arc/arcpgu_sim.c
index b8f6f9a5dfbe..68629e614990 100644
--- a/drivers/gpu/drm/arc/arcpgu_sim.c
+++ b/drivers/gpu/drm/arc/arcpgu_sim.c
@@ -99,7 +99,7 @@ int arcpgu_drm_sim_init(struct drm_device *drm, struct device_node *np)
 		goto error_encoder_cleanup;
 	}
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret < 0) {
 		dev_err(drm->dev, "could not attach connector to encoder\n");
 		drm_connector_unregister(connector);
diff --git a/drivers/gpu/drm/arm/Makefile b/drivers/gpu/drm/arm/Makefile
index bb8b158ff90d..3bf31d1a4722 100644
--- a/drivers/gpu/drm/arm/Makefile
+++ b/drivers/gpu/drm/arm/Makefile
@@ -1,4 +1,5 @@
 hdlcd-y := hdlcd_drv.o hdlcd_crtc.o
 obj-$(CONFIG_DRM_HDLCD)	+= hdlcd.o
 mali-dp-y := malidp_drv.o malidp_hw.o malidp_planes.o malidp_crtc.o
+mali-dp-y += malidp_mw.o
 obj-$(CONFIG_DRM_MALI_DISPLAY)	+= mali-dp.o
diff --git a/drivers/gpu/drm/arm/hdlcd_crtc.c b/drivers/gpu/drm/arm/hdlcd_crtc.c
index cf5cbd63ecdf..e4d67b70244d 100644
--- a/drivers/gpu/drm/arm/hdlcd_crtc.c
+++ b/drivers/gpu/drm/arm/hdlcd_crtc.c
@@ -229,6 +229,8 @@ static const struct drm_crtc_helper_funcs hdlcd_crtc_helper_funcs = {
 static int hdlcd_plane_atomic_check(struct drm_plane *plane,
 				    struct drm_plane_state *state)
 {
+	int i;
+	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
 	u32 src_h = state->src_h >> 16;
 
@@ -238,20 +240,17 @@ static int hdlcd_plane_atomic_check(struct drm_plane *plane,
 		return -EINVAL;
 	}
 
-	if (!state->fb || !state->crtc)
-		return 0;
-
-	crtc_state = drm_atomic_get_existing_crtc_state(state->state,
-							state->crtc);
-	if (!crtc_state) {
-		DRM_DEBUG_KMS("Invalid crtc state\n");
-		return -EINVAL;
+	for_each_new_crtc_in_state(state->state, crtc, crtc_state, i) {
+		/* we cannot disable the plane while the CRTC is active */
+		if (!state->fb && crtc_state->active)
+			return -EINVAL;
+		return drm_atomic_helper_check_plane_state(state, crtc_state,
+						DRM_PLANE_HELPER_NO_SCALING,
+						DRM_PLANE_HELPER_NO_SCALING,
+						false, true);
 	}
 
-	return drm_atomic_helper_check_plane_state(state, crtc_state,
-						   DRM_PLANE_HELPER_NO_SCALING,
-						   DRM_PLANE_HELPER_NO_SCALING,
-						   false, true);
+	return 0;
 }
 
 static void hdlcd_plane_atomic_update(struct drm_plane *plane,
@@ -280,16 +279,10 @@ static const struct drm_plane_helper_funcs hdlcd_plane_helper_funcs = {
 	.atomic_update = hdlcd_plane_atomic_update,
 };
 
-static void hdlcd_plane_destroy(struct drm_plane *plane)
-{
-	drm_plane_helper_disable(plane);
-	drm_plane_cleanup(plane);
-}
-
 static const struct drm_plane_funcs hdlcd_plane_funcs = {
 	.update_plane		= drm_atomic_helper_update_plane,
 	.disable_plane		= drm_atomic_helper_disable_plane,
-	.destroy		= hdlcd_plane_destroy,
+	.destroy		= drm_plane_cleanup,
 	.reset			= drm_atomic_helper_plane_reset,
 	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
 	.atomic_destroy_state	= drm_atomic_helper_plane_destroy_state,
@@ -334,10 +327,8 @@ int hdlcd_setup_crtc(struct drm_device *drm)
 
 	ret = drm_crtc_init_with_planes(drm, &hdlcd->crtc, primary, NULL,
 					&hdlcd_crtc_funcs, NULL);
-	if (ret) {
-		hdlcd_plane_destroy(primary);
+	if (ret)
 		return ret;
-	}
 
 	drm_crtc_helper_add(&hdlcd->crtc, &hdlcd_crtc_helper_funcs);
 	return 0;
diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c
index feaa8bc3d7b7..0ed1cde98cf8 100644
--- a/drivers/gpu/drm/arm/hdlcd_drv.c
+++ b/drivers/gpu/drm/arm/hdlcd_drv.c
@@ -27,6 +27,7 @@
 #include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
+#include <drm/drm_modeset_helper.h>
 #include <drm/drm_of.h>
 
 #include "hdlcd_drv.h"
@@ -100,16 +101,9 @@ setup_fail:
 	return ret;
 }
 
-static void hdlcd_fb_output_poll_changed(struct drm_device *drm)
-{
-	struct hdlcd_drm_private *hdlcd = drm->dev_private;
-
-	drm_fbdev_cma_hotplug_event(hdlcd->fbdev);
-}
-
 static const struct drm_mode_config_funcs hdlcd_mode_config_funcs = {
 	.fb_create = drm_gem_fb_create,
-	.output_poll_changed = hdlcd_fb_output_poll_changed,
+	.output_poll_changed = drm_fb_helper_output_poll_changed,
 	.atomic_check = drm_atomic_helper_check,
 	.atomic_commit = drm_atomic_helper_commit,
 };
@@ -124,13 +118,6 @@ static void hdlcd_setup_mode_config(struct drm_device *drm)
 	drm->mode_config.funcs = &hdlcd_mode_config_funcs;
 }
 
-static void hdlcd_lastclose(struct drm_device *drm)
-{
-	struct hdlcd_drm_private *hdlcd = drm->dev_private;
-
-	drm_fbdev_cma_restore_mode(hdlcd->fbdev);
-}
-
 static irqreturn_t hdlcd_irq(int irq, void *arg)
 {
 	struct drm_device *drm = arg;
@@ -246,7 +233,7 @@ static struct drm_driver hdlcd_driver = {
 	.driver_features = DRIVER_HAVE_IRQ | DRIVER_GEM |
 			   DRIVER_MODESET | DRIVER_PRIME |
 			   DRIVER_ATOMIC,
-	.lastclose = hdlcd_lastclose,
+	.lastclose = drm_fb_helper_lastclose,
 	.irq_handler = hdlcd_irq,
 	.irq_preinstall = hdlcd_irq_preinstall,
 	.irq_postinstall = hdlcd_irq_postinstall,
@@ -321,14 +308,9 @@ static int hdlcd_drm_bind(struct device *dev)
 	drm_mode_config_reset(drm);
 	drm_kms_helper_poll_init(drm);
 
-	hdlcd->fbdev = drm_fbdev_cma_init(drm, 32,
-					  drm->mode_config.num_connector);
-
-	if (IS_ERR(hdlcd->fbdev)) {
-		ret = PTR_ERR(hdlcd->fbdev);
-		hdlcd->fbdev = NULL;
+	ret = drm_fb_cma_fbdev_init(drm, 32, 0);
+	if (ret)
 		goto err_fbdev;
-	}
 
 	ret = drm_dev_register(drm, 0);
 	if (ret)
@@ -337,15 +319,13 @@ static int hdlcd_drm_bind(struct device *dev)
 	return 0;
 
 err_register:
-	if (hdlcd->fbdev) {
-		drm_fbdev_cma_fini(hdlcd->fbdev);
-		hdlcd->fbdev = NULL;
-	}
+	drm_fb_cma_fbdev_fini(drm);
 err_fbdev:
 	drm_kms_helper_poll_fini(drm);
 err_vblank:
 	pm_runtime_disable(drm->dev);
 err_pm_active:
+	drm_atomic_helper_shutdown(drm);
 	component_unbind_all(dev, drm);
 err_unload:
 	of_node_put(hdlcd->crtc.port);
@@ -366,23 +346,23 @@ static void hdlcd_drm_unbind(struct device *dev)
 	struct hdlcd_drm_private *hdlcd = drm->dev_private;
 
 	drm_dev_unregister(drm);
-	if (hdlcd->fbdev) {
-		drm_fbdev_cma_fini(hdlcd->fbdev);
-		hdlcd->fbdev = NULL;
-	}
+	drm_fb_cma_fbdev_fini(drm);
 	drm_kms_helper_poll_fini(drm);
 	component_unbind_all(dev, drm);
 	of_node_put(hdlcd->crtc.port);
 	hdlcd->crtc.port = NULL;
-	pm_runtime_get_sync(drm->dev);
+	pm_runtime_get_sync(dev);
+	drm_crtc_vblank_off(&hdlcd->crtc);
 	drm_irq_uninstall(drm);
-	pm_runtime_put_sync(drm->dev);
-	pm_runtime_disable(drm->dev);
-	of_reserved_mem_device_release(drm->dev);
+	drm_atomic_helper_shutdown(drm);
+	pm_runtime_put(dev);
+	if (pm_runtime_enabled(dev))
+		pm_runtime_disable(dev);
+	of_reserved_mem_device_release(dev);
 	drm_mode_config_cleanup(drm);
-	drm_dev_put(drm);
 	drm->dev_private = NULL;
 	dev_set_drvdata(dev, NULL);
+	drm_dev_put(drm);
 }
 
 static const struct component_master_ops hdlcd_master_ops = {
@@ -427,35 +407,15 @@ MODULE_DEVICE_TABLE(of, hdlcd_of_match);
 static int __maybe_unused hdlcd_pm_suspend(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
-	struct hdlcd_drm_private *hdlcd = drm ? drm->dev_private : NULL;
-
-	if (!hdlcd)
-		return 0;
 
-	drm_kms_helper_poll_disable(drm);
-	drm_fbdev_cma_set_suspend_unlocked(hdlcd->fbdev, 1);
-
-	hdlcd->state = drm_atomic_helper_suspend(drm);
-	if (IS_ERR(hdlcd->state)) {
-		drm_fbdev_cma_set_suspend_unlocked(hdlcd->fbdev, 0);
-		drm_kms_helper_poll_enable(drm);
-		return PTR_ERR(hdlcd->state);
-	}
-
-	return 0;
+	return drm_mode_config_helper_suspend(drm);
 }
 
 static int __maybe_unused hdlcd_pm_resume(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
-	struct hdlcd_drm_private *hdlcd = drm ? drm->dev_private : NULL;
-
-	if (!hdlcd)
-		return 0;
 
-	drm_atomic_helper_resume(drm, hdlcd->state);
-	drm_fbdev_cma_set_suspend_unlocked(hdlcd->fbdev, 0);
-	drm_kms_helper_poll_enable(drm);
+	drm_mode_config_helper_resume(drm);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/arm/hdlcd_drv.h b/drivers/gpu/drm/arm/hdlcd_drv.h
index 56f34dfff640..fd438d177b64 100644
--- a/drivers/gpu/drm/arm/hdlcd_drv.h
+++ b/drivers/gpu/drm/arm/hdlcd_drv.h
@@ -9,10 +9,8 @@
 struct hdlcd_drm_private {
 	void __iomem			*mmio;
 	struct clk			*clk;
-	struct drm_fbdev_cma		*fbdev;
 	struct drm_crtc			crtc;
 	struct drm_plane		*plane;
-	struct drm_atomic_state		*state;
 #ifdef CONFIG_DEBUG_FS
 	atomic_t buffer_underrun_count;
 	atomic_t bus_error_count;
diff --git a/drivers/gpu/drm/arm/malidp_crtc.c b/drivers/gpu/drm/arm/malidp_crtc.c
index fcc62bc60f6a..ef44202fb43f 100644
--- a/drivers/gpu/drm/arm/malidp_crtc.c
+++ b/drivers/gpu/drm/arm/malidp_crtc.c
@@ -411,6 +411,16 @@ static int malidp_crtc_atomic_check(struct drm_crtc *crtc,
 		}
 	}
 
+	/* If only the writeback routing has changed, we don't need a modeset */
+	if (state->connectors_changed) {
+		u32 old_mask = crtc->state->connector_mask;
+		u32 new_mask = state->connector_mask;
+
+		if ((old_mask ^ new_mask) ==
+		    (1 << drm_connector_index(&malidp->mw_connector.base)))
+			state->connectors_changed = false;
+	}
+
 	ret = malidp_crtc_atomic_check_gamma(crtc, state);
 	ret = ret ? ret : malidp_crtc_atomic_check_ctm(crtc, state);
 	ret = ret ? ret : malidp_crtc_atomic_check_scaling(crtc, state);
diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c
index 0a788d76ed5f..08b5bb219816 100644
--- a/drivers/gpu/drm/arm/malidp_drv.c
+++ b/drivers/gpu/drm/arm/malidp_drv.c
@@ -17,6 +17,7 @@
 #include <linux/of_graph.h>
 #include <linux/of_reserved_mem.h>
 #include <linux/pm_runtime.h>
+#include <linux/debugfs.h>
 
 #include <drm/drmP.h>
 #include <drm/drm_atomic.h>
@@ -31,6 +32,7 @@
 #include <drm/drm_of.h>
 
 #include "malidp_drv.h"
+#include "malidp_mw.h"
 #include "malidp_regs.h"
 #include "malidp_hw.h"
 
@@ -170,14 +172,15 @@ static int malidp_set_and_wait_config_valid(struct drm_device *drm)
 	struct malidp_hw_device *hwdev = malidp->dev;
 	int ret;
 
-	atomic_set(&malidp->config_valid, 0);
-	hwdev->hw->set_config_valid(hwdev);
+	hwdev->hw->set_config_valid(hwdev, 1);
 	/* don't wait for config_valid flag if we are in config mode */
-	if (hwdev->hw->in_config_mode(hwdev))
+	if (hwdev->hw->in_config_mode(hwdev)) {
+		atomic_set(&malidp->config_valid, MALIDP_CONFIG_VALID_DONE);
 		return 0;
+	}
 
 	ret = wait_event_interruptible_timeout(malidp->wq,
-			atomic_read(&malidp->config_valid) == 1,
+			atomic_read(&malidp->config_valid) == MALIDP_CONFIG_VALID_DONE,
 			msecs_to_jiffies(MALIDP_CONF_VALID_TIMEOUT));
 
 	return (ret > 0) ? 0 : -ETIMEDOUT;
@@ -216,12 +219,20 @@ static void malidp_atomic_commit_hw_done(struct drm_atomic_state *state)
 static void malidp_atomic_commit_tail(struct drm_atomic_state *state)
 {
 	struct drm_device *drm = state->dev;
+	struct malidp_drm *malidp = drm->dev_private;
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *old_crtc_state;
 	int i;
 
 	pm_runtime_get_sync(drm->dev);
 
+	/*
+	 * set config_valid to a special value to let IRQ handlers
+	 * know that we are updating registers
+	 */
+	atomic_set(&malidp->config_valid, MALIDP_CONFIG_START);
+	malidp->dev->hw->set_config_valid(malidp->dev, 0);
+
 	drm_atomic_helper_commit_modeset_disables(drm, state);
 
 	for_each_old_crtc_in_state(state, crtc, old_crtc_state, i) {
@@ -230,7 +241,9 @@ static void malidp_atomic_commit_tail(struct drm_atomic_state *state)
 		malidp_atomic_commit_se_config(crtc, old_crtc_state);
 	}
 
-	drm_atomic_helper_commit_planes(drm, state, 0);
+	drm_atomic_helper_commit_planes(drm, state, DRM_PLANE_COMMIT_ACTIVE_ONLY);
+
+	malidp_mw_atomic_commit(drm, state);
 
 	drm_atomic_helper_commit_modeset_enables(drm, state);
 
@@ -268,12 +281,18 @@ static int malidp_init(struct drm_device *drm)
 	drm->mode_config.helper_private = &malidp_mode_config_helpers;
 
 	ret = malidp_crtc_init(drm);
-	if (ret) {
-		drm_mode_config_cleanup(drm);
-		return ret;
-	}
+	if (ret)
+		goto crtc_fail;
+
+	ret = malidp_mw_connector_init(drm);
+	if (ret)
+		goto crtc_fail;
 
 	return 0;
+
+crtc_fail:
+	drm_mode_config_cleanup(drm);
+	return ret;
 }
 
 static void malidp_fini(struct drm_device *drm)
@@ -285,6 +304,8 @@ static int malidp_irq_init(struct platform_device *pdev)
 {
 	int irq_de, irq_se, ret = 0;
 	struct drm_device *drm = dev_get_drvdata(&pdev->dev);
+	struct malidp_drm *malidp = drm->dev_private;
+	struct malidp_hw_device *hwdev = malidp->dev;
 
 	/* fetch the interrupts from DT */
 	irq_de = platform_get_irq_byname(pdev, "DE");
@@ -304,7 +325,7 @@ static int malidp_irq_init(struct platform_device *pdev)
 
 	ret = malidp_se_irq_init(drm, irq_se);
 	if (ret) {
-		malidp_de_irq_fini(drm);
+		malidp_de_irq_fini(hwdev);
 		return ret;
 	}
 
@@ -326,6 +347,106 @@ static int malidp_dumb_create(struct drm_file *file_priv,
 	return drm_gem_cma_dumb_create_internal(file_priv, drm, args);
 }
 
+#ifdef CONFIG_DEBUG_FS
+
+static void malidp_error_stats_init(struct malidp_error_stats *error_stats)
+{
+	error_stats->num_errors = 0;
+	error_stats->last_error_status = 0;
+	error_stats->last_error_vblank = -1;
+}
+
+void malidp_error(struct malidp_drm *malidp,
+		  struct malidp_error_stats *error_stats, u32 status,
+		  u64 vblank)
+{
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&malidp->errors_lock, irqflags);
+	error_stats->last_error_status = status;
+	error_stats->last_error_vblank = vblank;
+	error_stats->num_errors++;
+	spin_unlock_irqrestore(&malidp->errors_lock, irqflags);
+}
+
+void malidp_error_stats_dump(const char *prefix,
+			     struct malidp_error_stats error_stats,
+			     struct seq_file *m)
+{
+	seq_printf(m, "[%s] num_errors : %d\n", prefix,
+		   error_stats.num_errors);
+	seq_printf(m, "[%s] last_error_status  : 0x%08x\n", prefix,
+		   error_stats.last_error_status);
+	seq_printf(m, "[%s] last_error_vblank : %lld\n", prefix,
+		   error_stats.last_error_vblank);
+}
+
+static int malidp_show_stats(struct seq_file *m, void *arg)
+{
+	struct drm_device *drm = m->private;
+	struct malidp_drm *malidp = drm->dev_private;
+	unsigned long irqflags;
+	struct malidp_error_stats de_errors, se_errors;
+
+	spin_lock_irqsave(&malidp->errors_lock, irqflags);
+	de_errors = malidp->de_errors;
+	se_errors = malidp->se_errors;
+	spin_unlock_irqrestore(&malidp->errors_lock, irqflags);
+	malidp_error_stats_dump("DE", de_errors, m);
+	malidp_error_stats_dump("SE", se_errors, m);
+	return 0;
+}
+
+static int malidp_debugfs_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, malidp_show_stats, inode->i_private);
+}
+
+static ssize_t malidp_debugfs_write(struct file *file, const char __user *ubuf,
+				    size_t len, loff_t *offp)
+{
+	struct seq_file *m = file->private_data;
+	struct drm_device *drm = m->private;
+	struct malidp_drm *malidp = drm->dev_private;
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&malidp->errors_lock, irqflags);
+	malidp_error_stats_init(&malidp->de_errors);
+	malidp_error_stats_init(&malidp->se_errors);
+	spin_unlock_irqrestore(&malidp->errors_lock, irqflags);
+	return len;
+}
+
+static const struct file_operations malidp_debugfs_fops = {
+	.owner = THIS_MODULE,
+	.open = malidp_debugfs_open,
+	.read = seq_read,
+	.write = malidp_debugfs_write,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int malidp_debugfs_init(struct drm_minor *minor)
+{
+	struct malidp_drm *malidp = minor->dev->dev_private;
+	struct dentry *dentry = NULL;
+
+	malidp_error_stats_init(&malidp->de_errors);
+	malidp_error_stats_init(&malidp->se_errors);
+	spin_lock_init(&malidp->errors_lock);
+	dentry = debugfs_create_file("debug",
+				     S_IRUGO | S_IWUSR,
+				     minor->debugfs_root, minor->dev,
+				     &malidp_debugfs_fops);
+	if (!dentry) {
+		DRM_ERROR("Cannot create debug file\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+#endif //CONFIG_DEBUG_FS
+
 static struct drm_driver malidp_driver = {
 	.driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC |
 			   DRIVER_PRIME,
@@ -342,6 +463,9 @@ static struct drm_driver malidp_driver = {
 	.gem_prime_vmap = drm_gem_cma_prime_vmap,
 	.gem_prime_vunmap = drm_gem_cma_prime_vunmap,
 	.gem_prime_mmap = drm_gem_cma_prime_mmap,
+#ifdef CONFIG_DEBUG_FS
+	.debugfs_init = malidp_debugfs_init,
+#endif
 	.fops = &fops,
 	.name = "mali-dp",
 	.desc = "ARM Mali Display Processor driver",
@@ -458,6 +582,8 @@ static int malidp_runtime_pm_suspend(struct device *dev)
 	/* we can only suspend if the hardware is in config mode */
 	WARN_ON(!hwdev->hw->in_config_mode(hwdev));
 
+	malidp_se_irq_fini(hwdev);
+	malidp_de_irq_fini(hwdev);
 	hwdev->pm_suspended = true;
 	clk_disable_unprepare(hwdev->mclk);
 	clk_disable_unprepare(hwdev->aclk);
@@ -476,6 +602,8 @@ static int malidp_runtime_pm_resume(struct device *dev)
 	clk_prepare_enable(hwdev->aclk);
 	clk_prepare_enable(hwdev->mclk);
 	hwdev->pm_suspended = false;
+	malidp_de_irq_hw_init(hwdev);
+	malidp_se_irq_hw_init(hwdev);
 
 	return 0;
 }
@@ -488,6 +616,7 @@ static int malidp_bind(struct device *dev)
 	struct malidp_hw_device *hwdev;
 	struct platform_device *pdev = to_platform_device(dev);
 	struct of_device_id const *dev_id;
+	struct drm_encoder *encoder;
 	/* number of lines for the R, G and B output */
 	u8 output_width[MAX_OUTPUT_CHANNELS];
 	int ret = 0, i;
@@ -587,8 +716,9 @@ static int malidp_bind(struct device *dev)
 	for (i = 0; i < MAX_OUTPUT_CHANNELS; i++)
 		out_depth = (out_depth << 8) | (output_width[i] & 0xf);
 	malidp_hw_write(hwdev, out_depth, hwdev->hw->map.out_depth_base);
+	hwdev->output_color_depth = out_depth;
 
-	atomic_set(&malidp->config_valid, 0);
+	atomic_set(&malidp->config_valid, MALIDP_CONFIG_VALID_INIT);
 	init_waitqueue_head(&malidp->wq);
 
 	ret = malidp_init(drm);
@@ -608,6 +738,15 @@ static int malidp_bind(struct device *dev)
 		goto bind_fail;
 	}
 
+	/* We expect to have a maximum of two encoders one for the actual
+	 * display and a virtual one for the writeback connector
+	 */
+	WARN_ON(drm->mode_config.num_encoder > 2);
+	list_for_each_entry(encoder, &drm->mode_config.encoder_list, head) {
+		encoder->possible_clones =
+				(1 << drm->mode_config.num_encoder) -  1;
+	}
+
 	ret = malidp_irq_init(pdev);
 	if (ret < 0)
 		goto irq_init_fail;
@@ -641,8 +780,8 @@ register_fail:
 fbdev_fail:
 	pm_runtime_get_sync(dev);
 vblank_fail:
-	malidp_se_irq_fini(drm);
-	malidp_de_irq_fini(drm);
+	malidp_se_irq_fini(hwdev);
+	malidp_de_irq_fini(hwdev);
 	drm->irq_enabled = false;
 irq_init_fail:
 	drm_atomic_helper_shutdown(drm);
@@ -672,14 +811,15 @@ static void malidp_unbind(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
 	struct malidp_drm *malidp = drm->dev_private;
+	struct malidp_hw_device *hwdev = malidp->dev;
 
 	drm_dev_unregister(drm);
 	drm_fb_cma_fbdev_fini(drm);
 	drm_kms_helper_poll_fini(drm);
 	pm_runtime_get_sync(dev);
 	drm_crtc_vblank_off(&malidp->crtc);
-	malidp_se_irq_fini(drm);
-	malidp_de_irq_fini(drm);
+	malidp_se_irq_fini(hwdev);
+	malidp_de_irq_fini(hwdev);
 	drm->irq_enabled = false;
 	drm_atomic_helper_shutdown(drm);
 	component_unbind_all(dev, drm);
@@ -752,8 +892,25 @@ static int __maybe_unused malidp_pm_resume(struct device *dev)
 	return 0;
 }
 
+static int __maybe_unused malidp_pm_suspend_late(struct device *dev)
+{
+	if (!pm_runtime_status_suspended(dev)) {
+		malidp_runtime_pm_suspend(dev);
+		pm_runtime_set_suspended(dev);
+	}
+	return 0;
+}
+
+static int __maybe_unused malidp_pm_resume_early(struct device *dev)
+{
+	malidp_runtime_pm_resume(dev);
+	pm_runtime_set_active(dev);
+	return 0;
+}
+
 static const struct dev_pm_ops malidp_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(malidp_pm_suspend, malidp_pm_resume) \
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(malidp_pm_suspend_late, malidp_pm_resume_early) \
 	SET_RUNTIME_PM_OPS(malidp_runtime_pm_suspend, malidp_runtime_pm_resume, NULL)
 };
 
diff --git a/drivers/gpu/drm/arm/malidp_drv.h b/drivers/gpu/drm/arm/malidp_drv.h
index c70989b93387..e3eb0cb1f385 100644
--- a/drivers/gpu/drm/arm/malidp_drv.h
+++ b/drivers/gpu/drm/arm/malidp_drv.h
@@ -13,18 +13,38 @@
 #ifndef __MALIDP_DRV_H__
 #define __MALIDP_DRV_H__
 
+#include <drm/drm_writeback.h>
+#include <drm/drm_encoder.h>
 #include <linux/mutex.h>
 #include <linux/wait.h>
+#include <linux/spinlock.h>
 #include <drm/drmP.h>
 #include "malidp_hw.h"
 
+#define MALIDP_CONFIG_VALID_INIT	0
+#define MALIDP_CONFIG_VALID_DONE	1
+#define MALIDP_CONFIG_START		0xd0
+
+struct malidp_error_stats {
+	s32 num_errors;
+	u32 last_error_status;
+	s64 last_error_vblank;
+};
+
 struct malidp_drm {
 	struct malidp_hw_device *dev;
 	struct drm_crtc crtc;
+	struct drm_writeback_connector mw_connector;
 	wait_queue_head_t wq;
 	struct drm_pending_vblank_event *event;
 	atomic_t config_valid;
 	u32 core_id;
+#ifdef CONFIG_DEBUG_FS
+	struct malidp_error_stats de_errors;
+	struct malidp_error_stats se_errors;
+	/* Protects errors stats */
+	spinlock_t errors_lock;
+#endif
 };
 
 #define crtc_to_malidp_device(x) container_of(x, struct malidp_drm, crtc)
@@ -62,6 +82,12 @@ struct malidp_crtc_state {
 int malidp_de_planes_init(struct drm_device *drm);
 int malidp_crtc_init(struct drm_device *drm);
 
+#ifdef CONFIG_DEBUG_FS
+void malidp_error(struct malidp_drm *malidp,
+		  struct malidp_error_stats *error_stats, u32 status,
+		  u64 vblank);
+#endif
+
 /* often used combination of rotational bits */
 #define MALIDP_ROTATED_MASK	(DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_270)
 
diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c
index 069783e715f1..c94a4422e0e9 100644
--- a/drivers/gpu/drm/arm/malidp_hw.c
+++ b/drivers/gpu/drm/arm/malidp_hw.c
@@ -21,15 +21,24 @@
 
 #include "malidp_drv.h"
 #include "malidp_hw.h"
+#include "malidp_mw.h"
+
+enum {
+	MW_NOT_ENABLED = 0,	/* SE writeback not enabled */
+	MW_ONESHOT,		/* SE in one-shot mode for writeback */
+	MW_START,		/* SE started writeback */
+	MW_RESTART,		/* SE will start another writeback after this one */
+	MW_STOP,		/* SE needs to stop after this writeback */
+};
 
 static const struct malidp_format_id malidp500_de_formats[] = {
 	/*    fourcc,   layers supporting the format,     internal id  */
-	{ DRM_FORMAT_ARGB2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  0 },
-	{ DRM_FORMAT_ABGR2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  1 },
+	{ DRM_FORMAT_ARGB2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2 | SE_MEMWRITE,  0 },
+	{ DRM_FORMAT_ABGR2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2 | SE_MEMWRITE,  1 },
 	{ DRM_FORMAT_ARGB8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  2 },
 	{ DRM_FORMAT_ABGR8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  3 },
-	{ DRM_FORMAT_XRGB8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  4 },
-	{ DRM_FORMAT_XBGR8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  5 },
+	{ DRM_FORMAT_XRGB8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2 | SE_MEMWRITE,  4 },
+	{ DRM_FORMAT_XBGR8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2 | SE_MEMWRITE,  5 },
 	{ DRM_FORMAT_RGB888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  6 },
 	{ DRM_FORMAT_BGR888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  7 },
 	{ DRM_FORMAT_RGBA5551, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  8 },
@@ -38,7 +47,7 @@ static const struct malidp_format_id malidp500_de_formats[] = {
 	{ DRM_FORMAT_BGR565, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2, 11 },
 	{ DRM_FORMAT_UYVY, DE_VIDEO1, 12 },
 	{ DRM_FORMAT_YUYV, DE_VIDEO1, 13 },
-	{ DRM_FORMAT_NV12, DE_VIDEO1, 14 },
+	{ DRM_FORMAT_NV12, DE_VIDEO1 | SE_MEMWRITE, 14 },
 	{ DRM_FORMAT_YUV420, DE_VIDEO1, 15 },
 };
 
@@ -47,27 +56,27 @@ static const struct malidp_format_id malidp500_de_formats[] = {
 
 #define MALIDP_COMMON_FORMATS \
 	/*    fourcc,   layers supporting the format,      internal id   */ \
-	{ DRM_FORMAT_ARGB2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(0, 0) }, \
-	{ DRM_FORMAT_ABGR2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(0, 1) }, \
-	{ DRM_FORMAT_RGBA1010102, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(0, 2) }, \
-	{ DRM_FORMAT_BGRA1010102, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(0, 3) }, \
+	{ DRM_FORMAT_ARGB2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | SE_MEMWRITE, MALIDP_ID(0, 0) }, \
+	{ DRM_FORMAT_ABGR2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | SE_MEMWRITE, MALIDP_ID(0, 1) }, \
+	{ DRM_FORMAT_RGBA1010102, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | SE_MEMWRITE, MALIDP_ID(0, 2) }, \
+	{ DRM_FORMAT_BGRA1010102, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | SE_MEMWRITE, MALIDP_ID(0, 3) }, \
 	{ DRM_FORMAT_ARGB8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(1, 0) }, \
 	{ DRM_FORMAT_ABGR8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(1, 1) }, \
 	{ DRM_FORMAT_RGBA8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(1, 2) }, \
 	{ DRM_FORMAT_BGRA8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(1, 3) }, \
-	{ DRM_FORMAT_XRGB8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(2, 0) }, \
-	{ DRM_FORMAT_XBGR8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(2, 1) }, \
-	{ DRM_FORMAT_RGBX8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(2, 2) }, \
-	{ DRM_FORMAT_BGRX8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(2, 3) }, \
-	{ DRM_FORMAT_RGB888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(3, 0) }, \
-	{ DRM_FORMAT_BGR888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(3, 1) }, \
+	{ DRM_FORMAT_XRGB8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART | SE_MEMWRITE, MALIDP_ID(2, 0) }, \
+	{ DRM_FORMAT_XBGR8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART | SE_MEMWRITE, MALIDP_ID(2, 1) }, \
+	{ DRM_FORMAT_RGBX8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART | SE_MEMWRITE, MALIDP_ID(2, 2) }, \
+	{ DRM_FORMAT_BGRX8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART | SE_MEMWRITE, MALIDP_ID(2, 3) }, \
+	{ DRM_FORMAT_RGB888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | SE_MEMWRITE, MALIDP_ID(3, 0) }, \
+	{ DRM_FORMAT_BGR888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | SE_MEMWRITE, MALIDP_ID(3, 1) }, \
 	{ DRM_FORMAT_RGBA5551, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(4, 0) }, \
 	{ DRM_FORMAT_ABGR1555, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(4, 1) }, \
 	{ DRM_FORMAT_RGB565, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(4, 2) }, \
 	{ DRM_FORMAT_BGR565, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(4, 3) }, \
 	{ DRM_FORMAT_YUYV, DE_VIDEO1 | DE_VIDEO2, MALIDP_ID(5, 2) },	\
 	{ DRM_FORMAT_UYVY, DE_VIDEO1 | DE_VIDEO2, MALIDP_ID(5, 3) },	\
-	{ DRM_FORMAT_NV12, DE_VIDEO1 | DE_VIDEO2, MALIDP_ID(5, 6) },	\
+	{ DRM_FORMAT_NV12, DE_VIDEO1 | DE_VIDEO2 | SE_MEMWRITE, MALIDP_ID(5, 6) },	\
 	{ DRM_FORMAT_YUV420, DE_VIDEO1 | DE_VIDEO2, MALIDP_ID(5, 7) }
 
 static const struct malidp_format_id malidp550_de_formats[] = {
@@ -223,15 +232,20 @@ static bool malidp500_in_config_mode(struct malidp_hw_device *hwdev)
 	return false;
 }
 
-static void malidp500_set_config_valid(struct malidp_hw_device *hwdev)
+static void malidp500_set_config_valid(struct malidp_hw_device *hwdev, u8 value)
 {
-	malidp_hw_setbits(hwdev, MALIDP_CFG_VALID, MALIDP500_CONFIG_VALID);
+	if (value)
+		malidp_hw_setbits(hwdev, MALIDP_CFG_VALID, MALIDP500_CONFIG_VALID);
+	else
+		malidp_hw_clearbits(hwdev, MALIDP_CFG_VALID, MALIDP500_CONFIG_VALID);
 }
 
 static void malidp500_modeset(struct malidp_hw_device *hwdev, struct videomode *mode)
 {
 	u32 val = 0;
 
+	malidp_hw_write(hwdev, hwdev->output_color_depth,
+		hwdev->hw->map.out_depth_base);
 	malidp_hw_clearbits(hwdev, MALIDP500_DC_CLEAR_MASK, MALIDP500_DC_CONTROL);
 	if (mode->flags & DISPLAY_FLAGS_HSYNC_HIGH)
 		val |= MALIDP500_HSYNCPOL;
@@ -368,6 +382,55 @@ static long malidp500_se_calc_mclk(struct malidp_hw_device *hwdev,
 	return ret;
 }
 
+static int malidp500_enable_memwrite(struct malidp_hw_device *hwdev,
+				     dma_addr_t *addrs, s32 *pitches,
+				     int num_planes, u16 w, u16 h, u32 fmt_id)
+{
+	u32 base = MALIDP500_SE_MEMWRITE_BASE;
+	u32 de_base = malidp_get_block_base(hwdev, MALIDP_DE_BLOCK);
+
+	/* enable the scaling engine block */
+	malidp_hw_setbits(hwdev, MALIDP_SCALE_ENGINE_EN, de_base + MALIDP_DE_DISPLAY_FUNC);
+
+	/* restart the writeback if already enabled */
+	if (hwdev->mw_state != MW_NOT_ENABLED)
+		hwdev->mw_state = MW_RESTART;
+	else
+		hwdev->mw_state = MW_START;
+
+	malidp_hw_write(hwdev, fmt_id, base + MALIDP_MW_FORMAT);
+	switch (num_planes) {
+	case 2:
+		malidp_hw_write(hwdev, lower_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_LOW);
+		malidp_hw_write(hwdev, upper_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_HIGH);
+		malidp_hw_write(hwdev, pitches[1], base + MALIDP_MW_P2_STRIDE);
+		/* fall through */
+	case 1:
+		malidp_hw_write(hwdev, lower_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_LOW);
+		malidp_hw_write(hwdev, upper_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_HIGH);
+		malidp_hw_write(hwdev, pitches[0], base + MALIDP_MW_P1_STRIDE);
+		break;
+	default:
+		WARN(1, "Invalid number of planes");
+	}
+
+	malidp_hw_write(hwdev, MALIDP_DE_H_ACTIVE(w) | MALIDP_DE_V_ACTIVE(h),
+			MALIDP500_SE_MEMWRITE_OUT_SIZE);
+	malidp_hw_setbits(hwdev, MALIDP_SE_MEMWRITE_EN, MALIDP500_SE_CONTROL);
+
+	return 0;
+}
+
+static void malidp500_disable_memwrite(struct malidp_hw_device *hwdev)
+{
+	u32 base = malidp_get_block_base(hwdev, MALIDP_DE_BLOCK);
+
+	if (hwdev->mw_state == MW_START || hwdev->mw_state == MW_RESTART)
+		hwdev->mw_state = MW_STOP;
+	malidp_hw_clearbits(hwdev, MALIDP_SE_MEMWRITE_EN, MALIDP500_SE_CONTROL);
+	malidp_hw_clearbits(hwdev, MALIDP_SCALE_ENGINE_EN, base + MALIDP_DE_DISPLAY_FUNC);
+}
+
 static int malidp550_query_hw(struct malidp_hw_device *hwdev)
 {
 	u32 conf = malidp_hw_read(hwdev, MALIDP550_CONFIG_ID);
@@ -447,15 +510,20 @@ static bool malidp550_in_config_mode(struct malidp_hw_device *hwdev)
 	return false;
 }
 
-static void malidp550_set_config_valid(struct malidp_hw_device *hwdev)
+static void malidp550_set_config_valid(struct malidp_hw_device *hwdev, u8 value)
 {
-	malidp_hw_setbits(hwdev, MALIDP_CFG_VALID, MALIDP550_CONFIG_VALID);
+	if (value)
+		malidp_hw_setbits(hwdev, MALIDP_CFG_VALID, MALIDP550_CONFIG_VALID);
+	else
+		malidp_hw_clearbits(hwdev, MALIDP_CFG_VALID, MALIDP550_CONFIG_VALID);
 }
 
 static void malidp550_modeset(struct malidp_hw_device *hwdev, struct videomode *mode)
 {
 	u32 val = MALIDP_DE_DEFAULT_PREFETCH_START;
 
+	malidp_hw_write(hwdev, hwdev->output_color_depth,
+		hwdev->hw->map.out_depth_base);
 	malidp_hw_write(hwdev, val, MALIDP550_DE_CONTROL);
 	/*
 	 * Mali-DP550 and Mali-DP650 encode the background color like this:
@@ -588,6 +656,51 @@ static long malidp550_se_calc_mclk(struct malidp_hw_device *hwdev,
 	return ret;
 }
 
+static int malidp550_enable_memwrite(struct malidp_hw_device *hwdev,
+				     dma_addr_t *addrs, s32 *pitches,
+				     int num_planes, u16 w, u16 h, u32 fmt_id)
+{
+	u32 base = MALIDP550_SE_MEMWRITE_BASE;
+	u32 de_base = malidp_get_block_base(hwdev, MALIDP_DE_BLOCK);
+
+	/* enable the scaling engine block */
+	malidp_hw_setbits(hwdev, MALIDP_SCALE_ENGINE_EN, de_base + MALIDP_DE_DISPLAY_FUNC);
+
+	hwdev->mw_state = MW_ONESHOT;
+
+	malidp_hw_write(hwdev, fmt_id, base + MALIDP_MW_FORMAT);
+	switch (num_planes) {
+	case 2:
+		malidp_hw_write(hwdev, lower_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_LOW);
+		malidp_hw_write(hwdev, upper_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_HIGH);
+		malidp_hw_write(hwdev, pitches[1], base + MALIDP_MW_P2_STRIDE);
+		/* fall through */
+	case 1:
+		malidp_hw_write(hwdev, lower_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_LOW);
+		malidp_hw_write(hwdev, upper_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_HIGH);
+		malidp_hw_write(hwdev, pitches[0], base + MALIDP_MW_P1_STRIDE);
+		break;
+	default:
+		WARN(1, "Invalid number of planes");
+	}
+
+	malidp_hw_write(hwdev, MALIDP_DE_H_ACTIVE(w) | MALIDP_DE_V_ACTIVE(h),
+			MALIDP550_SE_MEMWRITE_OUT_SIZE);
+	malidp_hw_setbits(hwdev, MALIDP550_SE_MEMWRITE_ONESHOT | MALIDP_SE_MEMWRITE_EN,
+			  MALIDP550_SE_CONTROL);
+
+	return 0;
+}
+
+static void malidp550_disable_memwrite(struct malidp_hw_device *hwdev)
+{
+	u32 base = malidp_get_block_base(hwdev, MALIDP_DE_BLOCK);
+
+	malidp_hw_clearbits(hwdev, MALIDP550_SE_MEMWRITE_ONESHOT | MALIDP_SE_MEMWRITE_EN,
+			    MALIDP550_SE_CONTROL);
+	malidp_hw_clearbits(hwdev, MALIDP_SCALE_ENGINE_EN, base + MALIDP_DE_DISPLAY_FUNC);
+}
+
 static int malidp650_query_hw(struct malidp_hw_device *hwdev)
 {
 	u32 conf = malidp_hw_read(hwdev, MALIDP550_CONFIG_ID);
@@ -632,11 +745,18 @@ const struct malidp_hw malidp_device[MALIDP_MAX_DEVICES] = {
 					    MALIDP500_DE_IRQ_VSYNC |
 					    MALIDP500_DE_IRQ_GLOBAL,
 				.vsync_irq = MALIDP500_DE_IRQ_VSYNC,
+				.err_mask = MALIDP_DE_IRQ_UNDERRUN |
+					    MALIDP500_DE_IRQ_AXI_ERR |
+					    MALIDP500_DE_IRQ_SATURATION,
 			},
 			.se_irq_map = {
 				.irq_mask = MALIDP500_SE_IRQ_CONF_MODE |
+					    MALIDP500_SE_IRQ_CONF_VALID |
 					    MALIDP500_SE_IRQ_GLOBAL,
-				.vsync_irq = 0,
+				.vsync_irq = MALIDP500_SE_IRQ_CONF_VALID,
+				.err_mask = MALIDP500_SE_IRQ_INIT_BUSY |
+					    MALIDP500_SE_IRQ_AXI_ERROR |
+					    MALIDP500_SE_IRQ_OVERRUN,
 			},
 			.dc_irq_map = {
 				.irq_mask = MALIDP500_DE_IRQ_CONF_VALID,
@@ -655,6 +775,8 @@ const struct malidp_hw malidp_device[MALIDP_MAX_DEVICES] = {
 		.rotmem_required = malidp500_rotmem_required,
 		.se_set_scaling_coeffs = malidp500_se_set_scaling_coeffs,
 		.se_calc_mclk = malidp500_se_calc_mclk,
+		.enable_memwrite = malidp500_enable_memwrite,
+		.disable_memwrite = malidp500_disable_memwrite,
 		.features = MALIDP_DEVICE_LV_HAS_3_STRIDES,
 	},
 	[MALIDP_550] = {
@@ -670,13 +792,20 @@ const struct malidp_hw malidp_device[MALIDP_MAX_DEVICES] = {
 				.irq_mask = MALIDP_DE_IRQ_UNDERRUN |
 					    MALIDP550_DE_IRQ_VSYNC,
 				.vsync_irq = MALIDP550_DE_IRQ_VSYNC,
+				.err_mask = MALIDP_DE_IRQ_UNDERRUN |
+					    MALIDP550_DE_IRQ_SATURATION |
+					    MALIDP550_DE_IRQ_AXI_ERR,
 			},
 			.se_irq_map = {
-				.irq_mask = MALIDP550_SE_IRQ_EOW |
-					    MALIDP550_SE_IRQ_AXI_ERR,
+				.irq_mask = MALIDP550_SE_IRQ_EOW,
+				.vsync_irq = MALIDP550_SE_IRQ_EOW,
+				.err_mask  = MALIDP550_SE_IRQ_AXI_ERR |
+					     MALIDP550_SE_IRQ_OVR |
+					     MALIDP550_SE_IRQ_IBSY,
 			},
 			.dc_irq_map = {
-				.irq_mask = MALIDP550_DC_IRQ_CONF_VALID,
+				.irq_mask = MALIDP550_DC_IRQ_CONF_VALID |
+					    MALIDP550_DC_IRQ_SE,
 				.vsync_irq = MALIDP550_DC_IRQ_CONF_VALID,
 			},
 			.pixel_formats = malidp550_de_formats,
@@ -692,6 +821,8 @@ const struct malidp_hw malidp_device[MALIDP_MAX_DEVICES] = {
 		.rotmem_required = malidp550_rotmem_required,
 		.se_set_scaling_coeffs = malidp550_se_set_scaling_coeffs,
 		.se_calc_mclk = malidp550_se_calc_mclk,
+		.enable_memwrite = malidp550_enable_memwrite,
+		.disable_memwrite = malidp550_disable_memwrite,
 		.features = 0,
 	},
 	[MALIDP_650] = {
@@ -708,13 +839,25 @@ const struct malidp_hw malidp_device[MALIDP_MAX_DEVICES] = {
 					    MALIDP650_DE_IRQ_DRIFT |
 					    MALIDP550_DE_IRQ_VSYNC,
 				.vsync_irq = MALIDP550_DE_IRQ_VSYNC,
+				.err_mask = MALIDP_DE_IRQ_UNDERRUN |
+					    MALIDP650_DE_IRQ_DRIFT |
+					    MALIDP550_DE_IRQ_SATURATION |
+					    MALIDP550_DE_IRQ_AXI_ERR |
+					    MALIDP650_DE_IRQ_ACEV1 |
+					    MALIDP650_DE_IRQ_ACEV2 |
+					    MALIDP650_DE_IRQ_ACEG |
+					    MALIDP650_DE_IRQ_AXIEP,
 			},
 			.se_irq_map = {
-				.irq_mask = MALIDP550_SE_IRQ_EOW |
-					    MALIDP550_SE_IRQ_AXI_ERR,
+				.irq_mask = MALIDP550_SE_IRQ_EOW,
+				.vsync_irq = MALIDP550_SE_IRQ_EOW,
+				.err_mask = MALIDP550_SE_IRQ_AXI_ERR |
+					    MALIDP550_SE_IRQ_OVR |
+					    MALIDP550_SE_IRQ_IBSY,
 			},
 			.dc_irq_map = {
-				.irq_mask = MALIDP550_DC_IRQ_CONF_VALID,
+				.irq_mask = MALIDP550_DC_IRQ_CONF_VALID |
+					    MALIDP550_DC_IRQ_SE,
 				.vsync_irq = MALIDP550_DC_IRQ_CONF_VALID,
 			},
 			.pixel_formats = malidp550_de_formats,
@@ -730,6 +873,8 @@ const struct malidp_hw malidp_device[MALIDP_MAX_DEVICES] = {
 		.rotmem_required = malidp550_rotmem_required,
 		.se_set_scaling_coeffs = malidp550_se_set_scaling_coeffs,
 		.se_calc_mclk = malidp550_se_calc_mclk,
+		.enable_memwrite = malidp550_enable_memwrite,
+		.disable_memwrite = malidp550_disable_memwrite,
 		.features = 0,
 	},
 };
@@ -791,7 +936,7 @@ static irqreturn_t malidp_de_irq(int irq, void *arg)
 			malidp->event = NULL;
 			spin_unlock(&drm->event_lock);
 		}
-		atomic_set(&malidp->config_valid, 1);
+		atomic_set(&malidp->config_valid, MALIDP_CONFIG_VALID_DONE);
 		ret = IRQ_WAKE_THREAD;
 	}
 
@@ -800,10 +945,17 @@ static irqreturn_t malidp_de_irq(int irq, void *arg)
 		return ret;
 
 	mask = malidp_hw_read(hwdev, MALIDP_REG_MASKIRQ);
-	status &= mask;
+	/* keep the status of the enabled interrupts, plus the error bits */
+	status &= (mask | de->err_mask);
 	if ((status & de->vsync_irq) && malidp->crtc.enabled)
 		drm_crtc_handle_vblank(&malidp->crtc);
 
+#ifdef CONFIG_DEBUG_FS
+	if (status & de->err_mask) {
+		malidp_error(malidp, &malidp->de_errors, status,
+			     drm_crtc_vblank_count(&malidp->crtc));
+	}
+#endif
 	malidp_hw_clear_irq(hwdev, MALIDP_DE_BLOCK, status);
 
 	return (ret == IRQ_NONE) ? IRQ_HANDLED : ret;
@@ -819,6 +971,23 @@ static irqreturn_t malidp_de_irq_thread_handler(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
+void malidp_de_irq_hw_init(struct malidp_hw_device *hwdev)
+{
+	/* ensure interrupts are disabled */
+	malidp_hw_disable_irq(hwdev, MALIDP_DE_BLOCK, 0xffffffff);
+	malidp_hw_clear_irq(hwdev, MALIDP_DE_BLOCK, 0xffffffff);
+	malidp_hw_disable_irq(hwdev, MALIDP_DC_BLOCK, 0xffffffff);
+	malidp_hw_clear_irq(hwdev, MALIDP_DC_BLOCK, 0xffffffff);
+
+	/* first enable the DC block IRQs */
+	malidp_hw_enable_irq(hwdev, MALIDP_DC_BLOCK,
+			     hwdev->hw->map.dc_irq_map.irq_mask);
+
+	/* now enable the DE block IRQs */
+	malidp_hw_enable_irq(hwdev, MALIDP_DE_BLOCK,
+			     hwdev->hw->map.de_irq_map.irq_mask);
+}
+
 int malidp_de_irq_init(struct drm_device *drm, int irq)
 {
 	struct malidp_drm *malidp = drm->dev_private;
@@ -839,22 +1008,13 @@ int malidp_de_irq_init(struct drm_device *drm, int irq)
 		return ret;
 	}
 
-	/* first enable the DC block IRQs */
-	malidp_hw_enable_irq(hwdev, MALIDP_DC_BLOCK,
-			     hwdev->hw->map.dc_irq_map.irq_mask);
-
-	/* now enable the DE block IRQs */
-	malidp_hw_enable_irq(hwdev, MALIDP_DE_BLOCK,
-			     hwdev->hw->map.de_irq_map.irq_mask);
+	malidp_de_irq_hw_init(hwdev);
 
 	return 0;
 }
 
-void malidp_de_irq_fini(struct drm_device *drm)
+void malidp_de_irq_fini(struct malidp_hw_device *hwdev)
 {
-	struct malidp_drm *malidp = drm->dev_private;
-	struct malidp_hw_device *hwdev = malidp->dev;
-
 	malidp_hw_disable_irq(hwdev, MALIDP_DE_BLOCK,
 			      hwdev->hw->map.de_irq_map.irq_mask);
 	malidp_hw_disable_irq(hwdev, MALIDP_DC_BLOCK,
@@ -879,19 +1039,61 @@ static irqreturn_t malidp_se_irq(int irq, void *arg)
 		return IRQ_NONE;
 
 	status = malidp_hw_read(hwdev, hw->map.se_base + MALIDP_REG_STATUS);
-	if (!(status & se->irq_mask))
+	if (!(status & (se->irq_mask | se->err_mask)))
 		return IRQ_NONE;
 
+#ifdef CONFIG_DEBUG_FS
+	if (status & se->err_mask)
+		malidp_error(malidp, &malidp->se_errors, status,
+			     drm_crtc_vblank_count(&malidp->crtc));
+#endif
 	mask = malidp_hw_read(hwdev, hw->map.se_base + MALIDP_REG_MASKIRQ);
-	status = malidp_hw_read(hwdev, hw->map.se_base + MALIDP_REG_STATUS);
 	status &= mask;
-	/* ToDo: status decoding and firing up of VSYNC and page flip events */
+
+	if (status & se->vsync_irq) {
+		switch (hwdev->mw_state) {
+		case MW_ONESHOT:
+			drm_writeback_signal_completion(&malidp->mw_connector, 0);
+			break;
+		case MW_STOP:
+			drm_writeback_signal_completion(&malidp->mw_connector, 0);
+			/* disable writeback after stop */
+			hwdev->mw_state = MW_NOT_ENABLED;
+			break;
+		case MW_RESTART:
+			drm_writeback_signal_completion(&malidp->mw_connector, 0);
+			/* fall through to a new start */
+		case MW_START:
+			/* writeback started, need to emulate one-shot mode */
+			hw->disable_memwrite(hwdev);
+			/*
+			 * only set config_valid HW bit if there is no other update
+			 * in progress or if we raced ahead of the DE IRQ handler
+			 * and config_valid flag will not be update until later
+			 */
+			status = malidp_hw_read(hwdev, hw->map.dc_base + MALIDP_REG_STATUS);
+			if ((atomic_read(&malidp->config_valid) != MALIDP_CONFIG_START) ||
+			    (status & hw->map.dc_irq_map.vsync_irq))
+				hw->set_config_valid(hwdev, 1);
+			break;
+		}
+	}
 
 	malidp_hw_clear_irq(hwdev, MALIDP_SE_BLOCK, status);
 
 	return IRQ_HANDLED;
 }
 
+void malidp_se_irq_hw_init(struct malidp_hw_device *hwdev)
+{
+	/* ensure interrupts are disabled */
+	malidp_hw_disable_irq(hwdev, MALIDP_SE_BLOCK, 0xffffffff);
+	malidp_hw_clear_irq(hwdev, MALIDP_SE_BLOCK, 0xffffffff);
+
+	malidp_hw_enable_irq(hwdev, MALIDP_SE_BLOCK,
+			     hwdev->hw->map.se_irq_map.irq_mask);
+}
+
 static irqreturn_t malidp_se_irq_thread_handler(int irq, void *arg)
 {
 	return IRQ_HANDLED;
@@ -915,17 +1117,14 @@ int malidp_se_irq_init(struct drm_device *drm, int irq)
 		return ret;
 	}
 
-	malidp_hw_enable_irq(hwdev, MALIDP_SE_BLOCK,
-			     hwdev->hw->map.se_irq_map.irq_mask);
+	hwdev->mw_state = MW_NOT_ENABLED;
+	malidp_se_irq_hw_init(hwdev);
 
 	return 0;
 }
 
-void malidp_se_irq_fini(struct drm_device *drm)
+void malidp_se_irq_fini(struct malidp_hw_device *hwdev)
 {
-	struct malidp_drm *malidp = drm->dev_private;
-	struct malidp_hw_device *hwdev = malidp->dev;
-
 	malidp_hw_disable_irq(hwdev, MALIDP_SE_BLOCK,
 			      hwdev->hw->map.se_irq_map.irq_mask);
 }
diff --git a/drivers/gpu/drm/arm/malidp_hw.h b/drivers/gpu/drm/arm/malidp_hw.h
index b5dd6c73ec9f..ad2e96915d44 100644
--- a/drivers/gpu/drm/arm/malidp_hw.h
+++ b/drivers/gpu/drm/arm/malidp_hw.h
@@ -33,6 +33,7 @@ enum {
 	DE_GRAPHICS2 = BIT(2), /* used only in DP500 */
 	DE_VIDEO2 = BIT(3),
 	DE_SMART = BIT(4),
+	SE_MEMWRITE = BIT(5),
 };
 
 struct malidp_format_id {
@@ -52,6 +53,7 @@ struct malidp_format_id {
 struct malidp_irq_map {
 	u32 irq_mask;		/* mask of IRQs that can be enabled in the block */
 	u32 vsync_irq;		/* IRQ bit used for signaling during VSYNC */
+	u32 err_mask;		/* mask of bits that represent errors */
 };
 
 struct malidp_layer {
@@ -151,12 +153,13 @@ struct malidp_hw {
 	bool (*in_config_mode)(struct malidp_hw_device *hwdev);
 
 	/*
-	 * Set configuration valid flag for hardware parameters that can
-	 * be changed outside the configuration mode. Hardware will use
-	 * the new settings when config valid is set after the end of the
-	 * current buffer scanout
+	 * Set/clear configuration valid flag for hardware parameters that can
+	 * be changed outside the configuration mode to the given value.
+	 * Hardware will use the new settings when config valid is set,
+	 * after the end of the current buffer scanout, and will ignore
+	 * any new values for those parameters if config valid flag is cleared
 	 */
-	void (*set_config_valid)(struct malidp_hw_device *hwdev);
+	void (*set_config_valid)(struct malidp_hw_device *hwdev, u8 value);
 
 	/*
 	 * Set a new mode in hardware. Requires the hardware to be in
@@ -177,6 +180,23 @@ struct malidp_hw {
 	long (*se_calc_mclk)(struct malidp_hw_device *hwdev,
 			     struct malidp_se_config *se_config,
 			     struct videomode *vm);
+	/*
+	 * Enable writing to memory the content of the next frame
+	 * @param hwdev - malidp_hw_device structure containing the HW description
+	 * @param addrs - array of addresses for each plane
+	 * @param pitches - array of pitches for each plane
+	 * @param num_planes - number of planes to be written
+	 * @param w - width of the output frame
+	 * @param h - height of the output frame
+	 * @param fmt_id - internal format ID of output buffer
+	 */
+	int (*enable_memwrite)(struct malidp_hw_device *hwdev, dma_addr_t *addrs,
+			       s32 *pitches, int num_planes, u16 w, u16 h, u32 fmt_id);
+
+	/*
+	 * Disable the writing to memory of the next frame's content.
+	 */
+	void (*disable_memwrite)(struct malidp_hw_device *hwdev);
 
 	u8 features;
 };
@@ -210,10 +230,14 @@ struct malidp_hw_device {
 
 	u8 min_line_size;
 	u16 max_line_size;
+	u32 output_color_depth;
 
 	/* track the device PM state */
 	bool pm_suspended;
 
+	/* track the SE memory writeback state */
+	u8 mw_state;
+
 	/* size of memory used for rotating layers, up to two banks available */
 	u32 rotation_memory[2];
 };
@@ -279,9 +303,11 @@ static inline void malidp_hw_enable_irq(struct malidp_hw_device *hwdev,
 }
 
 int malidp_de_irq_init(struct drm_device *drm, int irq);
-void malidp_de_irq_fini(struct drm_device *drm);
+void malidp_se_irq_hw_init(struct malidp_hw_device *hwdev);
+void malidp_de_irq_hw_init(struct malidp_hw_device *hwdev);
+void malidp_de_irq_fini(struct malidp_hw_device *hwdev);
 int malidp_se_irq_init(struct drm_device *drm, int irq);
-void malidp_se_irq_fini(struct drm_device *drm);
+void malidp_se_irq_fini(struct malidp_hw_device *hwdev);
 
 u8 malidp_hw_get_format_id(const struct malidp_hw_regmap *map,
 			   u8 layer_id, u32 format);
diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c
new file mode 100644
index 000000000000..ba6ae66387c9
--- /dev/null
+++ b/drivers/gpu/drm/arm/malidp_mw.c
@@ -0,0 +1,250 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * (C) COPYRIGHT 2016 ARM Limited. All rights reserved.
+ * Author: Brian Starkey <brian.starkey@arm.com>
+ *
+ * ARM Mali DP Writeback connector implementation
+ */
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_fb_cma_helper.h>
+#include <drm/drm_gem_cma_helper.h>
+#include <drm/drmP.h>
+#include <drm/drm_writeback.h>
+
+#include "malidp_drv.h"
+#include "malidp_hw.h"
+#include "malidp_mw.h"
+
+#define to_mw_state(_state) (struct malidp_mw_connector_state *)(_state)
+
+struct malidp_mw_connector_state {
+	struct drm_connector_state base;
+	dma_addr_t addrs[2];
+	s32 pitches[2];
+	u8 format;
+	u8 n_planes;
+};
+
+static int malidp_mw_connector_get_modes(struct drm_connector *connector)
+{
+	struct drm_device *dev = connector->dev;
+
+	return drm_add_modes_noedid(connector, dev->mode_config.max_width,
+				    dev->mode_config.max_height);
+}
+
+static enum drm_mode_status
+malidp_mw_connector_mode_valid(struct drm_connector *connector,
+			       struct drm_display_mode *mode)
+{
+	struct drm_device *dev = connector->dev;
+	struct drm_mode_config *mode_config = &dev->mode_config;
+	int w = mode->hdisplay, h = mode->vdisplay;
+
+	if ((w < mode_config->min_width) || (w > mode_config->max_width))
+		return MODE_BAD_HVALUE;
+
+	if ((h < mode_config->min_height) || (h > mode_config->max_height))
+		return MODE_BAD_VVALUE;
+
+	return MODE_OK;
+}
+
+const struct drm_connector_helper_funcs malidp_mw_connector_helper_funcs = {
+	.get_modes = malidp_mw_connector_get_modes,
+	.mode_valid = malidp_mw_connector_mode_valid,
+};
+
+static void malidp_mw_connector_reset(struct drm_connector *connector)
+{
+	struct malidp_mw_connector_state *mw_state =
+		kzalloc(sizeof(*mw_state), GFP_KERNEL);
+
+	if (connector->state)
+		__drm_atomic_helper_connector_destroy_state(connector->state);
+
+	kfree(connector->state);
+	__drm_atomic_helper_connector_reset(connector, &mw_state->base);
+}
+
+static enum drm_connector_status
+malidp_mw_connector_detect(struct drm_connector *connector, bool force)
+{
+	return connector_status_connected;
+}
+
+static void malidp_mw_connector_destroy(struct drm_connector *connector)
+{
+	drm_connector_cleanup(connector);
+}
+
+static struct drm_connector_state *
+malidp_mw_connector_duplicate_state(struct drm_connector *connector)
+{
+	struct malidp_mw_connector_state *mw_state;
+
+	if (WARN_ON(!connector->state))
+		return NULL;
+
+	mw_state = kzalloc(sizeof(*mw_state), GFP_KERNEL);
+	if (!mw_state)
+		return NULL;
+
+	/* No need to preserve any of our driver-local data */
+	__drm_atomic_helper_connector_duplicate_state(connector, &mw_state->base);
+
+	return &mw_state->base;
+}
+
+static const struct drm_connector_funcs malidp_mw_connector_funcs = {
+	.reset = malidp_mw_connector_reset,
+	.detect = malidp_mw_connector_detect,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = malidp_mw_connector_destroy,
+	.atomic_duplicate_state = malidp_mw_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+};
+
+static int
+malidp_mw_encoder_atomic_check(struct drm_encoder *encoder,
+			       struct drm_crtc_state *crtc_state,
+			       struct drm_connector_state *conn_state)
+{
+	struct malidp_mw_connector_state *mw_state = to_mw_state(conn_state);
+	struct malidp_drm *malidp = encoder->dev->dev_private;
+	struct drm_framebuffer *fb;
+	int i, n_planes;
+
+	if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
+		return 0;
+
+	fb = conn_state->writeback_job->fb;
+	if ((fb->width != crtc_state->mode.hdisplay) ||
+	    (fb->height != crtc_state->mode.vdisplay)) {
+		DRM_DEBUG_KMS("Invalid framebuffer size %ux%u\n",
+				fb->width, fb->height);
+		return -EINVAL;
+	}
+
+	mw_state->format =
+		malidp_hw_get_format_id(&malidp->dev->hw->map, SE_MEMWRITE,
+					fb->format->format);
+	if (mw_state->format == MALIDP_INVALID_FORMAT_ID) {
+		struct drm_format_name_buf format_name;
+
+		DRM_DEBUG_KMS("Invalid pixel format %s\n",
+			      drm_get_format_name(fb->format->format,
+						  &format_name));
+		return -EINVAL;
+	}
+
+	n_planes = drm_format_num_planes(fb->format->format);
+	for (i = 0; i < n_planes; i++) {
+		struct drm_gem_cma_object *obj = drm_fb_cma_get_gem_obj(fb, i);
+		/* memory write buffers are never rotated */
+		u8 alignment = malidp_hw_get_pitch_align(malidp->dev, 0);
+
+		if (fb->pitches[i] & (alignment - 1)) {
+			DRM_DEBUG_KMS("Invalid pitch %u for plane %d\n",
+				      fb->pitches[i], i);
+			return -EINVAL;
+		}
+		mw_state->pitches[i] = fb->pitches[i];
+		mw_state->addrs[i] = obj->paddr + fb->offsets[i];
+	}
+	mw_state->n_planes = n_planes;
+
+	return 0;
+}
+
+static const struct drm_encoder_helper_funcs malidp_mw_encoder_helper_funcs = {
+	.atomic_check = malidp_mw_encoder_atomic_check,
+};
+
+static u32 *get_writeback_formats(struct malidp_drm *malidp, int *n_formats)
+{
+	const struct malidp_hw_regmap *map = &malidp->dev->hw->map;
+	u32 *formats;
+	int n, i;
+
+	formats = kcalloc(map->n_pixel_formats, sizeof(*formats),
+			  GFP_KERNEL);
+	if (!formats)
+		return NULL;
+
+	for (n = 0, i = 0;  i < map->n_pixel_formats; i++) {
+		if (map->pixel_formats[i].layer & SE_MEMWRITE)
+			formats[n++] = map->pixel_formats[i].format;
+	}
+
+	*n_formats = n;
+
+	return formats;
+}
+
+int malidp_mw_connector_init(struct drm_device *drm)
+{
+	struct malidp_drm *malidp = drm->dev_private;
+	u32 *formats;
+	int ret, n_formats;
+
+	if (!malidp->dev->hw->enable_memwrite)
+		return 0;
+
+	malidp->mw_connector.encoder.possible_crtcs = 1 << drm_crtc_index(&malidp->crtc);
+	drm_connector_helper_add(&malidp->mw_connector.base,
+				 &malidp_mw_connector_helper_funcs);
+
+	formats = get_writeback_formats(malidp, &n_formats);
+	if (!formats)
+		return -ENOMEM;
+
+	ret = drm_writeback_connector_init(drm, &malidp->mw_connector,
+					   &malidp_mw_connector_funcs,
+					   &malidp_mw_encoder_helper_funcs,
+					   formats, n_formats);
+	kfree(formats);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+void malidp_mw_atomic_commit(struct drm_device *drm,
+			     struct drm_atomic_state *old_state)
+{
+	struct malidp_drm *malidp = drm->dev_private;
+	struct drm_writeback_connector *mw_conn = &malidp->mw_connector;
+	struct drm_connector_state *conn_state = mw_conn->base.state;
+	struct malidp_hw_device *hwdev = malidp->dev;
+	struct malidp_mw_connector_state *mw_state;
+
+	if (!conn_state)
+		return;
+
+	mw_state = to_mw_state(conn_state);
+
+	if (conn_state->writeback_job && conn_state->writeback_job->fb) {
+		struct drm_framebuffer *fb = conn_state->writeback_job->fb;
+
+		DRM_DEV_DEBUG_DRIVER(drm->dev,
+				     "Enable memwrite %ux%u:%d %pad fmt: %u\n",
+				     fb->width, fb->height,
+				     mw_state->pitches[0],
+				     &mw_state->addrs[0],
+				     mw_state->format);
+
+		drm_writeback_queue_job(mw_conn, conn_state->writeback_job);
+		conn_state->writeback_job = NULL;
+
+		hwdev->hw->enable_memwrite(hwdev, mw_state->addrs,
+					   mw_state->pitches, mw_state->n_planes,
+					   fb->width, fb->height, mw_state->format);
+	} else {
+		DRM_DEV_DEBUG_DRIVER(drm->dev, "Disable memwrite\n");
+		hwdev->hw->disable_memwrite(hwdev);
+	}
+}
diff --git a/drivers/gpu/drm/arm/malidp_mw.h b/drivers/gpu/drm/arm/malidp_mw.h
new file mode 100644
index 000000000000..19a007676a1d
--- /dev/null
+++ b/drivers/gpu/drm/arm/malidp_mw.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * (C) COPYRIGHT 2016 ARM Limited. All rights reserved.
+ * Author: Brian Starkey <brian.starkey@arm.com>
+ *
+ */
+
+#ifndef __MALIDP_MW_H__
+#define __MALIDP_MW_H__
+
+int malidp_mw_connector_init(struct drm_device *drm);
+void malidp_mw_atomic_commit(struct drm_device *drm,
+			     struct drm_atomic_state *old_state);
+#endif
diff --git a/drivers/gpu/drm/arm/malidp_regs.h b/drivers/gpu/drm/arm/malidp_regs.h
index 149024fb4432..3579d36b2a71 100644
--- a/drivers/gpu/drm/arm/malidp_regs.h
+++ b/drivers/gpu/drm/arm/malidp_regs.h
@@ -53,6 +53,8 @@
 #define MALIDP550_DE_IRQ_AXI_ERR		(1 << 16)
 #define MALIDP550_SE_IRQ_EOW			(1 << 0)
 #define MALIDP550_SE_IRQ_AXI_ERR		(1 << 16)
+#define MALIDP550_SE_IRQ_OVR			(1 << 17)
+#define MALIDP550_SE_IRQ_IBSY			(1 << 18)
 #define MALIDP550_DC_IRQ_CONF_VALID		(1 << 0)
 #define MALIDP550_DC_IRQ_CONF_MODE		(1 << 4)
 #define MALIDP550_DC_IRQ_CONF_ACTIVE		(1 << 16)
@@ -60,12 +62,18 @@
 #define MALIDP550_DC_IRQ_SE			(1 << 24)
 
 #define MALIDP650_DE_IRQ_DRIFT			(1 << 4)
+#define MALIDP650_DE_IRQ_ACEV1			(1 << 17)
+#define MALIDP650_DE_IRQ_ACEV2			(1 << 18)
+#define MALIDP650_DE_IRQ_ACEG			(1 << 19)
+#define MALIDP650_DE_IRQ_AXIEP			(1 << 28)
 
 /* bit masks that are common between products */
 #define   MALIDP_CFG_VALID		(1 << 0)
 #define   MALIDP_DISP_FUNC_GAMMA	(1 << 0)
 #define   MALIDP_DISP_FUNC_CADJ		(1 << 4)
 #define   MALIDP_DISP_FUNC_ILACED	(1 << 8)
+#define   MALIDP_SCALE_ENGINE_EN	(1 << 16)
+#define   MALIDP_SE_MEMWRITE_EN		(2 << 5)
 
 /* register offsets for IRQ management */
 #define MALIDP_REG_STATUS		0x00000
@@ -153,6 +161,16 @@
 		(((x) & MALIDP_SE_ENH_LIMIT_MASK) << 16)
 #define   MALIDP_SE_ENH_COEFF0			0x04
 
+
+/* register offsets relative to MALIDP5x0_SE_MEMWRITE_BASE */
+#define MALIDP_MW_FORMAT		0x00000
+#define MALIDP_MW_P1_STRIDE		0x00004
+#define MALIDP_MW_P2_STRIDE		0x00008
+#define MALIDP_MW_P1_PTR_LOW		0x0000c
+#define MALIDP_MW_P1_PTR_HIGH		0x00010
+#define MALIDP_MW_P2_PTR_LOW		0x0002c
+#define MALIDP_MW_P2_PTR_HIGH		0x00030
+
 /* register offsets and bits specific to DP500 */
 #define MALIDP500_ADDR_SPACE_SIZE	0x01000
 #define MALIDP500_DC_BASE		0x00000
@@ -186,7 +204,8 @@
 #define MALIDP500_DE_LG2_PTR_BASE	0x0031c
 #define MALIDP500_SE_BASE		0x00c00
 #define MALIDP500_SE_CONTROL		0x00c0c
-#define MALIDP500_SE_PTR_BASE		0x00e0c
+#define MALIDP500_SE_MEMWRITE_OUT_SIZE	0x00c2c
+#define MALIDP500_SE_MEMWRITE_BASE	0x00e00
 #define MALIDP500_DC_IRQ_BASE		0x00f00
 #define MALIDP500_CONFIG_VALID		0x00f00
 #define MALIDP500_CONFIG_ID		0x00fd4
@@ -217,6 +236,9 @@
 #define MALIDP550_DE_PERF_BASE		0x00500
 #define MALIDP550_SE_BASE		0x08000
 #define MALIDP550_SE_CONTROL		0x08010
+#define   MALIDP550_SE_MEMWRITE_ONESHOT	(1 << 7)
+#define MALIDP550_SE_MEMWRITE_OUT_SIZE	0x08030
+#define MALIDP550_SE_MEMWRITE_BASE	0x08100
 #define MALIDP550_DC_BASE		0x0c000
 #define MALIDP550_DC_CONTROL		0x0c010
 #define   MALIDP550_DC_CONFIG_REQ	(1 << 16)
diff --git a/drivers/gpu/drm/armada/Makefile b/drivers/gpu/drm/armada/Makefile
index ecf25cf9f9f5..9bc3c3213724 100644
--- a/drivers/gpu/drm/armada/Makefile
+++ b/drivers/gpu/drm/armada/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 armada-y	:= armada_crtc.o armada_drv.o armada_fb.o armada_fbdev.o \
-		   armada_gem.o armada_overlay.o armada_trace.o
+		   armada_gem.o armada_overlay.o armada_plane.o armada_trace.o
 armada-y	+= armada_510.o
 armada-$(CONFIG_DEBUG_FS) += armada_debugfs.o
 
diff --git a/drivers/gpu/drm/armada/armada_510.c b/drivers/gpu/drm/armada/armada_510.c
index 41a784f5a5e6..2f7c048c5361 100644
--- a/drivers/gpu/drm/armada/armada_510.c
+++ b/drivers/gpu/drm/armada/armada_510.c
@@ -27,6 +27,10 @@ static int armada510_crtc_init(struct armada_crtc *dcrtc, struct device *dev)
 	/* Lower the watermark so to eliminate jitter at higher bandwidths */
 	armada_updatel(0x20, (1 << 11) | 0xff, dcrtc->base + LCD_CFG_RDREG4F);
 
+	/* Initialise SPU register */
+	writel_relaxed(ADV_HWC32ENABLE | ADV_HWC32ARGB | ADV_HWC32BLEND,
+		       dcrtc->base + LCD_SPU_ADV_REG);
+
 	return 0;
 }
 
@@ -75,9 +79,27 @@ static int armada510_crtc_compute_clock(struct armada_crtc *dcrtc,
 	return 0;
 }
 
+static void armada510_crtc_disable(struct armada_crtc *dcrtc)
+{
+	if (!IS_ERR(dcrtc->clk)) {
+		clk_disable_unprepare(dcrtc->clk);
+		dcrtc->clk = ERR_PTR(-EINVAL);
+	}
+}
+
+static void armada510_crtc_enable(struct armada_crtc *dcrtc,
+	const struct drm_display_mode *mode)
+{
+	if (IS_ERR(dcrtc->clk)) {
+		dcrtc->clk = dcrtc->extclk[0];
+		WARN_ON(clk_prepare_enable(dcrtc->clk));
+	}
+}
+
 const struct armada_variant armada510_ops = {
 	.has_spu_adv_reg = true,
-	.spu_adv_reg = ADV_HWC32ENABLE | ADV_HWC32ARGB | ADV_HWC32BLEND,
 	.init = armada510_crtc_init,
 	.compute_clock = armada510_crtc_compute_clock,
+	.disable = armada510_crtc_disable,
+	.enable = armada510_crtc_enable,
 };
diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 42a40daff132..da9360688b55 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -11,6 +11,7 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <drm/drmP.h>
+#include <drm/drm_atomic.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_atomic_helper.h>
@@ -19,33 +20,9 @@
 #include "armada_fb.h"
 #include "armada_gem.h"
 #include "armada_hw.h"
+#include "armada_plane.h"
 #include "armada_trace.h"
 
-enum csc_mode {
-	CSC_AUTO = 0,
-	CSC_YUV_CCIR601 = 1,
-	CSC_YUV_CCIR709 = 2,
-	CSC_RGB_COMPUTER = 1,
-	CSC_RGB_STUDIO = 2,
-};
-
-static const uint32_t armada_primary_formats[] = {
-	DRM_FORMAT_UYVY,
-	DRM_FORMAT_YUYV,
-	DRM_FORMAT_VYUY,
-	DRM_FORMAT_YVYU,
-	DRM_FORMAT_ARGB8888,
-	DRM_FORMAT_ABGR8888,
-	DRM_FORMAT_XRGB8888,
-	DRM_FORMAT_XBGR8888,
-	DRM_FORMAT_RGB888,
-	DRM_FORMAT_BGR888,
-	DRM_FORMAT_ARGB1555,
-	DRM_FORMAT_ABGR1555,
-	DRM_FORMAT_RGB565,
-	DRM_FORMAT_BGR565,
-};
-
 /*
  * A note about interlacing.  Let's consider HDMI 1920x1080i.
  * The timing parameters we have from X are:
@@ -115,15 +92,13 @@ armada_drm_crtc_update_regs(struct armada_crtc *dcrtc, struct armada_regs *regs)
 	}
 }
 
-#define dpms_blanked(dpms)	((dpms) != DRM_MODE_DPMS_ON)
-
-static void armada_drm_crtc_update(struct armada_crtc *dcrtc)
+static void armada_drm_crtc_update(struct armada_crtc *dcrtc, bool enable)
 {
 	uint32_t dumb_ctrl;
 
 	dumb_ctrl = dcrtc->cfg_dumb_ctrl;
 
-	if (!dpms_blanked(dcrtc->dpms))
+	if (enable)
 		dumb_ctrl |= CFG_DUMB_ENA;
 
 	/*
@@ -132,295 +107,26 @@ static void armada_drm_crtc_update(struct armada_crtc *dcrtc)
 	 * force LCD_D[23:0] to output blank color, overriding the GPIO or
 	 * SPI usage.  So leave it as-is unless in DUMB24_RGB888_0 mode.
 	 */
-	if (dpms_blanked(dcrtc->dpms) &&
-	    (dumb_ctrl & DUMB_MASK) == DUMB24_RGB888_0) {
+	if (!enable && (dumb_ctrl & DUMB_MASK) == DUMB24_RGB888_0) {
 		dumb_ctrl &= ~DUMB_MASK;
 		dumb_ctrl |= DUMB_BLANK;
 	}
 
-	/*
-	 * The documentation doesn't indicate what the normal state of
-	 * the sync signals are.  Sebastian Hesselbart kindly probed
-	 * these signals on his board to determine their state.
-	 *
-	 * The non-inverted state of the sync signals is active high.
-	 * Setting these bits makes the appropriate signal active low.
-	 */
-	if (dcrtc->crtc.mode.flags & DRM_MODE_FLAG_NCSYNC)
-		dumb_ctrl |= CFG_INV_CSYNC;
-	if (dcrtc->crtc.mode.flags & DRM_MODE_FLAG_NHSYNC)
-		dumb_ctrl |= CFG_INV_HSYNC;
-	if (dcrtc->crtc.mode.flags & DRM_MODE_FLAG_NVSYNC)
-		dumb_ctrl |= CFG_INV_VSYNC;
-
-	if (dcrtc->dumb_ctrl != dumb_ctrl) {
-		dcrtc->dumb_ctrl = dumb_ctrl;
-		writel_relaxed(dumb_ctrl, dcrtc->base + LCD_SPU_DUMB_CTRL);
-	}
-}
-
-void armada_drm_plane_calc_addrs(u32 *addrs, struct drm_framebuffer *fb,
-	int x, int y)
-{
-	const struct drm_format_info *format = fb->format;
-	unsigned int num_planes = format->num_planes;
-	u32 addr = drm_fb_obj(fb)->dev_addr;
-	int i;
-
-	if (num_planes > 3)
-		num_planes = 3;
-
-	addrs[0] = addr + fb->offsets[0] + y * fb->pitches[0] +
-		   x * format->cpp[0];
-
-	y /= format->vsub;
-	x /= format->hsub;
-
-	for (i = 1; i < num_planes; i++)
-		addrs[i] = addr + fb->offsets[i] + y * fb->pitches[i] +
-			     x * format->cpp[i];
-	for (; i < 3; i++)
-		addrs[i] = 0;
-}
-
-static unsigned armada_drm_crtc_calc_fb(struct drm_framebuffer *fb,
-	int x, int y, struct armada_regs *regs, bool interlaced)
-{
-	unsigned pitch = fb->pitches[0];
-	u32 addrs[3], addr_odd, addr_even;
-	unsigned i = 0;
-
-	DRM_DEBUG_DRIVER("pitch %u x %d y %d bpp %d\n",
-		pitch, x, y, fb->format->cpp[0] * 8);
-
-	armada_drm_plane_calc_addrs(addrs, fb, x, y);
-
-	addr_odd = addr_even = addrs[0];
-
-	if (interlaced) {
-		addr_even += pitch;
-		pitch *= 2;
-	}
-
-	/* write offset, base, and pitch */
-	armada_reg_queue_set(regs, i, addr_odd, LCD_CFG_GRA_START_ADDR0);
-	armada_reg_queue_set(regs, i, addr_even, LCD_CFG_GRA_START_ADDR1);
-	armada_reg_queue_mod(regs, i, pitch, 0xffff, LCD_CFG_GRA_PITCH);
-
-	return i;
-}
-
-static void armada_drm_plane_work_call(struct armada_crtc *dcrtc,
-	struct armada_plane_work *work,
-	void (*fn)(struct armada_crtc *, struct armada_plane_work *))
-{
-	struct armada_plane *dplane = drm_to_armada_plane(work->plane);
-	struct drm_pending_vblank_event *event;
-	struct drm_framebuffer *fb;
-
-	if (fn)
-		fn(dcrtc, work);
-	drm_crtc_vblank_put(&dcrtc->crtc);
-
-	event = work->event;
-	fb = work->old_fb;
-	if (event || fb) {
-		struct drm_device *dev = dcrtc->crtc.dev;
-		unsigned long flags;
-
-		spin_lock_irqsave(&dev->event_lock, flags);
-		if (event)
-			drm_crtc_send_vblank_event(&dcrtc->crtc, event);
-		if (fb)
-			__armada_drm_queue_unref_work(dev, fb);
-		spin_unlock_irqrestore(&dev->event_lock, flags);
-	}
-
-	if (work->need_kfree)
-		kfree(work);
-
-	wake_up(&dplane->frame_wait);
-}
-
-static void armada_drm_plane_work_run(struct armada_crtc *dcrtc,
-	struct drm_plane *plane)
-{
-	struct armada_plane *dplane = drm_to_armada_plane(plane);
-	struct armada_plane_work *work = xchg(&dplane->work, NULL);
-
-	/* Handle any pending frame work. */
-	if (work)
-		armada_drm_plane_work_call(dcrtc, work, work->fn);
-}
-
-int armada_drm_plane_work_queue(struct armada_crtc *dcrtc,
-	struct armada_plane_work *work)
-{
-	struct armada_plane *plane = drm_to_armada_plane(work->plane);
-	int ret;
-
-	ret = drm_crtc_vblank_get(&dcrtc->crtc);
-	if (ret)
-		return ret;
-
-	ret = cmpxchg(&plane->work, NULL, work) ? -EBUSY : 0;
-	if (ret)
-		drm_crtc_vblank_put(&dcrtc->crtc);
-
-	return ret;
-}
-
-int armada_drm_plane_work_wait(struct armada_plane *plane, long timeout)
-{
-	return wait_event_timeout(plane->frame_wait, !plane->work, timeout);
-}
-
-void armada_drm_plane_work_cancel(struct armada_crtc *dcrtc,
-	struct armada_plane *dplane)
-{
-	struct armada_plane_work *work = xchg(&dplane->work, NULL);
-
-	if (work)
-		armada_drm_plane_work_call(dcrtc, work, work->cancel);
-}
-
-static void armada_drm_crtc_complete_frame_work(struct armada_crtc *dcrtc,
-	struct armada_plane_work *work)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&dcrtc->irq_lock, flags);
-	armada_drm_crtc_update_regs(dcrtc, work->regs);
-	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
-}
-
-static void armada_drm_crtc_complete_disable_work(struct armada_crtc *dcrtc,
-	struct armada_plane_work *work)
-{
-	unsigned long flags;
-
-	if (dcrtc->plane == work->plane)
-		dcrtc->plane = NULL;
-
-	spin_lock_irqsave(&dcrtc->irq_lock, flags);
-	armada_drm_crtc_update_regs(dcrtc, work->regs);
-	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
-}
-
-static struct armada_plane_work *
-armada_drm_crtc_alloc_plane_work(struct drm_plane *plane)
-{
-	struct armada_plane_work *work;
-	int i = 0;
-
-	work = kzalloc(sizeof(*work), GFP_KERNEL);
-	if (!work)
-		return NULL;
-
-	work->plane = plane;
-	work->fn = armada_drm_crtc_complete_frame_work;
-	work->need_kfree = true;
-	armada_reg_queue_end(work->regs, i);
-
-	return work;
-}
-
-static void armada_drm_crtc_finish_fb(struct armada_crtc *dcrtc,
-	struct drm_framebuffer *fb, bool force)
-{
-	struct armada_plane_work *work;
-
-	if (!fb)
-		return;
-
-	if (force) {
-		/* Display is disabled, so just drop the old fb */
-		drm_framebuffer_put(fb);
-		return;
-	}
-
-	work = armada_drm_crtc_alloc_plane_work(dcrtc->crtc.primary);
-	if (work) {
-		work->old_fb = fb;
-
-		if (armada_drm_plane_work_queue(dcrtc, work) == 0)
-			return;
-
-		kfree(work);
-	}
-
-	/*
-	 * Oops - just drop the reference immediately and hope for
-	 * the best.  The worst that will happen is the buffer gets
-	 * reused before it has finished being displayed.
-	 */
-	drm_framebuffer_put(fb);
+	armada_updatel(dumb_ctrl,
+		       ~(CFG_INV_CSYNC | CFG_INV_HSYNC | CFG_INV_VSYNC),
+		       dcrtc->base + LCD_SPU_DUMB_CTRL);
 }
 
-static void armada_drm_vblank_off(struct armada_crtc *dcrtc)
-{
-	/*
-	 * Tell the DRM core that vblank IRQs aren't going to happen for
-	 * a while.  This cleans up any pending vblank events for us.
-	 */
-	drm_crtc_vblank_off(&dcrtc->crtc);
-	armada_drm_plane_work_run(dcrtc, dcrtc->crtc.primary);
-}
-
-/* The mode_config.mutex will be held for this call */
-static void armada_drm_crtc_dpms(struct drm_crtc *crtc, int dpms)
-{
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-
-	if (dpms_blanked(dcrtc->dpms) != dpms_blanked(dpms)) {
-		if (dpms_blanked(dpms))
-			armada_drm_vblank_off(dcrtc);
-		else if (!IS_ERR(dcrtc->clk))
-			WARN_ON(clk_prepare_enable(dcrtc->clk));
-		dcrtc->dpms = dpms;
-		armada_drm_crtc_update(dcrtc);
-		if (!dpms_blanked(dpms))
-			drm_crtc_vblank_on(&dcrtc->crtc);
-		else if (!IS_ERR(dcrtc->clk))
-			clk_disable_unprepare(dcrtc->clk);
-	} else if (dcrtc->dpms != dpms) {
-		dcrtc->dpms = dpms;
-	}
-}
-
-/*
- * Prepare for a mode set.  Turn off overlay to ensure that we don't end
- * up with the overlay size being bigger than the active screen size.
- * We rely upon X refreshing this state after the mode set has completed.
- *
- * The mode_config.mutex will be held for this call
- */
-static void armada_drm_crtc_prepare(struct drm_crtc *crtc)
-{
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	struct drm_plane *plane;
-
-	/*
-	 * If we have an overlay plane associated with this CRTC, disable
-	 * it before the modeset to avoid its coordinates being outside
-	 * the new mode parameters.
-	 */
-	plane = dcrtc->plane;
-	if (plane) {
-		drm_plane_force_disable(plane);
-		WARN_ON(!armada_drm_plane_work_wait(drm_to_armada_plane(plane),
-						    HZ));
-	}
-}
-
-/* The mode_config.mutex will be held for this call */
-static void armada_drm_crtc_commit(struct drm_crtc *crtc)
+static void armada_drm_crtc_queue_state_event(struct drm_crtc *crtc)
 {
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	struct drm_pending_vblank_event *event;
 
-	if (dcrtc->dpms != DRM_MODE_DPMS_ON) {
-		dcrtc->dpms = DRM_MODE_DPMS_ON;
-		armada_drm_crtc_update(dcrtc);
+	/* If we have an event, we need vblank events enabled */
+	event = xchg(&crtc->state->event, NULL);
+	if (event) {
+		WARN_ON(drm_crtc_vblank_get(crtc) != 0);
+		dcrtc->event = event;
 	}
 }
 
@@ -465,8 +171,8 @@ static void armada_drm_crtc_enable_irq(struct armada_crtc *dcrtc, u32 mask)
 
 static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat)
 {
+	struct drm_pending_vblank_event *event;
 	void __iomem *base = dcrtc->base;
-	struct drm_plane *ovl_plane;
 
 	if (stat & DMA_FF_UNDERFLOW)
 		DRM_ERROR("video underflow on crtc %u\n", dcrtc->num);
@@ -476,10 +182,6 @@ static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat)
 	if (stat & VSYNC_IRQ)
 		drm_crtc_handle_vblank(&dcrtc->crtc);
 
-	ovl_plane = dcrtc->plane;
-	if (ovl_plane)
-		armada_drm_plane_work_run(dcrtc, ovl_plane);
-
 	spin_lock(&dcrtc->irq_lock);
 	if (stat & GRA_FRAME_IRQ && dcrtc->interlaced) {
 		int i = stat & GRA_FRAME_IRQ0 ? 0 : 1;
@@ -495,22 +197,35 @@ static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat)
 		writel_relaxed(val, base + LCD_SPU_ADV_REG);
 	}
 
-	if (stat & DUMB_FRAMEDONE && dcrtc->cursor_update) {
-		writel_relaxed(dcrtc->cursor_hw_pos,
-			       base + LCD_SPU_HWC_OVSA_HPXL_VLN);
-		writel_relaxed(dcrtc->cursor_hw_sz,
-			       base + LCD_SPU_HWC_HPXL_VLN);
-		armada_updatel(CFG_HWC_ENA,
-			       CFG_HWC_ENA | CFG_HWC_1BITMOD | CFG_HWC_1BITENA,
-			       base + LCD_SPU_DMA_CTRL0);
-		dcrtc->cursor_update = false;
+	if (stat & dcrtc->irq_ena & DUMB_FRAMEDONE) {
+		if (dcrtc->update_pending) {
+			armada_drm_crtc_update_regs(dcrtc, dcrtc->regs);
+			dcrtc->update_pending = false;
+		}
+		if (dcrtc->cursor_update) {
+			writel_relaxed(dcrtc->cursor_hw_pos,
+				       base + LCD_SPU_HWC_OVSA_HPXL_VLN);
+			writel_relaxed(dcrtc->cursor_hw_sz,
+				       base + LCD_SPU_HWC_HPXL_VLN);
+			armada_updatel(CFG_HWC_ENA,
+				       CFG_HWC_ENA | CFG_HWC_1BITMOD |
+				       CFG_HWC_1BITENA,
+				       base + LCD_SPU_DMA_CTRL0);
+			dcrtc->cursor_update = false;
+		}
 		armada_drm_crtc_disable_irq(dcrtc, DUMB_FRAMEDONE_ENA);
 	}
-
 	spin_unlock(&dcrtc->irq_lock);
 
-	if (stat & GRA_FRAME_IRQ)
-		armada_drm_plane_work_run(dcrtc, dcrtc->crtc.primary);
+	if (stat & VSYNC_IRQ && !dcrtc->update_pending) {
+		event = xchg(&dcrtc->event, NULL);
+		if (event) {
+			spin_lock(&dcrtc->crtc.dev->event_lock);
+			drm_crtc_send_vblank_event(&dcrtc->crtc, event);
+			spin_unlock(&dcrtc->crtc.dev->event_lock);
+			drm_crtc_vblank_put(&dcrtc->crtc);
+		}
+	}
 }
 
 static irqreturn_t armada_drm_irq(int irq, void *arg)
@@ -537,107 +252,16 @@ static irqreturn_t armada_drm_irq(int irq, void *arg)
 	return IRQ_NONE;
 }
 
-static uint32_t armada_drm_crtc_calculate_csc(struct armada_crtc *dcrtc)
-{
-	struct drm_display_mode *adj = &dcrtc->crtc.mode;
-	uint32_t val = 0;
-
-	if (dcrtc->csc_yuv_mode == CSC_YUV_CCIR709)
-		val |= CFG_CSC_YUV_CCIR709;
-	if (dcrtc->csc_rgb_mode == CSC_RGB_STUDIO)
-		val |= CFG_CSC_RGB_STUDIO;
-
-	/*
-	 * In auto mode, set the colorimetry, based upon the HDMI spec.
-	 * 1280x720p, 1920x1080p and 1920x1080i use ITU709, others use
-	 * ITU601.  It may be more appropriate to set this depending on
-	 * the source - but what if the graphic frame is YUV and the
-	 * video frame is RGB?
-	 */
-	if ((adj->hdisplay == 1280 && adj->vdisplay == 720 &&
-	     !(adj->flags & DRM_MODE_FLAG_INTERLACE)) ||
-	    (adj->hdisplay == 1920 && adj->vdisplay == 1080)) {
-		if (dcrtc->csc_yuv_mode == CSC_AUTO)
-			val |= CFG_CSC_YUV_CCIR709;
-	}
-
-	/*
-	 * We assume we're connected to a TV-like device, so the YUV->RGB
-	 * conversion should produce a limited range.  We should set this
-	 * depending on the connectors attached to this CRTC, and what
-	 * kind of device they report being connected.
-	 */
-	if (dcrtc->csc_rgb_mode == CSC_AUTO)
-		val |= CFG_CSC_RGB_STUDIO;
-
-	return val;
-}
-
-static void armada_drm_gra_plane_regs(struct armada_regs *regs,
-	struct drm_framebuffer *fb, struct armada_plane_state *state,
-	int x, int y, bool interlaced)
-{
-	unsigned int i;
-	u32 ctrl0;
-
-	i = armada_drm_crtc_calc_fb(fb, x, y, regs, interlaced);
-	armada_reg_queue_set(regs, i, state->dst_yx, LCD_SPU_GRA_OVSA_HPXL_VLN);
-	armada_reg_queue_set(regs, i, state->src_hw, LCD_SPU_GRA_HPXL_VLN);
-	armada_reg_queue_set(regs, i, state->dst_hw, LCD_SPU_GZM_HPXL_VLN);
-
-	ctrl0 = state->ctrl0;
-	if (interlaced)
-		ctrl0 |= CFG_GRA_FTOGGLE;
-
-	armada_reg_queue_mod(regs, i, ctrl0, CFG_GRAFORMAT |
-			     CFG_GRA_MOD(CFG_SWAPRB | CFG_SWAPUV |
-					 CFG_SWAPYU | CFG_YUV2RGB) |
-			     CFG_PALETTE_ENA | CFG_GRA_FTOGGLE |
-			     CFG_GRA_HSMOOTH | CFG_GRA_ENA,
-			     LCD_SPU_DMA_CTRL0);
-	armada_reg_queue_end(regs, i);
-}
-
-static void armada_drm_primary_set(struct drm_crtc *crtc,
-	struct drm_plane *plane, int x, int y)
-{
-	struct armada_plane_state *state = &drm_to_armada_plane(plane)->state;
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	struct armada_regs regs[8];
-	bool interlaced = dcrtc->interlaced;
-
-	armada_drm_gra_plane_regs(regs, plane->fb, state, x, y, interlaced);
-	armada_drm_crtc_update_regs(dcrtc, regs);
-}
-
 /* The mode_config.mutex will be held for this call */
-static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
-	struct drm_display_mode *mode, struct drm_display_mode *adj,
-	int x, int y, struct drm_framebuffer *old_fb)
+static void armada_drm_crtc_mode_set_nofb(struct drm_crtc *crtc)
 {
+	struct drm_display_mode *adj = &crtc->state->adjusted_mode;
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
 	struct armada_regs regs[17];
 	uint32_t lm, rm, tm, bm, val, sclk;
 	unsigned long flags;
 	unsigned i;
-	bool interlaced;
-
-	drm_framebuffer_get(crtc->primary->fb);
-
-	interlaced = !!(adj->flags & DRM_MODE_FLAG_INTERLACE);
-
-	val = CFG_GRA_ENA;
-	val |= CFG_GRA_FMT(drm_fb_to_armada_fb(dcrtc->crtc.primary->fb)->fmt);
-	val |= CFG_GRA_MOD(drm_fb_to_armada_fb(dcrtc->crtc.primary->fb)->mod);
-
-	if (drm_fb_to_armada_fb(dcrtc->crtc.primary->fb)->fmt > CFG_420)
-		val |= CFG_PALETTE_ENA;
-
-	drm_to_armada_plane(crtc->primary)->state.ctrl0 = val;
-	drm_to_armada_plane(crtc->primary)->state.src_hw =
-	drm_to_armada_plane(crtc->primary)->state.dst_hw =
-		adj->crtc_vdisplay << 16 | adj->crtc_hdisplay;
-	drm_to_armada_plane(crtc->primary)->state.dst_yx = 0;
+	bool interlaced = !!(adj->flags & DRM_MODE_FLAG_INTERLACE);
 
 	i = 0;
 	rm = adj->crtc_hsync_start - adj->crtc_hdisplay;
@@ -645,35 +269,15 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
 	bm = adj->crtc_vsync_start - adj->crtc_vdisplay;
 	tm = adj->crtc_vtotal - adj->crtc_vsync_end;
 
-	DRM_DEBUG_DRIVER("H: %d %d %d %d lm %d rm %d\n",
-		adj->crtc_hdisplay,
-		adj->crtc_hsync_start,
-		adj->crtc_hsync_end,
-		adj->crtc_htotal, lm, rm);
-	DRM_DEBUG_DRIVER("V: %d %d %d %d tm %d bm %d\n",
-		adj->crtc_vdisplay,
-		adj->crtc_vsync_start,
-		adj->crtc_vsync_end,
-		adj->crtc_vtotal, tm, bm);
-
-	/* Wait for pending flips to complete */
-	armada_drm_plane_work_wait(drm_to_armada_plane(dcrtc->crtc.primary),
-				   MAX_SCHEDULE_TIMEOUT);
-
-	drm_crtc_vblank_off(crtc);
-
-	val = dcrtc->dumb_ctrl & ~CFG_DUMB_ENA;
-	if (val != dcrtc->dumb_ctrl) {
-		dcrtc->dumb_ctrl = val;
-		writel_relaxed(val, dcrtc->base + LCD_SPU_DUMB_CTRL);
-	}
-
-	/*
-	 * If we are blanked, we would have disabled the clock.  Re-enable
-	 * it so that compute_clock() does the right thing.
-	 */
-	if (!IS_ERR(dcrtc->clk) && dpms_blanked(dcrtc->dpms))
-		WARN_ON(clk_prepare_enable(dcrtc->clk));
+	DRM_DEBUG_KMS("[CRTC:%d:%s] mode " DRM_MODE_FMT "\n",
+		      crtc->base.id, crtc->name,
+		      adj->base.id, adj->name, adj->vrefresh, adj->clock,
+		      adj->crtc_hdisplay, adj->crtc_hsync_start,
+		      adj->crtc_hsync_end, adj->crtc_htotal,
+		      adj->crtc_vdisplay, adj->crtc_vsync_start,
+		      adj->crtc_vsync_end, adj->crtc_vtotal,
+		      adj->type, adj->flags);
+	DRM_DEBUG_KMS("lm %d rm %d tm %d bm %d\n", lm, rm, tm, bm);
 
 	/* Now compute the divider for real */
 	dcrtc->variant->compute_clock(dcrtc, adj, &sclk);
@@ -690,25 +294,20 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
 
 	spin_lock_irqsave(&dcrtc->irq_lock, flags);
 
-	/* Ensure graphic fifo is enabled */
-	armada_reg_queue_mod(regs, i, 0, CFG_PDWN64x66, LCD_SPU_SRAM_PARA1);
-
 	/* Even interlaced/progressive frame */
 	dcrtc->v[1].spu_v_h_total = adj->crtc_vtotal << 16 |
 				    adj->crtc_htotal;
 	dcrtc->v[1].spu_v_porch = tm << 16 | bm;
 	val = adj->crtc_hsync_start;
-	dcrtc->v[1].spu_adv_reg = val << 20 | val | ADV_VSYNCOFFEN |
-		dcrtc->variant->spu_adv_reg;
+	dcrtc->v[1].spu_adv_reg = val << 20 | val | ADV_VSYNCOFFEN;
 
 	if (interlaced) {
 		/* Odd interlaced frame */
+		val -= adj->crtc_htotal / 2;
+		dcrtc->v[0].spu_adv_reg = val << 20 | val | ADV_VSYNCOFFEN;
 		dcrtc->v[0].spu_v_h_total = dcrtc->v[1].spu_v_h_total +
 						(1 << 16);
 		dcrtc->v[0].spu_v_porch = dcrtc->v[1].spu_v_porch + 1;
-		val = adj->crtc_hsync_start - adj->crtc_htotal / 2;
-		dcrtc->v[0].spu_adv_reg = val << 20 | val | ADV_VSYNCOFFEN |
-			dcrtc->variant->spu_adv_reg;
 	} else {
 		dcrtc->v[0] = dcrtc->v[1];
 	}
@@ -721,77 +320,136 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
 	armada_reg_queue_set(regs, i, dcrtc->v[0].spu_v_h_total,
 			   LCD_SPUT_V_H_TOTAL);
 
-	if (dcrtc->variant->has_spu_adv_reg) {
+	if (dcrtc->variant->has_spu_adv_reg)
 		armada_reg_queue_mod(regs, i, dcrtc->v[0].spu_adv_reg,
 				     ADV_VSYNC_L_OFF | ADV_VSYNC_H_OFF |
 				     ADV_VSYNCOFFEN, LCD_SPU_ADV_REG);
-	}
 
 	val = adj->flags & DRM_MODE_FLAG_NVSYNC ? CFG_VSYNC_INV : 0;
 	armada_reg_queue_mod(regs, i, val, CFG_VSYNC_INV, LCD_SPU_DMA_CTRL1);
 
-	val = dcrtc->spu_iopad_ctrl | armada_drm_crtc_calculate_csc(dcrtc);
-	armada_reg_queue_set(regs, i, val, LCD_SPU_IOPAD_CONTROL);
+	/*
+	 * The documentation doesn't indicate what the normal state of
+	 * the sync signals are.  Sebastian Hesselbart kindly probed
+	 * these signals on his board to determine their state.
+	 *
+	 * The non-inverted state of the sync signals is active high.
+	 * Setting these bits makes the appropriate signal active low.
+	 */
+	val = 0;
+	if (adj->flags & DRM_MODE_FLAG_NCSYNC)
+		val |= CFG_INV_CSYNC;
+	if (adj->flags & DRM_MODE_FLAG_NHSYNC)
+		val |= CFG_INV_HSYNC;
+	if (adj->flags & DRM_MODE_FLAG_NVSYNC)
+		val |= CFG_INV_VSYNC;
+	armada_reg_queue_mod(regs, i, val, CFG_INV_CSYNC | CFG_INV_HSYNC |
+			     CFG_INV_VSYNC, LCD_SPU_DUMB_CTRL);
 	armada_reg_queue_end(regs, i);
 
 	armada_drm_crtc_update_regs(dcrtc, regs);
-
-	armada_drm_primary_set(crtc, crtc->primary, x, y);
 	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
+}
 
-	armada_drm_crtc_update(dcrtc);
+static void armada_drm_crtc_atomic_begin(struct drm_crtc *crtc,
+					 struct drm_crtc_state *old_crtc_state)
+{
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
 
-	drm_crtc_vblank_on(crtc);
-	armada_drm_crtc_finish_fb(dcrtc, old_fb, dpms_blanked(dcrtc->dpms));
+	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name);
 
-	return 0;
+	dcrtc->regs_idx = 0;
+	dcrtc->regs = dcrtc->atomic_regs;
 }
 
-/* The mode_config.mutex will be held for this call */
-static int armada_drm_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y,
-	struct drm_framebuffer *old_fb)
+static void armada_drm_crtc_atomic_flush(struct drm_crtc *crtc,
+					 struct drm_crtc_state *old_crtc_state)
 {
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	struct armada_regs regs[4];
-	unsigned i;
 
-	i = armada_drm_crtc_calc_fb(crtc->primary->fb, crtc->x, crtc->y, regs,
-				    dcrtc->interlaced);
-	armada_reg_queue_end(regs, i);
+	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name);
 
-	/* Wait for pending flips to complete */
-	armada_drm_plane_work_wait(drm_to_armada_plane(dcrtc->crtc.primary),
-				   MAX_SCHEDULE_TIMEOUT);
+	armada_reg_queue_end(dcrtc->regs, dcrtc->regs_idx);
 
-	/* Take a reference to the new fb as we're using it */
-	drm_framebuffer_get(crtc->primary->fb);
+	/*
+	 * If we aren't doing a full modeset, then we need to queue
+	 * the event here.
+	 */
+	if (!drm_atomic_crtc_needs_modeset(crtc->state)) {
+		dcrtc->update_pending = true;
+		armada_drm_crtc_queue_state_event(crtc);
+		spin_lock_irq(&dcrtc->irq_lock);
+		armada_drm_crtc_enable_irq(dcrtc, DUMB_FRAMEDONE_ENA);
+		spin_unlock_irq(&dcrtc->irq_lock);
+	} else {
+		spin_lock_irq(&dcrtc->irq_lock);
+		armada_drm_crtc_update_regs(dcrtc, dcrtc->regs);
+		spin_unlock_irq(&dcrtc->irq_lock);
+	}
+}
 
-	/* Update the base in the CRTC */
-	armada_drm_crtc_update_regs(dcrtc, regs);
+static void armada_drm_crtc_atomic_disable(struct drm_crtc *crtc,
+					   struct drm_crtc_state *old_state)
+{
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	struct drm_pending_vblank_event *event;
 
-	/* Drop our previously held reference */
-	armada_drm_crtc_finish_fb(dcrtc, old_fb, dpms_blanked(dcrtc->dpms));
+	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name);
 
-	return 0;
+	drm_crtc_vblank_off(crtc);
+	armada_drm_crtc_update(dcrtc, false);
+
+	if (!crtc->state->active) {
+		/*
+		 * This modeset will be leaving the CRTC disabled, so
+		 * call the backend to disable upstream clocks etc.
+		 */
+		if (dcrtc->variant->disable)
+			dcrtc->variant->disable(dcrtc);
+
+		/*
+		 * We will not receive any further vblank events.
+		 * Send the flip_done event manually.
+		 */
+		event = crtc->state->event;
+		crtc->state->event = NULL;
+		if (event) {
+			spin_lock_irq(&crtc->dev->event_lock);
+			drm_crtc_send_vblank_event(crtc, event);
+			spin_unlock_irq(&crtc->dev->event_lock);
+		}
+	}
 }
 
-/* The mode_config.mutex will be held for this call */
-static void armada_drm_crtc_disable(struct drm_crtc *crtc)
+static void armada_drm_crtc_atomic_enable(struct drm_crtc *crtc,
+					  struct drm_crtc_state *old_state)
 {
-	armada_drm_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
 
-	/* Disable our primary plane when we disable the CRTC. */
-	crtc->primary->funcs->disable_plane(crtc->primary, NULL);
+	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name);
+
+	if (!old_state->active) {
+		/*
+		 * This modeset is enabling the CRTC after it having
+		 * been disabled.  Reverse the call to ->disable in
+		 * the atomic_disable().
+		 */
+		if (dcrtc->variant->enable)
+			dcrtc->variant->enable(dcrtc, &crtc->state->adjusted_mode);
+	}
+	armada_drm_crtc_update(dcrtc, true);
+	drm_crtc_vblank_on(crtc);
+
+	armada_drm_crtc_queue_state_event(crtc);
 }
 
 static const struct drm_crtc_helper_funcs armada_crtc_helper_funcs = {
-	.dpms		= armada_drm_crtc_dpms,
-	.prepare	= armada_drm_crtc_prepare,
-	.commit		= armada_drm_crtc_commit,
 	.mode_fixup	= armada_drm_crtc_mode_fixup,
-	.mode_set	= armada_drm_crtc_mode_set,
-	.mode_set_base	= armada_drm_crtc_mode_set_base,
-	.disable	= armada_drm_crtc_disable,
+	.mode_set_nofb	= armada_drm_crtc_mode_set_nofb,
+	.atomic_begin	= armada_drm_crtc_atomic_begin,
+	.atomic_flush	= armada_drm_crtc_atomic_flush,
+	.atomic_disable	= armada_drm_crtc_atomic_disable,
+	.atomic_enable	= armada_drm_crtc_atomic_enable,
 };
 
 static void armada_load_cursor_argb(void __iomem *base, uint32_t *pix,
@@ -884,7 +542,6 @@ static int armada_drm_crtc_cursor_update(struct armada_crtc *dcrtc, bool reload)
 
 	if (!dcrtc->cursor_obj || !h || !w) {
 		spin_lock_irq(&dcrtc->irq_lock);
-		armada_drm_crtc_disable_irq(dcrtc, DUMB_FRAMEDONE_ENA);
 		dcrtc->cursor_update = false;
 		armada_updatel(0, CFG_HWC_ENA, dcrtc->base + LCD_SPU_DMA_CTRL0);
 		spin_unlock_irq(&dcrtc->irq_lock);
@@ -908,7 +565,6 @@ static int armada_drm_crtc_cursor_update(struct armada_crtc *dcrtc, bool reload)
 
 	if (dcrtc->cursor_hw_sz != (h << 16 | w)) {
 		spin_lock_irq(&dcrtc->irq_lock);
-		armada_drm_crtc_disable_irq(dcrtc, DUMB_FRAMEDONE_ENA);
 		dcrtc->cursor_update = false;
 		armada_updatel(0, CFG_HWC_ENA, dcrtc->base + LCD_SPU_DMA_CTRL0);
 		spin_unlock_irq(&dcrtc->irq_lock);
@@ -1016,8 +672,8 @@ static void armada_drm_crtc_destroy(struct drm_crtc *crtc)
 	priv->dcrtc[dcrtc->num] = NULL;
 	drm_crtc_cleanup(&dcrtc->crtc);
 
-	if (!IS_ERR(dcrtc->clk))
-		clk_disable_unprepare(dcrtc->clk);
+	if (dcrtc->variant->disable)
+		dcrtc->variant->disable(dcrtc);
 
 	writel_relaxed(0, dcrtc->base + LCD_SPU_IRQ_ENA);
 
@@ -1026,93 +682,6 @@ static void armada_drm_crtc_destroy(struct drm_crtc *crtc)
 	kfree(dcrtc);
 }
 
-/*
- * The mode_config lock is held here, to prevent races between this
- * and a mode_set.
- */
-static int armada_drm_crtc_page_flip(struct drm_crtc *crtc,
-	struct drm_framebuffer *fb, struct drm_pending_vblank_event *event, uint32_t page_flip_flags,
-	struct drm_modeset_acquire_ctx *ctx)
-{
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	struct armada_plane_work *work;
-	unsigned i;
-	int ret;
-
-	/* We don't support changing the pixel format */
-	if (fb->format != crtc->primary->fb->format)
-		return -EINVAL;
-
-	work = armada_drm_crtc_alloc_plane_work(dcrtc->crtc.primary);
-	if (!work)
-		return -ENOMEM;
-
-	work->event = event;
-	work->old_fb = dcrtc->crtc.primary->fb;
-
-	i = armada_drm_crtc_calc_fb(fb, crtc->x, crtc->y, work->regs,
-				    dcrtc->interlaced);
-	armada_reg_queue_end(work->regs, i);
-
-	/*
-	 * Ensure that we hold a reference on the new framebuffer.
-	 * This has to match the behaviour in mode_set.
-	 */
-	drm_framebuffer_get(fb);
-
-	ret = armada_drm_plane_work_queue(dcrtc, work);
-	if (ret) {
-		/* Undo our reference above */
-		drm_framebuffer_put(fb);
-		kfree(work);
-		return ret;
-	}
-
-	/*
-	 * Don't take a reference on the new framebuffer;
-	 * drm_mode_page_flip_ioctl() has already grabbed a reference and
-	 * will _not_ drop that reference on successful return from this
-	 * function.  Simply mark this new framebuffer as the current one.
-	 */
-	dcrtc->crtc.primary->fb = fb;
-
-	/*
-	 * Finally, if the display is blanked, we won't receive an
-	 * interrupt, so complete it now.
-	 */
-	if (dpms_blanked(dcrtc->dpms))
-		armada_drm_plane_work_run(dcrtc, dcrtc->crtc.primary);
-
-	return 0;
-}
-
-static int
-armada_drm_crtc_set_property(struct drm_crtc *crtc,
-	struct drm_property *property, uint64_t val)
-{
-	struct armada_private *priv = crtc->dev->dev_private;
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	bool update_csc = false;
-
-	if (property == priv->csc_yuv_prop) {
-		dcrtc->csc_yuv_mode = val;
-		update_csc = true;
-	} else if (property == priv->csc_rgb_prop) {
-		dcrtc->csc_rgb_mode = val;
-		update_csc = true;
-	}
-
-	if (update_csc) {
-		uint32_t val;
-
-		val = dcrtc->spu_iopad_ctrl |
-		      armada_drm_crtc_calculate_csc(dcrtc);
-		writel_relaxed(val, dcrtc->base + LCD_SPU_IOPAD_CONTROL);
-	}
-
-	return 0;
-}
-
 /* These are called under the vbl_lock. */
 static int armada_drm_crtc_enable_vblank(struct drm_crtc *crtc)
 {
@@ -1136,257 +705,28 @@ static void armada_drm_crtc_disable_vblank(struct drm_crtc *crtc)
 }
 
 static const struct drm_crtc_funcs armada_crtc_funcs = {
+	.reset		= drm_atomic_helper_crtc_reset,
 	.cursor_set	= armada_drm_crtc_cursor_set,
 	.cursor_move	= armada_drm_crtc_cursor_move,
 	.destroy	= armada_drm_crtc_destroy,
-	.set_config	= drm_crtc_helper_set_config,
-	.page_flip	= armada_drm_crtc_page_flip,
-	.set_property	= armada_drm_crtc_set_property,
+	.set_config	= drm_atomic_helper_set_config,
+	.page_flip	= drm_atomic_helper_page_flip,
+	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_crtc_destroy_state,
 	.enable_vblank	= armada_drm_crtc_enable_vblank,
 	.disable_vblank	= armada_drm_crtc_disable_vblank,
 };
 
-static void armada_drm_primary_update_state(struct drm_plane_state *state,
-	struct armada_regs *regs)
-{
-	struct armada_plane *dplane = drm_to_armada_plane(state->plane);
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(state->crtc);
-	struct armada_framebuffer *dfb = drm_fb_to_armada_fb(state->fb);
-	bool was_disabled;
-	unsigned int idx = 0;
-	u32 val;
-
-	val = CFG_GRA_FMT(dfb->fmt) | CFG_GRA_MOD(dfb->mod);
-	if (dfb->fmt > CFG_420)
-		val |= CFG_PALETTE_ENA;
-	if (state->visible)
-		val |= CFG_GRA_ENA;
-	if (drm_rect_width(&state->src) >> 16 != drm_rect_width(&state->dst))
-		val |= CFG_GRA_HSMOOTH;
-
-	was_disabled = !(dplane->state.ctrl0 & CFG_GRA_ENA);
-	if (was_disabled)
-		armada_reg_queue_mod(regs, idx,
-				     0, CFG_PDWN64x66, LCD_SPU_SRAM_PARA1);
-
-	dplane->state.ctrl0 = val;
-	dplane->state.src_hw = (drm_rect_height(&state->src) & 0xffff0000) |
-				drm_rect_width(&state->src) >> 16;
-	dplane->state.dst_hw = drm_rect_height(&state->dst) << 16 |
-			       drm_rect_width(&state->dst);
-	dplane->state.dst_yx = state->dst.y1 << 16 | state->dst.x1;
-
-	armada_drm_gra_plane_regs(regs + idx, &dfb->fb, &dplane->state,
-				  state->src.x1 >> 16, state->src.y1 >> 16,
-				  dcrtc->interlaced);
-
-	dplane->state.vsync_update = !was_disabled;
-	dplane->state.changed = true;
-}
-
-static int armada_drm_primary_update(struct drm_plane *plane,
-	struct drm_crtc *crtc, struct drm_framebuffer *fb,
-	int crtc_x, int crtc_y, unsigned int crtc_w, unsigned int crtc_h,
-	uint32_t src_x, uint32_t src_y, uint32_t src_w, uint32_t src_h,
-	struct drm_modeset_acquire_ctx *ctx)
-{
-	struct armada_plane *dplane = drm_to_armada_plane(plane);
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	struct armada_plane_work *work;
-	struct drm_plane_state state = {
-		.plane = plane,
-		.crtc = crtc,
-		.fb = fb,
-		.src_x = src_x,
-		.src_y = src_y,
-		.src_w = src_w,
-		.src_h = src_h,
-		.crtc_x = crtc_x,
-		.crtc_y = crtc_y,
-		.crtc_w = crtc_w,
-		.crtc_h = crtc_h,
-		.rotation = DRM_MODE_ROTATE_0,
-	};
-	struct drm_crtc_state crtc_state = {
-		.crtc = crtc,
-		.enable = crtc->enabled,
-		.mode = crtc->mode,
-	};
-	int ret;
-
-	ret = drm_atomic_helper_check_plane_state(&state, &crtc_state, 0,
-						  INT_MAX, true, false);
-	if (ret)
-		return ret;
-
-	work = &dplane->works[dplane->next_work];
-	work->fn = armada_drm_crtc_complete_frame_work;
-
-	if (plane->fb != fb) {
-		/*
-		 * Take a reference on the new framebuffer - we want to
-		 * hold on to it while the hardware is displaying it.
-		 */
-		drm_framebuffer_reference(fb);
-
-		work->old_fb = plane->fb;
-	} else {
-		work->old_fb = NULL;
-	}
-
-	armada_drm_primary_update_state(&state, work->regs);
-
-	if (!dplane->state.changed)
-		return 0;
-
-	/* Wait for pending work to complete */
-	if (armada_drm_plane_work_wait(dplane, HZ / 10) == 0)
-		armada_drm_plane_work_cancel(dcrtc, dplane);
-
-	if (!dplane->state.vsync_update) {
-		work->fn(dcrtc, work);
-		if (work->old_fb)
-			drm_framebuffer_unreference(work->old_fb);
-		return 0;
-	}
-
-	/* Queue it for update on the next interrupt if we are enabled */
-	ret = armada_drm_plane_work_queue(dcrtc, work);
-	if (ret) {
-		work->fn(dcrtc, work);
-		if (work->old_fb)
-			drm_framebuffer_unreference(work->old_fb);
-	}
-
-	dplane->next_work = !dplane->next_work;
-
-	return 0;
-}
-
-int armada_drm_plane_disable(struct drm_plane *plane,
-			     struct drm_modeset_acquire_ctx *ctx)
-{
-	struct armada_plane *dplane = drm_to_armada_plane(plane);
-	struct armada_crtc *dcrtc;
-	struct armada_plane_work *work;
-	unsigned int idx = 0;
-	u32 sram_para1, enable_mask;
-
-	if (!plane->crtc)
-		return 0;
-
-	/*
-	 * Arrange to power down most RAMs and FIFOs if this is the primary
-	 * plane, otherwise just the YUV FIFOs for the overlay plane.
-	 */
-	if (plane->type == DRM_PLANE_TYPE_PRIMARY) {
-		sram_para1 = CFG_PDWN256x32 | CFG_PDWN256x24 | CFG_PDWN256x8 |
-			     CFG_PDWN32x32 | CFG_PDWN64x66;
-		enable_mask = CFG_GRA_ENA;
-	} else {
-		sram_para1 = CFG_PDWN16x66 | CFG_PDWN32x66;
-		enable_mask = CFG_DMA_ENA;
-	}
-
-	dplane->state.ctrl0 &= ~enable_mask;
-
-	dcrtc = drm_to_armada_crtc(plane->crtc);
-
-	/*
-	 * Try to disable the plane and drop our ref on the framebuffer
-	 * at the next frame update. If we fail for any reason, disable
-	 * the plane immediately.
-	 */
-	work = &dplane->works[dplane->next_work];
-	work->fn = armada_drm_crtc_complete_disable_work;
-	work->cancel = armada_drm_crtc_complete_disable_work;
-	work->old_fb = plane->fb;
-
-	armada_reg_queue_mod(work->regs, idx,
-			     0, enable_mask, LCD_SPU_DMA_CTRL0);
-	armada_reg_queue_mod(work->regs, idx,
-			     sram_para1, 0, LCD_SPU_SRAM_PARA1);
-	armada_reg_queue_end(work->regs, idx);
-
-	/* Wait for any preceding work to complete, but don't wedge */
-	if (WARN_ON(!armada_drm_plane_work_wait(dplane, HZ)))
-		armada_drm_plane_work_cancel(dcrtc, dplane);
-
-	if (armada_drm_plane_work_queue(dcrtc, work)) {
-		work->fn(dcrtc, work);
-		if (work->old_fb)
-			drm_framebuffer_unreference(work->old_fb);
-	}
-
-	dplane->next_work = !dplane->next_work;
-
-	return 0;
-}
-
-static const struct drm_plane_funcs armada_primary_plane_funcs = {
-	.update_plane	= armada_drm_primary_update,
-	.disable_plane	= armada_drm_plane_disable,
-	.destroy	= drm_primary_helper_destroy,
-};
-
-int armada_drm_plane_init(struct armada_plane *plane)
-{
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(plane->works); i++)
-		plane->works[i].plane = &plane->base;
-
-	init_waitqueue_head(&plane->frame_wait);
-
-	return 0;
-}
-
-static const struct drm_prop_enum_list armada_drm_csc_yuv_enum_list[] = {
-	{ CSC_AUTO,        "Auto" },
-	{ CSC_YUV_CCIR601, "CCIR601" },
-	{ CSC_YUV_CCIR709, "CCIR709" },
-};
-
-static const struct drm_prop_enum_list armada_drm_csc_rgb_enum_list[] = {
-	{ CSC_AUTO,         "Auto" },
-	{ CSC_RGB_COMPUTER, "Computer system" },
-	{ CSC_RGB_STUDIO,   "Studio" },
-};
-
-static int armada_drm_crtc_create_properties(struct drm_device *dev)
-{
-	struct armada_private *priv = dev->dev_private;
-
-	if (priv->csc_yuv_prop)
-		return 0;
-
-	priv->csc_yuv_prop = drm_property_create_enum(dev, 0,
-				"CSC_YUV", armada_drm_csc_yuv_enum_list,
-				ARRAY_SIZE(armada_drm_csc_yuv_enum_list));
-	priv->csc_rgb_prop = drm_property_create_enum(dev, 0,
-				"CSC_RGB", armada_drm_csc_rgb_enum_list,
-				ARRAY_SIZE(armada_drm_csc_rgb_enum_list));
-
-	if (!priv->csc_yuv_prop || !priv->csc_rgb_prop)
-		return -ENOMEM;
-
-	return 0;
-}
-
 static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev,
 	struct resource *res, int irq, const struct armada_variant *variant,
 	struct device_node *port)
 {
 	struct armada_private *priv = drm->dev_private;
 	struct armada_crtc *dcrtc;
-	struct armada_plane *primary;
+	struct drm_plane *primary;
 	void __iomem *base;
 	int ret;
 
-	ret = armada_drm_crtc_create_properties(drm);
-	if (ret)
-		return ret;
-
 	base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(base))
 		return PTR_ERR(base);
@@ -1404,8 +744,6 @@ static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev,
 	dcrtc->base = base;
 	dcrtc->num = drm->mode_config.num_crtc;
 	dcrtc->clk = ERR_PTR(-EINVAL);
-	dcrtc->csc_yuv_mode = CSC_AUTO;
-	dcrtc->csc_rgb_mode = CSC_AUTO;
 	dcrtc->cfg_dumb_ctrl = DUMB24_RGB888_0;
 	dcrtc->spu_iopad_ctrl = CFG_VSCALE_LN_EN | CFG_IOPAD_DUMB24;
 	spin_lock_init(&dcrtc->irq_lock);
@@ -1449,39 +787,23 @@ static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev,
 		goto err_crtc;
 	}
 
-	ret = armada_drm_plane_init(primary);
-	if (ret) {
-		kfree(primary);
-		goto err_crtc;
-	}
-
-	ret = drm_universal_plane_init(drm, &primary->base, 0,
-				       &armada_primary_plane_funcs,
-				       armada_primary_formats,
-				       ARRAY_SIZE(armada_primary_formats),
-				       NULL,
-				       DRM_PLANE_TYPE_PRIMARY, NULL);
+	ret = armada_drm_primary_plane_init(drm, primary);
 	if (ret) {
 		kfree(primary);
 		goto err_crtc;
 	}
 
-	ret = drm_crtc_init_with_planes(drm, &dcrtc->crtc, &primary->base, NULL,
+	ret = drm_crtc_init_with_planes(drm, &dcrtc->crtc, primary, NULL,
 					&armada_crtc_funcs, NULL);
 	if (ret)
 		goto err_crtc_init;
 
 	drm_crtc_helper_add(&dcrtc->crtc, &armada_crtc_helper_funcs);
 
-	drm_object_attach_property(&dcrtc->crtc.base, priv->csc_yuv_prop,
-				   dcrtc->csc_yuv_mode);
-	drm_object_attach_property(&dcrtc->crtc.base, priv->csc_rgb_prop,
-				   dcrtc->csc_rgb_mode);
-
 	return armada_overlay_plane_create(drm, 1 << dcrtc->num);
 
 err_crtc_init:
-	primary->base.funcs->destroy(&primary->base);
+	primary->funcs->destroy(primary);
 err_crtc:
 	kfree(dcrtc);
 
diff --git a/drivers/gpu/drm/armada/armada_crtc.h b/drivers/gpu/drm/armada/armada_crtc.h
index 445829b8877a..7ebd337b60af 100644
--- a/drivers/gpu/drm/armada/armada_crtc.h
+++ b/drivers/gpu/drm/armada/armada_crtc.h
@@ -32,49 +32,8 @@ struct armada_regs {
 	armada_reg_queue_mod(_r, _i, 0, 0, ~0)
 
 struct armada_crtc;
-struct armada_plane;
 struct armada_variant;
 
-struct armada_plane_work {
-	void (*fn)(struct armada_crtc *, struct armada_plane_work *);
-	void (*cancel)(struct armada_crtc *, struct armada_plane_work *);
-	bool need_kfree;
-	struct drm_plane *plane;
-	struct drm_framebuffer *old_fb;
-	struct drm_pending_vblank_event *event;
-	struct armada_regs regs[14];
-};
-
-struct armada_plane_state {
-	u16 src_x;
-	u16 src_y;
-	u32 src_hw;
-	u32 dst_hw;
-	u32 dst_yx;
-	u32 ctrl0;
-	bool changed;
-	bool vsync_update;
-};
-
-struct armada_plane {
-	struct drm_plane	base;
-	wait_queue_head_t	frame_wait;
-	bool			next_work;
-	struct armada_plane_work works[2];
-	struct armada_plane_work *work;
-	struct armada_plane_state state;
-};
-#define drm_to_armada_plane(p) container_of(p, struct armada_plane, base)
-
-int armada_drm_plane_init(struct armada_plane *plane);
-int armada_drm_plane_work_queue(struct armada_crtc *dcrtc,
-	struct armada_plane_work *work);
-int armada_drm_plane_work_wait(struct armada_plane *plane, long timeout);
-void armada_drm_plane_work_cancel(struct armada_crtc *dcrtc,
-	struct armada_plane *plane);
-void armada_drm_plane_calc_addrs(u32 *addrs, struct drm_framebuffer *fb,
-	int x, int y);
-
 struct armada_crtc {
 	struct drm_crtc		crtc;
 	const struct armada_variant *variant;
@@ -89,10 +48,6 @@ struct armada_crtc {
 	} v[2];
 	bool			interlaced;
 	bool			cursor_update;
-	uint8_t			csc_yuv_mode;
-	uint8_t			csc_rgb_mode;
-
-	struct drm_plane	*plane;
 
 	struct armada_gem_object	*cursor_obj;
 	int			cursor_x;
@@ -102,21 +57,22 @@ struct armada_crtc {
 	uint32_t		cursor_w;
 	uint32_t		cursor_h;
 
-	int			dpms;
 	uint32_t		cfg_dumb_ctrl;
-	uint32_t		dumb_ctrl;
 	uint32_t		spu_iopad_ctrl;
 
 	spinlock_t		irq_lock;
 	uint32_t		irq_ena;
+
+	bool			update_pending;
+	struct drm_pending_vblank_event *event;
+	struct armada_regs	atomic_regs[32];
+	struct armada_regs	*regs;
+	unsigned int		regs_idx;
 };
 #define drm_to_armada_crtc(c) container_of(c, struct armada_crtc, crtc)
 
 void armada_drm_crtc_update_regs(struct armada_crtc *, struct armada_regs *);
 
-int armada_drm_plane_disable(struct drm_plane *plane,
-			     struct drm_modeset_acquire_ctx *ctx);
-
 extern struct platform_driver armada_lcd_platform_driver;
 
 #endif
diff --git a/drivers/gpu/drm/armada/armada_drm.h b/drivers/gpu/drm/armada/armada_drm.h
index cc4c557c9f66..f09083ff15d3 100644
--- a/drivers/gpu/drm/armada/armada_drm.h
+++ b/drivers/gpu/drm/armada/armada_drm.h
@@ -42,11 +42,12 @@ struct armada_private;
 
 struct armada_variant {
 	bool has_spu_adv_reg;
-	uint32_t spu_adv_reg;
 	int (*init)(struct armada_crtc *, struct device *);
 	int (*compute_clock)(struct armada_crtc *,
 			     const struct drm_display_mode *,
 			     uint32_t *);
+	void (*disable)(struct armada_crtc *);
+	void (*enable)(struct armada_crtc *, const struct drm_display_mode *);
 };
 
 /* Variant ops */
@@ -54,14 +55,10 @@ extern const struct armada_variant armada510_ops;
 
 struct armada_private {
 	struct drm_device	drm;
-	struct work_struct	fb_unref_work;
-	DECLARE_KFIFO(fb_unref, struct drm_framebuffer *, 8);
 	struct drm_fb_helper	*fbdev;
 	struct armada_crtc	*dcrtc[2];
 	struct drm_mm		linear; /* protected by linear_lock */
 	struct mutex		linear_lock;
-	struct drm_property	*csc_yuv_prop;
-	struct drm_property	*csc_rgb_prop;
 	struct drm_property	*colorkey_prop;
 	struct drm_property	*colorkey_min_prop;
 	struct drm_property	*colorkey_max_prop;
@@ -76,13 +73,6 @@ struct armada_private {
 #endif
 };
 
-void __armada_drm_queue_unref_work(struct drm_device *,
-	struct drm_framebuffer *);
-void armada_drm_queue_unref_work(struct drm_device *,
-	struct drm_framebuffer *);
-
-extern const struct drm_mode_config_funcs armada_drm_mode_config_funcs;
-
 int armada_fbdev_init(struct drm_device *);
 void armada_fbdev_fini(struct drm_device *);
 
diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c
index 4b11b6b52f1d..fa31589b4fc0 100644
--- a/drivers/gpu/drm/armada/armada_drv.c
+++ b/drivers/gpu/drm/armada/armada_drv.c
@@ -9,46 +9,18 @@
 #include <linux/component.h>
 #include <linux/module.h>
 #include <linux/of_graph.h>
+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_of.h>
 #include "armada_crtc.h"
 #include "armada_drm.h"
 #include "armada_gem.h"
+#include "armada_fb.h"
 #include "armada_hw.h"
 #include <drm/armada_drm.h>
 #include "armada_ioctlP.h"
 
-static void armada_drm_unref_work(struct work_struct *work)
-{
-	struct armada_private *priv =
-		container_of(work, struct armada_private, fb_unref_work);
-	struct drm_framebuffer *fb;
-
-	while (kfifo_get(&priv->fb_unref, &fb))
-		drm_framebuffer_put(fb);
-}
-
-/* Must be called with dev->event_lock held */
-void __armada_drm_queue_unref_work(struct drm_device *dev,
-	struct drm_framebuffer *fb)
-{
-	struct armada_private *priv = dev->dev_private;
-
-	WARN_ON(!kfifo_put(&priv->fb_unref, fb));
-	schedule_work(&priv->fb_unref_work);
-}
-
-void armada_drm_queue_unref_work(struct drm_device *dev,
-	struct drm_framebuffer *fb)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&dev->event_lock, flags);
-	__armada_drm_queue_unref_work(dev, fb);
-	spin_unlock_irqrestore(&dev->event_lock, flags);
-}
-
 static struct drm_ioctl_desc armada_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(ARMADA_GEM_CREATE, armada_gem_create_ioctl,0),
 	DRM_IOCTL_DEF_DRV(ARMADA_GEM_MMAP, armada_gem_mmap_ioctl, 0),
@@ -72,11 +44,18 @@ static struct drm_driver armada_drm_driver = {
 	.desc			= "Armada SoC DRM",
 	.date			= "20120730",
 	.driver_features	= DRIVER_GEM | DRIVER_MODESET |
-				  DRIVER_PRIME,
+				  DRIVER_PRIME | DRIVER_ATOMIC,
 	.ioctls			= armada_ioctls,
 	.fops			= &armada_drm_fops,
 };
 
+static const struct drm_mode_config_funcs armada_drm_mode_config_funcs = {
+	.fb_create		= armada_fb_create,
+	.output_poll_changed	= drm_fb_helper_output_poll_changed,
+	.atomic_check		= drm_atomic_helper_check,
+	.atomic_commit		= drm_atomic_helper_commit,
+};
+
 static int armada_drm_bind(struct device *dev)
 {
 	struct armada_private *priv;
@@ -109,7 +88,7 @@ static int armada_drm_bind(struct device *dev)
 
 	/*
 	 * The drm_device structure must be at the start of
-	 * armada_private for drm_dev_unref() to work correctly.
+	 * armada_private for drm_dev_put() to work correctly.
 	 */
 	BUILD_BUG_ON(offsetof(struct armada_private, drm) != 0);
 
@@ -125,9 +104,6 @@ static int armada_drm_bind(struct device *dev)
 
 	dev_set_drvdata(dev, &priv->drm);
 
-	INIT_WORK(&priv->fb_unref_work, armada_drm_unref_work);
-	INIT_KFIFO(priv->fb_unref);
-
 	/* Mode setting support */
 	drm_mode_config_init(&priv->drm);
 	priv->drm.mode_config.min_width = 320;
@@ -155,6 +131,8 @@ static int armada_drm_bind(struct device *dev)
 
 	priv->drm.irq_enabled = true;
 
+	drm_mode_config_reset(&priv->drm);
+
 	ret = armada_fbdev_init(&priv->drm);
 	if (ret)
 		goto err_comp;
@@ -179,8 +157,7 @@ static int armada_drm_bind(struct device *dev)
  err_kms:
 	drm_mode_config_cleanup(&priv->drm);
 	drm_mm_takedown(&priv->linear);
-	flush_work(&priv->fb_unref_work);
-	drm_dev_unref(&priv->drm);
+	drm_dev_put(&priv->drm);
 	return ret;
 }
 
@@ -198,9 +175,8 @@ static void armada_drm_unbind(struct device *dev)
 
 	drm_mode_config_cleanup(&priv->drm);
 	drm_mm_takedown(&priv->linear);
-	flush_work(&priv->fb_unref_work);
 
-	drm_dev_unref(&priv->drm);
+	drm_dev_put(&priv->drm);
 }
 
 static int compare_of(struct device *dev, void *data)
diff --git a/drivers/gpu/drm/armada/armada_fb.c b/drivers/gpu/drm/armada/armada_fb.c
index ac92bce07ecd..6bd638a54579 100644
--- a/drivers/gpu/drm/armada/armada_fb.c
+++ b/drivers/gpu/drm/armada/armada_fb.c
@@ -7,30 +7,15 @@
  */
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 #include "armada_drm.h"
 #include "armada_fb.h"
 #include "armada_gem.h"
 #include "armada_hw.h"
 
-static void armada_fb_destroy(struct drm_framebuffer *fb)
-{
-	struct armada_framebuffer *dfb = drm_fb_to_armada_fb(fb);
-
-	drm_framebuffer_cleanup(&dfb->fb);
-	drm_gem_object_put_unlocked(&dfb->obj->obj);
-	kfree(dfb);
-}
-
-static int armada_fb_create_handle(struct drm_framebuffer *fb,
-	struct drm_file *dfile, unsigned int *handle)
-{
-	struct armada_framebuffer *dfb = drm_fb_to_armada_fb(fb);
-	return drm_gem_handle_create(dfile, &dfb->obj->obj, handle);
-}
-
 static const struct drm_framebuffer_funcs armada_fb_funcs = {
-	.destroy	= armada_fb_destroy,
-	.create_handle	= armada_fb_create_handle,
+	.destroy	= drm_gem_fb_destroy,
+	.create_handle	= drm_gem_fb_create_handle,
 };
 
 struct armada_framebuffer *armada_framebuffer_create(struct drm_device *dev,
@@ -78,7 +63,7 @@ struct armada_framebuffer *armada_framebuffer_create(struct drm_device *dev,
 
 	dfb->fmt = format;
 	dfb->mod = config;
-	dfb->obj = obj;
+	dfb->fb.obj[0] = &obj->obj;
 
 	drm_helper_mode_fill_fb_struct(dev, &dfb->fb, mode);
 
@@ -99,7 +84,7 @@ struct armada_framebuffer *armada_framebuffer_create(struct drm_device *dev,
 	return dfb;
 }
 
-static struct drm_framebuffer *armada_fb_create(struct drm_device *dev,
+struct drm_framebuffer *armada_fb_create(struct drm_device *dev,
 	struct drm_file *dfile, const struct drm_mode_fb_cmd2 *mode)
 {
 	struct armada_gem_object *obj;
@@ -153,8 +138,3 @@ static struct drm_framebuffer *armada_fb_create(struct drm_device *dev,
 	DRM_ERROR("failed to initialize framebuffer: %d\n", ret);
 	return ERR_PTR(ret);
 }
-
-const struct drm_mode_config_funcs armada_drm_mode_config_funcs = {
-	.fb_create		= armada_fb_create,
-	.output_poll_changed	= drm_fb_helper_output_poll_changed,
-};
diff --git a/drivers/gpu/drm/armada/armada_fb.h b/drivers/gpu/drm/armada/armada_fb.h
index 48073c4f54d8..476daad0a36a 100644
--- a/drivers/gpu/drm/armada/armada_fb.h
+++ b/drivers/gpu/drm/armada/armada_fb.h
@@ -10,15 +10,15 @@
 
 struct armada_framebuffer {
 	struct drm_framebuffer	fb;
-	struct armada_gem_object *obj;
 	uint8_t			fmt;
 	uint8_t			mod;
 };
 #define drm_fb_to_armada_fb(dfb) \
 	container_of(dfb, struct armada_framebuffer, fb)
-#define drm_fb_obj(fb) drm_fb_to_armada_fb(fb)->obj
+#define drm_fb_obj(fb) drm_to_armada_gem((fb)->obj[0])
 
 struct armada_framebuffer *armada_framebuffer_create(struct drm_device *,
 	const struct drm_mode_fb_cmd2 *, struct armada_gem_object *);
-
+struct drm_framebuffer *armada_fb_create(struct drm_device *dev,
+	struct drm_file *dfile, const struct drm_mode_fb_cmd2 *mode);
 #endif
diff --git a/drivers/gpu/drm/armada/armada_fbdev.c b/drivers/gpu/drm/armada/armada_fbdev.c
index 2a59db0994b2..8d23700848df 100644
--- a/drivers/gpu/drm/armada/armada_fbdev.c
+++ b/drivers/gpu/drm/armada/armada_fbdev.c
@@ -24,7 +24,7 @@ static /*const*/ struct fb_ops armada_fb_ops = {
 	.fb_imageblit	= drm_fb_helper_cfb_imageblit,
 };
 
-static int armada_fb_create(struct drm_fb_helper *fbh,
+static int armada_fbdev_create(struct drm_fb_helper *fbh,
 	struct drm_fb_helper_surface_size *sizes)
 {
 	struct drm_device *dev = fbh->dev;
@@ -108,7 +108,7 @@ static int armada_fb_probe(struct drm_fb_helper *fbh,
 	int ret = 0;
 
 	if (!fbh->fb) {
-		ret = armada_fb_create(fbh, sizes);
+		ret = armada_fbdev_create(fbh, sizes);
 		if (ret == 0)
 			ret = 1;
 	}
diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c
index a97f509743a5..892c1d9304bb 100644
--- a/drivers/gpu/drm/armada/armada_gem.c
+++ b/drivers/gpu/drm/armada/armada_gem.c
@@ -13,25 +13,14 @@
 #include <drm/armada_drm.h>
 #include "armada_ioctlP.h"
 
-static int armada_gem_vm_fault(struct vm_fault *vmf)
+static vm_fault_t armada_gem_vm_fault(struct vm_fault *vmf)
 {
 	struct drm_gem_object *gobj = vmf->vma->vm_private_data;
 	struct armada_gem_object *obj = drm_to_armada_gem(gobj);
 	unsigned long pfn = obj->phys_addr >> PAGE_SHIFT;
-	int ret;
 
 	pfn += (vmf->address - vmf->vma->vm_start) >> PAGE_SHIFT;
-	ret = vm_insert_pfn(vmf->vma, vmf->address, pfn);
-
-	switch (ret) {
-	case 0:
-	case -EBUSY:
-		return VM_FAULT_NOPAGE;
-	case -ENOMEM:
-		return VM_FAULT_OOM;
-	default:
-		return VM_FAULT_SIGBUS;
-	}
+	return vmf_insert_pfn(vmf->vma, vmf->address, pfn);
 }
 
 const struct vm_operations_struct armada_gem_vm_ops = {
@@ -490,8 +479,6 @@ static const struct dma_buf_ops armada_gem_prime_dmabuf_ops = {
 	.map_dma_buf	= armada_gem_prime_map_dma_buf,
 	.unmap_dma_buf	= armada_gem_prime_unmap_dma_buf,
 	.release	= drm_gem_dmabuf_release,
-	.map_atomic	= armada_gem_dmabuf_no_kmap,
-	.unmap_atomic	= armada_gem_dmabuf_no_kunmap,
 	.map		= armada_gem_dmabuf_no_kmap,
 	.unmap		= armada_gem_dmabuf_no_kunmap,
 	.mmap		= armada_gem_dmabuf_mmap,
diff --git a/drivers/gpu/drm/armada/armada_hw.h b/drivers/gpu/drm/armada/armada_hw.h
index 345dc4d0851e..277580b36758 100644
--- a/drivers/gpu/drm/armada/armada_hw.h
+++ b/drivers/gpu/drm/armada/armada_hw.h
@@ -316,4 +316,19 @@ enum {
 	PWRDN_IRQ_LEVEL		= 1 << 0,
 };
 
+static inline u32 armada_rect_hw_fp(struct drm_rect *r)
+{
+	return (drm_rect_height(r) & 0xffff0000) | drm_rect_width(r) >> 16;
+}
+
+static inline u32 armada_rect_hw(struct drm_rect *r)
+{
+	return drm_rect_height(r) << 16 | (drm_rect_width(r) & 0x0000ffff);
+}
+
+static inline u32 armada_rect_yx(struct drm_rect *r)
+{
+	return (r)->y1 << 16 | ((r)->x1 & 0x0000ffff);
+}
+
 #endif
diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index afa7ded3ae31..eb7dfb65ef47 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -7,358 +7,468 @@
  * published by the Free Software Foundation.
  */
 #include <drm/drmP.h>
+#include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_plane_helper.h>
+#include <drm/armada_drm.h>
 #include "armada_crtc.h"
 #include "armada_drm.h"
 #include "armada_fb.h"
 #include "armada_gem.h"
 #include "armada_hw.h"
-#include <drm/armada_drm.h>
 #include "armada_ioctlP.h"
+#include "armada_plane.h"
 #include "armada_trace.h"
 
-struct armada_ovl_plane_properties {
-	uint32_t colorkey_yr;
-	uint32_t colorkey_ug;
-	uint32_t colorkey_vb;
-#define K2R(val) (((val) >> 0) & 0xff)
-#define K2G(val) (((val) >> 8) & 0xff)
-#define K2B(val) (((val) >> 16) & 0xff)
-	int16_t  brightness;
-	uint16_t contrast;
-	uint16_t saturation;
-	uint32_t colorkey_mode;
-	uint32_t colorkey_enable;
-};
-
-struct armada_ovl_plane {
-	struct armada_plane base;
-	struct armada_ovl_plane_properties prop;
+#define DEFAULT_BRIGHTNESS	0
+#define DEFAULT_CONTRAST	0x4000
+#define DEFAULT_SATURATION	0x4000
+#define DEFAULT_ENCODING	DRM_COLOR_YCBCR_BT601
+
+struct armada_overlay_state {
+	struct drm_plane_state base;
+	u32 colorkey_yr;
+	u32 colorkey_ug;
+	u32 colorkey_vb;
+	u32 colorkey_mode;
+	u32 colorkey_enable;
+	s16 brightness;
+	u16 contrast;
+	u16 saturation;
 };
-#define drm_to_armada_ovl_plane(p) \
-	container_of(p, struct armada_ovl_plane, base.base)
-
+#define drm_to_overlay_state(s) \
+	container_of(s, struct armada_overlay_state, base)
 
-static void
-armada_ovl_update_attr(struct armada_ovl_plane_properties *prop,
-	struct armada_crtc *dcrtc)
+static inline u32 armada_spu_contrast(struct drm_plane_state *state)
 {
-	writel_relaxed(prop->colorkey_yr, dcrtc->base + LCD_SPU_COLORKEY_Y);
-	writel_relaxed(prop->colorkey_ug, dcrtc->base + LCD_SPU_COLORKEY_U);
-	writel_relaxed(prop->colorkey_vb, dcrtc->base + LCD_SPU_COLORKEY_V);
+	return drm_to_overlay_state(state)->brightness << 16 |
+	       drm_to_overlay_state(state)->contrast;
+}
 
-	writel_relaxed(prop->brightness << 16 | prop->contrast,
-		       dcrtc->base + LCD_SPU_CONTRAST);
+static inline u32 armada_spu_saturation(struct drm_plane_state *state)
+{
 	/* Docs say 15:0, but it seems to actually be 31:16 on Armada 510 */
-	writel_relaxed(prop->saturation << 16,
-		       dcrtc->base + LCD_SPU_SATURATION);
-	writel_relaxed(0x00002000, dcrtc->base + LCD_SPU_CBSH_HUE);
-
-	spin_lock_irq(&dcrtc->irq_lock);
-	armada_updatel(prop->colorkey_mode,
-		       CFG_CKMODE_MASK | CFG_ALPHAM_MASK | CFG_ALPHA_MASK,
-		       dcrtc->base + LCD_SPU_DMA_CTRL1);
-	if (dcrtc->variant->has_spu_adv_reg)
-		armada_updatel(prop->colorkey_enable,
-			       ADV_GRACOLORKEY | ADV_VIDCOLORKEY,
-			       dcrtc->base + LCD_SPU_ADV_REG);
-	spin_unlock_irq(&dcrtc->irq_lock);
+	return drm_to_overlay_state(state)->saturation << 16;
 }
 
-/* === Plane support === */
-static void armada_ovl_plane_work(struct armada_crtc *dcrtc,
-	struct armada_plane_work *work)
+static inline u32 armada_csc(struct drm_plane_state *state)
 {
-	unsigned long flags;
-
-	trace_armada_ovl_plane_work(&dcrtc->crtc, work->plane);
-
-	spin_lock_irqsave(&dcrtc->irq_lock, flags);
-	armada_drm_crtc_update_regs(dcrtc, work->regs);
-	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
+	/*
+	 * The CFG_CSC_RGB_* settings control the output of the colour space
+	 * converter, setting the range of output values it produces.  Since
+	 * we will be blending with the full-range graphics, we need to
+	 * produce full-range RGB output from the conversion.
+	 */
+	return CFG_CSC_RGB_COMPUTER |
+	       (state->color_encoding == DRM_COLOR_YCBCR_BT709 ?
+			CFG_CSC_YUV_CCIR709 : CFG_CSC_YUV_CCIR601);
 }
 
-static void armada_ovl_plane_update_state(struct drm_plane_state *state,
-	struct armada_regs *regs)
+/* === Plane support === */
+static void armada_drm_overlay_plane_atomic_update(struct drm_plane *plane,
+	struct drm_plane_state *old_state)
 {
-	struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(state->plane);
-	struct armada_framebuffer *dfb = drm_fb_to_armada_fb(state->fb);
-	const struct drm_format_info *format;
-	unsigned int idx = 0;
-	bool fb_changed;
-	u32 val, ctrl0;
-	u16 src_x, src_y;
+	struct drm_plane_state *state = plane->state;
+	struct armada_crtc *dcrtc;
+	struct armada_regs *regs;
+	unsigned int idx;
+	u32 cfg, cfg_mask, val;
 
-	ctrl0 = CFG_DMA_FMT(dfb->fmt) | CFG_DMA_MOD(dfb->mod) | CFG_CBSH_ENA;
-	if (state->visible)
-		ctrl0 |= CFG_DMA_ENA;
-	if (drm_rect_width(&state->src) >> 16 != drm_rect_width(&state->dst))
-		ctrl0 |= CFG_DMA_HSMOOTH;
+	DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name);
 
-	/*
-	 * Shifting a YUV packed format image by one pixel causes the U/V
-	 * planes to swap.  Compensate for it by also toggling the UV swap.
-	 */
-	format = dfb->fb.format;
-	if (format->num_planes == 1 && state->src.x1 >> 16 & (format->hsub - 1))
-		ctrl0 ^= CFG_DMA_MOD(CFG_SWAPUV);
+	if (!state->fb || WARN_ON(!state->crtc))
+		return;
+
+	DRM_DEBUG_KMS("[PLANE:%d:%s] is on [CRTC:%d:%s] with [FB:%d] visible %u->%u\n",
+		plane->base.id, plane->name,
+		state->crtc->base.id, state->crtc->name,
+		state->fb->base.id,
+		old_state->visible, state->visible);
+
+	dcrtc = drm_to_armada_crtc(state->crtc);
+	regs = dcrtc->regs + dcrtc->regs_idx;
 
-	if (~dplane->base.state.ctrl0 & ctrl0 & CFG_DMA_ENA) {
-		/* Power up the Y/U/V FIFOs on ENA 0->1 transitions */
+	idx = 0;
+	if (!old_state->visible && state->visible)
 		armada_reg_queue_mod(regs, idx,
 				     0, CFG_PDWN16x66 | CFG_PDWN32x66,
 				     LCD_SPU_SRAM_PARA1);
-	}
-
-	fb_changed = dplane->base.base.fb != &dfb->fb ||
-		     dplane->base.state.src_x != state->src.x1 >> 16 ||
-	             dplane->base.state.src_y != state->src.y1 >> 16;
-
-	dplane->base.state.vsync_update = fb_changed;
-
+	val = armada_rect_hw_fp(&state->src);
+	if (armada_rect_hw_fp(&old_state->src) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_DMA_HPXL_VLN);
+	val = armada_rect_yx(&state->dst);
+	if (armada_rect_yx(&old_state->dst) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_DMA_OVSA_HPXL_VLN);
+	val = armada_rect_hw(&state->dst);
+	if (armada_rect_hw(&old_state->dst) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_DZM_HPXL_VLN);
 	/* FIXME: overlay on an interlaced display */
-	if (fb_changed) {
-		u32 addrs[3];
-
-		dplane->base.state.src_y = src_y = state->src.y1 >> 16;
-		dplane->base.state.src_x = src_x = state->src.x1 >> 16;
+	if (old_state->src.x1 != state->src.x1 ||
+	    old_state->src.y1 != state->src.y1 ||
+	    old_state->fb != state->fb) {
+		const struct drm_format_info *format;
+		u16 src_x, pitches[3];
+		u32 addrs[2][3];
 
-		armada_drm_plane_calc_addrs(addrs, &dfb->fb, src_x, src_y);
+		armada_drm_plane_calc(state, addrs, pitches, false);
 
-		armada_reg_queue_set(regs, idx, addrs[0],
+		armada_reg_queue_set(regs, idx, addrs[0][0],
 				     LCD_SPU_DMA_START_ADDR_Y0);
-		armada_reg_queue_set(regs, idx, addrs[1],
+		armada_reg_queue_set(regs, idx, addrs[0][1],
 				     LCD_SPU_DMA_START_ADDR_U0);
-		armada_reg_queue_set(regs, idx, addrs[2],
+		armada_reg_queue_set(regs, idx, addrs[0][2],
 				     LCD_SPU_DMA_START_ADDR_V0);
-		armada_reg_queue_set(regs, idx, addrs[0],
+		armada_reg_queue_set(regs, idx, addrs[1][0],
 				     LCD_SPU_DMA_START_ADDR_Y1);
-		armada_reg_queue_set(regs, idx, addrs[1],
+		armada_reg_queue_set(regs, idx, addrs[1][1],
 				     LCD_SPU_DMA_START_ADDR_U1);
-		armada_reg_queue_set(regs, idx, addrs[2],
+		armada_reg_queue_set(regs, idx, addrs[1][2],
 				     LCD_SPU_DMA_START_ADDR_V1);
 
-		val = dfb->fb.pitches[0] << 16 | dfb->fb.pitches[0];
-		armada_reg_queue_set(regs, idx, val,
-				     LCD_SPU_DMA_PITCH_YC);
-		val = dfb->fb.pitches[1] << 16 | dfb->fb.pitches[2];
-		armada_reg_queue_set(regs, idx, val,
-				     LCD_SPU_DMA_PITCH_UV);
-	}
+		val = pitches[0] << 16 | pitches[0];
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_DMA_PITCH_YC);
+		val = pitches[1] << 16 | pitches[2];
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_DMA_PITCH_UV);
 
-	val = (drm_rect_height(&state->src) & 0xffff0000) |
-	       drm_rect_width(&state->src) >> 16;
-	if (dplane->base.state.src_hw != val) {
-		dplane->base.state.src_hw = val;
-		armada_reg_queue_set(regs, idx, val,
-				     LCD_SPU_DMA_HPXL_VLN);
-	}
+		cfg = CFG_DMA_FMT(drm_fb_to_armada_fb(state->fb)->fmt) |
+		      CFG_DMA_MOD(drm_fb_to_armada_fb(state->fb)->mod) |
+		      CFG_CBSH_ENA;
+		if (state->visible)
+			cfg |= CFG_DMA_ENA;
 
-	val = drm_rect_height(&state->dst) << 16 | drm_rect_width(&state->dst);
-	if (dplane->base.state.dst_hw != val) {
-		dplane->base.state.dst_hw = val;
-		armada_reg_queue_set(regs, idx, val,
-				     LCD_SPU_DZM_HPXL_VLN);
+		/*
+		 * Shifting a YUV packed format image by one pixel causes the
+		 * U/V planes to swap.  Compensate for it by also toggling
+		 * the UV swap.
+		 */
+		format = state->fb->format;
+		src_x = state->src.x1 >> 16;
+		if (format->num_planes == 1 && src_x & (format->hsub - 1))
+			cfg ^= CFG_DMA_MOD(CFG_SWAPUV);
+		cfg_mask = CFG_CBSH_ENA | CFG_DMAFORMAT |
+			   CFG_DMA_MOD(CFG_SWAPRB | CFG_SWAPUV |
+				       CFG_SWAPYU | CFG_YUV2RGB) |
+			   CFG_DMA_FTOGGLE | CFG_DMA_TSTMODE |
+			   CFG_DMA_ENA;
+	} else if (old_state->visible != state->visible) {
+		cfg = state->visible ? CFG_DMA_ENA : 0;
+		cfg_mask = CFG_DMA_ENA;
+	} else {
+		cfg = cfg_mask = 0;
 	}
-
-	val = state->dst.y1 << 16 | state->dst.x1;
-	if (dplane->base.state.dst_yx != val) {
-		dplane->base.state.dst_yx = val;
-		armada_reg_queue_set(regs, idx, val,
-				     LCD_SPU_DMA_OVSA_HPXL_VLN);
+	if (drm_rect_width(&old_state->src) != drm_rect_width(&state->src) ||
+	    drm_rect_width(&old_state->dst) != drm_rect_width(&state->dst)) {
+		cfg_mask |= CFG_DMA_HSMOOTH;
+		if (drm_rect_width(&state->src) >> 16 !=
+		    drm_rect_width(&state->dst))
+			cfg |= CFG_DMA_HSMOOTH;
 	}
 
-	if (dplane->base.state.ctrl0 != ctrl0) {
-		dplane->base.state.ctrl0 = ctrl0;
-		armada_reg_queue_mod(regs, idx, ctrl0,
-			CFG_CBSH_ENA | CFG_DMAFORMAT | CFG_DMA_FTOGGLE |
-			CFG_DMA_HSMOOTH | CFG_DMA_TSTMODE |
-			CFG_DMA_MOD(CFG_SWAPRB | CFG_SWAPUV | CFG_SWAPYU |
-			CFG_YUV2RGB) | CFG_DMA_ENA,
-			LCD_SPU_DMA_CTRL0);
-		dplane->base.state.vsync_update = true;
-	}
+	if (cfg_mask)
+		armada_reg_queue_mod(regs, idx, cfg, cfg_mask,
+				     LCD_SPU_DMA_CTRL0);
+
+	val = armada_spu_contrast(state);
+	if ((!old_state->visible && state->visible) ||
+	    armada_spu_contrast(old_state) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_CONTRAST);
+	val = armada_spu_saturation(state);
+	if ((!old_state->visible && state->visible) ||
+	    armada_spu_saturation(old_state) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_SATURATION);
+	if (!old_state->visible && state->visible)
+		armada_reg_queue_set(regs, idx, 0x00002000, LCD_SPU_CBSH_HUE);
+	val = armada_csc(state);
+	if ((!old_state->visible && state->visible) ||
+	    armada_csc(old_state) != val)
+		armada_reg_queue_mod(regs, idx, val, CFG_CSC_MASK,
+				     LCD_SPU_IOPAD_CONTROL);
+	val = drm_to_overlay_state(state)->colorkey_yr;
+	if ((!old_state->visible && state->visible) ||
+	    drm_to_overlay_state(old_state)->colorkey_yr != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_COLORKEY_Y);
+	val = drm_to_overlay_state(state)->colorkey_ug;
+	if ((!old_state->visible && state->visible) ||
+	    drm_to_overlay_state(old_state)->colorkey_ug != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_COLORKEY_U);
+	val = drm_to_overlay_state(state)->colorkey_vb;
+	if ((!old_state->visible && state->visible) ||
+	    drm_to_overlay_state(old_state)->colorkey_vb != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_COLORKEY_V);
+	val = drm_to_overlay_state(state)->colorkey_mode;
+	if ((!old_state->visible && state->visible) ||
+	    drm_to_overlay_state(old_state)->colorkey_mode != val)
+		armada_reg_queue_mod(regs, idx, val, CFG_CKMODE_MASK |
+				     CFG_ALPHAM_MASK | CFG_ALPHA_MASK,
+				     LCD_SPU_DMA_CTRL1);
+	val = drm_to_overlay_state(state)->colorkey_enable;
+	if (((!old_state->visible && state->visible) ||
+	     drm_to_overlay_state(old_state)->colorkey_enable != val) &&
+	    dcrtc->variant->has_spu_adv_reg)
+		armada_reg_queue_mod(regs, idx, val, ADV_GRACOLORKEY |
+				     ADV_VIDCOLORKEY, LCD_SPU_ADV_REG);
+
+	dcrtc->regs_idx += idx;
+}
+
+static void armada_drm_overlay_plane_atomic_disable(struct drm_plane *plane,
+	struct drm_plane_state *old_state)
+{
+	struct armada_crtc *dcrtc;
+	struct armada_regs *regs;
+	unsigned int idx = 0;
+
+	DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name);
+
+	if (!old_state->crtc)
+		return;
 
-	dplane->base.state.changed = idx != 0;
+	DRM_DEBUG_KMS("[PLANE:%d:%s] was on [CRTC:%d:%s] with [FB:%d]\n",
+		plane->base.id, plane->name,
+		old_state->crtc->base.id, old_state->crtc->name,
+		old_state->fb->base.id);
 
-	armada_reg_queue_end(regs, idx);
+	dcrtc = drm_to_armada_crtc(old_state->crtc);
+	regs = dcrtc->regs + dcrtc->regs_idx;
+
+	/* Disable plane and power down the YUV FIFOs */
+	armada_reg_queue_mod(regs, idx, 0, CFG_DMA_ENA, LCD_SPU_DMA_CTRL0);
+	armada_reg_queue_mod(regs, idx, CFG_PDWN16x66 | CFG_PDWN32x66, 0,
+			     LCD_SPU_SRAM_PARA1);
+
+	dcrtc->regs_idx += idx;
 }
 
+static const struct drm_plane_helper_funcs armada_overlay_plane_helper_funcs = {
+	.prepare_fb	= armada_drm_plane_prepare_fb,
+	.cleanup_fb	= armada_drm_plane_cleanup_fb,
+	.atomic_check	= armada_drm_plane_atomic_check,
+	.atomic_update	= armada_drm_overlay_plane_atomic_update,
+	.atomic_disable	= armada_drm_overlay_plane_atomic_disable,
+};
+
 static int
-armada_ovl_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
+armada_overlay_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 	struct drm_framebuffer *fb,
 	int crtc_x, int crtc_y, unsigned crtc_w, unsigned crtc_h,
 	uint32_t src_x, uint32_t src_y, uint32_t src_w, uint32_t src_h,
 	struct drm_modeset_acquire_ctx *ctx)
 {
-	struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane);
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	struct armada_plane_work *work;
-	struct drm_plane_state state = {
-		.plane = plane,
-		.crtc = crtc,
-		.fb = fb,
-		.src_x = src_x,
-		.src_y = src_y,
-		.src_w = src_w,
-		.src_h = src_h,
-		.crtc_x = crtc_x,
-		.crtc_y = crtc_y,
-		.crtc_w = crtc_w,
-		.crtc_h = crtc_h,
-		.rotation = DRM_MODE_ROTATE_0,
-	};
-	struct drm_crtc_state crtc_state = {
-		.crtc = crtc,
-		.enable = crtc->enabled,
-		.mode = crtc->mode,
-	};
-	int ret;
+	struct drm_atomic_state *state;
+	struct drm_plane_state *plane_state;
+	int ret = 0;
 
 	trace_armada_ovl_plane_update(plane, crtc, fb,
 				 crtc_x, crtc_y, crtc_w, crtc_h,
 				 src_x, src_y, src_w, src_h);
 
-	ret = drm_atomic_helper_check_plane_state(&state, &crtc_state, 0,
-						  INT_MAX, true, false);
-	if (ret)
-		return ret;
-
-	work = &dplane->base.works[dplane->base.next_work];
-
-	if (plane->fb != fb) {
-		/*
-		 * Take a reference on the new framebuffer - we want to
-		 * hold on to it while the hardware is displaying it.
-		 */
-		drm_framebuffer_reference(fb);
+	state = drm_atomic_state_alloc(plane->dev);
+	if (!state)
+		return -ENOMEM;
 
-		work->old_fb = plane->fb;
-	} else {
-		work->old_fb = NULL;
+	state->acquire_ctx = ctx;
+	plane_state = drm_atomic_get_plane_state(state, plane);
+	if (IS_ERR(plane_state)) {
+		ret = PTR_ERR(plane_state);
+		goto fail;
 	}
 
-	armada_ovl_plane_update_state(&state, work->regs);
-
-	if (!dplane->base.state.changed)
-		return 0;
-
-	/* Wait for pending work to complete */
-	if (armada_drm_plane_work_wait(&dplane->base, HZ / 25) == 0)
-		armada_drm_plane_work_cancel(dcrtc, &dplane->base);
+	ret = drm_atomic_set_crtc_for_plane(plane_state, crtc);
+	if (ret != 0)
+		goto fail;
+
+	drm_atomic_set_fb_for_plane(plane_state, fb);
+	plane_state->crtc_x = crtc_x;
+	plane_state->crtc_y = crtc_y;
+	plane_state->crtc_h = crtc_h;
+	plane_state->crtc_w = crtc_w;
+	plane_state->src_x = src_x;
+	plane_state->src_y = src_y;
+	plane_state->src_h = src_h;
+	plane_state->src_w = src_w;
+
+	ret = drm_atomic_nonblocking_commit(state);
+fail:
+	drm_atomic_state_put(state);
+	return ret;
+}
 
-	/* Just updating the position/size? */
-	if (!dplane->base.state.vsync_update) {
-		armada_ovl_plane_work(dcrtc, work);
-		return 0;
-	}
+static void armada_ovl_plane_destroy(struct drm_plane *plane)
+{
+	drm_plane_cleanup(plane);
+	kfree(plane);
+}
 
-	if (!dcrtc->plane) {
-		dcrtc->plane = plane;
-		armada_ovl_update_attr(&dplane->prop, dcrtc);
+static void armada_overlay_reset(struct drm_plane *plane)
+{
+	struct armada_overlay_state *state;
+
+	if (plane->state)
+		__drm_atomic_helper_plane_destroy_state(plane->state);
+	kfree(plane->state);
+
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	if (state) {
+		state->base.plane = plane;
+		state->base.color_encoding = DEFAULT_ENCODING;
+		state->base.color_range = DRM_COLOR_YCBCR_LIMITED_RANGE;
+		state->base.rotation = DRM_MODE_ROTATE_0;
+		state->colorkey_yr = 0xfefefe00;
+		state->colorkey_ug = 0x01010100;
+		state->colorkey_vb = 0x01010100;
+		state->colorkey_mode = CFG_CKMODE(CKMODE_RGB) |
+				       CFG_ALPHAM_GRA | CFG_ALPHA(0);
+		state->colorkey_enable = ADV_GRACOLORKEY;
+		state->brightness = DEFAULT_BRIGHTNESS;
+		state->contrast = DEFAULT_CONTRAST;
+		state->saturation = DEFAULT_SATURATION;
 	}
-
-	/* Queue it for update on the next interrupt if we are enabled */
-	ret = armada_drm_plane_work_queue(dcrtc, work);
-	if (ret)
-		DRM_ERROR("failed to queue plane work: %d\n", ret);
-
-	dplane->base.next_work = !dplane->base.next_work;
-
-	return 0;
+	plane->state = &state->base;
 }
 
-static void armada_ovl_plane_destroy(struct drm_plane *plane)
+struct drm_plane_state *
+armada_overlay_duplicate_state(struct drm_plane *plane)
 {
-	struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane);
+	struct armada_overlay_state *state;
 
-	drm_plane_cleanup(plane);
+	if (WARN_ON(!plane->state))
+		return NULL;
 
-	kfree(dplane);
+	state = kmemdup(plane->state, sizeof(*state), GFP_KERNEL);
+	if (state)
+		__drm_atomic_helper_plane_duplicate_state(plane, &state->base);
+	return &state->base;
 }
 
-static int armada_ovl_plane_set_property(struct drm_plane *plane,
-	struct drm_property *property, uint64_t val)
+static int armada_overlay_set_property(struct drm_plane *plane,
+	struct drm_plane_state *state, struct drm_property *property,
+	uint64_t val)
 {
 	struct armada_private *priv = plane->dev->dev_private;
-	struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane);
-	bool update_attr = false;
 
+#define K2R(val) (((val) >> 0) & 0xff)
+#define K2G(val) (((val) >> 8) & 0xff)
+#define K2B(val) (((val) >> 16) & 0xff)
 	if (property == priv->colorkey_prop) {
 #define CCC(v) ((v) << 24 | (v) << 16 | (v) << 8)
-		dplane->prop.colorkey_yr = CCC(K2R(val));
-		dplane->prop.colorkey_ug = CCC(K2G(val));
-		dplane->prop.colorkey_vb = CCC(K2B(val));
+		drm_to_overlay_state(state)->colorkey_yr = CCC(K2R(val));
+		drm_to_overlay_state(state)->colorkey_ug = CCC(K2G(val));
+		drm_to_overlay_state(state)->colorkey_vb = CCC(K2B(val));
 #undef CCC
-		update_attr = true;
 	} else if (property == priv->colorkey_min_prop) {
-		dplane->prop.colorkey_yr &= ~0x00ff0000;
-		dplane->prop.colorkey_yr |= K2R(val) << 16;
-		dplane->prop.colorkey_ug &= ~0x00ff0000;
-		dplane->prop.colorkey_ug |= K2G(val) << 16;
-		dplane->prop.colorkey_vb &= ~0x00ff0000;
-		dplane->prop.colorkey_vb |= K2B(val) << 16;
-		update_attr = true;
+		drm_to_overlay_state(state)->colorkey_yr &= ~0x00ff0000;
+		drm_to_overlay_state(state)->colorkey_yr |= K2R(val) << 16;
+		drm_to_overlay_state(state)->colorkey_ug &= ~0x00ff0000;
+		drm_to_overlay_state(state)->colorkey_ug |= K2G(val) << 16;
+		drm_to_overlay_state(state)->colorkey_vb &= ~0x00ff0000;
+		drm_to_overlay_state(state)->colorkey_vb |= K2B(val) << 16;
 	} else if (property == priv->colorkey_max_prop) {
-		dplane->prop.colorkey_yr &= ~0xff000000;
-		dplane->prop.colorkey_yr |= K2R(val) << 24;
-		dplane->prop.colorkey_ug &= ~0xff000000;
-		dplane->prop.colorkey_ug |= K2G(val) << 24;
-		dplane->prop.colorkey_vb &= ~0xff000000;
-		dplane->prop.colorkey_vb |= K2B(val) << 24;
-		update_attr = true;
+		drm_to_overlay_state(state)->colorkey_yr &= ~0xff000000;
+		drm_to_overlay_state(state)->colorkey_yr |= K2R(val) << 24;
+		drm_to_overlay_state(state)->colorkey_ug &= ~0xff000000;
+		drm_to_overlay_state(state)->colorkey_ug |= K2G(val) << 24;
+		drm_to_overlay_state(state)->colorkey_vb &= ~0xff000000;
+		drm_to_overlay_state(state)->colorkey_vb |= K2B(val) << 24;
 	} else if (property == priv->colorkey_val_prop) {
-		dplane->prop.colorkey_yr &= ~0x0000ff00;
-		dplane->prop.colorkey_yr |= K2R(val) << 8;
-		dplane->prop.colorkey_ug &= ~0x0000ff00;
-		dplane->prop.colorkey_ug |= K2G(val) << 8;
-		dplane->prop.colorkey_vb &= ~0x0000ff00;
-		dplane->prop.colorkey_vb |= K2B(val) << 8;
-		update_attr = true;
+		drm_to_overlay_state(state)->colorkey_yr &= ~0x0000ff00;
+		drm_to_overlay_state(state)->colorkey_yr |= K2R(val) << 8;
+		drm_to_overlay_state(state)->colorkey_ug &= ~0x0000ff00;
+		drm_to_overlay_state(state)->colorkey_ug |= K2G(val) << 8;
+		drm_to_overlay_state(state)->colorkey_vb &= ~0x0000ff00;
+		drm_to_overlay_state(state)->colorkey_vb |= K2B(val) << 8;
 	} else if (property == priv->colorkey_alpha_prop) {
-		dplane->prop.colorkey_yr &= ~0x000000ff;
-		dplane->prop.colorkey_yr |= K2R(val);
-		dplane->prop.colorkey_ug &= ~0x000000ff;
-		dplane->prop.colorkey_ug |= K2G(val);
-		dplane->prop.colorkey_vb &= ~0x000000ff;
-		dplane->prop.colorkey_vb |= K2B(val);
-		update_attr = true;
+		drm_to_overlay_state(state)->colorkey_yr &= ~0x000000ff;
+		drm_to_overlay_state(state)->colorkey_yr |= K2R(val);
+		drm_to_overlay_state(state)->colorkey_ug &= ~0x000000ff;
+		drm_to_overlay_state(state)->colorkey_ug |= K2G(val);
+		drm_to_overlay_state(state)->colorkey_vb &= ~0x000000ff;
+		drm_to_overlay_state(state)->colorkey_vb |= K2B(val);
 	} else if (property == priv->colorkey_mode_prop) {
 		if (val == CKMODE_DISABLE) {
-			dplane->prop.colorkey_mode =
+			drm_to_overlay_state(state)->colorkey_mode =
 				CFG_CKMODE(CKMODE_DISABLE) |
 				CFG_ALPHAM_CFG | CFG_ALPHA(255);
-			dplane->prop.colorkey_enable = 0;
+			drm_to_overlay_state(state)->colorkey_enable = 0;
 		} else {
-			dplane->prop.colorkey_mode =
+			drm_to_overlay_state(state)->colorkey_mode =
 				CFG_CKMODE(val) |
 				CFG_ALPHAM_GRA | CFG_ALPHA(0);
-			dplane->prop.colorkey_enable = ADV_GRACOLORKEY;
+			drm_to_overlay_state(state)->colorkey_enable =
+				ADV_GRACOLORKEY;
 		}
-		update_attr = true;
 	} else if (property == priv->brightness_prop) {
-		dplane->prop.brightness = val - 256;
-		update_attr = true;
+		drm_to_overlay_state(state)->brightness = val - 256;
 	} else if (property == priv->contrast_prop) {
-		dplane->prop.contrast = val;
-		update_attr = true;
+		drm_to_overlay_state(state)->contrast = val;
 	} else if (property == priv->saturation_prop) {
-		dplane->prop.saturation = val;
-		update_attr = true;
+		drm_to_overlay_state(state)->saturation = val;
+	} else {
+		return -EINVAL;
 	}
+	return 0;
+}
 
-	if (update_attr && dplane->base.base.crtc)
-		armada_ovl_update_attr(&dplane->prop,
-				       drm_to_armada_crtc(dplane->base.base.crtc));
+static int armada_overlay_get_property(struct drm_plane *plane,
+	const struct drm_plane_state *state, struct drm_property *property,
+	uint64_t *val)
+{
+	struct armada_private *priv = plane->dev->dev_private;
 
+#define C2K(c,s)	(((c) >> (s)) & 0xff)
+#define R2BGR(r,g,b,s)	(C2K(r,s) << 0 | C2K(g,s) << 8 | C2K(b,s) << 16)
+	if (property == priv->colorkey_prop) {
+		/* Do best-efforts here for this property */
+		*val = R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+			     drm_to_overlay_state(state)->colorkey_ug,
+			     drm_to_overlay_state(state)->colorkey_vb, 16);
+		/* If min != max, or min != val, error out */
+		if (*val != R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+				  drm_to_overlay_state(state)->colorkey_ug,
+				  drm_to_overlay_state(state)->colorkey_vb, 24) ||
+		    *val != R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+				  drm_to_overlay_state(state)->colorkey_ug,
+				  drm_to_overlay_state(state)->colorkey_vb, 8))
+			return -EINVAL;
+	} else if (property == priv->colorkey_min_prop) {
+		*val = R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+			     drm_to_overlay_state(state)->colorkey_ug,
+			     drm_to_overlay_state(state)->colorkey_vb, 16);
+	} else if (property == priv->colorkey_max_prop) {
+		*val = R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+			     drm_to_overlay_state(state)->colorkey_ug,
+			     drm_to_overlay_state(state)->colorkey_vb, 24);
+	} else if (property == priv->colorkey_val_prop) {
+		*val = R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+			     drm_to_overlay_state(state)->colorkey_ug,
+			     drm_to_overlay_state(state)->colorkey_vb, 8);
+	} else if (property == priv->colorkey_alpha_prop) {
+		*val = R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+			     drm_to_overlay_state(state)->colorkey_ug,
+			     drm_to_overlay_state(state)->colorkey_vb, 0);
+	} else if (property == priv->colorkey_mode_prop) {
+		*val = (drm_to_overlay_state(state)->colorkey_mode &
+			CFG_CKMODE_MASK) >> ffs(CFG_CKMODE_MASK);
+	} else if (property == priv->brightness_prop) {
+		*val = drm_to_overlay_state(state)->brightness + 256;
+	} else if (property == priv->contrast_prop) {
+		*val = drm_to_overlay_state(state)->contrast;
+	} else if (property == priv->saturation_prop) {
+		*val = drm_to_overlay_state(state)->saturation;
+	} else {
+		return -EINVAL;
+	}
 	return 0;
 }
 
 static const struct drm_plane_funcs armada_ovl_plane_funcs = {
-	.update_plane	= armada_ovl_plane_update,
-	.disable_plane	= armada_drm_plane_disable,
+	.update_plane	= armada_overlay_plane_update,
+	.disable_plane	= drm_atomic_helper_disable_plane,
 	.destroy	= armada_ovl_plane_destroy,
-	.set_property	= armada_ovl_plane_set_property,
+	.reset		= armada_overlay_reset,
+	.atomic_duplicate_state = armada_overlay_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
+	.atomic_set_property = armada_overlay_set_property,
+	.atomic_get_property = armada_overlay_get_property,
 };
 
 static const uint32_t armada_ovl_formats[] = {
@@ -431,48 +541,31 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs)
 {
 	struct armada_private *priv = dev->dev_private;
 	struct drm_mode_object *mobj;
-	struct armada_ovl_plane *dplane;
+	struct drm_plane *overlay;
 	int ret;
 
 	ret = armada_overlay_create_properties(dev);
 	if (ret)
 		return ret;
 
-	dplane = kzalloc(sizeof(*dplane), GFP_KERNEL);
-	if (!dplane)
+	overlay = kzalloc(sizeof(*overlay), GFP_KERNEL);
+	if (!overlay)
 		return -ENOMEM;
 
-	ret = armada_drm_plane_init(&dplane->base);
-	if (ret) {
-		kfree(dplane);
-		return ret;
-	}
-
-	dplane->base.works[0].fn = armada_ovl_plane_work;
-	dplane->base.works[1].fn = armada_ovl_plane_work;
+	drm_plane_helper_add(overlay, &armada_overlay_plane_helper_funcs);
 
-	ret = drm_universal_plane_init(dev, &dplane->base.base, crtcs,
+	ret = drm_universal_plane_init(dev, overlay, crtcs,
 				       &armada_ovl_plane_funcs,
 				       armada_ovl_formats,
 				       ARRAY_SIZE(armada_ovl_formats),
 				       NULL,
 				       DRM_PLANE_TYPE_OVERLAY, NULL);
 	if (ret) {
-		kfree(dplane);
+		kfree(overlay);
 		return ret;
 	}
 
-	dplane->prop.colorkey_yr = 0xfefefe00;
-	dplane->prop.colorkey_ug = 0x01010100;
-	dplane->prop.colorkey_vb = 0x01010100;
-	dplane->prop.colorkey_mode = CFG_CKMODE(CKMODE_RGB) |
-				     CFG_ALPHAM_GRA | CFG_ALPHA(0);
-	dplane->prop.colorkey_enable = ADV_GRACOLORKEY;
-	dplane->prop.brightness = 0;
-	dplane->prop.contrast = 0x4000;
-	dplane->prop.saturation = 0x4000;
-
-	mobj = &dplane->base.base.base;
+	mobj = &overlay->base;
 	drm_object_attach_property(mobj, priv->colorkey_prop,
 				   0x0101fe);
 	drm_object_attach_property(mobj, priv->colorkey_min_prop,
@@ -485,11 +578,19 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs)
 				   0x000000);
 	drm_object_attach_property(mobj, priv->colorkey_mode_prop,
 				   CKMODE_RGB);
-	drm_object_attach_property(mobj, priv->brightness_prop, 256);
+	drm_object_attach_property(mobj, priv->brightness_prop,
+				   256 + DEFAULT_BRIGHTNESS);
 	drm_object_attach_property(mobj, priv->contrast_prop,
-				   dplane->prop.contrast);
+				   DEFAULT_CONTRAST);
 	drm_object_attach_property(mobj, priv->saturation_prop,
-				   dplane->prop.saturation);
+				   DEFAULT_SATURATION);
 
-	return 0;
+	ret = drm_plane_create_color_properties(overlay,
+						BIT(DRM_COLOR_YCBCR_BT601) |
+						BIT(DRM_COLOR_YCBCR_BT709),
+						BIT(DRM_COLOR_YCBCR_LIMITED_RANGE),
+						DEFAULT_ENCODING,
+						DRM_COLOR_YCBCR_LIMITED_RANGE);
+
+	return ret;
 }
diff --git a/drivers/gpu/drm/armada/armada_plane.c b/drivers/gpu/drm/armada/armada_plane.c
new file mode 100644
index 000000000000..9f36423dd394
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_plane.c
@@ -0,0 +1,289 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *  Rewritten from the dovefb driver, and Armada510 manuals.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <drm/drmP.h>
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_plane_helper.h>
+#include "armada_crtc.h"
+#include "armada_drm.h"
+#include "armada_fb.h"
+#include "armada_gem.h"
+#include "armada_hw.h"
+#include "armada_plane.h"
+#include "armada_trace.h"
+
+static const uint32_t armada_primary_formats[] = {
+	DRM_FORMAT_UYVY,
+	DRM_FORMAT_YUYV,
+	DRM_FORMAT_VYUY,
+	DRM_FORMAT_YVYU,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_RGB888,
+	DRM_FORMAT_BGR888,
+	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_ABGR1555,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_BGR565,
+};
+
+void armada_drm_plane_calc(struct drm_plane_state *state, u32 addrs[2][3],
+	u16 pitches[3], bool interlaced)
+{
+	struct drm_framebuffer *fb = state->fb;
+	const struct drm_format_info *format = fb->format;
+	unsigned int num_planes = format->num_planes;
+	unsigned int x = state->src.x1 >> 16;
+	unsigned int y = state->src.y1 >> 16;
+	u32 addr = drm_fb_obj(fb)->dev_addr;
+	int i;
+
+	DRM_DEBUG_KMS("pitch %u x %d y %d bpp %d\n",
+		      fb->pitches[0], x, y, format->cpp[0] * 8);
+
+	if (num_planes > 3)
+		num_planes = 3;
+
+	addrs[0][0] = addr + fb->offsets[0] + y * fb->pitches[0] +
+		      x * format->cpp[0];
+	pitches[0] = fb->pitches[0];
+
+	y /= format->vsub;
+	x /= format->hsub;
+
+	for (i = 1; i < num_planes; i++) {
+		addrs[0][i] = addr + fb->offsets[i] + y * fb->pitches[i] +
+			      x * format->cpp[i];
+		pitches[i] = fb->pitches[i];
+	}
+	for (; i < 3; i++) {
+		addrs[0][i] = 0;
+		pitches[i] = 0;
+	}
+	if (interlaced) {
+		for (i = 0; i < 3; i++) {
+			addrs[1][i] = addrs[0][i] + pitches[i];
+			pitches[i] *= 2;
+		}
+	} else {
+		for (i = 0; i < 3; i++)
+			addrs[1][i] = addrs[0][i];
+	}
+}
+
+static unsigned armada_drm_crtc_calc_fb(struct drm_plane_state *state,
+	struct armada_regs *regs, bool interlaced)
+{
+	u16 pitches[3];
+	u32 addrs[2][3];
+	unsigned i = 0;
+
+	armada_drm_plane_calc(state, addrs, pitches, interlaced);
+
+	/* write offset, base, and pitch */
+	armada_reg_queue_set(regs, i, addrs[0][0], LCD_CFG_GRA_START_ADDR0);
+	armada_reg_queue_set(regs, i, addrs[1][0], LCD_CFG_GRA_START_ADDR1);
+	armada_reg_queue_mod(regs, i, pitches[0], 0xffff, LCD_CFG_GRA_PITCH);
+
+	return i;
+}
+
+int armada_drm_plane_prepare_fb(struct drm_plane *plane,
+	struct drm_plane_state *state)
+{
+	DRM_DEBUG_KMS("[PLANE:%d:%s] [FB:%d]\n",
+		plane->base.id, plane->name,
+		state->fb ? state->fb->base.id : 0);
+
+	/*
+	 * Take a reference on the new framebuffer - we want to
+	 * hold on to it while the hardware is displaying it.
+	 */
+	if (state->fb)
+		drm_framebuffer_get(state->fb);
+	return 0;
+}
+
+void armada_drm_plane_cleanup_fb(struct drm_plane *plane,
+	struct drm_plane_state *old_state)
+{
+	DRM_DEBUG_KMS("[PLANE:%d:%s] [FB:%d]\n",
+		plane->base.id, plane->name,
+		old_state->fb ? old_state->fb->base.id : 0);
+
+	if (old_state->fb)
+		drm_framebuffer_put(old_state->fb);
+}
+
+int armada_drm_plane_atomic_check(struct drm_plane *plane,
+	struct drm_plane_state *state)
+{
+	if (state->fb && !WARN_ON(!state->crtc)) {
+		struct drm_crtc *crtc = state->crtc;
+		struct drm_crtc_state *crtc_state;
+
+		if (state->state)
+			crtc_state = drm_atomic_get_existing_crtc_state(state->state, crtc);
+		else
+			crtc_state = crtc->state;
+		return drm_atomic_helper_check_plane_state(state, crtc_state,
+							   0, INT_MAX,
+							   true, false);
+	} else {
+		state->visible = false;
+	}
+	return 0;
+}
+
+static void armada_drm_primary_plane_atomic_update(struct drm_plane *plane,
+	struct drm_plane_state *old_state)
+{
+	struct drm_plane_state *state = plane->state;
+	struct armada_crtc *dcrtc;
+	struct armada_regs *regs;
+	u32 cfg, cfg_mask, val;
+	unsigned int idx;
+
+	DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name);
+
+	if (!state->fb || WARN_ON(!state->crtc))
+		return;
+
+	DRM_DEBUG_KMS("[PLANE:%d:%s] is on [CRTC:%d:%s] with [FB:%d] visible %u->%u\n",
+		plane->base.id, plane->name,
+		state->crtc->base.id, state->crtc->name,
+		state->fb->base.id,
+		old_state->visible, state->visible);
+
+	dcrtc = drm_to_armada_crtc(state->crtc);
+	regs = dcrtc->regs + dcrtc->regs_idx;
+
+	idx = 0;
+	if (!old_state->visible && state->visible) {
+		val = CFG_PDWN64x66;
+		if (drm_fb_to_armada_fb(state->fb)->fmt > CFG_420)
+			val |= CFG_PDWN256x24;
+		armada_reg_queue_mod(regs, idx, 0, val, LCD_SPU_SRAM_PARA1);
+	}
+	val = armada_rect_hw_fp(&state->src);
+	if (armada_rect_hw_fp(&old_state->src) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_GRA_HPXL_VLN);
+	val = armada_rect_yx(&state->dst);
+	if (armada_rect_yx(&old_state->dst) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_GRA_OVSA_HPXL_VLN);
+	val = armada_rect_hw(&state->dst);
+	if (armada_rect_hw(&old_state->dst) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_GZM_HPXL_VLN);
+	if (old_state->src.x1 != state->src.x1 ||
+	    old_state->src.y1 != state->src.y1 ||
+	    old_state->fb != state->fb ||
+	    state->crtc->state->mode_changed) {
+		idx += armada_drm_crtc_calc_fb(state, regs + idx,
+					       dcrtc->interlaced);
+	}
+	if (old_state->fb != state->fb ||
+	    state->crtc->state->mode_changed) {
+		cfg = CFG_GRA_FMT(drm_fb_to_armada_fb(state->fb)->fmt) |
+		      CFG_GRA_MOD(drm_fb_to_armada_fb(state->fb)->mod);
+		if (drm_fb_to_armada_fb(state->fb)->fmt > CFG_420)
+			cfg |= CFG_PALETTE_ENA;
+		if (state->visible)
+			cfg |= CFG_GRA_ENA;
+		if (dcrtc->interlaced)
+			cfg |= CFG_GRA_FTOGGLE;
+		cfg_mask = CFG_GRAFORMAT |
+			   CFG_GRA_MOD(CFG_SWAPRB | CFG_SWAPUV |
+				       CFG_SWAPYU | CFG_YUV2RGB) |
+			   CFG_PALETTE_ENA | CFG_GRA_FTOGGLE |
+			   CFG_GRA_ENA;
+	} else if (old_state->visible != state->visible) {
+		cfg = state->visible ? CFG_GRA_ENA : 0;
+		cfg_mask = CFG_GRA_ENA;
+	} else {
+		cfg = cfg_mask = 0;
+	}
+	if (drm_rect_width(&old_state->src) != drm_rect_width(&state->src) ||
+	    drm_rect_width(&old_state->dst) != drm_rect_width(&state->dst)) {
+		cfg_mask |= CFG_GRA_HSMOOTH;
+		if (drm_rect_width(&state->src) >> 16 !=
+		    drm_rect_width(&state->dst))
+			cfg |= CFG_GRA_HSMOOTH;
+	}
+
+	if (cfg_mask)
+		armada_reg_queue_mod(regs, idx, cfg, cfg_mask,
+				     LCD_SPU_DMA_CTRL0);
+
+	dcrtc->regs_idx += idx;
+}
+
+static void armada_drm_primary_plane_atomic_disable(struct drm_plane *plane,
+	struct drm_plane_state *old_state)
+{
+	struct armada_crtc *dcrtc;
+	struct armada_regs *regs;
+	unsigned int idx = 0;
+
+	DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name);
+
+	if (!old_state->crtc)
+		return;
+
+	DRM_DEBUG_KMS("[PLANE:%d:%s] was on [CRTC:%d:%s] with [FB:%d]\n",
+		plane->base.id, plane->name,
+		old_state->crtc->base.id, old_state->crtc->name,
+		old_state->fb->base.id);
+
+	dcrtc = drm_to_armada_crtc(old_state->crtc);
+	regs = dcrtc->regs + dcrtc->regs_idx;
+
+	/* Disable plane and power down most RAMs and FIFOs */
+	armada_reg_queue_mod(regs, idx, 0, CFG_GRA_ENA, LCD_SPU_DMA_CTRL0);
+	armada_reg_queue_mod(regs, idx, CFG_PDWN256x32 | CFG_PDWN256x24 |
+			     CFG_PDWN256x8 | CFG_PDWN32x32 | CFG_PDWN64x66,
+			     0, LCD_SPU_SRAM_PARA1);
+
+	dcrtc->regs_idx += idx;
+}
+
+static const struct drm_plane_helper_funcs armada_primary_plane_helper_funcs = {
+	.prepare_fb	= armada_drm_plane_prepare_fb,
+	.cleanup_fb	= armada_drm_plane_cleanup_fb,
+	.atomic_check	= armada_drm_plane_atomic_check,
+	.atomic_update	= armada_drm_primary_plane_atomic_update,
+	.atomic_disable	= armada_drm_primary_plane_atomic_disable,
+};
+
+static const struct drm_plane_funcs armada_primary_plane_funcs = {
+	.update_plane	= drm_atomic_helper_update_plane,
+	.disable_plane	= drm_atomic_helper_disable_plane,
+	.destroy	= drm_primary_helper_destroy,
+	.reset		= drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
+};
+
+int armada_drm_primary_plane_init(struct drm_device *drm,
+	struct drm_plane *primary)
+{
+	int ret;
+
+	drm_plane_helper_add(primary, &armada_primary_plane_helper_funcs);
+
+	ret = drm_universal_plane_init(drm, primary, 0,
+				       &armada_primary_plane_funcs,
+				       armada_primary_formats,
+				       ARRAY_SIZE(armada_primary_formats),
+				       NULL,
+				       DRM_PLANE_TYPE_PRIMARY, NULL);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/armada/armada_plane.h b/drivers/gpu/drm/armada/armada_plane.h
new file mode 100644
index 000000000000..ff4281ba7fad
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_plane.h
@@ -0,0 +1,15 @@
+#ifndef ARMADA_PLANE_H
+#define ARMADA_PLANE_H
+
+void armada_drm_plane_calc(struct drm_plane_state *state, u32 addrs[2][3],
+	u16 pitches[3], bool interlaced);
+int armada_drm_plane_prepare_fb(struct drm_plane *plane,
+	struct drm_plane_state *state);
+void armada_drm_plane_cleanup_fb(struct drm_plane *plane,
+	struct drm_plane_state *old_state);
+int armada_drm_plane_atomic_check(struct drm_plane *plane,
+	struct drm_plane_state *state);
+int armada_drm_primary_plane_init(struct drm_device *drm,
+	struct drm_plane *primary);
+
+#endif
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index 036dff8a1f33..5e77d456d9bb 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -790,12 +790,12 @@ static int ast_get_modes(struct drm_connector *connector)
 	if (!flags)
 		edid = drm_get_edid(connector, &ast_connector->i2c->adapter);
 	if (edid) {
-		drm_mode_connector_update_edid_property(&ast_connector->base, edid);
+		drm_connector_update_edid_property(&ast_connector->base, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 		return ret;
 	} else
-		drm_mode_connector_update_edid_property(&ast_connector->base, NULL);
+		drm_connector_update_edid_property(&ast_connector->base, NULL);
 	return 0;
 }
 
@@ -900,7 +900,7 @@ static int ast_connector_init(struct drm_device *dev)
 	connector->polled = DRM_CONNECTOR_POLL_CONNECT;
 
 	encoder = list_first_entry(&dev->mode_config.encoder_list, struct drm_encoder, head);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	ast_connector->i2c = ast_i2c_create(dev);
 	if (!ast_connector->i2c)
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
index c1ea5c36b006..843cac222e60 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
@@ -681,6 +681,7 @@ static void atmel_hlcdc_dc_unload(struct drm_device *dev)
 	drm_fb_cma_fbdev_fini(dev);
 	flush_workqueue(dc->wq);
 	drm_kms_helper_poll_fini(dev);
+	drm_atomic_helper_shutdown(dev);
 	drm_mode_config_cleanup(dev);
 
 	pm_runtime_get_sync(dev->dev);
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
index 47e0992f3908..04440064b9b7 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
@@ -412,9 +412,10 @@ static void atmel_hlcdc_plane_update_format(struct atmel_hlcdc_plane *plane,
 				    ATMEL_HLCDC_LAYER_FORMAT_CFG, cfg);
 }
 
-static void atmel_hlcdc_plane_update_clut(struct atmel_hlcdc_plane *plane)
+static void atmel_hlcdc_plane_update_clut(struct atmel_hlcdc_plane *plane,
+					  struct atmel_hlcdc_plane_state *state)
 {
-	struct drm_crtc *crtc = plane->base.crtc;
+	struct drm_crtc *crtc = state->base.crtc;
 	struct drm_color_lut *lut;
 	int idx;
 
@@ -779,7 +780,7 @@ static void atmel_hlcdc_plane_atomic_update(struct drm_plane *p,
 	atmel_hlcdc_plane_update_pos_and_size(plane, state);
 	atmel_hlcdc_plane_update_general_settings(plane, state);
 	atmel_hlcdc_plane_update_format(plane, state);
-	atmel_hlcdc_plane_update_clut(plane);
+	atmel_hlcdc_plane_update_clut(plane, state);
 	atmel_hlcdc_plane_update_buffers(plane, state);
 	atmel_hlcdc_plane_update_disc_area(plane, state);
 
@@ -816,16 +817,6 @@ static void atmel_hlcdc_plane_atomic_disable(struct drm_plane *p,
 	atmel_hlcdc_layer_read_reg(&plane->layer, ATMEL_HLCDC_LAYER_ISR);
 }
 
-static void atmel_hlcdc_plane_destroy(struct drm_plane *p)
-{
-	struct atmel_hlcdc_plane *plane = drm_plane_to_atmel_hlcdc_plane(p);
-
-	if (plane->base.fb)
-		drm_framebuffer_put(plane->base.fb);
-
-	drm_plane_cleanup(p);
-}
-
 static int atmel_hlcdc_plane_init_properties(struct atmel_hlcdc_plane *plane)
 {
 	const struct atmel_hlcdc_layer_desc *desc = plane->layer.desc;
@@ -1002,7 +993,7 @@ static void atmel_hlcdc_plane_atomic_destroy_state(struct drm_plane *p,
 static const struct drm_plane_funcs layer_plane_funcs = {
 	.update_plane = drm_atomic_helper_update_plane,
 	.disable_plane = drm_atomic_helper_disable_plane,
-	.destroy = atmel_hlcdc_plane_destroy,
+	.destroy = drm_plane_cleanup,
 	.reset = atmel_hlcdc_plane_reset,
 	.atomic_duplicate_state = atmel_hlcdc_plane_atomic_duplicate_state,
 	.atomic_destroy_state = atmel_hlcdc_plane_atomic_destroy_state,
diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c
index 233980a78591..ca5a9afdd5cf 100644
--- a/drivers/gpu/drm/bochs/bochs_kms.c
+++ b/drivers/gpu/drm/bochs/bochs_kms.c
@@ -259,7 +259,7 @@ int bochs_kms_init(struct bochs_device *bochs)
 	bochs_crtc_init(bochs->dev);
 	bochs_encoder_init(bochs->dev);
 	bochs_connector_init(bochs->dev);
-	drm_mode_connector_attach_encoder(&bochs->connector,
+	drm_connector_attach_encoder(&bochs->connector,
 					  &bochs->encoder);
 
 	return 0;
diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig
index fa2c7997e2fd..bf6cad6c9178 100644
--- a/drivers/gpu/drm/bridge/Kconfig
+++ b/drivers/gpu/drm/bridge/Kconfig
@@ -82,9 +82,11 @@ config DRM_PARADE_PS8622
 
 config DRM_SIL_SII8620
 	tristate "Silicon Image SII8620 HDMI/MHL bridge"
-	depends on OF && RC_CORE
+	depends on OF
 	select DRM_KMS_HELPER
 	imply EXTCON
+	select INPUT
+	select RC_CORE
 	help
 	  Silicon Image SII8620 HDMI/MHL bridge chip driver.
 
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
index dd3ff2f2cdce..85c2d407a52e 100644
--- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
@@ -613,7 +613,7 @@ static int adv7511_get_modes(struct adv7511 *adv7511,
 		__adv7511_power_off(adv7511);
 
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	count = drm_add_edid_modes(connector, edid);
 
 	adv7511_set_config_csc(adv7511, connector, adv7511->rgb,
@@ -872,7 +872,7 @@ static int adv7511_bridge_attach(struct drm_bridge *bridge)
 	}
 	drm_connector_helper_add(&adv->connector,
 				 &adv7511_connector_helper_funcs);
-	drm_mode_connector_attach_encoder(&adv->connector, bridge->encoder);
+	drm_connector_attach_encoder(&adv->connector, bridge->encoder);
 
 	if (adv->type == ADV7533)
 		ret = adv7533_attach_dsi(adv);
diff --git a/drivers/gpu/drm/bridge/analogix-anx78xx.c b/drivers/gpu/drm/bridge/analogix-anx78xx.c
index b49043866be6..f8433c93f463 100644
--- a/drivers/gpu/drm/bridge/analogix-anx78xx.c
+++ b/drivers/gpu/drm/bridge/analogix-anx78xx.c
@@ -969,8 +969,8 @@ static int anx78xx_get_modes(struct drm_connector *connector)
 		goto unlock;
 	}
 
-	err = drm_mode_connector_update_edid_property(connector,
-						      anx78xx->edid);
+	err = drm_connector_update_edid_property(connector,
+						 anx78xx->edid);
 	if (err) {
 		DRM_ERROR("Failed to update EDID property: %d\n", err);
 		goto unlock;
@@ -1048,8 +1048,8 @@ static int anx78xx_bridge_attach(struct drm_bridge *bridge)
 
 	anx78xx->connector.polled = DRM_CONNECTOR_POLL_HPD;
 
-	err = drm_mode_connector_attach_encoder(&anx78xx->connector,
-						bridge->encoder);
+	err = drm_connector_attach_encoder(&anx78xx->connector,
+					   bridge->encoder);
 	if (err) {
 		DRM_ERROR("Failed to link up connector to encoder: %d\n", err);
 		return err;
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
index 2bcbfadb6ac5..d68986cea132 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
@@ -1119,8 +1119,8 @@ static int analogix_dp_get_modes(struct drm_connector *connector)
 		edid = drm_get_edid(connector, &dp->aux.ddc);
 		pm_runtime_put(dp->dev);
 		if (edid) {
-			drm_mode_connector_update_edid_property(&dp->connector,
-								edid);
+			drm_connector_update_edid_property(&dp->connector,
+							   edid);
 			num_modes += drm_add_edid_modes(&dp->connector, edid);
 			kfree(edid);
 		}
@@ -1210,7 +1210,7 @@ static int analogix_dp_bridge_attach(struct drm_bridge *bridge)
 
 		drm_connector_helper_add(connector,
 					 &analogix_dp_connector_helper_funcs);
-		drm_mode_connector_attach_encoder(connector, encoder);
+		drm_connector_attach_encoder(connector, encoder);
 	}
 
 	/*
diff --git a/drivers/gpu/drm/bridge/cdns-dsi.c b/drivers/gpu/drm/bridge/cdns-dsi.c
index c255fc3e1be5..ce9496d13986 100644
--- a/drivers/gpu/drm/bridge/cdns-dsi.c
+++ b/drivers/gpu/drm/bridge/cdns-dsi.c
@@ -1152,7 +1152,7 @@ static int cdns_dsi_attach(struct mipi_dsi_host *host,
 		np = of_node_get(dev->dev.of_node);
 
 	panel = of_drm_find_panel(np);
-	if (panel) {
+	if (!IS_ERR(panel)) {
 		bridge = drm_panel_bridge_add(panel, DRM_MODE_CONNECTOR_DSI);
 	} else {
 		bridge = of_drm_find_bridge(dev->dev.of_node);
@@ -1337,7 +1337,7 @@ static const struct mipi_dsi_host_ops cdns_dsi_ops = {
 	.transfer = cdns_dsi_transfer,
 };
 
-static int cdns_dsi_resume(struct device *dev)
+static int __maybe_unused cdns_dsi_resume(struct device *dev)
 {
 	struct cdns_dsi *dsi = dev_get_drvdata(dev);
 
@@ -1350,7 +1350,7 @@ static int cdns_dsi_resume(struct device *dev)
 	return 0;
 }
 
-static int cdns_dsi_suspend(struct device *dev)
+static int __maybe_unused cdns_dsi_suspend(struct device *dev)
 {
 	struct cdns_dsi *dsi = dev_get_drvdata(dev);
 
diff --git a/drivers/gpu/drm/bridge/dumb-vga-dac.c b/drivers/gpu/drm/bridge/dumb-vga-dac.c
index 9837c8d69e69..9b706789a341 100644
--- a/drivers/gpu/drm/bridge/dumb-vga-dac.c
+++ b/drivers/gpu/drm/bridge/dumb-vga-dac.c
@@ -55,7 +55,7 @@ static int dumb_vga_get_modes(struct drm_connector *connector)
 		goto fallback;
 	}
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
 	kfree(edid);
 	return ret;
@@ -122,7 +122,7 @@ static int dumb_vga_attach(struct drm_bridge *bridge)
 		return ret;
 	}
 
-	drm_mode_connector_attach_encoder(&vga->connector,
+	drm_connector_attach_encoder(&vga->connector,
 					  bridge->encoder);
 
 	return 0;
diff --git a/drivers/gpu/drm/bridge/lvds-encoder.c b/drivers/gpu/drm/bridge/lvds-encoder.c
index 75b0d3f6e4de..f56c92f7af7c 100644
--- a/drivers/gpu/drm/bridge/lvds-encoder.c
+++ b/drivers/gpu/drm/bridge/lvds-encoder.c
@@ -68,9 +68,9 @@ static int lvds_encoder_probe(struct platform_device *pdev)
 
 	panel = of_drm_find_panel(panel_node);
 	of_node_put(panel_node);
-	if (!panel) {
+	if (IS_ERR(panel)) {
 		dev_dbg(&pdev->dev, "panel not found, deferring probe\n");
-		return -EPROBE_DEFER;
+		return PTR_ERR(panel);
 	}
 
 	lvds_encoder->panel_bridge =
diff --git a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c
index 7ccadba7c98c..2136c97aeb8e 100644
--- a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c
+++ b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c
@@ -152,7 +152,7 @@ static int ge_b850v3_lvds_get_modes(struct drm_connector *connector)
 	ge_b850v3_lvds_ptr->edid = (struct edid *)stdp2690_get_edid(client);
 
 	if (ge_b850v3_lvds_ptr->edid) {
-		drm_mode_connector_update_edid_property(connector,
+		drm_connector_update_edid_property(connector,
 						      ge_b850v3_lvds_ptr->edid);
 		num_modes = drm_add_edid_modes(connector,
 					       ge_b850v3_lvds_ptr->edid);
@@ -241,7 +241,7 @@ static int ge_b850v3_lvds_attach(struct drm_bridge *bridge)
 		return ret;
 	}
 
-	ret = drm_mode_connector_attach_encoder(connector, bridge->encoder);
+	ret = drm_connector_attach_encoder(connector, bridge->encoder);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/bridge/nxp-ptn3460.c b/drivers/gpu/drm/bridge/nxp-ptn3460.c
index d64a3283822a..a3e817abace1 100644
--- a/drivers/gpu/drm/bridge/nxp-ptn3460.c
+++ b/drivers/gpu/drm/bridge/nxp-ptn3460.c
@@ -222,7 +222,7 @@ static int ptn3460_get_modes(struct drm_connector *connector)
 	}
 
 	ptn_bridge->edid = (struct edid *)edid;
-	drm_mode_connector_update_edid_property(connector, ptn_bridge->edid);
+	drm_connector_update_edid_property(connector, ptn_bridge->edid);
 
 	num_modes = drm_add_edid_modes(connector, ptn_bridge->edid);
 
@@ -265,7 +265,7 @@ static int ptn3460_bridge_attach(struct drm_bridge *bridge)
 	drm_connector_helper_add(&ptn_bridge->connector,
 					&ptn3460_connector_helper_funcs);
 	drm_connector_register(&ptn_bridge->connector);
-	drm_mode_connector_attach_encoder(&ptn_bridge->connector,
+	drm_connector_attach_encoder(&ptn_bridge->connector,
 							bridge->encoder);
 
 	if (ptn_bridge->panel)
diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c
index 6d99d4a3beb3..7cbaba213ef6 100644
--- a/drivers/gpu/drm/bridge/panel.c
+++ b/drivers/gpu/drm/bridge/panel.c
@@ -79,7 +79,7 @@ static int panel_bridge_attach(struct drm_bridge *bridge)
 		return ret;
 	}
 
-	drm_mode_connector_attach_encoder(&panel_bridge->connector,
+	drm_connector_attach_encoder(&panel_bridge->connector,
 					  bridge->encoder);
 
 	ret = drm_panel_attach(panel_bridge->panel, &panel_bridge->connector);
diff --git a/drivers/gpu/drm/bridge/parade-ps8622.c b/drivers/gpu/drm/bridge/parade-ps8622.c
index 81198f5e9afa..7334d1b62b71 100644
--- a/drivers/gpu/drm/bridge/parade-ps8622.c
+++ b/drivers/gpu/drm/bridge/parade-ps8622.c
@@ -503,7 +503,7 @@ static int ps8622_attach(struct drm_bridge *bridge)
 	drm_connector_helper_add(&ps8622->connector,
 					&ps8622_connector_helper_funcs);
 	drm_connector_register(&ps8622->connector);
-	drm_mode_connector_attach_encoder(&ps8622->connector,
+	drm_connector_attach_encoder(&ps8622->connector,
 							bridge->encoder);
 
 	if (ps8622->panel)
diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c
index 60373d7eb220..e59a13542333 100644
--- a/drivers/gpu/drm/bridge/sii902x.c
+++ b/drivers/gpu/drm/bridge/sii902x.c
@@ -170,7 +170,7 @@ static int sii902x_get_modes(struct drm_connector *connector)
 		return ret;
 
 	edid = drm_get_edid(connector, sii902x->i2c->adapter);
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	if (edid) {
 		num = drm_add_edid_modes(connector, edid);
 		kfree(edid);
@@ -324,7 +324,7 @@ static int sii902x_bridge_attach(struct drm_bridge *bridge)
 	else
 		sii902x->connector.polled = DRM_CONNECTOR_POLL_CONNECT;
 
-	drm_mode_connector_attach_encoder(&sii902x->connector, bridge->encoder);
+	drm_connector_attach_encoder(&sii902x->connector, bridge->encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
index 3c136f2b954f..5971976284bf 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
@@ -1922,7 +1922,7 @@ static int dw_hdmi_connector_get_modes(struct drm_connector *connector)
 
 		hdmi->sink_is_hdmi = drm_detect_hdmi_monitor(edid);
 		hdmi->sink_has_audio = drm_detect_monitor_audio(edid);
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		cec_notifier_set_phys_addr_from_edid(hdmi->cec_notifier, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
@@ -1974,7 +1974,7 @@ static int dw_hdmi_bridge_attach(struct drm_bridge *bridge)
 	drm_connector_init(bridge->dev, connector, &dw_hdmi_connector_funcs,
 			   DRM_MODE_CONNECTOR_HDMIA);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
index 0fd9cf27542c..8e28e738cb52 100644
--- a/drivers/gpu/drm/bridge/tc358767.c
+++ b/drivers/gpu/drm/bridge/tc358767.c
@@ -1140,7 +1140,7 @@ static int tc_connector_get_modes(struct drm_connector *connector)
 	if (!edid)
 		return 0;
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	count = drm_add_edid_modes(connector, edid);
 
 	return count;
@@ -1195,7 +1195,7 @@ static int tc_bridge_attach(struct drm_bridge *bridge)
 
 	drm_display_info_set_bus_formats(&tc->connector.display_info,
 					 &bus_format, 1);
-	drm_mode_connector_attach_encoder(&tc->connector, tc->bridge.encoder);
+	drm_connector_attach_encoder(&tc->connector, tc->bridge.encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/bridge/ti-tfp410.c b/drivers/gpu/drm/bridge/ti-tfp410.c
index acb857030951..c3e32138c6bb 100644
--- a/drivers/gpu/drm/bridge/ti-tfp410.c
+++ b/drivers/gpu/drm/bridge/ti-tfp410.c
@@ -62,7 +62,7 @@ static int tfp410_get_modes(struct drm_connector *connector)
 		goto fallback;
 	}
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 
 	return drm_add_edid_modes(connector, edid);
 fallback:
@@ -132,7 +132,7 @@ static int tfp410_attach(struct drm_bridge *bridge)
 		return ret;
 	}
 
-	drm_mode_connector_attach_encoder(&dvi->connector,
+	drm_connector_attach_encoder(&dvi->connector,
 					  bridge->encoder);
 
 	return 0;
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.h b/drivers/gpu/drm/cirrus/cirrus_drv.h
index be2d7e488062..ce9db7aab225 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.h
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.h
@@ -92,7 +92,6 @@
 
 #define to_cirrus_crtc(x) container_of(x, struct cirrus_crtc, base)
 #define to_cirrus_encoder(x) container_of(x, struct cirrus_encoder, base)
-#define to_cirrus_framebuffer(x) container_of(x, struct cirrus_framebuffer, base)
 
 struct cirrus_crtc {
 	struct drm_crtc			base;
@@ -117,11 +116,6 @@ struct cirrus_connector {
 	struct drm_connector		base;
 };
 
-struct cirrus_framebuffer {
-	struct drm_framebuffer		base;
-	struct drm_gem_object *obj;
-};
-
 struct cirrus_mc {
 	resource_size_t			vram_size;
 	resource_size_t			vram_base;
@@ -152,7 +146,7 @@ struct cirrus_device {
 
 struct cirrus_fbdev {
 	struct drm_fb_helper helper;
-	struct cirrus_framebuffer gfb;
+	struct drm_framebuffer gfb;
 	void *sysram;
 	int size;
 	int x1, y1, x2, y2; /* dirty rect */
@@ -198,7 +192,7 @@ int cirrus_dumb_create(struct drm_file *file,
 		       struct drm_mode_create_dumb *args);
 
 int cirrus_framebuffer_init(struct drm_device *dev,
-			   struct cirrus_framebuffer *gfb,
+			    struct drm_framebuffer *gfb,
 			    const struct drm_mode_fb_cmd2 *mode_cmd,
 			    struct drm_gem_object *obj);
 
diff --git a/drivers/gpu/drm/cirrus/cirrus_fbdev.c b/drivers/gpu/drm/cirrus/cirrus_fbdev.c
index 32fbfba2c623..b643ac92801c 100644
--- a/drivers/gpu/drm/cirrus/cirrus_fbdev.c
+++ b/drivers/gpu/drm/cirrus/cirrus_fbdev.c
@@ -22,14 +22,14 @@ static void cirrus_dirty_update(struct cirrus_fbdev *afbdev,
 	struct drm_gem_object *obj;
 	struct cirrus_bo *bo;
 	int src_offset, dst_offset;
-	int bpp = afbdev->gfb.base.format->cpp[0];
+	int bpp = afbdev->gfb.format->cpp[0];
 	int ret = -EBUSY;
 	bool unmap = false;
 	bool store_for_later = false;
 	int x2, y2;
 	unsigned long flags;
 
-	obj = afbdev->gfb.obj;
+	obj = afbdev->gfb.obj[0];
 	bo = gem_to_cirrus_bo(obj);
 
 	/*
@@ -82,7 +82,7 @@ static void cirrus_dirty_update(struct cirrus_fbdev *afbdev,
 	}
 	for (i = y; i < y + height; i++) {
 		/* assume equal stride for now */
-		src_offset = dst_offset = i * afbdev->gfb.base.pitches[0] + (x * bpp);
+		src_offset = dst_offset = i * afbdev->gfb.pitches[0] + (x * bpp);
 		memcpy_toio(bo->kmap.virtual + src_offset, afbdev->sysram + src_offset, width * bpp);
 
 	}
@@ -204,7 +204,7 @@ static int cirrusfb_create(struct drm_fb_helper *helper,
 	gfbdev->sysram = sysram;
 	gfbdev->size = size;
 
-	fb = &gfbdev->gfb.base;
+	fb = &gfbdev->gfb;
 	if (!fb) {
 		DRM_INFO("fb is NULL\n");
 		return -EINVAL;
@@ -246,19 +246,19 @@ static int cirrusfb_create(struct drm_fb_helper *helper,
 static int cirrus_fbdev_destroy(struct drm_device *dev,
 				struct cirrus_fbdev *gfbdev)
 {
-	struct cirrus_framebuffer *gfb = &gfbdev->gfb;
+	struct drm_framebuffer *gfb = &gfbdev->gfb;
 
 	drm_fb_helper_unregister_fbi(&gfbdev->helper);
 
-	if (gfb->obj) {
-		drm_gem_object_put_unlocked(gfb->obj);
-		gfb->obj = NULL;
+	if (gfb->obj[0]) {
+		drm_gem_object_put_unlocked(gfb->obj[0]);
+		gfb->obj[0] = NULL;
 	}
 
 	vfree(gfbdev->sysram);
 	drm_fb_helper_fini(&gfbdev->helper);
-	drm_framebuffer_unregister_private(&gfb->base);
-	drm_framebuffer_cleanup(&gfb->base);
+	drm_framebuffer_unregister_private(gfb);
+	drm_framebuffer_cleanup(gfb);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/cirrus/cirrus_main.c b/drivers/gpu/drm/cirrus/cirrus_main.c
index 26df1e8cd490..60d54e10a34d 100644
--- a/drivers/gpu/drm/cirrus/cirrus_main.c
+++ b/drivers/gpu/drm/cirrus/cirrus_main.c
@@ -10,42 +10,25 @@
  */
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 
 #include "cirrus_drv.h"
 
-static int cirrus_create_handle(struct drm_framebuffer *fb,
-				struct drm_file* file_priv,
-				unsigned int* handle)
-{
-	struct cirrus_framebuffer *cirrus_fb = to_cirrus_framebuffer(fb);
-
-	return drm_gem_handle_create(file_priv, cirrus_fb->obj, handle);
-}
-
-static void cirrus_user_framebuffer_destroy(struct drm_framebuffer *fb)
-{
-	struct cirrus_framebuffer *cirrus_fb = to_cirrus_framebuffer(fb);
-
-	drm_gem_object_put_unlocked(cirrus_fb->obj);
-	drm_framebuffer_cleanup(fb);
-	kfree(fb);
-}
-
 static const struct drm_framebuffer_funcs cirrus_fb_funcs = {
-	.create_handle = cirrus_create_handle,
-	.destroy = cirrus_user_framebuffer_destroy,
+	.create_handle = drm_gem_fb_create_handle,
+	.destroy = drm_gem_fb_destroy,
 };
 
 int cirrus_framebuffer_init(struct drm_device *dev,
-			    struct cirrus_framebuffer *gfb,
+			    struct drm_framebuffer *gfb,
 			    const struct drm_mode_fb_cmd2 *mode_cmd,
 			    struct drm_gem_object *obj)
 {
 	int ret;
 
-	drm_helper_mode_fill_fb_struct(dev, &gfb->base, mode_cmd);
-	gfb->obj = obj;
-	ret = drm_framebuffer_init(dev, &gfb->base, &cirrus_fb_funcs);
+	drm_helper_mode_fill_fb_struct(dev, gfb, mode_cmd);
+	gfb->obj[0] = obj;
+	ret = drm_framebuffer_init(dev, gfb, &cirrus_fb_funcs);
 	if (ret) {
 		DRM_ERROR("drm_framebuffer_init failed: %d\n", ret);
 		return ret;
@@ -60,7 +43,7 @@ cirrus_user_framebuffer_create(struct drm_device *dev,
 {
 	struct cirrus_device *cdev = dev->dev_private;
 	struct drm_gem_object *obj;
-	struct cirrus_framebuffer *cirrus_fb;
+	struct drm_framebuffer *fb;
 	u32 bpp;
 	int ret;
 
@@ -74,19 +57,19 @@ cirrus_user_framebuffer_create(struct drm_device *dev,
 	if (obj == NULL)
 		return ERR_PTR(-ENOENT);
 
-	cirrus_fb = kzalloc(sizeof(*cirrus_fb), GFP_KERNEL);
-	if (!cirrus_fb) {
+	fb = kzalloc(sizeof(*fb), GFP_KERNEL);
+	if (!fb) {
 		drm_gem_object_put_unlocked(obj);
 		return ERR_PTR(-ENOMEM);
 	}
 
-	ret = cirrus_framebuffer_init(dev, cirrus_fb, mode_cmd, obj);
+	ret = cirrus_framebuffer_init(dev, fb, mode_cmd, obj);
 	if (ret) {
 		drm_gem_object_put_unlocked(obj);
-		kfree(cirrus_fb);
+		kfree(fb);
 		return ERR_PTR(ret);
 	}
-	return &cirrus_fb->base;
+	return fb;
 }
 
 static const struct drm_mode_config_funcs cirrus_mode_funcs = {
diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c
index c91b9b054e3f..336bfda40125 100644
--- a/drivers/gpu/drm/cirrus/cirrus_mode.c
+++ b/drivers/gpu/drm/cirrus/cirrus_mode.c
@@ -101,17 +101,13 @@ static int cirrus_crtc_do_set_base(struct drm_crtc *crtc,
 				int x, int y, int atomic)
 {
 	struct cirrus_device *cdev = crtc->dev->dev_private;
-	struct drm_gem_object *obj;
-	struct cirrus_framebuffer *cirrus_fb;
 	struct cirrus_bo *bo;
 	int ret;
 	u64 gpu_addr;
 
 	/* push the previous fb to system ram */
 	if (!atomic && fb) {
-		cirrus_fb = to_cirrus_framebuffer(fb);
-		obj = cirrus_fb->obj;
-		bo = gem_to_cirrus_bo(obj);
+		bo = gem_to_cirrus_bo(fb->obj[0]);
 		ret = cirrus_bo_reserve(bo, false);
 		if (ret)
 			return ret;
@@ -119,9 +115,7 @@ static int cirrus_crtc_do_set_base(struct drm_crtc *crtc,
 		cirrus_bo_unreserve(bo);
 	}
 
-	cirrus_fb = to_cirrus_framebuffer(crtc->primary->fb);
-	obj = cirrus_fb->obj;
-	bo = gem_to_cirrus_bo(obj);
+	bo = gem_to_cirrus_bo(crtc->primary->fb->obj[0]);
 
 	ret = cirrus_bo_reserve(bo, false);
 	if (ret)
@@ -133,7 +127,7 @@ static int cirrus_crtc_do_set_base(struct drm_crtc *crtc,
 		return ret;
 	}
 
-	if (&cdev->mode_info.gfbdev->gfb == cirrus_fb) {
+	if (&cdev->mode_info.gfbdev->gfb == crtc->primary->fb) {
 		/* if pushing console in kmap it */
 		ret = ttm_bo_kmap(&bo->bo, 0, bo->bo.num_pages, &bo->kmap);
 		if (ret)
@@ -536,7 +530,7 @@ int cirrus_modeset_init(struct cirrus_device *cdev)
 		return -1;
 	}
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	ret = cirrus_fbdev_init(cdev);
 	if (ret) {
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 895741e9cd7d..3eb061e11e2e 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -30,6 +30,7 @@
 #include <drm/drm_atomic.h>
 #include <drm/drm_mode.h>
 #include <drm/drm_print.h>
+#include <drm/drm_writeback.h>
 #include <linux/sync_file.h>
 
 #include "drm_crtc_internal.h"
@@ -325,6 +326,35 @@ static s32 __user *get_out_fence_for_crtc(struct drm_atomic_state *state,
 	return fence_ptr;
 }
 
+static int set_out_fence_for_connector(struct drm_atomic_state *state,
+					struct drm_connector *connector,
+					s32 __user *fence_ptr)
+{
+	unsigned int index = drm_connector_index(connector);
+
+	if (!fence_ptr)
+		return 0;
+
+	if (put_user(-1, fence_ptr))
+		return -EFAULT;
+
+	state->connectors[index].out_fence_ptr = fence_ptr;
+
+	return 0;
+}
+
+static s32 __user *get_out_fence_for_connector(struct drm_atomic_state *state,
+					       struct drm_connector *connector)
+{
+	unsigned int index = drm_connector_index(connector);
+	s32 __user *fence_ptr;
+
+	fence_ptr = state->connectors[index].out_fence_ptr;
+	state->connectors[index].out_fence_ptr = NULL;
+
+	return fence_ptr;
+}
+
 /**
  * drm_atomic_set_mode_for_crtc - set mode for CRTC
  * @state: the CRTC whose incoming state to update
@@ -339,6 +369,7 @@ static s32 __user *get_out_fence_for_crtc(struct drm_atomic_state *state,
 int drm_atomic_set_mode_for_crtc(struct drm_crtc_state *state,
 				 const struct drm_display_mode *mode)
 {
+	struct drm_crtc *crtc = state->crtc;
 	struct drm_mode_modeinfo umode;
 
 	/* Early return for no change. */
@@ -359,13 +390,13 @@ int drm_atomic_set_mode_for_crtc(struct drm_crtc_state *state,
 
 		drm_mode_copy(&state->mode, mode);
 		state->enable = true;
-		DRM_DEBUG_ATOMIC("Set [MODE:%s] for CRTC state %p\n",
-				 mode->name, state);
+		DRM_DEBUG_ATOMIC("Set [MODE:%s] for [CRTC:%d:%s] state %p\n",
+				 mode->name, crtc->base.id, crtc->name, state);
 	} else {
 		memset(&state->mode, 0, sizeof(state->mode));
 		state->enable = false;
-		DRM_DEBUG_ATOMIC("Set [NOMODE] for CRTC state %p\n",
-				 state);
+		DRM_DEBUG_ATOMIC("Set [NOMODE] for [CRTC:%d:%s] state %p\n",
+				 crtc->base.id, crtc->name, state);
 	}
 
 	return 0;
@@ -388,6 +419,8 @@ EXPORT_SYMBOL(drm_atomic_set_mode_for_crtc);
 int drm_atomic_set_mode_prop_for_crtc(struct drm_crtc_state *state,
                                       struct drm_property_blob *blob)
 {
+	struct drm_crtc *crtc = state->crtc;
+
 	if (blob == state->mode_blob)
 		return 0;
 
@@ -397,19 +430,34 @@ int drm_atomic_set_mode_prop_for_crtc(struct drm_crtc_state *state,
 	memset(&state->mode, 0, sizeof(state->mode));
 
 	if (blob) {
-		if (blob->length != sizeof(struct drm_mode_modeinfo) ||
-		    drm_mode_convert_umode(state->crtc->dev, &state->mode,
-					   blob->data))
+		int ret;
+
+		if (blob->length != sizeof(struct drm_mode_modeinfo)) {
+			DRM_DEBUG_ATOMIC("[CRTC:%d:%s] bad mode blob length: %zu\n",
+					 crtc->base.id, crtc->name,
+					 blob->length);
 			return -EINVAL;
+		}
+
+		ret = drm_mode_convert_umode(crtc->dev,
+					     &state->mode, blob->data);
+		if (ret) {
+			DRM_DEBUG_ATOMIC("[CRTC:%d:%s] invalid mode (ret=%d, status=%s):\n",
+					 crtc->base.id, crtc->name,
+					 ret, drm_get_mode_status_name(state->mode.status));
+			drm_mode_debug_printmodeline(&state->mode);
+			return -EINVAL;
+		}
 
 		state->mode_blob = drm_property_blob_get(blob);
 		state->enable = true;
-		DRM_DEBUG_ATOMIC("Set [MODE:%s] for CRTC state %p\n",
-				 state->mode.name, state);
+		DRM_DEBUG_ATOMIC("Set [MODE:%s] for [CRTC:%d:%s] state %p\n",
+				 state->mode.name, crtc->base.id, crtc->name,
+				 state);
 	} else {
 		state->enable = false;
-		DRM_DEBUG_ATOMIC("Set [NOMODE] for CRTC state %p\n",
-				 state);
+		DRM_DEBUG_ATOMIC("Set [NOMODE] for [CRTC:%d:%s] state %p\n",
+				 crtc->base.id, crtc->name, state);
 	}
 
 	return 0;
@@ -539,10 +587,14 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc,
 			return -EFAULT;
 
 		set_out_fence_for_crtc(state->state, crtc, fence_ptr);
-	} else if (crtc->funcs->atomic_set_property)
+	} else if (crtc->funcs->atomic_set_property) {
 		return crtc->funcs->atomic_set_property(crtc, state, property, val);
-	else
+	} else {
+		DRM_DEBUG_ATOMIC("[CRTC:%d:%s] unknown property [PROP:%d:%s]]\n",
+				 crtc->base.id, crtc->name,
+				 property->base.id, property->name);
 		return -EINVAL;
+	}
 
 	return 0;
 }
@@ -677,6 +729,51 @@ static void drm_atomic_crtc_print_state(struct drm_printer *p,
 }
 
 /**
+ * drm_atomic_connector_check - check connector state
+ * @connector: connector to check
+ * @state: connector state to check
+ *
+ * Provides core sanity checks for connector state.
+ *
+ * RETURNS:
+ * Zero on success, error code on failure
+ */
+static int drm_atomic_connector_check(struct drm_connector *connector,
+		struct drm_connector_state *state)
+{
+	struct drm_crtc_state *crtc_state;
+	struct drm_writeback_job *writeback_job = state->writeback_job;
+
+	if ((connector->connector_type != DRM_MODE_CONNECTOR_WRITEBACK) || !writeback_job)
+		return 0;
+
+	if (writeback_job->fb && !state->crtc) {
+		DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] framebuffer without CRTC\n",
+				 connector->base.id, connector->name);
+		return -EINVAL;
+	}
+
+	if (state->crtc)
+		crtc_state = drm_atomic_get_existing_crtc_state(state->state,
+								state->crtc);
+
+	if (writeback_job->fb && !crtc_state->active) {
+		DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] has framebuffer, but [CRTC:%d] is off\n",
+				 connector->base.id, connector->name,
+				 state->crtc->base.id);
+		return -EINVAL;
+	}
+
+	if (writeback_job->out_fence && !writeback_job->fb) {
+		DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] requesting out-fence without framebuffer\n",
+				 connector->base.id, connector->name);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
  * drm_atomic_get_plane_state - get plane state
  * @state: global atomic state object
  * @plane: plane to get state object for
@@ -700,6 +797,11 @@ drm_atomic_get_plane_state(struct drm_atomic_state *state,
 
 	WARN_ON(!state->acquire_ctx);
 
+	/* the legacy pointers should never be set */
+	WARN_ON(plane->fb);
+	WARN_ON(plane->old_fb);
+	WARN_ON(plane->crtc);
+
 	plane_state = drm_atomic_get_existing_plane_state(state, plane);
 	if (plane_state)
 		return plane_state;
@@ -794,8 +896,11 @@ static int drm_atomic_plane_set_property(struct drm_plane *plane,
 	} else if (property == plane->alpha_property) {
 		state->alpha = val;
 	} else if (property == plane->rotation_property) {
-		if (!is_power_of_2(val & DRM_MODE_ROTATE_MASK))
+		if (!is_power_of_2(val & DRM_MODE_ROTATE_MASK)) {
+			DRM_DEBUG_ATOMIC("[PLANE:%d:%s] bad rotation bitmask: 0x%llx\n",
+					 plane->base.id, plane->name, val);
 			return -EINVAL;
+		}
 		state->rotation = val;
 	} else if (property == plane->zpos_property) {
 		state->zpos = val;
@@ -807,6 +912,9 @@ static int drm_atomic_plane_set_property(struct drm_plane *plane,
 		return plane->funcs->atomic_set_property(plane, state,
 				property, val);
 	} else {
+		DRM_DEBUG_ATOMIC("[PLANE:%d:%s] unknown property [PROP:%d:%s]]\n",
+				 plane->base.id, plane->name,
+				 property->base.id, property->name);
 		return -EINVAL;
 	}
 
@@ -914,10 +1022,12 @@ static int drm_atomic_plane_check(struct drm_plane *plane,
 
 	/* either *both* CRTC and FB must be set, or neither */
 	if (state->crtc && !state->fb) {
-		DRM_DEBUG_ATOMIC("CRTC set but no FB\n");
+		DRM_DEBUG_ATOMIC("[PLANE:%d:%s] CRTC set but no FB\n",
+				 plane->base.id, plane->name);
 		return -EINVAL;
 	} else if (state->fb && !state->crtc) {
-		DRM_DEBUG_ATOMIC("FB set but no CRTC\n");
+		DRM_DEBUG_ATOMIC("[PLANE:%d:%s] FB set but no CRTC\n",
+				 plane->base.id, plane->name);
 		return -EINVAL;
 	}
 
@@ -927,7 +1037,9 @@ static int drm_atomic_plane_check(struct drm_plane *plane,
 
 	/* Check whether this plane is usable on this CRTC */
 	if (!(plane->possible_crtcs & drm_crtc_mask(state->crtc))) {
-		DRM_DEBUG_ATOMIC("Invalid crtc for plane\n");
+		DRM_DEBUG_ATOMIC("Invalid [CRTC:%d:%s] for [PLANE:%d:%s]\n",
+				 state->crtc->base.id, state->crtc->name,
+				 plane->base.id, plane->name);
 		return -EINVAL;
 	}
 
@@ -936,7 +1048,8 @@ static int drm_atomic_plane_check(struct drm_plane *plane,
 					   state->fb->modifier);
 	if (ret) {
 		struct drm_format_name_buf format_name;
-		DRM_DEBUG_ATOMIC("Invalid pixel format %s, modifier 0x%llx\n",
+		DRM_DEBUG_ATOMIC("[PLANE:%d:%s] invalid pixel format %s, modifier 0x%llx\n",
+				 plane->base.id, plane->name,
 				 drm_get_format_name(state->fb->format->format,
 						     &format_name),
 				 state->fb->modifier);
@@ -948,7 +1061,8 @@ static int drm_atomic_plane_check(struct drm_plane *plane,
 	    state->crtc_x > INT_MAX - (int32_t) state->crtc_w ||
 	    state->crtc_h > INT_MAX ||
 	    state->crtc_y > INT_MAX - (int32_t) state->crtc_h) {
-		DRM_DEBUG_ATOMIC("Invalid CRTC coordinates %ux%u+%d+%d\n",
+		DRM_DEBUG_ATOMIC("[PLANE:%d:%s] invalid CRTC coordinates %ux%u+%d+%d\n",
+				 plane->base.id, plane->name,
 				 state->crtc_w, state->crtc_h,
 				 state->crtc_x, state->crtc_y);
 		return -ERANGE;
@@ -962,8 +1076,9 @@ static int drm_atomic_plane_check(struct drm_plane *plane,
 	    state->src_x > fb_width - state->src_w ||
 	    state->src_h > fb_height ||
 	    state->src_y > fb_height - state->src_h) {
-		DRM_DEBUG_ATOMIC("Invalid source coordinates "
+		DRM_DEBUG_ATOMIC("[PLANE:%d:%s] invalid source coordinates "
 				 "%u.%06ux%u.%06u+%u.%06u+%u.%06u (fb %ux%u)\n",
+				 plane->base.id, plane->name,
 				 state->src_w >> 16, ((state->src_w & 0xffff) * 15625) >> 10,
 				 state->src_h >> 16, ((state->src_h & 0xffff) * 15625) >> 10,
 				 state->src_x >> 16, ((state->src_x & 0xffff) * 15625) >> 10,
@@ -996,6 +1111,7 @@ static void drm_atomic_plane_print_state(struct drm_printer *p,
 	drm_printf(p, "\tcrtc-pos=" DRM_RECT_FMT "\n", DRM_RECT_ARG(&dest));
 	drm_printf(p, "\tsrc-pos=" DRM_RECT_FP_FMT "\n", DRM_RECT_FP_ARG(&src));
 	drm_printf(p, "\trotation=%x\n", state->rotation);
+	drm_printf(p, "\tnormalized-zpos=%x\n", state->normalized_zpos);
 	drm_printf(p, "\tcolor-encoding=%s\n",
 		   drm_get_color_encoding_name(state->color_encoding));
 	drm_printf(p, "\tcolor-range=%s\n",
@@ -1120,6 +1236,7 @@ drm_atomic_get_private_obj_state(struct drm_atomic_state *state,
 	state->private_objs[index].old_state = obj->state;
 	state->private_objs[index].new_state = obj_state;
 	state->private_objs[index].ptr = obj;
+	obj_state->state = state;
 
 	state->num_private_objs = num_objs;
 
@@ -1278,6 +1395,8 @@ static int drm_atomic_connector_set_property(struct drm_connector *connector,
 			state->link_status = val;
 	} else if (property == config->aspect_ratio_property) {
 		state->picture_aspect_ratio = val;
+	} else if (property == config->content_type_property) {
+		state->content_type = val;
 	} else if (property == connector->scaling_mode_property) {
 		state->scaling_mode = val;
 	} else if (property == connector->content_protection_property) {
@@ -1286,10 +1405,24 @@ static int drm_atomic_connector_set_property(struct drm_connector *connector,
 			return -EINVAL;
 		}
 		state->content_protection = val;
+	} else if (property == config->writeback_fb_id_property) {
+		struct drm_framebuffer *fb = drm_framebuffer_lookup(dev, NULL, val);
+		int ret = drm_atomic_set_writeback_fb_for_connector(state, fb);
+		if (fb)
+			drm_framebuffer_put(fb);
+		return ret;
+	} else if (property == config->writeback_out_fence_ptr_property) {
+		s32 __user *fence_ptr = u64_to_user_ptr(val);
+
+		return set_out_fence_for_connector(state->state, connector,
+						   fence_ptr);
 	} else if (connector->funcs->atomic_set_property) {
 		return connector->funcs->atomic_set_property(connector,
 				state, property, val);
 	} else {
+		DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] unknown property [PROP:%d:%s]]\n",
+				 connector->base.id, connector->name,
+				 property->base.id, property->name);
 		return -EINVAL;
 	}
 
@@ -1304,6 +1437,10 @@ static void drm_atomic_connector_print_state(struct drm_printer *p,
 	drm_printf(p, "connector[%u]: %s\n", connector->base.id, connector->name);
 	drm_printf(p, "\tcrtc=%s\n", state->crtc ? state->crtc->name : "(null)");
 
+	if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK)
+		if (state->writeback_job && state->writeback_job->fb)
+			drm_printf(p, "\tfb=%d\n", state->writeback_job->fb->base.id);
+
 	if (connector->funcs->atomic_print_state)
 		connector->funcs->atomic_print_state(p, state);
 }
@@ -1363,10 +1500,17 @@ drm_atomic_connector_get_property(struct drm_connector *connector,
 		*val = state->link_status;
 	} else if (property == config->aspect_ratio_property) {
 		*val = state->picture_aspect_ratio;
+	} else if (property == config->content_type_property) {
+		*val = state->content_type;
 	} else if (property == connector->scaling_mode_property) {
 		*val = state->scaling_mode;
 	} else if (property == connector->content_protection_property) {
 		*val = state->content_protection;
+	} else if (property == config->writeback_fb_id_property) {
+		/* Writeback framebuffer is one-shot, write and forget */
+		*val = 0;
+	} else if (property == config->writeback_out_fence_ptr_property) {
+		*val = 0;
 	} else if (connector->funcs->atomic_get_property) {
 		return connector->funcs->atomic_get_property(connector,
 				state, property, val);
@@ -1442,7 +1586,7 @@ drm_atomic_set_crtc_for_plane(struct drm_plane_state *plane_state,
 		if (WARN_ON(IS_ERR(crtc_state)))
 			return PTR_ERR(crtc_state);
 
-		crtc_state->plane_mask &= ~(1 << drm_plane_index(plane));
+		crtc_state->plane_mask &= ~drm_plane_mask(plane);
 	}
 
 	plane_state->crtc = crtc;
@@ -1452,15 +1596,16 @@ drm_atomic_set_crtc_for_plane(struct drm_plane_state *plane_state,
 						       crtc);
 		if (IS_ERR(crtc_state))
 			return PTR_ERR(crtc_state);
-		crtc_state->plane_mask |= (1 << drm_plane_index(plane));
+		crtc_state->plane_mask |= drm_plane_mask(plane);
 	}
 
 	if (crtc)
-		DRM_DEBUG_ATOMIC("Link plane state %p to [CRTC:%d:%s]\n",
-				 plane_state, crtc->base.id, crtc->name);
+		DRM_DEBUG_ATOMIC("Link [PLANE:%d:%s] state %p to [CRTC:%d:%s]\n",
+				 plane->base.id, plane->name, plane_state,
+				 crtc->base.id, crtc->name);
 	else
-		DRM_DEBUG_ATOMIC("Link plane state %p to [NOCRTC]\n",
-				 plane_state);
+		DRM_DEBUG_ATOMIC("Link [PLANE:%d:%s] state %p to [NOCRTC]\n",
+				 plane->base.id, plane->name, plane_state);
 
 	return 0;
 }
@@ -1480,12 +1625,15 @@ void
 drm_atomic_set_fb_for_plane(struct drm_plane_state *plane_state,
 			    struct drm_framebuffer *fb)
 {
+	struct drm_plane *plane = plane_state->plane;
+
 	if (fb)
-		DRM_DEBUG_ATOMIC("Set [FB:%d] for plane state %p\n",
-				 fb->base.id, plane_state);
-	else
-		DRM_DEBUG_ATOMIC("Set [NOFB] for plane state %p\n",
+		DRM_DEBUG_ATOMIC("Set [FB:%d] for [PLANE:%d:%s] state %p\n",
+				 fb->base.id, plane->base.id, plane->name,
 				 plane_state);
+	else
+		DRM_DEBUG_ATOMIC("Set [NOFB] for [PLANE:%d:%s] state %p\n",
+				 plane->base.id, plane->name, plane_state);
 
 	drm_framebuffer_assign(&plane_state->fb, fb);
 }
@@ -1546,6 +1694,7 @@ int
 drm_atomic_set_crtc_for_connector(struct drm_connector_state *conn_state,
 				  struct drm_crtc *crtc)
 {
+	struct drm_connector *connector = conn_state->connector;
 	struct drm_crtc_state *crtc_state;
 
 	if (conn_state->crtc == crtc)
@@ -1556,7 +1705,7 @@ drm_atomic_set_crtc_for_connector(struct drm_connector_state *conn_state,
 							   conn_state->crtc);
 
 		crtc_state->connector_mask &=
-			~(1 << drm_connector_index(conn_state->connector));
+			~drm_connector_mask(conn_state->connector);
 
 		drm_connector_put(conn_state->connector);
 		conn_state->crtc = NULL;
@@ -1568,15 +1717,17 @@ drm_atomic_set_crtc_for_connector(struct drm_connector_state *conn_state,
 			return PTR_ERR(crtc_state);
 
 		crtc_state->connector_mask |=
-			1 << drm_connector_index(conn_state->connector);
+			drm_connector_mask(conn_state->connector);
 
 		drm_connector_get(conn_state->connector);
 		conn_state->crtc = crtc;
 
-		DRM_DEBUG_ATOMIC("Link connector state %p to [CRTC:%d:%s]\n",
+		DRM_DEBUG_ATOMIC("Link [CONNECTOR:%d:%s] state %p to [CRTC:%d:%s]\n",
+				 connector->base.id, connector->name,
 				 conn_state, crtc->base.id, crtc->name);
 	} else {
-		DRM_DEBUG_ATOMIC("Link connector state %p to [NOCRTC]\n",
+		DRM_DEBUG_ATOMIC("Link [CONNECTOR:%d:%s] state %p to [NOCRTC]\n",
+				 connector->base.id, connector->name,
 				 conn_state);
 	}
 
@@ -1584,6 +1735,70 @@ drm_atomic_set_crtc_for_connector(struct drm_connector_state *conn_state,
 }
 EXPORT_SYMBOL(drm_atomic_set_crtc_for_connector);
 
+/*
+ * drm_atomic_get_writeback_job - return or allocate a writeback job
+ * @conn_state: Connector state to get the job for
+ *
+ * Writeback jobs have a different lifetime to the atomic state they are
+ * associated with. This convenience function takes care of allocating a job
+ * if there isn't yet one associated with the connector state, otherwise
+ * it just returns the existing job.
+ *
+ * Returns: The writeback job for the given connector state
+ */
+static struct drm_writeback_job *
+drm_atomic_get_writeback_job(struct drm_connector_state *conn_state)
+{
+	WARN_ON(conn_state->connector->connector_type != DRM_MODE_CONNECTOR_WRITEBACK);
+
+	if (!conn_state->writeback_job)
+		conn_state->writeback_job =
+			kzalloc(sizeof(*conn_state->writeback_job), GFP_KERNEL);
+
+	return conn_state->writeback_job;
+}
+
+/**
+ * drm_atomic_set_writeback_fb_for_connector - set writeback framebuffer
+ * @conn_state: atomic state object for the connector
+ * @fb: fb to use for the connector
+ *
+ * This is used to set the framebuffer for a writeback connector, which outputs
+ * to a buffer instead of an actual physical connector.
+ * Changing the assigned framebuffer requires us to grab a reference to the new
+ * fb and drop the reference to the old fb, if there is one. This function
+ * takes care of all these details besides updating the pointer in the
+ * state object itself.
+ *
+ * Note: The only way conn_state can already have an fb set is if the commit
+ * sets the property more than once.
+ *
+ * See also: drm_writeback_connector_init()
+ *
+ * Returns: 0 on success
+ */
+int drm_atomic_set_writeback_fb_for_connector(
+		struct drm_connector_state *conn_state,
+		struct drm_framebuffer *fb)
+{
+	struct drm_writeback_job *job =
+		drm_atomic_get_writeback_job(conn_state);
+	if (!job)
+		return -ENOMEM;
+
+	drm_framebuffer_assign(&job->fb, fb);
+
+	if (fb)
+		DRM_DEBUG_ATOMIC("Set [FB:%d] for connector state %p\n",
+				 fb->base.id, conn_state);
+	else
+		DRM_DEBUG_ATOMIC("Set [NOFB] for connector state %p\n",
+				 conn_state);
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_atomic_set_writeback_fb_for_connector);
+
 /**
  * drm_atomic_add_affected_connectors - add connectors for crtc
  * @state: atomic state
@@ -1629,7 +1844,7 @@ drm_atomic_add_affected_connectors(struct drm_atomic_state *state,
 	 */
 	drm_connector_list_iter_begin(state->dev, &conn_iter);
 	drm_for_each_connector_iter(connector, &conn_iter) {
-		if (!(crtc_state->connector_mask & (1 << drm_connector_index(connector))))
+		if (!(crtc_state->connector_mask & drm_connector_mask(connector)))
 			continue;
 
 		conn_state = drm_atomic_get_connector_state(state, connector);
@@ -1672,6 +1887,9 @@ drm_atomic_add_affected_planes(struct drm_atomic_state *state,
 
 	WARN_ON(!drm_atomic_get_new_crtc_state(state, crtc));
 
+	DRM_DEBUG_ATOMIC("Adding all current planes for [CRTC:%d:%s] to %p\n",
+			 crtc->base.id, crtc->name, state);
+
 	drm_for_each_plane_mask(plane, state->dev, crtc->state->plane_mask) {
 		struct drm_plane_state *plane_state =
 			drm_atomic_get_plane_state(state, plane);
@@ -1702,6 +1920,8 @@ int drm_atomic_check_only(struct drm_atomic_state *state)
 	struct drm_plane_state *plane_state;
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
+	struct drm_connector *conn;
+	struct drm_connector_state *conn_state;
 	int i, ret = 0;
 
 	DRM_DEBUG_ATOMIC("checking %p\n", state);
@@ -1724,6 +1944,15 @@ int drm_atomic_check_only(struct drm_atomic_state *state)
 		}
 	}
 
+	for_each_new_connector_in_state(state, conn, conn_state, i) {
+		ret = drm_atomic_connector_check(conn, conn_state);
+		if (ret) {
+			DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] atomic core check failed\n",
+					 conn->base.id, conn->name);
+			return ret;
+		}
+	}
+
 	if (config->funcs->atomic_check) {
 		ret = config->funcs->atomic_check(state->dev, state);
 
@@ -2048,45 +2277,6 @@ int drm_atomic_set_property(struct drm_atomic_state *state,
 }
 
 /**
- * drm_atomic_clean_old_fb -- Unset old_fb pointers and set plane->fb pointers.
- *
- * @dev: drm device to check.
- * @plane_mask: plane mask for planes that were updated.
- * @ret: return value, can be -EDEADLK for a retry.
- *
- * Before doing an update &drm_plane.old_fb is set to &drm_plane.fb, but before
- * dropping the locks old_fb needs to be set to NULL and plane->fb updated. This
- * is a common operation for each atomic update, so this call is split off as a
- * helper.
- */
-void drm_atomic_clean_old_fb(struct drm_device *dev,
-			     unsigned plane_mask,
-			     int ret)
-{
-	struct drm_plane *plane;
-
-	/* if succeeded, fixup legacy plane crtc/fb ptrs before dropping
-	 * locks (ie. while it is still safe to deref plane->state).  We
-	 * need to do this here because the driver entry points cannot
-	 * distinguish between legacy and atomic ioctls.
-	 */
-	drm_for_each_plane_mask(plane, dev, plane_mask) {
-		if (ret == 0) {
-			struct drm_framebuffer *new_fb = plane->state->fb;
-			if (new_fb)
-				drm_framebuffer_get(new_fb);
-			plane->fb = new_fb;
-			plane->crtc = plane->state->crtc;
-
-			if (plane->old_fb)
-				drm_framebuffer_put(plane->old_fb);
-		}
-		plane->old_fb = NULL;
-	}
-}
-EXPORT_SYMBOL(drm_atomic_clean_old_fb);
-
-/**
  * DOC: explicit fencing properties
  *
  * Explicit fencing allows userspace to control the buffer synchronization
@@ -2161,7 +2351,7 @@ static int setup_out_fence(struct drm_out_fence_state *fence_state,
 	return 0;
 }
 
-static int prepare_crtc_signaling(struct drm_device *dev,
+static int prepare_signaling(struct drm_device *dev,
 				  struct drm_atomic_state *state,
 				  struct drm_mode_atomic *arg,
 				  struct drm_file *file_priv,
@@ -2170,6 +2360,8 @@ static int prepare_crtc_signaling(struct drm_device *dev,
 {
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
+	struct drm_connector *conn;
+	struct drm_connector_state *conn_state;
 	int i, c = 0, ret;
 
 	if (arg->flags & DRM_MODE_ATOMIC_TEST_ONLY)
@@ -2235,6 +2427,45 @@ static int prepare_crtc_signaling(struct drm_device *dev,
 		c++;
 	}
 
+	for_each_new_connector_in_state(state, conn, conn_state, i) {
+		struct drm_writeback_connector *wb_conn;
+		struct drm_writeback_job *job;
+		struct drm_out_fence_state *f;
+		struct dma_fence *fence;
+		s32 __user *fence_ptr;
+
+		fence_ptr = get_out_fence_for_connector(state, conn);
+		if (!fence_ptr)
+			continue;
+
+		job = drm_atomic_get_writeback_job(conn_state);
+		if (!job)
+			return -ENOMEM;
+
+		f = krealloc(*fence_state, sizeof(**fence_state) *
+			     (*num_fences + 1), GFP_KERNEL);
+		if (!f)
+			return -ENOMEM;
+
+		memset(&f[*num_fences], 0, sizeof(*f));
+
+		f[*num_fences].out_fence_ptr = fence_ptr;
+		*fence_state = f;
+
+		wb_conn = drm_connector_to_writeback(conn);
+		fence = drm_writeback_get_out_fence(wb_conn);
+		if (!fence)
+			return -ENOMEM;
+
+		ret = setup_out_fence(&f[(*num_fences)++], fence);
+		if (ret) {
+			dma_fence_put(fence);
+			return ret;
+		}
+
+		job->out_fence = fence;
+	}
+
 	/*
 	 * Having this flag means user mode pends on event which will never
 	 * reach due to lack of at least one CRTC for signaling
@@ -2245,11 +2476,11 @@ static int prepare_crtc_signaling(struct drm_device *dev,
 	return 0;
 }
 
-static void complete_crtc_signaling(struct drm_device *dev,
-				    struct drm_atomic_state *state,
-				    struct drm_out_fence_state *fence_state,
-				    unsigned int num_fences,
-				    bool install_fds)
+static void complete_signaling(struct drm_device *dev,
+			       struct drm_atomic_state *state,
+			       struct drm_out_fence_state *fence_state,
+			       unsigned int num_fences,
+			       bool install_fds)
 {
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
@@ -2306,9 +2537,7 @@ int drm_mode_atomic_ioctl(struct drm_device *dev,
 	unsigned int copied_objs, copied_props;
 	struct drm_atomic_state *state;
 	struct drm_modeset_acquire_ctx ctx;
-	struct drm_plane *plane;
 	struct drm_out_fence_state *fence_state;
-	unsigned plane_mask;
 	int ret = 0;
 	unsigned int i, j, num_fences;
 
@@ -2348,7 +2577,6 @@ int drm_mode_atomic_ioctl(struct drm_device *dev,
 	state->allow_modeset = !!(arg->flags & DRM_MODE_ATOMIC_ALLOW_MODESET);
 
 retry:
-	plane_mask = 0;
 	copied_objs = 0;
 	copied_props = 0;
 	fence_state = NULL;
@@ -2419,17 +2647,11 @@ retry:
 			copied_props++;
 		}
 
-		if (obj->type == DRM_MODE_OBJECT_PLANE && count_props &&
-		    !(arg->flags & DRM_MODE_ATOMIC_TEST_ONLY)) {
-			plane = obj_to_plane(obj);
-			plane_mask |= (1 << drm_plane_index(plane));
-			plane->old_fb = plane->fb;
-		}
 		drm_mode_object_put(obj);
 	}
 
-	ret = prepare_crtc_signaling(dev, state, arg, file_priv, &fence_state,
-				     &num_fences);
+	ret = prepare_signaling(dev, state, arg, file_priv, &fence_state,
+				&num_fences);
 	if (ret)
 		goto out;
 
@@ -2445,9 +2667,7 @@ retry:
 	}
 
 out:
-	drm_atomic_clean_old_fb(dev, plane_mask, ret);
-
-	complete_crtc_signaling(dev, state, fence_state, num_fences, !ret);
+	complete_signaling(dev, state, fence_state, num_fences, !ret);
 
 	if (ret == -EDEADLK) {
 		drm_atomic_state_clear(state);
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 81e32199d3ef..80be74df7ba6 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -30,6 +30,7 @@
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_writeback.h>
 #include <linux/dma-fence.h>
 
 #include "drm_crtc_helper_internal.h"
@@ -120,7 +121,7 @@ static int handle_conflicting_encoders(struct drm_atomic_state *state,
 			new_encoder = drm_atomic_helper_best_encoder(connector);
 
 		if (new_encoder) {
-			if (encoder_mask & (1 << drm_encoder_index(new_encoder))) {
+			if (encoder_mask & drm_encoder_mask(new_encoder)) {
 				DRM_DEBUG_ATOMIC("[ENCODER:%d:%s] on [CONNECTOR:%d:%s] already assigned\n",
 					new_encoder->base.id, new_encoder->name,
 					connector->base.id, connector->name);
@@ -128,7 +129,7 @@ static int handle_conflicting_encoders(struct drm_atomic_state *state,
 				return -EINVAL;
 			}
 
-			encoder_mask |= 1 << drm_encoder_index(new_encoder);
+			encoder_mask |= drm_encoder_mask(new_encoder);
 		}
 	}
 
@@ -154,7 +155,7 @@ static int handle_conflicting_encoders(struct drm_atomic_state *state,
 			continue;
 
 		encoder = connector->state->best_encoder;
-		if (!encoder || !(encoder_mask & (1 << drm_encoder_index(encoder))))
+		if (!encoder || !(encoder_mask & drm_encoder_mask(encoder)))
 			continue;
 
 		if (!disable_conflicting_encoders) {
@@ -222,7 +223,7 @@ set_best_encoder(struct drm_atomic_state *state,
 			crtc_state = drm_atomic_get_new_crtc_state(state, crtc);
 
 			crtc_state->encoder_mask &=
-				~(1 << drm_encoder_index(conn_state->best_encoder));
+				~drm_encoder_mask(conn_state->best_encoder);
 		}
 	}
 
@@ -233,7 +234,7 @@ set_best_encoder(struct drm_atomic_state *state,
 			crtc_state = drm_atomic_get_new_crtc_state(state, crtc);
 
 			crtc_state->encoder_mask |=
-				1 << drm_encoder_index(encoder);
+				drm_encoder_mask(encoder);
 		}
 	}
 
@@ -644,7 +645,7 @@ drm_atomic_helper_check_modeset(struct drm_device *dev,
 		if (ret)
 			return ret;
 
-		connectors_mask += BIT(i);
+		connectors_mask |= BIT(i);
 	}
 
 	/*
@@ -1172,6 +1173,27 @@ void drm_atomic_helper_commit_modeset_disables(struct drm_device *dev,
 }
 EXPORT_SYMBOL(drm_atomic_helper_commit_modeset_disables);
 
+static void drm_atomic_helper_commit_writebacks(struct drm_device *dev,
+						struct drm_atomic_state *old_state)
+{
+	struct drm_connector *connector;
+	struct drm_connector_state *new_conn_state;
+	int i;
+
+	for_each_new_connector_in_state(old_state, connector, new_conn_state, i) {
+		const struct drm_connector_helper_funcs *funcs;
+
+		funcs = connector->helper_private;
+		if (!funcs->atomic_commit)
+			continue;
+
+		if (new_conn_state->writeback_job && new_conn_state->writeback_job->fb) {
+			WARN_ON(connector->connector_type != DRM_MODE_CONNECTOR_WRITEBACK);
+			funcs->atomic_commit(connector, new_conn_state);
+		}
+	}
+}
+
 /**
  * drm_atomic_helper_commit_modeset_enables - modeset commit to enable outputs
  * @dev: DRM device
@@ -1251,6 +1273,8 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev,
 
 		drm_bridge_enable(encoder->bridge);
 	}
+
+	drm_atomic_helper_commit_writebacks(dev, old_state);
 }
 EXPORT_SYMBOL(drm_atomic_helper_commit_modeset_enables);
 
@@ -1426,6 +1450,8 @@ void drm_atomic_helper_commit_tail(struct drm_atomic_state *old_state)
 
 	drm_atomic_helper_commit_modeset_enables(dev, old_state);
 
+	drm_atomic_helper_fake_vblank(old_state);
+
 	drm_atomic_helper_commit_hw_done(old_state);
 
 	drm_atomic_helper_wait_for_vblanks(dev, old_state);
@@ -1455,6 +1481,8 @@ void drm_atomic_helper_commit_tail_rpm(struct drm_atomic_state *old_state)
 	drm_atomic_helper_commit_planes(dev, old_state,
 					DRM_PLANE_COMMIT_ACTIVE_ONLY);
 
+	drm_atomic_helper_fake_vblank(old_state);
+
 	drm_atomic_helper_commit_hw_done(old_state);
 
 	drm_atomic_helper_wait_for_vblanks(dev, old_state);
@@ -2032,6 +2060,45 @@ void drm_atomic_helper_wait_for_dependencies(struct drm_atomic_state *old_state)
 EXPORT_SYMBOL(drm_atomic_helper_wait_for_dependencies);
 
 /**
+ * drm_atomic_helper_fake_vblank - fake VBLANK events if needed
+ * @old_state: atomic state object with old state structures
+ *
+ * This function walks all CRTCs and fake VBLANK events on those with
+ * &drm_crtc_state.no_vblank set to true and &drm_crtc_state.event != NULL.
+ * The primary use of this function is writeback connectors working in oneshot
+ * mode and faking VBLANK events. In this case they only fake the VBLANK event
+ * when a job is queued, and any change to the pipeline that does not touch the
+ * connector is leading to timeouts when calling
+ * drm_atomic_helper_wait_for_vblanks() or
+ * drm_atomic_helper_wait_for_flip_done().
+ *
+ * This is part of the atomic helper support for nonblocking commits, see
+ * drm_atomic_helper_setup_commit() for an overview.
+ */
+void drm_atomic_helper_fake_vblank(struct drm_atomic_state *old_state)
+{
+	struct drm_crtc_state *new_crtc_state;
+	struct drm_crtc *crtc;
+	int i;
+
+	for_each_new_crtc_in_state(old_state, crtc, new_crtc_state, i) {
+		unsigned long flags;
+
+		if (!new_crtc_state->no_vblank)
+			continue;
+
+		spin_lock_irqsave(&old_state->dev->event_lock, flags);
+		if (new_crtc_state->event) {
+			drm_crtc_send_vblank_event(crtc,
+						   new_crtc_state->event);
+			new_crtc_state->event = NULL;
+		}
+		spin_unlock_irqrestore(&old_state->dev->event_lock, flags);
+	}
+}
+EXPORT_SYMBOL(drm_atomic_helper_fake_vblank);
+
+/**
  * drm_atomic_helper_commit_hw_done - setup possible nonblocking commit
  * @old_state: atomic state object with old state structures
  *
@@ -2322,11 +2389,13 @@ drm_atomic_helper_commit_planes_on_crtc(struct drm_crtc_state *old_crtc_state)
 	const struct drm_crtc_helper_funcs *crtc_funcs;
 	struct drm_crtc *crtc = old_crtc_state->crtc;
 	struct drm_atomic_state *old_state = old_crtc_state->state;
+	struct drm_crtc_state *new_crtc_state =
+		drm_atomic_get_new_crtc_state(old_state, crtc);
 	struct drm_plane *plane;
 	unsigned plane_mask;
 
 	plane_mask = old_crtc_state->plane_mask;
-	plane_mask |= crtc->state->plane_mask;
+	plane_mask |= new_crtc_state->plane_mask;
 
 	crtc_funcs = crtc->helper_private;
 	if (crtc_funcs && crtc_funcs->atomic_begin)
@@ -2335,6 +2404,8 @@ drm_atomic_helper_commit_planes_on_crtc(struct drm_crtc_state *old_crtc_state)
 	drm_for_each_plane_mask(plane, crtc->dev, plane_mask) {
 		struct drm_plane_state *old_plane_state =
 			drm_atomic_get_old_plane_state(old_state, plane);
+		struct drm_plane_state *new_plane_state =
+			drm_atomic_get_new_plane_state(old_state, plane);
 		const struct drm_plane_helper_funcs *plane_funcs;
 
 		plane_funcs = plane->helper_private;
@@ -2342,13 +2413,14 @@ drm_atomic_helper_commit_planes_on_crtc(struct drm_crtc_state *old_crtc_state)
 		if (!old_plane_state || !plane_funcs)
 			continue;
 
-		WARN_ON(plane->state->crtc && plane->state->crtc != crtc);
+		WARN_ON(new_plane_state->crtc &&
+			new_plane_state->crtc != crtc);
 
-		if (drm_atomic_plane_disabling(old_plane_state, plane->state) &&
+		if (drm_atomic_plane_disabling(old_plane_state, new_plane_state) &&
 		    plane_funcs->atomic_disable)
 			plane_funcs->atomic_disable(plane, old_plane_state);
-		else if (plane->state->crtc ||
-			 drm_atomic_plane_disabling(old_plane_state, plane->state))
+		else if (new_plane_state->crtc ||
+			 drm_atomic_plane_disabling(old_plane_state, new_plane_state))
 			plane_funcs->atomic_update(plane, old_plane_state);
 	}
 
@@ -2797,7 +2869,7 @@ static int update_output_state(struct drm_atomic_state *state,
  * resets the "link-status" property to GOOD, to force any link
  * re-training. The SETCRTC ioctl does not define whether an update does
  * need a full modeset or just a plane update, hence we're allowed to do
- * that. See also drm_mode_connector_set_link_status_property().
+ * that. See also drm_connector_set_link_status_property().
  *
  * Returns:
  * Returns 0 on success, negative errno numbers on failure.
@@ -2916,7 +2988,6 @@ static int __drm_atomic_helper_disable_all(struct drm_device *dev,
 	struct drm_plane *plane;
 	struct drm_crtc_state *crtc_state;
 	struct drm_crtc *crtc;
-	unsigned plane_mask = 0;
 	int ret, i;
 
 	state = drm_atomic_state_alloc(dev);
@@ -2959,17 +3030,10 @@ static int __drm_atomic_helper_disable_all(struct drm_device *dev,
 			goto free;
 
 		drm_atomic_set_fb_for_plane(plane_state, NULL);
-
-		if (clean_old_fbs) {
-			plane->old_fb = plane->fb;
-			plane_mask |= BIT(drm_plane_index(plane));
-		}
 	}
 
 	ret = drm_atomic_commit(state);
 free:
-	if (plane_mask)
-		drm_atomic_clean_old_fb(dev, plane_mask, ret);
 	drm_atomic_state_put(state);
 	return ret;
 }
@@ -3131,13 +3195,8 @@ int drm_atomic_helper_commit_duplicated_state(struct drm_atomic_state *state,
 
 	state->acquire_ctx = ctx;
 
-	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
-		WARN_ON(plane->crtc != new_plane_state->crtc);
-		WARN_ON(plane->fb != new_plane_state->fb);
-		WARN_ON(plane->old_fb);
-
+	for_each_new_plane_in_state(state, plane, new_plane_state, i)
 		state->planes[i].old_state = plane->state;
-	}
 
 	for_each_new_crtc_in_state(state, crtc, new_crtc_state, i)
 		state->crtcs[i].old_state = crtc->state;
@@ -3662,6 +3721,9 @@ __drm_atomic_helper_connector_duplicate_state(struct drm_connector *connector,
 	if (state->crtc)
 		drm_connector_get(connector);
 	state->commit = NULL;
+
+	/* Don't copy over a writeback job, they are used only once */
+	state->writeback_job = NULL;
 }
 EXPORT_SYMBOL(__drm_atomic_helper_connector_duplicate_state);
 
diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c
new file mode 100644
index 000000000000..baff50a4c234
--- /dev/null
+++ b/drivers/gpu/drm/drm_client.c
@@ -0,0 +1,406 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2018 Noralf Trønnes
+ */
+
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+
+#include <drm/drm_client.h>
+#include <drm/drm_debugfs.h>
+#include <drm/drm_device.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_file.h>
+#include <drm/drm_fourcc.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_mode.h>
+#include <drm/drm_print.h>
+#include <drm/drmP.h>
+
+#include "drm_crtc_internal.h"
+#include "drm_internal.h"
+
+/**
+ * DOC: overview
+ *
+ * This library provides support for clients running in the kernel like fbdev and bootsplash.
+ * Currently it's only partially implemented, just enough to support fbdev.
+ *
+ * GEM drivers which provide a GEM based dumb buffer with a virtual address are supported.
+ */
+
+static int drm_client_open(struct drm_client_dev *client)
+{
+	struct drm_device *dev = client->dev;
+	struct drm_file *file;
+
+	file = drm_file_alloc(dev->primary);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	mutex_lock(&dev->filelist_mutex);
+	list_add(&file->lhead, &dev->filelist_internal);
+	mutex_unlock(&dev->filelist_mutex);
+
+	client->file = file;
+
+	return 0;
+}
+
+static void drm_client_close(struct drm_client_dev *client)
+{
+	struct drm_device *dev = client->dev;
+
+	mutex_lock(&dev->filelist_mutex);
+	list_del(&client->file->lhead);
+	mutex_unlock(&dev->filelist_mutex);
+
+	drm_file_free(client->file);
+}
+EXPORT_SYMBOL(drm_client_close);
+
+/**
+ * drm_client_new - Create a DRM client
+ * @dev: DRM device
+ * @client: DRM client
+ * @name: Client name
+ * @funcs: DRM client functions (optional)
+ *
+ * The caller needs to hold a reference on @dev before calling this function.
+ * The client is freed when the &drm_device is unregistered. See drm_client_release().
+ *
+ * Returns:
+ * Zero on success or negative error code on failure.
+ */
+int drm_client_new(struct drm_device *dev, struct drm_client_dev *client,
+		   const char *name, const struct drm_client_funcs *funcs)
+{
+	int ret;
+
+	if (!drm_core_check_feature(dev, DRIVER_MODESET) ||
+	    !dev->driver->dumb_create || !dev->driver->gem_prime_vmap)
+		return -ENOTSUPP;
+
+	if (funcs && !try_module_get(funcs->owner))
+		return -ENODEV;
+
+	client->dev = dev;
+	client->name = name;
+	client->funcs = funcs;
+
+	ret = drm_client_open(client);
+	if (ret)
+		goto err_put_module;
+
+	mutex_lock(&dev->clientlist_mutex);
+	list_add(&client->list, &dev->clientlist);
+	mutex_unlock(&dev->clientlist_mutex);
+
+	drm_dev_get(dev);
+
+	return 0;
+
+err_put_module:
+	if (funcs)
+		module_put(funcs->owner);
+
+	return ret;
+}
+EXPORT_SYMBOL(drm_client_new);
+
+/**
+ * drm_client_release - Release DRM client resources
+ * @client: DRM client
+ *
+ * Releases resources by closing the &drm_file that was opened by drm_client_new().
+ * It is called automatically if the &drm_client_funcs.unregister callback is _not_ set.
+ *
+ * This function should only be called from the unregister callback. An exception
+ * is fbdev which cannot free the buffer if userspace has open file descriptors.
+ *
+ * Note:
+ * Clients cannot initiate a release by themselves. This is done to keep the code simple.
+ * The driver has to be unloaded before the client can be unloaded.
+ */
+void drm_client_release(struct drm_client_dev *client)
+{
+	struct drm_device *dev = client->dev;
+
+	DRM_DEV_DEBUG_KMS(dev->dev, "%s\n", client->name);
+
+	drm_client_close(client);
+	drm_dev_put(dev);
+	if (client->funcs)
+		module_put(client->funcs->owner);
+}
+EXPORT_SYMBOL(drm_client_release);
+
+void drm_client_dev_unregister(struct drm_device *dev)
+{
+	struct drm_client_dev *client, *tmp;
+
+	if (!drm_core_check_feature(dev, DRIVER_MODESET))
+		return;
+
+	mutex_lock(&dev->clientlist_mutex);
+	list_for_each_entry_safe(client, tmp, &dev->clientlist, list) {
+		list_del(&client->list);
+		if (client->funcs && client->funcs->unregister) {
+			client->funcs->unregister(client);
+		} else {
+			drm_client_release(client);
+			kfree(client);
+		}
+	}
+	mutex_unlock(&dev->clientlist_mutex);
+}
+
+/**
+ * drm_client_dev_hotplug - Send hotplug event to clients
+ * @dev: DRM device
+ *
+ * This function calls the &drm_client_funcs.hotplug callback on the attached clients.
+ *
+ * drm_kms_helper_hotplug_event() calls this function, so drivers that use it
+ * don't need to call this function themselves.
+ */
+void drm_client_dev_hotplug(struct drm_device *dev)
+{
+	struct drm_client_dev *client;
+	int ret;
+
+	if (!drm_core_check_feature(dev, DRIVER_MODESET))
+		return;
+
+	mutex_lock(&dev->clientlist_mutex);
+	list_for_each_entry(client, &dev->clientlist, list) {
+		if (!client->funcs || !client->funcs->hotplug)
+			continue;
+
+		ret = client->funcs->hotplug(client);
+		DRM_DEV_DEBUG_KMS(dev->dev, "%s: ret=%d\n", client->name, ret);
+	}
+	mutex_unlock(&dev->clientlist_mutex);
+}
+EXPORT_SYMBOL(drm_client_dev_hotplug);
+
+void drm_client_dev_restore(struct drm_device *dev)
+{
+	struct drm_client_dev *client;
+	int ret;
+
+	if (!drm_core_check_feature(dev, DRIVER_MODESET))
+		return;
+
+	mutex_lock(&dev->clientlist_mutex);
+	list_for_each_entry(client, &dev->clientlist, list) {
+		if (!client->funcs || !client->funcs->restore)
+			continue;
+
+		ret = client->funcs->restore(client);
+		DRM_DEV_DEBUG_KMS(dev->dev, "%s: ret=%d\n", client->name, ret);
+		if (!ret) /* The first one to return zero gets the privilege to restore */
+			break;
+	}
+	mutex_unlock(&dev->clientlist_mutex);
+}
+
+static void drm_client_buffer_delete(struct drm_client_buffer *buffer)
+{
+	struct drm_device *dev = buffer->client->dev;
+
+	if (buffer->vaddr && dev->driver->gem_prime_vunmap)
+		dev->driver->gem_prime_vunmap(buffer->gem, buffer->vaddr);
+
+	if (buffer->gem)
+		drm_gem_object_put_unlocked(buffer->gem);
+
+	if (buffer->handle)
+		drm_mode_destroy_dumb(dev, buffer->handle, buffer->client->file);
+
+	kfree(buffer);
+}
+
+static struct drm_client_buffer *
+drm_client_buffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format)
+{
+	struct drm_mode_create_dumb dumb_args = { };
+	struct drm_device *dev = client->dev;
+	struct drm_client_buffer *buffer;
+	struct drm_gem_object *obj;
+	void *vaddr;
+	int ret;
+
+	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
+	if (!buffer)
+		return ERR_PTR(-ENOMEM);
+
+	buffer->client = client;
+
+	dumb_args.width = width;
+	dumb_args.height = height;
+	dumb_args.bpp = drm_format_plane_cpp(format, 0) * 8;
+	ret = drm_mode_create_dumb(dev, &dumb_args, client->file);
+	if (ret)
+		goto err_delete;
+
+	buffer->handle = dumb_args.handle;
+	buffer->pitch = dumb_args.pitch;
+
+	obj = drm_gem_object_lookup(client->file, dumb_args.handle);
+	if (!obj)  {
+		ret = -ENOENT;
+		goto err_delete;
+	}
+
+	buffer->gem = obj;
+
+	/*
+	 * FIXME: The dependency on GEM here isn't required, we could
+	 * convert the driver handle to a dma-buf instead and use the
+	 * backend-agnostic dma-buf vmap support instead. This would
+	 * require that the handle2fd prime ioctl is reworked to pull the
+	 * fd_install step out of the driver backend hooks, to make that
+	 * final step optional for internal users.
+	 */
+	vaddr = dev->driver->gem_prime_vmap(obj);
+	if (!vaddr) {
+		ret = -ENOMEM;
+		goto err_delete;
+	}
+
+	buffer->vaddr = vaddr;
+
+	return buffer;
+
+err_delete:
+	drm_client_buffer_delete(buffer);
+
+	return ERR_PTR(ret);
+}
+
+static void drm_client_buffer_rmfb(struct drm_client_buffer *buffer)
+{
+	int ret;
+
+	if (!buffer->fb)
+		return;
+
+	ret = drm_mode_rmfb(buffer->client->dev, buffer->fb->base.id, buffer->client->file);
+	if (ret)
+		DRM_DEV_ERROR(buffer->client->dev->dev,
+			      "Error removing FB:%u (%d)\n", buffer->fb->base.id, ret);
+
+	buffer->fb = NULL;
+}
+
+static int drm_client_buffer_addfb(struct drm_client_buffer *buffer,
+				   u32 width, u32 height, u32 format)
+{
+	struct drm_client_dev *client = buffer->client;
+	struct drm_mode_fb_cmd fb_req = { };
+	const struct drm_format_info *info;
+	int ret;
+
+	info = drm_format_info(format);
+	fb_req.bpp = info->cpp[0] * 8;
+	fb_req.depth = info->depth;
+	fb_req.width = width;
+	fb_req.height = height;
+	fb_req.handle = buffer->handle;
+	fb_req.pitch = buffer->pitch;
+
+	ret = drm_mode_addfb(client->dev, &fb_req, client->file);
+	if (ret)
+		return ret;
+
+	buffer->fb = drm_framebuffer_lookup(client->dev, buffer->client->file, fb_req.fb_id);
+	if (WARN_ON(!buffer->fb))
+		return -ENOENT;
+
+	/* drop the reference we picked up in framebuffer lookup */
+	drm_framebuffer_put(buffer->fb);
+
+	strscpy(buffer->fb->comm, client->name, TASK_COMM_LEN);
+
+	return 0;
+}
+
+/**
+ * drm_client_framebuffer_create - Create a client framebuffer
+ * @client: DRM client
+ * @width: Framebuffer width
+ * @height: Framebuffer height
+ * @format: Buffer format
+ *
+ * This function creates a &drm_client_buffer which consists of a
+ * &drm_framebuffer backed by a dumb buffer.
+ * Call drm_client_framebuffer_delete() to free the buffer.
+ *
+ * Returns:
+ * Pointer to a client buffer or an error pointer on failure.
+ */
+struct drm_client_buffer *
+drm_client_framebuffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format)
+{
+	struct drm_client_buffer *buffer;
+	int ret;
+
+	buffer = drm_client_buffer_create(client, width, height, format);
+	if (IS_ERR(buffer))
+		return buffer;
+
+	ret = drm_client_buffer_addfb(buffer, width, height, format);
+	if (ret) {
+		drm_client_buffer_delete(buffer);
+		return ERR_PTR(ret);
+	}
+
+	return buffer;
+}
+EXPORT_SYMBOL(drm_client_framebuffer_create);
+
+/**
+ * drm_client_framebuffer_delete - Delete a client framebuffer
+ * @buffer: DRM client buffer (can be NULL)
+ */
+void drm_client_framebuffer_delete(struct drm_client_buffer *buffer)
+{
+	if (!buffer)
+		return;
+
+	drm_client_buffer_rmfb(buffer);
+	drm_client_buffer_delete(buffer);
+}
+EXPORT_SYMBOL(drm_client_framebuffer_delete);
+
+#ifdef CONFIG_DEBUG_FS
+static int drm_client_debugfs_internal_clients(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct drm_printer p = drm_seq_file_printer(m);
+	struct drm_client_dev *client;
+
+	mutex_lock(&dev->clientlist_mutex);
+	list_for_each_entry(client, &dev->clientlist, list)
+		drm_printf(&p, "%s\n", client->name);
+	mutex_unlock(&dev->clientlist_mutex);
+
+	return 0;
+}
+
+static const struct drm_info_list drm_client_debugfs_list[] = {
+	{ "internal_clients", drm_client_debugfs_internal_clients, 0 },
+};
+
+int drm_client_debugfs_init(struct drm_minor *minor)
+{
+	return drm_debugfs_create_files(drm_client_debugfs_list,
+					ARRAY_SIZE(drm_client_debugfs_list),
+					minor->debugfs_root, minor);
+}
+#endif
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 9b9ba5d5ec0c..6011d769d50b 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -48,7 +48,7 @@
  *
  * Connectors must be attached to an encoder to be used. For devices that map
  * connectors to encoders 1:1, the connector should be attached at
- * initialization time with a call to drm_mode_connector_attach_encoder(). The
+ * initialization time with a call to drm_connector_attach_encoder(). The
  * driver must also set the &drm_connector.encoder field to point to the
  * attached encoder.
  *
@@ -87,6 +87,7 @@ static struct drm_conn_prop_enum_list drm_connector_enum_list[] = {
 	{ DRM_MODE_CONNECTOR_VIRTUAL, "Virtual" },
 	{ DRM_MODE_CONNECTOR_DSI, "DSI" },
 	{ DRM_MODE_CONNECTOR_DPI, "DPI" },
+	{ DRM_MODE_CONNECTOR_WRITEBACK, "Writeback" },
 };
 
 void drm_connector_ida_init(void)
@@ -195,6 +196,10 @@ int drm_connector_init(struct drm_device *dev,
 	struct ida *connector_ida =
 		&drm_connector_enum_list[connector_type].ida;
 
+	WARN_ON(drm_drv_uses_atomic_modeset(dev) &&
+		(!funcs->atomic_destroy_state ||
+		 !funcs->atomic_duplicate_state));
+
 	ret = __drm_mode_object_add(dev, &connector->base,
 				    DRM_MODE_OBJECT_CONNECTOR,
 				    false, drm_connector_free);
@@ -249,7 +254,8 @@ int drm_connector_init(struct drm_device *dev,
 	config->num_connector++;
 	spin_unlock_irq(&config->connector_list_lock);
 
-	if (connector_type != DRM_MODE_CONNECTOR_VIRTUAL)
+	if (connector_type != DRM_MODE_CONNECTOR_VIRTUAL &&
+	    connector_type != DRM_MODE_CONNECTOR_WRITEBACK)
 		drm_object_attach_property(&connector->base,
 					      config->edid_property,
 					      0);
@@ -285,7 +291,7 @@ out_put:
 EXPORT_SYMBOL(drm_connector_init);
 
 /**
- * drm_mode_connector_attach_encoder - attach a connector to an encoder
+ * drm_connector_attach_encoder - attach a connector to an encoder
  * @connector: connector to attach
  * @encoder: encoder to attach @connector to
  *
@@ -296,8 +302,8 @@ EXPORT_SYMBOL(drm_connector_init);
  * Returns:
  * Zero on success, negative errno on failure.
  */
-int drm_mode_connector_attach_encoder(struct drm_connector *connector,
-				      struct drm_encoder *encoder)
+int drm_connector_attach_encoder(struct drm_connector *connector,
+				 struct drm_encoder *encoder)
 {
 	int i;
 
@@ -315,7 +321,7 @@ int drm_mode_connector_attach_encoder(struct drm_connector *connector,
 	if (WARN_ON(connector->encoder))
 		return -EINVAL;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
+	for (i = 0; i < ARRAY_SIZE(connector->encoder_ids); i++) {
 		if (connector->encoder_ids[i] == 0) {
 			connector->encoder_ids[i] = encoder->base.id;
 			return 0;
@@ -323,7 +329,30 @@ int drm_mode_connector_attach_encoder(struct drm_connector *connector,
 	}
 	return -ENOMEM;
 }
-EXPORT_SYMBOL(drm_mode_connector_attach_encoder);
+EXPORT_SYMBOL(drm_connector_attach_encoder);
+
+/**
+ * drm_connector_has_possible_encoder - check if the connector and encoder are assosicated with each other
+ * @connector: the connector
+ * @encoder: the encoder
+ *
+ * Returns:
+ * True if @encoder is one of the possible encoders for @connector.
+ */
+bool drm_connector_has_possible_encoder(struct drm_connector *connector,
+					struct drm_encoder *encoder)
+{
+	struct drm_encoder *enc;
+	int i;
+
+	drm_connector_for_each_possible_encoder(connector, enc, i) {
+		if (enc == encoder)
+			return true;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL(drm_connector_has_possible_encoder);
 
 static void drm_mode_remove(struct drm_connector *connector,
 			    struct drm_display_mode *mode)
@@ -577,7 +606,7 @@ __drm_connector_put_safe(struct drm_connector *conn)
 
 /**
  * drm_connector_list_iter_next - return next connector
- * @iter: connectr_list iterator
+ * @iter: connector_list iterator
  *
  * Returns the next connector for @iter, or NULL when the list walk has
  * completed.
@@ -720,6 +749,14 @@ static const struct drm_prop_enum_list drm_aspect_ratio_enum_list[] = {
 	{ DRM_MODE_PICTURE_ASPECT_16_9, "16:9" },
 };
 
+static const struct drm_prop_enum_list drm_content_type_enum_list[] = {
+	{ DRM_MODE_CONTENT_TYPE_NO_DATA, "No Data" },
+	{ DRM_MODE_CONTENT_TYPE_GRAPHICS, "Graphics" },
+	{ DRM_MODE_CONTENT_TYPE_PHOTO, "Photo" },
+	{ DRM_MODE_CONTENT_TYPE_CINEMA, "Cinema" },
+	{ DRM_MODE_CONTENT_TYPE_GAME, "Game" },
+};
+
 static const struct drm_prop_enum_list drm_panel_orientation_enum_list[] = {
 	{ DRM_MODE_PANEL_ORIENTATION_NORMAL,	"Normal"	},
 	{ DRM_MODE_PANEL_ORIENTATION_BOTTOM_UP,	"Upside Down"	},
@@ -777,7 +814,7 @@ DRM_ENUM_NAME_FN(drm_get_content_protection_name, drm_cp_enum_list)
  * 	Blob property which contains the current EDID read from the sink. This
  * 	is useful to parse sink identification information like vendor, model
  * 	and serial. Drivers should update this property by calling
- * 	drm_mode_connector_update_edid_property(), usually after having parsed
+ * 	drm_connector_update_edid_property(), usually after having parsed
  * 	the EDID using drm_add_edid_modes(). Userspace cannot change this
  * 	property.
  * DPMS:
@@ -815,7 +852,7 @@ DRM_ENUM_NAME_FN(drm_get_content_protection_name, drm_cp_enum_list)
  * PATH:
  * 	Connector path property to identify how this sink is physically
  * 	connected. Used by DP MST. This should be set by calling
- * 	drm_mode_connector_set_path_property(), in the case of DP MST with the
+ * 	drm_connector_set_path_property(), in the case of DP MST with the
  * 	path property the MST manager created. Userspace cannot change this
  * 	property.
  * TILE:
@@ -826,14 +863,14 @@ DRM_ENUM_NAME_FN(drm_get_content_protection_name, drm_cp_enum_list)
  * 	are not gen-locked. Note that for tiled panels which are genlocked, like
  * 	dual-link LVDS or dual-link DSI, the driver should try to not expose the
  * 	tiling and virtualize both &drm_crtc and &drm_plane if needed. Drivers
- * 	should update this value using drm_mode_connector_set_tile_property().
+ * 	should update this value using drm_connector_set_tile_property().
  * 	Userspace cannot change this property.
  * link-status:
  *      Connector link-status property to indicate the status of link. The
  *      default value of link-status is "GOOD". If something fails during or
  *      after modeset, the kernel driver may set this to "BAD" and issue a
  *      hotplug uevent. Drivers should update this value using
- *      drm_mode_connector_set_link_status_property().
+ *      drm_connector_set_link_status_property().
  * non_desktop:
  * 	Indicates the output should be ignored for purposes of displaying a
  * 	standard desktop environment or console. This is most likely because
@@ -997,6 +1034,82 @@ int drm_mode_create_dvi_i_properties(struct drm_device *dev)
 EXPORT_SYMBOL(drm_mode_create_dvi_i_properties);
 
 /**
+ * DOC: HDMI connector properties
+ *
+ * content type (HDMI specific):
+ *	Indicates content type setting to be used in HDMI infoframes to indicate
+ *	content type for the external device, so that it adjusts it's display
+ *	settings accordingly.
+ *
+ *	The value of this property can be one of the following:
+ *
+ *	No Data:
+ *		Content type is unknown
+ *	Graphics:
+ *		Content type is graphics
+ *	Photo:
+ *		Content type is photo
+ *	Cinema:
+ *		Content type is cinema
+ *	Game:
+ *		Content type is game
+ *
+ *	Drivers can set up this property by calling
+ *	drm_connector_attach_content_type_property(). Decoding to
+ *	infoframe values is done through drm_hdmi_avi_infoframe_content_type().
+ */
+
+/**
+ * drm_connector_attach_content_type_property - attach content-type property
+ * @connector: connector to attach content type property on.
+ *
+ * Called by a driver the first time a HDMI connector is made.
+ */
+int drm_connector_attach_content_type_property(struct drm_connector *connector)
+{
+	if (!drm_mode_create_content_type_property(connector->dev))
+		drm_object_attach_property(&connector->base,
+					   connector->dev->mode_config.content_type_property,
+					   DRM_MODE_CONTENT_TYPE_NO_DATA);
+	return 0;
+}
+EXPORT_SYMBOL(drm_connector_attach_content_type_property);
+
+
+/**
+ * drm_hdmi_avi_infoframe_content_type() - fill the HDMI AVI infoframe
+ *                                         content type information, based
+ *                                         on correspondent DRM property.
+ * @frame: HDMI AVI infoframe
+ * @conn_state: DRM display connector state
+ *
+ */
+void drm_hdmi_avi_infoframe_content_type(struct hdmi_avi_infoframe *frame,
+					 const struct drm_connector_state *conn_state)
+{
+	switch (conn_state->content_type) {
+	case DRM_MODE_CONTENT_TYPE_GRAPHICS:
+		frame->content_type = HDMI_CONTENT_TYPE_GRAPHICS;
+		break;
+	case DRM_MODE_CONTENT_TYPE_CINEMA:
+		frame->content_type = HDMI_CONTENT_TYPE_CINEMA;
+		break;
+	case DRM_MODE_CONTENT_TYPE_GAME:
+		frame->content_type = HDMI_CONTENT_TYPE_GAME;
+		break;
+	case DRM_MODE_CONTENT_TYPE_PHOTO:
+		frame->content_type = HDMI_CONTENT_TYPE_PHOTO;
+		break;
+	default:
+		/* Graphics is the default(0) */
+		frame->content_type = HDMI_CONTENT_TYPE_GRAPHICS;
+	}
+
+	frame->itc = conn_state->content_type != DRM_MODE_CONTENT_TYPE_NO_DATA;
+}
+EXPORT_SYMBOL(drm_hdmi_avi_infoframe_content_type);
+
+/**
  * drm_create_tv_properties - create TV specific connector properties
  * @dev: DRM device
  * @num_modes: number of different TV formats (modes) supported
@@ -1261,6 +1374,33 @@ int drm_mode_create_aspect_ratio_property(struct drm_device *dev)
 EXPORT_SYMBOL(drm_mode_create_aspect_ratio_property);
 
 /**
+ * drm_mode_create_content_type_property - create content type property
+ * @dev: DRM device
+ *
+ * Called by a driver the first time it's needed, must be attached to desired
+ * connectors.
+ *
+ * Returns:
+ * Zero on success, negative errno on failure.
+ */
+int drm_mode_create_content_type_property(struct drm_device *dev)
+{
+	if (dev->mode_config.content_type_property)
+		return 0;
+
+	dev->mode_config.content_type_property =
+		drm_property_create_enum(dev, 0, "content type",
+					 drm_content_type_enum_list,
+					 ARRAY_SIZE(drm_content_type_enum_list));
+
+	if (dev->mode_config.content_type_property == NULL)
+		return -ENOMEM;
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_mode_create_content_type_property);
+
+/**
  * drm_mode_create_suggested_offset_properties - create suggests offset properties
  * @dev: DRM device
  *
@@ -1285,7 +1425,7 @@ int drm_mode_create_suggested_offset_properties(struct drm_device *dev)
 EXPORT_SYMBOL(drm_mode_create_suggested_offset_properties);
 
 /**
- * drm_mode_connector_set_path_property - set tile property on connector
+ * drm_connector_set_path_property - set tile property on connector
  * @connector: connector to set property on.
  * @path: path to use for property; must not be NULL.
  *
@@ -1297,8 +1437,8 @@ EXPORT_SYMBOL(drm_mode_create_suggested_offset_properties);
  * Returns:
  * Zero on success, negative errno on failure.
  */
-int drm_mode_connector_set_path_property(struct drm_connector *connector,
-					 const char *path)
+int drm_connector_set_path_property(struct drm_connector *connector,
+				    const char *path)
 {
 	struct drm_device *dev = connector->dev;
 	int ret;
@@ -1311,10 +1451,10 @@ int drm_mode_connector_set_path_property(struct drm_connector *connector,
 	                                       dev->mode_config.path_property);
 	return ret;
 }
-EXPORT_SYMBOL(drm_mode_connector_set_path_property);
+EXPORT_SYMBOL(drm_connector_set_path_property);
 
 /**
- * drm_mode_connector_set_tile_property - set tile property on connector
+ * drm_connector_set_tile_property - set tile property on connector
  * @connector: connector to set property on.
  *
  * This looks up the tile information for a connector, and creates a
@@ -1324,7 +1464,7 @@ EXPORT_SYMBOL(drm_mode_connector_set_path_property);
  * Returns:
  * Zero on success, errno on failure.
  */
-int drm_mode_connector_set_tile_property(struct drm_connector *connector)
+int drm_connector_set_tile_property(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
 	char tile[256];
@@ -1354,10 +1494,10 @@ int drm_mode_connector_set_tile_property(struct drm_connector *connector)
 	                                       dev->mode_config.tile_property);
 	return ret;
 }
-EXPORT_SYMBOL(drm_mode_connector_set_tile_property);
+EXPORT_SYMBOL(drm_connector_set_tile_property);
 
 /**
- * drm_mode_connector_update_edid_property - update the edid property of a connector
+ * drm_connector_update_edid_property - update the edid property of a connector
  * @connector: drm connector
  * @edid: new value of the edid property
  *
@@ -1367,8 +1507,8 @@ EXPORT_SYMBOL(drm_mode_connector_set_tile_property);
  * Returns:
  * Zero on success, negative errno on failure.
  */
-int drm_mode_connector_update_edid_property(struct drm_connector *connector,
-					    const struct edid *edid)
+int drm_connector_update_edid_property(struct drm_connector *connector,
+				       const struct edid *edid)
 {
 	struct drm_device *dev = connector->dev;
 	size_t size = 0;
@@ -1406,10 +1546,10 @@ int drm_mode_connector_update_edid_property(struct drm_connector *connector,
 	                                       dev->mode_config.edid_property);
 	return ret;
 }
-EXPORT_SYMBOL(drm_mode_connector_update_edid_property);
+EXPORT_SYMBOL(drm_connector_update_edid_property);
 
 /**
- * drm_mode_connector_set_link_status_property - Set link status property of a connector
+ * drm_connector_set_link_status_property - Set link status property of a connector
  * @connector: drm connector
  * @link_status: new value of link status property (0: Good, 1: Bad)
  *
@@ -1427,8 +1567,8 @@ EXPORT_SYMBOL(drm_mode_connector_update_edid_property);
  * it is not limited to DP or link training. For example, if we implement
  * asynchronous setcrtc, this property can be used to report any failures in that.
  */
-void drm_mode_connector_set_link_status_property(struct drm_connector *connector,
-						 uint64_t link_status)
+void drm_connector_set_link_status_property(struct drm_connector *connector,
+					    uint64_t link_status)
 {
 	struct drm_device *dev = connector->dev;
 
@@ -1436,7 +1576,7 @@ void drm_mode_connector_set_link_status_property(struct drm_connector *connector
 	connector->state->link_status = link_status;
 	drm_modeset_unlock(&dev->mode_config.connection_mutex);
 }
-EXPORT_SYMBOL(drm_mode_connector_set_link_status_property);
+EXPORT_SYMBOL(drm_connector_set_link_status_property);
 
 /**
  * drm_connector_init_panel_orientation_property -
@@ -1489,7 +1629,7 @@ int drm_connector_init_panel_orientation_property(
 }
 EXPORT_SYMBOL(drm_connector_init_panel_orientation_property);
 
-int drm_mode_connector_set_obj_prop(struct drm_mode_object *obj,
+int drm_connector_set_obj_prop(struct drm_mode_object *obj,
 				    struct drm_property *property,
 				    uint64_t value)
 {
@@ -1507,8 +1647,8 @@ int drm_mode_connector_set_obj_prop(struct drm_mode_object *obj,
 	return ret;
 }
 
-int drm_mode_connector_property_set_ioctl(struct drm_device *dev,
-				       void *data, struct drm_file *file_priv)
+int drm_connector_property_set_ioctl(struct drm_device *dev,
+				     void *data, struct drm_file *file_priv)
 {
 	struct drm_mode_connector_set_property *conn_set_prop = data;
 	struct drm_mode_obj_set_property obj_set_prop = {
@@ -1589,22 +1729,19 @@ int drm_mode_getconnector(struct drm_device *dev, void *data,
 	if (!connector)
 		return -ENOENT;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++)
-		if (connector->encoder_ids[i] != 0)
-			encoders_count++;
+	drm_connector_for_each_possible_encoder(connector, encoder, i)
+		encoders_count++;
 
 	if ((out_resp->count_encoders >= encoders_count) && encoders_count) {
 		copied = 0;
 		encoder_ptr = (uint32_t __user *)(unsigned long)(out_resp->encoders_ptr);
-		for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-			if (connector->encoder_ids[i] != 0) {
-				if (put_user(connector->encoder_ids[i],
-					     encoder_ptr + copied)) {
-					ret = -EFAULT;
-					goto out;
-				}
-				copied++;
+
+		drm_connector_for_each_possible_encoder(connector, encoder, i) {
+			if (put_user(encoder->base.id, encoder_ptr + copied)) {
+				ret = -EFAULT;
+				goto out;
 			}
+			copied++;
 		}
 	}
 	out_resp->count_encoders = encoders_count;
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 98a36e6c69ad..bae43938c8f6 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -225,16 +225,9 @@ static const char *drm_crtc_fence_get_timeline_name(struct dma_fence *fence)
 	return crtc->timeline_name;
 }
 
-static bool drm_crtc_fence_enable_signaling(struct dma_fence *fence)
-{
-	return true;
-}
-
 static const struct dma_fence_ops drm_crtc_fence_ops = {
 	.get_driver_name = drm_crtc_fence_get_driver_name,
 	.get_timeline_name = drm_crtc_fence_get_timeline_name,
-	.enable_signaling = drm_crtc_fence_enable_signaling,
-	.wait = dma_fence_default_wait,
 };
 
 struct dma_fence *drm_crtc_create_fence(struct drm_crtc *crtc)
@@ -286,6 +279,10 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc,
 	if (WARN_ON(config->num_crtc >= 32))
 		return -EINVAL;
 
+	WARN_ON(drm_drv_uses_atomic_modeset(dev) &&
+		(!funcs->atomic_destroy_state ||
+		 !funcs->atomic_duplicate_state));
+
 	crtc->dev = dev;
 	crtc->funcs = funcs;
 
@@ -325,9 +322,9 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc,
 	crtc->primary = primary;
 	crtc->cursor = cursor;
 	if (primary && !primary->possible_crtcs)
-		primary->possible_crtcs = 1 << drm_crtc_index(crtc);
+		primary->possible_crtcs = drm_crtc_mask(crtc);
 	if (cursor && !cursor->possible_crtcs)
-		cursor->possible_crtcs = 1 << drm_crtc_index(crtc);
+		cursor->possible_crtcs = drm_crtc_mask(crtc);
 
 	ret = drm_crtc_crc_init(crtc);
 	if (ret) {
@@ -464,32 +461,42 @@ static int __drm_mode_set_config_internal(struct drm_mode_set *set,
 	struct drm_crtc *tmp;
 	int ret;
 
+	WARN_ON(drm_drv_uses_atomic_modeset(crtc->dev));
+
 	/*
 	 * NOTE: ->set_config can also disable other crtcs (if we steal all
 	 * connectors from it), hence we need to refcount the fbs across all
 	 * crtcs. Atomic modeset will have saner semantics ...
 	 */
-	drm_for_each_crtc(tmp, crtc->dev)
-		tmp->primary->old_fb = tmp->primary->fb;
+	drm_for_each_crtc(tmp, crtc->dev) {
+		struct drm_plane *plane = tmp->primary;
+
+		plane->old_fb = plane->fb;
+	}
 
 	fb = set->fb;
 
 	ret = crtc->funcs->set_config(set, ctx);
 	if (ret == 0) {
-		crtc->primary->crtc = fb ? crtc : NULL;
-		crtc->primary->fb = fb;
+		struct drm_plane *plane = crtc->primary;
+
+		plane->crtc = fb ? crtc : NULL;
+		plane->fb = fb;
 	}
 
 	drm_for_each_crtc(tmp, crtc->dev) {
-		if (tmp->primary->fb)
-			drm_framebuffer_get(tmp->primary->fb);
-		if (tmp->primary->old_fb)
-			drm_framebuffer_put(tmp->primary->old_fb);
-		tmp->primary->old_fb = NULL;
+		struct drm_plane *plane = tmp->primary;
+
+		if (plane->fb)
+			drm_framebuffer_get(plane->fb);
+		if (plane->old_fb)
+			drm_framebuffer_put(plane->old_fb);
+		plane->old_fb = NULL;
 	}
 
 	return ret;
 }
+
 /**
  * drm_mode_set_config_internal - helper to call &drm_mode_config_funcs.set_config
  * @set: modeset config to set
@@ -640,7 +647,9 @@ retry:
 
 		ret = drm_mode_convert_umode(dev, mode, &crtc_req->mode);
 		if (ret) {
-			DRM_DEBUG_KMS("Invalid mode\n");
+			DRM_DEBUG_KMS("Invalid mode (ret=%d, status=%s)\n",
+				      ret, drm_get_mode_status_name(mode->status));
+			drm_mode_debug_printmodeline(mode);
 			goto out;
 		}
 
@@ -732,7 +741,11 @@ retry:
 	set.connectors = connector_set;
 	set.num_connectors = crtc_req->count_connectors;
 	set.fb = fb;
-	ret = __drm_mode_set_config_internal(&set, &ctx);
+
+	if (drm_drv_uses_atomic_modeset(dev))
+		ret = crtc->funcs->set_config(&set, &ctx);
+	else
+		ret = __drm_mode_set_config_internal(&set, &ctx);
 
 out:
 	if (fb)
diff --git a/drivers/gpu/drm/drm_crtc_internal.h b/drivers/gpu/drm/drm_crtc_internal.h
index 5d307b23a4e6..b61322763394 100644
--- a/drivers/gpu/drm/drm_crtc_internal.h
+++ b/drivers/gpu/drm/drm_crtc_internal.h
@@ -56,12 +56,21 @@ int drm_mode_setcrtc(struct drm_device *dev,
 int drm_modeset_register_all(struct drm_device *dev);
 void drm_modeset_unregister_all(struct drm_device *dev);
 
+/* drm_modes.c */
+const char *drm_get_mode_status_name(enum drm_mode_status status);
+
 /* IOCTLs */
 int drm_mode_getresources(struct drm_device *dev,
 			  void *data, struct drm_file *file_priv);
 
 
 /* drm_dumb_buffers.c */
+int drm_mode_create_dumb(struct drm_device *dev,
+			 struct drm_mode_create_dumb *args,
+			 struct drm_file *file_priv);
+int drm_mode_destroy_dumb(struct drm_device *dev, u32 handle,
+			  struct drm_file *file_priv);
+
 /* IOCTLs */
 int drm_mode_create_dumb_ioctl(struct drm_device *dev,
 			       void *data, struct drm_file *file_priv);
@@ -139,7 +148,7 @@ void drm_connector_ida_init(void);
 void drm_connector_ida_destroy(void);
 void drm_connector_unregister_all(struct drm_device *dev);
 int drm_connector_register_all(struct drm_device *dev);
-int drm_mode_connector_set_obj_prop(struct drm_mode_object *obj,
+int drm_connector_set_obj_prop(struct drm_mode_object *obj,
 				    struct drm_property *property,
 				    uint64_t value);
 int drm_connector_create_standard_properties(struct drm_device *dev);
@@ -147,8 +156,8 @@ const char *drm_get_connector_force_name(enum drm_connector_force force);
 void drm_connector_free_work_fn(struct work_struct *work);
 
 /* IOCTL */
-int drm_mode_connector_property_set_ioctl(struct drm_device *dev,
-					  void *data, struct drm_file *file_priv);
+int drm_connector_property_set_ioctl(struct drm_device *dev,
+				     void *data, struct drm_file *file_priv);
 int drm_mode_getconnector(struct drm_device *dev,
 			  void *data, struct drm_file *file_priv);
 
@@ -163,14 +172,19 @@ int drm_framebuffer_check_src_coords(uint32_t src_x, uint32_t src_y,
 				     const struct drm_framebuffer *fb);
 void drm_fb_release(struct drm_file *file_priv);
 
+int drm_mode_addfb(struct drm_device *dev, struct drm_mode_fb_cmd *or,
+		   struct drm_file *file_priv);
+int drm_mode_rmfb(struct drm_device *dev, u32 fb_id,
+		  struct drm_file *file_priv);
+
 
 /* IOCTL */
-int drm_mode_addfb(struct drm_device *dev,
-		   void *data, struct drm_file *file_priv);
+int drm_mode_addfb_ioctl(struct drm_device *dev,
+			 void *data, struct drm_file *file_priv);
 int drm_mode_addfb2(struct drm_device *dev,
 		    void *data, struct drm_file *file_priv);
-int drm_mode_rmfb(struct drm_device *dev,
-		  void *data, struct drm_file *file_priv);
+int drm_mode_rmfb_ioctl(struct drm_device *dev,
+			void *data, struct drm_file *file_priv);
 int drm_mode_getfb(struct drm_device *dev,
 		   void *data, struct drm_file *file_priv);
 int drm_mode_dirtyfb_ioctl(struct drm_device *dev,
diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c
index b2482818fee8..6f28fe58f169 100644
--- a/drivers/gpu/drm/drm_debugfs.c
+++ b/drivers/gpu/drm/drm_debugfs.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/export.h>
 
+#include <drm/drm_client.h>
 #include <drm/drm_debugfs.h>
 #include <drm/drm_edid.h>
 #include <drm/drm_atomic.h>
@@ -164,6 +165,12 @@ int drm_debugfs_init(struct drm_minor *minor, int minor_id,
 			DRM_ERROR("Failed to create framebuffer debugfs file\n");
 			return ret;
 		}
+
+		ret = drm_client_debugfs_init(minor);
+		if (ret) {
+			DRM_ERROR("Failed to create client debugfs file\n");
+			return ret;
+		}
 	}
 
 	if (dev->driver->debugfs_init) {
@@ -307,13 +314,13 @@ static ssize_t edid_write(struct file *file, const char __user *ubuf,
 
 	if (len == 5 && !strncmp(buf, "reset", 5)) {
 		connector->override_edid = false;
-		ret = drm_mode_connector_update_edid_property(connector, NULL);
+		ret = drm_connector_update_edid_property(connector, NULL);
 	} else if (len < EDID_LENGTH ||
 		   EDID_LENGTH * (1 + edid->extensions) > len)
 		ret = -EINVAL;
 	else {
 		connector->override_edid = false;
-		ret = drm_mode_connector_update_edid_property(connector, edid);
+		ret = drm_connector_update_edid_property(connector, edid);
 		if (!ret)
 			connector->override_edid = true;
 	}
diff --git a/drivers/gpu/drm/drm_debugfs_crc.c b/drivers/gpu/drm/drm_debugfs_crc.c
index 9f8312137cad..99961192bf03 100644
--- a/drivers/gpu/drm/drm_debugfs_crc.c
+++ b/drivers/gpu/drm/drm_debugfs_crc.c
@@ -139,6 +139,7 @@ static int crtc_crc_data_count(struct drm_crtc_crc *crc)
 static void crtc_crc_cleanup(struct drm_crtc_crc *crc)
 {
 	kfree(crc->entries);
+	crc->overflow = false;
 	crc->entries = NULL;
 	crc->head = 0;
 	crc->tail = 0;
@@ -391,8 +392,14 @@ int drm_crtc_add_crc_entry(struct drm_crtc *crtc, bool has_frame,
 	tail = crc->tail;
 
 	if (CIRC_SPACE(head, tail, DRM_CRC_ENTRIES_NR) < 1) {
+		bool was_overflow = crc->overflow;
+
+		crc->overflow = true;
 		spin_unlock(&crc->lock);
-		DRM_ERROR("Overflow of CRC buffer, userspace reads too slow.\n");
+
+		if (!was_overflow)
+			DRM_ERROR("Overflow of CRC buffer, userspace reads too slow.\n");
+
 		return -ENOBUFS;
 	}
 
diff --git a/drivers/gpu/drm/drm_dp_cec.c b/drivers/gpu/drm/drm_dp_cec.c
new file mode 100644
index 000000000000..988513346e9c
--- /dev/null
+++ b/drivers/gpu/drm/drm_dp_cec.c
@@ -0,0 +1,428 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DisplayPort CEC-Tunneling-over-AUX support
+ *
+ * Copyright 2018 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <drm/drm_dp_helper.h>
+#include <media/cec.h>
+
+/*
+ * Unfortunately it turns out that we have a chicken-and-egg situation
+ * here. Quite a few active (mini-)DP-to-HDMI or USB-C-to-HDMI adapters
+ * have a converter chip that supports CEC-Tunneling-over-AUX (usually the
+ * Parade PS176), but they do not wire up the CEC pin, thus making CEC
+ * useless.
+ *
+ * Sadly there is no way for this driver to know this. What happens is
+ * that a /dev/cecX device is created that is isolated and unable to see
+ * any of the other CEC devices. Quite literally the CEC wire is cut
+ * (or in this case, never connected in the first place).
+ *
+ * The reason so few adapters support this is that this tunneling protocol
+ * was never supported by any OS. So there was no easy way of testing it,
+ * and no incentive to correctly wire up the CEC pin.
+ *
+ * Hopefully by creating this driver it will be easier for vendors to
+ * finally fix their adapters and test the CEC functionality.
+ *
+ * I keep a list of known working adapters here:
+ *
+ * https://hverkuil.home.xs4all.nl/cec-status.txt
+ *
+ * Please mail me (hverkuil@xs4all.nl) if you find an adapter that works
+ * and is not yet listed there.
+ *
+ * Note that the current implementation does not support CEC over an MST hub.
+ * As far as I can see there is no mechanism defined in the DisplayPort
+ * standard to transport CEC interrupts over an MST device. It might be
+ * possible to do this through polling, but I have not been able to get that
+ * to work.
+ */
+
+/**
+ * DOC: dp cec helpers
+ *
+ * These functions take care of supporting the CEC-Tunneling-over-AUX
+ * feature of DisplayPort-to-HDMI adapters.
+ */
+
+/*
+ * When the EDID is unset because the HPD went low, then the CEC DPCD registers
+ * typically can no longer be read (true for a DP-to-HDMI adapter since it is
+ * powered by the HPD). However, some displays toggle the HPD off and on for a
+ * short period for one reason or another, and that would cause the CEC adapter
+ * to be removed and added again, even though nothing else changed.
+ *
+ * This module parameter sets a delay in seconds before the CEC adapter is
+ * actually unregistered. Only if the HPD does not return within that time will
+ * the CEC adapter be unregistered.
+ *
+ * If it is set to a value >= NEVER_UNREG_DELAY, then the CEC adapter will never
+ * be unregistered for as long as the connector remains registered.
+ *
+ * If it is set to 0, then the CEC adapter will be unregistered immediately as
+ * soon as the HPD disappears.
+ *
+ * The default is one second to prevent short HPD glitches from unregistering
+ * the CEC adapter.
+ *
+ * Note that for integrated HDMI branch devices that support CEC the DPCD
+ * registers remain available even if the HPD goes low since it is not powered
+ * by the HPD. In that case the CEC adapter will never be unregistered during
+ * the life time of the connector. At least, this is the theory since I do not
+ * have hardware with an integrated HDMI branch device that supports CEC.
+ */
+#define NEVER_UNREG_DELAY 1000
+static unsigned int drm_dp_cec_unregister_delay = 1;
+module_param(drm_dp_cec_unregister_delay, uint, 0600);
+MODULE_PARM_DESC(drm_dp_cec_unregister_delay,
+		 "CEC unregister delay in seconds, 0: no delay, >= 1000: never unregister");
+
+static int drm_dp_cec_adap_enable(struct cec_adapter *adap, bool enable)
+{
+	struct drm_dp_aux *aux = cec_get_drvdata(adap);
+	u32 val = enable ? DP_CEC_TUNNELING_ENABLE : 0;
+	ssize_t err = 0;
+
+	err = drm_dp_dpcd_writeb(aux, DP_CEC_TUNNELING_CONTROL, val);
+	return (enable && err < 0) ? err : 0;
+}
+
+static int drm_dp_cec_adap_log_addr(struct cec_adapter *adap, u8 addr)
+{
+	struct drm_dp_aux *aux = cec_get_drvdata(adap);
+	/* Bit 15 (logical address 15) should always be set */
+	u16 la_mask = 1 << CEC_LOG_ADDR_BROADCAST;
+	u8 mask[2];
+	ssize_t err;
+
+	if (addr != CEC_LOG_ADDR_INVALID)
+		la_mask |= adap->log_addrs.log_addr_mask | (1 << addr);
+	mask[0] = la_mask & 0xff;
+	mask[1] = la_mask >> 8;
+	err = drm_dp_dpcd_write(aux, DP_CEC_LOGICAL_ADDRESS_MASK, mask, 2);
+	return (addr != CEC_LOG_ADDR_INVALID && err < 0) ? err : 0;
+}
+
+static int drm_dp_cec_adap_transmit(struct cec_adapter *adap, u8 attempts,
+				    u32 signal_free_time, struct cec_msg *msg)
+{
+	struct drm_dp_aux *aux = cec_get_drvdata(adap);
+	unsigned int retries = min(5, attempts - 1);
+	ssize_t err;
+
+	err = drm_dp_dpcd_write(aux, DP_CEC_TX_MESSAGE_BUFFER,
+				msg->msg, msg->len);
+	if (err < 0)
+		return err;
+
+	err = drm_dp_dpcd_writeb(aux, DP_CEC_TX_MESSAGE_INFO,
+				 (msg->len - 1) | (retries << 4) |
+				 DP_CEC_TX_MESSAGE_SEND);
+	return err < 0 ? err : 0;
+}
+
+static int drm_dp_cec_adap_monitor_all_enable(struct cec_adapter *adap,
+					      bool enable)
+{
+	struct drm_dp_aux *aux = cec_get_drvdata(adap);
+	ssize_t err;
+	u8 val;
+
+	if (!(adap->capabilities & CEC_CAP_MONITOR_ALL))
+		return 0;
+
+	err = drm_dp_dpcd_readb(aux, DP_CEC_TUNNELING_CONTROL, &val);
+	if (err >= 0) {
+		if (enable)
+			val |= DP_CEC_SNOOPING_ENABLE;
+		else
+			val &= ~DP_CEC_SNOOPING_ENABLE;
+		err = drm_dp_dpcd_writeb(aux, DP_CEC_TUNNELING_CONTROL, val);
+	}
+	return (enable && err < 0) ? err : 0;
+}
+
+static void drm_dp_cec_adap_status(struct cec_adapter *adap,
+				   struct seq_file *file)
+{
+	struct drm_dp_aux *aux = cec_get_drvdata(adap);
+	struct drm_dp_desc desc;
+	struct drm_dp_dpcd_ident *id = &desc.ident;
+
+	if (drm_dp_read_desc(aux, &desc, true))
+		return;
+	seq_printf(file, "OUI: %*phD\n",
+		   (int)sizeof(id->oui), id->oui);
+	seq_printf(file, "ID: %*pE\n",
+		   (int)strnlen(id->device_id, sizeof(id->device_id)),
+		   id->device_id);
+	seq_printf(file, "HW Rev: %d.%d\n", id->hw_rev >> 4, id->hw_rev & 0xf);
+	/*
+	 * Show this both in decimal and hex: at least one vendor
+	 * always reports this in hex.
+	 */
+	seq_printf(file, "FW/SW Rev: %d.%d (0x%02x.0x%02x)\n",
+		   id->sw_major_rev, id->sw_minor_rev,
+		   id->sw_major_rev, id->sw_minor_rev);
+}
+
+static const struct cec_adap_ops drm_dp_cec_adap_ops = {
+	.adap_enable = drm_dp_cec_adap_enable,
+	.adap_log_addr = drm_dp_cec_adap_log_addr,
+	.adap_transmit = drm_dp_cec_adap_transmit,
+	.adap_monitor_all_enable = drm_dp_cec_adap_monitor_all_enable,
+	.adap_status = drm_dp_cec_adap_status,
+};
+
+static int drm_dp_cec_received(struct drm_dp_aux *aux)
+{
+	struct cec_adapter *adap = aux->cec.adap;
+	struct cec_msg msg;
+	u8 rx_msg_info;
+	ssize_t err;
+
+	err = drm_dp_dpcd_readb(aux, DP_CEC_RX_MESSAGE_INFO, &rx_msg_info);
+	if (err < 0)
+		return err;
+
+	if (!(rx_msg_info & DP_CEC_RX_MESSAGE_ENDED))
+		return 0;
+
+	msg.len = (rx_msg_info & DP_CEC_RX_MESSAGE_LEN_MASK) + 1;
+	err = drm_dp_dpcd_read(aux, DP_CEC_RX_MESSAGE_BUFFER, msg.msg, msg.len);
+	if (err < 0)
+		return err;
+
+	cec_received_msg(adap, &msg);
+	return 0;
+}
+
+static void drm_dp_cec_handle_irq(struct drm_dp_aux *aux)
+{
+	struct cec_adapter *adap = aux->cec.adap;
+	u8 flags;
+
+	if (drm_dp_dpcd_readb(aux, DP_CEC_TUNNELING_IRQ_FLAGS, &flags) < 0)
+		return;
+
+	if (flags & DP_CEC_RX_MESSAGE_INFO_VALID)
+		drm_dp_cec_received(aux);
+
+	if (flags & DP_CEC_TX_MESSAGE_SENT)
+		cec_transmit_attempt_done(adap, CEC_TX_STATUS_OK);
+	else if (flags & DP_CEC_TX_LINE_ERROR)
+		cec_transmit_attempt_done(adap, CEC_TX_STATUS_ERROR |
+						CEC_TX_STATUS_MAX_RETRIES);
+	else if (flags &
+		 (DP_CEC_TX_ADDRESS_NACK_ERROR | DP_CEC_TX_DATA_NACK_ERROR))
+		cec_transmit_attempt_done(adap, CEC_TX_STATUS_NACK |
+						CEC_TX_STATUS_MAX_RETRIES);
+	drm_dp_dpcd_writeb(aux, DP_CEC_TUNNELING_IRQ_FLAGS, flags);
+}
+
+/**
+ * drm_dp_cec_irq() - handle CEC interrupt, if any
+ * @aux: DisplayPort AUX channel
+ *
+ * Should be called when handling an IRQ_HPD request. If CEC-tunneling-over-AUX
+ * is present, then it will check for a CEC_IRQ and handle it accordingly.
+ */
+void drm_dp_cec_irq(struct drm_dp_aux *aux)
+{
+	u8 cec_irq;
+	int ret;
+
+	mutex_lock(&aux->cec.lock);
+	if (!aux->cec.adap)
+		goto unlock;
+
+	ret = drm_dp_dpcd_readb(aux, DP_DEVICE_SERVICE_IRQ_VECTOR_ESI1,
+				&cec_irq);
+	if (ret < 0 || !(cec_irq & DP_CEC_IRQ))
+		goto unlock;
+
+	drm_dp_cec_handle_irq(aux);
+	drm_dp_dpcd_writeb(aux, DP_DEVICE_SERVICE_IRQ_VECTOR_ESI1, DP_CEC_IRQ);
+unlock:
+	mutex_unlock(&aux->cec.lock);
+}
+EXPORT_SYMBOL(drm_dp_cec_irq);
+
+static bool drm_dp_cec_cap(struct drm_dp_aux *aux, u8 *cec_cap)
+{
+	u8 cap = 0;
+
+	if (drm_dp_dpcd_readb(aux, DP_CEC_TUNNELING_CAPABILITY, &cap) != 1 ||
+	    !(cap & DP_CEC_TUNNELING_CAPABLE))
+		return false;
+	if (cec_cap)
+		*cec_cap = cap;
+	return true;
+}
+
+/*
+ * Called if the HPD was low for more than drm_dp_cec_unregister_delay
+ * seconds. This unregisters the CEC adapter.
+ */
+static void drm_dp_cec_unregister_work(struct work_struct *work)
+{
+	struct drm_dp_aux *aux = container_of(work, struct drm_dp_aux,
+					      cec.unregister_work.work);
+
+	mutex_lock(&aux->cec.lock);
+	cec_unregister_adapter(aux->cec.adap);
+	aux->cec.adap = NULL;
+	mutex_unlock(&aux->cec.lock);
+}
+
+/*
+ * A new EDID is set. If there is no CEC adapter, then create one. If
+ * there was a CEC adapter, then check if the CEC adapter properties
+ * were unchanged and just update the CEC physical address. Otherwise
+ * unregister the old CEC adapter and create a new one.
+ */
+void drm_dp_cec_set_edid(struct drm_dp_aux *aux, const struct edid *edid)
+{
+	u32 cec_caps = CEC_CAP_DEFAULTS | CEC_CAP_NEEDS_HPD;
+	unsigned int num_las = 1;
+	u8 cap;
+
+#ifndef CONFIG_MEDIA_CEC_RC
+	/*
+	 * CEC_CAP_RC is part of CEC_CAP_DEFAULTS, but it is stripped by
+	 * cec_allocate_adapter() if CONFIG_MEDIA_CEC_RC is undefined.
+	 *
+	 * Do this here as well to ensure the tests against cec_caps are
+	 * correct.
+	 */
+	cec_caps &= ~CEC_CAP_RC;
+#endif
+	cancel_delayed_work_sync(&aux->cec.unregister_work);
+
+	mutex_lock(&aux->cec.lock);
+	if (!drm_dp_cec_cap(aux, &cap)) {
+		/* CEC is not supported, unregister any existing adapter */
+		cec_unregister_adapter(aux->cec.adap);
+		aux->cec.adap = NULL;
+		goto unlock;
+	}
+
+	if (cap & DP_CEC_SNOOPING_CAPABLE)
+		cec_caps |= CEC_CAP_MONITOR_ALL;
+	if (cap & DP_CEC_MULTIPLE_LA_CAPABLE)
+		num_las = CEC_MAX_LOG_ADDRS;
+
+	if (aux->cec.adap) {
+		if (aux->cec.adap->capabilities == cec_caps &&
+		    aux->cec.adap->available_log_addrs == num_las) {
+			/* Unchanged, so just set the phys addr */
+			cec_s_phys_addr_from_edid(aux->cec.adap, edid);
+			goto unlock;
+		}
+		/*
+		 * The capabilities changed, so unregister the old
+		 * adapter first.
+		 */
+		cec_unregister_adapter(aux->cec.adap);
+	}
+
+	/* Create a new adapter */
+	aux->cec.adap = cec_allocate_adapter(&drm_dp_cec_adap_ops,
+					     aux, aux->cec.name, cec_caps,
+					     num_las);
+	if (IS_ERR(aux->cec.adap)) {
+		aux->cec.adap = NULL;
+		goto unlock;
+	}
+	if (cec_register_adapter(aux->cec.adap, aux->cec.parent)) {
+		cec_delete_adapter(aux->cec.adap);
+		aux->cec.adap = NULL;
+	} else {
+		/*
+		 * Update the phys addr for the new CEC adapter. When called
+		 * from drm_dp_cec_register_connector() edid == NULL, so in
+		 * that case the phys addr is just invalidated.
+		 */
+		cec_s_phys_addr_from_edid(aux->cec.adap, edid);
+	}
+unlock:
+	mutex_unlock(&aux->cec.lock);
+}
+EXPORT_SYMBOL(drm_dp_cec_set_edid);
+
+/*
+ * The EDID disappeared (likely because of the HPD going down).
+ */
+void drm_dp_cec_unset_edid(struct drm_dp_aux *aux)
+{
+	cancel_delayed_work_sync(&aux->cec.unregister_work);
+
+	mutex_lock(&aux->cec.lock);
+	if (!aux->cec.adap)
+		goto unlock;
+
+	cec_phys_addr_invalidate(aux->cec.adap);
+	/*
+	 * We're done if we want to keep the CEC device
+	 * (drm_dp_cec_unregister_delay is >= NEVER_UNREG_DELAY) or if the
+	 * DPCD still indicates the CEC capability (expected for an integrated
+	 * HDMI branch device).
+	 */
+	if (drm_dp_cec_unregister_delay < NEVER_UNREG_DELAY &&
+	    !drm_dp_cec_cap(aux, NULL)) {
+		/*
+		 * Unregister the CEC adapter after drm_dp_cec_unregister_delay
+		 * seconds. This to debounce short HPD off-and-on cycles from
+		 * displays.
+		 */
+		schedule_delayed_work(&aux->cec.unregister_work,
+				      drm_dp_cec_unregister_delay * HZ);
+	}
+unlock:
+	mutex_unlock(&aux->cec.lock);
+}
+EXPORT_SYMBOL(drm_dp_cec_unset_edid);
+
+/**
+ * drm_dp_cec_register_connector() - register a new connector
+ * @aux: DisplayPort AUX channel
+ * @name: name of the CEC device
+ * @parent: parent device
+ *
+ * A new connector was registered with associated CEC adapter name and
+ * CEC adapter parent device. After registering the name and parent
+ * drm_dp_cec_set_edid() is called to check if the connector supports
+ * CEC and to register a CEC adapter if that is the case.
+ */
+void drm_dp_cec_register_connector(struct drm_dp_aux *aux, const char *name,
+				   struct device *parent)
+{
+	WARN_ON(aux->cec.adap);
+	aux->cec.name = name;
+	aux->cec.parent = parent;
+	INIT_DELAYED_WORK(&aux->cec.unregister_work,
+			  drm_dp_cec_unregister_work);
+
+	drm_dp_cec_set_edid(aux, NULL);
+}
+EXPORT_SYMBOL(drm_dp_cec_register_connector);
+
+/**
+ * drm_dp_cec_unregister_connector() - unregister the CEC adapter, if any
+ * @aux: DisplayPort AUX channel
+ */
+void drm_dp_cec_unregister_connector(struct drm_dp_aux *aux)
+{
+	if (!aux->cec.adap)
+		return;
+	cancel_delayed_work_sync(&aux->cec.unregister_work);
+	cec_unregister_adapter(aux->cec.adap);
+	aux->cec.adap = NULL;
+}
+EXPORT_SYMBOL(drm_dp_cec_unregister_connector);
diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index a7ba602a43a8..0cccbcb2d03e 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -185,6 +185,20 @@ EXPORT_SYMBOL(drm_dp_bw_code_to_link_rate);
 
 #define AUX_RETRY_INTERVAL 500 /* us */
 
+static inline void
+drm_dp_dump_access(const struct drm_dp_aux *aux,
+		   u8 request, uint offset, void *buffer, int ret)
+{
+	const char *arrow = request == DP_AUX_NATIVE_READ ? "->" : "<-";
+
+	if (ret > 0)
+		drm_dbg(DRM_UT_DP, "%s: 0x%05x AUX %s (ret=%3d) %*ph\n",
+			aux->name, offset, arrow, ret, min(ret, 20), buffer);
+	else
+		drm_dbg(DRM_UT_DP, "%s: 0x%05x AUX %s (ret=%3d)\n",
+			aux->name, offset, arrow, ret);
+}
+
 /**
  * DOC: dp helpers
  *
@@ -288,10 +302,14 @@ ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset,
 	ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, DP_DPCD_REV, buffer,
 				 1);
 	if (ret != 1)
-		return ret;
+		goto out;
 
-	return drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, offset, buffer,
-				  size);
+	ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, offset, buffer,
+				 size);
+
+out:
+	drm_dp_dump_access(aux, DP_AUX_NATIVE_READ, offset, buffer, ret);
+	return ret;
 }
 EXPORT_SYMBOL(drm_dp_dpcd_read);
 
@@ -312,8 +330,12 @@ EXPORT_SYMBOL(drm_dp_dpcd_read);
 ssize_t drm_dp_dpcd_write(struct drm_dp_aux *aux, unsigned int offset,
 			  void *buffer, size_t size)
 {
-	return drm_dp_dpcd_access(aux, DP_AUX_NATIVE_WRITE, offset, buffer,
-				  size);
+	int ret;
+
+	ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_WRITE, offset, buffer,
+				 size);
+	drm_dp_dump_access(aux, DP_AUX_NATIVE_WRITE, offset, buffer, ret);
+	return ret;
 }
 EXPORT_SYMBOL(drm_dp_dpcd_write);
 
@@ -1087,6 +1109,7 @@ static void drm_dp_aux_crc_work(struct work_struct *work)
 void drm_dp_aux_init(struct drm_dp_aux *aux)
 {
 	mutex_init(&aux->hw_mutex);
+	mutex_init(&aux->cec.lock);
 	INIT_WORK(&aux->crc_work, drm_dp_aux_crc_work);
 
 	aux->ddc.algo = &drm_dp_i2c_algo;
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 658830620ca3..7780567aa669 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -1215,7 +1215,7 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb,
 		     port->pdt == DP_PEER_DEVICE_SST_SINK) &&
 		    port->port_num >= DP_MST_LOGICAL_PORT_0) {
 			port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc);
-			drm_mode_connector_set_tile_property(port->connector);
+			drm_connector_set_tile_property(port->connector);
 		}
 		(*mstb->mgr->cbs->register_connector)(port->connector);
 	}
@@ -2559,7 +2559,7 @@ struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_
 		edid = drm_edid_duplicate(port->cached_edid);
 	else {
 		edid = drm_get_edid(connector, &port->aux.ddc);
-		drm_mode_connector_set_tile_property(connector);
+		drm_connector_set_tile_property(connector);
 	}
 	port->has_audio = drm_detect_monitor_audio(edid);
 	drm_dp_put_port(port);
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 7af748ed1c58..ea4941da9b27 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -34,6 +34,7 @@
 #include <linux/slab.h>
 #include <linux/srcu.h>
 
+#include <drm/drm_client.h>
 #include <drm/drm_drv.h>
 #include <drm/drmP.h>
 
@@ -53,13 +54,14 @@ MODULE_AUTHOR("Gareth Hughes, Leif Delgass, José Fonseca, Jon Smirl");
 MODULE_DESCRIPTION("DRM shared core routines");
 MODULE_LICENSE("GPL and additional rights");
 MODULE_PARM_DESC(debug, "Enable debug output, where each bit enables a debug category.\n"
-"\t\tBit 0 (0x01) will enable CORE messages (drm core code)\n"
-"\t\tBit 1 (0x02) will enable DRIVER messages (drm controller code)\n"
-"\t\tBit 2 (0x04) will enable KMS messages (modesetting code)\n"
-"\t\tBit 3 (0x08) will enable PRIME messages (prime code)\n"
-"\t\tBit 4 (0x10) will enable ATOMIC messages (atomic code)\n"
-"\t\tBit 5 (0x20) will enable VBL messages (vblank code)\n"
-"\t\tBit 7 (0x80) will enable LEASE messages (leasing code)");
+"\t\tBit 0 (0x01)  will enable CORE messages (drm core code)\n"
+"\t\tBit 1 (0x02)  will enable DRIVER messages (drm controller code)\n"
+"\t\tBit 2 (0x04)  will enable KMS messages (modesetting code)\n"
+"\t\tBit 3 (0x08)  will enable PRIME messages (prime code)\n"
+"\t\tBit 4 (0x10)  will enable ATOMIC messages (atomic code)\n"
+"\t\tBit 5 (0x20)  will enable VBL messages (vblank code)\n"
+"\t\tBit 7 (0x80)  will enable LEASE messages (leasing code)\n"
+"\t\tBit 8 (0x100) will enable DP messages (displayport code)");
 module_param_named(debug, drm_debug, int, 0600);
 
 static DEFINE_SPINLOCK(drm_minor_lock);
@@ -505,6 +507,8 @@ int drm_dev_init(struct drm_device *dev,
 	dev->driver = driver;
 
 	INIT_LIST_HEAD(&dev->filelist);
+	INIT_LIST_HEAD(&dev->filelist_internal);
+	INIT_LIST_HEAD(&dev->clientlist);
 	INIT_LIST_HEAD(&dev->ctxlist);
 	INIT_LIST_HEAD(&dev->vmalist);
 	INIT_LIST_HEAD(&dev->maplist);
@@ -514,6 +518,7 @@ int drm_dev_init(struct drm_device *dev,
 	spin_lock_init(&dev->event_lock);
 	mutex_init(&dev->struct_mutex);
 	mutex_init(&dev->filelist_mutex);
+	mutex_init(&dev->clientlist_mutex);
 	mutex_init(&dev->ctxlist_mutex);
 	mutex_init(&dev->master_mutex);
 
@@ -569,6 +574,7 @@ err_minors:
 err_free:
 	mutex_destroy(&dev->master_mutex);
 	mutex_destroy(&dev->ctxlist_mutex);
+	mutex_destroy(&dev->clientlist_mutex);
 	mutex_destroy(&dev->filelist_mutex);
 	mutex_destroy(&dev->struct_mutex);
 	return ret;
@@ -603,6 +609,7 @@ void drm_dev_fini(struct drm_device *dev)
 
 	mutex_destroy(&dev->master_mutex);
 	mutex_destroy(&dev->ctxlist_mutex);
+	mutex_destroy(&dev->clientlist_mutex);
 	mutex_destroy(&dev->filelist_mutex);
 	mutex_destroy(&dev->struct_mutex);
 	kfree(dev->unique);
@@ -858,6 +865,8 @@ void drm_dev_unregister(struct drm_device *dev)
 
 	dev->registered = false;
 
+	drm_client_dev_unregister(dev);
+
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		drm_modeset_unregister_all(dev);
 
diff --git a/drivers/gpu/drm/drm_dumb_buffers.c b/drivers/gpu/drm/drm_dumb_buffers.c
index 9e2ae02f31e0..81dfdd33753a 100644
--- a/drivers/gpu/drm/drm_dumb_buffers.c
+++ b/drivers/gpu/drm/drm_dumb_buffers.c
@@ -53,10 +53,10 @@
  * a hardware-specific ioctl to allocate suitable buffer objects.
  */
 
-int drm_mode_create_dumb_ioctl(struct drm_device *dev,
-			       void *data, struct drm_file *file_priv)
+int drm_mode_create_dumb(struct drm_device *dev,
+			 struct drm_mode_create_dumb *args,
+			 struct drm_file *file_priv)
 {
-	struct drm_mode_create_dumb *args = data;
 	u32 cpp, stride, size;
 
 	if (!dev->driver->dumb_create)
@@ -92,6 +92,12 @@ int drm_mode_create_dumb_ioctl(struct drm_device *dev,
 	return dev->driver->dumb_create(file_priv, dev, args);
 }
 
+int drm_mode_create_dumb_ioctl(struct drm_device *dev,
+			       void *data, struct drm_file *file_priv)
+{
+	return drm_mode_create_dumb(dev, data, file_priv);
+}
+
 /**
  * drm_mode_mmap_dumb_ioctl - create an mmap offset for a dumb backing storage buffer
  * @dev: DRM device
@@ -123,17 +129,22 @@ int drm_mode_mmap_dumb_ioctl(struct drm_device *dev,
 					       &args->offset);
 }
 
-int drm_mode_destroy_dumb_ioctl(struct drm_device *dev,
-				void *data, struct drm_file *file_priv)
+int drm_mode_destroy_dumb(struct drm_device *dev, u32 handle,
+			  struct drm_file *file_priv)
 {
-	struct drm_mode_destroy_dumb *args = data;
-
 	if (!dev->driver->dumb_create)
 		return -ENOSYS;
 
 	if (dev->driver->dumb_destroy)
-		return dev->driver->dumb_destroy(file_priv, dev, args->handle);
+		return dev->driver->dumb_destroy(file_priv, dev, handle);
 	else
-		return drm_gem_dumb_destroy(file_priv, dev, args->handle);
+		return drm_gem_dumb_destroy(file_priv, dev, handle);
 }
 
+int drm_mode_destroy_dumb_ioctl(struct drm_device *dev,
+				void *data, struct drm_file *file_priv)
+{
+	struct drm_mode_destroy_dumb *args = data;
+
+	return drm_mode_destroy_dumb(dev, args->handle, file_priv);
+}
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index a5808382bdf0..5dc742b27ca0 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -163,8 +163,9 @@ static const struct edid_quirk {
 	/* Rotel RSX-1058 forwards sink's EDID but only does HDMI 1.1*/
 	{ "ETR", 13896, EDID_QUIRK_FORCE_8BPC },
 
-	/* HTC Vive VR Headset */
+	/* HTC Vive and Vive Pro VR Headsets */
 	{ "HVR", 0xaa01, EDID_QUIRK_NON_DESKTOP },
+	{ "HVR", 0xaa02, EDID_QUIRK_NON_DESKTOP },
 
 	/* Oculus Rift DK1, DK2, and CV1 VR Headsets */
 	{ "OVR", 0x0001, EDID_QUIRK_NON_DESKTOP },
@@ -687,562 +688,562 @@ static const struct minimode extra_modes[] = {
 static const struct drm_display_mode edid_cea_modes[] = {
 	/* 0 - dummy, VICs start at 1 */
 	{ },
-	/* 1 - 640x480@60Hz */
+	/* 1 - 640x480@60Hz 4:3 */
 	{ DRM_MODE("640x480", DRM_MODE_TYPE_DRIVER, 25175, 640, 656,
 		   752, 800, 0, 480, 490, 492, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 2 - 720x480@60Hz */
+	/* 2 - 720x480@60Hz 4:3 */
 	{ DRM_MODE("720x480", DRM_MODE_TYPE_DRIVER, 27000, 720, 736,
 		   798, 858, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 3 - 720x480@60Hz */
+	/* 3 - 720x480@60Hz 16:9 */
 	{ DRM_MODE("720x480", DRM_MODE_TYPE_DRIVER, 27000, 720, 736,
 		   798, 858, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 4 - 1280x720@60Hz */
+	/* 4 - 1280x720@60Hz 16:9 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 74250, 1280, 1390,
 		   1430, 1650, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 5 - 1920x1080i@60Hz */
+	/* 5 - 1920x1080i@60Hz 16:9 */
 	{ DRM_MODE("1920x1080i", DRM_MODE_TYPE_DRIVER, 74250, 1920, 2008,
 		   2052, 2200, 0, 1080, 1084, 1094, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC |
-			DRM_MODE_FLAG_INTERLACE),
+		   DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 6 - 720(1440)x480i@60Hz */
+	/* 6 - 720(1440)x480i@60Hz 4:3 */
 	{ DRM_MODE("720x480i", DRM_MODE_TYPE_DRIVER, 13500, 720, 739,
 		   801, 858, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 7 - 720(1440)x480i@60Hz */
+	/* 7 - 720(1440)x480i@60Hz 16:9 */
 	{ DRM_MODE("720x480i", DRM_MODE_TYPE_DRIVER, 13500, 720, 739,
 		   801, 858, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 8 - 720(1440)x240@60Hz */
+	/* 8 - 720(1440)x240@60Hz 4:3 */
 	{ DRM_MODE("720x240", DRM_MODE_TYPE_DRIVER, 13500, 720, 739,
 		   801, 858, 0, 240, 244, 247, 262, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 9 - 720(1440)x240@60Hz */
+	/* 9 - 720(1440)x240@60Hz 16:9 */
 	{ DRM_MODE("720x240", DRM_MODE_TYPE_DRIVER, 13500, 720, 739,
 		   801, 858, 0, 240, 244, 247, 262, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 10 - 2880x480i@60Hz */
+	/* 10 - 2880x480i@60Hz 4:3 */
 	{ DRM_MODE("2880x480i", DRM_MODE_TYPE_DRIVER, 54000, 2880, 2956,
 		   3204, 3432, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE),
+		   DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 11 - 2880x480i@60Hz */
+	/* 11 - 2880x480i@60Hz 16:9 */
 	{ DRM_MODE("2880x480i", DRM_MODE_TYPE_DRIVER, 54000, 2880, 2956,
 		   3204, 3432, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE),
+		   DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 12 - 2880x240@60Hz */
+	/* 12 - 2880x240@60Hz 4:3 */
 	{ DRM_MODE("2880x240", DRM_MODE_TYPE_DRIVER, 54000, 2880, 2956,
 		   3204, 3432, 0, 240, 244, 247, 262, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 13 - 2880x240@60Hz */
+	/* 13 - 2880x240@60Hz 16:9 */
 	{ DRM_MODE("2880x240", DRM_MODE_TYPE_DRIVER, 54000, 2880, 2956,
 		   3204, 3432, 0, 240, 244, 247, 262, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 14 - 1440x480@60Hz */
+	/* 14 - 1440x480@60Hz 4:3 */
 	{ DRM_MODE("1440x480", DRM_MODE_TYPE_DRIVER, 54000, 1440, 1472,
 		   1596, 1716, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 15 - 1440x480@60Hz */
+	/* 15 - 1440x480@60Hz 16:9 */
 	{ DRM_MODE("1440x480", DRM_MODE_TYPE_DRIVER, 54000, 1440, 1472,
 		   1596, 1716, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 16 - 1920x1080@60Hz */
+	/* 16 - 1920x1080@60Hz 16:9 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 148500, 1920, 2008,
 		   2052, 2200, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 17 - 720x576@50Hz */
+	/* 17 - 720x576@50Hz 4:3 */
 	{ DRM_MODE("720x576", DRM_MODE_TYPE_DRIVER, 27000, 720, 732,
 		   796, 864, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 18 - 720x576@50Hz */
+	/* 18 - 720x576@50Hz 16:9 */
 	{ DRM_MODE("720x576", DRM_MODE_TYPE_DRIVER, 27000, 720, 732,
 		   796, 864, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 19 - 1280x720@50Hz */
+	/* 19 - 1280x720@50Hz 16:9 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 74250, 1280, 1720,
 		   1760, 1980, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 20 - 1920x1080i@50Hz */
+	/* 20 - 1920x1080i@50Hz 16:9 */
 	{ DRM_MODE("1920x1080i", DRM_MODE_TYPE_DRIVER, 74250, 1920, 2448,
 		   2492, 2640, 0, 1080, 1084, 1094, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC |
-			DRM_MODE_FLAG_INTERLACE),
+		   DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 21 - 720(1440)x576i@50Hz */
+	/* 21 - 720(1440)x576i@50Hz 4:3 */
 	{ DRM_MODE("720x576i", DRM_MODE_TYPE_DRIVER, 13500, 720, 732,
 		   795, 864, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 22 - 720(1440)x576i@50Hz */
+	/* 22 - 720(1440)x576i@50Hz 16:9 */
 	{ DRM_MODE("720x576i", DRM_MODE_TYPE_DRIVER, 13500, 720, 732,
 		   795, 864, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 23 - 720(1440)x288@50Hz */
+	/* 23 - 720(1440)x288@50Hz 4:3 */
 	{ DRM_MODE("720x288", DRM_MODE_TYPE_DRIVER, 13500, 720, 732,
 		   795, 864, 0, 288, 290, 293, 312, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 24 - 720(1440)x288@50Hz */
+	/* 24 - 720(1440)x288@50Hz 16:9 */
 	{ DRM_MODE("720x288", DRM_MODE_TYPE_DRIVER, 13500, 720, 732,
 		   795, 864, 0, 288, 290, 293, 312, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 25 - 2880x576i@50Hz */
+	/* 25 - 2880x576i@50Hz 4:3 */
 	{ DRM_MODE("2880x576i", DRM_MODE_TYPE_DRIVER, 54000, 2880, 2928,
 		   3180, 3456, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE),
+		   DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 26 - 2880x576i@50Hz */
+	/* 26 - 2880x576i@50Hz 16:9 */
 	{ DRM_MODE("2880x576i", DRM_MODE_TYPE_DRIVER, 54000, 2880, 2928,
 		   3180, 3456, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE),
+		   DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 27 - 2880x288@50Hz */
+	/* 27 - 2880x288@50Hz 4:3 */
 	{ DRM_MODE("2880x288", DRM_MODE_TYPE_DRIVER, 54000, 2880, 2928,
 		   3180, 3456, 0, 288, 290, 293, 312, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 28 - 2880x288@50Hz */
+	/* 28 - 2880x288@50Hz 16:9 */
 	{ DRM_MODE("2880x288", DRM_MODE_TYPE_DRIVER, 54000, 2880, 2928,
 		   3180, 3456, 0, 288, 290, 293, 312, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 29 - 1440x576@50Hz */
+	/* 29 - 1440x576@50Hz 4:3 */
 	{ DRM_MODE("1440x576", DRM_MODE_TYPE_DRIVER, 54000, 1440, 1464,
 		   1592, 1728, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 30 - 1440x576@50Hz */
+	/* 30 - 1440x576@50Hz 16:9 */
 	{ DRM_MODE("1440x576", DRM_MODE_TYPE_DRIVER, 54000, 1440, 1464,
 		   1592, 1728, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 31 - 1920x1080@50Hz */
+	/* 31 - 1920x1080@50Hz 16:9 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 148500, 1920, 2448,
 		   2492, 2640, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 32 - 1920x1080@24Hz */
+	/* 32 - 1920x1080@24Hz 16:9 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 74250, 1920, 2558,
 		   2602, 2750, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 33 - 1920x1080@25Hz */
+	/* 33 - 1920x1080@25Hz 16:9 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 74250, 1920, 2448,
 		   2492, 2640, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 34 - 1920x1080@30Hz */
+	/* 34 - 1920x1080@30Hz 16:9 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 74250, 1920, 2008,
 		   2052, 2200, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 35 - 2880x480@60Hz */
+	/* 35 - 2880x480@60Hz 4:3 */
 	{ DRM_MODE("2880x480", DRM_MODE_TYPE_DRIVER, 108000, 2880, 2944,
 		   3192, 3432, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 36 - 2880x480@60Hz */
+	/* 36 - 2880x480@60Hz 16:9 */
 	{ DRM_MODE("2880x480", DRM_MODE_TYPE_DRIVER, 108000, 2880, 2944,
 		   3192, 3432, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 37 - 2880x576@50Hz */
+	/* 37 - 2880x576@50Hz 4:3 */
 	{ DRM_MODE("2880x576", DRM_MODE_TYPE_DRIVER, 108000, 2880, 2928,
 		   3184, 3456, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 38 - 2880x576@50Hz */
+	/* 38 - 2880x576@50Hz 16:9 */
 	{ DRM_MODE("2880x576", DRM_MODE_TYPE_DRIVER, 108000, 2880, 2928,
 		   3184, 3456, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 39 - 1920x1080i@50Hz */
+	/* 39 - 1920x1080i@50Hz 16:9 */
 	{ DRM_MODE("1920x1080i", DRM_MODE_TYPE_DRIVER, 72000, 1920, 1952,
 		   2120, 2304, 0, 1080, 1126, 1136, 1250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE),
+		   DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 40 - 1920x1080i@100Hz */
+	/* 40 - 1920x1080i@100Hz 16:9 */
 	{ DRM_MODE("1920x1080i", DRM_MODE_TYPE_DRIVER, 148500, 1920, 2448,
 		   2492, 2640, 0, 1080, 1084, 1094, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC |
-			DRM_MODE_FLAG_INTERLACE),
+		   DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 41 - 1280x720@100Hz */
+	/* 41 - 1280x720@100Hz 16:9 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 148500, 1280, 1720,
 		   1760, 1980, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 42 - 720x576@100Hz */
+	/* 42 - 720x576@100Hz 4:3 */
 	{ DRM_MODE("720x576", DRM_MODE_TYPE_DRIVER, 54000, 720, 732,
 		   796, 864, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 43 - 720x576@100Hz */
+	/* 43 - 720x576@100Hz 16:9 */
 	{ DRM_MODE("720x576", DRM_MODE_TYPE_DRIVER, 54000, 720, 732,
 		   796, 864, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 44 - 720(1440)x576i@100Hz */
+	/* 44 - 720(1440)x576i@100Hz 4:3 */
 	{ DRM_MODE("720x576i", DRM_MODE_TYPE_DRIVER, 27000, 720, 732,
 		   795, 864, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 45 - 720(1440)x576i@100Hz */
+	/* 45 - 720(1440)x576i@100Hz 16:9 */
 	{ DRM_MODE("720x576i", DRM_MODE_TYPE_DRIVER, 27000, 720, 732,
 		   795, 864, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 46 - 1920x1080i@120Hz */
+	/* 46 - 1920x1080i@120Hz 16:9 */
 	{ DRM_MODE("1920x1080i", DRM_MODE_TYPE_DRIVER, 148500, 1920, 2008,
 		   2052, 2200, 0, 1080, 1084, 1094, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC |
-			DRM_MODE_FLAG_INTERLACE),
+		   DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 47 - 1280x720@120Hz */
+	/* 47 - 1280x720@120Hz 16:9 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 148500, 1280, 1390,
 		   1430, 1650, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 48 - 720x480@120Hz */
+	/* 48 - 720x480@120Hz 4:3 */
 	{ DRM_MODE("720x480", DRM_MODE_TYPE_DRIVER, 54000, 720, 736,
 		   798, 858, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 49 - 720x480@120Hz */
+	/* 49 - 720x480@120Hz 16:9 */
 	{ DRM_MODE("720x480", DRM_MODE_TYPE_DRIVER, 54000, 720, 736,
 		   798, 858, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 50 - 720(1440)x480i@120Hz */
+	/* 50 - 720(1440)x480i@120Hz 4:3 */
 	{ DRM_MODE("720x480i", DRM_MODE_TYPE_DRIVER, 27000, 720, 739,
 		   801, 858, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 51 - 720(1440)x480i@120Hz */
+	/* 51 - 720(1440)x480i@120Hz 16:9 */
 	{ DRM_MODE("720x480i", DRM_MODE_TYPE_DRIVER, 27000, 720, 739,
 		   801, 858, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 52 - 720x576@200Hz */
+	/* 52 - 720x576@200Hz 4:3 */
 	{ DRM_MODE("720x576", DRM_MODE_TYPE_DRIVER, 108000, 720, 732,
 		   796, 864, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 200, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 53 - 720x576@200Hz */
+	/* 53 - 720x576@200Hz 16:9 */
 	{ DRM_MODE("720x576", DRM_MODE_TYPE_DRIVER, 108000, 720, 732,
 		   796, 864, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 200, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 54 - 720(1440)x576i@200Hz */
+	/* 54 - 720(1440)x576i@200Hz 4:3 */
 	{ DRM_MODE("720x576i", DRM_MODE_TYPE_DRIVER, 54000, 720, 732,
 		   795, 864, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 200, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 55 - 720(1440)x576i@200Hz */
+	/* 55 - 720(1440)x576i@200Hz 16:9 */
 	{ DRM_MODE("720x576i", DRM_MODE_TYPE_DRIVER, 54000, 720, 732,
 		   795, 864, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 200, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 56 - 720x480@240Hz */
+	/* 56 - 720x480@240Hz 4:3 */
 	{ DRM_MODE("720x480", DRM_MODE_TYPE_DRIVER, 108000, 720, 736,
 		   798, 858, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 240, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 57 - 720x480@240Hz */
+	/* 57 - 720x480@240Hz 16:9 */
 	{ DRM_MODE("720x480", DRM_MODE_TYPE_DRIVER, 108000, 720, 736,
 		   798, 858, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 240, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 58 - 720(1440)x480i@240Hz */
+	/* 58 - 720(1440)x480i@240Hz 4:3 */
 	{ DRM_MODE("720x480i", DRM_MODE_TYPE_DRIVER, 54000, 720, 739,
 		   801, 858, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 240, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 59 - 720(1440)x480i@240Hz */
+	/* 59 - 720(1440)x480i@240Hz 16:9 */
 	{ DRM_MODE("720x480i", DRM_MODE_TYPE_DRIVER, 54000, 720, 739,
 		   801, 858, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 240, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 60 - 1280x720@24Hz */
+	/* 60 - 1280x720@24Hz 16:9 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 59400, 1280, 3040,
 		   3080, 3300, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 61 - 1280x720@25Hz */
+	/* 61 - 1280x720@25Hz 16:9 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 74250, 1280, 3700,
 		   3740, 3960, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 62 - 1280x720@30Hz */
+	/* 62 - 1280x720@30Hz 16:9 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 74250, 1280, 3040,
 		   3080, 3300, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 63 - 1920x1080@120Hz */
+	/* 63 - 1920x1080@120Hz 16:9 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 297000, 1920, 2008,
 		   2052, 2200, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
-	 .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 64 - 1920x1080@100Hz */
+	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 64 - 1920x1080@100Hz 16:9 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 297000, 1920, 2448,
 		   2492, 2640, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
-	 .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 65 - 1280x720@24Hz */
+	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 65 - 1280x720@24Hz 64:27 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 59400, 1280, 3040,
 		   3080, 3300, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 66 - 1280x720@25Hz */
+	/* 66 - 1280x720@25Hz 64:27 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 74250, 1280, 3700,
 		   3740, 3960, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 67 - 1280x720@30Hz */
+	/* 67 - 1280x720@30Hz 64:27 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 74250, 1280, 3040,
 		   3080, 3300, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 68 - 1280x720@50Hz */
+	/* 68 - 1280x720@50Hz 64:27 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 74250, 1280, 1720,
 		   1760, 1980, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 69 - 1280x720@60Hz */
+	/* 69 - 1280x720@60Hz 64:27 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 74250, 1280, 1390,
 		   1430, 1650, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 70 - 1280x720@100Hz */
+	/* 70 - 1280x720@100Hz 64:27 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 148500, 1280, 1720,
 		   1760, 1980, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 71 - 1280x720@120Hz */
+	/* 71 - 1280x720@120Hz 64:27 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 148500, 1280, 1390,
 		   1430, 1650, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 72 - 1920x1080@24Hz */
+	/* 72 - 1920x1080@24Hz 64:27 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 74250, 1920, 2558,
 		   2602, 2750, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 73 - 1920x1080@25Hz */
+	/* 73 - 1920x1080@25Hz 64:27 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 74250, 1920, 2448,
 		   2492, 2640, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 74 - 1920x1080@30Hz */
+	/* 74 - 1920x1080@30Hz 64:27 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 74250, 1920, 2008,
 		   2052, 2200, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 75 - 1920x1080@50Hz */
+	/* 75 - 1920x1080@50Hz 64:27 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 148500, 1920, 2448,
 		   2492, 2640, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 76 - 1920x1080@60Hz */
+	/* 76 - 1920x1080@60Hz 64:27 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 148500, 1920, 2008,
 		   2052, 2200, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 77 - 1920x1080@100Hz */
+	/* 77 - 1920x1080@100Hz 64:27 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 297000, 1920, 2448,
 		   2492, 2640, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 78 - 1920x1080@120Hz */
+	/* 78 - 1920x1080@120Hz 64:27 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 297000, 1920, 2008,
 		   2052, 2200, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 79 - 1680x720@24Hz */
+	/* 79 - 1680x720@24Hz 64:27 */
 	{ DRM_MODE("1680x720", DRM_MODE_TYPE_DRIVER, 59400, 1680, 3040,
 		   3080, 3300, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 80 - 1680x720@25Hz */
+	/* 80 - 1680x720@25Hz 64:27 */
 	{ DRM_MODE("1680x720", DRM_MODE_TYPE_DRIVER, 59400, 1680, 2908,
 		   2948, 3168, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 81 - 1680x720@30Hz */
+	/* 81 - 1680x720@30Hz 64:27 */
 	{ DRM_MODE("1680x720", DRM_MODE_TYPE_DRIVER, 59400, 1680, 2380,
 		   2420, 2640, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 82 - 1680x720@50Hz */
+	/* 82 - 1680x720@50Hz 64:27 */
 	{ DRM_MODE("1680x720", DRM_MODE_TYPE_DRIVER, 82500, 1680, 1940,
 		   1980, 2200, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 83 - 1680x720@60Hz */
+	/* 83 - 1680x720@60Hz 64:27 */
 	{ DRM_MODE("1680x720", DRM_MODE_TYPE_DRIVER, 99000, 1680, 1940,
 		   1980, 2200, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 84 - 1680x720@100Hz */
+	/* 84 - 1680x720@100Hz 64:27 */
 	{ DRM_MODE("1680x720", DRM_MODE_TYPE_DRIVER, 165000, 1680, 1740,
 		   1780, 2000, 0, 720, 725, 730, 825, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 85 - 1680x720@120Hz */
+	/* 85 - 1680x720@120Hz 64:27 */
 	{ DRM_MODE("1680x720", DRM_MODE_TYPE_DRIVER, 198000, 1680, 1740,
 		   1780, 2000, 0, 720, 725, 730, 825, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 86 - 2560x1080@24Hz */
+	/* 86 - 2560x1080@24Hz 64:27 */
 	{ DRM_MODE("2560x1080", DRM_MODE_TYPE_DRIVER, 99000, 2560, 3558,
 		   3602, 3750, 0, 1080, 1084, 1089, 1100, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 87 - 2560x1080@25Hz */
+	/* 87 - 2560x1080@25Hz 64:27 */
 	{ DRM_MODE("2560x1080", DRM_MODE_TYPE_DRIVER, 90000, 2560, 3008,
 		   3052, 3200, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 88 - 2560x1080@30Hz */
+	/* 88 - 2560x1080@30Hz 64:27 */
 	{ DRM_MODE("2560x1080", DRM_MODE_TYPE_DRIVER, 118800, 2560, 3328,
 		   3372, 3520, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 89 - 2560x1080@50Hz */
+	/* 89 - 2560x1080@50Hz 64:27 */
 	{ DRM_MODE("2560x1080", DRM_MODE_TYPE_DRIVER, 185625, 2560, 3108,
 		   3152, 3300, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 90 - 2560x1080@60Hz */
+	/* 90 - 2560x1080@60Hz 64:27 */
 	{ DRM_MODE("2560x1080", DRM_MODE_TYPE_DRIVER, 198000, 2560, 2808,
 		   2852, 3000, 0, 1080, 1084, 1089, 1100, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 91 - 2560x1080@100Hz */
+	/* 91 - 2560x1080@100Hz 64:27 */
 	{ DRM_MODE("2560x1080", DRM_MODE_TYPE_DRIVER, 371250, 2560, 2778,
 		   2822, 2970, 0, 1080, 1084, 1089, 1250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 92 - 2560x1080@120Hz */
+	/* 92 - 2560x1080@120Hz 64:27 */
 	{ DRM_MODE("2560x1080", DRM_MODE_TYPE_DRIVER, 495000, 2560, 3108,
 		   3152, 3300, 0, 1080, 1084, 1089, 1250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 93 - 3840x2160p@24Hz 16:9 */
+	/* 93 - 3840x2160@24Hz 16:9 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 297000, 3840, 5116,
 		   5204, 5500, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 94 - 3840x2160p@25Hz 16:9 */
+	/* 94 - 3840x2160@25Hz 16:9 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 297000, 3840, 4896,
 		   4984, 5280, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 95 - 3840x2160p@30Hz 16:9 */
+	/* 95 - 3840x2160@30Hz 16:9 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 297000, 3840, 4016,
 		   4104, 4400, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 96 - 3840x2160p@50Hz 16:9 */
+	/* 96 - 3840x2160@50Hz 16:9 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 594000, 3840, 4896,
 		   4984, 5280, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 97 - 3840x2160p@60Hz 16:9 */
+	/* 97 - 3840x2160@60Hz 16:9 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 594000, 3840, 4016,
 		   4104, 4400, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 98 - 4096x2160p@24Hz 256:135 */
+	/* 98 - 4096x2160@24Hz 256:135 */
 	{ DRM_MODE("4096x2160", DRM_MODE_TYPE_DRIVER, 297000, 4096, 5116,
 		   5204, 5500, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_256_135, },
-	/* 99 - 4096x2160p@25Hz 256:135 */
+	/* 99 - 4096x2160@25Hz 256:135 */
 	{ DRM_MODE("4096x2160", DRM_MODE_TYPE_DRIVER, 297000, 4096, 5064,
 		   5152, 5280, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_256_135, },
-	/* 100 - 4096x2160p@30Hz 256:135 */
+	/* 100 - 4096x2160@30Hz 256:135 */
 	{ DRM_MODE("4096x2160", DRM_MODE_TYPE_DRIVER, 297000, 4096, 4184,
 		   4272, 4400, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_256_135, },
-	/* 101 - 4096x2160p@50Hz 256:135 */
+	/* 101 - 4096x2160@50Hz 256:135 */
 	{ DRM_MODE("4096x2160", DRM_MODE_TYPE_DRIVER, 594000, 4096, 5064,
 		   5152, 5280, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_256_135, },
-	/* 102 - 4096x2160p@60Hz 256:135 */
+	/* 102 - 4096x2160@60Hz 256:135 */
 	{ DRM_MODE("4096x2160", DRM_MODE_TYPE_DRIVER, 594000, 4096, 4184,
 		   4272, 4400, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_256_135, },
-	/* 103 - 3840x2160p@24Hz 64:27 */
+	/* 103 - 3840x2160@24Hz 64:27 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 297000, 3840, 5116,
 		   5204, 5500, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 104 - 3840x2160p@25Hz 64:27 */
+	/* 104 - 3840x2160@25Hz 64:27 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 297000, 3840, 4896,
 		   4984, 5280, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 105 - 3840x2160p@30Hz 64:27 */
+	/* 105 - 3840x2160@30Hz 64:27 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 297000, 3840, 4016,
 		   4104, 4400, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 106 - 3840x2160p@50Hz 64:27 */
+	/* 106 - 3840x2160@50Hz 64:27 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 594000, 3840, 4896,
 		   4984, 5280, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 107 - 3840x2160p@60Hz 64:27 */
+	/* 107 - 3840x2160@60Hz 64:27 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 594000, 3840, 4016,
 		   4104, 4400, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
@@ -4874,6 +4875,14 @@ drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame,
 	frame->picture_aspect = HDMI_PICTURE_ASPECT_NONE;
 
 	/*
+	 * As some drivers don't support atomic, we can't use connector state.
+	 * So just initialize the frame with default values, just the same way
+	 * as it's done with other properties here.
+	 */
+	frame->content_type = HDMI_CONTENT_TYPE_GRAPHICS;
+	frame->itc = 0;
+
+	/*
 	 * Populate picture aspect ratio from either
 	 * user input (if specified) or from the CEA mode list.
 	 */
diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c
index 186d00adfb5f..9da36a6271d3 100644
--- a/drivers/gpu/drm/drm_fb_cma_helper.c
+++ b/drivers/gpu/drm/drm_fb_cma_helper.c
@@ -18,6 +18,7 @@
  */
 
 #include <drm/drmP.h>
+#include <drm/drm_client.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_framebuffer.h>
 #include <drm/drm_gem_cma_helper.h>
@@ -26,11 +27,8 @@
 #include <drm/drm_print.h>
 #include <linux/module.h>
 
-#define DEFAULT_FBDEFIO_DELAY_MS 50
-
 struct drm_fbdev_cma {
 	struct drm_fb_helper	fb_helper;
-	const struct drm_framebuffer_funcs *fb_funcs;
 };
 
 /**
@@ -44,36 +42,6 @@ struct drm_fbdev_cma {
  *
  * An fbdev framebuffer backed by cma is also available by calling
  * drm_fb_cma_fbdev_init(). drm_fb_cma_fbdev_fini() tears it down.
- * If the &drm_framebuffer_funcs.dirty callback is set, fb_deferred_io will be
- * set up automatically. &drm_framebuffer_funcs.dirty is called by
- * drm_fb_helper_deferred_io() in process context (&struct delayed_work).
- *
- * Example fbdev deferred io code::
- *
- *     static int driver_fb_dirty(struct drm_framebuffer *fb,
- *                                struct drm_file *file_priv,
- *                                unsigned flags, unsigned color,
- *                                struct drm_clip_rect *clips,
- *                                unsigned num_clips)
- *     {
- *         struct drm_gem_cma_object *cma = drm_fb_cma_get_gem_obj(fb, 0);
- *         ... push changes ...
- *         return 0;
- *     }
- *
- *     static struct drm_framebuffer_funcs driver_fb_funcs = {
- *         .destroy       = drm_gem_fb_destroy,
- *         .create_handle = drm_gem_fb_create_handle,
- *         .dirty         = driver_fb_dirty,
- *     };
- *
- * Initialize::
- *
- *     fbdev = drm_fb_cma_fbdev_init_with_funcs(dev, 16,
- *                                           dev->mode_config.num_crtc,
- *                                           dev->mode_config.num_connector,
- *                                           &driver_fb_funcs);
- *
  */
 
 static inline struct drm_fbdev_cma *to_fbdev_cma(struct drm_fb_helper *helper)
@@ -131,236 +99,28 @@ dma_addr_t drm_fb_cma_get_gem_addr(struct drm_framebuffer *fb,
 }
 EXPORT_SYMBOL_GPL(drm_fb_cma_get_gem_addr);
 
-static int drm_fb_cma_mmap(struct fb_info *info, struct vm_area_struct *vma)
-{
-	return dma_mmap_writecombine(info->device, vma, info->screen_base,
-				     info->fix.smem_start, info->fix.smem_len);
-}
-
-static struct fb_ops drm_fbdev_cma_ops = {
-	.owner		= THIS_MODULE,
-	DRM_FB_HELPER_DEFAULT_OPS,
-	.fb_fillrect	= drm_fb_helper_sys_fillrect,
-	.fb_copyarea	= drm_fb_helper_sys_copyarea,
-	.fb_imageblit	= drm_fb_helper_sys_imageblit,
-	.fb_mmap	= drm_fb_cma_mmap,
-};
-
-static int drm_fbdev_cma_deferred_io_mmap(struct fb_info *info,
-					  struct vm_area_struct *vma)
-{
-	fb_deferred_io_mmap(info, vma);
-	vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
-
-	return 0;
-}
-
-static int drm_fbdev_cma_defio_init(struct fb_info *fbi,
-				    struct drm_gem_cma_object *cma_obj)
-{
-	struct fb_deferred_io *fbdefio;
-	struct fb_ops *fbops;
-
-	/*
-	 * Per device structures are needed because:
-	 * fbops: fb_deferred_io_cleanup() clears fbops.fb_mmap
-	 * fbdefio: individual delays
-	 */
-	fbdefio = kzalloc(sizeof(*fbdefio), GFP_KERNEL);
-	fbops = kzalloc(sizeof(*fbops), GFP_KERNEL);
-	if (!fbdefio || !fbops) {
-		kfree(fbdefio);
-		kfree(fbops);
-		return -ENOMEM;
-	}
-
-	/* can't be offset from vaddr since dirty() uses cma_obj */
-	fbi->screen_buffer = cma_obj->vaddr;
-	/* fb_deferred_io_fault() needs a physical address */
-	fbi->fix.smem_start = page_to_phys(virt_to_page(fbi->screen_buffer));
-
-	*fbops = *fbi->fbops;
-	fbi->fbops = fbops;
-
-	fbdefio->delay = msecs_to_jiffies(DEFAULT_FBDEFIO_DELAY_MS);
-	fbdefio->deferred_io = drm_fb_helper_deferred_io;
-	fbi->fbdefio = fbdefio;
-	fb_deferred_io_init(fbi);
-	fbi->fbops->fb_mmap = drm_fbdev_cma_deferred_io_mmap;
-
-	return 0;
-}
-
-static void drm_fbdev_cma_defio_fini(struct fb_info *fbi)
-{
-	if (!fbi->fbdefio)
-		return;
-
-	fb_deferred_io_cleanup(fbi);
-	kfree(fbi->fbdefio);
-	kfree(fbi->fbops);
-}
-
-static int
-drm_fbdev_cma_create(struct drm_fb_helper *helper,
-	struct drm_fb_helper_surface_size *sizes)
-{
-	struct drm_fbdev_cma *fbdev_cma = to_fbdev_cma(helper);
-	struct drm_device *dev = helper->dev;
-	struct drm_gem_cma_object *obj;
-	struct drm_framebuffer *fb;
-	unsigned int bytes_per_pixel;
-	unsigned long offset;
-	struct fb_info *fbi;
-	size_t size;
-	int ret;
-
-	DRM_DEBUG_KMS("surface width(%d), height(%d) and bpp(%d)\n",
-			sizes->surface_width, sizes->surface_height,
-			sizes->surface_bpp);
-
-	bytes_per_pixel = DIV_ROUND_UP(sizes->surface_bpp, 8);
-	size = sizes->surface_width * sizes->surface_height * bytes_per_pixel;
-	obj = drm_gem_cma_create(dev, size);
-	if (IS_ERR(obj))
-		return -ENOMEM;
-
-	fbi = drm_fb_helper_alloc_fbi(helper);
-	if (IS_ERR(fbi)) {
-		ret = PTR_ERR(fbi);
-		goto err_gem_free_object;
-	}
-
-	fb = drm_gem_fbdev_fb_create(dev, sizes, 0, &obj->base,
-				     fbdev_cma->fb_funcs);
-	if (IS_ERR(fb)) {
-		dev_err(dev->dev, "Failed to allocate DRM framebuffer.\n");
-		ret = PTR_ERR(fb);
-		goto err_fb_info_destroy;
-	}
-
-	helper->fb = fb;
-
-	fbi->par = helper;
-	fbi->flags = FBINFO_FLAG_DEFAULT;
-	fbi->fbops = &drm_fbdev_cma_ops;
-
-	drm_fb_helper_fill_fix(fbi, fb->pitches[0], fb->format->depth);
-	drm_fb_helper_fill_var(fbi, helper, sizes->fb_width, sizes->fb_height);
-
-	offset = fbi->var.xoffset * bytes_per_pixel;
-	offset += fbi->var.yoffset * fb->pitches[0];
-
-	dev->mode_config.fb_base = (resource_size_t)obj->paddr;
-	fbi->screen_base = obj->vaddr + offset;
-	fbi->fix.smem_start = (unsigned long)(obj->paddr + offset);
-	fbi->screen_size = size;
-	fbi->fix.smem_len = size;
-
-	if (fb->funcs->dirty) {
-		ret = drm_fbdev_cma_defio_init(fbi, obj);
-		if (ret)
-			goto err_cma_destroy;
-	}
-
-	return 0;
-
-err_cma_destroy:
-	drm_framebuffer_remove(fb);
-err_fb_info_destroy:
-	drm_fb_helper_fini(helper);
-err_gem_free_object:
-	drm_gem_object_put_unlocked(&obj->base);
-	return ret;
-}
-
-static const struct drm_fb_helper_funcs drm_fb_cma_helper_funcs = {
-	.fb_probe = drm_fbdev_cma_create,
-};
-
 /**
- * drm_fb_cma_fbdev_init_with_funcs() - Allocate and initialize fbdev emulation
+ * drm_fb_cma_fbdev_init() - Allocate and initialize fbdev emulation
  * @dev: DRM device
  * @preferred_bpp: Preferred bits per pixel for the device.
  *                 @dev->mode_config.preferred_depth is used if this is zero.
  * @max_conn_count: Maximum number of connectors.
  *                  @dev->mode_config.num_connector is used if this is zero.
- * @funcs: Framebuffer functions, in particular a custom dirty() callback.
- *         Can be NULL.
  *
  * Returns:
  * Zero on success or negative error code on failure.
  */
-int drm_fb_cma_fbdev_init_with_funcs(struct drm_device *dev,
-	unsigned int preferred_bpp, unsigned int max_conn_count,
-	const struct drm_framebuffer_funcs *funcs)
+int drm_fb_cma_fbdev_init(struct drm_device *dev, unsigned int preferred_bpp,
+			  unsigned int max_conn_count)
 {
 	struct drm_fbdev_cma *fbdev_cma;
-	struct drm_fb_helper *fb_helper;
-	int ret;
-
-	if (!preferred_bpp)
-		preferred_bpp = dev->mode_config.preferred_depth;
-	if (!preferred_bpp)
-		preferred_bpp = 32;
-
-	if (!max_conn_count)
-		max_conn_count = dev->mode_config.num_connector;
-
-	fbdev_cma = kzalloc(sizeof(*fbdev_cma), GFP_KERNEL);
-	if (!fbdev_cma)
-		return -ENOMEM;
 
-	fbdev_cma->fb_funcs = funcs;
-	fb_helper = &fbdev_cma->fb_helper;
-
-	drm_fb_helper_prepare(dev, fb_helper, &drm_fb_cma_helper_funcs);
-
-	ret = drm_fb_helper_init(dev, fb_helper, max_conn_count);
-	if (ret < 0) {
-		DRM_DEV_ERROR(dev->dev, "Failed to initialize fbdev helper.\n");
-		goto err_free;
-	}
-
-	ret = drm_fb_helper_single_add_all_connectors(fb_helper);
-	if (ret < 0) {
-		DRM_DEV_ERROR(dev->dev, "Failed to add connectors.\n");
-		goto err_drm_fb_helper_fini;
-	}
-
-	ret = drm_fb_helper_initial_config(fb_helper, preferred_bpp);
-	if (ret < 0) {
-		DRM_DEV_ERROR(dev->dev, "Failed to set fbdev configuration.\n");
-		goto err_drm_fb_helper_fini;
-	}
+	/* dev->fb_helper will indirectly point to fbdev_cma after this call */
+	fbdev_cma = drm_fbdev_cma_init(dev, preferred_bpp, max_conn_count);
+	if (IS_ERR(fbdev_cma))
+		return PTR_ERR(fbdev_cma);
 
 	return 0;
-
-err_drm_fb_helper_fini:
-	drm_fb_helper_fini(fb_helper);
-err_free:
-	kfree(fbdev_cma);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_init_with_funcs);
-
-/**
- * drm_fb_cma_fbdev_init() - Allocate and initialize fbdev emulation
- * @dev: DRM device
- * @preferred_bpp: Preferred bits per pixel for the device.
- *                 @dev->mode_config.preferred_depth is used if this is zero.
- * @max_conn_count: Maximum number of connectors.
- *                  @dev->mode_config.num_connector is used if this is zero.
- *
- * Returns:
- * Zero on success or negative error code on failure.
- */
-int drm_fb_cma_fbdev_init(struct drm_device *dev, unsigned int preferred_bpp,
-			  unsigned int max_conn_count)
-{
-	return drm_fb_cma_fbdev_init_with_funcs(dev, preferred_bpp,
-						max_conn_count, NULL);
 }
 EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_init);
 
@@ -370,104 +130,54 @@ EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_init);
  */
 void drm_fb_cma_fbdev_fini(struct drm_device *dev)
 {
-	struct drm_fb_helper *fb_helper = dev->fb_helper;
-
-	if (!fb_helper)
-		return;
-
-	/* Unregister if it hasn't been done already */
-	if (fb_helper->fbdev && fb_helper->fbdev->dev)
-		drm_fb_helper_unregister_fbi(fb_helper);
-
-	if (fb_helper->fbdev)
-		drm_fbdev_cma_defio_fini(fb_helper->fbdev);
-
-	if (fb_helper->fb)
-		drm_framebuffer_remove(fb_helper->fb);
-
-	drm_fb_helper_fini(fb_helper);
-	kfree(to_fbdev_cma(fb_helper));
+	if (dev->fb_helper)
+		drm_fbdev_cma_fini(to_fbdev_cma(dev->fb_helper));
 }
 EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_fini);
 
+static const struct drm_fb_helper_funcs drm_fb_cma_helper_funcs = {
+	.fb_probe = drm_fb_helper_generic_probe,
+};
+
 /**
- * drm_fbdev_cma_init_with_funcs() - Allocate and initializes a drm_fbdev_cma struct
+ * drm_fbdev_cma_init() - Allocate and initializes a drm_fbdev_cma struct
  * @dev: DRM device
  * @preferred_bpp: Preferred bits per pixel for the device
  * @max_conn_count: Maximum number of connectors
- * @funcs: fb helper functions, in particular a custom dirty() callback
  *
  * Returns a newly allocated drm_fbdev_cma struct or a ERR_PTR.
  */
-struct drm_fbdev_cma *drm_fbdev_cma_init_with_funcs(struct drm_device *dev,
-	unsigned int preferred_bpp, unsigned int max_conn_count,
-	const struct drm_framebuffer_funcs *funcs)
+struct drm_fbdev_cma *drm_fbdev_cma_init(struct drm_device *dev,
+	unsigned int preferred_bpp, unsigned int max_conn_count)
 {
 	struct drm_fbdev_cma *fbdev_cma;
-	struct drm_fb_helper *helper;
+	struct drm_fb_helper *fb_helper;
 	int ret;
 
 	fbdev_cma = kzalloc(sizeof(*fbdev_cma), GFP_KERNEL);
-	if (!fbdev_cma) {
-		dev_err(dev->dev, "Failed to allocate drm fbdev.\n");
+	if (!fbdev_cma)
 		return ERR_PTR(-ENOMEM);
-	}
-	fbdev_cma->fb_funcs = funcs;
 
-	helper = &fbdev_cma->fb_helper;
-
-	drm_fb_helper_prepare(dev, helper, &drm_fb_cma_helper_funcs);
+	fb_helper = &fbdev_cma->fb_helper;
 
-	ret = drm_fb_helper_init(dev, helper, max_conn_count);
-	if (ret < 0) {
-		dev_err(dev->dev, "Failed to initialize drm fb helper.\n");
+	ret = drm_client_new(dev, &fb_helper->client, "fbdev", NULL);
+	if (ret)
 		goto err_free;
-	}
-
-	ret = drm_fb_helper_single_add_all_connectors(helper);
-	if (ret < 0) {
-		dev_err(dev->dev, "Failed to add connectors.\n");
-		goto err_drm_fb_helper_fini;
-
-	}
 
-	ret = drm_fb_helper_initial_config(helper, preferred_bpp);
-	if (ret < 0) {
-		dev_err(dev->dev, "Failed to set initial hw configuration.\n");
-		goto err_drm_fb_helper_fini;
-	}
+	ret = drm_fb_helper_fbdev_setup(dev, fb_helper, &drm_fb_cma_helper_funcs,
+					preferred_bpp, max_conn_count);
+	if (ret)
+		goto err_client_put;
 
 	return fbdev_cma;
 
-err_drm_fb_helper_fini:
-	drm_fb_helper_fini(helper);
+err_client_put:
+	drm_client_release(&fb_helper->client);
 err_free:
 	kfree(fbdev_cma);
 
 	return ERR_PTR(ret);
 }
-EXPORT_SYMBOL_GPL(drm_fbdev_cma_init_with_funcs);
-
-static const struct drm_framebuffer_funcs drm_fb_cma_funcs = {
-	.destroy	= drm_gem_fb_destroy,
-	.create_handle	= drm_gem_fb_create_handle,
-};
-
-/**
- * drm_fbdev_cma_init() - Allocate and initializes a drm_fbdev_cma struct
- * @dev: DRM device
- * @preferred_bpp: Preferred bits per pixel for the device
- * @max_conn_count: Maximum number of connectors
- *
- * Returns a newly allocated drm_fbdev_cma struct or a ERR_PTR.
- */
-struct drm_fbdev_cma *drm_fbdev_cma_init(struct drm_device *dev,
-	unsigned int preferred_bpp, unsigned int max_conn_count)
-{
-	return drm_fbdev_cma_init_with_funcs(dev, preferred_bpp,
-					     max_conn_count,
-					     &drm_fb_cma_funcs);
-}
 EXPORT_SYMBOL_GPL(drm_fbdev_cma_init);
 
 /**
@@ -477,14 +187,7 @@ EXPORT_SYMBOL_GPL(drm_fbdev_cma_init);
 void drm_fbdev_cma_fini(struct drm_fbdev_cma *fbdev_cma)
 {
 	drm_fb_helper_unregister_fbi(&fbdev_cma->fb_helper);
-	if (fbdev_cma->fb_helper.fbdev)
-		drm_fbdev_cma_defio_fini(fbdev_cma->fb_helper.fbdev);
-
-	if (fbdev_cma->fb_helper.fb)
-		drm_framebuffer_remove(fbdev_cma->fb_helper.fb);
-
-	drm_fb_helper_fini(&fbdev_cma->fb_helper);
-	kfree(fbdev_cma);
+	/* All resources have now been freed by drm_fbdev_fb_destroy() */
 }
 EXPORT_SYMBOL_GPL(drm_fbdev_cma_fini);
 
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 2ee1eaa66188..4b0dd20bccb8 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -30,6 +30,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/console.h>
+#include <linux/dma-buf.h>
 #include <linux/kernel.h>
 #include <linux/sysrq.h>
 #include <linux/slab.h>
@@ -66,6 +67,9 @@ static DEFINE_MUTEX(kernel_fb_helper_lock);
  * helper functions used by many drivers to implement the kernel mode setting
  * interfaces.
  *
+ * Drivers that support a dumb buffer with a virtual address and mmap support,
+ * should try out the generic fbdev emulation using drm_fbdev_generic_setup().
+ *
  * Setup fbdev emulation by calling drm_fb_helper_fbdev_setup() and tear it
  * down by calling drm_fb_helper_fbdev_teardown().
  *
@@ -368,7 +372,6 @@ static int restore_fbdev_mode_atomic(struct drm_fb_helper *fb_helper, bool activ
 	struct drm_plane *plane;
 	struct drm_atomic_state *state;
 	int i, ret;
-	unsigned int plane_mask;
 	struct drm_modeset_acquire_ctx ctx;
 
 	drm_modeset_acquire_init(&ctx, 0);
@@ -381,7 +384,6 @@ static int restore_fbdev_mode_atomic(struct drm_fb_helper *fb_helper, bool activ
 
 	state->acquire_ctx = &ctx;
 retry:
-	plane_mask = 0;
 	drm_for_each_plane(plane, dev) {
 		plane_state = drm_atomic_get_plane_state(state, plane);
 		if (IS_ERR(plane_state)) {
@@ -391,9 +393,6 @@ retry:
 
 		plane_state->rotation = DRM_MODE_ROTATE_0;
 
-		plane->old_fb = plane->fb;
-		plane_mask |= 1 << drm_plane_index(plane);
-
 		/* disable non-primary: */
 		if (plane->type == DRM_PLANE_TYPE_PRIMARY)
 			continue;
@@ -430,8 +429,6 @@ retry:
 	ret = drm_atomic_commit(state);
 
 out_state:
-	drm_atomic_clean_old_fb(dev, plane_mask, ret);
-
 	if (ret == -EDEADLK)
 		goto backoff;
 
@@ -745,6 +742,24 @@ static void drm_fb_helper_resume_worker(struct work_struct *work)
 	console_unlock();
 }
 
+static void drm_fb_helper_dirty_blit_real(struct drm_fb_helper *fb_helper,
+					  struct drm_clip_rect *clip)
+{
+	struct drm_framebuffer *fb = fb_helper->fb;
+	unsigned int cpp = drm_format_plane_cpp(fb->format->format, 0);
+	size_t offset = clip->y1 * fb->pitches[0] + clip->x1 * cpp;
+	void *src = fb_helper->fbdev->screen_buffer + offset;
+	void *dst = fb_helper->buffer->vaddr + offset;
+	size_t len = (clip->x2 - clip->x1) * cpp;
+	unsigned int y;
+
+	for (y = clip->y1; y < clip->y2; y++) {
+		memcpy(dst, src, len);
+		src += fb->pitches[0];
+		dst += fb->pitches[0];
+	}
+}
+
 static void drm_fb_helper_dirty_work(struct work_struct *work)
 {
 	struct drm_fb_helper *helper = container_of(work, struct drm_fb_helper,
@@ -760,8 +775,12 @@ static void drm_fb_helper_dirty_work(struct work_struct *work)
 	spin_unlock_irqrestore(&helper->dirty_lock, flags);
 
 	/* call dirty callback only when it has been really touched */
-	if (clip_copy.x1 < clip_copy.x2 && clip_copy.y1 < clip_copy.y2)
+	if (clip_copy.x1 < clip_copy.x2 && clip_copy.y1 < clip_copy.y2) {
+		/* Generic fbdev uses a shadow buffer */
+		if (helper->buffer)
+			drm_fb_helper_dirty_blit_real(helper, &clip_copy);
 		helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, &clip_copy, 1);
+	}
 }
 
 /**
@@ -1164,7 +1183,7 @@ EXPORT_SYMBOL(drm_fb_helper_sys_imageblit);
  * @info: fbdev registered by the helper
  * @rect: info about rectangle to fill
  *
- * A wrapper around cfb_imageblit implemented by fbdev core
+ * A wrapper around cfb_fillrect implemented by fbdev core
  */
 void drm_fb_helper_cfb_fillrect(struct fb_info *info,
 				const struct fb_fillrect *rect)
@@ -2330,6 +2349,20 @@ retry:
 	return true;
 }
 
+static bool connector_has_possible_crtc(struct drm_connector *connector,
+					struct drm_crtc *crtc)
+{
+	struct drm_encoder *encoder;
+	int i;
+
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
+		if (encoder->possible_crtcs & drm_crtc_mask(crtc))
+			return true;
+	}
+
+	return false;
+}
+
 static int drm_pick_crtcs(struct drm_fb_helper *fb_helper,
 			  struct drm_fb_helper_crtc **best_crtcs,
 			  struct drm_display_mode **modes,
@@ -2338,7 +2371,6 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper,
 	int c, o;
 	struct drm_connector *connector;
 	const struct drm_connector_helper_funcs *connector_funcs;
-	struct drm_encoder *encoder;
 	int my_score, best_score, score;
 	struct drm_fb_helper_crtc **crtcs, *crtc;
 	struct drm_fb_helper_connector *fb_helper_conn;
@@ -2370,27 +2402,14 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper,
 	connector_funcs = connector->helper_private;
 
 	/*
-	 * If the DRM device implements atomic hooks and ->best_encoder() is
-	 * NULL we fallback to the default drm_atomic_helper_best_encoder()
-	 * helper.
-	 */
-	if (drm_drv_uses_atomic_modeset(fb_helper->dev) &&
-	    !connector_funcs->best_encoder)
-		encoder = drm_atomic_helper_best_encoder(connector);
-	else
-		encoder = connector_funcs->best_encoder(connector);
-
-	if (!encoder)
-		goto out;
-
-	/*
 	 * select a crtc for this connector and then attempt to configure
 	 * remaining connectors
 	 */
 	for (c = 0; c < fb_helper->crtc_count; c++) {
 		crtc = &fb_helper->crtc_info[c];
 
-		if ((encoder->possible_crtcs & (1 << c)) == 0)
+		if (!connector_has_possible_crtc(connector,
+						 crtc->mode_set.crtc))
 			continue;
 
 		for (o = 0; o < n; o++)
@@ -2417,7 +2436,7 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper,
 			       sizeof(struct drm_fb_helper_crtc *));
 		}
 	}
-out:
+
 	kfree(crtcs);
 	return best_score;
 }
@@ -2928,6 +2947,294 @@ void drm_fb_helper_output_poll_changed(struct drm_device *dev)
 }
 EXPORT_SYMBOL(drm_fb_helper_output_poll_changed);
 
+/* @user: 1=userspace, 0=fbcon */
+static int drm_fbdev_fb_open(struct fb_info *info, int user)
+{
+	struct drm_fb_helper *fb_helper = info->par;
+
+	if (!try_module_get(fb_helper->dev->driver->fops->owner))
+		return -ENODEV;
+
+	return 0;
+}
+
+static int drm_fbdev_fb_release(struct fb_info *info, int user)
+{
+	struct drm_fb_helper *fb_helper = info->par;
+
+	module_put(fb_helper->dev->driver->fops->owner);
+
+	return 0;
+}
+
+/*
+ * fb_ops.fb_destroy is called by the last put_fb_info() call at the end of
+ * unregister_framebuffer() or fb_release().
+ */
+static void drm_fbdev_fb_destroy(struct fb_info *info)
+{
+	struct drm_fb_helper *fb_helper = info->par;
+	struct fb_info *fbi = fb_helper->fbdev;
+	struct fb_ops *fbops = NULL;
+	void *shadow = NULL;
+
+	if (fbi->fbdefio) {
+		fb_deferred_io_cleanup(fbi);
+		shadow = fbi->screen_buffer;
+		fbops = fbi->fbops;
+	}
+
+	drm_fb_helper_fini(fb_helper);
+
+	if (shadow) {
+		vfree(shadow);
+		kfree(fbops);
+	}
+
+	drm_client_framebuffer_delete(fb_helper->buffer);
+	/*
+	 * FIXME:
+	 * Remove conditional when all CMA drivers have been moved over to using
+	 * drm_fbdev_generic_setup().
+	 */
+	if (fb_helper->client.funcs) {
+		drm_client_release(&fb_helper->client);
+		kfree(fb_helper);
+	}
+}
+
+static int drm_fbdev_fb_mmap(struct fb_info *info, struct vm_area_struct *vma)
+{
+	struct drm_fb_helper *fb_helper = info->par;
+
+	if (fb_helper->dev->driver->gem_prime_mmap)
+		return fb_helper->dev->driver->gem_prime_mmap(fb_helper->buffer->gem, vma);
+	else
+		return -ENODEV;
+}
+
+static struct fb_ops drm_fbdev_fb_ops = {
+	.owner		= THIS_MODULE,
+	DRM_FB_HELPER_DEFAULT_OPS,
+	.fb_open	= drm_fbdev_fb_open,
+	.fb_release	= drm_fbdev_fb_release,
+	.fb_destroy	= drm_fbdev_fb_destroy,
+	.fb_mmap	= drm_fbdev_fb_mmap,
+	.fb_read	= drm_fb_helper_sys_read,
+	.fb_write	= drm_fb_helper_sys_write,
+	.fb_fillrect	= drm_fb_helper_sys_fillrect,
+	.fb_copyarea	= drm_fb_helper_sys_copyarea,
+	.fb_imageblit	= drm_fb_helper_sys_imageblit,
+};
+
+static struct fb_deferred_io drm_fbdev_defio = {
+	.delay		= HZ / 20,
+	.deferred_io	= drm_fb_helper_deferred_io,
+};
+
+/**
+ * drm_fb_helper_generic_probe - Generic fbdev emulation probe helper
+ * @fb_helper: fbdev helper structure
+ * @sizes: describes fbdev size and scanout surface size
+ *
+ * This function uses the client API to crate a framebuffer backed by a dumb buffer.
+ *
+ * The _sys_ versions are used for &fb_ops.fb_read, fb_write, fb_fillrect,
+ * fb_copyarea, fb_imageblit.
+ *
+ * Returns:
+ * Zero on success or negative error code on failure.
+ */
+int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper,
+				struct drm_fb_helper_surface_size *sizes)
+{
+	struct drm_client_dev *client = &fb_helper->client;
+	struct drm_client_buffer *buffer;
+	struct drm_framebuffer *fb;
+	struct fb_info *fbi;
+	u32 format;
+	int ret;
+
+	DRM_DEBUG_KMS("surface width(%d), height(%d) and bpp(%d)\n",
+		      sizes->surface_width, sizes->surface_height,
+		      sizes->surface_bpp);
+
+	format = drm_mode_legacy_fb_format(sizes->surface_bpp, sizes->surface_depth);
+	buffer = drm_client_framebuffer_create(client, sizes->surface_width,
+					       sizes->surface_height, format);
+	if (IS_ERR(buffer))
+		return PTR_ERR(buffer);
+
+	fb_helper->buffer = buffer;
+	fb_helper->fb = buffer->fb;
+	fb = buffer->fb;
+
+	fbi = drm_fb_helper_alloc_fbi(fb_helper);
+	if (IS_ERR(fbi)) {
+		ret = PTR_ERR(fbi);
+		goto err_free_buffer;
+	}
+
+	fbi->par = fb_helper;
+	fbi->fbops = &drm_fbdev_fb_ops;
+	fbi->screen_size = fb->height * fb->pitches[0];
+	fbi->fix.smem_len = fbi->screen_size;
+	fbi->screen_buffer = buffer->vaddr;
+	strcpy(fbi->fix.id, "DRM emulated");
+
+	drm_fb_helper_fill_fix(fbi, fb->pitches[0], fb->format->depth);
+	drm_fb_helper_fill_var(fbi, fb_helper, sizes->fb_width, sizes->fb_height);
+
+	if (fb->funcs->dirty) {
+		struct fb_ops *fbops;
+		void *shadow;
+
+		/*
+		 * fb_deferred_io_cleanup() clears &fbops->fb_mmap so a per
+		 * instance version is necessary.
+		 */
+		fbops = kzalloc(sizeof(*fbops), GFP_KERNEL);
+		shadow = vzalloc(fbi->screen_size);
+		if (!fbops || !shadow) {
+			kfree(fbops);
+			vfree(shadow);
+			ret = -ENOMEM;
+			goto err_fb_info_destroy;
+		}
+
+		*fbops = *fbi->fbops;
+		fbi->fbops = fbops;
+		fbi->screen_buffer = shadow;
+		fbi->fbdefio = &drm_fbdev_defio;
+
+		fb_deferred_io_init(fbi);
+	}
+
+	return 0;
+
+err_fb_info_destroy:
+	drm_fb_helper_fini(fb_helper);
+err_free_buffer:
+	drm_client_framebuffer_delete(buffer);
+
+	return ret;
+}
+EXPORT_SYMBOL(drm_fb_helper_generic_probe);
+
+static const struct drm_fb_helper_funcs drm_fb_helper_generic_funcs = {
+	.fb_probe = drm_fb_helper_generic_probe,
+};
+
+static void drm_fbdev_client_unregister(struct drm_client_dev *client)
+{
+	struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client);
+
+	if (fb_helper->fbdev) {
+		drm_fb_helper_unregister_fbi(fb_helper);
+		/* drm_fbdev_fb_destroy() takes care of cleanup */
+		return;
+	}
+
+	/* Did drm_fb_helper_fbdev_setup() run? */
+	if (fb_helper->dev)
+		drm_fb_helper_fini(fb_helper);
+
+	drm_client_release(client);
+	kfree(fb_helper);
+}
+
+static int drm_fbdev_client_restore(struct drm_client_dev *client)
+{
+	struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client);
+
+	drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper);
+
+	return 0;
+}
+
+static int drm_fbdev_client_hotplug(struct drm_client_dev *client)
+{
+	struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client);
+	struct drm_device *dev = client->dev;
+	int ret;
+
+	/* If drm_fb_helper_fbdev_setup() failed, we only try once */
+	if (!fb_helper->dev && fb_helper->funcs)
+		return 0;
+
+	if (dev->fb_helper)
+		return drm_fb_helper_hotplug_event(dev->fb_helper);
+
+	if (!dev->mode_config.num_connector)
+		return 0;
+
+	ret = drm_fb_helper_fbdev_setup(dev, fb_helper, &drm_fb_helper_generic_funcs,
+					fb_helper->preferred_bpp, 0);
+	if (ret) {
+		fb_helper->dev = NULL;
+		fb_helper->fbdev = NULL;
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct drm_client_funcs drm_fbdev_client_funcs = {
+	.owner		= THIS_MODULE,
+	.unregister	= drm_fbdev_client_unregister,
+	.restore	= drm_fbdev_client_restore,
+	.hotplug	= drm_fbdev_client_hotplug,
+};
+
+/**
+ * drm_fb_helper_generic_fbdev_setup() - Setup generic fbdev emulation
+ * @dev: DRM device
+ * @preferred_bpp: Preferred bits per pixel for the device.
+ *                 @dev->mode_config.preferred_depth is used if this is zero.
+ *
+ * This function sets up generic fbdev emulation for drivers that supports
+ * dumb buffers with a virtual address and that can be mmap'ed.
+ *
+ * Restore, hotplug events and teardown are all taken care of. Drivers that do
+ * suspend/resume need to call drm_fb_helper_set_suspend_unlocked() themselves.
+ * Simple drivers might use drm_mode_config_helper_suspend().
+ *
+ * Drivers that set the dirty callback on their framebuffer will get a shadow
+ * fbdev buffer that is blitted onto the real buffer. This is done in order to
+ * make deferred I/O work with all kinds of buffers.
+ *
+ * This function is safe to call even when there are no connectors present.
+ * Setup will be retried on the next hotplug event.
+ *
+ * Returns:
+ * Zero on success or negative error code on failure.
+ */
+int drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp)
+{
+	struct drm_fb_helper *fb_helper;
+	int ret;
+
+	if (!drm_fbdev_emulation)
+		return 0;
+
+	fb_helper = kzalloc(sizeof(*fb_helper), GFP_KERNEL);
+	if (!fb_helper)
+		return -ENOMEM;
+
+	ret = drm_client_new(dev, &fb_helper->client, "fbdev", &drm_fbdev_client_funcs);
+	if (ret) {
+		kfree(fb_helper);
+		return ret;
+	}
+
+	fb_helper->preferred_bpp = preferred_bpp;
+
+	drm_fbdev_client_hotplug(&fb_helper->client);
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_fbdev_generic_setup);
+
 /* The Kconfig DRM_KMS_HELPER selects FRAMEBUFFER_CONSOLE (if !EXPERT)
  * but the module doesn't depend on any fb console symbols.  At least
  * attempt to load fbcon to avoid leaving the system without a usable console.
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index 6d9b9453707c..ffa8dc35515f 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -35,6 +35,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 
+#include <drm/drm_client.h>
 #include <drm/drm_file.h>
 #include <drm/drmP.h>
 
@@ -101,6 +102,166 @@ DEFINE_MUTEX(drm_global_mutex);
 
 static int drm_open_helper(struct file *filp, struct drm_minor *minor);
 
+/**
+ * drm_file_alloc - allocate file context
+ * @minor: minor to allocate on
+ *
+ * This allocates a new DRM file context. It is not linked into any context and
+ * can be used by the caller freely. Note that the context keeps a pointer to
+ * @minor, so it must be freed before @minor is.
+ *
+ * RETURNS:
+ * Pointer to newly allocated context, ERR_PTR on failure.
+ */
+struct drm_file *drm_file_alloc(struct drm_minor *minor)
+{
+	struct drm_device *dev = minor->dev;
+	struct drm_file *file;
+	int ret;
+
+	file = kzalloc(sizeof(*file), GFP_KERNEL);
+	if (!file)
+		return ERR_PTR(-ENOMEM);
+
+	file->pid = get_pid(task_pid(current));
+	file->minor = minor;
+
+	/* for compatibility root is always authenticated */
+	file->authenticated = capable(CAP_SYS_ADMIN);
+	file->lock_count = 0;
+
+	INIT_LIST_HEAD(&file->lhead);
+	INIT_LIST_HEAD(&file->fbs);
+	mutex_init(&file->fbs_lock);
+	INIT_LIST_HEAD(&file->blobs);
+	INIT_LIST_HEAD(&file->pending_event_list);
+	INIT_LIST_HEAD(&file->event_list);
+	init_waitqueue_head(&file->event_wait);
+	file->event_space = 4096; /* set aside 4k for event buffer */
+
+	mutex_init(&file->event_read_lock);
+
+	if (drm_core_check_feature(dev, DRIVER_GEM))
+		drm_gem_open(dev, file);
+
+	if (drm_core_check_feature(dev, DRIVER_SYNCOBJ))
+		drm_syncobj_open(file);
+
+	if (drm_core_check_feature(dev, DRIVER_PRIME))
+		drm_prime_init_file_private(&file->prime);
+
+	if (dev->driver->open) {
+		ret = dev->driver->open(dev, file);
+		if (ret < 0)
+			goto out_prime_destroy;
+	}
+
+	return file;
+
+out_prime_destroy:
+	if (drm_core_check_feature(dev, DRIVER_PRIME))
+		drm_prime_destroy_file_private(&file->prime);
+	if (drm_core_check_feature(dev, DRIVER_SYNCOBJ))
+		drm_syncobj_release(file);
+	if (drm_core_check_feature(dev, DRIVER_GEM))
+		drm_gem_release(dev, file);
+	put_pid(file->pid);
+	kfree(file);
+
+	return ERR_PTR(ret);
+}
+
+static void drm_events_release(struct drm_file *file_priv)
+{
+	struct drm_device *dev = file_priv->minor->dev;
+	struct drm_pending_event *e, *et;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->event_lock, flags);
+
+	/* Unlink pending events */
+	list_for_each_entry_safe(e, et, &file_priv->pending_event_list,
+				 pending_link) {
+		list_del(&e->pending_link);
+		e->file_priv = NULL;
+	}
+
+	/* Remove unconsumed events */
+	list_for_each_entry_safe(e, et, &file_priv->event_list, link) {
+		list_del(&e->link);
+		kfree(e);
+	}
+
+	spin_unlock_irqrestore(&dev->event_lock, flags);
+}
+
+/**
+ * drm_file_free - free file context
+ * @file: context to free, or NULL
+ *
+ * This destroys and deallocates a DRM file context previously allocated via
+ * drm_file_alloc(). The caller must make sure to unlink it from any contexts
+ * before calling this.
+ *
+ * If NULL is passed, this is a no-op.
+ *
+ * RETURNS:
+ * 0 on success, or error code on failure.
+ */
+void drm_file_free(struct drm_file *file)
+{
+	struct drm_device *dev;
+
+	if (!file)
+		return;
+
+	dev = file->minor->dev;
+
+	DRM_DEBUG("pid = %d, device = 0x%lx, open_count = %d\n",
+		  task_pid_nr(current),
+		  (long)old_encode_dev(file->minor->kdev->devt),
+		  dev->open_count);
+
+	if (drm_core_check_feature(dev, DRIVER_LEGACY) &&
+	    dev->driver->preclose)
+		dev->driver->preclose(dev, file);
+
+	if (drm_core_check_feature(dev, DRIVER_LEGACY))
+		drm_legacy_lock_release(dev, file->filp);
+
+	if (drm_core_check_feature(dev, DRIVER_HAVE_DMA))
+		drm_legacy_reclaim_buffers(dev, file);
+
+	drm_events_release(file);
+
+	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
+		drm_fb_release(file);
+		drm_property_destroy_user_blobs(dev, file);
+	}
+
+	if (drm_core_check_feature(dev, DRIVER_SYNCOBJ))
+		drm_syncobj_release(file);
+
+	if (drm_core_check_feature(dev, DRIVER_GEM))
+		drm_gem_release(dev, file);
+
+	drm_legacy_ctxbitmap_flush(dev, file);
+
+	if (drm_is_primary_client(file))
+		drm_master_release(file);
+
+	if (dev->driver->postclose)
+		dev->driver->postclose(dev, file);
+
+	if (drm_core_check_feature(dev, DRIVER_PRIME))
+		drm_prime_destroy_file_private(&file->prime);
+
+	WARN_ON(!list_empty(&file->event_list));
+
+	put_pid(file->pid);
+	kfree(file);
+}
+
 static int drm_setup(struct drm_device * dev)
 {
 	int ret;
@@ -207,52 +368,22 @@ static int drm_open_helper(struct file *filp, struct drm_minor *minor)
 
 	DRM_DEBUG("pid = %d, minor = %d\n", task_pid_nr(current), minor->index);
 
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv)
-		return -ENOMEM;
-
-	filp->private_data = priv;
-	filp->f_mode |= FMODE_UNSIGNED_OFFSET;
-	priv->filp = filp;
-	priv->pid = get_pid(task_pid(current));
-	priv->minor = minor;
-
-	/* for compatibility root is always authenticated */
-	priv->authenticated = capable(CAP_SYS_ADMIN);
-	priv->lock_count = 0;
-
-	INIT_LIST_HEAD(&priv->lhead);
-	INIT_LIST_HEAD(&priv->fbs);
-	mutex_init(&priv->fbs_lock);
-	INIT_LIST_HEAD(&priv->blobs);
-	INIT_LIST_HEAD(&priv->pending_event_list);
-	INIT_LIST_HEAD(&priv->event_list);
-	init_waitqueue_head(&priv->event_wait);
-	priv->event_space = 4096; /* set aside 4k for event buffer */
-
-	mutex_init(&priv->event_read_lock);
-
-	if (drm_core_check_feature(dev, DRIVER_GEM))
-		drm_gem_open(dev, priv);
-
-	if (drm_core_check_feature(dev, DRIVER_SYNCOBJ))
-		drm_syncobj_open(priv);
-
-	if (drm_core_check_feature(dev, DRIVER_PRIME))
-		drm_prime_init_file_private(&priv->prime);
-
-	if (dev->driver->open) {
-		ret = dev->driver->open(dev, priv);
-		if (ret < 0)
-			goto out_prime_destroy;
-	}
+	priv = drm_file_alloc(minor);
+	if (IS_ERR(priv))
+		return PTR_ERR(priv);
 
 	if (drm_is_primary_client(priv)) {
 		ret = drm_master_open(priv);
-		if (ret)
-			goto out_close;
+		if (ret) {
+			drm_file_free(priv);
+			return ret;
+		}
 	}
 
+	filp->private_data = priv;
+	filp->f_mode |= FMODE_UNSIGNED_OFFSET;
+	priv->filp = filp;
+
 	mutex_lock(&dev->filelist_mutex);
 	list_add(&priv->lhead, &dev->filelist);
 	mutex_unlock(&dev->filelist_mutex);
@@ -278,45 +409,6 @@ static int drm_open_helper(struct file *filp, struct drm_minor *minor)
 #endif
 
 	return 0;
-
-out_close:
-	if (dev->driver->postclose)
-		dev->driver->postclose(dev, priv);
-out_prime_destroy:
-	if (drm_core_check_feature(dev, DRIVER_PRIME))
-		drm_prime_destroy_file_private(&priv->prime);
-	if (drm_core_check_feature(dev, DRIVER_SYNCOBJ))
-		drm_syncobj_release(priv);
-	if (drm_core_check_feature(dev, DRIVER_GEM))
-		drm_gem_release(dev, priv);
-	put_pid(priv->pid);
-	kfree(priv);
-	filp->private_data = NULL;
-	return ret;
-}
-
-static void drm_events_release(struct drm_file *file_priv)
-{
-	struct drm_device *dev = file_priv->minor->dev;
-	struct drm_pending_event *e, *et;
-	unsigned long flags;
-
-	spin_lock_irqsave(&dev->event_lock, flags);
-
-	/* Unlink pending events */
-	list_for_each_entry_safe(e, et, &file_priv->pending_event_list,
-				 pending_link) {
-		list_del(&e->pending_link);
-		e->file_priv = NULL;
-	}
-
-	/* Remove unconsumed events */
-	list_for_each_entry_safe(e, et, &file_priv->event_list, link) {
-		list_del(&e->link);
-		kfree(e);
-	}
-
-	spin_unlock_irqrestore(&dev->event_lock, flags);
 }
 
 static void drm_legacy_dev_reinit(struct drm_device *dev)
@@ -353,6 +445,8 @@ void drm_lastclose(struct drm_device * dev)
 
 	if (drm_core_check_feature(dev, DRIVER_LEGACY))
 		drm_legacy_dev_reinit(dev);
+
+	drm_client_dev_restore(dev);
 }
 
 /**
@@ -383,57 +477,7 @@ int drm_release(struct inode *inode, struct file *filp)
 	list_del(&file_priv->lhead);
 	mutex_unlock(&dev->filelist_mutex);
 
-	if (drm_core_check_feature(dev, DRIVER_LEGACY) &&
-	    dev->driver->preclose)
-		dev->driver->preclose(dev, file_priv);
-
-	/* ========================================================
-	 * Begin inline drm_release
-	 */
-
-	DRM_DEBUG("pid = %d, device = 0x%lx, open_count = %d\n",
-		  task_pid_nr(current),
-		  (long)old_encode_dev(file_priv->minor->kdev->devt),
-		  dev->open_count);
-
-	if (drm_core_check_feature(dev, DRIVER_LEGACY))
-		drm_legacy_lock_release(dev, filp);
-
-	if (drm_core_check_feature(dev, DRIVER_HAVE_DMA))
-		drm_legacy_reclaim_buffers(dev, file_priv);
-
-	drm_events_release(file_priv);
-
-	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
-		drm_fb_release(file_priv);
-		drm_property_destroy_user_blobs(dev, file_priv);
-	}
-
-	if (drm_core_check_feature(dev, DRIVER_SYNCOBJ))
-		drm_syncobj_release(file_priv);
-
-	if (drm_core_check_feature(dev, DRIVER_GEM))
-		drm_gem_release(dev, file_priv);
-
-	drm_legacy_ctxbitmap_flush(dev, file_priv);
-
-	if (drm_is_primary_client(file_priv))
-		drm_master_release(file_priv);
-
-	if (dev->driver->postclose)
-		dev->driver->postclose(dev, file_priv);
-
-	if (drm_core_check_feature(dev, DRIVER_PRIME))
-		drm_prime_destroy_file_private(&file_priv->prime);
-
-	WARN_ON(!list_empty(&file_priv->event_list));
-
-	put_pid(file_priv->pid);
-	kfree(file_priv);
-
-	/* ========================================================
-	 * End inline drm_release
-	 */
+	drm_file_free(file_priv);
 
 	if (!--dev->open_count) {
 		drm_lastclose(dev);
diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c
index 5ca6395cd4d3..35c1e2742c27 100644
--- a/drivers/gpu/drm/drm_fourcc.c
+++ b/drivers/gpu/drm/drm_fourcc.c
@@ -152,27 +152,27 @@ const struct drm_format_info *__drm_format_info(u32 format)
 		{ .format = DRM_FORMAT_XBGR8888_A8,	.depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
 		{ .format = DRM_FORMAT_RGBX8888_A8,	.depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
 		{ .format = DRM_FORMAT_BGRX8888_A8,	.depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
-		{ .format = DRM_FORMAT_YUV410,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 4 },
-		{ .format = DRM_FORMAT_YVU410,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 4 },
-		{ .format = DRM_FORMAT_YUV411,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 1 },
-		{ .format = DRM_FORMAT_YVU411,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 1 },
-		{ .format = DRM_FORMAT_YUV420,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 2 },
-		{ .format = DRM_FORMAT_YVU420,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 2 },
-		{ .format = DRM_FORMAT_YUV422,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_YVU422,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_YUV444,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_YVU444,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_NV12,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 2 },
-		{ .format = DRM_FORMAT_NV21,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 2 },
-		{ .format = DRM_FORMAT_NV16,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_NV61,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_NV24,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_NV42,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_YUYV,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_YVYU,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_UYVY,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_VYUY,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_AYUV,		.depth = 0,  .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_YUV410,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 4, .is_yuv = true },
+		{ .format = DRM_FORMAT_YVU410,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 4, .is_yuv = true },
+		{ .format = DRM_FORMAT_YUV411,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YVU411,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YUV420,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 2, .is_yuv = true },
+		{ .format = DRM_FORMAT_YVU420,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 2, .is_yuv = true },
+		{ .format = DRM_FORMAT_YUV422,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YVU422,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YUV444,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 1, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YVU444,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 1, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV12,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 2, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV21,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 2, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV16,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV61,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV24,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 1, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV42,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 1, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YUYV,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YVYU,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_UYVY,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_VYUY,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_AYUV,		.depth = 0,  .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true, .is_yuv = true },
 	};
 
 	unsigned int i;
diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c
index bfedceff87bb..781af1d42d76 100644
--- a/drivers/gpu/drm/drm_framebuffer.c
+++ b/drivers/gpu/drm/drm_framebuffer.c
@@ -95,21 +95,20 @@ int drm_framebuffer_check_src_coords(uint32_t src_x, uint32_t src_y,
 /**
  * drm_mode_addfb - add an FB to the graphics configuration
  * @dev: drm device for the ioctl
- * @data: data pointer for the ioctl
- * @file_priv: drm file for the ioctl call
+ * @or: pointer to request structure
+ * @file_priv: drm file
  *
  * Add a new FB to the specified CRTC, given a user request. This is the
  * original addfb ioctl which only supported RGB formats.
  *
- * Called by the user via ioctl.
+ * Called by the user via ioctl, or by an in-kernel client.
  *
  * Returns:
  * Zero on success, negative errno on failure.
  */
-int drm_mode_addfb(struct drm_device *dev,
-		   void *data, struct drm_file *file_priv)
+int drm_mode_addfb(struct drm_device *dev, struct drm_mode_fb_cmd *or,
+		   struct drm_file *file_priv)
 {
-	struct drm_mode_fb_cmd *or = data;
 	struct drm_mode_fb_cmd2 r = {};
 	int ret;
 
@@ -134,6 +133,12 @@ int drm_mode_addfb(struct drm_device *dev,
 	return 0;
 }
 
+int drm_mode_addfb_ioctl(struct drm_device *dev,
+			 void *data, struct drm_file *file_priv)
+{
+	return drm_mode_addfb(dev, data, file_priv);
+}
+
 static int fb_plane_width(int width,
 			  const struct drm_format_info *format, int plane)
 {
@@ -367,29 +372,28 @@ static void drm_mode_rmfb_work_fn(struct work_struct *w)
 
 /**
  * drm_mode_rmfb - remove an FB from the configuration
- * @dev: drm device for the ioctl
- * @data: data pointer for the ioctl
- * @file_priv: drm file for the ioctl call
+ * @dev: drm device
+ * @fb_id: id of framebuffer to remove
+ * @file_priv: drm file
  *
- * Remove the FB specified by the user.
+ * Remove the specified FB.
  *
- * Called by the user via ioctl.
+ * Called by the user via ioctl, or by an in-kernel client.
  *
  * Returns:
  * Zero on success, negative errno on failure.
  */
-int drm_mode_rmfb(struct drm_device *dev,
-		   void *data, struct drm_file *file_priv)
+int drm_mode_rmfb(struct drm_device *dev, u32 fb_id,
+		  struct drm_file *file_priv)
 {
 	struct drm_framebuffer *fb = NULL;
 	struct drm_framebuffer *fbl = NULL;
-	uint32_t *id = data;
 	int found = 0;
 
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EINVAL;
 
-	fb = drm_framebuffer_lookup(dev, file_priv, *id);
+	fb = drm_framebuffer_lookup(dev, file_priv, fb_id);
 	if (!fb)
 		return -ENOENT;
 
@@ -435,6 +439,14 @@ fail_unref:
 	return -ENOENT;
 }
 
+int drm_mode_rmfb_ioctl(struct drm_device *dev,
+			void *data, struct drm_file *file_priv)
+{
+	uint32_t *fb_id = data;
+
+	return drm_mode_rmfb(dev, *fb_id, file_priv);
+}
+
 /**
  * drm_mode_getfb - get FB info
  * @dev: drm device for the ioctl
@@ -835,9 +847,7 @@ retry:
 		if (ret)
 			goto unlock;
 
-		plane_mask |= BIT(drm_plane_index(plane));
-
-		plane->old_fb = plane->fb;
+		plane_mask |= drm_plane_mask(plane);
 	}
 
 	/* This list is only filled when disable_crtcs is set. */
@@ -852,9 +862,6 @@ retry:
 		ret = drm_atomic_commit(state);
 
 unlock:
-	if (plane_mask)
-		drm_atomic_clean_old_fb(dev, plane_mask, ret);
-
 	if (ret == -EDEADLK) {
 		drm_atomic_state_clear(state);
 		drm_modeset_backoff(&ctx);
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 4a16d7b26c89..bf90625df3c5 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -1036,6 +1036,15 @@ int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 		return -EACCES;
 	}
 
+	if (node->readonly) {
+		if (vma->vm_flags & VM_WRITE) {
+			drm_gem_object_put_unlocked(obj);
+			return -EINVAL;
+		}
+
+		vma->vm_flags &= ~VM_MAYWRITE;
+	}
+
 	ret = drm_gem_mmap_obj(obj, drm_vma_node_size(node) << PAGE_SHIFT,
 			       vma);
 
diff --git a/drivers/gpu/drm/drm_gem_framebuffer_helper.c b/drivers/gpu/drm/drm_gem_framebuffer_helper.c
index acfbc0641a06..2810d4131411 100644
--- a/drivers/gpu/drm/drm_gem_framebuffer_helper.c
+++ b/drivers/gpu/drm/drm_gem_framebuffer_helper.c
@@ -253,7 +253,7 @@ int drm_gem_fb_prepare_fb(struct drm_plane *plane,
 	struct dma_buf *dma_buf;
 	struct dma_fence *fence;
 
-	if (plane->state->fb == state->fb || !state->fb)
+	if (!state->fb)
 		return 0;
 
 	dma_buf = drm_gem_fb_get_obj(state->fb, 0)->dma_buf;
diff --git a/drivers/gpu/drm/drm_global.c b/drivers/gpu/drm/drm_global.c
index b2dc21e33ae0..5799e2782dd1 100644
--- a/drivers/gpu/drm/drm_global.c
+++ b/drivers/gpu/drm/drm_global.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
  * Copyright 2008-2009 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index b72242e93ea4..40179c5fc6b8 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -26,6 +26,8 @@
 
 /* drm_file.c */
 extern struct mutex drm_global_mutex;
+struct drm_file *drm_file_alloc(struct drm_minor *minor);
+void drm_file_free(struct drm_file *file);
 void drm_lastclose(struct drm_device *dev);
 
 /* drm_pci.c */
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 0d4cfb232576..ea10e9a26aad 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -334,6 +334,13 @@ drm_setclientcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
 			return -EINVAL;
 		file_priv->aspect_ratio_allowed = req->value;
 		break;
+	case DRM_CLIENT_CAP_WRITEBACK_CONNECTORS:
+		if (!file_priv->atomic)
+			return -EINVAL;
+		if (req->value > 1)
+			return -EINVAL;
+		file_priv->writeback_connectors = req->value;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -634,12 +641,12 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ATTACHMODE, drm_noop, DRM_MASTER|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DETACHMODE, drm_noop, DRM_MASTER|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPERTY, drm_mode_getproperty_ioctl, DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPROPERTY, drm_mode_connector_property_set_ioctl, DRM_MASTER|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPROPERTY, drm_connector_property_set_ioctl, DRM_MASTER|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPBLOB, drm_mode_getblob_ioctl, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETFB, drm_mode_getfb, DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB, drm_mode_addfb, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB, drm_mode_addfb_ioctl, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB2, drm_mode_addfb2, DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_RMFB, drm_mode_rmfb, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_RMFB, drm_mode_rmfb_ioctl, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_PAGE_FLIP, drm_mode_page_flip_ioctl, DRM_MASTER|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DIRTYFB, drm_mode_dirtyfb_ioctl, DRM_MASTER|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATE_DUMB, drm_mode_create_dumb_ioctl, DRM_UNLOCKED),
diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c
index d638c0fb3418..b54fb78a283c 100644
--- a/drivers/gpu/drm/drm_lease.c
+++ b/drivers/gpu/drm/drm_lease.c
@@ -553,7 +553,7 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 
 	/* Clone the lessor file to create a new file for us */
 	DRM_DEBUG_LEASE("Allocating lease file\n");
-	lessee_file = filp_clone_open(lessor_file);
+	lessee_file = file_clone_open(lessor_file);
 	if (IS_ERR(lessee_file)) {
 		ret = PTR_ERR(lessee_file);
 		goto out_lessee;
diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c
index bc73b7f5b9fc..80b75501f5c6 100644
--- a/drivers/gpu/drm/drm_mipi_dsi.c
+++ b/drivers/gpu/drm/drm_mipi_dsi.c
@@ -392,6 +392,7 @@ bool mipi_dsi_packet_format_is_short(u8 type)
 	case MIPI_DSI_DCS_SHORT_WRITE:
 	case MIPI_DSI_DCS_SHORT_WRITE_PARAM:
 	case MIPI_DSI_DCS_READ:
+	case MIPI_DSI_DCS_COMPRESSION_MODE:
 	case MIPI_DSI_SET_MAXIMUM_RETURN_PACKET_SIZE:
 		return true;
 	}
@@ -410,6 +411,7 @@ EXPORT_SYMBOL(mipi_dsi_packet_format_is_short);
 bool mipi_dsi_packet_format_is_long(u8 type)
 {
 	switch (type) {
+	case MIPI_DSI_PPS_LONG_WRITE:
 	case MIPI_DSI_NULL_PACKET:
 	case MIPI_DSI_BLANKING_PACKET:
 	case MIPI_DSI_GENERIC_LONG_WRITE:
diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index 3166026a1874..3cc5fbd78ee2 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -239,6 +239,32 @@ static void drm_mm_interval_tree_add_node(struct drm_mm_node *hole_node,
 #define HOLE_SIZE(NODE) ((NODE)->hole_size)
 #define HOLE_ADDR(NODE) (__drm_mm_hole_node_start(NODE))
 
+static u64 rb_to_hole_size(struct rb_node *rb)
+{
+	return rb_entry(rb, struct drm_mm_node, rb_hole_size)->hole_size;
+}
+
+static void insert_hole_size(struct rb_root_cached *root,
+			     struct drm_mm_node *node)
+{
+	struct rb_node **link = &root->rb_root.rb_node, *rb = NULL;
+	u64 x = node->hole_size;
+	bool first = true;
+
+	while (*link) {
+		rb = *link;
+		if (x > rb_to_hole_size(rb)) {
+			link = &rb->rb_left;
+		} else {
+			link = &rb->rb_right;
+			first = false;
+		}
+	}
+
+	rb_link_node(&node->rb_hole_size, rb, link);
+	rb_insert_color_cached(&node->rb_hole_size, root, first);
+}
+
 static void add_hole(struct drm_mm_node *node)
 {
 	struct drm_mm *mm = node->mm;
@@ -247,7 +273,7 @@ static void add_hole(struct drm_mm_node *node)
 		__drm_mm_hole_node_end(node) - __drm_mm_hole_node_start(node);
 	DRM_MM_BUG_ON(!drm_mm_hole_follows(node));
 
-	RB_INSERT(mm->holes_size, rb_hole_size, HOLE_SIZE);
+	insert_hole_size(&mm->holes_size, node);
 	RB_INSERT(mm->holes_addr, rb_hole_addr, HOLE_ADDR);
 
 	list_add(&node->hole_stack, &mm->hole_stack);
@@ -258,7 +284,7 @@ static void rm_hole(struct drm_mm_node *node)
 	DRM_MM_BUG_ON(!drm_mm_hole_follows(node));
 
 	list_del(&node->hole_stack);
-	rb_erase(&node->rb_hole_size, &node->mm->holes_size);
+	rb_erase_cached(&node->rb_hole_size, &node->mm->holes_size);
 	rb_erase(&node->rb_hole_addr, &node->mm->holes_addr);
 	node->hole_size = 0;
 
@@ -282,38 +308,39 @@ static inline u64 rb_hole_size(struct rb_node *rb)
 
 static struct drm_mm_node *best_hole(struct drm_mm *mm, u64 size)
 {
-	struct rb_node *best = NULL;
-	struct rb_node **link = &mm->holes_size.rb_node;
+	struct rb_node *rb = mm->holes_size.rb_root.rb_node;
+	struct drm_mm_node *best = NULL;
 
-	while (*link) {
-		struct rb_node *rb = *link;
+	do {
+		struct drm_mm_node *node =
+			rb_entry(rb, struct drm_mm_node, rb_hole_size);
 
-		if (size <= rb_hole_size(rb)) {
-			link = &rb->rb_left;
-			best = rb;
+		if (size <= node->hole_size) {
+			best = node;
+			rb = rb->rb_right;
 		} else {
-			link = &rb->rb_right;
+			rb = rb->rb_left;
 		}
-	}
+	} while (rb);
 
-	return rb_hole_size_to_node(best);
+	return best;
 }
 
 static struct drm_mm_node *find_hole(struct drm_mm *mm, u64 addr)
 {
+	struct rb_node *rb = mm->holes_addr.rb_node;
 	struct drm_mm_node *node = NULL;
-	struct rb_node **link = &mm->holes_addr.rb_node;
 
-	while (*link) {
+	while (rb) {
 		u64 hole_start;
 
-		node = rb_hole_addr_to_node(*link);
+		node = rb_hole_addr_to_node(rb);
 		hole_start = __drm_mm_hole_node_start(node);
 
 		if (addr < hole_start)
-			link = &node->rb_hole_addr.rb_left;
+			rb = node->rb_hole_addr.rb_left;
 		else if (addr > hole_start + node->hole_size)
-			link = &node->rb_hole_addr.rb_right;
+			rb = node->rb_hole_addr.rb_right;
 		else
 			break;
 	}
@@ -326,9 +353,6 @@ first_hole(struct drm_mm *mm,
 	   u64 start, u64 end, u64 size,
 	   enum drm_mm_insert_mode mode)
 {
-	if (RB_EMPTY_ROOT(&mm->holes_size))
-		return NULL;
-
 	switch (mode) {
 	default:
 	case DRM_MM_INSERT_BEST:
@@ -355,7 +379,7 @@ next_hole(struct drm_mm *mm,
 	switch (mode) {
 	default:
 	case DRM_MM_INSERT_BEST:
-		return rb_hole_size_to_node(rb_next(&node->rb_hole_size));
+		return rb_hole_size_to_node(rb_prev(&node->rb_hole_size));
 
 	case DRM_MM_INSERT_LOW:
 		return rb_hole_addr_to_node(rb_next(&node->rb_hole_addr));
@@ -426,6 +450,11 @@ int drm_mm_reserve_node(struct drm_mm *mm, struct drm_mm_node *node)
 }
 EXPORT_SYMBOL(drm_mm_reserve_node);
 
+static u64 rb_to_hole_size_or_zero(struct rb_node *rb)
+{
+	return rb ? rb_to_hole_size(rb) : 0;
+}
+
 /**
  * drm_mm_insert_node_in_range - ranged search for space and insert @node
  * @mm: drm_mm to allocate from
@@ -451,18 +480,26 @@ int drm_mm_insert_node_in_range(struct drm_mm * const mm,
 {
 	struct drm_mm_node *hole;
 	u64 remainder_mask;
+	bool once;
 
 	DRM_MM_BUG_ON(range_start >= range_end);
 
 	if (unlikely(size == 0 || range_end - range_start < size))
 		return -ENOSPC;
 
+	if (rb_to_hole_size_or_zero(rb_first_cached(&mm->holes_size)) < size)
+		return -ENOSPC;
+
 	if (alignment <= 1)
 		alignment = 0;
 
+	once = mode & DRM_MM_INSERT_ONCE;
+	mode &= ~DRM_MM_INSERT_ONCE;
+
 	remainder_mask = is_power_of_2(alignment) ? alignment - 1 : 0;
-	for (hole = first_hole(mm, range_start, range_end, size, mode); hole;
-	     hole = next_hole(mm, hole, mode)) {
+	for (hole = first_hole(mm, range_start, range_end, size, mode);
+	     hole;
+	     hole = once ? NULL : next_hole(mm, hole, mode)) {
 		u64 hole_start = __drm_mm_hole_node_start(hole);
 		u64 hole_end = hole_start + hole->hole_size;
 		u64 adj_start, adj_end;
@@ -587,9 +624,9 @@ void drm_mm_replace_node(struct drm_mm_node *old, struct drm_mm_node *new)
 
 	if (drm_mm_hole_follows(old)) {
 		list_replace(&old->hole_stack, &new->hole_stack);
-		rb_replace_node(&old->rb_hole_size,
-				&new->rb_hole_size,
-				&mm->holes_size);
+		rb_replace_node_cached(&old->rb_hole_size,
+				       &new->rb_hole_size,
+				       &mm->holes_size);
 		rb_replace_node(&old->rb_hole_addr,
 				&new->rb_hole_addr,
 				&mm->holes_addr);
@@ -885,7 +922,7 @@ void drm_mm_init(struct drm_mm *mm, u64 start, u64 size)
 
 	INIT_LIST_HEAD(&mm->hole_stack);
 	mm->interval_tree = RB_ROOT_CACHED;
-	mm->holes_size = RB_ROOT;
+	mm->holes_size = RB_ROOT_CACHED;
 	mm->holes_addr = RB_ROOT;
 
 	/* Clever trick to avoid a special case in the free hole tracking. */
diff --git a/drivers/gpu/drm/drm_mode_config.c b/drivers/gpu/drm/drm_mode_config.c
index e5c653357024..21e353bd3948 100644
--- a/drivers/gpu/drm/drm_mode_config.c
+++ b/drivers/gpu/drm/drm_mode_config.c
@@ -145,6 +145,11 @@ int drm_mode_getresources(struct drm_device *dev, void *data,
 	count = 0;
 	connector_id = u64_to_user_ptr(card_res->connector_id_ptr);
 	drm_for_each_connector_iter(connector, &conn_iter) {
+		/* only expose writeback connectors if userspace understands them */
+		if (!file_priv->writeback_connectors &&
+		    (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK))
+			continue;
+
 		if (drm_lease_held(file_priv, connector->base.id)) {
 			if (count < card_res->count_connectors &&
 			    put_user(connector->base.id, connector_id + count)) {
diff --git a/drivers/gpu/drm/drm_mode_object.c b/drivers/gpu/drm/drm_mode_object.c
index ce4d2fb32810..fcb0ab0abb75 100644
--- a/drivers/gpu/drm/drm_mode_object.c
+++ b/drivers/gpu/drm/drm_mode_object.c
@@ -433,8 +433,7 @@ static int set_property_legacy(struct drm_mode_object *obj,
 	drm_modeset_lock_all(dev);
 	switch (obj->type) {
 	case DRM_MODE_OBJECT_CONNECTOR:
-		ret = drm_mode_connector_set_obj_prop(obj, prop,
-						      prop_value);
+		ret = drm_connector_set_obj_prop(obj, prop, prop_value);
 		break;
 	case DRM_MODE_OBJECT_CRTC:
 		ret = drm_mode_crtc_set_obj_prop(obj, prop, prop_value);
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index c78ca0e84ffd..02db9ac82d7a 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -659,10 +659,12 @@ EXPORT_SYMBOL_GPL(drm_display_mode_to_videomode);
  * drm_bus_flags_from_videomode - extract information about pixelclk and
  * DE polarity from videomode and store it in a separate variable
  * @vm: videomode structure to use
- * @bus_flags: information about pixelclk and DE polarity will be stored here
+ * @bus_flags: information about pixelclk, sync and DE polarity will be stored
+ * here
  *
- * Sets DRM_BUS_FLAG_DE_(LOW|HIGH) and DRM_BUS_FLAG_PIXDATA_(POS|NEG)EDGE
- * in @bus_flags according to DISPLAY_FLAGS found in @vm
+ * Sets DRM_BUS_FLAG_DE_(LOW|HIGH),  DRM_BUS_FLAG_PIXDATA_(POS|NEG)EDGE and
+ * DISPLAY_FLAGS_SYNC_(POS|NEG)EDGE in @bus_flags according to DISPLAY_FLAGS
+ * found in @vm
  */
 void drm_bus_flags_from_videomode(const struct videomode *vm, u32 *bus_flags)
 {
@@ -672,6 +674,11 @@ void drm_bus_flags_from_videomode(const struct videomode *vm, u32 *bus_flags)
 	if (vm->flags & DISPLAY_FLAGS_PIXDATA_NEGEDGE)
 		*bus_flags |= DRM_BUS_FLAG_PIXDATA_NEGEDGE;
 
+	if (vm->flags & DISPLAY_FLAGS_SYNC_POSEDGE)
+		*bus_flags |= DRM_BUS_FLAG_SYNC_POSEDGE;
+	if (vm->flags & DISPLAY_FLAGS_SYNC_NEGEDGE)
+		*bus_flags |= DRM_BUS_FLAG_SYNC_NEGEDGE;
+
 	if (vm->flags & DISPLAY_FLAGS_DE_LOW)
 		*bus_flags |= DRM_BUS_FLAG_DE_LOW;
 	if (vm->flags & DISPLAY_FLAGS_DE_HIGH)
@@ -684,7 +691,7 @@ EXPORT_SYMBOL_GPL(drm_bus_flags_from_videomode);
  * of_get_drm_display_mode - get a drm_display_mode from devicetree
  * @np: device_node with the timing specification
  * @dmode: will be set to the return value
- * @bus_flags: information about pixelclk and DE polarity
+ * @bus_flags: information about pixelclk, sync and DE polarity
  * @index: index into the list of display timings in devicetree
  *
  * This function is expensive and should only be used, if only one mode is to be
@@ -1257,7 +1264,7 @@ static const char * const drm_mode_status_names[] = {
 
 #undef MODE_STATUS
 
-static const char *drm_get_mode_status_name(enum drm_mode_status status)
+const char *drm_get_mode_status_name(enum drm_mode_status status)
 {
 	int index = status + 3;
 
@@ -1346,7 +1353,7 @@ void drm_mode_sort(struct list_head *mode_list)
 EXPORT_SYMBOL(drm_mode_sort);
 
 /**
- * drm_mode_connector_list_update - update the mode list for the connector
+ * drm_connector_list_update - update the mode list for the connector
  * @connector: the connector to update
  *
  * This moves the modes from the @connector probed_modes list
@@ -1356,7 +1363,7 @@ EXPORT_SYMBOL(drm_mode_sort);
  * This is just a helper functions doesn't validate any modes itself and also
  * doesn't prune any invalid modes. Callers need to do that themselves.
  */
-void drm_mode_connector_list_update(struct drm_connector *connector)
+void drm_connector_list_update(struct drm_connector *connector)
 {
 	struct drm_display_mode *pmode, *pt;
 
@@ -1405,7 +1412,7 @@ void drm_mode_connector_list_update(struct drm_connector *connector)
 		}
 	}
 }
-EXPORT_SYMBOL(drm_mode_connector_list_update);
+EXPORT_SYMBOL(drm_connector_list_update);
 
 /**
  * drm_mode_parse_command_line_for_connector - parse command line modeline for connector
diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c
index 1fe122461298..2763a5ec845b 100644
--- a/drivers/gpu/drm/drm_of.c
+++ b/drivers/gpu/drm/drm_of.c
@@ -9,21 +9,28 @@
 #include <drm/drm_panel.h>
 #include <drm/drm_of.h>
 
+/**
+ * DOC: overview
+ *
+ * A set of helper functions to aid DRM drivers in parsing standard DT
+ * properties.
+ */
+
 static void drm_release_of(struct device *dev, void *data)
 {
 	of_node_put(data);
 }
 
 /**
- * drm_crtc_port_mask - find the mask of a registered CRTC by port OF node
+ * drm_of_crtc_port_mask - find the mask of a registered CRTC by port OF node
  * @dev: DRM device
  * @port: port OF node
  *
  * Given a port OF node, return the possible mask of the corresponding
  * CRTC within a device's list of CRTCs.  Returns zero if not found.
  */
-static uint32_t drm_crtc_port_mask(struct drm_device *dev,
-				   struct device_node *port)
+uint32_t drm_of_crtc_port_mask(struct drm_device *dev,
+			    struct device_node *port)
 {
 	unsigned int index = 0;
 	struct drm_crtc *tmp;
@@ -37,6 +44,7 @@ static uint32_t drm_crtc_port_mask(struct drm_device *dev,
 
 	return 0;
 }
+EXPORT_SYMBOL(drm_of_crtc_port_mask);
 
 /**
  * drm_of_find_possible_crtcs - find the possible CRTCs for an encoder port
@@ -62,7 +70,7 @@ uint32_t drm_of_find_possible_crtcs(struct drm_device *dev,
 			return 0;
 		}
 
-		possible_crtcs |= drm_crtc_port_mask(dev, remote_port);
+		possible_crtcs |= drm_of_crtc_port_mask(dev, remote_port);
 
 		of_node_put(remote_port);
 	}
@@ -93,7 +101,7 @@ EXPORT_SYMBOL_GPL(drm_of_component_match_add);
  * drm_of_component_probe - Generic probe function for a component based master
  * @dev: master device containing the OF node
  * @compare_of: compare function used for matching components
- * @master_ops: component master ops to be used
+ * @m_ops: component master ops to be used
  *
  * Parse the platform device OF node and bind all the components associated
  * with the master. Interface ports are added before the encoders in order to
@@ -238,10 +246,17 @@ int drm_of_find_panel_or_bridge(const struct device_node *np,
 	if (!remote)
 		return -ENODEV;
 
+	if (!of_device_is_available(remote)) {
+		of_node_put(remote);
+		return -ENODEV;
+	}
+
 	if (panel) {
 		*panel = of_drm_find_panel(remote);
-		if (*panel)
+		if (!IS_ERR(*panel))
 			ret = 0;
+		else
+			*panel = NULL;
 	}
 
 	/* No panel found yet, check for a bridge next. */
diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c
index 308d442a531b..b902361dee6e 100644
--- a/drivers/gpu/drm/drm_panel.c
+++ b/drivers/gpu/drm/drm_panel.c
@@ -24,6 +24,7 @@
 #include <linux/err.h>
 #include <linux/module.h>
 
+#include <drm/drm_device.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_panel.h>
 
@@ -94,6 +95,9 @@ EXPORT_SYMBOL(drm_panel_remove);
  *
  * An error is returned if the panel is already attached to another connector.
  *
+ * When unloading, the driver should detach from the panel by calling
+ * drm_panel_detach().
+ *
  * Return: 0 on success or a negative error code on failure.
  */
 int drm_panel_attach(struct drm_panel *panel, struct drm_connector *connector)
@@ -101,6 +105,13 @@ int drm_panel_attach(struct drm_panel *panel, struct drm_connector *connector)
 	if (panel->connector)
 		return -EBUSY;
 
+	panel->link = device_link_add(connector->dev->dev, panel->dev, 0);
+	if (!panel->link) {
+		dev_err(panel->dev, "failed to link panel to %s\n",
+			dev_name(connector->dev->dev));
+		return -EINVAL;
+	}
+
 	panel->connector = connector;
 	panel->drm = connector->dev;
 
@@ -115,10 +126,15 @@ EXPORT_SYMBOL(drm_panel_attach);
  * Detaches a panel from the connector it is attached to. If a panel is not
  * attached to any connector this is effectively a no-op.
  *
+ * This function should not be called by the panel device itself. It
+ * is only for the drm device that called drm_panel_attach().
+ *
  * Return: 0 on success or a negative error code on failure.
  */
 int drm_panel_detach(struct drm_panel *panel)
 {
+	device_link_del(panel->link);
+
 	panel->connector = NULL;
 	panel->drm = NULL;
 
@@ -135,12 +151,19 @@ EXPORT_SYMBOL(drm_panel_detach);
  * tree node. If a matching panel is found, return a pointer to it.
  *
  * Return: A pointer to the panel registered for the specified device tree
- * node or NULL if no panel matching the device tree node can be found.
+ * node or an ERR_PTR() if no panel matching the device tree node can be found.
+ * Possible error codes returned by this function:
+ * - EPROBE_DEFER: the panel device has not been probed yet, and the caller
+ *   should retry later
+ * - ENODEV: the device is not available (status != "okay" or "ok")
  */
 struct drm_panel *of_drm_find_panel(const struct device_node *np)
 {
 	struct drm_panel *panel;
 
+	if (!of_device_is_available(np))
+		return ERR_PTR(-ENODEV);
+
 	mutex_lock(&panel_lock);
 
 	list_for_each_entry(panel, &panel_list, list) {
@@ -151,7 +174,7 @@ struct drm_panel *of_drm_find_panel(const struct device_node *np)
 	}
 
 	mutex_unlock(&panel_lock);
-	return NULL;
+	return ERR_PTR(-EPROBE_DEFER);
 }
 EXPORT_SYMBOL(of_drm_find_panel);
 #endif
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index 4db9c515b74f..896e42a34895 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -326,64 +326,6 @@ int drm_legacy_pci_init(struct drm_driver *driver, struct pci_driver *pdriver)
 }
 EXPORT_SYMBOL(drm_legacy_pci_init);
 
-int drm_pcie_get_speed_cap_mask(struct drm_device *dev, u32 *mask)
-{
-	struct pci_dev *root;
-	u32 lnkcap, lnkcap2;
-
-	*mask = 0;
-	if (!dev->pdev)
-		return -EINVAL;
-
-	root = dev->pdev->bus->self;
-
-	/* we've been informed via and serverworks don't make the cut */
-	if (root->vendor == PCI_VENDOR_ID_VIA ||
-	    root->vendor == PCI_VENDOR_ID_SERVERWORKS)
-		return -EINVAL;
-
-	pcie_capability_read_dword(root, PCI_EXP_LNKCAP, &lnkcap);
-	pcie_capability_read_dword(root, PCI_EXP_LNKCAP2, &lnkcap2);
-
-	if (lnkcap2) {	/* PCIe r3.0-compliant */
-		if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_2_5GB)
-			*mask |= DRM_PCIE_SPEED_25;
-		if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_5_0GB)
-			*mask |= DRM_PCIE_SPEED_50;
-		if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_8_0GB)
-			*mask |= DRM_PCIE_SPEED_80;
-	} else {	/* pre-r3.0 */
-		if (lnkcap & PCI_EXP_LNKCAP_SLS_2_5GB)
-			*mask |= DRM_PCIE_SPEED_25;
-		if (lnkcap & PCI_EXP_LNKCAP_SLS_5_0GB)
-			*mask |= (DRM_PCIE_SPEED_25 | DRM_PCIE_SPEED_50);
-	}
-
-	DRM_INFO("probing gen 2 caps for device %x:%x = %x/%x\n", root->vendor, root->device, lnkcap, lnkcap2);
-	return 0;
-}
-EXPORT_SYMBOL(drm_pcie_get_speed_cap_mask);
-
-int drm_pcie_get_max_link_width(struct drm_device *dev, u32 *mlw)
-{
-	struct pci_dev *root;
-	u32 lnkcap;
-
-	*mlw = 0;
-	if (!dev->pdev)
-		return -EINVAL;
-
-	root = dev->pdev->bus->self;
-
-	pcie_capability_read_dword(root, PCI_EXP_LNKCAP, &lnkcap);
-
-	*mlw = (lnkcap & PCI_EXP_LNKCAP_MLW) >> 4;
-
-	DRM_INFO("probing mlw for device %x:%x = %x\n", root->vendor, root->device, lnkcap);
-	return 0;
-}
-EXPORT_SYMBOL(drm_pcie_get_max_link_width);
-
 #else
 
 void drm_pci_agp_destroy(struct drm_device *dev) {}
diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index 035054455301..6153cbda239f 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -177,6 +177,10 @@ int drm_universal_plane_init(struct drm_device *dev, struct drm_plane *plane,
 	if (WARN_ON(config->num_total_plane >= 32))
 		return -EINVAL;
 
+	WARN_ON(drm_drv_uses_atomic_modeset(dev) &&
+		(!funcs->atomic_destroy_state ||
+		 !funcs->atomic_duplicate_state));
+
 	ret = drm_mode_object_add(dev, &plane->base, DRM_MODE_OBJECT_PLANE);
 	if (ret)
 		return ret;
@@ -561,19 +565,66 @@ int drm_plane_check_pixel_format(struct drm_plane *plane,
 	if (i == plane->format_count)
 		return -EINVAL;
 
-	if (!plane->modifier_count)
-		return 0;
+	if (plane->funcs->format_mod_supported) {
+		if (!plane->funcs->format_mod_supported(plane, format, modifier))
+			return -EINVAL;
+	} else {
+		if (!plane->modifier_count)
+			return 0;
 
-	for (i = 0; i < plane->modifier_count; i++) {
-		if (modifier == plane->modifiers[i])
-			break;
+		for (i = 0; i < plane->modifier_count; i++) {
+			if (modifier == plane->modifiers[i])
+				break;
+		}
+		if (i == plane->modifier_count)
+			return -EINVAL;
 	}
-	if (i == plane->modifier_count)
-		return -EINVAL;
 
-	if (plane->funcs->format_mod_supported &&
-	    !plane->funcs->format_mod_supported(plane, format, modifier))
+	return 0;
+}
+
+static int __setplane_check(struct drm_plane *plane,
+			    struct drm_crtc *crtc,
+			    struct drm_framebuffer *fb,
+			    int32_t crtc_x, int32_t crtc_y,
+			    uint32_t crtc_w, uint32_t crtc_h,
+			    uint32_t src_x, uint32_t src_y,
+			    uint32_t src_w, uint32_t src_h)
+{
+	int ret;
+
+	/* Check whether this plane is usable on this CRTC */
+	if (!(plane->possible_crtcs & drm_crtc_mask(crtc))) {
+		DRM_DEBUG_KMS("Invalid crtc for plane\n");
 		return -EINVAL;
+	}
+
+	/* Check whether this plane supports the fb pixel format. */
+	ret = drm_plane_check_pixel_format(plane, fb->format->format,
+					   fb->modifier);
+	if (ret) {
+		struct drm_format_name_buf format_name;
+
+		DRM_DEBUG_KMS("Invalid pixel format %s, modifier 0x%llx\n",
+			      drm_get_format_name(fb->format->format,
+						  &format_name),
+			      fb->modifier);
+		return ret;
+	}
+
+	/* Give drivers some help against integer overflows */
+	if (crtc_w > INT_MAX ||
+	    crtc_x > INT_MAX - (int32_t) crtc_w ||
+	    crtc_h > INT_MAX ||
+	    crtc_y > INT_MAX - (int32_t) crtc_h) {
+		DRM_DEBUG_KMS("Invalid CRTC coordinates %ux%u+%d+%d\n",
+			      crtc_w, crtc_h, crtc_x, crtc_y);
+		return -ERANGE;
+	}
+
+	ret = drm_framebuffer_check_src_coords(src_x, src_y, src_w, src_h, fb);
+	if (ret)
+		return ret;
 
 	return 0;
 }
@@ -598,6 +649,8 @@ static int __setplane_internal(struct drm_plane *plane,
 {
 	int ret = 0;
 
+	WARN_ON(drm_drv_uses_atomic_modeset(plane->dev));
+
 	/* No fb means shut it down */
 	if (!fb) {
 		plane->old_fb = plane->fb;
@@ -611,37 +664,9 @@ static int __setplane_internal(struct drm_plane *plane,
 		goto out;
 	}
 
-	/* Check whether this plane is usable on this CRTC */
-	if (!(plane->possible_crtcs & drm_crtc_mask(crtc))) {
-		DRM_DEBUG_KMS("Invalid crtc for plane\n");
-		ret = -EINVAL;
-		goto out;
-	}
-
-	/* Check whether this plane supports the fb pixel format. */
-	ret = drm_plane_check_pixel_format(plane, fb->format->format,
-					   fb->modifier);
-	if (ret) {
-		struct drm_format_name_buf format_name;
-		DRM_DEBUG_KMS("Invalid pixel format %s, modifier 0x%llx\n",
-			      drm_get_format_name(fb->format->format,
-						  &format_name),
-			      fb->modifier);
-		goto out;
-	}
-
-	/* Give drivers some help against integer overflows */
-	if (crtc_w > INT_MAX ||
-	    crtc_x > INT_MAX - (int32_t) crtc_w ||
-	    crtc_h > INT_MAX ||
-	    crtc_y > INT_MAX - (int32_t) crtc_h) {
-		DRM_DEBUG_KMS("Invalid CRTC coordinates %ux%u+%d+%d\n",
-			      crtc_w, crtc_h, crtc_x, crtc_y);
-		ret = -ERANGE;
-		goto out;
-	}
-
-	ret = drm_framebuffer_check_src_coords(src_x, src_y, src_w, src_h, fb);
+	ret = __setplane_check(plane, crtc, fb,
+			       crtc_x, crtc_y, crtc_w, crtc_h,
+			       src_x, src_y, src_w, src_h);
 	if (ret)
 		goto out;
 
@@ -665,6 +690,41 @@ out:
 	return ret;
 }
 
+static int __setplane_atomic(struct drm_plane *plane,
+			     struct drm_crtc *crtc,
+			     struct drm_framebuffer *fb,
+			     int32_t crtc_x, int32_t crtc_y,
+			     uint32_t crtc_w, uint32_t crtc_h,
+			     uint32_t src_x, uint32_t src_y,
+			     uint32_t src_w, uint32_t src_h,
+			     struct drm_modeset_acquire_ctx *ctx)
+{
+	int ret;
+
+	WARN_ON(!drm_drv_uses_atomic_modeset(plane->dev));
+
+	/* No fb means shut it down */
+	if (!fb)
+		return plane->funcs->disable_plane(plane, ctx);
+
+	/*
+	 * FIXME: This is redundant with drm_atomic_plane_check(),
+	 * but the legacy cursor/"async" .update_plane() tricks
+	 * don't call that so we still need this here. Should remove
+	 * this when all .update_plane() implementations have been
+	 * fixed to call drm_atomic_plane_check().
+	 */
+	ret = __setplane_check(plane, crtc, fb,
+			       crtc_x, crtc_y, crtc_w, crtc_h,
+			       src_x, src_y, src_w, src_h);
+	if (ret)
+		return ret;
+
+	return plane->funcs->update_plane(plane, crtc, fb,
+					  crtc_x, crtc_y, crtc_w, crtc_h,
+					  src_x, src_y, src_w, src_h, ctx);
+}
+
 static int setplane_internal(struct drm_plane *plane,
 			     struct drm_crtc *crtc,
 			     struct drm_framebuffer *fb,
@@ -682,9 +742,15 @@ retry:
 	ret = drm_modeset_lock_all_ctx(plane->dev, &ctx);
 	if (ret)
 		goto fail;
-	ret = __setplane_internal(plane, crtc, fb,
-				  crtc_x, crtc_y, crtc_w, crtc_h,
-				  src_x, src_y, src_w, src_h, &ctx);
+
+	if (drm_drv_uses_atomic_modeset(plane->dev))
+		ret = __setplane_atomic(plane, crtc, fb,
+					crtc_x, crtc_y, crtc_w, crtc_h,
+					src_x, src_y, src_w, src_h, &ctx);
+	else
+		ret = __setplane_internal(plane, crtc, fb,
+					  crtc_x, crtc_y, crtc_w, crtc_h,
+					  src_x, src_y, src_w, src_h, &ctx);
 
 fail:
 	if (ret == -EDEADLK) {
@@ -816,9 +882,14 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc,
 		src_h = fb->height << 16;
 	}
 
-	ret = __setplane_internal(plane, crtc, fb,
-				  crtc_x, crtc_y, crtc_w, crtc_h,
-				  0, 0, src_w, src_h, ctx);
+	if (drm_drv_uses_atomic_modeset(dev))
+		ret = __setplane_atomic(plane, crtc, fb,
+					crtc_x, crtc_y, crtc_w, crtc_h,
+					0, 0, src_w, src_h, ctx);
+	else
+		ret = __setplane_internal(plane, crtc, fb,
+					  crtc_x, crtc_y, crtc_w, crtc_h,
+					  0, 0, src_w, src_h, ctx);
 
 	if (fb)
 		drm_framebuffer_put(fb);
@@ -1092,8 +1163,10 @@ retry:
 		/* Keep the old fb, don't unref it. */
 		plane->old_fb = NULL;
 	} else {
-		plane->fb = fb;
-		drm_framebuffer_get(fb);
+		if (!plane->state) {
+			plane->fb = fb;
+			drm_framebuffer_get(fb);
+		}
 	}
 
 out:
diff --git a/drivers/gpu/drm/drm_plane_helper.c b/drivers/gpu/drm/drm_plane_helper.c
index f88f68161519..621f17643bb0 100644
--- a/drivers/gpu/drm/drm_plane_helper.c
+++ b/drivers/gpu/drm/drm_plane_helper.c
@@ -440,6 +440,7 @@ out:
  * @src_y: y offset of @fb for panning
  * @src_w: width of source rectangle in @fb
  * @src_h: height of source rectangle in @fb
+ * @ctx: lock acquire context, not used here
  *
  * Provides a default plane update handler using the atomic plane update
  * functions. It is fully left to the driver to check plane constraints and
@@ -455,7 +456,8 @@ int drm_plane_helper_update(struct drm_plane *plane, struct drm_crtc *crtc,
 			    int crtc_x, int crtc_y,
 			    unsigned int crtc_w, unsigned int crtc_h,
 			    uint32_t src_x, uint32_t src_y,
-			    uint32_t src_w, uint32_t src_h)
+			    uint32_t src_w, uint32_t src_h,
+			    struct drm_modeset_acquire_ctx *ctx)
 {
 	struct drm_plane_state *plane_state;
 
@@ -489,6 +491,7 @@ EXPORT_SYMBOL(drm_plane_helper_update);
 /**
  * drm_plane_helper_disable() - Transitional helper for plane disable
  * @plane: plane to disable
+ * @ctx: lock acquire context, not used here
  *
  * Provides a default plane disable handler using the atomic plane update
  * functions. It is fully left to the driver to check plane constraints and
@@ -499,9 +502,11 @@ EXPORT_SYMBOL(drm_plane_helper_update);
  * RETURNS:
  * Zero on success, error code on failure
  */
-int drm_plane_helper_disable(struct drm_plane *plane)
+int drm_plane_helper_disable(struct drm_plane *plane,
+			     struct drm_modeset_acquire_ctx *ctx)
 {
 	struct drm_plane_state *plane_state;
+	struct drm_framebuffer *old_fb;
 
 	/* crtc helpers love to call disable functions for already disabled hw
 	 * functions. So cope with that. */
@@ -521,8 +526,9 @@ int drm_plane_helper_disable(struct drm_plane *plane)
 	plane_state->plane = plane;
 
 	plane_state->crtc = NULL;
+	old_fb = plane_state->fb;
 	drm_atomic_set_fb_for_plane(plane_state, NULL);
 
-	return drm_plane_helper_commit(plane, plane_state, plane->fb);
+	return drm_plane_helper_commit(plane, plane_state, old_fb);
 }
 EXPORT_SYMBOL(drm_plane_helper_disable);
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 397b46b33739..186db2e4c57a 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -186,7 +186,6 @@ static int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fpri
 /**
  * drm_gem_map_attach - dma_buf attach implementation for GEM
  * @dma_buf: buffer to attach device to
- * @target_dev: not used
  * @attach: buffer attachment data
  *
  * Allocates &drm_prime_attachment and calls &drm_driver.gem_prime_pin for
@@ -195,7 +194,7 @@ static int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fpri
  *
  * Returns 0 on success, negative error code on failure.
  */
-int drm_gem_map_attach(struct dma_buf *dma_buf, struct device *target_dev,
+int drm_gem_map_attach(struct dma_buf *dma_buf,
 		       struct dma_buf_attachment *attach)
 {
 	struct drm_prime_attachment *prime_attach;
@@ -435,35 +434,6 @@ void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
 EXPORT_SYMBOL(drm_gem_dmabuf_vunmap);
 
 /**
- * drm_gem_dmabuf_kmap_atomic - map_atomic implementation for GEM
- * @dma_buf: buffer to be mapped
- * @page_num: page number within the buffer
- *
- * Not implemented. This can be used as the &dma_buf_ops.map_atomic callback.
- */
-void *drm_gem_dmabuf_kmap_atomic(struct dma_buf *dma_buf,
-				 unsigned long page_num)
-{
-	return NULL;
-}
-EXPORT_SYMBOL(drm_gem_dmabuf_kmap_atomic);
-
-/**
- * drm_gem_dmabuf_kunmap_atomic - unmap_atomic implementation for GEM
- * @dma_buf: buffer to be unmapped
- * @page_num: page number within the buffer
- * @addr: virtual address of the buffer
- *
- * Not implemented. This can be used as the &dma_buf_ops.unmap_atomic callback.
- */
-void drm_gem_dmabuf_kunmap_atomic(struct dma_buf *dma_buf,
-				  unsigned long page_num, void *addr)
-{
-
-}
-EXPORT_SYMBOL(drm_gem_dmabuf_kunmap_atomic);
-
-/**
  * drm_gem_dmabuf_kmap - map implementation for GEM
  * @dma_buf: buffer to be mapped
  * @page_num: page number within the buffer
@@ -520,9 +490,7 @@ static const struct dma_buf_ops drm_gem_prime_dmabuf_ops =  {
 	.unmap_dma_buf = drm_gem_unmap_dma_buf,
 	.release = drm_gem_dmabuf_release,
 	.map = drm_gem_dmabuf_kmap,
-	.map_atomic = drm_gem_dmabuf_kmap_atomic,
 	.unmap = drm_gem_dmabuf_kunmap,
-	.unmap_atomic = drm_gem_dmabuf_kunmap_atomic,
 	.mmap = drm_gem_dmabuf_mmap,
 	.vmap = drm_gem_dmabuf_vmap,
 	.vunmap = drm_gem_dmabuf_vunmap,
diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c
index b25f98f33f6c..0e7fc3e7dfb4 100644
--- a/drivers/gpu/drm/drm_print.c
+++ b/drivers/gpu/drm/drm_print.c
@@ -30,6 +30,100 @@
 #include <drm/drmP.h>
 #include <drm/drm_print.h>
 
+void __drm_puts_coredump(struct drm_printer *p, const char *str)
+{
+	struct drm_print_iterator *iterator = p->arg;
+	ssize_t len;
+
+	if (!iterator->remain)
+		return;
+
+	if (iterator->offset < iterator->start) {
+		ssize_t copy;
+
+		len = strlen(str);
+
+		if (iterator->offset + len <= iterator->start) {
+			iterator->offset += len;
+			return;
+		}
+
+		copy = len - (iterator->start - iterator->offset);
+
+		if (copy > iterator->remain)
+			copy = iterator->remain;
+
+		/* Copy out the bit of the string that we need */
+		memcpy(iterator->data,
+			str + (iterator->start - iterator->offset), copy);
+
+		iterator->offset = iterator->start + copy;
+		iterator->remain -= copy;
+	} else {
+		ssize_t pos = iterator->offset - iterator->start;
+
+		len = min_t(ssize_t, strlen(str), iterator->remain);
+
+		memcpy(iterator->data + pos, str, len);
+
+		iterator->offset += len;
+		iterator->remain -= len;
+	}
+}
+EXPORT_SYMBOL(__drm_puts_coredump);
+
+void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf)
+{
+	struct drm_print_iterator *iterator = p->arg;
+	size_t len;
+	char *buf;
+
+	if (!iterator->remain)
+		return;
+
+	/* Figure out how big the string will be */
+	len = snprintf(NULL, 0, "%pV", vaf);
+
+	/* This is the easiest path, we've already advanced beyond the offset */
+	if (iterator->offset + len <= iterator->start) {
+		iterator->offset += len;
+		return;
+	}
+
+	/* Then check if we can directly copy into the target buffer */
+	if ((iterator->offset >= iterator->start) && (len < iterator->remain)) {
+		ssize_t pos = iterator->offset - iterator->start;
+
+		snprintf(((char *) iterator->data) + pos,
+			iterator->remain, "%pV", vaf);
+
+		iterator->offset += len;
+		iterator->remain -= len;
+
+		return;
+	}
+
+	/*
+	 * Finally, hit the slow path and make a temporary string to copy over
+	 * using _drm_puts_coredump
+	 */
+	buf = kmalloc(len + 1, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
+	if (!buf)
+		return;
+
+	snprintf(buf, len + 1, "%pV", vaf);
+	__drm_puts_coredump(p, (const char *) buf);
+
+	kfree(buf);
+}
+EXPORT_SYMBOL(__drm_printfn_coredump);
+
+void __drm_puts_seq_file(struct drm_printer *p, const char *str)
+{
+	seq_puts(p->arg, str);
+}
+EXPORT_SYMBOL(__drm_puts_seq_file);
+
 void __drm_printfn_seq_file(struct drm_printer *p, struct va_format *vaf)
 {
 	seq_printf(p->arg, "%pV", vaf);
@@ -49,6 +143,23 @@ void __drm_printfn_debug(struct drm_printer *p, struct va_format *vaf)
 EXPORT_SYMBOL(__drm_printfn_debug);
 
 /**
+ * drm_puts - print a const string to a &drm_printer stream
+ * @p: the &drm printer
+ * @str: const string
+ *
+ * Allow &drm_printer types that have a constant string
+ * option to use it.
+ */
+void drm_puts(struct drm_printer *p, const char *str)
+{
+	if (p->puts)
+		p->puts(p, str);
+	else
+		drm_printf(p, "%s", str);
+}
+EXPORT_SYMBOL(drm_puts);
+
+/**
  * drm_printf - print to a &drm_printer stream
  * @p: the &drm_printer
  * @f: format string
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index 527743394150..a1bb157bfdfa 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -33,6 +33,7 @@
 #include <linux/moduleparam.h>
 
 #include <drm/drmP.h>
+#include <drm/drm_client.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_fourcc.h>
 #include <drm/drm_crtc_helper.h>
@@ -88,9 +89,9 @@ drm_mode_validate_pipeline(struct drm_display_mode *mode,
 			    struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	uint32_t *ids = connector->encoder_ids;
 	enum drm_mode_status ret = MODE_OK;
-	unsigned int i;
+	struct drm_encoder *encoder;
+	int i;
 
 	/* Step 1: Validate against connector */
 	ret = drm_connector_mode_valid(connector, mode);
@@ -98,13 +99,9 @@ drm_mode_validate_pipeline(struct drm_display_mode *mode,
 		return ret;
 
 	/* Step 2: Validate against encoders and crtcs */
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		struct drm_encoder *encoder = drm_encoder_find(dev, NULL, ids[i]);
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		struct drm_crtc *crtc;
 
-		if (!encoder)
-			continue;
-
 		ret = drm_encoder_mode_valid(encoder, mode);
 		if (ret != MODE_OK) {
 			/* No point in continuing for crtc check as this encoder
@@ -363,7 +360,7 @@ EXPORT_SYMBOL(drm_helper_probe_detect);
  *    using the VESA GTF/CVT formulas.
  *
  * 3. Modes are moved from the probed_modes list to the modes list. Potential
- *    duplicates are merged together (see drm_mode_connector_list_update()).
+ *    duplicates are merged together (see drm_connector_list_update()).
  *    After this step the probed_modes list will be empty again.
  *
  * 4. Any non-stale mode on the modes list then undergoes validation
@@ -475,7 +472,7 @@ retry:
 	if (connector->status == connector_status_disconnected) {
 		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] disconnected\n",
 			connector->base.id, connector->name);
-		drm_mode_connector_update_edid_property(connector, NULL);
+		drm_connector_update_edid_property(connector, NULL);
 		verbose_prune = false;
 		goto prune;
 	}
@@ -488,7 +485,7 @@ retry:
 	if (count == 0)
 		goto prune;
 
-	drm_mode_connector_list_update(connector);
+	drm_connector_list_update(connector);
 
 	if (connector->interlace_allowed)
 		mode_flags |= DRM_MODE_FLAG_INTERLACE;
@@ -563,6 +560,8 @@ void drm_kms_helper_hotplug_event(struct drm_device *dev)
 	drm_sysfs_hotplug_event(dev);
 	if (dev->mode_config.funcs->output_poll_changed)
 		dev->mode_config.funcs->output_poll_changed(dev);
+
+	drm_client_dev_hotplug(dev);
 }
 EXPORT_SYMBOL(drm_kms_helper_hotplug_event);
 
diff --git a/drivers/gpu/drm/drm_simple_kms_helper.c b/drivers/gpu/drm/drm_simple_kms_helper.c
index 7a00455ca568..51fa978f0d23 100644
--- a/drivers/gpu/drm/drm_simple_kms_helper.c
+++ b/drivers/gpu/drm/drm_simple_kms_helper.c
@@ -52,7 +52,7 @@ static int drm_simple_kms_crtc_check(struct drm_crtc *crtc,
 				     struct drm_crtc_state *state)
 {
 	bool has_primary = state->plane_mask &
-			   BIT(drm_plane_index(crtc->primary));
+			   drm_plane_mask(crtc->primary);
 
 	/* We always want to have an active plane with an active CRTC */
 	if (has_primary != state->enable)
@@ -281,13 +281,13 @@ int drm_simple_display_pipe_init(struct drm_device *dev,
 	if (ret)
 		return ret;
 
-	encoder->possible_crtcs = 1 << drm_crtc_index(crtc);
+	encoder->possible_crtcs = drm_crtc_mask(crtc);
 	ret = drm_encoder_init(dev, encoder, &drm_simple_kms_encoder_funcs,
 			       DRM_MODE_ENCODER_NONE, NULL);
 	if (ret || !connector)
 		return ret;
 
-	return drm_mode_connector_attach_encoder(connector, encoder);
+	return drm_connector_attach_encoder(connector, encoder);
 }
 EXPORT_SYMBOL(drm_simple_display_pipe_init);
 
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index d4f4ce484529..adb3cb27d31e 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -207,7 +207,6 @@ static const struct dma_fence_ops drm_syncobj_null_fence_ops = {
 	.get_driver_name = drm_syncobj_null_fence_get_name,
 	.get_timeline_name = drm_syncobj_null_fence_get_name,
 	.enable_signaling = drm_syncobj_null_fence_enable_signaling,
-	.wait = dma_fence_default_wait,
 	.release = NULL,
 };
 
diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
index 2660543ad86a..c3301046dfaa 100644
--- a/drivers/gpu/drm/drm_vm.c
+++ b/drivers/gpu/drm/drm_vm.c
@@ -100,7 +100,7 @@ static pgprot_t drm_dma_prot(uint32_t map_type, struct vm_area_struct *vma)
  * map, get the page, increment the use count and return it.
  */
 #if IS_ENABLED(CONFIG_AGP)
-static int drm_vm_fault(struct vm_fault *vmf)
+static vm_fault_t drm_vm_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_file *priv = vma->vm_file->private_data;
@@ -173,7 +173,7 @@ vm_fault_error:
 	return VM_FAULT_SIGBUS;	/* Disallow mremap */
 }
 #else
-static int drm_vm_fault(struct vm_fault *vmf)
+static vm_fault_t drm_vm_fault(struct vm_fault *vmf)
 {
 	return VM_FAULT_SIGBUS;
 }
@@ -189,7 +189,7 @@ static int drm_vm_fault(struct vm_fault *vmf)
  * Get the mapping, find the real physical page to map, get the page, and
  * return it.
  */
-static int drm_vm_shm_fault(struct vm_fault *vmf)
+static vm_fault_t drm_vm_shm_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_local_map *map = vma->vm_private_data;
@@ -291,7 +291,7 @@ static void drm_vm_shm_close(struct vm_area_struct *vma)
  *
  * Determine the page number from the page offset and get it from drm_device_dma::pagelist.
  */
-static int drm_vm_dma_fault(struct vm_fault *vmf)
+static vm_fault_t drm_vm_dma_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_file *priv = vma->vm_file->private_data;
@@ -326,7 +326,7 @@ static int drm_vm_dma_fault(struct vm_fault *vmf)
  *
  * Determine the map offset from the page offset and get it from drm_sg_mem::pagelist.
  */
-static int drm_vm_sg_fault(struct vm_fault *vmf)
+static vm_fault_t drm_vm_sg_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_local_map *map = vma->vm_private_data;
diff --git a/drivers/gpu/drm/drm_vma_manager.c b/drivers/gpu/drm/drm_vma_manager.c
index 23c749c05b5a..a6b2fe36b025 100644
--- a/drivers/gpu/drm/drm_vma_manager.c
+++ b/drivers/gpu/drm/drm_vma_manager.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /*
  * Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA
  * Copyright (c) 2012 David Airlie <airlied@linux.ie>
diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c
new file mode 100644
index 000000000000..c20e6fe00cb3
--- /dev/null
+++ b/drivers/gpu/drm/drm_writeback.c
@@ -0,0 +1,353 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * (C) COPYRIGHT 2016 ARM Limited. All rights reserved.
+ * Author: Brian Starkey <brian.starkey@arm.com>
+ *
+ * This program is free software and is provided to you under the terms of the
+ * GNU General Public License version 2 as published by the Free Software
+ * Foundation, and any use by you of this program is subject to the terms
+ * of such GNU licence.
+ */
+
+#include <drm/drm_crtc.h>
+#include <drm/drm_modeset_helper_vtables.h>
+#include <drm/drm_property.h>
+#include <drm/drm_writeback.h>
+#include <drm/drmP.h>
+#include <linux/dma-fence.h>
+
+/**
+ * DOC: overview
+ *
+ * Writeback connectors are used to expose hardware which can write the output
+ * from a CRTC to a memory buffer. They are used and act similarly to other
+ * types of connectors, with some important differences:
+ *
+ * * Writeback connectors don't provide a way to output visually to the user.
+ *
+ * * Writeback connectors are visible to userspace only when the client sets
+ *   DRM_CLIENT_CAP_WRITEBACK_CONNECTORS.
+ *
+ * * Writeback connectors don't have EDID.
+ *
+ * A framebuffer may only be attached to a writeback connector when the
+ * connector is attached to a CRTC. The WRITEBACK_FB_ID property which sets the
+ * framebuffer applies only to a single commit (see below). A framebuffer may
+ * not be attached while the CRTC is off.
+ *
+ * Unlike with planes, when a writeback framebuffer is removed by userspace DRM
+ * makes no attempt to remove it from active use by the connector. This is
+ * because no method is provided to abort a writeback operation, and in any
+ * case making a new commit whilst a writeback is ongoing is undefined (see
+ * WRITEBACK_OUT_FENCE_PTR below). As soon as the current writeback is finished,
+ * the framebuffer will automatically no longer be in active use. As it will
+ * also have already been removed from the framebuffer list, there will be no
+ * way for any userspace application to retrieve a reference to it in the
+ * intervening period.
+ *
+ * Writeback connectors have some additional properties, which userspace
+ * can use to query and control them:
+ *
+ *  "WRITEBACK_FB_ID":
+ *	Write-only object property storing a DRM_MODE_OBJECT_FB: it stores the
+ *	framebuffer to be written by the writeback connector. This property is
+ *	similar to the FB_ID property on planes, but will always read as zero
+ *	and is not preserved across commits.
+ *	Userspace must set this property to an output buffer every time it
+ *	wishes the buffer to get filled.
+ *
+ *  "WRITEBACK_PIXEL_FORMATS":
+ *	Immutable blob property to store the supported pixel formats table. The
+ *	data is an array of u32 DRM_FORMAT_* fourcc values.
+ *	Userspace can use this blob to find out what pixel formats are supported
+ *	by the connector's writeback engine.
+ *
+ *  "WRITEBACK_OUT_FENCE_PTR":
+ *	Userspace can use this property to provide a pointer for the kernel to
+ *	fill with a sync_file file descriptor, which will signal once the
+ *	writeback is finished. The value should be the address of a 32-bit
+ *	signed integer, cast to a u64.
+ *	Userspace should wait for this fence to signal before making another
+ *	commit affecting any of the same CRTCs, Planes or Connectors.
+ *	**Failure to do so will result in undefined behaviour.**
+ *	For this reason it is strongly recommended that all userspace
+ *	applications making use of writeback connectors *always* retrieve an
+ *	out-fence for the commit and use it appropriately.
+ *	From userspace, this property will always read as zero.
+ */
+
+#define fence_to_wb_connector(x) container_of(x->lock, \
+					      struct drm_writeback_connector, \
+					      fence_lock)
+
+static const char *drm_writeback_fence_get_driver_name(struct dma_fence *fence)
+{
+	struct drm_writeback_connector *wb_connector =
+		fence_to_wb_connector(fence);
+
+	return wb_connector->base.dev->driver->name;
+}
+
+static const char *
+drm_writeback_fence_get_timeline_name(struct dma_fence *fence)
+{
+	struct drm_writeback_connector *wb_connector =
+		fence_to_wb_connector(fence);
+
+	return wb_connector->timeline_name;
+}
+
+static bool drm_writeback_fence_enable_signaling(struct dma_fence *fence)
+{
+	return true;
+}
+
+static const struct dma_fence_ops drm_writeback_fence_ops = {
+	.get_driver_name = drm_writeback_fence_get_driver_name,
+	.get_timeline_name = drm_writeback_fence_get_timeline_name,
+	.enable_signaling = drm_writeback_fence_enable_signaling,
+	.wait = dma_fence_default_wait,
+};
+
+static int create_writeback_properties(struct drm_device *dev)
+{
+	struct drm_property *prop;
+
+	if (!dev->mode_config.writeback_fb_id_property) {
+		prop = drm_property_create_object(dev, DRM_MODE_PROP_ATOMIC,
+						  "WRITEBACK_FB_ID",
+						  DRM_MODE_OBJECT_FB);
+		if (!prop)
+			return -ENOMEM;
+		dev->mode_config.writeback_fb_id_property = prop;
+	}
+
+	if (!dev->mode_config.writeback_pixel_formats_property) {
+		prop = drm_property_create(dev, DRM_MODE_PROP_BLOB |
+					   DRM_MODE_PROP_ATOMIC |
+					   DRM_MODE_PROP_IMMUTABLE,
+					   "WRITEBACK_PIXEL_FORMATS", 0);
+		if (!prop)
+			return -ENOMEM;
+		dev->mode_config.writeback_pixel_formats_property = prop;
+	}
+
+	if (!dev->mode_config.writeback_out_fence_ptr_property) {
+		prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC,
+						 "WRITEBACK_OUT_FENCE_PTR", 0,
+						 U64_MAX);
+		if (!prop)
+			return -ENOMEM;
+		dev->mode_config.writeback_out_fence_ptr_property = prop;
+	}
+
+	return 0;
+}
+
+static const struct drm_encoder_funcs drm_writeback_encoder_funcs = {
+	.destroy = drm_encoder_cleanup,
+};
+
+/**
+ * drm_writeback_connector_init - Initialize a writeback connector and its properties
+ * @dev: DRM device
+ * @wb_connector: Writeback connector to initialize
+ * @con_funcs: Connector funcs vtable
+ * @enc_helper_funcs: Encoder helper funcs vtable to be used by the internal encoder
+ * @formats: Array of supported pixel formats for the writeback engine
+ * @n_formats: Length of the formats array
+ *
+ * This function creates the writeback-connector-specific properties if they
+ * have not been already created, initializes the connector as
+ * type DRM_MODE_CONNECTOR_WRITEBACK, and correctly initializes the property
+ * values. It will also create an internal encoder associated with the
+ * drm_writeback_connector and set it to use the @enc_helper_funcs vtable for
+ * the encoder helper.
+ *
+ * Drivers should always use this function instead of drm_connector_init() to
+ * set up writeback connectors.
+ *
+ * Returns: 0 on success, or a negative error code
+ */
+int drm_writeback_connector_init(struct drm_device *dev,
+				 struct drm_writeback_connector *wb_connector,
+				 const struct drm_connector_funcs *con_funcs,
+				 const struct drm_encoder_helper_funcs *enc_helper_funcs,
+				 const u32 *formats, int n_formats)
+{
+	struct drm_property_blob *blob;
+	struct drm_connector *connector = &wb_connector->base;
+	struct drm_mode_config *config = &dev->mode_config;
+	int ret = create_writeback_properties(dev);
+
+	if (ret != 0)
+		return ret;
+
+	blob = drm_property_create_blob(dev, n_formats * sizeof(*formats),
+					formats);
+	if (IS_ERR(blob))
+		return PTR_ERR(blob);
+
+	drm_encoder_helper_add(&wb_connector->encoder, enc_helper_funcs);
+	ret = drm_encoder_init(dev, &wb_connector->encoder,
+			       &drm_writeback_encoder_funcs,
+			       DRM_MODE_ENCODER_VIRTUAL, NULL);
+	if (ret)
+		goto fail;
+
+	connector->interlace_allowed = 0;
+
+	ret = drm_connector_init(dev, connector, con_funcs,
+				 DRM_MODE_CONNECTOR_WRITEBACK);
+	if (ret)
+		goto connector_fail;
+
+	ret = drm_connector_attach_encoder(connector,
+						&wb_connector->encoder);
+	if (ret)
+		goto attach_fail;
+
+	INIT_LIST_HEAD(&wb_connector->job_queue);
+	spin_lock_init(&wb_connector->job_lock);
+
+	wb_connector->fence_context = dma_fence_context_alloc(1);
+	spin_lock_init(&wb_connector->fence_lock);
+	snprintf(wb_connector->timeline_name,
+		 sizeof(wb_connector->timeline_name),
+		 "CONNECTOR:%d-%s", connector->base.id, connector->name);
+
+	drm_object_attach_property(&connector->base,
+				   config->writeback_out_fence_ptr_property, 0);
+
+	drm_object_attach_property(&connector->base,
+				   config->writeback_fb_id_property, 0);
+
+	drm_object_attach_property(&connector->base,
+				   config->writeback_pixel_formats_property,
+				   blob->base.id);
+	wb_connector->pixel_formats_blob_ptr = blob;
+
+	return 0;
+
+attach_fail:
+	drm_connector_cleanup(connector);
+connector_fail:
+	drm_encoder_cleanup(&wb_connector->encoder);
+fail:
+	drm_property_blob_put(blob);
+	return ret;
+}
+EXPORT_SYMBOL(drm_writeback_connector_init);
+
+/**
+ * drm_writeback_queue_job - Queue a writeback job for later signalling
+ * @wb_connector: The writeback connector to queue a job on
+ * @job: The job to queue
+ *
+ * This function adds a job to the job_queue for a writeback connector. It
+ * should be considered to take ownership of the writeback job, and so any other
+ * references to the job must be cleared after calling this function.
+ *
+ * Drivers must ensure that for a given writeback connector, jobs are queued in
+ * exactly the same order as they will be completed by the hardware (and
+ * signaled via drm_writeback_signal_completion).
+ *
+ * For every call to drm_writeback_queue_job() there must be exactly one call to
+ * drm_writeback_signal_completion()
+ *
+ * See also: drm_writeback_signal_completion()
+ */
+void drm_writeback_queue_job(struct drm_writeback_connector *wb_connector,
+			     struct drm_writeback_job *job)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&wb_connector->job_lock, flags);
+	list_add_tail(&job->list_entry, &wb_connector->job_queue);
+	spin_unlock_irqrestore(&wb_connector->job_lock, flags);
+}
+EXPORT_SYMBOL(drm_writeback_queue_job);
+
+/*
+ * @cleanup_work: deferred cleanup of a writeback job
+ *
+ * The job cannot be cleaned up directly in drm_writeback_signal_completion,
+ * because it may be called in interrupt context. Dropping the framebuffer
+ * reference can sleep, and so the cleanup is deferred to a workqueue.
+ */
+static void cleanup_work(struct work_struct *work)
+{
+	struct drm_writeback_job *job = container_of(work,
+						     struct drm_writeback_job,
+						     cleanup_work);
+	drm_framebuffer_put(job->fb);
+	kfree(job);
+}
+
+
+/**
+ * drm_writeback_signal_completion - Signal the completion of a writeback job
+ * @wb_connector: The writeback connector whose job is complete
+ * @status: Status code to set in the writeback out_fence (0 for success)
+ *
+ * Drivers should call this to signal the completion of a previously queued
+ * writeback job. It should be called as soon as possible after the hardware
+ * has finished writing, and may be called from interrupt context.
+ * It is the driver's responsibility to ensure that for a given connector, the
+ * hardware completes writeback jobs in the same order as they are queued.
+ *
+ * Unless the driver is holding its own reference to the framebuffer, it must
+ * not be accessed after calling this function.
+ *
+ * See also: drm_writeback_queue_job()
+ */
+void
+drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector,
+				int status)
+{
+	unsigned long flags;
+	struct drm_writeback_job *job;
+
+	spin_lock_irqsave(&wb_connector->job_lock, flags);
+	job = list_first_entry_or_null(&wb_connector->job_queue,
+				       struct drm_writeback_job,
+				       list_entry);
+	if (job) {
+		list_del(&job->list_entry);
+		if (job->out_fence) {
+			if (status)
+				dma_fence_set_error(job->out_fence, status);
+			dma_fence_signal(job->out_fence);
+			dma_fence_put(job->out_fence);
+		}
+	}
+	spin_unlock_irqrestore(&wb_connector->job_lock, flags);
+
+	if (WARN_ON(!job))
+		return;
+
+	INIT_WORK(&job->cleanup_work, cleanup_work);
+	queue_work(system_long_wq, &job->cleanup_work);
+}
+EXPORT_SYMBOL(drm_writeback_signal_completion);
+
+struct dma_fence *
+drm_writeback_get_out_fence(struct drm_writeback_connector *wb_connector)
+{
+	struct dma_fence *fence;
+
+	if (WARN_ON(wb_connector->base.connector_type !=
+		    DRM_MODE_CONNECTOR_WRITEBACK))
+		return NULL;
+
+	fence = kzalloc(sizeof(*fence), GFP_KERNEL);
+	if (!fence)
+		return NULL;
+
+	dma_fence_init(fence, &drm_writeback_fence_ops,
+		       &wb_connector->fence_lock, wb_connector->fence_context,
+		       ++wb_connector->fence_seqno);
+
+	return fence;
+}
+EXPORT_SYMBOL(drm_writeback_get_out_fence);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
index 540b59fb4103..9b2720b41571 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
@@ -49,12 +49,12 @@ static int etnaviv_open(struct drm_device *dev, struct drm_file *file)
 
 	for (i = 0; i < ETNA_MAX_PIPES; i++) {
 		struct etnaviv_gpu *gpu = priv->gpu[i];
+		struct drm_sched_rq *rq;
 
 		if (gpu) {
-			drm_sched_entity_init(&gpu->sched,
-				&ctx->sched_entity[i],
-				&gpu->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL],
-				NULL);
+			rq = &gpu->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
+			drm_sched_entity_init(&ctx->sched_entity[i],
+					      &rq, 1, NULL);
 			}
 	}
 
@@ -78,8 +78,7 @@ static void etnaviv_postclose(struct drm_device *dev, struct drm_file *file)
 				gpu->lastctx = NULL;
 			mutex_unlock(&gpu->lock);
 
-			drm_sched_entity_fini(&gpu->sched,
-					      &ctx->sched_entity[i]);
+			drm_sched_entity_destroy(&ctx->sched_entity[i]);
 		}
 	}
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.h b/drivers/gpu/drm/etnaviv/etnaviv_drv.h
index d36c7bbe66db..8d02d1b7dcf5 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.h
@@ -18,6 +18,7 @@
 #include <linux/time64.h>
 #include <linux/types.h>
 #include <linux/sizes.h>
+#include <linux/mm_types.h>
 
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
@@ -53,7 +54,7 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data,
 		struct drm_file *file);
 
 int etnaviv_gem_mmap(struct file *filp, struct vm_area_struct *vma);
-int etnaviv_gem_fault(struct vm_fault *vmf);
+vm_fault_t etnaviv_gem_fault(struct vm_fault *vmf);
 int etnaviv_gem_mmap_offset(struct drm_gem_object *obj, u64 *offset);
 struct sg_table *etnaviv_gem_prime_get_sg_table(struct drm_gem_object *obj);
 void *etnaviv_gem_prime_vmap(struct drm_gem_object *obj);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index 209ef1274b80..1fa74226db91 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -169,31 +169,30 @@ int etnaviv_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 	return obj->ops->mmap(obj, vma);
 }
 
-int etnaviv_gem_fault(struct vm_fault *vmf)
+vm_fault_t etnaviv_gem_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_gem_object *obj = vma->vm_private_data;
 	struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj);
 	struct page **pages, *page;
 	pgoff_t pgoff;
-	int ret;
+	int err;
 
 	/*
 	 * Make sure we don't parallel update on a fault, nor move or remove
-	 * something from beneath our feet.  Note that vm_insert_page() is
+	 * something from beneath our feet.  Note that vmf_insert_page() is
 	 * specifically coded to take care of this, so we don't have to.
 	 */
-	ret = mutex_lock_interruptible(&etnaviv_obj->lock);
-	if (ret)
-		goto out;
-
+	err = mutex_lock_interruptible(&etnaviv_obj->lock);
+	if (err)
+		return VM_FAULT_NOPAGE;
 	/* make sure we have pages attached now */
 	pages = etnaviv_gem_get_pages(etnaviv_obj);
 	mutex_unlock(&etnaviv_obj->lock);
 
 	if (IS_ERR(pages)) {
-		ret = PTR_ERR(pages);
-		goto out;
+		err = PTR_ERR(pages);
+		return vmf_error(err);
 	}
 
 	/* We don't use vmf->pgoff since that has the fake offset: */
@@ -204,25 +203,7 @@ int etnaviv_gem_fault(struct vm_fault *vmf)
 	VERB("Inserting %p pfn %lx, pa %lx", (void *)vmf->address,
 	     page_to_pfn(page), page_to_pfn(page) << PAGE_SHIFT);
 
-	ret = vm_insert_page(vma, vmf->address, page);
-
-out:
-	switch (ret) {
-	case -EAGAIN:
-	case 0:
-	case -ERESTARTSYS:
-	case -EINTR:
-	case -EBUSY:
-		/*
-		 * EBUSY is ok: this just means that another thread
-		 * already did the job.
-		 */
-		return VM_FAULT_NOPAGE;
-	case -ENOMEM:
-		return VM_FAULT_OOM;
-	default:
-		return VM_FAULT_SIGBUS;
-	}
+	return vmf_insert_page(vma, vmf->address, page);
 }
 
 int etnaviv_gem_mmap_offset(struct drm_gem_object *obj, u64 *offset)
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
index 46ecd3e66ac9..983e67f19e45 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
@@ -388,9 +388,9 @@ static void submit_cleanup(struct kref *kref)
 		dma_fence_put(submit->in_fence);
 	if (submit->out_fence) {
 		/* first remove from IDR, so fence can not be found anymore */
-		mutex_lock(&submit->gpu->fence_idr_lock);
+		mutex_lock(&submit->gpu->fence_lock);
 		idr_remove(&submit->gpu->fence_idr, submit->out_fence_id);
-		mutex_unlock(&submit->gpu->fence_idr_lock);
+		mutex_unlock(&submit->gpu->fence_lock);
 		dma_fence_put(submit->out_fence);
 	}
 	kfree(submit->pmrs);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index 686f6552db48..f225fbc6edd2 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -799,6 +799,7 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu)
 
 free_buffer:
 	etnaviv_cmdbuf_free(&gpu->buffer);
+	gpu->buffer.suballoc = NULL;
 destroy_iommu:
 	etnaviv_iommu_destroy(gpu->mmu);
 	gpu->mmu = NULL;
@@ -1027,11 +1028,6 @@ static const char *etnaviv_fence_get_timeline_name(struct dma_fence *fence)
 	return dev_name(f->gpu->dev);
 }
 
-static bool etnaviv_fence_enable_signaling(struct dma_fence *fence)
-{
-	return true;
-}
-
 static bool etnaviv_fence_signaled(struct dma_fence *fence)
 {
 	struct etnaviv_fence *f = to_etnaviv_fence(fence);
@@ -1049,9 +1045,7 @@ static void etnaviv_fence_release(struct dma_fence *fence)
 static const struct dma_fence_ops etnaviv_fence_ops = {
 	.get_driver_name = etnaviv_fence_get_driver_name,
 	.get_timeline_name = etnaviv_fence_get_timeline_name,
-	.enable_signaling = etnaviv_fence_enable_signaling,
 	.signaled = etnaviv_fence_signaled,
-	.wait = dma_fence_default_wait,
 	.release = etnaviv_fence_release,
 };
 
@@ -1733,7 +1727,7 @@ static int etnaviv_gpu_platform_probe(struct platform_device *pdev)
 
 	gpu->dev = &pdev->dev;
 	mutex_init(&gpu->lock);
-	mutex_init(&gpu->fence_idr_lock);
+	mutex_init(&gpu->fence_lock);
 
 	/* Map registers: */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
index 90f17ff7888e..9a75a6937268 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
@@ -118,7 +118,7 @@ struct etnaviv_gpu {
 	u32 idle_mask;
 
 	/* Fencing support */
-	struct mutex fence_idr_lock;
+	struct mutex fence_lock;
 	struct idr fence_idr;
 	u32 next_fence;
 	u32 active_fence;
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
index 71fbc1f96cb6..f1c88d8ad5ba 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
@@ -119,8 +119,7 @@ static size_t etnaviv_iommuv2_unmap(struct etnaviv_iommu_domain *domain,
 
 static int etnaviv_iommuv2_init(struct etnaviv_iommuv2_domain *etnaviv_domain)
 {
-	u32 *p;
-	int ret, i;
+	int ret;
 
 	/* allocate scratch page */
 	etnaviv_domain->base.bad_page_cpu =
@@ -131,9 +130,9 @@ static int etnaviv_iommuv2_init(struct etnaviv_iommuv2_domain *etnaviv_domain)
 		ret = -ENOMEM;
 		goto fail_mem;
 	}
-	p = etnaviv_domain->base.bad_page_cpu;
-	for (i = 0; i < SZ_4K / 4; i++)
-		*p++ = 0xdead55aa;
+
+	memset32(etnaviv_domain->base.bad_page_cpu, 0xdead55aa,
+		 SZ_4K / sizeof(u32));
 
 	etnaviv_domain->pta_cpu = dma_alloc_wc(etnaviv_domain->base.dev,
 					       SZ_4K, &etnaviv_domain->pta_dma,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
index 50d6b88cb7aa..69e9b431bf1f 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
@@ -140,28 +140,38 @@ static const struct drm_sched_backend_ops etnaviv_sched_ops = {
 int etnaviv_sched_push_job(struct drm_sched_entity *sched_entity,
 			   struct etnaviv_gem_submit *submit)
 {
-	int ret;
+	int ret = 0;
+
+	/*
+	 * Hold the fence lock across the whole operation to avoid jobs being
+	 * pushed out of order with regard to their sched fence seqnos as
+	 * allocated in drm_sched_job_init.
+	 */
+	mutex_lock(&submit->gpu->fence_lock);
 
-	ret = drm_sched_job_init(&submit->sched_job, &submit->gpu->sched,
-				 sched_entity, submit->cmdbuf.ctx);
+	ret = drm_sched_job_init(&submit->sched_job, sched_entity,
+				 submit->cmdbuf.ctx);
 	if (ret)
-		return ret;
+		goto out_unlock;
 
 	submit->out_fence = dma_fence_get(&submit->sched_job.s_fence->finished);
-	mutex_lock(&submit->gpu->fence_idr_lock);
 	submit->out_fence_id = idr_alloc_cyclic(&submit->gpu->fence_idr,
 						submit->out_fence, 0,
 						INT_MAX, GFP_KERNEL);
-	mutex_unlock(&submit->gpu->fence_idr_lock);
-	if (submit->out_fence_id < 0)
-		return -ENOMEM;
+	if (submit->out_fence_id < 0) {
+		ret = -ENOMEM;
+		goto out_unlock;
+	}
 
 	/* the scheduler holds on to the job now */
 	kref_get(&submit->refcount);
 
 	drm_sched_entity_push_job(&submit->sched_job, sched_entity);
 
-	return 0;
+out_unlock:
+	mutex_unlock(&submit->gpu->fence_lock);
+
+	return ret;
 }
 
 int etnaviv_sched_init(struct etnaviv_gpu *gpu)
diff --git a/drivers/gpu/drm/exynos/Makefile b/drivers/gpu/drm/exynos/Makefile
index 3b323f1e0475..2ad146bbf4f5 100644
--- a/drivers/gpu/drm/exynos/Makefile
+++ b/drivers/gpu/drm/exynos/Makefile
@@ -4,7 +4,7 @@
 # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher.
 
 exynosdrm-y := exynos_drm_drv.o exynos_drm_crtc.o exynos_drm_fb.o \
-		exynos_drm_gem.o exynos_drm_core.o exynos_drm_plane.o
+		exynos_drm_gem.o exynos_drm_plane.o
 
 exynosdrm-$(CONFIG_DRM_FBDEV_EMULATION) += exynos_drm_fbdev.o
 exynosdrm-$(CONFIG_DRM_EXYNOS_IOMMU) += exynos_drm_iommu.o
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index e868773ea509..94529aa82339 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -673,6 +673,8 @@ err:
 static const struct dev_pm_ops exynos5433_decon_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos5433_decon_suspend, exynos5433_decon_resume,
 			   NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				     pm_runtime_force_resume)
 };
 
 static const struct of_device_id exynos5433_decon_driver_dt_match[] = {
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index 3931d5e33fe0..88cbd000eb09 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -832,6 +832,8 @@ static int exynos7_decon_resume(struct device *dev)
 static const struct dev_pm_ops exynos7_decon_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos7_decon_suspend, exynos7_decon_resume,
 			   NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 struct platform_driver decon_driver = {
diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c
index 86330f396784..c8449ae4f4fe 100644
--- a/drivers/gpu/drm/exynos/exynos_dp.c
+++ b/drivers/gpu/drm/exynos/exynos_dp.c
@@ -16,6 +16,7 @@
 #include <linux/clk.h>
 #include <linux/of_graph.h>
 #include <linux/component.h>
+#include <linux/pm_runtime.h>
 #include <video/of_display_timing.h>
 #include <video/of_videomode.h>
 #include <video/videomode.h>
@@ -232,9 +233,11 @@ static int exynos_dp_probe(struct platform_device *pdev)
 	np = of_parse_phandle(dev->of_node, "panel", 0);
 	if (np) {
 		dp->plat_data.panel = of_drm_find_panel(np);
+
 		of_node_put(np);
-		if (!dp->plat_data.panel)
-			return -EPROBE_DEFER;
+		if (IS_ERR(dp->plat_data.panel))
+			return PTR_ERR(dp->plat_data.panel);
+
 		goto out;
 	}
 
@@ -276,6 +279,8 @@ static int exynos_dp_resume(struct device *dev)
 
 static const struct dev_pm_ops exynos_dp_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos_dp_suspend, exynos_dp_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 static const struct of_device_id exynos_dp_match[] = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_core.c b/drivers/gpu/drm/exynos/exynos_drm_core.c
deleted file mode 100644
index b0c0621fcdf7..000000000000
--- a/drivers/gpu/drm/exynos/exynos_drm_core.c
+++ /dev/null
@@ -1,119 +0,0 @@
-/* exynos_drm_core.c
- *
- * Copyright (c) 2011 Samsung Electronics Co., Ltd.
- * Author:
- *	Inki Dae <inki.dae@samsung.com>
- *	Joonyoung Shim <jy0922.shim@samsung.com>
- *	Seung-Woo Kim <sw0312.kim@samsung.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#include <drm/drmP.h>
-
-#include "exynos_drm_drv.h"
-#include "exynos_drm_crtc.h"
-
-static LIST_HEAD(exynos_drm_subdrv_list);
-
-int exynos_drm_subdrv_register(struct exynos_drm_subdrv *subdrv)
-{
-	if (!subdrv)
-		return -EINVAL;
-
-	list_add_tail(&subdrv->list, &exynos_drm_subdrv_list);
-
-	return 0;
-}
-
-int exynos_drm_subdrv_unregister(struct exynos_drm_subdrv *subdrv)
-{
-	if (!subdrv)
-		return -EINVAL;
-
-	list_del(&subdrv->list);
-
-	return 0;
-}
-
-int exynos_drm_device_subdrv_probe(struct drm_device *dev)
-{
-	struct exynos_drm_subdrv *subdrv, *n;
-	int err;
-
-	if (!dev)
-		return -EINVAL;
-
-	list_for_each_entry_safe(subdrv, n, &exynos_drm_subdrv_list, list) {
-		if (subdrv->probe) {
-			subdrv->drm_dev = dev;
-
-			/*
-			 * this probe callback would be called by sub driver
-			 * after setting of all resources to this sub driver,
-			 * such as clock, irq and register map are done.
-			 */
-			err = subdrv->probe(dev, subdrv->dev);
-			if (err) {
-				DRM_DEBUG("exynos drm subdrv probe failed.\n");
-				list_del(&subdrv->list);
-				continue;
-			}
-		}
-	}
-
-	return 0;
-}
-
-int exynos_drm_device_subdrv_remove(struct drm_device *dev)
-{
-	struct exynos_drm_subdrv *subdrv;
-
-	if (!dev) {
-		WARN(1, "Unexpected drm device unregister!\n");
-		return -EINVAL;
-	}
-
-	list_for_each_entry(subdrv, &exynos_drm_subdrv_list, list) {
-		if (subdrv->remove)
-			subdrv->remove(dev, subdrv->dev);
-	}
-
-	return 0;
-}
-
-int exynos_drm_subdrv_open(struct drm_device *dev, struct drm_file *file)
-{
-	struct exynos_drm_subdrv *subdrv;
-	int ret;
-
-	list_for_each_entry(subdrv, &exynos_drm_subdrv_list, list) {
-		if (subdrv->open) {
-			ret = subdrv->open(dev, subdrv->dev, file);
-			if (ret)
-				goto err;
-		}
-	}
-
-	return 0;
-
-err:
-	list_for_each_entry_continue_reverse(subdrv, &exynos_drm_subdrv_list, list) {
-		if (subdrv->close)
-			subdrv->close(dev, subdrv->dev, file);
-	}
-	return ret;
-}
-
-void exynos_drm_subdrv_close(struct drm_device *dev, struct drm_file *file)
-{
-	struct exynos_drm_subdrv *subdrv;
-
-	list_for_each_entry(subdrv, &exynos_drm_subdrv_list, list) {
-		if (subdrv->close)
-			subdrv->close(dev, subdrv->dev, file);
-	}
-}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dpi.c b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
index 66945e0dc57f..2f0babb67c51 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dpi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
@@ -113,7 +113,7 @@ static int exynos_dpi_create_connector(struct drm_encoder *encoder)
 	}
 
 	drm_connector_helper_add(connector, &exynos_dpi_connector_helper_funcs);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
@@ -240,8 +240,8 @@ struct drm_encoder *exynos_dpi_probe(struct device *dev)
 
 	if (ctx->panel_node) {
 		ctx->panel = of_drm_find_panel(ctx->panel_node);
-		if (!ctx->panel)
-			return ERR_PTR(-EPROBE_DEFER);
+		if (IS_ERR(ctx->panel))
+			return ERR_CAST(ctx->panel);
 	}
 
 	return &ctx->encoder;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index ed3cc2989f93..b599f74692e5 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -55,8 +55,7 @@ static int exynos_drm_open(struct drm_device *dev, struct drm_file *file)
 		return -ENOMEM;
 
 	file->driver_priv = file_priv;
-
-	ret = exynos_drm_subdrv_open(dev, file);
+	ret = g2d_open(dev, file);
 	if (ret)
 		goto err_file_priv_free;
 
@@ -70,7 +69,7 @@ err_file_priv_free:
 
 static void exynos_drm_postclose(struct drm_device *dev, struct drm_file *file)
 {
-	exynos_drm_subdrv_close(dev, file);
+	g2d_close(dev, file);
 	kfree(file->driver_priv);
 	file->driver_priv = NULL;
 }
@@ -147,13 +146,12 @@ static struct drm_driver exynos_drm_driver = {
 	.minor	= DRIVER_MINOR,
 };
 
-#ifdef CONFIG_PM_SLEEP
 static int exynos_drm_suspend(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct exynos_drm_private *private;
 
-	if (pm_runtime_suspended(dev) || !drm_dev)
+	if (!drm_dev)
 		return 0;
 
 	private = drm_dev->dev_private;
@@ -170,25 +168,23 @@ static int exynos_drm_suspend(struct device *dev)
 	return 0;
 }
 
-static int exynos_drm_resume(struct device *dev)
+static void exynos_drm_resume(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct exynos_drm_private *private;
 
-	if (pm_runtime_suspended(dev) || !drm_dev)
-		return 0;
+	if (!drm_dev)
+		return;
 
 	private = drm_dev->dev_private;
 	drm_atomic_helper_resume(drm_dev, private->suspend_state);
 	exynos_drm_fbdev_resume(drm_dev);
 	drm_kms_helper_poll_enable(drm_dev);
-
-	return 0;
 }
-#endif
 
 static const struct dev_pm_ops exynos_drm_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(exynos_drm_suspend, exynos_drm_resume)
+	.prepare = exynos_drm_suspend,
+	.complete = exynos_drm_resume,
 };
 
 /* forward declaration */
@@ -240,6 +236,7 @@ static struct exynos_drm_driver_info exynos_drm_drivers[] = {
 		DRM_COMPONENT_DRIVER | DRM_VIRTUAL_DEVICE
 	}, {
 		DRV_PTR(g2d_driver, CONFIG_DRM_EXYNOS_G2D),
+		DRM_COMPONENT_DRIVER
 	}, {
 		DRV_PTR(fimc_driver, CONFIG_DRM_EXYNOS_FIMC),
 		DRM_COMPONENT_DRIVER | DRM_FIMC_DEVICE,
@@ -376,11 +373,6 @@ static int exynos_drm_bind(struct device *dev)
 	if (ret)
 		goto err_unbind_all;
 
-	/* Probe non kms sub drivers and virtual display driver. */
-	ret = exynos_drm_device_subdrv_probe(drm);
-	if (ret)
-		goto err_unbind_all;
-
 	drm_mode_config_reset(drm);
 
 	/*
@@ -411,7 +403,6 @@ err_cleanup_fbdev:
 	exynos_drm_fbdev_fini(drm);
 err_cleanup_poll:
 	drm_kms_helper_poll_fini(drm);
-	exynos_drm_device_subdrv_remove(drm);
 err_unbind_all:
 	component_unbind_all(drm->dev, drm);
 err_mode_config_cleanup:
@@ -431,8 +422,6 @@ static void exynos_drm_unbind(struct device *dev)
 
 	drm_dev_unregister(drm);
 
-	exynos_drm_device_subdrv_remove(drm);
-
 	exynos_drm_fbdev_fini(drm);
 	drm_kms_helper_poll_fini(drm);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index 0f6d079a55c9..c737c4bd2c19 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -179,17 +179,13 @@ static inline void exynos_drm_pipe_clk_enable(struct exynos_drm_crtc *crtc,
 		crtc->pipe_clk->enable(crtc->pipe_clk, enable);
 }
 
-struct exynos_drm_g2d_private {
-	struct device		*dev;
+struct drm_exynos_file_private {
+	/* for g2d api */
 	struct list_head	inuse_cmdlist;
 	struct list_head	event_list;
 	struct list_head	userptr_list;
 };
 
-struct drm_exynos_file_private {
-	struct exynos_drm_g2d_private	*g2d_priv;
-};
-
 /*
  * Exynos drm private structure.
  *
@@ -201,6 +197,7 @@ struct exynos_drm_private {
 	struct drm_fb_helper *fb_helper;
 	struct drm_atomic_state *suspend_state;
 
+	struct device *g2d_dev;
 	struct device *dma_dev;
 	void *mapping;
 
@@ -217,44 +214,6 @@ static inline struct device *to_dma_dev(struct drm_device *dev)
 	return priv->dma_dev;
 }
 
-/*
- * Exynos drm sub driver structure.
- *
- * @list: sub driver has its own list object to register to exynos drm driver.
- * @dev: pointer to device object for subdrv device driver.
- * @drm_dev: pointer to drm_device and this pointer would be set
- *	when sub driver calls exynos_drm_subdrv_register().
- * @probe: this callback would be called by exynos drm driver after
- *     subdrv is registered to it.
- * @remove: this callback is used to release resources created
- *     by probe callback.
- * @open: this would be called with drm device file open.
- * @close: this would be called with drm device file close.
- */
-struct exynos_drm_subdrv {
-	struct list_head list;
-	struct device *dev;
-	struct drm_device *drm_dev;
-
-	int (*probe)(struct drm_device *drm_dev, struct device *dev);
-	void (*remove)(struct drm_device *drm_dev, struct device *dev);
-	int (*open)(struct drm_device *drm_dev, struct device *dev,
-			struct drm_file *file);
-	void (*close)(struct drm_device *drm_dev, struct device *dev,
-			struct drm_file *file);
-};
-
- /* This function would be called by non kms drivers such as g2d and ipp. */
-int exynos_drm_subdrv_register(struct exynos_drm_subdrv *drm_subdrv);
-
-/* this function removes subdrv list from exynos drm driver */
-int exynos_drm_subdrv_unregister(struct exynos_drm_subdrv *drm_subdrv);
-
-int exynos_drm_device_subdrv_probe(struct drm_device *dev);
-int exynos_drm_device_subdrv_remove(struct drm_device *dev);
-int exynos_drm_subdrv_open(struct drm_device *dev, struct drm_file *file);
-void exynos_drm_subdrv_close(struct drm_device *dev, struct drm_file *file);
-
 #ifdef CONFIG_DRM_EXYNOS_DPI
 struct drm_encoder *exynos_dpi_probe(struct device *dev);
 int exynos_dpi_remove(struct drm_encoder *encoder);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index 6d29777884f9..781b82c2c579 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -1479,7 +1479,7 @@ static int exynos_dsi_create_connector(struct drm_encoder *encoder)
 
 	connector->status = connector_status_disconnected;
 	drm_connector_helper_add(connector, &exynos_dsi_connector_helper_funcs);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
@@ -1519,6 +1519,9 @@ static int exynos_dsi_host_attach(struct mipi_dsi_host *host,
 	dsi->format = device->format;
 	dsi->mode_flags = device->mode_flags;
 	dsi->panel = of_drm_find_panel(device->dev.of_node);
+	if (IS_ERR(dsi->panel))
+		dsi->panel = NULL;
+
 	if (dsi->panel) {
 		drm_panel_attach(dsi->panel, &dsi->connector);
 		dsi->connector.status = connector_status_connected;
@@ -1860,6 +1863,8 @@ err_clk:
 
 static const struct dev_pm_ops exynos_dsi_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos_dsi_suspend, exynos_dsi_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 struct platform_driver dsi_driver = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.c b/drivers/gpu/drm/exynos/exynos_drm_fb.c
index 27b7d34d776c..9f52382e19ee 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fb.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fb.c
@@ -101,7 +101,6 @@ exynos_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 {
 	const struct drm_format_info *info = drm_get_format_info(dev, mode_cmd);
 	struct exynos_drm_gem *exynos_gem[MAX_FB_BUFFER];
-	struct drm_gem_object *obj;
 	struct drm_framebuffer *fb;
 	int i;
 	int ret;
@@ -112,15 +111,14 @@ exynos_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 		unsigned long size = height * mode_cmd->pitches[i] +
 				     mode_cmd->offsets[i];
 
-		obj = drm_gem_object_lookup(file_priv, mode_cmd->handles[i]);
-		if (!obj) {
+		exynos_gem[i] = exynos_drm_gem_get(file_priv,
+						   mode_cmd->handles[i]);
+		if (!exynos_gem[i]) {
 			DRM_ERROR("failed to lookup gem object\n");
 			ret = -ENOENT;
 			goto err;
 		}
 
-		exynos_gem[i] = to_exynos_gem(obj);
-
 		if (size > exynos_gem[i]->size) {
 			i++;
 			ret = -EINVAL;
@@ -138,7 +136,7 @@ exynos_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 
 err:
 	while (i--)
-		drm_gem_object_put_unlocked(&exynos_gem[i]->base);
+		exynos_drm_gem_put(exynos_gem[i]);
 
 	return ERR_PTR(ret);
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 01b1570d0c3a..b7f56935a46b 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -1192,6 +1192,8 @@ static int exynos_fimd_resume(struct device *dev)
 
 static const struct dev_pm_ops exynos_fimd_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos_fimd_suspend, exynos_fimd_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 struct platform_driver fimd_driver = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index f68ef1b3a28c..f2481a2014bb 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -9,6 +9,7 @@
 
 #include <linux/kernel.h>
 #include <linux/clk.h>
+#include <linux/component.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -190,7 +191,7 @@ struct g2d_buf_desc {
 struct g2d_buf_info {
 	unsigned int		map_nr;
 	enum g2d_reg_type	reg_types[MAX_REG_TYPE_NR];
-	unsigned long		handles[MAX_REG_TYPE_NR];
+	void			*obj[MAX_REG_TYPE_NR];
 	unsigned int		types[MAX_REG_TYPE_NR];
 	struct g2d_buf_desc	descs[MAX_REG_TYPE_NR];
 };
@@ -237,7 +238,7 @@ struct g2d_data {
 	int				irq;
 	struct workqueue_struct		*g2d_workq;
 	struct work_struct		runqueue_work;
-	struct exynos_drm_subdrv	subdrv;
+	struct drm_device		*drm_dev;
 	unsigned long			flags;
 
 	/* cmdlist */
@@ -268,14 +269,13 @@ static int g2d_init_cmdlist(struct g2d_data *g2d)
 {
 	struct device *dev = g2d->dev;
 	struct g2d_cmdlist_node *node = g2d->cmdlist_node;
-	struct exynos_drm_subdrv *subdrv = &g2d->subdrv;
 	int nr;
 	int ret;
 	struct g2d_buf_info *buf_info;
 
 	g2d->cmdlist_dma_attrs = DMA_ATTR_WRITE_COMBINE;
 
-	g2d->cmdlist_pool_virt = dma_alloc_attrs(to_dma_dev(subdrv->drm_dev),
+	g2d->cmdlist_pool_virt = dma_alloc_attrs(to_dma_dev(g2d->drm_dev),
 						G2D_CMDLIST_POOL_SIZE,
 						&g2d->cmdlist_pool, GFP_KERNEL,
 						g2d->cmdlist_dma_attrs);
@@ -308,7 +308,7 @@ static int g2d_init_cmdlist(struct g2d_data *g2d)
 	return 0;
 
 err:
-	dma_free_attrs(to_dma_dev(subdrv->drm_dev), G2D_CMDLIST_POOL_SIZE,
+	dma_free_attrs(to_dma_dev(g2d->drm_dev), G2D_CMDLIST_POOL_SIZE,
 			g2d->cmdlist_pool_virt,
 			g2d->cmdlist_pool, g2d->cmdlist_dma_attrs);
 	return ret;
@@ -316,12 +316,10 @@ err:
 
 static void g2d_fini_cmdlist(struct g2d_data *g2d)
 {
-	struct exynos_drm_subdrv *subdrv = &g2d->subdrv;
-
 	kfree(g2d->cmdlist_node);
 
 	if (g2d->cmdlist_pool_virt && g2d->cmdlist_pool) {
-		dma_free_attrs(to_dma_dev(subdrv->drm_dev),
+		dma_free_attrs(to_dma_dev(g2d->drm_dev),
 				G2D_CMDLIST_POOL_SIZE,
 				g2d->cmdlist_pool_virt,
 				g2d->cmdlist_pool, g2d->cmdlist_dma_attrs);
@@ -355,32 +353,31 @@ static void g2d_put_cmdlist(struct g2d_data *g2d, struct g2d_cmdlist_node *node)
 	mutex_unlock(&g2d->cmdlist_mutex);
 }
 
-static void g2d_add_cmdlist_to_inuse(struct exynos_drm_g2d_private *g2d_priv,
+static void g2d_add_cmdlist_to_inuse(struct drm_exynos_file_private *file_priv,
 				     struct g2d_cmdlist_node *node)
 {
 	struct g2d_cmdlist_node *lnode;
 
-	if (list_empty(&g2d_priv->inuse_cmdlist))
+	if (list_empty(&file_priv->inuse_cmdlist))
 		goto add_to_list;
 
 	/* this links to base address of new cmdlist */
-	lnode = list_entry(g2d_priv->inuse_cmdlist.prev,
+	lnode = list_entry(file_priv->inuse_cmdlist.prev,
 				struct g2d_cmdlist_node, list);
 	lnode->cmdlist->data[lnode->cmdlist->last] = node->dma_addr;
 
 add_to_list:
-	list_add_tail(&node->list, &g2d_priv->inuse_cmdlist);
+	list_add_tail(&node->list, &file_priv->inuse_cmdlist);
 
 	if (node->event)
-		list_add_tail(&node->event->base.link, &g2d_priv->event_list);
+		list_add_tail(&node->event->base.link, &file_priv->event_list);
 }
 
-static void g2d_userptr_put_dma_addr(struct drm_device *drm_dev,
-					unsigned long obj,
+static void g2d_userptr_put_dma_addr(struct g2d_data *g2d,
+					void *obj,
 					bool force)
 {
-	struct g2d_cmdlist_userptr *g2d_userptr =
-					(struct g2d_cmdlist_userptr *)obj;
+	struct g2d_cmdlist_userptr *g2d_userptr = obj;
 	struct page **pages;
 
 	if (!obj)
@@ -398,7 +395,7 @@ static void g2d_userptr_put_dma_addr(struct drm_device *drm_dev,
 		return;
 
 out:
-	dma_unmap_sg(to_dma_dev(drm_dev), g2d_userptr->sgt->sgl,
+	dma_unmap_sg(to_dma_dev(g2d->drm_dev), g2d_userptr->sgt->sgl,
 			g2d_userptr->sgt->nents, DMA_BIDIRECTIONAL);
 
 	pages = frame_vector_pages(g2d_userptr->vec);
@@ -419,16 +416,14 @@ out:
 	kfree(g2d_userptr);
 }
 
-static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
+static dma_addr_t *g2d_userptr_get_dma_addr(struct g2d_data *g2d,
 					unsigned long userptr,
 					unsigned long size,
 					struct drm_file *filp,
-					unsigned long *obj)
+					void **obj)
 {
 	struct drm_exynos_file_private *file_priv = filp->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
 	struct g2d_cmdlist_userptr *g2d_userptr;
-	struct g2d_data *g2d;
 	struct sg_table	*sgt;
 	unsigned long start, end;
 	unsigned int npages, offset;
@@ -439,10 +434,8 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
 		return ERR_PTR(-EINVAL);
 	}
 
-	g2d = dev_get_drvdata(g2d_priv->dev);
-
 	/* check if userptr already exists in userptr_list. */
-	list_for_each_entry(g2d_userptr, &g2d_priv->userptr_list, list) {
+	list_for_each_entry(g2d_userptr, &file_priv->userptr_list, list) {
 		if (g2d_userptr->userptr == userptr) {
 			/*
 			 * also check size because there could be same address
@@ -450,7 +443,7 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
 			 */
 			if (g2d_userptr->size == size) {
 				atomic_inc(&g2d_userptr->refcount);
-				*obj = (unsigned long)g2d_userptr;
+				*obj = g2d_userptr;
 
 				return &g2d_userptr->dma_addr;
 			}
@@ -517,7 +510,7 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
 
 	g2d_userptr->sgt = sgt;
 
-	if (!dma_map_sg(to_dma_dev(drm_dev), sgt->sgl, sgt->nents,
+	if (!dma_map_sg(to_dma_dev(g2d->drm_dev), sgt->sgl, sgt->nents,
 				DMA_BIDIRECTIONAL)) {
 		DRM_ERROR("failed to map sgt with dma region.\n");
 		ret = -ENOMEM;
@@ -527,14 +520,14 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
 	g2d_userptr->dma_addr = sgt->sgl[0].dma_address;
 	g2d_userptr->userptr = userptr;
 
-	list_add_tail(&g2d_userptr->list, &g2d_priv->userptr_list);
+	list_add_tail(&g2d_userptr->list, &file_priv->userptr_list);
 
 	if (g2d->current_pool + (npages << PAGE_SHIFT) < g2d->max_pool) {
 		g2d->current_pool += npages << PAGE_SHIFT;
 		g2d_userptr->in_pool = true;
 	}
 
-	*obj = (unsigned long)g2d_userptr;
+	*obj = g2d_userptr;
 
 	return &g2d_userptr->dma_addr;
 
@@ -556,19 +549,14 @@ err_free:
 	return ERR_PTR(ret);
 }
 
-static void g2d_userptr_free_all(struct drm_device *drm_dev,
-					struct g2d_data *g2d,
-					struct drm_file *filp)
+static void g2d_userptr_free_all(struct g2d_data *g2d, struct drm_file *filp)
 {
 	struct drm_exynos_file_private *file_priv = filp->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
 	struct g2d_cmdlist_userptr *g2d_userptr, *n;
 
-	list_for_each_entry_safe(g2d_userptr, n, &g2d_priv->userptr_list, list)
+	list_for_each_entry_safe(g2d_userptr, n, &file_priv->userptr_list, list)
 		if (g2d_userptr->in_pool)
-			g2d_userptr_put_dma_addr(drm_dev,
-						(unsigned long)g2d_userptr,
-						true);
+			g2d_userptr_put_dma_addr(g2d, g2d_userptr, true);
 
 	g2d->current_pool = 0;
 }
@@ -723,26 +711,23 @@ static int g2d_map_cmdlist_gem(struct g2d_data *g2d,
 		buf_desc = &buf_info->descs[reg_type];
 
 		if (buf_info->types[reg_type] == BUF_TYPE_GEM) {
-			unsigned long size;
+			struct exynos_drm_gem *exynos_gem;
 
-			size = exynos_drm_gem_get_size(drm_dev, handle, file);
-			if (!size) {
+			exynos_gem = exynos_drm_gem_get(file, handle);
+			if (!exynos_gem) {
 				ret = -EFAULT;
 				goto err;
 			}
 
-			if (!g2d_check_buf_desc_is_valid(buf_desc, reg_type,
-									size)) {
+			if (!g2d_check_buf_desc_is_valid(buf_desc,
+							 reg_type, exynos_gem->size)) {
+				exynos_drm_gem_put(exynos_gem);
 				ret = -EFAULT;
 				goto err;
 			}
 
-			addr = exynos_drm_gem_get_dma_addr(drm_dev, handle,
-								file);
-			if (IS_ERR(addr)) {
-				ret = -EFAULT;
-				goto err;
-			}
+			addr = &exynos_gem->dma_addr;
+			buf_info->obj[reg_type] = exynos_gem;
 		} else {
 			struct drm_exynos_g2d_userptr g2d_userptr;
 
@@ -758,11 +743,11 @@ static int g2d_map_cmdlist_gem(struct g2d_data *g2d,
 				goto err;
 			}
 
-			addr = g2d_userptr_get_dma_addr(drm_dev,
+			addr = g2d_userptr_get_dma_addr(g2d,
 							g2d_userptr.userptr,
 							g2d_userptr.size,
 							file,
-							&handle);
+							&buf_info->obj[reg_type]);
 			if (IS_ERR(addr)) {
 				ret = -EFAULT;
 				goto err;
@@ -771,7 +756,6 @@ static int g2d_map_cmdlist_gem(struct g2d_data *g2d,
 
 		cmdlist->data[reg_pos + 1] = *addr;
 		buf_info->reg_types[i] = reg_type;
-		buf_info->handles[reg_type] = handle;
 	}
 
 	return 0;
@@ -785,29 +769,26 @@ static void g2d_unmap_cmdlist_gem(struct g2d_data *g2d,
 				  struct g2d_cmdlist_node *node,
 				  struct drm_file *filp)
 {
-	struct exynos_drm_subdrv *subdrv = &g2d->subdrv;
 	struct g2d_buf_info *buf_info = &node->buf_info;
 	int i;
 
 	for (i = 0; i < buf_info->map_nr; i++) {
 		struct g2d_buf_desc *buf_desc;
 		enum g2d_reg_type reg_type;
-		unsigned long handle;
+		void *obj;
 
 		reg_type = buf_info->reg_types[i];
 
 		buf_desc = &buf_info->descs[reg_type];
-		handle = buf_info->handles[reg_type];
+		obj = buf_info->obj[reg_type];
 
 		if (buf_info->types[reg_type] == BUF_TYPE_GEM)
-			exynos_drm_gem_put_dma_addr(subdrv->drm_dev, handle,
-							filp);
+			exynos_drm_gem_put(obj);
 		else
-			g2d_userptr_put_dma_addr(subdrv->drm_dev, handle,
-							false);
+			g2d_userptr_put_dma_addr(g2d, obj, false);
 
 		buf_info->reg_types[i] = REG_TYPE_NONE;
-		buf_info->handles[reg_type] = 0;
+		buf_info->obj[reg_type] = NULL;
 		buf_info->types[reg_type] = 0;
 		memset(buf_desc, 0x00, sizeof(*buf_desc));
 	}
@@ -922,7 +903,7 @@ static void g2d_runqueue_worker(struct work_struct *work)
 
 static void g2d_finish_event(struct g2d_data *g2d, u32 cmdlist_no)
 {
-	struct drm_device *drm_dev = g2d->subdrv.drm_dev;
+	struct drm_device *drm_dev = g2d->drm_dev;
 	struct g2d_runqueue_node *runqueue_node = g2d->runqueue_node;
 	struct drm_exynos_pending_g2d_event *e;
 	struct timespec64 now;
@@ -1031,7 +1012,7 @@ out:
 	mutex_unlock(&g2d->runqueue_mutex);
 }
 
-static int g2d_check_reg_offset(struct device *dev,
+static int g2d_check_reg_offset(struct g2d_data *g2d,
 				struct g2d_cmdlist_node *node,
 				int nr, bool for_addr)
 {
@@ -1131,7 +1112,7 @@ static int g2d_check_reg_offset(struct device *dev,
 	return 0;
 
 err:
-	dev_err(dev, "Bad register offset: 0x%lx\n", cmdlist->data[index]);
+	dev_err(g2d->dev, "Bad register offset: 0x%lx\n", cmdlist->data[index]);
 	return -EINVAL;
 }
 
@@ -1139,23 +1120,8 @@ err:
 int exynos_g2d_get_ver_ioctl(struct drm_device *drm_dev, void *data,
 			     struct drm_file *file)
 {
-	struct drm_exynos_file_private *file_priv = file->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
-	struct device *dev;
-	struct g2d_data *g2d;
 	struct drm_exynos_g2d_get_ver *ver = data;
 
-	if (!g2d_priv)
-		return -ENODEV;
-
-	dev = g2d_priv->dev;
-	if (!dev)
-		return -ENODEV;
-
-	g2d = dev_get_drvdata(dev);
-	if (!g2d)
-		return -EFAULT;
-
 	ver->major = G2D_HW_MAJOR_VER;
 	ver->minor = G2D_HW_MINOR_VER;
 
@@ -1166,9 +1132,8 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 				 struct drm_file *file)
 {
 	struct drm_exynos_file_private *file_priv = file->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
-	struct device *dev;
-	struct g2d_data *g2d;
+	struct exynos_drm_private *priv = drm_dev->dev_private;
+	struct g2d_data *g2d = dev_get_drvdata(priv->g2d_dev);
 	struct drm_exynos_g2d_set_cmdlist *req = data;
 	struct drm_exynos_g2d_cmd *cmd;
 	struct drm_exynos_pending_g2d_event *e;
@@ -1177,17 +1142,6 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 	int size;
 	int ret;
 
-	if (!g2d_priv)
-		return -ENODEV;
-
-	dev = g2d_priv->dev;
-	if (!dev)
-		return -ENODEV;
-
-	g2d = dev_get_drvdata(dev);
-	if (!g2d)
-		return -EFAULT;
-
 	node = g2d_get_cmdlist(g2d);
 	if (!node)
 		return -ENOMEM;
@@ -1199,7 +1153,7 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 	 */
 	if (req->cmd_nr > G2D_CMDLIST_DATA_NUM ||
 	    req->cmd_buf_nr > G2D_CMDLIST_DATA_NUM) {
-		dev_err(dev, "number of submitted G2D commands exceeds limit\n");
+		dev_err(g2d->dev, "number of submitted G2D commands exceeds limit\n");
 		return -EINVAL;
 	}
 
@@ -1267,7 +1221,7 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 	 */
 	size = cmdlist->last + req->cmd_nr * 2 + req->cmd_buf_nr * 2 + 2;
 	if (size > G2D_CMDLIST_DATA_NUM) {
-		dev_err(dev, "cmdlist size is too big\n");
+		dev_err(g2d->dev, "cmdlist size is too big\n");
 		ret = -EINVAL;
 		goto err_free_event;
 	}
@@ -1282,7 +1236,7 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 	}
 	cmdlist->last += req->cmd_nr * 2;
 
-	ret = g2d_check_reg_offset(dev, node, req->cmd_nr, false);
+	ret = g2d_check_reg_offset(g2d, node, req->cmd_nr, false);
 	if (ret < 0)
 		goto err_free_event;
 
@@ -1301,7 +1255,7 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 		}
 		cmdlist->last += req->cmd_buf_nr * 2;
 
-		ret = g2d_check_reg_offset(dev, node, req->cmd_buf_nr, true);
+		ret = g2d_check_reg_offset(g2d, node, req->cmd_buf_nr, true);
 		if (ret < 0)
 			goto err_free_event;
 
@@ -1319,7 +1273,7 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 	/* tail */
 	cmdlist->data[cmdlist->last] = 0;
 
-	g2d_add_cmdlist_to_inuse(g2d_priv, node);
+	g2d_add_cmdlist_to_inuse(file_priv, node);
 
 	return 0;
 
@@ -1337,25 +1291,13 @@ int exynos_g2d_exec_ioctl(struct drm_device *drm_dev, void *data,
 			  struct drm_file *file)
 {
 	struct drm_exynos_file_private *file_priv = file->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
-	struct device *dev;
-	struct g2d_data *g2d;
+	struct exynos_drm_private *priv = drm_dev->dev_private;
+	struct g2d_data *g2d = dev_get_drvdata(priv->g2d_dev);
 	struct drm_exynos_g2d_exec *req = data;
 	struct g2d_runqueue_node *runqueue_node;
 	struct list_head *run_cmdlist;
 	struct list_head *event_list;
 
-	if (!g2d_priv)
-		return -ENODEV;
-
-	dev = g2d_priv->dev;
-	if (!dev)
-		return -ENODEV;
-
-	g2d = dev_get_drvdata(dev);
-	if (!g2d)
-		return -EFAULT;
-
 	runqueue_node = kmem_cache_alloc(g2d->runqueue_slab, GFP_KERNEL);
 	if (!runqueue_node)
 		return -ENOMEM;
@@ -1367,11 +1309,11 @@ int exynos_g2d_exec_ioctl(struct drm_device *drm_dev, void *data,
 	init_completion(&runqueue_node->complete);
 	runqueue_node->async = req->async;
 
-	list_splice_init(&g2d_priv->inuse_cmdlist, run_cmdlist);
-	list_splice_init(&g2d_priv->event_list, event_list);
+	list_splice_init(&file_priv->inuse_cmdlist, run_cmdlist);
+	list_splice_init(&file_priv->event_list, event_list);
 
 	if (list_empty(run_cmdlist)) {
-		dev_err(dev, "there is no inuse cmdlist\n");
+		dev_err(g2d->dev, "there is no inuse cmdlist\n");
 		kmem_cache_free(g2d->runqueue_slab, runqueue_node);
 		return -EPERM;
 	}
@@ -1395,71 +1337,28 @@ out:
 	return 0;
 }
 
-static int g2d_subdrv_probe(struct drm_device *drm_dev, struct device *dev)
-{
-	struct g2d_data *g2d;
-	int ret;
-
-	g2d = dev_get_drvdata(dev);
-	if (!g2d)
-		return -EFAULT;
-
-	/* allocate dma-aware cmdlist buffer. */
-	ret = g2d_init_cmdlist(g2d);
-	if (ret < 0) {
-		dev_err(dev, "cmdlist init failed\n");
-		return ret;
-	}
-
-	ret = drm_iommu_attach_device(drm_dev, dev);
-	if (ret < 0) {
-		dev_err(dev, "failed to enable iommu.\n");
-		g2d_fini_cmdlist(g2d);
-	}
-
-	return ret;
-
-}
-
-static void g2d_subdrv_remove(struct drm_device *drm_dev, struct device *dev)
-{
-	drm_iommu_detach_device(drm_dev, dev);
-}
-
-static int g2d_open(struct drm_device *drm_dev, struct device *dev,
-			struct drm_file *file)
+int g2d_open(struct drm_device *drm_dev, struct drm_file *file)
 {
 	struct drm_exynos_file_private *file_priv = file->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv;
-
-	g2d_priv = kzalloc(sizeof(*g2d_priv), GFP_KERNEL);
-	if (!g2d_priv)
-		return -ENOMEM;
 
-	g2d_priv->dev = dev;
-	file_priv->g2d_priv = g2d_priv;
-
-	INIT_LIST_HEAD(&g2d_priv->inuse_cmdlist);
-	INIT_LIST_HEAD(&g2d_priv->event_list);
-	INIT_LIST_HEAD(&g2d_priv->userptr_list);
+	INIT_LIST_HEAD(&file_priv->inuse_cmdlist);
+	INIT_LIST_HEAD(&file_priv->event_list);
+	INIT_LIST_HEAD(&file_priv->userptr_list);
 
 	return 0;
 }
 
-static void g2d_close(struct drm_device *drm_dev, struct device *dev,
-			struct drm_file *file)
+void g2d_close(struct drm_device *drm_dev, struct drm_file *file)
 {
 	struct drm_exynos_file_private *file_priv = file->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
+	struct exynos_drm_private *priv = drm_dev->dev_private;
 	struct g2d_data *g2d;
 	struct g2d_cmdlist_node *node, *n;
 
-	if (!dev)
+	if (!priv->g2d_dev)
 		return;
 
-	g2d = dev_get_drvdata(dev);
-	if (!g2d)
-		return;
+	g2d = dev_get_drvdata(priv->g2d_dev);
 
 	/* Remove the runqueue nodes that belong to us. */
 	mutex_lock(&g2d->runqueue_mutex);
@@ -1480,24 +1379,70 @@ static void g2d_close(struct drm_device *drm_dev, struct device *dev,
 	 * Properly unmap these buffers here.
 	 */
 	mutex_lock(&g2d->cmdlist_mutex);
-	list_for_each_entry_safe(node, n, &g2d_priv->inuse_cmdlist, list) {
+	list_for_each_entry_safe(node, n, &file_priv->inuse_cmdlist, list) {
 		g2d_unmap_cmdlist_gem(g2d, node, file);
 		list_move_tail(&node->list, &g2d->free_cmdlist);
 	}
 	mutex_unlock(&g2d->cmdlist_mutex);
 
 	/* release all g2d_userptr in pool. */
-	g2d_userptr_free_all(drm_dev, g2d, file);
+	g2d_userptr_free_all(g2d, file);
+}
+
+static int g2d_bind(struct device *dev, struct device *master, void *data)
+{
+	struct g2d_data *g2d = dev_get_drvdata(dev);
+	struct drm_device *drm_dev = data;
+	struct exynos_drm_private *priv = drm_dev->dev_private;
+	int ret;
+
+	g2d->drm_dev = drm_dev;
 
-	kfree(file_priv->g2d_priv);
+	/* allocate dma-aware cmdlist buffer. */
+	ret = g2d_init_cmdlist(g2d);
+	if (ret < 0) {
+		dev_err(dev, "cmdlist init failed\n");
+		return ret;
+	}
+
+	ret = drm_iommu_attach_device(drm_dev, dev);
+	if (ret < 0) {
+		dev_err(dev, "failed to enable iommu.\n");
+		g2d_fini_cmdlist(g2d);
+		return ret;
+	}
+	priv->g2d_dev = dev;
+
+	dev_info(dev, "The Exynos G2D (ver %d.%d) successfully registered.\n",
+			G2D_HW_MAJOR_VER, G2D_HW_MINOR_VER);
+	return 0;
+}
+
+static void g2d_unbind(struct device *dev, struct device *master, void *data)
+{
+	struct g2d_data *g2d = dev_get_drvdata(dev);
+	struct drm_device *drm_dev = data;
+	struct exynos_drm_private *priv = drm_dev->dev_private;
+
+	/* Suspend operation and wait for engine idle. */
+	set_bit(G2D_BIT_SUSPEND_RUNQUEUE, &g2d->flags);
+	g2d_wait_finish(g2d, NULL);
+	priv->g2d_dev = NULL;
+
+	cancel_work_sync(&g2d->runqueue_work);
+	drm_iommu_detach_device(g2d->drm_dev, dev);
 }
 
+static const struct component_ops g2d_component_ops = {
+	.bind	= g2d_bind,
+	.unbind = g2d_unbind,
+};
+
 static int g2d_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct resource *res;
 	struct g2d_data *g2d;
-	struct exynos_drm_subdrv *subdrv;
 	int ret;
 
 	g2d = devm_kzalloc(dev, sizeof(*g2d), GFP_KERNEL);
@@ -1564,22 +1509,12 @@ static int g2d_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, g2d);
 
-	subdrv = &g2d->subdrv;
-	subdrv->dev = dev;
-	subdrv->probe = g2d_subdrv_probe;
-	subdrv->remove = g2d_subdrv_remove;
-	subdrv->open = g2d_open;
-	subdrv->close = g2d_close;
-
-	ret = exynos_drm_subdrv_register(subdrv);
+	ret = component_add(dev, &g2d_component_ops);
 	if (ret < 0) {
 		dev_err(dev, "failed to register drm g2d device\n");
 		goto err_put_clk;
 	}
 
-	dev_info(dev, "The Exynos G2D (ver %d.%d) successfully probed.\n",
-			G2D_HW_MAJOR_VER, G2D_HW_MINOR_VER);
-
 	return 0;
 
 err_put_clk:
@@ -1595,12 +1530,7 @@ static int g2d_remove(struct platform_device *pdev)
 {
 	struct g2d_data *g2d = platform_get_drvdata(pdev);
 
-	/* Suspend operation and wait for engine idle. */
-	set_bit(G2D_BIT_SUSPEND_RUNQUEUE, &g2d->flags);
-	g2d_wait_finish(g2d, NULL);
-
-	cancel_work_sync(&g2d->runqueue_work);
-	exynos_drm_subdrv_unregister(&g2d->subdrv);
+	component_del(&pdev->dev, &g2d_component_ops);
 
 	/* There should be no locking needed here. */
 	g2d_remove_runqueue_nodes(g2d, NULL);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.h b/drivers/gpu/drm/exynos/exynos_drm_g2d.h
index 1a9c7ca8c15b..287b2ed8f178 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.h
@@ -14,6 +14,9 @@ extern int exynos_g2d_set_cmdlist_ioctl(struct drm_device *dev, void *data,
 					struct drm_file *file_priv);
 extern int exynos_g2d_exec_ioctl(struct drm_device *dev, void *data,
 				 struct drm_file *file_priv);
+
+extern int g2d_open(struct drm_device *drm_dev, struct drm_file *file);
+extern void g2d_close(struct drm_device *drm_dev, struct drm_file *file);
 #else
 static inline int exynos_g2d_get_ver_ioctl(struct drm_device *dev, void *data,
 					   struct drm_file *file_priv)
@@ -33,4 +36,12 @@ static inline int exynos_g2d_exec_ioctl(struct drm_device *dev, void *data,
 {
 	return -ENODEV;
 }
+
+int g2d_open(struct drm_device *drm_dev, struct drm_file *file)
+{
+	return 0;
+}
+
+void g2d_close(struct drm_device *drm_dev, struct drm_file *file)
+{ }
 #endif
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index bdf5a7655228..34ace85feb68 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -171,26 +171,6 @@ void exynos_drm_gem_destroy(struct exynos_drm_gem *exynos_gem)
 	kfree(exynos_gem);
 }
 
-unsigned long exynos_drm_gem_get_size(struct drm_device *dev,
-						unsigned int gem_handle,
-						struct drm_file *file_priv)
-{
-	struct exynos_drm_gem *exynos_gem;
-	struct drm_gem_object *obj;
-
-	obj = drm_gem_object_lookup(file_priv, gem_handle);
-	if (!obj) {
-		DRM_ERROR("failed to lookup gem object.\n");
-		return 0;
-	}
-
-	exynos_gem = to_exynos_gem(obj);
-
-	drm_gem_object_put_unlocked(obj);
-
-	return exynos_gem->size;
-}
-
 static struct exynos_drm_gem *exynos_drm_gem_init(struct drm_device *dev,
 						  unsigned long size)
 {
@@ -299,43 +279,15 @@ int exynos_drm_gem_map_ioctl(struct drm_device *dev, void *data,
 				       &args->offset);
 }
 
-dma_addr_t *exynos_drm_gem_get_dma_addr(struct drm_device *dev,
-					unsigned int gem_handle,
-					struct drm_file *filp)
+struct exynos_drm_gem *exynos_drm_gem_get(struct drm_file *filp,
+					  unsigned int gem_handle)
 {
-	struct exynos_drm_gem *exynos_gem;
 	struct drm_gem_object *obj;
 
 	obj = drm_gem_object_lookup(filp, gem_handle);
-	if (!obj) {
-		DRM_ERROR("failed to lookup gem object.\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	exynos_gem = to_exynos_gem(obj);
-
-	return &exynos_gem->dma_addr;
-}
-
-void exynos_drm_gem_put_dma_addr(struct drm_device *dev,
-					unsigned int gem_handle,
-					struct drm_file *filp)
-{
-	struct drm_gem_object *obj;
-
-	obj = drm_gem_object_lookup(filp, gem_handle);
-	if (!obj) {
-		DRM_ERROR("failed to lookup gem object.\n");
-		return;
-	}
-
-	drm_gem_object_put_unlocked(obj);
-
-	/*
-	 * decrease obj->refcount one more time because we has already
-	 * increased it at exynos_drm_gem_get_dma_addr().
-	 */
-	drm_gem_object_put_unlocked(obj);
+	if (!obj)
+		return NULL;
+	return to_exynos_gem(obj);
 }
 
 static int exynos_drm_gem_mmap_buffer(struct exynos_drm_gem *exynos_gem,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h
index 9057d7f1d6ed..d46a62c30812 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h
@@ -77,32 +77,26 @@ int exynos_drm_gem_map_ioctl(struct drm_device *dev, void *data,
 			     struct drm_file *file_priv);
 
 /*
- * get dma address from gem handle and this function could be used for
+ * get exynos drm object from gem handle, this function could be used for
  * other drivers such as 2d/3d acceleration drivers.
  * with this function call, gem object reference count would be increased.
  */
-dma_addr_t *exynos_drm_gem_get_dma_addr(struct drm_device *dev,
-					unsigned int gem_handle,
-					struct drm_file *filp);
+struct exynos_drm_gem *exynos_drm_gem_get(struct drm_file *filp,
+					  unsigned int gem_handle);
 
 /*
- * put dma address from gem handle and this function could be used for
- * other drivers such as 2d/3d acceleration drivers.
- * with this function call, gem object reference count would be decreased.
+ * put exynos drm object acquired from exynos_drm_gem_get(),
+ * gem object reference count would be decreased.
  */
-void exynos_drm_gem_put_dma_addr(struct drm_device *dev,
-					unsigned int gem_handle,
-					struct drm_file *filp);
+static inline void exynos_drm_gem_put(struct exynos_drm_gem *exynos_gem)
+{
+	drm_gem_object_put_unlocked(&exynos_gem->base);
+}
 
 /* get buffer information to memory region allocated by gem. */
 int exynos_drm_gem_get_ioctl(struct drm_device *dev, void *data,
 				      struct drm_file *file_priv);
 
-/* get buffer size to gem handle. */
-unsigned long exynos_drm_gem_get_size(struct drm_device *dev,
-						unsigned int gem_handle,
-						struct drm_file *file_priv);
-
 /* free gem object. */
 void exynos_drm_gem_free_object(struct drm_gem_object *obj);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
index b435db8fc916..23226a0212e8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
@@ -350,13 +350,13 @@ static int exynos_drm_ipp_task_setup_buffer(struct exynos_drm_ipp_buffer *buf,
 		unsigned int height = (i == 0) ? buf->buf.height :
 			     DIV_ROUND_UP(buf->buf.height, buf->format->vsub);
 		unsigned long size = height * buf->buf.pitch[i];
-		struct drm_gem_object *obj = drm_gem_object_lookup(filp,
+		struct exynos_drm_gem *gem = exynos_drm_gem_get(filp,
 							    buf->buf.gem_id[i]);
-		if (!obj) {
+		if (!gem) {
 			ret = -ENOENT;
 			goto gem_free;
 		}
-		buf->exynos_gem[i] = to_exynos_gem(obj);
+		buf->exynos_gem[i] = gem;
 
 		if (size + buf->buf.offset[i] > buf->exynos_gem[i]->size) {
 			i++;
@@ -370,7 +370,7 @@ static int exynos_drm_ipp_task_setup_buffer(struct exynos_drm_ipp_buffer *buf,
 	return 0;
 gem_free:
 	while (i--) {
-		drm_gem_object_put_unlocked(&buf->exynos_gem[i]->base);
+		exynos_drm_gem_put(buf->exynos_gem[i]);
 		buf->exynos_gem[i] = NULL;
 	}
 	return ret;
@@ -383,7 +383,7 @@ static void exynos_drm_ipp_task_release_buf(struct exynos_drm_ipp_buffer *buf)
 	if (!buf->exynos_gem[0])
 		return;
 	for (i = 0; i < buf->format->num_planes; i++)
-		drm_gem_object_put_unlocked(&buf->exynos_gem[i]->base);
+		exynos_drm_gem_put(buf->exynos_gem[i]);
 }
 
 static void exynos_drm_ipp_task_free(struct exynos_drm_ipp *ipp,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c
index 2174814273e2..2fd299a58297 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_mic.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c
@@ -367,6 +367,8 @@ static int exynos_mic_resume(struct device *dev)
 
 static const struct dev_pm_ops exynos_mic_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos_mic_suspend, exynos_mic_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 static int exynos_mic_probe(struct platform_device *pdev)
diff --git a/drivers/gpu/drm/exynos/exynos_drm_plane.c b/drivers/gpu/drm/exynos/exynos_drm_plane.c
index 7098c6d35266..dba29aec59b4 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_plane.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_plane.c
@@ -263,8 +263,6 @@ static void exynos_plane_atomic_update(struct drm_plane *plane,
 	if (!state->crtc)
 		return;
 
-	plane->crtc = state->crtc;
-
 	if (exynos_crtc->ops->update_plane)
 		exynos_crtc->ops->update_plane(exynos_crtc, exynos_plane);
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index e6b0940b1ac2..19697c1362d8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -319,7 +319,7 @@ static int vidi_get_modes(struct drm_connector *connector)
 		return -ENOMEM;
 	}
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 
 	return drm_add_edid_modes(connector, edid);
 }
@@ -344,7 +344,7 @@ static int vidi_create_connector(struct drm_encoder *encoder)
 	}
 
 	drm_connector_helper_add(connector, &vidi_connector_helper_funcs);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index db91932550cf..2092a650df7d 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -888,7 +888,7 @@ static int hdmi_get_modes(struct drm_connector *connector)
 		(hdata->dvi_mode ? "dvi monitor" : "hdmi monitor"),
 		edid->width_cm, edid->height_cm);
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	cec_notifier_set_phys_addr_from_edid(hdata->notifier, edid);
 
 	ret = drm_add_edid_modes(connector, edid);
@@ -951,7 +951,7 @@ static int hdmi_create_connector(struct drm_encoder *encoder)
 	}
 
 	drm_connector_helper_add(connector, &hdmi_connector_helper_funcs);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	if (hdata->bridge) {
 		ret = drm_bridge_attach(encoder, hdata->bridge, NULL);
@@ -2093,6 +2093,8 @@ static int __maybe_unused exynos_hdmi_resume(struct device *dev)
 
 static const struct dev_pm_ops exynos_hdmi_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos_hdmi_suspend, exynos_hdmi_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 struct platform_driver hdmi_driver = {
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index 272c79f5f5bf..ffbf4a950f69 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -837,8 +837,6 @@ static int mixer_initialize(struct mixer_context *mixer_ctx,
 			struct drm_device *drm_dev)
 {
 	int ret;
-	struct exynos_drm_private *priv;
-	priv = drm_dev->dev_private;
 
 	mixer_ctx->drm_dev = drm_dev;
 
@@ -1271,6 +1269,8 @@ static int __maybe_unused exynos_mixer_resume(struct device *dev)
 
 static const struct dev_pm_ops exynos_mixer_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos_mixer_suspend, exynos_mixer_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 struct platform_driver mixer_driver = {
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
index c54806d08dd7..2298ed2a9e1c 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
@@ -117,7 +117,7 @@ static int fsl_dcu_attach_panel(struct fsl_dcu_drm_device *fsl_dev,
 	if (ret < 0)
 		goto err_cleanup;
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret < 0)
 		goto err_sysfs;
 
@@ -148,8 +148,9 @@ int fsl_dcu_create_outputs(struct fsl_dcu_drm_device *fsl_dev)
 	if (panel_node) {
 		fsl_dev->connector.panel = of_drm_find_panel(panel_node);
 		of_node_put(panel_node);
-		if (!fsl_dev->connector.panel)
-			return -EPROBE_DEFER;
+		if (IS_ERR(fsl_dev->connector.panel))
+			return PTR_ERR(fsl_dev->connector.panel);
+
 		return fsl_dcu_attach_panel(fsl_dev, fsl_dev->connector.panel);
 	}
 
diff --git a/drivers/gpu/drm/gma500/accel_2d.c b/drivers/gpu/drm/gma500/accel_2d.c
index c51d9259c7a7..204c8e452eb7 100644
--- a/drivers/gpu/drm/gma500/accel_2d.c
+++ b/drivers/gpu/drm/gma500/accel_2d.c
@@ -251,7 +251,7 @@ static void psbfb_copyarea_accel(struct fb_info *info,
 	if (!fb)
 		return;
 
-	offset = psbfb->gtt->offset;
+	offset = to_gtt_range(fb->obj[0])->offset;
 	stride = fb->pitches[0];
 
 	switch (fb->format->depth) {
diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c
index 5ea785f07ba8..90ed20083009 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_dp.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c
@@ -1770,7 +1770,7 @@ static int cdv_intel_dp_get_modes(struct drm_connector *connector)
 
 	edid = drm_get_edid(connector, &intel_dp->adapter);
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 	}
diff --git a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c
index f0878998526a..4e4e4a66eaee 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c
@@ -216,7 +216,7 @@ static int cdv_hdmi_get_modes(struct drm_connector *connector)
 
 	edid = drm_get_edid(connector, &gma_encoder->i2c_bus->adapter);
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 	}
diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c
index cb0a2ae916e0..2f00a37684a2 100644
--- a/drivers/gpu/drm/gma500/framebuffer.c
+++ b/drivers/gpu/drm/gma500/framebuffer.c
@@ -33,6 +33,7 @@
 #include <drm/drm.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_fb_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 
 #include "psb_drv.h"
 #include "psb_intel_reg.h"
@@ -40,14 +41,9 @@
 #include "framebuffer.h"
 #include "gtt.h"
 
-static void psb_user_framebuffer_destroy(struct drm_framebuffer *fb);
-static int psb_user_framebuffer_create_handle(struct drm_framebuffer *fb,
-					      struct drm_file *file_priv,
-					      unsigned int *handle);
-
 static const struct drm_framebuffer_funcs psb_fb_funcs = {
-	.destroy = psb_user_framebuffer_destroy,
-	.create_handle = psb_user_framebuffer_create_handle,
+	.destroy = drm_gem_fb_destroy,
+	.create_handle = drm_gem_fb_create_handle,
 };
 
 #define CMAP_TOHW(_val, _width) ((((_val) << (_width)) + 0x7FFF - (_val)) >> 16)
@@ -96,17 +92,18 @@ static int psbfb_pan(struct fb_var_screeninfo *var, struct fb_info *info)
 	struct psb_fbdev *fbdev = info->par;
 	struct psb_framebuffer *psbfb = &fbdev->pfb;
 	struct drm_device *dev = psbfb->base.dev;
+	struct gtt_range *gtt = to_gtt_range(psbfb->base.obj[0]);
 
 	/*
 	 *	We have to poke our nose in here. The core fb code assumes
 	 *	panning is part of the hardware that can be invoked before
 	 *	the actual fb is mapped. In our case that isn't quite true.
 	 */
-	if (psbfb->gtt->npage) {
+	if (gtt->npage) {
 		/* GTT roll shifts in 4K pages, we need to shift the right
 		   number of pages */
 		int pages = info->fix.line_length >> 12;
-		psb_gtt_roll(dev, psbfb->gtt, var->yoffset * pages);
+		psb_gtt_roll(dev, gtt, var->yoffset * pages);
 	}
         return 0;
 }
@@ -117,13 +114,14 @@ static int psbfb_vm_fault(struct vm_fault *vmf)
 	struct psb_framebuffer *psbfb = vma->vm_private_data;
 	struct drm_device *dev = psbfb->base.dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
+	struct gtt_range *gtt = to_gtt_range(psbfb->base.obj[0]);
 	int page_num;
 	int i;
 	unsigned long address;
 	int ret;
 	unsigned long pfn;
 	unsigned long phys_addr = (unsigned long)dev_priv->stolen_base +
-				  psbfb->gtt->offset;
+				  gtt->offset;
 
 	page_num = vma_pages(vma);
 	address = vmf->address - (vmf->pgoff << PAGE_SHIFT);
@@ -246,7 +244,7 @@ static int psb_framebuffer_init(struct drm_device *dev,
 		return -EINVAL;
 
 	drm_helper_mode_fill_fb_struct(dev, &fb->base, mode_cmd);
-	fb->gtt = gt;
+	fb->base.obj[0] = &gt->gem;
 	ret = drm_framebuffer_init(dev, &fb->base, &psb_fb_funcs);
 	if (ret) {
 		dev_err(dev->dev, "framebuffer init failed: %d\n", ret);
@@ -518,8 +516,8 @@ static int psb_fbdev_destroy(struct drm_device *dev, struct psb_fbdev *fbdev)
 	drm_framebuffer_unregister_private(&psbfb->base);
 	drm_framebuffer_cleanup(&psbfb->base);
 
-	if (psbfb->gtt)
-		drm_gem_object_unreference_unlocked(&psbfb->gtt->gem);
+	if (psbfb->base.obj[0])
+		drm_gem_object_put_unlocked(psbfb->base.obj[0]);
 	return 0;
 }
 
@@ -576,44 +574,6 @@ static void psb_fbdev_fini(struct drm_device *dev)
 	dev_priv->fbdev = NULL;
 }
 
-/**
- *	psb_user_framebuffer_create_handle - add hamdle to a framebuffer
- *	@fb: framebuffer
- *	@file_priv: our DRM file
- *	@handle: returned handle
- *
- *	Our framebuffer object is a GTT range which also contains a GEM
- *	object. We need to turn it into a handle for userspace. GEM will do
- *	the work for us
- */
-static int psb_user_framebuffer_create_handle(struct drm_framebuffer *fb,
-					      struct drm_file *file_priv,
-					      unsigned int *handle)
-{
-	struct psb_framebuffer *psbfb = to_psb_fb(fb);
-	struct gtt_range *r = psbfb->gtt;
-	return drm_gem_handle_create(file_priv, &r->gem, handle);
-}
-
-/**
- *	psb_user_framebuffer_destroy	-	destruct user created fb
- *	@fb: framebuffer
- *
- *	User framebuffers are backed by GEM objects so all we have to do is
- *	clean up a bit and drop the reference, GEM will handle the fallout
- */
-static void psb_user_framebuffer_destroy(struct drm_framebuffer *fb)
-{
-	struct psb_framebuffer *psbfb = to_psb_fb(fb);
-	struct gtt_range *r = psbfb->gtt;
-
-	/* Let DRM do its clean up */
-	drm_framebuffer_cleanup(fb);
-	/*  We are no longer using the resource in GEM */
-	drm_gem_object_unreference_unlocked(&r->gem);
-	kfree(fb);
-}
-
 static const struct drm_mode_config_funcs psb_mode_funcs = {
 	.fb_create = psb_user_framebuffer_create,
 	.output_poll_changed = drm_fb_helper_output_poll_changed,
diff --git a/drivers/gpu/drm/gma500/framebuffer.h b/drivers/gpu/drm/gma500/framebuffer.h
index 395f20b07aab..23dc3c5f8f0d 100644
--- a/drivers/gpu/drm/gma500/framebuffer.h
+++ b/drivers/gpu/drm/gma500/framebuffer.h
@@ -31,7 +31,6 @@ struct psb_framebuffer {
 	struct drm_framebuffer base;
 	struct address_space *addr_space;
 	struct fb_info *fbdev;
-	struct gtt_range *gtt;
 };
 
 struct psb_fbdev {
diff --git a/drivers/gpu/drm/gma500/gem.c b/drivers/gpu/drm/gma500/gem.c
index 131239759a75..913bf4c256fa 100644
--- a/drivers/gpu/drm/gma500/gem.c
+++ b/drivers/gpu/drm/gma500/gem.c
@@ -93,7 +93,7 @@ int psb_gem_create(struct drm_file *file, struct drm_device *dev, u64 size,
 		return ret;
 	}
 	/* We have the initial and handle reference but need only one now */
-	drm_gem_object_unreference_unlocked(&r->gem);
+	drm_gem_object_put_unlocked(&r->gem);
 	*handlep = handle;
 	return 0;
 }
diff --git a/drivers/gpu/drm/gma500/gma_display.c b/drivers/gpu/drm/gma500/gma_display.c
index f3c48a2be71b..09c1161a7ac6 100644
--- a/drivers/gpu/drm/gma500/gma_display.c
+++ b/drivers/gpu/drm/gma500/gma_display.c
@@ -60,7 +60,7 @@ int gma_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	struct drm_framebuffer *fb = crtc->primary->fb;
-	struct psb_framebuffer *psbfb = to_psb_fb(fb);
+	struct gtt_range *gtt;
 	int pipe = gma_crtc->pipe;
 	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	unsigned long start, offset;
@@ -76,12 +76,14 @@ int gma_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 		goto gma_pipe_cleaner;
 	}
 
+	gtt = to_gtt_range(fb->obj[0]);
+
 	/* We are displaying this buffer, make sure it is actually loaded
 	   into the GTT */
-	ret = psb_gtt_pin(psbfb->gtt);
+	ret = psb_gtt_pin(gtt);
 	if (ret < 0)
 		goto gma_pipe_set_base_exit;
-	start = psbfb->gtt->offset;
+	start = gtt->offset;
 	offset = y * fb->pitches[0] + x * fb->format->cpp[0];
 
 	REG_WRITE(map->stride, fb->pitches[0]);
@@ -129,7 +131,7 @@ int gma_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 gma_pipe_cleaner:
 	/* If there was a previous display we can now unpin it */
 	if (old_fb)
-		psb_gtt_unpin(to_psb_fb(old_fb)->gtt);
+		psb_gtt_unpin(to_gtt_range(old_fb->obj[0]));
 
 gma_pipe_set_base_exit:
 	gma_power_end(dev);
@@ -353,7 +355,7 @@ int gma_crtc_cursor_set(struct drm_crtc *crtc,
 			gt = container_of(gma_crtc->cursor_obj,
 					  struct gtt_range, gem);
 			psb_gtt_unpin(gt);
-			drm_gem_object_unreference_unlocked(gma_crtc->cursor_obj);
+			drm_gem_object_put_unlocked(gma_crtc->cursor_obj);
 			gma_crtc->cursor_obj = NULL;
 		}
 		return 0;
@@ -429,7 +431,7 @@ int gma_crtc_cursor_set(struct drm_crtc *crtc,
 	if (gma_crtc->cursor_obj) {
 		gt = container_of(gma_crtc->cursor_obj, struct gtt_range, gem);
 		psb_gtt_unpin(gt);
-		drm_gem_object_unreference_unlocked(gma_crtc->cursor_obj);
+		drm_gem_object_put_unlocked(gma_crtc->cursor_obj);
 	}
 
 	gma_crtc->cursor_obj = obj;
@@ -437,7 +439,7 @@ unlock:
 	return ret;
 
 unref_cursor:
-	drm_gem_object_unreference_unlocked(obj);
+	drm_gem_object_put_unlocked(obj);
 	return ret;
 }
 
@@ -491,7 +493,7 @@ void gma_crtc_disable(struct drm_crtc *crtc)
 	crtc_funcs->dpms(crtc, DRM_MODE_DPMS_OFF);
 
 	if (crtc->primary->fb) {
-		gt = to_psb_fb(crtc->primary->fb)->gtt;
+		gt = to_gtt_range(crtc->primary->fb->obj[0]);
 		psb_gtt_unpin(gt);
 	}
 }
@@ -663,7 +665,7 @@ void gma_connector_attach_encoder(struct gma_connector *connector,
 				  struct gma_encoder *encoder)
 {
 	connector->encoder = encoder;
-	drm_mode_connector_attach_encoder(&connector->base,
+	drm_connector_attach_encoder(&connector->base,
 					  &encoder->base);
 }
 
diff --git a/drivers/gpu/drm/gma500/gtt.h b/drivers/gpu/drm/gma500/gtt.h
index cdbb350c9d5d..cb0c3a2a1fd4 100644
--- a/drivers/gpu/drm/gma500/gtt.h
+++ b/drivers/gpu/drm/gma500/gtt.h
@@ -53,6 +53,8 @@ struct gtt_range {
 	int roll;			/* Roll applied to the GTT entries */
 };
 
+#define to_gtt_range(x) container_of(x, struct gtt_range, gem)
+
 extern struct gtt_range *psb_gtt_alloc_range(struct drm_device *dev, int len,
 					     const char *name, int backed,
 					     u32 align);
diff --git a/drivers/gpu/drm/gma500/intel_bios.h b/drivers/gpu/drm/gma500/intel_bios.h
index 978ae4b25e82..e0ccf1d19a4d 100644
--- a/drivers/gpu/drm/gma500/intel_bios.h
+++ b/drivers/gpu/drm/gma500/intel_bios.h
@@ -34,7 +34,7 @@ struct vbt_header {
 	u8 reserved0;
 	u32 bdb_offset;			/**< from beginning of VBT */
 	u32 aim_offset[4];		/**< from beginning of VBT */
-} __attribute__((packed));
+} __packed;
 
 
 struct bdb_header {
@@ -61,7 +61,7 @@ struct vbios_data {
 	u8 rsvd4; /* popup memory size */
 	u8 resize_pci_bios;
 	u8 rsvd5; /* is crt already on ddc2 */
-} __attribute__((packed));
+} __packed;
 
 /*
  * There are several types of BIOS data blocks (BDBs), each block has
@@ -133,7 +133,7 @@ struct bdb_general_features {
 	u8 dp_ssc_enb:1;	/* PCH attached eDP supports SSC */
 	u8 dp_ssc_freq:1;	/* SSC freq for PCH attached eDP */
 	u8 rsvd11:3; /* finish byte */
-} __attribute__((packed));
+} __packed;
 
 /* pre-915 */
 #define GPIO_PIN_DVI_LVDS	0x03 /* "DVI/LVDS DDC GPIO pins" */
@@ -213,7 +213,7 @@ struct child_device_config {
 	u8  dvo2_wiring;
 	u16 extended_type;
 	u8  dvo_function;
-} __attribute__((packed));
+} __packed;
 
 
 struct bdb_general_definitions {
@@ -256,7 +256,7 @@ struct bdb_lvds_options {
 	u8 lvds_edid:1;
 	u8 rsvd2:1;
 	u8 rsvd4;
-} __attribute__((packed));
+} __packed;
 
 struct bdb_lvds_backlight {
 	u8 type:2;
@@ -268,7 +268,7 @@ struct bdb_lvds_backlight {
 	u8 i2caddr;
 	u8 brightnesscmd;
 	/*FIXME: more...*/
-} __attribute__((packed));
+} __packed;
 
 /* LFP pointer table contains entries to the struct below */
 struct bdb_lvds_lfp_data_ptr {
@@ -278,12 +278,12 @@ struct bdb_lvds_lfp_data_ptr {
 	u8 dvo_table_size;
 	u16 panel_pnp_id_offset;
 	u8 pnp_table_size;
-} __attribute__((packed));
+} __packed;
 
 struct bdb_lvds_lfp_data_ptrs {
 	u8 lvds_entries; /* followed by one or more lvds_data_ptr structs */
 	struct bdb_lvds_lfp_data_ptr ptr[16];
-} __attribute__((packed));
+} __packed;
 
 /* LFP data has 3 blocks per entry */
 struct lvds_fp_timing {
@@ -300,7 +300,7 @@ struct lvds_fp_timing {
 	u32 pfit_reg;
 	u32 pfit_reg_val;
 	u16 terminator;
-} __attribute__((packed));
+} __packed;
 
 struct lvds_dvo_timing {
 	u16 clock;		/**< In 10khz */
@@ -328,7 +328,7 @@ struct lvds_dvo_timing {
 	u8 vsync_positive:1;
 	u8 hsync_positive:1;
 	u8 rsvd2:1;
-} __attribute__((packed));
+} __packed;
 
 struct lvds_pnp_id {
 	u16 mfg_name;
@@ -336,17 +336,17 @@ struct lvds_pnp_id {
 	u32 serial;
 	u8 mfg_week;
 	u8 mfg_year;
-} __attribute__((packed));
+} __packed;
 
 struct bdb_lvds_lfp_data_entry {
 	struct lvds_fp_timing fp_timing;
 	struct lvds_dvo_timing dvo_timing;
 	struct lvds_pnp_id pnp_id;
-} __attribute__((packed));
+} __packed;
 
 struct bdb_lvds_lfp_data {
 	struct bdb_lvds_lfp_data_entry data[16];
-} __attribute__((packed));
+} __packed;
 
 struct aimdb_header {
 	char signature[16];
@@ -354,12 +354,12 @@ struct aimdb_header {
 	u16 aimdb_version;
 	u16 aimdb_header_size;
 	u16 aimdb_size;
-} __attribute__((packed));
+} __packed;
 
 struct aimdb_block {
 	u8 aimdb_id;
 	u16 aimdb_size;
-} __attribute__((packed));
+} __packed;
 
 struct vch_panel_data {
 	u16 fp_timing_offset;
@@ -370,12 +370,12 @@ struct vch_panel_data {
 	u8 text_fitting_size;
 	u16 graphics_fitting_offset;
 	u8 graphics_fitting_size;
-} __attribute__((packed));
+} __packed;
 
 struct vch_bdb_22 {
 	struct aimdb_block aimdb_block;
 	struct vch_panel_data panels[16];
-} __attribute__((packed));
+} __packed;
 
 struct bdb_sdvo_lvds_options {
 	u8 panel_backlight;
@@ -391,7 +391,7 @@ struct bdb_sdvo_lvds_options {
 	u8 panel_misc_bits_2;
 	u8 panel_misc_bits_3;
 	u8 panel_misc_bits_4;
-} __attribute__((packed));
+} __packed;
 
 #define BDB_DRIVER_FEATURE_NO_LVDS		0
 #define BDB_DRIVER_FEATURE_INT_LVDS		1
@@ -436,7 +436,7 @@ struct bdb_driver_features {
 
 	u8 hdmi_termination;
 	u8 custom_vbt_version;
-} __attribute__((packed));
+} __packed;
 
 #define EDP_18BPP	0
 #define EDP_24BPP	1
diff --git a/drivers/gpu/drm/gma500/mdfld_dsi_dpi.c b/drivers/gpu/drm/gma500/mdfld_dsi_dpi.c
index a05c020602bd..d0bf5a1e94e8 100644
--- a/drivers/gpu/drm/gma500/mdfld_dsi_dpi.c
+++ b/drivers/gpu/drm/gma500/mdfld_dsi_dpi.c
@@ -999,7 +999,7 @@ struct mdfld_dsi_encoder *mdfld_dsi_dpi_init(struct drm_device *dev,
 				p_funcs->encoder_helper_funcs);
 
 	/*attach to given connector*/
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	/*set possible crtcs and clones*/
 	if (dsi_connector->pipe) {
diff --git a/drivers/gpu/drm/gma500/mdfld_intel_display.c b/drivers/gpu/drm/gma500/mdfld_intel_display.c
index 5c066448be5b..2b9fa0163dea 100644
--- a/drivers/gpu/drm/gma500/mdfld_intel_display.c
+++ b/drivers/gpu/drm/gma500/mdfld_intel_display.c
@@ -167,7 +167,6 @@ static int mdfld__intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct drm_framebuffer *fb = crtc->primary->fb;
 	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
-	struct psb_framebuffer *psbfb = to_psb_fb(fb);
 	int pipe = gma_crtc->pipe;
 	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	unsigned long start, offset;
@@ -196,7 +195,7 @@ static int mdfld__intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 	if (!gma_power_begin(dev, true))
 		return 0;
 
-	start = psbfb->gtt->offset;
+	start = to_gtt_range(fb->obj[0])->offset;
 	offset = y * fb->pitches[0] + x * fb->format->cpp[0];
 
 	REG_WRITE(map->stride, fb->pitches[0]);
diff --git a/drivers/gpu/drm/gma500/oaktrail_crtc.c b/drivers/gpu/drm/gma500/oaktrail_crtc.c
index 0fff269d3fe6..1b7fd6a9d8a5 100644
--- a/drivers/gpu/drm/gma500/oaktrail_crtc.c
+++ b/drivers/gpu/drm/gma500/oaktrail_crtc.c
@@ -600,7 +600,6 @@ static int oaktrail_pipe_set_base(struct drm_crtc *crtc,
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	struct drm_framebuffer *fb = crtc->primary->fb;
-	struct psb_framebuffer *psbfb = to_psb_fb(fb);
 	int pipe = gma_crtc->pipe;
 	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	unsigned long start, offset;
@@ -617,7 +616,7 @@ static int oaktrail_pipe_set_base(struct drm_crtc *crtc,
 	if (!gma_power_begin(dev, true))
 		return 0;
 
-	start = psbfb->gtt->offset;
+	start = to_gtt_range(fb->obj[0])->offset;
 	offset = y * fb->pitches[0] + x * fb->format->cpp[0];
 
 	REG_WRITE(map->stride, fb->pitches[0]);
diff --git a/drivers/gpu/drm/gma500/oaktrail_hdmi.c b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
index 78566a80ad25..c6d72de1c054 100644
--- a/drivers/gpu/drm/gma500/oaktrail_hdmi.c
+++ b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
@@ -578,7 +578,7 @@ static int oaktrail_hdmi_get_modes(struct drm_connector *connector)
 	}
 
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 	}
 	return ret;
diff --git a/drivers/gpu/drm/gma500/oaktrail_lvds.c b/drivers/gpu/drm/gma500/oaktrail_lvds.c
index e6943fef0611..83babb815a5d 100644
--- a/drivers/gpu/drm/gma500/oaktrail_lvds.c
+++ b/drivers/gpu/drm/gma500/oaktrail_lvds.c
@@ -376,7 +376,7 @@ void oaktrail_lvds_init(struct drm_device *dev,
 	 * preferred mode is the right one.
 	 */
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		drm_add_edid_modes(connector, edid);
 		kfree(edid);
 
diff --git a/drivers/gpu/drm/gma500/psb_intel_modes.c b/drivers/gpu/drm/gma500/psb_intel_modes.c
index e5360726d80b..fb4da3cd6681 100644
--- a/drivers/gpu/drm/gma500/psb_intel_modes.c
+++ b/drivers/gpu/drm/gma500/psb_intel_modes.c
@@ -66,7 +66,7 @@ int psb_intel_ddc_get_modes(struct drm_connector *connector,
 
 	edid = drm_get_edid(connector, adapter);
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 	}
diff --git a/drivers/gpu/drm/gma500/psb_intel_sdvo.c b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
index f2ee6aa10afa..dd3cec0e3190 100644
--- a/drivers/gpu/drm/gma500/psb_intel_sdvo.c
+++ b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
@@ -429,13 +429,20 @@ static const char *cmd_status_names[] = {
 	"Scaling not supported"
 };
 
+#define MAX_ARG_LEN 32
+
 static bool psb_intel_sdvo_write_cmd(struct psb_intel_sdvo *psb_intel_sdvo, u8 cmd,
 				 const void *args, int args_len)
 {
-	u8 buf[args_len*2 + 2], status;
-	struct i2c_msg msgs[args_len + 3];
+	u8 buf[MAX_ARG_LEN*2 + 2], status;
+	struct i2c_msg msgs[MAX_ARG_LEN + 3];
 	int i, ret;
 
+	if (args_len > MAX_ARG_LEN) {
+		DRM_ERROR("Need to increase arg length\n");
+		return false;
+	}
+
 	psb_intel_sdvo_debug_write(psb_intel_sdvo, cmd, args, args_len);
 
 	for (i = 0; i < args_len; i++) {
@@ -1465,7 +1472,7 @@ static void psb_intel_sdvo_get_ddc_modes(struct drm_connector *connector)
 		bool connector_is_digital = !!IS_TMDS(psb_intel_sdvo_connector);
 
 		if (connector_is_digital == monitor_is_digital) {
-			drm_mode_connector_update_edid_property(connector, edid);
+			drm_connector_update_edid_property(connector, edid);
 			drm_add_edid_modes(connector, edid);
 		}
 
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c
index d2f4749ebf8d..744956cea749 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c
@@ -133,7 +133,7 @@ int hibmc_vdac_init(struct hibmc_drm_private *priv)
 	}
 
 	drm_encoder_helper_add(encoder, &hibmc_encoder_helper_funcs);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c
index 2269be91f3e1..bb774202a5a1 100644
--- a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c
+++ b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c
@@ -859,7 +859,6 @@ static int ade_plane_atomic_check(struct drm_plane *plane,
 		return PTR_ERR(crtc_state);
 
 	if (src_w != crtc_w || src_h != crtc_h) {
-		DRM_ERROR("Scale not support!!!\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index 6ebd8842dbcc..a7c39f39793f 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -69,6 +69,7 @@ struct tda998x_priv {
 	bool edid_delay_active;
 
 	struct drm_encoder encoder;
+	struct drm_bridge bridge;
 	struct drm_connector connector;
 
 	struct tda998x_audio_port audio_port[2];
@@ -79,9 +80,10 @@ struct tda998x_priv {
 
 #define conn_to_tda998x_priv(x) \
 	container_of(x, struct tda998x_priv, connector)
-
 #define enc_to_tda998x_priv(x) \
 	container_of(x, struct tda998x_priv, encoder)
+#define bridge_to_tda998x_priv(x) \
+	container_of(x, struct tda998x_priv, bridge)
 
 /* The TDA9988 series of devices use a paged register scheme.. to simplify
  * things we encode the page # in upper bits of the register #.  To read/
@@ -589,13 +591,22 @@ out:
 	return ret;
 }
 
+#define MAX_WRITE_RANGE_BUF 32
+
 static void
 reg_write_range(struct tda998x_priv *priv, u16 reg, u8 *p, int cnt)
 {
 	struct i2c_client *client = priv->hdmi;
-	u8 buf[cnt+1];
+	/* This is the maximum size of the buffer passed in */
+	u8 buf[MAX_WRITE_RANGE_BUF + 1];
 	int ret;
 
+	if (cnt > MAX_WRITE_RANGE_BUF) {
+		dev_err(&client->dev, "Fixed write buffer too small (%d)\n",
+				MAX_WRITE_RANGE_BUF);
+		return;
+	}
+
 	buf[0] = REG2ADDR(reg);
 	memcpy(&buf[1], p, cnt);
 
@@ -753,7 +764,7 @@ static void tda998x_detect_work(struct work_struct *work)
 {
 	struct tda998x_priv *priv =
 		container_of(work, struct tda998x_priv, detect_work);
-	struct drm_device *dev = priv->encoder.dev;
+	struct drm_device *dev = priv->connector.dev;
 
 	if (dev)
 		drm_kms_helper_hotplug_event(dev);
@@ -805,7 +816,7 @@ static void
 tda998x_write_if(struct tda998x_priv *priv, u8 bit, u16 addr,
 		 union hdmi_infoframe *frame)
 {
-	u8 buf[32];
+	u8 buf[MAX_WRITE_RANGE_BUF];
 	ssize_t len;
 
 	len = hdmi_infoframe_pack(frame, buf, sizeof(buf));
@@ -1095,29 +1106,6 @@ static int tda998x_audio_codec_init(struct tda998x_priv *priv,
 
 /* DRM connector functions */
 
-static int tda998x_connector_fill_modes(struct drm_connector *connector,
-					uint32_t maxX, uint32_t maxY)
-{
-	struct tda998x_priv *priv = conn_to_tda998x_priv(connector);
-	int ret;
-
-	mutex_lock(&priv->audio_mutex);
-	ret = drm_helper_probe_single_connector_modes(connector, maxX, maxY);
-
-	if (connector->edid_blob_ptr) {
-		struct edid *edid = (void *)connector->edid_blob_ptr->data;
-
-		cec_notifier_set_phys_addr_from_edid(priv->cec_notify, edid);
-
-		priv->sink_has_audio = drm_detect_monitor_audio(edid);
-	} else {
-		priv->sink_has_audio = false;
-	}
-	mutex_unlock(&priv->audio_mutex);
-
-	return ret;
-}
-
 static enum drm_connector_status
 tda998x_connector_detect(struct drm_connector *connector, bool force)
 {
@@ -1136,7 +1124,7 @@ static void tda998x_connector_destroy(struct drm_connector *connector)
 static const struct drm_connector_funcs tda998x_connector_funcs = {
 	.dpms = drm_helper_connector_dpms,
 	.reset = drm_atomic_helper_connector_reset,
-	.fill_modes = tda998x_connector_fill_modes,
+	.fill_modes = drm_helper_probe_single_connector_modes,
 	.detect = tda998x_connector_detect,
 	.destroy = tda998x_connector_destroy,
 	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
@@ -1234,41 +1222,30 @@ static int tda998x_connector_get_modes(struct drm_connector *connector)
 		return 0;
 	}
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
+	cec_notifier_set_phys_addr_from_edid(priv->cec_notify, edid);
+
+	mutex_lock(&priv->audio_mutex);
 	n = drm_add_edid_modes(connector, edid);
+	priv->sink_has_audio = drm_detect_monitor_audio(edid);
+	mutex_unlock(&priv->audio_mutex);
 
 	kfree(edid);
 
 	return n;
 }
 
-static enum drm_mode_status tda998x_connector_mode_valid(struct drm_connector *connector,
-					struct drm_display_mode *mode)
-{
-	/* TDA19988 dotclock can go up to 165MHz */
-	struct tda998x_priv *priv = conn_to_tda998x_priv(connector);
-
-	if (mode->clock > ((priv->rev == TDA19988) ? 165000 : 150000))
-		return MODE_CLOCK_HIGH;
-	if (mode->htotal >= BIT(13))
-		return MODE_BAD_HVALUE;
-	if (mode->vtotal >= BIT(11))
-		return MODE_BAD_VVALUE;
-	return MODE_OK;
-}
-
 static struct drm_encoder *
 tda998x_connector_best_encoder(struct drm_connector *connector)
 {
 	struct tda998x_priv *priv = conn_to_tda998x_priv(connector);
 
-	return &priv->encoder;
+	return priv->bridge.encoder;
 }
 
 static
 const struct drm_connector_helper_funcs tda998x_connector_helper_funcs = {
 	.get_modes = tda998x_connector_get_modes,
-	.mode_valid = tda998x_connector_mode_valid,
 	.best_encoder = tda998x_connector_best_encoder,
 };
 
@@ -1292,25 +1269,48 @@ static int tda998x_connector_init(struct tda998x_priv *priv,
 	if (ret)
 		return ret;
 
-	drm_mode_connector_attach_encoder(&priv->connector, &priv->encoder);
+	drm_connector_attach_encoder(&priv->connector,
+				     priv->bridge.encoder);
 
 	return 0;
 }
 
-/* DRM encoder functions */
+/* DRM bridge functions */
 
-static void tda998x_encoder_dpms(struct drm_encoder *encoder, int mode)
+static int tda998x_bridge_attach(struct drm_bridge *bridge)
 {
-	struct tda998x_priv *priv = enc_to_tda998x_priv(encoder);
-	bool on;
+	struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge);
 
-	/* we only care about on or off: */
-	on = mode == DRM_MODE_DPMS_ON;
+	return tda998x_connector_init(priv, bridge->dev);
+}
 
-	if (on == priv->is_on)
-		return;
+static void tda998x_bridge_detach(struct drm_bridge *bridge)
+{
+	struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge);
 
-	if (on) {
+	drm_connector_cleanup(&priv->connector);
+}
+
+static enum drm_mode_status tda998x_bridge_mode_valid(struct drm_bridge *bridge,
+				     const struct drm_display_mode *mode)
+{
+	/* TDA19988 dotclock can go up to 165MHz */
+	struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge);
+
+	if (mode->clock > ((priv->rev == TDA19988) ? 165000 : 150000))
+		return MODE_CLOCK_HIGH;
+	if (mode->htotal >= BIT(13))
+		return MODE_BAD_HVALUE;
+	if (mode->vtotal >= BIT(11))
+		return MODE_BAD_VVALUE;
+	return MODE_OK;
+}
+
+static void tda998x_bridge_enable(struct drm_bridge *bridge)
+{
+	struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge);
+
+	if (!priv->is_on) {
 		/* enable video ports, audio will be enabled later */
 		reg_write(priv, REG_ENA_VP_0, 0xff);
 		reg_write(priv, REG_ENA_VP_1, 0xff);
@@ -1321,7 +1321,14 @@ static void tda998x_encoder_dpms(struct drm_encoder *encoder, int mode)
 		reg_write(priv, REG_VIP_CNTRL_2, priv->vip_cntrl_2);
 
 		priv->is_on = true;
-	} else {
+	}
+}
+
+static void tda998x_bridge_disable(struct drm_bridge *bridge)
+{
+	struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge);
+
+	if (priv->is_on) {
 		/* disable video ports */
 		reg_write(priv, REG_ENA_VP_0, 0x00);
 		reg_write(priv, REG_ENA_VP_1, 0x00);
@@ -1331,12 +1338,12 @@ static void tda998x_encoder_dpms(struct drm_encoder *encoder, int mode)
 	}
 }
 
-static void
-tda998x_encoder_mode_set(struct drm_encoder *encoder,
-			 struct drm_display_mode *mode,
-			 struct drm_display_mode *adjusted_mode)
+static void tda998x_bridge_mode_set(struct drm_bridge *bridge,
+				    struct drm_display_mode *mode,
+				    struct drm_display_mode *adjusted_mode)
 {
-	struct tda998x_priv *priv = enc_to_tda998x_priv(encoder);
+	struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge);
+	unsigned long tmds_clock;
 	u16 ref_pix, ref_line, n_pix, n_line;
 	u16 hs_pix_s, hs_pix_e;
 	u16 vs1_pix_s, vs1_pix_e, vs1_line_s, vs1_line_e;
@@ -1407,12 +1414,19 @@ tda998x_encoder_mode_set(struct drm_encoder *encoder,
 			       (mode->vsync_end - mode->vsync_start)/2;
 	}
 
-	div = 148500 / mode->clock;
-	if (div != 0) {
-		div--;
-		if (div > 3)
-			div = 3;
-	}
+	tmds_clock = mode->clock;
+
+	/*
+	 * The divisor is power-of-2. The TDA9983B datasheet gives
+	 * this as ranges of Msample/s, which is 10x the TMDS clock:
+	 *   0 - 800 to 1500 Msample/s
+	 *   1 - 400 to 800 Msample/s
+	 *   2 - 200 to 400 Msample/s
+	 *   3 - as 2 above
+	 */
+	for (div = 0; div < 3; div++)
+		if (80000 >> div <= tmds_clock)
+			break;
 
 	mutex_lock(&priv->audio_mutex);
 
@@ -1543,26 +1557,14 @@ tda998x_encoder_mode_set(struct drm_encoder *encoder,
 	mutex_unlock(&priv->audio_mutex);
 }
 
-static void tda998x_destroy(struct tda998x_priv *priv)
-{
-	/* disable all IRQs and free the IRQ handler */
-	cec_write(priv, REG_CEC_RXSHPDINTENA, 0);
-	reg_clear(priv, REG_INT_FLAGS_2, INT_FLAGS_2_EDID_BLK_RD);
-
-	if (priv->audio_pdev)
-		platform_device_unregister(priv->audio_pdev);
-
-	if (priv->hdmi->irq)
-		free_irq(priv->hdmi->irq, priv);
-
-	del_timer_sync(&priv->edid_delay_timer);
-	cancel_work_sync(&priv->detect_work);
-
-	i2c_unregister_device(priv->cec);
-
-	if (priv->cec_notify)
-		cec_notifier_put(priv->cec_notify);
-}
+static const struct drm_bridge_funcs tda998x_bridge_funcs = {
+	.attach = tda998x_bridge_attach,
+	.detach = tda998x_bridge_detach,
+	.mode_valid = tda998x_bridge_mode_valid,
+	.disable = tda998x_bridge_disable,
+	.mode_set = tda998x_bridge_mode_set,
+	.enable = tda998x_bridge_enable,
+};
 
 /* I2C driver functions */
 
@@ -1608,16 +1610,69 @@ static int tda998x_get_audio_ports(struct tda998x_priv *priv,
 	return 0;
 }
 
-static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
+static void tda998x_set_config(struct tda998x_priv *priv,
+			       const struct tda998x_encoder_params *p)
 {
+	priv->vip_cntrl_0 = VIP_CNTRL_0_SWAP_A(p->swap_a) |
+			    (p->mirr_a ? VIP_CNTRL_0_MIRR_A : 0) |
+			    VIP_CNTRL_0_SWAP_B(p->swap_b) |
+			    (p->mirr_b ? VIP_CNTRL_0_MIRR_B : 0);
+	priv->vip_cntrl_1 = VIP_CNTRL_1_SWAP_C(p->swap_c) |
+			    (p->mirr_c ? VIP_CNTRL_1_MIRR_C : 0) |
+			    VIP_CNTRL_1_SWAP_D(p->swap_d) |
+			    (p->mirr_d ? VIP_CNTRL_1_MIRR_D : 0);
+	priv->vip_cntrl_2 = VIP_CNTRL_2_SWAP_E(p->swap_e) |
+			    (p->mirr_e ? VIP_CNTRL_2_MIRR_E : 0) |
+			    VIP_CNTRL_2_SWAP_F(p->swap_f) |
+			    (p->mirr_f ? VIP_CNTRL_2_MIRR_F : 0);
+
+	priv->audio_params = p->audio_params;
+}
+
+static void tda998x_destroy(struct device *dev)
+{
+	struct tda998x_priv *priv = dev_get_drvdata(dev);
+
+	drm_bridge_remove(&priv->bridge);
+
+	/* disable all IRQs and free the IRQ handler */
+	cec_write(priv, REG_CEC_RXSHPDINTENA, 0);
+	reg_clear(priv, REG_INT_FLAGS_2, INT_FLAGS_2_EDID_BLK_RD);
+
+	if (priv->audio_pdev)
+		platform_device_unregister(priv->audio_pdev);
+
+	if (priv->hdmi->irq)
+		free_irq(priv->hdmi->irq, priv);
+
+	del_timer_sync(&priv->edid_delay_timer);
+	cancel_work_sync(&priv->detect_work);
+
+	i2c_unregister_device(priv->cec);
+
+	if (priv->cec_notify)
+		cec_notifier_put(priv->cec_notify);
+}
+
+static int tda998x_create(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
 	struct device_node *np = client->dev.of_node;
 	struct i2c_board_info cec_info;
+	struct tda998x_priv *priv;
 	u32 video;
 	int rev_lo, rev_hi, ret;
 
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	dev_set_drvdata(dev, priv);
+
 	mutex_init(&priv->mutex);	/* protect the page access */
 	mutex_init(&priv->audio_mutex); /* protect access from audio thread */
 	mutex_init(&priv->edid_mutex);
+	INIT_LIST_HEAD(&priv->bridge.list);
 	init_waitqueue_head(&priv->edid_delay_waitq);
 	timer_setup(&priv->edid_delay_timer, tda998x_edid_delay_done, 0);
 	INIT_WORK(&priv->detect_work, tda998x_detect_work);
@@ -1640,13 +1695,13 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 	/* read version: */
 	rev_lo = reg_read(priv, REG_VERSION_LSB);
 	if (rev_lo < 0) {
-		dev_err(&client->dev, "failed to read version: %d\n", rev_lo);
+		dev_err(dev, "failed to read version: %d\n", rev_lo);
 		return rev_lo;
 	}
 
 	rev_hi = reg_read(priv, REG_VERSION_MSB);
 	if (rev_hi < 0) {
-		dev_err(&client->dev, "failed to read version: %d\n", rev_hi);
+		dev_err(dev, "failed to read version: %d\n", rev_hi);
 		return rev_hi;
 	}
 
@@ -1657,20 +1712,19 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 
 	switch (priv->rev) {
 	case TDA9989N2:
-		dev_info(&client->dev, "found TDA9989 n2");
+		dev_info(dev, "found TDA9989 n2");
 		break;
 	case TDA19989:
-		dev_info(&client->dev, "found TDA19989");
+		dev_info(dev, "found TDA19989");
 		break;
 	case TDA19989N2:
-		dev_info(&client->dev, "found TDA19989 n2");
+		dev_info(dev, "found TDA19989 n2");
 		break;
 	case TDA19988:
-		dev_info(&client->dev, "found TDA19988");
+		dev_info(dev, "found TDA19988");
 		break;
 	default:
-		dev_err(&client->dev, "found unsupported device: %04x\n",
-			priv->rev);
+		dev_err(dev, "found unsupported device: %04x\n", priv->rev);
 		return -ENXIO;
 	}
 
@@ -1713,8 +1767,7 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 					   tda998x_irq_thread, irq_flags,
 					   "tda998x", priv);
 		if (ret) {
-			dev_err(&client->dev,
-				"failed to request IRQ#%u: %d\n",
+			dev_err(dev, "failed to request IRQ#%u: %d\n",
 				client->irq, ret);
 			goto err_irq;
 		}
@@ -1723,13 +1776,13 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 		cec_write(priv, REG_CEC_RXSHPDINTENA, CEC_RXSHPDLEV_HPD);
 	}
 
-	priv->cec_notify = cec_notifier_get(&client->dev);
+	priv->cec_notify = cec_notifier_get(dev);
 	if (!priv->cec_notify) {
 		ret = -ENOMEM;
 		goto fail;
 	}
 
-	priv->cec_glue.parent = &client->dev;
+	priv->cec_glue.parent = dev;
 	priv->cec_glue.data = priv;
 	priv->cec_glue.init = tda998x_cec_hook_init;
 	priv->cec_glue.exit = tda998x_cec_hook_exit;
@@ -1759,61 +1812,44 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 	/* enable EDID read irq: */
 	reg_set(priv, REG_INT_FLAGS_2, INT_FLAGS_2_EDID_BLK_RD);
 
-	if (!np)
-		return 0;		/* non-DT */
+	if (np) {
+		/* get the device tree parameters */
+		ret = of_property_read_u32(np, "video-ports", &video);
+		if (ret == 0) {
+			priv->vip_cntrl_0 = video >> 16;
+			priv->vip_cntrl_1 = video >> 8;
+			priv->vip_cntrl_2 = video;
+		}
+
+		ret = tda998x_get_audio_ports(priv, np);
+		if (ret)
+			goto fail;
 
-	/* get the device tree parameters */
-	ret = of_property_read_u32(np, "video-ports", &video);
-	if (ret == 0) {
-		priv->vip_cntrl_0 = video >> 16;
-		priv->vip_cntrl_1 = video >> 8;
-		priv->vip_cntrl_2 = video;
+		if (priv->audio_port[0].format != AFMT_UNUSED)
+			tda998x_audio_codec_init(priv, &client->dev);
+	} else if (dev->platform_data) {
+		tda998x_set_config(priv, dev->platform_data);
 	}
 
-	ret = tda998x_get_audio_ports(priv, np);
-	if (ret)
-		goto fail;
+	priv->bridge.funcs = &tda998x_bridge_funcs;
+#ifdef CONFIG_OF
+	priv->bridge.of_node = dev->of_node;
+#endif
 
-	if (priv->audio_port[0].format != AFMT_UNUSED)
-		tda998x_audio_codec_init(priv, &client->dev);
+	drm_bridge_add(&priv->bridge);
 
 	return 0;
 
 fail:
-	/* if encoder_init fails, the encoder slave is never registered,
-	 * so cleanup here:
-	 */
-	i2c_unregister_device(priv->cec);
-	if (priv->cec_notify)
-		cec_notifier_put(priv->cec_notify);
-	if (client->irq)
-		free_irq(client->irq, priv);
+	tda998x_destroy(dev);
 err_irq:
 	return ret;
 }
 
-static void tda998x_encoder_prepare(struct drm_encoder *encoder)
-{
-	tda998x_encoder_dpms(encoder, DRM_MODE_DPMS_OFF);
-}
-
-static void tda998x_encoder_commit(struct drm_encoder *encoder)
-{
-	tda998x_encoder_dpms(encoder, DRM_MODE_DPMS_ON);
-}
-
-static const struct drm_encoder_helper_funcs tda998x_encoder_helper_funcs = {
-	.dpms = tda998x_encoder_dpms,
-	.prepare = tda998x_encoder_prepare,
-	.commit = tda998x_encoder_commit,
-	.mode_set = tda998x_encoder_mode_set,
-};
+/* DRM encoder functions */
 
 static void tda998x_encoder_destroy(struct drm_encoder *encoder)
 {
-	struct tda998x_priv *priv = enc_to_tda998x_priv(encoder);
-
-	tda998x_destroy(priv);
 	drm_encoder_cleanup(encoder);
 }
 
@@ -1821,40 +1857,12 @@ static const struct drm_encoder_funcs tda998x_encoder_funcs = {
 	.destroy = tda998x_encoder_destroy,
 };
 
-static void tda998x_set_config(struct tda998x_priv *priv,
-			       const struct tda998x_encoder_params *p)
-{
-	priv->vip_cntrl_0 = VIP_CNTRL_0_SWAP_A(p->swap_a) |
-			    (p->mirr_a ? VIP_CNTRL_0_MIRR_A : 0) |
-			    VIP_CNTRL_0_SWAP_B(p->swap_b) |
-			    (p->mirr_b ? VIP_CNTRL_0_MIRR_B : 0);
-	priv->vip_cntrl_1 = VIP_CNTRL_1_SWAP_C(p->swap_c) |
-			    (p->mirr_c ? VIP_CNTRL_1_MIRR_C : 0) |
-			    VIP_CNTRL_1_SWAP_D(p->swap_d) |
-			    (p->mirr_d ? VIP_CNTRL_1_MIRR_D : 0);
-	priv->vip_cntrl_2 = VIP_CNTRL_2_SWAP_E(p->swap_e) |
-			    (p->mirr_e ? VIP_CNTRL_2_MIRR_E : 0) |
-			    VIP_CNTRL_2_SWAP_F(p->swap_f) |
-			    (p->mirr_f ? VIP_CNTRL_2_MIRR_F : 0);
-
-	priv->audio_params = p->audio_params;
-}
-
-static int tda998x_bind(struct device *dev, struct device *master, void *data)
+static int tda998x_encoder_init(struct device *dev, struct drm_device *drm)
 {
-	struct tda998x_encoder_params *params = dev->platform_data;
-	struct i2c_client *client = to_i2c_client(dev);
-	struct drm_device *drm = data;
-	struct tda998x_priv *priv;
+	struct tda998x_priv *priv = dev_get_drvdata(dev);
 	u32 crtcs = 0;
 	int ret;
 
-	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
-	if (!priv)
-		return -ENOMEM;
-
-	dev_set_drvdata(dev, priv);
-
 	if (dev->of_node)
 		crtcs = drm_of_find_possible_crtcs(drm, dev->of_node);
 
@@ -1866,40 +1874,36 @@ static int tda998x_bind(struct device *dev, struct device *master, void *data)
 
 	priv->encoder.possible_crtcs = crtcs;
 
-	ret = tda998x_create(client, priv);
-	if (ret)
-		return ret;
-
-	if (!dev->of_node && params)
-		tda998x_set_config(priv, params);
-
-	drm_encoder_helper_add(&priv->encoder, &tda998x_encoder_helper_funcs);
 	ret = drm_encoder_init(drm, &priv->encoder, &tda998x_encoder_funcs,
 			       DRM_MODE_ENCODER_TMDS, NULL);
 	if (ret)
 		goto err_encoder;
 
-	ret = tda998x_connector_init(priv, drm);
+	ret = drm_bridge_attach(&priv->encoder, &priv->bridge, NULL);
 	if (ret)
-		goto err_connector;
+		goto err_bridge;
 
 	return 0;
 
-err_connector:
+err_bridge:
 	drm_encoder_cleanup(&priv->encoder);
 err_encoder:
-	tda998x_destroy(priv);
 	return ret;
 }
 
+static int tda998x_bind(struct device *dev, struct device *master, void *data)
+{
+	struct drm_device *drm = data;
+
+	return tda998x_encoder_init(dev, drm);
+}
+
 static void tda998x_unbind(struct device *dev, struct device *master,
 			   void *data)
 {
 	struct tda998x_priv *priv = dev_get_drvdata(dev);
 
-	drm_connector_cleanup(&priv->connector);
 	drm_encoder_cleanup(&priv->encoder);
-	tda998x_destroy(priv);
 }
 
 static const struct component_ops tda998x_ops = {
@@ -1910,16 +1914,27 @@ static const struct component_ops tda998x_ops = {
 static int
 tda998x_probe(struct i2c_client *client, const struct i2c_device_id *id)
 {
+	int ret;
+
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
 		dev_warn(&client->dev, "adapter does not support I2C\n");
 		return -EIO;
 	}
-	return component_add(&client->dev, &tda998x_ops);
+
+	ret = tda998x_create(&client->dev);
+	if (ret)
+		return ret;
+
+	ret = component_add(&client->dev, &tda998x_ops);
+	if (ret)
+		tda998x_destroy(&client->dev);
+	return ret;
 }
 
 static int tda998x_remove(struct i2c_client *client)
 {
 	component_del(&client->dev, &tda998x_ops);
+	tda998x_destroy(&client->dev);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c
index 576a417690d4..3b378936f575 100644
--- a/drivers/gpu/drm/i810/i810_dma.c
+++ b/drivers/gpu/drm/i810/i810_dma.c
@@ -934,7 +934,7 @@ static int i810_dma_vertex(struct drm_device *dev, void *data,
 	DRM_DEBUG("idx %d used %d discard %d\n",
 		  vertex->idx, vertex->used, vertex->discard);
 
-	if (vertex->idx < 0 || vertex->idx > dma->buf_count)
+	if (vertex->idx < 0 || vertex->idx >= dma->buf_count)
 		return -EINVAL;
 
 	i810_dma_dispatch_vertex(dev,
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index dfd95889f4b7..5c607f2c707b 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -23,6 +23,7 @@ config DRM_I915
 	select SYNC_FILE
 	select IOSF_MBI
 	select CRC32
+	select SND_HDA_I915 if SND_HDA_CORE
 	help
 	  Choose this option if you have a system that has "Intel Graphics
 	  Media Accelerator" or "HD Graphics" integrated graphics,
diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index 9de8b1c51a5c..459f8f88a34c 100644
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -51,6 +51,18 @@ config DRM_I915_DEBUG_GEM
 
           If in doubt, say "N".
 
+config DRM_I915_ERRLOG_GEM
+	bool "Insert extra logging (very verbose) for common GEM errors"
+	default n
+	depends on DRM_I915_DEBUG_GEM
+	help
+	  Enable additional logging that may help track down the cause of
+	  principally userspace errors.
+
+	  Recommended for driver developers only.
+
+	  If in doubt, say "N".
+
 config DRM_I915_TRACE_GEM
 	bool "Insert extra ftrace output from the GEM internals"
 	depends on DRM_I915_DEBUG_GEM
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 4c6adae23e18..5794f102f9b8 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -135,15 +135,14 @@ i915-y += dvo_ch7017.o \
 	  dvo_ns2501.o \
 	  dvo_sil164.o \
 	  dvo_tfp410.o \
+	  icl_dsi.o \
 	  intel_crt.o \
 	  intel_ddi.o \
 	  intel_dp_aux_backlight.o \
 	  intel_dp_link_training.o \
 	  intel_dp_mst.o \
 	  intel_dp.o \
-	  intel_dsi.o \
 	  intel_dsi_dcs_backlight.o \
-	  intel_dsi_pll.o \
 	  intel_dsi_vbt.o \
 	  intel_dvo.o \
 	  intel_hdmi.o \
@@ -152,7 +151,9 @@ i915-y += dvo_ch7017.o \
 	  intel_lvds.o \
 	  intel_panel.o \
 	  intel_sdvo.o \
-	  intel_tv.o
+	  intel_tv.o \
+	  vlv_dsi.o \
+	  vlv_dsi_pll.o
 
 # Post-mortem debug and GPU hang state capture
 i915-$(CONFIG_DRM_I915_CAPTURE_ERROR) += i915_gpu_error.o
diff --git a/drivers/gpu/drm/i915/dvo_ch7017.c b/drivers/gpu/drm/i915/dvo_ch7017.c
index 80b3e16cf48c..caac9942e1e3 100644
--- a/drivers/gpu/drm/i915/dvo_ch7017.c
+++ b/drivers/gpu/drm/i915/dvo_ch7017.c
@@ -159,7 +159,7 @@
 #define CH7017_BANG_LIMIT_CONTROL	0x7f
 
 struct ch7017_priv {
-	uint8_t dummy;
+	u8 dummy;
 };
 
 static void ch7017_dump_regs(struct intel_dvo_device *dvo);
@@ -186,7 +186,7 @@ static bool ch7017_read(struct intel_dvo_device *dvo, u8 addr, u8 *val)
 
 static bool ch7017_write(struct intel_dvo_device *dvo, u8 addr, u8 val)
 {
-	uint8_t buf[2] = { addr, val };
+	u8 buf[2] = { addr, val };
 	struct i2c_msg msg = {
 		.addr = dvo->slave_addr,
 		.flags = 0,
@@ -258,11 +258,11 @@ static void ch7017_mode_set(struct intel_dvo_device *dvo,
 			    const struct drm_display_mode *mode,
 			    const struct drm_display_mode *adjusted_mode)
 {
-	uint8_t lvds_pll_feedback_div, lvds_pll_vco_control;
-	uint8_t outputs_enable, lvds_control_2, lvds_power_down;
-	uint8_t horizontal_active_pixel_input;
-	uint8_t horizontal_active_pixel_output, vertical_active_line_output;
-	uint8_t active_input_line_output;
+	u8 lvds_pll_feedback_div, lvds_pll_vco_control;
+	u8 outputs_enable, lvds_control_2, lvds_power_down;
+	u8 horizontal_active_pixel_input;
+	u8 horizontal_active_pixel_output, vertical_active_line_output;
+	u8 active_input_line_output;
 
 	DRM_DEBUG_KMS("Registers before mode setting\n");
 	ch7017_dump_regs(dvo);
@@ -333,7 +333,7 @@ static void ch7017_mode_set(struct intel_dvo_device *dvo,
 /* set the CH7017 power state */
 static void ch7017_dpms(struct intel_dvo_device *dvo, bool enable)
 {
-	uint8_t val;
+	u8 val;
 
 	ch7017_read(dvo, CH7017_LVDS_POWER_DOWN, &val);
 
@@ -361,7 +361,7 @@ static void ch7017_dpms(struct intel_dvo_device *dvo, bool enable)
 
 static bool ch7017_get_hw_state(struct intel_dvo_device *dvo)
 {
-	uint8_t val;
+	u8 val;
 
 	ch7017_read(dvo, CH7017_LVDS_POWER_DOWN, &val);
 
@@ -373,7 +373,7 @@ static bool ch7017_get_hw_state(struct intel_dvo_device *dvo)
 
 static void ch7017_dump_regs(struct intel_dvo_device *dvo)
 {
-	uint8_t val;
+	u8 val;
 
 #define DUMP(reg)					\
 do {							\
diff --git a/drivers/gpu/drm/i915/dvo_ch7xxx.c b/drivers/gpu/drm/i915/dvo_ch7xxx.c
index 7aeeffd2428b..397ac5233726 100644
--- a/drivers/gpu/drm/i915/dvo_ch7xxx.c
+++ b/drivers/gpu/drm/i915/dvo_ch7xxx.c
@@ -85,7 +85,7 @@ SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
  */
 
 static struct ch7xxx_id_struct {
-	uint8_t vid;
+	u8 vid;
 	char *name;
 } ch7xxx_ids[] = {
 	{ CH7011_VID, "CH7011" },
@@ -96,7 +96,7 @@ static struct ch7xxx_id_struct {
 };
 
 static struct ch7xxx_did_struct {
-	uint8_t did;
+	u8 did;
 	char *name;
 } ch7xxx_dids[] = {
 	{ CH7xxx_DID, "CH7XXX" },
@@ -107,7 +107,7 @@ struct ch7xxx_priv {
 	bool quiet;
 };
 
-static char *ch7xxx_get_id(uint8_t vid)
+static char *ch7xxx_get_id(u8 vid)
 {
 	int i;
 
@@ -119,7 +119,7 @@ static char *ch7xxx_get_id(uint8_t vid)
 	return NULL;
 }
 
-static char *ch7xxx_get_did(uint8_t did)
+static char *ch7xxx_get_did(u8 did)
 {
 	int i;
 
@@ -132,7 +132,7 @@ static char *ch7xxx_get_did(uint8_t did)
 }
 
 /** Reads an 8 bit register */
-static bool ch7xxx_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch)
+static bool ch7xxx_readb(struct intel_dvo_device *dvo, int addr, u8 *ch)
 {
 	struct ch7xxx_priv *ch7xxx = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
@@ -170,11 +170,11 @@ static bool ch7xxx_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch)
 }
 
 /** Writes an 8 bit register */
-static bool ch7xxx_writeb(struct intel_dvo_device *dvo, int addr, uint8_t ch)
+static bool ch7xxx_writeb(struct intel_dvo_device *dvo, int addr, u8 ch)
 {
 	struct ch7xxx_priv *ch7xxx = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
-	uint8_t out_buf[2];
+	u8 out_buf[2];
 	struct i2c_msg msg = {
 		.addr = dvo->slave_addr,
 		.flags = 0,
@@ -201,7 +201,7 @@ static bool ch7xxx_init(struct intel_dvo_device *dvo,
 {
 	/* this will detect the CH7xxx chip on the specified i2c bus */
 	struct ch7xxx_priv *ch7xxx;
-	uint8_t vendor, device;
+	u8 vendor, device;
 	char *name, *devid;
 
 	ch7xxx = kzalloc(sizeof(struct ch7xxx_priv), GFP_KERNEL);
@@ -244,7 +244,7 @@ out:
 
 static enum drm_connector_status ch7xxx_detect(struct intel_dvo_device *dvo)
 {
-	uint8_t cdet, orig_pm, pm;
+	u8 cdet, orig_pm, pm;
 
 	ch7xxx_readb(dvo, CH7xxx_PM, &orig_pm);
 
@@ -276,7 +276,7 @@ static void ch7xxx_mode_set(struct intel_dvo_device *dvo,
 			    const struct drm_display_mode *mode,
 			    const struct drm_display_mode *adjusted_mode)
 {
-	uint8_t tvco, tpcp, tpd, tlpf, idf;
+	u8 tvco, tpcp, tpd, tlpf, idf;
 
 	if (mode->clock <= 65000) {
 		tvco = 0x23;
@@ -336,7 +336,7 @@ static void ch7xxx_dump_regs(struct intel_dvo_device *dvo)
 	int i;
 
 	for (i = 0; i < CH7xxx_NUM_REGS; i++) {
-		uint8_t val;
+		u8 val;
 		if ((i % 8) == 0)
 			DRM_DEBUG_KMS("\n %02X: ", i);
 		ch7xxx_readb(dvo, i, &val);
diff --git a/drivers/gpu/drm/i915/dvo_ivch.c b/drivers/gpu/drm/i915/dvo_ivch.c
index c73aff163908..24278cc49090 100644
--- a/drivers/gpu/drm/i915/dvo_ivch.c
+++ b/drivers/gpu/drm/i915/dvo_ivch.c
@@ -161,7 +161,7 @@
  * instead. The following list contains all registers that
  * require saving.
  */
-static const uint16_t backup_addresses[] = {
+static const u16 backup_addresses[] = {
 	0x11, 0x12,
 	0x18, 0x19, 0x1a, 0x1f,
 	0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27,
@@ -174,11 +174,11 @@ static const uint16_t backup_addresses[] = {
 struct ivch_priv {
 	bool quiet;
 
-	uint16_t width, height;
+	u16 width, height;
 
 	/* Register backup */
 
-	uint16_t reg_backup[ARRAY_SIZE(backup_addresses)];
+	u16 reg_backup[ARRAY_SIZE(backup_addresses)];
 };
 
 
@@ -188,7 +188,7 @@ static void ivch_dump_regs(struct intel_dvo_device *dvo);
  *
  * Each of the 256 registers are 16 bits long.
  */
-static bool ivch_read(struct intel_dvo_device *dvo, int addr, uint16_t *data)
+static bool ivch_read(struct intel_dvo_device *dvo, int addr, u16 *data)
 {
 	struct ivch_priv *priv = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
@@ -231,7 +231,7 @@ static bool ivch_read(struct intel_dvo_device *dvo, int addr, uint16_t *data)
 }
 
 /* Writes a 16-bit register on the ivch */
-static bool ivch_write(struct intel_dvo_device *dvo, int addr, uint16_t data)
+static bool ivch_write(struct intel_dvo_device *dvo, int addr, u16 data)
 {
 	struct ivch_priv *priv = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
@@ -263,7 +263,7 @@ static bool ivch_init(struct intel_dvo_device *dvo,
 		      struct i2c_adapter *adapter)
 {
 	struct ivch_priv *priv;
-	uint16_t temp;
+	u16 temp;
 	int i;
 
 	priv = kzalloc(sizeof(struct ivch_priv), GFP_KERNEL);
@@ -342,7 +342,7 @@ static void ivch_reset(struct intel_dvo_device *dvo)
 static void ivch_dpms(struct intel_dvo_device *dvo, bool enable)
 {
 	int i;
-	uint16_t vr01, vr30, backlight;
+	u16 vr01, vr30, backlight;
 
 	ivch_reset(dvo);
 
@@ -379,7 +379,7 @@ static void ivch_dpms(struct intel_dvo_device *dvo, bool enable)
 
 static bool ivch_get_hw_state(struct intel_dvo_device *dvo)
 {
-	uint16_t vr01;
+	u16 vr01;
 
 	ivch_reset(dvo);
 
@@ -398,9 +398,9 @@ static void ivch_mode_set(struct intel_dvo_device *dvo,
 			  const struct drm_display_mode *adjusted_mode)
 {
 	struct ivch_priv *priv = dvo->dev_priv;
-	uint16_t vr40 = 0;
-	uint16_t vr01 = 0;
-	uint16_t vr10;
+	u16 vr40 = 0;
+	u16 vr01 = 0;
+	u16 vr10;
 
 	ivch_reset(dvo);
 
@@ -416,7 +416,7 @@ static void ivch_mode_set(struct intel_dvo_device *dvo,
 
 	if (mode->hdisplay != adjusted_mode->crtc_hdisplay ||
 	    mode->vdisplay != adjusted_mode->crtc_vdisplay) {
-		uint16_t x_ratio, y_ratio;
+		u16 x_ratio, y_ratio;
 
 		vr01 |= VR01_PANEL_FIT_ENABLE;
 		vr40 |= VR40_CLOCK_GATING_ENABLE;
@@ -438,7 +438,7 @@ static void ivch_mode_set(struct intel_dvo_device *dvo,
 
 static void ivch_dump_regs(struct intel_dvo_device *dvo)
 {
-	uint16_t val;
+	u16 val;
 
 	ivch_read(dvo, VR00, &val);
 	DRM_DEBUG_KMS("VR00: 0x%04x\n", val);
diff --git a/drivers/gpu/drm/i915/dvo_ns2501.c b/drivers/gpu/drm/i915/dvo_ns2501.c
index 2379c33cfe51..c584e01dc8dc 100644
--- a/drivers/gpu/drm/i915/dvo_ns2501.c
+++ b/drivers/gpu/drm/i915/dvo_ns2501.c
@@ -191,8 +191,8 @@ enum {
 };
 
 struct ns2501_reg {
-	 uint8_t offset;
-	 uint8_t value;
+	u8 offset;
+	u8 value;
 };
 
 /*
@@ -202,23 +202,23 @@ struct ns2501_reg {
  * read all this with a grain of salt.
  */
 struct ns2501_configuration {
-	uint8_t sync;		/* configuration of the C0 register */
-	uint8_t conf;		/* configuration register 8 */
-	uint8_t syncb;		/* configuration register 41 */
-	uint8_t	dither;		/* configuration of the dithering */
-	uint8_t pll_a;		/* PLL configuration, register A, 1B */
-	uint16_t pll_b;		/* PLL configuration, register B, 1C/1D */
-	uint16_t hstart;	/* horizontal start, registers C1/C2 */
-	uint16_t hstop;		/* horizontal total, registers C3/C4 */
-	uint16_t vstart;	/* vertical start, registers C5/C6 */
-	uint16_t vstop;		/* vertical total, registers C7/C8 */
-	uint16_t vsync;         /* manual vertical sync start, 80/81 */
-	uint16_t vtotal;        /* number of lines generated, 82/83 */
-	uint16_t hpos;		/* horizontal position + 256, 98/99  */
-	uint16_t vpos;		/* vertical position, 8e/8f */
-	uint16_t voffs;		/* vertical output offset, 9c/9d */
-	uint16_t hscale;	/* horizontal scaling factor, b8/b9 */
-	uint16_t vscale;	/* vertical scaling factor, 10/11 */
+	u8 sync;		/* configuration of the C0 register */
+	u8 conf;		/* configuration register 8 */
+	u8 syncb;		/* configuration register 41 */
+	u8 dither;		/* configuration of the dithering */
+	u8 pll_a;		/* PLL configuration, register A, 1B */
+	u16 pll_b;		/* PLL configuration, register B, 1C/1D */
+	u16 hstart;		/* horizontal start, registers C1/C2 */
+	u16 hstop;		/* horizontal total, registers C3/C4 */
+	u16 vstart;		/* vertical start, registers C5/C6 */
+	u16 vstop;		/* vertical total, registers C7/C8 */
+	u16 vsync;		/* manual vertical sync start, 80/81 */
+	u16 vtotal;		/* number of lines generated, 82/83 */
+	u16 hpos;		/* horizontal position + 256, 98/99  */
+	u16 vpos;		/* vertical position, 8e/8f */
+	u16 voffs;		/* vertical output offset, 9c/9d */
+	u16 hscale;		/* horizontal scaling factor, b8/b9 */
+	u16 vscale;		/* vertical scaling factor, 10/11 */
 };
 
 /*
@@ -389,7 +389,7 @@ struct ns2501_priv {
 ** If it returns false, it might be wise to enable the
 ** DVO with the above function.
 */
-static bool ns2501_readb(struct intel_dvo_device *dvo, int addr, uint8_t * ch)
+static bool ns2501_readb(struct intel_dvo_device *dvo, int addr, u8 *ch)
 {
 	struct ns2501_priv *ns = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
@@ -434,11 +434,11 @@ static bool ns2501_readb(struct intel_dvo_device *dvo, int addr, uint8_t * ch)
 ** If it returns false, it might be wise to enable the
 ** DVO with the above function.
 */
-static bool ns2501_writeb(struct intel_dvo_device *dvo, int addr, uint8_t ch)
+static bool ns2501_writeb(struct intel_dvo_device *dvo, int addr, u8 ch)
 {
 	struct ns2501_priv *ns = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
-	uint8_t out_buf[2];
+	u8 out_buf[2];
 
 	struct i2c_msg msg = {
 		.addr = dvo->slave_addr,
diff --git a/drivers/gpu/drm/i915/dvo_sil164.c b/drivers/gpu/drm/i915/dvo_sil164.c
index 1c1a0674dbab..4ae5d8fd9ff0 100644
--- a/drivers/gpu/drm/i915/dvo_sil164.c
+++ b/drivers/gpu/drm/i915/dvo_sil164.c
@@ -65,7 +65,7 @@ struct sil164_priv {
 
 #define SILPTR(d) ((SIL164Ptr)(d->DriverPrivate.ptr))
 
-static bool sil164_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch)
+static bool sil164_readb(struct intel_dvo_device *dvo, int addr, u8 *ch)
 {
 	struct sil164_priv *sil = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
@@ -102,11 +102,11 @@ static bool sil164_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch)
 	return false;
 }
 
-static bool sil164_writeb(struct intel_dvo_device *dvo, int addr, uint8_t ch)
+static bool sil164_writeb(struct intel_dvo_device *dvo, int addr, u8 ch)
 {
 	struct sil164_priv *sil = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
-	uint8_t out_buf[2];
+	u8 out_buf[2];
 	struct i2c_msg msg = {
 		.addr = dvo->slave_addr,
 		.flags = 0,
@@ -173,7 +173,7 @@ out:
 
 static enum drm_connector_status sil164_detect(struct intel_dvo_device *dvo)
 {
-	uint8_t reg9;
+	u8 reg9;
 
 	sil164_readb(dvo, SIL164_REG9, &reg9);
 
@@ -243,7 +243,7 @@ static bool sil164_get_hw_state(struct intel_dvo_device *dvo)
 
 static void sil164_dump_regs(struct intel_dvo_device *dvo)
 {
-	uint8_t val;
+	u8 val;
 
 	sil164_readb(dvo, SIL164_FREQ_LO, &val);
 	DRM_DEBUG_KMS("SIL164_FREQ_LO: 0x%02x\n", val);
diff --git a/drivers/gpu/drm/i915/dvo_tfp410.c b/drivers/gpu/drm/i915/dvo_tfp410.c
index 31e181da93db..d603bc2f2506 100644
--- a/drivers/gpu/drm/i915/dvo_tfp410.c
+++ b/drivers/gpu/drm/i915/dvo_tfp410.c
@@ -90,7 +90,7 @@ struct tfp410_priv {
 	bool quiet;
 };
 
-static bool tfp410_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch)
+static bool tfp410_readb(struct intel_dvo_device *dvo, int addr, u8 *ch)
 {
 	struct tfp410_priv *tfp = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
@@ -127,11 +127,11 @@ static bool tfp410_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch)
 	return false;
 }
 
-static bool tfp410_writeb(struct intel_dvo_device *dvo, int addr, uint8_t ch)
+static bool tfp410_writeb(struct intel_dvo_device *dvo, int addr, u8 ch)
 {
 	struct tfp410_priv *tfp = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
-	uint8_t out_buf[2];
+	u8 out_buf[2];
 	struct i2c_msg msg = {
 		.addr = dvo->slave_addr,
 		.flags = 0,
@@ -155,7 +155,7 @@ static bool tfp410_writeb(struct intel_dvo_device *dvo, int addr, uint8_t ch)
 
 static int tfp410_getid(struct intel_dvo_device *dvo, int addr)
 {
-	uint8_t ch1, ch2;
+	u8 ch1, ch2;
 
 	if (tfp410_readb(dvo, addr+0, &ch1) &&
 	    tfp410_readb(dvo, addr+1, &ch2))
@@ -203,7 +203,7 @@ out:
 static enum drm_connector_status tfp410_detect(struct intel_dvo_device *dvo)
 {
 	enum drm_connector_status ret = connector_status_disconnected;
-	uint8_t ctl2;
+	u8 ctl2;
 
 	if (tfp410_readb(dvo, TFP410_CTL_2, &ctl2)) {
 		if (ctl2 & TFP410_CTL_2_RSEN)
@@ -236,7 +236,7 @@ static void tfp410_mode_set(struct intel_dvo_device *dvo,
 /* set the tfp410 power state */
 static void tfp410_dpms(struct intel_dvo_device *dvo, bool enable)
 {
-	uint8_t ctl1;
+	u8 ctl1;
 
 	if (!tfp410_readb(dvo, TFP410_CTL_1, &ctl1))
 		return;
@@ -251,7 +251,7 @@ static void tfp410_dpms(struct intel_dvo_device *dvo, bool enable)
 
 static bool tfp410_get_hw_state(struct intel_dvo_device *dvo)
 {
-	uint8_t ctl1;
+	u8 ctl1;
 
 	if (!tfp410_readb(dvo, TFP410_CTL_1, &ctl1))
 		return false;
@@ -264,7 +264,7 @@ static bool tfp410_get_hw_state(struct intel_dvo_device *dvo)
 
 static void tfp410_dump_regs(struct intel_dvo_device *dvo)
 {
-	uint8_t val, val2;
+	u8 val, val2;
 
 	tfp410_readb(dvo, TFP410_REV, &val);
 	DRM_DEBUG_KMS("TFP410_REV: 0x%02X\n", val);
diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c
index 7c9ec4f4f36c..380eeb2a0e83 100644
--- a/drivers/gpu/drm/i915/gvt/aperture_gm.c
+++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c
@@ -61,7 +61,7 @@ static int alloc_gm(struct intel_vgpu *vgpu, bool high_gm)
 	}
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	ret = i915_gem_gtt_insert(&dev_priv->ggtt.base, node,
+	ret = i915_gem_gtt_insert(&dev_priv->ggtt.vm, node,
 				  size, I915_GTT_PAGE_SIZE,
 				  I915_COLOR_UNEVICTABLE,
 				  start, end, flags);
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index 7f562410f9cf..45e89b1e0481 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -172,6 +172,7 @@ struct decode_info {
 #define OP_MEDIA_INTERFACE_DESCRIPTOR_LOAD      OP_3D_MEDIA(0x2, 0x0, 0x2)
 #define OP_MEDIA_GATEWAY_STATE                  OP_3D_MEDIA(0x2, 0x0, 0x3)
 #define OP_MEDIA_STATE_FLUSH                    OP_3D_MEDIA(0x2, 0x0, 0x4)
+#define OP_MEDIA_POOL_STATE                     OP_3D_MEDIA(0x2, 0x0, 0x5)
 
 #define OP_MEDIA_OBJECT                         OP_3D_MEDIA(0x2, 0x1, 0x0)
 #define OP_MEDIA_OBJECT_PRT                     OP_3D_MEDIA(0x2, 0x1, 0x2)
@@ -1279,7 +1280,9 @@ static int gen8_check_mi_display_flip(struct parser_exec_state *s,
 	if (!info->async_flip)
 		return 0;
 
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+	if (IS_SKYLAKE(dev_priv)
+		|| IS_KABYLAKE(dev_priv)
+		|| IS_BROXTON(dev_priv)) {
 		stride = vgpu_vreg_t(s->vgpu, info->stride_reg) & GENMASK(9, 0);
 		tile = (vgpu_vreg_t(s->vgpu, info->ctrl_reg) &
 				GENMASK(12, 10)) >> 10;
@@ -1307,7 +1310,9 @@ static int gen8_update_plane_mmio_from_mi_display_flip(
 
 	set_mask_bits(&vgpu_vreg_t(vgpu, info->surf_reg), GENMASK(31, 12),
 		      info->surf_val << 12);
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+	if (IS_SKYLAKE(dev_priv)
+		|| IS_KABYLAKE(dev_priv)
+		|| IS_BROXTON(dev_priv)) {
 		set_mask_bits(&vgpu_vreg_t(vgpu, info->stride_reg), GENMASK(9, 0),
 			      info->stride_val);
 		set_mask_bits(&vgpu_vreg_t(vgpu, info->ctrl_reg), GENMASK(12, 10),
@@ -1331,7 +1336,9 @@ static int decode_mi_display_flip(struct parser_exec_state *s,
 
 	if (IS_BROADWELL(dev_priv))
 		return gen8_decode_mi_display_flip(s, info);
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
+	if (IS_SKYLAKE(dev_priv)
+		|| IS_KABYLAKE(dev_priv)
+		|| IS_BROXTON(dev_priv))
 		return skl_decode_mi_display_flip(s, info);
 
 	return -ENODEV;
@@ -1340,26 +1347,14 @@ static int decode_mi_display_flip(struct parser_exec_state *s,
 static int check_mi_display_flip(struct parser_exec_state *s,
 		struct mi_display_flip_command_info *info)
 {
-	struct drm_i915_private *dev_priv = s->vgpu->gvt->dev_priv;
-
-	if (IS_BROADWELL(dev_priv)
-		|| IS_SKYLAKE(dev_priv)
-		|| IS_KABYLAKE(dev_priv))
-		return gen8_check_mi_display_flip(s, info);
-	return -ENODEV;
+	return gen8_check_mi_display_flip(s, info);
 }
 
 static int update_plane_mmio_from_mi_display_flip(
 		struct parser_exec_state *s,
 		struct mi_display_flip_command_info *info)
 {
-	struct drm_i915_private *dev_priv = s->vgpu->gvt->dev_priv;
-
-	if (IS_BROADWELL(dev_priv)
-		|| IS_SKYLAKE(dev_priv)
-		|| IS_KABYLAKE(dev_priv))
-		return gen8_update_plane_mmio_from_mi_display_flip(s, info);
-	return -ENODEV;
+	return gen8_update_plane_mmio_from_mi_display_flip(s, info);
 }
 
 static int cmd_handler_mi_display_flip(struct parser_exec_state *s)
@@ -1638,15 +1633,10 @@ static int copy_gma_to_hva(struct intel_vgpu *vgpu, struct intel_vgpu_mm *mm,
  */
 static int batch_buffer_needs_scan(struct parser_exec_state *s)
 {
-	struct intel_gvt *gvt = s->vgpu->gvt;
-
-	if (IS_BROADWELL(gvt->dev_priv) || IS_SKYLAKE(gvt->dev_priv)
-		|| IS_KABYLAKE(gvt->dev_priv)) {
-		/* BDW decides privilege based on address space */
-		if (cmd_val(s, 0) & (1 << 8) &&
+	/* Decide privilege based on address space */
+	if (cmd_val(s, 0) & (1 << 8) &&
 			!(s->vgpu->scan_nonprivbb & (1 << s->ring_id)))
-			return 0;
-	}
+		return 0;
 	return 1;
 }
 
@@ -2372,6 +2362,9 @@ static struct cmd_info cmd_info[] = {
 	{"MEDIA_STATE_FLUSH", OP_MEDIA_STATE_FLUSH, F_LEN_VAR, R_RCS, D_ALL,
 		0, 16, NULL},
 
+	{"MEDIA_POOL_STATE", OP_MEDIA_POOL_STATE, F_LEN_VAR, R_RCS, D_ALL,
+		0, 16, NULL},
+
 	{"MEDIA_OBJECT", OP_MEDIA_OBJECT, F_LEN_VAR, R_RCS, D_ALL, 0, 16, NULL},
 
 	{"MEDIA_CURBE_LOAD", OP_MEDIA_CURBE_LOAD, F_LEN_VAR, R_RCS, D_ALL,
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index 4b072ade8c38..3019dbc39aef 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -171,6 +171,29 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	int pipe;
 
+	if (IS_BROXTON(dev_priv)) {
+		vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &= ~(BXT_DE_PORT_HP_DDIA |
+			BXT_DE_PORT_HP_DDIB |
+			BXT_DE_PORT_HP_DDIC);
+
+		if (intel_vgpu_has_monitor_on_port(vgpu, PORT_A)) {
+			vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
+				BXT_DE_PORT_HP_DDIA;
+		}
+
+		if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
+			vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
+				BXT_DE_PORT_HP_DDIB;
+		}
+
+		if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
+			vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
+				BXT_DE_PORT_HP_DDIC;
+		}
+
+		return;
+	}
+
 	vgpu_vreg_t(vgpu, SDEISR) &= ~(SDE_PORTB_HOTPLUG_CPT |
 			SDE_PORTC_HOTPLUG_CPT |
 			SDE_PORTD_HOTPLUG_CPT);
@@ -273,8 +296,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 	for_each_pipe(dev_priv, pipe) {
 		vgpu_vreg_t(vgpu, DSPCNTR(pipe)) &= ~DISPLAY_PLANE_ENABLE;
 		vgpu_vreg_t(vgpu, SPRCTL(pipe)) &= ~SPRITE_ENABLE;
-		vgpu_vreg_t(vgpu, CURCNTR(pipe)) &= ~CURSOR_MODE;
-		vgpu_vreg_t(vgpu, CURCNTR(pipe)) |= CURSOR_MODE_DISABLE;
+		vgpu_vreg_t(vgpu, CURCNTR(pipe)) &= ~MCURSOR_MODE;
+		vgpu_vreg_t(vgpu, CURCNTR(pipe)) |= MCURSOR_MODE_DISABLE;
 	}
 
 	vgpu_vreg_t(vgpu, PIPECONF(PIPE_A)) |= PIPECONF_ENABLE;
@@ -337,26 +360,28 @@ void intel_gvt_check_vblank_emulation(struct intel_gvt *gvt)
 	struct intel_gvt_irq *irq = &gvt->irq;
 	struct intel_vgpu *vgpu;
 	int pipe, id;
+	int found = false;
 
-	if (WARN_ON(!mutex_is_locked(&gvt->lock)))
-		return;
-
+	mutex_lock(&gvt->lock);
 	for_each_active_vgpu(gvt, vgpu, id) {
 		for (pipe = 0; pipe < I915_MAX_PIPES; pipe++) {
-			if (pipe_is_enabled(vgpu, pipe))
-				goto out;
+			if (pipe_is_enabled(vgpu, pipe)) {
+				found = true;
+				break;
+			}
 		}
+		if (found)
+			break;
 	}
 
 	/* all the pipes are disabled */
-	hrtimer_cancel(&irq->vblank_timer.timer);
-	return;
-
-out:
-	hrtimer_start(&irq->vblank_timer.timer,
-		ktime_add_ns(ktime_get(), irq->vblank_timer.period),
-		HRTIMER_MODE_ABS);
-
+	if (!found)
+		hrtimer_cancel(&irq->vblank_timer.timer);
+	else
+		hrtimer_start(&irq->vblank_timer.timer,
+			ktime_add_ns(ktime_get(), irq->vblank_timer.period),
+			HRTIMER_MODE_ABS);
+	mutex_unlock(&gvt->lock);
 }
 
 static void emulate_vblank_on_pipe(struct intel_vgpu *vgpu, int pipe)
@@ -393,8 +418,10 @@ static void emulate_vblank(struct intel_vgpu *vgpu)
 {
 	int pipe;
 
+	mutex_lock(&vgpu->vgpu_lock);
 	for_each_pipe(vgpu->gvt->dev_priv, pipe)
 		emulate_vblank_on_pipe(vgpu, pipe);
+	mutex_unlock(&vgpu->vgpu_lock);
 }
 
 /**
@@ -409,11 +436,10 @@ void intel_gvt_emulate_vblank(struct intel_gvt *gvt)
 	struct intel_vgpu *vgpu;
 	int id;
 
-	if (WARN_ON(!mutex_is_locked(&gvt->lock)))
-		return;
-
+	mutex_lock(&gvt->lock);
 	for_each_active_vgpu(gvt, vgpu, id)
 		emulate_vblank(vgpu);
+	mutex_unlock(&gvt->lock);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index 6f4f8e941fc2..6e3f56684f4e 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -164,7 +164,9 @@ static struct drm_i915_gem_object *vgpu_create_gem(struct drm_device *dev,
 
 	obj->read_domains = I915_GEM_DOMAIN_GTT;
 	obj->write_domain = 0;
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+	if (IS_SKYLAKE(dev_priv)
+		|| IS_KABYLAKE(dev_priv)
+		|| IS_BROXTON(dev_priv)) {
 		unsigned int tiling_mode = 0;
 		unsigned int stride = 0;
 
@@ -192,6 +194,14 @@ static struct drm_i915_gem_object *vgpu_create_gem(struct drm_device *dev,
 	return obj;
 }
 
+static bool validate_hotspot(struct intel_vgpu_cursor_plane_format *c)
+{
+	if (c && c->x_hot <= c->width && c->y_hot <= c->height)
+		return true;
+	else
+		return false;
+}
+
 static int vgpu_get_plane_info(struct drm_device *dev,
 		struct intel_vgpu *vgpu,
 		struct intel_vgpu_fb_info *info,
@@ -229,12 +239,14 @@ static int vgpu_get_plane_info(struct drm_device *dev,
 		info->x_pos = c.x_pos;
 		info->y_pos = c.y_pos;
 
-		/* The invalid cursor hotspot value is delivered to host
-		 * until we find a way to get the cursor hotspot info of
-		 * guest OS.
-		 */
-		info->x_hot = UINT_MAX;
-		info->y_hot = UINT_MAX;
+		if (validate_hotspot(&c)) {
+			info->x_hot = c.x_hot;
+			info->y_hot = c.y_hot;
+		} else {
+			info->x_hot = UINT_MAX;
+			info->y_hot = UINT_MAX;
+		}
+
 		info->size = (((info->stride * c.height * c.bpp) / 8)
 				+ (PAGE_SIZE - 1)) >> PAGE_SHIFT;
 	} else {
diff --git a/drivers/gpu/drm/i915/gvt/edid.c b/drivers/gpu/drm/i915/gvt/edid.c
index f61337632969..4b98539025c5 100644
--- a/drivers/gpu/drm/i915/gvt/edid.c
+++ b/drivers/gpu/drm/i915/gvt/edid.c
@@ -77,6 +77,20 @@ static unsigned char edid_get_byte(struct intel_vgpu *vgpu)
 	return chr;
 }
 
+static inline int bxt_get_port_from_gmbus0(u32 gmbus0)
+{
+	int port_select = gmbus0 & _GMBUS_PIN_SEL_MASK;
+	int port = -EINVAL;
+
+	if (port_select == 1)
+		port = PORT_B;
+	else if (port_select == 2)
+		port = PORT_C;
+	else if (port_select == 3)
+		port = PORT_D;
+	return port;
+}
+
 static inline int get_port_from_gmbus0(u32 gmbus0)
 {
 	int port_select = gmbus0 & _GMBUS_PIN_SEL_MASK;
@@ -105,6 +119,7 @@ static void reset_gmbus_controller(struct intel_vgpu *vgpu)
 static int gmbus0_mmio_write(struct intel_vgpu *vgpu,
 			unsigned int offset, void *p_data, unsigned int bytes)
 {
+	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	int port, pin_select;
 
 	memcpy(&vgpu_vreg(vgpu, offset), p_data, bytes);
@@ -116,7 +131,10 @@ static int gmbus0_mmio_write(struct intel_vgpu *vgpu,
 	if (pin_select == 0)
 		return 0;
 
-	port = get_port_from_gmbus0(pin_select);
+	if (IS_BROXTON(dev_priv))
+		port = bxt_get_port_from_gmbus0(pin_select);
+	else
+		port = get_port_from_gmbus0(pin_select);
 	if (WARN_ON(port < 0))
 		return 0;
 
diff --git a/drivers/gpu/drm/i915/gvt/execlist.h b/drivers/gpu/drm/i915/gvt/execlist.h
index 427e40e64d41..714d709829a2 100644
--- a/drivers/gpu/drm/i915/gvt/execlist.h
+++ b/drivers/gpu/drm/i915/gvt/execlist.h
@@ -146,14 +146,11 @@ struct execlist_ring_context {
 	u32 nop4;
 	u32 lri_cmd_2;
 	struct execlist_mmio_pair ctx_timestamp;
-	struct execlist_mmio_pair pdp3_UDW;
-	struct execlist_mmio_pair pdp3_LDW;
-	struct execlist_mmio_pair pdp2_UDW;
-	struct execlist_mmio_pair pdp2_LDW;
-	struct execlist_mmio_pair pdp1_UDW;
-	struct execlist_mmio_pair pdp1_LDW;
-	struct execlist_mmio_pair pdp0_UDW;
-	struct execlist_mmio_pair pdp0_LDW;
+	/*
+	 * pdps[8]={ pdp3_UDW, pdp3_LDW, pdp2_UDW, pdp2_LDW,
+	 *           pdp1_UDW, pdp1_LDW, pdp0_UDW, pdp0_LDW}
+	 */
+	struct execlist_mmio_pair pdps[8];
 };
 
 struct intel_vgpu_elsp_dwords {
diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.c b/drivers/gpu/drm/i915/gvt/fb_decoder.c
index 1c120683e958..face664be3e8 100644
--- a/drivers/gpu/drm/i915/gvt/fb_decoder.c
+++ b/drivers/gpu/drm/i915/gvt/fb_decoder.c
@@ -36,6 +36,7 @@
 #include <uapi/drm/drm_fourcc.h>
 #include "i915_drv.h"
 #include "gvt.h"
+#include "i915_pvinfo.h"
 
 #define PRIMARY_FORMAT_NUM	16
 struct pixel_format {
@@ -150,7 +151,9 @@ static u32 intel_vgpu_get_stride(struct intel_vgpu *vgpu, int pipe,
 	u32 stride_reg = vgpu_vreg_t(vgpu, DSPSTRIDE(pipe)) & stride_mask;
 	u32 stride = stride_reg;
 
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+	if (IS_SKYLAKE(dev_priv)
+		|| IS_KABYLAKE(dev_priv)
+		|| IS_BROXTON(dev_priv)) {
 		switch (tiled) {
 		case PLANE_CTL_TILED_LINEAR:
 			stride = stride_reg * 64;
@@ -214,7 +217,9 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu,
 	if (!plane->enabled)
 		return -ENODEV;
 
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+	if (IS_SKYLAKE(dev_priv)
+		|| IS_KABYLAKE(dev_priv)
+		|| IS_BROXTON(dev_priv)) {
 		plane->tiled = (val & PLANE_CTL_TILED_MASK) >>
 		_PLANE_CTL_TILED_SHIFT;
 		fmt = skl_format_to_drm(
@@ -256,7 +261,9 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu,
 	}
 
 	plane->stride = intel_vgpu_get_stride(vgpu, pipe, (plane->tiled << 10),
-		(IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) ?
+		(IS_SKYLAKE(dev_priv)
+		|| IS_KABYLAKE(dev_priv)
+		|| IS_BROXTON(dev_priv)) ?
 			(_PRI_PLANE_STRIDE_MASK >> 6) :
 				_PRI_PLANE_STRIDE_MASK, plane->bpp);
 
@@ -300,16 +307,16 @@ static int cursor_mode_to_drm(int mode)
 	int cursor_pixel_formats_index = 4;
 
 	switch (mode) {
-	case CURSOR_MODE_128_ARGB_AX:
+	case MCURSOR_MODE_128_ARGB_AX:
 		cursor_pixel_formats_index = 0;
 		break;
-	case CURSOR_MODE_256_ARGB_AX:
+	case MCURSOR_MODE_256_ARGB_AX:
 		cursor_pixel_formats_index = 1;
 		break;
-	case CURSOR_MODE_64_ARGB_AX:
+	case MCURSOR_MODE_64_ARGB_AX:
 		cursor_pixel_formats_index = 2;
 		break;
-	case CURSOR_MODE_64_32B_AX:
+	case MCURSOR_MODE_64_32B_AX:
 		cursor_pixel_formats_index = 3;
 		break;
 
@@ -342,8 +349,8 @@ int intel_vgpu_decode_cursor_plane(struct intel_vgpu *vgpu,
 		return -ENODEV;
 
 	val = vgpu_vreg_t(vgpu, CURCNTR(pipe));
-	mode = val & CURSOR_MODE;
-	plane->enabled = (mode != CURSOR_MODE_DISABLE);
+	mode = val & MCURSOR_MODE;
+	plane->enabled = (mode != MCURSOR_MODE_DISABLE);
 	if (!plane->enabled)
 		return -ENODEV;
 
@@ -384,6 +391,8 @@ int intel_vgpu_decode_cursor_plane(struct intel_vgpu *vgpu,
 	plane->y_pos = (val & _CURSOR_POS_Y_MASK) >> _CURSOR_POS_Y_SHIFT;
 	plane->y_sign = (val & _CURSOR_SIGN_Y_MASK) >> _CURSOR_SIGN_Y_SHIFT;
 
+	plane->x_hot = vgpu_vreg_t(vgpu, vgtif_reg(cursor_x_hot));
+	plane->y_hot = vgpu_vreg_t(vgpu, vgtif_reg(cursor_y_hot));
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/firmware.c b/drivers/gpu/drm/i915/gvt/firmware.c
index a73e1d418c22..4ac18b447247 100644
--- a/drivers/gpu/drm/i915/gvt/firmware.c
+++ b/drivers/gpu/drm/i915/gvt/firmware.c
@@ -162,7 +162,7 @@ static int verify_firmware(struct intel_gvt *gvt,
 
 	h = (struct gvt_firmware_header *)fw->data;
 
-	crc32_start = offsetof(struct gvt_firmware_header, crc32) + 4;
+	crc32_start = offsetofend(struct gvt_firmware_header, crc32);
 	mem = fw->data + crc32_start;
 
 #define VERIFY(s, a, b) do { \
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 4efec8fa6c1d..00aad8164dec 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -216,16 +216,22 @@ static struct gtt_type_table_entry gtt_type_table[] = {
 			GTT_TYPE_PPGTT_PDE_PT,
 			GTT_TYPE_PPGTT_PTE_PT,
 			GTT_TYPE_PPGTT_PTE_2M_ENTRY),
+	/* We take IPS bit as 'PSE' for PTE level. */
 	GTT_TYPE_TABLE_ENTRY(GTT_TYPE_PPGTT_PTE_PT,
 			GTT_TYPE_PPGTT_PTE_4K_ENTRY,
 			GTT_TYPE_PPGTT_PTE_PT,
 			GTT_TYPE_INVALID,
-			GTT_TYPE_INVALID),
+			GTT_TYPE_PPGTT_PTE_64K_ENTRY),
 	GTT_TYPE_TABLE_ENTRY(GTT_TYPE_PPGTT_PTE_4K_ENTRY,
 			GTT_TYPE_PPGTT_PTE_4K_ENTRY,
 			GTT_TYPE_PPGTT_PTE_PT,
 			GTT_TYPE_INVALID,
-			GTT_TYPE_INVALID),
+			GTT_TYPE_PPGTT_PTE_64K_ENTRY),
+	GTT_TYPE_TABLE_ENTRY(GTT_TYPE_PPGTT_PTE_64K_ENTRY,
+			GTT_TYPE_PPGTT_PTE_4K_ENTRY,
+			GTT_TYPE_PPGTT_PTE_PT,
+			GTT_TYPE_INVALID,
+			GTT_TYPE_PPGTT_PTE_64K_ENTRY),
 	GTT_TYPE_TABLE_ENTRY(GTT_TYPE_PPGTT_PTE_2M_ENTRY,
 			GTT_TYPE_PPGTT_PDE_ENTRY,
 			GTT_TYPE_PPGTT_PDE_PT,
@@ -339,8 +345,14 @@ static inline int gtt_set_entry64(void *pt,
 
 #define ADDR_1G_MASK	GENMASK_ULL(GTT_HAW - 1, 30)
 #define ADDR_2M_MASK	GENMASK_ULL(GTT_HAW - 1, 21)
+#define ADDR_64K_MASK	GENMASK_ULL(GTT_HAW - 1, 16)
 #define ADDR_4K_MASK	GENMASK_ULL(GTT_HAW - 1, 12)
 
+#define GTT_SPTE_FLAG_MASK GENMASK_ULL(62, 52)
+#define GTT_SPTE_FLAG_64K_SPLITED BIT(52) /* splited 64K gtt entry */
+
+#define GTT_64K_PTE_STRIDE 16
+
 static unsigned long gen8_gtt_get_pfn(struct intel_gvt_gtt_entry *e)
 {
 	unsigned long pfn;
@@ -349,6 +361,8 @@ static unsigned long gen8_gtt_get_pfn(struct intel_gvt_gtt_entry *e)
 		pfn = (e->val64 & ADDR_1G_MASK) >> PAGE_SHIFT;
 	else if (e->type == GTT_TYPE_PPGTT_PTE_2M_ENTRY)
 		pfn = (e->val64 & ADDR_2M_MASK) >> PAGE_SHIFT;
+	else if (e->type == GTT_TYPE_PPGTT_PTE_64K_ENTRY)
+		pfn = (e->val64 & ADDR_64K_MASK) >> PAGE_SHIFT;
 	else
 		pfn = (e->val64 & ADDR_4K_MASK) >> PAGE_SHIFT;
 	return pfn;
@@ -362,6 +376,9 @@ static void gen8_gtt_set_pfn(struct intel_gvt_gtt_entry *e, unsigned long pfn)
 	} else if (e->type == GTT_TYPE_PPGTT_PTE_2M_ENTRY) {
 		e->val64 &= ~ADDR_2M_MASK;
 		pfn &= (ADDR_2M_MASK >> PAGE_SHIFT);
+	} else if (e->type == GTT_TYPE_PPGTT_PTE_64K_ENTRY) {
+		e->val64 &= ~ADDR_64K_MASK;
+		pfn &= (ADDR_64K_MASK >> PAGE_SHIFT);
 	} else {
 		e->val64 &= ~ADDR_4K_MASK;
 		pfn &= (ADDR_4K_MASK >> PAGE_SHIFT);
@@ -372,16 +389,41 @@ static void gen8_gtt_set_pfn(struct intel_gvt_gtt_entry *e, unsigned long pfn)
 
 static bool gen8_gtt_test_pse(struct intel_gvt_gtt_entry *e)
 {
-	/* Entry doesn't have PSE bit. */
-	if (get_pse_type(e->type) == GTT_TYPE_INVALID)
-		return false;
+	return !!(e->val64 & _PAGE_PSE);
+}
 
-	e->type = get_entry_type(e->type);
-	if (!(e->val64 & _PAGE_PSE))
+static void gen8_gtt_clear_pse(struct intel_gvt_gtt_entry *e)
+{
+	if (gen8_gtt_test_pse(e)) {
+		switch (e->type) {
+		case GTT_TYPE_PPGTT_PTE_2M_ENTRY:
+			e->val64 &= ~_PAGE_PSE;
+			e->type = GTT_TYPE_PPGTT_PDE_ENTRY;
+			break;
+		case GTT_TYPE_PPGTT_PTE_1G_ENTRY:
+			e->type = GTT_TYPE_PPGTT_PDP_ENTRY;
+			e->val64 &= ~_PAGE_PSE;
+			break;
+		default:
+			WARN_ON(1);
+		}
+	}
+}
+
+static bool gen8_gtt_test_ips(struct intel_gvt_gtt_entry *e)
+{
+	if (GEM_WARN_ON(e->type != GTT_TYPE_PPGTT_PDE_ENTRY))
 		return false;
 
-	e->type = get_pse_type(e->type);
-	return true;
+	return !!(e->val64 & GEN8_PDE_IPS_64K);
+}
+
+static void gen8_gtt_clear_ips(struct intel_gvt_gtt_entry *e)
+{
+	if (GEM_WARN_ON(e->type != GTT_TYPE_PPGTT_PDE_ENTRY))
+		return;
+
+	e->val64 &= ~GEN8_PDE_IPS_64K;
 }
 
 static bool gen8_gtt_test_present(struct intel_gvt_gtt_entry *e)
@@ -408,6 +450,21 @@ static void gtt_entry_set_present(struct intel_gvt_gtt_entry *e)
 	e->val64 |= _PAGE_PRESENT;
 }
 
+static bool gen8_gtt_test_64k_splited(struct intel_gvt_gtt_entry *e)
+{
+	return !!(e->val64 & GTT_SPTE_FLAG_64K_SPLITED);
+}
+
+static void gen8_gtt_set_64k_splited(struct intel_gvt_gtt_entry *e)
+{
+	e->val64 |= GTT_SPTE_FLAG_64K_SPLITED;
+}
+
+static void gen8_gtt_clear_64k_splited(struct intel_gvt_gtt_entry *e)
+{
+	e->val64 &= ~GTT_SPTE_FLAG_64K_SPLITED;
+}
+
 /*
  * Per-platform GMA routines.
  */
@@ -440,6 +497,12 @@ static struct intel_gvt_gtt_pte_ops gen8_gtt_pte_ops = {
 	.set_present = gtt_entry_set_present,
 	.test_present = gen8_gtt_test_present,
 	.test_pse = gen8_gtt_test_pse,
+	.clear_pse = gen8_gtt_clear_pse,
+	.clear_ips = gen8_gtt_clear_ips,
+	.test_ips = gen8_gtt_test_ips,
+	.clear_64k_splited = gen8_gtt_clear_64k_splited,
+	.set_64k_splited = gen8_gtt_set_64k_splited,
+	.test_64k_splited = gen8_gtt_test_64k_splited,
 	.get_pfn = gen8_gtt_get_pfn,
 	.set_pfn = gen8_gtt_set_pfn,
 };
@@ -453,6 +516,27 @@ static struct intel_gvt_gtt_gma_ops gen8_gtt_gma_ops = {
 	.gma_to_pml4_index = gen8_gma_to_pml4_index,
 };
 
+/* Update entry type per pse and ips bit. */
+static void update_entry_type_for_real(struct intel_gvt_gtt_pte_ops *pte_ops,
+	struct intel_gvt_gtt_entry *entry, bool ips)
+{
+	switch (entry->type) {
+	case GTT_TYPE_PPGTT_PDE_ENTRY:
+	case GTT_TYPE_PPGTT_PDP_ENTRY:
+		if (pte_ops->test_pse(entry))
+			entry->type = get_pse_type(entry->type);
+		break;
+	case GTT_TYPE_PPGTT_PTE_4K_ENTRY:
+		if (ips)
+			entry->type = get_pse_type(entry->type);
+		break;
+	default:
+		GEM_BUG_ON(!gtt_type_is_entry(entry->type));
+	}
+
+	GEM_BUG_ON(entry->type == GTT_TYPE_INVALID);
+}
+
 /*
  * MM helpers.
  */
@@ -468,8 +552,7 @@ static void _ppgtt_get_root_entry(struct intel_vgpu_mm *mm,
 	pte_ops->get_entry(guest ? mm->ppgtt_mm.guest_pdps :
 			   mm->ppgtt_mm.shadow_pdps,
 			   entry, index, false, 0, mm->vgpu);
-
-	pte_ops->test_pse(entry);
+	update_entry_type_for_real(pte_ops, entry, false);
 }
 
 static inline void ppgtt_get_guest_root_entry(struct intel_vgpu_mm *mm,
@@ -574,7 +657,8 @@ static inline int ppgtt_spt_get_entry(
 	if (ret)
 		return ret;
 
-	ops->test_pse(e);
+	update_entry_type_for_real(ops, e, guest ?
+				   spt->guest_page.pde_ips : false);
 
 	gvt_vdbg_mm("read ppgtt entry, spt type %d, entry type %d, index %lu, value %llx\n",
 		    type, e->type, index, e->val64);
@@ -653,10 +737,12 @@ static void ppgtt_free_spt(struct intel_vgpu_ppgtt_spt *spt)
 
 	radix_tree_delete(&spt->vgpu->gtt.spt_tree, spt->shadow_page.mfn);
 
-	if (spt->guest_page.oos_page)
-		detach_oos_page(spt->vgpu, spt->guest_page.oos_page);
+	if (spt->guest_page.gfn) {
+		if (spt->guest_page.oos_page)
+			detach_oos_page(spt->vgpu, spt->guest_page.oos_page);
 
-	intel_vgpu_unregister_page_track(spt->vgpu, spt->guest_page.gfn);
+		intel_vgpu_unregister_page_track(spt->vgpu, spt->guest_page.gfn);
+	}
 
 	list_del_init(&spt->post_shadow_list);
 	free_spt(spt);
@@ -717,8 +803,9 @@ static inline struct intel_vgpu_ppgtt_spt *intel_vgpu_find_spt_by_mfn(
 
 static int reclaim_one_ppgtt_mm(struct intel_gvt *gvt);
 
+/* Allocate shadow page table without guest page. */
 static struct intel_vgpu_ppgtt_spt *ppgtt_alloc_spt(
-		struct intel_vgpu *vgpu, int type, unsigned long gfn)
+		struct intel_vgpu *vgpu, intel_gvt_gtt_type_t type)
 {
 	struct device *kdev = &vgpu->gvt->dev_priv->drm.pdev->dev;
 	struct intel_vgpu_ppgtt_spt *spt = NULL;
@@ -753,26 +840,12 @@ retry:
 	spt->shadow_page.vaddr = page_address(spt->shadow_page.page);
 	spt->shadow_page.mfn = daddr >> I915_GTT_PAGE_SHIFT;
 
-	/*
-	 * Init guest_page.
-	 */
-	spt->guest_page.type = type;
-	spt->guest_page.gfn = gfn;
-
-	ret = intel_vgpu_register_page_track(vgpu, spt->guest_page.gfn,
-					ppgtt_write_protection_handler, spt);
-	if (ret)
-		goto err_unmap_dma;
-
 	ret = radix_tree_insert(&vgpu->gtt.spt_tree, spt->shadow_page.mfn, spt);
 	if (ret)
-		goto err_unreg_page_track;
+		goto err_unmap_dma;
 
-	trace_spt_alloc(vgpu->id, spt, type, spt->shadow_page.mfn, gfn);
 	return spt;
 
-err_unreg_page_track:
-	intel_vgpu_unregister_page_track(vgpu, spt->guest_page.gfn);
 err_unmap_dma:
 	dma_unmap_page(kdev, daddr, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
 err_free_spt:
@@ -780,6 +853,37 @@ err_free_spt:
 	return ERR_PTR(ret);
 }
 
+/* Allocate shadow page table associated with specific gfn. */
+static struct intel_vgpu_ppgtt_spt *ppgtt_alloc_spt_gfn(
+		struct intel_vgpu *vgpu, intel_gvt_gtt_type_t type,
+		unsigned long gfn, bool guest_pde_ips)
+{
+	struct intel_vgpu_ppgtt_spt *spt;
+	int ret;
+
+	spt = ppgtt_alloc_spt(vgpu, type);
+	if (IS_ERR(spt))
+		return spt;
+
+	/*
+	 * Init guest_page.
+	 */
+	ret = intel_vgpu_register_page_track(vgpu, gfn,
+			ppgtt_write_protection_handler, spt);
+	if (ret) {
+		ppgtt_free_spt(spt);
+		return ERR_PTR(ret);
+	}
+
+	spt->guest_page.type = type;
+	spt->guest_page.gfn = gfn;
+	spt->guest_page.pde_ips = guest_pde_ips;
+
+	trace_spt_alloc(vgpu->id, spt, type, spt->shadow_page.mfn, gfn);
+
+	return spt;
+}
+
 #define pt_entry_size_shift(spt) \
 	((spt)->vgpu->gvt->device_info.gtt_entry_size_shift)
 
@@ -787,24 +891,38 @@ err_free_spt:
 	(I915_GTT_PAGE_SIZE >> pt_entry_size_shift(spt))
 
 #define for_each_present_guest_entry(spt, e, i) \
-	for (i = 0; i < pt_entries(spt); i++) \
+	for (i = 0; i < pt_entries(spt); \
+	     i += spt->guest_page.pde_ips ? GTT_64K_PTE_STRIDE : 1) \
 		if (!ppgtt_get_guest_entry(spt, e, i) && \
 		    spt->vgpu->gvt->gtt.pte_ops->test_present(e))
 
 #define for_each_present_shadow_entry(spt, e, i) \
-	for (i = 0; i < pt_entries(spt); i++) \
+	for (i = 0; i < pt_entries(spt); \
+	     i += spt->shadow_page.pde_ips ? GTT_64K_PTE_STRIDE : 1) \
 		if (!ppgtt_get_shadow_entry(spt, e, i) && \
 		    spt->vgpu->gvt->gtt.pte_ops->test_present(e))
 
-static void ppgtt_get_spt(struct intel_vgpu_ppgtt_spt *spt)
+#define for_each_shadow_entry(spt, e, i) \
+	for (i = 0; i < pt_entries(spt); \
+	     i += (spt->shadow_page.pde_ips ? GTT_64K_PTE_STRIDE : 1)) \
+		if (!ppgtt_get_shadow_entry(spt, e, i))
+
+static inline void ppgtt_get_spt(struct intel_vgpu_ppgtt_spt *spt)
 {
 	int v = atomic_read(&spt->refcount);
 
 	trace_spt_refcount(spt->vgpu->id, "inc", spt, v, (v + 1));
-
 	atomic_inc(&spt->refcount);
 }
 
+static inline int ppgtt_put_spt(struct intel_vgpu_ppgtt_spt *spt)
+{
+	int v = atomic_read(&spt->refcount);
+
+	trace_spt_refcount(spt->vgpu->id, "dec", spt, v, (v - 1));
+	return atomic_dec_return(&spt->refcount);
+}
+
 static int ppgtt_invalidate_spt(struct intel_vgpu_ppgtt_spt *spt);
 
 static int ppgtt_invalidate_spt_by_shadow_entry(struct intel_vgpu *vgpu,
@@ -843,7 +961,8 @@ static inline void ppgtt_invalidate_pte(struct intel_vgpu_ppgtt_spt *spt,
 	pfn = ops->get_pfn(entry);
 	type = spt->shadow_page.type;
 
-	if (pfn == vgpu->gtt.scratch_pt[type].page_mfn)
+	/* Uninitialized spte or unshadowed spte. */
+	if (!pfn || pfn == vgpu->gtt.scratch_pt[type].page_mfn)
 		return;
 
 	intel_gvt_hypervisor_dma_unmap_guest_page(vgpu, pfn << PAGE_SHIFT);
@@ -855,14 +974,11 @@ static int ppgtt_invalidate_spt(struct intel_vgpu_ppgtt_spt *spt)
 	struct intel_gvt_gtt_entry e;
 	unsigned long index;
 	int ret;
-	int v = atomic_read(&spt->refcount);
 
 	trace_spt_change(spt->vgpu->id, "die", spt,
 			spt->guest_page.gfn, spt->shadow_page.type);
 
-	trace_spt_refcount(spt->vgpu->id, "dec", spt, v, (v - 1));
-
-	if (atomic_dec_return(&spt->refcount) > 0)
+	if (ppgtt_put_spt(spt) > 0)
 		return 0;
 
 	for_each_present_shadow_entry(spt, &e, index) {
@@ -871,9 +987,15 @@ static int ppgtt_invalidate_spt(struct intel_vgpu_ppgtt_spt *spt)
 			gvt_vdbg_mm("invalidate 4K entry\n");
 			ppgtt_invalidate_pte(spt, &e);
 			break;
+		case GTT_TYPE_PPGTT_PTE_64K_ENTRY:
+			/* We don't setup 64K shadow entry so far. */
+			WARN(1, "suspicious 64K gtt entry\n");
+			continue;
 		case GTT_TYPE_PPGTT_PTE_2M_ENTRY:
+			gvt_vdbg_mm("invalidate 2M entry\n");
+			continue;
 		case GTT_TYPE_PPGTT_PTE_1G_ENTRY:
-			WARN(1, "GVT doesn't support 2M/1GB page\n");
+			WARN(1, "GVT doesn't support 1GB page\n");
 			continue;
 		case GTT_TYPE_PPGTT_PML4_ENTRY:
 		case GTT_TYPE_PPGTT_PDP_ENTRY:
@@ -899,6 +1021,22 @@ fail:
 	return ret;
 }
 
+static bool vgpu_ips_enabled(struct intel_vgpu *vgpu)
+{
+	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
+
+	if (INTEL_GEN(dev_priv) == 9 || INTEL_GEN(dev_priv) == 10) {
+		u32 ips = vgpu_vreg_t(vgpu, GEN8_GAMW_ECO_DEV_RW_IA) &
+			GAMW_ECO_ENABLE_64K_IPS_FIELD;
+
+		return ips == GAMW_ECO_ENABLE_64K_IPS_FIELD;
+	} else if (INTEL_GEN(dev_priv) >= 11) {
+		/* 64K paging only controlled by IPS bit in PTE now. */
+		return true;
+	} else
+		return false;
+}
+
 static int ppgtt_populate_spt(struct intel_vgpu_ppgtt_spt *spt);
 
 static struct intel_vgpu_ppgtt_spt *ppgtt_populate_spt_by_guest_entry(
@@ -906,35 +1044,54 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_populate_spt_by_guest_entry(
 {
 	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
 	struct intel_vgpu_ppgtt_spt *spt = NULL;
+	bool ips = false;
 	int ret;
 
 	GEM_BUG_ON(!gtt_type_is_pt(get_next_pt_type(we->type)));
 
+	if (we->type == GTT_TYPE_PPGTT_PDE_ENTRY)
+		ips = vgpu_ips_enabled(vgpu) && ops->test_ips(we);
+
 	spt = intel_vgpu_find_spt_by_gfn(vgpu, ops->get_pfn(we));
-	if (spt)
+	if (spt) {
 		ppgtt_get_spt(spt);
-	else {
+
+		if (ips != spt->guest_page.pde_ips) {
+			spt->guest_page.pde_ips = ips;
+
+			gvt_dbg_mm("reshadow PDE since ips changed\n");
+			clear_page(spt->shadow_page.vaddr);
+			ret = ppgtt_populate_spt(spt);
+			if (ret) {
+				ppgtt_put_spt(spt);
+				goto err;
+			}
+		}
+	} else {
 		int type = get_next_pt_type(we->type);
 
-		spt = ppgtt_alloc_spt(vgpu, type, ops->get_pfn(we));
+		spt = ppgtt_alloc_spt_gfn(vgpu, type, ops->get_pfn(we), ips);
 		if (IS_ERR(spt)) {
 			ret = PTR_ERR(spt);
-			goto fail;
+			goto err;
 		}
 
 		ret = intel_vgpu_enable_page_track(vgpu, spt->guest_page.gfn);
 		if (ret)
-			goto fail;
+			goto err_free_spt;
 
 		ret = ppgtt_populate_spt(spt);
 		if (ret)
-			goto fail;
+			goto err_free_spt;
 
 		trace_spt_change(vgpu->id, "new", spt, spt->guest_page.gfn,
 				 spt->shadow_page.type);
 	}
 	return spt;
-fail:
+
+err_free_spt:
+	ppgtt_free_spt(spt);
+err:
 	gvt_vgpu_err("fail: shadow page %p guest entry 0x%llx type %d\n",
 		     spt, we->val64, we->type);
 	return ERR_PTR(ret);
@@ -948,16 +1105,118 @@ static inline void ppgtt_generate_shadow_entry(struct intel_gvt_gtt_entry *se,
 	se->type = ge->type;
 	se->val64 = ge->val64;
 
+	/* Because we always split 64KB pages, so clear IPS in shadow PDE. */
+	if (se->type == GTT_TYPE_PPGTT_PDE_ENTRY)
+		ops->clear_ips(se);
+
 	ops->set_pfn(se, s->shadow_page.mfn);
 }
 
+/**
+ * Return 1 if 2MB huge gtt shadowing is possilbe, 0 if miscondition,
+ * negtive if found err.
+ */
+static int is_2MB_gtt_possible(struct intel_vgpu *vgpu,
+	struct intel_gvt_gtt_entry *entry)
+{
+	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
+	unsigned long pfn;
+
+	if (!HAS_PAGE_SIZES(vgpu->gvt->dev_priv, I915_GTT_PAGE_SIZE_2M))
+		return 0;
+
+	pfn = intel_gvt_hypervisor_gfn_to_mfn(vgpu, ops->get_pfn(entry));
+	if (pfn == INTEL_GVT_INVALID_ADDR)
+		return -EINVAL;
+
+	return PageTransHuge(pfn_to_page(pfn));
+}
+
+static int split_2MB_gtt_entry(struct intel_vgpu *vgpu,
+	struct intel_vgpu_ppgtt_spt *spt, unsigned long index,
+	struct intel_gvt_gtt_entry *se)
+{
+	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
+	struct intel_vgpu_ppgtt_spt *sub_spt;
+	struct intel_gvt_gtt_entry sub_se;
+	unsigned long start_gfn;
+	dma_addr_t dma_addr;
+	unsigned long sub_index;
+	int ret;
+
+	gvt_dbg_mm("Split 2M gtt entry, index %lu\n", index);
+
+	start_gfn = ops->get_pfn(se);
+
+	sub_spt = ppgtt_alloc_spt(vgpu, GTT_TYPE_PPGTT_PTE_PT);
+	if (IS_ERR(sub_spt))
+		return PTR_ERR(sub_spt);
+
+	for_each_shadow_entry(sub_spt, &sub_se, sub_index) {
+		ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu,
+				start_gfn + sub_index, PAGE_SIZE, &dma_addr);
+		if (ret) {
+			ppgtt_invalidate_spt(spt);
+			return ret;
+		}
+		sub_se.val64 = se->val64;
+
+		/* Copy the PAT field from PDE. */
+		sub_se.val64 &= ~_PAGE_PAT;
+		sub_se.val64 |= (se->val64 & _PAGE_PAT_LARGE) >> 5;
+
+		ops->set_pfn(&sub_se, dma_addr >> PAGE_SHIFT);
+		ppgtt_set_shadow_entry(sub_spt, &sub_se, sub_index);
+	}
+
+	/* Clear dirty field. */
+	se->val64 &= ~_PAGE_DIRTY;
+
+	ops->clear_pse(se);
+	ops->clear_ips(se);
+	ops->set_pfn(se, sub_spt->shadow_page.mfn);
+	ppgtt_set_shadow_entry(spt, se, index);
+	return 0;
+}
+
+static int split_64KB_gtt_entry(struct intel_vgpu *vgpu,
+	struct intel_vgpu_ppgtt_spt *spt, unsigned long index,
+	struct intel_gvt_gtt_entry *se)
+{
+	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
+	struct intel_gvt_gtt_entry entry = *se;
+	unsigned long start_gfn;
+	dma_addr_t dma_addr;
+	int i, ret;
+
+	gvt_vdbg_mm("Split 64K gtt entry, index %lu\n", index);
+
+	GEM_BUG_ON(index % GTT_64K_PTE_STRIDE);
+
+	start_gfn = ops->get_pfn(se);
+
+	entry.type = GTT_TYPE_PPGTT_PTE_4K_ENTRY;
+	ops->set_64k_splited(&entry);
+
+	for (i = 0; i < GTT_64K_PTE_STRIDE; i++) {
+		ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu,
+					start_gfn + i, PAGE_SIZE, &dma_addr);
+		if (ret)
+			return ret;
+
+		ops->set_pfn(&entry, dma_addr >> PAGE_SHIFT);
+		ppgtt_set_shadow_entry(spt, &entry, index + i);
+	}
+	return 0;
+}
+
 static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
 	struct intel_vgpu_ppgtt_spt *spt, unsigned long index,
 	struct intel_gvt_gtt_entry *ge)
 {
 	struct intel_gvt_gtt_pte_ops *pte_ops = vgpu->gvt->gtt.pte_ops;
 	struct intel_gvt_gtt_entry se = *ge;
-	unsigned long gfn;
+	unsigned long gfn, page_size = PAGE_SIZE;
 	dma_addr_t dma_addr;
 	int ret;
 
@@ -970,16 +1229,33 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
 	case GTT_TYPE_PPGTT_PTE_4K_ENTRY:
 		gvt_vdbg_mm("shadow 4K gtt entry\n");
 		break;
+	case GTT_TYPE_PPGTT_PTE_64K_ENTRY:
+		gvt_vdbg_mm("shadow 64K gtt entry\n");
+		/*
+		 * The layout of 64K page is special, the page size is
+		 * controlled by uper PDE. To be simple, we always split
+		 * 64K page to smaller 4K pages in shadow PT.
+		 */
+		return split_64KB_gtt_entry(vgpu, spt, index, &se);
 	case GTT_TYPE_PPGTT_PTE_2M_ENTRY:
+		gvt_vdbg_mm("shadow 2M gtt entry\n");
+		ret = is_2MB_gtt_possible(vgpu, ge);
+		if (ret == 0)
+			return split_2MB_gtt_entry(vgpu, spt, index, &se);
+		else if (ret < 0)
+			return ret;
+		page_size = I915_GTT_PAGE_SIZE_2M;
+		break;
 	case GTT_TYPE_PPGTT_PTE_1G_ENTRY:
-		gvt_vgpu_err("GVT doesn't support 2M/1GB entry\n");
+		gvt_vgpu_err("GVT doesn't support 1GB entry\n");
 		return -EINVAL;
 	default:
 		GEM_BUG_ON(1);
 	};
 
 	/* direct shadow */
-	ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, gfn, &dma_addr);
+	ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, gfn, page_size,
+						      &dma_addr);
 	if (ret)
 		return -ENXIO;
 
@@ -1062,8 +1338,12 @@ static int ppgtt_handle_guest_entry_removal(struct intel_vgpu_ppgtt_spt *spt,
 		ret = ppgtt_invalidate_spt(s);
 		if (ret)
 			goto fail;
-	} else
+	} else {
+		/* We don't setup 64K shadow entry so far. */
+		WARN(se->type == GTT_TYPE_PPGTT_PTE_64K_ENTRY,
+		     "suspicious 64K entry\n");
 		ppgtt_invalidate_pte(spt, se);
+	}
 
 	return 0;
 fail:
@@ -1286,7 +1566,7 @@ static int ppgtt_handle_guest_write_page_table(
 	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
 	struct intel_gvt_gtt_entry old_se;
 	int new_present;
-	int ret;
+	int i, ret;
 
 	new_present = ops->test_present(we);
 
@@ -1308,8 +1588,27 @@ static int ppgtt_handle_guest_write_page_table(
 		goto fail;
 
 	if (!new_present) {
-		ops->set_pfn(&old_se, vgpu->gtt.scratch_pt[type].page_mfn);
-		ppgtt_set_shadow_entry(spt, &old_se, index);
+		/* For 64KB splited entries, we need clear them all. */
+		if (ops->test_64k_splited(&old_se) &&
+		    !(index % GTT_64K_PTE_STRIDE)) {
+			gvt_vdbg_mm("remove splited 64K shadow entries\n");
+			for (i = 0; i < GTT_64K_PTE_STRIDE; i++) {
+				ops->clear_64k_splited(&old_se);
+				ops->set_pfn(&old_se,
+					vgpu->gtt.scratch_pt[type].page_mfn);
+				ppgtt_set_shadow_entry(spt, &old_se, index + i);
+			}
+		} else if (old_se.type == GTT_TYPE_PPGTT_PTE_2M_ENTRY ||
+			   old_se.type == GTT_TYPE_PPGTT_PTE_1G_ENTRY) {
+			ops->clear_pse(&old_se);
+			ops->set_pfn(&old_se,
+				     vgpu->gtt.scratch_pt[type].page_mfn);
+			ppgtt_set_shadow_entry(spt, &old_se, index);
+		} else {
+			ops->set_pfn(&old_se,
+				     vgpu->gtt.scratch_pt[type].page_mfn);
+			ppgtt_set_shadow_entry(spt, &old_se, index);
+		}
 	}
 
 	return 0;
@@ -1391,7 +1690,17 @@ static int ppgtt_handle_guest_write_page_table_bytes(
 
 	ppgtt_get_guest_entry(spt, &we, index);
 
-	ops->test_pse(&we);
+	/*
+	 * For page table which has 64K gtt entry, only PTE#0, PTE#16,
+	 * PTE#32, ... PTE#496 are used. Unused PTEs update should be
+	 * ignored.
+	 */
+	if (we.type == GTT_TYPE_PPGTT_PTE_64K_ENTRY &&
+	    (index % GTT_64K_PTE_STRIDE)) {
+		gvt_vdbg_mm("Ignore write to unused PTE entry, index %lu\n",
+			    index);
+		return 0;
+	}
 
 	if (bytes == info->gtt_entry_size) {
 		ret = ppgtt_handle_guest_write_page_table(spt, &we, index);
@@ -1939,7 +2248,7 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 		}
 
 		ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, gfn,
-							      &dma_addr);
+							PAGE_SIZE, &dma_addr);
 		if (ret) {
 			gvt_vgpu_err("fail to populate guest ggtt entry\n");
 			/* guest driver may read/write the entry when partial
@@ -2031,7 +2340,7 @@ static int alloc_scratch_pages(struct intel_vgpu *vgpu,
 	 * GTT_TYPE_PPGTT_PDE_PT level pt, that means this scratch_pt it self
 	 * is GTT_TYPE_PPGTT_PTE_PT, and full filled by scratch page mfn.
 	 */
-	if (type > GTT_TYPE_PPGTT_PTE_PT && type < GTT_TYPE_MAX) {
+	if (type > GTT_TYPE_PPGTT_PTE_PT) {
 		struct intel_gvt_gtt_entry se;
 
 		memset(&se, 0, sizeof(struct intel_gvt_gtt_entry));
@@ -2315,13 +2624,8 @@ int intel_gvt_init_gtt(struct intel_gvt *gvt)
 
 	gvt_dbg_core("init gtt\n");
 
-	if (IS_BROADWELL(gvt->dev_priv) || IS_SKYLAKE(gvt->dev_priv)
-		|| IS_KABYLAKE(gvt->dev_priv)) {
-		gvt->gtt.pte_ops = &gen8_gtt_pte_ops;
-		gvt->gtt.gma_ops = &gen8_gtt_gma_ops;
-	} else {
-		return -ENODEV;
-	}
+	gvt->gtt.pte_ops = &gen8_gtt_pte_ops;
+	gvt->gtt.gma_ops = &gen8_gtt_gma_ops;
 
 	page = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!page) {
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index 97e62647418a..7a9b36176efb 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -63,6 +63,12 @@ struct intel_gvt_gtt_pte_ops {
 	void (*clear_present)(struct intel_gvt_gtt_entry *e);
 	void (*set_present)(struct intel_gvt_gtt_entry *e);
 	bool (*test_pse)(struct intel_gvt_gtt_entry *e);
+	void (*clear_pse)(struct intel_gvt_gtt_entry *e);
+	bool (*test_ips)(struct intel_gvt_gtt_entry *e);
+	void (*clear_ips)(struct intel_gvt_gtt_entry *e);
+	bool (*test_64k_splited)(struct intel_gvt_gtt_entry *e);
+	void (*clear_64k_splited)(struct intel_gvt_gtt_entry *e);
+	void (*set_64k_splited)(struct intel_gvt_gtt_entry *e);
 	void (*set_pfn)(struct intel_gvt_gtt_entry *e, unsigned long pfn);
 	unsigned long (*get_pfn)(struct intel_gvt_gtt_entry *e);
 };
@@ -95,6 +101,7 @@ typedef enum {
 	GTT_TYPE_GGTT_PTE,
 
 	GTT_TYPE_PPGTT_PTE_4K_ENTRY,
+	GTT_TYPE_PPGTT_PTE_64K_ENTRY,
 	GTT_TYPE_PPGTT_PTE_2M_ENTRY,
 	GTT_TYPE_PPGTT_PTE_1G_ENTRY,
 
@@ -222,6 +229,7 @@ struct intel_vgpu_ppgtt_spt {
 
 	struct {
 		intel_gvt_gtt_type_t type;
+		bool pde_ips; /* for 64KB PTEs */
 		void *vaddr;
 		struct page *page;
 		unsigned long mfn;
@@ -229,6 +237,7 @@ struct intel_vgpu_ppgtt_spt {
 
 	struct {
 		intel_gvt_gtt_type_t type;
+		bool pde_ips; /* for 64KB PTEs */
 		unsigned long gfn;
 		unsigned long write_cnt;
 		struct intel_vgpu_oos_page *oos_page;
diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c
index 61bd14fcb649..712f9d14e720 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.c
+++ b/drivers/gpu/drm/i915/gvt/gvt.c
@@ -238,18 +238,15 @@ static void init_device_info(struct intel_gvt *gvt)
 	struct intel_gvt_device_info *info = &gvt->device_info;
 	struct pci_dev *pdev = gvt->dev_priv->drm.pdev;
 
-	if (IS_BROADWELL(gvt->dev_priv) || IS_SKYLAKE(gvt->dev_priv)
-		|| IS_KABYLAKE(gvt->dev_priv)) {
-		info->max_support_vgpus = 8;
-		info->cfg_space_size = PCI_CFG_SPACE_EXP_SIZE;
-		info->mmio_size = 2 * 1024 * 1024;
-		info->mmio_bar = 0;
-		info->gtt_start_offset = 8 * 1024 * 1024;
-		info->gtt_entry_size = 8;
-		info->gtt_entry_size_shift = 3;
-		info->gmadr_bytes_in_cmd = 8;
-		info->max_surface_size = 36 * 1024 * 1024;
-	}
+	info->max_support_vgpus = 8;
+	info->cfg_space_size = PCI_CFG_SPACE_EXP_SIZE;
+	info->mmio_size = 2 * 1024 * 1024;
+	info->mmio_bar = 0;
+	info->gtt_start_offset = 8 * 1024 * 1024;
+	info->gtt_entry_size = 8;
+	info->gtt_entry_size_shift = 3;
+	info->gmadr_bytes_in_cmd = 8;
+	info->max_surface_size = 36 * 1024 * 1024;
 	info->msi_cap_offset = pdev->msi_cap;
 }
 
@@ -271,11 +268,8 @@ static int gvt_service_thread(void *data)
 			continue;
 
 		if (test_and_clear_bit(INTEL_GVT_REQUEST_EMULATE_VBLANK,
-					(void *)&gvt->service_request)) {
-			mutex_lock(&gvt->lock);
+					(void *)&gvt->service_request))
 			intel_gvt_emulate_vblank(gvt);
-			mutex_unlock(&gvt->lock);
-		}
 
 		if (test_bit(INTEL_GVT_REQUEST_SCHED,
 				(void *)&gvt->service_request) ||
@@ -379,6 +373,7 @@ int intel_gvt_init_device(struct drm_i915_private *dev_priv)
 	idr_init(&gvt->vgpu_idr);
 	spin_lock_init(&gvt->scheduler.mmio_context_lock);
 	mutex_init(&gvt->lock);
+	mutex_init(&gvt->sched_lock);
 	gvt->dev_priv = dev_priv;
 
 	init_device_info(gvt);
@@ -473,3 +468,7 @@ out_clean_idr:
 	kfree(gvt);
 	return ret;
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_GVT_KVMGT)
+MODULE_SOFTDEP("pre: kvmgt");
+#endif
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index 858967daf04b..9a9671522774 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -170,12 +170,18 @@ struct intel_vgpu_submission {
 
 struct intel_vgpu {
 	struct intel_gvt *gvt;
+	struct mutex vgpu_lock;
 	int id;
 	unsigned long handle; /* vGPU handle used by hypervisor MPT modules */
 	bool active;
 	bool pv_notified;
 	bool failsafe;
 	unsigned int resetting_eng;
+
+	/* Both sched_data and sched_ctl can be seen a part of the global gvt
+	 * scheduler structure. So below 2 vgpu data are protected
+	 * by sched_lock, not vgpu_lock.
+	 */
 	void *sched_data;
 	struct vgpu_sched_ctl sched_ctl;
 
@@ -296,7 +302,13 @@ struct intel_vgpu_type {
 };
 
 struct intel_gvt {
+	/* GVT scope lock, protect GVT itself, and all resource currently
+	 * not yet protected by special locks(vgpu and scheduler lock).
+	 */
 	struct mutex lock;
+	/* scheduler scope lock, protect gvt and vgpu schedule related data */
+	struct mutex sched_lock;
+
 	struct drm_i915_private *dev_priv;
 	struct idr vgpu_idr;	/* vGPU IDR pool */
 
@@ -316,6 +328,10 @@ struct intel_gvt {
 
 	struct task_struct *service_thread;
 	wait_queue_head_t service_thread_wq;
+
+	/* service_request is always used in bit operation, we should always
+	 * use it with atomic bit ops so that no need to use gvt big lock.
+	 */
 	unsigned long service_request;
 
 	struct {
@@ -363,9 +379,9 @@ int intel_gvt_load_firmware(struct intel_gvt *gvt);
 #define gvt_aperture_sz(gvt)	  (gvt->dev_priv->ggtt.mappable_end)
 #define gvt_aperture_pa_base(gvt) (gvt->dev_priv->ggtt.gmadr.start)
 
-#define gvt_ggtt_gm_sz(gvt)	  (gvt->dev_priv->ggtt.base.total)
+#define gvt_ggtt_gm_sz(gvt)	  (gvt->dev_priv->ggtt.vm.total)
 #define gvt_ggtt_sz(gvt) \
-	((gvt->dev_priv->ggtt.base.total >> PAGE_SHIFT) << 3)
+	((gvt->dev_priv->ggtt.vm.total >> PAGE_SHIFT) << 3)
 #define gvt_hidden_sz(gvt)	  (gvt_ggtt_gm_sz(gvt) - gvt_aperture_sz(gvt))
 
 #define gvt_aperture_gmadr_base(gvt) (0)
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 8f1caacdc78a..7a58ca555197 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -55,6 +55,8 @@ unsigned long intel_gvt_get_device_type(struct intel_gvt *gvt)
 		return D_SKL;
 	else if (IS_KABYLAKE(gvt->dev_priv))
 		return D_KBL;
+	else if (IS_BROXTON(gvt->dev_priv))
+		return D_BXT;
 
 	return 0;
 }
@@ -208,6 +210,31 @@ static int sanitize_fence_mmio_access(struct intel_vgpu *vgpu,
 	return 0;
 }
 
+static int gamw_echo_dev_rw_ia_write(struct intel_vgpu *vgpu,
+		unsigned int offset, void *p_data, unsigned int bytes)
+{
+	u32 ips = (*(u32 *)p_data) & GAMW_ECO_ENABLE_64K_IPS_FIELD;
+
+	if (INTEL_GEN(vgpu->gvt->dev_priv) <= 10) {
+		if (ips == GAMW_ECO_ENABLE_64K_IPS_FIELD)
+			gvt_dbg_core("vgpu%d: ips enabled\n", vgpu->id);
+		else if (!ips)
+			gvt_dbg_core("vgpu%d: ips disabled\n", vgpu->id);
+		else {
+			/* All engines must be enabled together for vGPU,
+			 * since we don't know which engine the ppgtt will
+			 * bind to when shadowing.
+			 */
+			gvt_vgpu_err("Unsupported IPS setting %x, cannot enable 64K gtt.\n",
+				     ips);
+			return -EINVAL;
+		}
+	}
+
+	write_vreg(vgpu, offset, p_data, bytes);
+	return 0;
+}
+
 static int fence_mmio_read(struct intel_vgpu *vgpu, unsigned int off,
 		void *p_data, unsigned int bytes)
 {
@@ -255,7 +282,8 @@ static int mul_force_wake_write(struct intel_vgpu *vgpu,
 	new = CALC_MODE_MASK_REG(old, *(u32 *)p_data);
 
 	if (IS_SKYLAKE(vgpu->gvt->dev_priv)
-		|| IS_KABYLAKE(vgpu->gvt->dev_priv)) {
+		|| IS_KABYLAKE(vgpu->gvt->dev_priv)
+		|| IS_BROXTON(vgpu->gvt->dev_priv)) {
 		switch (offset) {
 		case FORCEWAKE_RENDER_GEN9_REG:
 			ack_reg_offset = FORCEWAKE_ACK_RENDER_GEN9_REG;
@@ -316,6 +344,7 @@ static int gdrst_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 		}
 	}
 
+	/* vgpu_lock already hold by emulate mmio r/w */
 	intel_gvt_reset_vgpu_locked(vgpu, false, engine_mask);
 
 	/* sw will wait for the device to ack the reset request */
@@ -420,7 +449,10 @@ static int pipeconf_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 		vgpu_vreg(vgpu, offset) |= I965_PIPECONF_ACTIVE;
 	else
 		vgpu_vreg(vgpu, offset) &= ~I965_PIPECONF_ACTIVE;
+	/* vgpu_lock already hold by emulate mmio r/w */
+	mutex_unlock(&vgpu->vgpu_lock);
 	intel_gvt_check_vblank_emulation(vgpu->gvt);
+	mutex_lock(&vgpu->vgpu_lock);
 	return 0;
 }
 
@@ -857,7 +889,8 @@ static int dp_aux_ch_ctl_mmio_write(struct intel_vgpu *vgpu,
 	data = vgpu_vreg(vgpu, offset);
 
 	if ((IS_SKYLAKE(vgpu->gvt->dev_priv)
-		|| IS_KABYLAKE(vgpu->gvt->dev_priv))
+		|| IS_KABYLAKE(vgpu->gvt->dev_priv)
+		|| IS_BROXTON(vgpu->gvt->dev_priv))
 		&& offset != _REG_SKL_DP_AUX_CH_CTL(port_index)) {
 		/* SKL DPB/C/D aux ctl register changed */
 		return 0;
@@ -1209,8 +1242,8 @@ static int pvinfo_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 		ret = handle_g2v_notification(vgpu, data);
 		break;
 	/* add xhot and yhot to handled list to avoid error log */
-	case 0x78830:
-	case 0x78834:
+	case _vgtif_reg(cursor_x_hot):
+	case _vgtif_reg(cursor_y_hot):
 	case _vgtif_reg(pdp[0].lo):
 	case _vgtif_reg(pdp[0].hi):
 	case _vgtif_reg(pdp[1].lo):
@@ -1369,6 +1402,16 @@ static int mailbox_write(struct intel_vgpu *vgpu, unsigned int offset,
 				*data0 = 0x1e1a1100;
 			else
 				*data0 = 0x61514b3d;
+		} else if (IS_BROXTON(vgpu->gvt->dev_priv)) {
+			/**
+			 * "Read memory latency" command on gen9.
+			 * Below memory latency values are read
+			 * from Broxton MRB.
+			 */
+			if (!*data0)
+				*data0 = 0x16080707;
+			else
+				*data0 = 0x16161616;
 		}
 		break;
 	case SKL_PCODE_CDCLK_CONTROL:
@@ -1426,8 +1469,11 @@ static int skl_power_well_ctl_write(struct intel_vgpu *vgpu,
 {
 	u32 v = *(u32 *)p_data;
 
-	v &= (1 << 31) | (1 << 29) | (1 << 9) |
-	     (1 << 7) | (1 << 5) | (1 << 3) | (1 << 1);
+	if (IS_BROXTON(vgpu->gvt->dev_priv))
+		v &= (1 << 31) | (1 << 29);
+	else
+		v &= (1 << 31) | (1 << 29) | (1 << 9) |
+			(1 << 7) | (1 << 5) | (1 << 3) | (1 << 1);
 	v |= (v >> 1);
 
 	return intel_vgpu_default_mmio_write(vgpu, offset, &v, bytes);
@@ -1447,6 +1493,109 @@ static int skl_lcpll_write(struct intel_vgpu *vgpu, unsigned int offset,
 	return 0;
 }
 
+static int bxt_de_pll_enable_write(struct intel_vgpu *vgpu,
+		unsigned int offset, void *p_data, unsigned int bytes)
+{
+	u32 v = *(u32 *)p_data;
+
+	if (v & BXT_DE_PLL_PLL_ENABLE)
+		v |= BXT_DE_PLL_LOCK;
+
+	vgpu_vreg(vgpu, offset) = v;
+
+	return 0;
+}
+
+static int bxt_port_pll_enable_write(struct intel_vgpu *vgpu,
+		unsigned int offset, void *p_data, unsigned int bytes)
+{
+	u32 v = *(u32 *)p_data;
+
+	if (v & PORT_PLL_ENABLE)
+		v |= PORT_PLL_LOCK;
+
+	vgpu_vreg(vgpu, offset) = v;
+
+	return 0;
+}
+
+static int bxt_phy_ctl_family_write(struct intel_vgpu *vgpu,
+		unsigned int offset, void *p_data, unsigned int bytes)
+{
+	u32 v = *(u32 *)p_data;
+	u32 data = v & COMMON_RESET_DIS ? BXT_PHY_LANE_ENABLED : 0;
+
+	vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_A) = data;
+	vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_B) = data;
+	vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_C) = data;
+
+	vgpu_vreg(vgpu, offset) = v;
+
+	return 0;
+}
+
+static int bxt_port_tx_dw3_read(struct intel_vgpu *vgpu,
+		unsigned int offset, void *p_data, unsigned int bytes)
+{
+	u32 v = vgpu_vreg(vgpu, offset);
+
+	v &= ~UNIQUE_TRANGE_EN_METHOD;
+
+	vgpu_vreg(vgpu, offset) = v;
+
+	return intel_vgpu_default_mmio_read(vgpu, offset, p_data, bytes);
+}
+
+static int bxt_pcs_dw12_grp_write(struct intel_vgpu *vgpu,
+		unsigned int offset, void *p_data, unsigned int bytes)
+{
+	u32 v = *(u32 *)p_data;
+
+	if (offset == _PORT_PCS_DW12_GRP_A || offset == _PORT_PCS_DW12_GRP_B) {
+		vgpu_vreg(vgpu, offset - 0x600) = v;
+		vgpu_vreg(vgpu, offset - 0x800) = v;
+	} else {
+		vgpu_vreg(vgpu, offset - 0x400) = v;
+		vgpu_vreg(vgpu, offset - 0x600) = v;
+	}
+
+	vgpu_vreg(vgpu, offset) = v;
+
+	return 0;
+}
+
+static int bxt_gt_disp_pwron_write(struct intel_vgpu *vgpu,
+		unsigned int offset, void *p_data, unsigned int bytes)
+{
+	u32 v = *(u32 *)p_data;
+
+	if (v & BIT(0)) {
+		vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY0)) &=
+			~PHY_RESERVED;
+		vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY0)) |=
+			PHY_POWER_GOOD;
+	}
+
+	if (v & BIT(1)) {
+		vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY1)) &=
+			~PHY_RESERVED;
+		vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY1)) |=
+			PHY_POWER_GOOD;
+	}
+
+
+	vgpu_vreg(vgpu, offset) = v;
+
+	return 0;
+}
+
+static int bxt_edp_psr_imr_iir_write(struct intel_vgpu *vgpu,
+		unsigned int offset, void *p_data, unsigned int bytes)
+{
+	vgpu_vreg(vgpu, offset) = 0;
+	return 0;
+}
+
 static int mmio_read_from_hw(struct intel_vgpu *vgpu,
 		unsigned int offset, void *p_data, unsigned int bytes)
 {
@@ -1657,7 +1806,9 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 
 	MMIO_RING_DFH(RING_HWSTAM, D_ALL, F_CMD_ACCESS, NULL, NULL);
 
-	MMIO_GM_RDR(RENDER_HWS_PGA_GEN7, D_ALL, NULL, NULL);
+	MMIO_DH(GEN8_GAMW_ECO_DEV_RW_IA, D_BDW_PLUS, NULL,
+		gamw_echo_dev_rw_ia_write);
+
 	MMIO_GM_RDR(BSD_HWS_PGA_GEN7, D_ALL, NULL, NULL);
 	MMIO_GM_RDR(BLT_HWS_PGA_GEN7, D_ALL, NULL, NULL);
 	MMIO_GM_RDR(VEBOX_HWS_PGA_GEN7, D_ALL, NULL, NULL);
@@ -2670,17 +2821,17 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(_MMIO(0x45504), D_SKL_PLUS);
 	MMIO_D(_MMIO(0x45520), D_SKL_PLUS);
 	MMIO_D(_MMIO(0x46000), D_SKL_PLUS);
-	MMIO_DH(_MMIO(0x46010), D_SKL | D_KBL, NULL, skl_lcpll_write);
-	MMIO_DH(_MMIO(0x46014), D_SKL | D_KBL, NULL, skl_lcpll_write);
-	MMIO_D(_MMIO(0x6C040), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x6C048), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x6C050), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x6C044), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x6C04C), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x6C054), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x6c058), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x6c05c), D_SKL | D_KBL);
-	MMIO_DH(_MMIO(0x6c060), D_SKL | D_KBL, dpll_status_read, NULL);
+	MMIO_DH(_MMIO(0x46010), D_SKL_PLUS, NULL, skl_lcpll_write);
+	MMIO_DH(_MMIO(0x46014), D_SKL_PLUS, NULL, skl_lcpll_write);
+	MMIO_D(_MMIO(0x6C040), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x6C048), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x6C050), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x6C044), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x6C04C), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x6C054), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x6c058), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x6c05c), D_SKL_PLUS);
+	MMIO_DH(_MMIO(0x6c060), D_SKL_PLUS, dpll_status_read, NULL);
 
 	MMIO_DH(SKL_PS_WIN_POS(PIPE_A, 0), D_SKL_PLUS, NULL, pf_write);
 	MMIO_DH(SKL_PS_WIN_POS(PIPE_A, 1), D_SKL_PLUS, NULL, pf_write);
@@ -2805,53 +2956,57 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(_MMIO(0x7239c), D_SKL_PLUS);
 	MMIO_D(_MMIO(0x7039c), D_SKL_PLUS);
 
-	MMIO_D(_MMIO(0x8f074), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x8f004), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x8f034), D_SKL | D_KBL);
+	MMIO_D(_MMIO(0x8f074), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x8f004), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x8f034), D_SKL_PLUS);
 
-	MMIO_D(_MMIO(0xb11c), D_SKL | D_KBL);
+	MMIO_D(_MMIO(0xb11c), D_SKL_PLUS);
 
-	MMIO_D(_MMIO(0x51000), D_SKL | D_KBL);
+	MMIO_D(_MMIO(0x51000), D_SKL_PLUS);
 	MMIO_D(_MMIO(0x6c00c), D_SKL_PLUS);
 
-	MMIO_F(_MMIO(0xc800), 0x7f8, F_CMD_ACCESS, 0, 0, D_SKL | D_KBL, NULL, NULL);
-	MMIO_F(_MMIO(0xb020), 0x80, F_CMD_ACCESS, 0, 0, D_SKL | D_KBL, NULL, NULL);
+	MMIO_F(_MMIO(0xc800), 0x7f8, F_CMD_ACCESS, 0, 0, D_SKL_PLUS,
+		NULL, NULL);
+	MMIO_F(_MMIO(0xb020), 0x80, F_CMD_ACCESS, 0, 0, D_SKL_PLUS,
+		NULL, NULL);
 
 	MMIO_D(RPM_CONFIG0, D_SKL_PLUS);
 	MMIO_D(_MMIO(0xd08), D_SKL_PLUS);
 	MMIO_D(RC6_LOCATION, D_SKL_PLUS);
 	MMIO_DFH(_MMIO(0x20e0), D_SKL_PLUS, F_MODE_MASK, NULL, NULL);
-	MMIO_DFH(_MMIO(0x20ec), D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(_MMIO(0x20ec), D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS,
+		NULL, NULL);
 
 	/* TRTT */
-	MMIO_DFH(_MMIO(0x4de0), D_SKL | D_KBL, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(_MMIO(0x4de4), D_SKL | D_KBL, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(_MMIO(0x4de8), D_SKL | D_KBL, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(_MMIO(0x4dec), D_SKL | D_KBL, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(_MMIO(0x4df0), D_SKL | D_KBL, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(_MMIO(0x4df4), D_SKL | D_KBL, F_CMD_ACCESS, NULL, gen9_trtte_write);
-	MMIO_DH(_MMIO(0x4dfc), D_SKL | D_KBL, NULL, gen9_trtt_chicken_write);
+	MMIO_DFH(_MMIO(0x4de0), D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(_MMIO(0x4de4), D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(_MMIO(0x4de8), D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(_MMIO(0x4dec), D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(_MMIO(0x4df0), D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(_MMIO(0x4df4), D_SKL_PLUS, F_CMD_ACCESS,
+		NULL, gen9_trtte_write);
+	MMIO_DH(_MMIO(0x4dfc), D_SKL_PLUS, NULL, gen9_trtt_chicken_write);
 
-	MMIO_D(_MMIO(0x45008), D_SKL | D_KBL);
+	MMIO_D(_MMIO(0x45008), D_SKL_PLUS);
 
-	MMIO_D(_MMIO(0x46430), D_SKL | D_KBL);
+	MMIO_D(_MMIO(0x46430), D_SKL_PLUS);
 
-	MMIO_D(_MMIO(0x46520), D_SKL | D_KBL);
+	MMIO_D(_MMIO(0x46520), D_SKL_PLUS);
 
-	MMIO_D(_MMIO(0xc403c), D_SKL | D_KBL);
+	MMIO_D(_MMIO(0xc403c), D_SKL_PLUS);
 	MMIO_D(_MMIO(0xb004), D_SKL_PLUS);
 	MMIO_DH(DMA_CTRL, D_SKL_PLUS, NULL, dma_ctrl_write);
 
 	MMIO_D(_MMIO(0x65900), D_SKL_PLUS);
-	MMIO_D(_MMIO(0x1082c0), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x4068), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x67054), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x6e560), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x6e554), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x2b20), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x65f00), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x65f08), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x320f0), D_SKL | D_KBL);
+	MMIO_D(_MMIO(0x1082c0), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x4068), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x67054), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x6e560), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x6e554), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x2b20), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x65f00), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x65f08), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x320f0), D_SKL_PLUS);
 
 	MMIO_D(_MMIO(0x70034), D_SKL_PLUS);
 	MMIO_D(_MMIO(0x71034), D_SKL_PLUS);
@@ -2869,11 +3024,188 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 
 	MMIO_D(_MMIO(0x44500), D_SKL_PLUS);
 	MMIO_DFH(GEN9_CSFE_CHICKEN1_RCS, D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(GEN8_HDC_CHICKEN1, D_SKL | D_KBL, F_MODE_MASK | F_CMD_ACCESS,
+	MMIO_DFH(GEN8_HDC_CHICKEN1, D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS,
 		NULL, NULL);
 
 	MMIO_D(_MMIO(0x4ab8), D_KBL);
-	MMIO_D(_MMIO(0x2248), D_SKL_PLUS | D_KBL);
+	MMIO_D(_MMIO(0x2248), D_KBL | D_SKL);
+
+	return 0;
+}
+
+static int init_bxt_mmio_info(struct intel_gvt *gvt)
+{
+	struct drm_i915_private *dev_priv = gvt->dev_priv;
+	int ret;
+
+	MMIO_F(_MMIO(0x80000), 0x3000, 0, 0, 0, D_BXT, NULL, NULL);
+
+	MMIO_D(GEN7_SAMPLER_INSTDONE, D_BXT);
+	MMIO_D(GEN7_ROW_INSTDONE, D_BXT);
+	MMIO_D(GEN8_FAULT_TLB_DATA0, D_BXT);
+	MMIO_D(GEN8_FAULT_TLB_DATA1, D_BXT);
+	MMIO_D(ERROR_GEN6, D_BXT);
+	MMIO_D(DONE_REG, D_BXT);
+	MMIO_D(EIR, D_BXT);
+	MMIO_D(PGTBL_ER, D_BXT);
+	MMIO_D(_MMIO(0x4194), D_BXT);
+	MMIO_D(_MMIO(0x4294), D_BXT);
+	MMIO_D(_MMIO(0x4494), D_BXT);
+
+	MMIO_RING_D(RING_PSMI_CTL, D_BXT);
+	MMIO_RING_D(RING_DMA_FADD, D_BXT);
+	MMIO_RING_D(RING_DMA_FADD_UDW, D_BXT);
+	MMIO_RING_D(RING_IPEHR, D_BXT);
+	MMIO_RING_D(RING_INSTPS, D_BXT);
+	MMIO_RING_D(RING_BBADDR_UDW, D_BXT);
+	MMIO_RING_D(RING_BBSTATE, D_BXT);
+	MMIO_RING_D(RING_IPEIR, D_BXT);
+
+	MMIO_F(SOFT_SCRATCH(0), 16 * 4, 0, 0, 0, D_BXT, NULL, NULL);
+
+	MMIO_DH(BXT_P_CR_GT_DISP_PWRON, D_BXT, NULL, bxt_gt_disp_pwron_write);
+	MMIO_D(BXT_RP_STATE_CAP, D_BXT);
+	MMIO_DH(BXT_PHY_CTL_FAMILY(DPIO_PHY0), D_BXT,
+		NULL, bxt_phy_ctl_family_write);
+	MMIO_DH(BXT_PHY_CTL_FAMILY(DPIO_PHY1), D_BXT,
+		NULL, bxt_phy_ctl_family_write);
+	MMIO_D(BXT_PHY_CTL(PORT_A), D_BXT);
+	MMIO_D(BXT_PHY_CTL(PORT_B), D_BXT);
+	MMIO_D(BXT_PHY_CTL(PORT_C), D_BXT);
+	MMIO_DH(BXT_PORT_PLL_ENABLE(PORT_A), D_BXT,
+		NULL, bxt_port_pll_enable_write);
+	MMIO_DH(BXT_PORT_PLL_ENABLE(PORT_B), D_BXT,
+		NULL, bxt_port_pll_enable_write);
+	MMIO_DH(BXT_PORT_PLL_ENABLE(PORT_C), D_BXT, NULL,
+		bxt_port_pll_enable_write);
+
+	MMIO_D(BXT_PORT_CL1CM_DW0(DPIO_PHY0), D_BXT);
+	MMIO_D(BXT_PORT_CL1CM_DW9(DPIO_PHY0), D_BXT);
+	MMIO_D(BXT_PORT_CL1CM_DW10(DPIO_PHY0), D_BXT);
+	MMIO_D(BXT_PORT_CL1CM_DW28(DPIO_PHY0), D_BXT);
+	MMIO_D(BXT_PORT_CL1CM_DW30(DPIO_PHY0), D_BXT);
+	MMIO_D(BXT_PORT_CL2CM_DW6(DPIO_PHY0), D_BXT);
+	MMIO_D(BXT_PORT_REF_DW3(DPIO_PHY0), D_BXT);
+	MMIO_D(BXT_PORT_REF_DW6(DPIO_PHY0), D_BXT);
+	MMIO_D(BXT_PORT_REF_DW8(DPIO_PHY0), D_BXT);
+
+	MMIO_D(BXT_PORT_CL1CM_DW0(DPIO_PHY1), D_BXT);
+	MMIO_D(BXT_PORT_CL1CM_DW9(DPIO_PHY1), D_BXT);
+	MMIO_D(BXT_PORT_CL1CM_DW10(DPIO_PHY1), D_BXT);
+	MMIO_D(BXT_PORT_CL1CM_DW28(DPIO_PHY1), D_BXT);
+	MMIO_D(BXT_PORT_CL1CM_DW30(DPIO_PHY1), D_BXT);
+	MMIO_D(BXT_PORT_CL2CM_DW6(DPIO_PHY1), D_BXT);
+	MMIO_D(BXT_PORT_REF_DW3(DPIO_PHY1), D_BXT);
+	MMIO_D(BXT_PORT_REF_DW6(DPIO_PHY1), D_BXT);
+	MMIO_D(BXT_PORT_REF_DW8(DPIO_PHY1), D_BXT);
+
+	MMIO_D(BXT_PORT_PLL_EBB_0(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PLL_EBB_4(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW10_LN01(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW10_GRP(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW12_LN01(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW12_LN23(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_DH(BXT_PORT_PCS_DW12_GRP(DPIO_PHY0, DPIO_CH0), D_BXT,
+		NULL, bxt_pcs_dw12_grp_write);
+	MMIO_D(BXT_PORT_TX_DW2_LN0(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW2_GRP(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_DH(BXT_PORT_TX_DW3_LN0(DPIO_PHY0, DPIO_CH0), D_BXT,
+		bxt_port_tx_dw3_read, NULL);
+	MMIO_D(BXT_PORT_TX_DW3_GRP(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW4_LN0(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW4_GRP(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY0, DPIO_CH0, 0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY0, DPIO_CH0, 1), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY0, DPIO_CH0, 2), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY0, DPIO_CH0, 3), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH0, 0), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH0, 1), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH0, 2), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH0, 3), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH0, 6), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH0, 8), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH0, 9), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH0, 10), D_BXT);
+
+	MMIO_D(BXT_PORT_PLL_EBB_0(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_D(BXT_PORT_PLL_EBB_4(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW10_LN01(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW10_GRP(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW12_LN01(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW12_LN23(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_DH(BXT_PORT_PCS_DW12_GRP(DPIO_PHY0, DPIO_CH1), D_BXT,
+		NULL, bxt_pcs_dw12_grp_write);
+	MMIO_D(BXT_PORT_TX_DW2_LN0(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW2_GRP(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_DH(BXT_PORT_TX_DW3_LN0(DPIO_PHY0, DPIO_CH1), D_BXT,
+		bxt_port_tx_dw3_read, NULL);
+	MMIO_D(BXT_PORT_TX_DW3_GRP(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW4_LN0(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW4_GRP(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY0, DPIO_CH1, 0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY0, DPIO_CH1, 1), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY0, DPIO_CH1, 2), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY0, DPIO_CH1, 3), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH1, 0), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH1, 1), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH1, 2), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH1, 3), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH1, 6), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH1, 8), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH1, 9), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH1, 10), D_BXT);
+
+	MMIO_D(BXT_PORT_PLL_EBB_0(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PLL_EBB_4(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW10_LN01(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW10_GRP(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW12_LN01(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW12_LN23(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_DH(BXT_PORT_PCS_DW12_GRP(DPIO_PHY1, DPIO_CH0), D_BXT,
+		NULL, bxt_pcs_dw12_grp_write);
+	MMIO_D(BXT_PORT_TX_DW2_LN0(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW2_GRP(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_DH(BXT_PORT_TX_DW3_LN0(DPIO_PHY1, DPIO_CH0), D_BXT,
+		bxt_port_tx_dw3_read, NULL);
+	MMIO_D(BXT_PORT_TX_DW3_GRP(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW4_LN0(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW4_GRP(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY1, DPIO_CH0, 0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY1, DPIO_CH0, 1), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY1, DPIO_CH0, 2), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY1, DPIO_CH0, 3), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY1, DPIO_CH0, 0), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY1, DPIO_CH0, 1), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY1, DPIO_CH0, 2), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY1, DPIO_CH0, 3), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY1, DPIO_CH0, 6), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY1, DPIO_CH0, 8), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY1, DPIO_CH0, 9), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY1, DPIO_CH0, 10), D_BXT);
+
+	MMIO_D(BXT_DE_PLL_CTL, D_BXT);
+	MMIO_DH(BXT_DE_PLL_ENABLE, D_BXT, NULL, bxt_de_pll_enable_write);
+	MMIO_D(BXT_DSI_PLL_CTL, D_BXT);
+	MMIO_D(BXT_DSI_PLL_ENABLE, D_BXT);
+
+	MMIO_D(GEN9_CLKGATE_DIS_0, D_BXT);
+
+	MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_A), D_BXT);
+	MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_B), D_BXT);
+	MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_C), D_BXT);
+
+	MMIO_DH(EDP_PSR_IMR, D_BXT, NULL, bxt_edp_psr_imr_iir_write);
+	MMIO_DH(EDP_PSR_IIR, D_BXT, NULL, bxt_edp_psr_imr_iir_write);
+
+	MMIO_D(RC6_CTX_BASE, D_BXT);
+
+	MMIO_D(GEN8_PUSHBUS_CONTROL, D_BXT);
+	MMIO_D(GEN8_PUSHBUS_ENABLE, D_BXT);
+	MMIO_D(GEN8_PUSHBUS_SHIFT, D_BXT);
+	MMIO_D(GEN6_GFXPAUSE, D_BXT);
+	MMIO_D(GEN8_L3SQCREG1, D_BXT);
+
+	MMIO_DFH(GEN9_CTX_PREEMPT_REG, D_BXT, F_CMD_ACCESS, NULL, NULL);
 
 	return 0;
 }
@@ -2965,6 +3297,16 @@ int intel_gvt_setup_mmio_info(struct intel_gvt *gvt)
 		ret = init_skl_mmio_info(gvt);
 		if (ret)
 			goto err;
+	} else if (IS_BROXTON(dev_priv)) {
+		ret = init_broadwell_mmio_info(gvt);
+		if (ret)
+			goto err;
+		ret = init_skl_mmio_info(gvt);
+		if (ret)
+			goto err;
+		ret = init_bxt_mmio_info(gvt);
+		if (ret)
+			goto err;
 	}
 
 	gvt->mmio.mmio_block = mmio_blocks;
diff --git a/drivers/gpu/drm/i915/gvt/hypercall.h b/drivers/gpu/drm/i915/gvt/hypercall.h
index f6dd9f717888..5af11cf1b482 100644
--- a/drivers/gpu/drm/i915/gvt/hypercall.h
+++ b/drivers/gpu/drm/i915/gvt/hypercall.h
@@ -53,7 +53,7 @@ struct intel_gvt_mpt {
 	unsigned long (*gfn_to_mfn)(unsigned long handle, unsigned long gfn);
 
 	int (*dma_map_guest_page)(unsigned long handle, unsigned long gfn,
-				  dma_addr_t *dma_addr);
+				  unsigned long size, dma_addr_t *dma_addr);
 	void (*dma_unmap_guest_page)(unsigned long handle, dma_addr_t dma_addr);
 
 	int (*map_gfn_to_mfn)(unsigned long handle, unsigned long gfn,
diff --git a/drivers/gpu/drm/i915/gvt/interrupt.c b/drivers/gpu/drm/i915/gvt/interrupt.c
index 7a041b368f68..5daa23ae566b 100644
--- a/drivers/gpu/drm/i915/gvt/interrupt.c
+++ b/drivers/gpu/drm/i915/gvt/interrupt.c
@@ -350,7 +350,8 @@ static void update_upstream_irq(struct intel_vgpu *vgpu,
 			clear_bits |= (1 << bit);
 	}
 
-	WARN_ON(!up_irq_info);
+	if (WARN_ON(!up_irq_info))
+		return;
 
 	if (up_irq_info->group == INTEL_GVT_IRQ_INFO_MASTER) {
 		u32 isr = i915_mmio_reg_offset(up_irq_info->reg_base);
@@ -580,7 +581,9 @@ static void gen8_init_irq(
 
 		SET_BIT_INFO(irq, 4, PRIMARY_C_FLIP_DONE, INTEL_GVT_IRQ_INFO_DE_PIPE_C);
 		SET_BIT_INFO(irq, 5, SPRITE_C_FLIP_DONE, INTEL_GVT_IRQ_INFO_DE_PIPE_C);
-	} else if (IS_SKYLAKE(gvt->dev_priv) || IS_KABYLAKE(gvt->dev_priv)) {
+	} else if (IS_SKYLAKE(gvt->dev_priv)
+			|| IS_KABYLAKE(gvt->dev_priv)
+			|| IS_BROXTON(gvt->dev_priv)) {
 		SET_BIT_INFO(irq, 25, AUX_CHANNEL_B, INTEL_GVT_IRQ_INFO_DE_PORT);
 		SET_BIT_INFO(irq, 26, AUX_CHANNEL_C, INTEL_GVT_IRQ_INFO_DE_PORT);
 		SET_BIT_INFO(irq, 27, AUX_CHANNEL_D, INTEL_GVT_IRQ_INFO_DE_PORT);
@@ -690,14 +693,8 @@ int intel_gvt_init_irq(struct intel_gvt *gvt)
 
 	gvt_dbg_core("init irq framework\n");
 
-	if (IS_BROADWELL(gvt->dev_priv) || IS_SKYLAKE(gvt->dev_priv)
-		|| IS_KABYLAKE(gvt->dev_priv)) {
-		irq->ops = &gen8_irq_ops;
-		irq->irq_map = gen8_irq_map;
-	} else {
-		WARN_ON(1);
-		return -ENODEV;
-	}
+	irq->ops = &gen8_irq_ops;
+	irq->irq_map = gen8_irq_map;
 
 	/* common event initialization */
 	init_events(irq);
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index df4e4a07db3d..4d2f53ae9f0f 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -94,6 +94,7 @@ struct gvt_dma {
 	struct rb_node dma_addr_node;
 	gfn_t gfn;
 	dma_addr_t dma_addr;
+	unsigned long size;
 	struct kref ref;
 };
 
@@ -106,51 +107,103 @@ static int kvmgt_guest_init(struct mdev_device *mdev);
 static void intel_vgpu_release_work(struct work_struct *work);
 static bool kvmgt_guest_exit(struct kvmgt_guest_info *info);
 
-static int gvt_dma_map_page(struct intel_vgpu *vgpu, unsigned long gfn,
-		dma_addr_t *dma_addr)
+static void gvt_unpin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
+		unsigned long size)
 {
-	struct device *dev = &vgpu->gvt->dev_priv->drm.pdev->dev;
-	struct page *page;
-	unsigned long pfn;
+	int total_pages;
+	int npage;
 	int ret;
 
-	/* Pin the page first. */
-	ret = vfio_pin_pages(mdev_dev(vgpu->vdev.mdev), &gfn, 1,
-			     IOMMU_READ | IOMMU_WRITE, &pfn);
-	if (ret != 1) {
-		gvt_vgpu_err("vfio_pin_pages failed for gfn 0x%lx: %d\n",
-			     gfn, ret);
-		return -EINVAL;
+	total_pages = roundup(size, PAGE_SIZE) / PAGE_SIZE;
+
+	for (npage = 0; npage < total_pages; npage++) {
+		unsigned long cur_gfn = gfn + npage;
+
+		ret = vfio_unpin_pages(mdev_dev(vgpu->vdev.mdev), &cur_gfn, 1);
+		WARN_ON(ret != 1);
 	}
+}
 
-	if (!pfn_valid(pfn)) {
-		gvt_vgpu_err("pfn 0x%lx is not mem backed\n", pfn);
-		vfio_unpin_pages(mdev_dev(vgpu->vdev.mdev), &gfn, 1);
-		return -EINVAL;
+/* Pin a normal or compound guest page for dma. */
+static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
+		unsigned long size, struct page **page)
+{
+	unsigned long base_pfn = 0;
+	int total_pages;
+	int npage;
+	int ret;
+
+	total_pages = roundup(size, PAGE_SIZE) / PAGE_SIZE;
+	/*
+	 * We pin the pages one-by-one to avoid allocating a big arrary
+	 * on stack to hold pfns.
+	 */
+	for (npage = 0; npage < total_pages; npage++) {
+		unsigned long cur_gfn = gfn + npage;
+		unsigned long pfn;
+
+		ret = vfio_pin_pages(mdev_dev(vgpu->vdev.mdev), &cur_gfn, 1,
+				     IOMMU_READ | IOMMU_WRITE, &pfn);
+		if (ret != 1) {
+			gvt_vgpu_err("vfio_pin_pages failed for gfn 0x%lx, ret %d\n",
+				     cur_gfn, ret);
+			goto err;
+		}
+
+		if (!pfn_valid(pfn)) {
+			gvt_vgpu_err("pfn 0x%lx is not mem backed\n", pfn);
+			npage++;
+			ret = -EFAULT;
+			goto err;
+		}
+
+		if (npage == 0)
+			base_pfn = pfn;
+		else if (base_pfn + npage != pfn) {
+			gvt_vgpu_err("The pages are not continuous\n");
+			ret = -EINVAL;
+			npage++;
+			goto err;
+		}
 	}
 
+	*page = pfn_to_page(base_pfn);
+	return 0;
+err:
+	gvt_unpin_guest_page(vgpu, gfn, npage * PAGE_SIZE);
+	return ret;
+}
+
+static int gvt_dma_map_page(struct intel_vgpu *vgpu, unsigned long gfn,
+		dma_addr_t *dma_addr, unsigned long size)
+{
+	struct device *dev = &vgpu->gvt->dev_priv->drm.pdev->dev;
+	struct page *page = NULL;
+	int ret;
+
+	ret = gvt_pin_guest_page(vgpu, gfn, size, &page);
+	if (ret)
+		return ret;
+
 	/* Setup DMA mapping. */
-	page = pfn_to_page(pfn);
-	*dma_addr = dma_map_page(dev, page, 0, PAGE_SIZE,
-				 PCI_DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(dev, *dma_addr)) {
-		gvt_vgpu_err("DMA mapping failed for gfn 0x%lx\n", gfn);
-		vfio_unpin_pages(mdev_dev(vgpu->vdev.mdev), &gfn, 1);
-		return -ENOMEM;
+	*dma_addr = dma_map_page(dev, page, 0, size, PCI_DMA_BIDIRECTIONAL);
+	ret = dma_mapping_error(dev, *dma_addr);
+	if (ret) {
+		gvt_vgpu_err("DMA mapping failed for pfn 0x%lx, ret %d\n",
+			     page_to_pfn(page), ret);
+		gvt_unpin_guest_page(vgpu, gfn, size);
 	}
 
-	return 0;
+	return ret;
 }
 
 static void gvt_dma_unmap_page(struct intel_vgpu *vgpu, unsigned long gfn,
-		dma_addr_t dma_addr)
+		dma_addr_t dma_addr, unsigned long size)
 {
 	struct device *dev = &vgpu->gvt->dev_priv->drm.pdev->dev;
-	int ret;
 
-	dma_unmap_page(dev, dma_addr, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
-	ret = vfio_unpin_pages(mdev_dev(vgpu->vdev.mdev), &gfn, 1);
-	WARN_ON(ret != 1);
+	dma_unmap_page(dev, dma_addr, size, PCI_DMA_BIDIRECTIONAL);
+	gvt_unpin_guest_page(vgpu, gfn, size);
 }
 
 static struct gvt_dma *__gvt_cache_find_dma_addr(struct intel_vgpu *vgpu,
@@ -191,7 +244,7 @@ static struct gvt_dma *__gvt_cache_find_gfn(struct intel_vgpu *vgpu, gfn_t gfn)
 }
 
 static int __gvt_cache_add(struct intel_vgpu *vgpu, gfn_t gfn,
-		dma_addr_t dma_addr)
+		dma_addr_t dma_addr, unsigned long size)
 {
 	struct gvt_dma *new, *itr;
 	struct rb_node **link, *parent = NULL;
@@ -203,6 +256,7 @@ static int __gvt_cache_add(struct intel_vgpu *vgpu, gfn_t gfn,
 	new->vgpu = vgpu;
 	new->gfn = gfn;
 	new->dma_addr = dma_addr;
+	new->size = size;
 	kref_init(&new->ref);
 
 	/* gfn_cache maps gfn to struct gvt_dma. */
@@ -260,7 +314,7 @@ static void gvt_cache_destroy(struct intel_vgpu *vgpu)
 			break;
 		}
 		dma = rb_entry(node, struct gvt_dma, gfn_node);
-		gvt_dma_unmap_page(vgpu, dma->gfn, dma->dma_addr);
+		gvt_dma_unmap_page(vgpu, dma->gfn, dma->dma_addr, dma->size);
 		__gvt_cache_remove_entry(vgpu, dma);
 		mutex_unlock(&vgpu->vdev.cache_lock);
 	}
@@ -515,7 +569,8 @@ static int intel_vgpu_iommu_notifier(struct notifier_block *nb,
 			if (!entry)
 				continue;
 
-			gvt_dma_unmap_page(vgpu, entry->gfn, entry->dma_addr);
+			gvt_dma_unmap_page(vgpu, entry->gfn, entry->dma_addr,
+					   entry->size);
 			__gvt_cache_remove_entry(vgpu, entry);
 		}
 		mutex_unlock(&vgpu->vdev.cache_lock);
@@ -1648,7 +1703,7 @@ static unsigned long kvmgt_gfn_to_pfn(unsigned long handle, unsigned long gfn)
 }
 
 int kvmgt_dma_map_guest_page(unsigned long handle, unsigned long gfn,
-		dma_addr_t *dma_addr)
+		unsigned long size, dma_addr_t *dma_addr)
 {
 	struct kvmgt_guest_info *info;
 	struct intel_vgpu *vgpu;
@@ -1665,11 +1720,11 @@ int kvmgt_dma_map_guest_page(unsigned long handle, unsigned long gfn,
 
 	entry = __gvt_cache_find_gfn(info->vgpu, gfn);
 	if (!entry) {
-		ret = gvt_dma_map_page(vgpu, gfn, dma_addr);
+		ret = gvt_dma_map_page(vgpu, gfn, dma_addr, size);
 		if (ret)
 			goto err_unlock;
 
-		ret = __gvt_cache_add(info->vgpu, gfn, *dma_addr);
+		ret = __gvt_cache_add(info->vgpu, gfn, *dma_addr, size);
 		if (ret)
 			goto err_unmap;
 	} else {
@@ -1681,7 +1736,7 @@ int kvmgt_dma_map_guest_page(unsigned long handle, unsigned long gfn,
 	return 0;
 
 err_unmap:
-	gvt_dma_unmap_page(vgpu, gfn, *dma_addr);
+	gvt_dma_unmap_page(vgpu, gfn, *dma_addr, size);
 err_unlock:
 	mutex_unlock(&info->vgpu->vdev.cache_lock);
 	return ret;
@@ -1691,7 +1746,8 @@ static void __gvt_dma_release(struct kref *ref)
 {
 	struct gvt_dma *entry = container_of(ref, typeof(*entry), ref);
 
-	gvt_dma_unmap_page(entry->vgpu, entry->gfn, entry->dma_addr);
+	gvt_dma_unmap_page(entry->vgpu, entry->gfn, entry->dma_addr,
+			   entry->size);
 	__gvt_cache_remove_entry(entry->vgpu, entry);
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c
index b31eb36fc102..994366035364 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.c
+++ b/drivers/gpu/drm/i915/gvt/mmio.c
@@ -67,7 +67,7 @@ static void failsafe_emulate_mmio_rw(struct intel_vgpu *vgpu, uint64_t pa,
 		return;
 
 	gvt = vgpu->gvt;
-	mutex_lock(&gvt->lock);
+	mutex_lock(&vgpu->vgpu_lock);
 	offset = intel_vgpu_gpa_to_mmio_offset(vgpu, pa);
 	if (reg_is_mmio(gvt, offset)) {
 		if (read)
@@ -85,7 +85,7 @@ static void failsafe_emulate_mmio_rw(struct intel_vgpu *vgpu, uint64_t pa,
 			memcpy(pt, p_data, bytes);
 
 	}
-	mutex_unlock(&gvt->lock);
+	mutex_unlock(&vgpu->vgpu_lock);
 }
 
 /**
@@ -109,7 +109,7 @@ int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa,
 		failsafe_emulate_mmio_rw(vgpu, pa, p_data, bytes, true);
 		return 0;
 	}
-	mutex_lock(&gvt->lock);
+	mutex_lock(&vgpu->vgpu_lock);
 
 	offset = intel_vgpu_gpa_to_mmio_offset(vgpu, pa);
 
@@ -156,7 +156,7 @@ err:
 	gvt_vgpu_err("fail to emulate MMIO read %08x len %d\n",
 			offset, bytes);
 out:
-	mutex_unlock(&gvt->lock);
+	mutex_unlock(&vgpu->vgpu_lock);
 	return ret;
 }
 
@@ -182,7 +182,7 @@ int intel_vgpu_emulate_mmio_write(struct intel_vgpu *vgpu, uint64_t pa,
 		return 0;
 	}
 
-	mutex_lock(&gvt->lock);
+	mutex_lock(&vgpu->vgpu_lock);
 
 	offset = intel_vgpu_gpa_to_mmio_offset(vgpu, pa);
 
@@ -220,7 +220,7 @@ err:
 	gvt_vgpu_err("fail to emulate MMIO write %08x len %d\n", offset,
 		     bytes);
 out:
-	mutex_unlock(&gvt->lock);
+	mutex_unlock(&vgpu->vgpu_lock);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/mmio.h b/drivers/gpu/drm/i915/gvt/mmio.h
index dac8c6401e26..1ffc69eba30e 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.h
+++ b/drivers/gpu/drm/i915/gvt/mmio.h
@@ -42,15 +42,16 @@ struct intel_vgpu;
 #define D_BDW   (1 << 0)
 #define D_SKL	(1 << 1)
 #define D_KBL	(1 << 2)
+#define D_BXT	(1 << 3)
 
-#define D_GEN9PLUS	(D_SKL | D_KBL)
-#define D_GEN8PLUS	(D_BDW | D_SKL | D_KBL)
+#define D_GEN9PLUS	(D_SKL | D_KBL | D_BXT)
+#define D_GEN8PLUS	(D_BDW | D_SKL | D_KBL | D_BXT)
 
-#define D_SKL_PLUS	(D_SKL | D_KBL)
-#define D_BDW_PLUS	(D_BDW | D_SKL | D_KBL)
+#define D_SKL_PLUS	(D_SKL | D_KBL | D_BXT)
+#define D_BDW_PLUS	(D_BDW | D_SKL | D_KBL | D_BXT)
 
 #define D_PRE_SKL	(D_BDW)
-#define D_ALL		(D_BDW | D_SKL | D_KBL)
+#define D_ALL		(D_BDW | D_SKL | D_KBL | D_BXT)
 
 typedef int (*gvt_mmio_func)(struct intel_vgpu *, unsigned int, void *,
 			     unsigned int);
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index 5ca9caf7552a..42e1e6bdcc2c 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -364,7 +364,8 @@ static void handle_tlb_pending_event(struct intel_vgpu *vgpu, int ring_id)
 	 */
 	fw = intel_uncore_forcewake_for_reg(dev_priv, reg,
 					    FW_REG_READ | FW_REG_WRITE);
-	if (ring_id == RCS && (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)))
+	if (ring_id == RCS && (IS_SKYLAKE(dev_priv) ||
+			IS_KABYLAKE(dev_priv) || IS_BROXTON(dev_priv)))
 		fw |= FORCEWAKE_RENDER;
 
 	intel_uncore_forcewake_get(dev_priv, fw);
@@ -401,7 +402,7 @@ static void switch_mocs(struct intel_vgpu *pre, struct intel_vgpu *next,
 	if (WARN_ON(ring_id >= ARRAY_SIZE(regs)))
 		return;
 
-	if (IS_KABYLAKE(dev_priv) && ring_id == RCS)
+	if ((IS_KABYLAKE(dev_priv) || IS_BROXTON(dev_priv)) && ring_id == RCS)
 		return;
 
 	if (!pre && !gen9_render_mocs.initialized)
@@ -446,9 +447,9 @@ static void switch_mocs(struct intel_vgpu *pre, struct intel_vgpu *next,
 
 #define CTX_CONTEXT_CONTROL_VAL	0x03
 
-bool is_inhibit_context(struct i915_gem_context *ctx, int ring_id)
+bool is_inhibit_context(struct intel_context *ce)
 {
-	u32 *reg_state = ctx->__engine[ring_id].lrc_reg_state;
+	const u32 *reg_state = ce->lrc_reg_state;
 	u32 inhibit_mask =
 		_MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
 
@@ -467,7 +468,9 @@ static void switch_mmio(struct intel_vgpu *pre,
 	u32 old_v, new_v;
 
 	dev_priv = pre ? pre->gvt->dev_priv : next->gvt->dev_priv;
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
+	if (IS_SKYLAKE(dev_priv)
+		|| IS_KABYLAKE(dev_priv)
+		|| IS_BROXTON(dev_priv))
 		switch_mocs(pre, next, ring_id);
 
 	for (mmio = dev_priv->gvt->engine_mmio_list.mmio;
@@ -479,7 +482,8 @@ static void switch_mmio(struct intel_vgpu *pre,
 		 * state image on kabylake, it's initialized by lri command and
 		 * save or restore with context together.
 		 */
-		if (IS_KABYLAKE(dev_priv) && mmio->in_context)
+		if ((IS_KABYLAKE(dev_priv) || IS_BROXTON(dev_priv))
+			&& mmio->in_context)
 			continue;
 
 		// save
@@ -501,7 +505,7 @@ static void switch_mmio(struct intel_vgpu *pre,
 			 * itself.
 			 */
 			if (mmio->in_context &&
-			    !is_inhibit_context(s->shadow_ctx, ring_id))
+			    !is_inhibit_context(&s->shadow_ctx->__engine[ring_id]))
 				continue;
 
 			if (mmio->mask)
@@ -574,7 +578,9 @@ void intel_gvt_init_engine_mmio_context(struct intel_gvt *gvt)
 {
 	struct engine_mmio *mmio;
 
-	if (IS_SKYLAKE(gvt->dev_priv) || IS_KABYLAKE(gvt->dev_priv))
+	if (IS_SKYLAKE(gvt->dev_priv) ||
+		IS_KABYLAKE(gvt->dev_priv) ||
+		IS_BROXTON(gvt->dev_priv))
 		gvt->engine_mmio_list.mmio = gen9_engine_mmio_list;
 	else
 		gvt->engine_mmio_list.mmio = gen8_engine_mmio_list;
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.h b/drivers/gpu/drm/i915/gvt/mmio_context.h
index 0439eb8057a8..5c3b9ff9f96a 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.h
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.h
@@ -49,7 +49,7 @@ void intel_gvt_switch_mmio(struct intel_vgpu *pre,
 
 void intel_gvt_init_engine_mmio_context(struct intel_gvt *gvt);
 
-bool is_inhibit_context(struct i915_gem_context *ctx, int ring_id);
+bool is_inhibit_context(struct intel_context *ce);
 
 int intel_vgpu_restore_inhibit_context(struct intel_vgpu *vgpu,
 				       struct i915_request *req);
diff --git a/drivers/gpu/drm/i915/gvt/mpt.h b/drivers/gpu/drm/i915/gvt/mpt.h
index 32ffcd566cdd..67f19992b226 100644
--- a/drivers/gpu/drm/i915/gvt/mpt.h
+++ b/drivers/gpu/drm/i915/gvt/mpt.h
@@ -230,17 +230,18 @@ static inline unsigned long intel_gvt_hypervisor_gfn_to_mfn(
 /**
  * intel_gvt_hypervisor_dma_map_guest_page - setup dma map for guest page
  * @vgpu: a vGPU
- * @gpfn: guest pfn
+ * @gfn: guest pfn
+ * @size: page size
  * @dma_addr: retrieve allocated dma addr
  *
  * Returns:
  * 0 on success, negative error code if failed.
  */
 static inline int intel_gvt_hypervisor_dma_map_guest_page(
-		struct intel_vgpu *vgpu, unsigned long gfn,
+		struct intel_vgpu *vgpu, unsigned long gfn, unsigned long size,
 		dma_addr_t *dma_addr)
 {
-	return intel_gvt_host.mpt->dma_map_guest_page(vgpu->handle, gfn,
+	return intel_gvt_host.mpt->dma_map_guest_page(vgpu->handle, gfn, size,
 						      dma_addr);
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/page_track.c b/drivers/gpu/drm/i915/gvt/page_track.c
index 53e2bd79c97d..256d0db8bbb1 100644
--- a/drivers/gpu/drm/i915/gvt/page_track.c
+++ b/drivers/gpu/drm/i915/gvt/page_track.c
@@ -157,11 +157,10 @@ int intel_vgpu_disable_page_track(struct intel_vgpu *vgpu, unsigned long gfn)
 int intel_vgpu_page_track_handler(struct intel_vgpu *vgpu, u64 gpa,
 		void *data, unsigned int bytes)
 {
-	struct intel_gvt *gvt = vgpu->gvt;
 	struct intel_vgpu_page_track *page_track;
 	int ret = 0;
 
-	mutex_lock(&gvt->lock);
+	mutex_lock(&vgpu->vgpu_lock);
 
 	page_track = intel_vgpu_find_page_track(vgpu, gpa >> PAGE_SHIFT);
 	if (!page_track) {
@@ -179,6 +178,6 @@ int intel_vgpu_page_track_handler(struct intel_vgpu *vgpu, u64 gpa,
 	}
 
 out:
-	mutex_unlock(&gvt->lock);
+	mutex_unlock(&vgpu->vgpu_lock);
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c
index d053cbe1dc94..09d7bb72b4ff 100644
--- a/drivers/gpu/drm/i915/gvt/sched_policy.c
+++ b/drivers/gpu/drm/i915/gvt/sched_policy.c
@@ -228,7 +228,7 @@ void intel_gvt_schedule(struct intel_gvt *gvt)
 	struct gvt_sched_data *sched_data = gvt->scheduler.sched_data;
 	ktime_t cur_time;
 
-	mutex_lock(&gvt->lock);
+	mutex_lock(&gvt->sched_lock);
 	cur_time = ktime_get();
 
 	if (test_and_clear_bit(INTEL_GVT_REQUEST_SCHED,
@@ -244,7 +244,7 @@ void intel_gvt_schedule(struct intel_gvt *gvt)
 	vgpu_update_timeslice(gvt->scheduler.current_vgpu, cur_time);
 	tbs_sched_func(sched_data);
 
-	mutex_unlock(&gvt->lock);
+	mutex_unlock(&gvt->sched_lock);
 }
 
 static enum hrtimer_restart tbs_timer_fn(struct hrtimer *timer_data)
@@ -359,39 +359,65 @@ static struct intel_gvt_sched_policy_ops tbs_schedule_ops = {
 
 int intel_gvt_init_sched_policy(struct intel_gvt *gvt)
 {
+	int ret;
+
+	mutex_lock(&gvt->sched_lock);
 	gvt->scheduler.sched_ops = &tbs_schedule_ops;
+	ret = gvt->scheduler.sched_ops->init(gvt);
+	mutex_unlock(&gvt->sched_lock);
 
-	return gvt->scheduler.sched_ops->init(gvt);
+	return ret;
 }
 
 void intel_gvt_clean_sched_policy(struct intel_gvt *gvt)
 {
+	mutex_lock(&gvt->sched_lock);
 	gvt->scheduler.sched_ops->clean(gvt);
+	mutex_unlock(&gvt->sched_lock);
 }
 
+/* for per-vgpu scheduler policy, there are 2 per-vgpu data:
+ * sched_data, and sched_ctl. We see these 2 data as part of
+ * the global scheduler which are proteced by gvt->sched_lock.
+ * Caller should make their decision if the vgpu_lock should
+ * be hold outside.
+ */
+
 int intel_vgpu_init_sched_policy(struct intel_vgpu *vgpu)
 {
-	return vgpu->gvt->scheduler.sched_ops->init_vgpu(vgpu);
+	int ret;
+
+	mutex_lock(&vgpu->gvt->sched_lock);
+	ret = vgpu->gvt->scheduler.sched_ops->init_vgpu(vgpu);
+	mutex_unlock(&vgpu->gvt->sched_lock);
+
+	return ret;
 }
 
 void intel_vgpu_clean_sched_policy(struct intel_vgpu *vgpu)
 {
+	mutex_lock(&vgpu->gvt->sched_lock);
 	vgpu->gvt->scheduler.sched_ops->clean_vgpu(vgpu);
+	mutex_unlock(&vgpu->gvt->sched_lock);
 }
 
 void intel_vgpu_start_schedule(struct intel_vgpu *vgpu)
 {
 	struct vgpu_sched_data *vgpu_data = vgpu->sched_data;
 
+	mutex_lock(&vgpu->gvt->sched_lock);
 	if (!vgpu_data->active) {
 		gvt_dbg_core("vgpu%d: start schedule\n", vgpu->id);
 		vgpu->gvt->scheduler.sched_ops->start_schedule(vgpu);
 	}
+	mutex_unlock(&vgpu->gvt->sched_lock);
 }
 
 void intel_gvt_kick_schedule(struct intel_gvt *gvt)
 {
+	mutex_lock(&gvt->sched_lock);
 	intel_gvt_request_service(gvt, INTEL_GVT_REQUEST_EVENT_SCHED);
+	mutex_unlock(&gvt->sched_lock);
 }
 
 void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu)
@@ -406,6 +432,7 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu)
 
 	gvt_dbg_core("vgpu%d: stop schedule\n", vgpu->id);
 
+	mutex_lock(&vgpu->gvt->sched_lock);
 	scheduler->sched_ops->stop_schedule(vgpu);
 
 	if (scheduler->next_vgpu == vgpu)
@@ -425,4 +452,5 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu)
 		}
 	}
 	spin_unlock_bh(&scheduler->mmio_context_lock);
+	mutex_unlock(&vgpu->gvt->sched_lock);
 }
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index c2d183b91500..b0e566956b8d 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -45,20 +45,16 @@ static void set_context_pdp_root_pointer(
 		struct execlist_ring_context *ring_context,
 		u32 pdp[8])
 {
-	struct execlist_mmio_pair *pdp_pair = &ring_context->pdp3_UDW;
 	int i;
 
 	for (i = 0; i < 8; i++)
-		pdp_pair[i].val = pdp[7 - i];
+		ring_context->pdps[i].val = pdp[7 - i];
 }
 
 static void update_shadow_pdps(struct intel_vgpu_workload *workload)
 {
-	struct intel_vgpu *vgpu = workload->vgpu;
-	int ring_id = workload->ring_id;
-	struct i915_gem_context *shadow_ctx = vgpu->submission.shadow_ctx;
 	struct drm_i915_gem_object *ctx_obj =
-		shadow_ctx->__engine[ring_id].state->obj;
+		workload->req->hw_context->state->obj;
 	struct execlist_ring_context *shadow_ring_context;
 	struct page *page;
 
@@ -128,9 +124,8 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
 	struct intel_vgpu *vgpu = workload->vgpu;
 	struct intel_gvt *gvt = vgpu->gvt;
 	int ring_id = workload->ring_id;
-	struct i915_gem_context *shadow_ctx = vgpu->submission.shadow_ctx;
 	struct drm_i915_gem_object *ctx_obj =
-		shadow_ctx->__engine[ring_id].state->obj;
+		workload->req->hw_context->state->obj;
 	struct execlist_ring_context *shadow_ring_context;
 	struct page *page;
 	void *dst;
@@ -205,7 +200,7 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
 
 static inline bool is_gvt_request(struct i915_request *req)
 {
-	return i915_gem_context_force_single_submission(req->ctx);
+	return i915_gem_context_force_single_submission(req->gem_context);
 }
 
 static void save_ring_hw_state(struct intel_vgpu *vgpu, int ring_id)
@@ -280,10 +275,8 @@ static int shadow_context_status_change(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
-static void shadow_context_descriptor_update(struct i915_gem_context *ctx,
-		struct intel_engine_cs *engine)
+static void shadow_context_descriptor_update(struct intel_context *ce)
 {
-	struct intel_context *ce = to_intel_context(ctx, engine);
 	u64 desc = 0;
 
 	desc = ce->lrc_desc;
@@ -292,7 +285,7 @@ static void shadow_context_descriptor_update(struct i915_gem_context *ctx,
 	 * like GEN8_CTX_* cached in desc_template
 	 */
 	desc &= U64_MAX << 12;
-	desc |= ctx->desc_template & ((1ULL << 12) - 1);
+	desc |= ce->gem_context->desc_template & ((1ULL << 12) - 1);
 
 	ce->lrc_desc = desc;
 }
@@ -300,12 +293,12 @@ static void shadow_context_descriptor_update(struct i915_gem_context *ctx,
 static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload)
 {
 	struct intel_vgpu *vgpu = workload->vgpu;
+	struct i915_request *req = workload->req;
 	void *shadow_ring_buffer_va;
 	u32 *cs;
-	struct i915_request *req = workload->req;
 
-	if (IS_KABYLAKE(req->i915) &&
-	    is_inhibit_context(req->ctx, req->engine->id))
+	if ((IS_KABYLAKE(req->i915) || IS_BROXTON(req->i915))
+		&& is_inhibit_context(req->hw_context))
 		intel_vgpu_restore_inhibit_context(vgpu, req);
 
 	/* allocate shadow ring buffer */
@@ -353,92 +346,67 @@ int intel_gvt_scan_and_shadow_workload(struct intel_vgpu_workload *workload)
 	struct intel_vgpu_submission *s = &vgpu->submission;
 	struct i915_gem_context *shadow_ctx = s->shadow_ctx;
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
-	int ring_id = workload->ring_id;
-	struct intel_engine_cs *engine = dev_priv->engine[ring_id];
-	struct intel_ring *ring;
+	struct intel_engine_cs *engine = dev_priv->engine[workload->ring_id];
+	struct intel_context *ce;
+	struct i915_request *rq;
 	int ret;
 
 	lockdep_assert_held(&dev_priv->drm.struct_mutex);
 
-	if (workload->shadowed)
+	if (workload->req)
 		return 0;
 
+	/* pin shadow context by gvt even the shadow context will be pinned
+	 * when i915 alloc request. That is because gvt will update the guest
+	 * context from shadow context when workload is completed, and at that
+	 * moment, i915 may already unpined the shadow context to make the
+	 * shadow_ctx pages invalid. So gvt need to pin itself. After update
+	 * the guest context, gvt can unpin the shadow_ctx safely.
+	 */
+	ce = intel_context_pin(shadow_ctx, engine);
+	if (IS_ERR(ce)) {
+		gvt_vgpu_err("fail to pin shadow context\n");
+		return PTR_ERR(ce);
+	}
+
 	shadow_ctx->desc_template &= ~(0x3 << GEN8_CTX_ADDRESSING_MODE_SHIFT);
 	shadow_ctx->desc_template |= workload->ctx_desc.addressing_mode <<
 				    GEN8_CTX_ADDRESSING_MODE_SHIFT;
 
-	if (!test_and_set_bit(ring_id, s->shadow_ctx_desc_updated))
-		shadow_context_descriptor_update(shadow_ctx,
-					dev_priv->engine[ring_id]);
+	if (!test_and_set_bit(workload->ring_id, s->shadow_ctx_desc_updated))
+		shadow_context_descriptor_update(ce);
 
 	ret = intel_gvt_scan_and_shadow_ringbuffer(workload);
 	if (ret)
-		goto err_scan;
+		goto err_unpin;
 
 	if ((workload->ring_id == RCS) &&
 	    (workload->wa_ctx.indirect_ctx.size != 0)) {
 		ret = intel_gvt_scan_and_shadow_wa_ctx(&workload->wa_ctx);
 		if (ret)
-			goto err_scan;
+			goto err_shadow;
 	}
 
-	/* pin shadow context by gvt even the shadow context will be pinned
-	 * when i915 alloc request. That is because gvt will update the guest
-	 * context from shadow context when workload is completed, and at that
-	 * moment, i915 may already unpined the shadow context to make the
-	 * shadow_ctx pages invalid. So gvt need to pin itself. After update
-	 * the guest context, gvt can unpin the shadow_ctx safely.
-	 */
-	ring = intel_context_pin(shadow_ctx, engine);
-	if (IS_ERR(ring)) {
-		ret = PTR_ERR(ring);
-		gvt_vgpu_err("fail to pin shadow context\n");
+	rq = i915_request_alloc(engine, shadow_ctx);
+	if (IS_ERR(rq)) {
+		gvt_vgpu_err("fail to allocate gem request\n");
+		ret = PTR_ERR(rq);
 		goto err_shadow;
 	}
+	workload->req = i915_request_get(rq);
 
 	ret = populate_shadow_context(workload);
 	if (ret)
-		goto err_unpin;
-	workload->shadowed = true;
-	return 0;
+		goto err_req;
 
-err_unpin:
-	intel_context_unpin(shadow_ctx, engine);
+	return 0;
+err_req:
+	rq = fetch_and_zero(&workload->req);
+	i915_request_put(rq);
 err_shadow:
 	release_shadow_wa_ctx(&workload->wa_ctx);
-err_scan:
-	return ret;
-}
-
-static int intel_gvt_generate_request(struct intel_vgpu_workload *workload)
-{
-	int ring_id = workload->ring_id;
-	struct drm_i915_private *dev_priv = workload->vgpu->gvt->dev_priv;
-	struct intel_engine_cs *engine = dev_priv->engine[ring_id];
-	struct i915_request *rq;
-	struct intel_vgpu *vgpu = workload->vgpu;
-	struct intel_vgpu_submission *s = &vgpu->submission;
-	struct i915_gem_context *shadow_ctx = s->shadow_ctx;
-	int ret;
-
-	rq = i915_request_alloc(dev_priv->engine[ring_id], shadow_ctx);
-	if (IS_ERR(rq)) {
-		gvt_vgpu_err("fail to allocate gem request\n");
-		ret = PTR_ERR(rq);
-		goto err_unpin;
-	}
-
-	gvt_dbg_sched("ring id %d get i915 gem request %p\n", ring_id, rq);
-
-	workload->req = i915_request_get(rq);
-	ret = copy_workload_to_ring_buffer(workload);
-	if (ret)
-		goto err_unpin;
-	return 0;
-
 err_unpin:
-	intel_context_unpin(shadow_ctx, engine);
-	release_shadow_wa_ctx(&workload->wa_ctx);
+	intel_context_unpin(ce);
 	return ret;
 }
 
@@ -508,7 +476,11 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 			i915_gem_obj_finish_shmem_access(bb->obj);
 			bb->accessing = false;
 
-			i915_vma_move_to_active(bb->vma, workload->req, 0);
+			ret = i915_vma_move_to_active(bb->vma,
+						      workload->req,
+						      0);
+			if (ret)
+				goto err;
 		}
 	}
 	return 0;
@@ -517,21 +489,13 @@ err:
 	return ret;
 }
 
-static int update_wa_ctx_2_shadow_ctx(struct intel_shadow_wa_ctx *wa_ctx)
+static void update_wa_ctx_2_shadow_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 {
-	struct intel_vgpu_workload *workload = container_of(wa_ctx,
-					struct intel_vgpu_workload,
-					wa_ctx);
-	int ring_id = workload->ring_id;
-	struct intel_vgpu_submission *s = &workload->vgpu->submission;
-	struct i915_gem_context *shadow_ctx = s->shadow_ctx;
-	struct drm_i915_gem_object *ctx_obj =
-		shadow_ctx->__engine[ring_id].state->obj;
-	struct execlist_ring_context *shadow_ring_context;
-	struct page *page;
-
-	page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN);
-	shadow_ring_context = kmap_atomic(page);
+	struct intel_vgpu_workload *workload =
+		container_of(wa_ctx, struct intel_vgpu_workload, wa_ctx);
+	struct i915_request *rq = workload->req;
+	struct execlist_ring_context *shadow_ring_context =
+		(struct execlist_ring_context *)rq->hw_context->lrc_reg_state;
 
 	shadow_ring_context->bb_per_ctx_ptr.val =
 		(shadow_ring_context->bb_per_ctx_ptr.val &
@@ -539,9 +503,6 @@ static int update_wa_ctx_2_shadow_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 	shadow_ring_context->rcs_indirect_ctx.val =
 		(shadow_ring_context->rcs_indirect_ctx.val &
 		(~INDIRECT_CTX_ADDR_MASK)) | wa_ctx->indirect_ctx.shadow_gma;
-
-	kunmap_atomic(shadow_ring_context);
-	return 0;
 }
 
 static int prepare_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
@@ -633,7 +594,7 @@ static int prepare_workload(struct intel_vgpu_workload *workload)
 		goto err_unpin_mm;
 	}
 
-	ret = intel_gvt_generate_request(workload);
+	ret = copy_workload_to_ring_buffer(workload);
 	if (ret) {
 		gvt_vgpu_err("fail to generate request\n");
 		goto err_unpin_mm;
@@ -670,16 +631,14 @@ err_unpin_mm:
 static int dispatch_workload(struct intel_vgpu_workload *workload)
 {
 	struct intel_vgpu *vgpu = workload->vgpu;
-	struct intel_vgpu_submission *s = &vgpu->submission;
-	struct i915_gem_context *shadow_ctx = s->shadow_ctx;
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	int ring_id = workload->ring_id;
-	struct intel_engine_cs *engine = dev_priv->engine[ring_id];
-	int ret = 0;
+	int ret;
 
 	gvt_dbg_sched("ring id %d prepare to dispatch workload %p\n",
 		ring_id, workload);
 
+	mutex_lock(&vgpu->vgpu_lock);
 	mutex_lock(&dev_priv->drm.struct_mutex);
 
 	ret = intel_gvt_scan_and_shadow_workload(workload);
@@ -687,10 +646,6 @@ static int dispatch_workload(struct intel_vgpu_workload *workload)
 		goto out;
 
 	ret = prepare_workload(workload);
-	if (ret) {
-		intel_context_unpin(shadow_ctx, engine);
-		goto out;
-	}
 
 out:
 	if (ret)
@@ -704,6 +659,7 @@ out:
 	}
 
 	mutex_unlock(&dev_priv->drm.struct_mutex);
+	mutex_unlock(&vgpu->vgpu_lock);
 	return ret;
 }
 
@@ -713,7 +669,7 @@ static struct intel_vgpu_workload *pick_next_workload(
 	struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
 	struct intel_vgpu_workload *workload = NULL;
 
-	mutex_lock(&gvt->lock);
+	mutex_lock(&gvt->sched_lock);
 
 	/*
 	 * no current vgpu / will be scheduled out / no workload
@@ -759,33 +715,29 @@ static struct intel_vgpu_workload *pick_next_workload(
 
 	atomic_inc(&workload->vgpu->submission.running_workload_num);
 out:
-	mutex_unlock(&gvt->lock);
+	mutex_unlock(&gvt->sched_lock);
 	return workload;
 }
 
 static void update_guest_context(struct intel_vgpu_workload *workload)
 {
+	struct i915_request *rq = workload->req;
 	struct intel_vgpu *vgpu = workload->vgpu;
 	struct intel_gvt *gvt = vgpu->gvt;
-	struct intel_vgpu_submission *s = &vgpu->submission;
-	struct i915_gem_context *shadow_ctx = s->shadow_ctx;
-	int ring_id = workload->ring_id;
-	struct drm_i915_gem_object *ctx_obj =
-		shadow_ctx->__engine[ring_id].state->obj;
+	struct drm_i915_gem_object *ctx_obj = rq->hw_context->state->obj;
 	struct execlist_ring_context *shadow_ring_context;
 	struct page *page;
 	void *src;
 	unsigned long context_gpa, context_page_num;
 	int i;
 
-	gvt_dbg_sched("ring id %d workload lrca %x\n", ring_id,
-			workload->ctx_desc.lrca);
-
-	context_page_num = gvt->dev_priv->engine[ring_id]->context_size;
+	gvt_dbg_sched("ring id %d workload lrca %x\n", rq->engine->id,
+		      workload->ctx_desc.lrca);
 
+	context_page_num = rq->engine->context_size;
 	context_page_num = context_page_num >> PAGE_SHIFT;
 
-	if (IS_BROADWELL(gvt->dev_priv) && ring_id == RCS)
+	if (IS_BROADWELL(gvt->dev_priv) && rq->engine->id == RCS)
 		context_page_num = 19;
 
 	i = 2;
@@ -858,19 +810,17 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 		scheduler->current_workload[ring_id];
 	struct intel_vgpu *vgpu = workload->vgpu;
 	struct intel_vgpu_submission *s = &vgpu->submission;
+	struct i915_request *rq = workload->req;
 	int event;
 
-	mutex_lock(&gvt->lock);
+	mutex_lock(&vgpu->vgpu_lock);
+	mutex_lock(&gvt->sched_lock);
 
 	/* For the workload w/ request, needs to wait for the context
 	 * switch to make sure request is completed.
 	 * For the workload w/o request, directly complete the workload.
 	 */
-	if (workload->req) {
-		struct drm_i915_private *dev_priv =
-			workload->vgpu->gvt->dev_priv;
-		struct intel_engine_cs *engine =
-			dev_priv->engine[workload->ring_id];
+	if (rq) {
 		wait_event(workload->shadow_ctx_status_wq,
 			   !atomic_read(&workload->shadow_ctx_active));
 
@@ -886,8 +836,6 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 				workload->status = 0;
 		}
 
-		i915_request_put(fetch_and_zero(&workload->req));
-
 		if (!workload->status && !(vgpu->resetting_eng &
 					   ENGINE_MASK(ring_id))) {
 			update_guest_context(workload);
@@ -896,10 +844,13 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 					 INTEL_GVT_EVENT_MAX)
 				intel_vgpu_trigger_virtual_event(vgpu, event);
 		}
-		mutex_lock(&dev_priv->drm.struct_mutex);
+
 		/* unpin shadow ctx as the shadow_ctx update is done */
-		intel_context_unpin(s->shadow_ctx, engine);
-		mutex_unlock(&dev_priv->drm.struct_mutex);
+		mutex_lock(&rq->i915->drm.struct_mutex);
+		intel_context_unpin(rq->hw_context);
+		mutex_unlock(&rq->i915->drm.struct_mutex);
+
+		i915_request_put(fetch_and_zero(&workload->req));
 	}
 
 	gvt_dbg_sched("ring id %d complete workload %p status %d\n",
@@ -939,7 +890,8 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 	if (gvt->scheduler.need_reschedule)
 		intel_gvt_request_service(gvt, INTEL_GVT_REQUEST_EVENT_SCHED);
 
-	mutex_unlock(&gvt->lock);
+	mutex_unlock(&gvt->sched_lock);
+	mutex_unlock(&vgpu->vgpu_lock);
 }
 
 struct workload_thread_param {
@@ -957,7 +909,8 @@ static int workload_thread(void *priv)
 	struct intel_vgpu *vgpu = NULL;
 	int ret;
 	bool need_force_wake = IS_SKYLAKE(gvt->dev_priv)
-			|| IS_KABYLAKE(gvt->dev_priv);
+			|| IS_KABYLAKE(gvt->dev_priv)
+			|| IS_BROXTON(gvt->dev_priv);
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
 	kfree(p);
@@ -991,9 +944,7 @@ static int workload_thread(void *priv)
 			intel_uncore_forcewake_get(gvt->dev_priv,
 					FORCEWAKE_ALL);
 
-		mutex_lock(&gvt->lock);
 		ret = dispatch_workload(workload);
-		mutex_unlock(&gvt->lock);
 
 		if (ret) {
 			vgpu = workload->vgpu;
@@ -1270,7 +1221,6 @@ alloc_workload(struct intel_vgpu *vgpu)
 	atomic_set(&workload->shadow_ctx_active, 0);
 
 	workload->status = -EINPROGRESS;
-	workload->shadowed = false;
 	workload->vgpu = vgpu;
 
 	return workload;
@@ -1285,7 +1235,7 @@ static void read_guest_pdps(struct intel_vgpu *vgpu,
 	u64 gpa;
 	int i;
 
-	gpa = ring_context_gpa + RING_CTX_OFF(pdp3_UDW.val);
+	gpa = ring_context_gpa + RING_CTX_OFF(pdps[0].val);
 
 	for (i = 0; i < 8; i++)
 		intel_gvt_hypervisor_read_gpa(vgpu,
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h
index 6c644782193e..21eddab4a9cd 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.h
+++ b/drivers/gpu/drm/i915/gvt/scheduler.h
@@ -83,7 +83,6 @@ struct intel_vgpu_workload {
 	struct i915_request *req;
 	/* if this workload has been dispatched to i915? */
 	bool dispatched;
-	bool shadowed;
 	int status;
 
 	struct intel_vgpu_mm *shadow_mm;
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 572a18c2bfb5..f6fa916517c3 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -46,6 +46,7 @@ void populate_pvinfo_page(struct intel_vgpu *vgpu)
 
 	vgpu_vreg_t(vgpu, vgtif_reg(vgt_caps)) = VGT_CAPS_FULL_48BIT_PPGTT;
 	vgpu_vreg_t(vgpu, vgtif_reg(vgt_caps)) |= VGT_CAPS_HWSP_EMULATION;
+	vgpu_vreg_t(vgpu, vgtif_reg(vgt_caps)) |= VGT_CAPS_HUGE_GTT;
 
 	vgpu_vreg_t(vgpu, vgtif_reg(avail_rs.mappable_gmadr.base)) =
 		vgpu_aperture_gmadr_base(vgpu);
@@ -58,6 +59,9 @@ void populate_pvinfo_page(struct intel_vgpu *vgpu)
 
 	vgpu_vreg_t(vgpu, vgtif_reg(avail_rs.fence_num)) = vgpu_fence_sz(vgpu);
 
+	vgpu_vreg_t(vgpu, vgtif_reg(cursor_x_hot)) = UINT_MAX;
+	vgpu_vreg_t(vgpu, vgtif_reg(cursor_y_hot)) = UINT_MAX;
+
 	gvt_dbg_core("Populate PVINFO PAGE for vGPU %d\n", vgpu->id);
 	gvt_dbg_core("aperture base [GMADR] 0x%llx size 0x%llx\n",
 		vgpu_aperture_gmadr_base(vgpu), vgpu_aperture_sz(vgpu));
@@ -223,22 +227,20 @@ void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu)
  */
 void intel_gvt_deactivate_vgpu(struct intel_vgpu *vgpu)
 {
-	struct intel_gvt *gvt = vgpu->gvt;
-
-	mutex_lock(&gvt->lock);
+	mutex_lock(&vgpu->vgpu_lock);
 
 	vgpu->active = false;
 
 	if (atomic_read(&vgpu->submission.running_workload_num)) {
-		mutex_unlock(&gvt->lock);
+		mutex_unlock(&vgpu->vgpu_lock);
 		intel_gvt_wait_vgpu_idle(vgpu);
-		mutex_lock(&gvt->lock);
+		mutex_lock(&vgpu->vgpu_lock);
 	}
 
 	intel_vgpu_stop_schedule(vgpu);
 	intel_vgpu_dmabuf_cleanup(vgpu);
 
-	mutex_unlock(&gvt->lock);
+	mutex_unlock(&vgpu->vgpu_lock);
 }
 
 /**
@@ -252,14 +254,11 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
 {
 	struct intel_gvt *gvt = vgpu->gvt;
 
-	mutex_lock(&gvt->lock);
+	mutex_lock(&vgpu->vgpu_lock);
 
 	WARN(vgpu->active, "vGPU is still active!\n");
 
 	intel_gvt_debugfs_remove_vgpu(vgpu);
-	idr_remove(&gvt->vgpu_idr, vgpu->id);
-	if (idr_is_empty(&gvt->vgpu_idr))
-		intel_gvt_clean_irq(gvt);
 	intel_vgpu_clean_sched_policy(vgpu);
 	intel_vgpu_clean_submission(vgpu);
 	intel_vgpu_clean_display(vgpu);
@@ -269,10 +268,16 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
 	intel_vgpu_free_resource(vgpu);
 	intel_vgpu_clean_mmio(vgpu);
 	intel_vgpu_dmabuf_cleanup(vgpu);
-	vfree(vgpu);
+	mutex_unlock(&vgpu->vgpu_lock);
 
+	mutex_lock(&gvt->lock);
+	idr_remove(&gvt->vgpu_idr, vgpu->id);
+	if (idr_is_empty(&gvt->vgpu_idr))
+		intel_gvt_clean_irq(gvt);
 	intel_gvt_update_vgpu_types(gvt);
 	mutex_unlock(&gvt->lock);
+
+	vfree(vgpu);
 }
 
 #define IDLE_VGPU_IDR 0
@@ -298,6 +303,7 @@ struct intel_vgpu *intel_gvt_create_idle_vgpu(struct intel_gvt *gvt)
 
 	vgpu->id = IDLE_VGPU_IDR;
 	vgpu->gvt = gvt;
+	mutex_init(&vgpu->vgpu_lock);
 
 	for (i = 0; i < I915_NUM_ENGINES; i++)
 		INIT_LIST_HEAD(&vgpu->submission.workload_q_head[i]);
@@ -324,7 +330,10 @@ out_free_vgpu:
  */
 void intel_gvt_destroy_idle_vgpu(struct intel_vgpu *vgpu)
 {
+	mutex_lock(&vgpu->vgpu_lock);
 	intel_vgpu_clean_sched_policy(vgpu);
+	mutex_unlock(&vgpu->vgpu_lock);
+
 	vfree(vgpu);
 }
 
@@ -342,8 +351,6 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt,
 	if (!vgpu)
 		return ERR_PTR(-ENOMEM);
 
-	mutex_lock(&gvt->lock);
-
 	ret = idr_alloc(&gvt->vgpu_idr, vgpu, IDLE_VGPU_IDR + 1, GVT_MAX_VGPU,
 		GFP_KERNEL);
 	if (ret < 0)
@@ -353,6 +360,7 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt,
 	vgpu->handle = param->handle;
 	vgpu->gvt = gvt;
 	vgpu->sched_ctl.weight = param->weight;
+	mutex_init(&vgpu->vgpu_lock);
 	INIT_LIST_HEAD(&vgpu->dmabuf_obj_list_head);
 	INIT_RADIX_TREE(&vgpu->page_track_tree, GFP_KERNEL);
 	idr_init(&vgpu->object_idr);
@@ -400,8 +408,6 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt,
 	if (ret)
 		goto out_clean_sched_policy;
 
-	mutex_unlock(&gvt->lock);
-
 	return vgpu;
 
 out_clean_sched_policy:
@@ -424,7 +430,6 @@ out_clean_idr:
 	idr_remove(&gvt->vgpu_idr, vgpu->id);
 out_free_vgpu:
 	vfree(vgpu);
-	mutex_unlock(&gvt->lock);
 	return ERR_PTR(ret);
 }
 
@@ -456,12 +461,12 @@ struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt,
 	param.low_gm_sz = BYTES_TO_MB(param.low_gm_sz);
 	param.high_gm_sz = BYTES_TO_MB(param.high_gm_sz);
 
+	mutex_lock(&gvt->lock);
 	vgpu = __intel_gvt_create_vgpu(gvt, &param);
-	if (IS_ERR(vgpu))
-		return vgpu;
-
-	/* calculate left instance change for types */
-	intel_gvt_update_vgpu_types(gvt);
+	if (!IS_ERR(vgpu))
+		/* calculate left instance change for types */
+		intel_gvt_update_vgpu_types(gvt);
+	mutex_unlock(&gvt->lock);
 
 	return vgpu;
 }
@@ -473,7 +478,7 @@ struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt,
  * @engine_mask: engines to reset for GT reset
  *
  * This function is called when user wants to reset a virtual GPU through
- * device model reset or GT reset. The caller should hold the gvt lock.
+ * device model reset or GT reset. The caller should hold the vgpu lock.
  *
  * vGPU Device Model Level Reset (DMLR) simulates the PCI level reset to reset
  * the whole vGPU to default state as when it is created. This vGPU function
@@ -513,9 +518,9 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
 	 * scheduler when the reset is triggered by current vgpu.
 	 */
 	if (scheduler->current_vgpu == NULL) {
-		mutex_unlock(&gvt->lock);
+		mutex_unlock(&vgpu->vgpu_lock);
 		intel_gvt_wait_vgpu_idle(vgpu);
-		mutex_lock(&gvt->lock);
+		mutex_lock(&vgpu->vgpu_lock);
 	}
 
 	intel_vgpu_reset_submission(vgpu, resetting_eng);
@@ -555,7 +560,7 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
  */
 void intel_gvt_reset_vgpu(struct intel_vgpu *vgpu)
 {
-	mutex_lock(&vgpu->gvt->lock);
+	mutex_lock(&vgpu->vgpu_lock);
 	intel_gvt_reset_vgpu_locked(vgpu, true, 0);
-	mutex_unlock(&vgpu->gvt->lock);
+	mutex_unlock(&vgpu->vgpu_lock);
 }
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 13e7b9e4a6e6..f9ce35da4123 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -328,7 +328,7 @@ static int per_file_stats(int id, void *ptr, void *data)
 		} else {
 			struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vma->vm);
 
-			if (ppgtt->base.file != stats->file_priv)
+			if (ppgtt->vm.file != stats->file_priv)
 				continue;
 		}
 
@@ -508,7 +508,7 @@ static int i915_gem_object_info(struct seq_file *m, void *data)
 		   dpy_count, dpy_size);
 
 	seq_printf(m, "%llu [%pa] gtt total\n",
-		   ggtt->base.total, &ggtt->mappable_end);
+		   ggtt->vm.total, &ggtt->mappable_end);
 	seq_printf(m, "Supported page sizes: %s\n",
 		   stringify_page_sizes(INTEL_INFO(dev_priv)->page_sizes,
 					buf, sizeof(buf)));
@@ -542,8 +542,8 @@ static int i915_gem_object_info(struct seq_file *m, void *data)
 						   struct i915_request,
 						   client_link);
 		rcu_read_lock();
-		task = pid_task(request && request->ctx->pid ?
-				request->ctx->pid : file->pid,
+		task = pid_task(request && request->gem_context->pid ?
+				request->gem_context->pid : file->pid,
 				PIDTYPE_PID);
 		print_file_stats(m, task ? task->comm : "<unknown>", stats);
 		rcu_read_unlock();
@@ -1162,19 +1162,28 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 
 		intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 
-		if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv)) {
-			pm_ier = I915_READ(GEN6_PMIER);
-			pm_imr = I915_READ(GEN6_PMIMR);
-			pm_isr = I915_READ(GEN6_PMISR);
-			pm_iir = I915_READ(GEN6_PMIIR);
-			pm_mask = I915_READ(GEN6_PMINTRMSK);
-		} else {
+		if (INTEL_GEN(dev_priv) >= 11) {
+			pm_ier = I915_READ(GEN11_GPM_WGBOXPERF_INTR_ENABLE);
+			pm_imr = I915_READ(GEN11_GPM_WGBOXPERF_INTR_MASK);
+			/*
+			 * The equivalent to the PM ISR & IIR cannot be read
+			 * without affecting the current state of the system
+			 */
+			pm_isr = 0;
+			pm_iir = 0;
+		} else if (INTEL_GEN(dev_priv) >= 8) {
 			pm_ier = I915_READ(GEN8_GT_IER(2));
 			pm_imr = I915_READ(GEN8_GT_IMR(2));
 			pm_isr = I915_READ(GEN8_GT_ISR(2));
 			pm_iir = I915_READ(GEN8_GT_IIR(2));
-			pm_mask = I915_READ(GEN6_PMINTRMSK);
+		} else {
+			pm_ier = I915_READ(GEN6_PMIER);
+			pm_imr = I915_READ(GEN6_PMIMR);
+			pm_isr = I915_READ(GEN6_PMISR);
+			pm_iir = I915_READ(GEN6_PMIIR);
 		}
+		pm_mask = I915_READ(GEN6_PMINTRMSK);
+
 		seq_printf(m, "Video Turbo Mode: %s\n",
 			   yesno(rpmodectl & GEN6_RP_MEDIA_TURBO));
 		seq_printf(m, "HW control enabled: %s\n",
@@ -1182,8 +1191,12 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		seq_printf(m, "SW control enabled: %s\n",
 			   yesno((rpmodectl & GEN6_RP_MEDIA_MODE_MASK) ==
 				  GEN6_RP_MEDIA_SW_MODE));
-		seq_printf(m, "PM IER=0x%08x IMR=0x%08x ISR=0x%08x IIR=0x%08x, MASK=0x%08x\n",
-			   pm_ier, pm_imr, pm_isr, pm_iir, pm_mask);
+
+		seq_printf(m, "PM IER=0x%08x IMR=0x%08x, MASK=0x%08x\n",
+			   pm_ier, pm_imr, pm_mask);
+		if (INTEL_GEN(dev_priv) <= 10)
+			seq_printf(m, "PM ISR=0x%08x IIR=0x%08x\n",
+				   pm_isr, pm_iir);
 		seq_printf(m, "pm_intrmsk_mbz: 0x%08x\n",
 			   rps->pm_intrmsk_mbz);
 		seq_printf(m, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status);
@@ -1205,7 +1218,8 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 			   rpcurup, GT_PM_INTERVAL_TO_US(dev_priv, rpcurup));
 		seq_printf(m, "RP PREV UP: %d (%dus)\n",
 			   rpprevup, GT_PM_INTERVAL_TO_US(dev_priv, rpprevup));
-		seq_printf(m, "Up threshold: %d%%\n", rps->up_threshold);
+		seq_printf(m, "Up threshold: %d%%\n",
+			   rps->power.up_threshold);
 
 		seq_printf(m, "RP CUR DOWN EI: %d (%dus)\n",
 			   rpdownei, GT_PM_INTERVAL_TO_US(dev_priv, rpdownei));
@@ -1213,7 +1227,8 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 			   rpcurdown, GT_PM_INTERVAL_TO_US(dev_priv, rpcurdown));
 		seq_printf(m, "RP PREV DOWN: %d (%dus)\n",
 			   rpprevdown, GT_PM_INTERVAL_TO_US(dev_priv, rpprevdown));
-		seq_printf(m, "Down threshold: %d%%\n", rps->down_threshold);
+		seq_printf(m, "Down threshold: %d%%\n",
+			   rps->power.down_threshold);
 
 		max_freq = (IS_GEN9_LP(dev_priv) ? rp_state_cap >> 0 :
 			    rp_state_cap >> 16) & 0xff;
@@ -1346,11 +1361,12 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 		seq_printf(m, "\tseqno = %x [current %x, last %x]\n",
 			   engine->hangcheck.seqno, seqno[id],
 			   intel_engine_last_submit(engine));
-		seq_printf(m, "\twaiters? %s, fake irq active? %s, stalled? %s\n",
+		seq_printf(m, "\twaiters? %s, fake irq active? %s, stalled? %s, wedged? %s\n",
 			   yesno(intel_engine_has_waiter(engine)),
 			   yesno(test_bit(engine->id,
 					  &dev_priv->gpu_error.missed_irq_rings)),
-			   yesno(engine->hangcheck.stalled));
+			   yesno(engine->hangcheck.stalled),
+			   yesno(engine->hangcheck.wedged));
 
 		spin_lock_irq(&b->rb_lock);
 		for (rb = rb_first(&b->waiters); rb; rb = rb_next(rb)) {
@@ -1645,11 +1661,6 @@ static int i915_fbc_status(struct seq_file *m, void *unused)
 	else
 		seq_printf(m, "FBC disabled: %s\n", fbc->no_fbc_reason);
 
-	if (fbc->work.scheduled)
-		seq_printf(m, "FBC worker scheduled on vblank %llu, now %llu\n",
-			   fbc->work.scheduled_vblank,
-			   drm_crtc_vblank_count(&fbc->crtc->base));
-
 	if (intel_fbc_is_active(dev_priv)) {
 		u32 mask;
 
@@ -1895,7 +1906,7 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 			   fbdev_fb->base.format->cpp[0] * 8,
 			   fbdev_fb->base.modifier,
 			   drm_framebuffer_read_refcount(&fbdev_fb->base));
-		describe_obj(m, fbdev_fb->obj);
+		describe_obj(m, intel_fb_obj(&fbdev_fb->base));
 		seq_putc(m, '\n');
 	}
 #endif
@@ -1913,7 +1924,7 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 			   fb->base.format->cpp[0] * 8,
 			   fb->base.modifier,
 			   drm_framebuffer_read_refcount(&fb->base));
-		describe_obj(m, fb->obj);
+		describe_obj(m, intel_fb_obj(&fb->base));
 		seq_putc(m, '\n');
 	}
 	mutex_unlock(&dev->mode_config.fb_lock);
@@ -2209,6 +2220,7 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
 	seq_printf(m, "CPU waiting? %d\n", count_irq_waiters(dev_priv));
 	seq_printf(m, "Boosts outstanding? %d\n",
 		   atomic_read(&rps->num_waiters));
+	seq_printf(m, "Interactive? %d\n", READ_ONCE(rps->power.interactive));
 	seq_printf(m, "Frequency requested %d\n",
 		   intel_gpu_freq(dev_priv, rps->cur_freq));
 	seq_printf(m, "  min hard:%d, soft:%d; max soft:%d, hard:%d\n",
@@ -2252,13 +2264,13 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
 		intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 
 		seq_printf(m, "\nRPS Autotuning (current \"%s\" window):\n",
-			   rps_power_to_str(rps->power));
+			   rps_power_to_str(rps->power.mode));
 		seq_printf(m, "  Avg. up: %d%% [above threshold? %d%%]\n",
 			   rpup && rpupei ? 100 * rpup / rpupei : 0,
-			   rps->up_threshold);
+			   rps->power.up_threshold);
 		seq_printf(m, "  Avg. down: %d%% [below threshold? %d%%]\n",
 			   rpdown && rpdownei ? 100 * rpdown / rpdownei : 0,
-			   rps->down_threshold);
+			   rps->power.down_threshold);
 	} else {
 		seq_puts(m, "\nRPS Autotuning inactive\n");
 	}
@@ -2523,7 +2535,7 @@ static int i915_guc_log_level_get(void *data, u64 *val)
 	if (!USES_GUC(dev_priv))
 		return -ENODEV;
 
-	*val = intel_guc_log_level_get(&dev_priv->guc.log);
+	*val = intel_guc_log_get_level(&dev_priv->guc.log);
 
 	return 0;
 }
@@ -2535,7 +2547,7 @@ static int i915_guc_log_level_set(void *data, u64 val)
 	if (!USES_GUC(dev_priv))
 		return -ENODEV;
 
-	return intel_guc_log_level_set(&dev_priv->guc.log, val);
+	return intel_guc_log_set_level(&dev_priv->guc.log, val);
 }
 
 DEFINE_SIMPLE_ATTRIBUTE(i915_guc_log_level_fops,
@@ -2583,31 +2595,9 @@ static const struct file_operations i915_guc_log_relay_fops = {
 	.release = i915_guc_log_relay_release,
 };
 
-static const char *psr2_live_status(u32 val)
-{
-	static const char * const live_status[] = {
-		"IDLE",
-		"CAPTURE",
-		"CAPTURE_FS",
-		"SLEEP",
-		"BUFON_FW",
-		"ML_UP",
-		"SU_STANDBY",
-		"FAST_SLEEP",
-		"DEEP_SLEEP",
-		"BUF_ON",
-		"TG_ON"
-	};
-
-	val = (val & EDP_PSR2_STATUS_STATE_MASK) >> EDP_PSR2_STATUS_STATE_SHIFT;
-	if (val < ARRAY_SIZE(live_status))
-		return live_status[val];
-
-	return "unknown";
-}
-
-static const char *psr_sink_status(u8 val)
+static int i915_psr_sink_status_show(struct seq_file *m, void *data)
 {
+	u8 val;
 	static const char * const sink_status[] = {
 		"inactive",
 		"transition to active, capture and display",
@@ -2616,22 +2606,94 @@ static const char *psr_sink_status(u8 val)
 		"transition to inactive, capture and display, timing re-sync",
 		"reserved",
 		"reserved",
-		"sink internal error"
+		"sink internal error",
 	};
+	struct drm_connector *connector = m->private;
+	struct drm_i915_private *dev_priv = to_i915(connector->dev);
+	struct intel_dp *intel_dp =
+		enc_to_intel_dp(&intel_attached_encoder(connector)->base);
+	int ret;
 
-	val &= DP_PSR_SINK_STATE_MASK;
-	if (val < ARRAY_SIZE(sink_status))
-		return sink_status[val];
+	if (!CAN_PSR(dev_priv)) {
+		seq_puts(m, "PSR Unsupported\n");
+		return -ENODEV;
+	}
 
-	return "unknown";
+	if (connector->status != connector_status_connected)
+		return -ENODEV;
+
+	ret = drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_STATUS, &val);
+
+	if (ret == 1) {
+		const char *str = "unknown";
+
+		val &= DP_PSR_SINK_STATE_MASK;
+		if (val < ARRAY_SIZE(sink_status))
+			str = sink_status[val];
+		seq_printf(m, "Sink PSR status: 0x%x [%s]\n", val, str);
+	} else {
+		return ret;
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(i915_psr_sink_status);
+
+static void
+psr_source_status(struct drm_i915_private *dev_priv, struct seq_file *m)
+{
+	u32 val, psr_status;
+
+	if (dev_priv->psr.psr2_enabled) {
+		static const char * const live_status[] = {
+			"IDLE",
+			"CAPTURE",
+			"CAPTURE_FS",
+			"SLEEP",
+			"BUFON_FW",
+			"ML_UP",
+			"SU_STANDBY",
+			"FAST_SLEEP",
+			"DEEP_SLEEP",
+			"BUF_ON",
+			"TG_ON"
+		};
+		psr_status = I915_READ(EDP_PSR2_STATUS);
+		val = (psr_status & EDP_PSR2_STATUS_STATE_MASK) >>
+			EDP_PSR2_STATUS_STATE_SHIFT;
+		if (val < ARRAY_SIZE(live_status)) {
+			seq_printf(m, "Source PSR status: 0x%x [%s]\n",
+				   psr_status, live_status[val]);
+			return;
+		}
+	} else {
+		static const char * const live_status[] = {
+			"IDLE",
+			"SRDONACK",
+			"SRDENT",
+			"BUFOFF",
+			"BUFON",
+			"AUXACK",
+			"SRDOFFACK",
+			"SRDENT_ON",
+		};
+		psr_status = I915_READ(EDP_PSR_STATUS);
+		val = (psr_status & EDP_PSR_STATUS_STATE_MASK) >>
+			EDP_PSR_STATUS_STATE_SHIFT;
+		if (val < ARRAY_SIZE(live_status)) {
+			seq_printf(m, "Source PSR status: 0x%x [%s]\n",
+				   psr_status, live_status[val]);
+			return;
+		}
+	}
+
+	seq_printf(m, "Source PSR status: 0x%x [%s]\n", psr_status, "unknown");
 }
 
 static int i915_edp_psr_status(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	u32 psrperf = 0;
-	u32 stat[3];
-	enum pipe pipe;
 	bool enabled = false;
 	bool sink_support;
 
@@ -2649,50 +2711,18 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 	seq_printf(m, "Enabled: %s\n", yesno((bool)dev_priv->psr.enabled));
 	seq_printf(m, "Busy frontbuffer bits: 0x%03x\n",
 		   dev_priv->psr.busy_frontbuffer_bits);
-	seq_printf(m, "Re-enable work scheduled: %s\n",
-		   yesno(work_busy(&dev_priv->psr.work.work)));
-
-	if (HAS_DDI(dev_priv)) {
-		if (dev_priv->psr.psr2_enabled)
-			enabled = I915_READ(EDP_PSR2_CTL) & EDP_PSR2_ENABLE;
-		else
-			enabled = I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE;
-	} else {
-		for_each_pipe(dev_priv, pipe) {
-			enum transcoder cpu_transcoder =
-				intel_pipe_to_cpu_transcoder(dev_priv, pipe);
-			enum intel_display_power_domain power_domain;
 
-			power_domain = POWER_DOMAIN_TRANSCODER(cpu_transcoder);
-			if (!intel_display_power_get_if_enabled(dev_priv,
-								power_domain))
-				continue;
-
-			stat[pipe] = I915_READ(VLV_PSRSTAT(pipe)) &
-				VLV_EDP_PSR_CURR_STATE_MASK;
-			if ((stat[pipe] == VLV_EDP_PSR_ACTIVE_NORFB_UP) ||
-			    (stat[pipe] == VLV_EDP_PSR_ACTIVE_SF_UPDATE))
-				enabled = true;
-
-			intel_display_power_put(dev_priv, power_domain);
-		}
-	}
+	if (dev_priv->psr.psr2_enabled)
+		enabled = I915_READ(EDP_PSR2_CTL) & EDP_PSR2_ENABLE;
+	else
+		enabled = I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE;
 
 	seq_printf(m, "Main link in standby mode: %s\n",
 		   yesno(dev_priv->psr.link_standby));
 
-	seq_printf(m, "HW Enabled & Active bit: %s", yesno(enabled));
-
-	if (!HAS_DDI(dev_priv))
-		for_each_pipe(dev_priv, pipe) {
-			if ((stat[pipe] == VLV_EDP_PSR_ACTIVE_NORFB_UP) ||
-			    (stat[pipe] == VLV_EDP_PSR_ACTIVE_SF_UPDATE))
-				seq_printf(m, " pipe %c", pipe_name(pipe));
-		}
-	seq_puts(m, "\n");
+	seq_printf(m, "HW Enabled & Active bit: %s\n", yesno(enabled));
 
 	/*
-	 * VLV/CHV PSR has no kind of performance counter
 	 * SKL+ Perf counter is reset to 0 everytime DC state is entered
 	 */
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
@@ -2701,21 +2731,8 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 
 		seq_printf(m, "Performance_Counter: %u\n", psrperf);
 	}
-	if (dev_priv->psr.psr2_enabled) {
-		u32 psr2 = I915_READ(EDP_PSR2_STATUS);
-
-		seq_printf(m, "EDP_PSR2_STATUS: %x [%s]\n",
-			   psr2, psr2_live_status(psr2));
-	}
 
-	if (dev_priv->psr.enabled) {
-		struct drm_dp_aux *aux = &dev_priv->psr.enabled->aux;
-		u8 val;
-
-		if (drm_dp_dpcd_readb(aux, DP_PSR_STATUS, &val) == 1)
-			seq_printf(m, "Sink PSR status: 0x%x [%s]\n", val,
-				   psr_sink_status(val));
-	}
+	psr_source_status(dev_priv, m);
 	mutex_unlock(&dev_priv->psr.lock);
 
 	if (READ_ONCE(dev_priv->psr.debug)) {
@@ -2762,86 +2779,6 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_edp_psr_debug_fops,
 			i915_edp_psr_debug_get, i915_edp_psr_debug_set,
 			"%llu\n");
 
-static int i915_sink_crc(struct seq_file *m, void *data)
-{
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
-	struct intel_connector *connector;
-	struct drm_connector_list_iter conn_iter;
-	struct intel_dp *intel_dp = NULL;
-	struct drm_modeset_acquire_ctx ctx;
-	int ret;
-	u8 crc[6];
-
-	drm_modeset_acquire_init(&ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE);
-
-	drm_connector_list_iter_begin(dev, &conn_iter);
-
-	for_each_intel_connector_iter(connector, &conn_iter) {
-		struct drm_crtc *crtc;
-		struct drm_connector_state *state;
-		struct intel_crtc_state *crtc_state;
-
-		if (connector->base.connector_type != DRM_MODE_CONNECTOR_eDP)
-			continue;
-
-retry:
-		ret = drm_modeset_lock(&dev->mode_config.connection_mutex, &ctx);
-		if (ret)
-			goto err;
-
-		state = connector->base.state;
-		if (!state->best_encoder)
-			continue;
-
-		crtc = state->crtc;
-		ret = drm_modeset_lock(&crtc->mutex, &ctx);
-		if (ret)
-			goto err;
-
-		crtc_state = to_intel_crtc_state(crtc->state);
-		if (!crtc_state->base.active)
-			continue;
-
-		/*
-		 * We need to wait for all crtc updates to complete, to make
-		 * sure any pending modesets and plane updates are completed.
-		 */
-		if (crtc_state->base.commit) {
-			ret = wait_for_completion_interruptible(&crtc_state->base.commit->hw_done);
-
-			if (ret)
-				goto err;
-		}
-
-		intel_dp = enc_to_intel_dp(state->best_encoder);
-
-		ret = intel_dp_sink_crc(intel_dp, crtc_state, crc);
-		if (ret)
-			goto err;
-
-		seq_printf(m, "%02x%02x%02x%02x%02x%02x\n",
-			   crc[0], crc[1], crc[2],
-			   crc[3], crc[4], crc[5]);
-		goto out;
-
-err:
-		if (ret == -EDEADLK) {
-			ret = drm_modeset_backoff(&ctx);
-			if (!ret)
-				goto retry;
-		}
-		goto out;
-	}
-	ret = -ENODEV;
-out:
-	drm_connector_list_iter_end(&conn_iter);
-	drm_modeset_drop_locks(&ctx);
-	drm_modeset_acquire_fini(&ctx);
-
-	return ret;
-}
-
 static int i915_energy_uJ(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
@@ -3398,28 +3335,13 @@ static int i915_shared_dplls_info(struct seq_file *m, void *unused)
 
 static int i915_wa_registers(struct seq_file *m, void *unused)
 {
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct i915_workarounds *workarounds = &dev_priv->workarounds;
+	struct i915_workarounds *wa = &node_to_i915(m->private)->workarounds;
 	int i;
 
-	intel_runtime_pm_get(dev_priv);
-
-	seq_printf(m, "Workarounds applied: %d\n", workarounds->count);
-	for (i = 0; i < workarounds->count; ++i) {
-		i915_reg_t addr;
-		u32 mask, value, read;
-		bool ok;
-
-		addr = workarounds->reg[i].addr;
-		mask = workarounds->reg[i].mask;
-		value = workarounds->reg[i].value;
-		read = I915_READ(addr);
-		ok = (value & mask) == (read & mask);
-		seq_printf(m, "0x%X: 0x%08X, mask: 0x%08X, read: 0x%08x, status: %s\n",
-			   i915_mmio_reg_offset(addr), value, mask, read, ok ? "OK" : "FAIL");
-	}
-
-	intel_runtime_pm_put(dev_priv);
+	seq_printf(m, "Workarounds applied: %d\n", wa->count);
+	for (i = 0; i < wa->count; ++i)
+		seq_printf(m, "0x%X: 0x%08X, mask: 0x%08X\n",
+			   wa->reg[i].addr, wa->reg[i].value, wa->reg[i].mask);
 
 	return 0;
 }
@@ -4121,7 +4043,8 @@ fault_irq_set(struct drm_i915_private *i915,
 
 	err = i915_gem_wait_for_idle(i915,
 				     I915_WAIT_LOCKED |
-				     I915_WAIT_INTERRUPTIBLE);
+				     I915_WAIT_INTERRUPTIBLE,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (err)
 		goto err_unlock;
 
@@ -4226,7 +4149,8 @@ i915_drop_caches_set(void *data, u64 val)
 		if (val & DROP_ACTIVE)
 			ret = i915_gem_wait_for_idle(dev_priv,
 						     I915_WAIT_INTERRUPTIBLE |
-						     I915_WAIT_LOCKED);
+						     I915_WAIT_LOCKED,
+						     MAX_SCHEDULE_TIMEOUT);
 
 		if (val & DROP_RETIRE)
 			i915_retire_requests(dev_priv);
@@ -4245,8 +4169,13 @@ i915_drop_caches_set(void *data, u64 val)
 		i915_gem_shrink_all(dev_priv);
 	fs_reclaim_release(GFP_KERNEL);
 
-	if (val & DROP_IDLE)
-		drain_delayed_work(&dev_priv->gt.idle_work);
+	if (val & DROP_IDLE) {
+		do {
+			if (READ_ONCE(dev_priv->gt.active_requests))
+				flush_delayed_work(&dev_priv->gt.retire_work);
+			drain_delayed_work(&dev_priv->gt.idle_work);
+		} while (READ_ONCE(dev_priv->gt.awake));
+	}
 
 	if (val & DROP_FREED)
 		i915_gem_drain_freed_objects(dev_priv);
@@ -4795,7 +4724,6 @@ static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_ppgtt_info", i915_ppgtt_info, 0},
 	{"i915_llc", i915_llc, 0},
 	{"i915_edp_psr_status", i915_edp_psr_status, 0},
-	{"i915_sink_crc_eDP1", i915_sink_crc, 0},
 	{"i915_energy_uJ", i915_energy_uJ, 0},
 	{"i915_runtime_pm_status", i915_runtime_pm_status, 0},
 	{"i915_power_domain_info", i915_power_domain_info, 0},
@@ -4829,7 +4757,6 @@ static const struct i915_debugfs_files {
 #endif
 	{"i915_fifo_underrun_reset", &i915_fifo_underrun_reset_ops},
 	{"i915_next_seqno", &i915_next_seqno_fops},
-	{"i915_display_crc_ctl", &i915_display_crc_ctl_fops},
 	{"i915_pri_wm_latency", &i915_pri_wm_latency_fops},
 	{"i915_spr_wm_latency", &i915_spr_wm_latency_fops},
 	{"i915_cur_wm_latency", &i915_cur_wm_latency_fops},
@@ -4849,7 +4776,7 @@ int i915_debugfs_register(struct drm_i915_private *dev_priv)
 {
 	struct drm_minor *minor = dev_priv->drm.primary;
 	struct dentry *ent;
-	int ret, i;
+	int i;
 
 	ent = debugfs_create_file("i915_forcewake_user", S_IRUSR,
 				  minor->debugfs_root, to_i915(minor->dev),
@@ -4857,10 +4784,6 @@ int i915_debugfs_register(struct drm_i915_private *dev_priv)
 	if (!ent)
 		return -ENOMEM;
 
-	ret = intel_pipe_crc_create(minor);
-	if (ret)
-		return ret;
-
 	for (i = 0; i < ARRAY_SIZE(i915_debugfs_files); i++) {
 		ent = debugfs_create_file(i915_debugfs_files[i].name,
 					  S_IRUGO | S_IWUSR,
@@ -4982,9 +4905,12 @@ int i915_debugfs_connector_add(struct drm_connector *connector)
 		debugfs_create_file("i915_dpcd", S_IRUGO, root,
 				    connector, &i915_dpcd_fops);
 
-	if (connector->connector_type == DRM_MODE_CONNECTOR_eDP)
+	if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
 		debugfs_create_file("i915_panel_timings", S_IRUGO, root,
 				    connector, &i915_panel_fops);
+		debugfs_create_file("i915_psr_sink_status", S_IRUGO, root,
+				    connector, &i915_psr_sink_status_fops);
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 9c449b8d8eab..f8cfd16be534 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -67,11 +67,18 @@ bool __i915_inject_load_failure(const char *func, int line)
 	if (++i915_load_fail_count == i915_modparams.inject_load_failure) {
 		DRM_INFO("Injecting failure at checkpoint %u [%s:%d]\n",
 			 i915_modparams.inject_load_failure, func, line);
+		i915_modparams.inject_load_failure = 0;
 		return true;
 	}
 
 	return false;
 }
+
+bool i915_error_injected(void)
+{
+	return i915_load_fail_count && !i915_modparams.inject_load_failure;
+}
+
 #endif
 
 #define FDO_BUG_URL "https://bugs.freedesktop.org/enter_bug.cgi?product=DRI"
@@ -97,8 +104,13 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	dev_printk(level, kdev, "[" DRM_NAME ":%ps] %pV",
-		   __builtin_return_address(0), &vaf);
+	if (is_error)
+		dev_printk(level, kdev, "%pV", &vaf);
+	else
+		dev_printk(level, kdev, "[" DRM_NAME ":%ps] %pV",
+			   __builtin_return_address(0), &vaf);
+
+	va_end(args);
 
 	if (is_error && !shown_bug_once) {
 		/*
@@ -110,25 +122,8 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level,
 			dev_notice(kdev, "%s", FDO_BUG_MSG);
 		shown_bug_once = true;
 	}
-
-	va_end(args);
-}
-
-static bool i915_error_injected(struct drm_i915_private *dev_priv)
-{
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
-	return i915_modparams.inject_load_failure &&
-	       i915_load_fail_count == i915_modparams.inject_load_failure;
-#else
-	return false;
-#endif
 }
 
-#define i915_load_error(dev_priv, fmt, ...)				     \
-	__i915_printk(dev_priv,						     \
-		      i915_error_injected(dev_priv) ? KERN_DEBUG : KERN_ERR, \
-		      fmt, ##__VA_ARGS__)
-
 /* Map PCH device id to PCH type, or PCH_NONE if unknown. */
 static enum intel_pch
 intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id)
@@ -233,6 +228,8 @@ intel_virt_detect_pch(const struct drm_i915_private *dev_priv)
 		id = INTEL_PCH_SPT_DEVICE_ID_TYPE;
 	else if (IS_COFFEELAKE(dev_priv) || IS_CANNONLAKE(dev_priv))
 		id = INTEL_PCH_CNP_DEVICE_ID_TYPE;
+	else if (IS_ICELAKE(dev_priv))
+		id = INTEL_PCH_ICP_DEVICE_ID_TYPE;
 
 	if (id)
 		DRM_DEBUG_KMS("Assuming PCH ID %04x\n", id);
@@ -246,14 +243,6 @@ static void intel_detect_pch(struct drm_i915_private *dev_priv)
 {
 	struct pci_dev *pch = NULL;
 
-	/* In all current cases, num_pipes is equivalent to the PCH_NOP setting
-	 * (which really amounts to a PCH but no South Display).
-	 */
-	if (INTEL_INFO(dev_priv)->num_pipes == 0) {
-		dev_priv->pch_type = PCH_NOP;
-		return;
-	}
-
 	/*
 	 * The reason to probe ISA bridge instead of Dev31:Fun0 is to
 	 * make graphics device passthrough work easy for VMM, that only
@@ -282,18 +271,28 @@ static void intel_detect_pch(struct drm_i915_private *dev_priv)
 		} else if (intel_is_virt_pch(id, pch->subsystem_vendor,
 					 pch->subsystem_device)) {
 			id = intel_virt_detect_pch(dev_priv);
-			if (id) {
-				pch_type = intel_pch_type(dev_priv, id);
-				if (WARN_ON(pch_type == PCH_NONE))
-					pch_type = PCH_NOP;
-			} else {
-				pch_type = PCH_NOP;
-			}
+			pch_type = intel_pch_type(dev_priv, id);
+
+			/* Sanity check virtual PCH id */
+			if (WARN_ON(id && pch_type == PCH_NONE))
+				id = 0;
+
 			dev_priv->pch_type = pch_type;
 			dev_priv->pch_id = id;
 			break;
 		}
 	}
+
+	/*
+	 * Use PCH_NOP (PCH but no South Display) for PCH platforms without
+	 * display.
+	 */
+	if (pch && INTEL_INFO(dev_priv)->num_pipes == 0) {
+		DRM_DEBUG_KMS("Display disabled, reverting to NOP PCH\n");
+		dev_priv->pch_type = PCH_NOP;
+		dev_priv->pch_id = 0;
+	}
+
 	if (!pch)
 		DRM_DEBUG_KMS("No PCH found.\n");
 
@@ -634,26 +633,6 @@ static const struct vga_switcheroo_client_ops i915_switcheroo_ops = {
 	.can_switch = i915_switcheroo_can_switch,
 };
 
-static void i915_gem_fini(struct drm_i915_private *dev_priv)
-{
-	/* Flush any outstanding unpin_work. */
-	i915_gem_drain_workqueue(dev_priv);
-
-	mutex_lock(&dev_priv->drm.struct_mutex);
-	intel_uc_fini_hw(dev_priv);
-	intel_uc_fini(dev_priv);
-	i915_gem_cleanup_engines(dev_priv);
-	i915_gem_contexts_fini(dev_priv);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
-
-	intel_uc_fini_misc(dev_priv);
-	i915_gem_cleanup_userptr(dev_priv);
-
-	i915_gem_drain_freed_objects(dev_priv);
-
-	WARN_ON(!list_empty(&dev_priv->contexts.list));
-}
-
 static int i915_load_modeset_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -703,7 +682,7 @@ static int i915_load_modeset_init(struct drm_device *dev)
 
 	ret = i915_gem_init(dev_priv);
 	if (ret)
-		goto cleanup_irq;
+		goto cleanup_modeset;
 
 	intel_setup_overlay(dev_priv);
 
@@ -723,6 +702,8 @@ cleanup_gem:
 	if (i915_gem_suspend(dev_priv))
 		DRM_ERROR("failed to idle hardware; continuing to unload!\n");
 	i915_gem_fini(dev_priv);
+cleanup_modeset:
+	intel_modeset_cleanup(dev);
 cleanup_irq:
 	drm_irq_uninstall(dev);
 	intel_teardown_gmbus(dev_priv);
@@ -919,7 +900,6 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv,
 	spin_lock_init(&dev_priv->uncore.lock);
 
 	mutex_init(&dev_priv->sb_lock);
-	mutex_init(&dev_priv->modeset_restore_lock);
 	mutex_init(&dev_priv->av_mutex);
 	mutex_init(&dev_priv->wm.wm_mutex);
 	mutex_init(&dev_priv->pps_mutex);
@@ -1173,8 +1153,6 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
 
 	intel_uncore_sanitize(dev_priv);
 
-	intel_opregion_setup(dev_priv);
-
 	i915_gem_load_init_fences(dev_priv);
 
 	/* On the 945G/GM, the chipset reports the MSI capability on the
@@ -1189,6 +1167,12 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
 	 * get lost on g4x as well, and interrupt delivery seems to stay
 	 * properly dead afterwards. So we'll just disable them for all
 	 * pre-gen5 chipsets.
+	 *
+	 * dp aux and gmbus irq on gen4 seems to be able to generate legacy
+	 * interrupts even when in MSI mode. This results in spurious
+	 * interrupt warnings if the legacy irq no. is shared with another
+	 * device. The kernel then disables that interrupt source and so
+	 * prevents the other device from working properly.
 	 */
 	if (INTEL_GEN(dev_priv) >= 5) {
 		if (pci_enable_msi(pdev) < 0)
@@ -1197,10 +1181,16 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
 
 	ret = intel_gvt_init(dev_priv);
 	if (ret)
-		goto err_ggtt;
+		goto err_msi;
+
+	intel_opregion_setup(dev_priv);
 
 	return 0;
 
+err_msi:
+	if (pdev->msi_enabled)
+		pci_disable_msi(pdev);
+	pm_qos_remove_request(&dev_priv->pm_qos);
 err_ggtt:
 	i915_ggtt_cleanup_hw(dev_priv);
 err_perf:
@@ -1433,6 +1423,7 @@ out_fini:
 	drm_dev_fini(&dev_priv->drm);
 out_free:
 	kfree(dev_priv);
+	pci_set_drvdata(pdev, NULL);
 	return ret;
 }
 
@@ -1553,17 +1544,30 @@ static bool suspend_to_idle(struct drm_i915_private *dev_priv)
 	return false;
 }
 
+static int i915_drm_prepare(struct drm_device *dev)
+{
+	struct drm_i915_private *i915 = to_i915(dev);
+	int err;
+
+	/*
+	 * NB intel_display_suspend() may issue new requests after we've
+	 * ostensibly marked the GPU as ready-to-sleep here. We need to
+	 * split out that work and pull it forward so that after point,
+	 * the GPU is not woken again.
+	 */
+	err = i915_gem_suspend(i915);
+	if (err)
+		dev_err(&i915->drm.pdev->dev,
+			"GEM idle failed, suspend/resume might fail\n");
+
+	return err;
+}
+
 static int i915_drm_suspend(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct pci_dev *pdev = dev_priv->drm.pdev;
 	pci_power_t opregion_target_state;
-	int error;
-
-	/* ignore lid events during suspend */
-	mutex_lock(&dev_priv->modeset_restore_lock);
-	dev_priv->modeset_restore = MODESET_SUSPENDED;
-	mutex_unlock(&dev_priv->modeset_restore_lock);
 
 	disable_rpm_wakeref_asserts(dev_priv);
 
@@ -1575,16 +1579,9 @@ static int i915_drm_suspend(struct drm_device *dev)
 
 	pci_save_state(pdev);
 
-	error = i915_gem_suspend(dev_priv);
-	if (error) {
-		dev_err(&pdev->dev,
-			"GEM idle failed, resume might fail\n");
-		goto out;
-	}
-
 	intel_display_suspend(dev);
 
-	intel_dp_mst_suspend(dev);
+	intel_dp_mst_suspend(dev_priv);
 
 	intel_runtime_pm_disable_interrupts(dev_priv);
 	intel_hpd_cancel_work(dev_priv);
@@ -1600,7 +1597,6 @@ static int i915_drm_suspend(struct drm_device *dev)
 	opregion_target_state = suspend_to_idle(dev_priv) ? PCI_D1 : PCI_D3cold;
 	intel_opregion_notify_adapter(dev_priv, opregion_target_state);
 
-	intel_uncore_suspend(dev_priv);
 	intel_opregion_unregister(dev_priv);
 
 	intel_fbdev_set_suspend(dev, FBINFO_STATE_SUSPENDED, true);
@@ -1609,10 +1605,9 @@ static int i915_drm_suspend(struct drm_device *dev)
 
 	intel_csr_ucode_suspend(dev_priv);
 
-out:
 	enable_rpm_wakeref_asserts(dev_priv);
 
-	return error;
+	return 0;
 }
 
 static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation)
@@ -1623,7 +1618,10 @@ static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation)
 
 	disable_rpm_wakeref_asserts(dev_priv);
 
+	i915_gem_suspend_late(dev_priv);
+
 	intel_display_set_init_power(dev_priv, false);
+	intel_uncore_suspend(dev_priv);
 
 	/*
 	 * In case of firmware assisted context save/restore don't manually
@@ -1710,6 +1708,8 @@ static int i915_drm_resume(struct drm_device *dev)
 	disable_rpm_wakeref_asserts(dev_priv);
 	intel_sanitize_gt_powersave(dev_priv);
 
+	i915_gem_sanitize(dev_priv);
+
 	ret = i915_ggtt_enable_hw(dev_priv);
 	if (ret)
 		DRM_ERROR("failed to re-enable GGTT\n");
@@ -1746,7 +1746,7 @@ static int i915_drm_resume(struct drm_device *dev)
 		dev_priv->display.hpd_irq_setup(dev_priv);
 	spin_unlock_irq(&dev_priv->irq_lock);
 
-	intel_dp_mst_resume(dev);
+	intel_dp_mst_resume(dev_priv);
 
 	intel_display_resume(dev);
 
@@ -1764,10 +1764,6 @@ static int i915_drm_resume(struct drm_device *dev)
 
 	intel_fbdev_set_suspend(dev, FBINFO_STATE_RUNNING, false);
 
-	mutex_lock(&dev_priv->modeset_restore_lock);
-	dev_priv->modeset_restore = MODESET_DONE;
-	mutex_unlock(&dev_priv->modeset_restore_lock);
-
 	intel_opregion_notify_adapter(dev_priv, PCI_D0);
 
 	enable_rpm_wakeref_asserts(dev_priv);
@@ -1851,7 +1847,7 @@ static int i915_drm_resume_early(struct drm_device *dev)
 	else
 		intel_display_set_init_power(dev_priv, true);
 
-	i915_gem_sanitize(dev_priv);
+	intel_engines_sanitize(dev_priv);
 
 	enable_rpm_wakeref_asserts(dev_priv);
 
@@ -2081,6 +2077,22 @@ out:
 	return ret;
 }
 
+static int i915_pm_prepare(struct device *kdev)
+{
+	struct pci_dev *pdev = to_pci_dev(kdev);
+	struct drm_device *dev = pci_get_drvdata(pdev);
+
+	if (!dev) {
+		dev_err(kdev, "DRM not initialized, aborting suspend.\n");
+		return -ENODEV;
+	}
+
+	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
+		return 0;
+
+	return i915_drm_prepare(dev);
+}
+
 static int i915_pm_suspend(struct device *kdev)
 {
 	struct pci_dev *pdev = to_pci_dev(kdev);
@@ -2731,6 +2743,7 @@ const struct dev_pm_ops i915_pm_ops = {
 	 * S0ix (via system suspend) and S3 event handlers [PMSG_SUSPEND,
 	 * PMSG_RESUME]
 	 */
+	.prepare = i915_pm_prepare,
 	.suspend = i915_pm_suspend,
 	.suspend_late = i915_pm_suspend_late,
 	.resume_early = i915_pm_resume_early,
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 71e1aa54f774..4aca5344863d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -40,6 +40,7 @@
 #include <linux/hash.h>
 #include <linux/intel-iommu.h>
 #include <linux/kref.h>
+#include <linux/mm_types.h>
 #include <linux/perf_event.h>
 #include <linux/pm_qos.h>
 #include <linux/reservation.h>
@@ -85,8 +86,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20180514"
-#define DRIVER_TIMESTAMP	1526300884
+#define DRIVER_DATE		"20180719"
+#define DRIVER_TIMESTAMP	1532015279
 
 /* Use I915_STATE_WARN(x) and I915_STATE_WARN_ON() (rather than WARN() and
  * WARN_ON()) for hw state sanity checks to check for unexpected conditions
@@ -107,13 +108,24 @@
 	I915_STATE_WARN((x), "%s", "WARN_ON(" __stringify(x) ")")
 
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
+
 bool __i915_inject_load_failure(const char *func, int line);
 #define i915_inject_load_failure() \
 	__i915_inject_load_failure(__func__, __LINE__)
+
+bool i915_error_injected(void);
+
 #else
+
 #define i915_inject_load_failure() false
+#define i915_error_injected() false
+
 #endif
 
+#define i915_load_error(i915, fmt, ...)					 \
+	__i915_printk(i915, i915_error_injected() ? KERN_DEBUG : KERN_ERR, \
+		      fmt, ##__VA_ARGS__)
+
 typedef struct {
 	uint32_t val;
 } uint_fixed_16_16_t;
@@ -287,7 +299,6 @@ struct i915_hotplug {
 	u32 event_bits;
 	struct delayed_work reenable_work;
 
-	struct intel_digital_port *irq_port[I915_MAX_PORTS];
 	u32 long_port_mask;
 	u32 short_port_mask;
 	struct work_struct dig_port_work;
@@ -500,6 +511,7 @@ struct intel_fbc {
 
 	bool enabled;
 	bool active;
+	bool flip_pending;
 
 	bool underrun_detected;
 	struct work_struct underrun_work;
@@ -567,12 +579,6 @@ struct intel_fbc {
 		unsigned int gen9_wa_cfb_stride;
 	} params;
 
-	struct intel_fbc_work {
-		bool scheduled;
-		u64 scheduled_vblank;
-		struct work_struct work;
-	} work;
-
 	const char *no_fbc_reason;
 };
 
@@ -608,26 +614,17 @@ struct i915_psr {
 	bool sink_support;
 	struct intel_dp *enabled;
 	bool active;
-	struct delayed_work work;
+	struct work_struct work;
 	unsigned busy_frontbuffer_bits;
 	bool sink_psr2_support;
 	bool link_standby;
 	bool colorimetry_support;
 	bool alpm;
-	bool has_hw_tracking;
 	bool psr2_enabled;
 	u8 sink_sync_latency;
 	bool debug;
 	ktime_t last_entry_attempt;
 	ktime_t last_exit;
-
-	void (*enable_source)(struct intel_dp *,
-			      const struct intel_crtc_state *);
-	void (*disable_source)(struct intel_dp *,
-			       const struct intel_crtc_state *);
-	void (*enable_sink)(struct intel_dp *);
-	void (*activate)(struct intel_dp *);
-	void (*setup_vsc)(struct intel_dp *, const struct intel_crtc_state *);
 };
 
 enum intel_pch {
@@ -639,7 +636,7 @@ enum intel_pch {
 	PCH_KBP,        /* Kaby Lake PCH */
 	PCH_CNP,        /* Cannon Lake PCH */
 	PCH_ICP,	/* Ice Lake PCH */
-	PCH_NOP,
+	PCH_NOP,	/* PCH without south display */
 };
 
 enum intel_sbi_destination {
@@ -782,11 +779,17 @@ struct intel_rps {
 	u8 rp0_freq;		/* Non-overclocked max frequency. */
 	u16 gpll_ref_freq;	/* vlv/chv GPLL reference frequency */
 
-	u8 up_threshold; /* Current %busy required to uplock */
-	u8 down_threshold; /* Current %busy required to downclock */
-
 	int last_adj;
-	enum { LOW_POWER, BETWEEN, HIGH_POWER } power;
+
+	struct {
+		struct mutex mutex;
+
+		enum { LOW_POWER, BETWEEN, HIGH_POWER } mode;
+		unsigned int interactive;
+
+		u8 up_threshold; /* Current %busy required to uplock */
+		u8 down_threshold; /* Current %busy required to downclock */
+	} power;
 
 	bool enabled;
 	atomic_t num_waiters;
@@ -955,7 +958,7 @@ struct i915_gem_mm {
 	/**
 	 * Small stash of WC pages
 	 */
-	struct pagevec wc_stash;
+	struct pagestash wc_stash;
 
 	/**
 	 * tmpfs instance used for shmem backed objects
@@ -1003,16 +1006,13 @@ struct i915_gem_mm {
 #define I915_ENGINE_DEAD_TIMEOUT  (4 * HZ)  /* Seqno, head and subunits dead */
 #define I915_SEQNO_DEAD_TIMEOUT   (12 * HZ) /* Seqno dead with active head */
 
-enum modeset_restore {
-	MODESET_ON_LID_OPEN,
-	MODESET_DONE,
-	MODESET_SUSPENDED,
-};
+#define I915_ENGINE_WEDGED_TIMEOUT  (60 * HZ)  /* Reset but no recovery? */
 
 #define DP_AUX_A 0x40
 #define DP_AUX_B 0x10
 #define DP_AUX_C 0x20
 #define DP_AUX_D 0x30
+#define DP_AUX_E 0x50
 #define DP_AUX_F 0x60
 
 #define DDC_PIN_B  0x05
@@ -1057,9 +1057,9 @@ struct intel_vbt_data {
 	/* Feature bits */
 	unsigned int int_tv_support:1;
 	unsigned int lvds_dither:1;
-	unsigned int lvds_vbt:1;
 	unsigned int int_crt_support:1;
 	unsigned int lvds_use_ssc:1;
+	unsigned int int_lvds_support:1;
 	unsigned int display_clock_mode:1;
 	unsigned int fdi_rx_polarity_inverted:1;
 	unsigned int panel_type:4;
@@ -1075,7 +1075,6 @@ struct intel_vbt_data {
 		int vswing;
 		bool low_vswing;
 		bool initialized;
-		bool support;
 		int bpp;
 		struct edp_power_seq pps;
 	} edp;
@@ -1086,8 +1085,8 @@ struct intel_vbt_data {
 		bool require_aux_wakeup;
 		int idle_frames;
 		enum psr_lines_to_wait lines_to_wait;
-		int tp1_wakeup_time;
-		int tp2_tp3_wakeup_time;
+		int tp1_wakeup_time_us;
+		int tp2_tp3_wakeup_time_us;
 	} psr;
 
 	struct {
@@ -1272,20 +1271,11 @@ enum intel_pipe_crc_source {
 	INTEL_PIPE_CRC_SOURCE_MAX,
 };
 
-struct intel_pipe_crc_entry {
-	uint32_t frame;
-	uint32_t crc[5];
-};
-
 #define INTEL_PIPE_CRC_ENTRIES_NR	128
 struct intel_pipe_crc {
 	spinlock_t lock;
-	bool opened;		/* exclusive access to the result file */
-	struct intel_pipe_crc_entry *entries;
-	enum intel_pipe_crc_source source;
-	int head, tail;
-	wait_queue_head_t wq;
 	int skipped;
+	enum intel_pipe_crc_source source;
 };
 
 struct i915_frontbuffer_tracking {
@@ -1300,7 +1290,7 @@ struct i915_frontbuffer_tracking {
 };
 
 struct i915_wa_reg {
-	i915_reg_t addr;
+	u32 addr;
 	u32 value;
 	/* bitmask representing WA bits */
 	u32 mask;
@@ -1740,12 +1730,9 @@ struct drm_i915_private {
 
 	unsigned long quirks;
 
-	enum modeset_restore modeset_restore;
-	struct mutex modeset_restore_lock;
 	struct drm_atomic_state *modeset_restore_state;
 	struct drm_modeset_acquire_ctx reset_ctx;
 
-	struct list_head vm_list; /* Global list of all address spaces */
 	struct i915_ggtt ggtt; /* VM representing the global address space */
 
 	struct i915_gem_mm mm;
@@ -1851,6 +1838,7 @@ struct drm_i915_private {
 		 */
 		struct ida hw_ida;
 #define MAX_CONTEXT_HW_ID (1<<21) /* exclusive */
+#define MAX_GUC_CONTEXT_HW_ID (1 << 20) /* exclusive */
 #define GEN11_MAX_CONTEXT_HW_ID (1<<11) /* exclusive */
 	} contexts;
 
@@ -1958,7 +1946,9 @@ struct drm_i915_private {
 			 */
 			struct i915_perf_stream *exclusive_stream;
 
+			struct intel_context *pinned_ctx;
 			u32 specific_ctx_id;
+			u32 specific_ctx_id_mask;
 
 			struct hrtimer poll_check_timer;
 			wait_queue_head_t poll_wq;
@@ -2311,6 +2301,7 @@ intel_info(const struct drm_i915_private *dev_priv)
 }
 
 #define INTEL_INFO(dev_priv)	intel_info((dev_priv))
+#define DRIVER_CAPS(dev_priv)	(&(dev_priv)->caps)
 
 #define INTEL_GEN(dev_priv)	((dev_priv)->info.gen)
 #define INTEL_DEVID(dev_priv)	((dev_priv)->info.device_id)
@@ -2563,17 +2554,10 @@ intel_info(const struct drm_i915_private *dev_priv)
 	(IS_CANNONLAKE(dev_priv) || \
 	 IS_SKL_GT3(dev_priv) || IS_SKL_GT4(dev_priv))
 
-/*
- * dp aux and gmbus irq on gen4 seems to be able to generate legacy interrupts
- * even when in MSI mode. This results in spurious interrupt warnings if the
- * legacy irq no. is shared with another device. The kernel then disables that
- * interrupt source and so prevents the other device from working properly.
- *
- * Since we don't enable MSI anymore on gen4, we can always use GMBUS/AUX
- * interrupts.
- */
-#define HAS_AUX_IRQ(dev_priv)   true
 #define HAS_GMBUS_IRQ(dev_priv) (INTEL_GEN(dev_priv) >= 4)
+#define HAS_GMBUS_BURST_READ(dev_priv) (INTEL_GEN(dev_priv) >= 10 || \
+					IS_GEMINILAKE(dev_priv) || \
+					IS_KABYLAKE(dev_priv))
 
 /* With the 945 and later, Y tiling got adjusted so that it was 32 128-byte
  * rows, which changed the alignment requirements and fence programming.
@@ -2748,14 +2732,14 @@ int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool on);
 int intel_engines_init_mmio(struct drm_i915_private *dev_priv);
 int intel_engines_init(struct drm_i915_private *dev_priv);
 
+u32 intel_calculate_mcr_s_ss_select(struct drm_i915_private *dev_priv);
+
 /* intel_hotplug.c */
 void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 			   u32 pin_mask, u32 long_mask);
 void intel_hpd_init(struct drm_i915_private *dev_priv);
 void intel_hpd_init_work(struct drm_i915_private *dev_priv);
 void intel_hpd_cancel_work(struct drm_i915_private *dev_priv);
-enum port intel_hpd_pin_to_port(struct drm_i915_private *dev_priv,
-				enum hpd_pin pin);
 enum hpd_pin intel_hpd_pin_default(struct drm_i915_private *dev_priv,
 				   enum port port);
 bool intel_hpd_disable(struct drm_i915_private *dev_priv, enum hpd_pin pin);
@@ -3102,9 +3086,6 @@ i915_gem_obj_finish_shmem_access(struct drm_i915_gem_object *obj)
 }
 
 int __must_check i915_mutex_lock_interruptible(struct drm_device *dev);
-void i915_vma_move_to_active(struct i915_vma *vma,
-			     struct i915_request *rq,
-			     unsigned int flags);
 int i915_gem_dumb_create(struct drm_file *file_priv,
 			 struct drm_device *dev,
 			 struct drm_mode_create_dumb *args);
@@ -3169,12 +3150,14 @@ void i915_gem_init_mmio(struct drm_i915_private *i915);
 int __must_check i915_gem_init(struct drm_i915_private *dev_priv);
 int __must_check i915_gem_init_hw(struct drm_i915_private *dev_priv);
 void i915_gem_init_swizzling(struct drm_i915_private *dev_priv);
+void i915_gem_fini(struct drm_i915_private *dev_priv);
 void i915_gem_cleanup_engines(struct drm_i915_private *dev_priv);
 int i915_gem_wait_for_idle(struct drm_i915_private *dev_priv,
-			   unsigned int flags);
+			   unsigned int flags, long timeout);
 int __must_check i915_gem_suspend(struct drm_i915_private *dev_priv);
+void i915_gem_suspend_late(struct drm_i915_private *dev_priv);
 void i915_gem_resume(struct drm_i915_private *dev_priv);
-int i915_gem_fault(struct vm_fault *vmf);
+vm_fault_t i915_gem_fault(struct vm_fault *vmf);
 int i915_gem_object_wait(struct drm_i915_gem_object *obj,
 			 unsigned int flags,
 			 long timeout,
@@ -3213,7 +3196,7 @@ struct dma_buf *i915_gem_prime_export(struct drm_device *dev,
 static inline struct i915_hw_ppgtt *
 i915_vm_to_ppgtt(struct i915_address_space *vm)
 {
-	return container_of(vm, struct i915_hw_ppgtt, base);
+	return container_of(vm, struct i915_hw_ppgtt, vm);
 }
 
 /* i915_gem_fence_reg.c */
@@ -3320,7 +3303,7 @@ unsigned long i915_gem_shrink(struct drm_i915_private *i915,
 unsigned long i915_gem_shrink_all(struct drm_i915_private *i915);
 void i915_gem_shrinker_register(struct drm_i915_private *i915);
 void i915_gem_shrinker_unregister(struct drm_i915_private *i915);
-
+void i915_gem_shrinker_taints_mutex(struct mutex *mutex);
 
 /* i915_gem_tiling.c */
 static inline bool i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_object *obj)
@@ -3445,6 +3428,8 @@ extern void i915_redisable_vga_power_on(struct drm_i915_private *dev_priv);
 extern bool ironlake_set_drps(struct drm_i915_private *dev_priv, u8 val);
 extern void intel_init_pch_refclk(struct drm_i915_private *dev_priv);
 extern int intel_set_rps(struct drm_i915_private *dev_priv, u8 val);
+extern void intel_rps_mark_interactive(struct drm_i915_private *i915,
+				       bool interactive);
 extern bool intel_set_memory_cxsr(struct drm_i915_private *dev_priv,
 				  bool enable);
 
@@ -3678,14 +3663,6 @@ static inline unsigned long nsecs_to_jiffies_timeout(const u64 n)
         return min_t(u64, MAX_JIFFY_OFFSET, nsecs_to_jiffies64(n) + 1);
 }
 
-static inline unsigned long
-timespec_to_jiffies_timeout(const struct timespec *value)
-{
-	unsigned long j = timespec_to_jiffies(value);
-
-	return min_t(unsigned long, MAX_JIFFY_OFFSET, j + 1);
-}
-
 /*
  * If you need to wait X milliseconds between events A and B, but event B
  * doesn't happen exactly after event A, you record the timestamp (jiffies) of
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 17c5097721e8..fcc73a6ab503 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -65,7 +65,7 @@ insert_mappable_node(struct i915_ggtt *ggtt,
                      struct drm_mm_node *node, u32 size)
 {
 	memset(node, 0, sizeof(*node));
-	return drm_mm_insert_node_in_range(&ggtt->base.mm, node,
+	return drm_mm_insert_node_in_range(&ggtt->vm.mm, node,
 					   size, 0, I915_COLOR_UNEVICTABLE,
 					   0, ggtt->mappable_end,
 					   DRM_MM_INSERT_LOW);
@@ -139,6 +139,8 @@ int i915_mutex_lock_interruptible(struct drm_device *dev)
 
 static u32 __i915_gem_park(struct drm_i915_private *i915)
 {
+	GEM_TRACE("\n");
+
 	lockdep_assert_held(&i915->drm.struct_mutex);
 	GEM_BUG_ON(i915->gt.active_requests);
 	GEM_BUG_ON(!list_empty(&i915->gt.active_rings));
@@ -181,6 +183,8 @@ static u32 __i915_gem_park(struct drm_i915_private *i915)
 
 void i915_gem_park(struct drm_i915_private *i915)
 {
+	GEM_TRACE("\n");
+
 	lockdep_assert_held(&i915->drm.struct_mutex);
 	GEM_BUG_ON(i915->gt.active_requests);
 
@@ -193,6 +197,8 @@ void i915_gem_park(struct drm_i915_private *i915)
 
 void i915_gem_unpark(struct drm_i915_private *i915)
 {
+	GEM_TRACE("\n");
+
 	lockdep_assert_held(&i915->drm.struct_mutex);
 	GEM_BUG_ON(!i915->gt.active_requests);
 
@@ -243,17 +249,17 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
 	struct i915_vma *vma;
 	u64 pinned;
 
-	pinned = ggtt->base.reserved;
+	pinned = ggtt->vm.reserved;
 	mutex_lock(&dev->struct_mutex);
-	list_for_each_entry(vma, &ggtt->base.active_list, vm_link)
+	list_for_each_entry(vma, &ggtt->vm.active_list, vm_link)
 		if (i915_vma_is_pinned(vma))
 			pinned += vma->node.size;
-	list_for_each_entry(vma, &ggtt->base.inactive_list, vm_link)
+	list_for_each_entry(vma, &ggtt->vm.inactive_list, vm_link)
 		if (i915_vma_is_pinned(vma))
 			pinned += vma->node.size;
 	mutex_unlock(&dev->struct_mutex);
 
-	args->aper_size = ggtt->base.total;
+	args->aper_size = ggtt->vm.total;
 	args->aper_available_size = args->aper_size - pinned;
 
 	return 0;
@@ -796,7 +802,7 @@ void i915_gem_flush_ggtt_writes(struct drm_i915_private *dev_priv)
 	 * that was!).
 	 */
 
-	wmb();
+	i915_gem_chipset_flush(dev_priv);
 
 	intel_runtime_pm_get(dev_priv);
 	spin_lock_irq(&dev_priv->uncore.lock);
@@ -831,6 +837,10 @@ flush_write_domain(struct drm_i915_gem_object *obj, unsigned int flush_domains)
 		}
 		break;
 
+	case I915_GEM_DOMAIN_WC:
+		wmb();
+		break;
+
 	case I915_GEM_DOMAIN_CPU:
 		i915_gem_clflush_object(obj, I915_CLFLUSH_SYNC);
 		break;
@@ -1217,9 +1227,9 @@ i915_gem_gtt_pread(struct drm_i915_gem_object *obj,
 		page_length = remain < page_length ? remain : page_length;
 		if (node.allocated) {
 			wmb();
-			ggtt->base.insert_page(&ggtt->base,
-					       i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT),
-					       node.start, I915_CACHE_NONE, 0);
+			ggtt->vm.insert_page(&ggtt->vm,
+					     i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT),
+					     node.start, I915_CACHE_NONE, 0);
 			wmb();
 		} else {
 			page_base += offset & PAGE_MASK;
@@ -1240,8 +1250,7 @@ i915_gem_gtt_pread(struct drm_i915_gem_object *obj,
 out_unpin:
 	if (node.allocated) {
 		wmb();
-		ggtt->base.clear_range(&ggtt->base,
-				       node.start, node.size);
+		ggtt->vm.clear_range(&ggtt->vm, node.start, node.size);
 		remove_mappable_node(&node);
 	} else {
 		i915_vma_unpin(vma);
@@ -1420,9 +1429,9 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 		page_length = remain < page_length ? remain : page_length;
 		if (node.allocated) {
 			wmb(); /* flush the write before we modify the GGTT */
-			ggtt->base.insert_page(&ggtt->base,
-					       i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT),
-					       node.start, I915_CACHE_NONE, 0);
+			ggtt->vm.insert_page(&ggtt->vm,
+					     i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT),
+					     node.start, I915_CACHE_NONE, 0);
 			wmb(); /* flush modifications to the GGTT (insert_page) */
 		} else {
 			page_base += offset & PAGE_MASK;
@@ -1449,8 +1458,7 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 out_unpin:
 	if (node.allocated) {
 		wmb();
-		ggtt->base.clear_range(&ggtt->base,
-				       node.start, node.size);
+		ggtt->vm.clear_range(&ggtt->vm, node.start, node.size);
 		remove_mappable_node(&node);
 	} else {
 		i915_vma_unpin(vma);
@@ -1619,6 +1627,12 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 		goto err;
 	}
 
+	/* Writes not allowed into this read-only object */
+	if (i915_gem_object_is_readonly(obj)) {
+		ret = -EINVAL;
+		goto err;
+	}
+
 	trace_i915_gem_object_pwrite(obj, args->offset, args->size);
 
 	ret = -ENODEV;
@@ -1991,9 +2005,9 @@ compute_partial_view(struct drm_i915_gem_object *obj,
  * The current feature set supported by i915_gem_fault() and thus GTT mmaps
  * is exposed via I915_PARAM_MMAP_GTT_VERSION (see i915_gem_mmap_gtt_version).
  */
-int i915_gem_fault(struct vm_fault *vmf)
+vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 {
-#define MIN_CHUNK_PAGES ((1 << 20) >> PAGE_SHIFT) /* 1 MiB */
+#define MIN_CHUNK_PAGES (SZ_1M >> PAGE_SHIFT)
 	struct vm_area_struct *area = vmf->vma;
 	struct drm_i915_gem_object *obj = to_intel_bo(area->vm_private_data);
 	struct drm_device *dev = obj->base.dev;
@@ -2004,6 +2018,10 @@ int i915_gem_fault(struct vm_fault *vmf)
 	pgoff_t page_offset;
 	int ret;
 
+	/* Sanity check that we allow writing into this object */
+	if (i915_gem_object_is_readonly(obj) && write)
+		return VM_FAULT_SIGBUS;
+
 	/* We don't use vmf->pgoff since that has the fake offset */
 	page_offset = (vmf->address - area->vm_start) >> PAGE_SHIFT;
 
@@ -2114,10 +2132,9 @@ err:
 		 * fail). But any other -EIO isn't ours (e.g. swap in failure)
 		 * and so needs to be reported.
 		 */
-		if (!i915_terminally_wedged(&dev_priv->gpu_error)) {
-			ret = VM_FAULT_SIGBUS;
-			break;
-		}
+		if (!i915_terminally_wedged(&dev_priv->gpu_error))
+			return VM_FAULT_SIGBUS;
+		/* else: fall through */
 	case -EAGAIN:
 		/*
 		 * EAGAIN means the gpu is hung and we'll wait for the error
@@ -2132,21 +2149,16 @@ err:
 		 * EBUSY is ok: this just means that another thread
 		 * already did the job.
 		 */
-		ret = VM_FAULT_NOPAGE;
-		break;
+		return VM_FAULT_NOPAGE;
 	case -ENOMEM:
-		ret = VM_FAULT_OOM;
-		break;
+		return VM_FAULT_OOM;
 	case -ENOSPC:
 	case -EFAULT:
-		ret = VM_FAULT_SIGBUS;
-		break;
+		return VM_FAULT_SIGBUS;
 	default:
 		WARN_ONCE(ret, "unhandled error in i915_gem_fault: %i\n", ret);
-		ret = VM_FAULT_SIGBUS;
-		break;
+		return VM_FAULT_SIGBUS;
 	}
-	return ret;
 }
 
 static void __i915_gem_object_release_mmap(struct drm_i915_gem_object *obj)
@@ -2265,7 +2277,9 @@ static int i915_gem_object_create_mmap_offset(struct drm_i915_gem_object *obj)
 
 	/* Attempt to reap some mmap space from dead objects */
 	do {
-		err = i915_gem_wait_for_idle(dev_priv, I915_WAIT_INTERRUPTIBLE);
+		err = i915_gem_wait_for_idle(dev_priv,
+					     I915_WAIT_INTERRUPTIBLE,
+					     MAX_SCHEDULE_TIMEOUT);
 		if (err)
 			break;
 
@@ -2410,29 +2424,15 @@ static void __i915_gem_object_reset_page_iter(struct drm_i915_gem_object *obj)
 	rcu_read_unlock();
 }
 
-void __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
-				 enum i915_mm_subclass subclass)
+static struct sg_table *
+__i915_gem_object_unset_pages(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct sg_table *pages;
 
-	if (i915_gem_object_has_pinned_pages(obj))
-		return;
-
-	GEM_BUG_ON(obj->bind_count);
-	if (!i915_gem_object_has_pages(obj))
-		return;
-
-	/* May be called by shrinker from within get_pages() (on another bo) */
-	mutex_lock_nested(&obj->mm.lock, subclass);
-	if (unlikely(atomic_read(&obj->mm.pages_pin_count)))
-		goto unlock;
-
-	/* ->put_pages might need to allocate memory for the bit17 swizzle
-	 * array, hence protect them from being reaped by removing them from gtt
-	 * lists early. */
 	pages = fetch_and_zero(&obj->mm.pages);
-	GEM_BUG_ON(!pages);
+	if (!pages)
+		return NULL;
 
 	spin_lock(&i915->mm.obj_lock);
 	list_del(&obj->mm.link);
@@ -2451,12 +2451,37 @@ void __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
 	}
 
 	__i915_gem_object_reset_page_iter(obj);
+	obj->mm.page_sizes.phys = obj->mm.page_sizes.sg = 0;
+
+	return pages;
+}
+
+void __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
+				 enum i915_mm_subclass subclass)
+{
+	struct sg_table *pages;
 
+	if (i915_gem_object_has_pinned_pages(obj))
+		return;
+
+	GEM_BUG_ON(obj->bind_count);
+	if (!i915_gem_object_has_pages(obj))
+		return;
+
+	/* May be called by shrinker from within get_pages() (on another bo) */
+	mutex_lock_nested(&obj->mm.lock, subclass);
+	if (unlikely(atomic_read(&obj->mm.pages_pin_count)))
+		goto unlock;
+
+	/*
+	 * ->put_pages might need to allocate memory for the bit17 swizzle
+	 * array, hence protect them from being reaped by removing them from gtt
+	 * lists early.
+	 */
+	pages = __i915_gem_object_unset_pages(obj);
 	if (!IS_ERR(pages))
 		obj->ops->put_pages(obj, pages);
 
-	obj->mm.page_sizes.phys = obj->mm.page_sizes.sg = 0;
-
 unlock:
 	mutex_unlock(&obj->mm.lock);
 }
@@ -2974,16 +2999,16 @@ static void i915_gem_context_mark_guilty(struct i915_gem_context *ctx)
 	score = atomic_add_return(CONTEXT_SCORE_GUILTY, &ctx->ban_score);
 	banned = score >= CONTEXT_SCORE_BAN_THRESHOLD;
 
-	DRM_DEBUG_DRIVER("context %s: guilty %d, score %u, ban %s\n",
-			 ctx->name, atomic_read(&ctx->guilty_count),
-			 score, yesno(banned && bannable));
-
 	/* Cool contexts don't accumulate client ban score */
 	if (!bannable)
 		return;
 
-	if (banned)
+	if (banned) {
+		DRM_DEBUG_DRIVER("context %s: guilty %d, score %u, banned\n",
+				 ctx->name, atomic_read(&ctx->guilty_count),
+				 score);
 		i915_gem_context_set_banned(ctx);
+	}
 
 	if (!IS_ERR_OR_NULL(ctx->file_priv))
 		i915_gem_client_mark_guilty(ctx->file_priv, ctx);
@@ -3031,7 +3056,7 @@ i915_gem_find_active_request(struct intel_engine_cs *engine)
 struct i915_request *
 i915_gem_reset_prepare_engine(struct intel_engine_cs *engine)
 {
-	struct i915_request *request = NULL;
+	struct i915_request *request;
 
 	/*
 	 * During the reset sequence, we must prevent the engine from
@@ -3042,52 +3067,7 @@ i915_gem_reset_prepare_engine(struct intel_engine_cs *engine)
 	 */
 	intel_uncore_forcewake_get(engine->i915, FORCEWAKE_ALL);
 
-	/*
-	 * Prevent the signaler thread from updating the request
-	 * state (by calling dma_fence_signal) as we are processing
-	 * the reset. The write from the GPU of the seqno is
-	 * asynchronous and the signaler thread may see a different
-	 * value to us and declare the request complete, even though
-	 * the reset routine have picked that request as the active
-	 * (incomplete) request. This conflict is not handled
-	 * gracefully!
-	 */
-	kthread_park(engine->breadcrumbs.signaler);
-
-	/*
-	 * Prevent request submission to the hardware until we have
-	 * completed the reset in i915_gem_reset_finish(). If a request
-	 * is completed by one engine, it may then queue a request
-	 * to a second via its execlists->tasklet *just* as we are
-	 * calling engine->init_hw() and also writing the ELSP.
-	 * Turning off the execlists->tasklet until the reset is over
-	 * prevents the race.
-	 *
-	 * Note that this needs to be a single atomic operation on the
-	 * tasklet (flush existing tasks, prevent new tasks) to prevent
-	 * a race between reset and set-wedged. It is not, so we do the best
-	 * we can atm and make sure we don't lock the machine up in the more
-	 * common case of recursively being called from set-wedged from inside
-	 * i915_reset.
-	 */
-	if (!atomic_read(&engine->execlists.tasklet.count))
-		tasklet_kill(&engine->execlists.tasklet);
-	tasklet_disable(&engine->execlists.tasklet);
-
-	/*
-	 * We're using worker to queue preemption requests from the tasklet in
-	 * GuC submission mode.
-	 * Even though tasklet was disabled, we may still have a worker queued.
-	 * Let's make sure that all workers scheduled before disabling the
-	 * tasklet are completed before continuing with the reset.
-	 */
-	if (engine->i915->guc.preempt_wq)
-		flush_workqueue(engine->i915->guc.preempt_wq);
-
-	if (engine->irq_seqno_barrier)
-		engine->irq_seqno_barrier(engine);
-
-	request = i915_gem_find_active_request(engine);
+	request = engine->reset.prepare(engine);
 	if (request && request->fence.error == -EIO)
 		request = ERR_PTR(-EIO); /* Previous reset failed! */
 
@@ -3117,43 +3097,24 @@ int i915_gem_reset_prepare(struct drm_i915_private *dev_priv)
 	return err;
 }
 
-static void skip_request(struct i915_request *request)
-{
-	void *vaddr = request->ring->vaddr;
-	u32 head;
-
-	/* As this request likely depends on state from the lost
-	 * context, clear out all the user operations leaving the
-	 * breadcrumb at the end (so we get the fence notifications).
-	 */
-	head = request->head;
-	if (request->postfix < head) {
-		memset(vaddr + head, 0, request->ring->size - head);
-		head = 0;
-	}
-	memset(vaddr + head, 0, request->postfix - head);
-
-	dma_fence_set_error(&request->fence, -EIO);
-}
-
 static void engine_skip_context(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
-	struct i915_gem_context *hung_ctx = request->ctx;
+	struct i915_gem_context *hung_ctx = request->gem_context;
 	struct i915_timeline *timeline = request->timeline;
 	unsigned long flags;
 
 	GEM_BUG_ON(timeline == &engine->timeline);
 
 	spin_lock_irqsave(&engine->timeline.lock, flags);
-	spin_lock_nested(&timeline->lock, SINGLE_DEPTH_NESTING);
+	spin_lock(&timeline->lock);
 
 	list_for_each_entry_continue(request, &engine->timeline.requests, link)
-		if (request->ctx == hung_ctx)
-			skip_request(request);
+		if (request->gem_context == hung_ctx)
+			i915_request_skip(request, -EIO);
 
 	list_for_each_entry(request, &timeline->requests, link)
-		skip_request(request);
+		i915_request_skip(request, -EIO);
 
 	spin_unlock(&timeline->lock);
 	spin_unlock_irqrestore(&engine->timeline.lock, flags);
@@ -3195,11 +3156,11 @@ i915_gem_reset_request(struct intel_engine_cs *engine,
 	}
 
 	if (stalled) {
-		i915_gem_context_mark_guilty(request->ctx);
-		skip_request(request);
+		i915_gem_context_mark_guilty(request->gem_context);
+		i915_request_skip(request, -EIO);
 
 		/* If this context is now banned, skip all pending requests. */
-		if (i915_gem_context_is_banned(request->ctx))
+		if (i915_gem_context_is_banned(request->gem_context))
 			engine_skip_context(request);
 	} else {
 		/*
@@ -3209,15 +3170,17 @@ i915_gem_reset_request(struct intel_engine_cs *engine,
 		 */
 		request = i915_gem_find_active_request(engine);
 		if (request) {
-			i915_gem_context_mark_innocent(request->ctx);
+			unsigned long flags;
+
+			i915_gem_context_mark_innocent(request->gem_context);
 			dma_fence_set_error(&request->fence, -EAGAIN);
 
 			/* Rewind the engine to replay the incomplete rq */
-			spin_lock_irq(&engine->timeline.lock);
+			spin_lock_irqsave(&engine->timeline.lock, flags);
 			request = list_prev_entry(request, link);
 			if (&request->link == &engine->timeline.requests)
 				request = NULL;
-			spin_unlock_irq(&engine->timeline.lock);
+			spin_unlock_irqrestore(&engine->timeline.lock, flags);
 		}
 	}
 
@@ -3238,13 +3201,8 @@ void i915_gem_reset_engine(struct intel_engine_cs *engine,
 	if (request)
 		request = i915_gem_reset_request(engine, request, stalled);
 
-	if (request) {
-		DRM_DEBUG_DRIVER("resetting %s to restart from tail of request 0x%x\n",
-				 engine->name, request->global_seqno);
-	}
-
 	/* Setup the CS to resume from the breadcrumb of the hung request */
-	engine->reset_hw(engine, request);
+	engine->reset.reset(engine, request);
 }
 
 void i915_gem_reset(struct drm_i915_private *dev_priv,
@@ -3258,14 +3216,14 @@ void i915_gem_reset(struct drm_i915_private *dev_priv,
 	i915_retire_requests(dev_priv);
 
 	for_each_engine(engine, dev_priv, id) {
-		struct i915_gem_context *ctx;
+		struct intel_context *ce;
 
 		i915_gem_reset_engine(engine,
 				      engine->hangcheck.active_request,
 				      stalled_mask & ENGINE_MASK(id));
-		ctx = fetch_and_zero(&engine->last_retired_context);
-		if (ctx)
-			intel_context_unpin(ctx, engine);
+		ce = fetch_and_zero(&engine->last_retired_context);
+		if (ce)
+			intel_context_unpin(ce);
 
 		/*
 		 * Ostensibily, we always want a context loaded for powersaving,
@@ -3283,7 +3241,7 @@ void i915_gem_reset(struct drm_i915_private *dev_priv,
 			rq = i915_request_alloc(engine,
 						dev_priv->kernel_context);
 			if (!IS_ERR(rq))
-				__i915_request_add(rq, false);
+				i915_request_add(rq);
 		}
 	}
 
@@ -3292,8 +3250,7 @@ void i915_gem_reset(struct drm_i915_private *dev_priv,
 
 void i915_gem_reset_finish_engine(struct intel_engine_cs *engine)
 {
-	tasklet_enable(&engine->execlists.tasklet);
-	kthread_unpark(engine->breadcrumbs.signaler);
+	engine->reset.finish(engine);
 
 	intel_uncore_forcewake_put(engine->i915, FORCEWAKE_ALL);
 }
@@ -3571,6 +3528,22 @@ new_requests_since_last_retire(const struct drm_i915_private *i915)
 		work_pending(&i915->gt.idle_work.work));
 }
 
+static void assert_kernel_context_is_current(struct drm_i915_private *i915)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return;
+
+	GEM_BUG_ON(i915->gt.active_requests);
+	for_each_engine(engine, i915, id) {
+		GEM_BUG_ON(__i915_gem_active_peek(&engine->timeline.last_request));
+		GEM_BUG_ON(engine->last_retired_context !=
+			   to_intel_context(i915->kernel_context, engine));
+	}
+}
+
 static void
 i915_gem_idle_work_handler(struct work_struct *work)
 {
@@ -3582,6 +3555,24 @@ i915_gem_idle_work_handler(struct work_struct *work)
 	if (!READ_ONCE(dev_priv->gt.awake))
 		return;
 
+	if (READ_ONCE(dev_priv->gt.active_requests))
+		return;
+
+	/*
+	 * Flush out the last user context, leaving only the pinned
+	 * kernel context resident. When we are idling on the kernel_context,
+	 * no more new requests (with a context switch) are emitted and we
+	 * can finally rest. A consequence is that the idle work handler is
+	 * always called at least twice before idling (and if the system is
+	 * idle that implies a round trip through the retire worker).
+	 */
+	mutex_lock(&dev_priv->drm.struct_mutex);
+	i915_gem_switch_to_kernel_context(dev_priv);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
+
+	GEM_TRACE("active_requests=%d (after switch-to-kernel-context)\n",
+		  READ_ONCE(dev_priv->gt.active_requests));
+
 	/*
 	 * Wait for last execlists context complete, but bail out in case a
 	 * new request is submitted. As we don't trust the hardware, we
@@ -3615,6 +3606,8 @@ i915_gem_idle_work_handler(struct work_struct *work)
 
 	epoch = __i915_gem_park(dev_priv);
 
+	assert_kernel_context_is_current(dev_priv);
+
 	rearm_hangcheck = false;
 out_unlock:
 	mutex_unlock(&dev_priv->drm.struct_mutex);
@@ -3761,9 +3754,31 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	return ret;
 }
 
-static int wait_for_timeline(struct i915_timeline *tl, unsigned int flags)
+static long wait_for_timeline(struct i915_timeline *tl,
+			      unsigned int flags, long timeout)
 {
-	return i915_gem_active_wait(&tl->last_request, flags);
+	struct i915_request *rq;
+
+	rq = i915_gem_active_get_unlocked(&tl->last_request);
+	if (!rq)
+		return timeout;
+
+	/*
+	 * "Race-to-idle".
+	 *
+	 * Switching to the kernel context is often used a synchronous
+	 * step prior to idling, e.g. in suspend for flushing all
+	 * current operations to memory before sleeping. These we
+	 * want to complete as quickly as possible to avoid prolonged
+	 * stalls, so allow the gpu to boost to maximum clocks.
+	 */
+	if (flags & I915_WAIT_FOR_IDLE_BOOST)
+		gen6_rps_boost(rq, NULL);
+
+	timeout = i915_request_wait(rq, flags, timeout);
+	i915_request_put(rq);
+
+	return timeout;
 }
 
 static int wait_for_engines(struct drm_i915_private *i915)
@@ -3779,8 +3794,13 @@ static int wait_for_engines(struct drm_i915_private *i915)
 	return 0;
 }
 
-int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags)
+int i915_gem_wait_for_idle(struct drm_i915_private *i915,
+			   unsigned int flags, long timeout)
 {
+	GEM_TRACE("flags=%x (%s), timeout=%ld%s\n",
+		  flags, flags & I915_WAIT_LOCKED ? "locked" : "unlocked",
+		  timeout, timeout == MAX_SCHEDULE_TIMEOUT ? " (forever)" : "");
+
 	/* If the device is asleep, we have no requests outstanding */
 	if (!READ_ONCE(i915->gt.awake))
 		return 0;
@@ -3792,26 +3812,31 @@ int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags)
 		lockdep_assert_held(&i915->drm.struct_mutex);
 
 		list_for_each_entry(tl, &i915->gt.timelines, link) {
-			err = wait_for_timeline(tl, flags);
-			if (err)
-				return err;
+			timeout = wait_for_timeline(tl, flags, timeout);
+			if (timeout < 0)
+				return timeout;
 		}
-		i915_retire_requests(i915);
 
-		return wait_for_engines(i915);
+		err = wait_for_engines(i915);
+		if (err)
+			return err;
+
+		i915_retire_requests(i915);
+		GEM_BUG_ON(i915->gt.active_requests);
 	} else {
 		struct intel_engine_cs *engine;
 		enum intel_engine_id id;
-		int err;
 
 		for_each_engine(engine, i915, id) {
-			err = wait_for_timeline(&engine->timeline, flags);
-			if (err)
-				return err;
-		}
+			struct i915_timeline *tl = &engine->timeline;
 
-		return 0;
+			timeout = wait_for_timeline(tl, flags, timeout);
+			if (timeout < 0)
+				return timeout;
+		}
 	}
+
+	return 0;
 }
 
 static void __i915_gem_object_flush_for_display(struct drm_i915_gem_object *obj)
@@ -4385,7 +4410,7 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 			 u64 flags)
 {
 	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
-	struct i915_address_space *vm = &dev_priv->ggtt.base;
+	struct i915_address_space *vm = &dev_priv->ggtt.vm;
 	struct i915_vma *vma;
 	int ret;
 
@@ -4973,25 +4998,25 @@ void __i915_gem_object_release_unless_active(struct drm_i915_gem_object *obj)
 		i915_gem_object_put(obj);
 }
 
-static void assert_kernel_context_is_current(struct drm_i915_private *i915)
+void i915_gem_sanitize(struct drm_i915_private *i915)
 {
-	struct i915_gem_context *kernel_context = i915->kernel_context;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
+	int err;
 
-	for_each_engine(engine, i915, id) {
-		GEM_BUG_ON(__i915_gem_active_peek(&engine->timeline.last_request));
-		GEM_BUG_ON(engine->last_retired_context != kernel_context);
-	}
-}
+	GEM_TRACE("\n");
 
-void i915_gem_sanitize(struct drm_i915_private *i915)
-{
-	if (i915_terminally_wedged(&i915->gpu_error)) {
-		mutex_lock(&i915->drm.struct_mutex);
+	mutex_lock(&i915->drm.struct_mutex);
+
+	intel_runtime_pm_get(i915);
+	intel_uncore_forcewake_get(i915, FORCEWAKE_ALL);
+
+	/*
+	 * As we have just resumed the machine and woken the device up from
+	 * deep PCI sleep (presumably D3_cold), assume the HW has been reset
+	 * back to defaults, recovering from whatever wedged state we left it
+	 * in and so worth trying to use the device once more.
+	 */
+	if (i915_terminally_wedged(&i915->gpu_error))
 		i915_gem_unset_wedged(i915);
-		mutex_unlock(&i915->drm.struct_mutex);
-	}
 
 	/*
 	 * If we inherit context state from the BIOS or earlier occupants
@@ -5001,60 +5026,94 @@ void i915_gem_sanitize(struct drm_i915_private *i915)
 	 * it may impact the display and we are uncertain about the stability
 	 * of the reset, so this could be applied to even earlier gen.
 	 */
+	err = -ENODEV;
 	if (INTEL_GEN(i915) >= 5 && intel_has_gpu_reset(i915))
-		WARN_ON(intel_gpu_reset(i915, ALL_ENGINES));
+		err = WARN_ON(intel_gpu_reset(i915, ALL_ENGINES));
+	if (!err)
+		intel_engines_sanitize(i915);
+
+	intel_uncore_forcewake_put(i915, FORCEWAKE_ALL);
+	intel_runtime_pm_put(i915);
+
+	i915_gem_contexts_lost(i915);
+	mutex_unlock(&i915->drm.struct_mutex);
 }
 
-int i915_gem_suspend(struct drm_i915_private *dev_priv)
+int i915_gem_suspend(struct drm_i915_private *i915)
 {
-	struct drm_device *dev = &dev_priv->drm;
 	int ret;
 
-	intel_runtime_pm_get(dev_priv);
-	intel_suspend_gt_powersave(dev_priv);
+	GEM_TRACE("\n");
 
-	mutex_lock(&dev->struct_mutex);
+	intel_runtime_pm_get(i915);
+	intel_suspend_gt_powersave(i915);
 
-	/* We have to flush all the executing contexts to main memory so
+	mutex_lock(&i915->drm.struct_mutex);
+
+	/*
+	 * We have to flush all the executing contexts to main memory so
 	 * that they can saved in the hibernation image. To ensure the last
 	 * context image is coherent, we have to switch away from it. That
-	 * leaves the dev_priv->kernel_context still active when
+	 * leaves the i915->kernel_context still active when
 	 * we actually suspend, and its image in memory may not match the GPU
 	 * state. Fortunately, the kernel_context is disposable and we do
 	 * not rely on its state.
 	 */
-	if (!i915_terminally_wedged(&dev_priv->gpu_error)) {
-		ret = i915_gem_switch_to_kernel_context(dev_priv);
+	if (!i915_terminally_wedged(&i915->gpu_error)) {
+		ret = i915_gem_switch_to_kernel_context(i915);
 		if (ret)
 			goto err_unlock;
 
-		ret = i915_gem_wait_for_idle(dev_priv,
+		ret = i915_gem_wait_for_idle(i915,
 					     I915_WAIT_INTERRUPTIBLE |
-					     I915_WAIT_LOCKED);
+					     I915_WAIT_LOCKED |
+					     I915_WAIT_FOR_IDLE_BOOST,
+					     MAX_SCHEDULE_TIMEOUT);
 		if (ret && ret != -EIO)
 			goto err_unlock;
 
-		assert_kernel_context_is_current(dev_priv);
+		assert_kernel_context_is_current(i915);
 	}
-	i915_gem_contexts_lost(dev_priv);
-	mutex_unlock(&dev->struct_mutex);
+	i915_retire_requests(i915); /* ensure we flush after wedging */
+
+	mutex_unlock(&i915->drm.struct_mutex);
 
-	intel_uc_suspend(dev_priv);
+	intel_uc_suspend(i915);
 
-	cancel_delayed_work_sync(&dev_priv->gpu_error.hangcheck_work);
-	cancel_delayed_work_sync(&dev_priv->gt.retire_work);
+	cancel_delayed_work_sync(&i915->gpu_error.hangcheck_work);
+	cancel_delayed_work_sync(&i915->gt.retire_work);
 
-	/* As the idle_work is rearming if it detects a race, play safe and
+	/*
+	 * As the idle_work is rearming if it detects a race, play safe and
 	 * repeat the flush until it is definitely idle.
 	 */
-	drain_delayed_work(&dev_priv->gt.idle_work);
+	drain_delayed_work(&i915->gt.idle_work);
 
-	/* Assert that we sucessfully flushed all the work and
+	/*
+	 * Assert that we successfully flushed all the work and
 	 * reset the GPU back to its idle, low power state.
 	 */
-	WARN_ON(dev_priv->gt.awake);
-	if (WARN_ON(!intel_engines_are_idle(dev_priv)))
-		i915_gem_set_wedged(dev_priv); /* no hope, discard everything */
+	WARN_ON(i915->gt.awake);
+	if (WARN_ON(!intel_engines_are_idle(i915)))
+		i915_gem_set_wedged(i915); /* no hope, discard everything */
+
+	intel_runtime_pm_put(i915);
+	return 0;
+
+err_unlock:
+	mutex_unlock(&i915->drm.struct_mutex);
+	intel_runtime_pm_put(i915);
+	return ret;
+}
+
+void i915_gem_suspend_late(struct drm_i915_private *i915)
+{
+	struct drm_i915_gem_object *obj;
+	struct list_head *phases[] = {
+		&i915->mm.unbound_list,
+		&i915->mm.bound_list,
+		NULL
+	}, **phase;
 
 	/*
 	 * Neither the BIOS, ourselves or any other kernel
@@ -5075,20 +5134,22 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv)
 	 * machines is a good idea, we don't - just in case it leaves the
 	 * machine in an unusable condition.
 	 */
-	intel_uc_sanitize(dev_priv);
-	i915_gem_sanitize(dev_priv);
 
-	intel_runtime_pm_put(dev_priv);
-	return 0;
+	mutex_lock(&i915->drm.struct_mutex);
+	for (phase = phases; *phase; phase++) {
+		list_for_each_entry(obj, *phase, mm.link)
+			WARN_ON(i915_gem_object_set_to_gtt_domain(obj, false));
+	}
+	mutex_unlock(&i915->drm.struct_mutex);
 
-err_unlock:
-	mutex_unlock(&dev->struct_mutex);
-	intel_runtime_pm_put(dev_priv);
-	return ret;
+	intel_uc_sanitize(i915);
+	i915_gem_sanitize(i915);
 }
 
 void i915_gem_resume(struct drm_i915_private *i915)
 {
+	GEM_TRACE("\n");
+
 	WARN_ON(i915->gt.awake);
 
 	mutex_lock(&i915->drm.struct_mutex);
@@ -5262,8 +5323,18 @@ int i915_gem_init_hw(struct drm_i915_private *dev_priv)
 
 	/* Only when the HW is re-initialised, can we replay the requests */
 	ret = __i915_gem_restart_engines(dev_priv);
+	if (ret)
+		goto cleanup_uc;
+
+	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+
+	return 0;
+
+cleanup_uc:
+	intel_uc_fini_hw(dev_priv);
 out:
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+
 	return ret;
 }
 
@@ -5300,7 +5371,7 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915)
 		if (engine->init_context)
 			err = engine->init_context(rq);
 
-		__i915_request_add(rq, true);
+		i915_request_add(rq);
 		if (err)
 			goto err_active;
 	}
@@ -5309,9 +5380,11 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915)
 	if (err)
 		goto err_active;
 
-	err = i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED);
-	if (err)
+	if (i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED, HZ / 5)) {
+		i915_gem_set_wedged(i915);
+		err = -EIO; /* Caller will declare us wedged */
 		goto err_active;
+	}
 
 	assert_kernel_context_is_current(i915);
 
@@ -5374,7 +5447,9 @@ err_active:
 	if (WARN_ON(i915_gem_switch_to_kernel_context(i915)))
 		goto out_ctx;
 
-	if (WARN_ON(i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED)))
+	if (WARN_ON(i915_gem_wait_for_idle(i915,
+					   I915_WAIT_LOCKED,
+					   MAX_SCHEDULE_TIMEOUT)))
 		goto out_ctx;
 
 	i915_gem_contexts_lost(i915);
@@ -5385,12 +5460,8 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 {
 	int ret;
 
-	/*
-	 * We need to fallback to 4K pages since gvt gtt handling doesn't
-	 * support huge page entries - we will need to check either hypervisor
-	 * mm can support huge guest page or just do emulation in gvt.
-	 */
-	if (intel_vgpu_active(dev_priv))
+	/* We need to fallback to 4K pages if host doesn't support huge gtt. */
+	if (intel_vgpu_active(dev_priv) && !intel_vgpu_has_huge_gtt(dev_priv))
 		mkwrite_device_info(dev_priv)->page_sizes =
 			I915_GTT_PAGE_SIZE_4K;
 
@@ -5408,13 +5479,13 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	if (ret)
 		return ret;
 
-	ret = intel_wopcm_init(&dev_priv->wopcm);
+	ret = intel_uc_init_misc(dev_priv);
 	if (ret)
 		return ret;
 
-	ret = intel_uc_init_misc(dev_priv);
+	ret = intel_wopcm_init(&dev_priv->wopcm);
 	if (ret)
-		return ret;
+		goto err_uc_misc;
 
 	/* This is just a security blanket to placate dragons.
 	 * On some systems, we very sporadically observe that the first TLBs
@@ -5490,8 +5561,14 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	 * driver doesn't explode during runtime.
 	 */
 err_init_hw:
-	i915_gem_wait_for_idle(dev_priv, I915_WAIT_LOCKED);
-	i915_gem_contexts_lost(dev_priv);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
+
+	WARN_ON(i915_gem_suspend(dev_priv));
+	i915_gem_suspend_late(dev_priv);
+
+	i915_gem_drain_workqueue(dev_priv);
+
+	mutex_lock(&dev_priv->drm.struct_mutex);
 	intel_uc_fini_hw(dev_priv);
 err_uc_init:
 	intel_uc_fini(dev_priv);
@@ -5508,6 +5585,7 @@ err_unlock:
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
+err_uc_misc:
 	intel_uc_fini_misc(dev_priv);
 
 	if (ret != -EIO)
@@ -5520,7 +5598,8 @@ err_unlock:
 		 * for all other failure, such as an allocation failure, bail.
 		 */
 		if (!i915_terminally_wedged(&dev_priv->gpu_error)) {
-			DRM_ERROR("Failed to initialize GPU, declaring it wedged\n");
+			i915_load_error(dev_priv,
+					"Failed to initialize GPU, declaring it wedged!\n");
 			i915_gem_set_wedged(dev_priv);
 		}
 		ret = 0;
@@ -5530,6 +5609,28 @@ err_unlock:
 	return ret;
 }
 
+void i915_gem_fini(struct drm_i915_private *dev_priv)
+{
+	i915_gem_suspend_late(dev_priv);
+
+	/* Flush any outstanding unpin_work. */
+	i915_gem_drain_workqueue(dev_priv);
+
+	mutex_lock(&dev_priv->drm.struct_mutex);
+	intel_uc_fini_hw(dev_priv);
+	intel_uc_fini(dev_priv);
+	i915_gem_cleanup_engines(dev_priv);
+	i915_gem_contexts_fini(dev_priv);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
+
+	intel_uc_fini_misc(dev_priv);
+	i915_gem_cleanup_userptr(dev_priv);
+
+	i915_gem_drain_freed_objects(dev_priv);
+
+	WARN_ON(!list_empty(&dev_priv->contexts.list));
+}
+
 void i915_gem_init_mmio(struct drm_i915_private *i915)
 {
 	i915_gem_sanitize(i915);
@@ -5694,16 +5795,17 @@ int i915_gem_freeze(struct drm_i915_private *dev_priv)
 	return 0;
 }
 
-int i915_gem_freeze_late(struct drm_i915_private *dev_priv)
+int i915_gem_freeze_late(struct drm_i915_private *i915)
 {
 	struct drm_i915_gem_object *obj;
 	struct list_head *phases[] = {
-		&dev_priv->mm.unbound_list,
-		&dev_priv->mm.bound_list,
+		&i915->mm.unbound_list,
+		&i915->mm.bound_list,
 		NULL
-	}, **p;
+	}, **phase;
 
-	/* Called just before we write the hibernation image.
+	/*
+	 * Called just before we write the hibernation image.
 	 *
 	 * We need to update the domain tracking to reflect that the CPU
 	 * will be accessing all the pages to create and restore from the
@@ -5717,15 +5819,15 @@ int i915_gem_freeze_late(struct drm_i915_private *dev_priv)
 	 * the objects as well, see i915_gem_freeze()
 	 */
 
-	i915_gem_shrink(dev_priv, -1UL, NULL, I915_SHRINK_UNBOUND);
-	i915_gem_drain_freed_objects(dev_priv);
+	i915_gem_shrink(i915, -1UL, NULL, I915_SHRINK_UNBOUND);
+	i915_gem_drain_freed_objects(i915);
 
-	spin_lock(&dev_priv->mm.obj_lock);
-	for (p = phases; *p; p++) {
-		list_for_each_entry(obj, *p, mm.link)
-			__start_cpu_write(obj);
+	mutex_lock(&i915->drm.struct_mutex);
+	for (phase = phases; *phase; phase++) {
+		list_for_each_entry(obj, *phase, mm.link)
+			WARN_ON(i915_gem_object_set_to_cpu_domain(obj, true));
 	}
-	spin_unlock(&dev_priv->mm.obj_lock);
+	mutex_unlock(&i915->drm.struct_mutex);
 
 	return 0;
 }
@@ -6045,16 +6147,7 @@ int i915_gem_object_attach_phys(struct drm_i915_gem_object *obj, int align)
 		goto err_unlock;
 	}
 
-	pages = fetch_and_zero(&obj->mm.pages);
-	if (pages) {
-		struct drm_i915_private *i915 = to_i915(obj->base.dev);
-
-		__i915_gem_object_reset_page_iter(obj);
-
-		spin_lock(&i915->mm.obj_lock);
-		list_del(&obj->mm.link);
-		spin_unlock(&i915->mm.obj_lock);
-	}
+	pages = __i915_gem_object_unset_pages(obj);
 
 	obj->ops = &i915_gem_phys_ops;
 
@@ -6072,7 +6165,11 @@ int i915_gem_object_attach_phys(struct drm_i915_gem_object *obj, int align)
 
 err_xfer:
 	obj->ops = &i915_gem_object_ops;
-	obj->mm.pages = pages;
+	if (!IS_ERR_OR_NULL(pages)) {
+		unsigned int sg_page_sizes = i915_sg_page_sizes(pages->sgl);
+
+		__i915_gem_object_set_pages(obj, pages, sg_page_sizes);
+	}
 err_unlock:
 	mutex_unlock(&obj->mm.lock);
 	return err;
diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index 525920404ede..e46592956872 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -26,6 +26,7 @@
 #define __I915_GEM_H__
 
 #include <linux/bug.h>
+#include <linux/interrupt.h>
 
 struct drm_i915_private;
 
@@ -62,9 +63,12 @@ struct drm_i915_private;
 #if IS_ENABLED(CONFIG_DRM_I915_TRACE_GEM)
 #define GEM_TRACE(...) trace_printk(__VA_ARGS__)
 #define GEM_TRACE_DUMP() ftrace_dump(DUMP_ALL)
+#define GEM_TRACE_DUMP_ON(expr) \
+	do { if (expr) ftrace_dump(DUMP_ALL); } while (0)
 #else
 #define GEM_TRACE(...) do { } while (0)
 #define GEM_TRACE_DUMP() do { } while (0)
+#define GEM_TRACE_DUMP_ON(expr) BUILD_BUG_ON_INVALID(expr)
 #endif
 
 #define I915_NUM_ENGINES 8
@@ -72,4 +76,21 @@ struct drm_i915_private;
 void i915_gem_park(struct drm_i915_private *i915);
 void i915_gem_unpark(struct drm_i915_private *i915);
 
+static inline void __tasklet_disable_sync_once(struct tasklet_struct *t)
+{
+	if (atomic_inc_return(&t->count) == 1)
+		tasklet_unlock_wait(t);
+}
+
+static inline void __tasklet_enable_sync_once(struct tasklet_struct *t)
+{
+	if (atomic_dec_return(&t->count) == 0)
+		tasklet_kill(t);
+}
+
+static inline bool __tasklet_is_enabled(const struct tasklet_struct *t)
+{
+	return !atomic_read(&t->count);
+}
+
 #endif /* __I915_GEM_H__ */
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 060335d3d9e0..b10770cfccd2 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -127,14 +127,8 @@ static void i915_gem_context_free(struct i915_gem_context *ctx)
 	for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++) {
 		struct intel_context *ce = &ctx->__engine[n];
 
-		if (!ce->state)
-			continue;
-
-		WARN_ON(ce->pin_count);
-		if (ce->ring)
-			intel_ring_free(ce->ring);
-
-		__i915_gem_object_release_unless_active(ce->state->obj);
+		if (ce->ops)
+			ce->ops->destroy(ce);
 	}
 
 	kfree(ctx->name);
@@ -203,7 +197,7 @@ static void context_close(struct i915_gem_context *ctx)
 	 */
 	lut_close(ctx);
 	if (ctx->ppgtt)
-		i915_ppgtt_close(&ctx->ppgtt->base);
+		i915_ppgtt_close(&ctx->ppgtt->vm);
 
 	ctx->file_priv = ERR_PTR(-EBADF);
 	i915_gem_context_put(ctx);
@@ -214,10 +208,19 @@ static int assign_hw_id(struct drm_i915_private *dev_priv, unsigned *out)
 	int ret;
 	unsigned int max;
 
-	if (INTEL_GEN(dev_priv) >= 11)
+	if (INTEL_GEN(dev_priv) >= 11) {
 		max = GEN11_MAX_CONTEXT_HW_ID;
-	else
-		max = MAX_CONTEXT_HW_ID;
+	} else {
+		/*
+		 * When using GuC in proxy submission, GuC consumes the
+		 * highest bit in the context id to indicate proxy submission.
+		 */
+		if (USES_GUC_SUBMISSION(dev_priv))
+			max = MAX_GUC_CONTEXT_HW_ID;
+		else
+			max = MAX_CONTEXT_HW_ID;
+	}
+
 
 	ret = ida_simple_get(&dev_priv->contexts.hw_ida,
 			     0, max, GFP_KERNEL);
@@ -246,7 +249,7 @@ static u32 default_desc_template(const struct drm_i915_private *i915,
 	desc = GEN8_CTX_VALID | GEN8_CTX_PRIVILEGE;
 
 	address_mode = INTEL_LEGACY_32B_CONTEXT;
-	if (ppgtt && i915_vm_is_48bit(&ppgtt->base))
+	if (ppgtt && i915_vm_is_48bit(&ppgtt->vm))
 		address_mode = INTEL_LEGACY_64B_CONTEXT;
 	desc |= address_mode << GEN8_CTX_ADDRESSING_MODE_SHIFT;
 
@@ -266,6 +269,7 @@ __create_hw_context(struct drm_i915_private *dev_priv,
 		    struct drm_i915_file_private *file_priv)
 {
 	struct i915_gem_context *ctx;
+	unsigned int n;
 	int ret;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
@@ -283,6 +287,12 @@ __create_hw_context(struct drm_i915_private *dev_priv,
 	ctx->i915 = dev_priv;
 	ctx->sched.priority = I915_PRIORITY_NORMAL;
 
+	for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++) {
+		struct intel_context *ce = &ctx->__engine[n];
+
+		ce->gem_context = ctx;
+	}
+
 	INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
 	INIT_LIST_HEAD(&ctx->handles_list);
 
@@ -364,7 +374,7 @@ i915_gem_create_context(struct drm_i915_private *dev_priv,
 	if (USES_FULL_PPGTT(dev_priv)) {
 		struct i915_hw_ppgtt *ppgtt;
 
-		ppgtt = i915_ppgtt_create(dev_priv, file_priv, ctx->name);
+		ppgtt = i915_ppgtt_create(dev_priv, file_priv);
 		if (IS_ERR(ppgtt)) {
 			DRM_DEBUG_DRIVER("PPGTT setup failed (%ld)\n",
 					 PTR_ERR(ppgtt));
@@ -502,8 +512,8 @@ int i915_gem_contexts_init(struct drm_i915_private *dev_priv)
 	}
 
 	DRM_DEBUG_DRIVER("%s context support initialized\n",
-			 dev_priv->engine[RCS]->context_size ? "logical" :
-			 "fake");
+			 DRIVER_CAPS(dev_priv)->has_logical_contexts ?
+			 "logical" : "fake");
 	return 0;
 }
 
@@ -514,16 +524,8 @@ void i915_gem_contexts_lost(struct drm_i915_private *dev_priv)
 
 	lockdep_assert_held(&dev_priv->drm.struct_mutex);
 
-	for_each_engine(engine, dev_priv, id) {
-		engine->legacy_active_context = NULL;
-		engine->legacy_active_ppgtt = NULL;
-
-		if (!engine->last_retired_context)
-			continue;
-
-		intel_context_unpin(engine->last_retired_context, engine);
-		engine->last_retired_context = NULL;
-	}
+	for_each_engine(engine, dev_priv, id)
+		intel_engine_lost_context(engine);
 }
 
 void i915_gem_contexts_fini(struct drm_i915_private *i915)
@@ -583,68 +585,122 @@ last_request_on_engine(struct i915_timeline *timeline,
 {
 	struct i915_request *rq;
 
-	if (timeline == &engine->timeline)
-		return NULL;
+	GEM_BUG_ON(timeline == &engine->timeline);
 
 	rq = i915_gem_active_raw(&timeline->last_request,
 				 &engine->i915->drm.struct_mutex);
-	if (rq && rq->engine == engine)
+	if (rq && rq->engine == engine) {
+		GEM_TRACE("last request for %s on engine %s: %llx:%d\n",
+			  timeline->name, engine->name,
+			  rq->fence.context, rq->fence.seqno);
+		GEM_BUG_ON(rq->timeline != timeline);
 		return rq;
+	}
 
 	return NULL;
 }
 
-static bool engine_has_idle_kernel_context(struct intel_engine_cs *engine)
+static bool engine_has_kernel_context_barrier(struct intel_engine_cs *engine)
 {
-	struct i915_timeline *timeline;
+	struct drm_i915_private *i915 = engine->i915;
+	const struct intel_context * const ce =
+		to_intel_context(i915->kernel_context, engine);
+	struct i915_timeline *barrier = ce->ring->timeline;
+	struct intel_ring *ring;
+	bool any_active = false;
 
-	list_for_each_entry(timeline, &engine->i915->gt.timelines, link) {
-		if (last_request_on_engine(timeline, engine))
+	lockdep_assert_held(&i915->drm.struct_mutex);
+	list_for_each_entry(ring, &i915->gt.active_rings, active_link) {
+		struct i915_request *rq;
+
+		rq = last_request_on_engine(ring->timeline, engine);
+		if (!rq)
+			continue;
+
+		any_active = true;
+
+		if (rq->hw_context == ce)
+			continue;
+
+		/*
+		 * Was this request submitted after the previous
+		 * switch-to-kernel-context?
+		 */
+		if (!i915_timeline_sync_is_later(barrier, &rq->fence)) {
+			GEM_TRACE("%s needs barrier for %llx:%d\n",
+				  ring->timeline->name,
+				  rq->fence.context,
+				  rq->fence.seqno);
 			return false;
+		}
+
+		GEM_TRACE("%s has barrier after %llx:%d\n",
+			  ring->timeline->name,
+			  rq->fence.context,
+			  rq->fence.seqno);
 	}
 
-	return intel_engine_has_kernel_context(engine);
+	/*
+	 * If any other timeline was still active and behind the last barrier,
+	 * then our last switch-to-kernel-context must still be queued and
+	 * will run last (leaving the engine in the kernel context when it
+	 * eventually idles).
+	 */
+	if (any_active)
+		return true;
+
+	/* The engine is idle; check that it is idling in the kernel context. */
+	return engine->last_retired_context == ce;
 }
 
-int i915_gem_switch_to_kernel_context(struct drm_i915_private *dev_priv)
+int i915_gem_switch_to_kernel_context(struct drm_i915_private *i915)
 {
 	struct intel_engine_cs *engine;
-	struct i915_timeline *timeline;
 	enum intel_engine_id id;
 
-	lockdep_assert_held(&dev_priv->drm.struct_mutex);
+	GEM_TRACE("awake?=%s\n", yesno(i915->gt.awake));
 
-	i915_retire_requests(dev_priv);
+	lockdep_assert_held(&i915->drm.struct_mutex);
+	GEM_BUG_ON(!i915->kernel_context);
+
+	i915_retire_requests(i915);
 
-	for_each_engine(engine, dev_priv, id) {
+	for_each_engine(engine, i915, id) {
+		struct intel_ring *ring;
 		struct i915_request *rq;
 
-		if (engine_has_idle_kernel_context(engine))
+		GEM_BUG_ON(!to_intel_context(i915->kernel_context, engine));
+		if (engine_has_kernel_context_barrier(engine))
 			continue;
 
-		rq = i915_request_alloc(engine, dev_priv->kernel_context);
+		GEM_TRACE("emit barrier on %s\n", engine->name);
+
+		rq = i915_request_alloc(engine, i915->kernel_context);
 		if (IS_ERR(rq))
 			return PTR_ERR(rq);
 
 		/* Queue this switch after all other activity */
-		list_for_each_entry(timeline, &dev_priv->gt.timelines, link) {
+		list_for_each_entry(ring, &i915->gt.active_rings, active_link) {
 			struct i915_request *prev;
 
-			prev = last_request_on_engine(timeline, engine);
-			if (prev)
-				i915_sw_fence_await_sw_fence_gfp(&rq->submit,
-								 &prev->submit,
-								 I915_FENCE_GFP);
+			prev = last_request_on_engine(ring->timeline, engine);
+			if (!prev)
+				continue;
+
+			if (prev->gem_context == i915->kernel_context)
+				continue;
+
+			GEM_TRACE("add barrier on %s for %llx:%d\n",
+				  engine->name,
+				  prev->fence.context,
+				  prev->fence.seqno);
+			i915_sw_fence_await_sw_fence_gfp(&rq->submit,
+							 &prev->submit,
+							 I915_FENCE_GFP);
+			i915_timeline_sync_set(rq->timeline, &prev->fence);
 		}
 
-		/*
-		 * Force a flush after the switch to ensure that all rendering
-		 * and operations prior to switching to the kernel context hits
-		 * memory. This should be guaranteed by the previous request,
-		 * but an extra layer of paranoia before we declare the system
-		 * idle (on suspend etc) is advisable!
-		 */
-		__i915_request_add(rq, true);
+		i915_request_add(rq);
 	}
 
 	return 0;
@@ -664,7 +720,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 	struct i915_gem_context *ctx;
 	int ret;
 
-	if (!dev_priv->engine[RCS]->context_size)
+	if (!DRIVER_CAPS(dev_priv)->has_logical_contexts)
 		return -ENODEV;
 
 	if (args->pad != 0)
@@ -747,11 +803,11 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 		break;
 	case I915_CONTEXT_PARAM_GTT_SIZE:
 		if (ctx->ppgtt)
-			args->value = ctx->ppgtt->base.total;
+			args->value = ctx->ppgtt->vm.total;
 		else if (to_i915(dev)->mm.aliasing_ppgtt)
-			args->value = to_i915(dev)->mm.aliasing_ppgtt->base.total;
+			args->value = to_i915(dev)->mm.aliasing_ppgtt->vm.total;
 		else
-			args->value = to_i915(dev)->ggtt.base.total;
+			args->value = to_i915(dev)->ggtt.vm.total;
 		break;
 	case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE:
 		args->value = i915_gem_context_no_error_capture(ctx);
diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h
index ace3b129c189..b116e4942c10 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/i915_gem_context.h
@@ -30,6 +30,7 @@
 #include <linux/radix-tree.h>
 
 #include "i915_gem.h"
+#include "i915_scheduler.h"
 
 struct pid;
 
@@ -45,6 +46,13 @@ struct intel_ring;
 
 #define DEFAULT_CONTEXT_HANDLE 0
 
+struct intel_context;
+
+struct intel_context_ops {
+	void (*unpin)(struct intel_context *ce);
+	void (*destroy)(struct intel_context *ce);
+};
+
 /**
  * struct i915_gem_context - client state
  *
@@ -144,11 +152,14 @@ struct i915_gem_context {
 
 	/** engine: per-engine logical HW state */
 	struct intel_context {
+		struct i915_gem_context *gem_context;
 		struct i915_vma *state;
 		struct intel_ring *ring;
 		u32 *lrc_reg_state;
 		u64 lrc_desc;
 		int pin_count;
+
+		const struct intel_context_ops *ops;
 	} __engine[I915_NUM_ENGINES];
 
 	/** ring_size: size for allocating the per-engine ring buffer */
@@ -263,25 +274,26 @@ to_intel_context(struct i915_gem_context *ctx,
 	return &ctx->__engine[engine->id];
 }
 
-static inline struct intel_ring *
+static inline struct intel_context *
 intel_context_pin(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
 {
 	return engine->context_pin(engine, ctx);
 }
 
-static inline void __intel_context_pin(struct i915_gem_context *ctx,
-				       const struct intel_engine_cs *engine)
+static inline void __intel_context_pin(struct intel_context *ce)
 {
-	struct intel_context *ce = to_intel_context(ctx, engine);
-
 	GEM_BUG_ON(!ce->pin_count);
 	ce->pin_count++;
 }
 
-static inline void intel_context_unpin(struct i915_gem_context *ctx,
-				       struct intel_engine_cs *engine)
+static inline void intel_context_unpin(struct intel_context *ce)
 {
-	engine->context_unpin(engine, ctx);
+	GEM_BUG_ON(!ce->pin_count);
+	if (--ce->pin_count)
+		return;
+
+	GEM_BUG_ON(!ce->ops);
+	ce->ops->unpin(ce);
 }
 
 /* i915_gem_context.c */
diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
index 69a7aec49e84..82e2ca17a441 100644
--- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
@@ -111,15 +111,6 @@ static void i915_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
 	i915_gem_object_unpin_map(obj);
 }
 
-static void *i915_gem_dmabuf_kmap_atomic(struct dma_buf *dma_buf, unsigned long page_num)
-{
-	return NULL;
-}
-
-static void i915_gem_dmabuf_kunmap_atomic(struct dma_buf *dma_buf, unsigned long page_num, void *addr)
-{
-
-}
 static void *i915_gem_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num)
 {
 	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
@@ -225,9 +216,7 @@ static const struct dma_buf_ops i915_dmabuf_ops =  {
 	.unmap_dma_buf = i915_gem_unmap_dma_buf,
 	.release = drm_gem_dmabuf_release,
 	.map = i915_gem_dmabuf_kmap,
-	.map_atomic = i915_gem_dmabuf_kmap_atomic,
 	.unmap = i915_gem_dmabuf_kunmap,
-	.unmap_atomic = i915_gem_dmabuf_kunmap_atomic,
 	.mmap = i915_gem_dmabuf_mmap,
 	.vmap = i915_gem_dmabuf_vmap,
 	.vunmap = i915_gem_dmabuf_vunmap,
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 54814a196ee4..02b83a5ed96c 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -69,7 +69,8 @@ static int ggtt_flush(struct drm_i915_private *i915)
 
 	err = i915_gem_wait_for_idle(i915,
 				     I915_WAIT_INTERRUPTIBLE |
-				     I915_WAIT_LOCKED);
+				     I915_WAIT_LOCKED,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (err)
 		return err;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 22df17c8ca9b..3f0c612d42e7 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -66,6 +66,15 @@ enum {
 #define __I915_EXEC_ILLEGAL_FLAGS \
 	(__I915_EXEC_UNKNOWN_FLAGS | I915_EXEC_CONSTANTS_MASK)
 
+/* Catch emission of unexpected errors for CI! */
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
+#undef EINVAL
+#define EINVAL ({ \
+	DRM_DEBUG_DRIVER("EINVAL at %s:%d\n", __func__, __LINE__); \
+	22; \
+})
+#endif
+
 /**
  * DOC: User command execution
  *
@@ -534,7 +543,8 @@ eb_add_vma(struct i915_execbuffer *eb,
 	 * paranoia do it everywhere.
 	 */
 	if (i == batch_idx) {
-		if (!(eb->flags[i] & EXEC_OBJECT_PINNED))
+		if (entry->relocation_count &&
+		    !(eb->flags[i] & EXEC_OBJECT_PINNED))
 			eb->flags[i] |= __EXEC_OBJECT_NEEDS_BIAS;
 		if (eb->reloc_cache.has_fence)
 			eb->flags[i] |= EXEC_OBJECT_NEEDS_FENCE;
@@ -723,7 +733,7 @@ static int eb_select_context(struct i915_execbuffer *eb)
 		return -ENOENT;
 
 	eb->ctx = ctx;
-	eb->vm = ctx->ppgtt ? &ctx->ppgtt->base : &eb->i915->ggtt.base;
+	eb->vm = ctx->ppgtt ? &ctx->ppgtt->vm : &eb->i915->ggtt.vm;
 
 	eb->context_flags = 0;
 	if (ctx->flags & CONTEXT_NO_ZEROMAP)
@@ -921,7 +931,7 @@ static void reloc_gpu_flush(struct reloc_cache *cache)
 	i915_gem_object_unpin_map(cache->rq->batch->obj);
 	i915_gem_chipset_flush(cache->rq->i915);
 
-	__i915_request_add(cache->rq, true);
+	i915_request_add(cache->rq);
 	cache->rq = NULL;
 }
 
@@ -948,9 +958,9 @@ static void reloc_cache_reset(struct reloc_cache *cache)
 		if (cache->node.allocated) {
 			struct i915_ggtt *ggtt = cache_to_ggtt(cache);
 
-			ggtt->base.clear_range(&ggtt->base,
-					       cache->node.start,
-					       cache->node.size);
+			ggtt->vm.clear_range(&ggtt->vm,
+					     cache->node.start,
+					     cache->node.size);
 			drm_mm_remove_node(&cache->node);
 		} else {
 			i915_vma_unpin((struct i915_vma *)cache->node.mm);
@@ -1021,7 +1031,7 @@ static void *reloc_iomap(struct drm_i915_gem_object *obj,
 		if (IS_ERR(vma)) {
 			memset(&cache->node, 0, sizeof(cache->node));
 			err = drm_mm_insert_node_in_range
-				(&ggtt->base.mm, &cache->node,
+				(&ggtt->vm.mm, &cache->node,
 				 PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE,
 				 0, ggtt->mappable_end,
 				 DRM_MM_INSERT_LOW);
@@ -1042,9 +1052,9 @@ static void *reloc_iomap(struct drm_i915_gem_object *obj,
 	offset = cache->node.start;
 	if (cache->node.allocated) {
 		wmb();
-		ggtt->base.insert_page(&ggtt->base,
-				       i915_gem_object_get_dma_address(obj, page),
-				       offset, I915_CACHE_NONE, 0);
+		ggtt->vm.insert_page(&ggtt->vm,
+				     i915_gem_object_get_dma_address(obj, page),
+				     offset, I915_CACHE_NONE, 0);
 	} else {
 		offset += page << PAGE_SHIFT;
 	}
@@ -1155,18 +1165,16 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 		goto err_request;
 
 	GEM_BUG_ON(!reservation_object_test_signaled_rcu(batch->resv, true));
-	i915_vma_move_to_active(batch, rq, 0);
-	reservation_object_lock(batch->resv, NULL);
-	reservation_object_add_excl_fence(batch->resv, &rq->fence);
-	reservation_object_unlock(batch->resv);
-	i915_vma_unpin(batch);
+	err = i915_vma_move_to_active(batch, rq, 0);
+	if (err)
+		goto skip_request;
 
-	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
-	reservation_object_lock(vma->resv, NULL);
-	reservation_object_add_excl_fence(vma->resv, &rq->fence);
-	reservation_object_unlock(vma->resv);
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	if (err)
+		goto skip_request;
 
 	rq->batch = batch;
+	i915_vma_unpin(batch);
 
 	cache->rq = rq;
 	cache->rq_cmd = cmd;
@@ -1175,6 +1183,8 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 	/* Return with batch mapping (cmd) still pinned */
 	return 0;
 
+skip_request:
+	i915_request_skip(rq, err);
 err_request:
 	i915_request_add(rq);
 err_unpin:
@@ -1761,25 +1771,6 @@ slow:
 	return eb_relocate_slow(eb);
 }
 
-static void eb_export_fence(struct i915_vma *vma,
-			    struct i915_request *rq,
-			    unsigned int flags)
-{
-	struct reservation_object *resv = vma->resv;
-
-	/*
-	 * Ignore errors from failing to allocate the new fence, we can't
-	 * handle an error right now. Worst case should be missed
-	 * synchronisation leading to rendering corruption.
-	 */
-	reservation_object_lock(resv, NULL);
-	if (flags & EXEC_OBJECT_WRITE)
-		reservation_object_add_excl_fence(resv, &rq->fence);
-	else if (reservation_object_reserve_shared(resv) == 0)
-		reservation_object_add_shared_fence(resv, &rq->fence);
-	reservation_object_unlock(resv);
-}
-
 static int eb_move_to_gpu(struct i915_execbuffer *eb)
 {
 	const unsigned int count = eb->buffer_count;
@@ -1833,8 +1824,11 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb)
 		unsigned int flags = eb->flags[i];
 		struct i915_vma *vma = eb->vma[i];
 
-		i915_vma_move_to_active(vma, eb->request, flags);
-		eb_export_fence(vma, eb->request, flags);
+		err = i915_vma_move_to_active(vma, eb->request, flags);
+		if (unlikely(err)) {
+			i915_request_skip(eb->request, err);
+			return err;
+		}
 
 		__eb_unreserve_vma(vma, flags);
 		vma->exec_flags = NULL;
@@ -1874,45 +1868,6 @@ static bool i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
 	return true;
 }
 
-void i915_vma_move_to_active(struct i915_vma *vma,
-			     struct i915_request *rq,
-			     unsigned int flags)
-{
-	struct drm_i915_gem_object *obj = vma->obj;
-	const unsigned int idx = rq->engine->id;
-
-	lockdep_assert_held(&rq->i915->drm.struct_mutex);
-	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
-
-	/*
-	 * Add a reference if we're newly entering the active list.
-	 * The order in which we add operations to the retirement queue is
-	 * vital here: mark_active adds to the start of the callback list,
-	 * such that subsequent callbacks are called first. Therefore we
-	 * add the active reference first and queue for it to be dropped
-	 * *last*.
-	 */
-	if (!i915_vma_is_active(vma))
-		obj->active_count++;
-	i915_vma_set_active(vma, idx);
-	i915_gem_active_set(&vma->last_read[idx], rq);
-	list_move_tail(&vma->vm_link, &vma->vm->active_list);
-
-	obj->write_domain = 0;
-	if (flags & EXEC_OBJECT_WRITE) {
-		obj->write_domain = I915_GEM_DOMAIN_RENDER;
-
-		if (intel_fb_obj_invalidate(obj, ORIGIN_CS))
-			i915_gem_active_set(&obj->frontbuffer_write, rq);
-
-		obj->read_domains = 0;
-	}
-	obj->read_domains |= I915_GEM_GPU_DOMAINS;
-
-	if (flags & EXEC_OBJECT_NEEDS_FENCE)
-		i915_gem_active_set(&vma->last_fence, rq);
-}
-
 static int i915_reset_gen7_sol_offsets(struct i915_request *rq)
 {
 	u32 *cs;
@@ -2438,7 +2393,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	trace_i915_request_queue(eb.request, eb.batch_flags);
 	err = eb_submit(&eb);
 err_request:
-	__i915_request_add(eb.request, err == 0);
+	i915_request_add(eb.request);
 	add_to_client(eb.request, file);
 
 	if (fences)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 996ab2ad6c45..f00c7fbef79e 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -42,7 +42,7 @@
 #include "intel_drv.h"
 #include "intel_frontbuffer.h"
 
-#define I915_GFP_DMA (GFP_KERNEL | __GFP_HIGHMEM)
+#define I915_GFP_ALLOW_FAIL (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN)
 
 /**
  * DOC: Global GTT views
@@ -195,18 +195,18 @@ static int ppgtt_bind_vma(struct i915_vma *vma,
 			  u32 unused)
 {
 	u32 pte_flags;
-	int ret;
+	int err;
 
 	if (!(vma->flags & I915_VMA_LOCAL_BIND)) {
-		ret = vma->vm->allocate_va_range(vma->vm, vma->node.start,
-						 vma->size);
-		if (ret)
-			return ret;
+		err = vma->vm->allocate_va_range(vma->vm,
+						 vma->node.start, vma->size);
+		if (err)
+			return err;
 	}
 
-	/* Currently applicable only to VLV */
+	/* Applicable to VLV, and gen8+ */
 	pte_flags = 0;
-	if (vma->obj->gt_ro)
+	if (i915_gem_object_is_readonly(vma->obj))
 		pte_flags |= PTE_READ_ONLY;
 
 	vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
@@ -244,10 +244,13 @@ static void clear_pages(struct i915_vma *vma)
 }
 
 static gen8_pte_t gen8_pte_encode(dma_addr_t addr,
-				  enum i915_cache_level level)
+				  enum i915_cache_level level,
+				  u32 flags)
 {
-	gen8_pte_t pte = _PAGE_PRESENT | _PAGE_RW;
-	pte |= addr;
+	gen8_pte_t pte = addr | _PAGE_PRESENT | _PAGE_RW;
+
+	if (unlikely(flags & PTE_READ_ONLY))
+		pte &= ~_PAGE_RW;
 
 	switch (level) {
 	case I915_CACHE_NONE:
@@ -375,37 +378,70 @@ static gen6_pte_t iris_pte_encode(dma_addr_t addr,
 	return pte;
 }
 
+static void stash_init(struct pagestash *stash)
+{
+	pagevec_init(&stash->pvec);
+	spin_lock_init(&stash->lock);
+}
+
+static struct page *stash_pop_page(struct pagestash *stash)
+{
+	struct page *page = NULL;
+
+	spin_lock(&stash->lock);
+	if (likely(stash->pvec.nr))
+		page = stash->pvec.pages[--stash->pvec.nr];
+	spin_unlock(&stash->lock);
+
+	return page;
+}
+
+static void stash_push_pagevec(struct pagestash *stash, struct pagevec *pvec)
+{
+	int nr;
+
+	spin_lock_nested(&stash->lock, SINGLE_DEPTH_NESTING);
+
+	nr = min_t(int, pvec->nr, pagevec_space(&stash->pvec));
+	memcpy(stash->pvec.pages + stash->pvec.nr,
+	       pvec->pages + pvec->nr - nr,
+	       sizeof(pvec->pages[0]) * nr);
+	stash->pvec.nr += nr;
+
+	spin_unlock(&stash->lock);
+
+	pvec->nr -= nr;
+}
+
 static struct page *vm_alloc_page(struct i915_address_space *vm, gfp_t gfp)
 {
-	struct pagevec *pvec = &vm->free_pages;
-	struct pagevec stash;
+	struct pagevec stack;
+	struct page *page;
 
 	if (I915_SELFTEST_ONLY(should_fail(&vm->fault_attr, 1)))
 		i915_gem_shrink_all(vm->i915);
 
-	if (likely(pvec->nr))
-		return pvec->pages[--pvec->nr];
+	page = stash_pop_page(&vm->free_pages);
+	if (page)
+		return page;
 
 	if (!vm->pt_kmap_wc)
 		return alloc_page(gfp);
 
-	/* A placeholder for a specific mutex to guard the WC stash */
-	lockdep_assert_held(&vm->i915->drm.struct_mutex);
-
 	/* Look in our global stash of WC pages... */
-	pvec = &vm->i915->mm.wc_stash;
-	if (likely(pvec->nr))
-		return pvec->pages[--pvec->nr];
+	page = stash_pop_page(&vm->i915->mm.wc_stash);
+	if (page)
+		return page;
 
 	/*
-	 * Otherwise batch allocate pages to amoritize cost of set_pages_wc.
+	 * Otherwise batch allocate pages to amortize cost of set_pages_wc.
 	 *
 	 * We have to be careful as page allocation may trigger the shrinker
 	 * (via direct reclaim) which will fill up the WC stash underneath us.
 	 * So we add our WB pages into a temporary pvec on the stack and merge
 	 * them into the WC stash after all the allocations are complete.
 	 */
-	pagevec_init(&stash);
+	pagevec_init(&stack);
 	do {
 		struct page *page;
 
@@ -413,59 +449,67 @@ static struct page *vm_alloc_page(struct i915_address_space *vm, gfp_t gfp)
 		if (unlikely(!page))
 			break;
 
-		stash.pages[stash.nr++] = page;
-	} while (stash.nr < pagevec_space(pvec));
+		stack.pages[stack.nr++] = page;
+	} while (pagevec_space(&stack));
 
-	if (stash.nr) {
-		int nr = min_t(int, stash.nr, pagevec_space(pvec));
-		struct page **pages = stash.pages + stash.nr - nr;
+	if (stack.nr && !set_pages_array_wc(stack.pages, stack.nr)) {
+		page = stack.pages[--stack.nr];
 
-		if (nr && !set_pages_array_wc(pages, nr)) {
-			memcpy(pvec->pages + pvec->nr,
-			       pages, sizeof(pages[0]) * nr);
-			pvec->nr += nr;
-			stash.nr -= nr;
-		}
+		/* Merge spare WC pages to the global stash */
+		stash_push_pagevec(&vm->i915->mm.wc_stash, &stack);
 
-		pagevec_release(&stash);
+		/* Push any surplus WC pages onto the local VM stash */
+		if (stack.nr)
+			stash_push_pagevec(&vm->free_pages, &stack);
 	}
 
-	return likely(pvec->nr) ? pvec->pages[--pvec->nr] : NULL;
+	/* Return unwanted leftovers */
+	if (unlikely(stack.nr)) {
+		WARN_ON_ONCE(set_pages_array_wb(stack.pages, stack.nr));
+		__pagevec_release(&stack);
+	}
+
+	return page;
 }
 
 static void vm_free_pages_release(struct i915_address_space *vm,
 				  bool immediate)
 {
-	struct pagevec *pvec = &vm->free_pages;
+	struct pagevec *pvec = &vm->free_pages.pvec;
+	struct pagevec stack;
 
+	lockdep_assert_held(&vm->free_pages.lock);
 	GEM_BUG_ON(!pagevec_count(pvec));
 
 	if (vm->pt_kmap_wc) {
-		struct pagevec *stash = &vm->i915->mm.wc_stash;
-
-		/* When we use WC, first fill up the global stash and then
+		/*
+		 * When we use WC, first fill up the global stash and then
 		 * only if full immediately free the overflow.
 		 */
+		stash_push_pagevec(&vm->i915->mm.wc_stash, pvec);
 
-		lockdep_assert_held(&vm->i915->drm.struct_mutex);
-		if (pagevec_space(stash)) {
-			do {
-				stash->pages[stash->nr++] =
-					pvec->pages[--pvec->nr];
-				if (!pvec->nr)
-					return;
-			} while (pagevec_space(stash));
-
-			/* As we have made some room in the VM's free_pages,
-			 * we can wait for it to fill again. Unless we are
-			 * inside i915_address_space_fini() and must
-			 * immediately release the pages!
-			 */
-			if (!immediate)
-				return;
-		}
+		/*
+		 * As we have made some room in the VM's free_pages,
+		 * we can wait for it to fill again. Unless we are
+		 * inside i915_address_space_fini() and must
+		 * immediately release the pages!
+		 */
+		if (pvec->nr <= (immediate ? 0 : PAGEVEC_SIZE - 1))
+			return;
+
+		/*
+		 * We have to drop the lock to allow ourselves to sleep,
+		 * so take a copy of the pvec and clear the stash for
+		 * others to use it as we sleep.
+		 */
+		stack = *pvec;
+		pagevec_reinit(pvec);
+		spin_unlock(&vm->free_pages.lock);
 
+		pvec = &stack;
 		set_pages_array_wb(pvec->pages, pvec->nr);
+
+		spin_lock(&vm->free_pages.lock);
 	}
 
 	__pagevec_release(pvec);
@@ -481,20 +525,60 @@ static void vm_free_page(struct i915_address_space *vm, struct page *page)
 	 * unconditional might_sleep() for everybody.
 	 */
 	might_sleep();
-	if (!pagevec_add(&vm->free_pages, page))
+	spin_lock(&vm->free_pages.lock);
+	if (!pagevec_add(&vm->free_pages.pvec, page))
 		vm_free_pages_release(vm, false);
+	spin_unlock(&vm->free_pages.lock);
+}
+
+static void i915_address_space_init(struct i915_address_space *vm,
+				    struct drm_i915_private *dev_priv)
+{
+	/*
+	 * The vm->mutex must be reclaim safe (for use in the shrinker).
+	 * Do a dummy acquire now under fs_reclaim so that any allocation
+	 * attempt holding the lock is immediately reported by lockdep.
+	 */
+	mutex_init(&vm->mutex);
+	i915_gem_shrinker_taints_mutex(&vm->mutex);
+
+	GEM_BUG_ON(!vm->total);
+	drm_mm_init(&vm->mm, 0, vm->total);
+	vm->mm.head_node.color = I915_COLOR_UNEVICTABLE;
+
+	stash_init(&vm->free_pages);
+
+	INIT_LIST_HEAD(&vm->active_list);
+	INIT_LIST_HEAD(&vm->inactive_list);
+	INIT_LIST_HEAD(&vm->unbound_list);
+}
+
+static void i915_address_space_fini(struct i915_address_space *vm)
+{
+	spin_lock(&vm->free_pages.lock);
+	if (pagevec_count(&vm->free_pages.pvec))
+		vm_free_pages_release(vm, true);
+	GEM_BUG_ON(pagevec_count(&vm->free_pages.pvec));
+	spin_unlock(&vm->free_pages.lock);
+
+	drm_mm_takedown(&vm->mm);
+
+	mutex_destroy(&vm->mutex);
 }
 
 static int __setup_page_dma(struct i915_address_space *vm,
 			    struct i915_page_dma *p,
 			    gfp_t gfp)
 {
-	p->page = vm_alloc_page(vm, gfp | __GFP_NOWARN | __GFP_NORETRY);
+	p->page = vm_alloc_page(vm, gfp | I915_GFP_ALLOW_FAIL);
 	if (unlikely(!p->page))
 		return -ENOMEM;
 
-	p->daddr = dma_map_page(vm->dma, p->page, 0, PAGE_SIZE,
-				PCI_DMA_BIDIRECTIONAL);
+	p->daddr = dma_map_page_attrs(vm->dma,
+				      p->page, 0, PAGE_SIZE,
+				      PCI_DMA_BIDIRECTIONAL,
+				      DMA_ATTR_SKIP_CPU_SYNC |
+				      DMA_ATTR_NO_WARN);
 	if (unlikely(dma_mapping_error(vm->dma, p->daddr))) {
 		vm_free_page(vm, p->page);
 		return -ENOMEM;
@@ -506,7 +590,7 @@ static int __setup_page_dma(struct i915_address_space *vm,
 static int setup_page_dma(struct i915_address_space *vm,
 			  struct i915_page_dma *p)
 {
-	return __setup_page_dma(vm, p, I915_GFP_DMA);
+	return __setup_page_dma(vm, p, __GFP_HIGHMEM);
 }
 
 static void cleanup_page_dma(struct i915_address_space *vm,
@@ -520,8 +604,8 @@ static void cleanup_page_dma(struct i915_address_space *vm,
 
 #define setup_px(vm, px) setup_page_dma((vm), px_base(px))
 #define cleanup_px(vm, px) cleanup_page_dma((vm), px_base(px))
-#define fill_px(ppgtt, px, v) fill_page_dma((vm), px_base(px), (v))
-#define fill32_px(ppgtt, px, v) fill_page_dma_32((vm), px_base(px), (v))
+#define fill_px(vm, px, v) fill_page_dma((vm), px_base(px), (v))
+#define fill32_px(vm, px, v) fill_page_dma_32((vm), px_base(px), (v))
 
 static void fill_page_dma(struct i915_address_space *vm,
 			  struct i915_page_dma *p,
@@ -575,8 +659,11 @@ setup_scratch_page(struct i915_address_space *vm, gfp_t gfp)
 		if (unlikely(!page))
 			goto skip;
 
-		addr = dma_map_page(vm->dma, page, 0, size,
-				    PCI_DMA_BIDIRECTIONAL);
+		addr = dma_map_page_attrs(vm->dma,
+					  page, 0, size,
+					  PCI_DMA_BIDIRECTIONAL,
+					  DMA_ATTR_SKIP_CPU_SYNC |
+					  DMA_ATTR_NO_WARN);
 		if (unlikely(dma_mapping_error(vm->dma, addr)))
 			goto free_page;
 
@@ -614,7 +701,7 @@ static struct i915_page_table *alloc_pt(struct i915_address_space *vm)
 {
 	struct i915_page_table *pt;
 
-	pt = kmalloc(sizeof(*pt), GFP_KERNEL | __GFP_NOWARN);
+	pt = kmalloc(sizeof(*pt), I915_GFP_ALLOW_FAIL);
 	if (unlikely(!pt))
 		return ERR_PTR(-ENOMEM);
 
@@ -637,21 +724,20 @@ static void gen8_initialize_pt(struct i915_address_space *vm,
 			       struct i915_page_table *pt)
 {
 	fill_px(vm, pt,
-		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC));
+		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0));
 }
 
-static void gen6_initialize_pt(struct i915_address_space *vm,
+static void gen6_initialize_pt(struct gen6_hw_ppgtt *ppgtt,
 			       struct i915_page_table *pt)
 {
-	fill32_px(vm, pt,
-		  vm->pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0));
+	fill32_px(&ppgtt->base.vm, pt, ppgtt->scratch_pte);
 }
 
 static struct i915_page_directory *alloc_pd(struct i915_address_space *vm)
 {
 	struct i915_page_directory *pd;
 
-	pd = kzalloc(sizeof(*pd), GFP_KERNEL | __GFP_NOWARN);
+	pd = kzalloc(sizeof(*pd), I915_GFP_ALLOW_FAIL);
 	if (unlikely(!pd))
 		return ERR_PTR(-ENOMEM);
 
@@ -685,7 +771,7 @@ static int __pdp_init(struct i915_address_space *vm,
 	const unsigned int pdpes = i915_pdpes_per_pdp(vm);
 
 	pdp->page_directory = kmalloc_array(pdpes, sizeof(*pdp->page_directory),
-					    GFP_KERNEL | __GFP_NOWARN);
+					    I915_GFP_ALLOW_FAIL);
 	if (unlikely(!pdp->page_directory))
 		return -ENOMEM;
 
@@ -765,53 +851,6 @@ static void gen8_initialize_pml4(struct i915_address_space *vm,
 	memset_p((void **)pml4->pdps, vm->scratch_pdp, GEN8_PML4ES_PER_PML4);
 }
 
-/* Broadwell Page Directory Pointer Descriptors */
-static int gen8_write_pdp(struct i915_request *rq,
-			  unsigned entry,
-			  dma_addr_t addr)
-{
-	struct intel_engine_cs *engine = rq->engine;
-	u32 *cs;
-
-	BUG_ON(entry >= 4);
-
-	cs = intel_ring_begin(rq, 6);
-	if (IS_ERR(cs))
-		return PTR_ERR(cs);
-
-	*cs++ = MI_LOAD_REGISTER_IMM(1);
-	*cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(engine, entry));
-	*cs++ = upper_32_bits(addr);
-	*cs++ = MI_LOAD_REGISTER_IMM(1);
-	*cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(engine, entry));
-	*cs++ = lower_32_bits(addr);
-	intel_ring_advance(rq, cs);
-
-	return 0;
-}
-
-static int gen8_mm_switch_3lvl(struct i915_hw_ppgtt *ppgtt,
-			       struct i915_request *rq)
-{
-	int i, ret;
-
-	for (i = GEN8_3LVL_PDPES - 1; i >= 0; i--) {
-		const dma_addr_t pd_daddr = i915_page_dir_dma_addr(ppgtt, i);
-
-		ret = gen8_write_pdp(rq, i, pd_daddr);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-static int gen8_mm_switch_4lvl(struct i915_hw_ppgtt *ppgtt,
-			       struct i915_request *rq)
-{
-	return gen8_write_pdp(rq, 0, px_dma(&ppgtt->pml4));
-}
-
 /* PDE TLBs are a pain to invalidate on GEN8+. When we modify
  * the page table structures, we mark them dirty so that
  * context switching/execlist queuing code takes extra steps
@@ -819,7 +858,7 @@ static int gen8_mm_switch_4lvl(struct i915_hw_ppgtt *ppgtt,
  */
 static void mark_tlbs_dirty(struct i915_hw_ppgtt *ppgtt)
 {
-	ppgtt->pd_dirty_rings = INTEL_INFO(ppgtt->base.i915)->ring_mask;
+	ppgtt->pd_dirty_rings = INTEL_INFO(ppgtt->vm.i915)->ring_mask;
 }
 
 /* Removes entries from a single page table, releasing it if it's empty.
@@ -833,7 +872,7 @@ static bool gen8_ppgtt_clear_pt(struct i915_address_space *vm,
 	unsigned int pte = gen8_pte_index(start);
 	unsigned int pte_end = pte + num_entries;
 	const gen8_pte_t scratch_pte =
-		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC);
+		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
 	gen8_pte_t *vaddr;
 
 	GEM_BUG_ON(num_entries > pt->used_ptes);
@@ -1005,14 +1044,15 @@ gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt,
 			      struct i915_page_directory_pointer *pdp,
 			      struct sgt_dma *iter,
 			      struct gen8_insert_pte *idx,
-			      enum i915_cache_level cache_level)
+			      enum i915_cache_level cache_level,
+			      u32 flags)
 {
 	struct i915_page_directory *pd;
-	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level);
+	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
 	gen8_pte_t *vaddr;
 	bool ret;
 
-	GEM_BUG_ON(idx->pdpe >= i915_pdpes_per_pdp(&ppgtt->base));
+	GEM_BUG_ON(idx->pdpe >= i915_pdpes_per_pdp(&ppgtt->vm));
 	pd = pdp->page_directory[idx->pdpe];
 	vaddr = kmap_atomic_px(pd->page_table[idx->pde]);
 	do {
@@ -1043,7 +1083,7 @@ gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt,
 					break;
 				}
 
-				GEM_BUG_ON(idx->pdpe >= i915_pdpes_per_pdp(&ppgtt->base));
+				GEM_BUG_ON(idx->pdpe >= i915_pdpes_per_pdp(&ppgtt->vm));
 				pd = pdp->page_directory[idx->pdpe];
 			}
 
@@ -1059,14 +1099,14 @@ gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt,
 static void gen8_ppgtt_insert_3lvl(struct i915_address_space *vm,
 				   struct i915_vma *vma,
 				   enum i915_cache_level cache_level,
-				   u32 unused)
+				   u32 flags)
 {
 	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
 	struct sgt_dma iter = sgt_dma(vma);
 	struct gen8_insert_pte idx = gen8_insert_pte(vma->node.start);
 
 	gen8_ppgtt_insert_pte_entries(ppgtt, &ppgtt->pdp, &iter, &idx,
-				      cache_level);
+				      cache_level, flags);
 
 	vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
 }
@@ -1074,9 +1114,10 @@ static void gen8_ppgtt_insert_3lvl(struct i915_address_space *vm,
 static void gen8_ppgtt_insert_huge_entries(struct i915_vma *vma,
 					   struct i915_page_directory_pointer **pdps,
 					   struct sgt_dma *iter,
-					   enum i915_cache_level cache_level)
+					   enum i915_cache_level cache_level,
+					   u32 flags)
 {
-	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level);
+	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
 	u64 start = vma->node.start;
 	dma_addr_t rem = iter->sg->length;
 
@@ -1192,19 +1233,21 @@ static void gen8_ppgtt_insert_huge_entries(struct i915_vma *vma,
 static void gen8_ppgtt_insert_4lvl(struct i915_address_space *vm,
 				   struct i915_vma *vma,
 				   enum i915_cache_level cache_level,
-				   u32 unused)
+				   u32 flags)
 {
 	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
 	struct sgt_dma iter = sgt_dma(vma);
 	struct i915_page_directory_pointer **pdps = ppgtt->pml4.pdps;
 
 	if (vma->page_sizes.sg > I915_GTT_PAGE_SIZE) {
-		gen8_ppgtt_insert_huge_entries(vma, pdps, &iter, cache_level);
+		gen8_ppgtt_insert_huge_entries(vma, pdps, &iter, cache_level,
+					       flags);
 	} else {
 		struct gen8_insert_pte idx = gen8_insert_pte(vma->node.start);
 
 		while (gen8_ppgtt_insert_pte_entries(ppgtt, pdps[idx.pml4e++],
-						     &iter, &idx, cache_level))
+						     &iter, &idx, cache_level,
+						     flags))
 			GEM_BUG_ON(idx.pml4e >= GEN8_PML4ES_PER_PML4);
 
 		vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
@@ -1229,7 +1272,7 @@ static int gen8_init_scratch(struct i915_address_space *vm)
 {
 	int ret;
 
-	ret = setup_scratch_page(vm, I915_GFP_DMA);
+	ret = setup_scratch_page(vm, __GFP_HIGHMEM);
 	if (ret)
 		return ret;
 
@@ -1272,7 +1315,7 @@ free_scratch_page:
 
 static int gen8_ppgtt_notify_vgt(struct i915_hw_ppgtt *ppgtt, bool create)
 {
-	struct i915_address_space *vm = &ppgtt->base;
+	struct i915_address_space *vm = &ppgtt->vm;
 	struct drm_i915_private *dev_priv = vm->i915;
 	enum vgt_g2v_type msg;
 	int i;
@@ -1333,13 +1376,13 @@ static void gen8_ppgtt_cleanup_4lvl(struct i915_hw_ppgtt *ppgtt)
 	int i;
 
 	for (i = 0; i < GEN8_PML4ES_PER_PML4; i++) {
-		if (ppgtt->pml4.pdps[i] == ppgtt->base.scratch_pdp)
+		if (ppgtt->pml4.pdps[i] == ppgtt->vm.scratch_pdp)
 			continue;
 
-		gen8_ppgtt_cleanup_3lvl(&ppgtt->base, ppgtt->pml4.pdps[i]);
+		gen8_ppgtt_cleanup_3lvl(&ppgtt->vm, ppgtt->pml4.pdps[i]);
 	}
 
-	cleanup_px(&ppgtt->base, &ppgtt->pml4);
+	cleanup_px(&ppgtt->vm, &ppgtt->pml4);
 }
 
 static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
@@ -1353,7 +1396,7 @@ static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
 	if (use_4lvl(vm))
 		gen8_ppgtt_cleanup_4lvl(ppgtt);
 	else
-		gen8_ppgtt_cleanup_3lvl(&ppgtt->base, &ppgtt->pdp);
+		gen8_ppgtt_cleanup_3lvl(&ppgtt->vm, &ppgtt->pdp);
 
 	gen8_free_scratch(vm);
 }
@@ -1489,7 +1532,7 @@ static void gen8_dump_pdp(struct i915_hw_ppgtt *ppgtt,
 			  gen8_pte_t scratch_pte,
 			  struct seq_file *m)
 {
-	struct i915_address_space *vm = &ppgtt->base;
+	struct i915_address_space *vm = &ppgtt->vm;
 	struct i915_page_directory *pd;
 	u32 pdpe;
 
@@ -1499,7 +1542,7 @@ static void gen8_dump_pdp(struct i915_hw_ppgtt *ppgtt,
 		u64 pd_start = start;
 		u32 pde;
 
-		if (pdp->page_directory[pdpe] == ppgtt->base.scratch_pd)
+		if (pdp->page_directory[pdpe] == ppgtt->vm.scratch_pd)
 			continue;
 
 		seq_printf(m, "\tPDPE #%d\n", pdpe);
@@ -1507,7 +1550,7 @@ static void gen8_dump_pdp(struct i915_hw_ppgtt *ppgtt,
 			u32 pte;
 			gen8_pte_t *pt_vaddr;
 
-			if (pd->page_table[pde] == ppgtt->base.scratch_pt)
+			if (pd->page_table[pde] == ppgtt->vm.scratch_pt)
 				continue;
 
 			pt_vaddr = kmap_atomic_px(pt);
@@ -1540,10 +1583,10 @@ static void gen8_dump_pdp(struct i915_hw_ppgtt *ppgtt,
 
 static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
 {
-	struct i915_address_space *vm = &ppgtt->base;
+	struct i915_address_space *vm = &ppgtt->vm;
 	const gen8_pte_t scratch_pte =
-		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC);
-	u64 start = 0, length = ppgtt->base.total;
+		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
+	u64 start = 0, length = ppgtt->vm.total;
 
 	if (use_4lvl(vm)) {
 		u64 pml4e;
@@ -1551,7 +1594,7 @@ static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
 		struct i915_page_directory_pointer *pdp;
 
 		gen8_for_each_pml4e(pdp, pml4, start, length, pml4e) {
-			if (pml4->pdps[pml4e] == ppgtt->base.scratch_pdp)
+			if (pml4->pdps[pml4e] == ppgtt->vm.scratch_pdp)
 				continue;
 
 			seq_printf(m, "    PML4E #%llu\n", pml4e);
@@ -1564,10 +1607,10 @@ static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
 
 static int gen8_preallocate_top_level_pdp(struct i915_hw_ppgtt *ppgtt)
 {
-	struct i915_address_space *vm = &ppgtt->base;
+	struct i915_address_space *vm = &ppgtt->vm;
 	struct i915_page_directory_pointer *pdp = &ppgtt->pdp;
 	struct i915_page_directory *pd;
-	u64 start = 0, length = ppgtt->base.total;
+	u64 start = 0, length = ppgtt->vm.total;
 	u64 from = start;
 	unsigned int pdpe;
 
@@ -1601,211 +1644,153 @@ unwind:
  * space.
  *
  */
-static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
+static struct i915_hw_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
 {
-	struct i915_address_space *vm = &ppgtt->base;
-	struct drm_i915_private *dev_priv = vm->i915;
-	int ret;
+	struct i915_hw_ppgtt *ppgtt;
+	int err;
+
+	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
+	if (!ppgtt)
+		return ERR_PTR(-ENOMEM);
+
+	kref_init(&ppgtt->ref);
+
+	ppgtt->vm.i915 = i915;
+	ppgtt->vm.dma = &i915->drm.pdev->dev;
 
-	ppgtt->base.total = USES_FULL_48BIT_PPGTT(dev_priv) ?
+	ppgtt->vm.total = USES_FULL_48BIT_PPGTT(i915) ?
 		1ULL << 48 :
 		1ULL << 32;
 
+	/*
+	 * From bdw, there is support for read-only pages in the PPGTT.
+	 *
+	 * XXX GVT is not honouring the lack of RW in the PTE bits.
+	 */
+	ppgtt->vm.has_read_only = !intel_vgpu_active(i915);
+
+	i915_address_space_init(&ppgtt->vm, i915);
+
 	/* There are only few exceptions for gen >=6. chv and bxt.
 	 * And we are not sure about the latter so play safe for now.
 	 */
-	if (IS_CHERRYVIEW(dev_priv) || IS_BROXTON(dev_priv))
-		ppgtt->base.pt_kmap_wc = true;
+	if (IS_CHERRYVIEW(i915) || IS_BROXTON(i915))
+		ppgtt->vm.pt_kmap_wc = true;
 
-	ret = gen8_init_scratch(&ppgtt->base);
-	if (ret) {
-		ppgtt->base.total = 0;
-		return ret;
-	}
+	err = gen8_init_scratch(&ppgtt->vm);
+	if (err)
+		goto err_free;
 
-	if (use_4lvl(vm)) {
-		ret = setup_px(&ppgtt->base, &ppgtt->pml4);
-		if (ret)
-			goto free_scratch;
+	if (use_4lvl(&ppgtt->vm)) {
+		err = setup_px(&ppgtt->vm, &ppgtt->pml4);
+		if (err)
+			goto err_scratch;
 
-		gen8_initialize_pml4(&ppgtt->base, &ppgtt->pml4);
+		gen8_initialize_pml4(&ppgtt->vm, &ppgtt->pml4);
 
-		ppgtt->switch_mm = gen8_mm_switch_4lvl;
-		ppgtt->base.allocate_va_range = gen8_ppgtt_alloc_4lvl;
-		ppgtt->base.insert_entries = gen8_ppgtt_insert_4lvl;
-		ppgtt->base.clear_range = gen8_ppgtt_clear_4lvl;
+		ppgtt->vm.allocate_va_range = gen8_ppgtt_alloc_4lvl;
+		ppgtt->vm.insert_entries = gen8_ppgtt_insert_4lvl;
+		ppgtt->vm.clear_range = gen8_ppgtt_clear_4lvl;
 	} else {
-		ret = __pdp_init(&ppgtt->base, &ppgtt->pdp);
-		if (ret)
-			goto free_scratch;
+		err = __pdp_init(&ppgtt->vm, &ppgtt->pdp);
+		if (err)
+			goto err_scratch;
 
-		if (intel_vgpu_active(dev_priv)) {
-			ret = gen8_preallocate_top_level_pdp(ppgtt);
-			if (ret) {
+		if (intel_vgpu_active(i915)) {
+			err = gen8_preallocate_top_level_pdp(ppgtt);
+			if (err) {
 				__pdp_fini(&ppgtt->pdp);
-				goto free_scratch;
+				goto err_scratch;
 			}
 		}
 
-		ppgtt->switch_mm = gen8_mm_switch_3lvl;
-		ppgtt->base.allocate_va_range = gen8_ppgtt_alloc_3lvl;
-		ppgtt->base.insert_entries = gen8_ppgtt_insert_3lvl;
-		ppgtt->base.clear_range = gen8_ppgtt_clear_3lvl;
+		ppgtt->vm.allocate_va_range = gen8_ppgtt_alloc_3lvl;
+		ppgtt->vm.insert_entries = gen8_ppgtt_insert_3lvl;
+		ppgtt->vm.clear_range = gen8_ppgtt_clear_3lvl;
 	}
 
-	if (intel_vgpu_active(dev_priv))
+	if (intel_vgpu_active(i915))
 		gen8_ppgtt_notify_vgt(ppgtt, true);
 
-	ppgtt->base.cleanup = gen8_ppgtt_cleanup;
-	ppgtt->base.unbind_vma = ppgtt_unbind_vma;
-	ppgtt->base.bind_vma = ppgtt_bind_vma;
-	ppgtt->base.set_pages = ppgtt_set_pages;
-	ppgtt->base.clear_pages = clear_pages;
+	ppgtt->vm.cleanup = gen8_ppgtt_cleanup;
 	ppgtt->debug_dump = gen8_dump_ppgtt;
 
-	return 0;
+	ppgtt->vm.vma_ops.bind_vma    = ppgtt_bind_vma;
+	ppgtt->vm.vma_ops.unbind_vma  = ppgtt_unbind_vma;
+	ppgtt->vm.vma_ops.set_pages   = ppgtt_set_pages;
+	ppgtt->vm.vma_ops.clear_pages = clear_pages;
 
-free_scratch:
-	gen8_free_scratch(&ppgtt->base);
-	return ret;
+	return ppgtt;
+
+err_scratch:
+	gen8_free_scratch(&ppgtt->vm);
+err_free:
+	kfree(ppgtt);
+	return ERR_PTR(err);
 }
 
-static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
+static void gen6_dump_ppgtt(struct i915_hw_ppgtt *base, struct seq_file *m)
 {
-	struct i915_address_space *vm = &ppgtt->base;
-	struct i915_page_table *unused;
-	gen6_pte_t scratch_pte;
-	u32 pd_entry, pte, pde;
-	u32 start = 0, length = ppgtt->base.total;
+	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(base);
+	const gen6_pte_t scratch_pte = ppgtt->scratch_pte;
+	struct i915_page_table *pt;
+	u32 pte, pde;
 
-	scratch_pte = vm->pte_encode(vm->scratch_page.daddr,
-				     I915_CACHE_LLC, 0);
+	gen6_for_all_pdes(pt, &base->pd, pde) {
+		gen6_pte_t *vaddr;
+
+		if (pt == base->vm.scratch_pt)
+			continue;
+
+		if (i915_vma_is_bound(ppgtt->vma, I915_VMA_GLOBAL_BIND)) {
+			u32 expected =
+				GEN6_PDE_ADDR_ENCODE(px_dma(pt)) |
+				GEN6_PDE_VALID;
+			u32 pd_entry = readl(ppgtt->pd_addr + pde);
+
+			if (pd_entry != expected)
+				seq_printf(m,
+					   "\tPDE #%d mismatch: Actual PDE: %x Expected PDE: %x\n",
+					   pde,
+					   pd_entry,
+					   expected);
+
+			seq_printf(m, "\tPDE: %x\n", pd_entry);
+		}
 
-	gen6_for_each_pde(unused, &ppgtt->pd, start, length, pde) {
-		u32 expected;
-		gen6_pte_t *pt_vaddr;
-		const dma_addr_t pt_addr = px_dma(ppgtt->pd.page_table[pde]);
-		pd_entry = readl(ppgtt->pd_addr + pde);
-		expected = (GEN6_PDE_ADDR_ENCODE(pt_addr) | GEN6_PDE_VALID);
-
-		if (pd_entry != expected)
-			seq_printf(m, "\tPDE #%d mismatch: Actual PDE: %x Expected PDE: %x\n",
-				   pde,
-				   pd_entry,
-				   expected);
-		seq_printf(m, "\tPDE: %x\n", pd_entry);
-
-		pt_vaddr = kmap_atomic_px(ppgtt->pd.page_table[pde]);
-
-		for (pte = 0; pte < GEN6_PTES; pte+=4) {
-			unsigned long va =
-				(pde * PAGE_SIZE * GEN6_PTES) +
-				(pte * PAGE_SIZE);
+		vaddr = kmap_atomic_px(base->pd.page_table[pde]);
+		for (pte = 0; pte < GEN6_PTES; pte += 4) {
 			int i;
-			bool found = false;
+
 			for (i = 0; i < 4; i++)
-				if (pt_vaddr[pte + i] != scratch_pte)
-					found = true;
-			if (!found)
+				if (vaddr[pte + i] != scratch_pte)
+					break;
+			if (i == 4)
 				continue;
 
-			seq_printf(m, "\t\t0x%lx [%03d,%04d]: =", va, pde, pte);
+			seq_printf(m, "\t\t(%03d, %04d) %08lx: ",
+				   pde, pte,
+				   (pde * GEN6_PTES + pte) * PAGE_SIZE);
 			for (i = 0; i < 4; i++) {
-				if (pt_vaddr[pte + i] != scratch_pte)
-					seq_printf(m, " %08x", pt_vaddr[pte + i]);
+				if (vaddr[pte + i] != scratch_pte)
+					seq_printf(m, " %08x", vaddr[pte + i]);
 				else
-					seq_puts(m, "  SCRATCH ");
+					seq_puts(m, "  SCRATCH");
 			}
 			seq_puts(m, "\n");
 		}
-		kunmap_atomic(pt_vaddr);
+		kunmap_atomic(vaddr);
 	}
 }
 
 /* Write pde (index) from the page directory @pd to the page table @pt */
-static inline void gen6_write_pde(const struct i915_hw_ppgtt *ppgtt,
+static inline void gen6_write_pde(const struct gen6_hw_ppgtt *ppgtt,
 				  const unsigned int pde,
 				  const struct i915_page_table *pt)
 {
 	/* Caller needs to make sure the write completes if necessary */
-	writel_relaxed(GEN6_PDE_ADDR_ENCODE(px_dma(pt)) | GEN6_PDE_VALID,
-		       ppgtt->pd_addr + pde);
-}
-
-/* Write all the page tables found in the ppgtt structure to incrementing page
- * directories. */
-static void gen6_write_page_range(struct i915_hw_ppgtt *ppgtt,
-				  u32 start, u32 length)
-{
-	struct i915_page_table *pt;
-	unsigned int pde;
-
-	gen6_for_each_pde(pt, &ppgtt->pd, start, length, pde)
-		gen6_write_pde(ppgtt, pde, pt);
-
-	mark_tlbs_dirty(ppgtt);
-	wmb();
-}
-
-static inline u32 get_pd_offset(struct i915_hw_ppgtt *ppgtt)
-{
-	GEM_BUG_ON(ppgtt->pd.base.ggtt_offset & 0x3f);
-	return ppgtt->pd.base.ggtt_offset << 10;
-}
-
-static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
-			 struct i915_request *rq)
-{
-	struct intel_engine_cs *engine = rq->engine;
-	u32 *cs;
-
-	/* NB: TLBs must be flushed and invalidated before a switch */
-	cs = intel_ring_begin(rq, 6);
-	if (IS_ERR(cs))
-		return PTR_ERR(cs);
-
-	*cs++ = MI_LOAD_REGISTER_IMM(2);
-	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_DCLV(engine));
-	*cs++ = PP_DIR_DCLV_2G;
-	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine));
-	*cs++ = get_pd_offset(ppgtt);
-	*cs++ = MI_NOOP;
-	intel_ring_advance(rq, cs);
-
-	return 0;
-}
-
-static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
-			  struct i915_request *rq)
-{
-	struct intel_engine_cs *engine = rq->engine;
-	u32 *cs;
-
-	/* NB: TLBs must be flushed and invalidated before a switch */
-	cs = intel_ring_begin(rq, 6);
-	if (IS_ERR(cs))
-		return PTR_ERR(cs);
-
-	*cs++ = MI_LOAD_REGISTER_IMM(2);
-	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_DCLV(engine));
-	*cs++ = PP_DIR_DCLV_2G;
-	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine));
-	*cs++ = get_pd_offset(ppgtt);
-	*cs++ = MI_NOOP;
-	intel_ring_advance(rq, cs);
-
-	return 0;
-}
-
-static int gen6_mm_switch(struct i915_hw_ppgtt *ppgtt,
-			  struct i915_request *rq)
-{
-	struct intel_engine_cs *engine = rq->engine;
-	struct drm_i915_private *dev_priv = rq->i915;
-
-	I915_WRITE(RING_PP_DIR_DCLV(engine), PP_DIR_DCLV_2G);
-	I915_WRITE(RING_PP_DIR_BASE(engine), get_pd_offset(ppgtt));
-	return 0;
+	iowrite32(GEN6_PDE_ADDR_ENCODE(px_dma(pt)) | GEN6_PDE_VALID,
+		  ppgtt->pd_addr + pde);
 }
 
 static void gen8_ppgtt_enable(struct drm_i915_private *dev_priv)
@@ -1867,22 +1852,30 @@ static void gen6_ppgtt_enable(struct drm_i915_private *dev_priv)
 static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 				   u64 start, u64 length)
 {
-	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
+	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
 	unsigned int first_entry = start >> PAGE_SHIFT;
 	unsigned int pde = first_entry / GEN6_PTES;
 	unsigned int pte = first_entry % GEN6_PTES;
 	unsigned int num_entries = length >> PAGE_SHIFT;
-	gen6_pte_t scratch_pte =
-		vm->pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
+	const gen6_pte_t scratch_pte = ppgtt->scratch_pte;
 
 	while (num_entries) {
-		struct i915_page_table *pt = ppgtt->pd.page_table[pde++];
-		unsigned int end = min(pte + num_entries, GEN6_PTES);
+		struct i915_page_table *pt = ppgtt->base.pd.page_table[pde++];
+		const unsigned int end = min(pte + num_entries, GEN6_PTES);
+		const unsigned int count = end - pte;
 		gen6_pte_t *vaddr;
 
-		num_entries -= end - pte;
+		GEM_BUG_ON(pt == vm->scratch_pt);
+
+		num_entries -= count;
+
+		GEM_BUG_ON(count > pt->used_ptes);
+		pt->used_ptes -= count;
+		if (!pt->used_ptes)
+			ppgtt->scan_for_unused_pt = true;
 
-		/* Note that the hw doesn't support removing PDE on the fly
+		/*
+		 * Note that the hw doesn't support removing PDE on the fly
 		 * (they are cached inside the context with no means to
 		 * invalidate the cache), so we can only reset the PTE
 		 * entries back to scratch.
@@ -1911,6 +1904,8 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 	struct sgt_dma iter = sgt_dma(vma);
 	gen6_pte_t *vaddr;
 
+	GEM_BUG_ON(ppgtt->pd.page_table[act_pt] == vm->scratch_pt);
+
 	vaddr = kmap_atomic_px(ppgtt->pd.page_table[act_pt]);
 	do {
 		vaddr[act_pte] = pte_encode | GEN6_PTE_ADDR_ENCODE(iter.dma);
@@ -1939,218 +1934,280 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 static int gen6_alloc_va_range(struct i915_address_space *vm,
 			       u64 start, u64 length)
 {
-	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
+	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
 	struct i915_page_table *pt;
 	u64 from = start;
 	unsigned int pde;
 	bool flush = false;
 
-	gen6_for_each_pde(pt, &ppgtt->pd, start, length, pde) {
+	gen6_for_each_pde(pt, &ppgtt->base.pd, start, length, pde) {
+		const unsigned int count = gen6_pte_count(start, length);
+
 		if (pt == vm->scratch_pt) {
 			pt = alloc_pt(vm);
 			if (IS_ERR(pt))
 				goto unwind_out;
 
-			gen6_initialize_pt(vm, pt);
-			ppgtt->pd.page_table[pde] = pt;
-			gen6_write_pde(ppgtt, pde, pt);
-			flush = true;
+			gen6_initialize_pt(ppgtt, pt);
+			ppgtt->base.pd.page_table[pde] = pt;
+
+			if (i915_vma_is_bound(ppgtt->vma,
+					      I915_VMA_GLOBAL_BIND)) {
+				gen6_write_pde(ppgtt, pde, pt);
+				flush = true;
+			}
+
+			GEM_BUG_ON(pt->used_ptes);
 		}
+
+		pt->used_ptes += count;
 	}
 
 	if (flush) {
-		mark_tlbs_dirty(ppgtt);
-		wmb();
+		mark_tlbs_dirty(&ppgtt->base);
+		gen6_ggtt_invalidate(ppgtt->base.vm.i915);
 	}
 
 	return 0;
 
 unwind_out:
-	gen6_ppgtt_clear_range(vm, from, start);
+	gen6_ppgtt_clear_range(vm, from, start - from);
 	return -ENOMEM;
 }
 
-static int gen6_init_scratch(struct i915_address_space *vm)
+static int gen6_ppgtt_init_scratch(struct gen6_hw_ppgtt *ppgtt)
 {
+	struct i915_address_space * const vm = &ppgtt->base.vm;
+	struct i915_page_table *unused;
+	u32 pde;
 	int ret;
 
-	ret = setup_scratch_page(vm, I915_GFP_DMA);
+	ret = setup_scratch_page(vm, __GFP_HIGHMEM);
 	if (ret)
 		return ret;
 
+	ppgtt->scratch_pte =
+		vm->pte_encode(vm->scratch_page.daddr,
+			       I915_CACHE_NONE, PTE_READ_ONLY);
+
 	vm->scratch_pt = alloc_pt(vm);
 	if (IS_ERR(vm->scratch_pt)) {
 		cleanup_scratch_page(vm);
 		return PTR_ERR(vm->scratch_pt);
 	}
 
-	gen6_initialize_pt(vm, vm->scratch_pt);
+	gen6_initialize_pt(ppgtt, vm->scratch_pt);
+	gen6_for_all_pdes(unused, &ppgtt->base.pd, pde)
+		ppgtt->base.pd.page_table[pde] = vm->scratch_pt;
 
 	return 0;
 }
 
-static void gen6_free_scratch(struct i915_address_space *vm)
+static void gen6_ppgtt_free_scratch(struct i915_address_space *vm)
 {
 	free_pt(vm, vm->scratch_pt);
 	cleanup_scratch_page(vm);
 }
 
-static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
+static void gen6_ppgtt_free_pd(struct gen6_hw_ppgtt *ppgtt)
 {
-	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
-	struct i915_page_directory *pd = &ppgtt->pd;
 	struct i915_page_table *pt;
 	u32 pde;
 
-	drm_mm_remove_node(&ppgtt->node);
+	gen6_for_all_pdes(pt, &ppgtt->base.pd, pde)
+		if (pt != ppgtt->base.vm.scratch_pt)
+			free_pt(&ppgtt->base.vm, pt);
+}
+
+static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
+{
+	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
 
-	gen6_for_all_pdes(pt, pd, pde)
-		if (pt != vm->scratch_pt)
-			free_pt(vm, pt);
+	i915_vma_destroy(ppgtt->vma);
 
-	gen6_free_scratch(vm);
+	gen6_ppgtt_free_pd(ppgtt);
+	gen6_ppgtt_free_scratch(vm);
 }
 
-static int gen6_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt)
+static int pd_vma_set_pages(struct i915_vma *vma)
 {
-	struct i915_address_space *vm = &ppgtt->base;
-	struct drm_i915_private *dev_priv = ppgtt->base.i915;
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	int ret;
+	vma->pages = ERR_PTR(-ENODEV);
+	return 0;
+}
 
-	/* PPGTT PDEs reside in the GGTT and consists of 512 entries. The
-	 * allocator works in address space sizes, so it's multiplied by page
-	 * size. We allocate at the top of the GTT to avoid fragmentation.
-	 */
-	BUG_ON(!drm_mm_initialized(&ggtt->base.mm));
+static void pd_vma_clear_pages(struct i915_vma *vma)
+{
+	GEM_BUG_ON(!vma->pages);
 
-	ret = gen6_init_scratch(vm);
-	if (ret)
-		return ret;
+	vma->pages = NULL;
+}
 
-	ret = i915_gem_gtt_insert(&ggtt->base, &ppgtt->node,
-				  GEN6_PD_SIZE, GEN6_PD_ALIGN,
-				  I915_COLOR_UNEVICTABLE,
-				  0, ggtt->base.total,
-				  PIN_HIGH);
-	if (ret)
-		goto err_out;
+static int pd_vma_bind(struct i915_vma *vma,
+		       enum i915_cache_level cache_level,
+		       u32 unused)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vma->vm);
+	struct gen6_hw_ppgtt *ppgtt = vma->private;
+	u32 ggtt_offset = i915_ggtt_offset(vma) / PAGE_SIZE;
+	struct i915_page_table *pt;
+	unsigned int pde;
 
-	if (ppgtt->node.start < ggtt->mappable_end)
-		DRM_DEBUG("Forced to use aperture for PDEs\n");
+	ppgtt->base.pd.base.ggtt_offset = ggtt_offset * sizeof(gen6_pte_t);
+	ppgtt->pd_addr = (gen6_pte_t __iomem *)ggtt->gsm + ggtt_offset;
 
-	ppgtt->pd.base.ggtt_offset =
-		ppgtt->node.start / PAGE_SIZE * sizeof(gen6_pte_t);
+	gen6_for_all_pdes(pt, &ppgtt->base.pd, pde)
+		gen6_write_pde(ppgtt, pde, pt);
 
-	ppgtt->pd_addr = (gen6_pte_t __iomem *)ggtt->gsm +
-		ppgtt->pd.base.ggtt_offset / sizeof(gen6_pte_t);
+	mark_tlbs_dirty(&ppgtt->base);
+	gen6_ggtt_invalidate(ppgtt->base.vm.i915);
 
 	return 0;
-
-err_out:
-	gen6_free_scratch(vm);
-	return ret;
 }
 
-static int gen6_ppgtt_alloc(struct i915_hw_ppgtt *ppgtt)
+static void pd_vma_unbind(struct i915_vma *vma)
 {
-	return gen6_ppgtt_allocate_page_directories(ppgtt);
-}
+	struct gen6_hw_ppgtt *ppgtt = vma->private;
+	struct i915_page_table * const scratch_pt = ppgtt->base.vm.scratch_pt;
+	struct i915_page_table *pt;
+	unsigned int pde;
 
-static void gen6_scratch_va_range(struct i915_hw_ppgtt *ppgtt,
-				  u64 start, u64 length)
-{
-	struct i915_page_table *unused;
-	u32 pde;
+	if (!ppgtt->scan_for_unused_pt)
+		return;
+
+	/* Free all no longer used page tables */
+	gen6_for_all_pdes(pt, &ppgtt->base.pd, pde) {
+		if (pt->used_ptes || pt == scratch_pt)
+			continue;
 
-	gen6_for_each_pde(unused, &ppgtt->pd, start, length, pde)
-		ppgtt->pd.page_table[pde] = ppgtt->base.scratch_pt;
+		free_pt(&ppgtt->base.vm, pt);
+		ppgtt->base.pd.page_table[pde] = scratch_pt;
+	}
+
+	ppgtt->scan_for_unused_pt = false;
 }
 
-static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
-{
-	struct drm_i915_private *dev_priv = ppgtt->base.i915;
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	int ret;
+static const struct i915_vma_ops pd_vma_ops = {
+	.set_pages = pd_vma_set_pages,
+	.clear_pages = pd_vma_clear_pages,
+	.bind_vma = pd_vma_bind,
+	.unbind_vma = pd_vma_unbind,
+};
 
-	ppgtt->base.pte_encode = ggtt->base.pte_encode;
-	if (intel_vgpu_active(dev_priv) || IS_GEN6(dev_priv))
-		ppgtt->switch_mm = gen6_mm_switch;
-	else if (IS_HASWELL(dev_priv))
-		ppgtt->switch_mm = hsw_mm_switch;
-	else if (IS_GEN7(dev_priv))
-		ppgtt->switch_mm = gen7_mm_switch;
-	else
-		BUG();
+static struct i915_vma *pd_vma_create(struct gen6_hw_ppgtt *ppgtt, int size)
+{
+	struct drm_i915_private *i915 = ppgtt->base.vm.i915;
+	struct i915_ggtt *ggtt = &i915->ggtt;
+	struct i915_vma *vma;
 
-	ret = gen6_ppgtt_alloc(ppgtt);
-	if (ret)
-		return ret;
+	GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_PAGE_SIZE));
+	GEM_BUG_ON(size > ggtt->vm.total);
 
-	ppgtt->base.total = I915_PDES * GEN6_PTES * PAGE_SIZE;
+	vma = kmem_cache_zalloc(i915->vmas, GFP_KERNEL);
+	if (!vma)
+		return ERR_PTR(-ENOMEM);
 
-	gen6_scratch_va_range(ppgtt, 0, ppgtt->base.total);
-	gen6_write_page_range(ppgtt, 0, ppgtt->base.total);
+	init_request_active(&vma->last_fence, NULL);
 
-	ret = gen6_alloc_va_range(&ppgtt->base, 0, ppgtt->base.total);
-	if (ret) {
-		gen6_ppgtt_cleanup(&ppgtt->base);
-		return ret;
-	}
+	vma->vm = &ggtt->vm;
+	vma->ops = &pd_vma_ops;
+	vma->private = ppgtt;
 
-	ppgtt->base.clear_range = gen6_ppgtt_clear_range;
-	ppgtt->base.insert_entries = gen6_ppgtt_insert_entries;
-	ppgtt->base.unbind_vma = ppgtt_unbind_vma;
-	ppgtt->base.bind_vma = ppgtt_bind_vma;
-	ppgtt->base.set_pages = ppgtt_set_pages;
-	ppgtt->base.clear_pages = clear_pages;
-	ppgtt->base.cleanup = gen6_ppgtt_cleanup;
-	ppgtt->debug_dump = gen6_dump_ppgtt;
+	vma->active = RB_ROOT;
 
-	DRM_DEBUG_DRIVER("Allocated pde space (%lldM) at GTT entry: %llx\n",
-			 ppgtt->node.size >> 20,
-			 ppgtt->node.start / PAGE_SIZE);
+	vma->size = size;
+	vma->fence_size = size;
+	vma->flags = I915_VMA_GGTT;
+	vma->ggtt_view.type = I915_GGTT_VIEW_ROTATED; /* prevent fencing */
 
-	DRM_DEBUG_DRIVER("Adding PPGTT at offset %x\n",
-			 ppgtt->pd.base.ggtt_offset << 10);
+	INIT_LIST_HEAD(&vma->obj_link);
+	list_add(&vma->vm_link, &vma->vm->unbound_list);
 
-	return 0;
+	return vma;
 }
 
-static int __hw_ppgtt_init(struct i915_hw_ppgtt *ppgtt,
-			   struct drm_i915_private *dev_priv)
+int gen6_ppgtt_pin(struct i915_hw_ppgtt *base)
 {
-	ppgtt->base.i915 = dev_priv;
-	ppgtt->base.dma = &dev_priv->drm.pdev->dev;
+	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(base);
 
-	if (INTEL_GEN(dev_priv) < 8)
-		return gen6_ppgtt_init(ppgtt);
-	else
-		return gen8_ppgtt_init(ppgtt);
+	/*
+	 * Workaround the limited maximum vma->pin_count and the aliasing_ppgtt
+	 * which will be pinned into every active context.
+	 * (When vma->pin_count becomes atomic, I expect we will naturally
+	 * need a larger, unpacked, type and kill this redundancy.)
+	 */
+	if (ppgtt->pin_count++)
+		return 0;
+
+	/*
+	 * PPGTT PDEs reside in the GGTT and consists of 512 entries. The
+	 * allocator works in address space sizes, so it's multiplied by page
+	 * size. We allocate at the top of the GTT to avoid fragmentation.
+	 */
+	return i915_vma_pin(ppgtt->vma,
+			    0, GEN6_PD_ALIGN,
+			    PIN_GLOBAL | PIN_HIGH);
 }
 
-static void i915_address_space_init(struct i915_address_space *vm,
-				    struct drm_i915_private *dev_priv,
-				    const char *name)
+void gen6_ppgtt_unpin(struct i915_hw_ppgtt *base)
 {
-	drm_mm_init(&vm->mm, 0, vm->total);
-	vm->mm.head_node.color = I915_COLOR_UNEVICTABLE;
+	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(base);
 
-	INIT_LIST_HEAD(&vm->active_list);
-	INIT_LIST_HEAD(&vm->inactive_list);
-	INIT_LIST_HEAD(&vm->unbound_list);
+	GEM_BUG_ON(!ppgtt->pin_count);
+	if (--ppgtt->pin_count)
+		return;
 
-	list_add_tail(&vm->global_link, &dev_priv->vm_list);
-	pagevec_init(&vm->free_pages);
+	i915_vma_unpin(ppgtt->vma);
 }
 
-static void i915_address_space_fini(struct i915_address_space *vm)
+static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 {
-	if (pagevec_count(&vm->free_pages))
-		vm_free_pages_release(vm, true);
+	struct i915_ggtt * const ggtt = &i915->ggtt;
+	struct gen6_hw_ppgtt *ppgtt;
+	int err;
 
-	drm_mm_takedown(&vm->mm);
-	list_del(&vm->global_link);
+	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
+	if (!ppgtt)
+		return ERR_PTR(-ENOMEM);
+
+	kref_init(&ppgtt->base.ref);
+
+	ppgtt->base.vm.i915 = i915;
+	ppgtt->base.vm.dma = &i915->drm.pdev->dev;
+
+	ppgtt->base.vm.total = I915_PDES * GEN6_PTES * PAGE_SIZE;
+
+	i915_address_space_init(&ppgtt->base.vm, i915);
+
+	ppgtt->base.vm.allocate_va_range = gen6_alloc_va_range;
+	ppgtt->base.vm.clear_range = gen6_ppgtt_clear_range;
+	ppgtt->base.vm.insert_entries = gen6_ppgtt_insert_entries;
+	ppgtt->base.vm.cleanup = gen6_ppgtt_cleanup;
+	ppgtt->base.debug_dump = gen6_dump_ppgtt;
+
+	ppgtt->base.vm.vma_ops.bind_vma    = ppgtt_bind_vma;
+	ppgtt->base.vm.vma_ops.unbind_vma  = ppgtt_unbind_vma;
+	ppgtt->base.vm.vma_ops.set_pages   = ppgtt_set_pages;
+	ppgtt->base.vm.vma_ops.clear_pages = clear_pages;
+
+	ppgtt->base.vm.pte_encode = ggtt->vm.pte_encode;
+
+	err = gen6_ppgtt_init_scratch(ppgtt);
+	if (err)
+		goto err_free;
+
+	ppgtt->vma = pd_vma_create(ppgtt, GEN6_PD_SIZE);
+	if (IS_ERR(ppgtt->vma)) {
+		err = PTR_ERR(ppgtt->vma);
+		goto err_scratch;
+	}
+
+	return &ppgtt->base;
+
+err_scratch:
+	gen6_ppgtt_free_scratch(&ppgtt->base.vm);
+err_free:
+	kfree(ppgtt);
+	return ERR_PTR(err);
 }
 
 static void gtt_write_workarounds(struct drm_i915_private *dev_priv)
@@ -2212,29 +2269,28 @@ int i915_ppgtt_init_hw(struct drm_i915_private *dev_priv)
 	return 0;
 }
 
+static struct i915_hw_ppgtt *
+__hw_ppgtt_create(struct drm_i915_private *i915)
+{
+	if (INTEL_GEN(i915) < 8)
+		return gen6_ppgtt_create(i915);
+	else
+		return gen8_ppgtt_create(i915);
+}
+
 struct i915_hw_ppgtt *
-i915_ppgtt_create(struct drm_i915_private *dev_priv,
-		  struct drm_i915_file_private *fpriv,
-		  const char *name)
+i915_ppgtt_create(struct drm_i915_private *i915,
+		  struct drm_i915_file_private *fpriv)
 {
 	struct i915_hw_ppgtt *ppgtt;
-	int ret;
-
-	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
-	if (!ppgtt)
-		return ERR_PTR(-ENOMEM);
 
-	ret = __hw_ppgtt_init(ppgtt, dev_priv);
-	if (ret) {
-		kfree(ppgtt);
-		return ERR_PTR(ret);
-	}
+	ppgtt = __hw_ppgtt_create(i915);
+	if (IS_ERR(ppgtt))
+		return ppgtt;
 
-	kref_init(&ppgtt->ref);
-	i915_address_space_init(&ppgtt->base, dev_priv, name);
-	ppgtt->base.file = fpriv;
+	ppgtt->vm.file = fpriv;
 
-	trace_i915_ppgtt_create(&ppgtt->base);
+	trace_i915_ppgtt_create(&ppgtt->vm);
 
 	return ppgtt;
 }
@@ -2268,16 +2324,16 @@ void i915_ppgtt_release(struct kref *kref)
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(kref, struct i915_hw_ppgtt, ref);
 
-	trace_i915_ppgtt_release(&ppgtt->base);
+	trace_i915_ppgtt_release(&ppgtt->vm);
 
-	ppgtt_destroy_vma(&ppgtt->base);
+	ppgtt_destroy_vma(&ppgtt->vm);
 
-	GEM_BUG_ON(!list_empty(&ppgtt->base.active_list));
-	GEM_BUG_ON(!list_empty(&ppgtt->base.inactive_list));
-	GEM_BUG_ON(!list_empty(&ppgtt->base.unbound_list));
+	GEM_BUG_ON(!list_empty(&ppgtt->vm.active_list));
+	GEM_BUG_ON(!list_empty(&ppgtt->vm.inactive_list));
+	GEM_BUG_ON(!list_empty(&ppgtt->vm.unbound_list));
 
-	ppgtt->base.cleanup(&ppgtt->base);
-	i915_address_space_fini(&ppgtt->base);
+	ppgtt->vm.cleanup(&ppgtt->vm);
+	i915_address_space_fini(&ppgtt->vm);
 	kfree(ppgtt);
 }
 
@@ -2373,7 +2429,7 @@ void i915_gem_suspend_gtt_mappings(struct drm_i915_private *dev_priv)
 
 	i915_check_and_clear_faults(dev_priv);
 
-	ggtt->base.clear_range(&ggtt->base, 0, ggtt->base.total);
+	ggtt->vm.clear_range(&ggtt->vm, 0, ggtt->vm.total);
 
 	i915_ggtt_invalidate(dev_priv);
 }
@@ -2419,7 +2475,7 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm,
 	gen8_pte_t __iomem *pte =
 		(gen8_pte_t __iomem *)ggtt->gsm + (offset >> PAGE_SHIFT);
 
-	gen8_set_pte(pte, gen8_pte_encode(addr, level));
+	gen8_set_pte(pte, gen8_pte_encode(addr, level, 0));
 
 	ggtt->invalidate(vm->i915);
 }
@@ -2427,14 +2483,19 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm,
 static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct i915_vma *vma,
 				     enum i915_cache_level level,
-				     u32 unused)
+				     u32 flags)
 {
 	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
 	struct sgt_iter sgt_iter;
 	gen8_pte_t __iomem *gtt_entries;
-	const gen8_pte_t pte_encode = gen8_pte_encode(0, level);
+	const gen8_pte_t pte_encode = gen8_pte_encode(0, level, 0);
 	dma_addr_t addr;
 
+	/*
+	 * Note that we ignore PTE_READ_ONLY here. The caller must be careful
+	 * not to allow the user to override access to a read only page.
+	 */
+
 	gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm;
 	gtt_entries += vma->node.start >> PAGE_SHIFT;
 	for_each_sgt_dma(addr, sgt_iter, vma->pages)
@@ -2500,7 +2561,7 @@ static void gen8_ggtt_clear_range(struct i915_address_space *vm,
 	unsigned first_entry = start >> PAGE_SHIFT;
 	unsigned num_entries = length >> PAGE_SHIFT;
 	const gen8_pte_t scratch_pte =
-		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC);
+		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
 	gen8_pte_t __iomem *gtt_base =
 		(gen8_pte_t __iomem *)ggtt->gsm + first_entry;
 	const int max_entries = ggtt_total_entries(ggtt) - first_entry;
@@ -2561,13 +2622,14 @@ struct insert_entries {
 	struct i915_address_space *vm;
 	struct i915_vma *vma;
 	enum i915_cache_level level;
+	u32 flags;
 };
 
 static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
 {
 	struct insert_entries *arg = _arg;
 
-	gen8_ggtt_insert_entries(arg->vm, arg->vma, arg->level, 0);
+	gen8_ggtt_insert_entries(arg->vm, arg->vma, arg->level, arg->flags);
 	bxt_vtd_ggtt_wa(arg->vm);
 
 	return 0;
@@ -2576,9 +2638,9 @@ static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
 static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm,
 					     struct i915_vma *vma,
 					     enum i915_cache_level level,
-					     u32 unused)
+					     u32 flags)
 {
-	struct insert_entries arg = { vm, vma, level };
+	struct insert_entries arg = { vm, vma, level, flags };
 
 	stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL);
 }
@@ -2669,9 +2731,9 @@ static int ggtt_bind_vma(struct i915_vma *vma,
 	struct drm_i915_gem_object *obj = vma->obj;
 	u32 pte_flags;
 
-	/* Currently applicable only to VLV */
+	/* Applicable to VLV (gen8+ do not support RO in the GGTT) */
 	pte_flags = 0;
-	if (obj->gt_ro)
+	if (i915_gem_object_is_readonly(obj))
 		pte_flags |= PTE_READ_ONLY;
 
 	intel_runtime_pm_get(i915);
@@ -2709,23 +2771,22 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma,
 
 	/* Currently applicable only to VLV */
 	pte_flags = 0;
-	if (vma->obj->gt_ro)
+	if (i915_gem_object_is_readonly(vma->obj))
 		pte_flags |= PTE_READ_ONLY;
 
 	if (flags & I915_VMA_LOCAL_BIND) {
 		struct i915_hw_ppgtt *appgtt = i915->mm.aliasing_ppgtt;
 
-		if (!(vma->flags & I915_VMA_LOCAL_BIND) &&
-		    appgtt->base.allocate_va_range) {
-			ret = appgtt->base.allocate_va_range(&appgtt->base,
-							     vma->node.start,
-							     vma->size);
+		if (!(vma->flags & I915_VMA_LOCAL_BIND)) {
+			ret = appgtt->vm.allocate_va_range(&appgtt->vm,
+							   vma->node.start,
+							   vma->size);
 			if (ret)
 				return ret;
 		}
 
-		appgtt->base.insert_entries(&appgtt->base, vma, cache_level,
-					    pte_flags);
+		appgtt->vm.insert_entries(&appgtt->vm, vma, cache_level,
+					  pte_flags);
 	}
 
 	if (flags & I915_VMA_GLOBAL_BIND) {
@@ -2748,7 +2809,7 @@ static void aliasing_gtt_unbind_vma(struct i915_vma *vma)
 	}
 
 	if (vma->flags & I915_VMA_LOCAL_BIND) {
-		struct i915_address_space *vm = &i915->mm.aliasing_ppgtt->base;
+		struct i915_address_space *vm = &i915->mm.aliasing_ppgtt->vm;
 
 		vm->clear_range(vm, vma->node.start, vma->size);
 	}
@@ -2762,7 +2823,7 @@ void i915_gem_gtt_finish_pages(struct drm_i915_gem_object *obj,
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 
 	if (unlikely(ggtt->do_idle_maps)) {
-		if (i915_gem_wait_for_idle(dev_priv, 0)) {
+		if (i915_gem_wait_for_idle(dev_priv, 0, MAX_SCHEDULE_TIMEOUT)) {
 			DRM_ERROR("Failed to wait for idle; VT'd may hang.\n");
 			/* Wait a bit, in hopes it avoids the hang */
 			udelay(10);
@@ -2811,34 +2872,32 @@ int i915_gem_init_aliasing_ppgtt(struct drm_i915_private *i915)
 	struct i915_hw_ppgtt *ppgtt;
 	int err;
 
-	ppgtt = i915_ppgtt_create(i915, ERR_PTR(-EPERM), "[alias]");
+	ppgtt = i915_ppgtt_create(i915, ERR_PTR(-EPERM));
 	if (IS_ERR(ppgtt))
 		return PTR_ERR(ppgtt);
 
-	if (WARN_ON(ppgtt->base.total < ggtt->base.total)) {
+	if (GEM_WARN_ON(ppgtt->vm.total < ggtt->vm.total)) {
 		err = -ENODEV;
 		goto err_ppgtt;
 	}
 
-	if (ppgtt->base.allocate_va_range) {
-		/* Note we only pre-allocate as far as the end of the global
-		 * GTT. On 48b / 4-level page-tables, the difference is very,
-		 * very significant! We have to preallocate as GVT/vgpu does
-		 * not like the page directory disappearing.
-		 */
-		err = ppgtt->base.allocate_va_range(&ppgtt->base,
-						    0, ggtt->base.total);
-		if (err)
-			goto err_ppgtt;
-	}
+	/*
+	 * Note we only pre-allocate as far as the end of the global
+	 * GTT. On 48b / 4-level page-tables, the difference is very,
+	 * very significant! We have to preallocate as GVT/vgpu does
+	 * not like the page directory disappearing.
+	 */
+	err = ppgtt->vm.allocate_va_range(&ppgtt->vm, 0, ggtt->vm.total);
+	if (err)
+		goto err_ppgtt;
 
 	i915->mm.aliasing_ppgtt = ppgtt;
 
-	GEM_BUG_ON(ggtt->base.bind_vma != ggtt_bind_vma);
-	ggtt->base.bind_vma = aliasing_gtt_bind_vma;
+	GEM_BUG_ON(ggtt->vm.vma_ops.bind_vma != ggtt_bind_vma);
+	ggtt->vm.vma_ops.bind_vma = aliasing_gtt_bind_vma;
 
-	GEM_BUG_ON(ggtt->base.unbind_vma != ggtt_unbind_vma);
-	ggtt->base.unbind_vma = aliasing_gtt_unbind_vma;
+	GEM_BUG_ON(ggtt->vm.vma_ops.unbind_vma != ggtt_unbind_vma);
+	ggtt->vm.vma_ops.unbind_vma = aliasing_gtt_unbind_vma;
 
 	return 0;
 
@@ -2858,8 +2917,8 @@ void i915_gem_fini_aliasing_ppgtt(struct drm_i915_private *i915)
 
 	i915_ppgtt_put(ppgtt);
 
-	ggtt->base.bind_vma = ggtt_bind_vma;
-	ggtt->base.unbind_vma = ggtt_unbind_vma;
+	ggtt->vm.vma_ops.bind_vma   = ggtt_bind_vma;
+	ggtt->vm.vma_ops.unbind_vma = ggtt_unbind_vma;
 }
 
 int i915_gem_init_ggtt(struct drm_i915_private *dev_priv)
@@ -2883,7 +2942,7 @@ int i915_gem_init_ggtt(struct drm_i915_private *dev_priv)
 		return ret;
 
 	/* Reserve a mappable slot for our lockless error capture */
-	ret = drm_mm_insert_node_in_range(&ggtt->base.mm, &ggtt->error_capture,
+	ret = drm_mm_insert_node_in_range(&ggtt->vm.mm, &ggtt->error_capture,
 					  PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE,
 					  0, ggtt->mappable_end,
 					  DRM_MM_INSERT_LOW);
@@ -2891,16 +2950,15 @@ int i915_gem_init_ggtt(struct drm_i915_private *dev_priv)
 		return ret;
 
 	/* Clear any non-preallocated blocks */
-	drm_mm_for_each_hole(entry, &ggtt->base.mm, hole_start, hole_end) {
+	drm_mm_for_each_hole(entry, &ggtt->vm.mm, hole_start, hole_end) {
 		DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n",
 			      hole_start, hole_end);
-		ggtt->base.clear_range(&ggtt->base, hole_start,
-				       hole_end - hole_start);
+		ggtt->vm.clear_range(&ggtt->vm, hole_start,
+				     hole_end - hole_start);
 	}
 
 	/* And finally clear the reserved guard page */
-	ggtt->base.clear_range(&ggtt->base,
-			       ggtt->base.total - PAGE_SIZE, PAGE_SIZE);
+	ggtt->vm.clear_range(&ggtt->vm, ggtt->vm.total - PAGE_SIZE, PAGE_SIZE);
 
 	if (USES_PPGTT(dev_priv) && !USES_FULL_PPGTT(dev_priv)) {
 		ret = i915_gem_init_aliasing_ppgtt(dev_priv);
@@ -2925,30 +2983,26 @@ void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv)
 	struct i915_vma *vma, *vn;
 	struct pagevec *pvec;
 
-	ggtt->base.closed = true;
-
-	mutex_lock(&dev_priv->drm.struct_mutex);
-	GEM_BUG_ON(!list_empty(&ggtt->base.active_list));
-	list_for_each_entry_safe(vma, vn, &ggtt->base.inactive_list, vm_link)
-		WARN_ON(i915_vma_unbind(vma));
-	mutex_unlock(&dev_priv->drm.struct_mutex);
-
-	i915_gem_cleanup_stolen(&dev_priv->drm);
+	ggtt->vm.closed = true;
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
 	i915_gem_fini_aliasing_ppgtt(dev_priv);
 
+	GEM_BUG_ON(!list_empty(&ggtt->vm.active_list));
+	list_for_each_entry_safe(vma, vn, &ggtt->vm.inactive_list, vm_link)
+		WARN_ON(i915_vma_unbind(vma));
+
 	if (drm_mm_node_allocated(&ggtt->error_capture))
 		drm_mm_remove_node(&ggtt->error_capture);
 
-	if (drm_mm_initialized(&ggtt->base.mm)) {
+	if (drm_mm_initialized(&ggtt->vm.mm)) {
 		intel_vgt_deballoon(dev_priv);
-		i915_address_space_fini(&ggtt->base);
+		i915_address_space_fini(&ggtt->vm);
 	}
 
-	ggtt->base.cleanup(&ggtt->base);
+	ggtt->vm.cleanup(&ggtt->vm);
 
-	pvec = &dev_priv->mm.wc_stash;
+	pvec = &dev_priv->mm.wc_stash.pvec;
 	if (pvec->nr) {
 		set_pages_array_wb(pvec->pages, pvec->nr);
 		__pagevec_release(pvec);
@@ -2958,6 +3012,8 @@ void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv)
 
 	arch_phys_wc_del(ggtt->mtrr);
 	io_mapping_fini(&ggtt->iomap);
+
+	i915_gem_cleanup_stolen(&dev_priv->drm);
 }
 
 static unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
@@ -2996,7 +3052,7 @@ static unsigned int chv_get_total_gtt_size(u16 gmch_ctrl)
 
 static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
 {
-	struct drm_i915_private *dev_priv = ggtt->base.i915;
+	struct drm_i915_private *dev_priv = ggtt->vm.i915;
 	struct pci_dev *pdev = dev_priv->drm.pdev;
 	phys_addr_t phys_addr;
 	int ret;
@@ -3020,7 +3076,7 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
 		return -ENOMEM;
 	}
 
-	ret = setup_scratch_page(&ggtt->base, GFP_DMA32);
+	ret = setup_scratch_page(&ggtt->vm, GFP_DMA32);
 	if (ret) {
 		DRM_ERROR("Scratch setup failed\n");
 		/* iounmap will also get called at remove, but meh */
@@ -3326,7 +3382,7 @@ static void setup_private_pat(struct drm_i915_private *dev_priv)
 
 static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 {
-	struct drm_i915_private *dev_priv = ggtt->base.i915;
+	struct drm_i915_private *dev_priv = ggtt->vm.i915;
 	struct pci_dev *pdev = dev_priv->drm.pdev;
 	unsigned int size;
 	u16 snb_gmch_ctl;
@@ -3350,29 +3406,30 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 	else
 		size = gen8_get_total_gtt_size(snb_gmch_ctl);
 
-	ggtt->base.total = (size / sizeof(gen8_pte_t)) << PAGE_SHIFT;
-	ggtt->base.cleanup = gen6_gmch_remove;
-	ggtt->base.bind_vma = ggtt_bind_vma;
-	ggtt->base.unbind_vma = ggtt_unbind_vma;
-	ggtt->base.set_pages = ggtt_set_pages;
-	ggtt->base.clear_pages = clear_pages;
-	ggtt->base.insert_page = gen8_ggtt_insert_page;
-	ggtt->base.clear_range = nop_clear_range;
+	ggtt->vm.total = (size / sizeof(gen8_pte_t)) << PAGE_SHIFT;
+	ggtt->vm.cleanup = gen6_gmch_remove;
+	ggtt->vm.insert_page = gen8_ggtt_insert_page;
+	ggtt->vm.clear_range = nop_clear_range;
 	if (!USES_FULL_PPGTT(dev_priv) || intel_scanout_needs_vtd_wa(dev_priv))
-		ggtt->base.clear_range = gen8_ggtt_clear_range;
+		ggtt->vm.clear_range = gen8_ggtt_clear_range;
 
-	ggtt->base.insert_entries = gen8_ggtt_insert_entries;
+	ggtt->vm.insert_entries = gen8_ggtt_insert_entries;
 
 	/* Serialize GTT updates with aperture access on BXT if VT-d is on. */
 	if (intel_ggtt_update_needs_vtd_wa(dev_priv)) {
-		ggtt->base.insert_entries = bxt_vtd_ggtt_insert_entries__BKL;
-		ggtt->base.insert_page    = bxt_vtd_ggtt_insert_page__BKL;
-		if (ggtt->base.clear_range != nop_clear_range)
-			ggtt->base.clear_range = bxt_vtd_ggtt_clear_range__BKL;
+		ggtt->vm.insert_entries = bxt_vtd_ggtt_insert_entries__BKL;
+		ggtt->vm.insert_page    = bxt_vtd_ggtt_insert_page__BKL;
+		if (ggtt->vm.clear_range != nop_clear_range)
+			ggtt->vm.clear_range = bxt_vtd_ggtt_clear_range__BKL;
 	}
 
 	ggtt->invalidate = gen6_ggtt_invalidate;
 
+	ggtt->vm.vma_ops.bind_vma    = ggtt_bind_vma;
+	ggtt->vm.vma_ops.unbind_vma  = ggtt_unbind_vma;
+	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
+	ggtt->vm.vma_ops.clear_pages = clear_pages;
+
 	setup_private_pat(dev_priv);
 
 	return ggtt_probe_common(ggtt, size);
@@ -3380,7 +3437,7 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 
 static int gen6_gmch_probe(struct i915_ggtt *ggtt)
 {
-	struct drm_i915_private *dev_priv = ggtt->base.i915;
+	struct drm_i915_private *dev_priv = ggtt->vm.i915;
 	struct pci_dev *pdev = dev_priv->drm.pdev;
 	unsigned int size;
 	u16 snb_gmch_ctl;
@@ -3407,29 +3464,30 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt)
 	pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
 
 	size = gen6_get_total_gtt_size(snb_gmch_ctl);
-	ggtt->base.total = (size / sizeof(gen6_pte_t)) << PAGE_SHIFT;
+	ggtt->vm.total = (size / sizeof(gen6_pte_t)) << PAGE_SHIFT;
 
-	ggtt->base.clear_range = gen6_ggtt_clear_range;
-	ggtt->base.insert_page = gen6_ggtt_insert_page;
-	ggtt->base.insert_entries = gen6_ggtt_insert_entries;
-	ggtt->base.bind_vma = ggtt_bind_vma;
-	ggtt->base.unbind_vma = ggtt_unbind_vma;
-	ggtt->base.set_pages = ggtt_set_pages;
-	ggtt->base.clear_pages = clear_pages;
-	ggtt->base.cleanup = gen6_gmch_remove;
+	ggtt->vm.clear_range = gen6_ggtt_clear_range;
+	ggtt->vm.insert_page = gen6_ggtt_insert_page;
+	ggtt->vm.insert_entries = gen6_ggtt_insert_entries;
+	ggtt->vm.cleanup = gen6_gmch_remove;
 
 	ggtt->invalidate = gen6_ggtt_invalidate;
 
 	if (HAS_EDRAM(dev_priv))
-		ggtt->base.pte_encode = iris_pte_encode;
+		ggtt->vm.pte_encode = iris_pte_encode;
 	else if (IS_HASWELL(dev_priv))
-		ggtt->base.pte_encode = hsw_pte_encode;
+		ggtt->vm.pte_encode = hsw_pte_encode;
 	else if (IS_VALLEYVIEW(dev_priv))
-		ggtt->base.pte_encode = byt_pte_encode;
+		ggtt->vm.pte_encode = byt_pte_encode;
 	else if (INTEL_GEN(dev_priv) >= 7)
-		ggtt->base.pte_encode = ivb_pte_encode;
+		ggtt->vm.pte_encode = ivb_pte_encode;
 	else
-		ggtt->base.pte_encode = snb_pte_encode;
+		ggtt->vm.pte_encode = snb_pte_encode;
+
+	ggtt->vm.vma_ops.bind_vma    = ggtt_bind_vma;
+	ggtt->vm.vma_ops.unbind_vma  = ggtt_unbind_vma;
+	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
+	ggtt->vm.vma_ops.clear_pages = clear_pages;
 
 	return ggtt_probe_common(ggtt, size);
 }
@@ -3441,7 +3499,7 @@ static void i915_gmch_remove(struct i915_address_space *vm)
 
 static int i915_gmch_probe(struct i915_ggtt *ggtt)
 {
-	struct drm_i915_private *dev_priv = ggtt->base.i915;
+	struct drm_i915_private *dev_priv = ggtt->vm.i915;
 	phys_addr_t gmadr_base;
 	int ret;
 
@@ -3451,26 +3509,25 @@ static int i915_gmch_probe(struct i915_ggtt *ggtt)
 		return -EIO;
 	}
 
-	intel_gtt_get(&ggtt->base.total,
-		      &gmadr_base,
-		      &ggtt->mappable_end);
+	intel_gtt_get(&ggtt->vm.total, &gmadr_base, &ggtt->mappable_end);
 
 	ggtt->gmadr =
 		(struct resource) DEFINE_RES_MEM(gmadr_base,
 						 ggtt->mappable_end);
 
 	ggtt->do_idle_maps = needs_idle_maps(dev_priv);
-	ggtt->base.insert_page = i915_ggtt_insert_page;
-	ggtt->base.insert_entries = i915_ggtt_insert_entries;
-	ggtt->base.clear_range = i915_ggtt_clear_range;
-	ggtt->base.bind_vma = ggtt_bind_vma;
-	ggtt->base.unbind_vma = ggtt_unbind_vma;
-	ggtt->base.set_pages = ggtt_set_pages;
-	ggtt->base.clear_pages = clear_pages;
-	ggtt->base.cleanup = i915_gmch_remove;
+	ggtt->vm.insert_page = i915_ggtt_insert_page;
+	ggtt->vm.insert_entries = i915_ggtt_insert_entries;
+	ggtt->vm.clear_range = i915_ggtt_clear_range;
+	ggtt->vm.cleanup = i915_gmch_remove;
 
 	ggtt->invalidate = gmch_ggtt_invalidate;
 
+	ggtt->vm.vma_ops.bind_vma    = ggtt_bind_vma;
+	ggtt->vm.vma_ops.unbind_vma  = ggtt_unbind_vma;
+	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
+	ggtt->vm.vma_ops.clear_pages = clear_pages;
+
 	if (unlikely(ggtt->do_idle_maps))
 		DRM_INFO("applying Ironlake quirks for intel_iommu\n");
 
@@ -3486,8 +3543,8 @@ int i915_ggtt_probe_hw(struct drm_i915_private *dev_priv)
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	int ret;
 
-	ggtt->base.i915 = dev_priv;
-	ggtt->base.dma = &dev_priv->drm.pdev->dev;
+	ggtt->vm.i915 = dev_priv;
+	ggtt->vm.dma = &dev_priv->drm.pdev->dev;
 
 	if (INTEL_GEN(dev_priv) <= 5)
 		ret = i915_gmch_probe(ggtt);
@@ -3504,27 +3561,29 @@ int i915_ggtt_probe_hw(struct drm_i915_private *dev_priv)
 	 * restriction!
 	 */
 	if (USES_GUC(dev_priv)) {
-		ggtt->base.total = min_t(u64, ggtt->base.total, GUC_GGTT_TOP);
-		ggtt->mappable_end = min_t(u64, ggtt->mappable_end, ggtt->base.total);
+		ggtt->vm.total = min_t(u64, ggtt->vm.total, GUC_GGTT_TOP);
+		ggtt->mappable_end =
+			min_t(u64, ggtt->mappable_end, ggtt->vm.total);
 	}
 
-	if ((ggtt->base.total - 1) >> 32) {
+	if ((ggtt->vm.total - 1) >> 32) {
 		DRM_ERROR("We never expected a Global GTT with more than 32bits"
 			  " of address space! Found %lldM!\n",
-			  ggtt->base.total >> 20);
-		ggtt->base.total = 1ULL << 32;
-		ggtt->mappable_end = min_t(u64, ggtt->mappable_end, ggtt->base.total);
+			  ggtt->vm.total >> 20);
+		ggtt->vm.total = 1ULL << 32;
+		ggtt->mappable_end =
+			min_t(u64, ggtt->mappable_end, ggtt->vm.total);
 	}
 
-	if (ggtt->mappable_end > ggtt->base.total) {
+	if (ggtt->mappable_end > ggtt->vm.total) {
 		DRM_ERROR("mappable aperture extends past end of GGTT,"
 			  " aperture=%pa, total=%llx\n",
-			  &ggtt->mappable_end, ggtt->base.total);
-		ggtt->mappable_end = ggtt->base.total;
+			  &ggtt->mappable_end, ggtt->vm.total);
+		ggtt->mappable_end = ggtt->vm.total;
 	}
 
 	/* GMADR is the PCI mmio aperture into the global GTT. */
-	DRM_DEBUG_DRIVER("GGTT size = %lluM\n", ggtt->base.total >> 20);
+	DRM_DEBUG_DRIVER("GGTT size = %lluM\n", ggtt->vm.total >> 20);
 	DRM_DEBUG_DRIVER("GMADR size = %lluM\n", (u64)ggtt->mappable_end >> 20);
 	DRM_DEBUG_DRIVER("DSM size = %lluM\n",
 			 (u64)resource_size(&intel_graphics_stolen_res) >> 20);
@@ -3543,7 +3602,7 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	int ret;
 
-	INIT_LIST_HEAD(&dev_priv->vm_list);
+	stash_init(&dev_priv->mm.wc_stash);
 
 	/* Note that we use page colouring to enforce a guard page at the
 	 * end of the address space. This is required as the CS may prefetch
@@ -3551,9 +3610,13 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
 	 * and beyond the end of the GTT if we do not provide a guard.
 	 */
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	i915_address_space_init(&ggtt->base, dev_priv, "[global]");
+	i915_address_space_init(&ggtt->vm, dev_priv);
+
+	/* Only VLV supports read-only GGTT mappings */
+	ggtt->vm.has_read_only = IS_VALLEYVIEW(dev_priv);
+
 	if (!HAS_LLC(dev_priv) && !USES_PPGTT(dev_priv))
-		ggtt->base.mm.color_adjust = i915_gtt_color_adjust;
+		ggtt->vm.mm.color_adjust = i915_gtt_color_adjust;
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
 	if (!io_mapping_init_wc(&dev_priv->ggtt.iomap,
@@ -3576,7 +3639,7 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
 	return 0;
 
 out_gtt_cleanup:
-	ggtt->base.cleanup(&ggtt->base);
+	ggtt->vm.cleanup(&ggtt->vm);
 	return ret;
 }
 
@@ -3610,34 +3673,35 @@ void i915_ggtt_disable_guc(struct drm_i915_private *i915)
 void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv)
 {
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	struct drm_i915_gem_object *obj, *on;
+	struct i915_vma *vma, *vn;
 
 	i915_check_and_clear_faults(dev_priv);
 
 	/* First fill our portion of the GTT with scratch pages */
-	ggtt->base.clear_range(&ggtt->base, 0, ggtt->base.total);
+	ggtt->vm.clear_range(&ggtt->vm, 0, ggtt->vm.total);
 
-	ggtt->base.closed = true; /* skip rewriting PTE on VMA unbind */
+	ggtt->vm.closed = true; /* skip rewriting PTE on VMA unbind */
 
 	/* clflush objects bound into the GGTT and rebind them. */
-	list_for_each_entry_safe(obj, on, &dev_priv->mm.bound_list, mm.link) {
-		bool ggtt_bound = false;
-		struct i915_vma *vma;
+	GEM_BUG_ON(!list_empty(&ggtt->vm.active_list));
+	list_for_each_entry_safe(vma, vn, &ggtt->vm.inactive_list, vm_link) {
+		struct drm_i915_gem_object *obj = vma->obj;
 
-		for_each_ggtt_vma(vma, obj) {
-			if (!i915_vma_unbind(vma))
-				continue;
+		if (!(vma->flags & I915_VMA_GLOBAL_BIND))
+			continue;
 
-			WARN_ON(i915_vma_bind(vma, obj->cache_level,
-					      PIN_UPDATE));
-			ggtt_bound = true;
-		}
+		if (!i915_vma_unbind(vma))
+			continue;
 
-		if (ggtt_bound)
+		WARN_ON(i915_vma_bind(vma,
+				      obj ? obj->cache_level : 0,
+				      PIN_UPDATE));
+		if (obj)
 			WARN_ON(i915_gem_object_set_to_gtt_domain(obj, false));
 	}
 
-	ggtt->base.closed = false;
+	ggtt->vm.closed = false;
+	i915_ggtt_invalidate(dev_priv);
 
 	if (INTEL_GEN(dev_priv) >= 8) {
 		struct intel_ppat *ppat = &dev_priv->ppat;
@@ -3646,23 +3710,6 @@ void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv)
 		dev_priv->ppat.update_hw(dev_priv);
 		return;
 	}
-
-	if (USES_PPGTT(dev_priv)) {
-		struct i915_address_space *vm;
-
-		list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
-			struct i915_hw_ppgtt *ppgtt;
-
-			if (i915_is_ggtt(vm))
-				ppgtt = dev_priv->mm.aliasing_ppgtt;
-			else
-				ppgtt = i915_vm_to_ppgtt(vm);
-
-			gen6_write_page_range(ppgtt, 0, ppgtt->base.total);
-		}
-	}
-
-	i915_ggtt_invalidate(dev_priv);
 }
 
 static struct scatterlist *
@@ -3880,7 +3927,7 @@ int i915_gem_gtt_reserve(struct i915_address_space *vm,
 	GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_PAGE_SIZE));
 	GEM_BUG_ON(!IS_ALIGNED(offset, I915_GTT_MIN_ALIGNMENT));
 	GEM_BUG_ON(range_overflows(offset, size, vm->total));
-	GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->base);
+	GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->vm);
 	GEM_BUG_ON(drm_mm_node_allocated(node));
 
 	node->size = size;
@@ -3977,7 +4024,7 @@ int i915_gem_gtt_insert(struct i915_address_space *vm,
 	GEM_BUG_ON(start >= end);
 	GEM_BUG_ON(start > 0  && !IS_ALIGNED(start, I915_GTT_PAGE_SIZE));
 	GEM_BUG_ON(end < U64_MAX && !IS_ALIGNED(end, I915_GTT_PAGE_SIZE));
-	GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->base);
+	GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->vm);
 	GEM_BUG_ON(drm_mm_node_allocated(node));
 
 	if (unlikely(range_overflows(start, size, end)))
@@ -3988,7 +4035,7 @@ int i915_gem_gtt_insert(struct i915_address_space *vm,
 
 	mode = DRM_MM_INSERT_BEST;
 	if (flags & PIN_HIGH)
-		mode = DRM_MM_INSERT_HIGH;
+		mode = DRM_MM_INSERT_HIGHEST;
 	if (flags & PIN_MAPPABLE)
 		mode = DRM_MM_INSERT_LOW;
 
@@ -4008,6 +4055,15 @@ int i915_gem_gtt_insert(struct i915_address_space *vm,
 	if (err != -ENOSPC)
 		return err;
 
+	if (mode & DRM_MM_INSERT_ONCE) {
+		err = drm_mm_insert_node_in_range(&vm->mm, node,
+						  size, alignment, color,
+						  start, end,
+						  DRM_MM_INSERT_BEST);
+		if (err != -ENOSPC)
+			return err;
+	}
+
 	if (flags & PIN_NOEVICT)
 		return -ENOSPC;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index aec4f73574f4..2a116a91420b 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -58,6 +58,7 @@
 
 struct drm_i915_file_private;
 struct drm_i915_fence_reg;
+struct i915_vma;
 
 typedef u32 gen6_pte_t;
 typedef u64 gen8_pte_t;
@@ -65,7 +66,7 @@ typedef u64 gen8_pde_t;
 typedef u64 gen8_ppgtt_pdpe_t;
 typedef u64 gen8_ppgtt_pml4e_t;
 
-#define ggtt_total_entries(ggtt) ((ggtt)->base.total >> PAGE_SHIFT)
+#define ggtt_total_entries(ggtt) ((ggtt)->vm.total >> PAGE_SHIFT)
 
 /* gen6-hsw has bit 11-4 for physical addr bit 39-32 */
 #define GEN6_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0xff0))
@@ -254,6 +255,26 @@ struct i915_pml4 {
 	struct i915_page_directory_pointer *pdps[GEN8_PML4ES_PER_PML4];
 };
 
+struct i915_vma_ops {
+	/* Map an object into an address space with the given cache flags. */
+	int (*bind_vma)(struct i915_vma *vma,
+			enum i915_cache_level cache_level,
+			u32 flags);
+	/*
+	 * Unmap an object from an address space. This usually consists of
+	 * setting the valid PTE entries to a reserved scratch page.
+	 */
+	void (*unbind_vma)(struct i915_vma *vma);
+
+	int (*set_pages)(struct i915_vma *vma);
+	void (*clear_pages)(struct i915_vma *vma);
+};
+
+struct pagestash {
+	spinlock_t lock;
+	struct pagevec pvec;
+};
+
 struct i915_address_space {
 	struct drm_mm mm;
 	struct drm_i915_private *i915;
@@ -267,12 +288,13 @@ struct i915_address_space {
 	 * assign blame.
 	 */
 	struct drm_i915_file_private *file;
-	struct list_head global_link;
 	u64 total;		/* size addr space maps (ex. 2GB for ggtt) */
 	u64 reserved;		/* size addr space reserved */
 
 	bool closed;
 
+	struct mutex mutex; /* protects vma and our lists */
+
 	struct i915_page_dma scratch_page;
 	struct i915_page_table *scratch_pt;
 	struct i915_page_directory *scratch_pd;
@@ -308,8 +330,13 @@ struct i915_address_space {
 	 */
 	struct list_head unbound_list;
 
-	struct pagevec free_pages;
-	bool pt_kmap_wc;
+	struct pagestash free_pages;
+
+	/* Some systems require uncached updates of the page directories */
+	bool pt_kmap_wc:1;
+
+	/* Some systems support read-only mappings for GGTT and/or PPGTT */
+	bool has_read_only:1;
 
 	/* FIXME: Need a more generic return type */
 	gen6_pte_t (*pte_encode)(dma_addr_t addr,
@@ -331,15 +358,8 @@ struct i915_address_space {
 			       enum i915_cache_level cache_level,
 			       u32 flags);
 	void (*cleanup)(struct i915_address_space *vm);
-	/** Unmap an object from an address space. This usually consists of
-	 * setting the valid PTE entries to a reserved scratch page. */
-	void (*unbind_vma)(struct i915_vma *vma);
-	/* Map an object into an address space with the given cache flags. */
-	int (*bind_vma)(struct i915_vma *vma,
-			enum i915_cache_level cache_level,
-			u32 flags);
-	int (*set_pages)(struct i915_vma *vma);
-	void (*clear_pages)(struct i915_vma *vma);
+
+	struct i915_vma_ops vma_ops;
 
 	I915_SELFTEST_DECLARE(struct fault_attr fault_attr);
 	I915_SELFTEST_DECLARE(bool scrub_64K);
@@ -367,7 +387,7 @@ i915_vm_has_scratch_64K(struct i915_address_space *vm)
  * the spec.
  */
 struct i915_ggtt {
-	struct i915_address_space base;
+	struct i915_address_space vm;
 
 	struct io_mapping iomap;	/* Mapping to our CPU mappable region */
 	struct resource gmadr;          /* GMADR resource */
@@ -385,9 +405,9 @@ struct i915_ggtt {
 };
 
 struct i915_hw_ppgtt {
-	struct i915_address_space base;
+	struct i915_address_space vm;
 	struct kref ref;
-	struct drm_mm_node node;
+
 	unsigned long pd_dirty_rings;
 	union {
 		struct i915_pml4 pml4;		/* GEN8+ & 48b PPGTT */
@@ -395,13 +415,28 @@ struct i915_hw_ppgtt {
 		struct i915_page_directory pd;		/* GEN6-7 */
 	};
 
+	void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m);
+};
+
+struct gen6_hw_ppgtt {
+	struct i915_hw_ppgtt base;
+
+	struct i915_vma *vma;
 	gen6_pte_t __iomem *pd_addr;
+	gen6_pte_t scratch_pte;
 
-	int (*switch_mm)(struct i915_hw_ppgtt *ppgtt,
-			 struct i915_request *rq);
-	void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m);
+	unsigned int pin_count;
+	bool scan_for_unused_pt;
 };
 
+#define __to_gen6_ppgtt(base) container_of(base, struct gen6_hw_ppgtt, base)
+
+static inline struct gen6_hw_ppgtt *to_gen6_ppgtt(struct i915_hw_ppgtt *base)
+{
+	BUILD_BUG_ON(offsetof(struct gen6_hw_ppgtt, base));
+	return __to_gen6_ppgtt(base);
+}
+
 /*
  * gen6_for_each_pde() iterates over every pde from start until start+length.
  * If start and start+length are not perfectly divisible, the macro will round
@@ -440,8 +475,8 @@ static inline u32 i915_pte_count(u64 addr, u64 length, unsigned int pde_shift)
 	const u64 mask = ~((1ULL << pde_shift) - 1);
 	u64 end;
 
-	WARN_ON(length == 0);
-	WARN_ON(offset_in_page(addr|length));
+	GEM_BUG_ON(length == 0);
+	GEM_BUG_ON(offset_in_page(addr | length));
 
 	end = addr + length;
 
@@ -543,7 +578,7 @@ static inline struct i915_ggtt *
 i915_vm_to_ggtt(struct i915_address_space *vm)
 {
 	GEM_BUG_ON(!i915_is_ggtt(vm));
-	return container_of(vm, struct i915_ggtt, base);
+	return container_of(vm, struct i915_ggtt, vm);
 }
 
 #define INTEL_MAX_PPAT_ENTRIES 8
@@ -591,8 +626,7 @@ void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv);
 int i915_ppgtt_init_hw(struct drm_i915_private *dev_priv);
 void i915_ppgtt_release(struct kref *kref);
 struct i915_hw_ppgtt *i915_ppgtt_create(struct drm_i915_private *dev_priv,
-					struct drm_i915_file_private *fpriv,
-					const char *name);
+					struct drm_i915_file_private *fpriv);
 void i915_ppgtt_close(struct i915_address_space *vm);
 static inline void i915_ppgtt_get(struct i915_hw_ppgtt *ppgtt)
 {
@@ -605,6 +639,9 @@ static inline void i915_ppgtt_put(struct i915_hw_ppgtt *ppgtt)
 		kref_put(&ppgtt->ref, i915_ppgtt_release);
 }
 
+int gen6_ppgtt_pin(struct i915_hw_ppgtt *base);
+void gen6_ppgtt_unpin(struct i915_hw_ppgtt *base);
+
 void i915_check_and_clear_faults(struct drm_i915_private *dev_priv);
 void i915_gem_suspend_gtt_mappings(struct drm_i915_private *dev_priv);
 void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h
index 54f00b350779..83e5e01fa9ea 100644
--- a/drivers/gpu/drm/i915/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/i915_gem_object.h
@@ -141,7 +141,6 @@ struct drm_i915_gem_object {
 	 * Is the object to be mapped as read-only to the GPU
 	 * Only honoured if hardware has relevant pte bit
 	 */
-	unsigned long gt_ro:1;
 	unsigned int cache_level:3;
 	unsigned int cache_coherent:2;
 #define I915_BO_CACHE_COHERENT_FOR_READ BIT(0)
@@ -268,7 +267,6 @@ struct drm_i915_gem_object {
 	union {
 		struct i915_gem_userptr {
 			uintptr_t ptr;
-			unsigned read_only :1;
 
 			struct i915_mm_struct *mm;
 			struct i915_mmu_object *mmu_object;
@@ -337,26 +335,17 @@ __attribute__((nonnull))
 static inline struct drm_i915_gem_object *
 i915_gem_object_get(struct drm_i915_gem_object *obj)
 {
-	drm_gem_object_reference(&obj->base);
+	drm_gem_object_get(&obj->base);
 	return obj;
 }
 
-__deprecated
-extern void drm_gem_object_reference(struct drm_gem_object *);
-
 __attribute__((nonnull))
 static inline void
 i915_gem_object_put(struct drm_i915_gem_object *obj)
 {
-	__drm_gem_object_unreference(&obj->base);
+	__drm_gem_object_put(&obj->base);
 }
 
-__deprecated
-extern void drm_gem_object_unreference(struct drm_gem_object *);
-
-__deprecated
-extern void drm_gem_object_unreference_unlocked(struct drm_gem_object *);
-
 static inline void i915_gem_object_lock(struct drm_i915_gem_object *obj)
 {
 	reservation_object_lock(obj->resv, NULL);
@@ -367,6 +356,18 @@ static inline void i915_gem_object_unlock(struct drm_i915_gem_object *obj)
 	reservation_object_unlock(obj->resv);
 }
 
+static inline void
+i915_gem_object_set_readonly(struct drm_i915_gem_object *obj)
+{
+	obj->base.vma_node.readonly = true;
+}
+
+static inline bool
+i915_gem_object_is_readonly(const struct drm_i915_gem_object *obj)
+{
+	return obj->base.vma_node.readonly;
+}
+
 static inline bool
 i915_gem_object_has_struct_page(const struct drm_i915_gem_object *obj)
 {
diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
index 1036e8686916..90baf9086d0a 100644
--- a/drivers/gpu/drm/i915/i915_gem_render_state.c
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
@@ -194,7 +194,7 @@ int i915_gem_render_state_emit(struct i915_request *rq)
 	if (IS_ERR(so.obj))
 		return PTR_ERR(so.obj);
 
-	so.vma = i915_vma_instance(so.obj, &engine->i915->ggtt.base, NULL);
+	so.vma = i915_vma_instance(so.obj, &engine->i915->ggtt.vm, NULL);
 	if (IS_ERR(so.vma)) {
 		err = PTR_ERR(so.vma);
 		goto err_obj;
@@ -222,7 +222,7 @@ int i915_gem_render_state_emit(struct i915_request *rq)
 			goto err_unpin;
 	}
 
-	i915_vma_move_to_active(so.vma, rq, 0);
+	err = i915_vma_move_to_active(so.vma, rq, 0);
 err_unpin:
 	i915_vma_unpin(so.vma);
 err_vma:
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index 5757fb7c4b5a..ea90d3a0d511 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -23,6 +23,7 @@
  */
 
 #include <linux/oom.h>
+#include <linux/sched/mm.h>
 #include <linux/shmem_fs.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
@@ -172,7 +173,9 @@ i915_gem_shrink(struct drm_i915_private *i915,
 	 * we will free as much as we can and hope to get a second chance.
 	 */
 	if (flags & I915_SHRINK_ACTIVE)
-		i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED);
+		i915_gem_wait_for_idle(i915,
+				       I915_WAIT_LOCKED,
+				       MAX_SCHEDULE_TIMEOUT);
 
 	trace_i915_gem_shrink(i915, target, flags);
 	i915_retire_requests(i915);
@@ -392,7 +395,8 @@ shrinker_lock_uninterruptible(struct drm_i915_private *i915, bool *unlock,
 	unsigned long timeout = jiffies + msecs_to_jiffies_timeout(timeout_ms);
 
 	do {
-		if (i915_gem_wait_for_idle(i915, 0) == 0 &&
+		if (i915_gem_wait_for_idle(i915,
+					   0, MAX_SCHEDULE_TIMEOUT) == 0 &&
 		    shrinker_lock(i915, unlock))
 			break;
 
@@ -466,7 +470,9 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr
 		return NOTIFY_DONE;
 
 	/* Force everything onto the inactive lists */
-	ret = i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED);
+	ret = i915_gem_wait_for_idle(i915,
+				     I915_WAIT_LOCKED,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (ret)
 		goto out;
 
@@ -480,7 +486,7 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr
 
 	/* We also want to clear any cached iomaps as they wrap vmap */
 	list_for_each_entry_safe(vma, next,
-				 &i915->ggtt.base.inactive_list, vm_link) {
+				 &i915->ggtt.vm.inactive_list, vm_link) {
 		unsigned long count = vma->node.size >> PAGE_SHIFT;
 		if (vma->iomap && i915_vma_unbind(vma) == 0)
 			freed_pages += count;
@@ -526,3 +532,14 @@ void i915_gem_shrinker_unregister(struct drm_i915_private *i915)
 	WARN_ON(unregister_oom_notifier(&i915->mm.oom_notifier));
 	unregister_shrinker(&i915->mm.shrinker);
 }
+
+void i915_gem_shrinker_taints_mutex(struct mutex *mutex)
+{
+	if (!IS_ENABLED(CONFIG_LOCKDEP))
+		return;
+
+	fs_reclaim_acquire(GFP_KERNEL);
+	mutex_lock(mutex);
+	mutex_unlock(mutex);
+	fs_reclaim_release(GFP_KERNEL);
+}
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index ad949cc30928..53440bf87650 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -254,6 +254,7 @@ static void vlv_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	switch (reg_val & GEN7_STOLEN_RESERVED_SIZE_MASK) {
 	default:
 		MISSING_CASE(reg_val & GEN7_STOLEN_RESERVED_SIZE_MASK);
+		/* fall through */
 	case GEN7_STOLEN_RESERVED_1M:
 		*size = 1024 * 1024;
 		break;
@@ -343,6 +344,35 @@ static void bdw_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	*size = stolen_top - *base;
 }
 
+static void icl_get_stolen_reserved(struct drm_i915_private *dev_priv,
+				    resource_size_t *base,
+				    resource_size_t *size)
+{
+	u64 reg_val = I915_READ64(GEN6_STOLEN_RESERVED);
+
+	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = 0x%016llx\n", reg_val);
+
+	*base = reg_val & GEN11_STOLEN_RESERVED_ADDR_MASK;
+
+	switch (reg_val & GEN8_STOLEN_RESERVED_SIZE_MASK) {
+	case GEN8_STOLEN_RESERVED_1M:
+		*size = 1024 * 1024;
+		break;
+	case GEN8_STOLEN_RESERVED_2M:
+		*size = 2 * 1024 * 1024;
+		break;
+	case GEN8_STOLEN_RESERVED_4M:
+		*size = 4 * 1024 * 1024;
+		break;
+	case GEN8_STOLEN_RESERVED_8M:
+		*size = 8 * 1024 * 1024;
+		break;
+	default:
+		*size = 8 * 1024 * 1024;
+		MISSING_CASE(reg_val & GEN8_STOLEN_RESERVED_SIZE_MASK);
+	}
+}
+
 int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 {
 	resource_size_t reserved_base, stolen_top;
@@ -399,7 +429,9 @@ int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 			gen7_get_stolen_reserved(dev_priv,
 						 &reserved_base, &reserved_size);
 		break;
-	default:
+	case 8:
+	case 9:
+	case 10:
 		if (IS_LP(dev_priv))
 			chv_get_stolen_reserved(dev_priv,
 						&reserved_base, &reserved_size);
@@ -407,6 +439,11 @@ int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 			bdw_get_stolen_reserved(dev_priv,
 						&reserved_base, &reserved_size);
 		break;
+	case 11:
+	default:
+		icl_get_stolen_reserved(dev_priv, &reserved_base,
+					&reserved_size);
+		break;
 	}
 
 	/*
@@ -642,7 +679,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 	if (ret)
 		goto err;
 
-	vma = i915_vma_instance(obj, &ggtt->base, NULL);
+	vma = i915_vma_instance(obj, &ggtt->vm, NULL);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto err_pages;
@@ -653,7 +690,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 	 * setting up the GTT space. The actual reservation will occur
 	 * later.
 	 */
-	ret = i915_gem_gtt_reserve(&ggtt->base, &vma->node,
+	ret = i915_gem_gtt_reserve(&ggtt->vm, &vma->node,
 				   size, gtt_offset, obj->cache_level,
 				   0);
 	if (ret) {
@@ -666,7 +703,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 	vma->pages = obj->mm.pages;
 	vma->flags |= I915_VMA_GLOBAL_BIND;
 	__i915_vma_set_map_and_fenceable(vma);
-	list_move_tail(&vma->vm_link, &ggtt->base.inactive_list);
+	list_move_tail(&vma->vm_link, &ggtt->vm.inactive_list);
 
 	spin_lock(&dev_priv->mm.obj_lock);
 	list_move_tail(&obj->mm.link, &dev_priv->mm.bound_list);
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 854bd51b9478..dcd6e230d16a 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -507,7 +507,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 		struct mm_struct *mm = obj->userptr.mm->mm;
 		unsigned int flags = 0;
 
-		if (!obj->userptr.read_only)
+		if (!i915_gem_object_is_readonly(obj))
 			flags |= FOLL_WRITE;
 
 		ret = -EFAULT;
@@ -643,7 +643,7 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 		if (pvec) /* defer to worker if malloc fails */
 			pinned = __get_user_pages_fast(obj->userptr.ptr,
 						       num_pages,
-						       !obj->userptr.read_only,
+						       !i915_gem_object_is_readonly(obj),
 						       pvec);
 	}
 
@@ -789,10 +789,15 @@ i915_gem_userptr_ioctl(struct drm_device *dev,
 		return -EFAULT;
 
 	if (args->flags & I915_USERPTR_READ_ONLY) {
-		/* On almost all of the current hw, we cannot tell the GPU that a
-		 * page is readonly, so this is just a placeholder in the uAPI.
+		struct i915_hw_ppgtt *ppgtt;
+
+		/*
+		 * On almost all of the older hw, we cannot tell the GPU that
+		 * a page is readonly.
 		 */
-		return -ENODEV;
+		ppgtt = dev_priv->kernel_context->ppgtt;
+		if (!ppgtt || !ppgtt->vm.has_read_only)
+			return -ENODEV;
 	}
 
 	obj = i915_gem_object_alloc(dev_priv);
@@ -806,7 +811,8 @@ i915_gem_userptr_ioctl(struct drm_device *dev,
 	i915_gem_object_set_cache_coherency(obj, I915_CACHE_LLC);
 
 	obj->userptr.ptr = args->user_ptr;
-	obj->userptr.read_only = !!(args->flags & I915_USERPTR_READ_ONLY);
+	if (args->flags & I915_USERPTR_READ_ONLY)
+		i915_gem_object_set_readonly(obj);
 
 	/* And keep a pointer to the current->mm for resolving the user pages
 	 * at binding. This means that we need to hook into the mmu_notifier
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index df234dc23274..f7f2aa71d8d9 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -31,6 +31,7 @@
 #include <linux/stop_machine.h>
 #include <linux/zlib.h>
 #include <drm/drm_print.h>
+#include <linux/ascii85.h>
 
 #include "i915_gpu_error.h"
 #include "i915_drv.h"
@@ -335,21 +336,16 @@ static void print_error_buffers(struct drm_i915_error_state_buf *m,
 				struct drm_i915_error_buffer *err,
 				int count)
 {
-	int i;
-
 	err_printf(m, "%s [%d]:\n", name, count);
 
 	while (count--) {
-		err_printf(m, "    %08x_%08x %8u %02x %02x [ ",
+		err_printf(m, "    %08x_%08x %8u %02x %02x %02x",
 			   upper_32_bits(err->gtt_offset),
 			   lower_32_bits(err->gtt_offset),
 			   err->size,
 			   err->read_domains,
-			   err->write_domain);
-		for (i = 0; i < I915_NUM_ENGINES; i++)
-			err_printf(m, "%02x ", err->rseqno[i]);
-
-		err_printf(m, "] %02x", err->wseqno);
+			   err->write_domain,
+			   err->wseqno);
 		err_puts(m, tiling_flag(err->tiling));
 		err_puts(m, dirty_flag(err->dirty));
 		err_puts(m, purgeable_flag(err->purgeable));
@@ -522,35 +518,12 @@ void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...)
 	va_end(args);
 }
 
-static int
-ascii85_encode_len(int len)
-{
-	return DIV_ROUND_UP(len, 4);
-}
-
-static bool
-ascii85_encode(u32 in, char *out)
-{
-	int i;
-
-	if (in == 0)
-		return false;
-
-	out[5] = '\0';
-	for (i = 5; i--; ) {
-		out[i] = '!' + in % 85;
-		in /= 85;
-	}
-
-	return true;
-}
-
 static void print_error_obj(struct drm_i915_error_state_buf *m,
 			    struct intel_engine_cs *engine,
 			    const char *name,
 			    struct drm_i915_error_object *obj)
 {
-	char out[6];
+	char out[ASCII85_BUFSZ];
 	int page;
 
 	if (!obj)
@@ -572,12 +545,8 @@ static void print_error_obj(struct drm_i915_error_state_buf *m,
 			len -= obj->unused;
 		len = ascii85_encode_len(len);
 
-		for (i = 0; i < len; i++) {
-			if (ascii85_encode(obj->pages[page][i], out))
-				err_puts(m, out);
-			else
-				err_puts(m, "z");
-		}
+		for (i = 0; i < len; i++)
+			err_puts(m, ascii85_encode(obj->pages[page][i], out));
 	}
 	err_puts(m, "\n");
 }
@@ -973,8 +942,7 @@ i915_error_object_create(struct drm_i915_private *i915,
 		void __iomem *s;
 		int ret;
 
-		ggtt->base.insert_page(&ggtt->base, dma, slot,
-				       I915_CACHE_NONE, 0);
+		ggtt->vm.insert_page(&ggtt->vm, dma, slot, I915_CACHE_NONE, 0);
 
 		s = io_mapping_map_atomic_wc(&ggtt->iomap, slot);
 		ret = compress_page(&compress, (void  __force *)s, dst);
@@ -993,7 +961,7 @@ unwind:
 
 out:
 	compress_fini(&compress, dst);
-	ggtt->base.clear_range(&ggtt->base, slot, PAGE_SIZE);
+	ggtt->vm.clear_range(&ggtt->vm, slot, PAGE_SIZE);
 	return dst;
 }
 
@@ -1022,13 +990,10 @@ static void capture_bo(struct drm_i915_error_buffer *err,
 		       struct i915_vma *vma)
 {
 	struct drm_i915_gem_object *obj = vma->obj;
-	int i;
 
 	err->size = obj->base.size;
 	err->name = obj->base.name;
 
-	for (i = 0; i < I915_NUM_ENGINES; i++)
-		err->rseqno[i] = __active_get_seqno(&vma->last_read[i]);
 	err->wseqno = __active_get_seqno(&obj->frontbuffer_write);
 	err->engine = __active_get_engine_id(&obj->frontbuffer_write);
 
@@ -1051,6 +1016,9 @@ static u32 capture_error_bo(struct drm_i915_error_buffer *err,
 	int i = 0;
 
 	list_for_each_entry(vma, head, vm_link) {
+		if (!vma->obj)
+			continue;
+
 		if (pinned_only && !i915_vma_is_pinned(vma))
 			continue;
 
@@ -1287,9 +1255,11 @@ static void error_record_engine_registers(struct i915_gpu_state *error,
 static void record_request(struct i915_request *request,
 			   struct drm_i915_error_request *erq)
 {
-	erq->context = request->ctx->hw_id;
+	struct i915_gem_context *ctx = request->gem_context;
+
+	erq->context = ctx->hw_id;
 	erq->sched_attr = request->sched.attr;
-	erq->ban_score = atomic_read(&request->ctx->ban_score);
+	erq->ban_score = atomic_read(&ctx->ban_score);
 	erq->seqno = request->global_seqno;
 	erq->jiffies = request->emitted_jiffies;
 	erq->start = i915_ggtt_offset(request->ring->vma);
@@ -1297,7 +1267,7 @@ static void record_request(struct i915_request *request,
 	erq->tail = request->tail;
 
 	rcu_read_lock();
-	erq->pid = request->ctx->pid ? pid_nr(request->ctx->pid) : 0;
+	erq->pid = ctx->pid ? pid_nr(ctx->pid) : 0;
 	rcu_read_unlock();
 }
 
@@ -1461,12 +1431,12 @@ static void gem_record_rings(struct i915_gpu_state *error)
 
 		request = i915_gem_find_active_request(engine);
 		if (request) {
+			struct i915_gem_context *ctx = request->gem_context;
 			struct intel_ring *ring;
 
-			ee->vm = request->ctx->ppgtt ?
-				&request->ctx->ppgtt->base : &ggtt->base;
+			ee->vm = ctx->ppgtt ? &ctx->ppgtt->vm : &ggtt->vm;
 
-			record_context(&ee->context, request->ctx);
+			record_context(&ee->context, ctx);
 
 			/* We need to copy these to an anonymous buffer
 			 * as the simplest method to avoid being overwritten
@@ -1483,11 +1453,10 @@ static void gem_record_rings(struct i915_gpu_state *error)
 
 			ee->ctx =
 				i915_error_object_create(i915,
-							 to_intel_context(request->ctx,
-									  engine)->state);
+							 request->hw_context->state);
 
 			error->simulated |=
-				i915_gem_context_no_error_capture(request->ctx);
+				i915_gem_context_no_error_capture(ctx);
 
 			ee->rq_head = request->head;
 			ee->rq_post = request->postfix;
@@ -1563,17 +1532,17 @@ static void capture_active_buffers(struct i915_gpu_state *error)
 
 static void capture_pinned_buffers(struct i915_gpu_state *error)
 {
-	struct i915_address_space *vm = &error->i915->ggtt.base;
+	struct i915_address_space *vm = &error->i915->ggtt.vm;
 	struct drm_i915_error_buffer *bo;
 	struct i915_vma *vma;
 	int count_inactive, count_active;
 
 	count_inactive = 0;
-	list_for_each_entry(vma, &vm->active_list, vm_link)
+	list_for_each_entry(vma, &vm->inactive_list, vm_link)
 		count_inactive++;
 
 	count_active = 0;
-	list_for_each_entry(vma, &vm->inactive_list, vm_link)
+	list_for_each_entry(vma, &vm->active_list, vm_link)
 		count_active++;
 
 	bo = NULL;
@@ -1667,7 +1636,16 @@ static void capture_reg_state(struct i915_gpu_state *error)
 	}
 
 	/* 4: Everything else */
-	if (INTEL_GEN(dev_priv) >= 8) {
+	if (INTEL_GEN(dev_priv) >= 11) {
+		error->ier = I915_READ(GEN8_DE_MISC_IER);
+		error->gtier[0] = I915_READ(GEN11_RENDER_COPY_INTR_ENABLE);
+		error->gtier[1] = I915_READ(GEN11_VCS_VECS_INTR_ENABLE);
+		error->gtier[2] = I915_READ(GEN11_GUC_SG_INTR_ENABLE);
+		error->gtier[3] = I915_READ(GEN11_GPM_WGBOXPERF_INTR_ENABLE);
+		error->gtier[4] = I915_READ(GEN11_CRYPTO_RSVD_INTR_ENABLE);
+		error->gtier[5] = I915_READ(GEN11_GUNIT_CSME_INTR_ENABLE);
+		error->ngtier = 6;
+	} else if (INTEL_GEN(dev_priv) >= 8) {
 		error->ier = I915_READ(GEN8_DE_MISC_IER);
 		for (i = 0; i < 4; i++)
 			error->gtier[i] = I915_READ(GEN8_GT_IER(i));
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index dac0f8c4c1cf..f893a4e8b783 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -58,7 +58,7 @@ struct i915_gpu_state {
 	u32 eir;
 	u32 pgtbl_er;
 	u32 ier;
-	u32 gtier[4], ngtier;
+	u32 gtier[6], ngtier;
 	u32 ccid;
 	u32 derrmr;
 	u32 forcewake;
@@ -177,7 +177,7 @@ struct i915_gpu_state {
 	struct drm_i915_error_buffer {
 		u32 size;
 		u32 name;
-		u32 rseqno[I915_NUM_ENGINES], wseqno;
+		u32 wseqno;
 		u64 gtt_offset;
 		u32 read_domains;
 		u32 write_domain;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index c16cb025755e..90628a47ae17 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -115,6 +115,22 @@ static const u32 hpd_bxt[HPD_NUM_PINS] = {
 	[HPD_PORT_C] = BXT_DE_PORT_HP_DDIC
 };
 
+static const u32 hpd_gen11[HPD_NUM_PINS] = {
+	[HPD_PORT_C] = GEN11_TC1_HOTPLUG | GEN11_TBT1_HOTPLUG,
+	[HPD_PORT_D] = GEN11_TC2_HOTPLUG | GEN11_TBT2_HOTPLUG,
+	[HPD_PORT_E] = GEN11_TC3_HOTPLUG | GEN11_TBT3_HOTPLUG,
+	[HPD_PORT_F] = GEN11_TC4_HOTPLUG | GEN11_TBT4_HOTPLUG
+};
+
+static const u32 hpd_icp[HPD_NUM_PINS] = {
+	[HPD_PORT_A] = SDE_DDIA_HOTPLUG_ICP,
+	[HPD_PORT_B] = SDE_DDIB_HOTPLUG_ICP,
+	[HPD_PORT_C] = SDE_TC1_HOTPLUG_ICP,
+	[HPD_PORT_D] = SDE_TC2_HOTPLUG_ICP,
+	[HPD_PORT_E] = SDE_TC3_HOTPLUG_ICP,
+	[HPD_PORT_F] = SDE_TC4_HOTPLUG_ICP
+};
+
 /* IIR can theoretically queue up two events. Be paranoid. */
 #define GEN8_IRQ_RESET_NDX(type, which) do { \
 	I915_WRITE(GEN8_##type##_IMR(which), 0xffffffff); \
@@ -247,9 +263,9 @@ static u32
 gen11_gt_engine_identity(struct drm_i915_private * const i915,
 			 const unsigned int bank, const unsigned int bit);
 
-bool gen11_reset_one_iir(struct drm_i915_private * const i915,
-			 const unsigned int bank,
-			 const unsigned int bit)
+static bool gen11_reset_one_iir(struct drm_i915_private * const i915,
+				const unsigned int bank,
+				const unsigned int bit)
 {
 	void __iomem * const regs = i915->regs;
 	u32 dw;
@@ -1138,21 +1154,21 @@ static void ironlake_rps_change_irq_handler(struct drm_i915_private *dev_priv)
 
 static void notify_ring(struct intel_engine_cs *engine)
 {
+	const u32 seqno = intel_engine_get_seqno(engine);
 	struct i915_request *rq = NULL;
+	struct task_struct *tsk = NULL;
 	struct intel_wait *wait;
 
-	if (!engine->breadcrumbs.irq_armed)
+	if (unlikely(!engine->breadcrumbs.irq_armed))
 		return;
 
-	atomic_inc(&engine->irq_count);
-	set_bit(ENGINE_IRQ_BREADCRUMB, &engine->irq_posted);
+	rcu_read_lock();
 
 	spin_lock(&engine->breadcrumbs.irq_lock);
 	wait = engine->breadcrumbs.irq_wait;
 	if (wait) {
-		bool wakeup = engine->irq_seqno_barrier;
-
-		/* We use a callback from the dma-fence to submit
+		/*
+		 * We use a callback from the dma-fence to submit
 		 * requests after waiting on our own requests. To
 		 * ensure minimum delay in queuing the next request to
 		 * hardware, signal the fence now rather than wait for
@@ -1163,19 +1179,26 @@ static void notify_ring(struct intel_engine_cs *engine)
 		 * and to handle coalescing of multiple seqno updates
 		 * and many waiters.
 		 */
-		if (i915_seqno_passed(intel_engine_get_seqno(engine),
-				      wait->seqno)) {
+		if (i915_seqno_passed(seqno, wait->seqno)) {
 			struct i915_request *waiter = wait->request;
 
-			wakeup = true;
-			if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
+			if (waiter &&
+			    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
 				      &waiter->fence.flags) &&
 			    intel_wait_check_request(wait, waiter))
 				rq = i915_request_get(waiter);
+
+			tsk = wait->tsk;
+		} else {
+			if (engine->irq_seqno_barrier &&
+			    i915_seqno_passed(seqno, wait->seqno - 1)) {
+				set_bit(ENGINE_IRQ_BREADCRUMB,
+					&engine->irq_posted);
+				tsk = wait->tsk;
+			}
 		}
 
-		if (wakeup)
-			wake_up_process(wait->tsk);
+		engine->breadcrumbs.irq_count++;
 	} else {
 		if (engine->breadcrumbs.irq_armed)
 			__intel_engine_disarm_breadcrumbs(engine);
@@ -1183,11 +1206,19 @@ static void notify_ring(struct intel_engine_cs *engine)
 	spin_unlock(&engine->breadcrumbs.irq_lock);
 
 	if (rq) {
-		dma_fence_signal(&rq->fence);
+		spin_lock(&rq->lock);
+		dma_fence_signal_locked(&rq->fence);
 		GEM_BUG_ON(!i915_request_completed(rq));
+		spin_unlock(&rq->lock);
+
 		i915_request_put(rq);
 	}
 
+	if (tsk && tsk->state & TASK_NORMAL)
+		wake_up_process(tsk);
+
+	rcu_read_unlock();
+
 	trace_intel_engine_notify(engine, wait);
 }
 
@@ -1234,9 +1265,9 @@ static u32 vlv_wa_c0_ei(struct drm_i915_private *dev_priv, u32 pm_iir)
 		c0 = max(render, media);
 		c0 *= 1000 * 100 << 8; /* to usecs and scale to threshold% */
 
-		if (c0 > time * rps->up_threshold)
+		if (c0 > time * rps->power.up_threshold)
 			events = GEN6_PM_RP_UP_THRESHOLD;
-		else if (c0 < time * rps->down_threshold)
+		else if (c0 < time * rps->power.down_threshold)
 			events = GEN6_PM_RP_DOWN_THRESHOLD;
 	}
 
@@ -1462,14 +1493,10 @@ static void snb_gt_irq_handler(struct drm_i915_private *dev_priv,
 static void
 gen8_cs_irq_handler(struct intel_engine_cs *engine, u32 iir)
 {
-	struct intel_engine_execlists * const execlists = &engine->execlists;
 	bool tasklet = false;
 
-	if (iir & GT_CONTEXT_SWITCH_INTERRUPT) {
-		if (READ_ONCE(engine->execlists.active))
-			tasklet = !test_and_set_bit(ENGINE_IRQ_EXECLIST,
-						    &engine->irq_posted);
-	}
+	if (iir & GT_CONTEXT_SWITCH_INTERRUPT)
+		tasklet = true;
 
 	if (iir & GT_RENDER_USER_INTERRUPT) {
 		notify_ring(engine);
@@ -1477,7 +1504,7 @@ gen8_cs_irq_handler(struct intel_engine_cs *engine, u32 iir)
 	}
 
 	if (tasklet)
-		tasklet_hi_schedule(&execlists->tasklet);
+		tasklet_hi_schedule(&engine->execlists.tasklet);
 }
 
 static void gen8_gt_irq_ack(struct drm_i915_private *i915,
@@ -1549,78 +1576,122 @@ static void gen8_gt_irq_handler(struct drm_i915_private *i915,
 	}
 }
 
-static bool bxt_port_hotplug_long_detect(enum port port, u32 val)
+static bool gen11_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_A:
+	switch (pin) {
+	case HPD_PORT_C:
+		return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC1);
+	case HPD_PORT_D:
+		return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC2);
+	case HPD_PORT_E:
+		return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC3);
+	case HPD_PORT_F:
+		return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC4);
+	default:
+		return false;
+	}
+}
+
+static bool bxt_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
+{
+	switch (pin) {
+	case HPD_PORT_A:
 		return val & PORTA_HOTPLUG_LONG_DETECT;
-	case PORT_B:
+	case HPD_PORT_B:
 		return val & PORTB_HOTPLUG_LONG_DETECT;
-	case PORT_C:
+	case HPD_PORT_C:
 		return val & PORTC_HOTPLUG_LONG_DETECT;
 	default:
 		return false;
 	}
 }
 
-static bool spt_port_hotplug2_long_detect(enum port port, u32 val)
+static bool icp_ddi_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
+{
+	switch (pin) {
+	case HPD_PORT_A:
+		return val & ICP_DDIA_HPD_LONG_DETECT;
+	case HPD_PORT_B:
+		return val & ICP_DDIB_HPD_LONG_DETECT;
+	default:
+		return false;
+	}
+}
+
+static bool icp_tc_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
+{
+	switch (pin) {
+	case HPD_PORT_C:
+		return val & ICP_TC_HPD_LONG_DETECT(PORT_TC1);
+	case HPD_PORT_D:
+		return val & ICP_TC_HPD_LONG_DETECT(PORT_TC2);
+	case HPD_PORT_E:
+		return val & ICP_TC_HPD_LONG_DETECT(PORT_TC3);
+	case HPD_PORT_F:
+		return val & ICP_TC_HPD_LONG_DETECT(PORT_TC4);
+	default:
+		return false;
+	}
+}
+
+static bool spt_port_hotplug2_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_E:
+	switch (pin) {
+	case HPD_PORT_E:
 		return val & PORTE_HOTPLUG_LONG_DETECT;
 	default:
 		return false;
 	}
 }
 
-static bool spt_port_hotplug_long_detect(enum port port, u32 val)
+static bool spt_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_A:
+	switch (pin) {
+	case HPD_PORT_A:
 		return val & PORTA_HOTPLUG_LONG_DETECT;
-	case PORT_B:
+	case HPD_PORT_B:
 		return val & PORTB_HOTPLUG_LONG_DETECT;
-	case PORT_C:
+	case HPD_PORT_C:
 		return val & PORTC_HOTPLUG_LONG_DETECT;
-	case PORT_D:
+	case HPD_PORT_D:
 		return val & PORTD_HOTPLUG_LONG_DETECT;
 	default:
 		return false;
 	}
 }
 
-static bool ilk_port_hotplug_long_detect(enum port port, u32 val)
+static bool ilk_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_A:
+	switch (pin) {
+	case HPD_PORT_A:
 		return val & DIGITAL_PORTA_HOTPLUG_LONG_DETECT;
 	default:
 		return false;
 	}
 }
 
-static bool pch_port_hotplug_long_detect(enum port port, u32 val)
+static bool pch_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_B:
+	switch (pin) {
+	case HPD_PORT_B:
 		return val & PORTB_HOTPLUG_LONG_DETECT;
-	case PORT_C:
+	case HPD_PORT_C:
 		return val & PORTC_HOTPLUG_LONG_DETECT;
-	case PORT_D:
+	case HPD_PORT_D:
 		return val & PORTD_HOTPLUG_LONG_DETECT;
 	default:
 		return false;
 	}
 }
 
-static bool i9xx_port_hotplug_long_detect(enum port port, u32 val)
+static bool i9xx_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_B:
+	switch (pin) {
+	case HPD_PORT_B:
 		return val & PORTB_HOTPLUG_INT_LONG_PULSE;
-	case PORT_C:
+	case HPD_PORT_C:
 		return val & PORTC_HOTPLUG_INT_LONG_PULSE;
-	case PORT_D:
+	case HPD_PORT_D:
 		return val & PORTD_HOTPLUG_INT_LONG_PULSE;
 	default:
 		return false;
@@ -1638,27 +1709,22 @@ static void intel_get_hpd_pins(struct drm_i915_private *dev_priv,
 			       u32 *pin_mask, u32 *long_mask,
 			       u32 hotplug_trigger, u32 dig_hotplug_reg,
 			       const u32 hpd[HPD_NUM_PINS],
-			       bool long_pulse_detect(enum port port, u32 val))
+			       bool long_pulse_detect(enum hpd_pin pin, u32 val))
 {
-	enum port port;
-	int i;
+	enum hpd_pin pin;
 
-	for_each_hpd_pin(i) {
-		if ((hpd[i] & hotplug_trigger) == 0)
+	for_each_hpd_pin(pin) {
+		if ((hpd[pin] & hotplug_trigger) == 0)
 			continue;
 
-		*pin_mask |= BIT(i);
+		*pin_mask |= BIT(pin);
 
-		port = intel_hpd_pin_to_port(dev_priv, i);
-		if (port == PORT_NONE)
-			continue;
-
-		if (long_pulse_detect(port, dig_hotplug_reg))
-			*long_mask |= BIT(i);
+		if (long_pulse_detect(pin, dig_hotplug_reg))
+			*long_mask |= BIT(pin);
 	}
 
-	DRM_DEBUG_DRIVER("hotplug event received, stat 0x%08x, dig 0x%08x, pins 0x%08x\n",
-			 hotplug_trigger, dig_hotplug_reg, *pin_mask);
+	DRM_DEBUG_DRIVER("hotplug event received, stat 0x%08x, dig 0x%08x, pins 0x%08x, long 0x%08x\n",
+			 hotplug_trigger, dig_hotplug_reg, *pin_mask, *long_mask);
 
 }
 
@@ -1680,69 +1746,34 @@ static void display_pipe_crc_irq_handler(struct drm_i915_private *dev_priv,
 					 uint32_t crc4)
 {
 	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[pipe];
-	struct intel_pipe_crc_entry *entry;
 	struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
-	struct drm_driver *driver = dev_priv->drm.driver;
 	uint32_t crcs[5];
-	int head, tail;
 
 	spin_lock(&pipe_crc->lock);
-	if (pipe_crc->source && !crtc->base.crc.opened) {
-		if (!pipe_crc->entries) {
-			spin_unlock(&pipe_crc->lock);
-			DRM_DEBUG_KMS("spurious interrupt\n");
-			return;
-		}
-
-		head = pipe_crc->head;
-		tail = pipe_crc->tail;
-
-		if (CIRC_SPACE(head, tail, INTEL_PIPE_CRC_ENTRIES_NR) < 1) {
-			spin_unlock(&pipe_crc->lock);
-			DRM_ERROR("CRC buffer overflowing\n");
-			return;
-		}
-
-		entry = &pipe_crc->entries[head];
-
-		entry->frame = driver->get_vblank_counter(&dev_priv->drm, pipe);
-		entry->crc[0] = crc0;
-		entry->crc[1] = crc1;
-		entry->crc[2] = crc2;
-		entry->crc[3] = crc3;
-		entry->crc[4] = crc4;
-
-		head = (head + 1) & (INTEL_PIPE_CRC_ENTRIES_NR - 1);
-		pipe_crc->head = head;
-
-		spin_unlock(&pipe_crc->lock);
-
-		wake_up_interruptible(&pipe_crc->wq);
-	} else {
-		/*
-		 * For some not yet identified reason, the first CRC is
-		 * bonkers. So let's just wait for the next vblank and read
-		 * out the buggy result.
-		 *
-		 * On GEN8+ sometimes the second CRC is bonkers as well, so
-		 * don't trust that one either.
-		 */
-		if (pipe_crc->skipped <= 0 ||
-		    (INTEL_GEN(dev_priv) >= 8 && pipe_crc->skipped == 1)) {
-			pipe_crc->skipped++;
-			spin_unlock(&pipe_crc->lock);
-			return;
-		}
+	/*
+	 * For some not yet identified reason, the first CRC is
+	 * bonkers. So let's just wait for the next vblank and read
+	 * out the buggy result.
+	 *
+	 * On GEN8+ sometimes the second CRC is bonkers as well, so
+	 * don't trust that one either.
+	 */
+	if (pipe_crc->skipped <= 0 ||
+	    (INTEL_GEN(dev_priv) >= 8 && pipe_crc->skipped == 1)) {
+		pipe_crc->skipped++;
 		spin_unlock(&pipe_crc->lock);
-		crcs[0] = crc0;
-		crcs[1] = crc1;
-		crcs[2] = crc2;
-		crcs[3] = crc3;
-		crcs[4] = crc4;
-		drm_crtc_add_crc_entry(&crtc->base, true,
-				       drm_crtc_accurate_vblank_count(&crtc->base),
-				       crcs);
+		return;
 	}
+	spin_unlock(&pipe_crc->lock);
+
+	crcs[0] = crc0;
+	crcs[1] = crc1;
+	crcs[2] = crc2;
+	crcs[3] = crc3;
+	crcs[4] = crc4;
+	drm_crtc_add_crc_entry(&crtc->base, true,
+				drm_crtc_accurate_vblank_count(&crtc->base),
+				crcs);
 }
 #else
 static inline void
@@ -2136,7 +2167,6 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 
 		I915_WRITE(VLV_IER, ier);
 		I915_WRITE(VLV_MASTER_IER, MASTER_INTERRUPT_ENABLE);
-		POSTING_READ(VLV_MASTER_IER);
 
 		if (gt_iir)
 			snb_gt_irq_handler(dev_priv, gt_iir);
@@ -2221,7 +2251,6 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg)
 
 		I915_WRITE(VLV_IER, ier);
 		I915_WRITE(GEN8_MASTER_IRQ, GEN8_MASTER_IRQ_CONTROL);
-		POSTING_READ(GEN8_MASTER_IRQ);
 
 		gen8_gt_irq_handler(dev_priv, master_ctl, gt_iir);
 
@@ -2390,6 +2419,43 @@ static void cpt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 		cpt_serr_int_handler(dev_priv);
 }
 
+static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
+{
+	u32 ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_ICP;
+	u32 tc_hotplug_trigger = pch_iir & SDE_TC_MASK_ICP;
+	u32 pin_mask = 0, long_mask = 0;
+
+	if (ddi_hotplug_trigger) {
+		u32 dig_hotplug_reg;
+
+		dig_hotplug_reg = I915_READ(SHOTPLUG_CTL_DDI);
+		I915_WRITE(SHOTPLUG_CTL_DDI, dig_hotplug_reg);
+
+		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
+				   ddi_hotplug_trigger,
+				   dig_hotplug_reg, hpd_icp,
+				   icp_ddi_port_hotplug_long_detect);
+	}
+
+	if (tc_hotplug_trigger) {
+		u32 dig_hotplug_reg;
+
+		dig_hotplug_reg = I915_READ(SHOTPLUG_CTL_TC);
+		I915_WRITE(SHOTPLUG_CTL_TC, dig_hotplug_reg);
+
+		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
+				   tc_hotplug_trigger,
+				   dig_hotplug_reg, hpd_icp,
+				   icp_tc_port_hotplug_long_detect);
+	}
+
+	if (pin_mask)
+		intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
+
+	if (pch_iir & SDE_GMBUS_ICP)
+		gmbus_irq_handler(dev_priv);
+}
+
 static void spt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 {
 	u32 hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK_SPT &
@@ -2553,7 +2619,6 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	/* disable master interrupt before clearing iir  */
 	de_ier = I915_READ(DEIER);
 	I915_WRITE(DEIER, de_ier & ~DE_MASTER_IRQ_CONTROL);
-	POSTING_READ(DEIER);
 
 	/* Disable south interrupts. We'll only write to SDEIIR once, so further
 	 * interrupts will will be stored on its back queue, and then we'll be
@@ -2563,7 +2628,6 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	if (!HAS_PCH_NOP(dev_priv)) {
 		sde_ier = I915_READ(SDEIER);
 		I915_WRITE(SDEIER, 0);
-		POSTING_READ(SDEIER);
 	}
 
 	/* Find, clear, then process each source of interrupt */
@@ -2598,11 +2662,8 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	}
 
 	I915_WRITE(DEIER, de_ier);
-	POSTING_READ(DEIER);
-	if (!HAS_PCH_NOP(dev_priv)) {
+	if (!HAS_PCH_NOP(dev_priv))
 		I915_WRITE(SDEIER, sde_ier);
-		POSTING_READ(SDEIER);
-	}
 
 	/* IRQs are synced during runtime_suspend, we don't require a wakeref */
 	enable_rpm_wakeref_asserts(dev_priv);
@@ -2626,6 +2687,40 @@ static void bxt_hpd_irq_handler(struct drm_i915_private *dev_priv,
 	intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
 }
 
+static void gen11_hpd_irq_handler(struct drm_i915_private *dev_priv, u32 iir)
+{
+	u32 pin_mask = 0, long_mask = 0;
+	u32 trigger_tc = iir & GEN11_DE_TC_HOTPLUG_MASK;
+	u32 trigger_tbt = iir & GEN11_DE_TBT_HOTPLUG_MASK;
+
+	if (trigger_tc) {
+		u32 dig_hotplug_reg;
+
+		dig_hotplug_reg = I915_READ(GEN11_TC_HOTPLUG_CTL);
+		I915_WRITE(GEN11_TC_HOTPLUG_CTL, dig_hotplug_reg);
+
+		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, trigger_tc,
+				   dig_hotplug_reg, hpd_gen11,
+				   gen11_port_hotplug_long_detect);
+	}
+
+	if (trigger_tbt) {
+		u32 dig_hotplug_reg;
+
+		dig_hotplug_reg = I915_READ(GEN11_TBT_HOTPLUG_CTL);
+		I915_WRITE(GEN11_TBT_HOTPLUG_CTL, dig_hotplug_reg);
+
+		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, trigger_tbt,
+				   dig_hotplug_reg, hpd_gen11,
+				   gen11_port_hotplug_long_detect);
+	}
+
+	if (pin_mask)
+		intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
+	else
+		DRM_ERROR("Unexpected DE HPD interrupt 0x%08x\n", iir);
+}
+
 static irqreturn_t
 gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 {
@@ -2661,6 +2756,17 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 			DRM_ERROR("The master control interrupt lied (DE MISC)!\n");
 	}
 
+	if (INTEL_GEN(dev_priv) >= 11 && (master_ctl & GEN11_DE_HPD_IRQ)) {
+		iir = I915_READ(GEN11_DE_HPD_IIR);
+		if (iir) {
+			I915_WRITE(GEN11_DE_HPD_IIR, iir);
+			ret = IRQ_HANDLED;
+			gen11_hpd_irq_handler(dev_priv, iir);
+		} else {
+			DRM_ERROR("The master control interrupt lied, (DE HPD)!\n");
+		}
+	}
+
 	if (master_ctl & GEN8_DE_PORT_IRQ) {
 		iir = I915_READ(GEN8_DE_PORT_IIR);
 		if (iir) {
@@ -2676,7 +2782,11 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 					    GEN9_AUX_CHANNEL_C |
 					    GEN9_AUX_CHANNEL_D;
 
-			if (IS_CNL_WITH_PORT_F(dev_priv))
+			if (INTEL_GEN(dev_priv) >= 11)
+				tmp_mask |= ICL_AUX_CHANNEL_E;
+
+			if (IS_CNL_WITH_PORT_F(dev_priv) ||
+			    INTEL_GEN(dev_priv) >= 11)
 				tmp_mask |= CNL_AUX_CHANNEL_F;
 
 			if (iir & tmp_mask) {
@@ -2760,8 +2870,11 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 			I915_WRITE(SDEIIR, iir);
 			ret = IRQ_HANDLED;
 
-			if (HAS_PCH_SPT(dev_priv) || HAS_PCH_KBP(dev_priv) ||
-			    HAS_PCH_CNP(dev_priv))
+			if (HAS_PCH_ICP(dev_priv))
+				icp_irq_handler(dev_priv, iir);
+			else if (HAS_PCH_SPT(dev_priv) ||
+				 HAS_PCH_KBP(dev_priv) ||
+				 HAS_PCH_CNP(dev_priv))
 				spt_irq_handler(dev_priv, iir);
 			else
 				cpt_irq_handler(dev_priv, iir);
@@ -2978,11 +3091,44 @@ gen11_gt_irq_handler(struct drm_i915_private * const i915,
 	spin_unlock(&i915->irq_lock);
 }
 
+static void
+gen11_gu_misc_irq_ack(struct drm_i915_private *dev_priv, const u32 master_ctl,
+		      u32 *iir)
+{
+	void __iomem * const regs = dev_priv->regs;
+
+	if (!(master_ctl & GEN11_GU_MISC_IRQ))
+		return;
+
+	*iir = raw_reg_read(regs, GEN11_GU_MISC_IIR);
+	if (likely(*iir))
+		raw_reg_write(regs, GEN11_GU_MISC_IIR, *iir);
+}
+
+static void
+gen11_gu_misc_irq_handler(struct drm_i915_private *dev_priv,
+			  const u32 master_ctl, const u32 iir)
+{
+	if (!(master_ctl & GEN11_GU_MISC_IRQ))
+		return;
+
+	if (unlikely(!iir)) {
+		DRM_ERROR("GU_MISC iir blank!\n");
+		return;
+	}
+
+	if (iir & GEN11_GU_MISC_GSE)
+		intel_opregion_asle_intr(dev_priv);
+	else
+		DRM_ERROR("Unexpected GU_MISC interrupt 0x%x\n", iir);
+}
+
 static irqreturn_t gen11_irq_handler(int irq, void *arg)
 {
 	struct drm_i915_private * const i915 = to_i915(arg);
 	void __iomem * const regs = i915->regs;
 	u32 master_ctl;
+	u32 gu_misc_iir;
 
 	if (!intel_irqs_enabled(i915))
 		return IRQ_NONE;
@@ -3011,9 +3157,13 @@ static irqreturn_t gen11_irq_handler(int irq, void *arg)
 		enable_rpm_wakeref_asserts(i915);
 	}
 
+	gen11_gu_misc_irq_ack(i915, master_ctl, &gu_misc_iir);
+
 	/* Acknowledge and enable interrupts. */
 	raw_reg_write(regs, GEN11_GFX_MSTR_IRQ, GEN11_MASTER_IRQ | master_ctl);
 
+	gen11_gu_misc_irq_handler(i915, master_ctl, gu_misc_iir);
+
 	return IRQ_HANDLED;
 }
 
@@ -3089,7 +3239,7 @@ static void i915_clear_error_registers(struct drm_i915_private *dev_priv)
 		 */
 		DRM_DEBUG_DRIVER("EIR stuck: 0x%08x, masking\n", eir);
 		I915_WRITE(EMR, I915_READ(EMR) | eir);
-		I915_WRITE(IIR, I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT);
+		I915_WRITE(IIR, I915_MASTER_ERROR_INTERRUPT);
 	}
 }
 
@@ -3500,7 +3650,12 @@ static void gen11_irq_reset(struct drm_device *dev)
 
 	GEN3_IRQ_RESET(GEN8_DE_PORT_);
 	GEN3_IRQ_RESET(GEN8_DE_MISC_);
+	GEN3_IRQ_RESET(GEN11_DE_HPD_);
+	GEN3_IRQ_RESET(GEN11_GU_MISC_);
 	GEN3_IRQ_RESET(GEN8_PCU_);
+
+	if (HAS_PCH_ICP(dev_priv))
+		GEN3_IRQ_RESET(SDE);
 }
 
 void gen8_irq_power_well_post_enable(struct drm_i915_private *dev_priv,
@@ -3617,6 +3772,73 @@ static void ibx_hpd_irq_setup(struct drm_i915_private *dev_priv)
 	ibx_hpd_detection_setup(dev_priv);
 }
 
+static void icp_hpd_detection_setup(struct drm_i915_private *dev_priv)
+{
+	u32 hotplug;
+
+	hotplug = I915_READ(SHOTPLUG_CTL_DDI);
+	hotplug |= ICP_DDIA_HPD_ENABLE |
+		   ICP_DDIB_HPD_ENABLE;
+	I915_WRITE(SHOTPLUG_CTL_DDI, hotplug);
+
+	hotplug = I915_READ(SHOTPLUG_CTL_TC);
+	hotplug |= ICP_TC_HPD_ENABLE(PORT_TC1) |
+		   ICP_TC_HPD_ENABLE(PORT_TC2) |
+		   ICP_TC_HPD_ENABLE(PORT_TC3) |
+		   ICP_TC_HPD_ENABLE(PORT_TC4);
+	I915_WRITE(SHOTPLUG_CTL_TC, hotplug);
+}
+
+static void icp_hpd_irq_setup(struct drm_i915_private *dev_priv)
+{
+	u32 hotplug_irqs, enabled_irqs;
+
+	hotplug_irqs = SDE_DDI_MASK_ICP | SDE_TC_MASK_ICP;
+	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_icp);
+
+	ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs);
+
+	icp_hpd_detection_setup(dev_priv);
+}
+
+static void gen11_hpd_detection_setup(struct drm_i915_private *dev_priv)
+{
+	u32 hotplug;
+
+	hotplug = I915_READ(GEN11_TC_HOTPLUG_CTL);
+	hotplug |= GEN11_HOTPLUG_CTL_ENABLE(PORT_TC1) |
+		   GEN11_HOTPLUG_CTL_ENABLE(PORT_TC2) |
+		   GEN11_HOTPLUG_CTL_ENABLE(PORT_TC3) |
+		   GEN11_HOTPLUG_CTL_ENABLE(PORT_TC4);
+	I915_WRITE(GEN11_TC_HOTPLUG_CTL, hotplug);
+
+	hotplug = I915_READ(GEN11_TBT_HOTPLUG_CTL);
+	hotplug |= GEN11_HOTPLUG_CTL_ENABLE(PORT_TC1) |
+		   GEN11_HOTPLUG_CTL_ENABLE(PORT_TC2) |
+		   GEN11_HOTPLUG_CTL_ENABLE(PORT_TC3) |
+		   GEN11_HOTPLUG_CTL_ENABLE(PORT_TC4);
+	I915_WRITE(GEN11_TBT_HOTPLUG_CTL, hotplug);
+}
+
+static void gen11_hpd_irq_setup(struct drm_i915_private *dev_priv)
+{
+	u32 hotplug_irqs, enabled_irqs;
+	u32 val;
+
+	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_gen11);
+	hotplug_irqs = GEN11_DE_TC_HOTPLUG_MASK | GEN11_DE_TBT_HOTPLUG_MASK;
+
+	val = I915_READ(GEN11_DE_HPD_IMR);
+	val &= ~hotplug_irqs;
+	I915_WRITE(GEN11_DE_HPD_IMR, val);
+	POSTING_READ(GEN11_DE_HPD_IMR);
+
+	gen11_hpd_detection_setup(dev_priv);
+
+	if (HAS_PCH_ICP(dev_priv))
+		icp_hpd_irq_setup(dev_priv);
+}
+
 static void spt_hpd_detection_setup(struct drm_i915_private *dev_priv)
 {
 	u32 val, hotplug;
@@ -3943,9 +4165,12 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 	uint32_t de_pipe_enables;
 	u32 de_port_masked = GEN8_AUX_CHANNEL_A;
 	u32 de_port_enables;
-	u32 de_misc_masked = GEN8_DE_MISC_GSE | GEN8_DE_EDP_PSR;
+	u32 de_misc_masked = GEN8_DE_EDP_PSR;
 	enum pipe pipe;
 
+	if (INTEL_GEN(dev_priv) <= 10)
+		de_misc_masked |= GEN8_DE_MISC_GSE;
+
 	if (INTEL_GEN(dev_priv) >= 9) {
 		de_pipe_masked |= GEN9_DE_PIPE_IRQ_FAULT_ERRORS;
 		de_port_masked |= GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C |
@@ -3956,7 +4181,10 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 		de_pipe_masked |= GEN8_DE_PIPE_IRQ_FAULT_ERRORS;
 	}
 
-	if (IS_CNL_WITH_PORT_F(dev_priv))
+	if (INTEL_GEN(dev_priv) >= 11)
+		de_port_masked |= ICL_AUX_CHANNEL_E;
+
+	if (IS_CNL_WITH_PORT_F(dev_priv) || INTEL_GEN(dev_priv) >= 11)
 		de_port_masked |= CNL_AUX_CHANNEL_F;
 
 	de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK |
@@ -3984,10 +4212,18 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 	GEN3_IRQ_INIT(GEN8_DE_PORT_, ~de_port_masked, de_port_enables);
 	GEN3_IRQ_INIT(GEN8_DE_MISC_, ~de_misc_masked, de_misc_masked);
 
-	if (IS_GEN9_LP(dev_priv))
+	if (INTEL_GEN(dev_priv) >= 11) {
+		u32 de_hpd_masked = 0;
+		u32 de_hpd_enables = GEN11_DE_TC_HOTPLUG_MASK |
+				     GEN11_DE_TBT_HOTPLUG_MASK;
+
+		GEN3_IRQ_INIT(GEN11_DE_HPD_, ~de_hpd_masked, de_hpd_enables);
+		gen11_hpd_detection_setup(dev_priv);
+	} else if (IS_GEN9_LP(dev_priv)) {
 		bxt_hpd_detection_setup(dev_priv);
-	else if (IS_BROADWELL(dev_priv))
+	} else if (IS_BROADWELL(dev_priv)) {
 		ilk_hpd_detection_setup(dev_priv);
+	}
 }
 
 static int gen8_irq_postinstall(struct drm_device *dev)
@@ -4036,13 +4272,34 @@ static void gen11_gt_irq_postinstall(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN11_GPM_WGBOXPERF_INTR_MASK,  ~0);
 }
 
+static void icp_irq_postinstall(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	u32 mask = SDE_GMBUS_ICP;
+
+	WARN_ON(I915_READ(SDEIER) != 0);
+	I915_WRITE(SDEIER, 0xffffffff);
+	POSTING_READ(SDEIER);
+
+	gen3_assert_iir_is_zero(dev_priv, SDEIIR);
+	I915_WRITE(SDEIMR, ~mask);
+
+	icp_hpd_detection_setup(dev_priv);
+}
+
 static int gen11_irq_postinstall(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 gu_misc_masked = GEN11_GU_MISC_GSE;
+
+	if (HAS_PCH_ICP(dev_priv))
+		icp_irq_postinstall(dev);
 
 	gen11_gt_irq_postinstall(dev_priv);
 	gen8_de_irq_postinstall(dev_priv);
 
+	GEN3_IRQ_INIT(GEN11_GU_MISC_, ~gu_misc_masked, gu_misc_masked);
+
 	I915_WRITE(GEN11_DISPLAY_INT_CTL, GEN11_DISPLAY_IRQ_ENABLE);
 
 	I915_WRITE(GEN11_GFX_MSTR_IRQ, GEN11_MASTER_IRQ);
@@ -4090,11 +4347,13 @@ static int i8xx_irq_postinstall(struct drm_device *dev)
 	/* Unmask the interrupts that we always want on. */
 	dev_priv->irq_mask =
 		~(I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
-		  I915_DISPLAY_PIPE_B_EVENT_INTERRUPT);
+		  I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
+		  I915_MASTER_ERROR_INTERRUPT);
 
 	enable_mask =
 		I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
 		I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
+		I915_MASTER_ERROR_INTERRUPT |
 		I915_USER_INTERRUPT;
 
 	GEN2_IRQ_INIT(, dev_priv->irq_mask, enable_mask);
@@ -4109,6 +4368,81 @@ static int i8xx_irq_postinstall(struct drm_device *dev)
 	return 0;
 }
 
+static void i8xx_error_irq_ack(struct drm_i915_private *dev_priv,
+			       u16 *eir, u16 *eir_stuck)
+{
+	u16 emr;
+
+	*eir = I915_READ16(EIR);
+
+	if (*eir)
+		I915_WRITE16(EIR, *eir);
+
+	*eir_stuck = I915_READ16(EIR);
+	if (*eir_stuck == 0)
+		return;
+
+	/*
+	 * Toggle all EMR bits to make sure we get an edge
+	 * in the ISR master error bit if we don't clear
+	 * all the EIR bits. Otherwise the edge triggered
+	 * IIR on i965/g4x wouldn't notice that an interrupt
+	 * is still pending. Also some EIR bits can't be
+	 * cleared except by handling the underlying error
+	 * (or by a GPU reset) so we mask any bit that
+	 * remains set.
+	 */
+	emr = I915_READ16(EMR);
+	I915_WRITE16(EMR, 0xffff);
+	I915_WRITE16(EMR, emr | *eir_stuck);
+}
+
+static void i8xx_error_irq_handler(struct drm_i915_private *dev_priv,
+				   u16 eir, u16 eir_stuck)
+{
+	DRM_DEBUG("Master Error: EIR 0x%04x\n", eir);
+
+	if (eir_stuck)
+		DRM_DEBUG_DRIVER("EIR stuck: 0x%04x, masked\n", eir_stuck);
+}
+
+static void i9xx_error_irq_ack(struct drm_i915_private *dev_priv,
+			       u32 *eir, u32 *eir_stuck)
+{
+	u32 emr;
+
+	*eir = I915_READ(EIR);
+
+	I915_WRITE(EIR, *eir);
+
+	*eir_stuck = I915_READ(EIR);
+	if (*eir_stuck == 0)
+		return;
+
+	/*
+	 * Toggle all EMR bits to make sure we get an edge
+	 * in the ISR master error bit if we don't clear
+	 * all the EIR bits. Otherwise the edge triggered
+	 * IIR on i965/g4x wouldn't notice that an interrupt
+	 * is still pending. Also some EIR bits can't be
+	 * cleared except by handling the underlying error
+	 * (or by a GPU reset) so we mask any bit that
+	 * remains set.
+	 */
+	emr = I915_READ(EMR);
+	I915_WRITE(EMR, 0xffffffff);
+	I915_WRITE(EMR, emr | *eir_stuck);
+}
+
+static void i9xx_error_irq_handler(struct drm_i915_private *dev_priv,
+				   u32 eir, u32 eir_stuck)
+{
+	DRM_DEBUG("Master Error, EIR 0x%08x\n", eir);
+
+	if (eir_stuck)
+		DRM_DEBUG_DRIVER("EIR stuck: 0x%08x, masked\n", eir_stuck);
+}
+
 static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 {
 	struct drm_device *dev = arg;
@@ -4123,6 +4457,7 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 
 	do {
 		u32 pipe_stats[I915_MAX_PIPES] = {};
+		u16 eir = 0, eir_stuck = 0;
 		u16 iir;
 
 		iir = I915_READ16(IIR);
@@ -4135,13 +4470,16 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 		 * signalled in iir */
 		i9xx_pipestat_irq_ack(dev_priv, iir, pipe_stats);
 
+		if (iir & I915_MASTER_ERROR_INTERRUPT)
+			i8xx_error_irq_ack(dev_priv, &eir, &eir_stuck);
+
 		I915_WRITE16(IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
 			notify_ring(dev_priv->engine[RCS]);
 
-		if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT)
-			DRM_DEBUG("Command parser error, iir 0x%08x\n", iir);
+		if (iir & I915_MASTER_ERROR_INTERRUPT)
+			i8xx_error_irq_handler(dev_priv, eir, eir_stuck);
 
 		i8xx_pipestat_irq_handler(dev_priv, iir, pipe_stats);
 	} while (0);
@@ -4179,12 +4517,14 @@ static int i915_irq_postinstall(struct drm_device *dev)
 	dev_priv->irq_mask =
 		~(I915_ASLE_INTERRUPT |
 		  I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
-		  I915_DISPLAY_PIPE_B_EVENT_INTERRUPT);
+		  I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
+		  I915_MASTER_ERROR_INTERRUPT);
 
 	enable_mask =
 		I915_ASLE_INTERRUPT |
 		I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
 		I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
+		I915_MASTER_ERROR_INTERRUPT |
 		I915_USER_INTERRUPT;
 
 	if (I915_HAS_HOTPLUG(dev_priv)) {
@@ -4222,6 +4562,7 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 
 	do {
 		u32 pipe_stats[I915_MAX_PIPES] = {};
+		u32 eir = 0, eir_stuck = 0;
 		u32 hotplug_status = 0;
 		u32 iir;
 
@@ -4239,13 +4580,16 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 		 * signalled in iir */
 		i9xx_pipestat_irq_ack(dev_priv, iir, pipe_stats);
 
+		if (iir & I915_MASTER_ERROR_INTERRUPT)
+			i9xx_error_irq_ack(dev_priv, &eir, &eir_stuck);
+
 		I915_WRITE(IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
 			notify_ring(dev_priv->engine[RCS]);
 
-		if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT)
-			DRM_DEBUG("Command parser error, iir 0x%08x\n", iir);
+		if (iir & I915_MASTER_ERROR_INTERRUPT)
+			i9xx_error_irq_handler(dev_priv, eir, eir_stuck);
 
 		if (hotplug_status)
 			i9xx_hpd_irq_handler(dev_priv, hotplug_status);
@@ -4299,14 +4643,14 @@ static int i965_irq_postinstall(struct drm_device *dev)
 		  I915_DISPLAY_PORT_INTERRUPT |
 		  I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
 		  I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
-		  I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT);
+		  I915_MASTER_ERROR_INTERRUPT);
 
 	enable_mask =
 		I915_ASLE_INTERRUPT |
 		I915_DISPLAY_PORT_INTERRUPT |
 		I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
 		I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
-		I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT |
+		I915_MASTER_ERROR_INTERRUPT |
 		I915_USER_INTERRUPT;
 
 	if (IS_G4X(dev_priv))
@@ -4366,6 +4710,7 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 
 	do {
 		u32 pipe_stats[I915_MAX_PIPES] = {};
+		u32 eir = 0, eir_stuck = 0;
 		u32 hotplug_status = 0;
 		u32 iir;
 
@@ -4382,6 +4727,9 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		 * signalled in iir */
 		i9xx_pipestat_irq_ack(dev_priv, iir, pipe_stats);
 
+		if (iir & I915_MASTER_ERROR_INTERRUPT)
+			i9xx_error_irq_ack(dev_priv, &eir, &eir_stuck);
+
 		I915_WRITE(IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
@@ -4390,8 +4738,8 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		if (iir & I915_BSD_USER_INTERRUPT)
 			notify_ring(dev_priv->engine[VCS]);
 
-		if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT)
-			DRM_DEBUG("Command parser error, iir 0x%08x\n", iir);
+		if (iir & I915_MASTER_ERROR_INTERRUPT)
+			i9xx_error_irq_handler(dev_priv, eir, eir_stuck);
 
 		if (hotplug_status)
 			i9xx_hpd_irq_handler(dev_priv, hotplug_status);
@@ -4506,7 +4854,7 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
 		dev->driver->irq_uninstall = gen11_irq_reset;
 		dev->driver->enable_vblank = gen8_enable_vblank;
 		dev->driver->disable_vblank = gen8_disable_vblank;
-		dev_priv->display.hpd_irq_setup = spt_hpd_irq_setup;
+		dev_priv->display.hpd_irq_setup = gen11_hpd_irq_setup;
 	} else if (INTEL_GEN(dev_priv) >= 8) {
 		dev->driver->irq_handler = gen8_irq_handler;
 		dev->driver->irq_preinstall = gen8_irq_reset;
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index 66ea3552c63e..295e981e4a39 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -44,10 +44,6 @@ i915_param_named(modeset, int, 0400,
 	"Use kernel modesetting [KMS] (0=disable, "
 	"1=on, -1=force vga console preference [default])");
 
-i915_param_named_unsafe(panel_ignore_lid, int, 0600,
-	"Override lid status (0=autodetect, 1=autodetect disabled [default], "
-	"-1=force lid closed, -2=force lid open)");
-
 i915_param_named_unsafe(enable_dc, int, 0400,
 	"Enable power-saving display C-states. "
 	"(-1=auto [default]; 0=disable; 1=up to DC5; 2=up to DC6)");
@@ -92,7 +88,7 @@ i915_param_named_unsafe(enable_ppgtt, int, 0400,
 
 i915_param_named_unsafe(enable_psr, int, 0600,
 	"Enable PSR "
-	"(0=disabled, 1=enabled - link mode chosen per-platform, 2=force link-standby mode, 3=force link-off mode) "
+	"(0=disabled, 1=enabled) "
 	"Default: -1 (use per-chip default)");
 
 i915_param_named_unsafe(alpha_support, bool, 0400,
@@ -130,9 +126,6 @@ i915_param_named_unsafe(invert_brightness, int, 0600,
 i915_param_named(disable_display, bool, 0400,
 	"Disable display (default: false)");
 
-i915_param_named_unsafe(enable_cmd_parser, bool, 0400,
-	"Enable command parsing (true=enabled [default], false=disabled)");
-
 i915_param_named(mmio_debug, int, 0600,
 	"Enable the MMIO debug code for the first N failures (default: off). "
 	"This may negatively affect performance.");
diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h
index 6684025b7af8..6c4d4a21474b 100644
--- a/drivers/gpu/drm/i915/i915_params.h
+++ b/drivers/gpu/drm/i915/i915_params.h
@@ -36,7 +36,6 @@ struct drm_printer;
 #define I915_PARAMS_FOR_EACH(param) \
 	param(char *, vbt_firmware, NULL) \
 	param(int, modeset, -1) \
-	param(int, panel_ignore_lid, 1) \
 	param(int, lvds_channel_mode, 0) \
 	param(int, panel_use_ssc, -1) \
 	param(int, vbt_sdvo_panel_type, -1) \
@@ -58,7 +57,6 @@ struct drm_printer;
 	param(unsigned int, inject_load_failure, 0) \
 	/* leave bools at the end to not create holes */ \
 	param(bool, alpha_support, IS_ENABLED(CONFIG_DRM_I915_ALPHA_SUPPORT)) \
-	param(bool, enable_cmd_parser, true) \
 	param(bool, enable_hangcheck, true) \
 	param(bool, fastboot, false) \
 	param(bool, prefault_disable, false) \
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 4364922e935d..6a4d1388ad2d 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -340,7 +340,6 @@ static const struct intel_device_info intel_valleyview_info = {
 	GEN(7),
 	.is_lp = 1,
 	.num_pipes = 2,
-	.has_psr = 1,
 	.has_runtime_pm = 1,
 	.has_rc6 = 1,
 	.has_gmch_display = 1,
@@ -433,7 +432,6 @@ static const struct intel_device_info intel_cherryview_info = {
 	.is_lp = 1,
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
 	.has_64bit_reloc = 1,
-	.has_psr = 1,
 	.has_runtime_pm = 1,
 	.has_resource_streamer = 1,
 	.has_rc6 = 1,
@@ -659,12 +657,15 @@ static const struct pci_device_id pciidlist[] = {
 	INTEL_KBL_GT2_IDS(&intel_kabylake_gt2_info),
 	INTEL_KBL_GT3_IDS(&intel_kabylake_gt3_info),
 	INTEL_KBL_GT4_IDS(&intel_kabylake_gt3_info),
+	INTEL_AML_GT2_IDS(&intel_kabylake_gt2_info),
 	INTEL_CFL_S_GT1_IDS(&intel_coffeelake_gt1_info),
 	INTEL_CFL_S_GT2_IDS(&intel_coffeelake_gt2_info),
 	INTEL_CFL_H_GT2_IDS(&intel_coffeelake_gt2_info),
-	INTEL_CFL_U_GT1_IDS(&intel_coffeelake_gt1_info),
 	INTEL_CFL_U_GT2_IDS(&intel_coffeelake_gt2_info),
 	INTEL_CFL_U_GT3_IDS(&intel_coffeelake_gt3_info),
+	INTEL_WHL_U_GT1_IDS(&intel_coffeelake_gt1_info),
+	INTEL_WHL_U_GT2_IDS(&intel_coffeelake_gt2_info),
+	INTEL_WHL_U_GT3_IDS(&intel_coffeelake_gt3_info),
 	INTEL_CNL_IDS(&intel_cannonlake_info),
 	INTEL_ICL_11_IDS(&intel_icelake_11_info),
 	{0, 0, 0}
@@ -673,10 +674,16 @@ MODULE_DEVICE_TABLE(pci, pciidlist);
 
 static void i915_pci_remove(struct pci_dev *pdev)
 {
-	struct drm_device *dev = pci_get_drvdata(pdev);
+	struct drm_device *dev;
+
+	dev = pci_get_drvdata(pdev);
+	if (!dev) /* driver load aborted, nothing to cleanup */
+		return;
 
 	i915_driver_unload(dev);
 	drm_dev_put(dev);
+
+	pci_set_drvdata(pdev, NULL);
 }
 
 static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
@@ -711,6 +718,11 @@ static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		return err;
 
+	if (i915_inject_load_failure()) {
+		i915_pci_remove(pdev);
+		return -ENODEV;
+	}
+
 	err = i915_live_selftests(pdev);
 	if (err) {
 		i915_pci_remove(pdev);
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 019bd2d073ad..6bf10952c724 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -315,7 +315,7 @@ static u32 i915_oa_max_sample_rate = 100000;
  * code assumes all reports have a power-of-two size and ~(size - 1) can
  * be used as a mask to align the OA tail pointer.
  */
-static struct i915_oa_format hsw_oa_formats[I915_OA_FORMAT_MAX] = {
+static const struct i915_oa_format hsw_oa_formats[I915_OA_FORMAT_MAX] = {
 	[I915_OA_FORMAT_A13]	    = { 0, 64 },
 	[I915_OA_FORMAT_A29]	    = { 1, 128 },
 	[I915_OA_FORMAT_A13_B8_C8]  = { 2, 128 },
@@ -326,7 +326,7 @@ static struct i915_oa_format hsw_oa_formats[I915_OA_FORMAT_MAX] = {
 	[I915_OA_FORMAT_C4_B8]	    = { 7, 64 },
 };
 
-static struct i915_oa_format gen8_plus_oa_formats[I915_OA_FORMAT_MAX] = {
+static const struct i915_oa_format gen8_plus_oa_formats[I915_OA_FORMAT_MAX] = {
 	[I915_OA_FORMAT_A12]		    = { 0, 64 },
 	[I915_OA_FORMAT_A12_B8_C8]	    = { 2, 128 },
 	[I915_OA_FORMAT_A32u40_A4u32_B8_C8] = { 5, 256 },
@@ -737,12 +737,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 			continue;
 		}
 
-		/*
-		 * XXX: Just keep the lower 21 bits for now since I'm not
-		 * entirely sure if the HW touches any of the higher bits in
-		 * this field
-		 */
-		ctx_id = report32[2] & 0x1fffff;
+		ctx_id = report32[2] & dev_priv->perf.oa.specific_ctx_id_mask;
 
 		/*
 		 * Squash whatever is in the CTX_ID field if it's marked as
@@ -1203,6 +1198,33 @@ static int i915_oa_read(struct i915_perf_stream *stream,
 	return dev_priv->perf.oa.ops.read(stream, buf, count, offset);
 }
 
+static struct intel_context *oa_pin_context(struct drm_i915_private *i915,
+					    struct i915_gem_context *ctx)
+{
+	struct intel_engine_cs *engine = i915->engine[RCS];
+	struct intel_context *ce;
+	int ret;
+
+	ret = i915_mutex_lock_interruptible(&i915->drm);
+	if (ret)
+		return ERR_PTR(ret);
+
+	/*
+	 * As the ID is the gtt offset of the context's vma we
+	 * pin the vma to ensure the ID remains fixed.
+	 *
+	 * NB: implied RCS engine...
+	 */
+	ce = intel_context_pin(ctx, engine);
+	mutex_unlock(&i915->drm.struct_mutex);
+	if (IS_ERR(ce))
+		return ce;
+
+	i915->perf.oa.pinned_ctx = ce;
+
+	return ce;
+}
+
 /**
  * oa_get_render_ctx_id - determine and hold ctx hw id
  * @stream: An i915-perf stream opened for OA metrics
@@ -1215,40 +1237,76 @@ static int i915_oa_read(struct i915_perf_stream *stream,
  */
 static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct drm_i915_private *i915 = stream->dev_priv;
+	struct intel_context *ce;
 
-	if (HAS_LOGICAL_RING_CONTEXTS(dev_priv)) {
-		dev_priv->perf.oa.specific_ctx_id = stream->ctx->hw_id;
-	} else {
-		struct intel_engine_cs *engine = dev_priv->engine[RCS];
-		struct intel_ring *ring;
-		int ret;
-
-		ret = i915_mutex_lock_interruptible(&dev_priv->drm);
-		if (ret)
-			return ret;
+	ce = oa_pin_context(i915, stream->ctx);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
 
+	switch (INTEL_GEN(i915)) {
+	case 7: {
 		/*
-		 * As the ID is the gtt offset of the context's vma we
-		 * pin the vma to ensure the ID remains fixed.
-		 *
-		 * NB: implied RCS engine...
+		 * On Haswell we don't do any post processing of the reports
+		 * and don't need to use the mask.
 		 */
-		ring = intel_context_pin(stream->ctx, engine);
-		mutex_unlock(&dev_priv->drm.struct_mutex);
-		if (IS_ERR(ring))
-			return PTR_ERR(ring);
+		i915->perf.oa.specific_ctx_id = i915_ggtt_offset(ce->state);
+		i915->perf.oa.specific_ctx_id_mask = 0;
+		break;
+	}
 
+	case 8:
+	case 9:
+	case 10:
+		if (USES_GUC_SUBMISSION(i915)) {
+			/*
+			 * When using GuC, the context descriptor we write in
+			 * i915 is read by GuC and rewritten before it's
+			 * actually written into the hardware. The LRCA is
+			 * what is put into the context id field of the
+			 * context descriptor by GuC. Because it's aligned to
+			 * a page, the lower 12bits are always at 0 and
+			 * dropped by GuC. They won't be part of the context
+			 * ID in the OA reports, so squash those lower bits.
+			 */
+			i915->perf.oa.specific_ctx_id =
+				lower_32_bits(ce->lrc_desc) >> 12;
 
-		/*
-		 * Explicitly track the ID (instead of calling
-		 * i915_ggtt_offset() on the fly) considering the difference
-		 * with gen8+ and execlists
-		 */
-		dev_priv->perf.oa.specific_ctx_id =
-			i915_ggtt_offset(to_intel_context(stream->ctx, engine)->state);
+			/*
+			 * GuC uses the top bit to signal proxy submission, so
+			 * ignore that bit.
+			 */
+			i915->perf.oa.specific_ctx_id_mask =
+				(1U << (GEN8_CTX_ID_WIDTH - 1)) - 1;
+		} else {
+			i915->perf.oa.specific_ctx_id_mask =
+				(1U << GEN8_CTX_ID_WIDTH) - 1;
+			i915->perf.oa.specific_ctx_id =
+				upper_32_bits(ce->lrc_desc);
+			i915->perf.oa.specific_ctx_id &=
+				i915->perf.oa.specific_ctx_id_mask;
+		}
+		break;
+
+	case 11: {
+		i915->perf.oa.specific_ctx_id_mask =
+			((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32) |
+			((1U << GEN11_ENGINE_INSTANCE_WIDTH) - 1) << (GEN11_ENGINE_INSTANCE_SHIFT - 32) |
+			((1 << GEN11_ENGINE_CLASS_WIDTH) - 1) << (GEN11_ENGINE_CLASS_SHIFT - 32);
+		i915->perf.oa.specific_ctx_id = upper_32_bits(ce->lrc_desc);
+		i915->perf.oa.specific_ctx_id &=
+			i915->perf.oa.specific_ctx_id_mask;
+		break;
+	}
+
+	default:
+		MISSING_CASE(INTEL_GEN(i915));
 	}
 
+	DRM_DEBUG_DRIVER("filtering on ctx_id=0x%x ctx_id_mask=0x%x\n",
+			 i915->perf.oa.specific_ctx_id,
+			 i915->perf.oa.specific_ctx_id_mask);
+
 	return 0;
 }
 
@@ -1262,17 +1320,15 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 static void oa_put_render_ctx_id(struct i915_perf_stream *stream)
 {
 	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct intel_context *ce;
 
-	if (HAS_LOGICAL_RING_CONTEXTS(dev_priv)) {
-		dev_priv->perf.oa.specific_ctx_id = INVALID_CTX_ID;
-	} else {
-		struct intel_engine_cs *engine = dev_priv->engine[RCS];
+	dev_priv->perf.oa.specific_ctx_id = INVALID_CTX_ID;
+	dev_priv->perf.oa.specific_ctx_id_mask = 0;
 
+	ce = fetch_and_zero(&dev_priv->perf.oa.pinned_ctx);
+	if (ce) {
 		mutex_lock(&dev_priv->drm.struct_mutex);
-
-		dev_priv->perf.oa.specific_ctx_id = INVALID_CTX_ID;
-		intel_context_unpin(stream->ctx, engine);
-
+		intel_context_unpin(ce);
 		mutex_unlock(&dev_priv->drm.struct_mutex);
 	}
 }
@@ -1780,7 +1836,9 @@ static int gen8_configure_all_contexts(struct drm_i915_private *dev_priv,
 	 * So far the best way to work around this issue seems to be draining
 	 * the GPU from any submitted work.
 	 */
-	ret = i915_gem_wait_for_idle(dev_priv, wait_flags);
+	ret = i915_gem_wait_for_idle(dev_priv,
+				     wait_flags,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (ret)
 		goto out;
 
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index dc87797db500..d6c8f8fdfda5 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -4,6 +4,7 @@
  * Copyright © 2017-2018 Intel Corporation
  */
 
+#include <linux/irq.h>
 #include "i915_pmu.h"
 #include "intel_ringbuffer.h"
 #include "i915_drv.h"
@@ -127,6 +128,7 @@ static void __i915_pmu_maybe_start_timer(struct drm_i915_private *i915)
 {
 	if (!i915->pmu.timer_enabled && pmu_needs_timer(i915, true)) {
 		i915->pmu.timer_enabled = true;
+		i915->pmu.timer_last = ktime_get();
 		hrtimer_start_range_ns(&i915->pmu.timer,
 				       ns_to_ktime(PERIOD), 0,
 				       HRTIMER_MODE_REL_PINNED);
@@ -155,12 +157,13 @@ static bool grab_forcewake(struct drm_i915_private *i915, bool fw)
 }
 
 static void
-update_sample(struct i915_pmu_sample *sample, u32 unit, u32 val)
+add_sample(struct i915_pmu_sample *sample, u32 val)
 {
-	sample->cur += mul_u32_u32(val, unit);
+	sample->cur += val;
 }
 
-static void engines_sample(struct drm_i915_private *dev_priv)
+static void
+engines_sample(struct drm_i915_private *dev_priv, unsigned int period_ns)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -182,8 +185,9 @@ static void engines_sample(struct drm_i915_private *dev_priv)
 
 		val = !i915_seqno_passed(current_seqno, last_seqno);
 
-		update_sample(&engine->pmu.sample[I915_SAMPLE_BUSY],
-			      PERIOD, val);
+		if (val)
+			add_sample(&engine->pmu.sample[I915_SAMPLE_BUSY],
+				   period_ns);
 
 		if (val && (engine->pmu.enable &
 		    (BIT(I915_SAMPLE_WAIT) | BIT(I915_SAMPLE_SEMA)))) {
@@ -194,11 +198,13 @@ static void engines_sample(struct drm_i915_private *dev_priv)
 			val = 0;
 		}
 
-		update_sample(&engine->pmu.sample[I915_SAMPLE_WAIT],
-			      PERIOD, !!(val & RING_WAIT));
+		if (val & RING_WAIT)
+			add_sample(&engine->pmu.sample[I915_SAMPLE_WAIT],
+				   period_ns);
 
-		update_sample(&engine->pmu.sample[I915_SAMPLE_SEMA],
-			      PERIOD, !!(val & RING_WAIT_SEMAPHORE));
+		if (val & RING_WAIT_SEMAPHORE)
+			add_sample(&engine->pmu.sample[I915_SAMPLE_SEMA],
+				   period_ns);
 	}
 
 	if (fw)
@@ -207,7 +213,14 @@ static void engines_sample(struct drm_i915_private *dev_priv)
 	intel_runtime_pm_put(dev_priv);
 }
 
-static void frequency_sample(struct drm_i915_private *dev_priv)
+static void
+add_sample_mult(struct i915_pmu_sample *sample, u32 val, u32 mul)
+{
+	sample->cur += mul_u32_u32(val, mul);
+}
+
+static void
+frequency_sample(struct drm_i915_private *dev_priv, unsigned int period_ns)
 {
 	if (dev_priv->pmu.enable &
 	    config_enabled_mask(I915_PMU_ACTUAL_FREQUENCY)) {
@@ -221,15 +234,17 @@ static void frequency_sample(struct drm_i915_private *dev_priv)
 			intel_runtime_pm_put(dev_priv);
 		}
 
-		update_sample(&dev_priv->pmu.sample[__I915_SAMPLE_FREQ_ACT],
-			      1, intel_gpu_freq(dev_priv, val));
+		add_sample_mult(&dev_priv->pmu.sample[__I915_SAMPLE_FREQ_ACT],
+				intel_gpu_freq(dev_priv, val),
+				period_ns / 1000);
 	}
 
 	if (dev_priv->pmu.enable &
 	    config_enabled_mask(I915_PMU_REQUESTED_FREQUENCY)) {
-		update_sample(&dev_priv->pmu.sample[__I915_SAMPLE_FREQ_REQ], 1,
-			      intel_gpu_freq(dev_priv,
-					     dev_priv->gt_pm.rps.cur_freq));
+		add_sample_mult(&dev_priv->pmu.sample[__I915_SAMPLE_FREQ_REQ],
+				intel_gpu_freq(dev_priv,
+					       dev_priv->gt_pm.rps.cur_freq),
+				period_ns / 1000);
 	}
 }
 
@@ -237,14 +252,27 @@ static enum hrtimer_restart i915_sample(struct hrtimer *hrtimer)
 {
 	struct drm_i915_private *i915 =
 		container_of(hrtimer, struct drm_i915_private, pmu.timer);
+	unsigned int period_ns;
+	ktime_t now;
 
 	if (!READ_ONCE(i915->pmu.timer_enabled))
 		return HRTIMER_NORESTART;
 
-	engines_sample(i915);
-	frequency_sample(i915);
+	now = ktime_get();
+	period_ns = ktime_to_ns(ktime_sub(now, i915->pmu.timer_last));
+	i915->pmu.timer_last = now;
+
+	/*
+	 * Strictly speaking the passed in period may not be 100% accurate for
+	 * all internal calculation, since some amount of time can be spent on
+	 * grabbing the forcewake. However the potential error from timer call-
+	 * back delay greatly dominates this so we keep it simple.
+	 */
+	engines_sample(i915, period_ns);
+	frequency_sample(i915, period_ns);
+
+	hrtimer_forward(hrtimer, now, ns_to_ktime(PERIOD));
 
-	hrtimer_forward_now(hrtimer, ns_to_ktime(PERIOD));
 	return HRTIMER_RESTART;
 }
 
@@ -519,12 +547,12 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
 		case I915_PMU_ACTUAL_FREQUENCY:
 			val =
 			   div_u64(i915->pmu.sample[__I915_SAMPLE_FREQ_ACT].cur,
-				   FREQUENCY);
+				   USEC_PER_SEC /* to MHz */);
 			break;
 		case I915_PMU_REQUESTED_FREQUENCY:
 			val =
 			   div_u64(i915->pmu.sample[__I915_SAMPLE_FREQ_REQ].cur,
-				   FREQUENCY);
+				   USEC_PER_SEC /* to MHz */);
 			break;
 		case I915_PMU_INTERRUPTS:
 			val = count_interrupts(i915);
diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h
index 2ba735299f7c..7f164ca3db12 100644
--- a/drivers/gpu/drm/i915/i915_pmu.h
+++ b/drivers/gpu/drm/i915/i915_pmu.h
@@ -65,6 +65,14 @@ struct i915_pmu {
 	 * event types.
 	 */
 	u64 enable;
+
+	/**
+	 * @timer_last:
+	 *
+	 * Timestmap of the previous timer invocation.
+	 */
+	ktime_t timer_last;
+
 	/**
 	 * @enable_count: Reference counts for the enabled events.
 	 *
diff --git a/drivers/gpu/drm/i915/i915_pvinfo.h b/drivers/gpu/drm/i915/i915_pvinfo.h
index 195203f298df..eeaa3d506d95 100644
--- a/drivers/gpu/drm/i915/i915_pvinfo.h
+++ b/drivers/gpu/drm/i915/i915_pvinfo.h
@@ -54,6 +54,7 @@ enum vgt_g2v_type {
  */
 #define VGT_CAPS_FULL_48BIT_PPGTT	BIT(2)
 #define VGT_CAPS_HWSP_EMULATION		BIT(3)
+#define VGT_CAPS_HUGE_GTT		BIT(4)
 
 struct vgt_if {
 	u64 magic;		/* VGT_MAGIC */
@@ -93,7 +94,10 @@ struct vgt_if {
 	u32 rsv5[4];
 
 	u32 g2v_notify;
-	u32 rsv6[7];
+	u32 rsv6[5];
+
+	u32 cursor_x_hot;
+	u32 cursor_y_hot;
 
 	struct {
 		u32 lo;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 7720569f2024..91e7483228e1 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -139,23 +139,40 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 	return !i915_mmio_reg_equal(reg, INVALID_MMIO_REG);
 }
 
+/*
+ * Given the first two numbers __a and __b of arbitrarily many evenly spaced
+ * numbers, pick the 0-based __index'th value.
+ *
+ * Always prefer this over _PICK() if the numbers are evenly spaced.
+ */
+#define _PICK_EVEN(__index, __a, __b) ((__a) + (__index) * ((__b) - (__a)))
+
+/*
+ * Given the arbitrary numbers in varargs, pick the 0-based __index'th number.
+ *
+ * Always prefer _PICK_EVEN() over this if the numbers are evenly spaced.
+ */
 #define _PICK(__index, ...) (((const u32 []){ __VA_ARGS__ })[__index])
 
-#define _PIPE(pipe, a, b) ((a) + (pipe)*((b)-(a)))
+/*
+ * Named helper wrappers around _PICK_EVEN() and _PICK().
+ */
+#define _PIPE(pipe, a, b) _PICK_EVEN(pipe, a, b)
 #define _MMIO_PIPE(pipe, a, b) _MMIO(_PIPE(pipe, a, b))
-#define _PLANE(plane, a, b) _PIPE(plane, a, b)
+#define _PLANE(plane, a, b) _PICK_EVEN(plane, a, b)
 #define _MMIO_PLANE(plane, a, b) _MMIO_PIPE(plane, a, b)
-#define _TRANS(tran, a, b) ((a) + (tran)*((b)-(a)))
+#define _TRANS(tran, a, b) _PICK_EVEN(tran, a, b)
 #define _MMIO_TRANS(tran, a, b) _MMIO(_TRANS(tran, a, b))
-#define _PORT(port, a, b) ((a) + (port)*((b)-(a)))
+#define _PORT(port, a, b) _PICK_EVEN(port, a, b)
 #define _MMIO_PORT(port, a, b) _MMIO(_PORT(port, a, b))
 #define _MMIO_PIPE3(pipe, a, b, c) _MMIO(_PICK(pipe, a, b, c))
 #define _MMIO_PORT3(pipe, a, b, c) _MMIO(_PICK(pipe, a, b, c))
-#define _PLL(pll, a, b) ((a) + (pll)*((b)-(a)))
+#define _PLL(pll, a, b) _PICK_EVEN(pll, a, b)
 #define _MMIO_PLL(pll, a, b) _MMIO(_PLL(pll, a, b))
 #define _PHY3(phy, ...) _PICK(phy, __VA_ARGS__)
 #define _MMIO_PHY3(phy, a, b, c) _MMIO(_PHY3(phy, a, b, c))
 
+#define __MASKED_FIELD(mask, value) ((mask) << 16 | (value))
 #define _MASKED_FIELD(mask, value) ({					   \
 	if (__builtin_constant_p(mask))					   \
 		BUILD_BUG_ON_MSG(((mask) & 0xffff0000), "Incorrect mask"); \
@@ -164,7 +181,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 	if (__builtin_constant_p(mask) && __builtin_constant_p(value))	   \
 		BUILD_BUG_ON_MSG((value) & ~(mask),			   \
 				 "Incorrect value for mask");		   \
-	(mask) << 16 | (value); })
+	__MASKED_FIELD(mask, value); })
 #define _MASKED_BIT_ENABLE(a)	({ typeof(a) _a = (a); _MASKED_FIELD(_a, _a); })
 #define _MASKED_BIT_DISABLE(a)	(_MASKED_FIELD((a), 0))
 
@@ -270,19 +287,19 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 
 
 #define ILK_GDSR _MMIO(MCHBAR_MIRROR_BASE + 0x2ca4)
-#define  ILK_GRDOM_FULL		(0<<1)
-#define  ILK_GRDOM_RENDER	(1<<1)
-#define  ILK_GRDOM_MEDIA	(3<<1)
-#define  ILK_GRDOM_MASK		(3<<1)
-#define  ILK_GRDOM_RESET_ENABLE (1<<0)
+#define  ILK_GRDOM_FULL		(0 << 1)
+#define  ILK_GRDOM_RENDER	(1 << 1)
+#define  ILK_GRDOM_MEDIA	(3 << 1)
+#define  ILK_GRDOM_MASK		(3 << 1)
+#define  ILK_GRDOM_RESET_ENABLE (1 << 0)
 
 #define GEN6_MBCUNIT_SNPCR	_MMIO(0x900c) /* for LLC config */
 #define   GEN6_MBC_SNPCR_SHIFT	21
-#define   GEN6_MBC_SNPCR_MASK	(3<<21)
-#define   GEN6_MBC_SNPCR_MAX	(0<<21)
-#define   GEN6_MBC_SNPCR_MED	(1<<21)
-#define   GEN6_MBC_SNPCR_LOW	(2<<21)
-#define   GEN6_MBC_SNPCR_MIN	(3<<21) /* only 1/16th of the cache is shared */
+#define   GEN6_MBC_SNPCR_MASK	(3 << 21)
+#define   GEN6_MBC_SNPCR_MAX	(0 << 21)
+#define   GEN6_MBC_SNPCR_MED	(1 << 21)
+#define   GEN6_MBC_SNPCR_LOW	(2 << 21)
+#define   GEN6_MBC_SNPCR_MIN	(3 << 21) /* only 1/16th of the cache is shared */
 
 #define VLV_G3DCTL		_MMIO(0x9024)
 #define VLV_GSCKGCTL		_MMIO(0x9028)
@@ -314,13 +331,13 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define  GEN11_GRDOM_VECS		(1 << 13)
 #define  GEN11_GRDOM_VECS2		(1 << 14)
 
-#define RING_PP_DIR_BASE(engine)	_MMIO((engine)->mmio_base+0x228)
-#define RING_PP_DIR_BASE_READ(engine)	_MMIO((engine)->mmio_base+0x518)
-#define RING_PP_DIR_DCLV(engine)	_MMIO((engine)->mmio_base+0x220)
+#define RING_PP_DIR_BASE(engine)	_MMIO((engine)->mmio_base + 0x228)
+#define RING_PP_DIR_BASE_READ(engine)	_MMIO((engine)->mmio_base + 0x518)
+#define RING_PP_DIR_DCLV(engine)	_MMIO((engine)->mmio_base + 0x220)
 #define   PP_DIR_DCLV_2G		0xffffffff
 
-#define GEN8_RING_PDP_UDW(engine, n)	_MMIO((engine)->mmio_base+0x270 + (n) * 8 + 4)
-#define GEN8_RING_PDP_LDW(engine, n)	_MMIO((engine)->mmio_base+0x270 + (n) * 8)
+#define GEN8_RING_PDP_UDW(engine, n)	_MMIO((engine)->mmio_base + 0x270 + (n) * 8 + 4)
+#define GEN8_RING_PDP_LDW(engine, n)	_MMIO((engine)->mmio_base + 0x270 + (n) * 8)
 
 #define GEN8_R_PWR_CLK_STATE		_MMIO(0x20C8)
 #define   GEN8_RPCS_ENABLE		(1 << 31)
@@ -358,25 +375,25 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   GEN8_SELECTIVE_READ_ADDRESSING_ENABLE         (1 << 13)
 
 #define GAM_ECOCHK			_MMIO(0x4090)
-#define   BDW_DISABLE_HDC_INVALIDATION	(1<<25)
-#define   ECOCHK_SNB_BIT		(1<<10)
-#define   ECOCHK_DIS_TLB		(1<<8)
-#define   HSW_ECOCHK_ARB_PRIO_SOL	(1<<6)
-#define   ECOCHK_PPGTT_CACHE64B		(0x3<<3)
-#define   ECOCHK_PPGTT_CACHE4B		(0x0<<3)
-#define   ECOCHK_PPGTT_GFDT_IVB		(0x1<<4)
-#define   ECOCHK_PPGTT_LLC_IVB		(0x1<<3)
-#define   ECOCHK_PPGTT_UC_HSW		(0x1<<3)
-#define   ECOCHK_PPGTT_WT_HSW		(0x2<<3)
-#define   ECOCHK_PPGTT_WB_HSW		(0x3<<3)
+#define   BDW_DISABLE_HDC_INVALIDATION	(1 << 25)
+#define   ECOCHK_SNB_BIT		(1 << 10)
+#define   ECOCHK_DIS_TLB		(1 << 8)
+#define   HSW_ECOCHK_ARB_PRIO_SOL	(1 << 6)
+#define   ECOCHK_PPGTT_CACHE64B		(0x3 << 3)
+#define   ECOCHK_PPGTT_CACHE4B		(0x0 << 3)
+#define   ECOCHK_PPGTT_GFDT_IVB		(0x1 << 4)
+#define   ECOCHK_PPGTT_LLC_IVB		(0x1 << 3)
+#define   ECOCHK_PPGTT_UC_HSW		(0x1 << 3)
+#define   ECOCHK_PPGTT_WT_HSW		(0x2 << 3)
+#define   ECOCHK_PPGTT_WB_HSW		(0x3 << 3)
 
 #define GAC_ECO_BITS			_MMIO(0x14090)
-#define   ECOBITS_SNB_BIT		(1<<13)
-#define   ECOBITS_PPGTT_CACHE64B	(3<<8)
-#define   ECOBITS_PPGTT_CACHE4B		(0<<8)
+#define   ECOBITS_SNB_BIT		(1 << 13)
+#define   ECOBITS_PPGTT_CACHE64B	(3 << 8)
+#define   ECOBITS_PPGTT_CACHE4B		(0 << 8)
 
 #define GAB_CTL				_MMIO(0x24000)
-#define   GAB_CTL_CONT_AFTER_PAGEFAULT	(1<<8)
+#define   GAB_CTL_CONT_AFTER_PAGEFAULT	(1 << 8)
 
 #define GEN6_STOLEN_RESERVED		_MMIO(0x1082C0)
 #define GEN6_STOLEN_RESERVED_ADDR_MASK	(0xFFF << 20)
@@ -395,6 +412,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define GEN8_STOLEN_RESERVED_4M		(2 << 7)
 #define GEN8_STOLEN_RESERVED_8M		(3 << 7)
 #define GEN6_STOLEN_RESERVED_ENABLE	(1 << 0)
+#define GEN11_STOLEN_RESERVED_ADDR_MASK	(0xFFFFFFFFFFFULL << 20)
 
 /* VGA stuff */
 
@@ -404,15 +422,15 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define _VGA_MSR_WRITE _MMIO(0x3c2)
 #define VGA_MSR_WRITE 0x3c2
 #define VGA_MSR_READ 0x3cc
-#define   VGA_MSR_MEM_EN (1<<1)
-#define   VGA_MSR_CGA_MODE (1<<0)
+#define   VGA_MSR_MEM_EN (1 << 1)
+#define   VGA_MSR_CGA_MODE (1 << 0)
 
 #define VGA_SR_INDEX 0x3c4
 #define SR01			1
 #define VGA_SR_DATA 0x3c5
 
 #define VGA_AR_INDEX 0x3c0
-#define   VGA_AR_VID_EN (1<<5)
+#define   VGA_AR_VID_EN (1 << 5)
 #define VGA_AR_DATA_WRITE 0x3c0
 #define VGA_AR_DATA_READ 0x3c1
 
@@ -445,8 +463,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define MI_PREDICATE_SRC1_UDW	_MMIO(0x2408 + 4)
 
 #define MI_PREDICATE_RESULT_2	_MMIO(0x2214)
-#define  LOWER_SLICE_ENABLED	(1<<0)
-#define  LOWER_SLICE_DISABLED	(0<<0)
+#define  LOWER_SLICE_ENABLED	(1 << 0)
+#define  LOWER_SLICE_DISABLED	(0 << 0)
 
 /*
  * Registers used only by the command parser
@@ -504,47 +522,47 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define  GEN7_OACONTROL_CTX_MASK	    0xFFFFF000
 #define  GEN7_OACONTROL_TIMER_PERIOD_MASK   0x3F
 #define  GEN7_OACONTROL_TIMER_PERIOD_SHIFT  6
-#define  GEN7_OACONTROL_TIMER_ENABLE	    (1<<5)
-#define  GEN7_OACONTROL_FORMAT_A13	    (0<<2)
-#define  GEN7_OACONTROL_FORMAT_A29	    (1<<2)
-#define  GEN7_OACONTROL_FORMAT_A13_B8_C8    (2<<2)
-#define  GEN7_OACONTROL_FORMAT_A29_B8_C8    (3<<2)
-#define  GEN7_OACONTROL_FORMAT_B4_C8	    (4<<2)
-#define  GEN7_OACONTROL_FORMAT_A45_B8_C8    (5<<2)
-#define  GEN7_OACONTROL_FORMAT_B4_C8_A16    (6<<2)
-#define  GEN7_OACONTROL_FORMAT_C4_B8	    (7<<2)
+#define  GEN7_OACONTROL_TIMER_ENABLE	    (1 << 5)
+#define  GEN7_OACONTROL_FORMAT_A13	    (0 << 2)
+#define  GEN7_OACONTROL_FORMAT_A29	    (1 << 2)
+#define  GEN7_OACONTROL_FORMAT_A13_B8_C8    (2 << 2)
+#define  GEN7_OACONTROL_FORMAT_A29_B8_C8    (3 << 2)
+#define  GEN7_OACONTROL_FORMAT_B4_C8	    (4 << 2)
+#define  GEN7_OACONTROL_FORMAT_A45_B8_C8    (5 << 2)
+#define  GEN7_OACONTROL_FORMAT_B4_C8_A16    (6 << 2)
+#define  GEN7_OACONTROL_FORMAT_C4_B8	    (7 << 2)
 #define  GEN7_OACONTROL_FORMAT_SHIFT	    2
-#define  GEN7_OACONTROL_PER_CTX_ENABLE	    (1<<1)
-#define  GEN7_OACONTROL_ENABLE		    (1<<0)
+#define  GEN7_OACONTROL_PER_CTX_ENABLE	    (1 << 1)
+#define  GEN7_OACONTROL_ENABLE		    (1 << 0)
 
 #define GEN8_OACTXID _MMIO(0x2364)
 
 #define GEN8_OA_DEBUG _MMIO(0x2B04)
-#define  GEN9_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS    (1<<5)
-#define  GEN9_OA_DEBUG_INCLUDE_CLK_RATIO	    (1<<6)
-#define  GEN9_OA_DEBUG_DISABLE_GO_1_0_REPORTS	    (1<<2)
-#define  GEN9_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS   (1<<1)
+#define  GEN9_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS    (1 << 5)
+#define  GEN9_OA_DEBUG_INCLUDE_CLK_RATIO	    (1 << 6)
+#define  GEN9_OA_DEBUG_DISABLE_GO_1_0_REPORTS	    (1 << 2)
+#define  GEN9_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS   (1 << 1)
 
 #define GEN8_OACONTROL _MMIO(0x2B00)
-#define  GEN8_OA_REPORT_FORMAT_A12	    (0<<2)
-#define  GEN8_OA_REPORT_FORMAT_A12_B8_C8    (2<<2)
-#define  GEN8_OA_REPORT_FORMAT_A36_B8_C8    (5<<2)
-#define  GEN8_OA_REPORT_FORMAT_C4_B8	    (7<<2)
+#define  GEN8_OA_REPORT_FORMAT_A12	    (0 << 2)
+#define  GEN8_OA_REPORT_FORMAT_A12_B8_C8    (2 << 2)
+#define  GEN8_OA_REPORT_FORMAT_A36_B8_C8    (5 << 2)
+#define  GEN8_OA_REPORT_FORMAT_C4_B8	    (7 << 2)
 #define  GEN8_OA_REPORT_FORMAT_SHIFT	    2
-#define  GEN8_OA_SPECIFIC_CONTEXT_ENABLE    (1<<1)
-#define  GEN8_OA_COUNTER_ENABLE             (1<<0)
+#define  GEN8_OA_SPECIFIC_CONTEXT_ENABLE    (1 << 1)
+#define  GEN8_OA_COUNTER_ENABLE             (1 << 0)
 
 #define GEN8_OACTXCONTROL _MMIO(0x2360)
 #define  GEN8_OA_TIMER_PERIOD_MASK	    0x3F
 #define  GEN8_OA_TIMER_PERIOD_SHIFT	    2
-#define  GEN8_OA_TIMER_ENABLE		    (1<<1)
-#define  GEN8_OA_COUNTER_RESUME		    (1<<0)
+#define  GEN8_OA_TIMER_ENABLE		    (1 << 1)
+#define  GEN8_OA_COUNTER_RESUME		    (1 << 0)
 
 #define GEN7_OABUFFER _MMIO(0x23B0) /* R/W */
-#define  GEN7_OABUFFER_OVERRUN_DISABLE	    (1<<3)
-#define  GEN7_OABUFFER_EDGE_TRIGGER	    (1<<2)
-#define  GEN7_OABUFFER_STOP_RESUME_ENABLE   (1<<1)
-#define  GEN7_OABUFFER_RESUME		    (1<<0)
+#define  GEN7_OABUFFER_OVERRUN_DISABLE	    (1 << 3)
+#define  GEN7_OABUFFER_EDGE_TRIGGER	    (1 << 2)
+#define  GEN7_OABUFFER_STOP_RESUME_ENABLE   (1 << 1)
+#define  GEN7_OABUFFER_RESUME		    (1 << 0)
 
 #define GEN8_OABUFFER_UDW _MMIO(0x23b4)
 #define GEN8_OABUFFER _MMIO(0x2b14)
@@ -552,33 +570,33 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 
 #define GEN7_OASTATUS1 _MMIO(0x2364)
 #define  GEN7_OASTATUS1_TAIL_MASK	    0xffffffc0
-#define  GEN7_OASTATUS1_COUNTER_OVERFLOW    (1<<2)
-#define  GEN7_OASTATUS1_OABUFFER_OVERFLOW   (1<<1)
-#define  GEN7_OASTATUS1_REPORT_LOST	    (1<<0)
+#define  GEN7_OASTATUS1_COUNTER_OVERFLOW    (1 << 2)
+#define  GEN7_OASTATUS1_OABUFFER_OVERFLOW   (1 << 1)
+#define  GEN7_OASTATUS1_REPORT_LOST	    (1 << 0)
 
 #define GEN7_OASTATUS2 _MMIO(0x2368)
 #define  GEN7_OASTATUS2_HEAD_MASK           0xffffffc0
 #define  GEN7_OASTATUS2_MEM_SELECT_GGTT     (1 << 0) /* 0: PPGTT, 1: GGTT */
 
 #define GEN8_OASTATUS _MMIO(0x2b08)
-#define  GEN8_OASTATUS_OVERRUN_STATUS	    (1<<3)
-#define  GEN8_OASTATUS_COUNTER_OVERFLOW     (1<<2)
-#define  GEN8_OASTATUS_OABUFFER_OVERFLOW    (1<<1)
-#define  GEN8_OASTATUS_REPORT_LOST	    (1<<0)
+#define  GEN8_OASTATUS_OVERRUN_STATUS	    (1 << 3)
+#define  GEN8_OASTATUS_COUNTER_OVERFLOW     (1 << 2)
+#define  GEN8_OASTATUS_OABUFFER_OVERFLOW    (1 << 1)
+#define  GEN8_OASTATUS_REPORT_LOST	    (1 << 0)
 
 #define GEN8_OAHEADPTR _MMIO(0x2B0C)
 #define GEN8_OAHEADPTR_MASK    0xffffffc0
 #define GEN8_OATAILPTR _MMIO(0x2B10)
 #define GEN8_OATAILPTR_MASK    0xffffffc0
 
-#define OABUFFER_SIZE_128K  (0<<3)
-#define OABUFFER_SIZE_256K  (1<<3)
-#define OABUFFER_SIZE_512K  (2<<3)
-#define OABUFFER_SIZE_1M    (3<<3)
-#define OABUFFER_SIZE_2M    (4<<3)
-#define OABUFFER_SIZE_4M    (5<<3)
-#define OABUFFER_SIZE_8M    (6<<3)
-#define OABUFFER_SIZE_16M   (7<<3)
+#define OABUFFER_SIZE_128K  (0 << 3)
+#define OABUFFER_SIZE_256K  (1 << 3)
+#define OABUFFER_SIZE_512K  (2 << 3)
+#define OABUFFER_SIZE_1M    (3 << 3)
+#define OABUFFER_SIZE_2M    (4 << 3)
+#define OABUFFER_SIZE_4M    (5 << 3)
+#define OABUFFER_SIZE_8M    (6 << 3)
+#define OABUFFER_SIZE_16M   (7 << 3)
 
 /*
  * Flexible, Aggregate EU Counter Registers.
@@ -601,35 +619,35 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define OASTARTTRIG1_THRESHOLD_MASK	      0xffff
 
 #define OASTARTTRIG2 _MMIO(0x2714)
-#define OASTARTTRIG2_INVERT_A_0 (1<<0)
-#define OASTARTTRIG2_INVERT_A_1 (1<<1)
-#define OASTARTTRIG2_INVERT_A_2 (1<<2)
-#define OASTARTTRIG2_INVERT_A_3 (1<<3)
-#define OASTARTTRIG2_INVERT_A_4 (1<<4)
-#define OASTARTTRIG2_INVERT_A_5 (1<<5)
-#define OASTARTTRIG2_INVERT_A_6 (1<<6)
-#define OASTARTTRIG2_INVERT_A_7 (1<<7)
-#define OASTARTTRIG2_INVERT_A_8 (1<<8)
-#define OASTARTTRIG2_INVERT_A_9 (1<<9)
-#define OASTARTTRIG2_INVERT_A_10 (1<<10)
-#define OASTARTTRIG2_INVERT_A_11 (1<<11)
-#define OASTARTTRIG2_INVERT_A_12 (1<<12)
-#define OASTARTTRIG2_INVERT_A_13 (1<<13)
-#define OASTARTTRIG2_INVERT_A_14 (1<<14)
-#define OASTARTTRIG2_INVERT_A_15 (1<<15)
-#define OASTARTTRIG2_INVERT_B_0 (1<<16)
-#define OASTARTTRIG2_INVERT_B_1 (1<<17)
-#define OASTARTTRIG2_INVERT_B_2 (1<<18)
-#define OASTARTTRIG2_INVERT_B_3 (1<<19)
-#define OASTARTTRIG2_INVERT_C_0 (1<<20)
-#define OASTARTTRIG2_INVERT_C_1 (1<<21)
-#define OASTARTTRIG2_INVERT_D_0 (1<<22)
-#define OASTARTTRIG2_THRESHOLD_ENABLE	    (1<<23)
-#define OASTARTTRIG2_START_TRIG_FLAG_MBZ    (1<<24)
-#define OASTARTTRIG2_EVENT_SELECT_0  (1<<28)
-#define OASTARTTRIG2_EVENT_SELECT_1  (1<<29)
-#define OASTARTTRIG2_EVENT_SELECT_2  (1<<30)
-#define OASTARTTRIG2_EVENT_SELECT_3  (1<<31)
+#define OASTARTTRIG2_INVERT_A_0 (1 << 0)
+#define OASTARTTRIG2_INVERT_A_1 (1 << 1)
+#define OASTARTTRIG2_INVERT_A_2 (1 << 2)
+#define OASTARTTRIG2_INVERT_A_3 (1 << 3)
+#define OASTARTTRIG2_INVERT_A_4 (1 << 4)
+#define OASTARTTRIG2_INVERT_A_5 (1 << 5)
+#define OASTARTTRIG2_INVERT_A_6 (1 << 6)
+#define OASTARTTRIG2_INVERT_A_7 (1 << 7)
+#define OASTARTTRIG2_INVERT_A_8 (1 << 8)
+#define OASTARTTRIG2_INVERT_A_9 (1 << 9)
+#define OASTARTTRIG2_INVERT_A_10 (1 << 10)
+#define OASTARTTRIG2_INVERT_A_11 (1 << 11)
+#define OASTARTTRIG2_INVERT_A_12 (1 << 12)
+#define OASTARTTRIG2_INVERT_A_13 (1 << 13)
+#define OASTARTTRIG2_INVERT_A_14 (1 << 14)
+#define OASTARTTRIG2_INVERT_A_15 (1 << 15)
+#define OASTARTTRIG2_INVERT_B_0 (1 << 16)
+#define OASTARTTRIG2_INVERT_B_1 (1 << 17)
+#define OASTARTTRIG2_INVERT_B_2 (1 << 18)
+#define OASTARTTRIG2_INVERT_B_3 (1 << 19)
+#define OASTARTTRIG2_INVERT_C_0 (1 << 20)
+#define OASTARTTRIG2_INVERT_C_1 (1 << 21)
+#define OASTARTTRIG2_INVERT_D_0 (1 << 22)
+#define OASTARTTRIG2_THRESHOLD_ENABLE	    (1 << 23)
+#define OASTARTTRIG2_START_TRIG_FLAG_MBZ    (1 << 24)
+#define OASTARTTRIG2_EVENT_SELECT_0  (1 << 28)
+#define OASTARTTRIG2_EVENT_SELECT_1  (1 << 29)
+#define OASTARTTRIG2_EVENT_SELECT_2  (1 << 30)
+#define OASTARTTRIG2_EVENT_SELECT_3  (1 << 31)
 
 #define OASTARTTRIG3 _MMIO(0x2718)
 #define OASTARTTRIG3_NOA_SELECT_MASK	   0xf
@@ -658,35 +676,35 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define OASTARTTRIG5_THRESHOLD_MASK	      0xffff
 
 #define OASTARTTRIG6 _MMIO(0x2724)
-#define OASTARTTRIG6_INVERT_A_0 (1<<0)
-#define OASTARTTRIG6_INVERT_A_1 (1<<1)
-#define OASTARTTRIG6_INVERT_A_2 (1<<2)
-#define OASTARTTRIG6_INVERT_A_3 (1<<3)
-#define OASTARTTRIG6_INVERT_A_4 (1<<4)
-#define OASTARTTRIG6_INVERT_A_5 (1<<5)
-#define OASTARTTRIG6_INVERT_A_6 (1<<6)
-#define OASTARTTRIG6_INVERT_A_7 (1<<7)
-#define OASTARTTRIG6_INVERT_A_8 (1<<8)
-#define OASTARTTRIG6_INVERT_A_9 (1<<9)
-#define OASTARTTRIG6_INVERT_A_10 (1<<10)
-#define OASTARTTRIG6_INVERT_A_11 (1<<11)
-#define OASTARTTRIG6_INVERT_A_12 (1<<12)
-#define OASTARTTRIG6_INVERT_A_13 (1<<13)
-#define OASTARTTRIG6_INVERT_A_14 (1<<14)
-#define OASTARTTRIG6_INVERT_A_15 (1<<15)
-#define OASTARTTRIG6_INVERT_B_0 (1<<16)
-#define OASTARTTRIG6_INVERT_B_1 (1<<17)
-#define OASTARTTRIG6_INVERT_B_2 (1<<18)
-#define OASTARTTRIG6_INVERT_B_3 (1<<19)
-#define OASTARTTRIG6_INVERT_C_0 (1<<20)
-#define OASTARTTRIG6_INVERT_C_1 (1<<21)
-#define OASTARTTRIG6_INVERT_D_0 (1<<22)
-#define OASTARTTRIG6_THRESHOLD_ENABLE	    (1<<23)
-#define OASTARTTRIG6_START_TRIG_FLAG_MBZ    (1<<24)
-#define OASTARTTRIG6_EVENT_SELECT_4  (1<<28)
-#define OASTARTTRIG6_EVENT_SELECT_5  (1<<29)
-#define OASTARTTRIG6_EVENT_SELECT_6  (1<<30)
-#define OASTARTTRIG6_EVENT_SELECT_7  (1<<31)
+#define OASTARTTRIG6_INVERT_A_0 (1 << 0)
+#define OASTARTTRIG6_INVERT_A_1 (1 << 1)
+#define OASTARTTRIG6_INVERT_A_2 (1 << 2)
+#define OASTARTTRIG6_INVERT_A_3 (1 << 3)
+#define OASTARTTRIG6_INVERT_A_4 (1 << 4)
+#define OASTARTTRIG6_INVERT_A_5 (1 << 5)
+#define OASTARTTRIG6_INVERT_A_6 (1 << 6)
+#define OASTARTTRIG6_INVERT_A_7 (1 << 7)
+#define OASTARTTRIG6_INVERT_A_8 (1 << 8)
+#define OASTARTTRIG6_INVERT_A_9 (1 << 9)
+#define OASTARTTRIG6_INVERT_A_10 (1 << 10)
+#define OASTARTTRIG6_INVERT_A_11 (1 << 11)
+#define OASTARTTRIG6_INVERT_A_12 (1 << 12)
+#define OASTARTTRIG6_INVERT_A_13 (1 << 13)
+#define OASTARTTRIG6_INVERT_A_14 (1 << 14)
+#define OASTARTTRIG6_INVERT_A_15 (1 << 15)
+#define OASTARTTRIG6_INVERT_B_0 (1 << 16)
+#define OASTARTTRIG6_INVERT_B_1 (1 << 17)
+#define OASTARTTRIG6_INVERT_B_2 (1 << 18)
+#define OASTARTTRIG6_INVERT_B_3 (1 << 19)
+#define OASTARTTRIG6_INVERT_C_0 (1 << 20)
+#define OASTARTTRIG6_INVERT_C_1 (1 << 21)
+#define OASTARTTRIG6_INVERT_D_0 (1 << 22)
+#define OASTARTTRIG6_THRESHOLD_ENABLE	    (1 << 23)
+#define OASTARTTRIG6_START_TRIG_FLAG_MBZ    (1 << 24)
+#define OASTARTTRIG6_EVENT_SELECT_4  (1 << 28)
+#define OASTARTTRIG6_EVENT_SELECT_5  (1 << 29)
+#define OASTARTTRIG6_EVENT_SELECT_6  (1 << 30)
+#define OASTARTTRIG6_EVENT_SELECT_7  (1 << 31)
 
 #define OASTARTTRIG7 _MMIO(0x2728)
 #define OASTARTTRIG7_NOA_SELECT_MASK	   0xf
@@ -715,31 +733,31 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define OAREPORTTRIG1_EDGE_LEVEL_TRIGER_SELECT_MASK 0xffff0000 /* 0=level */
 
 #define OAREPORTTRIG2 _MMIO(0x2744)
-#define OAREPORTTRIG2_INVERT_A_0  (1<<0)
-#define OAREPORTTRIG2_INVERT_A_1  (1<<1)
-#define OAREPORTTRIG2_INVERT_A_2  (1<<2)
-#define OAREPORTTRIG2_INVERT_A_3  (1<<3)
-#define OAREPORTTRIG2_INVERT_A_4  (1<<4)
-#define OAREPORTTRIG2_INVERT_A_5  (1<<5)
-#define OAREPORTTRIG2_INVERT_A_6  (1<<6)
-#define OAREPORTTRIG2_INVERT_A_7  (1<<7)
-#define OAREPORTTRIG2_INVERT_A_8  (1<<8)
-#define OAREPORTTRIG2_INVERT_A_9  (1<<9)
-#define OAREPORTTRIG2_INVERT_A_10 (1<<10)
-#define OAREPORTTRIG2_INVERT_A_11 (1<<11)
-#define OAREPORTTRIG2_INVERT_A_12 (1<<12)
-#define OAREPORTTRIG2_INVERT_A_13 (1<<13)
-#define OAREPORTTRIG2_INVERT_A_14 (1<<14)
-#define OAREPORTTRIG2_INVERT_A_15 (1<<15)
-#define OAREPORTTRIG2_INVERT_B_0  (1<<16)
-#define OAREPORTTRIG2_INVERT_B_1  (1<<17)
-#define OAREPORTTRIG2_INVERT_B_2  (1<<18)
-#define OAREPORTTRIG2_INVERT_B_3  (1<<19)
-#define OAREPORTTRIG2_INVERT_C_0  (1<<20)
-#define OAREPORTTRIG2_INVERT_C_1  (1<<21)
-#define OAREPORTTRIG2_INVERT_D_0  (1<<22)
-#define OAREPORTTRIG2_THRESHOLD_ENABLE	    (1<<23)
-#define OAREPORTTRIG2_REPORT_TRIGGER_ENABLE (1<<31)
+#define OAREPORTTRIG2_INVERT_A_0  (1 << 0)
+#define OAREPORTTRIG2_INVERT_A_1  (1 << 1)
+#define OAREPORTTRIG2_INVERT_A_2  (1 << 2)
+#define OAREPORTTRIG2_INVERT_A_3  (1 << 3)
+#define OAREPORTTRIG2_INVERT_A_4  (1 << 4)
+#define OAREPORTTRIG2_INVERT_A_5  (1 << 5)
+#define OAREPORTTRIG2_INVERT_A_6  (1 << 6)
+#define OAREPORTTRIG2_INVERT_A_7  (1 << 7)
+#define OAREPORTTRIG2_INVERT_A_8  (1 << 8)
+#define OAREPORTTRIG2_INVERT_A_9  (1 << 9)
+#define OAREPORTTRIG2_INVERT_A_10 (1 << 10)
+#define OAREPORTTRIG2_INVERT_A_11 (1 << 11)
+#define OAREPORTTRIG2_INVERT_A_12 (1 << 12)
+#define OAREPORTTRIG2_INVERT_A_13 (1 << 13)
+#define OAREPORTTRIG2_INVERT_A_14 (1 << 14)
+#define OAREPORTTRIG2_INVERT_A_15 (1 << 15)
+#define OAREPORTTRIG2_INVERT_B_0  (1 << 16)
+#define OAREPORTTRIG2_INVERT_B_1  (1 << 17)
+#define OAREPORTTRIG2_INVERT_B_2  (1 << 18)
+#define OAREPORTTRIG2_INVERT_B_3  (1 << 19)
+#define OAREPORTTRIG2_INVERT_C_0  (1 << 20)
+#define OAREPORTTRIG2_INVERT_C_1  (1 << 21)
+#define OAREPORTTRIG2_INVERT_D_0  (1 << 22)
+#define OAREPORTTRIG2_THRESHOLD_ENABLE	    (1 << 23)
+#define OAREPORTTRIG2_REPORT_TRIGGER_ENABLE (1 << 31)
 
 #define OAREPORTTRIG3 _MMIO(0x2748)
 #define OAREPORTTRIG3_NOA_SELECT_MASK	    0xf
@@ -768,31 +786,31 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define OAREPORTTRIG5_EDGE_LEVEL_TRIGER_SELECT_MASK 0xffff0000 /* 0=level */
 
 #define OAREPORTTRIG6 _MMIO(0x2754)
-#define OAREPORTTRIG6_INVERT_A_0  (1<<0)
-#define OAREPORTTRIG6_INVERT_A_1  (1<<1)
-#define OAREPORTTRIG6_INVERT_A_2  (1<<2)
-#define OAREPORTTRIG6_INVERT_A_3  (1<<3)
-#define OAREPORTTRIG6_INVERT_A_4  (1<<4)
-#define OAREPORTTRIG6_INVERT_A_5  (1<<5)
-#define OAREPORTTRIG6_INVERT_A_6  (1<<6)
-#define OAREPORTTRIG6_INVERT_A_7  (1<<7)
-#define OAREPORTTRIG6_INVERT_A_8  (1<<8)
-#define OAREPORTTRIG6_INVERT_A_9  (1<<9)
-#define OAREPORTTRIG6_INVERT_A_10 (1<<10)
-#define OAREPORTTRIG6_INVERT_A_11 (1<<11)
-#define OAREPORTTRIG6_INVERT_A_12 (1<<12)
-#define OAREPORTTRIG6_INVERT_A_13 (1<<13)
-#define OAREPORTTRIG6_INVERT_A_14 (1<<14)
-#define OAREPORTTRIG6_INVERT_A_15 (1<<15)
-#define OAREPORTTRIG6_INVERT_B_0  (1<<16)
-#define OAREPORTTRIG6_INVERT_B_1  (1<<17)
-#define OAREPORTTRIG6_INVERT_B_2  (1<<18)
-#define OAREPORTTRIG6_INVERT_B_3  (1<<19)
-#define OAREPORTTRIG6_INVERT_C_0  (1<<20)
-#define OAREPORTTRIG6_INVERT_C_1  (1<<21)
-#define OAREPORTTRIG6_INVERT_D_0  (1<<22)
-#define OAREPORTTRIG6_THRESHOLD_ENABLE	    (1<<23)
-#define OAREPORTTRIG6_REPORT_TRIGGER_ENABLE (1<<31)
+#define OAREPORTTRIG6_INVERT_A_0  (1 << 0)
+#define OAREPORTTRIG6_INVERT_A_1  (1 << 1)
+#define OAREPORTTRIG6_INVERT_A_2  (1 << 2)
+#define OAREPORTTRIG6_INVERT_A_3  (1 << 3)
+#define OAREPORTTRIG6_INVERT_A_4  (1 << 4)
+#define OAREPORTTRIG6_INVERT_A_5  (1 << 5)
+#define OAREPORTTRIG6_INVERT_A_6  (1 << 6)
+#define OAREPORTTRIG6_INVERT_A_7  (1 << 7)
+#define OAREPORTTRIG6_INVERT_A_8  (1 << 8)
+#define OAREPORTTRIG6_INVERT_A_9  (1 << 9)
+#define OAREPORTTRIG6_INVERT_A_10 (1 << 10)
+#define OAREPORTTRIG6_INVERT_A_11 (1 << 11)
+#define OAREPORTTRIG6_INVERT_A_12 (1 << 12)
+#define OAREPORTTRIG6_INVERT_A_13 (1 << 13)
+#define OAREPORTTRIG6_INVERT_A_14 (1 << 14)
+#define OAREPORTTRIG6_INVERT_A_15 (1 << 15)
+#define OAREPORTTRIG6_INVERT_B_0  (1 << 16)
+#define OAREPORTTRIG6_INVERT_B_1  (1 << 17)
+#define OAREPORTTRIG6_INVERT_B_2  (1 << 18)
+#define OAREPORTTRIG6_INVERT_B_3  (1 << 19)
+#define OAREPORTTRIG6_INVERT_C_0  (1 << 20)
+#define OAREPORTTRIG6_INVERT_C_1  (1 << 21)
+#define OAREPORTTRIG6_INVERT_D_0  (1 << 22)
+#define OAREPORTTRIG6_THRESHOLD_ENABLE	    (1 << 23)
+#define OAREPORTTRIG6_REPORT_TRIGGER_ENABLE (1 << 31)
 
 #define OAREPORTTRIG7 _MMIO(0x2758)
 #define OAREPORTTRIG7_NOA_SELECT_MASK	    0xf
@@ -828,9 +846,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define OACEC_COMPARE_VALUE_MASK    0xffff
 #define OACEC_COMPARE_VALUE_SHIFT   3
 
-#define OACEC_SELECT_NOA	(0<<19)
-#define OACEC_SELECT_PREV	(1<<19)
-#define OACEC_SELECT_BOOLEAN	(2<<19)
+#define OACEC_SELECT_NOA	(0 << 19)
+#define OACEC_SELECT_PREV	(1 << 19)
+#define OACEC_SELECT_BOOLEAN	(2 << 19)
 
 /* CECX_1 */
 #define OACEC_MASK_MASK		    0xffff
@@ -948,9 +966,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
  * Reset registers
  */
 #define DEBUG_RESET_I830		_MMIO(0x6070)
-#define  DEBUG_RESET_FULL		(1<<7)
-#define  DEBUG_RESET_RENDER		(1<<8)
-#define  DEBUG_RESET_DISPLAY		(1<<9)
+#define  DEBUG_RESET_FULL		(1 << 7)
+#define  DEBUG_RESET_RENDER		(1 << 8)
+#define  DEBUG_RESET_DISPLAY		(1 << 9)
 
 /*
  * IOSF sideband
@@ -961,7 +979,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   IOSF_PORT_SHIFT			8
 #define   IOSF_BYTE_ENABLES_SHIFT		4
 #define   IOSF_BAR_SHIFT			1
-#define   IOSF_SB_BUSY				(1<<0)
+#define   IOSF_SB_BUSY				(1 << 0)
 #define   IOSF_PORT_BUNIT			0x03
 #define   IOSF_PORT_PUNIT			0x04
 #define   IOSF_PORT_NC				0x11
@@ -1044,13 +1062,13 @@ enum i915_power_well_id {
 
 	/*
 	 * HSW/BDW
-	 *  - HSW_PWR_WELL_CTL_DRIVER(0) (status bit: id*2, req bit: id*2+1)
+	 *  - _HSW_PWR_WELL_CTL1-4 (status bit: id*2, req bit: id*2+1)
 	 */
 	HSW_DISP_PW_GLOBAL = 15,
 
 	/*
 	 * GEN9+
-	 *  - HSW_PWR_WELL_CTL_DRIVER(0) (status bit: id*2, req bit: id*2+1)
+	 *  - _HSW_PWR_WELL_CTL1-4 (status bit: id*2, req bit: id*2+1)
 	 */
 	SKL_DISP_PW_MISC_IO = 0,
 	SKL_DISP_PW_DDI_A_E,
@@ -1074,17 +1092,54 @@ enum i915_power_well_id {
 	SKL_DISP_PW_2,
 
 	/* - custom power wells */
-	SKL_DISP_PW_DC_OFF,
 	BXT_DPIO_CMN_A,
 	BXT_DPIO_CMN_BC,
-	GLK_DPIO_CMN_C,			/* 19 */
+	GLK_DPIO_CMN_C,			/* 18 */
+
+	/*
+	 * GEN11+
+	 *  - _HSW_PWR_WELL_CTL1-4
+	 *    (status bit: (id&15)*2, req bit:(id&15)*2+1)
+	 */
+	ICL_DISP_PW_1 = 0,
+	ICL_DISP_PW_2,
+	ICL_DISP_PW_3,
+	ICL_DISP_PW_4,
+
+	/*
+	 *  - _HSW_PWR_WELL_CTL_AUX1/2/4
+	 *    (status bit: (id&15)*2, req bit:(id&15)*2+1)
+	 */
+	ICL_DISP_PW_AUX_A = 16,
+	ICL_DISP_PW_AUX_B,
+	ICL_DISP_PW_AUX_C,
+	ICL_DISP_PW_AUX_D,
+	ICL_DISP_PW_AUX_E,
+	ICL_DISP_PW_AUX_F,
+
+	ICL_DISP_PW_AUX_TBT1 = 24,
+	ICL_DISP_PW_AUX_TBT2,
+	ICL_DISP_PW_AUX_TBT3,
+	ICL_DISP_PW_AUX_TBT4,
+
+	/*
+	 *  - _HSW_PWR_WELL_CTL_DDI1/2/4
+	 *    (status bit: (id&15)*2, req bit:(id&15)*2+1)
+	 */
+	ICL_DISP_PW_DDI_A = 32,
+	ICL_DISP_PW_DDI_B,
+	ICL_DISP_PW_DDI_C,
+	ICL_DISP_PW_DDI_D,
+	ICL_DISP_PW_DDI_E,
+	ICL_DISP_PW_DDI_F,                      /* 37 */
 
 	/*
 	 * Multiple platforms.
 	 * Must start following the highest ID of any platform.
 	 * - custom power wells
 	 */
-	I915_DISP_PW_ALWAYS_ON = 20,
+	SKL_DISP_PW_DC_OFF = 38,
+	I915_DISP_PW_ALWAYS_ON,
 };
 
 #define PUNIT_REG_PWRGT_CTRL			0x60
@@ -1098,8 +1153,8 @@ enum i915_power_well_id {
 #define PUNIT_REG_GPU_LFM			0xd3
 #define PUNIT_REG_GPU_FREQ_REQ			0xd4
 #define PUNIT_REG_GPU_FREQ_STS			0xd8
-#define   GPLLENABLE				(1<<4)
-#define   GENFREQSTATUS				(1<<0)
+#define   GPLLENABLE				(1 << 4)
+#define   GENFREQSTATUS				(1 << 0)
 #define PUNIT_REG_MEDIA_TURBO_FREQ_REQ		0xdc
 #define PUNIT_REG_CZ_TIMESTAMP			0xce
 
@@ -1141,11 +1196,11 @@ enum i915_power_well_id {
 #define   FB_FMAX_VMIN_FREQ_LO_SHIFT		27
 #define   FB_FMAX_VMIN_FREQ_LO_MASK		0xf8000000
 
-#define VLV_TURBO_SOC_OVERRIDE	0x04
-#define 	VLV_OVERRIDE_EN	1
-#define 	VLV_SOC_TDP_EN	(1 << 1)
-#define 	VLV_BIAS_CPU_125_SOC_875 (6 << 2)
-#define 	CHV_BIAS_CPU_50_SOC_50 (3 << 2)
+#define VLV_TURBO_SOC_OVERRIDE		0x04
+#define   VLV_OVERRIDE_EN		1
+#define   VLV_SOC_TDP_EN		(1 << 1)
+#define   VLV_BIAS_CPU_125_SOC_875	(6 << 2)
+#define   CHV_BIAS_CPU_50_SOC_50	(3 << 2)
 
 /* vlv2 north clock has */
 #define CCK_FUSE_REG				0x8
@@ -1194,10 +1249,10 @@ enum i915_power_well_id {
 #define DPIO_DEVFN			0
 
 #define DPIO_CTL			_MMIO(VLV_DISPLAY_BASE + 0x2110)
-#define  DPIO_MODSEL1			(1<<3) /* if ref clk b == 27 */
-#define  DPIO_MODSEL0			(1<<2) /* if ref clk a == 27 */
-#define  DPIO_SFR_BYPASS		(1<<1)
-#define  DPIO_CMNRST			(1<<0)
+#define  DPIO_MODSEL1			(1 << 3) /* if ref clk b == 27 */
+#define  DPIO_MODSEL0			(1 << 2) /* if ref clk a == 27 */
+#define  DPIO_SFR_BYPASS		(1 << 1)
+#define  DPIO_CMNRST			(1 << 0)
 
 #define DPIO_PHY(pipe)			((pipe) >> 1)
 #define DPIO_PHY_IOSF_PORT(phy)		(dev_priv->dpio_phy_iosf_port[phy])
@@ -1215,7 +1270,7 @@ enum i915_power_well_id {
 #define   DPIO_P1_SHIFT			(21) /* 3 bits */
 #define   DPIO_P2_SHIFT			(16) /* 5 bits */
 #define   DPIO_N_SHIFT			(12) /* 4 bits */
-#define   DPIO_ENABLE_CALIBRATION	(1<<11)
+#define   DPIO_ENABLE_CALIBRATION	(1 << 11)
 #define   DPIO_M1DIV_SHIFT		(8) /* 3 bits */
 #define   DPIO_M2DIV_MASK		0xff
 #define _VLV_PLL_DW3_CH1		0x802c
@@ -1264,10 +1319,10 @@ enum i915_power_well_id {
 
 #define _VLV_PCS_DW0_CH0		0x8200
 #define _VLV_PCS_DW0_CH1		0x8400
-#define   DPIO_PCS_TX_LANE2_RESET	(1<<16)
-#define   DPIO_PCS_TX_LANE1_RESET	(1<<7)
-#define   DPIO_LEFT_TXFIFO_RST_MASTER2	(1<<4)
-#define   DPIO_RIGHT_TXFIFO_RST_MASTER2	(1<<3)
+#define   DPIO_PCS_TX_LANE2_RESET	(1 << 16)
+#define   DPIO_PCS_TX_LANE1_RESET	(1 << 7)
+#define   DPIO_LEFT_TXFIFO_RST_MASTER2	(1 << 4)
+#define   DPIO_RIGHT_TXFIFO_RST_MASTER2	(1 << 3)
 #define VLV_PCS_DW0(ch) _PORT(ch, _VLV_PCS_DW0_CH0, _VLV_PCS_DW0_CH1)
 
 #define _VLV_PCS01_DW0_CH0		0x200
@@ -1279,11 +1334,11 @@ enum i915_power_well_id {
 
 #define _VLV_PCS_DW1_CH0		0x8204
 #define _VLV_PCS_DW1_CH1		0x8404
-#define   CHV_PCS_REQ_SOFTRESET_EN	(1<<23)
-#define   DPIO_PCS_CLK_CRI_RXEB_EIOS_EN	(1<<22)
-#define   DPIO_PCS_CLK_CRI_RXDIGFILTSG_EN (1<<21)
+#define   CHV_PCS_REQ_SOFTRESET_EN	(1 << 23)
+#define   DPIO_PCS_CLK_CRI_RXEB_EIOS_EN	(1 << 22)
+#define   DPIO_PCS_CLK_CRI_RXDIGFILTSG_EN (1 << 21)
 #define   DPIO_PCS_CLK_DATAWIDTH_SHIFT	(6)
-#define   DPIO_PCS_CLK_SOFT_RESET	(1<<5)
+#define   DPIO_PCS_CLK_SOFT_RESET	(1 << 5)
 #define VLV_PCS_DW1(ch) _PORT(ch, _VLV_PCS_DW1_CH0, _VLV_PCS_DW1_CH1)
 
 #define _VLV_PCS01_DW1_CH0		0x204
@@ -1308,12 +1363,12 @@ enum i915_power_well_id {
 
 #define _VLV_PCS_DW9_CH0		0x8224
 #define _VLV_PCS_DW9_CH1		0x8424
-#define   DPIO_PCS_TX2MARGIN_MASK	(0x7<<13)
-#define   DPIO_PCS_TX2MARGIN_000	(0<<13)
-#define   DPIO_PCS_TX2MARGIN_101	(1<<13)
-#define   DPIO_PCS_TX1MARGIN_MASK	(0x7<<10)
-#define   DPIO_PCS_TX1MARGIN_000	(0<<10)
-#define   DPIO_PCS_TX1MARGIN_101	(1<<10)
+#define   DPIO_PCS_TX2MARGIN_MASK	(0x7 << 13)
+#define   DPIO_PCS_TX2MARGIN_000	(0 << 13)
+#define   DPIO_PCS_TX2MARGIN_101	(1 << 13)
+#define   DPIO_PCS_TX1MARGIN_MASK	(0x7 << 10)
+#define   DPIO_PCS_TX1MARGIN_000	(0 << 10)
+#define   DPIO_PCS_TX1MARGIN_101	(1 << 10)
 #define	VLV_PCS_DW9(ch) _PORT(ch, _VLV_PCS_DW9_CH0, _VLV_PCS_DW9_CH1)
 
 #define _VLV_PCS01_DW9_CH0		0x224
@@ -1325,14 +1380,14 @@ enum i915_power_well_id {
 
 #define _CHV_PCS_DW10_CH0		0x8228
 #define _CHV_PCS_DW10_CH1		0x8428
-#define   DPIO_PCS_SWING_CALC_TX0_TX2	(1<<30)
-#define   DPIO_PCS_SWING_CALC_TX1_TX3	(1<<31)
-#define   DPIO_PCS_TX2DEEMP_MASK	(0xf<<24)
-#define   DPIO_PCS_TX2DEEMP_9P5		(0<<24)
-#define   DPIO_PCS_TX2DEEMP_6P0		(2<<24)
-#define   DPIO_PCS_TX1DEEMP_MASK	(0xf<<16)
-#define   DPIO_PCS_TX1DEEMP_9P5		(0<<16)
-#define   DPIO_PCS_TX1DEEMP_6P0		(2<<16)
+#define   DPIO_PCS_SWING_CALC_TX0_TX2	(1 << 30)
+#define   DPIO_PCS_SWING_CALC_TX1_TX3	(1 << 31)
+#define   DPIO_PCS_TX2DEEMP_MASK	(0xf << 24)
+#define   DPIO_PCS_TX2DEEMP_9P5		(0 << 24)
+#define   DPIO_PCS_TX2DEEMP_6P0		(2 << 24)
+#define   DPIO_PCS_TX1DEEMP_MASK	(0xf << 16)
+#define   DPIO_PCS_TX1DEEMP_9P5		(0 << 16)
+#define   DPIO_PCS_TX1DEEMP_6P0		(2 << 16)
 #define CHV_PCS_DW10(ch) _PORT(ch, _CHV_PCS_DW10_CH0, _CHV_PCS_DW10_CH1)
 
 #define _VLV_PCS01_DW10_CH0		0x0228
@@ -1344,10 +1399,10 @@ enum i915_power_well_id {
 
 #define _VLV_PCS_DW11_CH0		0x822c
 #define _VLV_PCS_DW11_CH1		0x842c
-#define   DPIO_TX2_STAGGER_MASK(x)	((x)<<24)
-#define   DPIO_LANEDESKEW_STRAP_OVRD	(1<<3)
-#define   DPIO_LEFT_TXFIFO_RST_MASTER	(1<<1)
-#define   DPIO_RIGHT_TXFIFO_RST_MASTER	(1<<0)
+#define   DPIO_TX2_STAGGER_MASK(x)	((x) << 24)
+#define   DPIO_LANEDESKEW_STRAP_OVRD	(1 << 3)
+#define   DPIO_LEFT_TXFIFO_RST_MASTER	(1 << 1)
+#define   DPIO_RIGHT_TXFIFO_RST_MASTER	(1 << 0)
 #define VLV_PCS_DW11(ch) _PORT(ch, _VLV_PCS_DW11_CH0, _VLV_PCS_DW11_CH1)
 
 #define _VLV_PCS01_DW11_CH0		0x022c
@@ -1366,11 +1421,11 @@ enum i915_power_well_id {
 
 #define _VLV_PCS_DW12_CH0		0x8230
 #define _VLV_PCS_DW12_CH1		0x8430
-#define   DPIO_TX2_STAGGER_MULT(x)	((x)<<20)
-#define   DPIO_TX1_STAGGER_MULT(x)	((x)<<16)
-#define   DPIO_TX1_STAGGER_MASK(x)	((x)<<8)
-#define   DPIO_LANESTAGGER_STRAP_OVRD	(1<<6)
-#define   DPIO_LANESTAGGER_STRAP(x)	((x)<<0)
+#define   DPIO_TX2_STAGGER_MULT(x)	((x) << 20)
+#define   DPIO_TX1_STAGGER_MULT(x)	((x) << 16)
+#define   DPIO_TX1_STAGGER_MASK(x)	((x) << 8)
+#define   DPIO_LANESTAGGER_STRAP_OVRD	(1 << 6)
+#define   DPIO_LANESTAGGER_STRAP(x)	((x) << 0)
 #define VLV_PCS_DW12(ch) _PORT(ch, _VLV_PCS_DW12_CH0, _VLV_PCS_DW12_CH1)
 
 #define _VLV_PCS_DW14_CH0		0x8238
@@ -1391,7 +1446,7 @@ enum i915_power_well_id {
 #define _VLV_TX_DW3_CH0			0x828c
 #define _VLV_TX_DW3_CH1			0x848c
 /* The following bit for CHV phy */
-#define   DPIO_TX_UNIQ_TRANS_SCALE_EN	(1<<27)
+#define   DPIO_TX_UNIQ_TRANS_SCALE_EN	(1 << 27)
 #define   DPIO_SWING_MARGIN101_SHIFT	16
 #define   DPIO_SWING_MARGIN101_MASK	(0xff << DPIO_SWING_MARGIN101_SHIFT)
 #define VLV_TX_DW3(ch) _PORT(ch, _VLV_TX_DW3_CH0, _VLV_TX_DW3_CH1)
@@ -1410,7 +1465,7 @@ enum i915_power_well_id {
 
 #define _VLV_TX_DW5_CH0			0x8294
 #define _VLV_TX_DW5_CH1			0x8494
-#define   DPIO_TX_OCALINIT_EN		(1<<31)
+#define   DPIO_TX_OCALINIT_EN		(1 << 31)
 #define VLV_TX_DW5(ch) _PORT(ch, _VLV_TX_DW5_CH0, _VLV_TX_DW5_CH1)
 
 #define _VLV_TX_DW11_CH0		0x82ac
@@ -1640,10 +1695,10 @@ enum i915_power_well_id {
 #define  PORT_PLL_LOCK_THRESHOLD_SHIFT	1
 #define  PORT_PLL_LOCK_THRESHOLD_MASK	(0x7 << PORT_PLL_LOCK_THRESHOLD_SHIFT)
 /* PORT_PLL_10_A */
-#define  PORT_PLL_DCO_AMP_OVR_EN_H	(1<<27)
+#define  PORT_PLL_DCO_AMP_OVR_EN_H	(1 << 27)
 #define  PORT_PLL_DCO_AMP_DEFAULT	15
 #define  PORT_PLL_DCO_AMP_MASK		0x3c00
-#define  PORT_PLL_DCO_AMP(x)		((x)<<10)
+#define  PORT_PLL_DCO_AMP(x)		((x) << 10)
 #define _PORT_PLL_BASE(phy, ch)		_BXT_PHY_CH(phy, ch, \
 						    _PORT_PLL_0_B, \
 						    _PORT_PLL_0_C)
@@ -1666,6 +1721,26 @@ enum i915_power_well_id {
 #define ICL_PORT_CL_DW5(port)	_MMIO_PORT(port, _ICL_PORT_CL_DW5_A, \
 						 _ICL_PORT_CL_DW5_B)
 
+#define _CNL_PORT_CL_DW10_A		0x162028
+#define _ICL_PORT_CL_DW10_B		0x6c028
+#define ICL_PORT_CL_DW10(port)		_MMIO_PORT(port,	\
+						   _CNL_PORT_CL_DW10_A, \
+						   _ICL_PORT_CL_DW10_B)
+#define  PG_SEQ_DELAY_OVERRIDE_MASK	(3 << 25)
+#define  PG_SEQ_DELAY_OVERRIDE_SHIFT	25
+#define  PG_SEQ_DELAY_OVERRIDE_ENABLE	(1 << 24)
+#define  PWR_UP_ALL_LANES		(0x0 << 4)
+#define  PWR_DOWN_LN_3_2_1		(0xe << 4)
+#define  PWR_DOWN_LN_3_2		(0xc << 4)
+#define  PWR_DOWN_LN_3			(0x8 << 4)
+#define  PWR_DOWN_LN_2_1_0		(0x7 << 4)
+#define  PWR_DOWN_LN_1_0		(0x3 << 4)
+#define  PWR_DOWN_LN_1			(0x2 << 4)
+#define  PWR_DOWN_LN_3_1		(0xa << 4)
+#define  PWR_DOWN_LN_3_1_0		(0xb << 4)
+#define  PWR_DOWN_LN_MASK		(0xf << 4)
+#define  PWR_DOWN_LN_SHIFT		4
+
 #define _PORT_CL1CM_DW9_A		0x162024
 #define _PORT_CL1CM_DW9_BC		0x6C024
 #define   IREF0RC_OFFSET_SHIFT		8
@@ -1678,6 +1753,13 @@ enum i915_power_well_id {
 #define   IREF1RC_OFFSET_MASK		(0xFF << IREF1RC_OFFSET_SHIFT)
 #define BXT_PORT_CL1CM_DW10(phy)	_BXT_PHY((phy), _PORT_CL1CM_DW10_BC)
 
+#define _ICL_PORT_CL_DW12_A		0x162030
+#define _ICL_PORT_CL_DW12_B		0x6C030
+#define   ICL_LANE_ENABLE_AUX		(1 << 0)
+#define ICL_PORT_CL_DW12(port)		_MMIO_PORT((port),		\
+						   _ICL_PORT_CL_DW12_A, \
+						   _ICL_PORT_CL_DW12_B)
+
 #define _PORT_CL1CM_DW28_A		0x162070
 #define _PORT_CL1CM_DW28_BC		0x6C070
 #define   OCL1_POWER_DOWN_EN		(1 << 23)
@@ -1715,16 +1797,22 @@ enum i915_power_well_id {
 						    _CNL_PORT_PCS_DW1_LN0_D, \
 						    _CNL_PORT_PCS_DW1_LN0_AE, \
 						    _CNL_PORT_PCS_DW1_LN0_F))
+
 #define _ICL_PORT_PCS_DW1_GRP_A		0x162604
 #define _ICL_PORT_PCS_DW1_GRP_B		0x6C604
 #define _ICL_PORT_PCS_DW1_LN0_A		0x162804
 #define _ICL_PORT_PCS_DW1_LN0_B		0x6C804
+#define _ICL_PORT_PCS_DW1_AUX_A		0x162304
+#define _ICL_PORT_PCS_DW1_AUX_B		0x6c304
 #define ICL_PORT_PCS_DW1_GRP(port)	_MMIO_PORT(port,\
 						   _ICL_PORT_PCS_DW1_GRP_A, \
 						   _ICL_PORT_PCS_DW1_GRP_B)
 #define ICL_PORT_PCS_DW1_LN0(port)	_MMIO_PORT(port, \
 						   _ICL_PORT_PCS_DW1_LN0_A, \
 						   _ICL_PORT_PCS_DW1_LN0_B)
+#define ICL_PORT_PCS_DW1_AUX(port)	_MMIO_PORT(port, \
+						   _ICL_PORT_PCS_DW1_AUX_A, \
+						   _ICL_PORT_PCS_DW1_AUX_B)
 #define   COMMON_KEEPER_EN		(1 << 26)
 
 /* CNL Port TX registers */
@@ -1745,7 +1833,7 @@ enum i915_power_well_id {
 					       _CNL_PORT_TX_D_GRP_OFFSET, \
 					       _CNL_PORT_TX_AE_GRP_OFFSET, \
 					       _CNL_PORT_TX_F_GRP_OFFSET) + \
-					       4*(dw))
+					       4 * (dw))
 #define _CNL_PORT_TX_DW_LN0(port, dw)	(_PICK((port), \
 					       _CNL_PORT_TX_AE_LN0_OFFSET, \
 					       _CNL_PORT_TX_B_LN0_OFFSET, \
@@ -1753,7 +1841,7 @@ enum i915_power_well_id {
 					       _CNL_PORT_TX_D_LN0_OFFSET, \
 					       _CNL_PORT_TX_AE_LN0_OFFSET, \
 					       _CNL_PORT_TX_F_LN0_OFFSET) + \
-					       4*(dw))
+					       4 * (dw))
 
 #define CNL_PORT_TX_DW2_GRP(port)	_MMIO(_CNL_PORT_TX_DW_GRP((port), 2))
 #define CNL_PORT_TX_DW2_LN0(port)	_MMIO(_CNL_PORT_TX_DW_LN0((port), 2))
@@ -1761,16 +1849,23 @@ enum i915_power_well_id {
 #define _ICL_PORT_TX_DW2_GRP_B		0x6C688
 #define _ICL_PORT_TX_DW2_LN0_A		0x162888
 #define _ICL_PORT_TX_DW2_LN0_B		0x6C888
+#define _ICL_PORT_TX_DW2_AUX_A		0x162388
+#define _ICL_PORT_TX_DW2_AUX_B		0x6c388
 #define ICL_PORT_TX_DW2_GRP(port)	_MMIO_PORT(port, \
 						   _ICL_PORT_TX_DW2_GRP_A, \
 						   _ICL_PORT_TX_DW2_GRP_B)
 #define ICL_PORT_TX_DW2_LN0(port)	_MMIO_PORT(port, \
 						   _ICL_PORT_TX_DW2_LN0_A, \
 						   _ICL_PORT_TX_DW2_LN0_B)
+#define ICL_PORT_TX_DW2_AUX(port)	_MMIO_PORT(port, \
+						   _ICL_PORT_TX_DW2_AUX_A, \
+						   _ICL_PORT_TX_DW2_AUX_B)
 #define   SWING_SEL_UPPER(x)		(((x) >> 3) << 15)
 #define   SWING_SEL_UPPER_MASK		(1 << 15)
 #define   SWING_SEL_LOWER(x)		(((x) & 0x7) << 11)
 #define   SWING_SEL_LOWER_MASK		(0x7 << 11)
+#define   FRC_LATENCY_OPTIM_MASK	(0x7 << 8)
+#define   FRC_LATENCY_OPTIM_VAL(x)	((x) << 8)
 #define   RCOMP_SCALAR(x)		((x) << 0)
 #define   RCOMP_SCALAR_MASK		(0xFF << 0)
 
@@ -1779,21 +1874,26 @@ enum i915_power_well_id {
 #define CNL_PORT_TX_DW4_GRP(port)	_MMIO(_CNL_PORT_TX_DW_GRP((port), 4))
 #define CNL_PORT_TX_DW4_LN0(port)	_MMIO(_CNL_PORT_TX_DW_LN0((port), 4))
 #define CNL_PORT_TX_DW4_LN(port, ln)   _MMIO(_CNL_PORT_TX_DW_LN0((port), 4) + \
-					     (ln * (_CNL_PORT_TX_DW4_LN1_AE - \
+					   ((ln) * (_CNL_PORT_TX_DW4_LN1_AE - \
 						    _CNL_PORT_TX_DW4_LN0_AE)))
 #define _ICL_PORT_TX_DW4_GRP_A		0x162690
 #define _ICL_PORT_TX_DW4_GRP_B		0x6C690
 #define _ICL_PORT_TX_DW4_LN0_A		0x162890
 #define _ICL_PORT_TX_DW4_LN1_A		0x162990
 #define _ICL_PORT_TX_DW4_LN0_B		0x6C890
+#define _ICL_PORT_TX_DW4_AUX_A		0x162390
+#define _ICL_PORT_TX_DW4_AUX_B		0x6c390
 #define ICL_PORT_TX_DW4_GRP(port)	_MMIO_PORT(port, \
 						   _ICL_PORT_TX_DW4_GRP_A, \
 						   _ICL_PORT_TX_DW4_GRP_B)
 #define ICL_PORT_TX_DW4_LN(port, ln)	_MMIO(_PORT(port, \
 						   _ICL_PORT_TX_DW4_LN0_A, \
 						   _ICL_PORT_TX_DW4_LN0_B) + \
-					      (ln * (_ICL_PORT_TX_DW4_LN1_A - \
-						     _ICL_PORT_TX_DW4_LN0_A)))
+					     ((ln) * (_ICL_PORT_TX_DW4_LN1_A - \
+						      _ICL_PORT_TX_DW4_LN0_A)))
+#define ICL_PORT_TX_DW4_AUX(port)	_MMIO_PORT(port, \
+						   _ICL_PORT_TX_DW4_AUX_A, \
+						   _ICL_PORT_TX_DW4_AUX_B)
 #define   LOADGEN_SELECT		(1 << 31)
 #define   POST_CURSOR_1(x)		((x) << 12)
 #define   POST_CURSOR_1_MASK		(0x3F << 12)
@@ -1808,12 +1908,17 @@ enum i915_power_well_id {
 #define _ICL_PORT_TX_DW5_GRP_B		0x6C694
 #define _ICL_PORT_TX_DW5_LN0_A		0x162894
 #define _ICL_PORT_TX_DW5_LN0_B		0x6C894
+#define _ICL_PORT_TX_DW5_AUX_A		0x162394
+#define _ICL_PORT_TX_DW5_AUX_B		0x6c394
 #define ICL_PORT_TX_DW5_GRP(port)	_MMIO_PORT(port, \
 						   _ICL_PORT_TX_DW5_GRP_A, \
 						   _ICL_PORT_TX_DW5_GRP_B)
 #define ICL_PORT_TX_DW5_LN0(port)	_MMIO_PORT(port, \
 						   _ICL_PORT_TX_DW5_LN0_A, \
 						   _ICL_PORT_TX_DW5_LN0_B)
+#define ICL_PORT_TX_DW5_AUX(port)	_MMIO_PORT(port, \
+						   _ICL_PORT_TX_DW5_AUX_A, \
+						   _ICL_PORT_TX_DW5_AUX_B)
 #define   TX_TRAINING_EN		(1 << 31)
 #define   TAP2_DISABLE			(1 << 30)
 #define   TAP3_DISABLE			(1 << 29)
@@ -1990,6 +2095,11 @@ enum i915_power_well_id {
 						   _ICL_PORT_COMP_DW10_A, \
 						   _ICL_PORT_COMP_DW10_B)
 
+/* ICL PHY DFLEX registers */
+#define PORT_TX_DFLEXDPMLE1		_MMIO(0x1638C0)
+#define   DFLEXDPMLE1_DPMLETC_MASK(n)	(0xf << (4 * (n)))
+#define   DFLEXDPMLE1_DPMLETC(n, x)	((x) << (4 * (n)))
+
 /* BXT PHY Ref registers */
 #define _PORT_REF_DW3_A			0x16218C
 #define _PORT_REF_DW3_BC		0x6C18C
@@ -2134,8 +2244,8 @@ enum i915_power_well_id {
 /* SKL balance leg register */
 #define DISPIO_CR_TX_BMU_CR0		_MMIO(0x6C00C)
 /* I_boost values */
-#define BALANCE_LEG_SHIFT(port)		(8+3*(port))
-#define BALANCE_LEG_MASK(port)		(7<<(8+3*(port)))
+#define BALANCE_LEG_SHIFT(port)		(8 + 3 * (port))
+#define BALANCE_LEG_MASK(port)		(7 << (8 + 3 * (port)))
 /* Balance leg disable bits */
 #define BALANCE_LEG_DISABLE_SHIFT	23
 #define BALANCE_LEG_DISABLE(port)	(1 << (23 + (port)))
@@ -2155,10 +2265,10 @@ enum i915_power_well_id {
 #define   I830_FENCE_TILING_Y_SHIFT	12
 #define   I830_FENCE_SIZE_BITS(size)	((ffs((size) >> 19) - 1) << 8)
 #define   I830_FENCE_PITCH_SHIFT	4
-#define   I830_FENCE_REG_VALID		(1<<0)
+#define   I830_FENCE_REG_VALID		(1 << 0)
 #define   I915_FENCE_MAX_PITCH_VAL	4
 #define   I830_FENCE_MAX_PITCH_VAL	6
-#define   I830_FENCE_MAX_SIZE_VAL	(1<<8)
+#define   I830_FENCE_MAX_SIZE_VAL	(1 << 8)
 
 #define   I915_FENCE_START_MASK		0x0ff00000
 #define   I915_FENCE_SIZE_BITS(size)	((ffs((size) >> 20) - 1) << 8)
@@ -2167,7 +2277,7 @@ enum i915_power_well_id {
 #define FENCE_REG_965_HI(i)		_MMIO(0x03000 + (i) * 8 + 4)
 #define   I965_FENCE_PITCH_SHIFT	2
 #define   I965_FENCE_TILING_Y_SHIFT	1
-#define   I965_FENCE_REG_VALID		(1<<0)
+#define   I965_FENCE_REG_VALID		(1 << 0)
 #define   I965_FENCE_MAX_PITCH_VAL	0x0400
 
 #define FENCE_REG_GEN6_LO(i)		_MMIO(0x100000 + (i) * 8)
@@ -2190,13 +2300,13 @@ enum i915_power_well_id {
 #define   PGTBL_ADDRESS_LO_MASK	0xfffff000 /* bits [31:12] */
 #define   PGTBL_ADDRESS_HI_MASK	0x000000f0 /* bits [35:32] (gen4) */
 #define PGTBL_ER	_MMIO(0x02024)
-#define PRB0_BASE	(0x2030-0x30)
-#define PRB1_BASE	(0x2040-0x30) /* 830,gen3 */
-#define PRB2_BASE	(0x2050-0x30) /* gen3 */
-#define SRB0_BASE	(0x2100-0x30) /* gen2 */
-#define SRB1_BASE	(0x2110-0x30) /* gen2 */
-#define SRB2_BASE	(0x2120-0x30) /* 830 */
-#define SRB3_BASE	(0x2130-0x30) /* 830 */
+#define PRB0_BASE	(0x2030 - 0x30)
+#define PRB1_BASE	(0x2040 - 0x30) /* 830,gen3 */
+#define PRB2_BASE	(0x2050 - 0x30) /* gen3 */
+#define SRB0_BASE	(0x2100 - 0x30) /* gen2 */
+#define SRB1_BASE	(0x2110 - 0x30) /* gen2 */
+#define SRB2_BASE	(0x2120 - 0x30) /* 830 */
+#define SRB3_BASE	(0x2130 - 0x30) /* 830 */
 #define RENDER_RING_BASE	0x02000
 #define BSD_RING_BASE		0x04000
 #define GEN6_BSD_RING_BASE	0x12000
@@ -2209,14 +2319,14 @@ enum i915_power_well_id {
 #define GEN11_VEBOX_RING_BASE		0x1c8000
 #define GEN11_VEBOX2_RING_BASE		0x1d8000
 #define BLT_RING_BASE		0x22000
-#define RING_TAIL(base)		_MMIO((base)+0x30)
-#define RING_HEAD(base)		_MMIO((base)+0x34)
-#define RING_START(base)	_MMIO((base)+0x38)
-#define RING_CTL(base)		_MMIO((base)+0x3c)
+#define RING_TAIL(base)		_MMIO((base) + 0x30)
+#define RING_HEAD(base)		_MMIO((base) + 0x34)
+#define RING_START(base)	_MMIO((base) + 0x38)
+#define RING_CTL(base)		_MMIO((base) + 0x3c)
 #define   RING_CTL_SIZE(size)	((size) - PAGE_SIZE) /* in bytes -> pages */
-#define RING_SYNC_0(base)	_MMIO((base)+0x40)
-#define RING_SYNC_1(base)	_MMIO((base)+0x44)
-#define RING_SYNC_2(base)	_MMIO((base)+0x48)
+#define RING_SYNC_0(base)	_MMIO((base) + 0x40)
+#define RING_SYNC_1(base)	_MMIO((base) + 0x44)
+#define RING_SYNC_2(base)	_MMIO((base) + 0x48)
 #define GEN6_RVSYNC	(RING_SYNC_0(RENDER_RING_BASE))
 #define GEN6_RBSYNC	(RING_SYNC_1(RENDER_RING_BASE))
 #define GEN6_RVESYNC	(RING_SYNC_2(RENDER_RING_BASE))
@@ -2230,21 +2340,22 @@ enum i915_power_well_id {
 #define GEN6_VERSYNC	(RING_SYNC_1(VEBOX_RING_BASE))
 #define GEN6_VEVSYNC	(RING_SYNC_2(VEBOX_RING_BASE))
 #define GEN6_NOSYNC	INVALID_MMIO_REG
-#define RING_PSMI_CTL(base)	_MMIO((base)+0x50)
-#define RING_MAX_IDLE(base)	_MMIO((base)+0x54)
-#define RING_HWS_PGA(base)	_MMIO((base)+0x80)
-#define RING_HWS_PGA_GEN6(base)	_MMIO((base)+0x2080)
-#define RING_RESET_CTL(base)	_MMIO((base)+0xd0)
+#define RING_PSMI_CTL(base)	_MMIO((base) + 0x50)
+#define RING_MAX_IDLE(base)	_MMIO((base) + 0x54)
+#define RING_HWS_PGA(base)	_MMIO((base) + 0x80)
+#define RING_HWS_PGA_GEN6(base)	_MMIO((base) + 0x2080)
+#define RING_RESET_CTL(base)	_MMIO((base) + 0xd0)
 #define   RESET_CTL_REQUEST_RESET  (1 << 0)
 #define   RESET_CTL_READY_TO_RESET (1 << 1)
+#define RING_SEMA_WAIT_POLL(base) _MMIO((base) + 0x24c)
 
 #define HSW_GTT_CACHE_EN	_MMIO(0x4024)
 #define   GTT_CACHE_EN_ALL	0xF0007FFF
 #define GEN7_WR_WATERMARK	_MMIO(0x4028)
 #define GEN7_GFX_PRIO_CTRL	_MMIO(0x402C)
 #define ARB_MODE		_MMIO(0x4030)
-#define   ARB_MODE_SWIZZLE_SNB	(1<<4)
-#define   ARB_MODE_SWIZZLE_IVB	(1<<5)
+#define   ARB_MODE_SWIZZLE_SNB	(1 << 4)
+#define   ARB_MODE_SWIZZLE_IVB	(1 << 5)
 #define GEN7_GFX_PEND_TLB0	_MMIO(0x4034)
 #define GEN7_GFX_PEND_TLB1	_MMIO(0x4038)
 /* L3, CVS, ZTLB, RCC, CASC LRA min, max values */
@@ -2254,30 +2365,30 @@ enum i915_power_well_id {
 #define GEN7_GFX_MAX_REQ_COUNT		_MMIO(0x4074)
 
 #define GAMTARBMODE		_MMIO(0x04a08)
-#define   ARB_MODE_BWGTLB_DISABLE (1<<9)
-#define   ARB_MODE_SWIZZLE_BDW	(1<<1)
+#define   ARB_MODE_BWGTLB_DISABLE (1 << 9)
+#define   ARB_MODE_SWIZZLE_BDW	(1 << 1)
 #define RENDER_HWS_PGA_GEN7	_MMIO(0x04080)
-#define RING_FAULT_REG(engine)	_MMIO(0x4094 + 0x100*(engine)->hw_id)
+#define RING_FAULT_REG(engine)	_MMIO(0x4094 + 0x100 * (engine)->hw_id)
 #define GEN8_RING_FAULT_REG	_MMIO(0x4094)
 #define   GEN8_RING_FAULT_ENGINE_ID(x)	(((x) >> 12) & 0x7)
-#define   RING_FAULT_GTTSEL_MASK (1<<11)
+#define   RING_FAULT_GTTSEL_MASK (1 << 11)
 #define   RING_FAULT_SRCID(x)	(((x) >> 3) & 0xff)
 #define   RING_FAULT_FAULT_TYPE(x) (((x) >> 1) & 0x3)
-#define   RING_FAULT_VALID	(1<<0)
+#define   RING_FAULT_VALID	(1 << 0)
 #define DONE_REG		_MMIO(0x40b0)
 #define GEN8_PRIVATE_PAT_LO	_MMIO(0x40e0)
 #define GEN8_PRIVATE_PAT_HI	_MMIO(0x40e0 + 4)
-#define GEN10_PAT_INDEX(index)	_MMIO(0x40e0 + (index)*4)
+#define GEN10_PAT_INDEX(index)	_MMIO(0x40e0 + (index) * 4)
 #define BSD_HWS_PGA_GEN7	_MMIO(0x04180)
 #define BLT_HWS_PGA_GEN7	_MMIO(0x04280)
 #define VEBOX_HWS_PGA_GEN7	_MMIO(0x04380)
-#define RING_ACTHD(base)	_MMIO((base)+0x74)
-#define RING_ACTHD_UDW(base)	_MMIO((base)+0x5c)
-#define RING_NOPID(base)	_MMIO((base)+0x94)
-#define RING_IMR(base)		_MMIO((base)+0xa8)
-#define RING_HWSTAM(base)	_MMIO((base)+0x98)
-#define RING_TIMESTAMP(base)		_MMIO((base)+0x358)
-#define RING_TIMESTAMP_UDW(base)	_MMIO((base)+0x358 + 4)
+#define RING_ACTHD(base)	_MMIO((base) + 0x74)
+#define RING_ACTHD_UDW(base)	_MMIO((base) + 0x5c)
+#define RING_NOPID(base)	_MMIO((base) + 0x94)
+#define RING_IMR(base)		_MMIO((base) + 0xa8)
+#define RING_HWSTAM(base)	_MMIO((base) + 0x98)
+#define RING_TIMESTAMP(base)		_MMIO((base) + 0x358)
+#define RING_TIMESTAMP_UDW(base)	_MMIO((base) + 0x358 + 4)
 #define   TAIL_ADDR		0x001FFFF8
 #define   HEAD_WRAP_COUNT	0xFFE00000
 #define   HEAD_WRAP_ONE		0x00200000
@@ -2290,24 +2401,25 @@ enum i915_power_well_id {
 #define   RING_VALID_MASK	0x00000001
 #define   RING_VALID		0x00000001
 #define   RING_INVALID		0x00000000
-#define   RING_WAIT_I8XX	(1<<0) /* gen2, PRBx_HEAD */
-#define   RING_WAIT		(1<<11) /* gen3+, PRBx_CTL */
-#define   RING_WAIT_SEMAPHORE	(1<<10) /* gen6+ */
+#define   RING_WAIT_I8XX	(1 << 0) /* gen2, PRBx_HEAD */
+#define   RING_WAIT		(1 << 11) /* gen3+, PRBx_CTL */
+#define   RING_WAIT_SEMAPHORE	(1 << 10) /* gen6+ */
 
-#define RING_FORCE_TO_NONPRIV(base, i) _MMIO(((base)+0x4D0) + (i)*4)
+#define RING_FORCE_TO_NONPRIV(base, i) _MMIO(((base) + 0x4D0) + (i) * 4)
 #define   RING_MAX_NONPRIV_SLOTS  12
 
 #define GEN7_TLB_RD_ADDR	_MMIO(0x4700)
 
 #define GEN9_GAMT_ECO_REG_RW_IA _MMIO(0x4ab0)
-#define   GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS	(1<<18)
+#define   GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS	(1 << 18)
 
 #define GEN8_GAMW_ECO_DEV_RW_IA _MMIO(0x4080)
 #define   GAMW_ECO_ENABLE_64K_IPS_FIELD 0xF
 
 #define GAMT_CHKN_BIT_REG	_MMIO(0x4ab8)
-#define   GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING	(1<<28)
-#define   GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT	(1<<24)
+#define   GAMT_CHKN_DISABLE_L3_COH_PIPE			(1 << 31)
+#define   GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING	(1 << 28)
+#define   GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT	(1 << 24)
 
 #if 0
 #define PRB0_TAIL	_MMIO(0x2030)
@@ -2333,19 +2445,19 @@ enum i915_power_well_id {
 #define   GEN11_MCR_SLICE_MASK		GEN11_MCR_SLICE(0xf)
 #define   GEN11_MCR_SUBSLICE(subslice)	(((subslice) & 0x7) << 24)
 #define   GEN11_MCR_SUBSLICE_MASK	GEN11_MCR_SUBSLICE(0x7)
-#define RING_IPEIR(base)	_MMIO((base)+0x64)
-#define RING_IPEHR(base)	_MMIO((base)+0x68)
+#define RING_IPEIR(base)	_MMIO((base) + 0x64)
+#define RING_IPEHR(base)	_MMIO((base) + 0x68)
 /*
  * On GEN4, only the render ring INSTDONE exists and has a different
  * layout than the GEN7+ version.
  * The GEN2 counterpart of this register is GEN2_INSTDONE.
  */
-#define RING_INSTDONE(base)	_MMIO((base)+0x6c)
-#define RING_INSTPS(base)	_MMIO((base)+0x70)
-#define RING_DMA_FADD(base)	_MMIO((base)+0x78)
-#define RING_DMA_FADD_UDW(base)	_MMIO((base)+0x60) /* gen8+ */
-#define RING_INSTPM(base)	_MMIO((base)+0xc0)
-#define RING_MI_MODE(base)	_MMIO((base)+0x9c)
+#define RING_INSTDONE(base)	_MMIO((base) + 0x6c)
+#define RING_INSTPS(base)	_MMIO((base) + 0x70)
+#define RING_DMA_FADD(base)	_MMIO((base) + 0x78)
+#define RING_DMA_FADD_UDW(base)	_MMIO((base) + 0x60) /* gen8+ */
+#define RING_INSTPM(base)	_MMIO((base) + 0xc0)
+#define RING_MI_MODE(base)	_MMIO((base) + 0x9c)
 #define INSTPS		_MMIO(0x2070) /* 965+ only */
 #define GEN4_INSTDONE1	_MMIO(0x207c) /* 965+ only, aka INSTDONE_2 on SNB */
 #define ACTHD_I965	_MMIO(0x2074)
@@ -2353,37 +2465,37 @@ enum i915_power_well_id {
 #define HWS_ADDRESS_MASK	0xfffff000
 #define HWS_START_ADDRESS_SHIFT	4
 #define PWRCTXA		_MMIO(0x2088) /* 965GM+ only */
-#define   PWRCTX_EN	(1<<0)
+#define   PWRCTX_EN	(1 << 0)
 #define IPEIR		_MMIO(0x2088)
 #define IPEHR		_MMIO(0x208c)
 #define GEN2_INSTDONE	_MMIO(0x2090)
 #define NOPID		_MMIO(0x2094)
 #define HWSTAM		_MMIO(0x2098)
 #define DMA_FADD_I8XX	_MMIO(0x20d0)
-#define RING_BBSTATE(base)	_MMIO((base)+0x110)
+#define RING_BBSTATE(base)	_MMIO((base) + 0x110)
 #define   RING_BB_PPGTT		(1 << 5)
-#define RING_SBBADDR(base)	_MMIO((base)+0x114) /* hsw+ */
-#define RING_SBBSTATE(base)	_MMIO((base)+0x118) /* hsw+ */
-#define RING_SBBADDR_UDW(base)	_MMIO((base)+0x11c) /* gen8+ */
-#define RING_BBADDR(base)	_MMIO((base)+0x140)
-#define RING_BBADDR_UDW(base)	_MMIO((base)+0x168) /* gen8+ */
-#define RING_BB_PER_CTX_PTR(base)	_MMIO((base)+0x1c0) /* gen8+ */
-#define RING_INDIRECT_CTX(base)		_MMIO((base)+0x1c4) /* gen8+ */
-#define RING_INDIRECT_CTX_OFFSET(base)	_MMIO((base)+0x1c8) /* gen8+ */
-#define RING_CTX_TIMESTAMP(base)	_MMIO((base)+0x3a8) /* gen8+ */
+#define RING_SBBADDR(base)	_MMIO((base) + 0x114) /* hsw+ */
+#define RING_SBBSTATE(base)	_MMIO((base) + 0x118) /* hsw+ */
+#define RING_SBBADDR_UDW(base)	_MMIO((base) + 0x11c) /* gen8+ */
+#define RING_BBADDR(base)	_MMIO((base) + 0x140)
+#define RING_BBADDR_UDW(base)	_MMIO((base) + 0x168) /* gen8+ */
+#define RING_BB_PER_CTX_PTR(base)	_MMIO((base) + 0x1c0) /* gen8+ */
+#define RING_INDIRECT_CTX(base)		_MMIO((base) + 0x1c4) /* gen8+ */
+#define RING_INDIRECT_CTX_OFFSET(base)	_MMIO((base) + 0x1c8) /* gen8+ */
+#define RING_CTX_TIMESTAMP(base)	_MMIO((base) + 0x3a8) /* gen8+ */
 
 #define ERROR_GEN6	_MMIO(0x40a0)
 #define GEN7_ERR_INT	_MMIO(0x44040)
-#define   ERR_INT_POISON		(1<<31)
-#define   ERR_INT_MMIO_UNCLAIMED	(1<<13)
-#define   ERR_INT_PIPE_CRC_DONE_C	(1<<8)
-#define   ERR_INT_FIFO_UNDERRUN_C	(1<<6)
-#define   ERR_INT_PIPE_CRC_DONE_B	(1<<5)
-#define   ERR_INT_FIFO_UNDERRUN_B	(1<<3)
-#define   ERR_INT_PIPE_CRC_DONE_A	(1<<2)
-#define   ERR_INT_PIPE_CRC_DONE(pipe)	(1<<(2 + (pipe)*3))
-#define   ERR_INT_FIFO_UNDERRUN_A	(1<<0)
-#define   ERR_INT_FIFO_UNDERRUN(pipe)	(1<<((pipe)*3))
+#define   ERR_INT_POISON		(1 << 31)
+#define   ERR_INT_MMIO_UNCLAIMED	(1 << 13)
+#define   ERR_INT_PIPE_CRC_DONE_C	(1 << 8)
+#define   ERR_INT_FIFO_UNDERRUN_C	(1 << 6)
+#define   ERR_INT_PIPE_CRC_DONE_B	(1 << 5)
+#define   ERR_INT_FIFO_UNDERRUN_B	(1 << 3)
+#define   ERR_INT_PIPE_CRC_DONE_A	(1 << 2)
+#define   ERR_INT_PIPE_CRC_DONE(pipe)	(1 << (2 + (pipe) * 3))
+#define   ERR_INT_FIFO_UNDERRUN_A	(1 << 0)
+#define   ERR_INT_FIFO_UNDERRUN(pipe)	(1 << ((pipe) * 3))
 
 #define GEN8_FAULT_TLB_DATA0		_MMIO(0x4b10)
 #define GEN8_FAULT_TLB_DATA1		_MMIO(0x4b14)
@@ -2391,7 +2503,7 @@ enum i915_power_well_id {
 #define   FAULT_GTT_SEL			(1 << 4)
 
 #define FPGA_DBG		_MMIO(0x42300)
-#define   FPGA_DBG_RM_NOCLAIM	(1<<31)
+#define   FPGA_DBG_RM_NOCLAIM	(1 << 31)
 
 #define CLAIM_ER		_MMIO(VLV_DISPLAY_BASE + 0x2028)
 #define   CLAIM_ER_CLR		(1 << 31)
@@ -2400,22 +2512,22 @@ enum i915_power_well_id {
 
 #define DERRMR		_MMIO(0x44050)
 /* Note that HBLANK events are reserved on bdw+ */
-#define   DERRMR_PIPEA_SCANLINE		(1<<0)
-#define   DERRMR_PIPEA_PRI_FLIP_DONE	(1<<1)
-#define   DERRMR_PIPEA_SPR_FLIP_DONE	(1<<2)
-#define   DERRMR_PIPEA_VBLANK		(1<<3)
-#define   DERRMR_PIPEA_HBLANK		(1<<5)
-#define   DERRMR_PIPEB_SCANLINE 	(1<<8)
-#define   DERRMR_PIPEB_PRI_FLIP_DONE	(1<<9)
-#define   DERRMR_PIPEB_SPR_FLIP_DONE	(1<<10)
-#define   DERRMR_PIPEB_VBLANK		(1<<11)
-#define   DERRMR_PIPEB_HBLANK		(1<<13)
+#define   DERRMR_PIPEA_SCANLINE		(1 << 0)
+#define   DERRMR_PIPEA_PRI_FLIP_DONE	(1 << 1)
+#define   DERRMR_PIPEA_SPR_FLIP_DONE	(1 << 2)
+#define   DERRMR_PIPEA_VBLANK		(1 << 3)
+#define   DERRMR_PIPEA_HBLANK		(1 << 5)
+#define   DERRMR_PIPEB_SCANLINE		(1 << 8)
+#define   DERRMR_PIPEB_PRI_FLIP_DONE	(1 << 9)
+#define   DERRMR_PIPEB_SPR_FLIP_DONE	(1 << 10)
+#define   DERRMR_PIPEB_VBLANK		(1 << 11)
+#define   DERRMR_PIPEB_HBLANK		(1 << 13)
 /* Note that PIPEC is not a simple translation of PIPEA/PIPEB */
-#define   DERRMR_PIPEC_SCANLINE		(1<<14)
-#define   DERRMR_PIPEC_PRI_FLIP_DONE	(1<<15)
-#define   DERRMR_PIPEC_SPR_FLIP_DONE	(1<<20)
-#define   DERRMR_PIPEC_VBLANK		(1<<21)
-#define   DERRMR_PIPEC_HBLANK		(1<<22)
+#define   DERRMR_PIPEC_SCANLINE		(1 << 14)
+#define   DERRMR_PIPEC_PRI_FLIP_DONE	(1 << 15)
+#define   DERRMR_PIPEC_SPR_FLIP_DONE	(1 << 20)
+#define   DERRMR_PIPEC_VBLANK		(1 << 21)
+#define   DERRMR_PIPEC_HBLANK		(1 << 22)
 
 
 /* GM45+ chicken bits -- debug workaround bits that may be required
@@ -2439,7 +2551,7 @@ enum i915_power_well_id {
 #define  _3D_CHICKEN_SF_DISABLE_OBJEND_CULL		(1 << 10)
 #define  _3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE	(1 << 5)
 #define  _3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL		(1 << 5)
-#define  _3D_CHICKEN_SDE_LIMIT_FIFO_POLY_DEPTH(x)	((x)<<1) /* gen8+ */
+#define  _3D_CHICKEN_SDE_LIMIT_FIFO_POLY_DEPTH(x)	((x) << 1) /* gen8+ */
 #define  _3D_CHICKEN3_SF_DISABLE_PIPELINED_ATTR_FETCH	(1 << 1) /* gen6 */
 
 #define MI_MODE		_MMIO(0x209c)
@@ -2478,22 +2590,22 @@ enum i915_power_well_id {
 
 #define GFX_MODE	_MMIO(0x2520)
 #define GFX_MODE_GEN7	_MMIO(0x229c)
-#define RING_MODE_GEN7(engine)	_MMIO((engine)->mmio_base+0x29c)
-#define   GFX_RUN_LIST_ENABLE		(1<<15)
-#define   GFX_INTERRUPT_STEERING	(1<<14)
-#define   GFX_TLB_INVALIDATE_EXPLICIT	(1<<13)
-#define   GFX_SURFACE_FAULT_ENABLE	(1<<12)
-#define   GFX_REPLAY_MODE		(1<<11)
-#define   GFX_PSMI_GRANULARITY		(1<<10)
-#define   GFX_PPGTT_ENABLE		(1<<9)
-#define   GEN8_GFX_PPGTT_48B		(1<<7)
-
-#define   GFX_FORWARD_VBLANK_MASK	(3<<5)
-#define   GFX_FORWARD_VBLANK_NEVER	(0<<5)
-#define   GFX_FORWARD_VBLANK_ALWAYS	(1<<5)
-#define   GFX_FORWARD_VBLANK_COND	(2<<5)
-
-#define   GEN11_GFX_DISABLE_LEGACY_MODE	(1<<3)
+#define RING_MODE_GEN7(engine)	_MMIO((engine)->mmio_base + 0x29c)
+#define   GFX_RUN_LIST_ENABLE		(1 << 15)
+#define   GFX_INTERRUPT_STEERING	(1 << 14)
+#define   GFX_TLB_INVALIDATE_EXPLICIT	(1 << 13)
+#define   GFX_SURFACE_FAULT_ENABLE	(1 << 12)
+#define   GFX_REPLAY_MODE		(1 << 11)
+#define   GFX_PSMI_GRANULARITY		(1 << 10)
+#define   GFX_PPGTT_ENABLE		(1 << 9)
+#define   GEN8_GFX_PPGTT_48B		(1 << 7)
+
+#define   GFX_FORWARD_VBLANK_MASK	(3 << 5)
+#define   GFX_FORWARD_VBLANK_NEVER	(0 << 5)
+#define   GFX_FORWARD_VBLANK_ALWAYS	(1 << 5)
+#define   GFX_FORWARD_VBLANK_COND	(2 << 5)
+
+#define   GEN11_GFX_DISABLE_LEGACY_MODE	(1 << 3)
 
 #define VLV_DISPLAY_BASE 0x180000
 #define VLV_MIPI_BASE VLV_DISPLAY_BASE
@@ -2507,8 +2619,8 @@ enum i915_power_well_id {
 #define IMR		_MMIO(0x20a8)
 #define ISR		_MMIO(0x20ac)
 #define VLV_GUNIT_CLOCK_GATE	_MMIO(VLV_DISPLAY_BASE + 0x2060)
-#define   GINT_DIS		(1<<22)
-#define   GCFG_DIS		(1<<8)
+#define   GINT_DIS		(1 << 22)
+#define   GCFG_DIS		(1 << 8)
 #define VLV_GUNIT_CLOCK_GATE2	_MMIO(VLV_DISPLAY_BASE + 0x2064)
 #define VLV_IIR_RW	_MMIO(VLV_DISPLAY_BASE + 0x2084)
 #define VLV_IER		_MMIO(VLV_DISPLAY_BASE + 0x20a0)
@@ -2518,35 +2630,35 @@ enum i915_power_well_id {
 #define VLV_PCBR	_MMIO(VLV_DISPLAY_BASE + 0x2120)
 #define VLV_PCBR_ADDR_SHIFT	12
 
-#define   DISPLAY_PLANE_FLIP_PENDING(plane) (1<<(11-(plane))) /* A and B only */
+#define   DISPLAY_PLANE_FLIP_PENDING(plane) (1 << (11 - (plane))) /* A and B only */
 #define EIR		_MMIO(0x20b0)
 #define EMR		_MMIO(0x20b4)
 #define ESR		_MMIO(0x20b8)
-#define   GM45_ERROR_PAGE_TABLE				(1<<5)
-#define   GM45_ERROR_MEM_PRIV				(1<<4)
-#define   I915_ERROR_PAGE_TABLE				(1<<4)
-#define   GM45_ERROR_CP_PRIV				(1<<3)
-#define   I915_ERROR_MEMORY_REFRESH			(1<<1)
-#define   I915_ERROR_INSTRUCTION			(1<<0)
+#define   GM45_ERROR_PAGE_TABLE				(1 << 5)
+#define   GM45_ERROR_MEM_PRIV				(1 << 4)
+#define   I915_ERROR_PAGE_TABLE				(1 << 4)
+#define   GM45_ERROR_CP_PRIV				(1 << 3)
+#define   I915_ERROR_MEMORY_REFRESH			(1 << 1)
+#define   I915_ERROR_INSTRUCTION			(1 << 0)
 #define INSTPM	        _MMIO(0x20c0)
-#define   INSTPM_SELF_EN (1<<12) /* 915GM only */
-#define   INSTPM_AGPBUSY_INT_EN (1<<11) /* gen3: when disabled, pending interrupts
+#define   INSTPM_SELF_EN (1 << 12) /* 915GM only */
+#define   INSTPM_AGPBUSY_INT_EN (1 << 11) /* gen3: when disabled, pending interrupts
 					will not assert AGPBUSY# and will only
 					be delivered when out of C3. */
-#define   INSTPM_FORCE_ORDERING				(1<<7) /* GEN6+ */
-#define   INSTPM_TLB_INVALIDATE	(1<<9)
-#define   INSTPM_SYNC_FLUSH	(1<<5)
+#define   INSTPM_FORCE_ORDERING				(1 << 7) /* GEN6+ */
+#define   INSTPM_TLB_INVALIDATE	(1 << 9)
+#define   INSTPM_SYNC_FLUSH	(1 << 5)
 #define ACTHD	        _MMIO(0x20c8)
 #define MEM_MODE	_MMIO(0x20cc)
-#define   MEM_DISPLAY_B_TRICKLE_FEED_DISABLE (1<<3) /* 830 only */
-#define   MEM_DISPLAY_A_TRICKLE_FEED_DISABLE (1<<2) /* 830/845 only */
-#define   MEM_DISPLAY_TRICKLE_FEED_DISABLE (1<<2) /* 85x only */
+#define   MEM_DISPLAY_B_TRICKLE_FEED_DISABLE (1 << 3) /* 830 only */
+#define   MEM_DISPLAY_A_TRICKLE_FEED_DISABLE (1 << 2) /* 830/845 only */
+#define   MEM_DISPLAY_TRICKLE_FEED_DISABLE (1 << 2) /* 85x only */
 #define FW_BLC		_MMIO(0x20d8)
 #define FW_BLC2		_MMIO(0x20dc)
 #define FW_BLC_SELF	_MMIO(0x20e0) /* 915+ only */
-#define   FW_BLC_SELF_EN_MASK      (1<<31)
-#define   FW_BLC_SELF_FIFO_MASK    (1<<16) /* 945 only */
-#define   FW_BLC_SELF_EN           (1<<15) /* 945 only */
+#define   FW_BLC_SELF_EN_MASK      (1 << 31)
+#define   FW_BLC_SELF_FIFO_MASK    (1 << 16) /* 945 only */
+#define   FW_BLC_SELF_EN           (1 << 15) /* 945 only */
 #define MM_BURST_LENGTH     0x00700000
 #define MM_FIFO_WATERMARK   0x0001F000
 #define LM_BURST_LENGTH     0x00000700
@@ -2645,37 +2757,37 @@ enum i915_power_well_id {
 #define   MI_AGPBUSY_830_MODE			(1 << 0) /* 85x only */
 
 #define CACHE_MODE_0	_MMIO(0x2120) /* 915+ only */
-#define   CM0_PIPELINED_RENDER_FLUSH_DISABLE (1<<8)
-#define   CM0_IZ_OPT_DISABLE      (1<<6)
-#define   CM0_ZR_OPT_DISABLE      (1<<5)
-#define	  CM0_STC_EVICT_DISABLE_LRA_SNB	(1<<5)
-#define   CM0_DEPTH_EVICT_DISABLE (1<<4)
-#define   CM0_COLOR_EVICT_DISABLE (1<<3)
-#define   CM0_DEPTH_WRITE_DISABLE (1<<1)
-#define   CM0_RC_OP_FLUSH_DISABLE (1<<0)
+#define   CM0_PIPELINED_RENDER_FLUSH_DISABLE (1 << 8)
+#define   CM0_IZ_OPT_DISABLE      (1 << 6)
+#define   CM0_ZR_OPT_DISABLE      (1 << 5)
+#define	  CM0_STC_EVICT_DISABLE_LRA_SNB	(1 << 5)
+#define   CM0_DEPTH_EVICT_DISABLE (1 << 4)
+#define   CM0_COLOR_EVICT_DISABLE (1 << 3)
+#define   CM0_DEPTH_WRITE_DISABLE (1 << 1)
+#define   CM0_RC_OP_FLUSH_DISABLE (1 << 0)
 #define GFX_FLSH_CNTL	_MMIO(0x2170) /* 915+ only */
 #define GFX_FLSH_CNTL_GEN6	_MMIO(0x101008)
-#define   GFX_FLSH_CNTL_EN	(1<<0)
+#define   GFX_FLSH_CNTL_EN	(1 << 0)
 #define ECOSKPD		_MMIO(0x21d0)
-#define   ECO_GATING_CX_ONLY	(1<<3)
-#define   ECO_FLIP_DONE		(1<<0)
+#define   ECO_GATING_CX_ONLY	(1 << 3)
+#define   ECO_FLIP_DONE		(1 << 0)
 
 #define CACHE_MODE_0_GEN7	_MMIO(0x7000) /* IVB+ */
-#define RC_OP_FLUSH_ENABLE (1<<0)
-#define   HIZ_RAW_STALL_OPT_DISABLE (1<<2)
+#define RC_OP_FLUSH_ENABLE (1 << 0)
+#define   HIZ_RAW_STALL_OPT_DISABLE (1 << 2)
 #define CACHE_MODE_1		_MMIO(0x7004) /* IVB+ */
-#define   PIXEL_SUBSPAN_COLLECT_OPT_DISABLE	(1<<6)
-#define   GEN8_4x4_STC_OPTIMIZATION_DISABLE	(1<<6)
-#define   GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE	(1<<1)
+#define   PIXEL_SUBSPAN_COLLECT_OPT_DISABLE	(1 << 6)
+#define   GEN8_4x4_STC_OPTIMIZATION_DISABLE	(1 << 6)
+#define   GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE	(1 << 1)
 
 #define GEN6_BLITTER_ECOSKPD	_MMIO(0x221d0)
 #define   GEN6_BLITTER_LOCK_SHIFT			16
-#define   GEN6_BLITTER_FBC_NOTIFY			(1<<3)
+#define   GEN6_BLITTER_FBC_NOTIFY			(1 << 3)
 
 #define GEN6_RC_SLEEP_PSMI_CONTROL	_MMIO(0x2050)
 #define   GEN6_PSMI_SLEEP_MSG_DISABLE	(1 << 0)
 #define   GEN8_RC_SEMA_IDLE_MSG_DISABLE	(1 << 12)
-#define   GEN8_FF_DOP_CLOCK_GATE_DISABLE	(1<<10)
+#define   GEN8_FF_DOP_CLOCK_GATE_DISABLE	(1 << 10)
 
 #define GEN6_RCS_PWR_FSM _MMIO(0x22ac)
 #define GEN9_RCS_FE_FSM2 _MMIO(0x22a4)
@@ -2714,6 +2826,10 @@ enum i915_power_well_id {
 #define   GEN10_F2_SS_DIS_SHIFT		18
 #define   GEN10_F2_SS_DIS_MASK		(0xf << GEN10_F2_SS_DIS_SHIFT)
 
+#define	GEN10_MIRROR_FUSE3		_MMIO(0x9118)
+#define GEN10_L3BANK_PAIR_COUNT     4
+#define GEN10_L3BANK_MASK   0x0F
+
 #define GEN8_EU_DISABLE0		_MMIO(0x9134)
 #define   GEN8_EU_DIS0_S0_MASK		0xffffff
 #define   GEN8_EU_DIS0_S1_SHIFT		24
@@ -2727,7 +2843,7 @@ enum i915_power_well_id {
 #define GEN8_EU_DISABLE2		_MMIO(0x913c)
 #define   GEN8_EU_DIS2_S2_MASK		0xff
 
-#define GEN9_EU_DISABLE(slice)		_MMIO(0x9134 + (slice)*0x4)
+#define GEN9_EU_DISABLE(slice)		_MMIO(0x9134 + (slice) * 0x4)
 
 #define GEN10_EU_DISABLE3		_MMIO(0x9140)
 #define   GEN10_EU_DIS_SS_MASK		0xff
@@ -2784,44 +2900,43 @@ enum i915_power_well_id {
 	 (IS_HASWELL(dev_priv) ? GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1 : 0))
 
 /* These are all the "old" interrupts */
-#define ILK_BSD_USER_INTERRUPT				(1<<5)
-
-#define I915_PM_INTERRUPT				(1<<31)
-#define I915_ISP_INTERRUPT				(1<<22)
-#define I915_LPE_PIPE_B_INTERRUPT			(1<<21)
-#define I915_LPE_PIPE_A_INTERRUPT			(1<<20)
-#define I915_MIPIC_INTERRUPT				(1<<19)
-#define I915_MIPIA_INTERRUPT				(1<<18)
-#define I915_PIPE_CONTROL_NOTIFY_INTERRUPT		(1<<18)
-#define I915_DISPLAY_PORT_INTERRUPT			(1<<17)
-#define I915_DISPLAY_PIPE_C_HBLANK_INTERRUPT		(1<<16)
-#define I915_MASTER_ERROR_INTERRUPT			(1<<15)
-#define I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT	(1<<15)
-#define I915_DISPLAY_PIPE_B_HBLANK_INTERRUPT		(1<<14)
-#define I915_GMCH_THERMAL_SENSOR_EVENT_INTERRUPT	(1<<14) /* p-state */
-#define I915_DISPLAY_PIPE_A_HBLANK_INTERRUPT		(1<<13)
-#define I915_HWB_OOM_INTERRUPT				(1<<13)
-#define I915_LPE_PIPE_C_INTERRUPT			(1<<12)
-#define I915_SYNC_STATUS_INTERRUPT			(1<<12)
-#define I915_MISC_INTERRUPT				(1<<11)
-#define I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT	(1<<11)
-#define I915_DISPLAY_PIPE_C_VBLANK_INTERRUPT		(1<<10)
-#define I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT	(1<<10)
-#define I915_DISPLAY_PIPE_C_EVENT_INTERRUPT		(1<<9)
-#define I915_OVERLAY_PLANE_FLIP_PENDING_INTERRUPT	(1<<9)
-#define I915_DISPLAY_PIPE_C_DPBM_INTERRUPT		(1<<8)
-#define I915_DISPLAY_PLANE_C_FLIP_PENDING_INTERRUPT	(1<<8)
-#define I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT		(1<<7)
-#define I915_DISPLAY_PIPE_A_EVENT_INTERRUPT		(1<<6)
-#define I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT		(1<<5)
-#define I915_DISPLAY_PIPE_B_EVENT_INTERRUPT		(1<<4)
-#define I915_DISPLAY_PIPE_A_DPBM_INTERRUPT		(1<<3)
-#define I915_DISPLAY_PIPE_B_DPBM_INTERRUPT		(1<<2)
-#define I915_DEBUG_INTERRUPT				(1<<2)
-#define I915_WINVALID_INTERRUPT				(1<<1)
-#define I915_USER_INTERRUPT				(1<<1)
-#define I915_ASLE_INTERRUPT				(1<<0)
-#define I915_BSD_USER_INTERRUPT				(1<<25)
+#define ILK_BSD_USER_INTERRUPT				(1 << 5)
+
+#define I915_PM_INTERRUPT				(1 << 31)
+#define I915_ISP_INTERRUPT				(1 << 22)
+#define I915_LPE_PIPE_B_INTERRUPT			(1 << 21)
+#define I915_LPE_PIPE_A_INTERRUPT			(1 << 20)
+#define I915_MIPIC_INTERRUPT				(1 << 19)
+#define I915_MIPIA_INTERRUPT				(1 << 18)
+#define I915_PIPE_CONTROL_NOTIFY_INTERRUPT		(1 << 18)
+#define I915_DISPLAY_PORT_INTERRUPT			(1 << 17)
+#define I915_DISPLAY_PIPE_C_HBLANK_INTERRUPT		(1 << 16)
+#define I915_MASTER_ERROR_INTERRUPT			(1 << 15)
+#define I915_DISPLAY_PIPE_B_HBLANK_INTERRUPT		(1 << 14)
+#define I915_GMCH_THERMAL_SENSOR_EVENT_INTERRUPT	(1 << 14) /* p-state */
+#define I915_DISPLAY_PIPE_A_HBLANK_INTERRUPT		(1 << 13)
+#define I915_HWB_OOM_INTERRUPT				(1 << 13)
+#define I915_LPE_PIPE_C_INTERRUPT			(1 << 12)
+#define I915_SYNC_STATUS_INTERRUPT			(1 << 12)
+#define I915_MISC_INTERRUPT				(1 << 11)
+#define I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT	(1 << 11)
+#define I915_DISPLAY_PIPE_C_VBLANK_INTERRUPT		(1 << 10)
+#define I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT	(1 << 10)
+#define I915_DISPLAY_PIPE_C_EVENT_INTERRUPT		(1 << 9)
+#define I915_OVERLAY_PLANE_FLIP_PENDING_INTERRUPT	(1 << 9)
+#define I915_DISPLAY_PIPE_C_DPBM_INTERRUPT		(1 << 8)
+#define I915_DISPLAY_PLANE_C_FLIP_PENDING_INTERRUPT	(1 << 8)
+#define I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT		(1 << 7)
+#define I915_DISPLAY_PIPE_A_EVENT_INTERRUPT		(1 << 6)
+#define I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT		(1 << 5)
+#define I915_DISPLAY_PIPE_B_EVENT_INTERRUPT		(1 << 4)
+#define I915_DISPLAY_PIPE_A_DPBM_INTERRUPT		(1 << 3)
+#define I915_DISPLAY_PIPE_B_DPBM_INTERRUPT		(1 << 2)
+#define I915_DEBUG_INTERRUPT				(1 << 2)
+#define I915_WINVALID_INTERRUPT				(1 << 1)
+#define I915_USER_INTERRUPT				(1 << 1)
+#define I915_ASLE_INTERRUPT				(1 << 0)
+#define I915_BSD_USER_INTERRUPT				(1 << 25)
 
 #define I915_HDMI_LPE_AUDIO_BASE	(VLV_DISPLAY_BASE + 0x65000)
 #define I915_HDMI_LPE_AUDIO_SIZE	0x1000
@@ -2844,19 +2959,19 @@ enum i915_power_well_id {
 #define GEN7_FF_THREAD_MODE		_MMIO(0x20a0)
 #define   GEN7_FF_SCHED_MASK		0x0077070
 #define   GEN8_FF_DS_REF_CNT_FFME	(1 << 19)
-#define   GEN7_FF_TS_SCHED_HS1		(0x5<<16)
-#define   GEN7_FF_TS_SCHED_HS0		(0x3<<16)
-#define   GEN7_FF_TS_SCHED_LOAD_BALANCE	(0x1<<16)
-#define   GEN7_FF_TS_SCHED_HW		(0x0<<16) /* Default */
+#define   GEN7_FF_TS_SCHED_HS1		(0x5 << 16)
+#define   GEN7_FF_TS_SCHED_HS0		(0x3 << 16)
+#define   GEN7_FF_TS_SCHED_LOAD_BALANCE	(0x1 << 16)
+#define   GEN7_FF_TS_SCHED_HW		(0x0 << 16) /* Default */
 #define   GEN7_FF_VS_REF_CNT_FFME	(1 << 15)
-#define   GEN7_FF_VS_SCHED_HS1		(0x5<<12)
-#define   GEN7_FF_VS_SCHED_HS0		(0x3<<12)
-#define   GEN7_FF_VS_SCHED_LOAD_BALANCE	(0x1<<12) /* Default */
-#define   GEN7_FF_VS_SCHED_HW		(0x0<<12)
-#define   GEN7_FF_DS_SCHED_HS1		(0x5<<4)
-#define   GEN7_FF_DS_SCHED_HS0		(0x3<<4)
-#define   GEN7_FF_DS_SCHED_LOAD_BALANCE	(0x1<<4)  /* Default */
-#define   GEN7_FF_DS_SCHED_HW		(0x0<<4)
+#define   GEN7_FF_VS_SCHED_HS1		(0x5 << 12)
+#define   GEN7_FF_VS_SCHED_HS0		(0x3 << 12)
+#define   GEN7_FF_VS_SCHED_LOAD_BALANCE	(0x1 << 12) /* Default */
+#define   GEN7_FF_VS_SCHED_HW		(0x0 << 12)
+#define   GEN7_FF_DS_SCHED_HS1		(0x5 << 4)
+#define   GEN7_FF_DS_SCHED_HS0		(0x3 << 4)
+#define   GEN7_FF_DS_SCHED_LOAD_BALANCE	(0x1 << 4)  /* Default */
+#define   GEN7_FF_DS_SCHED_HW		(0x0 << 4)
 
 /*
  * Framebuffer compression (915+ only)
@@ -2865,51 +2980,51 @@ enum i915_power_well_id {
 #define FBC_CFB_BASE		_MMIO(0x3200) /* 4k page aligned */
 #define FBC_LL_BASE		_MMIO(0x3204) /* 4k page aligned */
 #define FBC_CONTROL		_MMIO(0x3208)
-#define   FBC_CTL_EN		(1<<31)
-#define   FBC_CTL_PERIODIC	(1<<30)
+#define   FBC_CTL_EN		(1 << 31)
+#define   FBC_CTL_PERIODIC	(1 << 30)
 #define   FBC_CTL_INTERVAL_SHIFT (16)
-#define   FBC_CTL_UNCOMPRESSIBLE (1<<14)
-#define   FBC_CTL_C3_IDLE	(1<<13)
+#define   FBC_CTL_UNCOMPRESSIBLE (1 << 14)
+#define   FBC_CTL_C3_IDLE	(1 << 13)
 #define   FBC_CTL_STRIDE_SHIFT	(5)
 #define   FBC_CTL_FENCENO_SHIFT	(0)
 #define FBC_COMMAND		_MMIO(0x320c)
-#define   FBC_CMD_COMPRESS	(1<<0)
+#define   FBC_CMD_COMPRESS	(1 << 0)
 #define FBC_STATUS		_MMIO(0x3210)
-#define   FBC_STAT_COMPRESSING	(1<<31)
-#define   FBC_STAT_COMPRESSED	(1<<30)
-#define   FBC_STAT_MODIFIED	(1<<29)
+#define   FBC_STAT_COMPRESSING	(1 << 31)
+#define   FBC_STAT_COMPRESSED	(1 << 30)
+#define   FBC_STAT_MODIFIED	(1 << 29)
 #define   FBC_STAT_CURRENT_LINE_SHIFT	(0)
 #define FBC_CONTROL2		_MMIO(0x3214)
-#define   FBC_CTL_FENCE_DBL	(0<<4)
-#define   FBC_CTL_IDLE_IMM	(0<<2)
-#define   FBC_CTL_IDLE_FULL	(1<<2)
-#define   FBC_CTL_IDLE_LINE	(2<<2)
-#define   FBC_CTL_IDLE_DEBUG	(3<<2)
-#define   FBC_CTL_CPU_FENCE	(1<<1)
-#define   FBC_CTL_PLANE(plane)	((plane)<<0)
+#define   FBC_CTL_FENCE_DBL	(0 << 4)
+#define   FBC_CTL_IDLE_IMM	(0 << 2)
+#define   FBC_CTL_IDLE_FULL	(1 << 2)
+#define   FBC_CTL_IDLE_LINE	(2 << 2)
+#define   FBC_CTL_IDLE_DEBUG	(3 << 2)
+#define   FBC_CTL_CPU_FENCE	(1 << 1)
+#define   FBC_CTL_PLANE(plane)	((plane) << 0)
 #define FBC_FENCE_OFF		_MMIO(0x3218) /* BSpec typo has 321Bh */
 #define FBC_TAG(i)		_MMIO(0x3300 + (i) * 4)
 
 #define FBC_LL_SIZE		(1536)
 
 #define FBC_LLC_READ_CTRL	_MMIO(0x9044)
-#define   FBC_LLC_FULLY_OPEN	(1<<30)
+#define   FBC_LLC_FULLY_OPEN	(1 << 30)
 
 /* Framebuffer compression for GM45+ */
 #define DPFC_CB_BASE		_MMIO(0x3200)
 #define DPFC_CONTROL		_MMIO(0x3208)
-#define   DPFC_CTL_EN		(1<<31)
-#define   DPFC_CTL_PLANE(plane)	((plane)<<30)
-#define   IVB_DPFC_CTL_PLANE(plane)	((plane)<<29)
-#define   DPFC_CTL_FENCE_EN	(1<<29)
-#define   IVB_DPFC_CTL_FENCE_EN	(1<<28)
-#define   DPFC_CTL_PERSISTENT_MODE	(1<<25)
-#define   DPFC_SR_EN		(1<<10)
-#define   DPFC_CTL_LIMIT_1X	(0<<6)
-#define   DPFC_CTL_LIMIT_2X	(1<<6)
-#define   DPFC_CTL_LIMIT_4X	(2<<6)
+#define   DPFC_CTL_EN		(1 << 31)
+#define   DPFC_CTL_PLANE(plane)	((plane) << 30)
+#define   IVB_DPFC_CTL_PLANE(plane)	((plane) << 29)
+#define   DPFC_CTL_FENCE_EN	(1 << 29)
+#define   IVB_DPFC_CTL_FENCE_EN	(1 << 28)
+#define   DPFC_CTL_PERSISTENT_MODE	(1 << 25)
+#define   DPFC_SR_EN		(1 << 10)
+#define   DPFC_CTL_LIMIT_1X	(0 << 6)
+#define   DPFC_CTL_LIMIT_2X	(1 << 6)
+#define   DPFC_CTL_LIMIT_4X	(2 << 6)
 #define DPFC_RECOMP_CTL		_MMIO(0x320c)
-#define   DPFC_RECOMP_STALL_EN	(1<<27)
+#define   DPFC_RECOMP_STALL_EN	(1 << 27)
 #define   DPFC_RECOMP_STALL_WM_SHIFT (16)
 #define   DPFC_RECOMP_STALL_WM_MASK (0x07ff0000)
 #define   DPFC_RECOMP_TIMER_COUNT_SHIFT (0)
@@ -2922,12 +3037,12 @@ enum i915_power_well_id {
 #define DPFC_STATUS2		_MMIO(0x3214)
 #define DPFC_FENCE_YOFF		_MMIO(0x3218)
 #define DPFC_CHICKEN		_MMIO(0x3224)
-#define   DPFC_HT_MODIFY	(1<<31)
+#define   DPFC_HT_MODIFY	(1 << 31)
 
 /* Framebuffer compression for Ironlake */
 #define ILK_DPFC_CB_BASE	_MMIO(0x43200)
 #define ILK_DPFC_CONTROL	_MMIO(0x43208)
-#define   FBC_CTL_FALSE_COLOR	(1<<10)
+#define   FBC_CTL_FALSE_COLOR	(1 << 10)
 /* The bit 28-8 is reserved */
 #define   DPFC_RESERVED		(0x1FFFFF00)
 #define ILK_DPFC_RECOMP_CTL	_MMIO(0x4320c)
@@ -2938,15 +3053,15 @@ enum i915_power_well_id {
 #define  BDW_FBC_COMP_SEG_MASK	0xfff
 #define ILK_DPFC_FENCE_YOFF	_MMIO(0x43218)
 #define ILK_DPFC_CHICKEN	_MMIO(0x43224)
-#define   ILK_DPFC_DISABLE_DUMMY0 (1<<8)
-#define   ILK_DPFC_NUKE_ON_ANY_MODIFICATION	(1<<23)
+#define   ILK_DPFC_DISABLE_DUMMY0 (1 << 8)
+#define   ILK_DPFC_NUKE_ON_ANY_MODIFICATION	(1 << 23)
 #define ILK_FBC_RT_BASE		_MMIO(0x2128)
-#define   ILK_FBC_RT_VALID	(1<<0)
-#define   SNB_FBC_FRONT_BUFFER	(1<<1)
+#define   ILK_FBC_RT_VALID	(1 << 0)
+#define   SNB_FBC_FRONT_BUFFER	(1 << 1)
 
 #define ILK_DISPLAY_CHICKEN1	_MMIO(0x42000)
-#define   ILK_FBCQ_DIS		(1<<22)
-#define	  ILK_PABSTRETCH_DIS	(1<<21)
+#define   ILK_FBCQ_DIS		(1 << 22)
+#define	  ILK_PABSTRETCH_DIS	(1 << 21)
 
 
 /*
@@ -2955,7 +3070,7 @@ enum i915_power_well_id {
  * The following two registers are of type GTTMMADR
  */
 #define SNB_DPFC_CTL_SA		_MMIO(0x100100)
-#define   SNB_CPU_FENCE_ENABLE	(1<<29)
+#define   SNB_CPU_FENCE_ENABLE	(1 << 29)
 #define DPFC_CPU_FENCE_OFFSET	_MMIO(0x100104)
 
 /* Framebuffer compression for Ivybridge */
@@ -2965,8 +3080,8 @@ enum i915_power_well_id {
 #define   IPS_ENABLE	(1 << 31)
 
 #define MSG_FBC_REND_STATE	_MMIO(0x50380)
-#define   FBC_REND_NUKE		(1<<2)
-#define   FBC_REND_CACHE_CLEAN	(1<<1)
+#define   FBC_REND_NUKE		(1 << 2)
+#define   FBC_REND_CACHE_CLEAN	(1 << 1)
 
 /*
  * GPIO regs
@@ -2979,6 +3094,10 @@ enum i915_power_well_id {
 #define GPIOF			_MMIO(0x5024)
 #define GPIOG			_MMIO(0x5028)
 #define GPIOH			_MMIO(0x502c)
+#define GPIOJ			_MMIO(0x5034)
+#define GPIOK			_MMIO(0x5038)
+#define GPIOL			_MMIO(0x503C)
+#define GPIOM			_MMIO(0x5040)
 # define GPIO_CLOCK_DIR_MASK		(1 << 0)
 # define GPIO_CLOCK_DIR_IN		(0 << 1)
 # define GPIO_CLOCK_DIR_OUT		(1 << 1)
@@ -2995,12 +3114,13 @@ enum i915_power_well_id {
 # define GPIO_DATA_PULLUP_DISABLE	(1 << 13)
 
 #define GMBUS0			_MMIO(dev_priv->gpio_mmio_base + 0x5100) /* clock/port select */
-#define   GMBUS_AKSV_SELECT	(1<<11)
-#define   GMBUS_RATE_100KHZ	(0<<8)
-#define   GMBUS_RATE_50KHZ	(1<<8)
-#define   GMBUS_RATE_400KHZ	(2<<8) /* reserved on Pineview */
-#define   GMBUS_RATE_1MHZ	(3<<8) /* reserved on Pineview */
-#define   GMBUS_HOLD_EXT	(1<<7) /* 300ns hold time, rsvd on Pineview */
+#define   GMBUS_AKSV_SELECT	(1 << 11)
+#define   GMBUS_RATE_100KHZ	(0 << 8)
+#define   GMBUS_RATE_50KHZ	(1 << 8)
+#define   GMBUS_RATE_400KHZ	(2 << 8) /* reserved on Pineview */
+#define   GMBUS_RATE_1MHZ	(3 << 8) /* reserved on Pineview */
+#define   GMBUS_HOLD_EXT	(1 << 7) /* 300ns hold time, rsvd on Pineview */
+#define   GMBUS_BYTE_CNT_OVERRIDE (1 << 6)
 #define   GMBUS_PIN_DISABLED	0
 #define   GMBUS_PIN_SSC		1
 #define   GMBUS_PIN_VGADDC	2
@@ -3021,36 +3141,37 @@ enum i915_power_well_id {
 
 #define   GMBUS_NUM_PINS	13 /* including 0 */
 #define GMBUS1			_MMIO(dev_priv->gpio_mmio_base + 0x5104) /* command/status */
-#define   GMBUS_SW_CLR_INT	(1<<31)
-#define   GMBUS_SW_RDY		(1<<30)
-#define   GMBUS_ENT		(1<<29) /* enable timeout */
-#define   GMBUS_CYCLE_NONE	(0<<25)
-#define   GMBUS_CYCLE_WAIT	(1<<25)
-#define   GMBUS_CYCLE_INDEX	(2<<25)
-#define   GMBUS_CYCLE_STOP	(4<<25)
+#define   GMBUS_SW_CLR_INT	(1 << 31)
+#define   GMBUS_SW_RDY		(1 << 30)
+#define   GMBUS_ENT		(1 << 29) /* enable timeout */
+#define   GMBUS_CYCLE_NONE	(0 << 25)
+#define   GMBUS_CYCLE_WAIT	(1 << 25)
+#define   GMBUS_CYCLE_INDEX	(2 << 25)
+#define   GMBUS_CYCLE_STOP	(4 << 25)
 #define   GMBUS_BYTE_COUNT_SHIFT 16
 #define   GMBUS_BYTE_COUNT_MAX   256U
+#define   GEN9_GMBUS_BYTE_COUNT_MAX 511U
 #define   GMBUS_SLAVE_INDEX_SHIFT 8
 #define   GMBUS_SLAVE_ADDR_SHIFT 1
-#define   GMBUS_SLAVE_READ	(1<<0)
-#define   GMBUS_SLAVE_WRITE	(0<<0)
+#define   GMBUS_SLAVE_READ	(1 << 0)
+#define   GMBUS_SLAVE_WRITE	(0 << 0)
 #define GMBUS2			_MMIO(dev_priv->gpio_mmio_base + 0x5108) /* status */
-#define   GMBUS_INUSE		(1<<15)
-#define   GMBUS_HW_WAIT_PHASE	(1<<14)
-#define   GMBUS_STALL_TIMEOUT	(1<<13)
-#define   GMBUS_INT		(1<<12)
-#define   GMBUS_HW_RDY		(1<<11)
-#define   GMBUS_SATOER		(1<<10)
-#define   GMBUS_ACTIVE		(1<<9)
+#define   GMBUS_INUSE		(1 << 15)
+#define   GMBUS_HW_WAIT_PHASE	(1 << 14)
+#define   GMBUS_STALL_TIMEOUT	(1 << 13)
+#define   GMBUS_INT		(1 << 12)
+#define   GMBUS_HW_RDY		(1 << 11)
+#define   GMBUS_SATOER		(1 << 10)
+#define   GMBUS_ACTIVE		(1 << 9)
 #define GMBUS3			_MMIO(dev_priv->gpio_mmio_base + 0x510c) /* data buffer bytes 3-0 */
 #define GMBUS4			_MMIO(dev_priv->gpio_mmio_base + 0x5110) /* interrupt mask (Pineview+) */
-#define   GMBUS_SLAVE_TIMEOUT_EN (1<<4)
-#define   GMBUS_NAK_EN		(1<<3)
-#define   GMBUS_IDLE_EN		(1<<2)
-#define   GMBUS_HW_WAIT_EN	(1<<1)
-#define   GMBUS_HW_RDY_EN	(1<<0)
+#define   GMBUS_SLAVE_TIMEOUT_EN (1 << 4)
+#define   GMBUS_NAK_EN		(1 << 3)
+#define   GMBUS_IDLE_EN		(1 << 2)
+#define   GMBUS_HW_WAIT_EN	(1 << 1)
+#define   GMBUS_HW_RDY_EN	(1 << 0)
 #define GMBUS5			_MMIO(dev_priv->gpio_mmio_base + 0x5120) /* byte index */
-#define   GMBUS_2BYTE_INDEX_EN	(1<<31)
+#define   GMBUS_2BYTE_INDEX_EN	(1 << 31)
 
 /*
  * Clock control & power management
@@ -3088,10 +3209,10 @@ enum i915_power_well_id {
 #define   DPLL_P2_CLOCK_DIV_MASK	0x03000000 /* i915 */
 #define   DPLL_FPA01_P1_POST_DIV_MASK	0x00ff0000 /* i915 */
 #define   DPLL_FPA01_P1_POST_DIV_MASK_PINEVIEW	0x00ff8000 /* Pineview */
-#define   DPLL_LOCK_VLV			(1<<15)
-#define   DPLL_INTEGRATED_CRI_CLK_VLV	(1<<14)
-#define   DPLL_INTEGRATED_REF_CLK_VLV	(1<<13)
-#define   DPLL_SSC_REF_CLK_CHV		(1<<13)
+#define   DPLL_LOCK_VLV			(1 << 15)
+#define   DPLL_INTEGRATED_CRI_CLK_VLV	(1 << 14)
+#define   DPLL_INTEGRATED_REF_CLK_VLV	(1 << 13)
+#define   DPLL_SSC_REF_CLK_CHV		(1 << 13)
 #define   DPLL_PORTC_READY_MASK		(0xf << 4)
 #define   DPLL_PORTB_READY_MASK		(0xf)
 
@@ -3101,20 +3222,20 @@ enum i915_power_well_id {
 #define DPIO_PHY_STATUS			_MMIO(VLV_DISPLAY_BASE + 0x6240)
 #define   DPLL_PORTD_READY_MASK		(0xf)
 #define DISPLAY_PHY_CONTROL _MMIO(VLV_DISPLAY_BASE + 0x60100)
-#define   PHY_CH_POWER_DOWN_OVRD_EN(phy, ch)	(1 << (2*(phy)+(ch)+27))
+#define   PHY_CH_POWER_DOWN_OVRD_EN(phy, ch)	(1 << (2 * (phy) + (ch) + 27))
 #define   PHY_LDO_DELAY_0NS			0x0
 #define   PHY_LDO_DELAY_200NS			0x1
 #define   PHY_LDO_DELAY_600NS			0x2
-#define   PHY_LDO_SEQ_DELAY(delay, phy)		((delay) << (2*(phy)+23))
-#define   PHY_CH_POWER_DOWN_OVRD(mask, phy, ch)	((mask) << (8*(phy)+4*(ch)+11))
+#define   PHY_LDO_SEQ_DELAY(delay, phy)		((delay) << (2 * (phy) + 23))
+#define   PHY_CH_POWER_DOWN_OVRD(mask, phy, ch)	((mask) << (8 * (phy) + 4 * (ch) + 11))
 #define   PHY_CH_SU_PSR				0x1
 #define   PHY_CH_DEEP_PSR			0x7
-#define   PHY_CH_POWER_MODE(mode, phy, ch)	((mode) << (6*(phy)+3*(ch)+2))
+#define   PHY_CH_POWER_MODE(mode, phy, ch)	((mode) << (6 * (phy) + 3 * (ch) + 2))
 #define   PHY_COM_LANE_RESET_DEASSERT(phy)	(1 << (phy))
 #define DISPLAY_PHY_STATUS _MMIO(VLV_DISPLAY_BASE + 0x60104)
-#define   PHY_POWERGOOD(phy)	(((phy) == DPIO_PHY0) ? (1<<31) : (1<<30))
-#define   PHY_STATUS_CMN_LDO(phy, ch)                   (1 << (6-(6*(phy)+3*(ch))))
-#define   PHY_STATUS_SPLINE_LDO(phy, ch, spline)        (1 << (8-(6*(phy)+3*(ch)+(spline))))
+#define   PHY_POWERGOOD(phy)	(((phy) == DPIO_PHY0) ? (1 << 31) : (1 << 30))
+#define   PHY_STATUS_CMN_LDO(phy, ch)                   (1 << (6 - (6 * (phy) + 3 * (ch))))
+#define   PHY_STATUS_SPLINE_LDO(phy, ch, spline)        (1 << (8 - (6 * (phy) + 3 * (ch) + (spline))))
 
 /*
  * The i830 generation, in LVDS mode, defines P1 as the bit number set within
@@ -3135,7 +3256,7 @@ enum i915_power_well_id {
 /* Ironlake */
 # define PLL_REF_SDVO_HDMI_MULTIPLIER_SHIFT     9
 # define PLL_REF_SDVO_HDMI_MULTIPLIER_MASK      (7 << 9)
-# define PLL_REF_SDVO_HDMI_MULTIPLIER(x)	(((x)-1) << 9)
+# define PLL_REF_SDVO_HDMI_MULTIPLIER(x)	(((x) - 1) << 9)
 # define DPLL_FPA1_P1_POST_DIV_SHIFT            0
 # define DPLL_FPA1_P1_POST_DIV_MASK             0xff
 
@@ -3224,10 +3345,10 @@ enum i915_power_well_id {
 #define   DPLLA_TEST_M_BYPASS		(1 << 2)
 #define   DPLLA_INPUT_BUFFER_ENABLE	(1 << 0)
 #define D_STATE		_MMIO(0x6104)
-#define  DSTATE_GFX_RESET_I830			(1<<6)
-#define  DSTATE_PLL_D3_OFF			(1<<3)
-#define  DSTATE_GFX_CLOCK_GATING		(1<<1)
-#define  DSTATE_DOT_CLOCK_GATING		(1<<0)
+#define  DSTATE_GFX_RESET_I830			(1 << 6)
+#define  DSTATE_PLL_D3_OFF			(1 << 3)
+#define  DSTATE_GFX_CLOCK_GATING		(1 << 1)
+#define  DSTATE_DOT_CLOCK_GATING		(1 << 0)
 #define DSPCLK_GATE_D	_MMIO(dev_priv->info.display_mmio_offset + 0x6200)
 # define DPUNIT_B_CLOCK_GATE_DISABLE		(1 << 30) /* 965 */
 # define VSUNIT_CLOCK_GATE_DISABLE		(1 << 29) /* 965 */
@@ -3344,7 +3465,7 @@ enum i915_power_well_id {
 #define DEUC			_MMIO(0x6214)          /* CRL only */
 
 #define FW_BLC_SELF_VLV		_MMIO(VLV_DISPLAY_BASE + 0x6500)
-#define  FW_CSPWRDWNEN		(1<<15)
+#define  FW_CSPWRDWNEN		(1 << 15)
 
 #define MI_ARB_VLV		_MMIO(VLV_DISPLAY_BASE + 0x6504)
 
@@ -3469,7 +3590,7 @@ enum i915_power_well_id {
 #define HPLLVCO_MOBILE          _MMIO(MCHBAR_MIRROR_BASE + 0xc0f)
 
 #define TSC1			_MMIO(0x11001)
-#define   TSE			(1<<0)
+#define   TSE			(1 << 0)
 #define TR1			_MMIO(0x11006)
 #define TSFS			_MMIO(0x11020)
 #define   TSFS_SLOPE_MASK	0x0000ff00
@@ -3515,23 +3636,23 @@ enum i915_power_well_id {
 #define   MEMCTL_CMD_CHVID	3
 #define   MEMCTL_CMD_VMMOFF	4
 #define   MEMCTL_CMD_VMMON	5
-#define   MEMCTL_CMD_STS	(1<<12) /* write 1 triggers command, clears
+#define   MEMCTL_CMD_STS	(1 << 12) /* write 1 triggers command, clears
 					   when command complete */
 #define   MEMCTL_FREQ_MASK	0x0f00 /* jitter, from 0-15 */
 #define   MEMCTL_FREQ_SHIFT	8
-#define   MEMCTL_SFCAVM		(1<<7)
+#define   MEMCTL_SFCAVM		(1 << 7)
 #define   MEMCTL_TGT_VID_MASK	0x007f
 #define MEMIHYST		_MMIO(0x1117c)
 #define MEMINTREN		_MMIO(0x11180) /* 16 bits */
-#define   MEMINT_RSEXIT_EN	(1<<8)
-#define   MEMINT_CX_SUPR_EN	(1<<7)
-#define   MEMINT_CONT_BUSY_EN	(1<<6)
-#define   MEMINT_AVG_BUSY_EN	(1<<5)
-#define   MEMINT_EVAL_CHG_EN	(1<<4)
-#define   MEMINT_MON_IDLE_EN	(1<<3)
-#define   MEMINT_UP_EVAL_EN	(1<<2)
-#define   MEMINT_DOWN_EVAL_EN	(1<<1)
-#define   MEMINT_SW_CMD_EN	(1<<0)
+#define   MEMINT_RSEXIT_EN	(1 << 8)
+#define   MEMINT_CX_SUPR_EN	(1 << 7)
+#define   MEMINT_CONT_BUSY_EN	(1 << 6)
+#define   MEMINT_AVG_BUSY_EN	(1 << 5)
+#define   MEMINT_EVAL_CHG_EN	(1 << 4)
+#define   MEMINT_MON_IDLE_EN	(1 << 3)
+#define   MEMINT_UP_EVAL_EN	(1 << 2)
+#define   MEMINT_DOWN_EVAL_EN	(1 << 1)
+#define   MEMINT_SW_CMD_EN	(1 << 0)
 #define MEMINTRSTR		_MMIO(0x11182) /* 16 bits */
 #define   MEM_RSEXIT_MASK	0xc000
 #define   MEM_RSEXIT_SHIFT	14
@@ -3553,26 +3674,26 @@ enum i915_power_well_id {
 #define   MEM_INT_STEER_SMI	2
 #define   MEM_INT_STEER_SCI	3
 #define MEMINTRSTS		_MMIO(0x11184)
-#define   MEMINT_RSEXIT		(1<<7)
-#define   MEMINT_CONT_BUSY	(1<<6)
-#define   MEMINT_AVG_BUSY	(1<<5)
-#define   MEMINT_EVAL_CHG	(1<<4)
-#define   MEMINT_MON_IDLE	(1<<3)
-#define   MEMINT_UP_EVAL	(1<<2)
-#define   MEMINT_DOWN_EVAL	(1<<1)
-#define   MEMINT_SW_CMD		(1<<0)
+#define   MEMINT_RSEXIT		(1 << 7)
+#define   MEMINT_CONT_BUSY	(1 << 6)
+#define   MEMINT_AVG_BUSY	(1 << 5)
+#define   MEMINT_EVAL_CHG	(1 << 4)
+#define   MEMINT_MON_IDLE	(1 << 3)
+#define   MEMINT_UP_EVAL	(1 << 2)
+#define   MEMINT_DOWN_EVAL	(1 << 1)
+#define   MEMINT_SW_CMD		(1 << 0)
 #define MEMMODECTL		_MMIO(0x11190)
-#define   MEMMODE_BOOST_EN	(1<<31)
+#define   MEMMODE_BOOST_EN	(1 << 31)
 #define   MEMMODE_BOOST_FREQ_MASK 0x0f000000 /* jitter for boost, 0-15 */
 #define   MEMMODE_BOOST_FREQ_SHIFT 24
 #define   MEMMODE_IDLE_MODE_MASK 0x00030000
 #define   MEMMODE_IDLE_MODE_SHIFT 16
 #define   MEMMODE_IDLE_MODE_EVAL 0
 #define   MEMMODE_IDLE_MODE_CONT 1
-#define   MEMMODE_HWIDLE_EN	(1<<15)
-#define   MEMMODE_SWMODE_EN	(1<<14)
-#define   MEMMODE_RCLK_GATE	(1<<13)
-#define   MEMMODE_HW_UPDATE	(1<<12)
+#define   MEMMODE_HWIDLE_EN	(1 << 15)
+#define   MEMMODE_SWMODE_EN	(1 << 14)
+#define   MEMMODE_RCLK_GATE	(1 << 13)
+#define   MEMMODE_HW_UPDATE	(1 << 12)
 #define   MEMMODE_FSTART_MASK	0x00000f00 /* starting jitter, 0-15 */
 #define   MEMMODE_FSTART_SHIFT	8
 #define   MEMMODE_FMAX_MASK	0x000000f0 /* max jitter, 0-15 */
@@ -3586,8 +3707,8 @@ enum i915_power_well_id {
 #define   SWMEMCMD_TARVID	(3 << 13)
 #define   SWMEMCMD_VRM_OFF	(4 << 13)
 #define   SWMEMCMD_VRM_ON	(5 << 13)
-#define   CMDSTS		(1<<12)
-#define   SFCAVM		(1<<11)
+#define   CMDSTS		(1 << 12)
+#define   SFCAVM		(1 << 11)
 #define   SWFREQ_MASK		0x0380 /* P0-7 */
 #define   SWFREQ_SHIFT		7
 #define   TARVID_MASK		0x001f
@@ -3596,49 +3717,49 @@ enum i915_power_well_id {
 #define RCUPEI			_MMIO(0x111b0)
 #define RCDNEI			_MMIO(0x111b4)
 #define RSTDBYCTL		_MMIO(0x111b8)
-#define   RS1EN			(1<<31)
-#define   RS2EN			(1<<30)
-#define   RS3EN			(1<<29)
-#define   D3RS3EN		(1<<28) /* Display D3 imlies RS3 */
-#define   SWPROMORSX		(1<<27) /* RSx promotion timers ignored */
-#define   RCWAKERW		(1<<26) /* Resetwarn from PCH causes wakeup */
-#define   DPRSLPVREN		(1<<25) /* Fast voltage ramp enable */
-#define   GFXTGHYST		(1<<24) /* Hysteresis to allow trunk gating */
-#define   RCX_SW_EXIT		(1<<23) /* Leave RSx and prevent re-entry */
-#define   RSX_STATUS_MASK	(7<<20)
-#define   RSX_STATUS_ON		(0<<20)
-#define   RSX_STATUS_RC1	(1<<20)
-#define   RSX_STATUS_RC1E	(2<<20)
-#define   RSX_STATUS_RS1	(3<<20)
-#define   RSX_STATUS_RS2	(4<<20) /* aka rc6 */
-#define   RSX_STATUS_RSVD	(5<<20) /* deep rc6 unsupported on ilk */
-#define   RSX_STATUS_RS3	(6<<20) /* rs3 unsupported on ilk */
-#define   RSX_STATUS_RSVD2	(7<<20)
-#define   UWRCRSXE		(1<<19) /* wake counter limit prevents rsx */
-#define   RSCRP			(1<<18) /* rs requests control on rs1/2 reqs */
-#define   JRSC			(1<<17) /* rsx coupled to cpu c-state */
-#define   RS2INC0		(1<<16) /* allow rs2 in cpu c0 */
-#define   RS1CONTSAV_MASK	(3<<14)
-#define   RS1CONTSAV_NO_RS1	(0<<14) /* rs1 doesn't save/restore context */
-#define   RS1CONTSAV_RSVD	(1<<14)
-#define   RS1CONTSAV_SAVE_RS1	(2<<14) /* rs1 saves context */
-#define   RS1CONTSAV_FULL_RS1	(3<<14) /* rs1 saves and restores context */
-#define   NORMSLEXLAT_MASK	(3<<12)
-#define   SLOW_RS123		(0<<12)
-#define   SLOW_RS23		(1<<12)
-#define   SLOW_RS3		(2<<12)
-#define   NORMAL_RS123		(3<<12)
-#define   RCMODE_TIMEOUT	(1<<11) /* 0 is eval interval method */
-#define   IMPROMOEN		(1<<10) /* promo is immediate or delayed until next idle interval (only for timeout method above) */
-#define   RCENTSYNC		(1<<9) /* rs coupled to cpu c-state (3/6/7) */
-#define   STATELOCK		(1<<7) /* locked to rs_cstate if 0 */
-#define   RS_CSTATE_MASK	(3<<4)
-#define   RS_CSTATE_C367_RS1	(0<<4)
-#define   RS_CSTATE_C36_RS1_C7_RS2 (1<<4)
-#define   RS_CSTATE_RSVD	(2<<4)
-#define   RS_CSTATE_C367_RS2	(3<<4)
-#define   REDSAVES		(1<<3) /* no context save if was idle during rs0 */
-#define   REDRESTORES		(1<<2) /* no restore if was idle during rs0 */
+#define   RS1EN			(1 << 31)
+#define   RS2EN			(1 << 30)
+#define   RS3EN			(1 << 29)
+#define   D3RS3EN		(1 << 28) /* Display D3 imlies RS3 */
+#define   SWPROMORSX		(1 << 27) /* RSx promotion timers ignored */
+#define   RCWAKERW		(1 << 26) /* Resetwarn from PCH causes wakeup */
+#define   DPRSLPVREN		(1 << 25) /* Fast voltage ramp enable */
+#define   GFXTGHYST		(1 << 24) /* Hysteresis to allow trunk gating */
+#define   RCX_SW_EXIT		(1 << 23) /* Leave RSx and prevent re-entry */
+#define   RSX_STATUS_MASK	(7 << 20)
+#define   RSX_STATUS_ON		(0 << 20)
+#define   RSX_STATUS_RC1	(1 << 20)
+#define   RSX_STATUS_RC1E	(2 << 20)
+#define   RSX_STATUS_RS1	(3 << 20)
+#define   RSX_STATUS_RS2	(4 << 20) /* aka rc6 */
+#define   RSX_STATUS_RSVD	(5 << 20) /* deep rc6 unsupported on ilk */
+#define   RSX_STATUS_RS3	(6 << 20) /* rs3 unsupported on ilk */
+#define   RSX_STATUS_RSVD2	(7 << 20)
+#define   UWRCRSXE		(1 << 19) /* wake counter limit prevents rsx */
+#define   RSCRP			(1 << 18) /* rs requests control on rs1/2 reqs */
+#define   JRSC			(1 << 17) /* rsx coupled to cpu c-state */
+#define   RS2INC0		(1 << 16) /* allow rs2 in cpu c0 */
+#define   RS1CONTSAV_MASK	(3 << 14)
+#define   RS1CONTSAV_NO_RS1	(0 << 14) /* rs1 doesn't save/restore context */
+#define   RS1CONTSAV_RSVD	(1 << 14)
+#define   RS1CONTSAV_SAVE_RS1	(2 << 14) /* rs1 saves context */
+#define   RS1CONTSAV_FULL_RS1	(3 << 14) /* rs1 saves and restores context */
+#define   NORMSLEXLAT_MASK	(3 << 12)
+#define   SLOW_RS123		(0 << 12)
+#define   SLOW_RS23		(1 << 12)
+#define   SLOW_RS3		(2 << 12)
+#define   NORMAL_RS123		(3 << 12)
+#define   RCMODE_TIMEOUT	(1 << 11) /* 0 is eval interval method */
+#define   IMPROMOEN		(1 << 10) /* promo is immediate or delayed until next idle interval (only for timeout method above) */
+#define   RCENTSYNC		(1 << 9) /* rs coupled to cpu c-state (3/6/7) */
+#define   STATELOCK		(1 << 7) /* locked to rs_cstate if 0 */
+#define   RS_CSTATE_MASK	(3 << 4)
+#define   RS_CSTATE_C367_RS1	(0 << 4)
+#define   RS_CSTATE_C36_RS1_C7_RS2 (1 << 4)
+#define   RS_CSTATE_RSVD	(2 << 4)
+#define   RS_CSTATE_C367_RS2	(3 << 4)
+#define   REDSAVES		(1 << 3) /* no context save if was idle during rs0 */
+#define   REDRESTORES		(1 << 2) /* no restore if was idle during rs0 */
 #define VIDCTL			_MMIO(0x111c0)
 #define VIDSTS			_MMIO(0x111c8)
 #define VIDSTART		_MMIO(0x111cc) /* 8 bits */
@@ -3647,7 +3768,7 @@ enum i915_power_well_id {
 #define   MEMSTAT_VID_SHIFT	8
 #define   MEMSTAT_PSTATE_MASK	0x00f8
 #define   MEMSTAT_PSTATE_SHIFT  3
-#define   MEMSTAT_MON_ACTV	(1<<2)
+#define   MEMSTAT_MON_ACTV	(1 << 2)
 #define   MEMSTAT_SRC_CTL_MASK	0x0003
 #define   MEMSTAT_SRC_CTL_CORE	0
 #define   MEMSTAT_SRC_CTL_TRB	1
@@ -3656,7 +3777,7 @@ enum i915_power_well_id {
 #define RCPREVBSYTUPAVG		_MMIO(0x113b8)
 #define RCPREVBSYTDNAVG		_MMIO(0x113bc)
 #define PMMISC			_MMIO(0x11214)
-#define   MCPPCE_EN		(1<<0) /* enable PM_MSG from PCH->MPC */
+#define   MCPPCE_EN		(1 << 0) /* enable PM_MSG from PCH->MPC */
 #define SDEW			_MMIO(0x1124c)
 #define CSIEW0			_MMIO(0x11250)
 #define CSIEW1			_MMIO(0x11254)
@@ -3673,8 +3794,8 @@ enum i915_power_well_id {
 #define RPPREVBSYTUPAVG		_MMIO(0x113b8)
 #define RPPREVBSYTDNAVG		_MMIO(0x113bc)
 #define ECR			_MMIO(0x11600)
-#define   ECR_GPFE		(1<<31)
-#define   ECR_IMONE		(1<<30)
+#define   ECR_GPFE		(1 << 31)
+#define   ECR_IMONE		(1 << 30)
 #define   ECR_CAP_MASK		0x0000001f /* Event range, 0-31 */
 #define OGW0			_MMIO(0x11608)
 #define OGW1			_MMIO(0x1160c)
@@ -3781,11 +3902,11 @@ enum {
 	FAULT_AND_CONTINUE /* Unsupported */
 };
 
-#define GEN8_CTX_VALID (1<<0)
-#define GEN8_CTX_FORCE_PD_RESTORE (1<<1)
-#define GEN8_CTX_FORCE_RESTORE (1<<2)
-#define GEN8_CTX_L3LLC_COHERENT (1<<5)
-#define GEN8_CTX_PRIVILEGE (1<<8)
+#define GEN8_CTX_VALID (1 << 0)
+#define GEN8_CTX_FORCE_PD_RESTORE (1 << 1)
+#define GEN8_CTX_FORCE_RESTORE (1 << 2)
+#define GEN8_CTX_L3LLC_COHERENT (1 << 5)
+#define GEN8_CTX_PRIVILEGE (1 << 8)
 #define GEN8_CTX_ADDRESSING_MODE_SHIFT 3
 
 #define GEN8_CTX_ID_SHIFT 32
@@ -3807,7 +3928,7 @@ enum {
 
 #define OVADD			_MMIO(0x30000)
 #define DOVSTA			_MMIO(0x30008)
-#define OC_BUF			(0x3<<20)
+#define OC_BUF			(0x3 << 20)
 #define OGAMC5			_MMIO(0x30010)
 #define OGAMC4			_MMIO(0x30014)
 #define OGAMC3			_MMIO(0x30018)
@@ -3975,64 +4096,65 @@ enum {
 /* VLV eDP PSR registers */
 #define _PSRCTLA				(VLV_DISPLAY_BASE + 0x60090)
 #define _PSRCTLB				(VLV_DISPLAY_BASE + 0x61090)
-#define  VLV_EDP_PSR_ENABLE			(1<<0)
-#define  VLV_EDP_PSR_RESET			(1<<1)
-#define  VLV_EDP_PSR_MODE_MASK			(7<<2)
-#define  VLV_EDP_PSR_MODE_HW_TIMER		(1<<3)
-#define  VLV_EDP_PSR_MODE_SW_TIMER		(1<<2)
-#define  VLV_EDP_PSR_SINGLE_FRAME_UPDATE	(1<<7)
-#define  VLV_EDP_PSR_ACTIVE_ENTRY		(1<<8)
-#define  VLV_EDP_PSR_SRC_TRANSMITTER_STATE	(1<<9)
-#define  VLV_EDP_PSR_DBL_FRAME			(1<<10)
-#define  VLV_EDP_PSR_FRAME_COUNT_MASK		(0xff<<16)
+#define  VLV_EDP_PSR_ENABLE			(1 << 0)
+#define  VLV_EDP_PSR_RESET			(1 << 1)
+#define  VLV_EDP_PSR_MODE_MASK			(7 << 2)
+#define  VLV_EDP_PSR_MODE_HW_TIMER		(1 << 3)
+#define  VLV_EDP_PSR_MODE_SW_TIMER		(1 << 2)
+#define  VLV_EDP_PSR_SINGLE_FRAME_UPDATE	(1 << 7)
+#define  VLV_EDP_PSR_ACTIVE_ENTRY		(1 << 8)
+#define  VLV_EDP_PSR_SRC_TRANSMITTER_STATE	(1 << 9)
+#define  VLV_EDP_PSR_DBL_FRAME			(1 << 10)
+#define  VLV_EDP_PSR_FRAME_COUNT_MASK		(0xff << 16)
 #define  VLV_EDP_PSR_IDLE_FRAME_SHIFT		16
 #define VLV_PSRCTL(pipe)	_MMIO_PIPE(pipe, _PSRCTLA, _PSRCTLB)
 
 #define _VSCSDPA			(VLV_DISPLAY_BASE + 0x600a0)
 #define _VSCSDPB			(VLV_DISPLAY_BASE + 0x610a0)
-#define  VLV_EDP_PSR_SDP_FREQ_MASK	(3<<30)
-#define  VLV_EDP_PSR_SDP_FREQ_ONCE	(1<<31)
-#define  VLV_EDP_PSR_SDP_FREQ_EVFRAME	(1<<30)
+#define  VLV_EDP_PSR_SDP_FREQ_MASK	(3 << 30)
+#define  VLV_EDP_PSR_SDP_FREQ_ONCE	(1 << 31)
+#define  VLV_EDP_PSR_SDP_FREQ_EVFRAME	(1 << 30)
 #define VLV_VSCSDP(pipe)	_MMIO_PIPE(pipe, _VSCSDPA, _VSCSDPB)
 
 #define _PSRSTATA			(VLV_DISPLAY_BASE + 0x60094)
 #define _PSRSTATB			(VLV_DISPLAY_BASE + 0x61094)
-#define  VLV_EDP_PSR_LAST_STATE_MASK	(7<<3)
+#define  VLV_EDP_PSR_LAST_STATE_MASK	(7 << 3)
 #define  VLV_EDP_PSR_CURR_STATE_MASK	7
-#define  VLV_EDP_PSR_DISABLED		(0<<0)
-#define  VLV_EDP_PSR_INACTIVE		(1<<0)
-#define  VLV_EDP_PSR_IN_TRANS_TO_ACTIVE	(2<<0)
-#define  VLV_EDP_PSR_ACTIVE_NORFB_UP	(3<<0)
-#define  VLV_EDP_PSR_ACTIVE_SF_UPDATE	(4<<0)
-#define  VLV_EDP_PSR_EXIT		(5<<0)
-#define  VLV_EDP_PSR_IN_TRANS		(1<<7)
+#define  VLV_EDP_PSR_DISABLED		(0 << 0)
+#define  VLV_EDP_PSR_INACTIVE		(1 << 0)
+#define  VLV_EDP_PSR_IN_TRANS_TO_ACTIVE	(2 << 0)
+#define  VLV_EDP_PSR_ACTIVE_NORFB_UP	(3 << 0)
+#define  VLV_EDP_PSR_ACTIVE_SF_UPDATE	(4 << 0)
+#define  VLV_EDP_PSR_EXIT		(5 << 0)
+#define  VLV_EDP_PSR_IN_TRANS		(1 << 7)
 #define VLV_PSRSTAT(pipe)	_MMIO_PIPE(pipe, _PSRSTATA, _PSRSTATB)
 
 /* HSW+ eDP PSR registers */
 #define HSW_EDP_PSR_BASE	0x64800
 #define BDW_EDP_PSR_BASE	0x6f800
 #define EDP_PSR_CTL				_MMIO(dev_priv->psr_mmio_base + 0)
-#define   EDP_PSR_ENABLE			(1<<31)
-#define   BDW_PSR_SINGLE_FRAME			(1<<30)
-#define   EDP_PSR_RESTORE_PSR_ACTIVE_CTX_MASK	(1<<29) /* SW can't modify */
-#define   EDP_PSR_LINK_STANDBY			(1<<27)
-#define   EDP_PSR_MIN_LINK_ENTRY_TIME_MASK	(3<<25)
-#define   EDP_PSR_MIN_LINK_ENTRY_TIME_8_LINES	(0<<25)
-#define   EDP_PSR_MIN_LINK_ENTRY_TIME_4_LINES	(1<<25)
-#define   EDP_PSR_MIN_LINK_ENTRY_TIME_2_LINES	(2<<25)
-#define   EDP_PSR_MIN_LINK_ENTRY_TIME_0_LINES	(3<<25)
+#define   EDP_PSR_ENABLE			(1 << 31)
+#define   BDW_PSR_SINGLE_FRAME			(1 << 30)
+#define   EDP_PSR_RESTORE_PSR_ACTIVE_CTX_MASK	(1 << 29) /* SW can't modify */
+#define   EDP_PSR_LINK_STANDBY			(1 << 27)
+#define   EDP_PSR_MIN_LINK_ENTRY_TIME_MASK	(3 << 25)
+#define   EDP_PSR_MIN_LINK_ENTRY_TIME_8_LINES	(0 << 25)
+#define   EDP_PSR_MIN_LINK_ENTRY_TIME_4_LINES	(1 << 25)
+#define   EDP_PSR_MIN_LINK_ENTRY_TIME_2_LINES	(2 << 25)
+#define   EDP_PSR_MIN_LINK_ENTRY_TIME_0_LINES	(3 << 25)
 #define   EDP_PSR_MAX_SLEEP_TIME_SHIFT		20
-#define   EDP_PSR_SKIP_AUX_EXIT			(1<<12)
-#define   EDP_PSR_TP1_TP2_SEL			(0<<11)
-#define   EDP_PSR_TP1_TP3_SEL			(1<<11)
-#define   EDP_PSR_TP2_TP3_TIME_500us		(0<<8)
-#define   EDP_PSR_TP2_TP3_TIME_100us		(1<<8)
-#define   EDP_PSR_TP2_TP3_TIME_2500us		(2<<8)
-#define   EDP_PSR_TP2_TP3_TIME_0us		(3<<8)
-#define   EDP_PSR_TP1_TIME_500us		(0<<4)
-#define   EDP_PSR_TP1_TIME_100us		(1<<4)
-#define   EDP_PSR_TP1_TIME_2500us		(2<<4)
-#define   EDP_PSR_TP1_TIME_0us			(3<<4)
+#define   EDP_PSR_SKIP_AUX_EXIT			(1 << 12)
+#define   EDP_PSR_TP1_TP2_SEL			(0 << 11)
+#define   EDP_PSR_TP1_TP3_SEL			(1 << 11)
+#define   EDP_PSR_CRC_ENABLE			(1 << 10) /* BDW+ */
+#define   EDP_PSR_TP2_TP3_TIME_500us		(0 << 8)
+#define   EDP_PSR_TP2_TP3_TIME_100us		(1 << 8)
+#define   EDP_PSR_TP2_TP3_TIME_2500us		(2 << 8)
+#define   EDP_PSR_TP2_TP3_TIME_0us		(3 << 8)
+#define   EDP_PSR_TP1_TIME_500us		(0 << 4)
+#define   EDP_PSR_TP1_TIME_100us		(1 << 4)
+#define   EDP_PSR_TP1_TIME_2500us		(2 << 4)
+#define   EDP_PSR_TP1_TIME_0us			(3 << 4)
 #define   EDP_PSR_IDLE_FRAME_SHIFT		0
 
 /* Bspec claims those aren't shifted but stay at 0x64800 */
@@ -4052,55 +4174,56 @@ enum {
 #define EDP_PSR_AUX_DATA(i)			_MMIO(dev_priv->psr_mmio_base + 0x14 + (i) * 4) /* 5 registers */
 
 #define EDP_PSR_STATUS				_MMIO(dev_priv->psr_mmio_base + 0x40)
-#define   EDP_PSR_STATUS_STATE_MASK		(7<<29)
-#define   EDP_PSR_STATUS_STATE_IDLE		(0<<29)
-#define   EDP_PSR_STATUS_STATE_SRDONACK		(1<<29)
-#define   EDP_PSR_STATUS_STATE_SRDENT		(2<<29)
-#define   EDP_PSR_STATUS_STATE_BUFOFF		(3<<29)
-#define   EDP_PSR_STATUS_STATE_BUFON		(4<<29)
-#define   EDP_PSR_STATUS_STATE_AUXACK		(5<<29)
-#define   EDP_PSR_STATUS_STATE_SRDOFFACK	(6<<29)
-#define   EDP_PSR_STATUS_LINK_MASK		(3<<26)
-#define   EDP_PSR_STATUS_LINK_FULL_OFF		(0<<26)
-#define   EDP_PSR_STATUS_LINK_FULL_ON		(1<<26)
-#define   EDP_PSR_STATUS_LINK_STANDBY		(2<<26)
+#define   EDP_PSR_STATUS_STATE_MASK		(7 << 29)
+#define   EDP_PSR_STATUS_STATE_SHIFT		29
+#define   EDP_PSR_STATUS_STATE_IDLE		(0 << 29)
+#define   EDP_PSR_STATUS_STATE_SRDONACK		(1 << 29)
+#define   EDP_PSR_STATUS_STATE_SRDENT		(2 << 29)
+#define   EDP_PSR_STATUS_STATE_BUFOFF		(3 << 29)
+#define   EDP_PSR_STATUS_STATE_BUFON		(4 << 29)
+#define   EDP_PSR_STATUS_STATE_AUXACK		(5 << 29)
+#define   EDP_PSR_STATUS_STATE_SRDOFFACK	(6 << 29)
+#define   EDP_PSR_STATUS_LINK_MASK		(3 << 26)
+#define   EDP_PSR_STATUS_LINK_FULL_OFF		(0 << 26)
+#define   EDP_PSR_STATUS_LINK_FULL_ON		(1 << 26)
+#define   EDP_PSR_STATUS_LINK_STANDBY		(2 << 26)
 #define   EDP_PSR_STATUS_MAX_SLEEP_TIMER_SHIFT	20
 #define   EDP_PSR_STATUS_MAX_SLEEP_TIMER_MASK	0x1f
 #define   EDP_PSR_STATUS_COUNT_SHIFT		16
 #define   EDP_PSR_STATUS_COUNT_MASK		0xf
-#define   EDP_PSR_STATUS_AUX_ERROR		(1<<15)
-#define   EDP_PSR_STATUS_AUX_SENDING		(1<<12)
-#define   EDP_PSR_STATUS_SENDING_IDLE		(1<<9)
-#define   EDP_PSR_STATUS_SENDING_TP2_TP3	(1<<8)
-#define   EDP_PSR_STATUS_SENDING_TP1		(1<<4)
+#define   EDP_PSR_STATUS_AUX_ERROR		(1 << 15)
+#define   EDP_PSR_STATUS_AUX_SENDING		(1 << 12)
+#define   EDP_PSR_STATUS_SENDING_IDLE		(1 << 9)
+#define   EDP_PSR_STATUS_SENDING_TP2_TP3	(1 << 8)
+#define   EDP_PSR_STATUS_SENDING_TP1		(1 << 4)
 #define   EDP_PSR_STATUS_IDLE_MASK		0xf
 
 #define EDP_PSR_PERF_CNT		_MMIO(dev_priv->psr_mmio_base + 0x44)
 #define   EDP_PSR_PERF_CNT_MASK		0xffffff
 
 #define EDP_PSR_DEBUG				_MMIO(dev_priv->psr_mmio_base + 0x60) /* PSR_MASK on SKL+ */
-#define   EDP_PSR_DEBUG_MASK_MAX_SLEEP         (1<<28)
-#define   EDP_PSR_DEBUG_MASK_LPSP              (1<<27)
-#define   EDP_PSR_DEBUG_MASK_MEMUP             (1<<26)
-#define   EDP_PSR_DEBUG_MASK_HPD               (1<<25)
-#define   EDP_PSR_DEBUG_MASK_DISP_REG_WRITE    (1<<16)
-#define   EDP_PSR_DEBUG_EXIT_ON_PIXEL_UNDERRUN (1<<15) /* SKL+ */
+#define   EDP_PSR_DEBUG_MASK_MAX_SLEEP         (1 << 28)
+#define   EDP_PSR_DEBUG_MASK_LPSP              (1 << 27)
+#define   EDP_PSR_DEBUG_MASK_MEMUP             (1 << 26)
+#define   EDP_PSR_DEBUG_MASK_HPD               (1 << 25)
+#define   EDP_PSR_DEBUG_MASK_DISP_REG_WRITE    (1 << 16)
+#define   EDP_PSR_DEBUG_EXIT_ON_PIXEL_UNDERRUN (1 << 15) /* SKL+ */
 
 #define EDP_PSR2_CTL			_MMIO(0x6f900)
-#define   EDP_PSR2_ENABLE		(1<<31)
-#define   EDP_SU_TRACK_ENABLE		(1<<30)
-#define   EDP_Y_COORDINATE_VALID	(1<<26) /* GLK and CNL+ */
-#define   EDP_Y_COORDINATE_ENABLE	(1<<25) /* GLK and CNL+ */
-#define   EDP_MAX_SU_DISABLE_TIME(t)	((t)<<20)
-#define   EDP_MAX_SU_DISABLE_TIME_MASK	(0x1f<<20)
-#define   EDP_PSR2_TP2_TIME_500		(0<<8)
-#define   EDP_PSR2_TP2_TIME_100		(1<<8)
-#define   EDP_PSR2_TP2_TIME_2500	(2<<8)
-#define   EDP_PSR2_TP2_TIME_50		(3<<8)
-#define   EDP_PSR2_TP2_TIME_MASK	(3<<8)
+#define   EDP_PSR2_ENABLE		(1 << 31)
+#define   EDP_SU_TRACK_ENABLE		(1 << 30)
+#define   EDP_Y_COORDINATE_VALID	(1 << 26) /* GLK and CNL+ */
+#define   EDP_Y_COORDINATE_ENABLE	(1 << 25) /* GLK and CNL+ */
+#define   EDP_MAX_SU_DISABLE_TIME(t)	((t) << 20)
+#define   EDP_MAX_SU_DISABLE_TIME_MASK	(0x1f << 20)
+#define   EDP_PSR2_TP2_TIME_500us	(0 << 8)
+#define   EDP_PSR2_TP2_TIME_100us	(1 << 8)
+#define   EDP_PSR2_TP2_TIME_2500us	(2 << 8)
+#define   EDP_PSR2_TP2_TIME_50us	(3 << 8)
+#define   EDP_PSR2_TP2_TIME_MASK	(3 << 8)
 #define   EDP_PSR2_FRAME_BEFORE_SU_SHIFT 4
-#define   EDP_PSR2_FRAME_BEFORE_SU_MASK	(0xf<<4)
-#define   EDP_PSR2_FRAME_BEFORE_SU(a)	((a)<<4)
+#define   EDP_PSR2_FRAME_BEFORE_SU_MASK	(0xf << 4)
+#define   EDP_PSR2_FRAME_BEFORE_SU(a)	((a) << 4)
 #define   EDP_PSR2_IDLE_FRAME_MASK	0xf
 #define   EDP_PSR2_IDLE_FRAME_SHIFT	0
 
@@ -4128,7 +4251,7 @@ enum {
 #define  PSR_EVENT_PSR_DISABLE			(1 << 0)
 
 #define EDP_PSR2_STATUS			_MMIO(0x6f940)
-#define EDP_PSR2_STATUS_STATE_MASK     (0xf<<28)
+#define EDP_PSR2_STATUS_STATE_MASK     (0xf << 28)
 #define EDP_PSR2_STATUS_STATE_SHIFT    28
 
 /* VGA port control */
@@ -4136,47 +4259,48 @@ enum {
 #define PCH_ADPA                _MMIO(0xe1100)
 #define VLV_ADPA		_MMIO(VLV_DISPLAY_BASE + 0x61100)
 
-#define   ADPA_DAC_ENABLE	(1<<31)
+#define   ADPA_DAC_ENABLE	(1 << 31)
 #define   ADPA_DAC_DISABLE	0
-#define   ADPA_PIPE_SELECT_MASK	(1<<30)
-#define   ADPA_PIPE_A_SELECT	0
-#define   ADPA_PIPE_B_SELECT	(1<<30)
-#define   ADPA_PIPE_SELECT(pipe) ((pipe) << 30)
-/* CPT uses bits 29:30 for pch transcoder select */
+#define   ADPA_PIPE_SEL_SHIFT		30
+#define   ADPA_PIPE_SEL_MASK		(1 << 30)
+#define   ADPA_PIPE_SEL(pipe)		((pipe) << 30)
+#define   ADPA_PIPE_SEL_SHIFT_CPT	29
+#define   ADPA_PIPE_SEL_MASK_CPT	(3 << 29)
+#define   ADPA_PIPE_SEL_CPT(pipe)	((pipe) << 29)
 #define   ADPA_CRT_HOTPLUG_MASK  0x03ff0000 /* bit 25-16 */
-#define   ADPA_CRT_HOTPLUG_MONITOR_NONE  (0<<24)
-#define   ADPA_CRT_HOTPLUG_MONITOR_MASK  (3<<24)
-#define   ADPA_CRT_HOTPLUG_MONITOR_COLOR (3<<24)
-#define   ADPA_CRT_HOTPLUG_MONITOR_MONO  (2<<24)
-#define   ADPA_CRT_HOTPLUG_ENABLE        (1<<23)
-#define   ADPA_CRT_HOTPLUG_PERIOD_64     (0<<22)
-#define   ADPA_CRT_HOTPLUG_PERIOD_128    (1<<22)
-#define   ADPA_CRT_HOTPLUG_WARMUP_5MS    (0<<21)
-#define   ADPA_CRT_HOTPLUG_WARMUP_10MS   (1<<21)
-#define   ADPA_CRT_HOTPLUG_SAMPLE_2S     (0<<20)
-#define   ADPA_CRT_HOTPLUG_SAMPLE_4S     (1<<20)
-#define   ADPA_CRT_HOTPLUG_VOLTAGE_40    (0<<18)
-#define   ADPA_CRT_HOTPLUG_VOLTAGE_50    (1<<18)
-#define   ADPA_CRT_HOTPLUG_VOLTAGE_60    (2<<18)
-#define   ADPA_CRT_HOTPLUG_VOLTAGE_70    (3<<18)
-#define   ADPA_CRT_HOTPLUG_VOLREF_325MV  (0<<17)
-#define   ADPA_CRT_HOTPLUG_VOLREF_475MV  (1<<17)
-#define   ADPA_CRT_HOTPLUG_FORCE_TRIGGER (1<<16)
-#define   ADPA_USE_VGA_HVPOLARITY (1<<15)
+#define   ADPA_CRT_HOTPLUG_MONITOR_NONE  (0 << 24)
+#define   ADPA_CRT_HOTPLUG_MONITOR_MASK  (3 << 24)
+#define   ADPA_CRT_HOTPLUG_MONITOR_COLOR (3 << 24)
+#define   ADPA_CRT_HOTPLUG_MONITOR_MONO  (2 << 24)
+#define   ADPA_CRT_HOTPLUG_ENABLE        (1 << 23)
+#define   ADPA_CRT_HOTPLUG_PERIOD_64     (0 << 22)
+#define   ADPA_CRT_HOTPLUG_PERIOD_128    (1 << 22)
+#define   ADPA_CRT_HOTPLUG_WARMUP_5MS    (0 << 21)
+#define   ADPA_CRT_HOTPLUG_WARMUP_10MS   (1 << 21)
+#define   ADPA_CRT_HOTPLUG_SAMPLE_2S     (0 << 20)
+#define   ADPA_CRT_HOTPLUG_SAMPLE_4S     (1 << 20)
+#define   ADPA_CRT_HOTPLUG_VOLTAGE_40    (0 << 18)
+#define   ADPA_CRT_HOTPLUG_VOLTAGE_50    (1 << 18)
+#define   ADPA_CRT_HOTPLUG_VOLTAGE_60    (2 << 18)
+#define   ADPA_CRT_HOTPLUG_VOLTAGE_70    (3 << 18)
+#define   ADPA_CRT_HOTPLUG_VOLREF_325MV  (0 << 17)
+#define   ADPA_CRT_HOTPLUG_VOLREF_475MV  (1 << 17)
+#define   ADPA_CRT_HOTPLUG_FORCE_TRIGGER (1 << 16)
+#define   ADPA_USE_VGA_HVPOLARITY (1 << 15)
 #define   ADPA_SETS_HVPOLARITY	0
-#define   ADPA_VSYNC_CNTL_DISABLE (1<<10)
+#define   ADPA_VSYNC_CNTL_DISABLE (1 << 10)
 #define   ADPA_VSYNC_CNTL_ENABLE 0
-#define   ADPA_HSYNC_CNTL_DISABLE (1<<11)
+#define   ADPA_HSYNC_CNTL_DISABLE (1 << 11)
 #define   ADPA_HSYNC_CNTL_ENABLE 0
-#define   ADPA_VSYNC_ACTIVE_HIGH (1<<4)
+#define   ADPA_VSYNC_ACTIVE_HIGH (1 << 4)
 #define   ADPA_VSYNC_ACTIVE_LOW	0
-#define   ADPA_HSYNC_ACTIVE_HIGH (1<<3)
+#define   ADPA_HSYNC_ACTIVE_HIGH (1 << 3)
 #define   ADPA_HSYNC_ACTIVE_LOW	0
-#define   ADPA_DPMS_MASK	(~(3<<10))
-#define   ADPA_DPMS_ON		(0<<10)
-#define   ADPA_DPMS_SUSPEND	(1<<10)
-#define   ADPA_DPMS_STANDBY	(2<<10)
-#define   ADPA_DPMS_OFF		(3<<10)
+#define   ADPA_DPMS_MASK	(~(3 << 10))
+#define   ADPA_DPMS_ON		(0 << 10)
+#define   ADPA_DPMS_SUSPEND	(1 << 10)
+#define   ADPA_DPMS_STANDBY	(2 << 10)
+#define   ADPA_DPMS_OFF		(3 << 10)
 
 
 /* Hotplug control (945+ only) */
@@ -4301,9 +4425,9 @@ enum {
 
 /* Gen 3 SDVO bits: */
 #define   SDVO_ENABLE				(1 << 31)
-#define   SDVO_PIPE_SEL(pipe)			((pipe) << 30)
+#define   SDVO_PIPE_SEL_SHIFT			30
 #define   SDVO_PIPE_SEL_MASK			(1 << 30)
-#define   SDVO_PIPE_B_SELECT			(1 << 30)
+#define   SDVO_PIPE_SEL(pipe)			((pipe) << 30)
 #define   SDVO_STALL_SELECT			(1 << 29)
 #define   SDVO_INTERRUPT_ENABLE			(1 << 26)
 /*
@@ -4343,12 +4467,14 @@ enum {
 #define   SDVOB_HOTPLUG_ENABLE			(1 << 23) /* SDVO only */
 
 /* Gen 6 (CPT) SDVO/HDMI bits: */
-#define   SDVO_PIPE_SEL_CPT(pipe)		((pipe) << 29)
+#define   SDVO_PIPE_SEL_SHIFT_CPT		29
 #define   SDVO_PIPE_SEL_MASK_CPT		(3 << 29)
+#define   SDVO_PIPE_SEL_CPT(pipe)		((pipe) << 29)
 
 /* CHV SDVO/HDMI bits: */
-#define   SDVO_PIPE_SEL_CHV(pipe)		((pipe) << 24)
+#define   SDVO_PIPE_SEL_SHIFT_CHV		24
 #define   SDVO_PIPE_SEL_MASK_CHV		(3 << 24)
+#define   SDVO_PIPE_SEL_CHV(pipe)		((pipe) << 24)
 
 
 /* DVO port control */
@@ -4359,7 +4485,9 @@ enum {
 #define _DVOC			0x61160
 #define DVOC			_MMIO(_DVOC)
 #define   DVO_ENABLE			(1 << 31)
-#define   DVO_PIPE_B_SELECT		(1 << 30)
+#define   DVO_PIPE_SEL_SHIFT		30
+#define   DVO_PIPE_SEL_MASK		(1 << 30)
+#define   DVO_PIPE_SEL(pipe)		((pipe) << 30)
 #define   DVO_PIPE_STALL_UNUSED		(0 << 28)
 #define   DVO_PIPE_STALL		(1 << 28)
 #define   DVO_PIPE_STALL_TV		(2 << 28)
@@ -4381,7 +4509,7 @@ enum {
 #define   DVO_BLANK_ACTIVE_HIGH		(1 << 2)
 #define   DVO_OUTPUT_CSTATE_PIXELS	(1 << 1)	/* SDG only */
 #define   DVO_OUTPUT_SOURCE_SIZE_PIXELS	(1 << 0)	/* SDG only */
-#define   DVO_PRESERVE_MASK		(0x7<<24)
+#define   DVO_PRESERVE_MASK		(0x7 << 24)
 #define DVOA_SRCDIM		_MMIO(0x61124)
 #define DVOB_SRCDIM		_MMIO(0x61144)
 #define DVOC_SRCDIM		_MMIO(0x61164)
@@ -4396,9 +4524,12 @@ enum {
  */
 #define   LVDS_PORT_EN			(1 << 31)
 /* Selects pipe B for LVDS data.  Must be set on pre-965. */
-#define   LVDS_PIPEB_SELECT		(1 << 30)
-#define   LVDS_PIPE_MASK		(1 << 30)
-#define   LVDS_PIPE(pipe)		((pipe) << 30)
+#define   LVDS_PIPE_SEL_SHIFT		30
+#define   LVDS_PIPE_SEL_MASK		(1 << 30)
+#define   LVDS_PIPE_SEL(pipe)		((pipe) << 30)
+#define   LVDS_PIPE_SEL_SHIFT_CPT	29
+#define   LVDS_PIPE_SEL_MASK_CPT	(3 << 29)
+#define   LVDS_PIPE_SEL_CPT(pipe)	((pipe) << 29)
 /* LVDS dithering flag on 965/g4x platform */
 #define   LVDS_ENABLE_DITHER		(1 << 25)
 /* LVDS sync polarity flags. Set to invert (i.e. negative) */
@@ -4471,6 +4602,16 @@ enum {
 #define   VIDEO_DIP_ENABLE_GMP_HSW	(1 << 4)
 #define   VIDEO_DIP_ENABLE_SPD_HSW	(1 << 0)
 
+#define  DRM_DIP_ENABLE			(1 << 28)
+#define  PSR_VSC_BIT_7_SET		(1 << 27)
+#define  VSC_SELECT_MASK		(0x3 << 26)
+#define  VSC_SELECT_SHIFT		26
+#define  VSC_DIP_HW_HEA_DATA		(0 << 26)
+#define  VSC_DIP_HW_HEA_SW_DATA		(1 << 26)
+#define  VSC_DIP_HW_DATA_SW_HEA		(2 << 26)
+#define  VSC_DIP_SW_HEA_DATA		(3 << 26)
+#define  VDIP_ENABLE_PPS		(1 << 24)
+
 /* Panel power sequencing */
 #define PPS_BASE			0x61200
 #define VLV_PPS_BASE			(VLV_DISPLAY_BASE + PPS_BASE)
@@ -4695,7 +4836,9 @@ enum {
 /* Enables the TV encoder */
 # define TV_ENC_ENABLE			(1 << 31)
 /* Sources the TV encoder input from pipe B instead of A. */
-# define TV_ENC_PIPEB_SELECT		(1 << 30)
+# define TV_ENC_PIPE_SEL_SHIFT		30
+# define TV_ENC_PIPE_SEL_MASK		(1 << 30)
+# define TV_ENC_PIPE_SEL(pipe)		((pipe) << 30)
 /* Outputs composite video (DAC A only) */
 # define TV_ENC_OUTPUT_COMPOSITE	(0 << 28)
 /* Outputs SVideo video (DAC B/C) */
@@ -5177,10 +5320,15 @@ enum {
 #define CHV_DP_D		_MMIO(VLV_DISPLAY_BASE + 0x64300)
 
 #define   DP_PORT_EN			(1 << 31)
-#define   DP_PIPEB_SELECT		(1 << 30)
-#define   DP_PIPE_MASK			(1 << 30)
-#define   DP_PIPE_SELECT_CHV(pipe)	((pipe) << 16)
-#define   DP_PIPE_MASK_CHV		(3 << 16)
+#define   DP_PIPE_SEL_SHIFT		30
+#define   DP_PIPE_SEL_MASK		(1 << 30)
+#define   DP_PIPE_SEL(pipe)		((pipe) << 30)
+#define   DP_PIPE_SEL_SHIFT_IVB		29
+#define   DP_PIPE_SEL_MASK_IVB		(3 << 29)
+#define   DP_PIPE_SEL_IVB(pipe)		((pipe) << 29)
+#define   DP_PIPE_SEL_SHIFT_CHV		16
+#define   DP_PIPE_SEL_MASK_CHV		(3 << 16)
+#define   DP_PIPE_SEL_CHV(pipe)		((pipe) << 16)
 
 /* Link training mode - select a suitable mode for each stage */
 #define   DP_LINK_TRAIN_PAT_1		(0 << 28)
@@ -5287,6 +5435,13 @@ enum {
 #define _DPD_AUX_CH_DATA4	(dev_priv->info.display_mmio_offset + 0x64320)
 #define _DPD_AUX_CH_DATA5	(dev_priv->info.display_mmio_offset + 0x64324)
 
+#define _DPE_AUX_CH_CTL		(dev_priv->info.display_mmio_offset + 0x64410)
+#define _DPE_AUX_CH_DATA1	(dev_priv->info.display_mmio_offset + 0x64414)
+#define _DPE_AUX_CH_DATA2	(dev_priv->info.display_mmio_offset + 0x64418)
+#define _DPE_AUX_CH_DATA3	(dev_priv->info.display_mmio_offset + 0x6441c)
+#define _DPE_AUX_CH_DATA4	(dev_priv->info.display_mmio_offset + 0x64420)
+#define _DPE_AUX_CH_DATA5	(dev_priv->info.display_mmio_offset + 0x64424)
+
 #define _DPF_AUX_CH_CTL		(dev_priv->info.display_mmio_offset + 0x64510)
 #define _DPF_AUX_CH_DATA1	(dev_priv->info.display_mmio_offset + 0x64514)
 #define _DPF_AUX_CH_DATA2	(dev_priv->info.display_mmio_offset + 0x64518)
@@ -5342,7 +5497,7 @@ enum {
 #define _PIPEB_DATA_M_G4X	0x71050
 
 /* Transfer unit size for display port - 1, default is 0x3f (for TU size 64) */
-#define  TU_SIZE(x)             (((x)-1) << 25) /* default size 64 */
+#define  TU_SIZE(x)             (((x) - 1) << 25) /* default size 64 */
 #define  TU_SIZE_SHIFT		25
 #define  TU_SIZE_MASK           (0x3f << 25)
 
@@ -5384,18 +5539,18 @@ enum {
 #define   DSL_LINEMASK_GEN2	0x00000fff
 #define   DSL_LINEMASK_GEN3	0x00001fff
 #define _PIPEACONF		0x70008
-#define   PIPECONF_ENABLE	(1<<31)
+#define   PIPECONF_ENABLE	(1 << 31)
 #define   PIPECONF_DISABLE	0
-#define   PIPECONF_DOUBLE_WIDE	(1<<30)
-#define   I965_PIPECONF_ACTIVE	(1<<30)
-#define   PIPECONF_DSI_PLL_LOCKED	(1<<29) /* vlv & pipe A only */
-#define   PIPECONF_FRAME_START_DELAY_MASK (3<<27)
+#define   PIPECONF_DOUBLE_WIDE	(1 << 30)
+#define   I965_PIPECONF_ACTIVE	(1 << 30)
+#define   PIPECONF_DSI_PLL_LOCKED	(1 << 29) /* vlv & pipe A only */
+#define   PIPECONF_FRAME_START_DELAY_MASK (3 << 27)
 #define   PIPECONF_SINGLE_WIDE	0
 #define   PIPECONF_PIPE_UNLOCKED 0
-#define   PIPECONF_PIPE_LOCKED	(1<<25)
+#define   PIPECONF_PIPE_LOCKED	(1 << 25)
 #define   PIPECONF_PALETTE	0
-#define   PIPECONF_GAMMA		(1<<24)
-#define   PIPECONF_FORCE_BORDER	(1<<25)
+#define   PIPECONF_GAMMA		(1 << 24)
+#define   PIPECONF_FORCE_BORDER	(1 << 25)
 #define   PIPECONF_INTERLACE_MASK	(7 << 21)
 #define   PIPECONF_INTERLACE_MASK_HSW	(3 << 21)
 /* Note that pre-gen3 does not support interlaced display directly. Panel
@@ -5414,67 +5569,67 @@ enum {
 #define   PIPECONF_PFIT_PF_INTERLACED_DBL_ILK	(5 << 21) /* ilk/snb only */
 #define   PIPECONF_INTERLACE_MODE_MASK		(7 << 21)
 #define   PIPECONF_EDP_RR_MODE_SWITCH		(1 << 20)
-#define   PIPECONF_CXSR_DOWNCLOCK	(1<<16)
+#define   PIPECONF_CXSR_DOWNCLOCK	(1 << 16)
 #define   PIPECONF_EDP_RR_MODE_SWITCH_VLV	(1 << 14)
 #define   PIPECONF_COLOR_RANGE_SELECT	(1 << 13)
 #define   PIPECONF_BPC_MASK	(0x7 << 5)
-#define   PIPECONF_8BPC		(0<<5)
-#define   PIPECONF_10BPC	(1<<5)
-#define   PIPECONF_6BPC		(2<<5)
-#define   PIPECONF_12BPC	(3<<5)
-#define   PIPECONF_DITHER_EN	(1<<4)
+#define   PIPECONF_8BPC		(0 << 5)
+#define   PIPECONF_10BPC	(1 << 5)
+#define   PIPECONF_6BPC		(2 << 5)
+#define   PIPECONF_12BPC	(3 << 5)
+#define   PIPECONF_DITHER_EN	(1 << 4)
 #define   PIPECONF_DITHER_TYPE_MASK (0x0000000c)
-#define   PIPECONF_DITHER_TYPE_SP (0<<2)
-#define   PIPECONF_DITHER_TYPE_ST1 (1<<2)
-#define   PIPECONF_DITHER_TYPE_ST2 (2<<2)
-#define   PIPECONF_DITHER_TYPE_TEMP (3<<2)
+#define   PIPECONF_DITHER_TYPE_SP (0 << 2)
+#define   PIPECONF_DITHER_TYPE_ST1 (1 << 2)
+#define   PIPECONF_DITHER_TYPE_ST2 (2 << 2)
+#define   PIPECONF_DITHER_TYPE_TEMP (3 << 2)
 #define _PIPEASTAT		0x70024
-#define   PIPE_FIFO_UNDERRUN_STATUS		(1UL<<31)
-#define   SPRITE1_FLIP_DONE_INT_EN_VLV		(1UL<<30)
-#define   PIPE_CRC_ERROR_ENABLE			(1UL<<29)
-#define   PIPE_CRC_DONE_ENABLE			(1UL<<28)
-#define   PERF_COUNTER2_INTERRUPT_EN		(1UL<<27)
-#define   PIPE_GMBUS_EVENT_ENABLE		(1UL<<27)
-#define   PLANE_FLIP_DONE_INT_EN_VLV		(1UL<<26)
-#define   PIPE_HOTPLUG_INTERRUPT_ENABLE		(1UL<<26)
-#define   PIPE_VSYNC_INTERRUPT_ENABLE		(1UL<<25)
-#define   PIPE_DISPLAY_LINE_COMPARE_ENABLE	(1UL<<24)
-#define   PIPE_DPST_EVENT_ENABLE		(1UL<<23)
-#define   SPRITE0_FLIP_DONE_INT_EN_VLV		(1UL<<22)
-#define   PIPE_LEGACY_BLC_EVENT_ENABLE		(1UL<<22)
-#define   PIPE_ODD_FIELD_INTERRUPT_ENABLE	(1UL<<21)
-#define   PIPE_EVEN_FIELD_INTERRUPT_ENABLE	(1UL<<20)
-#define   PIPE_B_PSR_INTERRUPT_ENABLE_VLV	(1UL<<19)
-#define   PERF_COUNTER_INTERRUPT_EN		(1UL<<19)
-#define   PIPE_HOTPLUG_TV_INTERRUPT_ENABLE	(1UL<<18) /* pre-965 */
-#define   PIPE_START_VBLANK_INTERRUPT_ENABLE	(1UL<<18) /* 965 or later */
-#define   PIPE_FRAMESTART_INTERRUPT_ENABLE	(1UL<<17)
-#define   PIPE_VBLANK_INTERRUPT_ENABLE		(1UL<<17)
-#define   PIPEA_HBLANK_INT_EN_VLV		(1UL<<16)
-#define   PIPE_OVERLAY_UPDATED_ENABLE		(1UL<<16)
-#define   SPRITE1_FLIP_DONE_INT_STATUS_VLV	(1UL<<15)
-#define   SPRITE0_FLIP_DONE_INT_STATUS_VLV	(1UL<<14)
-#define   PIPE_CRC_ERROR_INTERRUPT_STATUS	(1UL<<13)
-#define   PIPE_CRC_DONE_INTERRUPT_STATUS	(1UL<<12)
-#define   PERF_COUNTER2_INTERRUPT_STATUS	(1UL<<11)
-#define   PIPE_GMBUS_INTERRUPT_STATUS		(1UL<<11)
-#define   PLANE_FLIP_DONE_INT_STATUS_VLV	(1UL<<10)
-#define   PIPE_HOTPLUG_INTERRUPT_STATUS		(1UL<<10)
-#define   PIPE_VSYNC_INTERRUPT_STATUS		(1UL<<9)
-#define   PIPE_DISPLAY_LINE_COMPARE_STATUS	(1UL<<8)
-#define   PIPE_DPST_EVENT_STATUS		(1UL<<7)
-#define   PIPE_A_PSR_STATUS_VLV			(1UL<<6)
-#define   PIPE_LEGACY_BLC_EVENT_STATUS		(1UL<<6)
-#define   PIPE_ODD_FIELD_INTERRUPT_STATUS	(1UL<<5)
-#define   PIPE_EVEN_FIELD_INTERRUPT_STATUS	(1UL<<4)
-#define   PIPE_B_PSR_STATUS_VLV			(1UL<<3)
-#define   PERF_COUNTER_INTERRUPT_STATUS		(1UL<<3)
-#define   PIPE_HOTPLUG_TV_INTERRUPT_STATUS	(1UL<<2) /* pre-965 */
-#define   PIPE_START_VBLANK_INTERRUPT_STATUS	(1UL<<2) /* 965 or later */
-#define   PIPE_FRAMESTART_INTERRUPT_STATUS	(1UL<<1)
-#define   PIPE_VBLANK_INTERRUPT_STATUS		(1UL<<1)
-#define   PIPE_HBLANK_INT_STATUS		(1UL<<0)
-#define   PIPE_OVERLAY_UPDATED_STATUS		(1UL<<0)
+#define   PIPE_FIFO_UNDERRUN_STATUS		(1UL << 31)
+#define   SPRITE1_FLIP_DONE_INT_EN_VLV		(1UL << 30)
+#define   PIPE_CRC_ERROR_ENABLE			(1UL << 29)
+#define   PIPE_CRC_DONE_ENABLE			(1UL << 28)
+#define   PERF_COUNTER2_INTERRUPT_EN		(1UL << 27)
+#define   PIPE_GMBUS_EVENT_ENABLE		(1UL << 27)
+#define   PLANE_FLIP_DONE_INT_EN_VLV		(1UL << 26)
+#define   PIPE_HOTPLUG_INTERRUPT_ENABLE		(1UL << 26)
+#define   PIPE_VSYNC_INTERRUPT_ENABLE		(1UL << 25)
+#define   PIPE_DISPLAY_LINE_COMPARE_ENABLE	(1UL << 24)
+#define   PIPE_DPST_EVENT_ENABLE		(1UL << 23)
+#define   SPRITE0_FLIP_DONE_INT_EN_VLV		(1UL << 22)
+#define   PIPE_LEGACY_BLC_EVENT_ENABLE		(1UL << 22)
+#define   PIPE_ODD_FIELD_INTERRUPT_ENABLE	(1UL << 21)
+#define   PIPE_EVEN_FIELD_INTERRUPT_ENABLE	(1UL << 20)
+#define   PIPE_B_PSR_INTERRUPT_ENABLE_VLV	(1UL << 19)
+#define   PERF_COUNTER_INTERRUPT_EN		(1UL << 19)
+#define   PIPE_HOTPLUG_TV_INTERRUPT_ENABLE	(1UL << 18) /* pre-965 */
+#define   PIPE_START_VBLANK_INTERRUPT_ENABLE	(1UL << 18) /* 965 or later */
+#define   PIPE_FRAMESTART_INTERRUPT_ENABLE	(1UL << 17)
+#define   PIPE_VBLANK_INTERRUPT_ENABLE		(1UL << 17)
+#define   PIPEA_HBLANK_INT_EN_VLV		(1UL << 16)
+#define   PIPE_OVERLAY_UPDATED_ENABLE		(1UL << 16)
+#define   SPRITE1_FLIP_DONE_INT_STATUS_VLV	(1UL << 15)
+#define   SPRITE0_FLIP_DONE_INT_STATUS_VLV	(1UL << 14)
+#define   PIPE_CRC_ERROR_INTERRUPT_STATUS	(1UL << 13)
+#define   PIPE_CRC_DONE_INTERRUPT_STATUS	(1UL << 12)
+#define   PERF_COUNTER2_INTERRUPT_STATUS	(1UL << 11)
+#define   PIPE_GMBUS_INTERRUPT_STATUS		(1UL << 11)
+#define   PLANE_FLIP_DONE_INT_STATUS_VLV	(1UL << 10)
+#define   PIPE_HOTPLUG_INTERRUPT_STATUS		(1UL << 10)
+#define   PIPE_VSYNC_INTERRUPT_STATUS		(1UL << 9)
+#define   PIPE_DISPLAY_LINE_COMPARE_STATUS	(1UL << 8)
+#define   PIPE_DPST_EVENT_STATUS		(1UL << 7)
+#define   PIPE_A_PSR_STATUS_VLV			(1UL << 6)
+#define   PIPE_LEGACY_BLC_EVENT_STATUS		(1UL << 6)
+#define   PIPE_ODD_FIELD_INTERRUPT_STATUS	(1UL << 5)
+#define   PIPE_EVEN_FIELD_INTERRUPT_STATUS	(1UL << 4)
+#define   PIPE_B_PSR_STATUS_VLV			(1UL << 3)
+#define   PERF_COUNTER_INTERRUPT_STATUS		(1UL << 3)
+#define   PIPE_HOTPLUG_TV_INTERRUPT_STATUS	(1UL << 2) /* pre-965 */
+#define   PIPE_START_VBLANK_INTERRUPT_STATUS	(1UL << 2) /* 965 or later */
+#define   PIPE_FRAMESTART_INTERRUPT_STATUS	(1UL << 1)
+#define   PIPE_VBLANK_INTERRUPT_STATUS		(1UL << 1)
+#define   PIPE_HBLANK_INT_STATUS		(1UL << 0)
+#define   PIPE_OVERLAY_UPDATED_STATUS		(1UL << 0)
 
 #define PIPESTAT_INT_ENABLE_MASK		0x7fff0000
 #define PIPESTAT_INT_STATUS_MASK		0x0000ffff
@@ -5503,67 +5658,67 @@ enum {
 
 #define _PIPE_MISC_A			0x70030
 #define _PIPE_MISC_B			0x71030
-#define   PIPEMISC_YUV420_ENABLE	(1<<27)
-#define   PIPEMISC_YUV420_MODE_FULL_BLEND (1<<26)
-#define   PIPEMISC_OUTPUT_COLORSPACE_YUV  (1<<11)
-#define   PIPEMISC_DITHER_BPC_MASK	(7<<5)
-#define   PIPEMISC_DITHER_8_BPC		(0<<5)
-#define   PIPEMISC_DITHER_10_BPC	(1<<5)
-#define   PIPEMISC_DITHER_6_BPC		(2<<5)
-#define   PIPEMISC_DITHER_12_BPC	(3<<5)
-#define   PIPEMISC_DITHER_ENABLE	(1<<4)
-#define   PIPEMISC_DITHER_TYPE_MASK	(3<<2)
-#define   PIPEMISC_DITHER_TYPE_SP	(0<<2)
+#define   PIPEMISC_YUV420_ENABLE	(1 << 27)
+#define   PIPEMISC_YUV420_MODE_FULL_BLEND (1 << 26)
+#define   PIPEMISC_OUTPUT_COLORSPACE_YUV  (1 << 11)
+#define   PIPEMISC_DITHER_BPC_MASK	(7 << 5)
+#define   PIPEMISC_DITHER_8_BPC		(0 << 5)
+#define   PIPEMISC_DITHER_10_BPC	(1 << 5)
+#define   PIPEMISC_DITHER_6_BPC		(2 << 5)
+#define   PIPEMISC_DITHER_12_BPC	(3 << 5)
+#define   PIPEMISC_DITHER_ENABLE	(1 << 4)
+#define   PIPEMISC_DITHER_TYPE_MASK	(3 << 2)
+#define   PIPEMISC_DITHER_TYPE_SP	(0 << 2)
 #define PIPEMISC(pipe)			_MMIO_PIPE2(pipe, _PIPE_MISC_A)
 
 #define VLV_DPFLIPSTAT				_MMIO(VLV_DISPLAY_BASE + 0x70028)
-#define   PIPEB_LINE_COMPARE_INT_EN		(1<<29)
-#define   PIPEB_HLINE_INT_EN			(1<<28)
-#define   PIPEB_VBLANK_INT_EN			(1<<27)
-#define   SPRITED_FLIP_DONE_INT_EN		(1<<26)
-#define   SPRITEC_FLIP_DONE_INT_EN		(1<<25)
-#define   PLANEB_FLIP_DONE_INT_EN		(1<<24)
-#define   PIPE_PSR_INT_EN			(1<<22)
-#define   PIPEA_LINE_COMPARE_INT_EN		(1<<21)
-#define   PIPEA_HLINE_INT_EN			(1<<20)
-#define   PIPEA_VBLANK_INT_EN			(1<<19)
-#define   SPRITEB_FLIP_DONE_INT_EN		(1<<18)
-#define   SPRITEA_FLIP_DONE_INT_EN		(1<<17)
-#define   PLANEA_FLIPDONE_INT_EN		(1<<16)
-#define   PIPEC_LINE_COMPARE_INT_EN		(1<<13)
-#define   PIPEC_HLINE_INT_EN			(1<<12)
-#define   PIPEC_VBLANK_INT_EN			(1<<11)
-#define   SPRITEF_FLIPDONE_INT_EN		(1<<10)
-#define   SPRITEE_FLIPDONE_INT_EN		(1<<9)
-#define   PLANEC_FLIPDONE_INT_EN		(1<<8)
+#define   PIPEB_LINE_COMPARE_INT_EN		(1 << 29)
+#define   PIPEB_HLINE_INT_EN			(1 << 28)
+#define   PIPEB_VBLANK_INT_EN			(1 << 27)
+#define   SPRITED_FLIP_DONE_INT_EN		(1 << 26)
+#define   SPRITEC_FLIP_DONE_INT_EN		(1 << 25)
+#define   PLANEB_FLIP_DONE_INT_EN		(1 << 24)
+#define   PIPE_PSR_INT_EN			(1 << 22)
+#define   PIPEA_LINE_COMPARE_INT_EN		(1 << 21)
+#define   PIPEA_HLINE_INT_EN			(1 << 20)
+#define   PIPEA_VBLANK_INT_EN			(1 << 19)
+#define   SPRITEB_FLIP_DONE_INT_EN		(1 << 18)
+#define   SPRITEA_FLIP_DONE_INT_EN		(1 << 17)
+#define   PLANEA_FLIPDONE_INT_EN		(1 << 16)
+#define   PIPEC_LINE_COMPARE_INT_EN		(1 << 13)
+#define   PIPEC_HLINE_INT_EN			(1 << 12)
+#define   PIPEC_VBLANK_INT_EN			(1 << 11)
+#define   SPRITEF_FLIPDONE_INT_EN		(1 << 10)
+#define   SPRITEE_FLIPDONE_INT_EN		(1 << 9)
+#define   PLANEC_FLIPDONE_INT_EN		(1 << 8)
 
 #define DPINVGTT				_MMIO(VLV_DISPLAY_BASE + 0x7002c) /* VLV/CHV only */
-#define   SPRITEF_INVALID_GTT_INT_EN		(1<<27)
-#define   SPRITEE_INVALID_GTT_INT_EN		(1<<26)
-#define   PLANEC_INVALID_GTT_INT_EN		(1<<25)
-#define   CURSORC_INVALID_GTT_INT_EN		(1<<24)
-#define   CURSORB_INVALID_GTT_INT_EN		(1<<23)
-#define   CURSORA_INVALID_GTT_INT_EN		(1<<22)
-#define   SPRITED_INVALID_GTT_INT_EN		(1<<21)
-#define   SPRITEC_INVALID_GTT_INT_EN		(1<<20)
-#define   PLANEB_INVALID_GTT_INT_EN		(1<<19)
-#define   SPRITEB_INVALID_GTT_INT_EN		(1<<18)
-#define   SPRITEA_INVALID_GTT_INT_EN		(1<<17)
-#define   PLANEA_INVALID_GTT_INT_EN		(1<<16)
+#define   SPRITEF_INVALID_GTT_INT_EN		(1 << 27)
+#define   SPRITEE_INVALID_GTT_INT_EN		(1 << 26)
+#define   PLANEC_INVALID_GTT_INT_EN		(1 << 25)
+#define   CURSORC_INVALID_GTT_INT_EN		(1 << 24)
+#define   CURSORB_INVALID_GTT_INT_EN		(1 << 23)
+#define   CURSORA_INVALID_GTT_INT_EN		(1 << 22)
+#define   SPRITED_INVALID_GTT_INT_EN		(1 << 21)
+#define   SPRITEC_INVALID_GTT_INT_EN		(1 << 20)
+#define   PLANEB_INVALID_GTT_INT_EN		(1 << 19)
+#define   SPRITEB_INVALID_GTT_INT_EN		(1 << 18)
+#define   SPRITEA_INVALID_GTT_INT_EN		(1 << 17)
+#define   PLANEA_INVALID_GTT_INT_EN		(1 << 16)
 #define   DPINVGTT_EN_MASK			0xff0000
 #define   DPINVGTT_EN_MASK_CHV			0xfff0000
-#define   SPRITEF_INVALID_GTT_STATUS		(1<<11)
-#define   SPRITEE_INVALID_GTT_STATUS		(1<<10)
-#define   PLANEC_INVALID_GTT_STATUS		(1<<9)
-#define   CURSORC_INVALID_GTT_STATUS		(1<<8)
-#define   CURSORB_INVALID_GTT_STATUS		(1<<7)
-#define   CURSORA_INVALID_GTT_STATUS		(1<<6)
-#define   SPRITED_INVALID_GTT_STATUS		(1<<5)
-#define   SPRITEC_INVALID_GTT_STATUS		(1<<4)
-#define   PLANEB_INVALID_GTT_STATUS		(1<<3)
-#define   SPRITEB_INVALID_GTT_STATUS		(1<<2)
-#define   SPRITEA_INVALID_GTT_STATUS		(1<<1)
-#define   PLANEA_INVALID_GTT_STATUS		(1<<0)
+#define   SPRITEF_INVALID_GTT_STATUS		(1 << 11)
+#define   SPRITEE_INVALID_GTT_STATUS		(1 << 10)
+#define   PLANEC_INVALID_GTT_STATUS		(1 << 9)
+#define   CURSORC_INVALID_GTT_STATUS		(1 << 8)
+#define   CURSORB_INVALID_GTT_STATUS		(1 << 7)
+#define   CURSORA_INVALID_GTT_STATUS		(1 << 6)
+#define   SPRITED_INVALID_GTT_STATUS		(1 << 5)
+#define   SPRITEC_INVALID_GTT_STATUS		(1 << 4)
+#define   PLANEB_INVALID_GTT_STATUS		(1 << 3)
+#define   SPRITEB_INVALID_GTT_STATUS		(1 << 2)
+#define   SPRITEA_INVALID_GTT_STATUS		(1 << 1)
+#define   PLANEA_INVALID_GTT_STATUS		(1 << 0)
 #define   DPINVGTT_STATUS_MASK			0xff
 #define   DPINVGTT_STATUS_MASK_CHV		0xfff
 
@@ -5604,149 +5759,149 @@ enum {
 /* pnv/gen4/g4x/vlv/chv */
 #define DSPFW1		_MMIO(dev_priv->info.display_mmio_offset + 0x70034)
 #define   DSPFW_SR_SHIFT		23
-#define   DSPFW_SR_MASK			(0x1ff<<23)
+#define   DSPFW_SR_MASK			(0x1ff << 23)
 #define   DSPFW_CURSORB_SHIFT		16
-#define   DSPFW_CURSORB_MASK		(0x3f<<16)
+#define   DSPFW_CURSORB_MASK		(0x3f << 16)
 #define   DSPFW_PLANEB_SHIFT		8
-#define   DSPFW_PLANEB_MASK		(0x7f<<8)
-#define   DSPFW_PLANEB_MASK_VLV		(0xff<<8) /* vlv/chv */
+#define   DSPFW_PLANEB_MASK		(0x7f << 8)
+#define   DSPFW_PLANEB_MASK_VLV		(0xff << 8) /* vlv/chv */
 #define   DSPFW_PLANEA_SHIFT		0
-#define   DSPFW_PLANEA_MASK		(0x7f<<0)
-#define   DSPFW_PLANEA_MASK_VLV		(0xff<<0) /* vlv/chv */
+#define   DSPFW_PLANEA_MASK		(0x7f << 0)
+#define   DSPFW_PLANEA_MASK_VLV		(0xff << 0) /* vlv/chv */
 #define DSPFW2		_MMIO(dev_priv->info.display_mmio_offset + 0x70038)
-#define   DSPFW_FBC_SR_EN		(1<<31)	  /* g4x */
+#define   DSPFW_FBC_SR_EN		(1 << 31)	  /* g4x */
 #define   DSPFW_FBC_SR_SHIFT		28
-#define   DSPFW_FBC_SR_MASK		(0x7<<28) /* g4x */
+#define   DSPFW_FBC_SR_MASK		(0x7 << 28) /* g4x */
 #define   DSPFW_FBC_HPLL_SR_SHIFT	24
-#define   DSPFW_FBC_HPLL_SR_MASK	(0xf<<24) /* g4x */
+#define   DSPFW_FBC_HPLL_SR_MASK	(0xf << 24) /* g4x */
 #define   DSPFW_SPRITEB_SHIFT		(16)
-#define   DSPFW_SPRITEB_MASK		(0x7f<<16) /* g4x */
-#define   DSPFW_SPRITEB_MASK_VLV	(0xff<<16) /* vlv/chv */
+#define   DSPFW_SPRITEB_MASK		(0x7f << 16) /* g4x */
+#define   DSPFW_SPRITEB_MASK_VLV	(0xff << 16) /* vlv/chv */
 #define   DSPFW_CURSORA_SHIFT		8
-#define   DSPFW_CURSORA_MASK		(0x3f<<8)
+#define   DSPFW_CURSORA_MASK		(0x3f << 8)
 #define   DSPFW_PLANEC_OLD_SHIFT	0
-#define   DSPFW_PLANEC_OLD_MASK		(0x7f<<0) /* pre-gen4 sprite C */
+#define   DSPFW_PLANEC_OLD_MASK		(0x7f << 0) /* pre-gen4 sprite C */
 #define   DSPFW_SPRITEA_SHIFT		0
-#define   DSPFW_SPRITEA_MASK		(0x7f<<0) /* g4x */
-#define   DSPFW_SPRITEA_MASK_VLV	(0xff<<0) /* vlv/chv */
+#define   DSPFW_SPRITEA_MASK		(0x7f << 0) /* g4x */
+#define   DSPFW_SPRITEA_MASK_VLV	(0xff << 0) /* vlv/chv */
 #define DSPFW3		_MMIO(dev_priv->info.display_mmio_offset + 0x7003c)
-#define   DSPFW_HPLL_SR_EN		(1<<31)
-#define   PINEVIEW_SELF_REFRESH_EN	(1<<30)
+#define   DSPFW_HPLL_SR_EN		(1 << 31)
+#define   PINEVIEW_SELF_REFRESH_EN	(1 << 30)
 #define   DSPFW_CURSOR_SR_SHIFT		24
-#define   DSPFW_CURSOR_SR_MASK		(0x3f<<24)
+#define   DSPFW_CURSOR_SR_MASK		(0x3f << 24)
 #define   DSPFW_HPLL_CURSOR_SHIFT	16
-#define   DSPFW_HPLL_CURSOR_MASK	(0x3f<<16)
+#define   DSPFW_HPLL_CURSOR_MASK	(0x3f << 16)
 #define   DSPFW_HPLL_SR_SHIFT		0
-#define   DSPFW_HPLL_SR_MASK		(0x1ff<<0)
+#define   DSPFW_HPLL_SR_MASK		(0x1ff << 0)
 
 /* vlv/chv */
 #define DSPFW4		_MMIO(VLV_DISPLAY_BASE + 0x70070)
 #define   DSPFW_SPRITEB_WM1_SHIFT	16
-#define   DSPFW_SPRITEB_WM1_MASK	(0xff<<16)
+#define   DSPFW_SPRITEB_WM1_MASK	(0xff << 16)
 #define   DSPFW_CURSORA_WM1_SHIFT	8
-#define   DSPFW_CURSORA_WM1_MASK	(0x3f<<8)
+#define   DSPFW_CURSORA_WM1_MASK	(0x3f << 8)
 #define   DSPFW_SPRITEA_WM1_SHIFT	0
-#define   DSPFW_SPRITEA_WM1_MASK	(0xff<<0)
+#define   DSPFW_SPRITEA_WM1_MASK	(0xff << 0)
 #define DSPFW5		_MMIO(VLV_DISPLAY_BASE + 0x70074)
 #define   DSPFW_PLANEB_WM1_SHIFT	24
-#define   DSPFW_PLANEB_WM1_MASK		(0xff<<24)
+#define   DSPFW_PLANEB_WM1_MASK		(0xff << 24)
 #define   DSPFW_PLANEA_WM1_SHIFT	16
-#define   DSPFW_PLANEA_WM1_MASK		(0xff<<16)
+#define   DSPFW_PLANEA_WM1_MASK		(0xff << 16)
 #define   DSPFW_CURSORB_WM1_SHIFT	8
-#define   DSPFW_CURSORB_WM1_MASK	(0x3f<<8)
+#define   DSPFW_CURSORB_WM1_MASK	(0x3f << 8)
 #define   DSPFW_CURSOR_SR_WM1_SHIFT	0
-#define   DSPFW_CURSOR_SR_WM1_MASK	(0x3f<<0)
+#define   DSPFW_CURSOR_SR_WM1_MASK	(0x3f << 0)
 #define DSPFW6		_MMIO(VLV_DISPLAY_BASE + 0x70078)
 #define   DSPFW_SR_WM1_SHIFT		0
-#define   DSPFW_SR_WM1_MASK		(0x1ff<<0)
+#define   DSPFW_SR_WM1_MASK		(0x1ff << 0)
 #define DSPFW7		_MMIO(VLV_DISPLAY_BASE + 0x7007c)
 #define DSPFW7_CHV	_MMIO(VLV_DISPLAY_BASE + 0x700b4) /* wtf #1? */
 #define   DSPFW_SPRITED_WM1_SHIFT	24
-#define   DSPFW_SPRITED_WM1_MASK	(0xff<<24)
+#define   DSPFW_SPRITED_WM1_MASK	(0xff << 24)
 #define   DSPFW_SPRITED_SHIFT		16
-#define   DSPFW_SPRITED_MASK_VLV	(0xff<<16)
+#define   DSPFW_SPRITED_MASK_VLV	(0xff << 16)
 #define   DSPFW_SPRITEC_WM1_SHIFT	8
-#define   DSPFW_SPRITEC_WM1_MASK	(0xff<<8)
+#define   DSPFW_SPRITEC_WM1_MASK	(0xff << 8)
 #define   DSPFW_SPRITEC_SHIFT		0
-#define   DSPFW_SPRITEC_MASK_VLV	(0xff<<0)
+#define   DSPFW_SPRITEC_MASK_VLV	(0xff << 0)
 #define DSPFW8_CHV	_MMIO(VLV_DISPLAY_BASE + 0x700b8)
 #define   DSPFW_SPRITEF_WM1_SHIFT	24
-#define   DSPFW_SPRITEF_WM1_MASK	(0xff<<24)
+#define   DSPFW_SPRITEF_WM1_MASK	(0xff << 24)
 #define   DSPFW_SPRITEF_SHIFT		16
-#define   DSPFW_SPRITEF_MASK_VLV	(0xff<<16)
+#define   DSPFW_SPRITEF_MASK_VLV	(0xff << 16)
 #define   DSPFW_SPRITEE_WM1_SHIFT	8
-#define   DSPFW_SPRITEE_WM1_MASK	(0xff<<8)
+#define   DSPFW_SPRITEE_WM1_MASK	(0xff << 8)
 #define   DSPFW_SPRITEE_SHIFT		0
-#define   DSPFW_SPRITEE_MASK_VLV	(0xff<<0)
+#define   DSPFW_SPRITEE_MASK_VLV	(0xff << 0)
 #define DSPFW9_CHV	_MMIO(VLV_DISPLAY_BASE + 0x7007c) /* wtf #2? */
 #define   DSPFW_PLANEC_WM1_SHIFT	24
-#define   DSPFW_PLANEC_WM1_MASK		(0xff<<24)
+#define   DSPFW_PLANEC_WM1_MASK		(0xff << 24)
 #define   DSPFW_PLANEC_SHIFT		16
-#define   DSPFW_PLANEC_MASK_VLV		(0xff<<16)
+#define   DSPFW_PLANEC_MASK_VLV		(0xff << 16)
 #define   DSPFW_CURSORC_WM1_SHIFT	8
-#define   DSPFW_CURSORC_WM1_MASK	(0x3f<<16)
+#define   DSPFW_CURSORC_WM1_MASK	(0x3f << 16)
 #define   DSPFW_CURSORC_SHIFT		0
-#define   DSPFW_CURSORC_MASK		(0x3f<<0)
+#define   DSPFW_CURSORC_MASK		(0x3f << 0)
 
 /* vlv/chv high order bits */
 #define DSPHOWM		_MMIO(VLV_DISPLAY_BASE + 0x70064)
 #define   DSPFW_SR_HI_SHIFT		24
-#define   DSPFW_SR_HI_MASK		(3<<24) /* 2 bits for chv, 1 for vlv */
+#define   DSPFW_SR_HI_MASK		(3 << 24) /* 2 bits for chv, 1 for vlv */
 #define   DSPFW_SPRITEF_HI_SHIFT	23
-#define   DSPFW_SPRITEF_HI_MASK		(1<<23)
+#define   DSPFW_SPRITEF_HI_MASK		(1 << 23)
 #define   DSPFW_SPRITEE_HI_SHIFT	22
-#define   DSPFW_SPRITEE_HI_MASK		(1<<22)
+#define   DSPFW_SPRITEE_HI_MASK		(1 << 22)
 #define   DSPFW_PLANEC_HI_SHIFT		21
-#define   DSPFW_PLANEC_HI_MASK		(1<<21)
+#define   DSPFW_PLANEC_HI_MASK		(1 << 21)
 #define   DSPFW_SPRITED_HI_SHIFT	20
-#define   DSPFW_SPRITED_HI_MASK		(1<<20)
+#define   DSPFW_SPRITED_HI_MASK		(1 << 20)
 #define   DSPFW_SPRITEC_HI_SHIFT	16
-#define   DSPFW_SPRITEC_HI_MASK		(1<<16)
+#define   DSPFW_SPRITEC_HI_MASK		(1 << 16)
 #define   DSPFW_PLANEB_HI_SHIFT		12
-#define   DSPFW_PLANEB_HI_MASK		(1<<12)
+#define   DSPFW_PLANEB_HI_MASK		(1 << 12)
 #define   DSPFW_SPRITEB_HI_SHIFT	8
-#define   DSPFW_SPRITEB_HI_MASK		(1<<8)
+#define   DSPFW_SPRITEB_HI_MASK		(1 << 8)
 #define   DSPFW_SPRITEA_HI_SHIFT	4
-#define   DSPFW_SPRITEA_HI_MASK		(1<<4)
+#define   DSPFW_SPRITEA_HI_MASK		(1 << 4)
 #define   DSPFW_PLANEA_HI_SHIFT		0
-#define   DSPFW_PLANEA_HI_MASK		(1<<0)
+#define   DSPFW_PLANEA_HI_MASK		(1 << 0)
 #define DSPHOWM1	_MMIO(VLV_DISPLAY_BASE + 0x70068)
 #define   DSPFW_SR_WM1_HI_SHIFT		24
-#define   DSPFW_SR_WM1_HI_MASK		(3<<24) /* 2 bits for chv, 1 for vlv */
+#define   DSPFW_SR_WM1_HI_MASK		(3 << 24) /* 2 bits for chv, 1 for vlv */
 #define   DSPFW_SPRITEF_WM1_HI_SHIFT	23
-#define   DSPFW_SPRITEF_WM1_HI_MASK	(1<<23)
+#define   DSPFW_SPRITEF_WM1_HI_MASK	(1 << 23)
 #define   DSPFW_SPRITEE_WM1_HI_SHIFT	22
-#define   DSPFW_SPRITEE_WM1_HI_MASK	(1<<22)
+#define   DSPFW_SPRITEE_WM1_HI_MASK	(1 << 22)
 #define   DSPFW_PLANEC_WM1_HI_SHIFT	21
-#define   DSPFW_PLANEC_WM1_HI_MASK	(1<<21)
+#define   DSPFW_PLANEC_WM1_HI_MASK	(1 << 21)
 #define   DSPFW_SPRITED_WM1_HI_SHIFT	20
-#define   DSPFW_SPRITED_WM1_HI_MASK	(1<<20)
+#define   DSPFW_SPRITED_WM1_HI_MASK	(1 << 20)
 #define   DSPFW_SPRITEC_WM1_HI_SHIFT	16
-#define   DSPFW_SPRITEC_WM1_HI_MASK	(1<<16)
+#define   DSPFW_SPRITEC_WM1_HI_MASK	(1 << 16)
 #define   DSPFW_PLANEB_WM1_HI_SHIFT	12
-#define   DSPFW_PLANEB_WM1_HI_MASK	(1<<12)
+#define   DSPFW_PLANEB_WM1_HI_MASK	(1 << 12)
 #define   DSPFW_SPRITEB_WM1_HI_SHIFT	8
-#define   DSPFW_SPRITEB_WM1_HI_MASK	(1<<8)
+#define   DSPFW_SPRITEB_WM1_HI_MASK	(1 << 8)
 #define   DSPFW_SPRITEA_WM1_HI_SHIFT	4
-#define   DSPFW_SPRITEA_WM1_HI_MASK	(1<<4)
+#define   DSPFW_SPRITEA_WM1_HI_MASK	(1 << 4)
 #define   DSPFW_PLANEA_WM1_HI_SHIFT	0
-#define   DSPFW_PLANEA_WM1_HI_MASK	(1<<0)
+#define   DSPFW_PLANEA_WM1_HI_MASK	(1 << 0)
 
 /* drain latency register values*/
 #define VLV_DDL(pipe)			_MMIO(VLV_DISPLAY_BASE + 0x70050 + 4 * (pipe))
 #define DDL_CURSOR_SHIFT		24
-#define DDL_SPRITE_SHIFT(sprite)	(8+8*(sprite))
+#define DDL_SPRITE_SHIFT(sprite)	(8 + 8 * (sprite))
 #define DDL_PLANE_SHIFT			0
-#define DDL_PRECISION_HIGH		(1<<7)
-#define DDL_PRECISION_LOW		(0<<7)
+#define DDL_PRECISION_HIGH		(1 << 7)
+#define DDL_PRECISION_LOW		(0 << 7)
 #define DRAIN_LATENCY_MASK		0x7f
 
 #define CBR1_VLV			_MMIO(VLV_DISPLAY_BASE + 0x70400)
-#define  CBR_PND_DEADLINE_DISABLE	(1<<31)
-#define  CBR_PWM_CLOCK_MUX_SELECT	(1<<30)
+#define  CBR_PND_DEADLINE_DISABLE	(1 << 31)
+#define  CBR_PWM_CLOCK_MUX_SELECT	(1 << 30)
 
 #define CBR4_VLV			_MMIO(VLV_DISPLAY_BASE + 0x70450)
-#define  CBR_DPLLBMD_PIPE(pipe)		(1<<(7+(pipe)*11)) /* pipes B and C */
+#define  CBR_DPLLBMD_PIPE(pipe)		(1 << (7 + (pipe) * 11)) /* pipes B and C */
 
 /* FIFO watermark sizes etc */
 #define G4X_FIFO_LINE_SIZE	64
@@ -5818,32 +5973,32 @@ enum {
 
 /* define the Watermark register on Ironlake */
 #define WM0_PIPEA_ILK		_MMIO(0x45100)
-#define  WM0_PIPE_PLANE_MASK	(0xffff<<16)
+#define  WM0_PIPE_PLANE_MASK	(0xffff << 16)
 #define  WM0_PIPE_PLANE_SHIFT	16
-#define  WM0_PIPE_SPRITE_MASK	(0xff<<8)
+#define  WM0_PIPE_SPRITE_MASK	(0xff << 8)
 #define  WM0_PIPE_SPRITE_SHIFT	8
 #define  WM0_PIPE_CURSOR_MASK	(0xff)
 
 #define WM0_PIPEB_ILK		_MMIO(0x45104)
 #define WM0_PIPEC_IVB		_MMIO(0x45200)
 #define WM1_LP_ILK		_MMIO(0x45108)
-#define  WM1_LP_SR_EN		(1<<31)
+#define  WM1_LP_SR_EN		(1 << 31)
 #define  WM1_LP_LATENCY_SHIFT	24
-#define  WM1_LP_LATENCY_MASK	(0x7f<<24)
-#define  WM1_LP_FBC_MASK	(0xf<<20)
+#define  WM1_LP_LATENCY_MASK	(0x7f << 24)
+#define  WM1_LP_FBC_MASK	(0xf << 20)
 #define  WM1_LP_FBC_SHIFT	20
 #define  WM1_LP_FBC_SHIFT_BDW	19
-#define  WM1_LP_SR_MASK		(0x7ff<<8)
+#define  WM1_LP_SR_MASK		(0x7ff << 8)
 #define  WM1_LP_SR_SHIFT	8
 #define  WM1_LP_CURSOR_MASK	(0xff)
 #define WM2_LP_ILK		_MMIO(0x4510c)
-#define  WM2_LP_EN		(1<<31)
+#define  WM2_LP_EN		(1 << 31)
 #define WM3_LP_ILK		_MMIO(0x45110)
-#define  WM3_LP_EN		(1<<31)
+#define  WM3_LP_EN		(1 << 31)
 #define WM1S_LP_ILK		_MMIO(0x45120)
 #define WM2S_LP_IVB		_MMIO(0x45124)
 #define WM3S_LP_IVB		_MMIO(0x45128)
-#define  WM1S_LP_EN		(1<<31)
+#define  WM1S_LP_EN		(1 << 31)
 
 #define HSW_WM_LP_VAL(lat, fbc, pri, cur) \
 	(WM3_LP_EN | ((lat) << WM1_LP_LATENCY_SHIFT) | \
@@ -5900,8 +6055,7 @@ enum {
 #define   CURSOR_ENABLE		0x80000000
 #define   CURSOR_GAMMA_ENABLE	0x40000000
 #define   CURSOR_STRIDE_SHIFT	28
-#define   CURSOR_STRIDE(x)	((ffs(x)-9) << CURSOR_STRIDE_SHIFT) /* 256,512,1k,2k */
-#define   CURSOR_PIPE_CSC_ENABLE (1<<24)
+#define   CURSOR_STRIDE(x)	((ffs(x) - 9) << CURSOR_STRIDE_SHIFT) /* 256,512,1k,2k */
 #define   CURSOR_FORMAT_SHIFT	24
 #define   CURSOR_FORMAT_MASK	(0x07 << CURSOR_FORMAT_SHIFT)
 #define   CURSOR_FORMAT_2C	(0x00 << CURSOR_FORMAT_SHIFT)
@@ -5910,18 +6064,21 @@ enum {
 #define   CURSOR_FORMAT_ARGB	(0x04 << CURSOR_FORMAT_SHIFT)
 #define   CURSOR_FORMAT_XRGB	(0x05 << CURSOR_FORMAT_SHIFT)
 /* New style CUR*CNTR flags */
-#define   CURSOR_MODE		0x27
-#define   CURSOR_MODE_DISABLE   0x00
-#define   CURSOR_MODE_128_32B_AX 0x02
-#define   CURSOR_MODE_256_32B_AX 0x03
-#define   CURSOR_MODE_64_32B_AX 0x07
-#define   CURSOR_MODE_128_ARGB_AX ((1 << 5) | CURSOR_MODE_128_32B_AX)
-#define   CURSOR_MODE_256_ARGB_AX ((1 << 5) | CURSOR_MODE_256_32B_AX)
-#define   CURSOR_MODE_64_ARGB_AX ((1 << 5) | CURSOR_MODE_64_32B_AX)
+#define   MCURSOR_MODE		0x27
+#define   MCURSOR_MODE_DISABLE   0x00
+#define   MCURSOR_MODE_128_32B_AX 0x02
+#define   MCURSOR_MODE_256_32B_AX 0x03
+#define   MCURSOR_MODE_64_32B_AX 0x07
+#define   MCURSOR_MODE_128_ARGB_AX ((1 << 5) | MCURSOR_MODE_128_32B_AX)
+#define   MCURSOR_MODE_256_ARGB_AX ((1 << 5) | MCURSOR_MODE_256_32B_AX)
+#define   MCURSOR_MODE_64_ARGB_AX ((1 << 5) | MCURSOR_MODE_64_32B_AX)
+#define   MCURSOR_PIPE_SELECT_MASK	(0x3 << 28)
+#define   MCURSOR_PIPE_SELECT_SHIFT	28
 #define   MCURSOR_PIPE_SELECT(pipe)	((pipe) << 28)
 #define   MCURSOR_GAMMA_ENABLE  (1 << 26)
-#define   CURSOR_ROTATE_180	(1<<15)
-#define   CURSOR_TRICKLE_FEED_DISABLE	(1 << 14)
+#define   MCURSOR_PIPE_CSC_ENABLE (1 << 24)
+#define   MCURSOR_ROTATE_180	(1 << 15)
+#define   MCURSOR_TRICKLE_FEED_DISABLE	(1 << 14)
 #define _CURABASE		0x70084
 #define _CURAPOS		0x70088
 #define   CURSOR_POS_MASK       0x007FF
@@ -5958,41 +6115,41 @@ enum {
 
 /* Display A control */
 #define _DSPACNTR				0x70180
-#define   DISPLAY_PLANE_ENABLE			(1<<31)
+#define   DISPLAY_PLANE_ENABLE			(1 << 31)
 #define   DISPLAY_PLANE_DISABLE			0
-#define   DISPPLANE_GAMMA_ENABLE		(1<<30)
+#define   DISPPLANE_GAMMA_ENABLE		(1 << 30)
 #define   DISPPLANE_GAMMA_DISABLE		0
-#define   DISPPLANE_PIXFORMAT_MASK		(0xf<<26)
-#define   DISPPLANE_YUV422			(0x0<<26)
-#define   DISPPLANE_8BPP			(0x2<<26)
-#define   DISPPLANE_BGRA555			(0x3<<26)
-#define   DISPPLANE_BGRX555			(0x4<<26)
-#define   DISPPLANE_BGRX565			(0x5<<26)
-#define   DISPPLANE_BGRX888			(0x6<<26)
-#define   DISPPLANE_BGRA888			(0x7<<26)
-#define   DISPPLANE_RGBX101010			(0x8<<26)
-#define   DISPPLANE_RGBA101010			(0x9<<26)
-#define   DISPPLANE_BGRX101010			(0xa<<26)
-#define   DISPPLANE_RGBX161616			(0xc<<26)
-#define   DISPPLANE_RGBX888			(0xe<<26)
-#define   DISPPLANE_RGBA888			(0xf<<26)
-#define   DISPPLANE_STEREO_ENABLE		(1<<25)
+#define   DISPPLANE_PIXFORMAT_MASK		(0xf << 26)
+#define   DISPPLANE_YUV422			(0x0 << 26)
+#define   DISPPLANE_8BPP			(0x2 << 26)
+#define   DISPPLANE_BGRA555			(0x3 << 26)
+#define   DISPPLANE_BGRX555			(0x4 << 26)
+#define   DISPPLANE_BGRX565			(0x5 << 26)
+#define   DISPPLANE_BGRX888			(0x6 << 26)
+#define   DISPPLANE_BGRA888			(0x7 << 26)
+#define   DISPPLANE_RGBX101010			(0x8 << 26)
+#define   DISPPLANE_RGBA101010			(0x9 << 26)
+#define   DISPPLANE_BGRX101010			(0xa << 26)
+#define   DISPPLANE_RGBX161616			(0xc << 26)
+#define   DISPPLANE_RGBX888			(0xe << 26)
+#define   DISPPLANE_RGBA888			(0xf << 26)
+#define   DISPPLANE_STEREO_ENABLE		(1 << 25)
 #define   DISPPLANE_STEREO_DISABLE		0
-#define   DISPPLANE_PIPE_CSC_ENABLE		(1<<24)
+#define   DISPPLANE_PIPE_CSC_ENABLE		(1 << 24)
 #define   DISPPLANE_SEL_PIPE_SHIFT		24
-#define   DISPPLANE_SEL_PIPE_MASK		(3<<DISPPLANE_SEL_PIPE_SHIFT)
-#define   DISPPLANE_SEL_PIPE(pipe)		((pipe)<<DISPPLANE_SEL_PIPE_SHIFT)
-#define   DISPPLANE_SRC_KEY_ENABLE		(1<<22)
+#define   DISPPLANE_SEL_PIPE_MASK		(3 << DISPPLANE_SEL_PIPE_SHIFT)
+#define   DISPPLANE_SEL_PIPE(pipe)		((pipe) << DISPPLANE_SEL_PIPE_SHIFT)
+#define   DISPPLANE_SRC_KEY_ENABLE		(1 << 22)
 #define   DISPPLANE_SRC_KEY_DISABLE		0
-#define   DISPPLANE_LINE_DOUBLE			(1<<20)
+#define   DISPPLANE_LINE_DOUBLE			(1 << 20)
 #define   DISPPLANE_NO_LINE_DOUBLE		0
 #define   DISPPLANE_STEREO_POLARITY_FIRST	0
-#define   DISPPLANE_STEREO_POLARITY_SECOND	(1<<18)
-#define   DISPPLANE_ALPHA_PREMULTIPLY		(1<<16) /* CHV pipe B */
-#define   DISPPLANE_ROTATE_180			(1<<15)
-#define   DISPPLANE_TRICKLE_FEED_DISABLE	(1<<14) /* Ironlake */
-#define   DISPPLANE_TILED			(1<<10)
-#define   DISPPLANE_MIRROR			(1<<8) /* CHV pipe B */
+#define   DISPPLANE_STEREO_POLARITY_SECOND	(1 << 18)
+#define   DISPPLANE_ALPHA_PREMULTIPLY		(1 << 16) /* CHV pipe B */
+#define   DISPPLANE_ROTATE_180			(1 << 15)
+#define   DISPPLANE_TRICKLE_FEED_DISABLE	(1 << 14) /* Ironlake */
+#define   DISPPLANE_TILED			(1 << 10)
+#define   DISPPLANE_MIRROR			(1 << 8) /* CHV pipe B */
 #define _DSPAADDR				0x70184
 #define _DSPASTRIDE				0x70188
 #define _DSPAPOS				0x7018C /* reserved */
@@ -6015,15 +6172,15 @@ enum {
 
 /* CHV pipe B blender and primary plane */
 #define _CHV_BLEND_A		0x60a00
-#define   CHV_BLEND_LEGACY		(0<<30)
-#define   CHV_BLEND_ANDROID		(1<<30)
-#define   CHV_BLEND_MPO			(2<<30)
-#define   CHV_BLEND_MASK		(3<<30)
+#define   CHV_BLEND_LEGACY		(0 << 30)
+#define   CHV_BLEND_ANDROID		(1 << 30)
+#define   CHV_BLEND_MPO			(2 << 30)
+#define   CHV_BLEND_MASK		(3 << 30)
 #define _CHV_CANVAS_A		0x60a04
 #define _PRIMPOS_A		0x60a08
 #define _PRIMSIZE_A		0x60a0c
 #define _PRIMCNSTALPHA_A	0x60a10
-#define   PRIM_CONST_ALPHA_ENABLE	(1<<31)
+#define   PRIM_CONST_ALPHA_ENABLE	(1 << 31)
 
 #define CHV_BLEND(pipe)		_MMIO_TRANS2(pipe, _CHV_BLEND_A)
 #define CHV_CANVAS(pipe)	_MMIO_TRANS2(pipe, _CHV_CANVAS_A)
@@ -6033,8 +6190,8 @@ enum {
 
 /* Display/Sprite base address macros */
 #define DISP_BASEADDR_MASK	(0xfffff000)
-#define I915_LO_DISPBASE(val)	(val & ~DISP_BASEADDR_MASK)
-#define I915_HI_DISPBASE(val)	(val & DISP_BASEADDR_MASK)
+#define I915_LO_DISPBASE(val)	((val) & ~DISP_BASEADDR_MASK)
+#define I915_HI_DISPBASE(val)	((val) & DISP_BASEADDR_MASK)
 
 /*
  * VBIOS flags
@@ -6064,7 +6221,7 @@ enum {
 
 /* Display B control */
 #define _DSPBCNTR		(dev_priv->info.display_mmio_offset + 0x71180)
-#define   DISPPLANE_ALPHA_TRANS_ENABLE		(1<<15)
+#define   DISPPLANE_ALPHA_TRANS_ENABLE		(1 << 15)
 #define   DISPPLANE_ALPHA_TRANS_DISABLE		0
 #define   DISPPLANE_SPRITE_ABOVE_DISPLAY	0
 #define   DISPPLANE_SPRITE_ABOVE_OVERLAY	(1)
@@ -6079,27 +6236,27 @@ enum {
 
 /* Sprite A control */
 #define _DVSACNTR		0x72180
-#define   DVS_ENABLE		(1<<31)
-#define   DVS_GAMMA_ENABLE	(1<<30)
-#define   DVS_YUV_RANGE_CORRECTION_DISABLE	(1<<27)
-#define   DVS_PIXFORMAT_MASK	(3<<25)
-#define   DVS_FORMAT_YUV422	(0<<25)
-#define   DVS_FORMAT_RGBX101010	(1<<25)
-#define   DVS_FORMAT_RGBX888	(2<<25)
-#define   DVS_FORMAT_RGBX161616	(3<<25)
-#define   DVS_PIPE_CSC_ENABLE   (1<<24)
-#define   DVS_SOURCE_KEY	(1<<22)
-#define   DVS_RGB_ORDER_XBGR	(1<<20)
-#define   DVS_YUV_FORMAT_BT709	(1<<18)
-#define   DVS_YUV_BYTE_ORDER_MASK (3<<16)
-#define   DVS_YUV_ORDER_YUYV	(0<<16)
-#define   DVS_YUV_ORDER_UYVY	(1<<16)
-#define   DVS_YUV_ORDER_YVYU	(2<<16)
-#define   DVS_YUV_ORDER_VYUY	(3<<16)
-#define   DVS_ROTATE_180	(1<<15)
-#define   DVS_DEST_KEY		(1<<2)
-#define   DVS_TRICKLE_FEED_DISABLE (1<<14)
-#define   DVS_TILED		(1<<10)
+#define   DVS_ENABLE		(1 << 31)
+#define   DVS_GAMMA_ENABLE	(1 << 30)
+#define   DVS_YUV_RANGE_CORRECTION_DISABLE	(1 << 27)
+#define   DVS_PIXFORMAT_MASK	(3 << 25)
+#define   DVS_FORMAT_YUV422	(0 << 25)
+#define   DVS_FORMAT_RGBX101010	(1 << 25)
+#define   DVS_FORMAT_RGBX888	(2 << 25)
+#define   DVS_FORMAT_RGBX161616	(3 << 25)
+#define   DVS_PIPE_CSC_ENABLE   (1 << 24)
+#define   DVS_SOURCE_KEY	(1 << 22)
+#define   DVS_RGB_ORDER_XBGR	(1 << 20)
+#define   DVS_YUV_FORMAT_BT709	(1 << 18)
+#define   DVS_YUV_BYTE_ORDER_MASK (3 << 16)
+#define   DVS_YUV_ORDER_YUYV	(0 << 16)
+#define   DVS_YUV_ORDER_UYVY	(1 << 16)
+#define   DVS_YUV_ORDER_YVYU	(2 << 16)
+#define   DVS_YUV_ORDER_VYUY	(3 << 16)
+#define   DVS_ROTATE_180	(1 << 15)
+#define   DVS_DEST_KEY		(1 << 2)
+#define   DVS_TRICKLE_FEED_DISABLE (1 << 14)
+#define   DVS_TILED		(1 << 10)
 #define _DVSALINOFF		0x72184
 #define _DVSASTRIDE		0x72188
 #define _DVSAPOS		0x7218c
@@ -6111,13 +6268,13 @@ enum {
 #define _DVSATILEOFF		0x721a4
 #define _DVSASURFLIVE		0x721ac
 #define _DVSASCALE		0x72204
-#define   DVS_SCALE_ENABLE	(1<<31)
-#define   DVS_FILTER_MASK	(3<<29)
-#define   DVS_FILTER_MEDIUM	(0<<29)
-#define   DVS_FILTER_ENHANCING	(1<<29)
-#define   DVS_FILTER_SOFTENING	(2<<29)
-#define   DVS_VERTICAL_OFFSET_HALF (1<<28) /* must be enabled below */
-#define   DVS_VERTICAL_OFFSET_ENABLE (1<<27)
+#define   DVS_SCALE_ENABLE	(1 << 31)
+#define   DVS_FILTER_MASK	(3 << 29)
+#define   DVS_FILTER_MEDIUM	(0 << 29)
+#define   DVS_FILTER_ENHANCING	(1 << 29)
+#define   DVS_FILTER_SOFTENING	(2 << 29)
+#define   DVS_VERTICAL_OFFSET_HALF (1 << 28) /* must be enabled below */
+#define   DVS_VERTICAL_OFFSET_ENABLE (1 << 27)
 #define _DVSAGAMC		0x72300
 
 #define _DVSBCNTR		0x73180
@@ -6148,31 +6305,31 @@ enum {
 #define DVSSURFLIVE(pipe) _MMIO_PIPE(pipe, _DVSASURFLIVE, _DVSBSURFLIVE)
 
 #define _SPRA_CTL		0x70280
-#define   SPRITE_ENABLE			(1<<31)
-#define   SPRITE_GAMMA_ENABLE		(1<<30)
-#define   SPRITE_YUV_RANGE_CORRECTION_DISABLE	(1<<28)
-#define   SPRITE_PIXFORMAT_MASK		(7<<25)
-#define   SPRITE_FORMAT_YUV422		(0<<25)
-#define   SPRITE_FORMAT_RGBX101010	(1<<25)
-#define   SPRITE_FORMAT_RGBX888		(2<<25)
-#define   SPRITE_FORMAT_RGBX161616	(3<<25)
-#define   SPRITE_FORMAT_YUV444		(4<<25)
-#define   SPRITE_FORMAT_XR_BGR101010	(5<<25) /* Extended range */
-#define   SPRITE_PIPE_CSC_ENABLE	(1<<24)
-#define   SPRITE_SOURCE_KEY		(1<<22)
-#define   SPRITE_RGB_ORDER_RGBX		(1<<20) /* only for 888 and 161616 */
-#define   SPRITE_YUV_TO_RGB_CSC_DISABLE	(1<<19)
-#define   SPRITE_YUV_TO_RGB_CSC_FORMAT_BT709	(1<<18) /* 0 is BT601 */
-#define   SPRITE_YUV_BYTE_ORDER_MASK	(3<<16)
-#define   SPRITE_YUV_ORDER_YUYV		(0<<16)
-#define   SPRITE_YUV_ORDER_UYVY		(1<<16)
-#define   SPRITE_YUV_ORDER_YVYU		(2<<16)
-#define   SPRITE_YUV_ORDER_VYUY		(3<<16)
-#define   SPRITE_ROTATE_180		(1<<15)
-#define   SPRITE_TRICKLE_FEED_DISABLE	(1<<14)
-#define   SPRITE_INT_GAMMA_ENABLE	(1<<13)
-#define   SPRITE_TILED			(1<<10)
-#define   SPRITE_DEST_KEY		(1<<2)
+#define   SPRITE_ENABLE			(1 << 31)
+#define   SPRITE_GAMMA_ENABLE		(1 << 30)
+#define   SPRITE_YUV_RANGE_CORRECTION_DISABLE	(1 << 28)
+#define   SPRITE_PIXFORMAT_MASK		(7 << 25)
+#define   SPRITE_FORMAT_YUV422		(0 << 25)
+#define   SPRITE_FORMAT_RGBX101010	(1 << 25)
+#define   SPRITE_FORMAT_RGBX888		(2 << 25)
+#define   SPRITE_FORMAT_RGBX161616	(3 << 25)
+#define   SPRITE_FORMAT_YUV444		(4 << 25)
+#define   SPRITE_FORMAT_XR_BGR101010	(5 << 25) /* Extended range */
+#define   SPRITE_PIPE_CSC_ENABLE	(1 << 24)
+#define   SPRITE_SOURCE_KEY		(1 << 22)
+#define   SPRITE_RGB_ORDER_RGBX		(1 << 20) /* only for 888 and 161616 */
+#define   SPRITE_YUV_TO_RGB_CSC_DISABLE	(1 << 19)
+#define   SPRITE_YUV_TO_RGB_CSC_FORMAT_BT709	(1 << 18) /* 0 is BT601 */
+#define   SPRITE_YUV_BYTE_ORDER_MASK	(3 << 16)
+#define   SPRITE_YUV_ORDER_YUYV		(0 << 16)
+#define   SPRITE_YUV_ORDER_UYVY		(1 << 16)
+#define   SPRITE_YUV_ORDER_YVYU		(2 << 16)
+#define   SPRITE_YUV_ORDER_VYUY		(3 << 16)
+#define   SPRITE_ROTATE_180		(1 << 15)
+#define   SPRITE_TRICKLE_FEED_DISABLE	(1 << 14)
+#define   SPRITE_INT_GAMMA_ENABLE	(1 << 13)
+#define   SPRITE_TILED			(1 << 10)
+#define   SPRITE_DEST_KEY		(1 << 2)
 #define _SPRA_LINOFF		0x70284
 #define _SPRA_STRIDE		0x70288
 #define _SPRA_POS		0x7028c
@@ -6185,13 +6342,13 @@ enum {
 #define _SPRA_OFFSET		0x702a4
 #define _SPRA_SURFLIVE		0x702ac
 #define _SPRA_SCALE		0x70304
-#define   SPRITE_SCALE_ENABLE	(1<<31)
-#define   SPRITE_FILTER_MASK	(3<<29)
-#define   SPRITE_FILTER_MEDIUM	(0<<29)
-#define   SPRITE_FILTER_ENHANCING	(1<<29)
-#define   SPRITE_FILTER_SOFTENING	(2<<29)
-#define   SPRITE_VERTICAL_OFFSET_HALF	(1<<28) /* must be enabled below */
-#define   SPRITE_VERTICAL_OFFSET_ENABLE	(1<<27)
+#define   SPRITE_SCALE_ENABLE	(1 << 31)
+#define   SPRITE_FILTER_MASK	(3 << 29)
+#define   SPRITE_FILTER_MEDIUM	(0 << 29)
+#define   SPRITE_FILTER_ENHANCING	(1 << 29)
+#define   SPRITE_FILTER_SOFTENING	(2 << 29)
+#define   SPRITE_VERTICAL_OFFSET_HALF	(1 << 28) /* must be enabled below */
+#define   SPRITE_VERTICAL_OFFSET_ENABLE	(1 << 27)
 #define _SPRA_GAMC		0x70400
 
 #define _SPRB_CTL		0x71280
@@ -6225,28 +6382,28 @@ enum {
 #define SPRSURFLIVE(pipe) _MMIO_PIPE(pipe, _SPRA_SURFLIVE, _SPRB_SURFLIVE)
 
 #define _SPACNTR		(VLV_DISPLAY_BASE + 0x72180)
-#define   SP_ENABLE			(1<<31)
-#define   SP_GAMMA_ENABLE		(1<<30)
-#define   SP_PIXFORMAT_MASK		(0xf<<26)
-#define   SP_FORMAT_YUV422		(0<<26)
-#define   SP_FORMAT_BGR565		(5<<26)
-#define   SP_FORMAT_BGRX8888		(6<<26)
-#define   SP_FORMAT_BGRA8888		(7<<26)
-#define   SP_FORMAT_RGBX1010102		(8<<26)
-#define   SP_FORMAT_RGBA1010102		(9<<26)
-#define   SP_FORMAT_RGBX8888		(0xe<<26)
-#define   SP_FORMAT_RGBA8888		(0xf<<26)
-#define   SP_ALPHA_PREMULTIPLY		(1<<23) /* CHV pipe B */
-#define   SP_SOURCE_KEY			(1<<22)
-#define   SP_YUV_FORMAT_BT709		(1<<18)
-#define   SP_YUV_BYTE_ORDER_MASK	(3<<16)
-#define   SP_YUV_ORDER_YUYV		(0<<16)
-#define   SP_YUV_ORDER_UYVY		(1<<16)
-#define   SP_YUV_ORDER_YVYU		(2<<16)
-#define   SP_YUV_ORDER_VYUY		(3<<16)
-#define   SP_ROTATE_180			(1<<15)
-#define   SP_TILED			(1<<10)
-#define   SP_MIRROR			(1<<8) /* CHV pipe B */
+#define   SP_ENABLE			(1 << 31)
+#define   SP_GAMMA_ENABLE		(1 << 30)
+#define   SP_PIXFORMAT_MASK		(0xf << 26)
+#define   SP_FORMAT_YUV422		(0 << 26)
+#define   SP_FORMAT_BGR565		(5 << 26)
+#define   SP_FORMAT_BGRX8888		(6 << 26)
+#define   SP_FORMAT_BGRA8888		(7 << 26)
+#define   SP_FORMAT_RGBX1010102		(8 << 26)
+#define   SP_FORMAT_RGBA1010102		(9 << 26)
+#define   SP_FORMAT_RGBX8888		(0xe << 26)
+#define   SP_FORMAT_RGBA8888		(0xf << 26)
+#define   SP_ALPHA_PREMULTIPLY		(1 << 23) /* CHV pipe B */
+#define   SP_SOURCE_KEY			(1 << 22)
+#define   SP_YUV_FORMAT_BT709		(1 << 18)
+#define   SP_YUV_BYTE_ORDER_MASK	(3 << 16)
+#define   SP_YUV_ORDER_YUYV		(0 << 16)
+#define   SP_YUV_ORDER_UYVY		(1 << 16)
+#define   SP_YUV_ORDER_YVYU		(2 << 16)
+#define   SP_YUV_ORDER_VYUY		(3 << 16)
+#define   SP_ROTATE_180			(1 << 15)
+#define   SP_TILED			(1 << 10)
+#define   SP_MIRROR			(1 << 8) /* CHV pipe B */
 #define _SPALINOFF		(VLV_DISPLAY_BASE + 0x72184)
 #define _SPASTRIDE		(VLV_DISPLAY_BASE + 0x72188)
 #define _SPAPOS			(VLV_DISPLAY_BASE + 0x7218c)
@@ -6257,7 +6414,7 @@ enum {
 #define _SPAKEYMAXVAL		(VLV_DISPLAY_BASE + 0x721a0)
 #define _SPATILEOFF		(VLV_DISPLAY_BASE + 0x721a4)
 #define _SPACONSTALPHA		(VLV_DISPLAY_BASE + 0x721a8)
-#define   SP_CONST_ALPHA_ENABLE		(1<<31)
+#define   SP_CONST_ALPHA_ENABLE		(1 << 31)
 #define _SPACLRC0		(VLV_DISPLAY_BASE + 0x721d0)
 #define   SP_CONTRAST(x)		((x) << 18) /* u3.6 */
 #define   SP_BRIGHTNESS(x)		((x) & 0xff) /* s8 */
@@ -6349,40 +6506,40 @@ enum {
  * correctly map to the same formats in ICL, as long as bit 23 is set to 0
  */
 #define   PLANE_CTL_FORMAT_MASK			(0xf << 24)
-#define   PLANE_CTL_FORMAT_YUV422		(  0 << 24)
-#define   PLANE_CTL_FORMAT_NV12			(  1 << 24)
-#define   PLANE_CTL_FORMAT_XRGB_2101010		(  2 << 24)
-#define   PLANE_CTL_FORMAT_XRGB_8888		(  4 << 24)
-#define   PLANE_CTL_FORMAT_XRGB_16161616F	(  6 << 24)
-#define   PLANE_CTL_FORMAT_AYUV			(  8 << 24)
-#define   PLANE_CTL_FORMAT_INDEXED		( 12 << 24)
-#define   PLANE_CTL_FORMAT_RGB_565		( 14 << 24)
+#define   PLANE_CTL_FORMAT_YUV422		(0 << 24)
+#define   PLANE_CTL_FORMAT_NV12			(1 << 24)
+#define   PLANE_CTL_FORMAT_XRGB_2101010		(2 << 24)
+#define   PLANE_CTL_FORMAT_XRGB_8888		(4 << 24)
+#define   PLANE_CTL_FORMAT_XRGB_16161616F	(6 << 24)
+#define   PLANE_CTL_FORMAT_AYUV			(8 << 24)
+#define   PLANE_CTL_FORMAT_INDEXED		(12 << 24)
+#define   PLANE_CTL_FORMAT_RGB_565		(14 << 24)
 #define   ICL_PLANE_CTL_FORMAT_MASK		(0x1f << 23)
 #define   PLANE_CTL_PIPE_CSC_ENABLE		(1 << 23) /* Pre-GLK */
 #define   PLANE_CTL_KEY_ENABLE_MASK		(0x3 << 21)
-#define   PLANE_CTL_KEY_ENABLE_SOURCE		(  1 << 21)
-#define   PLANE_CTL_KEY_ENABLE_DESTINATION	(  2 << 21)
+#define   PLANE_CTL_KEY_ENABLE_SOURCE		(1 << 21)
+#define   PLANE_CTL_KEY_ENABLE_DESTINATION	(2 << 21)
 #define   PLANE_CTL_ORDER_BGRX			(0 << 20)
 #define   PLANE_CTL_ORDER_RGBX			(1 << 20)
 #define   PLANE_CTL_YUV_TO_RGB_CSC_FORMAT_BT709	(1 << 18)
 #define   PLANE_CTL_YUV422_ORDER_MASK		(0x3 << 16)
-#define   PLANE_CTL_YUV422_YUYV			(  0 << 16)
-#define   PLANE_CTL_YUV422_UYVY			(  1 << 16)
-#define   PLANE_CTL_YUV422_YVYU			(  2 << 16)
-#define   PLANE_CTL_YUV422_VYUY			(  3 << 16)
+#define   PLANE_CTL_YUV422_YUYV			(0 << 16)
+#define   PLANE_CTL_YUV422_UYVY			(1 << 16)
+#define   PLANE_CTL_YUV422_YVYU			(2 << 16)
+#define   PLANE_CTL_YUV422_VYUY			(3 << 16)
 #define   PLANE_CTL_DECOMPRESSION_ENABLE	(1 << 15)
 #define   PLANE_CTL_TRICKLE_FEED_DISABLE	(1 << 14)
 #define   PLANE_CTL_PLANE_GAMMA_DISABLE		(1 << 13) /* Pre-GLK */
 #define   PLANE_CTL_TILED_MASK			(0x7 << 10)
-#define   PLANE_CTL_TILED_LINEAR		(  0 << 10)
-#define   PLANE_CTL_TILED_X			(  1 << 10)
-#define   PLANE_CTL_TILED_Y			(  4 << 10)
-#define   PLANE_CTL_TILED_YF			(  5 << 10)
-#define   PLANE_CTL_FLIP_HORIZONTAL		(  1 << 8)
+#define   PLANE_CTL_TILED_LINEAR		(0 << 10)
+#define   PLANE_CTL_TILED_X			(1 << 10)
+#define   PLANE_CTL_TILED_Y			(4 << 10)
+#define   PLANE_CTL_TILED_YF			(5 << 10)
+#define   PLANE_CTL_FLIP_HORIZONTAL		(1 << 8)
 #define   PLANE_CTL_ALPHA_MASK			(0x3 << 4) /* Pre-GLK */
-#define   PLANE_CTL_ALPHA_DISABLE		(  0 << 4)
-#define   PLANE_CTL_ALPHA_SW_PREMULTIPLY	(  2 << 4)
-#define   PLANE_CTL_ALPHA_HW_PREMULTIPLY	(  3 << 4)
+#define   PLANE_CTL_ALPHA_DISABLE		(0 << 4)
+#define   PLANE_CTL_ALPHA_SW_PREMULTIPLY	(2 << 4)
+#define   PLANE_CTL_ALPHA_HW_PREMULTIPLY	(3 << 4)
 #define   PLANE_CTL_ROTATE_MASK			0x3
 #define   PLANE_CTL_ROTATE_0			0x0
 #define   PLANE_CTL_ROTATE_90			0x1
@@ -6610,7 +6767,7 @@ enum {
 # define VFMUNIT_CLOCK_GATE_DISABLE		(1 << 11)
 
 #define FDI_PLL_FREQ_CTL        _MMIO(0x46030)
-#define  FDI_PLL_FREQ_CHANGE_REQUEST    (1<<24)
+#define  FDI_PLL_FREQ_CHANGE_REQUEST    (1 << 24)
 #define  FDI_PLL_FREQ_LOCK_LIMIT_MASK   0xfff00
 #define  FDI_PLL_FREQ_DISABLE_COUNT_LIMIT_MASK  0xff
 
@@ -6659,14 +6816,14 @@ enum {
 /* IVB+ has 3 fitters, 0 is 7x5 capable, the other two only 3x3 */
 #define _PFA_CTL_1               0x68080
 #define _PFB_CTL_1               0x68880
-#define  PF_ENABLE              (1<<31)
-#define  PF_PIPE_SEL_MASK_IVB	(3<<29)
-#define  PF_PIPE_SEL_IVB(pipe)	((pipe)<<29)
-#define  PF_FILTER_MASK		(3<<23)
-#define  PF_FILTER_PROGRAMMED	(0<<23)
-#define  PF_FILTER_MED_3x3	(1<<23)
-#define  PF_FILTER_EDGE_ENHANCE	(2<<23)
-#define  PF_FILTER_EDGE_SOFTEN	(3<<23)
+#define  PF_ENABLE              (1 << 31)
+#define  PF_PIPE_SEL_MASK_IVB	(3 << 29)
+#define  PF_PIPE_SEL_IVB(pipe)	((pipe) << 29)
+#define  PF_FILTER_MASK		(3 << 23)
+#define  PF_FILTER_PROGRAMMED	(0 << 23)
+#define  PF_FILTER_MED_3x3	(1 << 23)
+#define  PF_FILTER_EDGE_ENHANCE	(2 << 23)
+#define  PF_FILTER_EDGE_SOFTEN	(3 << 23)
 #define _PFA_WIN_SZ		0x68074
 #define _PFB_WIN_SZ		0x68874
 #define _PFA_WIN_POS		0x68070
@@ -6684,7 +6841,7 @@ enum {
 
 #define _PSA_CTL		0x68180
 #define _PSB_CTL		0x68980
-#define PS_ENABLE		(1<<31)
+#define PS_ENABLE		(1 << 31)
 #define _PSA_WIN_SZ		0x68174
 #define _PSB_WIN_SZ		0x68974
 #define _PSA_WIN_POS		0x68170
@@ -6769,6 +6926,10 @@ enum {
 #define _PS_VPHASE_1B       0x68988
 #define _PS_VPHASE_2B       0x68A88
 #define _PS_VPHASE_1C       0x69188
+#define  PS_Y_PHASE(x)		((x) << 16)
+#define  PS_UV_RGB_PHASE(x)	((x) << 0)
+#define   PS_PHASE_MASK	(0x7fff << 1) /* u2.13 */
+#define   PS_PHASE_TRIP	(1 << 0)
 
 #define _PS_HPHASE_1A       0x68194
 #define _PS_HPHASE_2A       0x68294
@@ -6782,7 +6943,7 @@ enum {
 #define _PS_ECC_STAT_2B     0x68AD0
 #define _PS_ECC_STAT_1C     0x691D0
 
-#define _ID(id, a, b) ((a) + (id)*((b)-(a)))
+#define _ID(id, a, b) _PICK_EVEN(id, a, b)
 #define SKL_PS_CTRL(pipe, id) _MMIO_PIPE(pipe,        \
 			_ID(id, _PS_1A_CTRL, _PS_2A_CTRL),       \
 			_ID(id, _PS_1B_CTRL, _PS_2B_CTRL))
@@ -6863,37 +7024,37 @@ enum {
 #define DE_PIPEB_CRC_DONE	(1 << 10)
 #define DE_PIPEB_FIFO_UNDERRUN  (1 << 8)
 #define DE_PIPEA_VBLANK         (1 << 7)
-#define DE_PIPE_VBLANK(pipe)    (1 << (7 + 8*(pipe)))
+#define DE_PIPE_VBLANK(pipe)    (1 << (7 + 8 * (pipe)))
 #define DE_PIPEA_EVEN_FIELD     (1 << 6)
 #define DE_PIPEA_ODD_FIELD      (1 << 5)
 #define DE_PIPEA_LINE_COMPARE   (1 << 4)
 #define DE_PIPEA_VSYNC          (1 << 3)
 #define DE_PIPEA_CRC_DONE	(1 << 2)
-#define DE_PIPE_CRC_DONE(pipe)	(1 << (2 + 8*(pipe)))
+#define DE_PIPE_CRC_DONE(pipe)	(1 << (2 + 8 * (pipe)))
 #define DE_PIPEA_FIFO_UNDERRUN  (1 << 0)
-#define DE_PIPE_FIFO_UNDERRUN(pipe)  (1 << (8*(pipe)))
+#define DE_PIPE_FIFO_UNDERRUN(pipe)  (1 << (8 * (pipe)))
 
 /* More Ivybridge lolz */
-#define DE_ERR_INT_IVB			(1<<30)
-#define DE_GSE_IVB			(1<<29)
-#define DE_PCH_EVENT_IVB		(1<<28)
-#define DE_DP_A_HOTPLUG_IVB		(1<<27)
-#define DE_AUX_CHANNEL_A_IVB		(1<<26)
-#define DE_EDP_PSR_INT_HSW		(1<<19)
-#define DE_SPRITEC_FLIP_DONE_IVB	(1<<14)
-#define DE_PLANEC_FLIP_DONE_IVB		(1<<13)
-#define DE_PIPEC_VBLANK_IVB		(1<<10)
-#define DE_SPRITEB_FLIP_DONE_IVB	(1<<9)
-#define DE_PLANEB_FLIP_DONE_IVB		(1<<8)
-#define DE_PIPEB_VBLANK_IVB		(1<<5)
-#define DE_SPRITEA_FLIP_DONE_IVB	(1<<4)
-#define DE_PLANEA_FLIP_DONE_IVB		(1<<3)
-#define DE_PLANE_FLIP_DONE_IVB(plane)	(1<< (3 + 5*(plane)))
-#define DE_PIPEA_VBLANK_IVB		(1<<0)
+#define DE_ERR_INT_IVB			(1 << 30)
+#define DE_GSE_IVB			(1 << 29)
+#define DE_PCH_EVENT_IVB		(1 << 28)
+#define DE_DP_A_HOTPLUG_IVB		(1 << 27)
+#define DE_AUX_CHANNEL_A_IVB		(1 << 26)
+#define DE_EDP_PSR_INT_HSW		(1 << 19)
+#define DE_SPRITEC_FLIP_DONE_IVB	(1 << 14)
+#define DE_PLANEC_FLIP_DONE_IVB		(1 << 13)
+#define DE_PIPEC_VBLANK_IVB		(1 << 10)
+#define DE_SPRITEB_FLIP_DONE_IVB	(1 << 9)
+#define DE_PLANEB_FLIP_DONE_IVB		(1 << 8)
+#define DE_PIPEB_VBLANK_IVB		(1 << 5)
+#define DE_SPRITEA_FLIP_DONE_IVB	(1 << 4)
+#define DE_PLANEA_FLIP_DONE_IVB		(1 << 3)
+#define DE_PLANE_FLIP_DONE_IVB(plane)	(1 << (3 + 5 * (plane)))
+#define DE_PIPEA_VBLANK_IVB		(1 << 0)
 #define DE_PIPE_VBLANK_IVB(pipe)	(1 << ((pipe) * 5))
 
 #define VLV_MASTER_IER			_MMIO(0x4400c) /* Gunit master IER */
-#define   MASTER_INTERRUPT_ENABLE	(1<<31)
+#define   MASTER_INTERRUPT_ENABLE	(1 << 31)
 
 #define DEISR   _MMIO(0x44000)
 #define DEIMR   _MMIO(0x44004)
@@ -6906,37 +7067,37 @@ enum {
 #define GTIER   _MMIO(0x4401c)
 
 #define GEN8_MASTER_IRQ			_MMIO(0x44200)
-#define  GEN8_MASTER_IRQ_CONTROL	(1<<31)
-#define  GEN8_PCU_IRQ			(1<<30)
-#define  GEN8_DE_PCH_IRQ		(1<<23)
-#define  GEN8_DE_MISC_IRQ		(1<<22)
-#define  GEN8_DE_PORT_IRQ		(1<<20)
-#define  GEN8_DE_PIPE_C_IRQ		(1<<18)
-#define  GEN8_DE_PIPE_B_IRQ		(1<<17)
-#define  GEN8_DE_PIPE_A_IRQ		(1<<16)
-#define  GEN8_DE_PIPE_IRQ(pipe)		(1<<(16+(pipe)))
-#define  GEN8_GT_VECS_IRQ		(1<<6)
-#define  GEN8_GT_GUC_IRQ		(1<<5)
-#define  GEN8_GT_PM_IRQ			(1<<4)
-#define  GEN8_GT_VCS2_IRQ		(1<<3)
-#define  GEN8_GT_VCS1_IRQ		(1<<2)
-#define  GEN8_GT_BCS_IRQ		(1<<1)
-#define  GEN8_GT_RCS_IRQ		(1<<0)
+#define  GEN8_MASTER_IRQ_CONTROL	(1 << 31)
+#define  GEN8_PCU_IRQ			(1 << 30)
+#define  GEN8_DE_PCH_IRQ		(1 << 23)
+#define  GEN8_DE_MISC_IRQ		(1 << 22)
+#define  GEN8_DE_PORT_IRQ		(1 << 20)
+#define  GEN8_DE_PIPE_C_IRQ		(1 << 18)
+#define  GEN8_DE_PIPE_B_IRQ		(1 << 17)
+#define  GEN8_DE_PIPE_A_IRQ		(1 << 16)
+#define  GEN8_DE_PIPE_IRQ(pipe)		(1 << (16 + (pipe)))
+#define  GEN8_GT_VECS_IRQ		(1 << 6)
+#define  GEN8_GT_GUC_IRQ		(1 << 5)
+#define  GEN8_GT_PM_IRQ			(1 << 4)
+#define  GEN8_GT_VCS2_IRQ		(1 << 3)
+#define  GEN8_GT_VCS1_IRQ		(1 << 2)
+#define  GEN8_GT_BCS_IRQ		(1 << 1)
+#define  GEN8_GT_RCS_IRQ		(1 << 0)
 
 #define GEN8_GT_ISR(which) _MMIO(0x44300 + (0x10 * (which)))
 #define GEN8_GT_IMR(which) _MMIO(0x44304 + (0x10 * (which)))
 #define GEN8_GT_IIR(which) _MMIO(0x44308 + (0x10 * (which)))
 #define GEN8_GT_IER(which) _MMIO(0x4430c + (0x10 * (which)))
 
-#define GEN9_GUC_TO_HOST_INT_EVENT	(1<<31)
-#define GEN9_GUC_EXEC_ERROR_EVENT	(1<<30)
-#define GEN9_GUC_DISPLAY_EVENT		(1<<29)
-#define GEN9_GUC_SEMA_SIGNAL_EVENT	(1<<28)
-#define GEN9_GUC_IOMMU_MSG_EVENT	(1<<27)
-#define GEN9_GUC_DB_RING_EVENT		(1<<26)
-#define GEN9_GUC_DMA_DONE_EVENT		(1<<25)
-#define GEN9_GUC_FATAL_ERROR_EVENT	(1<<24)
-#define GEN9_GUC_NOTIFICATION_EVENT	(1<<23)
+#define GEN9_GUC_TO_HOST_INT_EVENT	(1 << 31)
+#define GEN9_GUC_EXEC_ERROR_EVENT	(1 << 30)
+#define GEN9_GUC_DISPLAY_EVENT		(1 << 29)
+#define GEN9_GUC_SEMA_SIGNAL_EVENT	(1 << 28)
+#define GEN9_GUC_IOMMU_MSG_EVENT	(1 << 27)
+#define GEN9_GUC_DB_RING_EVENT		(1 << 26)
+#define GEN9_GUC_DMA_DONE_EVENT		(1 << 25)
+#define GEN9_GUC_FATAL_ERROR_EVENT	(1 << 24)
+#define GEN9_GUC_NOTIFICATION_EVENT	(1 << 23)
 
 #define GEN8_RCS_IRQ_SHIFT 0
 #define GEN8_BCS_IRQ_SHIFT 16
@@ -6985,6 +7146,7 @@ enum {
 #define GEN8_DE_PORT_IMR _MMIO(0x44444)
 #define GEN8_DE_PORT_IIR _MMIO(0x44448)
 #define GEN8_DE_PORT_IER _MMIO(0x4444c)
+#define  ICL_AUX_CHANNEL_E		(1 << 29)
 #define  CNL_AUX_CHANNEL_F		(1 << 28)
 #define  GEN9_AUX_CHANNEL_D		(1 << 27)
 #define  GEN9_AUX_CHANNEL_C		(1 << 26)
@@ -7011,9 +7173,16 @@ enum {
 #define GEN8_PCU_IIR _MMIO(0x444e8)
 #define GEN8_PCU_IER _MMIO(0x444ec)
 
+#define GEN11_GU_MISC_ISR	_MMIO(0x444f0)
+#define GEN11_GU_MISC_IMR	_MMIO(0x444f4)
+#define GEN11_GU_MISC_IIR	_MMIO(0x444f8)
+#define GEN11_GU_MISC_IER	_MMIO(0x444fc)
+#define  GEN11_GU_MISC_GSE	(1 << 27)
+
 #define GEN11_GFX_MSTR_IRQ		_MMIO(0x190010)
 #define  GEN11_MASTER_IRQ		(1 << 31)
 #define  GEN11_PCU_IRQ			(1 << 30)
+#define  GEN11_GU_MISC_IRQ		(1 << 29)
 #define  GEN11_DISPLAY_IRQ		(1 << 16)
 #define  GEN11_GT_DW_IRQ(x)		(1 << (x))
 #define  GEN11_GT_DW1_IRQ		(1 << 1)
@@ -7024,11 +7193,40 @@ enum {
 #define  GEN11_AUDIO_CODEC_IRQ		(1 << 24)
 #define  GEN11_DE_PCH_IRQ		(1 << 23)
 #define  GEN11_DE_MISC_IRQ		(1 << 22)
+#define  GEN11_DE_HPD_IRQ		(1 << 21)
 #define  GEN11_DE_PORT_IRQ		(1 << 20)
 #define  GEN11_DE_PIPE_C		(1 << 18)
 #define  GEN11_DE_PIPE_B		(1 << 17)
 #define  GEN11_DE_PIPE_A		(1 << 16)
 
+#define GEN11_DE_HPD_ISR		_MMIO(0x44470)
+#define GEN11_DE_HPD_IMR		_MMIO(0x44474)
+#define GEN11_DE_HPD_IIR		_MMIO(0x44478)
+#define GEN11_DE_HPD_IER		_MMIO(0x4447c)
+#define  GEN11_TC4_HOTPLUG			(1 << 19)
+#define  GEN11_TC3_HOTPLUG			(1 << 18)
+#define  GEN11_TC2_HOTPLUG			(1 << 17)
+#define  GEN11_TC1_HOTPLUG			(1 << 16)
+#define  GEN11_DE_TC_HOTPLUG_MASK		(GEN11_TC4_HOTPLUG | \
+						 GEN11_TC3_HOTPLUG | \
+						 GEN11_TC2_HOTPLUG | \
+						 GEN11_TC1_HOTPLUG)
+#define  GEN11_TBT4_HOTPLUG			(1 << 3)
+#define  GEN11_TBT3_HOTPLUG			(1 << 2)
+#define  GEN11_TBT2_HOTPLUG			(1 << 1)
+#define  GEN11_TBT1_HOTPLUG			(1 << 0)
+#define  GEN11_DE_TBT_HOTPLUG_MASK		(GEN11_TBT4_HOTPLUG | \
+						 GEN11_TBT3_HOTPLUG | \
+						 GEN11_TBT2_HOTPLUG | \
+						 GEN11_TBT1_HOTPLUG)
+
+#define GEN11_TBT_HOTPLUG_CTL				_MMIO(0x44030)
+#define GEN11_TC_HOTPLUG_CTL				_MMIO(0x44038)
+#define  GEN11_HOTPLUG_CTL_ENABLE(tc_port)		(8 << (tc_port) * 4)
+#define  GEN11_HOTPLUG_CTL_LONG_DETECT(tc_port)		(2 << (tc_port) * 4)
+#define  GEN11_HOTPLUG_CTL_SHORT_DETECT(tc_port)	(1 << (tc_port) * 4)
+#define  GEN11_HOTPLUG_CTL_NO_DETECT(tc_port)		(0 << (tc_port) * 4)
+
 #define GEN11_GT_INTR_DW0		_MMIO(0x190018)
 #define  GEN11_CSME			(31)
 #define  GEN11_GUNIT			(28)
@@ -7043,7 +7241,7 @@ enum {
 #define  GEN11_VECS(x)			(31 - (x))
 #define  GEN11_VCS(x)			(x)
 
-#define GEN11_GT_INTR_DW(x)		_MMIO(0x190018 + (x * 4))
+#define GEN11_GT_INTR_DW(x)		_MMIO(0x190018 + ((x) * 4))
 
 #define GEN11_INTR_IDENTITY_REG0	_MMIO(0x190060)
 #define GEN11_INTR_IDENTITY_REG1	_MMIO(0x190064)
@@ -7052,12 +7250,12 @@ enum {
 #define  GEN11_INTR_ENGINE_INSTANCE(x)	(((x) & GENMASK(25, 20)) >> 20)
 #define  GEN11_INTR_ENGINE_INTR(x)	((x) & 0xffff)
 
-#define GEN11_INTR_IDENTITY_REG(x)	_MMIO(0x190060 + (x * 4))
+#define GEN11_INTR_IDENTITY_REG(x)	_MMIO(0x190060 + ((x) * 4))
 
 #define GEN11_IIR_REG0_SELECTOR		_MMIO(0x190070)
 #define GEN11_IIR_REG1_SELECTOR		_MMIO(0x190074)
 
-#define GEN11_IIR_REG_SELECTOR(x)	_MMIO(0x190070 + (x * 4))
+#define GEN11_IIR_REG_SELECTOR(x)	_MMIO(0x190070 + ((x) * 4))
 
 #define GEN11_RENDER_COPY_INTR_ENABLE	_MMIO(0x190030)
 #define GEN11_VCS_VECS_INTR_ENABLE	_MMIO(0x190034)
@@ -7079,8 +7277,8 @@ enum {
 #define ILK_DISPLAY_CHICKEN2	_MMIO(0x42004)
 /* Required on all Ironlake and Sandybridge according to the B-Spec. */
 #define  ILK_ELPIN_409_SELECT	(1 << 25)
-#define  ILK_DPARB_GATE	(1<<22)
-#define  ILK_VSDPFD_FULL	(1<<21)
+#define  ILK_DPARB_GATE	(1 << 22)
+#define  ILK_VSDPFD_FULL	(1 << 21)
 #define FUSE_STRAP			_MMIO(0x42014)
 #define  ILK_INTERNAL_GRAPHICS_DISABLE	(1 << 31)
 #define  ILK_INTERNAL_DISPLAY_DISABLE	(1 << 30)
@@ -7130,31 +7328,31 @@ enum {
 #define CHICKEN_TRANS_A         0x420c0
 #define CHICKEN_TRANS_B         0x420c4
 #define CHICKEN_TRANS(trans) _MMIO_TRANS(trans, CHICKEN_TRANS_A, CHICKEN_TRANS_B)
-#define  VSC_DATA_SEL_SOFTWARE_CONTROL	(1<<25) /* GLK and CNL+ */
-#define  DDI_TRAINING_OVERRIDE_ENABLE	(1<<19)
-#define  DDI_TRAINING_OVERRIDE_VALUE	(1<<18)
-#define  DDIE_TRAINING_OVERRIDE_ENABLE	(1<<17) /* CHICKEN_TRANS_A only */
-#define  DDIE_TRAINING_OVERRIDE_VALUE	(1<<16) /* CHICKEN_TRANS_A only */
-#define  PSR2_ADD_VERTICAL_LINE_COUNT   (1<<15)
-#define  PSR2_VSC_ENABLE_PROG_HEADER    (1<<12)
+#define  VSC_DATA_SEL_SOFTWARE_CONTROL	(1 << 25) /* GLK and CNL+ */
+#define  DDI_TRAINING_OVERRIDE_ENABLE	(1 << 19)
+#define  DDI_TRAINING_OVERRIDE_VALUE	(1 << 18)
+#define  DDIE_TRAINING_OVERRIDE_ENABLE	(1 << 17) /* CHICKEN_TRANS_A only */
+#define  DDIE_TRAINING_OVERRIDE_VALUE	(1 << 16) /* CHICKEN_TRANS_A only */
+#define  PSR2_ADD_VERTICAL_LINE_COUNT   (1 << 15)
+#define  PSR2_VSC_ENABLE_PROG_HEADER    (1 << 12)
 
 #define DISP_ARB_CTL	_MMIO(0x45000)
-#define  DISP_FBC_MEMORY_WAKE		(1<<31)
-#define  DISP_TILE_SURFACE_SWIZZLING	(1<<13)
-#define  DISP_FBC_WM_DIS		(1<<15)
+#define  DISP_FBC_MEMORY_WAKE		(1 << 31)
+#define  DISP_TILE_SURFACE_SWIZZLING	(1 << 13)
+#define  DISP_FBC_WM_DIS		(1 << 15)
 #define DISP_ARB_CTL2	_MMIO(0x45004)
-#define  DISP_DATA_PARTITION_5_6	(1<<6)
-#define  DISP_IPC_ENABLE		(1<<3)
+#define  DISP_DATA_PARTITION_5_6	(1 << 6)
+#define  DISP_IPC_ENABLE		(1 << 3)
 #define DBUF_CTL	_MMIO(0x45008)
 #define DBUF_CTL_S1	_MMIO(0x45008)
 #define DBUF_CTL_S2	_MMIO(0x44FE8)
-#define  DBUF_POWER_REQUEST		(1<<31)
-#define  DBUF_POWER_STATE		(1<<30)
+#define  DBUF_POWER_REQUEST		(1 << 31)
+#define  DBUF_POWER_STATE		(1 << 30)
 #define GEN7_MSG_CTL	_MMIO(0x45010)
-#define  WAIT_FOR_PCH_RESET_ACK		(1<<1)
-#define  WAIT_FOR_PCH_FLR_ACK		(1<<0)
+#define  WAIT_FOR_PCH_RESET_ACK		(1 << 1)
+#define  WAIT_FOR_PCH_FLR_ACK		(1 << 0)
 #define HSW_NDE_RSTWRN_OPT	_MMIO(0x46408)
-#define  RESET_PCH_HANDSHAKE_ENABLE	(1<<4)
+#define  RESET_PCH_HANDSHAKE_ENABLE	(1 << 4)
 
 #define GEN8_CHICKEN_DCPR_1		_MMIO(0x46430)
 #define   SKL_SELECT_ALTERNATE_DC_EXIT	(1 << 30)
@@ -7179,16 +7377,16 @@ enum {
 #define ICL_DSSM_CDCLK_PLL_REFCLK_38_4MHz	(2 << 29)
 
 #define GEN7_FF_SLICE_CS_CHICKEN1	_MMIO(0x20e0)
-#define   GEN9_FFSC_PERCTX_PREEMPT_CTRL	(1<<14)
+#define   GEN9_FFSC_PERCTX_PREEMPT_CTRL	(1 << 14)
 
 #define FF_SLICE_CS_CHICKEN2			_MMIO(0x20e4)
-#define  GEN9_TSG_BARRIER_ACK_DISABLE		(1<<8)
-#define  GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE  (1<<10)
+#define  GEN9_TSG_BARRIER_ACK_DISABLE		(1 << 8)
+#define  GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE  (1 << 10)
 
 #define GEN9_CS_DEBUG_MODE1		_MMIO(0x20ec)
 #define GEN9_CTX_PREEMPT_REG		_MMIO(0x2248)
 #define GEN8_CS_CHICKEN1		_MMIO(0x2580)
-#define GEN9_PREEMPT_3D_OBJECT_LEVEL		(1<<0)
+#define GEN9_PREEMPT_3D_OBJECT_LEVEL		(1 << 0)
 #define GEN9_PREEMPT_GPGPU_LEVEL(hi, lo)	(((hi) << 2) | ((lo) << 1))
 #define GEN9_PREEMPT_GPGPU_MID_THREAD_LEVEL	GEN9_PREEMPT_GPGPU_LEVEL(0, 0)
 #define GEN9_PREEMPT_GPGPU_THREAD_GROUP_LEVEL	GEN9_PREEMPT_GPGPU_LEVEL(0, 1)
@@ -7197,22 +7395,27 @@ enum {
 
 /* GEN7 chicken */
 #define GEN7_COMMON_SLICE_CHICKEN1		_MMIO(0x7010)
-# define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC	((1<<10) | (1<<26))
-# define GEN9_RHWO_OPTIMIZATION_DISABLE		(1<<14)
-#define COMMON_SLICE_CHICKEN2			_MMIO(0x7014)
-# define GEN9_PBE_COMPRESSED_HASH_SELECTION	(1<<13)
-# define GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE (1<<12)
-# define GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION (1<<8)
-# define GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE	(1<<0)
+  #define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC	((1 << 10) | (1 << 26))
+  #define GEN9_RHWO_OPTIMIZATION_DISABLE	(1 << 14)
+
+#define COMMON_SLICE_CHICKEN2					_MMIO(0x7014)
+  #define GEN9_PBE_COMPRESSED_HASH_SELECTION			(1 << 13)
+  #define GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE	(1 << 12)
+  #define GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION		(1 << 8)
+  #define GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE			(1 << 0)
+
+#define GEN11_COMMON_SLICE_CHICKEN3		_MMIO(0x7304)
+  #define GEN11_BLEND_EMB_FIX_DISABLE_IN_RCC	(1 << 11)
 
 #define HIZ_CHICKEN					_MMIO(0x7018)
-# define CHV_HZ_8X8_MODE_IN_1X				(1<<15)
-# define BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE	(1<<3)
+# define CHV_HZ_8X8_MODE_IN_1X				(1 << 15)
+# define BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE	(1 << 3)
 
 #define GEN9_SLICE_COMMON_ECO_CHICKEN0		_MMIO(0x7308)
-#define  DISABLE_PIXEL_MASK_CAMMING		(1<<14)
+#define  DISABLE_PIXEL_MASK_CAMMING		(1 << 14)
 
 #define GEN9_SLICE_COMMON_ECO_CHICKEN1		_MMIO(0x731c)
+#define   GEN11_STATE_CACHE_REDIRECT_TO_CS	(1 << 11)
 
 #define GEN7_L3SQCREG1				_MMIO(0xB010)
 #define  VLV_B0_WA_L3SQCREG1_VALUE		0x00D30000
@@ -7230,7 +7433,7 @@ enum {
 
 #define GEN7_L3CNTLREG1				_MMIO(0xB01C)
 #define  GEN7_WA_FOR_GEN7_L3_CONTROL			0x3C47FF8C
-#define  GEN7_L3AGDIS				(1<<19)
+#define  GEN7_L3AGDIS				(1 << 19)
 #define GEN7_L3CNTLREG2				_MMIO(0xB020)
 #define GEN7_L3CNTLREG3				_MMIO(0xB024)
 
@@ -7240,7 +7443,7 @@ enum {
 #define   GEN11_I2M_WRITE_DISABLE		(1 << 28)
 
 #define GEN7_L3SQCREG4				_MMIO(0xb034)
-#define  L3SQ_URB_READ_CAM_MATCH_DISABLE	(1<<27)
+#define  L3SQ_URB_READ_CAM_MATCH_DISABLE	(1 << 27)
 
 #define GEN8_L3SQCREG4				_MMIO(0xb118)
 #define  GEN11_LQSC_CLEAN_EVICT_DISABLE		(1 << 6)
@@ -7251,12 +7454,12 @@ enum {
 #define HDC_CHICKEN0				_MMIO(0x7300)
 #define CNL_HDC_CHICKEN0			_MMIO(0xE5F0)
 #define ICL_HDC_MODE				_MMIO(0xE5F4)
-#define  HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE	(1<<15)
-#define  HDC_FENCE_DEST_SLM_DISABLE		(1<<14)
-#define  HDC_DONOT_FETCH_MEM_WHEN_MASKED	(1<<11)
-#define  HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT	(1<<5)
-#define  HDC_FORCE_NON_COHERENT			(1<<4)
-#define  HDC_BARRIER_PERFORMANCE_DISABLE	(1<<10)
+#define  HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE	(1 << 15)
+#define  HDC_FENCE_DEST_SLM_DISABLE		(1 << 14)
+#define  HDC_DONOT_FETCH_MEM_WHEN_MASKED	(1 << 11)
+#define  HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT	(1 << 5)
+#define  HDC_FORCE_NON_COHERENT			(1 << 4)
+#define  HDC_BARRIER_PERFORMANCE_DISABLE	(1 << 10)
 
 #define GEN8_HDC_CHICKEN1			_MMIO(0x7304)
 
@@ -7269,13 +7472,21 @@ enum {
 
 /* WaCatErrorRejectionIssue */
 #define GEN7_SQ_CHICKEN_MBCUNIT_CONFIG		_MMIO(0x9030)
-#define  GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB	(1<<11)
+#define  GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB	(1 << 11)
 
 #define HSW_SCRATCH1				_MMIO(0xb038)
-#define  HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE	(1<<27)
+#define  HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE	(1 << 27)
 
 #define BDW_SCRATCH1					_MMIO(0xb11c)
-#define  GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE	(1<<2)
+#define  GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE	(1 << 2)
+
+/*GEN11 chicken */
+#define _PIPEA_CHICKEN			0x70038
+#define _PIPEB_CHICKEN			0x71038
+#define _PIPEC_CHICKEN			0x72038
+#define  PER_PIXEL_ALPHA_BYPASS_EN	(1 << 7)
+#define PIPE_CHICKEN(pipe)		_MMIO_PIPE(pipe, _PIPEA_CHICKEN,\
+						   _PIPEB_CHICKEN)
 
 /* PCH */
 
@@ -7320,7 +7531,7 @@ enum {
 #define SDE_TRANSA_FIFO_UNDER	(1 << 0)
 #define SDE_TRANS_MASK		(0x3f)
 
-/* south display engine interrupt: CPT/PPT */
+/* south display engine interrupt: CPT - CNP */
 #define SDE_AUDIO_POWER_D_CPT	(1 << 31)
 #define SDE_AUDIO_POWER_C_CPT	(1 << 30)
 #define SDE_AUDIO_POWER_B_CPT	(1 << 29)
@@ -7368,14 +7579,29 @@ enum {
 				 SDE_FDI_RXB_CPT | \
 				 SDE_FDI_RXA_CPT)
 
+/* south display engine interrupt: ICP */
+#define SDE_TC4_HOTPLUG_ICP		(1 << 27)
+#define SDE_TC3_HOTPLUG_ICP		(1 << 26)
+#define SDE_TC2_HOTPLUG_ICP		(1 << 25)
+#define SDE_TC1_HOTPLUG_ICP		(1 << 24)
+#define SDE_GMBUS_ICP			(1 << 23)
+#define SDE_DDIB_HOTPLUG_ICP		(1 << 17)
+#define SDE_DDIA_HOTPLUG_ICP		(1 << 16)
+#define SDE_DDI_MASK_ICP		(SDE_DDIB_HOTPLUG_ICP |	\
+					 SDE_DDIA_HOTPLUG_ICP)
+#define SDE_TC_MASK_ICP			(SDE_TC4_HOTPLUG_ICP |	\
+					 SDE_TC3_HOTPLUG_ICP |	\
+					 SDE_TC2_HOTPLUG_ICP |	\
+					 SDE_TC1_HOTPLUG_ICP)
+
 #define SDEISR  _MMIO(0xc4000)
 #define SDEIMR  _MMIO(0xc4004)
 #define SDEIIR  _MMIO(0xc4008)
 #define SDEIER  _MMIO(0xc400c)
 
 #define SERR_INT			_MMIO(0xc4040)
-#define  SERR_INT_POISON		(1<<31)
-#define  SERR_INT_TRANS_FIFO_UNDERRUN(pipe)	(1<<((pipe)*3))
+#define  SERR_INT_POISON		(1 << 31)
+#define  SERR_INT_TRANS_FIFO_UNDERRUN(pipe)	(1 << ((pipe) * 3))
 
 /* digital port hotplug */
 #define PCH_PORT_HOTPLUG		_MMIO(0xc4030)	/* SHOTPLUG_CTL */
@@ -7428,6 +7654,134 @@ enum {
 #define  PORTE_HOTPLUG_SHORT_DETECT	(1 << 0)
 #define  PORTE_HOTPLUG_LONG_DETECT	(2 << 0)
 
+/* This register is a reuse of PCH_PORT_HOTPLUG register. The
+ * functionality covered in PCH_PORT_HOTPLUG is split into
+ * SHOTPLUG_CTL_DDI and SHOTPLUG_CTL_TC.
+ */
+
+#define SHOTPLUG_CTL_DDI			_MMIO(0xc4030)
+#define   ICP_DDIB_HPD_ENABLE			(1 << 7)
+#define   ICP_DDIB_HPD_STATUS_MASK		(3 << 4)
+#define   ICP_DDIB_HPD_NO_DETECT		(0 << 4)
+#define   ICP_DDIB_HPD_SHORT_DETECT		(1 << 4)
+#define   ICP_DDIB_HPD_LONG_DETECT		(2 << 4)
+#define   ICP_DDIB_HPD_SHORT_LONG_DETECT	(3 << 4)
+#define   ICP_DDIA_HPD_ENABLE			(1 << 3)
+#define   ICP_DDIA_HPD_STATUS_MASK		(3 << 0)
+#define   ICP_DDIA_HPD_NO_DETECT		(0 << 0)
+#define   ICP_DDIA_HPD_SHORT_DETECT		(1 << 0)
+#define   ICP_DDIA_HPD_LONG_DETECT		(2 << 0)
+#define   ICP_DDIA_HPD_SHORT_LONG_DETECT	(3 << 0)
+
+#define SHOTPLUG_CTL_TC				_MMIO(0xc4034)
+#define   ICP_TC_HPD_ENABLE(tc_port)		(8 << (tc_port) * 4)
+/* Icelake DSC Rate Control Range Parameter Registers */
+#define DSCA_RC_RANGE_PARAMETERS_0		_MMIO(0x6B240)
+#define DSCA_RC_RANGE_PARAMETERS_0_UDW		_MMIO(0x6B240 + 4)
+#define DSCC_RC_RANGE_PARAMETERS_0		_MMIO(0x6BA40)
+#define DSCC_RC_RANGE_PARAMETERS_0_UDW		_MMIO(0x6BA40 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_0_PB	(0x78208)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW_PB	(0x78208 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_0_PB	(0x78308)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW_PB	(0x78308 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_0_PC	(0x78408)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW_PC	(0x78408 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_0_PC	(0x78508)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW_PC	(0x78508 + 4)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_0(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_0_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_0_PC)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_0(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_0_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_0_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW_PC)
+#define RC_BPG_OFFSET_SHIFT			10
+#define RC_MAX_QP_SHIFT				5
+#define RC_MIN_QP_SHIFT				0
+
+#define DSCA_RC_RANGE_PARAMETERS_1		_MMIO(0x6B248)
+#define DSCA_RC_RANGE_PARAMETERS_1_UDW		_MMIO(0x6B248 + 4)
+#define DSCC_RC_RANGE_PARAMETERS_1		_MMIO(0x6BA48)
+#define DSCC_RC_RANGE_PARAMETERS_1_UDW		_MMIO(0x6BA48 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_1_PB	(0x78210)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW_PB	(0x78210 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_1_PB	(0x78310)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW_PB	(0x78310 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_1_PC	(0x78410)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW_PC	(0x78410 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_1_PC	(0x78510)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW_PC	(0x78510 + 4)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_1(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_1_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_1_PC)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_1(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_1_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_1_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW_PC)
+
+#define DSCA_RC_RANGE_PARAMETERS_2		_MMIO(0x6B250)
+#define DSCA_RC_RANGE_PARAMETERS_2_UDW		_MMIO(0x6B250 + 4)
+#define DSCC_RC_RANGE_PARAMETERS_2		_MMIO(0x6BA50)
+#define DSCC_RC_RANGE_PARAMETERS_2_UDW		_MMIO(0x6BA50 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_2_PB	(0x78218)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW_PB	(0x78218 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_2_PB	(0x78318)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW_PB	(0x78318 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_2_PC	(0x78418)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW_PC	(0x78418 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_2_PC	(0x78518)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW_PC	(0x78518 + 4)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_2(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_2_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_2_PC)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_2(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_2_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_2_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW_PC)
+
+#define DSCA_RC_RANGE_PARAMETERS_3		_MMIO(0x6B258)
+#define DSCA_RC_RANGE_PARAMETERS_3_UDW		_MMIO(0x6B258 + 4)
+#define DSCC_RC_RANGE_PARAMETERS_3		_MMIO(0x6BA58)
+#define DSCC_RC_RANGE_PARAMETERS_3_UDW		_MMIO(0x6BA58 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_3_PB	(0x78220)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW_PB	(0x78220 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_3_PB	(0x78320)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW_PB	(0x78320 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_3_PC	(0x78420)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW_PC	(0x78420 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_3_PC	(0x78520)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW_PC	(0x78520 + 4)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_3(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_3_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_3_PC)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_3(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_3_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_3_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW_PC)
+
+#define   ICP_TC_HPD_LONG_DETECT(tc_port)	(2 << (tc_port) * 4)
+#define   ICP_TC_HPD_SHORT_DETECT(tc_port)	(1 << (tc_port) * 4)
+
 #define PCH_GPIOA               _MMIO(0xc5010)
 #define PCH_GPIOB               _MMIO(0xc5014)
 #define PCH_GPIOC               _MMIO(0xc5018)
@@ -7444,46 +7798,46 @@ enum {
 
 #define _PCH_DPLL_A              0xc6014
 #define _PCH_DPLL_B              0xc6018
-#define PCH_DPLL(pll) _MMIO(pll == 0 ? _PCH_DPLL_A : _PCH_DPLL_B)
+#define PCH_DPLL(pll) _MMIO((pll) == 0 ? _PCH_DPLL_A : _PCH_DPLL_B)
 
 #define _PCH_FPA0                0xc6040
-#define  FP_CB_TUNE		(0x3<<22)
+#define  FP_CB_TUNE		(0x3 << 22)
 #define _PCH_FPA1                0xc6044
 #define _PCH_FPB0                0xc6048
 #define _PCH_FPB1                0xc604c
-#define PCH_FP0(pll) _MMIO(pll == 0 ? _PCH_FPA0 : _PCH_FPB0)
-#define PCH_FP1(pll) _MMIO(pll == 0 ? _PCH_FPA1 : _PCH_FPB1)
+#define PCH_FP0(pll) _MMIO((pll) == 0 ? _PCH_FPA0 : _PCH_FPB0)
+#define PCH_FP1(pll) _MMIO((pll) == 0 ? _PCH_FPA1 : _PCH_FPB1)
 
 #define PCH_DPLL_TEST           _MMIO(0xc606c)
 
 #define PCH_DREF_CONTROL        _MMIO(0xC6200)
 #define  DREF_CONTROL_MASK      0x7fc3
-#define  DREF_CPU_SOURCE_OUTPUT_DISABLE         (0<<13)
-#define  DREF_CPU_SOURCE_OUTPUT_DOWNSPREAD      (2<<13)
-#define  DREF_CPU_SOURCE_OUTPUT_NONSPREAD       (3<<13)
-#define  DREF_CPU_SOURCE_OUTPUT_MASK		(3<<13)
-#define  DREF_SSC_SOURCE_DISABLE                (0<<11)
-#define  DREF_SSC_SOURCE_ENABLE                 (2<<11)
-#define  DREF_SSC_SOURCE_MASK			(3<<11)
-#define  DREF_NONSPREAD_SOURCE_DISABLE          (0<<9)
-#define  DREF_NONSPREAD_CK505_ENABLE		(1<<9)
-#define  DREF_NONSPREAD_SOURCE_ENABLE           (2<<9)
-#define  DREF_NONSPREAD_SOURCE_MASK		(3<<9)
-#define  DREF_SUPERSPREAD_SOURCE_DISABLE        (0<<7)
-#define  DREF_SUPERSPREAD_SOURCE_ENABLE         (2<<7)
-#define  DREF_SUPERSPREAD_SOURCE_MASK		(3<<7)
-#define  DREF_SSC4_DOWNSPREAD                   (0<<6)
-#define  DREF_SSC4_CENTERSPREAD                 (1<<6)
-#define  DREF_SSC1_DISABLE                      (0<<1)
-#define  DREF_SSC1_ENABLE                       (1<<1)
+#define  DREF_CPU_SOURCE_OUTPUT_DISABLE         (0 << 13)
+#define  DREF_CPU_SOURCE_OUTPUT_DOWNSPREAD      (2 << 13)
+#define  DREF_CPU_SOURCE_OUTPUT_NONSPREAD       (3 << 13)
+#define  DREF_CPU_SOURCE_OUTPUT_MASK		(3 << 13)
+#define  DREF_SSC_SOURCE_DISABLE                (0 << 11)
+#define  DREF_SSC_SOURCE_ENABLE                 (2 << 11)
+#define  DREF_SSC_SOURCE_MASK			(3 << 11)
+#define  DREF_NONSPREAD_SOURCE_DISABLE          (0 << 9)
+#define  DREF_NONSPREAD_CK505_ENABLE		(1 << 9)
+#define  DREF_NONSPREAD_SOURCE_ENABLE           (2 << 9)
+#define  DREF_NONSPREAD_SOURCE_MASK		(3 << 9)
+#define  DREF_SUPERSPREAD_SOURCE_DISABLE        (0 << 7)
+#define  DREF_SUPERSPREAD_SOURCE_ENABLE         (2 << 7)
+#define  DREF_SUPERSPREAD_SOURCE_MASK		(3 << 7)
+#define  DREF_SSC4_DOWNSPREAD                   (0 << 6)
+#define  DREF_SSC4_CENTERSPREAD                 (1 << 6)
+#define  DREF_SSC1_DISABLE                      (0 << 1)
+#define  DREF_SSC1_ENABLE                       (1 << 1)
 #define  DREF_SSC4_DISABLE                      (0)
 #define  DREF_SSC4_ENABLE                       (1)
 
 #define PCH_RAWCLK_FREQ         _MMIO(0xc6204)
 #define  FDL_TP1_TIMER_SHIFT    12
-#define  FDL_TP1_TIMER_MASK     (3<<12)
+#define  FDL_TP1_TIMER_MASK     (3 << 12)
 #define  FDL_TP2_TIMER_SHIFT    10
-#define  FDL_TP2_TIMER_MASK     (3<<10)
+#define  FDL_TP2_TIMER_MASK     (3 << 10)
 #define  RAWCLK_FREQ_MASK       0x3ff
 #define  CNP_RAWCLK_DIV_MASK	(0x3ff << 16)
 #define  CNP_RAWCLK_DIV(div)	((div) << 16)
@@ -7520,7 +7874,7 @@ enum {
 #define  TRANS_VBLANK_END_SHIFT		16
 #define  TRANS_VBLANK_START_SHIFT	0
 #define _PCH_TRANS_VSYNC_A		0xe0014
-#define  TRANS_VSYNC_END_SHIFT	 	16
+#define  TRANS_VSYNC_END_SHIFT		16
 #define  TRANS_VSYNC_START_SHIFT	0
 #define _PCH_TRANS_VSYNCSHIFT_A		0xe0028
 
@@ -7600,15 +7954,28 @@ enum {
 #define _HSW_VIDEO_DIP_VSC_ECC_B	0x61344
 #define _HSW_VIDEO_DIP_GCP_B		0x61210
 
+/* Icelake PPS_DATA and _ECC DIP Registers.
+ * These are available for transcoders B,C and eDP.
+ * Adding the _A so as to reuse the _MMIO_TRANS2
+ * definition, with which it offsets to the right location.
+ */
+
+#define _ICL_VIDEO_DIP_PPS_DATA_A	0x60350
+#define _ICL_VIDEO_DIP_PPS_DATA_B	0x61350
+#define _ICL_VIDEO_DIP_PPS_ECC_A	0x603D4
+#define _ICL_VIDEO_DIP_PPS_ECC_B	0x613D4
+
 #define HSW_TVIDEO_DIP_CTL(trans)		_MMIO_TRANS2(trans, _HSW_VIDEO_DIP_CTL_A)
 #define HSW_TVIDEO_DIP_AVI_DATA(trans, i)	_MMIO_TRANS2(trans, _HSW_VIDEO_DIP_AVI_DATA_A + (i) * 4)
 #define HSW_TVIDEO_DIP_VS_DATA(trans, i)	_MMIO_TRANS2(trans, _HSW_VIDEO_DIP_VS_DATA_A + (i) * 4)
 #define HSW_TVIDEO_DIP_SPD_DATA(trans, i)	_MMIO_TRANS2(trans, _HSW_VIDEO_DIP_SPD_DATA_A + (i) * 4)
 #define HSW_TVIDEO_DIP_GCP(trans)		_MMIO_TRANS2(trans, _HSW_VIDEO_DIP_GCP_A)
 #define HSW_TVIDEO_DIP_VSC_DATA(trans, i)	_MMIO_TRANS2(trans, _HSW_VIDEO_DIP_VSC_DATA_A + (i) * 4)
+#define ICL_VIDEO_DIP_PPS_DATA(trans, i)	_MMIO_TRANS2(trans, _ICL_VIDEO_DIP_PPS_DATA_A + (i) * 4)
+#define ICL_VIDEO_DIP_PPS_ECC(trans, i)		_MMIO_TRANS2(trans, _ICL_VIDEO_DIP_PPS_ECC_A + (i) * 4)
 
 #define _HSW_STEREO_3D_CTL_A		0x70020
-#define   S3D_ENABLE			(1<<31)
+#define   S3D_ENABLE			(1 << 31)
 #define _HSW_STEREO_3D_CTL_B		0x71020
 
 #define HSW_STEREO_3D_CTL(trans)	_MMIO_PIPE2(trans, _HSW_STEREO_3D_CTL_A)
@@ -7651,156 +8018,156 @@ enum {
 #define _PCH_TRANSBCONF              0xf1008
 #define PCH_TRANSCONF(pipe)	_MMIO_PIPE(pipe, _PCH_TRANSACONF, _PCH_TRANSBCONF)
 #define LPT_TRANSCONF		PCH_TRANSCONF(PIPE_A) /* lpt has only one transcoder */
-#define  TRANS_DISABLE          (0<<31)
-#define  TRANS_ENABLE           (1<<31)
-#define  TRANS_STATE_MASK       (1<<30)
-#define  TRANS_STATE_DISABLE    (0<<30)
-#define  TRANS_STATE_ENABLE     (1<<30)
-#define  TRANS_FSYNC_DELAY_HB1  (0<<27)
-#define  TRANS_FSYNC_DELAY_HB2  (1<<27)
-#define  TRANS_FSYNC_DELAY_HB3  (2<<27)
-#define  TRANS_FSYNC_DELAY_HB4  (3<<27)
-#define  TRANS_INTERLACE_MASK   (7<<21)
-#define  TRANS_PROGRESSIVE      (0<<21)
-#define  TRANS_INTERLACED       (3<<21)
-#define  TRANS_LEGACY_INTERLACED_ILK (2<<21)
-#define  TRANS_8BPC             (0<<5)
-#define  TRANS_10BPC            (1<<5)
-#define  TRANS_6BPC             (2<<5)
-#define  TRANS_12BPC            (3<<5)
+#define  TRANS_DISABLE          (0 << 31)
+#define  TRANS_ENABLE           (1 << 31)
+#define  TRANS_STATE_MASK       (1 << 30)
+#define  TRANS_STATE_DISABLE    (0 << 30)
+#define  TRANS_STATE_ENABLE     (1 << 30)
+#define  TRANS_FSYNC_DELAY_HB1  (0 << 27)
+#define  TRANS_FSYNC_DELAY_HB2  (1 << 27)
+#define  TRANS_FSYNC_DELAY_HB3  (2 << 27)
+#define  TRANS_FSYNC_DELAY_HB4  (3 << 27)
+#define  TRANS_INTERLACE_MASK   (7 << 21)
+#define  TRANS_PROGRESSIVE      (0 << 21)
+#define  TRANS_INTERLACED       (3 << 21)
+#define  TRANS_LEGACY_INTERLACED_ILK (2 << 21)
+#define  TRANS_8BPC             (0 << 5)
+#define  TRANS_10BPC            (1 << 5)
+#define  TRANS_6BPC             (2 << 5)
+#define  TRANS_12BPC            (3 << 5)
 
 #define _TRANSA_CHICKEN1	 0xf0060
 #define _TRANSB_CHICKEN1	 0xf1060
 #define TRANS_CHICKEN1(pipe)	_MMIO_PIPE(pipe, _TRANSA_CHICKEN1, _TRANSB_CHICKEN1)
-#define  TRANS_CHICKEN1_HDMIUNIT_GC_DISABLE	(1<<10)
-#define  TRANS_CHICKEN1_DP0UNIT_GC_DISABLE	(1<<4)
+#define  TRANS_CHICKEN1_HDMIUNIT_GC_DISABLE	(1 << 10)
+#define  TRANS_CHICKEN1_DP0UNIT_GC_DISABLE	(1 << 4)
 #define _TRANSA_CHICKEN2	 0xf0064
 #define _TRANSB_CHICKEN2	 0xf1064
 #define TRANS_CHICKEN2(pipe)	_MMIO_PIPE(pipe, _TRANSA_CHICKEN2, _TRANSB_CHICKEN2)
-#define  TRANS_CHICKEN2_TIMING_OVERRIDE			(1<<31)
-#define  TRANS_CHICKEN2_FDI_POLARITY_REVERSED		(1<<29)
-#define  TRANS_CHICKEN2_FRAME_START_DELAY_MASK		(3<<27)
-#define  TRANS_CHICKEN2_DISABLE_DEEP_COLOR_COUNTER	(1<<26)
-#define  TRANS_CHICKEN2_DISABLE_DEEP_COLOR_MODESWITCH	(1<<25)
+#define  TRANS_CHICKEN2_TIMING_OVERRIDE			(1 << 31)
+#define  TRANS_CHICKEN2_FDI_POLARITY_REVERSED		(1 << 29)
+#define  TRANS_CHICKEN2_FRAME_START_DELAY_MASK		(3 << 27)
+#define  TRANS_CHICKEN2_DISABLE_DEEP_COLOR_COUNTER	(1 << 26)
+#define  TRANS_CHICKEN2_DISABLE_DEEP_COLOR_MODESWITCH	(1 << 25)
 
 #define SOUTH_CHICKEN1		_MMIO(0xc2000)
 #define  FDIA_PHASE_SYNC_SHIFT_OVR	19
 #define  FDIA_PHASE_SYNC_SHIFT_EN	18
-#define  FDI_PHASE_SYNC_OVR(pipe) (1<<(FDIA_PHASE_SYNC_SHIFT_OVR - ((pipe) * 2)))
-#define  FDI_PHASE_SYNC_EN(pipe) (1<<(FDIA_PHASE_SYNC_SHIFT_EN - ((pipe) * 2)))
+#define  FDI_PHASE_SYNC_OVR(pipe) (1 << (FDIA_PHASE_SYNC_SHIFT_OVR - ((pipe) * 2)))
+#define  FDI_PHASE_SYNC_EN(pipe) (1 << (FDIA_PHASE_SYNC_SHIFT_EN - ((pipe) * 2)))
 #define  FDI_BC_BIFURCATION_SELECT	(1 << 12)
 #define  CHASSIS_CLK_REQ_DURATION_MASK	(0xf << 8)
 #define  CHASSIS_CLK_REQ_DURATION(x)	((x) << 8)
-#define  SPT_PWM_GRANULARITY		(1<<0)
+#define  SPT_PWM_GRANULARITY		(1 << 0)
 #define SOUTH_CHICKEN2		_MMIO(0xc2004)
-#define  FDI_MPHY_IOSFSB_RESET_STATUS	(1<<13)
-#define  FDI_MPHY_IOSFSB_RESET_CTL	(1<<12)
-#define  LPT_PWM_GRANULARITY		(1<<5)
-#define  DPLS_EDP_PPS_FIX_DIS		(1<<0)
+#define  FDI_MPHY_IOSFSB_RESET_STATUS	(1 << 13)
+#define  FDI_MPHY_IOSFSB_RESET_CTL	(1 << 12)
+#define  LPT_PWM_GRANULARITY		(1 << 5)
+#define  DPLS_EDP_PPS_FIX_DIS		(1 << 0)
 
 #define _FDI_RXA_CHICKEN        0xc200c
 #define _FDI_RXB_CHICKEN        0xc2010
-#define  FDI_RX_PHASE_SYNC_POINTER_OVR	(1<<1)
-#define  FDI_RX_PHASE_SYNC_POINTER_EN	(1<<0)
+#define  FDI_RX_PHASE_SYNC_POINTER_OVR	(1 << 1)
+#define  FDI_RX_PHASE_SYNC_POINTER_EN	(1 << 0)
 #define FDI_RX_CHICKEN(pipe)	_MMIO_PIPE(pipe, _FDI_RXA_CHICKEN, _FDI_RXB_CHICKEN)
 
 #define SOUTH_DSPCLK_GATE_D	_MMIO(0xc2020)
-#define  PCH_GMBUSUNIT_CLOCK_GATE_DISABLE (1<<31)
-#define  PCH_DPLUNIT_CLOCK_GATE_DISABLE (1<<30)
-#define  PCH_DPLSUNIT_CLOCK_GATE_DISABLE (1<<29)
-#define  PCH_CPUNIT_CLOCK_GATE_DISABLE (1<<14)
-#define  CNP_PWM_CGE_GATING_DISABLE (1<<13)
-#define  PCH_LP_PARTITION_LEVEL_DISABLE  (1<<12)
+#define  PCH_GMBUSUNIT_CLOCK_GATE_DISABLE (1 << 31)
+#define  PCH_DPLUNIT_CLOCK_GATE_DISABLE (1 << 30)
+#define  PCH_DPLSUNIT_CLOCK_GATE_DISABLE (1 << 29)
+#define  PCH_CPUNIT_CLOCK_GATE_DISABLE (1 << 14)
+#define  CNP_PWM_CGE_GATING_DISABLE (1 << 13)
+#define  PCH_LP_PARTITION_LEVEL_DISABLE  (1 << 12)
 
 /* CPU: FDI_TX */
 #define _FDI_TXA_CTL            0x60100
 #define _FDI_TXB_CTL            0x61100
 #define FDI_TX_CTL(pipe)	_MMIO_PIPE(pipe, _FDI_TXA_CTL, _FDI_TXB_CTL)
-#define  FDI_TX_DISABLE         (0<<31)
-#define  FDI_TX_ENABLE          (1<<31)
-#define  FDI_LINK_TRAIN_PATTERN_1       (0<<28)
-#define  FDI_LINK_TRAIN_PATTERN_2       (1<<28)
-#define  FDI_LINK_TRAIN_PATTERN_IDLE    (2<<28)
-#define  FDI_LINK_TRAIN_NONE            (3<<28)
-#define  FDI_LINK_TRAIN_VOLTAGE_0_4V    (0<<25)
-#define  FDI_LINK_TRAIN_VOLTAGE_0_6V    (1<<25)
-#define  FDI_LINK_TRAIN_VOLTAGE_0_8V    (2<<25)
-#define  FDI_LINK_TRAIN_VOLTAGE_1_2V    (3<<25)
-#define  FDI_LINK_TRAIN_PRE_EMPHASIS_NONE (0<<22)
-#define  FDI_LINK_TRAIN_PRE_EMPHASIS_1_5X (1<<22)
-#define  FDI_LINK_TRAIN_PRE_EMPHASIS_2X   (2<<22)
-#define  FDI_LINK_TRAIN_PRE_EMPHASIS_3X   (3<<22)
+#define  FDI_TX_DISABLE         (0 << 31)
+#define  FDI_TX_ENABLE          (1 << 31)
+#define  FDI_LINK_TRAIN_PATTERN_1       (0 << 28)
+#define  FDI_LINK_TRAIN_PATTERN_2       (1 << 28)
+#define  FDI_LINK_TRAIN_PATTERN_IDLE    (2 << 28)
+#define  FDI_LINK_TRAIN_NONE            (3 << 28)
+#define  FDI_LINK_TRAIN_VOLTAGE_0_4V    (0 << 25)
+#define  FDI_LINK_TRAIN_VOLTAGE_0_6V    (1 << 25)
+#define  FDI_LINK_TRAIN_VOLTAGE_0_8V    (2 << 25)
+#define  FDI_LINK_TRAIN_VOLTAGE_1_2V    (3 << 25)
+#define  FDI_LINK_TRAIN_PRE_EMPHASIS_NONE (0 << 22)
+#define  FDI_LINK_TRAIN_PRE_EMPHASIS_1_5X (1 << 22)
+#define  FDI_LINK_TRAIN_PRE_EMPHASIS_2X   (2 << 22)
+#define  FDI_LINK_TRAIN_PRE_EMPHASIS_3X   (3 << 22)
 /* ILK always use 400mV 0dB for voltage swing and pre-emphasis level.
    SNB has different settings. */
 /* SNB A-stepping */
-#define  FDI_LINK_TRAIN_400MV_0DB_SNB_A		(0x38<<22)
-#define  FDI_LINK_TRAIN_400MV_6DB_SNB_A		(0x02<<22)
-#define  FDI_LINK_TRAIN_600MV_3_5DB_SNB_A	(0x01<<22)
-#define  FDI_LINK_TRAIN_800MV_0DB_SNB_A		(0x0<<22)
+#define  FDI_LINK_TRAIN_400MV_0DB_SNB_A		(0x38 << 22)
+#define  FDI_LINK_TRAIN_400MV_6DB_SNB_A		(0x02 << 22)
+#define  FDI_LINK_TRAIN_600MV_3_5DB_SNB_A	(0x01 << 22)
+#define  FDI_LINK_TRAIN_800MV_0DB_SNB_A		(0x0 << 22)
 /* SNB B-stepping */
-#define  FDI_LINK_TRAIN_400MV_0DB_SNB_B		(0x0<<22)
-#define  FDI_LINK_TRAIN_400MV_6DB_SNB_B		(0x3a<<22)
-#define  FDI_LINK_TRAIN_600MV_3_5DB_SNB_B	(0x39<<22)
-#define  FDI_LINK_TRAIN_800MV_0DB_SNB_B		(0x38<<22)
-#define  FDI_LINK_TRAIN_VOL_EMP_MASK		(0x3f<<22)
+#define  FDI_LINK_TRAIN_400MV_0DB_SNB_B		(0x0 << 22)
+#define  FDI_LINK_TRAIN_400MV_6DB_SNB_B		(0x3a << 22)
+#define  FDI_LINK_TRAIN_600MV_3_5DB_SNB_B	(0x39 << 22)
+#define  FDI_LINK_TRAIN_800MV_0DB_SNB_B		(0x38 << 22)
+#define  FDI_LINK_TRAIN_VOL_EMP_MASK		(0x3f << 22)
 #define  FDI_DP_PORT_WIDTH_SHIFT		19
 #define  FDI_DP_PORT_WIDTH_MASK			(7 << FDI_DP_PORT_WIDTH_SHIFT)
 #define  FDI_DP_PORT_WIDTH(width)           (((width) - 1) << FDI_DP_PORT_WIDTH_SHIFT)
-#define  FDI_TX_ENHANCE_FRAME_ENABLE    (1<<18)
+#define  FDI_TX_ENHANCE_FRAME_ENABLE    (1 << 18)
 /* Ironlake: hardwired to 1 */
-#define  FDI_TX_PLL_ENABLE              (1<<14)
+#define  FDI_TX_PLL_ENABLE              (1 << 14)
 
 /* Ivybridge has different bits for lolz */
-#define  FDI_LINK_TRAIN_PATTERN_1_IVB       (0<<8)
-#define  FDI_LINK_TRAIN_PATTERN_2_IVB       (1<<8)
-#define  FDI_LINK_TRAIN_PATTERN_IDLE_IVB    (2<<8)
-#define  FDI_LINK_TRAIN_NONE_IVB            (3<<8)
+#define  FDI_LINK_TRAIN_PATTERN_1_IVB       (0 << 8)
+#define  FDI_LINK_TRAIN_PATTERN_2_IVB       (1 << 8)
+#define  FDI_LINK_TRAIN_PATTERN_IDLE_IVB    (2 << 8)
+#define  FDI_LINK_TRAIN_NONE_IVB            (3 << 8)
 
 /* both Tx and Rx */
-#define  FDI_COMPOSITE_SYNC		(1<<11)
-#define  FDI_LINK_TRAIN_AUTO		(1<<10)
-#define  FDI_SCRAMBLING_ENABLE          (0<<7)
-#define  FDI_SCRAMBLING_DISABLE         (1<<7)
+#define  FDI_COMPOSITE_SYNC		(1 << 11)
+#define  FDI_LINK_TRAIN_AUTO		(1 << 10)
+#define  FDI_SCRAMBLING_ENABLE          (0 << 7)
+#define  FDI_SCRAMBLING_DISABLE         (1 << 7)
 
 /* FDI_RX, FDI_X is hard-wired to Transcoder_X */
 #define _FDI_RXA_CTL             0xf000c
 #define _FDI_RXB_CTL             0xf100c
 #define FDI_RX_CTL(pipe)	_MMIO_PIPE(pipe, _FDI_RXA_CTL, _FDI_RXB_CTL)
-#define  FDI_RX_ENABLE          (1<<31)
+#define  FDI_RX_ENABLE          (1 << 31)
 /* train, dp width same as FDI_TX */
-#define  FDI_FS_ERRC_ENABLE		(1<<27)
-#define  FDI_FE_ERRC_ENABLE		(1<<26)
-#define  FDI_RX_POLARITY_REVERSED_LPT	(1<<16)
-#define  FDI_8BPC                       (0<<16)
-#define  FDI_10BPC                      (1<<16)
-#define  FDI_6BPC                       (2<<16)
-#define  FDI_12BPC                      (3<<16)
-#define  FDI_RX_LINK_REVERSAL_OVERRIDE  (1<<15)
-#define  FDI_DMI_LINK_REVERSE_MASK      (1<<14)
-#define  FDI_RX_PLL_ENABLE              (1<<13)
-#define  FDI_FS_ERR_CORRECT_ENABLE      (1<<11)
-#define  FDI_FE_ERR_CORRECT_ENABLE      (1<<10)
-#define  FDI_FS_ERR_REPORT_ENABLE       (1<<9)
-#define  FDI_FE_ERR_REPORT_ENABLE       (1<<8)
-#define  FDI_RX_ENHANCE_FRAME_ENABLE    (1<<6)
-#define  FDI_PCDCLK	                (1<<4)
+#define  FDI_FS_ERRC_ENABLE		(1 << 27)
+#define  FDI_FE_ERRC_ENABLE		(1 << 26)
+#define  FDI_RX_POLARITY_REVERSED_LPT	(1 << 16)
+#define  FDI_8BPC                       (0 << 16)
+#define  FDI_10BPC                      (1 << 16)
+#define  FDI_6BPC                       (2 << 16)
+#define  FDI_12BPC                      (3 << 16)
+#define  FDI_RX_LINK_REVERSAL_OVERRIDE  (1 << 15)
+#define  FDI_DMI_LINK_REVERSE_MASK      (1 << 14)
+#define  FDI_RX_PLL_ENABLE              (1 << 13)
+#define  FDI_FS_ERR_CORRECT_ENABLE      (1 << 11)
+#define  FDI_FE_ERR_CORRECT_ENABLE      (1 << 10)
+#define  FDI_FS_ERR_REPORT_ENABLE       (1 << 9)
+#define  FDI_FE_ERR_REPORT_ENABLE       (1 << 8)
+#define  FDI_RX_ENHANCE_FRAME_ENABLE    (1 << 6)
+#define  FDI_PCDCLK	                (1 << 4)
 /* CPT */
-#define  FDI_AUTO_TRAINING			(1<<10)
-#define  FDI_LINK_TRAIN_PATTERN_1_CPT		(0<<8)
-#define  FDI_LINK_TRAIN_PATTERN_2_CPT		(1<<8)
-#define  FDI_LINK_TRAIN_PATTERN_IDLE_CPT	(2<<8)
-#define  FDI_LINK_TRAIN_NORMAL_CPT		(3<<8)
-#define  FDI_LINK_TRAIN_PATTERN_MASK_CPT	(3<<8)
+#define  FDI_AUTO_TRAINING			(1 << 10)
+#define  FDI_LINK_TRAIN_PATTERN_1_CPT		(0 << 8)
+#define  FDI_LINK_TRAIN_PATTERN_2_CPT		(1 << 8)
+#define  FDI_LINK_TRAIN_PATTERN_IDLE_CPT	(2 << 8)
+#define  FDI_LINK_TRAIN_NORMAL_CPT		(3 << 8)
+#define  FDI_LINK_TRAIN_PATTERN_MASK_CPT	(3 << 8)
 
 #define _FDI_RXA_MISC			0xf0010
 #define _FDI_RXB_MISC			0xf1010
-#define  FDI_RX_PWRDN_LANE1_MASK	(3<<26)
-#define  FDI_RX_PWRDN_LANE1_VAL(x)	((x)<<26)
-#define  FDI_RX_PWRDN_LANE0_MASK	(3<<24)
-#define  FDI_RX_PWRDN_LANE0_VAL(x)	((x)<<24)
-#define  FDI_RX_TP1_TO_TP2_48		(2<<20)
-#define  FDI_RX_TP1_TO_TP2_64		(3<<20)
-#define  FDI_RX_FDI_DELAY_90		(0x90<<0)
+#define  FDI_RX_PWRDN_LANE1_MASK	(3 << 26)
+#define  FDI_RX_PWRDN_LANE1_VAL(x)	((x) << 26)
+#define  FDI_RX_PWRDN_LANE0_MASK	(3 << 24)
+#define  FDI_RX_PWRDN_LANE0_VAL(x)	((x) << 24)
+#define  FDI_RX_TP1_TO_TP2_48		(2 << 20)
+#define  FDI_RX_TP1_TO_TP2_64		(3 << 20)
+#define  FDI_RX_FDI_DELAY_90		(0x90 << 0)
 #define FDI_RX_MISC(pipe)	_MMIO_PIPE(pipe, _FDI_RXA_MISC, _FDI_RXB_MISC)
 
 #define _FDI_RXA_TUSIZE1        0xf0030
@@ -7811,17 +8178,17 @@ enum {
 #define FDI_RX_TUSIZE2(pipe)	_MMIO_PIPE(pipe, _FDI_RXA_TUSIZE2, _FDI_RXB_TUSIZE2)
 
 /* FDI_RX interrupt register format */
-#define FDI_RX_INTER_LANE_ALIGN         (1<<10)
-#define FDI_RX_SYMBOL_LOCK              (1<<9) /* train 2 */
-#define FDI_RX_BIT_LOCK                 (1<<8) /* train 1 */
-#define FDI_RX_TRAIN_PATTERN_2_FAIL     (1<<7)
-#define FDI_RX_FS_CODE_ERR              (1<<6)
-#define FDI_RX_FE_CODE_ERR              (1<<5)
-#define FDI_RX_SYMBOL_ERR_RATE_ABOVE    (1<<4)
-#define FDI_RX_HDCP_LINK_FAIL           (1<<3)
-#define FDI_RX_PIXEL_FIFO_OVERFLOW      (1<<2)
-#define FDI_RX_CROSS_CLOCK_OVERFLOW     (1<<1)
-#define FDI_RX_SYMBOL_QUEUE_OVERFLOW    (1<<0)
+#define FDI_RX_INTER_LANE_ALIGN         (1 << 10)
+#define FDI_RX_SYMBOL_LOCK              (1 << 9) /* train 2 */
+#define FDI_RX_BIT_LOCK                 (1 << 8) /* train 1 */
+#define FDI_RX_TRAIN_PATTERN_2_FAIL     (1 << 7)
+#define FDI_RX_FS_CODE_ERR              (1 << 6)
+#define FDI_RX_FE_CODE_ERR              (1 << 5)
+#define FDI_RX_SYMBOL_ERR_RATE_ABOVE    (1 << 4)
+#define FDI_RX_HDCP_LINK_FAIL           (1 << 3)
+#define FDI_RX_PIXEL_FIFO_OVERFLOW      (1 << 2)
+#define FDI_RX_CROSS_CLOCK_OVERFLOW     (1 << 1)
+#define FDI_RX_SYMBOL_QUEUE_OVERFLOW    (1 << 0)
 
 #define _FDI_RXA_IIR            0xf0014
 #define _FDI_RXA_IMR            0xf0018
@@ -7867,71 +8234,58 @@ enum {
 #define PCH_DP_AUX_CH_DATA(aux_ch, i)	_MMIO(_PORT((aux_ch) - AUX_CH_B, _PCH_DPB_AUX_CH_DATA1, _PCH_DPC_AUX_CH_DATA1) + (i) * 4) /* 5 registers */
 
 /* CPT */
-#define  PORT_TRANS_A_SEL_CPT	0
-#define  PORT_TRANS_B_SEL_CPT	(1<<29)
-#define  PORT_TRANS_C_SEL_CPT	(2<<29)
-#define  PORT_TRANS_SEL_MASK	(3<<29)
-#define  PORT_TRANS_SEL_CPT(pipe)	((pipe) << 29)
-#define  PORT_TO_PIPE(val)	(((val) & (1<<30)) >> 30)
-#define  PORT_TO_PIPE_CPT(val)	(((val) & PORT_TRANS_SEL_MASK) >> 29)
-#define  SDVO_PORT_TO_PIPE_CHV(val)	(((val) & (3<<24)) >> 24)
-#define  DP_PORT_TO_PIPE_CHV(val)	(((val) & (3<<16)) >> 16)
-
 #define _TRANS_DP_CTL_A		0xe0300
 #define _TRANS_DP_CTL_B		0xe1300
 #define _TRANS_DP_CTL_C		0xe2300
 #define TRANS_DP_CTL(pipe)	_MMIO_PIPE(pipe, _TRANS_DP_CTL_A, _TRANS_DP_CTL_B)
-#define  TRANS_DP_OUTPUT_ENABLE	(1<<31)
-#define  TRANS_DP_PORT_SEL_B	(0<<29)
-#define  TRANS_DP_PORT_SEL_C	(1<<29)
-#define  TRANS_DP_PORT_SEL_D	(2<<29)
-#define  TRANS_DP_PORT_SEL_NONE	(3<<29)
-#define  TRANS_DP_PORT_SEL_MASK	(3<<29)
-#define  TRANS_DP_PIPE_TO_PORT(val)	((((val) & TRANS_DP_PORT_SEL_MASK) >> 29) + PORT_B)
-#define  TRANS_DP_AUDIO_ONLY	(1<<26)
-#define  TRANS_DP_ENH_FRAMING	(1<<18)
-#define  TRANS_DP_8BPC		(0<<9)
-#define  TRANS_DP_10BPC		(1<<9)
-#define  TRANS_DP_6BPC		(2<<9)
-#define  TRANS_DP_12BPC		(3<<9)
-#define  TRANS_DP_BPC_MASK	(3<<9)
-#define  TRANS_DP_VSYNC_ACTIVE_HIGH	(1<<4)
+#define  TRANS_DP_OUTPUT_ENABLE	(1 << 31)
+#define  TRANS_DP_PORT_SEL_MASK		(3 << 29)
+#define  TRANS_DP_PORT_SEL_NONE		(3 << 29)
+#define  TRANS_DP_PORT_SEL(port)	(((port) - PORT_B) << 29)
+#define  TRANS_DP_AUDIO_ONLY	(1 << 26)
+#define  TRANS_DP_ENH_FRAMING	(1 << 18)
+#define  TRANS_DP_8BPC		(0 << 9)
+#define  TRANS_DP_10BPC		(1 << 9)
+#define  TRANS_DP_6BPC		(2 << 9)
+#define  TRANS_DP_12BPC		(3 << 9)
+#define  TRANS_DP_BPC_MASK	(3 << 9)
+#define  TRANS_DP_VSYNC_ACTIVE_HIGH	(1 << 4)
 #define  TRANS_DP_VSYNC_ACTIVE_LOW	0
-#define  TRANS_DP_HSYNC_ACTIVE_HIGH	(1<<3)
+#define  TRANS_DP_HSYNC_ACTIVE_HIGH	(1 << 3)
 #define  TRANS_DP_HSYNC_ACTIVE_LOW	0
-#define  TRANS_DP_SYNC_MASK	(3<<3)
+#define  TRANS_DP_SYNC_MASK	(3 << 3)
 
 /* SNB eDP training params */
 /* SNB A-stepping */
-#define  EDP_LINK_TRAIN_400MV_0DB_SNB_A		(0x38<<22)
-#define  EDP_LINK_TRAIN_400MV_6DB_SNB_A		(0x02<<22)
-#define  EDP_LINK_TRAIN_600MV_3_5DB_SNB_A	(0x01<<22)
-#define  EDP_LINK_TRAIN_800MV_0DB_SNB_A		(0x0<<22)
+#define  EDP_LINK_TRAIN_400MV_0DB_SNB_A		(0x38 << 22)
+#define  EDP_LINK_TRAIN_400MV_6DB_SNB_A		(0x02 << 22)
+#define  EDP_LINK_TRAIN_600MV_3_5DB_SNB_A	(0x01 << 22)
+#define  EDP_LINK_TRAIN_800MV_0DB_SNB_A		(0x0 << 22)
 /* SNB B-stepping */
-#define  EDP_LINK_TRAIN_400_600MV_0DB_SNB_B	(0x0<<22)
-#define  EDP_LINK_TRAIN_400MV_3_5DB_SNB_B	(0x1<<22)
-#define  EDP_LINK_TRAIN_400_600MV_6DB_SNB_B	(0x3a<<22)
-#define  EDP_LINK_TRAIN_600_800MV_3_5DB_SNB_B	(0x39<<22)
-#define  EDP_LINK_TRAIN_800_1200MV_0DB_SNB_B	(0x38<<22)
-#define  EDP_LINK_TRAIN_VOL_EMP_MASK_SNB	(0x3f<<22)
+#define  EDP_LINK_TRAIN_400_600MV_0DB_SNB_B	(0x0 << 22)
+#define  EDP_LINK_TRAIN_400MV_3_5DB_SNB_B	(0x1 << 22)
+#define  EDP_LINK_TRAIN_400_600MV_6DB_SNB_B	(0x3a << 22)
+#define  EDP_LINK_TRAIN_600_800MV_3_5DB_SNB_B	(0x39 << 22)
+#define  EDP_LINK_TRAIN_800_1200MV_0DB_SNB_B	(0x38 << 22)
+#define  EDP_LINK_TRAIN_VOL_EMP_MASK_SNB	(0x3f << 22)
 
 /* IVB */
-#define EDP_LINK_TRAIN_400MV_0DB_IVB		(0x24 <<22)
-#define EDP_LINK_TRAIN_400MV_3_5DB_IVB		(0x2a <<22)
-#define EDP_LINK_TRAIN_400MV_6DB_IVB		(0x2f <<22)
-#define EDP_LINK_TRAIN_600MV_0DB_IVB		(0x30 <<22)
-#define EDP_LINK_TRAIN_600MV_3_5DB_IVB		(0x36 <<22)
-#define EDP_LINK_TRAIN_800MV_0DB_IVB		(0x38 <<22)
-#define EDP_LINK_TRAIN_800MV_3_5DB_IVB		(0x3e <<22)
+#define EDP_LINK_TRAIN_400MV_0DB_IVB		(0x24 << 22)
+#define EDP_LINK_TRAIN_400MV_3_5DB_IVB		(0x2a << 22)
+#define EDP_LINK_TRAIN_400MV_6DB_IVB		(0x2f << 22)
+#define EDP_LINK_TRAIN_600MV_0DB_IVB		(0x30 << 22)
+#define EDP_LINK_TRAIN_600MV_3_5DB_IVB		(0x36 << 22)
+#define EDP_LINK_TRAIN_800MV_0DB_IVB		(0x38 << 22)
+#define EDP_LINK_TRAIN_800MV_3_5DB_IVB		(0x3e << 22)
 
 /* legacy values */
-#define EDP_LINK_TRAIN_500MV_0DB_IVB		(0x00 <<22)
-#define EDP_LINK_TRAIN_1000MV_0DB_IVB		(0x20 <<22)
-#define EDP_LINK_TRAIN_500MV_3_5DB_IVB		(0x02 <<22)
-#define EDP_LINK_TRAIN_1000MV_3_5DB_IVB		(0x22 <<22)
-#define EDP_LINK_TRAIN_1000MV_6DB_IVB		(0x23 <<22)
+#define EDP_LINK_TRAIN_500MV_0DB_IVB		(0x00 << 22)
+#define EDP_LINK_TRAIN_1000MV_0DB_IVB		(0x20 << 22)
+#define EDP_LINK_TRAIN_500MV_3_5DB_IVB		(0x02 << 22)
+#define EDP_LINK_TRAIN_1000MV_3_5DB_IVB		(0x22 << 22)
+#define EDP_LINK_TRAIN_1000MV_6DB_IVB		(0x23 << 22)
 
-#define  EDP_LINK_TRAIN_VOL_EMP_MASK_IVB	(0x3f<<22)
+#define  EDP_LINK_TRAIN_VOL_EMP_MASK_IVB	(0x3f << 22)
 
 #define  VLV_PMWGICZ				_MMIO(0x1300a4)
 
@@ -7978,7 +8332,7 @@ enum {
 #define   FORCEWAKE_KERNEL_FALLBACK		BIT(15)
 #define  FORCEWAKE_MT_ACK			_MMIO(0x130040)
 #define  ECOBUS					_MMIO(0xa180)
-#define    FORCEWAKE_MT_ENABLE			(1<<5)
+#define    FORCEWAKE_MT_ENABLE			(1 << 5)
 #define  VLV_SPAREG2H				_MMIO(0xA194)
 #define  GEN9_PWRGT_DOMAIN_STATUS		_MMIO(0xA2A0)
 #define   GEN9_PWRGT_MEDIA_STATUS_MASK		(1 << 0)
@@ -7987,13 +8341,13 @@ enum {
 #define  GTFIFODBG				_MMIO(0x120000)
 #define    GT_FIFO_SBDEDICATE_FREE_ENTRY_CHV	(0x1f << 20)
 #define    GT_FIFO_FREE_ENTRIES_CHV		(0x7f << 13)
-#define    GT_FIFO_SBDROPERR			(1<<6)
-#define    GT_FIFO_BLOBDROPERR			(1<<5)
-#define    GT_FIFO_SB_READ_ABORTERR		(1<<4)
-#define    GT_FIFO_DROPERR			(1<<3)
-#define    GT_FIFO_OVFERR			(1<<2)
-#define    GT_FIFO_IAWRERR			(1<<1)
-#define    GT_FIFO_IARDERR			(1<<0)
+#define    GT_FIFO_SBDROPERR			(1 << 6)
+#define    GT_FIFO_BLOBDROPERR			(1 << 5)
+#define    GT_FIFO_SB_READ_ABORTERR		(1 << 4)
+#define    GT_FIFO_DROPERR			(1 << 3)
+#define    GT_FIFO_OVFERR			(1 << 2)
+#define    GT_FIFO_IAWRERR			(1 << 1)
+#define    GT_FIFO_IARDERR			(1 << 0)
 
 #define  GTFIFOCTL				_MMIO(0x120008)
 #define    GT_FIFO_FREE_ENTRIES_MASK		0x7f
@@ -8027,37 +8381,37 @@ enum {
 # define GEN6_OACSUNIT_CLOCK_GATE_DISABLE		(1 << 20)
 
 #define GEN7_UCGCTL4				_MMIO(0x940c)
-#define  GEN7_L3BANK2X_CLOCK_GATE_DISABLE	(1<<25)
-#define  GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE	(1<<14)
+#define  GEN7_L3BANK2X_CLOCK_GATE_DISABLE	(1 << 25)
+#define  GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE	(1 << 14)
 
 #define GEN6_RCGCTL1				_MMIO(0x9410)
 #define GEN6_RCGCTL2				_MMIO(0x9414)
 #define GEN6_RSTCTL				_MMIO(0x9420)
 
 #define GEN8_UCGCTL6				_MMIO(0x9430)
-#define   GEN8_GAPSUNIT_CLOCK_GATE_DISABLE	(1<<24)
-#define   GEN8_SDEUNIT_CLOCK_GATE_DISABLE	(1<<14)
-#define   GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ (1<<28)
+#define   GEN8_GAPSUNIT_CLOCK_GATE_DISABLE	(1 << 24)
+#define   GEN8_SDEUNIT_CLOCK_GATE_DISABLE	(1 << 14)
+#define   GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ (1 << 28)
 
 #define GEN6_GFXPAUSE				_MMIO(0xA000)
 #define GEN6_RPNSWREQ				_MMIO(0xA008)
-#define   GEN6_TURBO_DISABLE			(1<<31)
-#define   GEN6_FREQUENCY(x)			((x)<<25)
-#define   HSW_FREQUENCY(x)			((x)<<24)
-#define   GEN9_FREQUENCY(x)			((x)<<23)
-#define   GEN6_OFFSET(x)			((x)<<19)
-#define   GEN6_AGGRESSIVE_TURBO			(0<<15)
+#define   GEN6_TURBO_DISABLE			(1 << 31)
+#define   GEN6_FREQUENCY(x)			((x) << 25)
+#define   HSW_FREQUENCY(x)			((x) << 24)
+#define   GEN9_FREQUENCY(x)			((x) << 23)
+#define   GEN6_OFFSET(x)			((x) << 19)
+#define   GEN6_AGGRESSIVE_TURBO			(0 << 15)
 #define GEN6_RC_VIDEO_FREQ			_MMIO(0xA00C)
 #define GEN6_RC_CONTROL				_MMIO(0xA090)
-#define   GEN6_RC_CTL_RC6pp_ENABLE		(1<<16)
-#define   GEN6_RC_CTL_RC6p_ENABLE		(1<<17)
-#define   GEN6_RC_CTL_RC6_ENABLE		(1<<18)
-#define   GEN6_RC_CTL_RC1e_ENABLE		(1<<20)
-#define   GEN6_RC_CTL_RC7_ENABLE		(1<<22)
-#define   VLV_RC_CTL_CTX_RST_PARALLEL		(1<<24)
-#define   GEN7_RC_CTL_TO_MODE			(1<<28)
-#define   GEN6_RC_CTL_EI_MODE(x)		((x)<<27)
-#define   GEN6_RC_CTL_HW_ENABLE			(1<<31)
+#define   GEN6_RC_CTL_RC6pp_ENABLE		(1 << 16)
+#define   GEN6_RC_CTL_RC6p_ENABLE		(1 << 17)
+#define   GEN6_RC_CTL_RC6_ENABLE		(1 << 18)
+#define   GEN6_RC_CTL_RC1e_ENABLE		(1 << 20)
+#define   GEN6_RC_CTL_RC7_ENABLE		(1 << 22)
+#define   VLV_RC_CTL_CTX_RST_PARALLEL		(1 << 24)
+#define   GEN7_RC_CTL_TO_MODE			(1 << 28)
+#define   GEN6_RC_CTL_EI_MODE(x)		((x) << 27)
+#define   GEN6_RC_CTL_HW_ENABLE			(1 << 31)
 #define GEN6_RP_DOWN_TIMEOUT			_MMIO(0xA010)
 #define GEN6_RP_INTERRUPT_LIMITS		_MMIO(0xA014)
 #define GEN6_RPSTAT1				_MMIO(0xA01C)
@@ -8068,19 +8422,19 @@ enum {
 #define   HSW_CAGF_MASK				(0x7f << HSW_CAGF_SHIFT)
 #define   GEN9_CAGF_MASK			(0x1ff << GEN9_CAGF_SHIFT)
 #define GEN6_RP_CONTROL				_MMIO(0xA024)
-#define   GEN6_RP_MEDIA_TURBO			(1<<11)
-#define   GEN6_RP_MEDIA_MODE_MASK		(3<<9)
-#define   GEN6_RP_MEDIA_HW_TURBO_MODE		(3<<9)
-#define   GEN6_RP_MEDIA_HW_NORMAL_MODE		(2<<9)
-#define   GEN6_RP_MEDIA_HW_MODE			(1<<9)
-#define   GEN6_RP_MEDIA_SW_MODE			(0<<9)
-#define   GEN6_RP_MEDIA_IS_GFX			(1<<8)
-#define   GEN6_RP_ENABLE			(1<<7)
-#define   GEN6_RP_UP_IDLE_MIN			(0x1<<3)
-#define   GEN6_RP_UP_BUSY_AVG			(0x2<<3)
-#define   GEN6_RP_UP_BUSY_CONT			(0x4<<3)
-#define   GEN6_RP_DOWN_IDLE_AVG			(0x2<<0)
-#define   GEN6_RP_DOWN_IDLE_CONT		(0x1<<0)
+#define   GEN6_RP_MEDIA_TURBO			(1 << 11)
+#define   GEN6_RP_MEDIA_MODE_MASK		(3 << 9)
+#define   GEN6_RP_MEDIA_HW_TURBO_MODE		(3 << 9)
+#define   GEN6_RP_MEDIA_HW_NORMAL_MODE		(2 << 9)
+#define   GEN6_RP_MEDIA_HW_MODE			(1 << 9)
+#define   GEN6_RP_MEDIA_SW_MODE			(0 << 9)
+#define   GEN6_RP_MEDIA_IS_GFX			(1 << 8)
+#define   GEN6_RP_ENABLE			(1 << 7)
+#define   GEN6_RP_UP_IDLE_MIN			(0x1 << 3)
+#define   GEN6_RP_UP_BUSY_AVG			(0x2 << 3)
+#define   GEN6_RP_UP_BUSY_CONT			(0x4 << 3)
+#define   GEN6_RP_DOWN_IDLE_AVG			(0x2 << 0)
+#define   GEN6_RP_DOWN_IDLE_CONT		(0x1 << 0)
 #define GEN6_RP_UP_THRESHOLD			_MMIO(0xA02C)
 #define GEN6_RP_DOWN_THRESHOLD			_MMIO(0xA030)
 #define GEN6_RP_CUR_UP_EI			_MMIO(0xA050)
@@ -8116,15 +8470,15 @@ enum {
 #define VLV_RCEDATA				_MMIO(0xA0BC)
 #define GEN6_RC6pp_THRESHOLD			_MMIO(0xA0C0)
 #define GEN6_PMINTRMSK				_MMIO(0xA168)
-#define   GEN8_PMINTR_DISABLE_REDIRECT_TO_GUC	(1<<31)
-#define   ARAT_EXPIRED_INTRMSK			(1<<9)
+#define   GEN8_PMINTR_DISABLE_REDIRECT_TO_GUC	(1 << 31)
+#define   ARAT_EXPIRED_INTRMSK			(1 << 9)
 #define GEN8_MISC_CTRL0				_MMIO(0xA180)
 #define VLV_PWRDWNUPCTL				_MMIO(0xA294)
 #define GEN9_MEDIA_PG_IDLE_HYSTERESIS		_MMIO(0xA0C4)
 #define GEN9_RENDER_PG_IDLE_HYSTERESIS		_MMIO(0xA0C8)
 #define GEN9_PG_ENABLE				_MMIO(0xA210)
-#define GEN9_RENDER_PG_ENABLE			(1<<0)
-#define GEN9_MEDIA_PG_ENABLE			(1<<1)
+#define GEN9_RENDER_PG_ENABLE			(1 << 0)
+#define GEN9_MEDIA_PG_ENABLE			(1 << 1)
 #define GEN8_PUSHBUS_CONTROL			_MMIO(0xA248)
 #define GEN8_PUSHBUS_ENABLE			_MMIO(0xA250)
 #define GEN8_PUSHBUS_SHIFT			_MMIO(0xA25C)
@@ -8137,13 +8491,13 @@ enum {
 #define GEN6_PMIMR				_MMIO(0x44024) /* rps_lock */
 #define GEN6_PMIIR				_MMIO(0x44028)
 #define GEN6_PMIER				_MMIO(0x4402C)
-#define  GEN6_PM_MBOX_EVENT			(1<<25)
-#define  GEN6_PM_THERMAL_EVENT			(1<<24)
-#define  GEN6_PM_RP_DOWN_TIMEOUT		(1<<6)
-#define  GEN6_PM_RP_UP_THRESHOLD		(1<<5)
-#define  GEN6_PM_RP_DOWN_THRESHOLD		(1<<4)
-#define  GEN6_PM_RP_UP_EI_EXPIRED		(1<<2)
-#define  GEN6_PM_RP_DOWN_EI_EXPIRED		(1<<1)
+#define  GEN6_PM_MBOX_EVENT			(1 << 25)
+#define  GEN6_PM_THERMAL_EVENT			(1 << 24)
+#define  GEN6_PM_RP_DOWN_TIMEOUT		(1 << 6)
+#define  GEN6_PM_RP_UP_THRESHOLD		(1 << 5)
+#define  GEN6_PM_RP_DOWN_THRESHOLD		(1 << 4)
+#define  GEN6_PM_RP_UP_EI_EXPIRED		(1 << 2)
+#define  GEN6_PM_RP_DOWN_EI_EXPIRED		(1 << 1)
 #define  GEN6_PM_RPS_EVENTS			(GEN6_PM_RP_UP_THRESHOLD | \
 						 GEN6_PM_RP_DOWN_THRESHOLD | \
 						 GEN6_PM_RP_DOWN_TIMEOUT)
@@ -8152,16 +8506,16 @@ enum {
 #define GEN7_GT_SCRATCH_REG_NUM			8
 
 #define VLV_GTLC_SURVIVABILITY_REG              _MMIO(0x130098)
-#define VLV_GFX_CLK_STATUS_BIT			(1<<3)
-#define VLV_GFX_CLK_FORCE_ON_BIT		(1<<2)
+#define VLV_GFX_CLK_STATUS_BIT			(1 << 3)
+#define VLV_GFX_CLK_FORCE_ON_BIT		(1 << 2)
 
 #define GEN6_GT_GFX_RC6_LOCKED			_MMIO(0x138104)
 #define VLV_COUNTER_CONTROL			_MMIO(0x138104)
-#define   VLV_COUNT_RANGE_HIGH			(1<<15)
-#define   VLV_MEDIA_RC0_COUNT_EN		(1<<5)
-#define   VLV_RENDER_RC0_COUNT_EN		(1<<4)
-#define   VLV_MEDIA_RC6_COUNT_EN		(1<<1)
-#define   VLV_RENDER_RC6_COUNT_EN		(1<<0)
+#define   VLV_COUNT_RANGE_HIGH			(1 << 15)
+#define   VLV_MEDIA_RC0_COUNT_EN		(1 << 5)
+#define   VLV_RENDER_RC0_COUNT_EN		(1 << 4)
+#define   VLV_MEDIA_RC6_COUNT_EN		(1 << 1)
+#define   VLV_RENDER_RC6_COUNT_EN		(1 << 0)
 #define GEN6_GT_GFX_RC6				_MMIO(0x138108)
 #define VLV_GT_RENDER_RC6			_MMIO(0x138108)
 #define VLV_GT_MEDIA_RC6			_MMIO(0x13810C)
@@ -8172,7 +8526,7 @@ enum {
 #define VLV_MEDIA_C0_COUNT			_MMIO(0x13811C)
 
 #define GEN6_PCODE_MAILBOX			_MMIO(0x138124)
-#define   GEN6_PCODE_READY			(1<<31)
+#define   GEN6_PCODE_READY			(1 << 31)
 #define   GEN6_PCODE_ERROR_MASK			0xFF
 #define     GEN6_PCODE_SUCCESS			0x0
 #define     GEN6_PCODE_ILLEGAL_CMD		0x1
@@ -8216,7 +8570,7 @@ enum {
 #define GEN6_PCODE_DATA1			_MMIO(0x13812C)
 
 #define GEN6_GT_CORE_STATUS		_MMIO(0x138060)
-#define   GEN6_CORE_CPD_STATE_MASK	(7<<4)
+#define   GEN6_CORE_CPD_STATE_MASK	(7 << 4)
 #define   GEN6_RCn_MASK			7
 #define   GEN6_RC0			0
 #define   GEN6_RC3			2
@@ -8228,26 +8582,26 @@ enum {
 
 #define CHV_POWER_SS0_SIG1		_MMIO(0xa720)
 #define CHV_POWER_SS1_SIG1		_MMIO(0xa728)
-#define   CHV_SS_PG_ENABLE		(1<<1)
-#define   CHV_EU08_PG_ENABLE		(1<<9)
-#define   CHV_EU19_PG_ENABLE		(1<<17)
-#define   CHV_EU210_PG_ENABLE		(1<<25)
+#define   CHV_SS_PG_ENABLE		(1 << 1)
+#define   CHV_EU08_PG_ENABLE		(1 << 9)
+#define   CHV_EU19_PG_ENABLE		(1 << 17)
+#define   CHV_EU210_PG_ENABLE		(1 << 25)
 
 #define CHV_POWER_SS0_SIG2		_MMIO(0xa724)
 #define CHV_POWER_SS1_SIG2		_MMIO(0xa72c)
-#define   CHV_EU311_PG_ENABLE		(1<<1)
+#define   CHV_EU311_PG_ENABLE		(1 << 1)
 
-#define GEN9_SLICE_PGCTL_ACK(slice)	_MMIO(0x804c + (slice)*0x4)
+#define GEN9_SLICE_PGCTL_ACK(slice)	_MMIO(0x804c + (slice) * 0x4)
 #define GEN10_SLICE_PGCTL_ACK(slice)	_MMIO(0x804c + ((slice) / 3) * 0x34 + \
 					      ((slice) % 3) * 0x4)
 #define   GEN9_PGCTL_SLICE_ACK		(1 << 0)
-#define   GEN9_PGCTL_SS_ACK(subslice)	(1 << (2 + (subslice)*2))
+#define   GEN9_PGCTL_SS_ACK(subslice)	(1 << (2 + (subslice) * 2))
 #define   GEN10_PGCTL_VALID_SS_MASK(slice) ((slice) == 0 ? 0x7F : 0x1F)
 
-#define GEN9_SS01_EU_PGCTL_ACK(slice)	_MMIO(0x805c + (slice)*0x8)
+#define GEN9_SS01_EU_PGCTL_ACK(slice)	_MMIO(0x805c + (slice) * 0x8)
 #define GEN10_SS01_EU_PGCTL_ACK(slice)	_MMIO(0x805c + ((slice) / 3) * 0x30 + \
 					      ((slice) % 3) * 0x8)
-#define GEN9_SS23_EU_PGCTL_ACK(slice)	_MMIO(0x8060 + (slice)*0x8)
+#define GEN9_SS23_EU_PGCTL_ACK(slice)	_MMIO(0x8060 + (slice) * 0x8)
 #define GEN10_SS23_EU_PGCTL_ACK(slice)	_MMIO(0x8060 + ((slice) / 3) * 0x30 + \
 					      ((slice) % 3) * 0x8)
 #define   GEN9_PGCTL_SSA_EU08_ACK	(1 << 0)
@@ -8260,10 +8614,10 @@ enum {
 #define   GEN9_PGCTL_SSB_EU311_ACK	(1 << 14)
 
 #define GEN7_MISCCPCTL				_MMIO(0x9424)
-#define   GEN7_DOP_CLOCK_GATE_ENABLE		(1<<0)
-#define   GEN8_DOP_CLOCK_GATE_CFCLK_ENABLE	(1<<2)
-#define   GEN8_DOP_CLOCK_GATE_GUC_ENABLE	(1<<4)
-#define   GEN8_DOP_CLOCK_GATE_MEDIA_ENABLE     (1<<6)
+#define   GEN7_DOP_CLOCK_GATE_ENABLE		(1 << 0)
+#define   GEN8_DOP_CLOCK_GATE_CFCLK_ENABLE	(1 << 2)
+#define   GEN8_DOP_CLOCK_GATE_GUC_ENABLE	(1 << 4)
+#define   GEN8_DOP_CLOCK_GATE_MEDIA_ENABLE     (1 << 6)
 
 #define GEN8_GARBCNTL				_MMIO(0xB004)
 #define   GEN9_GAPS_TSV_CREDIT_DISABLE		(1 << 7)
@@ -8292,61 +8646,62 @@ enum {
 
 /* IVYBRIDGE DPF */
 #define GEN7_L3CDERRST1(slice)		_MMIO(0xB008 + (slice) * 0x200) /* L3CD Error Status 1 */
-#define   GEN7_L3CDERRST1_ROW_MASK	(0x7ff<<14)
-#define   GEN7_PARITY_ERROR_VALID	(1<<13)
-#define   GEN7_L3CDERRST1_BANK_MASK	(3<<11)
-#define   GEN7_L3CDERRST1_SUBBANK_MASK	(7<<8)
+#define   GEN7_L3CDERRST1_ROW_MASK	(0x7ff << 14)
+#define   GEN7_PARITY_ERROR_VALID	(1 << 13)
+#define   GEN7_L3CDERRST1_BANK_MASK	(3 << 11)
+#define   GEN7_L3CDERRST1_SUBBANK_MASK	(7 << 8)
 #define GEN7_PARITY_ERROR_ROW(reg) \
-		((reg & GEN7_L3CDERRST1_ROW_MASK) >> 14)
+		(((reg) & GEN7_L3CDERRST1_ROW_MASK) >> 14)
 #define GEN7_PARITY_ERROR_BANK(reg) \
-		((reg & GEN7_L3CDERRST1_BANK_MASK) >> 11)
+		(((reg) & GEN7_L3CDERRST1_BANK_MASK) >> 11)
 #define GEN7_PARITY_ERROR_SUBBANK(reg) \
-		((reg & GEN7_L3CDERRST1_SUBBANK_MASK) >> 8)
-#define   GEN7_L3CDERRST1_ENABLE	(1<<7)
+		(((reg) & GEN7_L3CDERRST1_SUBBANK_MASK) >> 8)
+#define   GEN7_L3CDERRST1_ENABLE	(1 << 7)
 
 #define GEN7_L3LOG(slice, i)		_MMIO(0xB070 + (slice) * 0x200 + (i) * 4)
 #define GEN7_L3LOG_SIZE			0x80
 
 #define GEN7_HALF_SLICE_CHICKEN1	_MMIO(0xe100) /* IVB GT1 + VLV */
 #define GEN7_HALF_SLICE_CHICKEN1_GT2	_MMIO(0xf100)
-#define   GEN7_MAX_PS_THREAD_DEP		(8<<12)
-#define   GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE	(1<<10)
-#define   GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE	(1<<4)
-#define   GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE	(1<<3)
+#define   GEN7_MAX_PS_THREAD_DEP		(8 << 12)
+#define   GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE	(1 << 10)
+#define   GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE	(1 << 4)
+#define   GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE	(1 << 3)
 
 #define GEN9_HALF_SLICE_CHICKEN5	_MMIO(0xe188)
-#define   GEN9_DG_MIRROR_FIX_ENABLE	(1<<5)
-#define   GEN9_CCS_TLB_PREFETCH_ENABLE	(1<<3)
+#define   GEN9_DG_MIRROR_FIX_ENABLE	(1 << 5)
+#define   GEN9_CCS_TLB_PREFETCH_ENABLE	(1 << 3)
 
 #define GEN8_ROW_CHICKEN		_MMIO(0xe4f0)
-#define   FLOW_CONTROL_ENABLE		(1<<15)
-#define   PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE	(1<<8)
-#define   STALL_DOP_GATING_DISABLE		(1<<5)
-#define   THROTTLE_12_5				(7<<2)
-#define   DISABLE_EARLY_EOT			(1<<1)
+#define   FLOW_CONTROL_ENABLE		(1 << 15)
+#define   PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE	(1 << 8)
+#define   STALL_DOP_GATING_DISABLE		(1 << 5)
+#define   THROTTLE_12_5				(7 << 2)
+#define   DISABLE_EARLY_EOT			(1 << 1)
 
 #define GEN7_ROW_CHICKEN2		_MMIO(0xe4f4)
 #define GEN7_ROW_CHICKEN2_GT2		_MMIO(0xf4f4)
-#define   DOP_CLOCK_GATING_DISABLE	(1<<0)
-#define   PUSH_CONSTANT_DEREF_DISABLE	(1<<8)
+#define   DOP_CLOCK_GATING_DISABLE	(1 << 0)
+#define   PUSH_CONSTANT_DEREF_DISABLE	(1 << 8)
+#define   GEN11_TDL_CLOCK_GATING_FIX_DISABLE	(1 << 1)
 
 #define HSW_ROW_CHICKEN3		_MMIO(0xe49c)
 #define  HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE    (1 << 6)
 
 #define HALF_SLICE_CHICKEN2		_MMIO(0xe180)
-#define   GEN8_ST_PO_DISABLE		(1<<13)
+#define   GEN8_ST_PO_DISABLE		(1 << 13)
 
 #define HALF_SLICE_CHICKEN3		_MMIO(0xe184)
-#define   HSW_SAMPLE_C_PERFORMANCE	(1<<9)
-#define   GEN8_CENTROID_PIXEL_OPT_DIS	(1<<8)
-#define   GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC	(1<<5)
-#define   CNL_FAST_ANISO_L1_BANKING_FIX	(1<<4)
-#define   GEN8_SAMPLER_POWER_BYPASS_DIS	(1<<1)
+#define   HSW_SAMPLE_C_PERFORMANCE	(1 << 9)
+#define   GEN8_CENTROID_PIXEL_OPT_DIS	(1 << 8)
+#define   GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC	(1 << 5)
+#define   CNL_FAST_ANISO_L1_BANKING_FIX	(1 << 4)
+#define   GEN8_SAMPLER_POWER_BYPASS_DIS	(1 << 1)
 
 #define GEN9_HALF_SLICE_CHICKEN7	_MMIO(0xe194)
-#define   GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR	(1<<8)
-#define   GEN9_ENABLE_YV12_BUGFIX	(1<<4)
-#define   GEN9_ENABLE_GPGPU_PREEMPTION	(1<<2)
+#define   GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR	(1 << 8)
+#define   GEN9_ENABLE_YV12_BUGFIX	(1 << 4)
+#define   GEN9_ENABLE_GPGPU_PREEMPTION	(1 << 2)
 
 /* Audio */
 #define G4X_AUD_VID_DID			_MMIO(dev_priv->info.display_mmio_offset + 0x62020)
@@ -8478,6 +8833,14 @@ enum {
 #define _HSW_PWR_WELL_CTL3			0x45408
 #define _HSW_PWR_WELL_CTL4			0x4540C
 
+#define _ICL_PWR_WELL_CTL_AUX1			0x45440
+#define _ICL_PWR_WELL_CTL_AUX2			0x45444
+#define _ICL_PWR_WELL_CTL_AUX4			0x4544C
+
+#define _ICL_PWR_WELL_CTL_DDI1			0x45450
+#define _ICL_PWR_WELL_CTL_DDI2			0x45454
+#define _ICL_PWR_WELL_CTL_DDI4			0x4545C
+
 /*
  * Each power well control register contains up to 16 (request, status) HW
  * flag tuples. The register index and HW flag shift is determined by the
@@ -8487,21 +8850,27 @@ enum {
  */
 #define _HSW_PW_REG_IDX(pw)			((pw) >> 4)
 #define _HSW_PW_SHIFT(pw)			(((pw) & 0xf) * 2)
-/* TODO: Add all PWR_WELL_CTL registers below for new platforms */
 #define HSW_PWR_WELL_CTL_BIOS(pw)	_MMIO(_PICK(_HSW_PW_REG_IDX(pw),       \
-						    _HSW_PWR_WELL_CTL1))
+						    _HSW_PWR_WELL_CTL1,	       \
+						    _ICL_PWR_WELL_CTL_AUX1,    \
+						    _ICL_PWR_WELL_CTL_DDI1))
 #define HSW_PWR_WELL_CTL_DRIVER(pw)	_MMIO(_PICK(_HSW_PW_REG_IDX(pw),       \
-						    _HSW_PWR_WELL_CTL2))
+						    _HSW_PWR_WELL_CTL2,	       \
+						    _ICL_PWR_WELL_CTL_AUX2,    \
+						    _ICL_PWR_WELL_CTL_DDI2))
+/* KVMR doesn't have a reg for AUX or DDI power well control */
 #define HSW_PWR_WELL_CTL_KVMR		_MMIO(_HSW_PWR_WELL_CTL3)
 #define HSW_PWR_WELL_CTL_DEBUG(pw)	_MMIO(_PICK(_HSW_PW_REG_IDX(pw),       \
-						    _HSW_PWR_WELL_CTL4))
+						    _HSW_PWR_WELL_CTL4,	       \
+						    _ICL_PWR_WELL_CTL_AUX4,    \
+						    _ICL_PWR_WELL_CTL_DDI4))
 
 #define   HSW_PWR_WELL_CTL_REQ(pw)		(1 << (_HSW_PW_SHIFT(pw) + 1))
 #define   HSW_PWR_WELL_CTL_STATE(pw)		(1 << _HSW_PW_SHIFT(pw))
 #define HSW_PWR_WELL_CTL5			_MMIO(0x45410)
-#define   HSW_PWR_WELL_ENABLE_SINGLE_STEP	(1<<31)
-#define   HSW_PWR_WELL_PWR_GATE_OVERRIDE	(1<<20)
-#define   HSW_PWR_WELL_FORCE_ON			(1<<19)
+#define   HSW_PWR_WELL_ENABLE_SINGLE_STEP	(1 << 31)
+#define   HSW_PWR_WELL_PWR_GATE_OVERRIDE	(1 << 20)
+#define   HSW_PWR_WELL_FORCE_ON			(1 << 19)
 #define HSW_PWR_WELL_CTL6			_MMIO(0x45414)
 
 /* SKL Fuse Status */
@@ -8512,9 +8881,11 @@ enum skl_power_gate {
 };
 
 #define SKL_FUSE_STATUS				_MMIO(0x42000)
-#define  SKL_FUSE_DOWNLOAD_STATUS		(1<<31)
+#define  SKL_FUSE_DOWNLOAD_STATUS		(1 << 31)
 /* PG0 (HW control->no power well ID), PG1..PG2 (SKL_DISP_PW1..SKL_DISP_PW2) */
 #define  SKL_PW_TO_PG(pw)			((pw) - SKL_DISP_PW_1 + SKL_PG1)
+/* PG0 (HW control->no power well ID), PG1..PG4 (ICL_DISP_PW1..ICL_DISP_PW4) */
+#define  ICL_PW_TO_PG(pw)			((pw) - ICL_DISP_PW_1 + SKL_PG1)
 #define  SKL_FUSE_PG_DIST_STATUS(pg)		(1 << (27 - (pg)))
 
 #define _CNL_AUX_REG_IDX(pw)		((pw) - 9)
@@ -8527,8 +8898,8 @@ enum skl_power_gate {
 						    _CNL_AUX_ANAOVRD1_C, \
 						    _CNL_AUX_ANAOVRD1_D, \
 						    _CNL_AUX_ANAOVRD1_F))
-#define   CNL_AUX_ANAOVRD1_ENABLE	(1<<16)
-#define   CNL_AUX_ANAOVRD1_LDO_BYPASS	(1<<23)
+#define   CNL_AUX_ANAOVRD1_ENABLE	(1 << 16)
+#define   CNL_AUX_ANAOVRD1_LDO_BYPASS	(1 << 23)
 
 /* HDCP Key Registers */
 #define HDCP_KEY_CONF			_MMIO(0x66c00)
@@ -8573,7 +8944,7 @@ enum skl_power_gate {
 #define HDCP_SHA_V_PRIME_H2		_MMIO(0x66d0C)
 #define HDCP_SHA_V_PRIME_H3		_MMIO(0x66d10)
 #define HDCP_SHA_V_PRIME_H4		_MMIO(0x66d14)
-#define HDCP_SHA_V_PRIME(h)		_MMIO((0x66d04 + h * 4))
+#define HDCP_SHA_V_PRIME(h)		_MMIO((0x66d04 + (h) * 4))
 #define HDCP_SHA_TEXT			_MMIO(0x66d18)
 
 /* HDCP Auth Registers */
@@ -8589,7 +8960,7 @@ enum skl_power_gate {
 					  _PORTC_HDCP_AUTHENC, \
 					  _PORTD_HDCP_AUTHENC, \
 					  _PORTE_HDCP_AUTHENC, \
-					  _PORTF_HDCP_AUTHENC) + x)
+					  _PORTF_HDCP_AUTHENC) + (x))
 #define PORT_HDCP_CONF(port)		_PORT_HDCP_AUTHENC(port, 0x0)
 #define  HDCP_CONF_CAPTURE_AN		BIT(0)
 #define  HDCP_CONF_AUTH_AND_ENC		(BIT(1) | BIT(0))
@@ -8610,7 +8981,7 @@ enum skl_power_gate {
 #define  HDCP_STATUS_R0_READY		BIT(18)
 #define  HDCP_STATUS_AN_READY		BIT(17)
 #define  HDCP_STATUS_CIPHER		BIT(16)
-#define  HDCP_STATUS_FRAME_CNT(x)	((x >> 8) & 0xff)
+#define  HDCP_STATUS_FRAME_CNT(x)	(((x) >> 8) & 0xff)
 
 /* Per-pipe DDI Function Control */
 #define _TRANS_DDI_FUNC_CTL_A		0x60400
@@ -8619,37 +8990,37 @@ enum skl_power_gate {
 #define _TRANS_DDI_FUNC_CTL_EDP		0x6F400
 #define TRANS_DDI_FUNC_CTL(tran) _MMIO_TRANS2(tran, _TRANS_DDI_FUNC_CTL_A)
 
-#define  TRANS_DDI_FUNC_ENABLE		(1<<31)
+#define  TRANS_DDI_FUNC_ENABLE		(1 << 31)
 /* Those bits are ignored by pipe EDP since it can only connect to DDI A */
-#define  TRANS_DDI_PORT_MASK		(7<<28)
+#define  TRANS_DDI_PORT_MASK		(7 << 28)
 #define  TRANS_DDI_PORT_SHIFT		28
-#define  TRANS_DDI_SELECT_PORT(x)	((x)<<28)
-#define  TRANS_DDI_PORT_NONE		(0<<28)
-#define  TRANS_DDI_MODE_SELECT_MASK	(7<<24)
-#define  TRANS_DDI_MODE_SELECT_HDMI	(0<<24)
-#define  TRANS_DDI_MODE_SELECT_DVI	(1<<24)
-#define  TRANS_DDI_MODE_SELECT_DP_SST	(2<<24)
-#define  TRANS_DDI_MODE_SELECT_DP_MST	(3<<24)
-#define  TRANS_DDI_MODE_SELECT_FDI	(4<<24)
-#define  TRANS_DDI_BPC_MASK		(7<<20)
-#define  TRANS_DDI_BPC_8		(0<<20)
-#define  TRANS_DDI_BPC_10		(1<<20)
-#define  TRANS_DDI_BPC_6		(2<<20)
-#define  TRANS_DDI_BPC_12		(3<<20)
-#define  TRANS_DDI_PVSYNC		(1<<17)
-#define  TRANS_DDI_PHSYNC		(1<<16)
-#define  TRANS_DDI_EDP_INPUT_MASK	(7<<12)
-#define  TRANS_DDI_EDP_INPUT_A_ON	(0<<12)
-#define  TRANS_DDI_EDP_INPUT_A_ONOFF	(4<<12)
-#define  TRANS_DDI_EDP_INPUT_B_ONOFF	(5<<12)
-#define  TRANS_DDI_EDP_INPUT_C_ONOFF	(6<<12)
-#define  TRANS_DDI_HDCP_SIGNALLING	(1<<9)
-#define  TRANS_DDI_DP_VC_PAYLOAD_ALLOC	(1<<8)
-#define  TRANS_DDI_HDMI_SCRAMBLER_CTS_ENABLE (1<<7)
-#define  TRANS_DDI_HDMI_SCRAMBLER_RESET_FREQ (1<<6)
-#define  TRANS_DDI_BFI_ENABLE		(1<<4)
-#define  TRANS_DDI_HIGH_TMDS_CHAR_RATE	(1<<4)
-#define  TRANS_DDI_HDMI_SCRAMBLING	(1<<0)
+#define  TRANS_DDI_SELECT_PORT(x)	((x) << 28)
+#define  TRANS_DDI_PORT_NONE		(0 << 28)
+#define  TRANS_DDI_MODE_SELECT_MASK	(7 << 24)
+#define  TRANS_DDI_MODE_SELECT_HDMI	(0 << 24)
+#define  TRANS_DDI_MODE_SELECT_DVI	(1 << 24)
+#define  TRANS_DDI_MODE_SELECT_DP_SST	(2 << 24)
+#define  TRANS_DDI_MODE_SELECT_DP_MST	(3 << 24)
+#define  TRANS_DDI_MODE_SELECT_FDI	(4 << 24)
+#define  TRANS_DDI_BPC_MASK		(7 << 20)
+#define  TRANS_DDI_BPC_8		(0 << 20)
+#define  TRANS_DDI_BPC_10		(1 << 20)
+#define  TRANS_DDI_BPC_6		(2 << 20)
+#define  TRANS_DDI_BPC_12		(3 << 20)
+#define  TRANS_DDI_PVSYNC		(1 << 17)
+#define  TRANS_DDI_PHSYNC		(1 << 16)
+#define  TRANS_DDI_EDP_INPUT_MASK	(7 << 12)
+#define  TRANS_DDI_EDP_INPUT_A_ON	(0 << 12)
+#define  TRANS_DDI_EDP_INPUT_A_ONOFF	(4 << 12)
+#define  TRANS_DDI_EDP_INPUT_B_ONOFF	(5 << 12)
+#define  TRANS_DDI_EDP_INPUT_C_ONOFF	(6 << 12)
+#define  TRANS_DDI_HDCP_SIGNALLING	(1 << 9)
+#define  TRANS_DDI_DP_VC_PAYLOAD_ALLOC	(1 << 8)
+#define  TRANS_DDI_HDMI_SCRAMBLER_CTS_ENABLE (1 << 7)
+#define  TRANS_DDI_HDMI_SCRAMBLER_RESET_FREQ (1 << 6)
+#define  TRANS_DDI_BFI_ENABLE		(1 << 4)
+#define  TRANS_DDI_HIGH_TMDS_CHAR_RATE	(1 << 4)
+#define  TRANS_DDI_HDMI_SCRAMBLING	(1 << 0)
 #define  TRANS_DDI_HDMI_SCRAMBLING_MASK (TRANS_DDI_HDMI_SCRAMBLER_CTS_ENABLE \
 					| TRANS_DDI_HDMI_SCRAMBLER_RESET_FREQ \
 					| TRANS_DDI_HDMI_SCRAMBLING)
@@ -8658,28 +9029,29 @@ enum skl_power_gate {
 #define _DP_TP_CTL_A			0x64040
 #define _DP_TP_CTL_B			0x64140
 #define DP_TP_CTL(port) _MMIO_PORT(port, _DP_TP_CTL_A, _DP_TP_CTL_B)
-#define  DP_TP_CTL_ENABLE			(1<<31)
-#define  DP_TP_CTL_MODE_SST			(0<<27)
-#define  DP_TP_CTL_MODE_MST			(1<<27)
-#define  DP_TP_CTL_FORCE_ACT			(1<<25)
-#define  DP_TP_CTL_ENHANCED_FRAME_ENABLE	(1<<18)
-#define  DP_TP_CTL_FDI_AUTOTRAIN		(1<<15)
-#define  DP_TP_CTL_LINK_TRAIN_MASK		(7<<8)
-#define  DP_TP_CTL_LINK_TRAIN_PAT1		(0<<8)
-#define  DP_TP_CTL_LINK_TRAIN_PAT2		(1<<8)
-#define  DP_TP_CTL_LINK_TRAIN_PAT3		(4<<8)
-#define  DP_TP_CTL_LINK_TRAIN_IDLE		(2<<8)
-#define  DP_TP_CTL_LINK_TRAIN_NORMAL		(3<<8)
-#define  DP_TP_CTL_SCRAMBLE_DISABLE		(1<<7)
+#define  DP_TP_CTL_ENABLE			(1 << 31)
+#define  DP_TP_CTL_MODE_SST			(0 << 27)
+#define  DP_TP_CTL_MODE_MST			(1 << 27)
+#define  DP_TP_CTL_FORCE_ACT			(1 << 25)
+#define  DP_TP_CTL_ENHANCED_FRAME_ENABLE	(1 << 18)
+#define  DP_TP_CTL_FDI_AUTOTRAIN		(1 << 15)
+#define  DP_TP_CTL_LINK_TRAIN_MASK		(7 << 8)
+#define  DP_TP_CTL_LINK_TRAIN_PAT1		(0 << 8)
+#define  DP_TP_CTL_LINK_TRAIN_PAT2		(1 << 8)
+#define  DP_TP_CTL_LINK_TRAIN_PAT3		(4 << 8)
+#define  DP_TP_CTL_LINK_TRAIN_PAT4		(5 << 8)
+#define  DP_TP_CTL_LINK_TRAIN_IDLE		(2 << 8)
+#define  DP_TP_CTL_LINK_TRAIN_NORMAL		(3 << 8)
+#define  DP_TP_CTL_SCRAMBLE_DISABLE		(1 << 7)
 
 /* DisplayPort Transport Status */
 #define _DP_TP_STATUS_A			0x64044
 #define _DP_TP_STATUS_B			0x64144
 #define DP_TP_STATUS(port) _MMIO_PORT(port, _DP_TP_STATUS_A, _DP_TP_STATUS_B)
-#define  DP_TP_STATUS_IDLE_DONE			(1<<25)
-#define  DP_TP_STATUS_ACT_SENT			(1<<24)
-#define  DP_TP_STATUS_MODE_STATUS_MST		(1<<23)
-#define  DP_TP_STATUS_AUTOTRAIN_DONE		(1<<12)
+#define  DP_TP_STATUS_IDLE_DONE			(1 << 25)
+#define  DP_TP_STATUS_ACT_SENT			(1 << 24)
+#define  DP_TP_STATUS_MODE_STATUS_MST		(1 << 23)
+#define  DP_TP_STATUS_AUTOTRAIN_DONE		(1 << 12)
 #define  DP_TP_STATUS_PAYLOAD_MAPPING_VC2	(3 << 8)
 #define  DP_TP_STATUS_PAYLOAD_MAPPING_VC1	(3 << 4)
 #define  DP_TP_STATUS_PAYLOAD_MAPPING_VC0	(3 << 0)
@@ -8688,16 +9060,16 @@ enum skl_power_gate {
 #define _DDI_BUF_CTL_A				0x64000
 #define _DDI_BUF_CTL_B				0x64100
 #define DDI_BUF_CTL(port) _MMIO_PORT(port, _DDI_BUF_CTL_A, _DDI_BUF_CTL_B)
-#define  DDI_BUF_CTL_ENABLE			(1<<31)
+#define  DDI_BUF_CTL_ENABLE			(1 << 31)
 #define  DDI_BUF_TRANS_SELECT(n)	((n) << 24)
-#define  DDI_BUF_EMP_MASK			(0xf<<24)
-#define  DDI_BUF_PORT_REVERSAL			(1<<16)
-#define  DDI_BUF_IS_IDLE			(1<<7)
-#define  DDI_A_4_LANES				(1<<4)
+#define  DDI_BUF_EMP_MASK			(0xf << 24)
+#define  DDI_BUF_PORT_REVERSAL			(1 << 16)
+#define  DDI_BUF_IS_IDLE			(1 << 7)
+#define  DDI_A_4_LANES				(1 << 4)
 #define  DDI_PORT_WIDTH(width)			(((width) - 1) << 1)
 #define  DDI_PORT_WIDTH_MASK			(7 << 1)
 #define  DDI_PORT_WIDTH_SHIFT			1
-#define  DDI_INIT_DISPLAY_DETECTED		(1<<0)
+#define  DDI_INIT_DISPLAY_DETECTED		(1 << 0)
 
 /* DDI Buffer Translations */
 #define _DDI_BUF_TRANS_A		0x64E00
@@ -8712,95 +9084,99 @@ enum skl_power_gate {
 #define SBI_ADDR			_MMIO(0xC6000)
 #define SBI_DATA			_MMIO(0xC6004)
 #define SBI_CTL_STAT			_MMIO(0xC6008)
-#define  SBI_CTL_DEST_ICLK		(0x0<<16)
-#define  SBI_CTL_DEST_MPHY		(0x1<<16)
-#define  SBI_CTL_OP_IORD		(0x2<<8)
-#define  SBI_CTL_OP_IOWR		(0x3<<8)
-#define  SBI_CTL_OP_CRRD		(0x6<<8)
-#define  SBI_CTL_OP_CRWR		(0x7<<8)
-#define  SBI_RESPONSE_FAIL		(0x1<<1)
-#define  SBI_RESPONSE_SUCCESS		(0x0<<1)
-#define  SBI_BUSY			(0x1<<0)
-#define  SBI_READY			(0x0<<0)
+#define  SBI_CTL_DEST_ICLK		(0x0 << 16)
+#define  SBI_CTL_DEST_MPHY		(0x1 << 16)
+#define  SBI_CTL_OP_IORD		(0x2 << 8)
+#define  SBI_CTL_OP_IOWR		(0x3 << 8)
+#define  SBI_CTL_OP_CRRD		(0x6 << 8)
+#define  SBI_CTL_OP_CRWR		(0x7 << 8)
+#define  SBI_RESPONSE_FAIL		(0x1 << 1)
+#define  SBI_RESPONSE_SUCCESS		(0x0 << 1)
+#define  SBI_BUSY			(0x1 << 0)
+#define  SBI_READY			(0x0 << 0)
 
 /* SBI offsets */
 #define  SBI_SSCDIVINTPHASE			0x0200
 #define  SBI_SSCDIVINTPHASE6			0x0600
 #define   SBI_SSCDIVINTPHASE_DIVSEL_SHIFT	1
-#define   SBI_SSCDIVINTPHASE_DIVSEL_MASK	(0x7f<<1)
-#define   SBI_SSCDIVINTPHASE_DIVSEL(x)		((x)<<1)
+#define   SBI_SSCDIVINTPHASE_DIVSEL_MASK	(0x7f << 1)
+#define   SBI_SSCDIVINTPHASE_DIVSEL(x)		((x) << 1)
 #define   SBI_SSCDIVINTPHASE_INCVAL_SHIFT	8
-#define   SBI_SSCDIVINTPHASE_INCVAL_MASK	(0x7f<<8)
-#define   SBI_SSCDIVINTPHASE_INCVAL(x)		((x)<<8)
-#define   SBI_SSCDIVINTPHASE_DIR(x)		((x)<<15)
-#define   SBI_SSCDIVINTPHASE_PROPAGATE		(1<<0)
+#define   SBI_SSCDIVINTPHASE_INCVAL_MASK	(0x7f << 8)
+#define   SBI_SSCDIVINTPHASE_INCVAL(x)		((x) << 8)
+#define   SBI_SSCDIVINTPHASE_DIR(x)		((x) << 15)
+#define   SBI_SSCDIVINTPHASE_PROPAGATE		(1 << 0)
 #define  SBI_SSCDITHPHASE			0x0204
 #define  SBI_SSCCTL				0x020c
 #define  SBI_SSCCTL6				0x060C
-#define   SBI_SSCCTL_PATHALT			(1<<3)
-#define   SBI_SSCCTL_DISABLE			(1<<0)
+#define   SBI_SSCCTL_PATHALT			(1 << 3)
+#define   SBI_SSCCTL_DISABLE			(1 << 0)
 #define  SBI_SSCAUXDIV6				0x0610
 #define   SBI_SSCAUXDIV_FINALDIV2SEL_SHIFT	4
-#define   SBI_SSCAUXDIV_FINALDIV2SEL_MASK	(1<<4)
-#define   SBI_SSCAUXDIV_FINALDIV2SEL(x)		((x)<<4)
+#define   SBI_SSCAUXDIV_FINALDIV2SEL_MASK	(1 << 4)
+#define   SBI_SSCAUXDIV_FINALDIV2SEL(x)		((x) << 4)
 #define  SBI_DBUFF0				0x2a00
 #define  SBI_GEN0				0x1f00
-#define   SBI_GEN0_CFG_BUFFENABLE_DISABLE	(1<<0)
+#define   SBI_GEN0_CFG_BUFFENABLE_DISABLE	(1 << 0)
 
 /* LPT PIXCLK_GATE */
 #define PIXCLK_GATE			_MMIO(0xC6020)
-#define  PIXCLK_GATE_UNGATE		(1<<0)
-#define  PIXCLK_GATE_GATE		(0<<0)
+#define  PIXCLK_GATE_UNGATE		(1 << 0)
+#define  PIXCLK_GATE_GATE		(0 << 0)
 
 /* SPLL */
 #define SPLL_CTL			_MMIO(0x46020)
-#define  SPLL_PLL_ENABLE		(1<<31)
-#define  SPLL_PLL_SSC			(1<<28)
-#define  SPLL_PLL_NON_SSC		(2<<28)
-#define  SPLL_PLL_LCPLL			(3<<28)
-#define  SPLL_PLL_REF_MASK		(3<<28)
-#define  SPLL_PLL_FREQ_810MHz		(0<<26)
-#define  SPLL_PLL_FREQ_1350MHz		(1<<26)
-#define  SPLL_PLL_FREQ_2700MHz		(2<<26)
-#define  SPLL_PLL_FREQ_MASK		(3<<26)
+#define  SPLL_PLL_ENABLE		(1 << 31)
+#define  SPLL_PLL_SSC			(1 << 28)
+#define  SPLL_PLL_NON_SSC		(2 << 28)
+#define  SPLL_PLL_LCPLL			(3 << 28)
+#define  SPLL_PLL_REF_MASK		(3 << 28)
+#define  SPLL_PLL_FREQ_810MHz		(0 << 26)
+#define  SPLL_PLL_FREQ_1350MHz		(1 << 26)
+#define  SPLL_PLL_FREQ_2700MHz		(2 << 26)
+#define  SPLL_PLL_FREQ_MASK		(3 << 26)
 
 /* WRPLL */
 #define _WRPLL_CTL1			0x46040
 #define _WRPLL_CTL2			0x46060
 #define WRPLL_CTL(pll)			_MMIO_PIPE(pll, _WRPLL_CTL1, _WRPLL_CTL2)
-#define  WRPLL_PLL_ENABLE		(1<<31)
-#define  WRPLL_PLL_SSC			(1<<28)
-#define  WRPLL_PLL_NON_SSC		(2<<28)
-#define  WRPLL_PLL_LCPLL		(3<<28)
-#define  WRPLL_PLL_REF_MASK		(3<<28)
+#define  WRPLL_PLL_ENABLE		(1 << 31)
+#define  WRPLL_PLL_SSC			(1 << 28)
+#define  WRPLL_PLL_NON_SSC		(2 << 28)
+#define  WRPLL_PLL_LCPLL		(3 << 28)
+#define  WRPLL_PLL_REF_MASK		(3 << 28)
 /* WRPLL divider programming */
-#define  WRPLL_DIVIDER_REFERENCE(x)	((x)<<0)
+#define  WRPLL_DIVIDER_REFERENCE(x)	((x) << 0)
 #define  WRPLL_DIVIDER_REF_MASK		(0xff)
-#define  WRPLL_DIVIDER_POST(x)		((x)<<8)
-#define  WRPLL_DIVIDER_POST_MASK	(0x3f<<8)
+#define  WRPLL_DIVIDER_POST(x)		((x) << 8)
+#define  WRPLL_DIVIDER_POST_MASK	(0x3f << 8)
 #define  WRPLL_DIVIDER_POST_SHIFT	8
-#define  WRPLL_DIVIDER_FEEDBACK(x)	((x)<<16)
+#define  WRPLL_DIVIDER_FEEDBACK(x)	((x) << 16)
 #define  WRPLL_DIVIDER_FB_SHIFT		16
-#define  WRPLL_DIVIDER_FB_MASK		(0xff<<16)
+#define  WRPLL_DIVIDER_FB_MASK		(0xff << 16)
 
 /* Port clock selection */
 #define _PORT_CLK_SEL_A			0x46100
 #define _PORT_CLK_SEL_B			0x46104
 #define PORT_CLK_SEL(port) _MMIO_PORT(port, _PORT_CLK_SEL_A, _PORT_CLK_SEL_B)
-#define  PORT_CLK_SEL_LCPLL_2700	(0<<29)
-#define  PORT_CLK_SEL_LCPLL_1350	(1<<29)
-#define  PORT_CLK_SEL_LCPLL_810		(2<<29)
-#define  PORT_CLK_SEL_SPLL		(3<<29)
-#define  PORT_CLK_SEL_WRPLL(pll)	(((pll)+4)<<29)
-#define  PORT_CLK_SEL_WRPLL1		(4<<29)
-#define  PORT_CLK_SEL_WRPLL2		(5<<29)
-#define  PORT_CLK_SEL_NONE		(7<<29)
-#define  PORT_CLK_SEL_MASK		(7<<29)
+#define  PORT_CLK_SEL_LCPLL_2700	(0 << 29)
+#define  PORT_CLK_SEL_LCPLL_1350	(1 << 29)
+#define  PORT_CLK_SEL_LCPLL_810		(2 << 29)
+#define  PORT_CLK_SEL_SPLL		(3 << 29)
+#define  PORT_CLK_SEL_WRPLL(pll)	(((pll) + 4) << 29)
+#define  PORT_CLK_SEL_WRPLL1		(4 << 29)
+#define  PORT_CLK_SEL_WRPLL2		(5 << 29)
+#define  PORT_CLK_SEL_NONE		(7 << 29)
+#define  PORT_CLK_SEL_MASK		(7 << 29)
 
 /* On ICL+ this is the same as PORT_CLK_SEL, but all bits change. */
 #define DDI_CLK_SEL(port)		PORT_CLK_SEL(port)
 #define  DDI_CLK_SEL_NONE		(0x0 << 28)
 #define  DDI_CLK_SEL_MG			(0x8 << 28)
+#define  DDI_CLK_SEL_TBT_162		(0xC << 28)
+#define  DDI_CLK_SEL_TBT_270		(0xD << 28)
+#define  DDI_CLK_SEL_TBT_540		(0xE << 28)
+#define  DDI_CLK_SEL_TBT_810		(0xF << 28)
 #define  DDI_CLK_SEL_MASK		(0xF << 28)
 
 /* Transcoder clock selection */
@@ -8808,8 +9184,8 @@ enum skl_power_gate {
 #define _TRANS_CLK_SEL_B		0x46144
 #define TRANS_CLK_SEL(tran) _MMIO_TRANS(tran, _TRANS_CLK_SEL_A, _TRANS_CLK_SEL_B)
 /* For each transcoder, we need to select the corresponding port clock */
-#define  TRANS_CLK_SEL_DISABLED		(0x0<<29)
-#define  TRANS_CLK_SEL_PORT(x)		(((x)+1)<<29)
+#define  TRANS_CLK_SEL_DISABLED		(0x0 << 29)
+#define  TRANS_CLK_SEL_PORT(x)		(((x) + 1) << 29)
 
 #define CDCLK_FREQ			_MMIO(0x46200)
 
@@ -8819,28 +9195,28 @@ enum skl_power_gate {
 #define _TRANS_EDP_MSA_MISC		0x6f410
 #define TRANS_MSA_MISC(tran) _MMIO_TRANS2(tran, _TRANSA_MSA_MISC)
 
-#define  TRANS_MSA_SYNC_CLK		(1<<0)
-#define  TRANS_MSA_6_BPC		(0<<5)
-#define  TRANS_MSA_8_BPC		(1<<5)
-#define  TRANS_MSA_10_BPC		(2<<5)
-#define  TRANS_MSA_12_BPC		(3<<5)
-#define  TRANS_MSA_16_BPC		(4<<5)
+#define  TRANS_MSA_SYNC_CLK		(1 << 0)
+#define  TRANS_MSA_6_BPC		(0 << 5)
+#define  TRANS_MSA_8_BPC		(1 << 5)
+#define  TRANS_MSA_10_BPC		(2 << 5)
+#define  TRANS_MSA_12_BPC		(3 << 5)
+#define  TRANS_MSA_16_BPC		(4 << 5)
 
 /* LCPLL Control */
 #define LCPLL_CTL			_MMIO(0x130040)
-#define  LCPLL_PLL_DISABLE		(1<<31)
-#define  LCPLL_PLL_LOCK			(1<<30)
-#define  LCPLL_CLK_FREQ_MASK		(3<<26)
-#define  LCPLL_CLK_FREQ_450		(0<<26)
-#define  LCPLL_CLK_FREQ_54O_BDW		(1<<26)
-#define  LCPLL_CLK_FREQ_337_5_BDW	(2<<26)
-#define  LCPLL_CLK_FREQ_675_BDW		(3<<26)
-#define  LCPLL_CD_CLOCK_DISABLE		(1<<25)
-#define  LCPLL_ROOT_CD_CLOCK_DISABLE	(1<<24)
-#define  LCPLL_CD2X_CLOCK_DISABLE	(1<<23)
-#define  LCPLL_POWER_DOWN_ALLOW		(1<<22)
-#define  LCPLL_CD_SOURCE_FCLK		(1<<21)
-#define  LCPLL_CD_SOURCE_FCLK_DONE	(1<<19)
+#define  LCPLL_PLL_DISABLE		(1 << 31)
+#define  LCPLL_PLL_LOCK			(1 << 30)
+#define  LCPLL_CLK_FREQ_MASK		(3 << 26)
+#define  LCPLL_CLK_FREQ_450		(0 << 26)
+#define  LCPLL_CLK_FREQ_54O_BDW		(1 << 26)
+#define  LCPLL_CLK_FREQ_337_5_BDW	(2 << 26)
+#define  LCPLL_CLK_FREQ_675_BDW		(3 << 26)
+#define  LCPLL_CD_CLOCK_DISABLE		(1 << 25)
+#define  LCPLL_ROOT_CD_CLOCK_DISABLE	(1 << 24)
+#define  LCPLL_CD2X_CLOCK_DISABLE	(1 << 23)
+#define  LCPLL_POWER_DOWN_ALLOW		(1 << 22)
+#define  LCPLL_CD_SOURCE_FCLK		(1 << 21)
+#define  LCPLL_CD_SOURCE_FCLK_DONE	(1 << 19)
 
 /*
  * SKL Clocks
@@ -8868,16 +9244,16 @@ enum skl_power_gate {
 /* LCPLL_CTL */
 #define LCPLL1_CTL		_MMIO(0x46010)
 #define LCPLL2_CTL		_MMIO(0x46014)
-#define  LCPLL_PLL_ENABLE	(1<<31)
+#define  LCPLL_PLL_ENABLE	(1 << 31)
 
 /* DPLL control1 */
 #define DPLL_CTRL1		_MMIO(0x6C058)
-#define  DPLL_CTRL1_HDMI_MODE(id)		(1<<((id)*6+5))
-#define  DPLL_CTRL1_SSC(id)			(1<<((id)*6+4))
-#define  DPLL_CTRL1_LINK_RATE_MASK(id)		(7<<((id)*6+1))
-#define  DPLL_CTRL1_LINK_RATE_SHIFT(id)		((id)*6+1)
-#define  DPLL_CTRL1_LINK_RATE(linkrate, id)	((linkrate)<<((id)*6+1))
-#define  DPLL_CTRL1_OVERRIDE(id)		(1<<((id)*6))
+#define  DPLL_CTRL1_HDMI_MODE(id)		(1 << ((id) * 6 + 5))
+#define  DPLL_CTRL1_SSC(id)			(1 << ((id) * 6 + 4))
+#define  DPLL_CTRL1_LINK_RATE_MASK(id)		(7 << ((id) * 6 + 1))
+#define  DPLL_CTRL1_LINK_RATE_SHIFT(id)		((id) * 6 + 1)
+#define  DPLL_CTRL1_LINK_RATE(linkrate, id)	((linkrate) << ((id) * 6 + 1))
+#define  DPLL_CTRL1_OVERRIDE(id)		(1 << ((id) * 6))
 #define  DPLL_CTRL1_LINK_RATE_2700		0
 #define  DPLL_CTRL1_LINK_RATE_1350		1
 #define  DPLL_CTRL1_LINK_RATE_810		2
@@ -8887,43 +9263,43 @@ enum skl_power_gate {
 
 /* DPLL control2 */
 #define DPLL_CTRL2				_MMIO(0x6C05C)
-#define  DPLL_CTRL2_DDI_CLK_OFF(port)		(1<<((port)+15))
-#define  DPLL_CTRL2_DDI_CLK_SEL_MASK(port)	(3<<((port)*3+1))
-#define  DPLL_CTRL2_DDI_CLK_SEL_SHIFT(port)    ((port)*3+1)
-#define  DPLL_CTRL2_DDI_CLK_SEL(clk, port)	((clk)<<((port)*3+1))
-#define  DPLL_CTRL2_DDI_SEL_OVERRIDE(port)     (1<<((port)*3))
+#define  DPLL_CTRL2_DDI_CLK_OFF(port)		(1 << ((port) + 15))
+#define  DPLL_CTRL2_DDI_CLK_SEL_MASK(port)	(3 << ((port) * 3 + 1))
+#define  DPLL_CTRL2_DDI_CLK_SEL_SHIFT(port)    ((port) * 3 + 1)
+#define  DPLL_CTRL2_DDI_CLK_SEL(clk, port)	((clk) << ((port) * 3 + 1))
+#define  DPLL_CTRL2_DDI_SEL_OVERRIDE(port)     (1 << ((port) * 3))
 
 /* DPLL Status */
 #define DPLL_STATUS	_MMIO(0x6C060)
-#define  DPLL_LOCK(id) (1<<((id)*8))
+#define  DPLL_LOCK(id) (1 << ((id) * 8))
 
 /* DPLL cfg */
 #define _DPLL1_CFGCR1	0x6C040
 #define _DPLL2_CFGCR1	0x6C048
 #define _DPLL3_CFGCR1	0x6C050
-#define  DPLL_CFGCR1_FREQ_ENABLE	(1<<31)
-#define  DPLL_CFGCR1_DCO_FRACTION_MASK	(0x7fff<<9)
-#define  DPLL_CFGCR1_DCO_FRACTION(x)	((x)<<9)
+#define  DPLL_CFGCR1_FREQ_ENABLE	(1 << 31)
+#define  DPLL_CFGCR1_DCO_FRACTION_MASK	(0x7fff << 9)
+#define  DPLL_CFGCR1_DCO_FRACTION(x)	((x) << 9)
 #define  DPLL_CFGCR1_DCO_INTEGER_MASK	(0x1ff)
 
 #define _DPLL1_CFGCR2	0x6C044
 #define _DPLL2_CFGCR2	0x6C04C
 #define _DPLL3_CFGCR2	0x6C054
-#define  DPLL_CFGCR2_QDIV_RATIO_MASK	(0xff<<8)
-#define  DPLL_CFGCR2_QDIV_RATIO(x)	((x)<<8)
-#define  DPLL_CFGCR2_QDIV_MODE(x)	((x)<<7)
-#define  DPLL_CFGCR2_KDIV_MASK		(3<<5)
-#define  DPLL_CFGCR2_KDIV(x)		((x)<<5)
-#define  DPLL_CFGCR2_KDIV_5 (0<<5)
-#define  DPLL_CFGCR2_KDIV_2 (1<<5)
-#define  DPLL_CFGCR2_KDIV_3 (2<<5)
-#define  DPLL_CFGCR2_KDIV_1 (3<<5)
-#define  DPLL_CFGCR2_PDIV_MASK		(7<<2)
-#define  DPLL_CFGCR2_PDIV(x)		((x)<<2)
-#define  DPLL_CFGCR2_PDIV_1 (0<<2)
-#define  DPLL_CFGCR2_PDIV_2 (1<<2)
-#define  DPLL_CFGCR2_PDIV_3 (2<<2)
-#define  DPLL_CFGCR2_PDIV_7 (4<<2)
+#define  DPLL_CFGCR2_QDIV_RATIO_MASK	(0xff << 8)
+#define  DPLL_CFGCR2_QDIV_RATIO(x)	((x) << 8)
+#define  DPLL_CFGCR2_QDIV_MODE(x)	((x) << 7)
+#define  DPLL_CFGCR2_KDIV_MASK		(3 << 5)
+#define  DPLL_CFGCR2_KDIV(x)		((x) << 5)
+#define  DPLL_CFGCR2_KDIV_5 (0 << 5)
+#define  DPLL_CFGCR2_KDIV_2 (1 << 5)
+#define  DPLL_CFGCR2_KDIV_3 (2 << 5)
+#define  DPLL_CFGCR2_KDIV_1 (3 << 5)
+#define  DPLL_CFGCR2_PDIV_MASK		(7 << 2)
+#define  DPLL_CFGCR2_PDIV(x)		((x) << 2)
+#define  DPLL_CFGCR2_PDIV_1 (0 << 2)
+#define  DPLL_CFGCR2_PDIV_2 (1 << 2)
+#define  DPLL_CFGCR2_PDIV_3 (2 << 2)
+#define  DPLL_CFGCR2_PDIV_7 (4 << 2)
 #define  DPLL_CFGCR2_CENTRAL_FREQ_MASK	(3)
 
 #define DPLL_CFGCR1(id)	_MMIO_PIPE((id) - SKL_DPLL1, _DPLL1_CFGCR1, _DPLL2_CFGCR1)
@@ -8935,9 +9311,9 @@ enum skl_power_gate {
 #define DPCLKA_CFGCR0				_MMIO(0x6C200)
 #define DPCLKA_CFGCR0_ICL			_MMIO(0x164280)
 #define  DPCLKA_CFGCR0_DDI_CLK_OFF(port)	(1 << ((port) ==  PORT_F ? 23 : \
-						      (port)+10))
+						      (port) + 10))
 #define  DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(port)	((port) == PORT_F ? 21 : \
-						(port)*2)
+						(port) * 2)
 #define  DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(port)	(3 << DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(port))
 #define  DPCLKA_CFGCR0_DDI_CLK_SEL(pll, port)	((pll) << DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(port))
 
@@ -8950,6 +9326,8 @@ enum skl_power_gate {
 #define  PLL_POWER_STATE	(1 << 26)
 #define CNL_DPLL_ENABLE(pll)	_MMIO_PLL(pll, DPLL0_ENABLE, DPLL1_ENABLE)
 
+#define TBT_PLL_ENABLE		_MMIO(0x46020)
+
 #define _MG_PLL1_ENABLE		0x46030
 #define _MG_PLL2_ENABLE		0x46034
 #define _MG_PLL3_ENABLE		0x46038
@@ -8963,6 +9341,7 @@ enum skl_power_gate {
 #define _MG_REFCLKIN_CTL_PORT3				0x16A92C
 #define _MG_REFCLKIN_CTL_PORT4				0x16B92C
 #define   MG_REFCLKIN_CTL_OD_2_MUX(x)			((x) << 8)
+#define   MG_REFCLKIN_CTL_OD_2_MUX_MASK			(0x7 << 8)
 #define MG_REFCLKIN_CTL(port) _MMIO_PORT((port) - PORT_C, \
 					 _MG_REFCLKIN_CTL_PORT1, \
 					 _MG_REFCLKIN_CTL_PORT2)
@@ -8972,7 +9351,9 @@ enum skl_power_gate {
 #define _MG_CLKTOP2_CORECLKCTL1_PORT3			0x16A8D8
 #define _MG_CLKTOP2_CORECLKCTL1_PORT4			0x16B8D8
 #define   MG_CLKTOP2_CORECLKCTL1_B_DIVRATIO(x)		((x) << 16)
+#define   MG_CLKTOP2_CORECLKCTL1_B_DIVRATIO_MASK	(0xff << 16)
 #define   MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO(x)		((x) << 8)
+#define   MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK	(0xff << 8)
 #define MG_CLKTOP2_CORECLKCTL1(port) _MMIO_PORT((port) - PORT_C, \
 						_MG_CLKTOP2_CORECLKCTL1_PORT1, \
 						_MG_CLKTOP2_CORECLKCTL1_PORT2)
@@ -8982,9 +9363,13 @@ enum skl_power_gate {
 #define _MG_CLKTOP2_HSCLKCTL_PORT3			0x16A8D4
 #define _MG_CLKTOP2_HSCLKCTL_PORT4			0x16B8D4
 #define   MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL(x)		((x) << 16)
+#define   MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL_MASK	(0x1 << 16)
 #define   MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL(x)	((x) << 14)
+#define   MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL_MASK	(0x3 << 14)
 #define   MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO(x)		((x) << 12)
+#define   MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO_MASK		(0x3 << 12)
 #define   MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO(x)		((x) << 8)
+#define   MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO_MASK		(0xf << 8)
 #define MG_CLKTOP2_HSCLKCTL(port) _MMIO_PORT((port) - PORT_C, \
 					     _MG_CLKTOP2_HSCLKCTL_PORT1, \
 					     _MG_CLKTOP2_HSCLKCTL_PORT2)
@@ -9058,12 +9443,18 @@ enum skl_power_gate {
 #define _MG_PLL_BIAS_PORT3				0x16AA14
 #define _MG_PLL_BIAS_PORT4				0x16BA14
 #define   MG_PLL_BIAS_BIAS_GB_SEL(x)			((x) << 30)
+#define   MG_PLL_BIAS_BIAS_GB_SEL_MASK			(0x3 << 30)
 #define   MG_PLL_BIAS_INIT_DCOAMP(x)			((x) << 24)
+#define   MG_PLL_BIAS_INIT_DCOAMP_MASK			(0x3f << 24)
 #define   MG_PLL_BIAS_BIAS_BONUS(x)			((x) << 16)
+#define   MG_PLL_BIAS_BIAS_BONUS_MASK			(0xff << 16)
 #define   MG_PLL_BIAS_BIASCAL_EN			(1 << 15)
 #define   MG_PLL_BIAS_CTRIM(x)				((x) << 8)
+#define   MG_PLL_BIAS_CTRIM_MASK			(0x1f << 8)
 #define   MG_PLL_BIAS_VREF_RDAC(x)			((x) << 5)
+#define   MG_PLL_BIAS_VREF_RDAC_MASK			(0x7 << 5)
 #define   MG_PLL_BIAS_IREFTRIM(x)			((x) << 0)
+#define   MG_PLL_BIAS_IREFTRIM_MASK			(0x1f << 0)
 #define MG_PLL_BIAS(port) _MMIO_PORT((port) - PORT_C, _MG_PLL_BIAS_PORT1, \
 				     _MG_PLL_BIAS_PORT2)
 
@@ -9105,13 +9496,16 @@ enum skl_power_gate {
 #define  DPLL_CFGCR1_QDIV_RATIO_MASK	(0xff << 10)
 #define  DPLL_CFGCR1_QDIV_RATIO_SHIFT	(10)
 #define  DPLL_CFGCR1_QDIV_RATIO(x)	((x) << 10)
+#define  DPLL_CFGCR1_QDIV_MODE_SHIFT	(9)
 #define  DPLL_CFGCR1_QDIV_MODE(x)	((x) << 9)
 #define  DPLL_CFGCR1_KDIV_MASK		(7 << 6)
+#define  DPLL_CFGCR1_KDIV_SHIFT		(6)
 #define  DPLL_CFGCR1_KDIV(x)		((x) << 6)
 #define  DPLL_CFGCR1_KDIV_1		(1 << 6)
 #define  DPLL_CFGCR1_KDIV_2		(2 << 6)
 #define  DPLL_CFGCR1_KDIV_4		(4 << 6)
 #define  DPLL_CFGCR1_PDIV_MASK		(0xf << 2)
+#define  DPLL_CFGCR1_PDIV_SHIFT		(2)
 #define  DPLL_CFGCR1_PDIV(x)		((x) << 2)
 #define  DPLL_CFGCR1_PDIV_2		(1 << 2)
 #define  DPLL_CFGCR1_PDIV_3		(2 << 2)
@@ -9145,22 +9539,22 @@ enum skl_power_gate {
 /* GEN9 DC */
 #define DC_STATE_EN			_MMIO(0x45504)
 #define  DC_STATE_DISABLE		0
-#define  DC_STATE_EN_UPTO_DC5		(1<<0)
-#define  DC_STATE_EN_DC9		(1<<3)
-#define  DC_STATE_EN_UPTO_DC6		(2<<0)
+#define  DC_STATE_EN_UPTO_DC5		(1 << 0)
+#define  DC_STATE_EN_DC9		(1 << 3)
+#define  DC_STATE_EN_UPTO_DC6		(2 << 0)
 #define  DC_STATE_EN_UPTO_DC5_DC6_MASK   0x3
 
 #define  DC_STATE_DEBUG                  _MMIO(0x45520)
-#define  DC_STATE_DEBUG_MASK_CORES	(1<<0)
-#define  DC_STATE_DEBUG_MASK_MEMORY_UP	(1<<1)
+#define  DC_STATE_DEBUG_MASK_CORES	(1 << 0)
+#define  DC_STATE_DEBUG_MASK_MEMORY_UP	(1 << 1)
 
 /* Please see hsw_read_dcomp() and hsw_write_dcomp() before using this register,
  * since on HSW we can't write to it using I915_WRITE. */
 #define D_COMP_HSW			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5F0C)
 #define D_COMP_BDW			_MMIO(0x138144)
-#define  D_COMP_RCOMP_IN_PROGRESS	(1<<9)
-#define  D_COMP_COMP_FORCE		(1<<8)
-#define  D_COMP_COMP_DISABLE		(1<<0)
+#define  D_COMP_RCOMP_IN_PROGRESS	(1 << 9)
+#define  D_COMP_COMP_FORCE		(1 << 8)
+#define  D_COMP_COMP_DISABLE		(1 << 0)
 
 /* Pipe WM_LINETIME - watermark line time */
 #define _PIPE_WM_LINETIME_A		0x45270
@@ -9168,27 +9562,27 @@ enum skl_power_gate {
 #define PIPE_WM_LINETIME(pipe) _MMIO_PIPE(pipe, _PIPE_WM_LINETIME_A, _PIPE_WM_LINETIME_B)
 #define   PIPE_WM_LINETIME_MASK			(0x1ff)
 #define   PIPE_WM_LINETIME_TIME(x)		((x))
-#define   PIPE_WM_LINETIME_IPS_LINETIME_MASK	(0x1ff<<16)
-#define   PIPE_WM_LINETIME_IPS_LINETIME(x)	((x)<<16)
+#define   PIPE_WM_LINETIME_IPS_LINETIME_MASK	(0x1ff << 16)
+#define   PIPE_WM_LINETIME_IPS_LINETIME(x)	((x) << 16)
 
 /* SFUSE_STRAP */
 #define SFUSE_STRAP			_MMIO(0xc2014)
-#define  SFUSE_STRAP_FUSE_LOCK		(1<<13)
-#define  SFUSE_STRAP_RAW_FREQUENCY	(1<<8)
-#define  SFUSE_STRAP_DISPLAY_DISABLED	(1<<7)
-#define  SFUSE_STRAP_CRT_DISABLED	(1<<6)
-#define  SFUSE_STRAP_DDIF_DETECTED	(1<<3)
-#define  SFUSE_STRAP_DDIB_DETECTED	(1<<2)
-#define  SFUSE_STRAP_DDIC_DETECTED	(1<<1)
-#define  SFUSE_STRAP_DDID_DETECTED	(1<<0)
+#define  SFUSE_STRAP_FUSE_LOCK		(1 << 13)
+#define  SFUSE_STRAP_RAW_FREQUENCY	(1 << 8)
+#define  SFUSE_STRAP_DISPLAY_DISABLED	(1 << 7)
+#define  SFUSE_STRAP_CRT_DISABLED	(1 << 6)
+#define  SFUSE_STRAP_DDIF_DETECTED	(1 << 3)
+#define  SFUSE_STRAP_DDIB_DETECTED	(1 << 2)
+#define  SFUSE_STRAP_DDIC_DETECTED	(1 << 1)
+#define  SFUSE_STRAP_DDID_DETECTED	(1 << 0)
 
 #define WM_MISC				_MMIO(0x45260)
 #define  WM_MISC_DATA_PARTITION_5_6	(1 << 0)
 
 #define WM_DBG				_MMIO(0x45280)
-#define  WM_DBG_DISALLOW_MULTIPLE_LP	(1<<0)
-#define  WM_DBG_DISALLOW_MAXFIFO	(1<<1)
-#define  WM_DBG_DISALLOW_SPRITE		(1<<2)
+#define  WM_DBG_DISALLOW_MULTIPLE_LP	(1 << 0)
+#define  WM_DBG_DISALLOW_MAXFIFO	(1 << 1)
+#define  WM_DBG_DISALLOW_SPRITE		(1 << 2)
 
 /* pipe CSC */
 #define _PIPE_A_CSC_COEFF_RY_GY	0x49010
@@ -9314,6 +9708,22 @@ enum skl_power_gate {
 #define MIPIO_TXESC_CLK_DIV2			_MMIO(0x160008)
 #define  GLK_TX_ESC_CLK_DIV2_MASK			0x3FF
 
+#define _ICL_DSI_ESC_CLK_DIV0		0x6b090
+#define _ICL_DSI_ESC_CLK_DIV1		0x6b890
+#define ICL_DSI_ESC_CLK_DIV(port)	_MMIO_PORT((port),	\
+							_ICL_DSI_ESC_CLK_DIV0, \
+							_ICL_DSI_ESC_CLK_DIV1)
+#define _ICL_DPHY_ESC_CLK_DIV0		0x162190
+#define _ICL_DPHY_ESC_CLK_DIV1		0x6C190
+#define ICL_DPHY_ESC_CLK_DIV(port)	_MMIO_PORT((port),	\
+						_ICL_DPHY_ESC_CLK_DIV0, \
+						_ICL_DPHY_ESC_CLK_DIV1)
+#define  ICL_BYTE_CLK_PER_ESC_CLK_MASK		(0x1f << 16)
+#define  ICL_BYTE_CLK_PER_ESC_CLK_SHIFT	16
+#define  ICL_ESC_CLK_DIV_MASK			0x1ff
+#define  ICL_ESC_CLK_DIV_SHIFT			0
+#define DSI_MAX_ESC_CLK			20000		/* in KHz */
+
 /* Gen4+ Timestamp and Pipe Frame time stamp registers */
 #define GEN4_TIMESTAMP		_MMIO(0x2358)
 #define ILK_TIMESTAMP_HI	_MMIO(0x70070)
@@ -9351,7 +9761,7 @@ enum skl_power_gate {
 			_MIPI_PORT(port, BXT_MIPI1_TX_ESCLK_FIXDIV_MASK, \
 					BXT_MIPI2_TX_ESCLK_FIXDIV_MASK)
 #define  BXT_MIPI_TX_ESCLK_DIVIDER(port, val)	\
-		((val & 0x3F) << BXT_MIPI_TX_ESCLK_SHIFT(port))
+		(((val) & 0x3F) << BXT_MIPI_TX_ESCLK_SHIFT(port))
 /* RX upper control divider to select actual RX clock output from 8x */
 #define  BXT_MIPI1_RX_ESCLK_UPPER_SHIFT		21
 #define  BXT_MIPI2_RX_ESCLK_UPPER_SHIFT		5
@@ -9364,7 +9774,7 @@ enum skl_power_gate {
 			_MIPI_PORT(port, BXT_MIPI1_RX_ESCLK_UPPER_FIXDIV_MASK, \
 					BXT_MIPI2_RX_ESCLK_UPPER_FIXDIV_MASK)
 #define  BXT_MIPI_RX_ESCLK_UPPER_DIVIDER(port, val)	\
-		((val & 3) << BXT_MIPI_RX_ESCLK_UPPER_SHIFT(port))
+		(((val) & 3) << BXT_MIPI_RX_ESCLK_UPPER_SHIFT(port))
 /* 8/3X divider to select the actual 8/3X clock output from 8x */
 #define  BXT_MIPI1_8X_BY3_SHIFT                19
 #define  BXT_MIPI2_8X_BY3_SHIFT                3
@@ -9377,7 +9787,7 @@ enum skl_power_gate {
 			_MIPI_PORT(port, BXT_MIPI1_8X_BY3_DIVIDER_MASK, \
 						BXT_MIPI2_8X_BY3_DIVIDER_MASK)
 #define  BXT_MIPI_8X_BY3_DIVIDER(port, val)    \
-			((val & 3) << BXT_MIPI_8X_BY3_SHIFT(port))
+			(((val) & 3) << BXT_MIPI_8X_BY3_SHIFT(port))
 /* RX lower control divider to select actual RX clock output from 8x */
 #define  BXT_MIPI1_RX_ESCLK_LOWER_SHIFT		16
 #define  BXT_MIPI2_RX_ESCLK_LOWER_SHIFT		0
@@ -9390,7 +9800,7 @@ enum skl_power_gate {
 			_MIPI_PORT(port, BXT_MIPI1_RX_ESCLK_LOWER_FIXDIV_MASK, \
 					BXT_MIPI2_RX_ESCLK_LOWER_FIXDIV_MASK)
 #define  BXT_MIPI_RX_ESCLK_LOWER_DIVIDER(port, val)	\
-		((val & 3) << BXT_MIPI_RX_ESCLK_LOWER_SHIFT(port))
+		(((val) & 3) << BXT_MIPI_RX_ESCLK_LOWER_SHIFT(port))
 
 #define RX_DIVIDER_BIT_1_2                     0x3
 #define RX_DIVIDER_BIT_3_4                     0xC
@@ -9448,6 +9858,14 @@ enum skl_power_gate {
 #define _BXT_MIPIC_PORT_CTRL				0x6B8C0
 #define BXT_MIPI_PORT_CTRL(tc)	_MMIO_MIPI(tc, _BXT_MIPIA_PORT_CTRL, _BXT_MIPIC_PORT_CTRL)
 
+/* ICL DSI MODE control */
+#define _ICL_DSI_IO_MODECTL_0				0x6B094
+#define _ICL_DSI_IO_MODECTL_1				0x6B894
+#define ICL_DSI_IO_MODECTL(port)	_MMIO_PORT(port,	\
+						    _ICL_DSI_IO_MODECTL_0, \
+						    _ICL_DSI_IO_MODECTL_1)
+#define  COMBO_PHY_MODE_DSI				(1 << 0)
+
 #define BXT_P_DSI_REGULATOR_CFG			_MMIO(0x160020)
 #define  STAP_SELECT					(1 << 0)
 
@@ -9927,4 +10345,310 @@ enum skl_power_gate {
 						 _ICL_PHY_MISC_B)
 #define  ICL_PHY_MISC_DE_IO_COMP_PWR_DOWN	(1 << 23)
 
+/* Icelake Display Stream Compression Registers */
+#define DSCA_PICTURE_PARAMETER_SET_0		0x6B200
+#define DSCC_PICTURE_PARAMETER_SET_0		0x6BA00
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_0_PB	0x78270
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_0_PB	0x78370
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_0_PC	0x78470
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_0_PC	0x78570
+#define ICL_DSC0_PICTURE_PARAMETER_SET_0(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_0_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_0_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_0(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_0_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_0_PC)
+#define  DSC_VBR_ENABLE			(1 << 19)
+#define  DSC_422_ENABLE			(1 << 18)
+#define  DSC_COLOR_SPACE_CONVERSION	(1 << 17)
+#define  DSC_BLOCK_PREDICTION		(1 << 16)
+#define  DSC_LINE_BUF_DEPTH_SHIFT	12
+#define  DSC_BPC_SHIFT			8
+#define  DSC_VER_MIN_SHIFT		4
+#define  DSC_VER_MAJ			(0x1 << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_1		0x6B204
+#define DSCC_PICTURE_PARAMETER_SET_1		0x6BA04
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_1_PB	0x78274
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_1_PB	0x78374
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_1_PC	0x78474
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_1_PC	0x78574
+#define ICL_DSC0_PICTURE_PARAMETER_SET_1(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_1_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_1_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_1(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_1_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_1_PC)
+#define  DSC_BPP(bpp)				((bpp) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_2		0x6B208
+#define DSCC_PICTURE_PARAMETER_SET_2		0x6BA08
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_2_PB	0x78278
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_2_PB	0x78378
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_2_PC	0x78478
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_2_PC	0x78578
+#define ICL_DSC0_PICTURE_PARAMETER_SET_2(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_2_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_2_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_2(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+					    _ICL_DSC1_PICTURE_PARAMETER_SET_2_PB, \
+					    _ICL_DSC1_PICTURE_PARAMETER_SET_2_PC)
+#define  DSC_PIC_WIDTH(pic_width)	((pic_width) << 16)
+#define  DSC_PIC_HEIGHT(pic_height)	((pic_height) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_3		0x6B20C
+#define DSCC_PICTURE_PARAMETER_SET_3		0x6BA0C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_3_PB	0x7827C
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_3_PB	0x7837C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_3_PC	0x7847C
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_3_PC	0x7857C
+#define ICL_DSC0_PICTURE_PARAMETER_SET_3(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_3_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_3_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_3(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_3_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_3_PC)
+#define  DSC_SLICE_WIDTH(slice_width)   ((slice_width) << 16)
+#define  DSC_SLICE_HEIGHT(slice_height) ((slice_height) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_4		0x6B210
+#define DSCC_PICTURE_PARAMETER_SET_4		0x6BA10
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_4_PB	0x78280
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_4_PB	0x78380
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_4_PC	0x78480
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_4_PC	0x78580
+#define ICL_DSC0_PICTURE_PARAMETER_SET_4(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_4_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_4_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_4(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_4_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_4_PC)
+#define  DSC_INITIAL_DEC_DELAY(dec_delay)       ((dec_delay) << 16)
+#define  DSC_INITIAL_XMIT_DELAY(xmit_delay)     ((xmit_delay) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_5		0x6B214
+#define DSCC_PICTURE_PARAMETER_SET_5		0x6BA14
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_5_PB	0x78284
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_5_PB	0x78384
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_5_PC	0x78484
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_5_PC	0x78584
+#define ICL_DSC0_PICTURE_PARAMETER_SET_5(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_5_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_5_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_5(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_5_PC, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_5_PC)
+#define  DSC_SCALE_DEC_INTINT(scale_dec)	((scale_dec) << 16)
+#define  DSC_SCALE_INC_INT(scale_inc)		((scale_inc) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_6		0x6B218
+#define DSCC_PICTURE_PARAMETER_SET_6		0x6BA18
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_6_PB	0x78288
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_6_PB	0x78388
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_6_PC	0x78488
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_6_PC	0x78588
+#define ICL_DSC0_PICTURE_PARAMETER_SET_6(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_6_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_6_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_6(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_6_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_6_PC)
+#define  DSC_FLATNESS_MAX_QP(max_qp)		(qp << 24)
+#define  DSC_FLATNESS_MIN_QP(min_qp)		(qp << 16)
+#define  DSC_FIRST_LINE_BPG_OFFSET(offset)	((offset) << 8)
+#define  DSC_INITIAL_SCALE_VALUE(value)		((value) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_7		0x6B21C
+#define DSCC_PICTURE_PARAMETER_SET_7		0x6BA1C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_7_PB	0x7828C
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_7_PB	0x7838C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_7_PC	0x7848C
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_7_PC	0x7858C
+#define ICL_DSC0_PICTURE_PARAMETER_SET_7(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							    _ICL_DSC0_PICTURE_PARAMETER_SET_7_PB, \
+							    _ICL_DSC0_PICTURE_PARAMETER_SET_7_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_7(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							    _ICL_DSC1_PICTURE_PARAMETER_SET_7_PB, \
+							    _ICL_DSC1_PICTURE_PARAMETER_SET_7_PC)
+#define  DSC_NFL_BPG_OFFSET(bpg_offset)		((bpg_offset) << 16)
+#define  DSC_SLICE_BPG_OFFSET(bpg_offset)	((bpg_offset) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_8		0x6B220
+#define DSCC_PICTURE_PARAMETER_SET_8		0x6BA20
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_8_PB	0x78290
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_8_PB	0x78390
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_8_PC	0x78490
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_8_PC	0x78590
+#define ICL_DSC0_PICTURE_PARAMETER_SET_8(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_8_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_8_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_8(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_8_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_8_PC)
+#define  DSC_INITIAL_OFFSET(initial_offset)		((initial_offset) << 16)
+#define  DSC_FINAL_OFFSET(final_offset)			((final_offset) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_9		0x6B224
+#define DSCC_PICTURE_PARAMETER_SET_9		0x6BA24
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_9_PB	0x78294
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_9_PB	0x78394
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_9_PC	0x78494
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_9_PC	0x78594
+#define ICL_DSC0_PICTURE_PARAMETER_SET_9(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_9_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_9_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_9(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_9_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_9_PC)
+#define  DSC_RC_EDGE_FACTOR(rc_edge_fact)	((rc_edge_fact) << 16)
+#define  DSC_RC_MODEL_SIZE(rc_model_size)	((rc_model_size) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_10		0x6B228
+#define DSCC_PICTURE_PARAMETER_SET_10		0x6BA28
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_10_PB	0x78298
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_10_PB	0x78398
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_10_PC	0x78498
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_10_PC	0x78598
+#define ICL_DSC0_PICTURE_PARAMETER_SET_10(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_10_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_10_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_10(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_10_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_10_PC)
+#define  DSC_RC_TARGET_OFF_LOW(rc_tgt_off_low)		((rc_tgt_off_low) << 20)
+#define  DSC_RC_TARGET_OFF_HIGH(rc_tgt_off_high)	((rc_tgt_off_high) << 16)
+#define  DSC_RC_QUANT_INC_LIMIT1(lim)			((lim) << 8)
+#define  DSC_RC_QUANT_INC_LIMIT0(lim)			((lim) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_11		0x6B22C
+#define DSCC_PICTURE_PARAMETER_SET_11		0x6BA2C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_11_PB	0x7829C
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_11_PB	0x7839C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_11_PC	0x7849C
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_11_PC	0x7859C
+#define ICL_DSC0_PICTURE_PARAMETER_SET_11(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_11_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_11_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_11(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_11_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_11_PC)
+
+#define DSCA_PICTURE_PARAMETER_SET_12		0x6B260
+#define DSCC_PICTURE_PARAMETER_SET_12		0x6BA60
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_12_PB	0x782A0
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_12_PB	0x783A0
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_12_PC	0x784A0
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_12_PC	0x785A0
+#define ICL_DSC0_PICTURE_PARAMETER_SET_12(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_12_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_12_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_12(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_12_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_12_PC)
+
+#define DSCA_PICTURE_PARAMETER_SET_13		0x6B264
+#define DSCC_PICTURE_PARAMETER_SET_13		0x6BA64
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_13_PB	0x782A4
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_13_PB	0x783A4
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_13_PC	0x784A4
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_13_PC	0x785A4
+#define ICL_DSC0_PICTURE_PARAMETER_SET_13(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_13_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_13_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_13(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_13_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_13_PC)
+
+#define DSCA_PICTURE_PARAMETER_SET_14		0x6B268
+#define DSCC_PICTURE_PARAMETER_SET_14		0x6BA68
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_14_PB	0x782A8
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_14_PB	0x783A8
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_14_PC	0x784A8
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_14_PC	0x785A8
+#define ICL_DSC0_PICTURE_PARAMETER_SET_14(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_14_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_14_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_14(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_14_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_14_PC)
+
+#define DSCA_PICTURE_PARAMETER_SET_15		0x6B26C
+#define DSCC_PICTURE_PARAMETER_SET_15		0x6BA6C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_15_PB	0x782AC
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_15_PB	0x783AC
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_15_PC	0x784AC
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_15_PC	0x785AC
+#define ICL_DSC0_PICTURE_PARAMETER_SET_15(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_15_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_15_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_15(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_15_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_15_PC)
+
+#define DSCA_PICTURE_PARAMETER_SET_16		0x6B270
+#define DSCC_PICTURE_PARAMETER_SET_16		0x6BA70
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_16_PB	0x782B0
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_16_PB	0x783B0
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_16_PC	0x784B0
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_16_PC	0x785B0
+#define ICL_DSC0_PICTURE_PARAMETER_SET_16(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_16_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_16_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_16(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_16_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_16_PC)
+#define  DSC_SLICE_PER_LINE(slice_per_line)		((slice_per_line) << 16)
+#define  DSC_SLICE_CHUNK_SIZE(slice_chunk_aize)		(slice_chunk_size << 0)
+
+/* Icelake Rate Control Buffer Threshold Registers */
+#define DSCA_RC_BUF_THRESH_0			_MMIO(0x6B230)
+#define DSCA_RC_BUF_THRESH_0_UDW		_MMIO(0x6B230 + 4)
+#define DSCC_RC_BUF_THRESH_0			_MMIO(0x6BA30)
+#define DSCC_RC_BUF_THRESH_0_UDW		_MMIO(0x6BA30 + 4)
+#define _ICL_DSC0_RC_BUF_THRESH_0_PB		(0x78254)
+#define _ICL_DSC0_RC_BUF_THRESH_0_UDW_PB	(0x78254 + 4)
+#define _ICL_DSC1_RC_BUF_THRESH_0_PB		(0x78354)
+#define _ICL_DSC1_RC_BUF_THRESH_0_UDW_PB	(0x78354 + 4)
+#define _ICL_DSC0_RC_BUF_THRESH_0_PC		(0x78454)
+#define _ICL_DSC0_RC_BUF_THRESH_0_UDW_PC	(0x78454 + 4)
+#define _ICL_DSC1_RC_BUF_THRESH_0_PC		(0x78554)
+#define _ICL_DSC1_RC_BUF_THRESH_0_UDW_PC	(0x78554 + 4)
+#define ICL_DSC0_RC_BUF_THRESH_0(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC0_RC_BUF_THRESH_0_PB, \
+						_ICL_DSC0_RC_BUF_THRESH_0_PC)
+#define ICL_DSC0_RC_BUF_THRESH_0_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC0_RC_BUF_THRESH_0_UDW_PB, \
+						_ICL_DSC0_RC_BUF_THRESH_0_UDW_PC)
+#define ICL_DSC1_RC_BUF_THRESH_0(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC1_RC_BUF_THRESH_0_PB, \
+						_ICL_DSC1_RC_BUF_THRESH_0_PC)
+#define ICL_DSC1_RC_BUF_THRESH_0_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC1_RC_BUF_THRESH_0_UDW_PB, \
+						_ICL_DSC1_RC_BUF_THRESH_0_UDW_PC)
+
+#define DSCA_RC_BUF_THRESH_1			_MMIO(0x6B238)
+#define DSCA_RC_BUF_THRESH_1_UDW		_MMIO(0x6B238 + 4)
+#define DSCC_RC_BUF_THRESH_1			_MMIO(0x6BA38)
+#define DSCC_RC_BUF_THRESH_1_UDW		_MMIO(0x6BA38 + 4)
+#define _ICL_DSC0_RC_BUF_THRESH_1_PB		(0x7825C)
+#define _ICL_DSC0_RC_BUF_THRESH_1_UDW_PB	(0x7825C + 4)
+#define _ICL_DSC1_RC_BUF_THRESH_1_PB		(0x7835C)
+#define _ICL_DSC1_RC_BUF_THRESH_1_UDW_PB	(0x7835C + 4)
+#define _ICL_DSC0_RC_BUF_THRESH_1_PC		(0x7845C)
+#define _ICL_DSC0_RC_BUF_THRESH_1_UDW_PC	(0x7845C + 4)
+#define _ICL_DSC1_RC_BUF_THRESH_1_PC		(0x7855C)
+#define _ICL_DSC1_RC_BUF_THRESH_1_UDW_PC	(0x7855C + 4)
+#define ICL_DSC0_RC_BUF_THRESH_1(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC0_RC_BUF_THRESH_1_PB, \
+						_ICL_DSC0_RC_BUF_THRESH_1_PC)
+#define ICL_DSC0_RC_BUF_THRESH_1_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC0_RC_BUF_THRESH_1_UDW_PB, \
+						_ICL_DSC0_RC_BUF_THRESH_1_UDW_PC)
+#define ICL_DSC1_RC_BUF_THRESH_1(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC1_RC_BUF_THRESH_1_PB, \
+						_ICL_DSC1_RC_BUF_THRESH_1_PC)
+#define ICL_DSC1_RC_BUF_THRESH_1_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC1_RC_BUF_THRESH_1_UDW_PB, \
+						_ICL_DSC1_RC_BUF_THRESH_1_UDW_PC)
+
 #endif /* _I915_REG_H_ */
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 8928894dd9c7..5c2c93cbab12 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -206,7 +206,8 @@ static int reset_all_global_seqno(struct drm_i915_private *i915, u32 seqno)
 	/* Carefully retire all requests without writing to the rings */
 	ret = i915_gem_wait_for_idle(i915,
 				     I915_WAIT_INTERRUPTIBLE |
-				     I915_WAIT_LOCKED);
+				     I915_WAIT_LOCKED,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (ret)
 		return ret;
 
@@ -320,6 +321,7 @@ static void advance_ring(struct i915_request *request)
 		 * is just about to be. Either works, if we miss the last two
 		 * noops - they are safe to be replayed on a reset.
 		 */
+		GEM_TRACE("marking %s as inactive\n", ring->timeline->name);
 		tail = READ_ONCE(request->tail);
 		list_del(&ring->active_link);
 	} else {
@@ -383,8 +385,8 @@ static void __retire_engine_request(struct intel_engine_cs *engine,
 	 * the subsequent request.
 	 */
 	if (engine->last_retired_context)
-		intel_context_unpin(engine->last_retired_context, engine);
-	engine->last_retired_context = rq->ctx;
+		intel_context_unpin(engine->last_retired_context);
+	engine->last_retired_context = rq->hw_context;
 }
 
 static void __retire_engine_upto(struct intel_engine_cs *engine,
@@ -455,8 +457,8 @@ static void i915_request_retire(struct i915_request *request)
 	i915_request_remove_from_client(request);
 
 	/* Retirement decays the ban score as it is a sign of ctx progress */
-	atomic_dec_if_positive(&request->ctx->ban_score);
-	intel_context_unpin(request->ctx, request->engine);
+	atomic_dec_if_positive(&request->gem_context->ban_score);
+	intel_context_unpin(request->hw_context);
 
 	__retire_engine_upto(request->engine, request);
 
@@ -502,7 +504,7 @@ static void move_to_timeline(struct i915_request *request,
 	GEM_BUG_ON(request->timeline == &request->engine->timeline);
 	lockdep_assert_held(&request->engine->timeline.lock);
 
-	spin_lock_nested(&request->timeline->lock, SINGLE_DEPTH_NESTING);
+	spin_lock(&request->timeline->lock);
 	list_move_tail(&request->link, &timeline->requests);
 	spin_unlock(&request->timeline->lock);
 }
@@ -657,7 +659,7 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 {
 	struct drm_i915_private *i915 = engine->i915;
 	struct i915_request *rq;
-	struct intel_ring *ring;
+	struct intel_context *ce;
 	int ret;
 
 	lockdep_assert_held(&i915->drm.struct_mutex);
@@ -681,22 +683,21 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 	 * GGTT space, so do this first before we reserve a seqno for
 	 * ourselves.
 	 */
-	ring = intel_context_pin(ctx, engine);
-	if (IS_ERR(ring))
-		return ERR_CAST(ring);
-	GEM_BUG_ON(!ring);
+	ce = intel_context_pin(ctx, engine);
+	if (IS_ERR(ce))
+		return ERR_CAST(ce);
 
 	ret = reserve_gt(i915);
 	if (ret)
 		goto err_unpin;
 
-	ret = intel_ring_wait_for_space(ring, MIN_SPACE_FOR_ADD_REQUEST);
+	ret = intel_ring_wait_for_space(ce->ring, MIN_SPACE_FOR_ADD_REQUEST);
 	if (ret)
 		goto err_unreserve;
 
 	/* Move our oldest request to the slab-cache (if not in use!) */
-	rq = list_first_entry(&ring->request_list, typeof(*rq), ring_link);
-	if (!list_is_last(&rq->ring_link, &ring->request_list) &&
+	rq = list_first_entry(&ce->ring->request_list, typeof(*rq), ring_link);
+	if (!list_is_last(&rq->ring_link, &ce->ring->request_list) &&
 	    i915_request_completed(rq))
 		i915_request_retire(rq);
 
@@ -735,7 +736,8 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 		/* Ratelimit ourselves to prevent oom from malicious clients */
 		ret = i915_gem_wait_for_idle(i915,
 					     I915_WAIT_LOCKED |
-					     I915_WAIT_INTERRUPTIBLE);
+					     I915_WAIT_INTERRUPTIBLE,
+					     MAX_SCHEDULE_TIMEOUT);
 		if (ret)
 			goto err_unreserve;
 
@@ -760,9 +762,10 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 	INIT_LIST_HEAD(&rq->active_list);
 	rq->i915 = i915;
 	rq->engine = engine;
-	rq->ctx = ctx;
-	rq->ring = ring;
-	rq->timeline = ring->timeline;
+	rq->gem_context = ctx;
+	rq->hw_context = ce;
+	rq->ring = ce->ring;
+	rq->timeline = ce->ring->timeline;
 	GEM_BUG_ON(rq->timeline == &engine->timeline);
 
 	spin_lock_init(&rq->lock);
@@ -814,14 +817,16 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 		goto err_unwind;
 
 	/* Keep a second pin for the dual retirement along engine and ring */
-	__intel_context_pin(rq->ctx, engine);
+	__intel_context_pin(ce);
+
+	rq->infix = rq->ring->emit; /* end of header; start of user payload */
 
 	/* Check that we didn't interrupt ourselves with a new request */
 	GEM_BUG_ON(rq->timeline->seqno != rq->fence.seqno);
 	return rq;
 
 err_unwind:
-	rq->ring->emit = rq->head;
+	ce->ring->emit = rq->head;
 
 	/* Make sure we didn't add ourselves to external state before freeing */
 	GEM_BUG_ON(!list_empty(&rq->active_list));
@@ -832,7 +837,7 @@ err_unwind:
 err_unreserve:
 	unreserve_gt(i915);
 err_unpin:
-	intel_context_unpin(ctx, engine);
+	intel_context_unpin(ce);
 	return ERR_PTR(ret);
 }
 
@@ -1010,19 +1015,39 @@ i915_request_await_object(struct i915_request *to,
 	return ret;
 }
 
+void i915_request_skip(struct i915_request *rq, int error)
+{
+	void *vaddr = rq->ring->vaddr;
+	u32 head;
+
+	GEM_BUG_ON(!IS_ERR_VALUE((long)error));
+	dma_fence_set_error(&rq->fence, error);
+
+	/*
+	 * As this request likely depends on state from the lost
+	 * context, clear out all the user operations leaving the
+	 * breadcrumb at the end (so we get the fence notifications).
+	 */
+	head = rq->infix;
+	if (rq->postfix < head) {
+		memset(vaddr + head, 0, rq->ring->size - head);
+		head = 0;
+	}
+	memset(vaddr + head, 0, rq->postfix - head);
+}
+
 /*
  * NB: This function is not allowed to fail. Doing so would mean the the
  * request is not being tracked for completion but the work itself is
  * going to happen on the hardware. This would be a Bad Thing(tm).
  */
-void __i915_request_add(struct i915_request *request, bool flush_caches)
+void i915_request_add(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
-	struct intel_ring *ring = request->ring;
 	struct i915_timeline *timeline = request->timeline;
+	struct intel_ring *ring = request->ring;
 	struct i915_request *prev;
 	u32 *cs;
-	int err;
 
 	GEM_TRACE("%s fence %llx:%d\n",
 		  engine->name, request->fence.context, request->fence.seqno);
@@ -1043,20 +1068,7 @@ void __i915_request_add(struct i915_request *request, bool flush_caches)
 	 * know that it is time to use that space up.
 	 */
 	request->reserved_space = 0;
-
-	/*
-	 * Emit any outstanding flushes - execbuf can fail to emit the flush
-	 * after having emitted the batchbuffer command. Hence we need to fix
-	 * things up similar to emitting the lazy request. The difference here
-	 * is that the flush _must_ happen before the next request, no matter
-	 * what.
-	 */
-	if (flush_caches) {
-		err = engine->emit_flush(request, EMIT_FLUSH);
-
-		/* Not allowed to fail! */
-		WARN(err, "engine->emit_flush() failed: %d!\n", err);
-	}
+	engine->emit_flush(request, EMIT_FLUSH);
 
 	/*
 	 * Record the position of the start of the breadcrumb so that
@@ -1095,8 +1107,10 @@ void __i915_request_add(struct i915_request *request, bool flush_caches)
 	i915_gem_active_set(&timeline->last_request, request);
 
 	list_add_tail(&request->ring_link, &ring->request_list);
-	if (list_is_first(&request->ring_link, &ring->request_list))
+	if (list_is_first(&request->ring_link, &ring->request_list)) {
+		GEM_TRACE("marking %s as active\n", ring->timeline->name);
 		list_add(&ring->active_link, &request->i915->gt.active_rings);
+	}
 	request->emitted_jiffies = jiffies;
 
 	/*
@@ -1113,7 +1127,7 @@ void __i915_request_add(struct i915_request *request, bool flush_caches)
 	local_bh_disable();
 	rcu_read_lock(); /* RCU serialisation for set-wedged protection */
 	if (engine->schedule)
-		engine->schedule(request, &request->ctx->sched);
+		engine->schedule(request, &request->gem_context->sched);
 	rcu_read_unlock();
 	i915_sw_fence_commit(&request->submit);
 	local_bh_enable(); /* Kick the execlists tasklet if just scheduled */
@@ -1205,7 +1219,7 @@ static bool __i915_spin_request(const struct i915_request *rq,
 	 * takes to sleep on a request, on the order of a microsecond.
 	 */
 
-	irq = atomic_read(&engine->irq_count);
+	irq = READ_ONCE(engine->breadcrumbs.irq_count);
 	timeout_us += local_clock_us(&cpu);
 	do {
 		if (i915_seqno_passed(intel_engine_get_seqno(engine), seqno))
@@ -1217,7 +1231,7 @@ static bool __i915_spin_request(const struct i915_request *rq,
 		 * assume we won't see one in the near future but require
 		 * the engine->seqno_barrier() to fixup coherency.
 		 */
-		if (atomic_read(&engine->irq_count) != irq)
+		if (READ_ONCE(engine->breadcrumbs.irq_count) != irq)
 			break;
 
 		if (signal_pending_state(state, current))
@@ -1294,7 +1308,7 @@ long i915_request_wait(struct i915_request *rq,
 	if (flags & I915_WAIT_LOCKED)
 		add_wait_queue(errq, &reset);
 
-	intel_wait_init(&wait, rq);
+	intel_wait_init(&wait);
 
 restart:
 	do {
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index eddbd4245cb3..e1c9365dfefb 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -93,8 +93,9 @@ struct i915_request {
 	 * i915_request_free() will then decrement the refcount on the
 	 * context.
 	 */
-	struct i915_gem_context *ctx;
+	struct i915_gem_context *gem_context;
 	struct intel_engine_cs *engine;
+	struct intel_context *hw_context;
 	struct intel_ring *ring;
 	struct i915_timeline *timeline;
 	struct intel_signal_node signaling;
@@ -133,6 +134,9 @@ struct i915_request {
 	/** Position in the ring of the start of the request */
 	u32 head;
 
+	/** Position in the ring of the start of the user packets */
+	u32 infix;
+
 	/**
 	 * Position in the ring of the start of the postfix.
 	 * This is required to calculate the maximum available ring space
@@ -249,13 +253,13 @@ int i915_request_await_object(struct i915_request *to,
 int i915_request_await_dma_fence(struct i915_request *rq,
 				 struct dma_fence *fence);
 
-void __i915_request_add(struct i915_request *rq, bool flush_caches);
-#define i915_request_add(rq) \
-	__i915_request_add(rq, false)
+void i915_request_add(struct i915_request *rq);
 
 void __i915_request_submit(struct i915_request *request);
 void i915_request_submit(struct i915_request *request);
 
+void i915_request_skip(struct i915_request *request, int error);
+
 void __i915_request_unsubmit(struct i915_request *request);
 void i915_request_unsubmit(struct i915_request *request);
 
@@ -266,6 +270,7 @@ long i915_request_wait(struct i915_request *rq,
 #define I915_WAIT_INTERRUPTIBLE	BIT(0)
 #define I915_WAIT_LOCKED	BIT(1) /* struct_mutex held, handle GPU reset */
 #define I915_WAIT_ALL		BIT(2) /* used by i915_gem_object_wait() */
+#define I915_WAIT_FOR_IDLE_BOOST BIT(3)
 
 static inline u32 intel_engine_get_seqno(struct intel_engine_cs *engine);
 
@@ -375,6 +380,7 @@ static inline void
 init_request_active(struct i915_gem_active *active,
 		    i915_gem_retire_fn retire)
 {
+	RCU_INIT_POINTER(active->request, NULL);
 	INIT_LIST_HEAD(&active->link);
 	active->retire = retire ?: i915_gem_retire_noop;
 }
diff --git a/drivers/gpu/drm/i915/i915_selftest.h b/drivers/gpu/drm/i915/i915_selftest.h
index 9766e806dce6..a73472dd12fd 100644
--- a/drivers/gpu/drm/i915/i915_selftest.h
+++ b/drivers/gpu/drm/i915/i915_selftest.h
@@ -99,6 +99,6 @@ __printf(2, 3)
 bool __igt_timeout(unsigned long timeout, const char *fmt, ...);
 
 #define igt_timeout(t, fmt, ...) \
-	__igt_timeout((t), KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__)
+	__igt_timeout((t), KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
 
 #endif /* !__I915_SELFTEST_H__ */
diff --git a/drivers/gpu/drm/i915/i915_timeline.h b/drivers/gpu/drm/i915/i915_timeline.h
index dc2a4632faa7..a2c2c3ab5fb0 100644
--- a/drivers/gpu/drm/i915/i915_timeline.h
+++ b/drivers/gpu/drm/i915/i915_timeline.h
@@ -37,6 +37,8 @@ struct i915_timeline {
 	u32 seqno;
 
 	spinlock_t lock;
+#define TIMELINE_CLIENT 0 /* default subclass */
+#define TIMELINE_ENGINE 1
 
 	/**
 	 * List of breadcrumbs associated with GPU requests currently
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 8cc3a256f29d..b50c6b829715 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -591,21 +591,26 @@ TRACE_EVENT(i915_gem_ring_sync_to,
 
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
-			     __field(u32, sync_from)
-			     __field(u32, sync_to)
+			     __field(u32, from_class)
+			     __field(u32, from_instance)
+			     __field(u32, to_class)
+			     __field(u32, to_instance)
 			     __field(u32, seqno)
 			     ),
 
 	    TP_fast_assign(
 			   __entry->dev = from->i915->drm.primary->index;
-			   __entry->sync_from = from->engine->id;
-			   __entry->sync_to = to->engine->id;
+			   __entry->from_class = from->engine->uabi_class;
+			   __entry->from_instance = from->engine->instance;
+			   __entry->to_class = to->engine->uabi_class;
+			   __entry->to_instance = to->engine->instance;
 			   __entry->seqno = from->global_seqno;
 			   ),
 
-	    TP_printk("dev=%u, sync-from=%u, sync-to=%u, seqno=%u",
+	    TP_printk("dev=%u, sync-from=%u:%u, sync-to=%u:%u, seqno=%u",
 		      __entry->dev,
-		      __entry->sync_from, __entry->sync_to,
+		      __entry->from_class, __entry->from_instance,
+		      __entry->to_class, __entry->to_instance,
 		      __entry->seqno)
 );
 
@@ -616,24 +621,27 @@ TRACE_EVENT(i915_request_queue,
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
 			     __field(u32, hw_id)
-			     __field(u32, ring)
-			     __field(u32, ctx)
+			     __field(u64, ctx)
+			     __field(u16, class)
+			     __field(u16, instance)
 			     __field(u32, seqno)
 			     __field(u32, flags)
 			     ),
 
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
-			   __entry->hw_id = rq->ctx->hw_id;
-			   __entry->ring = rq->engine->id;
+			   __entry->hw_id = rq->gem_context->hw_id;
+			   __entry->class = rq->engine->uabi_class;
+			   __entry->instance = rq->engine->instance;
 			   __entry->ctx = rq->fence.context;
 			   __entry->seqno = rq->fence.seqno;
 			   __entry->flags = flags;
 			   ),
 
-	    TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, flags=0x%x",
-		      __entry->dev, __entry->hw_id, __entry->ring, __entry->ctx,
-		      __entry->seqno, __entry->flags)
+	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, flags=0x%x",
+		      __entry->dev, __entry->class, __entry->instance,
+		      __entry->hw_id, __entry->ctx, __entry->seqno,
+		      __entry->flags)
 );
 
 DECLARE_EVENT_CLASS(i915_request,
@@ -643,24 +651,27 @@ DECLARE_EVENT_CLASS(i915_request,
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
 			     __field(u32, hw_id)
-			     __field(u32, ring)
-			     __field(u32, ctx)
+			     __field(u64, ctx)
+			     __field(u16, class)
+			     __field(u16, instance)
 			     __field(u32, seqno)
 			     __field(u32, global)
 			     ),
 
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
-			   __entry->hw_id = rq->ctx->hw_id;
-			   __entry->ring = rq->engine->id;
+			   __entry->hw_id = rq->gem_context->hw_id;
+			   __entry->class = rq->engine->uabi_class;
+			   __entry->instance = rq->engine->instance;
 			   __entry->ctx = rq->fence.context;
 			   __entry->seqno = rq->fence.seqno;
 			   __entry->global = rq->global_seqno;
 			   ),
 
-	    TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, global=%u",
-		      __entry->dev, __entry->hw_id, __entry->ring, __entry->ctx,
-		      __entry->seqno, __entry->global)
+	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, global=%u",
+		      __entry->dev, __entry->class, __entry->instance,
+		      __entry->hw_id, __entry->ctx, __entry->seqno,
+		      __entry->global)
 );
 
 DEFINE_EVENT(i915_request, i915_request_add,
@@ -686,8 +697,9 @@ TRACE_EVENT(i915_request_in,
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
 			     __field(u32, hw_id)
-			     __field(u32, ring)
-			     __field(u32, ctx)
+			     __field(u64, ctx)
+			     __field(u16, class)
+			     __field(u16, instance)
 			     __field(u32, seqno)
 			     __field(u32, global_seqno)
 			     __field(u32, port)
@@ -696,8 +708,9 @@ TRACE_EVENT(i915_request_in,
 
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
-			   __entry->hw_id = rq->ctx->hw_id;
-			   __entry->ring = rq->engine->id;
+			   __entry->hw_id = rq->gem_context->hw_id;
+			   __entry->class = rq->engine->uabi_class;
+			   __entry->instance = rq->engine->instance;
 			   __entry->ctx = rq->fence.context;
 			   __entry->seqno = rq->fence.seqno;
 			   __entry->global_seqno = rq->global_seqno;
@@ -705,10 +718,10 @@ TRACE_EVENT(i915_request_in,
 			   __entry->port = port;
 			   ),
 
-	    TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, prio=%u, global=%u, port=%u",
-		      __entry->dev, __entry->hw_id, __entry->ring, __entry->ctx,
-		      __entry->seqno, __entry->prio, __entry->global_seqno,
-		      __entry->port)
+	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, prio=%u, global=%u, port=%u",
+		      __entry->dev, __entry->class, __entry->instance,
+		      __entry->hw_id, __entry->ctx, __entry->seqno,
+		      __entry->prio, __entry->global_seqno, __entry->port)
 );
 
 TRACE_EVENT(i915_request_out,
@@ -718,8 +731,9 @@ TRACE_EVENT(i915_request_out,
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
 			     __field(u32, hw_id)
-			     __field(u32, ring)
-			     __field(u32, ctx)
+			     __field(u64, ctx)
+			     __field(u16, class)
+			     __field(u16, instance)
 			     __field(u32, seqno)
 			     __field(u32, global_seqno)
 			     __field(u32, completed)
@@ -727,17 +741,18 @@ TRACE_EVENT(i915_request_out,
 
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
-			   __entry->hw_id = rq->ctx->hw_id;
-			   __entry->ring = rq->engine->id;
+			   __entry->hw_id = rq->gem_context->hw_id;
+			   __entry->class = rq->engine->uabi_class;
+			   __entry->instance = rq->engine->instance;
 			   __entry->ctx = rq->fence.context;
 			   __entry->seqno = rq->fence.seqno;
 			   __entry->global_seqno = rq->global_seqno;
 			   __entry->completed = i915_request_completed(rq);
 			   ),
 
-		    TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, global=%u, completed?=%u",
-			      __entry->dev, __entry->hw_id, __entry->ring,
-			      __entry->ctx, __entry->seqno,
+		    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, global=%u, completed?=%u",
+			      __entry->dev, __entry->class, __entry->instance,
+			      __entry->hw_id, __entry->ctx, __entry->seqno,
 			      __entry->global_seqno, __entry->completed)
 );
 
@@ -771,21 +786,23 @@ TRACE_EVENT(intel_engine_notify,
 
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
-			     __field(u32, ring)
+			     __field(u16, class)
+			     __field(u16, instance)
 			     __field(u32, seqno)
 			     __field(bool, waiters)
 			     ),
 
 	    TP_fast_assign(
 			   __entry->dev = engine->i915->drm.primary->index;
-			   __entry->ring = engine->id;
+			   __entry->class = engine->uabi_class;
+			   __entry->instance = engine->instance;
 			   __entry->seqno = intel_engine_get_seqno(engine);
 			   __entry->waiters = waiters;
 			   ),
 
-	    TP_printk("dev=%u, ring=%u, seqno=%u, waiters=%u",
-		      __entry->dev, __entry->ring, __entry->seqno,
-		      __entry->waiters)
+	    TP_printk("dev=%u, engine=%u:%u, seqno=%u, waiters=%u",
+		      __entry->dev, __entry->class, __entry->instance,
+		      __entry->seqno, __entry->waiters)
 );
 
 DEFINE_EVENT(i915_request, i915_request_retire,
@@ -800,8 +817,9 @@ TRACE_EVENT(i915_request_wait_begin,
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
 			     __field(u32, hw_id)
-			     __field(u32, ring)
-			     __field(u32, ctx)
+			     __field(u64, ctx)
+			     __field(u16, class)
+			     __field(u16, instance)
 			     __field(u32, seqno)
 			     __field(u32, global)
 			     __field(unsigned int, flags)
@@ -815,18 +833,20 @@ TRACE_EVENT(i915_request_wait_begin,
 	     */
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
-			   __entry->hw_id = rq->ctx->hw_id;
-			   __entry->ring = rq->engine->id;
+			   __entry->hw_id = rq->gem_context->hw_id;
+			   __entry->class = rq->engine->uabi_class;
+			   __entry->instance = rq->engine->instance;
 			   __entry->ctx = rq->fence.context;
 			   __entry->seqno = rq->fence.seqno;
 			   __entry->global = rq->global_seqno;
 			   __entry->flags = flags;
 			   ),
 
-	    TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, global=%u, blocking=%u, flags=0x%x",
-		      __entry->dev, __entry->hw_id, __entry->ring, __entry->ctx,
-		      __entry->seqno, __entry->global,
-		      !!(__entry->flags & I915_WAIT_LOCKED), __entry->flags)
+	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, global=%u, blocking=%u, flags=0x%x",
+		      __entry->dev, __entry->class, __entry->instance,
+		      __entry->hw_id, __entry->ctx, __entry->seqno,
+		      __entry->global, !!(__entry->flags & I915_WAIT_LOCKED),
+		      __entry->flags)
 );
 
 DEFINE_EVENT(i915_request, i915_request_wait_end,
@@ -936,7 +956,7 @@ DECLARE_EVENT_CLASS(i915_context,
 			__entry->dev = ctx->i915->drm.primary->index;
 			__entry->ctx = ctx;
 			__entry->hw_id = ctx->hw_id;
-			__entry->vm = ctx->ppgtt ? &ctx->ppgtt->base : NULL;
+			__entry->vm = ctx->ppgtt ? &ctx->ppgtt->vm : NULL;
 	),
 
 	TP_printk("dev=%u, ctx=%p, ctx_vm=%p, hw_id=%u",
@@ -953,36 +973,6 @@ DEFINE_EVENT(i915_context, i915_context_free,
 	TP_ARGS(ctx)
 );
 
-/**
- * DOC: switch_mm tracepoint
- *
- * This tracepoint allows tracking of the mm switch, which is an important point
- * in the lifetime of the vm in the legacy submission path. This tracepoint is
- * called only if full ppgtt is enabled.
- */
-TRACE_EVENT(switch_mm,
-	TP_PROTO(struct intel_engine_cs *engine, struct i915_gem_context *to),
-
-	TP_ARGS(engine, to),
-
-	TP_STRUCT__entry(
-			__field(u32, ring)
-			__field(struct i915_gem_context *, to)
-			__field(struct i915_address_space *, vm)
-			__field(u32, dev)
-	),
-
-	TP_fast_assign(
-			__entry->ring = engine->id;
-			__entry->to = to;
-			__entry->vm = to->ppgtt? &to->ppgtt->base : NULL;
-			__entry->dev = engine->i915->drm.primary->index;
-	),
-
-	TP_printk("dev=%u, ring=%u, ctx=%p, ctx_vm=%p",
-		  __entry->dev, __entry->ring, __entry->to, __entry->vm)
-);
-
 #endif /* _I915_TRACE_H_ */
 
 /* This part must be outside protection */
diff --git a/drivers/gpu/drm/i915/i915_vgpu.c b/drivers/gpu/drm/i915/i915_vgpu.c
index 5fe9f3f39467..869cf4a3b6de 100644
--- a/drivers/gpu/drm/i915/i915_vgpu.c
+++ b/drivers/gpu/drm/i915/i915_vgpu.c
@@ -105,7 +105,7 @@ static void vgt_deballoon_space(struct i915_ggtt *ggtt,
 			 node->start + node->size,
 			 node->size / 1024);
 
-	ggtt->base.reserved -= node->size;
+	ggtt->vm.reserved -= node->size;
 	drm_mm_remove_node(node);
 }
 
@@ -141,11 +141,11 @@ static int vgt_balloon_space(struct i915_ggtt *ggtt,
 
 	DRM_INFO("balloon space: range [ 0x%lx - 0x%lx ] %lu KiB.\n",
 		 start, end, size / 1024);
-	ret = i915_gem_gtt_reserve(&ggtt->base, node,
+	ret = i915_gem_gtt_reserve(&ggtt->vm, node,
 				   size, start, I915_COLOR_UNEVICTABLE,
 				   0);
 	if (!ret)
-		ggtt->base.reserved += size;
+		ggtt->vm.reserved += size;
 
 	return ret;
 }
@@ -197,7 +197,7 @@ static int vgt_balloon_space(struct i915_ggtt *ggtt,
 int intel_vgt_balloon(struct drm_i915_private *dev_priv)
 {
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	unsigned long ggtt_end = ggtt->base.total;
+	unsigned long ggtt_end = ggtt->vm.total;
 
 	unsigned long mappable_base, mappable_size, mappable_end;
 	unsigned long unmappable_base, unmappable_size, unmappable_end;
diff --git a/drivers/gpu/drm/i915/i915_vgpu.h b/drivers/gpu/drm/i915/i915_vgpu.h
index bb8338450dc1..551acc390046 100644
--- a/drivers/gpu/drm/i915/i915_vgpu.h
+++ b/drivers/gpu/drm/i915/i915_vgpu.h
@@ -36,6 +36,12 @@ intel_vgpu_has_hwsp_emulation(struct drm_i915_private *dev_priv)
 	return dev_priv->vgpu.caps & VGT_CAPS_HWSP_EMULATION;
 }
 
+static inline bool
+intel_vgpu_has_huge_gtt(struct drm_i915_private *dev_priv)
+{
+	return dev_priv->vgpu.caps & VGT_CAPS_HUGE_GTT;
+}
+
 int intel_vgt_balloon(struct drm_i915_private *dev_priv);
 void intel_vgt_deballoon(struct drm_i915_private *dev_priv);
 
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 0531c01c3604..11d834f94220 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -21,7 +21,7 @@
  * IN THE SOFTWARE.
  *
  */
- 
+
 #include "i915_vma.h"
 
 #include "i915_drv.h"
@@ -30,18 +30,53 @@
 
 #include <drm/drm_gem.h>
 
+#if IS_ENABLED(CONFIG_DRM_I915_ERRLOG_GEM) && IS_ENABLED(CONFIG_DRM_DEBUG_MM)
+
+#include <linux/stackdepot.h>
+
+static void vma_print_allocator(struct i915_vma *vma, const char *reason)
+{
+	unsigned long entries[12];
+	struct stack_trace trace = {
+		.entries = entries,
+		.max_entries = ARRAY_SIZE(entries),
+	};
+	char buf[512];
+
+	if (!vma->node.stack) {
+		DRM_DEBUG_DRIVER("vma.node [%08llx + %08llx] %s: unknown owner\n",
+				 vma->node.start, vma->node.size, reason);
+		return;
+	}
+
+	depot_fetch_stack(vma->node.stack, &trace);
+	snprint_stack_trace(buf, sizeof(buf), &trace, 0);
+	DRM_DEBUG_DRIVER("vma.node [%08llx + %08llx] %s: inserted at %s\n",
+			 vma->node.start, vma->node.size, reason, buf);
+}
+
+#else
+
+static void vma_print_allocator(struct i915_vma *vma, const char *reason)
+{
+}
+
+#endif
+
+struct i915_vma_active {
+	struct i915_gem_active base;
+	struct i915_vma *vma;
+	struct rb_node node;
+	u64 timeline;
+};
+
 static void
-i915_vma_retire(struct i915_gem_active *active, struct i915_request *rq)
+__i915_vma_retire(struct i915_vma *vma, struct i915_request *rq)
 {
-	const unsigned int idx = rq->engine->id;
-	struct i915_vma *vma =
-		container_of(active, struct i915_vma, last_read[idx]);
 	struct drm_i915_gem_object *obj = vma->obj;
 
-	GEM_BUG_ON(!i915_vma_has_active_engine(vma, idx));
-
-	i915_vma_clear_active(vma, idx);
-	if (i915_vma_is_active(vma))
+	GEM_BUG_ON(!i915_vma_is_active(vma));
+	if (--vma->active_count)
 		return;
 
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
@@ -75,6 +110,21 @@ i915_vma_retire(struct i915_gem_active *active, struct i915_request *rq)
 	}
 }
 
+static void
+i915_vma_retire(struct i915_gem_active *base, struct i915_request *rq)
+{
+	struct i915_vma_active *active =
+		container_of(base, typeof(*active), base);
+
+	__i915_vma_retire(active->vma, rq);
+}
+
+static void
+i915_vma_last_retire(struct i915_gem_active *base, struct i915_request *rq)
+{
+	__i915_vma_retire(container_of(base, struct i915_vma, last_active), rq);
+}
+
 static struct i915_vma *
 vma_create(struct drm_i915_gem_object *obj,
 	   struct i915_address_space *vm,
@@ -82,19 +132,20 @@ vma_create(struct drm_i915_gem_object *obj,
 {
 	struct i915_vma *vma;
 	struct rb_node *rb, **p;
-	int i;
 
 	/* The aliasing_ppgtt should never be used directly! */
-	GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->base);
+	GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->vm);
 
 	vma = kmem_cache_zalloc(vm->i915->vmas, GFP_KERNEL);
 	if (vma == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	for (i = 0; i < ARRAY_SIZE(vma->last_read); i++)
-		init_request_active(&vma->last_read[i], i915_vma_retire);
+	vma->active = RB_ROOT;
+
+	init_request_active(&vma->last_active, i915_vma_last_retire);
 	init_request_active(&vma->last_fence, NULL);
 	vma->vm = vm;
+	vma->ops = &vm->vma_ops;
 	vma->obj = obj;
 	vma->resv = obj->resv;
 	vma->size = obj->base.size;
@@ -280,7 +331,7 @@ int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
 	GEM_BUG_ON(!vma->pages);
 
 	trace_i915_vma_bind(vma, bind_flags);
-	ret = vma->vm->bind_vma(vma, cache_level, bind_flags);
+	ret = vma->ops->bind_vma(vma, cache_level, bind_flags);
 	if (ret)
 		return ret;
 
@@ -345,7 +396,7 @@ void i915_vma_flush_writes(struct i915_vma *vma)
 
 void i915_vma_unpin_iomap(struct i915_vma *vma)
 {
-	lockdep_assert_held(&vma->obj->base.dev->struct_mutex);
+	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
 
 	GEM_BUG_ON(vma->iomap == NULL);
 
@@ -365,6 +416,7 @@ void i915_vma_unpin_and_release(struct i915_vma **p_vma)
 		return;
 
 	obj = vma->obj;
+	GEM_BUG_ON(!obj);
 
 	i915_vma_unpin(vma);
 	i915_vma_close(vma);
@@ -459,6 +511,18 @@ bool i915_gem_valid_gtt_space(struct i915_vma *vma, unsigned long cache_level)
 	return true;
 }
 
+static void assert_bind_count(const struct drm_i915_gem_object *obj)
+{
+	/*
+	 * Combine the assertion that the object is bound and that we have
+	 * pinned its pages. But we should never have bound the object
+	 * more than we have pinned its pages. (For complete accuracy, we
+	 * assume that no else is pinning the pages, but as a rough assertion
+	 * that we will not run into problems later, this will do!)
+	 */
+	GEM_BUG_ON(atomic_read(&obj->mm.pages_pin_count) < obj->bind_count);
+}
+
 /**
  * i915_vma_insert - finds a slot for the vma in its address space
  * @vma: the vma
@@ -477,7 +541,7 @@ static int
 i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 {
 	struct drm_i915_private *dev_priv = vma->vm->i915;
-	struct drm_i915_gem_object *obj = vma->obj;
+	unsigned int cache_level;
 	u64 start, end;
 	int ret;
 
@@ -512,20 +576,25 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 	 * attempt to find space.
 	 */
 	if (size > end) {
-		DRM_DEBUG("Attempting to bind an object larger than the aperture: request=%llu [object=%zd] > %s aperture=%llu\n",
-			  size, obj->base.size,
-			  flags & PIN_MAPPABLE ? "mappable" : "total",
+		DRM_DEBUG("Attempting to bind an object larger than the aperture: request=%llu > %s aperture=%llu\n",
+			  size, flags & PIN_MAPPABLE ? "mappable" : "total",
 			  end);
 		return -ENOSPC;
 	}
 
-	ret = i915_gem_object_pin_pages(obj);
-	if (ret)
-		return ret;
+	if (vma->obj) {
+		ret = i915_gem_object_pin_pages(vma->obj);
+		if (ret)
+			return ret;
+
+		cache_level = vma->obj->cache_level;
+	} else {
+		cache_level = 0;
+	}
 
 	GEM_BUG_ON(vma->pages);
 
-	ret = vma->vm->set_pages(vma);
+	ret = vma->ops->set_pages(vma);
 	if (ret)
 		goto err_unpin;
 
@@ -538,7 +607,7 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 		}
 
 		ret = i915_gem_gtt_reserve(vma->vm, &vma->node,
-					   size, offset, obj->cache_level,
+					   size, offset, cache_level,
 					   flags);
 		if (ret)
 			goto err_clear;
@@ -577,7 +646,7 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 		}
 
 		ret = i915_gem_gtt_insert(vma->vm, &vma->node,
-					  size, alignment, obj->cache_level,
+					  size, alignment, cache_level,
 					  start, end, flags);
 		if (ret)
 			goto err_clear;
@@ -586,23 +655,28 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 		GEM_BUG_ON(vma->node.start + vma->node.size > end);
 	}
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
-	GEM_BUG_ON(!i915_gem_valid_gtt_space(vma, obj->cache_level));
+	GEM_BUG_ON(!i915_gem_valid_gtt_space(vma, cache_level));
 
 	list_move_tail(&vma->vm_link, &vma->vm->inactive_list);
 
-	spin_lock(&dev_priv->mm.obj_lock);
-	list_move_tail(&obj->mm.link, &dev_priv->mm.bound_list);
-	obj->bind_count++;
-	spin_unlock(&dev_priv->mm.obj_lock);
+	if (vma->obj) {
+		struct drm_i915_gem_object *obj = vma->obj;
 
-	GEM_BUG_ON(atomic_read(&obj->mm.pages_pin_count) < obj->bind_count);
+		spin_lock(&dev_priv->mm.obj_lock);
+		list_move_tail(&obj->mm.link, &dev_priv->mm.bound_list);
+		obj->bind_count++;
+		spin_unlock(&dev_priv->mm.obj_lock);
+
+		assert_bind_count(obj);
+	}
 
 	return 0;
 
 err_clear:
-	vma->vm->clear_pages(vma);
+	vma->ops->clear_pages(vma);
 err_unpin:
-	i915_gem_object_unpin_pages(obj);
+	if (vma->obj)
+		i915_gem_object_unpin_pages(vma->obj);
 	return ret;
 }
 
@@ -610,30 +684,35 @@ static void
 i915_vma_remove(struct i915_vma *vma)
 {
 	struct drm_i915_private *i915 = vma->vm->i915;
-	struct drm_i915_gem_object *obj = vma->obj;
 
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 	GEM_BUG_ON(vma->flags & (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND));
 
-	vma->vm->clear_pages(vma);
+	vma->ops->clear_pages(vma);
 
 	drm_mm_remove_node(&vma->node);
 	list_move_tail(&vma->vm_link, &vma->vm->unbound_list);
 
-	/* Since the unbound list is global, only move to that list if
+	/*
+	 * Since the unbound list is global, only move to that list if
 	 * no more VMAs exist.
 	 */
-	spin_lock(&i915->mm.obj_lock);
-	if (--obj->bind_count == 0)
-		list_move_tail(&obj->mm.link, &i915->mm.unbound_list);
-	spin_unlock(&i915->mm.obj_lock);
-
-	/* And finally now the object is completely decoupled from this vma,
-	 * we can drop its hold on the backing storage and allow it to be
-	 * reaped by the shrinker.
-	 */
-	i915_gem_object_unpin_pages(obj);
-	GEM_BUG_ON(atomic_read(&obj->mm.pages_pin_count) < obj->bind_count);
+	if (vma->obj) {
+		struct drm_i915_gem_object *obj = vma->obj;
+
+		spin_lock(&i915->mm.obj_lock);
+		if (--obj->bind_count == 0)
+			list_move_tail(&obj->mm.link, &i915->mm.unbound_list);
+		spin_unlock(&i915->mm.obj_lock);
+
+		/*
+		 * And finally now the object is completely decoupled from this
+		 * vma, we can drop its hold on the backing storage and allow
+		 * it to be reaped by the shrinker.
+		 */
+		i915_gem_object_unpin_pages(obj);
+		assert_bind_count(obj);
+	}
 }
 
 int __i915_vma_do_pin(struct i915_vma *vma,
@@ -658,7 +737,7 @@ int __i915_vma_do_pin(struct i915_vma *vma,
 	}
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 
-	ret = i915_vma_bind(vma, vma->obj->cache_level, flags);
+	ret = i915_vma_bind(vma, vma->obj ? vma->obj->cache_level : 0, flags);
 	if (ret)
 		goto err_remove;
 
@@ -715,23 +794,28 @@ void i915_vma_reopen(struct i915_vma *vma)
 
 static void __i915_vma_destroy(struct i915_vma *vma)
 {
-	int i;
+	struct drm_i915_private *i915 = vma->vm->i915;
+	struct i915_vma_active *iter, *n;
 
 	GEM_BUG_ON(vma->node.allocated);
 	GEM_BUG_ON(vma->fence);
 
-	for (i = 0; i < ARRAY_SIZE(vma->last_read); i++)
-		GEM_BUG_ON(i915_gem_active_isset(&vma->last_read[i]));
 	GEM_BUG_ON(i915_gem_active_isset(&vma->last_fence));
 
 	list_del(&vma->obj_link);
 	list_del(&vma->vm_link);
-	rb_erase(&vma->obj_node, &vma->obj->vma_tree);
+	if (vma->obj)
+		rb_erase(&vma->obj_node, &vma->obj->vma_tree);
 
 	if (!i915_vma_is_ggtt(vma))
 		i915_ppgtt_put(i915_vm_to_ppgtt(vma->vm));
 
-	kmem_cache_free(to_i915(vma->obj->base.dev)->vmas, vma);
+	rbtree_postorder_for_each_entry_safe(iter, n, &vma->active, node) {
+		GEM_BUG_ON(i915_gem_active_isset(&iter->base));
+		kfree(iter);
+	}
+
+	kmem_cache_free(i915->vmas, vma);
 }
 
 void i915_vma_destroy(struct i915_vma *vma)
@@ -795,23 +879,173 @@ void i915_vma_revoke_mmap(struct i915_vma *vma)
 		list_del(&vma->obj->userfault_link);
 }
 
-int i915_vma_unbind(struct i915_vma *vma)
+static void export_fence(struct i915_vma *vma,
+			 struct i915_request *rq,
+			 unsigned int flags)
+{
+	struct reservation_object *resv = vma->resv;
+
+	/*
+	 * Ignore errors from failing to allocate the new fence, we can't
+	 * handle an error right now. Worst case should be missed
+	 * synchronisation leading to rendering corruption.
+	 */
+	reservation_object_lock(resv, NULL);
+	if (flags & EXEC_OBJECT_WRITE)
+		reservation_object_add_excl_fence(resv, &rq->fence);
+	else if (reservation_object_reserve_shared(resv) == 0)
+		reservation_object_add_shared_fence(resv, &rq->fence);
+	reservation_object_unlock(resv);
+}
+
+static struct i915_gem_active *active_instance(struct i915_vma *vma, u64 idx)
+{
+	struct i915_vma_active *active;
+	struct rb_node **p, *parent;
+	struct i915_request *old;
+
+	/*
+	 * We track the most recently used timeline to skip a rbtree search
+	 * for the common case, under typical loads we never need the rbtree
+	 * at all. We can reuse the last_active slot if it is empty, that is
+	 * after the previous activity has been retired, or if the active
+	 * matches the current timeline.
+	 *
+	 * Note that we allow the timeline to be active simultaneously in
+	 * the rbtree and the last_active cache. We do this to avoid having
+	 * to search and replace the rbtree element for a new timeline, with
+	 * the cost being that we must be aware that the vma may be retired
+	 * twice for the same timeline (as the older rbtree element will be
+	 * retired before the new request added to last_active).
+	 */
+	old = i915_gem_active_raw(&vma->last_active,
+				  &vma->vm->i915->drm.struct_mutex);
+	if (!old || old->fence.context == idx)
+		goto out;
+
+	/* Move the currently active fence into the rbtree */
+	idx = old->fence.context;
+
+	parent = NULL;
+	p = &vma->active.rb_node;
+	while (*p) {
+		parent = *p;
+
+		active = rb_entry(parent, struct i915_vma_active, node);
+		if (active->timeline == idx)
+			goto replace;
+
+		if (active->timeline < idx)
+			p = &parent->rb_right;
+		else
+			p = &parent->rb_left;
+	}
+
+	active = kmalloc(sizeof(*active), GFP_KERNEL);
+
+	/* kmalloc may retire the vma->last_active request (thanks shrinker)! */
+	if (unlikely(!i915_gem_active_raw(&vma->last_active,
+					  &vma->vm->i915->drm.struct_mutex))) {
+		kfree(active);
+		goto out;
+	}
+
+	if (unlikely(!active))
+		return ERR_PTR(-ENOMEM);
+
+	init_request_active(&active->base, i915_vma_retire);
+	active->vma = vma;
+	active->timeline = idx;
+
+	rb_link_node(&active->node, parent, p);
+	rb_insert_color(&active->node, &vma->active);
+
+replace:
+	/*
+	 * Overwrite the previous active slot in the rbtree with last_active,
+	 * leaving last_active zeroed. If the previous slot is still active,
+	 * we must be careful as we now only expect to receive one retire
+	 * callback not two, and so much undo the active counting for the
+	 * overwritten slot.
+	 */
+	if (i915_gem_active_isset(&active->base)) {
+		/* Retire ourselves from the old rq->active_list */
+		__list_del_entry(&active->base.link);
+		vma->active_count--;
+		GEM_BUG_ON(!vma->active_count);
+	}
+	GEM_BUG_ON(list_empty(&vma->last_active.link));
+	list_replace_init(&vma->last_active.link, &active->base.link);
+	active->base.request = fetch_and_zero(&vma->last_active.request);
+
+out:
+	return &vma->last_active;
+}
+
+int i915_vma_move_to_active(struct i915_vma *vma,
+			    struct i915_request *rq,
+			    unsigned int flags)
 {
 	struct drm_i915_gem_object *obj = vma->obj;
-	unsigned long active;
+	struct i915_gem_active *active;
+
+	lockdep_assert_held(&rq->i915->drm.struct_mutex);
+	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
+
+	active = active_instance(vma, rq->fence.context);
+	if (IS_ERR(active))
+		return PTR_ERR(active);
+
+	/*
+	 * Add a reference if we're newly entering the active list.
+	 * The order in which we add operations to the retirement queue is
+	 * vital here: mark_active adds to the start of the callback list,
+	 * such that subsequent callbacks are called first. Therefore we
+	 * add the active reference first and queue for it to be dropped
+	 * *last*.
+	 */
+	if (!i915_gem_active_isset(active) && !vma->active_count++) {
+		list_move_tail(&vma->vm_link, &vma->vm->active_list);
+		obj->active_count++;
+	}
+	i915_gem_active_set(active, rq);
+	GEM_BUG_ON(!i915_vma_is_active(vma));
+	GEM_BUG_ON(!obj->active_count);
+
+	obj->write_domain = 0;
+	if (flags & EXEC_OBJECT_WRITE) {
+		obj->write_domain = I915_GEM_DOMAIN_RENDER;
+
+		if (intel_fb_obj_invalidate(obj, ORIGIN_CS))
+			i915_gem_active_set(&obj->frontbuffer_write, rq);
+
+		obj->read_domains = 0;
+	}
+	obj->read_domains |= I915_GEM_GPU_DOMAINS;
+
+	if (flags & EXEC_OBJECT_NEEDS_FENCE)
+		i915_gem_active_set(&vma->last_fence, rq);
+
+	export_fence(vma, rq, flags);
+	return 0;
+}
+
+int i915_vma_unbind(struct i915_vma *vma)
+{
 	int ret;
 
-	lockdep_assert_held(&obj->base.dev->struct_mutex);
+	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
 
-	/* First wait upon any activity as retiring the request may
+	/*
+	 * First wait upon any activity as retiring the request may
 	 * have side-effects such as unpinning or even unbinding this vma.
 	 */
 	might_sleep();
-	active = i915_vma_get_active(vma);
-	if (active) {
-		int idx;
+	if (i915_vma_is_active(vma)) {
+		struct i915_vma_active *active, *n;
 
-		/* When a closed VMA is retired, it is unbound - eek.
+		/*
+		 * When a closed VMA is retired, it is unbound - eek.
 		 * In order to prevent it from being recursively closed,
 		 * take a pin on the vma so that the second unbind is
 		 * aborted.
@@ -825,33 +1059,36 @@ int i915_vma_unbind(struct i915_vma *vma)
 		 */
 		__i915_vma_pin(vma);
 
-		for_each_active(active, idx) {
-			ret = i915_gem_active_retire(&vma->last_read[idx],
-						     &vma->vm->i915->drm.struct_mutex);
-			if (ret)
-				break;
-		}
+		ret = i915_gem_active_retire(&vma->last_active,
+					     &vma->vm->i915->drm.struct_mutex);
+		if (ret)
+			goto unpin;
 
-		if (!ret) {
-			ret = i915_gem_active_retire(&vma->last_fence,
+		rbtree_postorder_for_each_entry_safe(active, n,
+						     &vma->active, node) {
+			ret = i915_gem_active_retire(&active->base,
 						     &vma->vm->i915->drm.struct_mutex);
+			if (ret)
+				goto unpin;
 		}
 
+		ret = i915_gem_active_retire(&vma->last_fence,
+					     &vma->vm->i915->drm.struct_mutex);
+unpin:
 		__i915_vma_unpin(vma);
 		if (ret)
 			return ret;
 	}
 	GEM_BUG_ON(i915_vma_is_active(vma));
 
-	if (i915_vma_is_pinned(vma))
+	if (i915_vma_is_pinned(vma)) {
+		vma_print_allocator(vma, "is pinned");
 		return -EBUSY;
+	}
 
 	if (!drm_mm_node_allocated(&vma->node))
 		return 0;
 
-	GEM_BUG_ON(obj->bind_count == 0);
-	GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
-
 	if (i915_vma_is_map_and_fenceable(vma)) {
 		/*
 		 * Check that we have flushed all writes through the GGTT
@@ -878,7 +1115,7 @@ int i915_vma_unbind(struct i915_vma *vma)
 
 	if (likely(!vma->vm->closed)) {
 		trace_i915_vma_unbind(vma);
-		vma->vm->unbind_vma(vma);
+		vma->ops->unbind_vma(vma);
 	}
 	vma->flags &= ~(I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND);
 
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index fc4294cfaa91..f06d66377107 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -26,6 +26,7 @@
 #define __I915_VMA_H__
 
 #include <linux/io-mapping.h>
+#include <linux/rbtree.h>
 
 #include <drm/drm_mm.h>
 
@@ -49,10 +50,12 @@ struct i915_vma {
 	struct drm_mm_node node;
 	struct drm_i915_gem_object *obj;
 	struct i915_address_space *vm;
+	const struct i915_vma_ops *ops;
 	struct drm_i915_fence_reg *fence;
 	struct reservation_object *resv; /** Alias of obj->resv */
 	struct sg_table *pages;
 	void __iomem *iomap;
+	void *private; /* owned by creator */
 	u64 size;
 	u64 display_alignment;
 	struct i915_page_sizes page_sizes;
@@ -92,8 +95,9 @@ struct i915_vma {
 #define I915_VMA_USERFAULT	BIT(I915_VMA_USERFAULT_BIT)
 #define I915_VMA_GGTT_WRITE	BIT(12)
 
-	unsigned int active;
-	struct i915_gem_active last_read[I915_NUM_ENGINES];
+	unsigned int active_count;
+	struct rb_root active;
+	struct i915_gem_active last_active;
 	struct i915_gem_active last_fence;
 
 	/**
@@ -136,6 +140,15 @@ i915_vma_instance(struct drm_i915_gem_object *obj,
 
 void i915_vma_unpin_and_release(struct i915_vma **p_vma);
 
+static inline bool i915_vma_is_active(struct i915_vma *vma)
+{
+	return vma->active_count;
+}
+
+int __must_check i915_vma_move_to_active(struct i915_vma *vma,
+					 struct i915_request *rq,
+					 unsigned int flags);
+
 static inline bool i915_vma_is_ggtt(const struct i915_vma *vma)
 {
 	return vma->flags & I915_VMA_GGTT;
@@ -185,34 +198,6 @@ static inline bool i915_vma_has_userfault(const struct i915_vma *vma)
 	return test_bit(I915_VMA_USERFAULT_BIT, &vma->flags);
 }
 
-static inline unsigned int i915_vma_get_active(const struct i915_vma *vma)
-{
-	return vma->active;
-}
-
-static inline bool i915_vma_is_active(const struct i915_vma *vma)
-{
-	return i915_vma_get_active(vma);
-}
-
-static inline void i915_vma_set_active(struct i915_vma *vma,
-				       unsigned int engine)
-{
-	vma->active |= BIT(engine);
-}
-
-static inline void i915_vma_clear_active(struct i915_vma *vma,
-					 unsigned int engine)
-{
-	vma->active &= ~BIT(engine);
-}
-
-static inline bool i915_vma_has_active_engine(const struct i915_vma *vma,
-					      unsigned int engine)
-{
-	return vma->active & BIT(engine);
-}
-
 static inline u32 i915_ggtt_offset(const struct i915_vma *vma)
 {
 	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
@@ -339,6 +324,12 @@ static inline void i915_vma_unpin(struct i915_vma *vma)
 	__i915_vma_unpin(vma);
 }
 
+static inline bool i915_vma_is_bound(const struct i915_vma *vma,
+				     unsigned int where)
+{
+	return vma->flags & where;
+}
+
 /**
  * i915_vma_pin_iomap - calls ioremap_wc to map the GGTT VMA via the aperture
  * @vma: VMA to iomap
@@ -407,7 +398,7 @@ static inline void __i915_vma_unpin_fence(struct i915_vma *vma)
 static inline void
 i915_vma_unpin_fence(struct i915_vma *vma)
 {
-	lockdep_assert_held(&vma->obj->base.dev->struct_mutex);
+	/* lockdep_assert_held(&vma->vm->i915->drm.struct_mutex); */
 	if (vma->fence)
 		__i915_vma_unpin_fence(vma);
 }
diff --git a/drivers/gpu/drm/i915/icl_dsi.c b/drivers/gpu/drm/i915/icl_dsi.c
new file mode 100644
index 000000000000..13830e43a4d1
--- /dev/null
+++ b/drivers/gpu/drm/i915/icl_dsi.c
@@ -0,0 +1,127 @@
+/*
+ * Copyright © 2018 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ * Authors:
+ *   Madhav Chauhan <madhav.chauhan@intel.com>
+ *   Jani Nikula <jani.nikula@intel.com>
+ */
+
+#include "intel_dsi.h"
+
+static void gen11_dsi_program_esc_clk_div(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+	u32 bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
+	u32 afe_clk_khz; /* 8X Clock */
+	u32 esc_clk_div_m;
+
+	afe_clk_khz = DIV_ROUND_CLOSEST(intel_dsi->pclk * bpp,
+					intel_dsi->lane_count);
+
+	esc_clk_div_m = DIV_ROUND_UP(afe_clk_khz, DSI_MAX_ESC_CLK);
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		I915_WRITE(ICL_DSI_ESC_CLK_DIV(port),
+			   esc_clk_div_m & ICL_ESC_CLK_DIV_MASK);
+		POSTING_READ(ICL_DSI_ESC_CLK_DIV(port));
+	}
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		I915_WRITE(ICL_DPHY_ESC_CLK_DIV(port),
+			   esc_clk_div_m & ICL_ESC_CLK_DIV_MASK);
+		POSTING_READ(ICL_DPHY_ESC_CLK_DIV(port));
+	}
+}
+
+static void gen11_dsi_enable_io_power(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+	u32 tmp;
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		tmp = I915_READ(ICL_DSI_IO_MODECTL(port));
+		tmp |= COMBO_PHY_MODE_DSI;
+		I915_WRITE(ICL_DSI_IO_MODECTL(port), tmp);
+	}
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		intel_display_power_get(dev_priv, port == PORT_A ?
+					POWER_DOMAIN_PORT_DDI_A_IO :
+					POWER_DOMAIN_PORT_DDI_B_IO);
+	}
+}
+
+static void gen11_dsi_power_up_lanes(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+	u32 tmp;
+	u32 lane_mask;
+
+	switch (intel_dsi->lane_count) {
+	case 1:
+		lane_mask = PWR_DOWN_LN_3_1_0;
+		break;
+	case 2:
+		lane_mask = PWR_DOWN_LN_3_1;
+		break;
+	case 3:
+		lane_mask = PWR_DOWN_LN_3;
+		break;
+	case 4:
+	default:
+		lane_mask = PWR_UP_ALL_LANES;
+		break;
+	}
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		tmp = I915_READ(ICL_PORT_CL_DW10(port));
+		tmp &= ~PWR_DOWN_LN_MASK;
+		I915_WRITE(ICL_PORT_CL_DW10(port), tmp | lane_mask);
+	}
+}
+
+static void gen11_dsi_enable_port_and_phy(struct intel_encoder *encoder)
+{
+	/* step 4a: power up all lanes of the DDI used by DSI */
+	gen11_dsi_power_up_lanes(encoder);
+}
+
+static void __attribute__((unused))
+gen11_dsi_pre_enable(struct intel_encoder *encoder,
+		     const struct intel_crtc_state *pipe_config,
+		     const struct drm_connector_state *conn_state)
+{
+	/* step2: enable IO power */
+	gen11_dsi_enable_io_power(encoder);
+
+	/* step3: enable DSI PLL */
+	gen11_dsi_program_esc_clk_div(encoder);
+
+	/* step4: enable DSI port and DPHY */
+	gen11_dsi_enable_port_and_phy(encoder);
+}
diff --git a/drivers/gpu/drm/i915/intel_acpi.c b/drivers/gpu/drm/i915/intel_acpi.c
index d1abf4bb7c81..6ba478e57b9b 100644
--- a/drivers/gpu/drm/i915/intel_acpi.c
+++ b/drivers/gpu/drm/i915/intel_acpi.c
@@ -12,10 +12,6 @@
 #define INTEL_DSM_REVISION_ID 1 /* For Calpella anyway... */
 #define INTEL_DSM_FN_PLATFORM_MUX_INFO 1 /* No args */
 
-static struct intel_dsm_priv {
-	acpi_handle dhandle;
-} intel_dsm_priv;
-
 static const guid_t intel_dsm_guid =
 	GUID_INIT(0x7ed873d3, 0xc2d0, 0x4e4f,
 		  0xa8, 0x54, 0x0f, 0x13, 0x17, 0xb0, 0x1c, 0x2c);
@@ -72,12 +68,12 @@ static char *intel_dsm_mux_type(u8 type)
 	}
 }
 
-static void intel_dsm_platform_mux_info(void)
+static void intel_dsm_platform_mux_info(acpi_handle dhandle)
 {
 	int i;
 	union acpi_object *pkg, *connector_count;
 
-	pkg = acpi_evaluate_dsm_typed(intel_dsm_priv.dhandle, &intel_dsm_guid,
+	pkg = acpi_evaluate_dsm_typed(dhandle, &intel_dsm_guid,
 			INTEL_DSM_REVISION_ID, INTEL_DSM_FN_PLATFORM_MUX_INFO,
 			NULL, ACPI_TYPE_PACKAGE);
 	if (!pkg) {
@@ -107,41 +103,40 @@ static void intel_dsm_platform_mux_info(void)
 	ACPI_FREE(pkg);
 }
 
-static bool intel_dsm_pci_probe(struct pci_dev *pdev)
+static acpi_handle intel_dsm_pci_probe(struct pci_dev *pdev)
 {
 	acpi_handle dhandle;
 
 	dhandle = ACPI_HANDLE(&pdev->dev);
 	if (!dhandle)
-		return false;
+		return NULL;
 
 	if (!acpi_check_dsm(dhandle, &intel_dsm_guid, INTEL_DSM_REVISION_ID,
 			    1 << INTEL_DSM_FN_PLATFORM_MUX_INFO)) {
 		DRM_DEBUG_KMS("no _DSM method for intel device\n");
-		return false;
+		return NULL;
 	}
 
-	intel_dsm_priv.dhandle = dhandle;
-	intel_dsm_platform_mux_info();
+	intel_dsm_platform_mux_info(dhandle);
 
-	return true;
+	return dhandle;
 }
 
 static bool intel_dsm_detect(void)
 {
+	acpi_handle dhandle = NULL;
 	char acpi_method_name[255] = { 0 };
 	struct acpi_buffer buffer = {sizeof(acpi_method_name), acpi_method_name};
 	struct pci_dev *pdev = NULL;
-	bool has_dsm = false;
 	int vga_count = 0;
 
 	while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) {
 		vga_count++;
-		has_dsm |= intel_dsm_pci_probe(pdev);
+		dhandle = intel_dsm_pci_probe(pdev) ?: dhandle;
 	}
 
-	if (vga_count == 2 && has_dsm) {
-		acpi_get_name(intel_dsm_priv.dhandle, ACPI_FULL_PATHNAME, &buffer);
+	if (vga_count == 2 && dhandle) {
+		acpi_get_name(dhandle, ACPI_FULL_PATHNAME, &buffer);
 		DRM_DEBUG_DRIVER("vga_switcheroo: detected DSM switching method %s handle\n",
 				 acpi_method_name);
 		return true;
diff --git a/drivers/gpu/drm/i915/intel_atomic.c b/drivers/gpu/drm/i915/intel_atomic.c
index 40285d1b91b7..b04952bacf77 100644
--- a/drivers/gpu/drm/i915/intel_atomic.c
+++ b/drivers/gpu/drm/i915/intel_atomic.c
@@ -59,7 +59,8 @@ int intel_digital_connector_atomic_get_property(struct drm_connector *connector,
 	else if (property == dev_priv->broadcast_rgb_property)
 		*val = intel_conn_state->broadcast_rgb;
 	else {
-		DRM_DEBUG_ATOMIC("Unknown property %s\n", property->name);
+		DRM_DEBUG_ATOMIC("Unknown property [PROP:%d:%s]\n",
+				 property->base.id, property->name);
 		return -EINVAL;
 	}
 
@@ -95,7 +96,8 @@ int intel_digital_connector_atomic_set_property(struct drm_connector *connector,
 		return 0;
 	}
 
-	DRM_DEBUG_ATOMIC("Unknown property %s\n", property->name);
+	DRM_DEBUG_ATOMIC("Unknown property [PROP:%d:%s]\n",
+			 property->base.id, property->name);
 	return -EINVAL;
 }
 
@@ -124,6 +126,7 @@ int intel_digital_connector_atomic_check(struct drm_connector *conn,
 	if (new_conn_state->force_audio != old_conn_state->force_audio ||
 	    new_conn_state->broadcast_rgb != old_conn_state->broadcast_rgb ||
 	    new_conn_state->base.picture_aspect_ratio != old_conn_state->base.picture_aspect_ratio ||
+	    new_conn_state->base.content_type != old_conn_state->base.content_type ||
 	    new_conn_state->base.scaling_mode != old_conn_state->base.scaling_mode)
 		crtc_state->mode_changed = true;
 
diff --git a/drivers/gpu/drm/i915/intel_atomic_plane.c b/drivers/gpu/drm/i915/intel_atomic_plane.c
index 6d068786eb41..dcba645cabb8 100644
--- a/drivers/gpu/drm/i915/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/intel_atomic_plane.c
@@ -120,12 +120,6 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_
 		&crtc_state->base.adjusted_mode;
 	int ret;
 
-	/*
-	 * Both crtc and plane->crtc could be NULL if we're updating a
-	 * property while the plane is disabled.  We don't actually have
-	 * anything driver-specific we need to test in that case, so
-	 * just return success.
-	 */
 	if (!intel_state->base.crtc && !old_plane_state->base.crtc)
 		return 0;
 
@@ -209,12 +203,6 @@ static int intel_plane_atomic_check(struct drm_plane *plane,
 	const struct drm_crtc_state *old_crtc_state;
 	struct drm_crtc_state *new_crtc_state;
 
-	/*
-	 * Both crtc and plane->crtc could be NULL if we're updating a
-	 * property while the plane is disabled.  We don't actually have
-	 * anything driver-specific we need to test in that case, so
-	 * just return success.
-	 */
 	if (!crtc)
 		return 0;
 
@@ -277,7 +265,8 @@ intel_plane_atomic_get_property(struct drm_plane *plane,
 				struct drm_property *property,
 				uint64_t *val)
 {
-	DRM_DEBUG_KMS("Unknown plane property '%s'\n", property->name);
+	DRM_DEBUG_KMS("Unknown property [PROP:%d:%s]\n",
+		      property->base.id, property->name);
 	return -EINVAL;
 }
 
@@ -299,6 +288,7 @@ intel_plane_atomic_set_property(struct drm_plane *plane,
 				struct drm_property *property,
 				uint64_t val)
 {
-	DRM_DEBUG_KMS("Unknown plane property '%s'\n", property->name);
+	DRM_DEBUG_KMS("Unknown property [PROP:%d:%s]\n",
+		      property->base.id, property->name);
 	return -EINVAL;
 }
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index 3ea566f99450..b725835b47ef 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -59,6 +59,7 @@
  */
 
 /* DP N/M table */
+#define LC_810M	810000
 #define LC_540M	540000
 #define LC_270M	270000
 #define LC_162M	162000
@@ -99,6 +100,15 @@ static const struct dp_aud_n_m dp_aud_n_m[] = {
 	{ 128000, LC_540M, 4096, 33750 },
 	{ 176400, LC_540M, 3136, 18750 },
 	{ 192000, LC_540M, 2048, 11250 },
+	{ 32000, LC_810M, 1024, 50625 },
+	{ 44100, LC_810M, 784, 28125 },
+	{ 48000, LC_810M, 512, 16875 },
+	{ 64000, LC_810M, 2048, 50625 },
+	{ 88200, LC_810M, 1568, 28125 },
+	{ 96000, LC_810M, 1024, 16875 },
+	{ 128000, LC_810M, 4096, 50625 },
+	{ 176400, LC_810M, 3136, 28125 },
+	{ 192000, LC_810M, 2048, 16875 },
 };
 
 static const struct dp_aud_n_m *
@@ -198,13 +208,13 @@ static int audio_config_hdmi_get_n(const struct intel_crtc_state *crtc_state,
 }
 
 static bool intel_eld_uptodate(struct drm_connector *connector,
-			       i915_reg_t reg_eldv, uint32_t bits_eldv,
-			       i915_reg_t reg_elda, uint32_t bits_elda,
+			       i915_reg_t reg_eldv, u32 bits_eldv,
+			       i915_reg_t reg_elda, u32 bits_elda,
 			       i915_reg_t reg_edid)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	uint8_t *eld = connector->eld;
-	uint32_t tmp;
+	const u8 *eld = connector->eld;
+	u32 tmp;
 	int i;
 
 	tmp = I915_READ(reg_eldv);
@@ -218,7 +228,7 @@ static bool intel_eld_uptodate(struct drm_connector *connector,
 	I915_WRITE(reg_elda, tmp);
 
 	for (i = 0; i < drm_eld_size(eld) / 4; i++)
-		if (I915_READ(reg_edid) != *((uint32_t *)eld + i))
+		if (I915_READ(reg_edid) != *((const u32 *)eld + i))
 			return false;
 
 	return true;
@@ -229,7 +239,7 @@ static void g4x_audio_codec_disable(struct intel_encoder *encoder,
 				    const struct drm_connector_state *old_conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	uint32_t eldv, tmp;
+	u32 eldv, tmp;
 
 	DRM_DEBUG_KMS("Disable audio codec\n");
 
@@ -251,12 +261,12 @@ static void g4x_audio_codec_enable(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct drm_connector *connector = conn_state->connector;
-	uint8_t *eld = connector->eld;
-	uint32_t eldv;
-	uint32_t tmp;
+	const u8 *eld = connector->eld;
+	u32 eldv;
+	u32 tmp;
 	int len, i;
 
-	DRM_DEBUG_KMS("Enable audio codec, %u bytes ELD\n", eld[2]);
+	DRM_DEBUG_KMS("Enable audio codec, %u bytes ELD\n", drm_eld_size(eld));
 
 	tmp = I915_READ(G4X_AUD_VID_DID);
 	if (tmp == INTEL_AUDIO_DEVBLC || tmp == INTEL_AUDIO_DEVCL)
@@ -278,7 +288,7 @@ static void g4x_audio_codec_enable(struct intel_encoder *encoder,
 	len = min(drm_eld_size(eld) / 4, len);
 	DRM_DEBUG_DRIVER("ELD size %d\n", len);
 	for (i = 0; i < len; i++)
-		I915_WRITE(G4X_HDMIW_HDMIEDID, *((uint32_t *)eld + i));
+		I915_WRITE(G4X_HDMIW_HDMIEDID, *((const u32 *)eld + i));
 
 	tmp = I915_READ(G4X_AUD_CNTL_ST);
 	tmp |= eldv;
@@ -393,7 +403,7 @@ static void hsw_audio_codec_disable(struct intel_encoder *encoder,
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
 	enum pipe pipe = crtc->pipe;
-	uint32_t tmp;
+	u32 tmp;
 
 	DRM_DEBUG_KMS("Disable audio codec on pipe %c\n", pipe_name(pipe));
 
@@ -426,8 +436,8 @@ static void hsw_audio_codec_enable(struct intel_encoder *encoder,
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_connector *connector = conn_state->connector;
 	enum pipe pipe = crtc->pipe;
-	const uint8_t *eld = connector->eld;
-	uint32_t tmp;
+	const u8 *eld = connector->eld;
+	u32 tmp;
 	int len, i;
 
 	DRM_DEBUG_KMS("Enable audio codec on pipe %c, %u bytes ELD\n",
@@ -456,7 +466,7 @@ static void hsw_audio_codec_enable(struct intel_encoder *encoder,
 	/* Up to 84 bytes of hw ELD buffer */
 	len = min(drm_eld_size(eld), 84);
 	for (i = 0; i < len / 4; i++)
-		I915_WRITE(HSW_AUD_EDID_DATA(pipe), *((uint32_t *)eld + i));
+		I915_WRITE(HSW_AUD_EDID_DATA(pipe), *((const u32 *)eld + i));
 
 	/* ELD valid */
 	tmp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD);
@@ -477,7 +487,7 @@ static void ilk_audio_codec_disable(struct intel_encoder *encoder,
 	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
 	enum pipe pipe = crtc->pipe;
 	enum port port = encoder->port;
-	uint32_t tmp, eldv;
+	u32 tmp, eldv;
 	i915_reg_t aud_config, aud_cntrl_st2;
 
 	DRM_DEBUG_KMS("Disable audio codec on port %c, pipe %c\n",
@@ -524,8 +534,8 @@ static void ilk_audio_codec_enable(struct intel_encoder *encoder,
 	struct drm_connector *connector = conn_state->connector;
 	enum pipe pipe = crtc->pipe;
 	enum port port = encoder->port;
-	uint8_t *eld = connector->eld;
-	uint32_t tmp, eldv;
+	const u8 *eld = connector->eld;
+	u32 tmp, eldv;
 	int len, i;
 	i915_reg_t hdmiw_hdmiedid, aud_config, aud_cntl_st, aud_cntrl_st2;
 
@@ -575,7 +585,7 @@ static void ilk_audio_codec_enable(struct intel_encoder *encoder,
 	/* Up to 84 bytes of hw ELD buffer */
 	len = min(drm_eld_size(eld), 84);
 	for (i = 0; i < len / 4; i++)
-		I915_WRITE(hdmiw_hdmiedid, *((uint32_t *)eld + i));
+		I915_WRITE(hdmiw_hdmiedid, *((const u32 *)eld + i));
 
 	/* ELD valid */
 	tmp = I915_READ(aud_cntrl_st2);
@@ -639,11 +649,12 @@ void intel_audio_codec_enable(struct intel_encoder *encoder,
 	dev_priv->av_enc_map[pipe] = encoder;
 	mutex_unlock(&dev_priv->av_mutex);
 
-	if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify) {
+	if (acomp && acomp->base.audio_ops &&
+	    acomp->base.audio_ops->pin_eld_notify) {
 		/* audio drivers expect pipe = -1 to indicate Non-MST cases */
 		if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST))
 			pipe = -1;
-		acomp->audio_ops->pin_eld_notify(acomp->audio_ops->audio_ptr,
+		acomp->base.audio_ops->pin_eld_notify(acomp->base.audio_ops->audio_ptr,
 						 (int) port, (int) pipe);
 	}
 
@@ -681,11 +692,12 @@ void intel_audio_codec_disable(struct intel_encoder *encoder,
 	dev_priv->av_enc_map[pipe] = NULL;
 	mutex_unlock(&dev_priv->av_mutex);
 
-	if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify) {
+	if (acomp && acomp->base.audio_ops &&
+	    acomp->base.audio_ops->pin_eld_notify) {
 		/* audio drivers expect pipe = -1 to indicate Non-MST cases */
 		if (!intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DP_MST))
 			pipe = -1;
-		acomp->audio_ops->pin_eld_notify(acomp->audio_ops->audio_ptr,
+		acomp->base.audio_ops->pin_eld_notify(acomp->base.audio_ops->audio_ptr,
 						 (int) port, (int) pipe);
 	}
 
@@ -880,7 +892,7 @@ static int i915_audio_component_get_eld(struct device *kdev, int port,
 	return ret;
 }
 
-static const struct i915_audio_component_ops i915_audio_component_ops = {
+static const struct drm_audio_component_ops i915_audio_component_ops = {
 	.owner		= THIS_MODULE,
 	.get_power	= i915_audio_component_get_power,
 	.put_power	= i915_audio_component_put_power,
@@ -897,12 +909,12 @@ static int i915_audio_component_bind(struct device *i915_kdev,
 	struct drm_i915_private *dev_priv = kdev_to_i915(i915_kdev);
 	int i;
 
-	if (WARN_ON(acomp->ops || acomp->dev))
+	if (WARN_ON(acomp->base.ops || acomp->base.dev))
 		return -EEXIST;
 
 	drm_modeset_lock_all(&dev_priv->drm);
-	acomp->ops = &i915_audio_component_ops;
-	acomp->dev = i915_kdev;
+	acomp->base.ops = &i915_audio_component_ops;
+	acomp->base.dev = i915_kdev;
 	BUILD_BUG_ON(MAX_PORTS != I915_MAX_PORTS);
 	for (i = 0; i < ARRAY_SIZE(acomp->aud_sample_rate); i++)
 		acomp->aud_sample_rate[i] = 0;
@@ -919,8 +931,8 @@ static void i915_audio_component_unbind(struct device *i915_kdev,
 	struct drm_i915_private *dev_priv = kdev_to_i915(i915_kdev);
 
 	drm_modeset_lock_all(&dev_priv->drm);
-	acomp->ops = NULL;
-	acomp->dev = NULL;
+	acomp->base.ops = NULL;
+	acomp->base.dev = NULL;
 	dev_priv->audio_component = NULL;
 	drm_modeset_unlock_all(&dev_priv->drm);
 }
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 54270bdde100..1faa494e2bc9 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -267,8 +267,6 @@ parse_lfp_panel_data(struct drm_i915_private *dev_priv,
 	if (!lvds_lfp_data_ptrs)
 		return;
 
-	dev_priv->vbt.lvds_vbt = 1;
-
 	panel_dvo_timing = get_lvds_dvo_timing(lvds_lfp_data,
 					       lvds_lfp_data_ptrs,
 					       panel_type);
@@ -518,8 +516,31 @@ parse_driver_features(struct drm_i915_private *dev_priv,
 	if (!driver)
 		return;
 
-	if (driver->lvds_config == BDB_DRIVER_FEATURE_EDP)
-		dev_priv->vbt.edp.support = 1;
+	if (INTEL_GEN(dev_priv) >= 5) {
+		/*
+		 * Note that we consider BDB_DRIVER_FEATURE_INT_SDVO_LVDS
+		 * to mean "eDP". The VBT spec doesn't agree with that
+		 * interpretation, but real world VBTs seem to.
+		 */
+		if (driver->lvds_config != BDB_DRIVER_FEATURE_INT_LVDS)
+			dev_priv->vbt.int_lvds_support = 0;
+	} else {
+		/*
+		 * FIXME it's not clear which BDB version has the LVDS config
+		 * bits defined. Revision history in the VBT spec says:
+		 * "0.92 | Add two definitions for VBT value of LVDS Active
+		 *  Config (00b and 11b values defined) | 06/13/2005"
+		 * but does not the specify the BDB version.
+		 *
+		 * So far version 134 (on i945gm) is the oldest VBT observed
+		 * in the wild with the bits correctly populated. Version
+		 * 108 (on i85x) does not have the bits correctly populated.
+		 */
+		if (bdb->version >= 134 &&
+		    driver->lvds_config != BDB_DRIVER_FEATURE_INT_LVDS &&
+		    driver->lvds_config != BDB_DRIVER_FEATURE_INT_SDVO_LVDS)
+			dev_priv->vbt.int_lvds_support = 0;
+	}
 
 	DRM_DEBUG_KMS("DRRS State Enabled:%d\n", driver->drrs_enabled);
 	/*
@@ -542,11 +563,8 @@ parse_edp(struct drm_i915_private *dev_priv, const struct bdb_header *bdb)
 	int panel_type = dev_priv->vbt.panel_type;
 
 	edp = find_section(bdb, BDB_EDP);
-	if (!edp) {
-		if (dev_priv->vbt.edp.support)
-			DRM_DEBUG_KMS("No eDP BDB found but eDP panel supported.\n");
+	if (!edp)
 		return;
-	}
 
 	switch ((edp->color_depth >> (panel_type * 2)) & 3) {
 	case EDP_18BPP:
@@ -634,7 +652,7 @@ parse_edp(struct drm_i915_private *dev_priv, const struct bdb_header *bdb)
 	}
 
 	if (bdb->version >= 173) {
-		uint8_t vswing;
+		u8 vswing;
 
 		/* Don't read from VBT if module parameter has valid value*/
 		if (i915_modparams.edp_vswing) {
@@ -688,8 +706,54 @@ parse_psr(struct drm_i915_private *dev_priv, const struct bdb_header *bdb)
 		break;
 	}
 
-	dev_priv->vbt.psr.tp1_wakeup_time = psr_table->tp1_wakeup_time;
-	dev_priv->vbt.psr.tp2_tp3_wakeup_time = psr_table->tp2_tp3_wakeup_time;
+	/*
+	 * New psr options 0=500us, 1=100us, 2=2500us, 3=0us
+	 * Old decimal value is wake up time in multiples of 100 us.
+	 */
+	if (bdb->version >= 205 &&
+	    (IS_GEN9_BC(dev_priv) || IS_GEMINILAKE(dev_priv) ||
+	     INTEL_GEN(dev_priv) >= 10)) {
+		switch (psr_table->tp1_wakeup_time) {
+		case 0:
+			dev_priv->vbt.psr.tp1_wakeup_time_us = 500;
+			break;
+		case 1:
+			dev_priv->vbt.psr.tp1_wakeup_time_us = 100;
+			break;
+		case 3:
+			dev_priv->vbt.psr.tp1_wakeup_time_us = 0;
+			break;
+		default:
+			DRM_DEBUG_KMS("VBT tp1 wakeup time value %d is outside range[0-3], defaulting to max value 2500us\n",
+					psr_table->tp1_wakeup_time);
+			/* fallthrough */
+		case 2:
+			dev_priv->vbt.psr.tp1_wakeup_time_us = 2500;
+			break;
+		}
+
+		switch (psr_table->tp2_tp3_wakeup_time) {
+		case 0:
+			dev_priv->vbt.psr.tp2_tp3_wakeup_time_us = 500;
+			break;
+		case 1:
+			dev_priv->vbt.psr.tp2_tp3_wakeup_time_us = 100;
+			break;
+		case 3:
+			dev_priv->vbt.psr.tp2_tp3_wakeup_time_us = 0;
+			break;
+		default:
+			DRM_DEBUG_KMS("VBT tp2_tp3 wakeup time value %d is outside range[0-3], defaulting to max value 2500us\n",
+					psr_table->tp2_tp3_wakeup_time);
+			/* fallthrough */
+		case 2:
+			dev_priv->vbt.psr.tp2_tp3_wakeup_time_us = 2500;
+		break;
+		}
+	} else {
+		dev_priv->vbt.psr.tp1_wakeup_time_us = psr_table->tp1_wakeup_time * 100;
+		dev_priv->vbt.psr.tp2_tp3_wakeup_time_us = psr_table->tp2_tp3_wakeup_time * 100;
+	}
 }
 
 static void parse_dsi_backlight_ports(struct drm_i915_private *dev_priv,
@@ -902,7 +966,7 @@ static int goto_next_sequence_v3(const u8 *data, int index, int total)
 	 * includes MIPI_SEQ_ELEM_END byte, excludes the final MIPI_SEQ_END
 	 * byte.
 	 */
-	size_of_sequence = *((const uint32_t *)(data + index));
+	size_of_sequence = *((const u32 *)(data + index));
 	index += 4;
 
 	seq_end = index + size_of_sequence;
@@ -1197,18 +1261,37 @@ static const u8 cnp_ddc_pin_map[] = {
 	[DDC_BUS_DDI_F] = GMBUS_PIN_3_BXT, /* sic */
 };
 
+static const u8 icp_ddc_pin_map[] = {
+	[ICL_DDC_BUS_DDI_A] = GMBUS_PIN_1_BXT,
+	[ICL_DDC_BUS_DDI_B] = GMBUS_PIN_2_BXT,
+	[ICL_DDC_BUS_PORT_1] = GMBUS_PIN_9_TC1_ICP,
+	[ICL_DDC_BUS_PORT_2] = GMBUS_PIN_10_TC2_ICP,
+	[ICL_DDC_BUS_PORT_3] = GMBUS_PIN_11_TC3_ICP,
+	[ICL_DDC_BUS_PORT_4] = GMBUS_PIN_12_TC4_ICP,
+};
+
 static u8 map_ddc_pin(struct drm_i915_private *dev_priv, u8 vbt_pin)
 {
-	if (HAS_PCH_CNP(dev_priv)) {
-		if (vbt_pin < ARRAY_SIZE(cnp_ddc_pin_map)) {
-			return cnp_ddc_pin_map[vbt_pin];
-		} else {
-			DRM_DEBUG_KMS("Ignoring alternate pin: VBT claims DDC pin %d, which is not valid for this platform\n", vbt_pin);
-			return 0;
-		}
+	const u8 *ddc_pin_map;
+	int n_entries;
+
+	if (HAS_PCH_ICP(dev_priv)) {
+		ddc_pin_map = icp_ddc_pin_map;
+		n_entries = ARRAY_SIZE(icp_ddc_pin_map);
+	} else if (HAS_PCH_CNP(dev_priv)) {
+		ddc_pin_map = cnp_ddc_pin_map;
+		n_entries = ARRAY_SIZE(cnp_ddc_pin_map);
+	} else {
+		/* Assuming direct map */
+		return vbt_pin;
 	}
 
-	return vbt_pin;
+	if (vbt_pin < n_entries && ddc_pin_map[vbt_pin] != 0)
+		return ddc_pin_map[vbt_pin];
+
+	DRM_DEBUG_KMS("Ignoring alternate pin: VBT claims DDC pin %d, which is not valid for this platform\n",
+		      vbt_pin);
+	return 0;
 }
 
 static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port,
@@ -1504,7 +1587,6 @@ init_vbt_defaults(struct drm_i915_private *dev_priv)
 
 	/* LFP panel data */
 	dev_priv->vbt.lvds_dither = 1;
-	dev_priv->vbt.lvds_vbt = 0;
 
 	/* SDVO panel data */
 	dev_priv->vbt.sdvo_lvds_vbt_mode = NULL;
@@ -1513,6 +1595,9 @@ init_vbt_defaults(struct drm_i915_private *dev_priv)
 	dev_priv->vbt.int_tv_support = 1;
 	dev_priv->vbt.int_crt_support = 1;
 
+	/* driver features */
+	dev_priv->vbt.int_lvds_support = 1;
+
 	/* Default to using SSC */
 	dev_priv->vbt.lvds_use_ssc = 1;
 	/*
@@ -1636,7 +1721,7 @@ void intel_bios_init(struct drm_i915_private *dev_priv)
 	const struct bdb_header *bdb;
 	u8 __iomem *bios = NULL;
 
-	if (HAS_PCH_NOP(dev_priv)) {
+	if (INTEL_INFO(dev_priv)->num_pipes == 0) {
 		DRM_DEBUG_KMS("Skipping VBT init due to disabled display.\n");
 		return;
 	}
diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c
index 18e643df523e..1db6ba7d926e 100644
--- a/drivers/gpu/drm/i915/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c
@@ -98,12 +98,14 @@ static void intel_breadcrumbs_hangcheck(struct timer_list *t)
 	struct intel_engine_cs *engine =
 		from_timer(engine, t, breadcrumbs.hangcheck);
 	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+	unsigned int irq_count;
 
 	if (!b->irq_armed)
 		return;
 
-	if (b->hangcheck_interrupts != atomic_read(&engine->irq_count)) {
-		b->hangcheck_interrupts = atomic_read(&engine->irq_count);
+	irq_count = READ_ONCE(b->irq_count);
+	if (b->hangcheck_interrupts != irq_count) {
+		b->hangcheck_interrupts = irq_count;
 		mod_timer(&b->hangcheck, wait_timeout());
 		return;
 	}
@@ -272,13 +274,14 @@ static bool use_fake_irq(const struct intel_breadcrumbs *b)
 	if (!test_bit(engine->id, &engine->i915->gpu_error.missed_irq_rings))
 		return false;
 
-	/* Only start with the heavy weight fake irq timer if we have not
+	/*
+	 * Only start with the heavy weight fake irq timer if we have not
 	 * seen any interrupts since enabling it the first time. If the
 	 * interrupts are still arriving, it means we made a mistake in our
 	 * engine->seqno_barrier(), a timing error that should be transient
 	 * and unlikely to reoccur.
 	 */
-	return atomic_read(&engine->irq_count) == b->hangcheck_interrupts;
+	return READ_ONCE(b->irq_count) == b->hangcheck_interrupts;
 }
 
 static void enable_fake_irq(struct intel_breadcrumbs *b)
@@ -846,8 +849,9 @@ static void cancel_fake_irq(struct intel_engine_cs *engine)
 void intel_engine_reset_breadcrumbs(struct intel_engine_cs *engine)
 {
 	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+	unsigned long flags;
 
-	spin_lock_irq(&b->irq_lock);
+	spin_lock_irqsave(&b->irq_lock, flags);
 
 	/*
 	 * Leave the fake_irq timer enabled (if it is running), but clear the
@@ -871,7 +875,7 @@ void intel_engine_reset_breadcrumbs(struct intel_engine_cs *engine)
 	 */
 	clear_bit(ENGINE_IRQ_BREADCRUMB, &engine->irq_posted);
 
-	spin_unlock_irq(&b->irq_lock);
+	spin_unlock_irqrestore(&b->irq_lock, flags);
 }
 
 void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c
index 704ddb4d3ca7..29075c763428 100644
--- a/drivers/gpu/drm/i915/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/intel_cdclk.c
@@ -316,6 +316,7 @@ static void pnv_get_cdclk(struct drm_i915_private *dev_priv,
 		break;
 	default:
 		DRM_ERROR("Unknown pnv display core clock 0x%04x\n", gcfgc);
+		/* fall through */
 	case GC_DISPLAY_CLOCK_133_MHZ_PNV:
 		cdclk_state->cdclk = 133333;
 		break;
@@ -991,6 +992,16 @@ static void skl_set_cdclk(struct drm_i915_private *dev_priv,
 	u32 freq_select, cdclk_ctl;
 	int ret;
 
+	/*
+	 * Based on WA#1183 CDCLK rates 308 and 617MHz CDCLK rates are
+	 * unsupported on SKL. In theory this should never happen since only
+	 * the eDP1.4 2.16 and 4.32Gbps rates require it, but eDP1.4 is not
+	 * supported on SKL either, see the above WA. WARN whenever trying to
+	 * use the corresponding VCO freq as that always leads to using the
+	 * minimum 308MHz CDCLK.
+	 */
+	WARN_ON_ONCE(IS_SKYLAKE(dev_priv) && vco == 8640000);
+
 	mutex_lock(&dev_priv->pcu_lock);
 	ret = skl_pcode_request(dev_priv, SKL_PCODE_CDCLK_CONTROL,
 				SKL_CDCLK_PREPARE_FOR_CHANGE,
@@ -1787,6 +1798,7 @@ static int icl_calc_cdclk(int min_cdclk, unsigned int ref)
 	switch (ref) {
 	default:
 		MISSING_CASE(ref);
+		/* fall through */
 	case 24000:
 		ranges = ranges_24;
 		break;
@@ -1814,6 +1826,7 @@ static int icl_calc_cdclk_pll_vco(struct drm_i915_private *dev_priv, int cdclk)
 	switch (cdclk) {
 	default:
 		MISSING_CASE(cdclk);
+		/* fall through */
 	case 307200:
 	case 556800:
 	case 652800:
@@ -1861,11 +1874,36 @@ static void icl_set_cdclk(struct drm_i915_private *dev_priv,
 			      skl_cdclk_decimal(cdclk));
 
 	mutex_lock(&dev_priv->pcu_lock);
-	/* TODO: add proper DVFS support. */
-	sandybridge_pcode_write(dev_priv, SKL_PCODE_CDCLK_CONTROL, 2);
+	sandybridge_pcode_write(dev_priv, SKL_PCODE_CDCLK_CONTROL,
+				cdclk_state->voltage_level);
 	mutex_unlock(&dev_priv->pcu_lock);
 
 	intel_update_cdclk(dev_priv);
+
+	/*
+	 * Can't read out the voltage level :(
+	 * Let's just assume everything is as expected.
+	 */
+	dev_priv->cdclk.hw.voltage_level = cdclk_state->voltage_level;
+}
+
+static u8 icl_calc_voltage_level(int cdclk)
+{
+	switch (cdclk) {
+	case 50000:
+	case 307200:
+	case 312000:
+		return 0;
+	case 556800:
+	case 552000:
+		return 1;
+	default:
+		MISSING_CASE(cdclk);
+		/* fall through */
+	case 652800:
+	case 648000:
+		return 2;
+	}
 }
 
 static void icl_get_cdclk(struct drm_i915_private *dev_priv,
@@ -1879,6 +1917,7 @@ static void icl_get_cdclk(struct drm_i915_private *dev_priv,
 	switch (val & ICL_DSSM_CDCLK_PLL_REFCLK_MASK) {
 	default:
 		MISSING_CASE(val);
+		/* fall through */
 	case ICL_DSSM_CDCLK_PLL_REFCLK_24MHz:
 		cdclk_state->ref = 24000;
 		break;
@@ -1899,7 +1938,7 @@ static void icl_get_cdclk(struct drm_i915_private *dev_priv,
 		 */
 		cdclk_state->vco = 0;
 		cdclk_state->cdclk = cdclk_state->bypass;
-		return;
+		goto out;
 	}
 
 	cdclk_state->vco = (val & BXT_DE_PLL_RATIO_MASK) * cdclk_state->ref;
@@ -1908,6 +1947,14 @@ static void icl_get_cdclk(struct drm_i915_private *dev_priv,
 	WARN_ON((val & BXT_CDCLK_CD2X_DIV_SEL_MASK) != 0);
 
 	cdclk_state->cdclk = cdclk_state->vco / 2;
+
+out:
+	/*
+	 * Can't read this out :( Let's assume it's
+	 * at least what the CDCLK frequency requires.
+	 */
+	cdclk_state->voltage_level =
+		icl_calc_voltage_level(cdclk_state->cdclk);
 }
 
 /**
@@ -1950,6 +1997,8 @@ sanitize:
 	sanitized_state.cdclk = icl_calc_cdclk(0, sanitized_state.ref);
 	sanitized_state.vco = icl_calc_cdclk_pll_vco(dev_priv,
 						     sanitized_state.cdclk);
+	sanitized_state.voltage_level =
+				icl_calc_voltage_level(sanitized_state.cdclk);
 
 	icl_set_cdclk(dev_priv, &sanitized_state);
 }
@@ -1967,6 +2016,7 @@ void icl_uninit_cdclk(struct drm_i915_private *dev_priv)
 
 	cdclk_state.cdclk = cdclk_state.bypass;
 	cdclk_state.vco = 0;
+	cdclk_state.voltage_level = icl_calc_voltage_level(cdclk_state.cdclk);
 
 	icl_set_cdclk(dev_priv, &cdclk_state);
 }
@@ -2470,6 +2520,9 @@ static int icl_modeset_calc_cdclk(struct drm_atomic_state *state)
 
 	intel_state->cdclk.logical.vco = vco;
 	intel_state->cdclk.logical.cdclk = cdclk;
+	intel_state->cdclk.logical.voltage_level =
+		max(icl_calc_voltage_level(cdclk),
+		    cnl_compute_min_voltage_level(intel_state));
 
 	if (!intel_state->active_crtcs) {
 		cdclk = icl_calc_cdclk(0, ref);
@@ -2477,6 +2530,8 @@ static int icl_modeset_calc_cdclk(struct drm_atomic_state *state)
 
 		intel_state->cdclk.actual.vco = vco;
 		intel_state->cdclk.actual.cdclk = cdclk;
+		intel_state->cdclk.actual.voltage_level =
+			icl_calc_voltage_level(cdclk);
 	} else {
 		intel_state->cdclk.actual = intel_state->cdclk.logical;
 	}
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 072b326d5ee0..0c6bf82bb059 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -63,33 +63,35 @@ static struct intel_crt *intel_attached_crt(struct drm_connector *connector)
 	return intel_encoder_to_crt(intel_attached_encoder(connector));
 }
 
+bool intel_crt_port_enabled(struct drm_i915_private *dev_priv,
+			    i915_reg_t adpa_reg, enum pipe *pipe)
+{
+	u32 val;
+
+	val = I915_READ(adpa_reg);
+
+	/* asserts want to know the pipe even if the port is disabled */
+	if (HAS_PCH_CPT(dev_priv))
+		*pipe = (val & ADPA_PIPE_SEL_MASK_CPT) >> ADPA_PIPE_SEL_SHIFT_CPT;
+	else
+		*pipe = (val & ADPA_PIPE_SEL_MASK) >> ADPA_PIPE_SEL_SHIFT;
+
+	return val & ADPA_DAC_ENABLE;
+}
+
 static bool intel_crt_get_hw_state(struct intel_encoder *encoder,
 				   enum pipe *pipe)
 {
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_crt *crt = intel_encoder_to_crt(encoder);
-	u32 tmp;
 	bool ret;
 
 	if (!intel_display_power_get_if_enabled(dev_priv,
 						encoder->power_domain))
 		return false;
 
-	ret = false;
-
-	tmp = I915_READ(crt->adpa_reg);
+	ret = intel_crt_port_enabled(dev_priv, crt->adpa_reg, pipe);
 
-	if (!(tmp & ADPA_DAC_ENABLE))
-		goto out;
-
-	if (HAS_PCH_CPT(dev_priv))
-		*pipe = PORT_TO_PIPE_CPT(tmp);
-	else
-		*pipe = PORT_TO_PIPE(tmp);
-
-	ret = true;
-out:
 	intel_display_power_put(dev_priv, encoder->power_domain);
 
 	return ret;
@@ -168,11 +170,9 @@ static void intel_crt_set_dpms(struct intel_encoder *encoder,
 	if (HAS_PCH_LPT(dev_priv))
 		; /* Those bits don't exist here */
 	else if (HAS_PCH_CPT(dev_priv))
-		adpa |= PORT_TRANS_SEL_CPT(crtc->pipe);
-	else if (crtc->pipe == 0)
-		adpa |= ADPA_PIPE_A_SELECT;
+		adpa |= ADPA_PIPE_SEL_CPT(crtc->pipe);
 	else
-		adpa |= ADPA_PIPE_B_SELECT;
+		adpa |= ADPA_PIPE_SEL(crtc->pipe);
 
 	if (!HAS_PCH_SPLIT(dev_priv))
 		I915_WRITE(BCLRPAT(crtc->pipe), 0);
@@ -232,6 +232,8 @@ static void hsw_post_disable_crt(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
+	intel_ddi_disable_pipe_clock(old_crtc_state);
+
 	pch_post_disable_crt(encoder, old_crtc_state, old_conn_state);
 
 	lpt_disable_pch_transcoder(dev_priv);
@@ -268,6 +270,8 @@ static void hsw_pre_enable_crt(struct intel_encoder *encoder,
 	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
 
 	dev_priv->display.fdi_link_train(crtc, crtc_state);
+
+	intel_ddi_enable_pipe_clock(crtc_state);
 }
 
 static void hsw_enable_crt(struct intel_encoder *encoder,
@@ -333,6 +337,10 @@ intel_crt_mode_valid(struct drm_connector *connector,
 	    (ironlake_get_lanes_required(mode->clock, 270000, 24) > 2))
 		return MODE_CLOCK_HIGH;
 
+	/* HSW/BDW FDI limited to 4k */
+	if (mode->hdisplay > 4096)
+		return MODE_H_ILLEGAL;
+
 	return MODE_OK;
 }
 
@@ -375,6 +383,11 @@ static bool hsw_crt_compute_config(struct intel_encoder *encoder,
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return false;
 
+	/* HSW/BDW FDI limited to 4k */
+	if (adjusted_mode->crtc_hdisplay > 4096 ||
+	    adjusted_mode->crtc_hblank_start > 4096)
+		return false;
+
 	pipe_config->has_pch_encoder = true;
 
 	/* LPT FDI RX only supports 8bpc. */
@@ -513,7 +526,7 @@ static bool intel_crt_detect_hotplug(struct drm_connector *connector)
 	 * to get a reliable result.
 	 */
 
-	if (IS_G4X(dev_priv) && !IS_GM45(dev_priv))
+	if (IS_G45(dev_priv))
 		tries = 2;
 	else
 		tries = 1;
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index fed26d6e4e27..39d66f8493fa 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -915,7 +915,14 @@ static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port por
 
 	level = dev_priv->vbt.ddi_port_info[port].hdmi_level_shift;
 
-	if (IS_CANNONLAKE(dev_priv)) {
+	if (IS_ICELAKE(dev_priv)) {
+		if (port == PORT_A || port == PORT_B)
+			icl_get_combo_buf_trans(dev_priv, port,
+						INTEL_OUTPUT_HDMI, &n_entries);
+		else
+			n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations);
+		default_entry = n_entries - 1;
+	} else if (IS_CANNONLAKE(dev_priv)) {
 		cnl_get_buf_trans_hdmi(dev_priv, &n_entries);
 		default_entry = n_entries - 1;
 	} else if (IS_GEN9_LP(dev_priv)) {
@@ -1055,14 +1062,31 @@ static uint32_t hsw_pll_to_ddi_pll_sel(const struct intel_shared_dpll *pll)
 static uint32_t icl_pll_to_ddi_pll_sel(struct intel_encoder *encoder,
 				       const struct intel_shared_dpll *pll)
 {
+	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
+	int clock = crtc->config->port_clock;
 	const enum intel_dpll_id id = pll->info->id;
 
 	switch (id) {
 	default:
 		MISSING_CASE(id);
+		/* fall through */
 	case DPLL_ID_ICL_DPLL0:
 	case DPLL_ID_ICL_DPLL1:
 		return DDI_CLK_SEL_NONE;
+	case DPLL_ID_ICL_TBTPLL:
+		switch (clock) {
+		case 162000:
+			return DDI_CLK_SEL_TBT_162;
+		case 270000:
+			return DDI_CLK_SEL_TBT_270;
+		case 540000:
+			return DDI_CLK_SEL_TBT_540;
+		case 810000:
+			return DDI_CLK_SEL_TBT_810;
+		default:
+			MISSING_CASE(clock);
+			break;
+		}
 	case DPLL_ID_ICL_MGPLL1:
 	case DPLL_ID_ICL_MGPLL2:
 	case DPLL_ID_ICL_MGPLL3:
@@ -1243,35 +1267,6 @@ intel_ddi_get_crtc_encoder(struct intel_crtc *crtc)
 	return ret;
 }
 
-/* Finds the only possible encoder associated with the given CRTC. */
-struct intel_encoder *
-intel_ddi_get_crtc_new_encoder(struct intel_crtc_state *crtc_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct intel_encoder *ret = NULL;
-	struct drm_atomic_state *state;
-	struct drm_connector *connector;
-	struct drm_connector_state *connector_state;
-	int num_encoders = 0;
-	int i;
-
-	state = crtc_state->base.state;
-
-	for_each_new_connector_in_state(state, connector, connector_state, i) {
-		if (connector_state->crtc != crtc_state->base.crtc)
-			continue;
-
-		ret = to_intel_encoder(connector_state->best_encoder);
-		num_encoders++;
-	}
-
-	WARN(num_encoders != 1, "%d encoders on crtc for pipe %c\n", num_encoders,
-	     pipe_name(crtc->pipe));
-
-	BUG_ON(ret == NULL);
-	return ret;
-}
-
 #define LC_FREQ 2700
 
 static int hsw_ddi_calc_wrpll_link(struct drm_i915_private *dev_priv,
@@ -1374,8 +1369,13 @@ static int cnl_calc_wrpll_link(struct drm_i915_private *dev_priv,
 	uint32_t cfgcr0, cfgcr1;
 	uint32_t p0, p1, p2, dco_freq, ref_clock;
 
-	cfgcr0 = I915_READ(CNL_DPLL_CFGCR0(pll_id));
-	cfgcr1 = I915_READ(CNL_DPLL_CFGCR1(pll_id));
+	if (INTEL_GEN(dev_priv) >= 11) {
+		cfgcr0 = I915_READ(ICL_DPLL_CFGCR0(pll_id));
+		cfgcr1 = I915_READ(ICL_DPLL_CFGCR1(pll_id));
+	} else {
+		cfgcr0 = I915_READ(CNL_DPLL_CFGCR0(pll_id));
+		cfgcr1 = I915_READ(CNL_DPLL_CFGCR1(pll_id));
+	}
 
 	p0 = cfgcr1 & DPLL_CFGCR1_PDIV_MASK;
 	p2 = cfgcr1 & DPLL_CFGCR1_KDIV_MASK;
@@ -1451,6 +1451,30 @@ static void ddi_dotclock_get(struct intel_crtc_state *pipe_config)
 	pipe_config->base.adjusted_mode.crtc_clock = dotclock;
 }
 
+static void icl_ddi_clock_get(struct intel_encoder *encoder,
+			      struct intel_crtc_state *pipe_config)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	enum port port = encoder->port;
+	int link_clock = 0;
+	uint32_t pll_id;
+
+	pll_id = intel_get_shared_dpll_id(dev_priv, pipe_config->shared_dpll);
+	if (port == PORT_A || port == PORT_B) {
+		if (intel_crtc_has_type(pipe_config, INTEL_OUTPUT_HDMI))
+			link_clock = cnl_calc_wrpll_link(dev_priv, pll_id);
+		else
+			link_clock = icl_calc_dp_combo_pll_link(dev_priv,
+								pll_id);
+	} else {
+		/* FIXME - Add for MG PLL */
+		WARN(1, "MG PLL clock_get code not implemented yet\n");
+	}
+
+	pipe_config->port_clock = link_clock;
+	ddi_dotclock_get(pipe_config);
+}
+
 static void cnl_ddi_clock_get(struct intel_encoder *encoder,
 			      struct intel_crtc_state *pipe_config)
 {
@@ -1644,6 +1668,8 @@ static void intel_ddi_clock_get(struct intel_encoder *encoder,
 		bxt_ddi_clock_get(encoder, pipe_config);
 	else if (IS_CANNONLAKE(dev_priv))
 		cnl_ddi_clock_get(encoder, pipe_config);
+	else if (IS_ICELAKE(dev_priv))
+		icl_ddi_clock_get(encoder, pipe_config);
 }
 
 void intel_ddi_set_pipe_settings(const struct intel_crtc_state *crtc_state)
@@ -1967,15 +1993,50 @@ out:
 	return ret;
 }
 
-static u64 intel_ddi_get_power_domains(struct intel_encoder *encoder)
+static inline enum intel_display_power_domain
+intel_ddi_main_link_aux_domain(struct intel_dp *intel_dp)
+{
+	/* CNL HW requires corresponding AUX IOs to be powered up for PSR with
+	 * DC states enabled at the same time, while for driver initiated AUX
+	 * transfers we need the same AUX IOs to be powered but with DC states
+	 * disabled. Accordingly use the AUX power domain here which leaves DC
+	 * states enabled.
+	 * However, for non-A AUX ports the corresponding non-EDP transcoders
+	 * would have already enabled power well 2 and DC_OFF. This means we can
+	 * acquire a wider POWER_DOMAIN_AUX_{B,C,D,F} reference instead of a
+	 * specific AUX_IO reference without powering up any extra wells.
+	 * Note that PSR is enabled only on Port A even though this function
+	 * returns the correct domain for other ports too.
+	 */
+	return intel_dp->aux_ch == AUX_CH_A ? POWER_DOMAIN_AUX_IO_A :
+					      intel_dp->aux_power_domain;
+}
+
+static u64 intel_ddi_get_power_domains(struct intel_encoder *encoder,
+				       struct intel_crtc_state *crtc_state)
 {
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
-	enum pipe pipe;
+	struct intel_digital_port *dig_port;
+	u64 domains;
 
-	if (intel_ddi_get_hw_state(encoder, &pipe))
-		return BIT_ULL(dig_port->ddi_io_power_domain);
+	/*
+	 * TODO: Add support for MST encoders. Atm, the following should never
+	 * happen since fake-MST encoders don't set their get_power_domains()
+	 * hook.
+	 */
+	if (WARN_ON(intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST)))
+		return 0;
 
-	return 0;
+	dig_port = enc_to_dig_port(&encoder->base);
+	domains = BIT_ULL(dig_port->ddi_io_power_domain);
+
+	/* AUX power is only needed for (e)DP mode, not for HDMI. */
+	if (intel_crtc_has_dp_encoder(crtc_state)) {
+		struct intel_dp *intel_dp = &dig_port->dp;
+
+		domains |= BIT_ULL(intel_ddi_main_link_aux_domain(intel_dp));
+	}
+
+	return domains;
 }
 
 void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state)
@@ -2124,6 +2185,26 @@ u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder)
 		DP_TRAIN_VOLTAGE_SWING_MASK;
 }
 
+/*
+ * We assume that the full set of pre-emphasis values can be
+ * used on all DDI platforms. Should that change we need to
+ * rethink this code.
+ */
+u8 intel_ddi_dp_pre_emphasis_max(struct intel_encoder *encoder, u8 voltage_swing)
+{
+	switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
+		return DP_TRAIN_PRE_EMPH_LEVEL_3;
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_1:
+		return DP_TRAIN_PRE_EMPH_LEVEL_2;
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_2:
+		return DP_TRAIN_PRE_EMPH_LEVEL_1;
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_3:
+	default:
+		return DP_TRAIN_PRE_EMPH_LEVEL_0;
+	}
+}
+
 static void cnl_ddi_vswing_program(struct intel_encoder *encoder,
 				   int level, enum intel_output_type type)
 {
@@ -2595,6 +2676,9 @@ static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder,
 
 	WARN_ON(is_mst && (port == PORT_A || port == PORT_E));
 
+	intel_display_power_get(dev_priv,
+				intel_ddi_main_link_aux_domain(intel_dp));
+
 	intel_dp_set_link_params(intel_dp, crtc_state->port_clock,
 				 crtc_state->lane_count, is_mst);
 
@@ -2619,6 +2703,8 @@ static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	intel_dp_start_link_train(intel_dp);
 	if (port != PORT_A || INTEL_GEN(dev_priv) >= 9)
 		intel_dp_stop_link_train(intel_dp);
+
+	intel_ddi_enable_pipe_clock(crtc_state);
 }
 
 static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
@@ -2649,6 +2735,8 @@ static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
 	if (IS_GEN9_BC(dev_priv))
 		skl_ddi_set_iboost(encoder, level, INTEL_OUTPUT_HDMI);
 
+	intel_ddi_enable_pipe_clock(crtc_state);
+
 	intel_dig_port->set_infoframes(&encoder->base,
 				       crtc_state->has_infoframe,
 				       crtc_state, conn_state);
@@ -2718,6 +2806,8 @@ static void intel_ddi_post_disable_dp(struct intel_encoder *encoder,
 	bool is_mst = intel_crtc_has_type(old_crtc_state,
 					  INTEL_OUTPUT_DP_MST);
 
+	intel_ddi_disable_pipe_clock(old_crtc_state);
+
 	/*
 	 * Power down sink before disabling the port, otherwise we end
 	 * up getting interrupts from the sink on detecting link loss.
@@ -2733,6 +2823,9 @@ static void intel_ddi_post_disable_dp(struct intel_encoder *encoder,
 	intel_display_power_put(dev_priv, dig_port->ddi_io_power_domain);
 
 	intel_ddi_clk_disable(encoder);
+
+	intel_display_power_put(dev_priv,
+				intel_ddi_main_link_aux_domain(intel_dp));
 }
 
 static void intel_ddi_post_disable_hdmi(struct intel_encoder *encoder,
@@ -2743,11 +2836,13 @@ static void intel_ddi_post_disable_hdmi(struct intel_encoder *encoder,
 	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
 	struct intel_hdmi *intel_hdmi = &dig_port->hdmi;
 
-	intel_disable_ddi_buf(encoder);
-
 	dig_port->set_infoframes(&encoder->base, false,
 				 old_crtc_state, old_conn_state);
 
+	intel_ddi_disable_pipe_clock(old_crtc_state);
+
+	intel_disable_ddi_buf(encoder);
+
 	intel_display_power_put(dev_priv, dig_port->ddi_io_power_domain);
 
 	intel_ddi_clk_disable(encoder);
@@ -3034,6 +3129,8 @@ void intel_ddi_compute_min_voltage_level(struct drm_i915_private *dev_priv,
 {
 	if (IS_CANNONLAKE(dev_priv) && crtc_state->port_clock > 594000)
 		crtc_state->min_voltage_level = 2;
+	else if (IS_ICELAKE(dev_priv) && crtc_state->port_clock > 594000)
+		crtc_state->min_voltage_level = 1;
 }
 
 void intel_ddi_get_config(struct intel_encoder *encoder,
@@ -3542,7 +3639,6 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 			goto err;
 
 		intel_dig_port->hpd_pulse = intel_dp_hpd_pulse;
-		dev_priv->hotplug.irq_port[port] = intel_dig_port;
 	}
 
 	/* In theory we don't need the encoder->type check, but leave it just in
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 0fd13df424cf..0ef0c6448d53 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -858,6 +858,8 @@ void intel_device_info_runtime_init(struct intel_device_info *info)
 void intel_driver_caps_print(const struct intel_driver_caps *caps,
 			     struct drm_printer *p)
 {
+	drm_printf(p, "Has logical contexts? %s\n",
+		   yesno(caps->has_logical_contexts));
 	drm_printf(p, "scheduler: %x\n", caps->scheduler);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index 933e31669557..633f9fbf72ea 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -186,6 +186,7 @@ struct intel_device_info {
 
 struct intel_driver_caps {
 	unsigned int scheduler;
+	bool has_logical_contexts:1;
 };
 
 static inline unsigned int sseu_subslice_total(const struct sseu_dev_info *sseu)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index dec0d60921bf..ed3fa1c8a983 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1022,7 +1022,7 @@ bool intel_crtc_active(struct intel_crtc *crtc)
 	 * We can ditch the adjusted_mode.crtc_clock check as soon
 	 * as Haswell has gained clock readout/fastboot support.
 	 *
-	 * We can ditch the crtc->primary->fb check as soon as we can
+	 * We can ditch the crtc->primary->state->fb check as soon as we can
 	 * properly reconstruct framebuffers.
 	 *
 	 * FIXME: The intel_crtc->active here should be switched to
@@ -1202,7 +1202,7 @@ void assert_panel_unlocked(struct drm_i915_private *dev_priv, enum pipe pipe)
 {
 	i915_reg_t pp_reg;
 	u32 val;
-	enum pipe panel_pipe = PIPE_A;
+	enum pipe panel_pipe = INVALID_PIPE;
 	bool locked = true;
 
 	if (WARN_ON(HAS_DDI(dev_priv)))
@@ -1214,18 +1214,35 @@ void assert_panel_unlocked(struct drm_i915_private *dev_priv, enum pipe pipe)
 		pp_reg = PP_CONTROL(0);
 		port_sel = I915_READ(PP_ON_DELAYS(0)) & PANEL_PORT_SELECT_MASK;
 
-		if (port_sel == PANEL_PORT_SELECT_LVDS &&
-		    I915_READ(PCH_LVDS) & LVDS_PIPEB_SELECT)
-			panel_pipe = PIPE_B;
-		/* XXX: else fix for eDP */
+		switch (port_sel) {
+		case PANEL_PORT_SELECT_LVDS:
+			intel_lvds_port_enabled(dev_priv, PCH_LVDS, &panel_pipe);
+			break;
+		case PANEL_PORT_SELECT_DPA:
+			intel_dp_port_enabled(dev_priv, DP_A, PORT_A, &panel_pipe);
+			break;
+		case PANEL_PORT_SELECT_DPC:
+			intel_dp_port_enabled(dev_priv, PCH_DP_C, PORT_C, &panel_pipe);
+			break;
+		case PANEL_PORT_SELECT_DPD:
+			intel_dp_port_enabled(dev_priv, PCH_DP_D, PORT_D, &panel_pipe);
+			break;
+		default:
+			MISSING_CASE(port_sel);
+			break;
+		}
 	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		/* presumably write lock depends on pipe, not port select */
 		pp_reg = PP_CONTROL(pipe);
 		panel_pipe = pipe;
 	} else {
+		u32 port_sel;
+
 		pp_reg = PP_CONTROL(0);
-		if (I915_READ(LVDS) & LVDS_PIPEB_SELECT)
-			panel_pipe = PIPE_B;
+		port_sel = I915_READ(PP_ON_DELAYS(0)) & PANEL_PORT_SELECT_MASK;
+
+		WARN_ON(port_sel != PANEL_PORT_SELECT_LVDS);
+		intel_lvds_port_enabled(dev_priv, LVDS, &panel_pipe);
 	}
 
 	val = I915_READ(pp_reg);
@@ -1267,7 +1284,10 @@ void assert_pipe(struct drm_i915_private *dev_priv,
 
 static void assert_plane(struct intel_plane *plane, bool state)
 {
-	bool cur_state = plane->get_hw_state(plane);
+	enum pipe pipe;
+	bool cur_state;
+
+	cur_state = plane->get_hw_state(plane, &pipe);
 
 	I915_STATE_WARN(cur_state != state,
 			"%s assertion failure (expected %s, current %s)\n",
@@ -1305,125 +1325,64 @@ void assert_pch_transcoder_disabled(struct drm_i915_private *dev_priv,
 	     pipe_name(pipe));
 }
 
-static bool dp_pipe_enabled(struct drm_i915_private *dev_priv,
-			    enum pipe pipe, u32 port_sel, u32 val)
-{
-	if ((val & DP_PORT_EN) == 0)
-		return false;
-
-	if (HAS_PCH_CPT(dev_priv)) {
-		u32 trans_dp_ctl = I915_READ(TRANS_DP_CTL(pipe));
-		if ((trans_dp_ctl & TRANS_DP_PORT_SEL_MASK) != port_sel)
-			return false;
-	} else if (IS_CHERRYVIEW(dev_priv)) {
-		if ((val & DP_PIPE_MASK_CHV) != DP_PIPE_SELECT_CHV(pipe))
-			return false;
-	} else {
-		if ((val & DP_PIPE_MASK) != (pipe << 30))
-			return false;
-	}
-	return true;
-}
-
-static bool hdmi_pipe_enabled(struct drm_i915_private *dev_priv,
-			      enum pipe pipe, u32 val)
+static void assert_pch_dp_disabled(struct drm_i915_private *dev_priv,
+				   enum pipe pipe, enum port port,
+				   i915_reg_t dp_reg)
 {
-	if ((val & SDVO_ENABLE) == 0)
-		return false;
-
-	if (HAS_PCH_CPT(dev_priv)) {
-		if ((val & SDVO_PIPE_SEL_MASK_CPT) != SDVO_PIPE_SEL_CPT(pipe))
-			return false;
-	} else if (IS_CHERRYVIEW(dev_priv)) {
-		if ((val & SDVO_PIPE_SEL_MASK_CHV) != SDVO_PIPE_SEL_CHV(pipe))
-			return false;
-	} else {
-		if ((val & SDVO_PIPE_SEL_MASK) != SDVO_PIPE_SEL(pipe))
-			return false;
-	}
-	return true;
-}
+	enum pipe port_pipe;
+	bool state;
 
-static bool lvds_pipe_enabled(struct drm_i915_private *dev_priv,
-			      enum pipe pipe, u32 val)
-{
-	if ((val & LVDS_PORT_EN) == 0)
-		return false;
+	state = intel_dp_port_enabled(dev_priv, dp_reg, port, &port_pipe);
 
-	if (HAS_PCH_CPT(dev_priv)) {
-		if ((val & PORT_TRANS_SEL_MASK) != PORT_TRANS_SEL_CPT(pipe))
-			return false;
-	} else {
-		if ((val & LVDS_PIPE_MASK) != LVDS_PIPE(pipe))
-			return false;
-	}
-	return true;
-}
+	I915_STATE_WARN(state && port_pipe == pipe,
+			"PCH DP %c enabled on transcoder %c, should be disabled\n",
+			port_name(port), pipe_name(pipe));
 
-static bool adpa_pipe_enabled(struct drm_i915_private *dev_priv,
-			      enum pipe pipe, u32 val)
-{
-	if ((val & ADPA_DAC_ENABLE) == 0)
-		return false;
-	if (HAS_PCH_CPT(dev_priv)) {
-		if ((val & PORT_TRANS_SEL_MASK) != PORT_TRANS_SEL_CPT(pipe))
-			return false;
-	} else {
-		if ((val & ADPA_PIPE_SELECT_MASK) != ADPA_PIPE_SELECT(pipe))
-			return false;
-	}
-	return true;
+	I915_STATE_WARN(HAS_PCH_IBX(dev_priv) && !state && port_pipe == PIPE_B,
+			"IBX PCH DP %c still using transcoder B\n",
+			port_name(port));
 }
 
-static void assert_pch_dp_disabled(struct drm_i915_private *dev_priv,
-				   enum pipe pipe, i915_reg_t reg,
-				   u32 port_sel)
+static void assert_pch_hdmi_disabled(struct drm_i915_private *dev_priv,
+				     enum pipe pipe, enum port port,
+				     i915_reg_t hdmi_reg)
 {
-	u32 val = I915_READ(reg);
-	I915_STATE_WARN(dp_pipe_enabled(dev_priv, pipe, port_sel, val),
-	     "PCH DP (0x%08x) enabled on transcoder %c, should be disabled\n",
-	     i915_mmio_reg_offset(reg), pipe_name(pipe));
+	enum pipe port_pipe;
+	bool state;
 
-	I915_STATE_WARN(HAS_PCH_IBX(dev_priv) && (val & DP_PORT_EN) == 0
-	     && (val & DP_PIPEB_SELECT),
-	     "IBX PCH dp port still using transcoder B\n");
-}
+	state = intel_sdvo_port_enabled(dev_priv, hdmi_reg, &port_pipe);
 
-static void assert_pch_hdmi_disabled(struct drm_i915_private *dev_priv,
-				     enum pipe pipe, i915_reg_t reg)
-{
-	u32 val = I915_READ(reg);
-	I915_STATE_WARN(hdmi_pipe_enabled(dev_priv, pipe, val),
-	     "PCH HDMI (0x%08x) enabled on transcoder %c, should be disabled\n",
-	     i915_mmio_reg_offset(reg), pipe_name(pipe));
+	I915_STATE_WARN(state && port_pipe == pipe,
+			"PCH HDMI %c enabled on transcoder %c, should be disabled\n",
+			port_name(port), pipe_name(pipe));
 
-	I915_STATE_WARN(HAS_PCH_IBX(dev_priv) && (val & SDVO_ENABLE) == 0
-	     && (val & SDVO_PIPE_B_SELECT),
-	     "IBX PCH hdmi port still using transcoder B\n");
+	I915_STATE_WARN(HAS_PCH_IBX(dev_priv) && !state && port_pipe == PIPE_B,
+			"IBX PCH HDMI %c still using transcoder B\n",
+			port_name(port));
 }
 
 static void assert_pch_ports_disabled(struct drm_i915_private *dev_priv,
 				      enum pipe pipe)
 {
-	u32 val;
+	enum pipe port_pipe;
 
-	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_B, TRANS_DP_PORT_SEL_B);
-	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_C, TRANS_DP_PORT_SEL_C);
-	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_D, TRANS_DP_PORT_SEL_D);
+	assert_pch_dp_disabled(dev_priv, pipe, PORT_B, PCH_DP_B);
+	assert_pch_dp_disabled(dev_priv, pipe, PORT_C, PCH_DP_C);
+	assert_pch_dp_disabled(dev_priv, pipe, PORT_D, PCH_DP_D);
 
-	val = I915_READ(PCH_ADPA);
-	I915_STATE_WARN(adpa_pipe_enabled(dev_priv, pipe, val),
-	     "PCH VGA enabled on transcoder %c, should be disabled\n",
-	     pipe_name(pipe));
+	I915_STATE_WARN(intel_crt_port_enabled(dev_priv, PCH_ADPA, &port_pipe) &&
+			port_pipe == pipe,
+			"PCH VGA enabled on transcoder %c, should be disabled\n",
+			pipe_name(pipe));
 
-	val = I915_READ(PCH_LVDS);
-	I915_STATE_WARN(lvds_pipe_enabled(dev_priv, pipe, val),
-	     "PCH LVDS enabled on transcoder %c, should be disabled\n",
-	     pipe_name(pipe));
+	I915_STATE_WARN(intel_lvds_port_enabled(dev_priv, PCH_LVDS, &port_pipe) &&
+			port_pipe == pipe,
+			"PCH LVDS enabled on transcoder %c, should be disabled\n",
+			pipe_name(pipe));
 
-	assert_pch_hdmi_disabled(dev_priv, pipe, PCH_HDMIB);
-	assert_pch_hdmi_disabled(dev_priv, pipe, PCH_HDMIC);
-	assert_pch_hdmi_disabled(dev_priv, pipe, PCH_HDMID);
+	assert_pch_hdmi_disabled(dev_priv, pipe, PORT_B, PCH_HDMIB);
+	assert_pch_hdmi_disabled(dev_priv, pipe, PORT_C, PCH_HDMIC);
+	assert_pch_hdmi_disabled(dev_priv, pipe, PORT_D, PCH_HDMID);
 }
 
 static void _vlv_enable_pll(struct intel_crtc *crtc,
@@ -2521,6 +2480,7 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv,
 {
 	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
 	struct intel_rotation_info *rot_info = &intel_fb->rot_info;
+	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	u32 gtt_offset_rotated = 0;
 	unsigned int max_size = 0;
 	int i, num_planes = fb->format->num_planes;
@@ -2585,7 +2545,7 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv,
 		 * fb layout agrees with the fence layout. We already check that the
 		 * fb stride matches the fence stride elsewhere.
 		 */
-		if (i == 0 && i915_gem_object_is_tiled(intel_fb->obj) &&
+		if (i == 0 && i915_gem_object_is_tiled(obj) &&
 		    (x + width) * cpp > fb->pitches[i]) {
 			DRM_DEBUG_KMS("bad fb plane %d offset: 0x%x\n",
 				      i, fb->offsets[i]);
@@ -2670,9 +2630,9 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv,
 		max_size = max(max_size, offset + size);
 	}
 
-	if (max_size * tile_size > intel_fb->obj->base.size) {
+	if (max_size * tile_size > obj->base.size) {
 		DRM_DEBUG_KMS("fb too big for bo (need %u bytes, have %zu bytes)\n",
-			      max_size * tile_size, intel_fb->obj->base.size);
+			      max_size * tile_size, obj->base.size);
 		return -EINVAL;
 	}
 
@@ -2796,10 +2756,10 @@ intel_set_plane_visible(struct intel_crtc_state *crtc_state,
 
 	/* FIXME pre-g4x don't work like this */
 	if (visible) {
-		crtc_state->base.plane_mask |= BIT(drm_plane_index(&plane->base));
+		crtc_state->base.plane_mask |= drm_plane_mask(&plane->base);
 		crtc_state->active_planes |= BIT(plane->id);
 	} else {
-		crtc_state->base.plane_mask &= ~BIT(drm_plane_index(&plane->base));
+		crtc_state->base.plane_mask &= ~drm_plane_mask(&plane->base);
 		crtc_state->active_planes &= ~BIT(plane->id);
 	}
 
@@ -2922,9 +2882,8 @@ valid_fb:
 	if (i915_gem_object_is_tiled(obj))
 		dev_priv->preserve_bios_swizzle = true;
 
-	drm_framebuffer_get(fb);
-	primary->fb = primary->state->fb = fb;
-	primary->crtc = primary->state->crtc = &intel_crtc->base;
+	plane_state->fb = fb;
+	plane_state->crtc = &intel_crtc->base;
 
 	intel_set_plane_visible(to_intel_crtc_state(crtc_state),
 				to_intel_plane_state(plane_state),
@@ -3430,24 +3389,33 @@ static void i9xx_disable_plane(struct intel_plane *plane,
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 }
 
-static bool i9xx_plane_get_hw_state(struct intel_plane *plane)
+static bool i9xx_plane_get_hw_state(struct intel_plane *plane,
+				    enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
 	enum i9xx_plane_id i9xx_plane = plane->i9xx_plane;
-	enum pipe pipe = plane->pipe;
 	bool ret;
+	u32 val;
 
 	/*
 	 * Not 100% correct for planes that can move between pipes,
 	 * but that's only the case for gen2-4 which don't have any
 	 * display power wells.
 	 */
-	power_domain = POWER_DOMAIN_PIPE(pipe);
+	power_domain = POWER_DOMAIN_PIPE(plane->pipe);
 	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
-	ret = I915_READ(DSPCNTR(i9xx_plane)) & DISPLAY_PLANE_ENABLE;
+	val = I915_READ(DSPCNTR(i9xx_plane));
+
+	ret = val & DISPLAY_PLANE_ENABLE;
+
+	if (INTEL_GEN(dev_priv) >= 5)
+		*pipe = plane->pipe;
+	else
+		*pipe = (val & DISPPLANE_SEL_PIPE_MASK) >>
+			DISPPLANE_SEL_PIPE_SHIFT;
 
 	intel_display_power_put(dev_priv, power_domain);
 
@@ -3689,7 +3657,7 @@ u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state,
 	plane_color_ctl |= PLANE_COLOR_PLANE_GAMMA_DISABLE;
 	plane_color_ctl |= glk_plane_color_ctl_alpha(fb->format->format);
 
-	if (intel_format_is_yuv(fb->format->format)) {
+	if (fb->format->is_yuv) {
 		if (plane_state->base.color_encoding == DRM_COLOR_YCBCR_BT709)
 			plane_color_ctl |= PLANE_COLOR_CSC_MODE_YUV709_TO_RGB709;
 		else
@@ -4631,20 +4599,33 @@ static void ivybridge_update_fdi_bc_bifurcation(struct intel_crtc *intel_crtc)
 	}
 }
 
-/* Return which DP Port should be selected for Transcoder DP control */
-static enum port
-intel_trans_dp_port_sel(struct intel_crtc *crtc)
+/*
+ * Finds the encoder associated with the given CRTC. This can only be
+ * used when we know that the CRTC isn't feeding multiple encoders!
+ */
+static struct intel_encoder *
+intel_get_crtc_new_encoder(const struct intel_atomic_state *state,
+			   const struct intel_crtc_state *crtc_state)
 {
-	struct drm_device *dev = crtc->base.dev;
-	struct intel_encoder *encoder;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	const struct drm_connector_state *connector_state;
+	const struct drm_connector *connector;
+	struct intel_encoder *encoder = NULL;
+	int num_encoders = 0;
+	int i;
 
-	for_each_encoder_on_crtc(dev, &crtc->base, encoder) {
-		if (encoder->type == INTEL_OUTPUT_DP ||
-		    encoder->type == INTEL_OUTPUT_EDP)
-			return encoder->port;
+	for_each_new_connector_in_state(&state->base, connector, connector_state, i) {
+		if (connector_state->crtc != &crtc->base)
+			continue;
+
+		encoder = to_intel_encoder(connector_state->best_encoder);
+		num_encoders++;
 	}
 
-	return -1;
+	WARN(num_encoders != 1, "%d encoders for pipe %c\n",
+	     num_encoders, pipe_name(crtc->pipe));
+
+	return encoder;
 }
 
 /*
@@ -4655,7 +4636,8 @@ intel_trans_dp_port_sel(struct intel_crtc *crtc)
  *   - DP transcoding bits
  *   - transcoder
  */
-static void ironlake_pch_enable(const struct intel_crtc_state *crtc_state)
+static void ironlake_pch_enable(const struct intel_atomic_state *state,
+				const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_device *dev = crtc->base.dev;
@@ -4714,6 +4696,8 @@ static void ironlake_pch_enable(const struct intel_crtc_state *crtc_state)
 			&crtc_state->base.adjusted_mode;
 		u32 bpc = (I915_READ(PIPECONF(pipe)) & PIPECONF_BPC_MASK) >> 5;
 		i915_reg_t reg = TRANS_DP_CTL(pipe);
+		enum port port;
+
 		temp = I915_READ(reg);
 		temp &= ~(TRANS_DP_PORT_SEL_MASK |
 			  TRANS_DP_SYNC_MASK |
@@ -4726,19 +4710,9 @@ static void ironlake_pch_enable(const struct intel_crtc_state *crtc_state)
 		if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
 			temp |= TRANS_DP_VSYNC_ACTIVE_HIGH;
 
-		switch (intel_trans_dp_port_sel(crtc)) {
-		case PORT_B:
-			temp |= TRANS_DP_PORT_SEL_B;
-			break;
-		case PORT_C:
-			temp |= TRANS_DP_PORT_SEL_C;
-			break;
-		case PORT_D:
-			temp |= TRANS_DP_PORT_SEL_D;
-			break;
-		default:
-			BUG();
-		}
+		port = intel_get_crtc_new_encoder(state, crtc_state)->port;
+		WARN_ON(port < PORT_B || port > PORT_D);
+		temp |= TRANS_DP_PORT_SEL(port);
 
 		I915_WRITE(reg, temp);
 	}
@@ -4746,7 +4720,8 @@ static void ironlake_pch_enable(const struct intel_crtc_state *crtc_state)
 	ironlake_enable_pch_transcoder(dev_priv, pipe);
 }
 
-static void lpt_pch_enable(const struct intel_crtc_state *crtc_state)
+static void lpt_pch_enable(const struct intel_atomic_state *state,
+			   const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
@@ -4776,6 +4751,39 @@ static void cpt_verify_modeset(struct drm_device *dev, int pipe)
 	}
 }
 
+/*
+ * The hardware phase 0.0 refers to the center of the pixel.
+ * We want to start from the top/left edge which is phase
+ * -0.5. That matches how the hardware calculates the scaling
+ * factors (from top-left of the first pixel to bottom-right
+ * of the last pixel, as opposed to the pixel centers).
+ *
+ * For 4:2:0 subsampled chroma planes we obviously have to
+ * adjust that so that the chroma sample position lands in
+ * the right spot.
+ *
+ * Note that for packed YCbCr 4:2:2 formats there is no way to
+ * control chroma siting. The hardware simply replicates the
+ * chroma samples for both of the luma samples, and thus we don't
+ * actually get the expected MPEG2 chroma siting convention :(
+ * The same behaviour is observed on pre-SKL platforms as well.
+ */
+u16 skl_scaler_calc_phase(int sub, bool chroma_cosited)
+{
+	int phase = -0x8000;
+	u16 trip = 0;
+
+	if (chroma_cosited)
+		phase += (sub - 1) * 0x8000 / sub;
+
+	if (phase < 0)
+		phase = 0x10000 + phase;
+	else
+		trip = PS_PHASE_TRIP;
+
+	return ((phase >> 2) & PS_PHASE_MASK) | trip;
+}
+
 static int
 skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 		  unsigned int scaler_user, int *scaler_id,
@@ -4975,14 +4983,22 @@ static void skylake_pfit_enable(struct intel_crtc *crtc)
 		&crtc->config->scaler_state;
 
 	if (crtc->config->pch_pfit.enabled) {
+		u16 uv_rgb_hphase, uv_rgb_vphase;
 		int id;
 
 		if (WARN_ON(crtc->config->scaler_state.scaler_id < 0))
 			return;
 
+		uv_rgb_hphase = skl_scaler_calc_phase(1, false);
+		uv_rgb_vphase = skl_scaler_calc_phase(1, false);
+
 		id = scaler_state->scaler_id;
 		I915_WRITE(SKL_PS_CTRL(pipe, id), PS_SCALER_EN |
 			PS_FILTER_MEDIUM | scaler_state->scalers[id].mode);
+		I915_WRITE_FW(SKL_PS_VPHASE(pipe, id),
+			      PS_Y_PHASE(0) | PS_UV_RGB_PHASE(uv_rgb_vphase));
+		I915_WRITE_FW(SKL_PS_HPHASE(pipe, id),
+			      PS_Y_PHASE(0) | PS_UV_RGB_PHASE(uv_rgb_hphase));
 		I915_WRITE(SKL_PS_WIN_POS(pipe, id), crtc->config->pch_pfit.pos);
 		I915_WRITE(SKL_PS_WIN_SZ(pipe, id), crtc->config->pch_pfit.size);
 	}
@@ -5501,10 +5517,8 @@ static void ironlake_crtc_enable(struct intel_crtc_state *pipe_config,
 	 *
 	 * Spurious PCH underruns also occur during PCH enabling.
 	 */
-	if (intel_crtc->config->has_pch_encoder || IS_GEN5(dev_priv))
-		intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
-	if (intel_crtc->config->has_pch_encoder)
-		intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, false);
+	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
+	intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, false);
 
 	if (intel_crtc->config->has_pch_encoder)
 		intel_prepare_shared_dpll(intel_crtc);
@@ -5549,7 +5563,7 @@ static void ironlake_crtc_enable(struct intel_crtc_state *pipe_config,
 	intel_enable_pipe(pipe_config);
 
 	if (intel_crtc->config->has_pch_encoder)
-		ironlake_pch_enable(pipe_config);
+		ironlake_pch_enable(old_intel_state, pipe_config);
 
 	assert_vblank_disabled(crtc);
 	drm_crtc_vblank_on(crtc);
@@ -5559,9 +5573,16 @@ static void ironlake_crtc_enable(struct intel_crtc_state *pipe_config,
 	if (HAS_PCH_CPT(dev_priv))
 		cpt_verify_modeset(dev, intel_crtc->pipe);
 
-	/* Must wait for vblank to avoid spurious PCH FIFO underruns */
-	if (intel_crtc->config->has_pch_encoder)
+	/*
+	 * Must wait for vblank to avoid spurious PCH FIFO underruns.
+	 * And a second vblank wait is needed at least on ILK with
+	 * some interlaced HDMI modes. Let's do the double wait always
+	 * in case there are more corner cases we don't know about.
+	 */
+	if (intel_crtc->config->has_pch_encoder) {
 		intel_wait_for_vblank(dev_priv, pipe);
+		intel_wait_for_vblank(dev_priv, pipe);
+	}
 	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true);
 	intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, true);
 }
@@ -5611,6 +5632,7 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 	struct intel_atomic_state *old_intel_state =
 		to_intel_atomic_state(old_state);
 	bool psl_clkgate_wa;
+	u32 pipe_chicken;
 
 	if (WARN_ON(intel_crtc->active))
 		return;
@@ -5623,6 +5645,8 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 	if (INTEL_GEN(dev_priv) >= 11)
 		icl_map_plls_to_ports(crtc, pipe_config, old_state);
 
+	intel_encoders_pre_enable(crtc, pipe_config, old_state);
+
 	if (intel_crtc_has_dp_encoder(intel_crtc->config))
 		intel_dp_set_m_n(intel_crtc, M1_N1);
 
@@ -5651,11 +5675,6 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 
 	intel_crtc->active = true;
 
-	intel_encoders_pre_enable(crtc, pipe_config, old_state);
-
-	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_ddi_enable_pipe_clock(pipe_config);
-
 	/* Display WA #1180: WaDisableScalarClockGating: glk, cnl */
 	psl_clkgate_wa = (IS_GEMINILAKE(dev_priv) || IS_CANNONLAKE(dev_priv)) &&
 			 intel_crtc->config->pch_pfit.enabled;
@@ -5673,6 +5692,17 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 	 */
 	intel_color_load_luts(&pipe_config->base);
 
+	/*
+	 * Display WA #1153: enable hardware to bypass the alpha math
+	 * and rounding for per-pixel values 00 and 0xff
+	 */
+	if (INTEL_GEN(dev_priv) >= 11) {
+		pipe_chicken = I915_READ(PIPE_CHICKEN(pipe));
+		if (!(pipe_chicken & PER_PIXEL_ALPHA_BYPASS_EN))
+			I915_WRITE_FW(PIPE_CHICKEN(pipe),
+				      pipe_chicken | PER_PIXEL_ALPHA_BYPASS_EN);
+	}
+
 	intel_ddi_set_pipe_settings(pipe_config);
 	if (!transcoder_is_dsi(cpu_transcoder))
 		intel_ddi_enable_transcoder_func(pipe_config);
@@ -5688,7 +5718,7 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 		intel_enable_pipe(pipe_config);
 
 	if (intel_crtc->config->has_pch_encoder)
-		lpt_pch_enable(pipe_config);
+		lpt_pch_enable(old_intel_state, pipe_config);
 
 	if (intel_crtc_has_type(intel_crtc->config, INTEL_OUTPUT_DP_MST))
 		intel_ddi_set_vc_payload_alloc(pipe_config, true);
@@ -5741,10 +5771,8 @@ static void ironlake_crtc_disable(struct intel_crtc_state *old_crtc_state,
 	 * pipe is already disabled, but FDI RX/TX is still enabled.
 	 * Happens at least with VGA+HDMI cloning. Suppress them.
 	 */
-	if (intel_crtc->config->has_pch_encoder) {
-		intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
-		intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, false);
-	}
+	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
+	intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, false);
 
 	intel_encoders_disable(crtc, old_crtc_state, old_state);
 
@@ -5794,7 +5822,7 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state,
 	struct drm_crtc *crtc = old_crtc_state->base.crtc;
 	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder;
+	enum transcoder cpu_transcoder = old_crtc_state->cpu_transcoder;
 
 	intel_encoders_disable(crtc, old_crtc_state, old_state);
 
@@ -5805,8 +5833,8 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state,
 	if (!transcoder_is_dsi(cpu_transcoder))
 		intel_disable_pipe(old_crtc_state);
 
-	if (intel_crtc_has_type(intel_crtc->config, INTEL_OUTPUT_DP_MST))
-		intel_ddi_set_vc_payload_alloc(intel_crtc->config, false);
+	if (intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DP_MST))
+		intel_ddi_set_vc_payload_alloc(old_crtc_state, false);
 
 	if (!transcoder_is_dsi(cpu_transcoder))
 		intel_ddi_disable_transcoder_func(old_crtc_state);
@@ -5816,9 +5844,6 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state,
 	else
 		ironlake_pfit_disable(intel_crtc, false);
 
-	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_ddi_disable_pipe_clock(intel_crtc->config);
-
 	intel_encoders_post_disable(crtc, old_crtc_state, old_state);
 
 	if (INTEL_GEN(dev_priv) >= 11)
@@ -5849,6 +5874,22 @@ static void i9xx_pfit_enable(struct intel_crtc *crtc)
 	I915_WRITE(BCLRPAT(crtc->pipe), 0);
 }
 
+bool intel_port_is_tc(struct drm_i915_private *dev_priv, enum port port)
+{
+	if (IS_ICELAKE(dev_priv))
+		return port >= PORT_C && port <= PORT_F;
+
+	return false;
+}
+
+enum tc_port intel_port_to_tc(struct drm_i915_private *dev_priv, enum port port)
+{
+	if (!intel_port_is_tc(dev_priv, port))
+		return PORT_TC_NONE;
+
+	return port - PORT_C;
+}
+
 enum intel_display_power_domain intel_port_to_power_domain(enum port port)
 {
 	switch (port) {
@@ -7675,16 +7716,18 @@ i9xx_get_initial_plane_config(struct intel_crtc *crtc,
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_plane *plane = to_intel_plane(crtc->base.primary);
 	enum i9xx_plane_id i9xx_plane = plane->i9xx_plane;
-	enum pipe pipe = crtc->pipe;
+	enum pipe pipe;
 	u32 val, base, offset;
 	int fourcc, pixel_format;
 	unsigned int aligned_height;
 	struct drm_framebuffer *fb;
 	struct intel_framebuffer *intel_fb;
 
-	if (!plane->get_hw_state(plane))
+	if (!plane->get_hw_state(plane, &pipe))
 		return;
 
+	WARN_ON(pipe != crtc->pipe);
+
 	intel_fb = kzalloc(sizeof(*intel_fb), GFP_KERNEL);
 	if (!intel_fb) {
 		DRM_DEBUG_KMS("failed to alloc fb\n");
@@ -8705,16 +8748,18 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc,
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_plane *plane = to_intel_plane(crtc->base.primary);
 	enum plane_id plane_id = plane->id;
-	enum pipe pipe = crtc->pipe;
+	enum pipe pipe;
 	u32 val, base, offset, stride_mult, tiling, alpha;
 	int fourcc, pixel_format;
 	unsigned int aligned_height;
 	struct drm_framebuffer *fb;
 	struct intel_framebuffer *intel_fb;
 
-	if (!plane->get_hw_state(plane))
+	if (!plane->get_hw_state(plane, &pipe))
 		return;
 
+	WARN_ON(pipe != crtc->pipe);
+
 	intel_fb = kzalloc(sizeof(*intel_fb), GFP_KERNEL);
 	if (!intel_fb) {
 		DRM_DEBUG_KMS("failed to alloc fb\n");
@@ -9142,9 +9187,12 @@ void hsw_disable_pc8(struct drm_i915_private *dev_priv)
 static int haswell_crtc_compute_clock(struct intel_crtc *crtc,
 				      struct intel_crtc_state *crtc_state)
 {
+	struct intel_atomic_state *state =
+		to_intel_atomic_state(crtc_state->base.state);
+
 	if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI)) {
 		struct intel_encoder *encoder =
-			intel_ddi_get_crtc_new_encoder(crtc_state);
+			intel_get_crtc_new_encoder(state, crtc_state);
 
 		if (!intel_get_shared_dpll(crtc, crtc_state, encoder)) {
 			DRM_DEBUG_DRIVER("failed to find PLL for pipe %c\n",
@@ -9172,6 +9220,44 @@ static void cannonlake_get_ddi_pll(struct drm_i915_private *dev_priv,
 	pipe_config->shared_dpll = intel_get_shared_dpll_by_id(dev_priv, id);
 }
 
+static void icelake_get_ddi_pll(struct drm_i915_private *dev_priv,
+				enum port port,
+				struct intel_crtc_state *pipe_config)
+{
+	enum intel_dpll_id id;
+	u32 temp;
+
+	/* TODO: TBT pll not implemented. */
+	switch (port) {
+	case PORT_A:
+	case PORT_B:
+		temp = I915_READ(DPCLKA_CFGCR0_ICL) &
+		       DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(port);
+		id = temp >> DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(port);
+
+		if (WARN_ON(id != DPLL_ID_ICL_DPLL0 && id != DPLL_ID_ICL_DPLL1))
+			return;
+		break;
+	case PORT_C:
+		id = DPLL_ID_ICL_MGPLL1;
+		break;
+	case PORT_D:
+		id = DPLL_ID_ICL_MGPLL2;
+		break;
+	case PORT_E:
+		id = DPLL_ID_ICL_MGPLL3;
+		break;
+	case PORT_F:
+		id = DPLL_ID_ICL_MGPLL4;
+		break;
+	default:
+		MISSING_CASE(port);
+		return;
+	}
+
+	pipe_config->shared_dpll = intel_get_shared_dpll_by_id(dev_priv, id);
+}
+
 static void bxt_get_ddi_pll(struct drm_i915_private *dev_priv,
 				enum port port,
 				struct intel_crtc_state *pipe_config)
@@ -9273,6 +9359,7 @@ static bool hsw_get_transcoder_state(struct intel_crtc *crtc,
 		switch (tmp & TRANS_DDI_EDP_INPUT_MASK) {
 		default:
 			WARN(1, "unknown pipe linked to edp transcoder\n");
+			/* fall through */
 		case TRANS_DDI_EDP_INPUT_A_ONOFF:
 		case TRANS_DDI_EDP_INPUT_A_ON:
 			trans_edp_pipe = PIPE_A;
@@ -9328,7 +9415,7 @@ static bool bxt_get_dsi_transcoder_state(struct intel_crtc *crtc,
 		 * registers/MIPI[BXT]. We can break out here early, since we
 		 * need the same DSI PLL to be enabled for both DSI ports.
 		 */
-		if (!intel_dsi_pll_is_enabled(dev_priv))
+		if (!bxt_dsi_pll_is_enabled(dev_priv))
 			break;
 
 		/* XXX: this works for video mode only */
@@ -9359,7 +9446,9 @@ static void haswell_get_ddi_port_state(struct intel_crtc *crtc,
 
 	port = (tmp & TRANS_DDI_PORT_MASK) >> TRANS_DDI_PORT_SHIFT;
 
-	if (IS_CANNONLAKE(dev_priv))
+	if (IS_ICELAKE(dev_priv))
+		icelake_get_ddi_pll(dev_priv, port, pipe_config);
+	else if (IS_CANNONLAKE(dev_priv))
 		cannonlake_get_ddi_pll(dev_priv, port, pipe_config);
 	else if (IS_GEN9_BC(dev_priv))
 		skylake_get_ddi_pll(dev_priv, port, pipe_config);
@@ -9692,7 +9781,8 @@ static void i845_disable_cursor(struct intel_plane *plane,
 	i845_update_cursor(plane, NULL, NULL);
 }
 
-static bool i845_cursor_get_hw_state(struct intel_plane *plane)
+static bool i845_cursor_get_hw_state(struct intel_plane *plane,
+				     enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
@@ -9704,6 +9794,8 @@ static bool i845_cursor_get_hw_state(struct intel_plane *plane)
 
 	ret = I915_READ(CURCNTR(PIPE_A)) & CURSOR_ENABLE;
 
+	*pipe = PIPE_A;
+
 	intel_display_power_put(dev_priv, power_domain);
 
 	return ret;
@@ -9715,25 +9807,30 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state,
 	struct drm_i915_private *dev_priv =
 		to_i915(plane_state->base.plane->dev);
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	u32 cntl;
+	u32 cntl = 0;
 
-	cntl = MCURSOR_GAMMA_ENABLE;
+	if (IS_GEN6(dev_priv) || IS_IVYBRIDGE(dev_priv))
+		cntl |= MCURSOR_TRICKLE_FEED_DISABLE;
 
-	if (HAS_DDI(dev_priv))
-		cntl |= CURSOR_PIPE_CSC_ENABLE;
+	if (INTEL_GEN(dev_priv) <= 10) {
+		cntl |= MCURSOR_GAMMA_ENABLE;
+
+		if (HAS_DDI(dev_priv))
+			cntl |= MCURSOR_PIPE_CSC_ENABLE;
+	}
 
 	if (INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv))
 		cntl |= MCURSOR_PIPE_SELECT(crtc->pipe);
 
 	switch (plane_state->base.crtc_w) {
 	case 64:
-		cntl |= CURSOR_MODE_64_ARGB_AX;
+		cntl |= MCURSOR_MODE_64_ARGB_AX;
 		break;
 	case 128:
-		cntl |= CURSOR_MODE_128_ARGB_AX;
+		cntl |= MCURSOR_MODE_128_ARGB_AX;
 		break;
 	case 256:
-		cntl |= CURSOR_MODE_256_ARGB_AX;
+		cntl |= MCURSOR_MODE_256_ARGB_AX;
 		break;
 	default:
 		MISSING_CASE(plane_state->base.crtc_w);
@@ -9741,7 +9838,7 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state,
 	}
 
 	if (plane_state->base.rotation & DRM_MODE_ROTATE_180)
-		cntl |= CURSOR_ROTATE_180;
+		cntl |= MCURSOR_ROTATE_180;
 
 	return cntl;
 }
@@ -9903,23 +10000,32 @@ static void i9xx_disable_cursor(struct intel_plane *plane,
 	i9xx_update_cursor(plane, NULL, NULL);
 }
 
-static bool i9xx_cursor_get_hw_state(struct intel_plane *plane)
+static bool i9xx_cursor_get_hw_state(struct intel_plane *plane,
+				     enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
-	enum pipe pipe = plane->pipe;
 	bool ret;
+	u32 val;
 
 	/*
 	 * Not 100% correct for planes that can move between pipes,
 	 * but that's only the case for gen2-3 which don't have any
 	 * display power wells.
 	 */
-	power_domain = POWER_DOMAIN_PIPE(pipe);
+	power_domain = POWER_DOMAIN_PIPE(plane->pipe);
 	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
-	ret = I915_READ(CURCNTR(pipe)) & CURSOR_MODE;
+	val = I915_READ(CURCNTR(plane->pipe));
+
+	ret = val & MCURSOR_MODE;
+
+	if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv))
+		*pipe = plane->pipe;
+	else
+		*pipe = (val & MCURSOR_PIPE_SELECT_MASK) >>
+			MCURSOR_PIPE_SELECT_SHIFT;
 
 	intel_display_power_put(dev_priv, power_domain);
 
@@ -10631,7 +10737,7 @@ static void intel_modeset_update_connector_atomic_state(struct drm_device *dev)
 	drm_connector_list_iter_begin(dev, &conn_iter);
 	for_each_intel_connector_iter(connector, &conn_iter) {
 		if (connector->base.state->crtc)
-			drm_connector_unreference(&connector->base);
+			drm_connector_put(&connector->base);
 
 		if (connector->base.encoder) {
 			connector->base.state->best_encoder =
@@ -10639,7 +10745,7 @@ static void intel_modeset_update_connector_atomic_state(struct drm_device *dev)
 			connector->base.state->crtc =
 				connector->base.encoder->crtc;
 
-			drm_connector_reference(&connector->base);
+			drm_connector_get(&connector->base);
 		} else {
 			connector->base.state->best_encoder = NULL;
 			connector->base.state->crtc = NULL;
@@ -10918,6 +11024,7 @@ static bool check_digital_port_conflicts(struct drm_atomic_state *state)
 		case INTEL_OUTPUT_DDI:
 			if (WARN_ON(!HAS_DDI(to_i915(dev))))
 				break;
+			/* else: fall through */
 		case INTEL_OUTPUT_DP:
 		case INTEL_OUTPUT_HDMI:
 		case INTEL_OUTPUT_EDP:
@@ -11791,7 +11898,7 @@ verify_single_dpll_state(struct drm_i915_private *dev_priv,
 			 struct drm_crtc_state *new_state)
 {
 	struct intel_dpll_hw_state dpll_hw_state;
-	unsigned crtc_mask;
+	unsigned int crtc_mask;
 	bool active;
 
 	memset(&dpll_hw_state, 0, sizeof(dpll_hw_state));
@@ -11818,7 +11925,7 @@ verify_single_dpll_state(struct drm_i915_private *dev_priv,
 		return;
 	}
 
-	crtc_mask = 1 << drm_crtc_index(crtc);
+	crtc_mask = drm_crtc_mask(crtc);
 
 	if (new_state->active)
 		I915_STATE_WARN(!(pll->active_mask & crtc_mask),
@@ -11853,7 +11960,7 @@ verify_shared_dpll_state(struct drm_device *dev, struct drm_crtc *crtc,
 
 	if (old_state->shared_dpll &&
 	    old_state->shared_dpll != new_state->shared_dpll) {
-		unsigned crtc_mask = 1 << drm_crtc_index(crtc);
+		unsigned int crtc_mask = drm_crtc_mask(crtc);
 		struct intel_shared_dpll *pll = old_state->shared_dpll;
 
 		I915_STATE_WARN(pll->active_mask & crtc_mask,
@@ -12449,6 +12556,19 @@ static void intel_atomic_commit_fence_wait(struct intel_atomic_state *intel_stat
 	finish_wait(&dev_priv->gpu_error.wait_queue, &wait_reset);
 }
 
+static void intel_atomic_cleanup_work(struct work_struct *work)
+{
+	struct drm_atomic_state *state =
+		container_of(work, struct drm_atomic_state, commit_work);
+	struct drm_i915_private *i915 = to_i915(state->dev);
+
+	drm_atomic_helper_cleanup_planes(&i915->drm, state);
+	drm_atomic_helper_commit_cleanup_done(state);
+	drm_atomic_state_put(state);
+
+	intel_atomic_helper_free_state(i915);
+}
+
 static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 {
 	struct drm_device *dev = state->dev;
@@ -12609,13 +12729,16 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 		intel_display_power_put(dev_priv, POWER_DOMAIN_MODESET);
 	}
 
-	drm_atomic_helper_cleanup_planes(dev, state);
-
-	drm_atomic_helper_commit_cleanup_done(state);
-
-	drm_atomic_state_put(state);
-
-	intel_atomic_helper_free_state(dev_priv);
+	/*
+	 * Defer the cleanup of the old state to a separate worker to not
+	 * impede the current task (userspace for blocking modesets) that
+	 * are executed inline. For out-of-line asynchronous modesets/flips,
+	 * deferring to a new worker seems overkill, but we would place a
+	 * schedule point (cond_resched()) here anyway to keep latencies
+	 * down.
+	 */
+	INIT_WORK(&state->commit_work, intel_atomic_cleanup_work);
+	schedule_work(&state->commit_work);
 }
 
 static void intel_atomic_commit_work(struct work_struct *work)
@@ -12981,6 +13104,19 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 		add_rps_boost_after_vblank(new_state->crtc, new_state->fence);
 	}
 
+	/*
+	 * We declare pageflips to be interactive and so merit a small bias
+	 * towards upclocking to deliver the frame on time. By only changing
+	 * the RPS thresholds to sample more regularly and aim for higher
+	 * clocks we can hopefully deliver low power workloads (like kodi)
+	 * that are not quite steady state without resorting to forcing
+	 * maximum clocks following a vblank miss (see do_rps_boost()).
+	 */
+	if (!intel_state->rps_interactive) {
+		intel_rps_mark_interactive(dev_priv, true);
+		intel_state->rps_interactive = true;
+	}
+
 	return 0;
 }
 
@@ -12997,8 +13133,15 @@ void
 intel_cleanup_plane_fb(struct drm_plane *plane,
 		       struct drm_plane_state *old_state)
 {
+	struct intel_atomic_state *intel_state =
+		to_intel_atomic_state(old_state->state);
 	struct drm_i915_private *dev_priv = to_i915(plane->dev);
 
+	if (intel_state->rps_interactive) {
+		intel_rps_mark_interactive(dev_priv, false);
+		intel_state->rps_interactive = false;
+	}
+
 	/* Should only be called after a successful intel_prepare_plane_fb()! */
 	mutex_lock(&dev_priv->drm.struct_mutex);
 	intel_plane_unpin_fb(to_intel_plane_state(old_state));
@@ -13181,8 +13324,17 @@ void intel_plane_destroy(struct drm_plane *plane)
 	kfree(to_intel_plane(plane));
 }
 
-static bool i8xx_mod_supported(uint32_t format, uint64_t modifier)
+static bool i8xx_plane_format_mod_supported(struct drm_plane *_plane,
+					    u32 format, u64 modifier)
 {
+	switch (modifier) {
+	case DRM_FORMAT_MOD_LINEAR:
+	case I915_FORMAT_MOD_X_TILED:
+		break;
+	default:
+		return false;
+	}
+
 	switch (format) {
 	case DRM_FORMAT_C8:
 	case DRM_FORMAT_RGB565:
@@ -13195,8 +13347,17 @@ static bool i8xx_mod_supported(uint32_t format, uint64_t modifier)
 	}
 }
 
-static bool i965_mod_supported(uint32_t format, uint64_t modifier)
+static bool i965_plane_format_mod_supported(struct drm_plane *_plane,
+					    u32 format, u64 modifier)
 {
+	switch (modifier) {
+	case DRM_FORMAT_MOD_LINEAR:
+	case I915_FORMAT_MOD_X_TILED:
+		break;
+	default:
+		return false;
+	}
+
 	switch (format) {
 	case DRM_FORMAT_C8:
 	case DRM_FORMAT_RGB565:
@@ -13211,8 +13372,26 @@ static bool i965_mod_supported(uint32_t format, uint64_t modifier)
 	}
 }
 
-static bool skl_mod_supported(uint32_t format, uint64_t modifier)
+static bool skl_plane_format_mod_supported(struct drm_plane *_plane,
+					   u32 format, u64 modifier)
 {
+	struct intel_plane *plane = to_intel_plane(_plane);
+
+	switch (modifier) {
+	case DRM_FORMAT_MOD_LINEAR:
+	case I915_FORMAT_MOD_X_TILED:
+	case I915_FORMAT_MOD_Y_TILED:
+	case I915_FORMAT_MOD_Yf_TILED:
+		break;
+	case I915_FORMAT_MOD_Y_TILED_CCS:
+	case I915_FORMAT_MOD_Yf_TILED_CCS:
+		if (!plane->has_ccs)
+			return false;
+		break;
+	default:
+		return false;
+	}
+
 	switch (format) {
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_XBGR8888:
@@ -13244,38 +13423,36 @@ static bool skl_mod_supported(uint32_t format, uint64_t modifier)
 	}
 }
 
-static bool intel_primary_plane_format_mod_supported(struct drm_plane *plane,
-						     uint32_t format,
-						     uint64_t modifier)
+static bool intel_cursor_format_mod_supported(struct drm_plane *_plane,
+					      u32 format, u64 modifier)
 {
-	struct drm_i915_private *dev_priv = to_i915(plane->dev);
-
-	if (WARN_ON(modifier == DRM_FORMAT_MOD_INVALID))
-		return false;
-
-	if ((modifier >> 56) != DRM_FORMAT_MOD_VENDOR_INTEL &&
-	    modifier != DRM_FORMAT_MOD_LINEAR)
-		return false;
-
-	if (INTEL_GEN(dev_priv) >= 9)
-		return skl_mod_supported(format, modifier);
-	else if (INTEL_GEN(dev_priv) >= 4)
-		return i965_mod_supported(format, modifier);
-	else
-		return i8xx_mod_supported(format, modifier);
+	return modifier == DRM_FORMAT_MOD_LINEAR &&
+		format == DRM_FORMAT_ARGB8888;
 }
 
-static bool intel_cursor_plane_format_mod_supported(struct drm_plane *plane,
-						    uint32_t format,
-						    uint64_t modifier)
-{
-	if (WARN_ON(modifier == DRM_FORMAT_MOD_INVALID))
-		return false;
+static struct drm_plane_funcs skl_plane_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = intel_plane_destroy,
+	.atomic_get_property = intel_plane_atomic_get_property,
+	.atomic_set_property = intel_plane_atomic_set_property,
+	.atomic_duplicate_state = intel_plane_duplicate_state,
+	.atomic_destroy_state = intel_plane_destroy_state,
+	.format_mod_supported = skl_plane_format_mod_supported,
+};
 
-	return modifier == DRM_FORMAT_MOD_LINEAR && format == DRM_FORMAT_ARGB8888;
-}
+static struct drm_plane_funcs i965_plane_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = intel_plane_destroy,
+	.atomic_get_property = intel_plane_atomic_get_property,
+	.atomic_set_property = intel_plane_atomic_set_property,
+	.atomic_duplicate_state = intel_plane_duplicate_state,
+	.atomic_destroy_state = intel_plane_destroy_state,
+	.format_mod_supported = i965_plane_format_mod_supported,
+};
 
-static struct drm_plane_funcs intel_plane_funcs = {
+static struct drm_plane_funcs i8xx_plane_funcs = {
 	.update_plane = drm_atomic_helper_update_plane,
 	.disable_plane = drm_atomic_helper_disable_plane,
 	.destroy = intel_plane_destroy,
@@ -13283,7 +13460,7 @@ static struct drm_plane_funcs intel_plane_funcs = {
 	.atomic_set_property = intel_plane_atomic_set_property,
 	.atomic_duplicate_state = intel_plane_duplicate_state,
 	.atomic_destroy_state = intel_plane_destroy_state,
-	.format_mod_supported = intel_primary_plane_format_mod_supported,
+	.format_mod_supported = i8xx_plane_format_mod_supported,
 };
 
 static int
@@ -13408,7 +13585,7 @@ static const struct drm_plane_funcs intel_cursor_plane_funcs = {
 	.atomic_set_property = intel_plane_atomic_set_property,
 	.atomic_duplicate_state = intel_plane_duplicate_state,
 	.atomic_destroy_state = intel_plane_destroy_state,
-	.format_mod_supported = intel_cursor_plane_format_mod_supported,
+	.format_mod_supported = intel_cursor_format_mod_supported,
 };
 
 static bool i9xx_plane_has_fbc(struct drm_i915_private *dev_priv,
@@ -13466,6 +13643,7 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 {
 	struct intel_plane *primary = NULL;
 	struct intel_plane_state *state = NULL;
+	const struct drm_plane_funcs *plane_funcs;
 	const uint32_t *intel_primary_formats;
 	unsigned int supported_rotations;
 	unsigned int num_formats;
@@ -13521,6 +13699,9 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 	primary->check_plane = intel_check_primary_plane;
 
 	if (INTEL_GEN(dev_priv) >= 9) {
+		primary->has_ccs = skl_plane_has_ccs(dev_priv, pipe,
+						     PLANE_PRIMARY);
+
 		if (skl_plane_has_planar(dev_priv, pipe, PLANE_PRIMARY)) {
 			intel_primary_formats = skl_pri_planar_formats;
 			num_formats = ARRAY_SIZE(skl_pri_planar_formats);
@@ -13529,7 +13710,7 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 			num_formats = ARRAY_SIZE(skl_primary_formats);
 		}
 
-		if (skl_plane_has_ccs(dev_priv, pipe, PLANE_PRIMARY))
+		if (primary->has_ccs)
 			modifiers = skl_format_modifiers_ccs;
 		else
 			modifiers = skl_format_modifiers_noccs;
@@ -13537,6 +13718,8 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 		primary->update_plane = skl_update_plane;
 		primary->disable_plane = skl_disable_plane;
 		primary->get_hw_state = skl_plane_get_hw_state;
+
+		plane_funcs = &skl_plane_funcs;
 	} else if (INTEL_GEN(dev_priv) >= 4) {
 		intel_primary_formats = i965_primary_formats;
 		num_formats = ARRAY_SIZE(i965_primary_formats);
@@ -13545,6 +13728,8 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 		primary->update_plane = i9xx_update_plane;
 		primary->disable_plane = i9xx_disable_plane;
 		primary->get_hw_state = i9xx_plane_get_hw_state;
+
+		plane_funcs = &i965_plane_funcs;
 	} else {
 		intel_primary_formats = i8xx_primary_formats;
 		num_formats = ARRAY_SIZE(i8xx_primary_formats);
@@ -13553,25 +13738,27 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 		primary->update_plane = i9xx_update_plane;
 		primary->disable_plane = i9xx_disable_plane;
 		primary->get_hw_state = i9xx_plane_get_hw_state;
+
+		plane_funcs = &i8xx_plane_funcs;
 	}
 
 	if (INTEL_GEN(dev_priv) >= 9)
 		ret = drm_universal_plane_init(&dev_priv->drm, &primary->base,
-					       0, &intel_plane_funcs,
+					       0, plane_funcs,
 					       intel_primary_formats, num_formats,
 					       modifiers,
 					       DRM_PLANE_TYPE_PRIMARY,
 					       "plane 1%c", pipe_name(pipe));
 	else if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv))
 		ret = drm_universal_plane_init(&dev_priv->drm, &primary->base,
-					       0, &intel_plane_funcs,
+					       0, plane_funcs,
 					       intel_primary_formats, num_formats,
 					       modifiers,
 					       DRM_PLANE_TYPE_PRIMARY,
 					       "primary %c", pipe_name(pipe));
 	else
 		ret = drm_universal_plane_init(&dev_priv->drm, &primary->base,
-					       0, &intel_plane_funcs,
+					       0, plane_funcs,
 					       intel_primary_formats, num_formats,
 					       modifiers,
 					       DRM_PLANE_TYPE_PRIMARY,
@@ -13951,7 +14138,14 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 	if (intel_crt_present(dev_priv))
 		intel_crt_init(dev_priv);
 
-	if (IS_GEN9_LP(dev_priv)) {
+	if (IS_ICELAKE(dev_priv)) {
+		intel_ddi_init(dev_priv, PORT_A);
+		intel_ddi_init(dev_priv, PORT_B);
+		intel_ddi_init(dev_priv, PORT_C);
+		intel_ddi_init(dev_priv, PORT_D);
+		intel_ddi_init(dev_priv, PORT_E);
+		intel_ddi_init(dev_priv, PORT_F);
+	} else if (IS_GEN9_LP(dev_priv)) {
 		/*
 		 * FIXME: Broxton doesn't support port detection via the
 		 * DDI_BUF_CTL_A or SFUSE_STRAP registers, find another way to
@@ -13961,7 +14155,7 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 		intel_ddi_init(dev_priv, PORT_B);
 		intel_ddi_init(dev_priv, PORT_C);
 
-		intel_dsi_init(dev_priv);
+		vlv_dsi_init(dev_priv);
 	} else if (HAS_DDI(dev_priv)) {
 		int found;
 
@@ -14067,7 +14261,7 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 				intel_hdmi_init(dev_priv, CHV_HDMID, PORT_D);
 		}
 
-		intel_dsi_init(dev_priv);
+		vlv_dsi_init(dev_priv);
 	} else if (!IS_GEN2(dev_priv) && !IS_PINEVIEW(dev_priv)) {
 		bool found = false;
 
@@ -14124,14 +14318,15 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 static void intel_user_framebuffer_destroy(struct drm_framebuffer *fb)
 {
 	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
+	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 
 	drm_framebuffer_cleanup(fb);
 
-	i915_gem_object_lock(intel_fb->obj);
-	WARN_ON(!intel_fb->obj->framebuffer_references--);
-	i915_gem_object_unlock(intel_fb->obj);
+	i915_gem_object_lock(obj);
+	WARN_ON(!obj->framebuffer_references--);
+	i915_gem_object_unlock(obj);
 
-	i915_gem_object_put(intel_fb->obj);
+	i915_gem_object_put(obj);
 
 	kfree(intel_fb);
 }
@@ -14140,8 +14335,7 @@ static int intel_user_framebuffer_create_handle(struct drm_framebuffer *fb,
 						struct drm_file *file,
 						unsigned int *handle)
 {
-	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
-	struct drm_i915_gem_object *obj = intel_fb->obj;
+	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 
 	if (obj->userptr.mm) {
 		DRM_DEBUG("attempting to use a userptr for a framebuffer, denied\n");
@@ -14349,11 +14543,6 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb,
 		}
 		break;
 	case DRM_FORMAT_NV12:
-		if (mode_cmd->modifier[0] == I915_FORMAT_MOD_Y_TILED_CCS ||
-		    mode_cmd->modifier[0] == I915_FORMAT_MOD_Yf_TILED_CCS) {
-			DRM_DEBUG_KMS("RC not to be enabled with NV12\n");
-			goto err;
-		}
 		if (INTEL_GEN(dev_priv) < 9 || IS_SKYLAKE(dev_priv) ||
 		    IS_BROXTON(dev_priv)) {
 			DRM_DEBUG_KMS("unsupported pixel format: %s\n",
@@ -14411,9 +14600,9 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb,
 				      i, fb->pitches[i], stride_alignment);
 			goto err;
 		}
-	}
 
-	intel_fb->obj = obj;
+		fb->obj[i] = &obj->base;
+	}
 
 	ret = intel_fill_fb_info(dev_priv, fb);
 	if (ret)
@@ -14469,6 +14658,10 @@ static enum drm_mode_status
 intel_mode_valid(struct drm_device *dev,
 		 const struct drm_display_mode *mode)
 {
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	int hdisplay_max, htotal_max;
+	int vdisplay_max, vtotal_max;
+
 	/*
 	 * Can't reject DBLSCAN here because Xorg ddxen can add piles
 	 * of DBLSCAN modes to the output's mode list when they detect
@@ -14498,6 +14691,36 @@ intel_mode_valid(struct drm_device *dev,
 			   DRM_MODE_FLAG_CLKDIV2))
 		return MODE_BAD;
 
+	if (INTEL_GEN(dev_priv) >= 9 ||
+	    IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) {
+		hdisplay_max = 8192; /* FDI max 4096 handled elsewhere */
+		vdisplay_max = 4096;
+		htotal_max = 8192;
+		vtotal_max = 8192;
+	} else if (INTEL_GEN(dev_priv) >= 3) {
+		hdisplay_max = 4096;
+		vdisplay_max = 4096;
+		htotal_max = 8192;
+		vtotal_max = 8192;
+	} else {
+		hdisplay_max = 2048;
+		vdisplay_max = 2048;
+		htotal_max = 4096;
+		vtotal_max = 4096;
+	}
+
+	if (mode->hdisplay > hdisplay_max ||
+	    mode->hsync_start > htotal_max ||
+	    mode->hsync_end > htotal_max ||
+	    mode->htotal > htotal_max)
+		return MODE_H_ILLEGAL;
+
+	if (mode->vdisplay > vdisplay_max ||
+	    mode->vsync_start > vtotal_max ||
+	    mode->vsync_end > vtotal_max ||
+	    mode->vtotal > vtotal_max)
+		return MODE_V_ILLEGAL;
+
 	return MODE_OK;
 }
 
@@ -14955,6 +15178,7 @@ int intel_modeset_init(struct drm_device *dev)
 		}
 	}
 
+	/* maximum framebuffer dimensions */
 	if (IS_GEN2(dev_priv)) {
 		dev->mode_config.max_width = 2048;
 		dev->mode_config.max_height = 2048;
@@ -14970,11 +15194,11 @@ int intel_modeset_init(struct drm_device *dev)
 		dev->mode_config.cursor_width = IS_I845G(dev_priv) ? 64 : 512;
 		dev->mode_config.cursor_height = 1023;
 	} else if (IS_GEN2(dev_priv)) {
-		dev->mode_config.cursor_width = GEN2_CURSOR_WIDTH;
-		dev->mode_config.cursor_height = GEN2_CURSOR_HEIGHT;
+		dev->mode_config.cursor_width = 64;
+		dev->mode_config.cursor_height = 64;
 	} else {
-		dev->mode_config.cursor_width = MAX_CURSOR_WIDTH;
-		dev->mode_config.cursor_height = MAX_CURSOR_HEIGHT;
+		dev->mode_config.cursor_width = 256;
+		dev->mode_config.cursor_height = 256;
 	}
 
 	dev->mode_config.fb_base = ggtt->gmadr.start;
@@ -15124,8 +15348,8 @@ void i830_disable_pipe(struct drm_i915_private *dev_priv, enum pipe pipe)
 	WARN_ON(I915_READ(DSPCNTR(PLANE_A)) & DISPLAY_PLANE_ENABLE);
 	WARN_ON(I915_READ(DSPCNTR(PLANE_B)) & DISPLAY_PLANE_ENABLE);
 	WARN_ON(I915_READ(DSPCNTR(PLANE_C)) & DISPLAY_PLANE_ENABLE);
-	WARN_ON(I915_READ(CURCNTR(PIPE_A)) & CURSOR_MODE);
-	WARN_ON(I915_READ(CURCNTR(PIPE_B)) & CURSOR_MODE);
+	WARN_ON(I915_READ(CURCNTR(PIPE_A)) & MCURSOR_MODE);
+	WARN_ON(I915_READ(CURCNTR(PIPE_B)) & MCURSOR_MODE);
 
 	I915_WRITE(PIPECONF(pipe), 0);
 	POSTING_READ(PIPECONF(pipe));
@@ -15139,12 +15363,12 @@ void i830_disable_pipe(struct drm_i915_private *dev_priv, enum pipe pipe)
 static bool intel_plane_mapping_ok(struct intel_crtc *crtc,
 				   struct intel_plane *plane)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	enum i9xx_plane_id i9xx_plane = plane->i9xx_plane;
-	u32 val = I915_READ(DSPCNTR(i9xx_plane));
+	enum pipe pipe;
+
+	if (!plane->get_hw_state(plane, &pipe))
+		return true;
 
-	return (val & DISPLAY_PLANE_ENABLE) == 0 ||
-		(val & DISPPLANE_SEL_PIPE_MASK) == DISPPLANE_SEL_PIPE(crtc->pipe);
+	return pipe == crtc->pipe;
 }
 
 static void
@@ -15303,6 +15527,9 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 		connector->base.dpms = DRM_MODE_DPMS_OFF;
 		connector->base.encoder = NULL;
 	}
+
+	/* notify opregion of the sanitized encoder state */
+	intel_opregion_notify_encoder(encoder, connector && has_active_crtc);
 }
 
 void i915_redisable_vga_power_on(struct drm_i915_private *dev_priv)
@@ -15343,7 +15570,10 @@ static void readout_plane_state(struct intel_crtc *crtc)
 	for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) {
 		struct intel_plane_state *plane_state =
 			to_intel_plane_state(plane->base.state);
-		bool visible = plane->get_hw_state(plane);
+		enum pipe pipe;
+		bool visible;
+
+		visible = plane->get_hw_state(plane, &pipe);
 
 		intel_set_plane_visible(crtc_state, plane_state, visible);
 	}
@@ -15442,9 +15672,9 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 				 * rely on the connector_mask being accurate.
 				 */
 				encoder->base.crtc->state->connector_mask |=
-					1 << drm_connector_index(&connector->base);
+					drm_connector_mask(&connector->base);
 				encoder->base.crtc->state->encoder_mask |=
-					1 << drm_encoder_index(&encoder->base);
+					drm_encoder_mask(&encoder->base);
 			}
 
 		} else {
@@ -15510,11 +15740,20 @@ get_encoder_power_domains(struct drm_i915_private *dev_priv)
 	for_each_intel_encoder(&dev_priv->drm, encoder) {
 		u64 get_domains;
 		enum intel_display_power_domain domain;
+		struct intel_crtc_state *crtc_state;
 
 		if (!encoder->get_power_domains)
 			continue;
 
-		get_domains = encoder->get_power_domains(encoder);
+		/*
+		 * MST-primary and inactive encoders don't have a crtc state
+		 * and neither of these require any power domain references.
+		 */
+		if (!encoder->base.crtc)
+			continue;
+
+		crtc_state = to_intel_crtc_state(encoder->base.crtc->state);
+		get_domains = encoder->get_power_domains(encoder, crtc_state);
 		for_each_power_domain(domain, get_domains)
 			intel_display_power_get(dev_priv, domain);
 	}
@@ -15690,6 +15929,8 @@ void intel_modeset_cleanup(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
+	flush_workqueue(dev_priv->modeset_wq);
+
 	flush_work(&dev_priv->atomic_helper.free_work);
 	WARN_ON(!llist_empty(&dev_priv->atomic_helper.free_list));
 
@@ -15733,8 +15974,7 @@ void intel_connector_attach_encoder(struct intel_connector *connector,
 				    struct intel_encoder *encoder)
 {
 	connector->encoder = encoder;
-	drm_mode_connector_attach_encoder(&connector->base,
-					  &encoder->base);
+	drm_connector_attach_encoder(&connector->base, &encoder->base);
 }
 
 /*
diff --git a/drivers/gpu/drm/i915/intel_display.h b/drivers/gpu/drm/i915/intel_display.h
index 2ef31617614a..9292001cdd14 100644
--- a/drivers/gpu/drm/i915/intel_display.h
+++ b/drivers/gpu/drm/i915/intel_display.h
@@ -126,6 +126,17 @@ enum port {
 
 #define port_name(p) ((p) + 'A')
 
+enum tc_port {
+	PORT_TC_NONE = -1,
+
+	PORT_TC1 = 0,
+	PORT_TC2,
+	PORT_TC3,
+	PORT_TC4,
+
+	I915_MAX_TC_PORTS
+};
+
 enum dpio_channel {
 	DPIO_CH0,
 	DPIO_CH1
@@ -144,7 +155,7 @@ enum aux_ch {
 	AUX_CH_B,
 	AUX_CH_C,
 	AUX_CH_D,
-	_AUX_CH_E, /* does not exist */
+	AUX_CH_E, /* ICL+ */
 	AUX_CH_F,
 };
 
@@ -185,8 +196,13 @@ enum intel_display_power_domain {
 	POWER_DOMAIN_AUX_B,
 	POWER_DOMAIN_AUX_C,
 	POWER_DOMAIN_AUX_D,
+	POWER_DOMAIN_AUX_E,
 	POWER_DOMAIN_AUX_F,
 	POWER_DOMAIN_AUX_IO_A,
+	POWER_DOMAIN_AUX_TBT1,
+	POWER_DOMAIN_AUX_TBT2,
+	POWER_DOMAIN_AUX_TBT3,
+	POWER_DOMAIN_AUX_TBT4,
 	POWER_DOMAIN_GMBUS,
 	POWER_DOMAIN_MODESET,
 	POWER_DOMAIN_GT_IRQ,
@@ -249,7 +265,7 @@ struct intel_link_m_n {
 			    &(dev)->mode_config.plane_list,		\
 			    base.head)					\
 		for_each_if((plane_mask) &				\
-			    BIT(drm_plane_index(&intel_plane->base)))
+			    drm_plane_mask(&intel_plane->base)))
 
 #define for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane)	\
 	list_for_each_entry(intel_plane,				\
@@ -266,13 +282,17 @@ struct intel_link_m_n {
 	list_for_each_entry(intel_crtc,					\
 			    &(dev)->mode_config.crtc_list,		\
 			    base.head)					\
-		for_each_if((crtc_mask) & BIT(drm_crtc_index(&intel_crtc->base)))
+		for_each_if((crtc_mask) & drm_crtc_mask(&intel_crtc->base))
 
 #define for_each_intel_encoder(dev, intel_encoder)		\
 	list_for_each_entry(intel_encoder,			\
 			    &(dev)->mode_config.encoder_list,	\
 			    base.head)
 
+#define for_each_intel_dp(dev, intel_encoder)			\
+	for_each_intel_encoder(dev, intel_encoder)		\
+		for_each_if(intel_encoder_is_dp(intel_encoder))
+
 #define for_each_intel_connector_iter(intel_connector, iter) \
 	while ((intel_connector = to_intel_connector(drm_connector_list_iter_next(iter))))
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 16faea30114a..cd0f649b57a5 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -56,7 +56,7 @@ struct dp_link_dpll {
 	struct dpll dpll;
 };
 
-static const struct dp_link_dpll gen4_dpll[] = {
+static const struct dp_link_dpll g4x_dpll[] = {
 	{ 162000,
 		{ .p1 = 2, .p2 = 10, .n = 2, .m1 = 23, .m2 = 8 } },
 	{ 270000,
@@ -256,6 +256,17 @@ static int cnl_max_source_rate(struct intel_dp *intel_dp)
 	return 810000;
 }
 
+static int icl_max_source_rate(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
+	enum port port = dig_port->base.port;
+
+	if (port == PORT_B)
+		return 540000;
+
+	return 810000;
+}
+
 static void
 intel_dp_set_source_rates(struct intel_dp *intel_dp)
 {
@@ -285,10 +296,13 @@ intel_dp_set_source_rates(struct intel_dp *intel_dp)
 	/* This should only be done once */
 	WARN_ON(intel_dp->source_rates || intel_dp->num_source_rates);
 
-	if (IS_CANNONLAKE(dev_priv)) {
+	if (INTEL_GEN(dev_priv) >= 10) {
 		source_rates = cnl_rates;
 		size = ARRAY_SIZE(cnl_rates);
-		max_rate = cnl_max_source_rate(intel_dp);
+		if (INTEL_GEN(dev_priv) == 10)
+			max_rate = cnl_max_source_rate(intel_dp);
+		else
+			max_rate = icl_max_source_rate(intel_dp);
 	} else if (IS_GEN9_LP(dev_priv)) {
 		source_rates = bxt_rates;
 		size = ARRAY_SIZE(bxt_rates);
@@ -516,7 +530,7 @@ vlv_power_sequencer_kick(struct intel_dp *intel_dp)
 	uint32_t DP;
 
 	if (WARN(I915_READ(intel_dp->output_reg) & DP_PORT_EN,
-		 "skipping pipe %c power seqeuncer kick due to port %c being active\n",
+		 "skipping pipe %c power sequencer kick due to port %c being active\n",
 		 pipe_name(pipe), port_name(intel_dig_port->base.port)))
 		return;
 
@@ -532,9 +546,9 @@ vlv_power_sequencer_kick(struct intel_dp *intel_dp)
 	DP |= DP_LINK_TRAIN_PAT_1;
 
 	if (IS_CHERRYVIEW(dev_priv))
-		DP |= DP_PIPE_SELECT_CHV(pipe);
-	else if (pipe == PIPE_B)
-		DP |= DP_PIPEB_SELECT;
+		DP |= DP_PIPE_SEL_CHV(pipe);
+	else
+		DP |= DP_PIPE_SEL(pipe);
 
 	pll_enabled = I915_READ(DPLL(pipe)) & DPLL_VCO_ENABLE;
 
@@ -557,7 +571,7 @@ vlv_power_sequencer_kick(struct intel_dp *intel_dp)
 	/*
 	 * Similar magic as in intel_dp_enable_port().
 	 * We _must_ do this port enable + disable trick
-	 * to make this power seqeuencer lock onto the port.
+	 * to make this power sequencer lock onto the port.
 	 * Otherwise even VDD force bit won't work.
 	 */
 	I915_WRITE(intel_dp->output_reg, DP);
@@ -586,14 +600,8 @@ static enum pipe vlv_find_free_pps(struct drm_i915_private *dev_priv)
 	 * We don't have power sequencer currently.
 	 * Pick one that's not used by other ports.
 	 */
-	for_each_intel_encoder(&dev_priv->drm, encoder) {
-		struct intel_dp *intel_dp;
-
-		if (encoder->type != INTEL_OUTPUT_DP &&
-		    encoder->type != INTEL_OUTPUT_EDP)
-			continue;
-
-		intel_dp = enc_to_intel_dp(&encoder->base);
+	for_each_intel_dp(&dev_priv->drm, encoder) {
+		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 
 		if (encoder->type == INTEL_OUTPUT_EDP) {
 			WARN_ON(intel_dp->active_pipe != INVALID_PIPE &&
@@ -785,19 +793,8 @@ void intel_power_sequencer_reset(struct drm_i915_private *dev_priv)
 	 * should use them always.
 	 */
 
-	for_each_intel_encoder(&dev_priv->drm, encoder) {
-		struct intel_dp *intel_dp;
-
-		if (encoder->type != INTEL_OUTPUT_DP &&
-		    encoder->type != INTEL_OUTPUT_EDP &&
-		    encoder->type != INTEL_OUTPUT_DDI)
-			continue;
-
-		intel_dp = enc_to_intel_dp(&encoder->base);
-
-		/* Skip pure DVI/HDMI DDI encoders */
-		if (!i915_mmio_reg_valid(intel_dp->output_reg))
-			continue;
+	for_each_intel_dp(&dev_priv->drm, encoder) {
+		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 
 		WARN_ON(intel_dp->active_pipe != INVALID_PIPE);
 
@@ -939,7 +936,7 @@ intel_dp_check_edp(struct intel_dp *intel_dp)
 }
 
 static uint32_t
-intel_dp_aux_wait_done(struct intel_dp *intel_dp, bool has_aux_irq)
+intel_dp_aux_wait_done(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
 	i915_reg_t ch_ctl = intel_dp->aux_ch_ctl_reg(intel_dp);
@@ -947,14 +944,10 @@ intel_dp_aux_wait_done(struct intel_dp *intel_dp, bool has_aux_irq)
 	bool done;
 
 #define C (((status = I915_READ_NOTRACE(ch_ctl)) & DP_AUX_CH_CTL_SEND_BUSY) == 0)
-	if (has_aux_irq)
-		done = wait_event_timeout(dev_priv->gmbus_wait_queue, C,
-					  msecs_to_jiffies_timeout(10));
-	else
-		done = wait_for(C, 10) == 0;
+	done = wait_event_timeout(dev_priv->gmbus_wait_queue, C,
+				  msecs_to_jiffies_timeout(10));
 	if (!done)
-		DRM_ERROR("dp aux hw did not signal timeout (has irq: %i)!\n",
-			  has_aux_irq);
+		DRM_ERROR("dp aux hw did not signal timeout!\n");
 #undef C
 
 	return status;
@@ -1019,7 +1012,6 @@ static uint32_t skl_get_aux_clock_divider(struct intel_dp *intel_dp, int index)
 }
 
 static uint32_t g4x_get_aux_send_ctl(struct intel_dp *intel_dp,
-				     bool has_aux_irq,
 				     int send_bytes,
 				     uint32_t aux_clock_divider)
 {
@@ -1040,7 +1032,7 @@ static uint32_t g4x_get_aux_send_ctl(struct intel_dp *intel_dp,
 
 	return DP_AUX_CH_CTL_SEND_BUSY |
 	       DP_AUX_CH_CTL_DONE |
-	       (has_aux_irq ? DP_AUX_CH_CTL_INTERRUPT : 0) |
+	       DP_AUX_CH_CTL_INTERRUPT |
 	       DP_AUX_CH_CTL_TIME_OUT_ERROR |
 	       timeout |
 	       DP_AUX_CH_CTL_RECEIVE_ERROR |
@@ -1050,13 +1042,12 @@ static uint32_t g4x_get_aux_send_ctl(struct intel_dp *intel_dp,
 }
 
 static uint32_t skl_get_aux_send_ctl(struct intel_dp *intel_dp,
-				      bool has_aux_irq,
 				      int send_bytes,
 				      uint32_t unused)
 {
 	return DP_AUX_CH_CTL_SEND_BUSY |
 	       DP_AUX_CH_CTL_DONE |
-	       (has_aux_irq ? DP_AUX_CH_CTL_INTERRUPT : 0) |
+	       DP_AUX_CH_CTL_INTERRUPT |
 	       DP_AUX_CH_CTL_TIME_OUT_ERROR |
 	       DP_AUX_CH_CTL_TIME_OUT_MAX |
 	       DP_AUX_CH_CTL_RECEIVE_ERROR |
@@ -1079,7 +1070,6 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp,
 	int i, ret, recv_bytes;
 	uint32_t status;
 	int try, clock = 0;
-	bool has_aux_irq = HAS_AUX_IRQ(dev_priv);
 	bool vdd;
 
 	ch_ctl = intel_dp->aux_ch_ctl_reg(intel_dp);
@@ -1134,7 +1124,6 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp,
 
 	while ((aux_clock_divider = intel_dp->get_aux_clock_divider(intel_dp, clock++))) {
 		u32 send_ctl = intel_dp->get_aux_send_ctl(intel_dp,
-							  has_aux_irq,
 							  send_bytes,
 							  aux_clock_divider);
 
@@ -1151,7 +1140,7 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp,
 			/* Send the command and wait for it to complete */
 			I915_WRITE(ch_ctl, send_ctl);
 
-			status = intel_dp_aux_wait_done(intel_dp, has_aux_irq);
+			status = intel_dp_aux_wait_done(intel_dp);
 
 			/* Clear done status and any errors */
 			I915_WRITE(ch_ctl,
@@ -1350,6 +1339,9 @@ static enum aux_ch intel_aux_ch(struct intel_dp *intel_dp)
 	case DP_AUX_D:
 		aux_ch = AUX_CH_D;
 		break;
+	case DP_AUX_E:
+		aux_ch = AUX_CH_E;
+		break;
 	case DP_AUX_F:
 		aux_ch = AUX_CH_F;
 		break;
@@ -1377,6 +1369,8 @@ intel_aux_power_domain(struct intel_dp *intel_dp)
 		return POWER_DOMAIN_AUX_C;
 	case AUX_CH_D:
 		return POWER_DOMAIN_AUX_D;
+	case AUX_CH_E:
+		return POWER_DOMAIN_AUX_E;
 	case AUX_CH_F:
 		return POWER_DOMAIN_AUX_F;
 	default:
@@ -1463,6 +1457,7 @@ static i915_reg_t skl_aux_ctl_reg(struct intel_dp *intel_dp)
 	case AUX_CH_B:
 	case AUX_CH_C:
 	case AUX_CH_D:
+	case AUX_CH_E:
 	case AUX_CH_F:
 		return DP_AUX_CH_CTL(aux_ch);
 	default:
@@ -1481,6 +1476,7 @@ static i915_reg_t skl_aux_data_reg(struct intel_dp *intel_dp, int index)
 	case AUX_CH_B:
 	case AUX_CH_C:
 	case AUX_CH_D:
+	case AUX_CH_E:
 	case AUX_CH_F:
 		return DP_AUX_CH_DATA(aux_ch, index);
 	default:
@@ -1544,6 +1540,13 @@ bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp)
 	return max_rate >= 540000;
 }
 
+bool intel_dp_source_supports_hbr3(struct intel_dp *intel_dp)
+{
+	int max_rate = intel_dp->source_rates[intel_dp->num_source_rates - 1];
+
+	return max_rate >= 810000;
+}
+
 static void
 intel_dp_set_clock(struct intel_encoder *encoder,
 		   struct intel_crtc_state *pipe_config)
@@ -1553,8 +1556,8 @@ intel_dp_set_clock(struct intel_encoder *encoder,
 	int i, count = 0;
 
 	if (IS_G4X(dev_priv)) {
-		divisor = gen4_dpll;
-		count = ARRAY_SIZE(gen4_dpll);
+		divisor = g4x_dpll;
+		count = ARRAY_SIZE(g4x_dpll);
 	} else if (HAS_PCH_SPLIT(dev_priv)) {
 		divisor = pch_dpll;
 		count = ARRAY_SIZE(pch_dpll);
@@ -1970,7 +1973,7 @@ static void intel_dp_prepare(struct intel_encoder *encoder,
 
 	/* Split out the IBX/CPU vs CPT settings */
 
-	if (IS_GEN7(dev_priv) && port == PORT_A) {
+	if (IS_IVYBRIDGE(dev_priv) && port == PORT_A) {
 		if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
 			intel_dp->DP |= DP_SYNC_HS_HIGH;
 		if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
@@ -1980,7 +1983,7 @@ static void intel_dp_prepare(struct intel_encoder *encoder,
 		if (drm_dp_enhanced_frame_cap(intel_dp->dpcd))
 			intel_dp->DP |= DP_ENHANCED_FRAMING;
 
-		intel_dp->DP |= crtc->pipe << 29;
+		intel_dp->DP |= DP_PIPE_SEL_IVB(crtc->pipe);
 	} else if (HAS_PCH_CPT(dev_priv) && port != PORT_A) {
 		u32 trans_dp;
 
@@ -2006,9 +2009,9 @@ static void intel_dp_prepare(struct intel_encoder *encoder,
 			intel_dp->DP |= DP_ENHANCED_FRAMING;
 
 		if (IS_CHERRYVIEW(dev_priv))
-			intel_dp->DP |= DP_PIPE_SELECT_CHV(crtc->pipe);
-		else if (crtc->pipe == PIPE_B)
-			intel_dp->DP |= DP_PIPEB_SELECT;
+			intel_dp->DP |= DP_PIPE_SEL_CHV(crtc->pipe);
+		else
+			intel_dp->DP |= DP_PIPE_SEL(crtc->pipe);
 	}
 }
 
@@ -2630,52 +2633,66 @@ void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode)
 			      mode == DRM_MODE_DPMS_ON ? "enable" : "disable");
 }
 
+static bool cpt_dp_port_selected(struct drm_i915_private *dev_priv,
+				 enum port port, enum pipe *pipe)
+{
+	enum pipe p;
+
+	for_each_pipe(dev_priv, p) {
+		u32 val = I915_READ(TRANS_DP_CTL(p));
+
+		if ((val & TRANS_DP_PORT_SEL_MASK) == TRANS_DP_PORT_SEL(port)) {
+			*pipe = p;
+			return true;
+		}
+	}
+
+	DRM_DEBUG_KMS("No pipe for DP port %c found\n", port_name(port));
+
+	/* must initialize pipe to something for the asserts */
+	*pipe = PIPE_A;
+
+	return false;
+}
+
+bool intel_dp_port_enabled(struct drm_i915_private *dev_priv,
+			   i915_reg_t dp_reg, enum port port,
+			   enum pipe *pipe)
+{
+	bool ret;
+	u32 val;
+
+	val = I915_READ(dp_reg);
+
+	ret = val & DP_PORT_EN;
+
+	/* asserts want to know the pipe even if the port is disabled */
+	if (IS_IVYBRIDGE(dev_priv) && port == PORT_A)
+		*pipe = (val & DP_PIPE_SEL_MASK_IVB) >> DP_PIPE_SEL_SHIFT_IVB;
+	else if (HAS_PCH_CPT(dev_priv) && port != PORT_A)
+		ret &= cpt_dp_port_selected(dev_priv, port, pipe);
+	else if (IS_CHERRYVIEW(dev_priv))
+		*pipe = (val & DP_PIPE_SEL_MASK_CHV) >> DP_PIPE_SEL_SHIFT_CHV;
+	else
+		*pipe = (val & DP_PIPE_SEL_MASK) >> DP_PIPE_SEL_SHIFT;
+
+	return ret;
+}
+
 static bool intel_dp_get_hw_state(struct intel_encoder *encoder,
 				  enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-	enum port port = encoder->port;
-	u32 tmp;
 	bool ret;
 
 	if (!intel_display_power_get_if_enabled(dev_priv,
 						encoder->power_domain))
 		return false;
 
-	ret = false;
+	ret = intel_dp_port_enabled(dev_priv, intel_dp->output_reg,
+				    encoder->port, pipe);
 
-	tmp = I915_READ(intel_dp->output_reg);
-
-	if (!(tmp & DP_PORT_EN))
-		goto out;
-
-	if (IS_GEN7(dev_priv) && port == PORT_A) {
-		*pipe = PORT_TO_PIPE_CPT(tmp);
-	} else if (HAS_PCH_CPT(dev_priv) && port != PORT_A) {
-		enum pipe p;
-
-		for_each_pipe(dev_priv, p) {
-			u32 trans_dp = I915_READ(TRANS_DP_CTL(p));
-			if (TRANS_DP_PIPE_TO_PORT(trans_dp) == port) {
-				*pipe = p;
-				ret = true;
-
-				goto out;
-			}
-		}
-
-		DRM_DEBUG_KMS("No pipe for dp port 0x%x found\n",
-			      i915_mmio_reg_offset(intel_dp->output_reg));
-	} else if (IS_CHERRYVIEW(dev_priv)) {
-		*pipe = DP_PORT_TO_PIPE_CHV(tmp);
-	} else {
-		*pipe = PORT_TO_PIPE(tmp);
-	}
-
-	ret = true;
-
-out:
 	intel_display_power_put(dev_priv, encoder->power_domain);
 
 	return ret;
@@ -2796,10 +2813,6 @@ static void vlv_disable_dp(struct intel_encoder *encoder,
 			   const struct intel_crtc_state *old_crtc_state,
 			   const struct drm_connector_state *old_conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-
-	intel_psr_disable(intel_dp, old_crtc_state);
-
 	intel_disable_dp(encoder, old_crtc_state, old_conn_state);
 }
 
@@ -2854,10 +2867,11 @@ _intel_dp_set_link_train(struct intel_dp *intel_dp,
 	struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	enum port port = intel_dig_port->base.port;
+	uint8_t train_pat_mask = drm_dp_training_pattern_mask(intel_dp->dpcd);
 
-	if (dp_train_pat & DP_TRAINING_PATTERN_MASK)
+	if (dp_train_pat & train_pat_mask)
 		DRM_DEBUG_KMS("Using DP training pattern TPS%d\n",
-			      dp_train_pat & DP_TRAINING_PATTERN_MASK);
+			      dp_train_pat & train_pat_mask);
 
 	if (HAS_DDI(dev_priv)) {
 		uint32_t temp = I915_READ(DP_TP_CTL(port));
@@ -2868,7 +2882,7 @@ _intel_dp_set_link_train(struct intel_dp *intel_dp,
 			temp &= ~DP_TP_CTL_SCRAMBLE_DISABLE;
 
 		temp &= ~DP_TP_CTL_LINK_TRAIN_MASK;
-		switch (dp_train_pat & DP_TRAINING_PATTERN_MASK) {
+		switch (dp_train_pat & train_pat_mask) {
 		case DP_TRAINING_PATTERN_DISABLE:
 			temp |= DP_TP_CTL_LINK_TRAIN_NORMAL;
 
@@ -2882,10 +2896,13 @@ _intel_dp_set_link_train(struct intel_dp *intel_dp,
 		case DP_TRAINING_PATTERN_3:
 			temp |= DP_TP_CTL_LINK_TRAIN_PAT3;
 			break;
+		case DP_TRAINING_PATTERN_4:
+			temp |= DP_TP_CTL_LINK_TRAIN_PAT4;
+			break;
 		}
 		I915_WRITE(DP_TP_CTL(port), temp);
 
-	} else if ((IS_GEN7(dev_priv) && port == PORT_A) ||
+	} else if ((IS_IVYBRIDGE(dev_priv) && port == PORT_A) ||
 		   (HAS_PCH_CPT(dev_priv) && port != PORT_A)) {
 		*DP &= ~DP_LINK_TRAIN_MASK_CPT;
 
@@ -3008,10 +3025,7 @@ static void vlv_enable_dp(struct intel_encoder *encoder,
 			  const struct intel_crtc_state *pipe_config,
 			  const struct drm_connector_state *conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-
 	intel_edp_backlight_on(pipe_config, conn_state);
-	intel_psr_enable(intel_dp, pipe_config);
 }
 
 static void g4x_pre_enable_dp(struct intel_encoder *encoder,
@@ -3043,11 +3057,11 @@ static void vlv_detach_power_sequencer(struct intel_dp *intel_dp)
 	edp_panel_vdd_off_sync(intel_dp);
 
 	/*
-	 * VLV seems to get confused when multiple power seqeuencers
+	 * VLV seems to get confused when multiple power sequencers
 	 * have the same port selected (even if only one has power/vdd
 	 * enabled). The failure manifests as vlv_wait_port_ready() failing
 	 * CHV on the other hand doesn't seem to mind having the same port
-	 * selected in multiple power seqeuencers, but let's clear the
+	 * selected in multiple power sequencers, but let's clear the
 	 * port select always when logically disconnecting a power sequencer
 	 * from a port.
 	 */
@@ -3066,16 +3080,9 @@ static void vlv_steal_power_sequencer(struct drm_i915_private *dev_priv,
 
 	lockdep_assert_held(&dev_priv->pps_mutex);
 
-	for_each_intel_encoder(&dev_priv->drm, encoder) {
-		struct intel_dp *intel_dp;
-		enum port port;
-
-		if (encoder->type != INTEL_OUTPUT_DP &&
-		    encoder->type != INTEL_OUTPUT_EDP)
-			continue;
-
-		intel_dp = enc_to_intel_dp(&encoder->base);
-		port = dp_to_dig_port(intel_dp)->base.port;
+	for_each_intel_dp(&dev_priv->drm, encoder) {
+		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+		enum port port = encoder->port;
 
 		WARN(intel_dp->active_pipe == pipe,
 		     "stealing pipe %c power sequencer from active (e)DP port %c\n",
@@ -3197,14 +3204,14 @@ uint8_t
 intel_dp_voltage_max(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
-	enum port port = dp_to_dig_port(intel_dp)->base.port;
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	enum port port = encoder->port;
 
-	if (INTEL_GEN(dev_priv) >= 9) {
-		struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	if (HAS_DDI(dev_priv))
 		return intel_ddi_dp_voltage_max(encoder);
-	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+	else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
 		return DP_TRAIN_VOLTAGE_SWING_LEVEL_3;
-	else if (IS_GEN7(dev_priv) && port == PORT_A)
+	else if (IS_IVYBRIDGE(dev_priv) && port == PORT_A)
 		return DP_TRAIN_VOLTAGE_SWING_LEVEL_2;
 	else if (HAS_PCH_CPT(dev_priv) && port != PORT_A)
 		return DP_TRAIN_VOLTAGE_SWING_LEVEL_3;
@@ -3216,33 +3223,11 @@ uint8_t
 intel_dp_pre_emphasis_max(struct intel_dp *intel_dp, uint8_t voltage_swing)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
-	enum port port = dp_to_dig_port(intel_dp)->base.port;
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	enum port port = encoder->port;
 
-	if (INTEL_GEN(dev_priv) >= 9) {
-		switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
-		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
-			return DP_TRAIN_PRE_EMPH_LEVEL_3;
-		case DP_TRAIN_VOLTAGE_SWING_LEVEL_1:
-			return DP_TRAIN_PRE_EMPH_LEVEL_2;
-		case DP_TRAIN_VOLTAGE_SWING_LEVEL_2:
-			return DP_TRAIN_PRE_EMPH_LEVEL_1;
-		case DP_TRAIN_VOLTAGE_SWING_LEVEL_3:
-			return DP_TRAIN_PRE_EMPH_LEVEL_0;
-		default:
-			return DP_TRAIN_PRE_EMPH_LEVEL_0;
-		}
-	} else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
-		switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
-		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
-			return DP_TRAIN_PRE_EMPH_LEVEL_3;
-		case DP_TRAIN_VOLTAGE_SWING_LEVEL_1:
-			return DP_TRAIN_PRE_EMPH_LEVEL_2;
-		case DP_TRAIN_VOLTAGE_SWING_LEVEL_2:
-			return DP_TRAIN_PRE_EMPH_LEVEL_1;
-		case DP_TRAIN_VOLTAGE_SWING_LEVEL_3:
-		default:
-			return DP_TRAIN_PRE_EMPH_LEVEL_0;
-		}
+	if (HAS_DDI(dev_priv)) {
+		return intel_ddi_dp_pre_emphasis_max(encoder, voltage_swing);
 	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
 		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
@@ -3255,7 +3240,7 @@ intel_dp_pre_emphasis_max(struct intel_dp *intel_dp, uint8_t voltage_swing)
 		default:
 			return DP_TRAIN_PRE_EMPH_LEVEL_0;
 		}
-	} else if (IS_GEN7(dev_priv) && port == PORT_A) {
+	} else if (IS_IVYBRIDGE(dev_priv) && port == PORT_A) {
 		switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
 		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
 			return DP_TRAIN_PRE_EMPH_LEVEL_2;
@@ -3450,7 +3435,7 @@ static uint32_t chv_signal_levels(struct intel_dp *intel_dp)
 }
 
 static uint32_t
-gen4_signal_levels(uint8_t train_set)
+g4x_signal_levels(uint8_t train_set)
 {
 	uint32_t	signal_levels = 0;
 
@@ -3487,9 +3472,9 @@ gen4_signal_levels(uint8_t train_set)
 	return signal_levels;
 }
 
-/* Gen6's DP voltage swing and pre-emphasis control */
+/* SNB CPU eDP voltage swing and pre-emphasis control */
 static uint32_t
-gen6_edp_signal_levels(uint8_t train_set)
+snb_cpu_edp_signal_levels(uint8_t train_set)
 {
 	int signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK |
 					 DP_TRAIN_PRE_EMPHASIS_MASK);
@@ -3515,9 +3500,9 @@ gen6_edp_signal_levels(uint8_t train_set)
 	}
 }
 
-/* Gen7's DP voltage swing and pre-emphasis control */
+/* IVB CPU eDP voltage swing and pre-emphasis control */
 static uint32_t
-gen7_edp_signal_levels(uint8_t train_set)
+ivb_cpu_edp_signal_levels(uint8_t train_set)
 {
 	int signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK |
 					 DP_TRAIN_PRE_EMPHASIS_MASK);
@@ -3564,14 +3549,14 @@ intel_dp_set_signal_levels(struct intel_dp *intel_dp)
 		signal_levels = chv_signal_levels(intel_dp);
 	} else if (IS_VALLEYVIEW(dev_priv)) {
 		signal_levels = vlv_signal_levels(intel_dp);
-	} else if (IS_GEN7(dev_priv) && port == PORT_A) {
-		signal_levels = gen7_edp_signal_levels(train_set);
+	} else if (IS_IVYBRIDGE(dev_priv) && port == PORT_A) {
+		signal_levels = ivb_cpu_edp_signal_levels(train_set);
 		mask = EDP_LINK_TRAIN_VOL_EMP_MASK_IVB;
 	} else if (IS_GEN6(dev_priv) && port == PORT_A) {
-		signal_levels = gen6_edp_signal_levels(train_set);
+		signal_levels = snb_cpu_edp_signal_levels(train_set);
 		mask = EDP_LINK_TRAIN_VOL_EMP_MASK_SNB;
 	} else {
-		signal_levels = gen4_signal_levels(train_set);
+		signal_levels = g4x_signal_levels(train_set);
 		mask = DP_VOLTAGE_MASK | DP_PRE_EMPHASIS_MASK;
 	}
 
@@ -3654,7 +3639,7 @@ intel_dp_link_down(struct intel_encoder *encoder,
 
 	DRM_DEBUG_KMS("\n");
 
-	if ((IS_GEN7(dev_priv) && port == PORT_A) ||
+	if ((IS_IVYBRIDGE(dev_priv) && port == PORT_A) ||
 	    (HAS_PCH_CPT(dev_priv) && port != PORT_A)) {
 		DP &= ~DP_LINK_TRAIN_MASK_CPT;
 		DP |= DP_LINK_TRAIN_PAT_IDLE_CPT;
@@ -3683,8 +3668,9 @@ intel_dp_link_down(struct intel_encoder *encoder,
 		intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, false);
 
 		/* always enable with pattern 1 (as per spec) */
-		DP &= ~(DP_PIPEB_SELECT | DP_LINK_TRAIN_MASK);
-		DP |= DP_PORT_EN | DP_LINK_TRAIN_PAT_1;
+		DP &= ~(DP_PIPE_SEL_MASK | DP_LINK_TRAIN_MASK);
+		DP |= DP_PORT_EN | DP_PIPE_SEL(PIPE_A) |
+			DP_LINK_TRAIN_PAT_1;
 		I915_WRITE(intel_dp->output_reg, DP);
 		POSTING_READ(intel_dp->output_reg);
 
@@ -3739,8 +3725,6 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp)
 		dev_priv->no_aux_handshake = intel_dp->dpcd[DP_MAX_DOWNSPREAD] &
 			DP_NO_AUX_HANDSHAKE_LINK_TRAINING;
 
-	intel_psr_init_dpcd(intel_dp);
-
 	/*
 	 * Read the eDP display control registers.
 	 *
@@ -3756,6 +3740,12 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp)
 		DRM_DEBUG_KMS("eDP DPCD: %*ph\n", (int) sizeof(intel_dp->edp_dpcd),
 			      intel_dp->edp_dpcd);
 
+	/*
+	 * This has to be called after intel_dp->edp_dpcd is filled, PSR checks
+	 * for SET_POWER_CAPABLE bit in intel_dp->edp_dpcd[1]
+	 */
+	intel_psr_init_dpcd(intel_dp);
+
 	/* Read the eDP 1.4+ supported link rates. */
 	if (intel_dp->edp_dpcd[0] >= DP_EDP_14) {
 		__le16 sink_rates[DP_MAX_SUPPORTED_RATES];
@@ -3884,129 +3874,6 @@ intel_dp_configure_mst(struct intel_dp *intel_dp)
 					intel_dp->is_mst);
 }
 
-static int intel_dp_sink_crc_stop(struct intel_dp *intel_dp,
-				  struct intel_crtc_state *crtc_state, bool disable_wa)
-{
-	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
-	u8 buf;
-	int ret = 0;
-	int count = 0;
-	int attempts = 10;
-
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK, &buf) < 0) {
-		DRM_DEBUG_KMS("Sink CRC couldn't be stopped properly\n");
-		ret = -EIO;
-		goto out;
-	}
-
-	if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_SINK,
-			       buf & ~DP_TEST_SINK_START) < 0) {
-		DRM_DEBUG_KMS("Sink CRC couldn't be stopped properly\n");
-		ret = -EIO;
-		goto out;
-	}
-
-	do {
-		intel_wait_for_vblank(dev_priv, intel_crtc->pipe);
-
-		if (drm_dp_dpcd_readb(&intel_dp->aux,
-				      DP_TEST_SINK_MISC, &buf) < 0) {
-			ret = -EIO;
-			goto out;
-		}
-		count = buf & DP_TEST_COUNT_MASK;
-	} while (--attempts && count);
-
-	if (attempts == 0) {
-		DRM_DEBUG_KMS("TIMEOUT: Sink CRC counter is not zeroed after calculation is stopped\n");
-		ret = -ETIMEDOUT;
-	}
-
- out:
-	if (disable_wa)
-		hsw_enable_ips(crtc_state);
-	return ret;
-}
-
-static int intel_dp_sink_crc_start(struct intel_dp *intel_dp,
-				   struct intel_crtc_state *crtc_state)
-{
-	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
-	u8 buf;
-	int ret;
-
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK_MISC, &buf) < 0)
-		return -EIO;
-
-	if (!(buf & DP_TEST_CRC_SUPPORTED))
-		return -ENOTTY;
-
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK, &buf) < 0)
-		return -EIO;
-
-	if (buf & DP_TEST_SINK_START) {
-		ret = intel_dp_sink_crc_stop(intel_dp, crtc_state, false);
-		if (ret)
-			return ret;
-	}
-
-	hsw_disable_ips(crtc_state);
-
-	if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_SINK,
-			       buf | DP_TEST_SINK_START) < 0) {
-		hsw_enable_ips(crtc_state);
-		return -EIO;
-	}
-
-	intel_wait_for_vblank(dev_priv, intel_crtc->pipe);
-	return 0;
-}
-
-int intel_dp_sink_crc(struct intel_dp *intel_dp, struct intel_crtc_state *crtc_state, u8 *crc)
-{
-	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
-	u8 buf;
-	int count, ret;
-	int attempts = 6;
-
-	ret = intel_dp_sink_crc_start(intel_dp, crtc_state);
-	if (ret)
-		return ret;
-
-	do {
-		intel_wait_for_vblank(dev_priv, intel_crtc->pipe);
-
-		if (drm_dp_dpcd_readb(&intel_dp->aux,
-				      DP_TEST_SINK_MISC, &buf) < 0) {
-			ret = -EIO;
-			goto stop;
-		}
-		count = buf & DP_TEST_COUNT_MASK;
-
-	} while (--attempts && count == 0);
-
-	if (attempts == 0) {
-		DRM_ERROR("Panel is unable to calculate any CRC after 6 vblanks\n");
-		ret = -ETIMEDOUT;
-		goto stop;
-	}
-
-	if (drm_dp_dpcd_read(&intel_dp->aux, DP_TEST_CRC_R_CR, crc, 6) < 0) {
-		ret = -EIO;
-		goto stop;
-	}
-
-stop:
-	intel_dp_sink_crc_stop(intel_dp, crtc_state, true);
-	return ret;
-}
-
 static bool
 intel_dp_get_sink_irq(struct intel_dp *intel_dp, u8 *sink_irq_vector)
 {
@@ -4466,10 +4333,15 @@ intel_dp_short_pulse(struct intel_dp *intel_dp)
 			DRM_DEBUG_DRIVER("CP or sink specific irq unhandled\n");
 	}
 
+	/* Handle CEC interrupts, if any */
+	drm_dp_cec_irq(&intel_dp->aux);
+
 	/* defer to the hotplug work for link retraining if needed */
 	if (intel_dp_needs_link_retrain(intel_dp))
 		return false;
 
+	intel_psr_short_pulse(intel_dp);
+
 	if (intel_dp->compliance.test_type == DP_TEST_LINK_TRAINING) {
 		DRM_DEBUG_KMS("Link Training Compliance Test requested\n");
 		/* Send a Hotplug Uevent to userspace to start modeset */
@@ -4537,14 +4409,7 @@ intel_dp_detect_dpcd(struct intel_dp *intel_dp)
 static enum drm_connector_status
 edp_detect(struct intel_dp *intel_dp)
 {
-	struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
-	enum drm_connector_status status;
-
-	status = intel_panel_detect(dev_priv);
-	if (status == connector_status_unknown)
-		status = connector_status_connected;
-
-	return status;
+	return connector_status_connected;
 }
 
 static bool ibx_digital_port_connected(struct intel_encoder *encoder)
@@ -4780,6 +4645,7 @@ intel_dp_set_edid(struct intel_dp *intel_dp)
 	intel_connector->detect_edid = edid;
 
 	intel_dp->has_audio = drm_detect_monitor_audio(edid);
+	drm_dp_cec_set_edid(&intel_dp->aux, edid);
 }
 
 static void
@@ -4787,6 +4653,7 @@ intel_dp_unset_edid(struct intel_dp *intel_dp)
 {
 	struct intel_connector *intel_connector = intel_dp->attached_connector;
 
+	drm_dp_cec_unset_edid(&intel_dp->aux);
 	kfree(intel_connector->detect_edid);
 	intel_connector->detect_edid = NULL;
 
@@ -4805,7 +4672,7 @@ intel_dp_long_pulse(struct intel_connector *connector)
 
 	intel_display_power_get(dev_priv, intel_dp->aux_power_domain);
 
-	/* Can't disconnect eDP, but you can close the lid... */
+	/* Can't disconnect eDP */
 	if (intel_dp_is_edp(intel_dp))
 		status = edp_detect(intel_dp);
 	else if (intel_digital_port_connected(&dp_to_dig_port(intel_dp)->base))
@@ -4975,6 +4842,7 @@ static int
 intel_dp_connector_register(struct drm_connector *connector)
 {
 	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct drm_device *dev = connector->dev;
 	int ret;
 
 	ret = intel_connector_register(connector);
@@ -4987,13 +4855,20 @@ intel_dp_connector_register(struct drm_connector *connector)
 		      intel_dp->aux.name, connector->kdev->kobj.name);
 
 	intel_dp->aux.dev = connector->kdev;
-	return drm_dp_aux_register(&intel_dp->aux);
+	ret = drm_dp_aux_register(&intel_dp->aux);
+	if (!ret)
+		drm_dp_cec_register_connector(&intel_dp->aux,
+					      connector->name, dev->dev);
+	return ret;
 }
 
 static void
 intel_dp_connector_unregister(struct drm_connector *connector)
 {
-	drm_dp_aux_unregister(&intel_attached_dp(connector)->aux);
+	struct intel_dp *intel_dp = intel_attached_dp(connector);
+
+	drm_dp_cec_unregister_connector(&intel_dp->aux);
+	drm_dp_aux_unregister(&intel_dp->aux);
 	intel_connector_unregister(connector);
 }
 
@@ -5319,14 +5194,14 @@ static void intel_edp_panel_vdd_sanitize(struct intel_dp *intel_dp)
 static enum pipe vlv_active_pipe(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	enum pipe pipe;
 
-	if ((intel_dp->DP & DP_PORT_EN) == 0)
-		return INVALID_PIPE;
+	if (intel_dp_port_enabled(dev_priv, intel_dp->output_reg,
+				  encoder->port, &pipe))
+		return pipe;
 
-	if (IS_CHERRYVIEW(dev_priv))
-		return DP_PORT_TO_PIPE_CHV(intel_dp->DP);
-	else
-		return PORT_TO_PIPE(intel_dp->DP);
+	return INVALID_PIPE;
 }
 
 void intel_dp_encoder_reset(struct drm_encoder *encoder)
@@ -5675,7 +5550,7 @@ intel_dp_init_panel_power_sequencer_registers(struct intel_dp *intel_dp,
 
 	/*
 	 * On some VLV machines the BIOS can leave the VDD
-	 * enabled even on power seqeuencers which aren't
+	 * enabled even on power sequencers which aren't
 	 * hooked up to any port. This would mess up the
 	 * power domain tracking the first time we pick
 	 * one of these power sequencers for use since
@@ -5683,7 +5558,7 @@ intel_dp_init_panel_power_sequencer_registers(struct intel_dp *intel_dp,
 	 * already on and therefore wouldn't grab the power
 	 * domain reference. Disable VDD first to avoid this.
 	 * This also avoids spuriously turning the VDD on as
-	 * soon as the new power seqeuencer gets initialized.
+	 * soon as the new power sequencer gets initialized.
 	 */
 	if (force_disable_vdd) {
 		u32 pp = ironlake_get_pp_control(intel_dp);
@@ -5721,10 +5596,20 @@ intel_dp_init_panel_power_sequencer_registers(struct intel_dp *intel_dp,
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		port_sel = PANEL_PORT_SELECT_VLV(port);
 	} else if (HAS_PCH_IBX(dev_priv) || HAS_PCH_CPT(dev_priv)) {
-		if (port == PORT_A)
+		switch (port) {
+		case PORT_A:
 			port_sel = PANEL_PORT_SELECT_DPA;
-		else
+			break;
+		case PORT_C:
+			port_sel = PANEL_PORT_SELECT_DPC;
+			break;
+		case PORT_D:
 			port_sel = PANEL_PORT_SELECT_DPD;
+			break;
+		default:
+			MISSING_CASE(port);
+			break;
+		}
 	}
 
 	pp_on |= port_sel;
@@ -6179,7 +6064,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	edid = drm_get_edid(connector, &intel_dp->aux.ddc);
 	if (edid) {
 		if (drm_add_edid_modes(connector, edid)) {
-			drm_mode_connector_update_edid_property(connector,
+			drm_connector_update_edid_property(connector,
 								edid);
 		} else {
 			kfree(edid);
@@ -6268,8 +6153,8 @@ static void intel_dp_modeset_retry_work_fn(struct work_struct *work)
 	/* Set connector link status to BAD and send a Uevent to notify
 	 * userspace to do a modeset.
 	 */
-	drm_mode_connector_set_link_status_property(connector,
-						    DRM_MODE_LINK_STATUS_BAD);
+	drm_connector_set_link_status_property(connector,
+					       DRM_MODE_LINK_STATUS_BAD);
 	mutex_unlock(&connector->dev->mode_config.mutex);
 	/* Send Hotplug uevent so userspace can reprobe */
 	drm_kms_helper_hotplug_event(connector->dev);
@@ -6382,7 +6267,7 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	 * 0xd.  Failure to do so will result in spurious interrupts being
 	 * generated on the port when a cable is not attached.
 	 */
-	if (IS_G4X(dev_priv) && !IS_GM45(dev_priv)) {
+	if (IS_G45(dev_priv)) {
 		u32 temp = I915_READ(PEG_BAND_GAP_DATA);
 		I915_WRITE(PEG_BAND_GAP_DATA, (temp & ~0xf) | 0xd);
 	}
@@ -6462,7 +6347,6 @@ bool intel_dp_init(struct drm_i915_private *dev_priv,
 	intel_encoder->port = port;
 
 	intel_dig_port->hpd_pulse = intel_dp_hpd_pulse;
-	dev_priv->hotplug.irq_port[port] = intel_dig_port;
 
 	if (port != PORT_A)
 		intel_infoframe_init(intel_dig_port);
@@ -6481,37 +6365,44 @@ err_connector_alloc:
 	return false;
 }
 
-void intel_dp_mst_suspend(struct drm_device *dev)
+void intel_dp_mst_suspend(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	int i;
+	struct intel_encoder *encoder;
 
-	/* disable MST */
-	for (i = 0; i < I915_MAX_PORTS; i++) {
-		struct intel_digital_port *intel_dig_port = dev_priv->hotplug.irq_port[i];
+	for_each_intel_encoder(&dev_priv->drm, encoder) {
+		struct intel_dp *intel_dp;
 
-		if (!intel_dig_port || !intel_dig_port->dp.can_mst)
+		if (encoder->type != INTEL_OUTPUT_DDI)
 			continue;
 
-		if (intel_dig_port->dp.is_mst)
-			drm_dp_mst_topology_mgr_suspend(&intel_dig_port->dp.mst_mgr);
+		intel_dp = enc_to_intel_dp(&encoder->base);
+
+		if (!intel_dp->can_mst)
+			continue;
+
+		if (intel_dp->is_mst)
+			drm_dp_mst_topology_mgr_suspend(&intel_dp->mst_mgr);
 	}
 }
 
-void intel_dp_mst_resume(struct drm_device *dev)
+void intel_dp_mst_resume(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	int i;
+	struct intel_encoder *encoder;
 
-	for (i = 0; i < I915_MAX_PORTS; i++) {
-		struct intel_digital_port *intel_dig_port = dev_priv->hotplug.irq_port[i];
+	for_each_intel_encoder(&dev_priv->drm, encoder) {
+		struct intel_dp *intel_dp;
 		int ret;
 
-		if (!intel_dig_port || !intel_dig_port->dp.can_mst)
+		if (encoder->type != INTEL_OUTPUT_DDI)
+			continue;
+
+		intel_dp = enc_to_intel_dp(&encoder->base);
+
+		if (!intel_dp->can_mst)
 			continue;
 
-		ret = drm_dp_mst_topology_mgr_resume(&intel_dig_port->dp.mst_mgr);
+		ret = drm_dp_mst_topology_mgr_resume(&intel_dp->mst_mgr);
 		if (ret)
-			intel_dp_check_mst_status(&intel_dig_port->dp);
+			intel_dp_check_mst_status(intel_dp);
 	}
 }
diff --git a/drivers/gpu/drm/i915/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/intel_dp_aux_backlight.c
index 2bb2ceb9d463..357136f17f85 100644
--- a/drivers/gpu/drm/i915/intel_dp_aux_backlight.c
+++ b/drivers/gpu/drm/i915/intel_dp_aux_backlight.c
@@ -26,7 +26,7 @@
 
 static void set_aux_backlight_enable(struct intel_dp *intel_dp, bool enable)
 {
-	uint8_t reg_val = 0;
+	u8 reg_val = 0;
 
 	/* Early return when display use other mechanism to enable backlight. */
 	if (!(intel_dp->edp_dpcd[1] & DP_EDP_BACKLIGHT_AUX_ENABLE_CAP))
@@ -54,11 +54,11 @@ static void set_aux_backlight_enable(struct intel_dp *intel_dp, bool enable)
  * Read the current backlight value from DPCD register(s) based
  * on if 8-bit(MSB) or 16-bit(MSB and LSB) values are supported
  */
-static uint32_t intel_dp_aux_get_backlight(struct intel_connector *connector)
+static u32 intel_dp_aux_get_backlight(struct intel_connector *connector)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
-	uint8_t read_val[2] = { 0x0 };
-	uint16_t level = 0;
+	u8 read_val[2] = { 0x0 };
+	u16 level = 0;
 
 	if (drm_dp_dpcd_read(&intel_dp->aux, DP_EDP_BACKLIGHT_BRIGHTNESS_MSB,
 			     &read_val, sizeof(read_val)) < 0) {
@@ -82,7 +82,7 @@ intel_dp_aux_set_backlight(const struct drm_connector_state *conn_state, u32 lev
 {
 	struct intel_connector *connector = to_intel_connector(conn_state->connector);
 	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
-	uint8_t vals[2] = { 0x0 };
+	u8 vals[2] = { 0x0 };
 
 	vals[0] = level;
 
@@ -178,7 +178,7 @@ static void intel_dp_aux_enable_backlight(const struct intel_crtc_state *crtc_st
 {
 	struct intel_connector *connector = to_intel_connector(conn_state->connector);
 	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
-	uint8_t dpcd_buf, new_dpcd_buf, edp_backlight_mode;
+	u8 dpcd_buf, new_dpcd_buf, edp_backlight_mode;
 
 	if (drm_dp_dpcd_readb(&intel_dp->aux,
 			DP_EDP_BACKLIGHT_MODE_SET_REGISTER, &dpcd_buf) != 1) {
diff --git a/drivers/gpu/drm/i915/intel_dp_link_training.c b/drivers/gpu/drm/i915/intel_dp_link_training.c
index 3fcaa98b9055..4da6e33c7fa1 100644
--- a/drivers/gpu/drm/i915/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/intel_dp_link_training.c
@@ -219,32 +219,47 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp)
 }
 
 /*
- * Pick training pattern for channel equalization. Training Pattern 3 for HBR2
+ * Pick training pattern for channel equalization. Training pattern 4 for HBR3
+ * or for 1.4 devices that support it, training Pattern 3 for HBR2
  * or 1.2 devices that support it, Training Pattern 2 otherwise.
  */
 static u32 intel_dp_training_pattern(struct intel_dp *intel_dp)
 {
-	u32 training_pattern = DP_TRAINING_PATTERN_2;
-	bool source_tps3, sink_tps3;
+	bool source_tps3, sink_tps3, source_tps4, sink_tps4;
 
 	/*
+	 * Intel platforms that support HBR3 also support TPS4. It is mandatory
+	 * for all downstream devices that support HBR3. There are no known eDP
+	 * panels that support TPS4 as of Feb 2018 as per VESA eDP_v1.4b_E1
+	 * specification.
+	 */
+	source_tps4 = intel_dp_source_supports_hbr3(intel_dp);
+	sink_tps4 = drm_dp_tps4_supported(intel_dp->dpcd);
+	if (source_tps4 && sink_tps4) {
+		return DP_TRAINING_PATTERN_4;
+	} else if (intel_dp->link_rate == 810000) {
+		if (!source_tps4)
+			DRM_DEBUG_KMS("8.1 Gbps link rate without source HBR3/TPS4 support\n");
+		if (!sink_tps4)
+			DRM_DEBUG_KMS("8.1 Gbps link rate without sink TPS4 support\n");
+	}
+	/*
 	 * Intel platforms that support HBR2 also support TPS3. TPS3 support is
 	 * also mandatory for downstream devices that support HBR2. However, not
 	 * all sinks follow the spec.
 	 */
 	source_tps3 = intel_dp_source_supports_hbr2(intel_dp);
 	sink_tps3 = drm_dp_tps3_supported(intel_dp->dpcd);
-
 	if (source_tps3 && sink_tps3) {
-		training_pattern = DP_TRAINING_PATTERN_3;
-	} else if (intel_dp->link_rate == 540000) {
+		return  DP_TRAINING_PATTERN_3;
+	} else if (intel_dp->link_rate >= 540000) {
 		if (!source_tps3)
-			DRM_DEBUG_KMS("5.4 Gbps link rate without source HBR2/TPS3 support\n");
+			DRM_DEBUG_KMS(">=5.4/6.48 Gbps link rate without source HBR2/TPS3 support\n");
 		if (!sink_tps3)
-			DRM_DEBUG_KMS("5.4 Gbps link rate without sink TPS3 support\n");
+			DRM_DEBUG_KMS(">=5.4/6.48 Gbps link rate without sink TPS3 support\n");
 	}
 
-	return training_pattern;
+	return DP_TRAINING_PATTERN_2;
 }
 
 static bool
@@ -256,11 +271,13 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp)
 	bool channel_eq = false;
 
 	training_pattern = intel_dp_training_pattern(intel_dp);
+	/* Scrambling is disabled for TPS2/3 and enabled for TPS4 */
+	if (training_pattern != DP_TRAINING_PATTERN_4)
+		training_pattern |= DP_LINK_SCRAMBLING_DISABLE;
 
 	/* channel equalization */
 	if (!intel_dp_set_link_train(intel_dp,
-				     training_pattern |
-				     DP_LINK_SCRAMBLING_DISABLE)) {
+				     training_pattern)) {
 		DRM_ERROR("failed to start channel equalization\n");
 		return false;
 	}
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index 5890500a3a8b..7e3e01607643 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -403,20 +403,10 @@ static struct drm_encoder *intel_mst_atomic_best_encoder(struct drm_connector *c
 	return &intel_dp->mst_encoders[crtc->pipe]->base.base;
 }
 
-static struct drm_encoder *intel_mst_best_encoder(struct drm_connector *connector)
-{
-	struct intel_connector *intel_connector = to_intel_connector(connector);
-	struct intel_dp *intel_dp = intel_connector->mst_port;
-	if (!intel_dp)
-		return NULL;
-	return &intel_dp->mst_encoders[0]->base.base;
-}
-
 static const struct drm_connector_helper_funcs intel_dp_mst_connector_helper_funcs = {
 	.get_modes = intel_dp_mst_get_modes,
 	.mode_valid = intel_dp_mst_mode_valid,
 	.atomic_best_encoder = intel_mst_atomic_best_encoder,
-	.best_encoder = intel_mst_best_encoder,
 	.atomic_check = intel_dp_mst_atomic_check,
 };
 
@@ -476,8 +466,7 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
 		struct drm_encoder *enc =
 			&intel_dp->mst_encoders[pipe]->base.base;
 
-		ret = drm_mode_connector_attach_encoder(&intel_connector->base,
-							enc);
+		ret = drm_connector_attach_encoder(&intel_connector->base, enc);
 		if (ret)
 			goto err;
 	}
@@ -485,7 +474,7 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
 	drm_object_attach_property(&connector->base, dev->mode_config.path_property, 0);
 	drm_object_attach_property(&connector->base, dev->mode_config.tile_property, 0);
 
-	ret = drm_mode_connector_set_path_property(connector, pathprop);
+	ret = drm_connector_set_path_property(connector, pathprop);
 	if (ret)
 		goto err;
 
@@ -524,7 +513,7 @@ static void intel_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 	intel_connector->mst_port = NULL;
 	drm_modeset_unlock(&connector->dev->mode_config.connection_mutex);
 
-	drm_connector_unreference(connector);
+	drm_connector_put(connector);
 }
 
 static void intel_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr)
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index 383fbc15113d..b51ad2917dbe 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -163,8 +163,8 @@ void intel_enable_shared_dpll(struct intel_crtc *crtc)
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_shared_dpll *pll = crtc->config->shared_dpll;
-	unsigned crtc_mask = 1 << drm_crtc_index(&crtc->base);
-	unsigned old_mask;
+	unsigned int crtc_mask = drm_crtc_mask(&crtc->base);
+	unsigned int old_mask;
 
 	if (WARN_ON(pll == NULL))
 		return;
@@ -207,7 +207,7 @@ void intel_disable_shared_dpll(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_shared_dpll *pll = crtc->config->shared_dpll;
-	unsigned crtc_mask = 1 << drm_crtc_index(&crtc->base);
+	unsigned int crtc_mask = drm_crtc_mask(&crtc->base);
 
 	/* PCH only available on ILK+ */
 	if (INTEL_GEN(dev_priv) < 5)
@@ -2525,6 +2525,77 @@ static bool icl_calc_dpll_state(struct intel_crtc_state *crtc_state,
 	return true;
 }
 
+int icl_calc_dp_combo_pll_link(struct drm_i915_private *dev_priv,
+			       uint32_t pll_id)
+{
+	uint32_t cfgcr0, cfgcr1;
+	uint32_t pdiv, kdiv, qdiv_mode, qdiv_ratio, dco_integer, dco_fraction;
+	const struct skl_wrpll_params *params;
+	int index, n_entries, link_clock;
+
+	/* Read back values from DPLL CFGCR registers */
+	cfgcr0 = I915_READ(ICL_DPLL_CFGCR0(pll_id));
+	cfgcr1 = I915_READ(ICL_DPLL_CFGCR1(pll_id));
+
+	dco_integer = cfgcr0 & DPLL_CFGCR0_DCO_INTEGER_MASK;
+	dco_fraction = (cfgcr0 & DPLL_CFGCR0_DCO_FRACTION_MASK) >>
+		DPLL_CFGCR0_DCO_FRACTION_SHIFT;
+	pdiv = (cfgcr1 & DPLL_CFGCR1_PDIV_MASK) >> DPLL_CFGCR1_PDIV_SHIFT;
+	kdiv = (cfgcr1 & DPLL_CFGCR1_KDIV_MASK) >> DPLL_CFGCR1_KDIV_SHIFT;
+	qdiv_mode = (cfgcr1 & DPLL_CFGCR1_QDIV_MODE(1)) >>
+		DPLL_CFGCR1_QDIV_MODE_SHIFT;
+	qdiv_ratio = (cfgcr1 & DPLL_CFGCR1_QDIV_RATIO_MASK) >>
+		DPLL_CFGCR1_QDIV_RATIO_SHIFT;
+
+	params = dev_priv->cdclk.hw.ref == 24000 ?
+		icl_dp_combo_pll_24MHz_values :
+		icl_dp_combo_pll_19_2MHz_values;
+	n_entries = ARRAY_SIZE(icl_dp_combo_pll_24MHz_values);
+
+	for (index = 0; index < n_entries; index++) {
+		if (dco_integer == params[index].dco_integer &&
+		    dco_fraction == params[index].dco_fraction &&
+		    pdiv == params[index].pdiv &&
+		    kdiv == params[index].kdiv &&
+		    qdiv_mode == params[index].qdiv_mode &&
+		    qdiv_ratio == params[index].qdiv_ratio)
+			break;
+	}
+
+	/* Map PLL Index to Link Clock */
+	switch (index) {
+	default:
+		MISSING_CASE(index);
+		/* fall through */
+	case 0:
+		link_clock = 540000;
+		break;
+	case 1:
+		link_clock = 270000;
+		break;
+	case 2:
+		link_clock = 162000;
+		break;
+	case 3:
+		link_clock = 324000;
+		break;
+	case 4:
+		link_clock = 216000;
+		break;
+	case 5:
+		link_clock = 432000;
+		break;
+	case 6:
+		link_clock = 648000;
+		break;
+	case 7:
+		link_clock = 810000;
+		break;
+	}
+
+	return link_clock;
+}
+
 static enum port icl_mg_pll_id_to_port(enum intel_dpll_id id)
 {
 	return id - DPLL_ID_ICL_MGPLL1 + PORT_C;
@@ -2569,6 +2640,7 @@ static bool icl_mg_pll_find_divisors(int clock_khz, bool is_dp, bool use_ssc,
 			switch (div1) {
 			default:
 				MISSING_CASE(div1);
+				/* fall through */
 			case 2:
 				hsdiv = 0;
 				break;
@@ -2742,25 +2814,31 @@ static bool icl_calc_mg_pll_state(struct intel_crtc_state *crtc_state,
 				MG_PLL_SSC_FLLEN |
 				MG_PLL_SSC_STEPSIZE(ssc_stepsize);
 
-	pll_state->mg_pll_tdc_coldst_bias = MG_PLL_TDC_COLDST_COLDSTART;
-
-	if (refclk_khz != 38400) {
-		pll_state->mg_pll_tdc_coldst_bias |=
-			MG_PLL_TDC_COLDST_IREFINT_EN |
-			MG_PLL_TDC_COLDST_REFBIAS_START_PULSE_W(iref_pulse_w) |
-			MG_PLL_TDC_COLDST_COLDSTART |
-			MG_PLL_TDC_TDCOVCCORR_EN |
-			MG_PLL_TDC_TDCSEL(3);
-
-		pll_state->mg_pll_bias = MG_PLL_BIAS_BIAS_GB_SEL(3) |
-					 MG_PLL_BIAS_INIT_DCOAMP(0x3F) |
-					 MG_PLL_BIAS_BIAS_BONUS(10) |
-					 MG_PLL_BIAS_BIASCAL_EN |
-					 MG_PLL_BIAS_CTRIM(12) |
-					 MG_PLL_BIAS_VREF_RDAC(4) |
-					 MG_PLL_BIAS_IREFTRIM(iref_trim);
+	pll_state->mg_pll_tdc_coldst_bias = MG_PLL_TDC_COLDST_COLDSTART |
+					    MG_PLL_TDC_COLDST_IREFINT_EN |
+					    MG_PLL_TDC_COLDST_REFBIAS_START_PULSE_W(iref_pulse_w) |
+					    MG_PLL_TDC_TDCOVCCORR_EN |
+					    MG_PLL_TDC_TDCSEL(3);
+
+	pll_state->mg_pll_bias = MG_PLL_BIAS_BIAS_GB_SEL(3) |
+				 MG_PLL_BIAS_INIT_DCOAMP(0x3F) |
+				 MG_PLL_BIAS_BIAS_BONUS(10) |
+				 MG_PLL_BIAS_BIASCAL_EN |
+				 MG_PLL_BIAS_CTRIM(12) |
+				 MG_PLL_BIAS_VREF_RDAC(4) |
+				 MG_PLL_BIAS_IREFTRIM(iref_trim);
+
+	if (refclk_khz == 38400) {
+		pll_state->mg_pll_tdc_coldst_bias_mask = MG_PLL_TDC_COLDST_COLDSTART;
+		pll_state->mg_pll_bias_mask = 0;
+	} else {
+		pll_state->mg_pll_tdc_coldst_bias_mask = -1U;
+		pll_state->mg_pll_bias_mask = -1U;
 	}
 
+	pll_state->mg_pll_tdc_coldst_bias &= pll_state->mg_pll_tdc_coldst_bias_mask;
+	pll_state->mg_pll_bias &= pll_state->mg_pll_bias_mask;
+
 	return true;
 }
 
@@ -2787,10 +2865,17 @@ icl_get_dpll(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state,
 	case PORT_D:
 	case PORT_E:
 	case PORT_F:
-		min = icl_port_to_mg_pll_id(port);
-		max = min;
-		ret = icl_calc_mg_pll_state(crtc_state, encoder, clock,
-					    &pll_state);
+		if (0 /* TODO: TBT PLLs */) {
+			min = DPLL_ID_ICL_TBTPLL;
+			max = min;
+			ret = icl_calc_dpll_state(crtc_state, encoder, clock,
+						  &pll_state);
+		} else {
+			min = icl_port_to_mg_pll_id(port);
+			max = min;
+			ret = icl_calc_mg_pll_state(crtc_state, encoder, clock,
+						    &pll_state);
+		}
 		break;
 	default:
 		MISSING_CASE(port);
@@ -2820,9 +2905,12 @@ static i915_reg_t icl_pll_id_to_enable_reg(enum intel_dpll_id id)
 	switch (id) {
 	default:
 		MISSING_CASE(id);
+		/* fall through */
 	case DPLL_ID_ICL_DPLL0:
 	case DPLL_ID_ICL_DPLL1:
 		return CNL_DPLL_ENABLE(id);
+	case DPLL_ID_ICL_TBTPLL:
+		return TBT_PLL_ENABLE;
 	case DPLL_ID_ICL_MGPLL1:
 	case DPLL_ID_ICL_MGPLL2:
 	case DPLL_ID_ICL_MGPLL3:
@@ -2850,6 +2938,7 @@ static bool icl_pll_get_hw_state(struct drm_i915_private *dev_priv,
 	switch (id) {
 	case DPLL_ID_ICL_DPLL0:
 	case DPLL_ID_ICL_DPLL1:
+	case DPLL_ID_ICL_TBTPLL:
 		hw_state->cfgcr0 = I915_READ(ICL_DPLL_CFGCR0(id));
 		hw_state->cfgcr1 = I915_READ(ICL_DPLL_CFGCR1(id));
 		break;
@@ -2859,18 +2948,41 @@ static bool icl_pll_get_hw_state(struct drm_i915_private *dev_priv,
 	case DPLL_ID_ICL_MGPLL4:
 		port = icl_mg_pll_id_to_port(id);
 		hw_state->mg_refclkin_ctl = I915_READ(MG_REFCLKIN_CTL(port));
+		hw_state->mg_refclkin_ctl &= MG_REFCLKIN_CTL_OD_2_MUX_MASK;
+
 		hw_state->mg_clktop2_coreclkctl1 =
 			I915_READ(MG_CLKTOP2_CORECLKCTL1(port));
+		hw_state->mg_clktop2_coreclkctl1 &=
+			MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK;
+
 		hw_state->mg_clktop2_hsclkctl =
 			I915_READ(MG_CLKTOP2_HSCLKCTL(port));
+		hw_state->mg_clktop2_hsclkctl &=
+			MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL_MASK |
+			MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL_MASK |
+			MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO_MASK |
+			MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO_MASK;
+
 		hw_state->mg_pll_div0 = I915_READ(MG_PLL_DIV0(port));
 		hw_state->mg_pll_div1 = I915_READ(MG_PLL_DIV1(port));
 		hw_state->mg_pll_lf = I915_READ(MG_PLL_LF(port));
 		hw_state->mg_pll_frac_lock = I915_READ(MG_PLL_FRAC_LOCK(port));
 		hw_state->mg_pll_ssc = I915_READ(MG_PLL_SSC(port));
+
 		hw_state->mg_pll_bias = I915_READ(MG_PLL_BIAS(port));
 		hw_state->mg_pll_tdc_coldst_bias =
 			I915_READ(MG_PLL_TDC_COLDST_BIAS(port));
+
+		if (dev_priv->cdclk.hw.ref == 38400) {
+			hw_state->mg_pll_tdc_coldst_bias_mask = MG_PLL_TDC_COLDST_COLDSTART;
+			hw_state->mg_pll_bias_mask = 0;
+		} else {
+			hw_state->mg_pll_tdc_coldst_bias_mask = -1U;
+			hw_state->mg_pll_bias_mask = -1U;
+		}
+
+		hw_state->mg_pll_tdc_coldst_bias &= hw_state->mg_pll_tdc_coldst_bias_mask;
+		hw_state->mg_pll_bias &= hw_state->mg_pll_bias_mask;
 		break;
 	default:
 		MISSING_CASE(id);
@@ -2898,19 +3010,48 @@ static void icl_mg_pll_write(struct drm_i915_private *dev_priv,
 {
 	struct intel_dpll_hw_state *hw_state = &pll->state.hw_state;
 	enum port port = icl_mg_pll_id_to_port(pll->info->id);
+	u32 val;
+
+	/*
+	 * Some of the following registers have reserved fields, so program
+	 * these with RMW based on a mask. The mask can be fixed or generated
+	 * during the calc/readout phase if the mask depends on some other HW
+	 * state like refclk, see icl_calc_mg_pll_state().
+	 */
+	val = I915_READ(MG_REFCLKIN_CTL(port));
+	val &= ~MG_REFCLKIN_CTL_OD_2_MUX_MASK;
+	val |= hw_state->mg_refclkin_ctl;
+	I915_WRITE(MG_REFCLKIN_CTL(port), val);
+
+	val = I915_READ(MG_CLKTOP2_CORECLKCTL1(port));
+	val &= ~MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK;
+	val |= hw_state->mg_clktop2_coreclkctl1;
+	I915_WRITE(MG_CLKTOP2_CORECLKCTL1(port), val);
+
+	val = I915_READ(MG_CLKTOP2_HSCLKCTL(port));
+	val &= ~(MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL_MASK |
+		 MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL_MASK |
+		 MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO_MASK |
+		 MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO_MASK);
+	val |= hw_state->mg_clktop2_hsclkctl;
+	I915_WRITE(MG_CLKTOP2_HSCLKCTL(port), val);
 
-	I915_WRITE(MG_REFCLKIN_CTL(port), hw_state->mg_refclkin_ctl);
-	I915_WRITE(MG_CLKTOP2_CORECLKCTL1(port),
-		   hw_state->mg_clktop2_coreclkctl1);
-	I915_WRITE(MG_CLKTOP2_HSCLKCTL(port), hw_state->mg_clktop2_hsclkctl);
 	I915_WRITE(MG_PLL_DIV0(port), hw_state->mg_pll_div0);
 	I915_WRITE(MG_PLL_DIV1(port), hw_state->mg_pll_div1);
 	I915_WRITE(MG_PLL_LF(port), hw_state->mg_pll_lf);
 	I915_WRITE(MG_PLL_FRAC_LOCK(port), hw_state->mg_pll_frac_lock);
 	I915_WRITE(MG_PLL_SSC(port), hw_state->mg_pll_ssc);
-	I915_WRITE(MG_PLL_BIAS(port), hw_state->mg_pll_bias);
-	I915_WRITE(MG_PLL_TDC_COLDST_BIAS(port),
-		   hw_state->mg_pll_tdc_coldst_bias);
+
+	val = I915_READ(MG_PLL_BIAS(port));
+	val &= ~hw_state->mg_pll_bias_mask;
+	val |= hw_state->mg_pll_bias;
+	I915_WRITE(MG_PLL_BIAS(port), val);
+
+	val = I915_READ(MG_PLL_TDC_COLDST_BIAS(port));
+	val &= ~hw_state->mg_pll_tdc_coldst_bias_mask;
+	val |= hw_state->mg_pll_tdc_coldst_bias;
+	I915_WRITE(MG_PLL_TDC_COLDST_BIAS(port), val);
+
 	POSTING_READ(MG_PLL_TDC_COLDST_BIAS(port));
 }
 
@@ -2936,6 +3077,7 @@ static void icl_pll_enable(struct drm_i915_private *dev_priv,
 	switch (id) {
 	case DPLL_ID_ICL_DPLL0:
 	case DPLL_ID_ICL_DPLL1:
+	case DPLL_ID_ICL_TBTPLL:
 		icl_dpll_write(dev_priv, pll);
 		break;
 	case DPLL_ID_ICL_MGPLL1:
@@ -3034,6 +3176,7 @@ static const struct intel_shared_dpll_funcs icl_pll_funcs = {
 static const struct dpll_info icl_plls[] = {
 	{ "DPLL 0",   &icl_pll_funcs, DPLL_ID_ICL_DPLL0,  0 },
 	{ "DPLL 1",   &icl_pll_funcs, DPLL_ID_ICL_DPLL1,  0 },
+	{ "TBT PLL",  &icl_pll_funcs, DPLL_ID_ICL_TBTPLL, 0 },
 	{ "MG PLL 1", &icl_pll_funcs, DPLL_ID_ICL_MGPLL1, 0 },
 	{ "MG PLL 2", &icl_pll_funcs, DPLL_ID_ICL_MGPLL2, 0 },
 	{ "MG PLL 3", &icl_pll_funcs, DPLL_ID_ICL_MGPLL3, 0 },
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.h b/drivers/gpu/drm/i915/intel_dpll_mgr.h
index 7a0cd564a9ee..7e522cf4f13f 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.h
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.h
@@ -114,23 +114,27 @@ enum intel_dpll_id {
 	 */
 	DPLL_ID_ICL_DPLL1 = 1,
 	/**
+	 * @DPLL_ID_ICL_TBTPLL: ICL TBT PLL
+	 */
+	DPLL_ID_ICL_TBTPLL = 2,
+	/**
 	 * @DPLL_ID_ICL_MGPLL1: ICL MG PLL 1 port 1 (C)
 	 */
-	DPLL_ID_ICL_MGPLL1 = 2,
+	DPLL_ID_ICL_MGPLL1 = 3,
 	/**
 	 * @DPLL_ID_ICL_MGPLL2: ICL MG PLL 1 port 2 (D)
 	 */
-	DPLL_ID_ICL_MGPLL2 = 3,
+	DPLL_ID_ICL_MGPLL2 = 4,
 	/**
 	 * @DPLL_ID_ICL_MGPLL3: ICL MG PLL 1 port 3 (E)
 	 */
-	DPLL_ID_ICL_MGPLL3 = 4,
+	DPLL_ID_ICL_MGPLL3 = 5,
 	/**
 	 * @DPLL_ID_ICL_MGPLL4: ICL MG PLL 1 port 4 (F)
 	 */
-	DPLL_ID_ICL_MGPLL4 = 5,
+	DPLL_ID_ICL_MGPLL4 = 6,
 };
-#define I915_NUM_PLLS 6
+#define I915_NUM_PLLS 7
 
 struct intel_dpll_hw_state {
 	/* i9xx, pch plls */
@@ -176,6 +180,8 @@ struct intel_dpll_hw_state {
 	uint32_t mg_pll_ssc;
 	uint32_t mg_pll_bias;
 	uint32_t mg_pll_tdc_coldst_bias;
+	uint32_t mg_pll_bias_mask;
+	uint32_t mg_pll_tdc_coldst_bias_mask;
 };
 
 /**
@@ -336,5 +342,7 @@ void intel_shared_dpll_init(struct drm_device *dev);
 
 void intel_dpll_dump_hw_state(struct drm_i915_private *dev_priv,
 			      struct intel_dpll_hw_state *hw_state);
+int icl_calc_dp_combo_pll_link(struct drm_i915_private *dev_priv,
+			       uint32_t pll_id);
 
 #endif /* _INTEL_DPLL_MGR_H_ */
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index b8eefbffc77d..17af06d8a43e 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -158,12 +158,6 @@
 #define MAX_OUTPUTS 6
 /* maximum connectors per crtcs in the mode set */
 
-/* Maximum cursor sizes */
-#define GEN2_CURSOR_WIDTH 64
-#define GEN2_CURSOR_HEIGHT 64
-#define MAX_CURSOR_WIDTH 256
-#define MAX_CURSOR_HEIGHT 256
-
 #define INTEL_I2C_BUS_DVO 1
 #define INTEL_I2C_BUS_SDVO 2
 
@@ -194,7 +188,6 @@ enum intel_output_type {
 
 struct intel_framebuffer {
 	struct drm_framebuffer base;
-	struct drm_i915_gem_object *obj;
 	struct intel_rotation_info rot_info;
 
 	/* for each plane in the normal GTT view */
@@ -261,7 +254,8 @@ struct intel_encoder {
 			   struct intel_crtc_state *pipe_config);
 	/* Returns a mask of power domains that need to be referenced as part
 	 * of the hardware state readout code. */
-	u64 (*get_power_domains)(struct intel_encoder *encoder);
+	u64 (*get_power_domains)(struct intel_encoder *encoder,
+				 struct intel_crtc_state *crtc_state);
 	/*
 	 * Called during system suspend after all pending requests for the
 	 * encoder are flushed (for example for DP AUX transactions) and
@@ -310,6 +304,8 @@ struct intel_panel {
 	} backlight;
 };
 
+struct intel_digital_port;
+
 /*
  * This structure serves as a translation layer between the generic HDCP code
  * and the bus-specific code. What that means is that HDCP over HDMI differs
@@ -488,6 +484,8 @@ struct intel_atomic_state {
 	 */
 	bool skip_intermediate_wm;
 
+	bool rps_interactive;
+
 	/* Gen9+ only */
 	struct skl_ddb_values wm_results;
 
@@ -953,6 +951,7 @@ struct intel_plane {
 	enum pipe pipe;
 	bool can_scale;
 	bool has_fbc;
+	bool has_ccs;
 	int max_downscale;
 	uint32_t frontbuffer_bit;
 
@@ -971,7 +970,7 @@ struct intel_plane {
 			     const struct intel_plane_state *plane_state);
 	void (*disable_plane)(struct intel_plane *plane,
 			      struct intel_crtc *crtc);
-	bool (*get_hw_state)(struct intel_plane *plane);
+	bool (*get_hw_state)(struct intel_plane *plane, enum pipe *pipe);
 	int (*check_plane)(struct intel_plane *plane,
 			   struct intel_crtc_state *crtc_state,
 			   struct intel_plane_state *state);
@@ -1004,7 +1003,7 @@ struct cxsr_latency {
 #define to_intel_framebuffer(x) container_of(x, struct intel_framebuffer, base)
 #define to_intel_plane(x) container_of(x, struct intel_plane, base)
 #define to_intel_plane_state(x) container_of(x, struct intel_plane_state, base)
-#define intel_fb_obj(x) (x ? to_intel_framebuffer(x)->obj : NULL)
+#define intel_fb_obj(x) ((x) ? to_intel_bo((x)->obj[0]) : NULL)
 
 struct intel_hdmi {
 	i915_reg_t hdmi_reg;
@@ -1139,7 +1138,6 @@ struct intel_dp {
 	 * register with to kick off an AUX transaction.
 	 */
 	uint32_t (*get_aux_send_ctl)(struct intel_dp *dp,
-				     bool has_aux_irq,
 				     int send_bytes,
 				     uint32_t aux_clock_divider);
 
@@ -1252,22 +1250,29 @@ intel_attached_encoder(struct drm_connector *connector)
 	return to_intel_connector(connector)->encoder;
 }
 
-static inline struct intel_digital_port *
-enc_to_dig_port(struct drm_encoder *encoder)
+static inline bool intel_encoder_is_dig_port(struct intel_encoder *encoder)
 {
-	struct intel_encoder *intel_encoder = to_intel_encoder(encoder);
-
-	switch (intel_encoder->type) {
+	switch (encoder->type) {
 	case INTEL_OUTPUT_DDI:
-		WARN_ON(!HAS_DDI(to_i915(encoder->dev)));
 	case INTEL_OUTPUT_DP:
 	case INTEL_OUTPUT_EDP:
 	case INTEL_OUTPUT_HDMI:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static inline struct intel_digital_port *
+enc_to_dig_port(struct drm_encoder *encoder)
+{
+	struct intel_encoder *intel_encoder = to_intel_encoder(encoder);
+
+	if (intel_encoder_is_dig_port(intel_encoder))
 		return container_of(encoder, struct intel_digital_port,
 				    base.base);
-	default:
+	else
 		return NULL;
-	}
 }
 
 static inline struct intel_dp_mst_encoder *
@@ -1281,6 +1286,20 @@ static inline struct intel_dp *enc_to_intel_dp(struct drm_encoder *encoder)
 	return &enc_to_dig_port(encoder)->dp;
 }
 
+static inline bool intel_encoder_is_dp(struct intel_encoder *encoder)
+{
+	switch (encoder->type) {
+	case INTEL_OUTPUT_DP:
+	case INTEL_OUTPUT_EDP:
+		return true;
+	case INTEL_OUTPUT_DDI:
+		/* Skip pure HDMI/DVI DDI encoders */
+		return i915_mmio_reg_valid(enc_to_intel_dp(&encoder->base)->output_reg);
+	default:
+		return false;
+	}
+}
+
 static inline struct intel_digital_port *
 dp_to_dig_port(struct intel_dp *intel_dp)
 {
@@ -1337,9 +1356,6 @@ void intel_check_cpu_fifo_underruns(struct drm_i915_private *dev_priv);
 void intel_check_pch_fifo_underruns(struct drm_i915_private *dev_priv);
 
 /* i915_irq.c */
-bool gen11_reset_one_iir(struct drm_i915_private * const i915,
-			 const unsigned int bank,
-			 const unsigned int bit);
 void gen5_enable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 void gen5_disable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 void gen6_mask_pm_irq(struct drm_i915_private *dev_priv, u32 mask);
@@ -1376,6 +1392,8 @@ void gen9_enable_guc_interrupts(struct drm_i915_private *dev_priv);
 void gen9_disable_guc_interrupts(struct drm_i915_private *dev_priv);
 
 /* intel_crt.c */
+bool intel_crt_port_enabled(struct drm_i915_private *dev_priv,
+			    i915_reg_t adpa_reg, enum pipe *pipe);
 void intel_crt_init(struct drm_i915_private *dev_priv);
 void intel_crt_reset(struct drm_encoder *encoder);
 
@@ -1391,8 +1409,6 @@ void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state)
 void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state);
 void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state);
 void intel_ddi_disable_pipe_clock(const  struct intel_crtc_state *crtc_state);
-struct intel_encoder *
-intel_ddi_get_crtc_new_encoder(struct intel_crtc_state *crtc_state);
 void intel_ddi_set_pipe_settings(const struct intel_crtc_state *crtc_state);
 void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp);
 bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector);
@@ -1406,6 +1422,8 @@ void intel_ddi_compute_min_voltage_level(struct drm_i915_private *dev_priv,
 u32 bxt_signal_levels(struct intel_dp *intel_dp);
 uint32_t ddi_signal_levels(struct intel_dp *intel_dp);
 u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder);
+u8 intel_ddi_dp_pre_emphasis_max(struct intel_encoder *encoder,
+				 u8 voltage_swing);
 int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder,
 				     bool enable);
 void icl_map_plls_to_ports(struct drm_crtc *crtc,
@@ -1487,6 +1505,9 @@ void intel_connector_attach_encoder(struct intel_connector *connector,
 				    struct intel_encoder *encoder);
 struct drm_display_mode *
 intel_encoder_current_mode(struct intel_encoder *encoder);
+bool intel_port_is_tc(struct drm_i915_private *dev_priv, enum port port);
+enum tc_port intel_port_to_tc(struct drm_i915_private *dev_priv,
+			      enum port port);
 
 enum pipe intel_get_pipe_from_connector(struct intel_connector *connector);
 int intel_get_pipe_from_crtc_id_ioctl(struct drm_device *dev, void *data,
@@ -1614,6 +1635,7 @@ void intel_mode_from_pipe_config(struct drm_display_mode *mode,
 void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc,
 				  struct intel_crtc_state *crtc_state);
 
+u16 skl_scaler_calc_phase(int sub, bool chroma_center);
 int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state);
 int skl_max_scale(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state,
 		  uint32_t pixel_format);
@@ -1643,6 +1665,9 @@ void intel_csr_ucode_suspend(struct drm_i915_private *);
 void intel_csr_ucode_resume(struct drm_i915_private *);
 
 /* intel_dp.c */
+bool intel_dp_port_enabled(struct drm_i915_private *dev_priv,
+			   i915_reg_t dp_reg, enum port port,
+			   enum pipe *pipe);
 bool intel_dp_init(struct drm_i915_private *dev_priv, i915_reg_t output_reg,
 		   enum port port);
 bool intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
@@ -1660,8 +1685,6 @@ void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode);
 void intel_dp_encoder_reset(struct drm_encoder *encoder);
 void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder);
 void intel_dp_encoder_destroy(struct drm_encoder *encoder);
-int intel_dp_sink_crc(struct intel_dp *intel_dp,
-		      struct intel_crtc_state *crtc_state, u8 *crc);
 bool intel_dp_compute_config(struct intel_encoder *encoder,
 			     struct intel_crtc_state *pipe_config,
 			     struct drm_connector_state *conn_state);
@@ -1675,8 +1698,8 @@ void intel_edp_backlight_off(const struct drm_connector_state *conn_state);
 void intel_edp_panel_vdd_on(struct intel_dp *intel_dp);
 void intel_edp_panel_on(struct intel_dp *intel_dp);
 void intel_edp_panel_off(struct intel_dp *intel_dp);
-void intel_dp_mst_suspend(struct drm_device *dev);
-void intel_dp_mst_resume(struct drm_device *dev);
+void intel_dp_mst_suspend(struct drm_i915_private *dev_priv);
+void intel_dp_mst_resume(struct drm_i915_private *dev_priv);
 int intel_dp_max_link_rate(struct intel_dp *intel_dp);
 int intel_dp_max_lane_count(struct intel_dp *intel_dp);
 int intel_dp_rate_select(struct intel_dp *intel_dp, int rate);
@@ -1706,6 +1729,7 @@ intel_dp_pre_emphasis_max(struct intel_dp *intel_dp, uint8_t voltage_swing);
 void intel_dp_compute_rate(struct intel_dp *intel_dp, int port_clock,
 			   uint8_t *link_bw, uint8_t *rate_select);
 bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp);
+bool intel_dp_source_supports_hbr3(struct intel_dp *intel_dp);
 bool
 intel_dp_get_link_status(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_STATUS_SIZE]);
 
@@ -1725,8 +1749,8 @@ int intel_dp_aux_init_backlight_funcs(struct intel_connector *intel_connector);
 /* intel_dp_mst.c */
 int intel_dp_mst_encoder_init(struct intel_digital_port *intel_dig_port, int conn_id);
 void intel_dp_mst_encoder_cleanup(struct intel_digital_port *intel_dig_port);
-/* intel_dsi.c */
-void intel_dsi_init(struct drm_i915_private *dev_priv);
+/* vlv_dsi.c */
+void vlv_dsi_init(struct drm_i915_private *dev_priv);
 
 /* intel_dsi_dcs_backlight.c */
 int intel_dsi_dcs_init_backlight_funcs(struct intel_connector *intel_connector);
@@ -1820,6 +1844,8 @@ void intel_infoframe_init(struct intel_digital_port *intel_dig_port);
 
 
 /* intel_lvds.c */
+bool intel_lvds_port_enabled(struct drm_i915_private *dev_priv,
+			     i915_reg_t lvds_reg, enum pipe *pipe);
 void intel_lvds_init(struct drm_i915_private *dev_priv);
 struct intel_encoder *intel_get_lvds_encoder(struct drm_device *dev);
 bool intel_is_dual_link_lvds(struct drm_device *dev);
@@ -1866,7 +1892,6 @@ void intel_panel_enable_backlight(const struct intel_crtc_state *crtc_state,
 				  const struct drm_connector_state *conn_state);
 void intel_panel_disable_backlight(const struct drm_connector_state *old_conn_state);
 void intel_panel_destroy_backlight(struct drm_connector *connector);
-enum drm_connector_status intel_panel_detect(struct drm_i915_private *dev_priv);
 extern struct drm_display_mode *intel_find_panel_downclock(
 				struct drm_i915_private *dev_priv,
 				struct drm_display_mode *fixed_mode,
@@ -1910,12 +1935,12 @@ void intel_psr_flush(struct drm_i915_private *dev_priv,
 		     unsigned frontbuffer_bits,
 		     enum fb_op_origin origin);
 void intel_psr_init(struct drm_i915_private *dev_priv);
-void intel_psr_single_frame_update(struct drm_i915_private *dev_priv,
-				   unsigned frontbuffer_bits);
 void intel_psr_compute_config(struct intel_dp *intel_dp,
 			      struct intel_crtc_state *crtc_state);
 void intel_psr_irq_control(struct drm_i915_private *dev_priv, bool debug);
 void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir);
+void intel_psr_short_pulse(struct intel_dp *intel_dp);
+int intel_psr_wait_for_idle(const struct intel_crtc_state *new_crtc_state);
 
 /* intel_runtime_pm.c */
 int intel_power_domains_init(struct drm_i915_private *);
@@ -2057,12 +2082,13 @@ void intel_init_ipc(struct drm_i915_private *dev_priv);
 void intel_enable_ipc(struct drm_i915_private *dev_priv);
 
 /* intel_sdvo.c */
+bool intel_sdvo_port_enabled(struct drm_i915_private *dev_priv,
+			     i915_reg_t sdvo_reg, enum pipe *pipe);
 bool intel_sdvo_init(struct drm_i915_private *dev_priv,
 		     i915_reg_t reg, enum port port);
 
 
 /* intel_sprite.c */
-bool intel_format_is_yuv(u32 format);
 int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
 			     int usecs);
 struct intel_plane *intel_sprite_plane_create(struct drm_i915_private *dev_priv,
@@ -2075,10 +2101,9 @@ void skl_update_plane(struct intel_plane *plane,
 		      const struct intel_crtc_state *crtc_state,
 		      const struct intel_plane_state *plane_state);
 void skl_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc);
-bool skl_plane_get_hw_state(struct intel_plane *plane);
+bool skl_plane_get_hw_state(struct intel_plane *plane, enum pipe *pipe);
 bool skl_plane_has_ccs(struct drm_i915_private *dev_priv,
 		       enum pipe pipe, enum plane_id plane_id);
-bool intel_format_is_yuv(uint32_t format);
 bool skl_plane_has_planar(struct drm_i915_private *dev_priv,
 			  enum pipe pipe, enum plane_id plane_id);
 
@@ -2144,7 +2169,6 @@ void lspcon_resume(struct intel_lspcon *lspcon);
 void lspcon_wait_pcon_mode(struct intel_lspcon *lspcon);
 
 /* intel_pipe_crc.c */
-int intel_pipe_crc_create(struct drm_minor *minor);
 #ifdef CONFIG_DEBUG_FS
 int intel_crtc_set_crc_source(struct drm_crtc *crtc, const char *source_name,
 			      size_t *values_cnt);
@@ -2160,5 +2184,4 @@ static inline void intel_crtc_enable_pipe_crc(struct intel_crtc *crtc)
 {
 }
 #endif
-extern const struct file_operations i915_display_crc_ctl_fops;
 #endif /* __INTEL_DRV_H__ */
diff --git a/drivers/gpu/drm/i915/intel_dsi.h b/drivers/gpu/drm/i915/intel_dsi.h
index 7afeb9580f41..ad7c1cb32983 100644
--- a/drivers/gpu/drm/i915/intel_dsi.h
+++ b/drivers/gpu/drm/i915/intel_dsi.h
@@ -129,21 +129,29 @@ static inline struct intel_dsi *enc_to_intel_dsi(struct drm_encoder *encoder)
 	return container_of(encoder, struct intel_dsi, base.base);
 }
 
-/* intel_dsi.c */
-void wait_for_dsi_fifo_empty(struct intel_dsi *intel_dsi, enum port port);
+/* vlv_dsi.c */
+void vlv_dsi_wait_for_fifo_empty(struct intel_dsi *intel_dsi, enum port port);
 enum mipi_dsi_pixel_format pixel_format_from_register_bits(u32 fmt);
 
-/* intel_dsi_pll.c */
-bool intel_dsi_pll_is_enabled(struct drm_i915_private *dev_priv);
-int intel_compute_dsi_pll(struct intel_encoder *encoder,
-			  struct intel_crtc_state *config);
-void intel_enable_dsi_pll(struct intel_encoder *encoder,
-			  const struct intel_crtc_state *config);
-void intel_disable_dsi_pll(struct intel_encoder *encoder);
-u32 intel_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
-		       struct intel_crtc_state *config);
-void intel_dsi_reset_clocks(struct intel_encoder *encoder,
-			    enum port port);
+/* vlv_dsi_pll.c */
+int vlv_dsi_pll_compute(struct intel_encoder *encoder,
+			struct intel_crtc_state *config);
+void vlv_dsi_pll_enable(struct intel_encoder *encoder,
+			const struct intel_crtc_state *config);
+void vlv_dsi_pll_disable(struct intel_encoder *encoder);
+u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
+		     struct intel_crtc_state *config);
+void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port);
+
+bool bxt_dsi_pll_is_enabled(struct drm_i915_private *dev_priv);
+int bxt_dsi_pll_compute(struct intel_encoder *encoder,
+			struct intel_crtc_state *config);
+void bxt_dsi_pll_enable(struct intel_encoder *encoder,
+			const struct intel_crtc_state *config);
+void bxt_dsi_pll_disable(struct intel_encoder *encoder);
+u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
+		     struct intel_crtc_state *config);
+void bxt_dsi_reset_clocks(struct intel_encoder *encoder, enum port port);
 
 /* intel_dsi_vbt.c */
 bool intel_dsi_vbt_init(struct intel_dsi *intel_dsi, u16 panel_id);
diff --git a/drivers/gpu/drm/i915/intel_dsi_vbt.c b/drivers/gpu/drm/i915/intel_dsi_vbt.c
index 4d6ffa7b3e7b..ac83d6b89ae0 100644
--- a/drivers/gpu/drm/i915/intel_dsi_vbt.c
+++ b/drivers/gpu/drm/i915/intel_dsi_vbt.c
@@ -181,7 +181,7 @@ static const u8 *mipi_exec_send_packet(struct intel_dsi *intel_dsi,
 		break;
 	}
 
-	wait_for_dsi_fifo_empty(intel_dsi, port);
+	vlv_dsi_wait_for_fifo_empty(intel_dsi, port);
 
 out:
 	data += len;
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index 61d908e0df0e..4e142ff49708 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -137,19 +137,15 @@ static bool intel_dvo_connector_get_hw_state(struct intel_connector *connector)
 static bool intel_dvo_get_hw_state(struct intel_encoder *encoder,
 				   enum pipe *pipe)
 {
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
 	u32 tmp;
 
 	tmp = I915_READ(intel_dvo->dev.dvo_reg);
 
-	if (!(tmp & DVO_ENABLE))
-		return false;
-
-	*pipe = PORT_TO_PIPE(tmp);
+	*pipe = (tmp & DVO_PIPE_SEL_MASK) >> DVO_PIPE_SEL_SHIFT;
 
-	return true;
+	return tmp & DVO_ENABLE;
 }
 
 static void intel_dvo_get_config(struct intel_encoder *encoder,
@@ -282,8 +278,7 @@ static void intel_dvo_pre_enable(struct intel_encoder *encoder,
 	dvo_val |= DVO_DATA_ORDER_FP | DVO_BORDER_ENABLE |
 		   DVO_BLANK_ACTIVE_HIGH;
 
-	if (pipe == 1)
-		dvo_val |= DVO_PIPE_B_SELECT;
+	dvo_val |= DVO_PIPE_SEL(pipe);
 	dvo_val |= DVO_PIPE_STALL;
 	if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
 		dvo_val |= DVO_HSYNC_ACTIVE_HIGH;
@@ -443,7 +438,7 @@ void intel_dvo_init(struct drm_i915_private *dev_priv)
 		int gpio;
 		bool dvoinit;
 		enum pipe pipe;
-		uint32_t dpll[I915_MAX_PIPES];
+		u32 dpll[I915_MAX_PIPES];
 		enum port port;
 
 		/*
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 1590375f31cb..2d1952849d69 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -25,7 +25,6 @@
 #include <drm/drm_print.h>
 
 #include "i915_drv.h"
-#include "i915_vgpu.h"
 #include "intel_ringbuffer.h"
 #include "intel_lrc.h"
 
@@ -230,6 +229,7 @@ __intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
 		break;
 	default:
 		MISSING_CASE(class);
+		/* fall through */
 	case VIDEO_DECODE_CLASS:
 	case VIDEO_ENHANCEMENT_CLASS:
 	case COPY_ENGINE_CLASS:
@@ -302,6 +302,8 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 							   engine->class);
 	if (WARN_ON(engine->context_size > BIT(20)))
 		engine->context_size = 0;
+	if (engine->context_size)
+		DRIVER_CAPS(dev_priv)->has_logical_contexts = true;
 
 	/* Nothing to do here, execute in order of dependencies */
 	engine->schedule = NULL;
@@ -456,28 +458,16 @@ static void intel_engine_init_batch_pool(struct intel_engine_cs *engine)
 	i915_gem_batch_pool_init(&engine->batch_pool, engine);
 }
 
-static bool csb_force_mmio(struct drm_i915_private *i915)
-{
-	/* Older GVT emulation depends upon intercepting CSB mmio */
-	if (intel_vgpu_active(i915) && !intel_vgpu_has_hwsp_emulation(i915))
-		return true;
-
-	return false;
-}
-
 static void intel_engine_init_execlist(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 
-	execlists->csb_use_mmio = csb_force_mmio(engine->i915);
-
 	execlists->port_mask = 1;
 	BUILD_BUG_ON_NOT_POWER_OF_2(execlists_num_ports(execlists));
 	GEM_BUG_ON(execlists_num_ports(execlists) > EXECLIST_MAX_PORTS);
 
 	execlists->queue_priority = INT_MIN;
-	execlists->queue = RB_ROOT;
-	execlists->first = NULL;
+	execlists->queue = RB_ROOT_CACHED;
 }
 
 /**
@@ -492,6 +482,7 @@ static void intel_engine_init_execlist(struct intel_engine_cs *engine)
 void intel_engine_setup_common(struct intel_engine_cs *engine)
 {
 	i915_timeline_init(engine->i915, &engine->timeline, engine->name);
+	lockdep_set_subclass(&engine->timeline.lock, TIMELINE_ENGINE);
 
 	intel_engine_init_execlist(engine);
 	intel_engine_init_hangcheck(engine);
@@ -499,7 +490,8 @@ void intel_engine_setup_common(struct intel_engine_cs *engine)
 	intel_engine_init_cmd_parser(engine);
 }
 
-int intel_engine_create_scratch(struct intel_engine_cs *engine, int size)
+int intel_engine_create_scratch(struct intel_engine_cs *engine,
+				unsigned int size)
 {
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
@@ -515,7 +507,7 @@ int intel_engine_create_scratch(struct intel_engine_cs *engine, int size)
 		return PTR_ERR(obj);
 	}
 
-	vma = i915_vma_instance(obj, &engine->i915->ggtt.base, NULL);
+	vma = i915_vma_instance(obj, &engine->i915->ggtt.vm, NULL);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto err_unref;
@@ -533,7 +525,7 @@ err_unref:
 	return ret;
 }
 
-static void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
+void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
 {
 	i915_vma_unpin_and_release(&engine->scratch);
 }
@@ -585,7 +577,7 @@ static int init_status_page(struct intel_engine_cs *engine)
 	if (ret)
 		goto err;
 
-	vma = i915_vma_instance(obj, &engine->i915->ggtt.base, NULL);
+	vma = i915_vma_instance(obj, &engine->i915->ggtt.vm, NULL);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto err;
@@ -645,6 +637,12 @@ static int init_phys_status_page(struct intel_engine_cs *engine)
 	return 0;
 }
 
+static void __intel_context_unpin(struct i915_gem_context *ctx,
+				  struct intel_engine_cs *engine)
+{
+	intel_context_unpin(to_intel_context(ctx, engine));
+}
+
 /**
  * intel_engines_init_common - initialize cengine state which might require hw access
  * @engine: Engine to initialize.
@@ -658,7 +656,8 @@ static int init_phys_status_page(struct intel_engine_cs *engine)
  */
 int intel_engine_init_common(struct intel_engine_cs *engine)
 {
-	struct intel_ring *ring;
+	struct drm_i915_private *i915 = engine->i915;
+	struct intel_context *ce;
 	int ret;
 
 	engine->set_default_submission(engine);
@@ -670,18 +669,18 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
 	 * be available. To avoid this we always pin the default
 	 * context.
 	 */
-	ring = intel_context_pin(engine->i915->kernel_context, engine);
-	if (IS_ERR(ring))
-		return PTR_ERR(ring);
+	ce = intel_context_pin(i915->kernel_context, engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
 
 	/*
 	 * Similarly the preempt context must always be available so that
 	 * we can interrupt the engine at any time.
 	 */
-	if (engine->i915->preempt_context) {
-		ring = intel_context_pin(engine->i915->preempt_context, engine);
-		if (IS_ERR(ring)) {
-			ret = PTR_ERR(ring);
+	if (i915->preempt_context) {
+		ce = intel_context_pin(i915->preempt_context, engine);
+		if (IS_ERR(ce)) {
+			ret = PTR_ERR(ce);
 			goto err_unpin_kernel;
 		}
 	}
@@ -690,7 +689,7 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
 	if (ret)
 		goto err_unpin_preempt;
 
-	if (HWS_NEEDS_PHYSICAL(engine->i915))
+	if (HWS_NEEDS_PHYSICAL(i915))
 		ret = init_phys_status_page(engine);
 	else
 		ret = init_status_page(engine);
@@ -702,10 +701,11 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
 err_breadcrumbs:
 	intel_engine_fini_breadcrumbs(engine);
 err_unpin_preempt:
-	if (engine->i915->preempt_context)
-		intel_context_unpin(engine->i915->preempt_context, engine);
+	if (i915->preempt_context)
+		__intel_context_unpin(i915->preempt_context, engine);
+
 err_unpin_kernel:
-	intel_context_unpin(engine->i915->kernel_context, engine);
+	__intel_context_unpin(i915->kernel_context, engine);
 	return ret;
 }
 
@@ -718,6 +718,8 @@ err_unpin_kernel:
  */
 void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 {
+	struct drm_i915_private *i915 = engine->i915;
+
 	intel_engine_cleanup_scratch(engine);
 
 	if (HWS_NEEDS_PHYSICAL(engine->i915))
@@ -732,9 +734,9 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 	if (engine->default_state)
 		i915_gem_object_put(engine->default_state);
 
-	if (engine->i915->preempt_context)
-		intel_context_unpin(engine->i915->preempt_context, engine);
-	intel_context_unpin(engine->i915->kernel_context, engine);
+	if (i915->preempt_context)
+		__intel_context_unpin(i915->preempt_context, engine);
+	__intel_context_unpin(i915->kernel_context, engine);
 
 	i915_timeline_fini(&engine->timeline);
 }
@@ -769,6 +771,35 @@ u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine)
 	return bbaddr;
 }
 
+int intel_engine_stop_cs(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+	const u32 base = engine->mmio_base;
+	const i915_reg_t mode = RING_MI_MODE(base);
+	int err;
+
+	if (INTEL_GEN(dev_priv) < 3)
+		return -ENODEV;
+
+	GEM_TRACE("%s\n", engine->name);
+
+	I915_WRITE_FW(mode, _MASKED_BIT_ENABLE(STOP_RING));
+
+	err = 0;
+	if (__intel_wait_for_register_fw(dev_priv,
+					 mode, MODE_IDLE, MODE_IDLE,
+					 1000, 0,
+					 NULL)) {
+		GEM_TRACE("%s: timed out on STOP_RING -> IDLE\n", engine->name);
+		err = -ETIMEDOUT;
+	}
+
+	/* A final mmio read to let GPU writes be hopefully flushed to memory */
+	POSTING_READ_FW(mode);
+
+	return err;
+}
+
 const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
 {
 	switch (type) {
@@ -780,12 +811,32 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
 	}
 }
 
+u32 intel_calculate_mcr_s_ss_select(struct drm_i915_private *dev_priv)
+{
+	const struct sseu_dev_info *sseu = &(INTEL_INFO(dev_priv)->sseu);
+	u32 mcr_s_ss_select;
+	u32 slice = fls(sseu->slice_mask);
+	u32 subslice = fls(sseu->subslice_mask[slice]);
+
+	if (INTEL_GEN(dev_priv) == 10)
+		mcr_s_ss_select = GEN8_MCR_SLICE(slice) |
+				  GEN8_MCR_SUBSLICE(subslice);
+	else if (INTEL_GEN(dev_priv) >= 11)
+		mcr_s_ss_select = GEN11_MCR_SLICE(slice) |
+				  GEN11_MCR_SUBSLICE(subslice);
+	else
+		mcr_s_ss_select = 0;
+
+	return mcr_s_ss_select;
+}
+
 static inline uint32_t
 read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
 		  int subslice, i915_reg_t reg)
 {
 	uint32_t mcr_slice_subslice_mask;
 	uint32_t mcr_slice_subslice_select;
+	uint32_t default_mcr_s_ss_select;
 	uint32_t mcr;
 	uint32_t ret;
 	enum forcewake_domains fw_domains;
@@ -802,6 +853,8 @@ read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
 					    GEN8_MCR_SUBSLICE(subslice);
 	}
 
+	default_mcr_s_ss_select = intel_calculate_mcr_s_ss_select(dev_priv);
+
 	fw_domains = intel_uncore_forcewake_for_reg(dev_priv, reg,
 						    FW_REG_READ);
 	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
@@ -812,11 +865,10 @@ read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
 	intel_uncore_forcewake_get__locked(dev_priv, fw_domains);
 
 	mcr = I915_READ_FW(GEN8_MCR_SELECTOR);
-	/*
-	 * The HW expects the slice and sublice selectors to be reset to 0
-	 * after reading out the registers.
-	 */
-	WARN_ON_ONCE(mcr & mcr_slice_subslice_mask);
+
+	WARN_ON_ONCE((mcr & mcr_slice_subslice_mask) !=
+		     default_mcr_s_ss_select);
+
 	mcr &= ~mcr_slice_subslice_mask;
 	mcr |= mcr_slice_subslice_select;
 	I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr);
@@ -824,6 +876,8 @@ read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
 	ret = I915_READ_FW(reg);
 
 	mcr &= ~mcr_slice_subslice_mask;
+	mcr |= default_mcr_s_ss_select;
+
 	I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr);
 
 	intel_uncore_forcewake_put__locked(dev_priv, fw_domains);
@@ -934,11 +988,24 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
 		return true;
 
 	/* Waiting to drain ELSP? */
-	if (READ_ONCE(engine->execlists.active))
-		return false;
+	if (READ_ONCE(engine->execlists.active)) {
+		struct tasklet_struct *t = &engine->execlists.tasklet;
+
+		local_bh_disable();
+		if (tasklet_trylock(t)) {
+			/* Must wait for any GPU reset in progress. */
+			if (__tasklet_is_enabled(t))
+				t->func(t->data);
+			tasklet_unlock(t);
+		}
+		local_bh_enable();
 
-	/* ELSP is empty, but there are ready requests? */
-	if (READ_ONCE(engine->execlists.first))
+		if (READ_ONCE(engine->execlists.active))
+			return false;
+	}
+
+	/* ELSP is empty, but there are ready requests? E.g. after reset */
+	if (!RB_EMPTY_ROOT(&engine->execlists.queue.rb_root))
 		return false;
 
 	/* Ring stopped? */
@@ -978,8 +1045,8 @@ bool intel_engines_are_idle(struct drm_i915_private *dev_priv)
  */
 bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine)
 {
-	const struct i915_gem_context * const kernel_context =
-		engine->i915->kernel_context;
+	const struct intel_context *kernel_context =
+		to_intel_context(engine->i915->kernel_context, engine);
 	struct i915_request *rq;
 
 	lockdep_assert_held(&engine->i915->drm.struct_mutex);
@@ -991,7 +1058,7 @@ bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine)
 	 */
 	rq = __i915_gem_active_peek(&engine->timeline.last_request);
 	if (rq)
-		return rq->ctx == kernel_context;
+		return rq->hw_context == kernel_context;
 	else
 		return engine->last_retired_context == kernel_context;
 }
@@ -1006,6 +1073,28 @@ void intel_engines_reset_default_submission(struct drm_i915_private *i915)
 }
 
 /**
+ * intel_engines_sanitize: called after the GPU has lost power
+ * @i915: the i915 device
+ *
+ * Anytime we reset the GPU, either with an explicit GPU reset or through a
+ * PCI power cycle, the GPU loses state and we must reset our state tracking
+ * to match. Note that calling intel_engines_sanitize() if the GPU has not
+ * been reset results in much confusion!
+ */
+void intel_engines_sanitize(struct drm_i915_private *i915)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	GEM_TRACE("\n");
+
+	for_each_engine(engine, i915, id) {
+		if (engine->reset.reset)
+			engine->reset.reset(engine, NULL);
+	}
+}
+
+/**
  * intel_engines_park: called when the GT is transitioning from busy->idle
  * @i915: the i915 device
  *
@@ -1043,6 +1132,11 @@ void intel_engines_park(struct drm_i915_private *i915)
 		if (engine->park)
 			engine->park(engine);
 
+		if (engine->pinned_default_state) {
+			i915_gem_object_unpin_map(engine->default_state);
+			engine->pinned_default_state = NULL;
+		}
+
 		i915_gem_batch_pool_fini(&engine->batch_pool);
 		engine->execlists.no_priolist = false;
 	}
@@ -1060,6 +1154,16 @@ void intel_engines_unpark(struct drm_i915_private *i915)
 	enum intel_engine_id id;
 
 	for_each_engine(engine, i915, id) {
+		void *map;
+
+		/* Pin the default state for fast resets from atomic context. */
+		map = NULL;
+		if (engine->default_state)
+			map = i915_gem_object_pin_map(engine->default_state,
+						      I915_MAP_WB);
+		if (!IS_ERR_OR_NULL(map))
+			engine->pinned_default_state = map;
+
 		if (engine->unpark)
 			engine->unpark(engine);
 
@@ -1067,6 +1171,26 @@ void intel_engines_unpark(struct drm_i915_private *i915)
 	}
 }
 
+/**
+ * intel_engine_lost_context: called when the GPU is reset into unknown state
+ * @engine: the engine
+ *
+ * We have either reset the GPU or otherwise about to lose state tracking of
+ * the current GPU logical state (e.g. suspend). On next use, it is therefore
+ * imperative that we make no presumptions about the current state and load
+ * from scratch.
+ */
+void intel_engine_lost_context(struct intel_engine_cs *engine)
+{
+	struct intel_context *ce;
+
+	lockdep_assert_held(&engine->i915->drm.struct_mutex);
+
+	ce = fetch_and_zero(&engine->last_retired_context);
+	if (ce)
+		intel_context_unpin(ce);
+}
+
 bool intel_engine_can_store_dword(struct intel_engine_cs *engine)
 {
 	switch (INTEL_GEN(engine->i915)) {
@@ -1151,7 +1275,7 @@ static void hexdump(struct drm_printer *m, const void *buf, size_t len)
 						rowsize, sizeof(u32),
 						line, sizeof(line),
 						false) >= sizeof(line));
-		drm_printf(m, "%08zx %s\n", pos, line);
+		drm_printf(m, "[%04zx] %s\n", pos, line);
 
 		prev = buf + pos;
 		skip = false;
@@ -1166,6 +1290,8 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
 		&engine->execlists;
 	u64 addr;
 
+	if (engine->id == RCS && IS_GEN(dev_priv, 4, 7))
+		drm_printf(m, "\tCCID: 0x%08x\n", I915_READ(CCID));
 	drm_printf(m, "\tRING_START: 0x%08x\n",
 		   I915_READ(RING_START(engine->mmio_base)));
 	drm_printf(m, "\tRING_HEAD:  0x%08x\n",
@@ -1232,12 +1358,10 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
 		ptr = I915_READ(RING_CONTEXT_STATUS_PTR(engine));
 		read = GEN8_CSB_READ_PTR(ptr);
 		write = GEN8_CSB_WRITE_PTR(ptr);
-		drm_printf(m, "\tExeclist CSB read %d [%d cached], write %d [%d from hws], interrupt posted? %s, tasklet queued? %s (%s)\n",
+		drm_printf(m, "\tExeclist CSB read %d [%d cached], write %d [%d from hws], tasklet queued? %s (%s)\n",
 			   read, execlists->csb_head,
 			   write,
 			   intel_read_status_page(engine, intel_hws_csb_write_index(engine->i915)),
-			   yesno(test_bit(ENGINE_IRQ_EXECLIST,
-					  &engine->irq_posted)),
 			   yesno(test_bit(TASKLET_STATE_SCHED,
 					  &engine->execlists.tasklet.state)),
 			   enableddisabled(!atomic_read(&engine->execlists.tasklet.count)));
@@ -1287,6 +1411,39 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
 	}
 }
 
+static void print_request_ring(struct drm_printer *m, struct i915_request *rq)
+{
+	void *ring;
+	int size;
+
+	drm_printf(m,
+		   "[head %04x, postfix %04x, tail %04x, batch 0x%08x_%08x]:\n",
+		   rq->head, rq->postfix, rq->tail,
+		   rq->batch ? upper_32_bits(rq->batch->node.start) : ~0u,
+		   rq->batch ? lower_32_bits(rq->batch->node.start) : ~0u);
+
+	size = rq->tail - rq->head;
+	if (rq->tail < rq->head)
+		size += rq->ring->size;
+
+	ring = kmalloc(size, GFP_ATOMIC);
+	if (ring) {
+		const void *vaddr = rq->ring->vaddr;
+		unsigned int head = rq->head;
+		unsigned int len = 0;
+
+		if (rq->tail < head) {
+			len = rq->ring->size - head;
+			memcpy(ring, vaddr + head, len);
+			head = 0;
+		}
+		memcpy(ring + len, vaddr + head, size - len);
+
+		hexdump(m, ring, size);
+		kfree(ring);
+	}
+}
+
 void intel_engine_dump(struct intel_engine_cs *engine,
 		       struct drm_printer *m,
 		       const char *header, ...)
@@ -1296,6 +1453,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	const struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_gpu_error * const error = &engine->i915->gpu_error;
 	struct i915_request *rq, *last;
+	unsigned long flags;
 	struct rb_node *rb;
 	int count;
 
@@ -1336,11 +1494,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	rq = i915_gem_find_active_request(engine);
 	if (rq) {
 		print_request(m, rq, "\t\tactive ");
-		drm_printf(m,
-			   "\t\t[head %04x, postfix %04x, tail %04x, batch 0x%08x_%08x]\n",
-			   rq->head, rq->postfix, rq->tail,
-			   rq->batch ? upper_32_bits(rq->batch->node.start) : ~0u,
-			   rq->batch ? lower_32_bits(rq->batch->node.start) : ~0u);
+
 		drm_printf(m, "\t\tring->start:  0x%08x\n",
 			   i915_ggtt_offset(rq->ring->vma));
 		drm_printf(m, "\t\tring->head:   0x%08x\n",
@@ -1351,6 +1505,8 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 			   rq->ring->emit);
 		drm_printf(m, "\t\tring->space:  0x%08x\n",
 			   rq->ring->space);
+
+		print_request_ring(m, rq);
 	}
 
 	rcu_read_unlock();
@@ -1362,7 +1518,8 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		drm_printf(m, "\tDevice is asleep; skipping register dump\n");
 	}
 
-	spin_lock_irq(&engine->timeline.lock);
+	local_irq_save(flags);
+	spin_lock(&engine->timeline.lock);
 
 	last = NULL;
 	count = 0;
@@ -1384,7 +1541,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	last = NULL;
 	count = 0;
 	drm_printf(m, "\t\tQueue priority: %d\n", execlists->queue_priority);
-	for (rb = execlists->first; rb; rb = rb_next(rb)) {
+	for (rb = rb_first_cached(&execlists->queue); rb; rb = rb_next(rb)) {
 		struct i915_priolist *p =
 			rb_entry(rb, typeof(*p), node);
 
@@ -1404,22 +1561,21 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		print_request(m, last, "\t\tQ ");
 	}
 
-	spin_unlock_irq(&engine->timeline.lock);
+	spin_unlock(&engine->timeline.lock);
 
-	spin_lock_irq(&b->rb_lock);
+	spin_lock(&b->rb_lock);
 	for (rb = rb_first(&b->waiters); rb; rb = rb_next(rb)) {
 		struct intel_wait *w = rb_entry(rb, typeof(*w), node);
 
 		drm_printf(m, "\t%s [%d] waiting for %x\n",
 			   w->tsk->comm, w->tsk->pid, w->seqno);
 	}
-	spin_unlock_irq(&b->rb_lock);
+	spin_unlock(&b->rb_lock);
+	local_irq_restore(flags);
 
-	drm_printf(m, "IRQ? 0x%lx (breadcrumbs? %s) (execlists? %s)\n",
+	drm_printf(m, "IRQ? 0x%lx (breadcrumbs? %s)\n",
 		   engine->irq_posted,
 		   yesno(test_bit(ENGINE_IRQ_BREADCRUMB,
-				  &engine->irq_posted)),
-		   yesno(test_bit(ENGINE_IRQ_EXECLIST,
 				  &engine->irq_posted)));
 
 	drm_printf(m, "HWSP:\n");
@@ -1468,8 +1624,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 	if (!intel_engine_supports_stats(engine))
 		return -ENODEV;
 
-	tasklet_disable(&execlists->tasklet);
-	write_seqlock_irqsave(&engine->stats.lock, flags);
+	spin_lock_irqsave(&engine->timeline.lock, flags);
+	write_seqlock(&engine->stats.lock);
 
 	if (unlikely(engine->stats.enabled == ~0)) {
 		err = -EBUSY;
@@ -1493,8 +1649,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 	}
 
 unlock:
-	write_sequnlock_irqrestore(&engine->stats.lock, flags);
-	tasklet_enable(&execlists->tasklet);
+	write_sequnlock(&engine->stats.lock);
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index b431b6733cc1..01d1d2088f04 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -399,89 +399,6 @@ bool intel_fbc_is_active(struct drm_i915_private *dev_priv)
 	return dev_priv->fbc.active;
 }
 
-static void intel_fbc_work_fn(struct work_struct *__work)
-{
-	struct drm_i915_private *dev_priv =
-		container_of(__work, struct drm_i915_private, fbc.work.work);
-	struct intel_fbc *fbc = &dev_priv->fbc;
-	struct intel_fbc_work *work = &fbc->work;
-	struct intel_crtc *crtc = fbc->crtc;
-	struct drm_vblank_crtc *vblank = &dev_priv->drm.vblank[crtc->pipe];
-
-	if (drm_crtc_vblank_get(&crtc->base)) {
-		/* CRTC is now off, leave FBC deactivated */
-		mutex_lock(&fbc->lock);
-		work->scheduled = false;
-		mutex_unlock(&fbc->lock);
-		return;
-	}
-
-retry:
-	/* Delay the actual enabling to let pageflipping cease and the
-	 * display to settle before starting the compression. Note that
-	 * this delay also serves a second purpose: it allows for a
-	 * vblank to pass after disabling the FBC before we attempt
-	 * to modify the control registers.
-	 *
-	 * WaFbcWaitForVBlankBeforeEnable:ilk,snb
-	 *
-	 * It is also worth mentioning that since work->scheduled_vblank can be
-	 * updated multiple times by the other threads, hitting the timeout is
-	 * not an error condition. We'll just end up hitting the "goto retry"
-	 * case below.
-	 */
-	wait_event_timeout(vblank->queue,
-		drm_crtc_vblank_count(&crtc->base) != work->scheduled_vblank,
-		msecs_to_jiffies(50));
-
-	mutex_lock(&fbc->lock);
-
-	/* Were we cancelled? */
-	if (!work->scheduled)
-		goto out;
-
-	/* Were we delayed again while this function was sleeping? */
-	if (drm_crtc_vblank_count(&crtc->base) == work->scheduled_vblank) {
-		mutex_unlock(&fbc->lock);
-		goto retry;
-	}
-
-	intel_fbc_hw_activate(dev_priv);
-
-	work->scheduled = false;
-
-out:
-	mutex_unlock(&fbc->lock);
-	drm_crtc_vblank_put(&crtc->base);
-}
-
-static void intel_fbc_schedule_activation(struct intel_crtc *crtc)
-{
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	struct intel_fbc *fbc = &dev_priv->fbc;
-	struct intel_fbc_work *work = &fbc->work;
-
-	WARN_ON(!mutex_is_locked(&fbc->lock));
-	if (WARN_ON(!fbc->enabled))
-		return;
-
-	if (drm_crtc_vblank_get(&crtc->base)) {
-		DRM_ERROR("vblank not available for FBC on pipe %c\n",
-			  pipe_name(crtc->pipe));
-		return;
-	}
-
-	/* It is useless to call intel_fbc_cancel_work() or cancel_work() in
-	 * this function since we're not releasing fbc.lock, so it won't have an
-	 * opportunity to grab it to discover that it was cancelled. So we just
-	 * update the expected jiffy count. */
-	work->scheduled = true;
-	work->scheduled_vblank = drm_crtc_vblank_count(&crtc->base);
-	drm_crtc_vblank_put(&crtc->base);
-
-	schedule_work(&work->work);
-}
-
 static void intel_fbc_deactivate(struct drm_i915_private *dev_priv,
 				 const char *reason)
 {
@@ -489,11 +406,6 @@ static void intel_fbc_deactivate(struct drm_i915_private *dev_priv,
 
 	WARN_ON(!mutex_is_locked(&fbc->lock));
 
-	/* Calling cancel_work() here won't help due to the fact that the work
-	 * function grabs fbc->lock. Just set scheduled to false so the work
-	 * function can know it was cancelled. */
-	fbc->work.scheduled = false;
-
 	if (fbc->active)
 		intel_fbc_hw_deactivate(dev_priv);
 
@@ -924,13 +836,6 @@ static void intel_fbc_get_reg_params(struct intel_crtc *crtc,
 						32 * fbc->threshold) * 8;
 }
 
-static bool intel_fbc_reg_params_equal(struct intel_fbc_reg_params *params1,
-				       struct intel_fbc_reg_params *params2)
-{
-	/* We can use this since intel_fbc_get_reg_params() does a memset. */
-	return memcmp(params1, params2, sizeof(*params1)) == 0;
-}
-
 void intel_fbc_pre_update(struct intel_crtc *crtc,
 			  struct intel_crtc_state *crtc_state,
 			  struct intel_plane_state *plane_state)
@@ -953,6 +858,7 @@ void intel_fbc_pre_update(struct intel_crtc *crtc,
 		goto unlock;
 
 	intel_fbc_update_state_cache(crtc, crtc_state, plane_state);
+	fbc->flip_pending = true;
 
 deactivate:
 	intel_fbc_deactivate(dev_priv, reason);
@@ -988,13 +894,15 @@ static void __intel_fbc_post_update(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
-	struct intel_fbc_reg_params old_params;
 
 	WARN_ON(!mutex_is_locked(&fbc->lock));
 
 	if (!fbc->enabled || fbc->crtc != crtc)
 		return;
 
+	fbc->flip_pending = false;
+	WARN_ON(fbc->active);
+
 	if (!i915_modparams.enable_fbc) {
 		intel_fbc_deactivate(dev_priv, "disabled at runtime per module param");
 		__intel_fbc_disable(dev_priv);
@@ -1002,25 +910,16 @@ static void __intel_fbc_post_update(struct intel_crtc *crtc)
 		return;
 	}
 
-	if (!intel_fbc_can_activate(crtc)) {
-		WARN_ON(fbc->active);
-		return;
-	}
-
-	old_params = fbc->params;
 	intel_fbc_get_reg_params(crtc, &fbc->params);
 
-	/* If the scanout has not changed, don't modify the FBC settings.
-	 * Note that we make the fundamental assumption that the fb->obj
-	 * cannot be unpinned (and have its GTT offset and fence revoked)
-	 * without first being decoupled from the scanout and FBC disabled.
-	 */
-	if (fbc->active &&
-	    intel_fbc_reg_params_equal(&old_params, &fbc->params))
+	if (!intel_fbc_can_activate(crtc))
 		return;
 
-	intel_fbc_deactivate(dev_priv, "FBC enabled (active or scheduled)");
-	intel_fbc_schedule_activation(crtc);
+	if (!fbc->busy_bits) {
+		intel_fbc_deactivate(dev_priv, "FBC enabled (active or scheduled)");
+		intel_fbc_hw_activate(dev_priv);
+	} else
+		intel_fbc_deactivate(dev_priv, "frontbuffer write");
 }
 
 void intel_fbc_post_update(struct intel_crtc *crtc)
@@ -1085,7 +984,7 @@ void intel_fbc_flush(struct drm_i915_private *dev_priv,
 	    (frontbuffer_bits & intel_fbc_get_frontbuffer_bit(fbc))) {
 		if (fbc->active)
 			intel_fbc_recompress(dev_priv);
-		else
+		else if (!fbc->flip_pending)
 			__intel_fbc_post_update(fbc->crtc);
 	}
 
@@ -1225,8 +1124,6 @@ void intel_fbc_disable(struct intel_crtc *crtc)
 	if (fbc->crtc == crtc)
 		__intel_fbc_disable(dev_priv);
 	mutex_unlock(&fbc->lock);
-
-	cancel_work_sync(&fbc->work.work);
 }
 
 /**
@@ -1248,8 +1145,6 @@ void intel_fbc_global_disable(struct drm_i915_private *dev_priv)
 		__intel_fbc_disable(dev_priv);
 	}
 	mutex_unlock(&fbc->lock);
-
-	cancel_work_sync(&fbc->work.work);
 }
 
 static void intel_fbc_underrun_work_fn(struct work_struct *work)
@@ -1400,12 +1295,10 @@ void intel_fbc_init(struct drm_i915_private *dev_priv)
 {
 	struct intel_fbc *fbc = &dev_priv->fbc;
 
-	INIT_WORK(&fbc->work.work, intel_fbc_work_fn);
 	INIT_WORK(&fbc->underrun_work, intel_fbc_underrun_work_fn);
 	mutex_init(&fbc->lock);
 	fbc->enabled = false;
 	fbc->active = false;
-	fbc->work.scheduled = false;
 
 	if (need_fbc_vtd_wa(dev_priv))
 		mkwrite_device_info(dev_priv)->has_fbc = false;
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index e9e02b58b7be..fb2f9fce34cd 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -47,7 +47,7 @@
 
 static void intel_fbdev_invalidate(struct intel_fbdev *ifbdev)
 {
-	struct drm_i915_gem_object *obj = ifbdev->fb->obj;
+	struct drm_i915_gem_object *obj = intel_fb_obj(&ifbdev->fb->base);
 	unsigned int origin =
 		ifbdev->vma_flags & PLANE_HAS_FENCE ? ORIGIN_GTT : ORIGIN_CPU;
 
@@ -193,7 +193,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 		drm_framebuffer_put(&intel_fb->base);
 		intel_fb = ifbdev->fb = NULL;
 	}
-	if (!intel_fb || WARN_ON(!intel_fb->obj)) {
+	if (!intel_fb || WARN_ON(!intel_fb_obj(&intel_fb->base))) {
 		DRM_DEBUG_KMS("no BIOS fb, allocating a new one\n");
 		ret = intelfb_alloc(helper, sizes);
 		if (ret)
@@ -265,7 +265,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	 * If the object is stolen however, it will be full of whatever
 	 * garbage was left in there.
 	 */
-	if (intel_fb->obj->stolen && !prealloc)
+	if (intel_fb_obj(fb)->stolen && !prealloc)
 		memset_io(info->screen_base, 0, info->screen_size);
 
 	/* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
@@ -792,7 +792,8 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous
 	 * been restored from swap. If the object is stolen however, it will be
 	 * full of whatever garbage was left in there.
 	 */
-	if (state == FBINFO_STATE_RUNNING && ifbdev->fb->obj->stolen)
+	if (state == FBINFO_STATE_RUNNING &&
+	    intel_fb_obj(&ifbdev->fb->base)->stolen)
 		memset_io(info->screen_base, 0, info->screen_size);
 
 	drm_fb_helper_set_suspend(&ifbdev->helper, state);
diff --git a/drivers/gpu/drm/i915/intel_frontbuffer.c b/drivers/gpu/drm/i915/intel_frontbuffer.c
index 7fff0a0eceb4..c3379bde266f 100644
--- a/drivers/gpu/drm/i915/intel_frontbuffer.c
+++ b/drivers/gpu/drm/i915/intel_frontbuffer.c
@@ -153,8 +153,6 @@ void intel_frontbuffer_flip_prepare(struct drm_i915_private *dev_priv,
 	/* Remove stale busy bits due to the old buffer. */
 	dev_priv->fb_tracking.busy_bits &= ~frontbuffer_bits;
 	spin_unlock(&dev_priv->fb_tracking.lock);
-
-	intel_psr_single_frame_update(dev_priv, frontbuffer_bits);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index 116f4ccf1bbd..560c7406ae40 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -27,6 +27,8 @@
 #include "intel_guc_submission.h"
 #include "i915_drv.h"
 
+static void guc_init_ggtt_pin_bias(struct intel_guc *guc);
+
 static void gen8_guc_raise_irq(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
@@ -73,7 +75,7 @@ void intel_guc_init_early(struct intel_guc *guc)
 	guc->notify = gen8_guc_raise_irq;
 }
 
-int intel_guc_init_wq(struct intel_guc *guc)
+static int guc_init_wq(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 
@@ -124,7 +126,7 @@ int intel_guc_init_wq(struct intel_guc *guc)
 	return 0;
 }
 
-void intel_guc_fini_wq(struct intel_guc *guc)
+static void guc_fini_wq(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 
@@ -135,6 +137,28 @@ void intel_guc_fini_wq(struct intel_guc *guc)
 	destroy_workqueue(guc->log.relay.flush_wq);
 }
 
+int intel_guc_init_misc(struct intel_guc *guc)
+{
+	struct drm_i915_private *i915 = guc_to_i915(guc);
+	int ret;
+
+	guc_init_ggtt_pin_bias(guc);
+
+	ret = guc_init_wq(guc);
+	if (ret)
+		return ret;
+
+	intel_uc_fw_fetch(i915, &guc->fw);
+
+	return 0;
+}
+
+void intel_guc_fini_misc(struct intel_guc *guc)
+{
+	intel_uc_fw_fini(&guc->fw);
+	guc_fini_wq(guc);
+}
+
 static int guc_shared_data_create(struct intel_guc *guc)
 {
 	struct i915_vma *vma;
@@ -169,7 +193,7 @@ int intel_guc_init(struct intel_guc *guc)
 
 	ret = guc_shared_data_create(guc);
 	if (ret)
-		return ret;
+		goto err_fetch;
 	GEM_BUG_ON(!guc->shared_data);
 
 	ret = intel_guc_log_create(&guc->log);
@@ -190,6 +214,8 @@ err_log:
 	intel_guc_log_destroy(&guc->log);
 err_shared:
 	guc_shared_data_destroy(guc);
+err_fetch:
+	intel_uc_fw_fini(&guc->fw);
 	return ret;
 }
 
@@ -201,14 +227,17 @@ void intel_guc_fini(struct intel_guc *guc)
 	intel_guc_ads_destroy(guc);
 	intel_guc_log_destroy(&guc->log);
 	guc_shared_data_destroy(guc);
+	intel_uc_fw_fini(&guc->fw);
 }
 
-static u32 get_log_control_flags(void)
+static u32 guc_ctl_debug_flags(struct intel_guc *guc)
 {
-	u32 level = i915_modparams.guc_log_level;
-	u32 flags = 0;
+	u32 level = intel_guc_log_get_level(&guc->log);
+	u32 flags;
+	u32 ads;
 
-	GEM_BUG_ON(level < 0);
+	ads = intel_guc_ggtt_offset(guc, guc->ads_vma) >> PAGE_SHIFT;
+	flags = ads << GUC_ADS_ADDR_SHIFT | GUC_ADS_ENABLED;
 
 	if (!GUC_LOG_LEVEL_IS_ENABLED(level))
 		flags |= GUC_LOG_DEFAULT_DISABLED;
@@ -222,6 +251,78 @@ static u32 get_log_control_flags(void)
 	return flags;
 }
 
+static u32 guc_ctl_feature_flags(struct intel_guc *guc)
+{
+	u32 flags = 0;
+
+	flags |=  GUC_CTL_VCS2_ENABLED;
+
+	if (USES_GUC_SUBMISSION(guc_to_i915(guc)))
+		flags |= GUC_CTL_KERNEL_SUBMISSIONS;
+	else
+		flags |= GUC_CTL_DISABLE_SCHEDULER;
+
+	return flags;
+}
+
+static u32 guc_ctl_ctxinfo_flags(struct intel_guc *guc)
+{
+	u32 flags = 0;
+
+	if (USES_GUC_SUBMISSION(guc_to_i915(guc))) {
+		u32 ctxnum, base;
+
+		base = intel_guc_ggtt_offset(guc, guc->stage_desc_pool);
+		ctxnum = GUC_MAX_STAGE_DESCRIPTORS / 16;
+
+		base >>= PAGE_SHIFT;
+		flags |= (base << GUC_CTL_BASE_ADDR_SHIFT) |
+			(ctxnum << GUC_CTL_CTXNUM_IN16_SHIFT);
+	}
+	return flags;
+}
+
+static u32 guc_ctl_log_params_flags(struct intel_guc *guc)
+{
+	u32 offset = intel_guc_ggtt_offset(guc, guc->log.vma) >> PAGE_SHIFT;
+	u32 flags;
+
+	#if (((CRASH_BUFFER_SIZE) % SZ_1M) == 0)
+	#define UNIT SZ_1M
+	#define FLAG GUC_LOG_ALLOC_IN_MEGABYTE
+	#else
+	#define UNIT SZ_4K
+	#define FLAG 0
+	#endif
+
+	BUILD_BUG_ON(!CRASH_BUFFER_SIZE);
+	BUILD_BUG_ON(!IS_ALIGNED(CRASH_BUFFER_SIZE, UNIT));
+	BUILD_BUG_ON(!DPC_BUFFER_SIZE);
+	BUILD_BUG_ON(!IS_ALIGNED(DPC_BUFFER_SIZE, UNIT));
+	BUILD_BUG_ON(!ISR_BUFFER_SIZE);
+	BUILD_BUG_ON(!IS_ALIGNED(ISR_BUFFER_SIZE, UNIT));
+
+	BUILD_BUG_ON((CRASH_BUFFER_SIZE / UNIT - 1) >
+			(GUC_LOG_CRASH_MASK >> GUC_LOG_CRASH_SHIFT));
+	BUILD_BUG_ON((DPC_BUFFER_SIZE / UNIT - 1) >
+			(GUC_LOG_DPC_MASK >> GUC_LOG_DPC_SHIFT));
+	BUILD_BUG_ON((ISR_BUFFER_SIZE / UNIT - 1) >
+			(GUC_LOG_ISR_MASK >> GUC_LOG_ISR_SHIFT));
+
+	flags = GUC_LOG_VALID |
+		GUC_LOG_NOTIFY_ON_HALF_FULL |
+		FLAG |
+		((CRASH_BUFFER_SIZE / UNIT - 1) << GUC_LOG_CRASH_SHIFT) |
+		((DPC_BUFFER_SIZE / UNIT - 1) << GUC_LOG_DPC_SHIFT) |
+		((ISR_BUFFER_SIZE / UNIT - 1) << GUC_LOG_ISR_SHIFT) |
+		(offset << GUC_LOG_BUF_ADDR_SHIFT);
+
+	#undef UNIT
+	#undef FLAG
+
+	return flags;
+}
+
 /*
  * Initialise the GuC parameter block before starting the firmware
  * transfer. These parameters are read by the firmware on startup
@@ -245,32 +346,13 @@ void intel_guc_init_params(struct intel_guc *guc)
 
 	params[GUC_CTL_WA] |= GUC_CTL_WA_UK_BY_DRIVER;
 
-	params[GUC_CTL_FEATURE] |= GUC_CTL_DISABLE_SCHEDULER |
-			GUC_CTL_VCS2_ENABLED;
-
-	params[GUC_CTL_LOG_PARAMS] = guc->log.flags;
-
-	params[GUC_CTL_DEBUG] = get_log_control_flags();
+	params[GUC_CTL_FEATURE] = guc_ctl_feature_flags(guc);
+	params[GUC_CTL_LOG_PARAMS]  = guc_ctl_log_params_flags(guc);
+	params[GUC_CTL_DEBUG] = guc_ctl_debug_flags(guc);
+	params[GUC_CTL_CTXINFO] = guc_ctl_ctxinfo_flags(guc);
 
-	/* If GuC submission is enabled, set up additional parameters here */
-	if (USES_GUC_SUBMISSION(dev_priv)) {
-		u32 ads = intel_guc_ggtt_offset(guc,
-						guc->ads_vma) >> PAGE_SHIFT;
-		u32 pgs = intel_guc_ggtt_offset(guc, guc->stage_desc_pool);
-		u32 ctx_in_16 = GUC_MAX_STAGE_DESCRIPTORS / 16;
-
-		params[GUC_CTL_DEBUG] |= ads << GUC_ADS_ADDR_SHIFT;
-		params[GUC_CTL_DEBUG] |= GUC_ADS_ENABLED;
-
-		pgs >>= PAGE_SHIFT;
-		params[GUC_CTL_CTXINFO] = (pgs << GUC_CTL_BASE_ADDR_SHIFT) |
-			(ctx_in_16 << GUC_CTL_CTXNUM_IN16_SHIFT);
-
-		params[GUC_CTL_FEATURE] |= GUC_CTL_KERNEL_SUBMISSIONS;
-
-		/* Unmask this bit to enable the GuC's internal scheduler */
-		params[GUC_CTL_FEATURE] &= ~GUC_CTL_DISABLE_SCHEDULER;
-	}
+	for (i = 0; i < GUC_CTL_MAX_DWORDS; i++)
+		DRM_DEBUG_DRIVER("param[%2d] = %#x\n", i, params[i]);
 
 	/*
 	 * All SOFT_SCRATCH registers are in FORCEWAKE_BLITTER domain and
@@ -346,10 +428,8 @@ int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len,
 		ret = -EIO;
 
 	if (ret) {
-		DRM_DEBUG_DRIVER("INTEL_GUC_SEND: Action 0x%X failed;"
-				 " ret=%d status=0x%08X response=0x%08X\n",
-				 action[0], ret, status,
-				 I915_READ(SOFT_SCRATCH(15)));
+		DRM_ERROR("MMIO: GuC action %#x failed with error %d %#x\n",
+			  action[0], ret, status);
 		goto out;
 	}
 
@@ -386,11 +466,13 @@ void intel_guc_to_host_event_handler_mmio(struct intel_guc *guc)
 	 * could happen that GuC sets the bit for 2nd interrupt but Host
 	 * clears out the bit on handling the 1st interrupt.
 	 */
+	disable_rpm_wakeref_asserts(dev_priv);
 	spin_lock(&guc->irq_lock);
 	val = I915_READ(SOFT_SCRATCH(15));
 	msg = val & guc->msg_enabled_mask;
 	I915_WRITE(SOFT_SCRATCH(15), val & ~msg);
 	spin_unlock(&guc->irq_lock);
+	enable_rpm_wakeref_asserts(dev_priv);
 
 	intel_guc_to_host_process_recv_msg(guc, msg);
 }
@@ -532,13 +614,13 @@ int intel_guc_resume(struct intel_guc *guc)
  */
 
 /**
- * intel_guc_init_ggtt_pin_bias() - Initialize the GuC ggtt_pin_bias value.
+ * guc_init_ggtt_pin_bias() - Initialize the GuC ggtt_pin_bias value.
  * @guc: intel_guc structure.
  *
  * This function will calculate and initialize the ggtt_pin_bias value based on
  * overall WOPCM size and GuC WOPCM size.
  */
-void intel_guc_init_ggtt_pin_bias(struct intel_guc *guc)
+static void guc_init_ggtt_pin_bias(struct intel_guc *guc)
 {
 	struct drm_i915_private *i915 = guc_to_i915(guc);
 
@@ -572,7 +654,7 @@ struct i915_vma *intel_guc_allocate_vma(struct intel_guc *guc, u32 size)
 	if (IS_ERR(obj))
 		return ERR_CAST(obj);
 
-	vma = i915_vma_instance(obj, &dev_priv->ggtt.base, NULL);
+	vma = i915_vma_instance(obj, &dev_priv->ggtt.vm, NULL);
 	if (IS_ERR(vma))
 		goto err;
 
diff --git a/drivers/gpu/drm/i915/intel_guc.h b/drivers/gpu/drm/i915/intel_guc.h
index f1265e122d30..4121928a495e 100644
--- a/drivers/gpu/drm/i915/intel_guc.h
+++ b/drivers/gpu/drm/i915/intel_guc.h
@@ -151,11 +151,10 @@ static inline u32 intel_guc_ggtt_offset(struct intel_guc *guc,
 void intel_guc_init_early(struct intel_guc *guc);
 void intel_guc_init_send_regs(struct intel_guc *guc);
 void intel_guc_init_params(struct intel_guc *guc);
-void intel_guc_init_ggtt_pin_bias(struct intel_guc *guc);
-int intel_guc_init_wq(struct intel_guc *guc);
-void intel_guc_fini_wq(struct intel_guc *guc);
+int intel_guc_init_misc(struct intel_guc *guc);
 int intel_guc_init(struct intel_guc *guc);
 void intel_guc_fini(struct intel_guc *guc);
+void intel_guc_fini_misc(struct intel_guc *guc);
 int intel_guc_send_nop(struct intel_guc *guc, const u32 *action, u32 len,
 		       u32 *response_buf, u32 response_buf_size);
 int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len,
diff --git a/drivers/gpu/drm/i915/intel_guc_fwif.h b/drivers/gpu/drm/i915/intel_guc_fwif.h
index 0867ba76d445..1a0f2a39cef9 100644
--- a/drivers/gpu/drm/i915/intel_guc_fwif.h
+++ b/drivers/gpu/drm/i915/intel_guc_fwif.h
@@ -84,12 +84,12 @@
 #define   GUC_LOG_VALID			(1 << 0)
 #define   GUC_LOG_NOTIFY_ON_HALF_FULL	(1 << 1)
 #define   GUC_LOG_ALLOC_IN_MEGABYTE	(1 << 3)
-#define   GUC_LOG_CRASH_PAGES		1
 #define   GUC_LOG_CRASH_SHIFT		4
-#define   GUC_LOG_DPC_PAGES		7
+#define   GUC_LOG_CRASH_MASK		(0x1 << GUC_LOG_CRASH_SHIFT)
 #define   GUC_LOG_DPC_SHIFT		6
-#define   GUC_LOG_ISR_PAGES		7
+#define   GUC_LOG_DPC_MASK	        (0x7 << GUC_LOG_DPC_SHIFT)
 #define   GUC_LOG_ISR_SHIFT		9
+#define   GUC_LOG_ISR_MASK	        (0x7 << GUC_LOG_ISR_SHIFT)
 #define   GUC_LOG_BUF_ADDR_SHIFT	12
 
 #define GUC_CTL_PAGE_FAULT_CONTROL	5
@@ -532,20 +532,6 @@ enum guc_log_buffer_type {
 };
 
 /**
- * DOC: GuC Log buffer Layout
- *
- * Page0  +-------------------------------+
- *        |   ISR state header (32 bytes) |
- *        |      DPC state header         |
- *        |   Crash dump state header     |
- * Page1  +-------------------------------+
- *        |           ISR logs            |
- * Page9  +-------------------------------+
- *        |           DPC logs            |
- * Page17 +-------------------------------+
- *        |         Crash Dump logs       |
- *        +-------------------------------+
- *
  * Below state structure is used for coordination of retrieval of GuC firmware
  * logs. Separate state is maintained for each log buffer type.
  * read_ptr points to the location where i915 read last in log buffer and
diff --git a/drivers/gpu/drm/i915/intel_guc_log.c b/drivers/gpu/drm/i915/intel_guc_log.c
index 401e1704d61e..6da61a71d28f 100644
--- a/drivers/gpu/drm/i915/intel_guc_log.c
+++ b/drivers/gpu/drm/i915/intel_guc_log.c
@@ -215,11 +215,11 @@ static unsigned int guc_get_log_buffer_size(enum guc_log_buffer_type type)
 {
 	switch (type) {
 	case GUC_ISR_LOG_BUFFER:
-		return (GUC_LOG_ISR_PAGES + 1) * PAGE_SIZE;
+		return ISR_BUFFER_SIZE;
 	case GUC_DPC_LOG_BUFFER:
-		return (GUC_LOG_DPC_PAGES + 1) * PAGE_SIZE;
+		return DPC_BUFFER_SIZE;
 	case GUC_CRASH_DUMP_LOG_BUFFER:
-		return (GUC_LOG_CRASH_PAGES + 1) * PAGE_SIZE;
+		return CRASH_BUFFER_SIZE;
 	default:
 		MISSING_CASE(type);
 	}
@@ -397,7 +397,7 @@ static int guc_log_relay_create(struct intel_guc_log *log)
 	lockdep_assert_held(&log->relay.lock);
 
 	 /* Keep the size of sub buffers same as shared log buffer */
-	subbuf_size = GUC_LOG_SIZE;
+	subbuf_size = log->vma->size;
 
 	/*
 	 * Store up to 8 snapshots, which is large enough to buffer sufficient
@@ -452,13 +452,34 @@ int intel_guc_log_create(struct intel_guc_log *log)
 {
 	struct intel_guc *guc = log_to_guc(log);
 	struct i915_vma *vma;
-	unsigned long offset;
-	u32 flags;
+	u32 guc_log_size;
 	int ret;
 
 	GEM_BUG_ON(log->vma);
 
-	vma = intel_guc_allocate_vma(guc, GUC_LOG_SIZE);
+	/*
+	 *  GuC Log buffer Layout
+	 *
+	 *  +===============================+ 00B
+	 *  |    Crash dump state header    |
+	 *  +-------------------------------+ 32B
+	 *  |       DPC state header        |
+	 *  +-------------------------------+ 64B
+	 *  |       ISR state header        |
+	 *  +-------------------------------+ 96B
+	 *  |                               |
+	 *  +===============================+ PAGE_SIZE (4KB)
+	 *  |        Crash Dump logs        |
+	 *  +===============================+ + CRASH_SIZE
+	 *  |           DPC logs            |
+	 *  +===============================+ + DPC_SIZE
+	 *  |           ISR logs            |
+	 *  +===============================+ + ISR_SIZE
+	 */
+	guc_log_size = PAGE_SIZE + CRASH_BUFFER_SIZE + DPC_BUFFER_SIZE +
+			ISR_BUFFER_SIZE;
+
+	vma = intel_guc_allocate_vma(guc, guc_log_size);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto err;
@@ -466,20 +487,12 @@ int intel_guc_log_create(struct intel_guc_log *log)
 
 	log->vma = vma;
 
-	/* each allocated unit is a page */
-	flags = GUC_LOG_VALID | GUC_LOG_NOTIFY_ON_HALF_FULL |
-		(GUC_LOG_DPC_PAGES << GUC_LOG_DPC_SHIFT) |
-		(GUC_LOG_ISR_PAGES << GUC_LOG_ISR_SHIFT) |
-		(GUC_LOG_CRASH_PAGES << GUC_LOG_CRASH_SHIFT);
-
-	offset = intel_guc_ggtt_offset(guc, vma) >> PAGE_SHIFT;
-	log->flags = (offset << GUC_LOG_BUF_ADDR_SHIFT) | flags;
+	log->level = i915_modparams.guc_log_level;
 
 	return 0;
 
 err:
-	/* logging will be off */
-	i915_modparams.guc_log_level = 0;
+	DRM_ERROR("Failed to allocate GuC log buffer. %d\n", ret);
 	return ret;
 }
 
@@ -488,15 +501,7 @@ void intel_guc_log_destroy(struct intel_guc_log *log)
 	i915_vma_unpin_and_release(&log->vma);
 }
 
-int intel_guc_log_level_get(struct intel_guc_log *log)
-{
-	GEM_BUG_ON(!log->vma);
-	GEM_BUG_ON(i915_modparams.guc_log_level < 0);
-
-	return i915_modparams.guc_log_level;
-}
-
-int intel_guc_log_level_set(struct intel_guc_log *log, u64 val)
+int intel_guc_log_set_level(struct intel_guc_log *log, u32 level)
 {
 	struct intel_guc *guc = log_to_guc(log);
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
@@ -504,33 +509,32 @@ int intel_guc_log_level_set(struct intel_guc_log *log, u64 val)
 
 	BUILD_BUG_ON(GUC_LOG_VERBOSITY_MIN != 0);
 	GEM_BUG_ON(!log->vma);
-	GEM_BUG_ON(i915_modparams.guc_log_level < 0);
 
 	/*
 	 * GuC is recognizing log levels starting from 0 to max, we're using 0
 	 * as indication that logging should be disabled.
 	 */
-	if (val < GUC_LOG_LEVEL_DISABLED || val > GUC_LOG_LEVEL_MAX)
+	if (level < GUC_LOG_LEVEL_DISABLED || level > GUC_LOG_LEVEL_MAX)
 		return -EINVAL;
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
 
-	if (i915_modparams.guc_log_level == val) {
+	if (log->level == level) {
 		ret = 0;
 		goto out_unlock;
 	}
 
 	intel_runtime_pm_get(dev_priv);
-	ret = guc_action_control_log(guc, GUC_LOG_LEVEL_IS_VERBOSE(val),
-				     GUC_LOG_LEVEL_IS_ENABLED(val),
-				     GUC_LOG_LEVEL_TO_VERBOSITY(val));
+	ret = guc_action_control_log(guc, GUC_LOG_LEVEL_IS_VERBOSE(level),
+				     GUC_LOG_LEVEL_IS_ENABLED(level),
+				     GUC_LOG_LEVEL_TO_VERBOSITY(level));
 	intel_runtime_pm_put(dev_priv);
 	if (ret) {
 		DRM_DEBUG_DRIVER("guc_log_control action failed %d\n", ret);
 		goto out_unlock;
 	}
 
-	i915_modparams.guc_log_level = val;
+	log->level = level;
 
 out_unlock:
 	mutex_unlock(&dev_priv->drm.struct_mutex);
diff --git a/drivers/gpu/drm/i915/intel_guc_log.h b/drivers/gpu/drm/i915/intel_guc_log.h
index fa80535a6f9d..7bc763f10c03 100644
--- a/drivers/gpu/drm/i915/intel_guc_log.h
+++ b/drivers/gpu/drm/i915/intel_guc_log.h
@@ -30,15 +30,19 @@
 #include <linux/workqueue.h>
 
 #include "intel_guc_fwif.h"
+#include "i915_gem.h"
 
 struct intel_guc;
 
-/*
- * The first page is to save log buffer state. Allocate one
- * extra page for others in case for overlap
- */
-#define GUC_LOG_SIZE	((1 + GUC_LOG_DPC_PAGES + 1 + GUC_LOG_ISR_PAGES + \
-			  1 + GUC_LOG_CRASH_PAGES + 1) << PAGE_SHIFT)
+#ifdef CONFIG_DRM_I915_DEBUG_GUC
+#define CRASH_BUFFER_SIZE	SZ_2M
+#define DPC_BUFFER_SIZE		SZ_8M
+#define ISR_BUFFER_SIZE		SZ_8M
+#else
+#define CRASH_BUFFER_SIZE	SZ_8K
+#define DPC_BUFFER_SIZE		SZ_32K
+#define ISR_BUFFER_SIZE		SZ_32K
+#endif
 
 /*
  * While we're using plain log level in i915, GuC controls are much more...
@@ -58,7 +62,7 @@ struct intel_guc;
 #define GUC_LOG_LEVEL_MAX GUC_VERBOSITY_TO_LOG_LEVEL(GUC_LOG_VERBOSITY_MAX)
 
 struct intel_guc_log {
-	u32 flags;
+	u32 level;
 	struct i915_vma *vma;
 	struct {
 		void *buf_addr;
@@ -80,8 +84,7 @@ void intel_guc_log_init_early(struct intel_guc_log *log);
 int intel_guc_log_create(struct intel_guc_log *log);
 void intel_guc_log_destroy(struct intel_guc_log *log);
 
-int intel_guc_log_level_get(struct intel_guc_log *log);
-int intel_guc_log_level_set(struct intel_guc_log *log, u64 control_val);
+int intel_guc_log_set_level(struct intel_guc_log *log, u32 level);
 bool intel_guc_log_relay_enabled(const struct intel_guc_log *log);
 int intel_guc_log_relay_open(struct intel_guc_log *log);
 void intel_guc_log_relay_flush(struct intel_guc_log *log);
@@ -89,4 +92,9 @@ void intel_guc_log_relay_close(struct intel_guc_log *log);
 
 void intel_guc_log_handle_flush_event(struct intel_guc_log *log);
 
+static inline u32 intel_guc_log_get_level(struct intel_guc_log *log)
+{
+	return log->level;
+}
+
 #endif
diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index 2feb65096966..4aa5e6463e7b 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -513,8 +513,7 @@ static void guc_add_request(struct intel_guc *guc, struct i915_request *rq)
 {
 	struct intel_guc_client *client = guc->execbuf_client;
 	struct intel_engine_cs *engine = rq->engine;
-	u32 ctx_desc = lower_32_bits(intel_lr_context_descriptor(rq->ctx,
-								 engine));
+	u32 ctx_desc = lower_32_bits(rq->hw_context->lrc_desc);
 	u32 ring_tail = intel_ring_set_tail(rq->ring, rq->tail) / sizeof(u64);
 
 	spin_lock(&client->wq_lock);
@@ -537,7 +536,7 @@ static void guc_add_request(struct intel_guc *guc, struct i915_request *rq)
  */
 static void flush_ggtt_writes(struct i915_vma *vma)
 {
-	struct drm_i915_private *dev_priv = to_i915(vma->obj->base.dev);
+	struct drm_i915_private *dev_priv = vma->vm->i915;
 
 	if (i915_vma_is_map_and_fenceable(vma))
 		POSTING_READ_FW(GUC_STATUS);
@@ -552,8 +551,8 @@ static void inject_preempt_context(struct work_struct *work)
 					     preempt_work[engine->id]);
 	struct intel_guc_client *client = guc->preempt_client;
 	struct guc_stage_desc *stage_desc = __get_stage_desc(client);
-	u32 ctx_desc = lower_32_bits(intel_lr_context_descriptor(client->owner,
-								 engine));
+	u32 ctx_desc = lower_32_bits(to_intel_context(client->owner,
+						      engine)->lrc_desc);
 	u32 data[7];
 
 	/*
@@ -623,6 +622,22 @@ static void wait_for_guc_preempt_report(struct intel_engine_cs *engine)
 	report->report_return_status = INTEL_GUC_REPORT_STATUS_UNKNOWN;
 }
 
+static void complete_preempt_context(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists *execlists = &engine->execlists;
+
+	GEM_BUG_ON(!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT));
+
+	if (inject_preempt_hang(execlists))
+		return;
+
+	execlists_cancel_port_requests(execlists);
+	execlists_unwind_incomplete_requests(execlists);
+
+	wait_for_guc_preempt_report(engine);
+	intel_write_status_page(engine, I915_GEM_HWS_PREEMPT_INDEX, 0);
+}
+
 /**
  * guc_submit() - Submit commands through GuC
  * @engine: engine associated with the commands
@@ -681,9 +696,6 @@ static bool __guc_dequeue(struct intel_engine_cs *engine)
 
 	lockdep_assert_held(&engine->timeline.lock);
 
-	rb = execlists->first;
-	GEM_BUG_ON(rb_first(&execlists->queue) != rb);
-
 	if (port_isset(port)) {
 		if (intel_engine_has_preemption(engine)) {
 			struct guc_preempt_work *preempt_work =
@@ -705,12 +717,12 @@ static bool __guc_dequeue(struct intel_engine_cs *engine)
 	}
 	GEM_BUG_ON(port_isset(port));
 
-	while (rb) {
+	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 		struct i915_request *rq, *rn;
 
 		list_for_each_entry_safe(rq, rn, &p->requests, sched.link) {
-			if (last && rq->ctx != last->ctx) {
+			if (last && rq->hw_context != last->hw_context) {
 				if (port == last_port) {
 					__list_del_many(&p->requests,
 							&rq->sched.link);
@@ -730,15 +742,13 @@ static bool __guc_dequeue(struct intel_engine_cs *engine)
 			submit = true;
 		}
 
-		rb = rb_next(rb);
-		rb_erase(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &execlists->queue);
 		INIT_LIST_HEAD(&p->requests);
 		if (p->priority != I915_PRIORITY_NORMAL)
 			kmem_cache_free(engine->i915->priorities, p);
 	}
 done:
 	execlists->queue_priority = rb ? to_priolist(rb)->priority : INT_MIN;
-	execlists->first = rb;
 	if (submit)
 		port_assign(port, last);
 	if (last)
@@ -747,7 +757,8 @@ done:
 	/* We must always keep the beast fed if we have work piled up */
 	GEM_BUG_ON(port_isset(execlists->port) &&
 		   !execlists_is_active(execlists, EXECLISTS_ACTIVE_USER));
-	GEM_BUG_ON(execlists->first && !port_isset(execlists->port));
+	GEM_BUG_ON(rb_first_cached(&execlists->queue) &&
+		   !port_isset(execlists->port));
 
 	return submit;
 }
@@ -793,20 +804,44 @@ static void guc_submission_tasklet(unsigned long data)
 
 	if (execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT) &&
 	    intel_read_status_page(engine, I915_GEM_HWS_PREEMPT_INDEX) ==
-	    GUC_PREEMPT_FINISHED) {
-		execlists_cancel_port_requests(&engine->execlists);
-		execlists_unwind_incomplete_requests(execlists);
-
-		wait_for_guc_preempt_report(engine);
-
-		execlists_clear_active(execlists, EXECLISTS_ACTIVE_PREEMPT);
-		intel_write_status_page(engine, I915_GEM_HWS_PREEMPT_INDEX, 0);
-	}
+	    GUC_PREEMPT_FINISHED)
+		complete_preempt_context(engine);
 
 	if (!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT))
 		guc_dequeue(engine);
 }
 
+static struct i915_request *
+guc_reset_prepare(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists * const execlists = &engine->execlists;
+
+	GEM_TRACE("%s\n", engine->name);
+
+	/*
+	 * Prevent request submission to the hardware until we have
+	 * completed the reset in i915_gem_reset_finish(). If a request
+	 * is completed by one engine, it may then queue a request
+	 * to a second via its execlists->tasklet *just* as we are
+	 * calling engine->init_hw() and also writing the ELSP.
+	 * Turning off the execlists->tasklet until the reset is over
+	 * prevents the race.
+	 */
+	__tasklet_disable_sync_once(&execlists->tasklet);
+
+	/*
+	 * We're using worker to queue preemption requests from the tasklet in
+	 * GuC submission mode.
+	 * Even though tasklet was disabled, we may still have a worker queued.
+	 * Let's make sure that all workers scheduled before disabling the
+	 * tasklet are completed before continuing with the reset.
+	 */
+	if (engine->i915->guc.preempt_wq)
+		flush_workqueue(engine->i915->guc.preempt_wq);
+
+	return i915_gem_find_active_request(engine);
+}
+
 /*
  * Everything below here is concerned with setup & teardown, and is
  * therefore not part of the somewhat time-critical batch-submission
@@ -876,8 +911,12 @@ static void guc_clients_doorbell_fini(struct intel_guc *guc)
 		__update_doorbell_desc(guc->preempt_client,
 				       GUC_DOORBELL_INVALID);
 	}
-	__destroy_doorbell(guc->execbuf_client);
-	__update_doorbell_desc(guc->execbuf_client, GUC_DOORBELL_INVALID);
+
+	if (guc->execbuf_client) {
+		__destroy_doorbell(guc->execbuf_client);
+		__update_doorbell_desc(guc->execbuf_client,
+				       GUC_DOORBELL_INVALID);
+	}
 }
 
 /**
@@ -1090,7 +1129,8 @@ static void guc_clients_destroy(struct intel_guc *guc)
 		guc_client_free(client);
 
 	client = fetch_and_zero(&guc->execbuf_client);
-	guc_client_free(client);
+	if (client)
+		guc_client_free(client);
 }
 
 /*
@@ -1119,7 +1159,7 @@ int intel_guc_submission_init(struct intel_guc *guc)
 	WARN_ON(!guc_verify_doorbells(guc));
 	ret = guc_clients_create(guc);
 	if (ret)
-		return ret;
+		goto err_pool;
 
 	for_each_engine(engine, dev_priv, id) {
 		guc->preempt_work[id].engine = engine;
@@ -1128,6 +1168,9 @@ int intel_guc_submission_init(struct intel_guc *guc)
 
 	return 0;
 
+err_pool:
+	guc_stage_desc_pool_destroy(guc);
+	return ret;
 }
 
 void intel_guc_submission_fini(struct intel_guc *guc)
@@ -1142,7 +1185,8 @@ void intel_guc_submission_fini(struct intel_guc *guc)
 	guc_clients_destroy(guc);
 	WARN_ON(!guc_verify_doorbells(guc));
 
-	guc_stage_desc_pool_destroy(guc);
+	if (guc->stage_desc_pool)
+		guc_stage_desc_pool_destroy(guc);
 }
 
 static void guc_interrupts_capture(struct drm_i915_private *dev_priv)
@@ -1225,6 +1269,31 @@ static void guc_submission_unpark(struct intel_engine_cs *engine)
 	intel_engine_pin_breadcrumbs_irq(engine);
 }
 
+static void guc_set_default_submission(struct intel_engine_cs *engine)
+{
+	/*
+	 * We inherit a bunch of functions from execlists that we'd like
+	 * to keep using:
+	 *
+	 *    engine->submit_request = execlists_submit_request;
+	 *    engine->cancel_requests = execlists_cancel_requests;
+	 *    engine->schedule = execlists_schedule;
+	 *
+	 * But we need to override the actual submission backend in order
+	 * to talk to the GuC.
+	 */
+	intel_execlists_set_default_submission(engine);
+
+	engine->execlists.tasklet.func = guc_submission_tasklet;
+
+	engine->park = guc_submission_park;
+	engine->unpark = guc_submission_unpark;
+
+	engine->reset.prepare = guc_reset_prepare;
+
+	engine->flags &= ~I915_ENGINE_SUPPORTS_STATS;
+}
+
 int intel_guc_submission_enable(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
@@ -1263,14 +1332,8 @@ int intel_guc_submission_enable(struct intel_guc *guc)
 	guc_interrupts_capture(dev_priv);
 
 	for_each_engine(engine, dev_priv, id) {
-		struct intel_engine_execlists * const execlists =
-			&engine->execlists;
-
-		execlists->tasklet.func = guc_submission_tasklet;
-		engine->park = guc_submission_park;
-		engine->unpark = guc_submission_unpark;
-
-		engine->flags &= ~I915_ENGINE_SUPPORTS_STATS;
+		engine->set_default_submission = guc_set_default_submission;
+		engine->set_default_submission(engine);
 	}
 
 	return 0;
@@ -1284,9 +1347,6 @@ void intel_guc_submission_disable(struct intel_guc *guc)
 
 	guc_interrupts_release(dev_priv);
 	guc_clients_doorbell_fini(guc);
-
-	/* Revert back to manual ELSP submission */
-	intel_engines_reset_default_submission(dev_priv);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c
index a2fe7c8d4477..c22b3e18a0f5 100644
--- a/drivers/gpu/drm/i915/intel_gvt.c
+++ b/drivers/gpu/drm/i915/intel_gvt.c
@@ -47,6 +47,8 @@ static bool is_supported_device(struct drm_i915_private *dev_priv)
 		return true;
 	if (IS_KABYLAKE(dev_priv))
 		return true;
+	if (IS_BROXTON(dev_priv))
+		return true;
 	return false;
 }
 
@@ -90,6 +92,9 @@ int intel_gvt_init(struct drm_i915_private *dev_priv)
 {
 	int ret;
 
+	if (i915_inject_load_failure())
+		return -ENODEV;
+
 	if (!i915_modparams.enable_gvt) {
 		DRM_DEBUG_DRIVER("GVT-g is disabled by kernel params\n");
 		return 0;
diff --git a/drivers/gpu/drm/i915/intel_hangcheck.c b/drivers/gpu/drm/i915/intel_hangcheck.c
index d47e346bd49e..2fc7a0dd0df9 100644
--- a/drivers/gpu/drm/i915/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/intel_hangcheck.c
@@ -294,6 +294,7 @@ static void hangcheck_store_sample(struct intel_engine_cs *engine,
 	engine->hangcheck.seqno = hc->seqno;
 	engine->hangcheck.action = hc->action;
 	engine->hangcheck.stalled = hc->stalled;
+	engine->hangcheck.wedged = hc->wedged;
 }
 
 static enum intel_engine_hangcheck_action
@@ -368,6 +369,9 @@ static void hangcheck_accumulate_sample(struct intel_engine_cs *engine,
 
 	hc->stalled = time_after(jiffies,
 				 engine->hangcheck.action_timestamp + timeout);
+	hc->wedged = time_after(jiffies,
+				 engine->hangcheck.action_timestamp +
+				 I915_ENGINE_WEDGED_TIMEOUT);
 }
 
 static void hangcheck_declare_hang(struct drm_i915_private *i915,
@@ -409,7 +413,7 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 			     gpu_error.hangcheck_work.work);
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	unsigned int hung = 0, stuck = 0;
+	unsigned int hung = 0, stuck = 0, wedged = 0;
 
 	if (!i915_modparams.enable_hangcheck)
 		return;
@@ -440,6 +444,17 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 			if (hc.action != ENGINE_DEAD)
 				stuck |= intel_engine_flag(engine);
 		}
+
+		if (engine->hangcheck.wedged)
+			wedged |= intel_engine_flag(engine);
+	}
+
+	if (wedged) {
+		dev_err(dev_priv->drm.dev,
+			"GPU recovery timed out,"
+			" cancelling all in-flight rendering.\n");
+		GEM_TRACE_DUMP();
+		i915_gem_set_wedged(dev_priv);
 	}
 
 	if (hung)
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index d8cb53ef4351..8363fbd18ee8 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -51,7 +51,7 @@ assert_hdmi_port_disabled(struct intel_hdmi *intel_hdmi)
 {
 	struct drm_device *dev = intel_hdmi_to_dev(intel_hdmi);
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	uint32_t enabled_bits;
+	u32 enabled_bits;
 
 	enabled_bits = HAS_DDI(dev_priv) ? DDI_BUF_CTL_ENABLE : SDVO_ENABLE;
 
@@ -59,6 +59,15 @@ assert_hdmi_port_disabled(struct intel_hdmi *intel_hdmi)
 	     "HDMI port enabled, expecting disabled\n");
 }
 
+static void
+assert_hdmi_transcoder_func_disabled(struct drm_i915_private *dev_priv,
+				     enum transcoder cpu_transcoder)
+{
+	WARN(I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder)) &
+	     TRANS_DDI_FUNC_ENABLE,
+	     "HDMI transcoder function enabled, expecting disabled\n");
+}
+
 struct intel_hdmi *enc_to_intel_hdmi(struct drm_encoder *encoder)
 {
 	struct intel_digital_port *intel_dig_port =
@@ -144,7 +153,7 @@ static void g4x_write_infoframe(struct drm_encoder *encoder,
 				unsigned int type,
 				const void *frame, ssize_t len)
 {
-	const uint32_t *data = frame;
+	const u32 *data = frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 val = I915_READ(VIDEO_DIP_CTL);
@@ -199,7 +208,7 @@ static void ibx_write_infoframe(struct drm_encoder *encoder,
 				unsigned int type,
 				const void *frame, ssize_t len)
 {
-	const uint32_t *data = frame;
+	const u32 *data = frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
@@ -259,7 +268,7 @@ static void cpt_write_infoframe(struct drm_encoder *encoder,
 				unsigned int type,
 				const void *frame, ssize_t len)
 {
-	const uint32_t *data = frame;
+	const u32 *data = frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
@@ -317,7 +326,7 @@ static void vlv_write_infoframe(struct drm_encoder *encoder,
 				unsigned int type,
 				const void *frame, ssize_t len)
 {
-	const uint32_t *data = frame;
+	const u32 *data = frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
@@ -376,19 +385,16 @@ static void hsw_write_infoframe(struct drm_encoder *encoder,
 				unsigned int type,
 				const void *frame, ssize_t len)
 {
-	const uint32_t *data = frame;
+	const u32 *data = frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 	i915_reg_t ctl_reg = HSW_TVIDEO_DIP_CTL(cpu_transcoder);
-	i915_reg_t data_reg;
 	int data_size = type == DP_SDP_VSC ?
 		VIDEO_DIP_VSC_DATA_SIZE : VIDEO_DIP_DATA_SIZE;
 	int i;
 	u32 val = I915_READ(ctl_reg);
 
-	data_reg = hsw_dip_data_reg(dev_priv, cpu_transcoder, type, 0);
-
 	val &= ~hsw_infoframe_enable(type);
 	I915_WRITE(ctl_reg, val);
 
@@ -442,7 +448,7 @@ static void intel_write_infoframe(struct drm_encoder *encoder,
 				  union hdmi_infoframe *frame)
 {
 	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
-	uint8_t buffer[VIDEO_DIP_DATA_SIZE];
+	u8 buffer[VIDEO_DIP_DATA_SIZE];
 	ssize_t len;
 
 	/* see comment above for the reason for this offset */
@@ -461,7 +467,8 @@ static void intel_write_infoframe(struct drm_encoder *encoder,
 }
 
 static void intel_hdmi_set_avi_infoframe(struct drm_encoder *encoder,
-					 const struct intel_crtc_state *crtc_state)
+					 const struct intel_crtc_state *crtc_state,
+					 const struct drm_connector_state *conn_state)
 {
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	const struct drm_display_mode *adjusted_mode =
@@ -491,6 +498,9 @@ static void intel_hdmi_set_avi_infoframe(struct drm_encoder *encoder,
 					   intel_hdmi->rgb_quant_range_selectable,
 					   is_hdmi2_sink);
 
+	drm_hdmi_avi_infoframe_content_type(&frame.avi,
+					    conn_state);
+
 	/* TODO: handle pixel repetition for YCBCR420 outputs */
 	intel_write_infoframe(encoder, crtc_state, &frame);
 }
@@ -586,7 +596,7 @@ static void g4x_set_infoframes(struct drm_encoder *encoder,
 	I915_WRITE(reg, val);
 	POSTING_READ(reg);
 
-	intel_hdmi_set_avi_infoframe(encoder, crtc_state);
+	intel_hdmi_set_avi_infoframe(encoder, crtc_state, conn_state);
 	intel_hdmi_set_spd_infoframe(encoder, crtc_state);
 	intel_hdmi_set_hdmi_infoframe(encoder, crtc_state, conn_state);
 }
@@ -727,7 +737,7 @@ static void ibx_set_infoframes(struct drm_encoder *encoder,
 	I915_WRITE(reg, val);
 	POSTING_READ(reg);
 
-	intel_hdmi_set_avi_infoframe(encoder, crtc_state);
+	intel_hdmi_set_avi_infoframe(encoder, crtc_state, conn_state);
 	intel_hdmi_set_spd_infoframe(encoder, crtc_state);
 	intel_hdmi_set_hdmi_infoframe(encoder, crtc_state, conn_state);
 }
@@ -770,7 +780,7 @@ static void cpt_set_infoframes(struct drm_encoder *encoder,
 	I915_WRITE(reg, val);
 	POSTING_READ(reg);
 
-	intel_hdmi_set_avi_infoframe(encoder, crtc_state);
+	intel_hdmi_set_avi_infoframe(encoder, crtc_state, conn_state);
 	intel_hdmi_set_spd_infoframe(encoder, crtc_state);
 	intel_hdmi_set_hdmi_infoframe(encoder, crtc_state, conn_state);
 }
@@ -823,7 +833,7 @@ static void vlv_set_infoframes(struct drm_encoder *encoder,
 	I915_WRITE(reg, val);
 	POSTING_READ(reg);
 
-	intel_hdmi_set_avi_infoframe(encoder, crtc_state);
+	intel_hdmi_set_avi_infoframe(encoder, crtc_state, conn_state);
 	intel_hdmi_set_spd_infoframe(encoder, crtc_state);
 	intel_hdmi_set_hdmi_infoframe(encoder, crtc_state, conn_state);
 }
@@ -834,11 +844,11 @@ static void hsw_set_infoframes(struct drm_encoder *encoder,
 			       const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->dev);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	i915_reg_t reg = HSW_TVIDEO_DIP_CTL(crtc_state->cpu_transcoder);
 	u32 val = I915_READ(reg);
 
-	assert_hdmi_port_disabled(intel_hdmi);
+	assert_hdmi_transcoder_func_disabled(dev_priv,
+					     crtc_state->cpu_transcoder);
 
 	val &= ~(VIDEO_DIP_ENABLE_VSC_HSW | VIDEO_DIP_ENABLE_AVI_HSW |
 		 VIDEO_DIP_ENABLE_GCP_HSW | VIDEO_DIP_ENABLE_VS_HSW |
@@ -856,7 +866,7 @@ static void hsw_set_infoframes(struct drm_encoder *encoder,
 	I915_WRITE(reg, val);
 	POSTING_READ(reg);
 
-	intel_hdmi_set_avi_infoframe(encoder, crtc_state);
+	intel_hdmi_set_avi_infoframe(encoder, crtc_state, conn_state);
 	intel_hdmi_set_spd_infoframe(encoder, crtc_state);
 	intel_hdmi_set_hdmi_infoframe(encoder, crtc_state, conn_state);
 }
@@ -1161,33 +1171,16 @@ static void intel_hdmi_prepare(struct intel_encoder *encoder,
 static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder,
 				    enum pipe *pipe)
 {
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
-	u32 tmp;
 	bool ret;
 
 	if (!intel_display_power_get_if_enabled(dev_priv,
 						encoder->power_domain))
 		return false;
 
-	ret = false;
+	ret = intel_sdvo_port_enabled(dev_priv, intel_hdmi->hdmi_reg, pipe);
 
-	tmp = I915_READ(intel_hdmi->hdmi_reg);
-
-	if (!(tmp & SDVO_ENABLE))
-		goto out;
-
-	if (HAS_PCH_CPT(dev_priv))
-		*pipe = PORT_TO_PIPE_CPT(tmp);
-	else if (IS_CHERRYVIEW(dev_priv))
-		*pipe = SDVO_PORT_TO_PIPE_CHV(tmp);
-	else
-		*pipe = PORT_TO_PIPE(tmp);
-
-	ret = true;
-
-out:
 	intel_display_power_put(dev_priv, encoder->power_domain);
 
 	return ret;
@@ -1421,8 +1414,8 @@ static void intel_disable_hdmi(struct intel_encoder *encoder,
 		intel_set_cpu_fifo_underrun_reporting(dev_priv, PIPE_A, false);
 		intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, false);
 
-		temp &= ~SDVO_PIPE_B_SELECT;
-		temp |= SDVO_ENABLE;
+		temp &= ~SDVO_PIPE_SEL_MASK;
+		temp |= SDVO_ENABLE | SDVO_PIPE_SEL(PIPE_A);
 		/*
 		 * HW workaround, need to write this twice for issue
 		 * that may result in first write getting masked.
@@ -1577,14 +1570,23 @@ intel_hdmi_mode_valid(struct drm_connector *connector,
 	/* check if we can do 8bpc */
 	status = hdmi_port_clock_valid(hdmi, clock, true, force_dvi);
 
-	/* if we can't do 8bpc we may still be able to do 12bpc */
-	if (!HAS_GMCH_DISPLAY(dev_priv) && status != MODE_OK && hdmi->has_hdmi_sink && !force_dvi)
-		status = hdmi_port_clock_valid(hdmi, clock * 3 / 2, true, force_dvi);
+	if (hdmi->has_hdmi_sink && !force_dvi) {
+		/* if we can't do 8bpc we may still be able to do 12bpc */
+		if (status != MODE_OK && !HAS_GMCH_DISPLAY(dev_priv))
+			status = hdmi_port_clock_valid(hdmi, clock * 3 / 2,
+						       true, force_dvi);
+
+		/* if we can't do 8,12bpc we may still be able to do 10bpc */
+		if (status != MODE_OK && INTEL_GEN(dev_priv) >= 11)
+			status = hdmi_port_clock_valid(hdmi, clock * 5 / 4,
+						       true, force_dvi);
+	}
 
 	return status;
 }
 
-static bool hdmi_12bpc_possible(const struct intel_crtc_state *crtc_state)
+static bool hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state,
+				     int bpc)
 {
 	struct drm_i915_private *dev_priv =
 		to_i915(crtc_state->base.crtc->dev);
@@ -1596,6 +1598,9 @@ static bool hdmi_12bpc_possible(const struct intel_crtc_state *crtc_state)
 	if (HAS_GMCH_DISPLAY(dev_priv))
 		return false;
 
+	if (bpc == 10 && INTEL_GEN(dev_priv) < 11)
+		return false;
+
 	if (crtc_state->pipe_bpp <= 8*3)
 		return false;
 
@@ -1603,7 +1608,7 @@ static bool hdmi_12bpc_possible(const struct intel_crtc_state *crtc_state)
 		return false;
 
 	/*
-	 * HDMI 12bpc affects the clocks, so it's only possible
+	 * HDMI deep color affects the clocks, so it's only possible
 	 * when not cloning with other encoder types.
 	 */
 	if (crtc_state->output_types != 1 << INTEL_OUTPUT_HDMI)
@@ -1618,16 +1623,24 @@ static bool hdmi_12bpc_possible(const struct intel_crtc_state *crtc_state)
 		if (crtc_state->ycbcr420) {
 			const struct drm_hdmi_info *hdmi = &info->hdmi;
 
-			if (!(hdmi->y420_dc_modes & DRM_EDID_YCBCR420_DC_36))
+			if (bpc == 12 && !(hdmi->y420_dc_modes &
+					   DRM_EDID_YCBCR420_DC_36))
+				return false;
+			else if (bpc == 10 && !(hdmi->y420_dc_modes &
+						DRM_EDID_YCBCR420_DC_30))
 				return false;
 		} else {
-			if (!(info->edid_hdmi_dc_modes & DRM_EDID_HDMI_DC_36))
+			if (bpc == 12 && !(info->edid_hdmi_dc_modes &
+					   DRM_EDID_HDMI_DC_36))
+				return false;
+			else if (bpc == 10 && !(info->edid_hdmi_dc_modes &
+						DRM_EDID_HDMI_DC_30))
 				return false;
 		}
 	}
 
 	/* Display WA #1139: glk */
-	if (IS_GLK_REVID(dev_priv, 0, GLK_REVID_A1) &&
+	if (bpc == 12 && IS_GLK_REVID(dev_priv, 0, GLK_REVID_A1) &&
 	    crtc_state->base.adjusted_mode.htotal > 5460)
 		return false;
 
@@ -1637,7 +1650,8 @@ static bool hdmi_12bpc_possible(const struct intel_crtc_state *crtc_state)
 static bool
 intel_hdmi_ycbcr420_config(struct drm_connector *connector,
 			   struct intel_crtc_state *config,
-			   int *clock_12bpc, int *clock_8bpc)
+			   int *clock_12bpc, int *clock_10bpc,
+			   int *clock_8bpc)
 {
 	struct intel_crtc *intel_crtc = to_intel_crtc(config->base.crtc);
 
@@ -1649,6 +1663,7 @@ intel_hdmi_ycbcr420_config(struct drm_connector *connector,
 	/* YCBCR420 TMDS rate requirement is half the pixel clock */
 	config->port_clock /= 2;
 	*clock_12bpc /= 2;
+	*clock_10bpc /= 2;
 	*clock_8bpc /= 2;
 	config->ycbcr420 = true;
 
@@ -1676,6 +1691,7 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 	struct intel_digital_connector_state *intel_conn_state =
 		to_intel_digital_connector_state(conn_state);
 	int clock_8bpc = pipe_config->base.adjusted_mode.crtc_clock;
+	int clock_10bpc = clock_8bpc * 5 / 4;
 	int clock_12bpc = clock_8bpc * 3 / 2;
 	int desired_bpp;
 	bool force_dvi = intel_conn_state->force_audio == HDMI_AUDIO_OFF_DVI;
@@ -1702,12 +1718,14 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK) {
 		pipe_config->pixel_multiplier = 2;
 		clock_8bpc *= 2;
+		clock_10bpc *= 2;
 		clock_12bpc *= 2;
 	}
 
 	if (drm_mode_is_420_only(&connector->display_info, adjusted_mode)) {
 		if (!intel_hdmi_ycbcr420_config(connector, pipe_config,
-						&clock_12bpc, &clock_8bpc)) {
+						&clock_12bpc, &clock_10bpc,
+						&clock_8bpc)) {
 			DRM_ERROR("Can't support YCBCR420 output\n");
 			return false;
 		}
@@ -1725,18 +1743,25 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 	}
 
 	/*
-	 * HDMI is either 12 or 8, so if the display lets 10bpc sneak
-	 * through, clamp it down. Note that g4x/vlv don't support 12bpc hdmi
-	 * outputs. We also need to check that the higher clock still fits
-	 * within limits.
+	 * Note that g4x/vlv don't support 12bpc hdmi outputs. We also need
+	 * to check that the higher clock still fits within limits.
 	 */
-	if (hdmi_12bpc_possible(pipe_config) &&
-	    hdmi_port_clock_valid(intel_hdmi, clock_12bpc, true, force_dvi) == MODE_OK) {
+	if (hdmi_deep_color_possible(pipe_config, 12) &&
+	    hdmi_port_clock_valid(intel_hdmi, clock_12bpc,
+				  true, force_dvi) == MODE_OK) {
 		DRM_DEBUG_KMS("picking bpc to 12 for HDMI output\n");
 		desired_bpp = 12*3;
 
 		/* Need to adjust the port link by 1.5x for 12bpc. */
 		pipe_config->port_clock = clock_12bpc;
+	} else if (hdmi_deep_color_possible(pipe_config, 10) &&
+		   hdmi_port_clock_valid(intel_hdmi, clock_10bpc,
+					 true, force_dvi) == MODE_OK) {
+		DRM_DEBUG_KMS("picking bpc to 10 for HDMI output\n");
+		desired_bpp = 10 * 3;
+
+		/* Need to adjust the port link by 1.25x for 10bpc. */
+		pipe_config->port_clock = clock_10bpc;
 	} else {
 		DRM_DEBUG_KMS("picking bpc to 8 for HDMI output\n");
 		desired_bpp = 8*3;
@@ -2071,6 +2096,7 @@ intel_hdmi_add_properties(struct intel_hdmi *intel_hdmi, struct drm_connector *c
 	intel_attach_force_audio_property(connector);
 	intel_attach_broadcast_rgb_property(connector);
 	intel_attach_aspect_ratio_property(connector);
+	drm_connector_attach_content_type_property(connector);
 	connector->state->picture_aspect_ratio = HDMI_PICTURE_ASPECT_NONE;
 }
 
@@ -2257,7 +2283,7 @@ static u8 intel_hdmi_ddc_pin(struct drm_i915_private *dev_priv,
 		ddc_pin = bxt_port_to_ddc_pin(dev_priv, port);
 	else if (HAS_PCH_CNP(dev_priv))
 		ddc_pin = cnp_port_to_ddc_pin(dev_priv, port);
-	else if (IS_ICELAKE(dev_priv))
+	else if (HAS_PCH_ICP(dev_priv))
 		ddc_pin = icl_port_to_ddc_pin(dev_priv, port);
 	else
 		ddc_pin = g4x_port_to_ddc_pin(dev_priv, port);
@@ -2352,7 +2378,7 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 	 * 0xd.  Failure to do so will result in spurious interrupts being
 	 * generated on the port when a cable is not attached.
 	 */
-	if (IS_G4X(dev_priv) && !IS_GM45(dev_priv)) {
+	if (IS_G45(dev_priv)) {
 		u32 temp = I915_READ(PEG_BAND_GAP_DATA);
 		I915_WRITE(PEG_BAND_GAP_DATA, (temp & ~0xf) | 0xd);
 	}
diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c
index 43aa92beff2a..648a13c6043c 100644
--- a/drivers/gpu/drm/i915/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/intel_hotplug.c
@@ -77,37 +77,6 @@
  */
 
 /**
- * intel_hpd_port - return port hard associated with certain pin.
- * @dev_priv: private driver data pointer
- * @pin: the hpd pin to get associated port
- *
- * Return port that is associatade with @pin and PORT_NONE if no port is
- * hard associated with that @pin.
- */
-enum port intel_hpd_pin_to_port(struct drm_i915_private *dev_priv,
-				enum hpd_pin pin)
-{
-	switch (pin) {
-	case HPD_PORT_A:
-		return PORT_A;
-	case HPD_PORT_B:
-		return PORT_B;
-	case HPD_PORT_C:
-		return PORT_C;
-	case HPD_PORT_D:
-		return PORT_D;
-	case HPD_PORT_E:
-		if (IS_CNL_WITH_PORT_F(dev_priv))
-			return PORT_F;
-		return PORT_E;
-	case HPD_PORT_F:
-		return PORT_F;
-	default:
-		return PORT_NONE; /* no port for this pin */
-	}
-}
-
-/**
  * intel_hpd_pin_default - return default pin associated with certain port.
  * @dev_priv: private driver data pointer
  * @port: the hpd port to get associated pin
@@ -241,25 +210,25 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work)
 		container_of(work, typeof(*dev_priv),
 			     hotplug.reenable_work.work);
 	struct drm_device *dev = &dev_priv->drm;
-	int i;
+	enum hpd_pin pin;
 
 	intel_runtime_pm_get(dev_priv);
 
 	spin_lock_irq(&dev_priv->irq_lock);
-	for_each_hpd_pin(i) {
+	for_each_hpd_pin(pin) {
 		struct drm_connector *connector;
 		struct drm_connector_list_iter conn_iter;
 
-		if (dev_priv->hotplug.stats[i].state != HPD_DISABLED)
+		if (dev_priv->hotplug.stats[pin].state != HPD_DISABLED)
 			continue;
 
-		dev_priv->hotplug.stats[i].state = HPD_ENABLED;
+		dev_priv->hotplug.stats[pin].state = HPD_ENABLED;
 
 		drm_connector_list_iter_begin(dev, &conn_iter);
 		drm_for_each_connector_iter(connector, &conn_iter) {
 			struct intel_connector *intel_connector = to_intel_connector(connector);
 
-			if (intel_connector->encoder->hpd_pin == i) {
+			if (intel_connector->encoder->hpd_pin == pin) {
 				if (connector->polled != intel_connector->polled)
 					DRM_DEBUG_DRIVER("Reenabling HPD on connector %s\n",
 							 connector->name);
@@ -301,13 +270,18 @@ bool intel_encoder_hotplug(struct intel_encoder *encoder,
 	return true;
 }
 
+static bool intel_encoder_has_hpd_pulse(struct intel_encoder *encoder)
+{
+	return intel_encoder_is_dig_port(encoder) &&
+		enc_to_dig_port(&encoder->base)->hpd_pulse != NULL;
+}
+
 static void i915_digport_work_func(struct work_struct *work)
 {
 	struct drm_i915_private *dev_priv =
 		container_of(work, struct drm_i915_private, hotplug.dig_port_work);
 	u32 long_port_mask, short_port_mask;
-	struct intel_digital_port *intel_dig_port;
-	int i;
+	struct intel_encoder *encoder;
 	u32 old_bits = 0;
 
 	spin_lock_irq(&dev_priv->irq_lock);
@@ -317,27 +291,27 @@ static void i915_digport_work_func(struct work_struct *work)
 	dev_priv->hotplug.short_port_mask = 0;
 	spin_unlock_irq(&dev_priv->irq_lock);
 
-	for (i = 0; i < I915_MAX_PORTS; i++) {
-		bool valid = false;
-		bool long_hpd = false;
-		intel_dig_port = dev_priv->hotplug.irq_port[i];
-		if (!intel_dig_port || !intel_dig_port->hpd_pulse)
+	for_each_intel_encoder(&dev_priv->drm, encoder) {
+		struct intel_digital_port *dig_port;
+		enum port port = encoder->port;
+		bool long_hpd, short_hpd;
+		enum irqreturn ret;
+
+		if (!intel_encoder_has_hpd_pulse(encoder))
 			continue;
 
-		if (long_port_mask & (1 << i))  {
-			valid = true;
-			long_hpd = true;
-		} else if (short_port_mask & (1 << i))
-			valid = true;
+		long_hpd = long_port_mask & BIT(port);
+		short_hpd = short_port_mask & BIT(port);
 
-		if (valid) {
-			enum irqreturn ret;
+		if (!long_hpd && !short_hpd)
+			continue;
 
-			ret = intel_dig_port->hpd_pulse(intel_dig_port, long_hpd);
-			if (ret == IRQ_NONE) {
-				/* fall back to old school hpd */
-				old_bits |= (1 << intel_dig_port->base.hpd_pin);
-			}
+		dig_port = enc_to_dig_port(&encoder->base);
+
+		ret = dig_port->hpd_pulse(dig_port, long_hpd);
+		if (ret == IRQ_NONE) {
+			/* fall back to old school hpd */
+			old_bits |= BIT(encoder->hpd_pin);
 		}
 	}
 
@@ -418,26 +392,24 @@ static void i915_hotplug_work_func(struct work_struct *work)
 void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 			   u32 pin_mask, u32 long_mask)
 {
-	int i;
-	enum port port;
+	struct intel_encoder *encoder;
 	bool storm_detected = false;
 	bool queue_dig = false, queue_hp = false;
-	bool is_dig_port;
 
 	if (!pin_mask)
 		return;
 
 	spin_lock(&dev_priv->irq_lock);
-	for_each_hpd_pin(i) {
-		if (!(BIT(i) & pin_mask))
-			continue;
+	for_each_intel_encoder(&dev_priv->drm, encoder) {
+		enum hpd_pin pin = encoder->hpd_pin;
+		bool has_hpd_pulse = intel_encoder_has_hpd_pulse(encoder);
 
-		port = intel_hpd_pin_to_port(dev_priv, i);
-		is_dig_port = port != PORT_NONE &&
-			dev_priv->hotplug.irq_port[port];
+		if (!(BIT(pin) & pin_mask))
+			continue;
 
-		if (is_dig_port) {
-			bool long_hpd = long_mask & BIT(i);
+		if (has_hpd_pulse) {
+			bool long_hpd = long_mask & BIT(pin);
+			enum port port = encoder->port;
 
 			DRM_DEBUG_DRIVER("digital hpd port %c - %s\n", port_name(port),
 					 long_hpd ? "long" : "short");
@@ -455,7 +427,7 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 			}
 		}
 
-		if (dev_priv->hotplug.stats[i].state == HPD_DISABLED) {
+		if (dev_priv->hotplug.stats[pin].state == HPD_DISABLED) {
 			/*
 			 * On GMCH platforms the interrupt mask bits only
 			 * prevent irq generation, not the setting of the
@@ -463,20 +435,20 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 			 * interrupts on saner platforms.
 			 */
 			WARN_ONCE(!HAS_GMCH_DISPLAY(dev_priv),
-				  "Received HPD interrupt on pin %d although disabled\n", i);
+				  "Received HPD interrupt on pin %d although disabled\n", pin);
 			continue;
 		}
 
-		if (dev_priv->hotplug.stats[i].state != HPD_ENABLED)
+		if (dev_priv->hotplug.stats[pin].state != HPD_ENABLED)
 			continue;
 
-		if (!is_dig_port) {
-			dev_priv->hotplug.event_bits |= BIT(i);
+		if (!has_hpd_pulse) {
+			dev_priv->hotplug.event_bits |= BIT(pin);
 			queue_hp = true;
 		}
 
-		if (intel_hpd_irq_storm_detect(dev_priv, i)) {
-			dev_priv->hotplug.event_bits &= ~BIT(i);
+		if (intel_hpd_irq_storm_detect(dev_priv, pin)) {
+			dev_priv->hotplug.event_bits &= ~BIT(pin);
 			storm_detected = true;
 		}
 	}
diff --git a/drivers/gpu/drm/i915/intel_huc.c b/drivers/gpu/drm/i915/intel_huc.c
index 291285277403..ffcad5fad6a7 100644
--- a/drivers/gpu/drm/i915/intel_huc.c
+++ b/drivers/gpu/drm/i915/intel_huc.c
@@ -32,6 +32,14 @@ void intel_huc_init_early(struct intel_huc *huc)
 	intel_huc_fw_init_early(huc);
 }
 
+int intel_huc_init_misc(struct intel_huc *huc)
+{
+	struct drm_i915_private *i915 = huc_to_i915(huc);
+
+	intel_uc_fw_fetch(i915, &huc->fw);
+	return 0;
+}
+
 /**
  * intel_huc_auth() - Authenticate HuC uCode
  * @huc: intel_huc structure
diff --git a/drivers/gpu/drm/i915/intel_huc.h b/drivers/gpu/drm/i915/intel_huc.h
index aa854907abac..7e41d870b509 100644
--- a/drivers/gpu/drm/i915/intel_huc.h
+++ b/drivers/gpu/drm/i915/intel_huc.h
@@ -36,9 +36,15 @@ struct intel_huc {
 };
 
 void intel_huc_init_early(struct intel_huc *huc);
+int intel_huc_init_misc(struct intel_huc *huc);
 int intel_huc_auth(struct intel_huc *huc);
 int intel_huc_check_status(struct intel_huc *huc);
 
+static inline void intel_huc_fini_misc(struct intel_huc *huc)
+{
+	intel_uc_fw_fini(&huc->fw);
+}
+
 static inline int intel_huc_sanitize(struct intel_huc *huc)
 {
 	intel_uc_fw_sanitize(&huc->fw);
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index e6875509bcd9..bef32b7c248e 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -77,12 +77,12 @@ static const struct gmbus_pin gmbus_pins_cnp[] = {
 };
 
 static const struct gmbus_pin gmbus_pins_icp[] = {
-	[GMBUS_PIN_1_BXT] = { "dpa", GPIOA },
-	[GMBUS_PIN_2_BXT] = { "dpb", GPIOB },
-	[GMBUS_PIN_9_TC1_ICP] = { "tc1", GPIOC },
-	[GMBUS_PIN_10_TC2_ICP] = { "tc2", GPIOD },
-	[GMBUS_PIN_11_TC3_ICP] = { "tc3", GPIOE },
-	[GMBUS_PIN_12_TC4_ICP] = { "tc4", GPIOF },
+	[GMBUS_PIN_1_BXT] = { "dpa", GPIOB },
+	[GMBUS_PIN_2_BXT] = { "dpb", GPIOC },
+	[GMBUS_PIN_9_TC1_ICP] = { "tc1", GPIOJ },
+	[GMBUS_PIN_10_TC2_ICP] = { "tc2", GPIOK },
+	[GMBUS_PIN_11_TC3_ICP] = { "tc3", GPIOL },
+	[GMBUS_PIN_12_TC4_ICP] = { "tc4", GPIOM },
 };
 
 /* pin is expected to be valid */
@@ -361,15 +361,39 @@ gmbus_wait_idle(struct drm_i915_private *dev_priv)
 	return ret;
 }
 
+static inline
+unsigned int gmbus_max_xfer_size(struct drm_i915_private *dev_priv)
+{
+	return INTEL_GEN(dev_priv) >= 9 ? GEN9_GMBUS_BYTE_COUNT_MAX :
+	       GMBUS_BYTE_COUNT_MAX;
+}
+
 static int
 gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv,
 		      unsigned short addr, u8 *buf, unsigned int len,
-		      u32 gmbus1_index)
+		      u32 gmbus0_reg, u32 gmbus1_index)
 {
+	unsigned int size = len;
+	bool burst_read = len > gmbus_max_xfer_size(dev_priv);
+	bool extra_byte_added = false;
+
+	if (burst_read) {
+		/*
+		 * As per HW Spec, for 512Bytes need to read extra Byte and
+		 * Ignore the extra byte read.
+		 */
+		if (len == 512) {
+			extra_byte_added = true;
+			len++;
+		}
+		size = len % 256 + 256;
+		I915_WRITE_FW(GMBUS0, gmbus0_reg | GMBUS_BYTE_CNT_OVERRIDE);
+	}
+
 	I915_WRITE_FW(GMBUS1,
 		      gmbus1_index |
 		      GMBUS_CYCLE_WAIT |
-		      (len << GMBUS_BYTE_COUNT_SHIFT) |
+		      (size << GMBUS_BYTE_COUNT_SHIFT) |
 		      (addr << GMBUS_SLAVE_ADDR_SHIFT) |
 		      GMBUS_SLAVE_READ | GMBUS_SW_RDY);
 	while (len) {
@@ -382,17 +406,34 @@ gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv,
 
 		val = I915_READ_FW(GMBUS3);
 		do {
+			if (extra_byte_added && len == 1)
+				break;
+
 			*buf++ = val & 0xff;
 			val >>= 8;
 		} while (--len && ++loop < 4);
+
+		if (burst_read && len == size - 4)
+			/* Reset the override bit */
+			I915_WRITE_FW(GMBUS0, gmbus0_reg);
 	}
 
 	return 0;
 }
 
+/*
+ * HW spec says that 512Bytes in Burst read need special treatment.
+ * But it doesn't talk about other multiple of 256Bytes. And couldn't locate
+ * an I2C slave, which supports such a lengthy burst read too for experiments.
+ *
+ * So until things get clarified on HW support, to avoid the burst read length
+ * in fold of 256Bytes except 512, max burst read length is fixed at 767Bytes.
+ */
+#define INTEL_GMBUS_BURST_READ_MAX_LEN		767U
+
 static int
 gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg,
-		u32 gmbus1_index)
+		u32 gmbus0_reg, u32 gmbus1_index)
 {
 	u8 *buf = msg->buf;
 	unsigned int rx_size = msg->len;
@@ -400,10 +441,13 @@ gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg,
 	int ret;
 
 	do {
-		len = min(rx_size, GMBUS_BYTE_COUNT_MAX);
+		if (HAS_GMBUS_BURST_READ(dev_priv))
+			len = min(rx_size, INTEL_GMBUS_BURST_READ_MAX_LEN);
+		else
+			len = min(rx_size, gmbus_max_xfer_size(dev_priv));
 
-		ret = gmbus_xfer_read_chunk(dev_priv, msg->addr,
-					    buf, len, gmbus1_index);
+		ret = gmbus_xfer_read_chunk(dev_priv, msg->addr, buf, len,
+					    gmbus0_reg, gmbus1_index);
 		if (ret)
 			return ret;
 
@@ -462,7 +506,7 @@ gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg,
 	int ret;
 
 	do {
-		len = min(tx_size, GMBUS_BYTE_COUNT_MAX);
+		len = min(tx_size, gmbus_max_xfer_size(dev_priv));
 
 		ret = gmbus_xfer_write_chunk(dev_priv, msg->addr, buf, len,
 					     gmbus1_index);
@@ -491,7 +535,8 @@ gmbus_is_index_xfer(struct i2c_msg *msgs, int i, int num)
 }
 
 static int
-gmbus_index_xfer(struct drm_i915_private *dev_priv, struct i2c_msg *msgs)
+gmbus_index_xfer(struct drm_i915_private *dev_priv, struct i2c_msg *msgs,
+		 u32 gmbus0_reg)
 {
 	u32 gmbus1_index = 0;
 	u32 gmbus5 = 0;
@@ -509,7 +554,8 @@ gmbus_index_xfer(struct drm_i915_private *dev_priv, struct i2c_msg *msgs)
 		I915_WRITE_FW(GMBUS5, gmbus5);
 
 	if (msgs[1].flags & I2C_M_RD)
-		ret = gmbus_xfer_read(dev_priv, &msgs[1], gmbus1_index);
+		ret = gmbus_xfer_read(dev_priv, &msgs[1], gmbus0_reg,
+				      gmbus1_index);
 	else
 		ret = gmbus_xfer_write(dev_priv, &msgs[1], gmbus1_index);
 
@@ -544,10 +590,12 @@ retry:
 	for (; i < num; i += inc) {
 		inc = 1;
 		if (gmbus_is_index_xfer(msgs, i, num)) {
-			ret = gmbus_index_xfer(dev_priv, &msgs[i]);
+			ret = gmbus_index_xfer(dev_priv, &msgs[i],
+					       gmbus0_source | bus->reg0);
 			inc = 2; /* an index transmission is two msgs */
 		} else if (msgs[i].flags & I2C_M_RD) {
-			ret = gmbus_xfer_read(dev_priv, &msgs[i], 0);
+			ret = gmbus_xfer_read(dev_priv, &msgs[i],
+					      gmbus0_source | bus->reg0, 0);
 		} else {
 			ret = gmbus_xfer_write(dev_priv, &msgs[i], 0);
 		}
@@ -771,7 +819,7 @@ int intel_setup_gmbus(struct drm_i915_private *dev_priv)
 	unsigned int pin;
 	int ret;
 
-	if (HAS_PCH_NOP(dev_priv))
+	if (INTEL_INFO(dev_priv)->num_pipes == 0)
 		return 0;
 
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
diff --git a/drivers/gpu/drm/i915/intel_lpe_audio.c b/drivers/gpu/drm/i915/intel_lpe_audio.c
index 6269750e2b54..cdf19553ffac 100644
--- a/drivers/gpu/drm/i915/intel_lpe_audio.c
+++ b/drivers/gpu/drm/i915/intel_lpe_audio.c
@@ -62,6 +62,7 @@
 
 #include <linux/acpi.h>
 #include <linux/device.h>
+#include <linux/irq.h>
 #include <linux/pci.h>
 #include <linux/pm_runtime.h>
 
@@ -126,9 +127,7 @@ lpe_audio_platdev_create(struct drm_i915_private *dev_priv)
 		return platdev;
 	}
 
-	pm_runtime_forbid(&platdev->dev);
-	pm_runtime_set_active(&platdev->dev);
-	pm_runtime_enable(&platdev->dev);
+	pm_runtime_no_callbacks(&platdev->dev);
 
 	return platdev;
 }
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 7c4c8fb1dae4..174479232e94 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -137,6 +137,7 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 #include "i915_gem_render_state.h"
+#include "i915_vgpu.h"
 #include "intel_lrc_reg.h"
 #include "intel_mocs.h"
 #include "intel_workarounds.h"
@@ -164,7 +165,8 @@
 #define WA_TAIL_BYTES (sizeof(u32) * WA_TAIL_DWORDS)
 
 static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
-					    struct intel_engine_cs *engine);
+					    struct intel_engine_cs *engine,
+					    struct intel_context *ce);
 static void execlists_init_reg_state(u32 *reg_state,
 				     struct i915_gem_context *ctx,
 				     struct intel_engine_cs *engine,
@@ -189,12 +191,7 @@ static inline bool need_preempt(const struct intel_engine_cs *engine,
 		!i915_request_completed(last));
 }
 
-/**
- * intel_lr_context_descriptor_update() - calculate & cache the descriptor
- * 					  descriptor for a pinned context
- * @ctx: Context to work on
- * @engine: Engine the descriptor will be used with
- *
+/*
  * The context descriptor encodes various attributes of a context,
  * including its GTT address and some flags. Because it's fairly
  * expensive to calculate, we'll just do it once and cache the result,
@@ -204,7 +201,7 @@ static inline bool need_preempt(const struct intel_engine_cs *engine,
  *
  *      bits  0-11:    flags, GEN8_CTX_* (cached in ctx->desc_template)
  *      bits 12-31:    LRCA, GTT address of (the HWSP of) this context
- *      bits 32-52:    ctx ID, a globally unique tag
+ *      bits 32-52:    ctx ID, a globally unique tag (highest bit used by GuC)
  *      bits 53-54:    mbz, reserved for use by hardware
  *      bits 55-63:    group ID, currently unused and set to 0
  *
@@ -222,9 +219,9 @@ static inline bool need_preempt(const struct intel_engine_cs *engine,
  */
 static void
 intel_lr_context_descriptor_update(struct i915_gem_context *ctx,
-				   struct intel_engine_cs *engine)
+				   struct intel_engine_cs *engine,
+				   struct intel_context *ce)
 {
-	struct intel_context *ce = to_intel_context(ctx, engine);
 	u64 desc;
 
 	BUILD_BUG_ON(MAX_CONTEXT_HW_ID > (BIT(GEN8_CTX_ID_WIDTH)));
@@ -237,6 +234,11 @@ intel_lr_context_descriptor_update(struct i915_gem_context *ctx,
 								/* bits 12-31 */
 	GEM_BUG_ON(desc & GENMASK_ULL(63, 32));
 
+	/*
+	 * The following 32bits are copied into the OA reports (dword 2).
+	 * Consider updating oa_get_render_ctx_id in i915_perf.c when changing
+	 * anything below.
+	 */
 	if (INTEL_GEN(ctx->i915) >= 11) {
 		GEM_BUG_ON(ctx->hw_id >= BIT(GEN11_SW_CTX_ID_WIDTH));
 		desc |= (u64)ctx->hw_id << GEN11_SW_CTX_ID_SHIFT;
@@ -271,7 +273,7 @@ lookup_priolist(struct intel_engine_cs *engine, int prio)
 find_priolist:
 	/* most positive priority is scheduled first, equal priorities fifo */
 	rb = NULL;
-	parent = &execlists->queue.rb_node;
+	parent = &execlists->queue.rb_root.rb_node;
 	while (*parent) {
 		rb = *parent;
 		p = to_priolist(rb);
@@ -309,10 +311,7 @@ find_priolist:
 	p->priority = prio;
 	INIT_LIST_HEAD(&p->requests);
 	rb_link_node(&p->node, rb, parent);
-	rb_insert_color(&p->node, &execlists->queue);
-
-	if (first)
-		execlists->first = &p->node;
+	rb_insert_color_cached(&p->node, &execlists->queue, first);
 
 	return p;
 }
@@ -418,9 +417,9 @@ execlists_update_context_pdps(struct i915_hw_ppgtt *ppgtt, u32 *reg_state)
 
 static u64 execlists_update_context(struct i915_request *rq)
 {
-	struct intel_context *ce = to_intel_context(rq->ctx, rq->engine);
+	struct intel_context *ce = rq->hw_context;
 	struct i915_hw_ppgtt *ppgtt =
-		rq->ctx->ppgtt ?: rq->i915->mm.aliasing_ppgtt;
+		rq->gem_context->ppgtt ?: rq->i915->mm.aliasing_ppgtt;
 	u32 *reg_state = ce->lrc_reg_state;
 
 	reg_state[CTX_RING_TAIL+1] = intel_ring_set_tail(rq->ring, rq->tail);
@@ -430,7 +429,7 @@ static u64 execlists_update_context(struct i915_request *rq)
 	 * PML4 is allocated during ppgtt init, so this is not needed
 	 * in 48-bit mode.
 	 */
-	if (ppgtt && !i915_vm_is_48bit(&ppgtt->base))
+	if (ppgtt && !i915_vm_is_48bit(&ppgtt->vm))
 		execlists_update_context_pdps(ppgtt, reg_state);
 
 	return ce->lrc_desc;
@@ -454,6 +453,16 @@ static void execlists_submit_ports(struct intel_engine_cs *engine)
 	unsigned int n;
 
 	/*
+	 * We can skip acquiring intel_runtime_pm_get() here as it was taken
+	 * on our behalf by the request (see i915_gem_mark_busy()) and it will
+	 * not be relinquished until the device is idle (see
+	 * i915_gem_idle_work_handler()). As a precaution, we make sure
+	 * that all ELSP are drained i.e. we have processed the CSB,
+	 * before allowing ourselves to idle and calling intel_runtime_pm_put().
+	 */
+	GEM_BUG_ON(!engine->i915->gt.awake);
+
+	/*
 	 * ELSQ note: the submit queue is not cleared after being submitted
 	 * to the HW so we need to make sure we always clean it up. This is
 	 * currently ensured by the fact that we always write the same number
@@ -495,14 +504,14 @@ static void execlists_submit_ports(struct intel_engine_cs *engine)
 	execlists_clear_active(execlists, EXECLISTS_ACTIVE_HWACK);
 }
 
-static bool ctx_single_port_submission(const struct i915_gem_context *ctx)
+static bool ctx_single_port_submission(const struct intel_context *ce)
 {
 	return (IS_ENABLED(CONFIG_DRM_I915_GVT) &&
-		i915_gem_context_force_single_submission(ctx));
+		i915_gem_context_force_single_submission(ce->gem_context));
 }
 
-static bool can_merge_ctx(const struct i915_gem_context *prev,
-			  const struct i915_gem_context *next)
+static bool can_merge_ctx(const struct intel_context *prev,
+			  const struct intel_context *next)
 {
 	if (prev != next)
 		return false;
@@ -552,11 +561,24 @@ static void inject_preempt_context(struct intel_engine_cs *engine)
 	if (execlists->ctrl_reg)
 		writel(EL_CTRL_LOAD, execlists->ctrl_reg);
 
-	execlists_clear_active(&engine->execlists, EXECLISTS_ACTIVE_HWACK);
-	execlists_set_active(&engine->execlists, EXECLISTS_ACTIVE_PREEMPT);
+	execlists_clear_active(execlists, EXECLISTS_ACTIVE_HWACK);
+	execlists_set_active(execlists, EXECLISTS_ACTIVE_PREEMPT);
+}
+
+static void complete_preempt_context(struct intel_engine_execlists *execlists)
+{
+	GEM_BUG_ON(!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT));
+
+	if (inject_preempt_hang(execlists))
+		return;
+
+	execlists_cancel_port_requests(execlists);
+	__unwind_incomplete_requests(container_of(execlists,
+						  struct intel_engine_cs,
+						  execlists));
 }
 
-static bool __execlists_dequeue(struct intel_engine_cs *engine)
+static void execlists_dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct execlist_port *port = execlists->port;
@@ -566,9 +588,8 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 	struct rb_node *rb;
 	bool submit = false;
 
-	lockdep_assert_held(&engine->timeline.lock);
-
-	/* Hardware submission is through 2 ports. Conceptually each port
+	/*
+	 * Hardware submission is through 2 ports. Conceptually each port
 	 * has a (RING_START, RING_HEAD, RING_TAIL) tuple. RING_START is
 	 * static for a context, and unique to each, so we only execute
 	 * requests belonging to a single context from each ring. RING_HEAD
@@ -589,9 +610,6 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 	 * and context switches) submission.
 	 */
 
-	rb = execlists->first;
-	GEM_BUG_ON(rb_first(&execlists->queue) != rb);
-
 	if (last) {
 		/*
 		 * Don't resubmit or switch until all outstanding
@@ -602,8 +620,6 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 		GEM_BUG_ON(!execlists_is_active(execlists,
 						EXECLISTS_ACTIVE_USER));
 		GEM_BUG_ON(!port_count(&port[0]));
-		if (port_count(&port[0]) > 1)
-			return false;
 
 		/*
 		 * If we write to ELSP a second time before the HW has had
@@ -613,11 +629,11 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 		 * the HW to indicate that it has had a chance to respond.
 		 */
 		if (!execlists_is_active(execlists, EXECLISTS_ACTIVE_HWACK))
-			return false;
+			return;
 
 		if (need_preempt(engine, last, execlists->queue_priority)) {
 			inject_preempt_context(engine);
-			return false;
+			return;
 		}
 
 		/*
@@ -642,7 +658,7 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 		 * priorities of the ports haven't been switch.
 		 */
 		if (port_count(&port[1]))
-			return false;
+			return;
 
 		/*
 		 * WaIdleLiteRestore:bdw,skl
@@ -655,7 +671,7 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 		last->tail = last->wa_tail;
 	}
 
-	while (rb) {
+	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 		struct i915_request *rq, *rn;
 
@@ -671,7 +687,8 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 			 * second request, and so we never need to tell the
 			 * hardware about the first.
 			 */
-			if (last && !can_merge_ctx(rq->ctx, last->ctx)) {
+			if (last &&
+			    !can_merge_ctx(rq->hw_context, last->hw_context)) {
 				/*
 				 * If we are on the second port and cannot
 				 * combine this request with the last, then we
@@ -690,14 +707,14 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 				 * the same context (even though a different
 				 * request) to the second port.
 				 */
-				if (ctx_single_port_submission(last->ctx) ||
-				    ctx_single_port_submission(rq->ctx)) {
+				if (ctx_single_port_submission(last->hw_context) ||
+				    ctx_single_port_submission(rq->hw_context)) {
 					__list_del_many(&p->requests,
 							&rq->sched.link);
 					goto done;
 				}
 
-				GEM_BUG_ON(last->ctx == rq->ctx);
+				GEM_BUG_ON(last->hw_context == rq->hw_context);
 
 				if (submit)
 					port_assign(port, last);
@@ -713,8 +730,7 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 			submit = true;
 		}
 
-		rb = rb_next(rb);
-		rb_erase(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &execlists->queue);
 		INIT_LIST_HEAD(&p->requests);
 		if (p->priority != I915_PRIORITY_NORMAL)
 			kmem_cache_free(engine->i915->priorities, p);
@@ -740,35 +756,23 @@ done:
 	execlists->queue_priority =
 		port != execlists->port ? rq_prio(last) : INT_MIN;
 
-	execlists->first = rb;
-	if (submit)
+	if (submit) {
 		port_assign(port, last);
+		execlists_submit_ports(engine);
+	}
 
 	/* We must always keep the beast fed if we have work piled up */
-	GEM_BUG_ON(execlists->first && !port_isset(execlists->port));
+	GEM_BUG_ON(rb_first_cached(&execlists->queue) &&
+		   !port_isset(execlists->port));
 
 	/* Re-evaluate the executing context setup after each preemptive kick */
 	if (last)
 		execlists_user_begin(execlists, execlists->port);
 
-	return submit;
-}
-
-static void execlists_dequeue(struct intel_engine_cs *engine)
-{
-	struct intel_engine_execlists * const execlists = &engine->execlists;
-	unsigned long flags;
-	bool submit;
-
-	spin_lock_irqsave(&engine->timeline.lock, flags);
-	submit = __execlists_dequeue(engine);
-	spin_unlock_irqrestore(&engine->timeline.lock, flags);
-
-	if (submit)
-		execlists_submit_ports(engine);
-
-	GEM_BUG_ON(port_isset(execlists->port) &&
-		   !execlists_is_active(execlists, EXECLISTS_ACTIVE_USER));
+	/* If the engine is now idle, so should be the flag; and vice versa. */
+	GEM_BUG_ON(execlists_is_active(&engine->execlists,
+				       EXECLISTS_ACTIVE_USER) ==
+		   !port_isset(engine->execlists.port));
 }
 
 void
@@ -799,82 +803,27 @@ execlists_cancel_port_requests(struct intel_engine_execlists * const execlists)
 		port++;
 	}
 
-	execlists_user_end(execlists);
+	execlists_clear_all_active(execlists);
 }
 
-static void clear_gtiir(struct intel_engine_cs *engine)
+static void reset_csb_pointers(struct intel_engine_execlists *execlists)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
-	int i;
-
 	/*
-	 * Clear any pending interrupt state.
-	 *
-	 * We do it twice out of paranoia that some of the IIR are
-	 * double buffered, and so if we only reset it once there may
-	 * still be an interrupt pending.
+	 * After a reset, the HW starts writing into CSB entry [0]. We
+	 * therefore have to set our HEAD pointer back one entry so that
+	 * the *first* entry we check is entry 0. To complicate this further,
+	 * as we don't wait for the first interrupt after reset, we have to
+	 * fake the HW write to point back to the last entry so that our
+	 * inline comparison of our cached head position against the last HW
+	 * write works even before the first interrupt.
 	 */
-	if (INTEL_GEN(dev_priv) >= 11) {
-		static const struct {
-			u8 bank;
-			u8 bit;
-		} gen11_gtiir[] = {
-			[RCS] = {0, GEN11_RCS0},
-			[BCS] = {0, GEN11_BCS},
-			[_VCS(0)] = {1, GEN11_VCS(0)},
-			[_VCS(1)] = {1, GEN11_VCS(1)},
-			[_VCS(2)] = {1, GEN11_VCS(2)},
-			[_VCS(3)] = {1, GEN11_VCS(3)},
-			[_VECS(0)] = {1, GEN11_VECS(0)},
-			[_VECS(1)] = {1, GEN11_VECS(1)},
-		};
-		unsigned long irqflags;
-
-		GEM_BUG_ON(engine->id >= ARRAY_SIZE(gen11_gtiir));
-
-		spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-		for (i = 0; i < 2; i++) {
-			gen11_reset_one_iir(dev_priv,
-					    gen11_gtiir[engine->id].bank,
-					    gen11_gtiir[engine->id].bit);
-		}
-		spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
-	} else {
-		static const u8 gtiir[] = {
-			[RCS]  = 0,
-			[BCS]  = 0,
-			[VCS]  = 1,
-			[VCS2] = 1,
-			[VECS] = 3,
-		};
-
-		GEM_BUG_ON(engine->id >= ARRAY_SIZE(gtiir));
-
-		for (i = 0; i < 2; i++) {
-			I915_WRITE(GEN8_GT_IIR(gtiir[engine->id]),
-				   engine->irq_keep_mask);
-			POSTING_READ(GEN8_GT_IIR(gtiir[engine->id]));
-		}
-		GEM_BUG_ON(I915_READ(GEN8_GT_IIR(gtiir[engine->id])) &
-			   engine->irq_keep_mask);
-	}
+	execlists->csb_head = execlists->csb_write_reset;
+	WRITE_ONCE(*execlists->csb_write, execlists->csb_write_reset);
 }
 
-static void reset_irq(struct intel_engine_cs *engine)
+static void nop_submission_tasklet(unsigned long data)
 {
-	/* Mark all CS interrupts as complete */
-	smp_store_mb(engine->execlists.active, 0);
-	synchronize_hardirq(engine->i915->drm.irq);
-
-	clear_gtiir(engine);
-
-	/*
-	 * The port is checked prior to scheduling a tasklet, but
-	 * just in case we have suspended the tasklet to do the
-	 * wedging make sure that when it wakes, it decides there
-	 * is no work to do by clearing the irq_posted bit.
-	 */
-	clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
+	/* The driver is wedged; don't process any more events. */
 }
 
 static void execlists_cancel_requests(struct intel_engine_cs *engine)
@@ -901,13 +850,11 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	 * submission's irq state, we also wish to remind ourselves that
 	 * it is irq state.)
 	 */
-	local_irq_save(flags);
+	spin_lock_irqsave(&engine->timeline.lock, flags);
 
 	/* Cancel the requests on the HW and clear the ELSP tracker. */
 	execlists_cancel_port_requests(execlists);
-	reset_irq(engine);
-
-	spin_lock(&engine->timeline.lock);
+	execlists_user_end(execlists);
 
 	/* Mark all executing requests as skipped. */
 	list_for_each_entry(rq, &engine->timeline.requests, link) {
@@ -917,8 +864,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	}
 
 	/* Flush the queued requests to the timeline list (for retiring). */
-	rb = execlists->first;
-	while (rb) {
+	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 
 		list_for_each_entry_safe(rq, rn, &p->requests, sched.link) {
@@ -928,8 +874,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 			__i915_request_submit(rq);
 		}
 
-		rb = rb_next(rb);
-		rb_erase(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &execlists->queue);
 		INIT_LIST_HEAD(&p->requests);
 		if (p->priority != I915_PRIORITY_NORMAL)
 			kmem_cache_free(engine->i915->priorities, p);
@@ -938,221 +883,198 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	/* Remaining _unready_ requests will be nop'ed when submitted */
 
 	execlists->queue_priority = INT_MIN;
-	execlists->queue = RB_ROOT;
-	execlists->first = NULL;
+	execlists->queue = RB_ROOT_CACHED;
 	GEM_BUG_ON(port_isset(execlists->port));
 
-	spin_unlock(&engine->timeline.lock);
+	GEM_BUG_ON(__tasklet_is_enabled(&execlists->tasklet));
+	execlists->tasklet.func = nop_submission_tasklet;
 
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 }
 
-/*
- * Check the unread Context Status Buffers and manage the submission of new
- * contexts to the ELSP accordingly.
- */
-static void execlists_submission_tasklet(unsigned long data)
+static inline bool
+reset_in_progress(const struct intel_engine_execlists *execlists)
+{
+	return unlikely(!__tasklet_is_enabled(&execlists->tasklet));
+}
+
+static void process_csb(struct intel_engine_cs *engine)
 {
-	struct intel_engine_cs * const engine = (struct intel_engine_cs *)data;
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct execlist_port *port = execlists->port;
-	struct drm_i915_private *dev_priv = engine->i915;
-	bool fw = false;
+	const u32 * const buf = execlists->csb_status;
+	u8 head, tail;
 
 	/*
-	 * We can skip acquiring intel_runtime_pm_get() here as it was taken
-	 * on our behalf by the request (see i915_gem_mark_busy()) and it will
-	 * not be relinquished until the device is idle (see
-	 * i915_gem_idle_work_handler()). As a precaution, we make sure
-	 * that all ELSP are drained i.e. we have processed the CSB,
-	 * before allowing ourselves to idle and calling intel_runtime_pm_put().
+	 * Note that csb_write, csb_status may be either in HWSP or mmio.
+	 * When reading from the csb_write mmio register, we have to be
+	 * careful to only use the GEN8_CSB_WRITE_PTR portion, which is
+	 * the low 4bits. As it happens we know the next 4bits are always
+	 * zero and so we can simply masked off the low u8 of the register
+	 * and treat it identically to reading from the HWSP (without having
+	 * to use explicit shifting and masking, and probably bifurcating
+	 * the code to handle the legacy mmio read).
 	 */
-	GEM_BUG_ON(!dev_priv->gt.awake);
+	head = execlists->csb_head;
+	tail = READ_ONCE(*execlists->csb_write);
+	GEM_TRACE("%s cs-irq head=%d, tail=%d\n", engine->name, head, tail);
+	if (unlikely(head == tail))
+		return;
 
 	/*
-	 * Prefer doing test_and_clear_bit() as a two stage operation to avoid
-	 * imposing the cost of a locked atomic transaction when submitting a
-	 * new request (outside of the context-switch interrupt).
+	 * Hopefully paired with a wmb() in HW!
+	 *
+	 * We must complete the read of the write pointer before any reads
+	 * from the CSB, so that we do not see stale values. Without an rmb
+	 * (lfence) the HW may speculatively perform the CSB[] reads *before*
+	 * we perform the READ_ONCE(*csb_write).
 	 */
-	while (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted)) {
-		/* The HWSP contains a (cacheable) mirror of the CSB */
-		const u32 *buf =
-			&engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
-		unsigned int head, tail;
+	rmb();
 
-		if (unlikely(execlists->csb_use_mmio)) {
-			buf = (u32 * __force)
-				(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0)));
-			execlists->csb_head = -1; /* force mmio read of CSB ptrs */
-		}
+	do {
+		struct i915_request *rq;
+		unsigned int status;
+		unsigned int count;
 
-		/* Clear before reading to catch new interrupts */
-		clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
-		smp_mb__after_atomic();
+		if (++head == GEN8_CSB_ENTRIES)
+			head = 0;
 
-		if (unlikely(execlists->csb_head == -1)) { /* following a reset */
-			if (!fw) {
-				intel_uncore_forcewake_get(dev_priv,
-							   execlists->fw_domains);
-				fw = true;
-			}
+		/*
+		 * We are flying near dragons again.
+		 *
+		 * We hold a reference to the request in execlist_port[]
+		 * but no more than that. We are operating in softirq
+		 * context and so cannot hold any mutex or sleep. That
+		 * prevents us stopping the requests we are processing
+		 * in port[] from being retired simultaneously (the
+		 * breadcrumb will be complete before we see the
+		 * context-switch). As we only hold the reference to the
+		 * request, any pointer chasing underneath the request
+		 * is subject to a potential use-after-free. Thus we
+		 * store all of the bookkeeping within port[] as
+		 * required, and avoid using unguarded pointers beneath
+		 * request itself. The same applies to the atomic
+		 * status notifier.
+		 */
 
-			head = readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
-			tail = GEN8_CSB_WRITE_PTR(head);
-			head = GEN8_CSB_READ_PTR(head);
-			execlists->csb_head = head;
-		} else {
-			const int write_idx =
-				intel_hws_csb_write_index(dev_priv) -
-				I915_HWS_CSB_BUF0_INDEX;
+		GEM_TRACE("%s csb[%d]: status=0x%08x:0x%08x, active=0x%x\n",
+			  engine->name, head,
+			  buf[2 * head + 0], buf[2 * head + 1],
+			  execlists->active);
+
+		status = buf[2 * head];
+		if (status & (GEN8_CTX_STATUS_IDLE_ACTIVE |
+			      GEN8_CTX_STATUS_PREEMPTED))
+			execlists_set_active(execlists,
+					     EXECLISTS_ACTIVE_HWACK);
+		if (status & GEN8_CTX_STATUS_ACTIVE_IDLE)
+			execlists_clear_active(execlists,
+					       EXECLISTS_ACTIVE_HWACK);
+
+		if (!(status & GEN8_CTX_STATUS_COMPLETED_MASK))
+			continue;
+
+		/* We should never get a COMPLETED | IDLE_ACTIVE! */
+		GEM_BUG_ON(status & GEN8_CTX_STATUS_IDLE_ACTIVE);
 
-			head = execlists->csb_head;
-			tail = READ_ONCE(buf[write_idx]);
-			rmb(); /* Hopefully paired with a wmb() in HW */
+		if (status & GEN8_CTX_STATUS_COMPLETE &&
+		    buf[2*head + 1] == execlists->preempt_complete_status) {
+			GEM_TRACE("%s preempt-idle\n", engine->name);
+			complete_preempt_context(execlists);
+			continue;
 		}
-		GEM_TRACE("%s cs-irq head=%d [%d%s], tail=%d [%d%s]\n",
-			  engine->name,
-			  head, GEN8_CSB_READ_PTR(readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?",
-			  tail, GEN8_CSB_WRITE_PTR(readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?");
 
-		while (head != tail) {
-			struct i915_request *rq;
-			unsigned int status;
-			unsigned int count;
+		if (status & GEN8_CTX_STATUS_PREEMPTED &&
+		    execlists_is_active(execlists,
+					EXECLISTS_ACTIVE_PREEMPT))
+			continue;
 
-			if (++head == GEN8_CSB_ENTRIES)
-				head = 0;
+		GEM_BUG_ON(!execlists_is_active(execlists,
+						EXECLISTS_ACTIVE_USER));
 
-			/* We are flying near dragons again.
-			 *
-			 * We hold a reference to the request in execlist_port[]
-			 * but no more than that. We are operating in softirq
-			 * context and so cannot hold any mutex or sleep. That
-			 * prevents us stopping the requests we are processing
-			 * in port[] from being retired simultaneously (the
-			 * breadcrumb will be complete before we see the
-			 * context-switch). As we only hold the reference to the
-			 * request, any pointer chasing underneath the request
-			 * is subject to a potential use-after-free. Thus we
-			 * store all of the bookkeeping within port[] as
-			 * required, and avoid using unguarded pointers beneath
-			 * request itself. The same applies to the atomic
-			 * status notifier.
+		rq = port_unpack(port, &count);
+		GEM_TRACE("%s out[0]: ctx=%d.%d, global=%d (fence %llx:%d) (current %d), prio=%d\n",
+			  engine->name,
+			  port->context_id, count,
+			  rq ? rq->global_seqno : 0,
+			  rq ? rq->fence.context : 0,
+			  rq ? rq->fence.seqno : 0,
+			  intel_engine_get_seqno(engine),
+			  rq ? rq_prio(rq) : 0);
+
+		/* Check the context/desc id for this event matches */
+		GEM_DEBUG_BUG_ON(buf[2 * head + 1] != port->context_id);
+
+		GEM_BUG_ON(count == 0);
+		if (--count == 0) {
+			/*
+			 * On the final event corresponding to the
+			 * submission of this context, we expect either
+			 * an element-switch event or a completion
+			 * event (and on completion, the active-idle
+			 * marker). No more preemptions, lite-restore
+			 * or otherwise.
 			 */
+			GEM_BUG_ON(status & GEN8_CTX_STATUS_PREEMPTED);
+			GEM_BUG_ON(port_isset(&port[1]) &&
+				   !(status & GEN8_CTX_STATUS_ELEMENT_SWITCH));
+			GEM_BUG_ON(!port_isset(&port[1]) &&
+				   !(status & GEN8_CTX_STATUS_ACTIVE_IDLE));
 
-			status = READ_ONCE(buf[2 * head]); /* maybe mmio! */
-			GEM_TRACE("%s csb[%d]: status=0x%08x:0x%08x, active=0x%x\n",
-				  engine->name, head,
-				  status, buf[2*head + 1],
-				  execlists->active);
-
-			if (status & (GEN8_CTX_STATUS_IDLE_ACTIVE |
-				      GEN8_CTX_STATUS_PREEMPTED))
-				execlists_set_active(execlists,
-						     EXECLISTS_ACTIVE_HWACK);
-			if (status & GEN8_CTX_STATUS_ACTIVE_IDLE)
-				execlists_clear_active(execlists,
-						       EXECLISTS_ACTIVE_HWACK);
-
-			if (!(status & GEN8_CTX_STATUS_COMPLETED_MASK))
-				continue;
-
-			/* We should never get a COMPLETED | IDLE_ACTIVE! */
-			GEM_BUG_ON(status & GEN8_CTX_STATUS_IDLE_ACTIVE);
-
-			if (status & GEN8_CTX_STATUS_COMPLETE &&
-			    buf[2*head + 1] == execlists->preempt_complete_status) {
-				GEM_TRACE("%s preempt-idle\n", engine->name);
-
-				execlists_cancel_port_requests(execlists);
-				execlists_unwind_incomplete_requests(execlists);
-
-				GEM_BUG_ON(!execlists_is_active(execlists,
-								EXECLISTS_ACTIVE_PREEMPT));
-				execlists_clear_active(execlists,
-						       EXECLISTS_ACTIVE_PREEMPT);
-				continue;
-			}
-
-			if (status & GEN8_CTX_STATUS_PREEMPTED &&
-			    execlists_is_active(execlists,
-						EXECLISTS_ACTIVE_PREEMPT))
-				continue;
+			/*
+			 * We rely on the hardware being strongly
+			 * ordered, that the breadcrumb write is
+			 * coherent (visible from the CPU) before the
+			 * user interrupt and CSB is processed.
+			 */
+			GEM_BUG_ON(!i915_request_completed(rq));
 
-			GEM_BUG_ON(!execlists_is_active(execlists,
-							EXECLISTS_ACTIVE_USER));
+			execlists_context_schedule_out(rq,
+						       INTEL_CONTEXT_SCHEDULE_OUT);
+			i915_request_put(rq);
 
-			rq = port_unpack(port, &count);
-			GEM_TRACE("%s out[0]: ctx=%d.%d, global=%d (fence %llx:%d) (current %d), prio=%d\n",
-				  engine->name,
-				  port->context_id, count,
-				  rq ? rq->global_seqno : 0,
-				  rq ? rq->fence.context : 0,
-				  rq ? rq->fence.seqno : 0,
-				  intel_engine_get_seqno(engine),
-				  rq ? rq_prio(rq) : 0);
+			GEM_TRACE("%s completed ctx=%d\n",
+				  engine->name, port->context_id);
 
-			/* Check the context/desc id for this event matches */
-			GEM_DEBUG_BUG_ON(buf[2 * head + 1] != port->context_id);
-
-			GEM_BUG_ON(count == 0);
-			if (--count == 0) {
-				/*
-				 * On the final event corresponding to the
-				 * submission of this context, we expect either
-				 * an element-switch event or a completion
-				 * event (and on completion, the active-idle
-				 * marker). No more preemptions, lite-restore
-				 * or otherwise.
-				 */
-				GEM_BUG_ON(status & GEN8_CTX_STATUS_PREEMPTED);
-				GEM_BUG_ON(port_isset(&port[1]) &&
-					   !(status & GEN8_CTX_STATUS_ELEMENT_SWITCH));
-				GEM_BUG_ON(!port_isset(&port[1]) &&
-					   !(status & GEN8_CTX_STATUS_ACTIVE_IDLE));
-
-				/*
-				 * We rely on the hardware being strongly
-				 * ordered, that the breadcrumb write is
-				 * coherent (visible from the CPU) before the
-				 * user interrupt and CSB is processed.
-				 */
-				GEM_BUG_ON(!i915_request_completed(rq));
-
-				execlists_context_schedule_out(rq,
-							       INTEL_CONTEXT_SCHEDULE_OUT);
-				i915_request_put(rq);
-
-				GEM_TRACE("%s completed ctx=%d\n",
-					  engine->name, port->context_id);
-
-				port = execlists_port_complete(execlists, port);
-				if (port_isset(port))
-					execlists_user_begin(execlists, port);
-				else
-					execlists_user_end(execlists);
-			} else {
-				port_set(port, port_pack(rq, count));
-			}
+			port = execlists_port_complete(execlists, port);
+			if (port_isset(port))
+				execlists_user_begin(execlists, port);
+			else
+				execlists_user_end(execlists);
+		} else {
+			port_set(port, port_pack(rq, count));
 		}
+	} while (head != tail);
 
-		if (head != execlists->csb_head) {
-			execlists->csb_head = head;
-			writel(_MASKED_FIELD(GEN8_CSB_READ_PTR_MASK, head << 8),
-			       dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
-		}
-	}
+	execlists->csb_head = head;
+}
 
-	if (!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT))
+static void __execlists_submission_tasklet(struct intel_engine_cs *const engine)
+{
+	lockdep_assert_held(&engine->timeline.lock);
+
+	process_csb(engine);
+	if (!execlists_is_active(&engine->execlists, EXECLISTS_ACTIVE_PREEMPT))
 		execlists_dequeue(engine);
+}
+
+/*
+ * Check the unread Context Status Buffers and manage the submission of new
+ * contexts to the ELSP accordingly.
+ */
+static void execlists_submission_tasklet(unsigned long data)
+{
+	struct intel_engine_cs * const engine = (struct intel_engine_cs *)data;
+	unsigned long flags;
 
-	if (fw)
-		intel_uncore_forcewake_put(dev_priv, execlists->fw_domains);
+	GEM_TRACE("%s awake?=%d, active=%x\n",
+		  engine->name,
+		  engine->i915->gt.awake,
+		  engine->execlists.active);
 
-	/* If the engine is now idle, so should be the flag; and vice versa. */
-	GEM_BUG_ON(execlists_is_active(&engine->execlists,
-				       EXECLISTS_ACTIVE_USER) ==
-		   !port_isset(engine->execlists.port));
+	spin_lock_irqsave(&engine->timeline.lock, flags);
+	__execlists_submission_tasklet(engine);
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 }
 
 static void queue_request(struct intel_engine_cs *engine,
@@ -1163,16 +1085,30 @@ static void queue_request(struct intel_engine_cs *engine,
 		      &lookup_priolist(engine, prio)->requests);
 }
 
-static void __submit_queue(struct intel_engine_cs *engine, int prio)
+static void __update_queue(struct intel_engine_cs *engine, int prio)
 {
 	engine->execlists.queue_priority = prio;
-	tasklet_hi_schedule(&engine->execlists.tasklet);
+}
+
+static void __submit_queue_imm(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists * const execlists = &engine->execlists;
+
+	if (reset_in_progress(execlists))
+		return; /* defer until we restart the engine following reset */
+
+	if (execlists->tasklet.func == execlists_submission_tasklet)
+		__execlists_submission_tasklet(engine);
+	else
+		tasklet_hi_schedule(&execlists->tasklet);
 }
 
 static void submit_queue(struct intel_engine_cs *engine, int prio)
 {
-	if (prio > engine->execlists.queue_priority)
-		__submit_queue(engine, prio);
+	if (prio > engine->execlists.queue_priority) {
+		__update_queue(engine, prio);
+		__submit_queue_imm(engine);
+	}
 }
 
 static void execlists_submit_request(struct i915_request *request)
@@ -1184,11 +1120,12 @@ static void execlists_submit_request(struct i915_request *request)
 	spin_lock_irqsave(&engine->timeline.lock, flags);
 
 	queue_request(engine, &request->sched, rq_prio(request));
-	submit_queue(engine, rq_prio(request));
 
-	GEM_BUG_ON(!engine->execlists.first);
+	GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
 	GEM_BUG_ON(list_empty(&request->sched.link));
 
+	submit_queue(engine, rq_prio(request));
+
 	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 }
 
@@ -1315,13 +1252,40 @@ static void execlists_schedule(struct i915_request *request,
 		}
 
 		if (prio > engine->execlists.queue_priority &&
-		    i915_sw_fence_done(&sched_to_request(node)->submit))
-			__submit_queue(engine, prio);
+		    i915_sw_fence_done(&sched_to_request(node)->submit)) {
+			/* defer submission until after all of our updates */
+			__update_queue(engine, prio);
+			tasklet_hi_schedule(&engine->execlists.tasklet);
+		}
 	}
 
 	spin_unlock_irq(&engine->timeline.lock);
 }
 
+static void execlists_context_destroy(struct intel_context *ce)
+{
+	GEM_BUG_ON(ce->pin_count);
+
+	if (!ce->state)
+		return;
+
+	intel_ring_free(ce->ring);
+
+	GEM_BUG_ON(i915_gem_object_is_active(ce->state->obj));
+	i915_gem_object_put(ce->state->obj);
+}
+
+static void execlists_context_unpin(struct intel_context *ce)
+{
+	intel_ring_unpin(ce->ring);
+
+	ce->state->obj->pin_global--;
+	i915_gem_object_unpin_map(ce->state->obj);
+	i915_vma_unpin(ce->state);
+
+	i915_gem_context_put(ce->gem_context);
+}
+
 static int __context_pin(struct i915_gem_context *ctx, struct i915_vma *vma)
 {
 	unsigned int flags;
@@ -1345,21 +1309,15 @@ static int __context_pin(struct i915_gem_context *ctx, struct i915_vma *vma)
 	return i915_vma_pin(vma, 0, GEN8_LR_CONTEXT_ALIGN, flags);
 }
 
-static struct intel_ring *
-execlists_context_pin(struct intel_engine_cs *engine,
-		      struct i915_gem_context *ctx)
+static struct intel_context *
+__execlists_context_pin(struct intel_engine_cs *engine,
+			struct i915_gem_context *ctx,
+			struct intel_context *ce)
 {
-	struct intel_context *ce = to_intel_context(ctx, engine);
 	void *vaddr;
 	int ret;
 
-	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
-
-	if (likely(ce->pin_count++))
-		goto out;
-	GEM_BUG_ON(!ce->pin_count); /* no overflow please! */
-
-	ret = execlists_context_deferred_alloc(ctx, engine);
+	ret = execlists_context_deferred_alloc(ctx, engine, ce);
 	if (ret)
 		goto err;
 	GEM_BUG_ON(!ce->state);
@@ -1378,17 +1336,17 @@ execlists_context_pin(struct intel_engine_cs *engine,
 	if (ret)
 		goto unpin_map;
 
-	intel_lr_context_descriptor_update(ctx, engine);
+	intel_lr_context_descriptor_update(ctx, engine, ce);
 
 	ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
 	ce->lrc_reg_state[CTX_RING_BUFFER_START+1] =
 		i915_ggtt_offset(ce->ring->vma);
+	GEM_BUG_ON(!intel_ring_offset_valid(ce->ring, ce->ring->head));
 	ce->lrc_reg_state[CTX_RING_HEAD+1] = ce->ring->head;
 
 	ce->state->obj->pin_global++;
 	i915_gem_context_get(ctx);
-out:
-	return ce->ring;
+	return ce;
 
 unpin_map:
 	i915_gem_object_unpin_map(ce->state->obj);
@@ -1399,33 +1357,33 @@ err:
 	return ERR_PTR(ret);
 }
 
-static void execlists_context_unpin(struct intel_engine_cs *engine,
-				    struct i915_gem_context *ctx)
+static const struct intel_context_ops execlists_context_ops = {
+	.unpin = execlists_context_unpin,
+	.destroy = execlists_context_destroy,
+};
+
+static struct intel_context *
+execlists_context_pin(struct intel_engine_cs *engine,
+		      struct i915_gem_context *ctx)
 {
 	struct intel_context *ce = to_intel_context(ctx, engine);
 
 	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
-	GEM_BUG_ON(ce->pin_count == 0);
 
-	if (--ce->pin_count)
-		return;
-
-	intel_ring_unpin(ce->ring);
+	if (likely(ce->pin_count++))
+		return ce;
+	GEM_BUG_ON(!ce->pin_count); /* no overflow please! */
 
-	ce->state->obj->pin_global--;
-	i915_gem_object_unpin_map(ce->state->obj);
-	i915_vma_unpin(ce->state);
+	ce->ops = &execlists_context_ops;
 
-	i915_gem_context_put(ctx);
+	return __execlists_context_pin(engine, ctx, ce);
 }
 
 static int execlists_request_alloc(struct i915_request *request)
 {
-	struct intel_context *ce =
-		to_intel_context(request->ctx, request->engine);
 	int ret;
 
-	GEM_BUG_ON(!ce->pin_count);
+	GEM_BUG_ON(!request->hw_context->pin_count);
 
 	/* Flush enough space to reduce the likelihood of waiting after
 	 * we start building the request - in which case we will just
@@ -1538,29 +1496,56 @@ static u32 *gen8_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
 	return batch;
 }
 
-static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
+struct lri {
+	i915_reg_t reg;
+	u32 value;
+};
+
+static u32 *emit_lri(u32 *batch, const struct lri *lri, unsigned int count)
 {
-	*batch++ = MI_ARB_ON_OFF | MI_ARB_DISABLE;
+	GEM_BUG_ON(!count || count > 63);
 
-	/* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */
-	batch = gen8_emit_flush_coherentl3_wa(engine, batch);
+	*batch++ = MI_LOAD_REGISTER_IMM(count);
+	do {
+		*batch++ = i915_mmio_reg_offset(lri->reg);
+		*batch++ = lri->value;
+	} while (lri++, --count);
+	*batch++ = MI_NOOP;
 
-	*batch++ = MI_LOAD_REGISTER_IMM(3);
+	return batch;
+}
 
-	/* WaDisableGatherAtSetShaderCommonSlice:skl,bxt,kbl,glk */
-	*batch++ = i915_mmio_reg_offset(COMMON_SLICE_CHICKEN2);
-	*batch++ = _MASKED_BIT_DISABLE(
-			GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE);
+static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
+{
+	static const struct lri lri[] = {
+		/* WaDisableGatherAtSetShaderCommonSlice:skl,bxt,kbl,glk */
+		{
+			COMMON_SLICE_CHICKEN2,
+			__MASKED_FIELD(GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE,
+				       0),
+		},
+
+		/* BSpec: 11391 */
+		{
+			FF_SLICE_CHICKEN,
+			__MASKED_FIELD(FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX,
+				       FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX),
+		},
+
+		/* BSpec: 11299 */
+		{
+			_3D_CHICKEN3,
+			__MASKED_FIELD(_3D_CHICKEN_SF_PROVOKING_VERTEX_FIX,
+				       _3D_CHICKEN_SF_PROVOKING_VERTEX_FIX),
+		}
+	};
 
-	/* BSpec: 11391 */
-	*batch++ = i915_mmio_reg_offset(FF_SLICE_CHICKEN);
-	*batch++ = _MASKED_BIT_ENABLE(FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX);
+	*batch++ = MI_ARB_ON_OFF | MI_ARB_DISABLE;
 
-	/* BSpec: 11299 */
-	*batch++ = i915_mmio_reg_offset(_3D_CHICKEN3);
-	*batch++ = _MASKED_BIT_ENABLE(_3D_CHICKEN_SF_PROVOKING_VERTEX_FIX);
+	/* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */
+	batch = gen8_emit_flush_coherentl3_wa(engine, batch);
 
-	*batch++ = MI_NOOP;
+	batch = emit_lri(batch, lri, ARRAY_SIZE(lri));
 
 	/* WaClearSlmSpaceAtContextSwitch:kbl */
 	/* Actual scratch location is at 128 bytes offset */
@@ -1652,7 +1637,7 @@ static int lrc_setup_wa_ctx(struct intel_engine_cs *engine)
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
-	vma = i915_vma_instance(obj, &engine->i915->ggtt.base, NULL);
+	vma = i915_vma_instance(obj, &engine->i915->ggtt.vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		goto err;
@@ -1767,17 +1752,29 @@ static void enable_execlists(struct intel_engine_cs *engine)
 		I915_WRITE(RING_MODE_GEN7(engine),
 			   _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE));
 
+	I915_WRITE(RING_MI_MODE(engine->mmio_base),
+		   _MASKED_BIT_DISABLE(STOP_RING));
+
 	I915_WRITE(RING_HWS_PGA(engine->mmio_base),
 		   engine->status_page.ggtt_offset);
 	POSTING_READ(RING_HWS_PGA(engine->mmio_base));
+}
 
-	/* Following the reset, we need to reload the CSB read/write pointers */
-	engine->execlists.csb_head = -1;
+static bool unexpected_starting_state(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+	bool unexpected = false;
+
+	if (I915_READ(RING_MI_MODE(engine->mmio_base)) & STOP_RING) {
+		DRM_DEBUG_DRIVER("STOP_RING still set in RING_MI_MODE\n");
+		unexpected = true;
+	}
+
+	return unexpected;
 }
 
 static int gen8_init_common_ring(struct intel_engine_cs *engine)
 {
-	struct intel_engine_execlists * const execlists = &engine->execlists;
 	int ret;
 
 	ret = intel_mocs_init_engine(engine);
@@ -1785,13 +1782,14 @@ static int gen8_init_common_ring(struct intel_engine_cs *engine)
 		return ret;
 
 	intel_engine_reset_breadcrumbs(engine);
-	intel_engine_init_hangcheck(engine);
 
-	enable_execlists(engine);
+	if (GEM_SHOW_DEBUG() && unexpected_starting_state(engine)) {
+		struct drm_printer p = drm_debug_printer(__func__);
 
-	/* After a GPU reset, we may have requests to replay */
-	if (execlists->first)
-		tasklet_schedule(&execlists->tasklet);
+		intel_engine_dump(engine, &p, NULL);
+	}
+
+	enable_execlists(engine);
 
 	return 0;
 }
@@ -1833,8 +1831,69 @@ static int gen9_init_render_ring(struct intel_engine_cs *engine)
 	return 0;
 }
 
-static void reset_common_ring(struct intel_engine_cs *engine,
-			      struct i915_request *request)
+static struct i915_request *
+execlists_reset_prepare(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists * const execlists = &engine->execlists;
+	struct i915_request *request, *active;
+	unsigned long flags;
+
+	GEM_TRACE("%s\n", engine->name);
+
+	/*
+	 * Prevent request submission to the hardware until we have
+	 * completed the reset in i915_gem_reset_finish(). If a request
+	 * is completed by one engine, it may then queue a request
+	 * to a second via its execlists->tasklet *just* as we are
+	 * calling engine->init_hw() and also writing the ELSP.
+	 * Turning off the execlists->tasklet until the reset is over
+	 * prevents the race.
+	 */
+	__tasklet_disable_sync_once(&execlists->tasklet);
+
+	spin_lock_irqsave(&engine->timeline.lock, flags);
+
+	/*
+	 * We want to flush the pending context switches, having disabled
+	 * the tasklet above, we can assume exclusive access to the execlists.
+	 * For this allows us to catch up with an inflight preemption event,
+	 * and avoid blaming an innocent request if the stall was due to the
+	 * preemption itself.
+	 */
+	process_csb(engine);
+
+	/*
+	 * The last active request can then be no later than the last request
+	 * now in ELSP[0]. So search backwards from there, so that if the GPU
+	 * has advanced beyond the last CSB update, it will be pardoned.
+	 */
+	active = NULL;
+	request = port_request(execlists->port);
+	if (request) {
+		/*
+		 * Prevent the breadcrumb from advancing before we decide
+		 * which request is currently active.
+		 */
+		intel_engine_stop_cs(engine);
+
+		list_for_each_entry_from_reverse(request,
+						 &engine->timeline.requests,
+						 link) {
+			if (__i915_request_completed(request,
+						     request->global_seqno))
+				break;
+
+			active = request;
+		}
+	}
+
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
+
+	return active;
+}
+
+static void execlists_reset(struct intel_engine_cs *engine,
+			    struct i915_request *request)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	unsigned long flags;
@@ -1844,8 +1903,7 @@ static void reset_common_ring(struct intel_engine_cs *engine,
 		  engine->name, request ? request->global_seqno : 0,
 		  intel_engine_get_seqno(engine));
 
-	/* See execlists_cancel_requests() for the irq/spinlock split. */
-	local_irq_save(flags);
+	spin_lock_irqsave(&engine->timeline.lock, flags);
 
 	/*
 	 * Catch up with any missed context-switch interrupts.
@@ -1857,14 +1915,14 @@ static void reset_common_ring(struct intel_engine_cs *engine,
 	 * requests were completed.
 	 */
 	execlists_cancel_port_requests(execlists);
-	reset_irq(engine);
 
 	/* Push back any incomplete requests for replay after the reset. */
-	spin_lock(&engine->timeline.lock);
 	__unwind_incomplete_requests(engine);
-	spin_unlock(&engine->timeline.lock);
 
-	local_irq_restore(flags);
+	/* Following the reset, we need to reload the CSB read/write pointers */
+	reset_csb_pointers(&engine->execlists);
+
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 
 	/*
 	 * If the request was innocent, we leave the request in the ELSP
@@ -1888,35 +1946,52 @@ static void reset_common_ring(struct intel_engine_cs *engine,
 	 * future request will be after userspace has had the opportunity
 	 * to recreate its own state.
 	 */
-	regs = to_intel_context(request->ctx, engine)->lrc_reg_state;
-	if (engine->default_state) {
-		void *defaults;
-
-		defaults = i915_gem_object_pin_map(engine->default_state,
-						   I915_MAP_WB);
-		if (!IS_ERR(defaults)) {
-			memcpy(regs, /* skip restoring the vanilla PPHWSP */
-			       defaults + LRC_STATE_PN * PAGE_SIZE,
-			       engine->context_size - PAGE_SIZE);
-			i915_gem_object_unpin_map(engine->default_state);
-		}
+	regs = request->hw_context->lrc_reg_state;
+	if (engine->pinned_default_state) {
+		memcpy(regs, /* skip restoring the vanilla PPHWSP */
+		       engine->pinned_default_state + LRC_STATE_PN * PAGE_SIZE,
+		       engine->context_size - PAGE_SIZE);
 	}
-	execlists_init_reg_state(regs, request->ctx, engine, request->ring);
+	execlists_init_reg_state(regs,
+				 request->gem_context, engine, request->ring);
 
 	/* Move the RING_HEAD onto the breadcrumb, past the hanging batch */
 	regs[CTX_RING_BUFFER_START + 1] = i915_ggtt_offset(request->ring->vma);
-	regs[CTX_RING_HEAD + 1] = request->postfix;
 
-	request->ring->head = request->postfix;
+	request->ring->head = intel_ring_wrap(request->ring, request->postfix);
+	regs[CTX_RING_HEAD + 1] = request->ring->head;
+
 	intel_ring_update_space(request->ring);
 
 	/* Reset WaIdleLiteRestore:bdw,skl as well */
 	unwind_wa_tail(request);
 }
 
+static void execlists_reset_finish(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists * const execlists = &engine->execlists;
+
+	/* After a GPU reset, we may have requests to replay */
+	if (!RB_EMPTY_ROOT(&execlists->queue.rb_root))
+		tasklet_schedule(&execlists->tasklet);
+
+	/*
+	 * Flush the tasklet while we still have the forcewake to be sure
+	 * that it is not allowed to sleep before we restart and reload a
+	 * context.
+	 *
+	 * As before (with execlists_reset_prepare) we rely on the caller
+	 * serialising multiple attempts to reset so that we know that we
+	 * are the only one manipulating tasklet state.
+	 */
+	__tasklet_enable_sync_once(&execlists->tasklet);
+
+	GEM_TRACE("%s\n", engine->name);
+}
+
 static int intel_logical_ring_emit_pdps(struct i915_request *rq)
 {
-	struct i915_hw_ppgtt *ppgtt = rq->ctx->ppgtt;
+	struct i915_hw_ppgtt *ppgtt = rq->gem_context->ppgtt;
 	struct intel_engine_cs *engine = rq->engine;
 	const int num_lri_cmds = GEN8_3LVL_PDPES * 2;
 	u32 *cs;
@@ -1955,15 +2030,15 @@ static int gen8_emit_bb_start(struct i915_request *rq,
 	 * it is unsafe in case of lite-restore (because the ctx is
 	 * not idle). PML4 is allocated during ppgtt init so this is
 	 * not needed in 48-bit.*/
-	if (rq->ctx->ppgtt &&
-	    (intel_engine_flag(rq->engine) & rq->ctx->ppgtt->pd_dirty_rings) &&
-	    !i915_vm_is_48bit(&rq->ctx->ppgtt->base) &&
+	if (rq->gem_context->ppgtt &&
+	    (intel_engine_flag(rq->engine) & rq->gem_context->ppgtt->pd_dirty_rings) &&
+	    !i915_vm_is_48bit(&rq->gem_context->ppgtt->vm) &&
 	    !intel_vgpu_active(rq->i915)) {
 		ret = intel_logical_ring_emit_pdps(rq);
 		if (ret)
 			return ret;
 
-		rq->ctx->ppgtt->pd_dirty_rings &= ~intel_engine_flag(rq->engine);
+		rq->gem_context->ppgtt->pd_dirty_rings &= ~intel_engine_flag(rq->engine);
 	}
 
 	cs = intel_ring_begin(rq, 6);
@@ -2217,13 +2292,15 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *engine)
 	kfree(engine);
 }
 
-static void execlists_set_default_submission(struct intel_engine_cs *engine)
+void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
 {
 	engine->submit_request = execlists_submit_request;
 	engine->cancel_requests = execlists_cancel_requests;
 	engine->schedule = execlists_schedule;
 	engine->execlists.tasklet.func = execlists_submission_tasklet;
 
+	engine->reset.prepare = execlists_reset_prepare;
+
 	engine->park = NULL;
 	engine->unpark = NULL;
 
@@ -2243,18 +2320,19 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 {
 	/* Default vfuncs which can be overriden by each engine. */
 	engine->init_hw = gen8_init_common_ring;
-	engine->reset_hw = reset_common_ring;
 
-	engine->context_pin = execlists_context_pin;
-	engine->context_unpin = execlists_context_unpin;
+	engine->reset.prepare = execlists_reset_prepare;
+	engine->reset.reset = execlists_reset;
+	engine->reset.finish = execlists_reset_finish;
 
+	engine->context_pin = execlists_context_pin;
 	engine->request_alloc = execlists_request_alloc;
 
 	engine->emit_flush = gen8_emit_flush;
 	engine->emit_breadcrumb = gen8_emit_breadcrumb;
 	engine->emit_breadcrumb_sz = gen8_emit_breadcrumb_sz;
 
-	engine->set_default_submission = execlists_set_default_submission;
+	engine->set_default_submission = intel_execlists_set_default_submission;
 
 	if (INTEL_GEN(engine->i915) < 11) {
 		engine->irq_enable = gen8_logical_ring_enable_irq;
@@ -2294,28 +2372,11 @@ logical_ring_default_irqs(struct intel_engine_cs *engine)
 static void
 logical_ring_setup(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
-	enum forcewake_domains fw_domains;
-
 	intel_engine_setup_common(engine);
 
 	/* Intentionally left blank. */
 	engine->buffer = NULL;
 
-	fw_domains = intel_uncore_forcewake_for_reg(dev_priv,
-						    RING_ELSP(engine),
-						    FW_REG_WRITE);
-
-	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
-						     RING_CONTEXT_STATUS_PTR(engine),
-						     FW_REG_READ | FW_REG_WRITE);
-
-	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
-						     RING_CONTEXT_STATUS_BUF_BASE(engine),
-						     FW_REG_READ);
-
-	engine->execlists.fw_domains = fw_domains;
-
 	tasklet_init(&engine->execlists.tasklet,
 		     execlists_submission_tasklet, (unsigned long)engine);
 
@@ -2323,33 +2384,61 @@ logical_ring_setup(struct intel_engine_cs *engine)
 	logical_ring_default_irqs(engine);
 }
 
+static bool csb_force_mmio(struct drm_i915_private *i915)
+{
+	/* Older GVT emulation depends upon intercepting CSB mmio */
+	return intel_vgpu_active(i915) && !intel_vgpu_has_hwsp_emulation(i915);
+}
+
 static int logical_ring_init(struct intel_engine_cs *engine)
 {
+	struct drm_i915_private *i915 = engine->i915;
+	struct intel_engine_execlists * const execlists = &engine->execlists;
 	int ret;
 
 	ret = intel_engine_init_common(engine);
 	if (ret)
 		goto error;
 
-	if (HAS_LOGICAL_RING_ELSQ(engine->i915)) {
-		engine->execlists.submit_reg = engine->i915->regs +
+	if (HAS_LOGICAL_RING_ELSQ(i915)) {
+		execlists->submit_reg = i915->regs +
 			i915_mmio_reg_offset(RING_EXECLIST_SQ_CONTENTS(engine));
-		engine->execlists.ctrl_reg = engine->i915->regs +
+		execlists->ctrl_reg = i915->regs +
 			i915_mmio_reg_offset(RING_EXECLIST_CONTROL(engine));
 	} else {
-		engine->execlists.submit_reg = engine->i915->regs +
+		execlists->submit_reg = i915->regs +
 			i915_mmio_reg_offset(RING_ELSP(engine));
 	}
 
-	engine->execlists.preempt_complete_status = ~0u;
-	if (engine->i915->preempt_context) {
+	execlists->preempt_complete_status = ~0u;
+	if (i915->preempt_context) {
 		struct intel_context *ce =
-			to_intel_context(engine->i915->preempt_context, engine);
+			to_intel_context(i915->preempt_context, engine);
 
-		engine->execlists.preempt_complete_status =
+		execlists->preempt_complete_status =
 			upper_32_bits(ce->lrc_desc);
 	}
 
+	execlists->csb_read =
+		i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine));
+	if (csb_force_mmio(i915)) {
+		execlists->csb_status = (u32 __force *)
+			(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0)));
+
+		execlists->csb_write = (u32 __force *)execlists->csb_read;
+		execlists->csb_write_reset =
+			_MASKED_FIELD(GEN8_CSB_WRITE_PTR_MASK,
+				      GEN8_CSB_ENTRIES - 1);
+	} else {
+		execlists->csb_status =
+			&engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
+
+		execlists->csb_write =
+			&engine->status_page.page_addr[intel_hws_csb_write_index(i915)];
+		execlists->csb_write_reset = GEN8_CSB_ENTRIES - 1;
+	}
+	reset_csb_pointers(execlists);
+
 	return 0;
 
 error:
@@ -2482,7 +2571,7 @@ static void execlists_init_reg_state(u32 *regs,
 	struct drm_i915_private *dev_priv = engine->i915;
 	struct i915_hw_ppgtt *ppgtt = ctx->ppgtt ?: dev_priv->mm.aliasing_ppgtt;
 	u32 base = engine->mmio_base;
-	bool rcs = engine->id == RCS;
+	bool rcs = engine->class == RENDER_CLASS;
 
 	/* A context is actually a big batch buffer with several
 	 * MI_LOAD_REGISTER_IMM commands followed by (reg, value) pairs. The
@@ -2550,7 +2639,7 @@ static void execlists_init_reg_state(u32 *regs,
 	CTX_REG(regs, CTX_PDP0_UDW, GEN8_RING_PDP_UDW(engine, 0), 0);
 	CTX_REG(regs, CTX_PDP0_LDW, GEN8_RING_PDP_LDW(engine, 0), 0);
 
-	if (ppgtt && i915_vm_is_48bit(&ppgtt->base)) {
+	if (ppgtt && i915_vm_is_48bit(&ppgtt->vm)) {
 		/* 64b PPGTT (48bit canonical)
 		 * PDP0_DESCRIPTOR contains the base address to PML4 and
 		 * other PDP Descriptors are ignored.
@@ -2629,10 +2718,10 @@ err_unpin_ctx:
 }
 
 static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
-					    struct intel_engine_cs *engine)
+					    struct intel_engine_cs *engine,
+					    struct intel_context *ce)
 {
 	struct drm_i915_gem_object *ctx_obj;
-	struct intel_context *ce = to_intel_context(ctx, engine);
 	struct i915_vma *vma;
 	uint32_t context_size;
 	struct intel_ring *ring;
@@ -2654,7 +2743,7 @@ static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
 	if (IS_ERR(ctx_obj))
 		return PTR_ERR(ctx_obj);
 
-	vma = i915_vma_instance(ctx_obj, &ctx->i915->ggtt.base, NULL);
+	vma = i915_vma_instance(ctx_obj, &ctx->i915->ggtt.vm, NULL);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto error_deref_obj;
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 4ec7d8dd13c8..4dfb78e3ec7e 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -104,11 +104,6 @@ struct i915_gem_context;
 
 void intel_lr_context_resume(struct drm_i915_private *dev_priv);
 
-static inline uint64_t
-intel_lr_context_descriptor(struct i915_gem_context *ctx,
-			    struct intel_engine_cs *engine)
-{
-	return to_intel_context(ctx, engine)->lrc_desc;
-}
+void intel_execlists_set_default_submission(struct intel_engine_cs *engine);
 
 #endif /* _INTEL_LRC_H_ */
diff --git a/drivers/gpu/drm/i915/intel_lspcon.c b/drivers/gpu/drm/i915/intel_lspcon.c
index 8ae8f42f430a..5dae16ccd9f1 100644
--- a/drivers/gpu/drm/i915/intel_lspcon.c
+++ b/drivers/gpu/drm/i915/intel_lspcon.c
@@ -116,7 +116,7 @@ static int lspcon_change_mode(struct intel_lspcon *lspcon,
 
 static bool lspcon_wake_native_aux_ch(struct intel_lspcon *lspcon)
 {
-	uint8_t rev;
+	u8 rev;
 
 	if (drm_dp_dpcd_readb(&lspcon_to_intel_dp(lspcon)->aux, DP_DPCD_REV,
 			      &rev) != 1) {
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 48f618dc9abb..f9f3b0885ba5 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -44,8 +44,6 @@
 /* Private structure for the integrated LVDS support */
 struct intel_lvds_connector {
 	struct intel_connector base;
-
-	struct notifier_block lid_notifier;
 };
 
 struct intel_lvds_pps {
@@ -85,34 +83,35 @@ static struct intel_lvds_connector *to_lvds_connector(struct drm_connector *conn
 	return container_of(connector, struct intel_lvds_connector, base.base);
 }
 
+bool intel_lvds_port_enabled(struct drm_i915_private *dev_priv,
+			     i915_reg_t lvds_reg, enum pipe *pipe)
+{
+	u32 val;
+
+	val = I915_READ(lvds_reg);
+
+	/* asserts want to know the pipe even if the port is disabled */
+	if (HAS_PCH_CPT(dev_priv))
+		*pipe = (val & LVDS_PIPE_SEL_MASK_CPT) >> LVDS_PIPE_SEL_SHIFT_CPT;
+	else
+		*pipe = (val & LVDS_PIPE_SEL_MASK) >> LVDS_PIPE_SEL_SHIFT;
+
+	return val & LVDS_PORT_EN;
+}
+
 static bool intel_lvds_get_hw_state(struct intel_encoder *encoder,
 				    enum pipe *pipe)
 {
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
-	u32 tmp;
 	bool ret;
 
 	if (!intel_display_power_get_if_enabled(dev_priv,
 						encoder->power_domain))
 		return false;
 
-	ret = false;
-
-	tmp = I915_READ(lvds_encoder->reg);
-
-	if (!(tmp & LVDS_PORT_EN))
-		goto out;
-
-	if (HAS_PCH_CPT(dev_priv))
-		*pipe = PORT_TO_PIPE_CPT(tmp);
-	else
-		*pipe = PORT_TO_PIPE(tmp);
-
-	ret = true;
+	ret = intel_lvds_port_enabled(dev_priv, lvds_encoder->reg, pipe);
 
-out:
 	intel_display_power_put(dev_priv, encoder->power_domain);
 
 	return ret;
@@ -255,14 +254,11 @@ static void intel_pre_enable_lvds(struct intel_encoder *encoder,
 	temp |= LVDS_PORT_EN | LVDS_A0A2_CLKA_POWER_UP;
 
 	if (HAS_PCH_CPT(dev_priv)) {
-		temp &= ~PORT_TRANS_SEL_MASK;
-		temp |= PORT_TRANS_SEL_CPT(pipe);
+		temp &= ~LVDS_PIPE_SEL_MASK_CPT;
+		temp |= LVDS_PIPE_SEL_CPT(pipe);
 	} else {
-		if (pipe == 1) {
-			temp |= LVDS_PIPEB_SELECT;
-		} else {
-			temp &= ~LVDS_PIPEB_SELECT;
-		}
+		temp &= ~LVDS_PIPE_SEL_MASK;
+		temp |= LVDS_PIPE_SEL(pipe);
 	}
 
 	/* set the corresponsding LVDS_BORDER bit */
@@ -454,26 +450,9 @@ static bool intel_lvds_compute_config(struct intel_encoder *intel_encoder,
 	return true;
 }
 
-/*
- * Detect the LVDS connection.
- *
- * Since LVDS doesn't have hotlug, we use the lid as a proxy.  Open means
- * connected and closed means disconnected.  We also send hotplug events as
- * needed, using lid status notification from the input layer.
- */
 static enum drm_connector_status
 intel_lvds_detect(struct drm_connector *connector, bool force)
 {
-	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	enum drm_connector_status status;
-
-	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
-		      connector->base.id, connector->name);
-
-	status = intel_panel_detect(dev_priv);
-	if (status != connector_status_unknown)
-		return status;
-
 	return connector_status_connected;
 }
 
@@ -498,117 +477,6 @@ static int intel_lvds_get_modes(struct drm_connector *connector)
 	return 1;
 }
 
-static int intel_no_modeset_on_lid_dmi_callback(const struct dmi_system_id *id)
-{
-	DRM_INFO("Skipping forced modeset for %s\n", id->ident);
-	return 1;
-}
-
-/* The GPU hangs up on these systems if modeset is performed on LID open */
-static const struct dmi_system_id intel_no_modeset_on_lid[] = {
-	{
-		.callback = intel_no_modeset_on_lid_dmi_callback,
-		.ident = "Toshiba Tecra A11",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "TECRA A11"),
-		},
-	},
-
-	{ }	/* terminating entry */
-};
-
-/*
- * Lid events. Note the use of 'modeset':
- *  - we set it to MODESET_ON_LID_OPEN on lid close,
- *    and set it to MODESET_DONE on open
- *  - we use it as a "only once" bit (ie we ignore
- *    duplicate events where it was already properly set)
- *  - the suspend/resume paths will set it to
- *    MODESET_SUSPENDED and ignore the lid open event,
- *    because they restore the mode ("lid open").
- */
-static int intel_lid_notify(struct notifier_block *nb, unsigned long val,
-			    void *unused)
-{
-	struct intel_lvds_connector *lvds_connector =
-		container_of(nb, struct intel_lvds_connector, lid_notifier);
-	struct drm_connector *connector = &lvds_connector->base.base;
-	struct drm_device *dev = connector->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-
-	if (dev->switch_power_state != DRM_SWITCH_POWER_ON)
-		return NOTIFY_OK;
-
-	mutex_lock(&dev_priv->modeset_restore_lock);
-	if (dev_priv->modeset_restore == MODESET_SUSPENDED)
-		goto exit;
-	/*
-	 * check and update the status of LVDS connector after receiving
-	 * the LID nofication event.
-	 */
-	connector->status = connector->funcs->detect(connector, false);
-
-	/* Don't force modeset on machines where it causes a GPU lockup */
-	if (dmi_check_system(intel_no_modeset_on_lid))
-		goto exit;
-	if (!acpi_lid_open()) {
-		/* do modeset on next lid open event */
-		dev_priv->modeset_restore = MODESET_ON_LID_OPEN;
-		goto exit;
-	}
-
-	if (dev_priv->modeset_restore == MODESET_DONE)
-		goto exit;
-
-	/*
-	 * Some old platform's BIOS love to wreak havoc while the lid is closed.
-	 * We try to detect this here and undo any damage. The split for PCH
-	 * platforms is rather conservative and a bit arbitrary expect that on
-	 * those platforms VGA disabling requires actual legacy VGA I/O access,
-	 * and as part of the cleanup in the hw state restore we also redisable
-	 * the vga plane.
-	 */
-	if (!HAS_PCH_SPLIT(dev_priv))
-		intel_display_resume(dev);
-
-	dev_priv->modeset_restore = MODESET_DONE;
-
-exit:
-	mutex_unlock(&dev_priv->modeset_restore_lock);
-	return NOTIFY_OK;
-}
-
-static int
-intel_lvds_connector_register(struct drm_connector *connector)
-{
-	struct intel_lvds_connector *lvds = to_lvds_connector(connector);
-	int ret;
-
-	ret = intel_connector_register(connector);
-	if (ret)
-		return ret;
-
-	lvds->lid_notifier.notifier_call = intel_lid_notify;
-	if (acpi_lid_notifier_register(&lvds->lid_notifier)) {
-		DRM_DEBUG_KMS("lid notifier registration failed\n");
-		lvds->lid_notifier.notifier_call = NULL;
-	}
-
-	return 0;
-}
-
-static void
-intel_lvds_connector_unregister(struct drm_connector *connector)
-{
-	struct intel_lvds_connector *lvds = to_lvds_connector(connector);
-
-	if (lvds->lid_notifier.notifier_call)
-		acpi_lid_notifier_unregister(&lvds->lid_notifier);
-
-	intel_connector_unregister(connector);
-}
-
 /**
  * intel_lvds_destroy - unregister and free LVDS structures
  * @connector: connector to free
@@ -641,8 +509,8 @@ static const struct drm_connector_funcs intel_lvds_connector_funcs = {
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.atomic_get_property = intel_digital_connector_atomic_get_property,
 	.atomic_set_property = intel_digital_connector_atomic_set_property,
-	.late_register = intel_lvds_connector_register,
-	.early_unregister = intel_lvds_connector_unregister,
+	.late_register = intel_connector_register,
+	.early_unregister = intel_connector_unregister,
 	.destroy = intel_lvds_destroy,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 	.atomic_duplicate_state = intel_digital_connector_duplicate_state,
@@ -948,7 +816,11 @@ static bool compute_is_dual_link_lvds(struct intel_lvds_encoder *lvds_encoder)
 	 * register is uninitialized.
 	 */
 	val = I915_READ(lvds_encoder->reg);
-	if (!(val & ~(LVDS_PIPE_MASK | LVDS_DETECTED)))
+	if (HAS_PCH_CPT(dev_priv))
+		val &= ~(LVDS_DETECTED | LVDS_PIPE_SEL_MASK_CPT);
+	else
+		val &= ~(LVDS_DETECTED | LVDS_PIPE_SEL_MASK);
+	if (val == 0)
 		val = dev_priv->vbt.bios_lvds_val;
 
 	return (val & LVDS_CLKB_POWER_MASK) == LVDS_CLKB_POWER_UP;
@@ -1003,8 +875,16 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 		return;
 
 	/* Skip init on machines we know falsely report LVDS */
-	if (dmi_check_system(intel_no_lvds))
+	if (dmi_check_system(intel_no_lvds)) {
+		WARN(!dev_priv->vbt.int_lvds_support,
+		     "Useless DMI match. Internal LVDS support disabled by VBT\n");
+		return;
+	}
+
+	if (!dev_priv->vbt.int_lvds_support) {
+		DRM_DEBUG_KMS("Internal LVDS support disabled by VBT\n");
 		return;
+	}
 
 	if (HAS_PCH_SPLIT(dev_priv))
 		lvds_reg = PCH_LVDS;
@@ -1016,10 +896,6 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 	if (HAS_PCH_SPLIT(dev_priv)) {
 		if ((lvds & LVDS_DETECTED) == 0)
 			return;
-		if (dev_priv->vbt.edp.support) {
-			DRM_DEBUG_KMS("disable LVDS for eDP support\n");
-			return;
-		}
 	}
 
 	pin = GMBUS_PIN_PANEL;
@@ -1108,8 +984,6 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 	 * 2) check for VBT data
 	 * 3) check to see if LVDS is already on
 	 *    if none of the above, no panel
-	 * 4) make sure lid is open
-	 *    if closed, act like it's not there for now
 	 */
 
 	/*
@@ -1125,7 +999,7 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 				    intel_gmbus_get_adapter(dev_priv, pin));
 	if (edid) {
 		if (drm_add_edid_modes(connector, edid)) {
-			drm_mode_connector_update_edid_property(connector,
+			drm_connector_update_edid_property(connector,
 								edid);
 		} else {
 			kfree(edid);
diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c
index b39846613e3c..ca44bf368e24 100644
--- a/drivers/gpu/drm/i915/intel_modes.c
+++ b/drivers/gpu/drm/i915/intel_modes.c
@@ -40,7 +40,7 @@ int intel_connector_update_modes(struct drm_connector *connector,
 {
 	int ret;
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
 
 	return ret;
diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c
index c58e5f53bab0..e034b4166d32 100644
--- a/drivers/gpu/drm/i915/intel_opregion.c
+++ b/drivers/gpu/drm/i915/intel_opregion.c
@@ -608,16 +608,16 @@ void intel_opregion_asle_intr(struct drm_i915_private *dev_priv)
 #define ACPI_EV_LID            (1<<1)
 #define ACPI_EV_DOCK           (1<<2)
 
-static struct intel_opregion *system_opregion;
-
+/*
+ * The only video events relevant to opregion are 0x80. These indicate either a
+ * docking event, lid switch or display switch request. In Linux, these are
+ * handled by the dock, button and video drivers.
+ */
 static int intel_opregion_video_event(struct notifier_block *nb,
 				      unsigned long val, void *data)
 {
-	/* The only video events relevant to opregion are 0x80. These indicate
-	   either a docking event, lid switch or display switch request. In
-	   Linux, these are handled by the dock, button and video drivers.
-	*/
-
+	struct intel_opregion *opregion = container_of(nb, struct intel_opregion,
+						       acpi_notifier);
 	struct acpi_bus_event *event = data;
 	struct opregion_acpi *acpi;
 	int ret = NOTIFY_OK;
@@ -625,10 +625,7 @@ static int intel_opregion_video_event(struct notifier_block *nb,
 	if (strcmp(event->device_class, ACPI_VIDEO_CLASS) != 0)
 		return NOTIFY_DONE;
 
-	if (!system_opregion)
-		return NOTIFY_DONE;
-
-	acpi = system_opregion->acpi;
+	acpi = opregion->acpi;
 
 	if (event->type == 0x80 && ((acpi->cevt & 1) == 0))
 		ret = NOTIFY_BAD;
@@ -638,10 +635,6 @@ static int intel_opregion_video_event(struct notifier_block *nb,
 	return ret;
 }
 
-static struct notifier_block intel_opregion_notifier = {
-	.notifier_call = intel_opregion_video_event,
-};
-
 /*
  * Initialise the DIDL field in opregion. This passes a list of devices to
  * the firmware. Values are defined by section B.4.2 of the ACPI specification
@@ -797,8 +790,8 @@ void intel_opregion_register(struct drm_i915_private *dev_priv)
 		opregion->acpi->csts = 0;
 		opregion->acpi->drdy = 1;
 
-		system_opregion = opregion;
-		register_acpi_notifier(&intel_opregion_notifier);
+		opregion->acpi_notifier.notifier_call = intel_opregion_video_event;
+		register_acpi_notifier(&opregion->acpi_notifier);
 	}
 
 	if (opregion->asle) {
@@ -822,8 +815,8 @@ void intel_opregion_unregister(struct drm_i915_private *dev_priv)
 	if (opregion->acpi) {
 		opregion->acpi->drdy = 0;
 
-		system_opregion = NULL;
-		unregister_acpi_notifier(&intel_opregion_notifier);
+		unregister_acpi_notifier(&opregion->acpi_notifier);
+		opregion->acpi_notifier.notifier_call = NULL;
 	}
 
 	/* just clear all opregion memory pointers now */
diff --git a/drivers/gpu/drm/i915/intel_opregion.h b/drivers/gpu/drm/i915/intel_opregion.h
index e0e437ba9e51..e8498a8cda3d 100644
--- a/drivers/gpu/drm/i915/intel_opregion.h
+++ b/drivers/gpu/drm/i915/intel_opregion.h
@@ -49,6 +49,7 @@ struct intel_opregion {
 	u32 vbt_size;
 	u32 *lid_state;
 	struct work_struct asle_work;
+	struct notifier_block acpi_notifier;
 };
 
 #define OPREGION_SIZE            (8 * 1024)
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index b443278e569c..4a9f139e7b73 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -375,26 +375,6 @@ out:
 	pipe_config->gmch_pfit.lvds_border_bits = border;
 }
 
-enum drm_connector_status
-intel_panel_detect(struct drm_i915_private *dev_priv)
-{
-	/* Assume that the BIOS does not lie through the OpRegion... */
-	if (!i915_modparams.panel_ignore_lid && dev_priv->opregion.lid_state) {
-		return *dev_priv->opregion.lid_state & 0x1 ?
-			connector_status_connected :
-			connector_status_disconnected;
-	}
-
-	switch (i915_modparams.panel_ignore_lid) {
-	case -2:
-		return connector_status_connected;
-	case -1:
-		return connector_status_disconnected;
-	default:
-		return connector_status_unknown;
-	}
-}
-
 /**
  * scale - scale values from one range to another
  * @source_val: value in range [@source_min..@source_max]
@@ -406,11 +386,11 @@ intel_panel_detect(struct drm_i915_private *dev_priv)
  * Return @source_val in range [@source_min..@source_max] scaled to range
  * [@target_min..@target_max].
  */
-static uint32_t scale(uint32_t source_val,
-		      uint32_t source_min, uint32_t source_max,
-		      uint32_t target_min, uint32_t target_max)
+static u32 scale(u32 source_val,
+		 u32 source_min, u32 source_max,
+		 u32 target_min, u32 target_max)
 {
-	uint64_t target_val;
+	u64 target_val;
 
 	WARN_ON(source_min > source_max);
 	WARN_ON(target_min > target_max);
diff --git a/drivers/gpu/drm/i915/intel_pipe_crc.c b/drivers/gpu/drm/i915/intel_pipe_crc.c
index 39a4e4edda07..849e1b69ba73 100644
--- a/drivers/gpu/drm/i915/intel_pipe_crc.c
+++ b/drivers/gpu/drm/i915/intel_pipe_crc.c
@@ -30,160 +30,6 @@
 #include <linux/debugfs.h>
 #include "intel_drv.h"
 
-struct pipe_crc_info {
-	const char *name;
-	struct drm_i915_private *dev_priv;
-	enum pipe pipe;
-};
-
-static int i915_pipe_crc_open(struct inode *inode, struct file *filep)
-{
-	struct pipe_crc_info *info = inode->i_private;
-	struct drm_i915_private *dev_priv = info->dev_priv;
-	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[info->pipe];
-
-	if (info->pipe >= INTEL_INFO(dev_priv)->num_pipes)
-		return -ENODEV;
-
-	spin_lock_irq(&pipe_crc->lock);
-
-	if (pipe_crc->opened) {
-		spin_unlock_irq(&pipe_crc->lock);
-		return -EBUSY; /* already open */
-	}
-
-	pipe_crc->opened = true;
-	filep->private_data = inode->i_private;
-
-	spin_unlock_irq(&pipe_crc->lock);
-
-	return 0;
-}
-
-static int i915_pipe_crc_release(struct inode *inode, struct file *filep)
-{
-	struct pipe_crc_info *info = inode->i_private;
-	struct drm_i915_private *dev_priv = info->dev_priv;
-	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[info->pipe];
-
-	spin_lock_irq(&pipe_crc->lock);
-	pipe_crc->opened = false;
-	spin_unlock_irq(&pipe_crc->lock);
-
-	return 0;
-}
-
-/* (6 fields, 8 chars each, space separated (5) + '\n') */
-#define PIPE_CRC_LINE_LEN	(6 * 8 + 5 + 1)
-/* account for \'0' */
-#define PIPE_CRC_BUFFER_LEN	(PIPE_CRC_LINE_LEN + 1)
-
-static int pipe_crc_data_count(struct intel_pipe_crc *pipe_crc)
-{
-	lockdep_assert_held(&pipe_crc->lock);
-	return CIRC_CNT(pipe_crc->head, pipe_crc->tail,
-			INTEL_PIPE_CRC_ENTRIES_NR);
-}
-
-static ssize_t
-i915_pipe_crc_read(struct file *filep, char __user *user_buf, size_t count,
-		   loff_t *pos)
-{
-	struct pipe_crc_info *info = filep->private_data;
-	struct drm_i915_private *dev_priv = info->dev_priv;
-	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[info->pipe];
-	char buf[PIPE_CRC_BUFFER_LEN];
-	int n_entries;
-	ssize_t bytes_read;
-
-	/*
-	 * Don't allow user space to provide buffers not big enough to hold
-	 * a line of data.
-	 */
-	if (count < PIPE_CRC_LINE_LEN)
-		return -EINVAL;
-
-	if (pipe_crc->source == INTEL_PIPE_CRC_SOURCE_NONE)
-		return 0;
-
-	/* nothing to read */
-	spin_lock_irq(&pipe_crc->lock);
-	while (pipe_crc_data_count(pipe_crc) == 0) {
-		int ret;
-
-		if (filep->f_flags & O_NONBLOCK) {
-			spin_unlock_irq(&pipe_crc->lock);
-			return -EAGAIN;
-		}
-
-		ret = wait_event_interruptible_lock_irq(pipe_crc->wq,
-				pipe_crc_data_count(pipe_crc), pipe_crc->lock);
-		if (ret) {
-			spin_unlock_irq(&pipe_crc->lock);
-			return ret;
-		}
-	}
-
-	/* We now have one or more entries to read */
-	n_entries = count / PIPE_CRC_LINE_LEN;
-
-	bytes_read = 0;
-	while (n_entries > 0) {
-		struct intel_pipe_crc_entry *entry =
-			&pipe_crc->entries[pipe_crc->tail];
-
-		if (CIRC_CNT(pipe_crc->head, pipe_crc->tail,
-			     INTEL_PIPE_CRC_ENTRIES_NR) < 1)
-			break;
-
-		BUILD_BUG_ON_NOT_POWER_OF_2(INTEL_PIPE_CRC_ENTRIES_NR);
-		pipe_crc->tail = (pipe_crc->tail + 1) &
-				 (INTEL_PIPE_CRC_ENTRIES_NR - 1);
-
-		bytes_read += snprintf(buf, PIPE_CRC_BUFFER_LEN,
-				       "%8u %8x %8x %8x %8x %8x\n",
-				       entry->frame, entry->crc[0],
-				       entry->crc[1], entry->crc[2],
-				       entry->crc[3], entry->crc[4]);
-
-		spin_unlock_irq(&pipe_crc->lock);
-
-		if (copy_to_user(user_buf, buf, PIPE_CRC_LINE_LEN))
-			return -EFAULT;
-
-		user_buf += PIPE_CRC_LINE_LEN;
-		n_entries--;
-
-		spin_lock_irq(&pipe_crc->lock);
-	}
-
-	spin_unlock_irq(&pipe_crc->lock);
-
-	return bytes_read;
-}
-
-static const struct file_operations i915_pipe_crc_fops = {
-	.owner = THIS_MODULE,
-	.open = i915_pipe_crc_open,
-	.read = i915_pipe_crc_read,
-	.release = i915_pipe_crc_release,
-};
-
-static struct pipe_crc_info i915_pipe_crc_data[I915_MAX_PIPES] = {
-	{
-		.name = "i915_pipe_A_crc",
-		.pipe = PIPE_A,
-	},
-	{
-		.name = "i915_pipe_B_crc",
-		.pipe = PIPE_B,
-	},
-	{
-		.name = "i915_pipe_C_crc",
-		.pipe = PIPE_C,
-	},
-};
-
 static const char * const pipe_crc_sources[] = {
 	"none",
 	"plane1",
@@ -197,29 +43,6 @@ static const char * const pipe_crc_sources[] = {
 	"auto",
 };
 
-static const char *pipe_crc_source_name(enum intel_pipe_crc_source source)
-{
-	BUILD_BUG_ON(ARRAY_SIZE(pipe_crc_sources) != INTEL_PIPE_CRC_SOURCE_MAX);
-	return pipe_crc_sources[source];
-}
-
-static int display_crc_ctl_show(struct seq_file *m, void *data)
-{
-	struct drm_i915_private *dev_priv = m->private;
-	enum pipe pipe;
-
-	for_each_pipe(dev_priv, pipe)
-		seq_printf(m, "%c %s\n", pipe_name(pipe),
-			   pipe_crc_source_name(dev_priv->pipe_crc[pipe].source));
-
-	return 0;
-}
-
-static int display_crc_ctl_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, display_crc_ctl_show, inode->i_private);
-}
-
 static int i8xx_pipe_crc_ctl_reg(enum intel_pipe_crc_source *source,
 				 uint32_t *val)
 {
@@ -616,177 +439,6 @@ static int get_new_crc_ctl_reg(struct drm_i915_private *dev_priv,
 		return ivb_pipe_crc_ctl_reg(dev_priv, pipe, source, val, set_wa);
 }
 
-static int pipe_crc_set_source(struct drm_i915_private *dev_priv,
-			       enum pipe pipe,
-			       enum intel_pipe_crc_source source)
-{
-	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[pipe];
-	enum intel_display_power_domain power_domain;
-	u32 val = 0; /* shut up gcc */
-	int ret;
-
-	if (pipe_crc->source == source)
-		return 0;
-
-	/* forbid changing the source without going back to 'none' */
-	if (pipe_crc->source && source)
-		return -EINVAL;
-
-	power_domain = POWER_DOMAIN_PIPE(pipe);
-	if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) {
-		DRM_DEBUG_KMS("Trying to capture CRC while pipe is off\n");
-		return -EIO;
-	}
-
-	ret = get_new_crc_ctl_reg(dev_priv, pipe, &source, &val, true);
-	if (ret != 0)
-		goto out;
-
-	/* none -> real source transition */
-	if (source) {
-		struct intel_pipe_crc_entry *entries;
-
-		DRM_DEBUG_DRIVER("collecting CRCs for pipe %c, %s\n",
-				 pipe_name(pipe), pipe_crc_source_name(source));
-
-		entries = kcalloc(INTEL_PIPE_CRC_ENTRIES_NR,
-				  sizeof(pipe_crc->entries[0]),
-				  GFP_KERNEL);
-		if (!entries) {
-			ret = -ENOMEM;
-			goto out;
-		}
-
-		spin_lock_irq(&pipe_crc->lock);
-		kfree(pipe_crc->entries);
-		pipe_crc->entries = entries;
-		pipe_crc->head = 0;
-		pipe_crc->tail = 0;
-		spin_unlock_irq(&pipe_crc->lock);
-	}
-
-	pipe_crc->source = source;
-
-	I915_WRITE(PIPE_CRC_CTL(pipe), val);
-	POSTING_READ(PIPE_CRC_CTL(pipe));
-
-	/* real source -> none transition */
-	if (!source) {
-		struct intel_pipe_crc_entry *entries;
-		struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv,
-								  pipe);
-
-		DRM_DEBUG_DRIVER("stopping CRCs for pipe %c\n",
-				 pipe_name(pipe));
-
-		drm_modeset_lock(&crtc->base.mutex, NULL);
-		if (crtc->base.state->active)
-			intel_wait_for_vblank(dev_priv, pipe);
-		drm_modeset_unlock(&crtc->base.mutex);
-
-		spin_lock_irq(&pipe_crc->lock);
-		entries = pipe_crc->entries;
-		pipe_crc->entries = NULL;
-		pipe_crc->head = 0;
-		pipe_crc->tail = 0;
-		spin_unlock_irq(&pipe_crc->lock);
-
-		kfree(entries);
-
-		if (IS_G4X(dev_priv))
-			g4x_undo_pipe_scramble_reset(dev_priv, pipe);
-		else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-			vlv_undo_pipe_scramble_reset(dev_priv, pipe);
-		else if ((IS_HASWELL(dev_priv) ||
-			  IS_BROADWELL(dev_priv)) && pipe == PIPE_A)
-			hsw_pipe_A_crc_wa(dev_priv, false);
-	}
-
-	ret = 0;
-
-out:
-	intel_display_power_put(dev_priv, power_domain);
-
-	return ret;
-}
-
-/*
- * Parse pipe CRC command strings:
- *   command: wsp* object wsp+ name wsp+ source wsp*
- *   object: 'pipe'
- *   name: (A | B | C)
- *   source: (none | plane1 | plane2 | pf)
- *   wsp: (#0x20 | #0x9 | #0xA)+
- *
- * eg.:
- *  "pipe A plane1"  ->  Start CRC computations on plane1 of pipe A
- *  "pipe A none"    ->  Stop CRC
- */
-static int display_crc_ctl_tokenize(char *buf, char *words[], int max_words)
-{
-	int n_words = 0;
-
-	while (*buf) {
-		char *end;
-
-		/* skip leading white space */
-		buf = skip_spaces(buf);
-		if (!*buf)
-			break;	/* end of buffer */
-
-		/* find end of word */
-		for (end = buf; *end && !isspace(*end); end++)
-			;
-
-		if (n_words == max_words) {
-			DRM_DEBUG_DRIVER("too many words, allowed <= %d\n",
-					 max_words);
-			return -EINVAL;	/* ran out of words[] before bytes */
-		}
-
-		if (*end)
-			*end++ = '\0';
-		words[n_words++] = buf;
-		buf = end;
-	}
-
-	return n_words;
-}
-
-enum intel_pipe_crc_object {
-	PIPE_CRC_OBJECT_PIPE,
-};
-
-static const char * const pipe_crc_objects[] = {
-	"pipe",
-};
-
-static int
-display_crc_ctl_parse_object(const char *buf, enum intel_pipe_crc_object *o)
-{
-	int i;
-
-	i = match_string(pipe_crc_objects, ARRAY_SIZE(pipe_crc_objects), buf);
-	if (i < 0)
-		return i;
-
-	*o = i;
-	return 0;
-}
-
-static int display_crc_ctl_parse_pipe(struct drm_i915_private *dev_priv,
-				      const char *buf, enum pipe *pipe)
-{
-	const char name = buf[0];
-
-	if (name < 'A' || name >= pipe_name(INTEL_INFO(dev_priv)->num_pipes))
-		return -EINVAL;
-
-	*pipe = name - 'A';
-
-	return 0;
-}
-
 static int
 display_crc_ctl_parse_source(const char *buf, enum intel_pipe_crc_source *s)
 {
@@ -805,81 +457,6 @@ display_crc_ctl_parse_source(const char *buf, enum intel_pipe_crc_source *s)
 	return 0;
 }
 
-static int display_crc_ctl_parse(struct drm_i915_private *dev_priv,
-				 char *buf, size_t len)
-{
-#define N_WORDS 3
-	int n_words;
-	char *words[N_WORDS];
-	enum pipe pipe;
-	enum intel_pipe_crc_object object;
-	enum intel_pipe_crc_source source;
-
-	n_words = display_crc_ctl_tokenize(buf, words, N_WORDS);
-	if (n_words != N_WORDS) {
-		DRM_DEBUG_DRIVER("tokenize failed, a command is %d words\n",
-				 N_WORDS);
-		return -EINVAL;
-	}
-
-	if (display_crc_ctl_parse_object(words[0], &object) < 0) {
-		DRM_DEBUG_DRIVER("unknown object %s\n", words[0]);
-		return -EINVAL;
-	}
-
-	if (display_crc_ctl_parse_pipe(dev_priv, words[1], &pipe) < 0) {
-		DRM_DEBUG_DRIVER("unknown pipe %s\n", words[1]);
-		return -EINVAL;
-	}
-
-	if (display_crc_ctl_parse_source(words[2], &source) < 0) {
-		DRM_DEBUG_DRIVER("unknown source %s\n", words[2]);
-		return -EINVAL;
-	}
-
-	return pipe_crc_set_source(dev_priv, pipe, source);
-}
-
-static ssize_t display_crc_ctl_write(struct file *file, const char __user *ubuf,
-				     size_t len, loff_t *offp)
-{
-	struct seq_file *m = file->private_data;
-	struct drm_i915_private *dev_priv = m->private;
-	char *tmpbuf;
-	int ret;
-
-	if (len == 0)
-		return 0;
-
-	if (len > PAGE_SIZE - 1) {
-		DRM_DEBUG_DRIVER("expected <%lu bytes into pipe crc control\n",
-				 PAGE_SIZE);
-		return -E2BIG;
-	}
-
-	tmpbuf = memdup_user_nul(ubuf, len);
-	if (IS_ERR(tmpbuf))
-		return PTR_ERR(tmpbuf);
-
-	ret = display_crc_ctl_parse(dev_priv, tmpbuf, len);
-
-	kfree(tmpbuf);
-	if (ret < 0)
-		return ret;
-
-	*offp += len;
-	return len;
-}
-
-const struct file_operations i915_display_crc_ctl_fops = {
-	.owner = THIS_MODULE,
-	.open = display_crc_ctl_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-	.write = display_crc_ctl_write
-};
-
 void intel_display_crc_init(struct drm_i915_private *dev_priv)
 {
 	enum pipe pipe;
@@ -887,30 +464,8 @@ void intel_display_crc_init(struct drm_i915_private *dev_priv)
 	for_each_pipe(dev_priv, pipe) {
 		struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[pipe];
 
-		pipe_crc->opened = false;
 		spin_lock_init(&pipe_crc->lock);
-		init_waitqueue_head(&pipe_crc->wq);
-	}
-}
-
-int intel_pipe_crc_create(struct drm_minor *minor)
-{
-	struct drm_i915_private *dev_priv = to_i915(minor->dev);
-	struct dentry *ent;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(i915_pipe_crc_data); i++) {
-		struct pipe_crc_info *info = &i915_pipe_crc_data[i];
-
-		info->dev_priv = dev_priv;
-		ent = debugfs_create_file(info->name, S_IRUGO,
-					  minor->debugfs_root, info,
-					  &i915_pipe_crc_fops);
-		if (!ent)
-			return -ENOMEM;
 	}
-
-	return 0;
 }
 
 int intel_crtc_set_crc_source(struct drm_crtc *crtc, const char *source_name,
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 53aaaa3e6886..43ae9de12ba3 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -6264,42 +6264,15 @@ static u32 intel_rps_limits(struct drm_i915_private *dev_priv, u8 val)
 	return limits;
 }
 
-static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
+static void rps_set_power(struct drm_i915_private *dev_priv, int new_power)
 {
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	int new_power;
 	u32 threshold_up = 0, threshold_down = 0; /* in % */
 	u32 ei_up = 0, ei_down = 0;
 
-	new_power = rps->power;
-	switch (rps->power) {
-	case LOW_POWER:
-		if (val > rps->efficient_freq + 1 &&
-		    val > rps->cur_freq)
-			new_power = BETWEEN;
-		break;
-
-	case BETWEEN:
-		if (val <= rps->efficient_freq &&
-		    val < rps->cur_freq)
-			new_power = LOW_POWER;
-		else if (val >= rps->rp0_freq &&
-			 val > rps->cur_freq)
-			new_power = HIGH_POWER;
-		break;
+	lockdep_assert_held(&rps->power.mutex);
 
-	case HIGH_POWER:
-		if (val < (rps->rp1_freq + rps->rp0_freq) >> 1 &&
-		    val < rps->cur_freq)
-			new_power = BETWEEN;
-		break;
-	}
-	/* Max/min bins are special */
-	if (val <= rps->min_freq_softlimit)
-		new_power = LOW_POWER;
-	if (val >= rps->max_freq_softlimit)
-		new_power = HIGH_POWER;
-	if (new_power == rps->power)
+	if (new_power == rps->power.mode)
 		return;
 
 	/* Note the units here are not exactly 1us, but 1280ns. */
@@ -6362,12 +6335,71 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
 		   GEN6_RP_DOWN_IDLE_AVG);
 
 skip_hw_write:
-	rps->power = new_power;
-	rps->up_threshold = threshold_up;
-	rps->down_threshold = threshold_down;
+	rps->power.mode = new_power;
+	rps->power.up_threshold = threshold_up;
+	rps->power.down_threshold = threshold_down;
+}
+
+static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
+{
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+	int new_power;
+
+	new_power = rps->power.mode;
+	switch (rps->power.mode) {
+	case LOW_POWER:
+		if (val > rps->efficient_freq + 1 &&
+		    val > rps->cur_freq)
+			new_power = BETWEEN;
+		break;
+
+	case BETWEEN:
+		if (val <= rps->efficient_freq &&
+		    val < rps->cur_freq)
+			new_power = LOW_POWER;
+		else if (val >= rps->rp0_freq &&
+			 val > rps->cur_freq)
+			new_power = HIGH_POWER;
+		break;
+
+	case HIGH_POWER:
+		if (val < (rps->rp1_freq + rps->rp0_freq) >> 1 &&
+		    val < rps->cur_freq)
+			new_power = BETWEEN;
+		break;
+	}
+	/* Max/min bins are special */
+	if (val <= rps->min_freq_softlimit)
+		new_power = LOW_POWER;
+	if (val >= rps->max_freq_softlimit)
+		new_power = HIGH_POWER;
+
+	mutex_lock(&rps->power.mutex);
+	if (rps->power.interactive)
+		new_power = HIGH_POWER;
+	rps_set_power(dev_priv, new_power);
+	mutex_unlock(&rps->power.mutex);
 	rps->last_adj = 0;
 }
 
+void intel_rps_mark_interactive(struct drm_i915_private *i915, bool interactive)
+{
+	struct intel_rps *rps = &i915->gt_pm.rps;
+
+	if (INTEL_GEN(i915) < 6)
+		return;
+
+	mutex_lock(&rps->power.mutex);
+	if (interactive) {
+		if (!rps->power.interactive++ && READ_ONCE(i915->gt.awake))
+			rps_set_power(i915, HIGH_POWER);
+	} else {
+		GEM_BUG_ON(!rps->power.interactive);
+		rps->power.interactive--;
+	}
+	mutex_unlock(&rps->power.mutex);
+}
+
 static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val)
 {
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
@@ -6780,7 +6812,7 @@ static void reset_rps(struct drm_i915_private *dev_priv,
 	u8 freq = rps->cur_freq;
 
 	/* force a reset */
-	rps->power = -1;
+	rps->power.mode = -1;
 	rps->cur_freq = -1;
 
 	if (set(dev_priv, freq))
@@ -7347,11 +7379,11 @@ out:
 
 static void valleyview_cleanup_pctx(struct drm_i915_private *dev_priv)
 {
-	if (WARN_ON(!dev_priv->vlv_pctx))
-		return;
+	struct drm_i915_gem_object *pctx;
 
-	i915_gem_object_put(dev_priv->vlv_pctx);
-	dev_priv->vlv_pctx = NULL;
+	pctx = fetch_and_zero(&dev_priv->vlv_pctx);
+	if (pctx)
+		i915_gem_object_put(pctx);
 }
 
 static void vlv_init_gpll_ref_freq(struct drm_i915_private *dev_priv)
@@ -9604,6 +9636,7 @@ int intel_freq_opcode(struct drm_i915_private *dev_priv, int val)
 void intel_pm_setup(struct drm_i915_private *dev_priv)
 {
 	mutex_init(&dev_priv->pcu_lock);
+	mutex_init(&dev_priv->gt_pm.rps.power.mutex);
 
 	atomic_set(&dev_priv->gt_pm.rps.num_waiters, 0);
 
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index db27f2faa1de..4bd5768731ee 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -56,51 +56,10 @@
 #include "intel_drv.h"
 #include "i915_drv.h"
 
-static inline enum intel_display_power_domain
-psr_aux_domain(struct intel_dp *intel_dp)
-{
-	/* CNL HW requires corresponding AUX IOs to be powered up for PSR.
-	 * However, for non-A AUX ports the corresponding non-EDP transcoders
-	 * would have already enabled power well 2 and DC_OFF. This means we can
-	 * acquire a wider POWER_DOMAIN_AUX_{B,C,D,F} reference instead of a
-	 * specific AUX_IO reference without powering up any extra wells.
-	 * Note that PSR is enabled only on Port A even though this function
-	 * returns the correct domain for other ports too.
-	 */
-	return intel_dp->aux_ch == AUX_CH_A ? POWER_DOMAIN_AUX_IO_A :
-					      intel_dp->aux_power_domain;
-}
-
-static void psr_aux_io_power_get(struct intel_dp *intel_dp)
-{
-	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv = to_i915(intel_dig_port->base.base.dev);
-
-	if (INTEL_GEN(dev_priv) < 10)
-		return;
-
-	intel_display_power_get(dev_priv, psr_aux_domain(intel_dp));
-}
-
-static void psr_aux_io_power_put(struct intel_dp *intel_dp)
-{
-	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv = to_i915(intel_dig_port->base.base.dev);
-
-	if (INTEL_GEN(dev_priv) < 10)
-		return;
-
-	intel_display_power_put(dev_priv, psr_aux_domain(intel_dp));
-}
-
 void intel_psr_irq_control(struct drm_i915_private *dev_priv, bool debug)
 {
 	u32 debug_mask, mask;
 
-	/* No PSR interrupts on VLV/CHV */
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		return;
-
 	mask = EDP_PSR_ERROR(TRANSCODER_EDP);
 	debug_mask = EDP_PSR_POST_EXIT(TRANSCODER_EDP) |
 		     EDP_PSR_PRE_ENTRY(TRANSCODER_EDP);
@@ -201,15 +160,6 @@ void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir)
 	}
 }
 
-static bool intel_dp_get_y_coord_required(struct intel_dp *intel_dp)
-{
-	uint8_t psr_caps = 0;
-
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_CAPS, &psr_caps) != 1)
-		return false;
-	return psr_caps & DP_PSR2_SU_Y_COORDINATE_REQUIRED;
-}
-
 static bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp)
 {
 	uint8_t dprx = 0;
@@ -232,13 +182,13 @@ static bool intel_dp_get_alpm_status(struct intel_dp *intel_dp)
 
 static u8 intel_dp_get_sink_sync_latency(struct intel_dp *intel_dp)
 {
-	u8 val = 0;
+	u8 val = 8; /* assume the worst if we can't read the value */
 
 	if (drm_dp_dpcd_readb(&intel_dp->aux,
 			      DP_SYNCHRONIZATION_LATENCY_IN_SINK, &val) == 1)
 		val &= DP_MAX_RESYNC_FRAME_COUNT_MASK;
 	else
-		DRM_ERROR("Unable to get sink synchronization latency\n");
+		DRM_DEBUG_KMS("Unable to get sink synchronization latency, assuming 8 frames\n");
 	return val;
 }
 
@@ -250,13 +200,25 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 	drm_dp_dpcd_read(&intel_dp->aux, DP_PSR_SUPPORT, intel_dp->psr_dpcd,
 			 sizeof(intel_dp->psr_dpcd));
 
-	if (intel_dp->psr_dpcd[0]) {
-		dev_priv->psr.sink_support = true;
-		DRM_DEBUG_KMS("Detected EDP PSR Panel.\n");
+	if (!intel_dp->psr_dpcd[0])
+		return;
+	DRM_DEBUG_KMS("eDP panel supports PSR version %x\n",
+		      intel_dp->psr_dpcd[0]);
+
+	if (!(intel_dp->edp_dpcd[1] & DP_EDP_SET_POWER_CAP)) {
+		DRM_DEBUG_KMS("Panel lacks power state control, PSR cannot be enabled\n");
+		return;
 	}
+	dev_priv->psr.sink_support = true;
+	dev_priv->psr.sink_sync_latency =
+		intel_dp_get_sink_sync_latency(intel_dp);
 
 	if (INTEL_GEN(dev_priv) >= 9 &&
 	    (intel_dp->psr_dpcd[0] == DP_PSR2_WITH_Y_COORD_IS_SUPPORTED)) {
+		bool y_req = intel_dp->psr_dpcd[1] &
+			     DP_PSR2_SU_Y_COORDINATE_REQUIRED;
+		bool alpm = intel_dp_get_alpm_status(intel_dp);
+
 		/*
 		 * All panels that supports PSR version 03h (PSR2 +
 		 * Y-coordinate) can handle Y-coordinates in VSC but we are
@@ -268,49 +230,19 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 		 * Y-coordinate requirement panels we would need to enable
 		 * GTC first.
 		 */
-		dev_priv->psr.sink_psr2_support =
-				intel_dp_get_y_coord_required(intel_dp);
-		DRM_DEBUG_KMS("PSR2 %s on sink", dev_priv->psr.sink_psr2_support
-			      ? "supported" : "not supported");
+		dev_priv->psr.sink_psr2_support = y_req && alpm;
+		DRM_DEBUG_KMS("PSR2 %ssupported\n",
+			      dev_priv->psr.sink_psr2_support ? "" : "not ");
 
 		if (dev_priv->psr.sink_psr2_support) {
 			dev_priv->psr.colorimetry_support =
 				intel_dp_get_colorimetry_status(intel_dp);
-			dev_priv->psr.alpm =
-				intel_dp_get_alpm_status(intel_dp);
-			dev_priv->psr.sink_sync_latency =
-				intel_dp_get_sink_sync_latency(intel_dp);
 		}
 	}
 }
 
-static bool vlv_is_psr_active_on_pipe(struct drm_device *dev, int pipe)
-{
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	uint32_t val;
-
-	val = I915_READ(VLV_PSRSTAT(pipe)) &
-	      VLV_EDP_PSR_CURR_STATE_MASK;
-	return (val == VLV_EDP_PSR_ACTIVE_NORFB_UP) ||
-	       (val == VLV_EDP_PSR_ACTIVE_SF_UPDATE);
-}
-
-static void vlv_psr_setup_vsc(struct intel_dp *intel_dp,
-			      const struct intel_crtc_state *crtc_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	uint32_t val;
-
-	/* VLV auto-generate VSC package as per EDP 1.3 spec, Table 3.10 */
-	val  = I915_READ(VLV_VSCSDP(crtc->pipe));
-	val &= ~VLV_EDP_PSR_SDP_FREQ_MASK;
-	val |= VLV_EDP_PSR_SDP_FREQ_EVFRAME;
-	I915_WRITE(VLV_VSCSDP(crtc->pipe), val);
-}
-
-static void hsw_psr_setup_vsc(struct intel_dp *intel_dp,
-			      const struct intel_crtc_state *crtc_state)
+static void intel_psr_setup_vsc(struct intel_dp *intel_dp,
+				const struct intel_crtc_state *crtc_state)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_i915_private *dev_priv = to_i915(intel_dig_port->base.base.dev);
@@ -341,12 +273,6 @@ static void hsw_psr_setup_vsc(struct intel_dp *intel_dp,
 					DP_SDP_VSC, &psr_vsc, sizeof(psr_vsc));
 }
 
-static void vlv_psr_enable_sink(struct intel_dp *intel_dp)
-{
-	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG,
-			   DP_PSR_ENABLE | DP_PSR_MAIN_LINK_ACTIVE);
-}
-
 static void hsw_psr_setup_aux(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
@@ -373,7 +299,7 @@ static void hsw_psr_setup_aux(struct intel_dp *intel_dp)
 	aux_clock_divider = intel_dp->get_aux_clock_divider(intel_dp, 0);
 
 	/* Start with bits set for DDI_AUX_CTL register */
-	aux_ctl = intel_dp->get_aux_send_ctl(intel_dp, 0, sizeof(aux_msg),
+	aux_ctl = intel_dp->get_aux_send_ctl(intel_dp, sizeof(aux_msg),
 					     aux_clock_divider);
 
 	/* Select only valid bits for SRD_AUX_CTL */
@@ -381,7 +307,7 @@ static void hsw_psr_setup_aux(struct intel_dp *intel_dp)
 	I915_WRITE(EDP_PSR_AUX_CTL, aux_ctl);
 }
 
-static void hsw_psr_enable_sink(struct intel_dp *intel_dp)
+static void intel_psr_enable_sink(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = dig_port->base.base.dev;
@@ -389,95 +315,64 @@ static void hsw_psr_enable_sink(struct intel_dp *intel_dp)
 	u8 dpcd_val = DP_PSR_ENABLE;
 
 	/* Enable ALPM at sink for psr2 */
-	if (dev_priv->psr.psr2_enabled && dev_priv->psr.alpm)
-		drm_dp_dpcd_writeb(&intel_dp->aux,
-				DP_RECEIVER_ALPM_CONFIG,
-				DP_ALPM_ENABLE);
-
-	if (dev_priv->psr.psr2_enabled)
+	if (dev_priv->psr.psr2_enabled) {
+		drm_dp_dpcd_writeb(&intel_dp->aux, DP_RECEIVER_ALPM_CONFIG,
+				   DP_ALPM_ENABLE);
 		dpcd_val |= DP_PSR_ENABLE_PSR2;
+	}
+
 	if (dev_priv->psr.link_standby)
 		dpcd_val |= DP_PSR_MAIN_LINK_ACTIVE;
+	if (!dev_priv->psr.psr2_enabled && INTEL_GEN(dev_priv) >= 8)
+		dpcd_val |= DP_PSR_CRC_VERIFICATION;
 	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, dpcd_val);
 
 	drm_dp_dpcd_writeb(&intel_dp->aux, DP_SET_POWER, DP_SET_POWER_D0);
 }
 
-static void vlv_psr_enable_source(struct intel_dp *intel_dp,
-				  const struct intel_crtc_state *crtc_state)
-{
-	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-
-	/* Transition from PSR_state 0 (disabled) to PSR_state 1 (inactive) */
-	I915_WRITE(VLV_PSRCTL(crtc->pipe),
-		   VLV_EDP_PSR_MODE_SW_TIMER |
-		   VLV_EDP_PSR_SRC_TRANSMITTER_STATE |
-		   VLV_EDP_PSR_ENABLE);
-}
-
-static void vlv_psr_activate(struct intel_dp *intel_dp)
-{
-	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
-	struct drm_device *dev = dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct drm_crtc *crtc = dig_port->base.base.crtc;
-	enum pipe pipe = to_intel_crtc(crtc)->pipe;
-
-	/*
-	 * Let's do the transition from PSR_state 1 (inactive) to
-	 * PSR_state 2 (transition to active - static frame transmission).
-	 * Then Hardware is responsible for the transition to
-	 * PSR_state 3 (active - no Remote Frame Buffer (RFB) update).
-	 */
-	I915_WRITE(VLV_PSRCTL(pipe), I915_READ(VLV_PSRCTL(pipe)) |
-		   VLV_EDP_PSR_ACTIVE_ENTRY);
-}
-
 static void hsw_activate_psr1(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
+	u32 max_sleep_time = 0x1f;
+	u32 val = EDP_PSR_ENABLE;
 
-	uint32_t max_sleep_time = 0x1f;
-	/*
-	 * Let's respect VBT in case VBT asks a higher idle_frame value.
-	 * Let's use 6 as the minimum to cover all known cases including
-	 * the off-by-one issue that HW has in some cases. Also there are
-	 * cases where sink should be able to train
-	 * with the 5 or 6 idle patterns.
+	/* Let's use 6 as the minimum to cover all known cases including the
+	 * off-by-one issue that HW has in some cases.
 	 */
-	uint32_t idle_frames = max(6, dev_priv->vbt.psr.idle_frames);
-	uint32_t val = EDP_PSR_ENABLE;
+	int idle_frames = max(6, dev_priv->vbt.psr.idle_frames);
 
-	val |= max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT;
+	/* sink_sync_latency of 8 means source has to wait for more than 8
+	 * frames, we'll go with 9 frames for now
+	 */
+	idle_frames = max(idle_frames, dev_priv->psr.sink_sync_latency + 1);
 	val |= idle_frames << EDP_PSR_IDLE_FRAME_SHIFT;
 
+	val |= max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT;
 	if (IS_HASWELL(dev_priv))
 		val |= EDP_PSR_MIN_LINK_ENTRY_TIME_8_LINES;
 
 	if (dev_priv->psr.link_standby)
 		val |= EDP_PSR_LINK_STANDBY;
 
-	if (dev_priv->vbt.psr.tp1_wakeup_time > 5)
-		val |= EDP_PSR_TP1_TIME_2500us;
-	else if (dev_priv->vbt.psr.tp1_wakeup_time > 1)
-		val |= EDP_PSR_TP1_TIME_500us;
-	else if (dev_priv->vbt.psr.tp1_wakeup_time > 0)
+	if (dev_priv->vbt.psr.tp1_wakeup_time_us == 0)
+		val |=  EDP_PSR_TP1_TIME_0us;
+	else if (dev_priv->vbt.psr.tp1_wakeup_time_us <= 100)
 		val |= EDP_PSR_TP1_TIME_100us;
+	else if (dev_priv->vbt.psr.tp1_wakeup_time_us <= 500)
+		val |= EDP_PSR_TP1_TIME_500us;
 	else
-		val |= EDP_PSR_TP1_TIME_0us;
+		val |= EDP_PSR_TP1_TIME_2500us;
 
-	if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 5)
-		val |= EDP_PSR_TP2_TP3_TIME_2500us;
-	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 1)
-		val |= EDP_PSR_TP2_TP3_TIME_500us;
-	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 0)
+	if (dev_priv->vbt.psr.tp2_tp3_wakeup_time_us == 0)
+		val |=  EDP_PSR_TP2_TP3_TIME_0us;
+	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time_us <= 100)
 		val |= EDP_PSR_TP2_TP3_TIME_100us;
+	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time_us <= 500)
+		val |= EDP_PSR_TP2_TP3_TIME_500us;
 	else
-		val |= EDP_PSR_TP2_TP3_TIME_0us;
+		val |= EDP_PSR_TP2_TP3_TIME_2500us;
 
 	if (intel_dp_source_supports_hbr2(intel_dp) &&
 	    drm_dp_tps3_supported(intel_dp->dpcd))
@@ -485,6 +380,9 @@ static void hsw_activate_psr1(struct intel_dp *intel_dp)
 	else
 		val |= EDP_PSR_TP1_TP2_SEL;
 
+	if (INTEL_GEN(dev_priv) >= 8)
+		val |= EDP_PSR_CRC_ENABLE;
+
 	val |= I915_READ(EDP_PSR_CTL) & EDP_PSR_RESTORE_PSR_ACTIVE_CTX_MASK;
 	I915_WRITE(EDP_PSR_CTL, val);
 }
@@ -494,15 +392,15 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp)
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	/*
-	 * Let's respect VBT in case VBT asks a higher idle_frame value.
-	 * Let's use 6 as the minimum to cover all known cases including
-	 * the off-by-one issue that HW has in some cases. Also there are
-	 * cases where sink should be able to train
-	 * with the 5 or 6 idle patterns.
+	u32 val;
+
+	/* Let's use 6 as the minimum to cover all known cases including the
+	 * off-by-one issue that HW has in some cases.
 	 */
-	uint32_t idle_frames = max(6, dev_priv->vbt.psr.idle_frames);
-	u32 val = idle_frames << EDP_PSR2_IDLE_FRAME_SHIFT;
+	int idle_frames = max(6, dev_priv->vbt.psr.idle_frames);
+
+	idle_frames = max(idle_frames, dev_priv->psr.sink_sync_latency + 1);
+	val = idle_frames << EDP_PSR2_IDLE_FRAME_SHIFT;
 
 	/* FIXME: selective update is probably totally broken because it doesn't
 	 * mesh at all with our frontbuffer tracking. And the hw alone isn't
@@ -513,36 +411,19 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp)
 
 	val |= EDP_PSR2_FRAME_BEFORE_SU(dev_priv->psr.sink_sync_latency + 1);
 
-	if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 5)
-		val |= EDP_PSR2_TP2_TIME_2500;
-	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 1)
-		val |= EDP_PSR2_TP2_TIME_500;
-	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 0)
-		val |= EDP_PSR2_TP2_TIME_100;
+	if (dev_priv->vbt.psr.tp2_tp3_wakeup_time_us >= 0 &&
+	    dev_priv->vbt.psr.tp2_tp3_wakeup_time_us <= 50)
+		val |= EDP_PSR2_TP2_TIME_50us;
+	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time_us <= 100)
+		val |= EDP_PSR2_TP2_TIME_100us;
+	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time_us <= 500)
+		val |= EDP_PSR2_TP2_TIME_500us;
 	else
-		val |= EDP_PSR2_TP2_TIME_50;
+		val |= EDP_PSR2_TP2_TIME_2500us;
 
 	I915_WRITE(EDP_PSR2_CTL, val);
 }
 
-static void hsw_psr_activate(struct intel_dp *intel_dp)
-{
-	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
-	struct drm_device *dev = dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-
-	/* On HSW+ after we enable PSR on source it will activate it
-	 * as soon as it match configure idle_frame count. So
-	 * we just actually enable it here on activation time.
-	 */
-
-	/* psr1 and psr2 are mutually exclusive.*/
-	if (dev_priv->psr.psr2_enabled)
-		hsw_activate_psr2(intel_dp);
-	else
-		hsw_activate_psr1(intel_dp);
-}
-
 static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 				    struct intel_crtc_state *crtc_state)
 {
@@ -602,17 +483,11 @@ void intel_psr_compute_config(struct intel_dp *intel_dp,
 	 * ones. Since by Display design transcoder EDP is tied to port A
 	 * we can safely escape based on the port A.
 	 */
-	if (HAS_DDI(dev_priv) && dig_port->base.port != PORT_A) {
+	if (dig_port->base.port != PORT_A) {
 		DRM_DEBUG_KMS("PSR condition failed: Port not supported\n");
 		return;
 	}
 
-	if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
-	    !dev_priv->psr.link_standby) {
-		DRM_ERROR("PSR condition failed: Link off requested but not supported on this platform\n");
-		return;
-	}
-
 	if (IS_HASWELL(dev_priv) &&
 	    I915_READ(HSW_STEREO_3D_CTL(crtc_state->cpu_transcoder)) &
 		      S3D_ENABLE) {
@@ -640,11 +515,6 @@ void intel_psr_compute_config(struct intel_dp *intel_dp,
 		return;
 	}
 
-	if (!(intel_dp->edp_dpcd[1] & DP_EDP_SET_POWER_CAP)) {
-		DRM_DEBUG_KMS("PSR condition failed: panel lacks power state control\n");
-		return;
-	}
-
 	crtc_state->has_psr = true;
 	crtc_state->has_psr2 = intel_psr2_config_valid(intel_dp, crtc_state);
 	DRM_DEBUG_KMS("Enabling PSR%s\n", crtc_state->has_psr2 ? "2" : "");
@@ -656,27 +526,29 @@ static void intel_psr_activate(struct intel_dp *intel_dp)
 	struct drm_device *dev = intel_dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
-	if (dev_priv->psr.psr2_enabled)
+	if (INTEL_GEN(dev_priv) >= 9)
 		WARN_ON(I915_READ(EDP_PSR2_CTL) & EDP_PSR2_ENABLE);
-	else
-		WARN_ON(I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE);
+	WARN_ON(I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE);
 	WARN_ON(dev_priv->psr.active);
 	lockdep_assert_held(&dev_priv->psr.lock);
 
-	dev_priv->psr.activate(intel_dp);
+	/* psr1 and psr2 are mutually exclusive.*/
+	if (dev_priv->psr.psr2_enabled)
+		hsw_activate_psr2(intel_dp);
+	else
+		hsw_activate_psr1(intel_dp);
+
 	dev_priv->psr.active = true;
 }
 
-static void hsw_psr_enable_source(struct intel_dp *intel_dp,
-				  const struct intel_crtc_state *crtc_state)
+static void intel_psr_enable_source(struct intel_dp *intel_dp,
+				    const struct intel_crtc_state *crtc_state)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 
-	psr_aux_io_power_get(intel_dp);
-
 	/* Only HSW and BDW have PSR AUX registers that need to be setup. SKL+
 	 * use hardcoded values PSR AUX transactions
 	 */
@@ -712,7 +584,8 @@ static void hsw_psr_enable_source(struct intel_dp *intel_dp,
 			   EDP_PSR_DEBUG_MASK_MEMUP |
 			   EDP_PSR_DEBUG_MASK_HPD |
 			   EDP_PSR_DEBUG_MASK_LPSP |
-			   EDP_PSR_DEBUG_MASK_DISP_REG_WRITE);
+			   EDP_PSR_DEBUG_MASK_DISP_REG_WRITE |
+			   EDP_PSR_DEBUG_MASK_MAX_SLEEP);
 	}
 }
 
@@ -746,64 +619,19 @@ void intel_psr_enable(struct intel_dp *intel_dp,
 	dev_priv->psr.psr2_enabled = crtc_state->has_psr2;
 	dev_priv->psr.busy_frontbuffer_bits = 0;
 
-	dev_priv->psr.setup_vsc(intel_dp, crtc_state);
-	dev_priv->psr.enable_sink(intel_dp);
-	dev_priv->psr.enable_source(intel_dp, crtc_state);
+	intel_psr_setup_vsc(intel_dp, crtc_state);
+	intel_psr_enable_sink(intel_dp);
+	intel_psr_enable_source(intel_dp, crtc_state);
 	dev_priv->psr.enabled = intel_dp;
 
-	if (INTEL_GEN(dev_priv) >= 9) {
-		intel_psr_activate(intel_dp);
-	} else {
-		/*
-		 * FIXME: Activation should happen immediately since this
-		 * function is just called after pipe is fully trained and
-		 * enabled.
-		 * However on some platforms we face issues when first
-		 * activation follows a modeset so quickly.
-		 *     - On VLV/CHV we get bank screen on first activation
-		 *     - On HSW/BDW we get a recoverable frozen screen until
-		 *       next exit-activate sequence.
-		 */
-		schedule_delayed_work(&dev_priv->psr.work,
-				      msecs_to_jiffies(intel_dp->panel_power_cycle_delay * 5));
-	}
+	intel_psr_activate(intel_dp);
 
 unlock:
 	mutex_unlock(&dev_priv->psr.lock);
 }
 
-static void vlv_psr_disable(struct intel_dp *intel_dp,
-			    const struct intel_crtc_state *old_crtc_state)
-{
-	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
-	uint32_t val;
-
-	if (dev_priv->psr.active) {
-		/* Put VLV PSR back to PSR_state 0 (disabled). */
-		if (intel_wait_for_register(dev_priv,
-					    VLV_PSRSTAT(crtc->pipe),
-					    VLV_EDP_PSR_IN_TRANS,
-					    0,
-					    1))
-			WARN(1, "PSR transition took longer than expected\n");
-
-		val = I915_READ(VLV_PSRCTL(crtc->pipe));
-		val &= ~VLV_EDP_PSR_ACTIVE_ENTRY;
-		val &= ~VLV_EDP_PSR_ENABLE;
-		val &= ~VLV_EDP_PSR_MODE_MASK;
-		I915_WRITE(VLV_PSRCTL(crtc->pipe), val);
-
-		dev_priv->psr.active = false;
-	} else {
-		WARN_ON(vlv_is_psr_active_on_pipe(dev, crtc->pipe));
-	}
-}
-
-static void hsw_psr_disable(struct intel_dp *intel_dp,
-			    const struct intel_crtc_state *old_crtc_state)
+static void
+intel_psr_disable_source(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
@@ -842,8 +670,25 @@ static void hsw_psr_disable(struct intel_dp *intel_dp,
 		else
 			WARN_ON(I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE);
 	}
+}
+
+static void intel_psr_disable_locked(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = intel_dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+
+	lockdep_assert_held(&dev_priv->psr.lock);
+
+	if (!dev_priv->psr.enabled)
+		return;
+
+	intel_psr_disable_source(intel_dp);
 
-	psr_aux_io_power_put(intel_dp);
+	/* Disable PSR on Sink */
+	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, 0);
+
+	dev_priv->psr.enabled = NULL;
 }
 
 /**
@@ -867,23 +712,49 @@ void intel_psr_disable(struct intel_dp *intel_dp,
 		return;
 
 	mutex_lock(&dev_priv->psr.lock);
-	if (!dev_priv->psr.enabled) {
-		mutex_unlock(&dev_priv->psr.lock);
-		return;
-	}
+	intel_psr_disable_locked(intel_dp);
+	mutex_unlock(&dev_priv->psr.lock);
+	cancel_work_sync(&dev_priv->psr.work);
+}
 
-	dev_priv->psr.disable_source(intel_dp, old_crtc_state);
+int intel_psr_wait_for_idle(const struct intel_crtc_state *new_crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	i915_reg_t reg;
+	u32 mask;
 
-	/* Disable PSR on Sink */
-	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, 0);
+	if (!new_crtc_state->has_psr)
+		return 0;
 
-	dev_priv->psr.enabled = NULL;
-	mutex_unlock(&dev_priv->psr.lock);
+	/*
+	 * The sole user right now is intel_pipe_update_start(),
+	 * which won't race with psr_enable/disable, which is
+	 * where psr2_enabled is written to. So, we don't need
+	 * to acquire the psr.lock. More importantly, we want the
+	 * latency inside intel_pipe_update_start() to be as low
+	 * as possible, so no need to acquire psr.lock when it is
+	 * not needed and will induce latencies in the atomic
+	 * update path.
+	 */
+	if (dev_priv->psr.psr2_enabled) {
+		reg = EDP_PSR2_STATUS;
+		mask = EDP_PSR2_STATUS_STATE_MASK;
+	} else {
+		reg = EDP_PSR_STATUS;
+		mask = EDP_PSR_STATUS_STATE_MASK;
+	}
 
-	cancel_delayed_work_sync(&dev_priv->psr.work);
+	/*
+	 * Max time for PSR to idle = Inverse of the refresh rate +
+	 * 6 ms of exit training time + 1.5 ms of aux channel
+	 * handshake. 50 msec is defesive enough to cover everything.
+	 */
+	return intel_wait_for_register(dev_priv, reg, mask,
+				       EDP_PSR_STATUS_STATE_IDLE, 50);
 }
 
-static bool psr_wait_for_idle(struct drm_i915_private *dev_priv)
+static bool __psr_wait_for_idle_locked(struct drm_i915_private *dev_priv)
 {
 	struct intel_dp *intel_dp;
 	i915_reg_t reg;
@@ -894,21 +765,12 @@ static bool psr_wait_for_idle(struct drm_i915_private *dev_priv)
 	if (!intel_dp)
 		return false;
 
-	if (HAS_DDI(dev_priv)) {
-		if (dev_priv->psr.psr2_enabled) {
-			reg = EDP_PSR2_STATUS;
-			mask = EDP_PSR2_STATUS_STATE_MASK;
-		} else {
-			reg = EDP_PSR_STATUS;
-			mask = EDP_PSR_STATUS_STATE_MASK;
-		}
+	if (dev_priv->psr.psr2_enabled) {
+		reg = EDP_PSR2_STATUS;
+		mask = EDP_PSR2_STATUS_STATE_MASK;
 	} else {
-		struct drm_crtc *crtc =
-			dp_to_dig_port(intel_dp)->base.base.crtc;
-		enum pipe pipe = to_intel_crtc(crtc)->pipe;
-
-		reg = VLV_PSRSTAT(pipe);
-		mask = VLV_EDP_PSR_IN_TRANS;
+		reg = EDP_PSR_STATUS;
+		mask = EDP_PSR_STATUS_STATE_MASK;
 	}
 
 	mutex_unlock(&dev_priv->psr.lock);
@@ -925,17 +787,20 @@ static bool psr_wait_for_idle(struct drm_i915_private *dev_priv)
 static void intel_psr_work(struct work_struct *work)
 {
 	struct drm_i915_private *dev_priv =
-		container_of(work, typeof(*dev_priv), psr.work.work);
+		container_of(work, typeof(*dev_priv), psr.work);
 
 	mutex_lock(&dev_priv->psr.lock);
 
+	if (!dev_priv->psr.enabled)
+		goto unlock;
+
 	/*
 	 * We have to make sure PSR is ready for re-enable
 	 * otherwise it keeps disabled until next full enable/disable cycle.
 	 * PSR might take some time to get fully disabled
 	 * and be ready for re-enable.
 	 */
-	if (!psr_wait_for_idle(dev_priv))
+	if (!__psr_wait_for_idle_locked(dev_priv))
 		goto unlock;
 
 	/*
@@ -943,7 +808,7 @@ static void intel_psr_work(struct work_struct *work)
 	 * recheck. Since psr_flush first clears this and then reschedules we
 	 * won't ever miss a flush when bailing out here.
 	 */
-	if (dev_priv->psr.busy_frontbuffer_bits)
+	if (dev_priv->psr.busy_frontbuffer_bits || dev_priv->psr.active)
 		goto unlock;
 
 	intel_psr_activate(dev_priv->psr.enabled);
@@ -953,103 +818,24 @@ unlock:
 
 static void intel_psr_exit(struct drm_i915_private *dev_priv)
 {
-	struct intel_dp *intel_dp = dev_priv->psr.enabled;
-	struct drm_crtc *crtc = dp_to_dig_port(intel_dp)->base.base.crtc;
-	enum pipe pipe = to_intel_crtc(crtc)->pipe;
 	u32 val;
 
 	if (!dev_priv->psr.active)
 		return;
 
-	if (HAS_DDI(dev_priv)) {
-		if (dev_priv->psr.psr2_enabled) {
-			val = I915_READ(EDP_PSR2_CTL);
-			WARN_ON(!(val & EDP_PSR2_ENABLE));
-			I915_WRITE(EDP_PSR2_CTL, val & ~EDP_PSR2_ENABLE);
-		} else {
-			val = I915_READ(EDP_PSR_CTL);
-			WARN_ON(!(val & EDP_PSR_ENABLE));
-			I915_WRITE(EDP_PSR_CTL, val & ~EDP_PSR_ENABLE);
-		}
+	if (dev_priv->psr.psr2_enabled) {
+		val = I915_READ(EDP_PSR2_CTL);
+		WARN_ON(!(val & EDP_PSR2_ENABLE));
+		I915_WRITE(EDP_PSR2_CTL, val & ~EDP_PSR2_ENABLE);
 	} else {
-		val = I915_READ(VLV_PSRCTL(pipe));
-
-		/*
-		 * Here we do the transition drirectly from
-		 * PSR_state 3 (active - no Remote Frame Buffer (RFB) update) to
-		 * PSR_state 5 (exit).
-		 * PSR State 4 (active with single frame update) can be skipped.
-		 * On PSR_state 5 (exit) Hardware is responsible to transition
-		 * back to PSR_state 1 (inactive).
-		 * Now we are at Same state after vlv_psr_enable_source.
-		 */
-		val &= ~VLV_EDP_PSR_ACTIVE_ENTRY;
-		I915_WRITE(VLV_PSRCTL(pipe), val);
-
-		/*
-		 * Send AUX wake up - Spec says after transitioning to PSR
-		 * active we have to send AUX wake up by writing 01h in DPCD
-		 * 600h of sink device.
-		 * XXX: This might slow down the transition, but without this
-		 * HW doesn't complete the transition to PSR_state 1 and we
-		 * never get the screen updated.
-		 */
-		drm_dp_dpcd_writeb(&intel_dp->aux, DP_SET_POWER,
-				   DP_SET_POWER_D0);
+		val = I915_READ(EDP_PSR_CTL);
+		WARN_ON(!(val & EDP_PSR_ENABLE));
+		I915_WRITE(EDP_PSR_CTL, val & ~EDP_PSR_ENABLE);
 	}
-
 	dev_priv->psr.active = false;
 }
 
 /**
- * intel_psr_single_frame_update - Single Frame Update
- * @dev_priv: i915 device
- * @frontbuffer_bits: frontbuffer plane tracking bits
- *
- * Some platforms support a single frame update feature that is used to
- * send and update only one frame on Remote Frame Buffer.
- * So far it is only implemented for Valleyview and Cherryview because
- * hardware requires this to be done before a page flip.
- */
-void intel_psr_single_frame_update(struct drm_i915_private *dev_priv,
-				   unsigned frontbuffer_bits)
-{
-	struct drm_crtc *crtc;
-	enum pipe pipe;
-	u32 val;
-
-	if (!CAN_PSR(dev_priv))
-		return;
-
-	/*
-	 * Single frame update is already supported on BDW+ but it requires
-	 * many W/A and it isn't really needed.
-	 */
-	if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv))
-		return;
-
-	mutex_lock(&dev_priv->psr.lock);
-	if (!dev_priv->psr.enabled) {
-		mutex_unlock(&dev_priv->psr.lock);
-		return;
-	}
-
-	crtc = dp_to_dig_port(dev_priv->psr.enabled)->base.base.crtc;
-	pipe = to_intel_crtc(crtc)->pipe;
-
-	if (frontbuffer_bits & INTEL_FRONTBUFFER_ALL_MASK(pipe)) {
-		val = I915_READ(VLV_PSRCTL(pipe));
-
-		/*
-		 * We need to set this bit before writing registers for a flip.
-		 * This bit will be self-clear when it gets to the PSR active state.
-		 */
-		I915_WRITE(VLV_PSRCTL(pipe), val | VLV_EDP_PSR_SINGLE_FRAME_UPDATE);
-	}
-	mutex_unlock(&dev_priv->psr.lock);
-}
-
-/**
  * intel_psr_invalidate - Invalidade PSR
  * @dev_priv: i915 device
  * @frontbuffer_bits: frontbuffer plane tracking bits
@@ -1071,7 +857,7 @@ void intel_psr_invalidate(struct drm_i915_private *dev_priv,
 	if (!CAN_PSR(dev_priv))
 		return;
 
-	if (dev_priv->psr.has_hw_tracking && origin == ORIGIN_FLIP)
+	if (origin == ORIGIN_FLIP)
 		return;
 
 	mutex_lock(&dev_priv->psr.lock);
@@ -1114,7 +900,7 @@ void intel_psr_flush(struct drm_i915_private *dev_priv,
 	if (!CAN_PSR(dev_priv))
 		return;
 
-	if (dev_priv->psr.has_hw_tracking && origin == ORIGIN_FLIP)
+	if (origin == ORIGIN_FLIP)
 		return;
 
 	mutex_lock(&dev_priv->psr.lock);
@@ -1131,8 +917,7 @@ void intel_psr_flush(struct drm_i915_private *dev_priv,
 
 	/* By definition flush = invalidate + flush */
 	if (frontbuffer_bits) {
-		if (dev_priv->psr.psr2_enabled ||
-		    IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
+		if (dev_priv->psr.psr2_enabled) {
 			intel_psr_exit(dev_priv);
 		} else {
 			/*
@@ -1149,9 +934,7 @@ void intel_psr_flush(struct drm_i915_private *dev_priv,
 	}
 
 	if (!dev_priv->psr.active && !dev_priv->psr.busy_frontbuffer_bits)
-		if (!work_busy(&dev_priv->psr.work.work))
-			schedule_delayed_work(&dev_priv->psr.work,
-					      msecs_to_jiffies(100));
+		schedule_work(&dev_priv->psr.work);
 	mutex_unlock(&dev_priv->psr.lock);
 }
 
@@ -1184,38 +967,64 @@ void intel_psr_init(struct drm_i915_private *dev_priv)
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
 		/* HSW and BDW require workarounds that we don't implement. */
 		dev_priv->psr.link_standby = false;
-	else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		/* On VLV and CHV only standby mode is supported. */
-		dev_priv->psr.link_standby = true;
 	else
 		/* For new platforms let's respect VBT back again */
 		dev_priv->psr.link_standby = dev_priv->vbt.psr.full_link;
 
-	/* Override link_standby x link_off defaults */
-	if (i915_modparams.enable_psr == 2 && !dev_priv->psr.link_standby) {
-		DRM_DEBUG_KMS("PSR: Forcing link standby\n");
-		dev_priv->psr.link_standby = true;
-	}
-	if (i915_modparams.enable_psr == 3 && dev_priv->psr.link_standby) {
-		DRM_DEBUG_KMS("PSR: Forcing main link off\n");
-		dev_priv->psr.link_standby = false;
+	INIT_WORK(&dev_priv->psr.work, intel_psr_work);
+	mutex_init(&dev_priv->psr.lock);
+}
+
+void intel_psr_short_pulse(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = intel_dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct i915_psr *psr = &dev_priv->psr;
+	u8 val;
+	const u8 errors = DP_PSR_RFB_STORAGE_ERROR |
+			  DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR |
+			  DP_PSR_LINK_CRC_ERROR;
+
+	if (!CAN_PSR(dev_priv) || !intel_dp_is_edp(intel_dp))
+		return;
+
+	mutex_lock(&psr->lock);
+
+	if (psr->enabled != intel_dp)
+		goto exit;
+
+	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_STATUS, &val) != 1) {
+		DRM_ERROR("PSR_STATUS dpcd read failed\n");
+		goto exit;
 	}
 
-	INIT_DELAYED_WORK(&dev_priv->psr.work, intel_psr_work);
-	mutex_init(&dev_priv->psr.lock);
+	if ((val & DP_PSR_SINK_STATE_MASK) == DP_PSR_SINK_INTERNAL_ERROR) {
+		DRM_DEBUG_KMS("PSR sink internal error, disabling PSR\n");
+		intel_psr_disable_locked(intel_dp);
+	}
 
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		dev_priv->psr.enable_source = vlv_psr_enable_source;
-		dev_priv->psr.disable_source = vlv_psr_disable;
-		dev_priv->psr.enable_sink = vlv_psr_enable_sink;
-		dev_priv->psr.activate = vlv_psr_activate;
-		dev_priv->psr.setup_vsc = vlv_psr_setup_vsc;
-	} else {
-		dev_priv->psr.has_hw_tracking = true;
-		dev_priv->psr.enable_source = hsw_psr_enable_source;
-		dev_priv->psr.disable_source = hsw_psr_disable;
-		dev_priv->psr.enable_sink = hsw_psr_enable_sink;
-		dev_priv->psr.activate = hsw_psr_activate;
-		dev_priv->psr.setup_vsc = hsw_psr_setup_vsc;
+	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_ERROR_STATUS, &val) != 1) {
+		DRM_ERROR("PSR_ERROR_STATUS dpcd read failed\n");
+		goto exit;
 	}
+
+	if (val & DP_PSR_RFB_STORAGE_ERROR)
+		DRM_DEBUG_KMS("PSR RFB storage error, disabling PSR\n");
+	if (val & DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR)
+		DRM_DEBUG_KMS("PSR VSC SDP uncorrectable error, disabling PSR\n");
+	if (val & DP_PSR_LINK_CRC_ERROR)
+		DRM_ERROR("PSR Link CRC error, disabling PSR\n");
+
+	if (val & ~errors)
+		DRM_ERROR("PSR_ERROR_STATUS unhandled errors %x\n",
+			  val & ~errors);
+	if (val & errors)
+		intel_psr_disable_locked(intel_dp);
+	/* clear status register */
+	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_ERROR_STATUS, val);
+
+	/* TODO: handle PSR2 errors */
+exit:
+	mutex_unlock(&psr->lock);
 }
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 8f19349a6055..33faad3197fe 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -496,6 +496,10 @@ static int init_ring_common(struct intel_engine_cs *engine)
 		DRM_DEBUG_DRIVER("%s initialization failed [head=%08x], fudging\n",
 				 engine->name, I915_READ_HEAD(engine));
 
+	/* Check that the ring offsets point within the ring! */
+	GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->head));
+	GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->tail));
+
 	intel_ring_update_space(ring);
 	I915_WRITE_HEAD(engine, ring->head);
 	I915_WRITE_TAIL(engine, ring->tail);
@@ -520,8 +524,6 @@ static int init_ring_common(struct intel_engine_cs *engine)
 		goto out;
 	}
 
-	intel_engine_init_hangcheck(engine);
-
 	if (INTEL_GEN(dev_priv) > 2)
 		I915_WRITE_MODE(engine, _MASKED_BIT_DISABLE(STOP_RING));
 
@@ -531,16 +533,33 @@ out:
 	return ret;
 }
 
-static void reset_ring_common(struct intel_engine_cs *engine,
-			      struct i915_request *request)
+static struct i915_request *reset_prepare(struct intel_engine_cs *engine)
 {
-	/*
-	 * RC6 must be prevented until the reset is complete and the engine
-	 * reinitialised. If it occurs in the middle of this sequence, the
-	 * state written to/loaded from the power context is ill-defined (e.g.
-	 * the PP_BASE_DIR may be lost).
-	 */
-	assert_forcewakes_active(engine->i915, FORCEWAKE_ALL);
+	intel_engine_stop_cs(engine);
+
+	if (engine->irq_seqno_barrier)
+		engine->irq_seqno_barrier(engine);
+
+	return i915_gem_find_active_request(engine);
+}
+
+static void skip_request(struct i915_request *rq)
+{
+	void *vaddr = rq->ring->vaddr;
+	u32 head;
+
+	head = rq->infix;
+	if (rq->postfix < head) {
+		memset32(vaddr + head, MI_NOOP,
+			 (rq->ring->size - head) / sizeof(u32));
+		head = 0;
+	}
+	memset32(vaddr + head, MI_NOOP, (rq->postfix - head) / sizeof(u32));
+}
+
+static void reset_ring(struct intel_engine_cs *engine, struct i915_request *rq)
+{
+	GEM_TRACE("%s seqno=%x\n", engine->name, rq ? rq->global_seqno : 0);
 
 	/*
 	 * Try to restore the logical GPU state to match the continuation
@@ -556,47 +575,18 @@ static void reset_ring_common(struct intel_engine_cs *engine,
 	 * If the request was innocent, we try to replay the request with
 	 * the restored context.
 	 */
-	if (request) {
-		struct drm_i915_private *dev_priv = request->i915;
-		struct intel_context *ce = to_intel_context(request->ctx,
-							    engine);
-		struct i915_hw_ppgtt *ppgtt;
-
-		if (ce->state) {
-			I915_WRITE(CCID,
-				   i915_ggtt_offset(ce->state) |
-				   BIT(8) /* must be set! */ |
-				   CCID_EXTENDED_STATE_SAVE |
-				   CCID_EXTENDED_STATE_RESTORE |
-				   CCID_EN);
-		}
-
-		ppgtt = request->ctx->ppgtt ?: engine->i915->mm.aliasing_ppgtt;
-		if (ppgtt) {
-			u32 pd_offset = ppgtt->pd.base.ggtt_offset << 10;
-
-			I915_WRITE(RING_PP_DIR_DCLV(engine), PP_DIR_DCLV_2G);
-			I915_WRITE(RING_PP_DIR_BASE(engine), pd_offset);
-
-			/* Wait for the PD reload to complete */
-			if (intel_wait_for_register(dev_priv,
-						    RING_PP_DIR_BASE(engine),
-						    BIT(0), 0,
-						    10))
-				DRM_ERROR("Wait for reload of ppgtt page-directory timed out\n");
-
-			ppgtt->pd_dirty_rings &= ~intel_engine_flag(engine);
-		}
-
+	if (rq) {
 		/* If the rq hung, jump to its breadcrumb and skip the batch */
-		if (request->fence.error == -EIO)
-			request->ring->head = request->postfix;
-	} else {
-		engine->legacy_active_context = NULL;
-		engine->legacy_active_ppgtt = NULL;
+		rq->ring->head = intel_ring_wrap(rq->ring, rq->head);
+		if (rq->fence.error == -EIO)
+			skip_request(rq);
 	}
 }
 
+static void reset_finish(struct intel_engine_cs *engine)
+{
+}
+
 static int intel_rcs_ctx_init(struct i915_request *rq)
 {
 	int ret;
@@ -1033,6 +1023,8 @@ int intel_ring_pin(struct intel_ring *ring,
 		flags |= PIN_OFFSET_BIAS | offset_bias;
 	if (vma->obj->stolen)
 		flags |= PIN_MAPPABLE;
+	else
+		flags |= PIN_HIGH;
 
 	if (!(vma->flags & I915_VMA_GLOBAL_BIND)) {
 		if (flags & PIN_MAPPABLE || map == I915_MAP_WC)
@@ -1066,6 +1058,8 @@ err:
 
 void intel_ring_reset(struct intel_ring *ring, u32 tail)
 {
+	GEM_BUG_ON(!intel_ring_offset_valid(ring, tail));
+
 	ring->tail = tail;
 	ring->head = tail;
 	ring->emit = tail;
@@ -1093,6 +1087,7 @@ void intel_ring_unpin(struct intel_ring *ring)
 static struct i915_vma *
 intel_ring_create_vma(struct drm_i915_private *dev_priv, int size)
 {
+	struct i915_address_space *vm = &dev_priv->ggtt.vm;
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
 
@@ -1102,10 +1097,14 @@ intel_ring_create_vma(struct drm_i915_private *dev_priv, int size)
 	if (IS_ERR(obj))
 		return ERR_CAST(obj);
 
-	/* mark ring buffers as read-only from GPU side by default */
-	obj->gt_ro = 1;
+	/*
+	 * Mark ring buffers as read-only from GPU side (so no stray overwrites)
+	 * if supported by the platform's GGTT.
+	 */
+	if (vm->has_read_only)
+		i915_gem_object_set_readonly(obj);
 
-	vma = i915_vma_instance(obj, &dev_priv->ggtt.base, NULL);
+	vma = i915_vma_instance(obj, vm, NULL);
 	if (IS_ERR(vma))
 		goto err;
 
@@ -1169,10 +1168,46 @@ intel_ring_free(struct intel_ring *ring)
 	kfree(ring);
 }
 
-static int context_pin(struct intel_context *ce)
+static void intel_ring_context_destroy(struct intel_context *ce)
 {
-	struct i915_vma *vma = ce->state;
-	int ret;
+	GEM_BUG_ON(ce->pin_count);
+
+	if (!ce->state)
+		return;
+
+	GEM_BUG_ON(i915_gem_object_is_active(ce->state->obj));
+	i915_gem_object_put(ce->state->obj);
+}
+
+static int __context_pin_ppgtt(struct i915_gem_context *ctx)
+{
+	struct i915_hw_ppgtt *ppgtt;
+	int err = 0;
+
+	ppgtt = ctx->ppgtt ?: ctx->i915->mm.aliasing_ppgtt;
+	if (ppgtt)
+		err = gen6_ppgtt_pin(ppgtt);
+
+	return err;
+}
+
+static void __context_unpin_ppgtt(struct i915_gem_context *ctx)
+{
+	struct i915_hw_ppgtt *ppgtt;
+
+	ppgtt = ctx->ppgtt ?: ctx->i915->mm.aliasing_ppgtt;
+	if (ppgtt)
+		gen6_ppgtt_unpin(ppgtt);
+}
+
+static int __context_pin(struct intel_context *ce)
+{
+	struct i915_vma *vma;
+	int err;
+
+	vma = ce->state;
+	if (!vma)
+		return 0;
 
 	/*
 	 * Clear this page out of any CPU caches for coherent swap-in/out.
@@ -1180,13 +1215,43 @@ static int context_pin(struct intel_context *ce)
 	 * on an active context (which by nature is already on the GPU).
 	 */
 	if (!(vma->flags & I915_VMA_GLOBAL_BIND)) {
-		ret = i915_gem_object_set_to_gtt_domain(vma->obj, true);
-		if (ret)
-			return ret;
+		err = i915_gem_object_set_to_gtt_domain(vma->obj, true);
+		if (err)
+			return err;
 	}
 
-	return i915_vma_pin(vma, 0, I915_GTT_MIN_ALIGNMENT,
-			    PIN_GLOBAL | PIN_HIGH);
+	err = i915_vma_pin(vma, 0, I915_GTT_MIN_ALIGNMENT,
+			   PIN_GLOBAL | PIN_HIGH);
+	if (err)
+		return err;
+
+	/*
+	 * And mark is as a globally pinned object to let the shrinker know
+	 * it cannot reclaim the object until we release it.
+	 */
+	vma->obj->pin_global++;
+
+	return 0;
+}
+
+static void __context_unpin(struct intel_context *ce)
+{
+	struct i915_vma *vma;
+
+	vma = ce->state;
+	if (!vma)
+		return;
+
+	vma->obj->pin_global--;
+	i915_vma_unpin(vma);
+}
+
+static void intel_ring_context_unpin(struct intel_context *ce)
+{
+	__context_unpin_ppgtt(ce->gem_context);
+	__context_unpin(ce);
+
+	i915_gem_context_put(ce->gem_context);
 }
 
 static struct i915_vma *
@@ -1243,7 +1308,7 @@ alloc_context_vma(struct intel_engine_cs *engine)
 		i915_gem_object_set_cache_level(obj, I915_CACHE_L3_LLC);
 	}
 
-	vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+	vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		goto err_obj;
@@ -1258,81 +1323,79 @@ err_obj:
 	return ERR_PTR(err);
 }
 
-static struct intel_ring *
-intel_ring_context_pin(struct intel_engine_cs *engine,
-		       struct i915_gem_context *ctx)
+static struct intel_context *
+__ring_context_pin(struct intel_engine_cs *engine,
+		   struct i915_gem_context *ctx,
+		   struct intel_context *ce)
 {
-	struct intel_context *ce = to_intel_context(ctx, engine);
-	int ret;
-
-	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
-
-	if (likely(ce->pin_count++))
-		goto out;
-	GEM_BUG_ON(!ce->pin_count); /* no overflow please! */
+	int err;
 
 	if (!ce->state && engine->context_size) {
 		struct i915_vma *vma;
 
 		vma = alloc_context_vma(engine);
 		if (IS_ERR(vma)) {
-			ret = PTR_ERR(vma);
+			err = PTR_ERR(vma);
 			goto err;
 		}
 
 		ce->state = vma;
 	}
 
-	if (ce->state) {
-		ret = context_pin(ce);
-		if (ret)
-			goto err;
+	err = __context_pin(ce);
+	if (err)
+		goto err;
 
-		ce->state->obj->pin_global++;
-	}
+	err = __context_pin_ppgtt(ce->gem_context);
+	if (err)
+		goto err_unpin;
 
 	i915_gem_context_get(ctx);
 
-out:
 	/* One ringbuffer to rule them all */
-	return engine->buffer;
+	GEM_BUG_ON(!engine->buffer);
+	ce->ring = engine->buffer;
+
+	return ce;
 
+err_unpin:
+	__context_unpin(ce);
 err:
 	ce->pin_count = 0;
-	return ERR_PTR(ret);
+	return ERR_PTR(err);
 }
 
-static void intel_ring_context_unpin(struct intel_engine_cs *engine,
-				     struct i915_gem_context *ctx)
+static const struct intel_context_ops ring_context_ops = {
+	.unpin = intel_ring_context_unpin,
+	.destroy = intel_ring_context_destroy,
+};
+
+static struct intel_context *
+intel_ring_context_pin(struct intel_engine_cs *engine,
+		       struct i915_gem_context *ctx)
 {
 	struct intel_context *ce = to_intel_context(ctx, engine);
 
 	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
-	GEM_BUG_ON(ce->pin_count == 0);
 
-	if (--ce->pin_count)
-		return;
+	if (likely(ce->pin_count++))
+		return ce;
+	GEM_BUG_ON(!ce->pin_count); /* no overflow please! */
 
-	if (ce->state) {
-		ce->state->obj->pin_global--;
-		i915_vma_unpin(ce->state);
-	}
+	ce->ops = &ring_context_ops;
 
-	i915_gem_context_put(ctx);
+	return __ring_context_pin(engine, ctx, ce);
 }
 
 static int intel_init_ring_buffer(struct intel_engine_cs *engine)
 {
-	struct intel_ring *ring;
 	struct i915_timeline *timeline;
+	struct intel_ring *ring;
+	unsigned int size;
 	int err;
 
 	intel_engine_setup_common(engine);
 
-	err = intel_engine_init_common(engine);
-	if (err)
-		goto err;
-
 	timeline = i915_timeline_create(engine->i915, engine->name);
 	if (IS_ERR(timeline)) {
 		err = PTR_ERR(timeline);
@@ -1354,8 +1417,23 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine)
 	GEM_BUG_ON(engine->buffer);
 	engine->buffer = ring;
 
+	size = PAGE_SIZE;
+	if (HAS_BROKEN_CS_TLB(engine->i915))
+		size = I830_WA_SIZE;
+	err = intel_engine_create_scratch(engine, size);
+	if (err)
+		goto err_unpin;
+
+	err = intel_engine_init_common(engine);
+	if (err)
+		goto err_scratch;
+
 	return 0;
 
+err_scratch:
+	intel_engine_cleanup_scratch(engine);
+err_unpin:
+	intel_ring_unpin(ring);
 err_ring:
 	intel_ring_free(ring);
 err:
@@ -1392,6 +1470,48 @@ void intel_legacy_submission_resume(struct drm_i915_private *dev_priv)
 		intel_ring_reset(engine->buffer, 0);
 }
 
+static int load_pd_dir(struct i915_request *rq,
+		       const struct i915_hw_ppgtt *ppgtt)
+{
+	const struct intel_engine_cs * const engine = rq->engine;
+	u32 *cs;
+
+	cs = intel_ring_begin(rq, 6);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_DCLV(engine));
+	*cs++ = PP_DIR_DCLV_2G;
+
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine));
+	*cs++ = ppgtt->pd.base.ggtt_offset << 10;
+
+	intel_ring_advance(rq, cs);
+
+	return 0;
+}
+
+static int flush_pd_dir(struct i915_request *rq)
+{
+	const struct intel_engine_cs * const engine = rq->engine;
+	u32 *cs;
+
+	cs = intel_ring_begin(rq, 4);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	/* Stall until the page table load is complete */
+	*cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
+	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine));
+	*cs++ = i915_ggtt_offset(engine->scratch);
+	*cs++ = MI_NOOP;
+
+	intel_ring_advance(rq, cs);
+	return 0;
+}
+
 static inline int mi_set_context(struct i915_request *rq, u32 flags)
 {
 	struct drm_i915_private *i915 = rq->i915;
@@ -1402,6 +1522,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 		(HAS_LEGACY_SEMAPHORES(i915) && IS_GEN7(i915)) ?
 		INTEL_INFO(i915)->num_rings - 1 :
 		0;
+	bool force_restore = false;
 	int len;
 	u32 *cs;
 
@@ -1415,6 +1536,12 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 	len = 4;
 	if (IS_GEN7(i915))
 		len += 2 + (num_rings ? 4*num_rings + 6 : 0);
+	if (flags & MI_FORCE_RESTORE) {
+		GEM_BUG_ON(flags & MI_RESTORE_INHIBIT);
+		flags &= ~MI_FORCE_RESTORE;
+		force_restore = true;
+		len += 2;
+	}
 
 	cs = intel_ring_begin(rq, len);
 	if (IS_ERR(cs))
@@ -1439,9 +1566,29 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 		}
 	}
 
+	if (force_restore) {
+		/*
+		 * The HW doesn't handle being told to restore the current
+		 * context very well. Quite often it likes goes to go off and
+		 * sulk, especially when it is meant to be reloading PP_DIR.
+		 * A very simple fix to force the reload is to simply switch
+		 * away from the current context and back again.
+		 *
+		 * Note that the kernel_context will contain random state
+		 * following the INHIBIT_RESTORE. We accept this since we
+		 * never use the kernel_context state; it is merely a
+		 * placeholder we use to flush other contexts.
+		 */
+		*cs++ = MI_SET_CONTEXT;
+		*cs++ = i915_ggtt_offset(to_intel_context(i915->kernel_context,
+							  engine)->state) |
+			MI_MM_SPACE_GTT |
+			MI_RESTORE_INHIBIT;
+	}
+
 	*cs++ = MI_NOOP;
 	*cs++ = MI_SET_CONTEXT;
-	*cs++ = i915_ggtt_offset(to_intel_context(rq->ctx, engine)->state) | flags;
+	*cs++ = i915_ggtt_offset(rq->hw_context->state) | flags;
 	/*
 	 * w/a: MI_SET_CONTEXT must always be followed by MI_NOOP
 	 * WaMiSetContext_Hang:snb,ivb,vlv
@@ -1509,31 +1656,28 @@ static int remap_l3(struct i915_request *rq, int slice)
 static int switch_context(struct i915_request *rq)
 {
 	struct intel_engine_cs *engine = rq->engine;
-	struct i915_gem_context *to_ctx = rq->ctx;
-	struct i915_hw_ppgtt *to_mm =
-		to_ctx->ppgtt ?: rq->i915->mm.aliasing_ppgtt;
-	struct i915_gem_context *from_ctx = engine->legacy_active_context;
-	struct i915_hw_ppgtt *from_mm = engine->legacy_active_ppgtt;
+	struct i915_gem_context *ctx = rq->gem_context;
+	struct i915_hw_ppgtt *ppgtt = ctx->ppgtt ?: rq->i915->mm.aliasing_ppgtt;
+	unsigned int unwind_mm = 0;
 	u32 hw_flags = 0;
 	int ret, i;
 
 	lockdep_assert_held(&rq->i915->drm.struct_mutex);
 	GEM_BUG_ON(HAS_EXECLISTS(rq->i915));
 
-	if (to_mm != from_mm ||
-	    (to_mm && intel_engine_flag(engine) & to_mm->pd_dirty_rings)) {
-		trace_switch_mm(engine, to_ctx);
-		ret = to_mm->switch_mm(to_mm, rq);
+	if (ppgtt) {
+		ret = load_pd_dir(rq, ppgtt);
 		if (ret)
 			goto err;
 
-		to_mm->pd_dirty_rings &= ~intel_engine_flag(engine);
-		engine->legacy_active_ppgtt = to_mm;
-		hw_flags = MI_FORCE_RESTORE;
+		if (intel_engine_flag(engine) & ppgtt->pd_dirty_rings) {
+			unwind_mm = intel_engine_flag(engine);
+			ppgtt->pd_dirty_rings &= ~unwind_mm;
+			hw_flags = MI_FORCE_RESTORE;
+		}
 	}
 
-	if (to_intel_context(to_ctx, engine)->state &&
-	    (to_ctx != from_ctx || hw_flags & MI_FORCE_RESTORE)) {
+	if (rq->hw_context->state) {
 		GEM_BUG_ON(engine->id != RCS);
 
 		/*
@@ -1543,35 +1687,38 @@ static int switch_context(struct i915_request *rq)
 		 * as nothing actually executes using the kernel context; it
 		 * is purely used for flushing user contexts.
 		 */
-		if (i915_gem_context_is_kernel(to_ctx))
+		if (i915_gem_context_is_kernel(ctx))
 			hw_flags = MI_RESTORE_INHIBIT;
 
 		ret = mi_set_context(rq, hw_flags);
 		if (ret)
 			goto err_mm;
+	}
 
-		engine->legacy_active_context = to_ctx;
+	if (ppgtt) {
+		ret = flush_pd_dir(rq);
+		if (ret)
+			goto err_mm;
 	}
 
-	if (to_ctx->remap_slice) {
+	if (ctx->remap_slice) {
 		for (i = 0; i < MAX_L3_SLICES; i++) {
-			if (!(to_ctx->remap_slice & BIT(i)))
+			if (!(ctx->remap_slice & BIT(i)))
 				continue;
 
 			ret = remap_l3(rq, i);
 			if (ret)
-				goto err_ctx;
+				goto err_mm;
 		}
 
-		to_ctx->remap_slice = 0;
+		ctx->remap_slice = 0;
 	}
 
 	return 0;
 
-err_ctx:
-	engine->legacy_active_context = from_ctx;
 err_mm:
-	engine->legacy_active_ppgtt = from_mm;
+	if (unwind_mm)
+		ppgtt->pd_dirty_rings |= unwind_mm;
 err:
 	return ret;
 }
@@ -1580,7 +1727,7 @@ static int ring_request_alloc(struct i915_request *request)
 {
 	int ret;
 
-	GEM_BUG_ON(!to_intel_context(request->ctx, request->engine)->pin_count);
+	GEM_BUG_ON(!request->hw_context->pin_count);
 
 	/* Flush enough space to reduce the likelihood of waiting after
 	 * we start building the request - in which case we will just
@@ -2006,11 +2153,11 @@ static void intel_ring_default_vfuncs(struct drm_i915_private *dev_priv,
 	intel_ring_init_semaphores(dev_priv, engine);
 
 	engine->init_hw = init_ring_common;
-	engine->reset_hw = reset_ring_common;
+	engine->reset.prepare = reset_prepare;
+	engine->reset.reset = reset_ring;
+	engine->reset.finish = reset_finish;
 
 	engine->context_pin = intel_ring_context_pin;
-	engine->context_unpin = intel_ring_context_unpin;
-
 	engine->request_alloc = ring_request_alloc;
 
 	engine->emit_breadcrumb = i9xx_emit_breadcrumb;
@@ -2074,16 +2221,6 @@ int intel_init_render_ring_buffer(struct intel_engine_cs *engine)
 	if (ret)
 		return ret;
 
-	if (INTEL_GEN(dev_priv) >= 6) {
-		ret = intel_engine_create_scratch(engine, PAGE_SIZE);
-		if (ret)
-			return ret;
-	} else if (HAS_BROKEN_CS_TLB(dev_priv)) {
-		ret = intel_engine_create_scratch(engine, I830_WA_SIZE);
-		if (ret)
-			return ret;
-	}
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 010750e8ee44..f5ffa6d31e82 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -122,7 +122,8 @@ struct intel_engine_hangcheck {
 	int deadlock;
 	struct intel_instdone instdone;
 	struct i915_request *active_request;
-	bool stalled;
+	bool stalled:1;
+	bool wedged:1;
 };
 
 struct intel_ring {
@@ -192,6 +193,11 @@ struct i915_priolist {
 	int priority;
 };
 
+struct st_preempt_hang {
+	struct completion completion;
+	bool inject_hang;
+};
+
 /**
  * struct intel_engine_execlists - execlist submission queue and port state
  *
@@ -291,32 +297,49 @@ struct intel_engine_execlists {
 	/**
 	 * @queue: queue of requests, in priority lists
 	 */
-	struct rb_root queue;
+	struct rb_root_cached queue;
 
 	/**
-	 * @first: leftmost level in priority @queue
+	 * @csb_read: control register for Context Switch buffer
+	 *
+	 * Note this register is always in mmio.
 	 */
-	struct rb_node *first;
+	u32 __iomem *csb_read;
 
 	/**
-	 * @fw_domains: forcewake domains for irq tasklet
+	 * @csb_write: control register for Context Switch buffer
+	 *
+	 * Note this register may be either mmio or HWSP shadow.
 	 */
-	unsigned int fw_domains;
+	u32 *csb_write;
 
 	/**
-	 * @csb_head: context status buffer head
+	 * @csb_status: status array for Context Switch buffer
+	 *
+	 * Note these register may be either mmio or HWSP shadow.
 	 */
-	unsigned int csb_head;
+	u32 *csb_status;
 
 	/**
-	 * @csb_use_mmio: access csb through mmio, instead of hwsp
+	 * @preempt_complete_status: expected CSB upon completing preemption
 	 */
-	bool csb_use_mmio;
+	u32 preempt_complete_status;
 
 	/**
-	 * @preempt_complete_status: expected CSB upon completing preemption
+	 * @csb_write_reset: reset value for CSB write pointer
+	 *
+	 * As the CSB write pointer maybe either in HWSP or as a field
+	 * inside an mmio register, we want to reprogram it slightly
+	 * differently to avoid later confusion.
 	 */
-	u32 preempt_complete_status;
+	u32 csb_write_reset;
+
+	/**
+	 * @csb_head: context status buffer head
+	 */
+	u8 csb_head;
+
+	I915_SELFTEST_DECLARE(struct st_preempt_hang preempt_hang;)
 };
 
 #define INTEL_ENGINE_CS_MAX_NAME 8
@@ -342,11 +365,10 @@ struct intel_engine_cs {
 	struct i915_timeline timeline;
 
 	struct drm_i915_gem_object *default_state;
+	void *pinned_default_state;
 
-	atomic_t irq_count;
 	unsigned long irq_posted;
 #define ENGINE_IRQ_BREADCRUMB 0
-#define ENGINE_IRQ_EXECLIST 1
 
 	/* Rather than have every client wait upon all user interrupts,
 	 * with the herd waking after every interrupt and each doing the
@@ -378,6 +400,7 @@ struct intel_engine_cs {
 
 		unsigned int hangcheck_interrupts;
 		unsigned int irq_enabled;
+		unsigned int irq_count;
 
 		bool irq_armed : 1;
 		I915_SELFTEST_DECLARE(bool mock : 1);
@@ -423,18 +446,22 @@ struct intel_engine_cs {
 	void		(*irq_disable)(struct intel_engine_cs *engine);
 
 	int		(*init_hw)(struct intel_engine_cs *engine);
-	void		(*reset_hw)(struct intel_engine_cs *engine,
-				    struct i915_request *rq);
+
+	struct {
+		struct i915_request *(*prepare)(struct intel_engine_cs *engine);
+		void (*reset)(struct intel_engine_cs *engine,
+			      struct i915_request *rq);
+		void (*finish)(struct intel_engine_cs *engine);
+	} reset;
 
 	void		(*park)(struct intel_engine_cs *engine);
 	void		(*unpark)(struct intel_engine_cs *engine);
 
 	void		(*set_default_submission)(struct intel_engine_cs *engine);
 
-	struct intel_ring *(*context_pin)(struct intel_engine_cs *engine,
-					  struct i915_gem_context *ctx);
-	void		(*context_unpin)(struct intel_engine_cs *engine,
-					 struct i915_gem_context *ctx);
+	struct intel_context *(*context_pin)(struct intel_engine_cs *engine,
+					     struct i915_gem_context *ctx);
+
 	int		(*request_alloc)(struct i915_request *rq);
 	int		(*init_context)(struct i915_request *rq);
 
@@ -550,16 +577,7 @@ struct intel_engine_cs {
 	 * to the kernel context and trash it as the save may not happen
 	 * before the hardware is powered down.
 	 */
-	struct i915_gem_context *last_retired_context;
-
-	/* We track the current MI_SET_CONTEXT in order to eliminate
-	 * redudant context switches. This presumes that requests are not
-	 * reordered! Or when they are the tracking is updated along with
-	 * the emission of individual requests into the legacy command
-	 * stream (ring).
-	 */
-	struct i915_gem_context *legacy_active_context;
-	struct i915_hw_ppgtt *legacy_active_ppgtt;
+	struct intel_context *last_retired_context;
 
 	/* status_notifier: list of callbacks for context-switch changes */
 	struct atomic_notifier_head context_status_notifier;
@@ -672,6 +690,12 @@ execlists_clear_active(struct intel_engine_execlists *execlists,
 	__clear_bit(bit, (unsigned long *)&execlists->active);
 }
 
+static inline void
+execlists_clear_all_active(struct intel_engine_execlists *execlists)
+{
+	execlists->active = 0;
+}
+
 static inline bool
 execlists_is_active(const struct intel_engine_execlists *execlists,
 		    unsigned int bit)
@@ -809,6 +833,19 @@ static inline u32 intel_ring_wrap(const struct intel_ring *ring, u32 pos)
 	return pos & (ring->size - 1);
 }
 
+static inline bool
+intel_ring_offset_valid(const struct intel_ring *ring,
+			unsigned int pos)
+{
+	if (pos & -ring->size) /* must be strictly within the ring */
+		return false;
+
+	if (!IS_ALIGNED(pos, 8)) /* must be qword aligned */
+		return false;
+
+	return true;
+}
+
 static inline u32 intel_ring_offset(const struct i915_request *rq, void *addr)
 {
 	/* Don't write ring->size (equivalent to 0) as that hangs some GPUs. */
@@ -820,12 +857,7 @@ static inline u32 intel_ring_offset(const struct i915_request *rq, void *addr)
 static inline void
 assert_ring_tail_valid(const struct intel_ring *ring, unsigned int tail)
 {
-	/* We could combine these into a single tail operation, but keeping
-	 * them as seperate tests will help identify the cause should one
-	 * ever fire.
-	 */
-	GEM_BUG_ON(!IS_ALIGNED(tail, 8));
-	GEM_BUG_ON(tail >= ring->size);
+	GEM_BUG_ON(!intel_ring_offset_valid(ring, tail));
 
 	/*
 	 * "Ring Buffer Use"
@@ -865,14 +897,19 @@ void intel_engine_init_global_seqno(struct intel_engine_cs *engine, u32 seqno);
 
 void intel_engine_setup_common(struct intel_engine_cs *engine);
 int intel_engine_init_common(struct intel_engine_cs *engine);
-int intel_engine_create_scratch(struct intel_engine_cs *engine, int size);
 void intel_engine_cleanup_common(struct intel_engine_cs *engine);
 
+int intel_engine_create_scratch(struct intel_engine_cs *engine,
+				unsigned int size);
+void intel_engine_cleanup_scratch(struct intel_engine_cs *engine);
+
 int intel_init_render_ring_buffer(struct intel_engine_cs *engine);
 int intel_init_bsd_ring_buffer(struct intel_engine_cs *engine);
 int intel_init_blt_ring_buffer(struct intel_engine_cs *engine);
 int intel_init_vebox_ring_buffer(struct intel_engine_cs *engine);
 
+int intel_engine_stop_cs(struct intel_engine_cs *engine);
+
 u64 intel_engine_get_active_head(const struct intel_engine_cs *engine);
 u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine);
 
@@ -918,11 +955,10 @@ static inline u32 intel_hws_preempt_done_address(struct intel_engine_cs *engine)
 /* intel_breadcrumbs.c -- user interrupt bottom-half for waiters */
 int intel_engine_init_breadcrumbs(struct intel_engine_cs *engine);
 
-static inline void intel_wait_init(struct intel_wait *wait,
-				   struct i915_request *rq)
+static inline void intel_wait_init(struct intel_wait *wait)
 {
 	wait->tsk = current;
-	wait->request = rq;
+	wait->request = NULL;
 }
 
 static inline void intel_wait_init_for_seqno(struct intel_wait *wait, u32 seqno)
@@ -1042,10 +1078,13 @@ gen8_emit_ggtt_write(u32 *cs, u32 value, u32 gtt_offset)
 	return cs;
 }
 
+void intel_engines_sanitize(struct drm_i915_private *i915);
+
 bool intel_engine_is_idle(struct intel_engine_cs *engine);
 bool intel_engines_are_idle(struct drm_i915_private *dev_priv);
 
 bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine);
+void intel_engine_lost_context(struct intel_engine_cs *engine);
 
 void intel_engines_park(struct drm_i915_private *i915);
 void intel_engines_unpark(struct drm_i915_private *i915);
@@ -1123,4 +1162,24 @@ void intel_disable_engine_stats(struct intel_engine_cs *engine);
 
 ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine);
 
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+
+static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists)
+{
+	if (!execlists->preempt_hang.inject_hang)
+		return false;
+
+	complete(&execlists->preempt_hang.completion);
+	return true;
+}
+
+#else
+
+static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists)
+{
+	return false;
+}
+
+#endif
+
 #endif /* _INTEL_RINGBUFFER_H_ */
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 53a6eaa9671a..6b5aa3b074ec 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -128,10 +128,20 @@ intel_display_power_domain_str(enum intel_display_power_domain domain)
 		return "AUX_C";
 	case POWER_DOMAIN_AUX_D:
 		return "AUX_D";
+	case POWER_DOMAIN_AUX_E:
+		return "AUX_E";
 	case POWER_DOMAIN_AUX_F:
 		return "AUX_F";
 	case POWER_DOMAIN_AUX_IO_A:
 		return "AUX_IO_A";
+	case POWER_DOMAIN_AUX_TBT1:
+		return "AUX_TBT1";
+	case POWER_DOMAIN_AUX_TBT2:
+		return "AUX_TBT2";
+	case POWER_DOMAIN_AUX_TBT3:
+		return "AUX_TBT3";
+	case POWER_DOMAIN_AUX_TBT4:
+		return "AUX_TBT4";
 	case POWER_DOMAIN_GMBUS:
 		return "GMBUS";
 	case POWER_DOMAIN_INIT:
@@ -382,7 +392,8 @@ static void hsw_power_well_enable(struct drm_i915_private *dev_priv,
 	u32 val;
 
 	if (wait_fuses) {
-		pg = SKL_PW_TO_PG(id);
+		pg = INTEL_GEN(dev_priv) >= 11 ? ICL_PW_TO_PG(id) :
+						 SKL_PW_TO_PG(id);
 		/*
 		 * For PW1 we have to wait both for the PW0/PG0 fuse state
 		 * before enabling the power well and PW1/PG1's own fuse
@@ -428,6 +439,43 @@ static void hsw_power_well_disable(struct drm_i915_private *dev_priv,
 	hsw_wait_for_power_well_disable(dev_priv, power_well);
 }
 
+#define ICL_AUX_PW_TO_PORT(pw)	((pw) - ICL_DISP_PW_AUX_A)
+
+static void
+icl_combo_phy_aux_power_well_enable(struct drm_i915_private *dev_priv,
+				    struct i915_power_well *power_well)
+{
+	enum i915_power_well_id id = power_well->id;
+	enum port port = ICL_AUX_PW_TO_PORT(id);
+	u32 val;
+
+	val = I915_READ(HSW_PWR_WELL_CTL_DRIVER(id));
+	I915_WRITE(HSW_PWR_WELL_CTL_DRIVER(id), val | HSW_PWR_WELL_CTL_REQ(id));
+
+	val = I915_READ(ICL_PORT_CL_DW12(port));
+	I915_WRITE(ICL_PORT_CL_DW12(port), val | ICL_LANE_ENABLE_AUX);
+
+	hsw_wait_for_power_well_enable(dev_priv, power_well);
+}
+
+static void
+icl_combo_phy_aux_power_well_disable(struct drm_i915_private *dev_priv,
+				     struct i915_power_well *power_well)
+{
+	enum i915_power_well_id id = power_well->id;
+	enum port port = ICL_AUX_PW_TO_PORT(id);
+	u32 val;
+
+	val = I915_READ(ICL_PORT_CL_DW12(port));
+	I915_WRITE(ICL_PORT_CL_DW12(port), val & ~ICL_LANE_ENABLE_AUX);
+
+	val = I915_READ(HSW_PWR_WELL_CTL_DRIVER(id));
+	I915_WRITE(HSW_PWR_WELL_CTL_DRIVER(id),
+		   val & ~HSW_PWR_WELL_CTL_REQ(id));
+
+	hsw_wait_for_power_well_disable(dev_priv, power_well);
+}
+
 /*
  * We should only use the power well if we explicitly asked the hardware to
  * enable it, so check if it's enabled and also check if we've requested it to
@@ -1822,6 +1870,7 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 	BIT_ULL(POWER_DOMAIN_INIT))
 #define GLK_DISPLAY_AUX_A_POWER_DOMAINS (		\
 	BIT_ULL(POWER_DOMAIN_AUX_A) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_IO_A) |		\
 	BIT_ULL(POWER_DOMAIN_INIT))
 #define GLK_DISPLAY_AUX_B_POWER_DOMAINS (		\
 	BIT_ULL(POWER_DOMAIN_AUX_B) |		\
@@ -1894,6 +1943,105 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 	BIT_ULL(POWER_DOMAIN_AUX_A) |			\
 	BIT_ULL(POWER_DOMAIN_INIT))
 
+/*
+ * ICL PW_0/PG_0 domains (HW/DMC control):
+ * - PCI
+ * - clocks except port PLL
+ * - central power except FBC
+ * - shared functions except pipe interrupts, pipe MBUS, DBUF registers
+ * ICL PW_1/PG_1 domains (HW/DMC control):
+ * - DBUF function
+ * - PIPE_A and its planes, except VGA
+ * - transcoder EDP + PSR
+ * - transcoder DSI
+ * - DDI_A
+ * - FBC
+ */
+#define ICL_PW_4_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PIPE_C) |			\
+	BIT_ULL(POWER_DOMAIN_PIPE_C_PANEL_FITTER) |	\
+	BIT_ULL(POWER_DOMAIN_INIT))
+	/* VDSC/joining */
+#define ICL_PW_3_POWER_DOMAINS (			\
+	ICL_PW_4_POWER_DOMAINS |			\
+	BIT_ULL(POWER_DOMAIN_PIPE_B) |			\
+	BIT_ULL(POWER_DOMAIN_TRANSCODER_A) |		\
+	BIT_ULL(POWER_DOMAIN_TRANSCODER_B) |		\
+	BIT_ULL(POWER_DOMAIN_TRANSCODER_C) |		\
+	BIT_ULL(POWER_DOMAIN_PIPE_B_PANEL_FITTER) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_B_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_B_IO) |		\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_C_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_C_IO) |		\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_D_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_D_IO) |		\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_E_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_E_IO) |		\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_F_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_F_IO) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_B) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_C) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_D) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_E) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_F) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT1) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT2) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT3) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT4) |		\
+	BIT_ULL(POWER_DOMAIN_VGA) |			\
+	BIT_ULL(POWER_DOMAIN_AUDIO) |			\
+	BIT_ULL(POWER_DOMAIN_INIT))
+	/*
+	 * - transcoder WD
+	 * - KVMR (HW control)
+	 */
+#define ICL_PW_2_POWER_DOMAINS (			\
+	ICL_PW_3_POWER_DOMAINS |			\
+	BIT_ULL(POWER_DOMAIN_INIT))
+	/*
+	 * - eDP/DSI VDSC
+	 * - KVMR (HW control)
+	 */
+#define ICL_DISPLAY_DC_OFF_POWER_DOMAINS (		\
+	ICL_PW_2_POWER_DOMAINS |			\
+	BIT_ULL(POWER_DOMAIN_MODESET) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_A) |			\
+	BIT_ULL(POWER_DOMAIN_INIT))
+
+#define ICL_DDI_IO_A_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_A_IO))
+#define ICL_DDI_IO_B_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_B_IO))
+#define ICL_DDI_IO_C_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_C_IO))
+#define ICL_DDI_IO_D_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_D_IO))
+#define ICL_DDI_IO_E_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_E_IO))
+#define ICL_DDI_IO_F_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_F_IO))
+
+#define ICL_AUX_A_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_A))
+#define ICL_AUX_B_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_B))
+#define ICL_AUX_C_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_C))
+#define ICL_AUX_D_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_D))
+#define ICL_AUX_E_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_E))
+#define ICL_AUX_F_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_F))
+#define ICL_AUX_TBT1_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT1))
+#define ICL_AUX_TBT2_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT2))
+#define ICL_AUX_TBT3_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT3))
+#define ICL_AUX_TBT4_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT4))
+
 static const struct i915_power_well_ops i9xx_always_on_power_well_ops = {
 	.sync_hw = i9xx_power_well_sync_hw_noop,
 	.enable = i9xx_always_on_power_well_noop,
@@ -2451,6 +2599,157 @@ static struct i915_power_well cnl_power_wells[] = {
 	},
 };
 
+static const struct i915_power_well_ops icl_combo_phy_aux_power_well_ops = {
+	.sync_hw = hsw_power_well_sync_hw,
+	.enable = icl_combo_phy_aux_power_well_enable,
+	.disable = icl_combo_phy_aux_power_well_disable,
+	.is_enabled = hsw_power_well_enabled,
+};
+
+static struct i915_power_well icl_power_wells[] = {
+	{
+		.name = "always-on",
+		.always_on = 1,
+		.domains = POWER_DOMAIN_MASK,
+		.ops = &i9xx_always_on_power_well_ops,
+		.id = I915_DISP_PW_ALWAYS_ON,
+	},
+	{
+		.name = "power well 1",
+		/* Handled by the DMC firmware */
+		.domains = 0,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_1,
+		.hsw.has_fuses = true,
+	},
+	{
+		.name = "power well 2",
+		.domains = ICL_PW_2_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_2,
+		.hsw.has_fuses = true,
+	},
+	{
+		.name = "DC off",
+		.domains = ICL_DISPLAY_DC_OFF_POWER_DOMAINS,
+		.ops = &gen9_dc_off_power_well_ops,
+		.id = SKL_DISP_PW_DC_OFF,
+	},
+	{
+		.name = "power well 3",
+		.domains = ICL_PW_3_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_3,
+		.hsw.irq_pipe_mask = BIT(PIPE_B),
+		.hsw.has_vga = true,
+		.hsw.has_fuses = true,
+	},
+	{
+		.name = "DDI A IO",
+		.domains = ICL_DDI_IO_A_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_DDI_A,
+	},
+	{
+		.name = "DDI B IO",
+		.domains = ICL_DDI_IO_B_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_DDI_B,
+	},
+	{
+		.name = "DDI C IO",
+		.domains = ICL_DDI_IO_C_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_DDI_C,
+	},
+	{
+		.name = "DDI D IO",
+		.domains = ICL_DDI_IO_D_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_DDI_D,
+	},
+	{
+		.name = "DDI E IO",
+		.domains = ICL_DDI_IO_E_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_DDI_E,
+	},
+	{
+		.name = "DDI F IO",
+		.domains = ICL_DDI_IO_F_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_DDI_F,
+	},
+	{
+		.name = "AUX A",
+		.domains = ICL_AUX_A_IO_POWER_DOMAINS,
+		.ops = &icl_combo_phy_aux_power_well_ops,
+		.id = ICL_DISP_PW_AUX_A,
+	},
+	{
+		.name = "AUX B",
+		.domains = ICL_AUX_B_IO_POWER_DOMAINS,
+		.ops = &icl_combo_phy_aux_power_well_ops,
+		.id = ICL_DISP_PW_AUX_B,
+	},
+	{
+		.name = "AUX C",
+		.domains = ICL_AUX_C_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_C,
+	},
+	{
+		.name = "AUX D",
+		.domains = ICL_AUX_D_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_D,
+	},
+	{
+		.name = "AUX E",
+		.domains = ICL_AUX_E_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_E,
+	},
+	{
+		.name = "AUX F",
+		.domains = ICL_AUX_F_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_F,
+	},
+	{
+		.name = "AUX TBT1",
+		.domains = ICL_AUX_TBT1_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_TBT1,
+	},
+	{
+		.name = "AUX TBT2",
+		.domains = ICL_AUX_TBT2_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_TBT2,
+	},
+	{
+		.name = "AUX TBT3",
+		.domains = ICL_AUX_TBT3_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_TBT3,
+	},
+	{
+		.name = "AUX TBT4",
+		.domains = ICL_AUX_TBT4_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_TBT4,
+	},
+	{
+		.name = "power well 4",
+		.domains = ICL_PW_4_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_4,
+		.hsw.has_fuses = true,
+		.hsw.irq_pipe_mask = BIT(PIPE_C),
+	},
+};
+
 static int
 sanitize_disable_power_well_option(const struct drm_i915_private *dev_priv,
 				   int disable_power_well)
@@ -2468,7 +2767,7 @@ static uint32_t get_allowed_dc_mask(const struct drm_i915_private *dev_priv,
 	int requested_dc;
 	int max_dc;
 
-	if (IS_GEN9_BC(dev_priv) || IS_CANNONLAKE(dev_priv)) {
+	if (IS_GEN9_BC(dev_priv) || INTEL_INFO(dev_priv)->gen >= 10) {
 		max_dc = 2;
 		mask = 0;
 	} else if (IS_GEN9_LP(dev_priv)) {
@@ -2556,7 +2855,9 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv)
 	 * The enabling order will be from lower to higher indexed wells,
 	 * the disabling order is reversed.
 	 */
-	if (IS_HASWELL(dev_priv)) {
+	if (IS_ICELAKE(dev_priv)) {
+		set_power_wells(power_domains, icl_power_wells);
+	} else if (IS_HASWELL(dev_priv)) {
 		set_power_wells(power_domains, hsw_power_wells);
 	} else if (IS_BROADWELL(dev_priv)) {
 		set_power_wells(power_domains, bdw_power_wells);
@@ -2911,6 +3212,7 @@ static void cnl_set_procmon_ref_values(struct drm_i915_private *dev_priv,
 	switch (val & (PROCESS_INFO_MASK | VOLTAGE_INFO_MASK)) {
 	default:
 		MISSING_CASE(val);
+		/* fall through */
 	case VOLTAGE_INFO_0_85V | PROCESS_INFO_DOT_0:
 		procmon = &cnl_procmon_values[PROCMON_0_85V_DOT_0];
 		break;
@@ -3023,6 +3325,8 @@ static void cnl_display_core_uninit(struct drm_i915_private *dev_priv)
 static void icl_display_core_init(struct drm_i915_private *dev_priv,
 				  bool resume)
 {
+	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+	struct i915_power_well *well;
 	enum port port;
 	u32 val;
 
@@ -3051,8 +3355,14 @@ static void icl_display_core_init(struct drm_i915_private *dev_priv,
 		I915_WRITE(ICL_PORT_CL_DW5(port), val);
 	}
 
-	/* 4. Enable power well 1 (PG1) and aux IO power. */
-	/* FIXME: ICL power wells code not here yet. */
+	/*
+	 * 4. Enable Power Well 1 (PG1).
+	 *    The AUX IO power wells will be enabled on demand.
+	 */
+	mutex_lock(&power_domains->lock);
+	well = lookup_power_well(dev_priv, ICL_DISP_PW_1);
+	intel_power_well_enable(dev_priv, well);
+	mutex_unlock(&power_domains->lock);
 
 	/* 5. Enable CDCLK. */
 	icl_init_cdclk(dev_priv);
@@ -3070,6 +3380,8 @@ static void icl_display_core_init(struct drm_i915_private *dev_priv,
 
 static void icl_display_core_uninit(struct drm_i915_private *dev_priv)
 {
+	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+	struct i915_power_well *well;
 	enum port port;
 	u32 val;
 
@@ -3083,8 +3395,15 @@ static void icl_display_core_uninit(struct drm_i915_private *dev_priv)
 	/* 3. Disable CD clock */
 	icl_uninit_cdclk(dev_priv);
 
-	/* 4. Disable Power Well 1 (PG1) and Aux IO Power */
-	/* FIXME: ICL power wells code not here yet. */
+	/*
+	 * 4. Disable Power Well 1 (PG1).
+	 *    The AUX IO power wells are toggled on demand, so they are already
+	 *    disabled at this point.
+	 */
+	mutex_lock(&power_domains->lock);
+	well = lookup_power_well(dev_priv, ICL_DISP_PW_1);
+	intel_power_well_disable(dev_priv, well);
+	mutex_unlock(&power_domains->lock);
 
 	/* 5. Disable Comp */
 	for (port = PORT_A; port <= PORT_B; port++) {
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 26975df4e593..812fe7b06f87 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -1340,6 +1340,7 @@ static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder,
 	switch (crtc_state->pixel_multiplier) {
 	default:
 		WARN(1, "unknown pixel multiplier specified\n");
+		/* fall through */
 	case 1: rate = SDVO_CLOCK_RATE_MULT_1X; break;
 	case 2: rate = SDVO_CLOCK_RATE_MULT_2X; break;
 	case 4: rate = SDVO_CLOCK_RATE_MULT_4X; break;
@@ -1400,33 +1401,40 @@ static bool intel_sdvo_connector_get_hw_state(struct intel_connector *connector)
 
 	intel_sdvo_get_active_outputs(intel_sdvo, &active_outputs);
 
-	if (active_outputs & intel_sdvo_connector->output_flag)
-		return true;
+	return active_outputs & intel_sdvo_connector->output_flag;
+}
+
+bool intel_sdvo_port_enabled(struct drm_i915_private *dev_priv,
+			     i915_reg_t sdvo_reg, enum pipe *pipe)
+{
+	u32 val;
+
+	val = I915_READ(sdvo_reg);
+
+	/* asserts want to know the pipe even if the port is disabled */
+	if (HAS_PCH_CPT(dev_priv))
+		*pipe = (val & SDVO_PIPE_SEL_MASK_CPT) >> SDVO_PIPE_SEL_SHIFT_CPT;
+	else if (IS_CHERRYVIEW(dev_priv))
+		*pipe = (val & SDVO_PIPE_SEL_MASK_CHV) >> SDVO_PIPE_SEL_SHIFT_CHV;
 	else
-		return false;
+		*pipe = (val & SDVO_PIPE_SEL_MASK) >> SDVO_PIPE_SEL_SHIFT;
+
+	return val & SDVO_ENABLE;
 }
 
 static bool intel_sdvo_get_hw_state(struct intel_encoder *encoder,
 				    enum pipe *pipe)
 {
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
 	u16 active_outputs = 0;
-	u32 tmp;
+	bool ret;
 
-	tmp = I915_READ(intel_sdvo->sdvo_reg);
 	intel_sdvo_get_active_outputs(intel_sdvo, &active_outputs);
 
-	if (!(tmp & SDVO_ENABLE) && (active_outputs == 0))
-		return false;
+	ret = intel_sdvo_port_enabled(dev_priv, intel_sdvo->sdvo_reg, pipe);
 
-	if (HAS_PCH_CPT(dev_priv))
-		*pipe = PORT_TO_PIPE_CPT(tmp);
-	else
-		*pipe = PORT_TO_PIPE(tmp);
-
-	return true;
+	return ret || active_outputs;
 }
 
 static void intel_sdvo_get_config(struct intel_encoder *encoder,
@@ -1553,8 +1561,8 @@ static void intel_disable_sdvo(struct intel_encoder *encoder,
 		intel_set_cpu_fifo_underrun_reporting(dev_priv, PIPE_A, false);
 		intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, false);
 
-		temp &= ~SDVO_PIPE_B_SELECT;
-		temp |= SDVO_ENABLE;
+		temp &= ~SDVO_PIPE_SEL_MASK;
+		temp |= SDVO_ENABLE | SDVO_PIPE_SEL(PIPE_A);
 		intel_sdvo_write_sdvox(intel_sdvo, temp);
 
 		temp &= ~SDVO_ENABLE;
@@ -1903,7 +1911,7 @@ static void intel_sdvo_get_ddc_modes(struct drm_connector *connector)
 	if (edid != NULL) {
 		if (intel_sdvo_connector_matches_edid(to_intel_sdvo_connector(connector),
 						      edid)) {
-			drm_mode_connector_update_edid_property(connector, edid);
+			drm_connector_update_edid_property(connector, edid);
 			drm_add_edid_modes(connector, edid);
 		}
 
@@ -2306,14 +2314,19 @@ intel_sdvo_guess_ddc_bus(struct intel_sdvo *sdvo)
 	switch (sdvo->controlled_output) {
 	case SDVO_OUTPUT_LVDS1:
 		mask |= SDVO_OUTPUT_LVDS1;
+		/* fall through */
 	case SDVO_OUTPUT_LVDS0:
 		mask |= SDVO_OUTPUT_LVDS0;
+		/* fall through */
 	case SDVO_OUTPUT_TMDS1:
 		mask |= SDVO_OUTPUT_TMDS1;
+		/* fall through */
 	case SDVO_OUTPUT_TMDS0:
 		mask |= SDVO_OUTPUT_TMDS0;
+		/* fall through */
 	case SDVO_OUTPUT_RGB1:
 		mask |= SDVO_OUTPUT_RGB1;
+		/* fall through */
 	case SDVO_OUTPUT_RGB0:
 		mask |= SDVO_OUTPUT_RGB0;
 		break;
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index ee23613f9fd4..f7026e887fa9 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -41,20 +41,6 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 
-bool intel_format_is_yuv(u32 format)
-{
-	switch (format) {
-	case DRM_FORMAT_YUYV:
-	case DRM_FORMAT_UYVY:
-	case DRM_FORMAT_VYUY:
-	case DRM_FORMAT_YVYU:
-	case DRM_FORMAT_NV12:
-		return true;
-	default:
-		return false;
-	}
-}
-
 int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
 			     int usecs)
 {
@@ -107,13 +93,21 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state)
 						      VBLANK_EVASION_TIME_US);
 	max = vblank_start - 1;
 
-	local_irq_disable();
-
 	if (min <= 0 || max <= 0)
-		return;
+		goto irq_disable;
 
 	if (WARN_ON(drm_crtc_vblank_get(&crtc->base)))
-		return;
+		goto irq_disable;
+
+	/*
+	 * Wait for psr to idle out after enabling the VBL interrupts
+	 * VBL interrupts will start the PSR exit and prevent a PSR
+	 * re-entry as well.
+	 */
+	if (intel_psr_wait_for_idle(new_crtc_state))
+		DRM_ERROR("PSR idle timed out, atomic update may fail\n");
+
+	local_irq_disable();
 
 	crtc->debug.min_vbl = min;
 	crtc->debug.max_vbl = max;
@@ -171,6 +165,10 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state)
 	crtc->debug.start_vbl_count = intel_crtc_get_vblank_counter(crtc);
 
 	trace_i915_pipe_update_vblank_evaded(crtc);
+	return;
+
+irq_disable:
+	local_irq_disable();
 }
 
 /**
@@ -284,13 +282,35 @@ skl_update_plane(struct intel_plane *plane,
 	/* program plane scaler */
 	if (plane_state->scaler_id >= 0) {
 		int scaler_id = plane_state->scaler_id;
-		const struct intel_scaler *scaler;
+		const struct intel_scaler *scaler =
+			&crtc_state->scaler_state.scalers[scaler_id];
+		u16 y_hphase, uv_rgb_hphase;
+		u16 y_vphase, uv_rgb_vphase;
+
+		/* TODO: handle sub-pixel coordinates */
+		if (fb->format->format == DRM_FORMAT_NV12) {
+			y_hphase = skl_scaler_calc_phase(1, false);
+			y_vphase = skl_scaler_calc_phase(1, false);
+
+			/* MPEG2 chroma siting convention */
+			uv_rgb_hphase = skl_scaler_calc_phase(2, true);
+			uv_rgb_vphase = skl_scaler_calc_phase(2, false);
+		} else {
+			/* not used */
+			y_hphase = 0;
+			y_vphase = 0;
 
-		scaler = &crtc_state->scaler_state.scalers[scaler_id];
+			uv_rgb_hphase = skl_scaler_calc_phase(1, false);
+			uv_rgb_vphase = skl_scaler_calc_phase(1, false);
+		}
 
 		I915_WRITE_FW(SKL_PS_CTRL(pipe, scaler_id),
 			      PS_SCALER_EN | PS_PLANE_SEL(plane_id) | scaler->mode);
 		I915_WRITE_FW(SKL_PS_PWR_GATE(pipe, scaler_id), 0);
+		I915_WRITE_FW(SKL_PS_VPHASE(pipe, scaler_id),
+			      PS_Y_PHASE(y_vphase) | PS_UV_RGB_PHASE(uv_rgb_vphase));
+		I915_WRITE_FW(SKL_PS_HPHASE(pipe, scaler_id),
+			      PS_Y_PHASE(y_hphase) | PS_UV_RGB_PHASE(uv_rgb_hphase));
 		I915_WRITE_FW(SKL_PS_WIN_POS(pipe, scaler_id), (crtc_x << 16) | crtc_y);
 		I915_WRITE_FW(SKL_PS_WIN_SZ(pipe, scaler_id),
 			      ((crtc_w + 1) << 16)|(crtc_h + 1));
@@ -327,19 +347,21 @@ skl_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc)
 }
 
 bool
-skl_plane_get_hw_state(struct intel_plane *plane)
+skl_plane_get_hw_state(struct intel_plane *plane,
+		       enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
 	enum plane_id plane_id = plane->id;
-	enum pipe pipe = plane->pipe;
 	bool ret;
 
-	power_domain = POWER_DOMAIN_PIPE(pipe);
+	power_domain = POWER_DOMAIN_PIPE(plane->pipe);
 	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
-	ret = I915_READ(PLANE_CTL(pipe, plane_id)) & PLANE_CTL_ENABLE;
+	ret = I915_READ(PLANE_CTL(plane->pipe, plane_id)) & PLANE_CTL_ENABLE;
+
+	*pipe = plane->pipe;
 
 	intel_display_power_put(dev_priv, power_domain);
 
@@ -380,7 +402,7 @@ chv_update_csc(const struct intel_plane_state *plane_state)
 	const s16 *csc = csc_matrix[plane_state->base.color_encoding];
 
 	/* Seems RGB data bypasses the CSC always */
-	if (!intel_format_is_yuv(fb->format->format))
+	if (!fb->format->is_yuv)
 		return;
 
 	I915_WRITE_FW(SPCSCYGOFF(plane_id), SPCSC_OOFF(0) | SPCSC_IOFF(0));
@@ -415,7 +437,7 @@ vlv_update_clrc(const struct intel_plane_state *plane_state)
 	enum plane_id plane_id = plane->id;
 	int contrast, brightness, sh_scale, sh_sin, sh_cos;
 
-	if (intel_format_is_yuv(fb->format->format) &&
+	if (fb->format->is_yuv &&
 	    plane_state->base.color_range == DRM_COLOR_YCBCR_LIMITED_RANGE) {
 		/*
 		 * Expand limited range to full range:
@@ -588,19 +610,21 @@ vlv_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc)
 }
 
 static bool
-vlv_plane_get_hw_state(struct intel_plane *plane)
+vlv_plane_get_hw_state(struct intel_plane *plane,
+		       enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
 	enum plane_id plane_id = plane->id;
-	enum pipe pipe = plane->pipe;
 	bool ret;
 
-	power_domain = POWER_DOMAIN_PIPE(pipe);
+	power_domain = POWER_DOMAIN_PIPE(plane->pipe);
 	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
-	ret = I915_READ(SPCNTR(pipe, plane_id)) & SP_ENABLE;
+	ret = I915_READ(SPCNTR(plane->pipe, plane_id)) & SP_ENABLE;
+
+	*pipe = plane->pipe;
 
 	intel_display_power_put(dev_priv, power_domain);
 
@@ -754,18 +778,20 @@ ivb_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc)
 }
 
 static bool
-ivb_plane_get_hw_state(struct intel_plane *plane)
+ivb_plane_get_hw_state(struct intel_plane *plane,
+		       enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
-	enum pipe pipe = plane->pipe;
 	bool ret;
 
-	power_domain = POWER_DOMAIN_PIPE(pipe);
+	power_domain = POWER_DOMAIN_PIPE(plane->pipe);
 	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
-	ret =  I915_READ(SPRCTL(pipe)) & SPRITE_ENABLE;
+	ret =  I915_READ(SPRCTL(plane->pipe)) & SPRITE_ENABLE;
+
+	*pipe = plane->pipe;
 
 	intel_display_power_put(dev_priv, power_domain);
 
@@ -910,18 +936,20 @@ g4x_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc)
 }
 
 static bool
-g4x_plane_get_hw_state(struct intel_plane *plane)
+g4x_plane_get_hw_state(struct intel_plane *plane,
+		       enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
-	enum pipe pipe = plane->pipe;
 	bool ret;
 
-	power_domain = POWER_DOMAIN_PIPE(pipe);
+	power_domain = POWER_DOMAIN_PIPE(plane->pipe);
 	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
-	ret = I915_READ(DVSCNTR(pipe)) & DVS_ENABLE;
+	ret = I915_READ(DVSCNTR(plane->pipe)) & DVS_ENABLE;
+
+	*pipe = plane->pipe;
 
 	intel_display_power_put(dev_priv, power_domain);
 
@@ -1010,7 +1038,7 @@ intel_check_sprite_plane(struct intel_plane *plane,
 		src->y1 = src_y << 16;
 		src->y2 = (src_y + src_h) << 16;
 
-		if (intel_format_is_yuv(fb->format->format) &&
+		if (fb->format->is_yuv &&
     		    fb->format->format != DRM_FORMAT_NV12 &&
 		    (src_x % 2 || src_w % 2)) {
 			DRM_DEBUG_KMS("src x/w (%u, %u) must be a multiple of 2 for YUV planes\n",
@@ -1071,6 +1099,37 @@ intel_check_sprite_plane(struct intel_plane *plane,
 	return 0;
 }
 
+static bool has_dst_key_in_primary_plane(struct drm_i915_private *dev_priv)
+{
+	return INTEL_GEN(dev_priv) >= 9;
+}
+
+static void intel_plane_set_ckey(struct intel_plane_state *plane_state,
+				 const struct drm_intel_sprite_colorkey *set)
+{
+	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
+	struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
+
+	*key = *set;
+
+	/*
+	 * We want src key enabled on the
+	 * sprite and not on the primary.
+	 */
+	if (plane->id == PLANE_PRIMARY &&
+	    set->flags & I915_SET_COLORKEY_SOURCE)
+		key->flags = 0;
+
+	/*
+	 * On SKL+ we want dst key enabled on
+	 * the primary and not on the sprite.
+	 */
+	if (INTEL_GEN(dev_priv) >= 9 && plane->id != PLANE_PRIMARY &&
+	    set->flags & I915_SET_COLORKEY_DESTINATION)
+		key->flags = 0;
+}
+
 int intel_sprite_set_colorkey_ioctl(struct drm_device *dev, void *data,
 				    struct drm_file *file_priv)
 {
@@ -1100,6 +1159,16 @@ int intel_sprite_set_colorkey_ioctl(struct drm_device *dev, void *data,
 	if (!plane || plane->type != DRM_PLANE_TYPE_OVERLAY)
 		return -ENOENT;
 
+	/*
+	 * SKL+ only plane 2 can do destination keying against plane 1.
+	 * Also multiple planes can't do destination keying on the same
+	 * pipe simultaneously.
+	 */
+	if (INTEL_GEN(dev_priv) >= 9 &&
+	    to_intel_plane(plane)->id >= PLANE_SPRITE1 &&
+	    set->flags & I915_SET_COLORKEY_DESTINATION)
+		return -EINVAL;
+
 	drm_modeset_acquire_init(&ctx, 0);
 
 	state = drm_atomic_state_alloc(plane->dev);
@@ -1112,11 +1181,28 @@ int intel_sprite_set_colorkey_ioctl(struct drm_device *dev, void *data,
 	while (1) {
 		plane_state = drm_atomic_get_plane_state(state, plane);
 		ret = PTR_ERR_OR_ZERO(plane_state);
-		if (!ret) {
-			to_intel_plane_state(plane_state)->ckey = *set;
-			ret = drm_atomic_commit(state);
+		if (!ret)
+			intel_plane_set_ckey(to_intel_plane_state(plane_state), set);
+
+		/*
+		 * On some platforms we have to configure
+		 * the dst colorkey on the primary plane.
+		 */
+		if (!ret && has_dst_key_in_primary_plane(dev_priv)) {
+			struct intel_crtc *crtc =
+				intel_get_crtc_for_pipe(dev_priv,
+							to_intel_plane(plane)->pipe);
+
+			plane_state = drm_atomic_get_plane_state(state,
+								 crtc->base.primary);
+			ret = PTR_ERR_OR_ZERO(plane_state);
+			if (!ret)
+				intel_plane_set_ckey(to_intel_plane_state(plane_state), set);
 		}
 
+		if (!ret)
+			ret = drm_atomic_commit(state);
+
 		if (ret != -EDEADLK)
 			break;
 
@@ -1211,8 +1297,17 @@ static const uint64_t skl_plane_format_modifiers_ccs[] = {
 	DRM_FORMAT_MOD_INVALID
 };
 
-static bool g4x_mod_supported(uint32_t format, uint64_t modifier)
+static bool g4x_sprite_format_mod_supported(struct drm_plane *_plane,
+					    u32 format, u64 modifier)
 {
+	switch (modifier) {
+	case DRM_FORMAT_MOD_LINEAR:
+	case I915_FORMAT_MOD_X_TILED:
+		break;
+	default:
+		return false;
+	}
+
 	switch (format) {
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_YUYV:
@@ -1228,8 +1323,17 @@ static bool g4x_mod_supported(uint32_t format, uint64_t modifier)
 	}
 }
 
-static bool snb_mod_supported(uint32_t format, uint64_t modifier)
+static bool snb_sprite_format_mod_supported(struct drm_plane *_plane,
+					    u32 format, u64 modifier)
 {
+	switch (modifier) {
+	case DRM_FORMAT_MOD_LINEAR:
+	case I915_FORMAT_MOD_X_TILED:
+		break;
+	default:
+		return false;
+	}
+
 	switch (format) {
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_XBGR8888:
@@ -1246,8 +1350,17 @@ static bool snb_mod_supported(uint32_t format, uint64_t modifier)
 	}
 }
 
-static bool vlv_mod_supported(uint32_t format, uint64_t modifier)
+static bool vlv_sprite_format_mod_supported(struct drm_plane *_plane,
+					    u32 format, u64 modifier)
 {
+	switch (modifier) {
+	case DRM_FORMAT_MOD_LINEAR:
+	case I915_FORMAT_MOD_X_TILED:
+		break;
+	default:
+		return false;
+	}
+
 	switch (format) {
 	case DRM_FORMAT_RGB565:
 	case DRM_FORMAT_ABGR8888:
@@ -1269,8 +1382,26 @@ static bool vlv_mod_supported(uint32_t format, uint64_t modifier)
 	}
 }
 
-static bool skl_mod_supported(uint32_t format, uint64_t modifier)
+static bool skl_plane_format_mod_supported(struct drm_plane *_plane,
+					   u32 format, u64 modifier)
 {
+	struct intel_plane *plane = to_intel_plane(_plane);
+
+	switch (modifier) {
+	case DRM_FORMAT_MOD_LINEAR:
+	case I915_FORMAT_MOD_X_TILED:
+	case I915_FORMAT_MOD_Y_TILED:
+	case I915_FORMAT_MOD_Yf_TILED:
+		break;
+	case I915_FORMAT_MOD_Y_TILED_CCS:
+	case I915_FORMAT_MOD_Yf_TILED_CCS:
+		if (!plane->has_ccs)
+			return false;
+		break;
+	default:
+		return false;
+	}
+
 	switch (format) {
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_XBGR8888:
@@ -1302,38 +1433,48 @@ static bool skl_mod_supported(uint32_t format, uint64_t modifier)
 	}
 }
 
-static bool intel_sprite_plane_format_mod_supported(struct drm_plane *plane,
-                                                    uint32_t format,
-                                                    uint64_t modifier)
-{
-	struct drm_i915_private *dev_priv = to_i915(plane->dev);
-
-	if (WARN_ON(modifier == DRM_FORMAT_MOD_INVALID))
-		return false;
+static const struct drm_plane_funcs g4x_sprite_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = intel_plane_destroy,
+	.atomic_get_property = intel_plane_atomic_get_property,
+	.atomic_set_property = intel_plane_atomic_set_property,
+	.atomic_duplicate_state = intel_plane_duplicate_state,
+	.atomic_destroy_state = intel_plane_destroy_state,
+	.format_mod_supported = g4x_sprite_format_mod_supported,
+};
 
-	if ((modifier >> 56) != DRM_FORMAT_MOD_VENDOR_INTEL &&
-	    modifier != DRM_FORMAT_MOD_LINEAR)
-		return false;
+static const struct drm_plane_funcs snb_sprite_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = intel_plane_destroy,
+	.atomic_get_property = intel_plane_atomic_get_property,
+	.atomic_set_property = intel_plane_atomic_set_property,
+	.atomic_duplicate_state = intel_plane_duplicate_state,
+	.atomic_destroy_state = intel_plane_destroy_state,
+	.format_mod_supported = snb_sprite_format_mod_supported,
+};
 
-	if (INTEL_GEN(dev_priv) >= 9)
-		return skl_mod_supported(format, modifier);
-	else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		return vlv_mod_supported(format, modifier);
-	else if (INTEL_GEN(dev_priv) >= 6)
-		return snb_mod_supported(format, modifier);
-	else
-		return g4x_mod_supported(format, modifier);
-}
+static const struct drm_plane_funcs vlv_sprite_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = intel_plane_destroy,
+	.atomic_get_property = intel_plane_atomic_get_property,
+	.atomic_set_property = intel_plane_atomic_set_property,
+	.atomic_duplicate_state = intel_plane_duplicate_state,
+	.atomic_destroy_state = intel_plane_destroy_state,
+	.format_mod_supported = vlv_sprite_format_mod_supported,
+};
 
-static const struct drm_plane_funcs intel_sprite_plane_funcs = {
-        .update_plane = drm_atomic_helper_update_plane,
-        .disable_plane = drm_atomic_helper_disable_plane,
-        .destroy = intel_plane_destroy,
-        .atomic_get_property = intel_plane_atomic_get_property,
-        .atomic_set_property = intel_plane_atomic_set_property,
-        .atomic_duplicate_state = intel_plane_duplicate_state,
-        .atomic_destroy_state = intel_plane_destroy_state,
-        .format_mod_supported = intel_sprite_plane_format_mod_supported,
+static const struct drm_plane_funcs skl_plane_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = intel_plane_destroy,
+	.atomic_get_property = intel_plane_atomic_get_property,
+	.atomic_set_property = intel_plane_atomic_set_property,
+	.atomic_duplicate_state = intel_plane_duplicate_state,
+	.atomic_destroy_state = intel_plane_destroy_state,
+	.format_mod_supported = skl_plane_format_mod_supported,
 };
 
 bool skl_plane_has_ccs(struct drm_i915_private *dev_priv,
@@ -1359,6 +1500,7 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 {
 	struct intel_plane *intel_plane = NULL;
 	struct intel_plane_state *state = NULL;
+	const struct drm_plane_funcs *plane_funcs;
 	unsigned long possible_crtcs;
 	const uint32_t *plane_formats;
 	const uint64_t *modifiers;
@@ -1383,6 +1525,9 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 		intel_plane->can_scale = true;
 		state->scaler_id = -1;
 
+		intel_plane->has_ccs = skl_plane_has_ccs(dev_priv, pipe,
+							 PLANE_SPRITE0 + plane);
+
 		intel_plane->update_plane = skl_update_plane;
 		intel_plane->disable_plane = skl_disable_plane;
 		intel_plane->get_hw_state = skl_plane_get_hw_state;
@@ -1396,10 +1541,12 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 			num_plane_formats = ARRAY_SIZE(skl_plane_formats);
 		}
 
-		if (skl_plane_has_ccs(dev_priv, pipe, PLANE_SPRITE0 + plane))
+		if (intel_plane->has_ccs)
 			modifiers = skl_plane_format_modifiers_ccs;
 		else
 			modifiers = skl_plane_format_modifiers_noccs;
+
+		plane_funcs = &skl_plane_funcs;
 	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		intel_plane->can_scale = false;
 		intel_plane->max_downscale = 1;
@@ -1411,6 +1558,8 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 		plane_formats = vlv_plane_formats;
 		num_plane_formats = ARRAY_SIZE(vlv_plane_formats);
 		modifiers = i9xx_plane_format_modifiers;
+
+		plane_funcs = &vlv_sprite_funcs;
 	} else if (INTEL_GEN(dev_priv) >= 7) {
 		if (IS_IVYBRIDGE(dev_priv)) {
 			intel_plane->can_scale = true;
@@ -1427,6 +1576,8 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 		plane_formats = snb_plane_formats;
 		num_plane_formats = ARRAY_SIZE(snb_plane_formats);
 		modifiers = i9xx_plane_format_modifiers;
+
+		plane_funcs = &snb_sprite_funcs;
 	} else {
 		intel_plane->can_scale = true;
 		intel_plane->max_downscale = 16;
@@ -1439,9 +1590,13 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 		if (IS_GEN6(dev_priv)) {
 			plane_formats = snb_plane_formats;
 			num_plane_formats = ARRAY_SIZE(snb_plane_formats);
+
+			plane_funcs = &snb_sprite_funcs;
 		} else {
 			plane_formats = g4x_plane_formats;
 			num_plane_formats = ARRAY_SIZE(g4x_plane_formats);
+
+			plane_funcs = &g4x_sprite_funcs;
 		}
 	}
 
@@ -1468,14 +1623,14 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 
 	if (INTEL_GEN(dev_priv) >= 9)
 		ret = drm_universal_plane_init(&dev_priv->drm, &intel_plane->base,
-					       possible_crtcs, &intel_sprite_plane_funcs,
+					       possible_crtcs, plane_funcs,
 					       plane_formats, num_plane_formats,
 					       modifiers,
 					       DRM_PLANE_TYPE_OVERLAY,
 					       "plane %d%c", plane + 2, pipe_name(pipe));
 	else
 		ret = drm_universal_plane_init(&dev_priv->drm, &intel_plane->base,
-					       possible_crtcs, &intel_sprite_plane_funcs,
+					       possible_crtcs, plane_funcs,
 					       plane_formats, num_plane_formats,
 					       modifiers,
 					       DRM_PLANE_TYPE_OVERLAY,
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index b55b5c157e38..b5b04cb892e9 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -798,16 +798,12 @@ static struct intel_tv *intel_attached_tv(struct drm_connector *connector)
 static bool
 intel_tv_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe)
 {
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	u32 tmp = I915_READ(TV_CTL);
 
-	if (!(tmp & TV_ENC_ENABLE))
-		return false;
+	*pipe = (tmp & TV_ENC_PIPE_SEL_MASK) >> TV_ENC_PIPE_SEL_SHIFT;
 
-	*pipe = PORT_TO_PIPE(tmp);
-
-	return true;
+	return tmp & TV_ENC_ENABLE;
 }
 
 static void
@@ -1032,8 +1028,7 @@ static void intel_tv_pre_enable(struct intel_encoder *encoder,
 		break;
 	}
 
-	if (intel_crtc->pipe == 1)
-		tv_ctl |= TV_ENC_PIPEB_SELECT;
+	tv_ctl |= TV_ENC_PIPE_SEL(intel_crtc->pipe);
 	tv_ctl |= tv_mode->oversample;
 
 	if (tv_mode->progressive)
@@ -1157,12 +1152,9 @@ intel_tv_detect_type(struct intel_tv *intel_tv,
 	save_tv_ctl = tv_ctl = I915_READ(TV_CTL);
 
 	/* Poll for TV detection */
-	tv_ctl &= ~(TV_ENC_ENABLE | TV_TEST_MODE_MASK);
+	tv_ctl &= ~(TV_ENC_ENABLE | TV_ENC_PIPE_SEL_MASK | TV_TEST_MODE_MASK);
 	tv_ctl |= TV_TEST_MODE_MONITOR_DETECT;
-	if (intel_crtc->pipe == 1)
-		tv_ctl |= TV_ENC_PIPEB_SELECT;
-	else
-		tv_ctl &= ~TV_ENC_PIPEB_SELECT;
+	tv_ctl |= TV_ENC_PIPE_SEL(intel_crtc->pipe);
 
 	tv_dac &= ~(TVDAC_SENSE_MASK | DAC_A_MASK | DAC_B_MASK | DAC_C_MASK);
 	tv_dac |= (TVDAC_STATE_CHG_EN |
@@ -1355,8 +1347,7 @@ intel_tv_get_modes(struct drm_connector *connector)
 		mode_ptr = drm_mode_create(connector->dev);
 		if (!mode_ptr)
 			continue;
-		strncpy(mode_ptr->name, input->name, DRM_DISPLAY_MODE_LEN);
-		mode_ptr->name[DRM_DISPLAY_MODE_LEN - 1] = '\0';
+		strlcpy(mode_ptr->name, input->name, DRM_DISPLAY_MODE_LEN);
 
 		mode_ptr->hdisplay = hactive_s;
 		mode_ptr->hsync_start = hactive_s + 1;
diff --git a/drivers/gpu/drm/i915/intel_uc.c b/drivers/gpu/drm/i915/intel_uc.c
index 1cffaf7b5dbe..7c95697e1a35 100644
--- a/drivers/gpu/drm/i915/intel_uc.c
+++ b/drivers/gpu/drm/i915/intel_uc.c
@@ -50,10 +50,10 @@ static int __intel_uc_reset_hw(struct drm_i915_private *dev_priv)
 	return ret;
 }
 
-static int __get_platform_enable_guc(struct drm_i915_private *dev_priv)
+static int __get_platform_enable_guc(struct drm_i915_private *i915)
 {
-	struct intel_uc_fw *guc_fw = &dev_priv->guc.fw;
-	struct intel_uc_fw *huc_fw = &dev_priv->huc.fw;
+	struct intel_uc_fw *guc_fw = &i915->guc.fw;
+	struct intel_uc_fw *huc_fw = &i915->huc.fw;
 	int enable_guc = 0;
 
 	/* Default is to enable GuC/HuC if we know their firmwares */
@@ -67,11 +67,11 @@ static int __get_platform_enable_guc(struct drm_i915_private *dev_priv)
 	return enable_guc;
 }
 
-static int __get_default_guc_log_level(struct drm_i915_private *dev_priv)
+static int __get_default_guc_log_level(struct drm_i915_private *i915)
 {
 	int guc_log_level;
 
-	if (!HAS_GUC(dev_priv) || !intel_uc_is_using_guc())
+	if (!HAS_GUC(i915) || !intel_uc_is_using_guc())
 		guc_log_level = GUC_LOG_LEVEL_DISABLED;
 	else if (IS_ENABLED(CONFIG_DRM_I915_DEBUG) ||
 		 IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
@@ -86,7 +86,7 @@ static int __get_default_guc_log_level(struct drm_i915_private *dev_priv)
 
 /**
  * sanitize_options_early - sanitize uC related modparam options
- * @dev_priv: device private
+ * @i915: device private
  *
  * In case of "enable_guc" option this function will attempt to modify
  * it only if it was initially set to "auto(-1)". Default value for this
@@ -101,14 +101,14 @@ static int __get_default_guc_log_level(struct drm_i915_private *dev_priv)
  * unless GuC is enabled on given platform and the driver is compiled with
  * debug config when this modparam will default to "enable(1..4)".
  */
-static void sanitize_options_early(struct drm_i915_private *dev_priv)
+static void sanitize_options_early(struct drm_i915_private *i915)
 {
-	struct intel_uc_fw *guc_fw = &dev_priv->guc.fw;
-	struct intel_uc_fw *huc_fw = &dev_priv->huc.fw;
+	struct intel_uc_fw *guc_fw = &i915->guc.fw;
+	struct intel_uc_fw *huc_fw = &i915->huc.fw;
 
 	/* A negative value means "use platform default" */
 	if (i915_modparams.enable_guc < 0)
-		i915_modparams.enable_guc = __get_platform_enable_guc(dev_priv);
+		i915_modparams.enable_guc = __get_platform_enable_guc(i915);
 
 	DRM_DEBUG_DRIVER("enable_guc=%d (submission:%s huc:%s)\n",
 			 i915_modparams.enable_guc,
@@ -119,28 +119,28 @@ static void sanitize_options_early(struct drm_i915_private *dev_priv)
 	if (intel_uc_is_using_guc() && !intel_uc_fw_is_selected(guc_fw)) {
 		DRM_WARN("Incompatible option detected: %s=%d, %s!\n",
 			 "enable_guc", i915_modparams.enable_guc,
-			 !HAS_GUC(dev_priv) ? "no GuC hardware" :
-					      "no GuC firmware");
+			 !HAS_GUC(i915) ? "no GuC hardware" :
+					  "no GuC firmware");
 	}
 
 	/* Verify HuC firmware availability */
 	if (intel_uc_is_using_huc() && !intel_uc_fw_is_selected(huc_fw)) {
 		DRM_WARN("Incompatible option detected: %s=%d, %s!\n",
 			 "enable_guc", i915_modparams.enable_guc,
-			 !HAS_HUC(dev_priv) ? "no HuC hardware" :
-					      "no HuC firmware");
+			 !HAS_HUC(i915) ? "no HuC hardware" :
+					  "no HuC firmware");
 	}
 
 	/* A negative value means "use platform/config default" */
 	if (i915_modparams.guc_log_level < 0)
 		i915_modparams.guc_log_level =
-			__get_default_guc_log_level(dev_priv);
+			__get_default_guc_log_level(i915);
 
 	if (i915_modparams.guc_log_level > 0 && !intel_uc_is_using_guc()) {
 		DRM_WARN("Incompatible option detected: %s=%d, %s!\n",
 			 "guc_log_level", i915_modparams.guc_log_level,
-			 !HAS_GUC(dev_priv) ? "no GuC hardware" :
-					      "GuC not enabled");
+			 !HAS_GUC(i915) ? "no GuC hardware" :
+					  "GuC not enabled");
 		i915_modparams.guc_log_level = 0;
 	}
 
@@ -171,44 +171,30 @@ void intel_uc_init_early(struct drm_i915_private *i915)
 	intel_huc_init_early(huc);
 
 	sanitize_options_early(i915);
-
-	if (USES_GUC(i915))
-		intel_uc_fw_fetch(i915, &guc->fw);
-
-	if (USES_HUC(i915))
-		intel_uc_fw_fetch(i915, &huc->fw);
 }
 
 void intel_uc_cleanup_early(struct drm_i915_private *i915)
 {
 	struct intel_guc *guc = &i915->guc;
-	struct intel_huc *huc = &i915->huc;
-
-	if (USES_HUC(i915))
-		intel_uc_fw_fini(&huc->fw);
-
-	if (USES_GUC(i915))
-		intel_uc_fw_fini(&guc->fw);
 
 	guc_free_load_err_log(guc);
 }
 
 /**
  * intel_uc_init_mmio - setup uC MMIO access
- *
- * @dev_priv: device private
+ * @i915: device private
  *
  * Setup minimal state necessary for MMIO accesses later in the
  * initialization sequence.
  */
-void intel_uc_init_mmio(struct drm_i915_private *dev_priv)
+void intel_uc_init_mmio(struct drm_i915_private *i915)
 {
-	intel_guc_init_send_regs(&dev_priv->guc);
+	intel_guc_init_send_regs(&i915->guc);
 }
 
 static void guc_capture_load_err_log(struct intel_guc *guc)
 {
-	if (!guc->log.vma || !i915_modparams.guc_log_level)
+	if (!guc->log.vma || !intel_guc_log_get_level(&guc->log))
 		return;
 
 	if (!guc->load_err_log)
@@ -225,11 +211,11 @@ static void guc_free_load_err_log(struct intel_guc *guc)
 
 static int guc_enable_communication(struct intel_guc *guc)
 {
-	struct drm_i915_private *dev_priv = guc_to_i915(guc);
+	struct drm_i915_private *i915 = guc_to_i915(guc);
 
-	gen9_enable_guc_interrupts(dev_priv);
+	gen9_enable_guc_interrupts(i915);
 
-	if (HAS_GUC_CT(dev_priv))
+	if (HAS_GUC_CT(i915))
 		return intel_guc_ct_enable(&guc->ct);
 
 	guc->send = intel_guc_send_mmio;
@@ -239,60 +225,73 @@ static int guc_enable_communication(struct intel_guc *guc)
 
 static void guc_disable_communication(struct intel_guc *guc)
 {
-	struct drm_i915_private *dev_priv = guc_to_i915(guc);
+	struct drm_i915_private *i915 = guc_to_i915(guc);
 
-	if (HAS_GUC_CT(dev_priv))
+	if (HAS_GUC_CT(i915))
 		intel_guc_ct_disable(&guc->ct);
 
-	gen9_disable_guc_interrupts(dev_priv);
+	gen9_disable_guc_interrupts(i915);
 
 	guc->send = intel_guc_send_nop;
 	guc->handler = intel_guc_to_host_event_handler_nop;
 }
 
-int intel_uc_init_misc(struct drm_i915_private *dev_priv)
+int intel_uc_init_misc(struct drm_i915_private *i915)
 {
-	struct intel_guc *guc = &dev_priv->guc;
+	struct intel_guc *guc = &i915->guc;
+	struct intel_huc *huc = &i915->huc;
 	int ret;
 
-	if (!USES_GUC(dev_priv))
+	if (!USES_GUC(i915))
 		return 0;
 
-	intel_guc_init_ggtt_pin_bias(guc);
-
-	ret = intel_guc_init_wq(guc);
+	ret = intel_guc_init_misc(guc);
 	if (ret)
 		return ret;
 
+	if (USES_HUC(i915)) {
+		ret = intel_huc_init_misc(huc);
+		if (ret)
+			goto err_guc;
+	}
+
 	return 0;
+
+err_guc:
+	intel_guc_fini_misc(guc);
+	return ret;
 }
 
-void intel_uc_fini_misc(struct drm_i915_private *dev_priv)
+void intel_uc_fini_misc(struct drm_i915_private *i915)
 {
-	struct intel_guc *guc = &dev_priv->guc;
+	struct intel_guc *guc = &i915->guc;
+	struct intel_huc *huc = &i915->huc;
 
-	if (!USES_GUC(dev_priv))
+	if (!USES_GUC(i915))
 		return;
 
-	intel_guc_fini_wq(guc);
+	if (USES_HUC(i915))
+		intel_huc_fini_misc(huc);
+
+	intel_guc_fini_misc(guc);
 }
 
-int intel_uc_init(struct drm_i915_private *dev_priv)
+int intel_uc_init(struct drm_i915_private *i915)
 {
-	struct intel_guc *guc = &dev_priv->guc;
+	struct intel_guc *guc = &i915->guc;
 	int ret;
 
-	if (!USES_GUC(dev_priv))
+	if (!USES_GUC(i915))
 		return 0;
 
-	if (!HAS_GUC(dev_priv))
+	if (!HAS_GUC(i915))
 		return -ENODEV;
 
 	ret = intel_guc_init(guc);
 	if (ret)
 		return ret;
 
-	if (USES_GUC_SUBMISSION(dev_priv)) {
+	if (USES_GUC_SUBMISSION(i915)) {
 		/*
 		 * This is stuff we need to have available at fw load time
 		 * if we are planning to enable submission later
@@ -307,16 +306,16 @@ int intel_uc_init(struct drm_i915_private *dev_priv)
 	return 0;
 }
 
-void intel_uc_fini(struct drm_i915_private *dev_priv)
+void intel_uc_fini(struct drm_i915_private *i915)
 {
-	struct intel_guc *guc = &dev_priv->guc;
+	struct intel_guc *guc = &i915->guc;
 
-	if (!USES_GUC(dev_priv))
+	if (!USES_GUC(i915))
 		return;
 
-	GEM_BUG_ON(!HAS_GUC(dev_priv));
+	GEM_BUG_ON(!HAS_GUC(i915));
 
-	if (USES_GUC_SUBMISSION(dev_priv))
+	if (USES_GUC_SUBMISSION(i915))
 		intel_guc_submission_fini(guc);
 
 	intel_guc_fini(guc);
@@ -340,22 +339,22 @@ void intel_uc_sanitize(struct drm_i915_private *i915)
 	__intel_uc_reset_hw(i915);
 }
 
-int intel_uc_init_hw(struct drm_i915_private *dev_priv)
+int intel_uc_init_hw(struct drm_i915_private *i915)
 {
-	struct intel_guc *guc = &dev_priv->guc;
-	struct intel_huc *huc = &dev_priv->huc;
+	struct intel_guc *guc = &i915->guc;
+	struct intel_huc *huc = &i915->huc;
 	int ret, attempts;
 
-	if (!USES_GUC(dev_priv))
+	if (!USES_GUC(i915))
 		return 0;
 
-	GEM_BUG_ON(!HAS_GUC(dev_priv));
+	GEM_BUG_ON(!HAS_GUC(i915));
 
-	gen9_reset_guc_interrupts(dev_priv);
+	gen9_reset_guc_interrupts(i915);
 
 	/* WaEnableuKernelHeaderValidFix:skl */
 	/* WaEnableGuCBootHashCheckNotSet:skl,bxt,kbl */
-	if (IS_GEN9(dev_priv))
+	if (IS_GEN9(i915))
 		attempts = 3;
 	else
 		attempts = 1;
@@ -365,11 +364,11 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv)
 		 * Always reset the GuC just before (re)loading, so
 		 * that the state and timing are fairly predictable
 		 */
-		ret = __intel_uc_reset_hw(dev_priv);
+		ret = __intel_uc_reset_hw(i915);
 		if (ret)
 			goto err_out;
 
-		if (USES_HUC(dev_priv)) {
+		if (USES_HUC(i915)) {
 			ret = intel_huc_fw_upload(huc);
 			if (ret)
 				goto err_out;
@@ -392,24 +391,24 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv)
 	if (ret)
 		goto err_log_capture;
 
-	if (USES_HUC(dev_priv)) {
+	if (USES_HUC(i915)) {
 		ret = intel_huc_auth(huc);
 		if (ret)
 			goto err_communication;
 	}
 
-	if (USES_GUC_SUBMISSION(dev_priv)) {
+	if (USES_GUC_SUBMISSION(i915)) {
 		ret = intel_guc_submission_enable(guc);
 		if (ret)
 			goto err_communication;
 	}
 
-	dev_info(dev_priv->drm.dev, "GuC firmware version %u.%u\n",
+	dev_info(i915->drm.dev, "GuC firmware version %u.%u\n",
 		 guc->fw.major_ver_found, guc->fw.minor_ver_found);
-	dev_info(dev_priv->drm.dev, "GuC submission %s\n",
-		 enableddisabled(USES_GUC_SUBMISSION(dev_priv)));
-	dev_info(dev_priv->drm.dev, "HuC %s\n",
-		 enableddisabled(USES_HUC(dev_priv)));
+	dev_info(i915->drm.dev, "GuC submission %s\n",
+		 enableddisabled(USES_GUC_SUBMISSION(i915)));
+	dev_info(i915->drm.dev, "HuC %s\n",
+		 enableddisabled(USES_HUC(i915)));
 
 	return 0;
 
@@ -428,20 +427,20 @@ err_out:
 	if (GEM_WARN_ON(ret == -EIO))
 		ret = -EINVAL;
 
-	dev_err(dev_priv->drm.dev, "GuC initialization failed %d\n", ret);
+	dev_err(i915->drm.dev, "GuC initialization failed %d\n", ret);
 	return ret;
 }
 
-void intel_uc_fini_hw(struct drm_i915_private *dev_priv)
+void intel_uc_fini_hw(struct drm_i915_private *i915)
 {
-	struct intel_guc *guc = &dev_priv->guc;
+	struct intel_guc *guc = &i915->guc;
 
-	if (!USES_GUC(dev_priv))
+	if (!USES_GUC(i915))
 		return;
 
-	GEM_BUG_ON(!HAS_GUC(dev_priv));
+	GEM_BUG_ON(!HAS_GUC(i915));
 
-	if (USES_GUC_SUBMISSION(dev_priv))
+	if (USES_GUC_SUBMISSION(i915))
 		intel_guc_submission_disable(guc);
 
 	guc_disable_communication(guc);
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 448293eb638d..b892ca8396e8 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1702,15 +1702,9 @@ static void gen3_stop_engine(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
 	const u32 base = engine->mmio_base;
-	const i915_reg_t mode = RING_MI_MODE(base);
-
-	I915_WRITE_FW(mode, _MASKED_BIT_ENABLE(STOP_RING));
-	if (__intel_wait_for_register_fw(dev_priv,
-					 mode, MODE_IDLE, MODE_IDLE,
-					 500, 0,
-					 NULL))
-		DRM_DEBUG_DRIVER("%s: timed out on STOP_RING\n",
-				 engine->name);
+
+	if (intel_engine_stop_cs(engine))
+		DRM_DEBUG_DRIVER("%s: timed out on STOP_RING\n", engine->name);
 
 	I915_WRITE_FW(RING_HEAD(base), I915_READ_FW(RING_TAIL(base)));
 	POSTING_READ_FW(RING_HEAD(base)); /* paranoia */
@@ -2099,21 +2093,25 @@ static int gen8_reset_engines(struct drm_i915_private *dev_priv,
 {
 	struct intel_engine_cs *engine;
 	unsigned int tmp;
+	int ret;
 
-	for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
-		if (gen8_reset_engine_start(engine))
+	for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
+		if (gen8_reset_engine_start(engine)) {
+			ret = -EIO;
 			goto not_ready;
+		}
+	}
 
 	if (INTEL_GEN(dev_priv) >= 11)
-		return gen11_reset_engines(dev_priv, engine_mask);
+		ret = gen11_reset_engines(dev_priv, engine_mask);
 	else
-		return gen6_reset_engines(dev_priv, engine_mask);
+		ret = gen6_reset_engines(dev_priv, engine_mask);
 
 not_ready:
 	for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
 		gen8_reset_engine_cancel(engine);
 
-	return -EIO;
+	return ret;
 }
 
 typedef int (*reset_func)(struct drm_i915_private *, unsigned engine_mask);
@@ -2176,6 +2174,8 @@ int intel_gpu_reset(struct drm_i915_private *dev_priv, unsigned engine_mask)
 		 * Thus assume it is best to stop engines on all gens
 		 * where we have a gpu reset.
 		 *
+		 * WaKBLVECSSemaphoreWaitPoll:kbl (on ALL_ENGINES)
+		 *
 		 * WaMediaResetMainRingCleanup:ctg,elk (presumably)
 		 *
 		 * FIXME: Wa for more modern gens needs to be validated
diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h
index 47478d609630..2fbe93178fb2 100644
--- a/drivers/gpu/drm/i915/intel_uncore.h
+++ b/drivers/gpu/drm/i915/intel_uncore.h
@@ -67,21 +67,21 @@ struct intel_uncore_funcs {
 	void (*force_wake_put)(struct drm_i915_private *dev_priv,
 			       enum forcewake_domains domains);
 
-	uint8_t  (*mmio_readb)(struct drm_i915_private *dev_priv,
-			       i915_reg_t r, bool trace);
-	uint16_t (*mmio_readw)(struct drm_i915_private *dev_priv,
-			       i915_reg_t r, bool trace);
-	uint32_t (*mmio_readl)(struct drm_i915_private *dev_priv,
-			       i915_reg_t r, bool trace);
-	uint64_t (*mmio_readq)(struct drm_i915_private *dev_priv,
-			       i915_reg_t r, bool trace);
+	u8 (*mmio_readb)(struct drm_i915_private *dev_priv,
+			 i915_reg_t r, bool trace);
+	u16 (*mmio_readw)(struct drm_i915_private *dev_priv,
+			  i915_reg_t r, bool trace);
+	u32 (*mmio_readl)(struct drm_i915_private *dev_priv,
+			  i915_reg_t r, bool trace);
+	u64 (*mmio_readq)(struct drm_i915_private *dev_priv,
+			  i915_reg_t r, bool trace);
 
 	void (*mmio_writeb)(struct drm_i915_private *dev_priv,
-			    i915_reg_t r, uint8_t val, bool trace);
+			    i915_reg_t r, u8 val, bool trace);
 	void (*mmio_writew)(struct drm_i915_private *dev_priv,
-			    i915_reg_t r, uint16_t val, bool trace);
+			    i915_reg_t r, u16 val, bool trace);
 	void (*mmio_writel)(struct drm_i915_private *dev_priv,
-			    i915_reg_t r, uint32_t val, bool trace);
+			    i915_reg_t r, u32 val, bool trace);
 };
 
 struct intel_forcewake_range {
diff --git a/drivers/gpu/drm/i915/intel_vbt_defs.h b/drivers/gpu/drm/i915/intel_vbt_defs.h
index 458468237b5f..bba98cf83cbd 100644
--- a/drivers/gpu/drm/i915/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/intel_vbt_defs.h
@@ -318,6 +318,12 @@ enum vbt_gmbus_ddi {
 	DDC_BUS_DDI_C,
 	DDC_BUS_DDI_D,
 	DDC_BUS_DDI_F,
+	ICL_DDC_BUS_DDI_A = 0x1,
+	ICL_DDC_BUS_DDI_B,
+	ICL_DDC_BUS_PORT_1 = 0x4,
+	ICL_DDC_BUS_PORT_2,
+	ICL_DDC_BUS_PORT_3,
+	ICL_DDC_BUS_PORT_4,
 };
 
 #define VBT_DP_MAX_LINK_RATE_HBR3	0
@@ -414,7 +420,9 @@ struct child_device_config {
 	u16 extended_type;
 	u8 dvo_function;
 	u8 dp_usb_type_c:1;					/* 195 */
-	u8 flags2_reserved:7;					/* 195 */
+	u8 tbt:1;						/* 209 */
+	u8 flags2_reserved:2;					/* 195 */
+	u8 dp_port_trace_length:4;				/* 209 */
 	u8 dp_gpio_index;					/* 195 */
 	u16 dp_gpio_pin_num;					/* 195 */
 	u8 dp_iboost_level:4;					/* 196 */
@@ -448,7 +456,7 @@ struct bdb_general_definitions {
 	 * number = (block_size - sizeof(bdb_general_definitions))/
 	 *	     defs->child_dev_size;
 	 */
-	uint8_t devices[0];
+	u8 devices[0];
 } __packed;
 
 /* Mask for DRRS / Panel Channel / SSC / BLT control bits extraction */
@@ -635,7 +643,7 @@ struct bdb_sdvo_lvds_options {
 #define BDB_DRIVER_FEATURE_NO_LVDS		0
 #define BDB_DRIVER_FEATURE_INT_LVDS		1
 #define BDB_DRIVER_FEATURE_SDVO_LVDS		2
-#define BDB_DRIVER_FEATURE_EDP			3
+#define BDB_DRIVER_FEATURE_INT_SDVO_LVDS	3
 
 struct bdb_driver_features {
 	u8 boot_dev_algorithm:1;
diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
index 2df3538ceba5..4bcdeaf8d98f 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -48,29 +48,58 @@
  * - Public functions to init or apply the given workaround type.
  */
 
-static int wa_add(struct drm_i915_private *dev_priv,
-		  i915_reg_t addr,
-		  const u32 mask, const u32 val)
+static void wa_add(struct drm_i915_private *i915,
+		   i915_reg_t reg, const u32 mask, const u32 val)
 {
-	const unsigned int idx = dev_priv->workarounds.count;
+	struct i915_workarounds *wa = &i915->workarounds;
+	unsigned int start = 0, end = wa->count;
+	unsigned int addr = i915_mmio_reg_offset(reg);
+	struct i915_wa_reg *r;
+
+	while (start < end) {
+		unsigned int mid = start + (end - start) / 2;
+
+		if (wa->reg[mid].addr < addr) {
+			start = mid + 1;
+		} else if (wa->reg[mid].addr > addr) {
+			end = mid;
+		} else {
+			r = &wa->reg[mid];
+
+			if ((mask & ~r->mask) == 0) {
+				DRM_ERROR("Discarding overwritten w/a for reg %04x (mask: %08x, value: %08x)\n",
+					  addr, r->mask, r->value);
+
+				r->value &= ~mask;
+			}
+
+			r->value |= val;
+			r->mask  |= mask;
+			return;
+		}
+	}
 
-	if (WARN_ON(idx >= I915_MAX_WA_REGS))
-		return -ENOSPC;
+	if (WARN_ON_ONCE(wa->count >= I915_MAX_WA_REGS)) {
+		DRM_ERROR("Dropping w/a for reg %04x (mask: %08x, value: %08x)\n",
+			  addr, mask, val);
+		return;
+	}
 
-	dev_priv->workarounds.reg[idx].addr = addr;
-	dev_priv->workarounds.reg[idx].value = val;
-	dev_priv->workarounds.reg[idx].mask = mask;
+	r = &wa->reg[wa->count++];
+	r->addr  = addr;
+	r->value = val;
+	r->mask  = mask;
 
-	dev_priv->workarounds.count++;
+	while (r-- > wa->reg) {
+		GEM_BUG_ON(r[0].addr == r[1].addr);
+		if (r[1].addr > r[0].addr)
+			break;
 
-	return 0;
+		swap(r[1], r[0]);
+	}
 }
 
-#define WA_REG(addr, mask, val) do { \
-		const int r = wa_add(dev_priv, (addr), (mask), (val)); \
-		if (r) \
-			return r; \
-	} while (0)
+#define WA_REG(addr, mask, val) wa_add(dev_priv, (addr), (mask), (val))
 
 #define WA_SET_BIT_MASKED(addr, mask) \
 	WA_REG(addr, (mask), _MASKED_BIT_ENABLE(mask))
@@ -463,6 +492,22 @@ static int icl_ctx_workarounds_init(struct drm_i915_private *dev_priv)
 	 */
 	WA_SET_BIT_MASKED(ICL_HDC_MODE, HDC_FORCE_NON_COHERENT);
 
+	/* Wa_2006611047:icl (pre-prod)
+	 * Formerly known as WaDisableImprovedTdlClkGating
+	 */
+	if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_A0))
+		WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2,
+				  GEN11_TDL_CLOCK_GATING_FIX_DISABLE);
+
+	/* WaEnableStateCacheRedirectToCS:icl */
+	WA_SET_BIT_MASKED(GEN9_SLICE_COMMON_ECO_CHICKEN1,
+			  GEN11_STATE_CACHE_REDIRECT_TO_CS);
+
+	/* Wa_2006665173:icl (pre-prod) */
+	if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_A0))
+		WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3,
+				  GEN11_BLEND_EMB_FIX_DISABLE_IN_RCC);
+
 	return 0;
 }
 
@@ -521,7 +566,7 @@ int intel_ctx_workarounds_emit(struct i915_request *rq)
 
 	*cs++ = MI_LOAD_REGISTER_IMM(w->count);
 	for (i = 0; i < w->count; i++) {
-		*cs++ = i915_mmio_reg_offset(w->reg[i].addr);
+		*cs++ = w->reg[i].addr;
 		*cs++ = w->reg[i].value;
 	}
 	*cs++ = MI_NOOP;
@@ -647,6 +692,19 @@ static void kbl_gt_workarounds_apply(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA,
 		   I915_READ(GEN9_GAMT_ECO_REG_RW_IA) |
 		   GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
+
+	/* WaKBLVECSSemaphoreWaitPoll:kbl */
+	if (IS_KBL_REVID(dev_priv, KBL_REVID_A0, KBL_REVID_E0)) {
+		struct intel_engine_cs *engine;
+		unsigned int tmp;
+
+		for_each_engine(engine, dev_priv, tmp) {
+			if (engine->id == RCS)
+				continue;
+
+			I915_WRITE(RING_SEMA_WAIT_POLL(engine->mmio_base), 1);
+		}
+	}
 }
 
 static void glk_gt_workarounds_apply(struct drm_i915_private *dev_priv)
@@ -672,8 +730,74 @@ static void cfl_gt_workarounds_apply(struct drm_i915_private *dev_priv)
 		   GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
 }
 
+static void wa_init_mcr(struct drm_i915_private *dev_priv)
+{
+	const struct sseu_dev_info *sseu = &(INTEL_INFO(dev_priv)->sseu);
+	u32 mcr;
+	u32 mcr_slice_subslice_mask;
+
+	/*
+	 * WaProgramMgsrForL3BankSpecificMmioReads: cnl,icl
+	 * L3Banks could be fused off in single slice scenario. If that is
+	 * the case, we might need to program MCR select to a valid L3Bank
+	 * by default, to make sure we correctly read certain registers
+	 * later on (in the range 0xB100 - 0xB3FF).
+	 * This might be incompatible with
+	 * WaProgramMgsrForCorrectSliceSpecificMmioReads.
+	 * Fortunately, this should not happen in production hardware, so
+	 * we only assert that this is the case (instead of implementing
+	 * something more complex that requires checking the range of every
+	 * MMIO read).
+	 */
+	if (INTEL_GEN(dev_priv) >= 10 &&
+	    is_power_of_2(sseu->slice_mask)) {
+		/*
+		 * read FUSE3 for enabled L3 Bank IDs, if L3 Bank matches
+		 * enabled subslice, no need to redirect MCR packet
+		 */
+		u32 slice = fls(sseu->slice_mask);
+		u32 fuse3 = I915_READ(GEN10_MIRROR_FUSE3);
+		u8 ss_mask = sseu->subslice_mask[slice];
+
+		u8 enabled_mask = (ss_mask | ss_mask >>
+				   GEN10_L3BANK_PAIR_COUNT) & GEN10_L3BANK_MASK;
+		u8 disabled_mask = fuse3 & GEN10_L3BANK_MASK;
+
+		/*
+		 * Production silicon should have matched L3Bank and
+		 * subslice enabled
+		 */
+		WARN_ON((enabled_mask & disabled_mask) != enabled_mask);
+	}
+
+	mcr = I915_READ(GEN8_MCR_SELECTOR);
+
+	if (INTEL_GEN(dev_priv) >= 11)
+		mcr_slice_subslice_mask = GEN11_MCR_SLICE_MASK |
+					  GEN11_MCR_SUBSLICE_MASK;
+	else
+		mcr_slice_subslice_mask = GEN8_MCR_SLICE_MASK |
+					  GEN8_MCR_SUBSLICE_MASK;
+	/*
+	 * WaProgramMgsrForCorrectSliceSpecificMmioReads:cnl,icl
+	 * Before any MMIO read into slice/subslice specific registers, MCR
+	 * packet control register needs to be programmed to point to any
+	 * enabled s/ss pair. Otherwise, incorrect values will be returned.
+	 * This means each subsequent MMIO read will be forwarded to an
+	 * specific s/ss combination, but this is OK since these registers
+	 * are consistent across s/ss in almost all cases. In the rare
+	 * occasions, such as INSTDONE, where this value is dependent
+	 * on s/ss combo, the read should be done with read_subslice_reg.
+	 */
+	mcr &= ~mcr_slice_subslice_mask;
+	mcr |= intel_calculate_mcr_s_ss_select(dev_priv);
+	I915_WRITE(GEN8_MCR_SELECTOR, mcr);
+}
+
 static void cnl_gt_workarounds_apply(struct drm_i915_private *dev_priv)
 {
+	wa_init_mcr(dev_priv);
+
 	/* WaDisableI2mCycleOnWRPort:cnl (pre-prod) */
 	if (IS_CNL_REVID(dev_priv, CNL_REVID_B0, CNL_REVID_B0))
 		I915_WRITE(GAMT_CHKN_BIT_REG,
@@ -692,6 +816,8 @@ static void cnl_gt_workarounds_apply(struct drm_i915_private *dev_priv)
 
 static void icl_gt_workarounds_apply(struct drm_i915_private *dev_priv)
 {
+	wa_init_mcr(dev_priv);
+
 	/* This is not an Wa. Enable for better image quality */
 	I915_WRITE(_3D_CHICKEN3,
 		   _MASKED_BIT_ENABLE(_3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE));
@@ -772,6 +898,13 @@ static void icl_gt_workarounds_apply(struct drm_i915_private *dev_priv)
 		   PMFLUSHDONE_LNICRSDROP |
 		   PMFLUSH_GAPL3UNBLOCK |
 		   PMFLUSHDONE_LNEBLK);
+
+	/* Wa_1406463099:icl
+	 * Formerly known as WaGamTlbPendError
+	 */
+	I915_WRITE(GAMT_CHKN_BIT_REG,
+		   I915_READ(GAMT_CHKN_BIT_REG) |
+		   GAMT_CHKN_DISABLE_L3_COH_PIPE);
 }
 
 void intel_gt_workarounds_apply(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c
index 91c72911be3c..7efb326badcd 100644
--- a/drivers/gpu/drm/i915/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/selftests/huge_pages.c
@@ -338,7 +338,7 @@ fake_huge_pages_object(struct drm_i915_private *i915, u64 size, bool single)
 
 static int igt_check_page_sizes(struct i915_vma *vma)
 {
-	struct drm_i915_private *i915 = to_i915(vma->obj->base.dev);
+	struct drm_i915_private *i915 = vma->vm->i915;
 	unsigned int supported = INTEL_INFO(i915)->page_sizes;
 	struct drm_i915_gem_object *obj = vma->obj;
 	int err = 0;
@@ -379,7 +379,7 @@ static int igt_check_page_sizes(struct i915_vma *vma)
 static int igt_mock_exhaust_device_supported_pages(void *arg)
 {
 	struct i915_hw_ppgtt *ppgtt = arg;
-	struct drm_i915_private *i915 = ppgtt->base.i915;
+	struct drm_i915_private *i915 = ppgtt->vm.i915;
 	unsigned int saved_mask = INTEL_INFO(i915)->page_sizes;
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
@@ -415,7 +415,7 @@ static int igt_mock_exhaust_device_supported_pages(void *arg)
 				goto out_put;
 			}
 
-			vma = i915_vma_instance(obj, &ppgtt->base, NULL);
+			vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
 			if (IS_ERR(vma)) {
 				err = PTR_ERR(vma);
 				goto out_put;
@@ -458,7 +458,7 @@ out_device:
 static int igt_mock_ppgtt_misaligned_dma(void *arg)
 {
 	struct i915_hw_ppgtt *ppgtt = arg;
-	struct drm_i915_private *i915 = ppgtt->base.i915;
+	struct drm_i915_private *i915 = ppgtt->vm.i915;
 	unsigned long supported = INTEL_INFO(i915)->page_sizes;
 	struct drm_i915_gem_object *obj;
 	int bit;
@@ -500,7 +500,7 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg)
 		/* Force the page size for this object */
 		obj->mm.page_sizes.sg = page_size;
 
-		vma = i915_vma_instance(obj, &ppgtt->base, NULL);
+		vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto out_unpin;
@@ -570,6 +570,7 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg)
 		i915_vma_close(vma);
 
 		i915_gem_object_unpin_pages(obj);
+		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
 		i915_gem_object_put(obj);
 	}
 
@@ -591,12 +592,13 @@ static void close_object_list(struct list_head *objects,
 	list_for_each_entry_safe(obj, on, objects, st_link) {
 		struct i915_vma *vma;
 
-		vma = i915_vma_instance(obj, &ppgtt->base, NULL);
+		vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
 		if (!IS_ERR(vma))
 			i915_vma_close(vma);
 
 		list_del(&obj->st_link);
 		i915_gem_object_unpin_pages(obj);
+		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
 		i915_gem_object_put(obj);
 	}
 }
@@ -604,8 +606,8 @@ static void close_object_list(struct list_head *objects,
 static int igt_mock_ppgtt_huge_fill(void *arg)
 {
 	struct i915_hw_ppgtt *ppgtt = arg;
-	struct drm_i915_private *i915 = ppgtt->base.i915;
-	unsigned long max_pages = ppgtt->base.total >> PAGE_SHIFT;
+	struct drm_i915_private *i915 = ppgtt->vm.i915;
+	unsigned long max_pages = ppgtt->vm.total >> PAGE_SHIFT;
 	unsigned long page_num;
 	bool single = false;
 	LIST_HEAD(objects);
@@ -641,7 +643,7 @@ static int igt_mock_ppgtt_huge_fill(void *arg)
 
 		list_add(&obj->st_link, &objects);
 
-		vma = i915_vma_instance(obj, &ppgtt->base, NULL);
+		vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			break;
@@ -725,7 +727,7 @@ static int igt_mock_ppgtt_huge_fill(void *arg)
 static int igt_mock_ppgtt_64K(void *arg)
 {
 	struct i915_hw_ppgtt *ppgtt = arg;
-	struct drm_i915_private *i915 = ppgtt->base.i915;
+	struct drm_i915_private *i915 = ppgtt->vm.i915;
 	struct drm_i915_gem_object *obj;
 	const struct object_info {
 		unsigned int size;
@@ -819,7 +821,7 @@ static int igt_mock_ppgtt_64K(void *arg)
 			 */
 			obj->mm.page_sizes.sg &= ~I915_GTT_PAGE_SIZE_2M;
 
-			vma = i915_vma_instance(obj, &ppgtt->base, NULL);
+			vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
 			if (IS_ERR(vma)) {
 				err = PTR_ERR(vma);
 				goto out_object_unpin;
@@ -866,6 +868,7 @@ static int igt_mock_ppgtt_64K(void *arg)
 			i915_vma_close(vma);
 
 			i915_gem_object_unpin_pages(obj);
+			__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
 			i915_gem_object_put(obj);
 		}
 	}
@@ -887,8 +890,8 @@ out_object_put:
 static struct i915_vma *
 gpu_write_dw(struct i915_vma *vma, u64 offset, u32 val)
 {
-	struct drm_i915_private *i915 = to_i915(vma->obj->base.dev);
-	const int gen = INTEL_GEN(vma->vm->i915);
+	struct drm_i915_private *i915 = vma->vm->i915;
+	const int gen = INTEL_GEN(i915);
 	unsigned int count = vma->size >> PAGE_SHIFT;
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *batch;
@@ -919,12 +922,12 @@ gpu_write_dw(struct i915_vma *vma, u64 offset, u32 val)
 			*cmd++ = val;
 		} else if (gen >= 4) {
 			*cmd++ = MI_STORE_DWORD_IMM_GEN4 |
-				(gen < 6 ? 1 << 22 : 0);
+				(gen < 6 ? MI_USE_GGTT : 0);
 			*cmd++ = 0;
 			*cmd++ = offset;
 			*cmd++ = val;
 		} else {
-			*cmd++ = MI_STORE_DWORD_IMM | 1 << 22;
+			*cmd++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
 			*cmd++ = offset;
 			*cmd++ = val;
 		}
@@ -985,7 +988,10 @@ static int gpu_write(struct i915_vma *vma,
 		goto err_request;
 	}
 
-	i915_vma_move_to_active(batch, rq, 0);
+	err = i915_vma_move_to_active(batch, rq, 0);
+	if (err)
+		goto err_request;
+
 	i915_gem_object_set_active_reference(batch->obj);
 	i915_vma_unpin(batch);
 	i915_vma_close(batch);
@@ -996,14 +1002,12 @@ static int gpu_write(struct i915_vma *vma,
 	if (err)
 		goto err_request;
 
-	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
-
-	reservation_object_lock(vma->resv, NULL);
-	reservation_object_add_excl_fence(vma->resv, &rq->fence);
-	reservation_object_unlock(vma->resv);
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	if (err)
+		i915_request_skip(rq, err);
 
 err_request:
-	__i915_request_add(rq, err == 0);
+	i915_request_add(rq);
 
 	return err;
 }
@@ -1047,7 +1051,8 @@ static int __igt_write_huge(struct i915_gem_context *ctx,
 			    u32 dword, u32 val)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
-	struct i915_address_space *vm = ctx->ppgtt ? &ctx->ppgtt->base : &i915->ggtt.base;
+	struct i915_address_space *vm =
+		ctx->ppgtt ? &ctx->ppgtt->vm : &i915->ggtt.vm;
 	unsigned int flags = PIN_USER | PIN_OFFSET_FIXED;
 	struct i915_vma *vma;
 	int err;
@@ -1100,7 +1105,8 @@ static int igt_write_huge(struct i915_gem_context *ctx,
 			  struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
-	struct i915_address_space *vm = ctx->ppgtt ? &ctx->ppgtt->base : &i915->ggtt.base;
+	struct i915_address_space *vm =
+		ctx->ppgtt ? &ctx->ppgtt->vm : &i915->ggtt.vm;
 	static struct intel_engine_cs *engines[I915_NUM_ENGINES];
 	struct intel_engine_cs *engine;
 	I915_RND_STATE(prng);
@@ -1262,6 +1268,7 @@ static int igt_ppgtt_exhaust_huge(void *arg)
 			}
 
 			i915_gem_object_unpin_pages(obj);
+			__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
 			i915_gem_object_put(obj);
 		}
 	}
@@ -1323,6 +1330,7 @@ static int igt_ppgtt_internal_huge(void *arg)
 		}
 
 		i915_gem_object_unpin_pages(obj);
+		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
 		i915_gem_object_put(obj);
 	}
 
@@ -1391,6 +1399,7 @@ static int igt_ppgtt_gemfs_huge(void *arg)
 		}
 
 		i915_gem_object_unpin_pages(obj);
+		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
 		i915_gem_object_put(obj);
 	}
 
@@ -1439,7 +1448,7 @@ static int igt_ppgtt_pin_update(void *arg)
 		if (IS_ERR(obj))
 			return PTR_ERR(obj);
 
-		vma = i915_vma_instance(obj, &ppgtt->base, NULL);
+		vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto out_put;
@@ -1493,7 +1502,7 @@ static int igt_ppgtt_pin_update(void *arg)
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
-	vma = i915_vma_instance(obj, &ppgtt->base, NULL);
+	vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		goto out_put;
@@ -1531,7 +1540,8 @@ static int igt_tmpfs_fallback(void *arg)
 	struct i915_gem_context *ctx = arg;
 	struct drm_i915_private *i915 = ctx->i915;
 	struct vfsmount *gemfs = i915->mm.gemfs;
-	struct i915_address_space *vm = ctx->ppgtt ? &ctx->ppgtt->base : &i915->ggtt.base;
+	struct i915_address_space *vm =
+		ctx->ppgtt ? &ctx->ppgtt->vm : &i915->ggtt.vm;
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
 	u32 *vaddr;
@@ -1587,7 +1597,8 @@ static int igt_shrink_thp(void *arg)
 {
 	struct i915_gem_context *ctx = arg;
 	struct drm_i915_private *i915 = ctx->i915;
-	struct i915_address_space *vm = ctx->ppgtt ? &ctx->ppgtt->base : &i915->ggtt.base;
+	struct i915_address_space *vm =
+		ctx->ppgtt ? &ctx->ppgtt->vm : &i915->ggtt.vm;
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
 	unsigned int flags = PIN_USER;
@@ -1690,20 +1701,20 @@ int i915_gem_huge_page_mock_selftests(void)
 	dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(39));
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	ppgtt = i915_ppgtt_create(dev_priv, ERR_PTR(-ENODEV), "mock");
+	ppgtt = i915_ppgtt_create(dev_priv, ERR_PTR(-ENODEV));
 	if (IS_ERR(ppgtt)) {
 		err = PTR_ERR(ppgtt);
 		goto out_unlock;
 	}
 
-	if (!i915_vm_is_48bit(&ppgtt->base)) {
+	if (!i915_vm_is_48bit(&ppgtt->vm)) {
 		pr_err("failed to create 48b PPGTT\n");
 		err = -EINVAL;
 		goto out_close;
 	}
 
 	/* If we were ever hit this then it's time to mock the 64K scratch */
-	if (!i915_vm_has_scratch_64K(&ppgtt->base)) {
+	if (!i915_vm_has_scratch_64K(&ppgtt->vm)) {
 		pr_err("PPGTT missing 64K scratch page\n");
 		err = -EINVAL;
 		goto out_close;
@@ -1712,7 +1723,7 @@ int i915_gem_huge_page_mock_selftests(void)
 	err = i915_subtests(tests, ppgtt);
 
 out_close:
-	i915_ppgtt_close(&ppgtt->base);
+	i915_ppgtt_close(&ppgtt->vm);
 	i915_ppgtt_put(ppgtt);
 
 out_unlock:
@@ -1720,7 +1731,7 @@ out_unlock:
 
 	i915_modparams.enable_ppgtt = saved_ppgtt;
 
-	drm_dev_unref(&dev_priv->drm);
+	drm_dev_put(&dev_priv->drm);
 
 	return err;
 }
@@ -1744,6 +1755,9 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *dev_priv)
 		return 0;
 	}
 
+	if (i915_terminally_wedged(&dev_priv->gpu_error))
+		return 0;
+
 	file = mock_file(dev_priv);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
@@ -1758,7 +1772,7 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *dev_priv)
 	}
 
 	if (ctx->ppgtt)
-		ctx->ppgtt->base.scrub_64K = true;
+		ctx->ppgtt->vm.scrub_64K = true;
 
 	err = i915_subtests(tests, ctx);
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
index 340a98c0c804..3a095c37c120 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
@@ -42,11 +42,21 @@ static int cpu_set(struct drm_i915_gem_object *obj,
 
 	page = i915_gem_object_get_page(obj, offset >> PAGE_SHIFT);
 	map = kmap_atomic(page);
-	if (needs_clflush & CLFLUSH_BEFORE)
+
+	if (needs_clflush & CLFLUSH_BEFORE) {
+		mb();
 		clflush(map+offset_in_page(offset) / sizeof(*map));
+		mb();
+	}
+
 	map[offset_in_page(offset) / sizeof(*map)] = v;
-	if (needs_clflush & CLFLUSH_AFTER)
+
+	if (needs_clflush & CLFLUSH_AFTER) {
+		mb();
 		clflush(map+offset_in_page(offset) / sizeof(*map));
+		mb();
+	}
+
 	kunmap_atomic(map);
 
 	i915_gem_obj_finish_shmem_access(obj);
@@ -68,8 +78,13 @@ static int cpu_get(struct drm_i915_gem_object *obj,
 
 	page = i915_gem_object_get_page(obj, offset >> PAGE_SHIFT);
 	map = kmap_atomic(page);
-	if (needs_clflush & CLFLUSH_BEFORE)
+
+	if (needs_clflush & CLFLUSH_BEFORE) {
+		mb();
 		clflush(map+offset_in_page(offset) / sizeof(*map));
+		mb();
+	}
+
 	*v = map[offset_in_page(offset) / sizeof(*map)];
 	kunmap_atomic(map);
 
@@ -199,7 +214,7 @@ static int gpu_set(struct drm_i915_gem_object *obj,
 
 	cs = intel_ring_begin(rq, 4);
 	if (IS_ERR(cs)) {
-		__i915_request_add(rq, false);
+		i915_request_add(rq);
 		i915_vma_unpin(vma);
 		return PTR_ERR(cs);
 	}
@@ -210,28 +225,24 @@ static int gpu_set(struct drm_i915_gem_object *obj,
 		*cs++ = upper_32_bits(i915_ggtt_offset(vma) + offset);
 		*cs++ = v;
 	} else if (INTEL_GEN(i915) >= 4) {
-		*cs++ = MI_STORE_DWORD_IMM_GEN4 | 1 << 22;
+		*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
 		*cs++ = 0;
 		*cs++ = i915_ggtt_offset(vma) + offset;
 		*cs++ = v;
 	} else {
-		*cs++ = MI_STORE_DWORD_IMM | 1 << 22;
+		*cs++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
 		*cs++ = i915_ggtt_offset(vma) + offset;
 		*cs++ = v;
 		*cs++ = MI_NOOP;
 	}
 	intel_ring_advance(rq, cs);
 
-	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
 	i915_vma_unpin(vma);
 
-	reservation_object_lock(obj->resv, NULL);
-	reservation_object_add_excl_fence(obj->resv, &rq->fence);
-	reservation_object_unlock(obj->resv);
-
-	__i915_request_add(rq, true);
+	i915_request_add(rq);
 
-	return 0;
+	return err;
 }
 
 static bool always_valid(struct drm_i915_private *i915)
@@ -239,8 +250,16 @@ static bool always_valid(struct drm_i915_private *i915)
 	return true;
 }
 
+static bool needs_fence_registers(struct drm_i915_private *i915)
+{
+	return !i915_terminally_wedged(&i915->gpu_error);
+}
+
 static bool needs_mi_store_dword(struct drm_i915_private *i915)
 {
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return false;
+
 	return intel_engine_can_store_dword(i915->engine[RCS]);
 }
 
@@ -251,7 +270,7 @@ static const struct igt_coherency_mode {
 	bool (*valid)(struct drm_i915_private *i915);
 } igt_coherency_mode[] = {
 	{ "cpu", cpu_set, cpu_get, always_valid },
-	{ "gtt", gtt_set, gtt_get, always_valid },
+	{ "gtt", gtt_set, gtt_get, needs_fence_registers },
 	{ "wc", wc_set, wc_get, always_valid },
 	{ "gpu", gpu_set, NULL, needs_mi_store_dword },
 	{ },
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index ddb03f009232..1c92560d35da 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -23,9 +23,11 @@
  */
 
 #include "../i915_selftest.h"
+#include "i915_random.h"
 #include "igt_flush_test.h"
 
 #include "mock_drm.h"
+#include "mock_gem_device.h"
 #include "huge_gem_object.h"
 
 #define DW_PER_PAGE (PAGE_SIZE / sizeof(u32))
@@ -62,12 +64,12 @@ gpu_fill_dw(struct i915_vma *vma, u64 offset, unsigned long count, u32 value)
 			*cmd++ = value;
 		} else if (gen >= 4) {
 			*cmd++ = MI_STORE_DWORD_IMM_GEN4 |
-				(gen < 6 ? 1 << 22 : 0);
+				(gen < 6 ? MI_USE_GGTT : 0);
 			*cmd++ = 0;
 			*cmd++ = offset;
 			*cmd++ = value;
 		} else {
-			*cmd++ = MI_STORE_DWORD_IMM | 1 << 22;
+			*cmd++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
 			*cmd++ = offset;
 			*cmd++ = value;
 		}
@@ -114,7 +116,7 @@ static int gpu_fill(struct drm_i915_gem_object *obj,
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct i915_address_space *vm =
-		ctx->ppgtt ? &ctx->ppgtt->base : &i915->ggtt.base;
+		ctx->ppgtt ? &ctx->ppgtt->vm : &i915->ggtt.vm;
 	struct i915_request *rq;
 	struct i915_vma *vma;
 	struct i915_vma *batch;
@@ -169,24 +171,28 @@ static int gpu_fill(struct drm_i915_gem_object *obj,
 	if (err)
 		goto err_request;
 
-	i915_vma_move_to_active(batch, rq, 0);
+	err = i915_vma_move_to_active(batch, rq, 0);
+	if (err)
+		goto skip_request;
+
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	if (err)
+		goto skip_request;
+
 	i915_gem_object_set_active_reference(batch->obj);
 	i915_vma_unpin(batch);
 	i915_vma_close(batch);
 
-	i915_vma_move_to_active(vma, rq, 0);
 	i915_vma_unpin(vma);
 
-	reservation_object_lock(obj->resv, NULL);
-	reservation_object_add_excl_fence(obj->resv, &rq->fence);
-	reservation_object_unlock(obj->resv);
-
-	__i915_request_add(rq, true);
+	i915_request_add(rq);
 
 	return 0;
 
+skip_request:
+	i915_request_skip(rq, err);
 err_request:
-	__i915_request_add(rq, false);
+	i915_request_add(rq);
 err_batch:
 	i915_vma_unpin(batch);
 err_vma:
@@ -247,9 +253,9 @@ static int cpu_check(struct drm_i915_gem_object *obj, unsigned int max)
 		}
 
 		for (; m < DW_PER_PAGE; m++) {
-			if (map[m] != 0xdeadbeef) {
+			if (map[m] != STACK_MAGIC) {
 				pr_err("Invalid value at page %d, offset %d: found %x expected %x\n",
-				       n, m, map[m], 0xdeadbeef);
+				       n, m, map[m], STACK_MAGIC);
 				err = -EINVAL;
 				goto out_unmap;
 			}
@@ -289,7 +295,7 @@ create_test_object(struct i915_gem_context *ctx,
 {
 	struct drm_i915_gem_object *obj;
 	struct i915_address_space *vm =
-		ctx->ppgtt ? &ctx->ppgtt->base : &ctx->i915->ggtt.base;
+		ctx->ppgtt ? &ctx->ppgtt->vm : &ctx->i915->ggtt.vm;
 	u64 size;
 	int err;
 
@@ -305,7 +311,7 @@ create_test_object(struct i915_gem_context *ctx,
 	if (err)
 		return ERR_PTR(err);
 
-	err = cpu_fill(obj, 0xdeadbeef);
+	err = cpu_fill(obj, STACK_MAGIC);
 	if (err) {
 		pr_err("Failed to fill object with cpu, err=%d\n",
 		       err);
@@ -335,11 +341,15 @@ static int igt_ctx_exec(void *arg)
 	bool first_shared_gtt = true;
 	int err = -ENODEV;
 
-	/* Create a few different contexts (with different mm) and write
+	/*
+	 * Create a few different contexts (with different mm) and write
 	 * through each ctx/mm using the GPU making sure those writes end
 	 * up in the expected pages of our obj.
 	 */
 
+	if (!DRIVER_CAPS(i915)->has_logical_contexts)
+		return 0;
+
 	file = mock_file(i915);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
@@ -366,6 +376,9 @@ static int igt_ctx_exec(void *arg)
 		}
 
 		for_each_engine(engine, i915, id) {
+			if (!engine->context_size)
+				continue; /* No logical context support in HW */
+
 			if (!intel_engine_can_store_dword(engine))
 				continue;
 
@@ -420,6 +433,237 @@ out_unlock:
 	return err;
 }
 
+static int igt_ctx_readonly(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct drm_i915_gem_object *obj = NULL;
+	struct drm_file *file;
+	I915_RND_STATE(prng);
+	IGT_TIMEOUT(end_time);
+	LIST_HEAD(objects);
+	struct i915_gem_context *ctx;
+	struct i915_hw_ppgtt *ppgtt;
+	unsigned long ndwords, dw;
+	int err = -ENODEV;
+
+	/*
+	 * Create a few read-only objects (with the occasional writable object)
+	 * and try to write into these object checking that the GPU discards
+	 * any write to a read-only object.
+	 */
+
+	file = mock_file(i915);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	mutex_lock(&i915->drm.struct_mutex);
+
+	ctx = i915_gem_create_context(i915, file->driver_priv);
+	if (IS_ERR(ctx)) {
+		err = PTR_ERR(ctx);
+		goto out_unlock;
+	}
+
+	ppgtt = ctx->ppgtt ?: i915->mm.aliasing_ppgtt;
+	if (!ppgtt || !ppgtt->vm.has_read_only) {
+		err = 0;
+		goto out_unlock;
+	}
+
+	ndwords = 0;
+	dw = 0;
+	while (!time_after(jiffies, end_time)) {
+		struct intel_engine_cs *engine;
+		unsigned int id;
+
+		for_each_engine(engine, i915, id) {
+			if (!intel_engine_can_store_dword(engine))
+				continue;
+
+			if (!obj) {
+				obj = create_test_object(ctx, file, &objects);
+				if (IS_ERR(obj)) {
+					err = PTR_ERR(obj);
+					goto out_unlock;
+				}
+
+				if (prandom_u32_state(&prng) & 1)
+					i915_gem_object_set_readonly(obj);
+			}
+
+			intel_runtime_pm_get(i915);
+			err = gpu_fill(obj, ctx, engine, dw);
+			intel_runtime_pm_put(i915);
+			if (err) {
+				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) in ctx %u [full-ppgtt? %s], err=%d\n",
+				       ndwords, dw, max_dwords(obj),
+				       engine->name, ctx->hw_id,
+				       yesno(!!ctx->ppgtt), err);
+				goto out_unlock;
+			}
+
+			if (++dw == max_dwords(obj)) {
+				obj = NULL;
+				dw = 0;
+			}
+			ndwords++;
+		}
+	}
+	pr_info("Submitted %lu dwords (across %u engines)\n",
+		ndwords, INTEL_INFO(i915)->num_rings);
+
+	dw = 0;
+	list_for_each_entry(obj, &objects, st_link) {
+		unsigned int rem =
+			min_t(unsigned int, ndwords - dw, max_dwords(obj));
+		unsigned int num_writes;
+
+		num_writes = rem;
+		if (i915_gem_object_is_readonly(obj))
+			num_writes = 0;
+
+		err = cpu_check(obj, num_writes);
+		if (err)
+			break;
+
+		dw += rem;
+	}
+
+out_unlock:
+	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+		err = -EIO;
+	mutex_unlock(&i915->drm.struct_mutex);
+
+	mock_file_free(i915, file);
+	return err;
+}
+
+static __maybe_unused const char *
+__engine_name(struct drm_i915_private *i915, unsigned int engines)
+{
+	struct intel_engine_cs *engine;
+	unsigned int tmp;
+
+	if (engines == ALL_ENGINES)
+		return "all";
+
+	for_each_engine_masked(engine, i915, engines, tmp)
+		return engine->name;
+
+	return "none";
+}
+
+static int __igt_switch_to_kernel_context(struct drm_i915_private *i915,
+					  struct i915_gem_context *ctx,
+					  unsigned int engines)
+{
+	struct intel_engine_cs *engine;
+	unsigned int tmp;
+	int err;
+
+	GEM_TRACE("Testing %s\n", __engine_name(i915, engines));
+	for_each_engine_masked(engine, i915, engines, tmp) {
+		struct i915_request *rq;
+
+		rq = i915_request_alloc(engine, ctx);
+		if (IS_ERR(rq))
+			return PTR_ERR(rq);
+
+		i915_request_add(rq);
+	}
+
+	err = i915_gem_switch_to_kernel_context(i915);
+	if (err)
+		return err;
+
+	for_each_engine_masked(engine, i915, engines, tmp) {
+		if (!engine_has_kernel_context_barrier(engine)) {
+			pr_err("kernel context not last on engine %s!\n",
+			       engine->name);
+			return -EINVAL;
+		}
+	}
+
+	err = i915_gem_wait_for_idle(i915,
+				     I915_WAIT_LOCKED,
+				     MAX_SCHEDULE_TIMEOUT);
+	if (err)
+		return err;
+
+	GEM_BUG_ON(i915->gt.active_requests);
+	for_each_engine_masked(engine, i915, engines, tmp) {
+		if (engine->last_retired_context->gem_context != i915->kernel_context) {
+			pr_err("engine %s not idling in kernel context!\n",
+			       engine->name);
+			return -EINVAL;
+		}
+	}
+
+	err = i915_gem_switch_to_kernel_context(i915);
+	if (err)
+		return err;
+
+	if (i915->gt.active_requests) {
+		pr_err("switch-to-kernel-context emitted %d requests even though it should already be idling in the kernel context\n",
+		       i915->gt.active_requests);
+		return -EINVAL;
+	}
+
+	for_each_engine_masked(engine, i915, engines, tmp) {
+		if (!intel_engine_has_kernel_context(engine)) {
+			pr_err("kernel context not last on engine %s!\n",
+			       engine->name);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int igt_switch_to_kernel_context(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_engine_cs *engine;
+	struct i915_gem_context *ctx;
+	enum intel_engine_id id;
+	int err;
+
+	/*
+	 * A core premise of switching to the kernel context is that
+	 * if an engine is already idling in the kernel context, we
+	 * do not emit another request and wake it up. The other being
+	 * that we do indeed end up idling in the kernel context.
+	 */
+
+	mutex_lock(&i915->drm.struct_mutex);
+	ctx = kernel_context(i915);
+	if (IS_ERR(ctx)) {
+		mutex_unlock(&i915->drm.struct_mutex);
+		return PTR_ERR(ctx);
+	}
+
+	/* First check idling each individual engine */
+	for_each_engine(engine, i915, id) {
+		err = __igt_switch_to_kernel_context(i915, ctx, BIT(id));
+		if (err)
+			goto out_unlock;
+	}
+
+	/* Now en masse */
+	err = __igt_switch_to_kernel_context(i915, ctx, ALL_ENGINES);
+	if (err)
+		goto out_unlock;
+
+out_unlock:
+	GEM_TRACE_DUMP_ON(err);
+	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+		err = -EIO;
+	mutex_unlock(&i915->drm.struct_mutex);
+
+	kernel_context_close(ctx);
+	return err;
+}
+
 static int fake_aliasing_ppgtt_enable(struct drm_i915_private *i915)
 {
 	struct drm_i915_gem_object *obj;
@@ -432,7 +676,7 @@ static int fake_aliasing_ppgtt_enable(struct drm_i915_private *i915)
 	list_for_each_entry(obj, &i915->mm.bound_list, mm.link) {
 		struct i915_vma *vma;
 
-		vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+		vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 		if (IS_ERR(vma))
 			continue;
 
@@ -447,14 +691,37 @@ static void fake_aliasing_ppgtt_disable(struct drm_i915_private *i915)
 	i915_gem_fini_aliasing_ppgtt(i915);
 }
 
+int i915_gem_context_mock_selftests(void)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(igt_switch_to_kernel_context),
+	};
+	struct drm_i915_private *i915;
+	int err;
+
+	i915 = mock_gem_device();
+	if (!i915)
+		return -ENOMEM;
+
+	err = i915_subtests(tests, i915);
+
+	drm_dev_put(&i915->drm);
+	return err;
+}
+
 int i915_gem_context_live_selftests(struct drm_i915_private *dev_priv)
 {
 	static const struct i915_subtest tests[] = {
+		SUBTEST(igt_switch_to_kernel_context),
 		SUBTEST(igt_ctx_exec),
+		SUBTEST(igt_ctx_readonly),
 	};
 	bool fake_alias = false;
 	int err;
 
+	if (i915_terminally_wedged(&dev_priv->gpu_error))
+		return 0;
+
 	/* Install a fake aliasing gtt for exercise */
 	if (USES_PPGTT(dev_priv) && !dev_priv->mm.aliasing_ppgtt) {
 		mutex_lock(&dev_priv->drm.struct_mutex);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c
index 89dc25a5a53b..a7055b12e53c 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c
@@ -389,7 +389,7 @@ int i915_gem_dmabuf_mock_selftests(void)
 
 	err = i915_subtests(tests, i915);
 
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
index ab9d7bee0aae..128ad1cf0647 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -35,7 +35,7 @@ static int populate_ggtt(struct drm_i915_private *i915)
 	u64 size;
 
 	for (size = 0;
-	     size + I915_GTT_PAGE_SIZE <= i915->ggtt.base.total;
+	     size + I915_GTT_PAGE_SIZE <= i915->ggtt.vm.total;
 	     size += I915_GTT_PAGE_SIZE) {
 		struct i915_vma *vma;
 
@@ -57,7 +57,7 @@ static int populate_ggtt(struct drm_i915_private *i915)
 		return -EINVAL;
 	}
 
-	if (list_empty(&i915->ggtt.base.inactive_list)) {
+	if (list_empty(&i915->ggtt.vm.inactive_list)) {
 		pr_err("No objects on the GGTT inactive list!\n");
 		return -EINVAL;
 	}
@@ -69,7 +69,7 @@ static void unpin_ggtt(struct drm_i915_private *i915)
 {
 	struct i915_vma *vma;
 
-	list_for_each_entry(vma, &i915->ggtt.base.inactive_list, vm_link)
+	list_for_each_entry(vma, &i915->ggtt.vm.inactive_list, vm_link)
 		i915_vma_unpin(vma);
 }
 
@@ -103,7 +103,7 @@ static int igt_evict_something(void *arg)
 		goto cleanup;
 
 	/* Everything is pinned, nothing should happen */
-	err = i915_gem_evict_something(&ggtt->base,
+	err = i915_gem_evict_something(&ggtt->vm,
 				       I915_GTT_PAGE_SIZE, 0, 0,
 				       0, U64_MAX,
 				       0);
@@ -116,7 +116,7 @@ static int igt_evict_something(void *arg)
 	unpin_ggtt(i915);
 
 	/* Everything is unpinned, we should be able to evict something */
-	err = i915_gem_evict_something(&ggtt->base,
+	err = i915_gem_evict_something(&ggtt->vm,
 				       I915_GTT_PAGE_SIZE, 0, 0,
 				       0, U64_MAX,
 				       0);
@@ -181,7 +181,7 @@ static int igt_evict_for_vma(void *arg)
 		goto cleanup;
 
 	/* Everything is pinned, nothing should happen */
-	err = i915_gem_evict_for_node(&ggtt->base, &target, 0);
+	err = i915_gem_evict_for_node(&ggtt->vm, &target, 0);
 	if (err != -ENOSPC) {
 		pr_err("i915_gem_evict_for_node on a full GGTT returned err=%d\n",
 		       err);
@@ -191,7 +191,7 @@ static int igt_evict_for_vma(void *arg)
 	unpin_ggtt(i915);
 
 	/* Everything is unpinned, we should be able to evict the node */
-	err = i915_gem_evict_for_node(&ggtt->base, &target, 0);
+	err = i915_gem_evict_for_node(&ggtt->vm, &target, 0);
 	if (err) {
 		pr_err("i915_gem_evict_for_node returned err=%d\n",
 		       err);
@@ -229,7 +229,7 @@ static int igt_evict_for_cache_color(void *arg)
 	 * i915_gtt_color_adjust throughout our driver, so using a mock color
 	 * adjust will work just fine for our purposes.
 	 */
-	ggtt->base.mm.color_adjust = mock_color_adjust;
+	ggtt->vm.mm.color_adjust = mock_color_adjust;
 
 	obj = i915_gem_object_create_internal(i915, I915_GTT_PAGE_SIZE);
 	if (IS_ERR(obj)) {
@@ -265,7 +265,7 @@ static int igt_evict_for_cache_color(void *arg)
 	i915_vma_unpin(vma);
 
 	/* Remove just the second vma */
-	err = i915_gem_evict_for_node(&ggtt->base, &target, 0);
+	err = i915_gem_evict_for_node(&ggtt->vm, &target, 0);
 	if (err) {
 		pr_err("[0]i915_gem_evict_for_node returned err=%d\n", err);
 		goto cleanup;
@@ -276,7 +276,7 @@ static int igt_evict_for_cache_color(void *arg)
 	 */
 	target.color = I915_CACHE_L3_LLC;
 
-	err = i915_gem_evict_for_node(&ggtt->base, &target, 0);
+	err = i915_gem_evict_for_node(&ggtt->vm, &target, 0);
 	if (!err) {
 		pr_err("[1]i915_gem_evict_for_node returned err=%d\n", err);
 		err = -EINVAL;
@@ -288,7 +288,7 @@ static int igt_evict_for_cache_color(void *arg)
 cleanup:
 	unpin_ggtt(i915);
 	cleanup_objects(i915);
-	ggtt->base.mm.color_adjust = NULL;
+	ggtt->vm.mm.color_adjust = NULL;
 	return err;
 }
 
@@ -305,7 +305,7 @@ static int igt_evict_vm(void *arg)
 		goto cleanup;
 
 	/* Everything is pinned, nothing should happen */
-	err = i915_gem_evict_vm(&ggtt->base);
+	err = i915_gem_evict_vm(&ggtt->vm);
 	if (err) {
 		pr_err("i915_gem_evict_vm on a full GGTT returned err=%d]\n",
 		       err);
@@ -314,7 +314,7 @@ static int igt_evict_vm(void *arg)
 
 	unpin_ggtt(i915);
 
-	err = i915_gem_evict_vm(&ggtt->base);
+	err = i915_gem_evict_vm(&ggtt->vm);
 	if (err) {
 		pr_err("i915_gem_evict_vm on a full GGTT returned err=%d]\n",
 		       err);
@@ -359,9 +359,9 @@ static int igt_evict_contexts(void *arg)
 
 	/* Reserve a block so that we know we have enough to fit a few rq */
 	memset(&hole, 0, sizeof(hole));
-	err = i915_gem_gtt_insert(&i915->ggtt.base, &hole,
+	err = i915_gem_gtt_insert(&i915->ggtt.vm, &hole,
 				  PRETEND_GGTT_SIZE, 0, I915_COLOR_UNEVICTABLE,
-				  0, i915->ggtt.base.total,
+				  0, i915->ggtt.vm.total,
 				  PIN_NOEVICT);
 	if (err)
 		goto out_locked;
@@ -377,9 +377,9 @@ static int igt_evict_contexts(void *arg)
 			goto out_locked;
 		}
 
-		if (i915_gem_gtt_insert(&i915->ggtt.base, &r->node,
+		if (i915_gem_gtt_insert(&i915->ggtt.vm, &r->node,
 					1ul << 20, 0, I915_COLOR_UNEVICTABLE,
-					0, i915->ggtt.base.total,
+					0, i915->ggtt.vm.total,
 					PIN_NOEVICT)) {
 			kfree(r);
 			break;
@@ -490,7 +490,7 @@ int i915_gem_evict_mock_selftests(void)
 	err = i915_subtests(tests, i915);
 	mutex_unlock(&i915->drm.struct_mutex);
 
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 	return err;
 }
 
@@ -500,5 +500,8 @@ int i915_gem_evict_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_evict_contexts),
 	};
 
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return 0;
+
 	return i915_subtests(tests, i915);
 }
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index f7dc926f4ef1..8e2e269db97e 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -32,6 +32,20 @@
 #include "mock_drm.h"
 #include "mock_gem_device.h"
 
+static void cleanup_freed_objects(struct drm_i915_private *i915)
+{
+	/*
+	 * As we may hold onto the struct_mutex for inordinate lengths of
+	 * time, the NMI khungtaskd detector may fire for the free objects
+	 * worker.
+	 */
+	mutex_unlock(&i915->drm.struct_mutex);
+
+	i915_gem_drain_freed_objects(i915);
+
+	mutex_lock(&i915->drm.struct_mutex);
+}
+
 static void fake_free_pages(struct drm_i915_gem_object *obj,
 			    struct sg_table *pages)
 {
@@ -134,31 +148,34 @@ static int igt_ppgtt_alloc(void *arg)
 {
 	struct drm_i915_private *dev_priv = arg;
 	struct i915_hw_ppgtt *ppgtt;
-	u64 size, last;
-	int err;
+	u64 size, last, limit;
+	int err = 0;
 
 	/* Allocate a ppggt and try to fill the entire range */
 
 	if (!USES_PPGTT(dev_priv))
 		return 0;
 
-	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
-	if (!ppgtt)
-		return -ENOMEM;
+	ppgtt = __hw_ppgtt_create(dev_priv);
+	if (IS_ERR(ppgtt))
+		return PTR_ERR(ppgtt);
 
-	mutex_lock(&dev_priv->drm.struct_mutex);
-	err = __hw_ppgtt_init(ppgtt, dev_priv);
-	if (err)
-		goto err_ppgtt;
-
-	if (!ppgtt->base.allocate_va_range)
+	if (!ppgtt->vm.allocate_va_range)
 		goto err_ppgtt_cleanup;
 
+	/*
+	 * While we only allocate the page tables here and so we could
+	 * address a much larger GTT than we could actually fit into
+	 * RAM, a practical limit is the amount of physical pages in the system.
+	 * This should ensure that we do not run into the oomkiller during
+	 * the test and take down the machine wilfully.
+	 */
+	limit = totalram_pages << PAGE_SHIFT;
+	limit = min(ppgtt->vm.total, limit);
+
 	/* Check we can allocate the entire range */
-	for (size = 4096;
-	     size <= ppgtt->base.total;
-	     size <<= 2) {
-		err = ppgtt->base.allocate_va_range(&ppgtt->base, 0, size);
+	for (size = 4096; size <= limit; size <<= 2) {
+		err = ppgtt->vm.allocate_va_range(&ppgtt->vm, 0, size);
 		if (err) {
 			if (err == -ENOMEM) {
 				pr_info("[1] Ran out of memory for va_range [0 + %llx] [bit %d]\n",
@@ -168,15 +185,15 @@ static int igt_ppgtt_alloc(void *arg)
 			goto err_ppgtt_cleanup;
 		}
 
-		ppgtt->base.clear_range(&ppgtt->base, 0, size);
+		cond_resched();
+
+		ppgtt->vm.clear_range(&ppgtt->vm, 0, size);
 	}
 
 	/* Check we can incrementally allocate the entire range */
-	for (last = 0, size = 4096;
-	     size <= ppgtt->base.total;
-	     last = size, size <<= 2) {
-		err = ppgtt->base.allocate_va_range(&ppgtt->base,
-						    last, size - last);
+	for (last = 0, size = 4096; size <= limit; last = size, size <<= 2) {
+		err = ppgtt->vm.allocate_va_range(&ppgtt->vm,
+						  last, size - last);
 		if (err) {
 			if (err == -ENOMEM) {
 				pr_info("[2] Ran out of memory for va_range [%llx + %llx] [bit %d]\n",
@@ -185,13 +202,14 @@ static int igt_ppgtt_alloc(void *arg)
 			}
 			goto err_ppgtt_cleanup;
 		}
+
+		cond_resched();
 	}
 
 err_ppgtt_cleanup:
-	ppgtt->base.cleanup(&ppgtt->base);
-err_ppgtt:
+	mutex_lock(&dev_priv->drm.struct_mutex);
+	i915_ppgtt_put(ppgtt);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
-	kfree(ppgtt);
 	return err;
 }
 
@@ -293,6 +311,8 @@ static int lowlevel_hole(struct drm_i915_private *i915,
 		i915_gem_object_put(obj);
 
 		kfree(order);
+
+		cleanup_freed_objects(i915);
 	}
 
 	return 0;
@@ -521,6 +541,7 @@ static int fill_hole(struct drm_i915_private *i915,
 		}
 
 		close_object_list(&objects, vm);
+		cleanup_freed_objects(i915);
 	}
 
 	return 0;
@@ -607,6 +628,8 @@ err_put:
 		i915_gem_object_put(obj);
 		if (err)
 			return err;
+
+		cleanup_freed_objects(i915);
 	}
 
 	return 0;
@@ -791,6 +814,8 @@ err_obj:
 		kfree(order);
 		if (err)
 			return err;
+
+		cleanup_freed_objects(i915);
 	}
 
 	return 0;
@@ -859,6 +884,7 @@ static int __shrink_hole(struct drm_i915_private *i915,
 	}
 
 	close_object_list(&objects, vm);
+	cleanup_freed_objects(i915);
 	return err;
 }
 
@@ -951,6 +977,7 @@ static int shrink_boom(struct drm_i915_private *i915,
 		i915_gem_object_put(explode);
 
 		memset(&vm->fault_attr, 0, sizeof(vm->fault_attr));
+		cleanup_freed_objects(i915);
 	}
 
 	return 0;
@@ -982,17 +1009,17 @@ static int exercise_ppgtt(struct drm_i915_private *dev_priv,
 		return PTR_ERR(file);
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	ppgtt = i915_ppgtt_create(dev_priv, file->driver_priv, "mock");
+	ppgtt = i915_ppgtt_create(dev_priv, file->driver_priv);
 	if (IS_ERR(ppgtt)) {
 		err = PTR_ERR(ppgtt);
 		goto out_unlock;
 	}
-	GEM_BUG_ON(offset_in_page(ppgtt->base.total));
-	GEM_BUG_ON(ppgtt->base.closed);
+	GEM_BUG_ON(offset_in_page(ppgtt->vm.total));
+	GEM_BUG_ON(ppgtt->vm.closed);
 
-	err = func(dev_priv, &ppgtt->base, 0, ppgtt->base.total, end_time);
+	err = func(dev_priv, &ppgtt->vm, 0, ppgtt->vm.total, end_time);
 
-	i915_ppgtt_close(&ppgtt->base);
+	i915_ppgtt_close(&ppgtt->vm);
 	i915_ppgtt_put(ppgtt);
 out_unlock:
 	mutex_unlock(&dev_priv->drm.struct_mutex);
@@ -1061,18 +1088,18 @@ static int exercise_ggtt(struct drm_i915_private *i915,
 
 	mutex_lock(&i915->drm.struct_mutex);
 restart:
-	list_sort(NULL, &ggtt->base.mm.hole_stack, sort_holes);
-	drm_mm_for_each_hole(node, &ggtt->base.mm, hole_start, hole_end) {
+	list_sort(NULL, &ggtt->vm.mm.hole_stack, sort_holes);
+	drm_mm_for_each_hole(node, &ggtt->vm.mm, hole_start, hole_end) {
 		if (hole_start < last)
 			continue;
 
-		if (ggtt->base.mm.color_adjust)
-			ggtt->base.mm.color_adjust(node, 0,
-						   &hole_start, &hole_end);
+		if (ggtt->vm.mm.color_adjust)
+			ggtt->vm.mm.color_adjust(node, 0,
+						 &hole_start, &hole_end);
 		if (hole_start >= hole_end)
 			continue;
 
-		err = func(i915, &ggtt->base, hole_start, hole_end, end_time);
+		err = func(i915, &ggtt->vm, hole_start, hole_end, end_time);
 		if (err)
 			break;
 
@@ -1134,7 +1161,7 @@ static int igt_ggtt_page(void *arg)
 		goto out_free;
 
 	memset(&tmp, 0, sizeof(tmp));
-	err = drm_mm_insert_node_in_range(&ggtt->base.mm, &tmp,
+	err = drm_mm_insert_node_in_range(&ggtt->vm.mm, &tmp,
 					  count * PAGE_SIZE, 0,
 					  I915_COLOR_UNEVICTABLE,
 					  0, ggtt->mappable_end,
@@ -1147,9 +1174,9 @@ static int igt_ggtt_page(void *arg)
 	for (n = 0; n < count; n++) {
 		u64 offset = tmp.start + n * PAGE_SIZE;
 
-		ggtt->base.insert_page(&ggtt->base,
-				       i915_gem_object_get_dma_address(obj, 0),
-				       offset, I915_CACHE_NONE, 0);
+		ggtt->vm.insert_page(&ggtt->vm,
+				     i915_gem_object_get_dma_address(obj, 0),
+				     offset, I915_CACHE_NONE, 0);
 	}
 
 	order = i915_random_order(count, &prng);
@@ -1188,7 +1215,7 @@ static int igt_ggtt_page(void *arg)
 
 	kfree(order);
 out_remove:
-	ggtt->base.clear_range(&ggtt->base, tmp.start, tmp.size);
+	ggtt->vm.clear_range(&ggtt->vm, tmp.start, tmp.size);
 	intel_runtime_pm_put(i915);
 	drm_mm_remove_node(&tmp);
 out_unpin:
@@ -1217,6 +1244,7 @@ static int exercise_mock(struct drm_i915_private *i915,
 				     u64 hole_start, u64 hole_end,
 				     unsigned long end_time))
 {
+	const u64 limit = totalram_pages << PAGE_SHIFT;
 	struct i915_gem_context *ctx;
 	struct i915_hw_ppgtt *ppgtt;
 	IGT_TIMEOUT(end_time);
@@ -1229,7 +1257,7 @@ static int exercise_mock(struct drm_i915_private *i915,
 	ppgtt = ctx->ppgtt;
 	GEM_BUG_ON(!ppgtt);
 
-	err = func(i915, &ppgtt->base, 0, ppgtt->base.total, end_time);
+	err = func(i915, &ppgtt->vm, 0, min(ppgtt->vm.total, limit), end_time);
 
 	mock_context_close(ctx);
 	return err;
@@ -1270,7 +1298,7 @@ static int igt_gtt_reserve(void *arg)
 
 	/* Start by filling the GGTT */
 	for (total = 0;
-	     total + 2*I915_GTT_PAGE_SIZE <= i915->ggtt.base.total;
+	     total + 2*I915_GTT_PAGE_SIZE <= i915->ggtt.vm.total;
 	     total += 2*I915_GTT_PAGE_SIZE) {
 		struct i915_vma *vma;
 
@@ -1288,20 +1316,20 @@ static int igt_gtt_reserve(void *arg)
 
 		list_add(&obj->st_link, &objects);
 
-		vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+		vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto out;
 		}
 
-		err = i915_gem_gtt_reserve(&i915->ggtt.base, &vma->node,
+		err = i915_gem_gtt_reserve(&i915->ggtt.vm, &vma->node,
 					   obj->base.size,
 					   total,
 					   obj->cache_level,
 					   0);
 		if (err) {
 			pr_err("i915_gem_gtt_reserve (pass 1) failed at %llu/%llu with err=%d\n",
-			       total, i915->ggtt.base.total, err);
+			       total, i915->ggtt.vm.total, err);
 			goto out;
 		}
 		track_vma_bind(vma);
@@ -1319,7 +1347,7 @@ static int igt_gtt_reserve(void *arg)
 
 	/* Now we start forcing evictions */
 	for (total = I915_GTT_PAGE_SIZE;
-	     total + 2*I915_GTT_PAGE_SIZE <= i915->ggtt.base.total;
+	     total + 2*I915_GTT_PAGE_SIZE <= i915->ggtt.vm.total;
 	     total += 2*I915_GTT_PAGE_SIZE) {
 		struct i915_vma *vma;
 
@@ -1337,20 +1365,20 @@ static int igt_gtt_reserve(void *arg)
 
 		list_add(&obj->st_link, &objects);
 
-		vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+		vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto out;
 		}
 
-		err = i915_gem_gtt_reserve(&i915->ggtt.base, &vma->node,
+		err = i915_gem_gtt_reserve(&i915->ggtt.vm, &vma->node,
 					   obj->base.size,
 					   total,
 					   obj->cache_level,
 					   0);
 		if (err) {
 			pr_err("i915_gem_gtt_reserve (pass 2) failed at %llu/%llu with err=%d\n",
-			       total, i915->ggtt.base.total, err);
+			       total, i915->ggtt.vm.total, err);
 			goto out;
 		}
 		track_vma_bind(vma);
@@ -1371,7 +1399,7 @@ static int igt_gtt_reserve(void *arg)
 		struct i915_vma *vma;
 		u64 offset;
 
-		vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+		vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto out;
@@ -1383,18 +1411,18 @@ static int igt_gtt_reserve(void *arg)
 			goto out;
 		}
 
-		offset = random_offset(0, i915->ggtt.base.total,
+		offset = random_offset(0, i915->ggtt.vm.total,
 				       2*I915_GTT_PAGE_SIZE,
 				       I915_GTT_MIN_ALIGNMENT);
 
-		err = i915_gem_gtt_reserve(&i915->ggtt.base, &vma->node,
+		err = i915_gem_gtt_reserve(&i915->ggtt.vm, &vma->node,
 					   obj->base.size,
 					   offset,
 					   obj->cache_level,
 					   0);
 		if (err) {
 			pr_err("i915_gem_gtt_reserve (pass 3) failed at %llu/%llu with err=%d\n",
-			       total, i915->ggtt.base.total, err);
+			       total, i915->ggtt.vm.total, err);
 			goto out;
 		}
 		track_vma_bind(vma);
@@ -1429,8 +1457,8 @@ static int igt_gtt_insert(void *arg)
 		u64 start, end;
 	} invalid_insert[] = {
 		{
-			i915->ggtt.base.total + I915_GTT_PAGE_SIZE, 0,
-			0, i915->ggtt.base.total,
+			i915->ggtt.vm.total + I915_GTT_PAGE_SIZE, 0,
+			0, i915->ggtt.vm.total,
 		},
 		{
 			2*I915_GTT_PAGE_SIZE, 0,
@@ -1460,7 +1488,7 @@ static int igt_gtt_insert(void *arg)
 
 	/* Check a couple of obviously invalid requests */
 	for (ii = invalid_insert; ii->size; ii++) {
-		err = i915_gem_gtt_insert(&i915->ggtt.base, &tmp,
+		err = i915_gem_gtt_insert(&i915->ggtt.vm, &tmp,
 					  ii->size, ii->alignment,
 					  I915_COLOR_UNEVICTABLE,
 					  ii->start, ii->end,
@@ -1475,7 +1503,7 @@ static int igt_gtt_insert(void *arg)
 
 	/* Start by filling the GGTT */
 	for (total = 0;
-	     total + I915_GTT_PAGE_SIZE <= i915->ggtt.base.total;
+	     total + I915_GTT_PAGE_SIZE <= i915->ggtt.vm.total;
 	     total += I915_GTT_PAGE_SIZE) {
 		struct i915_vma *vma;
 
@@ -1493,15 +1521,15 @@ static int igt_gtt_insert(void *arg)
 
 		list_add(&obj->st_link, &objects);
 
-		vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+		vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto out;
 		}
 
-		err = i915_gem_gtt_insert(&i915->ggtt.base, &vma->node,
+		err = i915_gem_gtt_insert(&i915->ggtt.vm, &vma->node,
 					  obj->base.size, 0, obj->cache_level,
-					  0, i915->ggtt.base.total,
+					  0, i915->ggtt.vm.total,
 					  0);
 		if (err == -ENOSPC) {
 			/* maxed out the GGTT space */
@@ -1510,7 +1538,7 @@ static int igt_gtt_insert(void *arg)
 		}
 		if (err) {
 			pr_err("i915_gem_gtt_insert (pass 1) failed at %llu/%llu with err=%d\n",
-			       total, i915->ggtt.base.total, err);
+			       total, i915->ggtt.vm.total, err);
 			goto out;
 		}
 		track_vma_bind(vma);
@@ -1522,7 +1550,7 @@ static int igt_gtt_insert(void *arg)
 	list_for_each_entry(obj, &objects, st_link) {
 		struct i915_vma *vma;
 
-		vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+		vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto out;
@@ -1542,7 +1570,7 @@ static int igt_gtt_insert(void *arg)
 		struct i915_vma *vma;
 		u64 offset;
 
-		vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+		vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto out;
@@ -1557,13 +1585,13 @@ static int igt_gtt_insert(void *arg)
 			goto out;
 		}
 
-		err = i915_gem_gtt_insert(&i915->ggtt.base, &vma->node,
+		err = i915_gem_gtt_insert(&i915->ggtt.vm, &vma->node,
 					  obj->base.size, 0, obj->cache_level,
-					  0, i915->ggtt.base.total,
+					  0, i915->ggtt.vm.total,
 					  0);
 		if (err) {
 			pr_err("i915_gem_gtt_insert (pass 2) failed at %llu/%llu with err=%d\n",
-			       total, i915->ggtt.base.total, err);
+			       total, i915->ggtt.vm.total, err);
 			goto out;
 		}
 		track_vma_bind(vma);
@@ -1579,7 +1607,7 @@ static int igt_gtt_insert(void *arg)
 
 	/* And then force evictions */
 	for (total = 0;
-	     total + 2*I915_GTT_PAGE_SIZE <= i915->ggtt.base.total;
+	     total + 2*I915_GTT_PAGE_SIZE <= i915->ggtt.vm.total;
 	     total += 2*I915_GTT_PAGE_SIZE) {
 		struct i915_vma *vma;
 
@@ -1597,19 +1625,19 @@ static int igt_gtt_insert(void *arg)
 
 		list_add(&obj->st_link, &objects);
 
-		vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+		vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto out;
 		}
 
-		err = i915_gem_gtt_insert(&i915->ggtt.base, &vma->node,
+		err = i915_gem_gtt_insert(&i915->ggtt.vm, &vma->node,
 					  obj->base.size, 0, obj->cache_level,
-					  0, i915->ggtt.base.total,
+					  0, i915->ggtt.vm.total,
 					  0);
 		if (err) {
 			pr_err("i915_gem_gtt_insert (pass 3) failed at %llu/%llu with err=%d\n",
-			       total, i915->ggtt.base.total, err);
+			       total, i915->ggtt.vm.total, err);
 			goto out;
 		}
 		track_vma_bind(vma);
@@ -1646,7 +1674,7 @@ int i915_gem_gtt_mock_selftests(void)
 	err = i915_subtests(tests, i915);
 	mutex_unlock(&i915->drm.struct_mutex);
 
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 	return err;
 }
 
@@ -1669,7 +1697,7 @@ int i915_gem_gtt_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_ggtt_page),
 	};
 
-	GEM_BUG_ON(offset_in_page(i915->ggtt.base.total));
+	GEM_BUG_ON(offset_in_page(i915->ggtt.vm.total));
 
 	return i915_subtests(tests, i915);
 }
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
index fbdb2419d418..c69cbd5aed52 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
@@ -113,7 +113,7 @@ static int igt_gem_huge(void *arg)
 
 	obj = huge_gem_object(i915,
 			      nreal * PAGE_SIZE,
-			      i915->ggtt.base.total + PAGE_SIZE);
+			      i915->ggtt.vm.total + PAGE_SIZE);
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
@@ -169,9 +169,16 @@ static u64 tiled_offset(const struct tile *tile, u64 v)
 		v += y * tile->width;
 		v += div64_u64_rem(x, tile->width, &x) << tile->size;
 		v += x;
-	} else {
+	} else if (tile->width == 128) {
 		const unsigned int ytile_span = 16;
-		const unsigned int ytile_height = 32 * ytile_span;
+		const unsigned int ytile_height = 512;
+
+		v += y * ytile_span;
+		v += div64_u64_rem(x, ytile_span, &x) * ytile_height;
+		v += x;
+	} else {
+		const unsigned int ytile_span = 32;
+		const unsigned int ytile_height = 256;
 
 		v += y * ytile_span;
 		v += div64_u64_rem(x, ytile_span, &x) * ytile_height;
@@ -288,6 +295,8 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj,
 		kunmap(p);
 		if (err)
 			return err;
+
+		i915_vma_destroy(vma);
 	}
 
 	return 0;
@@ -311,7 +320,7 @@ static int igt_partial_tiling(void *arg)
 
 	obj = huge_gem_object(i915,
 			      nreal << PAGE_SHIFT,
-			      (1 + next_prime_number(i915->ggtt.base.total >> PAGE_SHIFT)) << PAGE_SHIFT);
+			      (1 + next_prime_number(i915->ggtt.vm.total >> PAGE_SHIFT)) << PAGE_SHIFT);
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
@@ -347,6 +356,14 @@ static int igt_partial_tiling(void *arg)
 		unsigned int pitch;
 		struct tile tile;
 
+		if (i915->quirks & QUIRK_PIN_SWIZZLED_PAGES)
+			/*
+			 * The swizzling pattern is actually unknown as it
+			 * varies based on physical address of each page.
+			 * See i915_gem_detect_bit_6_swizzle().
+			 */
+			break;
+
 		tile.tiling = tiling;
 		switch (tiling) {
 		case I915_TILING_X:
@@ -357,7 +374,8 @@ static int igt_partial_tiling(void *arg)
 			break;
 		}
 
-		if (tile.swizzle == I915_BIT_6_SWIZZLE_UNKNOWN ||
+		GEM_BUG_ON(tile.swizzle == I915_BIT_6_SWIZZLE_UNKNOWN);
+		if (tile.swizzle == I915_BIT_6_SWIZZLE_9_17 ||
 		    tile.swizzle == I915_BIT_6_SWIZZLE_9_10_17)
 			continue;
 
@@ -440,7 +458,7 @@ static int make_obj_busy(struct drm_i915_gem_object *obj)
 	struct i915_vma *vma;
 	int err;
 
-	vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+	vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
@@ -454,12 +472,14 @@ static int make_obj_busy(struct drm_i915_gem_object *obj)
 		return PTR_ERR(rq);
 	}
 
-	i915_vma_move_to_active(vma, rq, 0);
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+
 	i915_request_add(rq);
 
-	i915_gem_object_set_active_reference(obj);
+	__i915_gem_object_release_unless_active(obj);
 	i915_vma_unpin(vma);
-	return 0;
+
+	return err;
 }
 
 static bool assert_mmap_offset(struct drm_i915_private *i915,
@@ -488,6 +508,15 @@ static int igt_mmap_offset_exhaustion(void *arg)
 	u64 hole_start, hole_end;
 	int loop, err;
 
+	/* Disable background reaper */
+	mutex_lock(&i915->drm.struct_mutex);
+	if (!i915->gt.active_requests++)
+		i915_gem_unpark(i915);
+	mutex_unlock(&i915->drm.struct_mutex);
+	cancel_delayed_work_sync(&i915->gt.retire_work);
+	cancel_delayed_work_sync(&i915->gt.idle_work);
+	GEM_BUG_ON(!i915->gt.awake);
+
 	/* Trim the device mmap space to only a page */
 	memset(&resv, 0, sizeof(resv));
 	drm_mm_for_each_hole(hole, mm, hole_start, hole_end) {
@@ -496,7 +525,7 @@ static int igt_mmap_offset_exhaustion(void *arg)
 		err = drm_mm_reserve_node(mm, &resv);
 		if (err) {
 			pr_err("Failed to trim VMA manager, err=%d\n", err);
-			return err;
+			goto out_park;
 		}
 		break;
 	}
@@ -538,6 +567,9 @@ static int igt_mmap_offset_exhaustion(void *arg)
 
 	/* Now fill with busy dead objects that we expect to reap */
 	for (loop = 0; loop < 3; loop++) {
+		if (i915_terminally_wedged(&i915->gpu_error))
+			break;
+
 		obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
 		if (IS_ERR(obj)) {
 			err = PTR_ERR(obj);
@@ -554,6 +586,7 @@ static int igt_mmap_offset_exhaustion(void *arg)
 			goto err_obj;
 		}
 
+		/* NB we rely on the _active_ reference to access obj now */
 		GEM_BUG_ON(!i915_gem_object_is_active(obj));
 		err = i915_gem_object_create_mmap_offset(obj);
 		if (err) {
@@ -565,6 +598,13 @@ static int igt_mmap_offset_exhaustion(void *arg)
 
 out:
 	drm_mm_remove_node(&resv);
+out_park:
+	mutex_lock(&i915->drm.struct_mutex);
+	if (--i915->gt.active_requests)
+		queue_delayed_work(i915->wq, &i915->gt.retire_work, 0);
+	else
+		queue_delayed_work(i915->wq, &i915->gt.idle_work, 0);
+	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 err_obj:
 	i915_gem_object_put(obj);
@@ -586,7 +626,7 @@ int i915_gem_object_mock_selftests(void)
 
 	err = i915_subtests(tests, i915);
 
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
index d16d74178e9d..1b70208eeea7 100644
--- a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
@@ -24,3 +24,4 @@ selftest(vma, i915_vma_mock_selftests)
 selftest(evict, i915_gem_evict_mock_selftests)
 selftest(gtt, i915_gem_gtt_mock_selftests)
 selftest(hugepages, i915_gem_huge_page_mock_selftests)
+selftest(contexts, i915_gem_context_mock_selftests)
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 94bc2e1898a4..c4aac6141e04 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -262,7 +262,7 @@ int i915_request_mock_selftests(void)
 		return -ENOMEM;
 
 	err = i915_subtests(tests, i915);
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 
 	return err;
 }
@@ -286,7 +286,9 @@ static int begin_live_test(struct live_test *t,
 	t->func = func;
 	t->name = name;
 
-	err = i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED);
+	err = i915_gem_wait_for_idle(i915,
+				     I915_WAIT_LOCKED,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (err) {
 		pr_err("%s(%s): failed to idle before, with err=%d!",
 		       func, name, err);
@@ -342,9 +344,9 @@ static int live_nop_request(void *arg)
 	mutex_lock(&i915->drm.struct_mutex);
 
 	for_each_engine(engine, i915, id) {
-		IGT_TIMEOUT(end_time);
-		struct i915_request *request;
+		struct i915_request *request = NULL;
 		unsigned long n, prime;
+		IGT_TIMEOUT(end_time);
 		ktime_t times[2] = {};
 
 		err = begin_live_test(&t, i915, __func__, engine->name);
@@ -430,7 +432,7 @@ static struct i915_vma *empty_batch(struct drm_i915_private *i915)
 	if (err)
 		goto err;
 
-	vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+	vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		goto err;
@@ -466,7 +468,7 @@ empty_request(struct intel_engine_cs *engine,
 		goto out_request;
 
 out_request:
-	__i915_request_add(request, err == 0);
+	i915_request_add(request);
 	return err ? ERR_PTR(err) : request;
 }
 
@@ -555,7 +557,8 @@ out_unlock:
 static struct i915_vma *recursive_batch(struct drm_i915_private *i915)
 {
 	struct i915_gem_context *ctx = i915->kernel_context;
-	struct i915_address_space *vm = ctx->ppgtt ? &ctx->ppgtt->base : &i915->ggtt.base;
+	struct i915_address_space *vm =
+		ctx->ppgtt ? &ctx->ppgtt->vm : &i915->ggtt.vm;
 	struct drm_i915_gem_object *obj;
 	const int gen = INTEL_GEN(i915);
 	struct i915_vma *vma;
@@ -593,11 +596,8 @@ static struct i915_vma *recursive_batch(struct drm_i915_private *i915)
 	} else if (gen >= 6) {
 		*cmd++ = MI_BATCH_BUFFER_START | 1 << 8;
 		*cmd++ = lower_32_bits(vma->node.start);
-	} else if (gen >= 4) {
-		*cmd++ = MI_BATCH_BUFFER_START | MI_BATCH_GTT;
-		*cmd++ = lower_32_bits(vma->node.start);
 	} else {
-		*cmd++ = MI_BATCH_BUFFER_START | MI_BATCH_GTT | 1;
+		*cmd++ = MI_BATCH_BUFFER_START | MI_BATCH_GTT;
 		*cmd++ = lower_32_bits(vma->node.start);
 	}
 	*cmd++ = MI_BATCH_BUFFER_END; /* terminate early in case of error */
@@ -677,7 +677,9 @@ static int live_all_engines(void *arg)
 			i915_gem_object_set_active_reference(batch->obj);
 		}
 
-		i915_vma_move_to_active(batch, request[id], 0);
+		err = i915_vma_move_to_active(batch, request[id], 0);
+		GEM_BUG_ON(err);
+
 		i915_request_get(request[id]);
 		i915_request_add(request[id]);
 	}
@@ -787,7 +789,9 @@ static int live_sequential_engines(void *arg)
 		GEM_BUG_ON(err);
 		request[id]->batch = batch;
 
-		i915_vma_move_to_active(batch, request[id], 0);
+		err = i915_vma_move_to_active(batch, request[id], 0);
+		GEM_BUG_ON(err);
+
 		i915_gem_object_set_active_reference(batch->obj);
 		i915_vma_get(batch);
 
@@ -861,5 +865,9 @@ int i915_request_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_sequential_engines),
 		SUBTEST(live_empty_request),
 	};
+
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return 0;
+
 	return i915_subtests(tests, i915);
 }
diff --git a/drivers/gpu/drm/i915/selftests/i915_selftest.c b/drivers/gpu/drm/i915/selftests/i915_selftest.c
index addc5a599c4a..86c54ea37f48 100644
--- a/drivers/gpu/drm/i915/selftests/i915_selftest.c
+++ b/drivers/gpu/drm/i915/selftests/i915_selftest.c
@@ -210,6 +210,8 @@ int __i915_subtests(const char *caller,
 			return -EINTR;
 
 		pr_debug(DRIVER_NAME ": Running %s/%s\n", caller, st->name);
+		GEM_TRACE("Running %s/%s\n", caller, st->name);
+
 		err = st->func(data);
 		if (err && err != -EINTR) {
 			pr_err(DRIVER_NAME "/%s: %s failed with error %d\n",
diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c
index e90f97236e50..ffa74290e054 100644
--- a/drivers/gpu/drm/i915/selftests/i915_vma.c
+++ b/drivers/gpu/drm/i915/selftests/i915_vma.c
@@ -35,7 +35,7 @@ static bool assert_vma(struct i915_vma *vma,
 {
 	bool ok = true;
 
-	if (vma->vm != &ctx->ppgtt->base) {
+	if (vma->vm != &ctx->ppgtt->vm) {
 		pr_err("VMA created with wrong VM\n");
 		ok = false;
 	}
@@ -110,8 +110,7 @@ static int create_vmas(struct drm_i915_private *i915,
 	list_for_each_entry(obj, objects, st_link) {
 		for (pinned = 0; pinned <= 1; pinned++) {
 			list_for_each_entry(ctx, contexts, link) {
-				struct i915_address_space *vm =
-					&ctx->ppgtt->base;
+				struct i915_address_space *vm = &ctx->ppgtt->vm;
 				struct i915_vma *vma;
 				int err;
 
@@ -259,12 +258,12 @@ static int igt_vma_pin1(void *arg)
 		VALID(0, PIN_GLOBAL | PIN_OFFSET_BIAS | 8192),
 		VALID(0, PIN_GLOBAL | PIN_OFFSET_BIAS | (i915->ggtt.mappable_end - 4096)),
 		VALID(0, PIN_GLOBAL | PIN_MAPPABLE | PIN_OFFSET_BIAS | (i915->ggtt.mappable_end - 4096)),
-		VALID(0, PIN_GLOBAL | PIN_OFFSET_BIAS | (i915->ggtt.base.total - 4096)),
+		VALID(0, PIN_GLOBAL | PIN_OFFSET_BIAS | (i915->ggtt.vm.total - 4096)),
 
 		VALID(0, PIN_GLOBAL | PIN_MAPPABLE | PIN_OFFSET_FIXED | (i915->ggtt.mappable_end - 4096)),
 		INVALID(0, PIN_GLOBAL | PIN_MAPPABLE | PIN_OFFSET_FIXED | i915->ggtt.mappable_end),
-		VALID(0, PIN_GLOBAL | PIN_OFFSET_FIXED | (i915->ggtt.base.total - 4096)),
-		INVALID(0, PIN_GLOBAL | PIN_OFFSET_FIXED | i915->ggtt.base.total),
+		VALID(0, PIN_GLOBAL | PIN_OFFSET_FIXED | (i915->ggtt.vm.total - 4096)),
+		INVALID(0, PIN_GLOBAL | PIN_OFFSET_FIXED | i915->ggtt.vm.total),
 		INVALID(0, PIN_GLOBAL | PIN_OFFSET_FIXED | round_down(U64_MAX, PAGE_SIZE)),
 
 		VALID(4096, PIN_GLOBAL),
@@ -272,12 +271,12 @@ static int igt_vma_pin1(void *arg)
 		VALID(i915->ggtt.mappable_end - 4096, PIN_GLOBAL | PIN_MAPPABLE),
 		VALID(i915->ggtt.mappable_end, PIN_GLOBAL | PIN_MAPPABLE),
 		NOSPACE(i915->ggtt.mappable_end + 4096, PIN_GLOBAL | PIN_MAPPABLE),
-		VALID(i915->ggtt.base.total - 4096, PIN_GLOBAL),
-		VALID(i915->ggtt.base.total, PIN_GLOBAL),
-		NOSPACE(i915->ggtt.base.total + 4096, PIN_GLOBAL),
+		VALID(i915->ggtt.vm.total - 4096, PIN_GLOBAL),
+		VALID(i915->ggtt.vm.total, PIN_GLOBAL),
+		NOSPACE(i915->ggtt.vm.total + 4096, PIN_GLOBAL),
 		NOSPACE(round_down(U64_MAX, PAGE_SIZE), PIN_GLOBAL),
 		INVALID(8192, PIN_GLOBAL | PIN_MAPPABLE | PIN_OFFSET_FIXED | (i915->ggtt.mappable_end - 4096)),
-		INVALID(8192, PIN_GLOBAL | PIN_OFFSET_FIXED | (i915->ggtt.base.total - 4096)),
+		INVALID(8192, PIN_GLOBAL | PIN_OFFSET_FIXED | (i915->ggtt.vm.total - 4096)),
 		INVALID(8192, PIN_GLOBAL | PIN_OFFSET_FIXED | (round_down(U64_MAX, PAGE_SIZE) - 4096)),
 
 		VALID(8192, PIN_GLOBAL | PIN_OFFSET_BIAS | (i915->ggtt.mappable_end - 4096)),
@@ -289,9 +288,9 @@ static int igt_vma_pin1(void *arg)
 		 * variable start, end and size.
 		 */
 		NOSPACE(0, PIN_GLOBAL | PIN_MAPPABLE | PIN_OFFSET_BIAS | i915->ggtt.mappable_end),
-		NOSPACE(0, PIN_GLOBAL | PIN_OFFSET_BIAS | i915->ggtt.base.total),
+		NOSPACE(0, PIN_GLOBAL | PIN_OFFSET_BIAS | i915->ggtt.vm.total),
 		NOSPACE(8192, PIN_GLOBAL | PIN_MAPPABLE | PIN_OFFSET_BIAS | (i915->ggtt.mappable_end - 4096)),
-		NOSPACE(8192, PIN_GLOBAL | PIN_OFFSET_BIAS | (i915->ggtt.base.total - 4096)),
+		NOSPACE(8192, PIN_GLOBAL | PIN_OFFSET_BIAS | (i915->ggtt.vm.total - 4096)),
 #endif
 		{ },
 #undef NOSPACE
@@ -307,13 +306,13 @@ static int igt_vma_pin1(void *arg)
 	 * focusing on error handling of boundary conditions.
 	 */
 
-	GEM_BUG_ON(!drm_mm_clean(&i915->ggtt.base.mm));
+	GEM_BUG_ON(!drm_mm_clean(&i915->ggtt.vm.mm));
 
 	obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
-	vma = checked_vma_instance(obj, &i915->ggtt.base, NULL);
+	vma = checked_vma_instance(obj, &i915->ggtt.vm, NULL);
 	if (IS_ERR(vma))
 		goto out;
 
@@ -405,7 +404,7 @@ static unsigned int rotated_size(const struct intel_rotation_plane_info *a,
 static int igt_vma_rotate(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
-	struct i915_address_space *vm = &i915->ggtt.base;
+	struct i915_address_space *vm = &i915->ggtt.vm;
 	struct drm_i915_gem_object *obj;
 	const struct intel_rotation_plane_info planes[] = {
 		{ .width = 1, .height = 1, .stride = 1 },
@@ -604,7 +603,7 @@ static bool assert_pin(struct i915_vma *vma,
 static int igt_vma_partial(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
-	struct i915_address_space *vm = &i915->ggtt.base;
+	struct i915_address_space *vm = &i915->ggtt.vm;
 	const unsigned int npages = 1021; /* prime! */
 	struct drm_i915_gem_object *obj;
 	const struct phase {
@@ -734,7 +733,7 @@ int i915_vma_mock_selftests(void)
 	err = i915_subtests(tests, i915);
 	mutex_unlock(&i915->drm.struct_mutex);
 
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/igt_flush_test.c b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
index 0d06f559243f..af66e3d4e23a 100644
--- a/drivers/gpu/drm/i915/selftests/igt_flush_test.c
+++ b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
@@ -9,52 +9,8 @@
 #include "../i915_selftest.h"
 #include "igt_flush_test.h"
 
-struct wedge_me {
-	struct delayed_work work;
-	struct drm_i915_private *i915;
-	const void *symbol;
-};
-
-static void wedge_me(struct work_struct *work)
-{
-	struct wedge_me *w = container_of(work, typeof(*w), work.work);
-
-	pr_err("%pS timed out, cancelling all further testing.\n", w->symbol);
-
-	GEM_TRACE("%pS timed out.\n", w->symbol);
-	GEM_TRACE_DUMP();
-
-	i915_gem_set_wedged(w->i915);
-}
-
-static void __init_wedge(struct wedge_me *w,
-			 struct drm_i915_private *i915,
-			 long timeout,
-			 const void *symbol)
-{
-	w->i915 = i915;
-	w->symbol = symbol;
-
-	INIT_DELAYED_WORK_ONSTACK(&w->work, wedge_me);
-	schedule_delayed_work(&w->work, timeout);
-}
-
-static void __fini_wedge(struct wedge_me *w)
-{
-	cancel_delayed_work_sync(&w->work);
-	destroy_delayed_work_on_stack(&w->work);
-	w->i915 = NULL;
-}
-
-#define wedge_on_timeout(W, DEV, TIMEOUT)				\
-	for (__init_wedge((W), (DEV), (TIMEOUT), __builtin_return_address(0)); \
-	     (W)->i915;							\
-	     __fini_wedge((W)))
-
 int igt_flush_test(struct drm_i915_private *i915, unsigned int flags)
 {
-	struct wedge_me w;
-
 	cond_resched();
 
 	if (flags & I915_WAIT_LOCKED &&
@@ -63,8 +19,15 @@ int igt_flush_test(struct drm_i915_private *i915, unsigned int flags)
 		i915_gem_set_wedged(i915);
 	}
 
-	wedge_on_timeout(&w, i915, HZ)
-		i915_gem_wait_for_idle(i915, flags);
+	if (i915_gem_wait_for_idle(i915, flags, HZ / 5) == -ETIME) {
+		pr_err("%pS timed out, cancelling all further testing.\n",
+		       __builtin_return_address(0));
+
+		GEM_TRACE("%pS timed out.\n", __builtin_return_address(0));
+		GEM_TRACE_DUMP();
+
+		i915_gem_set_wedged(i915);
+	}
 
 	return i915_terminally_wedged(&i915->gpu_error) ? -EIO : 0;
 }
diff --git a/drivers/gpu/drm/i915/selftests/igt_wedge_me.h b/drivers/gpu/drm/i915/selftests/igt_wedge_me.h
new file mode 100644
index 000000000000..08e5ff11bbd9
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/igt_wedge_me.h
@@ -0,0 +1,58 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2018 Intel Corporation
+ */
+
+#ifndef IGT_WEDGE_ME_H
+#define IGT_WEDGE_ME_H
+
+#include <linux/workqueue.h>
+
+#include "../i915_gem.h"
+
+struct drm_i915_private;
+
+struct igt_wedge_me {
+	struct delayed_work work;
+	struct drm_i915_private *i915;
+	const char *name;
+};
+
+static void __igt_wedge_me(struct work_struct *work)
+{
+	struct igt_wedge_me *w = container_of(work, typeof(*w), work.work);
+
+	pr_err("%s timed out, cancelling test.\n", w->name);
+
+	GEM_TRACE("%s timed out.\n", w->name);
+	GEM_TRACE_DUMP();
+
+	i915_gem_set_wedged(w->i915);
+}
+
+static void __igt_init_wedge(struct igt_wedge_me *w,
+			     struct drm_i915_private *i915,
+			     long timeout,
+			     const char *name)
+{
+	w->i915 = i915;
+	w->name = name;
+
+	INIT_DELAYED_WORK_ONSTACK(&w->work, __igt_wedge_me);
+	schedule_delayed_work(&w->work, timeout);
+}
+
+static void __igt_fini_wedge(struct igt_wedge_me *w)
+{
+	cancel_delayed_work_sync(&w->work);
+	destroy_delayed_work_on_stack(&w->work);
+	w->i915 = NULL;
+}
+
+#define igt_wedge_on_timeout(W, DEV, TIMEOUT)				\
+	for (__igt_init_wedge((W), (DEV), (TIMEOUT), __func__);		\
+	     (W)->i915;							\
+	     __igt_fini_wedge((W)))
+
+#endif /* IGT_WEDGE_ME_H */
diff --git a/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c b/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c
index d6926e7820e5..f03b407fdbe2 100644
--- a/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c
@@ -464,7 +464,7 @@ int intel_breadcrumbs_mock_selftests(void)
 		return -ENOMEM;
 
 	err = i915_subtests(tests, i915->engine[RCS]);
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/selftests/intel_guc.c b/drivers/gpu/drm/i915/selftests/intel_guc.c
index fb74e2cf8a0a..407c98fb9170 100644
--- a/drivers/gpu/drm/i915/selftests/intel_guc.c
+++ b/drivers/gpu/drm/i915/selftests/intel_guc.c
@@ -196,19 +196,23 @@ static int igt_guc_clients(void *args)
 	}
 
 	unreserve_doorbell(guc->execbuf_client);
-	err = guc_clients_doorbell_init(guc);
+
+	__create_doorbell(guc->execbuf_client);
+	err = __guc_allocate_doorbell(guc, guc->execbuf_client->stage_id);
 	if (err != -EIO) {
 		pr_err("unexpected (err = %d)", err);
-		goto out;
+		goto out_db;
 	}
 
 	if (!available_dbs(guc, guc->execbuf_client->priority)) {
 		pr_err("doorbell not available when it should\n");
 		err = -EIO;
-		goto out;
+		goto out_db;
 	}
 
+out_db:
 	/* clean after test */
+	__destroy_doorbell(guc->execbuf_client);
 	err = reserve_doorbell(guc->execbuf_client);
 	if (err) {
 		pr_err("failed to reserve back the doorbell back\n");
diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index 438e0b045a2c..65d66cdedd26 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -27,6 +27,7 @@
 #include "../i915_selftest.h"
 #include "i915_random.h"
 #include "igt_flush_test.h"
+#include "igt_wedge_me.h"
 
 #include "mock_context.h"
 #include "mock_drm.h"
@@ -105,7 +106,10 @@ static int emit_recurse_batch(struct hang *h,
 			      struct i915_request *rq)
 {
 	struct drm_i915_private *i915 = h->i915;
-	struct i915_address_space *vm = rq->ctx->ppgtt ? &rq->ctx->ppgtt->base : &i915->ggtt.base;
+	struct i915_address_space *vm =
+		rq->gem_context->ppgtt ?
+		&rq->gem_context->ppgtt->vm :
+		&i915->ggtt.vm;
 	struct i915_vma *hws, *vma;
 	unsigned int flags;
 	u32 *batch;
@@ -127,13 +131,19 @@ static int emit_recurse_batch(struct hang *h,
 	if (err)
 		goto unpin_vma;
 
-	i915_vma_move_to_active(vma, rq, 0);
+	err = i915_vma_move_to_active(vma, rq, 0);
+	if (err)
+		goto unpin_hws;
+
 	if (!i915_gem_object_has_active_reference(vma->obj)) {
 		i915_gem_object_get(vma->obj);
 		i915_gem_object_set_active_reference(vma->obj);
 	}
 
-	i915_vma_move_to_active(hws, rq, 0);
+	err = i915_vma_move_to_active(hws, rq, 0);
+	if (err)
+		goto unpin_hws;
+
 	if (!i915_gem_object_has_active_reference(hws->obj)) {
 		i915_gem_object_get(hws->obj);
 		i915_gem_object_set_active_reference(hws->obj);
@@ -168,7 +178,7 @@ static int emit_recurse_batch(struct hang *h,
 		*batch++ = MI_BATCH_BUFFER_START | 1 << 8;
 		*batch++ = lower_32_bits(vma->node.start);
 	} else if (INTEL_GEN(i915) >= 4) {
-		*batch++ = MI_STORE_DWORD_IMM_GEN4 | 1 << 22;
+		*batch++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
 		*batch++ = 0;
 		*batch++ = lower_32_bits(hws_address(hws, rq));
 		*batch++ = rq->fence.seqno;
@@ -181,7 +191,7 @@ static int emit_recurse_batch(struct hang *h,
 		*batch++ = MI_BATCH_BUFFER_START | 2 << 6;
 		*batch++ = lower_32_bits(vma->node.start);
 	} else {
-		*batch++ = MI_STORE_DWORD_IMM;
+		*batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
 		*batch++ = lower_32_bits(hws_address(hws, rq));
 		*batch++ = rq->fence.seqno;
 		*batch++ = MI_ARB_CHECK;
@@ -190,7 +200,7 @@ static int emit_recurse_batch(struct hang *h,
 		batch += 1024 / sizeof(*batch);
 
 		*batch++ = MI_ARB_CHECK;
-		*batch++ = MI_BATCH_BUFFER_START | 2 << 6 | 1;
+		*batch++ = MI_BATCH_BUFFER_START | 2 << 6;
 		*batch++ = lower_32_bits(vma->node.start);
 	}
 	*batch++ = MI_BATCH_BUFFER_END; /* not reached */
@@ -202,6 +212,7 @@ static int emit_recurse_batch(struct hang *h,
 
 	err = rq->engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, flags);
 
+unpin_hws:
 	i915_vma_unpin(hws);
 unpin_vma:
 	i915_vma_unpin(vma);
@@ -242,7 +253,7 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 
 	err = emit_recurse_batch(h, rq);
 	if (err) {
-		__i915_request_add(rq, false);
+		i915_request_add(rq);
 		return ERR_PTR(err);
 	}
 
@@ -315,7 +326,7 @@ static int igt_hang_sanitycheck(void *arg)
 		*h.batch = MI_BATCH_BUFFER_END;
 		i915_gem_chipset_flush(i915);
 
-		__i915_request_add(rq, true);
+		i915_request_add(rq);
 
 		timeout = i915_request_wait(rq,
 					    I915_WAIT_LOCKED,
@@ -461,7 +472,7 @@ static int __igt_reset_engine(struct drm_i915_private *i915, bool active)
 				}
 
 				i915_request_get(rq);
-				__i915_request_add(rq, true);
+				i915_request_add(rq);
 				mutex_unlock(&i915->drm.struct_mutex);
 
 				if (!wait_until_running(&h, rq)) {
@@ -560,6 +571,30 @@ struct active_engine {
 #define TEST_SELF	BIT(2)
 #define TEST_PRIORITY	BIT(3)
 
+static int active_request_put(struct i915_request *rq)
+{
+	int err = 0;
+
+	if (!rq)
+		return 0;
+
+	if (i915_request_wait(rq, 0, 5 * HZ) < 0) {
+		GEM_TRACE("%s timed out waiting for completion of fence %llx:%d, seqno %d.\n",
+			  rq->engine->name,
+			  rq->fence.context,
+			  rq->fence.seqno,
+			  i915_request_global_seqno(rq));
+		GEM_TRACE_DUMP();
+
+		i915_gem_set_wedged(rq->i915);
+		err = -EIO;
+	}
+
+	i915_request_put(rq);
+
+	return err;
+}
+
 static int active_engine(void *data)
 {
 	I915_RND_STATE(prng);
@@ -608,24 +643,20 @@ static int active_engine(void *data)
 		i915_request_add(new);
 		mutex_unlock(&engine->i915->drm.struct_mutex);
 
-		if (old) {
-			if (i915_request_wait(old, 0, HZ) < 0) {
-				GEM_TRACE("%s timed out.\n", engine->name);
-				GEM_TRACE_DUMP();
-
-				i915_gem_set_wedged(engine->i915);
-				i915_request_put(old);
-				err = -EIO;
-				break;
-			}
-			i915_request_put(old);
-		}
+		err = active_request_put(old);
+		if (err)
+			break;
 
 		cond_resched();
 	}
 
-	for (count = 0; count < ARRAY_SIZE(rq); count++)
-		i915_request_put(rq[count]);
+	for (count = 0; count < ARRAY_SIZE(rq); count++) {
+		int err__ = active_request_put(rq[count]);
+
+		/* Keep the first error */
+		if (!err)
+			err = err__;
+	}
 
 err_file:
 	mock_file_free(engine->i915, file);
@@ -719,7 +750,7 @@ static int __igt_reset_engines(struct drm_i915_private *i915,
 				}
 
 				i915_request_get(rq);
-				__i915_request_add(rq, true);
+				i915_request_add(rq);
 				mutex_unlock(&i915->drm.struct_mutex);
 
 				if (!wait_until_running(&h, rq)) {
@@ -891,7 +922,7 @@ static u32 fake_hangcheck(struct i915_request *rq, u32 mask)
 	return reset_count;
 }
 
-static int igt_wait_reset(void *arg)
+static int igt_reset_wait(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct i915_request *rq;
@@ -919,7 +950,7 @@ static int igt_wait_reset(void *arg)
 	}
 
 	i915_request_get(rq);
-	__i915_request_add(rq, true);
+	i915_request_add(rq);
 
 	if (!wait_until_running(&h, rq)) {
 		struct drm_printer p = drm_info_printer(i915->drm.dev);
@@ -965,6 +996,170 @@ unlock:
 	return err;
 }
 
+struct evict_vma {
+	struct completion completion;
+	struct i915_vma *vma;
+};
+
+static int evict_vma(void *data)
+{
+	struct evict_vma *arg = data;
+	struct i915_address_space *vm = arg->vma->vm;
+	struct drm_i915_private *i915 = vm->i915;
+	struct drm_mm_node evict = arg->vma->node;
+	int err;
+
+	complete(&arg->completion);
+
+	mutex_lock(&i915->drm.struct_mutex);
+	err = i915_gem_evict_for_node(vm, &evict, 0);
+	mutex_unlock(&i915->drm.struct_mutex);
+
+	return err;
+}
+
+static int __igt_reset_evict_vma(struct drm_i915_private *i915,
+				 struct i915_address_space *vm)
+{
+	struct drm_i915_gem_object *obj;
+	struct task_struct *tsk = NULL;
+	struct i915_request *rq;
+	struct evict_vma arg;
+	struct hang h;
+	int err;
+
+	if (!intel_engine_can_store_dword(i915->engine[RCS]))
+		return 0;
+
+	/* Check that we can recover an unbind stuck on a hanging request */
+
+	global_reset_lock(i915);
+
+	mutex_lock(&i915->drm.struct_mutex);
+	err = hang_init(&h, i915);
+	if (err)
+		goto unlock;
+
+	obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	if (IS_ERR(obj)) {
+		err = PTR_ERR(obj);
+		goto fini;
+	}
+
+	arg.vma = i915_vma_instance(obj, vm, NULL);
+	if (IS_ERR(arg.vma)) {
+		err = PTR_ERR(arg.vma);
+		goto out_obj;
+	}
+
+	rq = hang_create_request(&h, i915->engine[RCS]);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto out_obj;
+	}
+
+	err = i915_vma_pin(arg.vma, 0, 0,
+			   i915_vma_is_ggtt(arg.vma) ? PIN_GLOBAL : PIN_USER);
+	if (err)
+		goto out_obj;
+
+	err = i915_vma_move_to_active(arg.vma, rq, EXEC_OBJECT_WRITE);
+	i915_vma_unpin(arg.vma);
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+	if (err)
+		goto out_rq;
+
+	mutex_unlock(&i915->drm.struct_mutex);
+
+	if (!wait_until_running(&h, rq)) {
+		struct drm_printer p = drm_info_printer(i915->drm.dev);
+
+		pr_err("%s: Failed to start request %x, at %x\n",
+		       __func__, rq->fence.seqno, hws_seqno(&h, rq));
+		intel_engine_dump(rq->engine, &p, "%s\n", rq->engine->name);
+
+		i915_gem_set_wedged(i915);
+		goto out_reset;
+	}
+
+	init_completion(&arg.completion);
+
+	tsk = kthread_run(evict_vma, &arg, "igt/evict_vma");
+	if (IS_ERR(tsk)) {
+		err = PTR_ERR(tsk);
+		tsk = NULL;
+		goto out_reset;
+	}
+
+	wait_for_completion(&arg.completion);
+
+	if (wait_for(waitqueue_active(&rq->execute), 10)) {
+		struct drm_printer p = drm_info_printer(i915->drm.dev);
+
+		pr_err("igt/evict_vma kthread did not wait\n");
+		intel_engine_dump(rq->engine, &p, "%s\n", rq->engine->name);
+
+		i915_gem_set_wedged(i915);
+		goto out_reset;
+	}
+
+out_reset:
+	fake_hangcheck(rq, intel_engine_flag(rq->engine));
+
+	if (tsk) {
+		struct igt_wedge_me w;
+
+		/* The reset, even indirectly, should take less than 10ms. */
+		igt_wedge_on_timeout(&w, i915, HZ / 10 /* 100ms timeout*/)
+			err = kthread_stop(tsk);
+	}
+
+	mutex_lock(&i915->drm.struct_mutex);
+out_rq:
+	i915_request_put(rq);
+out_obj:
+	i915_gem_object_put(obj);
+fini:
+	hang_fini(&h);
+unlock:
+	mutex_unlock(&i915->drm.struct_mutex);
+	global_reset_unlock(i915);
+
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return -EIO;
+
+	return err;
+}
+
+static int igt_reset_evict_ggtt(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+
+	return __igt_reset_evict_vma(i915, &i915->ggtt.vm);
+}
+
+static int igt_reset_evict_ppgtt(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct i915_gem_context *ctx;
+	int err;
+
+	mutex_lock(&i915->drm.struct_mutex);
+	ctx = kernel_context(i915);
+	mutex_unlock(&i915->drm.struct_mutex);
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	err = 0;
+	if (ctx->ppgtt) /* aliasing == global gtt locking, covered above */
+		err = __igt_reset_evict_vma(i915, &ctx->ppgtt->vm);
+
+	kernel_context_close(ctx);
+	return err;
+}
+
 static int wait_for_others(struct drm_i915_private *i915,
 			   struct intel_engine_cs *exclude)
 {
@@ -1014,7 +1209,7 @@ static int igt_reset_queue(void *arg)
 		}
 
 		i915_request_get(prev);
-		__i915_request_add(prev, true);
+		i915_request_add(prev);
 
 		count = 0;
 		do {
@@ -1028,7 +1223,7 @@ static int igt_reset_queue(void *arg)
 			}
 
 			i915_request_get(rq);
-			__i915_request_add(rq, true);
+			i915_request_add(rq);
 
 			/*
 			 * XXX We don't handle resetting the kernel context
@@ -1161,7 +1356,7 @@ static int igt_handle_error(void *arg)
 	}
 
 	i915_request_get(rq);
-	__i915_request_add(rq, true);
+	i915_request_add(rq);
 
 	if (!wait_until_running(&h, rq)) {
 		struct drm_printer p = drm_info_printer(i915->drm.dev);
@@ -1210,8 +1405,10 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_reset_idle_engine),
 		SUBTEST(igt_reset_active_engine),
 		SUBTEST(igt_reset_engines),
-		SUBTEST(igt_wait_reset),
 		SUBTEST(igt_reset_queue),
+		SUBTEST(igt_reset_wait),
+		SUBTEST(igt_reset_evict_ggtt),
+		SUBTEST(igt_reset_evict_ppgtt),
 		SUBTEST(igt_handle_error),
 	};
 	bool saved_hangcheck;
@@ -1220,6 +1417,9 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 	if (!intel_has_gpu_reset(i915))
 		return 0;
 
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return -EIO; /* we're long past hope of a successful reset */
+
 	intel_runtime_pm_get(i915);
 	saved_hangcheck = fetch_and_zero(&i915_modparams.enable_hangcheck);
 
diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c
index 1b8a07125150..582566faef09 100644
--- a/drivers/gpu/drm/i915/selftests/intel_lrc.c
+++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c
@@ -83,7 +83,7 @@ static int emit_recurse_batch(struct spinner *spin,
 			      struct i915_request *rq,
 			      u32 arbitration_command)
 {
-	struct i915_address_space *vm = &rq->ctx->ppgtt->base;
+	struct i915_address_space *vm = &rq->gem_context->ppgtt->vm;
 	struct i915_vma *hws, *vma;
 	u32 *batch;
 	int err;
@@ -104,13 +104,19 @@ static int emit_recurse_batch(struct spinner *spin,
 	if (err)
 		goto unpin_vma;
 
-	i915_vma_move_to_active(vma, rq, 0);
+	err = i915_vma_move_to_active(vma, rq, 0);
+	if (err)
+		goto unpin_hws;
+
 	if (!i915_gem_object_has_active_reference(vma->obj)) {
 		i915_gem_object_get(vma->obj);
 		i915_gem_object_set_active_reference(vma->obj);
 	}
 
-	i915_vma_move_to_active(hws, rq, 0);
+	err = i915_vma_move_to_active(hws, rq, 0);
+	if (err)
+		goto unpin_hws;
+
 	if (!i915_gem_object_has_active_reference(hws->obj)) {
 		i915_gem_object_get(hws->obj);
 		i915_gem_object_set_active_reference(hws->obj);
@@ -134,6 +140,7 @@ static int emit_recurse_batch(struct spinner *spin,
 
 	err = rq->engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, 0);
 
+unpin_hws:
 	i915_vma_unpin(hws);
 unpin_vma:
 	i915_vma_unpin(vma);
@@ -155,7 +162,7 @@ spinner_create_request(struct spinner *spin,
 
 	err = emit_recurse_batch(spin, rq, arbitration_command);
 	if (err) {
-		__i915_request_add(rq, false);
+		i915_request_add(rq);
 		return ERR_PTR(err);
 	}
 
@@ -444,16 +451,134 @@ err_wedged:
 	goto err_ctx_lo;
 }
 
+static int live_preempt_hang(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct i915_gem_context *ctx_hi, *ctx_lo;
+	struct spinner spin_hi, spin_lo;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = -ENOMEM;
+
+	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
+		return 0;
+
+	if (!intel_has_reset_engine(i915))
+		return 0;
+
+	mutex_lock(&i915->drm.struct_mutex);
+
+	if (spinner_init(&spin_hi, i915))
+		goto err_unlock;
+
+	if (spinner_init(&spin_lo, i915))
+		goto err_spin_hi;
+
+	ctx_hi = kernel_context(i915);
+	if (!ctx_hi)
+		goto err_spin_lo;
+	ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY;
+
+	ctx_lo = kernel_context(i915);
+	if (!ctx_lo)
+		goto err_ctx_hi;
+	ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY;
+
+	for_each_engine(engine, i915, id) {
+		struct i915_request *rq;
+
+		if (!intel_engine_has_preemption(engine))
+			continue;
+
+		rq = spinner_create_request(&spin_lo, ctx_lo, engine,
+					    MI_ARB_CHECK);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto err_ctx_lo;
+		}
+
+		i915_request_add(rq);
+		if (!wait_for_spinner(&spin_lo, rq)) {
+			GEM_TRACE("lo spinner failed to start\n");
+			GEM_TRACE_DUMP();
+			i915_gem_set_wedged(i915);
+			err = -EIO;
+			goto err_ctx_lo;
+		}
+
+		rq = spinner_create_request(&spin_hi, ctx_hi, engine,
+					    MI_ARB_CHECK);
+		if (IS_ERR(rq)) {
+			spinner_end(&spin_lo);
+			err = PTR_ERR(rq);
+			goto err_ctx_lo;
+		}
+
+		init_completion(&engine->execlists.preempt_hang.completion);
+		engine->execlists.preempt_hang.inject_hang = true;
+
+		i915_request_add(rq);
+
+		if (!wait_for_completion_timeout(&engine->execlists.preempt_hang.completion,
+						 HZ / 10)) {
+			pr_err("Preemption did not occur within timeout!");
+			GEM_TRACE_DUMP();
+			i915_gem_set_wedged(i915);
+			err = -EIO;
+			goto err_ctx_lo;
+		}
+
+		set_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
+		i915_reset_engine(engine, NULL);
+		clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
+
+		engine->execlists.preempt_hang.inject_hang = false;
+
+		if (!wait_for_spinner(&spin_hi, rq)) {
+			GEM_TRACE("hi spinner failed to start\n");
+			GEM_TRACE_DUMP();
+			i915_gem_set_wedged(i915);
+			err = -EIO;
+			goto err_ctx_lo;
+		}
+
+		spinner_end(&spin_hi);
+		spinner_end(&spin_lo);
+		if (igt_flush_test(i915, I915_WAIT_LOCKED)) {
+			err = -EIO;
+			goto err_ctx_lo;
+		}
+	}
+
+	err = 0;
+err_ctx_lo:
+	kernel_context_close(ctx_lo);
+err_ctx_hi:
+	kernel_context_close(ctx_hi);
+err_spin_lo:
+	spinner_fini(&spin_lo);
+err_spin_hi:
+	spinner_fini(&spin_hi);
+err_unlock:
+	igt_flush_test(i915, I915_WAIT_LOCKED);
+	mutex_unlock(&i915->drm.struct_mutex);
+	return err;
+}
+
 int intel_execlists_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(live_sanitycheck),
 		SUBTEST(live_preempt),
 		SUBTEST(live_late_preempt),
+		SUBTEST(live_preempt_hang),
 	};
 
 	if (!HAS_EXECLISTS(i915))
 		return 0;
 
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return 0;
+
 	return i915_subtests(tests, i915);
 }
diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
index 17444a3abbb9..0d39b3bf0c0d 100644
--- a/drivers/gpu/drm/i915/selftests/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
@@ -6,6 +6,7 @@
 
 #include "../i915_selftest.h"
 
+#include "igt_wedge_me.h"
 #include "mock_context.h"
 
 static struct drm_i915_gem_object *
@@ -33,7 +34,7 @@ read_nonprivs(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
 	memset(cs, 0xc5, PAGE_SIZE);
 	i915_gem_object_unpin_map(result);
 
-	vma = i915_vma_instance(result, &engine->i915->ggtt.base, NULL);
+	vma = i915_vma_instance(result, &engine->i915->ggtt.vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		goto err_obj;
@@ -49,6 +50,10 @@ read_nonprivs(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
 		goto err_pin;
 	}
 
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	if (err)
+		goto err_req;
+
 	srm = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
 	if (INTEL_GEN(ctx->i915) >= 8)
 		srm++;
@@ -67,15 +72,10 @@ read_nonprivs(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
 	}
 	intel_ring_advance(rq, cs);
 
-	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
-	reservation_object_lock(vma->resv, NULL);
-	reservation_object_add_excl_fence(vma->resv, &rq->fence);
-	reservation_object_unlock(vma->resv);
-
 	i915_gem_object_get(result);
 	i915_gem_object_set_active_reference(result);
 
-	__i915_request_add(rq, true);
+	i915_request_add(rq);
 	i915_vma_unpin(vma);
 
 	return result;
@@ -112,6 +112,7 @@ static int check_whitelist(const struct whitelist *w,
 			   struct intel_engine_cs *engine)
 {
 	struct drm_i915_gem_object *results;
+	struct igt_wedge_me wedge;
 	u32 *vaddr;
 	int err;
 	int i;
@@ -120,7 +121,11 @@ static int check_whitelist(const struct whitelist *w,
 	if (IS_ERR(results))
 		return PTR_ERR(results);
 
-	err = i915_gem_object_set_to_cpu_domain(results, false);
+	err = 0;
+	igt_wedge_on_timeout(&wedge, ctx->i915, HZ / 5) /* a safety net! */
+		err = i915_gem_object_set_to_cpu_domain(results, false);
+	if (i915_terminally_wedged(&ctx->i915->gpu_error))
+		err = -EIO;
 	if (err)
 		goto out_put;
 
@@ -283,6 +288,9 @@ int intel_workarounds_live_selftests(struct drm_i915_private *i915)
 	};
 	int err;
 
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return 0;
+
 	mutex_lock(&i915->drm.struct_mutex);
 	err = i915_subtests(tests, i915);
 	mutex_unlock(&i915->drm.struct_mutex);
diff --git a/drivers/gpu/drm/i915/selftests/mock_context.c b/drivers/gpu/drm/i915/selftests/mock_context.c
index 501becc47c0c..8904f1ce64e3 100644
--- a/drivers/gpu/drm/i915/selftests/mock_context.c
+++ b/drivers/gpu/drm/i915/selftests/mock_context.c
@@ -30,6 +30,7 @@ mock_context(struct drm_i915_private *i915,
 	     const char *name)
 {
 	struct i915_gem_context *ctx;
+	unsigned int n;
 	int ret;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
@@ -43,6 +44,12 @@ mock_context(struct drm_i915_private *i915,
 	INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
 	INIT_LIST_HEAD(&ctx->handles_list);
 
+	for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++) {
+		struct intel_context *ce = &ctx->__engine[n];
+
+		ce->gem_context = ctx;
+	}
+
 	ret = ida_simple_get(&i915->contexts.hw_ida,
 			     0, MAX_CONTEXT_HW_ID, GFP_KERNEL);
 	if (ret < 0)
diff --git a/drivers/gpu/drm/i915/selftests/mock_dmabuf.c b/drivers/gpu/drm/i915/selftests/mock_dmabuf.c
index 302f7d103635..ca682caf1062 100644
--- a/drivers/gpu/drm/i915/selftests/mock_dmabuf.c
+++ b/drivers/gpu/drm/i915/selftests/mock_dmabuf.c
@@ -94,18 +94,6 @@ static void mock_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
 	vm_unmap_ram(vaddr, mock->npages);
 }
 
-static void *mock_dmabuf_kmap_atomic(struct dma_buf *dma_buf, unsigned long page_num)
-{
-	struct mock_dmabuf *mock = to_mock(dma_buf);
-
-	return kmap_atomic(mock->pages[page_num]);
-}
-
-static void mock_dmabuf_kunmap_atomic(struct dma_buf *dma_buf, unsigned long page_num, void *addr)
-{
-	kunmap_atomic(addr);
-}
-
 static void *mock_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num)
 {
 	struct mock_dmabuf *mock = to_mock(dma_buf);
@@ -130,9 +118,7 @@ static const struct dma_buf_ops mock_dmabuf_ops =  {
 	.unmap_dma_buf = mock_unmap_dma_buf,
 	.release = mock_dmabuf_release,
 	.map = mock_dmabuf_kmap,
-	.map_atomic = mock_dmabuf_kmap_atomic,
 	.unmap = mock_dmabuf_kunmap,
-	.unmap_atomic = mock_dmabuf_kunmap_atomic,
 	.mmap = mock_dmabuf_mmap,
 	.vmap = mock_dmabuf_vmap,
 	.vunmap = mock_dmabuf_vunmap,
diff --git a/drivers/gpu/drm/i915/selftests/mock_engine.c b/drivers/gpu/drm/i915/selftests/mock_engine.c
index 26bf29d97007..22a73da45ad5 100644
--- a/drivers/gpu/drm/i915/selftests/mock_engine.c
+++ b/drivers/gpu/drm/i915/selftests/mock_engine.c
@@ -72,25 +72,34 @@ static void hw_delay_complete(struct timer_list *t)
 	spin_unlock(&engine->hw_lock);
 }
 
-static struct intel_ring *
-mock_context_pin(struct intel_engine_cs *engine,
-		 struct i915_gem_context *ctx)
+static void mock_context_unpin(struct intel_context *ce)
 {
-	struct intel_context *ce = to_intel_context(ctx, engine);
-
-	if (!ce->pin_count++)
-		i915_gem_context_get(ctx);
+	i915_gem_context_put(ce->gem_context);
+}
 
-	return engine->buffer;
+static void mock_context_destroy(struct intel_context *ce)
+{
+	GEM_BUG_ON(ce->pin_count);
 }
 
-static void mock_context_unpin(struct intel_engine_cs *engine,
-			       struct i915_gem_context *ctx)
+static const struct intel_context_ops mock_context_ops = {
+	.unpin = mock_context_unpin,
+	.destroy = mock_context_destroy,
+};
+
+static struct intel_context *
+mock_context_pin(struct intel_engine_cs *engine,
+		 struct i915_gem_context *ctx)
 {
 	struct intel_context *ce = to_intel_context(ctx, engine);
 
-	if (!--ce->pin_count)
-		i915_gem_context_put(ctx);
+	if (!ce->pin_count++) {
+		i915_gem_context_get(ctx);
+		ce->ring = engine->buffer;
+		ce->ops = &mock_context_ops;
+	}
+
+	return ce;
 }
 
 static int mock_request_alloc(struct i915_request *request)
@@ -185,13 +194,14 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 	engine->base.status_page.page_addr = (void *)(engine + 1);
 
 	engine->base.context_pin = mock_context_pin;
-	engine->base.context_unpin = mock_context_unpin;
 	engine->base.request_alloc = mock_request_alloc;
 	engine->base.emit_flush = mock_emit_flush;
 	engine->base.emit_breadcrumb = mock_emit_breadcrumb;
 	engine->base.submit_request = mock_submit_request;
 
 	i915_timeline_init(i915, &engine->base.timeline, engine->base.name);
+	lockdep_set_subclass(&engine->base.timeline.lock, TIMELINE_ENGINE);
+
 	intel_engine_init_breadcrumbs(&engine->base);
 	engine->base.breadcrumbs.mock = true; /* prevent touching HW for irqs */
 
@@ -204,8 +214,13 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 	if (!engine->base.buffer)
 		goto err_breadcrumbs;
 
+	if (IS_ERR(intel_context_pin(i915->kernel_context, &engine->base)))
+		goto err_ring;
+
 	return &engine->base;
 
+err_ring:
+	mock_ring_free(engine->base.buffer);
 err_breadcrumbs:
 	intel_engine_fini_breadcrumbs(&engine->base);
 	i915_timeline_fini(&engine->base.timeline);
@@ -238,11 +253,15 @@ void mock_engine_free(struct intel_engine_cs *engine)
 {
 	struct mock_engine *mock =
 		container_of(engine, typeof(*mock), base);
+	struct intel_context *ce;
 
 	GEM_BUG_ON(timer_pending(&mock->hw_delay));
 
-	if (engine->last_retired_context)
-		intel_context_unpin(engine->last_retired_context, engine);
+	ce = fetch_and_zero(&engine->last_retired_context);
+	if (ce)
+		intel_context_unpin(ce);
+
+	__intel_context_unpin(engine->i915->kernel_context, engine);
 
 	mock_ring_free(engine->buffer);
 
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 94baedfa0f74..43ed8b28aeaa 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -136,8 +136,6 @@ static struct dev_pm_domain pm_domain = {
 struct drm_i915_private *mock_gem_device(void)
 {
 	struct drm_i915_private *i915;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
 	struct pci_dev *pdev;
 	int err;
 
@@ -159,7 +157,8 @@ struct drm_i915_private *mock_gem_device(void)
 	dev_pm_domain_set(&pdev->dev, &pm_domain);
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_dont_use_autosuspend(&pdev->dev);
-	WARN_ON(pm_runtime_get_sync(&pdev->dev));
+	if (pm_runtime_enabled(&pdev->dev))
+		WARN_ON(pm_runtime_get_sync(&pdev->dev));
 
 	i915 = (struct drm_i915_private *)(pdev + 1);
 	pci_set_drvdata(pdev, i915);
@@ -233,13 +232,13 @@ struct drm_i915_private *mock_gem_device(void)
 	mock_init_ggtt(i915);
 
 	mkwrite_device_info(i915)->ring_mask = BIT(0);
-	i915->engine[RCS] = mock_engine(i915, "mock", RCS);
-	if (!i915->engine[RCS])
-		goto err_unlock;
-
 	i915->kernel_context = mock_context(i915, NULL);
 	if (!i915->kernel_context)
-		goto err_engine;
+		goto err_unlock;
+
+	i915->engine[RCS] = mock_engine(i915, "mock", RCS);
+	if (!i915->engine[RCS])
+		goto err_context;
 
 	mutex_unlock(&i915->drm.struct_mutex);
 
@@ -247,9 +246,8 @@ struct drm_i915_private *mock_gem_device(void)
 
 	return i915;
 
-err_engine:
-	for_each_engine(engine, i915, id)
-		mock_engine_free(engine);
+err_context:
+	i915_gem_contexts_fini(i915);
 err_unlock:
 	mutex_unlock(&i915->drm.struct_mutex);
 	kmem_cache_destroy(i915->priorities);
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c
index 36c112088940..a140ea5c3a7c 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c
@@ -66,25 +66,21 @@ mock_ppgtt(struct drm_i915_private *i915,
 		return NULL;
 
 	kref_init(&ppgtt->ref);
-	ppgtt->base.i915 = i915;
-	ppgtt->base.total = round_down(U64_MAX, PAGE_SIZE);
-	ppgtt->base.file = ERR_PTR(-ENODEV);
-
-	INIT_LIST_HEAD(&ppgtt->base.active_list);
-	INIT_LIST_HEAD(&ppgtt->base.inactive_list);
-	INIT_LIST_HEAD(&ppgtt->base.unbound_list);
-
-	INIT_LIST_HEAD(&ppgtt->base.global_link);
-	drm_mm_init(&ppgtt->base.mm, 0, ppgtt->base.total);
-
-	ppgtt->base.clear_range = nop_clear_range;
-	ppgtt->base.insert_page = mock_insert_page;
-	ppgtt->base.insert_entries = mock_insert_entries;
-	ppgtt->base.bind_vma = mock_bind_ppgtt;
-	ppgtt->base.unbind_vma = mock_unbind_ppgtt;
-	ppgtt->base.set_pages = ppgtt_set_pages;
-	ppgtt->base.clear_pages = clear_pages;
-	ppgtt->base.cleanup = mock_cleanup;
+	ppgtt->vm.i915 = i915;
+	ppgtt->vm.total = round_down(U64_MAX, PAGE_SIZE);
+	ppgtt->vm.file = ERR_PTR(-ENODEV);
+
+	i915_address_space_init(&ppgtt->vm, i915);
+
+	ppgtt->vm.clear_range = nop_clear_range;
+	ppgtt->vm.insert_page = mock_insert_page;
+	ppgtt->vm.insert_entries = mock_insert_entries;
+	ppgtt->vm.cleanup = mock_cleanup;
+
+	ppgtt->vm.vma_ops.bind_vma    = mock_bind_ppgtt;
+	ppgtt->vm.vma_ops.unbind_vma  = mock_unbind_ppgtt;
+	ppgtt->vm.vma_ops.set_pages   = ppgtt_set_pages;
+	ppgtt->vm.vma_ops.clear_pages = clear_pages;
 
 	return ppgtt;
 }
@@ -105,29 +101,28 @@ void mock_init_ggtt(struct drm_i915_private *i915)
 {
 	struct i915_ggtt *ggtt = &i915->ggtt;
 
-	INIT_LIST_HEAD(&i915->vm_list);
-
-	ggtt->base.i915 = i915;
+	ggtt->vm.i915 = i915;
 
 	ggtt->gmadr = (struct resource) DEFINE_RES_MEM(0, 2048 * PAGE_SIZE);
 	ggtt->mappable_end = resource_size(&ggtt->gmadr);
-	ggtt->base.total = 4096 * PAGE_SIZE;
-
-	ggtt->base.clear_range = nop_clear_range;
-	ggtt->base.insert_page = mock_insert_page;
-	ggtt->base.insert_entries = mock_insert_entries;
-	ggtt->base.bind_vma = mock_bind_ggtt;
-	ggtt->base.unbind_vma = mock_unbind_ggtt;
-	ggtt->base.set_pages = ggtt_set_pages;
-	ggtt->base.clear_pages = clear_pages;
-	ggtt->base.cleanup = mock_cleanup;
-
-	i915_address_space_init(&ggtt->base, i915, "global");
+	ggtt->vm.total = 4096 * PAGE_SIZE;
+
+	ggtt->vm.clear_range = nop_clear_range;
+	ggtt->vm.insert_page = mock_insert_page;
+	ggtt->vm.insert_entries = mock_insert_entries;
+	ggtt->vm.cleanup = mock_cleanup;
+
+	ggtt->vm.vma_ops.bind_vma    = mock_bind_ggtt;
+	ggtt->vm.vma_ops.unbind_vma  = mock_unbind_ggtt;
+	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
+	ggtt->vm.vma_ops.clear_pages = clear_pages;
+
+	i915_address_space_init(&ggtt->vm, i915);
 }
 
 void mock_fini_ggtt(struct drm_i915_private *i915)
 {
 	struct i915_ggtt *ggtt = &i915->ggtt;
 
-	i915_address_space_fini(&ggtt->base);
+	i915_address_space_fini(&ggtt->vm);
 }
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/vlv_dsi.c
index f349b3920199..435a2c35ee8c 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/vlv_dsi.c
@@ -69,7 +69,7 @@ enum mipi_dsi_pixel_format pixel_format_from_register_bits(u32 fmt)
 	}
 }
 
-void wait_for_dsi_fifo_empty(struct intel_dsi *intel_dsi, enum port port)
+void vlv_dsi_wait_for_fifo_empty(struct intel_dsi *intel_dsi, enum port port)
 {
 	struct drm_encoder *encoder = &intel_dsi->base.base;
 	struct drm_device *dev = encoder->dev;
@@ -342,11 +342,15 @@ static bool intel_dsi_compute_config(struct intel_encoder *encoder,
 			pipe_config->cpu_transcoder = TRANSCODER_DSI_C;
 		else
 			pipe_config->cpu_transcoder = TRANSCODER_DSI_A;
-	}
 
-	ret = intel_compute_dsi_pll(encoder, pipe_config);
-	if (ret)
-		return false;
+		ret = bxt_dsi_pll_compute(encoder, pipe_config);
+		if (ret)
+			return false;
+	} else {
+		ret = vlv_dsi_pll_compute(encoder, pipe_config);
+		if (ret)
+			return false;
+	}
 
 	pipe_config->clock_set = true;
 
@@ -546,12 +550,12 @@ static void intel_dsi_device_ready(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		vlv_dsi_device_ready(encoder);
-	else if (IS_BROXTON(dev_priv))
-		bxt_dsi_device_ready(encoder);
-	else if (IS_GEMINILAKE(dev_priv))
+	if (IS_GEMINILAKE(dev_priv))
 		glk_dsi_device_ready(encoder);
+	else if (IS_GEN9_LP(dev_priv))
+		bxt_dsi_device_ready(encoder);
+	else
+		vlv_dsi_device_ready(encoder);
 }
 
 static void glk_dsi_enter_low_power_mode(struct intel_encoder *encoder)
@@ -810,8 +814,13 @@ static void intel_dsi_pre_enable(struct intel_encoder *encoder,
 	 * The BIOS may leave the PLL in a wonky state where it doesn't
 	 * lock. It needs to be fully powered down to fix it.
 	 */
-	intel_disable_dsi_pll(encoder);
-	intel_enable_dsi_pll(encoder, pipe_config);
+	if (IS_GEN9_LP(dev_priv)) {
+		bxt_dsi_pll_disable(encoder);
+		bxt_dsi_pll_enable(encoder, pipe_config);
+	} else {
+		vlv_dsi_pll_disable(encoder);
+		vlv_dsi_pll_enable(encoder, pipe_config);
+	}
 
 	if (IS_BROXTON(dev_priv)) {
 		/* Add MIPI IO reset programming for modeset */
@@ -929,11 +938,10 @@ static void intel_dsi_clear_device_ready(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv) ||
-	    IS_BROXTON(dev_priv))
-		vlv_dsi_clear_device_ready(encoder);
-	else if (IS_GEMINILAKE(dev_priv))
+	if (IS_GEMINILAKE(dev_priv))
 		glk_dsi_clear_device_ready(encoder);
+	else
+		vlv_dsi_clear_device_ready(encoder);
 }
 
 static void intel_dsi_post_disable(struct intel_encoder *encoder,
@@ -949,7 +957,7 @@ static void intel_dsi_post_disable(struct intel_encoder *encoder,
 
 	if (is_vid_mode(intel_dsi)) {
 		for_each_dsi_port(port, intel_dsi->ports)
-			wait_for_dsi_fifo_empty(intel_dsi, port);
+			vlv_dsi_wait_for_fifo_empty(intel_dsi, port);
 
 		intel_dsi_port_disable(encoder);
 		usleep_range(2000, 5000);
@@ -979,11 +987,13 @@ static void intel_dsi_post_disable(struct intel_encoder *encoder,
 				val & ~MIPIO_RST_CTRL);
 	}
 
-	intel_disable_dsi_pll(encoder);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
+	if (IS_GEN9_LP(dev_priv)) {
+		bxt_dsi_pll_disable(encoder);
+	} else {
 		u32 val;
 
+		vlv_dsi_pll_disable(encoder);
+
 		val = I915_READ(DSPCLK_GATE_D);
 		val &= ~DPOUNIT_CLOCK_GATE_DISABLE;
 		I915_WRITE(DSPCLK_GATE_D, val);
@@ -1024,7 +1034,7 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
 	 * configuration, otherwise accessing DSI registers will hang the
 	 * machine. See BSpec North Display Engine registers/MIPI[BXT].
 	 */
-	if (IS_GEN9_LP(dev_priv) && !intel_dsi_pll_is_enabled(dev_priv))
+	if (IS_GEN9_LP(dev_priv) && !bxt_dsi_pll_is_enabled(dev_priv))
 		goto out_put_power;
 
 	/* XXX: this only works for one DSI output */
@@ -1247,16 +1257,19 @@ static void intel_dsi_get_config(struct intel_encoder *encoder,
 
 	pipe_config->output_types |= BIT(INTEL_OUTPUT_DSI);
 
-	if (IS_GEN9_LP(dev_priv))
+	if (IS_GEN9_LP(dev_priv)) {
 		bxt_dsi_get_pipe_config(encoder, pipe_config);
+		pclk = bxt_dsi_get_pclk(encoder, pipe_config->pipe_bpp,
+					pipe_config);
+	} else {
+		pclk = vlv_dsi_get_pclk(encoder, pipe_config->pipe_bpp,
+					pipe_config);
+	}
 
-	pclk = intel_dsi_get_pclk(encoder, pipe_config->pipe_bpp,
-				  pipe_config);
-	if (!pclk)
-		return;
-
-	pipe_config->base.adjusted_mode.crtc_clock = pclk;
-	pipe_config->port_clock = pclk;
+	if (pclk) {
+		pipe_config->base.adjusted_mode.crtc_clock = pclk;
+		pipe_config->port_clock = pclk;
+	}
 }
 
 static enum drm_mode_status
@@ -1585,20 +1598,24 @@ static void intel_dsi_unprepare(struct intel_encoder *encoder)
 	enum port port;
 	u32 val;
 
-	if (!IS_GEMINILAKE(dev_priv)) {
-		for_each_dsi_port(port, intel_dsi->ports) {
-			/* Panel commands can be sent when clock is in LP11 */
-			I915_WRITE(MIPI_DEVICE_READY(port), 0x0);
+	if (IS_GEMINILAKE(dev_priv))
+		return;
 
-			intel_dsi_reset_clocks(encoder, port);
-			I915_WRITE(MIPI_EOT_DISABLE(port), CLOCKSTOP);
+	for_each_dsi_port(port, intel_dsi->ports) {
+		/* Panel commands can be sent when clock is in LP11 */
+		I915_WRITE(MIPI_DEVICE_READY(port), 0x0);
 
-			val = I915_READ(MIPI_DSI_FUNC_PRG(port));
-			val &= ~VID_MODE_FORMAT_MASK;
-			I915_WRITE(MIPI_DSI_FUNC_PRG(port), val);
+		if (IS_GEN9_LP(dev_priv))
+			bxt_dsi_reset_clocks(encoder, port);
+		else
+			vlv_dsi_reset_clocks(encoder, port);
+		I915_WRITE(MIPI_EOT_DISABLE(port), CLOCKSTOP);
 
-			I915_WRITE(MIPI_DEVICE_READY(port), 0x1);
-		}
+		val = I915_READ(MIPI_DSI_FUNC_PRG(port));
+		val &= ~VID_MODE_FORMAT_MASK;
+		I915_WRITE(MIPI_DSI_FUNC_PRG(port), val);
+
+		I915_WRITE(MIPI_DEVICE_READY(port), 0x1);
 	}
 }
 
@@ -1671,16 +1688,16 @@ static int intel_dsi_get_panel_orientation(struct intel_connector *connector)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
 	int orientation = DRM_MODE_PANEL_ORIENTATION_NORMAL;
-	enum i9xx_plane_id plane;
+	enum i9xx_plane_id i9xx_plane;
 	u32 val;
 
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		if (connector->encoder->crtc_mask == BIT(PIPE_B))
-			plane = PLANE_B;
+			i9xx_plane = PLANE_B;
 		else
-			plane = PLANE_A;
+			i9xx_plane = PLANE_A;
 
-		val = I915_READ(DSPCNTR(plane));
+		val = I915_READ(DSPCNTR(i9xx_plane));
 		if (val & DISPPLANE_ROTATE_180)
 			orientation = DRM_MODE_PANEL_ORIENTATION_BOTTOM_UP;
 	}
@@ -1713,7 +1730,7 @@ static void intel_dsi_add_properties(struct intel_connector *connector)
 	}
 }
 
-void intel_dsi_init(struct drm_i915_private *dev_priv)
+void vlv_dsi_init(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = &dev_priv->drm;
 	struct intel_dsi *intel_dsi;
@@ -1730,14 +1747,10 @@ void intel_dsi_init(struct drm_i915_private *dev_priv)
 	if (!intel_bios_is_dsi_present(dev_priv, &port))
 		return;
 
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		dev_priv->mipi_mmio_base = VLV_MIPI_BASE;
-	} else if (IS_GEN9_LP(dev_priv)) {
+	if (IS_GEN9_LP(dev_priv))
 		dev_priv->mipi_mmio_base = BXT_MIPI_BASE;
-	} else {
-		DRM_ERROR("Unsupported Mipi device to reg base");
-		return;
-	}
+	else
+		dev_priv->mipi_mmio_base = VLV_MIPI_BASE;
 
 	intel_dsi = kzalloc(sizeof(*intel_dsi), GFP_KERNEL);
 	if (!intel_dsi)
diff --git a/drivers/gpu/drm/i915/intel_dsi_pll.c b/drivers/gpu/drm/i915/vlv_dsi_pll.c
index 2ff2ee7f3b78..a132a8037ecc 100644
--- a/drivers/gpu/drm/i915/intel_dsi_pll.c
+++ b/drivers/gpu/drm/i915/vlv_dsi_pll.c
@@ -111,8 +111,8 @@ static int dsi_calc_mnp(struct drm_i915_private *dev_priv,
  * XXX: The muxing and gating is hard coded for now. Need to add support for
  * sharing PLLs with two DSI outputs.
  */
-static int vlv_compute_dsi_pll(struct intel_encoder *encoder,
-			       struct intel_crtc_state *config)
+int vlv_dsi_pll_compute(struct intel_encoder *encoder,
+			struct intel_crtc_state *config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
@@ -142,8 +142,8 @@ static int vlv_compute_dsi_pll(struct intel_encoder *encoder,
 	return 0;
 }
 
-static void vlv_enable_dsi_pll(struct intel_encoder *encoder,
-			       const struct intel_crtc_state *config)
+void vlv_dsi_pll_enable(struct intel_encoder *encoder,
+			const struct intel_crtc_state *config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
@@ -175,7 +175,7 @@ static void vlv_enable_dsi_pll(struct intel_encoder *encoder,
 	DRM_DEBUG_KMS("DSI PLL locked\n");
 }
 
-static void vlv_disable_dsi_pll(struct intel_encoder *encoder)
+void vlv_dsi_pll_disable(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	u32 tmp;
@@ -192,7 +192,7 @@ static void vlv_disable_dsi_pll(struct intel_encoder *encoder)
 	mutex_unlock(&dev_priv->sb_lock);
 }
 
-static bool bxt_dsi_pll_is_enabled(struct drm_i915_private *dev_priv)
+bool bxt_dsi_pll_is_enabled(struct drm_i915_private *dev_priv)
 {
 	bool enabled;
 	u32 val;
@@ -229,7 +229,7 @@ static bool bxt_dsi_pll_is_enabled(struct drm_i915_private *dev_priv)
 	return enabled;
 }
 
-static void bxt_disable_dsi_pll(struct intel_encoder *encoder)
+void bxt_dsi_pll_disable(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	u32 val;
@@ -261,8 +261,8 @@ static void assert_bpp_mismatch(enum mipi_dsi_pixel_format fmt, int pipe_bpp)
 	     bpp, pipe_bpp);
 }
 
-static u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
-			    struct intel_crtc_state *config)
+u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
+		     struct intel_crtc_state *config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
@@ -327,8 +327,8 @@ static u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
 	return pclk;
 }
 
-static u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
-			    struct intel_crtc_state *config)
+u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
+		     struct intel_crtc_state *config)
 {
 	u32 pclk;
 	u32 dsi_clk;
@@ -357,16 +357,7 @@ static u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
 	return pclk;
 }
 
-u32 intel_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
-		       struct intel_crtc_state *config)
-{
-	if (IS_GEN9_LP(to_i915(encoder->base.dev)))
-		return bxt_dsi_get_pclk(encoder, pipe_bpp, config);
-	else
-		return vlv_dsi_get_pclk(encoder, pipe_bpp, config);
-}
-
-static void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
+void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
 {
 	u32 temp;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
@@ -480,8 +471,8 @@ static void bxt_dsi_program_clocks(struct drm_device *dev, enum port port,
 	I915_WRITE(BXT_MIPI_CLOCK_CTL, tmp);
 }
 
-static int gen9lp_compute_dsi_pll(struct intel_encoder *encoder,
-			       struct intel_crtc_state *config)
+int bxt_dsi_pll_compute(struct intel_encoder *encoder,
+			struct intel_crtc_state *config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
@@ -528,8 +519,8 @@ static int gen9lp_compute_dsi_pll(struct intel_encoder *encoder,
 	return 0;
 }
 
-static void gen9lp_enable_dsi_pll(struct intel_encoder *encoder,
-			       const struct intel_crtc_state *config)
+void bxt_dsi_pll_enable(struct intel_encoder *encoder,
+			const struct intel_crtc_state *config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
@@ -568,52 +559,7 @@ static void gen9lp_enable_dsi_pll(struct intel_encoder *encoder,
 	DRM_DEBUG_KMS("DSI PLL locked\n");
 }
 
-bool intel_dsi_pll_is_enabled(struct drm_i915_private *dev_priv)
-{
-	if (IS_GEN9_LP(dev_priv))
-		return bxt_dsi_pll_is_enabled(dev_priv);
-
-	MISSING_CASE(INTEL_DEVID(dev_priv));
-
-	return false;
-}
-
-int intel_compute_dsi_pll(struct intel_encoder *encoder,
-			  struct intel_crtc_state *config)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		return vlv_compute_dsi_pll(encoder, config);
-	else if (IS_GEN9_LP(dev_priv))
-		return gen9lp_compute_dsi_pll(encoder, config);
-
-	return -ENODEV;
-}
-
-void intel_enable_dsi_pll(struct intel_encoder *encoder,
-			  const struct intel_crtc_state *config)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		vlv_enable_dsi_pll(encoder, config);
-	else if (IS_GEN9_LP(dev_priv))
-		gen9lp_enable_dsi_pll(encoder, config);
-}
-
-void intel_disable_dsi_pll(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		vlv_disable_dsi_pll(encoder);
-	else if (IS_GEN9_LP(dev_priv))
-		bxt_disable_dsi_pll(encoder);
-}
-
-static void gen9lp_dsi_reset_clocks(struct intel_encoder *encoder,
-				    enum port port)
+void bxt_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
 {
 	u32 tmp;
 	struct drm_device *dev = encoder->base.dev;
@@ -638,13 +584,3 @@ static void gen9lp_dsi_reset_clocks(struct intel_encoder *encoder,
 	}
 	I915_WRITE(MIPI_EOT_DISABLE(port), CLOCKSTOP);
 }
-
-void intel_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (IS_GEN9_LP(dev_priv))
-		gen9lp_dsi_reset_clocks(encoder, port);
-	else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		vlv_dsi_reset_clocks(encoder, port);
-}
diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index 1d053bbefc02..5ea0c82f9957 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -35,12 +35,6 @@
 
 #define MAX_CRTC	4
 
-struct imx_drm_device {
-	struct drm_device			*drm;
-	unsigned int				pipes;
-	struct drm_atomic_state			*state;
-};
-
 #if IS_ENABLED(CONFIG_DRM_FBDEV_EMULATION)
 static int legacyfb_depth = 16;
 module_param(legacyfb_depth, int, 0444);
@@ -219,22 +213,12 @@ static int compare_of(struct device *dev, void *data)
 static int imx_drm_bind(struct device *dev)
 {
 	struct drm_device *drm;
-	struct imx_drm_device *imxdrm;
 	int ret;
 
 	drm = drm_dev_alloc(&imx_drm_driver, dev);
 	if (IS_ERR(drm))
 		return PTR_ERR(drm);
 
-	imxdrm = devm_kzalloc(dev, sizeof(*imxdrm), GFP_KERNEL);
-	if (!imxdrm) {
-		ret = -ENOMEM;
-		goto err_unref;
-	}
-
-	imxdrm->drm = drm;
-	drm->dev_private = imxdrm;
-
 	/*
 	 * enable drm irq mode.
 	 * - with irq_enabled = true, we can use the vblank feature.
@@ -306,8 +290,7 @@ err_unbind:
 	component_unbind_all(drm->dev, drm);
 err_kms:
 	drm_mode_config_cleanup(drm);
-err_unref:
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 
 	return ret;
 }
@@ -327,7 +310,7 @@ static void imx_drm_unbind(struct device *dev)
 	component_unbind_all(drm->dev, drm);
 	dev_set_drvdata(dev, NULL);
 
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 }
 
 static const struct component_master_ops imx_drm_ops = {
@@ -355,37 +338,15 @@ static int imx_drm_platform_remove(struct platform_device *pdev)
 static int imx_drm_suspend(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
-	struct imx_drm_device *imxdrm;
-
-	/* The drm_dev is NULL before .load hook is called */
-	if (drm_dev == NULL)
-		return 0;
-
-	drm_kms_helper_poll_disable(drm_dev);
 
-	imxdrm = drm_dev->dev_private;
-	imxdrm->state = drm_atomic_helper_suspend(drm_dev);
-	if (IS_ERR(imxdrm->state)) {
-		drm_kms_helper_poll_enable(drm_dev);
-		return PTR_ERR(imxdrm->state);
-	}
-
-	return 0;
+	return drm_mode_config_helper_suspend(drm_dev);
 }
 
 static int imx_drm_resume(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
-	struct imx_drm_device *imx_drm;
 
-	if (drm_dev == NULL)
-		return 0;
-
-	imx_drm = drm_dev->dev_private;
-	drm_atomic_helper_resume(drm_dev, imx_drm->state);
-	drm_kms_helper_poll_enable(drm_dev);
-
-	return 0;
+	return drm_mode_config_helper_resume(drm_dev);
 }
 #endif
 
diff --git a/drivers/gpu/drm/imx/imx-drm.h b/drivers/gpu/drm/imx/imx-drm.h
index 15c2bec47a04..ab9c6f706eb3 100644
--- a/drivers/gpu/drm/imx/imx-drm.h
+++ b/drivers/gpu/drm/imx/imx-drm.h
@@ -10,7 +10,6 @@ struct drm_display_mode;
 struct drm_encoder;
 struct drm_framebuffer;
 struct drm_plane;
-struct imx_drm_crtc;
 struct platform_device;
 
 struct imx_crtc_state {
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index dd5312b02a8d..3bd0f8a18e74 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -143,7 +143,7 @@ static int imx_ldb_connector_get_modes(struct drm_connector *connector)
 		imx_ldb_ch->edid = drm_get_edid(connector, imx_ldb_ch->ddc);
 
 	if (imx_ldb_ch->edid) {
-		drm_mode_connector_update_edid_property(connector,
+		drm_connector_update_edid_property(connector,
 							imx_ldb_ch->edid);
 		num_modes = drm_add_edid_modes(connector, imx_ldb_ch->edid);
 	}
@@ -471,8 +471,7 @@ static int imx_ldb_register(struct drm_device *drm,
 		drm_connector_init(drm, &imx_ldb_ch->connector,
 				&imx_ldb_connector_funcs,
 				DRM_MODE_CONNECTOR_LVDS);
-		drm_mode_connector_attach_encoder(&imx_ldb_ch->connector,
-				encoder);
+		drm_connector_attach_encoder(&imx_ldb_ch->connector, encoder);
 	}
 
 	if (imx_ldb_ch->panel) {
diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c
index bc27c2699464..cffd3310240e 100644
--- a/drivers/gpu/drm/imx/imx-tve.c
+++ b/drivers/gpu/drm/imx/imx-tve.c
@@ -235,7 +235,7 @@ static int imx_tve_connector_get_modes(struct drm_connector *connector)
 
 	edid = drm_get_edid(connector, tve->ddc);
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 	}
@@ -493,7 +493,7 @@ static int imx_tve_register(struct drm_device *drm, struct imx_tve *tve)
 	drm_connector_init(drm, &tve->connector, &imx_tve_connector_funcs,
 			   DRM_MODE_CONNECTOR_VGA);
 
-	drm_mode_connector_attach_encoder(&tve->connector, &tve->encoder);
+	drm_connector_attach_encoder(&tve->connector, &tve->encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index e83af0f2be86..7d4b710b837a 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -35,7 +35,6 @@
 struct ipu_crtc {
 	struct device		*dev;
 	struct drm_crtc		base;
-	struct imx_drm_crtc	*imx_crtc;
 
 	/* plane[0] is the full plane, plane[1] is the partial plane */
 	struct ipu_plane	*plane[2];
@@ -213,7 +212,7 @@ static bool ipu_crtc_mode_fixup(struct drm_crtc *crtc,
 static int ipu_crtc_atomic_check(struct drm_crtc *crtc,
 				 struct drm_crtc_state *state)
 {
-	u32 primary_plane_mask = 1 << drm_plane_index(crtc->primary);
+	u32 primary_plane_mask = drm_plane_mask(crtc->primary);
 
 	if (state->active && (primary_plane_mask & state->plane_mask) == 0)
 		return -EINVAL;
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index aedecda9728a..aefd04e18f93 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -63,7 +63,7 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector)
 	}
 
 	if (imxpd->edid) {
-		drm_mode_connector_update_edid_property(connector, imxpd->edid);
+		drm_connector_update_edid_property(connector, imxpd->edid);
 		num_modes = drm_add_edid_modes(connector, imxpd->edid);
 	}
 
@@ -197,7 +197,7 @@ static int imx_pd_register(struct drm_device *drm,
 			return ret;
 		}
 	} else {
-		drm_mode_connector_attach_encoder(&imxpd->connector, encoder);
+		drm_connector_attach_encoder(&imxpd->connector, encoder);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index 658b8dd45b83..2d6aa150a9ff 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -539,6 +539,9 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 	int ret;
 	int i;
 
+	if (!path)
+		return 0;
+
 	for (i = 0; i < path_len; i++) {
 		enum mtk_ddp_comp_id comp_id = path[i];
 		struct device_node *node;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index 8130f3dab661..87e4191c250e 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -28,8 +28,12 @@
 #define DISP_REG_CONFIG_DISP_UFOE_MOUT_EN	0x050
 #define DISP_REG_CONFIG_DISP_COLOR0_SEL_IN	0x084
 #define DISP_REG_CONFIG_DISP_COLOR1_SEL_IN	0x088
+#define DISP_REG_CONFIG_DSIE_SEL_IN		0x0a4
+#define DISP_REG_CONFIG_DSIO_SEL_IN		0x0a8
 #define DISP_REG_CONFIG_DPI_SEL_IN		0x0ac
-#define DISP_REG_CONFIG_DISP_RDMA1_MOUT_EN	0x0c8
+#define DISP_REG_CONFIG_DISP_RDMA2_SOUT		0x0b8
+#define DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN	0x0c4
+#define DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN	0x0c8
 #define DISP_REG_CONFIG_MMSYS_CG_CON0		0x100
 
 #define DISP_REG_CONFIG_DISP_OVL_MOUT_EN	0x030
@@ -41,45 +45,89 @@
 #define DISP_REG_MUTEX_RST(n)	(0x28 + 0x20 * (n))
 #define DISP_REG_MUTEX_MOD(n)	(0x2c + 0x20 * (n))
 #define DISP_REG_MUTEX_SOF(n)	(0x30 + 0x20 * (n))
+#define DISP_REG_MUTEX_MOD2(n)	(0x34 + 0x20 * (n))
 
 #define INT_MUTEX				BIT(1)
 
-#define MT8173_MUTEX_MOD_DISP_OVL0		BIT(11)
-#define MT8173_MUTEX_MOD_DISP_OVL1		BIT(12)
-#define MT8173_MUTEX_MOD_DISP_RDMA0		BIT(13)
-#define MT8173_MUTEX_MOD_DISP_RDMA1		BIT(14)
-#define MT8173_MUTEX_MOD_DISP_RDMA2		BIT(15)
-#define MT8173_MUTEX_MOD_DISP_WDMA0		BIT(16)
-#define MT8173_MUTEX_MOD_DISP_WDMA1		BIT(17)
-#define MT8173_MUTEX_MOD_DISP_COLOR0		BIT(18)
-#define MT8173_MUTEX_MOD_DISP_COLOR1		BIT(19)
-#define MT8173_MUTEX_MOD_DISP_AAL		BIT(20)
-#define MT8173_MUTEX_MOD_DISP_GAMMA		BIT(21)
-#define MT8173_MUTEX_MOD_DISP_UFOE		BIT(22)
-#define MT8173_MUTEX_MOD_DISP_PWM0		BIT(23)
-#define MT8173_MUTEX_MOD_DISP_PWM1		BIT(24)
-#define MT8173_MUTEX_MOD_DISP_OD		BIT(25)
-
-#define MT2701_MUTEX_MOD_DISP_OVL		BIT(3)
-#define MT2701_MUTEX_MOD_DISP_WDMA		BIT(6)
-#define MT2701_MUTEX_MOD_DISP_COLOR		BIT(7)
-#define MT2701_MUTEX_MOD_DISP_BLS		BIT(9)
-#define MT2701_MUTEX_MOD_DISP_RDMA0		BIT(10)
-#define MT2701_MUTEX_MOD_DISP_RDMA1		BIT(12)
+#define MT8173_MUTEX_MOD_DISP_OVL0		11
+#define MT8173_MUTEX_MOD_DISP_OVL1		12
+#define MT8173_MUTEX_MOD_DISP_RDMA0		13
+#define MT8173_MUTEX_MOD_DISP_RDMA1		14
+#define MT8173_MUTEX_MOD_DISP_RDMA2		15
+#define MT8173_MUTEX_MOD_DISP_WDMA0		16
+#define MT8173_MUTEX_MOD_DISP_WDMA1		17
+#define MT8173_MUTEX_MOD_DISP_COLOR0		18
+#define MT8173_MUTEX_MOD_DISP_COLOR1		19
+#define MT8173_MUTEX_MOD_DISP_AAL		20
+#define MT8173_MUTEX_MOD_DISP_GAMMA		21
+#define MT8173_MUTEX_MOD_DISP_UFOE		22
+#define MT8173_MUTEX_MOD_DISP_PWM0		23
+#define MT8173_MUTEX_MOD_DISP_PWM1		24
+#define MT8173_MUTEX_MOD_DISP_OD		25
+
+#define MT2712_MUTEX_MOD_DISP_PWM2		10
+#define MT2712_MUTEX_MOD_DISP_OVL0		11
+#define MT2712_MUTEX_MOD_DISP_OVL1		12
+#define MT2712_MUTEX_MOD_DISP_RDMA0		13
+#define MT2712_MUTEX_MOD_DISP_RDMA1		14
+#define MT2712_MUTEX_MOD_DISP_RDMA2		15
+#define MT2712_MUTEX_MOD_DISP_WDMA0		16
+#define MT2712_MUTEX_MOD_DISP_WDMA1		17
+#define MT2712_MUTEX_MOD_DISP_COLOR0		18
+#define MT2712_MUTEX_MOD_DISP_COLOR1		19
+#define MT2712_MUTEX_MOD_DISP_AAL0		20
+#define MT2712_MUTEX_MOD_DISP_UFOE		22
+#define MT2712_MUTEX_MOD_DISP_PWM0		23
+#define MT2712_MUTEX_MOD_DISP_PWM1		24
+#define MT2712_MUTEX_MOD_DISP_OD0		25
+#define MT2712_MUTEX_MOD2_DISP_AAL1		33
+#define MT2712_MUTEX_MOD2_DISP_OD1		34
+
+#define MT2701_MUTEX_MOD_DISP_OVL		3
+#define MT2701_MUTEX_MOD_DISP_WDMA		6
+#define MT2701_MUTEX_MOD_DISP_COLOR		7
+#define MT2701_MUTEX_MOD_DISP_BLS		9
+#define MT2701_MUTEX_MOD_DISP_RDMA0		10
+#define MT2701_MUTEX_MOD_DISP_RDMA1		12
 
 #define MUTEX_SOF_SINGLE_MODE		0
 #define MUTEX_SOF_DSI0			1
 #define MUTEX_SOF_DSI1			2
 #define MUTEX_SOF_DPI0			3
+#define MUTEX_SOF_DPI1			4
+#define MUTEX_SOF_DSI2			5
+#define MUTEX_SOF_DSI3			6
 
 #define OVL0_MOUT_EN_COLOR0		0x1
 #define OD_MOUT_EN_RDMA0		0x1
+#define OD1_MOUT_EN_RDMA1		BIT(16)
 #define UFOE_MOUT_EN_DSI0		0x1
 #define COLOR0_SEL_IN_OVL0		0x1
 #define OVL1_MOUT_EN_COLOR1		0x1
 #define GAMMA_MOUT_EN_RDMA1		0x1
-#define RDMA1_MOUT_DPI0			0x2
+#define RDMA0_SOUT_DPI0			0x2
+#define RDMA0_SOUT_DSI2			0x4
+#define RDMA0_SOUT_DSI3			0x5
+#define RDMA1_SOUT_DPI0			0x2
+#define RDMA1_SOUT_DPI1			0x3
+#define RDMA1_SOUT_DSI1			0x1
+#define RDMA1_SOUT_DSI2			0x4
+#define RDMA1_SOUT_DSI3			0x5
+#define RDMA2_SOUT_DPI0			0x2
+#define RDMA2_SOUT_DPI1			0x3
+#define RDMA2_SOUT_DSI1			0x1
+#define RDMA2_SOUT_DSI2			0x4
+#define RDMA2_SOUT_DSI3			0x5
 #define DPI0_SEL_IN_RDMA1		0x1
+#define DPI0_SEL_IN_RDMA2		0x3
+#define DPI1_SEL_IN_RDMA1		(0x1 << 8)
+#define DPI1_SEL_IN_RDMA2		(0x3 << 8)
+#define DSI1_SEL_IN_RDMA1		0x1
+#define DSI1_SEL_IN_RDMA2		0x4
+#define DSI2_SEL_IN_RDMA1		(0x1 << 16)
+#define DSI2_SEL_IN_RDMA2		(0x4 << 16)
+#define DSI3_SEL_IN_RDMA1		(0x1 << 16)
+#define DSI3_SEL_IN_RDMA2		(0x4 << 16)
 #define COLOR1_SEL_IN_OVL1		0x1
 
 #define OVL_MOUT_EN_RDMA		0x1
@@ -108,12 +156,32 @@ static const unsigned int mt2701_mutex_mod[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_WDMA0] = MT2701_MUTEX_MOD_DISP_WDMA,
 };
 
+static const unsigned int mt2712_mutex_mod[DDP_COMPONENT_ID_MAX] = {
+	[DDP_COMPONENT_AAL0] = MT2712_MUTEX_MOD_DISP_AAL0,
+	[DDP_COMPONENT_AAL1] = MT2712_MUTEX_MOD2_DISP_AAL1,
+	[DDP_COMPONENT_COLOR0] = MT2712_MUTEX_MOD_DISP_COLOR0,
+	[DDP_COMPONENT_COLOR1] = MT2712_MUTEX_MOD_DISP_COLOR1,
+	[DDP_COMPONENT_OD0] = MT2712_MUTEX_MOD_DISP_OD0,
+	[DDP_COMPONENT_OD1] = MT2712_MUTEX_MOD2_DISP_OD1,
+	[DDP_COMPONENT_OVL0] = MT2712_MUTEX_MOD_DISP_OVL0,
+	[DDP_COMPONENT_OVL1] = MT2712_MUTEX_MOD_DISP_OVL1,
+	[DDP_COMPONENT_PWM0] = MT2712_MUTEX_MOD_DISP_PWM0,
+	[DDP_COMPONENT_PWM1] = MT2712_MUTEX_MOD_DISP_PWM1,
+	[DDP_COMPONENT_PWM2] = MT2712_MUTEX_MOD_DISP_PWM2,
+	[DDP_COMPONENT_RDMA0] = MT2712_MUTEX_MOD_DISP_RDMA0,
+	[DDP_COMPONENT_RDMA1] = MT2712_MUTEX_MOD_DISP_RDMA1,
+	[DDP_COMPONENT_RDMA2] = MT2712_MUTEX_MOD_DISP_RDMA2,
+	[DDP_COMPONENT_UFOE] = MT2712_MUTEX_MOD_DISP_UFOE,
+	[DDP_COMPONENT_WDMA0] = MT2712_MUTEX_MOD_DISP_WDMA0,
+	[DDP_COMPONENT_WDMA1] = MT2712_MUTEX_MOD_DISP_WDMA1,
+};
+
 static const unsigned int mt8173_mutex_mod[DDP_COMPONENT_ID_MAX] = {
-	[DDP_COMPONENT_AAL] = MT8173_MUTEX_MOD_DISP_AAL,
+	[DDP_COMPONENT_AAL0] = MT8173_MUTEX_MOD_DISP_AAL,
 	[DDP_COMPONENT_COLOR0] = MT8173_MUTEX_MOD_DISP_COLOR0,
 	[DDP_COMPONENT_COLOR1] = MT8173_MUTEX_MOD_DISP_COLOR1,
 	[DDP_COMPONENT_GAMMA] = MT8173_MUTEX_MOD_DISP_GAMMA,
-	[DDP_COMPONENT_OD] = MT8173_MUTEX_MOD_DISP_OD,
+	[DDP_COMPONENT_OD0] = MT8173_MUTEX_MOD_DISP_OD,
 	[DDP_COMPONENT_OVL0] = MT8173_MUTEX_MOD_DISP_OVL0,
 	[DDP_COMPONENT_OVL1] = MT8173_MUTEX_MOD_DISP_OVL1,
 	[DDP_COMPONENT_PWM0] = MT8173_MUTEX_MOD_DISP_PWM0,
@@ -138,7 +206,7 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_OVL0 && next == DDP_COMPONENT_RDMA0) {
 		*addr = DISP_REG_CONFIG_DISP_OVL_MOUT_EN;
 		value = OVL_MOUT_EN_RDMA;
-	} else if (cur == DDP_COMPONENT_OD && next == DDP_COMPONENT_RDMA0) {
+	} else if (cur == DDP_COMPONENT_OD0 && next == DDP_COMPONENT_RDMA0) {
 		*addr = DISP_REG_CONFIG_DISP_OD_MOUT_EN;
 		value = OD_MOUT_EN_RDMA0;
 	} else if (cur == DDP_COMPONENT_UFOE && next == DDP_COMPONENT_DSI0) {
@@ -150,9 +218,48 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_GAMMA && next == DDP_COMPONENT_RDMA1) {
 		*addr = DISP_REG_CONFIG_DISP_GAMMA_MOUT_EN;
 		value = GAMMA_MOUT_EN_RDMA1;
+	} else if (cur == DDP_COMPONENT_OD1 && next == DDP_COMPONENT_RDMA1) {
+		*addr = DISP_REG_CONFIG_DISP_OD_MOUT_EN;
+		value = OD1_MOUT_EN_RDMA1;
+	} else if (cur == DDP_COMPONENT_RDMA0 && next == DDP_COMPONENT_DPI0) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN;
+		value = RDMA0_SOUT_DPI0;
+	} else if (cur == DDP_COMPONENT_RDMA0 && next == DDP_COMPONENT_DSI2) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN;
+		value = RDMA0_SOUT_DSI2;
+	} else if (cur == DDP_COMPONENT_RDMA0 && next == DDP_COMPONENT_DSI3) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN;
+		value = RDMA0_SOUT_DSI3;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI1) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
+		value = RDMA1_SOUT_DSI1;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI2) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
+		value = RDMA1_SOUT_DSI2;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI3) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
+		value = RDMA1_SOUT_DSI3;
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI0) {
-		*addr = DISP_REG_CONFIG_DISP_RDMA1_MOUT_EN;
-		value = RDMA1_MOUT_DPI0;
+		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
+		value = RDMA1_SOUT_DPI0;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI1) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
+		value = RDMA1_SOUT_DPI1;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DPI0) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA2_SOUT;
+		value = RDMA2_SOUT_DPI0;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DPI1) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA2_SOUT;
+		value = RDMA2_SOUT_DPI1;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI1) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA2_SOUT;
+		value = RDMA2_SOUT_DSI1;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI2) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA2_SOUT;
+		value = RDMA2_SOUT_DSI2;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI3) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA2_SOUT;
+		value = RDMA2_SOUT_DSI3;
 	} else {
 		value = 0;
 	}
@@ -172,6 +279,33 @@ static unsigned int mtk_ddp_sel_in(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI0) {
 		*addr = DISP_REG_CONFIG_DPI_SEL_IN;
 		value = DPI0_SEL_IN_RDMA1;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI1) {
+		*addr = DISP_REG_CONFIG_DPI_SEL_IN;
+		value = DPI1_SEL_IN_RDMA1;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI1) {
+		*addr = DISP_REG_CONFIG_DSIO_SEL_IN;
+		value = DSI1_SEL_IN_RDMA1;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI2) {
+		*addr = DISP_REG_CONFIG_DSIE_SEL_IN;
+		value = DSI2_SEL_IN_RDMA1;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI3) {
+		*addr = DISP_REG_CONFIG_DSIO_SEL_IN;
+		value = DSI3_SEL_IN_RDMA1;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DPI0) {
+		*addr = DISP_REG_CONFIG_DPI_SEL_IN;
+		value = DPI0_SEL_IN_RDMA2;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DPI1) {
+		*addr = DISP_REG_CONFIG_DPI_SEL_IN;
+		value = DPI1_SEL_IN_RDMA2;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI1) {
+		*addr = DISP_REG_CONFIG_DSIE_SEL_IN;
+		value = DSI1_SEL_IN_RDMA2;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI2) {
+		*addr = DISP_REG_CONFIG_DSIE_SEL_IN;
+		value = DSI2_SEL_IN_RDMA2;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI3) {
+		*addr = DISP_REG_CONFIG_DSIE_SEL_IN;
+		value = DSI3_SEL_IN_RDMA2;
 	} else if (cur == DDP_COMPONENT_OVL1 && next == DDP_COMPONENT_COLOR1) {
 		*addr = DISP_REG_CONFIG_DISP_COLOR1_SEL_IN;
 		value = COLOR1_SEL_IN_OVL1;
@@ -278,6 +412,7 @@ void mtk_disp_mutex_add_comp(struct mtk_disp_mutex *mutex,
 	struct mtk_ddp *ddp = container_of(mutex, struct mtk_ddp,
 					   mutex[mutex->id]);
 	unsigned int reg;
+	unsigned int offset;
 
 	WARN_ON(&ddp->mutex[mutex->id] != mutex);
 
@@ -288,13 +423,30 @@ void mtk_disp_mutex_add_comp(struct mtk_disp_mutex *mutex,
 	case DDP_COMPONENT_DSI1:
 		reg = MUTEX_SOF_DSI0;
 		break;
+	case DDP_COMPONENT_DSI2:
+		reg = MUTEX_SOF_DSI2;
+		break;
+	case DDP_COMPONENT_DSI3:
+		reg = MUTEX_SOF_DSI3;
+		break;
 	case DDP_COMPONENT_DPI0:
 		reg = MUTEX_SOF_DPI0;
 		break;
+	case DDP_COMPONENT_DPI1:
+		reg = MUTEX_SOF_DPI1;
+		break;
 	default:
-		reg = readl_relaxed(ddp->regs + DISP_REG_MUTEX_MOD(mutex->id));
-		reg |= ddp->mutex_mod[id];
-		writel_relaxed(reg, ddp->regs + DISP_REG_MUTEX_MOD(mutex->id));
+		if (ddp->mutex_mod[id] < 32) {
+			offset = DISP_REG_MUTEX_MOD(mutex->id);
+			reg = readl_relaxed(ddp->regs + offset);
+			reg |= 1 << ddp->mutex_mod[id];
+			writel_relaxed(reg, ddp->regs + offset);
+		} else {
+			offset = DISP_REG_MUTEX_MOD2(mutex->id);
+			reg = readl_relaxed(ddp->regs + offset);
+			reg |= 1 << (ddp->mutex_mod[id] - 32);
+			writel_relaxed(reg, ddp->regs + offset);
+		}
 		return;
 	}
 
@@ -307,20 +459,32 @@ void mtk_disp_mutex_remove_comp(struct mtk_disp_mutex *mutex,
 	struct mtk_ddp *ddp = container_of(mutex, struct mtk_ddp,
 					   mutex[mutex->id]);
 	unsigned int reg;
+	unsigned int offset;
 
 	WARN_ON(&ddp->mutex[mutex->id] != mutex);
 
 	switch (id) {
 	case DDP_COMPONENT_DSI0:
 	case DDP_COMPONENT_DSI1:
+	case DDP_COMPONENT_DSI2:
+	case DDP_COMPONENT_DSI3:
 	case DDP_COMPONENT_DPI0:
+	case DDP_COMPONENT_DPI1:
 		writel_relaxed(MUTEX_SOF_SINGLE_MODE,
 			       ddp->regs + DISP_REG_MUTEX_SOF(mutex->id));
 		break;
 	default:
-		reg = readl_relaxed(ddp->regs + DISP_REG_MUTEX_MOD(mutex->id));
-		reg &= ~(ddp->mutex_mod[id]);
-		writel_relaxed(reg, ddp->regs + DISP_REG_MUTEX_MOD(mutex->id));
+		if (ddp->mutex_mod[id] < 32) {
+			offset = DISP_REG_MUTEX_MOD(mutex->id);
+			reg = readl_relaxed(ddp->regs + offset);
+			reg &= ~(1 << ddp->mutex_mod[id]);
+			writel_relaxed(reg, ddp->regs + offset);
+		} else {
+			offset = DISP_REG_MUTEX_MOD2(mutex->id);
+			reg = readl_relaxed(ddp->regs + offset);
+			reg &= ~(1 << (ddp->mutex_mod[id] - 32));
+			writel_relaxed(reg, ddp->regs + offset);
+		}
 		break;
 	}
 }
@@ -407,6 +571,7 @@ static int mtk_ddp_remove(struct platform_device *pdev)
 
 static const struct of_device_id ddp_driver_dt_match[] = {
 	{ .compatible = "mediatek,mt2701-disp-mutex", .data = mt2701_mutex_mod},
+	{ .compatible = "mediatek,mt2712-disp-mutex", .data = mt2712_mutex_mod},
 	{ .compatible = "mediatek,mt8173-disp-mutex", .data = mt8173_mutex_mod},
 	{},
 };
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index 4672317e3ad1..ff974d82a4a6 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -218,18 +218,25 @@ struct mtk_ddp_comp_match {
 };
 
 static const struct mtk_ddp_comp_match mtk_ddp_matches[DDP_COMPONENT_ID_MAX] = {
-	[DDP_COMPONENT_AAL]	= { MTK_DISP_AAL,	0, &ddp_aal },
+	[DDP_COMPONENT_AAL0]	= { MTK_DISP_AAL,	0, &ddp_aal },
+	[DDP_COMPONENT_AAL1]	= { MTK_DISP_AAL,	1, &ddp_aal },
 	[DDP_COMPONENT_BLS]	= { MTK_DISP_BLS,	0, NULL },
 	[DDP_COMPONENT_COLOR0]	= { MTK_DISP_COLOR,	0, NULL },
 	[DDP_COMPONENT_COLOR1]	= { MTK_DISP_COLOR,	1, NULL },
 	[DDP_COMPONENT_DPI0]	= { MTK_DPI,		0, NULL },
+	[DDP_COMPONENT_DPI1]	= { MTK_DPI,		1, NULL },
 	[DDP_COMPONENT_DSI0]	= { MTK_DSI,		0, NULL },
 	[DDP_COMPONENT_DSI1]	= { MTK_DSI,		1, NULL },
+	[DDP_COMPONENT_DSI2]	= { MTK_DSI,		2, NULL },
+	[DDP_COMPONENT_DSI3]	= { MTK_DSI,		3, NULL },
 	[DDP_COMPONENT_GAMMA]	= { MTK_DISP_GAMMA,	0, &ddp_gamma },
-	[DDP_COMPONENT_OD]	= { MTK_DISP_OD,	0, &ddp_od },
+	[DDP_COMPONENT_OD0]	= { MTK_DISP_OD,	0, &ddp_od },
+	[DDP_COMPONENT_OD1]	= { MTK_DISP_OD,	1, &ddp_od },
 	[DDP_COMPONENT_OVL0]	= { MTK_DISP_OVL,	0, NULL },
 	[DDP_COMPONENT_OVL1]	= { MTK_DISP_OVL,	1, NULL },
 	[DDP_COMPONENT_PWM0]	= { MTK_DISP_PWM,	0, NULL },
+	[DDP_COMPONENT_PWM1]	= { MTK_DISP_PWM,	1, NULL },
+	[DDP_COMPONENT_PWM2]	= { MTK_DISP_PWM,	2, NULL },
 	[DDP_COMPONENT_RDMA0]	= { MTK_DISP_RDMA,	0, NULL },
 	[DDP_COMPONENT_RDMA1]	= { MTK_DISP_RDMA,	1, NULL },
 	[DDP_COMPONENT_RDMA2]	= { MTK_DISP_RDMA,	2, NULL },
@@ -271,7 +278,11 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node,
 
 	if (comp_id == DDP_COMPONENT_BLS ||
 	    comp_id == DDP_COMPONENT_DPI0 ||
+	    comp_id == DDP_COMPONENT_DPI1 ||
 	    comp_id == DDP_COMPONENT_DSI0 ||
+	    comp_id == DDP_COMPONENT_DSI1 ||
+	    comp_id == DDP_COMPONENT_DSI2 ||
+	    comp_id == DDP_COMPONENT_DSI3 ||
 	    comp_id == DDP_COMPONENT_PWM0) {
 		comp->regs = NULL;
 		comp->clk = NULL;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
index 0828cf8bf85c..7413ffeb3c9d 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
@@ -41,19 +41,25 @@ enum mtk_ddp_comp_type {
 };
 
 enum mtk_ddp_comp_id {
-	DDP_COMPONENT_AAL,
+	DDP_COMPONENT_AAL0,
+	DDP_COMPONENT_AAL1,
 	DDP_COMPONENT_BLS,
 	DDP_COMPONENT_COLOR0,
 	DDP_COMPONENT_COLOR1,
 	DDP_COMPONENT_DPI0,
+	DDP_COMPONENT_DPI1,
 	DDP_COMPONENT_DSI0,
 	DDP_COMPONENT_DSI1,
+	DDP_COMPONENT_DSI2,
+	DDP_COMPONENT_DSI3,
 	DDP_COMPONENT_GAMMA,
-	DDP_COMPONENT_OD,
+	DDP_COMPONENT_OD0,
+	DDP_COMPONENT_OD1,
 	DDP_COMPONENT_OVL0,
 	DDP_COMPONENT_OVL1,
 	DDP_COMPONENT_PWM0,
 	DDP_COMPONENT_PWM1,
+	DDP_COMPONENT_PWM2,
 	DDP_COMPONENT_RDMA0,
 	DDP_COMPONENT_RDMA1,
 	DDP_COMPONENT_RDMA2,
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index a2ca90fc403c..39721119713b 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -146,11 +146,37 @@ static const enum mtk_ddp_comp_id mt2701_mtk_ddp_ext[] = {
 	DDP_COMPONENT_DPI0,
 };
 
+static const enum mtk_ddp_comp_id mt2712_mtk_ddp_main[] = {
+	DDP_COMPONENT_OVL0,
+	DDP_COMPONENT_COLOR0,
+	DDP_COMPONENT_AAL0,
+	DDP_COMPONENT_OD0,
+	DDP_COMPONENT_RDMA0,
+	DDP_COMPONENT_DPI0,
+	DDP_COMPONENT_PWM0,
+};
+
+static const enum mtk_ddp_comp_id mt2712_mtk_ddp_ext[] = {
+	DDP_COMPONENT_OVL1,
+	DDP_COMPONENT_COLOR1,
+	DDP_COMPONENT_AAL1,
+	DDP_COMPONENT_OD1,
+	DDP_COMPONENT_RDMA1,
+	DDP_COMPONENT_DPI1,
+	DDP_COMPONENT_PWM1,
+};
+
+static const enum mtk_ddp_comp_id mt2712_mtk_ddp_third[] = {
+	DDP_COMPONENT_RDMA2,
+	DDP_COMPONENT_DSI3,
+	DDP_COMPONENT_PWM2,
+};
+
 static const enum mtk_ddp_comp_id mt8173_mtk_ddp_main[] = {
 	DDP_COMPONENT_OVL0,
 	DDP_COMPONENT_COLOR0,
-	DDP_COMPONENT_AAL,
-	DDP_COMPONENT_OD,
+	DDP_COMPONENT_AAL0,
+	DDP_COMPONENT_OD0,
 	DDP_COMPONENT_RDMA0,
 	DDP_COMPONENT_UFOE,
 	DDP_COMPONENT_DSI0,
@@ -173,6 +199,15 @@ static const struct mtk_mmsys_driver_data mt2701_mmsys_driver_data = {
 	.shadow_register = true,
 };
 
+static const struct mtk_mmsys_driver_data mt2712_mmsys_driver_data = {
+	.main_path = mt2712_mtk_ddp_main,
+	.main_len = ARRAY_SIZE(mt2712_mtk_ddp_main),
+	.ext_path = mt2712_mtk_ddp_ext,
+	.ext_len = ARRAY_SIZE(mt2712_mtk_ddp_ext),
+	.third_path = mt2712_mtk_ddp_third,
+	.third_len = ARRAY_SIZE(mt2712_mtk_ddp_third),
+};
+
 static const struct mtk_mmsys_driver_data mt8173_mmsys_driver_data = {
 	.main_path = mt8173_mtk_ddp_main,
 	.main_len = ARRAY_SIZE(mt8173_mtk_ddp_main),
@@ -232,6 +267,11 @@ static int mtk_drm_kms_init(struct drm_device *drm)
 	if (ret < 0)
 		goto err_component_unbind;
 
+	ret = mtk_drm_crtc_create(drm, private->data->third_path,
+				  private->data->third_len);
+	if (ret < 0)
+		goto err_component_unbind;
+
 	/* Use OVL device for all DMA memory allocations */
 	np = private->comp_node[private->data->main_path[0]] ?:
 	     private->comp_node[private->data->ext_path[0]];
@@ -360,24 +400,44 @@ static const struct component_master_ops mtk_drm_ops = {
 };
 
 static const struct of_device_id mtk_ddp_comp_dt_ids[] = {
-	{ .compatible = "mediatek,mt2701-disp-ovl",   .data = (void *)MTK_DISP_OVL },
-	{ .compatible = "mediatek,mt8173-disp-ovl",   .data = (void *)MTK_DISP_OVL },
-	{ .compatible = "mediatek,mt2701-disp-rdma",  .data = (void *)MTK_DISP_RDMA },
-	{ .compatible = "mediatek,mt8173-disp-rdma",  .data = (void *)MTK_DISP_RDMA },
-	{ .compatible = "mediatek,mt8173-disp-wdma",  .data = (void *)MTK_DISP_WDMA },
-	{ .compatible = "mediatek,mt2701-disp-color", .data = (void *)MTK_DISP_COLOR },
-	{ .compatible = "mediatek,mt8173-disp-color", .data = (void *)MTK_DISP_COLOR },
-	{ .compatible = "mediatek,mt8173-disp-aal",   .data = (void *)MTK_DISP_AAL},
-	{ .compatible = "mediatek,mt8173-disp-gamma", .data = (void *)MTK_DISP_GAMMA, },
-	{ .compatible = "mediatek,mt8173-disp-ufoe",  .data = (void *)MTK_DISP_UFOE },
-	{ .compatible = "mediatek,mt2701-dsi",	      .data = (void *)MTK_DSI },
-	{ .compatible = "mediatek,mt8173-dsi",        .data = (void *)MTK_DSI },
-	{ .compatible = "mediatek,mt8173-dpi",        .data = (void *)MTK_DPI },
-	{ .compatible = "mediatek,mt2701-disp-mutex", .data = (void *)MTK_DISP_MUTEX },
-	{ .compatible = "mediatek,mt8173-disp-mutex", .data = (void *)MTK_DISP_MUTEX },
-	{ .compatible = "mediatek,mt2701-disp-pwm",   .data = (void *)MTK_DISP_BLS },
-	{ .compatible = "mediatek,mt8173-disp-pwm",   .data = (void *)MTK_DISP_PWM },
-	{ .compatible = "mediatek,mt8173-disp-od",    .data = (void *)MTK_DISP_OD },
+	{ .compatible = "mediatek,mt2701-disp-ovl",
+	  .data = (void *)MTK_DISP_OVL },
+	{ .compatible = "mediatek,mt8173-disp-ovl",
+	  .data = (void *)MTK_DISP_OVL },
+	{ .compatible = "mediatek,mt2701-disp-rdma",
+	  .data = (void *)MTK_DISP_RDMA },
+	{ .compatible = "mediatek,mt8173-disp-rdma",
+	  .data = (void *)MTK_DISP_RDMA },
+	{ .compatible = "mediatek,mt8173-disp-wdma",
+	  .data = (void *)MTK_DISP_WDMA },
+	{ .compatible = "mediatek,mt2701-disp-color",
+	  .data = (void *)MTK_DISP_COLOR },
+	{ .compatible = "mediatek,mt8173-disp-color",
+	  .data = (void *)MTK_DISP_COLOR },
+	{ .compatible = "mediatek,mt8173-disp-aal",
+	  .data = (void *)MTK_DISP_AAL},
+	{ .compatible = "mediatek,mt8173-disp-gamma",
+	  .data = (void *)MTK_DISP_GAMMA, },
+	{ .compatible = "mediatek,mt8173-disp-ufoe",
+	  .data = (void *)MTK_DISP_UFOE },
+	{ .compatible = "mediatek,mt2701-dsi",
+	  .data = (void *)MTK_DSI },
+	{ .compatible = "mediatek,mt8173-dsi",
+	  .data = (void *)MTK_DSI },
+	{ .compatible = "mediatek,mt8173-dpi",
+	  .data = (void *)MTK_DPI },
+	{ .compatible = "mediatek,mt2701-disp-mutex",
+	  .data = (void *)MTK_DISP_MUTEX },
+	{ .compatible = "mediatek,mt2712-disp-mutex",
+	  .data = (void *)MTK_DISP_MUTEX },
+	{ .compatible = "mediatek,mt8173-disp-mutex",
+	  .data = (void *)MTK_DISP_MUTEX },
+	{ .compatible = "mediatek,mt2701-disp-pwm",
+	  .data = (void *)MTK_DISP_BLS },
+	{ .compatible = "mediatek,mt8173-disp-pwm",
+	  .data = (void *)MTK_DISP_PWM },
+	{ .compatible = "mediatek,mt8173-disp-od",
+	  .data = (void *)MTK_DISP_OD },
 	{ }
 };
 
@@ -552,6 +612,8 @@ static SIMPLE_DEV_PM_OPS(mtk_drm_pm_ops, mtk_drm_sys_suspend,
 static const struct of_device_id mtk_drm_of_ids[] = {
 	{ .compatible = "mediatek,mt2701-mmsys",
 	  .data = &mt2701_mmsys_driver_data},
+	{ .compatible = "mediatek,mt2712-mmsys",
+	  .data = &mt2712_mmsys_driver_data},
 	{ .compatible = "mediatek,mt8173-mmsys",
 	  .data = &mt8173_mmsys_driver_data},
 	{ }
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.h b/drivers/gpu/drm/mediatek/mtk_drm_drv.h
index c3378c452c0a..ecc00ca3221d 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.h
@@ -17,7 +17,7 @@
 #include <linux/io.h>
 #include "mtk_drm_ddp_comp.h"
 
-#define MAX_CRTC	2
+#define MAX_CRTC	3
 #define MAX_CONNECTOR	2
 
 struct device;
@@ -33,6 +33,9 @@ struct mtk_mmsys_driver_data {
 	unsigned int main_len;
 	const enum mtk_ddp_comp_id *ext_path;
 	unsigned int ext_len;
+	const enum mtk_ddp_comp_id *third_path;
+	unsigned int third_len;
+
 	bool shadow_register;
 };
 
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_fb.c b/drivers/gpu/drm/mediatek/mtk_drm_fb.c
index 0d8d506695f9..be5f6f1daf55 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_fb.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_fb.c
@@ -15,6 +15,7 @@
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_gem.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 #include <linux/dma-buf.h>
 #include <linux/reservation.h>
 
@@ -22,78 +23,37 @@
 #include "mtk_drm_fb.h"
 #include "mtk_drm_gem.h"
 
-/*
- * mtk specific framebuffer structure.
- *
- * @fb: drm framebuffer object.
- * @gem_obj: array of gem objects.
- */
-struct mtk_drm_fb {
-	struct drm_framebuffer	base;
-	/* For now we only support a single plane */
-	struct drm_gem_object	*gem_obj;
-};
-
-#define to_mtk_fb(x) container_of(x, struct mtk_drm_fb, base)
-
-struct drm_gem_object *mtk_fb_get_gem_obj(struct drm_framebuffer *fb)
-{
-	struct mtk_drm_fb *mtk_fb = to_mtk_fb(fb);
-
-	return mtk_fb->gem_obj;
-}
-
-static int mtk_drm_fb_create_handle(struct drm_framebuffer *fb,
-				    struct drm_file *file_priv,
-				    unsigned int *handle)
-{
-	struct mtk_drm_fb *mtk_fb = to_mtk_fb(fb);
-
-	return drm_gem_handle_create(file_priv, mtk_fb->gem_obj, handle);
-}
-
-static void mtk_drm_fb_destroy(struct drm_framebuffer *fb)
-{
-	struct mtk_drm_fb *mtk_fb = to_mtk_fb(fb);
-
-	drm_framebuffer_cleanup(fb);
-
-	drm_gem_object_put_unlocked(mtk_fb->gem_obj);
-
-	kfree(mtk_fb);
-}
-
 static const struct drm_framebuffer_funcs mtk_drm_fb_funcs = {
-	.create_handle = mtk_drm_fb_create_handle,
-	.destroy = mtk_drm_fb_destroy,
+	.create_handle = drm_gem_fb_create_handle,
+	.destroy = drm_gem_fb_destroy,
 };
 
-static struct mtk_drm_fb *mtk_drm_framebuffer_init(struct drm_device *dev,
+static struct drm_framebuffer *mtk_drm_framebuffer_init(struct drm_device *dev,
 					const struct drm_mode_fb_cmd2 *mode,
 					struct drm_gem_object *obj)
 {
-	struct mtk_drm_fb *mtk_fb;
+	struct drm_framebuffer *fb;
 	int ret;
 
 	if (drm_format_num_planes(mode->pixel_format) != 1)
 		return ERR_PTR(-EINVAL);
 
-	mtk_fb = kzalloc(sizeof(*mtk_fb), GFP_KERNEL);
-	if (!mtk_fb)
+	fb = kzalloc(sizeof(*fb), GFP_KERNEL);
+	if (!fb)
 		return ERR_PTR(-ENOMEM);
 
-	drm_helper_mode_fill_fb_struct(dev, &mtk_fb->base, mode);
+	drm_helper_mode_fill_fb_struct(dev, fb, mode);
 
-	mtk_fb->gem_obj = obj;
+	fb->obj[0] = obj;
 
-	ret = drm_framebuffer_init(dev, &mtk_fb->base, &mtk_drm_fb_funcs);
+	ret = drm_framebuffer_init(dev, fb, &mtk_drm_fb_funcs);
 	if (ret) {
 		DRM_ERROR("failed to initialize framebuffer\n");
-		kfree(mtk_fb);
+		kfree(fb);
 		return ERR_PTR(ret);
 	}
 
-	return mtk_fb;
+	return fb;
 }
 
 /*
@@ -110,7 +70,7 @@ int mtk_fb_wait(struct drm_framebuffer *fb)
 	if (!fb)
 		return 0;
 
-	gem = mtk_fb_get_gem_obj(fb);
+	gem = fb->obj[0];
 	if (!gem || !gem->dma_buf || !gem->dma_buf->resv)
 		return 0;
 
@@ -128,7 +88,7 @@ struct drm_framebuffer *mtk_drm_mode_fb_create(struct drm_device *dev,
 					       struct drm_file *file,
 					       const struct drm_mode_fb_cmd2 *cmd)
 {
-	struct mtk_drm_fb *mtk_fb;
+	struct drm_framebuffer *fb;
 	struct drm_gem_object *gem;
 	unsigned int width = cmd->width;
 	unsigned int height = cmd->height;
@@ -151,13 +111,13 @@ struct drm_framebuffer *mtk_drm_mode_fb_create(struct drm_device *dev,
 		goto unreference;
 	}
 
-	mtk_fb = mtk_drm_framebuffer_init(dev, cmd, gem);
-	if (IS_ERR(mtk_fb)) {
-		ret = PTR_ERR(mtk_fb);
+	fb = mtk_drm_framebuffer_init(dev, cmd, gem);
+	if (IS_ERR(fb)) {
+		ret = PTR_ERR(fb);
 		goto unreference;
 	}
 
-	return &mtk_fb->base;
+	return fb;
 
 unreference:
 	drm_gem_object_put_unlocked(gem);
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_fb.h b/drivers/gpu/drm/mediatek/mtk_drm_fb.h
index 9b2ae345a4e9..7f976b196a15 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_fb.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_fb.h
@@ -14,7 +14,6 @@
 #ifndef MTK_DRM_FB_H
 #define MTK_DRM_FB_H
 
-struct drm_gem_object *mtk_fb_get_gem_obj(struct drm_framebuffer *fb);
 int mtk_fb_wait(struct drm_framebuffer *fb);
 struct drm_framebuffer *mtk_drm_mode_fb_create(struct drm_device *dev,
 					       struct drm_file *file,
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
index 2f4b0ffee598..f7e6aa1b5b7d 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
@@ -95,11 +95,6 @@ static int mtk_plane_atomic_check(struct drm_plane *plane,
 	if (!fb)
 		return 0;
 
-	if (!mtk_fb_get_gem_obj(fb)) {
-		DRM_DEBUG_KMS("buffer is null\n");
-		return -EFAULT;
-	}
-
 	if (!state->crtc)
 		return 0;
 
@@ -127,7 +122,7 @@ static void mtk_plane_atomic_update(struct drm_plane *plane,
 	if (!crtc || WARN_ON(!fb))
 		return;
 
-	gem = mtk_fb_get_gem_obj(fb);
+	gem = fb->obj[0];
 	mtk_gem = to_mtk_gem_obj(gem);
 	addr = mtk_gem->dma_addr;
 	pitch = fb->pitches[0];
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index aa0943ec32b0..66df1b177959 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -782,7 +782,7 @@ static int mtk_dsi_create_connector(struct drm_device *drm, struct mtk_dsi *dsi)
 	drm_connector_helper_add(&dsi->conn, &mtk_dsi_connector_helper_funcs);
 
 	dsi->conn.dpms = DRM_MODE_DPMS_OFF;
-	drm_mode_connector_attach_encoder(&dsi->conn, &dsi->encoder);
+	drm_connector_attach_encoder(&dsi->conn, &dsi->encoder);
 
 	if (dsi->panel) {
 		ret = drm_panel_attach(dsi->panel, &dsi->conn);
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index 59a11026dceb..2d45d1dd9554 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -1220,7 +1220,7 @@ static int mtk_hdmi_conn_get_modes(struct drm_connector *conn)
 
 	hdmi->dvi_mode = !drm_detect_monitor_audio(edid);
 
-	drm_mode_connector_update_edid_property(conn, edid);
+	drm_connector_update_edid_property(conn, edid);
 
 	ret = drm_add_edid_modes(conn, edid);
 	kfree(edid);
@@ -1306,7 +1306,7 @@ static int mtk_hdmi_bridge_attach(struct drm_bridge *bridge)
 	hdmi->conn.interlace_allowed = true;
 	hdmi->conn.doublescan_allowed = false;
 
-	ret = drm_mode_connector_attach_encoder(&hdmi->conn,
+	ret = drm_connector_attach_encoder(&hdmi->conn,
 						bridge->encoder);
 	if (ret) {
 		dev_err(hdmi->dev,
diff --git a/drivers/gpu/drm/meson/meson_dw_hdmi.c b/drivers/gpu/drm/meson/meson_dw_hdmi.c
index c9ad45686e7a..df7247cd93f9 100644
--- a/drivers/gpu/drm/meson/meson_dw_hdmi.c
+++ b/drivers/gpu/drm/meson/meson_dw_hdmi.c
@@ -329,6 +329,12 @@ static void dw_hdmi_set_vclk(struct meson_dw_hdmi *dw_hdmi,
 
 	vclk_freq = mode->clock;
 
+	if (!vic) {
+		meson_vclk_setup(priv, MESON_VCLK_TARGET_DMT, vclk_freq,
+				 vclk_freq, vclk_freq, false);
+		return;
+	}
+
 	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
 		vclk_freq *= 2;
 
@@ -542,10 +548,12 @@ static enum drm_mode_status
 dw_hdmi_mode_valid(struct drm_connector *connector,
 		   const struct drm_display_mode *mode)
 {
+	struct meson_drm *priv = connector->dev->dev_private;
 	unsigned int vclk_freq;
 	unsigned int venc_freq;
 	unsigned int hdmi_freq;
 	int vic = drm_match_cea_mode(mode);
+	enum drm_mode_status status;
 
 	DRM_DEBUG_DRIVER("Modeline %d:\"%s\" %d %d %d %d %d %d %d %d %d %d 0x%x 0x%x\n",
 		mode->base.id, mode->name, mode->vrefresh, mode->clock,
@@ -556,8 +564,11 @@ dw_hdmi_mode_valid(struct drm_connector *connector,
 
 	/* Check against non-VIC supported modes */
 	if (!vic) {
-		if (!meson_venc_hdmi_supported_mode(mode))
-			return MODE_BAD;
+		status = meson_venc_hdmi_supported_mode(mode);
+		if (status != MODE_OK)
+			return status;
+
+		return meson_vclk_dmt_supported_freq(priv, mode->clock);
 	/* Check against supported VIC modes */
 	} else if (!meson_venc_hdmi_supported_vic(vic))
 		return MODE_BAD;
@@ -583,16 +594,11 @@ dw_hdmi_mode_valid(struct drm_connector *connector,
 	dev_dbg(connector->dev->dev, "%s: vclk:%d venc=%d hdmi=%d\n", __func__,
 		vclk_freq, venc_freq, hdmi_freq);
 
-	/* Finally filter by configurable vclk frequencies */
+	/* Finally filter by configurable vclk frequencies for VIC modes */
 	switch (vclk_freq) {
-	case 25175:
-	case 40000:
 	case 54000:
-	case 65000:
 	case 74250:
-	case 108000:
 	case 148500:
-	case 162000:
 	case 297000:
 	case 594000:
 		return MODE_OK;
diff --git a/drivers/gpu/drm/meson/meson_vclk.c b/drivers/gpu/drm/meson/meson_vclk.c
index f0511220317f..ae5473257f72 100644
--- a/drivers/gpu/drm/meson/meson_vclk.c
+++ b/drivers/gpu/drm/meson/meson_vclk.c
@@ -320,32 +320,23 @@ static void meson_venci_cvbs_clock_config(struct meson_drm *priv)
 				CTS_VDAC_EN, CTS_VDAC_EN);
 }
 
-
+enum {
 /* PLL	O1 O2 O3 VP DV     EN TX */
 /* 4320 /4 /4 /1 /5 /1  => /2 /2 */
-#define MESON_VCLK_HDMI_ENCI_54000	1
+	MESON_VCLK_HDMI_ENCI_54000 = 1,
 /* 4320 /4 /4 /1 /5 /1  => /1 /2 */
-#define MESON_VCLK_HDMI_DDR_54000	2
+	MESON_VCLK_HDMI_DDR_54000,
 /* 2970 /4 /1 /1 /5 /1  => /1 /2 */
-#define MESON_VCLK_HDMI_DDR_148500	3
-/* 4028 /4 /4 /1 /5 /2  => /1 /1 */
-#define MESON_VCLK_HDMI_25175		4
-/* 3200 /4 /2 /1 /5 /2  => /1 /1 */
-#define MESON_VCLK_HDMI_40000		5
-/* 5200 /4 /2 /1 /5 /2  => /1 /1 */
-#define MESON_VCLK_HDMI_65000		6
+	MESON_VCLK_HDMI_DDR_148500,
 /* 2970 /2 /2 /2 /5 /1  => /1 /1 */
-#define MESON_VCLK_HDMI_74250		7
-/* 4320 /4 /1 /1 /5 /2  => /1 /1 */
-#define MESON_VCLK_HDMI_108000		8
+	MESON_VCLK_HDMI_74250,
 /* 2970 /1 /2 /2 /5 /1  => /1 /1 */
-#define MESON_VCLK_HDMI_148500		9
-/* 3240 /2 /1 /1 /5 /2  => /1 /1 */
-#define MESON_VCLK_HDMI_162000		10
+	MESON_VCLK_HDMI_148500,
 /* 2970 /1 /1 /1 /5 /2  => /1 /1 */
-#define MESON_VCLK_HDMI_297000		11
+	MESON_VCLK_HDMI_297000,
 /* 5940 /1 /1 /2 /5 /1  => /1 /1 */
-#define MESON_VCLK_HDMI_594000		12
+	MESON_VCLK_HDMI_594000
+};
 
 struct meson_vclk_params {
 	unsigned int pll_base_freq;
@@ -411,46 +402,6 @@ struct meson_vclk_params {
 		.vid_pll_div = VID_PLL_DIV_5,
 		.vclk_div = 1,
 	},
-	[MESON_VCLK_HDMI_25175] = {
-		.pll_base_freq = 4028000,
-		.pll_od1 = 4,
-		.pll_od2 = 4,
-		.pll_od3 = 1,
-		.vid_pll_div = VID_PLL_DIV_5,
-		.vclk_div = 2,
-	},
-	[MESON_VCLK_HDMI_40000] = {
-		.pll_base_freq = 3200000,
-		.pll_od1 = 4,
-		.pll_od2 = 2,
-		.pll_od3 = 1,
-		.vid_pll_div = VID_PLL_DIV_5,
-		.vclk_div = 2,
-	},
-	[MESON_VCLK_HDMI_65000] = {
-		.pll_base_freq = 5200000,
-		.pll_od1 = 4,
-		.pll_od2 = 2,
-		.pll_od3 = 1,
-		.vid_pll_div = VID_PLL_DIV_5,
-		.vclk_div = 2,
-	},
-	[MESON_VCLK_HDMI_108000] = {
-		.pll_base_freq = 4320000,
-		.pll_od1 = 4,
-		.pll_od2 = 1,
-		.pll_od3 = 1,
-		.vid_pll_div = VID_PLL_DIV_5,
-		.vclk_div = 2,
-	},
-	[MESON_VCLK_HDMI_162000] = {
-		.pll_base_freq = 3240000,
-		.pll_od1 = 2,
-		.pll_od2 = 1,
-		.pll_od3 = 1,
-		.vid_pll_div = VID_PLL_DIV_5,
-		.vclk_div = 2,
-	},
 };
 
 static inline unsigned int pll_od_to_reg(unsigned int od)
@@ -470,358 +421,217 @@ static inline unsigned int pll_od_to_reg(unsigned int od)
 	return 0;
 }
 
-void meson_hdmi_pll_set(struct meson_drm *priv,
-			unsigned int base,
-			unsigned int od1,
-			unsigned int od2,
-			unsigned int od3)
+void meson_hdmi_pll_set_params(struct meson_drm *priv, unsigned int m,
+			       unsigned int frac, unsigned int od1,
+			       unsigned int od2, unsigned int od3)
 {
 	unsigned int val;
 
 	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu")) {
-		switch (base) {
-		case 2970000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x5800023d);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* Enable and unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						0x7 << 28, 0x4 << 28);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-
-			/* div_frac */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-						0xFFFF,  0x4e00);
-			break;
-
-		case 3200000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x58000242);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-
-			/* div_frac */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-						0xFFFF,  0x4aab);
-			break;
-
-		case 3240000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x58000243);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-
-			/* div_frac */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-						0xFFFF,  0x4800);
-			break;
-
-		case 3865000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x58000250);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-
-			/* div_frac */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-						0xFFFF,  0x4855);
-			break;
-
-		case 4028000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x58000253);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-
-			/* div_frac */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-						0xFFFF,  0x4eab);
-			break;
-
-		case 4320000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x5800025a);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-			break;
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x58000200 | m);
+		if (frac)
+			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2,
+				     0x00004000 | frac);
+		else
+			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2,
+				     0x00000000);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
 
-		case 5940000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x5800027b);
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-						0xFFFF,  0x4c00);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x135c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-			break;
+		/* Enable and unreset */
+		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
+				   0x7 << 28, 0x4 << 28);
 
-		case 5200000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x5800026c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x135c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-			break;
-		};
+		/* Poll for lock bit */
+		regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
+					 val, (val & HDMI_PLL_LOCK), 10, 0);
 	} else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxm-vpu") ||
 		   meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu")) {
-		switch (base) {
-		case 2970000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x4000027b);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb300);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 3200000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x40000285);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb155);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 3240000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x40000287);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 3865000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x400002a1);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb02b);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 4028000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x400002a7);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb355);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 4320000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x400002b4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 5940000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x400002f7);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb200);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 5200000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x400002d8);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb2ab);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		};
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x40000200 | m);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb000 | frac);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
 
 		/* Reset PLL */
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-					HDMI_PLL_RESET, HDMI_PLL_RESET);
+				HDMI_PLL_RESET, HDMI_PLL_RESET);
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-					HDMI_PLL_RESET, 0);
+				HDMI_PLL_RESET, 0);
 
 		/* Poll for lock bit */
 		regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL, val,
 				(val & HDMI_PLL_LOCK), 10, 0);
-	};
+	}
 
 	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu"))
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-				   3 << 16, pll_od_to_reg(od1) << 16);
+				3 << 16, pll_od_to_reg(od1) << 16);
 	else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxm-vpu") ||
-		 meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu"))
+			meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu"))
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL3,
-				   3 << 21, pll_od_to_reg(od1) << 21);
+				3 << 21, pll_od_to_reg(od1) << 21);
 
 	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu"))
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-				   3 << 22, pll_od_to_reg(od2) << 22);
+				3 << 22, pll_od_to_reg(od2) << 22);
 	else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxm-vpu") ||
-		 meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu"))
+			meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu"))
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL3,
-				   3 << 23, pll_od_to_reg(od2) << 23);
+				3 << 23, pll_od_to_reg(od2) << 23);
 
 	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu"))
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-				   3 << 18, pll_od_to_reg(od3) << 18);
+				3 << 18, pll_od_to_reg(od3) << 18);
 	else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxm-vpu") ||
-		 meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu"))
+			meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu"))
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL3,
-				   3 << 19, pll_od_to_reg(od3) << 19);
+				3 << 19, pll_od_to_reg(od3) << 19);
+
 }
 
-void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
-		      unsigned int vclk_freq, unsigned int venc_freq,
-		      unsigned int dac_freq, bool hdmi_use_enci)
+#define XTAL_FREQ 24000
+
+static unsigned int meson_hdmi_pll_get_m(struct meson_drm *priv,
+					 unsigned int pll_freq)
 {
-	unsigned int freq;
-	unsigned int hdmi_tx_div;
-	unsigned int venc_div;
+	/* The GXBB PLL has a /2 pre-multiplier */
+	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu"))
+		pll_freq /= 2;
 
-	if (target == MESON_VCLK_TARGET_CVBS) {
-		meson_venci_cvbs_clock_config(priv);
-		return;
+	return pll_freq / XTAL_FREQ;
+}
+
+#define HDMI_FRAC_MAX_GXBB	4096
+#define HDMI_FRAC_MAX_GXL	1024
+
+static unsigned int meson_hdmi_pll_get_frac(struct meson_drm *priv,
+					    unsigned int m,
+					    unsigned int pll_freq)
+{
+	unsigned int parent_freq = XTAL_FREQ;
+	unsigned int frac_max = HDMI_FRAC_MAX_GXL;
+	unsigned int frac_m;
+	unsigned int frac;
+
+	/* The GXBB PLL has a /2 pre-multiplier and a larger FRAC width */
+	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu")) {
+		frac_max = HDMI_FRAC_MAX_GXBB;
+		parent_freq *= 2;
 	}
 
-	hdmi_tx_div = vclk_freq / dac_freq;
+	/* We can have a perfect match !*/
+	if (pll_freq / m == parent_freq &&
+	    pll_freq % m == 0)
+		return 0;
 
-	if (hdmi_tx_div == 0) {
-		pr_err("Fatal Error, invalid HDMI-TX freq %d\n",
-				dac_freq);
-		return;
+	frac = div_u64((u64)pll_freq * (u64)frac_max, parent_freq);
+	frac_m = m * frac_max;
+	if (frac_m > frac)
+		return frac_max;
+	frac -= frac_m;
+
+	return min((u16)frac, (u16)(frac_max - 1));
+}
+
+static bool meson_hdmi_pll_validate_params(struct meson_drm *priv,
+					   unsigned int m,
+					   unsigned int frac)
+{
+	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu")) {
+		/* Empiric supported min/max dividers */
+		if (m < 53 || m > 123)
+			return false;
+		if (frac >= HDMI_FRAC_MAX_GXBB)
+			return false;
+	} else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxm-vpu") ||
+		   meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu")) {
+		/* Empiric supported min/max dividers */
+		if (m < 106 || m > 247)
+			return false;
+		if (frac >= HDMI_FRAC_MAX_GXL)
+			return false;
 	}
 
-	venc_div = vclk_freq / venc_freq;
+	return true;
+}
 
-	if (venc_div == 0) {
-		pr_err("Fatal Error, invalid HDMI venc freq %d\n",
-				venc_freq);
-		return;
+static bool meson_hdmi_pll_find_params(struct meson_drm *priv,
+				       unsigned int freq,
+				       unsigned int *m,
+				       unsigned int *frac,
+				       unsigned int *od)
+{
+	/* Cycle from /16 to /2 */
+	for (*od = 16 ; *od > 1 ; *od >>= 1) {
+		*m = meson_hdmi_pll_get_m(priv, freq * *od);
+		if (!*m)
+			continue;
+		*frac = meson_hdmi_pll_get_frac(priv, *m, freq * *od);
+
+		DRM_DEBUG_DRIVER("PLL params for %dkHz: m=%x frac=%x od=%d\n",
+				 freq, *m, *frac, *od);
+
+		if (meson_hdmi_pll_validate_params(priv, *m, *frac))
+			return true;
 	}
 
-	switch (vclk_freq) {
-	case 54000:
-		if (hdmi_use_enci)
-			freq = MESON_VCLK_HDMI_ENCI_54000;
-		else
-			freq = MESON_VCLK_HDMI_DDR_54000;
-		break;
-	case 25175:
-		freq = MESON_VCLK_HDMI_25175;
-		break;
-	case 40000:
-		freq = MESON_VCLK_HDMI_40000;
-		break;
-	case 65000:
-		freq = MESON_VCLK_HDMI_65000;
-		break;
-	case 74250:
-		freq = MESON_VCLK_HDMI_74250;
-		break;
-	case 108000:
-		freq = MESON_VCLK_HDMI_108000;
-		break;
-	case 148500:
-		if (dac_freq != 148500)
-			freq = MESON_VCLK_HDMI_DDR_148500;
-		else
-			freq = MESON_VCLK_HDMI_148500;
-		break;
-	case 162000:
-		freq = MESON_VCLK_HDMI_162000;
-		break;
-	case 297000:
-		freq = MESON_VCLK_HDMI_297000;
-		break;
-	case 594000:
-		freq = MESON_VCLK_HDMI_594000;
-		break;
-	default:
-		pr_err("Fatal Error, invalid HDMI vclk freq %d\n",
-			vclk_freq);
+	return false;
+}
+
+/* pll_freq is the frequency after the OD dividers */
+enum drm_mode_status
+meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned int freq)
+{
+	unsigned int od, m, frac;
+
+	/* In DMT mode, path after PLL is always /10 */
+	freq *= 10;
+
+	if (meson_hdmi_pll_find_params(priv, freq, &m, &frac, &od))
+		return MODE_OK;
+
+	return MODE_CLOCK_RANGE;
+}
+EXPORT_SYMBOL_GPL(meson_vclk_dmt_supported_freq);
+
+/* pll_freq is the frequency after the OD dividers */
+static void meson_hdmi_pll_generic_set(struct meson_drm *priv,
+				       unsigned int pll_freq)
+{
+	unsigned int od, m, frac, od1, od2, od3;
+
+	if (meson_hdmi_pll_find_params(priv, pll_freq, &m, &frac, &od)) {
+		od3 = 1;
+		if (od < 4) {
+			od1 = 2;
+			od2 = 1;
+		} else {
+			od2 = od / 4;
+			od1 = od / od2;
+		}
+
+		DRM_DEBUG_DRIVER("PLL params for %dkHz: m=%x frac=%x od=%d/%d/%d\n",
+				 pll_freq, m, frac, od1, od2, od3);
+
+		meson_hdmi_pll_set_params(priv, m, frac, od1, od2, od3);
+
 		return;
 	}
 
+	DRM_ERROR("Fatal, unable to find parameters for PLL freq %d\n",
+		  pll_freq);
+}
+
+static void meson_vclk_set(struct meson_drm *priv, unsigned int pll_base_freq,
+			   unsigned int od1, unsigned int od2, unsigned int od3,
+			   unsigned int vid_pll_div, unsigned int vclk_div,
+			   unsigned int hdmi_tx_div, unsigned int venc_div,
+			   bool hdmi_use_enci)
+{
 	/* Set HDMI-TX sys clock */
 	regmap_update_bits(priv->hhi, HHI_HDMI_CLK_CNTL,
 			   CTS_HDMI_SYS_SEL_MASK, 0);
@@ -831,19 +641,49 @@ void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
 			   CTS_HDMI_SYS_EN, CTS_HDMI_SYS_EN);
 
 	/* Set HDMI PLL rate */
-	meson_hdmi_pll_set(priv, params[freq].pll_base_freq,
-			   params[freq].pll_od1,
-			   params[freq].pll_od2,
-			   params[freq].pll_od3);
+	if (!od1 && !od2 && !od3) {
+		meson_hdmi_pll_generic_set(priv, pll_base_freq);
+	} else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu")) {
+		switch (pll_base_freq) {
+		case 2970000:
+			meson_hdmi_pll_set_params(priv, 0x3d, 0xe00,
+						  od1, od2, od3);
+			break;
+		case 4320000:
+			meson_hdmi_pll_set_params(priv, 0x5a, 0,
+						  od1, od2, od3);
+			break;
+		case 5940000:
+			meson_hdmi_pll_set_params(priv, 0x7b, 0xc00,
+						  od1, od2, od3);
+			break;
+		}
+	} else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxm-vpu") ||
+		   meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu")) {
+		switch (pll_base_freq) {
+		case 2970000:
+			meson_hdmi_pll_set_params(priv, 0x7b, 0x300,
+						  od1, od2, od3);
+			break;
+		case 4320000:
+			meson_hdmi_pll_set_params(priv, 0xb4, 0,
+						  od1, od2, od3);
+			break;
+		case 5940000:
+			meson_hdmi_pll_set_params(priv, 0xf7, 0x200,
+						  od1, od2, od3);
+			break;
+		}
+	}
 
 	/* Setup vid_pll divider */
-	meson_vid_pll_set(priv, params[freq].vid_pll_div);
+	meson_vid_pll_set(priv, vid_pll_div);
 
 	/* Set VCLK div */
 	regmap_update_bits(priv->hhi, HHI_VID_CLK_CNTL,
 			   VCLK_SEL_MASK, 0);
 	regmap_update_bits(priv->hhi, HHI_VID_CLK_DIV,
-			   VCLK_DIV_MASK, params[freq].vclk_div - 1);
+			   VCLK_DIV_MASK, vclk_div - 1);
 
 	/* Set HDMI-TX source */
 	switch (hdmi_tx_div) {
@@ -981,4 +821,80 @@ void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
 
 	regmap_update_bits(priv->hhi, HHI_VID_CLK_CNTL, VCLK_EN, VCLK_EN);
 }
+
+void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
+		      unsigned int vclk_freq, unsigned int venc_freq,
+		      unsigned int dac_freq, bool hdmi_use_enci)
+{
+	unsigned int freq;
+	unsigned int hdmi_tx_div;
+	unsigned int venc_div;
+
+	if (target == MESON_VCLK_TARGET_CVBS) {
+		meson_venci_cvbs_clock_config(priv);
+		return;
+	} else if (target == MESON_VCLK_TARGET_DMT) {
+		/* The DMT clock path is fixed after the PLL:
+		 * - automatic PLL freq + OD management
+		 * - vid_pll_div = VID_PLL_DIV_5
+		 * - vclk_div = 2
+		 * - hdmi_tx_div = 1
+		 * - venc_div = 1
+		 * - encp encoder
+		 */
+		meson_vclk_set(priv, vclk_freq * 10, 0, 0, 0,
+			       VID_PLL_DIV_5, 2, 1, 1, false);
+		return;
+	}
+
+	hdmi_tx_div = vclk_freq / dac_freq;
+
+	if (hdmi_tx_div == 0) {
+		pr_err("Fatal Error, invalid HDMI-TX freq %d\n",
+		       dac_freq);
+		return;
+	}
+
+	venc_div = vclk_freq / venc_freq;
+
+	if (venc_div == 0) {
+		pr_err("Fatal Error, invalid HDMI venc freq %d\n",
+		       venc_freq);
+		return;
+	}
+
+	switch (vclk_freq) {
+	case 54000:
+		if (hdmi_use_enci)
+			freq = MESON_VCLK_HDMI_ENCI_54000;
+		else
+			freq = MESON_VCLK_HDMI_DDR_54000;
+		break;
+	case 74250:
+		freq = MESON_VCLK_HDMI_74250;
+		break;
+	case 148500:
+		if (dac_freq != 148500)
+			freq = MESON_VCLK_HDMI_DDR_148500;
+		else
+			freq = MESON_VCLK_HDMI_148500;
+		break;
+	case 297000:
+		freq = MESON_VCLK_HDMI_297000;
+		break;
+	case 594000:
+		freq = MESON_VCLK_HDMI_594000;
+		break;
+	default:
+		pr_err("Fatal Error, invalid HDMI vclk freq %d\n",
+		       vclk_freq);
+		return;
+	}
+
+	meson_vclk_set(priv, params[freq].pll_base_freq,
+		       params[freq].pll_od1, params[freq].pll_od2,
+		       params[freq].pll_od3, params[freq].vid_pll_div,
+		       params[freq].vclk_div, hdmi_tx_div, venc_div,
+		       hdmi_use_enci);
+}
 EXPORT_SYMBOL_GPL(meson_vclk_setup);
diff --git a/drivers/gpu/drm/meson/meson_vclk.h b/drivers/gpu/drm/meson/meson_vclk.h
index 0401b5213471..869fa3a3073e 100644
--- a/drivers/gpu/drm/meson/meson_vclk.h
+++ b/drivers/gpu/drm/meson/meson_vclk.h
@@ -24,11 +24,15 @@
 enum {
 	MESON_VCLK_TARGET_CVBS = 0,
 	MESON_VCLK_TARGET_HDMI = 1,
+	MESON_VCLK_TARGET_DMT = 2,
 };
 
 /* 27MHz is the CVBS Pixel Clock */
 #define MESON_VCLK_CVBS			27000
 
+enum drm_mode_status
+meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned int freq);
+
 void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
 		      unsigned int vclk_freq, unsigned int venc_freq,
 		      unsigned int dac_freq, bool hdmi_use_enci);
diff --git a/drivers/gpu/drm/meson/meson_venc.c b/drivers/gpu/drm/meson/meson_venc.c
index 6e2701389801..514245e69b38 100644
--- a/drivers/gpu/drm/meson/meson_venc.c
+++ b/drivers/gpu/drm/meson/meson_venc.c
@@ -697,314 +697,6 @@ union meson_hdmi_venc_mode meson_hdmi_encp_mode_1080p60 = {
 	},
 };
 
-union meson_hdmi_venc_mode meson_hdmi_encp_mode_640x480_60 = {
-	.encp = {
-		.dvi_settings = 0x21,
-		.video_mode = 0x4040,
-		.video_mode_adv = 0x18,
-		/* video_prog_mode */
-		/* video_sync_mode */
-		/* video_yc_dly */
-		/* video_rgb_ctrl */
-		/* video_filt_ctrl */
-		/* video_ofld_voav_ofst */
-		/* yfp1_htime */
-		/* yfp2_htime */
-		.max_pxcnt = 0x31f,
-		/* hspuls_begin */
-		/* hspuls_end */
-		/* hspuls_switch */
-		/* vspuls_begin */
-		/* vspuls_end */
-		/* vspuls_bline */
-		/* vspuls_eline */
-		.havon_begin = 0x90,
-		.havon_end = 0x30f,
-		.vavon_bline = 0x23,
-		.vavon_eline = 0x202,
-		/* eqpuls_begin */
-		/* eqpuls_end */
-		/* eqpuls_bline */
-		/* eqpuls_eline */
-		.hso_begin = 0,
-		.hso_end = 0x60,
-		.vso_begin = 0x1e,
-		.vso_end = 0x32,
-		.vso_bline = 0,
-		.vso_eline = 2,
-		.vso_eline_present = true,
-		/* sy_val */
-		/* sy2_val */
-		.max_lncnt = 0x20c,
-	},
-};
-
-union meson_hdmi_venc_mode meson_hdmi_encp_mode_800x600_60 = {
-	.encp = {
-		.dvi_settings = 0x21,
-		.video_mode = 0x4040,
-		.video_mode_adv = 0x18,
-		/* video_prog_mode */
-		/* video_sync_mode */
-		/* video_yc_dly */
-		/* video_rgb_ctrl */
-		/* video_filt_ctrl */
-		/* video_ofld_voav_ofst */
-		/* yfp1_htime */
-		/* yfp2_htime */
-		.max_pxcnt = 0x41f,
-		/* hspuls_begin */
-		/* hspuls_end */
-		/* hspuls_switch */
-		/* vspuls_begin */
-		/* vspuls_end */
-		/* vspuls_bline */
-		/* vspuls_eline */
-		.havon_begin = 0xD8,
-		.havon_end = 0x3f7,
-		.vavon_bline = 0x1b,
-		.vavon_eline = 0x272,
-		/* eqpuls_begin */
-		/* eqpuls_end */
-		/* eqpuls_bline */
-		/* eqpuls_eline */
-		.hso_begin = 0,
-		.hso_end = 0x80,
-		.vso_begin = 0x1e,
-		.vso_end = 0x32,
-		.vso_bline = 0,
-		.vso_eline = 4,
-		.vso_eline_present = true,
-		/* sy_val */
-		/* sy2_val */
-		.max_lncnt = 0x273,
-	},
-};
-
-union meson_hdmi_venc_mode meson_hdmi_encp_mode_1024x768_60 = {
-	.encp = {
-		.dvi_settings = 0x21,
-		.video_mode = 0x4040,
-		.video_mode_adv = 0x18,
-		/* video_prog_mode */
-		/* video_sync_mode */
-		/* video_yc_dly */
-		/* video_rgb_ctrl */
-		/* video_filt_ctrl */
-		/* video_ofld_voav_ofst */
-		/* yfp1_htime */
-		/* yfp2_htime */
-		.max_pxcnt = 1343,
-		/* hspuls_begin */
-		/* hspuls_end */
-		/* hspuls_switch */
-		/* vspuls_begin */
-		/* vspuls_end */
-		/* vspuls_bline */
-		/* vspuls_eline */
-		.havon_begin = 296,
-		.havon_end = 1319,
-		.vavon_bline = 35,
-		.vavon_eline = 802,
-		/* eqpuls_begin */
-		/* eqpuls_end */
-		/* eqpuls_bline */
-		/* eqpuls_eline */
-		.hso_begin = 0,
-		.hso_end = 136,
-		.vso_begin = 30,
-		.vso_end = 50,
-		.vso_bline = 0,
-		.vso_eline = 6,
-		.vso_eline_present = true,
-		/* sy_val */
-		/* sy2_val */
-		.max_lncnt = 805,
-	},
-};
-
-union meson_hdmi_venc_mode meson_hdmi_encp_mode_1152x864_75 = {
-	.encp = {
-		.dvi_settings = 0x21,
-		.video_mode = 0x4040,
-		.video_mode_adv = 0x18,
-		/* video_prog_mode */
-		/* video_sync_mode */
-		/* video_yc_dly */
-		/* video_rgb_ctrl */
-		/* video_filt_ctrl */
-		/* video_ofld_voav_ofst */
-		/* yfp1_htime */
-		/* yfp2_htime */
-		.max_pxcnt = 0x63f,
-		/* hspuls_begin */
-		/* hspuls_end */
-		/* hspuls_switch */
-		/* vspuls_begin */
-		/* vspuls_end */
-		/* vspuls_bline */
-		/* vspuls_eline */
-		.havon_begin = 0x180,
-		.havon_end = 0x5ff,
-		.vavon_bline = 0x23,
-		.vavon_eline = 0x382,
-		/* eqpuls_begin */
-		/* eqpuls_end */
-		/* eqpuls_bline */
-		/* eqpuls_eline */
-		.hso_begin = 0,
-		.hso_end = 0x80,
-		.vso_begin = 0x1e,
-		.vso_end = 0x32,
-		.vso_bline = 0,
-		.vso_eline = 3,
-		.vso_eline_present = true,
-		/* sy_val */
-		/* sy2_val */
-		.max_lncnt = 0x383,
-	},
-};
-
-union meson_hdmi_venc_mode meson_hdmi_encp_mode_1280x1024_60 = {
-	.encp = {
-		.dvi_settings = 0x21,
-		.video_mode = 0x4040,
-		.video_mode_adv = 0x18,
-		/* video_prog_mode */
-		/* video_sync_mode */
-		/* video_yc_dly */
-		/* video_rgb_ctrl */
-		/* video_filt_ctrl */
-		/* video_ofld_voav_ofst */
-		/* yfp1_htime */
-		/* yfp2_htime */
-		.max_pxcnt = 0x697,
-		/* hspuls_begin */
-		/* hspuls_end */
-		/* hspuls_switch */
-		/* vspuls_begin */
-		/* vspuls_end */
-		/* vspuls_bline */
-		/* vspuls_eline */
-		.havon_begin = 0x168,
-		.havon_end = 0x667,
-		.vavon_bline = 0x29,
-		.vavon_eline = 0x428,
-		/* eqpuls_begin */
-		/* eqpuls_end */
-		/* eqpuls_bline */
-		/* eqpuls_eline */
-		.hso_begin = 0,
-		.hso_end = 0x70,
-		.vso_begin = 0x1e,
-		.vso_end = 0x32,
-		.vso_bline = 0,
-		.vso_eline = 3,
-		.vso_eline_present = true,
-		/* sy_val */
-		/* sy2_val */
-		.max_lncnt = 0x429,
-	},
-};
-
-union meson_hdmi_venc_mode meson_hdmi_encp_mode_1600x1200_60 = {
-	.encp = {
-		.dvi_settings = 0x21,
-		.video_mode = 0x4040,
-		.video_mode_adv = 0x18,
-		/* video_prog_mode */
-		/* video_sync_mode */
-		/* video_yc_dly */
-		/* video_rgb_ctrl */
-		/* video_filt_ctrl */
-		/* video_ofld_voav_ofst */
-		/* yfp1_htime */
-		/* yfp2_htime */
-		.max_pxcnt = 0x86f,
-		/* hspuls_begin */
-		/* hspuls_end */
-		/* hspuls_switch */
-		/* vspuls_begin */
-		/* vspuls_end */
-		/* vspuls_bline */
-		/* vspuls_eline */
-		.havon_begin = 0x1f0,
-		.havon_end = 0x82f,
-		.vavon_bline = 0x31,
-		.vavon_eline = 0x4e0,
-		/* eqpuls_begin */
-		/* eqpuls_end */
-		/* eqpuls_bline */
-		/* eqpuls_eline */
-		.hso_begin = 0,
-		.hso_end = 0xc0,
-		.vso_begin = 0x1e,
-		.vso_end = 0x32,
-		.vso_bline = 0,
-		.vso_eline = 3,
-		.vso_eline_present = true,
-		/* sy_val */
-		/* sy2_val */
-		.max_lncnt = 0x4e1,
-	},
-};
-
-struct meson_hdmi_venc_dmt_mode {
-	struct drm_display_mode drm_mode;
-	union meson_hdmi_venc_mode *mode;
-} meson_hdmi_venc_dmt_modes[] = {
-	/* 640x480@60Hz */
-	{
-		{ DRM_MODE("640x480", DRM_MODE_TYPE_DRIVER, 25175, 640, 656,
-		  752, 800, 0, 480, 490, 492, 525, 0,
-		  DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC) },
-		&meson_hdmi_encp_mode_640x480_60,
-	},
-	/* 800x600@60Hz */
-	{
-		{ DRM_MODE("800x600", DRM_MODE_TYPE_DRIVER, 40000, 800, 840,
-		  968, 1056, 0, 600, 601, 605, 628, 0,
-		  DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-		&meson_hdmi_encp_mode_800x600_60,
-	},
-	/* 1024x768@60Hz */
-	{
-		{ DRM_MODE("1024x768", DRM_MODE_TYPE_DRIVER, 65000, 1024,
-		  1048, 1184, 1344, 0, 768, 771, 777, 806, 0,
-		  DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC) },
-		&meson_hdmi_encp_mode_1024x768_60,
-	},
-	/* 1152x864@75Hz */
-	{
-		{ DRM_MODE("1152x864", DRM_MODE_TYPE_DRIVER, 108000, 1152,
-		  1216, 1344, 1600, 0, 864, 865, 868, 900, 0,
-		  DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-		&meson_hdmi_encp_mode_1152x864_75,
-	},
-	/* 1280x1024@60Hz */
-	{
-		{ DRM_MODE("1280x1024", DRM_MODE_TYPE_DRIVER, 108000, 1280,
-		  1328, 1440, 1688, 0, 1024, 1025, 1028, 1066, 0,
-		  DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-		&meson_hdmi_encp_mode_1280x1024_60,
-	},
-	/* 1600x1200@60Hz */
-	{
-		{ DRM_MODE("1600x1200", DRM_MODE_TYPE_DRIVER, 162000, 1600,
-		  1664, 1856, 2160, 0, 1200, 1201, 1204, 1250, 0,
-		  DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-		&meson_hdmi_encp_mode_1600x1200_60,
-	},
-	/* 1920x1080@60Hz */
-	{
-		{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 148500, 1920,
-		  2008, 2052, 2200, 0, 1080, 1084, 1089, 1125, 0,
-		  DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC) },
-		&meson_hdmi_encp_mode_1080p60
-	},
-	{ }, /* sentinel */
-};
-
 struct meson_hdmi_venc_vic_mode {
 	unsigned int vic;
 	union meson_hdmi_venc_mode *mode;
@@ -1044,17 +736,20 @@ static unsigned long modulo(unsigned long a, unsigned long b)
 		return a;
 }
 
-bool meson_venc_hdmi_supported_mode(const struct drm_display_mode *mode)
+enum drm_mode_status
+meson_venc_hdmi_supported_mode(const struct drm_display_mode *mode)
 {
-	struct meson_hdmi_venc_dmt_mode *vmode = meson_hdmi_venc_dmt_modes;
+	if (mode->flags & ~(DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NHSYNC |
+			    DRM_MODE_FLAG_PVSYNC | DRM_MODE_FLAG_NVSYNC))
+		return MODE_BAD;
 
-	while (vmode->mode) {
-		if (drm_mode_equal(&vmode->drm_mode, mode))
-			return true;
-		vmode++;
-	}
+	if (mode->hdisplay < 640 || mode->hdisplay > 1920)
+		return MODE_BAD_HVALUE;
 
-	return false;
+	if (mode->vdisplay < 480 || mode->vdisplay > 1200)
+		return MODE_BAD_VVALUE;
+
+	return MODE_OK;
 }
 EXPORT_SYMBOL_GPL(meson_venc_hdmi_supported_mode);
 
@@ -1072,18 +767,29 @@ bool meson_venc_hdmi_supported_vic(int vic)
 }
 EXPORT_SYMBOL_GPL(meson_venc_hdmi_supported_vic);
 
-static union meson_hdmi_venc_mode
-*meson_venc_hdmi_get_dmt_vmode(const struct drm_display_mode *mode)
+void meson_venc_hdmi_get_dmt_vmode(const struct drm_display_mode *mode,
+				   union meson_hdmi_venc_mode *dmt_mode)
 {
-	struct meson_hdmi_venc_dmt_mode *vmode = meson_hdmi_venc_dmt_modes;
-
-	while (vmode->mode) {
-		if (drm_mode_equal(&vmode->drm_mode, mode))
-			return vmode->mode;
-		vmode++;
-	}
-
-	return NULL;
+	memset(dmt_mode, 0, sizeof(*dmt_mode));
+
+	dmt_mode->encp.dvi_settings = 0x21;
+	dmt_mode->encp.video_mode = 0x4040;
+	dmt_mode->encp.video_mode_adv = 0x18;
+	dmt_mode->encp.max_pxcnt = mode->htotal - 1;
+	dmt_mode->encp.havon_begin = mode->htotal - mode->hsync_start;
+	dmt_mode->encp.havon_end = dmt_mode->encp.havon_begin +
+				   mode->hdisplay - 1;
+	dmt_mode->encp.vavon_bline = mode->vtotal - mode->vsync_start;
+	dmt_mode->encp.vavon_eline = dmt_mode->encp.vavon_bline +
+				     mode->vdisplay - 1;
+	dmt_mode->encp.hso_begin = 0;
+	dmt_mode->encp.hso_end = mode->hsync_end - mode->hsync_start;
+	dmt_mode->encp.vso_begin = 30;
+	dmt_mode->encp.vso_end = 50;
+	dmt_mode->encp.vso_bline = 0;
+	dmt_mode->encp.vso_eline = mode->vsync_end - mode->vsync_start;
+	dmt_mode->encp.vso_eline_present = true;
+	dmt_mode->encp.max_lncnt = mode->vtotal - 1;
 }
 
 static union meson_hdmi_venc_mode *meson_venc_hdmi_get_vic_vmode(int vic)
@@ -1120,6 +826,7 @@ void meson_venc_hdmi_mode_set(struct meson_drm *priv, int vic,
 			      struct drm_display_mode *mode)
 {
 	union meson_hdmi_venc_mode *vmode = NULL;
+	union meson_hdmi_venc_mode vmode_dmt;
 	bool use_enci = false;
 	bool venc_repeat = false;
 	bool hdmi_repeat = false;
@@ -1147,14 +854,17 @@ void meson_venc_hdmi_mode_set(struct meson_drm *priv, int vic,
 	unsigned int sof_lines;
 	unsigned int vsync_lines;
 
-	if (meson_venc_hdmi_supported_vic(vic))
+	if (meson_venc_hdmi_supported_vic(vic)) {
 		vmode = meson_venc_hdmi_get_vic_vmode(vic);
-	else
-		vmode = meson_venc_hdmi_get_dmt_vmode(mode);
-	if (!vmode) {
-		dev_err(priv->dev, "%s: Fatal Error, unsupported mode "
-			DRM_MODE_FMT "\n", __func__, DRM_MODE_ARG(mode));
-		return;
+		if (!vmode) {
+			dev_err(priv->dev, "%s: Fatal Error, unsupported mode "
+				DRM_MODE_FMT "\n", __func__,
+				DRM_MODE_ARG(mode));
+			return;
+		}
+	} else {
+		meson_venc_hdmi_get_dmt_vmode(mode, &vmode_dmt);
+		vmode = &vmode_dmt;
 	}
 
 	/* Use VENCI for 480i and 576i and double HDMI pixels */
diff --git a/drivers/gpu/drm/meson/meson_venc.h b/drivers/gpu/drm/meson/meson_venc.h
index 7c18a36a0dd0..97eaebbfa0c4 100644
--- a/drivers/gpu/drm/meson/meson_venc.h
+++ b/drivers/gpu/drm/meson/meson_venc.h
@@ -58,7 +58,8 @@ struct meson_cvbs_enci_mode {
 };
 
 /* HDMI Clock parameters */
-bool meson_venc_hdmi_supported_mode(const struct drm_display_mode *mode);
+enum drm_mode_status
+meson_venc_hdmi_supported_mode(const struct drm_display_mode *mode);
 bool meson_venc_hdmi_supported_vic(int vic);
 bool meson_venc_hdmi_venc_repeat(int vic);
 
diff --git a/drivers/gpu/drm/meson/meson_venc_cvbs.c b/drivers/gpu/drm/meson/meson_venc_cvbs.c
index 79d95ca8a0c0..f7945bae3b4a 100644
--- a/drivers/gpu/drm/meson/meson_venc_cvbs.c
+++ b/drivers/gpu/drm/meson/meson_venc_cvbs.c
@@ -282,7 +282,7 @@ int meson_venc_cvbs_create(struct meson_drm *priv)
 
 	encoder->possible_crtcs = BIT(0);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 8918539a19aa..acf7bfe68454 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -1553,7 +1553,7 @@ static int mga_vga_get_modes(struct drm_connector *connector)
 
 	edid = drm_get_edid(connector, &mga_connector->i2c->adapter);
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 	}
@@ -1747,7 +1747,7 @@ int mgag200_modeset_init(struct mga_device *mdev)
 		return -1;
 	}
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	ret = mgag200_fbdev_init(mdev);
 	if (ret) {
diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index 38cbde971b48..843a9d40c05e 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -12,6 +12,7 @@ config DRM_MSM
 	select SHMEM
 	select TMPFS
 	select QCOM_SCM
+	select WANT_DEV_COREDUMP
 	select SND_SOC_HDMI_CODEC if SND_SOC
 	select SYNC_FILE
 	select PM_OPP
diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile
index cd40c050b2d7..7c773e003663 100644
--- a/drivers/gpu/drm/msm/Makefile
+++ b/drivers/gpu/drm/msm/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 ccflags-y := -Idrivers/gpu/drm/msm
+ccflags-y += -Idrivers/gpu/drm/msm/disp/dpu1
 ccflags-$(CONFIG_DRM_MSM_DSI) += -Idrivers/gpu/drm/msm/dsi
 
 msm-y := \
@@ -45,6 +46,33 @@ msm-y := \
 	disp/mdp5/mdp5_mixer.o \
 	disp/mdp5/mdp5_plane.o \
 	disp/mdp5/mdp5_smp.o \
+	disp/dpu1/dpu_core_irq.o \
+	disp/dpu1/dpu_core_perf.o \
+	disp/dpu1/dpu_crtc.o \
+	disp/dpu1/dpu_encoder.o \
+	disp/dpu1/dpu_encoder_phys_cmd.o \
+	disp/dpu1/dpu_encoder_phys_vid.o \
+	disp/dpu1/dpu_formats.o \
+	disp/dpu1/dpu_hw_blk.o \
+	disp/dpu1/dpu_hw_catalog.o \
+	disp/dpu1/dpu_hw_cdm.o \
+	disp/dpu1/dpu_hw_ctl.o \
+	disp/dpu1/dpu_hw_interrupts.o \
+	disp/dpu1/dpu_hw_intf.o \
+	disp/dpu1/dpu_hw_lm.o \
+	disp/dpu1/dpu_hw_pingpong.o \
+	disp/dpu1/dpu_hw_sspp.o \
+	disp/dpu1/dpu_hw_top.o \
+	disp/dpu1/dpu_hw_util.o \
+	disp/dpu1/dpu_hw_vbif.o \
+	disp/dpu1/dpu_io_util.o \
+	disp/dpu1/dpu_irq.o \
+	disp/dpu1/dpu_kms.o \
+	disp/dpu1/dpu_mdss.o \
+	disp/dpu1/dpu_plane.o \
+	disp/dpu1/dpu_power_handle.o \
+	disp/dpu1/dpu_rm.o \
+	disp/dpu1/dpu_vbif.o \
 	msm_atomic.o \
 	msm_debugfs.o \
 	msm_drv.o \
@@ -62,7 +90,8 @@ msm-y := \
 	msm_ringbuffer.o \
 	msm_submitqueue.o
 
-msm-$(CONFIG_DEBUG_FS) += adreno/a5xx_debugfs.o
+msm-$(CONFIG_DEBUG_FS) += adreno/a5xx_debugfs.o \
+			  disp/dpu1/dpu_dbg.o
 
 msm-$(CONFIG_DRM_FBDEV_EMULATION) += msm_fbdev.o
 msm-$(CONFIG_COMMON_CLK) += disp/mdp4/mdp4_lvds_pll.o
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 3ebbeb3a9b68..669c2d4b070d 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -411,15 +411,6 @@ static const unsigned int a3xx_registers[] = {
 	~0   /* sentinel */
 };
 
-#ifdef CONFIG_DEBUG_FS
-static void a3xx_show(struct msm_gpu *gpu, struct seq_file *m)
-{
-	seq_printf(m, "status:   %08x\n",
-			gpu_read(gpu, REG_A3XX_RBBM_STATUS));
-	adreno_show(gpu, m);
-}
-#endif
-
 /* would be nice to not have to duplicate the _show() stuff with printk(): */
 static void a3xx_dump(struct msm_gpu *gpu)
 {
@@ -427,6 +418,21 @@ static void a3xx_dump(struct msm_gpu *gpu)
 			gpu_read(gpu, REG_A3XX_RBBM_STATUS));
 	adreno_dump(gpu);
 }
+
+static struct msm_gpu_state *a3xx_gpu_state_get(struct msm_gpu *gpu)
+{
+	struct msm_gpu_state *state = kzalloc(sizeof(*state), GFP_KERNEL);
+
+	if (!state)
+		return ERR_PTR(-ENOMEM);
+
+	adreno_gpu_state_get(gpu, state);
+
+	state->rbbm_status = gpu_read(gpu, REG_A3XX_RBBM_STATUS);
+
+	return state;
+}
+
 /* Register offset defines for A3XX */
 static const unsigned int a3xx_register_offsets[REG_ADRENO_REGISTER_MAX] = {
 	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE, REG_AXXX_CP_RB_BASE),
@@ -450,9 +456,11 @@ static const struct adreno_gpu_funcs funcs = {
 		.active_ring = adreno_active_ring,
 		.irq = a3xx_irq,
 		.destroy = a3xx_destroy,
-#ifdef CONFIG_DEBUG_FS
-		.show = a3xx_show,
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
+		.show = adreno_show,
 #endif
+		.gpu_state_get = a3xx_gpu_state_get,
+		.gpu_state_put = adreno_gpu_state_put,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index 16d3d596638e..7c4e6dc1ed59 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -455,15 +455,19 @@ static const unsigned int a4xx_registers[] = {
 	~0 /* sentinel */
 };
 
-#ifdef CONFIG_DEBUG_FS
-static void a4xx_show(struct msm_gpu *gpu, struct seq_file *m)
+static struct msm_gpu_state *a4xx_gpu_state_get(struct msm_gpu *gpu)
 {
-	seq_printf(m, "status:   %08x\n",
-			gpu_read(gpu, REG_A4XX_RBBM_STATUS));
-	adreno_show(gpu, m);
+	struct msm_gpu_state *state = kzalloc(sizeof(*state), GFP_KERNEL);
+
+	if (!state)
+		return ERR_PTR(-ENOMEM);
+
+	adreno_gpu_state_get(gpu, state);
 
+	state->rbbm_status = gpu_read(gpu, REG_A4XX_RBBM_STATUS);
+
+	return state;
 }
-#endif
 
 /* Register offset defines for A4XX, in order of enum adreno_regs */
 static const unsigned int a4xx_register_offsets[REG_ADRENO_REGISTER_MAX] = {
@@ -538,9 +542,11 @@ static const struct adreno_gpu_funcs funcs = {
 		.active_ring = adreno_active_ring,
 		.irq = a4xx_irq,
 		.destroy = a4xx_destroy,
-#ifdef CONFIG_DEBUG_FS
-		.show = a4xx_show,
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
+		.show = adreno_show,
 #endif
+		.gpu_state_get = a4xx_gpu_state_get,
+		.gpu_state_put = adreno_gpu_state_put,
 	},
 	.get_timestamp = a4xx_get_timestamp,
 };
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index d39400e5bc42..bd84f71d27d8 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -19,6 +19,7 @@
 #include <linux/soc/qcom/mdt_loader.h>
 #include <linux/pm_opp.h>
 #include <linux/nvmem-consumer.h>
+#include <linux/iopoll.h>
 #include "msm_gem.h"
 #include "msm_mmu.h"
 #include "a5xx_gpu.h"
@@ -1123,8 +1124,9 @@ static const u32 a5xx_registers[] = {
 	0xE800, 0xE806, 0xE810, 0xE89A, 0xE8A0, 0xE8A4, 0xE8AA, 0xE8EB,
 	0xE900, 0xE905, 0xEB80, 0xEB8F, 0xEBB0, 0xEBB0, 0xEC00, 0xEC05,
 	0xEC08, 0xECE9, 0xECF0, 0xECF0, 0xEA80, 0xEA80, 0xEA82, 0xEAA3,
-	0xEAA5, 0xEAC2, 0xA800, 0xA8FF, 0xAC60, 0xAC60, 0xB000, 0xB97F,
-	0xB9A0, 0xB9BF, ~0
+	0xEAA5, 0xEAC2, 0xA800, 0xA800, 0xA820, 0xA828, 0xA840, 0xA87D,
+	0XA880, 0xA88D, 0xA890, 0xA8A3, 0xA8D0, 0xA8D8, 0xA8E0, 0xA8F5,
+	0xAC60, 0xAC60, ~0,
 };
 
 static void a5xx_dump(struct msm_gpu *gpu)
@@ -1195,19 +1197,231 @@ static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
 	return 0;
 }
 
-#ifdef CONFIG_DEBUG_FS
-static void a5xx_show(struct msm_gpu *gpu, struct seq_file *m)
+struct a5xx_crashdumper {
+	void *ptr;
+	struct drm_gem_object *bo;
+	u64 iova;
+};
+
+struct a5xx_gpu_state {
+	struct msm_gpu_state base;
+	u32 *hlsqregs;
+};
+
+#define gpu_poll_timeout(gpu, addr, val, cond, interval, timeout) \
+	readl_poll_timeout((gpu)->mmio + ((addr) << 2), val, cond, \
+		interval, timeout)
+
+static int a5xx_crashdumper_init(struct msm_gpu *gpu,
+		struct a5xx_crashdumper *dumper)
 {
-	seq_printf(m, "status:   %08x\n",
-			gpu_read(gpu, REG_A5XX_RBBM_STATUS));
+	dumper->ptr = msm_gem_kernel_new_locked(gpu->dev,
+		SZ_1M, MSM_BO_UNCACHED, gpu->aspace,
+		&dumper->bo, &dumper->iova);
 
-	/*
-	 * Temporarily disable hardware clock gating before going into
-	 * adreno_show to avoid issues while reading the registers
-	 */
+	if (IS_ERR(dumper->ptr))
+		return PTR_ERR(dumper->ptr);
+
+	return 0;
+}
+
+static void a5xx_crashdumper_free(struct msm_gpu *gpu,
+		struct a5xx_crashdumper *dumper)
+{
+	msm_gem_put_iova(dumper->bo, gpu->aspace);
+	msm_gem_put_vaddr(dumper->bo);
+
+	drm_gem_object_unreference(dumper->bo);
+}
+
+static int a5xx_crashdumper_run(struct msm_gpu *gpu,
+		struct a5xx_crashdumper *dumper)
+{
+	u32 val;
+
+	if (IS_ERR_OR_NULL(dumper->ptr))
+		return -EINVAL;
+
+	gpu_write64(gpu, REG_A5XX_CP_CRASH_SCRIPT_BASE_LO,
+		REG_A5XX_CP_CRASH_SCRIPT_BASE_HI, dumper->iova);
+
+	gpu_write(gpu, REG_A5XX_CP_CRASH_DUMP_CNTL, 1);
+
+	return gpu_poll_timeout(gpu, REG_A5XX_CP_CRASH_DUMP_CNTL, val,
+		val & 0x04, 100, 10000);
+}
+
+/*
+ * These are a list of the registers that need to be read through the HLSQ
+ * aperture through the crashdumper.  These are not nominally accessible from
+ * the CPU on a secure platform.
+ */
+static const struct {
+	u32 type;
+	u32 regoffset;
+	u32 count;
+} a5xx_hlsq_aperture_regs[] = {
+	{ 0x35, 0xe00, 0x32 },   /* HSLQ non-context */
+	{ 0x31, 0x2080, 0x1 },   /* HLSQ 2D context 0 */
+	{ 0x33, 0x2480, 0x1 },   /* HLSQ 2D context 1 */
+	{ 0x32, 0xe780, 0x62 },  /* HLSQ 3D context 0 */
+	{ 0x34, 0xef80, 0x62 },  /* HLSQ 3D context 1 */
+	{ 0x3f, 0x0ec0, 0x40 },  /* SP non-context */
+	{ 0x3d, 0x2040, 0x1 },   /* SP 2D context 0 */
+	{ 0x3b, 0x2440, 0x1 },   /* SP 2D context 1 */
+	{ 0x3e, 0xe580, 0x170 }, /* SP 3D context 0 */
+	{ 0x3c, 0xed80, 0x170 }, /* SP 3D context 1 */
+	{ 0x3a, 0x0f00, 0x1c },  /* TP non-context */
+	{ 0x38, 0x2000, 0xa },   /* TP 2D context 0 */
+	{ 0x36, 0x2400, 0xa },   /* TP 2D context 1 */
+	{ 0x39, 0xe700, 0x80 },  /* TP 3D context 0 */
+	{ 0x37, 0xef00, 0x80 },  /* TP 3D context 1 */
+};
+
+static void a5xx_gpu_state_get_hlsq_regs(struct msm_gpu *gpu,
+		struct a5xx_gpu_state *a5xx_state)
+{
+	struct a5xx_crashdumper dumper = { 0 };
+	u32 offset, count = 0;
+	u64 *ptr;
+	int i;
+
+	if (a5xx_crashdumper_init(gpu, &dumper))
+		return;
+
+	/* The script will be written at offset 0 */
+	ptr = dumper.ptr;
+
+	/* Start writing the data at offset 256k */
+	offset = dumper.iova + (256 * SZ_1K);
+
+	/* Count how many additional registers to get from the HLSQ aperture */
+	for (i = 0; i < ARRAY_SIZE(a5xx_hlsq_aperture_regs); i++)
+		count += a5xx_hlsq_aperture_regs[i].count;
+
+	a5xx_state->hlsqregs = kcalloc(count, sizeof(u32), GFP_KERNEL);
+	if (!a5xx_state->hlsqregs)
+		return;
+
+	/* Build the crashdump script */
+	for (i = 0; i < ARRAY_SIZE(a5xx_hlsq_aperture_regs); i++) {
+		u32 type = a5xx_hlsq_aperture_regs[i].type;
+		u32 c = a5xx_hlsq_aperture_regs[i].count;
+
+		/* Write the register to select the desired bank */
+		*ptr++ = ((u64) type << 8);
+		*ptr++ = (((u64) REG_A5XX_HLSQ_DBG_READ_SEL) << 44) |
+			(1 << 21) | 1;
+
+		*ptr++ = offset;
+		*ptr++ = (((u64) REG_A5XX_HLSQ_DBG_AHB_READ_APERTURE) << 44)
+			| c;
+
+		offset += c * sizeof(u32);
+	}
+
+	/* Write two zeros to close off the script */
+	*ptr++ = 0;
+	*ptr++ = 0;
+
+	if (a5xx_crashdumper_run(gpu, &dumper)) {
+		kfree(a5xx_state->hlsqregs);
+		a5xx_crashdumper_free(gpu, &dumper);
+		return;
+	}
+
+	/* Copy the data from the crashdumper to the state */
+	memcpy(a5xx_state->hlsqregs, dumper.ptr + (256 * SZ_1K),
+		count * sizeof(u32));
+
+	a5xx_crashdumper_free(gpu, &dumper);
+}
+
+static struct msm_gpu_state *a5xx_gpu_state_get(struct msm_gpu *gpu)
+{
+	struct a5xx_gpu_state *a5xx_state = kzalloc(sizeof(*a5xx_state),
+			GFP_KERNEL);
+
+	if (!a5xx_state)
+		return ERR_PTR(-ENOMEM);
+
+	/* Temporarily disable hardware clock gating before reading the hw */
 	a5xx_set_hwcg(gpu, false);
-	adreno_show(gpu, m);
+
+	/* First get the generic state from the adreno core */
+	adreno_gpu_state_get(gpu, &(a5xx_state->base));
+
+	a5xx_state->base.rbbm_status = gpu_read(gpu, REG_A5XX_RBBM_STATUS);
+
+	/* Get the HLSQ regs with the help of the crashdumper */
+	a5xx_gpu_state_get_hlsq_regs(gpu, a5xx_state);
+
 	a5xx_set_hwcg(gpu, true);
+
+	return &a5xx_state->base;
+}
+
+static void a5xx_gpu_state_destroy(struct kref *kref)
+{
+	struct msm_gpu_state *state = container_of(kref,
+		struct msm_gpu_state, ref);
+	struct a5xx_gpu_state *a5xx_state = container_of(state,
+		struct a5xx_gpu_state, base);
+
+	kfree(a5xx_state->hlsqregs);
+
+	adreno_gpu_state_destroy(state);
+	kfree(a5xx_state);
+}
+
+int a5xx_gpu_state_put(struct msm_gpu_state *state)
+{
+	if (IS_ERR_OR_NULL(state))
+		return 1;
+
+	return kref_put(&state->ref, a5xx_gpu_state_destroy);
+}
+
+
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
+void a5xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
+		struct drm_printer *p)
+{
+	int i, j;
+	u32 pos = 0;
+	struct a5xx_gpu_state *a5xx_state = container_of(state,
+		struct a5xx_gpu_state, base);
+
+	if (IS_ERR_OR_NULL(state))
+		return;
+
+	adreno_show(gpu, state, p);
+
+	/* Dump the additional a5xx HLSQ registers */
+	if (!a5xx_state->hlsqregs)
+		return;
+
+	drm_printf(p, "registers-hlsq:\n");
+
+	for (i = 0; i < ARRAY_SIZE(a5xx_hlsq_aperture_regs); i++) {
+		u32 o = a5xx_hlsq_aperture_regs[i].regoffset;
+		u32 c = a5xx_hlsq_aperture_regs[i].count;
+
+		for (j = 0; j < c; j++, pos++, o++) {
+			/*
+			 * To keep the crashdump simple we pull the entire range
+			 * for each register type but not all of the registers
+			 * in the range are valid. Fortunately invalid registers
+			 * stick out like a sore thumb with a value of
+			 * 0xdeadbeef
+			 */
+			if (a5xx_state->hlsqregs[pos] == 0xdeadbeef)
+				continue;
+
+			drm_printf(p, "  - { offset: 0x%04x, value: 0x%08x }\n",
+				o << 2, a5xx_state->hlsqregs[pos]);
+		}
+	}
 }
 #endif
 
@@ -1239,11 +1453,15 @@ static const struct adreno_gpu_funcs funcs = {
 		.active_ring = a5xx_active_ring,
 		.irq = a5xx_irq,
 		.destroy = a5xx_destroy,
-#ifdef CONFIG_DEBUG_FS
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
 		.show = a5xx_show,
+#endif
+#if defined(CONFIG_DEBUG_FS)
 		.debugfs_init = a5xx_debugfs_init,
 #endif
 		.gpu_busy = a5xx_gpu_busy,
+		.gpu_state_get = a5xx_gpu_state_get,
+		.gpu_state_put = a5xx_gpu_state_put,
 	},
 	.get_timestamp = a5xx_get_timestamp,
 };
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 0ae5ace65462..44813624a286 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -35,6 +35,7 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_PFP] = "a300_pfp.fw",
 		},
 		.gmem  = SZ_256K,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a3xx_gpu_init,
 	}, {
 		.rev   = ADRENO_REV(3, 0, 6, 0),
@@ -45,6 +46,7 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_PFP] = "a300_pfp.fw",
 		},
 		.gmem  = SZ_128K,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a3xx_gpu_init,
 	}, {
 		.rev   = ADRENO_REV(3, 2, ANY_ID, ANY_ID),
@@ -55,6 +57,7 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_PFP] = "a300_pfp.fw",
 		},
 		.gmem  = SZ_512K,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a3xx_gpu_init,
 	}, {
 		.rev   = ADRENO_REV(3, 3, 0, ANY_ID),
@@ -65,6 +68,7 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_PFP] = "a330_pfp.fw",
 		},
 		.gmem  = SZ_1M,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a3xx_gpu_init,
 	}, {
 		.rev   = ADRENO_REV(4, 2, 0, ANY_ID),
@@ -75,6 +79,7 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_PFP] = "a420_pfp.fw",
 		},
 		.gmem  = (SZ_1M + SZ_512K),
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a4xx_gpu_init,
 	}, {
 		.rev   = ADRENO_REV(4, 3, 0, ANY_ID),
@@ -85,6 +90,7 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_PFP] = "a420_pfp.fw",
 		},
 		.gmem  = (SZ_1M + SZ_512K),
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a4xx_gpu_init,
 	}, {
 		.rev = ADRENO_REV(5, 3, 0, 2),
@@ -96,6 +102,11 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_GPMU] = "a530v3_gpmu.fw2",
 		},
 		.gmem = SZ_1M,
+		/*
+		 * Increase inactive period to 250 to avoid bouncing
+		 * the GDSC which appears to make it grumpy
+		 */
+		.inactive_period = 250,
 		.quirks = ADRENO_QUIRK_TWO_PASS_USE_WFI |
 			ADRENO_QUIRK_FAULT_DETECT_MASK,
 		.init = a5xx_gpu_init,
@@ -158,7 +169,7 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev)
 	mutex_lock(&dev->struct_mutex);
 	ret = msm_gpu_hw_init(gpu);
 	mutex_unlock(&dev->struct_mutex);
-	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_put_autosuspend(&pdev->dev);
 	if (ret) {
 		dev_err(dev->dev, "gpu hw init failed: %d\n", ret);
 		return NULL;
@@ -316,6 +327,7 @@ static int adreno_suspend(struct device *dev)
 #endif
 
 static const struct dev_pm_ops adreno_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
 	SET_RUNTIME_PM_OPS(adreno_suspend, adreno_resume, NULL)
 };
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 17d0506d058c..38ac50b73829 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -17,6 +17,7 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/ascii85.h>
 #include <linux/pm_opp.h>
 #include "adreno_gpu.h"
 #include "msm_gem.h"
@@ -368,40 +369,185 @@ bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 	return false;
 }
 
-#ifdef CONFIG_DEBUG_FS
-void adreno_show(struct msm_gpu *gpu, struct seq_file *m)
+int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	int i, count = 0;
+
+	kref_init(&state->ref);
+
+	ktime_get_real_ts64(&state->time);
+
+	for (i = 0; i < gpu->nr_rings; i++) {
+		int size = 0, j;
+
+		state->ring[i].fence = gpu->rb[i]->memptrs->fence;
+		state->ring[i].iova = gpu->rb[i]->iova;
+		state->ring[i].seqno = gpu->rb[i]->seqno;
+		state->ring[i].rptr = get_rptr(adreno_gpu, gpu->rb[i]);
+		state->ring[i].wptr = get_wptr(gpu->rb[i]);
+
+		/* Copy at least 'wptr' dwords of the data */
+		size = state->ring[i].wptr;
+
+		/* After wptr find the last non zero dword to save space */
+		for (j = state->ring[i].wptr; j < MSM_GPU_RINGBUFFER_SZ >> 2; j++)
+			if (gpu->rb[i]->start[j])
+				size = j + 1;
+
+		if (size) {
+			state->ring[i].data = kmalloc(size << 2, GFP_KERNEL);
+			if (state->ring[i].data) {
+				memcpy(state->ring[i].data, gpu->rb[i]->start, size << 2);
+				state->ring[i].data_size = size << 2;
+			}
+		}
+	}
+
+	/* Count the number of registers */
+	for (i = 0; adreno_gpu->registers[i] != ~0; i += 2)
+		count += adreno_gpu->registers[i + 1] -
+			adreno_gpu->registers[i] + 1;
+
+	state->registers = kcalloc(count * 2, sizeof(u32), GFP_KERNEL);
+	if (state->registers) {
+		int pos = 0;
+
+		for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) {
+			u32 start = adreno_gpu->registers[i];
+			u32 end   = adreno_gpu->registers[i + 1];
+			u32 addr;
+
+			for (addr = start; addr <= end; addr++) {
+				state->registers[pos++] = addr;
+				state->registers[pos++] = gpu_read(gpu, addr);
+			}
+		}
+
+		state->nr_registers = count;
+	}
+
+	return 0;
+}
+
+void adreno_gpu_state_destroy(struct msm_gpu_state *state)
+{
 	int i;
 
-	seq_printf(m, "revision: %d (%d.%d.%d.%d)\n",
+	for (i = 0; i < ARRAY_SIZE(state->ring); i++)
+		kfree(state->ring[i].data);
+
+	for (i = 0; state->bos && i < state->nr_bos; i++)
+		kvfree(state->bos[i].data);
+
+	kfree(state->bos);
+	kfree(state->comm);
+	kfree(state->cmd);
+	kfree(state->registers);
+}
+
+static void adreno_gpu_state_kref_destroy(struct kref *kref)
+{
+	struct msm_gpu_state *state = container_of(kref,
+		struct msm_gpu_state, ref);
+
+	adreno_gpu_state_destroy(state);
+	kfree(state);
+}
+
+int adreno_gpu_state_put(struct msm_gpu_state *state)
+{
+	if (IS_ERR_OR_NULL(state))
+		return 1;
+
+	return kref_put(&state->ref, adreno_gpu_state_kref_destroy);
+}
+
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
+
+static void adreno_show_object(struct drm_printer *p, u32 *ptr, int len)
+{
+	char out[ASCII85_BUFSZ];
+	long l, datalen, i;
+
+	if (!ptr || !len)
+		return;
+
+	/*
+	 * Only dump the non-zero part of the buffer - rarely will any data
+	 * completely fill the entire allocated size of the buffer
+	 */
+	for (datalen = 0, i = 0; i < len >> 2; i++) {
+		if (ptr[i])
+			datalen = (i << 2) + 1;
+	}
+
+	/* Skip printing the object if it is empty */
+	if (datalen == 0)
+		return;
+
+	l = ascii85_encode_len(datalen);
+
+	drm_puts(p, "    data: !!ascii85 |\n");
+	drm_puts(p, "     ");
+
+	for (i = 0; i < l; i++)
+		drm_puts(p, ascii85_encode(ptr[i], out));
+
+	drm_puts(p, "\n");
+}
+
+void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
+		struct drm_printer *p)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	int i;
+
+	if (IS_ERR_OR_NULL(state))
+		return;
+
+	drm_printf(p, "revision: %d (%d.%d.%d.%d)\n",
 			adreno_gpu->info->revn, adreno_gpu->rev.core,
 			adreno_gpu->rev.major, adreno_gpu->rev.minor,
 			adreno_gpu->rev.patchid);
 
-	for (i = 0; i < gpu->nr_rings; i++) {
-		struct msm_ringbuffer *ring = gpu->rb[i];
+	drm_printf(p, "rbbm-status: 0x%08x\n", state->rbbm_status);
 
-		seq_printf(m, "rb %d: fence:    %d/%d\n", i,
-			ring->memptrs->fence, ring->seqno);
+	drm_puts(p, "ringbuffer:\n");
 
-		seq_printf(m, "      rptr:     %d\n",
-			get_rptr(adreno_gpu, ring));
-		seq_printf(m, "rb wptr:  %d\n", get_wptr(ring));
+	for (i = 0; i < gpu->nr_rings; i++) {
+		drm_printf(p, "  - id: %d\n", i);
+		drm_printf(p, "    iova: 0x%016llx\n", state->ring[i].iova);
+		drm_printf(p, "    last-fence: %d\n", state->ring[i].seqno);
+		drm_printf(p, "    retired-fence: %d\n", state->ring[i].fence);
+		drm_printf(p, "    rptr: %d\n", state->ring[i].rptr);
+		drm_printf(p, "    wptr: %d\n", state->ring[i].wptr);
+		drm_printf(p, "    size: %d\n", MSM_GPU_RINGBUFFER_SZ);
+
+		adreno_show_object(p, state->ring[i].data,
+			state->ring[i].data_size);
 	}
 
-	/* dump these out in a form that can be parsed by demsm: */
-	seq_printf(m, "IO:region %s 00000000 00020000\n", gpu->name);
-	for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) {
-		uint32_t start = adreno_gpu->registers[i];
-		uint32_t end   = adreno_gpu->registers[i+1];
-		uint32_t addr;
+	if (state->bos) {
+		drm_puts(p, "bos:\n");
 
-		for (addr = start; addr <= end; addr++) {
-			uint32_t val = gpu_read(gpu, addr);
-			seq_printf(m, "IO:R %08x %08x\n", addr<<2, val);
+		for (i = 0; i < state->nr_bos; i++) {
+			drm_printf(p, "  - iova: 0x%016llx\n",
+				state->bos[i].iova);
+			drm_printf(p, "    size: %zd\n", state->bos[i].size);
+
+			adreno_show_object(p, state->bos[i].data,
+				state->bos[i].size);
 		}
 	}
+
+	drm_puts(p, "registers:\n");
+
+	for (i = 0; i < state->nr_registers; i++) {
+		drm_printf(p, "  - { offset: 0x%04x, value: 0x%08x }\n",
+			state->registers[i * 2] << 2,
+			state->registers[(i * 2) + 1]);
+	}
 }
 #endif
 
@@ -565,7 +711,8 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 
 	adreno_get_pwrlevels(&pdev->dev, gpu);
 
-	pm_runtime_set_autosuspend_delay(&pdev->dev, DRM_MSM_INACTIVE_PERIOD);
+	pm_runtime_set_autosuspend_delay(&pdev->dev,
+		adreno_gpu->info->inactive_period);
 	pm_runtime_use_autosuspend(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index d6b0e7b813f4..4406776597fd 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -84,6 +84,7 @@ struct adreno_info {
 	enum adreno_quirks quirks;
 	struct msm_gpu *(*init)(struct drm_device *dev);
 	const char *zapfw;
+	u32 inactive_period;
 };
 
 const struct adreno_info *adreno_info(struct adreno_rev rev);
@@ -214,8 +215,9 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 		struct msm_file_private *ctx);
 void adreno_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
 bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
-#ifdef CONFIG_DEBUG_FS
-void adreno_show(struct msm_gpu *gpu, struct seq_file *m);
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
+void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
+		struct drm_printer *p);
 #endif
 void adreno_dump_info(struct msm_gpu *gpu);
 void adreno_dump(struct msm_gpu *gpu);
@@ -228,6 +230,11 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 void adreno_gpu_cleanup(struct adreno_gpu *gpu);
 
 
+void adreno_gpu_state_destroy(struct msm_gpu_state *state);
+
+int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state);
+int adreno_gpu_state_put(struct msm_gpu_state *state);
+
 /* ringbuffer helpers (the parts that are adreno specific) */
 
 static inline void
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c
new file mode 100644
index 000000000000..879c13fe74e0
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c
@@ -0,0 +1,479 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/debugfs.h>
+#include <linux/irqdomain.h>
+#include <linux/irq.h>
+#include <linux/kthread.h>
+
+#include "dpu_core_irq.h"
+#include "dpu_trace.h"
+
+/**
+ * dpu_core_irq_callback_handler - dispatch core interrupts
+ * @arg:		private data of callback handler
+ * @irq_idx:		interrupt index
+ */
+static void dpu_core_irq_callback_handler(void *arg, int irq_idx)
+{
+	struct dpu_kms *dpu_kms = arg;
+	struct dpu_irq *irq_obj = &dpu_kms->irq_obj;
+	struct dpu_irq_callback *cb;
+	unsigned long irq_flags;
+
+	pr_debug("irq_idx=%d\n", irq_idx);
+
+	if (list_empty(&irq_obj->irq_cb_tbl[irq_idx])) {
+		DRM_ERROR("no registered cb, idx:%d enable_count:%d\n", irq_idx,
+			atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idx]));
+	}
+
+	atomic_inc(&irq_obj->irq_counts[irq_idx]);
+
+	/*
+	 * Perform registered function callback
+	 */
+	spin_lock_irqsave(&dpu_kms->irq_obj.cb_lock, irq_flags);
+	list_for_each_entry(cb, &irq_obj->irq_cb_tbl[irq_idx], list)
+		if (cb->func)
+			cb->func(cb->arg, irq_idx);
+	spin_unlock_irqrestore(&dpu_kms->irq_obj.cb_lock, irq_flags);
+
+	/*
+	 * Clear pending interrupt status in HW.
+	 * NOTE: dpu_core_irq_callback_handler is protected by top-level
+	 *       spinlock, so it is safe to clear any interrupt status here.
+	 */
+	dpu_kms->hw_intr->ops.clear_intr_status_nolock(
+			dpu_kms->hw_intr,
+			irq_idx);
+}
+
+int dpu_core_irq_idx_lookup(struct dpu_kms *dpu_kms,
+		enum dpu_intr_type intr_type, u32 instance_idx)
+{
+	if (!dpu_kms || !dpu_kms->hw_intr ||
+			!dpu_kms->hw_intr->ops.irq_idx_lookup)
+		return -EINVAL;
+
+	return dpu_kms->hw_intr->ops.irq_idx_lookup(intr_type,
+			instance_idx);
+}
+
+/**
+ * _dpu_core_irq_enable - enable core interrupt given by the index
+ * @dpu_kms:		Pointer to dpu kms context
+ * @irq_idx:		interrupt index
+ */
+static int _dpu_core_irq_enable(struct dpu_kms *dpu_kms, int irq_idx)
+{
+	unsigned long irq_flags;
+	int ret = 0, enable_count;
+
+	if (!dpu_kms || !dpu_kms->hw_intr ||
+			!dpu_kms->irq_obj.enable_counts ||
+			!dpu_kms->irq_obj.irq_counts) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+
+	if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->irq_idx_tbl_size) {
+		DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	enable_count = atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idx]);
+	DRM_DEBUG_KMS("irq_idx=%d enable_count=%d\n", irq_idx, enable_count);
+	trace_dpu_core_irq_enable_idx(irq_idx, enable_count);
+
+	if (atomic_inc_return(&dpu_kms->irq_obj.enable_counts[irq_idx]) == 1) {
+		ret = dpu_kms->hw_intr->ops.enable_irq(
+				dpu_kms->hw_intr,
+				irq_idx);
+		if (ret)
+			DPU_ERROR("Fail to enable IRQ for irq_idx:%d\n",
+					irq_idx);
+
+		DPU_DEBUG("irq_idx=%d ret=%d\n", irq_idx, ret);
+
+		spin_lock_irqsave(&dpu_kms->irq_obj.cb_lock, irq_flags);
+		/* empty callback list but interrupt is enabled */
+		if (list_empty(&dpu_kms->irq_obj.irq_cb_tbl[irq_idx]))
+			DPU_ERROR("irq_idx=%d enabled with no callback\n",
+					irq_idx);
+		spin_unlock_irqrestore(&dpu_kms->irq_obj.cb_lock, irq_flags);
+	}
+
+	return ret;
+}
+
+int dpu_core_irq_enable(struct dpu_kms *dpu_kms, int *irq_idxs, u32 irq_count)
+{
+	int i, ret = 0, counts;
+
+	if (!dpu_kms || !irq_idxs || !irq_count) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+
+	counts = atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idxs[0]]);
+	if (counts)
+		DRM_ERROR("irq_idx=%d enable_count=%d\n", irq_idxs[0], counts);
+
+	for (i = 0; (i < irq_count) && !ret; i++)
+		ret = _dpu_core_irq_enable(dpu_kms, irq_idxs[i]);
+
+	return ret;
+}
+
+/**
+ * _dpu_core_irq_disable - disable core interrupt given by the index
+ * @dpu_kms:		Pointer to dpu kms context
+ * @irq_idx:		interrupt index
+ */
+static int _dpu_core_irq_disable(struct dpu_kms *dpu_kms, int irq_idx)
+{
+	int ret = 0, enable_count;
+
+	if (!dpu_kms || !dpu_kms->hw_intr || !dpu_kms->irq_obj.enable_counts) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+
+	if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->irq_idx_tbl_size) {
+		DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	enable_count = atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idx]);
+	DRM_DEBUG_KMS("irq_idx=%d enable_count=%d\n", irq_idx, enable_count);
+	trace_dpu_core_irq_disable_idx(irq_idx, enable_count);
+
+	if (atomic_dec_return(&dpu_kms->irq_obj.enable_counts[irq_idx]) == 0) {
+		ret = dpu_kms->hw_intr->ops.disable_irq(
+				dpu_kms->hw_intr,
+				irq_idx);
+		if (ret)
+			DPU_ERROR("Fail to disable IRQ for irq_idx:%d\n",
+					irq_idx);
+		DPU_DEBUG("irq_idx=%d ret=%d\n", irq_idx, ret);
+	}
+
+	return ret;
+}
+
+int dpu_core_irq_disable(struct dpu_kms *dpu_kms, int *irq_idxs, u32 irq_count)
+{
+	int i, ret = 0, counts;
+
+	if (!dpu_kms || !irq_idxs || !irq_count) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+
+	counts = atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idxs[0]]);
+	if (counts == 2)
+		DRM_ERROR("irq_idx=%d enable_count=%d\n", irq_idxs[0], counts);
+
+	for (i = 0; (i < irq_count) && !ret; i++)
+		ret = _dpu_core_irq_disable(dpu_kms, irq_idxs[i]);
+
+	return ret;
+}
+
+u32 dpu_core_irq_read(struct dpu_kms *dpu_kms, int irq_idx, bool clear)
+{
+	if (!dpu_kms || !dpu_kms->hw_intr ||
+			!dpu_kms->hw_intr->ops.get_interrupt_status)
+		return 0;
+
+	if (irq_idx < 0) {
+		DPU_ERROR("[%pS] invalid irq_idx=%d\n",
+				__builtin_return_address(0), irq_idx);
+		return 0;
+	}
+
+	return dpu_kms->hw_intr->ops.get_interrupt_status(dpu_kms->hw_intr,
+			irq_idx, clear);
+}
+
+int dpu_core_irq_register_callback(struct dpu_kms *dpu_kms, int irq_idx,
+		struct dpu_irq_callback *register_irq_cb)
+{
+	unsigned long irq_flags;
+
+	if (!dpu_kms || !dpu_kms->irq_obj.irq_cb_tbl) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+
+	if (!register_irq_cb || !register_irq_cb->func) {
+		DPU_ERROR("invalid irq_cb:%d func:%d\n",
+				register_irq_cb != NULL,
+				register_irq_cb ?
+					register_irq_cb->func != NULL : -1);
+		return -EINVAL;
+	}
+
+	if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->irq_idx_tbl_size) {
+		DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	DPU_DEBUG("[%pS] irq_idx=%d\n", __builtin_return_address(0), irq_idx);
+
+	spin_lock_irqsave(&dpu_kms->irq_obj.cb_lock, irq_flags);
+	trace_dpu_core_irq_register_callback(irq_idx, register_irq_cb);
+	list_del_init(&register_irq_cb->list);
+	list_add_tail(&register_irq_cb->list,
+			&dpu_kms->irq_obj.irq_cb_tbl[irq_idx]);
+	spin_unlock_irqrestore(&dpu_kms->irq_obj.cb_lock, irq_flags);
+
+	return 0;
+}
+
+int dpu_core_irq_unregister_callback(struct dpu_kms *dpu_kms, int irq_idx,
+		struct dpu_irq_callback *register_irq_cb)
+{
+	unsigned long irq_flags;
+
+	if (!dpu_kms || !dpu_kms->irq_obj.irq_cb_tbl) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+
+	if (!register_irq_cb || !register_irq_cb->func) {
+		DPU_ERROR("invalid irq_cb:%d func:%d\n",
+				register_irq_cb != NULL,
+				register_irq_cb ?
+					register_irq_cb->func != NULL : -1);
+		return -EINVAL;
+	}
+
+	if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->irq_idx_tbl_size) {
+		DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	DPU_DEBUG("[%pS] irq_idx=%d\n", __builtin_return_address(0), irq_idx);
+
+	spin_lock_irqsave(&dpu_kms->irq_obj.cb_lock, irq_flags);
+	trace_dpu_core_irq_unregister_callback(irq_idx, register_irq_cb);
+	list_del_init(&register_irq_cb->list);
+	/* empty callback list but interrupt is still enabled */
+	if (list_empty(&dpu_kms->irq_obj.irq_cb_tbl[irq_idx]) &&
+			atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idx]))
+		DPU_ERROR("irq_idx=%d enabled with no callback\n", irq_idx);
+	spin_unlock_irqrestore(&dpu_kms->irq_obj.cb_lock, irq_flags);
+
+	return 0;
+}
+
+static void dpu_clear_all_irqs(struct dpu_kms *dpu_kms)
+{
+	if (!dpu_kms || !dpu_kms->hw_intr ||
+			!dpu_kms->hw_intr->ops.clear_all_irqs)
+		return;
+
+	dpu_kms->hw_intr->ops.clear_all_irqs(dpu_kms->hw_intr);
+}
+
+static void dpu_disable_all_irqs(struct dpu_kms *dpu_kms)
+{
+	if (!dpu_kms || !dpu_kms->hw_intr ||
+			!dpu_kms->hw_intr->ops.disable_all_irqs)
+		return;
+
+	dpu_kms->hw_intr->ops.disable_all_irqs(dpu_kms->hw_intr);
+}
+
+#ifdef CONFIG_DEBUG_FS
+#define DEFINE_DPU_DEBUGFS_SEQ_FOPS(__prefix)				\
+static int __prefix ## _open(struct inode *inode, struct file *file)	\
+{									\
+	return single_open(file, __prefix ## _show, inode->i_private);	\
+}									\
+static const struct file_operations __prefix ## _fops = {		\
+	.owner = THIS_MODULE,						\
+	.open = __prefix ## _open,					\
+	.release = single_release,					\
+	.read = seq_read,						\
+	.llseek = seq_lseek,						\
+}
+
+static int dpu_debugfs_core_irq_show(struct seq_file *s, void *v)
+{
+	struct dpu_irq *irq_obj = s->private;
+	struct dpu_irq_callback *cb;
+	unsigned long irq_flags;
+	int i, irq_count, enable_count, cb_count;
+
+	if (!irq_obj || !irq_obj->enable_counts || !irq_obj->irq_cb_tbl) {
+		DPU_ERROR("invalid parameters\n");
+		return 0;
+	}
+
+	for (i = 0; i < irq_obj->total_irqs; i++) {
+		spin_lock_irqsave(&irq_obj->cb_lock, irq_flags);
+		cb_count = 0;
+		irq_count = atomic_read(&irq_obj->irq_counts[i]);
+		enable_count = atomic_read(&irq_obj->enable_counts[i]);
+		list_for_each_entry(cb, &irq_obj->irq_cb_tbl[i], list)
+			cb_count++;
+		spin_unlock_irqrestore(&irq_obj->cb_lock, irq_flags);
+
+		if (irq_count || enable_count || cb_count)
+			seq_printf(s, "idx:%d irq:%d enable:%d cb:%d\n",
+					i, irq_count, enable_count, cb_count);
+	}
+
+	return 0;
+}
+
+DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_debugfs_core_irq);
+
+int dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
+		struct dentry *parent)
+{
+	dpu_kms->irq_obj.debugfs_file = debugfs_create_file("core_irq", 0600,
+			parent, &dpu_kms->irq_obj,
+			&dpu_debugfs_core_irq_fops);
+
+	return 0;
+}
+
+void dpu_debugfs_core_irq_destroy(struct dpu_kms *dpu_kms)
+{
+	debugfs_remove(dpu_kms->irq_obj.debugfs_file);
+	dpu_kms->irq_obj.debugfs_file = NULL;
+}
+
+#else
+int dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
+		struct dentry *parent)
+{
+	return 0;
+}
+
+void dpu_debugfs_core_irq_destroy(struct dpu_kms *dpu_kms)
+{
+}
+#endif
+
+void dpu_core_irq_preinstall(struct dpu_kms *dpu_kms)
+{
+	struct msm_drm_private *priv;
+	int i;
+
+	if (!dpu_kms) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return;
+	} else if (!dpu_kms->dev) {
+		DPU_ERROR("invalid drm device\n");
+		return;
+	} else if (!dpu_kms->dev->dev_private) {
+		DPU_ERROR("invalid device private\n");
+		return;
+	}
+	priv = dpu_kms->dev->dev_private;
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+	dpu_clear_all_irqs(dpu_kms);
+	dpu_disable_all_irqs(dpu_kms);
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	spin_lock_init(&dpu_kms->irq_obj.cb_lock);
+
+	/* Create irq callbacks for all possible irq_idx */
+	dpu_kms->irq_obj.total_irqs = dpu_kms->hw_intr->irq_idx_tbl_size;
+	dpu_kms->irq_obj.irq_cb_tbl = kcalloc(dpu_kms->irq_obj.total_irqs,
+			sizeof(struct list_head), GFP_KERNEL);
+	dpu_kms->irq_obj.enable_counts = kcalloc(dpu_kms->irq_obj.total_irqs,
+			sizeof(atomic_t), GFP_KERNEL);
+	dpu_kms->irq_obj.irq_counts = kcalloc(dpu_kms->irq_obj.total_irqs,
+			sizeof(atomic_t), GFP_KERNEL);
+	for (i = 0; i < dpu_kms->irq_obj.total_irqs; i++) {
+		INIT_LIST_HEAD(&dpu_kms->irq_obj.irq_cb_tbl[i]);
+		atomic_set(&dpu_kms->irq_obj.enable_counts[i], 0);
+		atomic_set(&dpu_kms->irq_obj.irq_counts[i], 0);
+	}
+}
+
+int dpu_core_irq_postinstall(struct dpu_kms *dpu_kms)
+{
+	return 0;
+}
+
+void dpu_core_irq_uninstall(struct dpu_kms *dpu_kms)
+{
+	struct msm_drm_private *priv;
+	int i;
+
+	if (!dpu_kms) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return;
+	} else if (!dpu_kms->dev) {
+		DPU_ERROR("invalid drm device\n");
+		return;
+	} else if (!dpu_kms->dev->dev_private) {
+		DPU_ERROR("invalid device private\n");
+		return;
+	}
+	priv = dpu_kms->dev->dev_private;
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+	for (i = 0; i < dpu_kms->irq_obj.total_irqs; i++)
+		if (atomic_read(&dpu_kms->irq_obj.enable_counts[i]) ||
+				!list_empty(&dpu_kms->irq_obj.irq_cb_tbl[i]))
+			DPU_ERROR("irq_idx=%d still enabled/registered\n", i);
+
+	dpu_clear_all_irqs(dpu_kms);
+	dpu_disable_all_irqs(dpu_kms);
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	kfree(dpu_kms->irq_obj.irq_cb_tbl);
+	kfree(dpu_kms->irq_obj.enable_counts);
+	kfree(dpu_kms->irq_obj.irq_counts);
+	dpu_kms->irq_obj.irq_cb_tbl = NULL;
+	dpu_kms->irq_obj.enable_counts = NULL;
+	dpu_kms->irq_obj.irq_counts = NULL;
+	dpu_kms->irq_obj.total_irqs = 0;
+}
+
+irqreturn_t dpu_core_irq(struct dpu_kms *dpu_kms)
+{
+	/*
+	 * Read interrupt status from all sources. Interrupt status are
+	 * stored within hw_intr.
+	 * Function will also clear the interrupt status after reading.
+	 * Individual interrupt status bit will only get stored if it
+	 * is enabled.
+	 */
+	dpu_kms->hw_intr->ops.get_interrupt_statuses(dpu_kms->hw_intr);
+
+	/*
+	 * Dispatch to HW driver to handle interrupt lookup that is being
+	 * fired. When matching interrupt is located, HW driver will call to
+	 * dpu_core_irq_callback_handler with the irq_idx from the lookup table.
+	 * dpu_core_irq_callback_handler will perform the registered function
+	 * callback, and do the interrupt status clearing once the registered
+	 * callback is finished.
+	 */
+	dpu_kms->hw_intr->ops.dispatch_irqs(
+			dpu_kms->hw_intr,
+			dpu_core_irq_callback_handler,
+			dpu_kms);
+
+	return IRQ_HANDLED;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h
new file mode 100644
index 000000000000..5e98bba46af5
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h
@@ -0,0 +1,153 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DPU_CORE_IRQ_H__
+#define __DPU_CORE_IRQ_H__
+
+#include "dpu_kms.h"
+#include "dpu_hw_interrupts.h"
+
+/**
+ * dpu_core_irq_preinstall - perform pre-installation of core IRQ handler
+ * @dpu_kms:		DPU handle
+ * @return:		none
+ */
+void dpu_core_irq_preinstall(struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_core_irq_postinstall - perform post-installation of core IRQ handler
+ * @dpu_kms:		DPU handle
+ * @return:		0 if success; error code otherwise
+ */
+int dpu_core_irq_postinstall(struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_core_irq_uninstall - uninstall core IRQ handler
+ * @dpu_kms:		DPU handle
+ * @return:		none
+ */
+void dpu_core_irq_uninstall(struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_core_irq - core IRQ handler
+ * @dpu_kms:		DPU handle
+ * @return:		interrupt handling status
+ */
+irqreturn_t dpu_core_irq(struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_core_irq_idx_lookup - IRQ helper function for lookup irq_idx from HW
+ *                      interrupt mapping table.
+ * @dpu_kms:		DPU handle
+ * @intr_type:		DPU HW interrupt type for lookup
+ * @instance_idx:	DPU HW block instance defined in dpu_hw_mdss.h
+ * @return:		irq_idx or -EINVAL when fail to lookup
+ */
+int dpu_core_irq_idx_lookup(
+		struct dpu_kms *dpu_kms,
+		enum dpu_intr_type intr_type,
+		uint32_t instance_idx);
+
+/**
+ * dpu_core_irq_enable - IRQ helper function for enabling one or more IRQs
+ * @dpu_kms:		DPU handle
+ * @irq_idxs:		Array of irq index
+ * @irq_count:		Number of irq_idx provided in the array
+ * @return:		0 for success enabling IRQ, otherwise failure
+ *
+ * This function increments count on each enable and decrements on each
+ * disable.  Interrupts is enabled if count is 0 before increment.
+ */
+int dpu_core_irq_enable(
+		struct dpu_kms *dpu_kms,
+		int *irq_idxs,
+		uint32_t irq_count);
+
+/**
+ * dpu_core_irq_disable - IRQ helper function for disabling one of more IRQs
+ * @dpu_kms:		DPU handle
+ * @irq_idxs:		Array of irq index
+ * @irq_count:		Number of irq_idx provided in the array
+ * @return:		0 for success disabling IRQ, otherwise failure
+ *
+ * This function increments count on each enable and decrements on each
+ * disable.  Interrupts is disabled if count is 0 after decrement.
+ */
+int dpu_core_irq_disable(
+		struct dpu_kms *dpu_kms,
+		int *irq_idxs,
+		uint32_t irq_count);
+
+/**
+ * dpu_core_irq_read - IRQ helper function for reading IRQ status
+ * @dpu_kms:		DPU handle
+ * @irq_idx:		irq index
+ * @clear:		True to clear the irq after read
+ * @return:		non-zero if irq detected; otherwise no irq detected
+ */
+u32 dpu_core_irq_read(
+		struct dpu_kms *dpu_kms,
+		int irq_idx,
+		bool clear);
+
+/**
+ * dpu_core_irq_register_callback - For registering callback function on IRQ
+ *                             interrupt
+ * @dpu_kms:		DPU handle
+ * @irq_idx:		irq index
+ * @irq_cb:		IRQ callback structure, containing callback function
+ *			and argument. Passing NULL for irq_cb will unregister
+ *			the callback for the given irq_idx
+ *			This must exist until un-registration.
+ * @return:		0 for success registering callback, otherwise failure
+ *
+ * This function supports registration of multiple callbacks for each interrupt.
+ */
+int dpu_core_irq_register_callback(
+		struct dpu_kms *dpu_kms,
+		int irq_idx,
+		struct dpu_irq_callback *irq_cb);
+
+/**
+ * dpu_core_irq_unregister_callback - For unregistering callback function on IRQ
+ *                             interrupt
+ * @dpu_kms:		DPU handle
+ * @irq_idx:		irq index
+ * @irq_cb:		IRQ callback structure, containing callback function
+ *			and argument. Passing NULL for irq_cb will unregister
+ *			the callback for the given irq_idx
+ *			This must match with registration.
+ * @return:		0 for success registering callback, otherwise failure
+ *
+ * This function supports registration of multiple callbacks for each interrupt.
+ */
+int dpu_core_irq_unregister_callback(
+		struct dpu_kms *dpu_kms,
+		int irq_idx,
+		struct dpu_irq_callback *irq_cb);
+
+/**
+ * dpu_debugfs_core_irq_init - register core irq debugfs
+ * @dpu_kms: pointer to kms
+ * @parent: debugfs directory root
+ * @Return: 0 on success
+ */
+int dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
+		struct dentry *parent);
+
+/**
+ * dpu_debugfs_core_irq_destroy - deregister core irq debugfs
+ * @dpu_kms: pointer to kms
+ */
+void dpu_debugfs_core_irq_destroy(struct dpu_kms *dpu_kms);
+
+#endif /* __DPU_CORE_IRQ_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
new file mode 100644
index 000000000000..41c5191f9056
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -0,0 +1,637 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/debugfs.h>
+#include <linux/errno.h>
+#include <linux/mutex.h>
+#include <linux/sort.h>
+#include <linux/clk.h>
+#include <linux/bitmap.h>
+
+#include "dpu_kms.h"
+#include "dpu_trace.h"
+#include "dpu_crtc.h"
+#include "dpu_core_perf.h"
+
+#define DPU_PERF_MODE_STRING_SIZE	128
+
+/**
+ * enum dpu_perf_mode - performance tuning mode
+ * @DPU_PERF_MODE_NORMAL: performance controlled by user mode client
+ * @DPU_PERF_MODE_MINIMUM: performance bounded by minimum setting
+ * @DPU_PERF_MODE_FIXED: performance bounded by fixed setting
+ */
+enum dpu_perf_mode {
+	DPU_PERF_MODE_NORMAL,
+	DPU_PERF_MODE_MINIMUM,
+	DPU_PERF_MODE_FIXED,
+	DPU_PERF_MODE_MAX
+};
+
+static struct dpu_kms *_dpu_crtc_get_kms(struct drm_crtc *crtc)
+{
+	struct msm_drm_private *priv;
+
+	if (!crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid device\n");
+		return NULL;
+	}
+
+	priv = crtc->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid kms\n");
+		return NULL;
+	}
+
+	return to_dpu_kms(priv->kms);
+}
+
+static bool _dpu_core_perf_crtc_is_power_on(struct drm_crtc *crtc)
+{
+	return dpu_crtc_is_enabled(crtc);
+}
+
+static bool _dpu_core_video_mode_intf_connected(struct drm_crtc *crtc)
+{
+	struct drm_crtc *tmp_crtc;
+	bool intf_connected = false;
+
+	if (!crtc)
+		goto end;
+
+	drm_for_each_crtc(tmp_crtc, crtc->dev) {
+		if ((dpu_crtc_get_intf_mode(tmp_crtc) == INTF_MODE_VIDEO) &&
+				_dpu_core_perf_crtc_is_power_on(tmp_crtc)) {
+			DPU_DEBUG("video interface connected crtc:%d\n",
+				tmp_crtc->base.id);
+			intf_connected = true;
+			goto end;
+		}
+	}
+
+end:
+	return intf_connected;
+}
+
+static void _dpu_core_perf_calc_crtc(struct dpu_kms *kms,
+		struct drm_crtc *crtc,
+		struct drm_crtc_state *state,
+		struct dpu_core_perf_params *perf)
+{
+	struct dpu_crtc_state *dpu_cstate;
+	int i;
+
+	if (!kms || !kms->catalog || !crtc || !state || !perf) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	dpu_cstate = to_dpu_crtc_state(state);
+	memset(perf, 0, sizeof(struct dpu_core_perf_params));
+
+	if (!dpu_cstate->bw_control) {
+		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+			perf->bw_ctl[i] = kms->catalog->perf.max_bw_high *
+					1000ULL;
+			perf->max_per_pipe_ib[i] = perf->bw_ctl[i];
+		}
+		perf->core_clk_rate = kms->perf.max_core_clk_rate;
+	} else if (kms->perf.perf_tune.mode == DPU_PERF_MODE_MINIMUM) {
+		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+			perf->bw_ctl[i] = 0;
+			perf->max_per_pipe_ib[i] = 0;
+		}
+		perf->core_clk_rate = 0;
+	} else if (kms->perf.perf_tune.mode == DPU_PERF_MODE_FIXED) {
+		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+			perf->bw_ctl[i] = kms->perf.fix_core_ab_vote;
+			perf->max_per_pipe_ib[i] = kms->perf.fix_core_ib_vote;
+		}
+		perf->core_clk_rate = kms->perf.fix_core_clk_rate;
+	}
+
+	DPU_DEBUG(
+		"crtc=%d clk_rate=%llu core_ib=%llu core_ab=%llu llcc_ib=%llu llcc_ab=%llu mem_ib=%llu mem_ab=%llu\n",
+			crtc->base.id, perf->core_clk_rate,
+			perf->max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_MNOC],
+			perf->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_MNOC],
+			perf->max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_LLCC],
+			perf->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_LLCC],
+			perf->max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_EBI],
+			perf->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_EBI]);
+}
+
+int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
+		struct drm_crtc_state *state)
+{
+	u32 bw, threshold;
+	u64 bw_sum_of_intfs = 0;
+	enum dpu_crtc_client_type curr_client_type;
+	bool is_video_mode;
+	struct dpu_crtc_state *dpu_cstate;
+	struct drm_crtc *tmp_crtc;
+	struct dpu_kms *kms;
+	int i;
+
+	if (!crtc || !state) {
+		DPU_ERROR("invalid crtc\n");
+		return -EINVAL;
+	}
+
+	kms = _dpu_crtc_get_kms(crtc);
+	if (!kms || !kms->catalog) {
+		DPU_ERROR("invalid parameters\n");
+		return 0;
+	}
+
+	/* we only need bandwidth check on real-time clients (interfaces) */
+	if (dpu_crtc_get_client_type(crtc) == NRT_CLIENT)
+		return 0;
+
+	dpu_cstate = to_dpu_crtc_state(state);
+
+	/* obtain new values */
+	_dpu_core_perf_calc_crtc(kms, crtc, state, &dpu_cstate->new_perf);
+
+	for (i = DPU_POWER_HANDLE_DBUS_ID_MNOC;
+			i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+		bw_sum_of_intfs = dpu_cstate->new_perf.bw_ctl[i];
+		curr_client_type = dpu_crtc_get_client_type(crtc);
+
+		drm_for_each_crtc(tmp_crtc, crtc->dev) {
+			if (_dpu_core_perf_crtc_is_power_on(tmp_crtc) &&
+			    (dpu_crtc_get_client_type(tmp_crtc) ==
+					    curr_client_type) &&
+			    (tmp_crtc != crtc)) {
+				struct dpu_crtc_state *tmp_cstate =
+					to_dpu_crtc_state(tmp_crtc->state);
+
+				DPU_DEBUG("crtc:%d bw:%llu ctrl:%d\n",
+					tmp_crtc->base.id,
+					tmp_cstate->new_perf.bw_ctl[i],
+					tmp_cstate->bw_control);
+				/*
+				 * For bw check only use the bw if the
+				 * atomic property has been already set
+				 */
+				if (tmp_cstate->bw_control)
+					bw_sum_of_intfs +=
+						tmp_cstate->new_perf.bw_ctl[i];
+			}
+		}
+
+		/* convert bandwidth to kb */
+		bw = DIV_ROUND_UP_ULL(bw_sum_of_intfs, 1000);
+		DPU_DEBUG("calculated bandwidth=%uk\n", bw);
+
+		is_video_mode = dpu_crtc_get_intf_mode(crtc) == INTF_MODE_VIDEO;
+		threshold = (is_video_mode ||
+			_dpu_core_video_mode_intf_connected(crtc)) ?
+			kms->catalog->perf.max_bw_low :
+			kms->catalog->perf.max_bw_high;
+
+		DPU_DEBUG("final threshold bw limit = %d\n", threshold);
+
+		if (!dpu_cstate->bw_control) {
+			DPU_DEBUG("bypass bandwidth check\n");
+		} else if (!threshold) {
+			DPU_ERROR("no bandwidth limits specified\n");
+			return -E2BIG;
+		} else if (bw > threshold) {
+			DPU_ERROR("exceeds bandwidth: %ukb > %ukb\n", bw,
+					threshold);
+			return -E2BIG;
+		}
+	}
+
+	return 0;
+}
+
+static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms,
+		struct drm_crtc *crtc, u32 bus_id)
+{
+	struct dpu_core_perf_params perf = { { 0 } };
+	enum dpu_crtc_client_type curr_client_type
+					= dpu_crtc_get_client_type(crtc);
+	struct drm_crtc *tmp_crtc;
+	struct dpu_crtc_state *dpu_cstate;
+	int ret = 0;
+
+	drm_for_each_crtc(tmp_crtc, crtc->dev) {
+		if (_dpu_core_perf_crtc_is_power_on(tmp_crtc) &&
+			curr_client_type ==
+				dpu_crtc_get_client_type(tmp_crtc)) {
+			dpu_cstate = to_dpu_crtc_state(tmp_crtc->state);
+
+			perf.max_per_pipe_ib[bus_id] =
+				max(perf.max_per_pipe_ib[bus_id],
+				dpu_cstate->new_perf.max_per_pipe_ib[bus_id]);
+
+			DPU_DEBUG("crtc=%d bus_id=%d bw=%llu\n",
+				tmp_crtc->base.id, bus_id,
+				dpu_cstate->new_perf.bw_ctl[bus_id]);
+		}
+	}
+	return ret;
+}
+
+/**
+ * @dpu_core_perf_crtc_release_bw() - request zero bandwidth
+ * @crtc - pointer to a crtc
+ *
+ * Function checks a state variable for the crtc, if all pending commit
+ * requests are done, meaning no more bandwidth is needed, release
+ * bandwidth request.
+ */
+void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc)
+{
+	struct drm_crtc *tmp_crtc;
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *dpu_cstate;
+	struct dpu_kms *kms;
+	int i;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	kms = _dpu_crtc_get_kms(crtc);
+	if (!kms || !kms->catalog) {
+		DPU_ERROR("invalid kms\n");
+		return;
+	}
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	dpu_cstate = to_dpu_crtc_state(crtc->state);
+
+	/* only do this for command mode rt client */
+	if (dpu_crtc_get_intf_mode(crtc) != INTF_MODE_CMD)
+		return;
+
+	/*
+	 * If video interface present, cmd panel bandwidth cannot be
+	 * released.
+	 */
+	if (dpu_crtc_get_intf_mode(crtc) == INTF_MODE_CMD)
+		drm_for_each_crtc(tmp_crtc, crtc->dev) {
+			if (_dpu_core_perf_crtc_is_power_on(tmp_crtc) &&
+				dpu_crtc_get_intf_mode(tmp_crtc) ==
+						INTF_MODE_VIDEO)
+				return;
+		}
+
+	/* Release the bandwidth */
+	if (kms->perf.enable_bw_release) {
+		trace_dpu_cmd_release_bw(crtc->base.id);
+		DPU_DEBUG("Release BW crtc=%d\n", crtc->base.id);
+		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+			dpu_crtc->cur_perf.bw_ctl[i] = 0;
+			_dpu_core_perf_crtc_update_bus(kms, crtc, i);
+		}
+	}
+}
+
+static int _dpu_core_perf_set_core_clk_rate(struct dpu_kms *kms, u64 rate)
+{
+	struct dss_clk *core_clk = kms->perf.core_clk;
+
+	if (core_clk->max_rate && (rate > core_clk->max_rate))
+		rate = core_clk->max_rate;
+
+	core_clk->rate = rate;
+	return msm_dss_clk_set_rate(core_clk, 1);
+}
+
+static u64 _dpu_core_perf_get_core_clk_rate(struct dpu_kms *kms)
+{
+	u64 clk_rate = kms->perf.perf_tune.min_core_clk;
+	struct drm_crtc *crtc;
+	struct dpu_crtc_state *dpu_cstate;
+
+	drm_for_each_crtc(crtc, kms->dev) {
+		if (_dpu_core_perf_crtc_is_power_on(crtc)) {
+			dpu_cstate = to_dpu_crtc_state(crtc->state);
+			clk_rate = max(dpu_cstate->new_perf.core_clk_rate,
+							clk_rate);
+			clk_rate = clk_round_rate(kms->perf.core_clk->clk,
+					clk_rate);
+		}
+	}
+
+	if (kms->perf.perf_tune.mode == DPU_PERF_MODE_FIXED)
+		clk_rate = kms->perf.fix_core_clk_rate;
+
+	DPU_DEBUG("clk:%llu\n", clk_rate);
+
+	return clk_rate;
+}
+
+int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
+		int params_changed, bool stop_req)
+{
+	struct dpu_core_perf_params *new, *old;
+	int update_bus = 0, update_clk = 0;
+	u64 clk_rate = 0;
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *dpu_cstate;
+	int i;
+	struct msm_drm_private *priv;
+	struct dpu_kms *kms;
+	int ret;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return -EINVAL;
+	}
+
+	kms = _dpu_crtc_get_kms(crtc);
+	if (!kms || !kms->catalog) {
+		DPU_ERROR("invalid kms\n");
+		return -EINVAL;
+	}
+	priv = kms->dev->dev_private;
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	dpu_cstate = to_dpu_crtc_state(crtc->state);
+
+	DPU_DEBUG("crtc:%d stop_req:%d core_clk:%llu\n",
+			crtc->base.id, stop_req, kms->perf.core_clk_rate);
+
+	old = &dpu_crtc->cur_perf;
+	new = &dpu_cstate->new_perf;
+
+	if (_dpu_core_perf_crtc_is_power_on(crtc) && !stop_req) {
+		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+			/*
+			 * cases for bus bandwidth update.
+			 * 1. new bandwidth vote - "ab or ib vote" is higher
+			 *    than current vote for update request.
+			 * 2. new bandwidth vote - "ab or ib vote" is lower
+			 *    than current vote at end of commit or stop.
+			 */
+			if ((params_changed && ((new->bw_ctl[i] >
+						old->bw_ctl[i]) ||
+				  (new->max_per_pipe_ib[i] >
+						old->max_per_pipe_ib[i]))) ||
+			    (!params_changed && ((new->bw_ctl[i] <
+						old->bw_ctl[i]) ||
+				  (new->max_per_pipe_ib[i] <
+						old->max_per_pipe_ib[i])))) {
+				DPU_DEBUG(
+					"crtc=%d p=%d new_bw=%llu,old_bw=%llu\n",
+					crtc->base.id, params_changed,
+					new->bw_ctl[i], old->bw_ctl[i]);
+				old->bw_ctl[i] = new->bw_ctl[i];
+				old->max_per_pipe_ib[i] =
+						new->max_per_pipe_ib[i];
+				update_bus |= BIT(i);
+			}
+		}
+
+		if ((params_changed &&
+				(new->core_clk_rate > old->core_clk_rate)) ||
+				(!params_changed &&
+				(new->core_clk_rate < old->core_clk_rate))) {
+			old->core_clk_rate = new->core_clk_rate;
+			update_clk = 1;
+		}
+	} else {
+		DPU_DEBUG("crtc=%d disable\n", crtc->base.id);
+		memset(old, 0, sizeof(*old));
+		memset(new, 0, sizeof(*new));
+		update_bus = ~0;
+		update_clk = 1;
+	}
+	trace_dpu_perf_crtc_update(crtc->base.id,
+				new->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_MNOC],
+				new->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_LLCC],
+				new->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_EBI],
+				new->core_clk_rate, stop_req,
+				update_bus, update_clk);
+
+	for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+		if (update_bus & BIT(i)) {
+			ret = _dpu_core_perf_crtc_update_bus(kms, crtc, i);
+			if (ret) {
+				DPU_ERROR("crtc-%d: failed to update bw vote for bus-%d\n",
+					  crtc->base.id, i);
+				return ret;
+			}
+		}
+	}
+
+	/*
+	 * Update the clock after bandwidth vote to ensure
+	 * bandwidth is available before clock rate is increased.
+	 */
+	if (update_clk) {
+		clk_rate = _dpu_core_perf_get_core_clk_rate(kms);
+
+		trace_dpu_core_perf_update_clk(kms->dev, stop_req, clk_rate);
+
+		ret = _dpu_core_perf_set_core_clk_rate(kms, clk_rate);
+		if (ret) {
+			DPU_ERROR("failed to set %s clock rate %llu\n",
+					kms->perf.core_clk->clk_name, clk_rate);
+			return ret;
+		}
+
+		kms->perf.core_clk_rate = clk_rate;
+		DPU_DEBUG("update clk rate = %lld HZ\n", clk_rate);
+	}
+	return 0;
+}
+
+#ifdef CONFIG_DEBUG_FS
+
+static ssize_t _dpu_core_perf_mode_write(struct file *file,
+		    const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	struct dpu_core_perf *perf = file->private_data;
+	struct dpu_perf_cfg *cfg = &perf->catalog->perf;
+	u32 perf_mode = 0;
+	char buf[10];
+
+	if (!perf)
+		return -ENODEV;
+
+	if (count >= sizeof(buf))
+		return -EFAULT;
+
+	if (copy_from_user(buf, user_buf, count))
+		return -EFAULT;
+
+	buf[count] = 0;	/* end of string */
+
+	if (kstrtouint(buf, 0, &perf_mode))
+		return -EFAULT;
+
+	if (perf_mode >= DPU_PERF_MODE_MAX)
+		return -EFAULT;
+
+	if (perf_mode == DPU_PERF_MODE_FIXED) {
+		DRM_INFO("fix performance mode\n");
+	} else if (perf_mode == DPU_PERF_MODE_MINIMUM) {
+		/* run the driver with max clk and BW vote */
+		perf->perf_tune.min_core_clk = perf->max_core_clk_rate;
+		perf->perf_tune.min_bus_vote =
+				(u64) cfg->max_bw_high * 1000;
+		DRM_INFO("minimum performance mode\n");
+	} else if (perf_mode == DPU_PERF_MODE_NORMAL) {
+		/* reset the perf tune params to 0 */
+		perf->perf_tune.min_core_clk = 0;
+		perf->perf_tune.min_bus_vote = 0;
+		DRM_INFO("normal performance mode\n");
+	}
+	perf->perf_tune.mode = perf_mode;
+
+	return count;
+}
+
+static ssize_t _dpu_core_perf_mode_read(struct file *file,
+			char __user *buff, size_t count, loff_t *ppos)
+{
+	struct dpu_core_perf *perf = file->private_data;
+	int len = 0;
+	char buf[DPU_PERF_MODE_STRING_SIZE] = {'\0'};
+
+	if (!perf)
+		return -ENODEV;
+
+	if (*ppos)
+		return 0;	/* the end */
+
+	len = snprintf(buf, sizeof(buf),
+			"mode %d min_mdp_clk %llu min_bus_vote %llu\n",
+			perf->perf_tune.mode,
+			perf->perf_tune.min_core_clk,
+			perf->perf_tune.min_bus_vote);
+	if (len < 0 || len >= sizeof(buf))
+		return 0;
+
+	if ((count < sizeof(buf)) || copy_to_user(buff, buf, len))
+		return -EFAULT;
+
+	*ppos += len;   /* increase offset */
+
+	return len;
+}
+
+static const struct file_operations dpu_core_perf_mode_fops = {
+	.open = simple_open,
+	.read = _dpu_core_perf_mode_read,
+	.write = _dpu_core_perf_mode_write,
+};
+
+static void dpu_core_perf_debugfs_destroy(struct dpu_core_perf *perf)
+{
+	debugfs_remove_recursive(perf->debugfs_root);
+	perf->debugfs_root = NULL;
+}
+
+int dpu_core_perf_debugfs_init(struct dpu_core_perf *perf,
+		struct dentry *parent)
+{
+	struct dpu_mdss_cfg *catalog = perf->catalog;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	priv = perf->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid KMS reference\n");
+		return -EINVAL;
+	}
+
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	perf->debugfs_root = debugfs_create_dir("core_perf", parent);
+	if (!perf->debugfs_root) {
+		DPU_ERROR("failed to create core perf debugfs\n");
+		return -EINVAL;
+	}
+
+	debugfs_create_u64("max_core_clk_rate", 0600, perf->debugfs_root,
+			&perf->max_core_clk_rate);
+	debugfs_create_u64("core_clk_rate", 0600, perf->debugfs_root,
+			&perf->core_clk_rate);
+	debugfs_create_u32("enable_bw_release", 0600, perf->debugfs_root,
+			(u32 *)&perf->enable_bw_release);
+	debugfs_create_u32("threshold_low", 0600, perf->debugfs_root,
+			(u32 *)&catalog->perf.max_bw_low);
+	debugfs_create_u32("threshold_high", 0600, perf->debugfs_root,
+			(u32 *)&catalog->perf.max_bw_high);
+	debugfs_create_u32("min_core_ib", 0600, perf->debugfs_root,
+			(u32 *)&catalog->perf.min_core_ib);
+	debugfs_create_u32("min_llcc_ib", 0600, perf->debugfs_root,
+			(u32 *)&catalog->perf.min_llcc_ib);
+	debugfs_create_u32("min_dram_ib", 0600, perf->debugfs_root,
+			(u32 *)&catalog->perf.min_dram_ib);
+	debugfs_create_file("perf_mode", 0600, perf->debugfs_root,
+			(u32 *)perf, &dpu_core_perf_mode_fops);
+	debugfs_create_u64("fix_core_clk_rate", 0600, perf->debugfs_root,
+			&perf->fix_core_clk_rate);
+	debugfs_create_u64("fix_core_ib_vote", 0600, perf->debugfs_root,
+			&perf->fix_core_ib_vote);
+	debugfs_create_u64("fix_core_ab_vote", 0600, perf->debugfs_root,
+			&perf->fix_core_ab_vote);
+
+	return 0;
+}
+#else
+static void dpu_core_perf_debugfs_destroy(struct dpu_core_perf *perf)
+{
+}
+
+int dpu_core_perf_debugfs_init(struct dpu_core_perf *perf,
+		struct dentry *parent)
+{
+	return 0;
+}
+#endif
+
+void dpu_core_perf_destroy(struct dpu_core_perf *perf)
+{
+	if (!perf) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	dpu_core_perf_debugfs_destroy(perf);
+	perf->max_core_clk_rate = 0;
+	perf->core_clk = NULL;
+	perf->phandle = NULL;
+	perf->catalog = NULL;
+	perf->dev = NULL;
+}
+
+int dpu_core_perf_init(struct dpu_core_perf *perf,
+		struct drm_device *dev,
+		struct dpu_mdss_cfg *catalog,
+		struct dpu_power_handle *phandle,
+		struct dss_clk *core_clk)
+{
+	perf->dev = dev;
+	perf->catalog = catalog;
+	perf->phandle = phandle;
+	perf->core_clk = core_clk;
+
+	perf->max_core_clk_rate = core_clk->max_rate;
+	if (!perf->max_core_clk_rate) {
+		DPU_DEBUG("optional max core clk rate, use default\n");
+		perf->max_core_clk_rate = DPU_PERF_DEFAULT_MAX_CORE_CLK_RATE;
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
new file mode 100644
index 000000000000..fbcbe0c7527a
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
@@ -0,0 +1,133 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_CORE_PERF_H_
+#define _DPU_CORE_PERF_H_
+
+#include <linux/types.h>
+#include <linux/dcache.h>
+#include <linux/mutex.h>
+#include <drm/drm_crtc.h>
+
+#include "dpu_hw_catalog.h"
+#include "dpu_power_handle.h"
+
+#define	DPU_PERF_DEFAULT_MAX_CORE_CLK_RATE	412500000
+
+/**
+ * struct dpu_core_perf_params - definition of performance parameters
+ * @max_per_pipe_ib: maximum instantaneous bandwidth request
+ * @bw_ctl: arbitrated bandwidth request
+ * @core_clk_rate: core clock rate request
+ */
+struct dpu_core_perf_params {
+	u64 max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_MAX];
+	u64 bw_ctl[DPU_POWER_HANDLE_DBUS_ID_MAX];
+	u64 core_clk_rate;
+};
+
+/**
+ * struct dpu_core_perf_tune - definition of performance tuning control
+ * @mode: performance mode
+ * @min_core_clk: minimum core clock
+ * @min_bus_vote: minimum bus vote
+ */
+struct dpu_core_perf_tune {
+	u32 mode;
+	u64 min_core_clk;
+	u64 min_bus_vote;
+};
+
+/**
+ * struct dpu_core_perf - definition of core performance context
+ * @dev: Pointer to drm device
+ * @debugfs_root: top level debug folder
+ * @catalog: Pointer to catalog configuration
+ * @phandle: Pointer to power handler
+ * @core_clk: Pointer to core clock structure
+ * @core_clk_rate: current core clock rate
+ * @max_core_clk_rate: maximum allowable core clock rate
+ * @perf_tune: debug control for performance tuning
+ * @enable_bw_release: debug control for bandwidth release
+ * @fix_core_clk_rate: fixed core clock request in Hz used in mode 2
+ * @fix_core_ib_vote: fixed core ib vote in bps used in mode 2
+ * @fix_core_ab_vote: fixed core ab vote in bps used in mode 2
+ */
+struct dpu_core_perf {
+	struct drm_device *dev;
+	struct dentry *debugfs_root;
+	struct dpu_mdss_cfg *catalog;
+	struct dpu_power_handle *phandle;
+	struct dss_clk *core_clk;
+	u64 core_clk_rate;
+	u64 max_core_clk_rate;
+	struct dpu_core_perf_tune perf_tune;
+	u32 enable_bw_release;
+	u64 fix_core_clk_rate;
+	u64 fix_core_ib_vote;
+	u64 fix_core_ab_vote;
+};
+
+/**
+ * dpu_core_perf_crtc_check - validate performance of the given crtc state
+ * @crtc: Pointer to crtc
+ * @state: Pointer to new crtc state
+ * return: zero if success, or error code otherwise
+ */
+int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
+		struct drm_crtc_state *state);
+
+/**
+ * dpu_core_perf_crtc_update - update performance of the given crtc
+ * @crtc: Pointer to crtc
+ * @params_changed: true if crtc parameters are modified
+ * @stop_req: true if this is a stop request
+ * return: zero if success, or error code otherwise
+ */
+int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
+		int params_changed, bool stop_req);
+
+/**
+ * dpu_core_perf_crtc_release_bw - release bandwidth of the given crtc
+ * @crtc: Pointer to crtc
+ */
+void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc);
+
+/**
+ * dpu_core_perf_destroy - destroy the given core performance context
+ * @perf: Pointer to core performance context
+ */
+void dpu_core_perf_destroy(struct dpu_core_perf *perf);
+
+/**
+ * dpu_core_perf_init - initialize the given core performance context
+ * @perf: Pointer to core performance context
+ * @dev: Pointer to drm device
+ * @catalog: Pointer to catalog
+ * @phandle: Pointer to power handle
+ * @core_clk: pointer to core clock
+ */
+int dpu_core_perf_init(struct dpu_core_perf *perf,
+		struct drm_device *dev,
+		struct dpu_mdss_cfg *catalog,
+		struct dpu_power_handle *phandle,
+		struct dss_clk *core_clk);
+
+/**
+ * dpu_core_perf_debugfs_init - initialize debugfs for core performance context
+ * @perf: Pointer to core performance context
+ * @debugfs_parent: Pointer to parent debugfs
+ */
+int dpu_core_perf_debugfs_init(struct dpu_core_perf *perf,
+		struct dentry *parent);
+
+#endif /* _DPU_CORE_PERF_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
new file mode 100644
index 000000000000..80cbf75bc2ff
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -0,0 +1,2138 @@
+/*
+ * Copyright (c) 2014-2018 The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include <linux/sort.h>
+#include <linux/debugfs.h>
+#include <linux/ktime.h>
+#include <drm/drm_mode.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_flip_work.h>
+#include <drm/drm_rect.h>
+
+#include "dpu_kms.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_crtc.h"
+#include "dpu_plane.h"
+#include "dpu_encoder.h"
+#include "dpu_vbif.h"
+#include "dpu_power_handle.h"
+#include "dpu_core_perf.h"
+#include "dpu_trace.h"
+
+#define DPU_DRM_BLEND_OP_NOT_DEFINED    0
+#define DPU_DRM_BLEND_OP_OPAQUE         1
+#define DPU_DRM_BLEND_OP_PREMULTIPLIED  2
+#define DPU_DRM_BLEND_OP_COVERAGE       3
+#define DPU_DRM_BLEND_OP_MAX            4
+
+/* layer mixer index on dpu_crtc */
+#define LEFT_MIXER 0
+#define RIGHT_MIXER 1
+
+#define MISR_BUFF_SIZE			256
+
+static inline struct dpu_kms *_dpu_crtc_get_kms(struct drm_crtc *crtc)
+{
+	struct msm_drm_private *priv;
+
+	if (!crtc || !crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid crtc\n");
+		return NULL;
+	}
+	priv = crtc->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid kms\n");
+		return NULL;
+	}
+
+	return to_dpu_kms(priv->kms);
+}
+
+static inline int _dpu_crtc_power_enable(struct dpu_crtc *dpu_crtc, bool enable)
+{
+	struct drm_crtc *crtc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!dpu_crtc) {
+		DPU_ERROR("invalid dpu crtc\n");
+		return -EINVAL;
+	}
+
+	crtc = &dpu_crtc->base;
+	if (!crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid drm device\n");
+		return -EINVAL;
+	}
+
+	priv = crtc->dev->dev_private;
+	if (!priv->kms) {
+		DPU_ERROR("invalid kms\n");
+		return -EINVAL;
+	}
+
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	if (enable)
+		pm_runtime_get_sync(&dpu_kms->pdev->dev);
+	else
+		pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	return 0;
+}
+
+/**
+ * _dpu_crtc_rp_to_crtc - get crtc from resource pool object
+ * @rp: Pointer to resource pool
+ * return: Pointer to drm crtc if success; null otherwise
+ */
+static struct drm_crtc *_dpu_crtc_rp_to_crtc(struct dpu_crtc_respool *rp)
+{
+	if (!rp)
+		return NULL;
+
+	return container_of(rp, struct dpu_crtc_state, rp)->base.crtc;
+}
+
+/**
+ * _dpu_crtc_rp_reclaim - reclaim unused, or all if forced, resources in pool
+ * @rp: Pointer to resource pool
+ * @force: True to reclaim all resources; otherwise, reclaim only unused ones
+ * return: None
+ */
+static void _dpu_crtc_rp_reclaim(struct dpu_crtc_respool *rp, bool force)
+{
+	struct dpu_crtc_res *res, *next;
+	struct drm_crtc *crtc;
+
+	crtc = _dpu_crtc_rp_to_crtc(rp);
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	DPU_DEBUG("crtc%d.%u %s\n", crtc->base.id, rp->sequence_id,
+			force ? "destroy" : "free_unused");
+
+	list_for_each_entry_safe(res, next, &rp->res_list, list) {
+		if (!force && !(res->flags & DPU_CRTC_RES_FLAG_FREE))
+			continue;
+		DPU_DEBUG("crtc%d.%u reclaim res:0x%x/0x%llx/%pK/%d\n",
+				crtc->base.id, rp->sequence_id,
+				res->type, res->tag, res->val,
+				atomic_read(&res->refcount));
+		list_del(&res->list);
+		if (res->ops.put)
+			res->ops.put(res->val);
+		kfree(res);
+	}
+}
+
+/**
+ * _dpu_crtc_rp_free_unused - free unused resource in pool
+ * @rp: Pointer to resource pool
+ * return: none
+ */
+static void _dpu_crtc_rp_free_unused(struct dpu_crtc_respool *rp)
+{
+	mutex_lock(rp->rp_lock);
+	_dpu_crtc_rp_reclaim(rp, false);
+	mutex_unlock(rp->rp_lock);
+}
+
+/**
+ * _dpu_crtc_rp_destroy - destroy resource pool
+ * @rp: Pointer to resource pool
+ * return: None
+ */
+static void _dpu_crtc_rp_destroy(struct dpu_crtc_respool *rp)
+{
+	mutex_lock(rp->rp_lock);
+	list_del_init(&rp->rp_list);
+	_dpu_crtc_rp_reclaim(rp, true);
+	mutex_unlock(rp->rp_lock);
+}
+
+/**
+ * _dpu_crtc_hw_blk_get - get callback for hardware block
+ * @val: Resource handle
+ * @type: Resource type
+ * @tag: Search tag for given resource
+ * return: Resource handle
+ */
+static void *_dpu_crtc_hw_blk_get(void *val, u32 type, u64 tag)
+{
+	DPU_DEBUG("res:%d/0x%llx/%pK\n", type, tag, val);
+	return dpu_hw_blk_get(val, type, tag);
+}
+
+/**
+ * _dpu_crtc_hw_blk_put - put callback for hardware block
+ * @val: Resource handle
+ * return: None
+ */
+static void _dpu_crtc_hw_blk_put(void *val)
+{
+	DPU_DEBUG("res://%pK\n", val);
+	dpu_hw_blk_put(val);
+}
+
+/**
+ * _dpu_crtc_rp_duplicate - duplicate resource pool and reset reference count
+ * @rp: Pointer to original resource pool
+ * @dup_rp: Pointer to duplicated resource pool
+ * return: None
+ */
+static void _dpu_crtc_rp_duplicate(struct dpu_crtc_respool *rp,
+		struct dpu_crtc_respool *dup_rp)
+{
+	struct dpu_crtc_res *res, *dup_res;
+	struct drm_crtc *crtc;
+
+	if (!rp || !dup_rp || !rp->rp_head) {
+		DPU_ERROR("invalid resource pool\n");
+		return;
+	}
+
+	crtc = _dpu_crtc_rp_to_crtc(rp);
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	DPU_DEBUG("crtc%d.%u duplicate\n", crtc->base.id, rp->sequence_id);
+
+	mutex_lock(rp->rp_lock);
+	dup_rp->sequence_id = rp->sequence_id + 1;
+	INIT_LIST_HEAD(&dup_rp->res_list);
+	dup_rp->ops = rp->ops;
+	list_for_each_entry(res, &rp->res_list, list) {
+		dup_res = kzalloc(sizeof(struct dpu_crtc_res), GFP_KERNEL);
+		if (!dup_res) {
+			mutex_unlock(rp->rp_lock);
+			return;
+		}
+		INIT_LIST_HEAD(&dup_res->list);
+		atomic_set(&dup_res->refcount, 0);
+		dup_res->type = res->type;
+		dup_res->tag = res->tag;
+		dup_res->val = res->val;
+		dup_res->ops = res->ops;
+		dup_res->flags = DPU_CRTC_RES_FLAG_FREE;
+		DPU_DEBUG("crtc%d.%u dup res:0x%x/0x%llx/%pK/%d\n",
+				crtc->base.id, dup_rp->sequence_id,
+				dup_res->type, dup_res->tag, dup_res->val,
+				atomic_read(&dup_res->refcount));
+		list_add_tail(&dup_res->list, &dup_rp->res_list);
+		if (dup_res->ops.get)
+			dup_res->ops.get(dup_res->val, 0, -1);
+	}
+
+	dup_rp->rp_lock = rp->rp_lock;
+	dup_rp->rp_head = rp->rp_head;
+	INIT_LIST_HEAD(&dup_rp->rp_list);
+	list_add_tail(&dup_rp->rp_list, rp->rp_head);
+	mutex_unlock(rp->rp_lock);
+}
+
+/**
+ * _dpu_crtc_rp_reset - reset resource pool after allocation
+ * @rp: Pointer to original resource pool
+ * @rp_lock: Pointer to serialization resource pool lock
+ * @rp_head: Pointer to crtc resource pool head
+ * return: None
+ */
+static void _dpu_crtc_rp_reset(struct dpu_crtc_respool *rp,
+		struct mutex *rp_lock, struct list_head *rp_head)
+{
+	if (!rp || !rp_lock || !rp_head) {
+		DPU_ERROR("invalid resource pool\n");
+		return;
+	}
+
+	mutex_lock(rp_lock);
+	rp->rp_lock = rp_lock;
+	rp->rp_head = rp_head;
+	INIT_LIST_HEAD(&rp->rp_list);
+	rp->sequence_id = 0;
+	INIT_LIST_HEAD(&rp->res_list);
+	rp->ops.get = _dpu_crtc_hw_blk_get;
+	rp->ops.put = _dpu_crtc_hw_blk_put;
+	list_add_tail(&rp->rp_list, rp->rp_head);
+	mutex_unlock(rp_lock);
+}
+
+static void dpu_crtc_destroy(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+
+	DPU_DEBUG("\n");
+
+	if (!crtc)
+		return;
+
+	dpu_crtc->phandle = NULL;
+
+	drm_crtc_cleanup(crtc);
+	mutex_destroy(&dpu_crtc->crtc_lock);
+	kfree(dpu_crtc);
+}
+
+static void _dpu_crtc_setup_blend_cfg(struct dpu_crtc_mixer *mixer,
+		struct dpu_plane_state *pstate)
+{
+	struct dpu_hw_mixer *lm = mixer->hw_lm;
+
+	/* default to opaque blending */
+	lm->ops.setup_blend_config(lm, pstate->stage, 0XFF, 0,
+				DPU_BLEND_FG_ALPHA_FG_CONST |
+				DPU_BLEND_BG_ALPHA_BG_CONST);
+}
+
+static void _dpu_crtc_program_lm_output_roi(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *crtc_state;
+	int lm_idx, lm_horiz_position;
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	crtc_state = to_dpu_crtc_state(crtc->state);
+
+	lm_horiz_position = 0;
+	for (lm_idx = 0; lm_idx < dpu_crtc->num_mixers; lm_idx++) {
+		const struct drm_rect *lm_roi = &crtc_state->lm_bounds[lm_idx];
+		struct dpu_hw_mixer *hw_lm = dpu_crtc->mixers[lm_idx].hw_lm;
+		struct dpu_hw_mixer_cfg cfg;
+
+		if (!lm_roi || !drm_rect_visible(lm_roi))
+			continue;
+
+		cfg.out_width = drm_rect_width(lm_roi);
+		cfg.out_height = drm_rect_height(lm_roi);
+		cfg.right_mixer = lm_horiz_position++;
+		cfg.flags = 0;
+		hw_lm->ops.setup_mixer_out(hw_lm, &cfg);
+	}
+}
+
+static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc,
+	struct dpu_crtc *dpu_crtc, struct dpu_crtc_mixer *mixer)
+{
+	struct drm_plane *plane;
+	struct drm_framebuffer *fb;
+	struct drm_plane_state *state;
+	struct dpu_crtc_state *cstate;
+	struct dpu_plane_state *pstate = NULL;
+	struct dpu_format *format;
+	struct dpu_hw_ctl *ctl;
+	struct dpu_hw_mixer *lm;
+	struct dpu_hw_stage_cfg *stage_cfg;
+
+	u32 flush_mask;
+	uint32_t stage_idx, lm_idx;
+	int zpos_cnt[DPU_STAGE_MAX + 1] = { 0 };
+	bool bg_alpha_enable = false;
+
+	if (!dpu_crtc || !mixer) {
+		DPU_ERROR("invalid dpu_crtc or mixer\n");
+		return;
+	}
+
+	ctl = mixer->hw_ctl;
+	lm = mixer->hw_lm;
+	stage_cfg = &dpu_crtc->stage_cfg;
+	cstate = to_dpu_crtc_state(crtc->state);
+
+	drm_atomic_crtc_for_each_plane(plane, crtc) {
+		state = plane->state;
+		if (!state)
+			continue;
+
+		pstate = to_dpu_plane_state(state);
+		fb = state->fb;
+
+		dpu_plane_get_ctl_flush(plane, ctl, &flush_mask);
+
+		DPU_DEBUG("crtc %d stage:%d - plane %d sspp %d fb %d\n",
+				crtc->base.id,
+				pstate->stage,
+				plane->base.id,
+				dpu_plane_pipe(plane) - SSPP_VIG0,
+				state->fb ? state->fb->base.id : -1);
+
+		format = to_dpu_format(msm_framebuffer_format(pstate->base.fb));
+		if (!format) {
+			DPU_ERROR("invalid format\n");
+			return;
+		}
+
+		if (pstate->stage == DPU_STAGE_BASE && format->alpha_enable)
+			bg_alpha_enable = true;
+
+		stage_idx = zpos_cnt[pstate->stage]++;
+		stage_cfg->stage[pstate->stage][stage_idx] =
+					dpu_plane_pipe(plane);
+		stage_cfg->multirect_index[pstate->stage][stage_idx] =
+					pstate->multirect_index;
+
+		trace_dpu_crtc_setup_mixer(DRMID(crtc), DRMID(plane),
+					   state, pstate, stage_idx,
+					   dpu_plane_pipe(plane) - SSPP_VIG0,
+					   format->base.pixel_format,
+					   fb ? fb->modifier : 0);
+
+		/* blend config update */
+		for (lm_idx = 0; lm_idx < dpu_crtc->num_mixers; lm_idx++) {
+			_dpu_crtc_setup_blend_cfg(mixer + lm_idx, pstate);
+
+			mixer[lm_idx].flush_mask |= flush_mask;
+
+			if (bg_alpha_enable && !format->alpha_enable)
+				mixer[lm_idx].mixer_op_mode = 0;
+			else
+				mixer[lm_idx].mixer_op_mode |=
+						1 << pstate->stage;
+		}
+	}
+
+	 _dpu_crtc_program_lm_output_roi(crtc);
+}
+
+/**
+ * _dpu_crtc_blend_setup - configure crtc mixers
+ * @crtc: Pointer to drm crtc structure
+ */
+static void _dpu_crtc_blend_setup(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *dpu_crtc_state;
+	struct dpu_crtc_mixer *mixer;
+	struct dpu_hw_ctl *ctl;
+	struct dpu_hw_mixer *lm;
+
+	int i;
+
+	if (!crtc)
+		return;
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	dpu_crtc_state = to_dpu_crtc_state(crtc->state);
+	mixer = dpu_crtc->mixers;
+
+	DPU_DEBUG("%s\n", dpu_crtc->name);
+
+	if (dpu_crtc->num_mixers > CRTC_DUAL_MIXERS) {
+		DPU_ERROR("invalid number mixers: %d\n", dpu_crtc->num_mixers);
+		return;
+	}
+
+	for (i = 0; i < dpu_crtc->num_mixers; i++) {
+		if (!mixer[i].hw_lm || !mixer[i].hw_ctl) {
+			DPU_ERROR("invalid lm or ctl assigned to mixer\n");
+			return;
+		}
+		mixer[i].mixer_op_mode = 0;
+		mixer[i].flush_mask = 0;
+		if (mixer[i].hw_ctl->ops.clear_all_blendstages)
+			mixer[i].hw_ctl->ops.clear_all_blendstages(
+					mixer[i].hw_ctl);
+	}
+
+	/* initialize stage cfg */
+	memset(&dpu_crtc->stage_cfg, 0, sizeof(struct dpu_hw_stage_cfg));
+
+	_dpu_crtc_blend_setup_mixer(crtc, dpu_crtc, mixer);
+
+	for (i = 0; i < dpu_crtc->num_mixers; i++) {
+		ctl = mixer[i].hw_ctl;
+		lm = mixer[i].hw_lm;
+
+		lm->ops.setup_alpha_out(lm, mixer[i].mixer_op_mode);
+
+		mixer[i].flush_mask |= ctl->ops.get_bitmask_mixer(ctl,
+			mixer[i].hw_lm->idx);
+
+		/* stage config flush mask */
+		ctl->ops.update_pending_flush(ctl, mixer[i].flush_mask);
+
+		DPU_DEBUG("lm %d, op_mode 0x%X, ctl %d, flush mask 0x%x\n",
+			mixer[i].hw_lm->idx - LM_0,
+			mixer[i].mixer_op_mode,
+			ctl->idx - CTL_0,
+			mixer[i].flush_mask);
+
+		ctl->ops.setup_blendstage(ctl, mixer[i].hw_lm->idx,
+			&dpu_crtc->stage_cfg);
+	}
+}
+
+/**
+ *  _dpu_crtc_complete_flip - signal pending page_flip events
+ * Any pending vblank events are added to the vblank_event_list
+ * so that the next vblank interrupt shall signal them.
+ * However PAGE_FLIP events are not handled through the vblank_event_list.
+ * This API signals any pending PAGE_FLIP events requested through
+ * DRM_IOCTL_MODE_PAGE_FLIP and are cached in the dpu_crtc->event.
+ * @crtc: Pointer to drm crtc structure
+ */
+static void _dpu_crtc_complete_flip(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct drm_device *dev = crtc->dev;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->event_lock, flags);
+	if (dpu_crtc->event) {
+		DRM_DEBUG_VBL("%s: send event: %pK\n", dpu_crtc->name,
+			      dpu_crtc->event);
+		trace_dpu_crtc_complete_flip(DRMID(crtc));
+		drm_crtc_send_vblank_event(crtc, dpu_crtc->event);
+		dpu_crtc->event = NULL;
+	}
+	spin_unlock_irqrestore(&dev->event_lock, flags);
+}
+
+enum dpu_intf_mode dpu_crtc_get_intf_mode(struct drm_crtc *crtc)
+{
+	struct drm_encoder *encoder;
+
+	if (!crtc || !crtc->dev) {
+		DPU_ERROR("invalid crtc\n");
+		return INTF_MODE_NONE;
+	}
+
+	drm_for_each_encoder(encoder, crtc->dev)
+		if (encoder->crtc == crtc)
+			return dpu_encoder_get_intf_mode(encoder);
+
+	return INTF_MODE_NONE;
+}
+
+static void dpu_crtc_vblank_cb(void *data)
+{
+	struct drm_crtc *crtc = (struct drm_crtc *)data;
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+
+	/* keep statistics on vblank callback - with auto reset via debugfs */
+	if (ktime_compare(dpu_crtc->vblank_cb_time, ktime_set(0, 0)) == 0)
+		dpu_crtc->vblank_cb_time = ktime_get();
+	else
+		dpu_crtc->vblank_cb_count++;
+	_dpu_crtc_complete_flip(crtc);
+	drm_crtc_handle_vblank(crtc);
+	trace_dpu_crtc_vblank_cb(DRMID(crtc));
+}
+
+static void dpu_crtc_frame_event_work(struct kthread_work *work)
+{
+	struct msm_drm_private *priv;
+	struct dpu_crtc_frame_event *fevent;
+	struct drm_crtc *crtc;
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_kms *dpu_kms;
+	unsigned long flags;
+	bool frame_done = false;
+
+	if (!work) {
+		DPU_ERROR("invalid work handle\n");
+		return;
+	}
+
+	fevent = container_of(work, struct dpu_crtc_frame_event, work);
+	if (!fevent->crtc || !fevent->crtc->state) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	crtc = fevent->crtc;
+	dpu_crtc = to_dpu_crtc(crtc);
+
+	dpu_kms = _dpu_crtc_get_kms(crtc);
+	if (!dpu_kms) {
+		DPU_ERROR("invalid kms handle\n");
+		return;
+	}
+	priv = dpu_kms->dev->dev_private;
+	DPU_ATRACE_BEGIN("crtc_frame_event");
+
+	DRM_DEBUG_KMS("crtc%d event:%u ts:%lld\n", crtc->base.id, fevent->event,
+			ktime_to_ns(fevent->ts));
+
+	if (fevent->event & (DPU_ENCODER_FRAME_EVENT_DONE
+				| DPU_ENCODER_FRAME_EVENT_ERROR
+				| DPU_ENCODER_FRAME_EVENT_PANEL_DEAD)) {
+
+		if (atomic_read(&dpu_crtc->frame_pending) < 1) {
+			/* this should not happen */
+			DRM_ERROR("crtc%d ev:%u ts:%lld frame_pending:%d\n",
+					crtc->base.id,
+					fevent->event,
+					ktime_to_ns(fevent->ts),
+					atomic_read(&dpu_crtc->frame_pending));
+		} else if (atomic_dec_return(&dpu_crtc->frame_pending) == 0) {
+			/* release bandwidth and other resources */
+			trace_dpu_crtc_frame_event_done(DRMID(crtc),
+							fevent->event);
+			dpu_core_perf_crtc_release_bw(crtc);
+		} else {
+			trace_dpu_crtc_frame_event_more_pending(DRMID(crtc),
+								fevent->event);
+		}
+
+		if (fevent->event & DPU_ENCODER_FRAME_EVENT_DONE)
+			dpu_core_perf_crtc_update(crtc, 0, false);
+
+		if (fevent->event & (DPU_ENCODER_FRAME_EVENT_DONE
+					| DPU_ENCODER_FRAME_EVENT_ERROR))
+			frame_done = true;
+	}
+
+	if (fevent->event & DPU_ENCODER_FRAME_EVENT_PANEL_DEAD)
+		DPU_ERROR("crtc%d ts:%lld received panel dead event\n",
+				crtc->base.id, ktime_to_ns(fevent->ts));
+
+	if (frame_done)
+		complete_all(&dpu_crtc->frame_done_comp);
+
+	spin_lock_irqsave(&dpu_crtc->spin_lock, flags);
+	list_add_tail(&fevent->list, &dpu_crtc->frame_event_list);
+	spin_unlock_irqrestore(&dpu_crtc->spin_lock, flags);
+	DPU_ATRACE_END("crtc_frame_event");
+}
+
+/*
+ * dpu_crtc_frame_event_cb - crtc frame event callback API. CRTC module
+ * registers this API to encoder for all frame event callbacks like
+ * frame_error, frame_done, idle_timeout, etc. Encoder may call different events
+ * from different context - IRQ, user thread, commit_thread, etc. Each event
+ * should be carefully reviewed and should be processed in proper task context
+ * to avoid schedulin delay or properly manage the irq context's bottom half
+ * processing.
+ */
+static void dpu_crtc_frame_event_cb(void *data, u32 event)
+{
+	struct drm_crtc *crtc = (struct drm_crtc *)data;
+	struct dpu_crtc *dpu_crtc;
+	struct msm_drm_private *priv;
+	struct dpu_crtc_frame_event *fevent;
+	unsigned long flags;
+	u32 crtc_id;
+
+	if (!crtc || !crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	/* Nothing to do on idle event */
+	if (event & DPU_ENCODER_FRAME_EVENT_IDLE)
+		return;
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	priv = crtc->dev->dev_private;
+	crtc_id = drm_crtc_index(crtc);
+
+	trace_dpu_crtc_frame_event_cb(DRMID(crtc), event);
+
+	spin_lock_irqsave(&dpu_crtc->spin_lock, flags);
+	fevent = list_first_entry_or_null(&dpu_crtc->frame_event_list,
+			struct dpu_crtc_frame_event, list);
+	if (fevent)
+		list_del_init(&fevent->list);
+	spin_unlock_irqrestore(&dpu_crtc->spin_lock, flags);
+
+	if (!fevent) {
+		DRM_ERROR("crtc%d event %d overflow\n", crtc->base.id, event);
+		return;
+	}
+
+	fevent->event = event;
+	fevent->crtc = crtc;
+	fevent->ts = ktime_get();
+	kthread_queue_work(&priv->event_thread[crtc_id].worker, &fevent->work);
+}
+
+void dpu_crtc_complete_commit(struct drm_crtc *crtc,
+		struct drm_crtc_state *old_state)
+{
+	if (!crtc || !crtc->state) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+	trace_dpu_crtc_complete_commit(DRMID(crtc));
+}
+
+static void _dpu_crtc_setup_mixer_for_encoder(
+		struct drm_crtc *crtc,
+		struct drm_encoder *enc)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct dpu_kms *dpu_kms = _dpu_crtc_get_kms(crtc);
+	struct dpu_rm *rm = &dpu_kms->rm;
+	struct dpu_crtc_mixer *mixer;
+	struct dpu_hw_ctl *last_valid_ctl = NULL;
+	int i;
+	struct dpu_rm_hw_iter lm_iter, ctl_iter;
+
+	dpu_rm_init_hw_iter(&lm_iter, enc->base.id, DPU_HW_BLK_LM);
+	dpu_rm_init_hw_iter(&ctl_iter, enc->base.id, DPU_HW_BLK_CTL);
+
+	/* Set up all the mixers and ctls reserved by this encoder */
+	for (i = dpu_crtc->num_mixers; i < ARRAY_SIZE(dpu_crtc->mixers); i++) {
+		mixer = &dpu_crtc->mixers[i];
+
+		if (!dpu_rm_get_hw(rm, &lm_iter))
+			break;
+		mixer->hw_lm = (struct dpu_hw_mixer *)lm_iter.hw;
+
+		/* CTL may be <= LMs, if <, multiple LMs controlled by 1 CTL */
+		if (!dpu_rm_get_hw(rm, &ctl_iter)) {
+			DPU_DEBUG("no ctl assigned to lm %d, using previous\n",
+					mixer->hw_lm->idx - LM_0);
+			mixer->hw_ctl = last_valid_ctl;
+		} else {
+			mixer->hw_ctl = (struct dpu_hw_ctl *)ctl_iter.hw;
+			last_valid_ctl = mixer->hw_ctl;
+		}
+
+		/* Shouldn't happen, mixers are always >= ctls */
+		if (!mixer->hw_ctl) {
+			DPU_ERROR("no valid ctls found for lm %d\n",
+					mixer->hw_lm->idx - LM_0);
+			return;
+		}
+
+		mixer->encoder = enc;
+
+		dpu_crtc->num_mixers++;
+		DPU_DEBUG("setup mixer %d: lm %d\n",
+				i, mixer->hw_lm->idx - LM_0);
+		DPU_DEBUG("setup mixer %d: ctl %d\n",
+				i, mixer->hw_ctl->idx - CTL_0);
+	}
+}
+
+static void _dpu_crtc_setup_mixers(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct drm_encoder *enc;
+
+	dpu_crtc->num_mixers = 0;
+	dpu_crtc->mixers_swapped = false;
+	memset(dpu_crtc->mixers, 0, sizeof(dpu_crtc->mixers));
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+	/* Check for mixers on all encoders attached to this crtc */
+	list_for_each_entry(enc, &crtc->dev->mode_config.encoder_list, head) {
+		if (enc->crtc != crtc)
+			continue;
+
+		_dpu_crtc_setup_mixer_for_encoder(crtc, enc);
+	}
+
+	mutex_unlock(&dpu_crtc->crtc_lock);
+}
+
+static void _dpu_crtc_setup_lm_bounds(struct drm_crtc *crtc,
+		struct drm_crtc_state *state)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *cstate;
+	struct drm_display_mode *adj_mode;
+	u32 crtc_split_width;
+	int i;
+
+	if (!crtc || !state) {
+		DPU_ERROR("invalid args\n");
+		return;
+	}
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	cstate = to_dpu_crtc_state(state);
+
+	adj_mode = &state->adjusted_mode;
+	crtc_split_width = dpu_crtc_get_mixer_width(dpu_crtc, cstate, adj_mode);
+
+	for (i = 0; i < dpu_crtc->num_mixers; i++) {
+		struct drm_rect *r = &cstate->lm_bounds[i];
+		r->x1 = crtc_split_width * i;
+		r->y1 = 0;
+		r->x2 = r->x1 + crtc_split_width;
+		r->y2 = dpu_crtc_get_mixer_height(dpu_crtc, cstate, adj_mode);
+
+		trace_dpu_crtc_setup_lm_bounds(DRMID(crtc), i, r);
+	}
+
+	drm_mode_debug_printmodeline(adj_mode);
+}
+
+static void dpu_crtc_atomic_begin(struct drm_crtc *crtc,
+		struct drm_crtc_state *old_state)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct drm_encoder *encoder;
+	struct drm_device *dev;
+	unsigned long flags;
+	struct dpu_crtc_smmu_state_data *smmu_state;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	if (!crtc->state->enable) {
+		DPU_DEBUG("crtc%d -> enable %d, skip atomic_begin\n",
+				crtc->base.id, crtc->state->enable);
+		return;
+	}
+
+	DPU_DEBUG("crtc%d\n", crtc->base.id);
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	dev = crtc->dev;
+	smmu_state = &dpu_crtc->smmu_state;
+
+	if (!dpu_crtc->num_mixers) {
+		_dpu_crtc_setup_mixers(crtc);
+		_dpu_crtc_setup_lm_bounds(crtc, crtc->state);
+	}
+
+	if (dpu_crtc->event) {
+		WARN_ON(dpu_crtc->event);
+	} else {
+		spin_lock_irqsave(&dev->event_lock, flags);
+		dpu_crtc->event = crtc->state->event;
+		crtc->state->event = NULL;
+		spin_unlock_irqrestore(&dev->event_lock, flags);
+	}
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+		if (encoder->crtc != crtc)
+			continue;
+
+		/* encoder will trigger pending mask now */
+		dpu_encoder_trigger_kickoff_pending(encoder);
+	}
+
+	/*
+	 * If no mixers have been allocated in dpu_crtc_atomic_check(),
+	 * it means we are trying to flush a CRTC whose state is disabled:
+	 * nothing else needs to be done.
+	 */
+	if (unlikely(!dpu_crtc->num_mixers))
+		return;
+
+	_dpu_crtc_blend_setup(crtc);
+
+	/*
+	 * PP_DONE irq is only used by command mode for now.
+	 * It is better to request pending before FLUSH and START trigger
+	 * to make sure no pp_done irq missed.
+	 * This is safe because no pp_done will happen before SW trigger
+	 * in command mode.
+	 */
+}
+
+static void dpu_crtc_atomic_flush(struct drm_crtc *crtc,
+		struct drm_crtc_state *old_crtc_state)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct drm_device *dev;
+	struct drm_plane *plane;
+	struct msm_drm_private *priv;
+	struct msm_drm_thread *event_thread;
+	unsigned long flags;
+	struct dpu_crtc_state *cstate;
+
+	if (!crtc || !crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	if (!crtc->state->enable) {
+		DPU_DEBUG("crtc%d -> enable %d, skip atomic_flush\n",
+				crtc->base.id, crtc->state->enable);
+		return;
+	}
+
+	DPU_DEBUG("crtc%d\n", crtc->base.id);
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	cstate = to_dpu_crtc_state(crtc->state);
+	dev = crtc->dev;
+	priv = dev->dev_private;
+
+	if (crtc->index >= ARRAY_SIZE(priv->event_thread)) {
+		DPU_ERROR("invalid crtc index[%d]\n", crtc->index);
+		return;
+	}
+
+	event_thread = &priv->event_thread[crtc->index];
+
+	if (dpu_crtc->event) {
+		DPU_DEBUG("already received dpu_crtc->event\n");
+	} else {
+		spin_lock_irqsave(&dev->event_lock, flags);
+		dpu_crtc->event = crtc->state->event;
+		crtc->state->event = NULL;
+		spin_unlock_irqrestore(&dev->event_lock, flags);
+	}
+
+	/*
+	 * If no mixers has been allocated in dpu_crtc_atomic_check(),
+	 * it means we are trying to flush a CRTC whose state is disabled:
+	 * nothing else needs to be done.
+	 */
+	if (unlikely(!dpu_crtc->num_mixers))
+		return;
+
+	/*
+	 * For planes without commit update, drm framework will not add
+	 * those planes to current state since hardware update is not
+	 * required. However, if those planes were power collapsed since
+	 * last commit cycle, driver has to restore the hardware state
+	 * of those planes explicitly here prior to plane flush.
+	 */
+	drm_atomic_crtc_for_each_plane(plane, crtc)
+		dpu_plane_restore(plane);
+
+	/* update performance setting before crtc kickoff */
+	dpu_core_perf_crtc_update(crtc, 1, false);
+
+	/*
+	 * Final plane updates: Give each plane a chance to complete all
+	 *                      required writes/flushing before crtc's "flush
+	 *                      everything" call below.
+	 */
+	drm_atomic_crtc_for_each_plane(plane, crtc) {
+		if (dpu_crtc->smmu_state.transition_error)
+			dpu_plane_set_error(plane, true);
+		dpu_plane_flush(plane);
+	}
+
+	/* Kickoff will be scheduled by outer layer */
+}
+
+/**
+ * dpu_crtc_destroy_state - state destroy hook
+ * @crtc: drm CRTC
+ * @state: CRTC state object to release
+ */
+static void dpu_crtc_destroy_state(struct drm_crtc *crtc,
+		struct drm_crtc_state *state)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *cstate;
+
+	if (!crtc || !state) {
+		DPU_ERROR("invalid argument(s)\n");
+		return;
+	}
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	cstate = to_dpu_crtc_state(state);
+
+	DPU_DEBUG("crtc%d\n", crtc->base.id);
+
+	_dpu_crtc_rp_destroy(&cstate->rp);
+
+	__drm_atomic_helper_crtc_destroy_state(state);
+
+	kfree(cstate);
+}
+
+static int _dpu_crtc_wait_for_frame_done(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	int ret, rc = 0;
+
+	if (!crtc) {
+		DPU_ERROR("invalid argument\n");
+		return -EINVAL;
+	}
+	dpu_crtc = to_dpu_crtc(crtc);
+
+	if (!atomic_read(&dpu_crtc->frame_pending)) {
+		DPU_DEBUG("no frames pending\n");
+		return 0;
+	}
+
+	DPU_ATRACE_BEGIN("frame done completion wait");
+	ret = wait_for_completion_timeout(&dpu_crtc->frame_done_comp,
+			msecs_to_jiffies(DPU_FRAME_DONE_TIMEOUT));
+	if (!ret) {
+		DRM_ERROR("frame done wait timed out, ret:%d\n", ret);
+		rc = -ETIMEDOUT;
+	}
+	DPU_ATRACE_END("frame done completion wait");
+
+	return rc;
+}
+
+void dpu_crtc_commit_kickoff(struct drm_crtc *crtc)
+{
+	struct drm_encoder *encoder;
+	struct drm_device *dev;
+	struct dpu_crtc *dpu_crtc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	struct dpu_crtc_state *cstate;
+	int ret;
+
+	if (!crtc) {
+		DPU_ERROR("invalid argument\n");
+		return;
+	}
+	dev = crtc->dev;
+	dpu_crtc = to_dpu_crtc(crtc);
+	dpu_kms = _dpu_crtc_get_kms(crtc);
+
+	if (!dpu_kms || !dpu_kms->dev || !dpu_kms->dev->dev_private) {
+		DPU_ERROR("invalid argument\n");
+		return;
+	}
+
+	priv = dpu_kms->dev->dev_private;
+	cstate = to_dpu_crtc_state(crtc->state);
+
+	/*
+	 * If no mixers has been allocated in dpu_crtc_atomic_check(),
+	 * it means we are trying to start a CRTC whose state is disabled:
+	 * nothing else needs to be done.
+	 */
+	if (unlikely(!dpu_crtc->num_mixers))
+		return;
+
+	DPU_ATRACE_BEGIN("crtc_commit");
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+		struct dpu_encoder_kickoff_params params = { 0 };
+
+		if (encoder->crtc != crtc)
+			continue;
+
+		/*
+		 * Encoder will flush/start now, unless it has a tx pending.
+		 * If so, it may delay and flush at an irq event (e.g. ppdone)
+		 */
+		dpu_encoder_prepare_for_kickoff(encoder, &params);
+	}
+
+	/* wait for frame_event_done completion */
+	DPU_ATRACE_BEGIN("wait_for_frame_done_event");
+	ret = _dpu_crtc_wait_for_frame_done(crtc);
+	DPU_ATRACE_END("wait_for_frame_done_event");
+	if (ret) {
+		DPU_ERROR("crtc%d wait for frame done failed;frame_pending%d\n",
+				crtc->base.id,
+				atomic_read(&dpu_crtc->frame_pending));
+		goto end;
+	}
+
+	if (atomic_inc_return(&dpu_crtc->frame_pending) == 1) {
+		/* acquire bandwidth and other resources */
+		DPU_DEBUG("crtc%d first commit\n", crtc->base.id);
+	} else
+		DPU_DEBUG("crtc%d commit\n", crtc->base.id);
+
+	dpu_crtc->play_count++;
+
+	dpu_vbif_clear_errors(dpu_kms);
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+		if (encoder->crtc != crtc)
+			continue;
+
+		dpu_encoder_kickoff(encoder);
+	}
+
+end:
+	reinit_completion(&dpu_crtc->frame_done_comp);
+	DPU_ATRACE_END("crtc_commit");
+}
+
+/**
+ * _dpu_crtc_vblank_enable_no_lock - update power resource and vblank request
+ * @dpu_crtc: Pointer to dpu crtc structure
+ * @enable: Whether to enable/disable vblanks
+ *
+ * @Return: error code
+ */
+static int _dpu_crtc_vblank_enable_no_lock(
+		struct dpu_crtc *dpu_crtc, bool enable)
+{
+	struct drm_device *dev;
+	struct drm_crtc *crtc;
+	struct drm_encoder *enc;
+
+	if (!dpu_crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return -EINVAL;
+	}
+
+	crtc = &dpu_crtc->base;
+	dev = crtc->dev;
+
+	if (enable) {
+		int ret;
+
+		/* drop lock since power crtc cb may try to re-acquire lock */
+		mutex_unlock(&dpu_crtc->crtc_lock);
+		ret = _dpu_crtc_power_enable(dpu_crtc, true);
+		mutex_lock(&dpu_crtc->crtc_lock);
+		if (ret)
+			return ret;
+
+		list_for_each_entry(enc, &dev->mode_config.encoder_list, head) {
+			if (enc->crtc != crtc)
+				continue;
+
+			trace_dpu_crtc_vblank_enable(DRMID(&dpu_crtc->base),
+						     DRMID(enc), enable,
+						     dpu_crtc);
+
+			dpu_encoder_register_vblank_callback(enc,
+					dpu_crtc_vblank_cb, (void *)crtc);
+		}
+	} else {
+		list_for_each_entry(enc, &dev->mode_config.encoder_list, head) {
+			if (enc->crtc != crtc)
+				continue;
+
+			trace_dpu_crtc_vblank_enable(DRMID(&dpu_crtc->base),
+						     DRMID(enc), enable,
+						     dpu_crtc);
+
+			dpu_encoder_register_vblank_callback(enc, NULL, NULL);
+		}
+
+		/* drop lock since power crtc cb may try to re-acquire lock */
+		mutex_unlock(&dpu_crtc->crtc_lock);
+		_dpu_crtc_power_enable(dpu_crtc, false);
+		mutex_lock(&dpu_crtc->crtc_lock);
+	}
+
+	return 0;
+}
+
+/**
+ * _dpu_crtc_set_suspend - notify crtc of suspend enable/disable
+ * @crtc: Pointer to drm crtc object
+ * @enable: true to enable suspend, false to indicate resume
+ */
+static void _dpu_crtc_set_suspend(struct drm_crtc *crtc, bool enable)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	int ret = 0;
+
+	if (!crtc || !crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+	dpu_crtc = to_dpu_crtc(crtc);
+	priv = crtc->dev->dev_private;
+
+	if (!priv->kms) {
+		DPU_ERROR("invalid crtc kms\n");
+		return;
+	}
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	DRM_DEBUG_KMS("crtc%d suspend = %d\n", crtc->base.id, enable);
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+
+	/*
+	 * If the vblank is enabled, release a power reference on suspend
+	 * and take it back during resume (if it is still enabled).
+	 */
+	trace_dpu_crtc_set_suspend(DRMID(&dpu_crtc->base), enable, dpu_crtc);
+	if (dpu_crtc->suspend == enable)
+		DPU_DEBUG("crtc%d suspend already set to %d, ignoring update\n",
+				crtc->base.id, enable);
+	else if (dpu_crtc->enabled && dpu_crtc->vblank_requested) {
+		ret = _dpu_crtc_vblank_enable_no_lock(dpu_crtc, !enable);
+		if (ret)
+			DPU_ERROR("%s vblank enable failed: %d\n",
+					dpu_crtc->name, ret);
+	}
+
+	dpu_crtc->suspend = enable;
+	mutex_unlock(&dpu_crtc->crtc_lock);
+}
+
+/**
+ * dpu_crtc_duplicate_state - state duplicate hook
+ * @crtc: Pointer to drm crtc structure
+ * @Returns: Pointer to new drm_crtc_state structure
+ */
+static struct drm_crtc_state *dpu_crtc_duplicate_state(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *cstate, *old_cstate;
+
+	if (!crtc || !crtc->state) {
+		DPU_ERROR("invalid argument(s)\n");
+		return NULL;
+	}
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	old_cstate = to_dpu_crtc_state(crtc->state);
+	cstate = kmemdup(old_cstate, sizeof(*old_cstate), GFP_KERNEL);
+	if (!cstate) {
+		DPU_ERROR("failed to allocate state\n");
+		return NULL;
+	}
+
+	/* duplicate base helper */
+	__drm_atomic_helper_crtc_duplicate_state(crtc, &cstate->base);
+
+	_dpu_crtc_rp_duplicate(&old_cstate->rp, &cstate->rp);
+
+	return &cstate->base;
+}
+
+/**
+ * dpu_crtc_reset - reset hook for CRTCs
+ * Resets the atomic state for @crtc by freeing the state pointer (which might
+ * be NULL, e.g. at driver load time) and allocating a new empty state object.
+ * @crtc: Pointer to drm crtc structure
+ */
+static void dpu_crtc_reset(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *cstate;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	/* revert suspend actions, if necessary */
+	if (dpu_kms_is_suspend_state(crtc->dev))
+		_dpu_crtc_set_suspend(crtc, false);
+
+	/* remove previous state, if present */
+	if (crtc->state) {
+		dpu_crtc_destroy_state(crtc, crtc->state);
+		crtc->state = 0;
+	}
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	cstate = kzalloc(sizeof(*cstate), GFP_KERNEL);
+	if (!cstate) {
+		DPU_ERROR("failed to allocate state\n");
+		return;
+	}
+
+	_dpu_crtc_rp_reset(&cstate->rp, &dpu_crtc->rp_lock,
+			&dpu_crtc->rp_head);
+
+	cstate->base.crtc = crtc;
+	crtc->state = &cstate->base;
+}
+
+static void dpu_crtc_handle_power_event(u32 event_type, void *arg)
+{
+	struct drm_crtc *crtc = arg;
+	struct dpu_crtc *dpu_crtc;
+	struct drm_encoder *encoder;
+	struct dpu_crtc_mixer *m;
+	u32 i, misr_status;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+	dpu_crtc = to_dpu_crtc(crtc);
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+
+	trace_dpu_crtc_handle_power_event(DRMID(crtc), event_type);
+
+	switch (event_type) {
+	case DPU_POWER_EVENT_POST_ENABLE:
+		/* restore encoder; crtc will be programmed during commit */
+		drm_for_each_encoder(encoder, crtc->dev) {
+			if (encoder->crtc != crtc)
+				continue;
+
+			dpu_encoder_virt_restore(encoder);
+		}
+
+		for (i = 0; i < dpu_crtc->num_mixers; ++i) {
+			m = &dpu_crtc->mixers[i];
+			if (!m->hw_lm || !m->hw_lm->ops.setup_misr ||
+					!dpu_crtc->misr_enable)
+				continue;
+
+			m->hw_lm->ops.setup_misr(m->hw_lm, true,
+					dpu_crtc->misr_frame_count);
+		}
+		break;
+	case DPU_POWER_EVENT_PRE_DISABLE:
+		for (i = 0; i < dpu_crtc->num_mixers; ++i) {
+			m = &dpu_crtc->mixers[i];
+			if (!m->hw_lm || !m->hw_lm->ops.collect_misr ||
+					!dpu_crtc->misr_enable)
+				continue;
+
+			misr_status = m->hw_lm->ops.collect_misr(m->hw_lm);
+			dpu_crtc->misr_data[i] = misr_status ? misr_status :
+							dpu_crtc->misr_data[i];
+		}
+		break;
+	case DPU_POWER_EVENT_POST_DISABLE:
+		/**
+		 * Nothing to do. All the planes on the CRTC will be
+		 * programmed for every frame
+		 */
+		break;
+	default:
+		DPU_DEBUG("event:%d not handled\n", event_type);
+		break;
+	}
+
+	mutex_unlock(&dpu_crtc->crtc_lock);
+}
+
+static void dpu_crtc_disable(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *cstate;
+	struct drm_display_mode *mode;
+	struct drm_encoder *encoder;
+	struct msm_drm_private *priv;
+	int ret;
+	unsigned long flags;
+
+	if (!crtc || !crtc->dev || !crtc->dev->dev_private || !crtc->state) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+	dpu_crtc = to_dpu_crtc(crtc);
+	cstate = to_dpu_crtc_state(crtc->state);
+	mode = &cstate->base.adjusted_mode;
+	priv = crtc->dev->dev_private;
+
+	DRM_DEBUG_KMS("crtc%d\n", crtc->base.id);
+
+	if (dpu_kms_is_suspend_state(crtc->dev))
+		_dpu_crtc_set_suspend(crtc, true);
+
+	/* Disable/save vblank irq handling */
+	drm_crtc_vblank_off(crtc);
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+
+	/* wait for frame_event_done completion */
+	if (_dpu_crtc_wait_for_frame_done(crtc))
+		DPU_ERROR("crtc%d wait for frame done failed;frame_pending%d\n",
+				crtc->base.id,
+				atomic_read(&dpu_crtc->frame_pending));
+
+	trace_dpu_crtc_disable(DRMID(crtc), false, dpu_crtc);
+	if (dpu_crtc->enabled && !dpu_crtc->suspend &&
+			dpu_crtc->vblank_requested) {
+		ret = _dpu_crtc_vblank_enable_no_lock(dpu_crtc, false);
+		if (ret)
+			DPU_ERROR("%s vblank enable failed: %d\n",
+					dpu_crtc->name, ret);
+	}
+	dpu_crtc->enabled = false;
+
+	if (atomic_read(&dpu_crtc->frame_pending)) {
+		trace_dpu_crtc_disable_frame_pending(DRMID(crtc),
+				     atomic_read(&dpu_crtc->frame_pending));
+		dpu_core_perf_crtc_release_bw(crtc);
+		atomic_set(&dpu_crtc->frame_pending, 0);
+	}
+
+	dpu_core_perf_crtc_update(crtc, 0, true);
+
+	drm_for_each_encoder(encoder, crtc->dev) {
+		if (encoder->crtc != crtc)
+			continue;
+		dpu_encoder_register_frame_event_callback(encoder, NULL, NULL);
+	}
+
+	if (dpu_crtc->power_event)
+		dpu_power_handle_unregister_event(dpu_crtc->phandle,
+				dpu_crtc->power_event);
+
+	memset(dpu_crtc->mixers, 0, sizeof(dpu_crtc->mixers));
+	dpu_crtc->num_mixers = 0;
+	dpu_crtc->mixers_swapped = false;
+
+	/* disable clk & bw control until clk & bw properties are set */
+	cstate->bw_control = false;
+	cstate->bw_split_vote = false;
+
+	mutex_unlock(&dpu_crtc->crtc_lock);
+
+	if (crtc->state->event && !crtc->state->active) {
+		spin_lock_irqsave(&crtc->dev->event_lock, flags);
+		drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		crtc->state->event = NULL;
+		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+	}
+}
+
+static void dpu_crtc_enable(struct drm_crtc *crtc,
+		struct drm_crtc_state *old_crtc_state)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct drm_encoder *encoder;
+	struct msm_drm_private *priv;
+	int ret;
+
+	if (!crtc || !crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+	priv = crtc->dev->dev_private;
+
+	DRM_DEBUG_KMS("crtc%d\n", crtc->base.id);
+	dpu_crtc = to_dpu_crtc(crtc);
+
+	drm_for_each_encoder(encoder, crtc->dev) {
+		if (encoder->crtc != crtc)
+			continue;
+		dpu_encoder_register_frame_event_callback(encoder,
+				dpu_crtc_frame_event_cb, (void *)crtc);
+	}
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+	trace_dpu_crtc_enable(DRMID(crtc), true, dpu_crtc);
+	if (!dpu_crtc->enabled && !dpu_crtc->suspend &&
+			dpu_crtc->vblank_requested) {
+		ret = _dpu_crtc_vblank_enable_no_lock(dpu_crtc, true);
+		if (ret)
+			DPU_ERROR("%s vblank enable failed: %d\n",
+					dpu_crtc->name, ret);
+	}
+	dpu_crtc->enabled = true;
+
+	mutex_unlock(&dpu_crtc->crtc_lock);
+
+	/* Enable/restore vblank irq handling */
+	drm_crtc_vblank_on(crtc);
+
+	dpu_crtc->power_event = dpu_power_handle_register_event(
+		dpu_crtc->phandle,
+		DPU_POWER_EVENT_POST_ENABLE | DPU_POWER_EVENT_POST_DISABLE |
+		DPU_POWER_EVENT_PRE_DISABLE,
+		dpu_crtc_handle_power_event, crtc, dpu_crtc->name);
+
+}
+
+struct plane_state {
+	struct dpu_plane_state *dpu_pstate;
+	const struct drm_plane_state *drm_pstate;
+	int stage;
+	u32 pipe_id;
+};
+
+static int dpu_crtc_atomic_check(struct drm_crtc *crtc,
+		struct drm_crtc_state *state)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct plane_state *pstates;
+	struct dpu_crtc_state *cstate;
+
+	const struct drm_plane_state *pstate;
+	struct drm_plane *plane;
+	struct drm_display_mode *mode;
+
+	int cnt = 0, rc = 0, mixer_width, i, z_pos;
+
+	struct dpu_multirect_plane_states multirect_plane[DPU_STAGE_MAX * 2];
+	int multirect_count = 0;
+	const struct drm_plane_state *pipe_staged[SSPP_MAX];
+	int left_zpos_cnt = 0, right_zpos_cnt = 0;
+	struct drm_rect crtc_rect = { 0 };
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return -EINVAL;
+	}
+
+	pstates = kzalloc(sizeof(*pstates) * DPU_STAGE_MAX * 4, GFP_KERNEL);
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	cstate = to_dpu_crtc_state(state);
+
+	if (!state->enable || !state->active) {
+		DPU_DEBUG("crtc%d -> enable %d, active %d, skip atomic_check\n",
+				crtc->base.id, state->enable, state->active);
+		goto end;
+	}
+
+	mode = &state->adjusted_mode;
+	DPU_DEBUG("%s: check", dpu_crtc->name);
+
+	/* force a full mode set if active state changed */
+	if (state->active_changed)
+		state->mode_changed = true;
+
+	memset(pipe_staged, 0, sizeof(pipe_staged));
+
+	mixer_width = dpu_crtc_get_mixer_width(dpu_crtc, cstate, mode);
+
+	_dpu_crtc_setup_lm_bounds(crtc, state);
+
+	crtc_rect.x2 = mode->hdisplay;
+	crtc_rect.y2 = mode->vdisplay;
+
+	 /* get plane state for all drm planes associated with crtc state */
+	drm_atomic_crtc_state_for_each_plane_state(plane, pstate, state) {
+		struct drm_rect dst, clip = crtc_rect;
+
+		if (IS_ERR_OR_NULL(pstate)) {
+			rc = PTR_ERR(pstate);
+			DPU_ERROR("%s: failed to get plane%d state, %d\n",
+					dpu_crtc->name, plane->base.id, rc);
+			goto end;
+		}
+		if (cnt >= DPU_STAGE_MAX * 4)
+			continue;
+
+		pstates[cnt].dpu_pstate = to_dpu_plane_state(pstate);
+		pstates[cnt].drm_pstate = pstate;
+		pstates[cnt].stage = pstate->normalized_zpos;
+		pstates[cnt].pipe_id = dpu_plane_pipe(plane);
+
+		if (pipe_staged[pstates[cnt].pipe_id]) {
+			multirect_plane[multirect_count].r0 =
+				pipe_staged[pstates[cnt].pipe_id];
+			multirect_plane[multirect_count].r1 = pstate;
+			multirect_count++;
+
+			pipe_staged[pstates[cnt].pipe_id] = NULL;
+		} else {
+			pipe_staged[pstates[cnt].pipe_id] = pstate;
+		}
+
+		cnt++;
+
+		dst = drm_plane_state_dest(pstate);
+		if (!drm_rect_intersect(&clip, &dst) ||
+		    !drm_rect_equals(&clip, &dst)) {
+			DPU_ERROR("invalid vertical/horizontal destination\n");
+			DPU_ERROR("display: " DRM_RECT_FMT " plane: "
+				  DRM_RECT_FMT "\n", DRM_RECT_ARG(&crtc_rect),
+				  DRM_RECT_ARG(&dst));
+			rc = -E2BIG;
+			goto end;
+		}
+	}
+
+	for (i = 1; i < SSPP_MAX; i++) {
+		if (pipe_staged[i]) {
+			dpu_plane_clear_multirect(pipe_staged[i]);
+
+			if (is_dpu_plane_virtual(pipe_staged[i]->plane)) {
+				DPU_ERROR(
+					"r1 only virt plane:%d not supported\n",
+					pipe_staged[i]->plane->base.id);
+				rc  = -EINVAL;
+				goto end;
+			}
+		}
+	}
+
+	z_pos = -1;
+	for (i = 0; i < cnt; i++) {
+		/* reset counts at every new blend stage */
+		if (pstates[i].stage != z_pos) {
+			left_zpos_cnt = 0;
+			right_zpos_cnt = 0;
+			z_pos = pstates[i].stage;
+		}
+
+		/* verify z_pos setting before using it */
+		if (z_pos >= DPU_STAGE_MAX - DPU_STAGE_0) {
+			DPU_ERROR("> %d plane stages assigned\n",
+					DPU_STAGE_MAX - DPU_STAGE_0);
+			rc = -EINVAL;
+			goto end;
+		} else if (pstates[i].drm_pstate->crtc_x < mixer_width) {
+			if (left_zpos_cnt == 2) {
+				DPU_ERROR("> 2 planes @ stage %d on left\n",
+					z_pos);
+				rc = -EINVAL;
+				goto end;
+			}
+			left_zpos_cnt++;
+
+		} else {
+			if (right_zpos_cnt == 2) {
+				DPU_ERROR("> 2 planes @ stage %d on right\n",
+					z_pos);
+				rc = -EINVAL;
+				goto end;
+			}
+			right_zpos_cnt++;
+		}
+
+		pstates[i].dpu_pstate->stage = z_pos + DPU_STAGE_0;
+		DPU_DEBUG("%s: zpos %d", dpu_crtc->name, z_pos);
+	}
+
+	for (i = 0; i < multirect_count; i++) {
+		if (dpu_plane_validate_multirect_v2(&multirect_plane[i])) {
+			DPU_ERROR(
+			"multirect validation failed for planes (%d - %d)\n",
+					multirect_plane[i].r0->plane->base.id,
+					multirect_plane[i].r1->plane->base.id);
+			rc = -EINVAL;
+			goto end;
+		}
+	}
+
+	rc = dpu_core_perf_crtc_check(crtc, state);
+	if (rc) {
+		DPU_ERROR("crtc%d failed performance check %d\n",
+				crtc->base.id, rc);
+		goto end;
+	}
+
+	/* validate source split:
+	 * use pstates sorted by stage to check planes on same stage
+	 * we assume that all pipes are in source split so its valid to compare
+	 * without taking into account left/right mixer placement
+	 */
+	for (i = 1; i < cnt; i++) {
+		struct plane_state *prv_pstate, *cur_pstate;
+		struct drm_rect left_rect, right_rect;
+		int32_t left_pid, right_pid;
+		int32_t stage;
+
+		prv_pstate = &pstates[i - 1];
+		cur_pstate = &pstates[i];
+		if (prv_pstate->stage != cur_pstate->stage)
+			continue;
+
+		stage = cur_pstate->stage;
+
+		left_pid = prv_pstate->dpu_pstate->base.plane->base.id;
+		left_rect = drm_plane_state_dest(prv_pstate->drm_pstate);
+
+		right_pid = cur_pstate->dpu_pstate->base.plane->base.id;
+		right_rect = drm_plane_state_dest(cur_pstate->drm_pstate);
+
+		if (right_rect.x1 < left_rect.x1) {
+			swap(left_pid, right_pid);
+			swap(left_rect, right_rect);
+		}
+
+		/**
+		 * - planes are enumerated in pipe-priority order such that
+		 *   planes with lower drm_id must be left-most in a shared
+		 *   blend-stage when using source split.
+		 * - planes in source split must be contiguous in width
+		 * - planes in source split must have same dest yoff and height
+		 */
+		if (right_pid < left_pid) {
+			DPU_ERROR(
+				"invalid src split cfg. priority mismatch. stage: %d left: %d right: %d\n",
+				stage, left_pid, right_pid);
+			rc = -EINVAL;
+			goto end;
+		} else if (right_rect.x1 != drm_rect_width(&left_rect)) {
+			DPU_ERROR("non-contiguous coordinates for src split. "
+				  "stage: %d left: " DRM_RECT_FMT " right: "
+				  DRM_RECT_FMT "\n", stage,
+				  DRM_RECT_ARG(&left_rect),
+				  DRM_RECT_ARG(&right_rect));
+			rc = -EINVAL;
+			goto end;
+		} else if (left_rect.y1 != right_rect.y1 ||
+			   drm_rect_height(&left_rect) != drm_rect_height(&right_rect)) {
+			DPU_ERROR("source split at stage: %d. invalid "
+				  "yoff/height: left: " DRM_RECT_FMT " right: "
+				  DRM_RECT_FMT "\n", stage,
+				  DRM_RECT_ARG(&left_rect),
+				  DRM_RECT_ARG(&right_rect));
+			rc = -EINVAL;
+			goto end;
+		}
+	}
+
+end:
+	_dpu_crtc_rp_free_unused(&cstate->rp);
+	kfree(pstates);
+	return rc;
+}
+
+int dpu_crtc_vblank(struct drm_crtc *crtc, bool en)
+{
+	struct dpu_crtc *dpu_crtc;
+	int ret;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return -EINVAL;
+	}
+	dpu_crtc = to_dpu_crtc(crtc);
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+	trace_dpu_crtc_vblank(DRMID(&dpu_crtc->base), en, dpu_crtc);
+	if (dpu_crtc->enabled && !dpu_crtc->suspend) {
+		ret = _dpu_crtc_vblank_enable_no_lock(dpu_crtc, en);
+		if (ret)
+			DPU_ERROR("%s vblank enable failed: %d\n",
+					dpu_crtc->name, ret);
+	}
+	dpu_crtc->vblank_requested = en;
+	mutex_unlock(&dpu_crtc->crtc_lock);
+
+	return 0;
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int _dpu_debugfs_status_show(struct seq_file *s, void *data)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_plane_state *pstate = NULL;
+	struct dpu_crtc_mixer *m;
+
+	struct drm_crtc *crtc;
+	struct drm_plane *plane;
+	struct drm_display_mode *mode;
+	struct drm_framebuffer *fb;
+	struct drm_plane_state *state;
+	struct dpu_crtc_state *cstate;
+
+	int i, out_width;
+
+	if (!s || !s->private)
+		return -EINVAL;
+
+	dpu_crtc = s->private;
+	crtc = &dpu_crtc->base;
+	cstate = to_dpu_crtc_state(crtc->state);
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+	mode = &crtc->state->adjusted_mode;
+	out_width = dpu_crtc_get_mixer_width(dpu_crtc, cstate, mode);
+
+	seq_printf(s, "crtc:%d width:%d height:%d\n", crtc->base.id,
+				mode->hdisplay, mode->vdisplay);
+
+	seq_puts(s, "\n");
+
+	for (i = 0; i < dpu_crtc->num_mixers; ++i) {
+		m = &dpu_crtc->mixers[i];
+		if (!m->hw_lm)
+			seq_printf(s, "\tmixer[%d] has no lm\n", i);
+		else if (!m->hw_ctl)
+			seq_printf(s, "\tmixer[%d] has no ctl\n", i);
+		else
+			seq_printf(s, "\tmixer:%d ctl:%d width:%d height:%d\n",
+				m->hw_lm->idx - LM_0, m->hw_ctl->idx - CTL_0,
+				out_width, mode->vdisplay);
+	}
+
+	seq_puts(s, "\n");
+
+	drm_atomic_crtc_for_each_plane(plane, crtc) {
+		pstate = to_dpu_plane_state(plane->state);
+		state = plane->state;
+
+		if (!pstate || !state)
+			continue;
+
+		seq_printf(s, "\tplane:%u stage:%d\n", plane->base.id,
+			pstate->stage);
+
+		if (plane->state->fb) {
+			fb = plane->state->fb;
+
+			seq_printf(s, "\tfb:%d image format:%4.4s wxh:%ux%u ",
+				fb->base.id, (char *) &fb->format->format,
+				fb->width, fb->height);
+			for (i = 0; i < ARRAY_SIZE(fb->format->cpp); ++i)
+				seq_printf(s, "cpp[%d]:%u ",
+						i, fb->format->cpp[i]);
+			seq_puts(s, "\n\t");
+
+			seq_printf(s, "modifier:%8llu ", fb->modifier);
+			seq_puts(s, "\n");
+
+			seq_puts(s, "\t");
+			for (i = 0; i < ARRAY_SIZE(fb->pitches); i++)
+				seq_printf(s, "pitches[%d]:%8u ", i,
+							fb->pitches[i]);
+			seq_puts(s, "\n");
+
+			seq_puts(s, "\t");
+			for (i = 0; i < ARRAY_SIZE(fb->offsets); i++)
+				seq_printf(s, "offsets[%d]:%8u ", i,
+							fb->offsets[i]);
+			seq_puts(s, "\n");
+		}
+
+		seq_printf(s, "\tsrc_x:%4d src_y:%4d src_w:%4d src_h:%4d\n",
+			state->src_x, state->src_y, state->src_w, state->src_h);
+
+		seq_printf(s, "\tdst x:%4d dst_y:%4d dst_w:%4d dst_h:%4d\n",
+			state->crtc_x, state->crtc_y, state->crtc_w,
+			state->crtc_h);
+		seq_printf(s, "\tmultirect: mode: %d index: %d\n",
+			pstate->multirect_mode, pstate->multirect_index);
+
+		seq_puts(s, "\n");
+	}
+	if (dpu_crtc->vblank_cb_count) {
+		ktime_t diff = ktime_sub(ktime_get(), dpu_crtc->vblank_cb_time);
+		s64 diff_ms = ktime_to_ms(diff);
+		s64 fps = diff_ms ? div_s64(
+				dpu_crtc->vblank_cb_count * 1000, diff_ms) : 0;
+
+		seq_printf(s,
+			"vblank fps:%lld count:%u total:%llums total_framecount:%llu\n",
+				fps, dpu_crtc->vblank_cb_count,
+				ktime_to_ms(diff), dpu_crtc->play_count);
+
+		/* reset time & count for next measurement */
+		dpu_crtc->vblank_cb_count = 0;
+		dpu_crtc->vblank_cb_time = ktime_set(0, 0);
+	}
+
+	seq_printf(s, "vblank_enable:%d\n", dpu_crtc->vblank_requested);
+
+	mutex_unlock(&dpu_crtc->crtc_lock);
+
+	return 0;
+}
+
+static int _dpu_debugfs_status_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, _dpu_debugfs_status_show, inode->i_private);
+}
+
+static ssize_t _dpu_crtc_misr_setup(struct file *file,
+		const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_mixer *m;
+	int i = 0, rc;
+	char buf[MISR_BUFF_SIZE + 1];
+	u32 frame_count, enable;
+	size_t buff_copy;
+
+	if (!file || !file->private_data)
+		return -EINVAL;
+
+	dpu_crtc = file->private_data;
+	buff_copy = min_t(size_t, count, MISR_BUFF_SIZE);
+	if (copy_from_user(buf, user_buf, buff_copy)) {
+		DPU_ERROR("buffer copy failed\n");
+		return -EINVAL;
+	}
+
+	buf[buff_copy] = 0; /* end of string */
+
+	if (sscanf(buf, "%u %u", &enable, &frame_count) != 2)
+		return -EINVAL;
+
+	rc = _dpu_crtc_power_enable(dpu_crtc, true);
+	if (rc)
+		return rc;
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+	dpu_crtc->misr_enable = enable;
+	dpu_crtc->misr_frame_count = frame_count;
+	for (i = 0; i < dpu_crtc->num_mixers; ++i) {
+		dpu_crtc->misr_data[i] = 0;
+		m = &dpu_crtc->mixers[i];
+		if (!m->hw_lm || !m->hw_lm->ops.setup_misr)
+			continue;
+
+		m->hw_lm->ops.setup_misr(m->hw_lm, enable, frame_count);
+	}
+	mutex_unlock(&dpu_crtc->crtc_lock);
+	_dpu_crtc_power_enable(dpu_crtc, false);
+
+	return count;
+}
+
+static ssize_t _dpu_crtc_misr_read(struct file *file,
+		char __user *user_buff, size_t count, loff_t *ppos)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_mixer *m;
+	int i = 0, rc;
+	u32 misr_status;
+	ssize_t len = 0;
+	char buf[MISR_BUFF_SIZE + 1] = {'\0'};
+
+	if (*ppos)
+		return 0;
+
+	if (!file || !file->private_data)
+		return -EINVAL;
+
+	dpu_crtc = file->private_data;
+	rc = _dpu_crtc_power_enable(dpu_crtc, true);
+	if (rc)
+		return rc;
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+	if (!dpu_crtc->misr_enable) {
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len,
+			"disabled\n");
+		goto buff_check;
+	}
+
+	for (i = 0; i < dpu_crtc->num_mixers; ++i) {
+		m = &dpu_crtc->mixers[i];
+		if (!m->hw_lm || !m->hw_lm->ops.collect_misr)
+			continue;
+
+		misr_status = m->hw_lm->ops.collect_misr(m->hw_lm);
+		dpu_crtc->misr_data[i] = misr_status ? misr_status :
+							dpu_crtc->misr_data[i];
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len, "lm idx:%d\n",
+					m->hw_lm->idx - LM_0);
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len, "0x%x\n",
+							dpu_crtc->misr_data[i]);
+	}
+
+buff_check:
+	if (count <= len) {
+		len = 0;
+		goto end;
+	}
+
+	if (copy_to_user(user_buff, buf, len)) {
+		len = -EFAULT;
+		goto end;
+	}
+
+	*ppos += len;   /* increase offset */
+
+end:
+	mutex_unlock(&dpu_crtc->crtc_lock);
+	_dpu_crtc_power_enable(dpu_crtc, false);
+	return len;
+}
+
+#define DEFINE_DPU_DEBUGFS_SEQ_FOPS(__prefix)                          \
+static int __prefix ## _open(struct inode *inode, struct file *file)	\
+{									\
+	return single_open(file, __prefix ## _show, inode->i_private);	\
+}									\
+static const struct file_operations __prefix ## _fops = {		\
+	.owner = THIS_MODULE,						\
+	.open = __prefix ## _open,					\
+	.release = single_release,					\
+	.read = seq_read,						\
+	.llseek = seq_lseek,						\
+}
+
+static int dpu_crtc_debugfs_state_show(struct seq_file *s, void *v)
+{
+	struct drm_crtc *crtc = (struct drm_crtc *) s->private;
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct dpu_crtc_res *res;
+	struct dpu_crtc_respool *rp;
+	int i;
+
+	seq_printf(s, "client type: %d\n", dpu_crtc_get_client_type(crtc));
+	seq_printf(s, "intf_mode: %d\n", dpu_crtc_get_intf_mode(crtc));
+	seq_printf(s, "core_clk_rate: %llu\n",
+			dpu_crtc->cur_perf.core_clk_rate);
+	for (i = DPU_POWER_HANDLE_DBUS_ID_MNOC;
+			i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+		seq_printf(s, "bw_ctl[%s]: %llu\n",
+				dpu_power_handle_get_dbus_name(i),
+				dpu_crtc->cur_perf.bw_ctl[i]);
+		seq_printf(s, "max_per_pipe_ib[%s]: %llu\n",
+				dpu_power_handle_get_dbus_name(i),
+				dpu_crtc->cur_perf.max_per_pipe_ib[i]);
+	}
+
+	mutex_lock(&dpu_crtc->rp_lock);
+	list_for_each_entry(rp, &dpu_crtc->rp_head, rp_list) {
+		seq_printf(s, "rp.%d: ", rp->sequence_id);
+		list_for_each_entry(res, &rp->res_list, list)
+			seq_printf(s, "0x%x/0x%llx/%pK/%d ",
+					res->type, res->tag, res->val,
+					atomic_read(&res->refcount));
+		seq_puts(s, "\n");
+	}
+	mutex_unlock(&dpu_crtc->rp_lock);
+
+	return 0;
+}
+DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_crtc_debugfs_state);
+
+static int _dpu_crtc_init_debugfs(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_kms *dpu_kms;
+
+	static const struct file_operations debugfs_status_fops = {
+		.open =		_dpu_debugfs_status_open,
+		.read =		seq_read,
+		.llseek =	seq_lseek,
+		.release =	single_release,
+	};
+	static const struct file_operations debugfs_misr_fops = {
+		.open =		simple_open,
+		.read =		_dpu_crtc_misr_read,
+		.write =	_dpu_crtc_misr_setup,
+	};
+
+	if (!crtc)
+		return -EINVAL;
+	dpu_crtc = to_dpu_crtc(crtc);
+
+	dpu_kms = _dpu_crtc_get_kms(crtc);
+	if (!dpu_kms)
+		return -EINVAL;
+
+	dpu_crtc->debugfs_root = debugfs_create_dir(dpu_crtc->name,
+			crtc->dev->primary->debugfs_root);
+	if (!dpu_crtc->debugfs_root)
+		return -ENOMEM;
+
+	/* don't error check these */
+	debugfs_create_file("status", 0400,
+			dpu_crtc->debugfs_root,
+			dpu_crtc, &debugfs_status_fops);
+	debugfs_create_file("state", 0600,
+			dpu_crtc->debugfs_root,
+			&dpu_crtc->base,
+			&dpu_crtc_debugfs_state_fops);
+	debugfs_create_file("misr_data", 0600, dpu_crtc->debugfs_root,
+					dpu_crtc, &debugfs_misr_fops);
+
+	return 0;
+}
+
+static void _dpu_crtc_destroy_debugfs(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+
+	if (!crtc)
+		return;
+	dpu_crtc = to_dpu_crtc(crtc);
+	debugfs_remove_recursive(dpu_crtc->debugfs_root);
+}
+#else
+static int _dpu_crtc_init_debugfs(struct drm_crtc *crtc)
+{
+	return 0;
+}
+
+static void _dpu_crtc_destroy_debugfs(struct drm_crtc *crtc)
+{
+}
+#endif /* CONFIG_DEBUG_FS */
+
+static int dpu_crtc_late_register(struct drm_crtc *crtc)
+{
+	return _dpu_crtc_init_debugfs(crtc);
+}
+
+static void dpu_crtc_early_unregister(struct drm_crtc *crtc)
+{
+	_dpu_crtc_destroy_debugfs(crtc);
+}
+
+static const struct drm_crtc_funcs dpu_crtc_funcs = {
+	.set_config = drm_atomic_helper_set_config,
+	.destroy = dpu_crtc_destroy,
+	.page_flip = drm_atomic_helper_page_flip,
+	.reset = dpu_crtc_reset,
+	.atomic_duplicate_state = dpu_crtc_duplicate_state,
+	.atomic_destroy_state = dpu_crtc_destroy_state,
+	.late_register = dpu_crtc_late_register,
+	.early_unregister = dpu_crtc_early_unregister,
+};
+
+static const struct drm_crtc_helper_funcs dpu_crtc_helper_funcs = {
+	.disable = dpu_crtc_disable,
+	.atomic_enable = dpu_crtc_enable,
+	.atomic_check = dpu_crtc_atomic_check,
+	.atomic_begin = dpu_crtc_atomic_begin,
+	.atomic_flush = dpu_crtc_atomic_flush,
+};
+
+/* initialize crtc */
+struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane)
+{
+	struct drm_crtc *crtc = NULL;
+	struct dpu_crtc *dpu_crtc = NULL;
+	struct msm_drm_private *priv = NULL;
+	struct dpu_kms *kms = NULL;
+	int i;
+
+	priv = dev->dev_private;
+	kms = to_dpu_kms(priv->kms);
+
+	dpu_crtc = kzalloc(sizeof(*dpu_crtc), GFP_KERNEL);
+	if (!dpu_crtc)
+		return ERR_PTR(-ENOMEM);
+
+	crtc = &dpu_crtc->base;
+	crtc->dev = dev;
+
+	mutex_init(&dpu_crtc->crtc_lock);
+	spin_lock_init(&dpu_crtc->spin_lock);
+	atomic_set(&dpu_crtc->frame_pending, 0);
+
+	mutex_init(&dpu_crtc->rp_lock);
+	INIT_LIST_HEAD(&dpu_crtc->rp_head);
+
+	init_completion(&dpu_crtc->frame_done_comp);
+
+	INIT_LIST_HEAD(&dpu_crtc->frame_event_list);
+
+	for (i = 0; i < ARRAY_SIZE(dpu_crtc->frame_events); i++) {
+		INIT_LIST_HEAD(&dpu_crtc->frame_events[i].list);
+		list_add(&dpu_crtc->frame_events[i].list,
+				&dpu_crtc->frame_event_list);
+		kthread_init_work(&dpu_crtc->frame_events[i].work,
+				dpu_crtc_frame_event_work);
+	}
+
+	drm_crtc_init_with_planes(dev, crtc, plane, NULL, &dpu_crtc_funcs,
+				NULL);
+
+	drm_crtc_helper_add(crtc, &dpu_crtc_helper_funcs);
+	plane->crtc = crtc;
+
+	/* save user friendly CRTC name for later */
+	snprintf(dpu_crtc->name, DPU_CRTC_NAME_SIZE, "crtc%u", crtc->base.id);
+
+	/* initialize event handling */
+	spin_lock_init(&dpu_crtc->event_lock);
+
+	dpu_crtc->phandle = &kms->phandle;
+
+	DPU_DEBUG("%s: successfully initialized crtc\n", dpu_crtc->name);
+	return crtc;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h
new file mode 100644
index 000000000000..e87109e608e9
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h
@@ -0,0 +1,423 @@
+/*
+ * Copyright (c) 2015-2018 The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _DPU_CRTC_H_
+#define _DPU_CRTC_H_
+
+#include <linux/kthread.h>
+#include <drm/drm_crtc.h>
+#include "dpu_kms.h"
+#include "dpu_core_perf.h"
+#include "dpu_hw_blk.h"
+
+#define DPU_CRTC_NAME_SIZE	12
+
+/* define the maximum number of in-flight frame events */
+#define DPU_CRTC_FRAME_EVENT_SIZE	4
+
+/**
+ * enum dpu_crtc_client_type: crtc client type
+ * @RT_CLIENT:	RealTime client like video/cmd mode display
+ *              voting through apps rsc
+ * @NRT_CLIENT:	Non-RealTime client like WB display
+ *              voting through apps rsc
+ */
+enum dpu_crtc_client_type {
+	RT_CLIENT,
+	NRT_CLIENT,
+};
+
+/**
+ * enum dpu_crtc_smmu_state:	smmu state
+ * @ATTACHED:	 all the context banks are attached.
+ * @DETACHED:	 all the context banks are detached.
+ * @ATTACH_ALL_REQ:	 transient state of attaching context banks.
+ * @DETACH_ALL_REQ:	 transient state of detaching context banks.
+ */
+enum dpu_crtc_smmu_state {
+	ATTACHED = 0,
+	DETACHED,
+	ATTACH_ALL_REQ,
+	DETACH_ALL_REQ,
+};
+
+/**
+ * enum dpu_crtc_smmu_state_transition_type: state transition type
+ * @NONE: no pending state transitions
+ * @PRE_COMMIT: state transitions should be done before processing the commit
+ * @POST_COMMIT: state transitions to be done after processing the commit.
+ */
+enum dpu_crtc_smmu_state_transition_type {
+	NONE,
+	PRE_COMMIT,
+	POST_COMMIT
+};
+
+/**
+ * struct dpu_crtc_smmu_state_data: stores the smmu state and transition type
+ * @state: current state of smmu context banks
+ * @transition_type: transition request type
+ * @transition_error: whether there is error while transitioning the state
+ */
+struct dpu_crtc_smmu_state_data {
+	uint32_t state;
+	uint32_t transition_type;
+	uint32_t transition_error;
+};
+
+/**
+ * struct dpu_crtc_mixer: stores the map for each virtual pipeline in the CRTC
+ * @hw_lm:	LM HW Driver context
+ * @hw_ctl:	CTL Path HW driver context
+ * @encoder:	Encoder attached to this lm & ctl
+ * @mixer_op_mode:	mixer blending operation mode
+ * @flush_mask:	mixer flush mask for ctl, mixer and pipe
+ */
+struct dpu_crtc_mixer {
+	struct dpu_hw_mixer *hw_lm;
+	struct dpu_hw_ctl *hw_ctl;
+	struct drm_encoder *encoder;
+	u32 mixer_op_mode;
+	u32 flush_mask;
+};
+
+/**
+ * struct dpu_crtc_frame_event: stores crtc frame event for crtc processing
+ * @work:	base work structure
+ * @crtc:	Pointer to crtc handling this event
+ * @list:	event list
+ * @ts:		timestamp at queue entry
+ * @event:	event identifier
+ */
+struct dpu_crtc_frame_event {
+	struct kthread_work work;
+	struct drm_crtc *crtc;
+	struct list_head list;
+	ktime_t ts;
+	u32 event;
+};
+
+/*
+ * Maximum number of free event structures to cache
+ */
+#define DPU_CRTC_MAX_EVENT_COUNT	16
+
+/**
+ * struct dpu_crtc - virtualized CRTC data structure
+ * @base          : Base drm crtc structure
+ * @name          : ASCII description of this crtc
+ * @num_ctls      : Number of ctl paths in use
+ * @num_mixers    : Number of mixers in use
+ * @mixers_swapped: Whether the mixers have been swapped for left/right update
+ *                  especially in the case of DSC Merge.
+ * @mixers        : List of active mixers
+ * @event         : Pointer to last received drm vblank event. If there is a
+ *                  pending vblank event, this will be non-null.
+ * @vsync_count   : Running count of received vsync events
+ * @drm_requested_vblank : Whether vblanks have been enabled in the encoder
+ * @property_info : Opaque structure for generic property support
+ * @property_defaults : Array of default values for generic property support
+ * @stage_cfg     : H/w mixer stage configuration
+ * @debugfs_root  : Parent of debugfs node
+ * @vblank_cb_count : count of vblank callback since last reset
+ * @play_count    : frame count between crtc enable and disable
+ * @vblank_cb_time  : ktime at vblank count reset
+ * @vblank_requested : whether the user has requested vblank events
+ * @suspend         : whether or not a suspend operation is in progress
+ * @enabled       : whether the DPU CRTC is currently enabled. updated in the
+ *                  commit-thread, not state-swap time which is earlier, so
+ *                  safe to make decisions on during VBLANK on/off work
+ * @feature_list  : list of color processing features supported on a crtc
+ * @active_list   : list of color processing features are active
+ * @dirty_list    : list of color processing features are dirty
+ * @ad_dirty: list containing ad properties that are dirty
+ * @ad_active: list containing ad properties that are active
+ * @crtc_lock     : crtc lock around create, destroy and access.
+ * @frame_pending : Whether or not an update is pending
+ * @frame_events  : static allocation of in-flight frame events
+ * @frame_event_list : available frame event list
+ * @spin_lock     : spin lock for frame event, transaction status, etc...
+ * @frame_done_comp    : for frame_event_done synchronization
+ * @event_thread  : Pointer to event handler thread
+ * @event_worker  : Event worker queue
+ * @event_lock    : Spinlock around event handling code
+ * @misr_enable   : boolean entry indicates misr enable/disable status.
+ * @misr_frame_count  : misr frame count provided by client
+ * @misr_data     : store misr data before turning off the clocks.
+ * @phandle: Pointer to power handler
+ * @power_event   : registered power event handle
+ * @cur_perf      : current performance committed to clock/bandwidth driver
+ * @rp_lock       : serialization lock for resource pool
+ * @rp_head       : list of active resource pool
+ * @scl3_cfg_lut  : qseed3 lut config
+ */
+struct dpu_crtc {
+	struct drm_crtc base;
+	char name[DPU_CRTC_NAME_SIZE];
+
+	/* HW Resources reserved for the crtc */
+	u32 num_ctls;
+	u32 num_mixers;
+	bool mixers_swapped;
+	struct dpu_crtc_mixer mixers[CRTC_DUAL_MIXERS];
+	struct dpu_hw_scaler3_lut_cfg *scl3_lut_cfg;
+
+	struct drm_pending_vblank_event *event;
+	u32 vsync_count;
+
+	struct dpu_hw_stage_cfg stage_cfg;
+	struct dentry *debugfs_root;
+
+	u32 vblank_cb_count;
+	u64 play_count;
+	ktime_t vblank_cb_time;
+	bool vblank_requested;
+	bool suspend;
+	bool enabled;
+
+	struct list_head feature_list;
+	struct list_head active_list;
+	struct list_head dirty_list;
+	struct list_head ad_dirty;
+	struct list_head ad_active;
+
+	struct mutex crtc_lock;
+
+	atomic_t frame_pending;
+	struct dpu_crtc_frame_event frame_events[DPU_CRTC_FRAME_EVENT_SIZE];
+	struct list_head frame_event_list;
+	spinlock_t spin_lock;
+	struct completion frame_done_comp;
+
+	/* for handling internal event thread */
+	spinlock_t event_lock;
+	bool misr_enable;
+	u32 misr_frame_count;
+	u32 misr_data[CRTC_DUAL_MIXERS];
+
+	struct dpu_power_handle *phandle;
+	struct dpu_power_event *power_event;
+
+	struct dpu_core_perf_params cur_perf;
+
+	struct mutex rp_lock;
+	struct list_head rp_head;
+
+	struct dpu_crtc_smmu_state_data smmu_state;
+};
+
+#define to_dpu_crtc(x) container_of(x, struct dpu_crtc, base)
+
+/**
+ * struct dpu_crtc_res_ops - common operations for crtc resources
+ * @get: get given resource
+ * @put: put given resource
+ */
+struct dpu_crtc_res_ops {
+	void *(*get)(void *val, u32 type, u64 tag);
+	void (*put)(void *val);
+};
+
+#define DPU_CRTC_RES_FLAG_FREE		BIT(0)
+
+/**
+ * struct dpu_crtc_res - definition of crtc resources
+ * @list: list of crtc resource
+ * @type: crtc resource type
+ * @tag: unique identifier per type
+ * @refcount: reference/usage count
+ * @ops: callback operations
+ * @val: resource handle associated with type/tag
+ * @flags: customization flags
+ */
+struct dpu_crtc_res {
+	struct list_head list;
+	u32 type;
+	u64 tag;
+	atomic_t refcount;
+	struct dpu_crtc_res_ops ops;
+	void *val;
+	u32 flags;
+};
+
+/**
+ * dpu_crtc_respool - crtc resource pool
+ * @rp_lock: pointer to serialization lock
+ * @rp_head: pointer to head of active resource pools of this crtc
+ * @rp_list: list of crtc resource pool
+ * @sequence_id: sequence identifier, incremented per state duplication
+ * @res_list: list of resource managed by this resource pool
+ * @ops: resource operations for parent resource pool
+ */
+struct dpu_crtc_respool {
+	struct mutex *rp_lock;
+	struct list_head *rp_head;
+	struct list_head rp_list;
+	u32 sequence_id;
+	struct list_head res_list;
+	struct dpu_crtc_res_ops ops;
+};
+
+/**
+ * struct dpu_crtc_state - dpu container for atomic crtc state
+ * @base: Base drm crtc state structure
+ * @is_ppsplit    : Whether current topology requires PPSplit special handling
+ * @bw_control    : true if bw/clk controlled by core bw/clk properties
+ * @bw_split_vote : true if bw controlled by llcc/dram bw properties
+ * @lm_bounds     : LM boundaries based on current mode full resolution, no ROI.
+ *                  Origin top left of CRTC.
+ * @property_state: Local storage for msm_prop properties
+ * @property_values: Current crtc property values
+ * @input_fence_timeout_ns : Cached input fence timeout, in ns
+ * @new_perf: new performance state being requested
+ */
+struct dpu_crtc_state {
+	struct drm_crtc_state base;
+
+	bool bw_control;
+	bool bw_split_vote;
+
+	bool is_ppsplit;
+	struct drm_rect lm_bounds[CRTC_DUAL_MIXERS];
+
+	uint64_t input_fence_timeout_ns;
+
+	struct dpu_core_perf_params new_perf;
+	struct dpu_crtc_respool rp;
+};
+
+#define to_dpu_crtc_state(x) \
+	container_of(x, struct dpu_crtc_state, base)
+
+/**
+ * dpu_crtc_get_mixer_width - get the mixer width
+ * Mixer width will be same as panel width(/2 for split)
+ */
+static inline int dpu_crtc_get_mixer_width(struct dpu_crtc *dpu_crtc,
+	struct dpu_crtc_state *cstate, struct drm_display_mode *mode)
+{
+	u32 mixer_width;
+
+	if (!dpu_crtc || !cstate || !mode)
+		return 0;
+
+	mixer_width = (dpu_crtc->num_mixers == CRTC_DUAL_MIXERS ?
+			mode->hdisplay / CRTC_DUAL_MIXERS : mode->hdisplay);
+
+	return mixer_width;
+}
+
+/**
+ * dpu_crtc_get_mixer_height - get the mixer height
+ * Mixer height will be same as panel height
+ */
+static inline int dpu_crtc_get_mixer_height(struct dpu_crtc *dpu_crtc,
+		struct dpu_crtc_state *cstate, struct drm_display_mode *mode)
+{
+	if (!dpu_crtc || !cstate || !mode)
+		return 0;
+
+	return mode->vdisplay;
+}
+
+/**
+ * dpu_crtc_frame_pending - retun the number of pending frames
+ * @crtc: Pointer to drm crtc object
+ */
+static inline int dpu_crtc_frame_pending(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+
+	if (!crtc)
+		return -EINVAL;
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	return atomic_read(&dpu_crtc->frame_pending);
+}
+
+/**
+ * dpu_crtc_vblank - enable or disable vblanks for this crtc
+ * @crtc: Pointer to drm crtc object
+ * @en: true to enable vblanks, false to disable
+ */
+int dpu_crtc_vblank(struct drm_crtc *crtc, bool en);
+
+/**
+ * dpu_crtc_commit_kickoff - trigger kickoff of the commit for this crtc
+ * @crtc: Pointer to drm crtc object
+ */
+void dpu_crtc_commit_kickoff(struct drm_crtc *crtc);
+
+/**
+ * dpu_crtc_complete_commit - callback signalling completion of current commit
+ * @crtc: Pointer to drm crtc object
+ * @old_state: Pointer to drm crtc old state object
+ */
+void dpu_crtc_complete_commit(struct drm_crtc *crtc,
+		struct drm_crtc_state *old_state);
+
+/**
+ * dpu_crtc_init - create a new crtc object
+ * @dev: dpu device
+ * @plane: base plane
+ * @Return: new crtc object or error
+ */
+struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane);
+
+/**
+ * dpu_crtc_register_custom_event - api for enabling/disabling crtc event
+ * @kms: Pointer to dpu_kms
+ * @crtc_drm: Pointer to crtc object
+ * @event: Event that client is interested
+ * @en: Flag to enable/disable the event
+ */
+int dpu_crtc_register_custom_event(struct dpu_kms *kms,
+		struct drm_crtc *crtc_drm, u32 event, bool en);
+
+/**
+ * dpu_crtc_get_intf_mode - get interface mode of the given crtc
+ * @crtc: Pointert to crtc
+ */
+enum dpu_intf_mode dpu_crtc_get_intf_mode(struct drm_crtc *crtc);
+
+/**
+ * dpu_crtc_get_client_type - check the crtc type- rt, nrt etc.
+ * @crtc: Pointer to crtc
+ */
+static inline enum dpu_crtc_client_type dpu_crtc_get_client_type(
+						struct drm_crtc *crtc)
+{
+	struct dpu_crtc_state *cstate =
+			crtc ? to_dpu_crtc_state(crtc->state) : NULL;
+
+	if (!cstate)
+		return NRT_CLIENT;
+
+	return RT_CLIENT;
+}
+
+/**
+ * dpu_crtc_is_enabled - check if dpu crtc is enabled or not
+ * @crtc: Pointer to crtc
+ */
+static inline bool dpu_crtc_is_enabled(struct drm_crtc *crtc)
+{
+	return crtc ? crtc->enabled : false;
+}
+
+#endif /* _DPU_CRTC_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.c
new file mode 100644
index 000000000000..ae2aee7ed9e1
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.c
@@ -0,0 +1,2393 @@
+/* Copyright (c) 2009-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/ktime.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/dma-buf.h>
+#include <linux/slab.h>
+#include <linux/list_sort.h>
+#include <linux/pm_runtime.h>
+
+#include "dpu_dbg.h"
+#include "disp/dpu1/dpu_hw_catalog.h"
+
+
+#define DEFAULT_DBGBUS_DPU	DPU_DBG_DUMP_IN_MEM
+#define DEFAULT_DBGBUS_VBIFRT	DPU_DBG_DUMP_IN_MEM
+#define REG_BASE_NAME_LEN	80
+
+#define DBGBUS_FLAGS_DSPP	BIT(0)
+#define DBGBUS_DSPP_STATUS	0x34C
+
+#define DBGBUS_NAME_DPU		"dpu"
+#define DBGBUS_NAME_VBIF_RT	"vbif_rt"
+
+/* offsets from dpu top address for the debug buses */
+#define DBGBUS_SSPP0	0x188
+#define DBGBUS_AXI_INTF	0x194
+#define DBGBUS_SSPP1	0x298
+#define DBGBUS_DSPP	0x348
+#define DBGBUS_PERIPH	0x418
+
+#define TEST_MASK(id, tp)	((id << 4) | (tp << 1) | BIT(0))
+
+/* following offsets are with respect to MDP VBIF base for DBG BUS access */
+#define MMSS_VBIF_CLKON			0x4
+#define MMSS_VBIF_TEST_BUS_OUT_CTRL	0x210
+#define MMSS_VBIF_TEST_BUS_OUT		0x230
+
+/* Vbif error info */
+#define MMSS_VBIF_PND_ERR		0x190
+#define MMSS_VBIF_SRC_ERR		0x194
+#define MMSS_VBIF_XIN_HALT_CTRL1	0x204
+#define MMSS_VBIF_ERR_INFO		0X1a0
+#define MMSS_VBIF_ERR_INFO_1		0x1a4
+#define MMSS_VBIF_CLIENT_NUM		14
+
+/**
+ * struct dpu_dbg_reg_base - register region base.
+ *	may sub-ranges: sub-ranges are used for dumping
+ *	or may not have sub-ranges: dumping is base -> max_offset
+ * @reg_base_head: head of this node
+ * @name: register base name
+ * @base: base pointer
+ * @off: cached offset of region for manual register dumping
+ * @cnt: cached range of region for manual register dumping
+ * @max_offset: length of region
+ * @buf: buffer used for manual register dumping
+ * @buf_len:  buffer length used for manual register dumping
+ * @cb: callback for external dump function, null if not defined
+ * @cb_ptr: private pointer to callback function
+ */
+struct dpu_dbg_reg_base {
+	struct list_head reg_base_head;
+	char name[REG_BASE_NAME_LEN];
+	void __iomem *base;
+	size_t off;
+	size_t cnt;
+	size_t max_offset;
+	char *buf;
+	size_t buf_len;
+	void (*cb)(void *ptr);
+	void *cb_ptr;
+};
+
+struct dpu_debug_bus_entry {
+	u32 wr_addr;
+	u32 block_id;
+	u32 test_id;
+	void (*analyzer)(void __iomem *mem_base,
+				struct dpu_debug_bus_entry *entry, u32 val);
+};
+
+struct vbif_debug_bus_entry {
+	u32 disable_bus_addr;
+	u32 block_bus_addr;
+	u32 bit_offset;
+	u32 block_cnt;
+	u32 test_pnt_start;
+	u32 test_pnt_cnt;
+};
+
+struct dpu_dbg_debug_bus_common {
+	char *name;
+	u32 enable_mask;
+	bool include_in_deferred_work;
+	u32 flags;
+	u32 entries_size;
+	u32 *dumped_content;
+};
+
+struct dpu_dbg_dpu_debug_bus {
+	struct dpu_dbg_debug_bus_common cmn;
+	struct dpu_debug_bus_entry *entries;
+	u32 top_blk_off;
+};
+
+struct dpu_dbg_vbif_debug_bus {
+	struct dpu_dbg_debug_bus_common cmn;
+	struct vbif_debug_bus_entry *entries;
+};
+
+/**
+ * struct dpu_dbg_base - global dpu debug base structure
+ * @reg_base_list: list of register dumping regions
+ * @dev: device pointer
+ * @dump_work: work struct for deferring register dump work to separate thread
+ * @dbgbus_dpu: debug bus structure for the dpu
+ * @dbgbus_vbif_rt: debug bus structure for the realtime vbif
+ */
+static struct dpu_dbg_base {
+	struct list_head reg_base_list;
+	struct device *dev;
+
+	struct work_struct dump_work;
+
+	struct dpu_dbg_dpu_debug_bus dbgbus_dpu;
+	struct dpu_dbg_vbif_debug_bus dbgbus_vbif_rt;
+} dpu_dbg_base;
+
+static void _dpu_debug_bus_xbar_dump(void __iomem *mem_base,
+		struct dpu_debug_bus_entry *entry, u32 val)
+{
+	dev_err(dpu_dbg_base.dev, "xbar 0x%x %d %d 0x%x\n",
+			entry->wr_addr, entry->block_id, entry->test_id, val);
+}
+
+static void _dpu_debug_bus_lm_dump(void __iomem *mem_base,
+		struct dpu_debug_bus_entry *entry, u32 val)
+{
+	if (!(val & 0xFFF000))
+		return;
+
+	dev_err(dpu_dbg_base.dev, "lm 0x%x %d %d 0x%x\n",
+			entry->wr_addr, entry->block_id, entry->test_id, val);
+}
+
+static void _dpu_debug_bus_ppb0_dump(void __iomem *mem_base,
+		struct dpu_debug_bus_entry *entry, u32 val)
+{
+	if (!(val & BIT(15)))
+		return;
+
+	dev_err(dpu_dbg_base.dev, "ppb0 0x%x %d %d 0x%x\n",
+			entry->wr_addr, entry->block_id, entry->test_id, val);
+}
+
+static void _dpu_debug_bus_ppb1_dump(void __iomem *mem_base,
+		struct dpu_debug_bus_entry *entry, u32 val)
+{
+	if (!(val & BIT(15)))
+		return;
+
+	dev_err(dpu_dbg_base.dev, "ppb1 0x%x %d %d 0x%x\n",
+			entry->wr_addr, entry->block_id, entry->test_id, val);
+}
+
+static struct dpu_debug_bus_entry dbg_bus_dpu_8998[] = {
+
+	/* Unpack 0 sspp 0*/
+	{ DBGBUS_SSPP0, 50, 2 },
+	{ DBGBUS_SSPP0, 60, 2 },
+	{ DBGBUS_SSPP0, 70, 2 },
+	{ DBGBUS_SSPP0, 85, 2 },
+
+	/* Upack 0 sspp 1*/
+	{ DBGBUS_SSPP1, 50, 2 },
+	{ DBGBUS_SSPP1, 60, 2 },
+	{ DBGBUS_SSPP1, 70, 2 },
+	{ DBGBUS_SSPP1, 85, 2 },
+
+	/* scheduler */
+	{ DBGBUS_DSPP, 130, 0 },
+	{ DBGBUS_DSPP, 130, 1 },
+	{ DBGBUS_DSPP, 130, 2 },
+	{ DBGBUS_DSPP, 130, 3 },
+	{ DBGBUS_DSPP, 130, 4 },
+	{ DBGBUS_DSPP, 130, 5 },
+
+	/* qseed */
+	{ DBGBUS_SSPP0, 6, 0},
+	{ DBGBUS_SSPP0, 6, 1},
+	{ DBGBUS_SSPP0, 26, 0},
+	{ DBGBUS_SSPP0, 26, 1},
+	{ DBGBUS_SSPP1, 6, 0},
+	{ DBGBUS_SSPP1, 6, 1},
+	{ DBGBUS_SSPP1, 26, 0},
+	{ DBGBUS_SSPP1, 26, 1},
+
+	/* scale */
+	{ DBGBUS_SSPP0, 16, 0},
+	{ DBGBUS_SSPP0, 16, 1},
+	{ DBGBUS_SSPP0, 36, 0},
+	{ DBGBUS_SSPP0, 36, 1},
+	{ DBGBUS_SSPP1, 16, 0},
+	{ DBGBUS_SSPP1, 16, 1},
+	{ DBGBUS_SSPP1, 36, 0},
+	{ DBGBUS_SSPP1, 36, 1},
+
+	/* fetch sspp0 */
+
+	/* vig 0 */
+	{ DBGBUS_SSPP0, 0, 0 },
+	{ DBGBUS_SSPP0, 0, 1 },
+	{ DBGBUS_SSPP0, 0, 2 },
+	{ DBGBUS_SSPP0, 0, 3 },
+	{ DBGBUS_SSPP0, 0, 4 },
+	{ DBGBUS_SSPP0, 0, 5 },
+	{ DBGBUS_SSPP0, 0, 6 },
+	{ DBGBUS_SSPP0, 0, 7 },
+
+	{ DBGBUS_SSPP0, 1, 0 },
+	{ DBGBUS_SSPP0, 1, 1 },
+	{ DBGBUS_SSPP0, 1, 2 },
+	{ DBGBUS_SSPP0, 1, 3 },
+	{ DBGBUS_SSPP0, 1, 4 },
+	{ DBGBUS_SSPP0, 1, 5 },
+	{ DBGBUS_SSPP0, 1, 6 },
+	{ DBGBUS_SSPP0, 1, 7 },
+
+	{ DBGBUS_SSPP0, 2, 0 },
+	{ DBGBUS_SSPP0, 2, 1 },
+	{ DBGBUS_SSPP0, 2, 2 },
+	{ DBGBUS_SSPP0, 2, 3 },
+	{ DBGBUS_SSPP0, 2, 4 },
+	{ DBGBUS_SSPP0, 2, 5 },
+	{ DBGBUS_SSPP0, 2, 6 },
+	{ DBGBUS_SSPP0, 2, 7 },
+
+	{ DBGBUS_SSPP0, 4, 0 },
+	{ DBGBUS_SSPP0, 4, 1 },
+	{ DBGBUS_SSPP0, 4, 2 },
+	{ DBGBUS_SSPP0, 4, 3 },
+	{ DBGBUS_SSPP0, 4, 4 },
+	{ DBGBUS_SSPP0, 4, 5 },
+	{ DBGBUS_SSPP0, 4, 6 },
+	{ DBGBUS_SSPP0, 4, 7 },
+
+	{ DBGBUS_SSPP0, 5, 0 },
+	{ DBGBUS_SSPP0, 5, 1 },
+	{ DBGBUS_SSPP0, 5, 2 },
+	{ DBGBUS_SSPP0, 5, 3 },
+	{ DBGBUS_SSPP0, 5, 4 },
+	{ DBGBUS_SSPP0, 5, 5 },
+	{ DBGBUS_SSPP0, 5, 6 },
+	{ DBGBUS_SSPP0, 5, 7 },
+
+	/* vig 2 */
+	{ DBGBUS_SSPP0, 20, 0 },
+	{ DBGBUS_SSPP0, 20, 1 },
+	{ DBGBUS_SSPP0, 20, 2 },
+	{ DBGBUS_SSPP0, 20, 3 },
+	{ DBGBUS_SSPP0, 20, 4 },
+	{ DBGBUS_SSPP0, 20, 5 },
+	{ DBGBUS_SSPP0, 20, 6 },
+	{ DBGBUS_SSPP0, 20, 7 },
+
+	{ DBGBUS_SSPP0, 21, 0 },
+	{ DBGBUS_SSPP0, 21, 1 },
+	{ DBGBUS_SSPP0, 21, 2 },
+	{ DBGBUS_SSPP0, 21, 3 },
+	{ DBGBUS_SSPP0, 21, 4 },
+	{ DBGBUS_SSPP0, 21, 5 },
+	{ DBGBUS_SSPP0, 21, 6 },
+	{ DBGBUS_SSPP0, 21, 7 },
+
+	{ DBGBUS_SSPP0, 22, 0 },
+	{ DBGBUS_SSPP0, 22, 1 },
+	{ DBGBUS_SSPP0, 22, 2 },
+	{ DBGBUS_SSPP0, 22, 3 },
+	{ DBGBUS_SSPP0, 22, 4 },
+	{ DBGBUS_SSPP0, 22, 5 },
+	{ DBGBUS_SSPP0, 22, 6 },
+	{ DBGBUS_SSPP0, 22, 7 },
+
+	{ DBGBUS_SSPP0, 24, 0 },
+	{ DBGBUS_SSPP0, 24, 1 },
+	{ DBGBUS_SSPP0, 24, 2 },
+	{ DBGBUS_SSPP0, 24, 3 },
+	{ DBGBUS_SSPP0, 24, 4 },
+	{ DBGBUS_SSPP0, 24, 5 },
+	{ DBGBUS_SSPP0, 24, 6 },
+	{ DBGBUS_SSPP0, 24, 7 },
+
+	{ DBGBUS_SSPP0, 25, 0 },
+	{ DBGBUS_SSPP0, 25, 1 },
+	{ DBGBUS_SSPP0, 25, 2 },
+	{ DBGBUS_SSPP0, 25, 3 },
+	{ DBGBUS_SSPP0, 25, 4 },
+	{ DBGBUS_SSPP0, 25, 5 },
+	{ DBGBUS_SSPP0, 25, 6 },
+	{ DBGBUS_SSPP0, 25, 7 },
+
+	/* dma 2 */
+	{ DBGBUS_SSPP0, 30, 0 },
+	{ DBGBUS_SSPP0, 30, 1 },
+	{ DBGBUS_SSPP0, 30, 2 },
+	{ DBGBUS_SSPP0, 30, 3 },
+	{ DBGBUS_SSPP0, 30, 4 },
+	{ DBGBUS_SSPP0, 30, 5 },
+	{ DBGBUS_SSPP0, 30, 6 },
+	{ DBGBUS_SSPP0, 30, 7 },
+
+	{ DBGBUS_SSPP0, 31, 0 },
+	{ DBGBUS_SSPP0, 31, 1 },
+	{ DBGBUS_SSPP0, 31, 2 },
+	{ DBGBUS_SSPP0, 31, 3 },
+	{ DBGBUS_SSPP0, 31, 4 },
+	{ DBGBUS_SSPP0, 31, 5 },
+	{ DBGBUS_SSPP0, 31, 6 },
+	{ DBGBUS_SSPP0, 31, 7 },
+
+	{ DBGBUS_SSPP0, 32, 0 },
+	{ DBGBUS_SSPP0, 32, 1 },
+	{ DBGBUS_SSPP0, 32, 2 },
+	{ DBGBUS_SSPP0, 32, 3 },
+	{ DBGBUS_SSPP0, 32, 4 },
+	{ DBGBUS_SSPP0, 32, 5 },
+	{ DBGBUS_SSPP0, 32, 6 },
+	{ DBGBUS_SSPP0, 32, 7 },
+
+	{ DBGBUS_SSPP0, 33, 0 },
+	{ DBGBUS_SSPP0, 33, 1 },
+	{ DBGBUS_SSPP0, 33, 2 },
+	{ DBGBUS_SSPP0, 33, 3 },
+	{ DBGBUS_SSPP0, 33, 4 },
+	{ DBGBUS_SSPP0, 33, 5 },
+	{ DBGBUS_SSPP0, 33, 6 },
+	{ DBGBUS_SSPP0, 33, 7 },
+
+	{ DBGBUS_SSPP0, 34, 0 },
+	{ DBGBUS_SSPP0, 34, 1 },
+	{ DBGBUS_SSPP0, 34, 2 },
+	{ DBGBUS_SSPP0, 34, 3 },
+	{ DBGBUS_SSPP0, 34, 4 },
+	{ DBGBUS_SSPP0, 34, 5 },
+	{ DBGBUS_SSPP0, 34, 6 },
+	{ DBGBUS_SSPP0, 34, 7 },
+
+	{ DBGBUS_SSPP0, 35, 0 },
+	{ DBGBUS_SSPP0, 35, 1 },
+	{ DBGBUS_SSPP0, 35, 2 },
+	{ DBGBUS_SSPP0, 35, 3 },
+
+	/* dma 0 */
+	{ DBGBUS_SSPP0, 40, 0 },
+	{ DBGBUS_SSPP0, 40, 1 },
+	{ DBGBUS_SSPP0, 40, 2 },
+	{ DBGBUS_SSPP0, 40, 3 },
+	{ DBGBUS_SSPP0, 40, 4 },
+	{ DBGBUS_SSPP0, 40, 5 },
+	{ DBGBUS_SSPP0, 40, 6 },
+	{ DBGBUS_SSPP0, 40, 7 },
+
+	{ DBGBUS_SSPP0, 41, 0 },
+	{ DBGBUS_SSPP0, 41, 1 },
+	{ DBGBUS_SSPP0, 41, 2 },
+	{ DBGBUS_SSPP0, 41, 3 },
+	{ DBGBUS_SSPP0, 41, 4 },
+	{ DBGBUS_SSPP0, 41, 5 },
+	{ DBGBUS_SSPP0, 41, 6 },
+	{ DBGBUS_SSPP0, 41, 7 },
+
+	{ DBGBUS_SSPP0, 42, 0 },
+	{ DBGBUS_SSPP0, 42, 1 },
+	{ DBGBUS_SSPP0, 42, 2 },
+	{ DBGBUS_SSPP0, 42, 3 },
+	{ DBGBUS_SSPP0, 42, 4 },
+	{ DBGBUS_SSPP0, 42, 5 },
+	{ DBGBUS_SSPP0, 42, 6 },
+	{ DBGBUS_SSPP0, 42, 7 },
+
+	{ DBGBUS_SSPP0, 44, 0 },
+	{ DBGBUS_SSPP0, 44, 1 },
+	{ DBGBUS_SSPP0, 44, 2 },
+	{ DBGBUS_SSPP0, 44, 3 },
+	{ DBGBUS_SSPP0, 44, 4 },
+	{ DBGBUS_SSPP0, 44, 5 },
+	{ DBGBUS_SSPP0, 44, 6 },
+	{ DBGBUS_SSPP0, 44, 7 },
+
+	{ DBGBUS_SSPP0, 45, 0 },
+	{ DBGBUS_SSPP0, 45, 1 },
+	{ DBGBUS_SSPP0, 45, 2 },
+	{ DBGBUS_SSPP0, 45, 3 },
+	{ DBGBUS_SSPP0, 45, 4 },
+	{ DBGBUS_SSPP0, 45, 5 },
+	{ DBGBUS_SSPP0, 45, 6 },
+	{ DBGBUS_SSPP0, 45, 7 },
+
+	/* fetch sspp1 */
+	/* vig 1 */
+	{ DBGBUS_SSPP1, 0, 0 },
+	{ DBGBUS_SSPP1, 0, 1 },
+	{ DBGBUS_SSPP1, 0, 2 },
+	{ DBGBUS_SSPP1, 0, 3 },
+	{ DBGBUS_SSPP1, 0, 4 },
+	{ DBGBUS_SSPP1, 0, 5 },
+	{ DBGBUS_SSPP1, 0, 6 },
+	{ DBGBUS_SSPP1, 0, 7 },
+
+	{ DBGBUS_SSPP1, 1, 0 },
+	{ DBGBUS_SSPP1, 1, 1 },
+	{ DBGBUS_SSPP1, 1, 2 },
+	{ DBGBUS_SSPP1, 1, 3 },
+	{ DBGBUS_SSPP1, 1, 4 },
+	{ DBGBUS_SSPP1, 1, 5 },
+	{ DBGBUS_SSPP1, 1, 6 },
+	{ DBGBUS_SSPP1, 1, 7 },
+
+	{ DBGBUS_SSPP1, 2, 0 },
+	{ DBGBUS_SSPP1, 2, 1 },
+	{ DBGBUS_SSPP1, 2, 2 },
+	{ DBGBUS_SSPP1, 2, 3 },
+	{ DBGBUS_SSPP1, 2, 4 },
+	{ DBGBUS_SSPP1, 2, 5 },
+	{ DBGBUS_SSPP1, 2, 6 },
+	{ DBGBUS_SSPP1, 2, 7 },
+
+	{ DBGBUS_SSPP1, 4, 0 },
+	{ DBGBUS_SSPP1, 4, 1 },
+	{ DBGBUS_SSPP1, 4, 2 },
+	{ DBGBUS_SSPP1, 4, 3 },
+	{ DBGBUS_SSPP1, 4, 4 },
+	{ DBGBUS_SSPP1, 4, 5 },
+	{ DBGBUS_SSPP1, 4, 6 },
+	{ DBGBUS_SSPP1, 4, 7 },
+
+	{ DBGBUS_SSPP1, 5, 0 },
+	{ DBGBUS_SSPP1, 5, 1 },
+	{ DBGBUS_SSPP1, 5, 2 },
+	{ DBGBUS_SSPP1, 5, 3 },
+	{ DBGBUS_SSPP1, 5, 4 },
+	{ DBGBUS_SSPP1, 5, 5 },
+	{ DBGBUS_SSPP1, 5, 6 },
+	{ DBGBUS_SSPP1, 5, 7 },
+
+	/* vig 3 */
+	{ DBGBUS_SSPP1, 20, 0 },
+	{ DBGBUS_SSPP1, 20, 1 },
+	{ DBGBUS_SSPP1, 20, 2 },
+	{ DBGBUS_SSPP1, 20, 3 },
+	{ DBGBUS_SSPP1, 20, 4 },
+	{ DBGBUS_SSPP1, 20, 5 },
+	{ DBGBUS_SSPP1, 20, 6 },
+	{ DBGBUS_SSPP1, 20, 7 },
+
+	{ DBGBUS_SSPP1, 21, 0 },
+	{ DBGBUS_SSPP1, 21, 1 },
+	{ DBGBUS_SSPP1, 21, 2 },
+	{ DBGBUS_SSPP1, 21, 3 },
+	{ DBGBUS_SSPP1, 21, 4 },
+	{ DBGBUS_SSPP1, 21, 5 },
+	{ DBGBUS_SSPP1, 21, 6 },
+	{ DBGBUS_SSPP1, 21, 7 },
+
+	{ DBGBUS_SSPP1, 22, 0 },
+	{ DBGBUS_SSPP1, 22, 1 },
+	{ DBGBUS_SSPP1, 22, 2 },
+	{ DBGBUS_SSPP1, 22, 3 },
+	{ DBGBUS_SSPP1, 22, 4 },
+	{ DBGBUS_SSPP1, 22, 5 },
+	{ DBGBUS_SSPP1, 22, 6 },
+	{ DBGBUS_SSPP1, 22, 7 },
+
+	{ DBGBUS_SSPP1, 24, 0 },
+	{ DBGBUS_SSPP1, 24, 1 },
+	{ DBGBUS_SSPP1, 24, 2 },
+	{ DBGBUS_SSPP1, 24, 3 },
+	{ DBGBUS_SSPP1, 24, 4 },
+	{ DBGBUS_SSPP1, 24, 5 },
+	{ DBGBUS_SSPP1, 24, 6 },
+	{ DBGBUS_SSPP1, 24, 7 },
+
+	{ DBGBUS_SSPP1, 25, 0 },
+	{ DBGBUS_SSPP1, 25, 1 },
+	{ DBGBUS_SSPP1, 25, 2 },
+	{ DBGBUS_SSPP1, 25, 3 },
+	{ DBGBUS_SSPP1, 25, 4 },
+	{ DBGBUS_SSPP1, 25, 5 },
+	{ DBGBUS_SSPP1, 25, 6 },
+	{ DBGBUS_SSPP1, 25, 7 },
+
+	/* dma 3 */
+	{ DBGBUS_SSPP1, 30, 0 },
+	{ DBGBUS_SSPP1, 30, 1 },
+	{ DBGBUS_SSPP1, 30, 2 },
+	{ DBGBUS_SSPP1, 30, 3 },
+	{ DBGBUS_SSPP1, 30, 4 },
+	{ DBGBUS_SSPP1, 30, 5 },
+	{ DBGBUS_SSPP1, 30, 6 },
+	{ DBGBUS_SSPP1, 30, 7 },
+
+	{ DBGBUS_SSPP1, 31, 0 },
+	{ DBGBUS_SSPP1, 31, 1 },
+	{ DBGBUS_SSPP1, 31, 2 },
+	{ DBGBUS_SSPP1, 31, 3 },
+	{ DBGBUS_SSPP1, 31, 4 },
+	{ DBGBUS_SSPP1, 31, 5 },
+	{ DBGBUS_SSPP1, 31, 6 },
+	{ DBGBUS_SSPP1, 31, 7 },
+
+	{ DBGBUS_SSPP1, 32, 0 },
+	{ DBGBUS_SSPP1, 32, 1 },
+	{ DBGBUS_SSPP1, 32, 2 },
+	{ DBGBUS_SSPP1, 32, 3 },
+	{ DBGBUS_SSPP1, 32, 4 },
+	{ DBGBUS_SSPP1, 32, 5 },
+	{ DBGBUS_SSPP1, 32, 6 },
+	{ DBGBUS_SSPP1, 32, 7 },
+
+	{ DBGBUS_SSPP1, 33, 0 },
+	{ DBGBUS_SSPP1, 33, 1 },
+	{ DBGBUS_SSPP1, 33, 2 },
+	{ DBGBUS_SSPP1, 33, 3 },
+	{ DBGBUS_SSPP1, 33, 4 },
+	{ DBGBUS_SSPP1, 33, 5 },
+	{ DBGBUS_SSPP1, 33, 6 },
+	{ DBGBUS_SSPP1, 33, 7 },
+
+	{ DBGBUS_SSPP1, 34, 0 },
+	{ DBGBUS_SSPP1, 34, 1 },
+	{ DBGBUS_SSPP1, 34, 2 },
+	{ DBGBUS_SSPP1, 34, 3 },
+	{ DBGBUS_SSPP1, 34, 4 },
+	{ DBGBUS_SSPP1, 34, 5 },
+	{ DBGBUS_SSPP1, 34, 6 },
+	{ DBGBUS_SSPP1, 34, 7 },
+
+	{ DBGBUS_SSPP1, 35, 0 },
+	{ DBGBUS_SSPP1, 35, 1 },
+	{ DBGBUS_SSPP1, 35, 2 },
+
+	/* dma 1 */
+	{ DBGBUS_SSPP1, 40, 0 },
+	{ DBGBUS_SSPP1, 40, 1 },
+	{ DBGBUS_SSPP1, 40, 2 },
+	{ DBGBUS_SSPP1, 40, 3 },
+	{ DBGBUS_SSPP1, 40, 4 },
+	{ DBGBUS_SSPP1, 40, 5 },
+	{ DBGBUS_SSPP1, 40, 6 },
+	{ DBGBUS_SSPP1, 40, 7 },
+
+	{ DBGBUS_SSPP1, 41, 0 },
+	{ DBGBUS_SSPP1, 41, 1 },
+	{ DBGBUS_SSPP1, 41, 2 },
+	{ DBGBUS_SSPP1, 41, 3 },
+	{ DBGBUS_SSPP1, 41, 4 },
+	{ DBGBUS_SSPP1, 41, 5 },
+	{ DBGBUS_SSPP1, 41, 6 },
+	{ DBGBUS_SSPP1, 41, 7 },
+
+	{ DBGBUS_SSPP1, 42, 0 },
+	{ DBGBUS_SSPP1, 42, 1 },
+	{ DBGBUS_SSPP1, 42, 2 },
+	{ DBGBUS_SSPP1, 42, 3 },
+	{ DBGBUS_SSPP1, 42, 4 },
+	{ DBGBUS_SSPP1, 42, 5 },
+	{ DBGBUS_SSPP1, 42, 6 },
+	{ DBGBUS_SSPP1, 42, 7 },
+
+	{ DBGBUS_SSPP1, 44, 0 },
+	{ DBGBUS_SSPP1, 44, 1 },
+	{ DBGBUS_SSPP1, 44, 2 },
+	{ DBGBUS_SSPP1, 44, 3 },
+	{ DBGBUS_SSPP1, 44, 4 },
+	{ DBGBUS_SSPP1, 44, 5 },
+	{ DBGBUS_SSPP1, 44, 6 },
+	{ DBGBUS_SSPP1, 44, 7 },
+
+	{ DBGBUS_SSPP1, 45, 0 },
+	{ DBGBUS_SSPP1, 45, 1 },
+	{ DBGBUS_SSPP1, 45, 2 },
+	{ DBGBUS_SSPP1, 45, 3 },
+	{ DBGBUS_SSPP1, 45, 4 },
+	{ DBGBUS_SSPP1, 45, 5 },
+	{ DBGBUS_SSPP1, 45, 6 },
+	{ DBGBUS_SSPP1, 45, 7 },
+
+	/* cursor 1 */
+	{ DBGBUS_SSPP1, 80, 0 },
+	{ DBGBUS_SSPP1, 80, 1 },
+	{ DBGBUS_SSPP1, 80, 2 },
+	{ DBGBUS_SSPP1, 80, 3 },
+	{ DBGBUS_SSPP1, 80, 4 },
+	{ DBGBUS_SSPP1, 80, 5 },
+	{ DBGBUS_SSPP1, 80, 6 },
+	{ DBGBUS_SSPP1, 80, 7 },
+
+	{ DBGBUS_SSPP1, 81, 0 },
+	{ DBGBUS_SSPP1, 81, 1 },
+	{ DBGBUS_SSPP1, 81, 2 },
+	{ DBGBUS_SSPP1, 81, 3 },
+	{ DBGBUS_SSPP1, 81, 4 },
+	{ DBGBUS_SSPP1, 81, 5 },
+	{ DBGBUS_SSPP1, 81, 6 },
+	{ DBGBUS_SSPP1, 81, 7 },
+
+	{ DBGBUS_SSPP1, 82, 0 },
+	{ DBGBUS_SSPP1, 82, 1 },
+	{ DBGBUS_SSPP1, 82, 2 },
+	{ DBGBUS_SSPP1, 82, 3 },
+	{ DBGBUS_SSPP1, 82, 4 },
+	{ DBGBUS_SSPP1, 82, 5 },
+	{ DBGBUS_SSPP1, 82, 6 },
+	{ DBGBUS_SSPP1, 82, 7 },
+
+	{ DBGBUS_SSPP1, 83, 0 },
+	{ DBGBUS_SSPP1, 83, 1 },
+	{ DBGBUS_SSPP1, 83, 2 },
+	{ DBGBUS_SSPP1, 83, 3 },
+	{ DBGBUS_SSPP1, 83, 4 },
+	{ DBGBUS_SSPP1, 83, 5 },
+	{ DBGBUS_SSPP1, 83, 6 },
+	{ DBGBUS_SSPP1, 83, 7 },
+
+	{ DBGBUS_SSPP1, 84, 0 },
+	{ DBGBUS_SSPP1, 84, 1 },
+	{ DBGBUS_SSPP1, 84, 2 },
+	{ DBGBUS_SSPP1, 84, 3 },
+	{ DBGBUS_SSPP1, 84, 4 },
+	{ DBGBUS_SSPP1, 84, 5 },
+	{ DBGBUS_SSPP1, 84, 6 },
+	{ DBGBUS_SSPP1, 84, 7 },
+
+	/* dspp */
+	{ DBGBUS_DSPP, 13, 0 },
+	{ DBGBUS_DSPP, 19, 0 },
+	{ DBGBUS_DSPP, 14, 0 },
+	{ DBGBUS_DSPP, 14, 1 },
+	{ DBGBUS_DSPP, 14, 3 },
+	{ DBGBUS_DSPP, 20, 0 },
+	{ DBGBUS_DSPP, 20, 1 },
+	{ DBGBUS_DSPP, 20, 3 },
+
+	/* ppb_0 */
+	{ DBGBUS_DSPP, 31, 0, _dpu_debug_bus_ppb0_dump },
+	{ DBGBUS_DSPP, 33, 0, _dpu_debug_bus_ppb0_dump },
+	{ DBGBUS_DSPP, 35, 0, _dpu_debug_bus_ppb0_dump },
+	{ DBGBUS_DSPP, 42, 0, _dpu_debug_bus_ppb0_dump },
+
+	/* ppb_1 */
+	{ DBGBUS_DSPP, 32, 0, _dpu_debug_bus_ppb1_dump },
+	{ DBGBUS_DSPP, 34, 0, _dpu_debug_bus_ppb1_dump },
+	{ DBGBUS_DSPP, 36, 0, _dpu_debug_bus_ppb1_dump },
+	{ DBGBUS_DSPP, 43, 0, _dpu_debug_bus_ppb1_dump },
+
+	/* lm_lut */
+	{ DBGBUS_DSPP, 109, 0 },
+	{ DBGBUS_DSPP, 105, 0 },
+	{ DBGBUS_DSPP, 103, 0 },
+
+	/* tear-check */
+	{ DBGBUS_PERIPH, 63, 0 },
+	{ DBGBUS_PERIPH, 64, 0 },
+	{ DBGBUS_PERIPH, 65, 0 },
+	{ DBGBUS_PERIPH, 73, 0 },
+	{ DBGBUS_PERIPH, 74, 0 },
+
+	/* crossbar */
+	{ DBGBUS_DSPP, 0, 0, _dpu_debug_bus_xbar_dump },
+
+	/* rotator */
+	{ DBGBUS_DSPP, 9, 0},
+
+	/* blend */
+	/* LM0 */
+	{ DBGBUS_DSPP, 63, 0},
+	{ DBGBUS_DSPP, 63, 1},
+	{ DBGBUS_DSPP, 63, 2},
+	{ DBGBUS_DSPP, 63, 3},
+	{ DBGBUS_DSPP, 63, 4},
+	{ DBGBUS_DSPP, 63, 5},
+	{ DBGBUS_DSPP, 63, 6},
+	{ DBGBUS_DSPP, 63, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 64, 0},
+	{ DBGBUS_DSPP, 64, 1},
+	{ DBGBUS_DSPP, 64, 2},
+	{ DBGBUS_DSPP, 64, 3},
+	{ DBGBUS_DSPP, 64, 4},
+	{ DBGBUS_DSPP, 64, 5},
+	{ DBGBUS_DSPP, 64, 6},
+	{ DBGBUS_DSPP, 64, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 65, 0},
+	{ DBGBUS_DSPP, 65, 1},
+	{ DBGBUS_DSPP, 65, 2},
+	{ DBGBUS_DSPP, 65, 3},
+	{ DBGBUS_DSPP, 65, 4},
+	{ DBGBUS_DSPP, 65, 5},
+	{ DBGBUS_DSPP, 65, 6},
+	{ DBGBUS_DSPP, 65, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 66, 0},
+	{ DBGBUS_DSPP, 66, 1},
+	{ DBGBUS_DSPP, 66, 2},
+	{ DBGBUS_DSPP, 66, 3},
+	{ DBGBUS_DSPP, 66, 4},
+	{ DBGBUS_DSPP, 66, 5},
+	{ DBGBUS_DSPP, 66, 6},
+	{ DBGBUS_DSPP, 66, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 67, 0},
+	{ DBGBUS_DSPP, 67, 1},
+	{ DBGBUS_DSPP, 67, 2},
+	{ DBGBUS_DSPP, 67, 3},
+	{ DBGBUS_DSPP, 67, 4},
+	{ DBGBUS_DSPP, 67, 5},
+	{ DBGBUS_DSPP, 67, 6},
+	{ DBGBUS_DSPP, 67, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 68, 0},
+	{ DBGBUS_DSPP, 68, 1},
+	{ DBGBUS_DSPP, 68, 2},
+	{ DBGBUS_DSPP, 68, 3},
+	{ DBGBUS_DSPP, 68, 4},
+	{ DBGBUS_DSPP, 68, 5},
+	{ DBGBUS_DSPP, 68, 6},
+	{ DBGBUS_DSPP, 68, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 69, 0},
+	{ DBGBUS_DSPP, 69, 1},
+	{ DBGBUS_DSPP, 69, 2},
+	{ DBGBUS_DSPP, 69, 3},
+	{ DBGBUS_DSPP, 69, 4},
+	{ DBGBUS_DSPP, 69, 5},
+	{ DBGBUS_DSPP, 69, 6},
+	{ DBGBUS_DSPP, 69, 7, _dpu_debug_bus_lm_dump },
+
+	/* LM1 */
+	{ DBGBUS_DSPP, 70, 0},
+	{ DBGBUS_DSPP, 70, 1},
+	{ DBGBUS_DSPP, 70, 2},
+	{ DBGBUS_DSPP, 70, 3},
+	{ DBGBUS_DSPP, 70, 4},
+	{ DBGBUS_DSPP, 70, 5},
+	{ DBGBUS_DSPP, 70, 6},
+	{ DBGBUS_DSPP, 70, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 71, 0},
+	{ DBGBUS_DSPP, 71, 1},
+	{ DBGBUS_DSPP, 71, 2},
+	{ DBGBUS_DSPP, 71, 3},
+	{ DBGBUS_DSPP, 71, 4},
+	{ DBGBUS_DSPP, 71, 5},
+	{ DBGBUS_DSPP, 71, 6},
+	{ DBGBUS_DSPP, 71, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 72, 0},
+	{ DBGBUS_DSPP, 72, 1},
+	{ DBGBUS_DSPP, 72, 2},
+	{ DBGBUS_DSPP, 72, 3},
+	{ DBGBUS_DSPP, 72, 4},
+	{ DBGBUS_DSPP, 72, 5},
+	{ DBGBUS_DSPP, 72, 6},
+	{ DBGBUS_DSPP, 72, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 73, 0},
+	{ DBGBUS_DSPP, 73, 1},
+	{ DBGBUS_DSPP, 73, 2},
+	{ DBGBUS_DSPP, 73, 3},
+	{ DBGBUS_DSPP, 73, 4},
+	{ DBGBUS_DSPP, 73, 5},
+	{ DBGBUS_DSPP, 73, 6},
+	{ DBGBUS_DSPP, 73, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 74, 0},
+	{ DBGBUS_DSPP, 74, 1},
+	{ DBGBUS_DSPP, 74, 2},
+	{ DBGBUS_DSPP, 74, 3},
+	{ DBGBUS_DSPP, 74, 4},
+	{ DBGBUS_DSPP, 74, 5},
+	{ DBGBUS_DSPP, 74, 6},
+	{ DBGBUS_DSPP, 74, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 75, 0},
+	{ DBGBUS_DSPP, 75, 1},
+	{ DBGBUS_DSPP, 75, 2},
+	{ DBGBUS_DSPP, 75, 3},
+	{ DBGBUS_DSPP, 75, 4},
+	{ DBGBUS_DSPP, 75, 5},
+	{ DBGBUS_DSPP, 75, 6},
+	{ DBGBUS_DSPP, 75, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 76, 0},
+	{ DBGBUS_DSPP, 76, 1},
+	{ DBGBUS_DSPP, 76, 2},
+	{ DBGBUS_DSPP, 76, 3},
+	{ DBGBUS_DSPP, 76, 4},
+	{ DBGBUS_DSPP, 76, 5},
+	{ DBGBUS_DSPP, 76, 6},
+	{ DBGBUS_DSPP, 76, 7, _dpu_debug_bus_lm_dump },
+
+	/* LM2 */
+	{ DBGBUS_DSPP, 77, 0},
+	{ DBGBUS_DSPP, 77, 1},
+	{ DBGBUS_DSPP, 77, 2},
+	{ DBGBUS_DSPP, 77, 3},
+	{ DBGBUS_DSPP, 77, 4},
+	{ DBGBUS_DSPP, 77, 5},
+	{ DBGBUS_DSPP, 77, 6},
+	{ DBGBUS_DSPP, 77, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 78, 0},
+	{ DBGBUS_DSPP, 78, 1},
+	{ DBGBUS_DSPP, 78, 2},
+	{ DBGBUS_DSPP, 78, 3},
+	{ DBGBUS_DSPP, 78, 4},
+	{ DBGBUS_DSPP, 78, 5},
+	{ DBGBUS_DSPP, 78, 6},
+	{ DBGBUS_DSPP, 78, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 79, 0},
+	{ DBGBUS_DSPP, 79, 1},
+	{ DBGBUS_DSPP, 79, 2},
+	{ DBGBUS_DSPP, 79, 3},
+	{ DBGBUS_DSPP, 79, 4},
+	{ DBGBUS_DSPP, 79, 5},
+	{ DBGBUS_DSPP, 79, 6},
+	{ DBGBUS_DSPP, 79, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 80, 0},
+	{ DBGBUS_DSPP, 80, 1},
+	{ DBGBUS_DSPP, 80, 2},
+	{ DBGBUS_DSPP, 80, 3},
+	{ DBGBUS_DSPP, 80, 4},
+	{ DBGBUS_DSPP, 80, 5},
+	{ DBGBUS_DSPP, 80, 6},
+	{ DBGBUS_DSPP, 80, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 81, 0},
+	{ DBGBUS_DSPP, 81, 1},
+	{ DBGBUS_DSPP, 81, 2},
+	{ DBGBUS_DSPP, 81, 3},
+	{ DBGBUS_DSPP, 81, 4},
+	{ DBGBUS_DSPP, 81, 5},
+	{ DBGBUS_DSPP, 81, 6},
+	{ DBGBUS_DSPP, 81, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 82, 0},
+	{ DBGBUS_DSPP, 82, 1},
+	{ DBGBUS_DSPP, 82, 2},
+	{ DBGBUS_DSPP, 82, 3},
+	{ DBGBUS_DSPP, 82, 4},
+	{ DBGBUS_DSPP, 82, 5},
+	{ DBGBUS_DSPP, 82, 6},
+	{ DBGBUS_DSPP, 82, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 83, 0},
+	{ DBGBUS_DSPP, 83, 1},
+	{ DBGBUS_DSPP, 83, 2},
+	{ DBGBUS_DSPP, 83, 3},
+	{ DBGBUS_DSPP, 83, 4},
+	{ DBGBUS_DSPP, 83, 5},
+	{ DBGBUS_DSPP, 83, 6},
+	{ DBGBUS_DSPP, 83, 7, _dpu_debug_bus_lm_dump },
+
+	/* csc */
+	{ DBGBUS_SSPP0, 7, 0},
+	{ DBGBUS_SSPP0, 7, 1},
+	{ DBGBUS_SSPP0, 27, 0},
+	{ DBGBUS_SSPP0, 27, 1},
+	{ DBGBUS_SSPP1, 7, 0},
+	{ DBGBUS_SSPP1, 7, 1},
+	{ DBGBUS_SSPP1, 27, 0},
+	{ DBGBUS_SSPP1, 27, 1},
+
+	/* pcc */
+	{ DBGBUS_SSPP0, 3,  3},
+	{ DBGBUS_SSPP0, 23, 3},
+	{ DBGBUS_SSPP0, 33, 3},
+	{ DBGBUS_SSPP0, 43, 3},
+	{ DBGBUS_SSPP1, 3,  3},
+	{ DBGBUS_SSPP1, 23, 3},
+	{ DBGBUS_SSPP1, 33, 3},
+	{ DBGBUS_SSPP1, 43, 3},
+
+	/* spa */
+	{ DBGBUS_SSPP0, 8,  0},
+	{ DBGBUS_SSPP0, 28, 0},
+	{ DBGBUS_SSPP1, 8,  0},
+	{ DBGBUS_SSPP1, 28, 0},
+	{ DBGBUS_DSPP, 13, 0},
+	{ DBGBUS_DSPP, 19, 0},
+
+	/* igc */
+	{ DBGBUS_SSPP0, 9,  0},
+	{ DBGBUS_SSPP0, 9,  1},
+	{ DBGBUS_SSPP0, 9,  3},
+	{ DBGBUS_SSPP0, 29, 0},
+	{ DBGBUS_SSPP0, 29, 1},
+	{ DBGBUS_SSPP0, 29, 3},
+	{ DBGBUS_SSPP0, 17, 0},
+	{ DBGBUS_SSPP0, 17, 1},
+	{ DBGBUS_SSPP0, 17, 3},
+	{ DBGBUS_SSPP0, 37, 0},
+	{ DBGBUS_SSPP0, 37, 1},
+	{ DBGBUS_SSPP0, 37, 3},
+	{ DBGBUS_SSPP0, 46, 0},
+	{ DBGBUS_SSPP0, 46, 1},
+	{ DBGBUS_SSPP0, 46, 3},
+
+	{ DBGBUS_SSPP1, 9,  0},
+	{ DBGBUS_SSPP1, 9,  1},
+	{ DBGBUS_SSPP1, 9,  3},
+	{ DBGBUS_SSPP1, 29, 0},
+	{ DBGBUS_SSPP1, 29, 1},
+	{ DBGBUS_SSPP1, 29, 3},
+	{ DBGBUS_SSPP1, 17, 0},
+	{ DBGBUS_SSPP1, 17, 1},
+	{ DBGBUS_SSPP1, 17, 3},
+	{ DBGBUS_SSPP1, 37, 0},
+	{ DBGBUS_SSPP1, 37, 1},
+	{ DBGBUS_SSPP1, 37, 3},
+	{ DBGBUS_SSPP1, 46, 0},
+	{ DBGBUS_SSPP1, 46, 1},
+	{ DBGBUS_SSPP1, 46, 3},
+
+	{ DBGBUS_DSPP, 14, 0},
+	{ DBGBUS_DSPP, 14, 1},
+	{ DBGBUS_DSPP, 14, 3},
+	{ DBGBUS_DSPP, 20, 0},
+	{ DBGBUS_DSPP, 20, 1},
+	{ DBGBUS_DSPP, 20, 3},
+
+	{ DBGBUS_PERIPH, 60, 0},
+};
+
+static struct dpu_debug_bus_entry dbg_bus_dpu_sdm845[] = {
+
+	/* Unpack 0 sspp 0*/
+	{ DBGBUS_SSPP0, 50, 2 },
+	{ DBGBUS_SSPP0, 60, 2 },
+	{ DBGBUS_SSPP0, 70, 2 },
+
+	/* Upack 0 sspp 1*/
+	{ DBGBUS_SSPP1, 50, 2 },
+	{ DBGBUS_SSPP1, 60, 2 },
+	{ DBGBUS_SSPP1, 70, 2 },
+
+	/* scheduler */
+	{ DBGBUS_DSPP, 130, 0 },
+	{ DBGBUS_DSPP, 130, 1 },
+	{ DBGBUS_DSPP, 130, 2 },
+	{ DBGBUS_DSPP, 130, 3 },
+	{ DBGBUS_DSPP, 130, 4 },
+	{ DBGBUS_DSPP, 130, 5 },
+
+	/* qseed */
+	{ DBGBUS_SSPP0, 6, 0},
+	{ DBGBUS_SSPP0, 6, 1},
+	{ DBGBUS_SSPP0, 26, 0},
+	{ DBGBUS_SSPP0, 26, 1},
+	{ DBGBUS_SSPP1, 6, 0},
+	{ DBGBUS_SSPP1, 6, 1},
+	{ DBGBUS_SSPP1, 26, 0},
+	{ DBGBUS_SSPP1, 26, 1},
+
+	/* scale */
+	{ DBGBUS_SSPP0, 16, 0},
+	{ DBGBUS_SSPP0, 16, 1},
+	{ DBGBUS_SSPP0, 36, 0},
+	{ DBGBUS_SSPP0, 36, 1},
+	{ DBGBUS_SSPP1, 16, 0},
+	{ DBGBUS_SSPP1, 16, 1},
+	{ DBGBUS_SSPP1, 36, 0},
+	{ DBGBUS_SSPP1, 36, 1},
+
+	/* fetch sspp0 */
+
+	/* vig 0 */
+	{ DBGBUS_SSPP0, 0, 0 },
+	{ DBGBUS_SSPP0, 0, 1 },
+	{ DBGBUS_SSPP0, 0, 2 },
+	{ DBGBUS_SSPP0, 0, 3 },
+	{ DBGBUS_SSPP0, 0, 4 },
+	{ DBGBUS_SSPP0, 0, 5 },
+	{ DBGBUS_SSPP0, 0, 6 },
+	{ DBGBUS_SSPP0, 0, 7 },
+
+	{ DBGBUS_SSPP0, 1, 0 },
+	{ DBGBUS_SSPP0, 1, 1 },
+	{ DBGBUS_SSPP0, 1, 2 },
+	{ DBGBUS_SSPP0, 1, 3 },
+	{ DBGBUS_SSPP0, 1, 4 },
+	{ DBGBUS_SSPP0, 1, 5 },
+	{ DBGBUS_SSPP0, 1, 6 },
+	{ DBGBUS_SSPP0, 1, 7 },
+
+	{ DBGBUS_SSPP0, 2, 0 },
+	{ DBGBUS_SSPP0, 2, 1 },
+	{ DBGBUS_SSPP0, 2, 2 },
+	{ DBGBUS_SSPP0, 2, 3 },
+	{ DBGBUS_SSPP0, 2, 4 },
+	{ DBGBUS_SSPP0, 2, 5 },
+	{ DBGBUS_SSPP0, 2, 6 },
+	{ DBGBUS_SSPP0, 2, 7 },
+
+	{ DBGBUS_SSPP0, 4, 0 },
+	{ DBGBUS_SSPP0, 4, 1 },
+	{ DBGBUS_SSPP0, 4, 2 },
+	{ DBGBUS_SSPP0, 4, 3 },
+	{ DBGBUS_SSPP0, 4, 4 },
+	{ DBGBUS_SSPP0, 4, 5 },
+	{ DBGBUS_SSPP0, 4, 6 },
+	{ DBGBUS_SSPP0, 4, 7 },
+
+	{ DBGBUS_SSPP0, 5, 0 },
+	{ DBGBUS_SSPP0, 5, 1 },
+	{ DBGBUS_SSPP0, 5, 2 },
+	{ DBGBUS_SSPP0, 5, 3 },
+	{ DBGBUS_SSPP0, 5, 4 },
+	{ DBGBUS_SSPP0, 5, 5 },
+	{ DBGBUS_SSPP0, 5, 6 },
+	{ DBGBUS_SSPP0, 5, 7 },
+
+	/* vig 2 */
+	{ DBGBUS_SSPP0, 20, 0 },
+	{ DBGBUS_SSPP0, 20, 1 },
+	{ DBGBUS_SSPP0, 20, 2 },
+	{ DBGBUS_SSPP0, 20, 3 },
+	{ DBGBUS_SSPP0, 20, 4 },
+	{ DBGBUS_SSPP0, 20, 5 },
+	{ DBGBUS_SSPP0, 20, 6 },
+	{ DBGBUS_SSPP0, 20, 7 },
+
+	{ DBGBUS_SSPP0, 21, 0 },
+	{ DBGBUS_SSPP0, 21, 1 },
+	{ DBGBUS_SSPP0, 21, 2 },
+	{ DBGBUS_SSPP0, 21, 3 },
+	{ DBGBUS_SSPP0, 21, 4 },
+	{ DBGBUS_SSPP0, 21, 5 },
+	{ DBGBUS_SSPP0, 21, 6 },
+	{ DBGBUS_SSPP0, 21, 7 },
+
+	{ DBGBUS_SSPP0, 22, 0 },
+	{ DBGBUS_SSPP0, 22, 1 },
+	{ DBGBUS_SSPP0, 22, 2 },
+	{ DBGBUS_SSPP0, 22, 3 },
+	{ DBGBUS_SSPP0, 22, 4 },
+	{ DBGBUS_SSPP0, 22, 5 },
+	{ DBGBUS_SSPP0, 22, 6 },
+	{ DBGBUS_SSPP0, 22, 7 },
+
+	{ DBGBUS_SSPP0, 24, 0 },
+	{ DBGBUS_SSPP0, 24, 1 },
+	{ DBGBUS_SSPP0, 24, 2 },
+	{ DBGBUS_SSPP0, 24, 3 },
+	{ DBGBUS_SSPP0, 24, 4 },
+	{ DBGBUS_SSPP0, 24, 5 },
+	{ DBGBUS_SSPP0, 24, 6 },
+	{ DBGBUS_SSPP0, 24, 7 },
+
+	{ DBGBUS_SSPP0, 25, 0 },
+	{ DBGBUS_SSPP0, 25, 1 },
+	{ DBGBUS_SSPP0, 25, 2 },
+	{ DBGBUS_SSPP0, 25, 3 },
+	{ DBGBUS_SSPP0, 25, 4 },
+	{ DBGBUS_SSPP0, 25, 5 },
+	{ DBGBUS_SSPP0, 25, 6 },
+	{ DBGBUS_SSPP0, 25, 7 },
+
+	/* dma 2 */
+	{ DBGBUS_SSPP0, 30, 0 },
+	{ DBGBUS_SSPP0, 30, 1 },
+	{ DBGBUS_SSPP0, 30, 2 },
+	{ DBGBUS_SSPP0, 30, 3 },
+	{ DBGBUS_SSPP0, 30, 4 },
+	{ DBGBUS_SSPP0, 30, 5 },
+	{ DBGBUS_SSPP0, 30, 6 },
+	{ DBGBUS_SSPP0, 30, 7 },
+
+	{ DBGBUS_SSPP0, 31, 0 },
+	{ DBGBUS_SSPP0, 31, 1 },
+	{ DBGBUS_SSPP0, 31, 2 },
+	{ DBGBUS_SSPP0, 31, 3 },
+	{ DBGBUS_SSPP0, 31, 4 },
+	{ DBGBUS_SSPP0, 31, 5 },
+	{ DBGBUS_SSPP0, 31, 6 },
+	{ DBGBUS_SSPP0, 31, 7 },
+
+	{ DBGBUS_SSPP0, 32, 0 },
+	{ DBGBUS_SSPP0, 32, 1 },
+	{ DBGBUS_SSPP0, 32, 2 },
+	{ DBGBUS_SSPP0, 32, 3 },
+	{ DBGBUS_SSPP0, 32, 4 },
+	{ DBGBUS_SSPP0, 32, 5 },
+	{ DBGBUS_SSPP0, 32, 6 },
+	{ DBGBUS_SSPP0, 32, 7 },
+
+	{ DBGBUS_SSPP0, 33, 0 },
+	{ DBGBUS_SSPP0, 33, 1 },
+	{ DBGBUS_SSPP0, 33, 2 },
+	{ DBGBUS_SSPP0, 33, 3 },
+	{ DBGBUS_SSPP0, 33, 4 },
+	{ DBGBUS_SSPP0, 33, 5 },
+	{ DBGBUS_SSPP0, 33, 6 },
+	{ DBGBUS_SSPP0, 33, 7 },
+
+	{ DBGBUS_SSPP0, 34, 0 },
+	{ DBGBUS_SSPP0, 34, 1 },
+	{ DBGBUS_SSPP0, 34, 2 },
+	{ DBGBUS_SSPP0, 34, 3 },
+	{ DBGBUS_SSPP0, 34, 4 },
+	{ DBGBUS_SSPP0, 34, 5 },
+	{ DBGBUS_SSPP0, 34, 6 },
+	{ DBGBUS_SSPP0, 34, 7 },
+
+	{ DBGBUS_SSPP0, 35, 0 },
+	{ DBGBUS_SSPP0, 35, 1 },
+	{ DBGBUS_SSPP0, 35, 2 },
+	{ DBGBUS_SSPP0, 35, 3 },
+
+	/* dma 0 */
+	{ DBGBUS_SSPP0, 40, 0 },
+	{ DBGBUS_SSPP0, 40, 1 },
+	{ DBGBUS_SSPP0, 40, 2 },
+	{ DBGBUS_SSPP0, 40, 3 },
+	{ DBGBUS_SSPP0, 40, 4 },
+	{ DBGBUS_SSPP0, 40, 5 },
+	{ DBGBUS_SSPP0, 40, 6 },
+	{ DBGBUS_SSPP0, 40, 7 },
+
+	{ DBGBUS_SSPP0, 41, 0 },
+	{ DBGBUS_SSPP0, 41, 1 },
+	{ DBGBUS_SSPP0, 41, 2 },
+	{ DBGBUS_SSPP0, 41, 3 },
+	{ DBGBUS_SSPP0, 41, 4 },
+	{ DBGBUS_SSPP0, 41, 5 },
+	{ DBGBUS_SSPP0, 41, 6 },
+	{ DBGBUS_SSPP0, 41, 7 },
+
+	{ DBGBUS_SSPP0, 42, 0 },
+	{ DBGBUS_SSPP0, 42, 1 },
+	{ DBGBUS_SSPP0, 42, 2 },
+	{ DBGBUS_SSPP0, 42, 3 },
+	{ DBGBUS_SSPP0, 42, 4 },
+	{ DBGBUS_SSPP0, 42, 5 },
+	{ DBGBUS_SSPP0, 42, 6 },
+	{ DBGBUS_SSPP0, 42, 7 },
+
+	{ DBGBUS_SSPP0, 44, 0 },
+	{ DBGBUS_SSPP0, 44, 1 },
+	{ DBGBUS_SSPP0, 44, 2 },
+	{ DBGBUS_SSPP0, 44, 3 },
+	{ DBGBUS_SSPP0, 44, 4 },
+	{ DBGBUS_SSPP0, 44, 5 },
+	{ DBGBUS_SSPP0, 44, 6 },
+	{ DBGBUS_SSPP0, 44, 7 },
+
+	{ DBGBUS_SSPP0, 45, 0 },
+	{ DBGBUS_SSPP0, 45, 1 },
+	{ DBGBUS_SSPP0, 45, 2 },
+	{ DBGBUS_SSPP0, 45, 3 },
+	{ DBGBUS_SSPP0, 45, 4 },
+	{ DBGBUS_SSPP0, 45, 5 },
+	{ DBGBUS_SSPP0, 45, 6 },
+	{ DBGBUS_SSPP0, 45, 7 },
+
+	/* fetch sspp1 */
+	/* vig 1 */
+	{ DBGBUS_SSPP1, 0, 0 },
+	{ DBGBUS_SSPP1, 0, 1 },
+	{ DBGBUS_SSPP1, 0, 2 },
+	{ DBGBUS_SSPP1, 0, 3 },
+	{ DBGBUS_SSPP1, 0, 4 },
+	{ DBGBUS_SSPP1, 0, 5 },
+	{ DBGBUS_SSPP1, 0, 6 },
+	{ DBGBUS_SSPP1, 0, 7 },
+
+	{ DBGBUS_SSPP1, 1, 0 },
+	{ DBGBUS_SSPP1, 1, 1 },
+	{ DBGBUS_SSPP1, 1, 2 },
+	{ DBGBUS_SSPP1, 1, 3 },
+	{ DBGBUS_SSPP1, 1, 4 },
+	{ DBGBUS_SSPP1, 1, 5 },
+	{ DBGBUS_SSPP1, 1, 6 },
+	{ DBGBUS_SSPP1, 1, 7 },
+
+	{ DBGBUS_SSPP1, 2, 0 },
+	{ DBGBUS_SSPP1, 2, 1 },
+	{ DBGBUS_SSPP1, 2, 2 },
+	{ DBGBUS_SSPP1, 2, 3 },
+	{ DBGBUS_SSPP1, 2, 4 },
+	{ DBGBUS_SSPP1, 2, 5 },
+	{ DBGBUS_SSPP1, 2, 6 },
+	{ DBGBUS_SSPP1, 2, 7 },
+
+	{ DBGBUS_SSPP1, 4, 0 },
+	{ DBGBUS_SSPP1, 4, 1 },
+	{ DBGBUS_SSPP1, 4, 2 },
+	{ DBGBUS_SSPP1, 4, 3 },
+	{ DBGBUS_SSPP1, 4, 4 },
+	{ DBGBUS_SSPP1, 4, 5 },
+	{ DBGBUS_SSPP1, 4, 6 },
+	{ DBGBUS_SSPP1, 4, 7 },
+
+	{ DBGBUS_SSPP1, 5, 0 },
+	{ DBGBUS_SSPP1, 5, 1 },
+	{ DBGBUS_SSPP1, 5, 2 },
+	{ DBGBUS_SSPP1, 5, 3 },
+	{ DBGBUS_SSPP1, 5, 4 },
+	{ DBGBUS_SSPP1, 5, 5 },
+	{ DBGBUS_SSPP1, 5, 6 },
+	{ DBGBUS_SSPP1, 5, 7 },
+
+	/* vig 3 */
+	{ DBGBUS_SSPP1, 20, 0 },
+	{ DBGBUS_SSPP1, 20, 1 },
+	{ DBGBUS_SSPP1, 20, 2 },
+	{ DBGBUS_SSPP1, 20, 3 },
+	{ DBGBUS_SSPP1, 20, 4 },
+	{ DBGBUS_SSPP1, 20, 5 },
+	{ DBGBUS_SSPP1, 20, 6 },
+	{ DBGBUS_SSPP1, 20, 7 },
+
+	{ DBGBUS_SSPP1, 21, 0 },
+	{ DBGBUS_SSPP1, 21, 1 },
+	{ DBGBUS_SSPP1, 21, 2 },
+	{ DBGBUS_SSPP1, 21, 3 },
+	{ DBGBUS_SSPP1, 21, 4 },
+	{ DBGBUS_SSPP1, 21, 5 },
+	{ DBGBUS_SSPP1, 21, 6 },
+	{ DBGBUS_SSPP1, 21, 7 },
+
+	{ DBGBUS_SSPP1, 22, 0 },
+	{ DBGBUS_SSPP1, 22, 1 },
+	{ DBGBUS_SSPP1, 22, 2 },
+	{ DBGBUS_SSPP1, 22, 3 },
+	{ DBGBUS_SSPP1, 22, 4 },
+	{ DBGBUS_SSPP1, 22, 5 },
+	{ DBGBUS_SSPP1, 22, 6 },
+	{ DBGBUS_SSPP1, 22, 7 },
+
+	{ DBGBUS_SSPP1, 24, 0 },
+	{ DBGBUS_SSPP1, 24, 1 },
+	{ DBGBUS_SSPP1, 24, 2 },
+	{ DBGBUS_SSPP1, 24, 3 },
+	{ DBGBUS_SSPP1, 24, 4 },
+	{ DBGBUS_SSPP1, 24, 5 },
+	{ DBGBUS_SSPP1, 24, 6 },
+	{ DBGBUS_SSPP1, 24, 7 },
+
+	{ DBGBUS_SSPP1, 25, 0 },
+	{ DBGBUS_SSPP1, 25, 1 },
+	{ DBGBUS_SSPP1, 25, 2 },
+	{ DBGBUS_SSPP1, 25, 3 },
+	{ DBGBUS_SSPP1, 25, 4 },
+	{ DBGBUS_SSPP1, 25, 5 },
+	{ DBGBUS_SSPP1, 25, 6 },
+	{ DBGBUS_SSPP1, 25, 7 },
+
+	/* dma 3 */
+	{ DBGBUS_SSPP1, 30, 0 },
+	{ DBGBUS_SSPP1, 30, 1 },
+	{ DBGBUS_SSPP1, 30, 2 },
+	{ DBGBUS_SSPP1, 30, 3 },
+	{ DBGBUS_SSPP1, 30, 4 },
+	{ DBGBUS_SSPP1, 30, 5 },
+	{ DBGBUS_SSPP1, 30, 6 },
+	{ DBGBUS_SSPP1, 30, 7 },
+
+	{ DBGBUS_SSPP1, 31, 0 },
+	{ DBGBUS_SSPP1, 31, 1 },
+	{ DBGBUS_SSPP1, 31, 2 },
+	{ DBGBUS_SSPP1, 31, 3 },
+	{ DBGBUS_SSPP1, 31, 4 },
+	{ DBGBUS_SSPP1, 31, 5 },
+	{ DBGBUS_SSPP1, 31, 6 },
+	{ DBGBUS_SSPP1, 31, 7 },
+
+	{ DBGBUS_SSPP1, 32, 0 },
+	{ DBGBUS_SSPP1, 32, 1 },
+	{ DBGBUS_SSPP1, 32, 2 },
+	{ DBGBUS_SSPP1, 32, 3 },
+	{ DBGBUS_SSPP1, 32, 4 },
+	{ DBGBUS_SSPP1, 32, 5 },
+	{ DBGBUS_SSPP1, 32, 6 },
+	{ DBGBUS_SSPP1, 32, 7 },
+
+	{ DBGBUS_SSPP1, 33, 0 },
+	{ DBGBUS_SSPP1, 33, 1 },
+	{ DBGBUS_SSPP1, 33, 2 },
+	{ DBGBUS_SSPP1, 33, 3 },
+	{ DBGBUS_SSPP1, 33, 4 },
+	{ DBGBUS_SSPP1, 33, 5 },
+	{ DBGBUS_SSPP1, 33, 6 },
+	{ DBGBUS_SSPP1, 33, 7 },
+
+	{ DBGBUS_SSPP1, 34, 0 },
+	{ DBGBUS_SSPP1, 34, 1 },
+	{ DBGBUS_SSPP1, 34, 2 },
+	{ DBGBUS_SSPP1, 34, 3 },
+	{ DBGBUS_SSPP1, 34, 4 },
+	{ DBGBUS_SSPP1, 34, 5 },
+	{ DBGBUS_SSPP1, 34, 6 },
+	{ DBGBUS_SSPP1, 34, 7 },
+
+	{ DBGBUS_SSPP1, 35, 0 },
+	{ DBGBUS_SSPP1, 35, 1 },
+	{ DBGBUS_SSPP1, 35, 2 },
+
+	/* dma 1 */
+	{ DBGBUS_SSPP1, 40, 0 },
+	{ DBGBUS_SSPP1, 40, 1 },
+	{ DBGBUS_SSPP1, 40, 2 },
+	{ DBGBUS_SSPP1, 40, 3 },
+	{ DBGBUS_SSPP1, 40, 4 },
+	{ DBGBUS_SSPP1, 40, 5 },
+	{ DBGBUS_SSPP1, 40, 6 },
+	{ DBGBUS_SSPP1, 40, 7 },
+
+	{ DBGBUS_SSPP1, 41, 0 },
+	{ DBGBUS_SSPP1, 41, 1 },
+	{ DBGBUS_SSPP1, 41, 2 },
+	{ DBGBUS_SSPP1, 41, 3 },
+	{ DBGBUS_SSPP1, 41, 4 },
+	{ DBGBUS_SSPP1, 41, 5 },
+	{ DBGBUS_SSPP1, 41, 6 },
+	{ DBGBUS_SSPP1, 41, 7 },
+
+	{ DBGBUS_SSPP1, 42, 0 },
+	{ DBGBUS_SSPP1, 42, 1 },
+	{ DBGBUS_SSPP1, 42, 2 },
+	{ DBGBUS_SSPP1, 42, 3 },
+	{ DBGBUS_SSPP1, 42, 4 },
+	{ DBGBUS_SSPP1, 42, 5 },
+	{ DBGBUS_SSPP1, 42, 6 },
+	{ DBGBUS_SSPP1, 42, 7 },
+
+	{ DBGBUS_SSPP1, 44, 0 },
+	{ DBGBUS_SSPP1, 44, 1 },
+	{ DBGBUS_SSPP1, 44, 2 },
+	{ DBGBUS_SSPP1, 44, 3 },
+	{ DBGBUS_SSPP1, 44, 4 },
+	{ DBGBUS_SSPP1, 44, 5 },
+	{ DBGBUS_SSPP1, 44, 6 },
+	{ DBGBUS_SSPP1, 44, 7 },
+
+	{ DBGBUS_SSPP1, 45, 0 },
+	{ DBGBUS_SSPP1, 45, 1 },
+	{ DBGBUS_SSPP1, 45, 2 },
+	{ DBGBUS_SSPP1, 45, 3 },
+	{ DBGBUS_SSPP1, 45, 4 },
+	{ DBGBUS_SSPP1, 45, 5 },
+	{ DBGBUS_SSPP1, 45, 6 },
+	{ DBGBUS_SSPP1, 45, 7 },
+
+	/* dspp */
+	{ DBGBUS_DSPP, 13, 0 },
+	{ DBGBUS_DSPP, 19, 0 },
+	{ DBGBUS_DSPP, 14, 0 },
+	{ DBGBUS_DSPP, 14, 1 },
+	{ DBGBUS_DSPP, 14, 3 },
+	{ DBGBUS_DSPP, 20, 0 },
+	{ DBGBUS_DSPP, 20, 1 },
+	{ DBGBUS_DSPP, 20, 3 },
+
+	/* ppb_0 */
+	{ DBGBUS_DSPP, 31, 0, _dpu_debug_bus_ppb0_dump },
+	{ DBGBUS_DSPP, 33, 0, _dpu_debug_bus_ppb0_dump },
+	{ DBGBUS_DSPP, 35, 0, _dpu_debug_bus_ppb0_dump },
+	{ DBGBUS_DSPP, 42, 0, _dpu_debug_bus_ppb0_dump },
+
+	/* ppb_1 */
+	{ DBGBUS_DSPP, 32, 0, _dpu_debug_bus_ppb1_dump },
+	{ DBGBUS_DSPP, 34, 0, _dpu_debug_bus_ppb1_dump },
+	{ DBGBUS_DSPP, 36, 0, _dpu_debug_bus_ppb1_dump },
+	{ DBGBUS_DSPP, 43, 0, _dpu_debug_bus_ppb1_dump },
+
+	/* lm_lut */
+	{ DBGBUS_DSPP, 109, 0 },
+	{ DBGBUS_DSPP, 105, 0 },
+	{ DBGBUS_DSPP, 103, 0 },
+
+	/* crossbar */
+	{ DBGBUS_DSPP, 0, 0, _dpu_debug_bus_xbar_dump },
+
+	/* rotator */
+	{ DBGBUS_DSPP, 9, 0},
+
+	/* blend */
+	/* LM0 */
+	{ DBGBUS_DSPP, 63, 1},
+	{ DBGBUS_DSPP, 63, 2},
+	{ DBGBUS_DSPP, 63, 3},
+	{ DBGBUS_DSPP, 63, 4},
+	{ DBGBUS_DSPP, 63, 5},
+	{ DBGBUS_DSPP, 63, 6},
+	{ DBGBUS_DSPP, 63, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 64, 1},
+	{ DBGBUS_DSPP, 64, 2},
+	{ DBGBUS_DSPP, 64, 3},
+	{ DBGBUS_DSPP, 64, 4},
+	{ DBGBUS_DSPP, 64, 5},
+	{ DBGBUS_DSPP, 64, 6},
+	{ DBGBUS_DSPP, 64, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 65, 1},
+	{ DBGBUS_DSPP, 65, 2},
+	{ DBGBUS_DSPP, 65, 3},
+	{ DBGBUS_DSPP, 65, 4},
+	{ DBGBUS_DSPP, 65, 5},
+	{ DBGBUS_DSPP, 65, 6},
+	{ DBGBUS_DSPP, 65, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 66, 1},
+	{ DBGBUS_DSPP, 66, 2},
+	{ DBGBUS_DSPP, 66, 3},
+	{ DBGBUS_DSPP, 66, 4},
+	{ DBGBUS_DSPP, 66, 5},
+	{ DBGBUS_DSPP, 66, 6},
+	{ DBGBUS_DSPP, 66, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 67, 1},
+	{ DBGBUS_DSPP, 67, 2},
+	{ DBGBUS_DSPP, 67, 3},
+	{ DBGBUS_DSPP, 67, 4},
+	{ DBGBUS_DSPP, 67, 5},
+	{ DBGBUS_DSPP, 67, 6},
+	{ DBGBUS_DSPP, 67, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 68, 1},
+	{ DBGBUS_DSPP, 68, 2},
+	{ DBGBUS_DSPP, 68, 3},
+	{ DBGBUS_DSPP, 68, 4},
+	{ DBGBUS_DSPP, 68, 5},
+	{ DBGBUS_DSPP, 68, 6},
+	{ DBGBUS_DSPP, 68, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 69, 1},
+	{ DBGBUS_DSPP, 69, 2},
+	{ DBGBUS_DSPP, 69, 3},
+	{ DBGBUS_DSPP, 69, 4},
+	{ DBGBUS_DSPP, 69, 5},
+	{ DBGBUS_DSPP, 69, 6},
+	{ DBGBUS_DSPP, 69, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 84, 1},
+	{ DBGBUS_DSPP, 84, 2},
+	{ DBGBUS_DSPP, 84, 3},
+	{ DBGBUS_DSPP, 84, 4},
+	{ DBGBUS_DSPP, 84, 5},
+	{ DBGBUS_DSPP, 84, 6},
+	{ DBGBUS_DSPP, 84, 7, _dpu_debug_bus_lm_dump },
+
+
+	{ DBGBUS_DSPP, 85, 1},
+	{ DBGBUS_DSPP, 85, 2},
+	{ DBGBUS_DSPP, 85, 3},
+	{ DBGBUS_DSPP, 85, 4},
+	{ DBGBUS_DSPP, 85, 5},
+	{ DBGBUS_DSPP, 85, 6},
+	{ DBGBUS_DSPP, 85, 7, _dpu_debug_bus_lm_dump },
+
+
+	{ DBGBUS_DSPP, 86, 1},
+	{ DBGBUS_DSPP, 86, 2},
+	{ DBGBUS_DSPP, 86, 3},
+	{ DBGBUS_DSPP, 86, 4},
+	{ DBGBUS_DSPP, 86, 5},
+	{ DBGBUS_DSPP, 86, 6},
+	{ DBGBUS_DSPP, 86, 7, _dpu_debug_bus_lm_dump },
+
+
+	{ DBGBUS_DSPP, 87, 1},
+	{ DBGBUS_DSPP, 87, 2},
+	{ DBGBUS_DSPP, 87, 3},
+	{ DBGBUS_DSPP, 87, 4},
+	{ DBGBUS_DSPP, 87, 5},
+	{ DBGBUS_DSPP, 87, 6},
+	{ DBGBUS_DSPP, 87, 7, _dpu_debug_bus_lm_dump },
+
+	/* LM1 */
+	{ DBGBUS_DSPP, 70, 1},
+	{ DBGBUS_DSPP, 70, 2},
+	{ DBGBUS_DSPP, 70, 3},
+	{ DBGBUS_DSPP, 70, 4},
+	{ DBGBUS_DSPP, 70, 5},
+	{ DBGBUS_DSPP, 70, 6},
+	{ DBGBUS_DSPP, 70, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 71, 1},
+	{ DBGBUS_DSPP, 71, 2},
+	{ DBGBUS_DSPP, 71, 3},
+	{ DBGBUS_DSPP, 71, 4},
+	{ DBGBUS_DSPP, 71, 5},
+	{ DBGBUS_DSPP, 71, 6},
+	{ DBGBUS_DSPP, 71, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 72, 1},
+	{ DBGBUS_DSPP, 72, 2},
+	{ DBGBUS_DSPP, 72, 3},
+	{ DBGBUS_DSPP, 72, 4},
+	{ DBGBUS_DSPP, 72, 5},
+	{ DBGBUS_DSPP, 72, 6},
+	{ DBGBUS_DSPP, 72, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 73, 1},
+	{ DBGBUS_DSPP, 73, 2},
+	{ DBGBUS_DSPP, 73, 3},
+	{ DBGBUS_DSPP, 73, 4},
+	{ DBGBUS_DSPP, 73, 5},
+	{ DBGBUS_DSPP, 73, 6},
+	{ DBGBUS_DSPP, 73, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 74, 1},
+	{ DBGBUS_DSPP, 74, 2},
+	{ DBGBUS_DSPP, 74, 3},
+	{ DBGBUS_DSPP, 74, 4},
+	{ DBGBUS_DSPP, 74, 5},
+	{ DBGBUS_DSPP, 74, 6},
+	{ DBGBUS_DSPP, 74, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 75, 1},
+	{ DBGBUS_DSPP, 75, 2},
+	{ DBGBUS_DSPP, 75, 3},
+	{ DBGBUS_DSPP, 75, 4},
+	{ DBGBUS_DSPP, 75, 5},
+	{ DBGBUS_DSPP, 75, 6},
+	{ DBGBUS_DSPP, 75, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 76, 1},
+	{ DBGBUS_DSPP, 76, 2},
+	{ DBGBUS_DSPP, 76, 3},
+	{ DBGBUS_DSPP, 76, 4},
+	{ DBGBUS_DSPP, 76, 5},
+	{ DBGBUS_DSPP, 76, 6},
+	{ DBGBUS_DSPP, 76, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 88, 1},
+	{ DBGBUS_DSPP, 88, 2},
+	{ DBGBUS_DSPP, 88, 3},
+	{ DBGBUS_DSPP, 88, 4},
+	{ DBGBUS_DSPP, 88, 5},
+	{ DBGBUS_DSPP, 88, 6},
+	{ DBGBUS_DSPP, 88, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 89, 1},
+	{ DBGBUS_DSPP, 89, 2},
+	{ DBGBUS_DSPP, 89, 3},
+	{ DBGBUS_DSPP, 89, 4},
+	{ DBGBUS_DSPP, 89, 5},
+	{ DBGBUS_DSPP, 89, 6},
+	{ DBGBUS_DSPP, 89, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 90, 1},
+	{ DBGBUS_DSPP, 90, 2},
+	{ DBGBUS_DSPP, 90, 3},
+	{ DBGBUS_DSPP, 90, 4},
+	{ DBGBUS_DSPP, 90, 5},
+	{ DBGBUS_DSPP, 90, 6},
+	{ DBGBUS_DSPP, 90, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 91, 1},
+	{ DBGBUS_DSPP, 91, 2},
+	{ DBGBUS_DSPP, 91, 3},
+	{ DBGBUS_DSPP, 91, 4},
+	{ DBGBUS_DSPP, 91, 5},
+	{ DBGBUS_DSPP, 91, 6},
+	{ DBGBUS_DSPP, 91, 7, _dpu_debug_bus_lm_dump },
+
+	/* LM2 */
+	{ DBGBUS_DSPP, 77, 0},
+	{ DBGBUS_DSPP, 77, 1},
+	{ DBGBUS_DSPP, 77, 2},
+	{ DBGBUS_DSPP, 77, 3},
+	{ DBGBUS_DSPP, 77, 4},
+	{ DBGBUS_DSPP, 77, 5},
+	{ DBGBUS_DSPP, 77, 6},
+	{ DBGBUS_DSPP, 77, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 78, 0},
+	{ DBGBUS_DSPP, 78, 1},
+	{ DBGBUS_DSPP, 78, 2},
+	{ DBGBUS_DSPP, 78, 3},
+	{ DBGBUS_DSPP, 78, 4},
+	{ DBGBUS_DSPP, 78, 5},
+	{ DBGBUS_DSPP, 78, 6},
+	{ DBGBUS_DSPP, 78, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 79, 0},
+	{ DBGBUS_DSPP, 79, 1},
+	{ DBGBUS_DSPP, 79, 2},
+	{ DBGBUS_DSPP, 79, 3},
+	{ DBGBUS_DSPP, 79, 4},
+	{ DBGBUS_DSPP, 79, 5},
+	{ DBGBUS_DSPP, 79, 6},
+	{ DBGBUS_DSPP, 79, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 80, 0},
+	{ DBGBUS_DSPP, 80, 1},
+	{ DBGBUS_DSPP, 80, 2},
+	{ DBGBUS_DSPP, 80, 3},
+	{ DBGBUS_DSPP, 80, 4},
+	{ DBGBUS_DSPP, 80, 5},
+	{ DBGBUS_DSPP, 80, 6},
+	{ DBGBUS_DSPP, 80, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 81, 0},
+	{ DBGBUS_DSPP, 81, 1},
+	{ DBGBUS_DSPP, 81, 2},
+	{ DBGBUS_DSPP, 81, 3},
+	{ DBGBUS_DSPP, 81, 4},
+	{ DBGBUS_DSPP, 81, 5},
+	{ DBGBUS_DSPP, 81, 6},
+	{ DBGBUS_DSPP, 81, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 82, 0},
+	{ DBGBUS_DSPP, 82, 1},
+	{ DBGBUS_DSPP, 82, 2},
+	{ DBGBUS_DSPP, 82, 3},
+	{ DBGBUS_DSPP, 82, 4},
+	{ DBGBUS_DSPP, 82, 5},
+	{ DBGBUS_DSPP, 82, 6},
+	{ DBGBUS_DSPP, 82, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 83, 0},
+	{ DBGBUS_DSPP, 83, 1},
+	{ DBGBUS_DSPP, 83, 2},
+	{ DBGBUS_DSPP, 83, 3},
+	{ DBGBUS_DSPP, 83, 4},
+	{ DBGBUS_DSPP, 83, 5},
+	{ DBGBUS_DSPP, 83, 6},
+	{ DBGBUS_DSPP, 83, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 92, 1},
+	{ DBGBUS_DSPP, 92, 2},
+	{ DBGBUS_DSPP, 92, 3},
+	{ DBGBUS_DSPP, 92, 4},
+	{ DBGBUS_DSPP, 92, 5},
+	{ DBGBUS_DSPP, 92, 6},
+	{ DBGBUS_DSPP, 92, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 93, 1},
+	{ DBGBUS_DSPP, 93, 2},
+	{ DBGBUS_DSPP, 93, 3},
+	{ DBGBUS_DSPP, 93, 4},
+	{ DBGBUS_DSPP, 93, 5},
+	{ DBGBUS_DSPP, 93, 6},
+	{ DBGBUS_DSPP, 93, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 94, 1},
+	{ DBGBUS_DSPP, 94, 2},
+	{ DBGBUS_DSPP, 94, 3},
+	{ DBGBUS_DSPP, 94, 4},
+	{ DBGBUS_DSPP, 94, 5},
+	{ DBGBUS_DSPP, 94, 6},
+	{ DBGBUS_DSPP, 94, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 95, 1},
+	{ DBGBUS_DSPP, 95, 2},
+	{ DBGBUS_DSPP, 95, 3},
+	{ DBGBUS_DSPP, 95, 4},
+	{ DBGBUS_DSPP, 95, 5},
+	{ DBGBUS_DSPP, 95, 6},
+	{ DBGBUS_DSPP, 95, 7, _dpu_debug_bus_lm_dump },
+
+	/* LM5 */
+	{ DBGBUS_DSPP, 110, 1},
+	{ DBGBUS_DSPP, 110, 2},
+	{ DBGBUS_DSPP, 110, 3},
+	{ DBGBUS_DSPP, 110, 4},
+	{ DBGBUS_DSPP, 110, 5},
+	{ DBGBUS_DSPP, 110, 6},
+	{ DBGBUS_DSPP, 110, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 111, 1},
+	{ DBGBUS_DSPP, 111, 2},
+	{ DBGBUS_DSPP, 111, 3},
+	{ DBGBUS_DSPP, 111, 4},
+	{ DBGBUS_DSPP, 111, 5},
+	{ DBGBUS_DSPP, 111, 6},
+	{ DBGBUS_DSPP, 111, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 112, 1},
+	{ DBGBUS_DSPP, 112, 2},
+	{ DBGBUS_DSPP, 112, 3},
+	{ DBGBUS_DSPP, 112, 4},
+	{ DBGBUS_DSPP, 112, 5},
+	{ DBGBUS_DSPP, 112, 6},
+	{ DBGBUS_DSPP, 112, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 113, 1},
+	{ DBGBUS_DSPP, 113, 2},
+	{ DBGBUS_DSPP, 113, 3},
+	{ DBGBUS_DSPP, 113, 4},
+	{ DBGBUS_DSPP, 113, 5},
+	{ DBGBUS_DSPP, 113, 6},
+	{ DBGBUS_DSPP, 113, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 114, 1},
+	{ DBGBUS_DSPP, 114, 2},
+	{ DBGBUS_DSPP, 114, 3},
+	{ DBGBUS_DSPP, 114, 4},
+	{ DBGBUS_DSPP, 114, 5},
+	{ DBGBUS_DSPP, 114, 6},
+	{ DBGBUS_DSPP, 114, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 115, 1},
+	{ DBGBUS_DSPP, 115, 2},
+	{ DBGBUS_DSPP, 115, 3},
+	{ DBGBUS_DSPP, 115, 4},
+	{ DBGBUS_DSPP, 115, 5},
+	{ DBGBUS_DSPP, 115, 6},
+	{ DBGBUS_DSPP, 115, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 116, 1},
+	{ DBGBUS_DSPP, 116, 2},
+	{ DBGBUS_DSPP, 116, 3},
+	{ DBGBUS_DSPP, 116, 4},
+	{ DBGBUS_DSPP, 116, 5},
+	{ DBGBUS_DSPP, 116, 6},
+	{ DBGBUS_DSPP, 116, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 117, 1},
+	{ DBGBUS_DSPP, 117, 2},
+	{ DBGBUS_DSPP, 117, 3},
+	{ DBGBUS_DSPP, 117, 4},
+	{ DBGBUS_DSPP, 117, 5},
+	{ DBGBUS_DSPP, 117, 6},
+	{ DBGBUS_DSPP, 117, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 118, 1},
+	{ DBGBUS_DSPP, 118, 2},
+	{ DBGBUS_DSPP, 118, 3},
+	{ DBGBUS_DSPP, 118, 4},
+	{ DBGBUS_DSPP, 118, 5},
+	{ DBGBUS_DSPP, 118, 6},
+	{ DBGBUS_DSPP, 118, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 119, 1},
+	{ DBGBUS_DSPP, 119, 2},
+	{ DBGBUS_DSPP, 119, 3},
+	{ DBGBUS_DSPP, 119, 4},
+	{ DBGBUS_DSPP, 119, 5},
+	{ DBGBUS_DSPP, 119, 6},
+	{ DBGBUS_DSPP, 119, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 120, 1},
+	{ DBGBUS_DSPP, 120, 2},
+	{ DBGBUS_DSPP, 120, 3},
+	{ DBGBUS_DSPP, 120, 4},
+	{ DBGBUS_DSPP, 120, 5},
+	{ DBGBUS_DSPP, 120, 6},
+	{ DBGBUS_DSPP, 120, 7, _dpu_debug_bus_lm_dump },
+
+	/* csc */
+	{ DBGBUS_SSPP0, 7, 0},
+	{ DBGBUS_SSPP0, 7, 1},
+	{ DBGBUS_SSPP0, 27, 0},
+	{ DBGBUS_SSPP0, 27, 1},
+	{ DBGBUS_SSPP1, 7, 0},
+	{ DBGBUS_SSPP1, 7, 1},
+	{ DBGBUS_SSPP1, 27, 0},
+	{ DBGBUS_SSPP1, 27, 1},
+
+	/* pcc */
+	{ DBGBUS_SSPP0, 3,  3},
+	{ DBGBUS_SSPP0, 23, 3},
+	{ DBGBUS_SSPP0, 33, 3},
+	{ DBGBUS_SSPP0, 43, 3},
+	{ DBGBUS_SSPP1, 3,  3},
+	{ DBGBUS_SSPP1, 23, 3},
+	{ DBGBUS_SSPP1, 33, 3},
+	{ DBGBUS_SSPP1, 43, 3},
+
+	/* spa */
+	{ DBGBUS_SSPP0, 8,  0},
+	{ DBGBUS_SSPP0, 28, 0},
+	{ DBGBUS_SSPP1, 8,  0},
+	{ DBGBUS_SSPP1, 28, 0},
+	{ DBGBUS_DSPP, 13, 0},
+	{ DBGBUS_DSPP, 19, 0},
+
+	/* igc */
+	{ DBGBUS_SSPP0, 17, 0},
+	{ DBGBUS_SSPP0, 17, 1},
+	{ DBGBUS_SSPP0, 17, 3},
+	{ DBGBUS_SSPP0, 37, 0},
+	{ DBGBUS_SSPP0, 37, 1},
+	{ DBGBUS_SSPP0, 37, 3},
+	{ DBGBUS_SSPP0, 46, 0},
+	{ DBGBUS_SSPP0, 46, 1},
+	{ DBGBUS_SSPP0, 46, 3},
+
+	{ DBGBUS_SSPP1, 17, 0},
+	{ DBGBUS_SSPP1, 17, 1},
+	{ DBGBUS_SSPP1, 17, 3},
+	{ DBGBUS_SSPP1, 37, 0},
+	{ DBGBUS_SSPP1, 37, 1},
+	{ DBGBUS_SSPP1, 37, 3},
+	{ DBGBUS_SSPP1, 46, 0},
+	{ DBGBUS_SSPP1, 46, 1},
+	{ DBGBUS_SSPP1, 46, 3},
+
+	{ DBGBUS_DSPP, 14, 0},
+	{ DBGBUS_DSPP, 14, 1},
+	{ DBGBUS_DSPP, 14, 3},
+	{ DBGBUS_DSPP, 20, 0},
+	{ DBGBUS_DSPP, 20, 1},
+	{ DBGBUS_DSPP, 20, 3},
+
+	/* intf0-3 */
+	{ DBGBUS_PERIPH, 0, 0},
+	{ DBGBUS_PERIPH, 1, 0},
+	{ DBGBUS_PERIPH, 2, 0},
+	{ DBGBUS_PERIPH, 3, 0},
+
+	/* te counter wrapper */
+	{ DBGBUS_PERIPH, 60, 0},
+
+	/* dsc0 */
+	{ DBGBUS_PERIPH, 47, 0},
+	{ DBGBUS_PERIPH, 47, 1},
+	{ DBGBUS_PERIPH, 47, 2},
+	{ DBGBUS_PERIPH, 47, 3},
+	{ DBGBUS_PERIPH, 47, 4},
+	{ DBGBUS_PERIPH, 47, 5},
+	{ DBGBUS_PERIPH, 47, 6},
+	{ DBGBUS_PERIPH, 47, 7},
+
+	/* dsc1 */
+	{ DBGBUS_PERIPH, 48, 0},
+	{ DBGBUS_PERIPH, 48, 1},
+	{ DBGBUS_PERIPH, 48, 2},
+	{ DBGBUS_PERIPH, 48, 3},
+	{ DBGBUS_PERIPH, 48, 4},
+	{ DBGBUS_PERIPH, 48, 5},
+	{ DBGBUS_PERIPH, 48, 6},
+	{ DBGBUS_PERIPH, 48, 7},
+
+	/* dsc2 */
+	{ DBGBUS_PERIPH, 51, 0},
+	{ DBGBUS_PERIPH, 51, 1},
+	{ DBGBUS_PERIPH, 51, 2},
+	{ DBGBUS_PERIPH, 51, 3},
+	{ DBGBUS_PERIPH, 51, 4},
+	{ DBGBUS_PERIPH, 51, 5},
+	{ DBGBUS_PERIPH, 51, 6},
+	{ DBGBUS_PERIPH, 51, 7},
+
+	/* dsc3 */
+	{ DBGBUS_PERIPH, 52, 0},
+	{ DBGBUS_PERIPH, 52, 1},
+	{ DBGBUS_PERIPH, 52, 2},
+	{ DBGBUS_PERIPH, 52, 3},
+	{ DBGBUS_PERIPH, 52, 4},
+	{ DBGBUS_PERIPH, 52, 5},
+	{ DBGBUS_PERIPH, 52, 6},
+	{ DBGBUS_PERIPH, 52, 7},
+
+	/* tear-check */
+	{ DBGBUS_PERIPH, 63, 0 },
+	{ DBGBUS_PERIPH, 64, 0 },
+	{ DBGBUS_PERIPH, 65, 0 },
+	{ DBGBUS_PERIPH, 73, 0 },
+	{ DBGBUS_PERIPH, 74, 0 },
+
+	/* cdwn */
+	{ DBGBUS_PERIPH, 80, 0},
+	{ DBGBUS_PERIPH, 80, 1},
+	{ DBGBUS_PERIPH, 80, 2},
+
+	{ DBGBUS_PERIPH, 81, 0},
+	{ DBGBUS_PERIPH, 81, 1},
+	{ DBGBUS_PERIPH, 81, 2},
+
+	{ DBGBUS_PERIPH, 82, 0},
+	{ DBGBUS_PERIPH, 82, 1},
+	{ DBGBUS_PERIPH, 82, 2},
+	{ DBGBUS_PERIPH, 82, 3},
+	{ DBGBUS_PERIPH, 82, 4},
+	{ DBGBUS_PERIPH, 82, 5},
+	{ DBGBUS_PERIPH, 82, 6},
+	{ DBGBUS_PERIPH, 82, 7},
+
+	/* hdmi */
+	{ DBGBUS_PERIPH, 68, 0},
+	{ DBGBUS_PERIPH, 68, 1},
+	{ DBGBUS_PERIPH, 68, 2},
+	{ DBGBUS_PERIPH, 68, 3},
+	{ DBGBUS_PERIPH, 68, 4},
+	{ DBGBUS_PERIPH, 68, 5},
+
+	/* edp */
+	{ DBGBUS_PERIPH, 69, 0},
+	{ DBGBUS_PERIPH, 69, 1},
+	{ DBGBUS_PERIPH, 69, 2},
+	{ DBGBUS_PERIPH, 69, 3},
+	{ DBGBUS_PERIPH, 69, 4},
+	{ DBGBUS_PERIPH, 69, 5},
+
+	/* dsi0 */
+	{ DBGBUS_PERIPH, 70, 0},
+	{ DBGBUS_PERIPH, 70, 1},
+	{ DBGBUS_PERIPH, 70, 2},
+	{ DBGBUS_PERIPH, 70, 3},
+	{ DBGBUS_PERIPH, 70, 4},
+	{ DBGBUS_PERIPH, 70, 5},
+
+	/* dsi1 */
+	{ DBGBUS_PERIPH, 71, 0},
+	{ DBGBUS_PERIPH, 71, 1},
+	{ DBGBUS_PERIPH, 71, 2},
+	{ DBGBUS_PERIPH, 71, 3},
+	{ DBGBUS_PERIPH, 71, 4},
+	{ DBGBUS_PERIPH, 71, 5},
+};
+
+static struct vbif_debug_bus_entry vbif_dbg_bus_msm8998[] = {
+	{0x214, 0x21c, 16, 2, 0x0, 0xd},     /* arb clients */
+	{0x214, 0x21c, 16, 2, 0x80, 0xc0},   /* arb clients */
+	{0x214, 0x21c, 16, 2, 0x100, 0x140}, /* arb clients */
+	{0x214, 0x21c, 0, 16, 0x0, 0xf},     /* xin blocks - axi side */
+	{0x214, 0x21c, 0, 16, 0x80, 0xa4},   /* xin blocks - axi side */
+	{0x214, 0x21c, 0, 15, 0x100, 0x124}, /* xin blocks - axi side */
+	{0x21c, 0x214, 0, 14, 0, 0xc}, /* xin blocks - clock side */
+};
+
+/**
+ * _dpu_dbg_enable_power - use callback to turn power on for hw register access
+ * @enable: whether to turn power on or off
+ */
+static inline void _dpu_dbg_enable_power(int enable)
+{
+	if (enable)
+		pm_runtime_get_sync(dpu_dbg_base.dev);
+	else
+		pm_runtime_put_sync(dpu_dbg_base.dev);
+}
+
+static void _dpu_dbg_dump_dpu_dbg_bus(struct dpu_dbg_dpu_debug_bus *bus)
+{
+	bool in_log, in_mem;
+	u32 **dump_mem = NULL;
+	u32 *dump_addr = NULL;
+	u32 status = 0;
+	struct dpu_debug_bus_entry *head;
+	phys_addr_t phys = 0;
+	int list_size;
+	int i;
+	u32 offset;
+	void __iomem *mem_base = NULL;
+	struct dpu_dbg_reg_base *reg_base;
+
+	if (!bus || !bus->cmn.entries_size)
+		return;
+
+	list_for_each_entry(reg_base, &dpu_dbg_base.reg_base_list,
+			reg_base_head)
+		if (strlen(reg_base->name) &&
+			!strcmp(reg_base->name, bus->cmn.name))
+			mem_base = reg_base->base + bus->top_blk_off;
+
+	if (!mem_base) {
+		pr_err("unable to find mem_base for %s\n", bus->cmn.name);
+		return;
+	}
+
+	dump_mem = &bus->cmn.dumped_content;
+
+	/* will keep in memory 4 entries of 4 bytes each */
+	list_size = (bus->cmn.entries_size * 4 * 4);
+
+	in_log = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_LOG);
+	in_mem = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_MEM);
+
+	if (!in_log && !in_mem)
+		return;
+
+	dev_info(dpu_dbg_base.dev, "======== start %s dump =========\n",
+			bus->cmn.name);
+
+	if (in_mem) {
+		if (!(*dump_mem))
+			*dump_mem = dma_alloc_coherent(dpu_dbg_base.dev,
+				list_size, &phys, GFP_KERNEL);
+
+		if (*dump_mem) {
+			dump_addr = *dump_mem;
+			dev_info(dpu_dbg_base.dev,
+				"%s: start_addr:0x%pK len:0x%x\n",
+				__func__, dump_addr, list_size);
+		} else {
+			in_mem = false;
+			pr_err("dump_mem: allocation fails\n");
+		}
+	}
+
+	_dpu_dbg_enable_power(true);
+	for (i = 0; i < bus->cmn.entries_size; i++) {
+		head = bus->entries + i;
+		writel_relaxed(TEST_MASK(head->block_id, head->test_id),
+				mem_base + head->wr_addr);
+		wmb(); /* make sure test bits were written */
+
+		if (bus->cmn.flags & DBGBUS_FLAGS_DSPP) {
+			offset = DBGBUS_DSPP_STATUS;
+			/* keep DSPP test point enabled */
+			if (head->wr_addr != DBGBUS_DSPP)
+				writel_relaxed(0xF, mem_base + DBGBUS_DSPP);
+		} else {
+			offset = head->wr_addr + 0x4;
+		}
+
+		status = readl_relaxed(mem_base + offset);
+
+		if (in_log)
+			dev_info(dpu_dbg_base.dev,
+					"waddr=0x%x blk=%d tst=%d val=0x%x\n",
+					head->wr_addr, head->block_id,
+					head->test_id, status);
+
+		if (dump_addr && in_mem) {
+			dump_addr[i*4]     = head->wr_addr;
+			dump_addr[i*4 + 1] = head->block_id;
+			dump_addr[i*4 + 2] = head->test_id;
+			dump_addr[i*4 + 3] = status;
+		}
+
+		if (head->analyzer)
+			head->analyzer(mem_base, head, status);
+
+		/* Disable debug bus once we are done */
+		writel_relaxed(0, mem_base + head->wr_addr);
+		if (bus->cmn.flags & DBGBUS_FLAGS_DSPP &&
+						head->wr_addr != DBGBUS_DSPP)
+			writel_relaxed(0x0, mem_base + DBGBUS_DSPP);
+	}
+	_dpu_dbg_enable_power(false);
+
+	dev_info(dpu_dbg_base.dev, "======== end %s dump =========\n",
+			bus->cmn.name);
+}
+
+static void _dpu_dbg_dump_vbif_debug_bus_entry(
+		struct vbif_debug_bus_entry *head, void __iomem *mem_base,
+		u32 *dump_addr, bool in_log)
+{
+	int i, j;
+	u32 val;
+
+	if (!dump_addr && !in_log)
+		return;
+
+	for (i = 0; i < head->block_cnt; i++) {
+		writel_relaxed(1 << (i + head->bit_offset),
+				mem_base + head->block_bus_addr);
+		/* make sure that current bus blcok enable */
+		wmb();
+		for (j = head->test_pnt_start; j < head->test_pnt_cnt; j++) {
+			writel_relaxed(j, mem_base + head->block_bus_addr + 4);
+			/* make sure that test point is enabled */
+			wmb();
+			val = readl_relaxed(mem_base + MMSS_VBIF_TEST_BUS_OUT);
+			if (dump_addr) {
+				*dump_addr++ = head->block_bus_addr;
+				*dump_addr++ = i;
+				*dump_addr++ = j;
+				*dump_addr++ = val;
+			}
+			if (in_log)
+				dev_info(dpu_dbg_base.dev,
+					"testpoint:%x arb/xin id=%d index=%d val=0x%x\n",
+					head->block_bus_addr, i, j, val);
+		}
+	}
+}
+
+static void _dpu_dbg_dump_vbif_dbg_bus(struct dpu_dbg_vbif_debug_bus *bus)
+{
+	bool in_log, in_mem;
+	u32 **dump_mem = NULL;
+	u32 *dump_addr = NULL;
+	u32 value, d0, d1;
+	unsigned long reg, reg1, reg2;
+	struct vbif_debug_bus_entry *head;
+	phys_addr_t phys = 0;
+	int i, list_size = 0;
+	void __iomem *mem_base = NULL;
+	struct vbif_debug_bus_entry *dbg_bus;
+	u32 bus_size;
+	struct dpu_dbg_reg_base *reg_base;
+
+	if (!bus || !bus->cmn.entries_size)
+		return;
+
+	list_for_each_entry(reg_base, &dpu_dbg_base.reg_base_list,
+			reg_base_head)
+		if (strlen(reg_base->name) &&
+			!strcmp(reg_base->name, bus->cmn.name))
+			mem_base = reg_base->base;
+
+	if (!mem_base) {
+		pr_err("unable to find mem_base for %s\n", bus->cmn.name);
+		return;
+	}
+
+	dbg_bus = bus->entries;
+	bus_size = bus->cmn.entries_size;
+	list_size = bus->cmn.entries_size;
+	dump_mem = &bus->cmn.dumped_content;
+
+	dev_info(dpu_dbg_base.dev, "======== start %s dump =========\n",
+			bus->cmn.name);
+
+	if (!dump_mem || !dbg_bus || !bus_size || !list_size)
+		return;
+
+	/* allocate memory for each test point */
+	for (i = 0; i < bus_size; i++) {
+		head = dbg_bus + i;
+		list_size += (head->block_cnt * head->test_pnt_cnt);
+	}
+
+	/* 4 bytes * 4 entries for each test point*/
+	list_size *= 16;
+
+	in_log = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_LOG);
+	in_mem = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_MEM);
+
+	if (!in_log && !in_mem)
+		return;
+
+	if (in_mem) {
+		if (!(*dump_mem))
+			*dump_mem = dma_alloc_coherent(dpu_dbg_base.dev,
+				list_size, &phys, GFP_KERNEL);
+
+		if (*dump_mem) {
+			dump_addr = *dump_mem;
+			dev_info(dpu_dbg_base.dev,
+				"%s: start_addr:0x%pK len:0x%x\n",
+				__func__, dump_addr, list_size);
+		} else {
+			in_mem = false;
+			pr_err("dump_mem: allocation fails\n");
+		}
+	}
+
+	_dpu_dbg_enable_power(true);
+
+	value = readl_relaxed(mem_base + MMSS_VBIF_CLKON);
+	writel_relaxed(value | BIT(1), mem_base + MMSS_VBIF_CLKON);
+
+	/* make sure that vbif core is on */
+	wmb();
+
+	/**
+	 * Extract VBIF error info based on XIN halt and error status.
+	 * If the XIN client is not in HALT state, or an error is detected,
+	 * then retrieve the VBIF error info for it.
+	 */
+	reg = readl_relaxed(mem_base + MMSS_VBIF_XIN_HALT_CTRL1);
+	reg1 = readl_relaxed(mem_base + MMSS_VBIF_PND_ERR);
+	reg2 = readl_relaxed(mem_base + MMSS_VBIF_SRC_ERR);
+	dev_err(dpu_dbg_base.dev,
+			"XIN HALT:0x%lX, PND ERR:0x%lX, SRC ERR:0x%lX\n",
+			reg, reg1, reg2);
+	reg >>= 16;
+	reg &= ~(reg1 | reg2);
+	for (i = 0; i < MMSS_VBIF_CLIENT_NUM; i++) {
+		if (!test_bit(0, &reg)) {
+			writel_relaxed(i, mem_base + MMSS_VBIF_ERR_INFO);
+			/* make sure reg write goes through */
+			wmb();
+
+			d0 = readl_relaxed(mem_base + MMSS_VBIF_ERR_INFO);
+			d1 = readl_relaxed(mem_base + MMSS_VBIF_ERR_INFO_1);
+
+			dev_err(dpu_dbg_base.dev,
+					"Client:%d, errinfo=0x%X, errinfo1=0x%X\n",
+					i, d0, d1);
+		}
+		reg >>= 1;
+	}
+
+	for (i = 0; i < bus_size; i++) {
+		head = dbg_bus + i;
+
+		writel_relaxed(0, mem_base + head->disable_bus_addr);
+		writel_relaxed(BIT(0), mem_base + MMSS_VBIF_TEST_BUS_OUT_CTRL);
+		/* make sure that other bus is off */
+		wmb();
+
+		_dpu_dbg_dump_vbif_debug_bus_entry(head, mem_base, dump_addr,
+				in_log);
+		if (dump_addr)
+			dump_addr += (head->block_cnt * head->test_pnt_cnt * 4);
+	}
+
+	_dpu_dbg_enable_power(false);
+
+	dev_info(dpu_dbg_base.dev, "======== end %s dump =========\n",
+			bus->cmn.name);
+}
+
+/**
+ * _dpu_dump_array - dump array of register bases
+ * @name: string indicating origin of dump
+ * @dump_dbgbus_dpu: whether to dump the dpu debug bus
+ * @dump_dbgbus_vbif_rt: whether to dump the vbif rt debug bus
+ */
+static void _dpu_dump_array(const char *name, bool dump_dbgbus_dpu,
+			    bool dump_dbgbus_vbif_rt)
+{
+	if (dump_dbgbus_dpu)
+		_dpu_dbg_dump_dpu_dbg_bus(&dpu_dbg_base.dbgbus_dpu);
+
+	if (dump_dbgbus_vbif_rt)
+		_dpu_dbg_dump_vbif_dbg_bus(&dpu_dbg_base.dbgbus_vbif_rt);
+}
+
+/**
+ * _dpu_dump_work - deferred dump work function
+ * @work: work structure
+ */
+static void _dpu_dump_work(struct work_struct *work)
+{
+	_dpu_dump_array("dpudump_workitem",
+		dpu_dbg_base.dbgbus_dpu.cmn.include_in_deferred_work,
+		dpu_dbg_base.dbgbus_vbif_rt.cmn.include_in_deferred_work);
+}
+
+void dpu_dbg_dump(bool queue_work, const char *name, bool dump_dbgbus_dpu,
+		  bool dump_dbgbus_vbif_rt)
+{
+	if (queue_work && work_pending(&dpu_dbg_base.dump_work))
+		return;
+
+	if (!queue_work) {
+		_dpu_dump_array(name, dump_dbgbus_dpu, dump_dbgbus_vbif_rt);
+		return;
+	}
+
+	/* schedule work to dump later */
+	dpu_dbg_base.dbgbus_dpu.cmn.include_in_deferred_work = dump_dbgbus_dpu;
+	dpu_dbg_base.dbgbus_vbif_rt.cmn.include_in_deferred_work =
+			dump_dbgbus_vbif_rt;
+	schedule_work(&dpu_dbg_base.dump_work);
+}
+
+/*
+ * dpu_dbg_debugfs_open - debugfs open handler for debug dump
+ * @inode: debugfs inode
+ * @file: file handle
+ */
+static int dpu_dbg_debugfs_open(struct inode *inode, struct file *file)
+{
+	/* non-seekable */
+	file->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
+	file->private_data = inode->i_private;
+	return 0;
+}
+
+/**
+ * dpu_dbg_dump_write - debugfs write handler for debug dump
+ * @file: file handler
+ * @user_buf: user buffer content from debugfs
+ * @count: size of user buffer
+ * @ppos: position offset of user buffer
+ */
+static ssize_t dpu_dbg_dump_write(struct file *file,
+	const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	_dpu_dump_array("dump_debugfs", true, true);
+	return count;
+}
+
+static const struct file_operations dpu_dbg_dump_fops = {
+	.open = dpu_dbg_debugfs_open,
+	.write = dpu_dbg_dump_write,
+};
+
+int dpu_dbg_debugfs_register(struct dentry *debugfs_root)
+{
+	static struct dpu_dbg_base *dbg = &dpu_dbg_base;
+	char debug_name[80] = "";
+
+	if (!debugfs_root)
+		return -EINVAL;
+
+	debugfs_create_file("dump", 0600, debugfs_root, NULL,
+			&dpu_dbg_dump_fops);
+
+	if (dbg->dbgbus_dpu.entries) {
+		dbg->dbgbus_dpu.cmn.name = DBGBUS_NAME_DPU;
+		snprintf(debug_name, sizeof(debug_name), "%s_dbgbus",
+				dbg->dbgbus_dpu.cmn.name);
+		dbg->dbgbus_dpu.cmn.enable_mask = DEFAULT_DBGBUS_DPU;
+		debugfs_create_u32(debug_name, 0600, debugfs_root,
+				&dbg->dbgbus_dpu.cmn.enable_mask);
+	}
+
+	if (dbg->dbgbus_vbif_rt.entries) {
+		dbg->dbgbus_vbif_rt.cmn.name = DBGBUS_NAME_VBIF_RT;
+		snprintf(debug_name, sizeof(debug_name), "%s_dbgbus",
+				dbg->dbgbus_vbif_rt.cmn.name);
+		dbg->dbgbus_vbif_rt.cmn.enable_mask = DEFAULT_DBGBUS_VBIFRT;
+		debugfs_create_u32(debug_name, 0600, debugfs_root,
+				&dbg->dbgbus_vbif_rt.cmn.enable_mask);
+	}
+
+	return 0;
+}
+
+static void _dpu_dbg_debugfs_destroy(void)
+{
+}
+
+void dpu_dbg_init_dbg_buses(u32 hwversion)
+{
+	static struct dpu_dbg_base *dbg = &dpu_dbg_base;
+
+	memset(&dbg->dbgbus_dpu, 0, sizeof(dbg->dbgbus_dpu));
+	memset(&dbg->dbgbus_vbif_rt, 0, sizeof(dbg->dbgbus_vbif_rt));
+
+	if (IS_MSM8998_TARGET(hwversion)) {
+		dbg->dbgbus_dpu.entries = dbg_bus_dpu_8998;
+		dbg->dbgbus_dpu.cmn.entries_size = ARRAY_SIZE(dbg_bus_dpu_8998);
+		dbg->dbgbus_dpu.cmn.flags = DBGBUS_FLAGS_DSPP;
+
+		dbg->dbgbus_vbif_rt.entries = vbif_dbg_bus_msm8998;
+		dbg->dbgbus_vbif_rt.cmn.entries_size =
+				ARRAY_SIZE(vbif_dbg_bus_msm8998);
+	} else if (IS_SDM845_TARGET(hwversion) || IS_SDM670_TARGET(hwversion)) {
+		dbg->dbgbus_dpu.entries = dbg_bus_dpu_sdm845;
+		dbg->dbgbus_dpu.cmn.entries_size =
+				ARRAY_SIZE(dbg_bus_dpu_sdm845);
+		dbg->dbgbus_dpu.cmn.flags = DBGBUS_FLAGS_DSPP;
+
+		/* vbif is unchanged vs 8998 */
+		dbg->dbgbus_vbif_rt.entries = vbif_dbg_bus_msm8998;
+		dbg->dbgbus_vbif_rt.cmn.entries_size =
+				ARRAY_SIZE(vbif_dbg_bus_msm8998);
+	} else {
+		pr_err("unsupported chipset id %X\n", hwversion);
+	}
+}
+
+int dpu_dbg_init(struct device *dev)
+{
+	if (!dev) {
+		pr_err("invalid params\n");
+		return -EINVAL;
+	}
+
+	INIT_LIST_HEAD(&dpu_dbg_base.reg_base_list);
+	dpu_dbg_base.dev = dev;
+
+	INIT_WORK(&dpu_dbg_base.dump_work, _dpu_dump_work);
+
+	return 0;
+}
+
+/**
+ * dpu_dbg_destroy - destroy dpu debug facilities
+ */
+void dpu_dbg_destroy(void)
+{
+	_dpu_dbg_debugfs_destroy();
+}
+
+void dpu_dbg_set_dpu_top_offset(u32 blk_off)
+{
+	dpu_dbg_base.dbgbus_dpu.top_blk_off = blk_off;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.h
new file mode 100644
index 000000000000..1e6fa945f98b
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.h
@@ -0,0 +1,103 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef DPU_DBG_H_
+#define DPU_DBG_H_
+
+#include <stdarg.h>
+#include <linux/debugfs.h>
+#include <linux/list.h>
+
+enum dpu_dbg_dump_flag {
+	DPU_DBG_DUMP_IN_LOG = BIT(0),
+	DPU_DBG_DUMP_IN_MEM = BIT(1),
+};
+
+#if defined(CONFIG_DEBUG_FS)
+
+/**
+ * dpu_dbg_init_dbg_buses - initialize debug bus dumping support for the chipset
+ * @hwversion:		Chipset revision
+ */
+void dpu_dbg_init_dbg_buses(u32 hwversion);
+
+/**
+ * dpu_dbg_init - initialize global dpu debug facilities: regdump
+ * @dev:		device handle
+ * Returns:		0 or -ERROR
+ */
+int dpu_dbg_init(struct device *dev);
+
+/**
+ * dpu_dbg_debugfs_register - register entries at the given debugfs dir
+ * @debugfs_root:	debugfs root in which to create dpu debug entries
+ * Returns:	0 or -ERROR
+ */
+int dpu_dbg_debugfs_register(struct dentry *debugfs_root);
+
+/**
+ * dpu_dbg_destroy - destroy the global dpu debug facilities
+ * Returns:	none
+ */
+void dpu_dbg_destroy(void);
+
+/**
+ * dpu_dbg_dump - trigger dumping of all dpu_dbg facilities
+ * @queue_work:	  whether to queue the dumping work to the work_struct
+ * @name:	  string indicating origin of dump
+ * @dump_dbgbus:  dump the dpu debug bus
+ * @dump_vbif_rt: dump the vbif rt bus
+ * Returns:	none
+ */
+void dpu_dbg_dump(bool queue_work, const char *name, bool dump_dbgbus_dpu,
+		  bool dump_dbgbus_vbif_rt);
+
+/**
+ * dpu_dbg_set_dpu_top_offset - set the target specific offset from mdss base
+ *	address of the top registers. Used for accessing debug bus controls.
+ * @blk_off: offset from mdss base of the top block
+ */
+void dpu_dbg_set_dpu_top_offset(u32 blk_off);
+
+#else
+
+static inline void dpu_dbg_init_dbg_buses(u32 hwversion)
+{
+}
+
+static inline int dpu_dbg_init(struct device *dev)
+{
+	return 0;
+}
+
+static inline int dpu_dbg_debugfs_register(struct dentry *debugfs_root)
+{
+	return 0;
+}
+
+static inline void dpu_dbg_destroy(void)
+{
+}
+
+static inline void dpu_dbg_dump(bool queue_work, const char *name,
+				bool dump_dbgbus_dpu, bool dump_dbgbus_vbif_rt)
+{
+}
+
+static inline void dpu_dbg_set_dpu_top_offset(u32 blk_off)
+{
+}
+
+#endif /* defined(CONFIG_DEBUG_FS) */
+
+
+#endif /* DPU_DBG_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
new file mode 100644
index 000000000000..0bd3eda93e22
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -0,0 +1,2498 @@
+/*
+ * Copyright (c) 2014-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include <linux/kthread.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include "msm_drv.h"
+#include "dpu_kms.h"
+#include <drm/drm_crtc.h>
+#include <drm/drm_crtc_helper.h>
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_intf.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_formats.h"
+#include "dpu_encoder_phys.h"
+#include "dpu_crtc.h"
+#include "dpu_trace.h"
+#include "dpu_core_irq.h"
+
+#define DPU_DEBUG_ENC(e, fmt, ...) DPU_DEBUG("enc%d " fmt,\
+		(e) ? (e)->base.base.id : -1, ##__VA_ARGS__)
+
+#define DPU_ERROR_ENC(e, fmt, ...) DPU_ERROR("enc%d " fmt,\
+		(e) ? (e)->base.base.id : -1, ##__VA_ARGS__)
+
+#define DPU_DEBUG_PHYS(p, fmt, ...) DPU_DEBUG("enc%d intf%d pp%d " fmt,\
+		(p) ? (p)->parent->base.id : -1, \
+		(p) ? (p)->intf_idx - INTF_0 : -1, \
+		(p) ? ((p)->hw_pp ? (p)->hw_pp->idx - PINGPONG_0 : -1) : -1, \
+		##__VA_ARGS__)
+
+#define DPU_ERROR_PHYS(p, fmt, ...) DPU_ERROR("enc%d intf%d pp%d " fmt,\
+		(p) ? (p)->parent->base.id : -1, \
+		(p) ? (p)->intf_idx - INTF_0 : -1, \
+		(p) ? ((p)->hw_pp ? (p)->hw_pp->idx - PINGPONG_0 : -1) : -1, \
+		##__VA_ARGS__)
+
+/*
+ * Two to anticipate panels that can do cmd/vid dynamic switching
+ * plan is to create all possible physical encoder types, and switch between
+ * them at runtime
+ */
+#define NUM_PHYS_ENCODER_TYPES 2
+
+#define MAX_PHYS_ENCODERS_PER_VIRTUAL \
+	(MAX_H_TILES_PER_DISPLAY * NUM_PHYS_ENCODER_TYPES)
+
+#define MAX_CHANNELS_PER_ENC 2
+
+#define MISR_BUFF_SIZE			256
+
+#define IDLE_SHORT_TIMEOUT	1
+
+#define MAX_VDISPLAY_SPLIT 1080
+
+/**
+ * enum dpu_enc_rc_events - events for resource control state machine
+ * @DPU_ENC_RC_EVENT_KICKOFF:
+ *	This event happens at NORMAL priority.
+ *	Event that signals the start of the transfer. When this event is
+ *	received, enable MDP/DSI core clocks. Regardless of the previous
+ *	state, the resource should be in ON state at the end of this event.
+ * @DPU_ENC_RC_EVENT_FRAME_DONE:
+ *	This event happens at INTERRUPT level.
+ *	Event signals the end of the data transfer after the PP FRAME_DONE
+ *	event. At the end of this event, a delayed work is scheduled to go to
+ *	IDLE_PC state after IDLE_TIMEOUT time.
+ * @DPU_ENC_RC_EVENT_PRE_STOP:
+ *	This event happens at NORMAL priority.
+ *	This event, when received during the ON state, leave the RC STATE
+ *	in the PRE_OFF state. It should be followed by the STOP event as
+ *	part of encoder disable.
+ *	If received during IDLE or OFF states, it will do nothing.
+ * @DPU_ENC_RC_EVENT_STOP:
+ *	This event happens at NORMAL priority.
+ *	When this event is received, disable all the MDP/DSI core clocks, and
+ *	disable IRQs. It should be called from the PRE_OFF or IDLE states.
+ *	IDLE is expected when IDLE_PC has run, and PRE_OFF did nothing.
+ *	PRE_OFF is expected when PRE_STOP was executed during the ON state.
+ *	Resource state should be in OFF at the end of the event.
+ * @DPU_ENC_RC_EVENT_ENTER_IDLE:
+ *	This event happens at NORMAL priority from a work item.
+ *	Event signals that there were no frame updates for IDLE_TIMEOUT time.
+ *	This would disable MDP/DSI core clocks and change the resource state
+ *	to IDLE.
+ */
+enum dpu_enc_rc_events {
+	DPU_ENC_RC_EVENT_KICKOFF = 1,
+	DPU_ENC_RC_EVENT_FRAME_DONE,
+	DPU_ENC_RC_EVENT_PRE_STOP,
+	DPU_ENC_RC_EVENT_STOP,
+	DPU_ENC_RC_EVENT_ENTER_IDLE
+};
+
+/*
+ * enum dpu_enc_rc_states - states that the resource control maintains
+ * @DPU_ENC_RC_STATE_OFF: Resource is in OFF state
+ * @DPU_ENC_RC_STATE_PRE_OFF: Resource is transitioning to OFF state
+ * @DPU_ENC_RC_STATE_ON: Resource is in ON state
+ * @DPU_ENC_RC_STATE_MODESET: Resource is in modeset state
+ * @DPU_ENC_RC_STATE_IDLE: Resource is in IDLE state
+ */
+enum dpu_enc_rc_states {
+	DPU_ENC_RC_STATE_OFF,
+	DPU_ENC_RC_STATE_PRE_OFF,
+	DPU_ENC_RC_STATE_ON,
+	DPU_ENC_RC_STATE_IDLE
+};
+
+/**
+ * struct dpu_encoder_virt - virtual encoder. Container of one or more physical
+ *	encoders. Virtual encoder manages one "logical" display. Physical
+ *	encoders manage one intf block, tied to a specific panel/sub-panel.
+ *	Virtual encoder defers as much as possible to the physical encoders.
+ *	Virtual encoder registers itself with the DRM Framework as the encoder.
+ * @base:		drm_encoder base class for registration with DRM
+ * @enc_spin_lock:	Virtual-Encoder-Wide Spin Lock for IRQ purposes
+ * @bus_scaling_client:	Client handle to the bus scaling interface
+ * @num_phys_encs:	Actual number of physical encoders contained.
+ * @phys_encs:		Container of physical encoders managed.
+ * @cur_master:		Pointer to the current master in this mode. Optimization
+ *			Only valid after enable. Cleared as disable.
+ * @hw_pp		Handle to the pingpong blocks used for the display. No.
+ *			pingpong blocks can be different than num_phys_encs.
+ * @intfs_swapped	Whether or not the phys_enc interfaces have been swapped
+ *			for partial update right-only cases, such as pingpong
+ *			split where virtual pingpong does not generate IRQs
+ * @crtc_vblank_cb:	Callback into the upper layer / CRTC for
+ *			notification of the VBLANK
+ * @crtc_vblank_cb_data:	Data from upper layer for VBLANK notification
+ * @crtc_kickoff_cb:		Callback into CRTC that will flush & start
+ *				all CTL paths
+ * @crtc_kickoff_cb_data:	Opaque user data given to crtc_kickoff_cb
+ * @debugfs_root:		Debug file system root file node
+ * @enc_lock:			Lock around physical encoder create/destroy and
+				access.
+ * @frame_busy_mask:		Bitmask tracking which phys_enc we are still
+ *				busy processing current command.
+ *				Bit0 = phys_encs[0] etc.
+ * @crtc_frame_event_cb:	callback handler for frame event
+ * @crtc_frame_event_cb_data:	callback handler private data
+ * @frame_done_timeout:		frame done timeout in Hz
+ * @frame_done_timer:		watchdog timer for frame done event
+ * @vsync_event_timer:		vsync timer
+ * @disp_info:			local copy of msm_display_info struct
+ * @misr_enable:		misr enable/disable status
+ * @misr_frame_count:		misr frame count before start capturing the data
+ * @idle_pc_supported:		indicate if idle power collaps is supported
+ * @rc_lock:			resource control mutex lock to protect
+ *				virt encoder over various state changes
+ * @rc_state:			resource controller state
+ * @delayed_off_work:		delayed worker to schedule disabling of
+ *				clks and resources after IDLE_TIMEOUT time.
+ * @vsync_event_work:		worker to handle vsync event for autorefresh
+ * @topology:                   topology of the display
+ * @mode_set_complete:          flag to indicate modeset completion
+ * @idle_timeout:		idle timeout duration in milliseconds
+ */
+struct dpu_encoder_virt {
+	struct drm_encoder base;
+	spinlock_t enc_spinlock;
+	uint32_t bus_scaling_client;
+
+	uint32_t display_num_of_h_tiles;
+
+	unsigned int num_phys_encs;
+	struct dpu_encoder_phys *phys_encs[MAX_PHYS_ENCODERS_PER_VIRTUAL];
+	struct dpu_encoder_phys *cur_master;
+	struct dpu_hw_pingpong *hw_pp[MAX_CHANNELS_PER_ENC];
+
+	bool intfs_swapped;
+
+	void (*crtc_vblank_cb)(void *);
+	void *crtc_vblank_cb_data;
+
+	struct dentry *debugfs_root;
+	struct mutex enc_lock;
+	DECLARE_BITMAP(frame_busy_mask, MAX_PHYS_ENCODERS_PER_VIRTUAL);
+	void (*crtc_frame_event_cb)(void *, u32 event);
+	void *crtc_frame_event_cb_data;
+
+	atomic_t frame_done_timeout;
+	struct timer_list frame_done_timer;
+	struct timer_list vsync_event_timer;
+
+	struct msm_display_info disp_info;
+	bool misr_enable;
+	u32 misr_frame_count;
+
+	bool idle_pc_supported;
+	struct mutex rc_lock;
+	enum dpu_enc_rc_states rc_state;
+	struct kthread_delayed_work delayed_off_work;
+	struct kthread_work vsync_event_work;
+	struct msm_display_topology topology;
+	bool mode_set_complete;
+
+	u32 idle_timeout;
+};
+
+#define to_dpu_encoder_virt(x) container_of(x, struct dpu_encoder_virt, base)
+static inline int _dpu_encoder_power_enable(struct dpu_encoder_virt *dpu_enc,
+								bool enable)
+{
+	struct drm_encoder *drm_enc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!dpu_enc) {
+		DPU_ERROR("invalid dpu enc\n");
+		return -EINVAL;
+	}
+
+	drm_enc = &dpu_enc->base;
+	if (!drm_enc->dev || !drm_enc->dev->dev_private) {
+		DPU_ERROR("drm device invalid\n");
+		return -EINVAL;
+	}
+
+	priv = drm_enc->dev->dev_private;
+	if (!priv->kms) {
+		DPU_ERROR("invalid kms\n");
+		return -EINVAL;
+	}
+
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	if (enable)
+		pm_runtime_get_sync(&dpu_kms->pdev->dev);
+	else
+		pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	return 0;
+}
+
+void dpu_encoder_helper_report_irq_timeout(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx)
+{
+	DRM_ERROR("irq timeout id=%u, intf=%d, pp=%d, intr=%d\n",
+		  DRMID(phys_enc->parent), phys_enc->intf_idx - INTF_0,
+		  phys_enc->hw_pp->idx - PINGPONG_0, intr_idx);
+
+	if (phys_enc->parent_ops->handle_frame_done)
+		phys_enc->parent_ops->handle_frame_done(
+				phys_enc->parent, phys_enc,
+				DPU_ENCODER_FRAME_EVENT_ERROR);
+}
+
+static int dpu_encoder_helper_wait_event_timeout(int32_t drm_id,
+		int32_t hw_id, struct dpu_encoder_wait_info *info);
+
+int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx,
+		struct dpu_encoder_wait_info *wait_info)
+{
+	struct dpu_encoder_irq *irq;
+	u32 irq_status;
+	int ret;
+
+	if (!phys_enc || !wait_info || intr_idx >= INTR_IDX_MAX) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+	irq = &phys_enc->irq[intr_idx];
+
+	/* note: do master / slave checking outside */
+
+	/* return EWOULDBLOCK since we know the wait isn't necessary */
+	if (phys_enc->enable_state == DPU_ENC_DISABLED) {
+		DRM_ERROR("encoder is disabled id=%u, intr=%d, hw=%d, irq=%d",
+			  DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+			  irq->irq_idx);
+		return -EWOULDBLOCK;
+	}
+
+	if (irq->irq_idx < 0) {
+		DRM_DEBUG_KMS("skip irq wait id=%u, intr=%d, hw=%d, irq=%s",
+			      DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+			      irq->name);
+		return 0;
+	}
+
+	DRM_DEBUG_KMS("id=%u, intr=%d, hw=%d, irq=%d, pp=%d, pending_cnt=%d",
+		      DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+		      irq->irq_idx, phys_enc->hw_pp->idx - PINGPONG_0,
+		      atomic_read(wait_info->atomic_cnt));
+
+	ret = dpu_encoder_helper_wait_event_timeout(
+			DRMID(phys_enc->parent),
+			irq->hw_idx,
+			wait_info);
+
+	if (ret <= 0) {
+		irq_status = dpu_core_irq_read(phys_enc->dpu_kms,
+				irq->irq_idx, true);
+		if (irq_status) {
+			unsigned long flags;
+
+			DRM_DEBUG_KMS("irq not triggered id=%u, intr=%d, "
+				      "hw=%d, irq=%d, pp=%d, atomic_cnt=%d",
+				      DRMID(phys_enc->parent), intr_idx,
+				      irq->hw_idx, irq->irq_idx,
+				      phys_enc->hw_pp->idx - PINGPONG_0,
+				      atomic_read(wait_info->atomic_cnt));
+			local_irq_save(flags);
+			irq->cb.func(phys_enc, irq->irq_idx);
+			local_irq_restore(flags);
+			ret = 0;
+		} else {
+			ret = -ETIMEDOUT;
+			DRM_DEBUG_KMS("irq timeout id=%u, intr=%d, "
+				      "hw=%d, irq=%d, pp=%d, atomic_cnt=%d",
+				      DRMID(phys_enc->parent), intr_idx,
+				      irq->hw_idx, irq->irq_idx,
+				      phys_enc->hw_pp->idx - PINGPONG_0,
+				      atomic_read(wait_info->atomic_cnt));
+		}
+	} else {
+		ret = 0;
+		trace_dpu_enc_irq_wait_success(DRMID(phys_enc->parent),
+			intr_idx, irq->hw_idx, irq->irq_idx,
+			phys_enc->hw_pp->idx - PINGPONG_0,
+			atomic_read(wait_info->atomic_cnt));
+	}
+
+	return ret;
+}
+
+int dpu_encoder_helper_register_irq(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx)
+{
+	struct dpu_encoder_irq *irq;
+	int ret = 0;
+
+	if (!phys_enc || intr_idx >= INTR_IDX_MAX) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+	irq = &phys_enc->irq[intr_idx];
+
+	if (irq->irq_idx >= 0) {
+		DPU_DEBUG_PHYS(phys_enc,
+				"skipping already registered irq %s type %d\n",
+				irq->name, irq->intr_type);
+		return 0;
+	}
+
+	irq->irq_idx = dpu_core_irq_idx_lookup(phys_enc->dpu_kms,
+			irq->intr_type, irq->hw_idx);
+	if (irq->irq_idx < 0) {
+		DPU_ERROR_PHYS(phys_enc,
+			"failed to lookup IRQ index for %s type:%d\n",
+			irq->name, irq->intr_type);
+		return -EINVAL;
+	}
+
+	ret = dpu_core_irq_register_callback(phys_enc->dpu_kms, irq->irq_idx,
+			&irq->cb);
+	if (ret) {
+		DPU_ERROR_PHYS(phys_enc,
+			"failed to register IRQ callback for %s\n",
+			irq->name);
+		irq->irq_idx = -EINVAL;
+		return ret;
+	}
+
+	ret = dpu_core_irq_enable(phys_enc->dpu_kms, &irq->irq_idx, 1);
+	if (ret) {
+		DRM_ERROR("enable failed id=%u, intr=%d, hw=%d, irq=%d",
+			  DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+			  irq->irq_idx);
+		dpu_core_irq_unregister_callback(phys_enc->dpu_kms,
+				irq->irq_idx, &irq->cb);
+		irq->irq_idx = -EINVAL;
+		return ret;
+	}
+
+	trace_dpu_enc_irq_register_success(DRMID(phys_enc->parent), intr_idx,
+				irq->hw_idx, irq->irq_idx);
+
+	return ret;
+}
+
+int dpu_encoder_helper_unregister_irq(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx)
+{
+	struct dpu_encoder_irq *irq;
+	int ret;
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return -EINVAL;
+	}
+	irq = &phys_enc->irq[intr_idx];
+
+	/* silently skip irqs that weren't registered */
+	if (irq->irq_idx < 0) {
+		DRM_ERROR("duplicate unregister id=%u, intr=%d, hw=%d, irq=%d",
+			  DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+			  irq->irq_idx);
+		return 0;
+	}
+
+	ret = dpu_core_irq_disable(phys_enc->dpu_kms, &irq->irq_idx, 1);
+	if (ret) {
+		DRM_ERROR("diable failed id=%u, intr=%d, hw=%d, irq=%d ret=%d",
+			  DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+			  irq->irq_idx, ret);
+	}
+
+	ret = dpu_core_irq_unregister_callback(phys_enc->dpu_kms, irq->irq_idx,
+			&irq->cb);
+	if (ret) {
+		DRM_ERROR("unreg cb fail id=%u, intr=%d, hw=%d, irq=%d ret=%d",
+			  DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+			  irq->irq_idx, ret);
+	}
+
+	trace_dpu_enc_irq_unregister_success(DRMID(phys_enc->parent), intr_idx,
+					     irq->hw_idx, irq->irq_idx);
+
+	irq->irq_idx = -EINVAL;
+
+	return 0;
+}
+
+void dpu_encoder_get_hw_resources(struct drm_encoder *drm_enc,
+		struct dpu_encoder_hw_resources *hw_res,
+		struct drm_connector_state *conn_state)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i = 0;
+
+	if (!hw_res || !drm_enc || !conn_state) {
+		DPU_ERROR("invalid argument(s), drm_enc %d, res %d, state %d\n",
+				drm_enc != 0, hw_res != 0, conn_state != 0);
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	/* Query resources used by phys encs, expected to be without overlap */
+	memset(hw_res, 0, sizeof(*hw_res));
+	hw_res->display_num_of_h_tiles = dpu_enc->display_num_of_h_tiles;
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys && phys->ops.get_hw_resources)
+			phys->ops.get_hw_resources(phys, hw_res, conn_state);
+	}
+}
+
+static void dpu_encoder_destroy(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i = 0;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	mutex_lock(&dpu_enc->enc_lock);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys && phys->ops.destroy) {
+			phys->ops.destroy(phys);
+			--dpu_enc->num_phys_encs;
+			dpu_enc->phys_encs[i] = NULL;
+		}
+	}
+
+	if (dpu_enc->num_phys_encs)
+		DPU_ERROR_ENC(dpu_enc, "expected 0 num_phys_encs not %d\n",
+				dpu_enc->num_phys_encs);
+	dpu_enc->num_phys_encs = 0;
+	mutex_unlock(&dpu_enc->enc_lock);
+
+	drm_encoder_cleanup(drm_enc);
+	mutex_destroy(&dpu_enc->enc_lock);
+
+	kfree(dpu_enc);
+}
+
+void dpu_encoder_helper_split_config(
+		struct dpu_encoder_phys *phys_enc,
+		enum dpu_intf interface)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct split_pipe_cfg cfg = { 0 };
+	struct dpu_hw_mdp *hw_mdptop;
+	struct msm_display_info *disp_info;
+
+	if (!phys_enc || !phys_enc->hw_mdptop || !phys_enc->parent) {
+		DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != 0);
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(phys_enc->parent);
+	hw_mdptop = phys_enc->hw_mdptop;
+	disp_info = &dpu_enc->disp_info;
+
+	if (disp_info->intf_type != DRM_MODE_CONNECTOR_DSI)
+		return;
+
+	/**
+	 * disable split modes since encoder will be operating in as the only
+	 * encoder, either for the entire use case in the case of, for example,
+	 * single DSI, or for this frame in the case of left/right only partial
+	 * update.
+	 */
+	if (phys_enc->split_role == ENC_ROLE_SOLO) {
+		if (hw_mdptop->ops.setup_split_pipe)
+			hw_mdptop->ops.setup_split_pipe(hw_mdptop, &cfg);
+		return;
+	}
+
+	cfg.en = true;
+	cfg.mode = phys_enc->intf_mode;
+	cfg.intf = interface;
+
+	if (cfg.en && phys_enc->ops.needs_single_flush &&
+			phys_enc->ops.needs_single_flush(phys_enc))
+		cfg.split_flush_en = true;
+
+	if (phys_enc->split_role == ENC_ROLE_MASTER) {
+		DPU_DEBUG_ENC(dpu_enc, "enable %d\n", cfg.en);
+
+		if (hw_mdptop->ops.setup_split_pipe)
+			hw_mdptop->ops.setup_split_pipe(hw_mdptop, &cfg);
+	}
+}
+
+static void _dpu_encoder_adjust_mode(struct drm_connector *connector,
+		struct drm_display_mode *adj_mode)
+{
+	struct drm_display_mode *cur_mode;
+
+	if (!connector || !adj_mode)
+		return;
+
+	list_for_each_entry(cur_mode, &connector->modes, head) {
+		if (cur_mode->vdisplay == adj_mode->vdisplay &&
+			cur_mode->hdisplay == adj_mode->hdisplay &&
+			cur_mode->vrefresh == adj_mode->vrefresh) {
+			adj_mode->private = cur_mode->private;
+			adj_mode->private_flags |= cur_mode->private_flags;
+		}
+	}
+}
+
+static struct msm_display_topology dpu_encoder_get_topology(
+			struct dpu_encoder_virt *dpu_enc,
+			struct dpu_kms *dpu_kms,
+			struct drm_display_mode *mode)
+{
+	struct msm_display_topology topology;
+	int i, intf_count = 0;
+
+	for (i = 0; i < MAX_PHYS_ENCODERS_PER_VIRTUAL; i++)
+		if (dpu_enc->phys_encs[i])
+			intf_count++;
+
+	/* User split topology for width > 1080 */
+	topology.num_lm = (mode->vdisplay > MAX_VDISPLAY_SPLIT) ? 2 : 1;
+	topology.num_enc = 0;
+	topology.num_intf = intf_count;
+
+	return topology;
+}
+static int dpu_encoder_virt_atomic_check(
+		struct drm_encoder *drm_enc,
+		struct drm_crtc_state *crtc_state,
+		struct drm_connector_state *conn_state)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	const struct drm_display_mode *mode;
+	struct drm_display_mode *adj_mode;
+	struct msm_display_topology topology;
+	int i = 0;
+	int ret = 0;
+
+	if (!drm_enc || !crtc_state || !conn_state) {
+		DPU_ERROR("invalid arg(s), drm_enc %d, crtc/conn state %d/%d\n",
+				drm_enc != 0, crtc_state != 0, conn_state != 0);
+		return -EINVAL;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+	mode = &crtc_state->mode;
+	adj_mode = &crtc_state->adjusted_mode;
+	trace_dpu_enc_atomic_check(DRMID(drm_enc));
+
+	/*
+	 * display drivers may populate private fields of the drm display mode
+	 * structure while registering possible modes of a connector with DRM.
+	 * These private fields are not populated back while DRM invokes
+	 * the mode_set callbacks. This module retrieves and populates the
+	 * private fields of the given mode.
+	 */
+	_dpu_encoder_adjust_mode(conn_state->connector, adj_mode);
+
+	/* perform atomic check on the first physical encoder (master) */
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys && phys->ops.atomic_check)
+			ret = phys->ops.atomic_check(phys, crtc_state,
+					conn_state);
+		else if (phys && phys->ops.mode_fixup)
+			if (!phys->ops.mode_fixup(phys, mode, adj_mode))
+				ret = -EINVAL;
+
+		if (ret) {
+			DPU_ERROR_ENC(dpu_enc,
+					"mode unsupported, phys idx %d\n", i);
+			break;
+		}
+	}
+
+	topology = dpu_encoder_get_topology(dpu_enc, dpu_kms, adj_mode);
+
+	/* Reserve dynamic resources now. Indicating AtomicTest phase */
+	if (!ret) {
+		/*
+		 * Avoid reserving resources when mode set is pending. Topology
+		 * info may not be available to complete reservation.
+		 */
+		if (drm_atomic_crtc_needs_modeset(crtc_state)
+				&& dpu_enc->mode_set_complete) {
+			ret = dpu_rm_reserve(&dpu_kms->rm, drm_enc, crtc_state,
+				conn_state, topology, true);
+			dpu_enc->mode_set_complete = false;
+		}
+	}
+
+	if (!ret)
+		drm_mode_set_crtcinfo(adj_mode, 0);
+
+	trace_dpu_enc_atomic_check_flags(DRMID(drm_enc), adj_mode->flags,
+			adj_mode->private_flags);
+
+	return ret;
+}
+
+static void _dpu_encoder_update_vsync_source(struct dpu_encoder_virt *dpu_enc,
+			struct msm_display_info *disp_info)
+{
+	struct dpu_vsync_source_cfg vsync_cfg = { 0 };
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	struct dpu_hw_mdp *hw_mdptop;
+	struct drm_encoder *drm_enc;
+	int i;
+
+	if (!dpu_enc || !disp_info) {
+		DPU_ERROR("invalid param dpu_enc:%d or disp_info:%d\n",
+					dpu_enc != NULL, disp_info != NULL);
+		return;
+	} else if (dpu_enc->num_phys_encs > ARRAY_SIZE(dpu_enc->hw_pp)) {
+		DPU_ERROR("invalid num phys enc %d/%d\n",
+				dpu_enc->num_phys_encs,
+				(int) ARRAY_SIZE(dpu_enc->hw_pp));
+		return;
+	}
+
+	drm_enc = &dpu_enc->base;
+	/* this pointers are checked in virt_enable_helper */
+	priv = drm_enc->dev->dev_private;
+
+	dpu_kms = to_dpu_kms(priv->kms);
+	if (!dpu_kms) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return;
+	}
+
+	hw_mdptop = dpu_kms->hw_mdp;
+	if (!hw_mdptop) {
+		DPU_ERROR("invalid mdptop\n");
+		return;
+	}
+
+	if (hw_mdptop->ops.setup_vsync_source &&
+			disp_info->capabilities & MSM_DISPLAY_CAP_CMD_MODE) {
+		for (i = 0; i < dpu_enc->num_phys_encs; i++)
+			vsync_cfg.ppnumber[i] = dpu_enc->hw_pp[i]->idx;
+
+		vsync_cfg.pp_count = dpu_enc->num_phys_encs;
+		if (disp_info->is_te_using_watchdog_timer)
+			vsync_cfg.vsync_source = DPU_VSYNC_SOURCE_WD_TIMER_0;
+		else
+			vsync_cfg.vsync_source = DPU_VSYNC0_SOURCE_GPIO;
+
+		hw_mdptop->ops.setup_vsync_source(hw_mdptop, &vsync_cfg);
+	}
+}
+
+static void _dpu_encoder_irq_control(struct drm_encoder *drm_enc, bool enable)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	int i;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	DPU_DEBUG_ENC(dpu_enc, "enable:%d\n", enable);
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys && phys->ops.irq_control)
+			phys->ops.irq_control(phys, enable);
+	}
+
+}
+
+static void _dpu_encoder_resource_control_helper(struct drm_encoder *drm_enc,
+		bool enable)
+{
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	struct dpu_encoder_virt *dpu_enc;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	trace_dpu_enc_rc_helper(DRMID(drm_enc), enable);
+
+	if (!dpu_enc->cur_master) {
+		DPU_ERROR("encoder master not set\n");
+		return;
+	}
+
+	if (enable) {
+		/* enable DPU core clks */
+		pm_runtime_get_sync(&dpu_kms->pdev->dev);
+
+		/* enable all the irq */
+		_dpu_encoder_irq_control(drm_enc, true);
+
+	} else {
+		/* disable all the irq */
+		_dpu_encoder_irq_control(drm_enc, false);
+
+		/* disable DPU core clks */
+		pm_runtime_put_sync(&dpu_kms->pdev->dev);
+	}
+
+}
+
+static int dpu_encoder_resource_control(struct drm_encoder *drm_enc,
+		u32 sw_event)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct msm_drm_private *priv;
+	struct msm_drm_thread *disp_thread;
+	bool is_vid_mode = false;
+
+	if (!drm_enc || !drm_enc->dev || !drm_enc->dev->dev_private ||
+			!drm_enc->crtc) {
+		DPU_ERROR("invalid parameters\n");
+		return -EINVAL;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	priv = drm_enc->dev->dev_private;
+	is_vid_mode = dpu_enc->disp_info.capabilities &
+						MSM_DISPLAY_CAP_VID_MODE;
+
+	if (drm_enc->crtc->index >= ARRAY_SIZE(priv->disp_thread)) {
+		DPU_ERROR("invalid crtc index\n");
+		return -EINVAL;
+	}
+	disp_thread = &priv->disp_thread[drm_enc->crtc->index];
+
+	/*
+	 * when idle_pc is not supported, process only KICKOFF, STOP and MODESET
+	 * events and return early for other events (ie wb display).
+	 */
+	if (!dpu_enc->idle_pc_supported &&
+			(sw_event != DPU_ENC_RC_EVENT_KICKOFF &&
+			sw_event != DPU_ENC_RC_EVENT_STOP &&
+			sw_event != DPU_ENC_RC_EVENT_PRE_STOP))
+		return 0;
+
+	trace_dpu_enc_rc(DRMID(drm_enc), sw_event, dpu_enc->idle_pc_supported,
+			 dpu_enc->rc_state, "begin");
+
+	switch (sw_event) {
+	case DPU_ENC_RC_EVENT_KICKOFF:
+		/* cancel delayed off work, if any */
+		if (kthread_cancel_delayed_work_sync(
+				&dpu_enc->delayed_off_work))
+			DPU_DEBUG_ENC(dpu_enc, "sw_event:%d, work cancelled\n",
+					sw_event);
+
+		mutex_lock(&dpu_enc->rc_lock);
+
+		/* return if the resource control is already in ON state */
+		if (dpu_enc->rc_state == DPU_ENC_RC_STATE_ON) {
+			DRM_DEBUG_KMS("id;%u, sw_event:%d, rc in ON state\n",
+				      DRMID(drm_enc), sw_event);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		} else if (dpu_enc->rc_state != DPU_ENC_RC_STATE_OFF &&
+				dpu_enc->rc_state != DPU_ENC_RC_STATE_IDLE) {
+			DRM_DEBUG_KMS("id;%u, sw_event:%d, rc in state %d\n",
+				      DRMID(drm_enc), sw_event,
+				      dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return -EINVAL;
+		}
+
+		if (is_vid_mode && dpu_enc->rc_state == DPU_ENC_RC_STATE_IDLE)
+			_dpu_encoder_irq_control(drm_enc, true);
+		else
+			_dpu_encoder_resource_control_helper(drm_enc, true);
+
+		dpu_enc->rc_state = DPU_ENC_RC_STATE_ON;
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "kickoff");
+
+		mutex_unlock(&dpu_enc->rc_lock);
+		break;
+
+	case DPU_ENC_RC_EVENT_FRAME_DONE:
+		/*
+		 * mutex lock is not used as this event happens at interrupt
+		 * context. And locking is not required as, the other events
+		 * like KICKOFF and STOP does a wait-for-idle before executing
+		 * the resource_control
+		 */
+		if (dpu_enc->rc_state != DPU_ENC_RC_STATE_ON) {
+			DRM_DEBUG_KMS("id:%d, sw_event:%d,rc:%d-unexpected\n",
+				      DRMID(drm_enc), sw_event,
+				      dpu_enc->rc_state);
+			return -EINVAL;
+		}
+
+		/*
+		 * schedule off work item only when there are no
+		 * frames pending
+		 */
+		if (dpu_crtc_frame_pending(drm_enc->crtc) > 1) {
+			DRM_DEBUG_KMS("id:%d skip schedule work\n",
+				      DRMID(drm_enc));
+			return 0;
+		}
+
+		kthread_queue_delayed_work(
+			&disp_thread->worker,
+			&dpu_enc->delayed_off_work,
+			msecs_to_jiffies(dpu_enc->idle_timeout));
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "frame done");
+		break;
+
+	case DPU_ENC_RC_EVENT_PRE_STOP:
+		/* cancel delayed off work, if any */
+		if (kthread_cancel_delayed_work_sync(
+				&dpu_enc->delayed_off_work))
+			DPU_DEBUG_ENC(dpu_enc, "sw_event:%d, work cancelled\n",
+					sw_event);
+
+		mutex_lock(&dpu_enc->rc_lock);
+
+		if (is_vid_mode &&
+			  dpu_enc->rc_state == DPU_ENC_RC_STATE_IDLE) {
+			_dpu_encoder_irq_control(drm_enc, true);
+		}
+		/* skip if is already OFF or IDLE, resources are off already */
+		else if (dpu_enc->rc_state == DPU_ENC_RC_STATE_OFF ||
+				dpu_enc->rc_state == DPU_ENC_RC_STATE_IDLE) {
+			DRM_DEBUG_KMS("id:%u, sw_event:%d, rc in %d state\n",
+				      DRMID(drm_enc), sw_event,
+				      dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		}
+
+		dpu_enc->rc_state = DPU_ENC_RC_STATE_PRE_OFF;
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "pre stop");
+
+		mutex_unlock(&dpu_enc->rc_lock);
+		break;
+
+	case DPU_ENC_RC_EVENT_STOP:
+		mutex_lock(&dpu_enc->rc_lock);
+
+		/* return if the resource control is already in OFF state */
+		if (dpu_enc->rc_state == DPU_ENC_RC_STATE_OFF) {
+			DRM_DEBUG_KMS("id: %u, sw_event:%d, rc in OFF state\n",
+				      DRMID(drm_enc), sw_event);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		} else if (dpu_enc->rc_state == DPU_ENC_RC_STATE_ON) {
+			DRM_ERROR("id: %u, sw_event:%d, rc in state %d\n",
+				  DRMID(drm_enc), sw_event, dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return -EINVAL;
+		}
+
+		/**
+		 * expect to arrive here only if in either idle state or pre-off
+		 * and in IDLE state the resources are already disabled
+		 */
+		if (dpu_enc->rc_state == DPU_ENC_RC_STATE_PRE_OFF)
+			_dpu_encoder_resource_control_helper(drm_enc, false);
+
+		dpu_enc->rc_state = DPU_ENC_RC_STATE_OFF;
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "stop");
+
+		mutex_unlock(&dpu_enc->rc_lock);
+		break;
+
+	case DPU_ENC_RC_EVENT_ENTER_IDLE:
+		mutex_lock(&dpu_enc->rc_lock);
+
+		if (dpu_enc->rc_state != DPU_ENC_RC_STATE_ON) {
+			DRM_ERROR("id: %u, sw_event:%d, rc:%d !ON state\n",
+				  DRMID(drm_enc), sw_event, dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		}
+
+		/*
+		 * if we are in ON but a frame was just kicked off,
+		 * ignore the IDLE event, it's probably a stale timer event
+		 */
+		if (dpu_enc->frame_busy_mask[0]) {
+			DRM_ERROR("id:%u, sw_event:%d, rc:%d frame pending\n",
+				  DRMID(drm_enc), sw_event, dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		}
+
+		if (is_vid_mode)
+			_dpu_encoder_irq_control(drm_enc, false);
+		else
+			_dpu_encoder_resource_control_helper(drm_enc, false);
+
+		dpu_enc->rc_state = DPU_ENC_RC_STATE_IDLE;
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "idle");
+
+		mutex_unlock(&dpu_enc->rc_lock);
+		break;
+
+	default:
+		DRM_ERROR("id:%u, unexpected sw_event: %d\n", DRMID(drm_enc),
+			  sw_event);
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "error");
+		break;
+	}
+
+	trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+			 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+			 "end");
+	return 0;
+}
+
+static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc,
+				      struct drm_display_mode *mode,
+				      struct drm_display_mode *adj_mode)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	struct list_head *connector_list;
+	struct drm_connector *conn = NULL, *conn_iter;
+	struct dpu_rm_hw_iter pp_iter;
+	struct msm_display_topology topology;
+	enum dpu_rm_topology_name topology_name;
+	int i = 0, ret;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+	connector_list = &dpu_kms->dev->mode_config.connector_list;
+
+	trace_dpu_enc_mode_set(DRMID(drm_enc));
+
+	list_for_each_entry(conn_iter, connector_list, head)
+		if (conn_iter->encoder == drm_enc)
+			conn = conn_iter;
+
+	if (!conn) {
+		DPU_ERROR_ENC(dpu_enc, "failed to find attached connector\n");
+		return;
+	} else if (!conn->state) {
+		DPU_ERROR_ENC(dpu_enc, "invalid connector state\n");
+		return;
+	}
+
+	topology = dpu_encoder_get_topology(dpu_enc, dpu_kms, adj_mode);
+
+	/* Reserve dynamic resources now. Indicating non-AtomicTest phase */
+	ret = dpu_rm_reserve(&dpu_kms->rm, drm_enc, drm_enc->crtc->state,
+			conn->state, topology, false);
+	if (ret) {
+		DPU_ERROR_ENC(dpu_enc,
+				"failed to reserve hw resources, %d\n", ret);
+		return;
+	}
+
+	dpu_rm_init_hw_iter(&pp_iter, drm_enc->base.id, DPU_HW_BLK_PINGPONG);
+	for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) {
+		dpu_enc->hw_pp[i] = NULL;
+		if (!dpu_rm_get_hw(&dpu_kms->rm, &pp_iter))
+			break;
+		dpu_enc->hw_pp[i] = (struct dpu_hw_pingpong *) pp_iter.hw;
+	}
+
+	topology_name = dpu_rm_get_topology_name(topology);
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys) {
+			if (!dpu_enc->hw_pp[i]) {
+				DPU_ERROR_ENC(dpu_enc,
+				    "invalid pingpong block for the encoder\n");
+				return;
+			}
+			phys->hw_pp = dpu_enc->hw_pp[i];
+			phys->connector = conn->state->connector;
+			phys->topology_name = topology_name;
+			if (phys->ops.mode_set)
+				phys->ops.mode_set(phys, mode, adj_mode);
+		}
+	}
+
+	dpu_enc->mode_set_complete = true;
+}
+
+static void _dpu_encoder_virt_enable_helper(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!drm_enc || !drm_enc->dev || !drm_enc->dev->dev_private) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+	if (!dpu_kms) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	if (!dpu_enc || !dpu_enc->cur_master) {
+		DPU_ERROR("invalid dpu encoder/master\n");
+		return;
+	}
+
+	if (dpu_enc->disp_info.intf_type == DRM_MODE_CONNECTOR_DisplayPort &&
+	    dpu_enc->cur_master->hw_mdptop &&
+	    dpu_enc->cur_master->hw_mdptop->ops.intf_audio_select)
+		dpu_enc->cur_master->hw_mdptop->ops.intf_audio_select(
+					dpu_enc->cur_master->hw_mdptop);
+
+	if (dpu_enc->cur_master->hw_mdptop &&
+			dpu_enc->cur_master->hw_mdptop->ops.reset_ubwc)
+		dpu_enc->cur_master->hw_mdptop->ops.reset_ubwc(
+				dpu_enc->cur_master->hw_mdptop,
+				dpu_kms->catalog);
+
+	_dpu_encoder_update_vsync_source(dpu_enc, &dpu_enc->disp_info);
+}
+
+void dpu_encoder_virt_restore(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys && (phys != dpu_enc->cur_master) && phys->ops.restore)
+			phys->ops.restore(phys);
+	}
+
+	if (dpu_enc->cur_master && dpu_enc->cur_master->ops.restore)
+		dpu_enc->cur_master->ops.restore(dpu_enc->cur_master);
+
+	_dpu_encoder_virt_enable_helper(drm_enc);
+}
+
+static void dpu_encoder_virt_enable(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i, ret = 0;
+	struct drm_display_mode *cur_mode = NULL;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	cur_mode = &dpu_enc->base.crtc->state->adjusted_mode;
+
+	trace_dpu_enc_enable(DRMID(drm_enc), cur_mode->hdisplay,
+			     cur_mode->vdisplay);
+
+	dpu_enc->cur_master = NULL;
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys && phys->ops.is_master && phys->ops.is_master(phys)) {
+			DPU_DEBUG_ENC(dpu_enc, "master is now idx %d\n", i);
+			dpu_enc->cur_master = phys;
+			break;
+		}
+	}
+
+	if (!dpu_enc->cur_master) {
+		DPU_ERROR("virt encoder has no master! num_phys %d\n", i);
+		return;
+	}
+
+	ret = dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_KICKOFF);
+	if (ret) {
+		DPU_ERROR_ENC(dpu_enc, "dpu resource control failed: %d\n",
+				ret);
+		return;
+	}
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (!phys)
+			continue;
+
+		if (phys != dpu_enc->cur_master) {
+			if (phys->ops.enable)
+				phys->ops.enable(phys);
+		}
+
+		if (dpu_enc->misr_enable && (dpu_enc->disp_info.capabilities &
+		     MSM_DISPLAY_CAP_VID_MODE) && phys->ops.setup_misr)
+			phys->ops.setup_misr(phys, true,
+						dpu_enc->misr_frame_count);
+	}
+
+	if (dpu_enc->cur_master->ops.enable)
+		dpu_enc->cur_master->ops.enable(dpu_enc->cur_master);
+
+	_dpu_encoder_virt_enable_helper(drm_enc);
+}
+
+static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	struct drm_display_mode *mode;
+	int i = 0;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	} else if (!drm_enc->dev) {
+		DPU_ERROR("invalid dev\n");
+		return;
+	} else if (!drm_enc->dev->dev_private) {
+		DPU_ERROR("invalid dev_private\n");
+		return;
+	}
+
+	mode = &drm_enc->crtc->state->adjusted_mode;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	trace_dpu_enc_disable(DRMID(drm_enc));
+
+	/* wait for idle */
+	dpu_encoder_wait_for_event(drm_enc, MSM_ENC_TX_COMPLETE);
+
+	dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_PRE_STOP);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys && phys->ops.disable)
+			phys->ops.disable(phys);
+	}
+
+	/* after phys waits for frame-done, should be no more frames pending */
+	if (atomic_xchg(&dpu_enc->frame_done_timeout, 0)) {
+		DPU_ERROR("enc%d timeout pending\n", drm_enc->base.id);
+		del_timer_sync(&dpu_enc->frame_done_timer);
+	}
+
+	dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_STOP);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		if (dpu_enc->phys_encs[i])
+			dpu_enc->phys_encs[i]->connector = NULL;
+	}
+
+	dpu_enc->cur_master = NULL;
+
+	DPU_DEBUG_ENC(dpu_enc, "encoder disabled\n");
+
+	dpu_rm_release(&dpu_kms->rm, drm_enc);
+}
+
+static enum dpu_intf dpu_encoder_get_intf(struct dpu_mdss_cfg *catalog,
+		enum dpu_intf_type type, u32 controller_id)
+{
+	int i = 0;
+
+	for (i = 0; i < catalog->intf_count; i++) {
+		if (catalog->intf[i].type == type
+		    && catalog->intf[i].controller_id == controller_id) {
+			return catalog->intf[i].id;
+		}
+	}
+
+	return INTF_MAX;
+}
+
+static void dpu_encoder_vblank_callback(struct drm_encoder *drm_enc,
+		struct dpu_encoder_phys *phy_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	unsigned long lock_flags;
+
+	if (!drm_enc || !phy_enc)
+		return;
+
+	DPU_ATRACE_BEGIN("encoder_vblank_callback");
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
+	if (dpu_enc->crtc_vblank_cb)
+		dpu_enc->crtc_vblank_cb(dpu_enc->crtc_vblank_cb_data);
+	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+
+	atomic_inc(&phy_enc->vsync_cnt);
+	DPU_ATRACE_END("encoder_vblank_callback");
+}
+
+static void dpu_encoder_underrun_callback(struct drm_encoder *drm_enc,
+		struct dpu_encoder_phys *phy_enc)
+{
+	if (!phy_enc)
+		return;
+
+	DPU_ATRACE_BEGIN("encoder_underrun_callback");
+	atomic_inc(&phy_enc->underrun_cnt);
+	trace_dpu_enc_underrun_cb(DRMID(drm_enc),
+				  atomic_read(&phy_enc->underrun_cnt));
+	DPU_ATRACE_END("encoder_underrun_callback");
+}
+
+void dpu_encoder_register_vblank_callback(struct drm_encoder *drm_enc,
+		void (*vbl_cb)(void *), void *vbl_data)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+	unsigned long lock_flags;
+	bool enable;
+	int i;
+
+	enable = vbl_cb ? true : false;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	trace_dpu_enc_vblank_cb(DRMID(drm_enc), enable);
+
+	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
+	dpu_enc->crtc_vblank_cb = vbl_cb;
+	dpu_enc->crtc_vblank_cb_data = vbl_data;
+	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys && phys->ops.control_vblank_irq)
+			phys->ops.control_vblank_irq(phys, enable);
+	}
+}
+
+void dpu_encoder_register_frame_event_callback(struct drm_encoder *drm_enc,
+		void (*frame_event_cb)(void *, u32 event),
+		void *frame_event_cb_data)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+	unsigned long lock_flags;
+	bool enable;
+
+	enable = frame_event_cb ? true : false;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	trace_dpu_enc_frame_event_cb(DRMID(drm_enc), enable);
+
+	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
+	dpu_enc->crtc_frame_event_cb = frame_event_cb;
+	dpu_enc->crtc_frame_event_cb_data = frame_event_cb_data;
+	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+}
+
+static void dpu_encoder_frame_done_callback(
+		struct drm_encoder *drm_enc,
+		struct dpu_encoder_phys *ready_phys, u32 event)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+	unsigned int i;
+
+	if (event & (DPU_ENCODER_FRAME_EVENT_DONE
+			| DPU_ENCODER_FRAME_EVENT_ERROR
+			| DPU_ENCODER_FRAME_EVENT_PANEL_DEAD)) {
+
+		if (!dpu_enc->frame_busy_mask[0]) {
+			/**
+			 * suppress frame_done without waiter,
+			 * likely autorefresh
+			 */
+			trace_dpu_enc_frame_done_cb_not_busy(DRMID(drm_enc),
+					event, ready_phys->intf_idx);
+			return;
+		}
+
+		/* One of the physical encoders has become idle */
+		for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+			if (dpu_enc->phys_encs[i] == ready_phys) {
+				clear_bit(i, dpu_enc->frame_busy_mask);
+				trace_dpu_enc_frame_done_cb(DRMID(drm_enc), i,
+						dpu_enc->frame_busy_mask[0]);
+			}
+		}
+
+		if (!dpu_enc->frame_busy_mask[0]) {
+			atomic_set(&dpu_enc->frame_done_timeout, 0);
+			del_timer(&dpu_enc->frame_done_timer);
+
+			dpu_encoder_resource_control(drm_enc,
+					DPU_ENC_RC_EVENT_FRAME_DONE);
+
+			if (dpu_enc->crtc_frame_event_cb)
+				dpu_enc->crtc_frame_event_cb(
+					dpu_enc->crtc_frame_event_cb_data,
+					event);
+		}
+	} else {
+		if (dpu_enc->crtc_frame_event_cb)
+			dpu_enc->crtc_frame_event_cb(
+				dpu_enc->crtc_frame_event_cb_data, event);
+	}
+}
+
+static void dpu_encoder_off_work(struct kthread_work *work)
+{
+	struct dpu_encoder_virt *dpu_enc = container_of(work,
+			struct dpu_encoder_virt, delayed_off_work.work);
+
+	if (!dpu_enc) {
+		DPU_ERROR("invalid dpu encoder\n");
+		return;
+	}
+
+	dpu_encoder_resource_control(&dpu_enc->base,
+						DPU_ENC_RC_EVENT_ENTER_IDLE);
+
+	dpu_encoder_frame_done_callback(&dpu_enc->base, NULL,
+				DPU_ENCODER_FRAME_EVENT_IDLE);
+}
+
+/**
+ * _dpu_encoder_trigger_flush - trigger flush for a physical encoder
+ * drm_enc: Pointer to drm encoder structure
+ * phys: Pointer to physical encoder structure
+ * extra_flush_bits: Additional bit mask to include in flush trigger
+ */
+static inline void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc,
+		struct dpu_encoder_phys *phys, uint32_t extra_flush_bits)
+{
+	struct dpu_hw_ctl *ctl;
+	int pending_kickoff_cnt;
+	u32 ret = UINT_MAX;
+
+	if (!drm_enc || !phys) {
+		DPU_ERROR("invalid argument(s), drm_enc %d, phys_enc %d\n",
+				drm_enc != 0, phys != 0);
+		return;
+	}
+
+	if (!phys->hw_pp) {
+		DPU_ERROR("invalid pingpong hw\n");
+		return;
+	}
+
+	ctl = phys->hw_ctl;
+	if (!ctl || !ctl->ops.trigger_flush) {
+		DPU_ERROR("missing trigger cb\n");
+		return;
+	}
+
+	pending_kickoff_cnt = dpu_encoder_phys_inc_pending(phys);
+
+	if (extra_flush_bits && ctl->ops.update_pending_flush)
+		ctl->ops.update_pending_flush(ctl, extra_flush_bits);
+
+	ctl->ops.trigger_flush(ctl);
+
+	if (ctl->ops.get_pending_flush)
+		ret = ctl->ops.get_pending_flush(ctl);
+
+	trace_dpu_enc_trigger_flush(DRMID(drm_enc), phys->intf_idx,
+				    pending_kickoff_cnt, ctl->idx, ret);
+}
+
+/**
+ * _dpu_encoder_trigger_start - trigger start for a physical encoder
+ * phys: Pointer to physical encoder structure
+ */
+static inline void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys)
+{
+	if (!phys) {
+		DPU_ERROR("invalid argument(s)\n");
+		return;
+	}
+
+	if (!phys->hw_pp) {
+		DPU_ERROR("invalid pingpong hw\n");
+		return;
+	}
+
+	if (phys->ops.trigger_start && phys->enable_state != DPU_ENC_DISABLED)
+		phys->ops.trigger_start(phys);
+}
+
+void dpu_encoder_helper_trigger_start(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_ctl *ctl;
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	ctl = phys_enc->hw_ctl;
+	if (ctl && ctl->ops.trigger_start) {
+		ctl->ops.trigger_start(ctl);
+		trace_dpu_enc_trigger_start(DRMID(phys_enc->parent), ctl->idx);
+	}
+}
+
+static int dpu_encoder_helper_wait_event_timeout(
+		int32_t drm_id,
+		int32_t hw_id,
+		struct dpu_encoder_wait_info *info)
+{
+	int rc = 0;
+	s64 expected_time = ktime_to_ms(ktime_get()) + info->timeout_ms;
+	s64 jiffies = msecs_to_jiffies(info->timeout_ms);
+	s64 time;
+
+	do {
+		rc = wait_event_timeout(*(info->wq),
+				atomic_read(info->atomic_cnt) == 0, jiffies);
+		time = ktime_to_ms(ktime_get());
+
+		trace_dpu_enc_wait_event_timeout(drm_id, hw_id, rc, time,
+						 expected_time,
+						 atomic_read(info->atomic_cnt));
+	/* If we timed out, counter is valid and time is less, wait again */
+	} while (atomic_read(info->atomic_cnt) && (rc == 0) &&
+			(time < expected_time));
+
+	return rc;
+}
+
+void dpu_encoder_helper_hw_reset(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_hw_ctl *ctl;
+	int rc;
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	dpu_enc = to_dpu_encoder_virt(phys_enc->parent);
+	ctl = phys_enc->hw_ctl;
+
+	if (!ctl || !ctl->ops.reset)
+		return;
+
+	DRM_DEBUG_KMS("id:%u ctl %d reset\n", DRMID(phys_enc->parent),
+		      ctl->idx);
+
+	rc = ctl->ops.reset(ctl);
+	if (rc) {
+		DPU_ERROR_ENC(dpu_enc, "ctl %d reset failure\n",  ctl->idx);
+		dpu_dbg_dump(false, __func__, true, true);
+	}
+
+	phys_enc->enable_state = DPU_ENC_ENABLED;
+}
+
+/**
+ * _dpu_encoder_kickoff_phys - handle physical encoder kickoff
+ *	Iterate through the physical encoders and perform consolidated flush
+ *	and/or control start triggering as needed. This is done in the virtual
+ *	encoder rather than the individual physical ones in order to handle
+ *	use cases that require visibility into multiple physical encoders at
+ *	a time.
+ * dpu_enc: Pointer to virtual encoder structure
+ */
+static void _dpu_encoder_kickoff_phys(struct dpu_encoder_virt *dpu_enc)
+{
+	struct dpu_hw_ctl *ctl;
+	uint32_t i, pending_flush;
+	unsigned long lock_flags;
+
+	if (!dpu_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	pending_flush = 0x0;
+
+	/* update pending counts and trigger kickoff ctl flush atomically */
+	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
+
+	/* don't perform flush/start operations for slave encoders */
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (!phys || phys->enable_state == DPU_ENC_DISABLED)
+			continue;
+
+		ctl = phys->hw_ctl;
+		if (!ctl)
+			continue;
+
+		if (phys->split_role != ENC_ROLE_SLAVE)
+			set_bit(i, dpu_enc->frame_busy_mask);
+		if (!phys->ops.needs_single_flush ||
+				!phys->ops.needs_single_flush(phys))
+			_dpu_encoder_trigger_flush(&dpu_enc->base, phys, 0x0);
+		else if (ctl->ops.get_pending_flush)
+			pending_flush |= ctl->ops.get_pending_flush(ctl);
+	}
+
+	/* for split flush, combine pending flush masks and send to master */
+	if (pending_flush && dpu_enc->cur_master) {
+		_dpu_encoder_trigger_flush(
+				&dpu_enc->base,
+				dpu_enc->cur_master,
+				pending_flush);
+	}
+
+	_dpu_encoder_trigger_start(dpu_enc->cur_master);
+
+	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+}
+
+void dpu_encoder_trigger_kickoff_pending(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_phys *phys;
+	unsigned int i;
+	struct dpu_hw_ctl *ctl;
+	struct msm_display_info *disp_info;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	disp_info = &dpu_enc->disp_info;
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		phys = dpu_enc->phys_encs[i];
+
+		if (phys && phys->hw_ctl) {
+			ctl = phys->hw_ctl;
+			if (ctl->ops.clear_pending_flush)
+				ctl->ops.clear_pending_flush(ctl);
+
+			/* update only for command mode primary ctl */
+			if ((phys == dpu_enc->cur_master) &&
+			   (disp_info->capabilities & MSM_DISPLAY_CAP_CMD_MODE)
+			    && ctl->ops.trigger_pending)
+				ctl->ops.trigger_pending(ctl);
+		}
+	}
+}
+
+static u32 _dpu_encoder_calculate_linetime(struct dpu_encoder_virt *dpu_enc,
+		struct drm_display_mode *mode)
+{
+	u64 pclk_rate;
+	u32 pclk_period;
+	u32 line_time;
+
+	/*
+	 * For linetime calculation, only operate on master encoder.
+	 */
+	if (!dpu_enc->cur_master)
+		return 0;
+
+	if (!dpu_enc->cur_master->ops.get_line_count) {
+		DPU_ERROR("get_line_count function not defined\n");
+		return 0;
+	}
+
+	pclk_rate = mode->clock; /* pixel clock in kHz */
+	if (pclk_rate == 0) {
+		DPU_ERROR("pclk is 0, cannot calculate line time\n");
+		return 0;
+	}
+
+	pclk_period = DIV_ROUND_UP_ULL(1000000000ull, pclk_rate);
+	if (pclk_period == 0) {
+		DPU_ERROR("pclk period is 0\n");
+		return 0;
+	}
+
+	/*
+	 * Line time calculation based on Pixel clock and HTOTAL.
+	 * Final unit is in ns.
+	 */
+	line_time = (pclk_period * mode->htotal) / 1000;
+	if (line_time == 0) {
+		DPU_ERROR("line time calculation is 0\n");
+		return 0;
+	}
+
+	DPU_DEBUG_ENC(dpu_enc,
+			"clk_rate=%lldkHz, clk_period=%d, linetime=%dns\n",
+			pclk_rate, pclk_period, line_time);
+
+	return line_time;
+}
+
+static int _dpu_encoder_wakeup_time(struct drm_encoder *drm_enc,
+		ktime_t *wakeup_time)
+{
+	struct drm_display_mode *mode;
+	struct dpu_encoder_virt *dpu_enc;
+	u32 cur_line;
+	u32 line_time;
+	u32 vtotal, time_to_vsync;
+	ktime_t cur_time;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	if (!drm_enc->crtc || !drm_enc->crtc->state) {
+		DPU_ERROR("crtc/crtc state object is NULL\n");
+		return -EINVAL;
+	}
+	mode = &drm_enc->crtc->state->adjusted_mode;
+
+	line_time = _dpu_encoder_calculate_linetime(dpu_enc, mode);
+	if (!line_time)
+		return -EINVAL;
+
+	cur_line = dpu_enc->cur_master->ops.get_line_count(dpu_enc->cur_master);
+
+	vtotal = mode->vtotal;
+	if (cur_line >= vtotal)
+		time_to_vsync = line_time * vtotal;
+	else
+		time_to_vsync = line_time * (vtotal - cur_line);
+
+	if (time_to_vsync == 0) {
+		DPU_ERROR("time to vsync should not be zero, vtotal=%d\n",
+				vtotal);
+		return -EINVAL;
+	}
+
+	cur_time = ktime_get();
+	*wakeup_time = ktime_add_ns(cur_time, time_to_vsync);
+
+	DPU_DEBUG_ENC(dpu_enc,
+			"cur_line=%u vtotal=%u time_to_vsync=%u, cur_time=%lld, wakeup_time=%lld\n",
+			cur_line, vtotal, time_to_vsync,
+			ktime_to_ms(cur_time),
+			ktime_to_ms(*wakeup_time));
+	return 0;
+}
+
+static void dpu_encoder_vsync_event_handler(struct timer_list *t)
+{
+	struct dpu_encoder_virt *dpu_enc = from_timer(dpu_enc, t,
+			vsync_event_timer);
+	struct drm_encoder *drm_enc = &dpu_enc->base;
+	struct msm_drm_private *priv;
+	struct msm_drm_thread *event_thread;
+
+	if (!drm_enc->dev || !drm_enc->dev->dev_private ||
+			!drm_enc->crtc) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	priv = drm_enc->dev->dev_private;
+
+	if (drm_enc->crtc->index >= ARRAY_SIZE(priv->event_thread)) {
+		DPU_ERROR("invalid crtc index\n");
+		return;
+	}
+	event_thread = &priv->event_thread[drm_enc->crtc->index];
+	if (!event_thread) {
+		DPU_ERROR("event_thread not found for crtc:%d\n",
+				drm_enc->crtc->index);
+		return;
+	}
+
+	del_timer(&dpu_enc->vsync_event_timer);
+}
+
+static void dpu_encoder_vsync_event_work_handler(struct kthread_work *work)
+{
+	struct dpu_encoder_virt *dpu_enc = container_of(work,
+			struct dpu_encoder_virt, vsync_event_work);
+	ktime_t wakeup_time;
+
+	if (!dpu_enc) {
+		DPU_ERROR("invalid dpu encoder\n");
+		return;
+	}
+
+	if (_dpu_encoder_wakeup_time(&dpu_enc->base, &wakeup_time))
+		return;
+
+	trace_dpu_enc_vsync_event_work(DRMID(&dpu_enc->base), wakeup_time);
+	mod_timer(&dpu_enc->vsync_event_timer,
+			nsecs_to_jiffies(ktime_to_ns(wakeup_time)));
+}
+
+void dpu_encoder_prepare_for_kickoff(struct drm_encoder *drm_enc,
+		struct dpu_encoder_kickoff_params *params)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_phys *phys;
+	bool needs_hw_reset = false;
+	unsigned int i;
+
+	if (!drm_enc || !params) {
+		DPU_ERROR("invalid args\n");
+		return;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	trace_dpu_enc_prepare_kickoff(DRMID(drm_enc));
+
+	/* prepare for next kickoff, may include waiting on previous kickoff */
+	DPU_ATRACE_BEGIN("enc_prepare_for_kickoff");
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		phys = dpu_enc->phys_encs[i];
+		if (phys) {
+			if (phys->ops.prepare_for_kickoff)
+				phys->ops.prepare_for_kickoff(phys, params);
+			if (phys->enable_state == DPU_ENC_ERR_NEEDS_HW_RESET)
+				needs_hw_reset = true;
+		}
+	}
+	DPU_ATRACE_END("enc_prepare_for_kickoff");
+
+	dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_KICKOFF);
+
+	/* if any phys needs reset, reset all phys, in-order */
+	if (needs_hw_reset) {
+		trace_dpu_enc_prepare_kickoff_reset(DRMID(drm_enc));
+		for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+			phys = dpu_enc->phys_encs[i];
+			if (phys && phys->ops.hw_reset)
+				phys->ops.hw_reset(phys);
+		}
+	}
+}
+
+void dpu_encoder_kickoff(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_phys *phys;
+	ktime_t wakeup_time;
+	unsigned int i;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	DPU_ATRACE_BEGIN("encoder_kickoff");
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	trace_dpu_enc_kickoff(DRMID(drm_enc));
+
+	atomic_set(&dpu_enc->frame_done_timeout,
+			DPU_FRAME_DONE_TIMEOUT * 1000 /
+			drm_enc->crtc->state->adjusted_mode.vrefresh);
+	mod_timer(&dpu_enc->frame_done_timer, jiffies +
+		((atomic_read(&dpu_enc->frame_done_timeout) * HZ) / 1000));
+
+	/* All phys encs are ready to go, trigger the kickoff */
+	_dpu_encoder_kickoff_phys(dpu_enc);
+
+	/* allow phys encs to handle any post-kickoff business */
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		phys = dpu_enc->phys_encs[i];
+		if (phys && phys->ops.handle_post_kickoff)
+			phys->ops.handle_post_kickoff(phys);
+	}
+
+	if (dpu_enc->disp_info.intf_type == DRM_MODE_CONNECTOR_DSI &&
+			!_dpu_encoder_wakeup_time(drm_enc, &wakeup_time)) {
+		trace_dpu_enc_early_kickoff(DRMID(drm_enc),
+					    ktime_to_ms(wakeup_time));
+		mod_timer(&dpu_enc->vsync_event_timer,
+				nsecs_to_jiffies(ktime_to_ns(wakeup_time)));
+	}
+
+	DPU_ATRACE_END("encoder_kickoff");
+}
+
+void dpu_encoder_prepare_commit(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_phys *phys;
+	int i;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		phys = dpu_enc->phys_encs[i];
+		if (phys && phys->ops.prepare_commit)
+			phys->ops.prepare_commit(phys);
+	}
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int _dpu_encoder_status_show(struct seq_file *s, void *data)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	int i;
+
+	if (!s || !s->private)
+		return -EINVAL;
+
+	dpu_enc = s->private;
+
+	mutex_lock(&dpu_enc->enc_lock);
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (!phys)
+			continue;
+
+		seq_printf(s, "intf:%d    vsync:%8d     underrun:%8d    ",
+				phys->intf_idx - INTF_0,
+				atomic_read(&phys->vsync_cnt),
+				atomic_read(&phys->underrun_cnt));
+
+		switch (phys->intf_mode) {
+		case INTF_MODE_VIDEO:
+			seq_puts(s, "mode: video\n");
+			break;
+		case INTF_MODE_CMD:
+			seq_puts(s, "mode: command\n");
+			break;
+		default:
+			seq_puts(s, "mode: ???\n");
+			break;
+		}
+	}
+	mutex_unlock(&dpu_enc->enc_lock);
+
+	return 0;
+}
+
+static int _dpu_encoder_debugfs_status_open(struct inode *inode,
+		struct file *file)
+{
+	return single_open(file, _dpu_encoder_status_show, inode->i_private);
+}
+
+static ssize_t _dpu_encoder_misr_setup(struct file *file,
+		const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	int i = 0, rc;
+	char buf[MISR_BUFF_SIZE + 1];
+	size_t buff_copy;
+	u32 frame_count, enable;
+
+	if (!file || !file->private_data)
+		return -EINVAL;
+
+	dpu_enc = file->private_data;
+
+	buff_copy = min_t(size_t, count, MISR_BUFF_SIZE);
+	if (copy_from_user(buf, user_buf, buff_copy))
+		return -EINVAL;
+
+	buf[buff_copy] = 0; /* end of string */
+
+	if (sscanf(buf, "%u %u", &enable, &frame_count) != 2)
+		return -EINVAL;
+
+	rc = _dpu_encoder_power_enable(dpu_enc, true);
+	if (rc)
+		return rc;
+
+	mutex_lock(&dpu_enc->enc_lock);
+	dpu_enc->misr_enable = enable;
+	dpu_enc->misr_frame_count = frame_count;
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (!phys || !phys->ops.setup_misr)
+			continue;
+
+		phys->ops.setup_misr(phys, enable, frame_count);
+	}
+	mutex_unlock(&dpu_enc->enc_lock);
+	_dpu_encoder_power_enable(dpu_enc, false);
+
+	return count;
+}
+
+static ssize_t _dpu_encoder_misr_read(struct file *file,
+		char __user *user_buff, size_t count, loff_t *ppos)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	int i = 0, len = 0;
+	char buf[MISR_BUFF_SIZE + 1] = {'\0'};
+	int rc;
+
+	if (*ppos)
+		return 0;
+
+	if (!file || !file->private_data)
+		return -EINVAL;
+
+	dpu_enc = file->private_data;
+
+	rc = _dpu_encoder_power_enable(dpu_enc, true);
+	if (rc)
+		return rc;
+
+	mutex_lock(&dpu_enc->enc_lock);
+	if (!dpu_enc->misr_enable) {
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len,
+			"disabled\n");
+		goto buff_check;
+	} else if (dpu_enc->disp_info.capabilities &
+						~MSM_DISPLAY_CAP_VID_MODE) {
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len,
+			"unsupported\n");
+		goto buff_check;
+	}
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (!phys || !phys->ops.collect_misr)
+			continue;
+
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len,
+			"Intf idx:%d\n", phys->intf_idx - INTF_0);
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len, "0x%x\n",
+					phys->ops.collect_misr(phys));
+	}
+
+buff_check:
+	if (count <= len) {
+		len = 0;
+		goto end;
+	}
+
+	if (copy_to_user(user_buff, buf, len)) {
+		len = -EFAULT;
+		goto end;
+	}
+
+	*ppos += len;   /* increase offset */
+
+end:
+	mutex_unlock(&dpu_enc->enc_lock);
+	_dpu_encoder_power_enable(dpu_enc, false);
+	return len;
+}
+
+static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	int i;
+
+	static const struct file_operations debugfs_status_fops = {
+		.open =		_dpu_encoder_debugfs_status_open,
+		.read =		seq_read,
+		.llseek =	seq_lseek,
+		.release =	single_release,
+	};
+
+	static const struct file_operations debugfs_misr_fops = {
+		.open = simple_open,
+		.read = _dpu_encoder_misr_read,
+		.write = _dpu_encoder_misr_setup,
+	};
+
+	char name[DPU_NAME_SIZE];
+
+	if (!drm_enc || !drm_enc->dev || !drm_enc->dev->dev_private) {
+		DPU_ERROR("invalid encoder or kms\n");
+		return -EINVAL;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	snprintf(name, DPU_NAME_SIZE, "encoder%u", drm_enc->base.id);
+
+	/* create overall sub-directory for the encoder */
+	dpu_enc->debugfs_root = debugfs_create_dir(name,
+			drm_enc->dev->primary->debugfs_root);
+	if (!dpu_enc->debugfs_root)
+		return -ENOMEM;
+
+	/* don't error check these */
+	debugfs_create_file("status", 0600,
+		dpu_enc->debugfs_root, dpu_enc, &debugfs_status_fops);
+
+	debugfs_create_file("misr_data", 0600,
+		dpu_enc->debugfs_root, dpu_enc, &debugfs_misr_fops);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++)
+		if (dpu_enc->phys_encs[i] &&
+				dpu_enc->phys_encs[i]->ops.late_register)
+			dpu_enc->phys_encs[i]->ops.late_register(
+					dpu_enc->phys_encs[i],
+					dpu_enc->debugfs_root);
+
+	return 0;
+}
+
+static void _dpu_encoder_destroy_debugfs(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+
+	if (!drm_enc)
+		return;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	debugfs_remove_recursive(dpu_enc->debugfs_root);
+}
+#else
+static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
+{
+	return 0;
+}
+
+static void _dpu_encoder_destroy_debugfs(struct drm_encoder *drm_enc)
+{
+}
+#endif
+
+static int dpu_encoder_late_register(struct drm_encoder *encoder)
+{
+	return _dpu_encoder_init_debugfs(encoder);
+}
+
+static void dpu_encoder_early_unregister(struct drm_encoder *encoder)
+{
+	_dpu_encoder_destroy_debugfs(encoder);
+}
+
+static int dpu_encoder_virt_add_phys_encs(
+		u32 display_caps,
+		struct dpu_encoder_virt *dpu_enc,
+		struct dpu_enc_phys_init_params *params)
+{
+	struct dpu_encoder_phys *enc = NULL;
+
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	/*
+	 * We may create up to NUM_PHYS_ENCODER_TYPES physical encoder types
+	 * in this function, check up-front.
+	 */
+	if (dpu_enc->num_phys_encs + NUM_PHYS_ENCODER_TYPES >=
+			ARRAY_SIZE(dpu_enc->phys_encs)) {
+		DPU_ERROR_ENC(dpu_enc, "too many physical encoders %d\n",
+			  dpu_enc->num_phys_encs);
+		return -EINVAL;
+	}
+
+	if (display_caps & MSM_DISPLAY_CAP_VID_MODE) {
+		enc = dpu_encoder_phys_vid_init(params);
+
+		if (IS_ERR_OR_NULL(enc)) {
+			DPU_ERROR_ENC(dpu_enc, "failed to init vid enc: %ld\n",
+				PTR_ERR(enc));
+			return enc == 0 ? -EINVAL : PTR_ERR(enc);
+		}
+
+		dpu_enc->phys_encs[dpu_enc->num_phys_encs] = enc;
+		++dpu_enc->num_phys_encs;
+	}
+
+	if (display_caps & MSM_DISPLAY_CAP_CMD_MODE) {
+		enc = dpu_encoder_phys_cmd_init(params);
+
+		if (IS_ERR_OR_NULL(enc)) {
+			DPU_ERROR_ENC(dpu_enc, "failed to init cmd enc: %ld\n",
+				PTR_ERR(enc));
+			return enc == 0 ? -EINVAL : PTR_ERR(enc);
+		}
+
+		dpu_enc->phys_encs[dpu_enc->num_phys_encs] = enc;
+		++dpu_enc->num_phys_encs;
+	}
+
+	return 0;
+}
+
+static const struct dpu_encoder_virt_ops dpu_encoder_parent_ops = {
+	.handle_vblank_virt = dpu_encoder_vblank_callback,
+	.handle_underrun_virt = dpu_encoder_underrun_callback,
+	.handle_frame_done = dpu_encoder_frame_done_callback,
+};
+
+static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc,
+				 struct dpu_kms *dpu_kms,
+				 struct msm_display_info *disp_info,
+				 int *drm_enc_mode)
+{
+	int ret = 0;
+	int i = 0;
+	enum dpu_intf_type intf_type;
+	struct dpu_enc_phys_init_params phys_params;
+
+	if (!dpu_enc || !dpu_kms) {
+		DPU_ERROR("invalid arg(s), enc %d kms %d\n",
+				dpu_enc != 0, dpu_kms != 0);
+		return -EINVAL;
+	}
+
+	memset(&phys_params, 0, sizeof(phys_params));
+	phys_params.dpu_kms = dpu_kms;
+	phys_params.parent = &dpu_enc->base;
+	phys_params.parent_ops = &dpu_encoder_parent_ops;
+	phys_params.enc_spinlock = &dpu_enc->enc_spinlock;
+
+	DPU_DEBUG("\n");
+
+	if (disp_info->intf_type == DRM_MODE_CONNECTOR_DSI) {
+		*drm_enc_mode = DRM_MODE_ENCODER_DSI;
+		intf_type = INTF_DSI;
+	} else if (disp_info->intf_type == DRM_MODE_CONNECTOR_HDMIA) {
+		*drm_enc_mode = DRM_MODE_ENCODER_TMDS;
+		intf_type = INTF_HDMI;
+	} else if (disp_info->intf_type == DRM_MODE_CONNECTOR_DisplayPort) {
+		*drm_enc_mode = DRM_MODE_ENCODER_TMDS;
+		intf_type = INTF_DP;
+	} else {
+		DPU_ERROR_ENC(dpu_enc, "unsupported display interface type\n");
+		return -EINVAL;
+	}
+
+	WARN_ON(disp_info->num_of_h_tiles < 1);
+
+	dpu_enc->display_num_of_h_tiles = disp_info->num_of_h_tiles;
+
+	DPU_DEBUG("dsi_info->num_of_h_tiles %d\n", disp_info->num_of_h_tiles);
+
+	if ((disp_info->capabilities & MSM_DISPLAY_CAP_CMD_MODE) ||
+	    (disp_info->capabilities & MSM_DISPLAY_CAP_VID_MODE))
+		dpu_enc->idle_pc_supported =
+				dpu_kms->catalog->caps->has_idle_pc;
+
+	mutex_lock(&dpu_enc->enc_lock);
+	for (i = 0; i < disp_info->num_of_h_tiles && !ret; i++) {
+		/*
+		 * Left-most tile is at index 0, content is controller id
+		 * h_tile_instance_ids[2] = {0, 1}; DSI0 = left, DSI1 = right
+		 * h_tile_instance_ids[2] = {1, 0}; DSI1 = left, DSI0 = right
+		 */
+		u32 controller_id = disp_info->h_tile_instance[i];
+
+		if (disp_info->num_of_h_tiles > 1) {
+			if (i == 0)
+				phys_params.split_role = ENC_ROLE_MASTER;
+			else
+				phys_params.split_role = ENC_ROLE_SLAVE;
+		} else {
+			phys_params.split_role = ENC_ROLE_SOLO;
+		}
+
+		DPU_DEBUG("h_tile_instance %d = %d, split_role %d\n",
+				i, controller_id, phys_params.split_role);
+
+		phys_params.intf_idx = dpu_encoder_get_intf(dpu_kms->catalog,
+													intf_type,
+													controller_id);
+		if (phys_params.intf_idx == INTF_MAX) {
+			DPU_ERROR_ENC(dpu_enc, "could not get intf: type %d, id %d\n",
+						  intf_type, controller_id);
+			ret = -EINVAL;
+		}
+
+		if (!ret) {
+			ret = dpu_encoder_virt_add_phys_encs(disp_info->capabilities,
+												 dpu_enc,
+												 &phys_params);
+			if (ret)
+				DPU_ERROR_ENC(dpu_enc, "failed to add phys encs\n");
+		}
+	}
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys) {
+			atomic_set(&phys->vsync_cnt, 0);
+			atomic_set(&phys->underrun_cnt, 0);
+		}
+	}
+	mutex_unlock(&dpu_enc->enc_lock);
+
+	return ret;
+}
+
+static void dpu_encoder_frame_done_timeout(struct timer_list *t)
+{
+	struct dpu_encoder_virt *dpu_enc = from_timer(dpu_enc, t,
+			frame_done_timer);
+	struct drm_encoder *drm_enc = &dpu_enc->base;
+	struct msm_drm_private *priv;
+	u32 event;
+
+	if (!drm_enc->dev || !drm_enc->dev->dev_private) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+	priv = drm_enc->dev->dev_private;
+
+	if (!dpu_enc->frame_busy_mask[0] || !dpu_enc->crtc_frame_event_cb) {
+		DRM_DEBUG_KMS("id:%u invalid timeout frame_busy_mask=%lu\n",
+			      DRMID(drm_enc), dpu_enc->frame_busy_mask[0]);
+		return;
+	} else if (!atomic_xchg(&dpu_enc->frame_done_timeout, 0)) {
+		DRM_DEBUG_KMS("id:%u invalid timeout\n", DRMID(drm_enc));
+		return;
+	}
+
+	DPU_ERROR_ENC(dpu_enc, "frame done timeout\n");
+
+	event = DPU_ENCODER_FRAME_EVENT_ERROR;
+	trace_dpu_enc_frame_done_timeout(DRMID(drm_enc), event);
+	dpu_enc->crtc_frame_event_cb(dpu_enc->crtc_frame_event_cb_data, event);
+}
+
+static const struct drm_encoder_helper_funcs dpu_encoder_helper_funcs = {
+	.mode_set = dpu_encoder_virt_mode_set,
+	.disable = dpu_encoder_virt_disable,
+	.enable = dpu_kms_encoder_enable,
+	.atomic_check = dpu_encoder_virt_atomic_check,
+
+	/* This is called by dpu_kms_encoder_enable */
+	.commit = dpu_encoder_virt_enable,
+};
+
+static const struct drm_encoder_funcs dpu_encoder_funcs = {
+		.destroy = dpu_encoder_destroy,
+		.late_register = dpu_encoder_late_register,
+		.early_unregister = dpu_encoder_early_unregister,
+};
+
+int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc,
+		struct msm_display_info *disp_info)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms);
+	struct drm_encoder *drm_enc = NULL;
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int drm_enc_mode = DRM_MODE_ENCODER_NONE;
+	int ret = 0;
+
+	dpu_enc = to_dpu_encoder_virt(enc);
+
+	mutex_init(&dpu_enc->enc_lock);
+	ret = dpu_encoder_setup_display(dpu_enc, dpu_kms, disp_info,
+			&drm_enc_mode);
+	if (ret)
+		goto fail;
+
+	dpu_enc->cur_master = NULL;
+	spin_lock_init(&dpu_enc->enc_spinlock);
+
+	atomic_set(&dpu_enc->frame_done_timeout, 0);
+	timer_setup(&dpu_enc->frame_done_timer,
+			dpu_encoder_frame_done_timeout, 0);
+
+	if (disp_info->intf_type == DRM_MODE_CONNECTOR_DSI)
+		timer_setup(&dpu_enc->vsync_event_timer,
+				dpu_encoder_vsync_event_handler,
+				0);
+
+
+	mutex_init(&dpu_enc->rc_lock);
+	kthread_init_delayed_work(&dpu_enc->delayed_off_work,
+			dpu_encoder_off_work);
+	dpu_enc->idle_timeout = IDLE_TIMEOUT;
+
+	kthread_init_work(&dpu_enc->vsync_event_work,
+			dpu_encoder_vsync_event_work_handler);
+
+	memcpy(&dpu_enc->disp_info, disp_info, sizeof(*disp_info));
+
+	DPU_DEBUG_ENC(dpu_enc, "created\n");
+
+	return ret;
+
+fail:
+	DPU_ERROR("failed to create encoder\n");
+	if (drm_enc)
+		dpu_encoder_destroy(drm_enc);
+
+	return ret;
+
+
+}
+
+struct drm_encoder *dpu_encoder_init(struct drm_device *dev,
+		int drm_enc_mode)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int rc = 0;
+
+	dpu_enc = devm_kzalloc(dev->dev, sizeof(*dpu_enc), GFP_KERNEL);
+	if (!dpu_enc)
+		return ERR_PTR(ENOMEM);
+
+	rc = drm_encoder_init(dev, &dpu_enc->base, &dpu_encoder_funcs,
+			drm_enc_mode, NULL);
+	if (rc) {
+		devm_kfree(dev->dev, dpu_enc);
+		return ERR_PTR(rc);
+	}
+
+	drm_encoder_helper_add(&dpu_enc->base, &dpu_encoder_helper_funcs);
+
+	return &dpu_enc->base;
+}
+
+int dpu_encoder_wait_for_event(struct drm_encoder *drm_enc,
+	enum msm_event_wait event)
+{
+	int (*fn_wait)(struct dpu_encoder_phys *phys_enc) = NULL;
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i, ret = 0;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return -EINVAL;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		switch (event) {
+		case MSM_ENC_COMMIT_DONE:
+			fn_wait = phys->ops.wait_for_commit_done;
+			break;
+		case MSM_ENC_TX_COMPLETE:
+			fn_wait = phys->ops.wait_for_tx_complete;
+			break;
+		case MSM_ENC_VBLANK:
+			fn_wait = phys->ops.wait_for_vblank;
+			break;
+		default:
+			DPU_ERROR_ENC(dpu_enc, "unknown wait event %d\n",
+					event);
+			return -EINVAL;
+		};
+
+		if (phys && fn_wait) {
+			DPU_ATRACE_BEGIN("wait_for_completion_event");
+			ret = fn_wait(phys);
+			DPU_ATRACE_END("wait_for_completion_event");
+			if (ret)
+				return ret;
+		}
+	}
+
+	return ret;
+}
+
+enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i;
+
+	if (!encoder) {
+		DPU_ERROR("invalid encoder\n");
+		return INTF_MODE_NONE;
+	}
+	dpu_enc = to_dpu_encoder_virt(encoder);
+
+	if (dpu_enc->cur_master)
+		return dpu_enc->cur_master->intf_mode;
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys)
+			return phys->intf_mode;
+	}
+
+	return INTF_MODE_NONE;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h
new file mode 100644
index 000000000000..60f809fc7c13
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h
@@ -0,0 +1,177 @@
+/*
+ * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __DPU_ENCODER_H__
+#define __DPU_ENCODER_H__
+
+#include <drm/drm_crtc.h>
+#include "dpu_hw_mdss.h"
+
+#define DPU_ENCODER_FRAME_EVENT_DONE			BIT(0)
+#define DPU_ENCODER_FRAME_EVENT_ERROR			BIT(1)
+#define DPU_ENCODER_FRAME_EVENT_PANEL_DEAD		BIT(2)
+#define DPU_ENCODER_FRAME_EVENT_IDLE			BIT(3)
+
+#define IDLE_TIMEOUT	(66 - 16/2)
+
+/**
+ * Encoder functions and data types
+ * @intfs:	Interfaces this encoder is using, INTF_MODE_NONE if unused
+ * @needs_cdm:	Encoder requests a CDM based on pixel format conversion needs
+ * @display_num_of_h_tiles: Number of horizontal tiles in case of split
+ *                          interface
+ * @topology:   Topology of the display
+ */
+struct dpu_encoder_hw_resources {
+	enum dpu_intf_mode intfs[INTF_MAX];
+	bool needs_cdm;
+	u32 display_num_of_h_tiles;
+};
+
+/**
+ * dpu_encoder_kickoff_params - info encoder requires at kickoff
+ * @affected_displays:  bitmask, bit set means the ROI of the commit lies within
+ *                      the bounds of the physical display at the bit index
+ */
+struct dpu_encoder_kickoff_params {
+	unsigned long affected_displays;
+};
+
+/**
+ * dpu_encoder_get_hw_resources - Populate table of required hardware resources
+ * @encoder:	encoder pointer
+ * @hw_res:	resource table to populate with encoder required resources
+ * @conn_state:	report hw reqs based on this proposed connector state
+ */
+void dpu_encoder_get_hw_resources(struct drm_encoder *encoder,
+		struct dpu_encoder_hw_resources *hw_res,
+		struct drm_connector_state *conn_state);
+
+/**
+ * dpu_encoder_register_vblank_callback - provide callback to encoder that
+ *	will be called on the next vblank.
+ * @encoder:	encoder pointer
+ * @cb:		callback pointer, provide NULL to deregister and disable IRQs
+ * @data:	user data provided to callback
+ */
+void dpu_encoder_register_vblank_callback(struct drm_encoder *encoder,
+		void (*cb)(void *), void *data);
+
+/**
+ * dpu_encoder_register_frame_event_callback - provide callback to encoder that
+ *	will be called after the request is complete, or other events.
+ * @encoder:	encoder pointer
+ * @cb:		callback pointer, provide NULL to deregister
+ * @data:	user data provided to callback
+ */
+void dpu_encoder_register_frame_event_callback(struct drm_encoder *encoder,
+		void (*cb)(void *, u32), void *data);
+
+/**
+ * dpu_encoder_prepare_for_kickoff - schedule double buffer flip of the ctl
+ *	path (i.e. ctl flush and start) at next appropriate time.
+ *	Immediately: if no previous commit is outstanding.
+ *	Delayed: Block until next trigger can be issued.
+ * @encoder:	encoder pointer
+ * @params:	kickoff time parameters
+ */
+void dpu_encoder_prepare_for_kickoff(struct drm_encoder *encoder,
+		struct dpu_encoder_kickoff_params *params);
+
+/**
+ * dpu_encoder_trigger_kickoff_pending - Clear the flush bits from previous
+ *        kickoff and trigger the ctl prepare progress for command mode display.
+ * @encoder:	encoder pointer
+ */
+void dpu_encoder_trigger_kickoff_pending(struct drm_encoder *encoder);
+
+/**
+ * dpu_encoder_kickoff - trigger a double buffer flip of the ctl path
+ *	(i.e. ctl flush and start) immediately.
+ * @encoder:	encoder pointer
+ */
+void dpu_encoder_kickoff(struct drm_encoder *encoder);
+
+/**
+ * dpu_encoder_wait_for_event - Waits for encoder events
+ * @encoder:	encoder pointer
+ * @event:      event to wait for
+ * MSM_ENC_COMMIT_DONE -  Wait for hardware to have flushed the current pending
+ *                        frames to hardware at a vblank or ctl_start
+ *                        Encoders will map this differently depending on the
+ *                        panel type.
+ *	                  vid mode -> vsync_irq
+ *                        cmd mode -> ctl_start
+ * MSM_ENC_TX_COMPLETE -  Wait for the hardware to transfer all the pixels to
+ *                        the panel. Encoders will map this differently
+ *                        depending on the panel type.
+ *                        vid mode -> vsync_irq
+ *                        cmd mode -> pp_done
+ * Returns: 0 on success, -EWOULDBLOCK if already signaled, error otherwise
+ */
+int dpu_encoder_wait_for_event(struct drm_encoder *drm_encoder,
+						enum msm_event_wait event);
+
+/*
+ * dpu_encoder_get_intf_mode - get interface mode of the given encoder
+ * @encoder: Pointer to drm encoder object
+ */
+enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder);
+
+/**
+ * dpu_encoder_virt_restore - restore the encoder configs
+ * @encoder:	encoder pointer
+ */
+void dpu_encoder_virt_restore(struct drm_encoder *encoder);
+
+/**
+ * dpu_encoder_init - initialize virtual encoder object
+ * @dev:        Pointer to drm device structure
+ * @disp_info:  Pointer to display information structure
+ * Returns:     Pointer to newly created drm encoder
+ */
+struct drm_encoder *dpu_encoder_init(
+		struct drm_device *dev,
+		int drm_enc_mode);
+
+/**
+ * dpu_encoder_setup - setup dpu_encoder for the display probed
+ * @dev:		Pointer to drm device structure
+ * @enc:		Pointer to the drm_encoder
+ * @disp_info:	Pointer to the display info
+ */
+int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc,
+		struct msm_display_info *disp_info);
+
+/**
+ * dpu_encoder_prepare_commit - prepare encoder at the very beginning of an
+ *	atomic commit, before any registers are written
+ * @drm_enc:    Pointer to previously created drm encoder structure
+ */
+void dpu_encoder_prepare_commit(struct drm_encoder *drm_enc);
+
+/**
+ * dpu_encoder_set_idle_timeout - set the idle timeout for video
+ *                    and command mode encoders.
+ * @drm_enc:    Pointer to previously created drm encoder structure
+ * @idle_timeout:    idle timeout duration in milliseconds
+ */
+void dpu_encoder_set_idle_timeout(struct drm_encoder *drm_enc,
+							u32 idle_timeout);
+
+#endif /* __DPU_ENCODER_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
new file mode 100644
index 000000000000..c7df8aad6613
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
@@ -0,0 +1,430 @@
+/*
+ * Copyright (c) 2015-2018 The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __DPU_ENCODER_PHYS_H__
+#define __DPU_ENCODER_PHYS_H__
+
+#include <linux/jiffies.h>
+
+#include "dpu_kms.h"
+#include "dpu_hw_intf.h"
+#include "dpu_hw_pingpong.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_hw_top.h"
+#include "dpu_hw_cdm.h"
+#include "dpu_encoder.h"
+
+#define DPU_ENCODER_NAME_MAX	16
+
+/* wait for at most 2 vsync for lowest refresh rate (24hz) */
+#define KICKOFF_TIMEOUT_MS		84
+#define KICKOFF_TIMEOUT_JIFFIES		msecs_to_jiffies(KICKOFF_TIMEOUT_MS)
+
+/**
+ * enum dpu_enc_split_role - Role this physical encoder will play in a
+ *	split-panel configuration, where one panel is master, and others slaves.
+ *	Masters have extra responsibilities, like managing the VBLANK IRQ.
+ * @ENC_ROLE_SOLO:	This is the one and only panel. This encoder is master.
+ * @ENC_ROLE_MASTER:	This encoder is the master of a split panel config.
+ * @ENC_ROLE_SLAVE:	This encoder is not the master of a split panel config.
+ */
+enum dpu_enc_split_role {
+	ENC_ROLE_SOLO,
+	ENC_ROLE_MASTER,
+	ENC_ROLE_SLAVE,
+};
+
+/**
+ * enum dpu_enc_enable_state - current enabled state of the physical encoder
+ * @DPU_ENC_DISABLING:	Encoder transitioning to disable state
+ *			Events bounding transition are encoder type specific
+ * @DPU_ENC_DISABLED:	Encoder is disabled
+ * @DPU_ENC_ENABLING:	Encoder transitioning to enabled
+ *			Events bounding transition are encoder type specific
+ * @DPU_ENC_ENABLED:	Encoder is enabled
+ * @DPU_ENC_ERR_NEEDS_HW_RESET:	Encoder is enabled, but requires a hw_reset
+ *				to recover from a previous error
+ */
+enum dpu_enc_enable_state {
+	DPU_ENC_DISABLING,
+	DPU_ENC_DISABLED,
+	DPU_ENC_ENABLING,
+	DPU_ENC_ENABLED,
+	DPU_ENC_ERR_NEEDS_HW_RESET
+};
+
+struct dpu_encoder_phys;
+
+/**
+ * struct dpu_encoder_virt_ops - Interface the containing virtual encoder
+ *	provides for the physical encoders to use to callback.
+ * @handle_vblank_virt:	Notify virtual encoder of vblank IRQ reception
+ *			Note: This is called from IRQ handler context.
+ * @handle_underrun_virt: Notify virtual encoder of underrun IRQ reception
+ *			Note: This is called from IRQ handler context.
+ * @handle_frame_done:	Notify virtual encoder that this phys encoder
+ *			completes last request frame.
+ */
+struct dpu_encoder_virt_ops {
+	void (*handle_vblank_virt)(struct drm_encoder *,
+			struct dpu_encoder_phys *phys);
+	void (*handle_underrun_virt)(struct drm_encoder *,
+			struct dpu_encoder_phys *phys);
+	void (*handle_frame_done)(struct drm_encoder *,
+			struct dpu_encoder_phys *phys, u32 event);
+};
+
+/**
+ * struct dpu_encoder_phys_ops - Interface the physical encoders provide to
+ *	the containing virtual encoder.
+ * @late_register:		DRM Call. Add Userspace interfaces, debugfs.
+ * @prepare_commit:		MSM Atomic Call, start of atomic commit sequence
+ * @is_master:			Whether this phys_enc is the current master
+ *				encoder. Can be switched at enable time. Based
+ *				on split_role and current mode (CMD/VID).
+ * @mode_fixup:			DRM Call. Fixup a DRM mode.
+ * @mode_set:			DRM Call. Set a DRM mode.
+ *				This likely caches the mode, for use at enable.
+ * @enable:			DRM Call. Enable a DRM mode.
+ * @disable:			DRM Call. Disable mode.
+ * @atomic_check:		DRM Call. Atomic check new DRM state.
+ * @destroy:			DRM Call. Destroy and release resources.
+ * @get_hw_resources:		Populate the structure with the hardware
+ *				resources that this phys_enc is using.
+ *				Expect no overlap between phys_encs.
+ * @control_vblank_irq		Register/Deregister for VBLANK IRQ
+ * @wait_for_commit_done:	Wait for hardware to have flushed the
+ *				current pending frames to hardware
+ * @wait_for_tx_complete:	Wait for hardware to transfer the pixels
+ *				to the panel
+ * @wait_for_vblank:		Wait for VBLANK, for sub-driver internal use
+ * @prepare_for_kickoff:	Do any work necessary prior to a kickoff
+ *				For CMD encoder, may wait for previous tx done
+ * @handle_post_kickoff:	Do any work necessary post-kickoff work
+ * @trigger_start:		Process start event on physical encoder
+ * @needs_single_flush:		Whether encoder slaves need to be flushed
+ * @setup_misr:		Sets up MISR, enable and disables based on sysfs
+ * @collect_misr:		Collects MISR data on frame update
+ * @hw_reset:			Issue HW recovery such as CTL reset and clear
+ *				DPU_ENC_ERR_NEEDS_HW_RESET state
+ * @irq_control:		Handler to enable/disable all the encoder IRQs
+ * @prepare_idle_pc:		phys encoder can update the vsync_enable status
+ *                              on idle power collapse prepare
+ * @restore:			Restore all the encoder configs.
+ * @get_line_count:		Obtain current vertical line count
+ */
+
+struct dpu_encoder_phys_ops {
+	int (*late_register)(struct dpu_encoder_phys *encoder,
+			struct dentry *debugfs_root);
+	void (*prepare_commit)(struct dpu_encoder_phys *encoder);
+	bool (*is_master)(struct dpu_encoder_phys *encoder);
+	bool (*mode_fixup)(struct dpu_encoder_phys *encoder,
+			const struct drm_display_mode *mode,
+			struct drm_display_mode *adjusted_mode);
+	void (*mode_set)(struct dpu_encoder_phys *encoder,
+			struct drm_display_mode *mode,
+			struct drm_display_mode *adjusted_mode);
+	void (*enable)(struct dpu_encoder_phys *encoder);
+	void (*disable)(struct dpu_encoder_phys *encoder);
+	int (*atomic_check)(struct dpu_encoder_phys *encoder,
+			    struct drm_crtc_state *crtc_state,
+			    struct drm_connector_state *conn_state);
+	void (*destroy)(struct dpu_encoder_phys *encoder);
+	void (*get_hw_resources)(struct dpu_encoder_phys *encoder,
+			struct dpu_encoder_hw_resources *hw_res,
+			struct drm_connector_state *conn_state);
+	int (*control_vblank_irq)(struct dpu_encoder_phys *enc, bool enable);
+	int (*wait_for_commit_done)(struct dpu_encoder_phys *phys_enc);
+	int (*wait_for_tx_complete)(struct dpu_encoder_phys *phys_enc);
+	int (*wait_for_vblank)(struct dpu_encoder_phys *phys_enc);
+	void (*prepare_for_kickoff)(struct dpu_encoder_phys *phys_enc,
+			struct dpu_encoder_kickoff_params *params);
+	void (*handle_post_kickoff)(struct dpu_encoder_phys *phys_enc);
+	void (*trigger_start)(struct dpu_encoder_phys *phys_enc);
+	bool (*needs_single_flush)(struct dpu_encoder_phys *phys_enc);
+
+	void (*setup_misr)(struct dpu_encoder_phys *phys_encs,
+				bool enable, u32 frame_count);
+	u32 (*collect_misr)(struct dpu_encoder_phys *phys_enc);
+	void (*hw_reset)(struct dpu_encoder_phys *phys_enc);
+	void (*irq_control)(struct dpu_encoder_phys *phys, bool enable);
+	void (*prepare_idle_pc)(struct dpu_encoder_phys *phys_enc);
+	void (*restore)(struct dpu_encoder_phys *phys);
+	int (*get_line_count)(struct dpu_encoder_phys *phys);
+};
+
+/**
+ * enum dpu_intr_idx - dpu encoder interrupt index
+ * @INTR_IDX_VSYNC:    Vsync interrupt for video mode panel
+ * @INTR_IDX_PINGPONG: Pingpong done unterrupt for cmd mode panel
+ * @INTR_IDX_UNDERRUN: Underrun unterrupt for video and cmd mode panel
+ * @INTR_IDX_RDPTR:    Readpointer done unterrupt for cmd mode panel
+ */
+enum dpu_intr_idx {
+	INTR_IDX_VSYNC,
+	INTR_IDX_PINGPONG,
+	INTR_IDX_UNDERRUN,
+	INTR_IDX_CTL_START,
+	INTR_IDX_RDPTR,
+	INTR_IDX_MAX,
+};
+
+/**
+ * dpu_encoder_irq - tracking structure for interrupts
+ * @name:		string name of interrupt
+ * @intr_type:		Encoder interrupt type
+ * @intr_idx:		Encoder interrupt enumeration
+ * @hw_idx:		HW Block ID
+ * @irq_idx:		IRQ interface lookup index from DPU IRQ framework
+ *			will be -EINVAL if IRQ is not registered
+ * @irq_cb:		interrupt callback
+ */
+struct dpu_encoder_irq {
+	const char *name;
+	enum dpu_intr_type intr_type;
+	enum dpu_intr_idx intr_idx;
+	int hw_idx;
+	int irq_idx;
+	struct dpu_irq_callback cb;
+};
+
+/**
+ * struct dpu_encoder_phys - physical encoder that drives a single INTF block
+ *	tied to a specific panel / sub-panel. Abstract type, sub-classed by
+ *	phys_vid or phys_cmd for video mode or command mode encs respectively.
+ * @parent:		Pointer to the containing virtual encoder
+ * @connector:		If a mode is set, cached pointer to the active connector
+ * @ops:		Operations exposed to the virtual encoder
+ * @parent_ops:		Callbacks exposed by the parent to the phys_enc
+ * @hw_mdptop:		Hardware interface to the top registers
+ * @hw_ctl:		Hardware interface to the ctl registers
+ * @hw_cdm:		Hardware interface to the cdm registers
+ * @cdm_cfg:		Chroma-down hardware configuration
+ * @hw_pp:		Hardware interface to the ping pong registers
+ * @dpu_kms:		Pointer to the dpu_kms top level
+ * @cached_mode:	DRM mode cached at mode_set time, acted on in enable
+ * @enabled:		Whether the encoder has enabled and running a mode
+ * @split_role:		Role to play in a split-panel configuration
+ * @intf_mode:		Interface mode
+ * @intf_idx:		Interface index on dpu hardware
+ * @topology_name:	topology selected for the display
+ * @enc_spinlock:	Virtual-Encoder-Wide Spin Lock for IRQ purposes
+ * @enable_state:	Enable state tracking
+ * @vblank_refcount:	Reference count of vblank request
+ * @vsync_cnt:		Vsync count for the physical encoder
+ * @underrun_cnt:	Underrun count for the physical encoder
+ * @pending_kickoff_cnt:	Atomic counter tracking the number of kickoffs
+ *				vs. the number of done/vblank irqs. Should hover
+ *				between 0-2 Incremented when a new kickoff is
+ *				scheduled. Decremented in irq handler
+ * @pending_ctlstart_cnt:	Atomic counter tracking the number of ctl start
+ *                              pending.
+ * @pending_kickoff_wq:		Wait queue for blocking until kickoff completes
+ * @irq:			IRQ tracking structures
+ */
+struct dpu_encoder_phys {
+	struct drm_encoder *parent;
+	struct drm_connector *connector;
+	struct dpu_encoder_phys_ops ops;
+	const struct dpu_encoder_virt_ops *parent_ops;
+	struct dpu_hw_mdp *hw_mdptop;
+	struct dpu_hw_ctl *hw_ctl;
+	struct dpu_hw_cdm *hw_cdm;
+	struct dpu_hw_cdm_cfg cdm_cfg;
+	struct dpu_hw_pingpong *hw_pp;
+	struct dpu_kms *dpu_kms;
+	struct drm_display_mode cached_mode;
+	enum dpu_enc_split_role split_role;
+	enum dpu_intf_mode intf_mode;
+	enum dpu_intf intf_idx;
+	enum dpu_rm_topology_name topology_name;
+	spinlock_t *enc_spinlock;
+	enum dpu_enc_enable_state enable_state;
+	atomic_t vblank_refcount;
+	atomic_t vsync_cnt;
+	atomic_t underrun_cnt;
+	atomic_t pending_ctlstart_cnt;
+	atomic_t pending_kickoff_cnt;
+	wait_queue_head_t pending_kickoff_wq;
+	struct dpu_encoder_irq irq[INTR_IDX_MAX];
+};
+
+static inline int dpu_encoder_phys_inc_pending(struct dpu_encoder_phys *phys)
+{
+	atomic_inc_return(&phys->pending_ctlstart_cnt);
+	return atomic_inc_return(&phys->pending_kickoff_cnt);
+}
+
+/**
+ * struct dpu_encoder_phys_vid - sub-class of dpu_encoder_phys to handle video
+ *	mode specific operations
+ * @base:	Baseclass physical encoder structure
+ * @hw_intf:	Hardware interface to the intf registers
+ * @timing_params: Current timing parameter
+ */
+struct dpu_encoder_phys_vid {
+	struct dpu_encoder_phys base;
+	struct dpu_hw_intf *hw_intf;
+	struct intf_timing_params timing_params;
+};
+
+/**
+ * struct dpu_encoder_phys_cmd - sub-class of dpu_encoder_phys to handle command
+ *	mode specific operations
+ * @base:	Baseclass physical encoder structure
+ * @intf_idx:	Intf Block index used by this phys encoder
+ * @stream_sel:	Stream selection for multi-stream interfaces
+ * @serialize_wait4pp:	serialize wait4pp feature waits for pp_done interrupt
+ *			after ctl_start instead of before next frame kickoff
+ * @pp_timeout_report_cnt: number of pingpong done irq timeout errors
+ * @pending_vblank_cnt: Atomic counter tracking pending wait for VBLANK
+ * @pending_vblank_wq: Wait queue for blocking until VBLANK received
+ */
+struct dpu_encoder_phys_cmd {
+	struct dpu_encoder_phys base;
+	int stream_sel;
+	bool serialize_wait4pp;
+	int pp_timeout_report_cnt;
+	atomic_t pending_vblank_cnt;
+	wait_queue_head_t pending_vblank_wq;
+};
+
+/**
+ * struct dpu_enc_phys_init_params - initialization parameters for phys encs
+ * @dpu_kms:		Pointer to the dpu_kms top level
+ * @parent:		Pointer to the containing virtual encoder
+ * @parent_ops:		Callbacks exposed by the parent to the phys_enc
+ * @split_role:		Role to play in a split-panel configuration
+ * @intf_idx:		Interface index this phys_enc will control
+ * @enc_spinlock:	Virtual-Encoder-Wide Spin Lock for IRQ purposes
+ */
+struct dpu_enc_phys_init_params {
+	struct dpu_kms *dpu_kms;
+	struct drm_encoder *parent;
+	const struct dpu_encoder_virt_ops *parent_ops;
+	enum dpu_enc_split_role split_role;
+	enum dpu_intf intf_idx;
+	spinlock_t *enc_spinlock;
+};
+
+/**
+ * dpu_encoder_wait_info - container for passing arguments to irq wait functions
+ * @wq: wait queue structure
+ * @atomic_cnt: wait until atomic_cnt equals zero
+ * @timeout_ms: timeout value in milliseconds
+ */
+struct dpu_encoder_wait_info {
+	wait_queue_head_t *wq;
+	atomic_t *atomic_cnt;
+	s64 timeout_ms;
+};
+
+/**
+ * dpu_encoder_phys_vid_init - Construct a new video mode physical encoder
+ * @p:	Pointer to init params structure
+ * Return: Error code or newly allocated encoder
+ */
+struct dpu_encoder_phys *dpu_encoder_phys_vid_init(
+		struct dpu_enc_phys_init_params *p);
+
+/**
+ * dpu_encoder_phys_cmd_init - Construct a new command mode physical encoder
+ * @p:	Pointer to init params structure
+ * Return: Error code or newly allocated encoder
+ */
+struct dpu_encoder_phys *dpu_encoder_phys_cmd_init(
+		struct dpu_enc_phys_init_params *p);
+
+/**
+ * dpu_encoder_helper_trigger_start - control start helper function
+ *	This helper function may be optionally specified by physical
+ *	encoders if they require ctl_start triggering.
+ * @phys_enc: Pointer to physical encoder structure
+ */
+void dpu_encoder_helper_trigger_start(struct dpu_encoder_phys *phys_enc);
+
+/**
+ * dpu_encoder_helper_hw_reset - issue ctl hw reset
+ *	This helper function may be optionally specified by physical
+ *	encoders if they require ctl hw reset. If state is currently
+ *	DPU_ENC_ERR_NEEDS_HW_RESET, it is set back to DPU_ENC_ENABLED.
+ * @phys_enc: Pointer to physical encoder structure
+ */
+void dpu_encoder_helper_hw_reset(struct dpu_encoder_phys *phys_enc);
+
+static inline enum dpu_3d_blend_mode dpu_encoder_helper_get_3d_blend_mode(
+		struct dpu_encoder_phys *phys_enc)
+{
+	if (!phys_enc || phys_enc->enable_state == DPU_ENC_DISABLING)
+		return BLEND_3D_NONE;
+
+	if (phys_enc->split_role == ENC_ROLE_SOLO &&
+	    phys_enc->topology_name == DPU_RM_TOPOLOGY_DUALPIPE_3DMERGE)
+		return BLEND_3D_H_ROW_INT;
+
+	return BLEND_3D_NONE;
+}
+
+/**
+ * dpu_encoder_helper_split_config - split display configuration helper function
+ *	This helper function may be used by physical encoders to configure
+ *	the split display related registers.
+ * @phys_enc: Pointer to physical encoder structure
+ * @interface: enum dpu_intf setting
+ */
+void dpu_encoder_helper_split_config(
+		struct dpu_encoder_phys *phys_enc,
+		enum dpu_intf interface);
+
+/**
+ * dpu_encoder_helper_report_irq_timeout - utility to report error that irq has
+ *	timed out, including reporting frame error event to crtc and debug dump
+ * @phys_enc: Pointer to physical encoder structure
+ * @intr_idx: Failing interrupt index
+ */
+void dpu_encoder_helper_report_irq_timeout(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx);
+
+/**
+ * dpu_encoder_helper_wait_for_irq - utility to wait on an irq.
+ *	note: will call dpu_encoder_helper_wait_for_irq on timeout
+ * @phys_enc: Pointer to physical encoder structure
+ * @intr_idx: encoder interrupt index
+ * @wait_info: wait info struct
+ * @Return: 0 or -ERROR
+ */
+int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx,
+		struct dpu_encoder_wait_info *wait_info);
+
+/**
+ * dpu_encoder_helper_register_irq - register and enable an irq
+ * @phys_enc: Pointer to physical encoder structure
+ * @intr_idx: encoder interrupt index
+ * @Return: 0 or -ERROR
+ */
+int dpu_encoder_helper_register_irq(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx);
+
+/**
+ * dpu_encoder_helper_unregister_irq - unregister and disable an irq
+ * @phys_enc: Pointer to physical encoder structure
+ * @intr_idx: encoder interrupt index
+ * @Return: 0 or -ERROR
+ */
+int dpu_encoder_helper_unregister_irq(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx);
+
+#endif /* __dpu_encoder_phys_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
new file mode 100644
index 000000000000..3084675ed425
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
@@ -0,0 +1,905 @@
+/*
+ * Copyright (c) 2015-2018 The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include "dpu_encoder_phys.h"
+#include "dpu_hw_interrupts.h"
+#include "dpu_core_irq.h"
+#include "dpu_formats.h"
+#include "dpu_trace.h"
+
+#define DPU_DEBUG_CMDENC(e, fmt, ...) DPU_DEBUG("enc%d intf%d " fmt, \
+		(e) && (e)->base.parent ? \
+		(e)->base.parent->base.id : -1, \
+		(e) ? (e)->base.intf_idx - INTF_0 : -1, ##__VA_ARGS__)
+
+#define DPU_ERROR_CMDENC(e, fmt, ...) DPU_ERROR("enc%d intf%d " fmt, \
+		(e) && (e)->base.parent ? \
+		(e)->base.parent->base.id : -1, \
+		(e) ? (e)->base.intf_idx - INTF_0 : -1, ##__VA_ARGS__)
+
+#define to_dpu_encoder_phys_cmd(x) \
+	container_of(x, struct dpu_encoder_phys_cmd, base)
+
+#define PP_TIMEOUT_MAX_TRIALS	10
+
+/*
+ * Tearcheck sync start and continue thresholds are empirically found
+ * based on common panels In the future, may want to allow panels to override
+ * these default values
+ */
+#define DEFAULT_TEARCHECK_SYNC_THRESH_START	4
+#define DEFAULT_TEARCHECK_SYNC_THRESH_CONTINUE	4
+
+#define DPU_ENC_WR_PTR_START_TIMEOUT_US 20000
+
+static inline int _dpu_encoder_phys_cmd_get_idle_timeout(
+		struct dpu_encoder_phys_cmd *cmd_enc)
+{
+	return KICKOFF_TIMEOUT_MS;
+}
+
+static inline bool dpu_encoder_phys_cmd_is_master(
+		struct dpu_encoder_phys *phys_enc)
+{
+	return (phys_enc->split_role != ENC_ROLE_SLAVE) ? true : false;
+}
+
+static bool dpu_encoder_phys_cmd_mode_fixup(
+		struct dpu_encoder_phys *phys_enc,
+		const struct drm_display_mode *mode,
+		struct drm_display_mode *adj_mode)
+{
+	if (phys_enc)
+		DPU_DEBUG_CMDENC(to_dpu_encoder_phys_cmd(phys_enc), "\n");
+	return true;
+}
+
+static void _dpu_encoder_phys_cmd_update_intf_cfg(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	struct dpu_hw_ctl *ctl;
+	struct dpu_hw_intf_cfg intf_cfg = { 0 };
+
+	if (!phys_enc)
+		return;
+
+	ctl = phys_enc->hw_ctl;
+	if (!ctl || !ctl->ops.setup_intf_cfg)
+		return;
+
+	intf_cfg.intf = phys_enc->intf_idx;
+	intf_cfg.intf_mode_sel = DPU_CTL_MODE_SEL_CMD;
+	intf_cfg.stream_sel = cmd_enc->stream_sel;
+	intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc);
+	ctl->ops.setup_intf_cfg(ctl, &intf_cfg);
+}
+
+static void dpu_encoder_phys_cmd_pp_tx_done_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+	unsigned long lock_flags;
+	int new_cnt;
+	u32 event = DPU_ENCODER_FRAME_EVENT_DONE;
+
+	if (!phys_enc || !phys_enc->hw_pp)
+		return;
+
+	DPU_ATRACE_BEGIN("pp_done_irq");
+	/* notify all synchronous clients first, then asynchronous clients */
+	if (phys_enc->parent_ops->handle_frame_done)
+		phys_enc->parent_ops->handle_frame_done(phys_enc->parent,
+				phys_enc, event);
+
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	new_cnt = atomic_add_unless(&phys_enc->pending_kickoff_cnt, -1, 0);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+
+	trace_dpu_enc_phys_cmd_pp_tx_done(DRMID(phys_enc->parent),
+					  phys_enc->hw_pp->idx - PINGPONG_0,
+					  new_cnt, event);
+
+	/* Signal any waiting atomic commit thread */
+	wake_up_all(&phys_enc->pending_kickoff_wq);
+	DPU_ATRACE_END("pp_done_irq");
+}
+
+static void dpu_encoder_phys_cmd_pp_rd_ptr_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+	struct dpu_encoder_phys_cmd *cmd_enc;
+
+	if (!phys_enc || !phys_enc->hw_pp)
+		return;
+
+	DPU_ATRACE_BEGIN("rd_ptr_irq");
+	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
+
+	if (phys_enc->parent_ops->handle_vblank_virt)
+		phys_enc->parent_ops->handle_vblank_virt(phys_enc->parent,
+			phys_enc);
+
+	atomic_add_unless(&cmd_enc->pending_vblank_cnt, -1, 0);
+	wake_up_all(&cmd_enc->pending_vblank_wq);
+	DPU_ATRACE_END("rd_ptr_irq");
+}
+
+static void dpu_encoder_phys_cmd_ctl_start_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+	struct dpu_encoder_phys_cmd *cmd_enc;
+
+	if (!phys_enc || !phys_enc->hw_ctl)
+		return;
+
+	DPU_ATRACE_BEGIN("ctl_start_irq");
+	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
+
+	atomic_add_unless(&phys_enc->pending_ctlstart_cnt, -1, 0);
+
+	/* Signal any waiting ctl start interrupt */
+	wake_up_all(&phys_enc->pending_kickoff_wq);
+	DPU_ATRACE_END("ctl_start_irq");
+}
+
+static void dpu_encoder_phys_cmd_underrun_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+
+	if (!phys_enc)
+		return;
+
+	if (phys_enc->parent_ops->handle_underrun_virt)
+		phys_enc->parent_ops->handle_underrun_virt(phys_enc->parent,
+			phys_enc);
+}
+
+static void _dpu_encoder_phys_cmd_setup_irq_hw_idx(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_irq *irq;
+
+	irq = &phys_enc->irq[INTR_IDX_CTL_START];
+	irq->hw_idx = phys_enc->hw_ctl->idx;
+	irq->irq_idx = -EINVAL;
+
+	irq = &phys_enc->irq[INTR_IDX_PINGPONG];
+	irq->hw_idx = phys_enc->hw_pp->idx;
+	irq->irq_idx = -EINVAL;
+
+	irq = &phys_enc->irq[INTR_IDX_RDPTR];
+	irq->hw_idx = phys_enc->hw_pp->idx;
+	irq->irq_idx = -EINVAL;
+
+	irq = &phys_enc->irq[INTR_IDX_UNDERRUN];
+	irq->hw_idx = phys_enc->intf_idx;
+	irq->irq_idx = -EINVAL;
+}
+
+static void dpu_encoder_phys_cmd_mode_set(
+		struct dpu_encoder_phys *phys_enc,
+		struct drm_display_mode *mode,
+		struct drm_display_mode *adj_mode)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+	struct dpu_rm *rm = &phys_enc->dpu_kms->rm;
+	struct dpu_rm_hw_iter iter;
+	int i, instance;
+
+	if (!phys_enc || !mode || !adj_mode) {
+		DPU_ERROR("invalid args\n");
+		return;
+	}
+	phys_enc->cached_mode = *adj_mode;
+	DPU_DEBUG_CMDENC(cmd_enc, "caching mode:\n");
+	drm_mode_debug_printmodeline(adj_mode);
+
+	instance = phys_enc->split_role == ENC_ROLE_SLAVE ? 1 : 0;
+
+	/* Retrieve previously allocated HW Resources. Shouldn't fail */
+	dpu_rm_init_hw_iter(&iter, phys_enc->parent->base.id, DPU_HW_BLK_CTL);
+	for (i = 0; i <= instance; i++) {
+		if (dpu_rm_get_hw(rm, &iter))
+			phys_enc->hw_ctl = (struct dpu_hw_ctl *)iter.hw;
+	}
+
+	if (IS_ERR_OR_NULL(phys_enc->hw_ctl)) {
+		DPU_ERROR_CMDENC(cmd_enc, "failed to init ctl: %ld\n",
+				PTR_ERR(phys_enc->hw_ctl));
+		phys_enc->hw_ctl = NULL;
+		return;
+	}
+
+	_dpu_encoder_phys_cmd_setup_irq_hw_idx(phys_enc);
+}
+
+static int _dpu_encoder_phys_cmd_handle_ppdone_timeout(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	u32 frame_event = DPU_ENCODER_FRAME_EVENT_ERROR;
+	bool do_log = false;
+
+	if (!phys_enc || !phys_enc->hw_pp || !phys_enc->hw_ctl)
+		return -EINVAL;
+
+	cmd_enc->pp_timeout_report_cnt++;
+	if (cmd_enc->pp_timeout_report_cnt == PP_TIMEOUT_MAX_TRIALS) {
+		frame_event |= DPU_ENCODER_FRAME_EVENT_PANEL_DEAD;
+		do_log = true;
+	} else if (cmd_enc->pp_timeout_report_cnt == 1) {
+		do_log = true;
+	}
+
+	trace_dpu_enc_phys_cmd_pdone_timeout(DRMID(phys_enc->parent),
+		     phys_enc->hw_pp->idx - PINGPONG_0,
+		     cmd_enc->pp_timeout_report_cnt,
+		     atomic_read(&phys_enc->pending_kickoff_cnt),
+		     frame_event);
+
+	/* to avoid flooding, only log first time, and "dead" time */
+	if (do_log) {
+		DRM_ERROR("id:%d pp:%d kickoff timeout %d cnt %d koff_cnt %d\n",
+			  DRMID(phys_enc->parent),
+			  phys_enc->hw_pp->idx - PINGPONG_0,
+			  phys_enc->hw_ctl->idx - CTL_0,
+			  cmd_enc->pp_timeout_report_cnt,
+			  atomic_read(&phys_enc->pending_kickoff_cnt));
+
+		dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_RDPTR);
+		dpu_dbg_dump(false, __func__, true, true);
+	}
+
+	atomic_add_unless(&phys_enc->pending_kickoff_cnt, -1, 0);
+
+	/* request a ctl reset before the next kickoff */
+	phys_enc->enable_state = DPU_ENC_ERR_NEEDS_HW_RESET;
+
+	if (phys_enc->parent_ops->handle_frame_done)
+		phys_enc->parent_ops->handle_frame_done(
+				phys_enc->parent, phys_enc, frame_event);
+
+	return -ETIMEDOUT;
+}
+
+static int _dpu_encoder_phys_cmd_wait_for_idle(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	struct dpu_encoder_wait_info wait_info;
+	int ret;
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return -EINVAL;
+	}
+
+	wait_info.wq = &phys_enc->pending_kickoff_wq;
+	wait_info.atomic_cnt = &phys_enc->pending_kickoff_cnt;
+	wait_info.timeout_ms = KICKOFF_TIMEOUT_MS;
+
+	ret = dpu_encoder_helper_wait_for_irq(phys_enc, INTR_IDX_PINGPONG,
+			&wait_info);
+	if (ret == -ETIMEDOUT)
+		_dpu_encoder_phys_cmd_handle_ppdone_timeout(phys_enc);
+	else if (!ret)
+		cmd_enc->pp_timeout_report_cnt = 0;
+
+	return ret;
+}
+
+static int dpu_encoder_phys_cmd_control_vblank_irq(
+		struct dpu_encoder_phys *phys_enc,
+		bool enable)
+{
+	int ret = 0;
+	int refcount;
+
+	if (!phys_enc || !phys_enc->hw_pp) {
+		DPU_ERROR("invalid encoder\n");
+		return -EINVAL;
+	}
+
+	refcount = atomic_read(&phys_enc->vblank_refcount);
+
+	/* Slave encoders don't report vblank */
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		goto end;
+
+	/* protect against negative */
+	if (!enable && refcount == 0) {
+		ret = -EINVAL;
+		goto end;
+	}
+
+	DRM_DEBUG_KMS("id:%u pp:%d enable=%s/%d\n", DRMID(phys_enc->parent),
+		      phys_enc->hw_pp->idx - PINGPONG_0,
+		      enable ? "true" : "false", refcount);
+
+	if (enable && atomic_inc_return(&phys_enc->vblank_refcount) == 1)
+		ret = dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_RDPTR);
+	else if (!enable && atomic_dec_return(&phys_enc->vblank_refcount) == 0)
+		ret = dpu_encoder_helper_unregister_irq(phys_enc,
+				INTR_IDX_RDPTR);
+
+end:
+	if (ret) {
+		DRM_ERROR("vblank irq err id:%u pp:%d ret:%d, enable %s/%d\n",
+			  DRMID(phys_enc->parent),
+			  phys_enc->hw_pp->idx - PINGPONG_0, ret,
+			  enable ? "true" : "false", refcount);
+	}
+
+	return ret;
+}
+
+static void dpu_encoder_phys_cmd_irq_control(struct dpu_encoder_phys *phys_enc,
+		bool enable)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc;
+
+	if (!phys_enc)
+		return;
+
+	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
+
+	trace_dpu_enc_phys_cmd_irq_ctrl(DRMID(phys_enc->parent),
+			phys_enc->hw_pp->idx - PINGPONG_0,
+			enable, atomic_read(&phys_enc->vblank_refcount));
+
+	if (enable) {
+		dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_PINGPONG);
+		dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_UNDERRUN);
+		dpu_encoder_phys_cmd_control_vblank_irq(phys_enc, true);
+
+		if (dpu_encoder_phys_cmd_is_master(phys_enc))
+			dpu_encoder_helper_register_irq(phys_enc,
+					INTR_IDX_CTL_START);
+	} else {
+		if (dpu_encoder_phys_cmd_is_master(phys_enc))
+			dpu_encoder_helper_unregister_irq(phys_enc,
+					INTR_IDX_CTL_START);
+
+		dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_UNDERRUN);
+		dpu_encoder_phys_cmd_control_vblank_irq(phys_enc, false);
+		dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_PINGPONG);
+	}
+}
+
+static void dpu_encoder_phys_cmd_tearcheck_config(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+	struct dpu_hw_tear_check tc_cfg = { 0 };
+	struct drm_display_mode *mode;
+	bool tc_enable = true;
+	u32 vsync_hz;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!phys_enc || !phys_enc->hw_pp) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	mode = &phys_enc->cached_mode;
+
+	DPU_DEBUG_CMDENC(cmd_enc, "pp %d\n", phys_enc->hw_pp->idx - PINGPONG_0);
+
+	if (!phys_enc->hw_pp->ops.setup_tearcheck ||
+		!phys_enc->hw_pp->ops.enable_tearcheck) {
+		DPU_DEBUG_CMDENC(cmd_enc, "tearcheck not supported\n");
+		return;
+	}
+
+	dpu_kms = phys_enc->dpu_kms;
+	if (!dpu_kms || !dpu_kms->dev || !dpu_kms->dev->dev_private) {
+		DPU_ERROR("invalid device\n");
+		return;
+	}
+	priv = dpu_kms->dev->dev_private;
+
+	/*
+	 * TE default: dsi byte clock calculated base on 70 fps;
+	 * around 14 ms to complete a kickoff cycle if te disabled;
+	 * vclk_line base on 60 fps; write is faster than read;
+	 * init == start == rdptr;
+	 *
+	 * vsync_count is ratio of MDP VSYNC clock frequency to LCD panel
+	 * frequency divided by the no. of rows (lines) in the LCDpanel.
+	 */
+	vsync_hz = dpu_kms_get_clk_rate(dpu_kms, "vsync");
+	if (vsync_hz <= 0) {
+		DPU_DEBUG_CMDENC(cmd_enc, "invalid - vsync_hz %u\n",
+				 vsync_hz);
+		return;
+	}
+
+	tc_cfg.vsync_count = vsync_hz / (mode->vtotal * mode->vrefresh);
+
+	/* enable external TE after kickoff to avoid premature autorefresh */
+	tc_cfg.hw_vsync_mode = 0;
+
+	/*
+	 * By setting sync_cfg_height to near max register value, we essentially
+	 * disable dpu hw generated TE signal, since hw TE will arrive first.
+	 * Only caveat is if due to error, we hit wrap-around.
+	 */
+	tc_cfg.sync_cfg_height = 0xFFF0;
+	tc_cfg.vsync_init_val = mode->vdisplay;
+	tc_cfg.sync_threshold_start = DEFAULT_TEARCHECK_SYNC_THRESH_START;
+	tc_cfg.sync_threshold_continue = DEFAULT_TEARCHECK_SYNC_THRESH_CONTINUE;
+	tc_cfg.start_pos = mode->vdisplay;
+	tc_cfg.rd_ptr_irq = mode->vdisplay + 1;
+
+	DPU_DEBUG_CMDENC(cmd_enc,
+		"tc %d vsync_clk_speed_hz %u vtotal %u vrefresh %u\n",
+		phys_enc->hw_pp->idx - PINGPONG_0, vsync_hz,
+		mode->vtotal, mode->vrefresh);
+	DPU_DEBUG_CMDENC(cmd_enc,
+		"tc %d enable %u start_pos %u rd_ptr_irq %u\n",
+		phys_enc->hw_pp->idx - PINGPONG_0, tc_enable, tc_cfg.start_pos,
+		tc_cfg.rd_ptr_irq);
+	DPU_DEBUG_CMDENC(cmd_enc,
+		"tc %d hw_vsync_mode %u vsync_count %u vsync_init_val %u\n",
+		phys_enc->hw_pp->idx - PINGPONG_0, tc_cfg.hw_vsync_mode,
+		tc_cfg.vsync_count, tc_cfg.vsync_init_val);
+	DPU_DEBUG_CMDENC(cmd_enc,
+		"tc %d cfgheight %u thresh_start %u thresh_cont %u\n",
+		phys_enc->hw_pp->idx - PINGPONG_0, tc_cfg.sync_cfg_height,
+		tc_cfg.sync_threshold_start, tc_cfg.sync_threshold_continue);
+
+	phys_enc->hw_pp->ops.setup_tearcheck(phys_enc->hw_pp, &tc_cfg);
+	phys_enc->hw_pp->ops.enable_tearcheck(phys_enc->hw_pp, tc_enable);
+}
+
+static void _dpu_encoder_phys_cmd_pingpong_config(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+
+	if (!phys_enc || !phys_enc->hw_ctl || !phys_enc->hw_pp
+			|| !phys_enc->hw_ctl->ops.setup_intf_cfg) {
+		DPU_ERROR("invalid arg(s), enc %d\n", phys_enc != 0);
+		return;
+	}
+
+	DPU_DEBUG_CMDENC(cmd_enc, "pp %d, enabling mode:\n",
+			phys_enc->hw_pp->idx - PINGPONG_0);
+	drm_mode_debug_printmodeline(&phys_enc->cached_mode);
+
+	_dpu_encoder_phys_cmd_update_intf_cfg(phys_enc);
+	dpu_encoder_phys_cmd_tearcheck_config(phys_enc);
+}
+
+static bool dpu_encoder_phys_cmd_needs_single_flush(
+		struct dpu_encoder_phys *phys_enc)
+{
+	/**
+	 * we do separate flush for each CTL and let
+	 * CTL_START synchronize them
+	 */
+	return false;
+}
+
+static void dpu_encoder_phys_cmd_enable_helper(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_ctl *ctl;
+	u32 flush_mask = 0;
+
+	if (!phys_enc || !phys_enc->hw_ctl || !phys_enc->hw_pp) {
+		DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != 0);
+		return;
+	}
+
+	dpu_encoder_helper_split_config(phys_enc, phys_enc->intf_idx);
+
+	_dpu_encoder_phys_cmd_pingpong_config(phys_enc);
+
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		goto skip_flush;
+
+	ctl = phys_enc->hw_ctl;
+	ctl->ops.get_bitmask_intf(ctl, &flush_mask, phys_enc->intf_idx);
+	ctl->ops.update_pending_flush(ctl, flush_mask);
+
+skip_flush:
+	return;
+}
+
+static void dpu_encoder_phys_cmd_enable(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+
+	if (!phys_enc || !phys_enc->hw_pp) {
+		DPU_ERROR("invalid phys encoder\n");
+		return;
+	}
+
+	DPU_DEBUG_CMDENC(cmd_enc, "pp %d\n", phys_enc->hw_pp->idx - PINGPONG_0);
+
+	if (phys_enc->enable_state == DPU_ENC_ENABLED) {
+		DPU_ERROR("already enabled\n");
+		return;
+	}
+
+	dpu_encoder_phys_cmd_enable_helper(phys_enc);
+	phys_enc->enable_state = DPU_ENC_ENABLED;
+}
+
+static void _dpu_encoder_phys_cmd_connect_te(
+		struct dpu_encoder_phys *phys_enc, bool enable)
+{
+	if (!phys_enc || !phys_enc->hw_pp ||
+			!phys_enc->hw_pp->ops.connect_external_te)
+		return;
+
+	trace_dpu_enc_phys_cmd_connect_te(DRMID(phys_enc->parent), enable);
+	phys_enc->hw_pp->ops.connect_external_te(phys_enc->hw_pp, enable);
+}
+
+static void dpu_encoder_phys_cmd_prepare_idle_pc(
+		struct dpu_encoder_phys *phys_enc)
+{
+	_dpu_encoder_phys_cmd_connect_te(phys_enc, false);
+}
+
+static int dpu_encoder_phys_cmd_get_line_count(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_pingpong *hw_pp;
+
+	if (!phys_enc || !phys_enc->hw_pp)
+		return -EINVAL;
+
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		return -EINVAL;
+
+	hw_pp = phys_enc->hw_pp;
+	if (!hw_pp->ops.get_line_count)
+		return -EINVAL;
+
+	return hw_pp->ops.get_line_count(hw_pp);
+}
+
+static void dpu_encoder_phys_cmd_disable(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+
+	if (!phys_enc || !phys_enc->hw_pp) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	DRM_DEBUG_KMS("id:%u pp:%d state:%d\n", DRMID(phys_enc->parent),
+		      phys_enc->hw_pp->idx - PINGPONG_0,
+		      phys_enc->enable_state);
+
+	if (phys_enc->enable_state == DPU_ENC_DISABLED) {
+		DPU_ERROR_CMDENC(cmd_enc, "already disabled\n");
+		return;
+	}
+
+	if (phys_enc->hw_pp->ops.enable_tearcheck)
+		phys_enc->hw_pp->ops.enable_tearcheck(phys_enc->hw_pp, false);
+	phys_enc->enable_state = DPU_ENC_DISABLED;
+}
+
+static void dpu_encoder_phys_cmd_destroy(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	kfree(cmd_enc);
+}
+
+static void dpu_encoder_phys_cmd_get_hw_resources(
+		struct dpu_encoder_phys *phys_enc,
+		struct dpu_encoder_hw_resources *hw_res,
+		struct drm_connector_state *conn_state)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	if ((phys_enc->intf_idx - INTF_0) >= INTF_MAX) {
+		DPU_ERROR("invalid intf idx:%d\n", phys_enc->intf_idx);
+		return;
+	}
+
+	DPU_DEBUG_CMDENC(cmd_enc, "\n");
+	hw_res->intfs[phys_enc->intf_idx - INTF_0] = INTF_MODE_CMD;
+}
+
+static void dpu_encoder_phys_cmd_prepare_for_kickoff(
+		struct dpu_encoder_phys *phys_enc,
+		struct dpu_encoder_kickoff_params *params)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	int ret;
+
+	if (!phys_enc || !phys_enc->hw_pp) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	DRM_DEBUG_KMS("id:%u pp:%d pending_cnt:%d\n", DRMID(phys_enc->parent),
+		      phys_enc->hw_pp->idx - PINGPONG_0,
+		      atomic_read(&phys_enc->pending_kickoff_cnt));
+
+	/*
+	 * Mark kickoff request as outstanding. If there are more than one,
+	 * outstanding, then we have to wait for the previous one to complete
+	 */
+	ret = _dpu_encoder_phys_cmd_wait_for_idle(phys_enc);
+	if (ret) {
+		/* force pending_kickoff_cnt 0 to discard failed kickoff */
+		atomic_set(&phys_enc->pending_kickoff_cnt, 0);
+		DRM_ERROR("failed wait_for_idle: id:%u ret:%d pp:%d\n",
+			  DRMID(phys_enc->parent), ret,
+			  phys_enc->hw_pp->idx - PINGPONG_0);
+	}
+
+	DPU_DEBUG_CMDENC(cmd_enc, "pp:%d pending_cnt %d\n",
+			phys_enc->hw_pp->idx - PINGPONG_0,
+			atomic_read(&phys_enc->pending_kickoff_cnt));
+}
+
+static int _dpu_encoder_phys_cmd_wait_for_ctl_start(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	struct dpu_encoder_wait_info wait_info;
+	int ret;
+
+	if (!phys_enc || !phys_enc->hw_ctl) {
+		DPU_ERROR("invalid argument(s)\n");
+		return -EINVAL;
+	}
+
+	wait_info.wq = &phys_enc->pending_kickoff_wq;
+	wait_info.atomic_cnt = &phys_enc->pending_ctlstart_cnt;
+	wait_info.timeout_ms = KICKOFF_TIMEOUT_MS;
+
+	ret = dpu_encoder_helper_wait_for_irq(phys_enc, INTR_IDX_CTL_START,
+			&wait_info);
+	if (ret == -ETIMEDOUT) {
+		DPU_ERROR_CMDENC(cmd_enc, "ctl start interrupt wait failed\n");
+		ret = -EINVAL;
+	} else if (!ret)
+		ret = 0;
+
+	return ret;
+}
+
+static int dpu_encoder_phys_cmd_wait_for_tx_complete(
+		struct dpu_encoder_phys *phys_enc)
+{
+	int rc;
+	struct dpu_encoder_phys_cmd *cmd_enc;
+
+	if (!phys_enc)
+		return -EINVAL;
+
+	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
+
+	rc = _dpu_encoder_phys_cmd_wait_for_idle(phys_enc);
+	if (rc) {
+		DRM_ERROR("failed wait_for_idle: id:%u ret:%d intf:%d\n",
+			  DRMID(phys_enc->parent), rc,
+			  phys_enc->intf_idx - INTF_0);
+	}
+
+	return rc;
+}
+
+static int dpu_encoder_phys_cmd_wait_for_commit_done(
+		struct dpu_encoder_phys *phys_enc)
+{
+	int rc = 0;
+	struct dpu_encoder_phys_cmd *cmd_enc;
+
+	if (!phys_enc)
+		return -EINVAL;
+
+	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
+
+	/* only required for master controller */
+	if (dpu_encoder_phys_cmd_is_master(phys_enc))
+		rc = _dpu_encoder_phys_cmd_wait_for_ctl_start(phys_enc);
+
+	/* required for both controllers */
+	if (!rc && cmd_enc->serialize_wait4pp)
+		dpu_encoder_phys_cmd_prepare_for_kickoff(phys_enc, NULL);
+
+	return rc;
+}
+
+static int dpu_encoder_phys_cmd_wait_for_vblank(
+		struct dpu_encoder_phys *phys_enc)
+{
+	int rc = 0;
+	struct dpu_encoder_phys_cmd *cmd_enc;
+	struct dpu_encoder_wait_info wait_info;
+
+	if (!phys_enc)
+		return -EINVAL;
+
+	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
+
+	/* only required for master controller */
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		return rc;
+
+	wait_info.wq = &cmd_enc->pending_vblank_wq;
+	wait_info.atomic_cnt = &cmd_enc->pending_vblank_cnt;
+	wait_info.timeout_ms = _dpu_encoder_phys_cmd_get_idle_timeout(cmd_enc);
+
+	atomic_inc(&cmd_enc->pending_vblank_cnt);
+
+	rc = dpu_encoder_helper_wait_for_irq(phys_enc, INTR_IDX_RDPTR,
+			&wait_info);
+
+	return rc;
+}
+
+static void dpu_encoder_phys_cmd_handle_post_kickoff(
+		struct dpu_encoder_phys *phys_enc)
+{
+	if (!phys_enc)
+		return;
+
+	/**
+	 * re-enable external TE, either for the first time after enabling
+	 * or if disabled for Autorefresh
+	 */
+	_dpu_encoder_phys_cmd_connect_te(phys_enc, true);
+}
+
+static void dpu_encoder_phys_cmd_trigger_start(
+		struct dpu_encoder_phys *phys_enc)
+{
+	if (!phys_enc)
+		return;
+
+	dpu_encoder_helper_trigger_start(phys_enc);
+}
+
+static void dpu_encoder_phys_cmd_init_ops(
+		struct dpu_encoder_phys_ops *ops)
+{
+	ops->is_master = dpu_encoder_phys_cmd_is_master;
+	ops->mode_set = dpu_encoder_phys_cmd_mode_set;
+	ops->mode_fixup = dpu_encoder_phys_cmd_mode_fixup;
+	ops->enable = dpu_encoder_phys_cmd_enable;
+	ops->disable = dpu_encoder_phys_cmd_disable;
+	ops->destroy = dpu_encoder_phys_cmd_destroy;
+	ops->get_hw_resources = dpu_encoder_phys_cmd_get_hw_resources;
+	ops->control_vblank_irq = dpu_encoder_phys_cmd_control_vblank_irq;
+	ops->wait_for_commit_done = dpu_encoder_phys_cmd_wait_for_commit_done;
+	ops->prepare_for_kickoff = dpu_encoder_phys_cmd_prepare_for_kickoff;
+	ops->wait_for_tx_complete = dpu_encoder_phys_cmd_wait_for_tx_complete;
+	ops->wait_for_vblank = dpu_encoder_phys_cmd_wait_for_vblank;
+	ops->trigger_start = dpu_encoder_phys_cmd_trigger_start;
+	ops->needs_single_flush = dpu_encoder_phys_cmd_needs_single_flush;
+	ops->hw_reset = dpu_encoder_helper_hw_reset;
+	ops->irq_control = dpu_encoder_phys_cmd_irq_control;
+	ops->restore = dpu_encoder_phys_cmd_enable_helper;
+	ops->prepare_idle_pc = dpu_encoder_phys_cmd_prepare_idle_pc;
+	ops->handle_post_kickoff = dpu_encoder_phys_cmd_handle_post_kickoff;
+	ops->get_line_count = dpu_encoder_phys_cmd_get_line_count;
+}
+
+struct dpu_encoder_phys *dpu_encoder_phys_cmd_init(
+		struct dpu_enc_phys_init_params *p)
+{
+	struct dpu_encoder_phys *phys_enc = NULL;
+	struct dpu_encoder_phys_cmd *cmd_enc = NULL;
+	struct dpu_hw_mdp *hw_mdp;
+	struct dpu_encoder_irq *irq;
+	int i, ret = 0;
+
+	DPU_DEBUG("intf %d\n", p->intf_idx - INTF_0);
+
+	cmd_enc = kzalloc(sizeof(*cmd_enc), GFP_KERNEL);
+	if (!cmd_enc) {
+		ret = -ENOMEM;
+		DPU_ERROR("failed to allocate\n");
+		goto fail;
+	}
+	phys_enc = &cmd_enc->base;
+
+	hw_mdp = dpu_rm_get_mdp(&p->dpu_kms->rm);
+	if (IS_ERR_OR_NULL(hw_mdp)) {
+		ret = PTR_ERR(hw_mdp);
+		DPU_ERROR("failed to get mdptop\n");
+		goto fail_mdp_init;
+	}
+	phys_enc->hw_mdptop = hw_mdp;
+	phys_enc->intf_idx = p->intf_idx;
+
+	dpu_encoder_phys_cmd_init_ops(&phys_enc->ops);
+	phys_enc->parent = p->parent;
+	phys_enc->parent_ops = p->parent_ops;
+	phys_enc->dpu_kms = p->dpu_kms;
+	phys_enc->split_role = p->split_role;
+	phys_enc->intf_mode = INTF_MODE_CMD;
+	phys_enc->enc_spinlock = p->enc_spinlock;
+	cmd_enc->stream_sel = 0;
+	phys_enc->enable_state = DPU_ENC_DISABLED;
+	for (i = 0; i < INTR_IDX_MAX; i++) {
+		irq = &phys_enc->irq[i];
+		INIT_LIST_HEAD(&irq->cb.list);
+		irq->irq_idx = -EINVAL;
+		irq->hw_idx = -EINVAL;
+		irq->cb.arg = phys_enc;
+	}
+
+	irq = &phys_enc->irq[INTR_IDX_CTL_START];
+	irq->name = "ctl_start";
+	irq->intr_type = DPU_IRQ_TYPE_CTL_START;
+	irq->intr_idx = INTR_IDX_CTL_START;
+	irq->cb.func = dpu_encoder_phys_cmd_ctl_start_irq;
+
+	irq = &phys_enc->irq[INTR_IDX_PINGPONG];
+	irq->name = "pp_done";
+	irq->intr_type = DPU_IRQ_TYPE_PING_PONG_COMP;
+	irq->intr_idx = INTR_IDX_PINGPONG;
+	irq->cb.func = dpu_encoder_phys_cmd_pp_tx_done_irq;
+
+	irq = &phys_enc->irq[INTR_IDX_RDPTR];
+	irq->name = "pp_rd_ptr";
+	irq->intr_type = DPU_IRQ_TYPE_PING_PONG_RD_PTR;
+	irq->intr_idx = INTR_IDX_RDPTR;
+	irq->cb.func = dpu_encoder_phys_cmd_pp_rd_ptr_irq;
+
+	irq = &phys_enc->irq[INTR_IDX_UNDERRUN];
+	irq->name = "underrun";
+	irq->intr_type = DPU_IRQ_TYPE_INTF_UNDER_RUN;
+	irq->intr_idx = INTR_IDX_UNDERRUN;
+	irq->cb.func = dpu_encoder_phys_cmd_underrun_irq;
+
+	atomic_set(&phys_enc->vblank_refcount, 0);
+	atomic_set(&phys_enc->pending_kickoff_cnt, 0);
+	atomic_set(&phys_enc->pending_ctlstart_cnt, 0);
+	atomic_set(&cmd_enc->pending_vblank_cnt, 0);
+	init_waitqueue_head(&phys_enc->pending_kickoff_wq);
+	init_waitqueue_head(&cmd_enc->pending_vblank_wq);
+
+	DPU_DEBUG_CMDENC(cmd_enc, "created\n");
+
+	return phys_enc;
+
+fail_mdp_init:
+	kfree(cmd_enc);
+fail:
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
new file mode 100644
index 000000000000..14fc7c2a6bb7
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
@@ -0,0 +1,922 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include "dpu_encoder_phys.h"
+#include "dpu_hw_interrupts.h"
+#include "dpu_core_irq.h"
+#include "dpu_formats.h"
+#include "dpu_trace.h"
+
+#define DPU_DEBUG_VIDENC(e, fmt, ...) DPU_DEBUG("enc%d intf%d " fmt, \
+		(e) && (e)->base.parent ? \
+		(e)->base.parent->base.id : -1, \
+		(e) && (e)->hw_intf ? \
+		(e)->hw_intf->idx - INTF_0 : -1, ##__VA_ARGS__)
+
+#define DPU_ERROR_VIDENC(e, fmt, ...) DPU_ERROR("enc%d intf%d " fmt, \
+		(e) && (e)->base.parent ? \
+		(e)->base.parent->base.id : -1, \
+		(e) && (e)->hw_intf ? \
+		(e)->hw_intf->idx - INTF_0 : -1, ##__VA_ARGS__)
+
+#define to_dpu_encoder_phys_vid(x) \
+	container_of(x, struct dpu_encoder_phys_vid, base)
+
+static bool dpu_encoder_phys_vid_is_master(
+		struct dpu_encoder_phys *phys_enc)
+{
+	bool ret = false;
+
+	if (phys_enc->split_role != ENC_ROLE_SLAVE)
+		ret = true;
+
+	return ret;
+}
+
+static void drm_mode_to_intf_timing_params(
+		const struct dpu_encoder_phys_vid *vid_enc,
+		const struct drm_display_mode *mode,
+		struct intf_timing_params *timing)
+{
+	memset(timing, 0, sizeof(*timing));
+
+	if ((mode->htotal < mode->hsync_end)
+			|| (mode->hsync_start < mode->hdisplay)
+			|| (mode->vtotal < mode->vsync_end)
+			|| (mode->vsync_start < mode->vdisplay)
+			|| (mode->hsync_end < mode->hsync_start)
+			|| (mode->vsync_end < mode->vsync_start)) {
+		DPU_ERROR(
+		    "invalid params - hstart:%d,hend:%d,htot:%d,hdisplay:%d\n",
+				mode->hsync_start, mode->hsync_end,
+				mode->htotal, mode->hdisplay);
+		DPU_ERROR("vstart:%d,vend:%d,vtot:%d,vdisplay:%d\n",
+				mode->vsync_start, mode->vsync_end,
+				mode->vtotal, mode->vdisplay);
+		return;
+	}
+
+	/*
+	 * https://www.kernel.org/doc/htmldocs/drm/ch02s05.html
+	 *  Active Region      Front Porch   Sync   Back Porch
+	 * <-----------------><------------><-----><----------->
+	 * <- [hv]display --->
+	 * <--------- [hv]sync_start ------>
+	 * <----------------- [hv]sync_end ------->
+	 * <---------------------------- [hv]total ------------->
+	 */
+	timing->width = mode->hdisplay;	/* active width */
+	timing->height = mode->vdisplay;	/* active height */
+	timing->xres = timing->width;
+	timing->yres = timing->height;
+	timing->h_back_porch = mode->htotal - mode->hsync_end;
+	timing->h_front_porch = mode->hsync_start - mode->hdisplay;
+	timing->v_back_porch = mode->vtotal - mode->vsync_end;
+	timing->v_front_porch = mode->vsync_start - mode->vdisplay;
+	timing->hsync_pulse_width = mode->hsync_end - mode->hsync_start;
+	timing->vsync_pulse_width = mode->vsync_end - mode->vsync_start;
+	timing->hsync_polarity = (mode->flags & DRM_MODE_FLAG_NHSYNC) ? 1 : 0;
+	timing->vsync_polarity = (mode->flags & DRM_MODE_FLAG_NVSYNC) ? 1 : 0;
+	timing->border_clr = 0;
+	timing->underflow_clr = 0xff;
+	timing->hsync_skew = mode->hskew;
+
+	/* DSI controller cannot handle active-low sync signals. */
+	if (vid_enc->hw_intf->cap->type == INTF_DSI) {
+		timing->hsync_polarity = 0;
+		timing->vsync_polarity = 0;
+	}
+
+	/*
+	 * For edp only:
+	 * DISPLAY_V_START = (VBP * HCYCLE) + HBP
+	 * DISPLAY_V_END = (VBP + VACTIVE) * HCYCLE - 1 - HFP
+	 */
+	/*
+	 * if (vid_enc->hw->cap->type == INTF_EDP) {
+	 * display_v_start += mode->htotal - mode->hsync_start;
+	 * display_v_end -= mode->hsync_start - mode->hdisplay;
+	 * }
+	 */
+}
+
+static inline u32 get_horizontal_total(const struct intf_timing_params *timing)
+{
+	u32 active = timing->xres;
+	u32 inactive =
+	    timing->h_back_porch + timing->h_front_porch +
+	    timing->hsync_pulse_width;
+	return active + inactive;
+}
+
+static inline u32 get_vertical_total(const struct intf_timing_params *timing)
+{
+	u32 active = timing->yres;
+	u32 inactive =
+	    timing->v_back_porch + timing->v_front_porch +
+	    timing->vsync_pulse_width;
+	return active + inactive;
+}
+
+/*
+ * programmable_fetch_get_num_lines:
+ *	Number of fetch lines in vertical front porch
+ * @timing: Pointer to the intf timing information for the requested mode
+ *
+ * Returns the number of fetch lines in vertical front porch at which mdp
+ * can start fetching the next frame.
+ *
+ * Number of needed prefetch lines is anything that cannot be absorbed in the
+ * start of frame time (back porch + vsync pulse width).
+ *
+ * Some panels have very large VFP, however we only need a total number of
+ * lines based on the chip worst case latencies.
+ */
+static u32 programmable_fetch_get_num_lines(
+		struct dpu_encoder_phys_vid *vid_enc,
+		const struct intf_timing_params *timing)
+{
+	u32 worst_case_needed_lines =
+	    vid_enc->hw_intf->cap->prog_fetch_lines_worst_case;
+	u32 start_of_frame_lines =
+	    timing->v_back_porch + timing->vsync_pulse_width;
+	u32 needed_vfp_lines = worst_case_needed_lines - start_of_frame_lines;
+	u32 actual_vfp_lines = 0;
+
+	/* Fetch must be outside active lines, otherwise undefined. */
+	if (start_of_frame_lines >= worst_case_needed_lines) {
+		DPU_DEBUG_VIDENC(vid_enc,
+				"prog fetch is not needed, large vbp+vsw\n");
+		actual_vfp_lines = 0;
+	} else if (timing->v_front_porch < needed_vfp_lines) {
+		/* Warn fetch needed, but not enough porch in panel config */
+		pr_warn_once
+			("low vbp+vfp may lead to perf issues in some cases\n");
+		DPU_DEBUG_VIDENC(vid_enc,
+				"less vfp than fetch req, using entire vfp\n");
+		actual_vfp_lines = timing->v_front_porch;
+	} else {
+		DPU_DEBUG_VIDENC(vid_enc, "room in vfp for needed prefetch\n");
+		actual_vfp_lines = needed_vfp_lines;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc,
+		"v_front_porch %u v_back_porch %u vsync_pulse_width %u\n",
+		timing->v_front_porch, timing->v_back_porch,
+		timing->vsync_pulse_width);
+	DPU_DEBUG_VIDENC(vid_enc,
+		"wc_lines %u needed_vfp_lines %u actual_vfp_lines %u\n",
+		worst_case_needed_lines, needed_vfp_lines, actual_vfp_lines);
+
+	return actual_vfp_lines;
+}
+
+/*
+ * programmable_fetch_config: Programs HW to prefetch lines by offsetting
+ *	the start of fetch into the vertical front porch for cases where the
+ *	vsync pulse width and vertical back porch time is insufficient
+ *
+ *	Gets # of lines to pre-fetch, then calculate VSYNC counter value.
+ *	HW layer requires VSYNC counter of first pixel of tgt VFP line.
+ *
+ * @timing: Pointer to the intf timing information for the requested mode
+ */
+static void programmable_fetch_config(struct dpu_encoder_phys *phys_enc,
+				      const struct intf_timing_params *timing)
+{
+	struct dpu_encoder_phys_vid *vid_enc =
+		to_dpu_encoder_phys_vid(phys_enc);
+	struct intf_prog_fetch f = { 0 };
+	u32 vfp_fetch_lines = 0;
+	u32 horiz_total = 0;
+	u32 vert_total = 0;
+	u32 vfp_fetch_start_vsync_counter = 0;
+	unsigned long lock_flags;
+
+	if (WARN_ON_ONCE(!vid_enc->hw_intf->ops.setup_prg_fetch))
+		return;
+
+	vfp_fetch_lines = programmable_fetch_get_num_lines(vid_enc, timing);
+	if (vfp_fetch_lines) {
+		vert_total = get_vertical_total(timing);
+		horiz_total = get_horizontal_total(timing);
+		vfp_fetch_start_vsync_counter =
+		    (vert_total - vfp_fetch_lines) * horiz_total + 1;
+		f.enable = 1;
+		f.fetch_start = vfp_fetch_start_vsync_counter;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc,
+		"vfp_fetch_lines %u vfp_fetch_start_vsync_counter %u\n",
+		vfp_fetch_lines, vfp_fetch_start_vsync_counter);
+
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	vid_enc->hw_intf->ops.setup_prg_fetch(vid_enc->hw_intf, &f);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+}
+
+static bool dpu_encoder_phys_vid_mode_fixup(
+		struct dpu_encoder_phys *phys_enc,
+		const struct drm_display_mode *mode,
+		struct drm_display_mode *adj_mode)
+{
+	if (phys_enc)
+		DPU_DEBUG_VIDENC(to_dpu_encoder_phys_vid(phys_enc), "\n");
+
+	/*
+	 * Modifying mode has consequences when the mode comes back to us
+	 */
+	return true;
+}
+
+static void dpu_encoder_phys_vid_setup_timing_engine(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+	struct drm_display_mode mode;
+	struct intf_timing_params timing_params = { 0 };
+	const struct dpu_format *fmt = NULL;
+	u32 fmt_fourcc = DRM_FORMAT_RGB888;
+	unsigned long lock_flags;
+	struct dpu_hw_intf_cfg intf_cfg = { 0 };
+
+	if (!phys_enc || !phys_enc->hw_ctl->ops.setup_intf_cfg) {
+		DPU_ERROR("invalid encoder %d\n", phys_enc != 0);
+		return;
+	}
+
+	mode = phys_enc->cached_mode;
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	if (!vid_enc->hw_intf->ops.setup_timing_gen) {
+		DPU_ERROR("timing engine setup is not supported\n");
+		return;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc, "enabling mode:\n");
+	drm_mode_debug_printmodeline(&mode);
+
+	if (phys_enc->split_role != ENC_ROLE_SOLO) {
+		mode.hdisplay >>= 1;
+		mode.htotal >>= 1;
+		mode.hsync_start >>= 1;
+		mode.hsync_end >>= 1;
+
+		DPU_DEBUG_VIDENC(vid_enc,
+			"split_role %d, halve horizontal %d %d %d %d\n",
+			phys_enc->split_role,
+			mode.hdisplay, mode.htotal,
+			mode.hsync_start, mode.hsync_end);
+	}
+
+	drm_mode_to_intf_timing_params(vid_enc, &mode, &timing_params);
+
+	fmt = dpu_get_dpu_format(fmt_fourcc);
+	DPU_DEBUG_VIDENC(vid_enc, "fmt_fourcc 0x%X\n", fmt_fourcc);
+
+	intf_cfg.intf = vid_enc->hw_intf->idx;
+	intf_cfg.intf_mode_sel = DPU_CTL_MODE_SEL_VID;
+	intf_cfg.stream_sel = 0; /* Don't care value for video mode */
+	intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc);
+
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	vid_enc->hw_intf->ops.setup_timing_gen(vid_enc->hw_intf,
+			&timing_params, fmt);
+	phys_enc->hw_ctl->ops.setup_intf_cfg(phys_enc->hw_ctl, &intf_cfg);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+
+	programmable_fetch_config(phys_enc, &timing_params);
+
+	vid_enc->timing_params = timing_params;
+}
+
+static void dpu_encoder_phys_vid_vblank_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+	struct dpu_hw_ctl *hw_ctl;
+	unsigned long lock_flags;
+	u32 flush_register = 0;
+	int new_cnt = -1, old_cnt = -1;
+
+	if (!phys_enc)
+		return;
+
+	hw_ctl = phys_enc->hw_ctl;
+	if (!hw_ctl)
+		return;
+
+	DPU_ATRACE_BEGIN("vblank_irq");
+
+	if (phys_enc->parent_ops->handle_vblank_virt)
+		phys_enc->parent_ops->handle_vblank_virt(phys_enc->parent,
+				phys_enc);
+
+	old_cnt  = atomic_read(&phys_enc->pending_kickoff_cnt);
+
+	/*
+	 * only decrement the pending flush count if we've actually flushed
+	 * hardware. due to sw irq latency, vblank may have already happened
+	 * so we need to double-check with hw that it accepted the flush bits
+	 */
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	if (hw_ctl && hw_ctl->ops.get_flush_register)
+		flush_register = hw_ctl->ops.get_flush_register(hw_ctl);
+
+	if (flush_register == 0)
+		new_cnt = atomic_add_unless(&phys_enc->pending_kickoff_cnt,
+				-1, 0);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+
+	/* Signal any waiting atomic commit thread */
+	wake_up_all(&phys_enc->pending_kickoff_wq);
+	DPU_ATRACE_END("vblank_irq");
+}
+
+static void dpu_encoder_phys_vid_underrun_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+
+	if (!phys_enc)
+		return;
+
+	if (phys_enc->parent_ops->handle_underrun_virt)
+		phys_enc->parent_ops->handle_underrun_virt(phys_enc->parent,
+			phys_enc);
+}
+
+static bool _dpu_encoder_phys_is_dual_ctl(struct dpu_encoder_phys *phys_enc)
+{
+	if (!phys_enc)
+		return false;
+
+	if (phys_enc->topology_name == DPU_RM_TOPOLOGY_DUALPIPE)
+		return true;
+
+	return false;
+}
+
+static bool dpu_encoder_phys_vid_needs_single_flush(
+		struct dpu_encoder_phys *phys_enc)
+{
+	return (phys_enc && _dpu_encoder_phys_is_dual_ctl(phys_enc));
+}
+
+static void _dpu_encoder_phys_vid_setup_irq_hw_idx(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_irq *irq;
+
+	/*
+	 * Initialize irq->hw_idx only when irq is not registered.
+	 * Prevent invalidating irq->irq_idx as modeset may be
+	 * called many times during dfps.
+	 */
+
+	irq = &phys_enc->irq[INTR_IDX_VSYNC];
+	if (irq->irq_idx < 0)
+		irq->hw_idx = phys_enc->intf_idx;
+
+	irq = &phys_enc->irq[INTR_IDX_UNDERRUN];
+	if (irq->irq_idx < 0)
+		irq->hw_idx = phys_enc->intf_idx;
+}
+
+static void dpu_encoder_phys_vid_mode_set(
+		struct dpu_encoder_phys *phys_enc,
+		struct drm_display_mode *mode,
+		struct drm_display_mode *adj_mode)
+{
+	struct dpu_rm *rm;
+	struct dpu_rm_hw_iter iter;
+	int i, instance;
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc || !phys_enc->dpu_kms) {
+		DPU_ERROR("invalid encoder/kms\n");
+		return;
+	}
+
+	rm = &phys_enc->dpu_kms->rm;
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+
+	if (adj_mode) {
+		phys_enc->cached_mode = *adj_mode;
+		drm_mode_debug_printmodeline(adj_mode);
+		DPU_DEBUG_VIDENC(vid_enc, "caching mode:\n");
+	}
+
+	instance = phys_enc->split_role == ENC_ROLE_SLAVE ? 1 : 0;
+
+	/* Retrieve previously allocated HW Resources. Shouldn't fail */
+	dpu_rm_init_hw_iter(&iter, phys_enc->parent->base.id, DPU_HW_BLK_CTL);
+	for (i = 0; i <= instance; i++) {
+		if (dpu_rm_get_hw(rm, &iter))
+			phys_enc->hw_ctl = (struct dpu_hw_ctl *)iter.hw;
+	}
+	if (IS_ERR_OR_NULL(phys_enc->hw_ctl)) {
+		DPU_ERROR_VIDENC(vid_enc, "failed to init ctl, %ld\n",
+				PTR_ERR(phys_enc->hw_ctl));
+		phys_enc->hw_ctl = NULL;
+		return;
+	}
+
+	_dpu_encoder_phys_vid_setup_irq_hw_idx(phys_enc);
+}
+
+static int dpu_encoder_phys_vid_control_vblank_irq(
+		struct dpu_encoder_phys *phys_enc,
+		bool enable)
+{
+	int ret = 0;
+	struct dpu_encoder_phys_vid *vid_enc;
+	int refcount;
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return -EINVAL;
+	}
+
+	refcount = atomic_read(&phys_enc->vblank_refcount);
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+
+	/* Slave encoders don't report vblank */
+	if (!dpu_encoder_phys_vid_is_master(phys_enc))
+		goto end;
+
+	/* protect against negative */
+	if (!enable && refcount == 0) {
+		ret = -EINVAL;
+		goto end;
+	}
+
+	DRM_DEBUG_KMS("id:%u enable=%d/%d\n", DRMID(phys_enc->parent), enable,
+		      atomic_read(&phys_enc->vblank_refcount));
+
+	if (enable && atomic_inc_return(&phys_enc->vblank_refcount) == 1)
+		ret = dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_VSYNC);
+	else if (!enable && atomic_dec_return(&phys_enc->vblank_refcount) == 0)
+		ret = dpu_encoder_helper_unregister_irq(phys_enc,
+				INTR_IDX_VSYNC);
+
+end:
+	if (ret) {
+		DRM_ERROR("failed: id:%u intf:%d ret:%d enable:%d refcnt:%d\n",
+			  DRMID(phys_enc->parent),
+			  vid_enc->hw_intf->idx - INTF_0, ret, enable,
+			  refcount);
+	}
+	return ret;
+}
+
+static void dpu_encoder_phys_vid_enable(struct dpu_encoder_phys *phys_enc)
+{
+	struct msm_drm_private *priv;
+	struct dpu_encoder_phys_vid *vid_enc;
+	struct dpu_hw_intf *intf;
+	struct dpu_hw_ctl *ctl;
+	u32 flush_mask = 0;
+
+	if (!phys_enc || !phys_enc->parent || !phys_enc->parent->dev ||
+			!phys_enc->parent->dev->dev_private) {
+		DPU_ERROR("invalid encoder/device\n");
+		return;
+	}
+	priv = phys_enc->parent->dev->dev_private;
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	intf = vid_enc->hw_intf;
+	ctl = phys_enc->hw_ctl;
+	if (!vid_enc->hw_intf || !phys_enc->hw_ctl) {
+		DPU_ERROR("invalid hw_intf %d hw_ctl %d\n",
+				vid_enc->hw_intf != 0, phys_enc->hw_ctl != 0);
+		return;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc, "\n");
+
+	if (WARN_ON(!vid_enc->hw_intf->ops.enable_timing))
+		return;
+
+	dpu_encoder_helper_split_config(phys_enc, vid_enc->hw_intf->idx);
+
+	dpu_encoder_phys_vid_setup_timing_engine(phys_enc);
+
+	/*
+	 * For single flush cases (dual-ctl or pp-split), skip setting the
+	 * flush bit for the slave intf, since both intfs use same ctl
+	 * and HW will only flush the master.
+	 */
+	if (dpu_encoder_phys_vid_needs_single_flush(phys_enc) &&
+		!dpu_encoder_phys_vid_is_master(phys_enc))
+		goto skip_flush;
+
+	ctl->ops.get_bitmask_intf(ctl, &flush_mask, intf->idx);
+	ctl->ops.update_pending_flush(ctl, flush_mask);
+
+skip_flush:
+	DPU_DEBUG_VIDENC(vid_enc, "update pending flush ctl %d flush_mask %x\n",
+		ctl->idx - CTL_0, flush_mask);
+
+	/* ctl_flush & timing engine enable will be triggered by framework */
+	if (phys_enc->enable_state == DPU_ENC_DISABLED)
+		phys_enc->enable_state = DPU_ENC_ENABLING;
+}
+
+static void dpu_encoder_phys_vid_destroy(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	DPU_DEBUG_VIDENC(vid_enc, "\n");
+	kfree(vid_enc);
+}
+
+static void dpu_encoder_phys_vid_get_hw_resources(
+		struct dpu_encoder_phys *phys_enc,
+		struct dpu_encoder_hw_resources *hw_res,
+		struct drm_connector_state *conn_state)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc || !hw_res) {
+		DPU_ERROR("invalid arg(s), enc %d hw_res %d conn_state %d\n",
+				phys_enc != 0, hw_res != 0, conn_state != 0);
+		return;
+	}
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	if (!vid_enc->hw_intf) {
+		DPU_ERROR("invalid arg(s), hw_intf\n");
+		return;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc, "\n");
+	hw_res->intfs[vid_enc->hw_intf->idx - INTF_0] = INTF_MODE_VIDEO;
+}
+
+static int _dpu_encoder_phys_vid_wait_for_vblank(
+		struct dpu_encoder_phys *phys_enc, bool notify)
+{
+	struct dpu_encoder_wait_info wait_info;
+	int ret;
+
+	if (!phys_enc) {
+		pr_err("invalid encoder\n");
+		return -EINVAL;
+	}
+
+	wait_info.wq = &phys_enc->pending_kickoff_wq;
+	wait_info.atomic_cnt = &phys_enc->pending_kickoff_cnt;
+	wait_info.timeout_ms = KICKOFF_TIMEOUT_MS;
+
+	if (!dpu_encoder_phys_vid_is_master(phys_enc)) {
+		if (notify && phys_enc->parent_ops->handle_frame_done)
+			phys_enc->parent_ops->handle_frame_done(
+					phys_enc->parent, phys_enc,
+					DPU_ENCODER_FRAME_EVENT_DONE);
+		return 0;
+	}
+
+	/* Wait for kickoff to complete */
+	ret = dpu_encoder_helper_wait_for_irq(phys_enc, INTR_IDX_VSYNC,
+			&wait_info);
+
+	if (ret == -ETIMEDOUT) {
+		dpu_encoder_helper_report_irq_timeout(phys_enc, INTR_IDX_VSYNC);
+	} else if (!ret && notify && phys_enc->parent_ops->handle_frame_done)
+		phys_enc->parent_ops->handle_frame_done(
+				phys_enc->parent, phys_enc,
+				DPU_ENCODER_FRAME_EVENT_DONE);
+
+	return ret;
+}
+
+static int dpu_encoder_phys_vid_wait_for_vblank(
+		struct dpu_encoder_phys *phys_enc)
+{
+	return _dpu_encoder_phys_vid_wait_for_vblank(phys_enc, true);
+}
+
+static void dpu_encoder_phys_vid_prepare_for_kickoff(
+		struct dpu_encoder_phys *phys_enc,
+		struct dpu_encoder_kickoff_params *params)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+	struct dpu_hw_ctl *ctl;
+	int rc;
+
+	if (!phys_enc || !params) {
+		DPU_ERROR("invalid encoder/parameters\n");
+		return;
+	}
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+
+	ctl = phys_enc->hw_ctl;
+	if (!ctl || !ctl->ops.wait_reset_status)
+		return;
+
+	/*
+	 * hw supports hardware initiated ctl reset, so before we kickoff a new
+	 * frame, need to check and wait for hw initiated ctl reset completion
+	 */
+	rc = ctl->ops.wait_reset_status(ctl);
+	if (rc) {
+		DPU_ERROR_VIDENC(vid_enc, "ctl %d reset failure: %d\n",
+				ctl->idx, rc);
+		dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_VSYNC);
+		dpu_dbg_dump(false, __func__, true, true);
+	}
+}
+
+static void dpu_encoder_phys_vid_disable(struct dpu_encoder_phys *phys_enc)
+{
+	struct msm_drm_private *priv;
+	struct dpu_encoder_phys_vid *vid_enc;
+	unsigned long lock_flags;
+	int ret;
+
+	if (!phys_enc || !phys_enc->parent || !phys_enc->parent->dev ||
+			!phys_enc->parent->dev->dev_private) {
+		DPU_ERROR("invalid encoder/device\n");
+		return;
+	}
+	priv = phys_enc->parent->dev->dev_private;
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	if (!vid_enc->hw_intf || !phys_enc->hw_ctl) {
+		DPU_ERROR("invalid hw_intf %d hw_ctl %d\n",
+				vid_enc->hw_intf != 0, phys_enc->hw_ctl != 0);
+		return;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc, "\n");
+
+	if (WARN_ON(!vid_enc->hw_intf->ops.enable_timing))
+		return;
+
+	if (phys_enc->enable_state == DPU_ENC_DISABLED) {
+		DPU_ERROR("already disabled\n");
+		return;
+	}
+
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	vid_enc->hw_intf->ops.enable_timing(vid_enc->hw_intf, 0);
+	if (dpu_encoder_phys_vid_is_master(phys_enc))
+		dpu_encoder_phys_inc_pending(phys_enc);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+
+	/*
+	 * Wait for a vsync so we know the ENABLE=0 latched before
+	 * the (connector) source of the vsync's gets disabled,
+	 * otherwise we end up in a funny state if we re-enable
+	 * before the disable latches, which results that some of
+	 * the settings changes for the new modeset (like new
+	 * scanout buffer) don't latch properly..
+	 */
+	if (dpu_encoder_phys_vid_is_master(phys_enc)) {
+		ret = _dpu_encoder_phys_vid_wait_for_vblank(phys_enc, false);
+		if (ret) {
+			atomic_set(&phys_enc->pending_kickoff_cnt, 0);
+			DRM_ERROR("wait disable failed: id:%u intf:%d ret:%d\n",
+				  DRMID(phys_enc->parent),
+				  vid_enc->hw_intf->idx - INTF_0, ret);
+		}
+	}
+
+	phys_enc->enable_state = DPU_ENC_DISABLED;
+}
+
+static void dpu_encoder_phys_vid_handle_post_kickoff(
+		struct dpu_encoder_phys *phys_enc)
+{
+	unsigned long lock_flags;
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	DPU_DEBUG_VIDENC(vid_enc, "enable_state %d\n", phys_enc->enable_state);
+
+	/*
+	 * Video mode must flush CTL before enabling timing engine
+	 * Video encoders need to turn on their interfaces now
+	 */
+	if (phys_enc->enable_state == DPU_ENC_ENABLING) {
+		trace_dpu_enc_phys_vid_post_kickoff(DRMID(phys_enc->parent),
+				    vid_enc->hw_intf->idx - INTF_0);
+		spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+		vid_enc->hw_intf->ops.enable_timing(vid_enc->hw_intf, 1);
+		spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+		phys_enc->enable_state = DPU_ENC_ENABLED;
+	}
+}
+
+static void dpu_encoder_phys_vid_irq_control(struct dpu_encoder_phys *phys_enc,
+		bool enable)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+	int ret;
+
+	if (!phys_enc)
+		return;
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+
+	trace_dpu_enc_phys_vid_irq_ctrl(DRMID(phys_enc->parent),
+			    vid_enc->hw_intf->idx - INTF_0,
+			    enable,
+			    atomic_read(&phys_enc->vblank_refcount));
+
+	if (enable) {
+		ret = dpu_encoder_phys_vid_control_vblank_irq(phys_enc, true);
+		if (ret)
+			return;
+
+		dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_UNDERRUN);
+	} else {
+		dpu_encoder_phys_vid_control_vblank_irq(phys_enc, false);
+		dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_UNDERRUN);
+	}
+}
+
+static void dpu_encoder_phys_vid_setup_misr(struct dpu_encoder_phys *phys_enc,
+						bool enable, u32 frame_count)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc)
+		return;
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+
+	if (vid_enc->hw_intf && vid_enc->hw_intf->ops.setup_misr)
+		vid_enc->hw_intf->ops.setup_misr(vid_enc->hw_intf,
+							enable, frame_count);
+}
+
+static u32 dpu_encoder_phys_vid_collect_misr(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc)
+		return 0;
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+
+	return vid_enc->hw_intf && vid_enc->hw_intf->ops.collect_misr ?
+		vid_enc->hw_intf->ops.collect_misr(vid_enc->hw_intf) : 0;
+}
+
+static int dpu_encoder_phys_vid_get_line_count(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc)
+		return -EINVAL;
+
+	if (!dpu_encoder_phys_vid_is_master(phys_enc))
+		return -EINVAL;
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	if (!vid_enc->hw_intf || !vid_enc->hw_intf->ops.get_line_count)
+		return -EINVAL;
+
+	return vid_enc->hw_intf->ops.get_line_count(vid_enc->hw_intf);
+}
+
+static void dpu_encoder_phys_vid_init_ops(struct dpu_encoder_phys_ops *ops)
+{
+	ops->is_master = dpu_encoder_phys_vid_is_master;
+	ops->mode_set = dpu_encoder_phys_vid_mode_set;
+	ops->mode_fixup = dpu_encoder_phys_vid_mode_fixup;
+	ops->enable = dpu_encoder_phys_vid_enable;
+	ops->disable = dpu_encoder_phys_vid_disable;
+	ops->destroy = dpu_encoder_phys_vid_destroy;
+	ops->get_hw_resources = dpu_encoder_phys_vid_get_hw_resources;
+	ops->control_vblank_irq = dpu_encoder_phys_vid_control_vblank_irq;
+	ops->wait_for_commit_done = dpu_encoder_phys_vid_wait_for_vblank;
+	ops->wait_for_vblank = dpu_encoder_phys_vid_wait_for_vblank;
+	ops->wait_for_tx_complete = dpu_encoder_phys_vid_wait_for_vblank;
+	ops->irq_control = dpu_encoder_phys_vid_irq_control;
+	ops->prepare_for_kickoff = dpu_encoder_phys_vid_prepare_for_kickoff;
+	ops->handle_post_kickoff = dpu_encoder_phys_vid_handle_post_kickoff;
+	ops->needs_single_flush = dpu_encoder_phys_vid_needs_single_flush;
+	ops->setup_misr = dpu_encoder_phys_vid_setup_misr;
+	ops->collect_misr = dpu_encoder_phys_vid_collect_misr;
+	ops->hw_reset = dpu_encoder_helper_hw_reset;
+	ops->get_line_count = dpu_encoder_phys_vid_get_line_count;
+}
+
+struct dpu_encoder_phys *dpu_encoder_phys_vid_init(
+		struct dpu_enc_phys_init_params *p)
+{
+	struct dpu_encoder_phys *phys_enc = NULL;
+	struct dpu_encoder_phys_vid *vid_enc = NULL;
+	struct dpu_rm_hw_iter iter;
+	struct dpu_hw_mdp *hw_mdp;
+	struct dpu_encoder_irq *irq;
+	int i, ret = 0;
+
+	if (!p) {
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	vid_enc = kzalloc(sizeof(*vid_enc), GFP_KERNEL);
+	if (!vid_enc) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	phys_enc = &vid_enc->base;
+
+	hw_mdp = dpu_rm_get_mdp(&p->dpu_kms->rm);
+	if (IS_ERR_OR_NULL(hw_mdp)) {
+		ret = PTR_ERR(hw_mdp);
+		DPU_ERROR("failed to get mdptop\n");
+		goto fail;
+	}
+	phys_enc->hw_mdptop = hw_mdp;
+	phys_enc->intf_idx = p->intf_idx;
+
+	/**
+	 * hw_intf resource permanently assigned to this encoder
+	 * Other resources allocated at atomic commit time by use case
+	 */
+	dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_INTF);
+	while (dpu_rm_get_hw(&p->dpu_kms->rm, &iter)) {
+		struct dpu_hw_intf *hw_intf = (struct dpu_hw_intf *)iter.hw;
+
+		if (hw_intf->idx == p->intf_idx) {
+			vid_enc->hw_intf = hw_intf;
+			break;
+		}
+	}
+
+	if (!vid_enc->hw_intf) {
+		ret = -EINVAL;
+		DPU_ERROR("failed to get hw_intf\n");
+		goto fail;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc, "\n");
+
+	dpu_encoder_phys_vid_init_ops(&phys_enc->ops);
+	phys_enc->parent = p->parent;
+	phys_enc->parent_ops = p->parent_ops;
+	phys_enc->dpu_kms = p->dpu_kms;
+	phys_enc->split_role = p->split_role;
+	phys_enc->intf_mode = INTF_MODE_VIDEO;
+	phys_enc->enc_spinlock = p->enc_spinlock;
+	for (i = 0; i < INTR_IDX_MAX; i++) {
+		irq = &phys_enc->irq[i];
+		INIT_LIST_HEAD(&irq->cb.list);
+		irq->irq_idx = -EINVAL;
+		irq->hw_idx = -EINVAL;
+		irq->cb.arg = phys_enc;
+	}
+
+	irq = &phys_enc->irq[INTR_IDX_VSYNC];
+	irq->name = "vsync_irq";
+	irq->intr_type = DPU_IRQ_TYPE_INTF_VSYNC;
+	irq->intr_idx = INTR_IDX_VSYNC;
+	irq->cb.func = dpu_encoder_phys_vid_vblank_irq;
+
+	irq = &phys_enc->irq[INTR_IDX_UNDERRUN];
+	irq->name = "underrun";
+	irq->intr_type = DPU_IRQ_TYPE_INTF_UNDER_RUN;
+	irq->intr_idx = INTR_IDX_UNDERRUN;
+	irq->cb.func = dpu_encoder_phys_vid_underrun_irq;
+
+	atomic_set(&phys_enc->vblank_refcount, 0);
+	atomic_set(&phys_enc->pending_kickoff_cnt, 0);
+	init_waitqueue_head(&phys_enc->pending_kickoff_wq);
+	phys_enc->enable_state = DPU_ENC_DISABLED;
+
+	DPU_DEBUG_VIDENC(vid_enc, "created intf idx:%d\n", p->intf_idx);
+
+	return phys_enc;
+
+fail:
+	DPU_ERROR("failed to create encoder\n");
+	if (vid_enc)
+		dpu_encoder_phys_vid_destroy(phys_enc);
+
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
new file mode 100644
index 000000000000..bfcd165e96df
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
@@ -0,0 +1,1173 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <uapi/drm/drm_fourcc.h>
+
+#include "msm_media_info.h"
+#include "dpu_kms.h"
+#include "dpu_formats.h"
+
+#define DPU_UBWC_META_MACRO_W_H		16
+#define DPU_UBWC_META_BLOCK_SIZE	256
+#define DPU_UBWC_PLANE_SIZE_ALIGNMENT	4096
+
+#define DPU_TILE_HEIGHT_DEFAULT	1
+#define DPU_TILE_HEIGHT_TILED	4
+#define DPU_TILE_HEIGHT_UBWC	4
+#define DPU_TILE_HEIGHT_NV12	8
+
+#define DPU_MAX_IMG_WIDTH		0x3FFF
+#define DPU_MAX_IMG_HEIGHT		0x3FFF
+
+/**
+ * DPU supported format packing, bpp, and other format
+ * information.
+ * DPU currently only supports interleaved RGB formats
+ * UBWC support for a pixel format is indicated by the flag,
+ * there is additional meta data plane for such formats
+ */
+
+#define INTERLEAVED_RGB_FMT(fmt, a, r, g, b, e0, e1, e2, e3, uc, alpha,   \
+bp, flg, fm, np)                                                          \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_INTERLEAVED,                            \
+	.alpha_enable = alpha,                                            \
+	.element = { (e0), (e1), (e2), (e3) },                            \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = DPU_CHROMA_RGB,                                  \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = uc,                                               \
+	.bpp = bp,                                                        \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+#define INTERLEAVED_RGB_FMT_TILED(fmt, a, r, g, b, e0, e1, e2, e3, uc,    \
+alpha, bp, flg, fm, np, th)                                               \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_INTERLEAVED,                            \
+	.alpha_enable = alpha,                                            \
+	.element = { (e0), (e1), (e2), (e3) },                            \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = DPU_CHROMA_RGB,                                  \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = uc,                                               \
+	.bpp = bp,                                                        \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = th                                                 \
+}
+
+
+#define INTERLEAVED_YUV_FMT(fmt, a, r, g, b, e0, e1, e2, e3,              \
+alpha, chroma, count, bp, flg, fm, np)                                    \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_INTERLEAVED,                            \
+	.alpha_enable = alpha,                                            \
+	.element = { (e0), (e1), (e2), (e3)},                             \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = count,                                            \
+	.bpp = bp,                                                        \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+#define PSEUDO_YUV_FMT(fmt, a, r, g, b, e0, e1, chroma, flg, fm, np)      \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PSEUDO_PLANAR,                          \
+	.alpha_enable = false,                                            \
+	.element = { (e0), (e1), 0, 0 },                                  \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = 2,                                                \
+	.bpp = 2,                                                         \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+#define PSEUDO_YUV_FMT_TILED(fmt, a, r, g, b, e0, e1, chroma,             \
+flg, fm, np, th)                                                          \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PSEUDO_PLANAR,                          \
+	.alpha_enable = false,                                            \
+	.element = { (e0), (e1), 0, 0 },                                  \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = 2,                                                \
+	.bpp = 2,                                                         \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = th                                                 \
+}
+
+#define PSEUDO_YUV_FMT_LOOSE(fmt, a, r, g, b, e0, e1, chroma, flg, fm, np)\
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PSEUDO_PLANAR,                          \
+	.alpha_enable = false,                                            \
+	.element = { (e0), (e1), 0, 0 },                                  \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 1,                                            \
+	.unpack_tight = 0,                                                \
+	.unpack_count = 2,                                                \
+	.bpp = 2,                                                         \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+#define PSEUDO_YUV_FMT_LOOSE_TILED(fmt, a, r, g, b, e0, e1, chroma,       \
+flg, fm, np, th)                                                          \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PSEUDO_PLANAR,                          \
+	.alpha_enable = false,                                            \
+	.element = { (e0), (e1), 0, 0 },                                  \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 1,                                            \
+	.unpack_tight = 0,                                                \
+	.unpack_count = 2,                                                \
+	.bpp = 2,                                                         \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = th                                                 \
+}
+
+
+#define PLANAR_YUV_FMT(fmt, a, r, g, b, e0, e1, e2, alpha, chroma, bp,    \
+flg, fm, np)                                                      \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PLANAR,                                 \
+	.alpha_enable = alpha,                                            \
+	.element = { (e0), (e1), (e2), 0 },                               \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = 1,                                                \
+	.bpp = bp,                                                        \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+/*
+ * struct dpu_media_color_map - maps drm format to media format
+ * @format: DRM base pixel format
+ * @color: Media API color related to DRM format
+ */
+struct dpu_media_color_map {
+	uint32_t format;
+	uint32_t color;
+};
+
+static const struct dpu_format dpu_format_map[] = {
+	INTERLEAVED_RGB_FMT(ARGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		true, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ABGR8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XBGR8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBA8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		true, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRA8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		true, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRX8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		false, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XRGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		false, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBX8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		false, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGB888,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
+		false, 3, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGR888,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		false, 3, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGB565,
+		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGR565,
+		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ARGB1555,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ABGR1555,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBA5551,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRA5551,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XRGB1555,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XBGR1555,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBX5551,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRX5551,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ARGB4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ABGR4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBA4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRA4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XRGB4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XBGR4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBX4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRX4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRA1010102,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBA1010102,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ABGR2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ARGB2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XRGB2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		false, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRX1010102,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		false, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XBGR2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBX1010102,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		false, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	PSEUDO_YUV_FMT(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	PSEUDO_YUV_FMT(NV21,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C1_B_Cb,
+		DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	PSEUDO_YUV_FMT(NV16,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_H2V1, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	PSEUDO_YUV_FMT(NV61,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C1_B_Cb,
+		DPU_CHROMA_H2V1, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	INTERLEAVED_YUV_FMT(VYUY,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C0_G_Y,
+		false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	INTERLEAVED_YUV_FMT(UYVY,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C0_G_Y,
+		false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	INTERLEAVED_YUV_FMT(YUYV,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C0_G_Y, C1_B_Cb, C0_G_Y, C2_R_Cr,
+		false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	INTERLEAVED_YUV_FMT(YVYU,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C0_G_Y, C2_R_Cr, C0_G_Y, C1_B_Cb,
+		false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	PLANAR_YUV_FMT(YUV420,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C1_B_Cb, C0_G_Y,
+		false, DPU_CHROMA_420, 1, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 3),
+
+	PLANAR_YUV_FMT(YVU420,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr, C0_G_Y,
+		false, DPU_CHROMA_420, 1, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 3),
+};
+
+/*
+ * A5x tile formats tables:
+ * These tables hold the A5x tile formats supported.
+ */
+static const struct dpu_format dpu_format_map_tile[] = {
+	INTERLEAVED_RGB_FMT_TILED(BGR565,
+		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		false, 2, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(ARGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		true, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(ABGR8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		true, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(XBGR8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(RGBA8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(BGRA8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		true, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(BGRX8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		false, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(XRGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		false, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(RGBX8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(ABGR2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(XBGR2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	PSEUDO_YUV_FMT_TILED(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_NV12),
+
+	PSEUDO_YUV_FMT_TILED(NV21,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C1_B_Cb,
+		DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_NV12),
+};
+
+/*
+ * UBWC formats table:
+ * This table holds the UBWC formats supported.
+ * If a compression ratio needs to be used for this or any other format,
+ * the data will be passed by user-space.
+ */
+static const struct dpu_format dpu_format_map_ubwc[] = {
+	INTERLEAVED_RGB_FMT_TILED(BGR565,
+		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		false, 2, DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	INTERLEAVED_RGB_FMT_TILED(ABGR8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	INTERLEAVED_RGB_FMT_TILED(XBGR8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 4, DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	INTERLEAVED_RGB_FMT_TILED(ABGR2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_DX | DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	INTERLEAVED_RGB_FMT_TILED(XBGR2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_DX | DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	PSEUDO_YUV_FMT_TILED(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV |
+				DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 4, DPU_TILE_HEIGHT_NV12),
+};
+
+static const struct dpu_format dpu_format_map_p010[] = {
+	PSEUDO_YUV_FMT_LOOSE(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, (DPU_FORMAT_FLAG_YUV | DPU_FORMAT_FLAG_DX),
+		DPU_FETCH_LINEAR, 2),
+};
+
+static const struct dpu_format dpu_format_map_p010_ubwc[] = {
+	PSEUDO_YUV_FMT_LOOSE_TILED(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, (DPU_FORMAT_FLAG_YUV | DPU_FORMAT_FLAG_DX |
+				DPU_FORMAT_FLAG_COMPRESSED),
+		DPU_FETCH_UBWC, 4, DPU_TILE_HEIGHT_NV12),
+};
+
+static const struct dpu_format dpu_format_map_tp10_ubwc[] = {
+	PSEUDO_YUV_FMT_TILED(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, (DPU_FORMAT_FLAG_YUV | DPU_FORMAT_FLAG_DX |
+				DPU_FORMAT_FLAG_COMPRESSED),
+		DPU_FETCH_UBWC, 4, DPU_TILE_HEIGHT_NV12),
+};
+
+/* _dpu_get_v_h_subsample_rate - Get subsample rates for all formats we support
+ *   Note: Not using the drm_format_*_subsampling since we have formats
+ */
+static void _dpu_get_v_h_subsample_rate(
+	enum dpu_chroma_samp_type chroma_sample,
+	uint32_t *v_sample,
+	uint32_t *h_sample)
+{
+	if (!v_sample || !h_sample)
+		return;
+
+	switch (chroma_sample) {
+	case DPU_CHROMA_H2V1:
+		*v_sample = 1;
+		*h_sample = 2;
+		break;
+	case DPU_CHROMA_H1V2:
+		*v_sample = 2;
+		*h_sample = 1;
+		break;
+	case DPU_CHROMA_420:
+		*v_sample = 2;
+		*h_sample = 2;
+		break;
+	default:
+		*v_sample = 1;
+		*h_sample = 1;
+		break;
+	}
+}
+
+static int _dpu_format_get_media_color_ubwc(const struct dpu_format *fmt)
+{
+	static const struct dpu_media_color_map dpu_media_ubwc_map[] = {
+		{DRM_FORMAT_ABGR8888, COLOR_FMT_RGBA8888_UBWC},
+		{DRM_FORMAT_XBGR8888, COLOR_FMT_RGBA8888_UBWC},
+		{DRM_FORMAT_ABGR2101010, COLOR_FMT_RGBA1010102_UBWC},
+		{DRM_FORMAT_XBGR2101010, COLOR_FMT_RGBA1010102_UBWC},
+		{DRM_FORMAT_BGR565, COLOR_FMT_RGB565_UBWC},
+	};
+	int color_fmt = -1;
+	int i;
+
+	if (fmt->base.pixel_format == DRM_FORMAT_NV12) {
+		if (DPU_FORMAT_IS_DX(fmt)) {
+			if (fmt->unpack_tight)
+				color_fmt = COLOR_FMT_NV12_BPP10_UBWC;
+			else
+				color_fmt = COLOR_FMT_P010_UBWC;
+		} else
+			color_fmt = COLOR_FMT_NV12_UBWC;
+		return color_fmt;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(dpu_media_ubwc_map); ++i)
+		if (fmt->base.pixel_format == dpu_media_ubwc_map[i].format) {
+			color_fmt = dpu_media_ubwc_map[i].color;
+			break;
+		}
+	return color_fmt;
+}
+
+static int _dpu_format_get_plane_sizes_ubwc(
+		const struct dpu_format *fmt,
+		const uint32_t width,
+		const uint32_t height,
+		struct dpu_hw_fmt_layout *layout)
+{
+	int i;
+	int color;
+	bool meta = DPU_FORMAT_IS_UBWC(fmt);
+
+	memset(layout, 0, sizeof(struct dpu_hw_fmt_layout));
+	layout->format = fmt;
+	layout->width = width;
+	layout->height = height;
+	layout->num_planes = fmt->num_planes;
+
+	color = _dpu_format_get_media_color_ubwc(fmt);
+	if (color < 0) {
+		DRM_ERROR("UBWC format not supported for fmt: %4.4s\n",
+			(char *)&fmt->base.pixel_format);
+		return -EINVAL;
+	}
+
+	if (DPU_FORMAT_IS_YUV(layout->format)) {
+		uint32_t y_sclines, uv_sclines;
+		uint32_t y_meta_scanlines = 0;
+		uint32_t uv_meta_scanlines = 0;
+
+		layout->num_planes = 2;
+		layout->plane_pitch[0] = VENUS_Y_STRIDE(color, width);
+		y_sclines = VENUS_Y_SCANLINES(color, height);
+		layout->plane_size[0] = MSM_MEDIA_ALIGN(layout->plane_pitch[0] *
+			y_sclines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+		layout->plane_pitch[1] = VENUS_UV_STRIDE(color, width);
+		uv_sclines = VENUS_UV_SCANLINES(color, height);
+		layout->plane_size[1] = MSM_MEDIA_ALIGN(layout->plane_pitch[1] *
+			uv_sclines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+		if (!meta)
+			goto done;
+
+		layout->num_planes += 2;
+		layout->plane_pitch[2] = VENUS_Y_META_STRIDE(color, width);
+		y_meta_scanlines = VENUS_Y_META_SCANLINES(color, height);
+		layout->plane_size[2] = MSM_MEDIA_ALIGN(layout->plane_pitch[2] *
+			y_meta_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+		layout->plane_pitch[3] = VENUS_UV_META_STRIDE(color, width);
+		uv_meta_scanlines = VENUS_UV_META_SCANLINES(color, height);
+		layout->plane_size[3] = MSM_MEDIA_ALIGN(layout->plane_pitch[3] *
+			uv_meta_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+	} else {
+		uint32_t rgb_scanlines, rgb_meta_scanlines;
+
+		layout->num_planes = 1;
+
+		layout->plane_pitch[0] = VENUS_RGB_STRIDE(color, width);
+		rgb_scanlines = VENUS_RGB_SCANLINES(color, height);
+		layout->plane_size[0] = MSM_MEDIA_ALIGN(layout->plane_pitch[0] *
+			rgb_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+		if (!meta)
+			goto done;
+		layout->num_planes += 2;
+		layout->plane_pitch[2] = VENUS_RGB_META_STRIDE(color, width);
+		rgb_meta_scanlines = VENUS_RGB_META_SCANLINES(color, height);
+		layout->plane_size[2] = MSM_MEDIA_ALIGN(layout->plane_pitch[2] *
+			rgb_meta_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+	}
+
+done:
+	for (i = 0; i < DPU_MAX_PLANES; i++)
+		layout->total_size += layout->plane_size[i];
+
+	return 0;
+}
+
+static int _dpu_format_get_plane_sizes_linear(
+		const struct dpu_format *fmt,
+		const uint32_t width,
+		const uint32_t height,
+		struct dpu_hw_fmt_layout *layout,
+		const uint32_t *pitches)
+{
+	int i;
+
+	memset(layout, 0, sizeof(struct dpu_hw_fmt_layout));
+	layout->format = fmt;
+	layout->width = width;
+	layout->height = height;
+	layout->num_planes = fmt->num_planes;
+
+	/* Due to memset above, only need to set planes of interest */
+	if (fmt->fetch_planes == DPU_PLANE_INTERLEAVED) {
+		layout->num_planes = 1;
+		layout->plane_size[0] = width * height * layout->format->bpp;
+		layout->plane_pitch[0] = width * layout->format->bpp;
+	} else {
+		uint32_t v_subsample, h_subsample;
+		uint32_t chroma_samp;
+		uint32_t bpp = 1;
+
+		chroma_samp = fmt->chroma_sample;
+		_dpu_get_v_h_subsample_rate(chroma_samp, &v_subsample,
+				&h_subsample);
+
+		if (width % h_subsample || height % v_subsample) {
+			DRM_ERROR("mismatch in subsample vs dimensions\n");
+			return -EINVAL;
+		}
+
+		if ((fmt->base.pixel_format == DRM_FORMAT_NV12) &&
+			(DPU_FORMAT_IS_DX(fmt)))
+			bpp = 2;
+		layout->plane_pitch[0] = width * bpp;
+		layout->plane_pitch[1] = layout->plane_pitch[0] / h_subsample;
+		layout->plane_size[0] = layout->plane_pitch[0] * height;
+		layout->plane_size[1] = layout->plane_pitch[1] *
+				(height / v_subsample);
+
+		if (fmt->fetch_planes == DPU_PLANE_PSEUDO_PLANAR) {
+			layout->num_planes = 2;
+			layout->plane_size[1] *= 2;
+			layout->plane_pitch[1] *= 2;
+		} else {
+			/* planar */
+			layout->num_planes = 3;
+			layout->plane_size[2] = layout->plane_size[1];
+			layout->plane_pitch[2] = layout->plane_pitch[1];
+		}
+	}
+
+	/*
+	 * linear format: allow user allocated pitches if they are greater than
+	 * the requirement.
+	 * ubwc format: pitch values are computed uniformly across
+	 * all the components based on ubwc specifications.
+	 */
+	for (i = 0; i < layout->num_planes && i < DPU_MAX_PLANES; ++i) {
+		if (pitches && layout->plane_pitch[i] < pitches[i])
+			layout->plane_pitch[i] = pitches[i];
+	}
+
+	for (i = 0; i < DPU_MAX_PLANES; i++)
+		layout->total_size += layout->plane_size[i];
+
+	return 0;
+}
+
+static int dpu_format_get_plane_sizes(
+		const struct dpu_format *fmt,
+		const uint32_t w,
+		const uint32_t h,
+		struct dpu_hw_fmt_layout *layout,
+		const uint32_t *pitches)
+{
+	if (!layout || !fmt) {
+		DRM_ERROR("invalid pointer\n");
+		return -EINVAL;
+	}
+
+	if ((w > DPU_MAX_IMG_WIDTH) || (h > DPU_MAX_IMG_HEIGHT)) {
+		DRM_ERROR("image dimensions outside max range\n");
+		return -ERANGE;
+	}
+
+	if (DPU_FORMAT_IS_UBWC(fmt) || DPU_FORMAT_IS_TILE(fmt))
+		return _dpu_format_get_plane_sizes_ubwc(fmt, w, h, layout);
+
+	return _dpu_format_get_plane_sizes_linear(fmt, w, h, layout, pitches);
+}
+
+static int _dpu_format_populate_addrs_ubwc(
+		struct msm_gem_address_space *aspace,
+		struct drm_framebuffer *fb,
+		struct dpu_hw_fmt_layout *layout)
+{
+	uint32_t base_addr = 0;
+	bool meta;
+
+	if (!fb || !layout) {
+		DRM_ERROR("invalid pointers\n");
+		return -EINVAL;
+	}
+
+	if (aspace)
+		base_addr = msm_framebuffer_iova(fb, aspace, 0);
+	if (!base_addr) {
+		DRM_ERROR("failed to retrieve base addr\n");
+		return -EFAULT;
+	}
+
+	meta = DPU_FORMAT_IS_UBWC(layout->format);
+
+	/* Per-format logic for verifying active planes */
+	if (DPU_FORMAT_IS_YUV(layout->format)) {
+		/************************************************/
+		/*      UBWC            **                      */
+		/*      buffer          **      DPU PLANE       */
+		/*      format          **                      */
+		/************************************************/
+		/* -------------------  ** -------------------- */
+		/* |      Y meta     |  ** |    Y bitstream   | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/* |    Y bitstream  |  ** |  CbCr bitstream  | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/* |   Cbcr metadata |  ** |       Y meta     | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/* |  CbCr bitstream |  ** |     CbCr meta    | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/************************************************/
+
+		/* configure Y bitstream plane */
+		layout->plane_addr[0] = base_addr + layout->plane_size[2];
+
+		/* configure CbCr bitstream plane */
+		layout->plane_addr[1] = base_addr + layout->plane_size[0]
+			+ layout->plane_size[2] + layout->plane_size[3];
+
+		if (!meta)
+			goto done;
+
+		/* configure Y metadata plane */
+		layout->plane_addr[2] = base_addr;
+
+		/* configure CbCr metadata plane */
+		layout->plane_addr[3] = base_addr + layout->plane_size[0]
+			+ layout->plane_size[2];
+
+	} else {
+		/************************************************/
+		/*      UBWC            **                      */
+		/*      buffer          **      DPU PLANE       */
+		/*      format          **                      */
+		/************************************************/
+		/* -------------------  ** -------------------- */
+		/* |      RGB meta   |  ** |   RGB bitstream  | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/* |  RGB bitstream  |  ** |       NONE       | */
+		/* |       data      |  ** |                  | */
+		/* -------------------  ** -------------------- */
+		/*                      ** |     RGB meta     | */
+		/*                      ** |       plane      | */
+		/*                      ** -------------------- */
+		/************************************************/
+
+		layout->plane_addr[0] = base_addr + layout->plane_size[2];
+		layout->plane_addr[1] = 0;
+
+		if (!meta)
+			goto done;
+
+		layout->plane_addr[2] = base_addr;
+		layout->plane_addr[3] = 0;
+	}
+done:
+	return 0;
+}
+
+static int _dpu_format_populate_addrs_linear(
+		struct msm_gem_address_space *aspace,
+		struct drm_framebuffer *fb,
+		struct dpu_hw_fmt_layout *layout)
+{
+	unsigned int i;
+
+	/* Can now check the pitches given vs pitches expected */
+	for (i = 0; i < layout->num_planes; ++i) {
+		if (layout->plane_pitch[i] > fb->pitches[i]) {
+			DRM_ERROR("plane %u expected pitch %u, fb %u\n",
+				i, layout->plane_pitch[i], fb->pitches[i]);
+			return -EINVAL;
+		}
+	}
+
+	/* Populate addresses for simple formats here */
+	for (i = 0; i < layout->num_planes; ++i) {
+		if (aspace)
+			layout->plane_addr[i] =
+				msm_framebuffer_iova(fb, aspace, i);
+		if (!layout->plane_addr[i]) {
+			DRM_ERROR("failed to retrieve base addr\n");
+			return -EFAULT;
+		}
+	}
+
+	return 0;
+}
+
+int dpu_format_populate_layout(
+		struct msm_gem_address_space *aspace,
+		struct drm_framebuffer *fb,
+		struct dpu_hw_fmt_layout *layout)
+{
+	uint32_t plane_addr[DPU_MAX_PLANES];
+	int i, ret;
+
+	if (!fb || !layout) {
+		DRM_ERROR("invalid arguments\n");
+		return -EINVAL;
+	}
+
+	if ((fb->width > DPU_MAX_IMG_WIDTH) ||
+			(fb->height > DPU_MAX_IMG_HEIGHT)) {
+		DRM_ERROR("image dimensions outside max range\n");
+		return -ERANGE;
+	}
+
+	layout->format = to_dpu_format(msm_framebuffer_format(fb));
+
+	/* Populate the plane sizes etc via get_format */
+	ret = dpu_format_get_plane_sizes(layout->format, fb->width, fb->height,
+			layout, fb->pitches);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < DPU_MAX_PLANES; ++i)
+		plane_addr[i] = layout->plane_addr[i];
+
+	/* Populate the addresses given the fb */
+	if (DPU_FORMAT_IS_UBWC(layout->format) ||
+			DPU_FORMAT_IS_TILE(layout->format))
+		ret = _dpu_format_populate_addrs_ubwc(aspace, fb, layout);
+	else
+		ret = _dpu_format_populate_addrs_linear(aspace, fb, layout);
+
+	/* check if anything changed */
+	if (!ret && !memcmp(plane_addr, layout->plane_addr, sizeof(plane_addr)))
+		ret = -EAGAIN;
+
+	return ret;
+}
+
+int dpu_format_check_modified_format(
+		const struct msm_kms *kms,
+		const struct msm_format *msm_fmt,
+		const struct drm_mode_fb_cmd2 *cmd,
+		struct drm_gem_object **bos)
+{
+	int ret, i, num_base_fmt_planes;
+	const struct dpu_format *fmt;
+	struct dpu_hw_fmt_layout layout;
+	uint32_t bos_total_size = 0;
+
+	if (!msm_fmt || !cmd || !bos) {
+		DRM_ERROR("invalid arguments\n");
+		return -EINVAL;
+	}
+
+	fmt = to_dpu_format(msm_fmt);
+	num_base_fmt_planes = drm_format_num_planes(fmt->base.pixel_format);
+
+	ret = dpu_format_get_plane_sizes(fmt, cmd->width, cmd->height,
+			&layout, cmd->pitches);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < num_base_fmt_planes; i++) {
+		if (!bos[i]) {
+			DRM_ERROR("invalid handle for plane %d\n", i);
+			return -EINVAL;
+		}
+		if ((i == 0) || (bos[i] != bos[0]))
+			bos_total_size += bos[i]->size;
+	}
+
+	if (bos_total_size < layout.total_size) {
+		DRM_ERROR("buffers total size too small %u expected %u\n",
+				bos_total_size, layout.total_size);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+const struct dpu_format *dpu_get_dpu_format_ext(
+		const uint32_t format,
+		const uint64_t modifier)
+{
+	uint32_t i = 0;
+	const struct dpu_format *fmt = NULL;
+	const struct dpu_format *map = NULL;
+	ssize_t map_size = 0;
+
+	/*
+	 * Currently only support exactly zero or one modifier.
+	 * All planes use the same modifier.
+	 */
+	DPU_DEBUG("plane format modifier 0x%llX\n", modifier);
+
+	switch (modifier) {
+	case 0:
+		map = dpu_format_map;
+		map_size = ARRAY_SIZE(dpu_format_map);
+		break;
+	case DRM_FORMAT_MOD_QCOM_COMPRESSED:
+		map = dpu_format_map_ubwc;
+		map_size = ARRAY_SIZE(dpu_format_map_ubwc);
+		DPU_DEBUG("found fmt: %4.4s  DRM_FORMAT_MOD_QCOM_COMPRESSED\n",
+				(char *)&format);
+		break;
+	default:
+		DPU_ERROR("unsupported format modifier %llX\n", modifier);
+		return NULL;
+	}
+
+	for (i = 0; i < map_size; i++) {
+		if (format == map[i].base.pixel_format) {
+			fmt = &map[i];
+			break;
+		}
+	}
+
+	if (fmt == NULL)
+		DPU_ERROR("unsupported fmt: %4.4s modifier 0x%llX\n",
+			(char *)&format, modifier);
+	else
+		DPU_DEBUG("fmt %4.4s mod 0x%llX ubwc %d yuv %d\n",
+				(char *)&format, modifier,
+				DPU_FORMAT_IS_UBWC(fmt),
+				DPU_FORMAT_IS_YUV(fmt));
+
+	return fmt;
+}
+
+const struct msm_format *dpu_get_msm_format(
+		struct msm_kms *kms,
+		const uint32_t format,
+		const uint64_t modifiers)
+{
+	const struct dpu_format *fmt = dpu_get_dpu_format_ext(format,
+			modifiers);
+	if (fmt)
+		return &fmt->base;
+	return NULL;
+}
+
+uint32_t dpu_populate_formats(
+		const struct dpu_format_extended *format_list,
+		uint32_t *pixel_formats,
+		uint64_t *pixel_modifiers,
+		uint32_t pixel_formats_max)
+{
+	uint32_t i, fourcc_format;
+
+	if (!format_list || !pixel_formats)
+		return 0;
+
+	for (i = 0, fourcc_format = 0;
+			format_list->fourcc_format && i < pixel_formats_max;
+			++format_list) {
+		/* verify if listed format is in dpu_format_map? */
+
+		/* optionally return modified formats */
+		if (pixel_modifiers) {
+			/* assume same modifier for all fb planes */
+			pixel_formats[i] = format_list->fourcc_format;
+			pixel_modifiers[i++] = format_list->modifier;
+		} else {
+			/* assume base formats grouped together */
+			if (fourcc_format != format_list->fourcc_format) {
+				fourcc_format = format_list->fourcc_format;
+				pixel_formats[i++] = fourcc_format;
+			}
+		}
+	}
+
+	return i;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h
new file mode 100644
index 000000000000..a54451d8d011
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h
@@ -0,0 +1,88 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_FORMATS_H
+#define _DPU_FORMATS_H
+
+#include <drm/drm_fourcc.h>
+#include "msm_gem.h"
+#include "dpu_hw_mdss.h"
+
+/**
+ * dpu_get_dpu_format_ext() - Returns dpu format structure pointer.
+ * @format:          DRM FourCC Code
+ * @modifiers:       format modifier array from client, one per plane
+ */
+const struct dpu_format *dpu_get_dpu_format_ext(
+		const uint32_t format,
+		const uint64_t modifier);
+
+#define dpu_get_dpu_format(f) dpu_get_dpu_format_ext(f, 0)
+
+/**
+ * dpu_get_msm_format - get an dpu_format by its msm_format base
+ *                     callback function registers with the msm_kms layer
+ * @kms:             kms driver
+ * @format:          DRM FourCC Code
+ * @modifiers:       data layout modifier
+ */
+const struct msm_format *dpu_get_msm_format(
+		struct msm_kms *kms,
+		const uint32_t format,
+		const uint64_t modifiers);
+
+/**
+ * dpu_populate_formats - populate the given array with fourcc codes supported
+ * @format_list:       pointer to list of possible formats
+ * @pixel_formats:     array to populate with fourcc codes
+ * @pixel_modifiers:   array to populate with drm modifiers, can be NULL
+ * @pixel_formats_max: length of pixel formats array
+ * Return: number of elements populated
+ */
+uint32_t dpu_populate_formats(
+		const struct dpu_format_extended *format_list,
+		uint32_t *pixel_formats,
+		uint64_t *pixel_modifiers,
+		uint32_t pixel_formats_max);
+
+/**
+ * dpu_format_check_modified_format - validate format and buffers for
+ *                   dpu non-standard, i.e. modified format
+ * @kms:             kms driver
+ * @msm_fmt:         pointer to the msm_fmt base pointer of an dpu_format
+ * @cmd:             fb_cmd2 structure user request
+ * @bos:             gem buffer object list
+ *
+ * Return: error code on failure, 0 on success
+ */
+int dpu_format_check_modified_format(
+		const struct msm_kms *kms,
+		const struct msm_format *msm_fmt,
+		const struct drm_mode_fb_cmd2 *cmd,
+		struct drm_gem_object **bos);
+
+/**
+ * dpu_format_populate_layout - populate the given format layout based on
+ *                     mmu, fb, and format found in the fb
+ * @aspace:            address space pointer
+ * @fb:                framebuffer pointer
+ * @fmtl:              format layout structure to populate
+ *
+ * Return: error code on failure, -EAGAIN if success but the addresses
+ *         are the same as before or 0 if new addresses were populated
+ */
+int dpu_format_populate_layout(
+		struct msm_gem_address_space *aspace,
+		struct drm_framebuffer *fb,
+		struct dpu_hw_fmt_layout *fmtl);
+
+#endif /*_DPU_FORMATS_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.c
new file mode 100644
index 000000000000..58d29e43faef
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.c
@@ -0,0 +1,155 @@
+/* Copyright (c) 2017-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/mutex.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_blk.h"
+
+/* Serialization lock for dpu_hw_blk_list */
+static DEFINE_MUTEX(dpu_hw_blk_lock);
+
+/* List of all hw block objects */
+static LIST_HEAD(dpu_hw_blk_list);
+
+/**
+ * dpu_hw_blk_init - initialize hw block object
+ * @type: hw block type - enum dpu_hw_blk_type
+ * @id: instance id of the hw block
+ * @ops: Pointer to block operations
+ * return: 0 if success; error code otherwise
+ */
+int dpu_hw_blk_init(struct dpu_hw_blk *hw_blk, u32 type, int id,
+		struct dpu_hw_blk_ops *ops)
+{
+	if (!hw_blk) {
+		pr_err("invalid parameters\n");
+		return -EINVAL;
+	}
+
+	INIT_LIST_HEAD(&hw_blk->list);
+	hw_blk->type = type;
+	hw_blk->id = id;
+	atomic_set(&hw_blk->refcount, 0);
+
+	if (ops)
+		hw_blk->ops = *ops;
+
+	mutex_lock(&dpu_hw_blk_lock);
+	list_add(&hw_blk->list, &dpu_hw_blk_list);
+	mutex_unlock(&dpu_hw_blk_lock);
+
+	return 0;
+}
+
+/**
+ * dpu_hw_blk_destroy - destroy hw block object.
+ * @hw_blk:  pointer to hw block object
+ * return: none
+ */
+void dpu_hw_blk_destroy(struct dpu_hw_blk *hw_blk)
+{
+	if (!hw_blk) {
+		pr_err("invalid parameters\n");
+		return;
+	}
+
+	if (atomic_read(&hw_blk->refcount))
+		pr_err("hw_blk:%d.%d invalid refcount\n", hw_blk->type,
+				hw_blk->id);
+
+	mutex_lock(&dpu_hw_blk_lock);
+	list_del(&hw_blk->list);
+	mutex_unlock(&dpu_hw_blk_lock);
+}
+
+/**
+ * dpu_hw_blk_get - get hw_blk from free pool
+ * @hw_blk: if specified, increment reference count only
+ * @type: if hw_blk is not specified, allocate the next available of this type
+ * @id: if specified (>= 0), allocate the given instance of the above type
+ * return: pointer to hw block object
+ */
+struct dpu_hw_blk *dpu_hw_blk_get(struct dpu_hw_blk *hw_blk, u32 type, int id)
+{
+	struct dpu_hw_blk *curr;
+	int rc, refcount;
+
+	if (!hw_blk) {
+		mutex_lock(&dpu_hw_blk_lock);
+		list_for_each_entry(curr, &dpu_hw_blk_list, list) {
+			if ((curr->type != type) ||
+					(id >= 0 && curr->id != id) ||
+					(id < 0 &&
+						atomic_read(&curr->refcount)))
+				continue;
+
+			hw_blk = curr;
+			break;
+		}
+		mutex_unlock(&dpu_hw_blk_lock);
+	}
+
+	if (!hw_blk) {
+		pr_debug("no hw_blk:%d\n", type);
+		return NULL;
+	}
+
+	refcount = atomic_inc_return(&hw_blk->refcount);
+
+	if (refcount == 1 && hw_blk->ops.start) {
+		rc = hw_blk->ops.start(hw_blk);
+		if (rc) {
+			pr_err("failed to start  hw_blk:%d rc:%d\n", type, rc);
+			goto error_start;
+		}
+	}
+
+	pr_debug("hw_blk:%d.%d refcount:%d\n", hw_blk->type,
+			hw_blk->id, refcount);
+	return hw_blk;
+
+error_start:
+	dpu_hw_blk_put(hw_blk);
+	return ERR_PTR(rc);
+}
+
+/**
+ * dpu_hw_blk_put - put hw_blk to free pool if decremented refcount is zero
+ * @hw_blk: hw block to be freed
+ * @free_blk: function to be called when reference count goes to zero
+ */
+void dpu_hw_blk_put(struct dpu_hw_blk *hw_blk)
+{
+	if (!hw_blk) {
+		pr_err("invalid parameters\n");
+		return;
+	}
+
+	pr_debug("hw_blk:%d.%d refcount:%d\n", hw_blk->type, hw_blk->id,
+			atomic_read(&hw_blk->refcount));
+
+	if (!atomic_read(&hw_blk->refcount)) {
+		pr_err("hw_blk:%d.%d invalid put\n", hw_blk->type, hw_blk->id);
+		return;
+	}
+
+	if (atomic_dec_return(&hw_blk->refcount))
+		return;
+
+	if (hw_blk->ops.stop)
+		hw_blk->ops.stop(hw_blk);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.h
new file mode 100644
index 000000000000..0f4ca8af1ec5
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.h
@@ -0,0 +1,53 @@
+/* Copyright (c) 2017-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_BLK_H
+#define _DPU_HW_BLK_H
+
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/atomic.h>
+
+struct dpu_hw_blk;
+
+/**
+ * struct dpu_hw_blk_ops - common hardware block operations
+ * @start: start operation on first get
+ * @stop: stop operation on last put
+ */
+struct dpu_hw_blk_ops {
+	int (*start)(struct dpu_hw_blk *);
+	void (*stop)(struct dpu_hw_blk *);
+};
+
+/**
+ * struct dpu_hw_blk - definition of hardware block object
+ * @list: list of hardware blocks
+ * @type: hardware block type
+ * @id: instance id
+ * @refcount: reference/usage count
+ */
+struct dpu_hw_blk {
+	struct list_head list;
+	u32 type;
+	int id;
+	atomic_t refcount;
+	struct dpu_hw_blk_ops ops;
+};
+
+int dpu_hw_blk_init(struct dpu_hw_blk *hw_blk, u32 type, int id,
+		struct dpu_hw_blk_ops *ops);
+void dpu_hw_blk_destroy(struct dpu_hw_blk *hw_blk);
+
+struct dpu_hw_blk *dpu_hw_blk_get(struct dpu_hw_blk *hw_blk, u32 type, int id);
+void dpu_hw_blk_put(struct dpu_hw_blk *hw_blk);
+#endif /*_DPU_HW_BLK_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
new file mode 100644
index 000000000000..44ee06398b1d
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
@@ -0,0 +1,511 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include <linux/slab.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_catalog_format.h"
+#include "dpu_kms.h"
+
+#define VIG_SDM845_MASK \
+	(BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_SCALER_QSEED3) | BIT(DPU_SSPP_QOS) |\
+	BIT(DPU_SSPP_CSC_10BIT) | BIT(DPU_SSPP_CDP) | BIT(DPU_SSPP_QOS_8LVL) |\
+	BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_EXCL_RECT))
+
+#define DMA_SDM845_MASK \
+	(BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_QOS) | BIT(DPU_SSPP_QOS_8LVL) |\
+	BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_TS_PREFILL_REC1) |\
+	BIT(DPU_SSPP_CDP) | BIT(DPU_SSPP_EXCL_RECT))
+
+#define MIXER_SDM845_MASK \
+	(BIT(DPU_MIXER_SOURCESPLIT) | BIT(DPU_DIM_LAYER))
+
+#define PINGPONG_SDM845_MASK BIT(DPU_PINGPONG_DITHER)
+
+#define PINGPONG_SDM845_SPLIT_MASK \
+	(PINGPONG_SDM845_MASK | BIT(DPU_PINGPONG_TE2))
+
+#define DEFAULT_PIXEL_RAM_SIZE		(50 * 1024)
+#define DEFAULT_DPU_LINE_WIDTH		2048
+#define DEFAULT_DPU_OUTPUT_LINE_WIDTH	2560
+
+#define MAX_HORZ_DECIMATION	4
+#define MAX_VERT_DECIMATION	4
+
+#define MAX_UPSCALE_RATIO	20
+#define MAX_DOWNSCALE_RATIO	4
+#define SSPP_UNITY_SCALE	1
+
+#define STRCAT(X, Y) (X Y)
+
+/*************************************************************
+ * DPU sub blocks config
+ *************************************************************/
+/* DPU top level caps */
+static const struct dpu_caps sdm845_dpu_caps = {
+	.max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.max_mixer_blendstages = 0xb,
+	.qseed_type = DPU_SSPP_SCALER_QSEED3,
+	.smart_dma_rev = DPU_SSPP_SMART_DMA_V2,
+	.ubwc_version = DPU_HW_UBWC_VER_20,
+	.has_src_split = true,
+	.has_dim_layer = true,
+	.has_idle_pc = true,
+};
+
+static struct dpu_mdp_cfg sdm845_mdp[] = {
+	{
+	.name = "top_0", .id = MDP_TOP,
+	.base = 0x0, .len = 0x45C,
+	.features = 0,
+	.highest_bank_bit = 0x2,
+	.has_dest_scaler = true,
+	.clk_ctrls[DPU_CLK_CTRL_VIG0] = {
+			.reg_off = 0x2AC, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG1] = {
+			.reg_off = 0x2B4, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG2] = {
+			.reg_off = 0x2BC, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG3] = {
+			.reg_off = 0x2C4, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_DMA0] = {
+			.reg_off = 0x2AC, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_DMA1] = {
+			.reg_off = 0x2B4, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_CURSOR0] = {
+			.reg_off = 0x2BC, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_CURSOR1] = {
+			.reg_off = 0x2C4, .bit_off = 8},
+	},
+};
+
+/*************************************************************
+ * CTL sub blocks config
+ *************************************************************/
+static struct dpu_ctl_cfg sdm845_ctl[] = {
+	{
+	.name = "ctl_0", .id = CTL_0,
+	.base = 0x1000, .len = 0xE4,
+	.features = BIT(DPU_CTL_SPLIT_DISPLAY)
+	},
+	{
+	.name = "ctl_1", .id = CTL_1,
+	.base = 0x1200, .len = 0xE4,
+	.features = BIT(DPU_CTL_SPLIT_DISPLAY)
+	},
+	{
+	.name = "ctl_2", .id = CTL_2,
+	.base = 0x1400, .len = 0xE4,
+	.features = 0
+	},
+	{
+	.name = "ctl_3", .id = CTL_3,
+	.base = 0x1600, .len = 0xE4,
+	.features = 0
+	},
+	{
+	.name = "ctl_4", .id = CTL_4,
+	.base = 0x1800, .len = 0xE4,
+	.features = 0
+	},
+};
+
+/*************************************************************
+ * SSPP sub blocks config
+ *************************************************************/
+
+/* SSPP common configuration */
+static const struct dpu_sspp_blks_common sdm845_sspp_common = {
+	.maxlinewidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE,
+	.maxhdeciexp = MAX_HORZ_DECIMATION,
+	.maxvdeciexp = MAX_VERT_DECIMATION,
+};
+
+#define _VIG_SBLK(num, sdma_pri) \
+	{ \
+	.common = &sdm845_sspp_common, \
+	.maxdwnscale = MAX_DOWNSCALE_RATIO, \
+	.maxupscale = MAX_UPSCALE_RATIO, \
+	.smart_dma_priority = sdma_pri, \
+	.src_blk = {.name = STRCAT("sspp_src_", num), \
+		.id = DPU_SSPP_SRC, .base = 0x00, .len = 0x150,}, \
+	.scaler_blk = {.name = STRCAT("sspp_scaler", num), \
+		.id = DPU_SSPP_SCALER_QSEED3, \
+		.base = 0xa00, .len = 0xa0,}, \
+	.csc_blk = {.name = STRCAT("sspp_csc", num), \
+		.id = DPU_SSPP_CSC_10BIT, \
+		.base = 0x1a00, .len = 0x100,}, \
+	.format_list = plane_formats_yuv, \
+	.virt_format_list = plane_formats, \
+	}
+
+#define _DMA_SBLK(num, sdma_pri) \
+	{ \
+	.common = &sdm845_sspp_common, \
+	.maxdwnscale = SSPP_UNITY_SCALE, \
+	.maxupscale = SSPP_UNITY_SCALE, \
+	.smart_dma_priority = sdma_pri, \
+	.src_blk = {.name = STRCAT("sspp_src_", num), \
+		.id = DPU_SSPP_SRC, .base = 0x00, .len = 0x150,}, \
+	.format_list = plane_formats, \
+	.virt_format_list = plane_formats, \
+	}
+
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_0 = _VIG_SBLK("0", 5);
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_1 = _VIG_SBLK("1", 6);
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_2 = _VIG_SBLK("2", 7);
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_3 = _VIG_SBLK("3", 8);
+
+static const struct dpu_sspp_sub_blks sdm845_dma_sblk_0 = _DMA_SBLK("8", 1);
+static const struct dpu_sspp_sub_blks sdm845_dma_sblk_1 = _DMA_SBLK("9", 2);
+static const struct dpu_sspp_sub_blks sdm845_dma_sblk_2 = _DMA_SBLK("10", 3);
+static const struct dpu_sspp_sub_blks sdm845_dma_sblk_3 = _DMA_SBLK("11", 4);
+
+#define SSPP_VIG_BLK(_name, _id, _base, _sblk, _xinid, _clkctrl) \
+	{ \
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x1c8, \
+	.features = VIG_SDM845_MASK, \
+	.sblk = &_sblk, \
+	.xin_id = _xinid, \
+	.type = SSPP_TYPE_VIG, \
+	.clk_ctrl = _clkctrl \
+	}
+
+#define SSPP_DMA_BLK(_name, _id, _base, _sblk, _xinid, _clkctrl) \
+	{ \
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x1c8, \
+	.features = DMA_SDM845_MASK, \
+	.sblk = &_sblk, \
+	.xin_id = _xinid, \
+	.type = SSPP_TYPE_DMA, \
+	.clk_ctrl = _clkctrl \
+	}
+
+static struct dpu_sspp_cfg sdm845_sspp[] = {
+	SSPP_VIG_BLK("sspp_0", SSPP_VIG0, 0x4000,
+		sdm845_vig_sblk_0, 0, DPU_CLK_CTRL_VIG0),
+	SSPP_VIG_BLK("sspp_1", SSPP_VIG1, 0x6000,
+		sdm845_vig_sblk_1, 4, DPU_CLK_CTRL_VIG1),
+	SSPP_VIG_BLK("sspp_2", SSPP_VIG2, 0x8000,
+		sdm845_vig_sblk_2, 8, DPU_CLK_CTRL_VIG2),
+	SSPP_VIG_BLK("sspp_3", SSPP_VIG3, 0xa000,
+		sdm845_vig_sblk_3, 12, DPU_CLK_CTRL_VIG3),
+	SSPP_DMA_BLK("sspp_8", SSPP_DMA0, 0x24000,
+		sdm845_dma_sblk_0, 1, DPU_CLK_CTRL_DMA0),
+	SSPP_DMA_BLK("sspp_9", SSPP_DMA1, 0x26000,
+		sdm845_dma_sblk_1, 5, DPU_CLK_CTRL_DMA1),
+	SSPP_DMA_BLK("sspp_10", SSPP_DMA2, 0x28000,
+		sdm845_dma_sblk_2, 9, DPU_CLK_CTRL_CURSOR0),
+	SSPP_DMA_BLK("sspp_11", SSPP_DMA3, 0x2a000,
+		sdm845_dma_sblk_3, 13, DPU_CLK_CTRL_CURSOR1),
+};
+
+/*************************************************************
+ * MIXER sub blocks config
+ *************************************************************/
+static const struct dpu_lm_sub_blks sdm845_lm_sblk = {
+	.maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.maxblendstages = 11, /* excluding base layer */
+	.blendstage_base = { /* offsets relative to mixer base */
+		0x20, 0x38, 0x50, 0x68, 0x80, 0x98,
+		0xb0, 0xc8, 0xe0, 0xf8, 0x110
+	},
+};
+
+#define LM_BLK(_name, _id, _base, _ds, _pp, _lmpair) \
+	{ \
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x320, \
+	.features = MIXER_SDM845_MASK, \
+	.sblk = &sdm845_lm_sblk, \
+	.ds = _ds, \
+	.pingpong = _pp, \
+	.lm_pair_mask = (1 << _lmpair) \
+	}
+
+static struct dpu_lm_cfg sdm845_lm[] = {
+	LM_BLK("lm_0", LM_0, 0x44000, DS_0, PINGPONG_0, LM_1),
+	LM_BLK("lm_1", LM_1, 0x45000, DS_1, PINGPONG_1, LM_0),
+	LM_BLK("lm_2", LM_2, 0x46000, DS_MAX, PINGPONG_2, LM_5),
+	LM_BLK("lm_3", LM_3, 0x0, DS_MAX, PINGPONG_MAX, 0),
+	LM_BLK("lm_4", LM_4, 0x0, DS_MAX, PINGPONG_MAX, 0),
+	LM_BLK("lm_5", LM_5, 0x49000, DS_MAX, PINGPONG_3, LM_2),
+};
+
+/*************************************************************
+ * DS sub blocks config
+ *************************************************************/
+static const struct dpu_ds_top_cfg sdm845_ds_top = {
+	.name = "ds_top_0", .id = DS_TOP,
+	.base = 0x60000, .len = 0xc,
+	.maxinputwidth = DEFAULT_DPU_LINE_WIDTH,
+	.maxoutputwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.maxupscale = MAX_UPSCALE_RATIO,
+};
+
+#define DS_BLK(_name, _id, _base) \
+	{\
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x800, \
+	.features = DPU_SSPP_SCALER_QSEED3, \
+	.top = &sdm845_ds_top \
+	}
+
+static struct dpu_ds_cfg sdm845_ds[] = {
+	DS_BLK("ds_0", DS_0, 0x800),
+	DS_BLK("ds_1", DS_1, 0x1000),
+};
+
+/*************************************************************
+ * PINGPONG sub blocks config
+ *************************************************************/
+static const struct dpu_pingpong_sub_blks sdm845_pp_sblk_te = {
+	.te2 = {.id = DPU_PINGPONG_TE2, .base = 0x2000, .len = 0x0,
+		.version = 0x1},
+	.dither = {.id = DPU_PINGPONG_DITHER, .base = 0x30e0,
+		.len = 0x20, .version = 0x10000},
+};
+
+static const struct dpu_pingpong_sub_blks sdm845_pp_sblk = {
+	.dither = {.id = DPU_PINGPONG_DITHER, .base = 0x30e0,
+		.len = 0x20, .version = 0x10000},
+};
+
+#define PP_BLK_TE(_name, _id, _base) \
+	{\
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0xd4, \
+	.features = PINGPONG_SDM845_SPLIT_MASK, \
+	.sblk = &sdm845_pp_sblk_te \
+	}
+#define PP_BLK(_name, _id, _base) \
+	{\
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0xd4, \
+	.features = PINGPONG_SDM845_MASK, \
+	.sblk = &sdm845_pp_sblk \
+	}
+
+static struct dpu_pingpong_cfg sdm845_pp[] = {
+	PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000),
+	PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800),
+	PP_BLK("pingpong_2", PINGPONG_2, 0x71000),
+	PP_BLK("pingpong_3", PINGPONG_3, 0x71800),
+};
+
+/*************************************************************
+ * INTF sub blocks config
+ *************************************************************/
+#define INTF_BLK(_name, _id, _base, _type, _ctrl_id) \
+	{\
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x280, \
+	.type = _type, \
+	.controller_id = _ctrl_id, \
+	.prog_fetch_lines_worst_case = 24 \
+	}
+
+static struct dpu_intf_cfg sdm845_intf[] = {
+	INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0),
+	INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0),
+	INTF_BLK("intf_2", INTF_2, 0x6B000, INTF_DSI, 1),
+	INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_DP, 1),
+};
+
+/*************************************************************
+ * CDM sub blocks config
+ *************************************************************/
+static struct dpu_cdm_cfg sdm845_cdm[] = {
+	{
+	.name = "cdm_0", .id = CDM_0,
+	.base = 0x79200, .len = 0x224,
+	.features = 0,
+	.intf_connect = BIT(INTF_3),
+	},
+};
+
+/*************************************************************
+ * VBIF sub blocks config
+ *************************************************************/
+/* VBIF QOS remap */
+static u32 sdm845_rt_pri_lvl[] = {3, 3, 4, 4, 5, 5, 6, 6};
+static u32 sdm845_nrt_pri_lvl[] = {3, 3, 3, 3, 3, 3, 3, 3};
+
+static struct dpu_vbif_cfg sdm845_vbif[] = {
+	{
+	.name = "vbif_0", .id = VBIF_0,
+	.base = 0, .len = 0x1040,
+	.features = BIT(DPU_VBIF_QOS_REMAP),
+	.xin_halt_timeout = 0x4000,
+	.qos_rt_tbl = {
+		.npriority_lvl = ARRAY_SIZE(sdm845_rt_pri_lvl),
+		.priority_lvl = sdm845_rt_pri_lvl,
+		},
+	.qos_nrt_tbl = {
+		.npriority_lvl = ARRAY_SIZE(sdm845_nrt_pri_lvl),
+		.priority_lvl = sdm845_nrt_pri_lvl,
+		},
+	.memtype_count = 14,
+	.memtype = {3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3},
+	},
+};
+
+static struct dpu_reg_dma_cfg sdm845_regdma = {
+	.base = 0x0, .version = 0x1, .trigger_sel_off = 0x119c
+};
+
+/*************************************************************
+ * PERF data config
+ *************************************************************/
+
+/* SSPP QOS LUTs */
+static struct dpu_qos_lut_entry sdm845_qos_linear[] = {
+	{.fl = 4, .lut = 0x357},
+	{.fl = 5, .lut = 0x3357},
+	{.fl = 6, .lut = 0x23357},
+	{.fl = 7, .lut = 0x223357},
+	{.fl = 8, .lut = 0x2223357},
+	{.fl = 9, .lut = 0x22223357},
+	{.fl = 10, .lut = 0x222223357},
+	{.fl = 11, .lut = 0x2222223357},
+	{.fl = 12, .lut = 0x22222223357},
+	{.fl = 13, .lut = 0x222222223357},
+	{.fl = 14, .lut = 0x1222222223357},
+	{.fl = 0, .lut = 0x11222222223357}
+};
+
+static struct dpu_qos_lut_entry sdm845_qos_macrotile[] = {
+	{.fl = 10, .lut = 0x344556677},
+	{.fl = 11, .lut = 0x3344556677},
+	{.fl = 12, .lut = 0x23344556677},
+	{.fl = 13, .lut = 0x223344556677},
+	{.fl = 14, .lut = 0x1223344556677},
+	{.fl = 0, .lut = 0x112233344556677},
+};
+
+static struct dpu_qos_lut_entry sdm845_qos_nrt[] = {
+	{.fl = 0, .lut = 0x0},
+};
+
+static struct dpu_perf_cfg sdm845_perf_data = {
+	.max_bw_low = 6800000,
+	.max_bw_high = 6800000,
+	.min_core_ib = 2400000,
+	.min_llcc_ib = 800000,
+	.min_dram_ib = 800000,
+	.core_ib_ff = "6.0",
+	.core_clk_ff = "1.0",
+	.comp_ratio_rt =
+	"NV12/5/1/1.23 AB24/5/1/1.23 XB24/5/1/1.23",
+	.comp_ratio_nrt =
+	"NV12/5/1/1.25 AB24/5/1/1.25 XB24/5/1/1.25",
+	.undersized_prefill_lines = 2,
+	.xtra_prefill_lines = 2,
+	.dest_scale_prefill_lines = 3,
+	.macrotile_prefill_lines = 4,
+	.yuv_nv12_prefill_lines = 8,
+	.linear_prefill_lines = 1,
+	.downscaling_prefill_lines = 1,
+	.amortizable_threshold = 25,
+	.min_prefill_lines = 24,
+	.danger_lut_tbl = {0xf, 0xffff, 0x0},
+	.qos_lut_tbl = {
+		{.nentry = ARRAY_SIZE(sdm845_qos_linear),
+		.entries = sdm845_qos_linear
+		},
+		{.nentry = ARRAY_SIZE(sdm845_qos_macrotile),
+		.entries = sdm845_qos_macrotile
+		},
+		{.nentry = ARRAY_SIZE(sdm845_qos_nrt),
+		.entries = sdm845_qos_nrt
+		},
+	},
+	.cdp_cfg = {
+		{.rd_enable = 1, .wr_enable = 1},
+		{.rd_enable = 1, .wr_enable = 0}
+	},
+};
+
+/*************************************************************
+ * Hardware catalog init
+ *************************************************************/
+
+/*
+ * sdm845_cfg_init(): populate sdm845 dpu sub-blocks reg offsets
+ * and instance counts.
+ */
+static void sdm845_cfg_init(struct dpu_mdss_cfg *dpu_cfg)
+{
+	*dpu_cfg = (struct dpu_mdss_cfg){
+		.caps = &sdm845_dpu_caps,
+		.mdp_count = ARRAY_SIZE(sdm845_mdp),
+		.mdp = sdm845_mdp,
+		.ctl_count = ARRAY_SIZE(sdm845_ctl),
+		.ctl = sdm845_ctl,
+		.sspp_count = ARRAY_SIZE(sdm845_sspp),
+		.sspp = sdm845_sspp,
+		.mixer_count = ARRAY_SIZE(sdm845_lm),
+		.mixer = sdm845_lm,
+		.ds_count = ARRAY_SIZE(sdm845_ds),
+		.ds = sdm845_ds,
+		.pingpong_count = ARRAY_SIZE(sdm845_pp),
+		.pingpong = sdm845_pp,
+		.cdm_count = ARRAY_SIZE(sdm845_cdm),
+		.cdm = sdm845_cdm,
+		.intf_count = ARRAY_SIZE(sdm845_intf),
+		.intf = sdm845_intf,
+		.vbif_count = ARRAY_SIZE(sdm845_vbif),
+		.vbif = sdm845_vbif,
+		.reg_dma_count = 1,
+		.dma_cfg = sdm845_regdma,
+		.perf = sdm845_perf_data,
+	};
+}
+
+static struct dpu_mdss_hw_cfg_handler cfg_handler[] = {
+	{ .hw_rev = DPU_HW_VER_400, .cfg_init = sdm845_cfg_init},
+	{ .hw_rev = DPU_HW_VER_401, .cfg_init = sdm845_cfg_init},
+};
+
+void dpu_hw_catalog_deinit(struct dpu_mdss_cfg *dpu_cfg)
+{
+	kfree(dpu_cfg);
+}
+
+struct dpu_mdss_cfg *dpu_hw_catalog_init(u32 hw_rev)
+{
+	int i;
+	struct dpu_mdss_cfg *dpu_cfg;
+
+	dpu_cfg = kzalloc(sizeof(*dpu_cfg), GFP_KERNEL);
+	if (!dpu_cfg)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < ARRAY_SIZE(cfg_handler); i++) {
+		if (cfg_handler[i].hw_rev == hw_rev) {
+			cfg_handler[i].cfg_init(dpu_cfg);
+			dpu_cfg->hwversion = hw_rev;
+			return dpu_cfg;
+		}
+	}
+
+	DPU_ERROR("unsupported chipset id:%X\n", hw_rev);
+	dpu_hw_catalog_deinit(dpu_cfg);
+	return ERR_PTR(-ENODEV);
+}
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
new file mode 100644
index 000000000000..f0cb0d4fc80e
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
@@ -0,0 +1,804 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_CATALOG_H
+#define _DPU_HW_CATALOG_H
+
+#include <linux/kernel.h>
+#include <linux/bug.h>
+#include <linux/bitmap.h>
+#include <linux/err.h>
+#include <drm/drmP.h>
+
+/**
+ * Max hardware block count: For ex: max 12 SSPP pipes or
+ * 5 ctl paths. In all cases, it can have max 12 hardware blocks
+ * based on current design
+ */
+#define MAX_BLOCKS    12
+
+#define DPU_HW_VER(MAJOR, MINOR, STEP) (((MAJOR & 0xF) << 28)    |\
+		((MINOR & 0xFFF) << 16)  |\
+		(STEP & 0xFFFF))
+
+#define DPU_HW_MAJOR(rev)		((rev) >> 28)
+#define DPU_HW_MINOR(rev)		(((rev) >> 16) & 0xFFF)
+#define DPU_HW_STEP(rev)		((rev) & 0xFFFF)
+#define DPU_HW_MAJOR_MINOR(rev)		((rev) >> 16)
+
+#define IS_DPU_MAJOR_MINOR_SAME(rev1, rev2)   \
+	(DPU_HW_MAJOR_MINOR((rev1)) == DPU_HW_MAJOR_MINOR((rev2)))
+
+#define DPU_HW_VER_170	DPU_HW_VER(1, 7, 0) /* 8996 v1.0 */
+#define DPU_HW_VER_171	DPU_HW_VER(1, 7, 1) /* 8996 v2.0 */
+#define DPU_HW_VER_172	DPU_HW_VER(1, 7, 2) /* 8996 v3.0 */
+#define DPU_HW_VER_300	DPU_HW_VER(3, 0, 0) /* 8998 v1.0 */
+#define DPU_HW_VER_301	DPU_HW_VER(3, 0, 1) /* 8998 v1.1 */
+#define DPU_HW_VER_400	DPU_HW_VER(4, 0, 0) /* sdm845 v1.0 */
+#define DPU_HW_VER_401	DPU_HW_VER(4, 0, 1) /* sdm845 v2.0 */
+#define DPU_HW_VER_410	DPU_HW_VER(4, 1, 0) /* sdm670 v1.0 */
+#define DPU_HW_VER_500	DPU_HW_VER(5, 0, 0) /* sdm855 v1.0 */
+
+
+#define IS_MSM8996_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_170)
+#define IS_MSM8998_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_300)
+#define IS_SDM845_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_400)
+#define IS_SDM670_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_410)
+#define IS_SDM855_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_500)
+
+
+#define DPU_HW_BLK_NAME_LEN	16
+
+#define MAX_IMG_WIDTH 0x3fff
+#define MAX_IMG_HEIGHT 0x3fff
+
+#define CRTC_DUAL_MIXERS	2
+
+#define MAX_XIN_COUNT 16
+
+/**
+ * Supported UBWC feature versions
+ */
+enum {
+	DPU_HW_UBWC_VER_10 = 0x100,
+	DPU_HW_UBWC_VER_20 = 0x200,
+	DPU_HW_UBWC_VER_30 = 0x300,
+};
+
+#define IS_UBWC_20_SUPPORTED(rev)       ((rev) >= DPU_HW_UBWC_VER_20)
+
+/**
+ * MDP TOP BLOCK features
+ * @DPU_MDP_PANIC_PER_PIPE Panic configuration needs to be be done per pipe
+ * @DPU_MDP_10BIT_SUPPORT, Chipset supports 10 bit pixel formats
+ * @DPU_MDP_BWC,           MDSS HW supports Bandwidth compression.
+ * @DPU_MDP_UBWC_1_0,      This chipsets supports Universal Bandwidth
+ *                         compression initial revision
+ * @DPU_MDP_UBWC_1_5,      Universal Bandwidth compression version 1.5
+ * @DPU_MDP_MAX            Maximum value
+
+ */
+enum {
+	DPU_MDP_PANIC_PER_PIPE = 0x1,
+	DPU_MDP_10BIT_SUPPORT,
+	DPU_MDP_BWC,
+	DPU_MDP_UBWC_1_0,
+	DPU_MDP_UBWC_1_5,
+	DPU_MDP_MAX
+};
+
+/**
+ * SSPP sub-blocks/features
+ * @DPU_SSPP_SRC             Src and fetch part of the pipes,
+ * @DPU_SSPP_SCALER_QSEED2,  QSEED2 algorithm support
+ * @DPU_SSPP_SCALER_QSEED3,  QSEED3 alogorithm support
+ * @DPU_SSPP_SCALER_RGB,     RGB Scaler, supported by RGB pipes
+ * @DPU_SSPP_CSC,            Support of Color space converion
+ * @DPU_SSPP_CSC_10BIT,      Support of 10-bit Color space conversion
+ * @DPU_SSPP_CURSOR,         SSPP can be used as a cursor layer
+ * @DPU_SSPP_QOS,            SSPP support QoS control, danger/safe/creq
+ * @DPU_SSPP_QOS_8LVL,       SSPP support 8-level QoS control
+ * @DPU_SSPP_EXCL_RECT,      SSPP supports exclusion rect
+ * @DPU_SSPP_SMART_DMA_V1,   SmartDMA 1.0 support
+ * @DPU_SSPP_SMART_DMA_V2,   SmartDMA 2.0 support
+ * @DPU_SSPP_TS_PREFILL      Supports prefill with traffic shaper
+ * @DPU_SSPP_TS_PREFILL_REC1 Supports prefill with traffic shaper multirec
+ * @DPU_SSPP_CDP             Supports client driven prefetch
+ * @DPU_SSPP_MAX             maximum value
+ */
+enum {
+	DPU_SSPP_SRC = 0x1,
+	DPU_SSPP_SCALER_QSEED2,
+	DPU_SSPP_SCALER_QSEED3,
+	DPU_SSPP_SCALER_RGB,
+	DPU_SSPP_CSC,
+	DPU_SSPP_CSC_10BIT,
+	DPU_SSPP_CURSOR,
+	DPU_SSPP_QOS,
+	DPU_SSPP_QOS_8LVL,
+	DPU_SSPP_EXCL_RECT,
+	DPU_SSPP_SMART_DMA_V1,
+	DPU_SSPP_SMART_DMA_V2,
+	DPU_SSPP_TS_PREFILL,
+	DPU_SSPP_TS_PREFILL_REC1,
+	DPU_SSPP_CDP,
+	DPU_SSPP_MAX
+};
+
+/*
+ * MIXER sub-blocks/features
+ * @DPU_MIXER_LAYER           Layer mixer layer blend configuration,
+ * @DPU_MIXER_SOURCESPLIT     Layer mixer supports source-split configuration
+ * @DPU_MIXER_GC              Gamma correction block
+ * @DPU_DIM_LAYER             Layer mixer supports dim layer
+ * @DPU_MIXER_MAX             maximum value
+ */
+enum {
+	DPU_MIXER_LAYER = 0x1,
+	DPU_MIXER_SOURCESPLIT,
+	DPU_MIXER_GC,
+	DPU_DIM_LAYER,
+	DPU_MIXER_MAX
+};
+
+/**
+ * PINGPONG sub-blocks
+ * @DPU_PINGPONG_TE         Tear check block
+ * @DPU_PINGPONG_TE2        Additional tear check block for split pipes
+ * @DPU_PINGPONG_SPLIT      PP block supports split fifo
+ * @DPU_PINGPONG_SLAVE      PP block is a suitable slave for split fifo
+ * @DPU_PINGPONG_DITHER,    Dither blocks
+ * @DPU_PINGPONG_MAX
+ */
+enum {
+	DPU_PINGPONG_TE = 0x1,
+	DPU_PINGPONG_TE2,
+	DPU_PINGPONG_SPLIT,
+	DPU_PINGPONG_SLAVE,
+	DPU_PINGPONG_DITHER,
+	DPU_PINGPONG_MAX
+};
+
+/**
+ * CTL sub-blocks
+ * @DPU_CTL_SPLIT_DISPLAY       CTL supports video mode split display
+ * @DPU_CTL_MAX
+ */
+enum {
+	DPU_CTL_SPLIT_DISPLAY = 0x1,
+	DPU_CTL_MAX
+};
+
+/**
+ * VBIF sub-blocks and features
+ * @DPU_VBIF_QOS_OTLIM        VBIF supports OT Limit
+ * @DPU_VBIF_QOS_REMAP        VBIF supports QoS priority remap
+ * @DPU_VBIF_MAX              maximum value
+ */
+enum {
+	DPU_VBIF_QOS_OTLIM = 0x1,
+	DPU_VBIF_QOS_REMAP,
+	DPU_VBIF_MAX
+};
+
+/**
+ * MACRO DPU_HW_BLK_INFO - information of HW blocks inside DPU
+ * @name:              string name for debug purposes
+ * @id:                enum identifying this block
+ * @base:              register base offset to mdss
+ * @len:               length of hardware block
+ * @features           bit mask identifying sub-blocks/features
+ */
+#define DPU_HW_BLK_INFO \
+	char name[DPU_HW_BLK_NAME_LEN]; \
+	u32 id; \
+	u32 base; \
+	u32 len; \
+	unsigned long features
+
+/**
+ * MACRO DPU_HW_SUBBLK_INFO - information of HW sub-block inside DPU
+ * @name:              string name for debug purposes
+ * @id:                enum identifying this sub-block
+ * @base:              offset of this sub-block relative to the block
+ *                     offset
+ * @len                register block length of this sub-block
+ */
+#define DPU_HW_SUBBLK_INFO \
+	char name[DPU_HW_BLK_NAME_LEN]; \
+	u32 id; \
+	u32 base; \
+	u32 len
+
+/**
+ * struct dpu_src_blk: SSPP part of the source pipes
+ * @info:   HW register and features supported by this sub-blk
+ */
+struct dpu_src_blk {
+	DPU_HW_SUBBLK_INFO;
+};
+
+/**
+ * struct dpu_scaler_blk: Scaler information
+ * @info:   HW register and features supported by this sub-blk
+ * @version: qseed block revision
+ */
+struct dpu_scaler_blk {
+	DPU_HW_SUBBLK_INFO;
+	u32 version;
+};
+
+struct dpu_csc_blk {
+	DPU_HW_SUBBLK_INFO;
+};
+
+/**
+ * struct dpu_pp_blk : Pixel processing sub-blk information
+ * @info:   HW register and features supported by this sub-blk
+ * @version: HW Algorithm version
+ */
+struct dpu_pp_blk {
+	DPU_HW_SUBBLK_INFO;
+	u32 version;
+};
+
+/**
+ * struct dpu_format_extended - define dpu specific pixel format+modifier
+ * @fourcc_format: Base FOURCC pixel format code
+ * @modifier: 64-bit drm format modifier, same modifier must be applied to all
+ *            framebuffer planes
+ */
+struct dpu_format_extended {
+	uint32_t fourcc_format;
+	uint64_t modifier;
+};
+
+/**
+ * enum dpu_qos_lut_usage - define QoS LUT use cases
+ */
+enum dpu_qos_lut_usage {
+	DPU_QOS_LUT_USAGE_LINEAR,
+	DPU_QOS_LUT_USAGE_MACROTILE,
+	DPU_QOS_LUT_USAGE_NRT,
+	DPU_QOS_LUT_USAGE_MAX,
+};
+
+/**
+ * struct dpu_qos_lut_entry - define QoS LUT table entry
+ * @fl: fill level, or zero on last entry to indicate default lut
+ * @lut: lut to use if equal to or less than fill level
+ */
+struct dpu_qos_lut_entry {
+	u32 fl;
+	u64 lut;
+};
+
+/**
+ * struct dpu_qos_lut_tbl - define QoS LUT table
+ * @nentry: number of entry in this table
+ * @entries: Pointer to table entries
+ */
+struct dpu_qos_lut_tbl {
+	u32 nentry;
+	struct dpu_qos_lut_entry *entries;
+};
+
+/**
+ * struct dpu_caps - define DPU capabilities
+ * @max_mixer_width    max layer mixer line width support.
+ * @max_mixer_blendstages max layer mixer blend stages or
+ *                       supported z order
+ * @qseed_type         qseed2 or qseed3 support.
+ * @smart_dma_rev      Supported version of SmartDMA feature.
+ * @ubwc_version       UBWC feature version (0x0 for not supported)
+ * @has_src_split      source split feature status
+ * @has_dim_layer      dim layer feature status
+ * @has_idle_pc        indicate if idle power collapse feature is supported
+ */
+struct dpu_caps {
+	u32 max_mixer_width;
+	u32 max_mixer_blendstages;
+	u32 qseed_type;
+	u32 smart_dma_rev;
+	u32 ubwc_version;
+	bool has_src_split;
+	bool has_dim_layer;
+	bool has_idle_pc;
+};
+
+/**
+ * struct dpu_sspp_blks_common : SSPP sub-blocks common configuration
+ * @maxwidth: max pixelwidth supported by this pipe
+ * @pixel_ram_size: size of latency hiding and de-tiling buffer in bytes
+ * @maxhdeciexp: max horizontal decimation supported by this pipe
+ *				(max is 2^value)
+ * @maxvdeciexp: max vertical decimation supported by this pipe
+ *				(max is 2^value)
+ */
+struct dpu_sspp_blks_common {
+	u32 maxlinewidth;
+	u32 pixel_ram_size;
+	u32 maxhdeciexp;
+	u32 maxvdeciexp;
+};
+
+/**
+ * struct dpu_sspp_sub_blks : SSPP sub-blocks
+ * common: Pointer to common configurations shared by sub blocks
+ * @creq_vblank: creq priority during vertical blanking
+ * @danger_vblank: danger priority during vertical blanking
+ * @maxdwnscale: max downscale ratio supported(without DECIMATION)
+ * @maxupscale:  maxupscale ratio supported
+ * @smart_dma_priority: hw priority of rect1 of multirect pipe
+ * @max_per_pipe_bw: maximum allowable bandwidth of this pipe in kBps
+ * @src_blk:
+ * @scaler_blk:
+ * @csc_blk:
+ * @hsic:
+ * @memcolor:
+ * @pcc_blk:
+ * @igc_blk:
+ * @format_list: Pointer to list of supported formats
+ * @virt_format_list: Pointer to list of supported formats for virtual planes
+ */
+struct dpu_sspp_sub_blks {
+	const struct dpu_sspp_blks_common *common;
+	u32 creq_vblank;
+	u32 danger_vblank;
+	u32 maxdwnscale;
+	u32 maxupscale;
+	u32 smart_dma_priority;
+	u32 max_per_pipe_bw;
+	struct dpu_src_blk src_blk;
+	struct dpu_scaler_blk scaler_blk;
+	struct dpu_pp_blk csc_blk;
+	struct dpu_pp_blk hsic_blk;
+	struct dpu_pp_blk memcolor_blk;
+	struct dpu_pp_blk pcc_blk;
+	struct dpu_pp_blk igc_blk;
+
+	const struct dpu_format_extended *format_list;
+	const struct dpu_format_extended *virt_format_list;
+};
+
+/**
+ * struct dpu_lm_sub_blks:      information of mixer block
+ * @maxwidth:               Max pixel width supported by this mixer
+ * @maxblendstages:         Max number of blend-stages supported
+ * @blendstage_base:        Blend-stage register base offset
+ * @gc: gamma correction block
+ */
+struct dpu_lm_sub_blks {
+	u32 maxwidth;
+	u32 maxblendstages;
+	u32 blendstage_base[MAX_BLOCKS];
+	struct dpu_pp_blk gc;
+};
+
+struct dpu_pingpong_sub_blks {
+	struct dpu_pp_blk te;
+	struct dpu_pp_blk te2;
+	struct dpu_pp_blk dither;
+};
+
+/**
+ * dpu_clk_ctrl_type - Defines top level clock control signals
+ */
+enum dpu_clk_ctrl_type {
+	DPU_CLK_CTRL_NONE,
+	DPU_CLK_CTRL_VIG0,
+	DPU_CLK_CTRL_VIG1,
+	DPU_CLK_CTRL_VIG2,
+	DPU_CLK_CTRL_VIG3,
+	DPU_CLK_CTRL_VIG4,
+	DPU_CLK_CTRL_RGB0,
+	DPU_CLK_CTRL_RGB1,
+	DPU_CLK_CTRL_RGB2,
+	DPU_CLK_CTRL_RGB3,
+	DPU_CLK_CTRL_DMA0,
+	DPU_CLK_CTRL_DMA1,
+	DPU_CLK_CTRL_CURSOR0,
+	DPU_CLK_CTRL_CURSOR1,
+	DPU_CLK_CTRL_INLINE_ROT0_SSPP,
+	DPU_CLK_CTRL_MAX,
+};
+
+/* struct dpu_clk_ctrl_reg : Clock control register
+ * @reg_off:           register offset
+ * @bit_off:           bit offset
+ */
+struct dpu_clk_ctrl_reg {
+	u32 reg_off;
+	u32 bit_off;
+};
+
+/* struct dpu_mdp_cfg : MDP TOP-BLK instance info
+ * @id:                index identifying this block
+ * @base:              register base offset to mdss
+ * @features           bit mask identifying sub-blocks/features
+ * @highest_bank_bit:  UBWC parameter
+ * @ubwc_static:       ubwc static configuration
+ * @ubwc_swizzle:      ubwc default swizzle setting
+ * @has_dest_scaler:   indicates support of destination scaler
+ * @clk_ctrls          clock control register definition
+ */
+struct dpu_mdp_cfg {
+	DPU_HW_BLK_INFO;
+	u32 highest_bank_bit;
+	u32 ubwc_static;
+	u32 ubwc_swizzle;
+	bool has_dest_scaler;
+	struct dpu_clk_ctrl_reg clk_ctrls[DPU_CLK_CTRL_MAX];
+};
+
+/* struct dpu_mdp_cfg : MDP TOP-BLK instance info
+ * @id:                index identifying this block
+ * @base:              register base offset to mdss
+ * @features           bit mask identifying sub-blocks/features
+ */
+struct dpu_ctl_cfg {
+	DPU_HW_BLK_INFO;
+};
+
+/**
+ * struct dpu_sspp_cfg - information of source pipes
+ * @id:                index identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @sblk:              SSPP sub-blocks information
+ * @xin_id:            bus client identifier
+ * @clk_ctrl           clock control identifier
+ * @type               sspp type identifier
+ */
+struct dpu_sspp_cfg {
+	DPU_HW_BLK_INFO;
+	const struct dpu_sspp_sub_blks *sblk;
+	u32 xin_id;
+	enum dpu_clk_ctrl_type clk_ctrl;
+	u32 type;
+};
+
+/**
+ * struct dpu_lm_cfg - information of layer mixer blocks
+ * @id:                index identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @sblk:              LM Sub-blocks information
+ * @pingpong:          ID of connected PingPong, PINGPONG_MAX if unsupported
+ * @ds:                ID of connected DS, DS_MAX if unsupported
+ * @lm_pair_mask:      Bitmask of LMs that can be controlled by same CTL
+ */
+struct dpu_lm_cfg {
+	DPU_HW_BLK_INFO;
+	const struct dpu_lm_sub_blks *sblk;
+	u32 pingpong;
+	u32 ds;
+	unsigned long lm_pair_mask;
+};
+
+/**
+ * struct dpu_ds_top_cfg - information of dest scaler top
+ * @id               enum identifying this block
+ * @base             register offset of this block
+ * @features         bit mask identifying features
+ * @version          hw version of dest scaler
+ * @maxinputwidth    maximum input line width
+ * @maxoutputwidth   maximum output line width
+ * @maxupscale       maximum upscale ratio
+ */
+struct dpu_ds_top_cfg {
+	DPU_HW_BLK_INFO;
+	u32 version;
+	u32 maxinputwidth;
+	u32 maxoutputwidth;
+	u32 maxupscale;
+};
+
+/**
+ * struct dpu_ds_cfg - information of dest scaler blocks
+ * @id          enum identifying this block
+ * @base        register offset wrt DS top offset
+ * @features    bit mask identifying features
+ * @version     hw version of the qseed block
+ * @top         DS top information
+ */
+struct dpu_ds_cfg {
+	DPU_HW_BLK_INFO;
+	u32 version;
+	const struct dpu_ds_top_cfg *top;
+};
+
+/**
+ * struct dpu_pingpong_cfg - information of PING-PONG blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @sblk               sub-blocks information
+ */
+struct dpu_pingpong_cfg  {
+	DPU_HW_BLK_INFO;
+	const struct dpu_pingpong_sub_blks *sblk;
+};
+
+/**
+ * struct dpu_cdm_cfg - information of chroma down blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @intf_connect       Bitmask of INTF IDs this CDM can connect to
+ */
+struct dpu_cdm_cfg   {
+	DPU_HW_BLK_INFO;
+	unsigned long intf_connect;
+};
+
+/**
+ * struct dpu_intf_cfg - information of timing engine blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @type:              Interface type(DSI, DP, HDMI)
+ * @controller_id:     Controller Instance ID in case of multiple of intf type
+ * @prog_fetch_lines_worst_case	Worst case latency num lines needed to prefetch
+ */
+struct dpu_intf_cfg  {
+	DPU_HW_BLK_INFO;
+	u32 type;   /* interface type*/
+	u32 controller_id;
+	u32 prog_fetch_lines_worst_case;
+};
+
+/**
+ * struct dpu_vbif_dynamic_ot_cfg - dynamic OT setting
+ * @pps                pixel per seconds
+ * @ot_limit           OT limit to use up to specified pixel per second
+ */
+struct dpu_vbif_dynamic_ot_cfg {
+	u64 pps;
+	u32 ot_limit;
+};
+
+/**
+ * struct dpu_vbif_dynamic_ot_tbl - dynamic OT setting table
+ * @count              length of cfg
+ * @cfg                pointer to array of configuration settings with
+ *                     ascending requirements
+ */
+struct dpu_vbif_dynamic_ot_tbl {
+	u32 count;
+	struct dpu_vbif_dynamic_ot_cfg *cfg;
+};
+
+/**
+ * struct dpu_vbif_qos_tbl - QoS priority table
+ * @npriority_lvl      num of priority level
+ * @priority_lvl       pointer to array of priority level in ascending order
+ */
+struct dpu_vbif_qos_tbl {
+	u32 npriority_lvl;
+	u32 *priority_lvl;
+};
+
+/**
+ * struct dpu_vbif_cfg - information of VBIF blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @ot_rd_limit        default OT read limit
+ * @ot_wr_limit        default OT write limit
+ * @xin_halt_timeout   maximum time (in usec) for xin to halt
+ * @dynamic_ot_rd_tbl  dynamic OT read configuration table
+ * @dynamic_ot_wr_tbl  dynamic OT write configuration table
+ * @qos_rt_tbl         real-time QoS priority table
+ * @qos_nrt_tbl        non-real-time QoS priority table
+ * @memtype_count      number of defined memtypes
+ * @memtype            array of xin memtype definitions
+ */
+struct dpu_vbif_cfg {
+	DPU_HW_BLK_INFO;
+	u32 default_ot_rd_limit;
+	u32 default_ot_wr_limit;
+	u32 xin_halt_timeout;
+	struct dpu_vbif_dynamic_ot_tbl dynamic_ot_rd_tbl;
+	struct dpu_vbif_dynamic_ot_tbl dynamic_ot_wr_tbl;
+	struct dpu_vbif_qos_tbl qos_rt_tbl;
+	struct dpu_vbif_qos_tbl qos_nrt_tbl;
+	u32 memtype_count;
+	u32 memtype[MAX_XIN_COUNT];
+};
+/**
+ * struct dpu_reg_dma_cfg - information of lut dma blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @version            version of lutdma hw block
+ * @trigger_sel_off    offset to trigger select registers of lutdma
+ */
+struct dpu_reg_dma_cfg {
+	DPU_HW_BLK_INFO;
+	u32 version;
+	u32 trigger_sel_off;
+};
+
+/**
+ * Define CDP use cases
+ * @DPU_PERF_CDP_UDAGE_RT: real-time use cases
+ * @DPU_PERF_CDP_USAGE_NRT: non real-time use cases such as WFD
+ */
+enum {
+	DPU_PERF_CDP_USAGE_RT,
+	DPU_PERF_CDP_USAGE_NRT,
+	DPU_PERF_CDP_USAGE_MAX
+};
+
+/**
+ * struct dpu_perf_cdp_cfg - define CDP use case configuration
+ * @rd_enable: true if read pipe CDP is enabled
+ * @wr_enable: true if write pipe CDP is enabled
+ */
+struct dpu_perf_cdp_cfg {
+	bool rd_enable;
+	bool wr_enable;
+};
+
+/**
+ * struct dpu_perf_cfg - performance control settings
+ * @max_bw_low         low threshold of maximum bandwidth (kbps)
+ * @max_bw_high        high threshold of maximum bandwidth (kbps)
+ * @min_core_ib        minimum bandwidth for core (kbps)
+ * @min_core_ib        minimum mnoc ib vote in kbps
+ * @min_llcc_ib        minimum llcc ib vote in kbps
+ * @min_dram_ib        minimum dram ib vote in kbps
+ * @core_ib_ff         core instantaneous bandwidth fudge factor
+ * @core_clk_ff        core clock fudge factor
+ * @comp_ratio_rt      string of 0 or more of <fourcc>/<ven>/<mod>/<comp ratio>
+ * @comp_ratio_nrt     string of 0 or more of <fourcc>/<ven>/<mod>/<comp ratio>
+ * @undersized_prefill_lines   undersized prefill in lines
+ * @xtra_prefill_lines         extra prefill latency in lines
+ * @dest_scale_prefill_lines   destination scaler latency in lines
+ * @macrotile_perfill_lines    macrotile latency in lines
+ * @yuv_nv12_prefill_lines     yuv_nv12 latency in lines
+ * @linear_prefill_lines       linear latency in lines
+ * @downscaling_prefill_lines  downscaling latency in lines
+ * @amortizable_theshold minimum y position for traffic shaping prefill
+ * @min_prefill_lines  minimum pipeline latency in lines
+ * @safe_lut_tbl: LUT tables for safe signals
+ * @danger_lut_tbl: LUT tables for danger signals
+ * @qos_lut_tbl: LUT tables for QoS signals
+ * @cdp_cfg            cdp use case configurations
+ */
+struct dpu_perf_cfg {
+	u32 max_bw_low;
+	u32 max_bw_high;
+	u32 min_core_ib;
+	u32 min_llcc_ib;
+	u32 min_dram_ib;
+	const char *core_ib_ff;
+	const char *core_clk_ff;
+	const char *comp_ratio_rt;
+	const char *comp_ratio_nrt;
+	u32 undersized_prefill_lines;
+	u32 xtra_prefill_lines;
+	u32 dest_scale_prefill_lines;
+	u32 macrotile_prefill_lines;
+	u32 yuv_nv12_prefill_lines;
+	u32 linear_prefill_lines;
+	u32 downscaling_prefill_lines;
+	u32 amortizable_threshold;
+	u32 min_prefill_lines;
+	u32 safe_lut_tbl[DPU_QOS_LUT_USAGE_MAX];
+	u32 danger_lut_tbl[DPU_QOS_LUT_USAGE_MAX];
+	struct dpu_qos_lut_tbl qos_lut_tbl[DPU_QOS_LUT_USAGE_MAX];
+	struct dpu_perf_cdp_cfg cdp_cfg[DPU_PERF_CDP_USAGE_MAX];
+};
+
+/**
+ * struct dpu_mdss_cfg - information of MDSS HW
+ * This is the main catalog data structure representing
+ * this HW version. Contains number of instances,
+ * register offsets, capabilities of the all MDSS HW sub-blocks.
+ *
+ * @dma_formats        Supported formats for dma pipe
+ * @cursor_formats     Supported formats for cursor pipe
+ * @vig_formats        Supported formats for vig pipe
+ */
+struct dpu_mdss_cfg {
+	u32 hwversion;
+
+	const struct dpu_caps *caps;
+
+	u32 mdp_count;
+	struct dpu_mdp_cfg *mdp;
+
+	u32 ctl_count;
+	struct dpu_ctl_cfg *ctl;
+
+	u32 sspp_count;
+	struct dpu_sspp_cfg *sspp;
+
+	u32 mixer_count;
+	struct dpu_lm_cfg *mixer;
+
+	u32 ds_count;
+	struct dpu_ds_cfg *ds;
+
+	u32 pingpong_count;
+	struct dpu_pingpong_cfg *pingpong;
+
+	u32 cdm_count;
+	struct dpu_cdm_cfg *cdm;
+
+	u32 intf_count;
+	struct dpu_intf_cfg *intf;
+
+	u32 vbif_count;
+	struct dpu_vbif_cfg *vbif;
+
+	u32 reg_dma_count;
+	struct dpu_reg_dma_cfg dma_cfg;
+
+	u32 ad_count;
+
+	/* Add additional block data structures here */
+
+	struct dpu_perf_cfg perf;
+	struct dpu_format_extended *dma_formats;
+	struct dpu_format_extended *cursor_formats;
+	struct dpu_format_extended *vig_formats;
+};
+
+struct dpu_mdss_hw_cfg_handler {
+	u32 hw_rev;
+	void (*cfg_init)(struct dpu_mdss_cfg *dpu_cfg);
+};
+
+/*
+ * Access Macros
+ */
+#define BLK_MDP(s) ((s)->mdp)
+#define BLK_CTL(s) ((s)->ctl)
+#define BLK_VIG(s) ((s)->vig)
+#define BLK_RGB(s) ((s)->rgb)
+#define BLK_DMA(s) ((s)->dma)
+#define BLK_CURSOR(s) ((s)->cursor)
+#define BLK_MIXER(s) ((s)->mixer)
+#define BLK_DS(s) ((s)->ds)
+#define BLK_PINGPONG(s) ((s)->pingpong)
+#define BLK_CDM(s) ((s)->cdm)
+#define BLK_INTF(s) ((s)->intf)
+#define BLK_AD(s) ((s)->ad)
+
+/**
+ * dpu_hw_catalog_init - dpu hardware catalog init API retrieves
+ * hardcoded target specific catalog information in config structure
+ * @hw_rev:       caller needs provide the hardware revision.
+ *
+ * Return: dpu config structure
+ */
+struct dpu_mdss_cfg *dpu_hw_catalog_init(u32 hw_rev);
+
+/**
+ * dpu_hw_catalog_deinit - dpu hardware catalog cleanup
+ * @dpu_cfg:      pointer returned from init function
+ */
+void dpu_hw_catalog_deinit(struct dpu_mdss_cfg *dpu_cfg);
+
+/**
+ * dpu_hw_sspp_multirect_enabled - check multirect enabled for the sspp
+ * @cfg:          pointer to sspp cfg
+ */
+static inline bool dpu_hw_sspp_multirect_enabled(const struct dpu_sspp_cfg *cfg)
+{
+	return test_bit(DPU_SSPP_SMART_DMA_V1, &cfg->features) ||
+			 test_bit(DPU_SSPP_SMART_DMA_V2, &cfg->features);
+}
+#endif /* _DPU_HW_CATALOG_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h
new file mode 100644
index 000000000000..3c9f028628ef
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h
@@ -0,0 +1,168 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_hw_mdss.h"
+
+static const struct dpu_format_extended plane_formats[] = {
+	{DRM_FORMAT_ARGB8888, 0},
+	{DRM_FORMAT_ABGR8888, 0},
+	{DRM_FORMAT_RGBA8888, 0},
+	{DRM_FORMAT_ABGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_BGRA8888, 0},
+	{DRM_FORMAT_XRGB8888, 0},
+	{DRM_FORMAT_RGBX8888, 0},
+	{DRM_FORMAT_BGRX8888, 0},
+	{DRM_FORMAT_XBGR8888, 0},
+	{DRM_FORMAT_XBGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_RGB888, 0},
+	{DRM_FORMAT_BGR888, 0},
+	{DRM_FORMAT_RGB565, 0},
+	{DRM_FORMAT_BGR565, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_BGR565, 0},
+	{DRM_FORMAT_ARGB1555, 0},
+	{DRM_FORMAT_ABGR1555, 0},
+	{DRM_FORMAT_RGBA5551, 0},
+	{DRM_FORMAT_BGRA5551, 0},
+	{DRM_FORMAT_XRGB1555, 0},
+	{DRM_FORMAT_XBGR1555, 0},
+	{DRM_FORMAT_RGBX5551, 0},
+	{DRM_FORMAT_BGRX5551, 0},
+	{DRM_FORMAT_ARGB4444, 0},
+	{DRM_FORMAT_ABGR4444, 0},
+	{DRM_FORMAT_RGBA4444, 0},
+	{DRM_FORMAT_BGRA4444, 0},
+	{DRM_FORMAT_XRGB4444, 0},
+	{DRM_FORMAT_XBGR4444, 0},
+	{DRM_FORMAT_RGBX4444, 0},
+	{DRM_FORMAT_BGRX4444, 0},
+	{0, 0},
+};
+
+static const struct dpu_format_extended plane_formats_yuv[] = {
+	{DRM_FORMAT_ARGB8888, 0},
+	{DRM_FORMAT_ABGR8888, 0},
+	{DRM_FORMAT_RGBA8888, 0},
+	{DRM_FORMAT_BGRX8888, 0},
+	{DRM_FORMAT_ABGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_BGRA8888, 0},
+	{DRM_FORMAT_XRGB8888, 0},
+	{DRM_FORMAT_XBGR8888, 0},
+	{DRM_FORMAT_RGBX8888, 0},
+	{DRM_FORMAT_XBGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_RGB888, 0},
+	{DRM_FORMAT_BGR888, 0},
+	{DRM_FORMAT_RGB565, 0},
+	{DRM_FORMAT_BGR565, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_BGR565, 0},
+	{DRM_FORMAT_ARGB1555, 0},
+	{DRM_FORMAT_ABGR1555, 0},
+	{DRM_FORMAT_RGBA5551, 0},
+	{DRM_FORMAT_BGRA5551, 0},
+	{DRM_FORMAT_XRGB1555, 0},
+	{DRM_FORMAT_XBGR1555, 0},
+	{DRM_FORMAT_RGBX5551, 0},
+	{DRM_FORMAT_BGRX5551, 0},
+	{DRM_FORMAT_ARGB4444, 0},
+	{DRM_FORMAT_ABGR4444, 0},
+	{DRM_FORMAT_RGBA4444, 0},
+	{DRM_FORMAT_BGRA4444, 0},
+	{DRM_FORMAT_XRGB4444, 0},
+	{DRM_FORMAT_XBGR4444, 0},
+	{DRM_FORMAT_RGBX4444, 0},
+	{DRM_FORMAT_BGRX4444, 0},
+
+	{DRM_FORMAT_NV12, 0},
+	{DRM_FORMAT_NV12, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_NV21, 0},
+	{DRM_FORMAT_NV16, 0},
+	{DRM_FORMAT_NV61, 0},
+	{DRM_FORMAT_VYUY, 0},
+	{DRM_FORMAT_UYVY, 0},
+	{DRM_FORMAT_YUYV, 0},
+	{DRM_FORMAT_YVYU, 0},
+	{DRM_FORMAT_YUV420, 0},
+	{DRM_FORMAT_YVU420, 0},
+	{0, 0},
+};
+
+static const struct dpu_format_extended cursor_formats[] = {
+	{DRM_FORMAT_ARGB8888, 0},
+	{DRM_FORMAT_ABGR8888, 0},
+	{DRM_FORMAT_RGBA8888, 0},
+	{DRM_FORMAT_BGRA8888, 0},
+	{DRM_FORMAT_XRGB8888, 0},
+	{DRM_FORMAT_ARGB1555, 0},
+	{DRM_FORMAT_ABGR1555, 0},
+	{DRM_FORMAT_RGBA5551, 0},
+	{DRM_FORMAT_BGRA5551, 0},
+	{DRM_FORMAT_ARGB4444, 0},
+	{DRM_FORMAT_ABGR4444, 0},
+	{DRM_FORMAT_RGBA4444, 0},
+	{DRM_FORMAT_BGRA4444, 0},
+	{0, 0},
+};
+
+static const struct dpu_format_extended wb2_formats[] = {
+	{DRM_FORMAT_RGB565, 0},
+	{DRM_FORMAT_BGR565, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_RGB888, 0},
+	{DRM_FORMAT_ARGB8888, 0},
+	{DRM_FORMAT_RGBA8888, 0},
+	{DRM_FORMAT_ABGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_XRGB8888, 0},
+	{DRM_FORMAT_RGBX8888, 0},
+	{DRM_FORMAT_XBGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_ARGB1555, 0},
+	{DRM_FORMAT_RGBA5551, 0},
+	{DRM_FORMAT_XRGB1555, 0},
+	{DRM_FORMAT_RGBX5551, 0},
+	{DRM_FORMAT_ARGB4444, 0},
+	{DRM_FORMAT_RGBA4444, 0},
+	{DRM_FORMAT_RGBX4444, 0},
+	{DRM_FORMAT_XRGB4444, 0},
+
+	{DRM_FORMAT_BGR565, 0},
+	{DRM_FORMAT_BGR888, 0},
+	{DRM_FORMAT_ABGR8888, 0},
+	{DRM_FORMAT_BGRA8888, 0},
+	{DRM_FORMAT_BGRX8888, 0},
+	{DRM_FORMAT_XBGR8888, 0},
+	{DRM_FORMAT_ABGR1555, 0},
+	{DRM_FORMAT_BGRA5551, 0},
+	{DRM_FORMAT_XBGR1555, 0},
+	{DRM_FORMAT_BGRX5551, 0},
+	{DRM_FORMAT_ABGR4444, 0},
+	{DRM_FORMAT_BGRA4444, 0},
+	{DRM_FORMAT_BGRX4444, 0},
+	{DRM_FORMAT_XBGR4444, 0},
+
+	{DRM_FORMAT_YUV420, 0},
+	{DRM_FORMAT_NV12, 0},
+	{DRM_FORMAT_NV12, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_NV16, 0},
+	{DRM_FORMAT_YUYV, 0},
+
+	{0, 0},
+};
+
+static const struct dpu_format_extended rgb_10bit_formats[] = {
+	{DRM_FORMAT_BGRA1010102, 0},
+	{DRM_FORMAT_BGRX1010102, 0},
+	{DRM_FORMAT_RGBA1010102, 0},
+	{DRM_FORMAT_RGBX1010102, 0},
+	{DRM_FORMAT_ABGR2101010, 0},
+	{DRM_FORMAT_ABGR2101010, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_XBGR2101010, 0},
+	{DRM_FORMAT_XBGR2101010, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_ARGB2101010, 0},
+	{DRM_FORMAT_XRGB2101010, 0},
+};
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c
new file mode 100644
index 000000000000..554874ba0c3b
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c
@@ -0,0 +1,323 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_cdm.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+
+#define CDM_CSC_10_OPMODE                  0x000
+#define CDM_CSC_10_BASE                    0x004
+
+#define CDM_CDWN2_OP_MODE                  0x100
+#define CDM_CDWN2_CLAMP_OUT                0x104
+#define CDM_CDWN2_PARAMS_3D_0              0x108
+#define CDM_CDWN2_PARAMS_3D_1              0x10C
+#define CDM_CDWN2_COEFF_COSITE_H_0         0x110
+#define CDM_CDWN2_COEFF_COSITE_H_1         0x114
+#define CDM_CDWN2_COEFF_COSITE_H_2         0x118
+#define CDM_CDWN2_COEFF_OFFSITE_H_0        0x11C
+#define CDM_CDWN2_COEFF_OFFSITE_H_1        0x120
+#define CDM_CDWN2_COEFF_OFFSITE_H_2        0x124
+#define CDM_CDWN2_COEFF_COSITE_V           0x128
+#define CDM_CDWN2_COEFF_OFFSITE_V          0x12C
+#define CDM_CDWN2_OUT_SIZE                 0x130
+
+#define CDM_HDMI_PACK_OP_MODE              0x200
+#define CDM_CSC_10_MATRIX_COEFF_0          0x004
+
+/**
+ * Horizontal coefficients for cosite chroma downscale
+ * s13 representation of coefficients
+ */
+static u32 cosite_h_coeff[] = {0x00000016, 0x000001cc, 0x0100009e};
+
+/**
+ * Horizontal coefficients for offsite chroma downscale
+ */
+static u32 offsite_h_coeff[] = {0x000b0005, 0x01db01eb, 0x00e40046};
+
+/**
+ * Vertical coefficients for cosite chroma downscale
+ */
+static u32 cosite_v_coeff[] = {0x00080004};
+/**
+ * Vertical coefficients for offsite chroma downscale
+ */
+static u32 offsite_v_coeff[] = {0x00060002};
+
+/* Limited Range rgb2yuv coeff with clamp and bias values for CSC 10 module */
+static struct dpu_csc_cfg rgb2yuv_cfg = {
+	{
+		0x0083, 0x0102, 0x0032,
+		0x1fb5, 0x1f6c, 0x00e1,
+		0x00e1, 0x1f45, 0x1fdc
+	},
+	{ 0x00, 0x00, 0x00 },
+	{ 0x0040, 0x0200, 0x0200 },
+	{ 0x000, 0x3ff, 0x000, 0x3ff, 0x000, 0x3ff },
+	{ 0x040, 0x3ac, 0x040, 0x3c0, 0x040, 0x3c0 },
+};
+
+static struct dpu_cdm_cfg *_cdm_offset(enum dpu_cdm cdm,
+		struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->cdm_count; i++) {
+		if (cdm == m->cdm[i].id) {
+			b->base_off = addr;
+			b->blk_off = m->cdm[i].base;
+			b->length = m->cdm[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_CDM;
+			return &m->cdm[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static int dpu_hw_cdm_setup_csc_10bit(struct dpu_hw_cdm *ctx,
+		struct dpu_csc_cfg *data)
+{
+	dpu_hw_csc_setup(&ctx->hw, CDM_CSC_10_MATRIX_COEFF_0, data, true);
+
+	return 0;
+}
+
+static int dpu_hw_cdm_setup_cdwn(struct dpu_hw_cdm *ctx,
+		struct dpu_hw_cdm_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 opmode = 0;
+	u32 out_size = 0;
+
+	if (cfg->output_bit_depth == CDM_CDWN_OUTPUT_10BIT)
+		opmode &= ~BIT(7);
+	else
+		opmode |= BIT(7);
+
+	/* ENABLE DWNS_H bit */
+	opmode |= BIT(1);
+
+	switch (cfg->h_cdwn_type) {
+	case CDM_CDWN_DISABLE:
+		/* CLEAR METHOD_H field */
+		opmode &= ~(0x18);
+		/* CLEAR DWNS_H bit */
+		opmode &= ~BIT(1);
+		break;
+	case CDM_CDWN_PIXEL_DROP:
+		/* Clear METHOD_H field (pixel drop is 0) */
+		opmode &= ~(0x18);
+		break;
+	case CDM_CDWN_AVG:
+		/* Clear METHOD_H field (Average is 0x1) */
+		opmode &= ~(0x18);
+		opmode |= (0x1 << 0x3);
+		break;
+	case CDM_CDWN_COSITE:
+		/* Clear METHOD_H field (Average is 0x2) */
+		opmode &= ~(0x18);
+		opmode |= (0x2 << 0x3);
+		/* Co-site horizontal coefficients */
+		DPU_REG_WRITE(c, CDM_CDWN2_COEFF_COSITE_H_0,
+				cosite_h_coeff[0]);
+		DPU_REG_WRITE(c, CDM_CDWN2_COEFF_COSITE_H_1,
+				cosite_h_coeff[1]);
+		DPU_REG_WRITE(c, CDM_CDWN2_COEFF_COSITE_H_2,
+				cosite_h_coeff[2]);
+		break;
+	case CDM_CDWN_OFFSITE:
+		/* Clear METHOD_H field (Average is 0x3) */
+		opmode &= ~(0x18);
+		opmode |= (0x3 << 0x3);
+
+		/* Off-site horizontal coefficients */
+		DPU_REG_WRITE(c, CDM_CDWN2_COEFF_OFFSITE_H_0,
+				offsite_h_coeff[0]);
+		DPU_REG_WRITE(c, CDM_CDWN2_COEFF_OFFSITE_H_1,
+				offsite_h_coeff[1]);
+		DPU_REG_WRITE(c, CDM_CDWN2_COEFF_OFFSITE_H_2,
+				offsite_h_coeff[2]);
+		break;
+	default:
+		pr_err("%s invalid horz down sampling type\n", __func__);
+		return -EINVAL;
+	}
+
+	/* ENABLE DWNS_V bit */
+	opmode |= BIT(2);
+
+	switch (cfg->v_cdwn_type) {
+	case CDM_CDWN_DISABLE:
+		/* CLEAR METHOD_V field */
+		opmode &= ~(0x60);
+		/* CLEAR DWNS_V bit */
+		opmode &= ~BIT(2);
+		break;
+	case CDM_CDWN_PIXEL_DROP:
+		/* Clear METHOD_V field (pixel drop is 0) */
+		opmode &= ~(0x60);
+		break;
+	case CDM_CDWN_AVG:
+		/* Clear METHOD_V field (Average is 0x1) */
+		opmode &= ~(0x60);
+		opmode |= (0x1 << 0x5);
+		break;
+	case CDM_CDWN_COSITE:
+		/* Clear METHOD_V field (Average is 0x2) */
+		opmode &= ~(0x60);
+		opmode |= (0x2 << 0x5);
+		/* Co-site vertical coefficients */
+		DPU_REG_WRITE(c,
+				CDM_CDWN2_COEFF_COSITE_V,
+				cosite_v_coeff[0]);
+		break;
+	case CDM_CDWN_OFFSITE:
+		/* Clear METHOD_V field (Average is 0x3) */
+		opmode &= ~(0x60);
+		opmode |= (0x3 << 0x5);
+
+		/* Off-site vertical coefficients */
+		DPU_REG_WRITE(c,
+				CDM_CDWN2_COEFF_OFFSITE_V,
+				offsite_v_coeff[0]);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (cfg->v_cdwn_type || cfg->h_cdwn_type)
+		opmode |= BIT(0); /* EN CDWN module */
+	else
+		opmode &= ~BIT(0);
+
+	out_size = (cfg->output_width & 0xFFFF) |
+		((cfg->output_height & 0xFFFF) << 16);
+	DPU_REG_WRITE(c, CDM_CDWN2_OUT_SIZE, out_size);
+	DPU_REG_WRITE(c, CDM_CDWN2_OP_MODE, opmode);
+	DPU_REG_WRITE(c, CDM_CDWN2_CLAMP_OUT,
+			((0x3FF << 16) | 0x0));
+
+	return 0;
+}
+
+static int dpu_hw_cdm_enable(struct dpu_hw_cdm *ctx,
+		struct dpu_hw_cdm_cfg *cdm)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	const struct dpu_format *fmt = cdm->output_fmt;
+	struct cdm_output_cfg cdm_cfg = { 0 };
+	u32 opmode = 0;
+	u32 csc = 0;
+
+	if (!DPU_FORMAT_IS_YUV(fmt))
+		return -EINVAL;
+
+	if (cdm->output_type == CDM_CDWN_OUTPUT_HDMI) {
+		if (fmt->chroma_sample != DPU_CHROMA_H1V2)
+			return -EINVAL; /*unsupported format */
+		opmode = BIT(0);
+		opmode |= (fmt->chroma_sample << 1);
+		cdm_cfg.intf_en = true;
+	}
+
+	csc |= BIT(2);
+	csc &= ~BIT(1);
+	csc |= BIT(0);
+
+	if (ctx->hw_mdp && ctx->hw_mdp->ops.setup_cdm_output)
+		ctx->hw_mdp->ops.setup_cdm_output(ctx->hw_mdp, &cdm_cfg);
+
+	DPU_REG_WRITE(c, CDM_CSC_10_OPMODE, csc);
+	DPU_REG_WRITE(c, CDM_HDMI_PACK_OP_MODE, opmode);
+	return 0;
+}
+
+static void dpu_hw_cdm_disable(struct dpu_hw_cdm *ctx)
+{
+	struct cdm_output_cfg cdm_cfg = { 0 };
+
+	if (ctx->hw_mdp && ctx->hw_mdp->ops.setup_cdm_output)
+		ctx->hw_mdp->ops.setup_cdm_output(ctx->hw_mdp, &cdm_cfg);
+}
+
+static void _setup_cdm_ops(struct dpu_hw_cdm_ops *ops,
+	unsigned long features)
+{
+	ops->setup_csc_data = dpu_hw_cdm_setup_csc_10bit;
+	ops->setup_cdwn = dpu_hw_cdm_setup_cdwn;
+	ops->enable = dpu_hw_cdm_enable;
+	ops->disable = dpu_hw_cdm_disable;
+}
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_cdm *dpu_hw_cdm_init(enum dpu_cdm idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m,
+		struct dpu_hw_mdp *hw_mdp)
+{
+	struct dpu_hw_cdm *c;
+	struct dpu_cdm_cfg *cfg;
+	int rc;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _cdm_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		return ERR_PTR(-EINVAL);
+	}
+
+	c->idx = idx;
+	c->caps = cfg;
+	_setup_cdm_ops(&c->ops, c->caps->features);
+	c->hw_mdp = hw_mdp;
+
+	rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_CDM, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	/*
+	 * Perform any default initialization for the chroma down module
+	 * @setup default csc coefficients
+	 */
+	dpu_hw_cdm_setup_csc_10bit(c, &rgb2yuv_cfg);
+
+	return c;
+
+blk_init_error:
+	kzfree(c);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_cdm_destroy(struct dpu_hw_cdm *cdm)
+{
+	if (cdm)
+		dpu_hw_blk_destroy(&cdm->base);
+	kfree(cdm);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.h
new file mode 100644
index 000000000000..5cceb1ecb8e0
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.h
@@ -0,0 +1,139 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_CDM_H
+#define _DPU_HW_CDM_H
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_top.h"
+#include "dpu_hw_blk.h"
+
+struct dpu_hw_cdm;
+
+struct dpu_hw_cdm_cfg {
+	u32 output_width;
+	u32 output_height;
+	u32 output_bit_depth;
+	u32 h_cdwn_type;
+	u32 v_cdwn_type;
+	const struct dpu_format *output_fmt;
+	u32 output_type;
+	int flags;
+};
+
+enum dpu_hw_cdwn_type {
+	CDM_CDWN_DISABLE,
+	CDM_CDWN_PIXEL_DROP,
+	CDM_CDWN_AVG,
+	CDM_CDWN_COSITE,
+	CDM_CDWN_OFFSITE,
+};
+
+enum dpu_hw_cdwn_output_type {
+	CDM_CDWN_OUTPUT_HDMI,
+	CDM_CDWN_OUTPUT_WB,
+};
+
+enum dpu_hw_cdwn_output_bit_depth {
+	CDM_CDWN_OUTPUT_8BIT,
+	CDM_CDWN_OUTPUT_10BIT,
+};
+
+/**
+ * struct dpu_hw_cdm_ops : Interface to the chroma down Hw driver functions
+ *                         Assumption is these functions will be called after
+ *                         clocks are enabled
+ *  @setup_csc:            Programs the csc matrix
+ *  @setup_cdwn:           Sets up the chroma down sub module
+ *  @enable:               Enables the output to interface and programs the
+ *                         output packer
+ *  @disable:              Puts the cdm in bypass mode
+ */
+struct dpu_hw_cdm_ops {
+	/**
+	 * Programs the CSC matrix for conversion from RGB space to YUV space,
+	 * it is optional to call this function as this matrix is automatically
+	 * set during initialization, user should call this if it wants
+	 * to program a different matrix than default matrix.
+	 * @cdm:          Pointer to the chroma down context structure
+	 * @data          Pointer to CSC configuration data
+	 * return:        0 if success; error code otherwise
+	 */
+	int (*setup_csc_data)(struct dpu_hw_cdm *cdm,
+			struct dpu_csc_cfg *data);
+
+	/**
+	 * Programs the Chroma downsample part.
+	 * @cdm         Pointer to chroma down context
+	 */
+	int (*setup_cdwn)(struct dpu_hw_cdm *cdm,
+	struct dpu_hw_cdm_cfg *cfg);
+
+	/**
+	 * Enable the CDM module
+	 * @cdm         Pointer to chroma down context
+	 */
+	int (*enable)(struct dpu_hw_cdm *cdm,
+	struct dpu_hw_cdm_cfg *cfg);
+
+	/**
+	 * Disable the CDM module
+	 * @cdm         Pointer to chroma down context
+	 */
+	void (*disable)(struct dpu_hw_cdm *cdm);
+};
+
+struct dpu_hw_cdm {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* chroma down */
+	const struct dpu_cdm_cfg *caps;
+	enum  dpu_cdm  idx;
+
+	/* mdp top hw driver */
+	struct dpu_hw_mdp *hw_mdp;
+
+	/* ops */
+	struct dpu_hw_cdm_ops ops;
+};
+
+/**
+ * dpu_hw_cdm - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_cdm *to_dpu_hw_cdm(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_cdm, base);
+}
+
+/**
+ * dpu_hw_cdm_init - initializes the cdm hw driver object.
+ * should be called once before accessing every cdm.
+ * @idx:  cdm index for which driver object is required
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ * @hw_mdp:  pointer to mdp top hw driver object
+ */
+struct dpu_hw_cdm *dpu_hw_cdm_init(enum dpu_cdm idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m,
+		struct dpu_hw_mdp *hw_mdp);
+
+/**
+ * dpu_hw_cdm_destroy - destroys CDM driver context
+ * @cdm:   pointer to CDM driver context
+ */
+void dpu_hw_cdm_destroy(struct dpu_hw_cdm *cdm);
+
+#endif /*_DPU_HW_CDM_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
new file mode 100644
index 000000000000..06be7cf7ce50
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
@@ -0,0 +1,540 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/delay.h>
+#include "dpu_hwio.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+
+#define   CTL_LAYER(lm)                 \
+	(((lm) == LM_5) ? (0x024) : (((lm) - LM_0) * 0x004))
+#define   CTL_LAYER_EXT(lm)             \
+	(0x40 + (((lm) - LM_0) * 0x004))
+#define   CTL_LAYER_EXT2(lm)             \
+	(0x70 + (((lm) - LM_0) * 0x004))
+#define   CTL_LAYER_EXT3(lm)             \
+	(0xA0 + (((lm) - LM_0) * 0x004))
+#define   CTL_TOP                       0x014
+#define   CTL_FLUSH                     0x018
+#define   CTL_START                     0x01C
+#define   CTL_PREPARE                   0x0d0
+#define   CTL_SW_RESET                  0x030
+#define   CTL_LAYER_EXTN_OFFSET         0x40
+
+#define CTL_MIXER_BORDER_OUT            BIT(24)
+#define CTL_FLUSH_MASK_CTL              BIT(17)
+
+#define DPU_REG_RESET_TIMEOUT_US        2000
+
+static struct dpu_ctl_cfg *_ctl_offset(enum dpu_ctl ctl,
+		struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->ctl_count; i++) {
+		if (ctl == m->ctl[i].id) {
+			b->base_off = addr;
+			b->blk_off = m->ctl[i].base;
+			b->length = m->ctl[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_CTL;
+			return &m->ctl[i];
+		}
+	}
+	return ERR_PTR(-ENOMEM);
+}
+
+static int _mixer_stages(const struct dpu_lm_cfg *mixer, int count,
+		enum dpu_lm lm)
+{
+	int i;
+	int stages = -EINVAL;
+
+	for (i = 0; i < count; i++) {
+		if (lm == mixer[i].id) {
+			stages = mixer[i].sblk->maxblendstages;
+			break;
+		}
+	}
+
+	return stages;
+}
+
+static inline void dpu_hw_ctl_trigger_start(struct dpu_hw_ctl *ctx)
+{
+	DPU_REG_WRITE(&ctx->hw, CTL_START, 0x1);
+}
+
+static inline void dpu_hw_ctl_trigger_pending(struct dpu_hw_ctl *ctx)
+{
+	DPU_REG_WRITE(&ctx->hw, CTL_PREPARE, 0x1);
+}
+
+static inline void dpu_hw_ctl_clear_pending_flush(struct dpu_hw_ctl *ctx)
+{
+	ctx->pending_flush_mask = 0x0;
+}
+
+static inline void dpu_hw_ctl_update_pending_flush(struct dpu_hw_ctl *ctx,
+		u32 flushbits)
+{
+	ctx->pending_flush_mask |= flushbits;
+}
+
+static u32 dpu_hw_ctl_get_pending_flush(struct dpu_hw_ctl *ctx)
+{
+	if (!ctx)
+		return 0x0;
+
+	return ctx->pending_flush_mask;
+}
+
+static inline void dpu_hw_ctl_trigger_flush(struct dpu_hw_ctl *ctx)
+{
+
+	DPU_REG_WRITE(&ctx->hw, CTL_FLUSH, ctx->pending_flush_mask);
+}
+
+static inline u32 dpu_hw_ctl_get_flush_register(struct dpu_hw_ctl *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+
+	return DPU_REG_READ(c, CTL_FLUSH);
+}
+
+static inline uint32_t dpu_hw_ctl_get_bitmask_sspp(struct dpu_hw_ctl *ctx,
+	enum dpu_sspp sspp)
+{
+	uint32_t flushbits = 0;
+
+	switch (sspp) {
+	case SSPP_VIG0:
+		flushbits =  BIT(0);
+		break;
+	case SSPP_VIG1:
+		flushbits = BIT(1);
+		break;
+	case SSPP_VIG2:
+		flushbits = BIT(2);
+		break;
+	case SSPP_VIG3:
+		flushbits = BIT(18);
+		break;
+	case SSPP_RGB0:
+		flushbits = BIT(3);
+		break;
+	case SSPP_RGB1:
+		flushbits = BIT(4);
+		break;
+	case SSPP_RGB2:
+		flushbits = BIT(5);
+		break;
+	case SSPP_RGB3:
+		flushbits = BIT(19);
+		break;
+	case SSPP_DMA0:
+		flushbits = BIT(11);
+		break;
+	case SSPP_DMA1:
+		flushbits = BIT(12);
+		break;
+	case SSPP_DMA2:
+		flushbits = BIT(24);
+		break;
+	case SSPP_DMA3:
+		flushbits = BIT(25);
+		break;
+	case SSPP_CURSOR0:
+		flushbits = BIT(22);
+		break;
+	case SSPP_CURSOR1:
+		flushbits = BIT(23);
+		break;
+	default:
+		break;
+	}
+
+	return flushbits;
+}
+
+static inline uint32_t dpu_hw_ctl_get_bitmask_mixer(struct dpu_hw_ctl *ctx,
+	enum dpu_lm lm)
+{
+	uint32_t flushbits = 0;
+
+	switch (lm) {
+	case LM_0:
+		flushbits = BIT(6);
+		break;
+	case LM_1:
+		flushbits = BIT(7);
+		break;
+	case LM_2:
+		flushbits = BIT(8);
+		break;
+	case LM_3:
+		flushbits = BIT(9);
+		break;
+	case LM_4:
+		flushbits = BIT(10);
+		break;
+	case LM_5:
+		flushbits = BIT(20);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	flushbits |= CTL_FLUSH_MASK_CTL;
+
+	return flushbits;
+}
+
+static inline int dpu_hw_ctl_get_bitmask_intf(struct dpu_hw_ctl *ctx,
+		u32 *flushbits, enum dpu_intf intf)
+{
+	switch (intf) {
+	case INTF_0:
+		*flushbits |= BIT(31);
+		break;
+	case INTF_1:
+		*flushbits |= BIT(30);
+		break;
+	case INTF_2:
+		*flushbits |= BIT(29);
+		break;
+	case INTF_3:
+		*flushbits |= BIT(28);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static inline int dpu_hw_ctl_get_bitmask_cdm(struct dpu_hw_ctl *ctx,
+		u32 *flushbits, enum dpu_cdm cdm)
+{
+	switch (cdm) {
+	case CDM_0:
+		*flushbits |= BIT(26);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static u32 dpu_hw_ctl_poll_reset_status(struct dpu_hw_ctl *ctx, u32 timeout_us)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	ktime_t timeout;
+	u32 status;
+
+	timeout = ktime_add_us(ktime_get(), timeout_us);
+
+	/*
+	 * it takes around 30us to have mdp finish resetting its ctl path
+	 * poll every 50us so that reset should be completed at 1st poll
+	 */
+	do {
+		status = DPU_REG_READ(c, CTL_SW_RESET);
+		status &= 0x1;
+		if (status)
+			usleep_range(20, 50);
+	} while (status && ktime_compare_safe(ktime_get(), timeout) < 0);
+
+	return status;
+}
+
+static int dpu_hw_ctl_reset_control(struct dpu_hw_ctl *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+
+	pr_debug("issuing hw ctl reset for ctl:%d\n", ctx->idx);
+	DPU_REG_WRITE(c, CTL_SW_RESET, 0x1);
+	if (dpu_hw_ctl_poll_reset_status(ctx, DPU_REG_RESET_TIMEOUT_US))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int dpu_hw_ctl_wait_reset_status(struct dpu_hw_ctl *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 status;
+
+	status = DPU_REG_READ(c, CTL_SW_RESET);
+	status &= 0x01;
+	if (!status)
+		return 0;
+
+	pr_debug("hw ctl reset is set for ctl:%d\n", ctx->idx);
+	if (dpu_hw_ctl_poll_reset_status(ctx, DPU_REG_RESET_TIMEOUT_US)) {
+		pr_err("hw recovery is not complete for ctl:%d\n", ctx->idx);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void dpu_hw_ctl_clear_all_blendstages(struct dpu_hw_ctl *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	int i;
+
+	for (i = 0; i < ctx->mixer_count; i++) {
+		DPU_REG_WRITE(c, CTL_LAYER(LM_0 + i), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT(LM_0 + i), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT2(LM_0 + i), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT3(LM_0 + i), 0);
+	}
+}
+
+static void dpu_hw_ctl_setup_blendstage(struct dpu_hw_ctl *ctx,
+	enum dpu_lm lm, struct dpu_hw_stage_cfg *stage_cfg)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 mixercfg = 0, mixercfg_ext = 0, mix, ext;
+	u32 mixercfg_ext2 = 0, mixercfg_ext3 = 0;
+	int i, j;
+	u8 stages;
+	int pipes_per_stage;
+
+	stages = _mixer_stages(ctx->mixer_hw_caps, ctx->mixer_count, lm);
+	if (stages < 0)
+		return;
+
+	if (test_bit(DPU_MIXER_SOURCESPLIT,
+		&ctx->mixer_hw_caps->features))
+		pipes_per_stage = PIPES_PER_STAGE;
+	else
+		pipes_per_stage = 1;
+
+	mixercfg = CTL_MIXER_BORDER_OUT; /* always set BORDER_OUT */
+
+	if (!stage_cfg)
+		goto exit;
+
+	for (i = 0; i <= stages; i++) {
+		/* overflow to ext register if 'i + 1 > 7' */
+		mix = (i + 1) & 0x7;
+		ext = i >= 7;
+
+		for (j = 0 ; j < pipes_per_stage; j++) {
+			enum dpu_sspp_multirect_index rect_index =
+				stage_cfg->multirect_index[i][j];
+
+			switch (stage_cfg->stage[i][j]) {
+			case SSPP_VIG0:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext3 |= ((i + 1) & 0xF) << 0;
+				} else {
+					mixercfg |= mix << 0;
+					mixercfg_ext |= ext << 0;
+				}
+				break;
+			case SSPP_VIG1:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext3 |= ((i + 1) & 0xF) << 4;
+				} else {
+					mixercfg |= mix << 3;
+					mixercfg_ext |= ext << 2;
+				}
+				break;
+			case SSPP_VIG2:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext3 |= ((i + 1) & 0xF) << 8;
+				} else {
+					mixercfg |= mix << 6;
+					mixercfg_ext |= ext << 4;
+				}
+				break;
+			case SSPP_VIG3:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext3 |= ((i + 1) & 0xF) << 12;
+				} else {
+					mixercfg |= mix << 26;
+					mixercfg_ext |= ext << 6;
+				}
+				break;
+			case SSPP_RGB0:
+				mixercfg |= mix << 9;
+				mixercfg_ext |= ext << 8;
+				break;
+			case SSPP_RGB1:
+				mixercfg |= mix << 12;
+				mixercfg_ext |= ext << 10;
+				break;
+			case SSPP_RGB2:
+				mixercfg |= mix << 15;
+				mixercfg_ext |= ext << 12;
+				break;
+			case SSPP_RGB3:
+				mixercfg |= mix << 29;
+				mixercfg_ext |= ext << 14;
+				break;
+			case SSPP_DMA0:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext2 |= ((i + 1) & 0xF) << 8;
+				} else {
+					mixercfg |= mix << 18;
+					mixercfg_ext |= ext << 16;
+				}
+				break;
+			case SSPP_DMA1:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext2 |= ((i + 1) & 0xF) << 12;
+				} else {
+					mixercfg |= mix << 21;
+					mixercfg_ext |= ext << 18;
+				}
+				break;
+			case SSPP_DMA2:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext2 |= ((i + 1) & 0xF) << 16;
+				} else {
+					mix |= (i + 1) & 0xF;
+					mixercfg_ext2 |= mix << 0;
+				}
+				break;
+			case SSPP_DMA3:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext2 |= ((i + 1) & 0xF) << 20;
+				} else {
+					mix |= (i + 1) & 0xF;
+					mixercfg_ext2 |= mix << 4;
+				}
+				break;
+			case SSPP_CURSOR0:
+				mixercfg_ext |= ((i + 1) & 0xF) << 20;
+				break;
+			case SSPP_CURSOR1:
+				mixercfg_ext |= ((i + 1) & 0xF) << 26;
+				break;
+			default:
+				break;
+			}
+		}
+	}
+
+exit:
+	DPU_REG_WRITE(c, CTL_LAYER(lm), mixercfg);
+	DPU_REG_WRITE(c, CTL_LAYER_EXT(lm), mixercfg_ext);
+	DPU_REG_WRITE(c, CTL_LAYER_EXT2(lm), mixercfg_ext2);
+	DPU_REG_WRITE(c, CTL_LAYER_EXT3(lm), mixercfg_ext3);
+}
+
+static void dpu_hw_ctl_intf_cfg(struct dpu_hw_ctl *ctx,
+		struct dpu_hw_intf_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 intf_cfg = 0;
+
+	intf_cfg |= (cfg->intf & 0xF) << 4;
+
+	if (cfg->mode_3d) {
+		intf_cfg |= BIT(19);
+		intf_cfg |= (cfg->mode_3d - 0x1) << 20;
+	}
+
+	switch (cfg->intf_mode_sel) {
+	case DPU_CTL_MODE_SEL_VID:
+		intf_cfg &= ~BIT(17);
+		intf_cfg &= ~(0x3 << 15);
+		break;
+	case DPU_CTL_MODE_SEL_CMD:
+		intf_cfg |= BIT(17);
+		intf_cfg |= ((cfg->stream_sel & 0x3) << 15);
+		break;
+	default:
+		pr_err("unknown interface type %d\n", cfg->intf_mode_sel);
+		return;
+	}
+
+	DPU_REG_WRITE(c, CTL_TOP, intf_cfg);
+}
+
+static void _setup_ctl_ops(struct dpu_hw_ctl_ops *ops,
+		unsigned long cap)
+{
+	ops->clear_pending_flush = dpu_hw_ctl_clear_pending_flush;
+	ops->update_pending_flush = dpu_hw_ctl_update_pending_flush;
+	ops->get_pending_flush = dpu_hw_ctl_get_pending_flush;
+	ops->trigger_flush = dpu_hw_ctl_trigger_flush;
+	ops->get_flush_register = dpu_hw_ctl_get_flush_register;
+	ops->trigger_start = dpu_hw_ctl_trigger_start;
+	ops->trigger_pending = dpu_hw_ctl_trigger_pending;
+	ops->setup_intf_cfg = dpu_hw_ctl_intf_cfg;
+	ops->reset = dpu_hw_ctl_reset_control;
+	ops->wait_reset_status = dpu_hw_ctl_wait_reset_status;
+	ops->clear_all_blendstages = dpu_hw_ctl_clear_all_blendstages;
+	ops->setup_blendstage = dpu_hw_ctl_setup_blendstage;
+	ops->get_bitmask_sspp = dpu_hw_ctl_get_bitmask_sspp;
+	ops->get_bitmask_mixer = dpu_hw_ctl_get_bitmask_mixer;
+	ops->get_bitmask_intf = dpu_hw_ctl_get_bitmask_intf;
+	ops->get_bitmask_cdm = dpu_hw_ctl_get_bitmask_cdm;
+};
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_ctl *dpu_hw_ctl_init(enum dpu_ctl idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_ctl *c;
+	struct dpu_ctl_cfg *cfg;
+	int rc;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _ctl_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		pr_err("failed to create dpu_hw_ctl %d\n", idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	c->caps = cfg;
+	_setup_ctl_ops(&c->ops, c->caps->features);
+	c->idx = idx;
+	c->mixer_count = m->mixer_count;
+	c->mixer_hw_caps = m->mixer;
+
+	rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_CTL, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	return c;
+
+blk_init_error:
+	kzfree(c);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_ctl_destroy(struct dpu_hw_ctl *ctx)
+{
+	if (ctx)
+		dpu_hw_blk_destroy(&ctx->base);
+	kfree(ctx);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h
new file mode 100644
index 000000000000..c66a71f8b839
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h
@@ -0,0 +1,218 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_CTL_H
+#define _DPU_HW_CTL_H
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_sspp.h"
+#include "dpu_hw_blk.h"
+
+/**
+ * dpu_ctl_mode_sel: Interface mode selection
+ * DPU_CTL_MODE_SEL_VID:    Video mode interface
+ * DPU_CTL_MODE_SEL_CMD:    Command mode interface
+ */
+enum dpu_ctl_mode_sel {
+	DPU_CTL_MODE_SEL_VID = 0,
+	DPU_CTL_MODE_SEL_CMD
+};
+
+struct dpu_hw_ctl;
+/**
+ * struct dpu_hw_stage_cfg - blending stage cfg
+ * @stage : SSPP_ID at each stage
+ * @multirect_index: index of the rectangle of SSPP.
+ */
+struct dpu_hw_stage_cfg {
+	enum dpu_sspp stage[DPU_STAGE_MAX][PIPES_PER_STAGE];
+	enum dpu_sspp_multirect_index multirect_index
+					[DPU_STAGE_MAX][PIPES_PER_STAGE];
+};
+
+/**
+ * struct dpu_hw_intf_cfg :Describes how the DPU writes data to output interface
+ * @intf :                 Interface id
+ * @mode_3d:               3d mux configuration
+ * @intf_mode_sel:         Interface mode, cmd / vid
+ * @stream_sel:            Stream selection for multi-stream interfaces
+ */
+struct dpu_hw_intf_cfg {
+	enum dpu_intf intf;
+	enum dpu_3d_blend_mode mode_3d;
+	enum dpu_ctl_mode_sel intf_mode_sel;
+	int stream_sel;
+};
+
+/**
+ * struct dpu_hw_ctl_ops - Interface to the wb Hw driver functions
+ * Assumption is these functions will be called after clocks are enabled
+ */
+struct dpu_hw_ctl_ops {
+	/**
+	 * kickoff hw operation for Sw controlled interfaces
+	 * DSI cmd mode and WB interface are SW controlled
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*trigger_start)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * kickoff prepare is in progress hw operation for sw
+	 * controlled interfaces: DSI cmd mode and WB interface
+	 * are SW controlled
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*trigger_pending)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Clear the value of the cached pending_flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*clear_pending_flush)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Query the value of the cached pending_flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 */
+	u32 (*get_pending_flush)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * OR in the given flushbits to the cached pending_flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 * @flushbits : module flushmask
+	 */
+	void (*update_pending_flush)(struct dpu_hw_ctl *ctx,
+		u32 flushbits);
+
+	/**
+	 * Write the value of the pending_flush_mask to hardware
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*trigger_flush)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Read the value of the flush register
+	 * @ctx       : ctl path ctx pointer
+	 * @Return: value of the ctl flush register.
+	 */
+	u32 (*get_flush_register)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Setup ctl_path interface config
+	 * @ctx
+	 * @cfg    : interface config structure pointer
+	 */
+	void (*setup_intf_cfg)(struct dpu_hw_ctl *ctx,
+		struct dpu_hw_intf_cfg *cfg);
+
+	int (*reset)(struct dpu_hw_ctl *c);
+
+	/*
+	 * wait_reset_status - checks ctl reset status
+	 * @ctx       : ctl path ctx pointer
+	 *
+	 * This function checks the ctl reset status bit.
+	 * If the reset bit is set, it keeps polling the status till the hw
+	 * reset is complete.
+	 * Returns: 0 on success or -error if reset incomplete within interval
+	 */
+	int (*wait_reset_status)(struct dpu_hw_ctl *ctx);
+
+	uint32_t (*get_bitmask_sspp)(struct dpu_hw_ctl *ctx,
+		enum dpu_sspp blk);
+
+	uint32_t (*get_bitmask_mixer)(struct dpu_hw_ctl *ctx,
+		enum dpu_lm blk);
+
+	int (*get_bitmask_intf)(struct dpu_hw_ctl *ctx,
+		u32 *flushbits,
+		enum dpu_intf blk);
+
+	int (*get_bitmask_cdm)(struct dpu_hw_ctl *ctx,
+		u32 *flushbits,
+		enum dpu_cdm blk);
+
+	/**
+	 * Set all blend stages to disabled
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*clear_all_blendstages)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Configure layer mixer to pipe configuration
+	 * @ctx       : ctl path ctx pointer
+	 * @lm        : layer mixer enumeration
+	 * @cfg       : blend stage configuration
+	 */
+	void (*setup_blendstage)(struct dpu_hw_ctl *ctx,
+		enum dpu_lm lm, struct dpu_hw_stage_cfg *cfg);
+};
+
+/**
+ * struct dpu_hw_ctl : CTL PATH driver object
+ * @base: hardware block base structure
+ * @hw: block register map object
+ * @idx: control path index
+ * @caps: control path capabilities
+ * @mixer_count: number of mixers
+ * @mixer_hw_caps: mixer hardware capabilities
+ * @pending_flush_mask: storage for pending ctl_flush managed via ops
+ * @ops: operation list
+ */
+struct dpu_hw_ctl {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* ctl path */
+	int idx;
+	const struct dpu_ctl_cfg *caps;
+	int mixer_count;
+	const struct dpu_lm_cfg *mixer_hw_caps;
+	u32 pending_flush_mask;
+
+	/* ops */
+	struct dpu_hw_ctl_ops ops;
+};
+
+/**
+ * dpu_hw_ctl - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_ctl *to_dpu_hw_ctl(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_ctl, base);
+}
+
+/**
+ * dpu_hw_ctl_init(): Initializes the ctl_path hw driver object.
+ * should be called before accessing every ctl path registers.
+ * @idx:  ctl_path index for which driver object is required
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ */
+struct dpu_hw_ctl *dpu_hw_ctl_init(enum dpu_ctl idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_ctl_destroy(): Destroys ctl driver context
+ * should be called to free the context
+ */
+void dpu_hw_ctl_destroy(struct dpu_hw_ctl *ctx);
+
+#endif /*_DPU_HW_CTL_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
new file mode 100644
index 000000000000..c0b7f0049365
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
@@ -0,0 +1,1183 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/bitops.h>
+#include <linux/slab.h>
+
+#include "dpu_kms.h"
+#include "dpu_hw_interrupts.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_mdss.h"
+
+/**
+ * Register offsets in MDSS register file for the interrupt registers
+ * w.r.t. to the MDP base
+ */
+#define MDP_SSPP_TOP0_OFF		0x0
+#define MDP_INTF_0_OFF			0x6A000
+#define MDP_INTF_1_OFF			0x6A800
+#define MDP_INTF_2_OFF			0x6B000
+#define MDP_INTF_3_OFF			0x6B800
+#define MDP_INTF_4_OFF			0x6C000
+#define MDP_AD4_0_OFF			0x7C000
+#define MDP_AD4_1_OFF			0x7D000
+#define MDP_AD4_INTR_EN_OFF		0x41c
+#define MDP_AD4_INTR_CLEAR_OFF		0x424
+#define MDP_AD4_INTR_STATUS_OFF		0x420
+
+/**
+ * WB interrupt status bit definitions
+ */
+#define DPU_INTR_WB_0_DONE BIT(0)
+#define DPU_INTR_WB_1_DONE BIT(1)
+#define DPU_INTR_WB_2_DONE BIT(4)
+
+/**
+ * WDOG timer interrupt status bit definitions
+ */
+#define DPU_INTR_WD_TIMER_0_DONE BIT(2)
+#define DPU_INTR_WD_TIMER_1_DONE BIT(3)
+#define DPU_INTR_WD_TIMER_2_DONE BIT(5)
+#define DPU_INTR_WD_TIMER_3_DONE BIT(6)
+#define DPU_INTR_WD_TIMER_4_DONE BIT(7)
+
+/**
+ * Pingpong interrupt status bit definitions
+ */
+#define DPU_INTR_PING_PONG_0_DONE BIT(8)
+#define DPU_INTR_PING_PONG_1_DONE BIT(9)
+#define DPU_INTR_PING_PONG_2_DONE BIT(10)
+#define DPU_INTR_PING_PONG_3_DONE BIT(11)
+#define DPU_INTR_PING_PONG_0_RD_PTR BIT(12)
+#define DPU_INTR_PING_PONG_1_RD_PTR BIT(13)
+#define DPU_INTR_PING_PONG_2_RD_PTR BIT(14)
+#define DPU_INTR_PING_PONG_3_RD_PTR BIT(15)
+#define DPU_INTR_PING_PONG_0_WR_PTR BIT(16)
+#define DPU_INTR_PING_PONG_1_WR_PTR BIT(17)
+#define DPU_INTR_PING_PONG_2_WR_PTR BIT(18)
+#define DPU_INTR_PING_PONG_3_WR_PTR BIT(19)
+#define DPU_INTR_PING_PONG_0_AUTOREFRESH_DONE BIT(20)
+#define DPU_INTR_PING_PONG_1_AUTOREFRESH_DONE BIT(21)
+#define DPU_INTR_PING_PONG_2_AUTOREFRESH_DONE BIT(22)
+#define DPU_INTR_PING_PONG_3_AUTOREFRESH_DONE BIT(23)
+
+/**
+ * Interface interrupt status bit definitions
+ */
+#define DPU_INTR_INTF_0_UNDERRUN BIT(24)
+#define DPU_INTR_INTF_1_UNDERRUN BIT(26)
+#define DPU_INTR_INTF_2_UNDERRUN BIT(28)
+#define DPU_INTR_INTF_3_UNDERRUN BIT(30)
+#define DPU_INTR_INTF_0_VSYNC BIT(25)
+#define DPU_INTR_INTF_1_VSYNC BIT(27)
+#define DPU_INTR_INTF_2_VSYNC BIT(29)
+#define DPU_INTR_INTF_3_VSYNC BIT(31)
+
+/**
+ * Pingpong Secondary interrupt status bit definitions
+ */
+#define DPU_INTR_PING_PONG_S0_AUTOREFRESH_DONE BIT(0)
+#define DPU_INTR_PING_PONG_S0_WR_PTR BIT(4)
+#define DPU_INTR_PING_PONG_S0_RD_PTR BIT(8)
+#define DPU_INTR_PING_PONG_S0_TEAR_DETECTED BIT(22)
+#define DPU_INTR_PING_PONG_S0_TE_DETECTED BIT(28)
+
+/**
+ * Pingpong TEAR detection interrupt status bit definitions
+ */
+#define DPU_INTR_PING_PONG_0_TEAR_DETECTED BIT(16)
+#define DPU_INTR_PING_PONG_1_TEAR_DETECTED BIT(17)
+#define DPU_INTR_PING_PONG_2_TEAR_DETECTED BIT(18)
+#define DPU_INTR_PING_PONG_3_TEAR_DETECTED BIT(19)
+
+/**
+ * Pingpong TE detection interrupt status bit definitions
+ */
+#define DPU_INTR_PING_PONG_0_TE_DETECTED BIT(24)
+#define DPU_INTR_PING_PONG_1_TE_DETECTED BIT(25)
+#define DPU_INTR_PING_PONG_2_TE_DETECTED BIT(26)
+#define DPU_INTR_PING_PONG_3_TE_DETECTED BIT(27)
+
+/**
+ * Ctl start interrupt status bit definitions
+ */
+#define DPU_INTR_CTL_0_START BIT(9)
+#define DPU_INTR_CTL_1_START BIT(10)
+#define DPU_INTR_CTL_2_START BIT(11)
+#define DPU_INTR_CTL_3_START BIT(12)
+#define DPU_INTR_CTL_4_START BIT(13)
+
+/**
+ * Concurrent WB overflow interrupt status bit definitions
+ */
+#define DPU_INTR_CWB_2_OVERFLOW BIT(14)
+#define DPU_INTR_CWB_3_OVERFLOW BIT(15)
+
+/**
+ * Histogram VIG done interrupt status bit definitions
+ */
+#define DPU_INTR_HIST_VIG_0_DONE BIT(0)
+#define DPU_INTR_HIST_VIG_1_DONE BIT(4)
+#define DPU_INTR_HIST_VIG_2_DONE BIT(8)
+#define DPU_INTR_HIST_VIG_3_DONE BIT(10)
+
+/**
+ * Histogram VIG reset Sequence done interrupt status bit definitions
+ */
+#define DPU_INTR_HIST_VIG_0_RSTSEQ_DONE BIT(1)
+#define DPU_INTR_HIST_VIG_1_RSTSEQ_DONE BIT(5)
+#define DPU_INTR_HIST_VIG_2_RSTSEQ_DONE BIT(9)
+#define DPU_INTR_HIST_VIG_3_RSTSEQ_DONE BIT(11)
+
+/**
+ * Histogram DSPP done interrupt status bit definitions
+ */
+#define DPU_INTR_HIST_DSPP_0_DONE BIT(12)
+#define DPU_INTR_HIST_DSPP_1_DONE BIT(16)
+#define DPU_INTR_HIST_DSPP_2_DONE BIT(20)
+#define DPU_INTR_HIST_DSPP_3_DONE BIT(22)
+
+/**
+ * Histogram DSPP reset Sequence done interrupt status bit definitions
+ */
+#define DPU_INTR_HIST_DSPP_0_RSTSEQ_DONE BIT(13)
+#define DPU_INTR_HIST_DSPP_1_RSTSEQ_DONE BIT(17)
+#define DPU_INTR_HIST_DSPP_2_RSTSEQ_DONE BIT(21)
+#define DPU_INTR_HIST_DSPP_3_RSTSEQ_DONE BIT(23)
+
+/**
+ * INTF interrupt status bit definitions
+ */
+#define DPU_INTR_VIDEO_INTO_STATIC BIT(0)
+#define DPU_INTR_VIDEO_OUTOF_STATIC BIT(1)
+#define DPU_INTR_DSICMD_0_INTO_STATIC BIT(2)
+#define DPU_INTR_DSICMD_0_OUTOF_STATIC BIT(3)
+#define DPU_INTR_DSICMD_1_INTO_STATIC BIT(4)
+#define DPU_INTR_DSICMD_1_OUTOF_STATIC BIT(5)
+#define DPU_INTR_DSICMD_2_INTO_STATIC BIT(6)
+#define DPU_INTR_DSICMD_2_OUTOF_STATIC BIT(7)
+#define DPU_INTR_PROG_LINE BIT(8)
+
+/**
+ * AD4 interrupt status bit definitions
+ */
+#define DPU_INTR_BRIGHTPR_UPDATED BIT(4)
+#define DPU_INTR_DARKENH_UPDATED BIT(3)
+#define DPU_INTR_STREN_OUTROI_UPDATED BIT(2)
+#define DPU_INTR_STREN_INROI_UPDATED BIT(1)
+#define DPU_INTR_BACKLIGHT_UPDATED BIT(0)
+/**
+ * struct dpu_intr_reg - array of DPU register sets
+ * @clr_off:	offset to CLEAR reg
+ * @en_off:	offset to ENABLE reg
+ * @status_off:	offset to STATUS reg
+ */
+struct dpu_intr_reg {
+	u32 clr_off;
+	u32 en_off;
+	u32 status_off;
+};
+
+/**
+ * struct dpu_irq_type - maps each irq with i/f
+ * @intr_type:		type of interrupt listed in dpu_intr_type
+ * @instance_idx:	instance index of the associated HW block in DPU
+ * @irq_mask:		corresponding bit in the interrupt status reg
+ * @reg_idx:		which reg set to use
+ */
+struct dpu_irq_type {
+	u32 intr_type;
+	u32 instance_idx;
+	u32 irq_mask;
+	u32 reg_idx;
+};
+
+/**
+ * List of DPU interrupt registers
+ */
+static const struct dpu_intr_reg dpu_intr_set[] = {
+	{
+		MDP_SSPP_TOP0_OFF+INTR_CLEAR,
+		MDP_SSPP_TOP0_OFF+INTR_EN,
+		MDP_SSPP_TOP0_OFF+INTR_STATUS
+	},
+	{
+		MDP_SSPP_TOP0_OFF+INTR2_CLEAR,
+		MDP_SSPP_TOP0_OFF+INTR2_EN,
+		MDP_SSPP_TOP0_OFF+INTR2_STATUS
+	},
+	{
+		MDP_SSPP_TOP0_OFF+HIST_INTR_CLEAR,
+		MDP_SSPP_TOP0_OFF+HIST_INTR_EN,
+		MDP_SSPP_TOP0_OFF+HIST_INTR_STATUS
+	},
+	{
+		MDP_INTF_0_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_0_OFF+INTF_INTR_EN,
+		MDP_INTF_0_OFF+INTF_INTR_STATUS
+	},
+	{
+		MDP_INTF_1_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_1_OFF+INTF_INTR_EN,
+		MDP_INTF_1_OFF+INTF_INTR_STATUS
+	},
+	{
+		MDP_INTF_2_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_2_OFF+INTF_INTR_EN,
+		MDP_INTF_2_OFF+INTF_INTR_STATUS
+	},
+	{
+		MDP_INTF_3_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_3_OFF+INTF_INTR_EN,
+		MDP_INTF_3_OFF+INTF_INTR_STATUS
+	},
+	{
+		MDP_INTF_4_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_4_OFF+INTF_INTR_EN,
+		MDP_INTF_4_OFF+INTF_INTR_STATUS
+	},
+	{
+		MDP_AD4_0_OFF + MDP_AD4_INTR_CLEAR_OFF,
+		MDP_AD4_0_OFF + MDP_AD4_INTR_EN_OFF,
+		MDP_AD4_0_OFF + MDP_AD4_INTR_STATUS_OFF,
+	},
+	{
+		MDP_AD4_1_OFF + MDP_AD4_INTR_CLEAR_OFF,
+		MDP_AD4_1_OFF + MDP_AD4_INTR_EN_OFF,
+		MDP_AD4_1_OFF + MDP_AD4_INTR_STATUS_OFF,
+	}
+};
+
+/**
+ * IRQ mapping table - use for lookup an irq_idx in this table that have
+ *                     a matching interface type and instance index.
+ */
+static const struct dpu_irq_type dpu_irq_map[] = {
+	/* BEGIN MAP_RANGE: 0-31, INTR */
+	/* irq_idx: 0-3 */
+	{ DPU_IRQ_TYPE_WB_ROT_COMP, WB_0, DPU_INTR_WB_0_DONE, 0},
+	{ DPU_IRQ_TYPE_WB_ROT_COMP, WB_1, DPU_INTR_WB_1_DONE, 0},
+	{ DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_0, DPU_INTR_WD_TIMER_0_DONE, 0},
+	{ DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_1, DPU_INTR_WD_TIMER_1_DONE, 0},
+	/* irq_idx: 4-7 */
+	{ DPU_IRQ_TYPE_WB_WFD_COMP, WB_2, DPU_INTR_WB_2_DONE, 0},
+	{ DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_2, DPU_INTR_WD_TIMER_2_DONE, 0},
+	{ DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_3, DPU_INTR_WD_TIMER_3_DONE, 0},
+	{ DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_4, DPU_INTR_WD_TIMER_4_DONE, 0},
+	/* irq_idx: 8-11 */
+	{ DPU_IRQ_TYPE_PING_PONG_COMP, PINGPONG_0,
+		DPU_INTR_PING_PONG_0_DONE, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_COMP, PINGPONG_1,
+		DPU_INTR_PING_PONG_1_DONE, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_COMP, PINGPONG_2,
+		DPU_INTR_PING_PONG_2_DONE, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_COMP, PINGPONG_3,
+		DPU_INTR_PING_PONG_3_DONE, 0},
+	/* irq_idx: 12-15 */
+	{ DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_0,
+		DPU_INTR_PING_PONG_0_RD_PTR, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_1,
+		DPU_INTR_PING_PONG_1_RD_PTR, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_2,
+		DPU_INTR_PING_PONG_2_RD_PTR, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_3,
+		DPU_INTR_PING_PONG_3_RD_PTR, 0},
+	/* irq_idx: 16-19 */
+	{ DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_0,
+		DPU_INTR_PING_PONG_0_WR_PTR, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_1,
+		DPU_INTR_PING_PONG_1_WR_PTR, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_2,
+		DPU_INTR_PING_PONG_2_WR_PTR, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_3,
+		DPU_INTR_PING_PONG_3_WR_PTR, 0},
+	/* irq_idx: 20-23 */
+	{ DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_0,
+		DPU_INTR_PING_PONG_0_AUTOREFRESH_DONE, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_1,
+		DPU_INTR_PING_PONG_1_AUTOREFRESH_DONE, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_2,
+		DPU_INTR_PING_PONG_2_AUTOREFRESH_DONE, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_3,
+		DPU_INTR_PING_PONG_3_AUTOREFRESH_DONE, 0},
+	/* irq_idx: 24-27 */
+	{ DPU_IRQ_TYPE_INTF_UNDER_RUN, INTF_0, DPU_INTR_INTF_0_UNDERRUN, 0},
+	{ DPU_IRQ_TYPE_INTF_VSYNC, INTF_0, DPU_INTR_INTF_0_VSYNC, 0},
+	{ DPU_IRQ_TYPE_INTF_UNDER_RUN, INTF_1, DPU_INTR_INTF_1_UNDERRUN, 0},
+	{ DPU_IRQ_TYPE_INTF_VSYNC, INTF_1, DPU_INTR_INTF_1_VSYNC, 0},
+	/* irq_idx: 28-31 */
+	{ DPU_IRQ_TYPE_INTF_UNDER_RUN, INTF_2, DPU_INTR_INTF_2_UNDERRUN, 0},
+	{ DPU_IRQ_TYPE_INTF_VSYNC, INTF_2, DPU_INTR_INTF_2_VSYNC, 0},
+	{ DPU_IRQ_TYPE_INTF_UNDER_RUN, INTF_3, DPU_INTR_INTF_3_UNDERRUN, 0},
+	{ DPU_IRQ_TYPE_INTF_VSYNC, INTF_3, DPU_INTR_INTF_3_VSYNC, 0},
+
+	/* BEGIN MAP_RANGE: 32-64, INTR2 */
+	/* irq_idx: 32-35 */
+	{ DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_S0,
+		DPU_INTR_PING_PONG_S0_AUTOREFRESH_DONE, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	/* irq_idx: 36-39 */
+	{ DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_S0,
+		DPU_INTR_PING_PONG_S0_WR_PTR, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	/* irq_idx: 40 */
+	{ DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_S0,
+		DPU_INTR_PING_PONG_S0_RD_PTR, 1},
+	/* irq_idx: 41-45 */
+	{ DPU_IRQ_TYPE_CTL_START, CTL_0,
+		DPU_INTR_CTL_0_START, 1},
+	{ DPU_IRQ_TYPE_CTL_START, CTL_1,
+		DPU_INTR_CTL_1_START, 1},
+	{ DPU_IRQ_TYPE_CTL_START, CTL_2,
+		DPU_INTR_CTL_2_START, 1},
+	{ DPU_IRQ_TYPE_CTL_START, CTL_3,
+		DPU_INTR_CTL_3_START, 1},
+	{ DPU_IRQ_TYPE_CTL_START, CTL_4,
+		DPU_INTR_CTL_4_START, 1},
+	/* irq_idx: 46-47 */
+	{ DPU_IRQ_TYPE_CWB_OVERFLOW, CWB_2, DPU_INTR_CWB_2_OVERFLOW, 1},
+	{ DPU_IRQ_TYPE_CWB_OVERFLOW, CWB_3, DPU_INTR_CWB_3_OVERFLOW, 1},
+	/* irq_idx: 48-51 */
+	{ DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_0,
+		DPU_INTR_PING_PONG_0_TEAR_DETECTED, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_1,
+		DPU_INTR_PING_PONG_1_TEAR_DETECTED, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_2,
+		DPU_INTR_PING_PONG_2_TEAR_DETECTED, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_3,
+		DPU_INTR_PING_PONG_3_TEAR_DETECTED, 1},
+	/* irq_idx: 52-55 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_S0,
+		DPU_INTR_PING_PONG_S0_TEAR_DETECTED, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	/* irq_idx: 56-59 */
+	{ DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_0,
+		DPU_INTR_PING_PONG_0_TE_DETECTED, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_1,
+		DPU_INTR_PING_PONG_1_TE_DETECTED, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_2,
+		DPU_INTR_PING_PONG_2_TE_DETECTED, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_3,
+		DPU_INTR_PING_PONG_3_TE_DETECTED, 1},
+	/* irq_idx: 60-63 */
+	{ DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_S0,
+		DPU_INTR_PING_PONG_S0_TE_DETECTED, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+
+	/* BEGIN MAP_RANGE: 64-95 HIST */
+	/* irq_idx: 64-67 */
+	{ DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG0, DPU_INTR_HIST_VIG_0_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG0,
+		DPU_INTR_HIST_VIG_0_RSTSEQ_DONE, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	/* irq_idx: 68-71 */
+	{ DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG1, DPU_INTR_HIST_VIG_1_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG1,
+		DPU_INTR_HIST_VIG_1_RSTSEQ_DONE, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	/* irq_idx: 72-75 */
+	{ DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG2, DPU_INTR_HIST_VIG_2_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG2,
+		DPU_INTR_HIST_VIG_2_RSTSEQ_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG3, DPU_INTR_HIST_VIG_3_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG3,
+		DPU_INTR_HIST_VIG_3_RSTSEQ_DONE, 2},
+	/* irq_idx: 76-79 */
+	{ DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_0, DPU_INTR_HIST_DSPP_0_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_0,
+		DPU_INTR_HIST_DSPP_0_RSTSEQ_DONE, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	/* irq_idx: 80-83 */
+	{ DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_1, DPU_INTR_HIST_DSPP_1_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_1,
+		DPU_INTR_HIST_DSPP_1_RSTSEQ_DONE, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	/* irq_idx: 84-87 */
+	{ DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_2, DPU_INTR_HIST_DSPP_2_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_2,
+		DPU_INTR_HIST_DSPP_2_RSTSEQ_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_3, DPU_INTR_HIST_DSPP_3_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_3,
+		DPU_INTR_HIST_DSPP_3_RSTSEQ_DONE, 2},
+	/* irq_idx: 88-91 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	/* irq_idx: 92-95 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+
+	/* BEGIN MAP_RANGE: 96-127 INTF_0_INTR */
+	/* irq_idx: 96-99 */
+	{ DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_0,
+		DPU_INTR_VIDEO_INTO_STATIC, 3},
+	{ DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_0,
+		DPU_INTR_VIDEO_OUTOF_STATIC, 3},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_0,
+		DPU_INTR_DSICMD_0_INTO_STATIC, 3},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_0,
+		DPU_INTR_DSICMD_0_OUTOF_STATIC, 3},
+	/* irq_idx: 100-103 */
+	{ DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_0,
+		DPU_INTR_DSICMD_1_INTO_STATIC, 3},
+	{ DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_0,
+		DPU_INTR_DSICMD_1_OUTOF_STATIC, 3},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_0,
+		DPU_INTR_DSICMD_2_INTO_STATIC, 3},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_0,
+		DPU_INTR_DSICMD_2_OUTOF_STATIC, 3},
+	/* irq_idx: 104-107 */
+	{ DPU_IRQ_TYPE_PROG_LINE, INTF_0, DPU_INTR_PROG_LINE, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	/* irq_idx: 108-111 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	/* irq_idx: 112-115 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	/* irq_idx: 116-119 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	/* irq_idx: 120-123 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	/* irq_idx: 124-127 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+
+	/* BEGIN MAP_RANGE: 128-159 INTF_1_INTR */
+	/* irq_idx: 128-131 */
+	{ DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_1,
+		DPU_INTR_VIDEO_INTO_STATIC, 4},
+	{ DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_1,
+		DPU_INTR_VIDEO_OUTOF_STATIC, 4},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_1,
+		DPU_INTR_DSICMD_0_INTO_STATIC, 4},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_1,
+		DPU_INTR_DSICMD_0_OUTOF_STATIC, 4},
+	/* irq_idx: 132-135 */
+	{ DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_1,
+		DPU_INTR_DSICMD_1_INTO_STATIC, 4},
+	{ DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_1,
+		DPU_INTR_DSICMD_1_OUTOF_STATIC, 4},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_1,
+		DPU_INTR_DSICMD_2_INTO_STATIC, 4},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_1,
+		DPU_INTR_DSICMD_2_OUTOF_STATIC, 4},
+	/* irq_idx: 136-139 */
+	{ DPU_IRQ_TYPE_PROG_LINE, INTF_1, DPU_INTR_PROG_LINE, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	/* irq_idx: 140-143 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	/* irq_idx: 144-147 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	/* irq_idx: 148-151 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	/* irq_idx: 152-155 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	/* irq_idx: 156-159 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+
+	/* BEGIN MAP_RANGE: 160-191 INTF_2_INTR */
+	/* irq_idx: 160-163 */
+	{ DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_2,
+		DPU_INTR_VIDEO_INTO_STATIC, 5},
+	{ DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_2,
+		DPU_INTR_VIDEO_OUTOF_STATIC, 5},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_2,
+		DPU_INTR_DSICMD_0_INTO_STATIC, 5},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_2,
+		DPU_INTR_DSICMD_0_OUTOF_STATIC, 5},
+	/* irq_idx: 164-167 */
+	{ DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_2,
+		DPU_INTR_DSICMD_1_INTO_STATIC, 5},
+	{ DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_2,
+		DPU_INTR_DSICMD_1_OUTOF_STATIC, 5},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_2,
+		DPU_INTR_DSICMD_2_INTO_STATIC, 5},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_2,
+		DPU_INTR_DSICMD_2_OUTOF_STATIC, 5},
+	/* irq_idx: 168-171 */
+	{ DPU_IRQ_TYPE_PROG_LINE, INTF_2, DPU_INTR_PROG_LINE, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	/* irq_idx: 172-175 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	/* irq_idx: 176-179 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	/* irq_idx: 180-183 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	/* irq_idx: 184-187 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	/* irq_idx: 188-191 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+
+	/* BEGIN MAP_RANGE: 192-223 INTF_3_INTR */
+	/* irq_idx: 192-195 */
+	{ DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_3,
+		DPU_INTR_VIDEO_INTO_STATIC, 6},
+	{ DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_3,
+		DPU_INTR_VIDEO_OUTOF_STATIC, 6},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_3,
+		DPU_INTR_DSICMD_0_INTO_STATIC, 6},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_3,
+		DPU_INTR_DSICMD_0_OUTOF_STATIC, 6},
+	/* irq_idx: 196-199 */
+	{ DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_3,
+		DPU_INTR_DSICMD_1_INTO_STATIC, 6},
+	{ DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_3,
+		DPU_INTR_DSICMD_1_OUTOF_STATIC, 6},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_3,
+		DPU_INTR_DSICMD_2_INTO_STATIC, 6},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_3,
+		DPU_INTR_DSICMD_2_OUTOF_STATIC, 6},
+	/* irq_idx: 200-203 */
+	{ DPU_IRQ_TYPE_PROG_LINE, INTF_3, DPU_INTR_PROG_LINE, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	/* irq_idx: 204-207 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	/* irq_idx: 208-211 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	/* irq_idx: 212-215 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	/* irq_idx: 216-219 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	/* irq_idx: 220-223 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+
+	/* BEGIN MAP_RANGE: 224-255 INTF_4_INTR */
+	/* irq_idx: 224-227 */
+	{ DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_4,
+		DPU_INTR_VIDEO_INTO_STATIC, 7},
+	{ DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_4,
+		DPU_INTR_VIDEO_OUTOF_STATIC, 7},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_4,
+		DPU_INTR_DSICMD_0_INTO_STATIC, 7},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_4,
+		DPU_INTR_DSICMD_0_OUTOF_STATIC, 7},
+	/* irq_idx: 228-231 */
+	{ DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_4,
+		DPU_INTR_DSICMD_1_INTO_STATIC, 7},
+	{ DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_4,
+		DPU_INTR_DSICMD_1_OUTOF_STATIC, 7},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_4,
+		DPU_INTR_DSICMD_2_INTO_STATIC, 7},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_4,
+		DPU_INTR_DSICMD_2_OUTOF_STATIC, 7},
+	/* irq_idx: 232-235 */
+	{ DPU_IRQ_TYPE_PROG_LINE, INTF_4, DPU_INTR_PROG_LINE, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	/* irq_idx: 236-239 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	/* irq_idx: 240-243 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	/* irq_idx: 244-247 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	/* irq_idx: 248-251 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	/* irq_idx: 252-255 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+
+	/* BEGIN MAP_RANGE: 256-287 AD4_0_INTR */
+	/* irq_idx: 256-259 */
+	{ DPU_IRQ_TYPE_AD4_BL_DONE, DSPP_0, DPU_INTR_BACKLIGHT_UPDATED, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 260-263 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 264-267 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 268-271 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 272-275 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 276-279 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 280-283 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 284-287 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+
+	/* BEGIN MAP_RANGE: 288-319 AD4_1_INTR */
+	/* irq_idx: 288-291 */
+	{ DPU_IRQ_TYPE_AD4_BL_DONE, DSPP_1, DPU_INTR_BACKLIGHT_UPDATED, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 292-295 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 296-299 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 300-303 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 304-307 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 308-311 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 312-315 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 315-319 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+};
+
+static int dpu_hw_intr_irqidx_lookup(enum dpu_intr_type intr_type,
+		u32 instance_idx)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dpu_irq_map); i++) {
+		if (intr_type == dpu_irq_map[i].intr_type &&
+			instance_idx == dpu_irq_map[i].instance_idx)
+			return i;
+	}
+
+	pr_debug("IRQ lookup fail!! intr_type=%d, instance_idx=%d\n",
+			intr_type, instance_idx);
+	return -EINVAL;
+}
+
+static void dpu_hw_intr_set_mask(struct dpu_hw_intr *intr, uint32_t reg_off,
+		uint32_t mask)
+{
+	if (!intr)
+		return;
+
+	DPU_REG_WRITE(&intr->hw, reg_off, mask);
+
+	/* ensure register writes go through */
+	wmb();
+}
+
+static void dpu_hw_intr_dispatch_irq(struct dpu_hw_intr *intr,
+		void (*cbfunc)(void *, int),
+		void *arg)
+{
+	int reg_idx;
+	int irq_idx;
+	int start_idx;
+	int end_idx;
+	u32 irq_status;
+	unsigned long irq_flags;
+
+	if (!intr)
+		return;
+
+	/*
+	 * The dispatcher will save the IRQ status before calling here.
+	 * Now need to go through each IRQ status and find matching
+	 * irq lookup index.
+	 */
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+	for (reg_idx = 0; reg_idx < ARRAY_SIZE(dpu_intr_set); reg_idx++) {
+		irq_status = intr->save_irq_status[reg_idx];
+
+		/*
+		 * Each Interrupt register has a range of 32 indexes, and
+		 * that is static for dpu_irq_map.
+		 */
+		start_idx = reg_idx * 32;
+		end_idx = start_idx + 32;
+
+		if (start_idx >= ARRAY_SIZE(dpu_irq_map) ||
+				end_idx > ARRAY_SIZE(dpu_irq_map))
+			continue;
+
+		/*
+		 * Search through matching intr status from irq map.
+		 * start_idx and end_idx defined the search range in
+		 * the dpu_irq_map.
+		 */
+		for (irq_idx = start_idx;
+				(irq_idx < end_idx) && irq_status;
+				irq_idx++)
+			if ((irq_status & dpu_irq_map[irq_idx].irq_mask) &&
+				(dpu_irq_map[irq_idx].reg_idx == reg_idx)) {
+				/*
+				 * Once a match on irq mask, perform a callback
+				 * to the given cbfunc. cbfunc will take care
+				 * the interrupt status clearing. If cbfunc is
+				 * not provided, then the interrupt clearing
+				 * is here.
+				 */
+				if (cbfunc)
+					cbfunc(arg, irq_idx);
+				else
+					intr->ops.clear_intr_status_nolock(
+							intr, irq_idx);
+
+				/*
+				 * When callback finish, clear the irq_status
+				 * with the matching mask. Once irq_status
+				 * is all cleared, the search can be stopped.
+				 */
+				irq_status &= ~dpu_irq_map[irq_idx].irq_mask;
+			}
+	}
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+}
+
+static int dpu_hw_intr_enable_irq(struct dpu_hw_intr *intr, int irq_idx)
+{
+	int reg_idx;
+	unsigned long irq_flags;
+	const struct dpu_intr_reg *reg;
+	const struct dpu_irq_type *irq;
+	const char *dbgstr = NULL;
+	uint32_t cache_irq_mask;
+
+	if (!intr)
+		return -EINVAL;
+
+	if (irq_idx < 0 || irq_idx >= ARRAY_SIZE(dpu_irq_map)) {
+		pr_err("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	irq = &dpu_irq_map[irq_idx];
+	reg_idx = irq->reg_idx;
+	reg = &dpu_intr_set[reg_idx];
+
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+	cache_irq_mask = intr->cache_irq_mask[reg_idx];
+	if (cache_irq_mask & irq->irq_mask) {
+		dbgstr = "DPU IRQ already set:";
+	} else {
+		dbgstr = "DPU IRQ enabled:";
+
+		cache_irq_mask |= irq->irq_mask;
+		/* Cleaning any pending interrupt */
+		DPU_REG_WRITE(&intr->hw, reg->clr_off, irq->irq_mask);
+		/* Enabling interrupts with the new mask */
+		DPU_REG_WRITE(&intr->hw, reg->en_off, cache_irq_mask);
+
+		/* ensure register write goes through */
+		wmb();
+
+		intr->cache_irq_mask[reg_idx] = cache_irq_mask;
+	}
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+
+	pr_debug("%s MASK:0x%.8x, CACHE-MASK:0x%.8x\n", dbgstr,
+			irq->irq_mask, cache_irq_mask);
+
+	return 0;
+}
+
+static int dpu_hw_intr_disable_irq_nolock(struct dpu_hw_intr *intr, int irq_idx)
+{
+	int reg_idx;
+	const struct dpu_intr_reg *reg;
+	const struct dpu_irq_type *irq;
+	const char *dbgstr = NULL;
+	uint32_t cache_irq_mask;
+
+	if (!intr)
+		return -EINVAL;
+
+	if (irq_idx < 0 || irq_idx >= ARRAY_SIZE(dpu_irq_map)) {
+		pr_err("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	irq = &dpu_irq_map[irq_idx];
+	reg_idx = irq->reg_idx;
+	reg = &dpu_intr_set[reg_idx];
+
+	cache_irq_mask = intr->cache_irq_mask[reg_idx];
+	if ((cache_irq_mask & irq->irq_mask) == 0) {
+		dbgstr = "DPU IRQ is already cleared:";
+	} else {
+		dbgstr = "DPU IRQ mask disable:";
+
+		cache_irq_mask &= ~irq->irq_mask;
+		/* Disable interrupts based on the new mask */
+		DPU_REG_WRITE(&intr->hw, reg->en_off, cache_irq_mask);
+		/* Cleaning any pending interrupt */
+		DPU_REG_WRITE(&intr->hw, reg->clr_off, irq->irq_mask);
+
+		/* ensure register write goes through */
+		wmb();
+
+		intr->cache_irq_mask[reg_idx] = cache_irq_mask;
+	}
+
+	pr_debug("%s MASK:0x%.8x, CACHE-MASK:0x%.8x\n", dbgstr,
+			irq->irq_mask, cache_irq_mask);
+
+	return 0;
+}
+
+static int dpu_hw_intr_disable_irq(struct dpu_hw_intr *intr, int irq_idx)
+{
+	unsigned long irq_flags;
+
+	if (!intr)
+		return -EINVAL;
+
+	if (irq_idx < 0 || irq_idx >= ARRAY_SIZE(dpu_irq_map)) {
+		pr_err("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+	dpu_hw_intr_disable_irq_nolock(intr, irq_idx);
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+
+	return 0;
+}
+
+static int dpu_hw_intr_clear_irqs(struct dpu_hw_intr *intr)
+{
+	int i;
+
+	if (!intr)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++)
+		DPU_REG_WRITE(&intr->hw, dpu_intr_set[i].clr_off, 0xffffffff);
+
+	/* ensure register writes go through */
+	wmb();
+
+	return 0;
+}
+
+static int dpu_hw_intr_disable_irqs(struct dpu_hw_intr *intr)
+{
+	int i;
+
+	if (!intr)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++)
+		DPU_REG_WRITE(&intr->hw, dpu_intr_set[i].en_off, 0x00000000);
+
+	/* ensure register writes go through */
+	wmb();
+
+	return 0;
+}
+
+static int dpu_hw_intr_get_valid_interrupts(struct dpu_hw_intr *intr,
+		uint32_t *mask)
+{
+	if (!intr || !mask)
+		return -EINVAL;
+
+	*mask = IRQ_SOURCE_MDP | IRQ_SOURCE_DSI0 | IRQ_SOURCE_DSI1
+		| IRQ_SOURCE_HDMI | IRQ_SOURCE_EDP;
+
+	return 0;
+}
+
+static void dpu_hw_intr_get_interrupt_statuses(struct dpu_hw_intr *intr)
+{
+	int i;
+	u32 enable_mask;
+	unsigned long irq_flags;
+
+	if (!intr)
+		return;
+
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+	for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++) {
+		/* Read interrupt status */
+		intr->save_irq_status[i] = DPU_REG_READ(&intr->hw,
+				dpu_intr_set[i].status_off);
+
+		/* Read enable mask */
+		enable_mask = DPU_REG_READ(&intr->hw, dpu_intr_set[i].en_off);
+
+		/* and clear the interrupt */
+		if (intr->save_irq_status[i])
+			DPU_REG_WRITE(&intr->hw, dpu_intr_set[i].clr_off,
+					intr->save_irq_status[i]);
+
+		/* Finally update IRQ status based on enable mask */
+		intr->save_irq_status[i] &= enable_mask;
+	}
+
+	/* ensure register writes go through */
+	wmb();
+
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+}
+
+static void dpu_hw_intr_clear_intr_status_nolock(struct dpu_hw_intr *intr,
+		int irq_idx)
+{
+	int reg_idx;
+
+	if (!intr)
+		return;
+
+	reg_idx = dpu_irq_map[irq_idx].reg_idx;
+	DPU_REG_WRITE(&intr->hw, dpu_intr_set[reg_idx].clr_off,
+			dpu_irq_map[irq_idx].irq_mask);
+
+	/* ensure register writes go through */
+	wmb();
+}
+
+static void dpu_hw_intr_clear_interrupt_status(struct dpu_hw_intr *intr,
+		int irq_idx)
+{
+	unsigned long irq_flags;
+
+	if (!intr)
+		return;
+
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+	dpu_hw_intr_clear_intr_status_nolock(intr, irq_idx);
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+}
+
+static u32 dpu_hw_intr_get_interrupt_status(struct dpu_hw_intr *intr,
+		int irq_idx, bool clear)
+{
+	int reg_idx;
+	unsigned long irq_flags;
+	u32 intr_status;
+
+	if (!intr)
+		return 0;
+
+	if (irq_idx >= ARRAY_SIZE(dpu_irq_map) || irq_idx < 0) {
+		pr_err("invalid IRQ index: [%d]\n", irq_idx);
+		return 0;
+	}
+
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+
+	reg_idx = dpu_irq_map[irq_idx].reg_idx;
+	intr_status = DPU_REG_READ(&intr->hw,
+			dpu_intr_set[reg_idx].status_off) &
+					dpu_irq_map[irq_idx].irq_mask;
+	if (intr_status && clear)
+		DPU_REG_WRITE(&intr->hw, dpu_intr_set[reg_idx].clr_off,
+				intr_status);
+
+	/* ensure register writes go through */
+	wmb();
+
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+
+	return intr_status;
+}
+
+static void __setup_intr_ops(struct dpu_hw_intr_ops *ops)
+{
+	ops->set_mask = dpu_hw_intr_set_mask;
+	ops->irq_idx_lookup = dpu_hw_intr_irqidx_lookup;
+	ops->enable_irq = dpu_hw_intr_enable_irq;
+	ops->disable_irq = dpu_hw_intr_disable_irq;
+	ops->dispatch_irqs = dpu_hw_intr_dispatch_irq;
+	ops->clear_all_irqs = dpu_hw_intr_clear_irqs;
+	ops->disable_all_irqs = dpu_hw_intr_disable_irqs;
+	ops->get_valid_interrupts = dpu_hw_intr_get_valid_interrupts;
+	ops->get_interrupt_statuses = dpu_hw_intr_get_interrupt_statuses;
+	ops->clear_interrupt_status = dpu_hw_intr_clear_interrupt_status;
+	ops->clear_intr_status_nolock = dpu_hw_intr_clear_intr_status_nolock;
+	ops->get_interrupt_status = dpu_hw_intr_get_interrupt_status;
+}
+
+static void __intr_offset(struct dpu_mdss_cfg *m,
+		void __iomem *addr, struct dpu_hw_blk_reg_map *hw)
+{
+	hw->base_off = addr;
+	hw->blk_off = m->mdp[0].base;
+	hw->hwversion = m->hwversion;
+}
+
+struct dpu_hw_intr *dpu_hw_intr_init(void __iomem *addr,
+		struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_intr *intr;
+
+	if (!addr || !m)
+		return ERR_PTR(-EINVAL);
+
+	intr = kzalloc(sizeof(*intr), GFP_KERNEL);
+	if (!intr)
+		return ERR_PTR(-ENOMEM);
+
+	__intr_offset(m, addr, &intr->hw);
+	__setup_intr_ops(&intr->ops);
+
+	intr->irq_idx_tbl_size = ARRAY_SIZE(dpu_irq_map);
+
+	intr->cache_irq_mask = kcalloc(ARRAY_SIZE(dpu_intr_set), sizeof(u32),
+			GFP_KERNEL);
+	if (intr->cache_irq_mask == NULL) {
+		kfree(intr);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	intr->save_irq_status = kcalloc(ARRAY_SIZE(dpu_intr_set), sizeof(u32),
+			GFP_KERNEL);
+	if (intr->save_irq_status == NULL) {
+		kfree(intr->cache_irq_mask);
+		kfree(intr);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	spin_lock_init(&intr->irq_lock);
+
+	return intr;
+}
+
+void dpu_hw_intr_destroy(struct dpu_hw_intr *intr)
+{
+	if (intr) {
+		kfree(intr->cache_irq_mask);
+		kfree(intr->save_irq_status);
+		kfree(intr);
+	}
+}
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h
new file mode 100644
index 000000000000..61e4cba36562
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h
@@ -0,0 +1,257 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_INTERRUPTS_H
+#define _DPU_HW_INTERRUPTS_H
+
+#include <linux/types.h>
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_mdss.h"
+
+#define IRQ_SOURCE_MDP		BIT(0)
+#define IRQ_SOURCE_DSI0		BIT(4)
+#define IRQ_SOURCE_DSI1		BIT(5)
+#define IRQ_SOURCE_HDMI		BIT(8)
+#define IRQ_SOURCE_EDP		BIT(12)
+#define IRQ_SOURCE_MHL		BIT(16)
+
+/**
+ * dpu_intr_type - HW Interrupt Type
+ * @DPU_IRQ_TYPE_WB_ROT_COMP:		WB rotator done
+ * @DPU_IRQ_TYPE_WB_WFD_COMP:		WB WFD done
+ * @DPU_IRQ_TYPE_PING_PONG_COMP:	PingPong done
+ * @DPU_IRQ_TYPE_PING_PONG_RD_PTR:	PingPong read pointer
+ * @DPU_IRQ_TYPE_PING_PONG_WR_PTR:	PingPong write pointer
+ * @DPU_IRQ_TYPE_PING_PONG_AUTO_REF:	PingPong auto refresh
+ * @DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK:	PingPong Tear check
+ * @DPU_IRQ_TYPE_PING_PONG_TE_CHECK:	PingPong TE detection
+ * @DPU_IRQ_TYPE_INTF_UNDER_RUN:	INTF underrun
+ * @DPU_IRQ_TYPE_INTF_VSYNC:		INTF VSYNC
+ * @DPU_IRQ_TYPE_CWB_OVERFLOW:		Concurrent WB overflow
+ * @DPU_IRQ_TYPE_HIST_VIG_DONE:		VIG Histogram done
+ * @DPU_IRQ_TYPE_HIST_VIG_RSTSEQ:	VIG Histogram reset
+ * @DPU_IRQ_TYPE_HIST_DSPP_DONE:	DSPP Histogram done
+ * @DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ:	DSPP Histogram reset
+ * @DPU_IRQ_TYPE_WD_TIMER:		Watchdog timer
+ * @DPU_IRQ_TYPE_SFI_VIDEO_IN:		Video static frame INTR into static
+ * @DPU_IRQ_TYPE_SFI_VIDEO_OUT:		Video static frame INTR out-of static
+ * @DPU_IRQ_TYPE_SFI_CMD_0_IN:		DSI CMD0 static frame INTR into static
+ * @DPU_IRQ_TYPE_SFI_CMD_0_OUT:		DSI CMD0 static frame INTR out-of static
+ * @DPU_IRQ_TYPE_SFI_CMD_1_IN:		DSI CMD1 static frame INTR into static
+ * @DPU_IRQ_TYPE_SFI_CMD_1_OUT:		DSI CMD1 static frame INTR out-of static
+ * @DPU_IRQ_TYPE_SFI_CMD_2_IN:		DSI CMD2 static frame INTR into static
+ * @DPU_IRQ_TYPE_SFI_CMD_2_OUT:		DSI CMD2 static frame INTR out-of static
+ * @DPU_IRQ_TYPE_PROG_LINE:		Programmable Line interrupt
+ * @DPU_IRQ_TYPE_AD4_BL_DONE:		AD4 backlight
+ * @DPU_IRQ_TYPE_CTL_START:		Control start
+ * @DPU_IRQ_TYPE_RESERVED:		Reserved for expansion
+ */
+enum dpu_intr_type {
+	DPU_IRQ_TYPE_WB_ROT_COMP,
+	DPU_IRQ_TYPE_WB_WFD_COMP,
+	DPU_IRQ_TYPE_PING_PONG_COMP,
+	DPU_IRQ_TYPE_PING_PONG_RD_PTR,
+	DPU_IRQ_TYPE_PING_PONG_WR_PTR,
+	DPU_IRQ_TYPE_PING_PONG_AUTO_REF,
+	DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK,
+	DPU_IRQ_TYPE_PING_PONG_TE_CHECK,
+	DPU_IRQ_TYPE_INTF_UNDER_RUN,
+	DPU_IRQ_TYPE_INTF_VSYNC,
+	DPU_IRQ_TYPE_CWB_OVERFLOW,
+	DPU_IRQ_TYPE_HIST_VIG_DONE,
+	DPU_IRQ_TYPE_HIST_VIG_RSTSEQ,
+	DPU_IRQ_TYPE_HIST_DSPP_DONE,
+	DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ,
+	DPU_IRQ_TYPE_WD_TIMER,
+	DPU_IRQ_TYPE_SFI_VIDEO_IN,
+	DPU_IRQ_TYPE_SFI_VIDEO_OUT,
+	DPU_IRQ_TYPE_SFI_CMD_0_IN,
+	DPU_IRQ_TYPE_SFI_CMD_0_OUT,
+	DPU_IRQ_TYPE_SFI_CMD_1_IN,
+	DPU_IRQ_TYPE_SFI_CMD_1_OUT,
+	DPU_IRQ_TYPE_SFI_CMD_2_IN,
+	DPU_IRQ_TYPE_SFI_CMD_2_OUT,
+	DPU_IRQ_TYPE_PROG_LINE,
+	DPU_IRQ_TYPE_AD4_BL_DONE,
+	DPU_IRQ_TYPE_CTL_START,
+	DPU_IRQ_TYPE_RESERVED,
+};
+
+struct dpu_hw_intr;
+
+/**
+ * Interrupt operations.
+ */
+struct dpu_hw_intr_ops {
+	/**
+	 * set_mask - Programs the given interrupt register with the
+	 *            given interrupt mask. Register value will get overwritten.
+	 * @intr:	HW interrupt handle
+	 * @reg_off:	MDSS HW register offset
+	 * @irqmask:	IRQ mask value
+	 */
+	void (*set_mask)(
+			struct dpu_hw_intr *intr,
+			uint32_t reg,
+			uint32_t irqmask);
+
+	/**
+	 * irq_idx_lookup - Lookup IRQ index on the HW interrupt type
+	 *                 Used for all irq related ops
+	 * @intr_type:		Interrupt type defined in dpu_intr_type
+	 * @instance_idx:	HW interrupt block instance
+	 * @return:		irq_idx or -EINVAL for lookup fail
+	 */
+	int (*irq_idx_lookup)(
+			enum dpu_intr_type intr_type,
+			u32 instance_idx);
+
+	/**
+	 * enable_irq - Enable IRQ based on lookup IRQ index
+	 * @intr:	HW interrupt handle
+	 * @irq_idx:	Lookup irq index return from irq_idx_lookup
+	 * @return:	0 for success, otherwise failure
+	 */
+	int (*enable_irq)(
+			struct dpu_hw_intr *intr,
+			int irq_idx);
+
+	/**
+	 * disable_irq - Disable IRQ based on lookup IRQ index
+	 * @intr:	HW interrupt handle
+	 * @irq_idx:	Lookup irq index return from irq_idx_lookup
+	 * @return:	0 for success, otherwise failure
+	 */
+	int (*disable_irq)(
+			struct dpu_hw_intr *intr,
+			int irq_idx);
+
+	/**
+	 * clear_all_irqs - Clears all the interrupts (i.e. acknowledges
+	 *                  any asserted IRQs). Useful during reset.
+	 * @intr:	HW interrupt handle
+	 * @return:	0 for success, otherwise failure
+	 */
+	int (*clear_all_irqs)(
+			struct dpu_hw_intr *intr);
+
+	/**
+	 * disable_all_irqs - Disables all the interrupts. Useful during reset.
+	 * @intr:	HW interrupt handle
+	 * @return:	0 for success, otherwise failure
+	 */
+	int (*disable_all_irqs)(
+			struct dpu_hw_intr *intr);
+
+	/**
+	 * dispatch_irqs - IRQ dispatcher will call the given callback
+	 *                 function when a matching interrupt status bit is
+	 *                 found in the irq mapping table.
+	 * @intr:	HW interrupt handle
+	 * @cbfunc:	Callback function pointer
+	 * @arg:	Argument to pass back during callback
+	 */
+	void (*dispatch_irqs)(
+			struct dpu_hw_intr *intr,
+			void (*cbfunc)(void *arg, int irq_idx),
+			void *arg);
+
+	/**
+	 * get_interrupt_statuses - Gets and store value from all interrupt
+	 *                          status registers that are currently fired.
+	 * @intr:	HW interrupt handle
+	 */
+	void (*get_interrupt_statuses)(
+			struct dpu_hw_intr *intr);
+
+	/**
+	 * clear_interrupt_status - Clears HW interrupt status based on given
+	 *                          lookup IRQ index.
+	 * @intr:	HW interrupt handle
+	 * @irq_idx:	Lookup irq index return from irq_idx_lookup
+	 */
+	void (*clear_interrupt_status)(
+			struct dpu_hw_intr *intr,
+			int irq_idx);
+
+	/**
+	 * clear_intr_status_nolock() - clears the HW interrupts without lock
+	 * @intr:	HW interrupt handle
+	 * @irq_idx:	Lookup irq index return from irq_idx_lookup
+	 */
+	void (*clear_intr_status_nolock)(
+			struct dpu_hw_intr *intr,
+			int irq_idx);
+
+	/**
+	 * get_interrupt_status - Gets HW interrupt status, and clear if set,
+	 *                        based on given lookup IRQ index.
+	 * @intr:	HW interrupt handle
+	 * @irq_idx:	Lookup irq index return from irq_idx_lookup
+	 * @clear:	True to clear irq after read
+	 */
+	u32 (*get_interrupt_status)(
+			struct dpu_hw_intr *intr,
+			int irq_idx,
+			bool clear);
+
+	/**
+	 * get_valid_interrupts - Gets a mask of all valid interrupt sources
+	 *                        within DPU. These are actually status bits
+	 *                        within interrupt registers that specify the
+	 *                        source of the interrupt in IRQs. For example,
+	 *                        valid interrupt sources can be MDP, DSI,
+	 *                        HDMI etc.
+	 * @intr:	HW interrupt handle
+	 * @mask:	Returning the interrupt source MASK
+	 * @return:	0 for success, otherwise failure
+	 */
+	int (*get_valid_interrupts)(
+			struct dpu_hw_intr *intr,
+			uint32_t *mask);
+};
+
+/**
+ * struct dpu_hw_intr: hw interrupts handling data structure
+ * @hw:               virtual address mapping
+ * @ops:              function pointer mapping for IRQ handling
+ * @cache_irq_mask:   array of IRQ enable masks reg storage created during init
+ * @save_irq_status:  array of IRQ status reg storage created during init
+ * @irq_idx_tbl_size: total number of irq_idx mapped in the hw_interrupts
+ * @irq_lock:         spinlock for accessing IRQ resources
+ */
+struct dpu_hw_intr {
+	struct dpu_hw_blk_reg_map hw;
+	struct dpu_hw_intr_ops ops;
+	u32 *cache_irq_mask;
+	u32 *save_irq_status;
+	u32 irq_idx_tbl_size;
+	spinlock_t irq_lock;
+};
+
+/**
+ * dpu_hw_intr_init(): Initializes the interrupts hw object
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ */
+struct dpu_hw_intr *dpu_hw_intr_init(void __iomem *addr,
+		struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_intr_destroy(): Cleanup interrutps hw object
+ * @intr: pointer to interrupts hw object
+ */
+void dpu_hw_intr_destroy(struct dpu_hw_intr *intr);
+#endif
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
new file mode 100644
index 000000000000..d280df5613c9
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
@@ -0,0 +1,349 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_intf.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+
+#define INTF_TIMING_ENGINE_EN           0x000
+#define INTF_CONFIG                     0x004
+#define INTF_HSYNC_CTL                  0x008
+#define INTF_VSYNC_PERIOD_F0            0x00C
+#define INTF_VSYNC_PERIOD_F1            0x010
+#define INTF_VSYNC_PULSE_WIDTH_F0       0x014
+#define INTF_VSYNC_PULSE_WIDTH_F1       0x018
+#define INTF_DISPLAY_V_START_F0         0x01C
+#define INTF_DISPLAY_V_START_F1         0x020
+#define INTF_DISPLAY_V_END_F0           0x024
+#define INTF_DISPLAY_V_END_F1           0x028
+#define INTF_ACTIVE_V_START_F0          0x02C
+#define INTF_ACTIVE_V_START_F1          0x030
+#define INTF_ACTIVE_V_END_F0            0x034
+#define INTF_ACTIVE_V_END_F1            0x038
+#define INTF_DISPLAY_HCTL               0x03C
+#define INTF_ACTIVE_HCTL                0x040
+#define INTF_BORDER_COLOR               0x044
+#define INTF_UNDERFLOW_COLOR            0x048
+#define INTF_HSYNC_SKEW                 0x04C
+#define INTF_POLARITY_CTL               0x050
+#define INTF_TEST_CTL                   0x054
+#define INTF_TP_COLOR0                  0x058
+#define INTF_TP_COLOR1                  0x05C
+#define INTF_FRAME_LINE_COUNT_EN        0x0A8
+#define INTF_FRAME_COUNT                0x0AC
+#define   INTF_LINE_COUNT               0x0B0
+
+#define   INTF_DEFLICKER_CONFIG         0x0F0
+#define   INTF_DEFLICKER_STRNG_COEFF    0x0F4
+#define   INTF_DEFLICKER_WEAK_COEFF     0x0F8
+
+#define   INTF_DSI_CMD_MODE_TRIGGER_EN  0x084
+#define   INTF_PANEL_FORMAT             0x090
+#define   INTF_TPG_ENABLE               0x100
+#define   INTF_TPG_MAIN_CONTROL         0x104
+#define   INTF_TPG_VIDEO_CONFIG         0x108
+#define   INTF_TPG_COMPONENT_LIMITS     0x10C
+#define   INTF_TPG_RECTANGLE            0x110
+#define   INTF_TPG_INITIAL_VALUE        0x114
+#define   INTF_TPG_BLK_WHITE_PATTERN_FRAMES   0x118
+#define   INTF_TPG_RGB_MAPPING          0x11C
+#define   INTF_PROG_FETCH_START         0x170
+#define   INTF_PROG_ROT_START           0x174
+
+#define   INTF_FRAME_LINE_COUNT_EN      0x0A8
+#define   INTF_FRAME_COUNT              0x0AC
+#define   INTF_LINE_COUNT               0x0B0
+
+#define INTF_MISR_CTRL			0x180
+#define INTF_MISR_SIGNATURE		0x184
+
+static struct dpu_intf_cfg *_intf_offset(enum dpu_intf intf,
+		struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->intf_count; i++) {
+		if ((intf == m->intf[i].id) &&
+		(m->intf[i].type != INTF_NONE)) {
+			b->base_off = addr;
+			b->blk_off = m->intf[i].base;
+			b->length = m->intf[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_INTF;
+			return &m->intf[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static void dpu_hw_intf_setup_timing_engine(struct dpu_hw_intf *ctx,
+		const struct intf_timing_params *p,
+		const struct dpu_format *fmt)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 hsync_period, vsync_period;
+	u32 display_v_start, display_v_end;
+	u32 hsync_start_x, hsync_end_x;
+	u32 active_h_start, active_h_end;
+	u32 active_v_start, active_v_end;
+	u32 active_hctl, display_hctl, hsync_ctl;
+	u32 polarity_ctl, den_polarity, hsync_polarity, vsync_polarity;
+	u32 panel_format;
+	u32 intf_cfg;
+
+	/* read interface_cfg */
+	intf_cfg = DPU_REG_READ(c, INTF_CONFIG);
+	hsync_period = p->hsync_pulse_width + p->h_back_porch + p->width +
+	p->h_front_porch;
+	vsync_period = p->vsync_pulse_width + p->v_back_porch + p->height +
+	p->v_front_porch;
+
+	display_v_start = ((p->vsync_pulse_width + p->v_back_porch) *
+	hsync_period) + p->hsync_skew;
+	display_v_end = ((vsync_period - p->v_front_porch) * hsync_period) +
+	p->hsync_skew - 1;
+
+	if (ctx->cap->type == INTF_EDP || ctx->cap->type == INTF_DP) {
+		display_v_start += p->hsync_pulse_width + p->h_back_porch;
+		display_v_end -= p->h_front_porch;
+	}
+
+	hsync_start_x = p->h_back_porch + p->hsync_pulse_width;
+	hsync_end_x = hsync_period - p->h_front_porch - 1;
+
+	if (p->width != p->xres) {
+		active_h_start = hsync_start_x;
+		active_h_end = active_h_start + p->xres - 1;
+	} else {
+		active_h_start = 0;
+		active_h_end = 0;
+	}
+
+	if (p->height != p->yres) {
+		active_v_start = display_v_start;
+		active_v_end = active_v_start + (p->yres * hsync_period) - 1;
+	} else {
+		active_v_start = 0;
+		active_v_end = 0;
+	}
+
+	if (active_h_end) {
+		active_hctl = (active_h_end << 16) | active_h_start;
+		intf_cfg |= BIT(29);	/* ACTIVE_H_ENABLE */
+	} else {
+		active_hctl = 0;
+	}
+
+	if (active_v_end)
+		intf_cfg |= BIT(30); /* ACTIVE_V_ENABLE */
+
+	hsync_ctl = (hsync_period << 16) | p->hsync_pulse_width;
+	display_hctl = (hsync_end_x << 16) | hsync_start_x;
+
+	den_polarity = 0;
+	if (ctx->cap->type == INTF_HDMI) {
+		hsync_polarity = p->yres >= 720 ? 0 : 1;
+		vsync_polarity = p->yres >= 720 ? 0 : 1;
+	} else {
+		hsync_polarity = 0;
+		vsync_polarity = 0;
+	}
+	polarity_ctl = (den_polarity << 2) | /*  DEN Polarity  */
+		(vsync_polarity << 1) | /* VSYNC Polarity */
+		(hsync_polarity << 0);  /* HSYNC Polarity */
+
+	if (!DPU_FORMAT_IS_YUV(fmt))
+		panel_format = (fmt->bits[C0_G_Y] |
+				(fmt->bits[C1_B_Cb] << 2) |
+				(fmt->bits[C2_R_Cr] << 4) |
+				(0x21 << 8));
+	else
+		/* Interface treats all the pixel data in RGB888 format */
+		panel_format = (COLOR_8BIT |
+				(COLOR_8BIT << 2) |
+				(COLOR_8BIT << 4) |
+				(0x21 << 8));
+
+	DPU_REG_WRITE(c, INTF_HSYNC_CTL, hsync_ctl);
+	DPU_REG_WRITE(c, INTF_VSYNC_PERIOD_F0, vsync_period * hsync_period);
+	DPU_REG_WRITE(c, INTF_VSYNC_PULSE_WIDTH_F0,
+			p->vsync_pulse_width * hsync_period);
+	DPU_REG_WRITE(c, INTF_DISPLAY_HCTL, display_hctl);
+	DPU_REG_WRITE(c, INTF_DISPLAY_V_START_F0, display_v_start);
+	DPU_REG_WRITE(c, INTF_DISPLAY_V_END_F0, display_v_end);
+	DPU_REG_WRITE(c, INTF_ACTIVE_HCTL,  active_hctl);
+	DPU_REG_WRITE(c, INTF_ACTIVE_V_START_F0, active_v_start);
+	DPU_REG_WRITE(c, INTF_ACTIVE_V_END_F0, active_v_end);
+	DPU_REG_WRITE(c, INTF_BORDER_COLOR, p->border_clr);
+	DPU_REG_WRITE(c, INTF_UNDERFLOW_COLOR, p->underflow_clr);
+	DPU_REG_WRITE(c, INTF_HSYNC_SKEW, p->hsync_skew);
+	DPU_REG_WRITE(c, INTF_POLARITY_CTL, polarity_ctl);
+	DPU_REG_WRITE(c, INTF_FRAME_LINE_COUNT_EN, 0x3);
+	DPU_REG_WRITE(c, INTF_CONFIG, intf_cfg);
+	DPU_REG_WRITE(c, INTF_PANEL_FORMAT, panel_format);
+}
+
+static void dpu_hw_intf_enable_timing_engine(
+		struct dpu_hw_intf *intf,
+		u8 enable)
+{
+	struct dpu_hw_blk_reg_map *c = &intf->hw;
+	/* Note: Display interface select is handled in top block hw layer */
+	DPU_REG_WRITE(c, INTF_TIMING_ENGINE_EN, enable != 0);
+}
+
+static void dpu_hw_intf_setup_prg_fetch(
+		struct dpu_hw_intf *intf,
+		const struct intf_prog_fetch *fetch)
+{
+	struct dpu_hw_blk_reg_map *c = &intf->hw;
+	int fetch_enable;
+
+	/*
+	 * Fetch should always be outside the active lines. If the fetching
+	 * is programmed within active region, hardware behavior is unknown.
+	 */
+
+	fetch_enable = DPU_REG_READ(c, INTF_CONFIG);
+	if (fetch->enable) {
+		fetch_enable |= BIT(31);
+		DPU_REG_WRITE(c, INTF_PROG_FETCH_START,
+				fetch->fetch_start);
+	} else {
+		fetch_enable &= ~BIT(31);
+	}
+
+	DPU_REG_WRITE(c, INTF_CONFIG, fetch_enable);
+}
+
+static void dpu_hw_intf_get_status(
+		struct dpu_hw_intf *intf,
+		struct intf_status *s)
+{
+	struct dpu_hw_blk_reg_map *c = &intf->hw;
+
+	s->is_en = DPU_REG_READ(c, INTF_TIMING_ENGINE_EN);
+	if (s->is_en) {
+		s->frame_count = DPU_REG_READ(c, INTF_FRAME_COUNT);
+		s->line_count = DPU_REG_READ(c, INTF_LINE_COUNT);
+	} else {
+		s->line_count = 0;
+		s->frame_count = 0;
+	}
+}
+
+static void dpu_hw_intf_setup_misr(struct dpu_hw_intf *intf,
+						bool enable, u32 frame_count)
+{
+	struct dpu_hw_blk_reg_map *c = &intf->hw;
+	u32 config = 0;
+
+	DPU_REG_WRITE(c, INTF_MISR_CTRL, MISR_CTRL_STATUS_CLEAR);
+	/* clear misr data */
+	wmb();
+
+	if (enable)
+		config = (frame_count & MISR_FRAME_COUNT_MASK) |
+			MISR_CTRL_ENABLE | INTF_MISR_CTRL_FREE_RUN_MASK;
+
+	DPU_REG_WRITE(c, INTF_MISR_CTRL, config);
+}
+
+static u32 dpu_hw_intf_collect_misr(struct dpu_hw_intf *intf)
+{
+	struct dpu_hw_blk_reg_map *c = &intf->hw;
+
+	return DPU_REG_READ(c, INTF_MISR_SIGNATURE);
+}
+
+static u32 dpu_hw_intf_get_line_count(struct dpu_hw_intf *intf)
+{
+	struct dpu_hw_blk_reg_map *c;
+
+	if (!intf)
+		return 0;
+
+	c = &intf->hw;
+
+	return DPU_REG_READ(c, INTF_LINE_COUNT);
+}
+
+static void _setup_intf_ops(struct dpu_hw_intf_ops *ops,
+		unsigned long cap)
+{
+	ops->setup_timing_gen = dpu_hw_intf_setup_timing_engine;
+	ops->setup_prg_fetch  = dpu_hw_intf_setup_prg_fetch;
+	ops->get_status = dpu_hw_intf_get_status;
+	ops->enable_timing = dpu_hw_intf_enable_timing_engine;
+	ops->setup_misr = dpu_hw_intf_setup_misr;
+	ops->collect_misr = dpu_hw_intf_collect_misr;
+	ops->get_line_count = dpu_hw_intf_get_line_count;
+}
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_intf *dpu_hw_intf_init(enum dpu_intf idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_intf *c;
+	struct dpu_intf_cfg *cfg;
+	int rc;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _intf_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		pr_err("failed to create dpu_hw_intf %d\n", idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/*
+	 * Assign ops
+	 */
+	c->idx = idx;
+	c->cap = cfg;
+	c->mdss = m;
+	_setup_intf_ops(&c->ops, c->cap->features);
+
+	rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_INTF, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	return c;
+
+blk_init_error:
+	kzfree(c);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_intf_destroy(struct dpu_hw_intf *intf)
+{
+	if (intf)
+		dpu_hw_blk_destroy(&intf->base);
+	kfree(intf);
+}
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
new file mode 100644
index 000000000000..a79d735da68d
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
@@ -0,0 +1,128 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_INTF_H
+#define _DPU_HW_INTF_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_blk.h"
+
+struct dpu_hw_intf;
+
+/* intf timing settings */
+struct intf_timing_params {
+	u32 width;		/* active width */
+	u32 height;		/* active height */
+	u32 xres;		/* Display panel width */
+	u32 yres;		/* Display panel height */
+
+	u32 h_back_porch;
+	u32 h_front_porch;
+	u32 v_back_porch;
+	u32 v_front_porch;
+	u32 hsync_pulse_width;
+	u32 vsync_pulse_width;
+	u32 hsync_polarity;
+	u32 vsync_polarity;
+	u32 border_clr;
+	u32 underflow_clr;
+	u32 hsync_skew;
+};
+
+struct intf_prog_fetch {
+	u8 enable;
+	/* vsync counter for the front porch pixel line */
+	u32 fetch_start;
+};
+
+struct intf_status {
+	u8 is_en;		/* interface timing engine is enabled or not */
+	u32 frame_count;	/* frame count since timing engine enabled */
+	u32 line_count;		/* current line count including blanking */
+};
+
+/**
+ * struct dpu_hw_intf_ops : Interface to the interface Hw driver functions
+ *  Assumption is these functions will be called after clocks are enabled
+ * @ setup_timing_gen : programs the timing engine
+ * @ setup_prog_fetch : enables/disables the programmable fetch logic
+ * @ enable_timing: enable/disable timing engine
+ * @ get_status: returns if timing engine is enabled or not
+ * @ setup_misr: enables/disables MISR in HW register
+ * @ collect_misr: reads and stores MISR data from HW register
+ * @ get_line_count: reads current vertical line counter
+ */
+struct dpu_hw_intf_ops {
+	void (*setup_timing_gen)(struct dpu_hw_intf *intf,
+			const struct intf_timing_params *p,
+			const struct dpu_format *fmt);
+
+	void (*setup_prg_fetch)(struct dpu_hw_intf *intf,
+			const struct intf_prog_fetch *fetch);
+
+	void (*enable_timing)(struct dpu_hw_intf *intf,
+			u8 enable);
+
+	void (*get_status)(struct dpu_hw_intf *intf,
+			struct intf_status *status);
+
+	void (*setup_misr)(struct dpu_hw_intf *intf,
+			bool enable, u32 frame_count);
+
+	u32 (*collect_misr)(struct dpu_hw_intf *intf);
+
+	u32 (*get_line_count)(struct dpu_hw_intf *intf);
+};
+
+struct dpu_hw_intf {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* intf */
+	enum dpu_intf idx;
+	const struct dpu_intf_cfg *cap;
+	const struct dpu_mdss_cfg *mdss;
+
+	/* ops */
+	struct dpu_hw_intf_ops ops;
+};
+
+/**
+ * to_dpu_hw_intf - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_intf *to_dpu_hw_intf(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_intf, base);
+}
+
+/**
+ * dpu_hw_intf_init(): Initializes the intf driver for the passed
+ * interface idx.
+ * @idx:  interface index for which driver object is required
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ */
+struct dpu_hw_intf *dpu_hw_intf_init(enum dpu_intf idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_intf_destroy(): Destroys INTF driver context
+ * @intf:   Pointer to INTF driver context
+ */
+void dpu_hw_intf_destroy(struct dpu_hw_intf *intf);
+
+#endif /*_DPU_HW_INTF_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c
new file mode 100644
index 000000000000..4ab72b0f07a5
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c
@@ -0,0 +1,261 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_kms.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hwio.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+
+#define LM_OP_MODE                        0x00
+#define LM_OUT_SIZE                       0x04
+#define LM_BORDER_COLOR_0                 0x08
+#define LM_BORDER_COLOR_1                 0x010
+
+/* These register are offset to mixer base + stage base */
+#define LM_BLEND0_OP                     0x00
+#define LM_BLEND0_CONST_ALPHA            0x04
+#define LM_FG_COLOR_FILL_COLOR_0         0x08
+#define LM_FG_COLOR_FILL_COLOR_1         0x0C
+#define LM_FG_COLOR_FILL_SIZE            0x10
+#define LM_FG_COLOR_FILL_XY              0x14
+
+#define LM_BLEND0_FG_ALPHA               0x04
+#define LM_BLEND0_BG_ALPHA               0x08
+
+#define LM_MISR_CTRL			0x310
+#define LM_MISR_SIGNATURE		0x314
+
+static struct dpu_lm_cfg *_lm_offset(enum dpu_lm mixer,
+		struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->mixer_count; i++) {
+		if (mixer == m->mixer[i].id) {
+			b->base_off = addr;
+			b->blk_off = m->mixer[i].base;
+			b->length = m->mixer[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_LM;
+			return &m->mixer[i];
+		}
+	}
+
+	return ERR_PTR(-ENOMEM);
+}
+
+/**
+ * _stage_offset(): returns the relative offset of the blend registers
+ * for the stage to be setup
+ * @c:     mixer ctx contains the mixer to be programmed
+ * @stage: stage index to setup
+ */
+static inline int _stage_offset(struct dpu_hw_mixer *ctx, enum dpu_stage stage)
+{
+	const struct dpu_lm_sub_blks *sblk = ctx->cap->sblk;
+	int rc;
+
+	if (stage == DPU_STAGE_BASE)
+		rc = -EINVAL;
+	else if (stage <= sblk->maxblendstages)
+		rc = sblk->blendstage_base[stage - DPU_STAGE_0];
+	else
+		rc = -EINVAL;
+
+	return rc;
+}
+
+static void dpu_hw_lm_setup_out(struct dpu_hw_mixer *ctx,
+		struct dpu_hw_mixer_cfg *mixer)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 outsize;
+	u32 op_mode;
+
+	op_mode = DPU_REG_READ(c, LM_OP_MODE);
+
+	outsize = mixer->out_height << 16 | mixer->out_width;
+	DPU_REG_WRITE(c, LM_OUT_SIZE, outsize);
+
+	/* SPLIT_LEFT_RIGHT */
+	if (mixer->right_mixer)
+		op_mode |= BIT(31);
+	else
+		op_mode &= ~BIT(31);
+	DPU_REG_WRITE(c, LM_OP_MODE, op_mode);
+}
+
+static void dpu_hw_lm_setup_border_color(struct dpu_hw_mixer *ctx,
+		struct dpu_mdss_color *color,
+		u8 border_en)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+
+	if (border_en) {
+		DPU_REG_WRITE(c, LM_BORDER_COLOR_0,
+			(color->color_0 & 0xFFF) |
+			((color->color_1 & 0xFFF) << 0x10));
+		DPU_REG_WRITE(c, LM_BORDER_COLOR_1,
+			(color->color_2 & 0xFFF) |
+			((color->color_3 & 0xFFF) << 0x10));
+	}
+}
+
+static void dpu_hw_lm_setup_blend_config_sdm845(struct dpu_hw_mixer *ctx,
+	u32 stage, u32 fg_alpha, u32 bg_alpha, u32 blend_op)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	int stage_off;
+	u32 const_alpha;
+
+	if (stage == DPU_STAGE_BASE)
+		return;
+
+	stage_off = _stage_offset(ctx, stage);
+	if (WARN_ON(stage_off < 0))
+		return;
+
+	const_alpha = (bg_alpha & 0xFF) | ((fg_alpha & 0xFF) << 16);
+	DPU_REG_WRITE(c, LM_BLEND0_CONST_ALPHA + stage_off, const_alpha);
+	DPU_REG_WRITE(c, LM_BLEND0_OP + stage_off, blend_op);
+}
+
+static void dpu_hw_lm_setup_blend_config(struct dpu_hw_mixer *ctx,
+	u32 stage, u32 fg_alpha, u32 bg_alpha, u32 blend_op)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	int stage_off;
+
+	if (stage == DPU_STAGE_BASE)
+		return;
+
+	stage_off = _stage_offset(ctx, stage);
+	if (WARN_ON(stage_off < 0))
+		return;
+
+	DPU_REG_WRITE(c, LM_BLEND0_FG_ALPHA + stage_off, fg_alpha);
+	DPU_REG_WRITE(c, LM_BLEND0_BG_ALPHA + stage_off, bg_alpha);
+	DPU_REG_WRITE(c, LM_BLEND0_OP + stage_off, blend_op);
+}
+
+static void dpu_hw_lm_setup_color3(struct dpu_hw_mixer *ctx,
+	uint32_t mixer_op_mode)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	int op_mode;
+
+	/* read the existing op_mode configuration */
+	op_mode = DPU_REG_READ(c, LM_OP_MODE);
+
+	op_mode = (op_mode & (BIT(31) | BIT(30))) | mixer_op_mode;
+
+	DPU_REG_WRITE(c, LM_OP_MODE, op_mode);
+}
+
+static void dpu_hw_lm_gc(struct dpu_hw_mixer *mixer,
+			void *cfg)
+{
+}
+
+static void dpu_hw_lm_setup_misr(struct dpu_hw_mixer *ctx,
+				bool enable, u32 frame_count)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 config = 0;
+
+	DPU_REG_WRITE(c, LM_MISR_CTRL, MISR_CTRL_STATUS_CLEAR);
+	/* clear misr data */
+	wmb();
+
+	if (enable)
+		config = (frame_count & MISR_FRAME_COUNT_MASK) |
+			MISR_CTRL_ENABLE | INTF_MISR_CTRL_FREE_RUN_MASK;
+
+	DPU_REG_WRITE(c, LM_MISR_CTRL, config);
+}
+
+static u32 dpu_hw_lm_collect_misr(struct dpu_hw_mixer *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+
+	return DPU_REG_READ(c, LM_MISR_SIGNATURE);
+}
+
+static void _setup_mixer_ops(struct dpu_mdss_cfg *m,
+		struct dpu_hw_lm_ops *ops,
+		unsigned long features)
+{
+	ops->setup_mixer_out = dpu_hw_lm_setup_out;
+	if (IS_SDM845_TARGET(m->hwversion) || IS_SDM670_TARGET(m->hwversion))
+		ops->setup_blend_config = dpu_hw_lm_setup_blend_config_sdm845;
+	else
+		ops->setup_blend_config = dpu_hw_lm_setup_blend_config;
+	ops->setup_alpha_out = dpu_hw_lm_setup_color3;
+	ops->setup_border_color = dpu_hw_lm_setup_border_color;
+	ops->setup_gc = dpu_hw_lm_gc;
+	ops->setup_misr = dpu_hw_lm_setup_misr;
+	ops->collect_misr = dpu_hw_lm_collect_misr;
+};
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_mixer *dpu_hw_lm_init(enum dpu_lm idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_mixer *c;
+	struct dpu_lm_cfg *cfg;
+	int rc;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _lm_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* Assign ops */
+	c->idx = idx;
+	c->cap = cfg;
+	_setup_mixer_ops(m, &c->ops, c->cap->features);
+
+	rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_LM, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	return c;
+
+blk_init_error:
+	kzfree(c);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_lm_destroy(struct dpu_hw_mixer *lm)
+{
+	if (lm)
+		dpu_hw_blk_destroy(&lm->base);
+	kfree(lm);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h
new file mode 100644
index 000000000000..e29e5dab31bf
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h
@@ -0,0 +1,122 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_LM_H
+#define _DPU_HW_LM_H
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_blk.h"
+
+struct dpu_hw_mixer;
+
+struct dpu_hw_mixer_cfg {
+	u32 out_width;
+	u32 out_height;
+	bool right_mixer;
+	int flags;
+};
+
+struct dpu_hw_color3_cfg {
+	u8 keep_fg[DPU_STAGE_MAX];
+};
+
+/**
+ *
+ * struct dpu_hw_lm_ops : Interface to the mixer Hw driver functions
+ *  Assumption is these functions will be called after clocks are enabled
+ */
+struct dpu_hw_lm_ops {
+	/*
+	 * Sets up mixer output width and height
+	 * and border color if enabled
+	 */
+	void (*setup_mixer_out)(struct dpu_hw_mixer *ctx,
+		struct dpu_hw_mixer_cfg *cfg);
+
+	/*
+	 * Alpha blending configuration
+	 * for the specified stage
+	 */
+	void (*setup_blend_config)(struct dpu_hw_mixer *ctx, uint32_t stage,
+		uint32_t fg_alpha, uint32_t bg_alpha, uint32_t blend_op);
+
+	/*
+	 * Alpha color component selection from either fg or bg
+	 */
+	void (*setup_alpha_out)(struct dpu_hw_mixer *ctx, uint32_t mixer_op);
+
+	/**
+	 * setup_border_color : enable/disable border color
+	 */
+	void (*setup_border_color)(struct dpu_hw_mixer *ctx,
+		struct dpu_mdss_color *color,
+		u8 border_en);
+	/**
+	 * setup_gc : enable/disable gamma correction feature
+	 */
+	void (*setup_gc)(struct dpu_hw_mixer *mixer,
+			void *cfg);
+
+	/* setup_misr: enables/disables MISR in HW register */
+	void (*setup_misr)(struct dpu_hw_mixer *ctx,
+			bool enable, u32 frame_count);
+
+	/* collect_misr: reads and stores MISR data from HW register */
+	u32 (*collect_misr)(struct dpu_hw_mixer *ctx);
+};
+
+struct dpu_hw_mixer {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* lm */
+	enum dpu_lm  idx;
+	const struct dpu_lm_cfg   *cap;
+	const struct dpu_mdp_cfg  *mdp;
+	const struct dpu_ctl_cfg  *ctl;
+
+	/* ops */
+	struct dpu_hw_lm_ops ops;
+
+	/* store mixer info specific to display */
+	struct dpu_hw_mixer_cfg cfg;
+};
+
+/**
+ * to_dpu_hw_mixer - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_mixer *to_dpu_hw_mixer(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_mixer, base);
+}
+
+/**
+ * dpu_hw_lm_init(): Initializes the mixer hw driver object.
+ * should be called once before accessing every mixer.
+ * @idx:  mixer index for which driver object is required
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ */
+struct dpu_hw_mixer *dpu_hw_lm_init(enum dpu_lm idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_lm_destroy(): Destroys layer mixer driver context
+ * @lm:   Pointer to LM driver context
+ */
+void dpu_hw_lm_destroy(struct dpu_hw_mixer *lm);
+
+#endif /*_DPU_HW_LM_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h
new file mode 100644
index 000000000000..35e6bf930924
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h
@@ -0,0 +1,465 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_MDSS_H
+#define _DPU_HW_MDSS_H
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+
+#include "msm_drv.h"
+
+#define DPU_DBG_NAME			"dpu"
+
+#define DPU_NONE                        0
+
+#ifndef DPU_CSC_MATRIX_COEFF_SIZE
+#define DPU_CSC_MATRIX_COEFF_SIZE	9
+#endif
+
+#ifndef DPU_CSC_CLAMP_SIZE
+#define DPU_CSC_CLAMP_SIZE		6
+#endif
+
+#ifndef DPU_CSC_BIAS_SIZE
+#define DPU_CSC_BIAS_SIZE		3
+#endif
+
+#ifndef DPU_MAX_PLANES
+#define DPU_MAX_PLANES			4
+#endif
+
+#define PIPES_PER_STAGE			2
+#ifndef DPU_MAX_DE_CURVES
+#define DPU_MAX_DE_CURVES		3
+#endif
+
+enum dpu_format_flags {
+	DPU_FORMAT_FLAG_YUV_BIT,
+	DPU_FORMAT_FLAG_DX_BIT,
+	DPU_FORMAT_FLAG_COMPRESSED_BIT,
+	DPU_FORMAT_FLAG_BIT_MAX,
+};
+
+#define DPU_FORMAT_FLAG_YUV		BIT(DPU_FORMAT_FLAG_YUV_BIT)
+#define DPU_FORMAT_FLAG_DX		BIT(DPU_FORMAT_FLAG_DX_BIT)
+#define DPU_FORMAT_FLAG_COMPRESSED	BIT(DPU_FORMAT_FLAG_COMPRESSED_BIT)
+#define DPU_FORMAT_IS_YUV(X)		\
+	(test_bit(DPU_FORMAT_FLAG_YUV_BIT, (X)->flag))
+#define DPU_FORMAT_IS_DX(X)		\
+	(test_bit(DPU_FORMAT_FLAG_DX_BIT, (X)->flag))
+#define DPU_FORMAT_IS_LINEAR(X)		((X)->fetch_mode == DPU_FETCH_LINEAR)
+#define DPU_FORMAT_IS_TILE(X) \
+	(((X)->fetch_mode == DPU_FETCH_UBWC) && \
+			!test_bit(DPU_FORMAT_FLAG_COMPRESSED_BIT, (X)->flag))
+#define DPU_FORMAT_IS_UBWC(X) \
+	(((X)->fetch_mode == DPU_FETCH_UBWC) && \
+			test_bit(DPU_FORMAT_FLAG_COMPRESSED_BIT, (X)->flag))
+
+#define DPU_BLEND_FG_ALPHA_FG_CONST	(0 << 0)
+#define DPU_BLEND_FG_ALPHA_BG_CONST	(1 << 0)
+#define DPU_BLEND_FG_ALPHA_FG_PIXEL	(2 << 0)
+#define DPU_BLEND_FG_ALPHA_BG_PIXEL	(3 << 0)
+#define DPU_BLEND_FG_INV_ALPHA		(1 << 2)
+#define DPU_BLEND_FG_MOD_ALPHA		(1 << 3)
+#define DPU_BLEND_FG_INV_MOD_ALPHA	(1 << 4)
+#define DPU_BLEND_FG_TRANSP_EN		(1 << 5)
+#define DPU_BLEND_BG_ALPHA_FG_CONST	(0 << 8)
+#define DPU_BLEND_BG_ALPHA_BG_CONST	(1 << 8)
+#define DPU_BLEND_BG_ALPHA_FG_PIXEL	(2 << 8)
+#define DPU_BLEND_BG_ALPHA_BG_PIXEL	(3 << 8)
+#define DPU_BLEND_BG_INV_ALPHA		(1 << 10)
+#define DPU_BLEND_BG_MOD_ALPHA		(1 << 11)
+#define DPU_BLEND_BG_INV_MOD_ALPHA	(1 << 12)
+#define DPU_BLEND_BG_TRANSP_EN		(1 << 13)
+
+#define DPU_VSYNC0_SOURCE_GPIO		0
+#define DPU_VSYNC1_SOURCE_GPIO		1
+#define DPU_VSYNC2_SOURCE_GPIO		2
+#define DPU_VSYNC_SOURCE_INTF_0		3
+#define DPU_VSYNC_SOURCE_INTF_1		4
+#define DPU_VSYNC_SOURCE_INTF_2		5
+#define DPU_VSYNC_SOURCE_INTF_3		6
+#define DPU_VSYNC_SOURCE_WD_TIMER_4	11
+#define DPU_VSYNC_SOURCE_WD_TIMER_3	12
+#define DPU_VSYNC_SOURCE_WD_TIMER_2	13
+#define DPU_VSYNC_SOURCE_WD_TIMER_1	14
+#define DPU_VSYNC_SOURCE_WD_TIMER_0	15
+
+enum dpu_hw_blk_type {
+	DPU_HW_BLK_TOP = 0,
+	DPU_HW_BLK_SSPP,
+	DPU_HW_BLK_LM,
+	DPU_HW_BLK_CTL,
+	DPU_HW_BLK_CDM,
+	DPU_HW_BLK_PINGPONG,
+	DPU_HW_BLK_INTF,
+	DPU_HW_BLK_WB,
+	DPU_HW_BLK_MAX,
+};
+
+enum dpu_mdp {
+	MDP_TOP = 0x1,
+	MDP_MAX,
+};
+
+enum dpu_sspp {
+	SSPP_NONE,
+	SSPP_VIG0,
+	SSPP_VIG1,
+	SSPP_VIG2,
+	SSPP_VIG3,
+	SSPP_RGB0,
+	SSPP_RGB1,
+	SSPP_RGB2,
+	SSPP_RGB3,
+	SSPP_DMA0,
+	SSPP_DMA1,
+	SSPP_DMA2,
+	SSPP_DMA3,
+	SSPP_CURSOR0,
+	SSPP_CURSOR1,
+	SSPP_MAX
+};
+
+enum dpu_sspp_type {
+	SSPP_TYPE_VIG,
+	SSPP_TYPE_RGB,
+	SSPP_TYPE_DMA,
+	SSPP_TYPE_CURSOR,
+	SSPP_TYPE_MAX
+};
+
+enum dpu_lm {
+	LM_0 = 1,
+	LM_1,
+	LM_2,
+	LM_3,
+	LM_4,
+	LM_5,
+	LM_6,
+	LM_MAX
+};
+
+enum dpu_stage {
+	DPU_STAGE_BASE = 0,
+	DPU_STAGE_0,
+	DPU_STAGE_1,
+	DPU_STAGE_2,
+	DPU_STAGE_3,
+	DPU_STAGE_4,
+	DPU_STAGE_5,
+	DPU_STAGE_6,
+	DPU_STAGE_7,
+	DPU_STAGE_8,
+	DPU_STAGE_9,
+	DPU_STAGE_10,
+	DPU_STAGE_MAX
+};
+enum dpu_dspp {
+	DSPP_0 = 1,
+	DSPP_1,
+	DSPP_2,
+	DSPP_3,
+	DSPP_MAX
+};
+
+enum dpu_ds {
+	DS_TOP,
+	DS_0,
+	DS_1,
+	DS_MAX
+};
+
+enum dpu_ctl {
+	CTL_0 = 1,
+	CTL_1,
+	CTL_2,
+	CTL_3,
+	CTL_4,
+	CTL_MAX
+};
+
+enum dpu_cdm {
+	CDM_0 = 1,
+	CDM_1,
+	CDM_MAX
+};
+
+enum dpu_pingpong {
+	PINGPONG_0 = 1,
+	PINGPONG_1,
+	PINGPONG_2,
+	PINGPONG_3,
+	PINGPONG_4,
+	PINGPONG_S0,
+	PINGPONG_MAX
+};
+
+enum dpu_intf {
+	INTF_0 = 1,
+	INTF_1,
+	INTF_2,
+	INTF_3,
+	INTF_4,
+	INTF_5,
+	INTF_6,
+	INTF_MAX
+};
+
+enum dpu_intf_type {
+	INTF_NONE = 0x0,
+	INTF_DSI = 0x1,
+	INTF_HDMI = 0x3,
+	INTF_LCDC = 0x5,
+	INTF_EDP = 0x9,
+	INTF_DP = 0xa,
+	INTF_TYPE_MAX,
+
+	/* virtual interfaces */
+	INTF_WB = 0x100,
+};
+
+enum dpu_intf_mode {
+	INTF_MODE_NONE = 0,
+	INTF_MODE_CMD,
+	INTF_MODE_VIDEO,
+	INTF_MODE_WB_BLOCK,
+	INTF_MODE_WB_LINE,
+	INTF_MODE_MAX
+};
+
+enum dpu_wb {
+	WB_0 = 1,
+	WB_1,
+	WB_2,
+	WB_3,
+	WB_MAX
+};
+
+enum dpu_ad {
+	AD_0 = 0x1,
+	AD_1,
+	AD_MAX
+};
+
+enum dpu_cwb {
+	CWB_0 = 0x1,
+	CWB_1,
+	CWB_2,
+	CWB_3,
+	CWB_MAX
+};
+
+enum dpu_wd_timer {
+	WD_TIMER_0 = 0x1,
+	WD_TIMER_1,
+	WD_TIMER_2,
+	WD_TIMER_3,
+	WD_TIMER_4,
+	WD_TIMER_5,
+	WD_TIMER_MAX
+};
+
+enum dpu_vbif {
+	VBIF_0,
+	VBIF_1,
+	VBIF_MAX,
+	VBIF_RT = VBIF_0,
+	VBIF_NRT = VBIF_1
+};
+
+enum dpu_iommu_domain {
+	DPU_IOMMU_DOMAIN_UNSECURE,
+	DPU_IOMMU_DOMAIN_SECURE,
+	DPU_IOMMU_DOMAIN_MAX
+};
+
+/**
+ * DPU HW,Component order color map
+ */
+enum {
+	C0_G_Y = 0,
+	C1_B_Cb = 1,
+	C2_R_Cr = 2,
+	C3_ALPHA = 3
+};
+
+/**
+ * enum dpu_plane_type - defines how the color component pixel packing
+ * @DPU_PLANE_INTERLEAVED   : Color components in single plane
+ * @DPU_PLANE_PLANAR        : Color component in separate planes
+ * @DPU_PLANE_PSEUDO_PLANAR : Chroma components interleaved in separate plane
+ */
+enum dpu_plane_type {
+	DPU_PLANE_INTERLEAVED,
+	DPU_PLANE_PLANAR,
+	DPU_PLANE_PSEUDO_PLANAR,
+};
+
+/**
+ * enum dpu_chroma_samp_type - chroma sub-samplng type
+ * @DPU_CHROMA_RGB   : No chroma subsampling
+ * @DPU_CHROMA_H2V1  : Chroma pixels are horizontally subsampled
+ * @DPU_CHROMA_H1V2  : Chroma pixels are vertically subsampled
+ * @DPU_CHROMA_420   : 420 subsampling
+ */
+enum dpu_chroma_samp_type {
+	DPU_CHROMA_RGB,
+	DPU_CHROMA_H2V1,
+	DPU_CHROMA_H1V2,
+	DPU_CHROMA_420
+};
+
+/**
+ * dpu_fetch_type - Defines How DPU HW fetches data
+ * @DPU_FETCH_LINEAR   : fetch is line by line
+ * @DPU_FETCH_TILE     : fetches data in Z order from a tile
+ * @DPU_FETCH_UBWC     : fetch and decompress data
+ */
+enum dpu_fetch_type {
+	DPU_FETCH_LINEAR,
+	DPU_FETCH_TILE,
+	DPU_FETCH_UBWC
+};
+
+/**
+ * Value of enum chosen to fit the number of bits
+ * expected by the HW programming.
+ */
+enum {
+	COLOR_ALPHA_1BIT = 0,
+	COLOR_ALPHA_4BIT = 1,
+	COLOR_4BIT = 0,
+	COLOR_5BIT = 1, /* No 5-bit Alpha */
+	COLOR_6BIT = 2, /* 6-Bit Alpha also = 2 */
+	COLOR_8BIT = 3, /* 8-Bit Alpha also = 3 */
+};
+
+/**
+ * enum dpu_3d_blend_mode
+ * Desribes how the 3d data is blended
+ * @BLEND_3D_NONE      : 3d blending not enabled
+ * @BLEND_3D_FRAME_INT : Frame interleaving
+ * @BLEND_3D_H_ROW_INT : Horizontal row interleaving
+ * @BLEND_3D_V_ROW_INT : vertical row interleaving
+ * @BLEND_3D_COL_INT   : column interleaving
+ * @BLEND_3D_MAX       :
+ */
+enum dpu_3d_blend_mode {
+	BLEND_3D_NONE = 0,
+	BLEND_3D_FRAME_INT,
+	BLEND_3D_H_ROW_INT,
+	BLEND_3D_V_ROW_INT,
+	BLEND_3D_COL_INT,
+	BLEND_3D_MAX
+};
+
+/** struct dpu_format - defines the format configuration which
+ * allows DPU HW to correctly fetch and decode the format
+ * @base: base msm_format struture containing fourcc code
+ * @fetch_planes: how the color components are packed in pixel format
+ * @element: element color ordering
+ * @bits: element bit widths
+ * @chroma_sample: chroma sub-samplng type
+ * @unpack_align_msb: unpack aligned, 0 to LSB, 1 to MSB
+ * @unpack_tight: 0 for loose, 1 for tight
+ * @unpack_count: 0 = 1 component, 1 = 2 component
+ * @bpp: bytes per pixel
+ * @alpha_enable: whether the format has an alpha channel
+ * @num_planes: number of planes (including meta data planes)
+ * @fetch_mode: linear, tiled, or ubwc hw fetch behavior
+ * @is_yuv: is format a yuv variant
+ * @flag: usage bit flags
+ * @tile_width: format tile width
+ * @tile_height: format tile height
+ */
+struct dpu_format {
+	struct msm_format base;
+	enum dpu_plane_type fetch_planes;
+	u8 element[DPU_MAX_PLANES];
+	u8 bits[DPU_MAX_PLANES];
+	enum dpu_chroma_samp_type chroma_sample;
+	u8 unpack_align_msb;
+	u8 unpack_tight;
+	u8 unpack_count;
+	u8 bpp;
+	u8 alpha_enable;
+	u8 num_planes;
+	enum dpu_fetch_type fetch_mode;
+	DECLARE_BITMAP(flag, DPU_FORMAT_FLAG_BIT_MAX);
+	u16 tile_width;
+	u16 tile_height;
+};
+#define to_dpu_format(x) container_of(x, struct dpu_format, base)
+
+/**
+ * struct dpu_hw_fmt_layout - format information of the source pixel data
+ * @format: pixel format parameters
+ * @num_planes: number of planes (including meta data planes)
+ * @width: image width
+ * @height: image height
+ * @total_size: total size in bytes
+ * @plane_addr: address of each plane
+ * @plane_size: length of each plane
+ * @plane_pitch: pitch of each plane
+ */
+struct dpu_hw_fmt_layout {
+	const struct dpu_format *format;
+	uint32_t num_planes;
+	uint32_t width;
+	uint32_t height;
+	uint32_t total_size;
+	uint32_t plane_addr[DPU_MAX_PLANES];
+	uint32_t plane_size[DPU_MAX_PLANES];
+	uint32_t plane_pitch[DPU_MAX_PLANES];
+};
+
+struct dpu_csc_cfg {
+	/* matrix coefficients in S15.16 format */
+	uint32_t csc_mv[DPU_CSC_MATRIX_COEFF_SIZE];
+	uint32_t csc_pre_bv[DPU_CSC_BIAS_SIZE];
+	uint32_t csc_post_bv[DPU_CSC_BIAS_SIZE];
+	uint32_t csc_pre_lv[DPU_CSC_CLAMP_SIZE];
+	uint32_t csc_post_lv[DPU_CSC_CLAMP_SIZE];
+};
+
+/**
+ * struct dpu_mdss_color - mdss color description
+ * color 0 : green
+ * color 1 : blue
+ * color 2 : red
+ * color 3 : alpha
+ */
+struct dpu_mdss_color {
+	u32 color_0;
+	u32 color_1;
+	u32 color_2;
+	u32 color_3;
+};
+
+/*
+ * Define bit masks for h/w logging.
+ */
+#define DPU_DBG_MASK_NONE     (1 << 0)
+#define DPU_DBG_MASK_CDM      (1 << 1)
+#define DPU_DBG_MASK_INTF     (1 << 2)
+#define DPU_DBG_MASK_LM       (1 << 3)
+#define DPU_DBG_MASK_CTL      (1 << 4)
+#define DPU_DBG_MASK_PINGPONG (1 << 5)
+#define DPU_DBG_MASK_SSPP     (1 << 6)
+#define DPU_DBG_MASK_WB       (1 << 7)
+#define DPU_DBG_MASK_TOP      (1 << 8)
+#define DPU_DBG_MASK_VBIF     (1 << 9)
+#define DPU_DBG_MASK_ROT      (1 << 10)
+
+#endif  /* _DPU_HW_MDSS_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
new file mode 100644
index 000000000000..cc3a623903f4
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
@@ -0,0 +1,250 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/iopoll.h>
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_pingpong.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+#include "dpu_trace.h"
+
+#define PP_TEAR_CHECK_EN                0x000
+#define PP_SYNC_CONFIG_VSYNC            0x004
+#define PP_SYNC_CONFIG_HEIGHT           0x008
+#define PP_SYNC_WRCOUNT                 0x00C
+#define PP_VSYNC_INIT_VAL               0x010
+#define PP_INT_COUNT_VAL                0x014
+#define PP_SYNC_THRESH                  0x018
+#define PP_START_POS                    0x01C
+#define PP_RD_PTR_IRQ                   0x020
+#define PP_WR_PTR_IRQ                   0x024
+#define PP_OUT_LINE_COUNT               0x028
+#define PP_LINE_COUNT                   0x02C
+
+#define PP_FBC_MODE                     0x034
+#define PP_FBC_BUDGET_CTL               0x038
+#define PP_FBC_LOSSY_MODE               0x03C
+
+static struct dpu_pingpong_cfg *_pingpong_offset(enum dpu_pingpong pp,
+		struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->pingpong_count; i++) {
+		if (pp == m->pingpong[i].id) {
+			b->base_off = addr;
+			b->blk_off = m->pingpong[i].base;
+			b->length = m->pingpong[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_PINGPONG;
+			return &m->pingpong[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static int dpu_hw_pp_setup_te_config(struct dpu_hw_pingpong *pp,
+		struct dpu_hw_tear_check *te)
+{
+	struct dpu_hw_blk_reg_map *c;
+	int cfg;
+
+	if (!pp || !te)
+		return -EINVAL;
+	c = &pp->hw;
+
+	cfg = BIT(19); /*VSYNC_COUNTER_EN */
+	if (te->hw_vsync_mode)
+		cfg |= BIT(20);
+
+	cfg |= te->vsync_count;
+
+	DPU_REG_WRITE(c, PP_SYNC_CONFIG_VSYNC, cfg);
+	DPU_REG_WRITE(c, PP_SYNC_CONFIG_HEIGHT, te->sync_cfg_height);
+	DPU_REG_WRITE(c, PP_VSYNC_INIT_VAL, te->vsync_init_val);
+	DPU_REG_WRITE(c, PP_RD_PTR_IRQ, te->rd_ptr_irq);
+	DPU_REG_WRITE(c, PP_START_POS, te->start_pos);
+	DPU_REG_WRITE(c, PP_SYNC_THRESH,
+			((te->sync_threshold_continue << 16) |
+			 te->sync_threshold_start));
+	DPU_REG_WRITE(c, PP_SYNC_WRCOUNT,
+			(te->start_pos + te->sync_threshold_start + 1));
+
+	return 0;
+}
+
+static int dpu_hw_pp_poll_timeout_wr_ptr(struct dpu_hw_pingpong *pp,
+		u32 timeout_us)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 val;
+	int rc;
+
+	if (!pp)
+		return -EINVAL;
+
+	c = &pp->hw;
+	rc = readl_poll_timeout(c->base_off + c->blk_off + PP_LINE_COUNT,
+			val, (val & 0xffff) >= 1, 10, timeout_us);
+
+	return rc;
+}
+
+static int dpu_hw_pp_enable_te(struct dpu_hw_pingpong *pp, bool enable)
+{
+	struct dpu_hw_blk_reg_map *c;
+
+	if (!pp)
+		return -EINVAL;
+	c = &pp->hw;
+
+	DPU_REG_WRITE(c, PP_TEAR_CHECK_EN, enable);
+	return 0;
+}
+
+static int dpu_hw_pp_connect_external_te(struct dpu_hw_pingpong *pp,
+		bool enable_external_te)
+{
+	struct dpu_hw_blk_reg_map *c = &pp->hw;
+	u32 cfg;
+	int orig;
+
+	if (!pp)
+		return -EINVAL;
+
+	c = &pp->hw;
+	cfg = DPU_REG_READ(c, PP_SYNC_CONFIG_VSYNC);
+	orig = (bool)(cfg & BIT(20));
+	if (enable_external_te)
+		cfg |= BIT(20);
+	else
+		cfg &= ~BIT(20);
+	DPU_REG_WRITE(c, PP_SYNC_CONFIG_VSYNC, cfg);
+	trace_dpu_pp_connect_ext_te(pp->idx - PINGPONG_0, cfg);
+
+	return orig;
+}
+
+static int dpu_hw_pp_get_vsync_info(struct dpu_hw_pingpong *pp,
+		struct dpu_hw_pp_vsync_info *info)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 val;
+
+	if (!pp || !info)
+		return -EINVAL;
+	c = &pp->hw;
+
+	val = DPU_REG_READ(c, PP_VSYNC_INIT_VAL);
+	info->rd_ptr_init_val = val & 0xffff;
+
+	val = DPU_REG_READ(c, PP_INT_COUNT_VAL);
+	info->rd_ptr_frame_count = (val & 0xffff0000) >> 16;
+	info->rd_ptr_line_count = val & 0xffff;
+
+	val = DPU_REG_READ(c, PP_LINE_COUNT);
+	info->wr_ptr_line_count = val & 0xffff;
+
+	return 0;
+}
+
+static u32 dpu_hw_pp_get_line_count(struct dpu_hw_pingpong *pp)
+{
+	struct dpu_hw_blk_reg_map *c = &pp->hw;
+	u32 height, init;
+	u32 line = 0xFFFF;
+
+	if (!pp)
+		return 0;
+	c = &pp->hw;
+
+	init = DPU_REG_READ(c, PP_VSYNC_INIT_VAL) & 0xFFFF;
+	height = DPU_REG_READ(c, PP_SYNC_CONFIG_HEIGHT) & 0xFFFF;
+
+	if (height < init)
+		goto line_count_exit;
+
+	line = DPU_REG_READ(c, PP_INT_COUNT_VAL) & 0xFFFF;
+
+	if (line < init)
+		line += (0xFFFF - init);
+	else
+		line -= init;
+
+line_count_exit:
+	return line;
+}
+
+static void _setup_pingpong_ops(struct dpu_hw_pingpong_ops *ops,
+	const struct dpu_pingpong_cfg *hw_cap)
+{
+	ops->setup_tearcheck = dpu_hw_pp_setup_te_config;
+	ops->enable_tearcheck = dpu_hw_pp_enable_te;
+	ops->connect_external_te = dpu_hw_pp_connect_external_te;
+	ops->get_vsync_info = dpu_hw_pp_get_vsync_info;
+	ops->poll_timeout_wr_ptr = dpu_hw_pp_poll_timeout_wr_ptr;
+	ops->get_line_count = dpu_hw_pp_get_line_count;
+};
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_pingpong *dpu_hw_pingpong_init(enum dpu_pingpong idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_pingpong *c;
+	struct dpu_pingpong_cfg *cfg;
+	int rc;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _pingpong_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		return ERR_PTR(-EINVAL);
+	}
+
+	c->idx = idx;
+	c->caps = cfg;
+	_setup_pingpong_ops(&c->ops, c->caps);
+
+	rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_PINGPONG, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	return c;
+
+blk_init_error:
+	kzfree(c);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_pingpong_destroy(struct dpu_hw_pingpong *pp)
+{
+	if (pp)
+		dpu_hw_blk_destroy(&pp->base);
+	kfree(pp);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
new file mode 100644
index 000000000000..3caccd7d6a3e
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
@@ -0,0 +1,136 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_PINGPONG_H
+#define _DPU_HW_PINGPONG_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_blk.h"
+
+struct dpu_hw_pingpong;
+
+struct dpu_hw_tear_check {
+	/*
+	 * This is ratio of MDP VSYNC clk freq(Hz) to
+	 * refresh rate divided by no of lines
+	 */
+	u32 vsync_count;
+	u32 sync_cfg_height;
+	u32 vsync_init_val;
+	u32 sync_threshold_start;
+	u32 sync_threshold_continue;
+	u32 start_pos;
+	u32 rd_ptr_irq;
+	u8 hw_vsync_mode;
+};
+
+struct dpu_hw_pp_vsync_info {
+	u32 rd_ptr_init_val;	/* value of rd pointer at vsync edge */
+	u32 rd_ptr_frame_count;	/* num frames sent since enabling interface */
+	u32 rd_ptr_line_count;	/* current line on panel (rd ptr) */
+	u32 wr_ptr_line_count;	/* current line within pp fifo (wr ptr) */
+};
+
+/**
+ *
+ * struct dpu_hw_pingpong_ops : Interface to the pingpong Hw driver functions
+ *  Assumption is these functions will be called after clocks are enabled
+ *  @setup_tearcheck : program tear check values
+ *  @enable_tearcheck : enables tear check
+ *  @get_vsync_info : retries timing info of the panel
+ *  @setup_dither : function to program the dither hw block
+ *  @get_line_count: obtain current vertical line counter
+ */
+struct dpu_hw_pingpong_ops {
+	/**
+	 * enables vysnc generation and sets up init value of
+	 * read pointer and programs the tear check cofiguration
+	 */
+	int (*setup_tearcheck)(struct dpu_hw_pingpong *pp,
+			struct dpu_hw_tear_check *cfg);
+
+	/**
+	 * enables tear check block
+	 */
+	int (*enable_tearcheck)(struct dpu_hw_pingpong *pp,
+			bool enable);
+
+	/**
+	 * read, modify, write to either set or clear listening to external TE
+	 * @Return: 1 if TE was originally connected, 0 if not, or -ERROR
+	 */
+	int (*connect_external_te)(struct dpu_hw_pingpong *pp,
+			bool enable_external_te);
+
+	/**
+	 * provides the programmed and current
+	 * line_count
+	 */
+	int (*get_vsync_info)(struct dpu_hw_pingpong *pp,
+			struct dpu_hw_pp_vsync_info  *info);
+
+	/**
+	 * poll until write pointer transmission starts
+	 * @Return: 0 on success, -ETIMEDOUT on timeout
+	 */
+	int (*poll_timeout_wr_ptr)(struct dpu_hw_pingpong *pp, u32 timeout_us);
+
+	/**
+	 * Obtain current vertical line counter
+	 */
+	u32 (*get_line_count)(struct dpu_hw_pingpong *pp);
+};
+
+struct dpu_hw_pingpong {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* pingpong */
+	enum dpu_pingpong idx;
+	const struct dpu_pingpong_cfg *caps;
+
+	/* ops */
+	struct dpu_hw_pingpong_ops ops;
+};
+
+/**
+ * dpu_hw_pingpong - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_pingpong *to_dpu_hw_pingpong(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_pingpong, base);
+}
+
+/**
+ * dpu_hw_pingpong_init - initializes the pingpong driver for the passed
+ *	pingpong idx.
+ * @idx:  Pingpong index for which driver object is required
+ * @addr: Mapped register io address of MDP
+ * @m:    Pointer to mdss catalog data
+ * Returns: Error code or allocated dpu_hw_pingpong context
+ */
+struct dpu_hw_pingpong *dpu_hw_pingpong_init(enum dpu_pingpong idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_pingpong_destroy - destroys pingpong driver context
+ *	should be called to free the context
+ * @pp:   Pointer to PP driver context returned by dpu_hw_pingpong_init
+ */
+void dpu_hw_pingpong_destroy(struct dpu_hw_pingpong *pp);
+
+#endif /*_DPU_HW_PINGPONG_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
new file mode 100644
index 000000000000..c25b52a6b219
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
@@ -0,0 +1,753 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_sspp.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+
+#define DPU_FETCH_CONFIG_RESET_VALUE   0x00000087
+
+/* DPU_SSPP_SRC */
+#define SSPP_SRC_SIZE                      0x00
+#define SSPP_SRC_XY                        0x08
+#define SSPP_OUT_SIZE                      0x0c
+#define SSPP_OUT_XY                        0x10
+#define SSPP_SRC0_ADDR                     0x14
+#define SSPP_SRC1_ADDR                     0x18
+#define SSPP_SRC2_ADDR                     0x1C
+#define SSPP_SRC3_ADDR                     0x20
+#define SSPP_SRC_YSTRIDE0                  0x24
+#define SSPP_SRC_YSTRIDE1                  0x28
+#define SSPP_SRC_FORMAT                    0x30
+#define SSPP_SRC_UNPACK_PATTERN            0x34
+#define SSPP_SRC_OP_MODE                   0x38
+
+/* SSPP_MULTIRECT*/
+#define SSPP_SRC_SIZE_REC1                 0x16C
+#define SSPP_SRC_XY_REC1                   0x168
+#define SSPP_OUT_SIZE_REC1                 0x160
+#define SSPP_OUT_XY_REC1                   0x164
+#define SSPP_SRC_FORMAT_REC1               0x174
+#define SSPP_SRC_UNPACK_PATTERN_REC1       0x178
+#define SSPP_SRC_OP_MODE_REC1              0x17C
+#define SSPP_MULTIRECT_OPMODE              0x170
+#define SSPP_SRC_CONSTANT_COLOR_REC1       0x180
+#define SSPP_EXCL_REC_SIZE_REC1            0x184
+#define SSPP_EXCL_REC_XY_REC1              0x188
+
+#define MDSS_MDP_OP_DEINTERLACE            BIT(22)
+#define MDSS_MDP_OP_DEINTERLACE_ODD        BIT(23)
+#define MDSS_MDP_OP_IGC_ROM_1              BIT(18)
+#define MDSS_MDP_OP_IGC_ROM_0              BIT(17)
+#define MDSS_MDP_OP_IGC_EN                 BIT(16)
+#define MDSS_MDP_OP_FLIP_UD                BIT(14)
+#define MDSS_MDP_OP_FLIP_LR                BIT(13)
+#define MDSS_MDP_OP_BWC_EN                 BIT(0)
+#define MDSS_MDP_OP_PE_OVERRIDE            BIT(31)
+#define MDSS_MDP_OP_BWC_LOSSLESS           (0 << 1)
+#define MDSS_MDP_OP_BWC_Q_HIGH             (1 << 1)
+#define MDSS_MDP_OP_BWC_Q_MED              (2 << 1)
+
+#define SSPP_SRC_CONSTANT_COLOR            0x3c
+#define SSPP_EXCL_REC_CTL                  0x40
+#define SSPP_UBWC_STATIC_CTRL              0x44
+#define SSPP_FETCH_CONFIG                  0x048
+#define SSPP_DANGER_LUT                    0x60
+#define SSPP_SAFE_LUT                      0x64
+#define SSPP_CREQ_LUT                      0x68
+#define SSPP_QOS_CTRL                      0x6C
+#define SSPP_DECIMATION_CONFIG             0xB4
+#define SSPP_SRC_ADDR_SW_STATUS            0x70
+#define SSPP_CREQ_LUT_0                    0x74
+#define SSPP_CREQ_LUT_1                    0x78
+#define SSPP_SW_PIX_EXT_C0_LR              0x100
+#define SSPP_SW_PIX_EXT_C0_TB              0x104
+#define SSPP_SW_PIX_EXT_C0_REQ_PIXELS      0x108
+#define SSPP_SW_PIX_EXT_C1C2_LR            0x110
+#define SSPP_SW_PIX_EXT_C1C2_TB            0x114
+#define SSPP_SW_PIX_EXT_C1C2_REQ_PIXELS    0x118
+#define SSPP_SW_PIX_EXT_C3_LR              0x120
+#define SSPP_SW_PIX_EXT_C3_TB              0x124
+#define SSPP_SW_PIX_EXT_C3_REQ_PIXELS      0x128
+#define SSPP_TRAFFIC_SHAPER                0x130
+#define SSPP_CDP_CNTL                      0x134
+#define SSPP_UBWC_ERROR_STATUS             0x138
+#define SSPP_TRAFFIC_SHAPER_PREFILL        0x150
+#define SSPP_TRAFFIC_SHAPER_REC1_PREFILL   0x154
+#define SSPP_TRAFFIC_SHAPER_REC1           0x158
+#define SSPP_EXCL_REC_SIZE                 0x1B4
+#define SSPP_EXCL_REC_XY                   0x1B8
+#define SSPP_VIG_OP_MODE                   0x0
+#define SSPP_VIG_CSC_10_OP_MODE            0x0
+#define SSPP_TRAFFIC_SHAPER_BPC_MAX        0xFF
+
+/* SSPP_QOS_CTRL */
+#define SSPP_QOS_CTRL_VBLANK_EN            BIT(16)
+#define SSPP_QOS_CTRL_DANGER_SAFE_EN       BIT(0)
+#define SSPP_QOS_CTRL_DANGER_VBLANK_MASK   0x3
+#define SSPP_QOS_CTRL_DANGER_VBLANK_OFF    4
+#define SSPP_QOS_CTRL_CREQ_VBLANK_MASK     0x3
+#define SSPP_QOS_CTRL_CREQ_VBLANK_OFF      20
+
+/* DPU_SSPP_SCALER_QSEED2 */
+#define SCALE_CONFIG                       0x04
+#define COMP0_3_PHASE_STEP_X               0x10
+#define COMP0_3_PHASE_STEP_Y               0x14
+#define COMP1_2_PHASE_STEP_X               0x18
+#define COMP1_2_PHASE_STEP_Y               0x1c
+#define COMP0_3_INIT_PHASE_X               0x20
+#define COMP0_3_INIT_PHASE_Y               0x24
+#define COMP1_2_INIT_PHASE_X               0x28
+#define COMP1_2_INIT_PHASE_Y               0x2C
+#define VIG_0_QSEED2_SHARP                 0x30
+
+/*
+ * Definitions for ViG op modes
+ */
+#define VIG_OP_CSC_DST_DATAFMT BIT(19)
+#define VIG_OP_CSC_SRC_DATAFMT BIT(18)
+#define VIG_OP_CSC_EN          BIT(17)
+#define VIG_OP_MEM_PROT_CONT   BIT(15)
+#define VIG_OP_MEM_PROT_VAL    BIT(14)
+#define VIG_OP_MEM_PROT_SAT    BIT(13)
+#define VIG_OP_MEM_PROT_HUE    BIT(12)
+#define VIG_OP_HIST            BIT(8)
+#define VIG_OP_SKY_COL         BIT(7)
+#define VIG_OP_FOIL            BIT(6)
+#define VIG_OP_SKIN_COL        BIT(5)
+#define VIG_OP_PA_EN           BIT(4)
+#define VIG_OP_PA_SAT_ZERO_EXP BIT(2)
+#define VIG_OP_MEM_PROT_BLEND  BIT(1)
+
+/*
+ * Definitions for CSC 10 op modes
+ */
+#define VIG_CSC_10_SRC_DATAFMT BIT(1)
+#define VIG_CSC_10_EN          BIT(0)
+#define CSC_10BIT_OFFSET       4
+
+/* traffic shaper clock in Hz */
+#define TS_CLK			19200000
+
+static inline int _sspp_subblk_offset(struct dpu_hw_pipe *ctx,
+		int s_id,
+		u32 *idx)
+{
+	int rc = 0;
+	const struct dpu_sspp_sub_blks *sblk = ctx->cap->sblk;
+
+	if (!ctx)
+		return -EINVAL;
+
+	switch (s_id) {
+	case DPU_SSPP_SRC:
+		*idx = sblk->src_blk.base;
+		break;
+	case DPU_SSPP_SCALER_QSEED2:
+	case DPU_SSPP_SCALER_QSEED3:
+	case DPU_SSPP_SCALER_RGB:
+		*idx = sblk->scaler_blk.base;
+		break;
+	case DPU_SSPP_CSC:
+	case DPU_SSPP_CSC_10BIT:
+		*idx = sblk->csc_blk.base;
+		break;
+	default:
+		rc = -EINVAL;
+	}
+
+	return rc;
+}
+
+static void dpu_hw_sspp_setup_multirect(struct dpu_hw_pipe *ctx,
+		enum dpu_sspp_multirect_index index,
+		enum dpu_sspp_multirect_mode mode)
+{
+	u32 mode_mask;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (index == DPU_SSPP_RECT_SOLO) {
+		/**
+		 * if rect index is RECT_SOLO, we cannot expect a
+		 * virtual plane sharing the same SSPP id. So we go
+		 * and disable multirect
+		 */
+		mode_mask = 0;
+	} else {
+		mode_mask = DPU_REG_READ(&ctx->hw, SSPP_MULTIRECT_OPMODE + idx);
+		mode_mask |= index;
+		if (mode == DPU_SSPP_MULTIRECT_TIME_MX)
+			mode_mask |= BIT(2);
+		else
+			mode_mask &= ~BIT(2);
+	}
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_MULTIRECT_OPMODE + idx, mode_mask);
+}
+
+static void _sspp_setup_opmode(struct dpu_hw_pipe *ctx,
+		u32 mask, u8 en)
+{
+	u32 idx;
+	u32 opmode;
+
+	if (!test_bit(DPU_SSPP_SCALER_QSEED2, &ctx->cap->features) ||
+		_sspp_subblk_offset(ctx, DPU_SSPP_SCALER_QSEED2, &idx) ||
+		!test_bit(DPU_SSPP_CSC, &ctx->cap->features))
+		return;
+
+	opmode = DPU_REG_READ(&ctx->hw, SSPP_VIG_OP_MODE + idx);
+
+	if (en)
+		opmode |= mask;
+	else
+		opmode &= ~mask;
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_VIG_OP_MODE + idx, opmode);
+}
+
+static void _sspp_setup_csc10_opmode(struct dpu_hw_pipe *ctx,
+		u32 mask, u8 en)
+{
+	u32 idx;
+	u32 opmode;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_CSC_10BIT, &idx))
+		return;
+
+	opmode = DPU_REG_READ(&ctx->hw, SSPP_VIG_CSC_10_OP_MODE + idx);
+	if (en)
+		opmode |= mask;
+	else
+		opmode &= ~mask;
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_VIG_CSC_10_OP_MODE + idx, opmode);
+}
+
+/**
+ * Setup source pixel format, flip,
+ */
+static void dpu_hw_sspp_setup_format(struct dpu_hw_pipe *ctx,
+		const struct dpu_format *fmt, u32 flags,
+		enum dpu_sspp_multirect_index rect_mode)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 chroma_samp, unpack, src_format;
+	u32 opmode = 0;
+	u32 fast_clear = 0;
+	u32 op_mode_off, unpack_pat_off, format_off;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx) || !fmt)
+		return;
+
+	if (rect_mode == DPU_SSPP_RECT_SOLO || rect_mode == DPU_SSPP_RECT_0) {
+		op_mode_off = SSPP_SRC_OP_MODE;
+		unpack_pat_off = SSPP_SRC_UNPACK_PATTERN;
+		format_off = SSPP_SRC_FORMAT;
+	} else {
+		op_mode_off = SSPP_SRC_OP_MODE_REC1;
+		unpack_pat_off = SSPP_SRC_UNPACK_PATTERN_REC1;
+		format_off = SSPP_SRC_FORMAT_REC1;
+	}
+
+	c = &ctx->hw;
+	opmode = DPU_REG_READ(c, op_mode_off + idx);
+	opmode &= ~(MDSS_MDP_OP_FLIP_LR | MDSS_MDP_OP_FLIP_UD |
+			MDSS_MDP_OP_BWC_EN | MDSS_MDP_OP_PE_OVERRIDE);
+
+	if (flags & DPU_SSPP_FLIP_LR)
+		opmode |= MDSS_MDP_OP_FLIP_LR;
+	if (flags & DPU_SSPP_FLIP_UD)
+		opmode |= MDSS_MDP_OP_FLIP_UD;
+
+	chroma_samp = fmt->chroma_sample;
+	if (flags & DPU_SSPP_SOURCE_ROTATED_90) {
+		if (chroma_samp == DPU_CHROMA_H2V1)
+			chroma_samp = DPU_CHROMA_H1V2;
+		else if (chroma_samp == DPU_CHROMA_H1V2)
+			chroma_samp = DPU_CHROMA_H2V1;
+	}
+
+	src_format = (chroma_samp << 23) | (fmt->fetch_planes << 19) |
+		(fmt->bits[C3_ALPHA] << 6) | (fmt->bits[C2_R_Cr] << 4) |
+		(fmt->bits[C1_B_Cb] << 2) | (fmt->bits[C0_G_Y] << 0);
+
+	if (flags & DPU_SSPP_ROT_90)
+		src_format |= BIT(11); /* ROT90 */
+
+	if (fmt->alpha_enable && fmt->fetch_planes == DPU_PLANE_INTERLEAVED)
+		src_format |= BIT(8); /* SRCC3_EN */
+
+	if (flags & DPU_SSPP_SOLID_FILL)
+		src_format |= BIT(22);
+
+	unpack = (fmt->element[3] << 24) | (fmt->element[2] << 16) |
+		(fmt->element[1] << 8) | (fmt->element[0] << 0);
+	src_format |= ((fmt->unpack_count - 1) << 12) |
+		(fmt->unpack_tight << 17) |
+		(fmt->unpack_align_msb << 18) |
+		((fmt->bpp - 1) << 9);
+
+	if (fmt->fetch_mode != DPU_FETCH_LINEAR) {
+		if (DPU_FORMAT_IS_UBWC(fmt))
+			opmode |= MDSS_MDP_OP_BWC_EN;
+		src_format |= (fmt->fetch_mode & 3) << 30; /*FRAME_FORMAT */
+		DPU_REG_WRITE(c, SSPP_FETCH_CONFIG,
+			DPU_FETCH_CONFIG_RESET_VALUE |
+			ctx->mdp->highest_bank_bit << 18);
+		if (IS_UBWC_20_SUPPORTED(ctx->catalog->caps->ubwc_version)) {
+			fast_clear = fmt->alpha_enable ? BIT(31) : 0;
+			DPU_REG_WRITE(c, SSPP_UBWC_STATIC_CTRL,
+					fast_clear | (ctx->mdp->ubwc_swizzle) |
+					(ctx->mdp->highest_bank_bit << 4));
+		}
+	}
+
+	opmode |= MDSS_MDP_OP_PE_OVERRIDE;
+
+	/* if this is YUV pixel format, enable CSC */
+	if (DPU_FORMAT_IS_YUV(fmt))
+		src_format |= BIT(15);
+
+	if (DPU_FORMAT_IS_DX(fmt))
+		src_format |= BIT(14);
+
+	/* update scaler opmode, if appropriate */
+	if (test_bit(DPU_SSPP_CSC, &ctx->cap->features))
+		_sspp_setup_opmode(ctx, VIG_OP_CSC_EN | VIG_OP_CSC_SRC_DATAFMT,
+			DPU_FORMAT_IS_YUV(fmt));
+	else if (test_bit(DPU_SSPP_CSC_10BIT, &ctx->cap->features))
+		_sspp_setup_csc10_opmode(ctx,
+			VIG_CSC_10_EN | VIG_CSC_10_SRC_DATAFMT,
+			DPU_FORMAT_IS_YUV(fmt));
+
+	DPU_REG_WRITE(c, format_off + idx, src_format);
+	DPU_REG_WRITE(c, unpack_pat_off + idx, unpack);
+	DPU_REG_WRITE(c, op_mode_off + idx, opmode);
+
+	/* clear previous UBWC error */
+	DPU_REG_WRITE(c, SSPP_UBWC_ERROR_STATUS + idx, BIT(31));
+}
+
+static void dpu_hw_sspp_setup_pe_config(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pixel_ext *pe_ext)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u8 color;
+	u32 lr_pe[4], tb_pe[4], tot_req_pixels[4];
+	const u32 bytemask = 0xff;
+	const u32 shortmask = 0xffff;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx) || !pe_ext)
+		return;
+
+	c = &ctx->hw;
+
+	/* program SW pixel extension override for all pipes*/
+	for (color = 0; color < DPU_MAX_PLANES; color++) {
+		/* color 2 has the same set of registers as color 1 */
+		if (color == 2)
+			continue;
+
+		lr_pe[color] = ((pe_ext->right_ftch[color] & bytemask) << 24)|
+			((pe_ext->right_rpt[color] & bytemask) << 16)|
+			((pe_ext->left_ftch[color] & bytemask) << 8)|
+			(pe_ext->left_rpt[color] & bytemask);
+
+		tb_pe[color] = ((pe_ext->btm_ftch[color] & bytemask) << 24)|
+			((pe_ext->btm_rpt[color] & bytemask) << 16)|
+			((pe_ext->top_ftch[color] & bytemask) << 8)|
+			(pe_ext->top_rpt[color] & bytemask);
+
+		tot_req_pixels[color] = (((pe_ext->roi_h[color] +
+			pe_ext->num_ext_pxls_top[color] +
+			pe_ext->num_ext_pxls_btm[color]) & shortmask) << 16) |
+			((pe_ext->roi_w[color] +
+			pe_ext->num_ext_pxls_left[color] +
+			pe_ext->num_ext_pxls_right[color]) & shortmask);
+	}
+
+	/* color 0 */
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C0_LR + idx, lr_pe[0]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C0_TB + idx, tb_pe[0]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C0_REQ_PIXELS + idx,
+			tot_req_pixels[0]);
+
+	/* color 1 and color 2 */
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C1C2_LR + idx, lr_pe[1]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C1C2_TB + idx, tb_pe[1]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C1C2_REQ_PIXELS + idx,
+			tot_req_pixels[1]);
+
+	/* color 3 */
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C3_LR + idx, lr_pe[3]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C3_TB + idx, lr_pe[3]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C3_REQ_PIXELS + idx,
+			tot_req_pixels[3]);
+}
+
+static void _dpu_hw_sspp_setup_scaler3(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_cfg *sspp,
+		struct dpu_hw_pixel_ext *pe,
+		void *scaler_cfg)
+{
+	u32 idx;
+	struct dpu_hw_scaler3_cfg *scaler3_cfg = scaler_cfg;
+
+	(void)pe;
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SCALER_QSEED3, &idx) || !sspp
+		|| !scaler3_cfg || !ctx || !ctx->cap || !ctx->cap->sblk)
+		return;
+
+	dpu_hw_setup_scaler3(&ctx->hw, scaler3_cfg, idx,
+			ctx->cap->sblk->scaler_blk.version,
+			sspp->layout.format);
+}
+
+static u32 _dpu_hw_sspp_get_scaler3_ver(struct dpu_hw_pipe *ctx)
+{
+	u32 idx;
+
+	if (!ctx || _sspp_subblk_offset(ctx, DPU_SSPP_SCALER_QSEED3, &idx))
+		return 0;
+
+	return dpu_hw_get_scaler3_ver(&ctx->hw, idx);
+}
+
+/**
+ * dpu_hw_sspp_setup_rects()
+ */
+static void dpu_hw_sspp_setup_rects(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_cfg *cfg,
+		enum dpu_sspp_multirect_index rect_index)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 src_size, src_xy, dst_size, dst_xy, ystride0, ystride1;
+	u32 src_size_off, src_xy_off, out_size_off, out_xy_off;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx) || !cfg)
+		return;
+
+	c = &ctx->hw;
+
+	if (rect_index == DPU_SSPP_RECT_SOLO || rect_index == DPU_SSPP_RECT_0) {
+		src_size_off = SSPP_SRC_SIZE;
+		src_xy_off = SSPP_SRC_XY;
+		out_size_off = SSPP_OUT_SIZE;
+		out_xy_off = SSPP_OUT_XY;
+	} else {
+		src_size_off = SSPP_SRC_SIZE_REC1;
+		src_xy_off = SSPP_SRC_XY_REC1;
+		out_size_off = SSPP_OUT_SIZE_REC1;
+		out_xy_off = SSPP_OUT_XY_REC1;
+	}
+
+
+	/* src and dest rect programming */
+	src_xy = (cfg->src_rect.y1 << 16) | cfg->src_rect.x1;
+	src_size = (drm_rect_height(&cfg->src_rect) << 16) |
+		   drm_rect_width(&cfg->src_rect);
+	dst_xy = (cfg->dst_rect.y1 << 16) | cfg->dst_rect.x1;
+	dst_size = (drm_rect_height(&cfg->dst_rect) << 16) |
+		drm_rect_width(&cfg->dst_rect);
+
+	if (rect_index == DPU_SSPP_RECT_SOLO) {
+		ystride0 = (cfg->layout.plane_pitch[0]) |
+			(cfg->layout.plane_pitch[1] << 16);
+		ystride1 = (cfg->layout.plane_pitch[2]) |
+			(cfg->layout.plane_pitch[3] << 16);
+	} else {
+		ystride0 = DPU_REG_READ(c, SSPP_SRC_YSTRIDE0 + idx);
+		ystride1 = DPU_REG_READ(c, SSPP_SRC_YSTRIDE1 + idx);
+
+		if (rect_index == DPU_SSPP_RECT_0) {
+			ystride0 = (ystride0 & 0xFFFF0000) |
+				(cfg->layout.plane_pitch[0] & 0x0000FFFF);
+			ystride1 = (ystride1 & 0xFFFF0000)|
+				(cfg->layout.plane_pitch[2] & 0x0000FFFF);
+		} else {
+			ystride0 = (ystride0 & 0x0000FFFF) |
+				((cfg->layout.plane_pitch[0] << 16) &
+				 0xFFFF0000);
+			ystride1 = (ystride1 & 0x0000FFFF) |
+				((cfg->layout.plane_pitch[2] << 16) &
+				 0xFFFF0000);
+		}
+	}
+
+	/* rectangle register programming */
+	DPU_REG_WRITE(c, src_size_off + idx, src_size);
+	DPU_REG_WRITE(c, src_xy_off + idx, src_xy);
+	DPU_REG_WRITE(c, out_size_off + idx, dst_size);
+	DPU_REG_WRITE(c, out_xy_off + idx, dst_xy);
+
+	DPU_REG_WRITE(c, SSPP_SRC_YSTRIDE0 + idx, ystride0);
+	DPU_REG_WRITE(c, SSPP_SRC_YSTRIDE1 + idx, ystride1);
+}
+
+static void dpu_hw_sspp_setup_sourceaddress(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_cfg *cfg,
+		enum dpu_sspp_multirect_index rect_mode)
+{
+	int i;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (rect_mode == DPU_SSPP_RECT_SOLO) {
+		for (i = 0; i < ARRAY_SIZE(cfg->layout.plane_addr); i++)
+			DPU_REG_WRITE(&ctx->hw, SSPP_SRC0_ADDR + idx + i * 0x4,
+					cfg->layout.plane_addr[i]);
+	} else if (rect_mode == DPU_SSPP_RECT_0) {
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC0_ADDR + idx,
+				cfg->layout.plane_addr[0]);
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC2_ADDR + idx,
+				cfg->layout.plane_addr[2]);
+	} else {
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC1_ADDR + idx,
+				cfg->layout.plane_addr[0]);
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC3_ADDR + idx,
+				cfg->layout.plane_addr[2]);
+	}
+}
+
+static void dpu_hw_sspp_setup_csc(struct dpu_hw_pipe *ctx,
+		struct dpu_csc_cfg *data)
+{
+	u32 idx;
+	bool csc10 = false;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_CSC, &idx) || !data)
+		return;
+
+	if (test_bit(DPU_SSPP_CSC_10BIT, &ctx->cap->features)) {
+		idx += CSC_10BIT_OFFSET;
+		csc10 = true;
+	}
+
+	dpu_hw_csc_setup(&ctx->hw, idx, data, csc10);
+}
+
+static void dpu_hw_sspp_setup_solidfill(struct dpu_hw_pipe *ctx, u32 color, enum
+		dpu_sspp_multirect_index rect_index)
+{
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (rect_index == DPU_SSPP_RECT_SOLO || rect_index == DPU_SSPP_RECT_0)
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC_CONSTANT_COLOR + idx, color);
+	else
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC_CONSTANT_COLOR_REC1 + idx,
+				color);
+}
+
+static void dpu_hw_sspp_setup_danger_safe_lut(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_qos_cfg *cfg)
+{
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_DANGER_LUT + idx, cfg->danger_lut);
+	DPU_REG_WRITE(&ctx->hw, SSPP_SAFE_LUT + idx, cfg->safe_lut);
+}
+
+static void dpu_hw_sspp_setup_creq_lut(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_qos_cfg *cfg)
+{
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (ctx->cap && test_bit(DPU_SSPP_QOS_8LVL, &ctx->cap->features)) {
+		DPU_REG_WRITE(&ctx->hw, SSPP_CREQ_LUT_0 + idx, cfg->creq_lut);
+		DPU_REG_WRITE(&ctx->hw, SSPP_CREQ_LUT_1 + idx,
+				cfg->creq_lut >> 32);
+	} else {
+		DPU_REG_WRITE(&ctx->hw, SSPP_CREQ_LUT + idx, cfg->creq_lut);
+	}
+}
+
+static void dpu_hw_sspp_setup_qos_ctrl(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_qos_cfg *cfg)
+{
+	u32 idx;
+	u32 qos_ctrl = 0;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (cfg->vblank_en) {
+		qos_ctrl |= ((cfg->creq_vblank &
+				SSPP_QOS_CTRL_CREQ_VBLANK_MASK) <<
+				SSPP_QOS_CTRL_CREQ_VBLANK_OFF);
+		qos_ctrl |= ((cfg->danger_vblank &
+				SSPP_QOS_CTRL_DANGER_VBLANK_MASK) <<
+				SSPP_QOS_CTRL_DANGER_VBLANK_OFF);
+		qos_ctrl |= SSPP_QOS_CTRL_VBLANK_EN;
+	}
+
+	if (cfg->danger_safe_en)
+		qos_ctrl |= SSPP_QOS_CTRL_DANGER_SAFE_EN;
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_QOS_CTRL + idx, qos_ctrl);
+}
+
+static void dpu_hw_sspp_setup_cdp(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_cdp_cfg *cfg)
+{
+	u32 idx;
+	u32 cdp_cntl = 0;
+
+	if (!ctx || !cfg)
+		return;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (cfg->enable)
+		cdp_cntl |= BIT(0);
+	if (cfg->ubwc_meta_enable)
+		cdp_cntl |= BIT(1);
+	if (cfg->tile_amortize_enable)
+		cdp_cntl |= BIT(2);
+	if (cfg->preload_ahead == DPU_SSPP_CDP_PRELOAD_AHEAD_64)
+		cdp_cntl |= BIT(3);
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_CDP_CNTL, cdp_cntl);
+}
+
+static void _setup_layer_ops(struct dpu_hw_pipe *c,
+		unsigned long features)
+{
+	if (test_bit(DPU_SSPP_SRC, &features)) {
+		c->ops.setup_format = dpu_hw_sspp_setup_format;
+		c->ops.setup_rects = dpu_hw_sspp_setup_rects;
+		c->ops.setup_sourceaddress = dpu_hw_sspp_setup_sourceaddress;
+		c->ops.setup_solidfill = dpu_hw_sspp_setup_solidfill;
+		c->ops.setup_pe = dpu_hw_sspp_setup_pe_config;
+	}
+
+	if (test_bit(DPU_SSPP_QOS, &features)) {
+		c->ops.setup_danger_safe_lut =
+			dpu_hw_sspp_setup_danger_safe_lut;
+		c->ops.setup_creq_lut = dpu_hw_sspp_setup_creq_lut;
+		c->ops.setup_qos_ctrl = dpu_hw_sspp_setup_qos_ctrl;
+	}
+
+	if (test_bit(DPU_SSPP_CSC, &features) ||
+		test_bit(DPU_SSPP_CSC_10BIT, &features))
+		c->ops.setup_csc = dpu_hw_sspp_setup_csc;
+
+	if (dpu_hw_sspp_multirect_enabled(c->cap))
+		c->ops.setup_multirect = dpu_hw_sspp_setup_multirect;
+
+	if (test_bit(DPU_SSPP_SCALER_QSEED3, &features)) {
+		c->ops.setup_scaler = _dpu_hw_sspp_setup_scaler3;
+		c->ops.get_scaler_ver = _dpu_hw_sspp_get_scaler3_ver;
+	}
+
+	if (test_bit(DPU_SSPP_CDP, &features))
+		c->ops.setup_cdp = dpu_hw_sspp_setup_cdp;
+}
+
+static struct dpu_sspp_cfg *_sspp_offset(enum dpu_sspp sspp,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *catalog,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	if ((sspp < SSPP_MAX) && catalog && addr && b) {
+		for (i = 0; i < catalog->sspp_count; i++) {
+			if (sspp == catalog->sspp[i].id) {
+				b->base_off = addr;
+				b->blk_off = catalog->sspp[i].base;
+				b->length = catalog->sspp[i].len;
+				b->hwversion = catalog->hwversion;
+				b->log_mask = DPU_DBG_MASK_SSPP;
+				return &catalog->sspp[i];
+			}
+		}
+	}
+
+	return ERR_PTR(-ENOMEM);
+}
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_pipe *dpu_hw_sspp_init(enum dpu_sspp idx,
+		void __iomem *addr, struct dpu_mdss_cfg *catalog,
+		bool is_virtual_pipe)
+{
+	struct dpu_hw_pipe *hw_pipe;
+	struct dpu_sspp_cfg *cfg;
+	int rc;
+
+	if (!addr || !catalog)
+		return ERR_PTR(-EINVAL);
+
+	hw_pipe = kzalloc(sizeof(*hw_pipe), GFP_KERNEL);
+	if (!hw_pipe)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _sspp_offset(idx, addr, catalog, &hw_pipe->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(hw_pipe);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* Assign ops */
+	hw_pipe->catalog = catalog;
+	hw_pipe->mdp = &catalog->mdp[0];
+	hw_pipe->idx = idx;
+	hw_pipe->cap = cfg;
+	_setup_layer_ops(hw_pipe, hw_pipe->cap->features);
+
+	rc = dpu_hw_blk_init(&hw_pipe->base, DPU_HW_BLK_SSPP, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	return hw_pipe;
+
+blk_init_error:
+	kzfree(hw_pipe);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_sspp_destroy(struct dpu_hw_pipe *ctx)
+{
+	if (ctx)
+		dpu_hw_blk_destroy(&ctx->base);
+	kfree(ctx);
+}
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
new file mode 100644
index 000000000000..4d81e5f5ce1b
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
@@ -0,0 +1,424 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_SSPP_H
+#define _DPU_HW_SSPP_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_blk.h"
+#include "dpu_formats.h"
+
+struct dpu_hw_pipe;
+
+/**
+ * Flags
+ */
+#define DPU_SSPP_FLIP_LR		BIT(0)
+#define DPU_SSPP_FLIP_UD		BIT(1)
+#define DPU_SSPP_SOURCE_ROTATED_90	BIT(2)
+#define DPU_SSPP_ROT_90			BIT(3)
+#define DPU_SSPP_SOLID_FILL		BIT(4)
+
+/**
+ * Define all scaler feature bits in catalog
+ */
+#define DPU_SSPP_SCALER ((1UL << DPU_SSPP_SCALER_RGB) | \
+	(1UL << DPU_SSPP_SCALER_QSEED2) | \
+	(1UL << DPU_SSPP_SCALER_QSEED3))
+
+/**
+ * Component indices
+ */
+enum {
+	DPU_SSPP_COMP_0,
+	DPU_SSPP_COMP_1_2,
+	DPU_SSPP_COMP_2,
+	DPU_SSPP_COMP_3,
+
+	DPU_SSPP_COMP_MAX
+};
+
+/**
+ * DPU_SSPP_RECT_SOLO - multirect disabled
+ * DPU_SSPP_RECT_0 - rect0 of a multirect pipe
+ * DPU_SSPP_RECT_1 - rect1 of a multirect pipe
+ *
+ * Note: HW supports multirect with either RECT0 or
+ * RECT1. Considering no benefit of such configs over
+ * SOLO mode and to keep the plane management simple,
+ * we dont support single rect multirect configs.
+ */
+enum dpu_sspp_multirect_index {
+	DPU_SSPP_RECT_SOLO = 0,
+	DPU_SSPP_RECT_0,
+	DPU_SSPP_RECT_1,
+};
+
+enum dpu_sspp_multirect_mode {
+	DPU_SSPP_MULTIRECT_NONE = 0,
+	DPU_SSPP_MULTIRECT_PARALLEL,
+	DPU_SSPP_MULTIRECT_TIME_MX,
+};
+
+enum {
+	DPU_FRAME_LINEAR,
+	DPU_FRAME_TILE_A4X,
+	DPU_FRAME_TILE_A5X,
+};
+
+enum dpu_hw_filter {
+	DPU_SCALE_FILTER_NEAREST = 0,
+	DPU_SCALE_FILTER_BIL,
+	DPU_SCALE_FILTER_PCMN,
+	DPU_SCALE_FILTER_CA,
+	DPU_SCALE_FILTER_MAX
+};
+
+enum dpu_hw_filter_alpa {
+	DPU_SCALE_ALPHA_PIXEL_REP,
+	DPU_SCALE_ALPHA_BIL
+};
+
+enum dpu_hw_filter_yuv {
+	DPU_SCALE_2D_4X4,
+	DPU_SCALE_2D_CIR,
+	DPU_SCALE_1D_SEP,
+	DPU_SCALE_BIL
+};
+
+struct dpu_hw_sharp_cfg {
+	u32 strength;
+	u32 edge_thr;
+	u32 smooth_thr;
+	u32 noise_thr;
+};
+
+struct dpu_hw_pixel_ext {
+	/* scaling factors are enabled for this input layer */
+	uint8_t enable_pxl_ext;
+
+	int init_phase_x[DPU_MAX_PLANES];
+	int phase_step_x[DPU_MAX_PLANES];
+	int init_phase_y[DPU_MAX_PLANES];
+	int phase_step_y[DPU_MAX_PLANES];
+
+	/*
+	 * Number of pixels extension in left, right, top and bottom direction
+	 * for all color components. This pixel value for each color component
+	 * should be sum of fetch + repeat pixels.
+	 */
+	int num_ext_pxls_left[DPU_MAX_PLANES];
+	int num_ext_pxls_right[DPU_MAX_PLANES];
+	int num_ext_pxls_top[DPU_MAX_PLANES];
+	int num_ext_pxls_btm[DPU_MAX_PLANES];
+
+	/*
+	 * Number of pixels needs to be overfetched in left, right, top and
+	 * bottom directions from source image for scaling.
+	 */
+	int left_ftch[DPU_MAX_PLANES];
+	int right_ftch[DPU_MAX_PLANES];
+	int top_ftch[DPU_MAX_PLANES];
+	int btm_ftch[DPU_MAX_PLANES];
+
+	/*
+	 * Number of pixels needs to be repeated in left, right, top and
+	 * bottom directions for scaling.
+	 */
+	int left_rpt[DPU_MAX_PLANES];
+	int right_rpt[DPU_MAX_PLANES];
+	int top_rpt[DPU_MAX_PLANES];
+	int btm_rpt[DPU_MAX_PLANES];
+
+	uint32_t roi_w[DPU_MAX_PLANES];
+	uint32_t roi_h[DPU_MAX_PLANES];
+
+	/*
+	 * Filter type to be used for scaling in horizontal and vertical
+	 * directions
+	 */
+	enum dpu_hw_filter horz_filter[DPU_MAX_PLANES];
+	enum dpu_hw_filter vert_filter[DPU_MAX_PLANES];
+
+};
+
+/**
+ * struct dpu_hw_pipe_cfg : Pipe description
+ * @layout:    format layout information for programming buffer to hardware
+ * @src_rect:  src ROI, caller takes into account the different operations
+ *             such as decimation, flip etc to program this field
+ * @dest_rect: destination ROI.
+ * @index:     index of the rectangle of SSPP
+ * @mode:      parallel or time multiplex multirect mode
+ */
+struct dpu_hw_pipe_cfg {
+	struct dpu_hw_fmt_layout layout;
+	struct drm_rect src_rect;
+	struct drm_rect dst_rect;
+	enum dpu_sspp_multirect_index index;
+	enum dpu_sspp_multirect_mode mode;
+};
+
+/**
+ * struct dpu_hw_pipe_qos_cfg : Source pipe QoS configuration
+ * @danger_lut: LUT for generate danger level based on fill level
+ * @safe_lut: LUT for generate safe level based on fill level
+ * @creq_lut: LUT for generate creq level based on fill level
+ * @creq_vblank: creq value generated to vbif during vertical blanking
+ * @danger_vblank: danger value generated during vertical blanking
+ * @vblank_en: enable creq_vblank and danger_vblank during vblank
+ * @danger_safe_en: enable danger safe generation
+ */
+struct dpu_hw_pipe_qos_cfg {
+	u32 danger_lut;
+	u32 safe_lut;
+	u64 creq_lut;
+	u32 creq_vblank;
+	u32 danger_vblank;
+	bool vblank_en;
+	bool danger_safe_en;
+};
+
+/**
+ * enum CDP preload ahead address size
+ */
+enum {
+	DPU_SSPP_CDP_PRELOAD_AHEAD_32,
+	DPU_SSPP_CDP_PRELOAD_AHEAD_64
+};
+
+/**
+ * struct dpu_hw_pipe_cdp_cfg : CDP configuration
+ * @enable: true to enable CDP
+ * @ubwc_meta_enable: true to enable ubwc metadata preload
+ * @tile_amortize_enable: true to enable amortization control for tile format
+ * @preload_ahead: number of request to preload ahead
+ *	DPU_SSPP_CDP_PRELOAD_AHEAD_32,
+ *	DPU_SSPP_CDP_PRELOAD_AHEAD_64
+ */
+struct dpu_hw_pipe_cdp_cfg {
+	bool enable;
+	bool ubwc_meta_enable;
+	bool tile_amortize_enable;
+	u32 preload_ahead;
+};
+
+/**
+ * struct dpu_hw_pipe_ts_cfg - traffic shaper configuration
+ * @size: size to prefill in bytes, or zero to disable
+ * @time: time to prefill in usec, or zero to disable
+ */
+struct dpu_hw_pipe_ts_cfg {
+	u64 size;
+	u64 time;
+};
+
+/**
+ * struct dpu_hw_sspp_ops - interface to the SSPP Hw driver functions
+ * Caller must call the init function to get the pipe context for each pipe
+ * Assumption is these functions will be called after clocks are enabled
+ */
+struct dpu_hw_sspp_ops {
+	/**
+	 * setup_format - setup pixel format cropping rectangle, flip
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe config structure
+	 * @flags: Extra flags for format config
+	 * @index: rectangle index in multirect
+	 */
+	void (*setup_format)(struct dpu_hw_pipe *ctx,
+			const struct dpu_format *fmt, u32 flags,
+			enum dpu_sspp_multirect_index index);
+
+	/**
+	 * setup_rects - setup pipe ROI rectangles
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe config structure
+	 * @index: rectangle index in multirect
+	 */
+	void (*setup_rects)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_cfg *cfg,
+			enum dpu_sspp_multirect_index index);
+
+	/**
+	 * setup_pe - setup pipe pixel extension
+	 * @ctx: Pointer to pipe context
+	 * @pe_ext: Pointer to pixel ext settings
+	 */
+	void (*setup_pe)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pixel_ext *pe_ext);
+
+	/**
+	 * setup_sourceaddress - setup pipe source addresses
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe config structure
+	 * @index: rectangle index in multirect
+	 */
+	void (*setup_sourceaddress)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_cfg *cfg,
+			enum dpu_sspp_multirect_index index);
+
+	/**
+	 * setup_csc - setup color space coversion
+	 * @ctx: Pointer to pipe context
+	 * @data: Pointer to config structure
+	 */
+	void (*setup_csc)(struct dpu_hw_pipe *ctx, struct dpu_csc_cfg *data);
+
+	/**
+	 * setup_solidfill - enable/disable colorfill
+	 * @ctx: Pointer to pipe context
+	 * @const_color: Fill color value
+	 * @flags: Pipe flags
+	 * @index: rectangle index in multirect
+	 */
+	void (*setup_solidfill)(struct dpu_hw_pipe *ctx, u32 color,
+			enum dpu_sspp_multirect_index index);
+
+	/**
+	 * setup_multirect - setup multirect configuration
+	 * @ctx: Pointer to pipe context
+	 * @index: rectangle index in multirect
+	 * @mode: parallel fetch / time multiplex multirect mode
+	 */
+
+	void (*setup_multirect)(struct dpu_hw_pipe *ctx,
+			enum dpu_sspp_multirect_index index,
+			enum dpu_sspp_multirect_mode mode);
+
+	/**
+	 * setup_sharpening - setup sharpening
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to config structure
+	 */
+	void (*setup_sharpening)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_sharp_cfg *cfg);
+
+	/**
+	 * setup_danger_safe_lut - setup danger safe LUTs
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe QoS configuration
+	 *
+	 */
+	void (*setup_danger_safe_lut)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_qos_cfg *cfg);
+
+	/**
+	 * setup_creq_lut - setup CREQ LUT
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe QoS configuration
+	 *
+	 */
+	void (*setup_creq_lut)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_qos_cfg *cfg);
+
+	/**
+	 * setup_qos_ctrl - setup QoS control
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe QoS configuration
+	 *
+	 */
+	void (*setup_qos_ctrl)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_qos_cfg *cfg);
+
+	/**
+	 * setup_histogram - setup histograms
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to histogram configuration
+	 */
+	void (*setup_histogram)(struct dpu_hw_pipe *ctx,
+			void *cfg);
+
+	/**
+	 * setup_scaler - setup scaler
+	 * @ctx: Pointer to pipe context
+	 * @pipe_cfg: Pointer to pipe configuration
+	 * @pe_cfg: Pointer to pixel extension configuration
+	 * @scaler_cfg: Pointer to scaler configuration
+	 */
+	void (*setup_scaler)(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_cfg *pipe_cfg,
+		struct dpu_hw_pixel_ext *pe_cfg,
+		void *scaler_cfg);
+
+	/**
+	 * get_scaler_ver - get scaler h/w version
+	 * @ctx: Pointer to pipe context
+	 */
+	u32 (*get_scaler_ver)(struct dpu_hw_pipe *ctx);
+
+	/**
+	 * setup_cdp - setup client driven prefetch
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to cdp configuration
+	 */
+	void (*setup_cdp)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_cdp_cfg *cfg);
+};
+
+/**
+ * struct dpu_hw_pipe - pipe description
+ * @base: hardware block base structure
+ * @hw: block hardware details
+ * @catalog: back pointer to catalog
+ * @mdp: pointer to associated mdp portion of the catalog
+ * @idx: pipe index
+ * @cap: pointer to layer_cfg
+ * @ops: pointer to operations possible for this pipe
+ */
+struct dpu_hw_pipe {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+	struct dpu_mdss_cfg *catalog;
+	struct dpu_mdp_cfg *mdp;
+
+	/* Pipe */
+	enum dpu_sspp idx;
+	const struct dpu_sspp_cfg *cap;
+
+	/* Ops */
+	struct dpu_hw_sspp_ops ops;
+};
+
+/**
+ * dpu_hw_pipe - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_pipe *to_dpu_hw_pipe(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_pipe, base);
+}
+
+/**
+ * dpu_hw_sspp_init - initializes the sspp hw driver object.
+ * Should be called once before accessing every pipe.
+ * @idx:  Pipe index for which driver object is required
+ * @addr: Mapped register io address of MDP
+ * @catalog : Pointer to mdss catalog data
+ * @is_virtual_pipe: is this pipe virtual pipe
+ */
+struct dpu_hw_pipe *dpu_hw_sspp_init(enum dpu_sspp idx,
+		void __iomem *addr, struct dpu_mdss_cfg *catalog,
+		bool is_virtual_pipe);
+
+/**
+ * dpu_hw_sspp_destroy(): Destroys SSPP driver context
+ * should be called during Hw pipe cleanup.
+ * @ctx:  Pointer to SSPP driver context returned by dpu_hw_sspp_init
+ */
+void dpu_hw_sspp_destroy(struct dpu_hw_pipe *ctx);
+
+#endif /*_DPU_HW_SSPP_H */
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
new file mode 100644
index 000000000000..db2798e862fc
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
@@ -0,0 +1,398 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_top.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+
+#define SSPP_SPARE                        0x28
+#define UBWC_STATIC                       0x144
+
+#define FLD_SPLIT_DISPLAY_CMD             BIT(1)
+#define FLD_SMART_PANEL_FREE_RUN          BIT(2)
+#define FLD_INTF_1_SW_TRG_MUX             BIT(4)
+#define FLD_INTF_2_SW_TRG_MUX             BIT(8)
+#define FLD_TE_LINE_INTER_WATERLEVEL_MASK 0xFFFF
+
+#define DANGER_STATUS                     0x360
+#define SAFE_STATUS                       0x364
+
+#define TE_LINE_INTERVAL                  0x3F4
+
+#define TRAFFIC_SHAPER_EN                 BIT(31)
+#define TRAFFIC_SHAPER_RD_CLIENT(num)     (0x030 + (num * 4))
+#define TRAFFIC_SHAPER_WR_CLIENT(num)     (0x060 + (num * 4))
+#define TRAFFIC_SHAPER_FIXPOINT_FACTOR    4
+
+#define MDP_WD_TIMER_0_CTL                0x380
+#define MDP_WD_TIMER_0_CTL2               0x384
+#define MDP_WD_TIMER_0_LOAD_VALUE         0x388
+#define MDP_WD_TIMER_1_CTL                0x390
+#define MDP_WD_TIMER_1_CTL2               0x394
+#define MDP_WD_TIMER_1_LOAD_VALUE         0x398
+#define MDP_WD_TIMER_2_CTL                0x420
+#define MDP_WD_TIMER_2_CTL2               0x424
+#define MDP_WD_TIMER_2_LOAD_VALUE         0x428
+#define MDP_WD_TIMER_3_CTL                0x430
+#define MDP_WD_TIMER_3_CTL2               0x434
+#define MDP_WD_TIMER_3_LOAD_VALUE         0x438
+#define MDP_WD_TIMER_4_CTL                0x440
+#define MDP_WD_TIMER_4_CTL2               0x444
+#define MDP_WD_TIMER_4_LOAD_VALUE         0x448
+
+#define MDP_TICK_COUNT                    16
+#define XO_CLK_RATE                       19200
+#define MS_TICKS_IN_SEC                   1000
+
+#define CALCULATE_WD_LOAD_VALUE(fps) \
+	((uint32_t)((MS_TICKS_IN_SEC * XO_CLK_RATE)/(MDP_TICK_COUNT * fps)))
+
+#define DCE_SEL                           0x450
+
+static void dpu_hw_setup_split_pipe(struct dpu_hw_mdp *mdp,
+		struct split_pipe_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 upper_pipe = 0;
+	u32 lower_pipe = 0;
+
+	if (!mdp || !cfg)
+		return;
+
+	c = &mdp->hw;
+
+	if (cfg->en) {
+		if (cfg->mode == INTF_MODE_CMD) {
+			lower_pipe = FLD_SPLIT_DISPLAY_CMD;
+			/* interface controlling sw trigger */
+			if (cfg->intf == INTF_2)
+				lower_pipe |= FLD_INTF_1_SW_TRG_MUX;
+			else
+				lower_pipe |= FLD_INTF_2_SW_TRG_MUX;
+			upper_pipe = lower_pipe;
+		} else {
+			if (cfg->intf == INTF_2) {
+				lower_pipe = FLD_INTF_1_SW_TRG_MUX;
+				upper_pipe = FLD_INTF_2_SW_TRG_MUX;
+			} else {
+				lower_pipe = FLD_INTF_2_SW_TRG_MUX;
+				upper_pipe = FLD_INTF_1_SW_TRG_MUX;
+			}
+		}
+	}
+
+	DPU_REG_WRITE(c, SSPP_SPARE, cfg->split_flush_en ? 0x1 : 0x0);
+	DPU_REG_WRITE(c, SPLIT_DISPLAY_LOWER_PIPE_CTRL, lower_pipe);
+	DPU_REG_WRITE(c, SPLIT_DISPLAY_UPPER_PIPE_CTRL, upper_pipe);
+	DPU_REG_WRITE(c, SPLIT_DISPLAY_EN, cfg->en & 0x1);
+}
+
+static void dpu_hw_setup_cdm_output(struct dpu_hw_mdp *mdp,
+		struct cdm_output_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 out_ctl = 0;
+
+	if (!mdp || !cfg)
+		return;
+
+	c = &mdp->hw;
+
+	if (cfg->intf_en)
+		out_ctl |= BIT(19);
+
+	DPU_REG_WRITE(c, MDP_OUT_CTL_0, out_ctl);
+}
+
+static bool dpu_hw_setup_clk_force_ctrl(struct dpu_hw_mdp *mdp,
+		enum dpu_clk_ctrl_type clk_ctrl, bool enable)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg_off, bit_off;
+	u32 reg_val, new_val;
+	bool clk_forced_on;
+
+	if (!mdp)
+		return false;
+
+	c = &mdp->hw;
+
+	if (clk_ctrl <= DPU_CLK_CTRL_NONE || clk_ctrl >= DPU_CLK_CTRL_MAX)
+		return false;
+
+	reg_off = mdp->caps->clk_ctrls[clk_ctrl].reg_off;
+	bit_off = mdp->caps->clk_ctrls[clk_ctrl].bit_off;
+
+	reg_val = DPU_REG_READ(c, reg_off);
+
+	if (enable)
+		new_val = reg_val | BIT(bit_off);
+	else
+		new_val = reg_val & ~BIT(bit_off);
+
+	DPU_REG_WRITE(c, reg_off, new_val);
+
+	clk_forced_on = !(reg_val & BIT(bit_off));
+
+	return clk_forced_on;
+}
+
+
+static void dpu_hw_get_danger_status(struct dpu_hw_mdp *mdp,
+		struct dpu_danger_safe_status *status)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 value;
+
+	if (!mdp || !status)
+		return;
+
+	c = &mdp->hw;
+
+	value = DPU_REG_READ(c, DANGER_STATUS);
+	status->mdp = (value >> 0) & 0x3;
+	status->sspp[SSPP_VIG0] = (value >> 4) & 0x3;
+	status->sspp[SSPP_VIG1] = (value >> 6) & 0x3;
+	status->sspp[SSPP_VIG2] = (value >> 8) & 0x3;
+	status->sspp[SSPP_VIG3] = (value >> 10) & 0x3;
+	status->sspp[SSPP_RGB0] = (value >> 12) & 0x3;
+	status->sspp[SSPP_RGB1] = (value >> 14) & 0x3;
+	status->sspp[SSPP_RGB2] = (value >> 16) & 0x3;
+	status->sspp[SSPP_RGB3] = (value >> 18) & 0x3;
+	status->sspp[SSPP_DMA0] = (value >> 20) & 0x3;
+	status->sspp[SSPP_DMA1] = (value >> 22) & 0x3;
+	status->sspp[SSPP_DMA2] = (value >> 28) & 0x3;
+	status->sspp[SSPP_DMA3] = (value >> 30) & 0x3;
+	status->sspp[SSPP_CURSOR0] = (value >> 24) & 0x3;
+	status->sspp[SSPP_CURSOR1] = (value >> 26) & 0x3;
+}
+
+static void dpu_hw_setup_vsync_source(struct dpu_hw_mdp *mdp,
+		struct dpu_vsync_source_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg, wd_load_value, wd_ctl, wd_ctl2, i;
+	static const u32 pp_offset[PINGPONG_MAX] = {0xC, 0x8, 0x4, 0x13, 0x18};
+
+	if (!mdp || !cfg || (cfg->pp_count > ARRAY_SIZE(cfg->ppnumber)))
+		return;
+
+	c = &mdp->hw;
+	reg = DPU_REG_READ(c, MDP_VSYNC_SEL);
+	for (i = 0; i < cfg->pp_count; i++) {
+		int pp_idx = cfg->ppnumber[i] - PINGPONG_0;
+
+		if (pp_idx >= ARRAY_SIZE(pp_offset))
+			continue;
+
+		reg &= ~(0xf << pp_offset[pp_idx]);
+		reg |= (cfg->vsync_source & 0xf) << pp_offset[pp_idx];
+	}
+	DPU_REG_WRITE(c, MDP_VSYNC_SEL, reg);
+
+	if (cfg->vsync_source >= DPU_VSYNC_SOURCE_WD_TIMER_4 &&
+			cfg->vsync_source <= DPU_VSYNC_SOURCE_WD_TIMER_0) {
+		switch (cfg->vsync_source) {
+		case DPU_VSYNC_SOURCE_WD_TIMER_4:
+			wd_load_value = MDP_WD_TIMER_4_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_4_CTL;
+			wd_ctl2 = MDP_WD_TIMER_4_CTL2;
+			break;
+		case DPU_VSYNC_SOURCE_WD_TIMER_3:
+			wd_load_value = MDP_WD_TIMER_3_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_3_CTL;
+			wd_ctl2 = MDP_WD_TIMER_3_CTL2;
+			break;
+		case DPU_VSYNC_SOURCE_WD_TIMER_2:
+			wd_load_value = MDP_WD_TIMER_2_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_2_CTL;
+			wd_ctl2 = MDP_WD_TIMER_2_CTL2;
+			break;
+		case DPU_VSYNC_SOURCE_WD_TIMER_1:
+			wd_load_value = MDP_WD_TIMER_1_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_1_CTL;
+			wd_ctl2 = MDP_WD_TIMER_1_CTL2;
+			break;
+		case DPU_VSYNC_SOURCE_WD_TIMER_0:
+		default:
+			wd_load_value = MDP_WD_TIMER_0_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_0_CTL;
+			wd_ctl2 = MDP_WD_TIMER_0_CTL2;
+			break;
+		}
+
+		DPU_REG_WRITE(c, wd_load_value,
+			CALCULATE_WD_LOAD_VALUE(cfg->frame_rate));
+
+		DPU_REG_WRITE(c, wd_ctl, BIT(0)); /* clear timer */
+		reg = DPU_REG_READ(c, wd_ctl2);
+		reg |= BIT(8);		/* enable heartbeat timer */
+		reg |= BIT(0);		/* enable WD timer */
+		DPU_REG_WRITE(c, wd_ctl2, reg);
+
+		/* make sure that timers are enabled/disabled for vsync state */
+		wmb();
+	}
+}
+
+static void dpu_hw_get_safe_status(struct dpu_hw_mdp *mdp,
+		struct dpu_danger_safe_status *status)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 value;
+
+	if (!mdp || !status)
+		return;
+
+	c = &mdp->hw;
+
+	value = DPU_REG_READ(c, SAFE_STATUS);
+	status->mdp = (value >> 0) & 0x1;
+	status->sspp[SSPP_VIG0] = (value >> 4) & 0x1;
+	status->sspp[SSPP_VIG1] = (value >> 6) & 0x1;
+	status->sspp[SSPP_VIG2] = (value >> 8) & 0x1;
+	status->sspp[SSPP_VIG3] = (value >> 10) & 0x1;
+	status->sspp[SSPP_RGB0] = (value >> 12) & 0x1;
+	status->sspp[SSPP_RGB1] = (value >> 14) & 0x1;
+	status->sspp[SSPP_RGB2] = (value >> 16) & 0x1;
+	status->sspp[SSPP_RGB3] = (value >> 18) & 0x1;
+	status->sspp[SSPP_DMA0] = (value >> 20) & 0x1;
+	status->sspp[SSPP_DMA1] = (value >> 22) & 0x1;
+	status->sspp[SSPP_DMA2] = (value >> 28) & 0x1;
+	status->sspp[SSPP_DMA3] = (value >> 30) & 0x1;
+	status->sspp[SSPP_CURSOR0] = (value >> 24) & 0x1;
+	status->sspp[SSPP_CURSOR1] = (value >> 26) & 0x1;
+}
+
+static void dpu_hw_reset_ubwc(struct dpu_hw_mdp *mdp, struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_blk_reg_map c;
+
+	if (!mdp || !m)
+		return;
+
+	if (!IS_UBWC_20_SUPPORTED(m->caps->ubwc_version))
+		return;
+
+	/* force blk offset to zero to access beginning of register region */
+	c = mdp->hw;
+	c.blk_off = 0x0;
+	DPU_REG_WRITE(&c, UBWC_STATIC, m->mdp[0].ubwc_static);
+}
+
+static void dpu_hw_intf_audio_select(struct dpu_hw_mdp *mdp)
+{
+	struct dpu_hw_blk_reg_map *c;
+
+	if (!mdp)
+		return;
+
+	c = &mdp->hw;
+
+	DPU_REG_WRITE(c, HDMI_DP_CORE_SELECT, 0x1);
+}
+
+static void _setup_mdp_ops(struct dpu_hw_mdp_ops *ops,
+		unsigned long cap)
+{
+	ops->setup_split_pipe = dpu_hw_setup_split_pipe;
+	ops->setup_cdm_output = dpu_hw_setup_cdm_output;
+	ops->setup_clk_force_ctrl = dpu_hw_setup_clk_force_ctrl;
+	ops->get_danger_status = dpu_hw_get_danger_status;
+	ops->setup_vsync_source = dpu_hw_setup_vsync_source;
+	ops->get_safe_status = dpu_hw_get_safe_status;
+	ops->reset_ubwc = dpu_hw_reset_ubwc;
+	ops->intf_audio_select = dpu_hw_intf_audio_select;
+}
+
+static const struct dpu_mdp_cfg *_top_offset(enum dpu_mdp mdp,
+		const struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	if (!m || !addr || !b)
+		return ERR_PTR(-EINVAL);
+
+	for (i = 0; i < m->mdp_count; i++) {
+		if (mdp == m->mdp[i].id) {
+			b->base_off = addr;
+			b->blk_off = m->mdp[i].base;
+			b->length = m->mdp[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_TOP;
+			return &m->mdp[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_mdp *dpu_hw_mdptop_init(enum dpu_mdp idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_mdp *mdp;
+	const struct dpu_mdp_cfg *cfg;
+	int rc;
+
+	if (!addr || !m)
+		return ERR_PTR(-EINVAL);
+
+	mdp = kzalloc(sizeof(*mdp), GFP_KERNEL);
+	if (!mdp)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _top_offset(idx, m, addr, &mdp->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(mdp);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/*
+	 * Assign ops
+	 */
+	mdp->idx = idx;
+	mdp->caps = cfg;
+	_setup_mdp_ops(&mdp->ops, mdp->caps->features);
+
+	rc = dpu_hw_blk_init(&mdp->base, DPU_HW_BLK_TOP, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	dpu_dbg_set_dpu_top_offset(mdp->hw.blk_off);
+
+	return mdp;
+
+blk_init_error:
+	kzfree(mdp);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_mdp_destroy(struct dpu_hw_mdp *mdp)
+{
+	if (mdp)
+		dpu_hw_blk_destroy(&mdp->base);
+	kfree(mdp);
+}
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h
new file mode 100644
index 000000000000..899925aaa6d7
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h
@@ -0,0 +1,202 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_TOP_H
+#define _DPU_HW_TOP_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_blk.h"
+
+struct dpu_hw_mdp;
+
+/**
+ * struct traffic_shaper_cfg: traffic shaper configuration
+ * @en        : enable/disable traffic shaper
+ * @rd_client : true if read client; false if write client
+ * @client_id : client identifier
+ * @bpc_denom : denominator of byte per clk
+ * @bpc_numer : numerator of byte per clk
+ */
+struct traffic_shaper_cfg {
+	bool en;
+	bool rd_client;
+	u32 client_id;
+	u32 bpc_denom;
+	u64 bpc_numer;
+};
+
+/**
+ * struct split_pipe_cfg - pipe configuration for dual display panels
+ * @en        : Enable/disable dual pipe confguration
+ * @mode      : Panel interface mode
+ * @intf      : Interface id for main control path
+ * @split_flush_en: Allows both the paths to be flushed when master path is
+ *              flushed
+ */
+struct split_pipe_cfg {
+	bool en;
+	enum dpu_intf_mode mode;
+	enum dpu_intf intf;
+	bool split_flush_en;
+};
+
+/**
+ * struct cdm_output_cfg: output configuration for cdm
+ * @intf_en   : enable/disable interface output
+ */
+struct cdm_output_cfg {
+	bool intf_en;
+};
+
+/**
+ * struct dpu_danger_safe_status: danger and safe status signals
+ * @mdp: top level status
+ * @sspp: source pipe status
+ */
+struct dpu_danger_safe_status {
+	u8 mdp;
+	u8 sspp[SSPP_MAX];
+};
+
+/**
+ * struct dpu_vsync_source_cfg - configure vsync source and configure the
+ *                                    watchdog timers if required.
+ * @pp_count: number of ping pongs active
+ * @frame_rate: Display frame rate
+ * @ppnumber: ping pong index array
+ * @vsync_source: vsync source selection
+ */
+struct dpu_vsync_source_cfg {
+	u32 pp_count;
+	u32 frame_rate;
+	u32 ppnumber[PINGPONG_MAX];
+	u32 vsync_source;
+};
+
+/**
+ * struct dpu_hw_mdp_ops - interface to the MDP TOP Hw driver functions
+ * Assumption is these functions will be called after clocks are enabled.
+ * @setup_split_pipe : Programs the pipe control registers
+ * @setup_pp_split : Programs the pp split control registers
+ * @setup_cdm_output : programs cdm control
+ * @setup_traffic_shaper : programs traffic shaper control
+ */
+struct dpu_hw_mdp_ops {
+	/** setup_split_pipe() : Regsiters are not double buffered, thisk
+	 * function should be called before timing control enable
+	 * @mdp  : mdp top context driver
+	 * @cfg  : upper and lower part of pipe configuration
+	 */
+	void (*setup_split_pipe)(struct dpu_hw_mdp *mdp,
+			struct split_pipe_cfg *p);
+
+	/**
+	 * setup_cdm_output() : Setup selection control of the cdm data path
+	 * @mdp  : mdp top context driver
+	 * @cfg  : cdm output configuration
+	 */
+	void (*setup_cdm_output)(struct dpu_hw_mdp *mdp,
+			struct cdm_output_cfg *cfg);
+
+	/**
+	 * setup_traffic_shaper() : Setup traffic shaper control
+	 * @mdp  : mdp top context driver
+	 * @cfg  : traffic shaper configuration
+	 */
+	void (*setup_traffic_shaper)(struct dpu_hw_mdp *mdp,
+			struct traffic_shaper_cfg *cfg);
+
+	/**
+	 * setup_clk_force_ctrl - set clock force control
+	 * @mdp: mdp top context driver
+	 * @clk_ctrl: clock to be controlled
+	 * @enable: force on enable
+	 * @return: if the clock is forced-on by this function
+	 */
+	bool (*setup_clk_force_ctrl)(struct dpu_hw_mdp *mdp,
+			enum dpu_clk_ctrl_type clk_ctrl, bool enable);
+
+	/**
+	 * get_danger_status - get danger status
+	 * @mdp: mdp top context driver
+	 * @status: Pointer to danger safe status
+	 */
+	void (*get_danger_status)(struct dpu_hw_mdp *mdp,
+			struct dpu_danger_safe_status *status);
+
+	/**
+	 * setup_vsync_source - setup vsync source configuration details
+	 * @mdp: mdp top context driver
+	 * @cfg: vsync source selection configuration
+	 */
+	void (*setup_vsync_source)(struct dpu_hw_mdp *mdp,
+				struct dpu_vsync_source_cfg *cfg);
+
+	/**
+	 * get_safe_status - get safe status
+	 * @mdp: mdp top context driver
+	 * @status: Pointer to danger safe status
+	 */
+	void (*get_safe_status)(struct dpu_hw_mdp *mdp,
+			struct dpu_danger_safe_status *status);
+
+	/**
+	 * reset_ubwc - reset top level UBWC configuration
+	 * @mdp: mdp top context driver
+	 * @m: pointer to mdss catalog data
+	 */
+	void (*reset_ubwc)(struct dpu_hw_mdp *mdp, struct dpu_mdss_cfg *m);
+
+	/**
+	 * intf_audio_select - select the external interface for audio
+	 * @mdp: mdp top context driver
+	 */
+	void (*intf_audio_select)(struct dpu_hw_mdp *mdp);
+};
+
+struct dpu_hw_mdp {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* top */
+	enum dpu_mdp idx;
+	const struct dpu_mdp_cfg *caps;
+
+	/* ops */
+	struct dpu_hw_mdp_ops ops;
+};
+
+/**
+ * to_dpu_hw_mdp - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_mdp *to_dpu_hw_mdp(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_mdp, base);
+}
+
+/**
+ * dpu_hw_mdptop_init - initializes the top driver for the passed idx
+ * @idx:  Interface index for which driver object is required
+ * @addr: Mapped register io address of MDP
+ * @m:    Pointer to mdss catalog data
+ */
+struct dpu_hw_mdp *dpu_hw_mdptop_init(enum dpu_mdp idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m);
+
+void dpu_hw_mdp_destroy(struct dpu_hw_mdp *mdp);
+
+#endif /*_DPU_HW_TOP_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c
new file mode 100644
index 000000000000..4cabae480a7b
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c
@@ -0,0 +1,368 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include "msm_drv.h"
+#include "dpu_kms.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+
+/* using a file static variables for debugfs access */
+static u32 dpu_hw_util_log_mask = DPU_DBG_MASK_NONE;
+
+/* DPU_SCALER_QSEED3 */
+#define QSEED3_HW_VERSION                  0x00
+#define QSEED3_OP_MODE                     0x04
+#define QSEED3_RGB2Y_COEFF                 0x08
+#define QSEED3_PHASE_INIT                  0x0C
+#define QSEED3_PHASE_STEP_Y_H              0x10
+#define QSEED3_PHASE_STEP_Y_V              0x14
+#define QSEED3_PHASE_STEP_UV_H             0x18
+#define QSEED3_PHASE_STEP_UV_V             0x1C
+#define QSEED3_PRELOAD                     0x20
+#define QSEED3_DE_SHARPEN                  0x24
+#define QSEED3_DE_SHARPEN_CTL              0x28
+#define QSEED3_DE_SHAPE_CTL                0x2C
+#define QSEED3_DE_THRESHOLD                0x30
+#define QSEED3_DE_ADJUST_DATA_0            0x34
+#define QSEED3_DE_ADJUST_DATA_1            0x38
+#define QSEED3_DE_ADJUST_DATA_2            0x3C
+#define QSEED3_SRC_SIZE_Y_RGB_A            0x40
+#define QSEED3_SRC_SIZE_UV                 0x44
+#define QSEED3_DST_SIZE                    0x48
+#define QSEED3_COEF_LUT_CTRL               0x4C
+#define QSEED3_COEF_LUT_SWAP_BIT           0
+#define QSEED3_COEF_LUT_DIR_BIT            1
+#define QSEED3_COEF_LUT_Y_CIR_BIT          2
+#define QSEED3_COEF_LUT_UV_CIR_BIT         3
+#define QSEED3_COEF_LUT_Y_SEP_BIT          4
+#define QSEED3_COEF_LUT_UV_SEP_BIT         5
+#define QSEED3_BUFFER_CTRL                 0x50
+#define QSEED3_CLK_CTRL0                   0x54
+#define QSEED3_CLK_CTRL1                   0x58
+#define QSEED3_CLK_STATUS                  0x5C
+#define QSEED3_MISR_CTRL                   0x70
+#define QSEED3_MISR_SIGNATURE_0            0x74
+#define QSEED3_MISR_SIGNATURE_1            0x78
+#define QSEED3_PHASE_INIT_Y_H              0x90
+#define QSEED3_PHASE_INIT_Y_V              0x94
+#define QSEED3_PHASE_INIT_UV_H             0x98
+#define QSEED3_PHASE_INIT_UV_V             0x9C
+#define QSEED3_COEF_LUT                    0x100
+#define QSEED3_FILTERS                     5
+#define QSEED3_LUT_REGIONS                 4
+#define QSEED3_CIRCULAR_LUTS               9
+#define QSEED3_SEPARABLE_LUTS              10
+#define QSEED3_LUT_SIZE                    60
+#define QSEED3_ENABLE                      2
+#define QSEED3_DIR_LUT_SIZE                (200 * sizeof(u32))
+#define QSEED3_CIR_LUT_SIZE \
+	(QSEED3_LUT_SIZE * QSEED3_CIRCULAR_LUTS * sizeof(u32))
+#define QSEED3_SEP_LUT_SIZE \
+	(QSEED3_LUT_SIZE * QSEED3_SEPARABLE_LUTS * sizeof(u32))
+
+void dpu_reg_write(struct dpu_hw_blk_reg_map *c,
+		u32 reg_off,
+		u32 val,
+		const char *name)
+{
+	/* don't need to mutex protect this */
+	if (c->log_mask & dpu_hw_util_log_mask)
+		DPU_DEBUG_DRIVER("[%s:0x%X] <= 0x%X\n",
+				name, c->blk_off + reg_off, val);
+	writel_relaxed(val, c->base_off + c->blk_off + reg_off);
+}
+
+int dpu_reg_read(struct dpu_hw_blk_reg_map *c, u32 reg_off)
+{
+	return readl_relaxed(c->base_off + c->blk_off + reg_off);
+}
+
+u32 *dpu_hw_util_get_log_mask_ptr(void)
+{
+	return &dpu_hw_util_log_mask;
+}
+
+static void _dpu_hw_setup_scaler3_lut(struct dpu_hw_blk_reg_map *c,
+		struct dpu_hw_scaler3_cfg *scaler3_cfg, u32 offset)
+{
+	int i, j, filter;
+	int config_lut = 0x0;
+	unsigned long lut_flags;
+	u32 lut_addr, lut_offset, lut_len;
+	u32 *lut[QSEED3_FILTERS] = {NULL, NULL, NULL, NULL, NULL};
+	static const uint32_t off_tbl[QSEED3_FILTERS][QSEED3_LUT_REGIONS][2] = {
+		{{18, 0x000}, {12, 0x120}, {12, 0x1E0}, {8, 0x2A0} },
+		{{6, 0x320}, {3, 0x3E0}, {3, 0x440}, {3, 0x4A0} },
+		{{6, 0x500}, {3, 0x5c0}, {3, 0x620}, {3, 0x680} },
+		{{6, 0x380}, {3, 0x410}, {3, 0x470}, {3, 0x4d0} },
+		{{6, 0x560}, {3, 0x5f0}, {3, 0x650}, {3, 0x6b0} },
+	};
+
+	lut_flags = (unsigned long) scaler3_cfg->lut_flag;
+	if (test_bit(QSEED3_COEF_LUT_DIR_BIT, &lut_flags) &&
+		(scaler3_cfg->dir_len == QSEED3_DIR_LUT_SIZE)) {
+		lut[0] = scaler3_cfg->dir_lut;
+		config_lut = 1;
+	}
+	if (test_bit(QSEED3_COEF_LUT_Y_CIR_BIT, &lut_flags) &&
+		(scaler3_cfg->y_rgb_cir_lut_idx < QSEED3_CIRCULAR_LUTS) &&
+		(scaler3_cfg->cir_len == QSEED3_CIR_LUT_SIZE)) {
+		lut[1] = scaler3_cfg->cir_lut +
+			scaler3_cfg->y_rgb_cir_lut_idx * QSEED3_LUT_SIZE;
+		config_lut = 1;
+	}
+	if (test_bit(QSEED3_COEF_LUT_UV_CIR_BIT, &lut_flags) &&
+		(scaler3_cfg->uv_cir_lut_idx < QSEED3_CIRCULAR_LUTS) &&
+		(scaler3_cfg->cir_len == QSEED3_CIR_LUT_SIZE)) {
+		lut[2] = scaler3_cfg->cir_lut +
+			scaler3_cfg->uv_cir_lut_idx * QSEED3_LUT_SIZE;
+		config_lut = 1;
+	}
+	if (test_bit(QSEED3_COEF_LUT_Y_SEP_BIT, &lut_flags) &&
+		(scaler3_cfg->y_rgb_sep_lut_idx < QSEED3_SEPARABLE_LUTS) &&
+		(scaler3_cfg->sep_len == QSEED3_SEP_LUT_SIZE)) {
+		lut[3] = scaler3_cfg->sep_lut +
+			scaler3_cfg->y_rgb_sep_lut_idx * QSEED3_LUT_SIZE;
+		config_lut = 1;
+	}
+	if (test_bit(QSEED3_COEF_LUT_UV_SEP_BIT, &lut_flags) &&
+		(scaler3_cfg->uv_sep_lut_idx < QSEED3_SEPARABLE_LUTS) &&
+		(scaler3_cfg->sep_len == QSEED3_SEP_LUT_SIZE)) {
+		lut[4] = scaler3_cfg->sep_lut +
+			scaler3_cfg->uv_sep_lut_idx * QSEED3_LUT_SIZE;
+		config_lut = 1;
+	}
+
+	if (config_lut) {
+		for (filter = 0; filter < QSEED3_FILTERS; filter++) {
+			if (!lut[filter])
+				continue;
+			lut_offset = 0;
+			for (i = 0; i < QSEED3_LUT_REGIONS; i++) {
+				lut_addr = QSEED3_COEF_LUT + offset
+					+ off_tbl[filter][i][1];
+				lut_len = off_tbl[filter][i][0] << 2;
+				for (j = 0; j < lut_len; j++) {
+					DPU_REG_WRITE(c,
+						lut_addr,
+						(lut[filter])[lut_offset++]);
+					lut_addr += 4;
+				}
+			}
+		}
+	}
+
+	if (test_bit(QSEED3_COEF_LUT_SWAP_BIT, &lut_flags))
+		DPU_REG_WRITE(c, QSEED3_COEF_LUT_CTRL + offset, BIT(0));
+
+}
+
+static void _dpu_hw_setup_scaler3_de(struct dpu_hw_blk_reg_map *c,
+		struct dpu_hw_scaler3_de_cfg *de_cfg, u32 offset)
+{
+	u32 sharp_lvl, sharp_ctl, shape_ctl, de_thr;
+	u32 adjust_a, adjust_b, adjust_c;
+
+	if (!de_cfg->enable)
+		return;
+
+	sharp_lvl = (de_cfg->sharpen_level1 & 0x1FF) |
+		((de_cfg->sharpen_level2 & 0x1FF) << 16);
+
+	sharp_ctl = ((de_cfg->limit & 0xF) << 9) |
+		((de_cfg->prec_shift & 0x7) << 13) |
+		((de_cfg->clip & 0x7) << 16);
+
+	shape_ctl = (de_cfg->thr_quiet & 0xFF) |
+		((de_cfg->thr_dieout & 0x3FF) << 16);
+
+	de_thr = (de_cfg->thr_low & 0x3FF) |
+		((de_cfg->thr_high & 0x3FF) << 16);
+
+	adjust_a = (de_cfg->adjust_a[0] & 0x3FF) |
+		((de_cfg->adjust_a[1] & 0x3FF) << 10) |
+		((de_cfg->adjust_a[2] & 0x3FF) << 20);
+
+	adjust_b = (de_cfg->adjust_b[0] & 0x3FF) |
+		((de_cfg->adjust_b[1] & 0x3FF) << 10) |
+		((de_cfg->adjust_b[2] & 0x3FF) << 20);
+
+	adjust_c = (de_cfg->adjust_c[0] & 0x3FF) |
+		((de_cfg->adjust_c[1] & 0x3FF) << 10) |
+		((de_cfg->adjust_c[2] & 0x3FF) << 20);
+
+	DPU_REG_WRITE(c, QSEED3_DE_SHARPEN + offset, sharp_lvl);
+	DPU_REG_WRITE(c, QSEED3_DE_SHARPEN_CTL + offset, sharp_ctl);
+	DPU_REG_WRITE(c, QSEED3_DE_SHAPE_CTL + offset, shape_ctl);
+	DPU_REG_WRITE(c, QSEED3_DE_THRESHOLD + offset, de_thr);
+	DPU_REG_WRITE(c, QSEED3_DE_ADJUST_DATA_0 + offset, adjust_a);
+	DPU_REG_WRITE(c, QSEED3_DE_ADJUST_DATA_1 + offset, adjust_b);
+	DPU_REG_WRITE(c, QSEED3_DE_ADJUST_DATA_2 + offset, adjust_c);
+
+}
+
+void dpu_hw_setup_scaler3(struct dpu_hw_blk_reg_map *c,
+		struct dpu_hw_scaler3_cfg *scaler3_cfg,
+		u32 scaler_offset, u32 scaler_version,
+		const struct dpu_format *format)
+{
+	u32 op_mode = 0;
+	u32 phase_init, preload, src_y_rgb, src_uv, dst;
+
+	if (!scaler3_cfg->enable)
+		goto end;
+
+	op_mode |= BIT(0);
+	op_mode |= (scaler3_cfg->y_rgb_filter_cfg & 0x3) << 16;
+
+	if (format && DPU_FORMAT_IS_YUV(format)) {
+		op_mode |= BIT(12);
+		op_mode |= (scaler3_cfg->uv_filter_cfg & 0x3) << 24;
+	}
+
+	op_mode |= (scaler3_cfg->blend_cfg & 1) << 31;
+	op_mode |= (scaler3_cfg->dir_en) ? BIT(4) : 0;
+
+	preload =
+		((scaler3_cfg->preload_x[0] & 0x7F) << 0) |
+		((scaler3_cfg->preload_y[0] & 0x7F) << 8) |
+		((scaler3_cfg->preload_x[1] & 0x7F) << 16) |
+		((scaler3_cfg->preload_y[1] & 0x7F) << 24);
+
+	src_y_rgb = (scaler3_cfg->src_width[0] & 0x1FFFF) |
+		((scaler3_cfg->src_height[0] & 0x1FFFF) << 16);
+
+	src_uv = (scaler3_cfg->src_width[1] & 0x1FFFF) |
+		((scaler3_cfg->src_height[1] & 0x1FFFF) << 16);
+
+	dst = (scaler3_cfg->dst_width & 0x1FFFF) |
+		((scaler3_cfg->dst_height & 0x1FFFF) << 16);
+
+	if (scaler3_cfg->de.enable) {
+		_dpu_hw_setup_scaler3_de(c, &scaler3_cfg->de, scaler_offset);
+		op_mode |= BIT(8);
+	}
+
+	if (scaler3_cfg->lut_flag)
+		_dpu_hw_setup_scaler3_lut(c, scaler3_cfg,
+								scaler_offset);
+
+	if (scaler_version == 0x1002) {
+		phase_init =
+			((scaler3_cfg->init_phase_x[0] & 0x3F) << 0) |
+			((scaler3_cfg->init_phase_y[0] & 0x3F) << 8) |
+			((scaler3_cfg->init_phase_x[1] & 0x3F) << 16) |
+			((scaler3_cfg->init_phase_y[1] & 0x3F) << 24);
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT + scaler_offset, phase_init);
+	} else {
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT_Y_H + scaler_offset,
+			scaler3_cfg->init_phase_x[0] & 0x1FFFFF);
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT_Y_V + scaler_offset,
+			scaler3_cfg->init_phase_y[0] & 0x1FFFFF);
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT_UV_H + scaler_offset,
+			scaler3_cfg->init_phase_x[1] & 0x1FFFFF);
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT_UV_V + scaler_offset,
+			scaler3_cfg->init_phase_y[1] & 0x1FFFFF);
+	}
+
+	DPU_REG_WRITE(c, QSEED3_PHASE_STEP_Y_H + scaler_offset,
+		scaler3_cfg->phase_step_x[0] & 0xFFFFFF);
+
+	DPU_REG_WRITE(c, QSEED3_PHASE_STEP_Y_V + scaler_offset,
+		scaler3_cfg->phase_step_y[0] & 0xFFFFFF);
+
+	DPU_REG_WRITE(c, QSEED3_PHASE_STEP_UV_H + scaler_offset,
+		scaler3_cfg->phase_step_x[1] & 0xFFFFFF);
+
+	DPU_REG_WRITE(c, QSEED3_PHASE_STEP_UV_V + scaler_offset,
+		scaler3_cfg->phase_step_y[1] & 0xFFFFFF);
+
+	DPU_REG_WRITE(c, QSEED3_PRELOAD + scaler_offset, preload);
+
+	DPU_REG_WRITE(c, QSEED3_SRC_SIZE_Y_RGB_A + scaler_offset, src_y_rgb);
+
+	DPU_REG_WRITE(c, QSEED3_SRC_SIZE_UV + scaler_offset, src_uv);
+
+	DPU_REG_WRITE(c, QSEED3_DST_SIZE + scaler_offset, dst);
+
+end:
+	if (format && !DPU_FORMAT_IS_DX(format))
+		op_mode |= BIT(14);
+
+	if (format && format->alpha_enable) {
+		op_mode |= BIT(10);
+		if (scaler_version == 0x1002)
+			op_mode |= (scaler3_cfg->alpha_filter_cfg & 0x1) << 30;
+		else
+			op_mode |= (scaler3_cfg->alpha_filter_cfg & 0x3) << 29;
+	}
+
+	DPU_REG_WRITE(c, QSEED3_OP_MODE + scaler_offset, op_mode);
+}
+
+u32 dpu_hw_get_scaler3_ver(struct dpu_hw_blk_reg_map *c,
+			u32 scaler_offset)
+{
+	return DPU_REG_READ(c, QSEED3_HW_VERSION + scaler_offset);
+}
+
+void dpu_hw_csc_setup(struct dpu_hw_blk_reg_map *c,
+		u32 csc_reg_off,
+		struct dpu_csc_cfg *data, bool csc10)
+{
+	static const u32 matrix_shift = 7;
+	u32 clamp_shift = csc10 ? 16 : 8;
+	u32 val;
+
+	/* matrix coeff - convert S15.16 to S4.9 */
+	val = ((data->csc_mv[0] >> matrix_shift) & 0x1FFF) |
+		(((data->csc_mv[1] >> matrix_shift) & 0x1FFF) << 16);
+	DPU_REG_WRITE(c, csc_reg_off, val);
+	val = ((data->csc_mv[2] >> matrix_shift) & 0x1FFF) |
+		(((data->csc_mv[3] >> matrix_shift) & 0x1FFF) << 16);
+	DPU_REG_WRITE(c, csc_reg_off + 0x4, val);
+	val = ((data->csc_mv[4] >> matrix_shift) & 0x1FFF) |
+		(((data->csc_mv[5] >> matrix_shift) & 0x1FFF) << 16);
+	DPU_REG_WRITE(c, csc_reg_off + 0x8, val);
+	val = ((data->csc_mv[6] >> matrix_shift) & 0x1FFF) |
+		(((data->csc_mv[7] >> matrix_shift) & 0x1FFF) << 16);
+	DPU_REG_WRITE(c, csc_reg_off + 0xc, val);
+	val = (data->csc_mv[8] >> matrix_shift) & 0x1FFF;
+	DPU_REG_WRITE(c, csc_reg_off + 0x10, val);
+
+	/* Pre clamp */
+	val = (data->csc_pre_lv[0] << clamp_shift) | data->csc_pre_lv[1];
+	DPU_REG_WRITE(c, csc_reg_off + 0x14, val);
+	val = (data->csc_pre_lv[2] << clamp_shift) | data->csc_pre_lv[3];
+	DPU_REG_WRITE(c, csc_reg_off + 0x18, val);
+	val = (data->csc_pre_lv[4] << clamp_shift) | data->csc_pre_lv[5];
+	DPU_REG_WRITE(c, csc_reg_off + 0x1c, val);
+
+	/* Post clamp */
+	val = (data->csc_post_lv[0] << clamp_shift) | data->csc_post_lv[1];
+	DPU_REG_WRITE(c, csc_reg_off + 0x20, val);
+	val = (data->csc_post_lv[2] << clamp_shift) | data->csc_post_lv[3];
+	DPU_REG_WRITE(c, csc_reg_off + 0x24, val);
+	val = (data->csc_post_lv[4] << clamp_shift) | data->csc_post_lv[5];
+	DPU_REG_WRITE(c, csc_reg_off + 0x28, val);
+
+	/* Pre-Bias */
+	DPU_REG_WRITE(c, csc_reg_off + 0x2c, data->csc_pre_bv[0]);
+	DPU_REG_WRITE(c, csc_reg_off + 0x30, data->csc_pre_bv[1]);
+	DPU_REG_WRITE(c, csc_reg_off + 0x34, data->csc_pre_bv[2]);
+
+	/* Post-Bias */
+	DPU_REG_WRITE(c, csc_reg_off + 0x38, data->csc_post_bv[0]);
+	DPU_REG_WRITE(c, csc_reg_off + 0x3c, data->csc_post_bv[1]);
+	DPU_REG_WRITE(c, csc_reg_off + 0x40, data->csc_post_bv[2]);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h
new file mode 100644
index 000000000000..1240f505ca53
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h
@@ -0,0 +1,348 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_UTIL_H
+#define _DPU_HW_UTIL_H
+
+#include <linux/io.h>
+#include <linux/slab.h>
+#include "dpu_hw_mdss.h"
+
+#define REG_MASK(n)                     ((BIT(n)) - 1)
+struct dpu_format_extended;
+
+/*
+ * This is the common struct maintained by each sub block
+ * for mapping the register offsets in this block to the
+ * absoulute IO address
+ * @base_off:     mdp register mapped offset
+ * @blk_off:      pipe offset relative to mdss offset
+ * @length        length of register block offset
+ * @xin_id        xin id
+ * @hwversion     mdss hw version number
+ */
+struct dpu_hw_blk_reg_map {
+	void __iomem *base_off;
+	u32 blk_off;
+	u32 length;
+	u32 xin_id;
+	u32 hwversion;
+	u32 log_mask;
+};
+
+/**
+ * struct dpu_hw_scaler3_de_cfg : QSEEDv3 detail enhancer configuration
+ * @enable:         detail enhancer enable/disable
+ * @sharpen_level1: sharpening strength for noise
+ * @sharpen_level2: sharpening strength for signal
+ * @ clip:          clip shift
+ * @ limit:         limit value
+ * @ thr_quiet:     quiet threshold
+ * @ thr_dieout:    dieout threshold
+ * @ thr_high:      low threshold
+ * @ thr_high:      high threshold
+ * @ prec_shift:    precision shift
+ * @ adjust_a:      A-coefficients for mapping curve
+ * @ adjust_b:      B-coefficients for mapping curve
+ * @ adjust_c:      C-coefficients for mapping curve
+ */
+struct dpu_hw_scaler3_de_cfg {
+	u32 enable;
+	int16_t sharpen_level1;
+	int16_t sharpen_level2;
+	uint16_t clip;
+	uint16_t limit;
+	uint16_t thr_quiet;
+	uint16_t thr_dieout;
+	uint16_t thr_low;
+	uint16_t thr_high;
+	uint16_t prec_shift;
+	int16_t adjust_a[DPU_MAX_DE_CURVES];
+	int16_t adjust_b[DPU_MAX_DE_CURVES];
+	int16_t adjust_c[DPU_MAX_DE_CURVES];
+};
+
+
+/**
+ * struct dpu_hw_scaler3_cfg : QSEEDv3 configuration
+ * @enable:        scaler enable
+ * @dir_en:        direction detection block enable
+ * @ init_phase_x: horizontal initial phase
+ * @ phase_step_x: horizontal phase step
+ * @ init_phase_y: vertical initial phase
+ * @ phase_step_y: vertical phase step
+ * @ preload_x:    horizontal preload value
+ * @ preload_y:    vertical preload value
+ * @ src_width:    source width
+ * @ src_height:   source height
+ * @ dst_width:    destination width
+ * @ dst_height:   destination height
+ * @ y_rgb_filter_cfg: y/rgb plane filter configuration
+ * @ uv_filter_cfg: uv plane filter configuration
+ * @ alpha_filter_cfg: alpha filter configuration
+ * @ blend_cfg:    blend coefficients configuration
+ * @ lut_flag:     scaler LUT update flags
+ *                 0x1 swap LUT bank
+ *                 0x2 update 2D filter LUT
+ *                 0x4 update y circular filter LUT
+ *                 0x8 update uv circular filter LUT
+ *                 0x10 update y separable filter LUT
+ *                 0x20 update uv separable filter LUT
+ * @ dir_lut_idx:  2D filter LUT index
+ * @ y_rgb_cir_lut_idx: y circular filter LUT index
+ * @ uv_cir_lut_idx: uv circular filter LUT index
+ * @ y_rgb_sep_lut_idx: y circular filter LUT index
+ * @ uv_sep_lut_idx: uv separable filter LUT index
+ * @ dir_lut:      pointer to 2D LUT
+ * @ cir_lut:      pointer to circular filter LUT
+ * @ sep_lut:      pointer to separable filter LUT
+ * @ de: detail enhancer configuration
+ */
+struct dpu_hw_scaler3_cfg {
+	u32 enable;
+	u32 dir_en;
+	int32_t init_phase_x[DPU_MAX_PLANES];
+	int32_t phase_step_x[DPU_MAX_PLANES];
+	int32_t init_phase_y[DPU_MAX_PLANES];
+	int32_t phase_step_y[DPU_MAX_PLANES];
+
+	u32 preload_x[DPU_MAX_PLANES];
+	u32 preload_y[DPU_MAX_PLANES];
+	u32 src_width[DPU_MAX_PLANES];
+	u32 src_height[DPU_MAX_PLANES];
+
+	u32 dst_width;
+	u32 dst_height;
+
+	u32 y_rgb_filter_cfg;
+	u32 uv_filter_cfg;
+	u32 alpha_filter_cfg;
+	u32 blend_cfg;
+
+	u32 lut_flag;
+	u32 dir_lut_idx;
+
+	u32 y_rgb_cir_lut_idx;
+	u32 uv_cir_lut_idx;
+	u32 y_rgb_sep_lut_idx;
+	u32 uv_sep_lut_idx;
+	u32 *dir_lut;
+	size_t dir_len;
+	u32 *cir_lut;
+	size_t cir_len;
+	u32 *sep_lut;
+	size_t sep_len;
+
+	/*
+	 * Detail enhancer settings
+	 */
+	struct dpu_hw_scaler3_de_cfg de;
+};
+
+struct dpu_hw_scaler3_lut_cfg {
+	bool is_configured;
+	u32 *dir_lut;
+	size_t dir_len;
+	u32 *cir_lut;
+	size_t cir_len;
+	u32 *sep_lut;
+	size_t sep_len;
+};
+
+/**
+ * struct dpu_drm_pix_ext_v1 - version 1 of pixel ext structure
+ * @num_ext_pxls_lr: Number of total horizontal pixels
+ * @num_ext_pxls_tb: Number of total vertical lines
+ * @left_ftch:       Number of extra pixels to overfetch from left
+ * @right_ftch:      Number of extra pixels to overfetch from right
+ * @top_ftch:        Number of extra lines to overfetch from top
+ * @btm_ftch:        Number of extra lines to overfetch from bottom
+ * @left_rpt:        Number of extra pixels to repeat from left
+ * @right_rpt:       Number of extra pixels to repeat from right
+ * @top_rpt:         Number of extra lines to repeat from top
+ * @btm_rpt:         Number of extra lines to repeat from bottom
+ */
+struct dpu_drm_pix_ext_v1 {
+	/*
+	 * Number of pixels ext in left, right, top and bottom direction
+	 * for all color components.
+	 */
+	int32_t num_ext_pxls_lr[DPU_MAX_PLANES];
+	int32_t num_ext_pxls_tb[DPU_MAX_PLANES];
+
+	/*
+	 * Number of pixels needs to be overfetched in left, right, top
+	 * and bottom directions from source image for scaling.
+	 */
+	int32_t left_ftch[DPU_MAX_PLANES];
+	int32_t right_ftch[DPU_MAX_PLANES];
+	int32_t top_ftch[DPU_MAX_PLANES];
+	int32_t btm_ftch[DPU_MAX_PLANES];
+	/*
+	 * Number of pixels needs to be repeated in left, right, top and
+	 * bottom directions for scaling.
+	 */
+	int32_t left_rpt[DPU_MAX_PLANES];
+	int32_t right_rpt[DPU_MAX_PLANES];
+	int32_t top_rpt[DPU_MAX_PLANES];
+	int32_t btm_rpt[DPU_MAX_PLANES];
+
+};
+
+/**
+ * struct dpu_drm_de_v1 - version 1 of detail enhancer structure
+ * @enable:         Enables/disables detail enhancer
+ * @sharpen_level1: Sharpening strength for noise
+ * @sharpen_level2: Sharpening strength for context
+ * @clip:           Clip coefficient
+ * @limit:          Detail enhancer limit factor
+ * @thr_quiet:      Quite zone threshold
+ * @thr_dieout:     Die-out zone threshold
+ * @thr_low:        Linear zone left threshold
+ * @thr_high:       Linear zone right threshold
+ * @prec_shift:     Detail enhancer precision
+ * @adjust_a:       Mapping curves A coefficients
+ * @adjust_b:       Mapping curves B coefficients
+ * @adjust_c:       Mapping curves C coefficients
+ */
+struct dpu_drm_de_v1 {
+	uint32_t enable;
+	int16_t sharpen_level1;
+	int16_t sharpen_level2;
+	uint16_t clip;
+	uint16_t limit;
+	uint16_t thr_quiet;
+	uint16_t thr_dieout;
+	uint16_t thr_low;
+	uint16_t thr_high;
+	uint16_t prec_shift;
+	int16_t adjust_a[DPU_MAX_DE_CURVES];
+	int16_t adjust_b[DPU_MAX_DE_CURVES];
+	int16_t adjust_c[DPU_MAX_DE_CURVES];
+};
+
+/**
+ * struct dpu_drm_scaler_v2 - version 2 of struct dpu_drm_scaler
+ * @enable:            Scaler enable
+ * @dir_en:            Detail enhancer enable
+ * @pe:                Pixel extension settings
+ * @horz_decimate:     Horizontal decimation factor
+ * @vert_decimate:     Vertical decimation factor
+ * @init_phase_x:      Initial scaler phase values for x
+ * @phase_step_x:      Phase step values for x
+ * @init_phase_y:      Initial scaler phase values for y
+ * @phase_step_y:      Phase step values for y
+ * @preload_x:         Horizontal preload value
+ * @preload_y:         Vertical preload value
+ * @src_width:         Source width
+ * @src_height:        Source height
+ * @dst_width:         Destination width
+ * @dst_height:        Destination height
+ * @y_rgb_filter_cfg:  Y/RGB plane filter configuration
+ * @uv_filter_cfg:     UV plane filter configuration
+ * @alpha_filter_cfg:  Alpha filter configuration
+ * @blend_cfg:         Selection of blend coefficients
+ * @lut_flag:          LUT configuration flags
+ * @dir_lut_idx:       2d 4x4 LUT index
+ * @y_rgb_cir_lut_idx: Y/RGB circular LUT index
+ * @uv_cir_lut_idx:    UV circular LUT index
+ * @y_rgb_sep_lut_idx: Y/RGB separable LUT index
+ * @uv_sep_lut_idx:    UV separable LUT index
+ * @de:                Detail enhancer settings
+ */
+struct dpu_drm_scaler_v2 {
+	/*
+	 * General definitions
+	 */
+	uint32_t enable;
+	uint32_t dir_en;
+
+	/*
+	 * Pix ext settings
+	 */
+	struct dpu_drm_pix_ext_v1 pe;
+
+	/*
+	 * Decimation settings
+	 */
+	uint32_t horz_decimate;
+	uint32_t vert_decimate;
+
+	/*
+	 * Phase settings
+	 */
+	int32_t init_phase_x[DPU_MAX_PLANES];
+	int32_t phase_step_x[DPU_MAX_PLANES];
+	int32_t init_phase_y[DPU_MAX_PLANES];
+	int32_t phase_step_y[DPU_MAX_PLANES];
+
+	uint32_t preload_x[DPU_MAX_PLANES];
+	uint32_t preload_y[DPU_MAX_PLANES];
+	uint32_t src_width[DPU_MAX_PLANES];
+	uint32_t src_height[DPU_MAX_PLANES];
+
+	uint32_t dst_width;
+	uint32_t dst_height;
+
+	uint32_t y_rgb_filter_cfg;
+	uint32_t uv_filter_cfg;
+	uint32_t alpha_filter_cfg;
+	uint32_t blend_cfg;
+
+	uint32_t lut_flag;
+	uint32_t dir_lut_idx;
+
+	/* for Y(RGB) and UV planes*/
+	uint32_t y_rgb_cir_lut_idx;
+	uint32_t uv_cir_lut_idx;
+	uint32_t y_rgb_sep_lut_idx;
+	uint32_t uv_sep_lut_idx;
+
+	/*
+	 * Detail enhancer settings
+	 */
+	struct dpu_drm_de_v1 de;
+};
+
+
+u32 *dpu_hw_util_get_log_mask_ptr(void);
+
+void dpu_reg_write(struct dpu_hw_blk_reg_map *c,
+		u32 reg_off,
+		u32 val,
+		const char *name);
+int dpu_reg_read(struct dpu_hw_blk_reg_map *c, u32 reg_off);
+
+#define DPU_REG_WRITE(c, off, val) dpu_reg_write(c, off, val, #off)
+#define DPU_REG_READ(c, off) dpu_reg_read(c, off)
+
+#define MISR_FRAME_COUNT_MASK		0xFF
+#define MISR_CTRL_ENABLE		BIT(8)
+#define MISR_CTRL_STATUS		BIT(9)
+#define MISR_CTRL_STATUS_CLEAR		BIT(10)
+#define INTF_MISR_CTRL_FREE_RUN_MASK	BIT(31)
+
+void *dpu_hw_util_get_dir(void);
+
+void dpu_hw_setup_scaler3(struct dpu_hw_blk_reg_map *c,
+		struct dpu_hw_scaler3_cfg *scaler3_cfg,
+		u32 scaler_offset, u32 scaler_version,
+		const struct dpu_format *format);
+
+u32 dpu_hw_get_scaler3_ver(struct dpu_hw_blk_reg_map *c,
+		u32 scaler_offset);
+
+void dpu_hw_csc_setup(struct dpu_hw_blk_reg_map  *c,
+		u32 csc_reg_off,
+		struct dpu_csc_cfg *data, bool csc10);
+
+#endif /* _DPU_HW_UTIL_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c
new file mode 100644
index 000000000000..d43905525f92
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c
@@ -0,0 +1,275 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_vbif.h"
+#include "dpu_dbg.h"
+
+#define VBIF_VERSION			0x0000
+#define VBIF_CLK_FORCE_CTRL0		0x0008
+#define VBIF_CLK_FORCE_CTRL1		0x000C
+#define VBIF_QOS_REMAP_00		0x0020
+#define VBIF_QOS_REMAP_01		0x0024
+#define VBIF_QOS_REMAP_10		0x0028
+#define VBIF_QOS_REMAP_11		0x002C
+#define VBIF_WRITE_GATHER_EN		0x00AC
+#define VBIF_IN_RD_LIM_CONF0		0x00B0
+#define VBIF_IN_RD_LIM_CONF1		0x00B4
+#define VBIF_IN_RD_LIM_CONF2		0x00B8
+#define VBIF_IN_WR_LIM_CONF0		0x00C0
+#define VBIF_IN_WR_LIM_CONF1		0x00C4
+#define VBIF_IN_WR_LIM_CONF2		0x00C8
+#define VBIF_OUT_RD_LIM_CONF0		0x00D0
+#define VBIF_OUT_WR_LIM_CONF0		0x00D4
+#define VBIF_OUT_AXI_AMEMTYPE_CONF0	0x0160
+#define VBIF_OUT_AXI_AMEMTYPE_CONF1	0x0164
+#define VBIF_XIN_PND_ERR		0x0190
+#define VBIF_XIN_SRC_ERR		0x0194
+#define VBIF_XIN_CLR_ERR		0x019C
+#define VBIF_XIN_HALT_CTRL0		0x0200
+#define VBIF_XIN_HALT_CTRL1		0x0204
+#define VBIF_XINL_QOS_RP_REMAP_000	0x0550
+#define VBIF_XINL_QOS_LVL_REMAP_000	0x0590
+
+static void dpu_hw_clear_errors(struct dpu_hw_vbif *vbif,
+		u32 *pnd_errors, u32 *src_errors)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 pnd, src;
+
+	if (!vbif)
+		return;
+	c = &vbif->hw;
+	pnd = DPU_REG_READ(c, VBIF_XIN_PND_ERR);
+	src = DPU_REG_READ(c, VBIF_XIN_SRC_ERR);
+
+	if (pnd_errors)
+		*pnd_errors = pnd;
+	if (src_errors)
+		*src_errors = src;
+
+	DPU_REG_WRITE(c, VBIF_XIN_CLR_ERR, pnd | src);
+}
+
+static void dpu_hw_set_mem_type(struct dpu_hw_vbif *vbif,
+		u32 xin_id, u32 value)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg_off;
+	u32 bit_off;
+	u32 reg_val;
+
+	/*
+	 * Assume 4 bits per bit field, 8 fields per 32-bit register so
+	 * 16 bit fields maximum across two registers
+	 */
+	if (!vbif || xin_id >= MAX_XIN_COUNT || xin_id >= 16)
+		return;
+
+	c = &vbif->hw;
+
+	if (xin_id >= 8) {
+		xin_id -= 8;
+		reg_off = VBIF_OUT_AXI_AMEMTYPE_CONF1;
+	} else {
+		reg_off = VBIF_OUT_AXI_AMEMTYPE_CONF0;
+	}
+	bit_off = (xin_id & 0x7) * 4;
+	reg_val = DPU_REG_READ(c, reg_off);
+	reg_val &= ~(0x7 << bit_off);
+	reg_val |= (value & 0x7) << bit_off;
+	DPU_REG_WRITE(c, reg_off, reg_val);
+}
+
+static void dpu_hw_set_limit_conf(struct dpu_hw_vbif *vbif,
+		u32 xin_id, bool rd, u32 limit)
+{
+	struct dpu_hw_blk_reg_map *c = &vbif->hw;
+	u32 reg_val;
+	u32 reg_off;
+	u32 bit_off;
+
+	if (rd)
+		reg_off = VBIF_IN_RD_LIM_CONF0;
+	else
+		reg_off = VBIF_IN_WR_LIM_CONF0;
+
+	reg_off += (xin_id / 4) * 4;
+	bit_off = (xin_id % 4) * 8;
+	reg_val = DPU_REG_READ(c, reg_off);
+	reg_val &= ~(0xFF << bit_off);
+	reg_val |= (limit) << bit_off;
+	DPU_REG_WRITE(c, reg_off, reg_val);
+}
+
+static u32 dpu_hw_get_limit_conf(struct dpu_hw_vbif *vbif,
+		u32 xin_id, bool rd)
+{
+	struct dpu_hw_blk_reg_map *c = &vbif->hw;
+	u32 reg_val;
+	u32 reg_off;
+	u32 bit_off;
+	u32 limit;
+
+	if (rd)
+		reg_off = VBIF_IN_RD_LIM_CONF0;
+	else
+		reg_off = VBIF_IN_WR_LIM_CONF0;
+
+	reg_off += (xin_id / 4) * 4;
+	bit_off = (xin_id % 4) * 8;
+	reg_val = DPU_REG_READ(c, reg_off);
+	limit = (reg_val >> bit_off) & 0xFF;
+
+	return limit;
+}
+
+static void dpu_hw_set_halt_ctrl(struct dpu_hw_vbif *vbif,
+		u32 xin_id, bool enable)
+{
+	struct dpu_hw_blk_reg_map *c = &vbif->hw;
+	u32 reg_val;
+
+	reg_val = DPU_REG_READ(c, VBIF_XIN_HALT_CTRL0);
+
+	if (enable)
+		reg_val |= BIT(xin_id);
+	else
+		reg_val &= ~BIT(xin_id);
+
+	DPU_REG_WRITE(c, VBIF_XIN_HALT_CTRL0, reg_val);
+}
+
+static bool dpu_hw_get_halt_ctrl(struct dpu_hw_vbif *vbif,
+		u32 xin_id)
+{
+	struct dpu_hw_blk_reg_map *c = &vbif->hw;
+	u32 reg_val;
+
+	reg_val = DPU_REG_READ(c, VBIF_XIN_HALT_CTRL1);
+
+	return (reg_val & BIT(xin_id)) ? true : false;
+}
+
+static void dpu_hw_set_qos_remap(struct dpu_hw_vbif *vbif,
+		u32 xin_id, u32 level, u32 remap_level)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg_val, reg_val_lvl, mask, reg_high, reg_shift;
+
+	if (!vbif)
+		return;
+
+	c = &vbif->hw;
+
+	reg_high = ((xin_id & 0x8) >> 3) * 4 + (level * 8);
+	reg_shift = (xin_id & 0x7) * 4;
+
+	reg_val = DPU_REG_READ(c, VBIF_XINL_QOS_RP_REMAP_000 + reg_high);
+	reg_val_lvl = DPU_REG_READ(c, VBIF_XINL_QOS_LVL_REMAP_000 + reg_high);
+
+	mask = 0x7 << reg_shift;
+
+	reg_val &= ~mask;
+	reg_val |= (remap_level << reg_shift) & mask;
+
+	reg_val_lvl &= ~mask;
+	reg_val_lvl |= (remap_level << reg_shift) & mask;
+
+	DPU_REG_WRITE(c, VBIF_XINL_QOS_RP_REMAP_000 + reg_high, reg_val);
+	DPU_REG_WRITE(c, VBIF_XINL_QOS_LVL_REMAP_000 + reg_high, reg_val_lvl);
+}
+
+static void dpu_hw_set_write_gather_en(struct dpu_hw_vbif *vbif, u32 xin_id)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg_val;
+
+	if (!vbif || xin_id >= MAX_XIN_COUNT)
+		return;
+
+	c = &vbif->hw;
+
+	reg_val = DPU_REG_READ(c, VBIF_WRITE_GATHER_EN);
+	reg_val |= BIT(xin_id);
+	DPU_REG_WRITE(c, VBIF_WRITE_GATHER_EN, reg_val);
+}
+
+static void _setup_vbif_ops(struct dpu_hw_vbif_ops *ops,
+		unsigned long cap)
+{
+	ops->set_limit_conf = dpu_hw_set_limit_conf;
+	ops->get_limit_conf = dpu_hw_get_limit_conf;
+	ops->set_halt_ctrl = dpu_hw_set_halt_ctrl;
+	ops->get_halt_ctrl = dpu_hw_get_halt_ctrl;
+	if (test_bit(DPU_VBIF_QOS_REMAP, &cap))
+		ops->set_qos_remap = dpu_hw_set_qos_remap;
+	ops->set_mem_type = dpu_hw_set_mem_type;
+	ops->clear_errors = dpu_hw_clear_errors;
+	ops->set_write_gather_en = dpu_hw_set_write_gather_en;
+}
+
+static const struct dpu_vbif_cfg *_top_offset(enum dpu_vbif vbif,
+		const struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->vbif_count; i++) {
+		if (vbif == m->vbif[i].id) {
+			b->base_off = addr;
+			b->blk_off = m->vbif[i].base;
+			b->length = m->vbif[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_VBIF;
+			return &m->vbif[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+struct dpu_hw_vbif *dpu_hw_vbif_init(enum dpu_vbif idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_vbif *c;
+	const struct dpu_vbif_cfg *cfg;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _top_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/*
+	 * Assign ops
+	 */
+	c->idx = idx;
+	c->cap = cfg;
+	_setup_vbif_ops(&c->ops, c->cap->features);
+
+	/* no need to register sub-range in dpu dbg, dump entire vbif io base */
+
+	return c;
+}
+
+void dpu_hw_vbif_destroy(struct dpu_hw_vbif *vbif)
+{
+	kfree(vbif);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.h
new file mode 100644
index 000000000000..471ff673c045
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.h
@@ -0,0 +1,128 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_VBIF_H
+#define _DPU_HW_VBIF_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+
+struct dpu_hw_vbif;
+
+/**
+ * struct dpu_hw_vbif_ops : Interface to the VBIF hardware driver functions
+ *  Assumption is these functions will be called after clocks are enabled
+ */
+struct dpu_hw_vbif_ops {
+	/**
+	 * set_limit_conf - set transaction limit config
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @rd: true for read limit; false for write limit
+	 * @limit: outstanding transaction limit
+	 */
+	void (*set_limit_conf)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, bool rd, u32 limit);
+
+	/**
+	 * get_limit_conf - get transaction limit config
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @rd: true for read limit; false for write limit
+	 * @return: outstanding transaction limit
+	 */
+	u32 (*get_limit_conf)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, bool rd);
+
+	/**
+	 * set_halt_ctrl - set halt control
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @enable: halt control enable
+	 */
+	void (*set_halt_ctrl)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, bool enable);
+
+	/**
+	 * get_halt_ctrl - get halt control
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @return: halt control enable
+	 */
+	bool (*get_halt_ctrl)(struct dpu_hw_vbif *vbif,
+			u32 xin_id);
+
+	/**
+	 * set_qos_remap - set QoS priority remap
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @level: priority level
+	 * @remap_level: remapped level
+	 */
+	void (*set_qos_remap)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, u32 level, u32 remap_level);
+
+	/**
+	 * set_mem_type - set memory type
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @value: memory type value
+	 */
+	void (*set_mem_type)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, u32 value);
+
+	/**
+	 * clear_errors - clear any vbif errors
+	 *	This function clears any detected pending/source errors
+	 *	on the VBIF interface, and optionally returns the detected
+	 *	error mask(s).
+	 * @vbif: vbif context driver
+	 * @pnd_errors: pointer to pending error reporting variable
+	 * @src_errors: pointer to source error reporting variable
+	 */
+	void (*clear_errors)(struct dpu_hw_vbif *vbif,
+		u32 *pnd_errors, u32 *src_errors);
+
+	/**
+	 * set_write_gather_en - set write_gather enable
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 */
+	void (*set_write_gather_en)(struct dpu_hw_vbif *vbif, u32 xin_id);
+};
+
+struct dpu_hw_vbif {
+	/* base */
+	struct dpu_hw_blk_reg_map hw;
+
+	/* vbif */
+	enum dpu_vbif idx;
+	const struct dpu_vbif_cfg *cap;
+
+	/* ops */
+	struct dpu_hw_vbif_ops ops;
+};
+
+/**
+ * dpu_hw_vbif_init - initializes the vbif driver for the passed interface idx
+ * @idx:  Interface index for which driver object is required
+ * @addr: Mapped register io address of MDSS
+ * @m:    Pointer to mdss catalog data
+ */
+struct dpu_hw_vbif *dpu_hw_vbif_init(enum dpu_vbif idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m);
+
+void dpu_hw_vbif_destroy(struct dpu_hw_vbif *vbif);
+
+#endif /*_DPU_HW_VBIF_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h
new file mode 100644
index 000000000000..5b2bc9b65b15
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h
@@ -0,0 +1,56 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HWIO_H
+#define _DPU_HWIO_H
+
+#include "dpu_hw_util.h"
+
+/**
+ * MDP TOP block Register and bit fields and defines
+ */
+#define DISP_INTF_SEL                   0x004
+#define INTR_EN                         0x010
+#define INTR_STATUS                     0x014
+#define INTR_CLEAR                      0x018
+#define INTR2_EN                        0x008
+#define INTR2_STATUS                    0x00c
+#define INTR2_CLEAR                     0x02c
+#define HIST_INTR_EN                    0x01c
+#define HIST_INTR_STATUS                0x020
+#define HIST_INTR_CLEAR                 0x024
+#define INTF_INTR_EN                    0x1C0
+#define INTF_INTR_STATUS                0x1C4
+#define INTF_INTR_CLEAR                 0x1C8
+#define SPLIT_DISPLAY_EN                0x2F4
+#define SPLIT_DISPLAY_UPPER_PIPE_CTRL   0x2F8
+#define DSPP_IGC_COLOR0_RAM_LUTN        0x300
+#define DSPP_IGC_COLOR1_RAM_LUTN        0x304
+#define DSPP_IGC_COLOR2_RAM_LUTN        0x308
+#define HW_EVENTS_CTL                   0x37C
+#define CLK_CTRL3                       0x3A8
+#define CLK_STATUS3                     0x3AC
+#define CLK_CTRL4                       0x3B0
+#define CLK_STATUS4                     0x3B4
+#define CLK_CTRL5                       0x3B8
+#define CLK_STATUS5                     0x3BC
+#define CLK_CTRL7                       0x3D0
+#define CLK_STATUS7                     0x3D4
+#define SPLIT_DISPLAY_LOWER_PIPE_CTRL   0x3F0
+#define SPLIT_DISPLAY_TE_LINE_INTERVAL  0x3F4
+#define INTF_SW_RESET_MASK              0x3FC
+#define HDMI_DP_CORE_SELECT             0x408
+#define MDP_OUT_CTL_0                   0x410
+#define MDP_VSYNC_SEL                   0x414
+#define DCE_SEL                         0x450
+
+#endif /*_DPU_HWIO_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
new file mode 100644
index 000000000000..790d39f816dc
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
@@ -0,0 +1,203 @@
+/* Copyright (c) 2012-2015, 2017-2018, The Linux Foundation.
+ * All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/clk/clk-conf.h>
+#include <linux/err.h>
+#include <linux/delay.h>
+
+#include "dpu_io_util.h"
+
+void msm_dss_put_clk(struct dss_clk *clk_arry, int num_clk)
+{
+	int i;
+
+	for (i = num_clk - 1; i >= 0; i--) {
+		if (clk_arry[i].clk)
+			clk_put(clk_arry[i].clk);
+		clk_arry[i].clk = NULL;
+	}
+}
+
+int msm_dss_get_clk(struct device *dev, struct dss_clk *clk_arry, int num_clk)
+{
+	int i, rc = 0;
+
+	for (i = 0; i < num_clk; i++) {
+		clk_arry[i].clk = clk_get(dev, clk_arry[i].clk_name);
+		rc = PTR_ERR_OR_ZERO(clk_arry[i].clk);
+		if (rc) {
+			DEV_ERR("%pS->%s: '%s' get failed. rc=%d\n",
+				__builtin_return_address(0), __func__,
+				clk_arry[i].clk_name, rc);
+			goto error;
+		}
+	}
+
+	return rc;
+
+error:
+	for (i--; i >= 0; i--) {
+		if (clk_arry[i].clk)
+			clk_put(clk_arry[i].clk);
+		clk_arry[i].clk = NULL;
+	}
+
+	return rc;
+}
+
+int msm_dss_clk_set_rate(struct dss_clk *clk_arry, int num_clk)
+{
+	int i, rc = 0;
+
+	for (i = 0; i < num_clk; i++) {
+		if (clk_arry[i].clk) {
+			if (clk_arry[i].type != DSS_CLK_AHB) {
+				DEV_DBG("%pS->%s: '%s' rate %ld\n",
+					__builtin_return_address(0), __func__,
+					clk_arry[i].clk_name,
+					clk_arry[i].rate);
+				rc = clk_set_rate(clk_arry[i].clk,
+					clk_arry[i].rate);
+				if (rc) {
+					DEV_ERR("%pS->%s: %s failed. rc=%d\n",
+						__builtin_return_address(0),
+						__func__,
+						clk_arry[i].clk_name, rc);
+					break;
+				}
+			}
+		} else {
+			DEV_ERR("%pS->%s: '%s' is not available\n",
+				__builtin_return_address(0), __func__,
+				clk_arry[i].clk_name);
+			rc = -EPERM;
+			break;
+		}
+	}
+
+	return rc;
+}
+
+int msm_dss_enable_clk(struct dss_clk *clk_arry, int num_clk, int enable)
+{
+	int i, rc = 0;
+
+	if (enable) {
+		for (i = 0; i < num_clk; i++) {
+			DEV_DBG("%pS->%s: enable '%s'\n",
+				__builtin_return_address(0), __func__,
+				clk_arry[i].clk_name);
+			if (clk_arry[i].clk) {
+				rc = clk_prepare_enable(clk_arry[i].clk);
+				if (rc)
+					DEV_ERR("%pS->%s: %s en fail. rc=%d\n",
+						__builtin_return_address(0),
+						__func__,
+						clk_arry[i].clk_name, rc);
+			} else {
+				DEV_ERR("%pS->%s: '%s' is not available\n",
+					__builtin_return_address(0), __func__,
+					clk_arry[i].clk_name);
+				rc = -EPERM;
+			}
+
+			if (rc) {
+				msm_dss_enable_clk(&clk_arry[i],
+					i, false);
+				break;
+			}
+		}
+	} else {
+		for (i = num_clk - 1; i >= 0; i--) {
+			DEV_DBG("%pS->%s: disable '%s'\n",
+				__builtin_return_address(0), __func__,
+				clk_arry[i].clk_name);
+
+			if (clk_arry[i].clk)
+				clk_disable_unprepare(clk_arry[i].clk);
+			else
+				DEV_ERR("%pS->%s: '%s' is not available\n",
+					__builtin_return_address(0), __func__,
+					clk_arry[i].clk_name);
+		}
+	}
+
+	return rc;
+}
+
+int msm_dss_parse_clock(struct platform_device *pdev,
+			struct dss_module_power *mp)
+{
+	u32 i, rc = 0;
+	const char *clock_name;
+	int num_clk = 0;
+
+	if (!pdev || !mp)
+		return -EINVAL;
+
+	mp->num_clk = 0;
+	num_clk = of_property_count_strings(pdev->dev.of_node, "clock-names");
+	if (num_clk <= 0) {
+		pr_debug("clocks are not defined\n");
+		return 0;
+	}
+
+	mp->clk_config = devm_kzalloc(&pdev->dev,
+				      sizeof(struct dss_clk) * num_clk,
+				      GFP_KERNEL);
+	if (!mp->clk_config)
+		return -ENOMEM;
+
+	for (i = 0; i < num_clk; i++) {
+		rc = of_property_read_string_index(pdev->dev.of_node,
+						   "clock-names", i,
+						   &clock_name);
+		if (rc) {
+			dev_err(&pdev->dev, "Failed to get clock name for %d\n",
+				i);
+			break;
+		}
+		strlcpy(mp->clk_config[i].clk_name, clock_name,
+			sizeof(mp->clk_config[i].clk_name));
+
+		mp->clk_config[i].type = DSS_CLK_AHB;
+	}
+
+	rc = msm_dss_get_clk(&pdev->dev, mp->clk_config, num_clk);
+	if (rc) {
+		dev_err(&pdev->dev, "Failed to get clock refs %d\n", rc);
+		goto err;
+	}
+
+	rc = of_clk_set_defaults(pdev->dev.of_node, false);
+	if (rc) {
+		dev_err(&pdev->dev, "Failed to set clock defaults %d\n", rc);
+		goto err;
+	}
+
+	for (i = 0; i < num_clk; i++) {
+		u32 rate = clk_get_rate(mp->clk_config[i].clk);
+		if (!rate)
+			continue;
+		mp->clk_config[i].rate = rate;
+		mp->clk_config[i].type = DSS_CLK_PCLK;
+	}
+
+	mp->num_clk = num_clk;
+	return 0;
+
+err:
+	msm_dss_put_clk(mp->clk_config, num_clk);
+	return rc;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.h
new file mode 100644
index 000000000000..bc07381d7429
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.h
@@ -0,0 +1,57 @@
+/* Copyright (c) 2012, 2017-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DPU_IO_UTIL_H__
+#define __DPU_IO_UTIL_H__
+
+#include <linux/gpio.h>
+#include <linux/platform_device.h>
+#include <linux/types.h>
+
+#define DEV_DBG(fmt, args...)   pr_debug(fmt, ##args)
+#define DEV_INFO(fmt, args...)  pr_info(fmt, ##args)
+#define DEV_WARN(fmt, args...)  pr_warn(fmt, ##args)
+#define DEV_ERR(fmt, args...)   pr_err(fmt, ##args)
+
+struct dss_gpio {
+	unsigned int gpio;
+	unsigned int value;
+	char gpio_name[32];
+};
+
+enum dss_clk_type {
+	DSS_CLK_AHB, /* no set rate. rate controlled through rpm */
+	DSS_CLK_PCLK,
+};
+
+struct dss_clk {
+	struct clk *clk; /* clk handle */
+	char clk_name[32];
+	enum dss_clk_type type;
+	unsigned long rate;
+	unsigned long max_rate;
+};
+
+struct dss_module_power {
+	unsigned int num_gpio;
+	struct dss_gpio *gpio_config;
+	unsigned int num_clk;
+	struct dss_clk *clk_config;
+};
+
+int msm_dss_get_clk(struct device *dev, struct dss_clk *clk_arry, int num_clk);
+void msm_dss_put_clk(struct dss_clk *clk_arry, int num_clk);
+int msm_dss_clk_set_rate(struct dss_clk *clk_arry, int num_clk);
+int msm_dss_enable_clk(struct dss_clk *clk_arry, int num_clk, int enable);
+int msm_dss_parse_clock(struct platform_device *pdev,
+		struct dss_module_power *mp);
+#endif /* __DPU_IO_UTIL_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.c
new file mode 100644
index 000000000000..d5e6ce0140cf
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.c
@@ -0,0 +1,66 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/irqdomain.h>
+#include <linux/irq.h>
+#include <linux/kthread.h>
+
+#include "dpu_irq.h"
+#include "dpu_core_irq.h"
+
+irqreturn_t dpu_irq(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+
+	return dpu_core_irq(dpu_kms);
+}
+
+void dpu_irq_preinstall(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+
+	if (!dpu_kms->dev || !dpu_kms->dev->dev) {
+		pr_err("invalid device handles\n");
+		return;
+	}
+
+	dpu_core_irq_preinstall(dpu_kms);
+}
+
+int dpu_irq_postinstall(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+	int rc;
+
+	if (!kms) {
+		DPU_ERROR("invalid parameters\n");
+		return -EINVAL;
+	}
+
+	rc = dpu_core_irq_postinstall(dpu_kms);
+
+	return rc;
+}
+
+void dpu_irq_uninstall(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+
+	if (!kms) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	dpu_core_irq_uninstall(dpu_kms);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.h
new file mode 100644
index 000000000000..3e147f7176e2
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.h
@@ -0,0 +1,59 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DPU_IRQ_H__
+#define __DPU_IRQ_H__
+
+#include <linux/kernel.h>
+#include <linux/irqdomain.h>
+
+#include "msm_kms.h"
+
+/**
+ * dpu_irq_controller - define MDSS level interrupt controller context
+ * @enabled_mask:	enable status of MDSS level interrupt
+ * @domain:		interrupt domain of this controller
+ */
+struct dpu_irq_controller {
+	unsigned long enabled_mask;
+	struct irq_domain *domain;
+};
+
+/**
+ * dpu_irq_preinstall - perform pre-installation of MDSS IRQ handler
+ * @kms:		pointer to kms context
+ * @return:		none
+ */
+void dpu_irq_preinstall(struct msm_kms *kms);
+
+/**
+ * dpu_irq_postinstall - perform post-installation of MDSS IRQ handler
+ * @kms:		pointer to kms context
+ * @return:		0 if success; error code otherwise
+ */
+int dpu_irq_postinstall(struct msm_kms *kms);
+
+/**
+ * dpu_irq_uninstall - uninstall MDSS IRQ handler
+ * @drm_dev:		pointer to kms context
+ * @return:		none
+ */
+void dpu_irq_uninstall(struct msm_kms *kms);
+
+/**
+ * dpu_irq - MDSS level IRQ handler
+ * @kms:		pointer to kms context
+ * @return:		interrupt handling status
+ */
+irqreturn_t dpu_irq(struct msm_kms *kms);
+
+#endif /* __DPU_IRQ_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
new file mode 100644
index 000000000000..7dd6bd2d6d37
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -0,0 +1,1345 @@
+/*
+ * Copyright (c) 2014-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <drm/drm_crtc.h>
+#include <linux/debugfs.h>
+#include <linux/of_irq.h>
+#include <linux/dma-buf.h>
+
+#include "msm_drv.h"
+#include "msm_mmu.h"
+#include "msm_gem.h"
+
+#include "dpu_kms.h"
+#include "dpu_core_irq.h"
+#include "dpu_formats.h"
+#include "dpu_hw_vbif.h"
+#include "dpu_vbif.h"
+#include "dpu_encoder.h"
+#include "dpu_plane.h"
+#include "dpu_crtc.h"
+
+#define CREATE_TRACE_POINTS
+#include "dpu_trace.h"
+
+static const char * const iommu_ports[] = {
+		"mdp_0",
+};
+
+/*
+ * To enable overall DRM driver logging
+ * # echo 0x2 > /sys/module/drm/parameters/debug
+ *
+ * To enable DRM driver h/w logging
+ * # echo <mask> > /sys/kernel/debug/dri/0/debug/hw_log_mask
+ *
+ * See dpu_hw_mdss.h for h/w logging mask definitions (search for DPU_DBG_MASK_)
+ */
+#define DPU_DEBUGFS_DIR "msm_dpu"
+#define DPU_DEBUGFS_HWMASKNAME "hw_log_mask"
+
+static int dpu_kms_hw_init(struct msm_kms *kms);
+static int _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms);
+
+static unsigned long dpu_iomap_size(struct platform_device *pdev,
+				    const char *name)
+{
+	struct resource *res;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, name);
+	if (!res) {
+		DRM_ERROR("failed to get memory resource: %s\n", name);
+		return 0;
+	}
+
+	return resource_size(res);
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int _dpu_danger_signal_status(struct seq_file *s,
+		bool danger_status)
+{
+	struct dpu_kms *kms = (struct dpu_kms *)s->private;
+	struct msm_drm_private *priv;
+	struct dpu_danger_safe_status status;
+	int i;
+
+	if (!kms || !kms->dev || !kms->dev->dev_private || !kms->hw_mdp) {
+		DPU_ERROR("invalid arg(s)\n");
+		return 0;
+	}
+
+	priv = kms->dev->dev_private;
+	memset(&status, 0, sizeof(struct dpu_danger_safe_status));
+
+	pm_runtime_get_sync(&kms->pdev->dev);
+	if (danger_status) {
+		seq_puts(s, "\nDanger signal status:\n");
+		if (kms->hw_mdp->ops.get_danger_status)
+			kms->hw_mdp->ops.get_danger_status(kms->hw_mdp,
+					&status);
+	} else {
+		seq_puts(s, "\nSafe signal status:\n");
+		if (kms->hw_mdp->ops.get_danger_status)
+			kms->hw_mdp->ops.get_danger_status(kms->hw_mdp,
+					&status);
+	}
+	pm_runtime_put_sync(&kms->pdev->dev);
+
+	seq_printf(s, "MDP     :  0x%x\n", status.mdp);
+
+	for (i = SSPP_VIG0; i < SSPP_MAX; i++)
+		seq_printf(s, "SSPP%d   :  0x%x  \t", i - SSPP_VIG0,
+				status.sspp[i]);
+	seq_puts(s, "\n");
+
+	return 0;
+}
+
+#define DEFINE_DPU_DEBUGFS_SEQ_FOPS(__prefix)				\
+static int __prefix ## _open(struct inode *inode, struct file *file)	\
+{									\
+	return single_open(file, __prefix ## _show, inode->i_private);	\
+}									\
+static const struct file_operations __prefix ## _fops = {		\
+	.owner = THIS_MODULE,						\
+	.open = __prefix ## _open,					\
+	.release = single_release,					\
+	.read = seq_read,						\
+	.llseek = seq_lseek,						\
+}
+
+static int dpu_debugfs_danger_stats_show(struct seq_file *s, void *v)
+{
+	return _dpu_danger_signal_status(s, true);
+}
+DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_debugfs_danger_stats);
+
+static int dpu_debugfs_safe_stats_show(struct seq_file *s, void *v)
+{
+	return _dpu_danger_signal_status(s, false);
+}
+DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_debugfs_safe_stats);
+
+static void dpu_debugfs_danger_destroy(struct dpu_kms *dpu_kms)
+{
+	debugfs_remove_recursive(dpu_kms->debugfs_danger);
+	dpu_kms->debugfs_danger = NULL;
+}
+
+static int dpu_debugfs_danger_init(struct dpu_kms *dpu_kms,
+		struct dentry *parent)
+{
+	dpu_kms->debugfs_danger = debugfs_create_dir("danger",
+			parent);
+	if (!dpu_kms->debugfs_danger) {
+		DPU_ERROR("failed to create danger debugfs\n");
+		return -EINVAL;
+	}
+
+	debugfs_create_file("danger_status", 0600, dpu_kms->debugfs_danger,
+			dpu_kms, &dpu_debugfs_danger_stats_fops);
+	debugfs_create_file("safe_status", 0600, dpu_kms->debugfs_danger,
+			dpu_kms, &dpu_debugfs_safe_stats_fops);
+
+	return 0;
+}
+
+static int _dpu_debugfs_show_regset32(struct seq_file *s, void *data)
+{
+	struct dpu_debugfs_regset32 *regset;
+	struct dpu_kms *dpu_kms;
+	struct drm_device *dev;
+	struct msm_drm_private *priv;
+	void __iomem *base;
+	uint32_t i, addr;
+
+	if (!s || !s->private)
+		return 0;
+
+	regset = s->private;
+
+	dpu_kms = regset->dpu_kms;
+	if (!dpu_kms || !dpu_kms->mmio)
+		return 0;
+
+	dev = dpu_kms->dev;
+	if (!dev)
+		return 0;
+
+	priv = dev->dev_private;
+	if (!priv)
+		return 0;
+
+	base = dpu_kms->mmio + regset->offset;
+
+	/* insert padding spaces, if needed */
+	if (regset->offset & 0xF) {
+		seq_printf(s, "[%x]", regset->offset & ~0xF);
+		for (i = 0; i < (regset->offset & 0xF); i += 4)
+			seq_puts(s, "         ");
+	}
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+
+	/* main register output */
+	for (i = 0; i < regset->blk_len; i += 4) {
+		addr = regset->offset + i;
+		if ((addr & 0xF) == 0x0)
+			seq_printf(s, i ? "\n[%x]" : "[%x]", addr);
+		seq_printf(s, " %08x", readl_relaxed(base + i));
+	}
+	seq_puts(s, "\n");
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	return 0;
+}
+
+static int dpu_debugfs_open_regset32(struct inode *inode,
+		struct file *file)
+{
+	return single_open(file, _dpu_debugfs_show_regset32, inode->i_private);
+}
+
+static const struct file_operations dpu_fops_regset32 = {
+	.open =		dpu_debugfs_open_regset32,
+	.read =		seq_read,
+	.llseek =	seq_lseek,
+	.release =	single_release,
+};
+
+void dpu_debugfs_setup_regset32(struct dpu_debugfs_regset32 *regset,
+		uint32_t offset, uint32_t length, struct dpu_kms *dpu_kms)
+{
+	if (regset) {
+		regset->offset = offset;
+		regset->blk_len = length;
+		regset->dpu_kms = dpu_kms;
+	}
+}
+
+void *dpu_debugfs_create_regset32(const char *name, umode_t mode,
+		void *parent, struct dpu_debugfs_regset32 *regset)
+{
+	if (!name || !regset || !regset->dpu_kms || !regset->blk_len)
+		return NULL;
+
+	/* make sure offset is a multiple of 4 */
+	regset->offset = round_down(regset->offset, 4);
+
+	return debugfs_create_file(name, mode, parent,
+			regset, &dpu_fops_regset32);
+}
+
+static int _dpu_debugfs_init(struct dpu_kms *dpu_kms)
+{
+	void *p;
+	int rc;
+
+	p = dpu_hw_util_get_log_mask_ptr();
+
+	if (!dpu_kms || !p)
+		return -EINVAL;
+
+	dpu_kms->debugfs_root = debugfs_create_dir("debug",
+					   dpu_kms->dev->primary->debugfs_root);
+	if (IS_ERR_OR_NULL(dpu_kms->debugfs_root)) {
+		DRM_ERROR("debugfs create_dir failed %ld\n",
+			  PTR_ERR(dpu_kms->debugfs_root));
+		return PTR_ERR(dpu_kms->debugfs_root);
+	}
+
+	rc = dpu_dbg_debugfs_register(dpu_kms->debugfs_root);
+	if (rc) {
+		DRM_ERROR("failed to reg dpu dbg debugfs: %d\n", rc);
+		return rc;
+	}
+
+	/* allow root to be NULL */
+	debugfs_create_x32(DPU_DEBUGFS_HWMASKNAME, 0600, dpu_kms->debugfs_root, p);
+
+	(void) dpu_debugfs_danger_init(dpu_kms, dpu_kms->debugfs_root);
+	(void) dpu_debugfs_vbif_init(dpu_kms, dpu_kms->debugfs_root);
+	(void) dpu_debugfs_core_irq_init(dpu_kms, dpu_kms->debugfs_root);
+
+	rc = dpu_core_perf_debugfs_init(&dpu_kms->perf, dpu_kms->debugfs_root);
+	if (rc) {
+		DPU_ERROR("failed to init perf %d\n", rc);
+		return rc;
+	}
+
+	return 0;
+}
+
+static void _dpu_debugfs_destroy(struct dpu_kms *dpu_kms)
+{
+	/* don't need to NULL check debugfs_root */
+	if (dpu_kms) {
+		dpu_debugfs_vbif_destroy(dpu_kms);
+		dpu_debugfs_danger_destroy(dpu_kms);
+		dpu_debugfs_core_irq_destroy(dpu_kms);
+		debugfs_remove_recursive(dpu_kms->debugfs_root);
+	}
+}
+#else
+static void _dpu_debugfs_destroy(struct dpu_kms *dpu_kms)
+{
+}
+#endif
+
+static int dpu_kms_enable_vblank(struct msm_kms *kms, struct drm_crtc *crtc)
+{
+	return dpu_crtc_vblank(crtc, true);
+}
+
+static void dpu_kms_disable_vblank(struct msm_kms *kms, struct drm_crtc *crtc)
+{
+	dpu_crtc_vblank(crtc, false);
+}
+
+static void dpu_kms_prepare_commit(struct msm_kms *kms,
+		struct drm_atomic_state *state)
+{
+	struct dpu_kms *dpu_kms;
+	struct msm_drm_private *priv;
+	struct drm_device *dev;
+	struct drm_encoder *encoder;
+
+	if (!kms)
+		return;
+	dpu_kms = to_dpu_kms(kms);
+	dev = dpu_kms->dev;
+
+	if (!dev || !dev->dev_private)
+		return;
+	priv = dev->dev_private;
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head)
+		if (encoder->crtc != NULL)
+			dpu_encoder_prepare_commit(encoder);
+}
+
+/*
+ * Override the encoder enable since we need to setup the inline rotator and do
+ * some crtc magic before enabling any bridge that might be present.
+ */
+void dpu_kms_encoder_enable(struct drm_encoder *encoder)
+{
+	const struct drm_encoder_helper_funcs *funcs = encoder->helper_private;
+	struct drm_crtc *crtc = encoder->crtc;
+
+	/* Forward this enable call to the commit hook */
+	if (funcs && funcs->commit)
+		funcs->commit(encoder);
+
+	if (crtc && crtc->state->active) {
+		trace_dpu_kms_enc_enable(DRMID(crtc));
+		dpu_crtc_commit_kickoff(crtc);
+	}
+}
+
+static void dpu_kms_commit(struct msm_kms *kms, struct drm_atomic_state *state)
+{
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+	int i;
+
+	for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
+		/* If modeset is required, kickoff is run in encoder_enable */
+		if (drm_atomic_crtc_needs_modeset(crtc_state))
+			continue;
+
+		if (crtc->state->active) {
+			trace_dpu_kms_commit(DRMID(crtc));
+			dpu_crtc_commit_kickoff(crtc);
+		}
+	}
+}
+
+static void dpu_kms_complete_commit(struct msm_kms *kms,
+		struct drm_atomic_state *old_state)
+{
+	struct dpu_kms *dpu_kms;
+	struct msm_drm_private *priv;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *old_crtc_state;
+	int i;
+
+	if (!kms || !old_state)
+		return;
+	dpu_kms = to_dpu_kms(kms);
+
+	if (!dpu_kms->dev || !dpu_kms->dev->dev_private)
+		return;
+	priv = dpu_kms->dev->dev_private;
+
+	DPU_ATRACE_BEGIN("kms_complete_commit");
+
+	for_each_old_crtc_in_state(old_state, crtc, old_crtc_state, i)
+		dpu_crtc_complete_commit(crtc, old_crtc_state);
+
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	DPU_ATRACE_END("kms_complete_commit");
+}
+
+static void dpu_kms_wait_for_commit_done(struct msm_kms *kms,
+		struct drm_crtc *crtc)
+{
+	struct drm_encoder *encoder;
+	struct drm_device *dev;
+	int ret;
+
+	if (!kms || !crtc || !crtc->state) {
+		DPU_ERROR("invalid params\n");
+		return;
+	}
+
+	dev = crtc->dev;
+
+	if (!crtc->state->enable) {
+		DPU_DEBUG("[crtc:%d] not enable\n", crtc->base.id);
+		return;
+	}
+
+	if (!crtc->state->active) {
+		DPU_DEBUG("[crtc:%d] not active\n", crtc->base.id);
+		return;
+	}
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+		if (encoder->crtc != crtc)
+			continue;
+		/*
+		 * Wait for post-flush if necessary to delay before
+		 * plane_cleanup. For example, wait for vsync in case of video
+		 * mode panels. This may be a no-op for command mode panels.
+		 */
+		trace_dpu_kms_wait_for_commit_done(DRMID(crtc));
+		ret = dpu_encoder_wait_for_event(encoder, MSM_ENC_COMMIT_DONE);
+		if (ret && ret != -EWOULDBLOCK) {
+			DPU_ERROR("wait for commit done returned %d\n", ret);
+			break;
+		}
+	}
+}
+
+static void _dpu_kms_initialize_dsi(struct drm_device *dev,
+				    struct msm_drm_private *priv,
+				    struct dpu_kms *dpu_kms)
+{
+	struct drm_encoder *encoder = NULL;
+	int i, rc;
+
+	/*TODO: Support two independent DSI connectors */
+	encoder = dpu_encoder_init(dev, DRM_MODE_CONNECTOR_DSI);
+	if (IS_ERR_OR_NULL(encoder)) {
+		DPU_ERROR("encoder init failed for dsi display\n");
+		return;
+	}
+
+	priv->encoders[priv->num_encoders++] = encoder;
+
+	for (i = 0; i < ARRAY_SIZE(priv->dsi); i++) {
+		if (!priv->dsi[i]) {
+			DPU_DEBUG("invalid msm_dsi for ctrl %d\n", i);
+			return;
+		}
+
+		rc = msm_dsi_modeset_init(priv->dsi[i], dev, encoder);
+		if (rc) {
+			DPU_ERROR("modeset_init failed for dsi[%d], rc = %d\n",
+				i, rc);
+			continue;
+		}
+	}
+}
+
+/**
+ * _dpu_kms_setup_displays - create encoders, bridges and connectors
+ *                           for underlying displays
+ * @dev:        Pointer to drm device structure
+ * @priv:       Pointer to private drm device data
+ * @dpu_kms:    Pointer to dpu kms structure
+ * Returns:     Zero on success
+ */
+static void _dpu_kms_setup_displays(struct drm_device *dev,
+				    struct msm_drm_private *priv,
+				    struct dpu_kms *dpu_kms)
+{
+	_dpu_kms_initialize_dsi(dev, priv, dpu_kms);
+
+	/**
+	 * Extend this function to initialize other
+	 * types of displays
+	 */
+}
+
+static void _dpu_kms_drm_obj_destroy(struct dpu_kms *dpu_kms)
+{
+	struct msm_drm_private *priv;
+	int i;
+
+	if (!dpu_kms) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return;
+	} else if (!dpu_kms->dev) {
+		DPU_ERROR("invalid dev\n");
+		return;
+	} else if (!dpu_kms->dev->dev_private) {
+		DPU_ERROR("invalid dev_private\n");
+		return;
+	}
+	priv = dpu_kms->dev->dev_private;
+
+	for (i = 0; i < priv->num_crtcs; i++)
+		priv->crtcs[i]->funcs->destroy(priv->crtcs[i]);
+	priv->num_crtcs = 0;
+
+	for (i = 0; i < priv->num_planes; i++)
+		priv->planes[i]->funcs->destroy(priv->planes[i]);
+	priv->num_planes = 0;
+
+	for (i = 0; i < priv->num_connectors; i++)
+		priv->connectors[i]->funcs->destroy(priv->connectors[i]);
+	priv->num_connectors = 0;
+
+	for (i = 0; i < priv->num_encoders; i++)
+		priv->encoders[i]->funcs->destroy(priv->encoders[i]);
+	priv->num_encoders = 0;
+}
+
+static int _dpu_kms_drm_obj_init(struct dpu_kms *dpu_kms)
+{
+	struct drm_device *dev;
+	struct drm_plane *primary_planes[MAX_PLANES], *plane;
+	struct drm_crtc *crtc;
+
+	struct msm_drm_private *priv;
+	struct dpu_mdss_cfg *catalog;
+
+	int primary_planes_idx = 0, i, ret;
+	int max_crtc_count;
+
+	if (!dpu_kms || !dpu_kms->dev || !dpu_kms->dev->dev) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return -EINVAL;
+	}
+
+	dev = dpu_kms->dev;
+	priv = dev->dev_private;
+	catalog = dpu_kms->catalog;
+
+	/*
+	 * Create encoder and query display drivers to create
+	 * bridges and connectors
+	 */
+	_dpu_kms_setup_displays(dev, priv, dpu_kms);
+
+	max_crtc_count = min(catalog->mixer_count, priv->num_encoders);
+
+	/* Create the planes */
+	for (i = 0; i < catalog->sspp_count; i++) {
+		bool primary = true;
+
+		if (catalog->sspp[i].features & BIT(DPU_SSPP_CURSOR)
+			|| primary_planes_idx >= max_crtc_count)
+			primary = false;
+
+		plane = dpu_plane_init(dev, catalog->sspp[i].id, primary,
+				(1UL << max_crtc_count) - 1, 0);
+		if (IS_ERR(plane)) {
+			DPU_ERROR("dpu_plane_init failed\n");
+			ret = PTR_ERR(plane);
+			goto fail;
+		}
+		priv->planes[priv->num_planes++] = plane;
+
+		if (primary)
+			primary_planes[primary_planes_idx++] = plane;
+	}
+
+	max_crtc_count = min(max_crtc_count, primary_planes_idx);
+
+	/* Create one CRTC per encoder */
+	for (i = 0; i < max_crtc_count; i++) {
+		crtc = dpu_crtc_init(dev, primary_planes[i]);
+		if (IS_ERR(crtc)) {
+			ret = PTR_ERR(crtc);
+			goto fail;
+		}
+		priv->crtcs[priv->num_crtcs++] = crtc;
+	}
+
+	/* All CRTCs are compatible with all encoders */
+	for (i = 0; i < priv->num_encoders; i++)
+		priv->encoders[i]->possible_crtcs = (1 << priv->num_crtcs) - 1;
+
+	return 0;
+fail:
+	_dpu_kms_drm_obj_destroy(dpu_kms);
+	return ret;
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int dpu_kms_debugfs_init(struct msm_kms *kms, struct drm_minor *minor)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+	struct drm_device *dev;
+	int rc;
+
+	if (!dpu_kms || !dpu_kms->dev || !dpu_kms->dev->dev) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return -EINVAL;
+	}
+
+	dev = dpu_kms->dev;
+
+	rc = _dpu_debugfs_init(dpu_kms);
+	if (rc)
+		DPU_ERROR("dpu_debugfs init failed: %d\n", rc);
+
+	return rc;
+}
+#endif
+
+static long dpu_kms_round_pixclk(struct msm_kms *kms, unsigned long rate,
+		struct drm_encoder *encoder)
+{
+	return rate;
+}
+
+static void _dpu_kms_hw_destroy(struct dpu_kms *dpu_kms)
+{
+	struct drm_device *dev;
+	int i;
+
+	dev = dpu_kms->dev;
+	if (!dev)
+		return;
+
+	if (dpu_kms->hw_intr)
+		dpu_hw_intr_destroy(dpu_kms->hw_intr);
+	dpu_kms->hw_intr = NULL;
+
+	if (dpu_kms->power_event)
+		dpu_power_handle_unregister_event(
+				&dpu_kms->phandle, dpu_kms->power_event);
+
+	/* safe to call these more than once during shutdown */
+	_dpu_debugfs_destroy(dpu_kms);
+	_dpu_kms_mmu_destroy(dpu_kms);
+
+	if (dpu_kms->catalog) {
+		for (i = 0; i < dpu_kms->catalog->vbif_count; i++) {
+			u32 vbif_idx = dpu_kms->catalog->vbif[i].id;
+
+			if ((vbif_idx < VBIF_MAX) && dpu_kms->hw_vbif[vbif_idx])
+				dpu_hw_vbif_destroy(dpu_kms->hw_vbif[vbif_idx]);
+		}
+	}
+
+	if (dpu_kms->rm_init)
+		dpu_rm_destroy(&dpu_kms->rm);
+	dpu_kms->rm_init = false;
+
+	if (dpu_kms->catalog)
+		dpu_hw_catalog_deinit(dpu_kms->catalog);
+	dpu_kms->catalog = NULL;
+
+	if (dpu_kms->core_client)
+		dpu_power_client_destroy(&dpu_kms->phandle,
+			dpu_kms->core_client);
+	dpu_kms->core_client = NULL;
+
+	if (dpu_kms->vbif[VBIF_NRT])
+		devm_iounmap(&dpu_kms->pdev->dev, dpu_kms->vbif[VBIF_NRT]);
+	dpu_kms->vbif[VBIF_NRT] = NULL;
+
+	if (dpu_kms->vbif[VBIF_RT])
+		devm_iounmap(&dpu_kms->pdev->dev, dpu_kms->vbif[VBIF_RT]);
+	dpu_kms->vbif[VBIF_RT] = NULL;
+
+	if (dpu_kms->mmio)
+		devm_iounmap(&dpu_kms->pdev->dev, dpu_kms->mmio);
+	dpu_kms->mmio = NULL;
+}
+
+static void dpu_kms_destroy(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms;
+
+	if (!kms) {
+		DPU_ERROR("invalid kms\n");
+		return;
+	}
+
+	dpu_kms = to_dpu_kms(kms);
+
+	dpu_dbg_destroy();
+	_dpu_kms_hw_destroy(dpu_kms);
+}
+
+static int dpu_kms_pm_suspend(struct device *dev)
+{
+	struct drm_device *ddev;
+	struct drm_modeset_acquire_ctx ctx;
+	struct drm_atomic_state *state;
+	struct dpu_kms *dpu_kms;
+	int ret = 0, num_crtcs = 0;
+
+	if (!dev)
+		return -EINVAL;
+
+	ddev = dev_get_drvdata(dev);
+	if (!ddev || !ddev_to_msm_kms(ddev))
+		return -EINVAL;
+
+	dpu_kms = to_dpu_kms(ddev_to_msm_kms(ddev));
+
+	/* disable hot-plug polling */
+	drm_kms_helper_poll_disable(ddev);
+
+	/* acquire modeset lock(s) */
+	drm_modeset_acquire_init(&ctx, 0);
+
+retry:
+	DPU_ATRACE_BEGIN("kms_pm_suspend");
+
+	ret = drm_modeset_lock_all_ctx(ddev, &ctx);
+	if (ret)
+		goto unlock;
+
+	/* save current state for resume */
+	if (dpu_kms->suspend_state)
+		drm_atomic_state_put(dpu_kms->suspend_state);
+	dpu_kms->suspend_state = drm_atomic_helper_duplicate_state(ddev, &ctx);
+	if (IS_ERR_OR_NULL(dpu_kms->suspend_state)) {
+		DRM_ERROR("failed to back up suspend state\n");
+		dpu_kms->suspend_state = NULL;
+		goto unlock;
+	}
+
+	/* create atomic state to disable all CRTCs */
+	state = drm_atomic_state_alloc(ddev);
+	if (IS_ERR_OR_NULL(state)) {
+		DRM_ERROR("failed to allocate crtc disable state\n");
+		goto unlock;
+	}
+
+	state->acquire_ctx = &ctx;
+
+	/* check for nothing to do */
+	if (num_crtcs == 0) {
+		DRM_DEBUG("all crtcs are already in the off state\n");
+		drm_atomic_state_put(state);
+		goto suspended;
+	}
+
+	/* commit the "disable all" state */
+	ret = drm_atomic_commit(state);
+	if (ret < 0) {
+		DRM_ERROR("failed to disable crtcs, %d\n", ret);
+		drm_atomic_state_put(state);
+		goto unlock;
+	}
+
+suspended:
+	dpu_kms->suspend_block = true;
+
+unlock:
+	if (ret == -EDEADLK) {
+		drm_modeset_backoff(&ctx);
+		goto retry;
+	}
+	drm_modeset_drop_locks(&ctx);
+	drm_modeset_acquire_fini(&ctx);
+
+	DPU_ATRACE_END("kms_pm_suspend");
+	return 0;
+}
+
+static int dpu_kms_pm_resume(struct device *dev)
+{
+	struct drm_device *ddev;
+	struct dpu_kms *dpu_kms;
+	int ret;
+
+	if (!dev)
+		return -EINVAL;
+
+	ddev = dev_get_drvdata(dev);
+	if (!ddev || !ddev_to_msm_kms(ddev))
+		return -EINVAL;
+
+	dpu_kms = to_dpu_kms(ddev_to_msm_kms(ddev));
+
+	DPU_ATRACE_BEGIN("kms_pm_resume");
+
+	drm_mode_config_reset(ddev);
+
+	drm_modeset_lock_all(ddev);
+
+	dpu_kms->suspend_block = false;
+
+	if (dpu_kms->suspend_state) {
+		dpu_kms->suspend_state->acquire_ctx =
+			ddev->mode_config.acquire_ctx;
+		ret = drm_atomic_commit(dpu_kms->suspend_state);
+		if (ret < 0) {
+			DRM_ERROR("failed to restore state, %d\n", ret);
+			drm_atomic_state_put(dpu_kms->suspend_state);
+		}
+		dpu_kms->suspend_state = NULL;
+	}
+	drm_modeset_unlock_all(ddev);
+
+	/* enable hot-plug polling */
+	drm_kms_helper_poll_enable(ddev);
+
+	DPU_ATRACE_END("kms_pm_resume");
+	return 0;
+}
+
+static void _dpu_kms_set_encoder_mode(struct msm_kms *kms,
+				 struct drm_encoder *encoder,
+				 bool cmd_mode)
+{
+	struct msm_display_info info;
+	struct msm_drm_private *priv = encoder->dev->dev_private;
+	int i, rc = 0;
+
+	memset(&info, 0, sizeof(info));
+
+	info.intf_type = encoder->encoder_type;
+	info.capabilities = cmd_mode ? MSM_DISPLAY_CAP_CMD_MODE :
+			MSM_DISPLAY_CAP_VID_MODE;
+
+	/* TODO: No support for DSI swap */
+	for (i = 0; i < ARRAY_SIZE(priv->dsi); i++) {
+		if (priv->dsi[i]) {
+			info.h_tile_instance[info.num_of_h_tiles] = i;
+			info.num_of_h_tiles++;
+		}
+	}
+
+	rc = dpu_encoder_setup(encoder->dev, encoder, &info);
+	if (rc)
+		DPU_ERROR("failed to setup DPU encoder %d: rc:%d\n",
+			encoder->base.id, rc);
+}
+
+static const struct msm_kms_funcs kms_funcs = {
+	.hw_init         = dpu_kms_hw_init,
+	.irq_preinstall  = dpu_irq_preinstall,
+	.irq_postinstall = dpu_irq_postinstall,
+	.irq_uninstall   = dpu_irq_uninstall,
+	.irq             = dpu_irq,
+	.prepare_commit  = dpu_kms_prepare_commit,
+	.commit          = dpu_kms_commit,
+	.complete_commit = dpu_kms_complete_commit,
+	.wait_for_crtc_commit_done = dpu_kms_wait_for_commit_done,
+	.enable_vblank   = dpu_kms_enable_vblank,
+	.disable_vblank  = dpu_kms_disable_vblank,
+	.check_modified_format = dpu_format_check_modified_format,
+	.get_format      = dpu_get_msm_format,
+	.round_pixclk    = dpu_kms_round_pixclk,
+	.pm_suspend      = dpu_kms_pm_suspend,
+	.pm_resume       = dpu_kms_pm_resume,
+	.destroy         = dpu_kms_destroy,
+	.set_encoder_mode = _dpu_kms_set_encoder_mode,
+#ifdef CONFIG_DEBUG_FS
+	.debugfs_init    = dpu_kms_debugfs_init,
+#endif
+};
+
+/* the caller api needs to turn on clock before calling it */
+static inline void _dpu_kms_core_hw_rev_init(struct dpu_kms *dpu_kms)
+{
+	dpu_kms->core_rev = readl_relaxed(dpu_kms->mmio + 0x0);
+}
+
+static int _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms)
+{
+	struct msm_mmu *mmu;
+
+	mmu = dpu_kms->base.aspace->mmu;
+
+	mmu->funcs->detach(mmu, (const char **)iommu_ports,
+			ARRAY_SIZE(iommu_ports));
+	msm_gem_address_space_put(dpu_kms->base.aspace);
+
+	return 0;
+}
+
+static int _dpu_kms_mmu_init(struct dpu_kms *dpu_kms)
+{
+	struct iommu_domain *domain;
+	struct msm_gem_address_space *aspace;
+	int ret;
+
+	domain = iommu_domain_alloc(&platform_bus_type);
+	if (!domain)
+		return 0;
+
+	aspace = msm_gem_address_space_create(dpu_kms->dev->dev,
+			domain, "dpu1");
+	if (IS_ERR(aspace)) {
+		ret = PTR_ERR(aspace);
+		goto fail;
+	}
+
+	dpu_kms->base.aspace = aspace;
+
+	ret = aspace->mmu->funcs->attach(aspace->mmu, iommu_ports,
+			ARRAY_SIZE(iommu_ports));
+	if (ret) {
+		DPU_ERROR("failed to attach iommu %d\n", ret);
+		msm_gem_address_space_put(aspace);
+		goto fail;
+	}
+
+	return 0;
+fail:
+	_dpu_kms_mmu_destroy(dpu_kms);
+
+	return ret;
+}
+
+static struct dss_clk *_dpu_kms_get_clk(struct dpu_kms *dpu_kms,
+		char *clock_name)
+{
+	struct dss_module_power *mp = &dpu_kms->mp;
+	int i;
+
+	for (i = 0; i < mp->num_clk; i++) {
+		if (!strcmp(mp->clk_config[i].clk_name, clock_name))
+			return &mp->clk_config[i];
+	}
+
+	return NULL;
+}
+
+u64 dpu_kms_get_clk_rate(struct dpu_kms *dpu_kms, char *clock_name)
+{
+	struct dss_clk *clk;
+
+	clk = _dpu_kms_get_clk(dpu_kms, clock_name);
+	if (!clk)
+		return -EINVAL;
+
+	return clk_get_rate(clk->clk);
+}
+
+static void dpu_kms_handle_power_event(u32 event_type, void *usr)
+{
+	struct dpu_kms *dpu_kms = usr;
+
+	if (!dpu_kms)
+		return;
+
+	if (event_type == DPU_POWER_EVENT_POST_ENABLE)
+		dpu_vbif_init_memtypes(dpu_kms);
+}
+
+static int dpu_kms_hw_init(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms;
+	struct drm_device *dev;
+	struct msm_drm_private *priv;
+	int i, rc = -EINVAL;
+
+	if (!kms) {
+		DPU_ERROR("invalid kms\n");
+		goto end;
+	}
+
+	dpu_kms = to_dpu_kms(kms);
+	dev = dpu_kms->dev;
+	if (!dev) {
+		DPU_ERROR("invalid device\n");
+		goto end;
+	}
+
+	rc = dpu_dbg_init(&dpu_kms->pdev->dev);
+	if (rc) {
+		DRM_ERROR("failed to init dpu dbg: %d\n", rc);
+		goto end;
+	}
+
+	priv = dev->dev_private;
+	if (!priv) {
+		DPU_ERROR("invalid private data\n");
+		goto dbg_destroy;
+	}
+
+	dpu_kms->mmio = msm_ioremap(dpu_kms->pdev, "mdp", "mdp");
+	if (IS_ERR(dpu_kms->mmio)) {
+		rc = PTR_ERR(dpu_kms->mmio);
+		DPU_ERROR("mdp register memory map failed: %d\n", rc);
+		dpu_kms->mmio = NULL;
+		goto error;
+	}
+	DRM_DEBUG("mapped dpu address space @%pK\n", dpu_kms->mmio);
+	dpu_kms->mmio_len = dpu_iomap_size(dpu_kms->pdev, "mdp");
+
+	dpu_kms->vbif[VBIF_RT] = msm_ioremap(dpu_kms->pdev, "vbif", "vbif");
+	if (IS_ERR(dpu_kms->vbif[VBIF_RT])) {
+		rc = PTR_ERR(dpu_kms->vbif[VBIF_RT]);
+		DPU_ERROR("vbif register memory map failed: %d\n", rc);
+		dpu_kms->vbif[VBIF_RT] = NULL;
+		goto error;
+	}
+	dpu_kms->vbif_len[VBIF_RT] = dpu_iomap_size(dpu_kms->pdev, "vbif");
+	dpu_kms->vbif[VBIF_NRT] = msm_ioremap(dpu_kms->pdev, "vbif_nrt", "vbif_nrt");
+	if (IS_ERR(dpu_kms->vbif[VBIF_NRT])) {
+		dpu_kms->vbif[VBIF_NRT] = NULL;
+		DPU_DEBUG("VBIF NRT is not defined");
+	} else {
+		dpu_kms->vbif_len[VBIF_NRT] = dpu_iomap_size(dpu_kms->pdev,
+							     "vbif_nrt");
+	}
+
+	dpu_kms->reg_dma = msm_ioremap(dpu_kms->pdev, "regdma", "regdma");
+	if (IS_ERR(dpu_kms->reg_dma)) {
+		dpu_kms->reg_dma = NULL;
+		DPU_DEBUG("REG_DMA is not defined");
+	} else {
+		dpu_kms->reg_dma_len = dpu_iomap_size(dpu_kms->pdev, "regdma");
+	}
+
+	dpu_kms->core_client = dpu_power_client_create(&dpu_kms->phandle,
+					"core");
+	if (IS_ERR_OR_NULL(dpu_kms->core_client)) {
+		rc = PTR_ERR(dpu_kms->core_client);
+		if (!dpu_kms->core_client)
+			rc = -EINVAL;
+		DPU_ERROR("dpu power client create failed: %d\n", rc);
+		dpu_kms->core_client = NULL;
+		goto error;
+	}
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+
+	_dpu_kms_core_hw_rev_init(dpu_kms);
+
+	pr_info("dpu hardware revision:0x%x\n", dpu_kms->core_rev);
+
+	dpu_kms->catalog = dpu_hw_catalog_init(dpu_kms->core_rev);
+	if (IS_ERR_OR_NULL(dpu_kms->catalog)) {
+		rc = PTR_ERR(dpu_kms->catalog);
+		if (!dpu_kms->catalog)
+			rc = -EINVAL;
+		DPU_ERROR("catalog init failed: %d\n", rc);
+		dpu_kms->catalog = NULL;
+		goto power_error;
+	}
+
+	dpu_dbg_init_dbg_buses(dpu_kms->core_rev);
+
+	/*
+	 * Now we need to read the HW catalog and initialize resources such as
+	 * clocks, regulators, GDSC/MMAGIC, ioremap the register ranges etc
+	 */
+	rc = _dpu_kms_mmu_init(dpu_kms);
+	if (rc) {
+		DPU_ERROR("dpu_kms_mmu_init failed: %d\n", rc);
+		goto power_error;
+	}
+
+	rc = dpu_rm_init(&dpu_kms->rm, dpu_kms->catalog, dpu_kms->mmio,
+			dpu_kms->dev);
+	if (rc) {
+		DPU_ERROR("rm init failed: %d\n", rc);
+		goto power_error;
+	}
+
+	dpu_kms->rm_init = true;
+
+	dpu_kms->hw_mdp = dpu_rm_get_mdp(&dpu_kms->rm);
+	if (IS_ERR_OR_NULL(dpu_kms->hw_mdp)) {
+		rc = PTR_ERR(dpu_kms->hw_mdp);
+		if (!dpu_kms->hw_mdp)
+			rc = -EINVAL;
+		DPU_ERROR("failed to get hw_mdp: %d\n", rc);
+		dpu_kms->hw_mdp = NULL;
+		goto power_error;
+	}
+
+	for (i = 0; i < dpu_kms->catalog->vbif_count; i++) {
+		u32 vbif_idx = dpu_kms->catalog->vbif[i].id;
+
+		dpu_kms->hw_vbif[i] = dpu_hw_vbif_init(vbif_idx,
+				dpu_kms->vbif[vbif_idx], dpu_kms->catalog);
+		if (IS_ERR_OR_NULL(dpu_kms->hw_vbif[vbif_idx])) {
+			rc = PTR_ERR(dpu_kms->hw_vbif[vbif_idx]);
+			if (!dpu_kms->hw_vbif[vbif_idx])
+				rc = -EINVAL;
+			DPU_ERROR("failed to init vbif %d: %d\n", vbif_idx, rc);
+			dpu_kms->hw_vbif[vbif_idx] = NULL;
+			goto power_error;
+		}
+	}
+
+	rc = dpu_core_perf_init(&dpu_kms->perf, dev, dpu_kms->catalog,
+			&dpu_kms->phandle,
+			_dpu_kms_get_clk(dpu_kms, "core"));
+	if (rc) {
+		DPU_ERROR("failed to init perf %d\n", rc);
+		goto perf_err;
+	}
+
+	dpu_kms->hw_intr = dpu_hw_intr_init(dpu_kms->mmio, dpu_kms->catalog);
+	if (IS_ERR_OR_NULL(dpu_kms->hw_intr)) {
+		rc = PTR_ERR(dpu_kms->hw_intr);
+		DPU_ERROR("hw_intr init failed: %d\n", rc);
+		dpu_kms->hw_intr = NULL;
+		goto hw_intr_init_err;
+	}
+
+	/*
+	 * _dpu_kms_drm_obj_init should create the DRM related objects
+	 * i.e. CRTCs, planes, encoders, connectors and so forth
+	 */
+	rc = _dpu_kms_drm_obj_init(dpu_kms);
+	if (rc) {
+		DPU_ERROR("modeset init failed: %d\n", rc);
+		goto drm_obj_init_err;
+	}
+
+	dev->mode_config.min_width = 0;
+	dev->mode_config.min_height = 0;
+
+	/*
+	 * max crtc width is equal to the max mixer width * 2 and max height is
+	 * is 4K
+	 */
+	dev->mode_config.max_width =
+			dpu_kms->catalog->caps->max_mixer_width * 2;
+	dev->mode_config.max_height = 4096;
+
+	/*
+	 * Support format modifiers for compression etc.
+	 */
+	dev->mode_config.allow_fb_modifiers = true;
+
+	/*
+	 * Handle (re)initializations during power enable
+	 */
+	dpu_kms_handle_power_event(DPU_POWER_EVENT_POST_ENABLE, dpu_kms);
+	dpu_kms->power_event = dpu_power_handle_register_event(
+			&dpu_kms->phandle,
+			DPU_POWER_EVENT_POST_ENABLE,
+			dpu_kms_handle_power_event, dpu_kms, "kms");
+
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	return 0;
+
+drm_obj_init_err:
+	dpu_core_perf_destroy(&dpu_kms->perf);
+hw_intr_init_err:
+perf_err:
+power_error:
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+error:
+	_dpu_kms_hw_destroy(dpu_kms);
+dbg_destroy:
+	dpu_dbg_destroy();
+end:
+	return rc;
+}
+
+struct msm_kms *dpu_kms_init(struct drm_device *dev)
+{
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	int irq;
+
+	if (!dev || !dev->dev_private) {
+		DPU_ERROR("drm device node invalid\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	priv = dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	irq = irq_of_parse_and_map(dpu_kms->pdev->dev.of_node, 0);
+	if (irq < 0) {
+		DPU_ERROR("failed to get irq: %d\n", irq);
+		return ERR_PTR(irq);
+	}
+	dpu_kms->base.irq = irq;
+
+	return &dpu_kms->base;
+}
+
+static int dpu_bind(struct device *dev, struct device *master, void *data)
+{
+	struct drm_device *ddev = dev_get_drvdata(master);
+	struct platform_device *pdev = to_platform_device(dev);
+	struct msm_drm_private *priv = ddev->dev_private;
+	struct dpu_kms *dpu_kms;
+	struct dss_module_power *mp;
+	int ret = 0;
+
+	dpu_kms = devm_kzalloc(&pdev->dev, sizeof(*dpu_kms), GFP_KERNEL);
+	if (!dpu_kms)
+		return -ENOMEM;
+
+	mp = &dpu_kms->mp;
+	ret = msm_dss_parse_clock(pdev, mp);
+	if (ret) {
+		DPU_ERROR("failed to parse clocks, ret=%d\n", ret);
+		return ret;
+	}
+
+	dpu_power_resource_init(pdev, &dpu_kms->phandle);
+
+	platform_set_drvdata(pdev, dpu_kms);
+
+	msm_kms_init(&dpu_kms->base, &kms_funcs);
+	dpu_kms->dev = ddev;
+	dpu_kms->pdev = pdev;
+
+	pm_runtime_enable(&pdev->dev);
+	dpu_kms->rpm_enabled = true;
+
+	priv->kms = &dpu_kms->base;
+	return ret;
+}
+
+static void dpu_unbind(struct device *dev, struct device *master, void *data)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct dpu_kms *dpu_kms = platform_get_drvdata(pdev);
+	struct dss_module_power *mp = &dpu_kms->mp;
+
+	dpu_power_resource_deinit(pdev, &dpu_kms->phandle);
+	msm_dss_put_clk(mp->clk_config, mp->num_clk);
+	devm_kfree(&pdev->dev, mp->clk_config);
+	mp->num_clk = 0;
+
+	if (dpu_kms->rpm_enabled)
+		pm_runtime_disable(&pdev->dev);
+}
+
+static const struct component_ops dpu_ops = {
+	.bind   = dpu_bind,
+	.unbind = dpu_unbind,
+};
+
+static int dpu_dev_probe(struct platform_device *pdev)
+{
+	return component_add(&pdev->dev, &dpu_ops);
+}
+
+static int dpu_dev_remove(struct platform_device *pdev)
+{
+	component_del(&pdev->dev, &dpu_ops);
+	return 0;
+}
+
+static int __maybe_unused dpu_runtime_suspend(struct device *dev)
+{
+	int rc = -1;
+	struct platform_device *pdev = to_platform_device(dev);
+	struct dpu_kms *dpu_kms = platform_get_drvdata(pdev);
+	struct drm_device *ddev;
+	struct dss_module_power *mp = &dpu_kms->mp;
+
+	ddev = dpu_kms->dev;
+	if (!ddev) {
+		DPU_ERROR("invalid drm_device\n");
+		goto exit;
+	}
+
+	rc = dpu_power_resource_enable(&dpu_kms->phandle,
+			dpu_kms->core_client, false);
+	if (rc)
+		DPU_ERROR("resource disable failed: %d\n", rc);
+
+	rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, false);
+	if (rc)
+		DPU_ERROR("clock disable failed rc:%d\n", rc);
+
+exit:
+	return rc;
+}
+
+static int __maybe_unused dpu_runtime_resume(struct device *dev)
+{
+	int rc = -1;
+	struct platform_device *pdev = to_platform_device(dev);
+	struct dpu_kms *dpu_kms = platform_get_drvdata(pdev);
+	struct drm_device *ddev;
+	struct dss_module_power *mp = &dpu_kms->mp;
+
+	ddev = dpu_kms->dev;
+	if (!ddev) {
+		DPU_ERROR("invalid drm_device\n");
+		goto exit;
+	}
+
+	rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true);
+	if (rc) {
+		DPU_ERROR("clock enable failed rc:%d\n", rc);
+		goto exit;
+	}
+
+	rc = dpu_power_resource_enable(&dpu_kms->phandle,
+			dpu_kms->core_client, true);
+	if (rc)
+		DPU_ERROR("resource enable failed: %d\n", rc);
+
+exit:
+	return rc;
+}
+
+static const struct dev_pm_ops dpu_pm_ops = {
+	SET_RUNTIME_PM_OPS(dpu_runtime_suspend, dpu_runtime_resume, NULL)
+};
+
+static const struct of_device_id dpu_dt_match[] = {
+	{ .compatible = "qcom,sdm845-dpu", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, dpu_dt_match);
+
+static struct platform_driver dpu_driver = {
+	.probe = dpu_dev_probe,
+	.remove = dpu_dev_remove,
+	.driver = {
+		.name = "msm_dpu",
+		.of_match_table = dpu_dt_match,
+		.pm = &dpu_pm_ops,
+	},
+};
+
+void __init msm_dpu_register(void)
+{
+	platform_driver_register(&dpu_driver);
+}
+
+void __exit msm_dpu_unregister(void)
+{
+	platform_driver_unregister(&dpu_driver);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
new file mode 100644
index 000000000000..66d466628e2b
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
@@ -0,0 +1,290 @@
+/*
+ * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __DPU_KMS_H__
+#define __DPU_KMS_H__
+
+#include "msm_drv.h"
+#include "msm_kms.h"
+#include "msm_mmu.h"
+#include "msm_gem.h"
+#include "dpu_dbg.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_interrupts.h"
+#include "dpu_hw_top.h"
+#include "dpu_rm.h"
+#include "dpu_power_handle.h"
+#include "dpu_irq.h"
+#include "dpu_core_perf.h"
+
+#define DRMID(x) ((x) ? (x)->base.id : -1)
+
+/**
+ * DPU_DEBUG - macro for kms/plane/crtc/encoder/connector logs
+ * @fmt: Pointer to format string
+ */
+#define DPU_DEBUG(fmt, ...)                                                \
+	do {                                                               \
+		if (unlikely(drm_debug & DRM_UT_KMS))                      \
+			DRM_DEBUG(fmt, ##__VA_ARGS__); \
+		else                                                       \
+			pr_debug(fmt, ##__VA_ARGS__);                      \
+	} while (0)
+
+/**
+ * DPU_DEBUG_DRIVER - macro for hardware driver logging
+ * @fmt: Pointer to format string
+ */
+#define DPU_DEBUG_DRIVER(fmt, ...)                                         \
+	do {                                                               \
+		if (unlikely(drm_debug & DRM_UT_DRIVER))                   \
+			DRM_ERROR(fmt, ##__VA_ARGS__); \
+		else                                                       \
+			pr_debug(fmt, ##__VA_ARGS__);                      \
+	} while (0)
+
+#define DPU_ERROR(fmt, ...) pr_err("[dpu error]" fmt, ##__VA_ARGS__)
+
+/**
+ * ktime_compare_safe - compare two ktime structures
+ *	This macro is similar to the standard ktime_compare() function, but
+ *	attempts to also handle ktime overflows.
+ * @A: First ktime value
+ * @B: Second ktime value
+ * Returns: -1 if A < B, 0 if A == B, 1 if A > B
+ */
+#define ktime_compare_safe(A, B) \
+	ktime_compare(ktime_sub((A), (B)), ktime_set(0, 0))
+
+#define DPU_NAME_SIZE  12
+
+/* timeout in frames waiting for frame done */
+#define DPU_FRAME_DONE_TIMEOUT	60
+
+/*
+ * struct dpu_irq_callback - IRQ callback handlers
+ * @list: list to callback
+ * @func: intr handler
+ * @arg: argument for the handler
+ */
+struct dpu_irq_callback {
+	struct list_head list;
+	void (*func)(void *arg, int irq_idx);
+	void *arg;
+};
+
+/**
+ * struct dpu_irq: IRQ structure contains callback registration info
+ * @total_irq:    total number of irq_idx obtained from HW interrupts mapping
+ * @irq_cb_tbl:   array of IRQ callbacks setting
+ * @enable_counts array of IRQ enable counts
+ * @cb_lock:      callback lock
+ * @debugfs_file: debugfs file for irq statistics
+ */
+struct dpu_irq {
+	u32 total_irqs;
+	struct list_head *irq_cb_tbl;
+	atomic_t *enable_counts;
+	atomic_t *irq_counts;
+	spinlock_t cb_lock;
+	struct dentry *debugfs_file;
+};
+
+struct dpu_kms {
+	struct msm_kms base;
+	struct drm_device *dev;
+	int core_rev;
+	struct dpu_mdss_cfg *catalog;
+
+	struct dpu_power_handle phandle;
+	struct dpu_power_client *core_client;
+	struct dpu_power_event *power_event;
+
+	/* directory entry for debugfs */
+	struct dentry *debugfs_root;
+	struct dentry *debugfs_danger;
+	struct dentry *debugfs_vbif;
+
+	/* io/register spaces: */
+	void __iomem *mmio, *vbif[VBIF_MAX], *reg_dma;
+	unsigned long mmio_len, vbif_len[VBIF_MAX], reg_dma_len;
+
+	struct regulator *vdd;
+	struct regulator *mmagic;
+	struct regulator *venus;
+
+	struct dpu_hw_intr *hw_intr;
+	struct dpu_irq irq_obj;
+
+	struct dpu_core_perf perf;
+
+	/* saved atomic state during system suspend */
+	struct drm_atomic_state *suspend_state;
+	bool suspend_block;
+
+	struct dpu_rm rm;
+	bool rm_init;
+
+	struct dpu_hw_vbif *hw_vbif[VBIF_MAX];
+	struct dpu_hw_mdp *hw_mdp;
+
+	bool has_danger_ctrl;
+
+	struct platform_device *pdev;
+	bool rpm_enabled;
+	struct dss_module_power mp;
+};
+
+struct vsync_info {
+	u32 frame_count;
+	u32 line_count;
+};
+
+#define to_dpu_kms(x) container_of(x, struct dpu_kms, base)
+
+/* get struct msm_kms * from drm_device * */
+#define ddev_to_msm_kms(D) ((D) && (D)->dev_private ? \
+		((struct msm_drm_private *)((D)->dev_private))->kms : NULL)
+
+/**
+ * dpu_kms_is_suspend_state - whether or not the system is pm suspended
+ * @dev: Pointer to drm device
+ * Return: Suspend status
+ */
+static inline bool dpu_kms_is_suspend_state(struct drm_device *dev)
+{
+	if (!ddev_to_msm_kms(dev))
+		return false;
+
+	return to_dpu_kms(ddev_to_msm_kms(dev))->suspend_state != NULL;
+}
+
+/**
+ * dpu_kms_is_suspend_blocked - whether or not commits are blocked due to pm
+ *				suspend status
+ * @dev: Pointer to drm device
+ * Return: True if commits should be rejected due to pm suspend
+ */
+static inline bool dpu_kms_is_suspend_blocked(struct drm_device *dev)
+{
+	if (!dpu_kms_is_suspend_state(dev))
+		return false;
+
+	return to_dpu_kms(ddev_to_msm_kms(dev))->suspend_block;
+}
+
+/**
+ * Debugfs functions - extra helper functions for debugfs support
+ *
+ * Main debugfs documentation is located at,
+ *
+ * Documentation/filesystems/debugfs.txt
+ *
+ * @dpu_debugfs_setup_regset32: Initialize data for dpu_debugfs_create_regset32
+ * @dpu_debugfs_create_regset32: Create 32-bit register dump file
+ * @dpu_debugfs_get_root: Get root dentry for DPU_KMS's debugfs node
+ */
+
+/**
+ * Companion structure for dpu_debugfs_create_regset32. Do not initialize the
+ * members of this structure explicitly; use dpu_debugfs_setup_regset32 instead.
+ */
+struct dpu_debugfs_regset32 {
+	uint32_t offset;
+	uint32_t blk_len;
+	struct dpu_kms *dpu_kms;
+};
+
+/**
+ * dpu_debugfs_setup_regset32 - Initialize register block definition for debugfs
+ * This function is meant to initialize dpu_debugfs_regset32 structures for use
+ * with dpu_debugfs_create_regset32.
+ * @regset: opaque register definition structure
+ * @offset: sub-block offset
+ * @length: sub-block length, in bytes
+ * @dpu_kms: pointer to dpu kms structure
+ */
+void dpu_debugfs_setup_regset32(struct dpu_debugfs_regset32 *regset,
+		uint32_t offset, uint32_t length, struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_debugfs_create_regset32 - Create register read back file for debugfs
+ *
+ * This function is almost identical to the standard debugfs_create_regset32()
+ * function, with the main difference being that a list of register
+ * names/offsets do not need to be provided. The 'read' function simply outputs
+ * sequential register values over a specified range.
+ *
+ * Similar to the related debugfs_create_regset32 API, the structure pointed to
+ * by regset needs to persist for the lifetime of the created file. The calling
+ * code is responsible for initialization/management of this structure.
+ *
+ * The structure pointed to by regset is meant to be opaque. Please use
+ * dpu_debugfs_setup_regset32 to initialize it.
+ *
+ * @name:   File name within debugfs
+ * @mode:   File mode within debugfs
+ * @parent: Parent directory entry within debugfs, can be NULL
+ * @regset: Pointer to persistent register block definition
+ *
+ * Return: dentry pointer for newly created file, use either debugfs_remove()
+ *         or debugfs_remove_recursive() (on a parent directory) to remove the
+ *         file
+ */
+void *dpu_debugfs_create_regset32(const char *name, umode_t mode,
+		void *parent, struct dpu_debugfs_regset32 *regset);
+
+/**
+ * dpu_debugfs_get_root - Return root directory entry for KMS's debugfs
+ *
+ * The return value should be passed as the 'parent' argument to subsequent
+ * debugfs create calls.
+ *
+ * @dpu_kms: Pointer to DPU's KMS structure
+ *
+ * Return: dentry pointer for DPU's debugfs location
+ */
+void *dpu_debugfs_get_root(struct dpu_kms *dpu_kms);
+
+/**
+ * DPU info management functions
+ * These functions/definitions allow for building up a 'dpu_info' structure
+ * containing one or more "key=value\n" entries.
+ */
+#define DPU_KMS_INFO_MAX_SIZE	4096
+
+/**
+ * Vblank enable/disable functions
+ */
+int dpu_enable_vblank(struct msm_kms *kms, struct drm_crtc *crtc);
+void dpu_disable_vblank(struct msm_kms *kms, struct drm_crtc *crtc);
+
+void dpu_kms_encoder_enable(struct drm_encoder *encoder);
+
+/**
+ * dpu_kms_get_clk_rate() - get the clock rate
+ * @dpu_kms:  poiner to dpu_kms structure
+ * @clock_name: clock name to get the rate
+ *
+ * Return: current clock rate
+ */
+u64 dpu_kms_get_clk_rate(struct dpu_kms *dpu_kms, char *clock_name);
+
+#endif /* __dpu_kms_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
new file mode 100644
index 000000000000..9e533b86682c
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
@@ -0,0 +1,245 @@
+/*
+ * SPDX-License-Identifier: GPL-2.0
+ * Copyright (c) 2018, The Linux Foundation
+ */
+
+#include "dpu_kms.h"
+
+#define to_dpu_mdss(x) container_of(x, struct dpu_mdss, base)
+
+#define HW_INTR_STATUS			0x0010
+
+struct dpu_mdss {
+	struct msm_mdss base;
+	void __iomem *mmio;
+	unsigned long mmio_len;
+	u32 hwversion;
+	struct dss_module_power mp;
+	struct dpu_irq_controller irq_controller;
+};
+
+static irqreturn_t dpu_mdss_irq(int irq, void *arg)
+{
+	struct dpu_mdss *dpu_mdss = arg;
+	u32 interrupts;
+
+	interrupts = readl_relaxed(dpu_mdss->mmio + HW_INTR_STATUS);
+
+	while (interrupts) {
+		irq_hw_number_t hwirq = fls(interrupts) - 1;
+		unsigned int mapping;
+		int rc;
+
+		mapping = irq_find_mapping(dpu_mdss->irq_controller.domain,
+					   hwirq);
+		if (mapping == 0) {
+			DRM_ERROR("couldn't find irq mapping for %lu\n", hwirq);
+			return IRQ_NONE;
+		}
+
+		rc = generic_handle_irq(mapping);
+		if (rc < 0) {
+			DRM_ERROR("handle irq fail: irq=%lu mapping=%u rc=%d\n",
+				  hwirq, mapping, rc);
+			return IRQ_NONE;
+		}
+
+		interrupts &= ~(1 << hwirq);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void dpu_mdss_irq_mask(struct irq_data *irqd)
+{
+	struct dpu_mdss *dpu_mdss = irq_data_get_irq_chip_data(irqd);
+
+	/* memory barrier */
+	smp_mb__before_atomic();
+	clear_bit(irqd->hwirq, &dpu_mdss->irq_controller.enabled_mask);
+	/* memory barrier */
+	smp_mb__after_atomic();
+}
+
+static void dpu_mdss_irq_unmask(struct irq_data *irqd)
+{
+	struct dpu_mdss *dpu_mdss = irq_data_get_irq_chip_data(irqd);
+
+	/* memory barrier */
+	smp_mb__before_atomic();
+	set_bit(irqd->hwirq, &dpu_mdss->irq_controller.enabled_mask);
+	/* memory barrier */
+	smp_mb__after_atomic();
+}
+
+static struct irq_chip dpu_mdss_irq_chip = {
+	.name = "dpu_mdss",
+	.irq_mask = dpu_mdss_irq_mask,
+	.irq_unmask = dpu_mdss_irq_unmask,
+};
+
+static int dpu_mdss_irqdomain_map(struct irq_domain *domain,
+		unsigned int irq, irq_hw_number_t hwirq)
+{
+	struct dpu_mdss *dpu_mdss = domain->host_data;
+	int ret;
+
+	irq_set_chip_and_handler(irq, &dpu_mdss_irq_chip, handle_level_irq);
+	ret = irq_set_chip_data(irq, dpu_mdss);
+
+	return ret;
+}
+
+static const struct irq_domain_ops dpu_mdss_irqdomain_ops = {
+	.map = dpu_mdss_irqdomain_map,
+	.xlate = irq_domain_xlate_onecell,
+};
+
+static int _dpu_mdss_irq_domain_add(struct dpu_mdss *dpu_mdss)
+{
+	struct device *dev;
+	struct irq_domain *domain;
+
+	dev = dpu_mdss->base.dev->dev;
+
+	domain = irq_domain_add_linear(dev->of_node, 32,
+			&dpu_mdss_irqdomain_ops, dpu_mdss);
+	if (!domain) {
+		DPU_ERROR("failed to add irq_domain\n");
+		return -EINVAL;
+	}
+
+	dpu_mdss->irq_controller.enabled_mask = 0;
+	dpu_mdss->irq_controller.domain = domain;
+
+	return 0;
+}
+
+static int _dpu_mdss_irq_domain_fini(struct dpu_mdss *dpu_mdss)
+{
+	if (dpu_mdss->irq_controller.domain) {
+		irq_domain_remove(dpu_mdss->irq_controller.domain);
+		dpu_mdss->irq_controller.domain = NULL;
+	}
+	return 0;
+}
+static int dpu_mdss_enable(struct msm_mdss *mdss)
+{
+	struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss);
+	struct dss_module_power *mp = &dpu_mdss->mp;
+	int ret;
+
+	ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true);
+	if (ret)
+		DPU_ERROR("clock enable failed, ret:%d\n", ret);
+
+	return ret;
+}
+
+static int dpu_mdss_disable(struct msm_mdss *mdss)
+{
+	struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss);
+	struct dss_module_power *mp = &dpu_mdss->mp;
+	int ret;
+
+	ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, false);
+	if (ret)
+		DPU_ERROR("clock disable failed, ret:%d\n", ret);
+
+	return ret;
+}
+
+static void dpu_mdss_destroy(struct drm_device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev->dev);
+	struct msm_drm_private *priv = dev->dev_private;
+	struct dpu_mdss *dpu_mdss = to_dpu_mdss(priv->mdss);
+	struct dss_module_power *mp = &dpu_mdss->mp;
+
+	_dpu_mdss_irq_domain_fini(dpu_mdss);
+
+	msm_dss_put_clk(mp->clk_config, mp->num_clk);
+	devm_kfree(&pdev->dev, mp->clk_config);
+
+	if (dpu_mdss->mmio)
+		devm_iounmap(&pdev->dev, dpu_mdss->mmio);
+	dpu_mdss->mmio = NULL;
+
+	pm_runtime_disable(dev->dev);
+	priv->mdss = NULL;
+}
+
+static const struct msm_mdss_funcs mdss_funcs = {
+	.enable	= dpu_mdss_enable,
+	.disable = dpu_mdss_disable,
+	.destroy = dpu_mdss_destroy,
+};
+
+int dpu_mdss_init(struct drm_device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev->dev);
+	struct msm_drm_private *priv = dev->dev_private;
+	struct resource *res;
+	struct dpu_mdss *dpu_mdss;
+	struct dss_module_power *mp;
+	int ret = 0;
+
+	dpu_mdss = devm_kzalloc(dev->dev, sizeof(*dpu_mdss), GFP_KERNEL);
+	if (!dpu_mdss)
+		return -ENOMEM;
+
+	dpu_mdss->mmio = msm_ioremap(pdev, "mdss", "mdss");
+	if (IS_ERR(dpu_mdss->mmio))
+		return PTR_ERR(dpu_mdss->mmio);
+
+	DRM_DEBUG("mapped mdss address space @%pK\n", dpu_mdss->mmio);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "mdss");
+	if (!res) {
+		DRM_ERROR("failed to get memory resource for mdss\n");
+		return -ENOMEM;
+	}
+	dpu_mdss->mmio_len = resource_size(res);
+
+	mp = &dpu_mdss->mp;
+	ret = msm_dss_parse_clock(pdev, mp);
+	if (ret) {
+		DPU_ERROR("failed to parse clocks, ret=%d\n", ret);
+		goto clk_parse_err;
+	}
+
+	dpu_mdss->base.dev = dev;
+	dpu_mdss->base.funcs = &mdss_funcs;
+
+	ret = _dpu_mdss_irq_domain_add(dpu_mdss);
+	if (ret)
+		goto irq_domain_error;
+
+	ret = devm_request_irq(dev->dev, platform_get_irq(pdev, 0),
+			dpu_mdss_irq, 0, "dpu_mdss_isr", dpu_mdss);
+	if (ret) {
+		DPU_ERROR("failed to init irq: %d\n", ret);
+		goto irq_error;
+	}
+
+	pm_runtime_enable(dev->dev);
+
+	pm_runtime_get_sync(dev->dev);
+	dpu_mdss->hwversion = readl_relaxed(dpu_mdss->mmio);
+	pm_runtime_put_sync(dev->dev);
+
+	priv->mdss = &dpu_mdss->base;
+
+	return ret;
+
+irq_error:
+	_dpu_mdss_irq_domain_fini(dpu_mdss);
+irq_domain_error:
+	msm_dss_put_clk(mp->clk_config, mp->num_clk);
+clk_parse_err:
+	devm_kfree(&pdev->dev, mp->clk_config);
+	if (dpu_mdss->mmio)
+		devm_iounmap(&pdev->dev, dpu_mdss->mmio);
+	dpu_mdss->mmio = NULL;
+	return ret;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
new file mode 100644
index 000000000000..b640e39ebaca
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -0,0 +1,1963 @@
+/*
+ * Copyright (C) 2014-2018 The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/debugfs.h>
+#include <linux/dma-buf.h>
+
+#include "msm_drv.h"
+#include "dpu_kms.h"
+#include "dpu_formats.h"
+#include "dpu_hw_sspp.h"
+#include "dpu_hw_catalog_format.h"
+#include "dpu_trace.h"
+#include "dpu_crtc.h"
+#include "dpu_vbif.h"
+#include "dpu_plane.h"
+
+#define DPU_DEBUG_PLANE(pl, fmt, ...) DPU_DEBUG("plane%d " fmt,\
+		(pl) ? (pl)->base.base.id : -1, ##__VA_ARGS__)
+
+#define DPU_ERROR_PLANE(pl, fmt, ...) DPU_ERROR("plane%d " fmt,\
+		(pl) ? (pl)->base.base.id : -1, ##__VA_ARGS__)
+
+#define DECIMATED_DIMENSION(dim, deci) (((dim) + ((1 << (deci)) - 1)) >> (deci))
+#define PHASE_STEP_SHIFT	21
+#define PHASE_STEP_UNIT_SCALE   ((int) (1 << PHASE_STEP_SHIFT))
+#define PHASE_RESIDUAL		15
+
+#define SHARP_STRENGTH_DEFAULT	32
+#define SHARP_EDGE_THR_DEFAULT	112
+#define SHARP_SMOOTH_THR_DEFAULT	8
+#define SHARP_NOISE_THR_DEFAULT	2
+
+#define DPU_NAME_SIZE  12
+
+#define DPU_PLANE_COLOR_FILL_FLAG	BIT(31)
+#define DPU_ZPOS_MAX 255
+
+/* multirect rect index */
+enum {
+	R0,
+	R1,
+	R_MAX
+};
+
+#define DPU_QSEED3_DEFAULT_PRELOAD_H 0x4
+#define DPU_QSEED3_DEFAULT_PRELOAD_V 0x3
+
+#define DEFAULT_REFRESH_RATE	60
+
+/**
+ * enum dpu_plane_qos - Different qos configurations for each pipe
+ *
+ * @DPU_PLANE_QOS_VBLANK_CTRL: Setup VBLANK qos for the pipe.
+ * @DPU_PLANE_QOS_VBLANK_AMORTIZE: Enables Amortization within pipe.
+ *	this configuration is mutually exclusive from VBLANK_CTRL.
+ * @DPU_PLANE_QOS_PANIC_CTRL: Setup panic for the pipe.
+ */
+enum dpu_plane_qos {
+	DPU_PLANE_QOS_VBLANK_CTRL = BIT(0),
+	DPU_PLANE_QOS_VBLANK_AMORTIZE = BIT(1),
+	DPU_PLANE_QOS_PANIC_CTRL = BIT(2),
+};
+
+/*
+ * struct dpu_plane - local dpu plane structure
+ * @aspace: address space pointer
+ * @csc_ptr: Points to dpu_csc_cfg structure to use for current
+ * @mplane_list: List of multirect planes of the same pipe
+ * @catalog: Points to dpu catalog structure
+ * @revalidate: force revalidation of all the plane properties
+ */
+struct dpu_plane {
+	struct drm_plane base;
+
+	struct mutex lock;
+
+	enum dpu_sspp pipe;
+	uint32_t features;      /* capabilities from catalog */
+	uint32_t nformats;
+	uint32_t formats[64];
+
+	struct dpu_hw_pipe *pipe_hw;
+	struct dpu_hw_pipe_cfg pipe_cfg;
+	struct dpu_hw_pipe_qos_cfg pipe_qos_cfg;
+	uint32_t color_fill;
+	bool is_error;
+	bool is_rt_pipe;
+	bool is_virtual;
+	struct list_head mplane_list;
+	struct dpu_mdss_cfg *catalog;
+
+	struct dpu_csc_cfg *csc_ptr;
+
+	const struct dpu_sspp_sub_blks *pipe_sblk;
+	char pipe_name[DPU_NAME_SIZE];
+
+	/* debugfs related stuff */
+	struct dentry *debugfs_root;
+	struct dpu_debugfs_regset32 debugfs_src;
+	struct dpu_debugfs_regset32 debugfs_scaler;
+	struct dpu_debugfs_regset32 debugfs_csc;
+	bool debugfs_default_scale;
+};
+
+#define to_dpu_plane(x) container_of(x, struct dpu_plane, base)
+
+static struct dpu_kms *_dpu_plane_get_kms(struct drm_plane *plane)
+{
+	struct msm_drm_private *priv;
+
+	if (!plane || !plane->dev)
+		return NULL;
+	priv = plane->dev->dev_private;
+	if (!priv)
+		return NULL;
+	return to_dpu_kms(priv->kms);
+}
+
+static bool dpu_plane_enabled(struct drm_plane_state *state)
+{
+	return state && state->fb && state->crtc;
+}
+
+static bool dpu_plane_sspp_enabled(struct drm_plane_state *state)
+{
+	return state && state->crtc;
+}
+
+/**
+ * _dpu_plane_calc_fill_level - calculate fill level of the given source format
+ * @plane:		Pointer to drm plane
+ * @fmt:		Pointer to source buffer format
+ * @src_wdith:		width of source buffer
+ * Return: fill level corresponding to the source buffer/format or 0 if error
+ */
+static inline int _dpu_plane_calc_fill_level(struct drm_plane *plane,
+		const struct dpu_format *fmt, u32 src_width)
+{
+	struct dpu_plane *pdpu, *tmp;
+	struct dpu_plane_state *pstate;
+	u32 fixed_buff_size;
+	u32 total_fl;
+
+	if (!plane || !fmt || !plane->state || !src_width || !fmt->bpp) {
+		DPU_ERROR("invalid arguments\n");
+		return 0;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	pstate = to_dpu_plane_state(plane->state);
+	fixed_buff_size = pdpu->pipe_sblk->common->pixel_ram_size;
+
+	list_for_each_entry(tmp, &pdpu->mplane_list, mplane_list) {
+		if (!dpu_plane_enabled(tmp->base.state))
+			continue;
+		DPU_DEBUG("plane%d/%d src_width:%d/%d\n",
+				pdpu->base.base.id, tmp->base.base.id,
+				src_width,
+				drm_rect_width(&tmp->pipe_cfg.src_rect));
+		src_width = max_t(u32, src_width,
+				  drm_rect_width(&tmp->pipe_cfg.src_rect));
+	}
+
+	if (fmt->fetch_planes == DPU_PLANE_PSEUDO_PLANAR) {
+		if (fmt->chroma_sample == DPU_CHROMA_420) {
+			/* NV12 */
+			total_fl = (fixed_buff_size / 2) /
+				((src_width + 32) * fmt->bpp);
+		} else {
+			/* non NV12 */
+			total_fl = (fixed_buff_size / 2) * 2 /
+				((src_width + 32) * fmt->bpp);
+		}
+	} else {
+		if (pstate->multirect_mode == DPU_SSPP_MULTIRECT_PARALLEL) {
+			total_fl = (fixed_buff_size / 2) * 2 /
+				((src_width + 32) * fmt->bpp);
+		} else {
+			total_fl = (fixed_buff_size) * 2 /
+				((src_width + 32) * fmt->bpp);
+		}
+	}
+
+	DPU_DEBUG("plane%u: pnum:%d fmt: %4.4s w:%u fl:%u\n",
+			plane->base.id, pdpu->pipe - SSPP_VIG0,
+			(char *)&fmt->base.pixel_format,
+			src_width, total_fl);
+
+	return total_fl;
+}
+
+/**
+ * _dpu_plane_get_qos_lut - get LUT mapping based on fill level
+ * @tbl:		Pointer to LUT table
+ * @total_fl:		fill level
+ * Return: LUT setting corresponding to the fill level
+ */
+static u64 _dpu_plane_get_qos_lut(const struct dpu_qos_lut_tbl *tbl,
+		u32 total_fl)
+{
+	int i;
+
+	if (!tbl || !tbl->nentry || !tbl->entries)
+		return 0;
+
+	for (i = 0; i < tbl->nentry; i++)
+		if (total_fl <= tbl->entries[i].fl)
+			return tbl->entries[i].lut;
+
+	/* if last fl is zero, use as default */
+	if (!tbl->entries[i-1].fl)
+		return tbl->entries[i-1].lut;
+
+	return 0;
+}
+
+/**
+ * _dpu_plane_set_qos_lut - set QoS LUT of the given plane
+ * @plane:		Pointer to drm plane
+ * @fb:			Pointer to framebuffer associated with the given plane
+ */
+static void _dpu_plane_set_qos_lut(struct drm_plane *plane,
+		struct drm_framebuffer *fb)
+{
+	struct dpu_plane *pdpu;
+	const struct dpu_format *fmt = NULL;
+	u64 qos_lut;
+	u32 total_fl = 0, lut_usage;
+
+	if (!plane || !fb) {
+		DPU_ERROR("invalid arguments plane %d fb %d\n",
+				plane != 0, fb != 0);
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+
+	if (!pdpu->pipe_hw || !pdpu->pipe_sblk || !pdpu->catalog) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	} else if (!pdpu->pipe_hw->ops.setup_creq_lut) {
+		return;
+	}
+
+	if (!pdpu->is_rt_pipe) {
+		lut_usage = DPU_QOS_LUT_USAGE_NRT;
+	} else {
+		fmt = dpu_get_dpu_format_ext(
+				fb->format->format,
+				fb->modifier);
+		total_fl = _dpu_plane_calc_fill_level(plane, fmt,
+				drm_rect_width(&pdpu->pipe_cfg.src_rect));
+
+		if (fmt && DPU_FORMAT_IS_LINEAR(fmt))
+			lut_usage = DPU_QOS_LUT_USAGE_LINEAR;
+		else
+			lut_usage = DPU_QOS_LUT_USAGE_MACROTILE;
+	}
+
+	qos_lut = _dpu_plane_get_qos_lut(
+			&pdpu->catalog->perf.qos_lut_tbl[lut_usage], total_fl);
+
+	pdpu->pipe_qos_cfg.creq_lut = qos_lut;
+
+	trace_dpu_perf_set_qos_luts(pdpu->pipe - SSPP_VIG0,
+			(fmt) ? fmt->base.pixel_format : 0,
+			pdpu->is_rt_pipe, total_fl, qos_lut, lut_usage);
+
+	DPU_DEBUG("plane%u: pnum:%d fmt: %4.4s rt:%d fl:%u lut:0x%llx\n",
+			plane->base.id,
+			pdpu->pipe - SSPP_VIG0,
+			fmt ? (char *)&fmt->base.pixel_format : NULL,
+			pdpu->is_rt_pipe, total_fl, qos_lut);
+
+	pdpu->pipe_hw->ops.setup_creq_lut(pdpu->pipe_hw, &pdpu->pipe_qos_cfg);
+}
+
+/**
+ * _dpu_plane_set_panic_lut - set danger/safe LUT of the given plane
+ * @plane:		Pointer to drm plane
+ * @fb:			Pointer to framebuffer associated with the given plane
+ */
+static void _dpu_plane_set_danger_lut(struct drm_plane *plane,
+		struct drm_framebuffer *fb)
+{
+	struct dpu_plane *pdpu;
+	const struct dpu_format *fmt = NULL;
+	u32 danger_lut, safe_lut;
+
+	if (!plane || !fb) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+
+	if (!pdpu->pipe_hw || !pdpu->pipe_sblk || !pdpu->catalog) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	} else if (!pdpu->pipe_hw->ops.setup_danger_safe_lut) {
+		return;
+	}
+
+	if (!pdpu->is_rt_pipe) {
+		danger_lut = pdpu->catalog->perf.danger_lut_tbl
+				[DPU_QOS_LUT_USAGE_NRT];
+		safe_lut = pdpu->catalog->perf.safe_lut_tbl
+				[DPU_QOS_LUT_USAGE_NRT];
+	} else {
+		fmt = dpu_get_dpu_format_ext(
+				fb->format->format,
+				fb->modifier);
+
+		if (fmt && DPU_FORMAT_IS_LINEAR(fmt)) {
+			danger_lut = pdpu->catalog->perf.danger_lut_tbl
+					[DPU_QOS_LUT_USAGE_LINEAR];
+			safe_lut = pdpu->catalog->perf.safe_lut_tbl
+					[DPU_QOS_LUT_USAGE_LINEAR];
+		} else {
+			danger_lut = pdpu->catalog->perf.danger_lut_tbl
+					[DPU_QOS_LUT_USAGE_MACROTILE];
+			safe_lut = pdpu->catalog->perf.safe_lut_tbl
+					[DPU_QOS_LUT_USAGE_MACROTILE];
+		}
+	}
+
+	pdpu->pipe_qos_cfg.danger_lut = danger_lut;
+	pdpu->pipe_qos_cfg.safe_lut = safe_lut;
+
+	trace_dpu_perf_set_danger_luts(pdpu->pipe - SSPP_VIG0,
+			(fmt) ? fmt->base.pixel_format : 0,
+			(fmt) ? fmt->fetch_mode : 0,
+			pdpu->pipe_qos_cfg.danger_lut,
+			pdpu->pipe_qos_cfg.safe_lut);
+
+	DPU_DEBUG("plane%u: pnum:%d fmt: %4.4s mode:%d luts[0x%x, 0x%x]\n",
+		plane->base.id,
+		pdpu->pipe - SSPP_VIG0,
+		fmt ? (char *)&fmt->base.pixel_format : NULL,
+		fmt ? fmt->fetch_mode : -1,
+		pdpu->pipe_qos_cfg.danger_lut,
+		pdpu->pipe_qos_cfg.safe_lut);
+
+	pdpu->pipe_hw->ops.setup_danger_safe_lut(pdpu->pipe_hw,
+			&pdpu->pipe_qos_cfg);
+}
+
+/**
+ * _dpu_plane_set_qos_ctrl - set QoS control of the given plane
+ * @plane:		Pointer to drm plane
+ * @enable:		true to enable QoS control
+ * @flags:		QoS control mode (enum dpu_plane_qos)
+ */
+static void _dpu_plane_set_qos_ctrl(struct drm_plane *plane,
+	bool enable, u32 flags)
+{
+	struct dpu_plane *pdpu;
+
+	if (!plane) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+
+	if (!pdpu->pipe_hw || !pdpu->pipe_sblk) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	} else if (!pdpu->pipe_hw->ops.setup_qos_ctrl) {
+		return;
+	}
+
+	if (flags & DPU_PLANE_QOS_VBLANK_CTRL) {
+		pdpu->pipe_qos_cfg.creq_vblank = pdpu->pipe_sblk->creq_vblank;
+		pdpu->pipe_qos_cfg.danger_vblank =
+				pdpu->pipe_sblk->danger_vblank;
+		pdpu->pipe_qos_cfg.vblank_en = enable;
+	}
+
+	if (flags & DPU_PLANE_QOS_VBLANK_AMORTIZE) {
+		/* this feature overrules previous VBLANK_CTRL */
+		pdpu->pipe_qos_cfg.vblank_en = false;
+		pdpu->pipe_qos_cfg.creq_vblank = 0; /* clear vblank bits */
+	}
+
+	if (flags & DPU_PLANE_QOS_PANIC_CTRL)
+		pdpu->pipe_qos_cfg.danger_safe_en = enable;
+
+	if (!pdpu->is_rt_pipe) {
+		pdpu->pipe_qos_cfg.vblank_en = false;
+		pdpu->pipe_qos_cfg.danger_safe_en = false;
+	}
+
+	DPU_DEBUG("plane%u: pnum:%d ds:%d vb:%d pri[0x%x, 0x%x] is_rt:%d\n",
+		plane->base.id,
+		pdpu->pipe - SSPP_VIG0,
+		pdpu->pipe_qos_cfg.danger_safe_en,
+		pdpu->pipe_qos_cfg.vblank_en,
+		pdpu->pipe_qos_cfg.creq_vblank,
+		pdpu->pipe_qos_cfg.danger_vblank,
+		pdpu->is_rt_pipe);
+
+	pdpu->pipe_hw->ops.setup_qos_ctrl(pdpu->pipe_hw,
+			&pdpu->pipe_qos_cfg);
+}
+
+int dpu_plane_danger_signal_ctrl(struct drm_plane *plane, bool enable)
+{
+	struct dpu_plane *pdpu;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!plane || !plane->dev) {
+		DPU_ERROR("invalid arguments\n");
+		return -EINVAL;
+	}
+
+	priv = plane->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid KMS reference\n");
+		return -EINVAL;
+	}
+
+	dpu_kms = to_dpu_kms(priv->kms);
+	pdpu = to_dpu_plane(plane);
+
+	if (!pdpu->is_rt_pipe)
+		goto end;
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+	_dpu_plane_set_qos_ctrl(plane, enable, DPU_PLANE_QOS_PANIC_CTRL);
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+end:
+	return 0;
+}
+
+/**
+ * _dpu_plane_set_ot_limit - set OT limit for the given plane
+ * @plane:		Pointer to drm plane
+ * @crtc:		Pointer to drm crtc
+ */
+static void _dpu_plane_set_ot_limit(struct drm_plane *plane,
+		struct drm_crtc *crtc)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_vbif_set_ot_params ot_params;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!plane || !plane->dev || !crtc) {
+		DPU_ERROR("invalid arguments plane %d crtc %d\n",
+				plane != 0, crtc != 0);
+		return;
+	}
+
+	priv = plane->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid KMS reference\n");
+		return;
+	}
+
+	dpu_kms = to_dpu_kms(priv->kms);
+	pdpu = to_dpu_plane(plane);
+	if (!pdpu->pipe_hw) {
+		DPU_ERROR("invalid pipe reference\n");
+		return;
+	}
+
+	memset(&ot_params, 0, sizeof(ot_params));
+	ot_params.xin_id = pdpu->pipe_hw->cap->xin_id;
+	ot_params.num = pdpu->pipe_hw->idx - SSPP_NONE;
+	ot_params.width = drm_rect_width(&pdpu->pipe_cfg.src_rect);
+	ot_params.height = drm_rect_height(&pdpu->pipe_cfg.src_rect);
+	ot_params.is_wfd = !pdpu->is_rt_pipe;
+	ot_params.frame_rate = crtc->mode.vrefresh;
+	ot_params.vbif_idx = VBIF_RT;
+	ot_params.clk_ctrl = pdpu->pipe_hw->cap->clk_ctrl;
+	ot_params.rd = true;
+
+	dpu_vbif_set_ot_limit(dpu_kms, &ot_params);
+}
+
+/**
+ * _dpu_plane_set_vbif_qos - set vbif QoS for the given plane
+ * @plane:		Pointer to drm plane
+ */
+static void _dpu_plane_set_qos_remap(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_vbif_set_qos_params qos_params;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!plane || !plane->dev) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	}
+
+	priv = plane->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid KMS reference\n");
+		return;
+	}
+
+	dpu_kms = to_dpu_kms(priv->kms);
+	pdpu = to_dpu_plane(plane);
+	if (!pdpu->pipe_hw) {
+		DPU_ERROR("invalid pipe reference\n");
+		return;
+	}
+
+	memset(&qos_params, 0, sizeof(qos_params));
+	qos_params.vbif_idx = VBIF_RT;
+	qos_params.clk_ctrl = pdpu->pipe_hw->cap->clk_ctrl;
+	qos_params.xin_id = pdpu->pipe_hw->cap->xin_id;
+	qos_params.num = pdpu->pipe_hw->idx - SSPP_VIG0;
+	qos_params.is_rt = pdpu->is_rt_pipe;
+
+	DPU_DEBUG("plane%d pipe:%d vbif:%d xin:%d rt:%d, clk_ctrl:%d\n",
+			plane->base.id, qos_params.num,
+			qos_params.vbif_idx,
+			qos_params.xin_id, qos_params.is_rt,
+			qos_params.clk_ctrl);
+
+	dpu_vbif_set_qos_remap(dpu_kms, &qos_params);
+}
+
+/**
+ * _dpu_plane_get_aspace: gets the address space
+ */
+static int _dpu_plane_get_aspace(
+		struct dpu_plane *pdpu,
+		struct dpu_plane_state *pstate,
+		struct msm_gem_address_space **aspace)
+{
+	struct dpu_kms *kms;
+
+	if (!pdpu || !pstate || !aspace) {
+		DPU_ERROR("invalid parameters\n");
+		return -EINVAL;
+	}
+
+	kms = _dpu_plane_get_kms(&pdpu->base);
+	if (!kms) {
+		DPU_ERROR("invalid kms\n");
+		return -EINVAL;
+	}
+
+	*aspace = kms->base.aspace;
+
+	return 0;
+}
+
+static inline void _dpu_plane_set_scanout(struct drm_plane *plane,
+		struct dpu_plane_state *pstate,
+		struct dpu_hw_pipe_cfg *pipe_cfg,
+		struct drm_framebuffer *fb)
+{
+	struct dpu_plane *pdpu;
+	struct msm_gem_address_space *aspace = NULL;
+	int ret;
+
+	if (!plane || !pstate || !pipe_cfg || !fb) {
+		DPU_ERROR(
+			"invalid arg(s), plane %d state %d cfg %d fb %d\n",
+			plane != 0, pstate != 0, pipe_cfg != 0, fb != 0);
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	if (!pdpu->pipe_hw) {
+		DPU_ERROR_PLANE(pdpu, "invalid pipe_hw\n");
+		return;
+	}
+
+	ret = _dpu_plane_get_aspace(pdpu, pstate, &aspace);
+	if (ret) {
+		DPU_ERROR_PLANE(pdpu, "Failed to get aspace %d\n", ret);
+		return;
+	}
+
+	ret = dpu_format_populate_layout(aspace, fb, &pipe_cfg->layout);
+	if (ret == -EAGAIN)
+		DPU_DEBUG_PLANE(pdpu, "not updating same src addrs\n");
+	else if (ret)
+		DPU_ERROR_PLANE(pdpu, "failed to get format layout, %d\n", ret);
+	else if (pdpu->pipe_hw->ops.setup_sourceaddress) {
+		trace_dpu_plane_set_scanout(pdpu->pipe_hw->idx,
+					    &pipe_cfg->layout,
+					    pstate->multirect_index);
+		pdpu->pipe_hw->ops.setup_sourceaddress(pdpu->pipe_hw, pipe_cfg,
+						pstate->multirect_index);
+	}
+}
+
+static void _dpu_plane_setup_scaler3(struct dpu_plane *pdpu,
+		struct dpu_plane_state *pstate,
+		uint32_t src_w, uint32_t src_h, uint32_t dst_w, uint32_t dst_h,
+		struct dpu_hw_scaler3_cfg *scale_cfg,
+		const struct dpu_format *fmt,
+		uint32_t chroma_subsmpl_h, uint32_t chroma_subsmpl_v)
+{
+	uint32_t i;
+
+	if (!pdpu || !pstate || !scale_cfg || !fmt || !chroma_subsmpl_h ||
+			!chroma_subsmpl_v) {
+		DPU_ERROR(
+			"pdpu %d pstate %d scale_cfg %d fmt %d smp_h %d smp_v %d\n",
+			!!pdpu, !!pstate, !!scale_cfg, !!fmt, chroma_subsmpl_h,
+			chroma_subsmpl_v);
+		return;
+	}
+
+	memset(scale_cfg, 0, sizeof(*scale_cfg));
+	memset(&pstate->pixel_ext, 0, sizeof(struct dpu_hw_pixel_ext));
+
+	scale_cfg->phase_step_x[DPU_SSPP_COMP_0] =
+		mult_frac((1 << PHASE_STEP_SHIFT), src_w, dst_w);
+	scale_cfg->phase_step_y[DPU_SSPP_COMP_0] =
+		mult_frac((1 << PHASE_STEP_SHIFT), src_h, dst_h);
+
+
+	scale_cfg->phase_step_y[DPU_SSPP_COMP_1_2] =
+		scale_cfg->phase_step_y[DPU_SSPP_COMP_0] / chroma_subsmpl_v;
+	scale_cfg->phase_step_x[DPU_SSPP_COMP_1_2] =
+		scale_cfg->phase_step_x[DPU_SSPP_COMP_0] / chroma_subsmpl_h;
+
+	scale_cfg->phase_step_x[DPU_SSPP_COMP_2] =
+		scale_cfg->phase_step_x[DPU_SSPP_COMP_1_2];
+	scale_cfg->phase_step_y[DPU_SSPP_COMP_2] =
+		scale_cfg->phase_step_y[DPU_SSPP_COMP_1_2];
+
+	scale_cfg->phase_step_x[DPU_SSPP_COMP_3] =
+		scale_cfg->phase_step_x[DPU_SSPP_COMP_0];
+	scale_cfg->phase_step_y[DPU_SSPP_COMP_3] =
+		scale_cfg->phase_step_y[DPU_SSPP_COMP_0];
+
+	for (i = 0; i < DPU_MAX_PLANES; i++) {
+		scale_cfg->src_width[i] = src_w;
+		scale_cfg->src_height[i] = src_h;
+		if (i == DPU_SSPP_COMP_1_2 || i == DPU_SSPP_COMP_2) {
+			scale_cfg->src_width[i] /= chroma_subsmpl_h;
+			scale_cfg->src_height[i] /= chroma_subsmpl_v;
+		}
+		scale_cfg->preload_x[i] = DPU_QSEED3_DEFAULT_PRELOAD_H;
+		scale_cfg->preload_y[i] = DPU_QSEED3_DEFAULT_PRELOAD_V;
+		pstate->pixel_ext.num_ext_pxls_top[i] =
+			scale_cfg->src_height[i];
+		pstate->pixel_ext.num_ext_pxls_left[i] =
+			scale_cfg->src_width[i];
+	}
+	if (!(DPU_FORMAT_IS_YUV(fmt)) && (src_h == dst_h)
+		&& (src_w == dst_w))
+		return;
+
+	scale_cfg->dst_width = dst_w;
+	scale_cfg->dst_height = dst_h;
+	scale_cfg->y_rgb_filter_cfg = DPU_SCALE_BIL;
+	scale_cfg->uv_filter_cfg = DPU_SCALE_BIL;
+	scale_cfg->alpha_filter_cfg = DPU_SCALE_ALPHA_BIL;
+	scale_cfg->lut_flag = 0;
+	scale_cfg->blend_cfg = 1;
+	scale_cfg->enable = 1;
+}
+
+static inline void _dpu_plane_setup_csc(struct dpu_plane *pdpu)
+{
+	static const struct dpu_csc_cfg dpu_csc_YUV2RGB_601L = {
+		{
+			/* S15.16 format */
+			0x00012A00, 0x00000000, 0x00019880,
+			0x00012A00, 0xFFFF9B80, 0xFFFF3000,
+			0x00012A00, 0x00020480, 0x00000000,
+		},
+		/* signed bias */
+		{ 0xfff0, 0xff80, 0xff80,},
+		{ 0x0, 0x0, 0x0,},
+		/* unsigned clamp */
+		{ 0x10, 0xeb, 0x10, 0xf0, 0x10, 0xf0,},
+		{ 0x00, 0xff, 0x00, 0xff, 0x00, 0xff,},
+	};
+	static const struct dpu_csc_cfg dpu_csc10_YUV2RGB_601L = {
+		{
+			/* S15.16 format */
+			0x00012A00, 0x00000000, 0x00019880,
+			0x00012A00, 0xFFFF9B80, 0xFFFF3000,
+			0x00012A00, 0x00020480, 0x00000000,
+			},
+		/* signed bias */
+		{ 0xffc0, 0xfe00, 0xfe00,},
+		{ 0x0, 0x0, 0x0,},
+		/* unsigned clamp */
+		{ 0x40, 0x3ac, 0x40, 0x3c0, 0x40, 0x3c0,},
+		{ 0x00, 0x3ff, 0x00, 0x3ff, 0x00, 0x3ff,},
+	};
+
+	if (!pdpu) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	}
+
+	if (BIT(DPU_SSPP_CSC_10BIT) & pdpu->features)
+		pdpu->csc_ptr = (struct dpu_csc_cfg *)&dpu_csc10_YUV2RGB_601L;
+	else
+		pdpu->csc_ptr = (struct dpu_csc_cfg *)&dpu_csc_YUV2RGB_601L;
+
+	DPU_DEBUG_PLANE(pdpu, "using 0x%X 0x%X 0x%X...\n",
+			pdpu->csc_ptr->csc_mv[0],
+			pdpu->csc_ptr->csc_mv[1],
+			pdpu->csc_ptr->csc_mv[2]);
+}
+
+static void _dpu_plane_setup_scaler(struct dpu_plane *pdpu,
+		struct dpu_plane_state *pstate,
+		const struct dpu_format *fmt, bool color_fill)
+{
+	struct dpu_hw_pixel_ext *pe;
+	uint32_t chroma_subsmpl_h, chroma_subsmpl_v;
+
+	if (!pdpu || !fmt || !pstate) {
+		DPU_ERROR("invalid arg(s), plane %d fmt %d state %d\n",
+				pdpu != 0, fmt != 0, pstate != 0);
+		return;
+	}
+
+	pe = &pstate->pixel_ext;
+
+	/* don't chroma subsample if decimating */
+	chroma_subsmpl_h =
+		drm_format_horz_chroma_subsampling(fmt->base.pixel_format);
+	chroma_subsmpl_v =
+		drm_format_vert_chroma_subsampling(fmt->base.pixel_format);
+
+	/* update scaler. calculate default config for QSEED3 */
+	_dpu_plane_setup_scaler3(pdpu, pstate,
+			drm_rect_width(&pdpu->pipe_cfg.src_rect),
+			drm_rect_height(&pdpu->pipe_cfg.src_rect),
+			drm_rect_width(&pdpu->pipe_cfg.dst_rect),
+			drm_rect_height(&pdpu->pipe_cfg.dst_rect),
+			&pstate->scaler3_cfg, fmt,
+			chroma_subsmpl_h, chroma_subsmpl_v);
+}
+
+/**
+ * _dpu_plane_color_fill - enables color fill on plane
+ * @pdpu:   Pointer to DPU plane object
+ * @color:  RGB fill color value, [23..16] Blue, [15..8] Green, [7..0] Red
+ * @alpha:  8-bit fill alpha value, 255 selects 100% alpha
+ * Returns: 0 on success
+ */
+static int _dpu_plane_color_fill(struct dpu_plane *pdpu,
+		uint32_t color, uint32_t alpha)
+{
+	const struct dpu_format *fmt;
+	const struct drm_plane *plane;
+	struct dpu_plane_state *pstate;
+
+	if (!pdpu || !pdpu->base.state) {
+		DPU_ERROR("invalid plane\n");
+		return -EINVAL;
+	}
+
+	if (!pdpu->pipe_hw) {
+		DPU_ERROR_PLANE(pdpu, "invalid plane h/w pointer\n");
+		return -EINVAL;
+	}
+
+	plane = &pdpu->base;
+	pstate = to_dpu_plane_state(plane->state);
+
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	/*
+	 * select fill format to match user property expectation,
+	 * h/w only supports RGB variants
+	 */
+	fmt = dpu_get_dpu_format(DRM_FORMAT_ABGR8888);
+
+	/* update sspp */
+	if (fmt && pdpu->pipe_hw->ops.setup_solidfill) {
+		pdpu->pipe_hw->ops.setup_solidfill(pdpu->pipe_hw,
+				(color & 0xFFFFFF) | ((alpha & 0xFF) << 24),
+				pstate->multirect_index);
+
+		/* override scaler/decimation if solid fill */
+		pdpu->pipe_cfg.src_rect.x1 = 0;
+		pdpu->pipe_cfg.src_rect.y1 = 0;
+		pdpu->pipe_cfg.src_rect.x2 =
+			drm_rect_width(&pdpu->pipe_cfg.dst_rect);
+		pdpu->pipe_cfg.src_rect.y2 =
+			drm_rect_height(&pdpu->pipe_cfg.dst_rect);
+		_dpu_plane_setup_scaler(pdpu, pstate, fmt, true);
+
+		if (pdpu->pipe_hw->ops.setup_format)
+			pdpu->pipe_hw->ops.setup_format(pdpu->pipe_hw,
+					fmt, DPU_SSPP_SOLID_FILL,
+					pstate->multirect_index);
+
+		if (pdpu->pipe_hw->ops.setup_rects)
+			pdpu->pipe_hw->ops.setup_rects(pdpu->pipe_hw,
+					&pdpu->pipe_cfg,
+					pstate->multirect_index);
+
+		if (pdpu->pipe_hw->ops.setup_pe)
+			pdpu->pipe_hw->ops.setup_pe(pdpu->pipe_hw,
+					&pstate->pixel_ext);
+
+		if (pdpu->pipe_hw->ops.setup_scaler &&
+				pstate->multirect_index != DPU_SSPP_RECT_1)
+			pdpu->pipe_hw->ops.setup_scaler(pdpu->pipe_hw,
+					&pdpu->pipe_cfg, &pstate->pixel_ext,
+					&pstate->scaler3_cfg);
+	}
+
+	return 0;
+}
+
+void dpu_plane_clear_multirect(const struct drm_plane_state *drm_state)
+{
+	struct dpu_plane_state *pstate;
+
+	if (!drm_state)
+		return;
+
+	pstate = to_dpu_plane_state(drm_state);
+
+	pstate->multirect_index = DPU_SSPP_RECT_SOLO;
+	pstate->multirect_mode = DPU_SSPP_MULTIRECT_NONE;
+}
+
+int dpu_plane_validate_multirect_v2(struct dpu_multirect_plane_states *plane)
+{
+	struct dpu_plane_state *pstate[R_MAX];
+	const struct drm_plane_state *drm_state[R_MAX];
+	struct drm_rect src[R_MAX], dst[R_MAX];
+	struct dpu_plane *dpu_plane[R_MAX];
+	const struct dpu_format *fmt[R_MAX];
+	int i, buffer_lines;
+	unsigned int max_tile_height = 1;
+	bool parallel_fetch_qualified = true;
+	bool has_tiled_rect = false;
+
+	for (i = 0; i < R_MAX; i++) {
+		const struct msm_format *msm_fmt;
+
+		drm_state[i] = i ? plane->r1 : plane->r0;
+		msm_fmt = msm_framebuffer_format(drm_state[i]->fb);
+		fmt[i] = to_dpu_format(msm_fmt);
+
+		if (DPU_FORMAT_IS_UBWC(fmt[i])) {
+			has_tiled_rect = true;
+			if (fmt[i]->tile_height > max_tile_height)
+				max_tile_height = fmt[i]->tile_height;
+		}
+	}
+
+	for (i = 0; i < R_MAX; i++) {
+		int width_threshold;
+
+		pstate[i] = to_dpu_plane_state(drm_state[i]);
+		dpu_plane[i] = to_dpu_plane(drm_state[i]->plane);
+
+		if (pstate[i] == NULL) {
+			DPU_ERROR("DPU plane state of plane id %d is NULL\n",
+				drm_state[i]->plane->base.id);
+			return -EINVAL;
+		}
+
+		src[i].x1 = drm_state[i]->src_x >> 16;
+		src[i].y1 = drm_state[i]->src_y >> 16;
+		src[i].x2 = src[i].x1 + (drm_state[i]->src_w >> 16);
+		src[i].y2 = src[i].y1 + (drm_state[i]->src_h >> 16);
+
+		dst[i] = drm_plane_state_dest(drm_state[i]);
+
+		if (drm_rect_calc_hscale(&src[i], &dst[i], 1, 1) != 1 ||
+		    drm_rect_calc_vscale(&src[i], &dst[i], 1, 1) != 1) {
+			DPU_ERROR_PLANE(dpu_plane[i],
+				"scaling is not supported in multirect mode\n");
+			return -EINVAL;
+		}
+
+		if (DPU_FORMAT_IS_YUV(fmt[i])) {
+			DPU_ERROR_PLANE(dpu_plane[i],
+				"Unsupported format for multirect mode\n");
+			return -EINVAL;
+		}
+
+		/**
+		 * SSPP PD_MEM is split half - one for each RECT.
+		 * Tiled formats need 5 lines of buffering while fetching
+		 * whereas linear formats need only 2 lines.
+		 * So we cannot support more than half of the supported SSPP
+		 * width for tiled formats.
+		 */
+		width_threshold = dpu_plane[i]->pipe_sblk->common->maxlinewidth;
+		if (has_tiled_rect)
+			width_threshold /= 2;
+
+		if (parallel_fetch_qualified &&
+		    drm_rect_width(&src[i]) > width_threshold)
+			parallel_fetch_qualified = false;
+
+	}
+
+	/* Validate RECT's and set the mode */
+
+	/* Prefer PARALLEL FETCH Mode over TIME_MX Mode */
+	if (parallel_fetch_qualified) {
+		pstate[R0]->multirect_mode = DPU_SSPP_MULTIRECT_PARALLEL;
+		pstate[R1]->multirect_mode = DPU_SSPP_MULTIRECT_PARALLEL;
+
+		goto done;
+	}
+
+	/* TIME_MX Mode */
+	buffer_lines = 2 * max_tile_height;
+
+	if (dst[R1].y1 >= dst[R0].y2 + buffer_lines ||
+	    dst[R0].y1 >= dst[R1].y2 + buffer_lines) {
+		pstate[R0]->multirect_mode = DPU_SSPP_MULTIRECT_TIME_MX;
+		pstate[R1]->multirect_mode = DPU_SSPP_MULTIRECT_TIME_MX;
+	} else {
+		DPU_ERROR(
+			"No multirect mode possible for the planes (%d - %d)\n",
+			drm_state[R0]->plane->base.id,
+			drm_state[R1]->plane->base.id);
+		return -EINVAL;
+	}
+
+done:
+	if (dpu_plane[R0]->is_virtual) {
+		pstate[R0]->multirect_index = DPU_SSPP_RECT_1;
+		pstate[R1]->multirect_index = DPU_SSPP_RECT_0;
+	} else {
+		pstate[R0]->multirect_index = DPU_SSPP_RECT_0;
+		pstate[R1]->multirect_index = DPU_SSPP_RECT_1;
+	};
+
+	DPU_DEBUG_PLANE(dpu_plane[R0], "R0: %d - %d\n",
+		pstate[R0]->multirect_mode, pstate[R0]->multirect_index);
+	DPU_DEBUG_PLANE(dpu_plane[R1], "R1: %d - %d\n",
+		pstate[R1]->multirect_mode, pstate[R1]->multirect_index);
+	return 0;
+}
+
+/**
+ * dpu_plane_get_ctl_flush - get control flush for the given plane
+ * @plane: Pointer to drm plane structure
+ * @ctl: Pointer to hardware control driver
+ * @flush_sspp: Pointer to sspp flush control word
+ */
+void dpu_plane_get_ctl_flush(struct drm_plane *plane, struct dpu_hw_ctl *ctl,
+		u32 *flush_sspp)
+{
+	struct dpu_plane_state *pstate;
+
+	if (!plane || !flush_sspp) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	pstate = to_dpu_plane_state(plane->state);
+
+	*flush_sspp = ctl->ops.get_bitmask_sspp(ctl, dpu_plane_pipe(plane));
+}
+
+static int dpu_plane_prepare_fb(struct drm_plane *plane,
+		struct drm_plane_state *new_state)
+{
+	struct drm_framebuffer *fb = new_state->fb;
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+	struct dpu_plane_state *pstate = to_dpu_plane_state(new_state);
+	struct dpu_hw_fmt_layout layout;
+	struct drm_gem_object *obj;
+	struct msm_gem_object *msm_obj;
+	struct dma_fence *fence;
+	struct msm_gem_address_space *aspace;
+	int ret;
+
+	if (!new_state->fb)
+		return 0;
+
+	DPU_DEBUG_PLANE(pdpu, "FB[%u]\n", fb->base.id);
+
+	ret = _dpu_plane_get_aspace(pdpu, pstate, &aspace);
+	if (ret) {
+		DPU_ERROR_PLANE(pdpu, "Failed to get aspace\n");
+		return ret;
+	}
+
+	/* cache aspace */
+	pstate->aspace = aspace;
+
+	/*
+	 * TODO: Need to sort out the msm_framebuffer_prepare() call below so
+	 *       we can use msm_atomic_prepare_fb() instead of doing the
+	 *       implicit fence and fb prepare by hand here.
+	 */
+	obj = msm_framebuffer_bo(new_state->fb, 0);
+	msm_obj = to_msm_bo(obj);
+	fence = reservation_object_get_excl_rcu(msm_obj->resv);
+	if (fence)
+		drm_atomic_set_fence_for_plane(new_state, fence);
+
+	if (pstate->aspace) {
+		ret = msm_framebuffer_prepare(new_state->fb,
+				pstate->aspace);
+		if (ret) {
+			DPU_ERROR("failed to prepare framebuffer\n");
+			return ret;
+		}
+	}
+
+	/* validate framebuffer layout before commit */
+	ret = dpu_format_populate_layout(pstate->aspace,
+			new_state->fb, &layout);
+	if (ret) {
+		DPU_ERROR_PLANE(pdpu, "failed to get format layout, %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void dpu_plane_cleanup_fb(struct drm_plane *plane,
+		struct drm_plane_state *old_state)
+{
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+	struct dpu_plane_state *old_pstate;
+
+	if (!old_state || !old_state->fb)
+		return;
+
+	old_pstate = to_dpu_plane_state(old_state);
+
+	DPU_DEBUG_PLANE(pdpu, "FB[%u]\n", old_state->fb->base.id);
+
+	msm_framebuffer_cleanup(old_state->fb, old_pstate->aspace);
+}
+
+static bool dpu_plane_validate_src(struct drm_rect *src,
+				   struct drm_rect *fb_rect,
+				   uint32_t min_src_size)
+{
+	/* Ensure fb size is supported */
+	if (drm_rect_width(fb_rect) > MAX_IMG_WIDTH ||
+	    drm_rect_height(fb_rect) > MAX_IMG_HEIGHT)
+		return false;
+
+	/* Ensure src rect is above the minimum size */
+	if (drm_rect_width(src) < min_src_size ||
+	    drm_rect_height(src) < min_src_size)
+		return false;
+
+	/* Ensure src is fully encapsulated in fb */
+	return drm_rect_intersect(fb_rect, src) &&
+		drm_rect_equals(fb_rect, src);
+}
+
+static int dpu_plane_sspp_atomic_check(struct drm_plane *plane,
+		struct drm_plane_state *state)
+{
+	int ret = 0;
+	struct dpu_plane *pdpu;
+	struct dpu_plane_state *pstate;
+	const struct dpu_format *fmt;
+	struct drm_rect src, dst, fb_rect = { 0 };
+	uint32_t max_upscale = 1, max_downscale = 1;
+	uint32_t min_src_size, max_linewidth;
+	int hscale = 1, vscale = 1;
+
+	if (!plane || !state) {
+		DPU_ERROR("invalid arg(s), plane %d state %d\n",
+				plane != 0, state != 0);
+		ret = -EINVAL;
+		goto exit;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	pstate = to_dpu_plane_state(state);
+
+	if (!pdpu->pipe_sblk) {
+		DPU_ERROR_PLANE(pdpu, "invalid catalog\n");
+		ret = -EINVAL;
+		goto exit;
+	}
+
+	src.x1 = state->src_x >> 16;
+	src.y1 = state->src_y >> 16;
+	src.x2 = src.x1 + (state->src_w >> 16);
+	src.y2 = src.y1 + (state->src_h >> 16);
+
+	dst = drm_plane_state_dest(state);
+
+	fb_rect.x2 = state->fb->width;
+	fb_rect.y2 = state->fb->height;
+
+	max_linewidth = pdpu->pipe_sblk->common->maxlinewidth;
+
+	if (pdpu->features & DPU_SSPP_SCALER) {
+		max_downscale = pdpu->pipe_sblk->maxdwnscale;
+		max_upscale = pdpu->pipe_sblk->maxupscale;
+	}
+	if (drm_rect_width(&src) < drm_rect_width(&dst))
+		hscale = drm_rect_calc_hscale(&src, &dst, 1, max_upscale);
+	else
+		hscale = drm_rect_calc_hscale(&dst, &src, 1, max_downscale);
+	if (drm_rect_height(&src) < drm_rect_height(&dst))
+		vscale = drm_rect_calc_vscale(&src, &dst, 1, max_upscale);
+	else
+		vscale = drm_rect_calc_vscale(&dst, &src, 1, max_downscale);
+
+	DPU_DEBUG_PLANE(pdpu, "check %d -> %d\n",
+		dpu_plane_enabled(plane->state), dpu_plane_enabled(state));
+
+	if (!dpu_plane_enabled(state))
+		goto exit;
+
+	fmt = to_dpu_format(msm_framebuffer_format(state->fb));
+
+	min_src_size = DPU_FORMAT_IS_YUV(fmt) ? 2 : 1;
+
+	if (DPU_FORMAT_IS_YUV(fmt) &&
+		(!(pdpu->features & DPU_SSPP_SCALER) ||
+		 !(pdpu->features & (BIT(DPU_SSPP_CSC)
+		 | BIT(DPU_SSPP_CSC_10BIT))))) {
+		DPU_ERROR_PLANE(pdpu,
+				"plane doesn't have scaler/csc for yuv\n");
+		ret = -EINVAL;
+
+	/* check src bounds */
+	} else if (!dpu_plane_validate_src(&src, &fb_rect, min_src_size)) {
+		DPU_ERROR_PLANE(pdpu, "invalid source " DRM_RECT_FMT "\n",
+				DRM_RECT_ARG(&src));
+		ret = -E2BIG;
+
+	/* valid yuv image */
+	} else if (DPU_FORMAT_IS_YUV(fmt) &&
+		   (src.x1 & 0x1 || src.y1 & 0x1 ||
+		    drm_rect_width(&src) & 0x1 ||
+		    drm_rect_height(&src) & 0x1)) {
+		DPU_ERROR_PLANE(pdpu, "invalid yuv source " DRM_RECT_FMT "\n",
+				DRM_RECT_ARG(&src));
+		ret = -EINVAL;
+
+	/* min dst support */
+	} else if (drm_rect_width(&dst) < 0x1 || drm_rect_height(&dst) < 0x1) {
+		DPU_ERROR_PLANE(pdpu, "invalid dest rect " DRM_RECT_FMT "\n",
+				DRM_RECT_ARG(&dst));
+		ret = -EINVAL;
+
+	/* check decimated source width */
+	} else if (drm_rect_width(&src) > max_linewidth) {
+		DPU_ERROR_PLANE(pdpu, "invalid src " DRM_RECT_FMT " line:%u\n",
+				DRM_RECT_ARG(&src), max_linewidth);
+		ret = -E2BIG;
+
+	/* check scaler capability */
+	} else if (hscale < 0 || vscale < 0) {
+		DPU_ERROR_PLANE(pdpu, "invalid scaling requested src="
+				DRM_RECT_FMT " dst=" DRM_RECT_FMT "\n",
+				DRM_RECT_ARG(&src), DRM_RECT_ARG(&dst));
+		ret = -E2BIG;
+	}
+
+exit:
+	return ret;
+}
+
+static int dpu_plane_atomic_check(struct drm_plane *plane,
+		struct drm_plane_state *state)
+{
+	if (!state->fb)
+		return 0;
+
+	DPU_DEBUG_PLANE(to_dpu_plane(plane), "\n");
+
+	return dpu_plane_sspp_atomic_check(plane, state);
+}
+
+void dpu_plane_flush(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_plane_state *pstate;
+
+	if (!plane || !plane->state) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	pstate = to_dpu_plane_state(plane->state);
+
+	/*
+	 * These updates have to be done immediately before the plane flush
+	 * timing, and may not be moved to the atomic_update/mode_set functions.
+	 */
+	if (pdpu->is_error)
+		/* force white frame with 100% alpha pipe output on error */
+		_dpu_plane_color_fill(pdpu, 0xFFFFFF, 0xFF);
+	else if (pdpu->color_fill & DPU_PLANE_COLOR_FILL_FLAG)
+		/* force 100% alpha */
+		_dpu_plane_color_fill(pdpu, pdpu->color_fill, 0xFF);
+	else if (pdpu->pipe_hw && pdpu->csc_ptr && pdpu->pipe_hw->ops.setup_csc)
+		pdpu->pipe_hw->ops.setup_csc(pdpu->pipe_hw, pdpu->csc_ptr);
+
+	/* flag h/w flush complete */
+	if (plane->state)
+		pstate->pending = false;
+}
+
+/**
+ * dpu_plane_set_error: enable/disable error condition
+ * @plane: pointer to drm_plane structure
+ */
+void dpu_plane_set_error(struct drm_plane *plane, bool error)
+{
+	struct dpu_plane *pdpu;
+
+	if (!plane)
+		return;
+
+	pdpu = to_dpu_plane(plane);
+	pdpu->is_error = error;
+}
+
+static int dpu_plane_sspp_atomic_update(struct drm_plane *plane,
+				struct drm_plane_state *old_state)
+{
+	uint32_t nplanes, src_flags;
+	struct dpu_plane *pdpu;
+	struct drm_plane_state *state;
+	struct dpu_plane_state *pstate;
+	struct dpu_plane_state *old_pstate;
+	const struct dpu_format *fmt;
+	struct drm_crtc *crtc;
+	struct drm_framebuffer *fb;
+	struct drm_rect src, dst;
+
+	if (!plane) {
+		DPU_ERROR("invalid plane\n");
+		return -EINVAL;
+	} else if (!plane->state) {
+		DPU_ERROR("invalid plane state\n");
+		return -EINVAL;
+	} else if (!old_state) {
+		DPU_ERROR("invalid old state\n");
+		return -EINVAL;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	state = plane->state;
+
+	pstate = to_dpu_plane_state(state);
+
+	old_pstate = to_dpu_plane_state(old_state);
+
+	crtc = state->crtc;
+	fb = state->fb;
+	if (!crtc || !fb) {
+		DPU_ERROR_PLANE(pdpu, "invalid crtc %d or fb %d\n",
+				crtc != 0, fb != 0);
+		return -EINVAL;
+	}
+	fmt = to_dpu_format(msm_framebuffer_format(fb));
+	nplanes = fmt->num_planes;
+
+	memset(&(pdpu->pipe_cfg), 0, sizeof(struct dpu_hw_pipe_cfg));
+
+	_dpu_plane_set_scanout(plane, pstate, &pdpu->pipe_cfg, fb);
+
+	pstate->pending = true;
+
+	pdpu->is_rt_pipe = (dpu_crtc_get_client_type(crtc) != NRT_CLIENT);
+	_dpu_plane_set_qos_ctrl(plane, false, DPU_PLANE_QOS_PANIC_CTRL);
+
+	src.x1 = state->src_x >> 16;
+	src.y1 = state->src_y >> 16;
+	src.x2 = src.x1 + (state->src_w >> 16);
+	src.y2 = src.y1 + (state->src_h >> 16);
+
+	dst = drm_plane_state_dest(state);
+
+	DPU_DEBUG_PLANE(pdpu, "FB[%u] " DRM_RECT_FMT "->crtc%u " DRM_RECT_FMT
+			", %4.4s ubwc %d\n", fb->base.id, DRM_RECT_ARG(&src),
+			crtc->base.id, DRM_RECT_ARG(&dst),
+			(char *)&fmt->base.pixel_format,
+			DPU_FORMAT_IS_UBWC(fmt));
+
+	pdpu->pipe_cfg.src_rect = src;
+	pdpu->pipe_cfg.dst_rect = dst;
+
+	_dpu_plane_setup_scaler(pdpu, pstate, fmt, false);
+
+	/* override for color fill */
+	if (pdpu->color_fill & DPU_PLANE_COLOR_FILL_FLAG) {
+		/* skip remaining processing on color fill */
+		return 0;
+	}
+
+	if (pdpu->pipe_hw->ops.setup_rects) {
+		pdpu->pipe_hw->ops.setup_rects(pdpu->pipe_hw,
+				&pdpu->pipe_cfg,
+				pstate->multirect_index);
+	}
+
+	if (pdpu->pipe_hw->ops.setup_pe &&
+			(pstate->multirect_index != DPU_SSPP_RECT_1))
+		pdpu->pipe_hw->ops.setup_pe(pdpu->pipe_hw,
+				&pstate->pixel_ext);
+
+	/**
+	 * when programmed in multirect mode, scalar block will be
+	 * bypassed. Still we need to update alpha and bitwidth
+	 * ONLY for RECT0
+	 */
+	if (pdpu->pipe_hw->ops.setup_scaler &&
+			pstate->multirect_index != DPU_SSPP_RECT_1)
+		pdpu->pipe_hw->ops.setup_scaler(pdpu->pipe_hw,
+				&pdpu->pipe_cfg, &pstate->pixel_ext,
+				&pstate->scaler3_cfg);
+
+	if (pdpu->pipe_hw->ops.setup_multirect)
+		pdpu->pipe_hw->ops.setup_multirect(
+				pdpu->pipe_hw,
+				pstate->multirect_index,
+				pstate->multirect_mode);
+
+	if (pdpu->pipe_hw->ops.setup_format) {
+		src_flags = 0x0;
+
+		/* update format */
+		pdpu->pipe_hw->ops.setup_format(pdpu->pipe_hw, fmt, src_flags,
+				pstate->multirect_index);
+
+		if (pdpu->pipe_hw->ops.setup_cdp) {
+			struct dpu_hw_pipe_cdp_cfg *cdp_cfg = &pstate->cdp_cfg;
+
+			memset(cdp_cfg, 0, sizeof(struct dpu_hw_pipe_cdp_cfg));
+
+			cdp_cfg->enable = pdpu->catalog->perf.cdp_cfg
+					[DPU_PERF_CDP_USAGE_RT].rd_enable;
+			cdp_cfg->ubwc_meta_enable =
+					DPU_FORMAT_IS_UBWC(fmt);
+			cdp_cfg->tile_amortize_enable =
+					DPU_FORMAT_IS_UBWC(fmt) ||
+					DPU_FORMAT_IS_TILE(fmt);
+			cdp_cfg->preload_ahead = DPU_SSPP_CDP_PRELOAD_AHEAD_64;
+
+			pdpu->pipe_hw->ops.setup_cdp(pdpu->pipe_hw, cdp_cfg);
+		}
+
+		/* update csc */
+		if (DPU_FORMAT_IS_YUV(fmt))
+			_dpu_plane_setup_csc(pdpu);
+		else
+			pdpu->csc_ptr = 0;
+	}
+
+	_dpu_plane_set_qos_lut(plane, fb);
+	_dpu_plane_set_danger_lut(plane, fb);
+
+	if (plane->type != DRM_PLANE_TYPE_CURSOR) {
+		_dpu_plane_set_qos_ctrl(plane, true, DPU_PLANE_QOS_PANIC_CTRL);
+		_dpu_plane_set_ot_limit(plane, crtc);
+	}
+
+	_dpu_plane_set_qos_remap(plane);
+	return 0;
+}
+
+static void _dpu_plane_atomic_disable(struct drm_plane *plane,
+				struct drm_plane_state *old_state)
+{
+	struct dpu_plane *pdpu;
+	struct drm_plane_state *state;
+	struct dpu_plane_state *pstate;
+
+	if (!plane) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	} else if (!plane->state) {
+		DPU_ERROR("invalid plane state\n");
+		return;
+	} else if (!old_state) {
+		DPU_ERROR("invalid old state\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	state = plane->state;
+	pstate = to_dpu_plane_state(state);
+
+	trace_dpu_plane_disable(DRMID(plane), is_dpu_plane_virtual(plane),
+				pstate->multirect_mode);
+
+	pstate->pending = true;
+
+	if (is_dpu_plane_virtual(plane) &&
+			pdpu->pipe_hw && pdpu->pipe_hw->ops.setup_multirect)
+		pdpu->pipe_hw->ops.setup_multirect(pdpu->pipe_hw,
+				DPU_SSPP_RECT_SOLO, DPU_SSPP_MULTIRECT_NONE);
+}
+
+static void dpu_plane_atomic_update(struct drm_plane *plane,
+				struct drm_plane_state *old_state)
+{
+	struct dpu_plane *pdpu;
+	struct drm_plane_state *state;
+
+	if (!plane) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	} else if (!plane->state) {
+		DPU_ERROR("invalid plane state\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	pdpu->is_error = false;
+	state = plane->state;
+
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	if (!dpu_plane_sspp_enabled(state)) {
+		_dpu_plane_atomic_disable(plane, old_state);
+	} else {
+		int ret;
+
+		ret = dpu_plane_sspp_atomic_update(plane, old_state);
+		/* atomic_check should have ensured that this doesn't fail */
+		WARN_ON(ret < 0);
+	}
+}
+
+void dpu_plane_restore(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+
+	if (!plane || !plane->state) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	/* last plane state is same as current state */
+	dpu_plane_atomic_update(plane, plane->state);
+}
+
+static void dpu_plane_destroy(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu = plane ? to_dpu_plane(plane) : NULL;
+
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	if (pdpu) {
+		_dpu_plane_set_qos_ctrl(plane, false, DPU_PLANE_QOS_PANIC_CTRL);
+
+		mutex_destroy(&pdpu->lock);
+
+		drm_plane_helper_disable(plane, NULL);
+
+		/* this will destroy the states as well */
+		drm_plane_cleanup(plane);
+
+		if (pdpu->pipe_hw)
+			dpu_hw_sspp_destroy(pdpu->pipe_hw);
+
+		kfree(pdpu);
+	}
+}
+
+static void dpu_plane_destroy_state(struct drm_plane *plane,
+		struct drm_plane_state *state)
+{
+	struct dpu_plane_state *pstate;
+
+	if (!plane || !state) {
+		DPU_ERROR("invalid arg(s), plane %d state %d\n",
+				plane != 0, state != 0);
+		return;
+	}
+
+	pstate = to_dpu_plane_state(state);
+
+	/* remove ref count for frame buffers */
+	if (state->fb)
+		drm_framebuffer_put(state->fb);
+
+	kfree(pstate);
+}
+
+static struct drm_plane_state *
+dpu_plane_duplicate_state(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_plane_state *pstate;
+	struct dpu_plane_state *old_state;
+
+	if (!plane) {
+		DPU_ERROR("invalid plane\n");
+		return NULL;
+	} else if (!plane->state) {
+		DPU_ERROR("invalid plane state\n");
+		return NULL;
+	}
+
+	old_state = to_dpu_plane_state(plane->state);
+	pdpu = to_dpu_plane(plane);
+	pstate = kmemdup(old_state, sizeof(*old_state), GFP_KERNEL);
+	if (!pstate) {
+		DPU_ERROR_PLANE(pdpu, "failed to allocate state\n");
+		return NULL;
+	}
+
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	pstate->pending = false;
+
+	__drm_atomic_helper_plane_duplicate_state(plane, &pstate->base);
+
+	return &pstate->base;
+}
+
+static void dpu_plane_reset(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_plane_state *pstate;
+
+	if (!plane) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	/* remove previous state, if present */
+	if (plane->state) {
+		dpu_plane_destroy_state(plane, plane->state);
+		plane->state = 0;
+	}
+
+	pstate = kzalloc(sizeof(*pstate), GFP_KERNEL);
+	if (!pstate) {
+		DPU_ERROR_PLANE(pdpu, "failed to allocate state\n");
+		return;
+	}
+
+	pstate->base.plane = plane;
+
+	plane->state = &pstate->base;
+}
+
+#ifdef CONFIG_DEBUG_FS
+static ssize_t _dpu_plane_danger_read(struct file *file,
+			char __user *buff, size_t count, loff_t *ppos)
+{
+	struct dpu_kms *kms = file->private_data;
+	struct dpu_mdss_cfg *cfg = kms->catalog;
+	int len = 0;
+	char buf[40] = {'\0'};
+
+	if (!cfg)
+		return -ENODEV;
+
+	if (*ppos)
+		return 0; /* the end */
+
+	len = snprintf(buf, sizeof(buf), "%d\n", !kms->has_danger_ctrl);
+	if (len < 0 || len >= sizeof(buf))
+		return 0;
+
+	if ((count < sizeof(buf)) || copy_to_user(buff, buf, len))
+		return -EFAULT;
+
+	*ppos += len;   /* increase offset */
+
+	return len;
+}
+
+static void _dpu_plane_set_danger_state(struct dpu_kms *kms, bool enable)
+{
+	struct drm_plane *plane;
+
+	drm_for_each_plane(plane, kms->dev) {
+		if (plane->fb && plane->state) {
+			dpu_plane_danger_signal_ctrl(plane, enable);
+			DPU_DEBUG("plane:%d img:%dx%d ",
+				plane->base.id, plane->fb->width,
+				plane->fb->height);
+			DPU_DEBUG("src[%d,%d,%d,%d] dst[%d,%d,%d,%d]\n",
+				plane->state->src_x >> 16,
+				plane->state->src_y >> 16,
+				plane->state->src_w >> 16,
+				plane->state->src_h >> 16,
+				plane->state->crtc_x, plane->state->crtc_y,
+				plane->state->crtc_w, plane->state->crtc_h);
+		} else {
+			DPU_DEBUG("Inactive plane:%d\n", plane->base.id);
+		}
+	}
+}
+
+static ssize_t _dpu_plane_danger_write(struct file *file,
+		    const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	struct dpu_kms *kms = file->private_data;
+	struct dpu_mdss_cfg *cfg = kms->catalog;
+	int disable_panic;
+	char buf[10];
+
+	if (!cfg)
+		return -EFAULT;
+
+	if (count >= sizeof(buf))
+		return -EFAULT;
+
+	if (copy_from_user(buf, user_buf, count))
+		return -EFAULT;
+
+	buf[count] = 0;	/* end of string */
+
+	if (kstrtoint(buf, 0, &disable_panic))
+		return -EFAULT;
+
+	if (disable_panic) {
+		/* Disable panic signal for all active pipes */
+		DPU_DEBUG("Disabling danger:\n");
+		_dpu_plane_set_danger_state(kms, false);
+		kms->has_danger_ctrl = false;
+	} else {
+		/* Enable panic signal for all active pipes */
+		DPU_DEBUG("Enabling danger:\n");
+		kms->has_danger_ctrl = true;
+		_dpu_plane_set_danger_state(kms, true);
+	}
+
+	return count;
+}
+
+static const struct file_operations dpu_plane_danger_enable = {
+	.open = simple_open,
+	.read = _dpu_plane_danger_read,
+	.write = _dpu_plane_danger_write,
+};
+
+static int _dpu_plane_init_debugfs(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_kms *kms;
+	struct msm_drm_private *priv;
+	const struct dpu_sspp_sub_blks *sblk = 0;
+	const struct dpu_sspp_cfg *cfg = 0;
+
+	if (!plane || !plane->dev) {
+		DPU_ERROR("invalid arguments\n");
+		return -EINVAL;
+	}
+
+	priv = plane->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid KMS reference\n");
+		return -EINVAL;
+	}
+
+	kms = to_dpu_kms(priv->kms);
+	pdpu = to_dpu_plane(plane);
+
+	if (pdpu && pdpu->pipe_hw)
+		cfg = pdpu->pipe_hw->cap;
+	if (cfg)
+		sblk = cfg->sblk;
+
+	if (!sblk)
+		return 0;
+
+	/* create overall sub-directory for the pipe */
+	pdpu->debugfs_root =
+		debugfs_create_dir(pdpu->pipe_name,
+				plane->dev->primary->debugfs_root);
+
+	if (!pdpu->debugfs_root)
+		return -ENOMEM;
+
+	/* don't error check these */
+	debugfs_create_x32("features", 0600,
+			pdpu->debugfs_root, &pdpu->features);
+
+	/* add register dump support */
+	dpu_debugfs_setup_regset32(&pdpu->debugfs_src,
+			sblk->src_blk.base + cfg->base,
+			sblk->src_blk.len,
+			kms);
+	dpu_debugfs_create_regset32("src_blk", 0400,
+			pdpu->debugfs_root, &pdpu->debugfs_src);
+
+	if (cfg->features & BIT(DPU_SSPP_SCALER_QSEED3) ||
+			cfg->features & BIT(DPU_SSPP_SCALER_QSEED2)) {
+		dpu_debugfs_setup_regset32(&pdpu->debugfs_scaler,
+				sblk->scaler_blk.base + cfg->base,
+				sblk->scaler_blk.len,
+				kms);
+		dpu_debugfs_create_regset32("scaler_blk", 0400,
+				pdpu->debugfs_root,
+				&pdpu->debugfs_scaler);
+		debugfs_create_bool("default_scaling",
+				0600,
+				pdpu->debugfs_root,
+				&pdpu->debugfs_default_scale);
+	}
+
+	if (cfg->features & BIT(DPU_SSPP_CSC) ||
+			cfg->features & BIT(DPU_SSPP_CSC_10BIT)) {
+		dpu_debugfs_setup_regset32(&pdpu->debugfs_csc,
+				sblk->csc_blk.base + cfg->base,
+				sblk->csc_blk.len,
+				kms);
+		dpu_debugfs_create_regset32("csc_blk", 0400,
+				pdpu->debugfs_root, &pdpu->debugfs_csc);
+	}
+
+	debugfs_create_u32("xin_id",
+			0400,
+			pdpu->debugfs_root,
+			(u32 *) &cfg->xin_id);
+	debugfs_create_u32("clk_ctrl",
+			0400,
+			pdpu->debugfs_root,
+			(u32 *) &cfg->clk_ctrl);
+	debugfs_create_x32("creq_vblank",
+			0600,
+			pdpu->debugfs_root,
+			(u32 *) &sblk->creq_vblank);
+	debugfs_create_x32("danger_vblank",
+			0600,
+			pdpu->debugfs_root,
+			(u32 *) &sblk->danger_vblank);
+
+	debugfs_create_file("disable_danger",
+			0600,
+			pdpu->debugfs_root,
+			kms, &dpu_plane_danger_enable);
+
+	return 0;
+}
+
+static void _dpu_plane_destroy_debugfs(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+
+	if (!plane)
+		return;
+	pdpu = to_dpu_plane(plane);
+
+	debugfs_remove_recursive(pdpu->debugfs_root);
+}
+#else
+static int _dpu_plane_init_debugfs(struct drm_plane *plane)
+{
+	return 0;
+}
+static void _dpu_plane_destroy_debugfs(struct drm_plane *plane)
+{
+}
+#endif
+
+static int dpu_plane_late_register(struct drm_plane *plane)
+{
+	return _dpu_plane_init_debugfs(plane);
+}
+
+static void dpu_plane_early_unregister(struct drm_plane *plane)
+{
+	_dpu_plane_destroy_debugfs(plane);
+}
+
+static const struct drm_plane_funcs dpu_plane_funcs = {
+		.update_plane = drm_atomic_helper_update_plane,
+		.disable_plane = drm_atomic_helper_disable_plane,
+		.destroy = dpu_plane_destroy,
+		.reset = dpu_plane_reset,
+		.atomic_duplicate_state = dpu_plane_duplicate_state,
+		.atomic_destroy_state = dpu_plane_destroy_state,
+		.late_register = dpu_plane_late_register,
+		.early_unregister = dpu_plane_early_unregister,
+};
+
+static const struct drm_plane_helper_funcs dpu_plane_helper_funcs = {
+		.prepare_fb = dpu_plane_prepare_fb,
+		.cleanup_fb = dpu_plane_cleanup_fb,
+		.atomic_check = dpu_plane_atomic_check,
+		.atomic_update = dpu_plane_atomic_update,
+};
+
+enum dpu_sspp dpu_plane_pipe(struct drm_plane *plane)
+{
+	return plane ? to_dpu_plane(plane)->pipe : SSPP_NONE;
+}
+
+bool is_dpu_plane_virtual(struct drm_plane *plane)
+{
+	return plane ? to_dpu_plane(plane)->is_virtual : false;
+}
+
+/* initialize plane */
+struct drm_plane *dpu_plane_init(struct drm_device *dev,
+		uint32_t pipe, bool primary_plane,
+		unsigned long possible_crtcs, u32 master_plane_id)
+{
+	struct drm_plane *plane = NULL, *master_plane = NULL;
+	const struct dpu_format_extended *format_list;
+	struct dpu_plane *pdpu;
+	struct msm_drm_private *priv;
+	struct dpu_kms *kms;
+	enum drm_plane_type type;
+	int zpos_max = DPU_ZPOS_MAX;
+	int ret = -EINVAL;
+
+	if (!dev) {
+		DPU_ERROR("[%u]device is NULL\n", pipe);
+		goto exit;
+	}
+
+	priv = dev->dev_private;
+	if (!priv) {
+		DPU_ERROR("[%u]private data is NULL\n", pipe);
+		goto exit;
+	}
+
+	if (!priv->kms) {
+		DPU_ERROR("[%u]invalid KMS reference\n", pipe);
+		goto exit;
+	}
+	kms = to_dpu_kms(priv->kms);
+
+	if (!kms->catalog) {
+		DPU_ERROR("[%u]invalid catalog reference\n", pipe);
+		goto exit;
+	}
+
+	/* create and zero local structure */
+	pdpu = kzalloc(sizeof(*pdpu), GFP_KERNEL);
+	if (!pdpu) {
+		DPU_ERROR("[%u]failed to allocate local plane struct\n", pipe);
+		ret = -ENOMEM;
+		goto exit;
+	}
+
+	/* cache local stuff for later */
+	plane = &pdpu->base;
+	pdpu->pipe = pipe;
+	pdpu->is_virtual = (master_plane_id != 0);
+	INIT_LIST_HEAD(&pdpu->mplane_list);
+	master_plane = drm_plane_find(dev, NULL, master_plane_id);
+	if (master_plane) {
+		struct dpu_plane *mpdpu = to_dpu_plane(master_plane);
+
+		list_add_tail(&pdpu->mplane_list, &mpdpu->mplane_list);
+	}
+
+	/* initialize underlying h/w driver */
+	pdpu->pipe_hw = dpu_hw_sspp_init(pipe, kms->mmio, kms->catalog,
+							master_plane_id != 0);
+	if (IS_ERR(pdpu->pipe_hw)) {
+		DPU_ERROR("[%u]SSPP init failed\n", pipe);
+		ret = PTR_ERR(pdpu->pipe_hw);
+		goto clean_plane;
+	} else if (!pdpu->pipe_hw->cap || !pdpu->pipe_hw->cap->sblk) {
+		DPU_ERROR("[%u]SSPP init returned invalid cfg\n", pipe);
+		goto clean_sspp;
+	}
+
+	/* cache features mask for later */
+	pdpu->features = pdpu->pipe_hw->cap->features;
+	pdpu->pipe_sblk = pdpu->pipe_hw->cap->sblk;
+	if (!pdpu->pipe_sblk) {
+		DPU_ERROR("[%u]invalid sblk\n", pipe);
+		goto clean_sspp;
+	}
+
+	if (!master_plane_id)
+		format_list = pdpu->pipe_sblk->format_list;
+	else
+		format_list = pdpu->pipe_sblk->virt_format_list;
+
+	pdpu->nformats = dpu_populate_formats(format_list,
+				pdpu->formats,
+				0,
+				ARRAY_SIZE(pdpu->formats));
+
+	if (!pdpu->nformats) {
+		DPU_ERROR("[%u]no valid formats for plane\n", pipe);
+		goto clean_sspp;
+	}
+
+	if (pdpu->features & BIT(DPU_SSPP_CURSOR))
+		type = DRM_PLANE_TYPE_CURSOR;
+	else if (primary_plane)
+		type = DRM_PLANE_TYPE_PRIMARY;
+	else
+		type = DRM_PLANE_TYPE_OVERLAY;
+	ret = drm_universal_plane_init(dev, plane, 0xff, &dpu_plane_funcs,
+				pdpu->formats, pdpu->nformats,
+				NULL, type, NULL);
+	if (ret)
+		goto clean_sspp;
+
+	pdpu->catalog = kms->catalog;
+
+	if (kms->catalog->mixer_count &&
+		kms->catalog->mixer[0].sblk->maxblendstages) {
+		zpos_max = kms->catalog->mixer[0].sblk->maxblendstages - 1;
+		if (zpos_max > DPU_STAGE_MAX - DPU_STAGE_0 - 1)
+			zpos_max = DPU_STAGE_MAX - DPU_STAGE_0 - 1;
+	}
+
+	ret = drm_plane_create_zpos_property(plane, 0, 0, zpos_max);
+	if (ret)
+		DPU_ERROR("failed to install zpos property, rc = %d\n", ret);
+
+	/* success! finalize initialization */
+	drm_plane_helper_add(plane, &dpu_plane_helper_funcs);
+
+	/* save user friendly pipe name for later */
+	snprintf(pdpu->pipe_name, DPU_NAME_SIZE, "plane%u", plane->base.id);
+
+	mutex_init(&pdpu->lock);
+
+	DPU_DEBUG("%s created for pipe:%u id:%u virtual:%u\n", pdpu->pipe_name,
+					pipe, plane->base.id, master_plane_id);
+	return plane;
+
+clean_sspp:
+	if (pdpu && pdpu->pipe_hw)
+		dpu_hw_sspp_destroy(pdpu->pipe_hw);
+clean_plane:
+	kfree(pdpu);
+exit:
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h
new file mode 100644
index 000000000000..f6fe6ddc7a3a
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h
@@ -0,0 +1,175 @@
+/*
+ * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _DPU_PLANE_H_
+#define _DPU_PLANE_H_
+
+#include <drm/drm_crtc.h>
+
+#include "dpu_kms.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_sspp.h"
+
+/**
+ * struct dpu_plane_state: Define dpu extension of drm plane state object
+ * @base:	base drm plane state object
+ * @property_state: Local storage for msm_prop properties
+ * @property_values:	cached plane property values
+ * @aspace:	pointer to address space for input/output buffers
+ * @input_fence:	dereferenced input fence pointer
+ * @stage:	assigned by crtc blender
+ * @multirect_index: index of the rectangle of SSPP
+ * @multirect_mode: parallel or time multiplex multirect mode
+ * @pending:	whether the current update is still pending
+ * @scaler3_cfg: configuration data for scaler3
+ * @pixel_ext: configuration data for pixel extensions
+ * @scaler_check_state: indicates status of user provided pixel extension data
+ * @cdp_cfg:	CDP configuration
+ */
+struct dpu_plane_state {
+	struct drm_plane_state base;
+	struct msm_gem_address_space *aspace;
+	void *input_fence;
+	enum dpu_stage stage;
+	uint32_t multirect_index;
+	uint32_t multirect_mode;
+	bool pending;
+
+	/* scaler configuration */
+	struct dpu_hw_scaler3_cfg scaler3_cfg;
+	struct dpu_hw_pixel_ext pixel_ext;
+
+	struct dpu_hw_pipe_cdp_cfg cdp_cfg;
+};
+
+/**
+ * struct dpu_multirect_plane_states: Defines multirect pair of drm plane states
+ * @r0: drm plane configured on rect 0
+ * @r1: drm plane configured on rect 1
+ */
+struct dpu_multirect_plane_states {
+	const struct drm_plane_state *r0;
+	const struct drm_plane_state *r1;
+};
+
+#define to_dpu_plane_state(x) \
+	container_of(x, struct dpu_plane_state, base)
+
+/**
+ * dpu_plane_pipe - return sspp identifier for the given plane
+ * @plane:   Pointer to DRM plane object
+ * Returns: sspp identifier of the given plane
+ */
+enum dpu_sspp dpu_plane_pipe(struct drm_plane *plane);
+
+/**
+ * is_dpu_plane_virtual - check for virtual plane
+ * @plane: Pointer to DRM plane object
+ * returns: true - if the plane is virtual
+ *          false - if the plane is primary
+ */
+bool is_dpu_plane_virtual(struct drm_plane *plane);
+
+/**
+ * dpu_plane_get_ctl_flush - get control flush mask
+ * @plane:   Pointer to DRM plane object
+ * @ctl: Pointer to control hardware
+ * @flush_sspp: Pointer to sspp flush control word
+ */
+void dpu_plane_get_ctl_flush(struct drm_plane *plane, struct dpu_hw_ctl *ctl,
+		u32 *flush_sspp);
+
+/**
+ * dpu_plane_restore - restore hw state if previously power collapsed
+ * @plane: Pointer to drm plane structure
+ */
+void dpu_plane_restore(struct drm_plane *plane);
+
+/**
+ * dpu_plane_flush - final plane operations before commit flush
+ * @plane: Pointer to drm plane structure
+ */
+void dpu_plane_flush(struct drm_plane *plane);
+
+/**
+ * dpu_plane_kickoff - final plane operations before commit kickoff
+ * @plane: Pointer to drm plane structure
+ */
+void dpu_plane_kickoff(struct drm_plane *plane);
+
+/**
+ * dpu_plane_set_error: enable/disable error condition
+ * @plane: pointer to drm_plane structure
+ */
+void dpu_plane_set_error(struct drm_plane *plane, bool error);
+
+/**
+ * dpu_plane_init - create new dpu plane for the given pipe
+ * @dev:   Pointer to DRM device
+ * @pipe:  dpu hardware pipe identifier
+ * @primary_plane: true if this pipe is primary plane for crtc
+ * @possible_crtcs: bitmask of crtc that can be attached to the given pipe
+ * @master_plane_id: primary plane id of a multirect pipe. 0 value passed for
+ *                   a regular plane initialization. A non-zero primary plane
+ *                   id will be passed for a virtual pipe initialization.
+ *
+ */
+struct drm_plane *dpu_plane_init(struct drm_device *dev,
+		uint32_t pipe, bool primary_plane,
+		unsigned long possible_crtcs, u32 master_plane_id);
+
+/**
+ * dpu_plane_validate_multirecti_v2 - validate the multirect planes
+ *				      against hw limitations
+ * @plane: drm plate states of the multirect pair
+ */
+int dpu_plane_validate_multirect_v2(struct dpu_multirect_plane_states *plane);
+
+/**
+ * dpu_plane_clear_multirect - clear multirect bits for the given pipe
+ * @drm_state: Pointer to DRM plane state
+ */
+void dpu_plane_clear_multirect(const struct drm_plane_state *drm_state);
+
+/**
+ * dpu_plane_wait_input_fence - wait for input fence object
+ * @plane:   Pointer to DRM plane object
+ * @wait_ms: Wait timeout value
+ * Returns: Zero on success
+ */
+int dpu_plane_wait_input_fence(struct drm_plane *plane, uint32_t wait_ms);
+
+/**
+ * dpu_plane_color_fill - enables color fill on plane
+ * @plane:  Pointer to DRM plane object
+ * @color:  RGB fill color value, [23..16] Blue, [15..8] Green, [7..0] Red
+ * @alpha:  8-bit fill alpha value, 255 selects 100% alpha
+ * Returns: 0 on success
+ */
+int dpu_plane_color_fill(struct drm_plane *plane,
+		uint32_t color, uint32_t alpha);
+
+/**
+ * dpu_plane_set_revalidate - sets revalidate flag which forces a full
+ *	validation of the plane properties in the next atomic check
+ * @plane: Pointer to DRM plane object
+ * @enable: Boolean to set/unset the flag
+ */
+void dpu_plane_set_revalidate(struct drm_plane *plane, bool enable);
+
+#endif /* _DPU_PLANE_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c
new file mode 100644
index 000000000000..a68f1249388c
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c
@@ -0,0 +1,249 @@
+/* Copyright (c) 2014-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d]: " fmt, __func__, __LINE__
+
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/string.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/of_platform.h>
+
+#include "dpu_power_handle.h"
+#include "dpu_trace.h"
+
+static const char *data_bus_name[DPU_POWER_HANDLE_DBUS_ID_MAX] = {
+	[DPU_POWER_HANDLE_DBUS_ID_MNOC] = "qcom,dpu-data-bus",
+	[DPU_POWER_HANDLE_DBUS_ID_LLCC] = "qcom,dpu-llcc-bus",
+	[DPU_POWER_HANDLE_DBUS_ID_EBI] = "qcom,dpu-ebi-bus",
+};
+
+const char *dpu_power_handle_get_dbus_name(u32 bus_id)
+{
+	if (bus_id < DPU_POWER_HANDLE_DBUS_ID_MAX)
+		return data_bus_name[bus_id];
+
+	return NULL;
+}
+
+static void dpu_power_event_trigger_locked(struct dpu_power_handle *phandle,
+		u32 event_type)
+{
+	struct dpu_power_event *event;
+
+	list_for_each_entry(event, &phandle->event_list, list) {
+		if (event->event_type & event_type)
+			event->cb_fnc(event_type, event->usr);
+	}
+}
+
+struct dpu_power_client *dpu_power_client_create(
+	struct dpu_power_handle *phandle, char *client_name)
+{
+	struct dpu_power_client *client;
+	static u32 id;
+
+	if (!client_name || !phandle) {
+		pr_err("client name is null or invalid power data\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	client = kzalloc(sizeof(struct dpu_power_client), GFP_KERNEL);
+	if (!client)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_lock(&phandle->phandle_lock);
+	strlcpy(client->name, client_name, MAX_CLIENT_NAME_LEN);
+	client->usecase_ndx = VOTE_INDEX_DISABLE;
+	client->id = id;
+	client->active = true;
+	pr_debug("client %s created:%pK id :%d\n", client_name,
+		client, id);
+	id++;
+	list_add(&client->list, &phandle->power_client_clist);
+	mutex_unlock(&phandle->phandle_lock);
+
+	return client;
+}
+
+void dpu_power_client_destroy(struct dpu_power_handle *phandle,
+	struct dpu_power_client *client)
+{
+	if (!client  || !phandle) {
+		pr_err("reg bus vote: invalid client handle\n");
+	} else if (!client->active) {
+		pr_err("dpu power deinit already done\n");
+		kfree(client);
+	} else {
+		pr_debug("bus vote client %s destroyed:%pK id:%u\n",
+			client->name, client, client->id);
+		mutex_lock(&phandle->phandle_lock);
+		list_del_init(&client->list);
+		mutex_unlock(&phandle->phandle_lock);
+		kfree(client);
+	}
+}
+
+void dpu_power_resource_init(struct platform_device *pdev,
+	struct dpu_power_handle *phandle)
+{
+	phandle->dev = &pdev->dev;
+
+	INIT_LIST_HEAD(&phandle->power_client_clist);
+	INIT_LIST_HEAD(&phandle->event_list);
+
+	mutex_init(&phandle->phandle_lock);
+}
+
+void dpu_power_resource_deinit(struct platform_device *pdev,
+	struct dpu_power_handle *phandle)
+{
+	struct dpu_power_client *curr_client, *next_client;
+	struct dpu_power_event *curr_event, *next_event;
+
+	if (!phandle || !pdev) {
+		pr_err("invalid input param\n");
+		return;
+	}
+
+	mutex_lock(&phandle->phandle_lock);
+	list_for_each_entry_safe(curr_client, next_client,
+			&phandle->power_client_clist, list) {
+		pr_err("cliend:%s-%d still registered with refcount:%d\n",
+				curr_client->name, curr_client->id,
+				curr_client->refcount);
+		curr_client->active = false;
+		list_del(&curr_client->list);
+	}
+
+	list_for_each_entry_safe(curr_event, next_event,
+			&phandle->event_list, list) {
+		pr_err("event:%d, client:%s still registered\n",
+				curr_event->event_type,
+				curr_event->client_name);
+		curr_event->active = false;
+		list_del(&curr_event->list);
+	}
+	mutex_unlock(&phandle->phandle_lock);
+}
+
+int dpu_power_resource_enable(struct dpu_power_handle *phandle,
+	struct dpu_power_client *pclient, bool enable)
+{
+	bool changed = false;
+	u32 max_usecase_ndx = VOTE_INDEX_DISABLE, prev_usecase_ndx;
+	struct dpu_power_client *client;
+
+	if (!phandle || !pclient) {
+		pr_err("invalid input argument\n");
+		return -EINVAL;
+	}
+
+	mutex_lock(&phandle->phandle_lock);
+	if (enable)
+		pclient->refcount++;
+	else if (pclient->refcount)
+		pclient->refcount--;
+
+	if (pclient->refcount)
+		pclient->usecase_ndx = VOTE_INDEX_LOW;
+	else
+		pclient->usecase_ndx = VOTE_INDEX_DISABLE;
+
+	list_for_each_entry(client, &phandle->power_client_clist, list) {
+		if (client->usecase_ndx < VOTE_INDEX_MAX &&
+		    client->usecase_ndx > max_usecase_ndx)
+			max_usecase_ndx = client->usecase_ndx;
+	}
+
+	if (phandle->current_usecase_ndx != max_usecase_ndx) {
+		changed = true;
+		prev_usecase_ndx = phandle->current_usecase_ndx;
+		phandle->current_usecase_ndx = max_usecase_ndx;
+	}
+
+	pr_debug("%pS: changed=%d current idx=%d request client %s id:%u enable:%d refcount:%d\n",
+		__builtin_return_address(0), changed, max_usecase_ndx,
+		pclient->name, pclient->id, enable, pclient->refcount);
+
+	if (!changed)
+		goto end;
+
+	if (enable) {
+		dpu_power_event_trigger_locked(phandle,
+				DPU_POWER_EVENT_PRE_ENABLE);
+		dpu_power_event_trigger_locked(phandle,
+				DPU_POWER_EVENT_POST_ENABLE);
+
+	} else {
+		dpu_power_event_trigger_locked(phandle,
+				DPU_POWER_EVENT_PRE_DISABLE);
+		dpu_power_event_trigger_locked(phandle,
+				DPU_POWER_EVENT_POST_DISABLE);
+	}
+
+end:
+	mutex_unlock(&phandle->phandle_lock);
+	return 0;
+}
+
+struct dpu_power_event *dpu_power_handle_register_event(
+		struct dpu_power_handle *phandle,
+		u32 event_type, void (*cb_fnc)(u32 event_type, void *usr),
+		void *usr, char *client_name)
+{
+	struct dpu_power_event *event;
+
+	if (!phandle) {
+		pr_err("invalid power handle\n");
+		return ERR_PTR(-EINVAL);
+	} else if (!cb_fnc || !event_type) {
+		pr_err("no callback fnc or event type\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	event = kzalloc(sizeof(struct dpu_power_event), GFP_KERNEL);
+	if (!event)
+		return ERR_PTR(-ENOMEM);
+
+	event->event_type = event_type;
+	event->cb_fnc = cb_fnc;
+	event->usr = usr;
+	strlcpy(event->client_name, client_name, MAX_CLIENT_NAME_LEN);
+	event->active = true;
+
+	mutex_lock(&phandle->phandle_lock);
+	list_add(&event->list, &phandle->event_list);
+	mutex_unlock(&phandle->phandle_lock);
+
+	return event;
+}
+
+void dpu_power_handle_unregister_event(
+		struct dpu_power_handle *phandle,
+		struct dpu_power_event *event)
+{
+	if (!phandle || !event) {
+		pr_err("invalid phandle or event\n");
+	} else if (!event->active) {
+		pr_err("power handle deinit already done\n");
+		kfree(event);
+	} else {
+		mutex_lock(&phandle->phandle_lock);
+		list_del_init(&event->list);
+		mutex_unlock(&phandle->phandle_lock);
+		kfree(event);
+	}
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.h
new file mode 100644
index 000000000000..344f74464eca
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.h
@@ -0,0 +1,225 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _DPU_POWER_HANDLE_H_
+#define _DPU_POWER_HANDLE_H_
+
+#define MAX_CLIENT_NAME_LEN 128
+
+#define DPU_POWER_HANDLE_ENABLE_BUS_AB_QUOTA	0
+#define DPU_POWER_HANDLE_DISABLE_BUS_AB_QUOTA	0
+#define DPU_POWER_HANDLE_ENABLE_BUS_IB_QUOTA	1600000000
+#define DPU_POWER_HANDLE_DISABLE_BUS_IB_QUOTA	0
+
+#include "dpu_io_util.h"
+
+/* event will be triggered before power handler disable */
+#define DPU_POWER_EVENT_PRE_DISABLE	0x1
+
+/* event will be triggered after power handler disable */
+#define DPU_POWER_EVENT_POST_DISABLE	0x2
+
+/* event will be triggered before power handler enable */
+#define DPU_POWER_EVENT_PRE_ENABLE	0x4
+
+/* event will be triggered after power handler enable */
+#define DPU_POWER_EVENT_POST_ENABLE	0x8
+
+/**
+ * mdss_bus_vote_type: register bus vote type
+ * VOTE_INDEX_DISABLE: removes the client vote
+ * VOTE_INDEX_LOW: keeps the lowest vote for register bus
+ * VOTE_INDEX_MAX: invalid
+ */
+enum mdss_bus_vote_type {
+	VOTE_INDEX_DISABLE,
+	VOTE_INDEX_LOW,
+	VOTE_INDEX_MAX,
+};
+
+/**
+ * enum dpu_power_handle_data_bus_client - type of axi bus clients
+ * @DPU_POWER_HANDLE_DATA_BUS_CLIENT_RT: core real-time bus client
+ * @DPU_POWER_HANDLE_DATA_BUS_CLIENT_NRT: core non-real-time bus client
+ * @DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX: maximum number of bus client type
+ */
+enum dpu_power_handle_data_bus_client {
+	DPU_POWER_HANDLE_DATA_BUS_CLIENT_RT,
+	DPU_POWER_HANDLE_DATA_BUS_CLIENT_NRT,
+	DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX
+};
+
+/**
+ * enum DPU_POWER_HANDLE_DBUS_ID - data bus identifier
+ * @DPU_POWER_HANDLE_DBUS_ID_MNOC: DPU/MNOC data bus
+ * @DPU_POWER_HANDLE_DBUS_ID_LLCC: MNOC/LLCC data bus
+ * @DPU_POWER_HANDLE_DBUS_ID_EBI: LLCC/EBI data bus
+ */
+enum DPU_POWER_HANDLE_DBUS_ID {
+	DPU_POWER_HANDLE_DBUS_ID_MNOC,
+	DPU_POWER_HANDLE_DBUS_ID_LLCC,
+	DPU_POWER_HANDLE_DBUS_ID_EBI,
+	DPU_POWER_HANDLE_DBUS_ID_MAX,
+};
+
+/**
+ * struct dpu_power_client: stores the power client for dpu driver
+ * @name:	name of the client
+ * @usecase_ndx: current regs bus vote type
+ * @refcount:	current refcount if multiple modules are using same
+ *              same client for enable/disable. Power module will
+ *              aggregate the refcount and vote accordingly for this
+ *              client.
+ * @id:		assigned during create. helps for debugging.
+ * @list:	list to attach power handle master list
+ * @ab:         arbitrated bandwidth for each bus client
+ * @ib:         instantaneous bandwidth for each bus client
+ * @active:	inidcates the state of dpu power handle
+ */
+struct dpu_power_client {
+	char name[MAX_CLIENT_NAME_LEN];
+	short usecase_ndx;
+	short refcount;
+	u32 id;
+	struct list_head list;
+	u64 ab[DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX];
+	u64 ib[DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX];
+	bool active;
+};
+
+/*
+ * struct dpu_power_event - local event registration structure
+ * @client_name: name of the client registering
+ * @cb_fnc: pointer to desired callback function
+ * @usr: user pointer to pass to callback event trigger
+ * @event: refer to DPU_POWER_HANDLE_EVENT_*
+ * @list: list to attach event master list
+ * @active: indicates the state of dpu power handle
+ */
+struct dpu_power_event {
+	char client_name[MAX_CLIENT_NAME_LEN];
+	void (*cb_fnc)(u32 event_type, void *usr);
+	void *usr;
+	u32 event_type;
+	struct list_head list;
+	bool active;
+};
+
+/**
+ * struct dpu_power_handle: power handle main struct
+ * @client_clist: master list to store all clients
+ * @phandle_lock: lock to synchronize the enable/disable
+ * @dev: pointer to device structure
+ * @usecase_ndx: current usecase index
+ * @event_list: current power handle event list
+ */
+struct dpu_power_handle {
+	struct list_head power_client_clist;
+	struct mutex phandle_lock;
+	struct device *dev;
+	u32 current_usecase_ndx;
+	struct list_head event_list;
+};
+
+/**
+ * dpu_power_resource_init() - initializes the dpu power handle
+ * @pdev:   platform device to search the power resources
+ * @pdata:  power handle to store the power resources
+ */
+void dpu_power_resource_init(struct platform_device *pdev,
+	struct dpu_power_handle *pdata);
+
+/**
+ * dpu_power_resource_deinit() - release the dpu power handle
+ * @pdev:   platform device for power resources
+ * @pdata:  power handle containing the resources
+ *
+ * Return: error code.
+ */
+void dpu_power_resource_deinit(struct platform_device *pdev,
+	struct dpu_power_handle *pdata);
+
+/**
+ * dpu_power_client_create() - create the client on power handle
+ * @pdata:  power handle containing the resources
+ * @client_name: new client name for registration
+ *
+ * Return: error code.
+ */
+struct dpu_power_client *dpu_power_client_create(struct dpu_power_handle *pdata,
+	char *client_name);
+
+/**
+ * dpu_power_client_destroy() - destroy the client on power handle
+ * @pdata:  power handle containing the resources
+ * @client_name: new client name for registration
+ *
+ * Return: none
+ */
+void dpu_power_client_destroy(struct dpu_power_handle *phandle,
+	struct dpu_power_client *client);
+
+/**
+ * dpu_power_resource_enable() - enable/disable the power resources
+ * @pdata:  power handle containing the resources
+ * @client: client information to enable/disable its vote
+ * @enable: boolean request for enable/disable
+ *
+ * Return: error code.
+ */
+int dpu_power_resource_enable(struct dpu_power_handle *pdata,
+	struct dpu_power_client *pclient, bool enable);
+
+/**
+ * dpu_power_data_bus_bandwidth_ctrl() - control data bus bandwidth enable
+ * @phandle:  power handle containing the resources
+ * @client: client information to bandwidth control
+ * @enable: true to enable bandwidth for data base
+ *
+ * Return: none
+ */
+void dpu_power_data_bus_bandwidth_ctrl(struct dpu_power_handle *phandle,
+		struct dpu_power_client *pclient, int enable);
+
+/**
+ * dpu_power_handle_register_event - register a callback function for an event.
+ *	Clients can register for multiple events with a single register.
+ *	Any block with access to phandle can register for the event
+ *	notification.
+ * @phandle:	power handle containing the resources
+ * @event_type:	event type to register; refer DPU_POWER_HANDLE_EVENT_*
+ * @cb_fnc:	pointer to desired callback function
+ * @usr:	user pointer to pass to callback on event trigger
+ *
+ * Return:	event pointer if success, or error code otherwise
+ */
+struct dpu_power_event *dpu_power_handle_register_event(
+		struct dpu_power_handle *phandle,
+		u32 event_type, void (*cb_fnc)(u32 event_type, void *usr),
+		void *usr, char *client_name);
+/**
+ * dpu_power_handle_unregister_event - unregister callback for event(s)
+ * @phandle:	power handle containing the resources
+ * @event:	event pointer returned after power handle register
+ */
+void dpu_power_handle_unregister_event(struct dpu_power_handle *phandle,
+		struct dpu_power_event *event);
+
+/**
+ * dpu_power_handle_get_dbus_name - get name of given data bus identifier
+ * @bus_id:	data bus identifier
+ * Return:	Pointer to name string if success; NULL otherwise
+ */
+const char *dpu_power_handle_get_dbus_name(u32 bus_id);
+
+#endif /* _DPU_POWER_HANDLE_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
new file mode 100644
index 000000000000..13c0a36d4ef9
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
@@ -0,0 +1,1079 @@
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt)	"[drm:%s] " fmt, __func__
+#include "dpu_kms.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_hw_cdm.h"
+#include "dpu_hw_pingpong.h"
+#include "dpu_hw_intf.h"
+#include "dpu_encoder.h"
+#include "dpu_trace.h"
+
+#define RESERVED_BY_OTHER(h, r) \
+	((h)->rsvp && ((h)->rsvp->enc_id != (r)->enc_id))
+
+#define RM_RQ_LOCK(r) ((r)->top_ctrl & BIT(DPU_RM_TOPCTL_RESERVE_LOCK))
+#define RM_RQ_CLEAR(r) ((r)->top_ctrl & BIT(DPU_RM_TOPCTL_RESERVE_CLEAR))
+#define RM_RQ_DS(r) ((r)->top_ctrl & BIT(DPU_RM_TOPCTL_DS))
+#define RM_IS_TOPOLOGY_MATCH(t, r) ((t).num_lm == (r).num_lm && \
+				(t).num_comp_enc == (r).num_enc && \
+				(t).num_intf == (r).num_intf)
+
+struct dpu_rm_topology_def {
+	enum dpu_rm_topology_name top_name;
+	int num_lm;
+	int num_comp_enc;
+	int num_intf;
+	int num_ctl;
+	int needs_split_display;
+};
+
+static const struct dpu_rm_topology_def g_top_table[] = {
+	{   DPU_RM_TOPOLOGY_NONE,                 0, 0, 0, 0, false },
+	{   DPU_RM_TOPOLOGY_SINGLEPIPE,           1, 0, 1, 1, false },
+	{   DPU_RM_TOPOLOGY_DUALPIPE,             2, 0, 2, 2, true  },
+	{   DPU_RM_TOPOLOGY_DUALPIPE_3DMERGE,     2, 0, 1, 1, false },
+};
+
+/**
+ * struct dpu_rm_requirements - Reservation requirements parameter bundle
+ * @top_ctrl:  topology control preference from kernel client
+ * @top:       selected topology for the display
+ * @hw_res:	   Hardware resources required as reported by the encoders
+ */
+struct dpu_rm_requirements {
+	uint64_t top_ctrl;
+	const struct dpu_rm_topology_def *topology;
+	struct dpu_encoder_hw_resources hw_res;
+};
+
+/**
+ * struct dpu_rm_rsvp - Use Case Reservation tagging structure
+ *	Used to tag HW blocks as reserved by a CRTC->Encoder->Connector chain
+ *	By using as a tag, rather than lists of pointers to HW blocks used
+ *	we can avoid some list management since we don't know how many blocks
+ *	of each type a given use case may require.
+ * @list:	List head for list of all reservations
+ * @seq:	Global RSVP sequence number for debugging, especially for
+ *		differentiating differenct allocations for same encoder.
+ * @enc_id:	Reservations are tracked by Encoder DRM object ID.
+ *		CRTCs may be connected to multiple Encoders.
+ *		An encoder or connector id identifies the display path.
+ * @topology	DRM<->HW topology use case
+ */
+struct dpu_rm_rsvp {
+	struct list_head list;
+	uint32_t seq;
+	uint32_t enc_id;
+	enum dpu_rm_topology_name topology;
+};
+
+/**
+ * struct dpu_rm_hw_blk - hardware block tracking list member
+ * @list:	List head for list of all hardware blocks tracking items
+ * @rsvp:	Pointer to use case reservation if reserved by a client
+ * @rsvp_nxt:	Temporary pointer used during reservation to the incoming
+ *		request. Will be swapped into rsvp if proposal is accepted
+ * @type:	Type of hardware block this structure tracks
+ * @id:		Hardware ID number, within it's own space, ie. LM_X
+ * @catalog:	Pointer to the hardware catalog entry for this block
+ * @hw:		Pointer to the hardware register access object for this block
+ */
+struct dpu_rm_hw_blk {
+	struct list_head list;
+	struct dpu_rm_rsvp *rsvp;
+	struct dpu_rm_rsvp *rsvp_nxt;
+	enum dpu_hw_blk_type type;
+	uint32_t id;
+	struct dpu_hw_blk *hw;
+};
+
+/**
+ * dpu_rm_dbg_rsvp_stage - enum of steps in making reservation for event logging
+ */
+enum dpu_rm_dbg_rsvp_stage {
+	DPU_RM_STAGE_BEGIN,
+	DPU_RM_STAGE_AFTER_CLEAR,
+	DPU_RM_STAGE_AFTER_RSVPNEXT,
+	DPU_RM_STAGE_FINAL
+};
+
+static void _dpu_rm_print_rsvps(
+		struct dpu_rm *rm,
+		enum dpu_rm_dbg_rsvp_stage stage)
+{
+	struct dpu_rm_rsvp *rsvp;
+	struct dpu_rm_hw_blk *blk;
+	enum dpu_hw_blk_type type;
+
+	DPU_DEBUG("%d\n", stage);
+
+	list_for_each_entry(rsvp, &rm->rsvps, list) {
+		DRM_DEBUG_KMS("%d rsvp[s%ue%u] topology %d\n", stage, rsvp->seq,
+			      rsvp->enc_id, rsvp->topology);
+	}
+
+	for (type = 0; type < DPU_HW_BLK_MAX; type++) {
+		list_for_each_entry(blk, &rm->hw_blks[type], list) {
+			if (!blk->rsvp && !blk->rsvp_nxt)
+				continue;
+
+			DRM_DEBUG_KMS("%d rsvp[s%ue%u->s%ue%u] %d %d\n", stage,
+				(blk->rsvp) ? blk->rsvp->seq : 0,
+				(blk->rsvp) ? blk->rsvp->enc_id : 0,
+				(blk->rsvp_nxt) ? blk->rsvp_nxt->seq : 0,
+				(blk->rsvp_nxt) ? blk->rsvp_nxt->enc_id : 0,
+				blk->type, blk->id);
+		}
+	}
+}
+
+struct dpu_hw_mdp *dpu_rm_get_mdp(struct dpu_rm *rm)
+{
+	return rm->hw_mdp;
+}
+
+enum dpu_rm_topology_name
+dpu_rm_get_topology_name(struct msm_display_topology topology)
+{
+	int i;
+
+	for (i = 0; i < DPU_RM_TOPOLOGY_MAX; i++)
+		if (RM_IS_TOPOLOGY_MATCH(g_top_table[i], topology))
+			return g_top_table[i].top_name;
+
+	return DPU_RM_TOPOLOGY_NONE;
+}
+
+void dpu_rm_init_hw_iter(
+		struct dpu_rm_hw_iter *iter,
+		uint32_t enc_id,
+		enum dpu_hw_blk_type type)
+{
+	memset(iter, 0, sizeof(*iter));
+	iter->enc_id = enc_id;
+	iter->type = type;
+}
+
+static bool _dpu_rm_get_hw_locked(struct dpu_rm *rm, struct dpu_rm_hw_iter *i)
+{
+	struct list_head *blk_list;
+
+	if (!rm || !i || i->type >= DPU_HW_BLK_MAX) {
+		DPU_ERROR("invalid rm\n");
+		return false;
+	}
+
+	i->hw = NULL;
+	blk_list = &rm->hw_blks[i->type];
+
+	if (i->blk && (&i->blk->list == blk_list)) {
+		DPU_DEBUG("attempt resume iteration past last\n");
+		return false;
+	}
+
+	i->blk = list_prepare_entry(i->blk, blk_list, list);
+
+	list_for_each_entry_continue(i->blk, blk_list, list) {
+		struct dpu_rm_rsvp *rsvp = i->blk->rsvp;
+
+		if (i->blk->type != i->type) {
+			DPU_ERROR("found incorrect block type %d on %d list\n",
+					i->blk->type, i->type);
+			return false;
+		}
+
+		if ((i->enc_id == 0) || (rsvp && rsvp->enc_id == i->enc_id)) {
+			i->hw = i->blk->hw;
+			DPU_DEBUG("found type %d id %d for enc %d\n",
+					i->type, i->blk->id, i->enc_id);
+			return true;
+		}
+	}
+
+	DPU_DEBUG("no match, type %d for enc %d\n", i->type, i->enc_id);
+
+	return false;
+}
+
+bool dpu_rm_get_hw(struct dpu_rm *rm, struct dpu_rm_hw_iter *i)
+{
+	bool ret;
+
+	mutex_lock(&rm->rm_lock);
+	ret = _dpu_rm_get_hw_locked(rm, i);
+	mutex_unlock(&rm->rm_lock);
+
+	return ret;
+}
+
+static void _dpu_rm_hw_destroy(enum dpu_hw_blk_type type, void *hw)
+{
+	switch (type) {
+	case DPU_HW_BLK_LM:
+		dpu_hw_lm_destroy(hw);
+		break;
+	case DPU_HW_BLK_CTL:
+		dpu_hw_ctl_destroy(hw);
+		break;
+	case DPU_HW_BLK_CDM:
+		dpu_hw_cdm_destroy(hw);
+		break;
+	case DPU_HW_BLK_PINGPONG:
+		dpu_hw_pingpong_destroy(hw);
+		break;
+	case DPU_HW_BLK_INTF:
+		dpu_hw_intf_destroy(hw);
+		break;
+	case DPU_HW_BLK_SSPP:
+		/* SSPPs are not managed by the resource manager */
+	case DPU_HW_BLK_TOP:
+		/* Top is a singleton, not managed in hw_blks list */
+	case DPU_HW_BLK_MAX:
+	default:
+		DPU_ERROR("unsupported block type %d\n", type);
+		break;
+	}
+}
+
+int dpu_rm_destroy(struct dpu_rm *rm)
+{
+
+	struct dpu_rm_rsvp *rsvp_cur, *rsvp_nxt;
+	struct dpu_rm_hw_blk *hw_cur, *hw_nxt;
+	enum dpu_hw_blk_type type;
+
+	if (!rm) {
+		DPU_ERROR("invalid rm\n");
+		return -EINVAL;
+	}
+
+	list_for_each_entry_safe(rsvp_cur, rsvp_nxt, &rm->rsvps, list) {
+		list_del(&rsvp_cur->list);
+		kfree(rsvp_cur);
+	}
+
+
+	for (type = 0; type < DPU_HW_BLK_MAX; type++) {
+		list_for_each_entry_safe(hw_cur, hw_nxt, &rm->hw_blks[type],
+				list) {
+			list_del(&hw_cur->list);
+			_dpu_rm_hw_destroy(hw_cur->type, hw_cur->hw);
+			kfree(hw_cur);
+		}
+	}
+
+	dpu_hw_mdp_destroy(rm->hw_mdp);
+	rm->hw_mdp = NULL;
+
+	mutex_destroy(&rm->rm_lock);
+
+	return 0;
+}
+
+static int _dpu_rm_hw_blk_create(
+		struct dpu_rm *rm,
+		struct dpu_mdss_cfg *cat,
+		void __iomem *mmio,
+		enum dpu_hw_blk_type type,
+		uint32_t id,
+		void *hw_catalog_info)
+{
+	struct dpu_rm_hw_blk *blk;
+	struct dpu_hw_mdp *hw_mdp;
+	void *hw;
+
+	hw_mdp = rm->hw_mdp;
+
+	switch (type) {
+	case DPU_HW_BLK_LM:
+		hw = dpu_hw_lm_init(id, mmio, cat);
+		break;
+	case DPU_HW_BLK_CTL:
+		hw = dpu_hw_ctl_init(id, mmio, cat);
+		break;
+	case DPU_HW_BLK_CDM:
+		hw = dpu_hw_cdm_init(id, mmio, cat, hw_mdp);
+		break;
+	case DPU_HW_BLK_PINGPONG:
+		hw = dpu_hw_pingpong_init(id, mmio, cat);
+		break;
+	case DPU_HW_BLK_INTF:
+		hw = dpu_hw_intf_init(id, mmio, cat);
+		break;
+	case DPU_HW_BLK_SSPP:
+		/* SSPPs are not managed by the resource manager */
+	case DPU_HW_BLK_TOP:
+		/* Top is a singleton, not managed in hw_blks list */
+	case DPU_HW_BLK_MAX:
+	default:
+		DPU_ERROR("unsupported block type %d\n", type);
+		return -EINVAL;
+	}
+
+	if (IS_ERR_OR_NULL(hw)) {
+		DPU_ERROR("failed hw object creation: type %d, err %ld\n",
+				type, PTR_ERR(hw));
+		return -EFAULT;
+	}
+
+	blk = kzalloc(sizeof(*blk), GFP_KERNEL);
+	if (!blk) {
+		_dpu_rm_hw_destroy(type, hw);
+		return -ENOMEM;
+	}
+
+	blk->type = type;
+	blk->id = id;
+	blk->hw = hw;
+	list_add_tail(&blk->list, &rm->hw_blks[type]);
+
+	return 0;
+}
+
+int dpu_rm_init(struct dpu_rm *rm,
+		struct dpu_mdss_cfg *cat,
+		void __iomem *mmio,
+		struct drm_device *dev)
+{
+	int rc, i;
+	enum dpu_hw_blk_type type;
+
+	if (!rm || !cat || !mmio || !dev) {
+		DPU_ERROR("invalid kms\n");
+		return -EINVAL;
+	}
+
+	/* Clear, setup lists */
+	memset(rm, 0, sizeof(*rm));
+
+	mutex_init(&rm->rm_lock);
+
+	INIT_LIST_HEAD(&rm->rsvps);
+	for (type = 0; type < DPU_HW_BLK_MAX; type++)
+		INIT_LIST_HEAD(&rm->hw_blks[type]);
+
+	rm->dev = dev;
+
+	/* Some of the sub-blocks require an mdptop to be created */
+	rm->hw_mdp = dpu_hw_mdptop_init(MDP_TOP, mmio, cat);
+	if (IS_ERR_OR_NULL(rm->hw_mdp)) {
+		rc = PTR_ERR(rm->hw_mdp);
+		rm->hw_mdp = NULL;
+		DPU_ERROR("failed: mdp hw not available\n");
+		goto fail;
+	}
+
+	/* Interrogate HW catalog and create tracking items for hw blocks */
+	for (i = 0; i < cat->mixer_count; i++) {
+		struct dpu_lm_cfg *lm = &cat->mixer[i];
+
+		if (lm->pingpong == PINGPONG_MAX) {
+			DPU_DEBUG("skip mixer %d without pingpong\n", lm->id);
+			continue;
+		}
+
+		rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_LM,
+				cat->mixer[i].id, &cat->mixer[i]);
+		if (rc) {
+			DPU_ERROR("failed: lm hw not available\n");
+			goto fail;
+		}
+
+		if (!rm->lm_max_width) {
+			rm->lm_max_width = lm->sblk->maxwidth;
+		} else if (rm->lm_max_width != lm->sblk->maxwidth) {
+			/*
+			 * Don't expect to have hw where lm max widths differ.
+			 * If found, take the min.
+			 */
+			DPU_ERROR("unsupported: lm maxwidth differs\n");
+			if (rm->lm_max_width > lm->sblk->maxwidth)
+				rm->lm_max_width = lm->sblk->maxwidth;
+		}
+	}
+
+	for (i = 0; i < cat->pingpong_count; i++) {
+		rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_PINGPONG,
+				cat->pingpong[i].id, &cat->pingpong[i]);
+		if (rc) {
+			DPU_ERROR("failed: pp hw not available\n");
+			goto fail;
+		}
+	}
+
+	for (i = 0; i < cat->intf_count; i++) {
+		if (cat->intf[i].type == INTF_NONE) {
+			DPU_DEBUG("skip intf %d with type none\n", i);
+			continue;
+		}
+
+		rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_INTF,
+				cat->intf[i].id, &cat->intf[i]);
+		if (rc) {
+			DPU_ERROR("failed: intf hw not available\n");
+			goto fail;
+		}
+	}
+
+	for (i = 0; i < cat->ctl_count; i++) {
+		rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_CTL,
+				cat->ctl[i].id, &cat->ctl[i]);
+		if (rc) {
+			DPU_ERROR("failed: ctl hw not available\n");
+			goto fail;
+		}
+	}
+
+	for (i = 0; i < cat->cdm_count; i++) {
+		rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_CDM,
+				cat->cdm[i].id, &cat->cdm[i]);
+		if (rc) {
+			DPU_ERROR("failed: cdm hw not available\n");
+			goto fail;
+		}
+	}
+
+	return 0;
+
+fail:
+	dpu_rm_destroy(rm);
+
+	return rc;
+}
+
+/**
+ * _dpu_rm_check_lm_and_get_connected_blks - check if proposed layer mixer meets
+ *	proposed use case requirements, incl. hardwired dependent blocks like
+ *	pingpong
+ * @rm: dpu resource manager handle
+ * @rsvp: reservation currently being created
+ * @reqs: proposed use case requirements
+ * @lm: proposed layer mixer, function checks if lm, and all other hardwired
+ *      blocks connected to the lm (pp) is available and appropriate
+ * @pp: output parameter, pingpong block attached to the layer mixer.
+ *      NULL if pp was not available, or not matching requirements.
+ * @primary_lm: if non-null, this function check if lm is compatible primary_lm
+ *              as well as satisfying all other requirements
+ * @Return: true if lm matches all requirements, false otherwise
+ */
+static bool _dpu_rm_check_lm_and_get_connected_blks(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		struct dpu_rm_requirements *reqs,
+		struct dpu_rm_hw_blk *lm,
+		struct dpu_rm_hw_blk **pp,
+		struct dpu_rm_hw_blk *primary_lm)
+{
+	const struct dpu_lm_cfg *lm_cfg = to_dpu_hw_mixer(lm->hw)->cap;
+	struct dpu_rm_hw_iter iter;
+
+	*pp = NULL;
+
+	DPU_DEBUG("check lm %d pp %d\n",
+			   lm_cfg->id, lm_cfg->pingpong);
+
+	/* Check if this layer mixer is a peer of the proposed primary LM */
+	if (primary_lm) {
+		const struct dpu_lm_cfg *prim_lm_cfg =
+				to_dpu_hw_mixer(primary_lm->hw)->cap;
+
+		if (!test_bit(lm_cfg->id, &prim_lm_cfg->lm_pair_mask)) {
+			DPU_DEBUG("lm %d not peer of lm %d\n", lm_cfg->id,
+					prim_lm_cfg->id);
+			return false;
+		}
+	}
+
+	/* Already reserved? */
+	if (RESERVED_BY_OTHER(lm, rsvp)) {
+		DPU_DEBUG("lm %d already reserved\n", lm_cfg->id);
+		return false;
+	}
+
+	dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_PINGPONG);
+	while (_dpu_rm_get_hw_locked(rm, &iter)) {
+		if (iter.blk->id == lm_cfg->pingpong) {
+			*pp = iter.blk;
+			break;
+		}
+	}
+
+	if (!*pp) {
+		DPU_ERROR("failed to get pp on lm %d\n", lm_cfg->pingpong);
+		return false;
+	}
+
+	if (RESERVED_BY_OTHER(*pp, rsvp)) {
+		DPU_DEBUG("lm %d pp %d already reserved\n", lm->id,
+				(*pp)->id);
+		return false;
+	}
+
+	return true;
+}
+
+static int _dpu_rm_reserve_lms(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		struct dpu_rm_requirements *reqs)
+
+{
+	struct dpu_rm_hw_blk *lm[MAX_BLOCKS];
+	struct dpu_rm_hw_blk *pp[MAX_BLOCKS];
+	struct dpu_rm_hw_iter iter_i, iter_j;
+	int lm_count = 0;
+	int i, rc = 0;
+
+	if (!reqs->topology->num_lm) {
+		DPU_ERROR("invalid number of lm: %d\n", reqs->topology->num_lm);
+		return -EINVAL;
+	}
+
+	/* Find a primary mixer */
+	dpu_rm_init_hw_iter(&iter_i, 0, DPU_HW_BLK_LM);
+	while (lm_count != reqs->topology->num_lm &&
+			_dpu_rm_get_hw_locked(rm, &iter_i)) {
+		memset(&lm, 0, sizeof(lm));
+		memset(&pp, 0, sizeof(pp));
+
+		lm_count = 0;
+		lm[lm_count] = iter_i.blk;
+
+		if (!_dpu_rm_check_lm_and_get_connected_blks(
+				rm, rsvp, reqs, lm[lm_count],
+				&pp[lm_count], NULL))
+			continue;
+
+		++lm_count;
+
+		/* Valid primary mixer found, find matching peers */
+		dpu_rm_init_hw_iter(&iter_j, 0, DPU_HW_BLK_LM);
+
+		while (lm_count != reqs->topology->num_lm &&
+				_dpu_rm_get_hw_locked(rm, &iter_j)) {
+			if (iter_i.blk == iter_j.blk)
+				continue;
+
+			if (!_dpu_rm_check_lm_and_get_connected_blks(
+					rm, rsvp, reqs, iter_j.blk,
+					&pp[lm_count], iter_i.blk))
+				continue;
+
+			lm[lm_count] = iter_j.blk;
+			++lm_count;
+		}
+	}
+
+	if (lm_count != reqs->topology->num_lm) {
+		DPU_DEBUG("unable to find appropriate mixers\n");
+		return -ENAVAIL;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(lm); i++) {
+		if (!lm[i])
+			break;
+
+		lm[i]->rsvp_nxt = rsvp;
+		pp[i]->rsvp_nxt = rsvp;
+
+		trace_dpu_rm_reserve_lms(lm[i]->id, lm[i]->type, rsvp->enc_id,
+					 pp[i]->id);
+	}
+
+	return rc;
+}
+
+static int _dpu_rm_reserve_ctls(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		const struct dpu_rm_topology_def *top)
+{
+	struct dpu_rm_hw_blk *ctls[MAX_BLOCKS];
+	struct dpu_rm_hw_iter iter;
+	int i = 0;
+
+	memset(&ctls, 0, sizeof(ctls));
+
+	dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_CTL);
+	while (_dpu_rm_get_hw_locked(rm, &iter)) {
+		const struct dpu_hw_ctl *ctl = to_dpu_hw_ctl(iter.blk->hw);
+		unsigned long features = ctl->caps->features;
+		bool has_split_display;
+
+		if (RESERVED_BY_OTHER(iter.blk, rsvp))
+			continue;
+
+		has_split_display = BIT(DPU_CTL_SPLIT_DISPLAY) & features;
+
+		DPU_DEBUG("ctl %d caps 0x%lX\n", iter.blk->id, features);
+
+		if (top->needs_split_display != has_split_display)
+			continue;
+
+		ctls[i] = iter.blk;
+		DPU_DEBUG("ctl %d match\n", iter.blk->id);
+
+		if (++i == top->num_ctl)
+			break;
+	}
+
+	if (i != top->num_ctl)
+		return -ENAVAIL;
+
+	for (i = 0; i < ARRAY_SIZE(ctls) && i < top->num_ctl; i++) {
+		ctls[i]->rsvp_nxt = rsvp;
+		trace_dpu_rm_reserve_ctls(ctls[i]->id, ctls[i]->type,
+					  rsvp->enc_id);
+	}
+
+	return 0;
+}
+
+static int _dpu_rm_reserve_cdm(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		uint32_t id,
+		enum dpu_hw_blk_type type)
+{
+	struct dpu_rm_hw_iter iter;
+
+	DRM_DEBUG_KMS("type %d id %d\n", type, id);
+
+	dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_CDM);
+	while (_dpu_rm_get_hw_locked(rm, &iter)) {
+		const struct dpu_hw_cdm *cdm = to_dpu_hw_cdm(iter.blk->hw);
+		const struct dpu_cdm_cfg *caps = cdm->caps;
+		bool match = false;
+
+		if (RESERVED_BY_OTHER(iter.blk, rsvp))
+			continue;
+
+		if (type == DPU_HW_BLK_INTF && id != INTF_MAX)
+			match = test_bit(id, &caps->intf_connect);
+
+		DRM_DEBUG_KMS("iter: type:%d id:%d enc:%d cdm:%lu match:%d\n",
+			      iter.blk->type, iter.blk->id, rsvp->enc_id,
+			      caps->intf_connect, match);
+
+		if (!match)
+			continue;
+
+		trace_dpu_rm_reserve_cdm(iter.blk->id, iter.blk->type,
+					 rsvp->enc_id);
+		iter.blk->rsvp_nxt = rsvp;
+		break;
+	}
+
+	if (!iter.hw) {
+		DPU_ERROR("couldn't reserve cdm for type %d id %d\n", type, id);
+		return -ENAVAIL;
+	}
+
+	return 0;
+}
+
+static int _dpu_rm_reserve_intf(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		uint32_t id,
+		enum dpu_hw_blk_type type,
+		bool needs_cdm)
+{
+	struct dpu_rm_hw_iter iter;
+	int ret = 0;
+
+	/* Find the block entry in the rm, and note the reservation */
+	dpu_rm_init_hw_iter(&iter, 0, type);
+	while (_dpu_rm_get_hw_locked(rm, &iter)) {
+		if (iter.blk->id != id)
+			continue;
+
+		if (RESERVED_BY_OTHER(iter.blk, rsvp)) {
+			DPU_ERROR("type %d id %d already reserved\n", type, id);
+			return -ENAVAIL;
+		}
+
+		iter.blk->rsvp_nxt = rsvp;
+		trace_dpu_rm_reserve_intf(iter.blk->id, iter.blk->type,
+					  rsvp->enc_id);
+		break;
+	}
+
+	/* Shouldn't happen since intfs are fixed at probe */
+	if (!iter.hw) {
+		DPU_ERROR("couldn't find type %d id %d\n", type, id);
+		return -EINVAL;
+	}
+
+	if (needs_cdm)
+		ret = _dpu_rm_reserve_cdm(rm, rsvp, id, type);
+
+	return ret;
+}
+
+static int _dpu_rm_reserve_intf_related_hw(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		struct dpu_encoder_hw_resources *hw_res)
+{
+	int i, ret = 0;
+	u32 id;
+
+	for (i = 0; i < ARRAY_SIZE(hw_res->intfs); i++) {
+		if (hw_res->intfs[i] == INTF_MODE_NONE)
+			continue;
+		id = i + INTF_0;
+		ret = _dpu_rm_reserve_intf(rm, rsvp, id,
+				DPU_HW_BLK_INTF, hw_res->needs_cdm);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+static int _dpu_rm_make_next_rsvp(
+		struct dpu_rm *rm,
+		struct drm_encoder *enc,
+		struct drm_crtc_state *crtc_state,
+		struct drm_connector_state *conn_state,
+		struct dpu_rm_rsvp *rsvp,
+		struct dpu_rm_requirements *reqs)
+{
+	int ret;
+	struct dpu_rm_topology_def topology;
+
+	/* Create reservation info, tag reserved blocks with it as we go */
+	rsvp->seq = ++rm->rsvp_next_seq;
+	rsvp->enc_id = enc->base.id;
+	rsvp->topology = reqs->topology->top_name;
+	list_add_tail(&rsvp->list, &rm->rsvps);
+
+	ret = _dpu_rm_reserve_lms(rm, rsvp, reqs);
+	if (ret) {
+		DPU_ERROR("unable to find appropriate mixers\n");
+		return ret;
+	}
+
+	/*
+	 * Do assignment preferring to give away low-resource CTLs first:
+	 * - Check mixers without Split Display
+	 * - Only then allow to grab from CTLs with split display capability
+	 */
+	_dpu_rm_reserve_ctls(rm, rsvp, reqs->topology);
+	if (ret && !reqs->topology->needs_split_display) {
+		memcpy(&topology, reqs->topology, sizeof(topology));
+		topology.needs_split_display = true;
+		_dpu_rm_reserve_ctls(rm, rsvp, &topology);
+	}
+	if (ret) {
+		DPU_ERROR("unable to find appropriate CTL\n");
+		return ret;
+	}
+
+	/* Assign INTFs and blks whose usage is tied to them: CTL & CDM */
+	ret = _dpu_rm_reserve_intf_related_hw(rm, rsvp, &reqs->hw_res);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
+static int _dpu_rm_populate_requirements(
+		struct dpu_rm *rm,
+		struct drm_encoder *enc,
+		struct drm_crtc_state *crtc_state,
+		struct drm_connector_state *conn_state,
+		struct dpu_rm_requirements *reqs,
+		struct msm_display_topology req_topology)
+{
+	int i;
+
+	memset(reqs, 0, sizeof(*reqs));
+
+	dpu_encoder_get_hw_resources(enc, &reqs->hw_res, conn_state);
+
+	for (i = 0; i < DPU_RM_TOPOLOGY_MAX; i++) {
+		if (RM_IS_TOPOLOGY_MATCH(g_top_table[i],
+					req_topology)) {
+			reqs->topology = &g_top_table[i];
+			break;
+		}
+	}
+
+	if (!reqs->topology) {
+		DPU_ERROR("invalid topology for the display\n");
+		return -EINVAL;
+	}
+
+	/**
+	 * Set the requirement based on caps if not set from user space
+	 * This will ensure to select LM tied with DS blocks
+	 * Currently, DS blocks are tied with LM 0 and LM 1 (primary display)
+	 */
+	if (!RM_RQ_DS(reqs) && rm->hw_mdp->caps->has_dest_scaler &&
+		conn_state->connector->connector_type == DRM_MODE_CONNECTOR_DSI)
+		reqs->top_ctrl |= BIT(DPU_RM_TOPCTL_DS);
+
+	DRM_DEBUG_KMS("top_ctrl: 0x%llX num_h_tiles: %d\n", reqs->top_ctrl,
+		      reqs->hw_res.display_num_of_h_tiles);
+	DRM_DEBUG_KMS("num_lm: %d num_ctl: %d topology: %d split_display: %d\n",
+		      reqs->topology->num_lm, reqs->topology->num_ctl,
+		      reqs->topology->top_name,
+		      reqs->topology->needs_split_display);
+
+	return 0;
+}
+
+static struct dpu_rm_rsvp *_dpu_rm_get_rsvp(
+		struct dpu_rm *rm,
+		struct drm_encoder *enc)
+{
+	struct dpu_rm_rsvp *i;
+
+	if (!rm || !enc) {
+		DPU_ERROR("invalid params\n");
+		return NULL;
+	}
+
+	if (list_empty(&rm->rsvps))
+		return NULL;
+
+	list_for_each_entry(i, &rm->rsvps, list)
+		if (i->enc_id == enc->base.id)
+			return i;
+
+	return NULL;
+}
+
+static struct drm_connector *_dpu_rm_get_connector(
+		struct drm_encoder *enc)
+{
+	struct drm_connector *conn = NULL;
+	struct list_head *connector_list =
+			&enc->dev->mode_config.connector_list;
+
+	list_for_each_entry(conn, connector_list, head)
+		if (conn->encoder == enc)
+			return conn;
+
+	return NULL;
+}
+
+/**
+ * _dpu_rm_release_rsvp - release resources and release a reservation
+ * @rm:	KMS handle
+ * @rsvp:	RSVP pointer to release and release resources for
+ */
+static void _dpu_rm_release_rsvp(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		struct drm_connector *conn)
+{
+	struct dpu_rm_rsvp *rsvp_c, *rsvp_n;
+	struct dpu_rm_hw_blk *blk;
+	enum dpu_hw_blk_type type;
+
+	if (!rsvp)
+		return;
+
+	DPU_DEBUG("rel rsvp %d enc %d\n", rsvp->seq, rsvp->enc_id);
+
+	list_for_each_entry_safe(rsvp_c, rsvp_n, &rm->rsvps, list) {
+		if (rsvp == rsvp_c) {
+			list_del(&rsvp_c->list);
+			break;
+		}
+	}
+
+	for (type = 0; type < DPU_HW_BLK_MAX; type++) {
+		list_for_each_entry(blk, &rm->hw_blks[type], list) {
+			if (blk->rsvp == rsvp) {
+				blk->rsvp = NULL;
+				DPU_DEBUG("rel rsvp %d enc %d %d %d\n",
+						rsvp->seq, rsvp->enc_id,
+						blk->type, blk->id);
+			}
+			if (blk->rsvp_nxt == rsvp) {
+				blk->rsvp_nxt = NULL;
+				DPU_DEBUG("rel rsvp_nxt %d enc %d %d %d\n",
+						rsvp->seq, rsvp->enc_id,
+						blk->type, blk->id);
+			}
+		}
+	}
+
+	kfree(rsvp);
+}
+
+void dpu_rm_release(struct dpu_rm *rm, struct drm_encoder *enc)
+{
+	struct dpu_rm_rsvp *rsvp;
+	struct drm_connector *conn;
+
+	if (!rm || !enc) {
+		DPU_ERROR("invalid params\n");
+		return;
+	}
+
+	mutex_lock(&rm->rm_lock);
+
+	rsvp = _dpu_rm_get_rsvp(rm, enc);
+	if (!rsvp) {
+		DPU_ERROR("failed to find rsvp for enc %d\n", enc->base.id);
+		goto end;
+	}
+
+	conn = _dpu_rm_get_connector(enc);
+	if (!conn) {
+		DPU_ERROR("failed to get connector for enc %d\n", enc->base.id);
+		goto end;
+	}
+
+	_dpu_rm_release_rsvp(rm, rsvp, conn);
+end:
+	mutex_unlock(&rm->rm_lock);
+}
+
+static int _dpu_rm_commit_rsvp(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		struct drm_connector_state *conn_state)
+{
+	struct dpu_rm_hw_blk *blk;
+	enum dpu_hw_blk_type type;
+	int ret = 0;
+
+	/* Swap next rsvp to be the active */
+	for (type = 0; type < DPU_HW_BLK_MAX; type++) {
+		list_for_each_entry(blk, &rm->hw_blks[type], list) {
+			if (blk->rsvp_nxt) {
+				blk->rsvp = blk->rsvp_nxt;
+				blk->rsvp_nxt = NULL;
+			}
+		}
+	}
+
+	if (!ret)
+		DRM_DEBUG_KMS("rsrv enc %d topology %d\n", rsvp->enc_id,
+			      rsvp->topology);
+
+	return ret;
+}
+
+int dpu_rm_reserve(
+		struct dpu_rm *rm,
+		struct drm_encoder *enc,
+		struct drm_crtc_state *crtc_state,
+		struct drm_connector_state *conn_state,
+		struct msm_display_topology topology,
+		bool test_only)
+{
+	struct dpu_rm_rsvp *rsvp_cur, *rsvp_nxt;
+	struct dpu_rm_requirements reqs;
+	int ret;
+
+	if (!rm || !enc || !crtc_state || !conn_state) {
+		DPU_ERROR("invalid arguments\n");
+		return -EINVAL;
+	}
+
+	/* Check if this is just a page-flip */
+	if (!drm_atomic_crtc_needs_modeset(crtc_state))
+		return 0;
+
+	DRM_DEBUG_KMS("reserving hw for conn %d enc %d crtc %d test_only %d\n",
+		      conn_state->connector->base.id, enc->base.id,
+		      crtc_state->crtc->base.id, test_only);
+
+	mutex_lock(&rm->rm_lock);
+
+	_dpu_rm_print_rsvps(rm, DPU_RM_STAGE_BEGIN);
+
+	ret = _dpu_rm_populate_requirements(rm, enc, crtc_state,
+			conn_state, &reqs, topology);
+	if (ret) {
+		DPU_ERROR("failed to populate hw requirements\n");
+		goto end;
+	}
+
+	/*
+	 * We only support one active reservation per-hw-block. But to implement
+	 * transactional semantics for test-only, and for allowing failure while
+	 * modifying your existing reservation, over the course of this
+	 * function we can have two reservations:
+	 * Current: Existing reservation
+	 * Next: Proposed reservation. The proposed reservation may fail, or may
+	 *       be discarded if in test-only mode.
+	 * If reservation is successful, and we're not in test-only, then we
+	 * replace the current with the next.
+	 */
+	rsvp_nxt = kzalloc(sizeof(*rsvp_nxt), GFP_KERNEL);
+	if (!rsvp_nxt) {
+		ret = -ENOMEM;
+		goto end;
+	}
+
+	rsvp_cur = _dpu_rm_get_rsvp(rm, enc);
+
+	/*
+	 * User can request that we clear out any reservation during the
+	 * atomic_check phase by using this CLEAR bit
+	 */
+	if (rsvp_cur && test_only && RM_RQ_CLEAR(&reqs)) {
+		DPU_DEBUG("test_only & CLEAR: clear rsvp[s%de%d]\n",
+				rsvp_cur->seq, rsvp_cur->enc_id);
+		_dpu_rm_release_rsvp(rm, rsvp_cur, conn_state->connector);
+		rsvp_cur = NULL;
+		_dpu_rm_print_rsvps(rm, DPU_RM_STAGE_AFTER_CLEAR);
+	}
+
+	/* Check the proposed reservation, store it in hw's "next" field */
+	ret = _dpu_rm_make_next_rsvp(rm, enc, crtc_state, conn_state,
+			rsvp_nxt, &reqs);
+
+	_dpu_rm_print_rsvps(rm, DPU_RM_STAGE_AFTER_RSVPNEXT);
+
+	if (ret) {
+		DPU_ERROR("failed to reserve hw resources: %d\n", ret);
+		_dpu_rm_release_rsvp(rm, rsvp_nxt, conn_state->connector);
+	} else if (test_only && !RM_RQ_LOCK(&reqs)) {
+		/*
+		 * Normally, if test_only, test the reservation and then undo
+		 * However, if the user requests LOCK, then keep the reservation
+		 * made during the atomic_check phase.
+		 */
+		DPU_DEBUG("test_only: discard test rsvp[s%de%d]\n",
+				rsvp_nxt->seq, rsvp_nxt->enc_id);
+		_dpu_rm_release_rsvp(rm, rsvp_nxt, conn_state->connector);
+	} else {
+		if (test_only && RM_RQ_LOCK(&reqs))
+			DPU_DEBUG("test_only & LOCK: lock rsvp[s%de%d]\n",
+					rsvp_nxt->seq, rsvp_nxt->enc_id);
+
+		_dpu_rm_release_rsvp(rm, rsvp_cur, conn_state->connector);
+
+		ret = _dpu_rm_commit_rsvp(rm, rsvp_nxt, conn_state);
+	}
+
+	_dpu_rm_print_rsvps(rm, DPU_RM_STAGE_FINAL);
+
+end:
+	mutex_unlock(&rm->rm_lock);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h
new file mode 100644
index 000000000000..ffd1841a6067
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h
@@ -0,0 +1,199 @@
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __DPU_RM_H__
+#define __DPU_RM_H__
+
+#include <linux/list.h>
+
+#include "msm_kms.h"
+#include "dpu_hw_top.h"
+
+/**
+ * enum dpu_rm_topology_name - HW resource use case in use by connector
+ * @DPU_RM_TOPOLOGY_NONE:                 No topology in use currently
+ * @DPU_RM_TOPOLOGY_SINGLEPIPE:           1 LM, 1 PP, 1 INTF/WB
+ * @DPU_RM_TOPOLOGY_DUALPIPE:             2 LM, 2 PP, 2 INTF/WB
+ * @DPU_RM_TOPOLOGY_DUALPIPE_3DMERGE:     2 LM, 2 PP, 3DMux, 1 INTF/WB
+ */
+enum dpu_rm_topology_name {
+	DPU_RM_TOPOLOGY_NONE = 0,
+	DPU_RM_TOPOLOGY_SINGLEPIPE,
+	DPU_RM_TOPOLOGY_DUALPIPE,
+	DPU_RM_TOPOLOGY_DUALPIPE_3DMERGE,
+	DPU_RM_TOPOLOGY_MAX,
+};
+
+/**
+ * enum dpu_rm_topology_control - HW resource use case in use by connector
+ * @DPU_RM_TOPCTL_RESERVE_LOCK: If set, in AtomicTest phase, after a successful
+ *                              test, reserve the resources for this display.
+ *                              Normal behavior would not impact the reservation
+ *                              list during the AtomicTest phase.
+ * @DPU_RM_TOPCTL_RESERVE_CLEAR: If set, in AtomicTest phase, before testing,
+ *                               release any reservation held by this display.
+ *                               Normal behavior would not impact the
+ *                               reservation list during the AtomicTest phase.
+ * @DPU_RM_TOPCTL_DS  : Require layer mixers with DS capabilities
+ */
+enum dpu_rm_topology_control {
+	DPU_RM_TOPCTL_RESERVE_LOCK,
+	DPU_RM_TOPCTL_RESERVE_CLEAR,
+	DPU_RM_TOPCTL_DS,
+};
+
+/**
+ * struct dpu_rm - DPU dynamic hardware resource manager
+ * @dev: device handle for event logging purposes
+ * @rsvps: list of hardware reservations by each crtc->encoder->connector
+ * @hw_blks: array of lists of hardware resources present in the system, one
+ *	list per type of hardware block
+ * @hw_mdp: hardware object for mdp_top
+ * @lm_max_width: cached layer mixer maximum width
+ * @rsvp_next_seq: sequence number for next reservation for debugging purposes
+ * @rm_lock: resource manager mutex
+ */
+struct dpu_rm {
+	struct drm_device *dev;
+	struct list_head rsvps;
+	struct list_head hw_blks[DPU_HW_BLK_MAX];
+	struct dpu_hw_mdp *hw_mdp;
+	uint32_t lm_max_width;
+	uint32_t rsvp_next_seq;
+	struct mutex rm_lock;
+};
+
+/**
+ *  struct dpu_rm_hw_blk - resource manager internal structure
+ *	forward declaration for single iterator definition without void pointer
+ */
+struct dpu_rm_hw_blk;
+
+/**
+ * struct dpu_rm_hw_iter - iterator for use with dpu_rm
+ * @hw: dpu_hw object requested, or NULL on failure
+ * @blk: dpu_rm internal block representation. Clients ignore. Used as iterator.
+ * @enc_id: DRM ID of Encoder client wishes to search for, or 0 for Any Encoder
+ * @type: Hardware Block Type client wishes to search for.
+ */
+struct dpu_rm_hw_iter {
+	void *hw;
+	struct dpu_rm_hw_blk *blk;
+	uint32_t enc_id;
+	enum dpu_hw_blk_type type;
+};
+
+/**
+ * dpu_rm_init - Read hardware catalog and create reservation tracking objects
+ *	for all HW blocks.
+ * @rm: DPU Resource Manager handle
+ * @cat: Pointer to hardware catalog
+ * @mmio: mapped register io address of MDP
+ * @dev: device handle for event logging purposes
+ * @Return: 0 on Success otherwise -ERROR
+ */
+int dpu_rm_init(struct dpu_rm *rm,
+		struct dpu_mdss_cfg *cat,
+		void __iomem *mmio,
+		struct drm_device *dev);
+
+/**
+ * dpu_rm_destroy - Free all memory allocated by dpu_rm_init
+ * @rm: DPU Resource Manager handle
+ * @Return: 0 on Success otherwise -ERROR
+ */
+int dpu_rm_destroy(struct dpu_rm *rm);
+
+/**
+ * dpu_rm_reserve - Given a CRTC->Encoder->Connector display chain, analyze
+ *	the use connections and user requirements, specified through related
+ *	topology control properties, and reserve hardware blocks to that
+ *	display chain.
+ *	HW blocks can then be accessed through dpu_rm_get_* functions.
+ *	HW Reservations should be released via dpu_rm_release_hw.
+ * @rm: DPU Resource Manager handle
+ * @drm_enc: DRM Encoder handle
+ * @crtc_state: Proposed Atomic DRM CRTC State handle
+ * @conn_state: Proposed Atomic DRM Connector State handle
+ * @topology: Pointer to topology info for the display
+ * @test_only: Atomic-Test phase, discard results (unless property overrides)
+ * @Return: 0 on Success otherwise -ERROR
+ */
+int dpu_rm_reserve(struct dpu_rm *rm,
+		struct drm_encoder *drm_enc,
+		struct drm_crtc_state *crtc_state,
+		struct drm_connector_state *conn_state,
+		struct msm_display_topology topology,
+		bool test_only);
+
+/**
+ * dpu_rm_reserve - Given the encoder for the display chain, release any
+ *	HW blocks previously reserved for that use case.
+ * @rm: DPU Resource Manager handle
+ * @enc: DRM Encoder handle
+ * @Return: 0 on Success otherwise -ERROR
+ */
+void dpu_rm_release(struct dpu_rm *rm, struct drm_encoder *enc);
+
+/**
+ * dpu_rm_get_mdp - Retrieve HW block for MDP TOP.
+ *	This is never reserved, and is usable by any display.
+ * @rm: DPU Resource Manager handle
+ * @Return: Pointer to hw block or NULL
+ */
+struct dpu_hw_mdp *dpu_rm_get_mdp(struct dpu_rm *rm);
+
+/**
+ * dpu_rm_init_hw_iter - setup given iterator for new iteration over hw list
+ *	using dpu_rm_get_hw
+ * @iter: iter object to initialize
+ * @enc_id: DRM ID of Encoder client wishes to search for, or 0 for Any Encoder
+ * @type: Hardware Block Type client wishes to search for.
+ */
+void dpu_rm_init_hw_iter(
+		struct dpu_rm_hw_iter *iter,
+		uint32_t enc_id,
+		enum dpu_hw_blk_type type);
+/**
+ * dpu_rm_get_hw - retrieve reserved hw object given encoder and hw type
+ *	Meant to do a single pass through the hardware list to iteratively
+ *	retrieve hardware blocks of a given type for a given encoder.
+ *	Initialize an iterator object.
+ *	Set hw block type of interest. Set encoder id of interest, 0 for any.
+ *	Function returns first hw of type for that encoder.
+ *	Subsequent calls will return the next reserved hw of that type in-order.
+ *	Iterator HW pointer will be null on failure to find hw.
+ * @rm: DPU Resource Manager handle
+ * @iter: iterator object
+ * @Return: true on match found, false on no match found
+ */
+bool dpu_rm_get_hw(struct dpu_rm *rm, struct dpu_rm_hw_iter *iter);
+
+/**
+ * dpu_rm_check_property_topctl - validate property bitmask before it is set
+ * @val: user's proposed topology control bitmask
+ * @Return: 0 on success or error
+ */
+int dpu_rm_check_property_topctl(uint64_t val);
+
+/**
+ * dpu_rm_get_topology_name - returns the name of the the given topology
+ *                            definition
+ * @topology: topology definition
+ * @Return: name of the topology
+ */
+enum dpu_rm_topology_name
+dpu_rm_get_topology_name(struct msm_display_topology topology);
+
+#endif /* __DPU_RM_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h
new file mode 100644
index 000000000000..ae0ca5076238
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h
@@ -0,0 +1,1007 @@
+/* Copyright (c) 2014-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#if !defined(_DPU_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
+#define _DPU_TRACE_H_
+
+#include <linux/stringify.h>
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+
+#include <drm/drm_rect.h>
+#include "dpu_crtc.h"
+#include "dpu_encoder_phys.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_vbif.h"
+#include "dpu_plane.h"
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM dpu
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE dpu_trace
+
+TRACE_EVENT(dpu_perf_set_qos_luts,
+	TP_PROTO(u32 pnum, u32 fmt, bool rt, u32 fl,
+		u32 lut, u32 lut_usage),
+	TP_ARGS(pnum, fmt, rt, fl, lut, lut_usage),
+	TP_STRUCT__entry(
+			__field(u32, pnum)
+			__field(u32, fmt)
+			__field(bool, rt)
+			__field(u32, fl)
+			__field(u64, lut)
+			__field(u32, lut_usage)
+	),
+	TP_fast_assign(
+			__entry->pnum = pnum;
+			__entry->fmt = fmt;
+			__entry->rt = rt;
+			__entry->fl = fl;
+			__entry->lut = lut;
+			__entry->lut_usage = lut_usage;
+	),
+	TP_printk("pnum=%d fmt=%x rt=%d fl=%d lut=0x%llx lut_usage=%d",
+			__entry->pnum, __entry->fmt,
+			__entry->rt, __entry->fl,
+			__entry->lut, __entry->lut_usage)
+);
+
+TRACE_EVENT(dpu_perf_set_danger_luts,
+	TP_PROTO(u32 pnum, u32 fmt, u32 mode, u32 danger_lut,
+		u32 safe_lut),
+	TP_ARGS(pnum, fmt, mode, danger_lut, safe_lut),
+	TP_STRUCT__entry(
+			__field(u32, pnum)
+			__field(u32, fmt)
+			__field(u32, mode)
+			__field(u32, danger_lut)
+			__field(u32, safe_lut)
+	),
+	TP_fast_assign(
+			__entry->pnum = pnum;
+			__entry->fmt = fmt;
+			__entry->mode = mode;
+			__entry->danger_lut = danger_lut;
+			__entry->safe_lut = safe_lut;
+	),
+	TP_printk("pnum=%d fmt=%x mode=%d luts[0x%x, 0x%x]",
+			__entry->pnum, __entry->fmt,
+			__entry->mode, __entry->danger_lut,
+			__entry->safe_lut)
+);
+
+TRACE_EVENT(dpu_perf_set_ot,
+	TP_PROTO(u32 pnum, u32 xin_id, u32 rd_lim, u32 vbif_idx),
+	TP_ARGS(pnum, xin_id, rd_lim, vbif_idx),
+	TP_STRUCT__entry(
+			__field(u32, pnum)
+			__field(u32, xin_id)
+			__field(u32, rd_lim)
+			__field(u32, vbif_idx)
+	),
+	TP_fast_assign(
+			__entry->pnum = pnum;
+			__entry->xin_id = xin_id;
+			__entry->rd_lim = rd_lim;
+			__entry->vbif_idx = vbif_idx;
+	),
+	TP_printk("pnum:%d xin_id:%d ot:%d vbif:%d",
+			__entry->pnum, __entry->xin_id, __entry->rd_lim,
+			__entry->vbif_idx)
+)
+
+TRACE_EVENT(dpu_perf_update_bus,
+	TP_PROTO(int client, unsigned long long ab_quota,
+	unsigned long long ib_quota),
+	TP_ARGS(client, ab_quota, ib_quota),
+	TP_STRUCT__entry(
+			__field(int, client)
+			__field(u64, ab_quota)
+			__field(u64, ib_quota)
+	),
+	TP_fast_assign(
+			__entry->client = client;
+			__entry->ab_quota = ab_quota;
+			__entry->ib_quota = ib_quota;
+	),
+	TP_printk("Request client:%d ab=%llu ib=%llu",
+			__entry->client,
+			__entry->ab_quota,
+			__entry->ib_quota)
+)
+
+
+TRACE_EVENT(dpu_cmd_release_bw,
+	TP_PROTO(u32 crtc_id),
+	TP_ARGS(crtc_id),
+	TP_STRUCT__entry(
+			__field(u32, crtc_id)
+	),
+	TP_fast_assign(
+			__entry->crtc_id = crtc_id;
+	),
+	TP_printk("crtc:%d", __entry->crtc_id)
+);
+
+TRACE_EVENT(tracing_mark_write,
+	TP_PROTO(int pid, const char *name, bool trace_begin),
+	TP_ARGS(pid, name, trace_begin),
+	TP_STRUCT__entry(
+			__field(int, pid)
+			__string(trace_name, name)
+			__field(bool, trace_begin)
+	),
+	TP_fast_assign(
+			__entry->pid = pid;
+			__assign_str(trace_name, name);
+			__entry->trace_begin = trace_begin;
+	),
+	TP_printk("%s|%d|%s", __entry->trace_begin ? "B" : "E",
+		__entry->pid, __get_str(trace_name))
+)
+
+TRACE_EVENT(dpu_trace_counter,
+	TP_PROTO(int pid, char *name, int value),
+	TP_ARGS(pid, name, value),
+	TP_STRUCT__entry(
+			__field(int, pid)
+			__string(counter_name, name)
+			__field(int, value)
+	),
+	TP_fast_assign(
+			__entry->pid = current->tgid;
+			__assign_str(counter_name, name);
+			__entry->value = value;
+	),
+	TP_printk("%d|%s|%d", __entry->pid,
+			__get_str(counter_name), __entry->value)
+)
+
+TRACE_EVENT(dpu_perf_crtc_update,
+	TP_PROTO(u32 crtc, u64 bw_ctl_mnoc, u64 bw_ctl_llcc,
+			u64 bw_ctl_ebi, u32 core_clk_rate,
+			bool stop_req, u32 update_bus, u32 update_clk),
+	TP_ARGS(crtc, bw_ctl_mnoc, bw_ctl_llcc, bw_ctl_ebi, core_clk_rate,
+		stop_req, update_bus, update_clk),
+	TP_STRUCT__entry(
+			__field(u32, crtc)
+			__field(u64, bw_ctl_mnoc)
+			__field(u64, bw_ctl_llcc)
+			__field(u64, bw_ctl_ebi)
+			__field(u32, core_clk_rate)
+			__field(bool, stop_req)
+			__field(u32, update_bus)
+			__field(u32, update_clk)
+	),
+	TP_fast_assign(
+			__entry->crtc = crtc;
+			__entry->bw_ctl_mnoc = bw_ctl_mnoc;
+			__entry->bw_ctl_llcc = bw_ctl_llcc;
+			__entry->bw_ctl_ebi = bw_ctl_ebi;
+			__entry->core_clk_rate = core_clk_rate;
+			__entry->stop_req = stop_req;
+			__entry->update_bus = update_bus;
+			__entry->update_clk = update_clk;
+	),
+	 TP_printk(
+		"crtc=%d bw_mnoc=%llu bw_llcc=%llu bw_ebi=%llu clk_rate=%u stop_req=%d u_bus=%d u_clk=%d",
+			__entry->crtc,
+			__entry->bw_ctl_mnoc,
+			__entry->bw_ctl_llcc,
+			__entry->bw_ctl_ebi,
+			__entry->core_clk_rate,
+			__entry->stop_req,
+			__entry->update_bus,
+			__entry->update_clk)
+);
+
+DECLARE_EVENT_CLASS(dpu_enc_irq_template,
+	TP_PROTO(uint32_t drm_id, enum dpu_intr_idx intr_idx, int hw_idx,
+		 int irq_idx),
+	TP_ARGS(drm_id, intr_idx, hw_idx, irq_idx),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	enum dpu_intr_idx,	intr_idx	)
+		__field(	int,			hw_idx		)
+		__field(	int,			irq_idx		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->intr_idx = intr_idx;
+		__entry->hw_idx = hw_idx;
+		__entry->irq_idx = irq_idx;
+	),
+	TP_printk("id=%u, intr=%d, hw=%d, irq=%d",
+		  __entry->drm_id, __entry->intr_idx, __entry->hw_idx,
+		  __entry->irq_idx)
+);
+DEFINE_EVENT(dpu_enc_irq_template, dpu_enc_irq_register_success,
+	TP_PROTO(uint32_t drm_id, enum dpu_intr_idx intr_idx, int hw_idx,
+		 int irq_idx),
+	TP_ARGS(drm_id, intr_idx, hw_idx, irq_idx)
+);
+DEFINE_EVENT(dpu_enc_irq_template, dpu_enc_irq_unregister_success,
+	TP_PROTO(uint32_t drm_id, enum dpu_intr_idx intr_idx, int hw_idx,
+		 int irq_idx),
+	TP_ARGS(drm_id, intr_idx, hw_idx, irq_idx)
+);
+
+TRACE_EVENT(dpu_enc_irq_wait_success,
+	TP_PROTO(uint32_t drm_id, enum dpu_intr_idx intr_idx, int hw_idx,
+		 int irq_idx, enum dpu_pingpong pp_idx, int atomic_cnt),
+	TP_ARGS(drm_id, intr_idx, hw_idx, irq_idx, pp_idx, atomic_cnt),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	enum dpu_intr_idx,	intr_idx	)
+		__field(	int,			hw_idx		)
+		__field(	int,			irq_idx		)
+		__field(	enum dpu_pingpong,	pp_idx		)
+		__field(	int,			atomic_cnt	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->intr_idx = intr_idx;
+		__entry->hw_idx = hw_idx;
+		__entry->irq_idx = irq_idx;
+		__entry->pp_idx = pp_idx;
+		__entry->atomic_cnt = atomic_cnt;
+	),
+	TP_printk("id=%u, intr=%d, hw=%d, irq=%d, pp=%d, atomic_cnt=%d",
+		  __entry->drm_id, __entry->intr_idx, __entry->hw_idx,
+		  __entry->irq_idx, __entry->pp_idx, __entry->atomic_cnt)
+);
+
+DECLARE_EVENT_CLASS(dpu_drm_obj_template,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+	),
+	TP_printk("id=%u", __entry->drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_atomic_check,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_mode_set,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_disable,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_kickoff,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_prepare_kickoff,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_prepare_kickoff_reset,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_crtc_complete_flip,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_crtc_vblank_cb,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_crtc_complete_commit,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_kms_enc_enable,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_kms_commit,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_kms_wait_for_commit_done,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+
+TRACE_EVENT(dpu_enc_enable,
+	TP_PROTO(uint32_t drm_id, int hdisplay, int vdisplay),
+	TP_ARGS(drm_id, hdisplay, vdisplay),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	int,			hdisplay	)
+		__field(	int,			vdisplay	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->hdisplay = hdisplay;
+		__entry->vdisplay = vdisplay;
+	),
+	TP_printk("id=%u, mode=%dx%d",
+		  __entry->drm_id, __entry->hdisplay, __entry->vdisplay)
+);
+
+DECLARE_EVENT_CLASS(dpu_enc_keyval_template,
+	TP_PROTO(uint32_t drm_id, int val),
+	TP_ARGS(drm_id, val),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id	)
+		__field(	int,		val	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->val = val;
+	),
+	TP_printk("id=%u, val=%d", __entry->drm_id, __entry->val)
+);
+DEFINE_EVENT(dpu_enc_keyval_template, dpu_enc_underrun_cb,
+	TP_PROTO(uint32_t drm_id, int count),
+	TP_ARGS(drm_id, count)
+);
+DEFINE_EVENT(dpu_enc_keyval_template, dpu_enc_trigger_start,
+	TP_PROTO(uint32_t drm_id, int ctl_idx),
+	TP_ARGS(drm_id, ctl_idx)
+);
+
+TRACE_EVENT(dpu_enc_atomic_check_flags,
+	TP_PROTO(uint32_t drm_id, unsigned int flags, int private_flags),
+	TP_ARGS(drm_id, flags, private_flags),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	unsigned int,		flags		)
+		__field(	int,			private_flags	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->flags = flags;
+		__entry->private_flags = private_flags;
+	),
+	TP_printk("id=%u, flags=%u, private_flags=%d",
+		  __entry->drm_id, __entry->flags, __entry->private_flags)
+);
+
+DECLARE_EVENT_CLASS(dpu_enc_id_enable_template,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	bool,			enable		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->enable = enable;
+	),
+	TP_printk("id=%u, enable=%s",
+		  __entry->drm_id, __entry->enable ? "true" : "false")
+);
+DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_rc_helper,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable)
+);
+DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_vblank_cb,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable)
+);
+DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_frame_event_cb,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable)
+);
+DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_phys_cmd_connect_te,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable)
+);
+
+TRACE_EVENT(dpu_enc_rc,
+	TP_PROTO(uint32_t drm_id, u32 sw_event, bool idle_pc_supported,
+		 int rc_state, const char *stage),
+	TP_ARGS(drm_id, sw_event, idle_pc_supported, rc_state, stage),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id			)
+		__field(	u32,		sw_event		)
+		__field(	bool,		idle_pc_supported	)
+		__field(	int,		rc_state		)
+		__string(	stage_str,	stage			)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->sw_event = sw_event;
+		__entry->idle_pc_supported = idle_pc_supported;
+		__entry->rc_state = rc_state;
+		__assign_str(stage_str, stage);
+	),
+	TP_printk("%s: id:%u, sw_event:%d, idle_pc_supported:%s, rc_state:%d\n",
+		  __get_str(stage_str), __entry->drm_id, __entry->sw_event,
+		  __entry->idle_pc_supported ? "true" : "false",
+		  __entry->rc_state)
+);
+
+TRACE_EVENT(dpu_enc_frame_done_cb_not_busy,
+	TP_PROTO(uint32_t drm_id, u32 event, enum dpu_intf intf_idx),
+	TP_ARGS(drm_id, event, intf_idx),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id		)
+		__field(	u32,		event		)
+		__field(	enum dpu_intf,	intf_idx	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->event = event;
+		__entry->intf_idx = intf_idx;
+	),
+	TP_printk("id=%u, event=%u, intf=%d", __entry->drm_id, __entry->event,
+		  __entry->intf_idx)
+);
+
+TRACE_EVENT(dpu_enc_frame_done_cb,
+	TP_PROTO(uint32_t drm_id, unsigned int idx,
+		 unsigned long frame_busy_mask),
+	TP_ARGS(drm_id, idx, frame_busy_mask),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	unsigned int,		idx		)
+		__field(	unsigned long,		frame_busy_mask	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->idx = idx;
+		__entry->frame_busy_mask = frame_busy_mask;
+	),
+	TP_printk("id=%u, idx=%u, frame_busy_mask=%lx", __entry->drm_id,
+		  __entry->idx, __entry->frame_busy_mask)
+);
+
+TRACE_EVENT(dpu_enc_trigger_flush,
+	TP_PROTO(uint32_t drm_id, enum dpu_intf intf_idx,
+		 int pending_kickoff_cnt, int ctl_idx, u32 pending_flush_ret),
+	TP_ARGS(drm_id, intf_idx, pending_kickoff_cnt, ctl_idx,
+		pending_flush_ret),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id			)
+		__field(	enum dpu_intf,	intf_idx		)
+		__field(	int,		pending_kickoff_cnt	)
+		__field(	int,		ctl_idx			)
+		__field(	u32,		pending_flush_ret	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->intf_idx = intf_idx;
+		__entry->pending_kickoff_cnt = pending_kickoff_cnt;
+		__entry->ctl_idx = ctl_idx;
+		__entry->pending_flush_ret = pending_flush_ret;
+	),
+	TP_printk("id=%u, intf_idx=%d, pending_kickoff_cnt=%d ctl_idx=%d "
+		  "pending_flush_ret=%u", __entry->drm_id,
+		  __entry->intf_idx, __entry->pending_kickoff_cnt,
+		  __entry->ctl_idx, __entry->pending_flush_ret)
+);
+
+DECLARE_EVENT_CLASS(dpu_enc_ktime_template,
+	TP_PROTO(uint32_t drm_id, ktime_t time),
+	TP_ARGS(drm_id, time),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id	)
+		__field(	ktime_t,	time	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->time = time;
+	),
+	TP_printk("id=%u, time=%lld", __entry->drm_id,
+		  ktime_to_ms(__entry->time))
+);
+DEFINE_EVENT(dpu_enc_ktime_template, dpu_enc_vsync_event_work,
+	TP_PROTO(uint32_t drm_id, ktime_t time),
+	TP_ARGS(drm_id, time)
+);
+DEFINE_EVENT(dpu_enc_ktime_template, dpu_enc_early_kickoff,
+	TP_PROTO(uint32_t drm_id, ktime_t time),
+	TP_ARGS(drm_id, time)
+);
+
+DECLARE_EVENT_CLASS(dpu_id_event_template,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id	)
+		__field(	u32,		event	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->event = event;
+	),
+	TP_printk("id=%u, event=%u", __entry->drm_id, __entry->event)
+);
+DEFINE_EVENT(dpu_id_event_template, dpu_enc_frame_done_timeout,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event)
+);
+DEFINE_EVENT(dpu_id_event_template, dpu_crtc_frame_event_cb,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event)
+);
+DEFINE_EVENT(dpu_id_event_template, dpu_crtc_handle_power_event,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event)
+);
+DEFINE_EVENT(dpu_id_event_template, dpu_crtc_frame_event_done,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event)
+);
+DEFINE_EVENT(dpu_id_event_template, dpu_crtc_frame_event_more_pending,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event)
+);
+
+TRACE_EVENT(dpu_enc_wait_event_timeout,
+	TP_PROTO(uint32_t drm_id, int32_t hw_id, int rc, s64 time,
+		 s64 expected_time, int atomic_cnt),
+	TP_ARGS(drm_id, hw_id, rc, time, expected_time, atomic_cnt),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id		)
+		__field(	int32_t,	hw_id		)
+		__field(	int,		rc		)
+		__field(	s64,		time		)
+		__field(	s64,		expected_time	)
+		__field(	int,		atomic_cnt	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->hw_id = hw_id;
+		__entry->rc = rc;
+		__entry->time = time;
+		__entry->expected_time = expected_time;
+		__entry->atomic_cnt = atomic_cnt;
+	),
+	TP_printk("id=%u, hw_id=%d, rc=%d, time=%lld, expected=%lld cnt=%d",
+		  __entry->drm_id, __entry->hw_id, __entry->rc, __entry->time,
+		  __entry->expected_time, __entry->atomic_cnt)
+);
+
+TRACE_EVENT(dpu_enc_phys_cmd_irq_ctrl,
+	TP_PROTO(uint32_t drm_id, enum dpu_pingpong pp, bool enable,
+		 int refcnt),
+	TP_ARGS(drm_id, pp, enable, refcnt),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id	)
+		__field(	enum dpu_pingpong,	pp	)
+		__field(	bool,			enable	)
+		__field(	int,			refcnt	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->pp = pp;
+		__entry->enable = enable;
+		__entry->refcnt = refcnt;
+	),
+	TP_printk("id=%u, pp=%d, enable=%s, refcnt=%d", __entry->drm_id,
+		  __entry->pp, __entry->enable ? "true" : "false",
+		  __entry->refcnt)
+);
+
+TRACE_EVENT(dpu_enc_phys_cmd_pp_tx_done,
+	TP_PROTO(uint32_t drm_id, enum dpu_pingpong pp, int new_count,
+		 u32 event),
+	TP_ARGS(drm_id, pp, new_count, event),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	enum dpu_pingpong,	pp		)
+		__field(	int,			new_count	)
+		__field(	u32,			event		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->pp = pp;
+		__entry->new_count = new_count;
+		__entry->event = event;
+	),
+	TP_printk("id=%u, pp=%d, new_count=%d, event=%u", __entry->drm_id,
+		  __entry->pp, __entry->new_count, __entry->event)
+);
+
+TRACE_EVENT(dpu_enc_phys_cmd_pdone_timeout,
+	TP_PROTO(uint32_t drm_id, enum dpu_pingpong pp, int timeout_count,
+		 int kickoff_count, u32 event),
+	TP_ARGS(drm_id, pp, timeout_count, kickoff_count, event),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	enum dpu_pingpong,	pp		)
+		__field(	int,			timeout_count	)
+		__field(	int,			kickoff_count	)
+		__field(	u32,			event		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->pp = pp;
+		__entry->timeout_count = timeout_count;
+		__entry->kickoff_count = kickoff_count;
+		__entry->event = event;
+	),
+	TP_printk("id=%u, pp=%d, timeout_count=%d, kickoff_count=%d, event=%u",
+		  __entry->drm_id, __entry->pp, __entry->timeout_count,
+		  __entry->kickoff_count, __entry->event)
+);
+
+TRACE_EVENT(dpu_enc_phys_vid_post_kickoff,
+	TP_PROTO(uint32_t drm_id, enum dpu_intf intf_idx),
+	TP_ARGS(drm_id, intf_idx),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id			)
+		__field(	enum dpu_intf,	intf_idx		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->intf_idx = intf_idx;
+	),
+	TP_printk("id=%u, intf_idx=%d", __entry->drm_id, __entry->intf_idx)
+);
+
+TRACE_EVENT(dpu_enc_phys_vid_irq_ctrl,
+	TP_PROTO(uint32_t drm_id, enum dpu_intf intf_idx, bool enable,
+		 int refcnt),
+	TP_ARGS(drm_id, intf_idx, enable, refcnt),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id		)
+		__field(	enum dpu_intf,	intf_idx	)
+		__field(	bool,		enable		)
+		__field(	int,		refcnt		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->intf_idx = intf_idx;
+		__entry->enable = enable;
+		__entry->refcnt = refcnt;
+	),
+	TP_printk("id=%u, intf_idx=%d enable=%s refcnt=%d", __entry->drm_id,
+		  __entry->intf_idx, __entry->enable ? "true" : "false",
+		  __entry->drm_id)
+);
+
+TRACE_EVENT(dpu_crtc_setup_mixer,
+	TP_PROTO(uint32_t crtc_id, uint32_t plane_id,
+		 struct drm_plane_state *state, struct dpu_plane_state *pstate,
+		 uint32_t stage_idx, enum dpu_sspp sspp, uint32_t pixel_format,
+		 uint64_t modifier),
+	TP_ARGS(crtc_id, plane_id, state, pstate, stage_idx, sspp,
+		pixel_format, modifier),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		crtc_id		)
+		__field(	uint32_t,		plane_id	)
+		__field(	struct drm_plane_state*,state		)
+		__field(	struct dpu_plane_state*,pstate		)
+		__field(	uint32_t,		stage_idx	)
+		__field(	enum dpu_sspp,		sspp		)
+		__field(	uint32_t,		pixel_format	)
+		__field(	uint64_t,		modifier	)
+	),
+	TP_fast_assign(
+		__entry->crtc_id = crtc_id;
+		__entry->plane_id = plane_id;
+		__entry->state = state;
+		__entry->pstate = pstate;
+		__entry->stage_idx = stage_idx;
+		__entry->sspp = sspp;
+		__entry->pixel_format = pixel_format;
+		__entry->modifier = modifier;
+	),
+	TP_printk("crtc_id:%u plane_id:%u fb_id:%u src:{%ux%u+%ux%u} "
+		  "dst:{%ux%u+%ux%u} stage_idx:%u stage:%d, sspp:%d "
+		  "multirect_index:%d multirect_mode:%u pix_format:%u "
+		  "modifier:%llu",
+		  __entry->crtc_id, __entry->plane_id,
+		  __entry->state->fb ? __entry->state->fb->base.id : -1,
+		  __entry->state->src_w >> 16,  __entry->state->src_h >> 16,
+		  __entry->state->src_x >> 16,  __entry->state->src_y >> 16,
+		  __entry->state->crtc_w,  __entry->state->crtc_h,
+		  __entry->state->crtc_x,  __entry->state->crtc_y,
+		  __entry->stage_idx, __entry->pstate->stage, __entry->sspp,
+		  __entry->pstate->multirect_index,
+		  __entry->pstate->multirect_mode, __entry->pixel_format,
+		  __entry->modifier)
+);
+
+TRACE_EVENT(dpu_crtc_setup_lm_bounds,
+	TP_PROTO(uint32_t drm_id, int mixer, struct drm_rect *bounds),
+	TP_ARGS(drm_id, mixer, bounds),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id	)
+		__field(	int,			mixer	)
+		__field(	struct drm_rect *,	bounds	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->mixer = mixer;
+		__entry->bounds = bounds;
+	),
+	TP_printk("id:%u mixer:%d bounds:" DRM_RECT_FMT, __entry->drm_id,
+		  __entry->mixer, DRM_RECT_ARG(__entry->bounds))
+);
+
+TRACE_EVENT(dpu_crtc_vblank_enable,
+	TP_PROTO(uint32_t drm_id, uint32_t enc_id, bool enable,
+		 struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enc_id, enable, crtc),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id	)
+		__field(	uint32_t,		enc_id	)
+		__field(	bool,			enable	)
+		__field(	struct dpu_crtc *,	crtc	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->enc_id = enc_id;
+		__entry->enable = enable;
+		__entry->crtc = crtc;
+	),
+	TP_printk("id:%u encoder:%u enable:%s state{enabled:%s suspend:%s "
+		  "vblank_req:%s}",
+		  __entry->drm_id, __entry->enc_id,
+		  __entry->enable ? "true" : "false",
+		  __entry->crtc->enabled ? "true" : "false",
+		  __entry->crtc->suspend ? "true" : "false",
+		  __entry->crtc->vblank_requested ? "true" : "false")
+);
+
+DECLARE_EVENT_CLASS(dpu_crtc_enable_template,
+	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enable, crtc),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id	)
+		__field(	bool,			enable	)
+		__field(	struct dpu_crtc *,	crtc	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->enable = enable;
+		__entry->crtc = crtc;
+	),
+	TP_printk("id:%u enable:%s state{enabled:%s suspend:%s vblank_req:%s}",
+		  __entry->drm_id, __entry->enable ? "true" : "false",
+		  __entry->crtc->enabled ? "true" : "false",
+		  __entry->crtc->suspend ? "true" : "false",
+		  __entry->crtc->vblank_requested ? "true" : "false")
+);
+DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_set_suspend,
+	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enable, crtc)
+);
+DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_enable,
+	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enable, crtc)
+);
+DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_disable,
+	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enable, crtc)
+);
+DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_vblank,
+	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enable, crtc)
+);
+
+TRACE_EVENT(dpu_crtc_disable_frame_pending,
+	TP_PROTO(uint32_t drm_id, int frame_pending),
+	TP_ARGS(drm_id, frame_pending),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	int,			frame_pending	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->frame_pending = frame_pending;
+	),
+	TP_printk("id:%u frame_pending:%d", __entry->drm_id,
+		  __entry->frame_pending)
+);
+
+TRACE_EVENT(dpu_plane_set_scanout,
+	TP_PROTO(enum dpu_sspp index, struct dpu_hw_fmt_layout *layout,
+		 enum dpu_sspp_multirect_index multirect_index),
+	TP_ARGS(index, layout, multirect_index),
+	TP_STRUCT__entry(
+		__field(	enum dpu_sspp,			index	)
+		__field(	struct dpu_hw_fmt_layout*,	layout	)
+		__field(	enum dpu_sspp_multirect_index,	multirect_index)
+	),
+	TP_fast_assign(
+		__entry->index = index;
+		__entry->layout = layout;
+		__entry->multirect_index = multirect_index;
+	),
+	TP_printk("index:%d layout:{%ux%u @ [%u/%u, %u/%u, %u/%u, %u/%u]} "
+		  "multirect_index:%d", __entry->index, __entry->layout->width,
+		  __entry->layout->height, __entry->layout->plane_addr[0],
+		  __entry->layout->plane_size[0],
+		  __entry->layout->plane_addr[1],
+		  __entry->layout->plane_size[1],
+		  __entry->layout->plane_addr[2],
+		  __entry->layout->plane_size[2],
+		  __entry->layout->plane_addr[3],
+		  __entry->layout->plane_size[3], __entry->multirect_index)
+);
+
+TRACE_EVENT(dpu_plane_disable,
+	TP_PROTO(uint32_t drm_id, bool is_virtual, uint32_t multirect_mode),
+	TP_ARGS(drm_id, is_virtual, multirect_mode),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	bool,			is_virtual	)
+		__field(	uint32_t,		multirect_mode	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->is_virtual = is_virtual;
+		__entry->multirect_mode = multirect_mode;
+	),
+	TP_printk("id:%u is_virtual:%s multirect_mode:%u", __entry->drm_id,
+		  __entry->is_virtual ? "true" : "false",
+		  __entry->multirect_mode)
+);
+
+DECLARE_EVENT_CLASS(dpu_rm_iter_template,
+	TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id),
+	TP_ARGS(id, type, enc_id),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		id	)
+		__field(	enum dpu_hw_blk_type,	type	)
+		__field(	uint32_t,		enc_id	)
+	),
+	TP_fast_assign(
+		__entry->id = id;
+		__entry->type = type;
+		__entry->enc_id = enc_id;
+	),
+	TP_printk("id:%d type:%d enc_id:%u", __entry->id, __entry->type,
+		  __entry->enc_id)
+);
+DEFINE_EVENT(dpu_rm_iter_template, dpu_rm_reserve_cdm,
+	TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id),
+	TP_ARGS(id, type, enc_id)
+);
+DEFINE_EVENT(dpu_rm_iter_template, dpu_rm_reserve_intf,
+	TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id),
+	TP_ARGS(id, type, enc_id)
+);
+DEFINE_EVENT(dpu_rm_iter_template, dpu_rm_reserve_ctls,
+	TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id),
+	TP_ARGS(id, type, enc_id)
+);
+
+TRACE_EVENT(dpu_rm_reserve_lms,
+	TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id,
+		 uint32_t pp_id),
+	TP_ARGS(id, type, enc_id, pp_id),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		id	)
+		__field(	enum dpu_hw_blk_type,	type	)
+		__field(	uint32_t,		enc_id	)
+		__field(	uint32_t,		pp_id	)
+	),
+	TP_fast_assign(
+		__entry->id = id;
+		__entry->type = type;
+		__entry->enc_id = enc_id;
+		__entry->pp_id = pp_id;
+	),
+	TP_printk("id:%d type:%d enc_id:%u pp_id:%u", __entry->id,
+		  __entry->type, __entry->enc_id, __entry->pp_id)
+);
+
+TRACE_EVENT(dpu_vbif_wait_xin_halt_fail,
+	TP_PROTO(enum dpu_vbif index, u32 xin_id),
+	TP_ARGS(index, xin_id),
+	TP_STRUCT__entry(
+		__field(	enum dpu_vbif,	index	)
+		__field(	u32,		xin_id	)
+	),
+	TP_fast_assign(
+		__entry->index = index;
+		__entry->xin_id = xin_id;
+	),
+	TP_printk("index:%d xin_id:%u", __entry->index, __entry->xin_id)
+);
+
+TRACE_EVENT(dpu_pp_connect_ext_te,
+	TP_PROTO(enum dpu_pingpong pp, u32 cfg),
+	TP_ARGS(pp, cfg),
+	TP_STRUCT__entry(
+		__field(	enum dpu_pingpong,	pp	)
+		__field(	u32,			cfg	)
+	),
+	TP_fast_assign(
+		__entry->pp = pp;
+		__entry->cfg = cfg;
+	),
+	TP_printk("pp:%d cfg:%u", __entry->pp, __entry->cfg)
+);
+
+DECLARE_EVENT_CLASS(dpu_core_irq_idx_cnt_template,
+	TP_PROTO(int irq_idx, int enable_count),
+	TP_ARGS(irq_idx, enable_count),
+	TP_STRUCT__entry(
+		__field(	int,	irq_idx		)
+		__field(	int,	enable_count	)
+	),
+	TP_fast_assign(
+		__entry->irq_idx = irq_idx;
+		__entry->enable_count = enable_count;
+	),
+	TP_printk("irq_idx:%d enable_count:%u", __entry->irq_idx,
+		  __entry->enable_count)
+);
+DEFINE_EVENT(dpu_core_irq_idx_cnt_template, dpu_core_irq_enable_idx,
+	TP_PROTO(int irq_idx, int enable_count),
+	TP_ARGS(irq_idx, enable_count)
+);
+DEFINE_EVENT(dpu_core_irq_idx_cnt_template, dpu_core_irq_disable_idx,
+	TP_PROTO(int irq_idx, int enable_count),
+	TP_ARGS(irq_idx, enable_count)
+);
+
+DECLARE_EVENT_CLASS(dpu_core_irq_callback_template,
+	TP_PROTO(int irq_idx, struct dpu_irq_callback *callback),
+	TP_ARGS(irq_idx, callback),
+	TP_STRUCT__entry(
+		__field(	int,				irq_idx	)
+		__field(	struct dpu_irq_callback *,	callback)
+	),
+	TP_fast_assign(
+		__entry->irq_idx = irq_idx;
+		__entry->callback = callback;
+	),
+	TP_printk("irq_idx:%d callback:%pK", __entry->irq_idx,
+		  __entry->callback)
+);
+DEFINE_EVENT(dpu_core_irq_callback_template, dpu_core_irq_register_callback,
+	TP_PROTO(int irq_idx, struct dpu_irq_callback *callback),
+	TP_ARGS(irq_idx, callback)
+);
+DEFINE_EVENT(dpu_core_irq_callback_template, dpu_core_irq_unregister_callback,
+	TP_PROTO(int irq_idx, struct dpu_irq_callback *callback),
+	TP_ARGS(irq_idx, callback)
+);
+
+TRACE_EVENT(dpu_core_perf_update_clk,
+	TP_PROTO(struct drm_device *dev, bool stop_req, u64 clk_rate),
+	TP_ARGS(dev, stop_req, clk_rate),
+	TP_STRUCT__entry(
+		__field(	struct drm_device *,	dev		)
+		__field(	bool,			stop_req	)
+		__field(	u64,			clk_rate	)
+	),
+	TP_fast_assign(
+		__entry->dev = dev;
+		__entry->stop_req = stop_req;
+		__entry->clk_rate = clk_rate;
+	),
+	TP_printk("dev:%s stop_req:%s clk_rate:%llu", __entry->dev->unique,
+		  __entry->stop_req ? "true" : "false", __entry->clk_rate)
+);
+
+#define DPU_ATRACE_END(name) trace_tracing_mark_write(current->tgid, name, 0)
+#define DPU_ATRACE_BEGIN(name) trace_tracing_mark_write(current->tgid, name, 1)
+#define DPU_ATRACE_FUNC() DPU_ATRACE_BEGIN(__func__)
+
+#define DPU_ATRACE_INT(name, value) \
+	trace_dpu_trace_counter(current->tgid, name, value)
+
+#endif /* _DPU_TRACE_H_ */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#include <trace/define_trace.h>
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
new file mode 100644
index 000000000000..295528292296
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
@@ -0,0 +1,384 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/debugfs.h>
+
+#include "dpu_vbif.h"
+#include "dpu_hw_vbif.h"
+#include "dpu_trace.h"
+
+/**
+ * _dpu_vbif_wait_for_xin_halt - wait for the xin to halt
+ * @vbif:	Pointer to hardware vbif driver
+ * @xin_id:	Client interface identifier
+ * @return:	0 if success; error code otherwise
+ */
+static int _dpu_vbif_wait_for_xin_halt(struct dpu_hw_vbif *vbif, u32 xin_id)
+{
+	ktime_t timeout;
+	bool status;
+	int rc;
+
+	if (!vbif || !vbif->cap || !vbif->ops.get_halt_ctrl) {
+		DPU_ERROR("invalid arguments vbif %d\n", vbif != 0);
+		return -EINVAL;
+	}
+
+	timeout = ktime_add_us(ktime_get(), vbif->cap->xin_halt_timeout);
+	for (;;) {
+		status = vbif->ops.get_halt_ctrl(vbif, xin_id);
+		if (status)
+			break;
+		if (ktime_compare_safe(ktime_get(), timeout) > 0) {
+			status = vbif->ops.get_halt_ctrl(vbif, xin_id);
+			break;
+		}
+		usleep_range(501, 1000);
+	}
+
+	if (!status) {
+		rc = -ETIMEDOUT;
+		DPU_ERROR("VBIF %d client %d not halting. TIMEDOUT.\n",
+				vbif->idx - VBIF_0, xin_id);
+	} else {
+		rc = 0;
+		DPU_DEBUG("VBIF %d client %d is halted\n",
+				vbif->idx - VBIF_0, xin_id);
+	}
+
+	return rc;
+}
+
+/**
+ * _dpu_vbif_apply_dynamic_ot_limit - determine OT based on usecase parameters
+ * @vbif:	Pointer to hardware vbif driver
+ * @ot_lim:	Pointer to OT limit to be modified
+ * @params:	Pointer to usecase parameters
+ */
+static void _dpu_vbif_apply_dynamic_ot_limit(struct dpu_hw_vbif *vbif,
+		u32 *ot_lim, struct dpu_vbif_set_ot_params *params)
+{
+	u64 pps;
+	const struct dpu_vbif_dynamic_ot_tbl *tbl;
+	u32 i;
+
+	if (!vbif || !(vbif->cap->features & BIT(DPU_VBIF_QOS_OTLIM)))
+		return;
+
+	/* Dynamic OT setting done only for WFD */
+	if (!params->is_wfd)
+		return;
+
+	pps = params->frame_rate;
+	pps *= params->width;
+	pps *= params->height;
+
+	tbl = params->rd ? &vbif->cap->dynamic_ot_rd_tbl :
+			&vbif->cap->dynamic_ot_wr_tbl;
+
+	for (i = 0; i < tbl->count; i++) {
+		if (pps <= tbl->cfg[i].pps) {
+			*ot_lim = tbl->cfg[i].ot_limit;
+			break;
+		}
+	}
+
+	DPU_DEBUG("vbif:%d xin:%d w:%d h:%d fps:%d pps:%llu ot:%u\n",
+			vbif->idx - VBIF_0, params->xin_id,
+			params->width, params->height, params->frame_rate,
+			pps, *ot_lim);
+}
+
+/**
+ * _dpu_vbif_get_ot_limit - get OT based on usecase & configuration parameters
+ * @vbif:	Pointer to hardware vbif driver
+ * @params:	Pointer to usecase parameters
+ * @return:	OT limit
+ */
+static u32 _dpu_vbif_get_ot_limit(struct dpu_hw_vbif *vbif,
+	struct dpu_vbif_set_ot_params *params)
+{
+	u32 ot_lim = 0;
+	u32 val;
+
+	if (!vbif || !vbif->cap) {
+		DPU_ERROR("invalid arguments vbif %d\n", vbif != 0);
+		return -EINVAL;
+	}
+
+	if (vbif->cap->default_ot_wr_limit && !params->rd)
+		ot_lim = vbif->cap->default_ot_wr_limit;
+	else if (vbif->cap->default_ot_rd_limit && params->rd)
+		ot_lim = vbif->cap->default_ot_rd_limit;
+
+	/*
+	 * If default ot is not set from dt/catalog,
+	 * then do not configure it.
+	 */
+	if (ot_lim == 0)
+		goto exit;
+
+	/* Modify the limits if the target and the use case requires it */
+	_dpu_vbif_apply_dynamic_ot_limit(vbif, &ot_lim, params);
+
+	if (vbif && vbif->ops.get_limit_conf) {
+		val = vbif->ops.get_limit_conf(vbif,
+				params->xin_id, params->rd);
+		if (val == ot_lim)
+			ot_lim = 0;
+	}
+
+exit:
+	DPU_DEBUG("vbif:%d xin:%d ot_lim:%d\n",
+			vbif->idx - VBIF_0, params->xin_id, ot_lim);
+	return ot_lim;
+}
+
+/**
+ * dpu_vbif_set_ot_limit - set OT based on usecase & configuration parameters
+ * @vbif:	Pointer to hardware vbif driver
+ * @params:	Pointer to usecase parameters
+ *
+ * Note this function would block waiting for bus halt.
+ */
+void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms,
+		struct dpu_vbif_set_ot_params *params)
+{
+	struct dpu_hw_vbif *vbif = NULL;
+	struct dpu_hw_mdp *mdp;
+	bool forced_on = false;
+	u32 ot_lim;
+	int ret, i;
+
+	if (!dpu_kms) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	}
+	mdp = dpu_kms->hw_mdp;
+
+	for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) {
+		if (dpu_kms->hw_vbif[i] &&
+				dpu_kms->hw_vbif[i]->idx == params->vbif_idx)
+			vbif = dpu_kms->hw_vbif[i];
+	}
+
+	if (!vbif || !mdp) {
+		DPU_DEBUG("invalid arguments vbif %d mdp %d\n",
+				vbif != 0, mdp != 0);
+		return;
+	}
+
+	if (!mdp->ops.setup_clk_force_ctrl ||
+			!vbif->ops.set_limit_conf ||
+			!vbif->ops.set_halt_ctrl)
+		return;
+
+	/* set write_gather_en for all write clients */
+	if (vbif->ops.set_write_gather_en && !params->rd)
+		vbif->ops.set_write_gather_en(vbif, params->xin_id);
+
+	ot_lim = _dpu_vbif_get_ot_limit(vbif, params) & 0xFF;
+
+	if (ot_lim == 0)
+		goto exit;
+
+	trace_dpu_perf_set_ot(params->num, params->xin_id, ot_lim,
+		params->vbif_idx);
+
+	forced_on = mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, true);
+
+	vbif->ops.set_limit_conf(vbif, params->xin_id, params->rd, ot_lim);
+
+	vbif->ops.set_halt_ctrl(vbif, params->xin_id, true);
+
+	ret = _dpu_vbif_wait_for_xin_halt(vbif, params->xin_id);
+	if (ret)
+		trace_dpu_vbif_wait_xin_halt_fail(vbif->idx, params->xin_id);
+
+	vbif->ops.set_halt_ctrl(vbif, params->xin_id, false);
+
+	if (forced_on)
+		mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, false);
+exit:
+	return;
+}
+
+void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms,
+		struct dpu_vbif_set_qos_params *params)
+{
+	struct dpu_hw_vbif *vbif = NULL;
+	struct dpu_hw_mdp *mdp;
+	bool forced_on = false;
+	const struct dpu_vbif_qos_tbl *qos_tbl;
+	int i;
+
+	if (!dpu_kms || !params || !dpu_kms->hw_mdp) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	}
+	mdp = dpu_kms->hw_mdp;
+
+	for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) {
+		if (dpu_kms->hw_vbif[i] &&
+				dpu_kms->hw_vbif[i]->idx == params->vbif_idx) {
+			vbif = dpu_kms->hw_vbif[i];
+			break;
+		}
+	}
+
+	if (!vbif || !vbif->cap) {
+		DPU_ERROR("invalid vbif %d\n", params->vbif_idx);
+		return;
+	}
+
+	if (!vbif->ops.set_qos_remap || !mdp->ops.setup_clk_force_ctrl) {
+		DPU_DEBUG("qos remap not supported\n");
+		return;
+	}
+
+	qos_tbl = params->is_rt ? &vbif->cap->qos_rt_tbl :
+			&vbif->cap->qos_nrt_tbl;
+
+	if (!qos_tbl->npriority_lvl || !qos_tbl->priority_lvl) {
+		DPU_DEBUG("qos tbl not defined\n");
+		return;
+	}
+
+	forced_on = mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, true);
+
+	for (i = 0; i < qos_tbl->npriority_lvl; i++) {
+		DPU_DEBUG("vbif:%d xin:%d lvl:%d/%d\n",
+				params->vbif_idx, params->xin_id, i,
+				qos_tbl->priority_lvl[i]);
+		vbif->ops.set_qos_remap(vbif, params->xin_id, i,
+				qos_tbl->priority_lvl[i]);
+	}
+
+	if (forced_on)
+		mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, false);
+}
+
+void dpu_vbif_clear_errors(struct dpu_kms *dpu_kms)
+{
+	struct dpu_hw_vbif *vbif;
+	u32 i, pnd, src;
+
+	if (!dpu_kms) {
+		DPU_ERROR("invalid argument\n");
+		return;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) {
+		vbif = dpu_kms->hw_vbif[i];
+		if (vbif && vbif->ops.clear_errors) {
+			vbif->ops.clear_errors(vbif, &pnd, &src);
+			if (pnd || src) {
+				DRM_DEBUG_KMS("VBIF %d: pnd 0x%X, src 0x%X\n",
+					      vbif->idx - VBIF_0, pnd, src);
+			}
+		}
+	}
+}
+
+void dpu_vbif_init_memtypes(struct dpu_kms *dpu_kms)
+{
+	struct dpu_hw_vbif *vbif;
+	int i, j;
+
+	if (!dpu_kms) {
+		DPU_ERROR("invalid argument\n");
+		return;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) {
+		vbif = dpu_kms->hw_vbif[i];
+		if (vbif && vbif->cap && vbif->ops.set_mem_type) {
+			for (j = 0; j < vbif->cap->memtype_count; j++)
+				vbif->ops.set_mem_type(
+						vbif, j, vbif->cap->memtype[j]);
+		}
+	}
+}
+
+#ifdef CONFIG_DEBUG_FS
+void dpu_debugfs_vbif_destroy(struct dpu_kms *dpu_kms)
+{
+	debugfs_remove_recursive(dpu_kms->debugfs_vbif);
+	dpu_kms->debugfs_vbif = NULL;
+}
+
+int dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root)
+{
+	char vbif_name[32];
+	struct dentry *debugfs_vbif;
+	int i, j;
+
+	dpu_kms->debugfs_vbif = debugfs_create_dir("vbif", debugfs_root);
+	if (!dpu_kms->debugfs_vbif) {
+		DPU_ERROR("failed to create vbif debugfs\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < dpu_kms->catalog->vbif_count; i++) {
+		struct dpu_vbif_cfg *vbif = &dpu_kms->catalog->vbif[i];
+
+		snprintf(vbif_name, sizeof(vbif_name), "%d", vbif->id);
+
+		debugfs_vbif = debugfs_create_dir(vbif_name,
+				dpu_kms->debugfs_vbif);
+
+		debugfs_create_u32("features", 0600, debugfs_vbif,
+			(u32 *)&vbif->features);
+
+		debugfs_create_u32("xin_halt_timeout", 0400, debugfs_vbif,
+			(u32 *)&vbif->xin_halt_timeout);
+
+		debugfs_create_u32("default_rd_ot_limit", 0400, debugfs_vbif,
+			(u32 *)&vbif->default_ot_rd_limit);
+
+		debugfs_create_u32("default_wr_ot_limit", 0400, debugfs_vbif,
+			(u32 *)&vbif->default_ot_wr_limit);
+
+		for (j = 0; j < vbif->dynamic_ot_rd_tbl.count; j++) {
+			struct dpu_vbif_dynamic_ot_cfg *cfg =
+					&vbif->dynamic_ot_rd_tbl.cfg[j];
+
+			snprintf(vbif_name, sizeof(vbif_name),
+					"dynamic_ot_rd_%d_pps", j);
+			debugfs_create_u64(vbif_name, 0400, debugfs_vbif,
+					(u64 *)&cfg->pps);
+			snprintf(vbif_name, sizeof(vbif_name),
+					"dynamic_ot_rd_%d_ot_limit", j);
+			debugfs_create_u32(vbif_name, 0400, debugfs_vbif,
+					(u32 *)&cfg->ot_limit);
+		}
+
+		for (j = 0; j < vbif->dynamic_ot_wr_tbl.count; j++) {
+			struct dpu_vbif_dynamic_ot_cfg *cfg =
+					&vbif->dynamic_ot_wr_tbl.cfg[j];
+
+			snprintf(vbif_name, sizeof(vbif_name),
+					"dynamic_ot_wr_%d_pps", j);
+			debugfs_create_u64(vbif_name, 0400, debugfs_vbif,
+					(u64 *)&cfg->pps);
+			snprintf(vbif_name, sizeof(vbif_name),
+					"dynamic_ot_wr_%d_ot_limit", j);
+			debugfs_create_u32(vbif_name, 0400, debugfs_vbif,
+					(u32 *)&cfg->ot_limit);
+		}
+	}
+
+	return 0;
+}
+#endif
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h
new file mode 100644
index 000000000000..f17af52dbbd5
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h
@@ -0,0 +1,94 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DPU_VBIF_H__
+#define __DPU_VBIF_H__
+
+#include "dpu_kms.h"
+
+struct dpu_vbif_set_ot_params {
+	u32 xin_id;
+	u32 num;
+	u32 width;
+	u32 height;
+	u32 frame_rate;
+	bool rd;
+	bool is_wfd;
+	u32 vbif_idx;
+	u32 clk_ctrl;
+};
+
+struct dpu_vbif_set_memtype_params {
+	u32 xin_id;
+	u32 vbif_idx;
+	u32 clk_ctrl;
+	bool is_cacheable;
+};
+
+/**
+ * struct dpu_vbif_set_qos_params - QoS remapper parameter
+ * @vbif_idx: vbif identifier
+ * @xin_id: client interface identifier
+ * @clk_ctrl: clock control identifier of the xin
+ * @num: pipe identifier (debug only)
+ * @is_rt: true if pipe is used in real-time use case
+ */
+struct dpu_vbif_set_qos_params {
+	u32 vbif_idx;
+	u32 xin_id;
+	u32 clk_ctrl;
+	u32 num;
+	bool is_rt;
+};
+
+/**
+ * dpu_vbif_set_ot_limit - set OT limit for vbif client
+ * @dpu_kms:	DPU handler
+ * @params:	Pointer to OT configuration parameters
+ */
+void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms,
+		struct dpu_vbif_set_ot_params *params);
+
+/**
+ * dpu_vbif_set_qos_remap - set QoS priority level remap
+ * @dpu_kms:	DPU handler
+ * @params:	Pointer to QoS configuration parameters
+ */
+void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms,
+		struct dpu_vbif_set_qos_params *params);
+
+/**
+ * dpu_vbif_clear_errors - clear any vbif errors
+ * @dpu_kms:	DPU handler
+ */
+void dpu_vbif_clear_errors(struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_vbif_init_memtypes - initialize xin memory types for vbif
+ * @dpu_kms:	DPU handler
+ */
+void dpu_vbif_init_memtypes(struct dpu_kms *dpu_kms);
+
+#ifdef CONFIG_DEBUG_FS
+int dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root);
+void dpu_debugfs_vbif_destroy(struct dpu_kms *dpu_kms);
+#else
+static inline int dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms,
+		struct dentry *debugfs_root)
+{
+	return 0;
+}
+static inline void dpu_debugfs_vbif_destroy(struct dpu_kms *dpu_kms)
+{
+}
+#endif
+#endif /* __DPU_VBIF_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h b/drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h
new file mode 100644
index 000000000000..4f12e5c534c8
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h
@@ -0,0 +1,1376 @@
+#ifndef __MEDIA_INFO_H__
+#define __MEDIA_INFO_H__
+
+#ifndef MSM_MEDIA_ALIGN
+#define MSM_MEDIA_ALIGN(__sz, __align) (((__align) & ((__align) - 1)) ?\
+	((((__sz) + (__align) - 1) / (__align)) * (__align)) :\
+	(((__sz) + (__align) - 1) & (~((__align) - 1))))
+#endif
+
+#ifndef MSM_MEDIA_ROUNDUP
+#define MSM_MEDIA_ROUNDUP(__sz, __r) (((__sz) + ((__r) - 1)) / (__r))
+#endif
+
+#ifndef MSM_MEDIA_MAX
+#define MSM_MEDIA_MAX(__a, __b) ((__a) > (__b)?(__a):(__b))
+#endif
+
+enum color_fmts {
+	/* Venus NV12:
+	 * YUV 4:2:0 image with a plane of 8 bit Y samples followed
+	 * by an interleaved U/V plane containing 8 bit 2x2 subsampled
+	 * colour difference samples.
+	 *
+	 * <-------- Y/UV_Stride -------->
+	 * <------- Width ------->
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              V
+	 * U V U V U V U V U V U V . . . .  ^
+	 * U V U V U V U V U V U V . . . .  |
+	 * U V U V U V U V U V U V . . . .  |
+	 * U V U V U V U V U V U V . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  --> Buffer size alignment
+	 *
+	 * Y_Stride : Width aligned to 128
+	 * UV_Stride : Width aligned to 128
+	 * Y_Scanlines: Height aligned to 32
+	 * UV_Scanlines: Height/2 aligned to 16
+	 * Extradata: Arbitrary (software-imposed) padding
+	 * Total size = align((Y_Stride * Y_Scanlines
+	 *          + UV_Stride * UV_Scanlines
+	 *          + max(Extradata, Y_Stride * 8), 4096)
+	 */
+	COLOR_FMT_NV12,
+
+	/* Venus NV21:
+	 * YUV 4:2:0 image with a plane of 8 bit Y samples followed
+	 * by an interleaved V/U plane containing 8 bit 2x2 subsampled
+	 * colour difference samples.
+	 *
+	 * <-------- Y/UV_Stride -------->
+	 * <------- Width ------->
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              V
+	 * V U V U V U V U V U V U . . . .  ^
+	 * V U V U V U V U V U V U . . . .  |
+	 * V U V U V U V U V U V U . . . .  |
+	 * V U V U V U V U V U V U . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  --> Padding & Buffer size alignment
+	 *
+	 * Y_Stride : Width aligned to 128
+	 * UV_Stride : Width aligned to 128
+	 * Y_Scanlines: Height aligned to 32
+	 * UV_Scanlines: Height/2 aligned to 16
+	 * Extradata: Arbitrary (software-imposed) padding
+	 * Total size = align((Y_Stride * Y_Scanlines
+	 *          + UV_Stride * UV_Scanlines
+	 *          + max(Extradata, Y_Stride * 8), 4096)
+	 */
+	COLOR_FMT_NV21,
+	/* Venus NV12_MVTB:
+	 * Two YUV 4:2:0 images/views one after the other
+	 * in a top-bottom layout, same as NV12
+	 * with a plane of 8 bit Y samples followed
+	 * by an interleaved U/V plane containing 8 bit 2x2 subsampled
+	 * colour difference samples.
+	 *
+	 *
+	 * <-------- Y/UV_Stride -------->
+	 * <------- Width ------->
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^               ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |               |
+	 * . . . . . . . . . . . . . . . .              |             View_1
+	 * . . . . . . . . . . . . . . . .              |               |
+	 * . . . . . . . . . . . . . . . .              |               |
+	 * . . . . . . . . . . . . . . . .              V               |
+	 * U V U V U V U V U V U V . . . .  ^                           |
+	 * U V U V U V U V U V U V . . . .  |                           |
+	 * U V U V U V U V U V U V . . . .  |                           |
+	 * U V U V U V U V U V U V . . . .  UV_Scanlines                |
+	 * . . . . . . . . . . . . . . . .  |                           |
+	 * . . . . . . . . . . . . . . . .  V                           V
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^               ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |               |
+	 * . . . . . . . . . . . . . . . .              |             View_2
+	 * . . . . . . . . . . . . . . . .              |               |
+	 * . . . . . . . . . . . . . . . .              |               |
+	 * . . . . . . . . . . . . . . . .              V               |
+	 * U V U V U V U V U V U V . . . .  ^                           |
+	 * U V U V U V U V U V U V . . . .  |                           |
+	 * U V U V U V U V U V U V . . . .  |                           |
+	 * U V U V U V U V U V U V . . . .  UV_Scanlines                |
+	 * . . . . . . . . . . . . . . . .  |                           |
+	 * . . . . . . . . . . . . . . . .  V                           V
+	 * . . . . . . . . . . . . . . . .  --> Buffer size alignment
+	 *
+	 * Y_Stride : Width aligned to 128
+	 * UV_Stride : Width aligned to 128
+	 * Y_Scanlines: Height aligned to 32
+	 * UV_Scanlines: Height/2 aligned to 16
+	 * View_1 begin at: 0 (zero)
+	 * View_2 begin at: Y_Stride * Y_Scanlines + UV_Stride * UV_Scanlines
+	 * Extradata: Arbitrary (software-imposed) padding
+	 * Total size = align((2*(Y_Stride * Y_Scanlines)
+	 *          + 2*(UV_Stride * UV_Scanlines) + Extradata), 4096)
+	 */
+	COLOR_FMT_NV12_MVTB,
+	/*
+	 * The buffer can be of 2 types:
+	 * (1) Venus NV12 UBWC Progressive
+	 * (2) Venus NV12 UBWC Interlaced
+	 *
+	 * (1) Venus NV12 UBWC Progressive Buffer Format:
+	 * Compressed Macro-tile format for NV12.
+	 * Contains 4 planes in the following order -
+	 * (A) Y_Meta_Plane
+	 * (B) Y_UBWC_Plane
+	 * (C) UV_Meta_Plane
+	 * (D) UV_UBWC_Plane
+	 *
+	 * Y_Meta_Plane consists of meta information to decode compressed
+	 * tile data in Y_UBWC_Plane.
+	 * Y_UBWC_Plane consists of Y data in compressed macro-tile format.
+	 * UBWC decoder block will use the Y_Meta_Plane data together with
+	 * Y_UBWC_Plane data to produce loss-less uncompressed 8 bit Y samples.
+	 *
+	 * UV_Meta_Plane consists of meta information to decode compressed
+	 * tile data in UV_UBWC_Plane.
+	 * UV_UBWC_Plane consists of UV data in compressed macro-tile format.
+	 * UBWC decoder block will use UV_Meta_Plane data together with
+	 * UV_UBWC_Plane data to produce loss-less uncompressed 8 bit 2x2
+	 * subsampled color difference samples.
+	 *
+	 * Each tile in Y_UBWC_Plane/UV_UBWC_Plane is independently decodable
+	 * and randomly accessible. There is no dependency between tiles.
+	 *
+	 * <----- Y_Meta_Stride ---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <--Compressed tile Y Stride--->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  Height      |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----- UV_Meta_Stride ---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <--Compressed tile UV Stride--->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 *
+	 * Y_Stride = align(Width, 128)
+	 * UV_Stride = align(Width, 128)
+	 * Y_Scanlines = align(Height, 32)
+	 * UV_Scanlines = align(Height/2, 16)
+	 * Y_UBWC_Plane_size = align(Y_Stride * Y_Scanlines, 4096)
+	 * UV_UBWC_Plane_size = align(UV_Stride * UV_Scanlines, 4096)
+	 * Y_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_Meta_Scanlines = align(roundup(Height, Y_TileHeight), 16)
+	 * Y_Meta_Plane_size = align(Y_Meta_Stride * Y_Meta_Scanlines, 4096)
+	 * UV_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_Meta_Scanlines = align(roundup(Height, UV_TileHeight), 16)
+	 * UV_Meta_Plane_size = align(UV_Meta_Stride * UV_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align( Y_UBWC_Plane_size + UV_UBWC_Plane_size +
+	 *           Y_Meta_Plane_size + UV_Meta_Plane_size
+	 *           + max(Extradata, Y_Stride * 48), 4096)
+	 *
+	 *
+	 * (2) Venus NV12 UBWC Interlaced Buffer Format:
+	 * Compressed Macro-tile format for NV12 interlaced.
+	 * Contains 8 planes in the following order -
+	 * (A) Y_Meta_Top_Field_Plane
+	 * (B) Y_UBWC_Top_Field_Plane
+	 * (C) UV_Meta_Top_Field_Plane
+	 * (D) UV_UBWC_Top_Field_Plane
+	 * (E) Y_Meta_Bottom_Field_Plane
+	 * (F) Y_UBWC_Bottom_Field_Plane
+	 * (G) UV_Meta_Bottom_Field_Plane
+	 * (H) UV_UBWC_Bottom_Field_Plane
+	 * Y_Meta_Top_Field_Plane consists of meta information to decode
+	 * compressed tile data for Y_UBWC_Top_Field_Plane.
+	 * Y_UBWC_Top_Field_Plane consists of Y data in compressed macro-tile
+	 * format for top field of an interlaced frame.
+	 * UBWC decoder block will use the Y_Meta_Top_Field_Plane data together
+	 * with Y_UBWC_Top_Field_Plane data to produce loss-less uncompressed
+	 * 8 bit Y samples for top field of an interlaced frame.
+	 *
+	 * UV_Meta_Top_Field_Plane consists of meta information to decode
+	 * compressed tile data in UV_UBWC_Top_Field_Plane.
+	 * UV_UBWC_Top_Field_Plane consists of UV data in compressed macro-tile
+	 * format for top field of an interlaced frame.
+	 * UBWC decoder block will use UV_Meta_Top_Field_Plane data together
+	 * with UV_UBWC_Top_Field_Plane data to produce loss-less uncompressed
+	 * 8 bit subsampled color difference samples for top field of an
+	 * interlaced frame.
+	 *
+	 * Each tile in Y_UBWC_Top_Field_Plane/UV_UBWC_Top_Field_Plane is
+	 * independently decodable and randomly accessible. There is no
+	 * dependency between tiles.
+	 *
+	 * Y_Meta_Bottom_Field_Plane consists of meta information to decode
+	 * compressed tile data for Y_UBWC_Bottom_Field_Plane.
+	 * Y_UBWC_Bottom_Field_Plane consists of Y data in compressed macro-tile
+	 * format for bottom field of an interlaced frame.
+	 * UBWC decoder block will use the Y_Meta_Bottom_Field_Plane data
+	 * together with Y_UBWC_Bottom_Field_Plane data to produce loss-less
+	 * uncompressed 8 bit Y samples for bottom field of an interlaced frame.
+	 *
+	 * UV_Meta_Bottom_Field_Plane consists of meta information to decode
+	 * compressed tile data in UV_UBWC_Bottom_Field_Plane.
+	 * UV_UBWC_Bottom_Field_Plane consists of UV data in compressed
+	 * macro-tile format for bottom field of an interlaced frame.
+	 * UBWC decoder block will use UV_Meta_Bottom_Field_Plane data together
+	 * with UV_UBWC_Bottom_Field_Plane data to produce loss-less
+	 * uncompressed 8 bit subsampled color difference samples for bottom
+	 * field of an interlaced frame.
+	 *
+	 * Each tile in Y_UBWC_Bottom_Field_Plane/UV_UBWC_Bottom_Field_Plane is
+	 * independently decodable and randomly accessible. There is no
+	 * dependency between tiles.
+	 *
+	 * <-----Y_TF_Meta_Stride---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . . Half_height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_TF_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-Compressed tile Y_TF Stride->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . . Half_height  |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_TF_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----UV_TF_Meta_Stride---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_TF_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <-Compressed tile UV_TF Stride->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_TF_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * <-----Y_BF_Meta_Stride---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . . Half_height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_BF_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-Compressed tile Y_BF Stride->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . . Half_height  |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_BF_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----UV_BF_Meta_Stride---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_BF_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <-Compressed tile UV_BF Stride->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_BF_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 *
+	 * Half_height = (Height+1)>>1
+	 * Y_TF_Stride = align(Width, 128)
+	 * UV_TF_Stride = align(Width, 128)
+	 * Y_TF_Scanlines = align(Half_height, 32)
+	 * UV_TF_Scanlines = align((Half_height+1)/2, 32)
+	 * Y_UBWC_TF_Plane_size = align(Y_TF_Stride * Y_TF_Scanlines, 4096)
+	 * UV_UBWC_TF_Plane_size = align(UV_TF_Stride * UV_TF_Scanlines, 4096)
+	 * Y_TF_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_TF_Meta_Scanlines = align(roundup(Half_height, Y_TileHeight), 16)
+	 * Y_TF_Meta_Plane_size =
+	 *     align(Y_TF_Meta_Stride * Y_TF_Meta_Scanlines, 4096)
+	 * UV_TF_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_TF_Meta_Scanlines = align(roundup(Half_height, UV_TileHeight), 16)
+	 * UV_TF_Meta_Plane_size =
+	 *     align(UV_TF_Meta_Stride * UV_TF_Meta_Scanlines, 4096)
+	 * Y_BF_Stride = align(Width, 128)
+	 * UV_BF_Stride = align(Width, 128)
+	 * Y_BF_Scanlines = align(Half_height, 32)
+	 * UV_BF_Scanlines = align((Half_height+1)/2, 32)
+	 * Y_UBWC_BF_Plane_size = align(Y_BF_Stride * Y_BF_Scanlines, 4096)
+	 * UV_UBWC_BF_Plane_size = align(UV_BF_Stride * UV_BF_Scanlines, 4096)
+	 * Y_BF_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_BF_Meta_Scanlines = align(roundup(Half_height, Y_TileHeight), 16)
+	 * Y_BF_Meta_Plane_size =
+	 *     align(Y_BF_Meta_Stride * Y_BF_Meta_Scanlines, 4096)
+	 * UV_BF_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_BF_Meta_Scanlines = align(roundup(Half_height, UV_TileHeight), 16)
+	 * UV_BF_Meta_Plane_size =
+	 *     align(UV_BF_Meta_Stride * UV_BF_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align( Y_UBWC_TF_Plane_size + UV_UBWC_TF_Plane_size +
+	 *           Y_TF_Meta_Plane_size + UV_TF_Meta_Plane_size +
+	 *			 Y_UBWC_BF_Plane_size + UV_UBWC_BF_Plane_size +
+	 *           Y_BF_Meta_Plane_size + UV_BF_Meta_Plane_size +
+	 *           + max(Extradata, Y_TF_Stride * 48), 4096)
+	 */
+	COLOR_FMT_NV12_UBWC,
+	/* Venus NV12 10-bit UBWC:
+	 * Compressed Macro-tile format for NV12.
+	 * Contains 4 planes in the following order -
+	 * (A) Y_Meta_Plane
+	 * (B) Y_UBWC_Plane
+	 * (C) UV_Meta_Plane
+	 * (D) UV_UBWC_Plane
+	 *
+	 * Y_Meta_Plane consists of meta information to decode compressed
+	 * tile data in Y_UBWC_Plane.
+	 * Y_UBWC_Plane consists of Y data in compressed macro-tile format.
+	 * UBWC decoder block will use the Y_Meta_Plane data together with
+	 * Y_UBWC_Plane data to produce loss-less uncompressed 10 bit Y samples.
+	 *
+	 * UV_Meta_Plane consists of meta information to decode compressed
+	 * tile data in UV_UBWC_Plane.
+	 * UV_UBWC_Plane consists of UV data in compressed macro-tile format.
+	 * UBWC decoder block will use UV_Meta_Plane data together with
+	 * UV_UBWC_Plane data to produce loss-less uncompressed 10 bit 2x2
+	 * subsampled color difference samples.
+	 *
+	 * Each tile in Y_UBWC_Plane/UV_UBWC_Plane is independently decodable
+	 * and randomly accessible. There is no dependency between tiles.
+	 *
+	 * <----- Y_Meta_Stride ----->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <--Compressed tile Y Stride--->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  Height      |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----- UV_Meta_Stride ---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <--Compressed tile UV Stride--->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 *
+	 *
+	 * Y_Stride = align(Width * 4/3, 128)
+	 * UV_Stride = align(Width * 4/3, 128)
+	 * Y_Scanlines = align(Height, 32)
+	 * UV_Scanlines = align(Height/2, 16)
+	 * Y_UBWC_Plane_Size = align(Y_Stride * Y_Scanlines, 4096)
+	 * UV_UBWC_Plane_Size = align(UV_Stride * UV_Scanlines, 4096)
+	 * Y_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_Meta_Scanlines = align(roundup(Height, Y_TileHeight), 16)
+	 * Y_Meta_Plane_size = align(Y_Meta_Stride * Y_Meta_Scanlines, 4096)
+	 * UV_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_Meta_Scanlines = align(roundup(Height, UV_TileHeight), 16)
+	 * UV_Meta_Plane_size = align(UV_Meta_Stride * UV_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(Y_UBWC_Plane_size + UV_UBWC_Plane_size +
+	 *           Y_Meta_Plane_size + UV_Meta_Plane_size
+	 *           + max(Extradata, Y_Stride * 48), 4096)
+	 */
+	COLOR_FMT_NV12_BPP10_UBWC,
+	/* Venus RGBA8888 format:
+	 * Contains 1 plane in the following order -
+	 * (A) RGBA plane
+	 *
+	 * <-------- RGB_Stride -------->
+	 * <------- Width ------->
+	 * R R R R R R R R R R R R . . . .  ^           ^
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  Height      |
+	 * R R R R R R R R R R R R . . . .  |       RGB_Scanlines
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              V
+	 *
+	 * RGB_Stride = align(Width * 4, 128)
+	 * RGB_Scanlines = align(Height, 32)
+	 * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(RGB_Plane_size + Extradata, 4096)
+	 */
+	COLOR_FMT_RGBA8888,
+	/* Venus RGBA8888 UBWC format:
+	 * Contains 2 planes in the following order -
+	 * (A) Meta plane
+	 * (B) RGBA plane
+	 *
+	 * <--- RGB_Meta_Stride ---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |       Meta_RGB_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-------- RGB_Stride -------->
+	 * <------- Width ------->
+	 * R R R R R R R R R R R R . . . .  ^           ^
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  Height      |
+	 * R R R R R R R R R R R R . . . .  |       RGB_Scanlines
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .    -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 *
+	 * RGB_Stride = align(Width * 4, 128)
+	 * RGB_Scanlines = align(Height, 32)
+	 * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096)
+	 * RGB_Meta_Stride = align(roundup(Width, RGB_TileWidth), 64)
+	 * RGB_Meta_Scanline = align(roundup(Height, RGB_TileHeight), 16)
+	 * RGB_Meta_Plane_size = align(RGB_Meta_Stride *
+	 *		RGB_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(RGB_Meta_Plane_size + RGB_Plane_size +
+	 *		Extradata, 4096)
+	 */
+	COLOR_FMT_RGBA8888_UBWC,
+	/* Venus RGBA1010102 UBWC format:
+	 * Contains 2 planes in the following order -
+	 * (A) Meta plane
+	 * (B) RGBA plane
+	 *
+	 * <--- RGB_Meta_Stride ---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |       Meta_RGB_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-------- RGB_Stride -------->
+	 * <------- Width ------->
+	 * R R R R R R R R R R R R . . . .  ^           ^
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  Height      |
+	 * R R R R R R R R R R R R . . . .  |       RGB_Scanlines
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .    -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 *
+	 * RGB_Stride = align(Width * 4, 256)
+	 * RGB_Scanlines = align(Height, 16)
+	 * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096)
+	 * RGB_Meta_Stride = align(roundup(Width, RGB_TileWidth), 64)
+	 * RGB_Meta_Scanline = align(roundup(Height, RGB_TileHeight), 16)
+	 * RGB_Meta_Plane_size = align(RGB_Meta_Stride *
+	 *		RGB_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(RGB_Meta_Plane_size + RGB_Plane_size +
+	 *		Extradata, 4096)
+	 */
+	COLOR_FMT_RGBA1010102_UBWC,
+	/* Venus RGB565 UBWC format:
+	 * Contains 2 planes in the following order -
+	 * (A) Meta plane
+	 * (B) RGB plane
+	 *
+	 * <--- RGB_Meta_Stride ---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |       Meta_RGB_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-------- RGB_Stride -------->
+	 * <------- Width ------->
+	 * R R R R R R R R R R R R . . . .  ^           ^
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  Height      |
+	 * R R R R R R R R R R R R . . . .  |       RGB_Scanlines
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .    -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 *
+	 * RGB_Stride = align(Width * 2, 128)
+	 * RGB_Scanlines = align(Height, 16)
+	 * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096)
+	 * RGB_Meta_Stride = align(roundup(Width, RGB_TileWidth), 64)
+	 * RGB_Meta_Scanline = align(roundup(Height, RGB_TileHeight), 16)
+	 * RGB_Meta_Plane_size = align(RGB_Meta_Stride *
+	 *		RGB_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(RGB_Meta_Plane_size + RGB_Plane_size +
+	 *		Extradata, 4096)
+	 */
+	COLOR_FMT_RGB565_UBWC,
+	/* P010 UBWC:
+	 * Compressed Macro-tile format for NV12.
+	 * Contains 4 planes in the following order -
+	 * (A) Y_Meta_Plane
+	 * (B) Y_UBWC_Plane
+	 * (C) UV_Meta_Plane
+	 * (D) UV_UBWC_Plane
+	 *
+	 * Y_Meta_Plane consists of meta information to decode compressed
+	 * tile data in Y_UBWC_Plane.
+	 * Y_UBWC_Plane consists of Y data in compressed macro-tile format.
+	 * UBWC decoder block will use the Y_Meta_Plane data together with
+	 * Y_UBWC_Plane data to produce loss-less uncompressed 10 bit Y samples.
+	 *
+	 * UV_Meta_Plane consists of meta information to decode compressed
+	 * tile data in UV_UBWC_Plane.
+	 * UV_UBWC_Plane consists of UV data in compressed macro-tile format.
+	 * UBWC decoder block will use UV_Meta_Plane data together with
+	 * UV_UBWC_Plane data to produce loss-less uncompressed 10 bit 2x2
+	 * subsampled color difference samples.
+	 *
+	 * Each tile in Y_UBWC_Plane/UV_UBWC_Plane is independently decodable
+	 * and randomly accessible. There is no dependency between tiles.
+	 *
+	 * <----- Y_Meta_Stride ----->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <--Compressed tile Y Stride--->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  Height      |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----- UV_Meta_Stride ---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <--Compressed tile UV Stride--->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 *
+	 *
+	 * Y_Stride = align(Width * 2, 256)
+	 * UV_Stride = align(Width * 2, 256)
+	 * Y_Scanlines = align(Height, 16)
+	 * UV_Scanlines = align(Height/2, 16)
+	 * Y_UBWC_Plane_Size = align(Y_Stride * Y_Scanlines, 4096)
+	 * UV_UBWC_Plane_Size = align(UV_Stride * UV_Scanlines, 4096)
+	 * Y_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_Meta_Scanlines = align(roundup(Height, Y_TileHeight), 16)
+	 * Y_Meta_Plane_size = align(Y_Meta_Stride * Y_Meta_Scanlines, 4096)
+	 * UV_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_Meta_Scanlines = align(roundup(Height, UV_TileHeight), 16)
+	 * UV_Meta_Plane_size = align(UV_Meta_Stride * UV_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(Y_UBWC_Plane_size + UV_UBWC_Plane_size +
+	 *           Y_Meta_Plane_size + UV_Meta_Plane_size
+	 *           + max(Extradata, Y_Stride * 48), 4096)
+	 */
+	COLOR_FMT_P010_UBWC,
+	/* Venus P010:
+	 * YUV 4:2:0 image with a plane of 10 bit Y samples followed
+	 * by an interleaved U/V plane containing 10 bit 2x2 subsampled
+	 * colour difference samples.
+	 *
+	 * <-------- Y/UV_Stride -------->
+	 * <------- Width ------->
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              V
+	 * U V U V U V U V U V U V . . . .  ^
+	 * U V U V U V U V U V U V . . . .  |
+	 * U V U V U V U V U V U V . . . .  |
+	 * U V U V U V U V U V U V . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  --> Buffer size alignment
+	 *
+	 * Y_Stride : Width * 2 aligned to 128
+	 * UV_Stride : Width * 2 aligned to 128
+	 * Y_Scanlines: Height aligned to 32
+	 * UV_Scanlines: Height/2 aligned to 16
+	 * Extradata: Arbitrary (software-imposed) padding
+	 * Total size = align((Y_Stride * Y_Scanlines
+	 *          + UV_Stride * UV_Scanlines
+	 *          + max(Extradata, Y_Stride * 8), 4096)
+	 */
+	COLOR_FMT_P010,
+};
+
+#define COLOR_FMT_RGBA1010102_UBWC	COLOR_FMT_RGBA1010102_UBWC
+#define COLOR_FMT_RGB565_UBWC		COLOR_FMT_RGB565_UBWC
+#define COLOR_FMT_P010_UBWC		COLOR_FMT_P010_UBWC
+#define COLOR_FMT_P010		COLOR_FMT_P010
+
+static inline unsigned int VENUS_EXTRADATA_SIZE(int width, int height)
+{
+	(void)height;
+	(void)width;
+
+	/*
+	 * In the future, calculate the size based on the w/h but just
+	 * hardcode it for now since 16K satisfies all current usecases.
+	 */
+	return 16 * 1024;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @width
+ * Progressive: width
+ * Interlaced: width
+ */
+static inline unsigned int VENUS_Y_STRIDE(int color_fmt, int width)
+{
+	unsigned int alignment, stride = 0;
+
+	if (!width)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV21:
+	case COLOR_FMT_NV12:
+	case COLOR_FMT_NV12_MVTB:
+	case COLOR_FMT_NV12_UBWC:
+		alignment = 128;
+		stride = MSM_MEDIA_ALIGN(width, alignment);
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+		alignment = 256;
+		stride = MSM_MEDIA_ALIGN(width, 192);
+		stride = MSM_MEDIA_ALIGN(stride * 4/3, alignment);
+		break;
+	case COLOR_FMT_P010_UBWC:
+		alignment = 256;
+		stride = MSM_MEDIA_ALIGN(width * 2, alignment);
+		break;
+	case COLOR_FMT_P010:
+		alignment = 128;
+		stride = MSM_MEDIA_ALIGN(width*2, alignment);
+		break;
+	default:
+		break;
+	}
+invalid_input:
+	return stride;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @width
+ * Progressive: width
+ * Interlaced: width
+ */
+static inline unsigned int VENUS_UV_STRIDE(int color_fmt, int width)
+{
+	unsigned int alignment, stride = 0;
+
+	if (!width)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV21:
+	case COLOR_FMT_NV12:
+	case COLOR_FMT_NV12_MVTB:
+	case COLOR_FMT_NV12_UBWC:
+		alignment = 128;
+		stride = MSM_MEDIA_ALIGN(width, alignment);
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+		alignment = 256;
+		stride = MSM_MEDIA_ALIGN(width, 192);
+		stride = MSM_MEDIA_ALIGN(stride * 4/3, alignment);
+		break;
+	case COLOR_FMT_P010_UBWC:
+		alignment = 256;
+		stride = MSM_MEDIA_ALIGN(width * 2, alignment);
+		break;
+	case COLOR_FMT_P010:
+		alignment = 128;
+		stride = MSM_MEDIA_ALIGN(width*2, alignment);
+		break;
+	default:
+		break;
+	}
+invalid_input:
+	return stride;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @height
+ * Progressive: height
+ * Interlaced: (height+1)>>1
+ */
+static inline unsigned int VENUS_Y_SCANLINES(int color_fmt, int height)
+{
+	unsigned int alignment, sclines = 0;
+
+	if (!height)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV21:
+	case COLOR_FMT_NV12:
+	case COLOR_FMT_NV12_MVTB:
+	case COLOR_FMT_NV12_UBWC:
+	case COLOR_FMT_P010:
+		alignment = 32;
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		alignment = 16;
+		break;
+	default:
+		return 0;
+	}
+	sclines = MSM_MEDIA_ALIGN(height, alignment);
+invalid_input:
+	return sclines;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @height
+ * Progressive: height
+ * Interlaced: (height+1)>>1
+ */
+static inline unsigned int VENUS_UV_SCANLINES(int color_fmt, int height)
+{
+	unsigned int alignment, sclines = 0;
+
+	if (!height)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV21:
+	case COLOR_FMT_NV12:
+	case COLOR_FMT_NV12_MVTB:
+	case COLOR_FMT_NV12_BPP10_UBWC:
+	case COLOR_FMT_P010_UBWC:
+	case COLOR_FMT_P010:
+		alignment = 16;
+		break;
+	case COLOR_FMT_NV12_UBWC:
+		alignment = 32;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	sclines = MSM_MEDIA_ALIGN((height+1)>>1, alignment);
+
+invalid_input:
+	return sclines;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @width
+ * Progressive: width
+ * Interlaced: width
+ */
+static inline unsigned int VENUS_Y_META_STRIDE(int color_fmt, int width)
+{
+	int y_tile_width = 0, y_meta_stride = 0;
+
+	if (!width)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV12_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		y_tile_width = 32;
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+		y_tile_width = 48;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	y_meta_stride = MSM_MEDIA_ROUNDUP(width, y_tile_width);
+	y_meta_stride = MSM_MEDIA_ALIGN(y_meta_stride, 64);
+
+invalid_input:
+	return y_meta_stride;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @height
+ * Progressive: height
+ * Interlaced: (height+1)>>1
+ */
+static inline unsigned int VENUS_Y_META_SCANLINES(int color_fmt, int height)
+{
+	int y_tile_height = 0, y_meta_scanlines = 0;
+
+	if (!height)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV12_UBWC:
+		y_tile_height = 8;
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		y_tile_height = 4;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	y_meta_scanlines = MSM_MEDIA_ROUNDUP(height, y_tile_height);
+	y_meta_scanlines = MSM_MEDIA_ALIGN(y_meta_scanlines, 16);
+
+invalid_input:
+	return y_meta_scanlines;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @width
+ * Progressive: width
+ * Interlaced: width
+ */
+static inline unsigned int VENUS_UV_META_STRIDE(int color_fmt, int width)
+{
+	int uv_tile_width = 0, uv_meta_stride = 0;
+
+	if (!width)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV12_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		uv_tile_width = 16;
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+		uv_tile_width = 24;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	uv_meta_stride = MSM_MEDIA_ROUNDUP((width+1)>>1, uv_tile_width);
+	uv_meta_stride = MSM_MEDIA_ALIGN(uv_meta_stride, 64);
+
+invalid_input:
+	return uv_meta_stride;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @height
+ * Progressive: height
+ * Interlaced: (height+1)>>1
+ */
+static inline unsigned int VENUS_UV_META_SCANLINES(int color_fmt, int height)
+{
+	int uv_tile_height = 0, uv_meta_scanlines = 0;
+
+	if (!height)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV12_UBWC:
+		uv_tile_height = 8;
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		uv_tile_height = 4;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	uv_meta_scanlines = MSM_MEDIA_ROUNDUP((height+1)>>1, uv_tile_height);
+	uv_meta_scanlines = MSM_MEDIA_ALIGN(uv_meta_scanlines, 16);
+
+invalid_input:
+	return uv_meta_scanlines;
+}
+
+static inline unsigned int VENUS_RGB_STRIDE(int color_fmt, int width)
+{
+	unsigned int alignment = 0, stride = 0, bpp = 4;
+
+	if (!width)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_RGBA8888:
+		alignment = 128;
+		break;
+	case COLOR_FMT_RGB565_UBWC:
+		alignment = 256;
+		bpp = 2;
+		break;
+	case COLOR_FMT_RGBA8888_UBWC:
+	case COLOR_FMT_RGBA1010102_UBWC:
+		alignment = 256;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	stride = MSM_MEDIA_ALIGN(width * bpp, alignment);
+
+invalid_input:
+	return stride;
+}
+
+static inline unsigned int VENUS_RGB_SCANLINES(int color_fmt, int height)
+{
+	unsigned int alignment = 0, scanlines = 0;
+
+	if (!height)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_RGBA8888:
+		alignment = 32;
+		break;
+	case COLOR_FMT_RGBA8888_UBWC:
+	case COLOR_FMT_RGBA1010102_UBWC:
+	case COLOR_FMT_RGB565_UBWC:
+		alignment = 16;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	scanlines = MSM_MEDIA_ALIGN(height, alignment);
+
+invalid_input:
+	return scanlines;
+}
+
+static inline unsigned int VENUS_RGB_META_STRIDE(int color_fmt, int width)
+{
+	int rgb_tile_width = 0, rgb_meta_stride = 0;
+
+	if (!width)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_RGBA8888_UBWC:
+	case COLOR_FMT_RGBA1010102_UBWC:
+	case COLOR_FMT_RGB565_UBWC:
+		rgb_tile_width = 16;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	rgb_meta_stride = MSM_MEDIA_ROUNDUP(width, rgb_tile_width);
+	rgb_meta_stride = MSM_MEDIA_ALIGN(rgb_meta_stride, 64);
+
+invalid_input:
+	return rgb_meta_stride;
+}
+
+static inline unsigned int VENUS_RGB_META_SCANLINES(int color_fmt, int height)
+{
+	int rgb_tile_height = 0, rgb_meta_scanlines = 0;
+
+	if (!height)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_RGBA8888_UBWC:
+	case COLOR_FMT_RGBA1010102_UBWC:
+	case COLOR_FMT_RGB565_UBWC:
+		rgb_tile_height = 4;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	rgb_meta_scanlines = MSM_MEDIA_ROUNDUP(height, rgb_tile_height);
+	rgb_meta_scanlines = MSM_MEDIA_ALIGN(rgb_meta_scanlines, 16);
+
+invalid_input:
+	return rgb_meta_scanlines;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @width
+ * Progressive: width
+ * Interlaced: width
+ * @height
+ * Progressive: height
+ * Interlaced: height
+ */
+static inline unsigned int VENUS_BUFFER_SIZE(
+	int color_fmt, int width, int height)
+{
+	const unsigned int extra_size = VENUS_EXTRADATA_SIZE(width, height);
+	unsigned int uv_alignment = 0, size = 0;
+	unsigned int y_plane, uv_plane, y_stride,
+		uv_stride, y_sclines, uv_sclines;
+	unsigned int y_ubwc_plane = 0, uv_ubwc_plane = 0;
+	unsigned int y_meta_stride = 0, y_meta_scanlines = 0;
+	unsigned int uv_meta_stride = 0, uv_meta_scanlines = 0;
+	unsigned int y_meta_plane = 0, uv_meta_plane = 0;
+	unsigned int rgb_stride = 0, rgb_scanlines = 0;
+	unsigned int rgb_plane = 0, rgb_ubwc_plane = 0, rgb_meta_plane = 0;
+	unsigned int rgb_meta_stride = 0, rgb_meta_scanlines = 0;
+
+	if (!width || !height)
+		goto invalid_input;
+
+	y_stride = VENUS_Y_STRIDE(color_fmt, width);
+	uv_stride = VENUS_UV_STRIDE(color_fmt, width);
+	y_sclines = VENUS_Y_SCANLINES(color_fmt, height);
+	uv_sclines = VENUS_UV_SCANLINES(color_fmt, height);
+	rgb_stride = VENUS_RGB_STRIDE(color_fmt, width);
+	rgb_scanlines = VENUS_RGB_SCANLINES(color_fmt, height);
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV21:
+	case COLOR_FMT_NV12:
+	case COLOR_FMT_P010:
+		uv_alignment = 4096;
+		y_plane = y_stride * y_sclines;
+		uv_plane = uv_stride * uv_sclines + uv_alignment;
+		size = y_plane + uv_plane +
+				MSM_MEDIA_MAX(extra_size, 8 * y_stride);
+		size = MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	case COLOR_FMT_NV12_MVTB:
+		uv_alignment = 4096;
+		y_plane = y_stride * y_sclines;
+		uv_plane = uv_stride * uv_sclines + uv_alignment;
+		size = y_plane + uv_plane;
+		size = 2 * size + extra_size;
+		size = MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	case COLOR_FMT_NV12_UBWC:
+		y_sclines = VENUS_Y_SCANLINES(color_fmt, (height+1)>>1);
+		y_ubwc_plane = MSM_MEDIA_ALIGN(y_stride * y_sclines, 4096);
+		uv_sclines = VENUS_UV_SCANLINES(color_fmt, (height+1)>>1);
+		uv_ubwc_plane = MSM_MEDIA_ALIGN(uv_stride * uv_sclines, 4096);
+		y_meta_stride = VENUS_Y_META_STRIDE(color_fmt, width);
+		y_meta_scanlines =
+			VENUS_Y_META_SCANLINES(color_fmt, (height+1)>>1);
+		y_meta_plane = MSM_MEDIA_ALIGN(
+			y_meta_stride * y_meta_scanlines, 4096);
+		uv_meta_stride = VENUS_UV_META_STRIDE(color_fmt, width);
+		uv_meta_scanlines =
+			VENUS_UV_META_SCANLINES(color_fmt, (height+1)>>1);
+		uv_meta_plane = MSM_MEDIA_ALIGN(uv_meta_stride *
+			uv_meta_scanlines, 4096);
+
+		size = (y_ubwc_plane + uv_ubwc_plane + y_meta_plane +
+			uv_meta_plane)*2 +
+			MSM_MEDIA_MAX(extra_size + 8192, 48 * y_stride);
+		size = MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+		y_ubwc_plane = MSM_MEDIA_ALIGN(y_stride * y_sclines, 4096);
+		uv_ubwc_plane = MSM_MEDIA_ALIGN(uv_stride * uv_sclines, 4096);
+		y_meta_stride = VENUS_Y_META_STRIDE(color_fmt, width);
+		y_meta_scanlines = VENUS_Y_META_SCANLINES(color_fmt, height);
+		y_meta_plane = MSM_MEDIA_ALIGN(
+				y_meta_stride * y_meta_scanlines, 4096);
+		uv_meta_stride = VENUS_UV_META_STRIDE(color_fmt, width);
+		uv_meta_scanlines = VENUS_UV_META_SCANLINES(color_fmt, height);
+		uv_meta_plane = MSM_MEDIA_ALIGN(uv_meta_stride *
+					uv_meta_scanlines, 4096);
+
+		size = y_ubwc_plane + uv_ubwc_plane + y_meta_plane +
+			uv_meta_plane +
+			MSM_MEDIA_MAX(extra_size + 8192, 48 * y_stride);
+		size = MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	case COLOR_FMT_P010_UBWC:
+		y_ubwc_plane = MSM_MEDIA_ALIGN(y_stride * y_sclines, 4096);
+		uv_ubwc_plane = MSM_MEDIA_ALIGN(uv_stride * uv_sclines, 4096);
+		y_meta_stride = VENUS_Y_META_STRIDE(color_fmt, width);
+		y_meta_scanlines = VENUS_Y_META_SCANLINES(color_fmt, height);
+		y_meta_plane = MSM_MEDIA_ALIGN(
+				y_meta_stride * y_meta_scanlines, 4096);
+		uv_meta_stride = VENUS_UV_META_STRIDE(color_fmt, width);
+		uv_meta_scanlines = VENUS_UV_META_SCANLINES(color_fmt, height);
+		uv_meta_plane = MSM_MEDIA_ALIGN(uv_meta_stride *
+					uv_meta_scanlines, 4096);
+
+		size = y_ubwc_plane + uv_ubwc_plane + y_meta_plane +
+			uv_meta_plane;
+		size = MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	case COLOR_FMT_RGBA8888:
+		rgb_plane = MSM_MEDIA_ALIGN(rgb_stride  * rgb_scanlines, 4096);
+		size = rgb_plane;
+		size =  MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	case COLOR_FMT_RGBA8888_UBWC:
+	case COLOR_FMT_RGBA1010102_UBWC:
+	case COLOR_FMT_RGB565_UBWC:
+		rgb_ubwc_plane = MSM_MEDIA_ALIGN(rgb_stride * rgb_scanlines,
+							4096);
+		rgb_meta_stride = VENUS_RGB_META_STRIDE(color_fmt, width);
+		rgb_meta_scanlines = VENUS_RGB_META_SCANLINES(color_fmt,
+					height);
+		rgb_meta_plane = MSM_MEDIA_ALIGN(rgb_meta_stride *
+					rgb_meta_scanlines, 4096);
+		size = rgb_ubwc_plane + rgb_meta_plane;
+		size = MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	default:
+		break;
+	}
+invalid_input:
+	return size;
+}
+
+static inline unsigned int VENUS_VIEW2_OFFSET(
+	int color_fmt, int width, int height)
+{
+	unsigned int offset = 0;
+	unsigned int y_plane, uv_plane, y_stride,
+		uv_stride, y_sclines, uv_sclines;
+	if (!width || !height)
+		goto invalid_input;
+
+	y_stride = VENUS_Y_STRIDE(color_fmt, width);
+	uv_stride = VENUS_UV_STRIDE(color_fmt, width);
+	y_sclines = VENUS_Y_SCANLINES(color_fmt, height);
+	uv_sclines = VENUS_UV_SCANLINES(color_fmt, height);
+	switch (color_fmt) {
+	case COLOR_FMT_NV12_MVTB:
+		y_plane = y_stride * y_sclines;
+		uv_plane = uv_stride * uv_sclines;
+		offset = y_plane + uv_plane;
+		break;
+	default:
+		break;
+	}
+invalid_input:
+	return offset;
+}
+
+#endif
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c
index b001699297c4..457c29dba4a1 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c
@@ -201,7 +201,7 @@ static void blend_setup(struct drm_crtc *crtc)
 		int idx = idxs[pipe_id];
 		if (idx > 0) {
 			const struct mdp_format *format =
-					to_mdp_format(msm_framebuffer_format(plane->fb));
+					to_mdp_format(msm_framebuffer_format(plane->state->fb));
 			alpha[idx-1] = format->alpha_enable;
 		}
 	}
@@ -665,7 +665,6 @@ struct drm_crtc *mdp4_crtc_init(struct drm_device *dev,
 	drm_crtc_init_with_planes(dev, crtc, plane, NULL, &mdp4_crtc_funcs,
 				  NULL);
 	drm_crtc_helper_add(crtc, &mdp4_crtc_helper_funcs);
-	plane->crtc = crtc;
 
 	return crtc;
 }
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
index 4b646bf9c214..44d1cda56974 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
@@ -125,6 +125,8 @@ static void mdp4_complete_commit(struct msm_kms *kms, struct drm_atomic_state *s
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
 
+	drm_atomic_helper_wait_for_vblanks(mdp4_kms->dev, state);
+
 	/* see 119ecb7fd */
 	for_each_new_crtc_in_state(state, crtc, crtc_state, i)
 		drm_crtc_vblank_put(crtc);
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c
index 4a645926edb7..2bfb39082f54 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c
@@ -341,7 +341,7 @@ static void mdp4_lcdc_encoder_disable(struct drm_encoder *encoder)
 	mdp4_write(mdp4_kms, REG_MDP4_LCDC_ENABLE, 0);
 
 	panel = of_drm_find_panel(mdp4_lcdc_encoder->panel_node);
-	if (panel) {
+	if (!IS_ERR(panel)) {
 		drm_panel_disable(panel);
 		drm_panel_unprepare(panel);
 	}
@@ -410,7 +410,7 @@ static void mdp4_lcdc_encoder_enable(struct drm_encoder *encoder)
 		dev_err(dev->dev, "failed to enable lcdc_clk: %d\n", ret);
 
 	panel = of_drm_find_panel(mdp4_lcdc_encoder->panel_node);
-	if (panel) {
+	if (!IS_ERR(panel)) {
 		drm_panel_prepare(panel);
 		drm_panel_enable(panel);
 	}
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
index e3b1c86b7aae..5368e621999c 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
@@ -34,9 +34,12 @@ static enum drm_connector_status mdp4_lvds_connector_detect(
 	struct mdp4_lvds_connector *mdp4_lvds_connector =
 			to_mdp4_lvds_connector(connector);
 
-	if (!mdp4_lvds_connector->panel)
+	if (!mdp4_lvds_connector->panel) {
 		mdp4_lvds_connector->panel =
 			of_drm_find_panel(mdp4_lvds_connector->panel_node);
+		if (IS_ERR(mdp4_lvds_connector->panel))
+			mdp4_lvds_connector->panel = NULL;
+	}
 
 	return mdp4_lvds_connector->panel ?
 			connector_status_connected :
@@ -129,7 +132,7 @@ struct drm_connector *mdp4_lvds_connector_init(struct drm_device *dev,
 	connector->interlace_allowed = 0;
 	connector->doublescan_allowed = 0;
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return connector;
 }
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
index 20e956e14c21..79ff653d8081 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
@@ -68,7 +68,7 @@ static void mdp4_plane_destroy(struct drm_plane *plane)
 {
 	struct mdp4_plane *mdp4_plane = to_mdp4_plane(plane);
 
-	drm_plane_helper_disable(plane);
+	drm_plane_helper_disable(plane, NULL);
 	drm_plane_cleanup(plane);
 
 	kfree(mdp4_plane);
@@ -167,8 +167,6 @@ static void mdp4_plane_set_scanout(struct drm_plane *plane,
 			msm_framebuffer_iova(fb, kms->aspace, 2));
 	mdp4_write(mdp4_kms, REG_MDP4_PIPE_SRCP3_BASE(pipe),
 			msm_framebuffer_iova(fb, kms->aspace, 3));
-
-	plane->fb = fb;
 }
 
 static void mdp4_write_csc_config(struct mdp4_kms *mdp4_kms,
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index 10271359789e..b1da9ce54379 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -65,7 +65,7 @@ struct mdp5_crtc {
 		struct drm_gem_object *scanout_bo;
 		uint64_t iova;
 		uint32_t width, height;
-		uint32_t x, y;
+		int x, y;
 	} cursor;
 };
 #define to_mdp5_crtc(x) container_of(x, struct mdp5_crtc, base)
@@ -760,20 +760,31 @@ static void get_roi(struct drm_crtc *crtc, uint32_t *roi_w, uint32_t *roi_h)
 	 * Cursor Region Of Interest (ROI) is a plane read from cursor
 	 * buffer to render. The ROI region is determined by the visibility of
 	 * the cursor point. In the default Cursor image the cursor point will
-	 * be at the top left of the cursor image, unless it is specified
-	 * otherwise using hotspot feature.
+	 * be at the top left of the cursor image.
 	 *
+	 * Without rotation:
 	 * If the cursor point reaches the right (xres - x < cursor.width) or
 	 * bottom (yres - y < cursor.height) boundary of the screen, then ROI
 	 * width and ROI height need to be evaluated to crop the cursor image
 	 * accordingly.
 	 * (xres-x) will be new cursor width when x > (xres - cursor.width)
 	 * (yres-y) will be new cursor height when y > (yres - cursor.height)
+	 *
+	 * With rotation:
+	 * We get negative x and/or y coordinates.
+	 * (cursor.width - abs(x)) will be new cursor width when x < 0
+	 * (cursor.height - abs(y)) will be new cursor width when y < 0
 	 */
-	*roi_w = min(mdp5_crtc->cursor.width, xres -
+	if (mdp5_crtc->cursor.x >= 0)
+		*roi_w = min(mdp5_crtc->cursor.width, xres -
 			mdp5_crtc->cursor.x);
-	*roi_h = min(mdp5_crtc->cursor.height, yres -
+	else
+		*roi_w = mdp5_crtc->cursor.width - abs(mdp5_crtc->cursor.x);
+	if (mdp5_crtc->cursor.y >= 0)
+		*roi_h = min(mdp5_crtc->cursor.height, yres -
 			mdp5_crtc->cursor.y);
+	else
+		*roi_h = mdp5_crtc->cursor.height - abs(mdp5_crtc->cursor.y);
 }
 
 static void mdp5_crtc_restore_cursor(struct drm_crtc *crtc)
@@ -783,7 +794,7 @@ static void mdp5_crtc_restore_cursor(struct drm_crtc *crtc)
 	struct mdp5_kms *mdp5_kms = get_kms(crtc);
 	const enum mdp5_cursor_alpha cur_alpha = CURSOR_ALPHA_PER_PIXEL;
 	uint32_t blendcfg, stride;
-	uint32_t x, y, width, height;
+	uint32_t x, y, src_x, src_y, width, height;
 	uint32_t roi_w, roi_h;
 	int lm;
 
@@ -800,6 +811,26 @@ static void mdp5_crtc_restore_cursor(struct drm_crtc *crtc)
 
 	get_roi(crtc, &roi_w, &roi_h);
 
+	/* If cusror buffer overlaps due to rotation on the
+	 * upper or left screen border the pixel offset inside
+	 * the cursor buffer of the ROI is the positive overlap
+	 * distance.
+	 */
+	if (mdp5_crtc->cursor.x < 0) {
+		src_x = abs(mdp5_crtc->cursor.x);
+		x = 0;
+	} else {
+		src_x = 0;
+	}
+	if (mdp5_crtc->cursor.y < 0) {
+		src_y = abs(mdp5_crtc->cursor.y);
+		y = 0;
+	} else {
+		src_y = 0;
+	}
+	DBG("%s: x=%d, y=%d roi_w=%d roi_h=%d src_x=%d src_y=%d",
+		crtc->name, x, y, roi_w, roi_h, src_x, src_y);
+
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_STRIDE(lm), stride);
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_FORMAT(lm),
 			MDP5_LM_CURSOR_FORMAT_FORMAT(CURSOR_FMT_ARGB8888));
@@ -812,6 +843,9 @@ static void mdp5_crtc_restore_cursor(struct drm_crtc *crtc)
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_START_XY(lm),
 			MDP5_LM_CURSOR_START_XY_Y_START(y) |
 			MDP5_LM_CURSOR_START_XY_X_START(x));
+	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_XY(lm),
+			MDP5_LM_CURSOR_XY_SRC_Y(src_y) |
+			MDP5_LM_CURSOR_XY_SRC_X(src_x));
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_BASE_ADDR(lm),
 			mdp5_crtc->cursor.iova);
 
@@ -932,8 +966,9 @@ static int mdp5_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
 	if (unlikely(!crtc->state->enable))
 		return 0;
 
-	mdp5_crtc->cursor.x = x = max(x, 0);
-	mdp5_crtc->cursor.y = y = max(y, 0);
+	/* accept negative x/y coordinates up to maximum cursor overlap */
+	mdp5_crtc->cursor.x = x = max(x, -(int)mdp5_crtc->cursor.width);
+	mdp5_crtc->cursor.y = y = max(y, -(int)mdp5_crtc->cursor.height);
 
 	get_roi(crtc, &roi_w, &roi_h);
 
@@ -1207,7 +1242,6 @@ struct drm_crtc *mdp5_crtc_init(struct drm_device *dev,
 			"unref cursor", unref_cursor_worker);
 
 	drm_crtc_helper_add(crtc, &mdp5_crtc_helper_funcs);
-	plane->crtc = crtc;
 
 	return crtc;
 }
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c
index 9af94e35f678..fcd44d1d1068 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c
@@ -319,7 +319,17 @@ static int mdp5_encoder_atomic_check(struct drm_encoder *encoder,
 
 	mdp5_cstate->ctl = ctl;
 	mdp5_cstate->pipeline.intf = intf;
-	mdp5_cstate->defer_start = true;
+
+	/*
+	 * This is a bit awkward, but we want to flush the CTL and hit the
+	 * START bit at most once for an atomic update.  In the non-full-
+	 * modeset case, this is done from crtc->atomic_flush(), but that
+	 * is too early in the case of full modeset, in which case we
+	 * defer to encoder->enable().  But we need to *know* whether
+	 * encoder->enable() will be called to do this:
+	 */
+	if (drm_atomic_crtc_needs_modeset(crtc_state))
+		mdp5_cstate->defer_start = true;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
index 6e12e275deba..bddd625ab91b 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
@@ -170,6 +170,8 @@ static void mdp5_complete_commit(struct msm_kms *kms, struct drm_atomic_state *s
 	struct device *dev = &mdp5_kms->pdev->dev;
 	struct mdp5_global_state *global_state;
 
+	drm_atomic_helper_wait_for_vblanks(mdp5_kms->dev, state);
+
 	global_state = mdp5_get_existing_global_state(mdp5_kms);
 
 	if (mdp5_kms->smp)
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c
index f2a0db7a8a03..1cc4e57f0226 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c
@@ -20,12 +20,10 @@
 #include "msm_drv.h"
 #include "mdp5_kms.h"
 
-/*
- * If needed, this can become more specific: something like struct mdp5_mdss,
- * which contains a 'struct msm_mdss base' member.
- */
-struct msm_mdss {
-	struct drm_device *dev;
+#define to_mdp5_mdss(x) container_of(x, struct mdp5_mdss, base)
+
+struct mdp5_mdss {
+	struct msm_mdss base;
 
 	void __iomem *mmio, *vbif;
 
@@ -41,22 +39,22 @@ struct msm_mdss {
 	} irqcontroller;
 };
 
-static inline void mdss_write(struct msm_mdss *mdss, u32 reg, u32 data)
+static inline void mdss_write(struct mdp5_mdss *mdp5_mdss, u32 reg, u32 data)
 {
-	msm_writel(data, mdss->mmio + reg);
+	msm_writel(data, mdp5_mdss->mmio + reg);
 }
 
-static inline u32 mdss_read(struct msm_mdss *mdss, u32 reg)
+static inline u32 mdss_read(struct mdp5_mdss *mdp5_mdss, u32 reg)
 {
-	return msm_readl(mdss->mmio + reg);
+	return msm_readl(mdp5_mdss->mmio + reg);
 }
 
 static irqreturn_t mdss_irq(int irq, void *arg)
 {
-	struct msm_mdss *mdss = arg;
+	struct mdp5_mdss *mdp5_mdss = arg;
 	u32 intr;
 
-	intr = mdss_read(mdss, REG_MDSS_HW_INTR_STATUS);
+	intr = mdss_read(mdp5_mdss, REG_MDSS_HW_INTR_STATUS);
 
 	VERB("intr=%08x", intr);
 
@@ -64,7 +62,7 @@ static irqreturn_t mdss_irq(int irq, void *arg)
 		irq_hw_number_t hwirq = fls(intr) - 1;
 
 		generic_handle_irq(irq_find_mapping(
-				mdss->irqcontroller.domain, hwirq));
+				mdp5_mdss->irqcontroller.domain, hwirq));
 		intr &= ~(1 << hwirq);
 	}
 
@@ -84,19 +82,19 @@ static irqreturn_t mdss_irq(int irq, void *arg)
 
 static void mdss_hw_mask_irq(struct irq_data *irqd)
 {
-	struct msm_mdss *mdss = irq_data_get_irq_chip_data(irqd);
+	struct mdp5_mdss *mdp5_mdss = irq_data_get_irq_chip_data(irqd);
 
 	smp_mb__before_atomic();
-	clear_bit(irqd->hwirq, &mdss->irqcontroller.enabled_mask);
+	clear_bit(irqd->hwirq, &mdp5_mdss->irqcontroller.enabled_mask);
 	smp_mb__after_atomic();
 }
 
 static void mdss_hw_unmask_irq(struct irq_data *irqd)
 {
-	struct msm_mdss *mdss = irq_data_get_irq_chip_data(irqd);
+	struct mdp5_mdss *mdp5_mdss = irq_data_get_irq_chip_data(irqd);
 
 	smp_mb__before_atomic();
-	set_bit(irqd->hwirq, &mdss->irqcontroller.enabled_mask);
+	set_bit(irqd->hwirq, &mdp5_mdss->irqcontroller.enabled_mask);
 	smp_mb__after_atomic();
 }
 
@@ -109,13 +107,13 @@ static struct irq_chip mdss_hw_irq_chip = {
 static int mdss_hw_irqdomain_map(struct irq_domain *d, unsigned int irq,
 				 irq_hw_number_t hwirq)
 {
-	struct msm_mdss *mdss = d->host_data;
+	struct mdp5_mdss *mdp5_mdss = d->host_data;
 
 	if (!(VALID_IRQS & (1 << hwirq)))
 		return -EPERM;
 
 	irq_set_chip_and_handler(irq, &mdss_hw_irq_chip, handle_level_irq);
-	irq_set_chip_data(irq, mdss);
+	irq_set_chip_data(irq, mdp5_mdss);
 
 	return 0;
 }
@@ -126,90 +124,99 @@ static const struct irq_domain_ops mdss_hw_irqdomain_ops = {
 };
 
 
-static int mdss_irq_domain_init(struct msm_mdss *mdss)
+static int mdss_irq_domain_init(struct mdp5_mdss *mdp5_mdss)
 {
-	struct device *dev = mdss->dev->dev;
+	struct device *dev = mdp5_mdss->base.dev->dev;
 	struct irq_domain *d;
 
 	d = irq_domain_add_linear(dev->of_node, 32, &mdss_hw_irqdomain_ops,
-				  mdss);
+				  mdp5_mdss);
 	if (!d) {
 		dev_err(dev, "mdss irq domain add failed\n");
 		return -ENXIO;
 	}
 
-	mdss->irqcontroller.enabled_mask = 0;
-	mdss->irqcontroller.domain = d;
+	mdp5_mdss->irqcontroller.enabled_mask = 0;
+	mdp5_mdss->irqcontroller.domain = d;
 
 	return 0;
 }
 
-int msm_mdss_enable(struct msm_mdss *mdss)
+static int mdp5_mdss_enable(struct msm_mdss *mdss)
 {
+	struct mdp5_mdss *mdp5_mdss = to_mdp5_mdss(mdss);
 	DBG("");
 
-	clk_prepare_enable(mdss->ahb_clk);
-	if (mdss->axi_clk)
-		clk_prepare_enable(mdss->axi_clk);
-	if (mdss->vsync_clk)
-		clk_prepare_enable(mdss->vsync_clk);
+	clk_prepare_enable(mdp5_mdss->ahb_clk);
+	if (mdp5_mdss->axi_clk)
+		clk_prepare_enable(mdp5_mdss->axi_clk);
+	if (mdp5_mdss->vsync_clk)
+		clk_prepare_enable(mdp5_mdss->vsync_clk);
 
 	return 0;
 }
 
-int msm_mdss_disable(struct msm_mdss *mdss)
+static int mdp5_mdss_disable(struct msm_mdss *mdss)
 {
+	struct mdp5_mdss *mdp5_mdss = to_mdp5_mdss(mdss);
 	DBG("");
 
-	if (mdss->vsync_clk)
-		clk_disable_unprepare(mdss->vsync_clk);
-	if (mdss->axi_clk)
-		clk_disable_unprepare(mdss->axi_clk);
-	clk_disable_unprepare(mdss->ahb_clk);
+	if (mdp5_mdss->vsync_clk)
+		clk_disable_unprepare(mdp5_mdss->vsync_clk);
+	if (mdp5_mdss->axi_clk)
+		clk_disable_unprepare(mdp5_mdss->axi_clk);
+	clk_disable_unprepare(mdp5_mdss->ahb_clk);
 
 	return 0;
 }
 
-static int msm_mdss_get_clocks(struct msm_mdss *mdss)
+static int msm_mdss_get_clocks(struct mdp5_mdss *mdp5_mdss)
 {
-	struct platform_device *pdev = to_platform_device(mdss->dev->dev);
+	struct platform_device *pdev =
+			to_platform_device(mdp5_mdss->base.dev->dev);
 
-	mdss->ahb_clk = msm_clk_get(pdev, "iface");
-	if (IS_ERR(mdss->ahb_clk))
-		mdss->ahb_clk = NULL;
+	mdp5_mdss->ahb_clk = msm_clk_get(pdev, "iface");
+	if (IS_ERR(mdp5_mdss->ahb_clk))
+		mdp5_mdss->ahb_clk = NULL;
 
-	mdss->axi_clk = msm_clk_get(pdev, "bus");
-	if (IS_ERR(mdss->axi_clk))
-		mdss->axi_clk = NULL;
+	mdp5_mdss->axi_clk = msm_clk_get(pdev, "bus");
+	if (IS_ERR(mdp5_mdss->axi_clk))
+		mdp5_mdss->axi_clk = NULL;
 
-	mdss->vsync_clk = msm_clk_get(pdev, "vsync");
-	if (IS_ERR(mdss->vsync_clk))
-		mdss->vsync_clk = NULL;
+	mdp5_mdss->vsync_clk = msm_clk_get(pdev, "vsync");
+	if (IS_ERR(mdp5_mdss->vsync_clk))
+		mdp5_mdss->vsync_clk = NULL;
 
 	return 0;
 }
 
-void msm_mdss_destroy(struct drm_device *dev)
+static void mdp5_mdss_destroy(struct drm_device *dev)
 {
 	struct msm_drm_private *priv = dev->dev_private;
-	struct msm_mdss *mdss = priv->mdss;
+	struct mdp5_mdss *mdp5_mdss = to_mdp5_mdss(priv->mdss);
 
-	if (!mdss)
+	if (!mdp5_mdss)
 		return;
 
-	irq_domain_remove(mdss->irqcontroller.domain);
-	mdss->irqcontroller.domain = NULL;
+	irq_domain_remove(mdp5_mdss->irqcontroller.domain);
+	mdp5_mdss->irqcontroller.domain = NULL;
 
-	regulator_disable(mdss->vdd);
+	regulator_disable(mdp5_mdss->vdd);
 
 	pm_runtime_disable(dev->dev);
 }
 
-int msm_mdss_init(struct drm_device *dev)
+static const struct msm_mdss_funcs mdss_funcs = {
+	.enable	= mdp5_mdss_enable,
+	.disable = mdp5_mdss_disable,
+	.destroy = mdp5_mdss_destroy,
+};
+
+int mdp5_mdss_init(struct drm_device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev->dev);
 	struct msm_drm_private *priv = dev->dev_private;
-	struct msm_mdss *mdss;
+	struct mdp5_mdss *mdp5_mdss;
 	int ret;
 
 	DBG("");
@@ -217,40 +224,40 @@ int msm_mdss_init(struct drm_device *dev)
 	if (!of_device_is_compatible(dev->dev->of_node, "qcom,mdss"))
 		return 0;
 
-	mdss = devm_kzalloc(dev->dev, sizeof(*mdss), GFP_KERNEL);
-	if (!mdss) {
+	mdp5_mdss = devm_kzalloc(dev->dev, sizeof(*mdp5_mdss), GFP_KERNEL);
+	if (!mdp5_mdss) {
 		ret = -ENOMEM;
 		goto fail;
 	}
 
-	mdss->dev = dev;
+	mdp5_mdss->base.dev = dev;
 
-	mdss->mmio = msm_ioremap(pdev, "mdss_phys", "MDSS");
-	if (IS_ERR(mdss->mmio)) {
-		ret = PTR_ERR(mdss->mmio);
+	mdp5_mdss->mmio = msm_ioremap(pdev, "mdss_phys", "MDSS");
+	if (IS_ERR(mdp5_mdss->mmio)) {
+		ret = PTR_ERR(mdp5_mdss->mmio);
 		goto fail;
 	}
 
-	mdss->vbif = msm_ioremap(pdev, "vbif_phys", "VBIF");
-	if (IS_ERR(mdss->vbif)) {
-		ret = PTR_ERR(mdss->vbif);
+	mdp5_mdss->vbif = msm_ioremap(pdev, "vbif_phys", "VBIF");
+	if (IS_ERR(mdp5_mdss->vbif)) {
+		ret = PTR_ERR(mdp5_mdss->vbif);
 		goto fail;
 	}
 
-	ret = msm_mdss_get_clocks(mdss);
+	ret = msm_mdss_get_clocks(mdp5_mdss);
 	if (ret) {
 		dev_err(dev->dev, "failed to get clocks: %d\n", ret);
 		goto fail;
 	}
 
 	/* Regulator to enable GDSCs in downstream kernels */
-	mdss->vdd = devm_regulator_get(dev->dev, "vdd");
-	if (IS_ERR(mdss->vdd)) {
-		ret = PTR_ERR(mdss->vdd);
+	mdp5_mdss->vdd = devm_regulator_get(dev->dev, "vdd");
+	if (IS_ERR(mdp5_mdss->vdd)) {
+		ret = PTR_ERR(mdp5_mdss->vdd);
 		goto fail;
 	}
 
-	ret = regulator_enable(mdss->vdd);
+	ret = regulator_enable(mdp5_mdss->vdd);
 	if (ret) {
 		dev_err(dev->dev, "failed to enable regulator vdd: %d\n",
 			ret);
@@ -258,25 +265,26 @@ int msm_mdss_init(struct drm_device *dev)
 	}
 
 	ret = devm_request_irq(dev->dev, platform_get_irq(pdev, 0),
-			       mdss_irq, 0, "mdss_isr", mdss);
+			       mdss_irq, 0, "mdss_isr", mdp5_mdss);
 	if (ret) {
 		dev_err(dev->dev, "failed to init irq: %d\n", ret);
 		goto fail_irq;
 	}
 
-	ret = mdss_irq_domain_init(mdss);
+	ret = mdss_irq_domain_init(mdp5_mdss);
 	if (ret) {
 		dev_err(dev->dev, "failed to init sub-block irqs: %d\n", ret);
 		goto fail_irq;
 	}
 
-	priv->mdss = mdss;
+	mdp5_mdss->base.funcs = &mdss_funcs;
+	priv->mdss = &mdp5_mdss->base;
 
 	pm_runtime_enable(dev->dev);
 
 	return 0;
 fail_irq:
-	regulator_disable(mdss->vdd);
+	regulator_disable(mdp5_mdss->vdd);
 fail:
 	return ret;
 }
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
index e09bc53a0e65..7d306c5acd09 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
@@ -46,7 +46,7 @@ static void mdp5_plane_destroy(struct drm_plane *plane)
 {
 	struct mdp5_plane *mdp5_plane = to_mdp5_plane(plane);
 
-	drm_plane_helper_disable(plane);
+	drm_plane_helper_disable(plane, NULL);
 	drm_plane_cleanup(plane);
 
 	kfree(mdp5_plane);
@@ -512,7 +512,7 @@ static void mdp5_plane_atomic_async_update(struct drm_plane *plane,
 	if (plane_enabled(new_state)) {
 		struct mdp5_ctl *ctl;
 		struct mdp5_pipeline *pipeline =
-					mdp5_crtc_get_pipeline(plane->crtc);
+					mdp5_crtc_get_pipeline(new_state->crtc);
 		int ret;
 
 		ret = mdp5_plane_mode_set(plane, new_state->crtc, new_state->fb,
@@ -1029,8 +1029,6 @@ static int mdp5_plane_mode_set(struct drm_plane *plane,
 				     src_img_w, src_img_h,
 				     src_x + src_w, src_y, src_w, src_h);
 
-	plane->fb = fb;
-
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c
index b744bcc7d8ad..ff8164cc6738 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.c
+++ b/drivers/gpu/drm/msm/dsi/dsi.c
@@ -208,6 +208,9 @@ int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev,
 		goto fail;
 	}
 
+	if (!msm_dsi_manager_validate_current_config(msm_dsi->id))
+		goto fail;
+
 	msm_dsi->encoder = encoder;
 
 	msm_dsi->bridge = msm_dsi_manager_bridge_init(msm_dsi->id);
diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h
index 70d9a9a47acd..08f3fc6771b7 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.h
+++ b/drivers/gpu/drm/msm/dsi/dsi.h
@@ -100,6 +100,7 @@ bool msm_dsi_manager_cmd_xfer_trigger(int id, u32 dma_base, u32 len);
 void msm_dsi_manager_attach_dsi_device(int id, u32 device_flags);
 int msm_dsi_manager_register(struct msm_dsi *msm_dsi);
 void msm_dsi_manager_unregister(struct msm_dsi *msm_dsi);
+bool msm_dsi_manager_validate_current_config(u8 id);
 
 /* msm dsi */
 static inline bool msm_dsi_device_connected(struct msm_dsi *msm_dsi)
@@ -149,6 +150,7 @@ static inline int msm_dsi_pll_set_usecase(struct msm_dsi_pll *pll,
 #endif
 
 /* dsi host */
+struct msm_dsi_host;
 int msm_dsi_host_xfer_prepare(struct mipi_dsi_host *host,
 					const struct mipi_dsi_msg *msg);
 void msm_dsi_host_xfer_restore(struct mipi_dsi_host *host,
@@ -162,7 +164,8 @@ void msm_dsi_host_cmd_xfer_commit(struct mipi_dsi_host *host,
 int msm_dsi_host_enable(struct mipi_dsi_host *host);
 int msm_dsi_host_disable(struct mipi_dsi_host *host);
 int msm_dsi_host_power_on(struct mipi_dsi_host *host,
-			struct msm_dsi_phy_shared_timings *phy_shared_timings);
+			struct msm_dsi_phy_shared_timings *phy_shared_timings,
+			bool is_dual_dsi);
 int msm_dsi_host_power_off(struct mipi_dsi_host *host);
 int msm_dsi_host_set_display_mode(struct mipi_dsi_host *host,
 					struct drm_display_mode *mode);
@@ -175,13 +178,29 @@ int msm_dsi_host_set_src_pll(struct mipi_dsi_host *host,
 			struct msm_dsi_pll *src_pll);
 void msm_dsi_host_reset_phy(struct mipi_dsi_host *host);
 void msm_dsi_host_get_phy_clk_req(struct mipi_dsi_host *host,
-	struct msm_dsi_phy_clk_request *clk_req);
+	struct msm_dsi_phy_clk_request *clk_req,
+	bool is_dual_dsi);
 void msm_dsi_host_destroy(struct mipi_dsi_host *host);
 int msm_dsi_host_modeset_init(struct mipi_dsi_host *host,
 					struct drm_device *dev);
 int msm_dsi_host_init(struct msm_dsi *msm_dsi);
 int msm_dsi_runtime_suspend(struct device *dev);
 int msm_dsi_runtime_resume(struct device *dev);
+int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host);
+int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host);
+void dsi_link_clk_disable_6g(struct msm_dsi_host *msm_host);
+void dsi_link_clk_disable_v2(struct msm_dsi_host *msm_host);
+int dsi_tx_buf_alloc_6g(struct msm_dsi_host *msm_host, int size);
+int dsi_tx_buf_alloc_v2(struct msm_dsi_host *msm_host, int size);
+void *dsi_tx_buf_get_6g(struct msm_dsi_host *msm_host);
+void *dsi_tx_buf_get_v2(struct msm_dsi_host *msm_host);
+void dsi_tx_buf_put_6g(struct msm_dsi_host *msm_host);
+int dsi_dma_base_get_6g(struct msm_dsi_host *msm_host, uint64_t *iova);
+int dsi_dma_base_get_v2(struct msm_dsi_host *msm_host, uint64_t *iova);
+int dsi_clk_init_v2(struct msm_dsi_host *msm_host);
+int dsi_clk_init_6g_v2(struct msm_dsi_host *msm_host);
+int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host, bool is_dual_dsi);
+int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_dual_dsi);
 
 /* dsi phy */
 struct msm_dsi_phy;
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
index 0327bb54b01b..dcdfb1bb54f9 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
@@ -136,20 +136,58 @@ static const struct msm_dsi_config sdm845_dsi_cfg = {
 	.num_dsi = 2,
 };
 
+const static struct msm_dsi_host_cfg_ops msm_dsi_v2_host_ops = {
+	.link_clk_enable = dsi_link_clk_enable_v2,
+	.link_clk_disable = dsi_link_clk_disable_v2,
+	.clk_init_ver = dsi_clk_init_v2,
+	.tx_buf_alloc = dsi_tx_buf_alloc_v2,
+	.tx_buf_get = dsi_tx_buf_get_v2,
+	.tx_buf_put = NULL,
+	.dma_base_get = dsi_dma_base_get_v2,
+	.calc_clk_rate = dsi_calc_clk_rate_v2,
+};
+
+const static struct msm_dsi_host_cfg_ops msm_dsi_6g_host_ops = {
+	.link_clk_enable = dsi_link_clk_enable_6g,
+	.link_clk_disable = dsi_link_clk_disable_6g,
+	.clk_init_ver = NULL,
+	.tx_buf_alloc = dsi_tx_buf_alloc_6g,
+	.tx_buf_get = dsi_tx_buf_get_6g,
+	.tx_buf_put = dsi_tx_buf_put_6g,
+	.dma_base_get = dsi_dma_base_get_6g,
+	.calc_clk_rate = dsi_calc_clk_rate_6g,
+};
+
+const static struct msm_dsi_host_cfg_ops msm_dsi_6g_v2_host_ops = {
+	.link_clk_enable = dsi_link_clk_enable_6g,
+	.link_clk_disable = dsi_link_clk_disable_6g,
+	.clk_init_ver = dsi_clk_init_6g_v2,
+	.tx_buf_alloc = dsi_tx_buf_alloc_6g,
+	.tx_buf_get = dsi_tx_buf_get_6g,
+	.tx_buf_put = dsi_tx_buf_put_6g,
+	.dma_base_get = dsi_dma_base_get_6g,
+	.calc_clk_rate = dsi_calc_clk_rate_6g,
+};
+
 static const struct msm_dsi_cfg_handler dsi_cfg_handlers[] = {
-	{MSM_DSI_VER_MAJOR_V2, MSM_DSI_V2_VER_MINOR_8064, &apq8064_dsi_cfg},
+	{MSM_DSI_VER_MAJOR_V2, MSM_DSI_V2_VER_MINOR_8064,
+		&apq8064_dsi_cfg, &msm_dsi_v2_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_0,
-						&msm8974_apq8084_dsi_cfg},
+		&msm8974_apq8084_dsi_cfg, &msm_dsi_6g_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_1,
-						&msm8974_apq8084_dsi_cfg},
+		&msm8974_apq8084_dsi_cfg, &msm_dsi_6g_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_1_1,
-						&msm8974_apq8084_dsi_cfg},
+		&msm8974_apq8084_dsi_cfg, &msm_dsi_6g_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_2,
-						&msm8974_apq8084_dsi_cfg},
-	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_3, &msm8994_dsi_cfg},
-	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_3_1, &msm8916_dsi_cfg},
-	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_4_1, &msm8996_dsi_cfg},
-	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_2_1, &sdm845_dsi_cfg},
+		&msm8974_apq8084_dsi_cfg, &msm_dsi_6g_host_ops},
+	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_3,
+		&msm8994_dsi_cfg, &msm_dsi_6g_host_ops},
+	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_3_1,
+		&msm8916_dsi_cfg, &msm_dsi_6g_host_ops},
+	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_4_1,
+		&msm8996_dsi_cfg, &msm_dsi_6g_host_ops},
+	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_2_1,
+		&sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops},
 };
 
 const struct msm_dsi_cfg_handler *msm_dsi_cfg_get(u32 major, u32 minor)
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.h b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
index 9cfdcf1c95d5..16c507911110 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.h
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
@@ -40,10 +40,22 @@ struct msm_dsi_config {
 	const int num_dsi;
 };
 
+struct msm_dsi_host_cfg_ops {
+	int (*link_clk_enable)(struct msm_dsi_host *msm_host);
+	void (*link_clk_disable)(struct msm_dsi_host *msm_host);
+	int (*clk_init_ver)(struct msm_dsi_host *msm_host);
+	int (*tx_buf_alloc)(struct msm_dsi_host *msm_host, int size);
+	void* (*tx_buf_get)(struct msm_dsi_host *msm_host);
+	void (*tx_buf_put)(struct msm_dsi_host *msm_host);
+	int (*dma_base_get)(struct msm_dsi_host *msm_host, uint64_t *iova);
+	int (*calc_clk_rate)(struct msm_dsi_host *msm_host, bool is_dual_dsi);
+};
+
 struct msm_dsi_cfg_handler {
 	u32 major;
 	u32 minor;
 	const struct msm_dsi_config *cfg;
+	const struct msm_dsi_host_cfg_ops *ops;
 };
 
 const struct msm_dsi_cfg_handler *msm_dsi_cfg_get(u32 major, u32 minor);
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 2f1a2780658a..96fb5f635314 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -118,6 +118,7 @@ struct msm_dsi_host {
 	struct clk *byte_intf_clk;
 
 	u32 byte_clk_rate;
+	u32 pixel_clk_rate;
 	u32 esc_clk_rate;
 
 	/* DSI v2 specific clocks */
@@ -332,6 +333,54 @@ static int dsi_regulator_init(struct msm_dsi_host *msm_host)
 	return 0;
 }
 
+int dsi_clk_init_v2(struct msm_dsi_host *msm_host)
+{
+	struct platform_device *pdev = msm_host->pdev;
+	int ret = 0;
+
+	msm_host->src_clk = msm_clk_get(pdev, "src");
+
+	if (IS_ERR(msm_host->src_clk)) {
+		ret = PTR_ERR(msm_host->src_clk);
+		pr_err("%s: can't find src clock. ret=%d\n",
+			__func__, ret);
+		msm_host->src_clk = NULL;
+		return ret;
+	}
+
+	msm_host->esc_clk_src = clk_get_parent(msm_host->esc_clk);
+	if (!msm_host->esc_clk_src) {
+		ret = -ENODEV;
+		pr_err("%s: can't get esc clock parent. ret=%d\n",
+			__func__, ret);
+		return ret;
+	}
+
+	msm_host->dsi_clk_src = clk_get_parent(msm_host->src_clk);
+	if (!msm_host->dsi_clk_src) {
+		ret = -ENODEV;
+		pr_err("%s: can't get src clock parent. ret=%d\n",
+			__func__, ret);
+	}
+
+	return ret;
+}
+
+int dsi_clk_init_6g_v2(struct msm_dsi_host *msm_host)
+{
+	struct platform_device *pdev = msm_host->pdev;
+	int ret = 0;
+
+	msm_host->byte_intf_clk = msm_clk_get(pdev, "byte_intf");
+	if (IS_ERR(msm_host->byte_intf_clk)) {
+		ret = PTR_ERR(msm_host->byte_intf_clk);
+		pr_err("%s: can't find byte_intf clock. ret=%d\n",
+			__func__, ret);
+	}
+
+	return ret;
+}
+
 static int dsi_clk_init(struct msm_dsi_host *msm_host)
 {
 	struct platform_device *pdev = msm_host->pdev;
@@ -379,19 +428,6 @@ static int dsi_clk_init(struct msm_dsi_host *msm_host)
 		goto exit;
 	}
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G &&
-	    cfg_hnd->minor >= MSM_DSI_6G_VER_MINOR_V2_2_1) {
-		msm_host->byte_intf_clk = msm_clk_get(pdev, "byte_intf");
-		if (IS_ERR(msm_host->byte_intf_clk)) {
-			ret = PTR_ERR(msm_host->byte_intf_clk);
-			pr_err("%s: can't find byte_intf clock. ret=%d\n",
-			        __func__, ret);
-			goto exit;
-		}
-	} else {
-		msm_host->byte_intf_clk = NULL;
-	}
-
 	msm_host->byte_clk_src = clk_get_parent(msm_host->byte_clk);
 	if (!msm_host->byte_clk_src) {
 		ret = -ENODEV;
@@ -406,31 +442,8 @@ static int dsi_clk_init(struct msm_dsi_host *msm_host)
 		goto exit;
 	}
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_V2) {
-		msm_host->src_clk = msm_clk_get(pdev, "src");
-		if (IS_ERR(msm_host->src_clk)) {
-			ret = PTR_ERR(msm_host->src_clk);
-			pr_err("%s: can't find src clock. ret=%d\n",
-				__func__, ret);
-			msm_host->src_clk = NULL;
-			goto exit;
-		}
-
-		msm_host->esc_clk_src = clk_get_parent(msm_host->esc_clk);
-		if (!msm_host->esc_clk_src) {
-			ret = -ENODEV;
-			pr_err("%s: can't get esc clock parent. ret=%d\n",
-				__func__, ret);
-			goto exit;
-		}
-
-		msm_host->dsi_clk_src = clk_get_parent(msm_host->src_clk);
-		if (!msm_host->dsi_clk_src) {
-			ret = -ENODEV;
-			pr_err("%s: can't get src clock parent. ret=%d\n",
-				__func__, ret);
-		}
-	}
+	if (cfg_hnd->ops->clk_init_ver)
+		ret = cfg_hnd->ops->clk_init_ver(msm_host);
 exit:
 	return ret;
 }
@@ -498,7 +511,7 @@ int msm_dsi_runtime_resume(struct device *dev)
 	return dsi_bus_clk_enable(msm_host);
 }
 
-static int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host)
+int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host)
 {
 	int ret;
 
@@ -511,7 +524,7 @@ static int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host)
 		goto error;
 	}
 
-	ret = clk_set_rate(msm_host->pixel_clk, msm_host->mode->clock * 1000);
+	ret = clk_set_rate(msm_host->pixel_clk, msm_host->pixel_clk_rate);
 	if (ret) {
 		pr_err("%s: Failed to set rate pixel clk, %d\n", __func__, ret);
 		goto error;
@@ -566,7 +579,7 @@ error:
 	return ret;
 }
 
-static int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host)
+int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host)
 {
 	int ret;
 
@@ -592,7 +605,7 @@ static int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host)
 		goto error;
 	}
 
-	ret = clk_set_rate(msm_host->pixel_clk, msm_host->mode->clock * 1000);
+	ret = clk_set_rate(msm_host->pixel_clk, msm_host->pixel_clk_rate);
 	if (ret) {
 		pr_err("%s: Failed to set rate pixel clk, %d\n", __func__, ret);
 		goto error;
@@ -634,98 +647,121 @@ error:
 	return ret;
 }
 
-static int dsi_link_clk_enable(struct msm_dsi_host *msm_host)
+void dsi_link_clk_disable_6g(struct msm_dsi_host *msm_host)
 {
-	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
+	clk_disable_unprepare(msm_host->esc_clk);
+	clk_disable_unprepare(msm_host->pixel_clk);
+	if (msm_host->byte_intf_clk)
+		clk_disable_unprepare(msm_host->byte_intf_clk);
+	clk_disable_unprepare(msm_host->byte_clk);
+}
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G)
-		return dsi_link_clk_enable_6g(msm_host);
-	else
-		return dsi_link_clk_enable_v2(msm_host);
+void dsi_link_clk_disable_v2(struct msm_dsi_host *msm_host)
+{
+	clk_disable_unprepare(msm_host->pixel_clk);
+	clk_disable_unprepare(msm_host->src_clk);
+	clk_disable_unprepare(msm_host->esc_clk);
+	clk_disable_unprepare(msm_host->byte_clk);
 }
 
-static void dsi_link_clk_disable(struct msm_dsi_host *msm_host)
+static u32 dsi_get_pclk_rate(struct msm_dsi_host *msm_host, bool is_dual_dsi)
 {
-	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
+	struct drm_display_mode *mode = msm_host->mode;
+	u32 pclk_rate;
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
-		clk_disable_unprepare(msm_host->esc_clk);
-		clk_disable_unprepare(msm_host->pixel_clk);
-		if (msm_host->byte_intf_clk)
-			clk_disable_unprepare(msm_host->byte_intf_clk);
-		clk_disable_unprepare(msm_host->byte_clk);
-	} else {
-		clk_disable_unprepare(msm_host->pixel_clk);
-		clk_disable_unprepare(msm_host->src_clk);
-		clk_disable_unprepare(msm_host->esc_clk);
-		clk_disable_unprepare(msm_host->byte_clk);
-	}
+	pclk_rate = mode->clock * 1000;
+
+	/*
+	 * For dual DSI mode, the current DRM mode has the complete width of the
+	 * panel. Since, the complete panel is driven by two DSI controllers,
+	 * the clock rates have to be split between the two dsi controllers.
+	 * Adjust the byte and pixel clock rates for each dsi host accordingly.
+	 */
+	if (is_dual_dsi)
+		pclk_rate /= 2;
+
+	return pclk_rate;
 }
 
-static int dsi_calc_clk_rate(struct msm_dsi_host *msm_host)
+static void dsi_calc_pclk(struct msm_dsi_host *msm_host, bool is_dual_dsi)
 {
-	struct drm_display_mode *mode = msm_host->mode;
-	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	u8 lanes = msm_host->lanes;
 	u32 bpp = dsi_get_bpp(msm_host->format);
-	u32 pclk_rate;
+	u32 pclk_rate = dsi_get_pclk_rate(msm_host, is_dual_dsi);
+	u64 pclk_bpp = (u64)pclk_rate * bpp;
 
-	if (!mode) {
-		pr_err("%s: mode not set\n", __func__);
-		return -EINVAL;
-	}
-
-	pclk_rate = mode->clock * 1000;
-	if (lanes > 0) {
-		msm_host->byte_clk_rate = (pclk_rate * bpp) / (8 * lanes);
-	} else {
+	if (lanes == 0) {
 		pr_err("%s: forcing mdss_dsi lanes to 1\n", __func__);
-		msm_host->byte_clk_rate = (pclk_rate * bpp) / 8;
+		lanes = 1;
 	}
 
-	DBG("pclk=%d, bclk=%d", pclk_rate, msm_host->byte_clk_rate);
+	do_div(pclk_bpp, (8 * lanes));
 
-	msm_host->esc_clk_rate = clk_get_rate(msm_host->esc_clk);
+	msm_host->pixel_clk_rate = pclk_rate;
+	msm_host->byte_clk_rate = pclk_bpp;
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_V2) {
-		unsigned int esc_mhz, esc_div;
-		unsigned long byte_mhz;
+	DBG("pclk=%d, bclk=%d", msm_host->pixel_clk_rate,
+				msm_host->byte_clk_rate);
 
-		msm_host->src_clk_rate = (pclk_rate * bpp) / 8;
+}
 
-		/*
-		 * esc clock is byte clock followed by a 4 bit divider,
-		 * we need to find an escape clock frequency within the
-		 * mipi DSI spec range within the maximum divider limit
-		 * We iterate here between an escape clock frequencey
-		 * between 20 Mhz to 5 Mhz and pick up the first one
-		 * that can be supported by our divider
-		 */
+int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_dual_dsi)
+{
+	if (!msm_host->mode) {
+		pr_err("%s: mode not set\n", __func__);
+		return -EINVAL;
+	}
+
+	dsi_calc_pclk(msm_host, is_dual_dsi);
+	msm_host->esc_clk_rate = clk_get_rate(msm_host->esc_clk);
+	return 0;
+}
 
-		byte_mhz = msm_host->byte_clk_rate / 1000000;
+int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host, bool is_dual_dsi)
+{
+	u32 bpp = dsi_get_bpp(msm_host->format);
+	u64 pclk_bpp;
+	unsigned int esc_mhz, esc_div;
+	unsigned long byte_mhz;
 
-		for (esc_mhz = 20; esc_mhz >= 5; esc_mhz--) {
-			esc_div = DIV_ROUND_UP(byte_mhz, esc_mhz);
+	dsi_calc_pclk(msm_host, is_dual_dsi);
 
-			/*
-			 * TODO: Ideally, we shouldn't know what sort of divider
-			 * is available in mmss_cc, we're just assuming that
-			 * it'll always be a 4 bit divider. Need to come up with
-			 * a better way here.
-			 */
-			if (esc_div >= 1 && esc_div <= 16)
-				break;
-		}
+	pclk_bpp = (u64)dsi_get_pclk_rate(msm_host, is_dual_dsi) * bpp;
+	do_div(pclk_bpp, 8);
+	msm_host->src_clk_rate = pclk_bpp;
 
-		if (esc_mhz < 5)
-			return -EINVAL;
+	/*
+	 * esc clock is byte clock followed by a 4 bit divider,
+	 * we need to find an escape clock frequency within the
+	 * mipi DSI spec range within the maximum divider limit
+	 * We iterate here between an escape clock frequencey
+	 * between 20 Mhz to 5 Mhz and pick up the first one
+	 * that can be supported by our divider
+	 */
+
+	byte_mhz = msm_host->byte_clk_rate / 1000000;
 
-		msm_host->esc_clk_rate = msm_host->byte_clk_rate / esc_div;
+	for (esc_mhz = 20; esc_mhz >= 5; esc_mhz--) {
+		esc_div = DIV_ROUND_UP(byte_mhz, esc_mhz);
 
-		DBG("esc=%d, src=%d", msm_host->esc_clk_rate,
-			msm_host->src_clk_rate);
+		/*
+		 * TODO: Ideally, we shouldn't know what sort of divider
+		 * is available in mmss_cc, we're just assuming that
+		 * it'll always be a 4 bit divider. Need to come up with
+		 * a better way here.
+		 */
+		if (esc_div >= 1 && esc_div <= 16)
+			break;
 	}
 
+	if (esc_mhz < 5)
+		return -EINVAL;
+
+	msm_host->esc_clk_rate = msm_host->byte_clk_rate / esc_div;
+
+	DBG("esc=%d, src=%d", msm_host->esc_clk_rate,
+		msm_host->src_clk_rate);
+
 	return 0;
 }
 
@@ -885,7 +921,7 @@ static void dsi_ctrl_config(struct msm_dsi_host *msm_host, bool enable,
 	dsi_write(msm_host, REG_DSI_CTRL, data);
 }
 
-static void dsi_timing_setup(struct msm_dsi_host *msm_host)
+static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_dual_dsi)
 {
 	struct drm_display_mode *mode = msm_host->mode;
 	u32 hs_start = 0, vs_start = 0; /* take sync start as 0 */
@@ -897,10 +933,26 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host)
 	u32 ha_end = ha_start + mode->hdisplay;
 	u32 va_start = v_total - mode->vsync_start;
 	u32 va_end = va_start + mode->vdisplay;
+	u32 hdisplay = mode->hdisplay;
 	u32 wc;
 
 	DBG("");
 
+	/*
+	 * For dual DSI mode, the current DRM mode has
+	 * the complete width of the panel. Since, the complete
+	 * panel is driven by two DSI controllers, the horizontal
+	 * timings have to be split between the two dsi controllers.
+	 * Adjust the DSI host timing values accordingly.
+	 */
+	if (is_dual_dsi) {
+		h_total /= 2;
+		hs_end /= 2;
+		ha_start /= 2;
+		ha_end /= 2;
+		hdisplay /= 2;
+	}
+
 	if (msm_host->mode_flags & MIPI_DSI_MODE_VIDEO) {
 		dsi_write(msm_host, REG_DSI_ACTIVE_H,
 			DSI_ACTIVE_H_START(ha_start) |
@@ -921,7 +973,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host)
 			DSI_ACTIVE_VSYNC_VPOS_END(vs_end));
 	} else {		/* command mode */
 		/* image data and 1 byte write_memory_start cmd */
-		wc = mode->hdisplay * dsi_get_bpp(msm_host->format) / 8 + 1;
+		wc = hdisplay * dsi_get_bpp(msm_host->format) / 8 + 1;
 
 		dsi_write(msm_host, REG_DSI_CMD_MDP_STREAM_CTRL,
 			DSI_CMD_MDP_STREAM_CTRL_WORD_COUNT(wc) |
@@ -931,7 +983,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host)
 					MIPI_DSI_DCS_LONG_WRITE));
 
 		dsi_write(msm_host, REG_DSI_CMD_MDP_STREAM_TOTAL,
-			DSI_CMD_MDP_STREAM_TOTAL_H_TOTAL(mode->hdisplay) |
+			DSI_CMD_MDP_STREAM_TOTAL_H_TOTAL(hdisplay) |
 			DSI_CMD_MDP_STREAM_TOTAL_V_TOTAL(mode->vdisplay));
 	}
 }
@@ -1015,50 +1067,37 @@ static void dsi_wait4video_eng_busy(struct msm_dsi_host *msm_host)
 	}
 }
 
-/* dsi_cmd */
-static int dsi_tx_buf_alloc(struct msm_dsi_host *msm_host, int size)
+int dsi_tx_buf_alloc_6g(struct msm_dsi_host *msm_host, int size)
 {
 	struct drm_device *dev = msm_host->dev;
 	struct msm_drm_private *priv = dev->dev_private;
-	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
-	int ret;
 	uint64_t iova;
+	u8 *data;
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
-		msm_host->tx_gem_obj = msm_gem_new(dev, size, MSM_BO_UNCACHED);
-		if (IS_ERR(msm_host->tx_gem_obj)) {
-			ret = PTR_ERR(msm_host->tx_gem_obj);
-			pr_err("%s: failed to allocate gem, %d\n",
-				__func__, ret);
-			msm_host->tx_gem_obj = NULL;
-			return ret;
-		}
+	data = msm_gem_kernel_new(dev, size, MSM_BO_UNCACHED,
+					priv->kms->aspace,
+					&msm_host->tx_gem_obj, &iova);
 
-		ret = msm_gem_get_iova(msm_host->tx_gem_obj,
-				priv->kms->aspace, &iova);
-		if (ret) {
-			pr_err("%s: failed to get iova, %d\n", __func__, ret);
-			return ret;
-		}
+	if (IS_ERR(data)) {
+		msm_host->tx_gem_obj = NULL;
+		return PTR_ERR(data);
+	}
 
-		if (iova & 0x07) {
-			pr_err("%s: buf NOT 8 bytes aligned\n", __func__);
-			return -EINVAL;
-		}
+	msm_host->tx_size = msm_host->tx_gem_obj->size;
 
-		msm_host->tx_size = msm_host->tx_gem_obj->size;
-	} else {
-		msm_host->tx_buf = dma_alloc_coherent(dev->dev, size,
+	return 0;
+}
+
+int dsi_tx_buf_alloc_v2(struct msm_dsi_host *msm_host, int size)
+{
+	struct drm_device *dev = msm_host->dev;
+
+	msm_host->tx_buf = dma_alloc_coherent(dev->dev, size,
 					&msm_host->tx_buf_paddr, GFP_KERNEL);
-		if (!msm_host->tx_buf) {
-			ret = -ENOMEM;
-			pr_err("%s: failed to allocate tx buf, %d\n",
-				__func__, ret);
-			return ret;
-		}
+	if (!msm_host->tx_buf)
+		return -ENOMEM;
 
-		msm_host->tx_size = size;
-	}
+	msm_host->tx_size = size;
 
 	return 0;
 }
@@ -1089,6 +1128,21 @@ static void dsi_tx_buf_free(struct msm_dsi_host *msm_host)
 			msm_host->tx_buf_paddr);
 }
 
+void *dsi_tx_buf_get_6g(struct msm_dsi_host *msm_host)
+{
+	return msm_gem_get_vaddr(msm_host->tx_gem_obj);
+}
+
+void *dsi_tx_buf_get_v2(struct msm_dsi_host *msm_host)
+{
+	return msm_host->tx_buf;
+}
+
+void dsi_tx_buf_put_6g(struct msm_dsi_host *msm_host)
+{
+	msm_gem_put_vaddr(msm_host->tx_gem_obj);
+}
+
 /*
  * prepare cmd buffer to be txed
  */
@@ -1113,15 +1167,11 @@ static int dsi_cmd_dma_add(struct msm_dsi_host *msm_host,
 		return -EINVAL;
 	}
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
-		data = msm_gem_get_vaddr(msm_host->tx_gem_obj);
-		if (IS_ERR(data)) {
-			ret = PTR_ERR(data);
-			pr_err("%s: get vaddr failed, %d\n", __func__, ret);
-			return ret;
-		}
-	} else {
-		data = msm_host->tx_buf;
+	data = cfg_hnd->ops->tx_buf_get(msm_host);
+	if (IS_ERR(data)) {
+		ret = PTR_ERR(data);
+		pr_err("%s: get vaddr failed, %d\n", __func__, ret);
+		return ret;
 	}
 
 	/* MSM specific command format in memory */
@@ -1142,8 +1192,8 @@ static int dsi_cmd_dma_add(struct msm_dsi_host *msm_host,
 	if (packet.size < len)
 		memset(data + packet.size, 0xff, len - packet.size);
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G)
-		msm_gem_put_vaddr(msm_host->tx_gem_obj);
+	if (cfg_hnd->ops->tx_buf_put)
+		cfg_hnd->ops->tx_buf_put(msm_host);
 
 	return len;
 }
@@ -1190,24 +1240,38 @@ static int dsi_long_read_resp(u8 *buf, const struct mipi_dsi_msg *msg)
 	return msg->rx_len;
 }
 
-static int dsi_cmd_dma_tx(struct msm_dsi_host *msm_host, int len)
+int dsi_dma_base_get_6g(struct msm_dsi_host *msm_host, uint64_t *dma_base)
 {
-	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	struct drm_device *dev = msm_host->dev;
 	struct msm_drm_private *priv = dev->dev_private;
+
+	if (!dma_base)
+		return -EINVAL;
+
+	return msm_gem_get_iova(msm_host->tx_gem_obj,
+				priv->kms->aspace, dma_base);
+}
+
+int dsi_dma_base_get_v2(struct msm_dsi_host *msm_host, uint64_t *dma_base)
+{
+	if (!dma_base)
+		return -EINVAL;
+
+	*dma_base = msm_host->tx_buf_paddr;
+	return 0;
+}
+
+static int dsi_cmd_dma_tx(struct msm_dsi_host *msm_host, int len)
+{
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	int ret;
 	uint64_t dma_base;
 	bool triggered;
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
-		ret = msm_gem_get_iova(msm_host->tx_gem_obj,
-				priv->kms->aspace, &dma_base);
-		if (ret) {
-			pr_err("%s: failed to get iova: %d\n", __func__, ret);
-			return ret;
-		}
-	} else {
-		dma_base = msm_host->tx_buf_paddr;
+	ret = cfg_hnd->ops->dma_base_get(msm_host, &dma_base);
+	if (ret) {
+		pr_err("%s: failed to get iova: %d\n", __func__, ret);
+		return ret;
 	}
 
 	reinit_completion(&msm_host->dma_comp);
@@ -1845,6 +1909,7 @@ int msm_dsi_host_modeset_init(struct mipi_dsi_host *host,
 					struct drm_device *dev)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	struct platform_device *pdev = msm_host->pdev;
 	int ret;
 
@@ -1865,7 +1930,7 @@ int msm_dsi_host_modeset_init(struct mipi_dsi_host *host,
 	}
 
 	msm_host->dev = dev;
-	ret = dsi_tx_buf_alloc(msm_host, SZ_4K);
+	ret = cfg_hnd->ops->tx_buf_alloc(msm_host, SZ_4K);
 	if (ret) {
 		pr_err("%s: alloc tx gem obj failed, %d\n", __func__, ret);
 		return ret;
@@ -1898,7 +1963,7 @@ int msm_dsi_host_register(struct mipi_dsi_host *host, bool check_defer)
 		 * output
 		 */
 		if (check_defer && msm_host->device_node) {
-			if (!of_drm_find_panel(msm_host->device_node))
+			if (IS_ERR(of_drm_find_panel(msm_host->device_node)))
 				if (!of_drm_find_bridge(msm_host->device_node))
 					return -EPROBE_DEFER;
 		}
@@ -1923,6 +1988,7 @@ int msm_dsi_host_xfer_prepare(struct mipi_dsi_host *host,
 				const struct mipi_dsi_msg *msg)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 
 	/* TODO: make sure dsi_cmd_mdp is idle.
 	 * Since DSI6G v1.2.0, we can set DSI_TRIG_CTRL.BLOCK_DMA_WITHIN_FRAME
@@ -1935,7 +2001,7 @@ int msm_dsi_host_xfer_prepare(struct mipi_dsi_host *host,
 	 * mdp clock need to be enabled to receive dsi interrupt
 	 */
 	pm_runtime_get_sync(&msm_host->pdev->dev);
-	dsi_link_clk_enable(msm_host);
+	cfg_hnd->ops->link_clk_enable(msm_host);
 
 	/* TODO: vote for bus bandwidth */
 
@@ -1956,6 +2022,7 @@ void msm_dsi_host_xfer_restore(struct mipi_dsi_host *host,
 				const struct mipi_dsi_msg *msg)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 
 	dsi_intr_ctrl(msm_host, DSI_IRQ_MASK_CMD_DMA_DONE, 0);
 	dsi_write(msm_host, REG_DSI_CTRL, msm_host->dma_cmd_ctrl_restore);
@@ -1965,7 +2032,7 @@ void msm_dsi_host_xfer_restore(struct mipi_dsi_host *host,
 
 	/* TODO: unvote for bus bandwidth */
 
-	dsi_link_clk_disable(msm_host);
+	cfg_hnd->ops->link_clk_disable(msm_host);
 	pm_runtime_put_autosuspend(&msm_host->pdev->dev);
 }
 
@@ -2129,7 +2196,6 @@ int msm_dsi_host_set_src_pll(struct mipi_dsi_host *host,
 	struct msm_dsi_pll *src_pll)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
-	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	struct clk *byte_clk_provider, *pixel_clk_provider;
 	int ret;
 
@@ -2155,14 +2221,16 @@ int msm_dsi_host_set_src_pll(struct mipi_dsi_host *host,
 		goto exit;
 	}
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_V2) {
+	if (msm_host->dsi_clk_src) {
 		ret = clk_set_parent(msm_host->dsi_clk_src, pixel_clk_provider);
 		if (ret) {
 			pr_err("%s: can't set parent to dsi_clk_src. ret=%d\n",
 				__func__, ret);
 			goto exit;
 		}
+	}
 
+	if (msm_host->esc_clk_src) {
 		ret = clk_set_parent(msm_host->esc_clk_src, byte_clk_provider);
 		if (ret) {
 			pr_err("%s: can't set parent to esc_clk_src. ret=%d\n",
@@ -2189,12 +2257,14 @@ void msm_dsi_host_reset_phy(struct mipi_dsi_host *host)
 }
 
 void msm_dsi_host_get_phy_clk_req(struct mipi_dsi_host *host,
-	struct msm_dsi_phy_clk_request *clk_req)
+			struct msm_dsi_phy_clk_request *clk_req,
+			bool is_dual_dsi)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	int ret;
 
-	ret = dsi_calc_clk_rate(msm_host);
+	ret = cfg_hnd->ops->calc_clk_rate(msm_host, is_dual_dsi);
 	if (ret) {
 		pr_err("%s: unable to calc clk rate, %d\n", __func__, ret);
 		return;
@@ -2256,9 +2326,11 @@ static void msm_dsi_sfpb_config(struct msm_dsi_host *msm_host, bool enable)
 }
 
 int msm_dsi_host_power_on(struct mipi_dsi_host *host,
-			struct msm_dsi_phy_shared_timings *phy_shared_timings)
+			struct msm_dsi_phy_shared_timings *phy_shared_timings,
+			bool is_dual_dsi)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	int ret = 0;
 
 	mutex_lock(&msm_host->dev_mutex);
@@ -2277,7 +2349,7 @@ int msm_dsi_host_power_on(struct mipi_dsi_host *host,
 	}
 
 	pm_runtime_get_sync(&msm_host->pdev->dev);
-	ret = dsi_link_clk_enable(msm_host);
+	ret = cfg_hnd->ops->link_clk_enable(msm_host);
 	if (ret) {
 		pr_err("%s: failed to enable link clocks. ret=%d\n",
 		       __func__, ret);
@@ -2291,7 +2363,7 @@ int msm_dsi_host_power_on(struct mipi_dsi_host *host,
 		goto fail_disable_clk;
 	}
 
-	dsi_timing_setup(msm_host);
+	dsi_timing_setup(msm_host, is_dual_dsi);
 	dsi_sw_reset(msm_host);
 	dsi_ctrl_config(msm_host, true, phy_shared_timings);
 
@@ -2304,7 +2376,7 @@ int msm_dsi_host_power_on(struct mipi_dsi_host *host,
 	return 0;
 
 fail_disable_clk:
-	dsi_link_clk_disable(msm_host);
+	cfg_hnd->ops->link_clk_disable(msm_host);
 	pm_runtime_put_autosuspend(&msm_host->pdev->dev);
 fail_disable_reg:
 	dsi_host_regulator_disable(msm_host);
@@ -2316,6 +2388,7 @@ unlock_ret:
 int msm_dsi_host_power_off(struct mipi_dsi_host *host)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 
 	mutex_lock(&msm_host->dev_mutex);
 	if (!msm_host->power_on) {
@@ -2330,7 +2403,7 @@ int msm_dsi_host_power_off(struct mipi_dsi_host *host)
 
 	pinctrl_pm_select_sleep_state(&msm_host->pdev->dev);
 
-	dsi_link_clk_disable(msm_host);
+	cfg_hnd->ops->link_clk_disable(msm_host);
 	pm_runtime_put_autosuspend(&msm_host->pdev->dev);
 
 	dsi_host_regulator_disable(msm_host);
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index 4cb1cb68878b..5224010d90e4 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -134,8 +134,9 @@ static int enable_phy(struct msm_dsi *msm_dsi, int src_pll_id,
 {
 	struct msm_dsi_phy_clk_request clk_req;
 	int ret;
+	bool is_dual_dsi = IS_DUAL_DSI();
 
-	msm_dsi_host_get_phy_clk_req(msm_dsi->host, &clk_req);
+	msm_dsi_host_get_phy_clk_req(msm_dsi->host, &clk_req, is_dual_dsi);
 
 	ret = msm_dsi_phy_enable(msm_dsi->phy, src_pll_id, &clk_req);
 	msm_dsi_phy_get_shared_timings(msm_dsi->phy, shared_timings);
@@ -305,102 +306,25 @@ static void dsi_mgr_connector_destroy(struct drm_connector *connector)
 	kfree(dsi_connector);
 }
 
-static void dsi_dual_connector_fix_modes(struct drm_connector *connector)
-{
-	struct drm_display_mode *mode, *m;
-
-	/* Only support left-right mode */
-	list_for_each_entry_safe(mode, m, &connector->probed_modes, head) {
-		mode->clock >>= 1;
-		mode->hdisplay >>= 1;
-		mode->hsync_start >>= 1;
-		mode->hsync_end >>= 1;
-		mode->htotal >>= 1;
-		drm_mode_set_name(mode);
-	}
-}
-
-static int dsi_dual_connector_tile_init(
-			struct drm_connector *connector, int id)
-{
-	struct drm_display_mode *mode;
-	/* Fake topology id */
-	char topo_id[8] = {'M', 'S', 'M', 'D', 'U', 'D', 'S', 'I'};
-
-	if (connector->tile_group) {
-		DBG("Tile property has been initialized");
-		return 0;
-	}
-
-	/* Use the first mode only for now */
-	mode = list_first_entry(&connector->probed_modes,
-				struct drm_display_mode,
-				head);
-	if (!mode)
-		return -EINVAL;
-
-	connector->tile_group = drm_mode_get_tile_group(
-					connector->dev, topo_id);
-	if (!connector->tile_group)
-		connector->tile_group = drm_mode_create_tile_group(
-					connector->dev, topo_id);
-	if (!connector->tile_group) {
-		pr_err("%s: failed to create tile group\n", __func__);
-		return -ENOMEM;
-	}
-
-	connector->has_tile = true;
-	connector->tile_is_single_monitor = true;
-
-	/* mode has been fixed */
-	connector->tile_h_size = mode->hdisplay;
-	connector->tile_v_size = mode->vdisplay;
-
-	/* Only support left-right mode */
-	connector->num_h_tile = 2;
-	connector->num_v_tile = 1;
-
-	connector->tile_v_loc = 0;
-	connector->tile_h_loc = (id == DSI_RIGHT) ? 1 : 0;
-
-	return 0;
-}
-
 static int dsi_mgr_connector_get_modes(struct drm_connector *connector)
 {
 	int id = dsi_mgr_connector_get_id(connector);
 	struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
 	struct drm_panel *panel = msm_dsi->panel;
-	int ret, num;
+	int num;
 
 	if (!panel)
 		return 0;
 
-	/* Since we have 2 connectors, but only 1 drm_panel in dual DSI mode,
-	 * panel should not attach to any connector.
-	 * Only temporarily attach panel to the current connector here,
-	 * to let panel set mode to this connector.
+	/*
+	 * In dual DSI mode, we have one connector that can be
+	 * attached to the drm_panel.
 	 */
 	drm_panel_attach(panel, connector);
 	num = drm_panel_get_modes(panel);
-	drm_panel_detach(panel);
 	if (!num)
 		return 0;
 
-	if (IS_DUAL_DSI()) {
-		/* report half resolution to user */
-		dsi_dual_connector_fix_modes(connector);
-		ret = dsi_dual_connector_tile_init(connector, id);
-		if (ret)
-			return ret;
-		ret = drm_mode_connector_set_tile_property(connector);
-		if (ret) {
-			pr_err("%s: set tile property failed, %d\n",
-					__func__, ret);
-			return ret;
-		}
-	}
-
 	return num;
 }
 
@@ -454,11 +378,11 @@ static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge)
 	if (ret)
 		goto phy_en_fail;
 
-	/* Do nothing with the host if it is DSI 1 in case of dual DSI */
-	if (is_dual_dsi && (DSI_1 == id))
+	/* Do nothing with the host if it is slave-DSI in case of dual DSI */
+	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id))
 		return;
 
-	ret = msm_dsi_host_power_on(host, &phy_shared_timings[id]);
+	ret = msm_dsi_host_power_on(host, &phy_shared_timings[id], is_dual_dsi);
 	if (ret) {
 		pr_err("%s: power on host %d failed, %d\n", __func__, id, ret);
 		goto host_on_fail;
@@ -466,7 +390,7 @@ static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge)
 
 	if (is_dual_dsi && msm_dsi1) {
 		ret = msm_dsi_host_power_on(msm_dsi1->host,
-					    &phy_shared_timings[DSI_1]);
+				&phy_shared_timings[DSI_1], is_dual_dsi);
 		if (ret) {
 			pr_err("%s: power on host1 failed, %d\n",
 							__func__, ret);
@@ -556,11 +480,11 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge)
 		return;
 
 	/*
-	 * Do nothing with the host if it is DSI 1 in case of dual DSI.
+	 * Do nothing with the host if it is slave-DSI in case of dual DSI.
 	 * It is safe to call dsi_mgr_phy_disable() here because a single PHY
 	 * won't be diabled until both PHYs request disable.
 	 */
-	if (is_dual_dsi && (DSI_1 == id))
+	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id))
 		goto disable_phy;
 
 	if (panel) {
@@ -621,7 +545,7 @@ static void dsi_mgr_bridge_mode_set(struct drm_bridge *bridge,
 			mode->vsync_end, mode->vtotal,
 			mode->type, mode->flags);
 
-	if (is_dual_dsi && (DSI_1 == id))
+	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id))
 		return;
 
 	msm_dsi_host_set_display_mode(host, adjusted_mode);
@@ -684,11 +608,28 @@ struct drm_connector *msm_dsi_manager_connector_init(u8 id)
 	connector->interlace_allowed = 0;
 	connector->doublescan_allowed = 0;
 
-	drm_mode_connector_attach_encoder(connector, msm_dsi->encoder);
+	drm_connector_attach_encoder(connector, msm_dsi->encoder);
 
 	return connector;
 }
 
+bool msm_dsi_manager_validate_current_config(u8 id)
+{
+	bool is_dual_dsi = IS_DUAL_DSI();
+
+	/*
+	 * For dual DSI, we only have one drm panel. For this
+	 * use case, we register only one bridge/connector.
+	 * Skip bridge/connector initialisation if it is
+	 * slave-DSI for dual DSI configuration.
+	 */
+	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id)) {
+		DBG("Skip bridge registration for slave DSI->id: %d\n", id);
+		return false;
+	}
+	return true;
+}
+
 /* initialize bridge */
 struct drm_bridge *msm_dsi_manager_bridge_init(u8 id)
 {
@@ -751,12 +692,8 @@ struct drm_connector *msm_dsi_manager_ext_bridge_init(u8 id)
 	connector_list = &dev->mode_config.connector_list;
 
 	list_for_each_entry(connector, connector_list, head) {
-		int i;
-
-		for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-			if (connector->encoder_ids[i] == encoder->base.id)
-				return connector;
-		}
+		if (drm_connector_has_possible_encoder(connector, encoder))
+			return connector;
 	}
 
 	return ERR_PTR(-ENODEV);
@@ -836,6 +773,7 @@ void msm_dsi_manager_attach_dsi_device(int id, u32 device_flags)
 	struct msm_drm_private *priv;
 	struct msm_kms *kms;
 	struct drm_encoder *encoder;
+	bool cmd_mode;
 
 	/*
 	 * drm_device pointer is assigned to msm_dsi only in the modeset_init
@@ -850,10 +788,11 @@ void msm_dsi_manager_attach_dsi_device(int id, u32 device_flags)
 	priv = dev->dev_private;
 	kms = priv->kms;
 	encoder = msm_dsi_get_encoder(msm_dsi);
+	cmd_mode = !(device_flags &
+				 MIPI_DSI_MODE_VIDEO);
 
 	if (encoder && kms->funcs->set_encoder_mode)
-		if (!(device_flags & MIPI_DSI_MODE_VIDEO))
-			kms->funcs->set_encoder_mode(kms, encoder, true);
+		kms->funcs->set_encoder_mode(kms, encoder, cmd_mode);
 }
 
 int msm_dsi_manager_register(struct msm_dsi *msm_dsi)
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
index c4c37a7df637..4c03f0b7343e 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
@@ -798,6 +798,8 @@ struct msm_dsi_pll *msm_dsi_pll_10nm_init(struct platform_device *pdev, int id)
 		return ERR_PTR(-ENOMEM);
 	}
 
+	spin_lock_init(&pll_10nm->postdiv_lock);
+
 	pll = &pll_10nm->base;
 	pll->min_rate = 1000000000UL;
 	pll->max_rate = 3500000000UL;
diff --git a/drivers/gpu/drm/msm/edp/edp_connector.c b/drivers/gpu/drm/msm/edp/edp_connector.c
index 6f3fc6b0f0a3..058ff92a0207 100644
--- a/drivers/gpu/drm/msm/edp/edp_connector.c
+++ b/drivers/gpu/drm/msm/edp/edp_connector.c
@@ -56,7 +56,7 @@ static int edp_connector_get_modes(struct drm_connector *connector)
 	if (ret)
 		return ret;
 
-	drm_mode_connector_update_edid_property(connector, drm_edid);
+	drm_connector_update_edid_property(connector, drm_edid);
 	if (drm_edid)
 		ret = drm_add_edid_modes(connector, drm_edid);
 
@@ -134,7 +134,7 @@ struct drm_connector *msm_edp_connector_init(struct msm_edp *edp)
 	connector->interlace_allowed = false;
 	connector->doublescan_allowed = false;
 
-	drm_mode_connector_attach_encoder(connector, edp->encoder);
+	drm_connector_attach_encoder(connector, edp->encoder);
 
 	return connector;
 }
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
index c0848dfedd50..e9c9a0af508e 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
@@ -392,7 +392,7 @@ static int msm_hdmi_connector_get_modes(struct drm_connector *connector)
 	hdmi_write(hdmi, REG_HDMI_CTRL, hdmi_ctrl);
 
 	hdmi->hdmi_mode = drm_detect_hdmi_monitor(edid);
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 
 	if (edid) {
 		ret = drm_add_edid_modes(connector, edid);
@@ -477,7 +477,7 @@ struct drm_connector *msm_hdmi_connector_init(struct hdmi *hdmi)
 		return ERR_PTR(ret);
 	}
 
-	drm_mode_connector_attach_encoder(connector, hdmi->encoder);
+	drm_connector_attach_encoder(connector, hdmi->encoder);
 
 	return connector;
 }
diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c
index f0635c3da7f4..c1f1779c980f 100644
--- a/drivers/gpu/drm/msm/msm_atomic.c
+++ b/drivers/gpu/drm/msm/msm_atomic.c
@@ -71,12 +71,15 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state)
 
 	drm_atomic_helper_commit_modeset_enables(dev, state);
 
+	if (kms->funcs->commit) {
+		DRM_DEBUG_ATOMIC("triggering commit\n");
+		kms->funcs->commit(kms, state);
+	}
+
 	msm_atomic_wait_for_commit_done(dev, state);
 
 	kms->funcs->complete_commit(kms, state);
 
-	drm_atomic_helper_wait_for_vblanks(dev, state);
-
 	drm_atomic_helper_commit_hw_done(state);
 
 	drm_atomic_helper_cleanup_planes(dev, state);
diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index 1ff3fda245d1..f0da0d3c8a80 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/drivers/gpu/drm/msm/msm_debugfs.c
@@ -16,26 +16,101 @@
  */
 
 #ifdef CONFIG_DEBUG_FS
+#include <linux/debugfs.h>
 #include "msm_drv.h"
 #include "msm_gpu.h"
 #include "msm_kms.h"
 #include "msm_debugfs.h"
 
-static int msm_gpu_show(struct drm_device *dev, struct seq_file *m)
+struct msm_gpu_show_priv {
+	struct msm_gpu_state *state;
+	struct drm_device *dev;
+};
+
+static int msm_gpu_show(struct seq_file *m, void *arg)
+{
+	struct drm_printer p = drm_seq_file_printer(m);
+	struct msm_gpu_show_priv *show_priv = m->private;
+	struct msm_drm_private *priv = show_priv->dev->dev_private;
+	struct msm_gpu *gpu = priv->gpu;
+	int ret;
+
+	ret = mutex_lock_interruptible(&show_priv->dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	drm_printf(&p, "%s Status:\n", gpu->name);
+	gpu->funcs->show(gpu, show_priv->state, &p);
+
+	mutex_unlock(&show_priv->dev->struct_mutex);
+
+	return 0;
+}
+
+static int msm_gpu_release(struct inode *inode, struct file *file)
 {
+	struct seq_file *m = file->private_data;
+	struct msm_gpu_show_priv *show_priv = m->private;
+	struct msm_drm_private *priv = show_priv->dev->dev_private;
+	struct msm_gpu *gpu = priv->gpu;
+	int ret;
+
+	ret = mutex_lock_interruptible(&show_priv->dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	gpu->funcs->gpu_state_put(show_priv->state);
+	mutex_unlock(&show_priv->dev->struct_mutex);
+
+	kfree(show_priv);
+
+	return single_release(inode, file);
+}
+
+static int msm_gpu_open(struct inode *inode, struct file *file)
+{
+	struct drm_device *dev = inode->i_private;
 	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_gpu *gpu = priv->gpu;
+	struct msm_gpu_show_priv *show_priv;
+	int ret;
 
-	if (gpu) {
-		seq_printf(m, "%s Status:\n", gpu->name);
-		pm_runtime_get_sync(&gpu->pdev->dev);
-		gpu->funcs->show(gpu, m);
-		pm_runtime_put_sync(&gpu->pdev->dev);
+	if (!gpu)
+		return -ENODEV;
+
+	show_priv = kmalloc(sizeof(*show_priv), GFP_KERNEL);
+	if (!show_priv)
+		return -ENOMEM;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	pm_runtime_get_sync(&gpu->pdev->dev);
+	show_priv->state = gpu->funcs->gpu_state_get(gpu);
+	pm_runtime_put_sync(&gpu->pdev->dev);
+
+	mutex_unlock(&dev->struct_mutex);
+
+	if (IS_ERR(show_priv->state)) {
+		ret = PTR_ERR(show_priv->state);
+		kfree(show_priv);
+		return ret;
 	}
 
-	return 0;
+	show_priv->dev = dev;
+
+	return single_open(file, msm_gpu_show, show_priv);
 }
 
+static const struct file_operations msm_gpu_fops = {
+	.owner = THIS_MODULE,
+	.open = msm_gpu_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = msm_gpu_release,
+};
+
 static int msm_gem_show(struct drm_device *dev, struct seq_file *m)
 {
 	struct msm_drm_private *priv = dev->dev_private;
@@ -105,7 +180,6 @@ static int show_locked(struct seq_file *m, void *arg)
 }
 
 static struct drm_info_list msm_debugfs_list[] = {
-		{"gpu", show_locked, 0, msm_gpu_show},
 		{"gem", show_locked, 0, msm_gem_show},
 		{ "mm", show_locked, 0, msm_mm_show },
 		{ "fb", show_locked, 0, msm_fb_show },
@@ -158,6 +232,9 @@ int msm_debugfs_init(struct drm_minor *minor)
 		return ret;
 	}
 
+	debugfs_create_file("gpu", S_IRUSR, minor->debugfs_root,
+		dev, &msm_gpu_fops);
+
 	if (priv->kms->funcs->debugfs_init) {
 		ret = priv->kms->funcs->debugfs_init(priv->kms, minor);
 		if (ret)
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 021a0b6f9a59..46876bc8b707 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
  * Copyright (C) 2013 Red Hat
  * Author: Rob Clark <robdclark@gmail.com>
  *
@@ -15,6 +16,8 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/kthread.h>
+#include <uapi/linux/sched/types.h>
 #include <drm/drm_of.h>
 
 #include "msm_drv.h"
@@ -149,7 +152,7 @@ struct vblank_event {
 	bool enable;
 };
 
-static void vblank_ctrl_worker(struct work_struct *work)
+static void vblank_ctrl_worker(struct kthread_work *work)
 {
 	struct msm_vblank_ctrl *vbl_ctrl = container_of(work,
 						struct msm_vblank_ctrl, work);
@@ -197,7 +200,8 @@ static int vblank_ctrl_queue_work(struct msm_drm_private *priv,
 	list_add_tail(&vbl_ev->node, &vbl_ctrl->event_list);
 	spin_unlock_irqrestore(&vbl_ctrl->lock, flags);
 
-	queue_work(priv->wq, &vbl_ctrl->work);
+	kthread_queue_work(&priv->disp_thread[crtc_id].worker,
+			&vbl_ctrl->work);
 
 	return 0;
 }
@@ -208,19 +212,36 @@ static int msm_drm_uninit(struct device *dev)
 	struct drm_device *ddev = platform_get_drvdata(pdev);
 	struct msm_drm_private *priv = ddev->dev_private;
 	struct msm_kms *kms = priv->kms;
+	struct msm_mdss *mdss = priv->mdss;
 	struct msm_vblank_ctrl *vbl_ctrl = &priv->vblank_ctrl;
 	struct vblank_event *vbl_ev, *tmp;
+	int i;
 
 	/* We must cancel and cleanup any pending vblank enable/disable
 	 * work before drm_irq_uninstall() to avoid work re-enabling an
 	 * irq after uninstall has disabled it.
 	 */
-	cancel_work_sync(&vbl_ctrl->work);
+	kthread_flush_work(&vbl_ctrl->work);
 	list_for_each_entry_safe(vbl_ev, tmp, &vbl_ctrl->event_list, node) {
 		list_del(&vbl_ev->node);
 		kfree(vbl_ev);
 	}
 
+	/* clean up display commit/event worker threads */
+	for (i = 0; i < priv->num_crtcs; i++) {
+		if (priv->disp_thread[i].thread) {
+			kthread_flush_worker(&priv->disp_thread[i].worker);
+			kthread_stop(priv->disp_thread[i].thread);
+			priv->disp_thread[i].thread = NULL;
+		}
+
+		if (priv->event_thread[i].thread) {
+			kthread_flush_worker(&priv->event_thread[i].worker);
+			kthread_stop(priv->event_thread[i].thread);
+			priv->event_thread[i].thread = NULL;
+		}
+	}
+
 	msm_gem_shrinker_cleanup(ddev);
 
 	drm_kms_helper_poll_fini(ddev);
@@ -243,9 +264,6 @@ static int msm_drm_uninit(struct device *dev)
 	flush_workqueue(priv->wq);
 	destroy_workqueue(priv->wq);
 
-	flush_workqueue(priv->atomic_wq);
-	destroy_workqueue(priv->atomic_wq);
-
 	if (kms && kms->funcs)
 		kms->funcs->destroy(kms);
 
@@ -258,7 +276,8 @@ static int msm_drm_uninit(struct device *dev)
 
 	component_unbind_all(dev, ddev);
 
-	msm_mdss_destroy(ddev);
+	if (mdss && mdss->funcs)
+		mdss->funcs->destroy(ddev);
 
 	ddev->dev_private = NULL;
 	drm_dev_unref(ddev);
@@ -268,6 +287,10 @@ static int msm_drm_uninit(struct device *dev)
 	return 0;
 }
 
+#define KMS_MDP4 4
+#define KMS_MDP5 5
+#define KMS_DPU  3
+
 static int get_mdp_ver(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -357,7 +380,9 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	struct drm_device *ddev;
 	struct msm_drm_private *priv;
 	struct msm_kms *kms;
-	int ret;
+	struct msm_mdss *mdss;
+	int ret, i;
+	struct sched_param param;
 
 	ddev = drm_dev_alloc(drv, dev);
 	if (IS_ERR(ddev)) {
@@ -369,53 +394,61 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv) {
-		drm_dev_unref(ddev);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_unref_drm_dev;
 	}
 
 	ddev->dev_private = priv;
 	priv->dev = ddev;
 
-	ret = msm_mdss_init(ddev);
-	if (ret) {
-		kfree(priv);
-		drm_dev_unref(ddev);
-		return ret;
+	switch (get_mdp_ver(pdev)) {
+	case KMS_MDP5:
+		ret = mdp5_mdss_init(ddev);
+		break;
+	case KMS_DPU:
+		ret = dpu_mdss_init(ddev);
+		break;
+	default:
+		ret = 0;
+		break;
 	}
+	if (ret)
+		goto err_free_priv;
+
+	mdss = priv->mdss;
 
 	priv->wq = alloc_ordered_workqueue("msm", 0);
-	priv->atomic_wq = alloc_ordered_workqueue("msm:atomic", 0);
 
 	INIT_LIST_HEAD(&priv->inactive_list);
 	INIT_LIST_HEAD(&priv->vblank_ctrl.event_list);
-	INIT_WORK(&priv->vblank_ctrl.work, vblank_ctrl_worker);
+	kthread_init_work(&priv->vblank_ctrl.work, vblank_ctrl_worker);
 	spin_lock_init(&priv->vblank_ctrl.lock);
 
 	drm_mode_config_init(ddev);
 
 	/* Bind all our sub-components: */
 	ret = component_bind_all(dev, ddev);
-	if (ret) {
-		msm_mdss_destroy(ddev);
-		kfree(priv);
-		drm_dev_unref(ddev);
-		return ret;
-	}
+	if (ret)
+		goto err_destroy_mdss;
 
 	ret = msm_init_vram(ddev);
 	if (ret)
-		goto fail;
+		goto err_msm_uninit;
 
 	msm_gem_shrinker_init(ddev);
 
 	switch (get_mdp_ver(pdev)) {
-	case 4:
+	case KMS_MDP4:
 		kms = mdp4_kms_init(ddev);
 		priv->kms = kms;
 		break;
-	case 5:
+	case KMS_MDP5:
 		kms = mdp5_kms_init(ddev);
 		break;
+	case KMS_DPU:
+		kms = dpu_kms_init(ddev);
+		priv->kms = kms;
+		break;
 	default:
 		kms = ERR_PTR(-ENODEV);
 		break;
@@ -430,24 +463,100 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 		 */
 		dev_err(dev, "failed to load kms\n");
 		ret = PTR_ERR(kms);
-		goto fail;
+		goto err_msm_uninit;
 	}
 
+	/* Enable normalization of plane zpos */
+	ddev->mode_config.normalize_zpos = true;
+
 	if (kms) {
 		ret = kms->funcs->hw_init(kms);
 		if (ret) {
 			dev_err(dev, "kms hw init failed: %d\n", ret);
-			goto fail;
+			goto err_msm_uninit;
 		}
 	}
 
 	ddev->mode_config.funcs = &mode_config_funcs;
 	ddev->mode_config.helper_private = &mode_config_helper_funcs;
 
+	/**
+	 * this priority was found during empiric testing to have appropriate
+	 * realtime scheduling to process display updates and interact with
+	 * other real time and normal priority task
+	 */
+	param.sched_priority = 16;
+	for (i = 0; i < priv->num_crtcs; i++) {
+
+		/* initialize display thread */
+		priv->disp_thread[i].crtc_id = priv->crtcs[i]->base.id;
+		kthread_init_worker(&priv->disp_thread[i].worker);
+		priv->disp_thread[i].dev = ddev;
+		priv->disp_thread[i].thread =
+			kthread_run(kthread_worker_fn,
+				&priv->disp_thread[i].worker,
+				"crtc_commit:%d", priv->disp_thread[i].crtc_id);
+		ret = sched_setscheduler(priv->disp_thread[i].thread,
+							SCHED_FIFO, &param);
+		if (ret)
+			pr_warn("display thread priority update failed: %d\n",
+									ret);
+
+		if (IS_ERR(priv->disp_thread[i].thread)) {
+			dev_err(dev, "failed to create crtc_commit kthread\n");
+			priv->disp_thread[i].thread = NULL;
+		}
+
+		/* initialize event thread */
+		priv->event_thread[i].crtc_id = priv->crtcs[i]->base.id;
+		kthread_init_worker(&priv->event_thread[i].worker);
+		priv->event_thread[i].dev = ddev;
+		priv->event_thread[i].thread =
+			kthread_run(kthread_worker_fn,
+				&priv->event_thread[i].worker,
+				"crtc_event:%d", priv->event_thread[i].crtc_id);
+		/**
+		 * event thread should also run at same priority as disp_thread
+		 * because it is handling frame_done events. A lower priority
+		 * event thread and higher priority disp_thread can causes
+		 * frame_pending counters beyond 2. This can lead to commit
+		 * failure at crtc commit level.
+		 */
+		ret = sched_setscheduler(priv->event_thread[i].thread,
+							SCHED_FIFO, &param);
+		if (ret)
+			pr_warn("display event thread priority update failed: %d\n",
+									ret);
+
+		if (IS_ERR(priv->event_thread[i].thread)) {
+			dev_err(dev, "failed to create crtc_event kthread\n");
+			priv->event_thread[i].thread = NULL;
+		}
+
+		if ((!priv->disp_thread[i].thread) ||
+				!priv->event_thread[i].thread) {
+			/* clean up previously created threads if any */
+			for ( ; i >= 0; i--) {
+				if (priv->disp_thread[i].thread) {
+					kthread_stop(
+						priv->disp_thread[i].thread);
+					priv->disp_thread[i].thread = NULL;
+				}
+
+				if (priv->event_thread[i].thread) {
+					kthread_stop(
+						priv->event_thread[i].thread);
+					priv->event_thread[i].thread = NULL;
+				}
+			}
+			goto err_msm_uninit;
+		}
+	}
+
 	ret = drm_vblank_init(ddev, priv->num_crtcs);
 	if (ret < 0) {
 		dev_err(dev, "failed to initialize vblank\n");
-		goto fail;
+		goto err_msm_uninit;
 	}
 
 	if (kms) {
@@ -456,13 +565,13 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 		pm_runtime_put_sync(dev);
 		if (ret < 0) {
 			dev_err(dev, "failed to install IRQ handler\n");
-			goto fail;
+			goto err_msm_uninit;
 		}
 	}
 
 	ret = drm_dev_register(ddev, 0);
 	if (ret)
-		goto fail;
+		goto err_msm_uninit;
 
 	drm_mode_config_reset(ddev);
 
@@ -473,15 +582,23 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 
 	ret = msm_debugfs_late_init(ddev);
 	if (ret)
-		goto fail;
+		goto err_msm_uninit;
 
 	drm_kms_helper_poll_init(ddev);
 
 	return 0;
 
-fail:
+err_msm_uninit:
 	msm_drm_uninit(dev);
 	return ret;
+err_destroy_mdss:
+	if (mdss && mdss->funcs)
+		mdss->funcs->destroy(ddev);
+err_free_priv:
+	kfree(priv);
+err_unref_drm_dev:
+	drm_dev_unref(ddev);
+	return ret;
 }
 
 /*
@@ -894,16 +1011,35 @@ static struct drm_driver msm_driver = {
 static int msm_pm_suspend(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct msm_drm_private *priv = ddev->dev_private;
+	struct msm_kms *kms = priv->kms;
+
+	/* TODO: Use atomic helper suspend/resume */
+	if (kms && kms->funcs && kms->funcs->pm_suspend)
+		return kms->funcs->pm_suspend(dev);
 
 	drm_kms_helper_poll_disable(ddev);
 
+	priv->pm_state = drm_atomic_helper_suspend(ddev);
+	if (IS_ERR(priv->pm_state)) {
+		drm_kms_helper_poll_enable(ddev);
+		return PTR_ERR(priv->pm_state);
+	}
+
 	return 0;
 }
 
 static int msm_pm_resume(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct msm_drm_private *priv = ddev->dev_private;
+	struct msm_kms *kms = priv->kms;
+
+	/* TODO: Use atomic helper suspend/resume */
+	if (kms && kms->funcs && kms->funcs->pm_resume)
+		return kms->funcs->pm_resume(dev);
 
+	drm_atomic_helper_resume(ddev, priv->pm_state);
 	drm_kms_helper_poll_enable(ddev);
 
 	return 0;
@@ -915,11 +1051,12 @@ static int msm_runtime_suspend(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct msm_drm_private *priv = ddev->dev_private;
+	struct msm_mdss *mdss = priv->mdss;
 
 	DBG("");
 
-	if (priv->mdss)
-		return msm_mdss_disable(priv->mdss);
+	if (mdss && mdss->funcs)
+		return mdss->funcs->disable(mdss);
 
 	return 0;
 }
@@ -928,11 +1065,12 @@ static int msm_runtime_resume(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct msm_drm_private *priv = ddev->dev_private;
+	struct msm_mdss *mdss = priv->mdss;
 
 	DBG("");
 
-	if (priv->mdss)
-		return msm_mdss_enable(priv->mdss);
+	if (mdss && mdss->funcs)
+		return mdss->funcs->enable(mdss);
 
 	return 0;
 }
@@ -1031,12 +1169,13 @@ static int add_display_components(struct device *dev,
 	int ret;
 
 	/*
-	 * MDP5 based devices don't have a flat hierarchy. There is a top level
-	 * parent: MDSS, and children: MDP5, DSI, HDMI, eDP etc. Populate the
-	 * children devices, find the MDP5 node, and then add the interfaces
-	 * to our components list.
+	 * MDP5/DPU based devices don't have a flat hierarchy. There is a top
+	 * level parent: MDSS, and children: MDP5/DPU, DSI, HDMI, eDP etc.
+	 * Populate the children devices, find the MDP5/DPU node, and then add
+	 * the interfaces to our components list.
 	 */
-	if (of_device_is_compatible(dev->of_node, "qcom,mdss")) {
+	if (of_device_is_compatible(dev->of_node, "qcom,mdss") ||
+	    of_device_is_compatible(dev->of_node, "qcom,sdm845-mdss")) {
 		ret = of_platform_populate(dev->of_node, NULL, NULL, dev);
 		if (ret) {
 			dev_err(dev, "failed to populate children devices\n");
@@ -1146,8 +1285,9 @@ static int msm_pdev_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id dt_match[] = {
-	{ .compatible = "qcom,mdp4", .data = (void *)4 },	/* MDP4 */
-	{ .compatible = "qcom,mdss", .data = (void *)5 },	/* MDP5 MDSS */
+	{ .compatible = "qcom,mdp4", .data = (void *)KMS_MDP4 },
+	{ .compatible = "qcom,mdss", .data = (void *)KMS_MDP5 },
+	{ .compatible = "qcom,sdm845-mdss", .data = (void *)KMS_DPU },
 	{}
 };
 MODULE_DEVICE_TABLE(of, dt_match);
@@ -1169,6 +1309,7 @@ static int __init msm_drm_register(void)
 
 	DBG("init");
 	msm_mdp_register();
+	msm_dpu_register();
 	msm_dsi_register();
 	msm_edp_register();
 	msm_hdmi_register();
@@ -1185,6 +1326,7 @@ static void __exit msm_drm_unregister(void)
 	msm_edp_unregister();
 	msm_dsi_unregister();
 	msm_mdp_unregister();
+	msm_dpu_unregister();
 }
 
 module_init(msm_drm_register);
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index b2da1fbf81e0..0cba86ed3f54 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
  * Copyright (C) 2013 Red Hat
  * Author: Rob Clark <robdclark@gmail.com>
  *
@@ -33,6 +34,7 @@
 #include <linux/of_graph.h>
 #include <linux/of_device.h>
 #include <asm/sizes.h>
+#include <linux/kthread.h>
 
 #include <drm/drmP.h>
 #include <drm/drm_atomic.h>
@@ -54,6 +56,12 @@ struct msm_fence_context;
 struct msm_gem_address_space;
 struct msm_gem_vma;
 
+#define MAX_CRTCS      8
+#define MAX_PLANES     20
+#define MAX_ENCODERS   8
+#define MAX_BRIDGES    8
+#define MAX_CONNECTORS 8
+
 struct msm_file_private {
 	rwlock_t queuelock;
 	struct list_head submitqueues;
@@ -68,12 +76,77 @@ enum msm_mdp_plane_property {
 };
 
 struct msm_vblank_ctrl {
-	struct work_struct work;
+	struct kthread_work work;
 	struct list_head event_list;
 	spinlock_t lock;
 };
 
 #define MSM_GPU_MAX_RINGS 4
+#define MAX_H_TILES_PER_DISPLAY 2
+
+/**
+ * enum msm_display_caps - features/capabilities supported by displays
+ * @MSM_DISPLAY_CAP_VID_MODE:           Video or "active" mode supported
+ * @MSM_DISPLAY_CAP_CMD_MODE:           Command mode supported
+ * @MSM_DISPLAY_CAP_HOT_PLUG:           Hot plug detection supported
+ * @MSM_DISPLAY_CAP_EDID:               EDID supported
+ */
+enum msm_display_caps {
+	MSM_DISPLAY_CAP_VID_MODE	= BIT(0),
+	MSM_DISPLAY_CAP_CMD_MODE	= BIT(1),
+	MSM_DISPLAY_CAP_HOT_PLUG	= BIT(2),
+	MSM_DISPLAY_CAP_EDID		= BIT(3),
+};
+
+/**
+ * enum msm_event_wait - type of HW events to wait for
+ * @MSM_ENC_COMMIT_DONE - wait for the driver to flush the registers to HW
+ * @MSM_ENC_TX_COMPLETE - wait for the HW to transfer the frame to panel
+ * @MSM_ENC_VBLANK - wait for the HW VBLANK event (for driver-internal waiters)
+ */
+enum msm_event_wait {
+	MSM_ENC_COMMIT_DONE = 0,
+	MSM_ENC_TX_COMPLETE,
+	MSM_ENC_VBLANK,
+};
+
+/**
+ * struct msm_display_topology - defines a display topology pipeline
+ * @num_lm:       number of layer mixers used
+ * @num_enc:      number of compression encoder blocks used
+ * @num_intf:     number of interfaces the panel is mounted on
+ */
+struct msm_display_topology {
+	u32 num_lm;
+	u32 num_enc;
+	u32 num_intf;
+};
+
+/**
+ * struct msm_display_info - defines display properties
+ * @intf_type:          DRM_MODE_CONNECTOR_ display type
+ * @capabilities:       Bitmask of display flags
+ * @num_of_h_tiles:     Number of horizontal tiles in case of split interface
+ * @h_tile_instance:    Controller instance used per tile. Number of elements is
+ *                      based on num_of_h_tiles
+ * @is_te_using_watchdog_timer:  Boolean to indicate watchdog TE is
+ *				 used instead of panel TE in cmd mode panels
+ */
+struct msm_display_info {
+	int intf_type;
+	uint32_t capabilities;
+	uint32_t num_of_h_tiles;
+	uint32_t h_tile_instance[MAX_H_TILES_PER_DISPLAY];
+	bool is_te_using_watchdog_timer;
+};
+
+/* Commit/Event thread specific structure */
+struct msm_drm_thread {
+	struct drm_device *dev;
+	struct task_struct *thread;
+	unsigned int crtc_id;
+	struct kthread_worker worker;
+};
 
 struct msm_drm_private {
 
@@ -84,7 +157,7 @@ struct msm_drm_private {
 	/* subordinate devices, if present: */
 	struct platform_device *gpu_pdev;
 
-	/* top level MDSS wrapper device (for MDP5 only) */
+	/* top level MDSS wrapper device (for MDP5/DPU only) */
 	struct msm_mdss *mdss;
 
 	/* possibly this should be in the kms component, but it is
@@ -115,22 +188,24 @@ struct msm_drm_private {
 	struct list_head inactive_list;
 
 	struct workqueue_struct *wq;
-	struct workqueue_struct *atomic_wq;
 
 	unsigned int num_planes;
-	struct drm_plane *planes[16];
+	struct drm_plane *planes[MAX_PLANES];
 
 	unsigned int num_crtcs;
-	struct drm_crtc *crtcs[8];
+	struct drm_crtc *crtcs[MAX_CRTCS];
+
+	struct msm_drm_thread disp_thread[MAX_CRTCS];
+	struct msm_drm_thread event_thread[MAX_CRTCS];
 
 	unsigned int num_encoders;
-	struct drm_encoder *encoders[8];
+	struct drm_encoder *encoders[MAX_ENCODERS];
 
 	unsigned int num_bridges;
-	struct drm_bridge *bridges[8];
+	struct drm_bridge *bridges[MAX_BRIDGES];
 
 	unsigned int num_connectors;
-	struct drm_connector *connectors[8];
+	struct drm_connector *connectors[MAX_CONNECTORS];
 
 	/* Properties */
 	struct drm_property *plane_property[PLANE_PROP_MAX_NUM];
@@ -150,6 +225,7 @@ struct msm_drm_private {
 	struct shrinker shrinker;
 
 	struct msm_vblank_ctrl vblank_ctrl;
+	struct drm_atomic_state *pm_state;
 };
 
 struct msm_format {
@@ -174,6 +250,9 @@ struct msm_gem_address_space *
 msm_gem_address_space_create(struct device *dev, struct iommu_domain *domain,
 		const char *name);
 
+int msm_register_mmu(struct drm_device *dev, struct msm_mmu *mmu);
+void msm_unregister_mmu(struct drm_device *dev, struct msm_mmu *mmu);
+
 void msm_gem_submit_free(struct msm_gem_submit *submit);
 int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 		struct drm_file *file);
@@ -285,6 +364,8 @@ static inline int msm_dsi_modeset_init(struct msm_dsi *msm_dsi,
 
 void __init msm_mdp_register(void);
 void __exit msm_mdp_unregister(void);
+void __init msm_dpu_register(void);
+void __exit msm_dpu_unregister(void);
 
 #ifdef CONFIG_DEBUG_FS
 void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m);
diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c
index 7a16242bf8bf..2a7348aeb38d 100644
--- a/drivers/gpu/drm/msm/msm_fb.c
+++ b/drivers/gpu/drm/msm/msm_fb.c
@@ -17,6 +17,7 @@
 
 #include <drm/drm_crtc.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 
 #include "msm_drv.h"
 #include "msm_kms.h"
@@ -25,49 +26,20 @@
 struct msm_framebuffer {
 	struct drm_framebuffer base;
 	const struct msm_format *format;
-	struct drm_gem_object *planes[MAX_PLANE];
 };
 #define to_msm_framebuffer(x) container_of(x, struct msm_framebuffer, base)
 
 static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev,
 		const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object **bos);
 
-static int msm_framebuffer_create_handle(struct drm_framebuffer *fb,
-		struct drm_file *file_priv,
-		unsigned int *handle)
-{
-	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
-	return drm_gem_handle_create(file_priv,
-			msm_fb->planes[0], handle);
-}
-
-static void msm_framebuffer_destroy(struct drm_framebuffer *fb)
-{
-	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
-	int i, n = fb->format->num_planes;
-
-	DBG("destroy: FB ID: %d (%p)", fb->base.id, fb);
-
-	drm_framebuffer_cleanup(fb);
-
-	for (i = 0; i < n; i++) {
-		struct drm_gem_object *bo = msm_fb->planes[i];
-
-		drm_gem_object_put_unlocked(bo);
-	}
-
-	kfree(msm_fb);
-}
-
 static const struct drm_framebuffer_funcs msm_framebuffer_funcs = {
-	.create_handle = msm_framebuffer_create_handle,
-	.destroy = msm_framebuffer_destroy,
+	.create_handle = drm_gem_fb_create_handle,
+	.destroy = drm_gem_fb_destroy,
 };
 
 #ifdef CONFIG_DEBUG_FS
 void msm_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m)
 {
-	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
 	int i, n = fb->format->num_planes;
 
 	seq_printf(m, "fb: %dx%d@%4.4s (%2d, ID:%d)\n",
@@ -77,7 +49,7 @@ void msm_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m)
 	for (i = 0; i < n; i++) {
 		seq_printf(m, "   %d: offset=%d pitch=%d, obj: ",
 				i, fb->offsets[i], fb->pitches[i]);
-		msm_gem_describe(msm_fb->planes[i], m);
+		msm_gem_describe(fb->obj[i], m);
 	}
 }
 #endif
@@ -90,12 +62,11 @@ void msm_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m)
 int msm_framebuffer_prepare(struct drm_framebuffer *fb,
 		struct msm_gem_address_space *aspace)
 {
-	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
 	int ret, i, n = fb->format->num_planes;
 	uint64_t iova;
 
 	for (i = 0; i < n; i++) {
-		ret = msm_gem_get_iova(msm_fb->planes[i], aspace, &iova);
+		ret = msm_gem_get_iova(fb->obj[i], aspace, &iova);
 		DBG("FB[%u]: iova[%d]: %08llx (%d)", fb->base.id, i, iova, ret);
 		if (ret)
 			return ret;
@@ -107,26 +78,23 @@ int msm_framebuffer_prepare(struct drm_framebuffer *fb,
 void msm_framebuffer_cleanup(struct drm_framebuffer *fb,
 		struct msm_gem_address_space *aspace)
 {
-	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
 	int i, n = fb->format->num_planes;
 
 	for (i = 0; i < n; i++)
-		msm_gem_put_iova(msm_fb->planes[i], aspace);
+		msm_gem_put_iova(fb->obj[i], aspace);
 }
 
 uint32_t msm_framebuffer_iova(struct drm_framebuffer *fb,
 		struct msm_gem_address_space *aspace, int plane)
 {
-	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
-	if (!msm_fb->planes[plane])
+	if (!fb->obj[plane])
 		return 0;
-	return msm_gem_iova(msm_fb->planes[plane], aspace) + fb->offsets[plane];
+	return msm_gem_iova(fb->obj[plane], aspace) + fb->offsets[plane];
 }
 
 struct drm_gem_object *msm_framebuffer_bo(struct drm_framebuffer *fb, int plane)
 {
-	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
-	return msm_fb->planes[plane];
+	return drm_gem_fb_get_obj(fb, plane);
 }
 
 const struct msm_format *msm_framebuffer_format(struct drm_framebuffer *fb)
@@ -202,7 +170,7 @@ static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev,
 
 	msm_fb->format = format;
 
-	if (n > ARRAY_SIZE(msm_fb->planes)) {
+	if (n > ARRAY_SIZE(fb->obj)) {
 		ret = -EINVAL;
 		goto fail;
 	}
@@ -221,7 +189,7 @@ static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev,
 			goto fail;
 		}
 
-		msm_fb->planes[i] = bos[i];
+		msm_fb->base.obj[i] = bos[i];
 	}
 
 	drm_helper_mode_fill_fb_struct(dev, fb, mode_cmd);
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 1c09acfb4028..f388944c93e2 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -20,10 +20,11 @@
 #include "msm_mmu.h"
 #include "msm_fence.h"
 
+#include <generated/utsrelease.h>
 #include <linux/string_helpers.h>
 #include <linux/pm_opp.h>
 #include <linux/devfreq.h>
-
+#include <linux/devcoredump.h>
 
 /*
  * Power Management:
@@ -273,6 +274,123 @@ int msm_gpu_hw_init(struct msm_gpu *gpu)
 	return ret;
 }
 
+#ifdef CONFIG_DEV_COREDUMP
+static ssize_t msm_gpu_devcoredump_read(char *buffer, loff_t offset,
+		size_t count, void *data, size_t datalen)
+{
+	struct msm_gpu *gpu = data;
+	struct drm_print_iterator iter;
+	struct drm_printer p;
+	struct msm_gpu_state *state;
+
+	state = msm_gpu_crashstate_get(gpu);
+	if (!state)
+		return 0;
+
+	iter.data = buffer;
+	iter.offset = 0;
+	iter.start = offset;
+	iter.remain = count;
+
+	p = drm_coredump_printer(&iter);
+
+	drm_printf(&p, "---\n");
+	drm_printf(&p, "kernel: " UTS_RELEASE "\n");
+	drm_printf(&p, "module: " KBUILD_MODNAME "\n");
+	drm_printf(&p, "time: %lld.%09ld\n",
+		state->time.tv_sec, state->time.tv_nsec);
+	if (state->comm)
+		drm_printf(&p, "comm: %s\n", state->comm);
+	if (state->cmd)
+		drm_printf(&p, "cmdline: %s\n", state->cmd);
+
+	gpu->funcs->show(gpu, state, &p);
+
+	msm_gpu_crashstate_put(gpu);
+
+	return count - iter.remain;
+}
+
+static void msm_gpu_devcoredump_free(void *data)
+{
+	struct msm_gpu *gpu = data;
+
+	msm_gpu_crashstate_put(gpu);
+}
+
+static void msm_gpu_crashstate_get_bo(struct msm_gpu_state *state,
+		struct msm_gem_object *obj, u64 iova, u32 flags)
+{
+	struct msm_gpu_state_bo *state_bo = &state->bos[state->nr_bos];
+
+	/* Don't record write only objects */
+
+	state_bo->size = obj->base.size;
+	state_bo->iova = iova;
+
+	/* Only store the data for buffer objects marked for read */
+	if ((flags & MSM_SUBMIT_BO_READ)) {
+		void *ptr;
+
+		state_bo->data = kvmalloc(obj->base.size, GFP_KERNEL);
+		if (!state_bo->data)
+			return;
+
+		ptr = msm_gem_get_vaddr_active(&obj->base);
+		if (IS_ERR(ptr)) {
+			kvfree(state_bo->data);
+			return;
+		}
+
+		memcpy(state_bo->data, ptr, obj->base.size);
+		msm_gem_put_vaddr(&obj->base);
+	}
+
+	state->nr_bos++;
+}
+
+static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
+		struct msm_gem_submit *submit, char *comm, char *cmd)
+{
+	struct msm_gpu_state *state;
+
+	/* Only save one crash state at a time */
+	if (gpu->crashstate)
+		return;
+
+	state = gpu->funcs->gpu_state_get(gpu);
+	if (IS_ERR_OR_NULL(state))
+		return;
+
+	/* Fill in the additional crash state information */
+	state->comm = kstrdup(comm, GFP_KERNEL);
+	state->cmd = kstrdup(cmd, GFP_KERNEL);
+
+	if (submit) {
+		int i;
+
+		state->bos = kcalloc(submit->nr_bos,
+			sizeof(struct msm_gpu_state_bo), GFP_KERNEL);
+
+		for (i = 0; state->bos && i < submit->nr_bos; i++)
+			msm_gpu_crashstate_get_bo(state, submit->bos[i].obj,
+				submit->bos[i].iova, submit->bos[i].flags);
+	}
+
+	/* Set the active crash state to be dumped on failure */
+	gpu->crashstate = state;
+
+	/* FIXME: Release the crashstate if this errors out? */
+	dev_coredumpm(gpu->dev->dev, THIS_MODULE, gpu, 0, GFP_KERNEL,
+		msm_gpu_devcoredump_read, msm_gpu_devcoredump_free);
+}
+#else
+static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, char *comm,
+		char *cmd)
+{
+}
+#endif
+
 /*
  * Hangcheck detection for locked gpu:
  */
@@ -314,6 +432,7 @@ static void recover_worker(struct work_struct *work)
 	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_gem_submit *submit;
 	struct msm_ringbuffer *cur_ring = gpu->funcs->active_ring(gpu);
+	char *comm = NULL, *cmd = NULL;
 	int i;
 
 	mutex_lock(&dev->struct_mutex);
@@ -327,7 +446,7 @@ static void recover_worker(struct work_struct *work)
 		rcu_read_lock();
 		task = pid_task(submit->pid, PIDTYPE_PID);
 		if (task) {
-			char *cmd;
+			comm = kstrdup(task->comm, GFP_ATOMIC);
 
 			/*
 			 * So slightly annoying, in other paths like
@@ -340,22 +459,28 @@ static void recover_worker(struct work_struct *work)
 			 * about the submit going away.
 			 */
 			mutex_unlock(&dev->struct_mutex);
-			cmd = kstrdup_quotable_cmdline(task, GFP_KERNEL);
+			cmd = kstrdup_quotable_cmdline(task, GFP_ATOMIC);
 			mutex_lock(&dev->struct_mutex);
+		}
+		rcu_read_unlock();
 
+		if (comm && cmd) {
 			dev_err(dev->dev, "%s: offending task: %s (%s)\n",
-				gpu->name, task->comm, cmd);
+				gpu->name, comm, cmd);
 
 			msm_rd_dump_submit(priv->hangrd, submit,
-				"offending task: %s (%s)", task->comm, cmd);
-
-			kfree(cmd);
-		} else {
+				"offending task: %s (%s)", comm, cmd);
+		} else
 			msm_rd_dump_submit(priv->hangrd, submit, NULL);
-		}
-		rcu_read_unlock();
 	}
 
+	/* Record the crash state */
+	pm_runtime_get_sync(&gpu->pdev->dev);
+	msm_gpu_crashstate_capture(gpu, submit, comm, cmd);
+	pm_runtime_put_sync(&gpu->pdev->dev);
+
+	kfree(cmd);
+	kfree(comm);
 
 	/*
 	 * Update all the rings with the latest and greatest fence.. this
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index b8241179175a..1c6105bc55c7 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -27,6 +27,7 @@
 
 struct msm_gem_submit;
 struct msm_gpu_perfcntr;
+struct msm_gpu_state;
 
 struct msm_gpu_config {
 	const char *ioname;
@@ -64,11 +65,14 @@ struct msm_gpu_funcs {
 	void (*destroy)(struct msm_gpu *gpu);
 #ifdef CONFIG_DEBUG_FS
 	/* show GPU status in debugfs: */
-	void (*show)(struct msm_gpu *gpu, struct seq_file *m);
+	void (*show)(struct msm_gpu *gpu, struct msm_gpu_state *state,
+			struct drm_printer *p);
 	/* for generation specific debugfs: */
 	int (*debugfs_init)(struct msm_gpu *gpu, struct drm_minor *minor);
 #endif
 	int (*gpu_busy)(struct msm_gpu *gpu, uint64_t *value);
+	struct msm_gpu_state *(*gpu_state_get)(struct msm_gpu *gpu);
+	int (*gpu_state_put)(struct msm_gpu_state *state);
 };
 
 struct msm_gpu {
@@ -129,6 +133,8 @@ struct msm_gpu {
 		u64 busy_cycles;
 		ktime_t time;
 	} devfreq;
+
+	struct msm_gpu_state *crashstate;
 };
 
 /* It turns out that all targets use the same ringbuffer size */
@@ -175,6 +181,38 @@ struct msm_gpu_submitqueue {
 	struct kref ref;
 };
 
+struct msm_gpu_state_bo {
+	u64 iova;
+	size_t size;
+	void *data;
+};
+
+struct msm_gpu_state {
+	struct kref ref;
+	struct timespec64 time;
+
+	struct {
+		u64 iova;
+		u32 fence;
+		u32 seqno;
+		u32 rptr;
+		u32 wptr;
+		void *data;
+		int data_size;
+	} ring[MSM_GPU_MAX_RINGS];
+
+	int nr_registers;
+	u32 *registers;
+
+	u32 rbbm_status;
+
+	char *comm;
+	char *cmd;
+
+	int nr_bos;
+	struct msm_gpu_state_bo *bos;
+};
+
 static inline void gpu_write(struct msm_gpu *gpu, u32 reg, u32 data)
 {
 	msm_writel(data, gpu->mmio + (reg << 2));
@@ -254,4 +292,32 @@ static inline void msm_submitqueue_put(struct msm_gpu_submitqueue *queue)
 		kref_put(&queue->ref, msm_submitqueue_destroy);
 }
 
+static inline struct msm_gpu_state *msm_gpu_crashstate_get(struct msm_gpu *gpu)
+{
+	struct msm_gpu_state *state = NULL;
+
+	mutex_lock(&gpu->dev->struct_mutex);
+
+	if (gpu->crashstate) {
+		kref_get(&gpu->crashstate->ref);
+		state = gpu->crashstate;
+	}
+
+	mutex_unlock(&gpu->dev->struct_mutex);
+
+	return state;
+}
+
+static inline void msm_gpu_crashstate_put(struct msm_gpu *gpu)
+{
+	mutex_lock(&gpu->dev->struct_mutex);
+
+	if (gpu->crashstate) {
+		if (gpu->funcs->gpu_state_put(gpu->crashstate))
+			gpu->crashstate = NULL;
+	}
+
+	mutex_unlock(&gpu->dev->struct_mutex);
+}
+
 #endif /* __MSM_GPU_H__ */
diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h
index dfd92947de2c..fd88cebb6adb 100644
--- a/drivers/gpu/drm/msm/msm_kms.h
+++ b/drivers/gpu/drm/msm/msm_kms.h
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
  * Copyright (C) 2013 Red Hat
  * Author: Rob Clark <robdclark@gmail.com>
  *
@@ -42,6 +43,7 @@ struct msm_kms_funcs {
 	void (*disable_vblank)(struct msm_kms *kms, struct drm_crtc *crtc);
 	/* modeset, bracketing atomic_commit(): */
 	void (*prepare_commit)(struct msm_kms *kms, struct drm_atomic_state *state);
+	void (*commit)(struct msm_kms *kms, struct drm_atomic_state *state);
 	void (*complete_commit)(struct msm_kms *kms, struct drm_atomic_state *state);
 	/* functions to wait for atomic commit completed on each CRTC */
 	void (*wait_for_crtc_commit_done)(struct msm_kms *kms,
@@ -50,6 +52,11 @@ struct msm_kms_funcs {
 	const struct msm_format *(*get_format)(struct msm_kms *kms,
 					const uint32_t format,
 					const uint64_t modifiers);
+	/* do format checking on format modified through fb_cmd2 modifiers */
+	int (*check_modified_format)(const struct msm_kms *kms,
+			const struct msm_format *msm_fmt,
+			const struct drm_mode_fb_cmd2 *cmd,
+			struct drm_gem_object **bos);
 	/* misc: */
 	long (*round_pixclk)(struct msm_kms *kms, unsigned long rate,
 			struct drm_encoder *encoder);
@@ -60,6 +67,9 @@ struct msm_kms_funcs {
 	void (*set_encoder_mode)(struct msm_kms *kms,
 				 struct drm_encoder *encoder,
 				 bool cmd_mode);
+	/* pm suspend/resume hooks */
+	int (*pm_suspend)(struct device *dev);
+	int (*pm_resume)(struct device *dev);
 	/* cleanup: */
 	void (*destroy)(struct msm_kms *kms);
 #ifdef CONFIG_DEBUG_FS
@@ -86,9 +96,20 @@ static inline void msm_kms_init(struct msm_kms *kms,
 
 struct msm_kms *mdp4_kms_init(struct drm_device *dev);
 struct msm_kms *mdp5_kms_init(struct drm_device *dev);
-int msm_mdss_init(struct drm_device *dev);
-void msm_mdss_destroy(struct drm_device *dev);
-int msm_mdss_enable(struct msm_mdss *mdss);
-int msm_mdss_disable(struct msm_mdss *mdss);
+struct msm_kms *dpu_kms_init(struct drm_device *dev);
+
+struct msm_mdss_funcs {
+	int (*enable)(struct msm_mdss *mdss);
+	int (*disable)(struct msm_mdss *mdss);
+	void (*destroy)(struct drm_device *dev);
+};
+
+struct msm_mdss {
+	struct drm_device *dev;
+	const struct msm_mdss_funcs *funcs;
+};
+
+int mdp5_mdss_init(struct drm_device *dev);
+int dpu_mdss_init(struct drm_device *dev);
 
 #endif /* __MSM_KMS_H__ */
diff --git a/drivers/gpu/drm/nouveau/dispnv04/crtc.c b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
index 6aa6ee16dcbd..2c569e264df3 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/crtc.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
@@ -1017,7 +1017,7 @@ nv04_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv,
 	nv_crtc->cursor.set_offset(nv_crtc, nv_crtc->cursor.offset);
 	nv_crtc->cursor.show(nv_crtc, true);
 out:
-	drm_gem_object_unreference_unlocked(gem);
+	drm_gem_object_put_unlocked(gem);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/nouveau/dispnv04/dac.c b/drivers/gpu/drm/nouveau/dispnv04/dac.c
index 4feab0a5419d..e7af95d37ddb 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/dac.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/dac.c
@@ -556,6 +556,6 @@ nv04_dac_create(struct drm_connector *connector, struct dcb_output *entry)
 	encoder->possible_crtcs = entry->heads;
 	encoder->possible_clones = 0;
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/dispnv04/dfp.c b/drivers/gpu/drm/nouveau/dispnv04/dfp.c
index 9805d2cdc1a1..73d41abbb510 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/dfp.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/dfp.c
@@ -716,6 +716,6 @@ nv04_dfp_create(struct drm_connector *connector, struct dcb_output *entry)
 	    entry->location != DCB_LOC_ON_CHIP)
 		nv04_tmds_slave_init(encoder);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c b/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c
index 01664357d3e1..de4490b4ed30 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c
@@ -244,7 +244,7 @@ nv04_tv_create(struct drm_connector *connector, struct dcb_output *entry)
 
 	/* Attach it to the specified connector. */
 	get_slave_funcs(encoder)->create_resources(encoder, connector);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 
diff --git a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
index 6d99f11fee4e..6a4ca139cf5d 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
@@ -821,6 +821,6 @@ nv17_tv_create(struct drm_connector *connector, struct dcb_output *entry)
 	encoder->possible_clones = 0;
 
 	nv17_tv_create_resources(encoder, connector);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 9bae4db84cfb..8412119bd940 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -136,12 +136,24 @@ nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
 {
 	struct nouveau_cli *cli = (void *)device->object.client;
 	struct nv50_disp_core_channel_dma_v0 *args = data;
+	u8 type = NVIF_MEM_COHERENT;
 	int ret;
 
 	mutex_init(&dmac->lock);
 
-	ret = nvif_mem_init_map(&cli->mmu, NVIF_MEM_COHERENT, 0x1000,
-				&dmac->push);
+	/* Pascal added support for 47-bit physical addresses, but some
+	 * parts of EVO still only accept 40-bit PAs.
+	 *
+	 * To avoid issues on systems with large amounts of RAM, and on
+	 * systems where an IOMMU maps pages at a high address, we need
+	 * to allocate push buffers in VRAM instead.
+	 *
+	 * This appears to match NVIDIA's behaviour on Pascal.
+	 */
+	if (device->info.family == NV_DEVICE_INFO_V0_PASCAL)
+		type |= NVIF_MEM_VRAM;
+
+	ret = nvif_mem_init_map(&cli->mmu, type, 0x1000, &dmac->push);
 	if (ret)
 		return ret;
 
@@ -216,6 +228,19 @@ void
 evo_kick(u32 *push, struct nv50_dmac *evoc)
 {
 	struct nv50_dmac *dmac = evoc;
+
+	/* Push buffer fetches are not coherent with BAR1, we need to ensure
+	 * writes have been flushed right through to VRAM before writing PUT.
+	 */
+	if (dmac->push.type & NVIF_MEM_VRAM) {
+		struct nvif_device *device = dmac->base.device;
+		nvif_wr32(&device->object, 0x070000, 0x00000001);
+		nvif_msec(device, 2000,
+			if (!(nvif_rd32(&device->object, 0x070000) & 0x00000002))
+				break;
+		);
+	}
+
 	nvif_wr32(&dmac->base.user, 0x0000, (push - dmac->ptr) << 2);
 	mutex_unlock(&dmac->lock);
 }
@@ -424,7 +449,7 @@ nv50_dac_create(struct drm_connector *connector, struct dcb_output *dcbe)
 			 "dac-%04x-%04x", dcbe->hasht, dcbe->hashm);
 	drm_encoder_helper_add(encoder, &nv50_dac_help);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	return 0;
 }
 
@@ -850,7 +875,7 @@ nv50_mstc_get_modes(struct drm_connector *connector)
 	int ret = 0;
 
 	mstc->edid = drm_dp_mst_get_edid(&mstc->connector, mstc->port->mgr, mstc->port);
-	drm_mode_connector_update_edid_property(&mstc->connector, mstc->edid);
+	drm_connector_update_edid_property(&mstc->connector, mstc->edid);
 	if (mstc->edid)
 		ret = drm_add_edid_modes(&mstc->connector, mstc->edid);
 
@@ -927,11 +952,11 @@ nv50_mstc_new(struct nv50_mstm *mstm, struct drm_dp_mst_port *port,
 	nouveau_conn_attach_properties(&mstc->connector);
 
 	for (i = 0; i < ARRAY_SIZE(mstm->msto) && mstm->msto[i]; i++)
-		drm_mode_connector_attach_encoder(&mstc->connector, &mstm->msto[i]->encoder);
+		drm_connector_attach_encoder(&mstc->connector, &mstm->msto[i]->encoder);
 
 	drm_object_attach_property(&mstc->connector.base, dev->mode_config.path_property, 0);
 	drm_object_attach_property(&mstc->connector.base, dev->mode_config.tile_property, 0);
-	drm_mode_connector_set_path_property(&mstc->connector, path);
+	drm_connector_set_path_property(&mstc->connector, path);
 	return 0;
 }
 
@@ -1007,7 +1032,7 @@ nv50_mstm_destroy_connector(struct drm_dp_mst_topology_mgr *mgr,
 	mstc->port = NULL;
 	drm_modeset_unlock(&drm->dev->mode_config.connection_mutex);
 
-	drm_connector_unreference(&mstc->connector);
+	drm_connector_put(&mstc->connector);
 }
 
 static void
@@ -1418,7 +1443,7 @@ nv50_sor_create(struct drm_connector *connector, struct dcb_output *dcbe)
 			 "sor-%04x-%04x", dcbe->hasht, dcbe->hashm);
 	drm_encoder_helper_add(encoder, &nv50_sor_help);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	if (dcbe->type == DCB_OUTPUT_DP) {
 		struct nv50_disp *disp = nv50_disp(encoder->dev);
@@ -1576,7 +1601,7 @@ nv50_pior_create(struct drm_connector *connector, struct dcb_output *dcbe)
 			 "pior-%04x-%04x", dcbe->hasht, dcbe->hashm);
 	drm_encoder_helper_add(encoder, &nv50_pior_help);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	return 0;
 }
 
@@ -2232,6 +2257,9 @@ nv50_display_create(struct drm_device *dev)
 		connector->funcs->destroy(connector);
 	}
 
+	/* Disable vblank irqs aggressively for power-saving, safe on nv50+ */
+	dev->vblank_disable_immediate = true;
+
 out:
 	if (ret)
 		nv50_display_destroy(dev);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index c5a9bc1af5af..2187922e8dc2 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -586,7 +586,6 @@ nv50_wndw_new_(const struct nv50_wndw_func *func, struct drm_device *dev,
 	wndw->id = index;
 	wndw->interlock.type = interlock_type;
 	wndw->interlock.data = interlock_data;
-	wndw->ctxdma.parent = &wndw->wndw.base.user;
 
 	wndw->ctxdma.parent = &wndw->wndw.base.user;
 	INIT_LIST_HEAD(&wndw->ctxdma.list);
diff --git a/drivers/gpu/drm/nouveau/include/nvif/object.h b/drivers/gpu/drm/nouveau/include/nvif/object.h
index 20754d9e6883..8407651f6ac6 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/object.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/object.h
@@ -78,7 +78,7 @@ struct nvif_mclass {
 #define nvif_mclass(o,m) ({                                                    \
 	struct nvif_object *object = (o);                                      \
 	struct nvif_sclass *sclass;                                            \
-	const typeof(m[0]) *mclass = (m);                                      \
+	typeof(m[0]) *mclass = (m);                                            \
 	int ret = -ENODEV;                                                     \
 	int cnt, i, j;                                                         \
                                                                                \
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index e2211bb2cf79..e67a471331b5 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -139,7 +139,7 @@ nouveau_abi16_chan_fini(struct nouveau_abi16 *abi16,
 	if (chan->ntfy) {
 		nouveau_vma_del(&chan->ntfy_vma);
 		nouveau_bo_unpin(chan->ntfy);
-		drm_gem_object_unreference_unlocked(&chan->ntfy->gem);
+		drm_gem_object_put_unlocked(&chan->ntfy->gem);
 	}
 
 	if (chan->heap.block_size)
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index af68eae4c626..51932c72334e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -363,19 +363,11 @@ module_param_named(hdmimhz, nouveau_hdmimhz, int, 0400);
 struct nouveau_encoder *
 find_encoder(struct drm_connector *connector, int type)
 {
-	struct drm_device *dev = connector->dev;
 	struct nouveau_encoder *nv_encoder;
 	struct drm_encoder *enc;
-	int i, id;
-
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		id = connector->encoder_ids[i];
-		if (!id)
-			break;
+	int i;
 
-		enc = drm_encoder_find(dev, NULL, id);
-		if (!enc)
-			continue;
+	drm_connector_for_each_possible_encoder(connector, enc, i) {
 		nv_encoder = nouveau_encoder(enc);
 
 		if (type == DCB_OUTPUT_ANY ||
@@ -420,7 +412,7 @@ nouveau_connector_ddc_detect(struct drm_connector *connector)
 	struct nouveau_connector *nv_connector = nouveau_connector(connector);
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nvkm_gpio *gpio = nvxx_gpio(&drm->client.device);
-	struct nouveau_encoder *nv_encoder;
+	struct nouveau_encoder *nv_encoder = NULL;
 	struct drm_encoder *encoder;
 	int i, panel = -ENODEV;
 
@@ -436,14 +428,7 @@ nouveau_connector_ddc_detect(struct drm_connector *connector)
 		}
 	}
 
-	for (i = 0; nv_encoder = NULL, i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		int id = connector->encoder_ids[i];
-		if (id == 0)
-			break;
-
-		encoder = drm_encoder_find(dev, NULL, id);
-		if (!encoder)
-			continue;
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		nv_encoder = nouveau_encoder(encoder);
 
 		if (nv_encoder->dcb->type == DCB_OUTPUT_DP) {
@@ -565,7 +550,7 @@ nouveau_connector_detect(struct drm_connector *connector, bool force)
 
 	/* Cleanup the previous EDID block. */
 	if (nv_connector->edid) {
-		drm_mode_connector_update_edid_property(connector, NULL);
+		drm_connector_update_edid_property(connector, NULL);
 		kfree(nv_connector->edid);
 		nv_connector->edid = NULL;
 	}
@@ -590,7 +575,7 @@ nouveau_connector_detect(struct drm_connector *connector, bool force)
 		else
 			nv_connector->edid = drm_get_edid(connector, i2c);
 
-		drm_mode_connector_update_edid_property(connector,
+		drm_connector_update_edid_property(connector,
 							nv_connector->edid);
 		if (!nv_connector->edid) {
 			NV_ERROR(drm, "DDC responded, but no EDID for %s\n",
@@ -672,7 +657,7 @@ nouveau_connector_detect_lvds(struct drm_connector *connector, bool force)
 
 	/* Cleanup the previous EDID block. */
 	if (nv_connector->edid) {
-		drm_mode_connector_update_edid_property(connector, NULL);
+		drm_connector_update_edid_property(connector, NULL);
 		kfree(nv_connector->edid);
 		nv_connector->edid = NULL;
 	}
@@ -736,7 +721,7 @@ out:
 		status = connector_status_unknown;
 #endif
 
-	drm_mode_connector_update_edid_property(connector, nv_connector->edid);
+	drm_connector_update_edid_property(connector, nv_connector->edid);
 	nouveau_connector_set_encoder(connector, nv_encoder);
 	return status;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.c b/drivers/gpu/drm/nouveau/nouveau_debugfs.c
index 963a4dba8213..9109b69cd052 100644
--- a/drivers/gpu/drm/nouveau/nouveau_debugfs.c
+++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.c
@@ -160,7 +160,11 @@ nouveau_debugfs_pstate_set(struct file *file, const char __user *ubuf,
 		args.ustate = value;
 	}
 
+	ret = pm_runtime_get_sync(drm->dev);
+	if (IS_ERR_VALUE(ret) && ret != -EACCES)
+		return ret;
 	ret = nvif_mthd(ctrl, NVIF_CONTROL_PSTATE_USER, &args, sizeof(args));
+	pm_runtime_put_autosuspend(drm->dev);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index ec7861457b84..139368b31916 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -205,7 +205,7 @@ nouveau_user_framebuffer_destroy(struct drm_framebuffer *drm_fb)
 	struct nouveau_framebuffer *fb = nouveau_framebuffer(drm_fb);
 
 	if (fb->nvbo)
-		drm_gem_object_unreference_unlocked(&fb->nvbo->gem);
+		drm_gem_object_put_unlocked(&fb->nvbo->gem);
 
 	drm_framebuffer_cleanup(drm_fb);
 	kfree(fb);
@@ -287,7 +287,7 @@ nouveau_user_framebuffer_create(struct drm_device *dev,
 	if (ret == 0)
 		return &fb->base;
 
-	drm_gem_object_unreference_unlocked(gem);
+	drm_gem_object_put_unlocked(gem);
 	return ERR_PTR(ret);
 }
 
@@ -945,7 +945,7 @@ nouveau_display_dumb_create(struct drm_file *file_priv, struct drm_device *dev,
 		return ret;
 
 	ret = drm_gem_handle_create(file_priv, &bo->gem, &args->handle);
-	drm_gem_object_unreference_unlocked(&bo->gem);
+	drm_gem_object_put_unlocked(&bo->gem);
 	return ret;
 }
 
@@ -960,7 +960,7 @@ nouveau_display_dumb_map_offset(struct drm_file *file_priv,
 	if (gem) {
 		struct nouveau_bo *bo = nouveau_gem_object(gem);
 		*poffset = drm_vma_node_offset_addr(&bo->bo.vma_node);
-		drm_gem_object_unreference_unlocked(gem);
+		drm_gem_object_put_unlocked(gem);
 		return 0;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index f5d3158f0378..c7ec86d6c3c9 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -908,8 +908,10 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv)
 	get_task_comm(tmpname, current);
 	snprintf(name, sizeof(name), "%s[%d]", tmpname, pid_nr(fpriv->pid));
 
-	if (!(cli = kzalloc(sizeof(*cli), GFP_KERNEL)))
-		return ret;
+	if (!(cli = kzalloc(sizeof(*cli), GFP_KERNEL))) {
+		ret = -ENOMEM;
+		goto done;
+	}
 
 	ret = nouveau_cli_init(drm, name, cli);
 	if (ret)
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 85c1f10bc2b6..844498c4267c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -429,7 +429,7 @@ nouveau_fbcon_destroy(struct drm_device *dev, struct nouveau_fbdev *fbcon)
 		nouveau_vma_del(&nouveau_fb->vma);
 		nouveau_bo_unmap(nouveau_fb->nvbo);
 		nouveau_bo_unpin(nouveau_fb->nvbo);
-		drm_framebuffer_unreference(&nouveau_fb->base);
+		drm_framebuffer_put(&nouveau_fb->base);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index e6ccafcb9c41..b56524d343c3 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -274,7 +274,7 @@ nouveau_gem_ioctl_new(struct drm_device *dev, void *data,
 	}
 
 	/* drop reference from allocate - handle holds it now */
-	drm_gem_object_unreference_unlocked(&nvbo->gem);
+	drm_gem_object_put_unlocked(&nvbo->gem);
 	return ret;
 }
 
@@ -354,7 +354,7 @@ validate_fini_no_ticket(struct validate_op *op, struct nouveau_fence *fence,
 		list_del(&nvbo->entry);
 		nvbo->reserved_by = NULL;
 		ttm_bo_unreserve(&nvbo->bo);
-		drm_gem_object_unreference_unlocked(&nvbo->gem);
+		drm_gem_object_put_unlocked(&nvbo->gem);
 	}
 }
 
@@ -400,14 +400,14 @@ retry:
 		nvbo = nouveau_gem_object(gem);
 		if (nvbo == res_bo) {
 			res_bo = NULL;
-			drm_gem_object_unreference_unlocked(gem);
+			drm_gem_object_put_unlocked(gem);
 			continue;
 		}
 
 		if (nvbo->reserved_by && nvbo->reserved_by == file_priv) {
 			NV_PRINTK(err, cli, "multiple instances of buffer %d on "
 				      "validation list\n", b->handle);
-			drm_gem_object_unreference_unlocked(gem);
+			drm_gem_object_put_unlocked(gem);
 			ret = -EINVAL;
 			break;
 		}
@@ -894,7 +894,7 @@ nouveau_gem_ioctl_cpu_prep(struct drm_device *dev, void *data,
 		ret = lret;
 
 	nouveau_bo_sync_for_cpu(nvbo);
-	drm_gem_object_unreference_unlocked(gem);
+	drm_gem_object_put_unlocked(gem);
 
 	return ret;
 }
@@ -913,7 +913,7 @@ nouveau_gem_ioctl_cpu_fini(struct drm_device *dev, void *data,
 	nvbo = nouveau_gem_object(gem);
 
 	nouveau_bo_sync_for_device(nvbo);
-	drm_gem_object_unreference_unlocked(gem);
+	drm_gem_object_put_unlocked(gem);
 	return 0;
 }
 
@@ -930,7 +930,7 @@ nouveau_gem_ioctl_info(struct drm_device *dev, void *data,
 		return -ENOENT;
 
 	ret = nouveau_gem_info(file_priv, gem, req);
-	drm_gem_object_unreference_unlocked(gem);
+	drm_gem_object_put_unlocked(gem);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_hwmon.c b/drivers/gpu/drm/nouveau/nouveau_hwmon.c
index 44178b4c3599..08a1ab6b150d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_hwmon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_hwmon.c
@@ -69,8 +69,8 @@ nouveau_hwmon_set_temp1_auto_point1_temp(struct device *d,
 	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
 	long value;
 
-	if (kstrtol(buf, 10, &value) == -EINVAL)
-		return count;
+	if (kstrtol(buf, 10, &value))
+		return -EINVAL;
 
 	therm->attr_set(therm, NVKM_THERM_ATTR_THRS_FAN_BOOST,
 			value / 1000);
@@ -102,8 +102,8 @@ nouveau_hwmon_set_temp1_auto_point1_temp_hyst(struct device *d,
 	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
 	long value;
 
-	if (kstrtol(buf, 10, &value) == -EINVAL)
-		return count;
+	if (kstrtol(buf, 10, &value))
+		return -EINVAL;
 
 	therm->attr_set(therm, NVKM_THERM_ATTR_THRS_FAN_BOOST_HYST,
 			value / 1000);
@@ -156,7 +156,7 @@ nouveau_hwmon_set_pwm1_min(struct device *d, struct device_attribute *a,
 	long value;
 	int ret;
 
-	if (kstrtol(buf, 10, &value) == -EINVAL)
+	if (kstrtol(buf, 10, &value))
 		return -EINVAL;
 
 	ret = therm->attr_set(therm, NVKM_THERM_ATTR_FAN_MIN_DUTY, value);
@@ -179,7 +179,7 @@ nouveau_hwmon_set_pwm1_max(struct device *d, struct device_attribute *a,
 	long value;
 	int ret;
 
-	if (kstrtol(buf, 10, &value) == -EINVAL)
+	if (kstrtol(buf, 10, &value))
 		return -EINVAL;
 
 	ret = therm->attr_set(therm, NVKM_THERM_ATTR_FAN_MAX_DUTY, value);
diff --git a/drivers/gpu/drm/nouveau/nouveau_platform.c b/drivers/gpu/drm/nouveau/nouveau_platform.c
index 1ada186fab77..039e23548e08 100644
--- a/drivers/gpu/drm/nouveau/nouveau_platform.c
+++ b/drivers/gpu/drm/nouveau/nouveau_platform.c
@@ -36,7 +36,7 @@ static int nouveau_platform_probe(struct platform_device *pdev)
 
 	ret = drm_dev_register(drm, 0);
 	if (ret < 0) {
-		drm_dev_unref(drm);
+		drm_dev_put(drm);
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 8c093ca4222e..8edb9f2a4269 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -1,8 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /*
  * Copyright (c) 2007-2008 Tungsten Graphics, Inc., Cedar Park, TX., USA,
- * All Rights Reserved.
  * Copyright (c) 2009 VMware, Inc., Palo Alto, CA., USA,
- * All Rights Reserved.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/engine.c b/drivers/gpu/drm/nouveau/nvkm/core/engine.c
index d0322ce85172..1a47c40e171b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/engine.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/engine.c
@@ -87,11 +87,12 @@ nvkm_engine_info(struct nvkm_subdev *subdev, u64 mthd, u64 *data)
 {
 	struct nvkm_engine *engine = nvkm_engine(subdev);
 	if (engine->func->info) {
-		if ((engine = nvkm_engine_ref(engine))) {
+		if (!IS_ERR((engine = nvkm_engine_ref(engine)))) {
 			int ret = engine->func->info(engine, mthd, data);
 			nvkm_engine_unref(&engine);
 			return ret;
 		}
+		return PTR_ERR(engine);
 	}
 	return -ENOSYS;
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
index 78597da6313a..0e372a190d3f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
@@ -23,6 +23,10 @@
 #ifdef CONFIG_NOUVEAU_PLATFORM_DRIVER
 #include "priv.h"
 
+#if IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)
+#include <asm/dma-iommu.h>
+#endif
+
 static int
 nvkm_device_tegra_power_up(struct nvkm_device_tegra *tdev)
 {
@@ -105,6 +109,15 @@ nvkm_device_tegra_probe_iommu(struct nvkm_device_tegra *tdev)
 	unsigned long pgsize_bitmap;
 	int ret;
 
+#if IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)
+	if (dev->archdata.mapping) {
+		struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
+
+		arm_iommu_detach_device(dev);
+		arm_iommu_release_mapping(mapping);
+	}
+#endif
+
 	if (!tdev->func->iommu_bit)
 		return;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/changf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/changf119.c
index 29e6dd58ac48..525f95d06429 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/changf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/changf119.c
@@ -52,7 +52,7 @@ void
 gf119_disp_chan_intr(struct nv50_disp_chan *chan, bool en)
 {
 	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
-	const u64 mask = 0x00000001 << chan->chid.user;
+	const u32 mask = 0x00000001 << chan->chid.user;
 	if (!en) {
 		nvkm_mask(device, 0x610090, mask, 0x00000000);
 		nvkm_mask(device, 0x6100a0, mask, 0x00000000);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
index 57719f675eec..bcf32d92ee5a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
@@ -166,8 +166,8 @@ void
 nv50_disp_chan_intr(struct nv50_disp_chan *chan, bool en)
 {
 	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
-	const u64 mask = 0x00010001 << chan->chid.user;
-	const u64 data = en ? 0x00010000 : 0x00000000;
+	const u32 mask = 0x00010001 << chan->chid.user;
+	const u32 data = en ? 0x00010000 << chan->chid.user : 0x00000000;
 	nvkm_mask(device, 0x610028, mask, data);
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c
index 19173ea19096..3b3327789ae7 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c
@@ -25,24 +25,31 @@
 #include <nvif/class.h>
 
 static void
-gv100_gr_trap_mp(struct gf100_gr *gr, int gpc, int tpc)
+gv100_gr_trap_sm(struct gf100_gr *gr, int gpc, int tpc, int sm)
 {
 	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	u32 werr = nvkm_rd32(device, TPC_UNIT(gpc, tpc, 0x730));
-	u32 gerr = nvkm_rd32(device, TPC_UNIT(gpc, tpc, 0x734));
+	u32 werr = nvkm_rd32(device, TPC_UNIT(gpc, tpc, 0x730 + (sm * 0x80)));
+	u32 gerr = nvkm_rd32(device, TPC_UNIT(gpc, tpc, 0x734 + (sm * 0x80)));
 	const struct nvkm_enum *warp;
 	char glob[128];
 
 	nvkm_snprintbf(glob, sizeof(glob), gf100_mp_global_error, gerr);
 	warp = nvkm_enum_find(gf100_mp_warp_error, werr & 0xffff);
 
-	nvkm_error(subdev, "GPC%i/TPC%i/MP trap: "
+	nvkm_error(subdev, "GPC%i/TPC%i/SM%d trap: "
 			   "global %08x [%s] warp %04x [%s]\n",
-		   gpc, tpc, gerr, glob, werr, warp ? warp->name : "");
+		   gpc, tpc, sm, gerr, glob, werr, warp ? warp->name : "");
+
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x730 + sm * 0x80), 0x00000000);
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x734 + sm * 0x80), gerr);
+}
 
-	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x730), 0x00000000);
-	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x734), gerr);
+static void
+gv100_gr_trap_mp(struct gf100_gr *gr, int gpc, int tpc)
+{
+	gv100_gr_trap_sm(gr, gpc, tpc, 0);
+	gv100_gr_trap_sm(gr, gpc, tpc, 1);
 }
 
 static void
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/vpstate.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/vpstate.c
index 20b6fc8243e0..71524548de32 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/vpstate.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/vpstate.c
@@ -58,8 +58,14 @@ nvbios_vpstate_parse(struct nvkm_bios *b, struct nvbios_vpstate_header *h)
 		h->ecount   = nvbios_rd08(b, h->offset + 0x5);
 
 		h->base_id  = nvbios_rd08(b, h->offset + 0x0f);
-		h->boost_id = nvbios_rd08(b, h->offset + 0x10);
-		h->tdp_id   = nvbios_rd08(b, h->offset + 0x11);
+		if (h->hlen > 0x10)
+			h->boost_id = nvbios_rd08(b, h->offset + 0x10);
+		else
+			h->boost_id = 0xff;
+		if (h->hlen > 0x11)
+			h->tdp_id = nvbios_rd08(b, h->offset + 0x11);
+		else
+			h->tdp_id = 0xff;
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
index 007bf4af33b9..16ad91c91a7b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
@@ -133,8 +133,14 @@ nvkm_fault_oneinit(struct nvkm_subdev *subdev)
 		}
 	}
 
-	return nvkm_event_init(&nvkm_fault_ntfy, 1, fault->buffer_nr,
-			       &fault->event);
+	ret = nvkm_event_init(&nvkm_fault_ntfy, 1, fault->buffer_nr,
+			      &fault->event);
+	if (ret)
+		return ret;
+
+	if (fault->func->oneinit)
+		ret = fault->func->oneinit(fault);
+	return ret;
 }
 
 static void *
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c
index 73c7728b5969..3cd610d7deb5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c
@@ -176,8 +176,17 @@ gv100_fault_init(struct nvkm_fault *fault)
 	nvkm_notify_get(&fault->nrpfb);
 }
 
+static int
+gv100_fault_oneinit(struct nvkm_fault *fault)
+{
+	return nvkm_notify_init(&fault->buffer[0]->object, &fault->event,
+				gv100_fault_ntfy_nrpfb, false, NULL, 0, 0,
+				&fault->nrpfb);
+}
+
 static const struct nvkm_fault_func
 gv100_fault = {
+	.oneinit = gv100_fault_oneinit,
 	.init = gv100_fault_init,
 	.fini = gv100_fault_fini,
 	.intr = gv100_fault_intr,
@@ -192,15 +201,5 @@ int
 gv100_fault_new(struct nvkm_device *device, int index,
 		struct nvkm_fault **pfault)
 {
-	struct nvkm_fault *fault;
-	int ret;
-
-	ret = nvkm_fault_new_(&gv100_fault, device, index, &fault);
-	*pfault = fault;
-	if (ret)
-		return ret;
-
-	return nvkm_notify_init(&fault->buffer[0]->object, &fault->event,
-				gv100_fault_ntfy_nrpfb, false, NULL, 0, 0,
-				&fault->nrpfb);
+	return nvkm_fault_new_(&gv100_fault, device, index, pfault);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h
index 44843ecf12b0..e4d2f5234fd1 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h
@@ -20,6 +20,7 @@ int nvkm_fault_new_(const struct nvkm_fault_func *, struct nvkm_device *,
 		    int index, struct nvkm_fault **);
 
 struct nvkm_fault_func {
+	int (*oneinit)(struct nvkm_fault *);
 	void (*init)(struct nvkm_fault *);
 	void (*fini)(struct nvkm_fault *);
 	void (*intr)(struct nvkm_fault *);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gp10b. b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gp10b.
deleted file mode 100644
index e69de29bb2d1..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gp10b.
+++ /dev/null
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r352.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r352.c
index a721354249ce..d02e183717dc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r352.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r352.c
@@ -414,6 +414,20 @@ acr_r352_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
 {
 	struct ls_ucode_img *_img;
 	u32 pos = 0;
+	u32 max_desc_size = 0;
+	u8 *gdesc;
+
+	/* Figure out how large we need gdesc to be. */
+	list_for_each_entry(_img, imgs, node) {
+		const struct acr_r352_ls_func *ls_func =
+					    acr->func->ls_func[_img->falcon_id];
+
+		max_desc_size = max(max_desc_size, ls_func->bl_desc_size);
+	}
+
+	gdesc = kmalloc(max_desc_size, GFP_KERNEL);
+	if (!gdesc)
+		return -ENOMEM;
 
 	nvkm_kmap(wpr_blob);
 
@@ -421,7 +435,6 @@ acr_r352_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
 		struct ls_ucode_img_r352 *img = ls_ucode_img_r352(_img);
 		const struct acr_r352_ls_func *ls_func =
 					    acr->func->ls_func[_img->falcon_id];
-		u8 gdesc[ls_func->bl_desc_size];
 
 		nvkm_gpuobj_memcpy_to(wpr_blob, pos, &img->wpr_header,
 				      sizeof(img->wpr_header));
@@ -447,6 +460,8 @@ acr_r352_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
 
 	nvkm_done(wpr_blob);
 
+	kfree(gdesc);
+
 	return 0;
 }
 
@@ -771,7 +786,11 @@ acr_r352_load(struct nvkm_acr *_acr, struct nvkm_falcon *falcon,
 	struct fw_bl_desc *hsbl_desc;
 	void *bl, *blob_data, *hsbl_code, *hsbl_data;
 	u32 code_size;
-	u8 bl_desc[bl_desc_size];
+	u8 *bl_desc;
+
+	bl_desc = kzalloc(bl_desc_size, GFP_KERNEL);
+	if (!bl_desc)
+		return -ENOMEM;
 
 	/* Find the bootloader descriptor for our blob and copy it */
 	if (blob == acr->load_blob) {
@@ -802,7 +821,6 @@ acr_r352_load(struct nvkm_acr *_acr, struct nvkm_falcon *falcon,
 			      code_size, hsbl_desc->start_tag, 0, false);
 
 	/* Generate the BL header */
-	memset(bl_desc, 0, bl_desc_size);
 	acr->func->generate_hs_bl_desc(load_hdr, bl_desc, offset);
 
 	/*
@@ -811,6 +829,7 @@ acr_r352_load(struct nvkm_acr *_acr, struct nvkm_falcon *falcon,
 	nvkm_falcon_load_dmem(falcon, bl_desc, hsbl_desc->dmem_load_off,
 			      bl_desc_size, 0);
 
+	kfree(bl_desc);
 	return hsbl_desc->start_tag << 8;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.c
index 866877b88797..978ad0790367 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.c
@@ -265,6 +265,19 @@ acr_r367_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
 {
 	struct ls_ucode_img *_img;
 	u32 pos = 0;
+	u32 max_desc_size = 0;
+	u8 *gdesc;
+
+	list_for_each_entry(_img, imgs, node) {
+		const struct acr_r352_ls_func *ls_func =
+					    acr->func->ls_func[_img->falcon_id];
+
+		max_desc_size = max(max_desc_size, ls_func->bl_desc_size);
+	}
+
+	gdesc = kmalloc(max_desc_size, GFP_KERNEL);
+	if (!gdesc)
+		return -ENOMEM;
 
 	nvkm_kmap(wpr_blob);
 
@@ -272,7 +285,6 @@ acr_r367_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
 		struct ls_ucode_img_r367 *img = ls_ucode_img_r367(_img);
 		const struct acr_r352_ls_func *ls_func =
 					    acr->func->ls_func[_img->falcon_id];
-		u8 gdesc[ls_func->bl_desc_size];
 
 		nvkm_gpuobj_memcpy_to(wpr_blob, pos, &img->wpr_header,
 				      sizeof(img->wpr_header));
@@ -298,6 +310,8 @@ acr_r367_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
 
 	nvkm_done(wpr_blob);
 
+	kfree(gdesc);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
index 30491d132d59..df8b919dcf09 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
@@ -129,6 +129,7 @@ gm20b_secboot_new(struct nvkm_device *device, int index,
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC)
 MODULE_FIRMWARE("nvidia/gm20b/acr/bl.bin");
 MODULE_FIRMWARE("nvidia/gm20b/acr/ucode_load.bin");
 MODULE_FIRMWARE("nvidia/gm20b/gr/fecs_bl.bin");
@@ -144,3 +145,4 @@ MODULE_FIRMWARE("nvidia/gm20b/gr/sw_method_init.bin");
 MODULE_FIRMWARE("nvidia/gm20b/pmu/desc.bin");
 MODULE_FIRMWARE("nvidia/gm20b/pmu/image.bin");
 MODULE_FIRMWARE("nvidia/gm20b/pmu/sig.bin");
+#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp10b.c
index 632e9545e292..28ca29d0eeee 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp10b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp10b.c
@@ -74,6 +74,7 @@ gp10b_secboot_new(struct nvkm_device *device, int index,
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_ARCH_TEGRA_186_SOC)
 MODULE_FIRMWARE("nvidia/gp10b/acr/bl.bin");
 MODULE_FIRMWARE("nvidia/gp10b/acr/ucode_load.bin");
 MODULE_FIRMWARE("nvidia/gp10b/gr/fecs_bl.bin");
@@ -91,3 +92,4 @@ MODULE_FIRMWARE("nvidia/gp10b/gr/sw_method_init.bin");
 MODULE_FIRMWARE("nvidia/gp10b/pmu/desc.bin");
 MODULE_FIRMWARE("nvidia/gp10b/pmu/image.bin");
 MODULE_FIRMWARE("nvidia/gp10b/pmu/sig.bin");
+#endif
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c b/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c
index 92fe125ce22e..f34c06bb5bd7 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c
@@ -4,7 +4,7 @@
  * Copyright (C) 2010 Nokia Corporation
  *
  * Original Driver Author: Imre Deak <imre.deak@nokia.com>
- * Based on panel-generic.c by Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Based on panel-generic.c by Tomi Valkeinen <tomi.valkeinen@ti.com>
  * Adapted to new DSS2 framework: Roger Quadros <roger.quadros@nokia.com>
  *
  * This program is free software; you can redistribute it and/or modify it
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-tpo-td028ttec1.c b/drivers/gpu/drm/omapdrm/displays/panel-tpo-td028ttec1.c
index b5d8a00df811..a1f1dc18407a 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-tpo-td028ttec1.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-tpo-td028ttec1.c
@@ -2,7 +2,7 @@
  * Toppoly TD028TTEC1 panel support
  *
  * Copyright (C) 2008 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * Neo 1973 code (jbt6k74.c):
  * Copyright (C) 2006-2007 by OpenMoko, Inc.
diff --git a/drivers/gpu/drm/omapdrm/dss/core.c b/drivers/gpu/drm/omapdrm/dss/core.c
index acef7ece5783..07d00a186f15 100644
--- a/drivers/gpu/drm/omapdrm/dss/core.c
+++ b/drivers/gpu/drm/omapdrm/dss/core.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2009 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * Some code and ideas taken from drivers/video/omap/ driver
  * by Imre Deak.
@@ -82,7 +82,7 @@ static void __exit omap_dss_exit(void)
 module_init(omap_dss_init);
 module_exit(omap_dss_exit);
 
-MODULE_AUTHOR("Tomi Valkeinen <tomi.valkeinen@nokia.com>");
+MODULE_AUTHOR("Tomi Valkeinen <tomi.valkeinen@ti.com>");
 MODULE_DESCRIPTION("OMAP2/3 Display Subsystem");
 MODULE_LICENSE("GPL v2");
 
diff --git a/drivers/gpu/drm/omapdrm/dss/dispc.c b/drivers/gpu/drm/omapdrm/dss/dispc.c
index 7f3ac6b13b56..84f274c4a4cb 100644
--- a/drivers/gpu/drm/omapdrm/dss/dispc.c
+++ b/drivers/gpu/drm/omapdrm/dss/dispc.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2009 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * Some code and ideas taken from drivers/video/omap/ driver
  * by Imre Deak.
diff --git a/drivers/gpu/drm/omapdrm/dss/display.c b/drivers/gpu/drm/omapdrm/dss/display.c
index 424143128cd4..9e7fcbd57e52 100644
--- a/drivers/gpu/drm/omapdrm/dss/display.c
+++ b/drivers/gpu/drm/omapdrm/dss/display.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2009 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * Some code and ideas taken from drivers/video/omap/ driver
  * by Imre Deak.
diff --git a/drivers/gpu/drm/omapdrm/dss/dpi.c b/drivers/gpu/drm/omapdrm/dss/dpi.c
index 3d662e6805eb..9fcc50217133 100644
--- a/drivers/gpu/drm/omapdrm/dss/dpi.c
+++ b/drivers/gpu/drm/omapdrm/dss/dpi.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2009 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * Some code and ideas taken from drivers/video/omap/ driver
  * by Imre Deak.
diff --git a/drivers/gpu/drm/omapdrm/dss/dsi.c b/drivers/gpu/drm/omapdrm/dss/dsi.c
index d4a680629825..74467b308721 100644
--- a/drivers/gpu/drm/omapdrm/dss/dsi.c
+++ b/drivers/gpu/drm/omapdrm/dss/dsi.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2009 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License version 2 as published by
diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c
index 0b908e9de792..cb80ddaa19d2 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss.c
+++ b/drivers/gpu/drm/omapdrm/dss/dss.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2009 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * Some code and ideas taken from drivers/video/omap/ driver
  * by Imre Deak.
diff --git a/drivers/gpu/drm/omapdrm/dss/dss.h b/drivers/gpu/drm/omapdrm/dss/dss.h
index 847c78ade024..38302631b64b 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss.h
+++ b/drivers/gpu/drm/omapdrm/dss/dss.h
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2009 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * Some code and ideas taken from drivers/video/omap/ driver
  * by Imre Deak.
@@ -180,6 +180,9 @@ struct dss_pll_hw {
 
 	/* DRA7 errata i886: use high N & M to avoid jitter */
 	bool errata_i886;
+
+	/* DRA7 errata i932: retry pll lock on failure */
+	bool errata_i932;
 };
 
 struct dss_pll {
diff --git a/drivers/gpu/drm/omapdrm/dss/pll.c b/drivers/gpu/drm/omapdrm/dss/pll.c
index 078b0e8216c3..ff362b38bf0d 100644
--- a/drivers/gpu/drm/omapdrm/dss/pll.c
+++ b/drivers/gpu/drm/omapdrm/dss/pll.c
@@ -16,6 +16,7 @@
 
 #define DSS_SUBSYS_NAME "PLL"
 
+#include <linux/delay.h>
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
@@ -381,6 +382,22 @@ static int dss_wait_hsdiv_ack(struct dss_pll *pll, u32 hsdiv_ack_mask)
 	return -ETIMEDOUT;
 }
 
+static bool pll_is_locked(u32 stat)
+{
+	/*
+	 * Required value for each bitfield listed below
+	 *
+	 * PLL_STATUS[6] = 0  PLL_BYPASS
+	 * PLL_STATUS[5] = 0  PLL_HIGHJITTER
+	 *
+	 * PLL_STATUS[3] = 0  PLL_LOSSREF
+	 * PLL_STATUS[2] = 0  PLL_RECAL
+	 * PLL_STATUS[1] = 1  PLL_LOCK
+	 * PLL_STATUS[0] = 1  PLL_CTRL_RESET_DONE
+	 */
+	return ((stat & 0x6f) == 0x3);
+}
+
 int dss_pll_write_config_type_a(struct dss_pll *pll,
 		const struct dss_pll_clock_info *cinfo)
 {
@@ -436,18 +453,54 @@ int dss_pll_write_config_type_a(struct dss_pll *pll,
 	l = FLD_MOD(l, 0, 25, 25);		/* M7_CLOCK_EN */
 	writel_relaxed(l, base + PLL_CONFIGURATION2);
 
-	writel_relaxed(1, base + PLL_GO);	/* PLL_GO */
+	if (hw->errata_i932) {
+		int cnt = 0;
+		u32 sleep_time;
+		const u32 max_lock_retries = 20;
 
-	if (wait_for_bit_change(base + PLL_GO, 0, 0) != 0) {
-		DSSERR("DSS DPLL GO bit not going down.\n");
-		r = -EIO;
-		goto err;
-	}
+		/*
+		 * Calculate wait time for PLL LOCK
+		 * 1000 REFCLK cycles in us.
+		 */
+		sleep_time = DIV_ROUND_UP(1000*1000*1000, cinfo->fint);
 
-	if (wait_for_bit_change(base + PLL_STATUS, 1, 1) != 1) {
-		DSSERR("cannot lock DSS DPLL\n");
-		r = -EIO;
-		goto err;
+		for (cnt = 0; cnt < max_lock_retries; cnt++) {
+			writel_relaxed(1, base + PLL_GO);	/* PLL_GO */
+
+			/**
+			 * read the register back to ensure the write is
+			 * flushed
+			 */
+			readl_relaxed(base + PLL_GO);
+
+			usleep_range(sleep_time, sleep_time + 5);
+			l = readl_relaxed(base + PLL_STATUS);
+
+			if (pll_is_locked(l) &&
+			    !(readl_relaxed(base + PLL_GO) & 0x1))
+				break;
+
+		}
+
+		if (cnt == max_lock_retries) {
+			DSSERR("cannot lock PLL\n");
+			r = -EIO;
+			goto err;
+		}
+	} else {
+		writel_relaxed(1, base + PLL_GO);	/* PLL_GO */
+
+		if (wait_for_bit_change(base + PLL_GO, 0, 0) != 0) {
+			DSSERR("DSS DPLL GO bit not going down.\n");
+			r = -EIO;
+			goto err;
+		}
+
+		if (wait_for_bit_change(base + PLL_STATUS, 1, 1) != 1) {
+			DSSERR("cannot lock DSS DPLL\n");
+			r = -EIO;
+			goto err;
+		}
 	}
 
 	l = readl_relaxed(base + PLL_CONFIGURATION2);
diff --git a/drivers/gpu/drm/omapdrm/dss/sdi.c b/drivers/gpu/drm/omapdrm/dss/sdi.c
index 1e2c931f6acf..69c3b7a3d5c7 100644
--- a/drivers/gpu/drm/omapdrm/dss/sdi.c
+++ b/drivers/gpu/drm/omapdrm/dss/sdi.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2009 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License version 2 as published by
diff --git a/drivers/gpu/drm/omapdrm/dss/venc.c b/drivers/gpu/drm/omapdrm/dss/venc.c
index 24d1ced210bd..ac01907dcc34 100644
--- a/drivers/gpu/drm/omapdrm/dss/venc.c
+++ b/drivers/gpu/drm/omapdrm/dss/venc.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2009 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * VENC settings from TI's DSS driver
  *
diff --git a/drivers/gpu/drm/omapdrm/dss/video-pll.c b/drivers/gpu/drm/omapdrm/dss/video-pll.c
index 585ed94ccf17..cb46311f92c9 100644
--- a/drivers/gpu/drm/omapdrm/dss/video-pll.c
+++ b/drivers/gpu/drm/omapdrm/dss/video-pll.c
@@ -134,6 +134,7 @@ static const struct dss_pll_hw dss_dra7_video_pll_hw = {
 	.has_refsel = true,
 
 	.errata_i886 = true,
+	.errata_i932 = true,
 };
 
 struct dss_pll *dss_video_pll_init(struct dss_device *dss,
diff --git a/drivers/gpu/drm/omapdrm/omap_connector.c b/drivers/gpu/drm/omapdrm/omap_connector.c
index 5cde26ac937b..2ddb856666c4 100644
--- a/drivers/gpu/drm/omapdrm/omap_connector.c
+++ b/drivers/gpu/drm/omapdrm/omap_connector.c
@@ -126,14 +126,14 @@ static int omap_connector_get_modes(struct drm_connector *connector)
 
 		if ((dssdrv->read_edid(dssdev, edid, MAX_EDID) > 0) &&
 				drm_edid_is_valid(edid)) {
-			drm_mode_connector_update_edid_property(
+			drm_connector_update_edid_property(
 					connector, edid);
 			n = drm_add_edid_modes(connector, edid);
 
 			omap_connector->hdmi_mode =
 				drm_detect_hdmi_monitor(edid);
 		} else {
-			drm_mode_connector_update_edid_property(
+			drm_connector_update_edid_property(
 					connector, NULL);
 		}
 
diff --git a/drivers/gpu/drm/omapdrm/omap_debugfs.c b/drivers/gpu/drm/omapdrm/omap_debugfs.c
index b42e286616b0..91cf043f2b6b 100644
--- a/drivers/gpu/drm/omapdrm/omap_debugfs.c
+++ b/drivers/gpu/drm/omapdrm/omap_debugfs.c
@@ -30,16 +30,11 @@ static int gem_show(struct seq_file *m, void *arg)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct omap_drm_private *priv = dev->dev_private;
-	int ret;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
 
 	seq_printf(m, "All Objects:\n");
+	mutex_lock(&priv->list_lock);
 	omap_gem_describe_objects(&priv->obj_list, m);
-
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&priv->list_lock);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c
index ef3b0e3571ec..1b6601e9b107 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.c
+++ b/drivers/gpu/drm/omapdrm/omap_drv.c
@@ -274,7 +274,7 @@ static int omap_modeset_init(struct drm_device *dev)
 		if (IS_ERR(crtc))
 			return PTR_ERR(crtc);
 
-		drm_mode_connector_attach_encoder(connector, encoder);
+		drm_connector_attach_encoder(connector, encoder);
 		encoder->possible_crtcs = (1 << crtc_idx);
 
 		priv->crtcs[priv->num_crtcs++] = crtc;
@@ -493,7 +493,7 @@ static struct drm_driver omap_drm_driver = {
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_export = omap_gem_prime_export,
 	.gem_prime_import = omap_gem_prime_import,
-	.gem_free_object = omap_gem_free_object,
+	.gem_free_object_unlocked = omap_gem_free_object,
 	.gem_vm_ops = &omap_gem_vm_ops,
 	.dumb_create = omap_gem_dumb_create,
 	.dumb_map_offset = omap_gem_dumb_map_offset,
@@ -540,7 +540,7 @@ static int omapdrm_init(struct omap_drm_private *priv, struct device *dev)
 	priv->omaprev = soc ? (unsigned int)soc->data : 0;
 	priv->wq = alloc_ordered_workqueue("omapdrm", 0);
 
-	spin_lock_init(&priv->list_lock);
+	mutex_init(&priv->list_lock);
 	INIT_LIST_HEAD(&priv->obj_list);
 
 	/* Allocate and initialize the DRM device. */
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.h b/drivers/gpu/drm/omapdrm/omap_drv.h
index 6eaee4df4559..f27c8e216adf 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.h
+++ b/drivers/gpu/drm/omapdrm/omap_drv.h
@@ -71,7 +71,7 @@ struct omap_drm_private {
 	struct workqueue_struct *wq;
 
 	/* lock for obj_list below */
-	spinlock_t list_lock;
+	struct mutex list_lock;
 
 	/* list of GEM objects: */
 	struct list_head obj_list;
diff --git a/drivers/gpu/drm/omapdrm/omap_fb.c b/drivers/gpu/drm/omapdrm/omap_fb.c
index 5fd22ca73913..9f1e3d8f8488 100644
--- a/drivers/gpu/drm/omapdrm/omap_fb.c
+++ b/drivers/gpu/drm/omapdrm/omap_fb.c
@@ -19,6 +19,7 @@
 
 #include <drm/drm_crtc.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 
 #include "omap_dmm_tiler.h"
 #include "omap_drv.h"
@@ -51,9 +52,6 @@ static const u32 formats[] = {
 
 /* per-plane info for the fb: */
 struct plane {
-	struct drm_gem_object *bo;
-	u32 pitch;
-	u32 offset;
 	dma_addr_t dma_addr;
 };
 
@@ -68,56 +66,28 @@ struct omap_framebuffer {
 	struct mutex lock;
 };
 
-static int omap_framebuffer_create_handle(struct drm_framebuffer *fb,
-		struct drm_file *file_priv,
-		unsigned int *handle)
-{
-	struct omap_framebuffer *omap_fb = to_omap_framebuffer(fb);
-	return drm_gem_handle_create(file_priv,
-			omap_fb->planes[0].bo, handle);
-}
-
-static void omap_framebuffer_destroy(struct drm_framebuffer *fb)
-{
-	struct omap_framebuffer *omap_fb = to_omap_framebuffer(fb);
-	int i, n = fb->format->num_planes;
-
-	DBG("destroy: FB ID: %d (%p)", fb->base.id, fb);
-
-	drm_framebuffer_cleanup(fb);
-
-	for (i = 0; i < n; i++) {
-		struct plane *plane = &omap_fb->planes[i];
-
-		drm_gem_object_unreference_unlocked(plane->bo);
-	}
-
-	kfree(omap_fb);
-}
-
 static const struct drm_framebuffer_funcs omap_framebuffer_funcs = {
-	.create_handle = omap_framebuffer_create_handle,
-	.destroy = omap_framebuffer_destroy,
+	.create_handle = drm_gem_fb_create_handle,
+	.destroy = drm_gem_fb_destroy,
 };
 
-static u32 get_linear_addr(struct plane *plane,
+static u32 get_linear_addr(struct drm_framebuffer *fb,
 		const struct drm_format_info *format, int n, int x, int y)
 {
+	struct omap_framebuffer *omap_fb = to_omap_framebuffer(fb);
+	struct plane *plane = &omap_fb->planes[n];
 	u32 offset;
 
-	offset = plane->offset
+	offset = fb->offsets[n]
 	       + (x * format->cpp[n] / (n == 0 ? 1 : format->hsub))
-	       + (y * plane->pitch / (n == 0 ? 1 : format->vsub));
+	       + (y * fb->pitches[n] / (n == 0 ? 1 : format->vsub));
 
 	return plane->dma_addr + offset;
 }
 
 bool omap_framebuffer_supports_rotation(struct drm_framebuffer *fb)
 {
-	struct omap_framebuffer *omap_fb = to_omap_framebuffer(fb);
-	struct plane *plane = &omap_fb->planes[0];
-
-	return omap_gem_flags(plane->bo) & OMAP_BO_TILED;
+	return omap_gem_flags(fb->obj[0]) & OMAP_BO_TILED;
 }
 
 /* Note: DRM rotates counter-clockwise, TILER & DSS rotates clockwise */
@@ -176,7 +146,7 @@ void omap_framebuffer_update_scanout(struct drm_framebuffer *fb,
 	x = state->src_x >> 16;
 	y = state->src_y >> 16;
 
-	if (omap_gem_flags(plane->bo) & OMAP_BO_TILED) {
+	if (omap_gem_flags(fb->obj[0]) & OMAP_BO_TILED) {
 		u32 w = state->src_w >> 16;
 		u32 h = state->src_h >> 16;
 
@@ -201,12 +171,12 @@ void omap_framebuffer_update_scanout(struct drm_framebuffer *fb,
 			x += w - 1;
 
 		/* Note: x and y are in TILER units, not pixels */
-		omap_gem_rotated_dma_addr(plane->bo, orient, x, y,
+		omap_gem_rotated_dma_addr(fb->obj[0], orient, x, y,
 					  &info->paddr);
 		info->rotation_type = OMAP_DSS_ROT_TILER;
 		info->rotation = state->rotation ?: DRM_MODE_ROTATE_0;
 		/* Note: stride in TILER units, not pixels */
-		info->screen_width  = omap_gem_tiled_stride(plane->bo, orient);
+		info->screen_width  = omap_gem_tiled_stride(fb->obj[0], orient);
 	} else {
 		switch (state->rotation & DRM_MODE_ROTATE_MASK) {
 		case 0:
@@ -221,10 +191,10 @@ void omap_framebuffer_update_scanout(struct drm_framebuffer *fb,
 			break;
 		}
 
-		info->paddr         = get_linear_addr(plane, format, 0, x, y);
+		info->paddr         = get_linear_addr(fb, format, 0, x, y);
 		info->rotation_type = OMAP_DSS_ROT_NONE;
 		info->rotation      = DRM_MODE_ROTATE_0;
-		info->screen_width  = plane->pitch;
+		info->screen_width  = fb->pitches[0];
 	}
 
 	/* convert to pixels: */
@@ -234,11 +204,11 @@ void omap_framebuffer_update_scanout(struct drm_framebuffer *fb,
 		plane = &omap_fb->planes[1];
 
 		if (info->rotation_type == OMAP_DSS_ROT_TILER) {
-			WARN_ON(!(omap_gem_flags(plane->bo) & OMAP_BO_TILED));
-			omap_gem_rotated_dma_addr(plane->bo, orient, x/2, y/2,
+			WARN_ON(!(omap_gem_flags(fb->obj[1]) & OMAP_BO_TILED));
+			omap_gem_rotated_dma_addr(fb->obj[1], orient, x/2, y/2,
 						  &info->p_uv_addr);
 		} else {
-			info->p_uv_addr = get_linear_addr(plane, format, 1, x, y);
+			info->p_uv_addr = get_linear_addr(fb, format, 1, x, y);
 		}
 	} else {
 		info->p_uv_addr = 0;
@@ -261,10 +231,10 @@ int omap_framebuffer_pin(struct drm_framebuffer *fb)
 
 	for (i = 0; i < n; i++) {
 		struct plane *plane = &omap_fb->planes[i];
-		ret = omap_gem_pin(plane->bo, &plane->dma_addr);
+		ret = omap_gem_pin(fb->obj[i], &plane->dma_addr);
 		if (ret)
 			goto fail;
-		omap_gem_dma_sync_buffer(plane->bo, DMA_TO_DEVICE);
+		omap_gem_dma_sync_buffer(fb->obj[i], DMA_TO_DEVICE);
 	}
 
 	omap_fb->pin_count++;
@@ -276,7 +246,7 @@ int omap_framebuffer_pin(struct drm_framebuffer *fb)
 fail:
 	for (i--; i >= 0; i--) {
 		struct plane *plane = &omap_fb->planes[i];
-		omap_gem_unpin(plane->bo);
+		omap_gem_unpin(fb->obj[i]);
 		plane->dma_addr = 0;
 	}
 
@@ -302,54 +272,25 @@ void omap_framebuffer_unpin(struct drm_framebuffer *fb)
 
 	for (i = 0; i < n; i++) {
 		struct plane *plane = &omap_fb->planes[i];
-		omap_gem_unpin(plane->bo);
+		omap_gem_unpin(fb->obj[i]);
 		plane->dma_addr = 0;
 	}
 
 	mutex_unlock(&omap_fb->lock);
 }
 
-/* iterate thru all the connectors, returning ones that are attached
- * to the same fb..
- */
-struct drm_connector *omap_framebuffer_get_next_connector(
-		struct drm_framebuffer *fb, struct drm_connector *from)
-{
-	struct drm_device *dev = fb->dev;
-	struct list_head *connector_list = &dev->mode_config.connector_list;
-	struct drm_connector *connector = from;
-
-	if (!from)
-		return list_first_entry_or_null(connector_list, typeof(*from),
-						head);
-
-	list_for_each_entry_from(connector, connector_list, head) {
-		if (connector != from) {
-			struct drm_encoder *encoder = connector->encoder;
-			struct drm_crtc *crtc = encoder ? encoder->crtc : NULL;
-			if (crtc && crtc->primary->fb == fb)
-				return connector;
-
-		}
-	}
-
-	return NULL;
-}
-
 #ifdef CONFIG_DEBUG_FS
 void omap_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m)
 {
-	struct omap_framebuffer *omap_fb = to_omap_framebuffer(fb);
 	int i, n = fb->format->num_planes;
 
 	seq_printf(m, "fb: %dx%d@%4.4s\n", fb->width, fb->height,
 			(char *)&fb->format->format);
 
 	for (i = 0; i < n; i++) {
-		struct plane *plane = &omap_fb->planes[i];
 		seq_printf(m, "   %d: offset=%d pitch=%d, obj: ",
-				i, plane->offset, plane->pitch);
-		omap_gem_describe(plane->bo, m);
+				i, fb->offsets[n], fb->pitches[i]);
+		omap_gem_describe(fb->obj[i], m);
 	}
 }
 #endif
@@ -454,9 +395,7 @@ struct drm_framebuffer *omap_framebuffer_init(struct drm_device *dev,
 			goto fail;
 		}
 
-		plane->bo     = bos[i];
-		plane->offset = mode_cmd->offsets[i];
-		plane->pitch  = pitch;
+		fb->obj[i]    = bos[i];
 		plane->dma_addr  = 0;
 	}
 
diff --git a/drivers/gpu/drm/omapdrm/omap_fb.h b/drivers/gpu/drm/omapdrm/omap_fb.h
index 94ad5f9e4404..c20cb4bc714d 100644
--- a/drivers/gpu/drm/omapdrm/omap_fb.h
+++ b/drivers/gpu/drm/omapdrm/omap_fb.h
@@ -38,8 +38,6 @@ int omap_framebuffer_pin(struct drm_framebuffer *fb);
 void omap_framebuffer_unpin(struct drm_framebuffer *fb);
 void omap_framebuffer_update_scanout(struct drm_framebuffer *fb,
 		struct drm_plane_state *state, struct omap_overlay_info *info);
-struct drm_connector *omap_framebuffer_get_next_connector(
-		struct drm_framebuffer *fb, struct drm_connector *from);
 bool omap_framebuffer_supports_rotation(struct drm_framebuffer *fb);
 void omap_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m);
 
diff --git a/drivers/gpu/drm/omapdrm/omap_fbdev.c b/drivers/gpu/drm/omapdrm/omap_fbdev.c
index 0f66c74a54b0..d958cc813a94 100644
--- a/drivers/gpu/drm/omapdrm/omap_fbdev.c
+++ b/drivers/gpu/drm/omapdrm/omap_fbdev.c
@@ -170,13 +170,11 @@ static int omap_fbdev_create(struct drm_fb_helper *helper,
 		goto fail;
 	}
 
-	mutex_lock(&dev->struct_mutex);
-
 	fbi = drm_fb_helper_alloc_fbi(helper);
 	if (IS_ERR(fbi)) {
 		dev_err(dev->dev, "failed to allocate fb info\n");
 		ret = PTR_ERR(fbi);
-		goto fail_unlock;
+		goto fail;
 	}
 
 	DBG("fbi=%p, dev=%p", fbi, dev);
@@ -212,12 +210,8 @@ static int omap_fbdev_create(struct drm_fb_helper *helper,
 	DBG("par=%p, %dx%d", fbi->par, fbi->var.xres, fbi->var.yres);
 	DBG("allocated %dx%d fb", fbdev->fb->width, fbdev->fb->height);
 
-	mutex_unlock(&dev->struct_mutex);
-
 	return 0;
 
-fail_unlock:
-	mutex_unlock(&dev->struct_mutex);
 fail:
 
 	if (ret) {
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 17a53d207978..4ba5d035c590 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -47,6 +47,9 @@ struct omap_gem_object {
 	/** roll applied when mapping to DMM */
 	u32 roll;
 
+	/** protects dma_addr_cnt, block, pages, dma_addrs and vaddr */
+	struct mutex lock;
+
 	/**
 	 * dma_addr contains the buffer DMA address. It is valid for
 	 *
@@ -137,14 +140,12 @@ struct omap_drm_usergart {
  */
 
 /** get mmap offset */
-static u64 mmap_offset(struct drm_gem_object *obj)
+u64 omap_gem_mmap_offset(struct drm_gem_object *obj)
 {
 	struct drm_device *dev = obj->dev;
 	int ret;
 	size_t size;
 
-	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
-
 	/* Make it mmapable */
 	size = omap_gem_mmap_size(obj);
 	ret = drm_gem_create_mmap_offset_size(obj, size);
@@ -156,7 +157,7 @@ static u64 mmap_offset(struct drm_gem_object *obj)
 	return drm_vma_node_offset_addr(&obj->vma_node);
 }
 
-static bool is_contiguous(struct omap_gem_object *omap_obj)
+static bool omap_gem_is_contiguous(struct omap_gem_object *omap_obj)
 {
 	if (omap_obj->flags & OMAP_BO_MEM_DMA_API)
 		return true;
@@ -171,14 +172,14 @@ static bool is_contiguous(struct omap_gem_object *omap_obj)
  * Eviction
  */
 
-static void evict_entry(struct drm_gem_object *obj,
+static void omap_gem_evict_entry(struct drm_gem_object *obj,
 		enum tiler_fmt fmt, struct omap_drm_usergart_entry *entry)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 	struct omap_drm_private *priv = obj->dev->dev_private;
 	int n = priv->usergart[fmt].height;
 	size_t size = PAGE_SIZE * n;
-	loff_t off = mmap_offset(obj) +
+	loff_t off = omap_gem_mmap_offset(obj) +
 			(entry->obj_pgoff << PAGE_SHIFT);
 	const int m = DIV_ROUND_UP(omap_obj->width << fmt, PAGE_SIZE);
 
@@ -199,7 +200,7 @@ static void evict_entry(struct drm_gem_object *obj,
 }
 
 /* Evict a buffer from usergart, if it is mapped there */
-static void evict(struct drm_gem_object *obj)
+static void omap_gem_evict(struct drm_gem_object *obj)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 	struct omap_drm_private *priv = obj->dev->dev_private;
@@ -213,7 +214,7 @@ static void evict(struct drm_gem_object *obj)
 				&priv->usergart[fmt].entry[i];
 
 			if (entry->obj == obj)
-				evict_entry(obj, fmt, entry);
+				omap_gem_evict_entry(obj, fmt, entry);
 		}
 	}
 }
@@ -222,7 +223,10 @@ static void evict(struct drm_gem_object *obj)
  * Page Management
  */
 
-/** ensure backing pages are allocated */
+/*
+ * Ensure backing pages are allocated. Must be called with the omap_obj.lock
+ * held.
+ */
 static int omap_gem_attach_pages(struct drm_gem_object *obj)
 {
 	struct drm_device *dev = obj->dev;
@@ -232,7 +236,14 @@ static int omap_gem_attach_pages(struct drm_gem_object *obj)
 	int i, ret;
 	dma_addr_t *addrs;
 
-	WARN_ON(omap_obj->pages);
+	lockdep_assert_held(&omap_obj->lock);
+
+	/*
+	 * If not using shmem (in which case backing pages don't need to be
+	 * allocated) or if pages are already allocated we're done.
+	 */
+	if (!(omap_obj->flags & OMAP_BO_MEM_SHMEM) || omap_obj->pages)
+		return 0;
 
 	pages = drm_gem_get_pages(obj);
 	if (IS_ERR(pages)) {
@@ -288,35 +299,15 @@ free_pages:
 	return ret;
 }
 
-/* acquire pages when needed (for example, for DMA where physically
- * contiguous buffer is not required
- */
-static int get_pages(struct drm_gem_object *obj, struct page ***pages)
-{
-	struct omap_gem_object *omap_obj = to_omap_bo(obj);
-	int ret = 0;
-
-	if ((omap_obj->flags & OMAP_BO_MEM_SHMEM) && !omap_obj->pages) {
-		ret = omap_gem_attach_pages(obj);
-		if (ret) {
-			dev_err(obj->dev->dev, "could not attach pages\n");
-			return ret;
-		}
-	}
-
-	/* TODO: even phys-contig.. we should have a list of pages? */
-	*pages = omap_obj->pages;
-
-	return 0;
-}
-
-/** release backing pages */
+/* Release backing pages. Must be called with the omap_obj.lock held. */
 static void omap_gem_detach_pages(struct drm_gem_object *obj)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 	unsigned int npages = obj->size >> PAGE_SHIFT;
 	unsigned int i;
 
+	lockdep_assert_held(&omap_obj->lock);
+
 	for (i = 0; i < npages; i++) {
 		if (omap_obj->dma_addrs[i])
 			dma_unmap_page(obj->dev->dev, omap_obj->dma_addrs[i],
@@ -336,16 +327,6 @@ u32 omap_gem_flags(struct drm_gem_object *obj)
 	return to_omap_bo(obj)->flags;
 }
 
-u64 omap_gem_mmap_offset(struct drm_gem_object *obj)
-{
-	u64 offset;
-
-	mutex_lock(&obj->dev->struct_mutex);
-	offset = mmap_offset(obj);
-	mutex_unlock(&obj->dev->struct_mutex);
-	return offset;
-}
-
 /** get mmap size */
 size_t omap_gem_mmap_size(struct drm_gem_object *obj)
 {
@@ -371,7 +352,7 @@ size_t omap_gem_mmap_size(struct drm_gem_object *obj)
  */
 
 /* Normal handling for the case of faulting in non-tiled buffers */
-static int fault_1d(struct drm_gem_object *obj,
+static vm_fault_t omap_gem_fault_1d(struct drm_gem_object *obj,
 		struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
@@ -385,18 +366,19 @@ static int fault_1d(struct drm_gem_object *obj,
 		omap_gem_cpu_sync_page(obj, pgoff);
 		pfn = page_to_pfn(omap_obj->pages[pgoff]);
 	} else {
-		BUG_ON(!is_contiguous(omap_obj));
+		BUG_ON(!omap_gem_is_contiguous(omap_obj));
 		pfn = (omap_obj->dma_addr >> PAGE_SHIFT) + pgoff;
 	}
 
 	VERB("Inserting %p pfn %lx, pa %lx", (void *)vmf->address,
 			pfn, pfn << PAGE_SHIFT);
 
-	return vm_insert_mixed(vma, vmf->address, __pfn_to_pfn_t(pfn, PFN_DEV));
+	return vmf_insert_mixed(vma, vmf->address,
+			__pfn_to_pfn_t(pfn, PFN_DEV));
 }
 
 /* Special handling for the case of faulting in 2d tiled buffers */
-static int fault_2d(struct drm_gem_object *obj,
+static vm_fault_t omap_gem_fault_2d(struct drm_gem_object *obj,
 		struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
@@ -407,7 +389,8 @@ static int fault_2d(struct drm_gem_object *obj,
 	unsigned long pfn;
 	pgoff_t pgoff, base_pgoff;
 	unsigned long vaddr;
-	int i, ret, slots;
+	int i, err, slots;
+	vm_fault_t ret = VM_FAULT_NOPAGE;
 
 	/*
 	 * Note the height of the slot is also equal to the number of pages
@@ -443,7 +426,7 @@ static int fault_2d(struct drm_gem_object *obj,
 
 	/* evict previous buffer using this usergart entry, if any: */
 	if (entry->obj)
-		evict_entry(entry->obj, fmt, entry);
+		omap_gem_evict_entry(entry->obj, fmt, entry);
 
 	entry->obj = obj;
 	entry->obj_pgoff = base_pgoff;
@@ -473,9 +456,10 @@ static int fault_2d(struct drm_gem_object *obj,
 	memset(pages + slots, 0,
 			sizeof(struct page *) * (n - slots));
 
-	ret = tiler_pin(entry->block, pages, ARRAY_SIZE(pages), 0, true);
-	if (ret) {
-		dev_err(obj->dev->dev, "failed to pin: %d\n", ret);
+	err = tiler_pin(entry->block, pages, ARRAY_SIZE(pages), 0, true);
+	if (err) {
+		ret = vmf_error(err);
+		dev_err(obj->dev->dev, "failed to pin: %d\n", err);
 		return ret;
 	}
 
@@ -485,7 +469,10 @@ static int fault_2d(struct drm_gem_object *obj,
 			pfn, pfn << PAGE_SHIFT);
 
 	for (i = n; i > 0; i--) {
-		vm_insert_mixed(vma, vaddr, __pfn_to_pfn_t(pfn, PFN_DEV));
+		ret = vmf_insert_mixed(vma,
+			vaddr, __pfn_to_pfn_t(pfn, PFN_DEV));
+		if (ret & VM_FAULT_ERROR)
+			break;
 		pfn += priv->usergart[fmt].stride_pfn;
 		vaddr += PAGE_SIZE * m;
 	}
@@ -494,7 +481,7 @@ static int fault_2d(struct drm_gem_object *obj,
 	priv->usergart[fmt].last = (priv->usergart[fmt].last + 1)
 				 % NUM_USERGART_ENTRIES;
 
-	return 0;
+	return ret;
 }
 
 /**
@@ -509,24 +496,25 @@ static int fault_2d(struct drm_gem_object *obj,
  * vma->vm_private_data points to the GEM object that is backing this
  * mapping.
  */
-int omap_gem_fault(struct vm_fault *vmf)
+vm_fault_t omap_gem_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_gem_object *obj = vma->vm_private_data;
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
-	struct drm_device *dev = obj->dev;
-	struct page **pages;
-	int ret;
+	int err;
+	vm_fault_t ret;
 
 	/* Make sure we don't parallel update on a fault, nor move or remove
 	 * something from beneath our feet
 	 */
-	mutex_lock(&dev->struct_mutex);
+	mutex_lock(&omap_obj->lock);
 
 	/* if a shmem backed object, make sure we have pages attached now */
-	ret = get_pages(obj, &pages);
-	if (ret)
+	err = omap_gem_attach_pages(obj);
+	if (err) {
+		ret = vmf_error(err);
 		goto fail;
+	}
 
 	/* where should we do corresponding put_pages().. we are mapping
 	 * the original page, rather than thru a GART, so we can't rely
@@ -535,28 +523,14 @@ int omap_gem_fault(struct vm_fault *vmf)
 	 */
 
 	if (omap_obj->flags & OMAP_BO_TILED)
-		ret = fault_2d(obj, vma, vmf);
+		ret = omap_gem_fault_2d(obj, vma, vmf);
 	else
-		ret = fault_1d(obj, vma, vmf);
+		ret = omap_gem_fault_1d(obj, vma, vmf);
 
 
 fail:
-	mutex_unlock(&dev->struct_mutex);
-	switch (ret) {
-	case 0:
-	case -ERESTARTSYS:
-	case -EINTR:
-	case -EBUSY:
-		/*
-		 * EBUSY is ok: this just means that another thread
-		 * already did the job.
-		 */
-		return VM_FAULT_NOPAGE;
-	case -ENOMEM:
-		return VM_FAULT_OOM;
-	default:
-		return VM_FAULT_SIGBUS;
-	}
+	mutex_unlock(&omap_obj->lock);
+	return ret;
 }
 
 /** We override mainly to fix up some of the vm mapping flags.. */
@@ -689,21 +663,22 @@ int omap_gem_roll(struct drm_gem_object *obj, u32 roll)
 
 	omap_obj->roll = roll;
 
-	mutex_lock(&obj->dev->struct_mutex);
+	mutex_lock(&omap_obj->lock);
 
 	/* if we aren't mapped yet, we don't need to do anything */
 	if (omap_obj->block) {
-		struct page **pages;
-		ret = get_pages(obj, &pages);
+		ret = omap_gem_attach_pages(obj);
 		if (ret)
 			goto fail;
-		ret = tiler_pin(omap_obj->block, pages, npages, roll, true);
+
+		ret = tiler_pin(omap_obj->block, omap_obj->pages, npages,
+				roll, true);
 		if (ret)
 			dev_err(obj->dev->dev, "could not repin: %d\n", ret);
 	}
 
 fail:
-	mutex_unlock(&obj->dev->struct_mutex);
+	mutex_unlock(&omap_obj->lock);
 
 	return ret;
 }
@@ -722,7 +697,7 @@ fail:
  * the omap_obj->dma_addrs[i] is set to the DMA address, and the page is
  * unmapped from the CPU.
  */
-static inline bool is_cached_coherent(struct drm_gem_object *obj)
+static inline bool omap_gem_is_cached_coherent(struct drm_gem_object *obj)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 
@@ -738,7 +713,7 @@ void omap_gem_cpu_sync_page(struct drm_gem_object *obj, int pgoff)
 	struct drm_device *dev = obj->dev;
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 
-	if (is_cached_coherent(obj))
+	if (omap_gem_is_cached_coherent(obj))
 		return;
 
 	if (omap_obj->dma_addrs[pgoff]) {
@@ -758,7 +733,7 @@ void omap_gem_dma_sync_buffer(struct drm_gem_object *obj,
 	struct page **pages = omap_obj->pages;
 	bool dirty = false;
 
-	if (is_cached_coherent(obj))
+	if (omap_gem_is_cached_coherent(obj))
 		return;
 
 	for (i = 0; i < npages; i++) {
@@ -804,18 +779,17 @@ int omap_gem_pin(struct drm_gem_object *obj, dma_addr_t *dma_addr)
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 	int ret = 0;
 
-	mutex_lock(&obj->dev->struct_mutex);
+	mutex_lock(&omap_obj->lock);
 
-	if (!is_contiguous(omap_obj) && priv->has_dmm) {
+	if (!omap_gem_is_contiguous(omap_obj) && priv->has_dmm) {
 		if (omap_obj->dma_addr_cnt == 0) {
-			struct page **pages;
 			u32 npages = obj->size >> PAGE_SHIFT;
 			enum tiler_fmt fmt = gem2fmt(omap_obj->flags);
 			struct tiler_block *block;
 
 			BUG_ON(omap_obj->block);
 
-			ret = get_pages(obj, &pages);
+			ret = omap_gem_attach_pages(obj);
 			if (ret)
 				goto fail;
 
@@ -835,7 +809,7 @@ int omap_gem_pin(struct drm_gem_object *obj, dma_addr_t *dma_addr)
 			}
 
 			/* TODO: enable async refill.. */
-			ret = tiler_pin(block, pages, npages,
+			ret = tiler_pin(block, omap_obj->pages, npages,
 					omap_obj->roll, true);
 			if (ret) {
 				tiler_release(block);
@@ -853,7 +827,7 @@ int omap_gem_pin(struct drm_gem_object *obj, dma_addr_t *dma_addr)
 		omap_obj->dma_addr_cnt++;
 
 		*dma_addr = omap_obj->dma_addr;
-	} else if (is_contiguous(omap_obj)) {
+	} else if (omap_gem_is_contiguous(omap_obj)) {
 		*dma_addr = omap_obj->dma_addr;
 	} else {
 		ret = -EINVAL;
@@ -861,7 +835,7 @@ int omap_gem_pin(struct drm_gem_object *obj, dma_addr_t *dma_addr)
 	}
 
 fail:
-	mutex_unlock(&obj->dev->struct_mutex);
+	mutex_unlock(&omap_obj->lock);
 
 	return ret;
 }
@@ -879,7 +853,8 @@ void omap_gem_unpin(struct drm_gem_object *obj)
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 	int ret;
 
-	mutex_lock(&obj->dev->struct_mutex);
+	mutex_lock(&omap_obj->lock);
+
 	if (omap_obj->dma_addr_cnt > 0) {
 		omap_obj->dma_addr_cnt--;
 		if (omap_obj->dma_addr_cnt == 0) {
@@ -898,7 +873,7 @@ void omap_gem_unpin(struct drm_gem_object *obj)
 		}
 	}
 
-	mutex_unlock(&obj->dev->struct_mutex);
+	mutex_unlock(&omap_obj->lock);
 }
 
 /* Get rotated scanout address (only valid if already pinned), at the
@@ -911,13 +886,16 @@ int omap_gem_rotated_dma_addr(struct drm_gem_object *obj, u32 orient,
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 	int ret = -EINVAL;
 
-	mutex_lock(&obj->dev->struct_mutex);
+	mutex_lock(&omap_obj->lock);
+
 	if ((omap_obj->dma_addr_cnt > 0) && omap_obj->block &&
 			(omap_obj->flags & OMAP_BO_TILED)) {
 		*dma_addr = tiler_tsptr(omap_obj->block, orient, x, y);
 		ret = 0;
 	}
-	mutex_unlock(&obj->dev->struct_mutex);
+
+	mutex_unlock(&omap_obj->lock);
+
 	return ret;
 }
 
@@ -944,17 +922,27 @@ int omap_gem_tiled_stride(struct drm_gem_object *obj, u32 orient)
 int omap_gem_get_pages(struct drm_gem_object *obj, struct page ***pages,
 		bool remap)
 {
-	int ret;
-	if (!remap) {
-		struct omap_gem_object *omap_obj = to_omap_bo(obj);
-		if (!omap_obj->pages)
-			return -ENOMEM;
-		*pages = omap_obj->pages;
-		return 0;
+	struct omap_gem_object *omap_obj = to_omap_bo(obj);
+	int ret = 0;
+
+	mutex_lock(&omap_obj->lock);
+
+	if (remap) {
+		ret = omap_gem_attach_pages(obj);
+		if (ret)
+			goto unlock;
 	}
-	mutex_lock(&obj->dev->struct_mutex);
-	ret = get_pages(obj, pages);
-	mutex_unlock(&obj->dev->struct_mutex);
+
+	if (!omap_obj->pages) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	*pages = omap_obj->pages;
+
+unlock:
+	mutex_unlock(&omap_obj->lock);
+
 	return ret;
 }
 
@@ -969,23 +957,34 @@ int omap_gem_put_pages(struct drm_gem_object *obj)
 }
 
 #ifdef CONFIG_DRM_FBDEV_EMULATION
-/* Get kernel virtual address for CPU access.. this more or less only
- * exists for omap_fbdev.  This should be called with struct_mutex
- * held.
+/*
+ * Get kernel virtual address for CPU access.. this more or less only
+ * exists for omap_fbdev.
  */
 void *omap_gem_vaddr(struct drm_gem_object *obj)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
-	WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex));
+	void *vaddr;
+	int ret;
+
+	mutex_lock(&omap_obj->lock);
+
 	if (!omap_obj->vaddr) {
-		struct page **pages;
-		int ret = get_pages(obj, &pages);
-		if (ret)
-			return ERR_PTR(ret);
-		omap_obj->vaddr = vmap(pages, obj->size >> PAGE_SHIFT,
+		ret = omap_gem_attach_pages(obj);
+		if (ret) {
+			vaddr = ERR_PTR(ret);
+			goto unlock;
+		}
+
+		omap_obj->vaddr = vmap(omap_obj->pages, obj->size >> PAGE_SHIFT,
 				VM_MAP, pgprot_writecombine(PAGE_KERNEL));
 	}
-	return omap_obj->vaddr;
+
+	vaddr = omap_obj->vaddr;
+
+unlock:
+	mutex_unlock(&omap_obj->lock);
+	return vaddr;
 }
 #endif
 
@@ -1001,6 +1000,7 @@ int omap_gem_resume(struct drm_device *dev)
 	struct omap_gem_object *omap_obj;
 	int ret = 0;
 
+	mutex_lock(&priv->list_lock);
 	list_for_each_entry(omap_obj, &priv->obj_list, mm_list) {
 		if (omap_obj->block) {
 			struct drm_gem_object *obj = &omap_obj->base;
@@ -1012,12 +1012,14 @@ int omap_gem_resume(struct drm_device *dev)
 					omap_obj->roll, true);
 			if (ret) {
 				dev_err(dev->dev, "could not repin: %d\n", ret);
-				return ret;
+				goto done;
 			}
 		}
 	}
 
-	return 0;
+done:
+	mutex_unlock(&priv->list_lock);
+	return ret;
 }
 #endif
 
@@ -1033,6 +1035,8 @@ void omap_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 
 	off = drm_vma_node_start(&obj->vma_node);
 
+	mutex_lock(&omap_obj->lock);
+
 	seq_printf(m, "%08x: %2d (%2d) %08llx %pad (%2d) %p %4d",
 			omap_obj->flags, obj->name, kref_read(&obj->refcount),
 			off, &omap_obj->dma_addr, omap_obj->dma_addr_cnt,
@@ -1050,6 +1054,8 @@ void omap_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 		seq_printf(m, " %zu", obj->size);
 	}
 
+	mutex_unlock(&omap_obj->lock);
+
 	seq_printf(m, "\n");
 }
 
@@ -1081,17 +1087,21 @@ void omap_gem_free_object(struct drm_gem_object *obj)
 	struct omap_drm_private *priv = dev->dev_private;
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 
-	evict(obj);
-
-	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+	omap_gem_evict(obj);
 
-	spin_lock(&priv->list_lock);
+	mutex_lock(&priv->list_lock);
 	list_del(&omap_obj->mm_list);
-	spin_unlock(&priv->list_lock);
+	mutex_unlock(&priv->list_lock);
 
-	/* this means the object is still pinned.. which really should
-	 * not happen.  I think..
+	/*
+	 * We own the sole reference to the object at this point, but to keep
+	 * lockdep happy, we must still take the omap_obj_lock to call
+	 * omap_gem_detach_pages(). This should hardly make any difference as
+	 * there can't be any lock contention.
 	 */
+	mutex_lock(&omap_obj->lock);
+
+	/* The object should not be pinned. */
 	WARN_ON(omap_obj->dma_addr_cnt > 0);
 
 	if (omap_obj->pages) {
@@ -1110,8 +1120,12 @@ void omap_gem_free_object(struct drm_gem_object *obj)
 		drm_prime_gem_destroy(obj, omap_obj->sgt);
 	}
 
+	mutex_unlock(&omap_obj->lock);
+
 	drm_gem_object_release(obj);
 
+	mutex_destroy(&omap_obj->lock);
+
 	kfree(omap_obj);
 }
 
@@ -1167,6 +1181,7 @@ struct drm_gem_object *omap_gem_new(struct drm_device *dev,
 
 	obj = &omap_obj->base;
 	omap_obj->flags = flags;
+	mutex_init(&omap_obj->lock);
 
 	if (flags & OMAP_BO_TILED) {
 		/*
@@ -1206,9 +1221,9 @@ struct drm_gem_object *omap_gem_new(struct drm_device *dev,
 			goto err_release;
 	}
 
-	spin_lock(&priv->list_lock);
+	mutex_lock(&priv->list_lock);
 	list_add(&omap_obj->mm_list, &priv->obj_list);
-	spin_unlock(&priv->list_lock);
+	mutex_unlock(&priv->list_lock);
 
 	return obj;
 
@@ -1231,16 +1246,15 @@ struct drm_gem_object *omap_gem_new_dmabuf(struct drm_device *dev, size_t size,
 	if (sgt->orig_nents != 1 && !priv->has_dmm)
 		return ERR_PTR(-EINVAL);
 
-	mutex_lock(&dev->struct_mutex);
-
 	gsize.bytes = PAGE_ALIGN(size);
 	obj = omap_gem_new(dev, gsize, OMAP_BO_MEM_DMABUF | OMAP_BO_WC);
-	if (!obj) {
-		obj = ERR_PTR(-ENOMEM);
-		goto done;
-	}
+	if (!obj)
+		return ERR_PTR(-ENOMEM);
 
 	omap_obj = to_omap_bo(obj);
+
+	mutex_lock(&omap_obj->lock);
+
 	omap_obj->sgt = sgt;
 
 	if (sgt->orig_nents == 1) {
@@ -1276,7 +1290,7 @@ struct drm_gem_object *omap_gem_new_dmabuf(struct drm_device *dev, size_t size,
 	}
 
 done:
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&omap_obj->lock);
 	return obj;
 }
 
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.h b/drivers/gpu/drm/omapdrm/omap_gem.h
index a78bde05193a..c1c45fbde155 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.h
+++ b/drivers/gpu/drm/omapdrm/omap_gem.h
@@ -21,6 +21,7 @@
 #define __OMAPDRM_GEM_H__
 
 #include <linux/types.h>
+#include <linux/mm_types.h>
 
 enum dma_data_direction;
 
@@ -80,7 +81,7 @@ struct dma_buf *omap_gem_prime_export(struct drm_device *dev,
 struct drm_gem_object *omap_gem_prime_import(struct drm_device *dev,
 		struct dma_buf *buffer);
 
-int omap_gem_fault(struct vm_fault *vmf);
+vm_fault_t omap_gem_fault(struct vm_fault *vmf);
 int omap_gem_roll(struct drm_gem_object *obj, u32 roll);
 void omap_gem_cpu_sync_page(struct drm_gem_object *obj, int pgoff);
 void omap_gem_dma_sync_buffer(struct drm_gem_object *obj,
diff --git a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
index 8e41d649e248..ec04a69ade46 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
@@ -93,23 +93,6 @@ static int omap_gem_dmabuf_end_cpu_access(struct dma_buf *buffer,
 	return 0;
 }
 
-
-static void *omap_gem_dmabuf_kmap_atomic(struct dma_buf *buffer,
-		unsigned long page_num)
-{
-	struct drm_gem_object *obj = buffer->priv;
-	struct page **pages;
-	omap_gem_get_pages(obj, &pages, false);
-	omap_gem_cpu_sync_page(obj, page_num);
-	return kmap_atomic(pages[page_num]);
-}
-
-static void omap_gem_dmabuf_kunmap_atomic(struct dma_buf *buffer,
-		unsigned long page_num, void *addr)
-{
-	kunmap_atomic(addr);
-}
-
 static void *omap_gem_dmabuf_kmap(struct dma_buf *buffer,
 		unsigned long page_num)
 {
@@ -148,8 +131,6 @@ static const struct dma_buf_ops omap_dmabuf_ops = {
 	.release = drm_gem_dmabuf_release,
 	.begin_cpu_access = omap_gem_dmabuf_begin_cpu_access,
 	.end_cpu_access = omap_gem_dmabuf_end_cpu_access,
-	.map_atomic = omap_gem_dmabuf_kmap_atomic,
-	.unmap_atomic = omap_gem_dmabuf_kunmap_atomic,
 	.map = omap_gem_dmabuf_kmap,
 	.unmap = omap_gem_dmabuf_kunmap,
 	.mmap = omap_gem_dmabuf_mmap,
diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig
index 25682ff3449a..6020c30a33b3 100644
--- a/drivers/gpu/drm/panel/Kconfig
+++ b/drivers/gpu/drm/panel/Kconfig
@@ -46,6 +46,15 @@ config DRM_PANEL_ILITEK_IL9322
 	  Say Y here if you want to enable support for Ilitek IL9322
 	  QVGA (320x240) RGB, YUV and ITU-T BT.656 panels.
 
+config DRM_PANEL_ILITEK_ILI9881C
+	tristate "Ilitek ILI9881C-based panels"
+	depends on OF
+	depends on DRM_MIPI_DSI
+	depends on BACKLIGHT_CLASS_DEVICE
+	help
+	  Say Y if you want to enable support for panels based on the
+	  Ilitek ILI9881c controller.
+
 config DRM_PANEL_INNOLUX_P079ZCA
 	tristate "Innolux P079ZCA panel"
 	depends on OF
diff --git a/drivers/gpu/drm/panel/Makefile b/drivers/gpu/drm/panel/Makefile
index f26efc11d746..5ccaaa9d13af 100644
--- a/drivers/gpu/drm/panel/Makefile
+++ b/drivers/gpu/drm/panel/Makefile
@@ -3,6 +3,7 @@ obj-$(CONFIG_DRM_PANEL_ARM_VERSATILE) += panel-arm-versatile.o
 obj-$(CONFIG_DRM_PANEL_LVDS) += panel-lvds.o
 obj-$(CONFIG_DRM_PANEL_SIMPLE) += panel-simple.o
 obj-$(CONFIG_DRM_PANEL_ILITEK_IL9322) += panel-ilitek-ili9322.o
+obj-$(CONFIG_DRM_PANEL_ILITEK_ILI9881C) += panel-ilitek-ili9881c.o
 obj-$(CONFIG_DRM_PANEL_INNOLUX_P079ZCA) += panel-innolux-p079zca.o
 obj-$(CONFIG_DRM_PANEL_JDI_LT070ME05000) += panel-jdi-lt070me05000.o
 obj-$(CONFIG_DRM_PANEL_LG_LG4573) += panel-lg-lg4573.o
diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
new file mode 100644
index 000000000000..3ad4a46c4e94
--- /dev/null
+++ b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
@@ -0,0 +1,503 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017-2018, Bootlin
+ */
+
+#include <linux/backlight.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/fb.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <linux/gpio/consumer.h>
+#include <linux/regulator/consumer.h>
+
+#include <drm/drm_mipi_dsi.h>
+#include <drm/drm_modes.h>
+#include <drm/drm_panel.h>
+
+#include <video/mipi_display.h>
+
+struct ili9881c {
+	struct drm_panel	panel;
+	struct mipi_dsi_device	*dsi;
+
+	struct backlight_device *backlight;
+	struct regulator	*power;
+	struct gpio_desc	*reset;
+};
+
+enum ili9881c_op {
+	ILI9881C_SWITCH_PAGE,
+	ILI9881C_COMMAND,
+};
+
+struct ili9881c_instr {
+	enum ili9881c_op	op;
+
+	union arg {
+		struct cmd {
+			u8	cmd;
+			u8	data;
+		} cmd;
+		u8	page;
+	} arg;
+};
+
+#define ILI9881C_SWITCH_PAGE_INSTR(_page)	\
+	{					\
+		.op = ILI9881C_SWITCH_PAGE,	\
+		.arg = {			\
+			.page = (_page),	\
+		},				\
+	}
+
+#define ILI9881C_COMMAND_INSTR(_cmd, _data)		\
+	{						\
+		.op = ILI9881C_COMMAND,		\
+		.arg = {				\
+			.cmd = {			\
+				.cmd = (_cmd),		\
+				.data = (_data),	\
+			},				\
+		},					\
+	}
+
+static const struct ili9881c_instr ili9881c_init[] = {
+	ILI9881C_SWITCH_PAGE_INSTR(3),
+	ILI9881C_COMMAND_INSTR(0x01, 0x00),
+	ILI9881C_COMMAND_INSTR(0x02, 0x00),
+	ILI9881C_COMMAND_INSTR(0x03, 0x73),
+	ILI9881C_COMMAND_INSTR(0x04, 0x03),
+	ILI9881C_COMMAND_INSTR(0x05, 0x00),
+	ILI9881C_COMMAND_INSTR(0x06, 0x06),
+	ILI9881C_COMMAND_INSTR(0x07, 0x06),
+	ILI9881C_COMMAND_INSTR(0x08, 0x00),
+	ILI9881C_COMMAND_INSTR(0x09, 0x18),
+	ILI9881C_COMMAND_INSTR(0x0a, 0x04),
+	ILI9881C_COMMAND_INSTR(0x0b, 0x00),
+	ILI9881C_COMMAND_INSTR(0x0c, 0x02),
+	ILI9881C_COMMAND_INSTR(0x0d, 0x03),
+	ILI9881C_COMMAND_INSTR(0x0e, 0x00),
+	ILI9881C_COMMAND_INSTR(0x0f, 0x25),
+	ILI9881C_COMMAND_INSTR(0x10, 0x25),
+	ILI9881C_COMMAND_INSTR(0x11, 0x00),
+	ILI9881C_COMMAND_INSTR(0x12, 0x00),
+	ILI9881C_COMMAND_INSTR(0x13, 0x00),
+	ILI9881C_COMMAND_INSTR(0x14, 0x00),
+	ILI9881C_COMMAND_INSTR(0x15, 0x00),
+	ILI9881C_COMMAND_INSTR(0x16, 0x0C),
+	ILI9881C_COMMAND_INSTR(0x17, 0x00),
+	ILI9881C_COMMAND_INSTR(0x18, 0x00),
+	ILI9881C_COMMAND_INSTR(0x19, 0x00),
+	ILI9881C_COMMAND_INSTR(0x1a, 0x00),
+	ILI9881C_COMMAND_INSTR(0x1b, 0x00),
+	ILI9881C_COMMAND_INSTR(0x1c, 0x00),
+	ILI9881C_COMMAND_INSTR(0x1d, 0x00),
+	ILI9881C_COMMAND_INSTR(0x1e, 0xC0),
+	ILI9881C_COMMAND_INSTR(0x1f, 0x80),
+	ILI9881C_COMMAND_INSTR(0x20, 0x04),
+	ILI9881C_COMMAND_INSTR(0x21, 0x01),
+	ILI9881C_COMMAND_INSTR(0x22, 0x00),
+	ILI9881C_COMMAND_INSTR(0x23, 0x00),
+	ILI9881C_COMMAND_INSTR(0x24, 0x00),
+	ILI9881C_COMMAND_INSTR(0x25, 0x00),
+	ILI9881C_COMMAND_INSTR(0x26, 0x00),
+	ILI9881C_COMMAND_INSTR(0x27, 0x00),
+	ILI9881C_COMMAND_INSTR(0x28, 0x33),
+	ILI9881C_COMMAND_INSTR(0x29, 0x03),
+	ILI9881C_COMMAND_INSTR(0x2a, 0x00),
+	ILI9881C_COMMAND_INSTR(0x2b, 0x00),
+	ILI9881C_COMMAND_INSTR(0x2c, 0x00),
+	ILI9881C_COMMAND_INSTR(0x2d, 0x00),
+	ILI9881C_COMMAND_INSTR(0x2e, 0x00),
+	ILI9881C_COMMAND_INSTR(0x2f, 0x00),
+	ILI9881C_COMMAND_INSTR(0x30, 0x00),
+	ILI9881C_COMMAND_INSTR(0x31, 0x00),
+	ILI9881C_COMMAND_INSTR(0x32, 0x00),
+	ILI9881C_COMMAND_INSTR(0x33, 0x00),
+	ILI9881C_COMMAND_INSTR(0x34, 0x04),
+	ILI9881C_COMMAND_INSTR(0x35, 0x00),
+	ILI9881C_COMMAND_INSTR(0x36, 0x00),
+	ILI9881C_COMMAND_INSTR(0x37, 0x00),
+	ILI9881C_COMMAND_INSTR(0x38, 0x3C),
+	ILI9881C_COMMAND_INSTR(0x39, 0x00),
+	ILI9881C_COMMAND_INSTR(0x3a, 0x00),
+	ILI9881C_COMMAND_INSTR(0x3b, 0x00),
+	ILI9881C_COMMAND_INSTR(0x3c, 0x00),
+	ILI9881C_COMMAND_INSTR(0x3d, 0x00),
+	ILI9881C_COMMAND_INSTR(0x3e, 0x00),
+	ILI9881C_COMMAND_INSTR(0x3f, 0x00),
+	ILI9881C_COMMAND_INSTR(0x40, 0x00),
+	ILI9881C_COMMAND_INSTR(0x41, 0x00),
+	ILI9881C_COMMAND_INSTR(0x42, 0x00),
+	ILI9881C_COMMAND_INSTR(0x43, 0x00),
+	ILI9881C_COMMAND_INSTR(0x44, 0x00),
+	ILI9881C_COMMAND_INSTR(0x50, 0x01),
+	ILI9881C_COMMAND_INSTR(0x51, 0x23),
+	ILI9881C_COMMAND_INSTR(0x52, 0x45),
+	ILI9881C_COMMAND_INSTR(0x53, 0x67),
+	ILI9881C_COMMAND_INSTR(0x54, 0x89),
+	ILI9881C_COMMAND_INSTR(0x55, 0xab),
+	ILI9881C_COMMAND_INSTR(0x56, 0x01),
+	ILI9881C_COMMAND_INSTR(0x57, 0x23),
+	ILI9881C_COMMAND_INSTR(0x58, 0x45),
+	ILI9881C_COMMAND_INSTR(0x59, 0x67),
+	ILI9881C_COMMAND_INSTR(0x5a, 0x89),
+	ILI9881C_COMMAND_INSTR(0x5b, 0xab),
+	ILI9881C_COMMAND_INSTR(0x5c, 0xcd),
+	ILI9881C_COMMAND_INSTR(0x5d, 0xef),
+	ILI9881C_COMMAND_INSTR(0x5e, 0x11),
+	ILI9881C_COMMAND_INSTR(0x5f, 0x02),
+	ILI9881C_COMMAND_INSTR(0x60, 0x02),
+	ILI9881C_COMMAND_INSTR(0x61, 0x02),
+	ILI9881C_COMMAND_INSTR(0x62, 0x02),
+	ILI9881C_COMMAND_INSTR(0x63, 0x02),
+	ILI9881C_COMMAND_INSTR(0x64, 0x02),
+	ILI9881C_COMMAND_INSTR(0x65, 0x02),
+	ILI9881C_COMMAND_INSTR(0x66, 0x02),
+	ILI9881C_COMMAND_INSTR(0x67, 0x02),
+	ILI9881C_COMMAND_INSTR(0x68, 0x02),
+	ILI9881C_COMMAND_INSTR(0x69, 0x02),
+	ILI9881C_COMMAND_INSTR(0x6a, 0x0C),
+	ILI9881C_COMMAND_INSTR(0x6b, 0x02),
+	ILI9881C_COMMAND_INSTR(0x6c, 0x0F),
+	ILI9881C_COMMAND_INSTR(0x6d, 0x0E),
+	ILI9881C_COMMAND_INSTR(0x6e, 0x0D),
+	ILI9881C_COMMAND_INSTR(0x6f, 0x06),
+	ILI9881C_COMMAND_INSTR(0x70, 0x07),
+	ILI9881C_COMMAND_INSTR(0x71, 0x02),
+	ILI9881C_COMMAND_INSTR(0x72, 0x02),
+	ILI9881C_COMMAND_INSTR(0x73, 0x02),
+	ILI9881C_COMMAND_INSTR(0x74, 0x02),
+	ILI9881C_COMMAND_INSTR(0x75, 0x02),
+	ILI9881C_COMMAND_INSTR(0x76, 0x02),
+	ILI9881C_COMMAND_INSTR(0x77, 0x02),
+	ILI9881C_COMMAND_INSTR(0x78, 0x02),
+	ILI9881C_COMMAND_INSTR(0x79, 0x02),
+	ILI9881C_COMMAND_INSTR(0x7a, 0x02),
+	ILI9881C_COMMAND_INSTR(0x7b, 0x02),
+	ILI9881C_COMMAND_INSTR(0x7c, 0x02),
+	ILI9881C_COMMAND_INSTR(0x7d, 0x02),
+	ILI9881C_COMMAND_INSTR(0x7e, 0x02),
+	ILI9881C_COMMAND_INSTR(0x7f, 0x02),
+	ILI9881C_COMMAND_INSTR(0x80, 0x0C),
+	ILI9881C_COMMAND_INSTR(0x81, 0x02),
+	ILI9881C_COMMAND_INSTR(0x82, 0x0F),
+	ILI9881C_COMMAND_INSTR(0x83, 0x0E),
+	ILI9881C_COMMAND_INSTR(0x84, 0x0D),
+	ILI9881C_COMMAND_INSTR(0x85, 0x06),
+	ILI9881C_COMMAND_INSTR(0x86, 0x07),
+	ILI9881C_COMMAND_INSTR(0x87, 0x02),
+	ILI9881C_COMMAND_INSTR(0x88, 0x02),
+	ILI9881C_COMMAND_INSTR(0x89, 0x02),
+	ILI9881C_COMMAND_INSTR(0x8A, 0x02),
+	ILI9881C_SWITCH_PAGE_INSTR(4),
+	ILI9881C_COMMAND_INSTR(0x6C, 0x15),
+	ILI9881C_COMMAND_INSTR(0x6E, 0x22),
+	ILI9881C_COMMAND_INSTR(0x6F, 0x33),
+	ILI9881C_COMMAND_INSTR(0x3A, 0xA4),
+	ILI9881C_COMMAND_INSTR(0x8D, 0x0D),
+	ILI9881C_COMMAND_INSTR(0x87, 0xBA),
+	ILI9881C_COMMAND_INSTR(0x26, 0x76),
+	ILI9881C_COMMAND_INSTR(0xB2, 0xD1),
+	ILI9881C_SWITCH_PAGE_INSTR(1),
+	ILI9881C_COMMAND_INSTR(0x22, 0x0A),
+	ILI9881C_COMMAND_INSTR(0x53, 0xDC),
+	ILI9881C_COMMAND_INSTR(0x55, 0xA7),
+	ILI9881C_COMMAND_INSTR(0x50, 0x78),
+	ILI9881C_COMMAND_INSTR(0x51, 0x78),
+	ILI9881C_COMMAND_INSTR(0x31, 0x02),
+	ILI9881C_COMMAND_INSTR(0x60, 0x14),
+	ILI9881C_COMMAND_INSTR(0xA0, 0x2A),
+	ILI9881C_COMMAND_INSTR(0xA1, 0x39),
+	ILI9881C_COMMAND_INSTR(0xA2, 0x46),
+	ILI9881C_COMMAND_INSTR(0xA3, 0x0e),
+	ILI9881C_COMMAND_INSTR(0xA4, 0x12),
+	ILI9881C_COMMAND_INSTR(0xA5, 0x25),
+	ILI9881C_COMMAND_INSTR(0xA6, 0x19),
+	ILI9881C_COMMAND_INSTR(0xA7, 0x1d),
+	ILI9881C_COMMAND_INSTR(0xA8, 0xa6),
+	ILI9881C_COMMAND_INSTR(0xA9, 0x1C),
+	ILI9881C_COMMAND_INSTR(0xAA, 0x29),
+	ILI9881C_COMMAND_INSTR(0xAB, 0x85),
+	ILI9881C_COMMAND_INSTR(0xAC, 0x1C),
+	ILI9881C_COMMAND_INSTR(0xAD, 0x1B),
+	ILI9881C_COMMAND_INSTR(0xAE, 0x51),
+	ILI9881C_COMMAND_INSTR(0xAF, 0x22),
+	ILI9881C_COMMAND_INSTR(0xB0, 0x2d),
+	ILI9881C_COMMAND_INSTR(0xB1, 0x4f),
+	ILI9881C_COMMAND_INSTR(0xB2, 0x59),
+	ILI9881C_COMMAND_INSTR(0xB3, 0x3F),
+	ILI9881C_COMMAND_INSTR(0xC0, 0x2A),
+	ILI9881C_COMMAND_INSTR(0xC1, 0x3a),
+	ILI9881C_COMMAND_INSTR(0xC2, 0x45),
+	ILI9881C_COMMAND_INSTR(0xC3, 0x0e),
+	ILI9881C_COMMAND_INSTR(0xC4, 0x11),
+	ILI9881C_COMMAND_INSTR(0xC5, 0x24),
+	ILI9881C_COMMAND_INSTR(0xC6, 0x1a),
+	ILI9881C_COMMAND_INSTR(0xC7, 0x1c),
+	ILI9881C_COMMAND_INSTR(0xC8, 0xaa),
+	ILI9881C_COMMAND_INSTR(0xC9, 0x1C),
+	ILI9881C_COMMAND_INSTR(0xCA, 0x29),
+	ILI9881C_COMMAND_INSTR(0xCB, 0x96),
+	ILI9881C_COMMAND_INSTR(0xCC, 0x1C),
+	ILI9881C_COMMAND_INSTR(0xCD, 0x1B),
+	ILI9881C_COMMAND_INSTR(0xCE, 0x51),
+	ILI9881C_COMMAND_INSTR(0xCF, 0x22),
+	ILI9881C_COMMAND_INSTR(0xD0, 0x2b),
+	ILI9881C_COMMAND_INSTR(0xD1, 0x4b),
+	ILI9881C_COMMAND_INSTR(0xD2, 0x59),
+	ILI9881C_COMMAND_INSTR(0xD3, 0x3F),
+};
+
+static inline struct ili9881c *panel_to_ili9881c(struct drm_panel *panel)
+{
+	return container_of(panel, struct ili9881c, panel);
+}
+
+/*
+ * The panel seems to accept some private DCS commands that map
+ * directly to registers.
+ *
+ * It is organised by page, with each page having its own set of
+ * registers, and the first page looks like it's holding the standard
+ * DCS commands.
+ *
+ * So before any attempt at sending a command or data, we have to be
+ * sure if we're in the right page or not.
+ */
+static int ili9881c_switch_page(struct ili9881c *ctx, u8 page)
+{
+	u8 buf[4] = { 0xff, 0x98, 0x81, page };
+	int ret;
+
+	ret = mipi_dsi_dcs_write_buffer(ctx->dsi, buf, sizeof(buf));
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int ili9881c_send_cmd_data(struct ili9881c *ctx, u8 cmd, u8 data)
+{
+	u8 buf[2] = { cmd, data };
+	int ret;
+
+	ret = mipi_dsi_dcs_write_buffer(ctx->dsi, buf, sizeof(buf));
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int ili9881c_prepare(struct drm_panel *panel)
+{
+	struct ili9881c *ctx = panel_to_ili9881c(panel);
+	unsigned int i;
+	int ret;
+
+	/* Power the panel */
+	ret = regulator_enable(ctx->power);
+	if (ret)
+		return ret;
+	msleep(5);
+
+	/* And reset it */
+	gpiod_set_value(ctx->reset, 1);
+	msleep(20);
+
+	gpiod_set_value(ctx->reset, 0);
+	msleep(20);
+
+	for (i = 0; i < ARRAY_SIZE(ili9881c_init); i++) {
+		const struct ili9881c_instr *instr = &ili9881c_init[i];
+
+		if (instr->op == ILI9881C_SWITCH_PAGE)
+			ret = ili9881c_switch_page(ctx, instr->arg.page);
+		else if (instr->op == ILI9881C_COMMAND)
+			ret = ili9881c_send_cmd_data(ctx, instr->arg.cmd.cmd,
+						      instr->arg.cmd.data);
+
+		if (ret)
+			return ret;
+	}
+
+	ret = ili9881c_switch_page(ctx, 0);
+	if (ret)
+		return ret;
+
+	ret = mipi_dsi_dcs_set_tear_on(ctx->dsi, MIPI_DSI_DCS_TEAR_MODE_VBLANK);
+	if (ret)
+		return ret;
+
+	ret = mipi_dsi_dcs_exit_sleep_mode(ctx->dsi);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int ili9881c_enable(struct drm_panel *panel)
+{
+	struct ili9881c *ctx = panel_to_ili9881c(panel);
+
+	msleep(120);
+
+	mipi_dsi_dcs_set_display_on(ctx->dsi);
+	backlight_enable(ctx->backlight);
+
+	return 0;
+}
+
+static int ili9881c_disable(struct drm_panel *panel)
+{
+	struct ili9881c *ctx = panel_to_ili9881c(panel);
+
+	backlight_disable(ctx->backlight);
+	return mipi_dsi_dcs_set_display_off(ctx->dsi);
+}
+
+static int ili9881c_unprepare(struct drm_panel *panel)
+{
+	struct ili9881c *ctx = panel_to_ili9881c(panel);
+
+	mipi_dsi_dcs_enter_sleep_mode(ctx->dsi);
+	regulator_disable(ctx->power);
+	gpiod_set_value(ctx->reset, 1);
+
+	return 0;
+}
+
+static const struct drm_display_mode bananapi_default_mode = {
+	.clock		= 62000,
+	.vrefresh	= 60,
+
+	.hdisplay	= 720,
+	.hsync_start	= 720 + 10,
+	.hsync_end	= 720 + 10 + 20,
+	.htotal		= 720 + 10 + 20 + 30,
+
+	.vdisplay	= 1280,
+	.vsync_start	= 1280 + 10,
+	.vsync_end	= 1280 + 10 + 10,
+	.vtotal		= 1280 + 10 + 10 + 20,
+};
+
+static int ili9881c_get_modes(struct drm_panel *panel)
+{
+	struct drm_connector *connector = panel->connector;
+	struct ili9881c *ctx = panel_to_ili9881c(panel);
+	struct drm_display_mode *mode;
+
+	mode = drm_mode_duplicate(panel->drm, &bananapi_default_mode);
+	if (!mode) {
+		dev_err(&ctx->dsi->dev, "failed to add mode %ux%ux@%u\n",
+			bananapi_default_mode.hdisplay,
+			bananapi_default_mode.vdisplay,
+			bananapi_default_mode.vrefresh);
+		return -ENOMEM;
+	}
+
+	drm_mode_set_name(mode);
+
+	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
+	drm_mode_probed_add(connector, mode);
+
+	panel->connector->display_info.width_mm = 62;
+	panel->connector->display_info.height_mm = 110;
+
+	return 1;
+}
+
+static const struct drm_panel_funcs ili9881c_funcs = {
+	.prepare	= ili9881c_prepare,
+	.unprepare	= ili9881c_unprepare,
+	.enable		= ili9881c_enable,
+	.disable	= ili9881c_disable,
+	.get_modes	= ili9881c_get_modes,
+};
+
+static int ili9881c_dsi_probe(struct mipi_dsi_device *dsi)
+{
+	struct device_node *np;
+	struct ili9881c *ctx;
+	int ret;
+
+	ctx = devm_kzalloc(&dsi->dev, sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+	mipi_dsi_set_drvdata(dsi, ctx);
+	ctx->dsi = dsi;
+
+	drm_panel_init(&ctx->panel);
+	ctx->panel.dev = &dsi->dev;
+	ctx->panel.funcs = &ili9881c_funcs;
+
+	ctx->power = devm_regulator_get(&dsi->dev, "power");
+	if (IS_ERR(ctx->power)) {
+		dev_err(&dsi->dev, "Couldn't get our power regulator\n");
+		return PTR_ERR(ctx->power);
+	}
+
+	ctx->reset = devm_gpiod_get(&dsi->dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(ctx->reset)) {
+		dev_err(&dsi->dev, "Couldn't get our reset GPIO\n");
+		return PTR_ERR(ctx->reset);
+	}
+
+	np = of_parse_phandle(dsi->dev.of_node, "backlight", 0);
+	if (np) {
+		ctx->backlight = of_find_backlight_by_node(np);
+		of_node_put(np);
+
+		if (!ctx->backlight)
+			return -EPROBE_DEFER;
+	}
+
+	ret = drm_panel_add(&ctx->panel);
+	if (ret < 0)
+		return ret;
+
+	dsi->mode_flags = MIPI_DSI_MODE_VIDEO_SYNC_PULSE;
+	dsi->format = MIPI_DSI_FMT_RGB888;
+	dsi->lanes = 4;
+
+	return mipi_dsi_attach(dsi);
+}
+
+static int ili9881c_dsi_remove(struct mipi_dsi_device *dsi)
+{
+	struct ili9881c *ctx = mipi_dsi_get_drvdata(dsi);
+
+	mipi_dsi_detach(dsi);
+	drm_panel_remove(&ctx->panel);
+
+	if (ctx->backlight)
+		put_device(&ctx->backlight->dev);
+
+	return 0;
+}
+
+static const struct of_device_id ili9881c_of_match[] = {
+	{ .compatible = "bananapi,lhr050h41" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ili9881c_of_match);
+
+static struct mipi_dsi_driver ili9881c_dsi_driver = {
+	.probe		= ili9881c_dsi_probe,
+	.remove		= ili9881c_dsi_remove,
+	.driver = {
+		.name		= "ili9881c-dsi",
+		.of_match_table	= ili9881c_of_match,
+	},
+};
+module_mipi_dsi_driver(ili9881c_dsi_driver);
+
+MODULE_AUTHOR("Maxime Ripard <maxime.ripard@free-electrons.com>");
+MODULE_DESCRIPTION("Ilitek ILI9881C Controller Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/panel/panel-innolux-p079zca.c b/drivers/gpu/drm/panel/panel-innolux-p079zca.c
index 57df39b5c589..72edb334d997 100644
--- a/drivers/gpu/drm/panel/panel-innolux-p079zca.c
+++ b/drivers/gpu/drm/panel/panel-innolux-p079zca.c
@@ -11,6 +11,7 @@
 #include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/regulator/consumer.h>
 
 #include <drm/drmP.h>
@@ -20,12 +21,41 @@
 
 #include <video/mipi_display.h>
 
+struct panel_init_cmd {
+	size_t len;
+	const char *data;
+};
+
+#define _INIT_CMD(...) { \
+	.len = sizeof((char[]){__VA_ARGS__}), \
+	.data = (char[]){__VA_ARGS__} }
+
+struct panel_desc {
+	const struct drm_display_mode *mode;
+	unsigned int bpc;
+	struct {
+		unsigned int width;
+		unsigned int height;
+	} size;
+
+	unsigned long flags;
+	enum mipi_dsi_pixel_format format;
+	const struct panel_init_cmd *init_cmds;
+	unsigned int lanes;
+	const char * const *supply_names;
+	unsigned int num_supplies;
+	unsigned int sleep_mode_delay;
+	unsigned int power_down_delay;
+};
+
 struct innolux_panel {
 	struct drm_panel base;
 	struct mipi_dsi_device *link;
+	const struct panel_desc *desc;
 
 	struct backlight_device *backlight;
-	struct regulator *supply;
+	struct regulator_bulk_data *supplies;
+	unsigned int num_supplies;
 	struct gpio_desc *enable_gpio;
 
 	bool prepared;
@@ -72,12 +102,16 @@ static int innolux_panel_unprepare(struct drm_panel *panel)
 		return err;
 	}
 
+	if (innolux->desc->sleep_mode_delay)
+		msleep(innolux->desc->sleep_mode_delay);
+
 	gpiod_set_value_cansleep(innolux->enable_gpio, 0);
 
-	/* T8: 80ms - 1000ms */
-	msleep(80);
+	if (innolux->desc->power_down_delay)
+		msleep(innolux->desc->power_down_delay);
 
-	err = regulator_disable(innolux->supply);
+	err = regulator_bulk_disable(innolux->desc->num_supplies,
+				     innolux->supplies);
 	if (err < 0)
 		return err;
 
@@ -89,24 +123,55 @@ static int innolux_panel_unprepare(struct drm_panel *panel)
 static int innolux_panel_prepare(struct drm_panel *panel)
 {
 	struct innolux_panel *innolux = to_innolux_panel(panel);
-	int err, regulator_err;
+	int err;
 
 	if (innolux->prepared)
 		return 0;
 
 	gpiod_set_value_cansleep(innolux->enable_gpio, 0);
 
-	err = regulator_enable(innolux->supply);
+	err = regulator_bulk_enable(innolux->desc->num_supplies,
+				    innolux->supplies);
 	if (err < 0)
 		return err;
 
-	/* T2: 15ms - 1000ms */
-	usleep_range(15000, 16000);
+	/* p079zca: t2 (20ms), p097pfg: t4 (15ms) */
+	usleep_range(20000, 21000);
 
 	gpiod_set_value_cansleep(innolux->enable_gpio, 1);
 
-	/* T4: 15ms - 1000ms */
-	usleep_range(15000, 16000);
+	/* p079zca: t4, p097pfg: t5 */
+	usleep_range(20000, 21000);
+
+	if (innolux->desc->init_cmds) {
+		const struct panel_init_cmd *cmds =
+					innolux->desc->init_cmds;
+		unsigned int i;
+
+		for (i = 0; cmds[i].len != 0; i++) {
+			const struct panel_init_cmd *cmd = &cmds[i];
+
+			err = mipi_dsi_generic_write(innolux->link, cmd->data,
+						     cmd->len);
+			if (err < 0) {
+				dev_err(panel->dev,
+					"failed to write command %u\n", i);
+				goto poweroff;
+			}
+
+			/*
+			 * Included by random guessing, because without this
+			 * (or at least, some delay), the panel sometimes
+			 * didn't appear to pick up the command sequence.
+			 */
+			err = mipi_dsi_dcs_nop(innolux->link);
+			if (err < 0) {
+				dev_err(panel->dev,
+					"failed to send DCS nop: %d\n", err);
+				goto poweroff;
+			}
+		}
+	}
 
 	err = mipi_dsi_dcs_exit_sleep_mode(innolux->link);
 	if (err < 0) {
@@ -133,12 +198,9 @@ static int innolux_panel_prepare(struct drm_panel *panel)
 	return 0;
 
 poweroff:
-	regulator_err = regulator_disable(innolux->supply);
-	if (regulator_err)
-		DRM_DEV_ERROR(panel->dev, "failed to disable regulator: %d\n",
-			      regulator_err);
-
 	gpiod_set_value_cansleep(innolux->enable_gpio, 0);
+	regulator_bulk_disable(innolux->desc->num_supplies, innolux->supplies);
+
 	return err;
 }
 
@@ -162,7 +224,11 @@ static int innolux_panel_enable(struct drm_panel *panel)
 	return 0;
 }
 
-static const struct drm_display_mode default_mode = {
+static const char * const innolux_p079zca_supply_names[] = {
+	"power",
+};
+
+static const struct drm_display_mode innolux_p079zca_mode = {
 	.clock = 56900,
 	.hdisplay = 768,
 	.hsync_start = 768 + 40,
@@ -175,15 +241,181 @@ static const struct drm_display_mode default_mode = {
 	.vrefresh = 60,
 };
 
+static const struct panel_desc innolux_p079zca_panel_desc = {
+	.mode = &innolux_p079zca_mode,
+	.bpc = 8,
+	.size = {
+		.width = 120,
+		.height = 160,
+	},
+	.flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
+		 MIPI_DSI_MODE_LPM,
+	.format = MIPI_DSI_FMT_RGB888,
+	.lanes = 4,
+	.supply_names = innolux_p079zca_supply_names,
+	.num_supplies = ARRAY_SIZE(innolux_p079zca_supply_names),
+	.power_down_delay = 80, /* T8: 80ms - 1000ms */
+};
+
+static const char * const innolux_p097pfg_supply_names[] = {
+	"avdd",
+	"avee",
+};
+
+static const struct drm_display_mode innolux_p097pfg_mode = {
+	.clock = 229000,
+	.hdisplay = 1536,
+	.hsync_start = 1536 + 100,
+	.hsync_end = 1536 + 100 + 24,
+	.htotal = 1536 + 100 + 24 + 100,
+	.vdisplay = 2048,
+	.vsync_start = 2048 + 100,
+	.vsync_end = 2048 + 100 + 2,
+	.vtotal = 2048 + 100 + 2 + 18,
+	.vrefresh = 60,
+};
+
+/*
+ * Display manufacturer failed to provide init sequencing according to
+ * https://chromium-review.googlesource.com/c/chromiumos/third_party/coreboot/+/892065/
+ * so the init sequence stems from a register dump of a working panel.
+ */
+static const struct panel_init_cmd innolux_p097pfg_init_cmds[] = {
+	/* page 0 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x00),
+	_INIT_CMD(0xB1, 0xE8, 0x11),
+	_INIT_CMD(0xB2, 0x25, 0x02),
+	_INIT_CMD(0xB5, 0x08, 0x00),
+	_INIT_CMD(0xBC, 0x0F, 0x00),
+	_INIT_CMD(0xB8, 0x03, 0x06, 0x00, 0x00),
+	_INIT_CMD(0xBD, 0x01, 0x90, 0x14, 0x14),
+	_INIT_CMD(0x6F, 0x01),
+	_INIT_CMD(0xC0, 0x03),
+	_INIT_CMD(0x6F, 0x02),
+	_INIT_CMD(0xC1, 0x0D),
+	_INIT_CMD(0xD9, 0x01, 0x09, 0x70),
+	_INIT_CMD(0xC5, 0x12, 0x21, 0x00),
+	_INIT_CMD(0xBB, 0x93, 0x93),
+
+	/* page 1 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x01),
+	_INIT_CMD(0xB3, 0x3C, 0x3C),
+	_INIT_CMD(0xB4, 0x0F, 0x0F),
+	_INIT_CMD(0xB9, 0x45, 0x45),
+	_INIT_CMD(0xBA, 0x14, 0x14),
+	_INIT_CMD(0xCA, 0x02),
+	_INIT_CMD(0xCE, 0x04),
+	_INIT_CMD(0xC3, 0x9B, 0x9B),
+	_INIT_CMD(0xD8, 0xC0, 0x03),
+	_INIT_CMD(0xBC, 0x82, 0x01),
+	_INIT_CMD(0xBD, 0x9E, 0x01),
+
+	/* page 2 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x02),
+	_INIT_CMD(0xB0, 0x82),
+	_INIT_CMD(0xD1, 0x00, 0x00, 0x00, 0x3E, 0x00, 0x82, 0x00, 0xA5,
+		  0x00, 0xC1, 0x00, 0xEA, 0x01, 0x0D, 0x01, 0x40),
+	_INIT_CMD(0xD2, 0x01, 0x6A, 0x01, 0xA8, 0x01, 0xDC, 0x02, 0x29,
+		  0x02, 0x67, 0x02, 0x68, 0x02, 0xA8, 0x02, 0xF0),
+	_INIT_CMD(0xD3, 0x03, 0x19, 0x03, 0x49, 0x03, 0x67, 0x03, 0x8C,
+		  0x03, 0xA6, 0x03, 0xC7, 0x03, 0xDE, 0x03, 0xEC),
+	_INIT_CMD(0xD4, 0x03, 0xFF, 0x03, 0xFF),
+	_INIT_CMD(0xE0, 0x00, 0x00, 0x00, 0x86, 0x00, 0xC5, 0x00, 0xE5,
+		  0x00, 0xFF, 0x01, 0x26, 0x01, 0x45, 0x01, 0x75),
+	_INIT_CMD(0xE1, 0x01, 0x9C, 0x01, 0xD5, 0x02, 0x05, 0x02, 0x4D,
+		  0x02, 0x86, 0x02, 0x87, 0x02, 0xC3, 0x03, 0x03),
+	_INIT_CMD(0xE2, 0x03, 0x2A, 0x03, 0x56, 0x03, 0x72, 0x03, 0x94,
+		  0x03, 0xAC, 0x03, 0xCB, 0x03, 0xE0, 0x03, 0xED),
+	_INIT_CMD(0xE3, 0x03, 0xFF, 0x03, 0xFF),
+
+	/* page 3 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x03),
+	_INIT_CMD(0xB0, 0x00, 0x00, 0x00, 0x00),
+	_INIT_CMD(0xB1, 0x00, 0x00, 0x00, 0x00),
+	_INIT_CMD(0xB2, 0x00, 0x00, 0x06, 0x04, 0x01, 0x40, 0x85),
+	_INIT_CMD(0xB3, 0x10, 0x07, 0xFC, 0x04, 0x01, 0x40, 0x80),
+	_INIT_CMD(0xB6, 0xF0, 0x08, 0x00, 0x04, 0x00, 0x00, 0x00, 0x01,
+		  0x40, 0x80),
+	_INIT_CMD(0xBA, 0xC5, 0x07, 0x00, 0x04, 0x11, 0x25, 0x8C),
+	_INIT_CMD(0xBB, 0xC5, 0x07, 0x00, 0x03, 0x11, 0x25, 0x8C),
+	_INIT_CMD(0xC0, 0x00, 0x3C, 0x00, 0x00, 0x00, 0x80, 0x80),
+	_INIT_CMD(0xC1, 0x00, 0x3C, 0x00, 0x00, 0x00, 0x80, 0x80),
+	_INIT_CMD(0xC4, 0x00, 0x00),
+	_INIT_CMD(0xEF, 0x41),
+
+	/* page 4 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x04),
+	_INIT_CMD(0xEC, 0x4C),
+
+	/* page 5 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x05),
+	_INIT_CMD(0xB0, 0x13, 0x03, 0x03, 0x01),
+	_INIT_CMD(0xB1, 0x30, 0x00),
+	_INIT_CMD(0xB2, 0x02, 0x02, 0x00),
+	_INIT_CMD(0xB3, 0x82, 0x23, 0x82, 0x9D),
+	_INIT_CMD(0xB4, 0xC5, 0x75, 0x24, 0x57),
+	_INIT_CMD(0xB5, 0x00, 0xD4, 0x72, 0x11, 0x11, 0xAB, 0x0A),
+	_INIT_CMD(0xB6, 0x00, 0x00, 0xD5, 0x72, 0x24, 0x56),
+	_INIT_CMD(0xB7, 0x5C, 0xDC, 0x5C, 0x5C),
+	_INIT_CMD(0xB9, 0x0C, 0x00, 0x00, 0x01, 0x00),
+	_INIT_CMD(0xC0, 0x75, 0x11, 0x11, 0x54, 0x05),
+	_INIT_CMD(0xC6, 0x00, 0x00, 0x00, 0x00),
+	_INIT_CMD(0xD0, 0x00, 0x48, 0x08, 0x00, 0x00),
+	_INIT_CMD(0xD1, 0x00, 0x48, 0x09, 0x00, 0x00),
+
+	/* page 6 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x06),
+	_INIT_CMD(0xB0, 0x02, 0x32, 0x32, 0x08, 0x2F),
+	_INIT_CMD(0xB1, 0x2E, 0x15, 0x14, 0x13, 0x12),
+	_INIT_CMD(0xB2, 0x11, 0x10, 0x00, 0x3D, 0x3D),
+	_INIT_CMD(0xB3, 0x3D, 0x3D, 0x3D, 0x3D, 0x3D),
+	_INIT_CMD(0xB4, 0x3D, 0x32),
+	_INIT_CMD(0xB5, 0x03, 0x32, 0x32, 0x09, 0x2F),
+	_INIT_CMD(0xB6, 0x2E, 0x1B, 0x1A, 0x19, 0x18),
+	_INIT_CMD(0xB7, 0x17, 0x16, 0x01, 0x3D, 0x3D),
+	_INIT_CMD(0xB8, 0x3D, 0x3D, 0x3D, 0x3D, 0x3D),
+	_INIT_CMD(0xB9, 0x3D, 0x32),
+	_INIT_CMD(0xC0, 0x01, 0x32, 0x32, 0x09, 0x2F),
+	_INIT_CMD(0xC1, 0x2E, 0x1A, 0x1B, 0x16, 0x17),
+	_INIT_CMD(0xC2, 0x18, 0x19, 0x03, 0x3D, 0x3D),
+	_INIT_CMD(0xC3, 0x3D, 0x3D, 0x3D, 0x3D, 0x3D),
+	_INIT_CMD(0xC4, 0x3D, 0x32),
+	_INIT_CMD(0xC5, 0x00, 0x32, 0x32, 0x08, 0x2F),
+	_INIT_CMD(0xC6, 0x2E, 0x14, 0x15, 0x10, 0x11),
+	_INIT_CMD(0xC7, 0x12, 0x13, 0x02, 0x3D, 0x3D),
+	_INIT_CMD(0xC8, 0x3D, 0x3D, 0x3D, 0x3D, 0x3D),
+	_INIT_CMD(0xC9, 0x3D, 0x32),
+
+	{},
+};
+
+static const struct panel_desc innolux_p097pfg_panel_desc = {
+	.mode = &innolux_p097pfg_mode,
+	.bpc = 8,
+	.size = {
+		.width = 147,
+		.height = 196,
+	},
+	.flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
+		 MIPI_DSI_MODE_LPM,
+	.format = MIPI_DSI_FMT_RGB888,
+	.init_cmds = innolux_p097pfg_init_cmds,
+	.lanes = 4,
+	.supply_names = innolux_p097pfg_supply_names,
+	.num_supplies = ARRAY_SIZE(innolux_p097pfg_supply_names),
+	.sleep_mode_delay = 100, /* T15 */
+};
+
 static int innolux_panel_get_modes(struct drm_panel *panel)
 {
+	struct innolux_panel *innolux = to_innolux_panel(panel);
+	const struct drm_display_mode *m = innolux->desc->mode;
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &default_mode);
+	mode = drm_mode_duplicate(panel->drm, m);
 	if (!mode) {
 		DRM_DEV_ERROR(panel->drm->dev, "failed to add mode %ux%ux@%u\n",
-			      default_mode.hdisplay, default_mode.vdisplay,
-			      default_mode.vrefresh);
+			      m->hdisplay, m->vdisplay, m->vrefresh);
 		return -ENOMEM;
 	}
 
@@ -191,9 +423,11 @@ static int innolux_panel_get_modes(struct drm_panel *panel)
 
 	drm_mode_probed_add(panel->connector, mode);
 
-	panel->connector->display_info.width_mm = 120;
-	panel->connector->display_info.height_mm = 160;
-	panel->connector->display_info.bpc = 8;
+	panel->connector->display_info.width_mm =
+			innolux->desc->size.width;
+	panel->connector->display_info.height_mm =
+			innolux->desc->size.height;
+	panel->connector->display_info.bpc = innolux->desc->bpc;
 
 	return 1;
 }
@@ -207,19 +441,42 @@ static const struct drm_panel_funcs innolux_panel_funcs = {
 };
 
 static const struct of_device_id innolux_of_match[] = {
-	{ .compatible = "innolux,p079zca", },
+	{ .compatible = "innolux,p079zca",
+	  .data = &innolux_p079zca_panel_desc
+	},
+	{ .compatible = "innolux,p097pfg",
+	  .data = &innolux_p097pfg_panel_desc
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, innolux_of_match);
 
-static int innolux_panel_add(struct innolux_panel *innolux)
+static int innolux_panel_add(struct mipi_dsi_device *dsi,
+			     const struct panel_desc *desc)
 {
-	struct device *dev = &innolux->link->dev;
-	int err;
+	struct innolux_panel *innolux;
+	struct device *dev = &dsi->dev;
+	int err, i;
+
+	innolux = devm_kzalloc(dev, sizeof(*innolux), GFP_KERNEL);
+	if (!innolux)
+		return -ENOMEM;
+
+	innolux->desc = desc;
+
+	innolux->supplies = devm_kcalloc(dev, desc->num_supplies,
+					 sizeof(*innolux->supplies),
+					 GFP_KERNEL);
+	if (!innolux->supplies)
+		return -ENOMEM;
+
+	for (i = 0; i < desc->num_supplies; i++)
+		innolux->supplies[i].supply = desc->supply_names[i];
 
-	innolux->supply = devm_regulator_get(dev, "power");
-	if (IS_ERR(innolux->supply))
-		return PTR_ERR(innolux->supply);
+	err = devm_regulator_bulk_get(dev, desc->num_supplies,
+				      innolux->supplies);
+	if (err < 0)
+		return err;
 
 	innolux->enable_gpio = devm_gpiod_get_optional(dev, "enable",
 						       GPIOD_OUT_HIGH);
@@ -230,15 +487,21 @@ static int innolux_panel_add(struct innolux_panel *innolux)
 	}
 
 	innolux->backlight = devm_of_find_backlight(dev);
-
 	if (IS_ERR(innolux->backlight))
 		return PTR_ERR(innolux->backlight);
 
 	drm_panel_init(&innolux->base);
 	innolux->base.funcs = &innolux_panel_funcs;
-	innolux->base.dev = &innolux->link->dev;
+	innolux->base.dev = dev;
+
+	err = drm_panel_add(&innolux->base);
+	if (err < 0)
+		return err;
+
+	mipi_dsi_set_drvdata(dsi, innolux);
+	innolux->link = dsi;
 
-	return drm_panel_add(&innolux->base);
+	return 0;
 }
 
 static void innolux_panel_del(struct innolux_panel *innolux)
@@ -249,28 +512,19 @@ static void innolux_panel_del(struct innolux_panel *innolux)
 
 static int innolux_panel_probe(struct mipi_dsi_device *dsi)
 {
-	struct innolux_panel *innolux;
+	const struct panel_desc *desc;
 	int err;
 
-	dsi->lanes = 4;
-	dsi->format = MIPI_DSI_FMT_RGB888;
-	dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
-			  MIPI_DSI_MODE_LPM;
-
-	innolux = devm_kzalloc(&dsi->dev, sizeof(*innolux), GFP_KERNEL);
-	if (!innolux)
-		return -ENOMEM;
-
-	mipi_dsi_set_drvdata(dsi, innolux);
+	desc = of_device_get_match_data(&dsi->dev);
+	dsi->mode_flags = desc->flags;
+	dsi->format = desc->format;
+	dsi->lanes = desc->lanes;
 
-	innolux->link = dsi;
-
-	err = innolux_panel_add(innolux);
+	err = innolux_panel_add(dsi, desc);
 	if (err < 0)
 		return err;
 
-	err = mipi_dsi_attach(dsi);
-	return err;
+	return mipi_dsi_attach(dsi);
 }
 
 static int innolux_panel_remove(struct mipi_dsi_device *dsi)
@@ -292,7 +546,6 @@ static int innolux_panel_remove(struct mipi_dsi_device *dsi)
 		DRM_DEV_ERROR(&dsi->dev, "failed to detach from DSI host: %d\n",
 			      err);
 
-	drm_panel_detach(&innolux->base);
 	innolux_panel_del(innolux);
 
 	return 0;
@@ -318,5 +571,6 @@ static struct mipi_dsi_driver innolux_panel_driver = {
 module_mipi_dsi_driver(innolux_panel_driver);
 
 MODULE_AUTHOR("Chris Zhong <zyw@rock-chips.com>");
+MODULE_AUTHOR("Lin Huang <hl@rock-chips.com>");
 MODULE_DESCRIPTION("Innolux P079ZCA panel driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c b/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c
index 0a94ab79a6c0..99caa7835e7b 100644
--- a/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c
+++ b/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c
@@ -500,7 +500,6 @@ static int jdi_panel_remove(struct mipi_dsi_device *dsi)
 		dev_err(&dsi->dev, "failed to detach from DSI host: %d\n",
 			ret);
 
-	drm_panel_detach(&jdi->base);
 	jdi_panel_del(jdi);
 
 	return 0;
diff --git a/drivers/gpu/drm/panel/panel-lvds.c b/drivers/gpu/drm/panel/panel-lvds.c
index 5185819c5b79..8a1687887ae9 100644
--- a/drivers/gpu/drm/panel/panel-lvds.c
+++ b/drivers/gpu/drm/panel/panel-lvds.c
@@ -282,7 +282,6 @@ static int panel_lvds_remove(struct platform_device *pdev)
 {
 	struct panel_lvds *lvds = dev_get_drvdata(&pdev->dev);
 
-	drm_panel_detach(&lvds->panel);
 	drm_panel_remove(&lvds->panel);
 
 	panel_lvds_disable(&lvds->panel);
diff --git a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
index 90f1ae4af93c..87fa316e1d7b 100644
--- a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
+++ b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
@@ -14,8 +14,6 @@
 #include <linux/regulator/consumer.h>
 #include <video/mipi_display.h>
 
-#define DRV_NAME "orisetech_otm8009a"
-
 #define OTM8009A_BACKLIGHT_DEFAULT	240
 #define OTM8009A_BACKLIGHT_MAX		255
 
@@ -98,6 +96,20 @@ static void otm8009a_dcs_write_buf(struct otm8009a *ctx, const void *data,
 		DRM_WARN("mipi dsi dcs write buffer failed\n");
 }
 
+static void otm8009a_dcs_write_buf_hs(struct otm8009a *ctx, const void *data,
+				      size_t len)
+{
+	struct mipi_dsi_device *dsi = to_mipi_dsi_device(ctx->dev);
+
+	/* data will be sent in dsi hs mode (ie. no lpm) */
+	dsi->mode_flags &= ~MIPI_DSI_MODE_LPM;
+
+	otm8009a_dcs_write_buf(ctx, data, len);
+
+	/* restore back the dsi lpm mode */
+	dsi->mode_flags |= MIPI_DSI_MODE_LPM;
+}
+
 #define dcs_write_seq(ctx, seq...)			\
 ({							\
 	static const u8 d[] = { seq };			\
@@ -248,11 +260,7 @@ static int otm8009a_disable(struct drm_panel *panel)
 	if (!ctx->enabled)
 		return 0; /* This is not an issue so we return 0 here */
 
-	/* Power off the backlight. Note: end-user still controls brightness */
-	ctx->bl_dev->props.power = FB_BLANK_POWERDOWN;
-	ret = backlight_update_status(ctx->bl_dev);
-	if (ret)
-		return ret;
+	backlight_disable(ctx->bl_dev);
 
 	ret = mipi_dsi_dcs_set_display_off(dsi);
 	if (ret)
@@ -316,13 +324,6 @@ static int otm8009a_prepare(struct drm_panel *panel)
 
 	ctx->prepared = true;
 
-	/*
-	 * Power on the backlight. Note: end-user still controls brightness
-	 * Note: ctx->prepared must be true before updating the backlight.
-	 */
-	ctx->bl_dev->props.power = FB_BLANK_UNBLANK;
-	backlight_update_status(ctx->bl_dev);
-
 	return 0;
 }
 
@@ -330,6 +331,11 @@ static int otm8009a_enable(struct drm_panel *panel)
 {
 	struct otm8009a *ctx = panel_to_otm8009a(panel);
 
+	if (ctx->enabled)
+		return 0;
+
+	backlight_enable(ctx->bl_dev);
+
 	ctx->enabled = true;
 
 	return 0;
@@ -387,7 +393,7 @@ static int otm8009a_backlight_update_status(struct backlight_device *bd)
 		 */
 		data[0] = MIPI_DCS_SET_DISPLAY_BRIGHTNESS;
 		data[1] = bd->props.brightness;
-		otm8009a_dcs_write_buf(ctx, data, ARRAY_SIZE(data));
+		otm8009a_dcs_write_buf_hs(ctx, data, ARRAY_SIZE(data));
 
 		/* set Brightness Control & Backlight on */
 		data[1] = 0x24;
@@ -399,7 +405,7 @@ static int otm8009a_backlight_update_status(struct backlight_device *bd)
 
 	/* Update Brightness Control & Backlight */
 	data[0] = MIPI_DCS_WRITE_CONTROL_DISPLAY;
-	otm8009a_dcs_write_buf(ctx, data, ARRAY_SIZE(data));
+	otm8009a_dcs_write_buf_hs(ctx, data, ARRAY_SIZE(data));
 
 	return 0;
 }
@@ -444,11 +450,14 @@ static int otm8009a_probe(struct mipi_dsi_device *dsi)
 	ctx->panel.dev = dev;
 	ctx->panel.funcs = &otm8009a_drm_funcs;
 
-	ctx->bl_dev = backlight_device_register(DRV_NAME "_backlight", dev, ctx,
-						&otm8009a_backlight_ops, NULL);
+	ctx->bl_dev = devm_backlight_device_register(dev, dev_name(dev),
+						     dsi->host->dev, ctx,
+						     &otm8009a_backlight_ops,
+						     NULL);
 	if (IS_ERR(ctx->bl_dev)) {
-		dev_err(dev, "failed to register backlight device\n");
-		return PTR_ERR(ctx->bl_dev);
+		ret = PTR_ERR(ctx->bl_dev);
+		dev_err(dev, "failed to register backlight: %d\n", ret);
+		return ret;
 	}
 
 	ctx->bl_dev->props.max_brightness = OTM8009A_BACKLIGHT_MAX;
@@ -466,11 +475,6 @@ static int otm8009a_probe(struct mipi_dsi_device *dsi)
 		return ret;
 	}
 
-	DRM_INFO(DRV_NAME "_panel %ux%u@%u %ubpp dsi %udl - ready\n",
-		 default_mode.hdisplay, default_mode.vdisplay,
-		 default_mode.vrefresh,
-		 mipi_dsi_pixel_format_to_bpp(dsi->format), dsi->lanes);
-
 	return 0;
 }
 
@@ -481,8 +485,6 @@ static int otm8009a_remove(struct mipi_dsi_device *dsi)
 	mipi_dsi_detach(dsi);
 	drm_panel_remove(&ctx->panel);
 
-	backlight_device_unregister(ctx->bl_dev);
-
 	return 0;
 }
 
@@ -496,7 +498,7 @@ static struct mipi_dsi_driver orisetech_otm8009a_driver = {
 	.probe  = otm8009a_probe,
 	.remove = otm8009a_remove,
 	.driver = {
-		.name = DRV_NAME "_panel",
+		.name = "panel-orisetech-otm8009a",
 		.of_match_table = orisetech_otm8009a_of_match,
 	},
 };
diff --git a/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c b/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c
index 74a806121f80..cb4dfb98be0f 100644
--- a/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c
+++ b/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c
@@ -299,7 +299,6 @@ static int wuxga_nt_panel_remove(struct mipi_dsi_device *dsi)
 	if (ret < 0)
 		dev_err(&dsi->dev, "failed to detach from DSI host: %d\n", ret);
 
-	drm_panel_detach(&wuxga_nt->base);
 	wuxga_nt_panel_del(wuxga_nt);
 
 	return 0;
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c b/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c
index a188a3959f1a..6ad827b93ae1 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c
@@ -823,7 +823,7 @@ static void s6e8aa0_read_mtp_id(struct s6e8aa0 *ctx)
 	int ret, i;
 
 	ret = s6e8aa0_dcs_read(ctx, 0xd1, id, ARRAY_SIZE(id));
-	if (ret < ARRAY_SIZE(id) || id[0] == 0x00) {
+	if (ret < 0 || ret < ARRAY_SIZE(id) || id[0] == 0x00) {
 		dev_err(ctx->dev, "read id failed\n");
 		ctx->error = -EIO;
 		return;
diff --git a/drivers/gpu/drm/panel/panel-seiko-43wvf1g.c b/drivers/gpu/drm/panel/panel-seiko-43wvf1g.c
index 71c09ed436ae..75f925390551 100644
--- a/drivers/gpu/drm/panel/panel-seiko-43wvf1g.c
+++ b/drivers/gpu/drm/panel/panel-seiko-43wvf1g.c
@@ -292,7 +292,6 @@ static int seiko_panel_remove(struct platform_device *pdev)
 {
 	struct seiko_panel *panel = dev_get_drvdata(&pdev->dev);
 
-	drm_panel_detach(&panel->base);
 	drm_panel_remove(&panel->base);
 
 	seiko_panel_disable(&panel->base);
diff --git a/drivers/gpu/drm/panel/panel-sharp-lq101r1sx01.c b/drivers/gpu/drm/panel/panel-sharp-lq101r1sx01.c
index 6bf8730f1a21..02fc0f5423d4 100644
--- a/drivers/gpu/drm/panel/panel-sharp-lq101r1sx01.c
+++ b/drivers/gpu/drm/panel/panel-sharp-lq101r1sx01.c
@@ -418,7 +418,6 @@ static int sharp_panel_remove(struct mipi_dsi_device *dsi)
 	if (err < 0)
 		dev_err(&dsi->dev, "failed to detach from DSI host: %d\n", err);
 
-	drm_panel_detach(&sharp->base);
 	sharp_panel_del(sharp);
 
 	return 0;
diff --git a/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c b/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c
index 494aa9b1628a..e5cae0050f52 100644
--- a/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c
+++ b/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c
@@ -327,7 +327,6 @@ static int sharp_nt_panel_remove(struct mipi_dsi_device *dsi)
 	if (ret < 0)
 		dev_err(&dsi->dev, "failed to detach from DSI host: %d\n", ret);
 
-	drm_panel_detach(&sharp_nt->base);
 	sharp_nt_panel_del(sharp_nt);
 
 	return 0;
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index cbf1ab404ee7..5b5d0a24e713 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -252,7 +252,7 @@ static int panel_simple_get_modes(struct drm_panel *panel)
 	/* probe EDID if a DDC bus is available */
 	if (p->ddc) {
 		struct edid *edid = drm_get_edid(panel->connector, p->ddc);
-		drm_mode_connector_update_edid_property(panel->connector, edid);
+		drm_connector_update_edid_property(panel->connector, edid);
 		if (edid) {
 			num += drm_add_edid_modes(panel->connector, edid);
 			kfree(edid);
@@ -364,7 +364,6 @@ static int panel_simple_remove(struct device *dev)
 {
 	struct panel_simple *panel = dev_get_drvdata(dev);
 
-	drm_panel_detach(&panel->base);
 	drm_panel_remove(&panel->base);
 
 	panel_simple_disable(&panel->base);
@@ -581,6 +580,34 @@ static const struct panel_desc auo_b133htn01 = {
 	},
 };
 
+static const struct display_timing auo_g070vvn01_timings = {
+	.pixelclock = { 33300000, 34209000, 45000000 },
+	.hactive = { 800, 800, 800 },
+	.hfront_porch = { 20, 40, 200 },
+	.hback_porch = { 87, 40, 1 },
+	.hsync_len = { 1, 48, 87 },
+	.vactive = { 480, 480, 480 },
+	.vfront_porch = { 5, 13, 200 },
+	.vback_porch = { 31, 31, 29 },
+	.vsync_len = { 1, 1, 3 },
+};
+
+static const struct panel_desc auo_g070vvn01 = {
+	.timings = &auo_g070vvn01_timings,
+	.num_timings = 1,
+	.bpc = 8,
+	.size = {
+		.width = 152,
+		.height = 91,
+	},
+	.delay = {
+		.prepare = 200,
+		.enable = 50,
+		.disable = 50,
+		.unprepare = 1000,
+	},
+};
+
 static const struct drm_display_mode auo_g104sn02_mode = {
 	.clock = 40000,
 	.hdisplay = 800,
@@ -687,7 +714,7 @@ static const struct panel_desc auo_p320hvn03 = {
 		.enable = 450,
 		.unprepare = 500,
 	},
-	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA,
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG,
 };
 
 static const struct drm_display_mode auo_t215hvn01_mode = {
@@ -745,6 +772,28 @@ static const struct panel_desc avic_tm070ddh03 = {
 	},
 };
 
+static const struct drm_display_mode boe_hv070wsa_mode = {
+	.clock = 40800,
+	.hdisplay = 1024,
+	.hsync_start = 1024 + 90,
+	.hsync_end = 1024 + 90 + 90,
+	.htotal = 1024 + 90 + 90 + 90,
+	.vdisplay = 600,
+	.vsync_start = 600 + 3,
+	.vsync_end = 600 + 3 + 4,
+	.vtotal = 600 + 3 + 4 + 3,
+	.vrefresh = 60,
+};
+
+static const struct panel_desc boe_hv070wsa = {
+	.modes = &boe_hv070wsa_mode,
+	.num_modes = 1,
+	.size = {
+		.width = 154,
+		.height = 90,
+	},
+};
+
 static const struct drm_display_mode boe_nv101wxmn51_modes[] = {
 	{
 		.clock = 71900,
@@ -857,6 +906,61 @@ static const struct panel_desc chunghwa_claa101wb01 = {
 	},
 };
 
+static const struct drm_display_mode dataimage_scf0700c48ggu18_mode = {
+	.clock = 33260,
+	.hdisplay = 800,
+	.hsync_start = 800 + 40,
+	.hsync_end = 800 + 40 + 128,
+	.htotal = 800 + 40 + 128 + 88,
+	.vdisplay = 480,
+	.vsync_start = 480 + 10,
+	.vsync_end = 480 + 10 + 2,
+	.vtotal = 480 + 10 + 2 + 33,
+	.vrefresh = 60,
+	.flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC,
+};
+
+static const struct panel_desc dataimage_scf0700c48ggu18 = {
+	.modes = &dataimage_scf0700c48ggu18_mode,
+	.num_modes = 1,
+	.bpc = 8,
+	.size = {
+		.width = 152,
+		.height = 91,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_POSEDGE,
+};
+
+static const struct display_timing dlc_dlc0700yzg_1_timing = {
+	.pixelclock = { 45000000, 51200000, 57000000 },
+	.hactive = { 1024, 1024, 1024 },
+	.hfront_porch = { 100, 106, 113 },
+	.hback_porch = { 100, 106, 113 },
+	.hsync_len = { 100, 108, 114 },
+	.vactive = { 600, 600, 600 },
+	.vfront_porch = { 8, 11, 15 },
+	.vback_porch = { 8, 11, 15 },
+	.vsync_len = { 9, 13, 15 },
+	.flags = DISPLAY_FLAGS_DE_HIGH,
+};
+
+static const struct panel_desc dlc_dlc0700yzg_1 = {
+	.timings = &dlc_dlc0700yzg_1_timing,
+	.num_timings = 1,
+	.bpc = 6,
+	.size = {
+		.width = 154,
+		.height = 86,
+	},
+	.delay = {
+		.prepare = 30,
+		.enable = 200,
+		.disable = 200,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB666_1X7X3_SPWG,
+};
+
 static const struct drm_display_mode edt_et057090dhu_mode = {
 	.clock = 25175,
 	.hdisplay = 640,
@@ -909,6 +1013,18 @@ static const struct panel_desc edt_etm0700g0dh6 = {
 	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_NEGEDGE,
 };
 
+static const struct panel_desc edt_etm0700g0bdh6 = {
+	.modes = &edt_etm0700g0dh6_mode,
+	.num_modes = 1,
+	.bpc = 6,
+	.size = {
+		.width = 152,
+		.height = 91,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB666_1X18,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_POSEDGE,
+};
+
 static const struct drm_display_mode foxlink_fl500wvr00_a0t_mode = {
 	.clock = 32260,
 	.hdisplay = 800,
@@ -1086,6 +1202,36 @@ static const struct panel_desc innolux_at070tn92 = {
 	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
 };
 
+static const struct display_timing innolux_g070y2_l01_timing = {
+	.pixelclock = { 28000000, 29500000, 32000000 },
+	.hactive = { 800, 800, 800 },
+	.hfront_porch = { 61, 91, 141 },
+	.hback_porch = { 60, 90, 140 },
+	.hsync_len = { 12, 12, 12 },
+	.vactive = { 480, 480, 480 },
+	.vfront_porch = { 4, 9, 30 },
+	.vback_porch = { 4, 8, 28 },
+	.vsync_len = { 2, 2, 2 },
+	.flags = DISPLAY_FLAGS_DE_HIGH,
+};
+
+static const struct panel_desc innolux_g070y2_l01 = {
+	.timings = &innolux_g070y2_l01_timing,
+	.num_timings = 1,
+	.bpc = 6,
+	.size = {
+		.width = 152,
+		.height = 91,
+	},
+	.delay = {
+		.prepare = 10,
+		.enable = 100,
+		.disable = 100,
+		.unprepare = 800,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG,
+};
+
 static const struct display_timing innolux_g101ice_l01_timing = {
 	.pixelclock = { 60400000, 71100000, 74700000 },
 	.hactive = { 1280, 1280, 1280 },
@@ -1217,6 +1363,30 @@ static const struct panel_desc innolux_n156bge_l21 = {
 	},
 };
 
+static const struct drm_display_mode innolux_tv123wam_mode = {
+	.clock = 206016,
+	.hdisplay = 2160,
+	.hsync_start = 2160 + 48,
+	.hsync_end = 2160 + 48 + 32,
+	.htotal = 2160 + 48 + 32 + 80,
+	.vdisplay = 1440,
+	.vsync_start = 1440 + 3,
+	.vsync_end = 1440 + 3 + 10,
+	.vtotal = 1440 + 3 + 10 + 27,
+	.vrefresh = 60,
+	.flags = DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC,
+};
+
+static const struct panel_desc innolux_tv123wam = {
+	.modes = &innolux_tv123wam_mode,
+	.num_modes = 1,
+	.bpc = 8,
+	.size = {
+		.width = 259,
+		.height = 173,
+	},
+};
+
 static const struct drm_display_mode innolux_zj070na_01p_mode = {
 	.clock = 51501,
 	.hdisplay = 1024,
@@ -1247,8 +1417,8 @@ static const struct display_timing koe_tx31d200vm0baa_timing = {
 	.hback_porch = { 16, 36, 56 },
 	.hsync_len = { 8, 8, 8 },
 	.vactive = { 480, 480, 480 },
-	.vfront_porch = { 6, 21, 33.5 },
-	.vback_porch = { 6, 21, 33.5 },
+	.vfront_porch = { 6, 21, 33 },
+	.vback_porch = { 6, 21, 33 },
 	.vsync_len = { 8, 8, 8 },
 	.flags = DISPLAY_FLAGS_DE_HIGH,
 };
@@ -1511,6 +1681,33 @@ static const struct panel_desc netron_dy_e231732 = {
 	.bus_format = MEDIA_BUS_FMT_RGB666_1X18,
 };
 
+static const struct drm_display_mode newhaven_nhd_43_480272ef_atxl_mode = {
+	.clock = 9000,
+	.hdisplay = 480,
+	.hsync_start = 480 + 2,
+	.hsync_end = 480 + 2 + 41,
+	.htotal = 480 + 2 + 41 + 2,
+	.vdisplay = 272,
+	.vsync_start = 272 + 2,
+	.vsync_end = 272 + 2 + 10,
+	.vtotal = 272 + 2 + 10 + 2,
+	.vrefresh = 60,
+	.flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC,
+};
+
+static const struct panel_desc newhaven_nhd_43_480272ef_atxl = {
+	.modes = &newhaven_nhd_43_480272ef_atxl_mode,
+	.num_modes = 1,
+	.bpc = 8,
+	.size = {
+		.width = 95,
+		.height = 54,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_POSEDGE |
+		     DRM_BUS_FLAG_SYNC_POSEDGE,
+};
+
 static const struct display_timing nlt_nl192108ac18_02d_timing = {
 	.pixelclock = { 130000000, 148350000, 163000000 },
 	.hactive = { 1920, 1920, 1920 },
@@ -1696,6 +1893,36 @@ static const struct panel_desc qd43003c0_40 = {
 	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
 };
 
+static const struct display_timing rocktech_rk070er9427_timing = {
+	.pixelclock = { 26400000, 33300000, 46800000 },
+	.hactive = { 800, 800, 800 },
+	.hfront_porch = { 16, 210, 354 },
+	.hback_porch = { 46, 46, 46 },
+	.hsync_len = { 1, 1, 1 },
+	.vactive = { 480, 480, 480 },
+	.vfront_porch = { 7, 22, 147 },
+	.vback_porch = { 23, 23, 23 },
+	.vsync_len = { 1, 1, 1 },
+	.flags = DISPLAY_FLAGS_DE_HIGH,
+};
+
+static const struct panel_desc rocktech_rk070er9427 = {
+	.timings = &rocktech_rk070er9427_timing,
+	.num_timings = 1,
+	.bpc = 6,
+	.size = {
+		.width = 154,
+		.height = 86,
+	},
+	.delay = {
+		.prepare = 41,
+		.enable = 50,
+		.unprepare = 41,
+		.disable = 50,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB666_1X18,
+};
+
 static const struct drm_display_mode samsung_lsn122dl01_c01_mode = {
 	.clock = 271560,
 	.hdisplay = 2560,
@@ -1764,6 +1991,30 @@ static const struct panel_desc samsung_ltn140at29_301 = {
 	},
 };
 
+static const struct drm_display_mode sharp_lq035q7db03_mode = {
+	.clock = 5500,
+	.hdisplay = 240,
+	.hsync_start = 240 + 16,
+	.hsync_end = 240 + 16 + 7,
+	.htotal = 240 + 16 + 7 + 5,
+	.vdisplay = 320,
+	.vsync_start = 320 + 9,
+	.vsync_end = 320 + 9 + 1,
+	.vtotal = 320 + 9 + 1 + 7,
+	.vrefresh = 60,
+};
+
+static const struct panel_desc sharp_lq035q7db03 = {
+	.modes = &sharp_lq035q7db03_mode,
+	.num_modes = 1,
+	.bpc = 6,
+	.size = {
+		.width = 54,
+		.height = 72,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB666_1X18,
+};
+
 static const struct display_timing sharp_lq101k1ly04_timing = {
 	.pixelclock = { 60000000, 65000000, 80000000 },
 	.hactive = { 1280, 1280, 1280 },
@@ -2095,6 +2346,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "auo,b133xtn01",
 		.data = &auo_b133xtn01,
 	}, {
+		.compatible = "auo,g070vvn01",
+		.data = &auo_g070vvn01,
+	}, {
 		.compatible = "auo,g104sn02",
 		.data = &auo_g104sn02,
 	}, {
@@ -2113,6 +2367,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "avic,tm070ddh03",
 		.data = &avic_tm070ddh03,
 	}, {
+		.compatible = "boe,hv070wsa-100",
+		.data = &boe_hv070wsa
+	}, {
 		.compatible = "boe,nv101wxmn51",
 		.data = &boe_nv101wxmn51,
 	}, {
@@ -2125,6 +2382,12 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "chunghwa,claa101wb01",
 		.data = &chunghwa_claa101wb01
 	}, {
+		.compatible = "dataimage,scf0700c48ggu18",
+		.data = &dataimage_scf0700c48ggu18,
+	}, {
+		.compatible = "dlc,dlc0700yzg-1",
+		.data = &dlc_dlc0700yzg_1,
+	}, {
 		.compatible = "edt,et057090dhu",
 		.data = &edt_et057090dhu,
 	}, {
@@ -2134,6 +2397,12 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "edt,etm0700g0dh6",
 		.data = &edt_etm0700g0dh6,
 	}, {
+		.compatible = "edt,etm0700g0bdh6",
+		.data = &edt_etm0700g0bdh6,
+	}, {
+		.compatible = "edt,etm0700g0edh6",
+		.data = &edt_etm0700g0bdh6,
+	}, {
 		.compatible = "foxlink,fl500wvr00-a0t",
 		.data = &foxlink_fl500wvr00_a0t,
 	}, {
@@ -2155,10 +2424,13 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "innolux,at070tn92",
 		.data = &innolux_at070tn92,
 	}, {
-		.compatible ="innolux,g101ice-l01",
+		.compatible = "innolux,g070y2-l01",
+		.data = &innolux_g070y2_l01,
+	}, {
+		.compatible = "innolux,g101ice-l01",
 		.data = &innolux_g101ice_l01
 	}, {
-		.compatible ="innolux,g121i1-l01",
+		.compatible = "innolux,g121i1-l01",
 		.data = &innolux_g121i1_l01
 	}, {
 		.compatible = "innolux,g121x1-l03",
@@ -2170,6 +2442,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "innolux,n156bge-l21",
 		.data = &innolux_n156bge_l21,
 	}, {
+		.compatible = "innolux,tv123wam",
+		.data = &innolux_tv123wam,
+	}, {
 		.compatible = "innolux,zj070na-01p",
 		.data = &innolux_zj070na_01p,
 	}, {
@@ -2206,6 +2481,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "netron-dy,e231732",
 		.data = &netron_dy_e231732,
 	}, {
+		.compatible = "newhaven,nhd-4.3-480272ef-atxl",
+		.data = &newhaven_nhd_43_480272ef_atxl,
+	}, {
 		.compatible = "nlt,nl192108ac18-02d",
 		.data = &nlt_nl192108ac18_02d,
 	}, {
@@ -2227,6 +2505,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "qiaodian,qd43003c0-40",
 		.data = &qd43003c0_40,
 	}, {
+		.compatible = "rocktech,rk070er9427",
+		.data = &rocktech_rk070er9427,
+	}, {
 		.compatible = "samsung,lsn122dl01-c01",
 		.data = &samsung_lsn122dl01_c01,
 	}, {
@@ -2236,6 +2517,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "samsung,ltn140at29-301",
 		.data = &samsung_ltn140at29_301,
 	}, {
+		.compatible = "sharp,lq035q7db03",
+		.data = &sharp_lq035q7db03,
+	}, {
 		.compatible = "sharp,lq101k1ly04",
 		.data = &sharp_lq101k1ly04,
 	}, {
diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
index 358c64ef1922..74284e5afc5d 100644
--- a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
+++ b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
@@ -419,7 +419,6 @@ static int st7789v_remove(struct spi_device *spi)
 {
 	struct st7789v *ctx = spi_get_drvdata(spi);
 
-	drm_panel_detach(&ctx->panel);
 	drm_panel_remove(&ctx->panel);
 
 	if (ctx->backlight)
diff --git a/drivers/gpu/drm/pl111/Makefile b/drivers/gpu/drm/pl111/Makefile
index 19a8189dc54f..0c70f0e91d21 100644
--- a/drivers/gpu/drm/pl111/Makefile
+++ b/drivers/gpu/drm/pl111/Makefile
@@ -4,6 +4,7 @@ pl111_drm-y +=	pl111_display.o \
 		pl111_drv.o
 
 pl111_drm-$(CONFIG_ARCH_VEXPRESS) += pl111_vexpress.o
+pl111_drm-$(CONFIG_ARCH_NOMADIK) += pl111_nomadik.o
 pl111_drm-$(CONFIG_DEBUG_FS) += pl111_debugfs.o
 
 obj-$(CONFIG_DRM_PL111) += pl111_drm.o
diff --git a/drivers/gpu/drm/pl111/pl111_display.c b/drivers/gpu/drm/pl111/pl111_display.c
index 19b0d006a54a..754f6b25f265 100644
--- a/drivers/gpu/drm/pl111/pl111_display.c
+++ b/drivers/gpu/drm/pl111/pl111_display.c
@@ -63,7 +63,7 @@ pl111_mode_valid(struct drm_crtc *crtc,
 	 * We use the pixelclock to also account for interlaced modes, the
 	 * resulting bandwidth is in bytes per second.
 	 */
-	bw = mode->clock * 1000; /* In Hz */
+	bw = mode->clock * 1000ULL; /* In Hz */
 	bw = bw * mode->hdisplay * mode->vdisplay * cpp;
 	bw = div_u64(bw, mode->htotal * mode->vtotal);
 
@@ -223,48 +223,84 @@ static void pl111_display_enable(struct drm_simple_display_pipe *pipe,
 
 	/* Hard-code TFT panel */
 	cntl = CNTL_LCDEN | CNTL_LCDTFT | CNTL_LCDVCOMP(1);
+	/* On the ST Micro variant, assume all 24 bits are connected */
+	if (priv->variant->st_bitmux_control)
+		cntl |= CNTL_ST_CDWID_24;
 
-	/* Note that the the hardware's format reader takes 'r' from
+	/*
+	 * Note that the the ARM hardware's format reader takes 'r' from
 	 * the low bit, while DRM formats list channels from high bit
-	 * to low bit as you read left to right.
+	 * to low bit as you read left to right. The ST Micro version of
+	 * the PL110 (LCDC) however uses the standard DRM format.
 	 */
 	switch (fb->format->format) {
+	case DRM_FORMAT_BGR888:
+		/* Only supported on the ST Micro variant */
+		if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_ST_LCDBPP24_PACKED | CNTL_BGR;
+		break;
+	case DRM_FORMAT_RGB888:
+		/* Only supported on the ST Micro variant */
+		if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_ST_LCDBPP24_PACKED;
+		break;
 	case DRM_FORMAT_ABGR8888:
 	case DRM_FORMAT_XBGR8888:
-		cntl |= CNTL_LCDBPP24;
+		if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_LCDBPP24 | CNTL_BGR;
+		else
+			cntl |= CNTL_LCDBPP24;
 		break;
 	case DRM_FORMAT_ARGB8888:
 	case DRM_FORMAT_XRGB8888:
-		cntl |= CNTL_LCDBPP24 | CNTL_BGR;
+		if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_LCDBPP24;
+		else
+			cntl |= CNTL_LCDBPP24 | CNTL_BGR;
 		break;
 	case DRM_FORMAT_BGR565:
 		if (priv->variant->is_pl110)
 			cntl |= CNTL_LCDBPP16;
+		else if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_LCDBPP16 | CNTL_ST_1XBPP_565 | CNTL_BGR;
 		else
 			cntl |= CNTL_LCDBPP16_565;
 		break;
 	case DRM_FORMAT_RGB565:
 		if (priv->variant->is_pl110)
-			cntl |= CNTL_LCDBPP16;
+			cntl |= CNTL_LCDBPP16 | CNTL_BGR;
+		else if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_LCDBPP16 | CNTL_ST_1XBPP_565;
 		else
-			cntl |= CNTL_LCDBPP16_565;
-		cntl |= CNTL_BGR;
+			cntl |= CNTL_LCDBPP16_565 | CNTL_BGR;
 		break;
 	case DRM_FORMAT_ABGR1555:
 	case DRM_FORMAT_XBGR1555:
 		cntl |= CNTL_LCDBPP16;
+		if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_ST_1XBPP_5551 | CNTL_BGR;
 		break;
 	case DRM_FORMAT_ARGB1555:
 	case DRM_FORMAT_XRGB1555:
-		cntl |= CNTL_LCDBPP16 | CNTL_BGR;
+		cntl |= CNTL_LCDBPP16;
+		if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_ST_1XBPP_5551;
+		else
+			cntl |= CNTL_BGR;
 		break;
 	case DRM_FORMAT_ABGR4444:
 	case DRM_FORMAT_XBGR4444:
 		cntl |= CNTL_LCDBPP16_444;
+		if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_ST_1XBPP_444 | CNTL_BGR;
 		break;
 	case DRM_FORMAT_ARGB4444:
 	case DRM_FORMAT_XRGB4444:
-		cntl |= CNTL_LCDBPP16_444 | CNTL_BGR;
+		cntl |= CNTL_LCDBPP16_444;
+		if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_ST_1XBPP_444;
+		else
+			cntl |= CNTL_BGR;
 		break;
 	default:
 		WARN_ONCE(true, "Unknown FB format 0x%08x\n",
diff --git a/drivers/gpu/drm/pl111/pl111_drm.h b/drivers/gpu/drm/pl111/pl111_drm.h
index ce4501d0ab48..1aa015ccacef 100644
--- a/drivers/gpu/drm/pl111/pl111_drm.h
+++ b/drivers/gpu/drm/pl111/pl111_drm.h
@@ -36,11 +36,14 @@ struct drm_minor;
  * struct pl111_variant_data - encodes IP differences
  * @name: the name of this variant
  * @is_pl110: this is the early PL110 variant
+ * @is_lcdc: this is the ST Microelectronics Nomadik LCDC variant
  * @external_bgr: this is the Versatile Pl110 variant with external
  *	BGR/RGB routing
  * @broken_clockdivider: the clock divider is broken and we need to
  *	use the supplied clock directly
  * @broken_vblank: the vblank IRQ is broken on this variant
+ * @st_bitmux_control: this variant is using the ST Micro bitmux
+ *	extensions to the control register
  * @formats: array of supported pixel formats on this variant
  * @nformats: the length of the array of supported pixel formats
  * @fb_bpp: desired bits per pixel on the default framebuffer
@@ -48,9 +51,11 @@ struct drm_minor;
 struct pl111_variant_data {
 	const char *name;
 	bool is_pl110;
+	bool is_lcdc;
 	bool external_bgr;
 	bool broken_clockdivider;
 	bool broken_vblank;
+	bool st_bitmux_control;
 	const u32 *formats;
 	unsigned int nformats;
 	unsigned int fb_bpp;
diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c
index 454ff0804642..47fe30223444 100644
--- a/drivers/gpu/drm/pl111/pl111_drv.c
+++ b/drivers/gpu/drm/pl111/pl111_drv.c
@@ -75,6 +75,7 @@
 
 #include "pl111_drm.h"
 #include "pl111_versatile.h"
+#include "pl111_nomadik.h"
 
 #define DRIVER_DESC      "DRM module for PL111"
 
@@ -249,6 +250,8 @@ static struct drm_driver pl111_drm_driver = {
 	.gem_prime_import_sg_table = pl111_gem_import_sg_table,
 	.gem_prime_export = drm_gem_prime_export,
 	.gem_prime_get_sg_table	= drm_gem_cma_prime_get_sg_table,
+	.gem_prime_mmap = drm_gem_cma_prime_mmap,
+	.gem_prime_vmap = drm_gem_cma_prime_vmap,
 
 #if defined(CONFIG_DEBUG_FS)
 	.debugfs_init = pl111_debugfs_init,
@@ -288,8 +291,8 @@ static int pl111_amba_probe(struct amba_device *amba_dev,
 		priv->memory_bw = 0;
 	}
 
-	/* The two variants swap this register */
-	if (variant->is_pl110) {
+	/* The two main variants swap this register */
+	if (variant->is_pl110 || variant->is_lcdc) {
 		priv->ienb = CLCD_PL110_IENB;
 		priv->ctrl = CLCD_PL110_CNTL;
 	} else {
@@ -301,13 +304,15 @@ static int pl111_amba_probe(struct amba_device *amba_dev,
 	if (IS_ERR(priv->regs)) {
 		dev_err(dev, "%s failed mmio\n", __func__);
 		ret = PTR_ERR(priv->regs);
-		goto dev_unref;
+		goto dev_put;
 	}
 
 	/* This may override some variant settings */
 	ret = pl111_versatile_init(dev, priv);
 	if (ret)
-		goto dev_unref;
+		goto dev_put;
+
+	pl111_nomadik_init(dev);
 
 	/* turn off interrupts before requesting the irq */
 	writel(0, priv->regs + priv->ienb);
@@ -321,16 +326,16 @@ static int pl111_amba_probe(struct amba_device *amba_dev,
 
 	ret = pl111_modeset_init(drm);
 	if (ret != 0)
-		goto dev_unref;
+		goto dev_put;
 
 	ret = drm_dev_register(drm, 0);
 	if (ret < 0)
-		goto dev_unref;
+		goto dev_put;
 
 	return 0;
 
-dev_unref:
-	drm_dev_unref(drm);
+dev_put:
+	drm_dev_put(drm);
 	of_reserved_mem_device_release(dev);
 
 	return ret;
@@ -347,7 +352,7 @@ static int pl111_amba_remove(struct amba_device *amba_dev)
 	if (priv->panel)
 		drm_panel_bridge_remove(priv->bridge);
 	drm_mode_config_cleanup(drm);
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 	of_reserved_mem_device_release(dev);
 
 	return 0;
@@ -400,16 +405,50 @@ static const struct pl111_variant_data pl111_variant = {
 	.fb_bpp = 32,
 };
 
+static const u32 pl110_nomadik_pixel_formats[] = {
+	DRM_FORMAT_RGB888,
+	DRM_FORMAT_BGR888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_BGR565,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_ABGR1555,
+	DRM_FORMAT_XBGR1555,
+	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_XRGB1555,
+	DRM_FORMAT_ABGR4444,
+	DRM_FORMAT_XBGR4444,
+	DRM_FORMAT_ARGB4444,
+	DRM_FORMAT_XRGB4444,
+};
+
+static const struct pl111_variant_data pl110_nomadik_variant = {
+	.name = "LCDC (PL110 Nomadik)",
+	.formats = pl110_nomadik_pixel_formats,
+	.nformats = ARRAY_SIZE(pl110_nomadik_pixel_formats),
+	.is_lcdc = true,
+	.st_bitmux_control = true,
+	.broken_vblank = true,
+	.fb_bpp = 16,
+};
+
 static const struct amba_id pl111_id_table[] = {
 	{
 		.id = 0x00041110,
 		.mask = 0x000fffff,
-		.data = (void*)&pl110_variant,
+		.data = (void *)&pl110_variant,
+	},
+	{
+		.id = 0x00180110,
+		.mask = 0x00fffffe,
+		.data = (void *)&pl110_nomadik_variant,
 	},
 	{
 		.id = 0x00041111,
 		.mask = 0x000fffff,
-		.data = (void*)&pl111_variant,
+		.data = (void *)&pl111_variant,
 	},
 	{0, 0},
 };
diff --git a/drivers/gpu/drm/pl111/pl111_nomadik.c b/drivers/gpu/drm/pl111/pl111_nomadik.c
new file mode 100644
index 000000000000..6f385e59be22
--- /dev/null
+++ b/drivers/gpu/drm/pl111/pl111_nomadik.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0+
+#include <linux/device.h>
+#include <linux/regmap.h>
+#include <linux/mfd/syscon.h>
+#include <linux/bitops.h>
+#include <linux/module.h>
+#include "pl111_nomadik.h"
+
+#define PMU_CTRL_OFFSET 0x0000
+#define PMU_CTRL_LCDNDIF BIT(26)
+
+void pl111_nomadik_init(struct device *dev)
+{
+	struct regmap *pmu_regmap;
+
+	/*
+	 * Just bail out of this is not found, we could be running
+	 * multiplatform on something else than Nomadik.
+	 */
+	pmu_regmap =
+		syscon_regmap_lookup_by_compatible("stericsson,nomadik-pmu");
+	if (IS_ERR(pmu_regmap))
+		return;
+
+	/*
+	 * This bit in the PMU controller multiplexes the two graphics
+	 * blocks found in the Nomadik STn8815. The other one is called
+	 * MDIF (Master Display Interface) and gets muxed out here.
+	 */
+	regmap_update_bits(pmu_regmap,
+			   PMU_CTRL_OFFSET,
+			   PMU_CTRL_LCDNDIF,
+			   0);
+	dev_info(dev, "set Nomadik PMU mux to CLCD mode\n");
+}
+EXPORT_SYMBOL_GPL(pl111_nomadik_init);
diff --git a/drivers/gpu/drm/pl111/pl111_nomadik.h b/drivers/gpu/drm/pl111/pl111_nomadik.h
new file mode 100644
index 000000000000..19d663d46353
--- /dev/null
+++ b/drivers/gpu/drm/pl111/pl111_nomadik.h
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0+
+#include <linux/device.h>
+
+#ifndef PL111_NOMADIK_H
+#define PL111_NOMADIK_H
+#endif
+
+#ifdef CONFIG_ARCH_NOMADIK
+
+void pl111_nomadik_init(struct device *dev);
+
+#else
+
+static inline void pl111_nomadik_init(struct device *dev)
+{
+}
+
+#endif
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 768207fbbae3..0570c6826bff 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -1086,7 +1086,7 @@ static int qdev_output_init(struct drm_device *dev, int num_output)
 	/* we get HPD via client monitors config */
 	connector->polled = DRM_CONNECTOR_POLL_HPD;
 	encoder->possible_crtcs = 1 << num_output;
-	drm_mode_connector_attach_encoder(&qxl_output->base,
+	drm_connector_attach_encoder(&qxl_output->base,
 					  &qxl_output->enc);
 	drm_encoder_helper_add(encoder, &qxl_enc_helper_funcs);
 	drm_connector_helper_add(connector, &qxl_connector_helper_funcs);
diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index 7cb214577275..e37f0097f744 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -50,12 +50,6 @@ static const char *qxl_get_timeline_name(struct dma_fence *fence)
 	return "release";
 }
 
-static bool qxl_nop_signaling(struct dma_fence *fence)
-{
-	/* fences are always automatically signaled, so just pretend we did this.. */
-	return true;
-}
-
 static long qxl_fence_wait(struct dma_fence *fence, bool intr,
 			   signed long timeout)
 {
@@ -119,7 +113,6 @@ signaled:
 static const struct dma_fence_ops qxl_fence_ops = {
 	.get_driver_name = qxl_get_driver_name,
 	.get_timeline_name = qxl_get_timeline_name,
-	.enable_signaling = qxl_nop_signaling,
 	.wait = qxl_fence_wait,
 };
 
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index b9302c918271..d587779a80b4 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -5676,19 +5676,29 @@ int ci_dpm_init(struct radeon_device *rdev)
 	u16 data_offset, size;
 	u8 frev, crev;
 	struct ci_power_info *pi;
+	enum pci_bus_speed speed_cap;
+	struct pci_dev *root = rdev->pdev->bus->self;
 	int ret;
-	u32 mask;
 
 	pi = kzalloc(sizeof(struct ci_power_info), GFP_KERNEL);
 	if (pi == NULL)
 		return -ENOMEM;
 	rdev->pm.dpm.priv = pi;
 
-	ret = drm_pcie_get_speed_cap_mask(rdev->ddev, &mask);
-	if (ret)
+	speed_cap = pcie_get_speed_cap(root);
+	if (speed_cap == PCI_SPEED_UNKNOWN) {
 		pi->sys_pcie_mask = 0;
-	else
-		pi->sys_pcie_mask = mask;
+	} else {
+		if (speed_cap == PCIE_SPEED_8_0GT)
+			pi->sys_pcie_mask = RADEON_PCIE_SPEED_25 |
+				RADEON_PCIE_SPEED_50 |
+				RADEON_PCIE_SPEED_80;
+		else if (speed_cap == PCIE_SPEED_5_0GT)
+			pi->sys_pcie_mask = RADEON_PCIE_SPEED_25 |
+				RADEON_PCIE_SPEED_50;
+		else
+			pi->sys_pcie_mask = RADEON_PCIE_SPEED_25;
+	}
 	pi->force_pcie_gen = RADEON_PCIE_GEN_INVALID;
 
 	pi->pcie_gen_performance.max = RADEON_PCIE_GEN1;
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 7c73bc7e2f85..ebce4601a305 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -9499,9 +9499,10 @@ int cik_set_vce_clocks(struct radeon_device *rdev, u32 evclk, u32 ecclk)
 static void cik_pcie_gen3_enable(struct radeon_device *rdev)
 {
 	struct pci_dev *root = rdev->pdev->bus->self;
+	enum pci_bus_speed speed_cap;
 	int bridge_pos, gpu_pos;
-	u32 speed_cntl, mask, current_data_rate;
-	int ret, i;
+	u32 speed_cntl, current_data_rate;
+	int i;
 	u16 tmp16;
 
 	if (pci_is_root_bus(rdev->pdev->bus))
@@ -9516,23 +9517,24 @@ static void cik_pcie_gen3_enable(struct radeon_device *rdev)
 	if (!(rdev->flags & RADEON_IS_PCIE))
 		return;
 
-	ret = drm_pcie_get_speed_cap_mask(rdev->ddev, &mask);
-	if (ret != 0)
+	speed_cap = pcie_get_speed_cap(root);
+	if (speed_cap == PCI_SPEED_UNKNOWN)
 		return;
 
-	if (!(mask & (DRM_PCIE_SPEED_50 | DRM_PCIE_SPEED_80)))
+	if ((speed_cap != PCIE_SPEED_8_0GT) &&
+	    (speed_cap != PCIE_SPEED_5_0GT))
 		return;
 
 	speed_cntl = RREG32_PCIE_PORT(PCIE_LC_SPEED_CNTL);
 	current_data_rate = (speed_cntl & LC_CURRENT_DATA_RATE_MASK) >>
 		LC_CURRENT_DATA_RATE_SHIFT;
-	if (mask & DRM_PCIE_SPEED_80) {
+	if (speed_cap == PCIE_SPEED_8_0GT) {
 		if (current_data_rate == 2) {
 			DRM_INFO("PCIE gen 3 link speeds already enabled\n");
 			return;
 		}
 		DRM_INFO("enabling PCIE gen 3 link speeds, disable with radeon.pcie_gen2=0\n");
-	} else if (mask & DRM_PCIE_SPEED_50) {
+	} else if (speed_cap == PCIE_SPEED_5_0GT) {
 		if (current_data_rate == 1) {
 			DRM_INFO("PCIE gen 2 link speeds already enabled\n");
 			return;
@@ -9548,7 +9550,7 @@ static void cik_pcie_gen3_enable(struct radeon_device *rdev)
 	if (!gpu_pos)
 		return;
 
-	if (mask & DRM_PCIE_SPEED_80) {
+	if (speed_cap == PCIE_SPEED_8_0GT) {
 		/* re-try equalization if gen3 is not already enabled */
 		if (current_data_rate != 2) {
 			u16 bridge_cfg, gpu_cfg;
@@ -9636,9 +9638,9 @@ static void cik_pcie_gen3_enable(struct radeon_device *rdev)
 
 	pci_read_config_word(rdev->pdev, gpu_pos + PCI_EXP_LNKCTL2, &tmp16);
 	tmp16 &= ~0xf;
-	if (mask & DRM_PCIE_SPEED_80)
+	if (speed_cap == PCIE_SPEED_8_0GT)
 		tmp16 |= 3; /* gen3 */
-	else if (mask & DRM_PCIE_SPEED_50)
+	else if (speed_cap == PCIE_SPEED_5_0GT)
 		tmp16 |= 2; /* gen2 */
 	else
 		tmp16 |= 1; /* gen1 */
diff --git a/drivers/gpu/drm/radeon/r600_dpm.c b/drivers/gpu/drm/radeon/r600_dpm.c
index 73d4c5348116..5e044c98fca2 100644
--- a/drivers/gpu/drm/radeon/r600_dpm.c
+++ b/drivers/gpu/drm/radeon/r600_dpm.c
@@ -1327,9 +1327,9 @@ enum radeon_pcie_gen r600_get_pcie_gen_support(struct radeon_device *rdev,
 	case RADEON_PCIE_GEN3:
 		return RADEON_PCIE_GEN3;
 	default:
-		if ((sys_mask & DRM_PCIE_SPEED_80) && (default_gen == RADEON_PCIE_GEN3))
+		if ((sys_mask & RADEON_PCIE_SPEED_80) && (default_gen == RADEON_PCIE_GEN3))
 			return RADEON_PCIE_GEN3;
-		else if ((sys_mask & DRM_PCIE_SPEED_50) && (default_gen == RADEON_PCIE_GEN2))
+		else if ((sys_mask & RADEON_PCIE_SPEED_50) && (default_gen == RADEON_PCIE_GEN2))
 			return RADEON_PCIE_GEN2;
 		else
 			return RADEON_PCIE_GEN1;
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 4a2eb409aacc..1a6f6edb3515 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1653,6 +1653,10 @@ struct radeon_pm {
 	struct radeon_dpm       dpm;
 };
 
+#define RADEON_PCIE_SPEED_25 1
+#define RADEON_PCIE_SPEED_50 2
+#define RADEON_PCIE_SPEED_80 4
+
 int radeon_pm_get_type_index(struct radeon_device *rdev,
 			     enum radeon_pm_state_type ps_type,
 			     int instance);
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 2aea2bdff99b..414642e5b7a3 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -244,23 +244,15 @@ radeon_connector_update_scratch_regs(struct drm_connector *connector, enum drm_c
 {
 	struct drm_device *dev = connector->dev;
 	struct radeon_device *rdev = dev->dev_private;
-	struct drm_encoder *best_encoder = NULL;
-	struct drm_encoder *encoder = NULL;
+	struct drm_encoder *best_encoder;
+	struct drm_encoder *encoder;
 	const struct drm_connector_helper_funcs *connector_funcs = connector->helper_private;
 	bool connected;
 	int i;
 
 	best_encoder = connector_funcs->best_encoder(connector);
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL,
-					   connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if ((encoder == best_encoder) && (status == connector_status_connected))
 			connected = true;
 		else
@@ -270,7 +262,6 @@ radeon_connector_update_scratch_regs(struct drm_connector *connector, enum drm_c
 			radeon_atombios_connected_scratch_regs(connector, encoder, connected);
 		else
 			radeon_combios_connected_scratch_regs(connector, encoder, connected);
-
 	}
 }
 
@@ -279,17 +270,11 @@ static struct drm_encoder *radeon_find_encoder(struct drm_connector *connector,
 	struct drm_encoder *encoder;
 	int i;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if (encoder->encoder_type == encoder_type)
 			return encoder;
 	}
+
 	return NULL;
 }
 
@@ -383,20 +368,23 @@ static int radeon_ddc_get_modes(struct drm_connector *connector)
 	int ret;
 
 	if (radeon_connector->edid) {
-		drm_mode_connector_update_edid_property(connector, radeon_connector->edid);
+		drm_connector_update_edid_property(connector, radeon_connector->edid);
 		ret = drm_add_edid_modes(connector, radeon_connector->edid);
 		return ret;
 	}
-	drm_mode_connector_update_edid_property(connector, NULL);
+	drm_connector_update_edid_property(connector, NULL);
 	return 0;
 }
 
 static struct drm_encoder *radeon_best_single_encoder(struct drm_connector *connector)
 {
-	int enc_id = connector->encoder_ids[0];
-	/* pick the encoder ids */
-	if (enc_id)
-		return drm_encoder_find(connector->dev, NULL, enc_id);
+	struct drm_encoder *encoder;
+	int i;
+
+	/* pick the first one */
+	drm_connector_for_each_possible_encoder(connector, encoder, i)
+		return encoder;
+
 	return NULL;
 }
 
@@ -436,19 +424,19 @@ radeon_connector_analog_encoder_conflict_solve(struct drm_connector *connector,
 	struct drm_device *dev = connector->dev;
 	struct drm_connector *conflict;
 	struct radeon_connector *radeon_conflict;
-	int i;
 
 	list_for_each_entry(conflict, &dev->mode_config.connector_list, head) {
+		struct drm_encoder *enc;
+		int i;
+
 		if (conflict == connector)
 			continue;
 
 		radeon_conflict = to_radeon_connector(conflict);
-		for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-			if (conflict->encoder_ids[i] == 0)
-				break;
 
+		drm_connector_for_each_possible_encoder(conflict, enc, i) {
 			/* if the IDs match */
-			if (conflict->encoder_ids[i] == encoder->base.id) {
+			if (enc == encoder) {
 				if (conflict->status != connector_status_connected)
 					continue;
 
@@ -1256,7 +1244,7 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	struct drm_encoder *encoder = NULL;
 	const struct drm_encoder_helper_funcs *encoder_funcs;
-	int i, r;
+	int r;
 	enum drm_connector_status ret = connector_status_disconnected;
 	bool dret = false, broken_edid = false;
 
@@ -1374,15 +1362,9 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
 
 	/* find analog encoder */
 	if (radeon_connector->dac_load_detect) {
-		for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-			if (connector->encoder_ids[i] == 0)
-				break;
-
-			encoder = drm_encoder_find(connector->dev, NULL,
-						   connector->encoder_ids[i]);
-			if (!encoder)
-				continue;
+		int i;
 
+		drm_connector_for_each_possible_encoder(connector, encoder, i) {
 			if (encoder->encoder_type != DRM_MODE_ENCODER_DAC &&
 			    encoder->encoder_type != DRM_MODE_ENCODER_TVDAC)
 				continue;
@@ -1458,18 +1440,11 @@ exit:
 /* okay need to be smart in here about which encoder to pick */
 static struct drm_encoder *radeon_dvi_encoder(struct drm_connector *connector)
 {
-	int enc_id = connector->encoder_ids[0];
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	struct drm_encoder *encoder;
 	int i;
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
 
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if (radeon_connector->use_digital == true) {
 			if (encoder->encoder_type == DRM_MODE_ENCODER_TMDS)
 				return encoder;
@@ -1484,8 +1459,9 @@ static struct drm_encoder *radeon_dvi_encoder(struct drm_connector *connector)
 
 	/* then check use digitial */
 	/* pick the first one */
-	if (enc_id)
-		return drm_encoder_find(connector->dev, NULL, enc_id);
+	drm_connector_for_each_possible_encoder(connector, encoder, i)
+		return encoder;
+
 	return NULL;
 }
 
@@ -1628,14 +1604,7 @@ u16 radeon_connector_encoder_get_dp_bridge_encoder_id(struct drm_connector *conn
 	struct radeon_encoder *radeon_encoder;
 	int i;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		radeon_encoder = to_radeon_encoder(encoder);
 
 		switch (radeon_encoder->encoder_id) {
@@ -1657,14 +1626,7 @@ static bool radeon_connector_encoder_is_hbr2(struct drm_connector *connector)
 	int i;
 	bool found = false;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		radeon_encoder = to_radeon_encoder(encoder);
 		if (radeon_encoder->caps & ATOM_ENCODER_CAP_RECORD_HBR2)
 			found = true;
diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c
index cd8a3ee16649..f920be236cc9 100644
--- a/drivers/gpu/drm/radeon/radeon_dp_mst.c
+++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c
@@ -195,11 +195,11 @@ static int radeon_dp_mst_get_ddc_modes(struct drm_connector *connector)
 	radeon_connector->edid = edid;
 	DRM_DEBUG_KMS("edid retrieved %p\n", edid);
 	if (radeon_connector->edid) {
-		drm_mode_connector_update_edid_property(&radeon_connector->base, radeon_connector->edid);
+		drm_connector_update_edid_property(&radeon_connector->base, radeon_connector->edid);
 		ret = drm_add_edid_modes(&radeon_connector->base, radeon_connector->edid);
 		return ret;
 	}
-	drm_mode_connector_update_edid_property(&radeon_connector->base, NULL);
+	drm_connector_update_edid_property(&radeon_connector->base, NULL);
 
 	return ret;
 }
@@ -290,7 +290,7 @@ static struct drm_connector *radeon_dp_add_mst_connector(struct drm_dp_mst_topol
 
 	drm_object_attach_property(&connector->base, dev->mode_config.path_property, 0);
 	drm_object_attach_property(&connector->base, dev->mode_config.tile_property, 0);
-	drm_mode_connector_set_path_property(connector, pathprop);
+	drm_connector_set_path_property(connector, pathprop);
 
 	return connector;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c
index c6ee80216cf4..c341fb2a5b56 100644
--- a/drivers/gpu/drm/radeon/radeon_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_encoders.c
@@ -211,7 +211,7 @@ radeon_link_encoder_connector(struct drm_device *dev)
 		list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
 			radeon_encoder = to_radeon_encoder(encoder);
 			if (radeon_encoder->devices & radeon_connector->devices) {
-				drm_mode_connector_attach_encoder(connector, encoder);
+				drm_connector_attach_encoder(connector, encoder);
 				if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT))
 					radeon_encoder_add_backlight(radeon_encoder, connector);
 			}
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index edbb4cd519fd..ba2fd295697f 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -307,7 +307,7 @@ struct radeon_bo *radeon_bo_ref(struct radeon_bo *bo)
 	if (bo == NULL)
 		return NULL;
 
-	ttm_bo_reference(&bo->tbo);
+	ttm_bo_get(&bo->tbo);
 	return bo;
 }
 
@@ -320,9 +320,8 @@ void radeon_bo_unref(struct radeon_bo **bo)
 		return;
 	rdev = (*bo)->rdev;
 	tbo = &((*bo)->tbo);
-	ttm_bo_unref(&tbo);
-	if (tbo == NULL)
-		*bo = NULL;
+	ttm_bo_put(tbo);
+	*bo = NULL;
 }
 
 int radeon_bo_pin_restricted(struct radeon_bo *bo, u32 domain, u64 max_offset,
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index 48f4b273e316..0c7f228db6e3 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /*
  * Copyright 2009 VMware, Inc.
  *
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 8689fcca051c..cbb67e9ffb3a 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -947,11 +947,11 @@ void radeon_ttm_set_active_vram_size(struct radeon_device *rdev, u64 size)
 static struct vm_operations_struct radeon_ttm_vm_ops;
 static const struct vm_operations_struct *ttm_vm_ops = NULL;
 
-static int radeon_ttm_fault(struct vm_fault *vmf)
+static vm_fault_t radeon_ttm_fault(struct vm_fault *vmf)
 {
 	struct ttm_buffer_object *bo;
 	struct radeon_device *rdev;
-	int r;
+	vm_fault_t ret;
 
 	bo = (struct ttm_buffer_object *)vmf->vma->vm_private_data;
 	if (bo == NULL) {
@@ -959,9 +959,9 @@ static int radeon_ttm_fault(struct vm_fault *vmf)
 	}
 	rdev = radeon_get_rdev(bo->bdev);
 	down_read(&rdev->pm.mclk_lock);
-	r = ttm_vm_ops->fault(vmf);
+	ret = ttm_vm_ops->fault(vmf);
 	up_read(&rdev->pm.mclk_lock);
-	return r;
+	return ret;
 }
 
 int radeon_mmap(struct file *filp, struct vm_area_struct *vma)
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 1907c950d76f..85c604d29235 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -7082,9 +7082,10 @@ int si_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk)
 static void si_pcie_gen3_enable(struct radeon_device *rdev)
 {
 	struct pci_dev *root = rdev->pdev->bus->self;
+	enum pci_bus_speed speed_cap;
 	int bridge_pos, gpu_pos;
-	u32 speed_cntl, mask, current_data_rate;
-	int ret, i;
+	u32 speed_cntl, current_data_rate;
+	int i;
 	u16 tmp16;
 
 	if (pci_is_root_bus(rdev->pdev->bus))
@@ -7099,23 +7100,24 @@ static void si_pcie_gen3_enable(struct radeon_device *rdev)
 	if (!(rdev->flags & RADEON_IS_PCIE))
 		return;
 
-	ret = drm_pcie_get_speed_cap_mask(rdev->ddev, &mask);
-	if (ret != 0)
+	speed_cap = pcie_get_speed_cap(root);
+	if (speed_cap == PCI_SPEED_UNKNOWN)
 		return;
 
-	if (!(mask & (DRM_PCIE_SPEED_50 | DRM_PCIE_SPEED_80)))
+	if ((speed_cap != PCIE_SPEED_8_0GT) &&
+	    (speed_cap != PCIE_SPEED_5_0GT))
 		return;
 
 	speed_cntl = RREG32_PCIE_PORT(PCIE_LC_SPEED_CNTL);
 	current_data_rate = (speed_cntl & LC_CURRENT_DATA_RATE_MASK) >>
 		LC_CURRENT_DATA_RATE_SHIFT;
-	if (mask & DRM_PCIE_SPEED_80) {
+	if (speed_cap == PCIE_SPEED_8_0GT) {
 		if (current_data_rate == 2) {
 			DRM_INFO("PCIE gen 3 link speeds already enabled\n");
 			return;
 		}
 		DRM_INFO("enabling PCIE gen 3 link speeds, disable with radeon.pcie_gen2=0\n");
-	} else if (mask & DRM_PCIE_SPEED_50) {
+	} else if (speed_cap == PCIE_SPEED_5_0GT) {
 		if (current_data_rate == 1) {
 			DRM_INFO("PCIE gen 2 link speeds already enabled\n");
 			return;
@@ -7131,7 +7133,7 @@ static void si_pcie_gen3_enable(struct radeon_device *rdev)
 	if (!gpu_pos)
 		return;
 
-	if (mask & DRM_PCIE_SPEED_80) {
+	if (speed_cap == PCIE_SPEED_8_0GT) {
 		/* re-try equalization if gen3 is not already enabled */
 		if (current_data_rate != 2) {
 			u16 bridge_cfg, gpu_cfg;
@@ -7219,9 +7221,9 @@ static void si_pcie_gen3_enable(struct radeon_device *rdev)
 
 	pci_read_config_word(rdev->pdev, gpu_pos + PCI_EXP_LNKCTL2, &tmp16);
 	tmp16 &= ~0xf;
-	if (mask & DRM_PCIE_SPEED_80)
+	if (speed_cap == PCIE_SPEED_8_0GT)
 		tmp16 |= 3; /* gen3 */
-	else if (mask & DRM_PCIE_SPEED_50)
+	else if (speed_cap == PCIE_SPEED_5_0GT)
 		tmp16 |= 2; /* gen2 */
 	else
 		tmp16 |= 1; /* gen1 */
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index fea88078cf8e..8fb60b3af015 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -6899,8 +6899,9 @@ int si_dpm_init(struct radeon_device *rdev)
 	struct ni_power_info *ni_pi;
 	struct si_power_info *si_pi;
 	struct atom_clock_dividers dividers;
+	enum pci_bus_speed speed_cap;
+	struct pci_dev *root = rdev->pdev->bus->self;
 	int ret;
-	u32 mask;
 
 	si_pi = kzalloc(sizeof(struct si_power_info), GFP_KERNEL);
 	if (si_pi == NULL)
@@ -6910,11 +6911,20 @@ int si_dpm_init(struct radeon_device *rdev)
 	eg_pi = &ni_pi->eg;
 	pi = &eg_pi->rv7xx;
 
-	ret = drm_pcie_get_speed_cap_mask(rdev->ddev, &mask);
-	if (ret)
+	speed_cap = pcie_get_speed_cap(root);
+	if (speed_cap == PCI_SPEED_UNKNOWN) {
 		si_pi->sys_pcie_mask = 0;
-	else
-		si_pi->sys_pcie_mask = mask;
+	} else {
+		if (speed_cap == PCIE_SPEED_8_0GT)
+			si_pi->sys_pcie_mask = RADEON_PCIE_SPEED_25 |
+				RADEON_PCIE_SPEED_50 |
+				RADEON_PCIE_SPEED_80;
+		else if (speed_cap == PCIE_SPEED_5_0GT)
+			si_pi->sys_pcie_mask = RADEON_PCIE_SPEED_25 |
+				RADEON_PCIE_SPEED_50;
+		else
+			si_pi->sys_pcie_mask = RADEON_PCIE_SPEED_25;
+	}
 	si_pi->force_pcie_gen = RADEON_PCIE_GEN_INVALID;
 	si_pi->boot_pcie_gen = si_get_current_pcie_speed(rdev);
 
diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c
index 155ad840f3c5..4c39de3f4f0f 100644
--- a/drivers/gpu/drm/rcar-du/rcar_lvds.c
+++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c
@@ -353,7 +353,7 @@ static int rcar_lvds_attach(struct drm_bridge *bridge)
 
 	drm_connector_helper_add(connector, &rcar_lvds_conn_helper_funcs);
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret < 0)
 		return ret;
 
@@ -434,8 +434,8 @@ static int rcar_lvds_parse_dt(struct rcar_lvds *lvds)
 			ret = -EPROBE_DEFER;
 	} else {
 		lvds->panel = of_drm_find_panel(remote);
-		if (!lvds->panel)
-			ret = -EPROBE_DEFER;
+		if (IS_ERR(lvds->panel))
+			ret = PTR_ERR(lvds->panel);
 	}
 
 done:
diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c
index c6fbdcd87c16..8ad0d773dc33 100644
--- a/drivers/gpu/drm/rockchip/cdn-dp-core.c
+++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c
@@ -275,7 +275,7 @@ static int cdn_dp_connector_get_modes(struct drm_connector *connector)
 		dp->sink_has_audio = drm_detect_monitor_audio(edid);
 		ret = drm_add_edid_modes(connector, edid);
 		if (ret)
-			drm_mode_connector_update_edid_property(connector,
+			drm_connector_update_edid_property(connector,
 								edid);
 	}
 	mutex_unlock(&dp->lock);
@@ -1062,7 +1062,7 @@ static int cdn_dp_bind(struct device *dev, struct device *master, void *data)
 
 	drm_connector_helper_add(connector, &cdn_dp_connector_helper_funcs);
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret) {
 		DRM_ERROR("failed to attach connector and encoder\n");
 		goto err_free_connector;
diff --git a/drivers/gpu/drm/rockchip/cdn-dp-reg.c b/drivers/gpu/drm/rockchip/cdn-dp-reg.c
index eb3042c6d1b2..3105965fc260 100644
--- a/drivers/gpu/drm/rockchip/cdn-dp-reg.c
+++ b/drivers/gpu/drm/rockchip/cdn-dp-reg.c
@@ -792,7 +792,6 @@ err_config_video:
 
 int cdn_dp_audio_stop(struct cdn_dp_device *dp, struct audio_info *audio)
 {
-	u32 val;
 	int ret;
 
 	ret = cdn_dp_reg_write(dp, AUDIO_PACK_CONTROL, 0);
@@ -801,11 +800,7 @@ int cdn_dp_audio_stop(struct cdn_dp_device *dp, struct audio_info *audio)
 		return ret;
 	}
 
-	val = SPDIF_AVG_SEL | SPDIF_JITTER_BYPASS;
-	val |= SPDIF_FIFO_MID_RANGE(0xe0);
-	val |= SPDIF_JITTER_THRSH(0xe0);
-	val |= SPDIF_JITTER_AVG_WIN(7);
-	writel(val, dp->regs + SPDIF_CTRL_ADDR);
+	writel(0, dp->regs + SPDIF_CTRL_ADDR);
 
 	/* clearn the audio config and reset */
 	writel(0, dp->regs + AUDIO_SRC_CNTL);
@@ -929,12 +924,6 @@ static void cdn_dp_audio_config_spdif(struct cdn_dp_device *dp)
 {
 	u32 val;
 
-	val = SPDIF_AVG_SEL | SPDIF_JITTER_BYPASS;
-	val |= SPDIF_FIFO_MID_RANGE(0xe0);
-	val |= SPDIF_JITTER_THRSH(0xe0);
-	val |= SPDIF_JITTER_AVG_WIN(7);
-	writel(val, dp->regs + SPDIF_CTRL_ADDR);
-
 	writel(SYNC_WR_TO_CH_ZERO, dp->regs + FIFO_CNTL);
 
 	val = MAX_NUM_CH(2) | AUDIO_TYPE_LPCM | CFG_SUB_PCKT_NUM(4);
@@ -942,9 +931,6 @@ static void cdn_dp_audio_config_spdif(struct cdn_dp_device *dp)
 	writel(SMPL2PKT_EN, dp->regs + SMPL2PKT_CNTL);
 
 	val = SPDIF_ENABLE | SPDIF_AVG_SEL | SPDIF_JITTER_BYPASS;
-	val |= SPDIF_FIFO_MID_RANGE(0xe0);
-	val |= SPDIF_JITTER_THRSH(0xe0);
-	val |= SPDIF_JITTER_AVG_WIN(7);
 	writel(val, dp->regs + SPDIF_CTRL_ADDR);
 
 	clk_prepare_enable(dp->spdif_clk);
diff --git a/drivers/gpu/drm/rockchip/dw-mipi-dsi.c b/drivers/gpu/drm/rockchip/dw-mipi-dsi.c
index d53d5a09547f..662b6cb5d3f0 100644
--- a/drivers/gpu/drm/rockchip/dw-mipi-dsi.c
+++ b/drivers/gpu/drm/rockchip/dw-mipi-dsi.c
@@ -595,7 +595,7 @@ static int dw_mipi_dsi_host_attach(struct mipi_dsi_host *host,
 	dsi->format = device->format;
 	dsi->mode_flags = device->mode_flags;
 	dsi->panel = of_drm_find_panel(device->dev.of_node);
-	if (dsi->panel)
+	if (!IS_ERR(dsi->panel))
 		return drm_panel_attach(dsi->panel, &dsi->connector);
 
 	return -EINVAL;
@@ -1129,7 +1129,7 @@ static int dw_mipi_dsi_register(struct drm_device *drm,
 			   &dw_mipi_dsi_atomic_connector_funcs,
 			   DRM_MODE_CONNECTOR_DSI);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c
index 88d0774c97bd..1c02b3e61299 100644
--- a/drivers/gpu/drm/rockchip/inno_hdmi.c
+++ b/drivers/gpu/drm/rockchip/inno_hdmi.c
@@ -565,7 +565,7 @@ static int inno_hdmi_connector_get_modes(struct drm_connector *connector)
 	if (edid) {
 		hdmi->hdmi_data.sink_is_hdmi = drm_detect_hdmi_monitor(edid);
 		hdmi->hdmi_data.sink_has_audio = drm_detect_monitor_audio(edid);
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 	}
@@ -634,7 +634,7 @@ static int inno_hdmi_register(struct drm_device *drm, struct inno_hdmi *hdmi)
 	drm_connector_init(drm, &hdmi->connector, &inno_hdmi_connector_funcs,
 			   DRM_MODE_CONNECTOR_HDMIA);
 
-	drm_mode_connector_attach_encoder(&hdmi->connector, encoder);
+	drm_connector_attach_encoder(&hdmi->connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
index d4f4118b482d..ea18cb2a76c0 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
@@ -18,52 +18,13 @@
 #include <drm/drm_atomic.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 
 #include "rockchip_drm_drv.h"
 #include "rockchip_drm_fb.h"
 #include "rockchip_drm_gem.h"
 #include "rockchip_drm_psr.h"
 
-#define to_rockchip_fb(x) container_of(x, struct rockchip_drm_fb, fb)
-
-struct rockchip_drm_fb {
-	struct drm_framebuffer fb;
-	struct drm_gem_object *obj[ROCKCHIP_MAX_FB_BUFFER];
-};
-
-struct drm_gem_object *rockchip_fb_get_gem_obj(struct drm_framebuffer *fb,
-					       unsigned int plane)
-{
-	struct rockchip_drm_fb *rk_fb = to_rockchip_fb(fb);
-
-	if (plane >= ROCKCHIP_MAX_FB_BUFFER)
-		return NULL;
-
-	return rk_fb->obj[plane];
-}
-
-static void rockchip_drm_fb_destroy(struct drm_framebuffer *fb)
-{
-	struct rockchip_drm_fb *rockchip_fb = to_rockchip_fb(fb);
-	int i;
-
-	for (i = 0; i < ROCKCHIP_MAX_FB_BUFFER; i++)
-		drm_gem_object_put_unlocked(rockchip_fb->obj[i]);
-
-	drm_framebuffer_cleanup(fb);
-	kfree(rockchip_fb);
-}
-
-static int rockchip_drm_fb_create_handle(struct drm_framebuffer *fb,
-					 struct drm_file *file_priv,
-					 unsigned int *handle)
-{
-	struct rockchip_drm_fb *rockchip_fb = to_rockchip_fb(fb);
-
-	return drm_gem_handle_create(file_priv,
-				     rockchip_fb->obj[0], handle);
-}
-
 static int rockchip_drm_fb_dirty(struct drm_framebuffer *fb,
 				 struct drm_file *file,
 				 unsigned int flags, unsigned int color,
@@ -75,46 +36,45 @@ static int rockchip_drm_fb_dirty(struct drm_framebuffer *fb,
 }
 
 static const struct drm_framebuffer_funcs rockchip_drm_fb_funcs = {
-	.destroy	= rockchip_drm_fb_destroy,
-	.create_handle	= rockchip_drm_fb_create_handle,
-	.dirty		= rockchip_drm_fb_dirty,
+	.destroy       = drm_gem_fb_destroy,
+	.create_handle = drm_gem_fb_create_handle,
+	.dirty	       = rockchip_drm_fb_dirty,
 };
 
-static struct rockchip_drm_fb *
+static struct drm_framebuffer *
 rockchip_fb_alloc(struct drm_device *dev, const struct drm_mode_fb_cmd2 *mode_cmd,
 		  struct drm_gem_object **obj, unsigned int num_planes)
 {
-	struct rockchip_drm_fb *rockchip_fb;
+	struct drm_framebuffer *fb;
 	int ret;
 	int i;
 
-	rockchip_fb = kzalloc(sizeof(*rockchip_fb), GFP_KERNEL);
-	if (!rockchip_fb)
+	fb = kzalloc(sizeof(*fb), GFP_KERNEL);
+	if (!fb)
 		return ERR_PTR(-ENOMEM);
 
-	drm_helper_mode_fill_fb_struct(dev, &rockchip_fb->fb, mode_cmd);
+	drm_helper_mode_fill_fb_struct(dev, fb, mode_cmd);
 
 	for (i = 0; i < num_planes; i++)
-		rockchip_fb->obj[i] = obj[i];
+		fb->obj[i] = obj[i];
 
-	ret = drm_framebuffer_init(dev, &rockchip_fb->fb,
-				   &rockchip_drm_fb_funcs);
+	ret = drm_framebuffer_init(dev, fb, &rockchip_drm_fb_funcs);
 	if (ret) {
 		DRM_DEV_ERROR(dev->dev,
 			      "Failed to initialize framebuffer: %d\n",
 			      ret);
-		kfree(rockchip_fb);
+		kfree(fb);
 		return ERR_PTR(ret);
 	}
 
-	return rockchip_fb;
+	return fb;
 }
 
 static struct drm_framebuffer *
 rockchip_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 			const struct drm_mode_fb_cmd2 *mode_cmd)
 {
-	struct rockchip_drm_fb *rockchip_fb;
+	struct drm_framebuffer *fb;
 	struct drm_gem_object *objs[ROCKCHIP_MAX_FB_BUFFER];
 	struct drm_gem_object *obj;
 	unsigned int hsub;
@@ -153,13 +113,13 @@ rockchip_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 		objs[i] = obj;
 	}
 
-	rockchip_fb = rockchip_fb_alloc(dev, mode_cmd, objs, i);
-	if (IS_ERR(rockchip_fb)) {
-		ret = PTR_ERR(rockchip_fb);
+	fb = rockchip_fb_alloc(dev, mode_cmd, objs, i);
+	if (IS_ERR(fb)) {
+		ret = PTR_ERR(fb);
 		goto err_gem_object_unreference;
 	}
 
-	return &rockchip_fb->fb;
+	return fb;
 
 err_gem_object_unreference:
 	for (i--; i >= 0; i--)
@@ -242,13 +202,13 @@ rockchip_drm_framebuffer_init(struct drm_device *dev,
 			      const struct drm_mode_fb_cmd2 *mode_cmd,
 			      struct drm_gem_object *obj)
 {
-	struct rockchip_drm_fb *rockchip_fb;
+	struct drm_framebuffer *fb;
 
-	rockchip_fb = rockchip_fb_alloc(dev, mode_cmd, &obj, 1);
-	if (IS_ERR(rockchip_fb))
-		return ERR_CAST(rockchip_fb);
+	fb = rockchip_fb_alloc(dev, mode_cmd, &obj, 1);
+	if (IS_ERR(fb))
+		return ERR_CAST(fb);
 
-	return &rockchip_fb->fb;
+	return fb;
 }
 
 void rockchip_drm_mode_config_init(struct drm_device *dev)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.h b/drivers/gpu/drm/rockchip/rockchip_drm_fb.h
index 2fe47f1ee98f..f1265cb1aee8 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.h
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.h
@@ -22,7 +22,4 @@ rockchip_drm_framebuffer_init(struct drm_device *dev,
 void rockchip_drm_framebuffer_fini(struct drm_framebuffer *fb);
 
 void rockchip_drm_mode_config_init(struct drm_device *dev);
-
-struct drm_gem_object *rockchip_fb_get_gem_obj(struct drm_framebuffer *fb,
-					       unsigned int plane);
 #endif /* _ROCKCHIP_DRM_FB_H */
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index 2121345a61af..1359e5c773e4 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -243,18 +243,6 @@ static enum vop_data_format vop_convert_format(uint32_t format)
 	}
 }
 
-static bool is_yuv_support(uint32_t format)
-{
-	switch (format) {
-	case DRM_FORMAT_NV12:
-	case DRM_FORMAT_NV16:
-	case DRM_FORMAT_NV24:
-		return true;
-	default:
-		return false;
-	}
-}
-
 static uint16_t scl_vop_cal_scale(enum scale_mode mode, uint32_t src,
 				  uint32_t dst, bool is_horizontal,
 				  int vsu_mode, int *vskiplines)
@@ -298,7 +286,8 @@ static void scl_vop_cal_scl_fac(struct vop *vop, const struct vop_win_data *win,
 	uint16_t cbcr_ver_scl_mode = SCALE_NONE;
 	int hsub = drm_format_horz_chroma_subsampling(pixel_format);
 	int vsub = drm_format_vert_chroma_subsampling(pixel_format);
-	bool is_yuv = is_yuv_support(pixel_format);
+	const struct drm_format_info *info;
+	bool is_yuv = false;
 	uint16_t cbcr_src_w = src_w / hsub;
 	uint16_t cbcr_src_h = src_h / vsub;
 	uint16_t vsu_mode;
@@ -306,6 +295,11 @@ static void scl_vop_cal_scl_fac(struct vop *vop, const struct vop_win_data *win,
 	uint32_t val;
 	int vskiplines;
 
+	info = drm_format_info(pixel_format);
+
+	if (info->is_yuv)
+		is_yuv = true;
+
 	if (dst_w > 3840) {
 		DRM_DEV_ERROR(vop->dev, "Maximum dst width (3840) exceeded\n");
 		return;
@@ -486,6 +480,31 @@ static void vop_line_flag_irq_disable(struct vop *vop)
 	spin_unlock_irqrestore(&vop->irq_lock, flags);
 }
 
+static int vop_core_clks_enable(struct vop *vop)
+{
+	int ret;
+
+	ret = clk_enable(vop->hclk);
+	if (ret < 0)
+		return ret;
+
+	ret = clk_enable(vop->aclk);
+	if (ret < 0)
+		goto err_disable_hclk;
+
+	return 0;
+
+err_disable_hclk:
+	clk_disable(vop->hclk);
+	return ret;
+}
+
+static void vop_core_clks_disable(struct vop *vop)
+{
+	clk_disable(vop->aclk);
+	clk_disable(vop->hclk);
+}
+
 static int vop_enable(struct drm_crtc *crtc)
 {
 	struct vop *vop = to_vop(crtc);
@@ -497,17 +516,13 @@ static int vop_enable(struct drm_crtc *crtc)
 		return ret;
 	}
 
-	ret = clk_enable(vop->hclk);
+	ret = vop_core_clks_enable(vop);
 	if (WARN_ON(ret < 0))
 		goto err_put_pm_runtime;
 
 	ret = clk_enable(vop->dclk);
 	if (WARN_ON(ret < 0))
-		goto err_disable_hclk;
-
-	ret = clk_enable(vop->aclk);
-	if (WARN_ON(ret < 0))
-		goto err_disable_dclk;
+		goto err_disable_core;
 
 	/*
 	 * Slave iommu shares power, irq and clock with vop.  It was associated
@@ -519,7 +534,7 @@ static int vop_enable(struct drm_crtc *crtc)
 	if (ret) {
 		DRM_DEV_ERROR(vop->dev,
 			      "failed to attach dma mapping, %d\n", ret);
-		goto err_disable_aclk;
+		goto err_disable_dclk;
 	}
 
 	spin_lock(&vop->reg_lock);
@@ -552,18 +567,14 @@ static int vop_enable(struct drm_crtc *crtc)
 
 	spin_unlock(&vop->reg_lock);
 
-	enable_irq(vop->irq);
-
 	drm_crtc_vblank_on(crtc);
 
 	return 0;
 
-err_disable_aclk:
-	clk_disable(vop->aclk);
 err_disable_dclk:
 	clk_disable(vop->dclk);
-err_disable_hclk:
-	clk_disable(vop->hclk);
+err_disable_core:
+	vop_core_clks_disable(vop);
 err_put_pm_runtime:
 	pm_runtime_put_sync(vop->dev);
 	return ret;
@@ -599,8 +610,6 @@ static void vop_crtc_atomic_disable(struct drm_crtc *crtc,
 
 	vop_dsp_hold_valid_irq_disable(vop);
 
-	disable_irq(vop->irq);
-
 	vop->is_enabled = false;
 
 	/*
@@ -609,8 +618,7 @@ static void vop_crtc_atomic_disable(struct drm_crtc *crtc,
 	rockchip_drm_dma_detach_device(vop->drm_dev, vop->dev);
 
 	clk_disable(vop->dclk);
-	clk_disable(vop->aclk);
-	clk_disable(vop->hclk);
+	vop_core_clks_disable(vop);
 	pm_runtime_put(vop->dev);
 	mutex_unlock(&vop->vop_lock);
 
@@ -666,7 +674,7 @@ static int vop_plane_atomic_check(struct drm_plane *plane,
 	 * Src.x1 can be odd when do clip, but yuv plane start point
 	 * need align with 2 pixel.
 	 */
-	if (is_yuv_support(fb->format->format) && ((state->src.x1 >> 16) % 2)) {
+	if (fb->format->is_yuv && ((state->src.x1 >> 16) % 2)) {
 		DRM_ERROR("Invalid Source: Yuv format not support odd xpos\n");
 		return -EINVAL;
 	}
@@ -728,7 +736,7 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
 		return;
 	}
 
-	obj = rockchip_fb_get_gem_obj(fb, 0);
+	obj = fb->obj[0];
 	rk_obj = to_rockchip_obj(obj);
 
 	actual_w = drm_rect_width(src) >> 16;
@@ -753,12 +761,12 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
 	VOP_WIN_SET(vop, win, format, format);
 	VOP_WIN_SET(vop, win, yrgb_vir, DIV_ROUND_UP(fb->pitches[0], 4));
 	VOP_WIN_SET(vop, win, yrgb_mst, dma_addr);
-	if (is_yuv_support(fb->format->format)) {
+	if (fb->format->is_yuv) {
 		int hsub = drm_format_horz_chroma_subsampling(fb->format->format);
 		int vsub = drm_format_vert_chroma_subsampling(fb->format->format);
 		int bpp = fb->format->cpp[1];
 
-		uv_obj = rockchip_fb_get_gem_obj(fb, 1);
+		uv_obj = fb->obj[1];
 		rk_uv_obj = to_rockchip_obj(uv_obj);
 
 		offset = (src->x1 >> 16) * bpp / hsub;
@@ -1178,6 +1186,18 @@ static irqreturn_t vop_isr(int irq, void *data)
 	int ret = IRQ_NONE;
 
 	/*
+	 * The irq is shared with the iommu. If the runtime-pm state of the
+	 * vop-device is disabled the irq has to be targeted at the iommu.
+	 */
+	if (!pm_runtime_get_if_in_use(vop->dev))
+		return IRQ_NONE;
+
+	if (vop_core_clks_enable(vop)) {
+		DRM_DEV_ERROR_RATELIMITED(vop->dev, "couldn't enable clocks\n");
+		goto out;
+	}
+
+	/*
 	 * interrupt register has interrupt status, enable and clear bits, we
 	 * must hold irq_lock to avoid a race with enable/disable_vblank().
 	*/
@@ -1192,7 +1212,7 @@ static irqreturn_t vop_isr(int irq, void *data)
 
 	/* This is expected for vop iommu irqs, since the irq is shared */
 	if (!active_irqs)
-		return IRQ_NONE;
+		goto out_disable;
 
 	if (active_irqs & DSP_HOLD_VALID_INTR) {
 		complete(&vop->dsp_hold_completion);
@@ -1218,6 +1238,10 @@ static irqreturn_t vop_isr(int irq, void *data)
 		DRM_DEV_ERROR(vop->dev, "Unknown VOP IRQs: %#02x\n",
 			      active_irqs);
 
+out_disable:
+	vop_core_clks_disable(vop);
+out:
+	pm_runtime_put(vop->dev);
 	return ret;
 }
 
@@ -1278,7 +1302,7 @@ static int vop_create_crtc(struct vop *vop)
 	for (i = 0; i < vop_data->win_size; i++) {
 		struct vop_win *vop_win = &vop->win[i];
 		const struct vop_win_data *win_data = vop_win->data;
-		unsigned long possible_crtcs = 1 << drm_crtc_index(crtc);
+		unsigned long possible_crtcs = drm_crtc_mask(crtc);
 
 		if (win_data->type != DRM_PLANE_TYPE_OVERLAY)
 			continue;
@@ -1596,9 +1620,6 @@ static int vop_bind(struct device *dev, struct device *master, void *data)
 	if (ret)
 		goto err_disable_pm_runtime;
 
-	/* IRQ is initially disabled; it gets enabled in power_on */
-	disable_irq(vop->irq);
-
 	return 0;
 
 err_disable_pm_runtime:
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
index 084acdd0019a..fcb91041a666 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
@@ -331,16 +331,19 @@ static inline int scl_vop_cal_lb_mode(int width, bool is_yuv)
 {
 	int lb_mode;
 
-	if (width > 2560)
-		lb_mode = LB_RGB_3840X2;
-	else if (width > 1920)
-		lb_mode = LB_RGB_2560X4;
-	else if (!is_yuv)
-		lb_mode = LB_RGB_1920X5;
-	else if (width > 1280)
-		lb_mode = LB_YUV_3840X5;
-	else
-		lb_mode = LB_YUV_2560X8;
+	if (is_yuv) {
+		if (width > 1280)
+			lb_mode = LB_YUV_3840X5;
+		else
+			lb_mode = LB_YUV_2560X8;
+	} else {
+		if (width > 2560)
+			lb_mode = LB_RGB_3840X2;
+		else if (width > 1920)
+			lb_mode = LB_RGB_2560X4;
+		else
+			lb_mode = LB_RGB_1920X5;
+	}
 
 	return lb_mode;
 }
diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.c b/drivers/gpu/drm/rockchip/rockchip_lvds.c
index e67f4ea28c0e..456bd9f13bae 100644
--- a/drivers/gpu/drm/rockchip/rockchip_lvds.c
+++ b/drivers/gpu/drm/rockchip/rockchip_lvds.c
@@ -363,8 +363,10 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master,
 		of_property_read_u32(endpoint, "reg", &endpoint_id);
 		ret = drm_of_find_panel_or_bridge(dev->of_node, 1, endpoint_id,
 						  &lvds->panel, &lvds->bridge);
-		if (!ret)
+		if (!ret) {
+			of_node_put(endpoint);
 			break;
+		}
 	}
 	if (!child_count) {
 		DRM_DEV_ERROR(dev, "lvds port does not have any children\n");
@@ -432,7 +434,7 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master,
 		drm_connector_helper_add(connector,
 					 &rockchip_lvds_connector_helper_funcs);
 
-		ret = drm_mode_connector_attach_encoder(connector, encoder);
+		ret = drm_connector_attach_encoder(connector, encoder);
 		if (ret < 0) {
 			DRM_DEV_ERROR(drm_dev->dev,
 				      "failed to attach encoder: %d\n", ret);
@@ -446,14 +448,12 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master,
 			goto err_free_connector;
 		}
 	} else {
-		lvds->bridge->encoder = encoder;
 		ret = drm_bridge_attach(encoder, lvds->bridge, NULL);
 		if (ret) {
 			DRM_DEV_ERROR(drm_dev->dev,
 				      "failed to attach bridge: %d\n", ret);
 			goto err_free_encoder;
 		}
-		encoder->bridge = lvds->bridge;
 	}
 
 	pm_runtime_enable(dev);
diff --git a/drivers/gpu/drm/savage/savage_state.c b/drivers/gpu/drm/savage/savage_state.c
index 2db89bed52e8..7559a820bd43 100644
--- a/drivers/gpu/drm/savage/savage_state.c
+++ b/drivers/gpu/drm/savage/savage_state.c
@@ -971,7 +971,7 @@ int savage_bci_cmdbuf(struct drm_device *dev, void *data, struct drm_file *file_
 	LOCK_TEST_WITH_RETURN(dev, file_priv);
 
 	if (dma && dma->buflist) {
-		if (cmdbuf->dma_idx > dma->buf_count) {
+		if (cmdbuf->dma_idx >= dma->buf_count) {
 			DRM_ERROR
 			    ("vertex buffer index %u out of range (0-%u)\n",
 			     cmdbuf->dma_idx, dma->buf_count - 1);
diff --git a/drivers/gpu/drm/scheduler/Makefile b/drivers/gpu/drm/scheduler/Makefile
index bd0377c0d2ee..7665883f81d4 100644
--- a/drivers/gpu/drm/scheduler/Makefile
+++ b/drivers/gpu/drm/scheduler/Makefile
@@ -20,7 +20,6 @@
 # OTHER DEALINGS IN THE SOFTWARE.
 #
 #
-ccflags-y := -Iinclude/drm
 gpu-sched-y := gpu_scheduler.o sched_fence.o
 
 obj-$(CONFIG_DRM_SCHED) += gpu-sched.o
diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c
index 44d480768dfe..4fc211e19d6e 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c
@@ -21,6 +21,29 @@
  *
  */
 
+/**
+ * DOC: Overview
+ *
+ * The GPU scheduler provides entities which allow userspace to push jobs
+ * into software queues which are then scheduled on a hardware run queue.
+ * The software queues have a priority among them. The scheduler selects the entities
+ * from the run queue using a FIFO. The scheduler provides dependency handling
+ * features among jobs. The driver is supposed to provide callback functions for
+ * backend operations to the scheduler like submitting a job to hardware run queue,
+ * returning the dependencies of a job etc.
+ *
+ * The organisation of the scheduler is the following:
+ *
+ * 1. Each hw run queue has one scheduler
+ * 2. Each scheduler has multiple run queues with different priorities
+ *    (e.g., HIGH_HW,HIGH_SW, KERNEL, NORMAL)
+ * 3. Each scheduler run queue has a queue of entities to schedule
+ * 4. Entities themselves maintain a queue of jobs that will be scheduled on
+ *    the hardware.
+ *
+ * The jobs in a entity are always scheduled in the order that they were pushed.
+ */
+
 #include <linux/kthread.h>
 #include <linux/wait.h>
 #include <linux/sched.h>
@@ -39,14 +62,30 @@ static bool drm_sched_entity_is_ready(struct drm_sched_entity *entity);
 static void drm_sched_wakeup(struct drm_gpu_scheduler *sched);
 static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb);
 
-/* Initialize a given run queue struct */
-static void drm_sched_rq_init(struct drm_sched_rq *rq)
+/**
+ * drm_sched_rq_init - initialize a given run queue struct
+ *
+ * @rq: scheduler run queue
+ *
+ * Initializes a scheduler runqueue.
+ */
+static void drm_sched_rq_init(struct drm_gpu_scheduler *sched,
+			      struct drm_sched_rq *rq)
 {
 	spin_lock_init(&rq->lock);
 	INIT_LIST_HEAD(&rq->entities);
 	rq->current_entity = NULL;
+	rq->sched = sched;
 }
 
+/**
+ * drm_sched_rq_add_entity - add an entity
+ *
+ * @rq: scheduler run queue
+ * @entity: scheduler entity
+ *
+ * Adds a scheduler entity to the run queue.
+ */
 static void drm_sched_rq_add_entity(struct drm_sched_rq *rq,
 				    struct drm_sched_entity *entity)
 {
@@ -57,6 +96,14 @@ static void drm_sched_rq_add_entity(struct drm_sched_rq *rq,
 	spin_unlock(&rq->lock);
 }
 
+/**
+ * drm_sched_rq_remove_entity - remove an entity
+ *
+ * @rq: scheduler run queue
+ * @entity: scheduler entity
+ *
+ * Removes a scheduler entity from the run queue.
+ */
 static void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
 				       struct drm_sched_entity *entity)
 {
@@ -70,9 +117,9 @@ static void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
 }
 
 /**
- * Select an entity which could provide a job to run
+ * drm_sched_rq_select_entity - Select an entity which could provide a job to run
  *
- * @rq		The run queue to check.
+ * @rq: scheduler run queue to check.
  *
  * Try to find a ready entity, returns NULL if none found.
  */
@@ -112,30 +159,33 @@ drm_sched_rq_select_entity(struct drm_sched_rq *rq)
 }
 
 /**
- * Init a context entity used by scheduler when submit to HW ring.
+ * drm_sched_entity_init - Init a context entity used by scheduler when
+ * submit to HW ring.
+ *
+ * @entity: scheduler entity to init
+ * @rq_list: the list of run queue on which jobs from this
+ *           entity can be submitted
+ * @num_rq_list: number of run queue in rq_list
+ * @guilty: atomic_t set to 1 when a job on this queue
+ *          is found to be guilty causing a timeout
  *
- * @sched	The pointer to the scheduler
- * @entity	The pointer to a valid drm_sched_entity
- * @rq		The run queue this entity belongs
- * @guilty      atomic_t set to 1 when a job on this queue
- *              is found to be guilty causing a timeout
+ * Note: the rq_list should have atleast one element to schedule
+ *       the entity
  *
- * return 0 if succeed. negative error code on failure
+ * Returns 0 on success or a negative error code on failure.
 */
-int drm_sched_entity_init(struct drm_gpu_scheduler *sched,
-			  struct drm_sched_entity *entity,
-			  struct drm_sched_rq *rq,
+int drm_sched_entity_init(struct drm_sched_entity *entity,
+			  struct drm_sched_rq **rq_list,
+			  unsigned int num_rq_list,
 			  atomic_t *guilty)
 {
-	if (!(sched && entity && rq))
+	if (!(entity && rq_list && num_rq_list > 0 && rq_list[0]))
 		return -EINVAL;
 
 	memset(entity, 0, sizeof(struct drm_sched_entity));
 	INIT_LIST_HEAD(&entity->list);
-	entity->rq = rq;
-	entity->sched = sched;
+	entity->rq = rq_list[0];
 	entity->guilty = guilty;
-	entity->fini_status = 0;
 	entity->last_scheduled = NULL;
 
 	spin_lock_init(&entity->rq_lock);
@@ -149,40 +199,27 @@ int drm_sched_entity_init(struct drm_gpu_scheduler *sched,
 EXPORT_SYMBOL(drm_sched_entity_init);
 
 /**
- * Query if entity is initialized
+ * drm_sched_entity_is_idle - Check if entity is idle
  *
- * @sched       Pointer to scheduler instance
- * @entity	The pointer to a valid scheduler entity
- *
- * return true if entity is initialized, false otherwise
-*/
-static bool drm_sched_entity_is_initialized(struct drm_gpu_scheduler *sched,
-					    struct drm_sched_entity *entity)
-{
-	return entity->sched == sched &&
-		entity->rq != NULL;
-}
-
-/**
- * Check if entity is idle
+ * @entity: scheduler entity
  *
- * @entity	The pointer to a valid scheduler entity
- *
- * Return true if entity don't has any unscheduled jobs.
+ * Returns true if the entity does not have any unscheduled jobs.
  */
 static bool drm_sched_entity_is_idle(struct drm_sched_entity *entity)
 {
 	rmb();
-	if (spsc_queue_peek(&entity->job_queue) == NULL)
+
+	if (list_empty(&entity->list) ||
+	    spsc_queue_peek(&entity->job_queue) == NULL)
 		return true;
 
 	return false;
 }
 
 /**
- * Check if entity is ready
+ * drm_sched_entity_is_ready - Check if entity is ready
  *
- * @entity	The pointer to a valid scheduler entity
+ * @entity: scheduler entity
  *
  * Return true if entity could provide a job.
  */
@@ -210,44 +247,67 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
 
 
 /**
- * Destroy a context entity
+ * drm_sched_entity_flush - Flush a context entity
  *
- * @sched       Pointer to scheduler instance
- * @entity	The pointer to a valid scheduler entity
+ * @entity: scheduler entity
+ * @timeout: time to wait in for Q to become empty in jiffies.
  *
- * Splitting drm_sched_entity_fini() into two functions, The first one is does the waiting,
+ * Splitting drm_sched_entity_fini() into two functions, The first one does the waiting,
  * removes the entity from the runqueue and returns an error when the process was killed.
+ *
+ * Returns the remaining time in jiffies left from the input timeout
  */
-void drm_sched_entity_do_release(struct drm_gpu_scheduler *sched,
-			   struct drm_sched_entity *entity)
+long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
 {
-	if (!drm_sched_entity_is_initialized(sched, entity))
-		return;
+	struct drm_gpu_scheduler *sched;
+	struct task_struct *last_user;
+	long ret = timeout;
+
+	sched = entity->rq->sched;
 	/**
 	 * The client will not queue more IBs during this fini, consume existing
 	 * queued IBs or discard them on SIGKILL
 	*/
-	if ((current->flags & PF_SIGNALED) && current->exit_code == SIGKILL)
-		entity->fini_status = -ERESTARTSYS;
-	else
-		entity->fini_status = wait_event_killable(sched->job_scheduled,
-					drm_sched_entity_is_idle(entity));
-	drm_sched_entity_set_rq(entity, NULL);
+	if (current->flags & PF_EXITING) {
+		if (timeout)
+			ret = wait_event_timeout(
+					sched->job_scheduled,
+					drm_sched_entity_is_idle(entity),
+					timeout);
+	} else
+		wait_event_killable(sched->job_scheduled, drm_sched_entity_is_idle(entity));
+
+
+	/* For killed process disable any more IBs enqueue right now */
+	last_user = cmpxchg(&entity->last_user, current->group_leader, NULL);
+	if ((!last_user || last_user == current->group_leader) &&
+	    (current->flags & PF_EXITING) && (current->exit_code == SIGKILL))
+		drm_sched_rq_remove_entity(entity->rq, entity);
+
+	return ret;
 }
-EXPORT_SYMBOL(drm_sched_entity_do_release);
+EXPORT_SYMBOL(drm_sched_entity_flush);
 
 /**
- * Destroy a context entity
+ * drm_sched_entity_cleanup - Destroy a context entity
+ *
+ * @entity: scheduler entity
  *
- * @sched       Pointer to scheduler instance
- * @entity	The pointer to a valid scheduler entity
+ * This should be called after @drm_sched_entity_do_release. It goes over the
+ * entity and signals all jobs with an error code if the process was killed.
  *
- * The second one then goes over the entity and signals all jobs with an error code.
  */
-void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched,
-			   struct drm_sched_entity *entity)
+void drm_sched_entity_fini(struct drm_sched_entity *entity)
 {
-	if (entity->fini_status) {
+	struct drm_gpu_scheduler *sched;
+
+	sched = entity->rq->sched;
+	drm_sched_rq_remove_entity(entity->rq, entity);
+
+	/* Consumption of existing IBs wasn't completed. Forcefully
+	 * remove them here.
+	 */
+	if (spsc_queue_peek(&entity->job_queue)) {
 		struct drm_sched_job *job;
 		int r;
 
@@ -267,27 +327,43 @@ void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched,
 			struct drm_sched_fence *s_fence = job->s_fence;
 			drm_sched_fence_scheduled(s_fence);
 			dma_fence_set_error(&s_fence->finished, -ESRCH);
-			r = dma_fence_add_callback(entity->last_scheduled, &job->finish_cb,
-							drm_sched_entity_kill_jobs_cb);
-			if (r == -ENOENT)
+
+			/*
+			 * When pipe is hanged by older entity, new entity might
+			 * not even have chance to submit it's first job to HW
+			 * and so entity->last_scheduled will remain NULL
+			 */
+			if (!entity->last_scheduled) {
 				drm_sched_entity_kill_jobs_cb(NULL, &job->finish_cb);
-			else if (r)
-				DRM_ERROR("fence add callback failed (%d)\n", r);
+			} else {
+				r = dma_fence_add_callback(entity->last_scheduled, &job->finish_cb,
+								drm_sched_entity_kill_jobs_cb);
+				if (r == -ENOENT)
+					drm_sched_entity_kill_jobs_cb(NULL, &job->finish_cb);
+				else if (r)
+					DRM_ERROR("fence add callback failed (%d)\n", r);
+			}
 		}
 	}
 
 	dma_fence_put(entity->last_scheduled);
 	entity->last_scheduled = NULL;
 }
-EXPORT_SYMBOL(drm_sched_entity_cleanup);
+EXPORT_SYMBOL(drm_sched_entity_fini);
 
-void drm_sched_entity_fini(struct drm_gpu_scheduler *sched,
-				struct drm_sched_entity *entity)
+/**
+ * drm_sched_entity_fini - Destroy a context entity
+ *
+ * @entity: scheduler entity
+ *
+ * Calls drm_sched_entity_do_release() and drm_sched_entity_cleanup()
+ */
+void drm_sched_entity_destroy(struct drm_sched_entity *entity)
 {
-	drm_sched_entity_do_release(sched, entity);
-	drm_sched_entity_cleanup(sched, entity);
+	drm_sched_entity_flush(entity, MAX_WAIT_SCHED_ENTITY_Q_EMPTY);
+	drm_sched_entity_fini(entity);
 }
-EXPORT_SYMBOL(drm_sched_entity_fini);
+EXPORT_SYMBOL(drm_sched_entity_destroy);
 
 static void drm_sched_entity_wakeup(struct dma_fence *f, struct dma_fence_cb *cb)
 {
@@ -295,7 +371,7 @@ static void drm_sched_entity_wakeup(struct dma_fence *f, struct dma_fence_cb *cb
 		container_of(cb, struct drm_sched_entity, cb);
 	entity->dependency = NULL;
 	dma_fence_put(f);
-	drm_sched_wakeup(entity->sched);
+	drm_sched_wakeup(entity->rq->sched);
 }
 
 static void drm_sched_entity_clear_dep(struct dma_fence *f, struct dma_fence_cb *cb)
@@ -306,29 +382,43 @@ static void drm_sched_entity_clear_dep(struct dma_fence *f, struct dma_fence_cb
 	dma_fence_put(f);
 }
 
+/**
+ * drm_sched_entity_set_rq - Sets the run queue for an entity
+ *
+ * @entity: scheduler entity
+ * @rq: scheduler run queue
+ *
+ * Sets the run queue for an entity and removes the entity from the previous
+ * run queue in which was present.
+ */
 void drm_sched_entity_set_rq(struct drm_sched_entity *entity,
 			     struct drm_sched_rq *rq)
 {
 	if (entity->rq == rq)
 		return;
 
-	spin_lock(&entity->rq_lock);
-
-	if (entity->rq)
-		drm_sched_rq_remove_entity(entity->rq, entity);
+	BUG_ON(!rq);
 
+	spin_lock(&entity->rq_lock);
+	drm_sched_rq_remove_entity(entity->rq, entity);
 	entity->rq = rq;
-	if (rq)
-		drm_sched_rq_add_entity(rq, entity);
-
+	drm_sched_rq_add_entity(rq, entity);
 	spin_unlock(&entity->rq_lock);
 }
 EXPORT_SYMBOL(drm_sched_entity_set_rq);
 
+/**
+ * drm_sched_dependency_optimized
+ *
+ * @fence: the dependency fence
+ * @entity: the entity which depends on the above fence
+ *
+ * Returns true if the dependency can be optimized and false otherwise
+ */
 bool drm_sched_dependency_optimized(struct dma_fence* fence,
 				    struct drm_sched_entity *entity)
 {
-	struct drm_gpu_scheduler *sched = entity->sched;
+	struct drm_gpu_scheduler *sched = entity->rq->sched;
 	struct drm_sched_fence *s_fence;
 
 	if (!fence || dma_fence_is_signaled(fence))
@@ -345,7 +435,7 @@ EXPORT_SYMBOL(drm_sched_dependency_optimized);
 
 static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
 {
-	struct drm_gpu_scheduler *sched = entity->sched;
+	struct drm_gpu_scheduler *sched = entity->rq->sched;
 	struct dma_fence * fence = entity->dependency;
 	struct drm_sched_fence *s_fence;
 
@@ -390,7 +480,7 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
 static struct drm_sched_job *
 drm_sched_entity_pop_job(struct drm_sched_entity *entity)
 {
-	struct drm_gpu_scheduler *sched = entity->sched;
+	struct drm_gpu_scheduler *sched = entity->rq->sched;
 	struct drm_sched_job *sched_job = to_drm_sched_job(
 						spsc_queue_peek(&entity->job_queue));
 
@@ -413,9 +503,10 @@ drm_sched_entity_pop_job(struct drm_sched_entity *entity)
 }
 
 /**
- * Submit a job to the job queue
+ * drm_sched_entity_push_job - Submit a job to the entity's job queue
  *
- * @sched_job		The pointer to job required to submit
+ * @sched_job: job to submit
+ * @entity: scheduler entity
  *
  * Note: To guarantee that the order of insertion to queue matches
  * the job's fence sequence number this function should be
@@ -431,12 +522,18 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job,
 
 	trace_drm_sched_job(sched_job, entity);
 
+	WRITE_ONCE(entity->last_user, current->group_leader);
 	first = spsc_queue_push(&entity->job_queue, &sched_job->queue_node);
 
 	/* first job wakes up scheduler */
 	if (first) {
 		/* Add the entity to the run queue */
 		spin_lock(&entity->rq_lock);
+		if (!entity->rq) {
+			DRM_ERROR("Trying to push to a killed entity\n");
+			spin_unlock(&entity->rq_lock);
+			return;
+		}
 		drm_sched_rq_add_entity(entity->rq, entity);
 		spin_unlock(&entity->rq_lock);
 		drm_sched_wakeup(sched);
@@ -452,24 +549,28 @@ static void drm_sched_job_finish(struct work_struct *work)
 						   finish_work);
 	struct drm_gpu_scheduler *sched = s_job->sched;
 
-	/* remove job from ring_mirror_list */
-	spin_lock(&sched->job_list_lock);
-	list_del_init(&s_job->node);
-	if (sched->timeout != MAX_SCHEDULE_TIMEOUT) {
-		struct drm_sched_job *next;
-
-		spin_unlock(&sched->job_list_lock);
-		cancel_delayed_work_sync(&s_job->work_tdr);
-		spin_lock(&sched->job_list_lock);
+	/*
+	 * Canceling the timeout without removing our job from the ring mirror
+	 * list is safe, as we will only end up in this worker if our jobs
+	 * finished fence has been signaled. So even if some another worker
+	 * manages to find this job as the next job in the list, the fence
+	 * signaled check below will prevent the timeout to be restarted.
+	 */
+	cancel_delayed_work_sync(&s_job->work_tdr);
 
-		/* queue TDR for next job */
-		next = list_first_entry_or_null(&sched->ring_mirror_list,
-						struct drm_sched_job, node);
+	spin_lock(&sched->job_list_lock);
+	/* queue TDR for next job */
+	if (sched->timeout != MAX_SCHEDULE_TIMEOUT &&
+	    !list_is_last(&s_job->node, &sched->ring_mirror_list)) {
+		struct drm_sched_job *next = list_next_entry(s_job, node);
 
-		if (next)
+		if (!dma_fence_is_signaled(&next->s_fence->finished))
 			schedule_delayed_work(&next->work_tdr, sched->timeout);
 	}
+	/* remove job from ring_mirror_list */
+	list_del(&s_job->node);
 	spin_unlock(&sched->job_list_lock);
+
 	dma_fence_put(&s_job->s_fence->finished);
 	sched->ops->free_job(s_job);
 }
@@ -506,6 +607,13 @@ static void drm_sched_job_timedout(struct work_struct *work)
 	job->sched->ops->timedout_job(job);
 }
 
+/**
+ * drm_sched_hw_job_reset - stop the scheduler if it contains the bad job
+ *
+ * @sched: scheduler instance
+ * @bad: bad scheduler job
+ *
+ */
 void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
 {
 	struct drm_sched_job *s_job;
@@ -550,6 +658,12 @@ void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched, struct drm_sched_jo
 }
 EXPORT_SYMBOL(drm_sched_hw_job_reset);
 
+/**
+ * drm_sched_job_recovery - recover jobs after a reset
+ *
+ * @sched: scheduler instance
+ *
+ */
 void drm_sched_job_recovery(struct drm_gpu_scheduler *sched)
 {
 	struct drm_sched_job *s_job, *tmp;
@@ -599,16 +713,23 @@ void drm_sched_job_recovery(struct drm_gpu_scheduler *sched)
 EXPORT_SYMBOL(drm_sched_job_recovery);
 
 /**
- * Init a sched_job with basic field
+ * drm_sched_job_init - init a scheduler job
+ *
+ * @job: scheduler job to init
+ * @entity: scheduler entity to use
+ * @owner: job owner for debugging
  *
- * Note: Refer to drm_sched_entity_push_job documentation
+ * Refer to drm_sched_entity_push_job() documentation
  * for locking considerations.
+ *
+ * Returns 0 for success, negative error code otherwise.
  */
 int drm_sched_job_init(struct drm_sched_job *job,
-		       struct drm_gpu_scheduler *sched,
 		       struct drm_sched_entity *entity,
 		       void *owner)
 {
+	struct drm_gpu_scheduler *sched = entity->rq->sched;
+
 	job->sched = sched;
 	job->entity = entity;
 	job->s_priority = entity->rq - sched->sched_rq;
@@ -626,7 +747,11 @@ int drm_sched_job_init(struct drm_sched_job *job,
 EXPORT_SYMBOL(drm_sched_job_init);
 
 /**
- * Return ture if we can push more jobs to the hw.
+ * drm_sched_ready - is the scheduler ready
+ *
+ * @sched: scheduler instance
+ *
+ * Return true if we can push more jobs to the hw, otherwise false.
  */
 static bool drm_sched_ready(struct drm_gpu_scheduler *sched)
 {
@@ -635,7 +760,10 @@ static bool drm_sched_ready(struct drm_gpu_scheduler *sched)
 }
 
 /**
- * Wake up the scheduler when it is ready
+ * drm_sched_wakeup - Wake up the scheduler when it is ready
+ *
+ * @sched: scheduler instance
+ *
  */
 static void drm_sched_wakeup(struct drm_gpu_scheduler *sched)
 {
@@ -644,8 +772,12 @@ static void drm_sched_wakeup(struct drm_gpu_scheduler *sched)
 }
 
 /**
- * Select next entity to process
-*/
+ * drm_sched_select_entity - Select next entity to process
+ *
+ * @sched: scheduler instance
+ *
+ * Returns the entity to process or NULL if none are found.
+ */
 static struct drm_sched_entity *
 drm_sched_select_entity(struct drm_gpu_scheduler *sched)
 {
@@ -665,6 +797,14 @@ drm_sched_select_entity(struct drm_gpu_scheduler *sched)
 	return entity;
 }
 
+/**
+ * drm_sched_process_job - process a job
+ *
+ * @f: fence
+ * @cb: fence callbacks
+ *
+ * Called after job has finished execution.
+ */
 static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb)
 {
 	struct drm_sched_fence *s_fence =
@@ -680,6 +820,13 @@ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb)
 	wake_up_interruptible(&sched->wake_up_worker);
 }
 
+/**
+ * drm_sched_blocked - check if the scheduler is blocked
+ *
+ * @sched: scheduler instance
+ *
+ * Returns true if blocked, otherwise false.
+ */
 static bool drm_sched_blocked(struct drm_gpu_scheduler *sched)
 {
 	if (kthread_should_park()) {
@@ -690,6 +837,13 @@ static bool drm_sched_blocked(struct drm_gpu_scheduler *sched)
 	return false;
 }
 
+/**
+ * drm_sched_main - main scheduler thread
+ *
+ * @param: scheduler instance
+ *
+ * Returns 0.
+ */
 static int drm_sched_main(void *param)
 {
 	struct sched_param sparam = {.sched_priority = 1};
@@ -744,15 +898,17 @@ static int drm_sched_main(void *param)
 }
 
 /**
- * Init a gpu scheduler instance
+ * drm_sched_init - Init a gpu scheduler instance
  *
- * @sched		The pointer to the scheduler
- * @ops			The backend operations for this scheduler.
- * @hw_submissions	Number of hw submissions to do.
- * @name		Name used for debugging
+ * @sched: scheduler instance
+ * @ops: backend operations for this scheduler
+ * @hw_submission: number of hw submissions that can be in flight
+ * @hang_limit: number of times to allow a job to hang before dropping it
+ * @timeout: timeout value in jiffies for the scheduler
+ * @name: name used for debugging
  *
  * Return 0 on success, otherwise error code.
-*/
+ */
 int drm_sched_init(struct drm_gpu_scheduler *sched,
 		   const struct drm_sched_backend_ops *ops,
 		   unsigned hw_submission,
@@ -767,7 +923,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 	sched->timeout = timeout;
 	sched->hang_limit = hang_limit;
 	for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_MAX; i++)
-		drm_sched_rq_init(&sched->sched_rq[i]);
+		drm_sched_rq_init(sched, &sched->sched_rq[i]);
 
 	init_waitqueue_head(&sched->wake_up_worker);
 	init_waitqueue_head(&sched->job_scheduled);
@@ -788,9 +944,11 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 EXPORT_SYMBOL(drm_sched_init);
 
 /**
- * Destroy a gpu scheduler
+ * drm_sched_fini - Destroy a gpu scheduler
+ *
+ * @sched: scheduler instance
  *
- * @sched	The pointer to the scheduler
+ * Tears down and cleans up the scheduler.
  */
 void drm_sched_fini(struct drm_gpu_scheduler *sched)
 {
diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c
index df4461648e3f..d8d2dff9ea2f 100644
--- a/drivers/gpu/drm/scheduler/sched_fence.c
+++ b/drivers/gpu/drm/scheduler/sched_fence.c
@@ -81,11 +81,6 @@ static const char *drm_sched_fence_get_timeline_name(struct dma_fence *f)
 	return (const char *)fence->sched->name;
 }
 
-static bool drm_sched_fence_enable_signaling(struct dma_fence *f)
-{
-	return true;
-}
-
 /**
  * drm_sched_fence_free - free up the fence memory
  *
@@ -134,18 +129,12 @@ static void drm_sched_fence_release_finished(struct dma_fence *f)
 const struct dma_fence_ops drm_sched_fence_ops_scheduled = {
 	.get_driver_name = drm_sched_fence_get_driver_name,
 	.get_timeline_name = drm_sched_fence_get_timeline_name,
-	.enable_signaling = drm_sched_fence_enable_signaling,
-	.signaled = NULL,
-	.wait = dma_fence_default_wait,
 	.release = drm_sched_fence_release_scheduled,
 };
 
 const struct dma_fence_ops drm_sched_fence_ops_finished = {
 	.get_driver_name = drm_sched_fence_get_driver_name,
 	.get_timeline_name = drm_sched_fence_get_timeline_name,
-	.enable_signaling = drm_sched_fence_enable_signaling,
-	.signaled = NULL,
-	.wait = dma_fence_default_wait,
 	.release = drm_sched_fence_release_finished,
 };
 
@@ -172,7 +161,7 @@ struct drm_sched_fence *drm_sched_fence_create(struct drm_sched_entity *entity,
 		return NULL;
 
 	fence->owner = owner;
-	fence->sched = entity->sched;
+	fence->sched = entity->rq->sched;
 	spin_lock_init(&fence->lock);
 
 	seq = atomic_inc_return(&entity->fence_seq);
diff --git a/drivers/gpu/drm/selftests/drm_mm_selftests.h b/drivers/gpu/drm/selftests/drm_mm_selftests.h
index 54acc117550c..6b943ea1c57d 100644
--- a/drivers/gpu/drm/selftests/drm_mm_selftests.h
+++ b/drivers/gpu/drm/selftests/drm_mm_selftests.h
@@ -19,7 +19,9 @@ selftest(align64, igt_align64)
 selftest(evict, igt_evict)
 selftest(evict_range, igt_evict_range)
 selftest(bottomup, igt_bottomup)
+selftest(lowest, igt_lowest)
 selftest(topdown, igt_topdown)
+selftest(highest, igt_highest)
 selftest(color, igt_color)
 selftest(color_evict, igt_color_evict)
 selftest(color_evict_range, igt_color_evict_range)
diff --git a/drivers/gpu/drm/selftests/test-drm_mm.c b/drivers/gpu/drm/selftests/test-drm_mm.c
index 933af1c25387..fbed2c90fd51 100644
--- a/drivers/gpu/drm/selftests/test-drm_mm.c
+++ b/drivers/gpu/drm/selftests/test-drm_mm.c
@@ -1825,6 +1825,77 @@ err:
 	return ret;
 }
 
+static int __igt_once(unsigned int mode)
+{
+	struct drm_mm mm;
+	struct drm_mm_node rsvd_lo, rsvd_hi, node;
+	int err;
+
+	drm_mm_init(&mm, 0, 7);
+
+	memset(&rsvd_lo, 0, sizeof(rsvd_lo));
+	rsvd_lo.start = 1;
+	rsvd_lo.size = 1;
+	err = drm_mm_reserve_node(&mm, &rsvd_lo);
+	if (err) {
+		pr_err("Could not reserve low node\n");
+		goto err;
+	}
+
+	memset(&rsvd_hi, 0, sizeof(rsvd_hi));
+	rsvd_hi.start = 5;
+	rsvd_hi.size = 1;
+	err = drm_mm_reserve_node(&mm, &rsvd_hi);
+	if (err) {
+		pr_err("Could not reserve low node\n");
+		goto err_lo;
+	}
+
+	if (!drm_mm_hole_follows(&rsvd_lo) || !drm_mm_hole_follows(&rsvd_hi)) {
+		pr_err("Expected a hole after lo and high nodes!\n");
+		err = -EINVAL;
+		goto err_hi;
+	}
+
+	memset(&node, 0, sizeof(node));
+	err = drm_mm_insert_node_generic(&mm, &node,
+					 2, 0, 0,
+					 mode | DRM_MM_INSERT_ONCE);
+	if (!err) {
+		pr_err("Unexpectedly inserted the node into the wrong hole: node.start=%llx\n",
+		       node.start);
+		err = -EINVAL;
+		goto err_node;
+	}
+
+	err = drm_mm_insert_node_generic(&mm, &node, 2, 0, 0, mode);
+	if (err) {
+		pr_err("Could not insert the node into the available hole!\n");
+		err = -EINVAL;
+		goto err_hi;
+	}
+
+err_node:
+	drm_mm_remove_node(&node);
+err_hi:
+	drm_mm_remove_node(&rsvd_hi);
+err_lo:
+	drm_mm_remove_node(&rsvd_lo);
+err:
+	drm_mm_takedown(&mm);
+	return err;
+}
+
+static int igt_lowest(void *ignored)
+{
+	return __igt_once(DRM_MM_INSERT_LOW);
+}
+
+static int igt_highest(void *ignored)
+{
+	return __igt_once(DRM_MM_INSERT_HIGH);
+}
+
 static void separate_adjacent_colors(const struct drm_mm_node *node,
 				     unsigned long color,
 				     u64 *start,
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_crtc.c b/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
index 40df8887fc17..fc66167b0641 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
+++ b/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
@@ -675,7 +675,7 @@ int shmob_drm_connector_create(struct shmob_drm_device *sdev,
 	if (ret < 0)
 		goto err_cleanup;
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret < 0)
 		goto err_backlight;
 
diff --git a/drivers/gpu/drm/sti/sti_cursor.c b/drivers/gpu/drm/sti/sti_cursor.c
index df0a282b9615..57b870e1e696 100644
--- a/drivers/gpu/drm/sti/sti_cursor.c
+++ b/drivers/gpu/drm/sti/sti_cursor.c
@@ -332,7 +332,7 @@ static void sti_cursor_destroy(struct drm_plane *drm_plane)
 {
 	DRM_DEBUG_DRIVER("\n");
 
-	drm_plane_helper_disable(drm_plane);
+	drm_plane_helper_disable(drm_plane, NULL);
 	drm_plane_cleanup(drm_plane);
 }
 
diff --git a/drivers/gpu/drm/sti/sti_drv.c b/drivers/gpu/drm/sti/sti_drv.c
index 90c46b49c931..832fc43960ee 100644
--- a/drivers/gpu/drm/sti/sti_drv.c
+++ b/drivers/gpu/drm/sti/sti_drv.c
@@ -224,7 +224,7 @@ static int sti_bind(struct device *dev)
 
 	ret = sti_init(ddev);
 	if (ret)
-		goto err_drm_dev_unref;
+		goto err_drm_dev_put;
 
 	ret = component_bind_all(ddev->dev, ddev);
 	if (ret)
@@ -248,8 +248,8 @@ err_register:
 	drm_mode_config_cleanup(ddev);
 err_cleanup:
 	sti_cleanup(ddev);
-err_drm_dev_unref:
-	drm_dev_unref(ddev);
+err_drm_dev_put:
+	drm_dev_put(ddev);
 	return ret;
 }
 
@@ -259,7 +259,7 @@ static void sti_unbind(struct device *dev)
 
 	drm_dev_unregister(ddev);
 	sti_cleanup(ddev);
-	drm_dev_unref(ddev);
+	drm_dev_put(ddev);
 }
 
 static const struct component_master_ops sti_ops = {
diff --git a/drivers/gpu/drm/sti/sti_dvo.c b/drivers/gpu/drm/sti/sti_dvo.c
index a5979cd25cc7..b08376b7611b 100644
--- a/drivers/gpu/drm/sti/sti_dvo.c
+++ b/drivers/gpu/drm/sti/sti_dvo.c
@@ -387,7 +387,9 @@ sti_dvo_connector_detect(struct drm_connector *connector, bool force)
 
 	if (!dvo->panel) {
 		dvo->panel = of_drm_find_panel(dvo->panel_node);
-		if (dvo->panel)
+		if (IS_ERR(dvo->panel))
+			dvo->panel = NULL;
+		else
 			drm_panel_attach(dvo->panel, connector);
 	}
 
@@ -484,7 +486,7 @@ static int sti_dvo_bind(struct device *dev, struct device *master, void *data)
 	drm_connector_helper_add(drm_connector,
 				 &sti_dvo_connector_helper_funcs);
 
-	err = drm_mode_connector_attach_encoder(drm_connector, encoder);
+	err = drm_connector_attach_encoder(drm_connector, encoder);
 	if (err) {
 		DRM_ERROR("Failed to attach a connector to a encoder\n");
 		goto err_sysfs;
diff --git a/drivers/gpu/drm/sti/sti_gdp.c b/drivers/gpu/drm/sti/sti_gdp.c
index 9b2c47051b51..c32de6cbf061 100644
--- a/drivers/gpu/drm/sti/sti_gdp.c
+++ b/drivers/gpu/drm/sti/sti_gdp.c
@@ -211,7 +211,11 @@ static int gdp_dbg_show(struct seq_file *s, void *data)
 	struct drm_info_node *node = s->private;
 	struct sti_gdp *gdp = (struct sti_gdp *)node->info_ent->data;
 	struct drm_plane *drm_plane = &gdp->plane.drm_plane;
-	struct drm_crtc *crtc = drm_plane->crtc;
+	struct drm_crtc *crtc;
+
+	drm_modeset_lock(&drm_plane->mutex, NULL);
+	crtc = drm_plane->state->crtc;
+	drm_modeset_unlock(&drm_plane->mutex);
 
 	seq_printf(s, "%s: (vaddr = 0x%p)",
 		   sti_plane_to_str(&gdp->plane), gdp->regs);
@@ -879,7 +883,7 @@ static void sti_gdp_destroy(struct drm_plane *drm_plane)
 {
 	DRM_DEBUG_DRIVER("\n");
 
-	drm_plane_helper_disable(drm_plane);
+	drm_plane_helper_disable(drm_plane, NULL);
 	drm_plane_cleanup(drm_plane);
 }
 
diff --git a/drivers/gpu/drm/sti/sti_hda.c b/drivers/gpu/drm/sti/sti_hda.c
index 67bbdb49fffc..49438337f70d 100644
--- a/drivers/gpu/drm/sti/sti_hda.c
+++ b/drivers/gpu/drm/sti/sti_hda.c
@@ -709,7 +709,7 @@ static int sti_hda_bind(struct device *dev, struct device *master, void *data)
 	drm_connector_helper_add(drm_connector,
 			&sti_hda_connector_helper_funcs);
 
-	err = drm_mode_connector_attach_encoder(drm_connector, encoder);
+	err = drm_connector_attach_encoder(drm_connector, encoder);
 	if (err) {
 		DRM_ERROR("Failed to attach a connector to a encoder\n");
 		goto err_sysfs;
diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c
index 58f431102512..34cdc4644435 100644
--- a/drivers/gpu/drm/sti/sti_hdmi.c
+++ b/drivers/gpu/drm/sti/sti_hdmi.c
@@ -977,7 +977,7 @@ static int sti_hdmi_connector_get_modes(struct drm_connector *connector)
 	cec_notifier_set_phys_addr_from_edid(hdmi->notifier, edid);
 
 	count = drm_add_edid_modes(connector, edid);
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 
 	kfree(edid);
 	return count;
@@ -1290,7 +1290,7 @@ static int sti_hdmi_bind(struct device *dev, struct device *master, void *data)
 
 	hdmi->drm_connector = drm_connector;
 
-	err = drm_mode_connector_attach_encoder(drm_connector, encoder);
+	err = drm_connector_attach_encoder(drm_connector, encoder);
 	if (err) {
 		DRM_ERROR("Failed to attach a connector to a encoder\n");
 		goto err_sysfs;
diff --git a/drivers/gpu/drm/sti/sti_hqvdp.c b/drivers/gpu/drm/sti/sti_hqvdp.c
index 106be8c4e58b..03ac3b4a4469 100644
--- a/drivers/gpu/drm/sti/sti_hqvdp.c
+++ b/drivers/gpu/drm/sti/sti_hqvdp.c
@@ -1260,7 +1260,7 @@ static void sti_hqvdp_destroy(struct drm_plane *drm_plane)
 {
 	DRM_DEBUG_DRIVER("\n");
 
-	drm_plane_helper_disable(drm_plane);
+	drm_plane_helper_disable(drm_plane, NULL);
 	drm_plane_cleanup(drm_plane);
 }
 
diff --git a/drivers/gpu/drm/stm/drv.c b/drivers/gpu/drm/stm/drv.c
index 8698e08313e1..f2021b23554d 100644
--- a/drivers/gpu/drm/stm/drv.c
+++ b/drivers/gpu/drm/stm/drv.c
@@ -148,16 +148,16 @@ static int stm_drm_platform_probe(struct platform_device *pdev)
 
 	ret = drv_load(ddev);
 	if (ret)
-		goto err_unref;
+		goto err_put;
 
 	ret = drm_dev_register(ddev, 0);
 	if (ret)
-		goto err_unref;
+		goto err_put;
 
 	return 0;
 
-err_unref:
-	drm_dev_unref(ddev);
+err_put:
+	drm_dev_put(ddev);
 
 	return ret;
 }
@@ -170,7 +170,7 @@ static int stm_drm_platform_remove(struct platform_device *pdev)
 
 	drm_dev_unregister(ddev);
 	drv_unload(ddev);
-	drm_dev_unref(ddev);
+	drm_dev_put(ddev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c
index d997a6014d6c..808d9fb627e9 100644
--- a/drivers/gpu/drm/stm/ltdc.c
+++ b/drivers/gpu/drm/stm/ltdc.c
@@ -457,6 +457,14 @@ ltdc_crtc_mode_valid(struct drm_crtc *crtc,
 	int target_max = target + CLK_TOLERANCE_HZ;
 	int result;
 
+	result = clk_round_rate(ldev->pixel_clk, target);
+
+	DRM_DEBUG_DRIVER("clk rate target %d, available %d\n", target, result);
+
+	/* Filter modes according to the max frequency supported by the pads */
+	if (result > ldev->caps.pad_max_freq_hz)
+		return MODE_CLOCK_HIGH;
+
 	/*
 	 * Accept all "preferred" modes:
 	 * - this is important for panels because panel clock tolerances are
@@ -468,10 +476,6 @@ ltdc_crtc_mode_valid(struct drm_crtc *crtc,
 	if (mode->type & DRM_MODE_TYPE_PREFERRED)
 		return MODE_OK;
 
-	result = clk_round_rate(ldev->pixel_clk, target);
-
-	DRM_DEBUG_DRIVER("clk rate target %d, available %d\n", target, result);
-
 	/*
 	 * Filter modes according to the clock value, particularly useful for
 	 * hdmi modes that require precise pixel clocks.
@@ -991,11 +995,15 @@ static int ltdc_get_caps(struct drm_device *ddev)
 		 * does not work on 2nd layer.
 		 */
 		ldev->caps.non_alpha_only_l1 = true;
+		ldev->caps.pad_max_freq_hz = 90000000;
+		if (ldev->caps.hw_version == HWVER_10200)
+			ldev->caps.pad_max_freq_hz = 65000000;
 		break;
 	case HWVER_20101:
 		ldev->caps.reg_ofs = REG_OFS_4;
 		ldev->caps.pix_fmt_hw = ltdc_pix_fmt_a1;
 		ldev->caps.non_alpha_only_l1 = false;
+		ldev->caps.pad_max_freq_hz = 150000000;
 		break;
 	default:
 		return -ENODEV;
@@ -1074,8 +1082,11 @@ int ltdc_load(struct drm_device *ddev)
 		}
 	}
 
-	if (!IS_ERR(rstc))
+	if (!IS_ERR(rstc)) {
+		reset_control_assert(rstc);
+		usleep_range(10, 20);
 		reset_control_deassert(rstc);
+	}
 
 	/* Disable interrupts */
 	reg_clear(ldev->regs, LTDC_IER,
diff --git a/drivers/gpu/drm/stm/ltdc.h b/drivers/gpu/drm/stm/ltdc.h
index 1e16d6afb0d2..d5afb8960867 100644
--- a/drivers/gpu/drm/stm/ltdc.h
+++ b/drivers/gpu/drm/stm/ltdc.h
@@ -18,6 +18,7 @@ struct ltdc_caps {
 	u32 bus_width;		/* bus width (32 or 64 bits) */
 	const u32 *pix_fmt_hw;	/* supported pixel formats */
 	bool non_alpha_only_l1; /* non-native no-alpha formats on layer 1 */
+	int pad_max_freq_hz;	/* max frequency supported by pad */
 };
 
 #define LTDC_MAX_LAYER	4
diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig
index 156a865c3e6d..c2c042287c19 100644
--- a/drivers/gpu/drm/sun4i/Kconfig
+++ b/drivers/gpu/drm/sun4i/Kconfig
@@ -68,4 +68,11 @@ config DRM_SUN8I_MIXER
 	  graphics mixture and feed graphics to TCON, If M is
 	  selected the module will be called sun8i-mixer.
 
+config DRM_SUN8I_TCON_TOP
+	tristate
+	default DRM_SUN4I if DRM_SUN8I_MIXER!=n
+	help
+	  TCON TOP is responsible for configuring display pipeline for
+	  HTMI, TVE and LCD.
+
 endif
diff --git a/drivers/gpu/drm/sun4i/Makefile b/drivers/gpu/drm/sun4i/Makefile
index 9c81301d0eed..0eb38ac8e86e 100644
--- a/drivers/gpu/drm/sun4i/Makefile
+++ b/drivers/gpu/drm/sun4i/Makefile
@@ -40,3 +40,4 @@ obj-$(CONFIG_DRM_SUN4I_HDMI)	+= sun4i-drm-hdmi.o
 obj-$(CONFIG_DRM_SUN6I_DSI)	+= sun6i-dsi.o
 obj-$(CONFIG_DRM_SUN8I_DW_HDMI)	+= sun8i-drm-hdmi.o
 obj-$(CONFIG_DRM_SUN8I_MIXER)	+= sun8i-mixer.o
+obj-$(CONFIG_DRM_SUN8I_TCON_TOP) += sun8i_tcon_top.o
diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
index de0a76dfa1a2..d7950b52a1fd 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
@@ -86,12 +86,6 @@ static inline bool sun4i_backend_format_is_packed_yuv422(uint32_t format)
 	}
 }
 
-static inline bool sun4i_backend_format_is_yuv(uint32_t format)
-{
-	return sun4i_backend_format_is_planar_yuv(format) ||
-		sun4i_backend_format_is_packed_yuv422(format);
-}
-
 static void sun4i_backend_apply_color_correction(struct sunxi_engine *engine)
 {
 	int i;
@@ -304,7 +298,7 @@ int sun4i_backend_update_layer_formats(struct sun4i_backend *backend,
 			   SUN4I_BACKEND_ATTCTL_REG0_LAY_GLBALPHA_EN,
 			   val);
 
-	if (sun4i_backend_format_is_yuv(fb->format->format))
+	if (fb->format->is_yuv)
 		return sun4i_backend_update_yuv_format(backend, layer, plane);
 
 	ret = sun4i_backend_drm_format_to_layer(fb->format->format, &val);
@@ -384,7 +378,7 @@ int sun4i_backend_update_layer_buffer(struct sun4i_backend *backend,
 	 */
 	paddr -= PHYS_OFFSET;
 
-	if (sun4i_backend_format_is_yuv(fb->format->format))
+	if (fb->format->is_yuv)
 		return sun4i_backend_update_yuv_buffer(backend, fb, paddr);
 
 	/* Write the 32 lower bits of the address (in bits) */
@@ -502,7 +496,7 @@ static int sun4i_backend_atomic_check(struct sunxi_engine *engine,
 		if (fb->format->has_alpha || (plane_state->alpha != DRM_BLEND_ALPHA_OPAQUE))
 			num_alpha_planes++;
 
-		if (sun4i_backend_format_is_yuv(fb->format->format)) {
+		if (fb->format->is_yuv) {
 			DRM_DEBUG_DRIVER("Plane FB format is YUV\n");
 			num_yuv_planes++;
 		}
diff --git a/drivers/gpu/drm/sun4i/sun4i_crtc.c b/drivers/gpu/drm/sun4i/sun4i_crtc.c
index 2d7c57406715..3eedf335a935 100644
--- a/drivers/gpu/drm/sun4i/sun4i_crtc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_crtc.c
@@ -242,7 +242,7 @@ struct sun4i_crtc *sun4i_crtc_init(struct drm_device *drm,
 
 	/* Set possible_crtcs to this crtc for overlay planes */
 	for (i = 0; planes[i]; i++) {
-		uint32_t possible_crtcs = BIT(drm_crtc_index(&scrtc->crtc));
+		uint32_t possible_crtcs = drm_crtc_mask(&scrtc->crtc);
 		struct drm_plane *plane = planes[i];
 
 		if (plane->type == DRM_PLANE_TYPE_OVERLAY)
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index 50d19605c38f..dd19d674055c 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -26,6 +26,7 @@
 #include "sun4i_frontend.h"
 #include "sun4i_framebuffer.h"
 #include "sun4i_tcon.h"
+#include "sun8i_tcon_top.h"
 
 DEFINE_DRM_GEM_CMA_FOPS(sun4i_drv_fops);
 
@@ -143,7 +144,7 @@ cleanup_mode_config:
 	drm_mode_config_cleanup(drm);
 	of_reserved_mem_device_release(dev);
 free_drm:
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 	return ret;
 }
 
@@ -156,7 +157,7 @@ static void sun4i_drv_unbind(struct device *dev)
 	sun4i_framebuffer_free(drm);
 	drm_mode_config_cleanup(drm);
 	of_reserved_mem_device_release(dev);
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 }
 
 static const struct component_master_ops sun4i_drv_master_ops = {
@@ -197,6 +198,28 @@ static bool sun4i_drv_node_is_tcon(struct device_node *node)
 	return !!of_match_node(sun4i_tcon_of_table, node);
 }
 
+static bool sun4i_drv_node_is_tcon_with_ch0(struct device_node *node)
+{
+	const struct of_device_id *match;
+
+	match = of_match_node(sun4i_tcon_of_table, node);
+	if (match) {
+		struct sun4i_tcon_quirks *quirks;
+
+		quirks = (struct sun4i_tcon_quirks *)match->data;
+
+		return quirks->has_channel_0;
+	}
+
+	return false;
+}
+
+static bool sun4i_drv_node_is_tcon_top(struct device_node *node)
+{
+	return IS_ENABLED(CONFIG_DRM_SUN8I_TCON_TOP) &&
+		!!of_match_node(sun8i_tcon_top_of_table, node);
+}
+
 static int compare_of(struct device *dev, void *data)
 {
 	DRM_DEBUG_DRIVER("Comparing of node %pOF with %pOF\n",
@@ -231,12 +254,69 @@ struct endpoint_list {
 	DECLARE_KFIFO(fifo, struct device_node *, 16);
 };
 
+static void sun4i_drv_traverse_endpoints(struct endpoint_list *list,
+					 struct device_node *node,
+					 int port_id)
+{
+	struct device_node *ep, *remote, *port;
+
+	port = of_graph_get_port_by_id(node, port_id);
+	if (!port) {
+		DRM_DEBUG_DRIVER("No output to bind on port %d\n", port_id);
+		return;
+	}
+
+	for_each_available_child_of_node(port, ep) {
+		remote = of_graph_get_remote_port_parent(ep);
+		if (!remote) {
+			DRM_DEBUG_DRIVER("Error retrieving the output node\n");
+			continue;
+		}
+
+		if (sun4i_drv_node_is_tcon(node)) {
+			/*
+			 * TCON TOP is always probed before TCON. However, TCON
+			 * points back to TCON TOP when it is source for HDMI.
+			 * We have to skip it here to prevent infinite looping
+			 * between TCON TOP and TCON.
+			 */
+			if (sun4i_drv_node_is_tcon_top(remote)) {
+				DRM_DEBUG_DRIVER("TCON output endpoint is TCON TOP... skipping\n");
+				of_node_put(remote);
+				continue;
+			}
+
+			/*
+			 * If the node is our TCON with channel 0, the first
+			 * port is used for panel or bridges, and will not be
+			 * part of the component framework.
+			 */
+			if (sun4i_drv_node_is_tcon_with_ch0(node)) {
+				struct of_endpoint endpoint;
+
+				if (of_graph_parse_endpoint(ep, &endpoint)) {
+					DRM_DEBUG_DRIVER("Couldn't parse endpoint\n");
+					of_node_put(remote);
+					continue;
+				}
+
+				if (!endpoint.id) {
+					DRM_DEBUG_DRIVER("Endpoint is our panel... skipping\n");
+					of_node_put(remote);
+					continue;
+				}
+			}
+		}
+
+		kfifo_put(&list->fifo, remote);
+	}
+}
+
 static int sun4i_drv_add_endpoints(struct device *dev,
 				   struct endpoint_list *list,
 				   struct component_match **match,
 				   struct device_node *node)
 {
-	struct device_node *port, *ep, *remote;
 	int count = 0;
 
 	/*
@@ -272,41 +352,13 @@ static int sun4i_drv_add_endpoints(struct device *dev,
 		count++;
 	}
 
-	/* Inputs are listed first, then outputs */
-	port = of_graph_get_port_by_id(node, 1);
-	if (!port) {
-		DRM_DEBUG_DRIVER("No output to bind\n");
-		return count;
-	}
+	/* each node has at least one output */
+	sun4i_drv_traverse_endpoints(list, node, 1);
 
-	for_each_available_child_of_node(port, ep) {
-		remote = of_graph_get_remote_port_parent(ep);
-		if (!remote) {
-			DRM_DEBUG_DRIVER("Error retrieving the output node\n");
-			of_node_put(remote);
-			continue;
-		}
-
-		/*
-		 * If the node is our TCON, the first port is used for
-		 * panel or bridges, and will not be part of the
-		 * component framework.
-		 */
-		if (sun4i_drv_node_is_tcon(node)) {
-			struct of_endpoint endpoint;
-
-			if (of_graph_parse_endpoint(ep, &endpoint)) {
-				DRM_DEBUG_DRIVER("Couldn't parse endpoint\n");
-				continue;
-			}
-
-			if (!endpoint.id) {
-				DRM_DEBUG_DRIVER("Endpoint is our panel... skipping\n");
-				continue;
-			}
-		}
-
-		kfifo_put(&list->fifo, remote);
+	/* TCON TOP has second and third output */
+	if (sun4i_drv_node_is_tcon_top(node)) {
+		sun4i_drv_traverse_endpoints(list, node, 3);
+		sun4i_drv_traverse_endpoints(list, node, 5);
 	}
 
 	return count;
@@ -366,6 +418,7 @@ static const struct of_device_id sun4i_drv_of_table[] = {
 	{ .compatible = "allwinner,sun8i-a33-display-engine" },
 	{ .compatible = "allwinner,sun8i-a83t-display-engine" },
 	{ .compatible = "allwinner,sun8i-h3-display-engine" },
+	{ .compatible = "allwinner,sun8i-r40-display-engine" },
 	{ .compatible = "allwinner,sun8i-v3s-display-engine" },
 	{ .compatible = "allwinner,sun9i-a80-display-engine" },
 	{ }
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
index fa4bcd092eaf..061d2e0d9011 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
@@ -220,7 +220,7 @@ static int sun4i_hdmi_get_modes(struct drm_connector *connector)
 	DRM_DEBUG_DRIVER("Monitor is %s monitor\n",
 			 hdmi->hdmi_monitor ? "an HDMI" : "a DVI");
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	cec_s_phys_addr_from_edid(hdmi->cec_adap, edid);
 	ret = drm_add_edid_modes(connector, edid);
 	kfree(edid);
@@ -623,7 +623,7 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master,
 	ret = cec_register_adapter(hdmi->cec_adap, dev);
 	if (ret < 0)
 		goto err_cleanup_connector;
-	drm_mode_connector_attach_encoder(&hdmi->connector, &hdmi->encoder);
+	drm_connector_attach_encoder(&hdmi->connector, &hdmi->encoder);
 
 	return 0;
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_lvds.c b/drivers/gpu/drm/sun4i/sun4i_lvds.c
index be3f14d7746d..af7dcb6da351 100644
--- a/drivers/gpu/drm/sun4i/sun4i_lvds.c
+++ b/drivers/gpu/drm/sun4i/sun4i_lvds.c
@@ -136,7 +136,7 @@ int sun4i_lvds_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 	}
 
 	/* The LVDS encoder can only work with the TCON channel 0 */
-	lvds->encoder.possible_crtcs = BIT(drm_crtc_index(&tcon->crtc->crtc));
+	lvds->encoder.possible_crtcs = drm_crtc_mask(&tcon->crtc->crtc);
 
 	if (tcon->panel) {
 		drm_connector_helper_add(&lvds->connector,
@@ -149,7 +149,7 @@ int sun4i_lvds_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 			goto err_cleanup_connector;
 		}
 
-		drm_mode_connector_attach_encoder(&lvds->connector,
+		drm_connector_attach_encoder(&lvds->connector,
 						  &lvds->encoder);
 
 		ret = drm_panel_attach(tcon->panel, &lvds->connector);
diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c
index f2fa1f210509..bf068da6b12e 100644
--- a/drivers/gpu/drm/sun4i/sun4i_rgb.c
+++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c
@@ -202,7 +202,7 @@ int sun4i_rgb_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 	}
 
 	/* The RGB encoder can only work with the TCON channel 0 */
-	rgb->encoder.possible_crtcs = BIT(drm_crtc_index(&tcon->crtc->crtc));
+	rgb->encoder.possible_crtcs = drm_crtc_mask(&tcon->crtc->crtc);
 
 	if (tcon->panel) {
 		drm_connector_helper_add(&rgb->connector,
@@ -215,7 +215,7 @@ int sun4i_rgb_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 			goto err_cleanup_connector;
 		}
 
-		drm_mode_connector_attach_encoder(&rgb->connector,
+		drm_connector_attach_encoder(&rgb->connector,
 						  &rgb->encoder);
 
 		ret = drm_panel_attach(tcon->panel, &rgb->connector);
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index 8232b39e16ca..3fb084f802e2 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -766,12 +766,14 @@ static int sun4i_tcon_init_regmap(struct device *dev,
  */
 static struct sunxi_engine *
 sun4i_tcon_find_engine_traverse(struct sun4i_drv *drv,
-				struct device_node *node)
+				struct device_node *node,
+				u32 port_id)
 {
 	struct device_node *port, *ep, *remote;
 	struct sunxi_engine *engine = ERR_PTR(-EINVAL);
+	u32 reg = 0;
 
-	port = of_graph_get_port_by_id(node, 0);
+	port = of_graph_get_port_by_id(node, port_id);
 	if (!port)
 		return ERR_PTR(-EINVAL);
 
@@ -801,8 +803,21 @@ sun4i_tcon_find_engine_traverse(struct sun4i_drv *drv,
 		if (remote == engine->node)
 			goto out_put_remote;
 
+	/*
+	 * According to device tree binding input ports have even id
+	 * number and output ports have odd id. Since component with
+	 * more than one input and one output (TCON TOP) exits, correct
+	 * remote input id has to be calculated by subtracting 1 from
+	 * remote output id. If this for some reason can't be done, 0
+	 * is used as input port id.
+	 */
+	of_node_put(port);
+	port = of_graph_get_remote_port(ep);
+	if (!of_property_read_u32(port, "reg", &reg) && reg > 0)
+		reg -= 1;
+
 	/* keep looking through upstream ports */
-	engine = sun4i_tcon_find_engine_traverse(drv, remote);
+	engine = sun4i_tcon_find_engine_traverse(drv, remote, reg);
 
 out_put_remote:
 	of_node_put(remote);
@@ -925,7 +940,7 @@ static struct sunxi_engine *sun4i_tcon_find_engine(struct sun4i_drv *drv,
 
 	/* Fallback to old method by traversing input endpoints */
 	of_node_put(port);
-	return sun4i_tcon_find_engine_traverse(drv, node);
+	return sun4i_tcon_find_engine_traverse(drv, node, 0);
 }
 
 static int sun4i_tcon_bind(struct device *dev, struct device *master,
@@ -1067,23 +1082,25 @@ static int sun4i_tcon_bind(struct device *dev, struct device *master,
 		goto err_free_dotclock;
 	}
 
-	/*
-	 * If we have an LVDS panel connected to the TCON, we should
-	 * just probe the LVDS connector. Otherwise, just probe RGB as
-	 * we used to.
-	 */
-	remote = of_graph_get_remote_node(dev->of_node, 1, 0);
-	if (of_device_is_compatible(remote, "panel-lvds"))
-		if (can_lvds)
-			ret = sun4i_lvds_init(drm, tcon);
+	if (tcon->quirks->has_channel_0) {
+		/*
+		 * If we have an LVDS panel connected to the TCON, we should
+		 * just probe the LVDS connector. Otherwise, just probe RGB as
+		 * we used to.
+		 */
+		remote = of_graph_get_remote_node(dev->of_node, 1, 0);
+		if (of_device_is_compatible(remote, "panel-lvds"))
+			if (can_lvds)
+				ret = sun4i_lvds_init(drm, tcon);
+			else
+				ret = -EINVAL;
 		else
-			ret = -EINVAL;
-	else
-		ret = sun4i_rgb_init(drm, tcon);
-	of_node_put(remote);
+			ret = sun4i_rgb_init(drm, tcon);
+		of_node_put(remote);
 
-	if (ret < 0)
-		goto err_free_dotclock;
+		if (ret < 0)
+			goto err_free_dotclock;
+	}
 
 	if (tcon->quirks->needs_de_be_mux) {
 		/*
@@ -1137,13 +1154,19 @@ static const struct component_ops sun4i_tcon_ops = {
 static int sun4i_tcon_probe(struct platform_device *pdev)
 {
 	struct device_node *node = pdev->dev.of_node;
+	const struct sun4i_tcon_quirks *quirks;
 	struct drm_bridge *bridge;
 	struct drm_panel *panel;
 	int ret;
 
-	ret = drm_of_find_panel_or_bridge(node, 1, 0, &panel, &bridge);
-	if (ret == -EPROBE_DEFER)
-		return ret;
+	quirks = of_device_get_match_data(&pdev->dev);
+
+	/* panels and bridges are present only on TCONs with channel 0 */
+	if (quirks->has_channel_0) {
+		ret = drm_of_find_panel_or_bridge(node, 1, 0, &panel, &bridge);
+		if (ret == -EPROBE_DEFER)
+			return ret;
+	}
 
 	return component_add(&pdev->dev, &sun4i_tcon_ops);
 }
diff --git a/drivers/gpu/drm/sun4i/sun4i_tv.c b/drivers/gpu/drm/sun4i/sun4i_tv.c
index b070d522ed8d..1a838d208211 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tv.c
@@ -623,7 +623,7 @@ static int sun4i_tv_bind(struct device *dev, struct device *master,
 	}
 	tv->connector.interlace_allowed = true;
 
-	drm_mode_connector_attach_encoder(&tv->connector, &tv->encoder);
+	drm_connector_attach_encoder(&tv->connector, &tv->encoder);
 
 	return 0;
 
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
index bfbf761f0c1d..e3b34a345546 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -13,6 +13,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/regmap.h>
 #include <linux/reset.h>
+#include <linux/slab.h>
 
 #include <linux/phy/phy.h>
 
@@ -247,10 +248,8 @@ static u16 sun6i_dsi_crc_compute(u8 const *buffer, size_t len)
 	return crc_ccitt(0xffff, buffer, len);
 }
 
-static u16 sun6i_dsi_crc_repeat_compute(u8 pd, size_t len)
+static u16 sun6i_dsi_crc_repeat(u8 pd, u8 *buffer, size_t len)
 {
-	u8 buffer[len];
-
 	memset(buffer, pd, len);
 
 	return sun6i_dsi_crc_compute(buffer, len);
@@ -274,11 +273,11 @@ static u32 sun6i_dsi_build_blk0_pkt(u8 vc, u16 wc)
 					wc & 0xff, wc >> 8);
 }
 
-static u32 sun6i_dsi_build_blk1_pkt(u16 pd, size_t len)
+static u32 sun6i_dsi_build_blk1_pkt(u16 pd, u8 *buffer, size_t len)
 {
 	u32 val = SUN6I_DSI_BLK_PD(pd);
 
-	return val | SUN6I_DSI_BLK_PF(sun6i_dsi_crc_repeat_compute(pd, len));
+	return val | SUN6I_DSI_BLK_PF(sun6i_dsi_crc_repeat(pd, buffer, len));
 }
 
 static void sun6i_dsi_inst_abort(struct sun6i_dsi *dsi)
@@ -452,6 +451,54 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 	struct mipi_dsi_device *device = dsi->device;
 	unsigned int Bpp = mipi_dsi_pixel_format_to_bpp(device->format) / 8;
 	u16 hbp, hfp, hsa, hblk, vblk;
+	size_t bytes;
+	u8 *buffer;
+
+	/* Do all timing calculations up front to allocate buffer space */
+
+	/*
+	 * A sync period is composed of a blanking packet (4 bytes +
+	 * payload + 2 bytes) and a sync event packet (4 bytes). Its
+	 * minimal size is therefore 10 bytes
+	 */
+#define HSA_PACKET_OVERHEAD	10
+	hsa = max((unsigned int)HSA_PACKET_OVERHEAD,
+		  (mode->hsync_end - mode->hsync_start) * Bpp - HSA_PACKET_OVERHEAD);
+
+	/*
+	 * The backporch is set using a blanking packet (4 bytes +
+	 * payload + 2 bytes). Its minimal size is therefore 6 bytes
+	 */
+#define HBP_PACKET_OVERHEAD	6
+	hbp = max((unsigned int)HBP_PACKET_OVERHEAD,
+		  (mode->hsync_start - mode->hdisplay) * Bpp - HBP_PACKET_OVERHEAD);
+
+	/*
+	 * The frontporch is set using a blanking packet (4 bytes +
+	 * payload + 2 bytes). Its minimal size is therefore 6 bytes
+	 */
+#define HFP_PACKET_OVERHEAD	6
+	hfp = max((unsigned int)HFP_PACKET_OVERHEAD,
+		  (mode->htotal - mode->hsync_end) * Bpp - HFP_PACKET_OVERHEAD);
+
+	/*
+	 * hblk seems to be the line + porches length.
+	 */
+	hblk = mode->htotal * Bpp - hsa;
+
+	/*
+	 * And I'm not entirely sure what vblk is about. The driver in
+	 * Allwinner BSP is using a rather convoluted calculation
+	 * there only for 4 lanes. However, using 0 (the !4 lanes
+	 * case) even with a 4 lanes screen seems to work...
+	 */
+	vblk = 0;
+
+	/* How many bytes do we need to send all payloads? */
+	bytes = max_t(size_t, max(max(hfp, hblk), max(hsa, hbp)), vblk);
+	buffer = kmalloc(bytes, GFP_KERNEL);
+	if (WARN_ON(!buffer))
+		return;
 
 	regmap_write(dsi->regs, SUN6I_DSI_BASIC_CTL_REG, 0);
 
@@ -485,63 +532,37 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 		     SUN6I_DSI_BASIC_SIZE1_VACT(mode->vdisplay) |
 		     SUN6I_DSI_BASIC_SIZE1_VT(mode->vtotal));
 
-	/*
-	 * A sync period is composed of a blanking packet (4 bytes +
-	 * payload + 2 bytes) and a sync event packet (4 bytes). Its
-	 * minimal size is therefore 10 bytes
-	 */
-#define HSA_PACKET_OVERHEAD	10
-	hsa = max((unsigned int)HSA_PACKET_OVERHEAD,
-		  (mode->hsync_end - mode->hsync_start) * Bpp - HSA_PACKET_OVERHEAD);
+	/* sync */
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HSA0_REG,
 		     sun6i_dsi_build_blk0_pkt(device->channel, hsa));
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HSA1_REG,
-		     sun6i_dsi_build_blk1_pkt(0, hsa));
+		     sun6i_dsi_build_blk1_pkt(0, buffer, hsa));
 
-	/*
-	 * The backporch is set using a blanking packet (4 bytes +
-	 * payload + 2 bytes). Its minimal size is therefore 6 bytes
-	 */
-#define HBP_PACKET_OVERHEAD	6
-	hbp = max((unsigned int)HBP_PACKET_OVERHEAD,
-		  (mode->hsync_start - mode->hdisplay) * Bpp - HBP_PACKET_OVERHEAD);
+	/* backporch */
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HBP0_REG,
 		     sun6i_dsi_build_blk0_pkt(device->channel, hbp));
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HBP1_REG,
-		     sun6i_dsi_build_blk1_pkt(0, hbp));
+		     sun6i_dsi_build_blk1_pkt(0, buffer, hbp));
 
-	/*
-	 * The frontporch is set using a blanking packet (4 bytes +
-	 * payload + 2 bytes). Its minimal size is therefore 6 bytes
-	 */
-#define HFP_PACKET_OVERHEAD	6
-	hfp = max((unsigned int)HFP_PACKET_OVERHEAD,
-		  (mode->htotal - mode->hsync_end) * Bpp - HFP_PACKET_OVERHEAD);
+	/* frontporch */
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HFP0_REG,
 		     sun6i_dsi_build_blk0_pkt(device->channel, hfp));
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HFP1_REG,
-		     sun6i_dsi_build_blk1_pkt(0, hfp));
+		     sun6i_dsi_build_blk1_pkt(0, buffer, hfp));
 
-	/*
-	 * hblk seems to be the line + porches length.
-	 */
-	hblk = mode->htotal * Bpp - hsa;
+	/* hblk */
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HBLK0_REG,
 		     sun6i_dsi_build_blk0_pkt(device->channel, hblk));
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HBLK1_REG,
-		     sun6i_dsi_build_blk1_pkt(0, hblk));
+		     sun6i_dsi_build_blk1_pkt(0, buffer, hblk));
 
-	/*
-	 * And I'm not entirely sure what vblk is about. The driver in
-	 * Allwinner BSP is using a rather convoluted calculation
-	 * there only for 4 lanes. However, using 0 (the !4 lanes
-	 * case) even with a 4 lanes screen seems to work...
-	 */
-	vblk = 0;
+	/* vblk */
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_VBLK0_REG,
 		     sun6i_dsi_build_blk0_pkt(device->channel, vblk));
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_VBLK1_REG,
-		     sun6i_dsi_build_blk1_pkt(0, vblk));
+		     sun6i_dsi_build_blk1_pkt(0, buffer, vblk));
+
+	kfree(buffer);
 }
 
 static int sun6i_dsi_start(struct sun6i_dsi *dsi,
@@ -812,8 +833,8 @@ static int sun6i_dsi_attach(struct mipi_dsi_host *host,
 
 	dsi->device = device;
 	dsi->panel = of_drm_find_panel(device->dev.of_node);
-	if (!dsi->panel)
-		return -EINVAL;
+	if (IS_ERR(dsi->panel))
+		return PTR_ERR(dsi->panel);
 
 	dev_info(host->dev, "Attached device %s\n", device->name);
 
@@ -920,7 +941,7 @@ static int sun6i_dsi_bind(struct device *dev, struct device *master,
 		goto err_cleanup_connector;
 	}
 
-	drm_mode_connector_attach_encoder(&dsi->connector, &dsi->encoder);
+	drm_connector_attach_encoder(&dsi->connector, &dsi->encoder);
 	drm_panel_attach(dsi->panel, &dsi->connector);
 
 	return 0;
@@ -1040,7 +1061,7 @@ static int sun6i_dsi_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static int sun6i_dsi_runtime_resume(struct device *dev)
+static int __maybe_unused sun6i_dsi_runtime_resume(struct device *dev)
 {
 	struct sun6i_dsi *dsi = dev_get_drvdata(dev);
 
@@ -1069,7 +1090,7 @@ static int sun6i_dsi_runtime_resume(struct device *dev)
 	return 0;
 }
 
-static int sun6i_dsi_runtime_suspend(struct device *dev)
+static int __maybe_unused sun6i_dsi_runtime_suspend(struct device *dev)
 {
 	struct sun6i_dsi *dsi = dev_get_drvdata(dev);
 
diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
index 9f40a44b456b..31875b636434 100644
--- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
+++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
@@ -12,6 +12,7 @@
 #include <drm/drm_crtc_helper.h>
 
 #include "sun8i_dw_hdmi.h"
+#include "sun8i_tcon_top.h"
 
 static void sun8i_dw_hdmi_encoder_mode_set(struct drm_encoder *encoder,
 					   struct drm_display_mode *mode,
@@ -41,6 +42,44 @@ sun8i_dw_hdmi_mode_valid(struct drm_connector *connector,
 	return MODE_OK;
 }
 
+static bool sun8i_dw_hdmi_node_is_tcon_top(struct device_node *node)
+{
+	return IS_ENABLED(CONFIG_DRM_SUN8I_TCON_TOP) &&
+		!!of_match_node(sun8i_tcon_top_of_table, node);
+}
+
+static u32 sun8i_dw_hdmi_find_possible_crtcs(struct drm_device *drm,
+					     struct device_node *node)
+{
+	struct device_node *port, *ep, *remote, *remote_port;
+	u32 crtcs = 0;
+
+	remote = of_graph_get_remote_node(node, 0, -1);
+	if (!remote)
+		return 0;
+
+	if (sun8i_dw_hdmi_node_is_tcon_top(remote)) {
+		port = of_graph_get_port_by_id(remote, 4);
+		if (!port)
+			goto crtcs_exit;
+
+		for_each_child_of_node(port, ep) {
+			remote_port = of_graph_get_remote_port(ep);
+			if (remote_port) {
+				crtcs |= drm_of_crtc_port_mask(drm, remote_port);
+				of_node_put(remote_port);
+			}
+		}
+	} else {
+		crtcs = drm_of_find_possible_crtcs(drm, node);
+	}
+
+crtcs_exit:
+	of_node_put(remote);
+
+	return crtcs;
+}
+
 static int sun8i_dw_hdmi_bind(struct device *dev, struct device *master,
 			      void *data)
 {
@@ -63,7 +102,8 @@ static int sun8i_dw_hdmi_bind(struct device *dev, struct device *master,
 	hdmi->dev = &pdev->dev;
 	encoder = &hdmi->encoder;
 
-	encoder->possible_crtcs = drm_of_find_possible_crtcs(drm, dev->of_node);
+	encoder->possible_crtcs =
+		sun8i_dw_hdmi_find_possible_crtcs(drm, dev->of_node);
 	/*
 	 * If we failed to find the CRTC(s) which this encoder is
 	 * supposed to be connected to, it's because the CRTC has
@@ -181,7 +221,7 @@ static const struct of_device_id sun8i_dw_hdmi_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, sun8i_dw_hdmi_dt_ids);
 
-struct platform_driver sun8i_dw_hdmi_pltfm_driver = {
+static struct platform_driver sun8i_dw_hdmi_pltfm_driver = {
 	.probe  = sun8i_dw_hdmi_probe,
 	.remove = sun8i_dw_hdmi_remove,
 	.driver = {
diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h
index 79154f0f674a..aadbe0a10b0c 100644
--- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h
+++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h
@@ -98,7 +98,8 @@
 #define SUN8I_HDMI_PHY_PLL_CFG1_LDO2_EN		BIT(29)
 #define SUN8I_HDMI_PHY_PLL_CFG1_LDO1_EN		BIT(28)
 #define SUN8I_HDMI_PHY_PLL_CFG1_HV_IS_33	BIT(27)
-#define SUN8I_HDMI_PHY_PLL_CFG1_CKIN_SEL	BIT(26)
+#define SUN8I_HDMI_PHY_PLL_CFG1_CKIN_SEL_MSK	BIT(26)
+#define SUN8I_HDMI_PHY_PLL_CFG1_CKIN_SEL_SHIFT	26
 #define SUN8I_HDMI_PHY_PLL_CFG1_PLLEN		BIT(25)
 #define SUN8I_HDMI_PHY_PLL_CFG1_LDO_VSET(x)	((x) << 22)
 #define SUN8I_HDMI_PHY_PLL_CFG1_UNKNOWN(x)	((x) << 20)
@@ -147,6 +148,7 @@ struct sun8i_hdmi_phy;
 
 struct sun8i_hdmi_phy_variant {
 	bool has_phy_clk;
+	bool has_second_pll;
 	void (*phy_init)(struct sun8i_hdmi_phy *phy);
 	void (*phy_disable)(struct dw_hdmi *hdmi,
 			    struct sun8i_hdmi_phy *phy);
@@ -160,6 +162,7 @@ struct sun8i_hdmi_phy {
 	struct clk			*clk_mod;
 	struct clk			*clk_phy;
 	struct clk			*clk_pll0;
+	struct clk			*clk_pll1;
 	unsigned int			rcal;
 	struct regmap			*regs;
 	struct reset_control		*rst_phy;
@@ -188,6 +191,7 @@ void sun8i_hdmi_phy_remove(struct sun8i_dw_hdmi *hdmi);
 void sun8i_hdmi_phy_init(struct sun8i_hdmi_phy *phy);
 const struct dw_hdmi_phy_ops *sun8i_hdmi_phy_get_ops(void);
 
-int sun8i_phy_clk_create(struct sun8i_hdmi_phy *phy, struct device *dev);
+int sun8i_phy_clk_create(struct sun8i_hdmi_phy *phy, struct device *dev,
+			 bool second_parent);
 
 #endif /* _SUN8I_DW_HDMI_H_ */
diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
index 5a52fc489a9d..82502b351aec 100644
--- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
+++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
@@ -183,7 +183,13 @@ static int sun8i_hdmi_phy_config_h3(struct dw_hdmi *hdmi,
 	regmap_update_bits(phy->regs, SUN8I_HDMI_PHY_ANA_CFG1_REG,
 			   SUN8I_HDMI_PHY_ANA_CFG1_TXEN_MASK, 0);
 
-	regmap_write(phy->regs, SUN8I_HDMI_PHY_PLL_CFG1_REG, pll_cfg1_init);
+	/*
+	 * NOTE: We have to be careful not to overwrite PHY parent
+	 * clock selection bit and clock divider.
+	 */
+	regmap_update_bits(phy->regs, SUN8I_HDMI_PHY_PLL_CFG1_REG,
+			   (u32)~SUN8I_HDMI_PHY_PLL_CFG1_CKIN_SEL_MSK,
+			   pll_cfg1_init);
 	regmap_update_bits(phy->regs, SUN8I_HDMI_PHY_PLL_CFG2_REG,
 			   (u32)~SUN8I_HDMI_PHY_PLL_CFG2_PREDIV_MSK,
 			   pll_cfg2_init);
@@ -352,6 +358,10 @@ static void sun8i_hdmi_phy_init_h3(struct sun8i_hdmi_phy *phy)
 			   SUN8I_HDMI_PHY_ANA_CFG3_SCLEN |
 			   SUN8I_HDMI_PHY_ANA_CFG3_SDAEN);
 
+	/* reset PHY PLL clock parent */
+	regmap_update_bits(phy->regs, SUN8I_HDMI_PHY_PLL_CFG1_REG,
+			   SUN8I_HDMI_PHY_PLL_CFG1_CKIN_SEL_MSK, 0);
+
 	/* set HW control of CEC pins */
 	regmap_write(phy->regs, SUN8I_HDMI_PHY_CEC_REG, 0);
 
@@ -386,6 +396,14 @@ static struct regmap_config sun8i_hdmi_phy_regmap_config = {
 	.name		= "phy"
 };
 
+static const struct sun8i_hdmi_phy_variant sun50i_a64_hdmi_phy = {
+	.has_phy_clk = true,
+	.has_second_pll = true,
+	.phy_init = &sun8i_hdmi_phy_init_h3,
+	.phy_disable = &sun8i_hdmi_phy_disable_h3,
+	.phy_config = &sun8i_hdmi_phy_config_h3,
+};
+
 static const struct sun8i_hdmi_phy_variant sun8i_a83t_hdmi_phy = {
 	.phy_init = &sun8i_hdmi_phy_init_a83t,
 	.phy_disable = &sun8i_hdmi_phy_disable_a83t,
@@ -401,6 +419,10 @@ static const struct sun8i_hdmi_phy_variant sun8i_h3_hdmi_phy = {
 
 static const struct of_device_id sun8i_hdmi_phy_of_table[] = {
 	{
+		.compatible = "allwinner,sun50i-a64-hdmi-phy",
+		.data = &sun50i_a64_hdmi_phy,
+	},
+	{
 		.compatible = "allwinner,sun8i-a83t-hdmi-phy",
 		.data = &sun8i_a83t_hdmi_phy,
 	},
@@ -472,18 +494,30 @@ int sun8i_hdmi_phy_probe(struct sun8i_dw_hdmi *hdmi, struct device_node *node)
 			goto err_put_clk_mod;
 		}
 
-		ret = sun8i_phy_clk_create(phy, dev);
+		if (phy->variant->has_second_pll) {
+			phy->clk_pll1 = of_clk_get_by_name(node, "pll-1");
+			if (IS_ERR(phy->clk_pll1)) {
+				dev_err(dev, "Could not get pll-1 clock\n");
+				ret = PTR_ERR(phy->clk_pll1);
+				goto err_put_clk_pll0;
+			}
+		}
+
+		ret = sun8i_phy_clk_create(phy, dev,
+					   phy->variant->has_second_pll);
 		if (ret) {
 			dev_err(dev, "Couldn't create the PHY clock\n");
-			goto err_put_clk_pll0;
+			goto err_put_clk_pll1;
 		}
+
+		clk_prepare_enable(phy->clk_phy);
 	}
 
 	phy->rst_phy = of_reset_control_get_shared(node, "phy");
 	if (IS_ERR(phy->rst_phy)) {
 		dev_err(dev, "Could not get phy reset control\n");
 		ret = PTR_ERR(phy->rst_phy);
-		goto err_put_clk_pll0;
+		goto err_disable_clk_phy;
 	}
 
 	ret = reset_control_deassert(phy->rst_phy);
@@ -514,9 +548,12 @@ err_deassert_rst_phy:
 	reset_control_assert(phy->rst_phy);
 err_put_rst_phy:
 	reset_control_put(phy->rst_phy);
+err_disable_clk_phy:
+	clk_disable_unprepare(phy->clk_phy);
+err_put_clk_pll1:
+	clk_put(phy->clk_pll1);
 err_put_clk_pll0:
-	if (phy->variant->has_phy_clk)
-		clk_put(phy->clk_pll0);
+	clk_put(phy->clk_pll0);
 err_put_clk_mod:
 	clk_put(phy->clk_mod);
 err_put_clk_bus:
@@ -531,13 +568,14 @@ void sun8i_hdmi_phy_remove(struct sun8i_dw_hdmi *hdmi)
 
 	clk_disable_unprepare(phy->clk_mod);
 	clk_disable_unprepare(phy->clk_bus);
+	clk_disable_unprepare(phy->clk_phy);
 
 	reset_control_assert(phy->rst_phy);
 
 	reset_control_put(phy->rst_phy);
 
-	if (phy->variant->has_phy_clk)
-		clk_put(phy->clk_pll0);
+	clk_put(phy->clk_pll0);
+	clk_put(phy->clk_pll1);
 	clk_put(phy->clk_mod);
 	clk_put(phy->clk_bus);
 }
diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy_clk.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy_clk.c
index faea449812f8..a4d31fe3abff 100644
--- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy_clk.c
+++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy_clk.c
@@ -22,35 +22,45 @@ static int sun8i_phy_clk_determine_rate(struct clk_hw *hw,
 {
 	unsigned long rate = req->rate;
 	unsigned long best_rate = 0;
+	struct clk_hw *best_parent = NULL;
 	struct clk_hw *parent;
 	int best_div = 1;
-	int i;
+	int i, p;
 
-	parent = clk_hw_get_parent(hw);
-
-	for (i = 1; i <= 16; i++) {
-		unsigned long ideal = rate * i;
-		unsigned long rounded;
-
-		rounded = clk_hw_round_rate(parent, ideal);
+	for (p = 0; p < clk_hw_get_num_parents(hw); p++) {
+		parent = clk_hw_get_parent_by_index(hw, p);
+		if (!parent)
+			continue;
 
-		if (rounded == ideal) {
-			best_rate = rounded;
-			best_div = i;
-			break;
+		for (i = 1; i <= 16; i++) {
+			unsigned long ideal = rate * i;
+			unsigned long rounded;
+
+			rounded = clk_hw_round_rate(parent, ideal);
+
+			if (rounded == ideal) {
+				best_rate = rounded;
+				best_div = i;
+				best_parent = parent;
+				break;
+			}
+
+			if (!best_rate ||
+			    abs(rate - rounded / i) <
+			    abs(rate - best_rate / best_div)) {
+				best_rate = rounded;
+				best_div = i;
+				best_parent = parent;
+			}
 		}
 
-		if (!best_rate ||
-		    abs(rate - rounded / i) <
-		    abs(rate - best_rate / best_div)) {
-			best_rate = rounded;
-			best_div = i;
-		}
+		if (best_rate / best_div == rate)
+			break;
 	}
 
 	req->rate = best_rate / best_div;
 	req->best_parent_rate = best_rate;
-	req->best_parent_hw = parent;
+	req->best_parent_hw = best_parent;
 
 	return 0;
 }
@@ -95,22 +105,58 @@ static int sun8i_phy_clk_set_rate(struct clk_hw *hw, unsigned long rate,
 	return 0;
 }
 
+static u8 sun8i_phy_clk_get_parent(struct clk_hw *hw)
+{
+	struct sun8i_phy_clk *priv = hw_to_phy_clk(hw);
+	u32 reg;
+
+	regmap_read(priv->phy->regs, SUN8I_HDMI_PHY_PLL_CFG1_REG, &reg);
+	reg = (reg & SUN8I_HDMI_PHY_PLL_CFG1_CKIN_SEL_MSK) >>
+	      SUN8I_HDMI_PHY_PLL_CFG1_CKIN_SEL_SHIFT;
+
+	return reg;
+}
+
+static int sun8i_phy_clk_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct sun8i_phy_clk *priv = hw_to_phy_clk(hw);
+
+	if (index > 1)
+		return -EINVAL;
+
+	regmap_update_bits(priv->phy->regs, SUN8I_HDMI_PHY_PLL_CFG1_REG,
+			   SUN8I_HDMI_PHY_PLL_CFG1_CKIN_SEL_MSK,
+			   index << SUN8I_HDMI_PHY_PLL_CFG1_CKIN_SEL_SHIFT);
+
+	return 0;
+}
+
 static const struct clk_ops sun8i_phy_clk_ops = {
 	.determine_rate	= sun8i_phy_clk_determine_rate,
 	.recalc_rate	= sun8i_phy_clk_recalc_rate,
 	.set_rate	= sun8i_phy_clk_set_rate,
+
+	.get_parent	= sun8i_phy_clk_get_parent,
+	.set_parent	= sun8i_phy_clk_set_parent,
 };
 
-int sun8i_phy_clk_create(struct sun8i_hdmi_phy *phy, struct device *dev)
+int sun8i_phy_clk_create(struct sun8i_hdmi_phy *phy, struct device *dev,
+			 bool second_parent)
 {
 	struct clk_init_data init;
 	struct sun8i_phy_clk *priv;
-	const char *parents[1];
+	const char *parents[2];
 
 	parents[0] = __clk_get_name(phy->clk_pll0);
 	if (!parents[0])
 		return -ENODEV;
 
+	if (second_parent) {
+		parents[1] = __clk_get_name(phy->clk_pll1);
+		if (!parents[1])
+			return -ENODEV;
+	}
+
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
@@ -118,7 +164,7 @@ int sun8i_phy_clk_create(struct sun8i_hdmi_phy *phy, struct device *dev)
 	init.name = "hdmi-phy-clk";
 	init.ops = &sun8i_phy_clk_ops;
 	init.parent_names = parents;
-	init.num_parents = 1;
+	init.num_parents = second_parent ? 2 : 1;
 	init.flags = CLK_SET_RATE_PARENT;
 
 	priv->phy = phy;
diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c
index 126899d6f0d3..fc3713608f78 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c
@@ -21,8 +21,9 @@
 
 #include <linux/component.h>
 #include <linux/dma-mapping.h>
-#include <linux/reset.h>
 #include <linux/of_device.h>
+#include <linux/of_graph.h>
+#include <linux/reset.h>
 
 #include "sun4i_drv.h"
 #include "sun8i_mixer.h"
@@ -322,6 +323,42 @@ static struct regmap_config sun8i_mixer_regmap_config = {
 	.max_register	= 0xbfffc, /* guessed */
 };
 
+static int sun8i_mixer_of_get_id(struct device_node *node)
+{
+	struct device_node *port, *ep;
+	int ret = -EINVAL;
+
+	/* output is port 1 */
+	port = of_graph_get_port_by_id(node, 1);
+	if (!port)
+		return -EINVAL;
+
+	/* try to find downstream endpoint */
+	for_each_available_child_of_node(port, ep) {
+		struct device_node *remote;
+		u32 reg;
+
+		remote = of_graph_get_remote_endpoint(ep);
+		if (!remote)
+			continue;
+
+		ret = of_property_read_u32(remote, "reg", &reg);
+		if (!ret) {
+			of_node_put(remote);
+			of_node_put(ep);
+			of_node_put(port);
+
+			return reg;
+		}
+
+		of_node_put(remote);
+	}
+
+	of_node_put(port);
+
+	return ret;
+}
+
 static int sun8i_mixer_bind(struct device *dev, struct device *master,
 			      void *data)
 {
@@ -353,8 +390,16 @@ static int sun8i_mixer_bind(struct device *dev, struct device *master,
 	dev_set_drvdata(dev, mixer);
 	mixer->engine.ops = &sun8i_engine_ops;
 	mixer->engine.node = dev->of_node;
-	/* The ID of the mixer currently doesn't matter */
-	mixer->engine.id = -1;
+
+	/*
+	 * While this function can fail, we shouldn't do anything
+	 * if this happens. Some early DE2 DT entries don't provide
+	 * mixer id but work nevertheless because matching between
+	 * TCON and mixer is done by comparing node pointers (old
+	 * way) instead comparing ids. If this function fails and
+	 * id is needed, it will fail during id matching anyway.
+	 */
+	mixer->engine.id = sun8i_mixer_of_get_id(dev->of_node);
 
 	mixer->cfg = of_device_get_match_data(dev);
 	if (!mixer->cfg)
@@ -432,14 +477,14 @@ static int sun8i_mixer_bind(struct device *dev, struct device *master,
 	regmap_write(mixer->engine.regs, SUN8I_MIXER_BLEND_ATTR_FCOLOR(0),
 		     SUN8I_MIXER_BLEND_COLOR_BLACK);
 
-	/* Fixed zpos for now */
-	regmap_write(mixer->engine.regs, SUN8I_MIXER_BLEND_ROUTE, 0x43210);
-
 	plane_cnt = mixer->cfg->vi_num + mixer->cfg->ui_num;
 	for (i = 0; i < plane_cnt; i++)
 		regmap_write(mixer->engine.regs, SUN8I_MIXER_BLEND_MODE(i),
 			     SUN8I_MIXER_BLEND_MODE_DEF);
 
+	regmap_update_bits(mixer->engine.regs, SUN8I_MIXER_BLEND_PIPE_CTL,
+			   SUN8I_MIXER_BLEND_PIPE_CTL_EN_MSK, 0);
+
 	return 0;
 
 err_disable_bus_clk:
@@ -500,6 +545,22 @@ static const struct sun8i_mixer_cfg sun8i_h3_mixer0_cfg = {
 	.vi_num		= 1,
 };
 
+static const struct sun8i_mixer_cfg sun8i_r40_mixer0_cfg = {
+	.ccsc		= 0,
+	.mod_rate	= 297000000,
+	.scaler_mask	= 0xf,
+	.ui_num		= 3,
+	.vi_num		= 1,
+};
+
+static const struct sun8i_mixer_cfg sun8i_r40_mixer1_cfg = {
+	.ccsc		= 1,
+	.mod_rate	= 297000000,
+	.scaler_mask	= 0x3,
+	.ui_num		= 1,
+	.vi_num		= 1,
+};
+
 static const struct sun8i_mixer_cfg sun8i_v3s_mixer_cfg = {
 	.vi_num = 2,
 	.ui_num = 1,
@@ -522,6 +583,14 @@ static const struct of_device_id sun8i_mixer_of_table[] = {
 		.data = &sun8i_h3_mixer0_cfg,
 	},
 	{
+		.compatible = "allwinner,sun8i-r40-de2-mixer-0",
+		.data = &sun8i_r40_mixer0_cfg,
+	},
+	{
+		.compatible = "allwinner,sun8i-r40-de2-mixer-1",
+		.data = &sun8i_r40_mixer1_cfg,
+	},
+	{
 		.compatible = "allwinner,sun8i-v3s-de2-mixer",
 		.data = &sun8i_v3s_mixer_cfg,
 	},
diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.h b/drivers/gpu/drm/sun4i/sun8i_mixer.h
index f34e70c42adf..406c42e752d7 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.h
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.h
@@ -44,6 +44,7 @@
 #define SUN8I_MIXER_BLEND_CK_MIN(x)		(0x10e0 + 0x04 * (x))
 #define SUN8I_MIXER_BLEND_OUTCTL		0x10fc
 
+#define SUN8I_MIXER_BLEND_PIPE_CTL_EN_MSK	GENMASK(12, 8)
 #define SUN8I_MIXER_BLEND_PIPE_CTL_EN(pipe)	BIT(8 + pipe)
 #define SUN8I_MIXER_BLEND_PIPE_CTL_FC_EN(pipe)	BIT(pipe)
 /* colors are always in AARRGGBB format */
@@ -51,6 +52,9 @@
 /* The following numbers are some still unknown magic numbers */
 #define SUN8I_MIXER_BLEND_MODE_DEF		0x03010301
 
+#define SUN8I_MIXER_BLEND_ROUTE_PIPE_MSK(n)	(0xf << ((n) << 2))
+#define SUN8I_MIXER_BLEND_ROUTE_PIPE_SHIFT(n)	((n) << 2)
+
 #define SUN8I_MIXER_BLEND_OUTCTL_INTERLACED	BIT(1)
 
 #define SUN8I_MIXER_FBFMT_ARGB8888	0
diff --git a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
new file mode 100644
index 000000000000..55fe398d8290
--- /dev/null
+++ b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
@@ -0,0 +1,274 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (c) 2018 Jernej Skrabec <jernej.skrabec@siol.net> */
+
+#include <drm/drmP.h>
+
+#include <dt-bindings/clock/sun8i-tcon-top.h>
+
+#include <linux/bitfield.h>
+#include <linux/component.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/of_graph.h>
+#include <linux/platform_device.h>
+
+#include "sun8i_tcon_top.h"
+
+static bool sun8i_tcon_top_node_is_tcon_top(struct device_node *node)
+{
+	return !!of_match_node(sun8i_tcon_top_of_table, node);
+}
+
+int sun8i_tcon_top_set_hdmi_src(struct device *dev, int tcon)
+{
+	struct sun8i_tcon_top *tcon_top = dev_get_drvdata(dev);
+	unsigned long flags;
+	u32 val;
+
+	if (!sun8i_tcon_top_node_is_tcon_top(dev->of_node)) {
+		dev_err(dev, "Device is not TCON TOP!\n");
+		return -EINVAL;
+	}
+
+	if (tcon < 2 || tcon > 3) {
+		dev_err(dev, "TCON index must be 2 or 3!\n");
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&tcon_top->reg_lock, flags);
+
+	val = readl(tcon_top->regs + TCON_TOP_GATE_SRC_REG);
+	val &= ~TCON_TOP_HDMI_SRC_MSK;
+	val |= FIELD_PREP(TCON_TOP_HDMI_SRC_MSK, tcon - 1);
+	writel(val, tcon_top->regs + TCON_TOP_GATE_SRC_REG);
+
+	spin_unlock_irqrestore(&tcon_top->reg_lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL(sun8i_tcon_top_set_hdmi_src);
+
+int sun8i_tcon_top_de_config(struct device *dev, int mixer, int tcon)
+{
+	struct sun8i_tcon_top *tcon_top = dev_get_drvdata(dev);
+	unsigned long flags;
+	u32 reg;
+
+	if (!sun8i_tcon_top_node_is_tcon_top(dev->of_node)) {
+		dev_err(dev, "Device is not TCON TOP!\n");
+		return -EINVAL;
+	}
+
+	if (mixer > 1) {
+		dev_err(dev, "Mixer index is too high!\n");
+		return -EINVAL;
+	}
+
+	if (tcon > 3) {
+		dev_err(dev, "TCON index is too high!\n");
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&tcon_top->reg_lock, flags);
+
+	reg = readl(tcon_top->regs + TCON_TOP_PORT_SEL_REG);
+	if (mixer == 0) {
+		reg &= ~TCON_TOP_PORT_DE0_MSK;
+		reg |= FIELD_PREP(TCON_TOP_PORT_DE0_MSK, tcon);
+	} else {
+		reg &= ~TCON_TOP_PORT_DE1_MSK;
+		reg |= FIELD_PREP(TCON_TOP_PORT_DE1_MSK, tcon);
+	}
+	writel(reg, tcon_top->regs + TCON_TOP_PORT_SEL_REG);
+
+	spin_unlock_irqrestore(&tcon_top->reg_lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL(sun8i_tcon_top_de_config);
+
+
+static struct clk_hw *sun8i_tcon_top_register_gate(struct device *dev,
+						   const char *parent,
+						   void __iomem *regs,
+						   spinlock_t *lock,
+						   u8 bit, int name_index)
+{
+	const char *clk_name, *parent_name;
+	int ret, index;
+
+	index = of_property_match_string(dev->of_node, "clock-names", parent);
+	if (index < 0)
+		return ERR_PTR(index);
+
+	parent_name = of_clk_get_parent_name(dev->of_node, index);
+
+	ret = of_property_read_string_index(dev->of_node,
+					    "clock-output-names", name_index,
+					    &clk_name);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return clk_hw_register_gate(dev, clk_name, parent_name,
+				    CLK_SET_RATE_PARENT,
+				    regs + TCON_TOP_GATE_SRC_REG,
+				    bit, 0, lock);
+};
+
+static int sun8i_tcon_top_bind(struct device *dev, struct device *master,
+			       void *data)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct clk_hw_onecell_data *clk_data;
+	struct sun8i_tcon_top *tcon_top;
+	struct resource *res;
+	void __iomem *regs;
+	int ret, i;
+
+	tcon_top = devm_kzalloc(dev, sizeof(*tcon_top), GFP_KERNEL);
+	if (!tcon_top)
+		return -ENOMEM;
+
+	clk_data = devm_kzalloc(dev, sizeof(*clk_data) +
+				sizeof(*clk_data->hws) * CLK_NUM,
+				GFP_KERNEL);
+	if (!clk_data)
+		return -ENOMEM;
+	tcon_top->clk_data = clk_data;
+
+	spin_lock_init(&tcon_top->reg_lock);
+
+	tcon_top->rst = devm_reset_control_get(dev, NULL);
+	if (IS_ERR(tcon_top->rst)) {
+		dev_err(dev, "Couldn't get our reset line\n");
+		return PTR_ERR(tcon_top->rst);
+	}
+
+	tcon_top->bus = devm_clk_get(dev, "bus");
+	if (IS_ERR(tcon_top->bus)) {
+		dev_err(dev, "Couldn't get the bus clock\n");
+		return PTR_ERR(tcon_top->bus);
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	regs = devm_ioremap_resource(dev, res);
+	tcon_top->regs = regs;
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
+
+	ret = reset_control_deassert(tcon_top->rst);
+	if (ret) {
+		dev_err(dev, "Could not deassert ctrl reset control\n");
+		return ret;
+	}
+
+	ret = clk_prepare_enable(tcon_top->bus);
+	if (ret) {
+		dev_err(dev, "Could not enable bus clock\n");
+		goto err_assert_reset;
+	}
+
+	/*
+	 * TCON TOP has two muxes, which select parent clock for each TCON TV
+	 * channel clock. Parent could be either TCON TV or TVE clock. For now
+	 * we leave this fixed to TCON TV, since TVE driver for R40 is not yet
+	 * implemented. Once it is, graph needs to be traversed to determine
+	 * if TVE is active on each TCON TV. If it is, mux should be switched
+	 * to TVE clock parent.
+	 */
+	clk_data->hws[CLK_TCON_TOP_TV0] =
+		sun8i_tcon_top_register_gate(dev, "tcon-tv0", regs,
+					     &tcon_top->reg_lock,
+					     TCON_TOP_TCON_TV0_GATE, 0);
+
+	clk_data->hws[CLK_TCON_TOP_TV1] =
+		sun8i_tcon_top_register_gate(dev, "tcon-tv1", regs,
+					     &tcon_top->reg_lock,
+					     TCON_TOP_TCON_TV1_GATE, 1);
+
+	clk_data->hws[CLK_TCON_TOP_DSI] =
+		sun8i_tcon_top_register_gate(dev, "dsi", regs,
+					     &tcon_top->reg_lock,
+					     TCON_TOP_TCON_DSI_GATE, 2);
+
+	for (i = 0; i < CLK_NUM; i++)
+		if (IS_ERR(clk_data->hws[i])) {
+			ret = PTR_ERR(clk_data->hws[i]);
+			goto err_unregister_gates;
+		}
+
+	clk_data->num = CLK_NUM;
+
+	ret = of_clk_add_hw_provider(dev->of_node, of_clk_hw_onecell_get,
+				     clk_data);
+	if (ret)
+		goto err_unregister_gates;
+
+	dev_set_drvdata(dev, tcon_top);
+
+	return 0;
+
+err_unregister_gates:
+	for (i = 0; i < CLK_NUM; i++)
+		if (clk_data->hws[i])
+			clk_hw_unregister_gate(clk_data->hws[i]);
+	clk_disable_unprepare(tcon_top->bus);
+err_assert_reset:
+	reset_control_assert(tcon_top->rst);
+
+	return ret;
+}
+
+static void sun8i_tcon_top_unbind(struct device *dev, struct device *master,
+				  void *data)
+{
+	struct sun8i_tcon_top *tcon_top = dev_get_drvdata(dev);
+	struct clk_hw_onecell_data *clk_data = tcon_top->clk_data;
+	int i;
+
+	of_clk_del_provider(dev->of_node);
+	for (i = 0; i < CLK_NUM; i++)
+		clk_hw_unregister_gate(clk_data->hws[i]);
+
+	clk_disable_unprepare(tcon_top->bus);
+	reset_control_assert(tcon_top->rst);
+}
+
+static const struct component_ops sun8i_tcon_top_ops = {
+	.bind	= sun8i_tcon_top_bind,
+	.unbind	= sun8i_tcon_top_unbind,
+};
+
+static int sun8i_tcon_top_probe(struct platform_device *pdev)
+{
+	return component_add(&pdev->dev, &sun8i_tcon_top_ops);
+}
+
+static int sun8i_tcon_top_remove(struct platform_device *pdev)
+{
+	component_del(&pdev->dev, &sun8i_tcon_top_ops);
+
+	return 0;
+}
+
+/* sun4i_drv uses this list to check if a device node is a TCON TOP */
+const struct of_device_id sun8i_tcon_top_of_table[] = {
+	{ .compatible = "allwinner,sun8i-r40-tcon-top" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, sun8i_tcon_top_of_table);
+EXPORT_SYMBOL(sun8i_tcon_top_of_table);
+
+static struct platform_driver sun8i_tcon_top_platform_driver = {
+	.probe		= sun8i_tcon_top_probe,
+	.remove		= sun8i_tcon_top_remove,
+	.driver		= {
+		.name		= "sun8i-tcon-top",
+		.of_match_table	= sun8i_tcon_top_of_table,
+	},
+};
+module_platform_driver(sun8i_tcon_top_platform_driver);
+
+MODULE_AUTHOR("Jernej Skrabec <jernej.skrabec@siol.net>");
+MODULE_DESCRIPTION("Allwinner R40 TCON TOP driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/sun4i/sun8i_tcon_top.h b/drivers/gpu/drm/sun4i/sun8i_tcon_top.h
new file mode 100644
index 000000000000..0390584a330e
--- /dev/null
+++ b/drivers/gpu/drm/sun4i/sun8i_tcon_top.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (c) 2018 Jernej Skrabec <jernej.skrabec@siol.net> */
+
+#ifndef _SUN8I_TCON_TOP_H_
+#define _SUN8I_TCON_TOP_H_
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/reset.h>
+#include <linux/spinlock.h>
+
+#define TCON_TOP_TCON_TV_SETUP_REG	0x00
+
+#define TCON_TOP_PORT_SEL_REG		0x1C
+#define TCON_TOP_PORT_DE0_MSK			GENMASK(1, 0)
+#define TCON_TOP_PORT_DE1_MSK			GENMASK(5, 4)
+
+#define TCON_TOP_GATE_SRC_REG		0x20
+#define TCON_TOP_HDMI_SRC_MSK			GENMASK(29, 28)
+#define TCON_TOP_TCON_TV1_GATE			24
+#define TCON_TOP_TCON_TV0_GATE			20
+#define TCON_TOP_TCON_DSI_GATE			16
+
+#define CLK_NUM					3
+
+struct sun8i_tcon_top {
+	struct clk			*bus;
+	struct clk_hw_onecell_data	*clk_data;
+	void __iomem			*regs;
+	struct reset_control		*rst;
+
+	/*
+	 * spinlock is used to synchronize access to same
+	 * register where multiple clock gates can be set.
+	 */
+	spinlock_t			reg_lock;
+};
+
+extern const struct of_device_id sun8i_tcon_top_of_table[];
+
+int sun8i_tcon_top_set_hdmi_src(struct device *dev, int tcon);
+int sun8i_tcon_top_de_config(struct device *dev, int mixer, int tcon);
+
+#endif /* _SUN8I_TCON_TOP_H_ */
diff --git a/drivers/gpu/drm/sun4i/sun8i_ui_layer.c b/drivers/gpu/drm/sun4i/sun8i_ui_layer.c
index 9a540330cb79..28c15c6ef1ef 100644
--- a/drivers/gpu/drm/sun4i/sun8i_ui_layer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_ui_layer.c
@@ -27,7 +27,8 @@
 #include "sun8i_ui_scaler.h"
 
 static void sun8i_ui_layer_enable(struct sun8i_mixer *mixer, int channel,
-				  int overlay, bool enable)
+				  int overlay, bool enable, unsigned int zpos,
+				  unsigned int old_zpos)
 {
 	u32 val;
 
@@ -43,18 +44,36 @@ static void sun8i_ui_layer_enable(struct sun8i_mixer *mixer, int channel,
 			   SUN8I_MIXER_CHAN_UI_LAYER_ATTR(channel, overlay),
 			   SUN8I_MIXER_CHAN_UI_LAYER_ATTR_EN, val);
 
-	if (enable)
-		val = SUN8I_MIXER_BLEND_PIPE_CTL_EN(channel);
-	else
-		val = 0;
+	if (!enable || zpos != old_zpos) {
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_PIPE_CTL,
+				   SUN8I_MIXER_BLEND_PIPE_CTL_EN(old_zpos),
+				   0);
 
-	regmap_update_bits(mixer->engine.regs,
-			   SUN8I_MIXER_BLEND_PIPE_CTL,
-			   SUN8I_MIXER_BLEND_PIPE_CTL_EN(channel), val);
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_ROUTE,
+				   SUN8I_MIXER_BLEND_ROUTE_PIPE_MSK(old_zpos),
+				   0);
+	}
+
+	if (enable) {
+		val = SUN8I_MIXER_BLEND_PIPE_CTL_EN(zpos);
+
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_PIPE_CTL, val, val);
+
+		val = channel << SUN8I_MIXER_BLEND_ROUTE_PIPE_SHIFT(zpos);
+
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_ROUTE,
+				   SUN8I_MIXER_BLEND_ROUTE_PIPE_MSK(zpos),
+				   val);
+	}
 }
 
 static int sun8i_ui_layer_update_coord(struct sun8i_mixer *mixer, int channel,
-				       int overlay, struct drm_plane *plane)
+				       int overlay, struct drm_plane *plane,
+				       unsigned int zpos)
 {
 	struct drm_plane_state *state = plane->state;
 	u32 src_w, src_h, dst_w, dst_h;
@@ -137,10 +156,10 @@ static int sun8i_ui_layer_update_coord(struct sun8i_mixer *mixer, int channel,
 			 state->dst.x1, state->dst.y1);
 	DRM_DEBUG_DRIVER("Layer destination size W: %d H: %d\n", dst_w, dst_h);
 	regmap_write(mixer->engine.regs,
-		     SUN8I_MIXER_BLEND_ATTR_COORD(channel),
+		     SUN8I_MIXER_BLEND_ATTR_COORD(zpos),
 		     SUN8I_MIXER_COORD(state->dst.x1, state->dst.y1));
 	regmap_write(mixer->engine.regs,
-		     SUN8I_MIXER_BLEND_ATTR_INSIZE(channel),
+		     SUN8I_MIXER_BLEND_ATTR_INSIZE(zpos),
 		     outsize);
 
 	return 0;
@@ -236,30 +255,35 @@ static void sun8i_ui_layer_atomic_disable(struct drm_plane *plane,
 					  struct drm_plane_state *old_state)
 {
 	struct sun8i_ui_layer *layer = plane_to_sun8i_ui_layer(plane);
+	unsigned int old_zpos = old_state->normalized_zpos;
 	struct sun8i_mixer *mixer = layer->mixer;
 
-	sun8i_ui_layer_enable(mixer, layer->channel, layer->overlay, false);
+	sun8i_ui_layer_enable(mixer, layer->channel, layer->overlay, false, 0,
+			      old_zpos);
 }
 
 static void sun8i_ui_layer_atomic_update(struct drm_plane *plane,
 					 struct drm_plane_state *old_state)
 {
 	struct sun8i_ui_layer *layer = plane_to_sun8i_ui_layer(plane);
+	unsigned int zpos = plane->state->normalized_zpos;
+	unsigned int old_zpos = old_state->normalized_zpos;
 	struct sun8i_mixer *mixer = layer->mixer;
 
 	if (!plane->state->visible) {
 		sun8i_ui_layer_enable(mixer, layer->channel,
-				      layer->overlay, false);
+				      layer->overlay, false, 0, old_zpos);
 		return;
 	}
 
 	sun8i_ui_layer_update_coord(mixer, layer->channel,
-				    layer->overlay, plane);
+				    layer->overlay, plane, zpos);
 	sun8i_ui_layer_update_formats(mixer, layer->channel,
 				      layer->overlay, plane);
 	sun8i_ui_layer_update_buffer(mixer, layer->channel,
 				     layer->overlay, plane);
-	sun8i_ui_layer_enable(mixer, layer->channel, layer->overlay, true);
+	sun8i_ui_layer_enable(mixer, layer->channel, layer->overlay,
+			      true, zpos, old_zpos);
 }
 
 static struct drm_plane_helper_funcs sun8i_ui_layer_helper_funcs = {
@@ -307,6 +331,7 @@ struct sun8i_ui_layer *sun8i_ui_layer_init_one(struct drm_device *drm,
 	enum drm_plane_type type = DRM_PLANE_TYPE_OVERLAY;
 	int channel = mixer->cfg->vi_num + index;
 	struct sun8i_ui_layer *layer;
+	unsigned int plane_cnt;
 	int ret;
 
 	layer = devm_kzalloc(drm->dev, sizeof(*layer), GFP_KERNEL);
@@ -327,8 +352,10 @@ struct sun8i_ui_layer *sun8i_ui_layer_init_one(struct drm_device *drm,
 		return ERR_PTR(ret);
 	}
 
-	/* fixed zpos for now */
-	ret = drm_plane_create_zpos_immutable_property(&layer->plane, channel);
+	plane_cnt = mixer->cfg->ui_num + mixer->cfg->vi_num;
+
+	ret = drm_plane_create_zpos_property(&layer->plane, channel,
+					     0, plane_cnt - 1);
 	if (ret) {
 		dev_err(drm->dev, "Couldn't add zpos property\n");
 		return ERR_PTR(ret);
diff --git a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
index 5877f8ef5895..f4fe97813f94 100644
--- a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
@@ -21,7 +21,8 @@
 #include "sun8i_vi_scaler.h"
 
 static void sun8i_vi_layer_enable(struct sun8i_mixer *mixer, int channel,
-				  int overlay, bool enable)
+				  int overlay, bool enable, unsigned int zpos,
+				  unsigned int old_zpos)
 {
 	u32 val;
 
@@ -37,18 +38,36 @@ static void sun8i_vi_layer_enable(struct sun8i_mixer *mixer, int channel,
 			   SUN8I_MIXER_CHAN_VI_LAYER_ATTR(channel, overlay),
 			   SUN8I_MIXER_CHAN_VI_LAYER_ATTR_EN, val);
 
-	if (enable)
-		val = SUN8I_MIXER_BLEND_PIPE_CTL_EN(channel);
-	else
-		val = 0;
+	if (!enable || zpos != old_zpos) {
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_PIPE_CTL,
+				   SUN8I_MIXER_BLEND_PIPE_CTL_EN(old_zpos),
+				   0);
 
-	regmap_update_bits(mixer->engine.regs,
-			   SUN8I_MIXER_BLEND_PIPE_CTL,
-			   SUN8I_MIXER_BLEND_PIPE_CTL_EN(channel), val);
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_ROUTE,
+				   SUN8I_MIXER_BLEND_ROUTE_PIPE_MSK(old_zpos),
+				   0);
+	}
+
+	if (enable) {
+		val = SUN8I_MIXER_BLEND_PIPE_CTL_EN(zpos);
+
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_PIPE_CTL, val, val);
+
+		val = channel << SUN8I_MIXER_BLEND_ROUTE_PIPE_SHIFT(zpos);
+
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_ROUTE,
+				   SUN8I_MIXER_BLEND_ROUTE_PIPE_MSK(zpos),
+				   val);
+	}
 }
 
 static int sun8i_vi_layer_update_coord(struct sun8i_mixer *mixer, int channel,
-				       int overlay, struct drm_plane *plane)
+				       int overlay, struct drm_plane *plane,
+				       unsigned int zpos)
 {
 	struct drm_plane_state *state = plane->state;
 	const struct drm_format_info *format = state->fb->format;
@@ -130,10 +149,10 @@ static int sun8i_vi_layer_update_coord(struct sun8i_mixer *mixer, int channel,
 			 state->dst.x1, state->dst.y1);
 	DRM_DEBUG_DRIVER("Layer destination size W: %d H: %d\n", dst_w, dst_h);
 	regmap_write(mixer->engine.regs,
-		     SUN8I_MIXER_BLEND_ATTR_COORD(channel),
+		     SUN8I_MIXER_BLEND_ATTR_COORD(zpos),
 		     SUN8I_MIXER_COORD(state->dst.x1, state->dst.y1));
 	regmap_write(mixer->engine.regs,
-		     SUN8I_MIXER_BLEND_ATTR_INSIZE(channel),
+		     SUN8I_MIXER_BLEND_ATTR_INSIZE(zpos),
 		     outsize);
 
 	return 0;
@@ -264,30 +283,35 @@ static void sun8i_vi_layer_atomic_disable(struct drm_plane *plane,
 					  struct drm_plane_state *old_state)
 {
 	struct sun8i_vi_layer *layer = plane_to_sun8i_vi_layer(plane);
+	unsigned int old_zpos = old_state->normalized_zpos;
 	struct sun8i_mixer *mixer = layer->mixer;
 
-	sun8i_vi_layer_enable(mixer, layer->channel, layer->overlay, false);
+	sun8i_vi_layer_enable(mixer, layer->channel, layer->overlay, false, 0,
+			      old_zpos);
 }
 
 static void sun8i_vi_layer_atomic_update(struct drm_plane *plane,
 					 struct drm_plane_state *old_state)
 {
 	struct sun8i_vi_layer *layer = plane_to_sun8i_vi_layer(plane);
+	unsigned int zpos = plane->state->normalized_zpos;
+	unsigned int old_zpos = old_state->normalized_zpos;
 	struct sun8i_mixer *mixer = layer->mixer;
 
 	if (!plane->state->visible) {
 		sun8i_vi_layer_enable(mixer, layer->channel,
-				      layer->overlay, false);
+				      layer->overlay, false, 0, old_zpos);
 		return;
 	}
 
 	sun8i_vi_layer_update_coord(mixer, layer->channel,
-				    layer->overlay, plane);
+				    layer->overlay, plane, zpos);
 	sun8i_vi_layer_update_formats(mixer, layer->channel,
 				      layer->overlay, plane);
 	sun8i_vi_layer_update_buffer(mixer, layer->channel,
 				     layer->overlay, plane);
-	sun8i_vi_layer_enable(mixer, layer->channel, layer->overlay, true);
+	sun8i_vi_layer_enable(mixer, layer->channel, layer->overlay,
+			      true, zpos, old_zpos);
 }
 
 static struct drm_plane_helper_funcs sun8i_vi_layer_helper_funcs = {
@@ -351,6 +375,7 @@ struct sun8i_vi_layer *sun8i_vi_layer_init_one(struct drm_device *drm,
 					       int index)
 {
 	struct sun8i_vi_layer *layer;
+	unsigned int plane_cnt;
 	int ret;
 
 	layer = devm_kzalloc(drm->dev, sizeof(*layer), GFP_KERNEL);
@@ -368,8 +393,10 @@ struct sun8i_vi_layer *sun8i_vi_layer_init_one(struct drm_device *drm,
 		return ERR_PTR(ret);
 	}
 
-	/* fixed zpos for now */
-	ret = drm_plane_create_zpos_immutable_property(&layer->plane, index);
+	plane_cnt = mixer->cfg->ui_num + mixer->cfg->vi_num;
+
+	ret = drm_plane_create_zpos_property(&layer->plane, index,
+					     0, plane_cnt - 1);
 	if (ret) {
 		dev_err(drm->dev, "Couldn't add zpos property\n");
 		return ERR_PTR(ret);
diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index c3afe7b2237e..965088afcfad 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -2312,7 +2312,7 @@ static int tegra_dc_couple(struct tegra_dc *dc)
 	 * POWER_CONTROL registers during CRTC enabling.
 	 */
 	if (dc->soc->coupled_pm && dc->pipe == 1) {
-		u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE;
+		u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_CONSUMER;
 		struct device_link *link;
 		struct device *partner;
 
diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c
index 87c5d89bc9ba..ee6ca8fa1c65 100644
--- a/drivers/gpu/drm/tegra/dsi.c
+++ b/drivers/gpu/drm/tegra/dsi.c
@@ -1052,7 +1052,7 @@ static int tegra_dsi_init(struct host1x_client *client)
 		drm_encoder_helper_add(&dsi->output.encoder,
 				       &tegra_dsi_encoder_helper_funcs);
 
-		drm_mode_connector_attach_encoder(&dsi->output.connector,
+		drm_connector_attach_encoder(&dsi->output.connector,
 						  &dsi->output.encoder);
 		drm_connector_register(&dsi->output.connector);
 
@@ -1411,6 +1411,9 @@ static int tegra_dsi_host_attach(struct mipi_dsi_host *host,
 		struct tegra_output *output = &dsi->output;
 
 		output->panel = of_drm_find_panel(device->dev.of_node);
+		if (IS_ERR(output->panel))
+			output->panel = NULL;
+
 		if (output->panel && output->connector.dev) {
 			drm_panel_attach(output->panel, &output->connector);
 			drm_helper_hpd_irq_event(output->connector.dev);
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index 00a5c9f32254..4f80100ff5f3 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -582,18 +582,6 @@ static int tegra_gem_prime_end_cpu_access(struct dma_buf *buf,
 	return 0;
 }
 
-static void *tegra_gem_prime_kmap_atomic(struct dma_buf *buf,
-					 unsigned long page)
-{
-	return NULL;
-}
-
-static void tegra_gem_prime_kunmap_atomic(struct dma_buf *buf,
-					  unsigned long page,
-					  void *addr)
-{
-}
-
 static void *tegra_gem_prime_kmap(struct dma_buf *buf, unsigned long page)
 {
 	return NULL;
@@ -634,8 +622,6 @@ static const struct dma_buf_ops tegra_gem_prime_dmabuf_ops = {
 	.release = tegra_gem_prime_release,
 	.begin_cpu_access = tegra_gem_prime_begin_cpu_access,
 	.end_cpu_access = tegra_gem_prime_end_cpu_access,
-	.map_atomic = tegra_gem_prime_kmap_atomic,
-	.unmap_atomic = tegra_gem_prime_kunmap_atomic,
 	.map = tegra_gem_prime_kmap,
 	.unmap = tegra_gem_prime_kunmap,
 	.mmap = tegra_gem_prime_mmap,
diff --git a/drivers/gpu/drm/tegra/hdmi.c b/drivers/gpu/drm/tegra/hdmi.c
index 784739a9f497..0082468f703c 100644
--- a/drivers/gpu/drm/tegra/hdmi.c
+++ b/drivers/gpu/drm/tegra/hdmi.c
@@ -1488,7 +1488,7 @@ static int tegra_hdmi_init(struct host1x_client *client)
 	drm_encoder_helper_add(&hdmi->output.encoder,
 			       &tegra_hdmi_encoder_helper_funcs);
 
-	drm_mode_connector_attach_encoder(&hdmi->output.connector,
+	drm_connector_attach_encoder(&hdmi->output.connector,
 					  &hdmi->output.encoder);
 	drm_connector_register(&hdmi->output.connector);
 
diff --git a/drivers/gpu/drm/tegra/output.c b/drivers/gpu/drm/tegra/output.c
index ffe34bd0bb9d..c662efc7e413 100644
--- a/drivers/gpu/drm/tegra/output.c
+++ b/drivers/gpu/drm/tegra/output.c
@@ -37,7 +37,7 @@ int tegra_output_connector_get_modes(struct drm_connector *connector)
 		edid = drm_get_edid(connector, output->ddc);
 
 	cec_notifier_set_phys_addr_from_edid(output->notifier, edid);
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 
 	if (edid) {
 		err = drm_add_edid_modes(connector, edid);
@@ -110,8 +110,8 @@ int tegra_output_probe(struct tegra_output *output)
 	panel = of_parse_phandle(output->of_node, "nvidia,panel", 0);
 	if (panel) {
 		output->panel = of_drm_find_panel(panel);
-		if (!output->panel)
-			return -EPROBE_DEFER;
+		if (IS_ERR(output->panel))
+			return PTR_ERR(output->panel);
 
 		of_node_put(panel);
 	}
diff --git a/drivers/gpu/drm/tegra/rgb.c b/drivers/gpu/drm/tegra/rgb.c
index 78ec5193741d..28a78d3120bc 100644
--- a/drivers/gpu/drm/tegra/rgb.c
+++ b/drivers/gpu/drm/tegra/rgb.c
@@ -289,7 +289,7 @@ int tegra_dc_rgb_init(struct drm_device *drm, struct tegra_dc *dc)
 	drm_encoder_helper_add(&output->encoder,
 			       &tegra_rgb_encoder_helper_funcs);
 
-	drm_mode_connector_attach_encoder(&output->connector,
+	drm_connector_attach_encoder(&output->connector,
 					  &output->encoder);
 	drm_connector_register(&output->connector);
 
diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c
index 7d2a955fc515..d7fe9f15def1 100644
--- a/drivers/gpu/drm/tegra/sor.c
+++ b/drivers/gpu/drm/tegra/sor.c
@@ -2622,7 +2622,7 @@ static int tegra_sor_init(struct host1x_client *client)
 			 encoder, NULL);
 	drm_encoder_helper_add(&sor->output.encoder, helpers);
 
-	drm_mode_connector_attach_encoder(&sor->output.connector,
+	drm_connector_attach_encoder(&sor->output.connector,
 					  &sor->output.encoder);
 	drm_connector_register(&sor->output.connector);
 
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
index b8a5e4ed22e6..0fb300d41a09 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
@@ -378,7 +378,7 @@ static int tilcdc_init(struct drm_driver *ddrv, struct device *dev)
 	if (!priv->external_connector &&
 	    ((priv->num_encoders == 0) || (priv->num_connectors == 0))) {
 		dev_err(dev, "no encoders/connectors found\n");
-		ret = -ENXIO;
+		ret = -EPROBE_DEFER;
 		goto init_failed;
 	}
 
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_external.c b/drivers/gpu/drm/tilcdc/tilcdc_external.c
index d651bdd6597e..b4eaf9bc87f8 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_external.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_external.c
@@ -103,12 +103,11 @@ struct drm_connector *tilcdc_encoder_find_connector(struct drm_device *ddev,
 						    struct drm_encoder *encoder)
 {
 	struct drm_connector *connector;
-	int i;
 
-	list_for_each_entry(connector, &ddev->mode_config.connector_list, head)
-		for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++)
-			if (connector->encoder_ids[i] == encoder->base.id)
-				return connector;
+	list_for_each_entry(connector, &ddev->mode_config.connector_list, head) {
+		if (drm_connector_has_possible_encoder(connector, encoder))
+			return connector;
+	}
 
 	dev_err(ddev->dev, "No connector found for %s encoder (id %d)\n",
 		encoder->name, encoder->base.id);
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_panel.c b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
index d616d64a6725..a1acab39d87f 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_panel.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
@@ -223,7 +223,7 @@ static struct drm_connector *panel_connector_create(struct drm_device *dev,
 	connector->interlace_allowed = 0;
 	connector->doublescan_allowed = 0;
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret)
 		goto fail;
 
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
index c45cabb38db0..daebf1aa6b0a 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
@@ -173,7 +173,7 @@ static int tfp410_connector_get_modes(struct drm_connector *connector)
 
 	edid = drm_get_edid(connector, tfp410_connector->mod->i2c);
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 
 	if (edid) {
 		ret = drm_add_edid_modes(connector, edid);
@@ -240,7 +240,7 @@ static struct drm_connector *tfp410_connector_create(struct drm_device *dev,
 	connector->interlace_allowed = 0;
 	connector->doublescan_allowed = 0;
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret)
 		goto fail;
 
diff --git a/drivers/gpu/drm/tinydrm/Kconfig b/drivers/gpu/drm/tinydrm/Kconfig
index 4592a5e3f20b..16f4b5c91f1b 100644
--- a/drivers/gpu/drm/tinydrm/Kconfig
+++ b/drivers/gpu/drm/tinydrm/Kconfig
@@ -20,6 +20,17 @@ config TINYDRM_ILI9225
 
 	  If M is selected the module will be called ili9225.
 
+config TINYDRM_ILI9341
+	tristate "DRM support for ILI9341 display panels"
+	depends on DRM_TINYDRM && SPI
+	depends on BACKLIGHT_CLASS_DEVICE
+	select TINYDRM_MIPI_DBI
+	help
+	  DRM driver for the following Ilitek ILI9341 panels:
+	  * YX240QV29-T 2.4" 240x320 TFT (Adafruit 2.4")
+
+	  If M is selected the module will be called ili9341.
+
 config TINYDRM_MI0283QT
 	tristate "DRM support for MI0283QT"
 	depends on DRM_TINYDRM && SPI
diff --git a/drivers/gpu/drm/tinydrm/Makefile b/drivers/gpu/drm/tinydrm/Makefile
index 49a111929724..14d99080665a 100644
--- a/drivers/gpu/drm/tinydrm/Makefile
+++ b/drivers/gpu/drm/tinydrm/Makefile
@@ -5,6 +5,7 @@ obj-$(CONFIG_TINYDRM_MIPI_DBI)		+= mipi-dbi.o
 
 # Displays
 obj-$(CONFIG_TINYDRM_ILI9225)		+= ili9225.o
+obj-$(CONFIG_TINYDRM_ILI9341)		+= ili9341.o
 obj-$(CONFIG_TINYDRM_MI0283QT)		+= mi0283qt.o
 obj-$(CONFIG_TINYDRM_REPAPER)		+= repaper.o
 obj-$(CONFIG_TINYDRM_ST7586)		+= st7586.o
diff --git a/drivers/gpu/drm/tinydrm/core/tinydrm-core.c b/drivers/gpu/drm/tinydrm/core/tinydrm-core.c
index 24a33bf862fa..19c7f70adfa5 100644
--- a/drivers/gpu/drm/tinydrm/core/tinydrm-core.c
+++ b/drivers/gpu/drm/tinydrm/core/tinydrm-core.c
@@ -204,7 +204,7 @@ static int tinydrm_register(struct tinydrm_device *tdev)
 	if (ret)
 		return ret;
 
-	ret = drm_fb_cma_fbdev_init_with_funcs(drm, 0, 0, tdev->fb_funcs);
+	ret = drm_fbdev_generic_setup(drm, 0);
 	if (ret)
 		DRM_ERROR("Failed to initialize fbdev: %d\n", ret);
 
@@ -214,7 +214,6 @@ static int tinydrm_register(struct tinydrm_device *tdev)
 static void tinydrm_unregister(struct tinydrm_device *tdev)
 {
 	drm_atomic_helper_shutdown(tdev->drm);
-	drm_fb_cma_fbdev_fini(tdev->drm);
 	drm_dev_unregister(tdev->drm);
 }
 
diff --git a/drivers/gpu/drm/tinydrm/ili9225.c b/drivers/gpu/drm/tinydrm/ili9225.c
index 841c69aba059..455fefe012f5 100644
--- a/drivers/gpu/drm/tinydrm/ili9225.c
+++ b/drivers/gpu/drm/tinydrm/ili9225.c
@@ -368,7 +368,6 @@ static struct drm_driver ili9225_driver = {
 				  DRIVER_ATOMIC,
 	.fops			= &ili9225_fops,
 	TINYDRM_GEM_DRIVER_OPS,
-	.lastclose		= drm_fb_helper_lastclose,
 	.name			= "ili9225",
 	.desc			= "Ilitek ILI9225",
 	.date			= "20171106",
diff --git a/drivers/gpu/drm/tinydrm/ili9341.c b/drivers/gpu/drm/tinydrm/ili9341.c
new file mode 100644
index 000000000000..6701037749a7
--- /dev/null
+++ b/drivers/gpu/drm/tinydrm/ili9341.c
@@ -0,0 +1,232 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * DRM driver for Ilitek ILI9341 panels
+ *
+ * Copyright 2018 David Lechner <david@lechnology.com>
+ *
+ * Based on mi0283qt.c:
+ * Copyright 2016 Noralf Trønnes
+ */
+
+#include <linux/backlight.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/module.h>
+#include <linux/property.h>
+#include <linux/spi/spi.h>
+
+#include <drm/drm_fb_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
+#include <drm/drm_modeset_helper.h>
+#include <drm/tinydrm/mipi-dbi.h>
+#include <drm/tinydrm/tinydrm-helpers.h>
+#include <video/mipi_display.h>
+
+#define ILI9341_FRMCTR1		0xb1
+#define ILI9341_DISCTRL		0xb6
+#define ILI9341_ETMOD		0xb7
+
+#define ILI9341_PWCTRL1		0xc0
+#define ILI9341_PWCTRL2		0xc1
+#define ILI9341_VMCTRL1		0xc5
+#define ILI9341_VMCTRL2		0xc7
+#define ILI9341_PWCTRLA		0xcb
+#define ILI9341_PWCTRLB		0xcf
+
+#define ILI9341_PGAMCTRL	0xe0
+#define ILI9341_NGAMCTRL	0xe1
+#define ILI9341_DTCTRLA		0xe8
+#define ILI9341_DTCTRLB		0xea
+#define ILI9341_PWRSEQ		0xed
+
+#define ILI9341_EN3GAM		0xf2
+#define ILI9341_PUMPCTRL	0xf7
+
+#define ILI9341_MADCTL_BGR	BIT(3)
+#define ILI9341_MADCTL_MV	BIT(5)
+#define ILI9341_MADCTL_MX	BIT(6)
+#define ILI9341_MADCTL_MY	BIT(7)
+
+static void yx240qv29_enable(struct drm_simple_display_pipe *pipe,
+			     struct drm_crtc_state *crtc_state,
+			     struct drm_plane_state *plane_state)
+{
+	struct tinydrm_device *tdev = pipe_to_tinydrm(pipe);
+	struct mipi_dbi *mipi = mipi_dbi_from_tinydrm(tdev);
+	u8 addr_mode;
+	int ret;
+
+	DRM_DEBUG_KMS("\n");
+
+	ret = mipi_dbi_poweron_conditional_reset(mipi);
+	if (ret < 0)
+		return;
+	if (ret == 1)
+		goto out_enable;
+
+	mipi_dbi_command(mipi, MIPI_DCS_SET_DISPLAY_OFF);
+
+	mipi_dbi_command(mipi, ILI9341_PWCTRLB, 0x00, 0xc1, 0x30);
+	mipi_dbi_command(mipi, ILI9341_PWRSEQ, 0x64, 0x03, 0x12, 0x81);
+	mipi_dbi_command(mipi, ILI9341_DTCTRLA, 0x85, 0x00, 0x78);
+	mipi_dbi_command(mipi, ILI9341_PWCTRLA, 0x39, 0x2c, 0x00, 0x34, 0x02);
+	mipi_dbi_command(mipi, ILI9341_PUMPCTRL, 0x20);
+	mipi_dbi_command(mipi, ILI9341_DTCTRLB, 0x00, 0x00);
+
+	/* Power Control */
+	mipi_dbi_command(mipi, ILI9341_PWCTRL1, 0x23);
+	mipi_dbi_command(mipi, ILI9341_PWCTRL2, 0x10);
+	/* VCOM */
+	mipi_dbi_command(mipi, ILI9341_VMCTRL1, 0x3e, 0x28);
+	mipi_dbi_command(mipi, ILI9341_VMCTRL2, 0x86);
+
+	/* Memory Access Control */
+	mipi_dbi_command(mipi, MIPI_DCS_SET_PIXEL_FORMAT, MIPI_DCS_PIXEL_FMT_16BIT);
+
+	/* Frame Rate */
+	mipi_dbi_command(mipi, ILI9341_FRMCTR1, 0x00, 0x1b);
+
+	/* Gamma */
+	mipi_dbi_command(mipi, ILI9341_EN3GAM, 0x00);
+	mipi_dbi_command(mipi, MIPI_DCS_SET_GAMMA_CURVE, 0x01);
+	mipi_dbi_command(mipi, ILI9341_PGAMCTRL,
+			 0x0f, 0x31, 0x2b, 0x0c, 0x0e, 0x08, 0x4e, 0xf1,
+			 0x37, 0x07, 0x10, 0x03, 0x0e, 0x09, 0x00);
+	mipi_dbi_command(mipi, ILI9341_NGAMCTRL,
+			 0x00, 0x0e, 0x14, 0x03, 0x11, 0x07, 0x31, 0xc1,
+			 0x48, 0x08, 0x0f, 0x0c, 0x31, 0x36, 0x0f);
+
+	/* DDRAM */
+	mipi_dbi_command(mipi, ILI9341_ETMOD, 0x07);
+
+	/* Display */
+	mipi_dbi_command(mipi, ILI9341_DISCTRL, 0x08, 0x82, 0x27, 0x00);
+	mipi_dbi_command(mipi, MIPI_DCS_EXIT_SLEEP_MODE);
+	msleep(100);
+
+	mipi_dbi_command(mipi, MIPI_DCS_SET_DISPLAY_ON);
+	msleep(100);
+
+out_enable:
+	switch (mipi->rotation) {
+	default:
+		addr_mode = ILI9341_MADCTL_MX;
+		break;
+	case 90:
+		addr_mode = ILI9341_MADCTL_MV;
+		break;
+	case 180:
+		addr_mode = ILI9341_MADCTL_MY;
+		break;
+	case 270:
+		addr_mode = ILI9341_MADCTL_MV | ILI9341_MADCTL_MY |
+			    ILI9341_MADCTL_MX;
+		break;
+	}
+	addr_mode |= ILI9341_MADCTL_BGR;
+	mipi_dbi_command(mipi, MIPI_DCS_SET_ADDRESS_MODE, addr_mode);
+	mipi_dbi_enable_flush(mipi, crtc_state, plane_state);
+}
+
+static const struct drm_simple_display_pipe_funcs ili9341_pipe_funcs = {
+	.enable = yx240qv29_enable,
+	.disable = mipi_dbi_pipe_disable,
+	.update = tinydrm_display_pipe_update,
+	.prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb,
+};
+
+static const struct drm_display_mode yx240qv29_mode = {
+	TINYDRM_MODE(240, 320, 37, 49),
+};
+
+DEFINE_DRM_GEM_CMA_FOPS(ili9341_fops);
+
+static struct drm_driver ili9341_driver = {
+	.driver_features	= DRIVER_GEM | DRIVER_MODESET | DRIVER_PRIME | DRIVER_ATOMIC,
+	.fops			= &ili9341_fops,
+	TINYDRM_GEM_DRIVER_OPS,
+	.debugfs_init		= mipi_dbi_debugfs_init,
+	.name			= "ili9341",
+	.desc			= "Ilitek ILI9341",
+	.date			= "20180514",
+	.major			= 1,
+	.minor			= 0,
+};
+
+static const struct of_device_id ili9341_of_match[] = {
+	{ .compatible = "adafruit,yx240qv29" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ili9341_of_match);
+
+static const struct spi_device_id ili9341_id[] = {
+	{ "yx240qv29", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, ili9341_id);
+
+static int ili9341_probe(struct spi_device *spi)
+{
+	struct device *dev = &spi->dev;
+	struct mipi_dbi *mipi;
+	struct gpio_desc *dc;
+	u32 rotation = 0;
+	int ret;
+
+	mipi = devm_kzalloc(dev, sizeof(*mipi), GFP_KERNEL);
+	if (!mipi)
+		return -ENOMEM;
+
+	mipi->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(mipi->reset)) {
+		DRM_DEV_ERROR(dev, "Failed to get gpio 'reset'\n");
+		return PTR_ERR(mipi->reset);
+	}
+
+	dc = devm_gpiod_get_optional(dev, "dc", GPIOD_OUT_LOW);
+	if (IS_ERR(dc)) {
+		DRM_DEV_ERROR(dev, "Failed to get gpio 'dc'\n");
+		return PTR_ERR(dc);
+	}
+
+	mipi->backlight = devm_of_find_backlight(dev);
+	if (IS_ERR(mipi->backlight))
+		return PTR_ERR(mipi->backlight);
+
+	device_property_read_u32(dev, "rotation", &rotation);
+
+	ret = mipi_dbi_spi_init(spi, mipi, dc);
+	if (ret)
+		return ret;
+
+	ret = mipi_dbi_init(&spi->dev, mipi, &ili9341_pipe_funcs,
+			    &ili9341_driver, &yx240qv29_mode, rotation);
+	if (ret)
+		return ret;
+
+	spi_set_drvdata(spi, mipi);
+
+	return devm_tinydrm_register(&mipi->tinydrm);
+}
+
+static void ili9341_shutdown(struct spi_device *spi)
+{
+	struct mipi_dbi *mipi = spi_get_drvdata(spi);
+
+	tinydrm_shutdown(&mipi->tinydrm);
+}
+
+static struct spi_driver ili9341_spi_driver = {
+	.driver = {
+		.name = "ili9341",
+		.of_match_table = ili9341_of_match,
+	},
+	.id_table = ili9341_id,
+	.probe = ili9341_probe,
+	.shutdown = ili9341_shutdown,
+};
+module_spi_driver(ili9341_spi_driver);
+
+MODULE_DESCRIPTION("Ilitek ILI9341 DRM driver");
+MODULE_AUTHOR("David Lechner <david@lechnology.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/tinydrm/mi0283qt.c b/drivers/gpu/drm/tinydrm/mi0283qt.c
index 015d03f2acba..d7bb4c5e6657 100644
--- a/drivers/gpu/drm/tinydrm/mi0283qt.c
+++ b/drivers/gpu/drm/tinydrm/mi0283qt.c
@@ -154,7 +154,6 @@ static struct drm_driver mi0283qt_driver = {
 				  DRIVER_ATOMIC,
 	.fops			= &mi0283qt_fops,
 	TINYDRM_GEM_DRIVER_OPS,
-	.lastclose		= drm_fb_helper_lastclose,
 	.debugfs_init		= mipi_dbi_debugfs_init,
 	.name			= "mi0283qt",
 	.desc			= "Multi-Inno MI0283QT",
diff --git a/drivers/gpu/drm/tinydrm/mipi-dbi.c b/drivers/gpu/drm/tinydrm/mipi-dbi.c
index 4d1fb31a781f..cb3441e51d5f 100644
--- a/drivers/gpu/drm/tinydrm/mipi-dbi.c
+++ b/drivers/gpu/drm/tinydrm/mipi-dbi.c
@@ -260,6 +260,8 @@ static const struct drm_framebuffer_funcs mipi_dbi_fb_funcs = {
 /**
  * mipi_dbi_enable_flush - MIPI DBI enable helper
  * @mipi: MIPI DBI structure
+ * @crtc_state: CRTC state
+ * @plane_state: Plane state
  *
  * This function sets &mipi_dbi->enabled, flushes the whole framebuffer and
  * enables the backlight. Drivers can use this in their
diff --git a/drivers/gpu/drm/tinydrm/st7586.c b/drivers/gpu/drm/tinydrm/st7586.c
index 5c29e3803ecb..2fcbc3067d71 100644
--- a/drivers/gpu/drm/tinydrm/st7586.c
+++ b/drivers/gpu/drm/tinydrm/st7586.c
@@ -304,7 +304,6 @@ static struct drm_driver st7586_driver = {
 				  DRIVER_ATOMIC,
 	.fops			= &st7586_fops,
 	TINYDRM_GEM_DRIVER_OPS,
-	.lastclose		= drm_fb_helper_lastclose,
 	.debugfs_init		= mipi_dbi_debugfs_init,
 	.name			= "st7586",
 	.desc			= "Sitronix ST7586",
diff --git a/drivers/gpu/drm/tinydrm/st7735r.c b/drivers/gpu/drm/tinydrm/st7735r.c
index 6c7b15c9da4f..3081bc57c116 100644
--- a/drivers/gpu/drm/tinydrm/st7735r.c
+++ b/drivers/gpu/drm/tinydrm/st7735r.c
@@ -120,7 +120,6 @@ static struct drm_driver st7735r_driver = {
 				  DRIVER_ATOMIC,
 	.fops			= &st7735r_fops,
 	TINYDRM_GEM_DRIVER_OPS,
-	.lastclose		= drm_fb_helper_lastclose,
 	.debugfs_init		= mipi_dbi_debugfs_init,
 	.name			= "st7735r",
 	.desc			= "Sitronix ST7735R",
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 5d8688e522d1..7c484729f9b2 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -287,12 +287,9 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 
 	if (ret) {
 		if (bdev->driver->move_notify) {
-			struct ttm_mem_reg tmp_mem = *mem;
-			*mem = bo->mem;
-			bo->mem = tmp_mem;
+			swap(*mem, bo->mem);
 			bdev->driver->move_notify(bo, false, mem);
-			bo->mem = *mem;
-			*mem = tmp_mem;
+			swap(*mem, bo->mem);
 		}
 
 		goto out_err;
@@ -590,12 +587,18 @@ static void ttm_bo_release(struct kref *kref)
 	kref_put(&bo->list_kref, ttm_bo_release_list);
 }
 
+void ttm_bo_put(struct ttm_buffer_object *bo)
+{
+	kref_put(&bo->kref, ttm_bo_release);
+}
+EXPORT_SYMBOL(ttm_bo_put);
+
 void ttm_bo_unref(struct ttm_buffer_object **p_bo)
 {
 	struct ttm_buffer_object *bo = *p_bo;
 
 	*p_bo = NULL;
-	kref_put(&bo->kref, ttm_bo_release);
+	ttm_bo_put(bo);
 }
 EXPORT_SYMBOL(ttm_bo_unref);
 
@@ -1201,7 +1204,7 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 		if (!resv)
 			ttm_bo_unreserve(bo);
 
-		ttm_bo_unref(&bo);
+		ttm_bo_put(bo);
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index f2c167702eef..046a6dda690a 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -463,7 +463,7 @@ static void ttm_transfered_destroy(struct ttm_buffer_object *bo)
 	struct ttm_transfer_obj *fbo;
 
 	fbo = container_of(bo, struct ttm_transfer_obj, base);
-	ttm_bo_unref(&fbo->bo);
+	ttm_bo_put(fbo->bo);
 	kfree(fbo);
 }
 
@@ -492,8 +492,9 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	if (!fbo)
 		return -ENOMEM;
 
+	ttm_bo_get(bo);
 	fbo->base = *bo;
-	fbo->bo = ttm_bo_reference(bo);
+	fbo->bo = bo;
 
 	/**
 	 * Fix up members that we shouldn't copy directly:
@@ -730,7 +731,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 			bo->ttm = NULL;
 
 		ttm_bo_unreserve(ghost_obj);
-		ttm_bo_unref(&ghost_obj);
+		ttm_bo_put(ghost_obj);
 	}
 
 	*old_mem = *new_mem;
@@ -786,7 +787,7 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 			bo->ttm = NULL;
 
 		ttm_bo_unreserve(ghost_obj);
-		ttm_bo_unref(&ghost_obj);
+		ttm_bo_put(ghost_obj);
 
 	} else if (from->flags & TTM_MEMTYPE_FLAG_FIXED) {
 
@@ -851,7 +852,7 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
 	bo->ttm = NULL;
 
 	ttm_bo_unreserve(ghost);
-	ttm_bo_unref(&ghost);
+	ttm_bo_put(ghost);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index c7ece7613a6a..6fe91c1b692d 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -44,10 +44,11 @@
 
 #define TTM_BO_VM_NUM_PREFAULT 16
 
-static int ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
+static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 				struct vm_fault *vmf)
 {
-	int ret = 0;
+	vm_fault_t ret = 0;
+	int err = 0;
 
 	if (likely(!bo->moving))
 		goto out_unlock;
@@ -67,20 +68,20 @@ static int ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 		if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
 			goto out_unlock;
 
-		ttm_bo_reference(bo);
+		ttm_bo_get(bo);
 		up_read(&vmf->vma->vm_mm->mmap_sem);
 		(void) dma_fence_wait(bo->moving, true);
 		ttm_bo_unreserve(bo);
-		ttm_bo_unref(&bo);
+		ttm_bo_put(bo);
 		goto out_unlock;
 	}
 
 	/*
 	 * Ordinary wait.
 	 */
-	ret = dma_fence_wait(bo->moving, true);
-	if (unlikely(ret != 0)) {
-		ret = (ret != -ERESTARTSYS) ? VM_FAULT_SIGBUS :
+	err = dma_fence_wait(bo->moving, true);
+	if (unlikely(err != 0)) {
+		ret = (err != -ERESTARTSYS) ? VM_FAULT_SIGBUS :
 			VM_FAULT_NOPAGE;
 		goto out_unlock;
 	}
@@ -105,7 +106,7 @@ static unsigned long ttm_bo_io_mem_pfn(struct ttm_buffer_object *bo,
 		+ page_offset;
 }
 
-static int ttm_bo_vm_fault(struct vm_fault *vmf)
+static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct ttm_buffer_object *bo = (struct ttm_buffer_object *)
@@ -116,8 +117,9 @@ static int ttm_bo_vm_fault(struct vm_fault *vmf)
 	unsigned long pfn;
 	struct ttm_tt *ttm = NULL;
 	struct page *page;
-	int ret;
+	int err;
 	int i;
+	vm_fault_t ret = VM_FAULT_NOPAGE;
 	unsigned long address = vmf->address;
 	struct ttm_mem_type_manager *man =
 		&bdev->man[bo->mem.mem_type];
@@ -129,17 +131,17 @@ static int ttm_bo_vm_fault(struct vm_fault *vmf)
 	 * for reserve, and if it fails, retry the fault after waiting
 	 * for the buffer to become unreserved.
 	 */
-	ret = ttm_bo_reserve(bo, true, true, NULL);
-	if (unlikely(ret != 0)) {
-		if (ret != -EBUSY)
+	err = ttm_bo_reserve(bo, true, true, NULL);
+	if (unlikely(err != 0)) {
+		if (err != -EBUSY)
 			return VM_FAULT_NOPAGE;
 
 		if (vmf->flags & FAULT_FLAG_ALLOW_RETRY) {
 			if (!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
-				ttm_bo_reference(bo);
+				ttm_bo_get(bo);
 				up_read(&vmf->vma->vm_mm->mmap_sem);
 				(void) ttm_bo_wait_unreserved(bo);
-				ttm_bo_unref(&bo);
+				ttm_bo_put(bo);
 			}
 
 			return VM_FAULT_RETRY;
@@ -163,8 +165,8 @@ static int ttm_bo_vm_fault(struct vm_fault *vmf)
 	}
 
 	if (bdev->driver->fault_reserve_notify) {
-		ret = bdev->driver->fault_reserve_notify(bo);
-		switch (ret) {
+		err = bdev->driver->fault_reserve_notify(bo);
+		switch (err) {
 		case 0:
 			break;
 		case -EBUSY:
@@ -192,13 +194,13 @@ static int ttm_bo_vm_fault(struct vm_fault *vmf)
 		goto out_unlock;
 	}
 
-	ret = ttm_mem_io_lock(man, true);
-	if (unlikely(ret != 0)) {
+	err = ttm_mem_io_lock(man, true);
+	if (unlikely(err != 0)) {
 		ret = VM_FAULT_NOPAGE;
 		goto out_unlock;
 	}
-	ret = ttm_mem_io_reserve_vm(bo);
-	if (unlikely(ret != 0)) {
+	err = ttm_mem_io_reserve_vm(bo);
+	if (unlikely(err != 0)) {
 		ret = VM_FAULT_SIGBUS;
 		goto out_io_unlock;
 	}
@@ -266,23 +268,20 @@ static int ttm_bo_vm_fault(struct vm_fault *vmf)
 		}
 
 		if (vma->vm_flags & VM_MIXEDMAP)
-			ret = vm_insert_mixed(&cvma, address,
+			ret = vmf_insert_mixed(&cvma, address,
 					__pfn_to_pfn_t(pfn, PFN_DEV));
 		else
-			ret = vm_insert_pfn(&cvma, address, pfn);
+			ret = vmf_insert_pfn(&cvma, address, pfn);
 
 		/*
 		 * Somebody beat us to this PTE or prefaulting to
 		 * an already populated PTE, or prefaulting error.
 		 */
 
-		if (unlikely((ret == -EBUSY) || (ret != 0 && i > 0)))
+		if (unlikely((ret == VM_FAULT_NOPAGE && i > 0)))
 			break;
-		else if (unlikely(ret != 0)) {
-			ret =
-			    (ret == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS;
+		else if (unlikely(ret & VM_FAULT_ERROR))
 			goto out_io_unlock;
-		}
 
 		address += PAGE_SIZE;
 		if (unlikely(++page_offset >= page_last))
@@ -303,14 +302,14 @@ static void ttm_bo_vm_open(struct vm_area_struct *vma)
 
 	WARN_ON(bo->bdev->dev_mapping != vma->vm_file->f_mapping);
 
-	(void)ttm_bo_reference(bo);
+	ttm_bo_get(bo);
 }
 
 static void ttm_bo_vm_close(struct vm_area_struct *vma)
 {
 	struct ttm_buffer_object *bo = (struct ttm_buffer_object *)vma->vm_private_data;
 
-	ttm_bo_unref(&bo);
+	ttm_bo_put(bo);
 	vma->vm_private_data = NULL;
 }
 
@@ -462,7 +461,7 @@ int ttm_bo_mmap(struct file *filp, struct vm_area_struct *vma,
 	vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
 	return 0;
 out_unref:
-	ttm_bo_unref(&bo);
+	ttm_bo_put(bo);
 	return ret;
 }
 EXPORT_SYMBOL(ttm_bo_mmap);
@@ -472,8 +471,10 @@ int ttm_fbdev_mmap(struct vm_area_struct *vma, struct ttm_buffer_object *bo)
 	if (vma->vm_pgoff != 0)
 		return -EACCES;
 
+	ttm_bo_get(bo);
+
 	vma->vm_ops = &ttm_bo_vm_ops;
-	vma->vm_private_data = ttm_bo_reference(bo);
+	vma->vm_private_data = bo;
 	vma->vm_flags |= VM_MIXEDMAP;
 	vma->vm_flags |= VM_IO | VM_DONTEXPAND;
 	return 0;
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index 6e2d1300b457..f841accc2c00 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -47,13 +47,7 @@
 
 #include <drm/ttm/ttm_bo_driver.h>
 #include <drm/ttm/ttm_page_alloc.h>
-
-#if IS_ENABLED(CONFIG_AGP)
-#include <asm/agp.h>
-#endif
-#ifdef CONFIG_X86
-#include <asm/set_memory.h>
-#endif
+#include <drm/ttm/ttm_set_memory.h>
 
 #define NUM_PAGES_TO_ALLOC		(PAGE_SIZE/sizeof(struct page *))
 #define SMALL_ALLOCATION		16
@@ -222,52 +216,6 @@ static struct kobj_type ttm_pool_kobj_type = {
 
 static struct ttm_pool_manager *_manager;
 
-#ifndef CONFIG_X86
-static int set_pages_wb(struct page *page, int numpages)
-{
-#if IS_ENABLED(CONFIG_AGP)
-	int i;
-
-	for (i = 0; i < numpages; i++)
-		unmap_page_from_agp(page++);
-#endif
-	return 0;
-}
-
-static int set_pages_array_wb(struct page **pages, int addrinarray)
-{
-#if IS_ENABLED(CONFIG_AGP)
-	int i;
-
-	for (i = 0; i < addrinarray; i++)
-		unmap_page_from_agp(pages[i]);
-#endif
-	return 0;
-}
-
-static int set_pages_array_wc(struct page **pages, int addrinarray)
-{
-#if IS_ENABLED(CONFIG_AGP)
-	int i;
-
-	for (i = 0; i < addrinarray; i++)
-		map_page_into_agp(pages[i]);
-#endif
-	return 0;
-}
-
-static int set_pages_array_uc(struct page **pages, int addrinarray)
-{
-#if IS_ENABLED(CONFIG_AGP)
-	int i;
-
-	for (i = 0; i < addrinarray; i++)
-		map_page_into_agp(pages[i]);
-#endif
-	return 0;
-}
-#endif
-
 /**
  * Select the right pool or requested caching state and ttm flags. */
 static struct ttm_page_pool *ttm_get_pool(int flags, bool huge,
@@ -302,13 +250,13 @@ static void ttm_pages_put(struct page *pages[], unsigned npages,
 	unsigned int i, pages_nr = (1 << order);
 
 	if (order == 0) {
-		if (set_pages_array_wb(pages, npages))
+		if (ttm_set_pages_array_wb(pages, npages))
 			pr_err("Failed to set %d pages to wb!\n", npages);
 	}
 
 	for (i = 0; i < npages; ++i) {
 		if (order > 0) {
-			if (set_pages_wb(pages[i], pages_nr))
+			if (ttm_set_pages_wb(pages[i], pages_nr))
 				pr_err("Failed to set %d pages to wb!\n", pages_nr);
 		}
 		__free_pages(pages[i], order);
@@ -498,12 +446,12 @@ static int ttm_set_pages_caching(struct page **pages,
 	/* Set page caching */
 	switch (cstate) {
 	case tt_uncached:
-		r = set_pages_array_uc(pages, cpages);
+		r = ttm_set_pages_array_uc(pages, cpages);
 		if (r)
 			pr_err("Failed to set %d pages to uc!\n", cpages);
 		break;
 	case tt_wc:
-		r = set_pages_array_wc(pages, cpages);
+		r = ttm_set_pages_array_wc(pages, cpages);
 		if (r)
 			pr_err("Failed to set %d pages to wc!\n", cpages);
 		break;
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index 3f14c1cc0789..507be7ac1165 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -50,12 +50,7 @@
 #include <linux/kthread.h>
 #include <drm/ttm/ttm_bo_driver.h>
 #include <drm/ttm/ttm_page_alloc.h>
-#if IS_ENABLED(CONFIG_AGP)
-#include <asm/agp.h>
-#endif
-#ifdef CONFIG_X86
-#include <asm/set_memory.h>
-#endif
+#include <drm/ttm/ttm_set_memory.h>
 
 #define NUM_PAGES_TO_ALLOC		(PAGE_SIZE/sizeof(struct page *))
 #define SMALL_ALLOCATION		4
@@ -268,54 +263,19 @@ static struct kobj_type ttm_pool_kobj_type = {
 	.default_attrs = ttm_pool_attrs,
 };
 
-#ifndef CONFIG_X86
-static int set_pages_array_wb(struct page **pages, int addrinarray)
-{
-#if IS_ENABLED(CONFIG_AGP)
-	int i;
-
-	for (i = 0; i < addrinarray; i++)
-		unmap_page_from_agp(pages[i]);
-#endif
-	return 0;
-}
-
-static int set_pages_array_wc(struct page **pages, int addrinarray)
-{
-#if IS_ENABLED(CONFIG_AGP)
-	int i;
-
-	for (i = 0; i < addrinarray; i++)
-		map_page_into_agp(pages[i]);
-#endif
-	return 0;
-}
-
-static int set_pages_array_uc(struct page **pages, int addrinarray)
-{
-#if IS_ENABLED(CONFIG_AGP)
-	int i;
-
-	for (i = 0; i < addrinarray; i++)
-		map_page_into_agp(pages[i]);
-#endif
-	return 0;
-}
-#endif /* for !CONFIG_X86 */
-
 static int ttm_set_pages_caching(struct dma_pool *pool,
 				 struct page **pages, unsigned cpages)
 {
 	int r = 0;
 	/* Set page caching */
 	if (pool->type & IS_UC) {
-		r = set_pages_array_uc(pages, cpages);
+		r = ttm_set_pages_array_uc(pages, cpages);
 		if (r)
 			pr_err("%s: Failed to set %d pages to uc!\n",
 			       pool->dev_name, cpages);
 	}
 	if (pool->type & IS_WC) {
-		r = set_pages_array_wc(pages, cpages);
+		r = ttm_set_pages_array_wc(pages, cpages);
 		if (r)
 			pr_err("%s: Failed to set %d pages to wc!\n",
 			       pool->dev_name, cpages);
@@ -389,17 +349,14 @@ static void ttm_pool_update_free_locked(struct dma_pool *pool,
 static void ttm_dma_page_put(struct dma_pool *pool, struct dma_page *d_page)
 {
 	struct page *page = d_page->p;
-	unsigned i, num_pages;
+	unsigned num_pages;
 
 	/* Don't set WB on WB page pool. */
 	if (!(pool->type & IS_CACHED)) {
 		num_pages = pool->size / PAGE_SIZE;
-		for (i = 0; i < num_pages; ++i, ++page) {
-			if (set_pages_array_wb(&page, 1)) {
-				pr_err("%s: Failed to set %d pages to wb!\n",
-				       pool->dev_name, 1);
-			}
-		}
+		if (ttm_set_pages_wb(page, num_pages))
+			pr_err("%s: Failed to set %d pages to wb!\n",
+			       pool->dev_name, num_pages);
 	}
 
 	list_del(&d_page->page_list);
@@ -420,7 +377,7 @@ static void ttm_dma_pages_put(struct dma_pool *pool, struct list_head *d_pages,
 
 	/* Don't set WB on WB page pool. */
 	if (npages && !(pool->type & IS_CACHED) &&
-	    set_pages_array_wb(pages, npages))
+	    ttm_set_pages_array_wb(pages, npages))
 		pr_err("%s: Failed to set %d pages to wb!\n",
 		       pool->dev_name, npages);
 
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index a1e543972ca7..e3a0691582ff 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -38,9 +38,7 @@
 #include <drm/drm_cache.h>
 #include <drm/ttm/ttm_bo_driver.h>
 #include <drm/ttm/ttm_page_alloc.h>
-#ifdef CONFIG_X86
-#include <asm/set_memory.h>
-#endif
+#include <drm/ttm/ttm_set_memory.h>
 
 /**
  * Allocates a ttm structure for the given BO.
@@ -115,10 +113,9 @@ static int ttm_sg_tt_alloc_page_directory(struct ttm_dma_tt *ttm)
 	return 0;
 }
 
-#ifdef CONFIG_X86
-static inline int ttm_tt_set_page_caching(struct page *p,
-					  enum ttm_caching_state c_old,
-					  enum ttm_caching_state c_new)
+static int ttm_tt_set_page_caching(struct page *p,
+				   enum ttm_caching_state c_old,
+				   enum ttm_caching_state c_new)
 {
 	int ret = 0;
 
@@ -129,26 +126,18 @@ static inline int ttm_tt_set_page_caching(struct page *p,
 		/* p isn't in the default caching state, set it to
 		 * writeback first to free its current memtype. */
 
-		ret = set_pages_wb(p, 1);
+		ret = ttm_set_pages_wb(p, 1);
 		if (ret)
 			return ret;
 	}
 
 	if (c_new == tt_wc)
-		ret = set_memory_wc((unsigned long) page_address(p), 1);
+		ret = ttm_set_pages_wc(p, 1);
 	else if (c_new == tt_uncached)
-		ret = set_pages_uc(p, 1);
+		ret = ttm_set_pages_uc(p, 1);
 
 	return ret;
 }
-#else /* CONFIG_X86 */
-static inline int ttm_tt_set_page_caching(struct page *p,
-					  enum ttm_caching_state c_old,
-					  enum ttm_caching_state c_new)
-{
-	return 0;
-}
-#endif /* CONFIG_X86 */
 
 /*
  * Change caching policy for the linear kernel map
diff --git a/drivers/gpu/drm/udl/udl_connector.c b/drivers/gpu/drm/udl/udl_connector.c
index 09dc585aa46f..68e88bed77ca 100644
--- a/drivers/gpu/drm/udl/udl_connector.c
+++ b/drivers/gpu/drm/udl/udl_connector.c
@@ -99,7 +99,7 @@ static int udl_get_modes(struct drm_connector *connector)
 					struct udl_drm_connector,
 					connector);
 
-	drm_mode_connector_update_edid_property(connector, udl_connector->edid);
+	drm_connector_update_edid_property(connector, udl_connector->edid);
 	if (udl_connector->edid)
 		return drm_add_edid_modes(connector, udl_connector->edid);
 	return 0;
@@ -200,7 +200,7 @@ int udl_connector_init(struct drm_device *dev, struct drm_encoder *encoder)
 	drm_connector_helper_add(connector, &udl_connector_helper_funcs);
 
 	drm_connector_register(connector);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	connector->polled = DRM_CONNECTOR_POLL_HPD |
 		DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT;
 
diff --git a/drivers/gpu/drm/udl/udl_dmabuf.c b/drivers/gpu/drm/udl/udl_dmabuf.c
index 0a20695eb120..556f62662aa9 100644
--- a/drivers/gpu/drm/udl/udl_dmabuf.c
+++ b/drivers/gpu/drm/udl/udl_dmabuf.c
@@ -29,7 +29,6 @@ struct udl_drm_dmabuf_attachment {
 };
 
 static int udl_attach_dma_buf(struct dma_buf *dmabuf,
-			      struct device *dev,
 			      struct dma_buf_attachment *attach)
 {
 	struct udl_drm_dmabuf_attachment *udl_attach;
@@ -158,27 +157,12 @@ static void *udl_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num)
 	return NULL;
 }
 
-static void *udl_dmabuf_kmap_atomic(struct dma_buf *dma_buf,
-				    unsigned long page_num)
-{
-	/* TODO */
-
-	return NULL;
-}
-
 static void udl_dmabuf_kunmap(struct dma_buf *dma_buf,
 			      unsigned long page_num, void *addr)
 {
 	/* TODO */
 }
 
-static void udl_dmabuf_kunmap_atomic(struct dma_buf *dma_buf,
-				     unsigned long page_num,
-				     void *addr)
-{
-	/* TODO */
-}
-
 static int udl_dmabuf_mmap(struct dma_buf *dma_buf,
 			   struct vm_area_struct *vma)
 {
@@ -193,9 +177,7 @@ static const struct dma_buf_ops udl_dmabuf_ops = {
 	.map_dma_buf		= udl_map_dma_buf,
 	.unmap_dma_buf		= udl_unmap_dma_buf,
 	.map			= udl_dmabuf_kmap,
-	.map_atomic		= udl_dmabuf_kmap_atomic,
 	.unmap			= udl_dmabuf_kunmap,
-	.unmap_atomic		= udl_dmabuf_kunmap_atomic,
 	.mmap			= udl_dmabuf_mmap,
 	.release		= drm_gem_dmabuf_release,
 };
diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h
index 55c0cc309198..e9e9b1ff678e 100644
--- a/drivers/gpu/drm/udl/udl_drv.h
+++ b/drivers/gpu/drm/udl/udl_drv.h
@@ -16,6 +16,7 @@
 
 #include <linux/usb.h>
 #include <drm/drm_gem.h>
+#include <linux/mm_types.h>
 
 #define DRIVER_NAME		"udl"
 #define DRIVER_DESC		"DisplayLink"
@@ -112,7 +113,7 @@ udl_fb_user_fb_create(struct drm_device *dev,
 		      struct drm_file *file,
 		      const struct drm_mode_fb_cmd2 *mode_cmd);
 
-int udl_render_hline(struct drm_device *dev, int bpp, struct urb **urb_ptr,
+int udl_render_hline(struct drm_device *dev, int log_bpp, struct urb **urb_ptr,
 		     const char *front, char **urb_buf_ptr,
 		     u32 byte_offset, u32 device_byte_offset, u32 byte_width,
 		     int *ident_ptr, int *sent_ptr);
@@ -136,7 +137,7 @@ void udl_gem_put_pages(struct udl_gem_object *obj);
 int udl_gem_vmap(struct udl_gem_object *obj);
 void udl_gem_vunmap(struct udl_gem_object *obj);
 int udl_drm_gem_mmap(struct file *filp, struct vm_area_struct *vma);
-int udl_gem_fault(struct vm_fault *vmf);
+vm_fault_t udl_gem_fault(struct vm_fault *vmf);
 
 int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
 		      int width, int height);
diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c
index d5583190f3e4..dbb62f6eb48a 100644
--- a/drivers/gpu/drm/udl/udl_fb.c
+++ b/drivers/gpu/drm/udl/udl_fb.c
@@ -90,7 +90,10 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
 	int bytes_identical = 0;
 	struct urb *urb;
 	int aligned_x;
-	int bpp = fb->base.format->cpp[0];
+	int log_bpp;
+
+	BUG_ON(!is_power_of_2(fb->base.format->cpp[0]));
+	log_bpp = __ffs(fb->base.format->cpp[0]);
 
 	if (!fb->active_16)
 		return 0;
@@ -125,12 +128,12 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
 
 	for (i = y; i < y + height ; i++) {
 		const int line_offset = fb->base.pitches[0] * i;
-		const int byte_offset = line_offset + (x * bpp);
-		const int dev_byte_offset = (fb->base.width * bpp * i) + (x * bpp);
-		if (udl_render_hline(dev, bpp, &urb,
+		const int byte_offset = line_offset + (x << log_bpp);
+		const int dev_byte_offset = (fb->base.width * i + x) << log_bpp;
+		if (udl_render_hline(dev, log_bpp, &urb,
 				     (char *) fb->obj->vmapping,
 				     &cmd, byte_offset, dev_byte_offset,
-				     width * bpp,
+				     width << log_bpp,
 				     &bytes_identical, &bytes_sent))
 			goto error;
 	}
@@ -149,7 +152,7 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
 error:
 	atomic_add(bytes_sent, &udl->bytes_sent);
 	atomic_add(bytes_identical, &udl->bytes_identical);
-	atomic_add(width*height*bpp, &udl->bytes_rendered);
+	atomic_add((width * height) << log_bpp, &udl->bytes_rendered);
 	end_cycles = get_cycles();
 	atomic_add(((unsigned int) ((end_cycles - start_cycles)
 		    >> 10)), /* Kcycles */
@@ -175,7 +178,7 @@ static int udl_fb_mmap(struct fb_info *info, struct vm_area_struct *vma)
 
 	pos = (unsigned long)info->fix.smem_start + offset;
 
-	pr_notice("mmap() framebuffer addr:%lu size:%lu\n",
+	pr_debug("mmap() framebuffer addr:%lu size:%lu\n",
 		  pos, size);
 
 	/* We don't want the framebuffer to be mapped encrypted */
@@ -221,7 +224,7 @@ static int udl_fb_open(struct fb_info *info, int user)
 
 		struct fb_deferred_io *fbdefio;
 
-		fbdefio = kmalloc(sizeof(struct fb_deferred_io), GFP_KERNEL);
+		fbdefio = kzalloc(sizeof(struct fb_deferred_io), GFP_KERNEL);
 
 		if (fbdefio) {
 			fbdefio->delay = DL_DEFIO_WRITE_DELAY;
@@ -233,7 +236,7 @@ static int udl_fb_open(struct fb_info *info, int user)
 	}
 #endif
 
-	pr_notice("open /dev/fb%d user=%d fb_info=%p count=%d\n",
+	pr_debug("open /dev/fb%d user=%d fb_info=%p count=%d\n",
 		  info->node, user, info, ufbdev->fb_count);
 
 	return 0;
@@ -258,7 +261,7 @@ static int udl_fb_release(struct fb_info *info, int user)
 	}
 #endif
 
-	pr_warn("released /dev/fb%d user=%d count=%d\n",
+	pr_debug("released /dev/fb%d user=%d count=%d\n",
 		info->node, user, ufbdev->fb_count);
 
 	return 0;
diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c
index 9a15cce22cce..d5a23295dd80 100644
--- a/drivers/gpu/drm/udl/udl_gem.c
+++ b/drivers/gpu/drm/udl/udl_gem.c
@@ -100,13 +100,12 @@ int udl_drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 	return ret;
 }
 
-int udl_gem_fault(struct vm_fault *vmf)
+vm_fault_t udl_gem_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct udl_gem_object *obj = to_udl_bo(vma->vm_private_data);
 	struct page *page;
 	unsigned int page_offset;
-	int ret = 0;
 
 	page_offset = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
 
@@ -114,17 +113,7 @@ int udl_gem_fault(struct vm_fault *vmf)
 		return VM_FAULT_SIGBUS;
 
 	page = obj->pages[page_offset];
-	ret = vm_insert_page(vma, vmf->address, page);
-	switch (ret) {
-	case -EAGAIN:
-	case 0:
-	case -ERESTARTSYS:
-		return VM_FAULT_NOPAGE;
-	case -ENOMEM:
-		return VM_FAULT_OOM;
-	default:
-		return VM_FAULT_SIGBUS;
-	}
+	return vmf_insert_page(vma, vmf->address, page);
 }
 
 int udl_gem_get_pages(struct udl_gem_object *obj)
diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c
index d518de8f496b..f455f095a146 100644
--- a/drivers/gpu/drm/udl/udl_main.c
+++ b/drivers/gpu/drm/udl/udl_main.c
@@ -170,25 +170,19 @@ static void udl_free_urb_list(struct drm_device *dev)
 	struct list_head *node;
 	struct urb_node *unode;
 	struct urb *urb;
-	int ret;
-	unsigned long flags;
 
 	DRM_DEBUG("Waiting for completes and freeing all render urbs\n");
 
 	/* keep waiting and freeing, until we've got 'em all */
 	while (count--) {
+		down(&udl->urbs.limit_sem);
 
-		/* Getting interrupted means a leak, but ok at shutdown*/
-		ret = down_interruptible(&udl->urbs.limit_sem);
-		if (ret)
-			break;
-
-		spin_lock_irqsave(&udl->urbs.lock, flags);
+		spin_lock_irq(&udl->urbs.lock);
 
 		node = udl->urbs.list.next; /* have reserved one with sem */
 		list_del_init(node);
 
-		spin_unlock_irqrestore(&udl->urbs.lock, flags);
+		spin_unlock_irq(&udl->urbs.lock);
 
 		unode = list_entry(node, struct urb_node, entry);
 		urb = unode->urb;
@@ -205,17 +199,22 @@ static void udl_free_urb_list(struct drm_device *dev)
 static int udl_alloc_urb_list(struct drm_device *dev, int count, size_t size)
 {
 	struct udl_device *udl = dev->dev_private;
-	int i = 0;
 	struct urb *urb;
 	struct urb_node *unode;
 	char *buf;
+	size_t wanted_size = count * size;
 
 	spin_lock_init(&udl->urbs.lock);
 
+retry:
 	udl->urbs.size = size;
 	INIT_LIST_HEAD(&udl->urbs.list);
 
-	while (i < count) {
+	sema_init(&udl->urbs.limit_sem, 0);
+	udl->urbs.count = 0;
+	udl->urbs.available = 0;
+
+	while (udl->urbs.count * size < wanted_size) {
 		unode = kzalloc(sizeof(struct urb_node), GFP_KERNEL);
 		if (!unode)
 			break;
@@ -231,11 +230,16 @@ static int udl_alloc_urb_list(struct drm_device *dev, int count, size_t size)
 		}
 		unode->urb = urb;
 
-		buf = usb_alloc_coherent(udl->udev, MAX_TRANSFER, GFP_KERNEL,
+		buf = usb_alloc_coherent(udl->udev, size, GFP_KERNEL,
 					 &urb->transfer_dma);
 		if (!buf) {
 			kfree(unode);
 			usb_free_urb(urb);
+			if (size > PAGE_SIZE) {
+				size /= 2;
+				udl_free_urb_list(dev);
+				goto retry;
+			}
 			break;
 		}
 
@@ -246,16 +250,14 @@ static int udl_alloc_urb_list(struct drm_device *dev, int count, size_t size)
 
 		list_add_tail(&unode->entry, &udl->urbs.list);
 
-		i++;
+		up(&udl->urbs.limit_sem);
+		udl->urbs.count++;
+		udl->urbs.available++;
 	}
 
-	sema_init(&udl->urbs.limit_sem, i);
-	udl->urbs.count = i;
-	udl->urbs.available = i;
-
-	DRM_DEBUG("allocated %d %d byte urbs\n", i, (int) size);
+	DRM_DEBUG("allocated %d %d byte urbs\n", udl->urbs.count, (int) size);
 
-	return i;
+	return udl->urbs.count;
 }
 
 struct urb *udl_get_urb(struct drm_device *dev)
@@ -265,7 +267,6 @@ struct urb *udl_get_urb(struct drm_device *dev)
 	struct list_head *entry;
 	struct urb_node *unode;
 	struct urb *urb = NULL;
-	unsigned long flags;
 
 	/* Wait for an in-flight buffer to complete and get re-queued */
 	ret = down_timeout(&udl->urbs.limit_sem, GET_URB_TIMEOUT);
@@ -276,14 +277,14 @@ struct urb *udl_get_urb(struct drm_device *dev)
 		goto error;
 	}
 
-	spin_lock_irqsave(&udl->urbs.lock, flags);
+	spin_lock_irq(&udl->urbs.lock);
 
 	BUG_ON(list_empty(&udl->urbs.list)); /* reserved one with limit_sem */
 	entry = udl->urbs.list.next;
 	list_del_init(entry);
 	udl->urbs.available--;
 
-	spin_unlock_irqrestore(&udl->urbs.lock, flags);
+	spin_unlock_irq(&udl->urbs.lock);
 
 	unode = list_entry(entry, struct urb_node, entry);
 	urb = unode->urb;
diff --git a/drivers/gpu/drm/udl/udl_modeset.c b/drivers/gpu/drm/udl/udl_modeset.c
index 5bcae7649795..7e37765cf5ac 100644
--- a/drivers/gpu/drm/udl/udl_modeset.c
+++ b/drivers/gpu/drm/udl/udl_modeset.c
@@ -243,7 +243,7 @@ static int udl_crtc_write_mode_to_hw(struct drm_crtc *crtc)
 
 	memcpy(buf, udl->mode_buf, udl->mode_buf_len);
 	retval = udl_submit_urb(dev, urb, udl->mode_buf_len);
-	DRM_INFO("write mode info %d\n", udl->mode_buf_len);
+	DRM_DEBUG("write mode info %d\n", udl->mode_buf_len);
 	return retval;
 }
 
@@ -366,7 +366,6 @@ static int udl_crtc_page_flip(struct drm_crtc *crtc,
 {
 	struct udl_framebuffer *ufb = to_udl_fb(fb);
 	struct drm_device *dev = crtc->dev;
-	unsigned long flags;
 
 	struct drm_framebuffer *old_fb = crtc->primary->fb;
 	if (old_fb) {
@@ -377,10 +376,10 @@ static int udl_crtc_page_flip(struct drm_crtc *crtc,
 
 	udl_handle_damage(ufb, 0, 0, fb->width, fb->height);
 
-	spin_lock_irqsave(&dev->event_lock, flags);
+	spin_lock_irq(&dev->event_lock);
 	if (event)
 		drm_crtc_send_vblank_event(crtc, event);
-	spin_unlock_irqrestore(&dev->event_lock, flags);
+	spin_unlock_irq(&dev->event_lock);
 	crtc->primary->fb = fb;
 
 	return 0;
diff --git a/drivers/gpu/drm/udl/udl_transfer.c b/drivers/gpu/drm/udl/udl_transfer.c
index b992644c17e6..ce87661e544f 100644
--- a/drivers/gpu/drm/udl/udl_transfer.c
+++ b/drivers/gpu/drm/udl/udl_transfer.c
@@ -13,7 +13,6 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/fb.h>
-#include <linux/prefetch.h>
 #include <asm/unaligned.h>
 
 #include <drm/drmP.h>
@@ -51,9 +50,6 @@ static int udl_trim_hline(const u8 *bback, const u8 **bfront, int *width_bytes)
 	int start = width;
 	int end = width;
 
-	prefetch((void *) front);
-	prefetch((void *) back);
-
 	for (j = 0; j < width; j++) {
 		if (back[j] != front[j]) {
 			start = j;
@@ -83,12 +79,12 @@ static inline u16 pixel32_to_be16(const uint32_t pixel)
 		((pixel >> 8) & 0xf800));
 }
 
-static inline u16 get_pixel_val16(const uint8_t *pixel, int bpp)
+static inline u16 get_pixel_val16(const uint8_t *pixel, int log_bpp)
 {
-	u16 pixel_val16 = 0;
-	if (bpp == 2)
+	u16 pixel_val16;
+	if (log_bpp == 1)
 		pixel_val16 = *(const uint16_t *)pixel;
-	else if (bpp == 4)
+	else
 		pixel_val16 = pixel32_to_be16(*(const uint32_t *)pixel);
 	return pixel_val16;
 }
@@ -125,8 +121,9 @@ static void udl_compress_hline16(
 	const u8 *const pixel_end,
 	uint32_t *device_address_ptr,
 	uint8_t **command_buffer_ptr,
-	const uint8_t *const cmd_buffer_end, int bpp)
+	const uint8_t *const cmd_buffer_end, int log_bpp)
 {
+	const int bpp = 1 << log_bpp;
 	const u8 *pixel = *pixel_start_ptr;
 	uint32_t dev_addr  = *device_address_ptr;
 	uint8_t *cmd = *command_buffer_ptr;
@@ -139,8 +136,6 @@ static void udl_compress_hline16(
 		const u8 *cmd_pixel_start, *cmd_pixel_end = NULL;
 		uint16_t pixel_val16;
 
-		prefetchw((void *) cmd); /* pull in one cache line at least */
-
 		*cmd++ = 0xaf;
 		*cmd++ = 0x6b;
 		*cmd++ = (uint8_t) ((dev_addr >> 16) & 0xFF);
@@ -153,12 +148,11 @@ static void udl_compress_hline16(
 		raw_pixels_count_byte = cmd++; /*  we'll know this later */
 		raw_pixel_start = pixel;
 
-		cmd_pixel_end = pixel + min3(MAX_CMD_PIXELS + 1UL,
-					(unsigned long)(pixel_end - pixel) / bpp,
-					(unsigned long)(cmd_buffer_end - 1 - cmd) / 2) * bpp;
+		cmd_pixel_end = pixel + (min3(MAX_CMD_PIXELS + 1UL,
+					(unsigned long)(pixel_end - pixel) >> log_bpp,
+					(unsigned long)(cmd_buffer_end - 1 - cmd) / 2) << log_bpp);
 
-		prefetch_range((void *) pixel, cmd_pixel_end - pixel);
-		pixel_val16 = get_pixel_val16(pixel, bpp);
+		pixel_val16 = get_pixel_val16(pixel, log_bpp);
 
 		while (pixel < cmd_pixel_end) {
 			const u8 *const start = pixel;
@@ -170,7 +164,7 @@ static void udl_compress_hline16(
 			pixel += bpp;
 
 			while (pixel < cmd_pixel_end) {
-				pixel_val16 = get_pixel_val16(pixel, bpp);
+				pixel_val16 = get_pixel_val16(pixel, log_bpp);
 				if (pixel_val16 != repeating_pixel_val16)
 					break;
 				pixel += bpp;
@@ -179,10 +173,10 @@ static void udl_compress_hline16(
 			if (unlikely(pixel > start + bpp)) {
 				/* go back and fill in raw pixel count */
 				*raw_pixels_count_byte = (((start -
-						raw_pixel_start) / bpp) + 1) & 0xFF;
+						raw_pixel_start) >> log_bpp) + 1) & 0xFF;
 
 				/* immediately after raw data is repeat byte */
-				*cmd++ = (((pixel - start) / bpp) - 1) & 0xFF;
+				*cmd++ = (((pixel - start) >> log_bpp) - 1) & 0xFF;
 
 				/* Then start another raw pixel span */
 				raw_pixel_start = pixel;
@@ -192,14 +186,14 @@ static void udl_compress_hline16(
 
 		if (pixel > raw_pixel_start) {
 			/* finalize last RAW span */
-			*raw_pixels_count_byte = ((pixel-raw_pixel_start) / bpp) & 0xFF;
+			*raw_pixels_count_byte = ((pixel - raw_pixel_start) >> log_bpp) & 0xFF;
 		} else {
 			/* undo unused byte */
 			cmd--;
 		}
 
-		*cmd_pixels_count_byte = ((pixel - cmd_pixel_start) / bpp) & 0xFF;
-		dev_addr += ((pixel - cmd_pixel_start) / bpp) * 2;
+		*cmd_pixels_count_byte = ((pixel - cmd_pixel_start) >> log_bpp) & 0xFF;
+		dev_addr += ((pixel - cmd_pixel_start) >> log_bpp) * 2;
 	}
 
 	if (cmd_buffer_end <= MIN_RLX_CMD_BYTES + cmd) {
@@ -222,19 +216,19 @@ static void udl_compress_hline16(
  * (that we can only write to, slowly, and can never read), and (optionally)
  * our shadow copy that tracks what's been sent to that hardware buffer.
  */
-int udl_render_hline(struct drm_device *dev, int bpp, struct urb **urb_ptr,
+int udl_render_hline(struct drm_device *dev, int log_bpp, struct urb **urb_ptr,
 		     const char *front, char **urb_buf_ptr,
 		     u32 byte_offset, u32 device_byte_offset,
 		     u32 byte_width,
 		     int *ident_ptr, int *sent_ptr)
 {
 	const u8 *line_start, *line_end, *next_pixel;
-	u32 base16 = 0 + (device_byte_offset / bpp) * 2;
+	u32 base16 = 0 + (device_byte_offset >> log_bpp) * 2;
 	struct urb *urb = *urb_ptr;
 	u8 *cmd = *urb_buf_ptr;
 	u8 *cmd_end = (u8 *) urb->transfer_buffer + urb->transfer_buffer_length;
 
-	BUG_ON(!(bpp == 2 || bpp == 4));
+	BUG_ON(!(log_bpp == 1 || log_bpp == 2));
 
 	line_start = (u8 *) (front + byte_offset);
 	next_pixel = line_start;
@@ -244,7 +238,7 @@ int udl_render_hline(struct drm_device *dev, int bpp, struct urb **urb_ptr,
 
 		udl_compress_hline16(&next_pixel,
 			     line_end, &base16,
-			     (u8 **) &cmd, (u8 *) cmd_end, bpp);
+			     (u8 **) &cmd, (u8 *) cmd_end, log_bpp);
 
 		if (cmd >= cmd_end) {
 			int len = cmd - (u8 *) urb->transfer_buffer;
diff --git a/drivers/gpu/drm/v3d/v3d_bo.c b/drivers/gpu/drm/v3d/v3d_bo.c
index 7b1e2a549a71..54d96518a131 100644
--- a/drivers/gpu/drm/v3d/v3d_bo.c
+++ b/drivers/gpu/drm/v3d/v3d_bo.c
@@ -227,37 +227,19 @@ v3d_set_mmap_vma_flags(struct vm_area_struct *vma)
 	vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
 }
 
-int v3d_gem_fault(struct vm_fault *vmf)
+vm_fault_t v3d_gem_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_gem_object *obj = vma->vm_private_data;
 	struct v3d_bo *bo = to_v3d_bo(obj);
-	unsigned long pfn;
+	pfn_t pfn;
 	pgoff_t pgoff;
-	int ret;
 
 	/* We don't use vmf->pgoff since that has the fake offset: */
 	pgoff = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
-	pfn = page_to_pfn(bo->pages[pgoff]);
-
-	ret = vm_insert_mixed(vma, vmf->address, __pfn_to_pfn_t(pfn, PFN_DEV));
-
-	switch (ret) {
-	case -EAGAIN:
-	case 0:
-	case -ERESTARTSYS:
-	case -EINTR:
-	case -EBUSY:
-		/*
-		 * EBUSY is ok: this just means that another thread
-		 * already did the job.
-		 */
-		return VM_FAULT_NOPAGE;
-	case -ENOMEM:
-		return VM_FAULT_OOM;
-	default:
-		return VM_FAULT_SIGBUS;
-	}
+	pfn = __pfn_to_pfn_t(page_to_pfn(bo->pages[pgoff]), PFN_DEV);
+
+	return vmf_insert_mixed(vma, vmf->address, pfn);
 }
 
 int v3d_mmap(struct file *filp, struct vm_area_struct *vma)
diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c
index cdb582043b4f..2a85fa68ffea 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.c
+++ b/drivers/gpu/drm/v3d/v3d_drv.c
@@ -123,6 +123,7 @@ v3d_open(struct drm_device *dev, struct drm_file *file)
 {
 	struct v3d_dev *v3d = to_v3d_dev(dev);
 	struct v3d_file_priv *v3d_priv;
+	struct drm_sched_rq *rq;
 	int i;
 
 	v3d_priv = kzalloc(sizeof(*v3d_priv), GFP_KERNEL);
@@ -132,10 +133,8 @@ v3d_open(struct drm_device *dev, struct drm_file *file)
 	v3d_priv->v3d = v3d;
 
 	for (i = 0; i < V3D_MAX_QUEUES; i++) {
-		drm_sched_entity_init(&v3d->queue[i].sched,
-				      &v3d_priv->sched_entity[i],
-				      &v3d->queue[i].sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL],
-				      NULL);
+		rq = &v3d->queue[i].sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
+		drm_sched_entity_init(&v3d_priv->sched_entity[i], &rq, 1, NULL);
 	}
 
 	file->driver_priv = v3d_priv;
@@ -146,13 +145,11 @@ v3d_open(struct drm_device *dev, struct drm_file *file)
 static void
 v3d_postclose(struct drm_device *dev, struct drm_file *file)
 {
-	struct v3d_dev *v3d = to_v3d_dev(dev);
 	struct v3d_file_priv *v3d_priv = file->driver_priv;
 	enum v3d_queue q;
 
 	for (q = 0; q < V3D_MAX_QUEUES; q++) {
-		drm_sched_entity_fini(&v3d->queue[q].sched,
-				      &v3d_priv->sched_entity[q]);
+		drm_sched_entity_destroy(&v3d_priv->sched_entity[q]);
 	}
 
 	kfree(v3d_priv);
diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index a043ac3aae98..e6fed696ad86 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -2,6 +2,7 @@
 /* Copyright (C) 2015-2018 Broadcom */
 
 #include <linux/reservation.h>
+#include <linux/mm_types.h>
 #include <drm/drmP.h>
 #include <drm/drm_encoder.h>
 #include <drm/drm_gem.h>
@@ -25,7 +26,6 @@ struct v3d_queue_state {
 
 	u64 fence_context;
 	u64 emit_seqno;
-	u64 finished_seqno;
 };
 
 struct v3d_dev {
@@ -85,6 +85,11 @@ struct v3d_dev {
 	 */
 	struct mutex reset_lock;
 
+	/* Lock taken when creating and pushing the GPU scheduler
+	 * jobs, to keep the sched-fence seqnos in order.
+	 */
+	struct mutex sched_lock;
+
 	struct {
 		u32 num_allocated;
 		u32 pages_allocated;
@@ -179,6 +184,8 @@ struct v3d_job {
 
 	/* GPU virtual addresses of the start/end of the CL job. */
 	u32 start, end;
+
+	u32 timedout_ctca, timedout_ctra;
 };
 
 struct v3d_exec_info {
@@ -248,7 +255,7 @@ int v3d_mmap_bo_ioctl(struct drm_device *dev, void *data,
 		      struct drm_file *file_priv);
 int v3d_get_bo_offset_ioctl(struct drm_device *dev, void *data,
 			    struct drm_file *file_priv);
-int v3d_gem_fault(struct vm_fault *vmf);
+vm_fault_t v3d_gem_fault(struct vm_fault *vmf);
 int v3d_mmap(struct file *filp, struct vm_area_struct *vma);
 struct reservation_object *v3d_prime_res_obj(struct drm_gem_object *obj);
 int v3d_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
diff --git a/drivers/gpu/drm/v3d/v3d_fence.c b/drivers/gpu/drm/v3d/v3d_fence.c
index 087d49c8cb12..50bfcf9a8a1a 100644
--- a/drivers/gpu/drm/v3d/v3d_fence.c
+++ b/drivers/gpu/drm/v3d/v3d_fence.c
@@ -35,24 +35,7 @@ static const char *v3d_fence_get_timeline_name(struct dma_fence *fence)
 		return "v3d-render";
 }
 
-static bool v3d_fence_enable_signaling(struct dma_fence *fence)
-{
-	return true;
-}
-
-static bool v3d_fence_signaled(struct dma_fence *fence)
-{
-	struct v3d_fence *f = to_v3d_fence(fence);
-	struct v3d_dev *v3d = to_v3d_dev(f->dev);
-
-	return v3d->queue[f->queue].finished_seqno >= f->seqno;
-}
-
 const struct dma_fence_ops v3d_fence_ops = {
 	.get_driver_name = v3d_fence_get_driver_name,
 	.get_timeline_name = v3d_fence_get_timeline_name,
-	.enable_signaling = v3d_fence_enable_signaling,
-	.signaled = v3d_fence_signaled,
-	.wait = dma_fence_default_wait,
-	.release = dma_fence_free,
 };
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index b513f9189caf..5ce24098a5fd 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -550,9 +550,9 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		goto fail;
 
+	mutex_lock(&v3d->sched_lock);
 	if (exec->bin.start != exec->bin.end) {
 		ret = drm_sched_job_init(&exec->bin.base,
-					 &v3d->queue[V3D_BIN].sched,
 					 &v3d_priv->sched_entity[V3D_BIN],
 					 v3d_priv);
 		if (ret)
@@ -567,7 +567,6 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	}
 
 	ret = drm_sched_job_init(&exec->render.base,
-				 &v3d->queue[V3D_RENDER].sched,
 				 &v3d_priv->sched_entity[V3D_RENDER],
 				 v3d_priv);
 	if (ret)
@@ -576,6 +575,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	kref_get(&exec->refcount); /* put by scheduler job completion */
 	drm_sched_entity_push_job(&exec->render.base,
 				  &v3d_priv->sched_entity[V3D_RENDER]);
+	mutex_unlock(&v3d->sched_lock);
 
 	v3d_attach_object_fences(exec);
 
@@ -594,6 +594,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	return 0;
 
 fail_unreserve:
+	mutex_unlock(&v3d->sched_lock);
 	v3d_unlock_bo_reservations(dev, exec, &acquire_ctx);
 fail:
 	v3d_exec_put(exec);
@@ -615,6 +616,7 @@ v3d_gem_init(struct drm_device *dev)
 	spin_lock_init(&v3d->job_lock);
 	mutex_init(&v3d->bo_lock);
 	mutex_init(&v3d->reset_lock);
+	mutex_init(&v3d->sched_lock);
 
 	/* Note: We don't allocate address 0.  Various bits of HW
 	 * treat 0 as special, such as the occlusion query counters
@@ -650,17 +652,14 @@ void
 v3d_gem_destroy(struct drm_device *dev)
 {
 	struct v3d_dev *v3d = to_v3d_dev(dev);
-	enum v3d_queue q;
 
 	v3d_sched_fini(v3d);
 
 	/* Waiting for exec to finish would need to be done before
 	 * unregistering V3D.
 	 */
-	for (q = 0; q < V3D_MAX_QUEUES; q++) {
-		WARN_ON(v3d->queue[q].emit_seqno !=
-			v3d->queue[q].finished_seqno);
-	}
+	WARN_ON(v3d->bin_job);
+	WARN_ON(v3d->render_job);
 
 	drm_mm_takedown(&v3d->mm);
 
diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c
index 77e1fa046c10..e07514eb11b5 100644
--- a/drivers/gpu/drm/v3d/v3d_irq.c
+++ b/drivers/gpu/drm/v3d/v3d_irq.c
@@ -87,15 +87,12 @@ v3d_irq(int irq, void *arg)
 	}
 
 	if (intsts & V3D_INT_FLDONE) {
-		v3d->queue[V3D_BIN].finished_seqno++;
 		dma_fence_signal(v3d->bin_job->bin.done_fence);
 		status = IRQ_HANDLED;
 	}
 
 	if (intsts & V3D_INT_FRDONE) {
-		v3d->queue[V3D_RENDER].finished_seqno++;
 		dma_fence_signal(v3d->render_job->render.done_fence);
-
 		status = IRQ_HANDLED;
 	}
 
diff --git a/drivers/gpu/drm/v3d/v3d_regs.h b/drivers/gpu/drm/v3d/v3d_regs.h
index fc13282dfc2f..854046565989 100644
--- a/drivers/gpu/drm/v3d/v3d_regs.h
+++ b/drivers/gpu/drm/v3d/v3d_regs.h
@@ -222,6 +222,7 @@
 #define V3D_CLE_CTNCA(n) (V3D_CLE_CT0CA + 4 * n)
 #define V3D_CLE_CT0RA                                  0x00118
 #define V3D_CLE_CT1RA                                  0x0011c
+#define V3D_CLE_CTNRA(n) (V3D_CLE_CT0RA + 4 * n)
 #define V3D_CLE_CT0LC                                  0x00120
 #define V3D_CLE_CT1LC                                  0x00124
 #define V3D_CLE_CT0PC                                  0x00128
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index b07bece9417d..a5501581d96b 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -14,8 +14,8 @@
  * to the HW only when it has completed the last one, instead of
  * filling up the CT[01]Q FIFOs with jobs.  Similarly, we use
  * v3d_job_dependency() to manage the dependency between bin and
- * render, instead of having the clients submit jobs with using the
- * HW's semaphores to interlock between them.
+ * render, instead of having the clients submit jobs using the HW's
+ * semaphores to interlock between them.
  */
 
 #include <linux/kthread.h>
@@ -114,8 +114,8 @@ static struct dma_fence *v3d_job_run(struct drm_sched_job *sched_job)
 	v3d_invalidate_caches(v3d);
 
 	fence = v3d_fence_create(v3d, q);
-	if (!fence)
-		return fence;
+	if (IS_ERR(fence))
+		return NULL;
 
 	if (job->done_fence)
 		dma_fence_put(job->done_fence);
@@ -153,7 +153,25 @@ v3d_job_timedout(struct drm_sched_job *sched_job)
 	struct v3d_job *job = to_v3d_job(sched_job);
 	struct v3d_exec_info *exec = job->exec;
 	struct v3d_dev *v3d = exec->v3d;
+	enum v3d_queue job_q = job == &exec->bin ? V3D_BIN : V3D_RENDER;
 	enum v3d_queue q;
+	u32 ctca = V3D_CORE_READ(0, V3D_CLE_CTNCA(job_q));
+	u32 ctra = V3D_CORE_READ(0, V3D_CLE_CTNRA(job_q));
+
+	/* If the current address or return address have changed, then
+	 * the GPU has probably made progress and we should delay the
+	 * reset.  This could fail if the GPU got in an infinite loop
+	 * in the CL, but that is pretty unlikely outside of an i-g-t
+	 * testcase.
+	 */
+	if (job->timedout_ctca != ctca || job->timedout_ctra != ctra) {
+		job->timedout_ctca = ctca;
+		job->timedout_ctra = ctra;
+
+		schedule_delayed_work(&job->base.work_tdr,
+				      job->base.sched->timeout);
+		return;
+	}
 
 	mutex_lock(&v3d->reset_lock);
 
diff --git a/drivers/gpu/drm/vc4/Makefile b/drivers/gpu/drm/vc4/Makefile
index 4a3a868235f8..b303703bc7f3 100644
--- a/drivers/gpu/drm/vc4/Makefile
+++ b/drivers/gpu/drm/vc4/Makefile
@@ -19,6 +19,7 @@ vc4-y := \
 	vc4_plane.o \
 	vc4_render_cl.o \
 	vc4_trace_points.o \
+	vc4_txp.o \
 	vc4_v3d.o \
 	vc4_validate.o \
 	vc4_validate_shaders.o
diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index add9cc97a3b6..8dcce7182bb7 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -721,7 +721,7 @@ vc4_prime_export(struct drm_device *dev, struct drm_gem_object *obj, int flags)
 	return dmabuf;
 }
 
-int vc4_fault(struct vm_fault *vmf)
+vm_fault_t vc4_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_gem_object *obj = vma->vm_private_data;
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index c8650bbcbcb3..0e6a121858d1 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -46,6 +46,8 @@ struct vc4_crtc_state {
 	struct drm_crtc_state base;
 	/* Dlist area for this CRTC configuration. */
 	struct drm_mm_node mm;
+	bool feed_txp;
+	bool txp_armed;
 };
 
 static inline struct vc4_crtc_state *
@@ -324,10 +326,8 @@ static struct drm_encoder *vc4_get_crtc_encoder(struct drm_crtc *crtc)
 	return NULL;
 }
 
-static void vc4_crtc_mode_set_nofb(struct drm_crtc *crtc)
+static void vc4_crtc_config_pv(struct drm_crtc *crtc)
 {
-	struct drm_device *dev = crtc->dev;
-	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct drm_encoder *encoder = vc4_get_crtc_encoder(crtc);
 	struct vc4_encoder *vc4_encoder = to_vc4_encoder(encoder);
 	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
@@ -338,12 +338,6 @@ static void vc4_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	bool is_dsi = (vc4_encoder->type == VC4_ENCODER_TYPE_DSI0 ||
 		       vc4_encoder->type == VC4_ENCODER_TYPE_DSI1);
 	u32 format = is_dsi ? PV_CONTROL_FORMAT_DSIV_24 : PV_CONTROL_FORMAT_24;
-	bool debug_dump_regs = false;
-
-	if (debug_dump_regs) {
-		DRM_INFO("CRTC %d regs before:\n", drm_crtc_index(crtc));
-		vc4_crtc_dump_regs(vc4_crtc);
-	}
 
 	/* Reset the PV fifo. */
 	CRTC_WRITE(PV_CONTROL, 0);
@@ -419,6 +413,49 @@ static void vc4_crtc_mode_set_nofb(struct drm_crtc *crtc)
 				 PV_CONTROL_CLK_SELECT) |
 		   PV_CONTROL_FIFO_CLR |
 		   PV_CONTROL_EN);
+}
+
+static void vc4_crtc_mode_set_nofb(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
+	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state);
+	struct drm_display_mode *mode = &crtc->state->adjusted_mode;
+	bool interlace = mode->flags & DRM_MODE_FLAG_INTERLACE;
+	bool debug_dump_regs = false;
+
+	if (debug_dump_regs) {
+		DRM_INFO("CRTC %d regs before:\n", drm_crtc_index(crtc));
+		vc4_crtc_dump_regs(vc4_crtc);
+	}
+
+	if (vc4_crtc->channel == 2) {
+		u32 dispctrl;
+		u32 dsp3_mux;
+
+		/*
+		 * SCALER_DISPCTRL_DSP3 = X, where X < 2 means 'connect DSP3 to
+		 * FIFO X'.
+		 * SCALER_DISPCTRL_DSP3 = 3 means 'disable DSP 3'.
+		 *
+		 * DSP3 is connected to FIFO2 unless the transposer is
+		 * enabled. In this case, FIFO 2 is directly accessed by the
+		 * TXP IP, and we need to disable the FIFO2 -> pixelvalve1
+		 * route.
+		 */
+		if (vc4_state->feed_txp)
+			dsp3_mux = VC4_SET_FIELD(3, SCALER_DISPCTRL_DSP3_MUX);
+		else
+			dsp3_mux = VC4_SET_FIELD(2, SCALER_DISPCTRL_DSP3_MUX);
+
+		dispctrl = HVS_READ(SCALER_DISPCTRL) &
+			   ~SCALER_DISPCTRL_DSP3_MUX_MASK;
+		HVS_WRITE(SCALER_DISPCTRL, dispctrl | dsp3_mux);
+	}
+
+	if (!vc4_state->feed_txp)
+		vc4_crtc_config_pv(crtc);
 
 	HVS_WRITE(SCALER_DISPBKGNDX(vc4_crtc->channel),
 		  SCALER_DISPBKGND_AUTOHS |
@@ -499,6 +536,13 @@ static void vc4_crtc_atomic_disable(struct drm_crtc *crtc,
 	}
 }
 
+void vc4_crtc_txp_armed(struct drm_crtc_state *state)
+{
+	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(state);
+
+	vc4_state->txp_armed = true;
+}
+
 static void vc4_crtc_update_dlist(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
@@ -514,8 +558,11 @@ static void vc4_crtc_update_dlist(struct drm_crtc *crtc)
 		WARN_ON(drm_crtc_vblank_get(crtc) != 0);
 
 		spin_lock_irqsave(&dev->event_lock, flags);
-		vc4_crtc->event = crtc->state->event;
-		crtc->state->event = NULL;
+
+		if (!vc4_state->feed_txp || vc4_state->txp_armed) {
+			vc4_crtc->event = crtc->state->event;
+			crtc->state->event = NULL;
+		}
 
 		HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel),
 			  vc4_state->mm.start);
@@ -533,8 +580,8 @@ static void vc4_crtc_atomic_enable(struct drm_crtc *crtc,
 	struct drm_device *dev = crtc->dev;
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
-	struct drm_crtc_state *state = crtc->state;
-	struct drm_display_mode *mode = &state->adjusted_mode;
+	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state);
+	struct drm_display_mode *mode = &crtc->state->adjusted_mode;
 
 	require_hvs_enabled(dev);
 
@@ -546,15 +593,21 @@ static void vc4_crtc_atomic_enable(struct drm_crtc *crtc,
 
 	/* Turn on the scaler, which will wait for vstart to start
 	 * compositing.
+	 * When feeding the transposer, we should operate in oneshot
+	 * mode.
 	 */
 	HVS_WRITE(SCALER_DISPCTRLX(vc4_crtc->channel),
 		  VC4_SET_FIELD(mode->hdisplay, SCALER_DISPCTRLX_WIDTH) |
 		  VC4_SET_FIELD(mode->vdisplay, SCALER_DISPCTRLX_HEIGHT) |
-		  SCALER_DISPCTRLX_ENABLE);
+		  SCALER_DISPCTRLX_ENABLE |
+		  (vc4_state->feed_txp ? SCALER_DISPCTRLX_ONESHOT : 0));
 
-	/* Turn on the pixel valve, which will emit the vstart signal. */
-	CRTC_WRITE(PV_V_CONTROL,
-		   CRTC_READ(PV_V_CONTROL) | PV_VCONTROL_VIDEN);
+	/* When feeding the transposer block the pixelvalve is unneeded and
+	 * should not be enabled.
+	 */
+	if (!vc4_state->feed_txp)
+		CRTC_WRITE(PV_V_CONTROL,
+			   CRTC_READ(PV_V_CONTROL) | PV_VCONTROL_VIDEN);
 }
 
 static enum drm_mode_status vc4_crtc_mode_valid(struct drm_crtc *crtc,
@@ -579,8 +632,10 @@ static int vc4_crtc_atomic_check(struct drm_crtc *crtc,
 	struct drm_plane *plane;
 	unsigned long flags;
 	const struct drm_plane_state *plane_state;
+	struct drm_connector *conn;
+	struct drm_connector_state *conn_state;
 	u32 dlist_count = 0;
-	int ret;
+	int ret, i;
 
 	/* The pixelvalve can only feed one encoder (and encoders are
 	 * 1:1 with connectors.)
@@ -600,6 +655,24 @@ static int vc4_crtc_atomic_check(struct drm_crtc *crtc,
 	if (ret)
 		return ret;
 
+	for_each_new_connector_in_state(state->state, conn, conn_state, i) {
+		if (conn_state->crtc != crtc)
+			continue;
+
+		/* The writeback connector is implemented using the transposer
+		 * block which is directly taking its data from the HVS FIFO.
+		 */
+		if (conn->connector_type == DRM_MODE_CONNECTOR_WRITEBACK) {
+			state->no_vblank = true;
+			vc4_state->feed_txp = true;
+		} else {
+			state->no_vblank = false;
+			vc4_state->feed_txp = false;
+		}
+
+		break;
+	}
+
 	return 0;
 }
 
@@ -713,7 +786,8 @@ static void vc4_crtc_handle_page_flip(struct vc4_crtc *vc4_crtc)
 
 	spin_lock_irqsave(&dev->event_lock, flags);
 	if (vc4_crtc->event &&
-	    (vc4_state->mm.start == HVS_READ(SCALER_DISPLACTX(chan)))) {
+	    (vc4_state->mm.start == HVS_READ(SCALER_DISPLACTX(chan)) ||
+	     vc4_state->feed_txp)) {
 		drm_crtc_send_vblank_event(crtc, vc4_crtc->event);
 		vc4_crtc->event = NULL;
 		drm_crtc_vblank_put(crtc);
@@ -721,6 +795,13 @@ static void vc4_crtc_handle_page_flip(struct vc4_crtc *vc4_crtc)
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 }
 
+void vc4_crtc_handle_vblank(struct vc4_crtc *crtc)
+{
+	crtc->t_vblank = ktime_get();
+	drm_crtc_handle_vblank(&crtc->base);
+	vc4_crtc_handle_page_flip(crtc);
+}
+
 static irqreturn_t vc4_crtc_irq_handler(int irq, void *data)
 {
 	struct vc4_crtc *vc4_crtc = data;
@@ -728,10 +809,8 @@ static irqreturn_t vc4_crtc_irq_handler(int irq, void *data)
 	irqreturn_t ret = IRQ_NONE;
 
 	if (stat & PV_INT_VFP_START) {
-		vc4_crtc->t_vblank = ktime_get();
 		CRTC_WRITE(PV_INTSTAT, PV_INT_VFP_START);
-		drm_crtc_handle_vblank(&vc4_crtc->base);
-		vc4_crtc_handle_page_flip(vc4_crtc);
+		vc4_crtc_handle_vblank(vc4_crtc);
 		ret = IRQ_HANDLED;
 	}
 
@@ -862,7 +941,6 @@ static int vc4_async_page_flip(struct drm_crtc *crtc,
 	 * is released.
 	 */
 	drm_atomic_set_fb_for_plane(plane->state, fb);
-	plane->fb = fb;
 
 	vc4_queue_seqno_cb(dev, &flip_state->cb, bo->seqno,
 			   vc4_async_page_flip_complete);
@@ -885,12 +963,15 @@ static int vc4_page_flip(struct drm_crtc *crtc,
 
 static struct drm_crtc_state *vc4_crtc_duplicate_state(struct drm_crtc *crtc)
 {
-	struct vc4_crtc_state *vc4_state;
+	struct vc4_crtc_state *vc4_state, *old_vc4_state;
 
 	vc4_state = kzalloc(sizeof(*vc4_state), GFP_KERNEL);
 	if (!vc4_state)
 		return NULL;
 
+	old_vc4_state = to_vc4_crtc_state(crtc->state);
+	vc4_state->feed_txp = old_vc4_state->feed_txp;
+
 	__drm_atomic_helper_crtc_duplicate_state(crtc, &vc4_state->base);
 	return &vc4_state->base;
 }
@@ -988,9 +1069,17 @@ static void vc4_set_crtc_possible_masks(struct drm_device *drm,
 	struct drm_encoder *encoder;
 
 	drm_for_each_encoder(encoder, drm) {
-		struct vc4_encoder *vc4_encoder = to_vc4_encoder(encoder);
+		struct vc4_encoder *vc4_encoder;
 		int i;
 
+		/* HVS FIFO2 can feed the TXP IP. */
+		if (crtc_data->hvs_channel == 2 &&
+		    encoder->encoder_type == DRM_MODE_ENCODER_VIRTUAL) {
+			encoder->possible_crtcs |= drm_crtc_mask(crtc);
+			continue;
+		}
+
+		vc4_encoder = to_vc4_encoder(encoder);
 		for (i = 0; i < ARRAY_SIZE(crtc_data->encoder_types); i++) {
 			if (vc4_encoder->type == encoder_types[i]) {
 				vc4_encoder->clock_select = i;
@@ -1057,7 +1146,6 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data)
 	drm_crtc_init_with_planes(drm, crtc, primary_plane, NULL,
 				  &vc4_crtc_funcs, NULL);
 	drm_crtc_helper_add(crtc, &vc4_crtc_helper_funcs);
-	primary_plane->crtc = crtc;
 	vc4_crtc->channel = vc4_crtc->data->hvs_channel;
 	drm_mode_crtc_set_gamma_size(crtc, ARRAY_SIZE(vc4_crtc->lut_r));
 	drm_crtc_enable_color_mgmt(crtc, 0, false, crtc->gamma_size);
@@ -1083,7 +1171,7 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data)
 		if (IS_ERR(plane))
 			continue;
 
-		plane->possible_crtcs = 1 << drm_crtc_index(crtc);
+		plane->possible_crtcs = drm_crtc_mask(crtc);
 	}
 
 	/* Set up the legacy cursor after overlay initialization,
@@ -1092,8 +1180,7 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data)
 	 */
 	cursor_plane = vc4_plane_init(drm, DRM_PLANE_TYPE_CURSOR);
 	if (!IS_ERR(cursor_plane)) {
-		cursor_plane->possible_crtcs = 1 << drm_crtc_index(crtc);
-		cursor_plane->crtc = crtc;
+		cursor_plane->possible_crtcs = drm_crtc_mask(crtc);
 		crtc->cursor = cursor_plane;
 	}
 
@@ -1121,7 +1208,7 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data)
 err_destroy_planes:
 	list_for_each_entry_safe(destroy_plane, temp,
 				 &drm->mode_config.plane_list, head) {
-		if (destroy_plane->possible_crtcs == 1 << drm_crtc_index(crtc))
+		if (destroy_plane->possible_crtcs == drm_crtc_mask(crtc))
 		    destroy_plane->funcs->destroy(destroy_plane);
 	}
 err:
diff --git a/drivers/gpu/drm/vc4/vc4_debugfs.c b/drivers/gpu/drm/vc4/vc4_debugfs.c
index 5db06bdb5f27..7a0003de71ab 100644
--- a/drivers/gpu/drm/vc4/vc4_debugfs.c
+++ b/drivers/gpu/drm/vc4/vc4_debugfs.c
@@ -21,6 +21,7 @@ static const struct drm_info_list vc4_debugfs_list[] = {
 	{"dsi1_regs", vc4_dsi_debugfs_regs, 0, (void *)(uintptr_t)1},
 	{"hdmi_regs", vc4_hdmi_debugfs_regs, 0},
 	{"vec_regs", vc4_vec_debugfs_regs, 0},
+	{"txp_regs", vc4_txp_debugfs_regs, 0},
 	{"hvs_regs", vc4_hvs_debugfs_regs, 0},
 	{"crtc0_regs", vc4_crtc_debugfs_regs, 0, (void *)(uintptr_t)0},
 	{"crtc1_regs", vc4_crtc_debugfs_regs, 0, (void *)(uintptr_t)1},
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 466d0a27b415..04270a14fcaa 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -288,7 +288,7 @@ static int vc4_drm_bind(struct device *dev)
 
 	ret = vc4_bo_cache_init(drm);
 	if (ret)
-		goto dev_unref;
+		goto dev_put;
 
 	drm_mode_config_init(drm);
 
@@ -313,8 +313,8 @@ unbind_all:
 gem_destroy:
 	vc4_gem_destroy(drm);
 	vc4_bo_cache_destroy(drm);
-dev_unref:
-	drm_dev_unref(drm);
+dev_put:
+	drm_dev_put(drm);
 	return ret;
 }
 
@@ -331,7 +331,7 @@ static void vc4_drm_unbind(struct device *dev)
 
 	drm_atomic_private_obj_fini(&vc4->ctm_manager);
 
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 }
 
 static const struct component_master_ops vc4_drm_ops = {
@@ -344,6 +344,7 @@ static struct platform_driver *const component_drivers[] = {
 	&vc4_vec_driver,
 	&vc4_dpi_driver,
 	&vc4_dsi_driver,
+	&vc4_txp_driver,
 	&vc4_hvs_driver,
 	&vc4_crtc_driver,
 	&vc4_v3d_driver,
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 554a4e810d5b..bd6ef1f31822 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -6,6 +6,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/mm_types.h>
 #include <linux/reservation.h>
 #include <drm/drmP.h>
 #include <drm/drm_encoder.h>
@@ -72,6 +73,7 @@ struct vc4_dev {
 	struct vc4_dpi *dpi;
 	struct vc4_dsi *dsi1;
 	struct vc4_vec *vec;
+	struct vc4_txp *txp;
 
 	struct vc4_hang_state *hang_state;
 
@@ -674,7 +676,7 @@ int vc4_get_hang_state_ioctl(struct drm_device *dev, void *data,
 			     struct drm_file *file_priv);
 int vc4_label_bo_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv);
-int vc4_fault(struct vm_fault *vmf);
+vm_fault_t vc4_fault(struct vm_fault *vmf);
 int vc4_mmap(struct file *filp, struct vm_area_struct *vma);
 struct reservation_object *vc4_prime_res_obj(struct drm_gem_object *obj);
 int vc4_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
@@ -697,6 +699,8 @@ bool vc4_crtc_get_scanoutpos(struct drm_device *dev, unsigned int crtc_id,
 			     bool in_vblank_irq, int *vpos, int *hpos,
 			     ktime_t *stime, ktime_t *etime,
 			     const struct drm_display_mode *mode);
+void vc4_crtc_handle_vblank(struct vc4_crtc *crtc);
+void vc4_crtc_txp_armed(struct drm_crtc_state *state);
 
 /* vc4_debugfs.c */
 int vc4_debugfs_init(struct drm_minor *minor);
@@ -744,6 +748,10 @@ int vc4_hdmi_debugfs_regs(struct seq_file *m, void *unused);
 extern struct platform_driver vc4_vec_driver;
 int vc4_vec_debugfs_regs(struct seq_file *m, void *unused);
 
+/* vc4_txp.c */
+extern struct platform_driver vc4_txp_driver;
+int vc4_txp_debugfs_regs(struct seq_file *m, void *unused);
+
 /* vc4_irq.c */
 irqreturn_t vc4_irq(int irq, void *arg);
 void vc4_irq_preinstall(struct drm_device *dev);
diff --git a/drivers/gpu/drm/vc4/vc4_dsi.c b/drivers/gpu/drm/vc4/vc4_dsi.c
index 8aa897835118..0c607eb33d7e 100644
--- a/drivers/gpu/drm/vc4/vc4_dsi.c
+++ b/drivers/gpu/drm/vc4/vc4_dsi.c
@@ -814,7 +814,9 @@ static void vc4_dsi_encoder_disable(struct drm_encoder *encoder)
 	struct vc4_dsi *dsi = vc4_encoder->dsi;
 	struct device *dev = &dsi->pdev->dev;
 
+	drm_bridge_disable(dsi->bridge);
 	vc4_dsi_ulps(dsi, true);
+	drm_bridge_post_disable(dsi->bridge);
 
 	clk_disable_unprepare(dsi->pll_phy_clock);
 	clk_disable_unprepare(dsi->escape_clock);
@@ -1089,21 +1091,6 @@ static void vc4_dsi_encoder_enable(struct drm_encoder *encoder)
 	/* Display reset sequence timeout */
 	DSI_PORT_WRITE(PR_TO_CNT, 100000);
 
-	if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO) {
-		DSI_PORT_WRITE(DISP0_CTRL,
-			       VC4_SET_FIELD(dsi->divider,
-					     DSI_DISP0_PIX_CLK_DIV) |
-			       VC4_SET_FIELD(dsi->format, DSI_DISP0_PFORMAT) |
-			       VC4_SET_FIELD(DSI_DISP0_LP_STOP_PERFRAME,
-					     DSI_DISP0_LP_STOP_CTRL) |
-			       DSI_DISP0_ST_END |
-			       DSI_DISP0_ENABLE);
-	} else {
-		DSI_PORT_WRITE(DISP0_CTRL,
-			       DSI_DISP0_COMMAND_MODE |
-			       DSI_DISP0_ENABLE);
-	}
-
 	/* Set up DISP1 for transferring long command payloads through
 	 * the pixfifo.
 	 */
@@ -1128,6 +1115,25 @@ static void vc4_dsi_encoder_enable(struct drm_encoder *encoder)
 
 	vc4_dsi_ulps(dsi, false);
 
+	drm_bridge_pre_enable(dsi->bridge);
+
+	if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO) {
+		DSI_PORT_WRITE(DISP0_CTRL,
+			       VC4_SET_FIELD(dsi->divider,
+					     DSI_DISP0_PIX_CLK_DIV) |
+			       VC4_SET_FIELD(dsi->format, DSI_DISP0_PFORMAT) |
+			       VC4_SET_FIELD(DSI_DISP0_LP_STOP_PERFRAME,
+					     DSI_DISP0_LP_STOP_CTRL) |
+			       DSI_DISP0_ST_END |
+			       DSI_DISP0_ENABLE);
+	} else {
+		DSI_PORT_WRITE(DISP0_CTRL,
+			       DSI_DISP0_COMMAND_MODE |
+			       DSI_DISP0_ENABLE);
+	}
+
+	drm_bridge_enable(dsi->bridge);
+
 	if (debug_dump_regs) {
 		DRM_INFO("DSI regs after:\n");
 		vc4_dsi_dump_regs(dsi);
@@ -1606,8 +1612,18 @@ static int vc4_dsi_bind(struct device *dev, struct device *master, void *data)
 
 	ret = drm_of_find_panel_or_bridge(dev->of_node, 0, 0,
 					  &panel, &dsi->bridge);
-	if (ret)
+	if (ret) {
+		/* If the bridge or panel pointed by dev->of_node is not
+		 * enabled, just return 0 here so that we don't prevent the DRM
+		 * dev from being registered. Of course that means the DSI
+		 * encoder won't be exposed, but that's not a problem since
+		 * nothing is connected to it.
+		 */
+		if (ret == -ENODEV)
+			return 0;
+
 		return ret;
+	}
 
 	if (panel) {
 		dsi->bridge = devm_drm_panel_bridge_add(dev, panel,
@@ -1639,6 +1655,12 @@ static int vc4_dsi_bind(struct device *dev, struct device *master, void *data)
 		dev_err(dev, "bridge attach failed: %d\n", ret);
 		return ret;
 	}
+	/* Disable the atomic helper calls into the bridge.  We
+	 * manually call the bridge pre_enable / enable / etc. calls
+	 * from our driver, since we need to sequence them within the
+	 * encoder's enable/disable paths.
+	 */
+	dsi->encoder->bridge = NULL;
 
 	pm_runtime_enable(dev);
 
@@ -1652,7 +1674,8 @@ static void vc4_dsi_unbind(struct device *dev, struct device *master,
 	struct vc4_dev *vc4 = to_vc4_dev(drm);
 	struct vc4_dsi *dsi = dev_get_drvdata(dev);
 
-	pm_runtime_disable(dev);
+	if (dsi->bridge)
+		pm_runtime_disable(dev);
 
 	vc4_dsi_encoder_destroy(dsi->encoder);
 
diff --git a/drivers/gpu/drm/vc4/vc4_fence.c b/drivers/gpu/drm/vc4/vc4_fence.c
index dbf5a5a5d5f5..580214e2158c 100644
--- a/drivers/gpu/drm/vc4/vc4_fence.c
+++ b/drivers/gpu/drm/vc4/vc4_fence.c
@@ -33,11 +33,6 @@ static const char *vc4_fence_get_timeline_name(struct dma_fence *fence)
 	return "vc4-v3d";
 }
 
-static bool vc4_fence_enable_signaling(struct dma_fence *fence)
-{
-	return true;
-}
-
 static bool vc4_fence_signaled(struct dma_fence *fence)
 {
 	struct vc4_fence *f = to_vc4_fence(fence);
@@ -49,8 +44,5 @@ static bool vc4_fence_signaled(struct dma_fence *fence)
 const struct dma_fence_ops vc4_fence_ops = {
 	.get_driver_name = vc4_fence_get_driver_name,
 	.get_timeline_name = vc4_fence_get_timeline_name,
-	.enable_signaling = vc4_fence_enable_signaling,
 	.signaled = vc4_fence_signaled,
-	.wait = dma_fence_default_wait,
-	.release = dma_fence_free,
 };
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index b8d50533e2bb..fd5522fd179e 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -285,7 +285,7 @@ static int vc4_hdmi_connector_get_modes(struct drm_connector *connector)
 			drm_rgb_quant_range_selectable(edid);
 	}
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
 	kfree(edid);
 
@@ -329,7 +329,7 @@ static struct drm_connector *vc4_hdmi_connector_init(struct drm_device *dev,
 	connector->interlace_allowed = 1;
 	connector->doublescan_allowed = 0;
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return connector;
 }
diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index 8a411e5f8776..ca5aa7fba769 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -153,18 +153,11 @@ vc4_atomic_complete_commit(struct drm_atomic_state *state)
 
 	drm_atomic_helper_commit_modeset_enables(dev, state);
 
-	/* Make sure that drm_atomic_helper_wait_for_vblanks()
-	 * actually waits for vblank.  If we're doing a full atomic
-	 * modeset (as opposed to a vc4_update_plane() short circuit),
-	 * then we need to wait for scanout to be done with our
-	 * display lists before we free it and potentially reallocate
-	 * and overwrite the dlist memory with a new modeset.
-	 */
-	state->legacy_cursor_update = false;
+	drm_atomic_helper_fake_vblank(state);
 
 	drm_atomic_helper_commit_hw_done(state);
 
-	drm_atomic_helper_wait_for_vblanks(dev, state);
+	drm_atomic_helper_wait_for_flip_done(dev, state);
 
 	drm_atomic_helper_cleanup_planes(dev, state);
 
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index a951ec75d01f..cfb50fedfa2b 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -470,12 +470,14 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 	struct drm_framebuffer *fb = state->fb;
 	u32 ctl0_offset = vc4_state->dlist_count;
 	const struct hvs_format *format = vc4_get_hvs_format(fb->format->format);
+	u64 base_format_mod = fourcc_mod_broadcom_mod(fb->modifier);
 	int num_planes = drm_format_num_planes(format->drm);
 	bool mix_plane_alpha;
 	bool covers_screen;
 	u32 scl0, scl1, pitch0;
 	u32 lbm_size, tiling;
 	unsigned long irqflags;
+	u32 hvs_format = format->hvs;
 	int ret, i;
 
 	ret = vc4_plane_setup_clipping_and_scaling(state);
@@ -515,7 +517,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 		scl1 = vc4_get_scl_field(state, 0);
 	}
 
-	switch (fb->modifier) {
+	switch (base_format_mod) {
 	case DRM_FORMAT_MOD_LINEAR:
 		tiling = SCALER_CTL0_TILING_LINEAR;
 		pitch0 = VC4_SET_FIELD(fb->pitches[0], SCALER_SRC_PITCH);
@@ -538,6 +540,49 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 		break;
 	}
 
+	case DRM_FORMAT_MOD_BROADCOM_SAND64:
+	case DRM_FORMAT_MOD_BROADCOM_SAND128:
+	case DRM_FORMAT_MOD_BROADCOM_SAND256: {
+		uint32_t param = fourcc_mod_broadcom_param(fb->modifier);
+
+		/* Column-based NV12 or RGBA.
+		 */
+		if (fb->format->num_planes > 1) {
+			if (hvs_format != HVS_PIXEL_FORMAT_YCBCR_YUV420_2PLANE) {
+				DRM_DEBUG_KMS("SAND format only valid for NV12/21");
+				return -EINVAL;
+			}
+			hvs_format = HVS_PIXEL_FORMAT_H264;
+		} else {
+			if (base_format_mod == DRM_FORMAT_MOD_BROADCOM_SAND256) {
+				DRM_DEBUG_KMS("SAND256 format only valid for H.264");
+				return -EINVAL;
+			}
+		}
+
+		switch (base_format_mod) {
+		case DRM_FORMAT_MOD_BROADCOM_SAND64:
+			tiling = SCALER_CTL0_TILING_64B;
+			break;
+		case DRM_FORMAT_MOD_BROADCOM_SAND128:
+			tiling = SCALER_CTL0_TILING_128B;
+			break;
+		case DRM_FORMAT_MOD_BROADCOM_SAND256:
+			tiling = SCALER_CTL0_TILING_256B_OR_T;
+			break;
+		default:
+			break;
+		}
+
+		if (param > SCALER_TILE_HEIGHT_MASK) {
+			DRM_DEBUG_KMS("SAND height too large (%d)\n", param);
+			return -EINVAL;
+		}
+
+		pitch0 = VC4_SET_FIELD(param, SCALER_TILE_HEIGHT);
+		break;
+	}
+
 	default:
 		DRM_DEBUG_KMS("Unsupported FB tiling flag 0x%16llx",
 			      (long long)fb->modifier);
@@ -547,8 +592,9 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 	/* Control word */
 	vc4_dlist_write(vc4_state,
 			SCALER_CTL0_VALID |
+			VC4_SET_FIELD(SCALER_CTL0_RGBA_EXPAND_ROUND, SCALER_CTL0_RGBA_EXPAND) |
 			(format->pixel_order << SCALER_CTL0_ORDER_SHIFT) |
-			(format->hvs << SCALER_CTL0_PIXEL_FORMAT_SHIFT) |
+			(hvs_format << SCALER_CTL0_PIXEL_FORMAT_SHIFT) |
 			VC4_SET_FIELD(tiling, SCALER_CTL0_TILING) |
 			(vc4_state->is_unity ? SCALER_CTL0_UNITY : 0) |
 			VC4_SET_FIELD(scl0, SCALER_CTL0_SCL0) |
@@ -610,8 +656,13 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 
 	/* Pitch word 1/2 */
 	for (i = 1; i < num_planes; i++) {
-		vc4_dlist_write(vc4_state,
-				VC4_SET_FIELD(fb->pitches[i], SCALER_SRC_PITCH));
+		if (hvs_format != HVS_PIXEL_FORMAT_H264) {
+			vc4_dlist_write(vc4_state,
+					VC4_SET_FIELD(fb->pitches[i],
+						      SCALER_SRC_PITCH));
+		} else {
+			vc4_dlist_write(vc4_state, pitch0);
+		}
 	}
 
 	/* Colorspace conversion words */
@@ -813,18 +864,21 @@ static int vc4_prepare_fb(struct drm_plane *plane,
 	struct dma_fence *fence;
 	int ret;
 
-	if ((plane->state->fb == state->fb) || !state->fb)
+	if (!state->fb)
 		return 0;
 
 	bo = to_vc4_bo(&drm_fb_cma_get_gem_obj(state->fb, 0)->base);
 
+	fence = reservation_object_get_excl_rcu(bo->resv);
+	drm_atomic_set_fence_for_plane(state, fence);
+
+	if (plane->state->fb == state->fb)
+		return 0;
+
 	ret = vc4_bo_inc_usecnt(bo);
 	if (ret)
 		return ret;
 
-	fence = reservation_object_get_excl_rcu(bo->resv);
-	drm_atomic_set_fence_for_plane(state, fence);
-
 	return 0;
 }
 
@@ -851,7 +905,7 @@ static const struct drm_plane_helper_funcs vc4_plane_helper_funcs = {
 
 static void vc4_plane_destroy(struct drm_plane *plane)
 {
-	drm_plane_helper_disable(plane);
+	drm_plane_helper_disable(plane, NULL);
 	drm_plane_cleanup(plane);
 }
 
@@ -869,13 +923,32 @@ static bool vc4_format_mod_supported(struct drm_plane *plane,
 	case DRM_FORMAT_BGR565:
 	case DRM_FORMAT_ARGB1555:
 	case DRM_FORMAT_XRGB1555:
-		return true;
+		switch (fourcc_mod_broadcom_mod(modifier)) {
+		case DRM_FORMAT_MOD_LINEAR:
+		case DRM_FORMAT_MOD_BROADCOM_VC4_T_TILED:
+		case DRM_FORMAT_MOD_BROADCOM_SAND64:
+		case DRM_FORMAT_MOD_BROADCOM_SAND128:
+			return true;
+		default:
+			return false;
+		}
+	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_NV21:
+		switch (fourcc_mod_broadcom_mod(modifier)) {
+		case DRM_FORMAT_MOD_LINEAR:
+		case DRM_FORMAT_MOD_BROADCOM_SAND64:
+		case DRM_FORMAT_MOD_BROADCOM_SAND128:
+		case DRM_FORMAT_MOD_BROADCOM_SAND256:
+			return true;
+		default:
+			return false;
+		}
 	case DRM_FORMAT_YUV422:
 	case DRM_FORMAT_YVU422:
 	case DRM_FORMAT_YUV420:
 	case DRM_FORMAT_YVU420:
-	case DRM_FORMAT_NV12:
 	case DRM_FORMAT_NV16:
+	case DRM_FORMAT_NV61:
 	default:
 		return (modifier == DRM_FORMAT_MOD_LINEAR);
 	}
@@ -903,6 +976,9 @@ struct drm_plane *vc4_plane_init(struct drm_device *dev,
 	unsigned i;
 	static const uint64_t modifiers[] = {
 		DRM_FORMAT_MOD_BROADCOM_VC4_T_TILED,
+		DRM_FORMAT_MOD_BROADCOM_SAND128,
+		DRM_FORMAT_MOD_BROADCOM_SAND64,
+		DRM_FORMAT_MOD_BROADCOM_SAND256,
 		DRM_FORMAT_MOD_LINEAR,
 		DRM_FORMAT_MOD_INVALID
 	};
diff --git a/drivers/gpu/drm/vc4/vc4_regs.h b/drivers/gpu/drm/vc4/vc4_regs.h
index d1fb6fec46eb..d6864fa4bd14 100644
--- a/drivers/gpu/drm/vc4/vc4_regs.h
+++ b/drivers/gpu/drm/vc4/vc4_regs.h
@@ -1031,6 +1031,12 @@ enum hvs_pixel_format {
 #define SCALER_SRC_PITCH_MASK			VC4_MASK(15, 0)
 #define SCALER_SRC_PITCH_SHIFT			0
 
+/* PITCH0/1/2 fields for tiled (SAND). */
+#define SCALER_TILE_SKIP_0_MASK			VC4_MASK(18, 16)
+#define SCALER_TILE_SKIP_0_SHIFT		16
+#define SCALER_TILE_HEIGHT_MASK			VC4_MASK(15, 0)
+#define SCALER_TILE_HEIGHT_SHIFT		0
+
 /* PITCH0 fields for T-tiled. */
 #define SCALER_PITCH0_TILE_WIDTH_L_MASK		VC4_MASK(22, 16)
 #define SCALER_PITCH0_TILE_WIDTH_L_SHIFT	16
diff --git a/drivers/gpu/drm/vc4/vc4_txp.c b/drivers/gpu/drm/vc4/vc4_txp.c
new file mode 100644
index 000000000000..6e23c50168f9
--- /dev/null
+++ b/drivers/gpu/drm/vc4/vc4_txp.c
@@ -0,0 +1,477 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright © 2018 Broadcom
+ *
+ * Authors:
+ *	Eric Anholt <eric@anholt.net>
+ *	Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_fb_cma_helper.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_edid.h>
+#include <drm/drm_panel.h>
+#include <drm/drm_writeback.h>
+#include <linux/clk.h>
+#include <linux/component.h>
+#include <linux/of_graph.h>
+#include <linux/of_platform.h>
+#include <linux/pm_runtime.h>
+
+#include "vc4_drv.h"
+#include "vc4_regs.h"
+
+/* Base address of the output.  Raster formats must be 4-byte aligned,
+ * T and LT must be 16-byte aligned or maybe utile-aligned (docs are
+ * inconsistent, but probably utile).
+ */
+#define TXP_DST_PTR		0x00
+
+/* Pitch in bytes for raster images, 16-byte aligned.  For tiled, it's
+ * the width in tiles.
+ */
+#define TXP_DST_PITCH		0x04
+/* For T-tiled imgaes, DST_PITCH should be the number of tiles wide,
+ * shifted up.
+ */
+# define TXP_T_TILE_WIDTH_SHIFT		7
+/* For LT-tiled images, DST_PITCH should be the number of utiles wide,
+ * shifted up.
+ */
+# define TXP_LT_TILE_WIDTH_SHIFT	4
+
+/* Pre-rotation width/height of the image.  Must match HVS config.
+ *
+ * If TFORMAT and 32-bit, limit is 1920 for 32-bit and 3840 to 16-bit
+ * and width/height must be tile or utile-aligned as appropriate.  If
+ * transposing (rotating), width is limited to 1920.
+ *
+ * Height is limited to various numbers between 4088 and 4095.  I'd
+ * just use 4088 to be safe.
+ */
+#define TXP_DIM			0x08
+# define TXP_HEIGHT_SHIFT		16
+# define TXP_HEIGHT_MASK		GENMASK(31, 16)
+# define TXP_WIDTH_SHIFT		0
+# define TXP_WIDTH_MASK			GENMASK(15, 0)
+
+#define TXP_DST_CTRL		0x0c
+/* These bits are set to 0x54 */
+#define TXP_PILOT_SHIFT			24
+#define TXP_PILOT_MASK			GENMASK(31, 24)
+/* Bits 22-23 are set to 0x01 */
+#define TXP_VERSION_SHIFT		22
+#define TXP_VERSION_MASK		GENMASK(23, 22)
+
+/* Powers down the internal memory. */
+# define TXP_POWERDOWN			BIT(21)
+
+/* Enables storing the alpha component in 8888/4444, instead of
+ * filling with ~ALPHA_INVERT.
+ */
+# define TXP_ALPHA_ENABLE		BIT(20)
+
+/* 4 bits, each enables stores for a channel in each set of 4 bytes.
+ * Set to 0xf for normal operation.
+ */
+# define TXP_BYTE_ENABLE_SHIFT		16
+# define TXP_BYTE_ENABLE_MASK		GENMASK(19, 16)
+
+/* Debug: Generate VSTART again at EOF. */
+# define TXP_VSTART_AT_EOF		BIT(15)
+
+/* Debug: Terminate the current frame immediately.  Stops AXI
+ * writes.
+ */
+# define TXP_ABORT			BIT(14)
+
+# define TXP_DITHER			BIT(13)
+
+/* Inverts alpha if TXP_ALPHA_ENABLE, chooses fill value for
+ * !TXP_ALPHA_ENABLE.
+ */
+# define TXP_ALPHA_INVERT		BIT(12)
+
+/* Note: I've listed the channels here in high bit (in byte 3/2/1) to
+ * low bit (in byte 0) order.
+ */
+# define TXP_FORMAT_SHIFT		8
+# define TXP_FORMAT_MASK		GENMASK(11, 8)
+# define TXP_FORMAT_ABGR4444		0
+# define TXP_FORMAT_ARGB4444		1
+# define TXP_FORMAT_BGRA4444		2
+# define TXP_FORMAT_RGBA4444		3
+# define TXP_FORMAT_BGR565		6
+# define TXP_FORMAT_RGB565		7
+/* 888s are non-rotated, raster-only */
+# define TXP_FORMAT_BGR888		8
+# define TXP_FORMAT_RGB888		9
+# define TXP_FORMAT_ABGR8888		12
+# define TXP_FORMAT_ARGB8888		13
+# define TXP_FORMAT_BGRA8888		14
+# define TXP_FORMAT_RGBA8888		15
+
+/* If TFORMAT is set, generates LT instead of T format. */
+# define TXP_LINEAR_UTILE		BIT(7)
+
+/* Rotate output by 90 degrees. */
+# define TXP_TRANSPOSE			BIT(6)
+
+/* Generate a tiled format for V3D. */
+# define TXP_TFORMAT			BIT(5)
+
+/* Generates some undefined test mode output. */
+# define TXP_TEST_MODE			BIT(4)
+
+/* Request odd field from HVS. */
+# define TXP_FIELD			BIT(3)
+
+/* Raise interrupt when idle. */
+# define TXP_EI				BIT(2)
+
+/* Set when generating a frame, clears when idle. */
+# define TXP_BUSY			BIT(1)
+
+/* Starts a frame.  Self-clearing. */
+# define TXP_GO				BIT(0)
+
+/* Number of lines received and committed to memory. */
+#define TXP_PROGRESS		0x10
+
+#define TXP_READ(offset) readl(txp->regs + (offset))
+#define TXP_WRITE(offset, val) writel(val, txp->regs + (offset))
+
+struct vc4_txp {
+	struct platform_device *pdev;
+
+	struct drm_writeback_connector connector;
+
+	void __iomem *regs;
+};
+
+static inline struct vc4_txp *encoder_to_vc4_txp(struct drm_encoder *encoder)
+{
+	return container_of(encoder, struct vc4_txp, connector.encoder);
+}
+
+static inline struct vc4_txp *connector_to_vc4_txp(struct drm_connector *conn)
+{
+	return container_of(conn, struct vc4_txp, connector.base);
+}
+
+#define TXP_REG(reg) { reg, #reg }
+static const struct {
+	u32 reg;
+	const char *name;
+} txp_regs[] = {
+	TXP_REG(TXP_DST_PTR),
+	TXP_REG(TXP_DST_PITCH),
+	TXP_REG(TXP_DIM),
+	TXP_REG(TXP_DST_CTRL),
+	TXP_REG(TXP_PROGRESS),
+};
+
+#ifdef CONFIG_DEBUG_FS
+int vc4_txp_debugfs_regs(struct seq_file *m, void *unused)
+{
+	struct drm_info_node *node = (struct drm_info_node *)m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_txp *txp = vc4->txp;
+	int i;
+
+	if (!txp)
+		return 0;
+
+	for (i = 0; i < ARRAY_SIZE(txp_regs); i++) {
+		seq_printf(m, "%s (0x%04x): 0x%08x\n",
+			   txp_regs[i].name, txp_regs[i].reg,
+			   TXP_READ(txp_regs[i].reg));
+	}
+
+	return 0;
+}
+#endif
+
+static int vc4_txp_connector_get_modes(struct drm_connector *connector)
+{
+	struct drm_device *dev = connector->dev;
+
+	return drm_add_modes_noedid(connector, dev->mode_config.max_width,
+				    dev->mode_config.max_height);
+}
+
+static enum drm_mode_status
+vc4_txp_connector_mode_valid(struct drm_connector *connector,
+			     struct drm_display_mode *mode)
+{
+	struct drm_device *dev = connector->dev;
+	struct drm_mode_config *mode_config = &dev->mode_config;
+	int w = mode->hdisplay, h = mode->vdisplay;
+
+	if (w < mode_config->min_width || w > mode_config->max_width)
+		return MODE_BAD_HVALUE;
+
+	if (h < mode_config->min_height || h > mode_config->max_height)
+		return MODE_BAD_VVALUE;
+
+	return MODE_OK;
+}
+
+static const u32 drm_fmts[] = {
+	DRM_FORMAT_RGB888,
+	DRM_FORMAT_BGR888,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_RGBX8888,
+	DRM_FORMAT_BGRX8888,
+	DRM_FORMAT_RGBA8888,
+	DRM_FORMAT_BGRA8888,
+};
+
+static const u32 txp_fmts[] = {
+	TXP_FORMAT_RGB888,
+	TXP_FORMAT_BGR888,
+	TXP_FORMAT_ARGB8888,
+	TXP_FORMAT_ABGR8888,
+	TXP_FORMAT_ARGB8888,
+	TXP_FORMAT_ABGR8888,
+	TXP_FORMAT_RGBA8888,
+	TXP_FORMAT_BGRA8888,
+	TXP_FORMAT_RGBA8888,
+	TXP_FORMAT_BGRA8888,
+};
+
+static int vc4_txp_connector_atomic_check(struct drm_connector *conn,
+					struct drm_connector_state *conn_state)
+{
+	struct drm_crtc_state *crtc_state;
+	struct drm_gem_cma_object *gem;
+	struct drm_framebuffer *fb;
+	int i;
+
+	if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
+		return 0;
+
+	crtc_state = drm_atomic_get_new_crtc_state(conn_state->state,
+						   conn_state->crtc);
+
+	fb = conn_state->writeback_job->fb;
+	if (fb->width != crtc_state->mode.hdisplay ||
+	    fb->height != crtc_state->mode.vdisplay) {
+		DRM_DEBUG_KMS("Invalid framebuffer size %ux%u\n",
+			      fb->width, fb->height);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(drm_fmts); i++) {
+		if (fb->format->format == drm_fmts[i])
+			break;
+	}
+
+	if (i == ARRAY_SIZE(drm_fmts))
+		return -EINVAL;
+
+	gem = drm_fb_cma_get_gem_obj(fb, 0);
+
+	/* Pitch must be aligned on 16 bytes. */
+	if (fb->pitches[0] & GENMASK(3, 0))
+		return -EINVAL;
+
+	vc4_crtc_txp_armed(crtc_state);
+
+	return 0;
+}
+
+static void vc4_txp_connector_atomic_commit(struct drm_connector *conn,
+					struct drm_connector_state *conn_state)
+{
+	struct vc4_txp *txp = connector_to_vc4_txp(conn);
+	struct drm_gem_cma_object *gem;
+	struct drm_display_mode *mode;
+	struct drm_framebuffer *fb;
+	u32 ctrl;
+	int i;
+
+	if (WARN_ON(!conn_state->writeback_job ||
+		    !conn_state->writeback_job->fb))
+		return;
+
+	mode = &conn_state->crtc->state->adjusted_mode;
+	fb = conn_state->writeback_job->fb;
+
+	for (i = 0; i < ARRAY_SIZE(drm_fmts); i++) {
+		if (fb->format->format == drm_fmts[i])
+			break;
+	}
+
+	if (WARN_ON(i == ARRAY_SIZE(drm_fmts)))
+		return;
+
+	ctrl = TXP_GO | TXP_VSTART_AT_EOF | TXP_EI |
+	       VC4_SET_FIELD(0xf, TXP_BYTE_ENABLE) |
+	       VC4_SET_FIELD(txp_fmts[i], TXP_FORMAT);
+
+	if (fb->format->has_alpha)
+		ctrl |= TXP_ALPHA_ENABLE;
+
+	gem = drm_fb_cma_get_gem_obj(fb, 0);
+	TXP_WRITE(TXP_DST_PTR, gem->paddr + fb->offsets[0]);
+	TXP_WRITE(TXP_DST_PITCH, fb->pitches[0]);
+	TXP_WRITE(TXP_DIM,
+		  VC4_SET_FIELD(mode->hdisplay, TXP_WIDTH) |
+		  VC4_SET_FIELD(mode->vdisplay, TXP_HEIGHT));
+
+	TXP_WRITE(TXP_DST_CTRL, ctrl);
+
+	drm_writeback_queue_job(&txp->connector, conn_state->writeback_job);
+}
+
+static const struct drm_connector_helper_funcs vc4_txp_connector_helper_funcs = {
+	.get_modes = vc4_txp_connector_get_modes,
+	.mode_valid = vc4_txp_connector_mode_valid,
+	.atomic_check = vc4_txp_connector_atomic_check,
+	.atomic_commit = vc4_txp_connector_atomic_commit,
+};
+
+static enum drm_connector_status
+vc4_txp_connector_detect(struct drm_connector *connector, bool force)
+{
+	return connector_status_connected;
+}
+
+static void vc4_txp_connector_destroy(struct drm_connector *connector)
+{
+	drm_connector_unregister(connector);
+	drm_connector_cleanup(connector);
+}
+
+static const struct drm_connector_funcs vc4_txp_connector_funcs = {
+	.detect = vc4_txp_connector_detect,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = vc4_txp_connector_destroy,
+	.reset = drm_atomic_helper_connector_reset,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+};
+
+static void vc4_txp_encoder_disable(struct drm_encoder *encoder)
+{
+	struct vc4_txp *txp = encoder_to_vc4_txp(encoder);
+
+	if (TXP_READ(TXP_DST_CTRL) & TXP_BUSY) {
+		unsigned long timeout = jiffies + msecs_to_jiffies(1000);
+
+		TXP_WRITE(TXP_DST_CTRL, TXP_ABORT);
+
+		while (TXP_READ(TXP_DST_CTRL) & TXP_BUSY &&
+		       time_before(jiffies, timeout))
+			;
+
+		WARN_ON(TXP_READ(TXP_DST_CTRL) & TXP_BUSY);
+	}
+
+	TXP_WRITE(TXP_DST_CTRL, TXP_POWERDOWN);
+}
+
+static const struct drm_encoder_helper_funcs vc4_txp_encoder_helper_funcs = {
+	.disable = vc4_txp_encoder_disable,
+};
+
+static irqreturn_t vc4_txp_interrupt(int irq, void *data)
+{
+	struct vc4_txp *txp = data;
+
+	TXP_WRITE(TXP_DST_CTRL, TXP_READ(TXP_DST_CTRL) & ~TXP_EI);
+	vc4_crtc_handle_vblank(to_vc4_crtc(txp->connector.base.state->crtc));
+	drm_writeback_signal_completion(&txp->connector, 0);
+
+	return IRQ_HANDLED;
+}
+
+static int vc4_txp_bind(struct device *dev, struct device *master, void *data)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct drm_device *drm = dev_get_drvdata(master);
+	struct vc4_dev *vc4 = to_vc4_dev(drm);
+	struct vc4_txp *txp;
+	int ret, irq;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	txp = devm_kzalloc(dev, sizeof(*txp), GFP_KERNEL);
+	if (!txp)
+		return -ENOMEM;
+
+	txp->pdev = pdev;
+
+	txp->regs = vc4_ioremap_regs(pdev, 0);
+	if (IS_ERR(txp->regs))
+		return PTR_ERR(txp->regs);
+
+	drm_connector_helper_add(&txp->connector.base,
+				 &vc4_txp_connector_helper_funcs);
+	ret = drm_writeback_connector_init(drm, &txp->connector,
+					   &vc4_txp_connector_funcs,
+					   &vc4_txp_encoder_helper_funcs,
+					   drm_fmts, ARRAY_SIZE(drm_fmts));
+	if (ret)
+		return ret;
+
+	ret = devm_request_irq(dev, irq, vc4_txp_interrupt, 0,
+			       dev_name(dev), txp);
+	if (ret)
+		return ret;
+
+	dev_set_drvdata(dev, txp);
+	vc4->txp = txp;
+
+	return 0;
+}
+
+static void vc4_txp_unbind(struct device *dev, struct device *master,
+			   void *data)
+{
+	struct drm_device *drm = dev_get_drvdata(master);
+	struct vc4_dev *vc4 = to_vc4_dev(drm);
+	struct vc4_txp *txp = dev_get_drvdata(dev);
+
+	vc4_txp_connector_destroy(&txp->connector.base);
+
+	vc4->txp = NULL;
+}
+
+static const struct component_ops vc4_txp_ops = {
+	.bind   = vc4_txp_bind,
+	.unbind = vc4_txp_unbind,
+};
+
+static int vc4_txp_probe(struct platform_device *pdev)
+{
+	return component_add(&pdev->dev, &vc4_txp_ops);
+}
+
+static int vc4_txp_remove(struct platform_device *pdev)
+{
+	component_del(&pdev->dev, &vc4_txp_ops);
+	return 0;
+}
+
+static const struct of_device_id vc4_txp_dt_match[] = {
+	{ .compatible = "brcm,bcm2835-txp" },
+	{ /* sentinel */ },
+};
+
+struct platform_driver vc4_txp_driver = {
+	.probe = vc4_txp_probe,
+	.remove = vc4_txp_remove,
+	.driver = {
+		.name = "vc4_txp",
+		.of_match_table = vc4_txp_dt_match,
+	},
+};
diff --git a/drivers/gpu/drm/vc4/vc4_vec.c b/drivers/gpu/drm/vc4/vc4_vec.c
index 3a9a302247a2..8e7facb6514e 100644
--- a/drivers/gpu/drm/vc4/vc4_vec.c
+++ b/drivers/gpu/drm/vc4/vc4_vec.c
@@ -404,7 +404,7 @@ static struct drm_connector *vc4_vec_connector_init(struct drm_device *dev,
 				   VC4_VEC_TV_MODE_NTSC);
 	vec->tv_mode = &vc4_vec_tv_modes[VC4_VEC_TV_MODE_NTSC];
 
-	drm_mode_connector_attach_encoder(connector, vec->encoder);
+	drm_connector_attach_encoder(connector, vec->encoder);
 
 	return connector;
 }
diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c
index 2524ff116f00..0e5620f76ee0 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.c
+++ b/drivers/gpu/drm/vgem/vgem_drv.c
@@ -61,23 +61,22 @@ static void vgem_gem_free_object(struct drm_gem_object *obj)
 	kfree(vgem_obj);
 }
 
-static int vgem_gem_fault(struct vm_fault *vmf)
+static vm_fault_t vgem_gem_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_vgem_gem_object *obj = vma->vm_private_data;
 	/* We don't use vmf->pgoff since that has the fake offset */
 	unsigned long vaddr = vmf->address;
-	int ret;
+	vm_fault_t ret = VM_FAULT_SIGBUS;
 	loff_t num_pages;
 	pgoff_t page_offset;
 	page_offset = (vaddr - vma->vm_start) >> PAGE_SHIFT;
 
 	num_pages = DIV_ROUND_UP(obj->base.size, PAGE_SIZE);
 
-	if (page_offset > num_pages)
+	if (page_offset >= num_pages)
 		return VM_FAULT_SIGBUS;
 
-	ret = -ENOENT;
 	mutex_lock(&obj->pages_lock);
 	if (obj->pages) {
 		get_page(obj->pages[page_offset]);
diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c
index a5edd86603d9..25503b933599 100644
--- a/drivers/gpu/drm/virtio/virtgpu_display.c
+++ b/drivers/gpu/drm/virtio/virtgpu_display.c
@@ -28,6 +28,7 @@
 #include "virtgpu_drv.h"
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 
 #define XRES_MIN    32
 #define YRES_MIN    32
@@ -48,16 +49,6 @@ static const struct drm_crtc_funcs virtio_gpu_crtc_funcs = {
 	.atomic_destroy_state   = drm_atomic_helper_crtc_destroy_state,
 };
 
-static void virtio_gpu_user_framebuffer_destroy(struct drm_framebuffer *fb)
-{
-	struct virtio_gpu_framebuffer *virtio_gpu_fb
-		= to_virtio_gpu_framebuffer(fb);
-
-	drm_gem_object_put_unlocked(virtio_gpu_fb->obj);
-	drm_framebuffer_cleanup(fb);
-	kfree(virtio_gpu_fb);
-}
-
 static int
 virtio_gpu_framebuffer_surface_dirty(struct drm_framebuffer *fb,
 				     struct drm_file *file_priv,
@@ -71,20 +62,9 @@ virtio_gpu_framebuffer_surface_dirty(struct drm_framebuffer *fb,
 	return virtio_gpu_surface_dirty(virtio_gpu_fb, clips, num_clips);
 }
 
-static int
-virtio_gpu_framebuffer_create_handle(struct drm_framebuffer *fb,
-				     struct drm_file *file_priv,
-				     unsigned int *handle)
-{
-	struct virtio_gpu_framebuffer *virtio_gpu_fb =
-		to_virtio_gpu_framebuffer(fb);
-
-	return drm_gem_handle_create(file_priv, virtio_gpu_fb->obj, handle);
-}
-
 static const struct drm_framebuffer_funcs virtio_gpu_fb_funcs = {
-	.create_handle = virtio_gpu_framebuffer_create_handle,
-	.destroy = virtio_gpu_user_framebuffer_destroy,
+	.create_handle = drm_gem_fb_create_handle,
+	.destroy = drm_gem_fb_destroy,
 	.dirty = virtio_gpu_framebuffer_surface_dirty,
 };
 
@@ -97,7 +77,7 @@ virtio_gpu_framebuffer_init(struct drm_device *dev,
 	int ret;
 	struct virtio_gpu_object *bo;
 
-	vgfb->obj = obj;
+	vgfb->base.obj[0] = obj;
 
 	bo = gem_to_virtio_gpu_obj(obj);
 
@@ -105,7 +85,7 @@ virtio_gpu_framebuffer_init(struct drm_device *dev,
 
 	ret = drm_framebuffer_init(dev, &vgfb->base, &virtio_gpu_fb_funcs);
 	if (ret) {
-		vgfb->obj = NULL;
+		vgfb->base.obj[0] = NULL;
 		return ret;
 	}
 
@@ -302,8 +282,6 @@ static int vgdev_output_init(struct virtio_gpu_device *vgdev, int index)
 	drm_crtc_init_with_planes(dev, crtc, primary, cursor,
 				  &virtio_gpu_crtc_funcs, NULL);
 	drm_crtc_helper_add(crtc, &virtio_gpu_crtc_helper_funcs);
-	primary->crtc = crtc;
-	cursor->crtc = crtc;
 
 	drm_connector_init(dev, connector, &virtio_gpu_connector_funcs,
 			   DRM_MODE_CONNECTOR_VIRTUAL);
@@ -314,7 +292,7 @@ static int vgdev_output_init(struct virtio_gpu_device *vgdev, int index)
 	drm_encoder_helper_add(encoder, &virtio_gpu_enc_helper_funcs);
 	encoder->possible_crtcs = 1 << index;
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	drm_connector_register(connector);
 	return 0;
 }
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h
index d25c8ca224aa..65605e207bbe 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.h
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.h
@@ -124,7 +124,6 @@ struct virtio_gpu_output {
 
 struct virtio_gpu_framebuffer {
 	struct drm_framebuffer base;
-	struct drm_gem_object *obj;
 	int x1, y1, x2, y2; /* dirty rect */
 	spinlock_t dirty_lock;
 	uint32_t hw_res_handle;
diff --git a/drivers/gpu/drm/virtio/virtgpu_fb.c b/drivers/gpu/drm/virtio/virtgpu_fb.c
index 8af69ab58b89..a121b1c79522 100644
--- a/drivers/gpu/drm/virtio/virtgpu_fb.c
+++ b/drivers/gpu/drm/virtio/virtgpu_fb.c
@@ -46,7 +46,7 @@ static int virtio_gpu_dirty_update(struct virtio_gpu_framebuffer *fb,
 	int bpp = fb->base.format->cpp[0];
 	int x2, y2;
 	unsigned long flags;
-	struct virtio_gpu_object *obj = gem_to_virtio_gpu_obj(fb->obj);
+	struct virtio_gpu_object *obj = gem_to_virtio_gpu_obj(fb->base.obj[0]);
 
 	if ((width <= 0) ||
 	    (x + width > fb->base.width) ||
@@ -121,7 +121,7 @@ int virtio_gpu_surface_dirty(struct virtio_gpu_framebuffer *vgfb,
 			     unsigned int num_clips)
 {
 	struct virtio_gpu_device *vgdev = vgfb->base.dev->dev_private;
-	struct virtio_gpu_object *obj = gem_to_virtio_gpu_obj(vgfb->obj);
+	struct virtio_gpu_object *obj = gem_to_virtio_gpu_obj(vgfb->base.obj[0]);
 	struct drm_clip_rect norect;
 	struct drm_clip_rect *clips_ptr;
 	int left, right, top, bottom;
@@ -305,8 +305,8 @@ static int virtio_gpu_fbdev_destroy(struct drm_device *dev,
 
 	drm_fb_helper_unregister_fbi(&vgfbdev->helper);
 
-	if (vgfb->obj)
-		vgfb->obj = NULL;
+	if (vgfb->base.obj[0])
+		vgfb->base.obj[0] = NULL;
 	drm_fb_helper_fini(&vgfbdev->helper);
 	drm_framebuffer_cleanup(&vgfb->base);
 
diff --git a/drivers/gpu/drm/virtio/virtgpu_fence.c b/drivers/gpu/drm/virtio/virtgpu_fence.c
index 23353521f903..00c742a441bf 100644
--- a/drivers/gpu/drm/virtio/virtgpu_fence.c
+++ b/drivers/gpu/drm/virtio/virtgpu_fence.c
@@ -36,11 +36,6 @@ static const char *virtio_get_timeline_name(struct dma_fence *f)
 	return "controlq";
 }
 
-static bool virtio_enable_signaling(struct dma_fence *f)
-{
-	return true;
-}
-
 static bool virtio_signaled(struct dma_fence *f)
 {
 	struct virtio_gpu_fence *fence = to_virtio_fence(f);
@@ -67,9 +62,7 @@ static void virtio_timeline_value_str(struct dma_fence *f, char *str, int size)
 static const struct dma_fence_ops virtio_fence_ops = {
 	.get_driver_name     = virtio_get_driver_name,
 	.get_timeline_name   = virtio_get_timeline_name,
-	.enable_signaling    = virtio_enable_signaling,
 	.signaled            = virtio_signaled,
-	.wait                = dma_fence_default_wait,
 	.fence_value_str     = virtio_fence_value_str,
 	.timeline_value_str  = virtio_timeline_value_str,
 };
diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c
index 71ba455af915..dc5b5b2b7aab 100644
--- a/drivers/gpu/drm/virtio/virtgpu_plane.c
+++ b/drivers/gpu/drm/virtio/virtgpu_plane.c
@@ -154,7 +154,7 @@ static void virtio_gpu_primary_plane_update(struct drm_plane *plane,
 
 	if (plane->state->fb) {
 		vgfb = to_virtio_gpu_framebuffer(plane->state->fb);
-		bo = gem_to_virtio_gpu_obj(vgfb->obj);
+		bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]);
 		handle = bo->hw_res_handle;
 		if (bo->dumb) {
 			virtio_gpu_cmd_transfer_to_host_2d
@@ -208,7 +208,7 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane,
 
 	if (plane->state->fb) {
 		vgfb = to_virtio_gpu_framebuffer(plane->state->fb);
-		bo = gem_to_virtio_gpu_obj(vgfb->obj);
+		bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]);
 		handle = bo->hw_res_handle;
 	} else {
 		handle = 0;
diff --git a/drivers/gpu/drm/vkms/Makefile b/drivers/gpu/drm/vkms/Makefile
new file mode 100644
index 000000000000..986297da51bf
--- /dev/null
+++ b/drivers/gpu/drm/vkms/Makefile
@@ -0,0 +1,3 @@
+vkms-y := vkms_drv.o vkms_plane.o vkms_output.o vkms_crtc.o vkms_gem.o
+
+obj-$(CONFIG_DRM_VKMS) += vkms.o
diff --git a/drivers/gpu/drm/vkms/vkms_crtc.c b/drivers/gpu/drm/vkms/vkms_crtc.c
new file mode 100644
index 000000000000..875fca662ac0
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_crtc.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "vkms_drv.h"
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_crtc_helper.h>
+
+static enum hrtimer_restart vkms_vblank_simulate(struct hrtimer *timer)
+{
+	struct vkms_output *output = container_of(timer, struct vkms_output,
+						  vblank_hrtimer);
+	struct drm_crtc *crtc = &output->crtc;
+	int ret_overrun;
+	bool ret;
+
+	ret = drm_crtc_handle_vblank(crtc);
+	if (!ret)
+		DRM_ERROR("vkms failure on handling vblank");
+
+	ret_overrun = hrtimer_forward_now(&output->vblank_hrtimer,
+					  output->period_ns);
+
+	return HRTIMER_RESTART;
+}
+
+static int vkms_enable_vblank(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	unsigned int pipe = drm_crtc_index(crtc);
+	struct drm_vblank_crtc *vblank = &dev->vblank[pipe];
+	struct vkms_output *out = drm_crtc_to_vkms_output(crtc);
+
+	drm_calc_timestamping_constants(crtc, &crtc->mode);
+
+	hrtimer_init(&out->vblank_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	out->vblank_hrtimer.function = &vkms_vblank_simulate;
+	out->period_ns = ktime_set(0, vblank->framedur_ns);
+	hrtimer_start(&out->vblank_hrtimer, out->period_ns, HRTIMER_MODE_REL);
+
+	return 0;
+}
+
+static void vkms_disable_vblank(struct drm_crtc *crtc)
+{
+	struct vkms_output *out = drm_crtc_to_vkms_output(crtc);
+
+	hrtimer_cancel(&out->vblank_hrtimer);
+}
+
+bool vkms_get_vblank_timestamp(struct drm_device *dev, unsigned int pipe,
+			       int *max_error, ktime_t *vblank_time,
+			       bool in_vblank_irq)
+{
+	struct vkms_device *vkmsdev = drm_device_to_vkms_device(dev);
+	struct vkms_output *output = &vkmsdev->output;
+
+	*vblank_time = output->vblank_hrtimer.node.expires;
+
+	return true;
+}
+
+static const struct drm_crtc_funcs vkms_crtc_funcs = {
+	.set_config             = drm_atomic_helper_set_config,
+	.destroy                = drm_crtc_cleanup,
+	.page_flip              = drm_atomic_helper_page_flip,
+	.reset                  = drm_atomic_helper_crtc_reset,
+	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
+	.atomic_destroy_state   = drm_atomic_helper_crtc_destroy_state,
+	.enable_vblank		= vkms_enable_vblank,
+	.disable_vblank		= vkms_disable_vblank,
+};
+
+static void vkms_crtc_atomic_enable(struct drm_crtc *crtc,
+				    struct drm_crtc_state *old_state)
+{
+	drm_crtc_vblank_on(crtc);
+}
+
+static void vkms_crtc_atomic_disable(struct drm_crtc *crtc,
+				     struct drm_crtc_state *old_state)
+{
+	drm_crtc_vblank_off(crtc);
+}
+
+static void vkms_crtc_atomic_flush(struct drm_crtc *crtc,
+				   struct drm_crtc_state *old_crtc_state)
+{
+	unsigned long flags;
+
+	if (crtc->state->event) {
+		spin_lock_irqsave(&crtc->dev->event_lock, flags);
+
+		if (drm_crtc_vblank_get(crtc) != 0)
+			drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		else
+			drm_crtc_arm_vblank_event(crtc, crtc->state->event);
+
+		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+
+		crtc->state->event = NULL;
+	}
+}
+
+static const struct drm_crtc_helper_funcs vkms_crtc_helper_funcs = {
+	.atomic_flush	= vkms_crtc_atomic_flush,
+	.atomic_enable	= vkms_crtc_atomic_enable,
+	.atomic_disable	= vkms_crtc_atomic_disable,
+};
+
+int vkms_crtc_init(struct drm_device *dev, struct drm_crtc *crtc,
+		   struct drm_plane *primary, struct drm_plane *cursor)
+{
+	int ret;
+
+	ret = drm_crtc_init_with_planes(dev, crtc, primary, cursor,
+					&vkms_crtc_funcs, NULL);
+	if (ret) {
+		DRM_ERROR("Failed to init CRTC\n");
+		return ret;
+	}
+
+	drm_crtc_helper_add(crtc, &vkms_crtc_helper_funcs);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c
new file mode 100644
index 000000000000..6e728b825259
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_drv.c
@@ -0,0 +1,156 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
+#include <drm/drm_fb_helper.h>
+#include "vkms_drv.h"
+
+#define DRIVER_NAME	"vkms"
+#define DRIVER_DESC	"Virtual Kernel Mode Setting"
+#define DRIVER_DATE	"20180514"
+#define DRIVER_MAJOR	1
+#define DRIVER_MINOR	0
+
+static struct vkms_device *vkms_device;
+
+static const struct file_operations vkms_driver_fops = {
+	.owner		= THIS_MODULE,
+	.open		= drm_open,
+	.mmap		= drm_gem_mmap,
+	.unlocked_ioctl	= drm_ioctl,
+	.compat_ioctl	= drm_compat_ioctl,
+	.poll		= drm_poll,
+	.read		= drm_read,
+	.llseek		= no_llseek,
+	.release	= drm_release,
+};
+
+static const struct vm_operations_struct vkms_gem_vm_ops = {
+	.fault = vkms_gem_fault,
+	.open = drm_gem_vm_open,
+	.close = drm_gem_vm_close,
+};
+
+static void vkms_release(struct drm_device *dev)
+{
+	struct vkms_device *vkms = container_of(dev, struct vkms_device, drm);
+
+	platform_device_unregister(vkms->platform);
+	drm_atomic_helper_shutdown(&vkms->drm);
+	drm_mode_config_cleanup(&vkms->drm);
+	drm_dev_fini(&vkms->drm);
+}
+
+static struct drm_driver vkms_driver = {
+	.driver_features	= DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_GEM,
+	.release		= vkms_release,
+	.fops			= &vkms_driver_fops,
+	.dumb_create		= vkms_dumb_create,
+	.dumb_map_offset	= vkms_dumb_map,
+	.gem_vm_ops		= &vkms_gem_vm_ops,
+	.gem_free_object_unlocked = vkms_gem_free_object,
+	.get_vblank_timestamp	= vkms_get_vblank_timestamp,
+
+	.name			= DRIVER_NAME,
+	.desc			= DRIVER_DESC,
+	.date			= DRIVER_DATE,
+	.major			= DRIVER_MAJOR,
+	.minor			= DRIVER_MINOR,
+};
+
+static const struct drm_mode_config_funcs vkms_mode_funcs = {
+	.fb_create = drm_gem_fb_create,
+	.atomic_check = drm_atomic_helper_check,
+	.atomic_commit = drm_atomic_helper_commit,
+};
+
+static int vkms_modeset_init(struct vkms_device *vkmsdev)
+{
+	struct drm_device *dev = &vkmsdev->drm;
+
+	drm_mode_config_init(dev);
+	dev->mode_config.funcs = &vkms_mode_funcs;
+	dev->mode_config.min_width = XRES_MIN;
+	dev->mode_config.min_height = YRES_MIN;
+	dev->mode_config.max_width = XRES_MAX;
+	dev->mode_config.max_height = YRES_MAX;
+
+	return vkms_output_init(vkmsdev);
+}
+
+static int __init vkms_init(void)
+{
+	int ret;
+
+	vkms_device = kzalloc(sizeof(*vkms_device), GFP_KERNEL);
+	if (!vkms_device)
+		return -ENOMEM;
+
+	ret = drm_dev_init(&vkms_device->drm, &vkms_driver, NULL);
+	if (ret)
+		goto out_free;
+
+	vkms_device->platform =
+		platform_device_register_simple(DRIVER_NAME, -1, NULL, 0);
+	if (IS_ERR(vkms_device->platform)) {
+		ret = PTR_ERR(vkms_device->platform);
+		goto out_fini;
+	}
+
+	vkms_device->drm.irq_enabled = true;
+
+	ret = drm_vblank_init(&vkms_device->drm, 1);
+	if (ret) {
+		DRM_ERROR("Failed to vblank\n");
+		goto out_fini;
+	}
+
+	ret = vkms_modeset_init(vkms_device);
+	if (ret)
+		goto out_unregister;
+
+	ret = drm_dev_register(&vkms_device->drm, 0);
+	if (ret)
+		goto out_unregister;
+
+	return 0;
+
+out_unregister:
+	platform_device_unregister(vkms_device->platform);
+
+out_fini:
+	drm_dev_fini(&vkms_device->drm);
+
+out_free:
+	kfree(vkms_device);
+	return ret;
+}
+
+static void __exit vkms_exit(void)
+{
+	if (!vkms_device) {
+		DRM_INFO("vkms_device is NULL.\n");
+		return;
+	}
+
+	drm_dev_unregister(&vkms_device->drm);
+	drm_dev_put(&vkms_device->drm);
+
+	kfree(vkms_device);
+}
+
+module_init(vkms_init);
+module_exit(vkms_exit);
+
+MODULE_AUTHOR("Haneen Mohammed <hamohammed.sa@gmail.com>");
+MODULE_AUTHOR("Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>");
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h
new file mode 100644
index 000000000000..07be29f2dc44
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_drv.h
@@ -0,0 +1,78 @@
+#ifndef _VKMS_DRV_H_
+#define _VKMS_DRV_H_
+
+#include <drm/drmP.h>
+#include <drm/drm.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_encoder.h>
+#include <linux/hrtimer.h>
+
+#define XRES_MIN    32
+#define YRES_MIN    32
+
+#define XRES_DEF  1024
+#define YRES_DEF   768
+
+#define XRES_MAX  8192
+#define YRES_MAX  8192
+
+static const u32 vkms_formats[] = {
+	DRM_FORMAT_XRGB8888,
+};
+
+struct vkms_output {
+	struct drm_crtc crtc;
+	struct drm_encoder encoder;
+	struct drm_connector connector;
+	struct hrtimer vblank_hrtimer;
+	ktime_t period_ns;
+	struct drm_pending_vblank_event *event;
+};
+
+struct vkms_device {
+	struct drm_device drm;
+	struct platform_device *platform;
+	struct vkms_output output;
+};
+
+struct vkms_gem_object {
+	struct drm_gem_object gem;
+	struct mutex pages_lock; /* Page lock used in page fault handler */
+	struct page **pages;
+};
+
+#define drm_crtc_to_vkms_output(target) \
+	container_of(target, struct vkms_output, crtc)
+
+#define drm_device_to_vkms_device(target) \
+	container_of(target, struct vkms_device, drm)
+
+/* CRTC */
+int vkms_crtc_init(struct drm_device *dev, struct drm_crtc *crtc,
+		   struct drm_plane *primary, struct drm_plane *cursor);
+
+bool vkms_get_vblank_timestamp(struct drm_device *dev, unsigned int pipe,
+			       int *max_error, ktime_t *vblank_time,
+			       bool in_vblank_irq);
+
+int vkms_output_init(struct vkms_device *vkmsdev);
+
+struct drm_plane *vkms_plane_init(struct vkms_device *vkmsdev);
+
+/* Gem stuff */
+struct drm_gem_object *vkms_gem_create(struct drm_device *dev,
+				       struct drm_file *file,
+				       u32 *handle,
+				       u64 size);
+
+int vkms_gem_fault(struct vm_fault *vmf);
+
+int vkms_dumb_create(struct drm_file *file, struct drm_device *dev,
+		     struct drm_mode_create_dumb *args);
+
+int vkms_dumb_map(struct drm_file *file, struct drm_device *dev,
+		  u32 handle, u64 *offset);
+
+void vkms_gem_free_object(struct drm_gem_object *obj);
+
+#endif /* _VKMS_DRV_H_ */
diff --git a/drivers/gpu/drm/vkms/vkms_gem.c b/drivers/gpu/drm/vkms/vkms_gem.c
new file mode 100644
index 000000000000..c7e38368602b
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_gem.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/shmem_fs.h>
+
+#include "vkms_drv.h"
+
+static struct vkms_gem_object *__vkms_gem_create(struct drm_device *dev,
+						 u64 size)
+{
+	struct vkms_gem_object *obj;
+	int ret;
+
+	obj = kzalloc(sizeof(*obj), GFP_KERNEL);
+	if (!obj)
+		return ERR_PTR(-ENOMEM);
+
+	size = roundup(size, PAGE_SIZE);
+	ret = drm_gem_object_init(dev, &obj->gem, size);
+	if (ret) {
+		kfree(obj);
+		return ERR_PTR(ret);
+	}
+
+	mutex_init(&obj->pages_lock);
+
+	return obj;
+}
+
+void vkms_gem_free_object(struct drm_gem_object *obj)
+{
+	struct vkms_gem_object *gem = container_of(obj, struct vkms_gem_object,
+						   gem);
+
+	kvfree(gem->pages);
+	mutex_destroy(&gem->pages_lock);
+	drm_gem_object_release(obj);
+	kfree(gem);
+}
+
+int vkms_gem_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct vkms_gem_object *obj = vma->vm_private_data;
+	unsigned long vaddr = vmf->address;
+	pgoff_t page_offset;
+	loff_t num_pages;
+	int ret;
+
+	page_offset = (vaddr - vma->vm_start) >> PAGE_SHIFT;
+	num_pages = DIV_ROUND_UP(obj->gem.size, PAGE_SIZE);
+
+	if (page_offset > num_pages)
+		return VM_FAULT_SIGBUS;
+
+	ret = -ENOENT;
+	mutex_lock(&obj->pages_lock);
+	if (obj->pages) {
+		get_page(obj->pages[page_offset]);
+		vmf->page = obj->pages[page_offset];
+		ret = 0;
+	}
+	mutex_unlock(&obj->pages_lock);
+	if (ret) {
+		struct page *page;
+		struct address_space *mapping;
+
+		mapping = file_inode(obj->gem.filp)->i_mapping;
+		page = shmem_read_mapping_page(mapping, page_offset);
+
+		if (!IS_ERR(page)) {
+			vmf->page = page;
+			ret = 0;
+		} else {
+			switch (PTR_ERR(page)) {
+			case -ENOSPC:
+			case -ENOMEM:
+				ret = VM_FAULT_OOM;
+				break;
+			case -EBUSY:
+				ret = VM_FAULT_RETRY;
+				break;
+			case -EFAULT:
+			case -EINVAL:
+				ret = VM_FAULT_SIGBUS;
+				break;
+			default:
+				WARN_ON(PTR_ERR(page));
+				ret = VM_FAULT_SIGBUS;
+				break;
+			}
+		}
+	}
+	return ret;
+}
+
+struct drm_gem_object *vkms_gem_create(struct drm_device *dev,
+				       struct drm_file *file,
+				       u32 *handle,
+				       u64 size)
+{
+	struct vkms_gem_object *obj;
+	int ret;
+
+	if (!file || !dev || !handle)
+		return ERR_PTR(-EINVAL);
+
+	obj = __vkms_gem_create(dev, size);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
+
+	ret = drm_gem_handle_create(file, &obj->gem, handle);
+	drm_gem_object_put_unlocked(&obj->gem);
+	if (ret) {
+		drm_gem_object_release(&obj->gem);
+		kfree(obj);
+		return ERR_PTR(ret);
+	}
+
+	return &obj->gem;
+}
+
+int vkms_dumb_create(struct drm_file *file, struct drm_device *dev,
+		     struct drm_mode_create_dumb *args)
+{
+	struct drm_gem_object *gem_obj;
+	u64 pitch, size;
+
+	if (!args || !dev || !file)
+		return -EINVAL;
+
+	pitch = args->width * DIV_ROUND_UP(args->bpp, 8);
+	size = pitch * args->height;
+
+	if (!size)
+		return -EINVAL;
+
+	gem_obj = vkms_gem_create(dev, file, &args->handle, size);
+	if (IS_ERR(gem_obj))
+		return PTR_ERR(gem_obj);
+
+	args->size = gem_obj->size;
+	args->pitch = pitch;
+
+	DRM_DEBUG_DRIVER("Created object of size %lld\n", size);
+
+	return 0;
+}
+
+int vkms_dumb_map(struct drm_file *file, struct drm_device *dev,
+		  u32 handle, u64 *offset)
+{
+	struct drm_gem_object *obj;
+	int ret;
+
+	obj = drm_gem_object_lookup(file, handle);
+	if (!obj)
+		return -ENOENT;
+
+	if (!obj->filp) {
+		ret = -EINVAL;
+		goto unref;
+	}
+
+	ret = drm_gem_create_mmap_offset(obj);
+	if (ret)
+		goto unref;
+
+	*offset = drm_vma_node_offset_addr(&obj->vma_node);
+unref:
+	drm_gem_object_put_unlocked(obj);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/vkms/vkms_output.c b/drivers/gpu/drm/vkms/vkms_output.c
new file mode 100644
index 000000000000..901012cb1af1
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_output.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "vkms_drv.h"
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_atomic_helper.h>
+
+static void vkms_connector_destroy(struct drm_connector *connector)
+{
+	drm_connector_unregister(connector);
+	drm_connector_cleanup(connector);
+}
+
+static const struct drm_connector_funcs vkms_connector_funcs = {
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = vkms_connector_destroy,
+	.reset = drm_atomic_helper_connector_reset,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+};
+
+static const struct drm_encoder_funcs vkms_encoder_funcs = {
+	.destroy = drm_encoder_cleanup,
+};
+
+static int vkms_conn_get_modes(struct drm_connector *connector)
+{
+	int count;
+
+	count = drm_add_modes_noedid(connector, XRES_MAX, YRES_MAX);
+	drm_set_preferred_mode(connector, XRES_DEF, YRES_DEF);
+
+	return count;
+}
+
+static const struct drm_connector_helper_funcs vkms_conn_helper_funcs = {
+	.get_modes    = vkms_conn_get_modes,
+};
+
+int vkms_output_init(struct vkms_device *vkmsdev)
+{
+	struct vkms_output *output = &vkmsdev->output;
+	struct drm_device *dev = &vkmsdev->drm;
+	struct drm_connector *connector = &output->connector;
+	struct drm_encoder *encoder = &output->encoder;
+	struct drm_crtc *crtc = &output->crtc;
+	struct drm_plane *primary;
+	int ret;
+
+	primary = vkms_plane_init(vkmsdev);
+	if (IS_ERR(primary))
+		return PTR_ERR(primary);
+
+	ret = vkms_crtc_init(dev, crtc, primary, NULL);
+	if (ret)
+		goto err_crtc;
+
+	ret = drm_connector_init(dev, connector, &vkms_connector_funcs,
+				 DRM_MODE_CONNECTOR_VIRTUAL);
+	if (ret) {
+		DRM_ERROR("Failed to init connector\n");
+		goto err_connector;
+	}
+
+	drm_connector_helper_add(connector, &vkms_conn_helper_funcs);
+
+	ret = drm_connector_register(connector);
+	if (ret) {
+		DRM_ERROR("Failed to register connector\n");
+		goto err_connector_register;
+	}
+
+	ret = drm_encoder_init(dev, encoder, &vkms_encoder_funcs,
+			       DRM_MODE_ENCODER_VIRTUAL, NULL);
+	if (ret) {
+		DRM_ERROR("Failed to init encoder\n");
+		goto err_encoder;
+	}
+	encoder->possible_crtcs = 1;
+
+	ret = drm_connector_attach_encoder(connector, encoder);
+	if (ret) {
+		DRM_ERROR("Failed to attach connector to encoder\n");
+		goto err_attach;
+	}
+
+	drm_mode_config_reset(dev);
+
+	return 0;
+
+err_attach:
+	drm_encoder_cleanup(encoder);
+
+err_encoder:
+	drm_connector_unregister(connector);
+
+err_connector_register:
+	drm_connector_cleanup(connector);
+
+err_connector:
+	drm_crtc_cleanup(crtc);
+
+err_crtc:
+	drm_plane_cleanup(primary);
+	return ret;
+}
diff --git a/drivers/gpu/drm/vkms/vkms_plane.c b/drivers/gpu/drm/vkms/vkms_plane.c
new file mode 100644
index 000000000000..9f75b1e2c1c4
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_plane.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "vkms_drv.h"
+#include <drm/drm_plane_helper.h>
+#include <drm/drm_atomic_helper.h>
+
+static const struct drm_plane_funcs vkms_plane_funcs = {
+	.update_plane		= drm_atomic_helper_update_plane,
+	.disable_plane		= drm_atomic_helper_disable_plane,
+	.destroy		= drm_plane_cleanup,
+	.reset			= drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state	= drm_atomic_helper_plane_destroy_state,
+};
+
+static void vkms_primary_plane_update(struct drm_plane *plane,
+				      struct drm_plane_state *old_state)
+{
+}
+
+static const struct drm_plane_helper_funcs vkms_primary_helper_funcs = {
+	.atomic_update		= vkms_primary_plane_update,
+};
+
+struct drm_plane *vkms_plane_init(struct vkms_device *vkmsdev)
+{
+	struct drm_device *dev = &vkmsdev->drm;
+	struct drm_plane *plane;
+	const u32 *formats;
+	int ret, nformats;
+
+	plane = kzalloc(sizeof(*plane), GFP_KERNEL);
+	if (!plane)
+		return ERR_PTR(-ENOMEM);
+
+	formats = vkms_formats;
+	nformats = ARRAY_SIZE(vkms_formats);
+
+	ret = drm_universal_plane_init(dev, plane, 0,
+				       &vkms_plane_funcs,
+				       formats, nformats,
+				       NULL, DRM_PLANE_TYPE_PRIMARY, NULL);
+	if (ret) {
+		kfree(plane);
+		return ERR_PTR(ret);
+	}
+
+	drm_plane_helper_add(plane, &vkms_primary_helper_funcs);
+
+	return plane;
+}
diff --git a/drivers/gpu/drm/vmwgfx/Kconfig b/drivers/gpu/drm/vmwgfx/Kconfig
index 8c308dac99c5..6b28a326f8bb 100644
--- a/drivers/gpu/drm/vmwgfx/Kconfig
+++ b/drivers/gpu/drm/vmwgfx/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 config DRM_VMWGFX
 	tristate "DRM driver for VMware Virtual GPU"
 	depends on DRM && PCI && X86 && MMU
diff --git a/drivers/gpu/drm/vmwgfx/Makefile b/drivers/gpu/drm/vmwgfx/Makefile
index 794cc9d5c9b0..09b2aa08363e 100644
--- a/drivers/gpu/drm/vmwgfx/Makefile
+++ b/drivers/gpu/drm/vmwgfx/Makefile
@@ -1,9 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 vmwgfx-y := vmwgfx_execbuf.o vmwgfx_gmr.o vmwgfx_kms.o vmwgfx_drv.o \
-	    vmwgfx_fb.o vmwgfx_ioctl.o vmwgfx_resource.o vmwgfx_buffer.o \
+	    vmwgfx_fb.o vmwgfx_ioctl.o vmwgfx_resource.o vmwgfx_ttm_buffer.o \
 	    vmwgfx_fifo.o vmwgfx_irq.o vmwgfx_ldu.o vmwgfx_ttm_glue.o \
 	    vmwgfx_overlay.o vmwgfx_marker.o vmwgfx_gmrid_manager.o \
-	    vmwgfx_fence.o vmwgfx_dmabuf.o vmwgfx_scrn.o vmwgfx_context.o \
+	    vmwgfx_fence.o vmwgfx_bo.o vmwgfx_scrn.o vmwgfx_context.o \
 	    vmwgfx_surface.o vmwgfx_prime.o vmwgfx_mob.o vmwgfx_shader.o \
 	    vmwgfx_cmdbuf_res.o vmwgfx_cmdbuf.o vmwgfx_stdu.o \
 	    vmwgfx_cotable.o vmwgfx_so.o vmwgfx_binding.o vmwgfx_msg.o \
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_caps.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_caps.h
index 9ce2466a5d00..69c4253fbfbb 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_caps.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_caps.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2007-2015 VMware, Inc.  All rights reserved.
+ * Copyright 2007-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h
index 2dfd57c5f463..9cbba0e8ce6a 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 1998-2015 VMware, Inc.  All rights reserved.
+ * Copyright 1998-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
@@ -46,10 +47,10 @@
  * the SVGA3D protocol and remain reserved; they should not be used in the
  * future.
  *
- * IDs between 1040 and 1999 (inclusive) are available for use by the
+ * IDs between 1040 and 2999 (inclusive) are available for use by the
  * current SVGA3D protocol.
  *
- * FIFO clients other than SVGA3D should stay below 1000, or at 2000
+ * FIFO clients other than SVGA3D should stay below 1000, or at 3000
  * and up.
  */
 
@@ -89,19 +90,19 @@ typedef enum {
    SVGA_3D_CMD_BLIT_SURFACE_TO_SCREEN                     = 1069,
    SVGA_3D_CMD_SURFACE_DEFINE_V2                          = 1070,
    SVGA_3D_CMD_GENERATE_MIPMAPS                           = 1071,
-   SVGA_3D_CMD_VIDEO_CREATE_DECODER                       = 1072,
-   SVGA_3D_CMD_VIDEO_DESTROY_DECODER                      = 1073,
-   SVGA_3D_CMD_VIDEO_CREATE_PROCESSOR                     = 1074,
-   SVGA_3D_CMD_VIDEO_DESTROY_PROCESSOR                    = 1075,
-   SVGA_3D_CMD_VIDEO_DECODE_START_FRAME                   = 1076,
-   SVGA_3D_CMD_VIDEO_DECODE_RENDER                        = 1077,
-   SVGA_3D_CMD_VIDEO_DECODE_END_FRAME                     = 1078,
-   SVGA_3D_CMD_VIDEO_PROCESS_FRAME                        = 1079,
+   SVGA_3D_CMD_DEAD4                                      = 1072,
+   SVGA_3D_CMD_DEAD5                                      = 1073,
+   SVGA_3D_CMD_DEAD6                                      = 1074,
+   SVGA_3D_CMD_DEAD7                                      = 1075,
+   SVGA_3D_CMD_DEAD8                                      = 1076,
+   SVGA_3D_CMD_DEAD9                                      = 1077,
+   SVGA_3D_CMD_DEAD10                                     = 1078,
+   SVGA_3D_CMD_DEAD11                                     = 1079,
    SVGA_3D_CMD_ACTIVATE_SURFACE                           = 1080,
    SVGA_3D_CMD_DEACTIVATE_SURFACE                         = 1081,
    SVGA_3D_CMD_SCREEN_DMA                                 = 1082,
-   SVGA_3D_CMD_SET_UNITY_SURFACE_COOKIE                   = 1083,
-   SVGA_3D_CMD_OPEN_CONTEXT_SURFACE                       = 1084,
+   SVGA_3D_CMD_DEAD1                                      = 1083,
+   SVGA_3D_CMD_DEAD2                                      = 1084,
 
    SVGA_3D_CMD_LOGICOPS_BITBLT                            = 1085,
    SVGA_3D_CMD_LOGICOPS_TRANSBLT                          = 1086,
@@ -217,7 +218,7 @@ typedef enum {
    SVGA_3D_CMD_DX_CLEAR_DEPTHSTENCIL_VIEW                 = 1177,
    SVGA_3D_CMD_DX_PRED_COPY_REGION                        = 1178,
    SVGA_3D_CMD_DX_PRED_COPY                               = 1179,
-   SVGA_3D_CMD_DX_STRETCHBLT                              = 1180,
+   SVGA_3D_CMD_DX_PRESENTBLT                              = 1180,
    SVGA_3D_CMD_DX_GENMIPS                                 = 1181,
    SVGA_3D_CMD_DX_UPDATE_SUBRESOURCE                      = 1182,
    SVGA_3D_CMD_DX_READBACK_SUBRESOURCE                    = 1183,
@@ -254,7 +255,7 @@ typedef enum {
    SVGA_3D_CMD_DX_READBACK_ALL_QUERY                      = 1214,
    SVGA_3D_CMD_DX_PRED_TRANSFER_FROM_BUFFER               = 1215,
    SVGA_3D_CMD_DX_MOB_FENCE_64                            = 1216,
-   SVGA_3D_CMD_DX_BIND_SHADER_ON_CONTEXT                  = 1217,
+   SVGA_3D_CMD_DX_BIND_ALL_SHADER                         = 1217,
    SVGA_3D_CMD_DX_HINT                                    = 1218,
    SVGA_3D_CMD_DX_BUFFER_UPDATE                           = 1219,
    SVGA_3D_CMD_DX_SET_VS_CONSTANT_BUFFER_OFFSET           = 1220,
@@ -262,17 +263,47 @@ typedef enum {
    SVGA_3D_CMD_DX_SET_GS_CONSTANT_BUFFER_OFFSET           = 1222,
 
    /*
-    * Reserve some IDs to be used for the DX11 shader types.
+    * Reserve some IDs to be used for the SM5 shader types.
     */
    SVGA_3D_CMD_DX_RESERVED1                               = 1223,
    SVGA_3D_CMD_DX_RESERVED2                               = 1224,
    SVGA_3D_CMD_DX_RESERVED3                               = 1225,
 
-   SVGA_3D_CMD_DX_MAX                                     = 1226,
-   SVGA_3D_CMD_MAX                                        = 1226,
+   SVGA_3D_CMD_DX_COND_BIND_ALL_SHADER                    = 1226,
+   SVGA_3D_CMD_DX_MAX                                     = 1227,
+
+   SVGA_3D_CMD_SCREEN_COPY                                = 1227,
+
+   /*
+    * Reserve some IDs to be used for video.
+    */
+   SVGA_3D_CMD_VIDEO_RESERVED1                            = 1228,
+   SVGA_3D_CMD_VIDEO_RESERVED2                            = 1229,
+   SVGA_3D_CMD_VIDEO_RESERVED3                            = 1230,
+   SVGA_3D_CMD_VIDEO_RESERVED4                            = 1231,
+   SVGA_3D_CMD_VIDEO_RESERVED5                            = 1232,
+   SVGA_3D_CMD_VIDEO_RESERVED6                            = 1233,
+   SVGA_3D_CMD_VIDEO_RESERVED7                            = 1234,
+   SVGA_3D_CMD_VIDEO_RESERVED8                            = 1235,
+
+   SVGA_3D_CMD_GROW_OTABLE                                = 1236,
+   SVGA_3D_CMD_DX_GROW_COTABLE                            = 1237,
+   SVGA_3D_CMD_INTRA_SURFACE_COPY                         = 1238,
+
+   SVGA_3D_CMD_DEFINE_GB_SURFACE_V3                       = 1239,
+
+   SVGA_3D_CMD_DX_RESOLVE_COPY                            = 1240,
+   SVGA_3D_CMD_DX_PRED_RESOLVE_COPY                       = 1241,
+   SVGA_3D_CMD_DX_PRED_CONVERT_REGION                     = 1242,
+   SVGA_3D_CMD_DX_PRED_CONVERT                            = 1243,
+   SVGA_3D_CMD_WHOLE_SURFACE_COPY                         = 1244,
+
+   SVGA_3D_CMD_MAX                                        = 1245,
    SVGA_3D_CMD_FUTURE_MAX                                 = 3000
 } SVGAFifo3dCmdId;
 
+#define SVGA_NUM_3D_CMD (SVGA_3D_CMD_MAX - SVGA_3D_CMD_BASE)
+
 /*
  * FIFO command format definitions:
  */
@@ -301,7 +332,7 @@ typedef
 #include "vmware_pack_begin.h"
 struct {
    uint32                      sid;
-   SVGA3dSurfaceFlags          surfaceFlags;
+   SVGA3dSurface1Flags         surfaceFlags;
    SVGA3dSurfaceFormat         format;
    /*
     * If surfaceFlags has SVGA3D_SURFACE_CUBEMAP bit set, all SVGA3dSurfaceFace
@@ -327,7 +358,7 @@ typedef
 #include "vmware_pack_begin.h"
 struct {
    uint32                      sid;
-   SVGA3dSurfaceFlags          surfaceFlags;
+   SVGA3dSurface1Flags         surfaceFlags;
    SVGA3dSurfaceFormat         format;
    /*
     * If surfaceFlags has SVGA3D_SURFACE_CUBEMAP bit set, all SVGA3dSurfaceFace
@@ -459,6 +490,28 @@ struct {
 #include "vmware_pack_end.h"
 SVGA3dCmdSurfaceCopy;               /* SVGA_3D_CMD_SURFACE_COPY */
 
+/*
+ * Perform a surface copy within the same image.
+ * The src/dest boxes are allowed to overlap.
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   SVGA3dSurfaceImageId  surface;
+   SVGA3dCopyBox box;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdIntraSurfaceCopy;               /* SVGA_3D_CMD_INTRA_SURFACE_COPY */
+
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   uint32 srcSid;
+   uint32 destSid;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdWholeSurfaceCopy;               /* SVGA_3D_CMD_WHOLE_SURFACE_COPY */
+
 typedef
 #include "vmware_pack_begin.h"
 struct {
@@ -772,6 +825,17 @@ struct {
 #include "vmware_pack_end.h"
 SVGA3dVertexElement;
 
+/*
+ * Should the vertex element respect the stream value?  The high bit of the
+ * stream should be set to indicate that the stream should be respected.  If
+ * the high bit is not set, the stream will be ignored and replaced by the index
+ * of the position of the currently considered vertex element.
+ *
+ * All guests should set this bit and correctly specify the stream going
+ * forward.
+ */
+#define SVGA3D_VERTEX_ELEMENT_RESPECT_STREAM (1 << 7)
+
 typedef
 #include "vmware_pack_begin.h"
 struct {
@@ -1102,8 +1166,6 @@ struct {
 #include "vmware_pack_end.h"
 SVGA3dCmdGenerateMipmaps;             /* SVGA_3D_CMD_GENERATE_MIPMAPS */
 
-
-
 typedef
 #include "vmware_pack_begin.h"
 struct {
@@ -1147,38 +1209,6 @@ struct SVGA3dCmdScreenDMA {
 SVGA3dCmdScreenDMA;        /* SVGA_3D_CMD_SCREEN_DMA */
 
 /*
- * Set Unity Surface Cookie
- *
- * Associates the supplied cookie with the surface id for use with
- * Unity.  This cookie is a hint from guest to host, there is no way
- * for the guest to readback the cookie and the host is free to drop
- * the cookie association at will.  The default value for the cookie
- * on all surfaces is 0.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdSetUnitySurfaceCookie {
-   uint32 sid;
-   uint64 cookie;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetUnitySurfaceCookie;   /* SVGA_3D_CMD_SET_UNITY_SURFACE_COOKIE */
-
-/*
- * Open a context-specific surface in a non-context-specific manner.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdOpenContextSurface {
-   uint32 sid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdOpenContextSurface;   /* SVGA_3D_CMD_OPEN_CONTEXT_SURFACE */
-
-
-/*
  * Logic ops
  */
 
@@ -1324,7 +1354,7 @@ typedef
 #include "vmware_pack_begin.h"
 struct {
    SVGA3dSurfaceFormat format;
-   SVGA3dSurfaceFlags surfaceFlags;
+   SVGA3dSurface1Flags surface1Flags;
    uint32 numMipLevels;
    uint32 multisampleCount;
    SVGA3dTextureFilter autogenFilter;
@@ -1332,7 +1362,11 @@ struct {
    SVGAMobId mobid;
    uint32 arraySize;
    uint32 mobPitch;
-   uint32 pad[5];
+   SVGA3dSurface2Flags surface2Flags;
+   uint8 multisamplePattern;
+   uint8 qualityLevel;
+   uint8  pad0[2];
+   uint32 pad1[3];
 }
 #include "vmware_pack_end.h"
 SVGAOTableSurfaceEntry;
@@ -1360,7 +1394,8 @@ struct {
 SVGAOTableShaderEntry;
 #define SVGA3D_OTABLE_SHADER_ENTRY_SIZE (sizeof(SVGAOTableShaderEntry))
 
-#define SVGA_STFLAG_PRIMARY (1 << 0)
+#define SVGA_STFLAG_PRIMARY  (1 << 0)
+#define SVGA_STFLAG_RESERVED (1 << 1) /* Added with cap SVGA_CAP_HP_CMD_QUEUE */
 typedef uint32 SVGAScreenTargetFlags;
 
 typedef
@@ -1528,6 +1563,25 @@ struct {
 #include "vmware_pack_end.h"
 SVGA3dCmdSetOTableBase64;  /* SVGA_3D_CMD_SET_OTABLE_BASE64 */
 
+/*
+ * Guests using SVGA_3D_CMD_GROW_OTABLE are promising that
+ * the new OTable contains the same contents as the old one, except possibly
+ * for some new invalid entries at the end.
+ *
+ * (Otherwise, guests should use one of the SetOTableBase commands.)
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   SVGAOTableType type;
+   PPN64 baseAddress;
+   uint32 sizeInBytes;
+   uint32 validSizeInBytes;
+   SVGAMobFormat ptDepth;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdGrowOTable;  /* SVGA_3D_CMD_GROW_OTABLE */
+
 typedef
 #include "vmware_pack_begin.h"
 struct {
@@ -1615,7 +1669,7 @@ typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dCmdDefineGBSurface {
    uint32 sid;
-   SVGA3dSurfaceFlags surfaceFlags;
+   SVGA3dSurface1Flags surfaceFlags;
    SVGA3dSurfaceFormat format;
    uint32 numMipLevels;
    uint32 multisampleCount;
@@ -1626,6 +1680,45 @@ struct SVGA3dCmdDefineGBSurface {
 SVGA3dCmdDefineGBSurface;   /* SVGA_3D_CMD_DEFINE_GB_SURFACE */
 
 /*
+ * Defines a guest-backed surface, adding the arraySize field.
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDefineGBSurface_v2 {
+   uint32 sid;
+   SVGA3dSurface1Flags surfaceFlags;
+   SVGA3dSurfaceFormat format;
+   uint32 numMipLevels;
+   uint32 multisampleCount;
+   SVGA3dTextureFilter autogenFilter;
+   SVGA3dSize size;
+   uint32 arraySize;
+   uint32 pad;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDefineGBSurface_v2;   /* SVGA_3D_CMD_DEFINE_GB_SURFACE_V2 */
+
+/*
+ * Defines a guest-backed surface, adding the larger flags.
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDefineGBSurface_v3 {
+   uint32 sid;
+   SVGA3dSurfaceAllFlags surfaceFlags;
+   SVGA3dSurfaceFormat format;
+   uint32 numMipLevels;
+   uint32 multisampleCount;
+   SVGA3dMSPattern multisamplePattern;
+   SVGA3dMSQualityLevel qualityLevel;
+   SVGA3dTextureFilter autogenFilter;
+   SVGA3dSize size;
+   uint32 arraySize;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDefineGBSurface_v3;   /* SVGA_3D_CMD_DEFINE_GB_SURFACE_V3 */
+
+/*
  * Destroy a guest-backed surface.
  */
 
@@ -1672,7 +1765,7 @@ SVGA3dCmdBindGBSurfaceWithPitch;   /* SVGA_3D_CMD_BIND_GB_SURFACE_WITH_PITCH */
 
 typedef
 #include "vmware_pack_begin.h"
-struct{
+struct SVGA3dCmdCondBindGBSurface {
    uint32 sid;
    SVGAMobId testMobid;
    SVGAMobId mobid;
@@ -2066,6 +2159,26 @@ struct {
    uint32 mobOffset;
 }
 #include "vmware_pack_end.h"
-SVGA3dCmdGBMobFence;  /* SVGA_3D_CMD_GB_MOB_FENCE*/
+SVGA3dCmdGBMobFence;  /* SVGA_3D_CMD_GB_MOB_FENCE */
+
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   uint32 stid;
+   SVGA3dSurfaceImageId dest;
+
+   uint32 statusMobId;
+   uint32 statusMobOffset;
+
+   /* Reserved fields */
+   uint32 mustBeInvalidId;
+   uint32 mustBeZero;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdScreenCopy;  /* SVGA_3D_CMD_SCREEN_COPY */
+
+#define SVGA_SCREEN_COPY_STATUS_FAILURE 0x00
+#define SVGA_SCREEN_COPY_STATUS_SUCCESS 0x01
+#define SVGA_SCREEN_COPY_STATUS_INVALID 0xFFFFFFFF
 
 #endif /* _SVGA3D_CMD_H_ */
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h
index c18b663f360f..f256560049bf 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 1998-2015 VMware, Inc.  All rights reserved.
+ * Copyright 1998-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
@@ -229,9 +230,9 @@ typedef enum {
    SVGA3D_DEVCAP_DEAD2                             = 94,
 
    /*
-    * Does the device support the DX commands?
+    * Does the device support DXContexts?
     */
-   SVGA3D_DEVCAP_DX                                = 95,
+   SVGA3D_DEVCAP_DXCONTEXT                         = 95,
 
    /*
     * What is the maximum size of a texture array?
@@ -241,21 +242,47 @@ typedef enum {
    SVGA3D_DEVCAP_MAX_TEXTURE_ARRAY_SIZE            = 96,
 
    /*
-    * What is the maximum number of vertex buffers that can
-    * be used in the DXContext inputAssembly?
+    * What is the maximum number of vertex buffers or vertex input registers
+    * that can be expected to work correctly with a DXContext?
+    *
+    * The guest is allowed to set up to SVGA3D_DX_MAX_VERTEXBUFFERS, but
+    * anything in excess of this cap is not guaranteed to render correctly.
+    *
+    * Similarly, the guest can set up to SVGA3D_DX_MAX_VERTEXINPUTREGISTERS
+    * input registers without the SVGA3D_DEVCAP_SM4_1 cap, or
+    * SVGA3D_DX_SM41_MAX_VERTEXINPUTREGISTERS with the SVGA3D_DEVCAP_SM4_1,
+    * but only the registers up to this cap value are guaranteed to render
+    * correctly.
+    *
+    * If guest-drivers are able to expose a lower-limit, it's recommended
+    * that they clamp to this value.  Otherwise, the host will make a
+    * best-effort on case-by-case basis if guests exceed this.
     */
    SVGA3D_DEVCAP_DX_MAX_VERTEXBUFFERS              = 97,
 
    /*
-    * What is the maximum number of constant buffers
-    * that can be expected to work correctly with a
-    * DX context?
+    * What is the maximum number of constant buffers that can be expected to
+    * work correctly with a DX context?
+    *
+    * The guest is allowed to set up to SVGA3D_DX_MAX_CONSTBUFFERS, but
+    * anything in excess of this cap is not guaranteed to render correctly.
+    *
+    * If guest-drivers are able to expose a lower-limit, it's recommended
+    * that they clamp to this value.  Otherwise, the host will make a
+    * best-effort on case-by-case basis if guests exceed this.
     */
    SVGA3D_DEVCAP_DX_MAX_CONSTANT_BUFFERS           = 98,
 
    /*
     * Does the device support provoking vertex control?
-    * If zero, the first vertex will always be the provoking vertex.
+    *
+    * If this cap is present, the provokingVertexLast field in the
+    * rasterizer state is enabled.  (Guests can then set it to FALSE,
+    * meaning that the first vertex is the provoking vertex, or TRUE,
+    * meaning that the last verteix is the provoking vertex.)
+    *
+    * If this cap is FALSE, then guests should set the provokingVertexLast
+    * to FALSE, otherwise rendering behavior is undefined.
     */
    SVGA3D_DEVCAP_DX_PROVOKING_VERTEX               = 99,
 
@@ -281,7 +308,7 @@ typedef enum {
    SVGA3D_DEVCAP_DXFMT_BUMPU8V8                    = 119,
    SVGA3D_DEVCAP_DXFMT_BUMPL6V5U5                  = 120,
    SVGA3D_DEVCAP_DXFMT_BUMPX8L8V8U8                = 121,
-   SVGA3D_DEVCAP_DXFMT_BUMPL8V8U8                  = 122,
+   SVGA3D_DEVCAP_DXFMT_FORMAT_DEAD1                = 122,
    SVGA3D_DEVCAP_DXFMT_ARGB_S10E5                  = 123,
    SVGA3D_DEVCAP_DXFMT_ARGB_S23E8                  = 124,
    SVGA3D_DEVCAP_DXFMT_A2R10G10B10                 = 125,
@@ -320,8 +347,8 @@ typedef enum {
    SVGA3D_DEVCAP_DXFMT_R32G32_SINT                 = 158,
    SVGA3D_DEVCAP_DXFMT_R32G8X24_TYPELESS           = 159,
    SVGA3D_DEVCAP_DXFMT_D32_FLOAT_S8X24_UINT        = 160,
-   SVGA3D_DEVCAP_DXFMT_R32_FLOAT_X8X24_TYPELESS    = 161,
-   SVGA3D_DEVCAP_DXFMT_X32_TYPELESS_G8X24_UINT     = 162,
+   SVGA3D_DEVCAP_DXFMT_R32_FLOAT_X8X24             = 161,
+   SVGA3D_DEVCAP_DXFMT_X32_G8X24_UINT              = 162,
    SVGA3D_DEVCAP_DXFMT_R10G10B10A2_TYPELESS        = 163,
    SVGA3D_DEVCAP_DXFMT_R10G10B10A2_UINT            = 164,
    SVGA3D_DEVCAP_DXFMT_R11G11B10_FLOAT             = 165,
@@ -339,8 +366,8 @@ typedef enum {
    SVGA3D_DEVCAP_DXFMT_R32_SINT                    = 177,
    SVGA3D_DEVCAP_DXFMT_R24G8_TYPELESS              = 178,
    SVGA3D_DEVCAP_DXFMT_D24_UNORM_S8_UINT           = 179,
-   SVGA3D_DEVCAP_DXFMT_R24_UNORM_X8_TYPELESS       = 180,
-   SVGA3D_DEVCAP_DXFMT_X24_TYPELESS_G8_UINT        = 181,
+   SVGA3D_DEVCAP_DXFMT_R24_UNORM_X8                = 180,
+   SVGA3D_DEVCAP_DXFMT_X24_G8_UINT                 = 181,
    SVGA3D_DEVCAP_DXFMT_R8G8_TYPELESS               = 182,
    SVGA3D_DEVCAP_DXFMT_R8G8_UNORM                  = 183,
    SVGA3D_DEVCAP_DXFMT_R8G8_UINT                   = 184,
@@ -404,6 +431,17 @@ typedef enum {
    SVGA3D_DEVCAP_DXFMT_BC4_UNORM                   = 242,
    SVGA3D_DEVCAP_DXFMT_BC5_UNORM                   = 243,
 
+   /*
+    * Advertises shaderModel 4.1 support, independent blend-states,
+    * cube-map arrays, and a higher vertex input registers limit.
+    *
+    * (See documentation on SVGA3D_DEVCAP_DX_MAX_VERTEXBUFFERS.)
+    */
+   SVGA3D_DEVCAP_SM41                              = 244,
+
+   SVGA3D_DEVCAP_MULTISAMPLE_2X                    = 245,
+   SVGA3D_DEVCAP_MULTISAMPLE_4X                    = 246,
+
    SVGA3D_DEVCAP_MAX                       /* This must be the last index. */
 } SVGA3dDevCapIndex;
 
@@ -419,9 +457,7 @@ typedef enum {
  * MIPS: Does the format support mip levels?
  * ARRAY: Does the format support texture arrays?
  * VOLUME: Does the format support having volume?
- * MULTISAMPLE_2: Does the format support 2x multisample?
- * MULTISAMPLE_4: Does the format support 4x multisample?
- * MULTISAMPLE_8: Does the format support 8x multisample?
+ * MULTISAMPLE: Does the format support multisample?
  */
 #define SVGA3D_DXFMT_SUPPORTED                (1 <<  0)
 #define SVGA3D_DXFMT_SHADER_SAMPLE            (1 <<  1)
@@ -432,20 +468,8 @@ typedef enum {
 #define SVGA3D_DXFMT_ARRAY                    (1 <<  6)
 #define SVGA3D_DXFMT_VOLUME                   (1 <<  7)
 #define SVGA3D_DXFMT_DX_VERTEX_BUFFER         (1 <<  8)
-#define SVGADX_DXFMT_MULTISAMPLE_2            (1 <<  9)
-#define SVGADX_DXFMT_MULTISAMPLE_4            (1 << 10)
-#define SVGADX_DXFMT_MULTISAMPLE_8            (1 << 11)
-#define SVGADX_DXFMT_MAX                      (1 << 12)
-
-/*
- * Convenience mask for any multisample capability.
- *
- * The multisample bits imply both load and render capability.
- */
-#define SVGA3D_DXFMT_MULTISAMPLE ( \
-           SVGADX_DXFMT_MULTISAMPLE_2 | \
-           SVGADX_DXFMT_MULTISAMPLE_4 | \
-           SVGADX_DXFMT_MULTISAMPLE_8 )
+#define SVGA3D_DXFMT_MULTISAMPLE              (1 <<  9)
+#define SVGA3D_DXFMT_MAX                      (1 << 10)
 
 typedef union {
    Bool   b;
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h
index 8c5ae608cfb4..7a49c94df221 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2012-2015 VMware, Inc.  All rights reserved.
+ * Copyright 2012-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
@@ -56,6 +57,16 @@ typedef uint32 SVGA3dInputClassification;
 #define SVGA3D_RESOURCE_TYPE_MAX      7
 typedef uint32 SVGA3dResourceType;
 
+#define SVGA3D_COLOR_WRITE_ENABLE_RED     (1 << 0)
+#define SVGA3D_COLOR_WRITE_ENABLE_GREEN   (1 << 1)
+#define SVGA3D_COLOR_WRITE_ENABLE_BLUE    (1 << 2)
+#define SVGA3D_COLOR_WRITE_ENABLE_ALPHA   (1 << 3)
+#define SVGA3D_COLOR_WRITE_ENABLE_ALL     (SVGA3D_COLOR_WRITE_ENABLE_RED |   \
+                                           SVGA3D_COLOR_WRITE_ENABLE_GREEN | \
+                                           SVGA3D_COLOR_WRITE_ENABLE_BLUE |  \
+                                           SVGA3D_COLOR_WRITE_ENABLE_ALPHA)
+typedef uint8 SVGA3dColorWriteEnable;
+
 #define SVGA3D_DEPTH_WRITE_MASK_ZERO   0
 #define SVGA3D_DEPTH_WRITE_MASK_ALL    1
 typedef uint8 SVGA3dDepthWriteMask;
@@ -88,17 +99,28 @@ typedef uint8 SVGA3dCullMode;
 #define SVGA3D_COMPARISON_MAX             9
 typedef uint8 SVGA3dComparisonFunc;
 
+/*
+ * SVGA3D_MULTISAMPLE_RAST_DISABLE disables MSAA for all primitives.
+ * SVGA3D_MULTISAMPLE_RAST_DISABLE_LINE, which is supported in SM41,
+ * disables MSAA for lines only.
+ */
+#define SVGA3D_MULTISAMPLE_RAST_DISABLE        0
+#define SVGA3D_MULTISAMPLE_RAST_ENABLE         1
+#define SVGA3D_MULTISAMPLE_RAST_DX_MAX         1
+#define SVGA3D_MULTISAMPLE_RAST_DISABLE_LINE   2
+#define SVGA3D_MULTISAMPLE_RAST_MAX            2
+typedef uint8 SVGA3dMultisampleRastEnable;
+
 #define SVGA3D_DX_MAX_VERTEXBUFFERS 32
+#define SVGA3D_DX_MAX_VERTEXINPUTREGISTERS 16
+#define SVGA3D_DX_SM41_MAX_VERTEXINPUTREGISTERS 32
 #define SVGA3D_DX_MAX_SOTARGETS 4
 #define SVGA3D_DX_MAX_SRVIEWS 128
 #define SVGA3D_DX_MAX_CONSTBUFFERS 16
 #define SVGA3D_DX_MAX_SAMPLERS 16
 
-/* Id limits */
-static const uint32 SVGA3dBlendObjectCountPerContext = 4096;
-static const uint32 SVGA3dDepthStencilObjectCountPerContext = 4096;
+#define SVGA3D_DX_MAX_CONSTBUF_BINDING_SIZE (4096 * 4 * (uint32)sizeof(uint32))
 
-typedef uint32 SVGA3dSurfaceId;
 typedef uint32 SVGA3dShaderResourceViewId;
 typedef uint32 SVGA3dRenderTargetViewId;
 typedef uint32 SVGA3dDepthStencilViewId;
@@ -194,20 +216,6 @@ SVGA3dCmdDXInvalidateContext;   /* SVGA_3D_CMD_DX_INVALIDATE_CONTEXT */
 
 typedef
 #include "vmware_pack_begin.h"
-struct SVGA3dReplyFormatData {
-   uint32 formatSupport;
-   uint32 msaa2xQualityLevels:5;
-   uint32 msaa4xQualityLevels:5;
-   uint32 msaa8xQualityLevels:5;
-   uint32 msaa16xQualityLevels:5;
-   uint32 msaa32xQualityLevels:5;
-   uint32 pad:7;
-}
-#include "vmware_pack_end.h"
-SVGA3dReplyFormatData;
-
-typedef
-#include "vmware_pack_begin.h"
 struct SVGA3dCmdDXSetSingleConstantBuffer {
    uint32 slot;
    SVGA3dShaderType type;
@@ -624,6 +632,28 @@ SVGA3dCmdDXPredCopy; /* SVGA_3D_CMD_DX_PRED_COPY */
 
 typedef
 #include "vmware_pack_begin.h"
+struct SVGA3dCmdDXPredConvertRegion {
+   SVGA3dSurfaceId dstSid;
+   uint32 dstSubResource;
+   SVGA3dBox destBox;
+   SVGA3dSurfaceId srcSid;
+   uint32 srcSubResource;
+   SVGA3dBox srcBox;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXPredConvertRegion; /* SVGA_3D_CMD_DX_PRED_CONVERT_REGION */
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXPredConvert {
+   SVGA3dSurfaceId dstSid;
+   SVGA3dSurfaceId srcSid;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXPredConvert; /* SVGA_3D_CMD_DX_PRED_CONVERT */
+
+typedef
+#include "vmware_pack_begin.h"
 struct SVGA3dCmdDXBufferCopy {
    SVGA3dSurfaceId dest;
    SVGA3dSurfaceId src;
@@ -635,23 +665,57 @@ struct SVGA3dCmdDXBufferCopy {
 SVGA3dCmdDXBufferCopy;
 /* SVGA_3D_CMD_DX_BUFFER_COPY */
 
-typedef uint32 SVGA3dDXStretchBltMode;
-#define SVGADX_STRETCHBLT_LINEAR         (1 << 0)
-#define SVGADX_STRETCHBLT_FORCE_SRC_SRGB (1 << 1)
+/*
+ * Perform a surface copy between a multisample, and a non-multisampled
+ * surface.
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   SVGA3dSurfaceId dstSid;
+   uint32 dstSubResource;
+   SVGA3dSurfaceId srcSid;
+   uint32 srcSubResource;
+   SVGA3dSurfaceFormat copyFormat;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXResolveCopy;               /* SVGA_3D_CMD_DX_RESOLVE_COPY */
+
+/*
+ * Perform a predicated surface copy between a multisample, and a
+ * non-multisampled surface.
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   SVGA3dSurfaceId dstSid;
+   uint32 dstSubResource;
+   SVGA3dSurfaceId srcSid;
+   uint32 srcSubResource;
+   SVGA3dSurfaceFormat copyFormat;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXPredResolveCopy;           /* SVGA_3D_CMD_DX_PRED_RESOLVE_COPY */
+
+typedef uint32 SVGA3dDXPresentBltMode;
+#define SVGADX_PRESENTBLT_LINEAR           (1 << 0)
+#define SVGADX_PRESENTBLT_FORCE_SRC_SRGB   (1 << 1)
+#define SVGADX_PRESENTBLT_FORCE_SRC_XRBIAS (1 << 2)
+#define SVGADX_PRESENTBLT_MODE_MAX         (1 << 3)
 
 typedef
 #include "vmware_pack_begin.h"
-struct SVGA3dCmdDXStretchBlt {
+struct SVGA3dCmdDXPresentBlt {
    SVGA3dSurfaceId srcSid;
    uint32 srcSubResource;
    SVGA3dSurfaceId dstSid;
    uint32 destSubResource;
    SVGA3dBox boxSrc;
    SVGA3dBox boxDest;
-   SVGA3dDXStretchBltMode mode;
+   SVGA3dDXPresentBltMode mode;
 }
 #include "vmware_pack_end.h"
-SVGA3dCmdDXStretchBlt; /* SVGA_3D_CMD_DX_STRETCHBLT */
+SVGA3dCmdDXPresentBlt; /* SVGA_3D_CMD_DX_PRESENTBLT*/
 
 typedef
 #include "vmware_pack_begin.h"
@@ -662,26 +726,6 @@ struct SVGA3dCmdDXGenMips {
 SVGA3dCmdDXGenMips; /* SVGA_3D_CMD_DX_GENMIPS */
 
 /*
- * Defines a resource/DX surface.  Resources share the surfaceId namespace.
- *
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDefineGBSurface_v2 {
-   uint32 sid;
-   SVGA3dSurfaceFlags surfaceFlags;
-   SVGA3dSurfaceFormat format;
-   uint32 numMipLevels;
-   uint32 multisampleCount;
-   SVGA3dTextureFilter autogenFilter;
-   SVGA3dSize size;
-   uint32 arraySize;
-   uint32 pad;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDefineGBSurface_v2;   /* SVGA_3D_CMD_DEFINE_GB_SURFACE_V2 */
-
-/*
  * Update a sub-resource in a guest-backed resource.
  * (Inform the device that the guest-contents have been updated.)
  */
@@ -724,7 +768,8 @@ SVGA3dCmdDXInvalidateSubResource;   /* SVGA_3D_CMD_DX_INVALIDATE_SUBRESOURCE */
 
 /*
  * Raw byte wise transfer from a buffer surface into another surface
- * of the requested box.
+ * of the requested box.  Supported if 3d is enabled and SVGA_CAP_DX
+ * is set.  This command does not take a context.
  */
 typedef
 #include "vmware_pack_begin.h"
@@ -773,6 +818,93 @@ struct SVGA3dCmdDXSurfaceCopyAndReadback {
 SVGA3dCmdDXSurfaceCopyAndReadback;
 /* SVGA_3D_CMD_DX_SURFACE_COPY_AND_READBACK */
 
+/*
+ * SVGA_DX_HINT_NONE: Does nothing.
+ *
+ * SVGA_DX_HINT_PREFETCH_OBJECT:
+ * SVGA_DX_HINT_PREEVICT_OBJECT:
+ *      Consumes a SVGAObjectRef, and hints that the host should consider
+ *      fetching/evicting the specified object.
+ *
+ *      An id of SVGA3D_INVALID_ID can be used if the guest isn't sure
+ *      what object was affected.  (For instance, if the guest knows that
+ *      it is about to evict a DXShader, but doesn't know precisely which one,
+ *      the device can still use this to help limit it's search, or track
+ *      how many page-outs have happened.)
+ *
+ * SVGA_DX_HINT_PREFETCH_COBJECT:
+ * SVGA_DX_HINT_PREEVICT_COBJECT:
+ *      Same as the above, except they consume an SVGACObjectRef.
+ */
+typedef uint32 SVGADXHintId;
+#define SVGA_DX_HINT_NONE              0
+#define SVGA_DX_HINT_PREFETCH_OBJECT   1
+#define SVGA_DX_HINT_PREEVICT_OBJECT   2
+#define SVGA_DX_HINT_PREFETCH_COBJECT  3
+#define SVGA_DX_HINT_PREEVICT_COBJECT  4
+#define SVGA_DX_HINT_MAX               5
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGAObjectRef {
+   SVGAOTableType type;
+   uint32 id;
+}
+#include "vmware_pack_end.h"
+SVGAObjectRef;
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGACObjectRef {
+   SVGACOTableType type;
+   uint32 cid;
+   uint32 id;
+}
+#include "vmware_pack_end.h"
+SVGACObjectRef;
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXHint {
+   SVGADXHintId hintId;
+
+   /*
+    * Followed by variable sized data depending on the hintId.
+    */
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXHint;
+/* SVGA_3D_CMD_DX_HINT */
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXBufferUpdate {
+   SVGA3dSurfaceId sid;
+   uint32 x;
+   uint32 width;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXBufferUpdate;
+/* SVGA_3D_CMD_DX_BUFFER_UPDATE */
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXSetConstantBufferOffset {
+   uint32 slot;
+   uint32 offsetInBytes;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXSetConstantBufferOffset;
+
+typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetVSConstantBufferOffset;
+/* SVGA_3D_CMD_DX_SET_VS_CONSTANT_BUFFER_OFFSET */
+
+typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetPSConstantBufferOffset;
+/* SVGA_3D_CMD_DX_SET_PS_CONSTANT_BUFFER_OFFSET */
+
+typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetGSConstantBufferOffset;
+/* SVGA_3D_CMD_DX_SET_GS_CONSTANT_BUFFER_OFFSET */
+
 
 typedef
 #include "vmware_pack_begin.h"
@@ -789,7 +921,7 @@ struct {
          uint32 firstArraySlice;
          uint32 mipLevels;
          uint32 arraySize;
-      } tex;
+      } tex; /* 1d, 2d, 3d, cube */
       struct {
          uint32 firstElement;
          uint32 numElements;
@@ -844,6 +976,7 @@ struct SVGA3dRenderTargetViewDesc {
       struct {
          uint32 firstElement;
          uint32 numElements;
+         uint32 padding0;
       } buffer;
       struct {
          uint32 mipSlice;
@@ -964,9 +1097,6 @@ SVGA3dInputElementDesc;
 typedef
 #include "vmware_pack_begin.h"
 struct {
-   /*
-    * XXX: How many of these can there be?
-    */
    uint32 elid;
    uint32 numDescs;
    SVGA3dInputElementDesc desc[32];
@@ -1007,7 +1137,7 @@ struct SVGA3dDXBlendStatePerRT {
       uint8 srcBlendAlpha;
       uint8 destBlendAlpha;
       uint8 blendOpAlpha;
-      uint8 renderTargetWriteMask;
+      SVGA3dColorWriteEnable renderTargetWriteMask;
       uint8 logicOpEnable;
       uint8 logicOp;
       uint16 pad0;
@@ -1125,7 +1255,7 @@ struct {
    float slopeScaledDepthBias;
    uint8 depthClipEnable;
    uint8 scissorEnable;
-   uint8 multisampleEnable;
+   SVGA3dMultisampleRastEnable multisampleEnable;
    uint8 antialiasedLineEnable;
    float lineWidth;
    uint8 lineStippleEnable;
@@ -1152,7 +1282,7 @@ struct SVGA3dCmdDXDefineRasterizerState {
    float slopeScaledDepthBias;
    uint8 depthClipEnable;
    uint8 scissorEnable;
-   uint8 multisampleEnable;
+   SVGA3dMultisampleRastEnable multisampleEnable;
    uint8 antialiasedLineEnable;
    float lineWidth;
    uint8 lineStippleEnable;
@@ -1222,21 +1352,6 @@ struct SVGA3dCmdDXDestroySamplerState {
 #include "vmware_pack_end.h"
 SVGA3dCmdDXDestroySamplerState; /* SVGA_3D_CMD_DX_DESTROY_SAMPLER_STATE */
 
-/*
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dSignatureEntry {
-   uint8 systemValue;
-   uint8 reg;                 /* register is a reserved word */
-   uint16 mask;
-   uint8 registerComponentType;
-   uint8 minPrecision;
-   uint16 pad0;
-}
-#include "vmware_pack_end.h"
-SVGA3dSignatureEntry;
-
 typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dCmdDXDefineShader {
@@ -1254,12 +1369,7 @@ struct SVGACOTableDXShaderEntry {
    uint32 sizeInBytes;
    uint32 offsetInBytes;
    SVGAMobId mobid;
-   uint32 numInputSignatureEntries;
-   uint32 numOutputSignatureEntries;
-
-   uint32 numPatchConstantSignatureEntries;
-
-   uint32 pad;
+   uint32 pad[4];
 }
 #include "vmware_pack_end.h"
 SVGACOTableDXShaderEntry;
@@ -1283,6 +1393,25 @@ struct SVGA3dCmdDXBindShader {
 #include "vmware_pack_end.h"
 SVGA3dCmdDXBindShader;   /* SVGA_3D_CMD_DX_BIND_SHADER */
 
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXBindAllShader {
+   uint32 cid;
+   SVGAMobId mobid;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXBindAllShader;   /* SVGA_3D_CMD_DX_BIND_ALL_SHADER */
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXCondBindAllShader {
+   uint32 cid;
+   SVGAMobId testMobid;
+   SVGAMobId mobid;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXCondBindAllShader;   /* SVGA_3D_CMD_DX_COND_BIND_ALL_SHADER */
+
 /*
  * The maximum number of streamout decl's in each streamout entry.
  */
@@ -1356,7 +1485,6 @@ SVGA3dCmdDXMobFence64;  /* SVGA_3D_CMD_DX_MOB_FENCE_64 */
  *
  * This command allows the guest to bind a mob to a context-object table.
  */
-
 typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dCmdDXSetCOTable {
@@ -1368,6 +1496,26 @@ struct SVGA3dCmdDXSetCOTable {
 #include "vmware_pack_end.h"
 SVGA3dCmdDXSetCOTable; /* SVGA_3D_CMD_DX_SET_COTABLE */
 
+/*
+ * Guests using SVGA_3D_CMD_DX_GROW_COTABLE are promising that
+ * the new COTable contains the same contents as the old one, except possibly
+ * for some new invalid entries at the end.
+ *
+ * If there is an old cotable mob bound, it also has to still be valid.
+ *
+ * (Otherwise, guests should use the DXSetCOTableBase command.)
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXGrowCOTable {
+   uint32 cid;
+   uint32 mobid;
+   SVGACOTableType type;
+   uint32 validSizeInBytes;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXGrowCOTable; /* SVGA_3D_CMD_DX_GROW_COTABLE */
+
 typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dCmdDXReadbackCOTable {
@@ -1471,7 +1619,7 @@ struct SVGADXContextMobFormat {
    SVGA3dQueryId queryID[SVGA3D_MAX_QUERY];
 
    SVGA3dCOTableData cotables[SVGA_COTABLE_MAX];
-   uint32 pad7[381];
+   uint32 pad7[380];
 }
 #include "vmware_pack_end.h"
 SVGADXContextMobFormat;
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h
index a1c36877ad55..b22a67f15660 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2007-2015 VMware, Inc.  All rights reserved.
+ * Copyright 2007-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
@@ -62,7 +63,9 @@
  * Maximum size in dwords of shader text the SVGA device will allow.
  * Currently 8 MB.
  */
-#define SVGA3D_MAX_SHADER_MEMORY  (8 * 1024 * 1024 / sizeof(uint32))
+#define SVGA3D_MAX_SHADER_MEMORY_BYTES (8 * 1024 * 1024)
+#define SVGA3D_MAX_SHADER_MEMORY  (SVGA3D_MAX_SHADER_MEMORY_BYTES / \
+                                   sizeof(uint32))
 
 #define SVGA3D_MAX_CLIP_PLANES    6
 
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_reg.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_reg.h
index b44ce648f592..bdfc404c91e3 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_reg.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_reg.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 1998-2015 VMware, Inc.  All rights reserved.
+ * Copyright 1998-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h
index babe7cb84fc2..f2bfd3d80598 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h
@@ -1,7 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
- * Copyright © 2008-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2008-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -25,189 +25,355 @@
  *
  **************************************************************************/
 
-#include <linux/kernel.h>
-
-#ifdef __KERNEL__
-
-#include <drm/vmwgfx_drm.h>
-#define surf_size_struct struct drm_vmw_size
-
-#else /* __KERNEL__ */
+/*
+ * svga3d_surfacedefs.h --
+ *
+ *      Surface definitions and inlineable utilities for SVGA3d.
+ */
 
-#ifndef ARRAY_SIZE
-#define ARRAY_SIZE(_A) (sizeof(_A) / sizeof((_A)[0]))
-#endif /* ARRAY_SIZE */
+#ifndef _SVGA3D_SURFACEDEFS_H_
+#define _SVGA3D_SURFACEDEFS_H_
 
-#define max_t(type, x, y)  ((x) > (y) ? (x) : (y))
-#define surf_size_struct SVGA3dSize
-#define u32 uint32
+#define INCLUDE_ALLOW_USERLEVEL
+#define INCLUDE_ALLOW_MODULE
+#include "includeCheck.h"
 
-#endif /* __KERNEL__ */
+#include <linux/kernel.h>
+#include <drm/vmwgfx_drm.h>
 
 #include "svga3d_reg.h"
 
+#define surf_size_struct struct drm_vmw_size
+
 /*
- * enum svga3d_block_desc describes the active data channels in a block.
- *
- * There can be at-most four active channels in a block:
- *    1. Red, bump W, luminance and depth are stored in the first channel.
- *    2. Green, bump V and stencil are stored in the second channel.
- *    3. Blue and bump U are stored in the third channel.
- *    4. Alpha and bump Q are stored in the fourth channel.
- *
- * Block channels can be used to store compressed and buffer data:
- *    1. For compressed formats, only the data channel is used and its size
- *       is equal to that of a singular block in the compression scheme.
- *    2. For buffer formats, only the data channel is used and its size is
- *       exactly one byte in length.
- *    3. In each case the bit depth represent the size of a singular block.
- *
- * Note: Compressed and IEEE formats do not use the bitMask structure.
+ * enum svga3d_block_desc - describes generic properties about formats.
  */
-
 enum svga3d_block_desc {
-	SVGA3DBLOCKDESC_NONE        = 0,         /* No channels are active */
-	SVGA3DBLOCKDESC_BLUE        = 1 << 0,    /* Block with red channel
-						    data */
-	SVGA3DBLOCKDESC_U           = 1 << 0,    /* Block with bump U channel
-						    data */
-	SVGA3DBLOCKDESC_UV_VIDEO    = 1 << 7,    /* Block with alternating video
-						    U and V */
-	SVGA3DBLOCKDESC_GREEN       = 1 << 1,    /* Block with green channel
-						    data */
-	SVGA3DBLOCKDESC_V           = 1 << 1,    /* Block with bump V channel
-						    data */
-	SVGA3DBLOCKDESC_STENCIL     = 1 << 1,    /* Block with a stencil
-						    channel */
-	SVGA3DBLOCKDESC_RED         = 1 << 2,    /* Block with blue channel
-						    data */
-	SVGA3DBLOCKDESC_W           = 1 << 2,    /* Block with bump W channel
-						    data */
-	SVGA3DBLOCKDESC_LUMINANCE   = 1 << 2,    /* Block with luminance channel
-						    data */
-	SVGA3DBLOCKDESC_Y           = 1 << 2,    /* Block with video luminance
-						    data */
-	SVGA3DBLOCKDESC_DEPTH       = 1 << 2,    /* Block with depth channel */
-	SVGA3DBLOCKDESC_ALPHA       = 1 << 3,    /* Block with an alpha
-						    channel */
-	SVGA3DBLOCKDESC_Q           = 1 << 3,    /* Block with bump Q channel
-						    data */
-	SVGA3DBLOCKDESC_BUFFER      = 1 << 4,    /* Block stores 1 byte of
-						    data */
-	SVGA3DBLOCKDESC_COMPRESSED  = 1 << 5,    /* Block stores n bytes of
-						    data depending on the
-						    compression method used */
-	SVGA3DBLOCKDESC_IEEE_FP     = 1 << 6,    /* Block stores data in an IEEE
-						    floating point
-						    representation in
-						    all channels */
-	SVGA3DBLOCKDESC_PLANAR_YUV  = 1 << 8,    /* Three separate blocks store
-						    data. */
-	SVGA3DBLOCKDESC_U_VIDEO     = 1 << 9,    /* Block with U video data */
-	SVGA3DBLOCKDESC_V_VIDEO     = 1 << 10,   /* Block with V video data */
-	SVGA3DBLOCKDESC_EXP         = 1 << 11,   /* Shared exponent */
-	SVGA3DBLOCKDESC_SRGB        = 1 << 12,   /* Data is in sRGB format */
-	SVGA3DBLOCKDESC_2PLANAR_YUV = 1 << 13,   /* 2 planes of Y, UV,
-						    e.g., NV12. */
-	SVGA3DBLOCKDESC_3PLANAR_YUV = 1 << 14,   /* 3 planes of separate
-						    Y, U, V, e.g., YV12. */
-
-	SVGA3DBLOCKDESC_RG         = SVGA3DBLOCKDESC_RED |
-	SVGA3DBLOCKDESC_GREEN,
-	SVGA3DBLOCKDESC_RGB        = SVGA3DBLOCKDESC_RG |
-	SVGA3DBLOCKDESC_BLUE,
-	SVGA3DBLOCKDESC_RGB_SRGB   = SVGA3DBLOCKDESC_RGB |
-	SVGA3DBLOCKDESC_SRGB,
-	SVGA3DBLOCKDESC_RGBA       = SVGA3DBLOCKDESC_RGB |
-	SVGA3DBLOCKDESC_ALPHA,
-	SVGA3DBLOCKDESC_RGBA_SRGB  = SVGA3DBLOCKDESC_RGBA |
-	SVGA3DBLOCKDESC_SRGB,
+	/* Nothing special can be said about this format. */
+	SVGA3DBLOCKDESC_NONE        = 0,
+
+	/* Format contains Blue/U data */
+	SVGA3DBLOCKDESC_BLUE        = 1 << 0,
+	SVGA3DBLOCKDESC_W           = 1 << 0,
+	SVGA3DBLOCKDESC_BUMP_L      = 1 << 0,
+
+	/* Format contains Green/V data */
+	SVGA3DBLOCKDESC_GREEN       = 1 << 1,
+	SVGA3DBLOCKDESC_V           = 1 << 1,
+
+	/* Format contains Red/W/Luminance data */
+	SVGA3DBLOCKDESC_RED         = 1 << 2,
+	SVGA3DBLOCKDESC_U           = 1 << 2,
+	SVGA3DBLOCKDESC_LUMINANCE   = 1 << 2,
+
+	/* Format contains Alpha/Q data */
+	SVGA3DBLOCKDESC_ALPHA       = 1 << 3,
+	SVGA3DBLOCKDESC_Q           = 1 << 3,
+
+	/* Format is a buffer */
+	SVGA3DBLOCKDESC_BUFFER      = 1 << 4,
+
+	/* Format is compressed */
+	SVGA3DBLOCKDESC_COMPRESSED  = 1 << 5,
+
+	/* Format uses IEEE floating point */
+	SVGA3DBLOCKDESC_FP          = 1 << 6,
+
+	/* Three separate blocks store data. */
+	SVGA3DBLOCKDESC_PLANAR_YUV  = 1 << 7,
+
+	/* 2 planes of Y, UV, e.g., NV12. */
+	SVGA3DBLOCKDESC_2PLANAR_YUV = 1 << 8,
+
+	/* 3 planes of separate Y, U, V, e.g., YV12. */
+	SVGA3DBLOCKDESC_3PLANAR_YUV = 1 << 9,
+
+	/* Block with a stencil channel */
+	SVGA3DBLOCKDESC_STENCIL     = 1 << 11,
+
+	/* Typeless format */
+	SVGA3DBLOCKDESC_TYPELESS    = 1 << 12,
+
+	/* Channels are signed integers */
+	SVGA3DBLOCKDESC_SINT        = 1 << 13,
+
+	/* Channels are unsigned integers */
+	SVGA3DBLOCKDESC_UINT        = 1 << 14,
+
+	/* Channels are normalized (when sampling) */
+	SVGA3DBLOCKDESC_NORM        = 1 << 15,
+
+	/* Channels are in SRGB */
+	SVGA3DBLOCKDESC_SRGB        = 1 << 16,
+
+	/* Shared exponent */
+	SVGA3DBLOCKDESC_EXP         = 1 << 17,
+
+	/* Format contains color data. */
+	SVGA3DBLOCKDESC_COLOR       = 1 << 18,
+	/* Format contains depth data. */
+	SVGA3DBLOCKDESC_DEPTH       = 1 << 19,
+	/* Format contains bump data. */
+	SVGA3DBLOCKDESC_BUMP        = 1 << 20,
+
+	/* Format contains YUV video data. */
+	SVGA3DBLOCKDESC_YUV_VIDEO   = 1 << 21,
+
+	/* For mixed unsigned/signed formats. */
+	SVGA3DBLOCKDESC_MIXED       = 1 << 22,
+
+	/* For distingushing CxV8U8. */
+	SVGA3DBLOCKDESC_CX          = 1 << 23,
+
+	/* Different compressed format groups. */
+	SVGA3DBLOCKDESC_BC1         = 1 << 24,
+	SVGA3DBLOCKDESC_BC2         = 1 << 25,
+	SVGA3DBLOCKDESC_BC3         = 1 << 26,
+	SVGA3DBLOCKDESC_BC4         = 1 << 27,
+	SVGA3DBLOCKDESC_BC5         = 1 << 28,
+
+	SVGA3DBLOCKDESC_A_UINT    = SVGA3DBLOCKDESC_ALPHA |
+				    SVGA3DBLOCKDESC_UINT |
+				    SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_A_UNORM   = SVGA3DBLOCKDESC_A_UINT |
+				    SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_R_UINT    = SVGA3DBLOCKDESC_RED |
+				    SVGA3DBLOCKDESC_UINT |
+				    SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_R_UNORM   = SVGA3DBLOCKDESC_R_UINT |
+				    SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_R_SINT    = SVGA3DBLOCKDESC_RED |
+				    SVGA3DBLOCKDESC_SINT |
+				    SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_R_SNORM   = SVGA3DBLOCKDESC_R_SINT |
+				    SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_G_UINT    = SVGA3DBLOCKDESC_GREEN |
+				    SVGA3DBLOCKDESC_UINT |
+				    SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RG_UINT    = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_UINT |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RG_UNORM   = SVGA3DBLOCKDESC_RG_UINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RG_SINT    = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_SINT |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RG_SNORM   = SVGA3DBLOCKDESC_RG_SINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RGB_UINT   = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_BLUE |
+				     SVGA3DBLOCKDESC_UINT |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGB_SINT   = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_BLUE |
+				     SVGA3DBLOCKDESC_SINT |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGB_UNORM   = SVGA3DBLOCKDESC_RGB_UINT |
+				      SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RGB_UNORM_SRGB = SVGA3DBLOCKDESC_RGB_UNORM |
+					 SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_RGBA_UINT  = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_BLUE |
+				     SVGA3DBLOCKDESC_ALPHA |
+				     SVGA3DBLOCKDESC_UINT |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGBA_UNORM = SVGA3DBLOCKDESC_RGBA_UINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RGBA_UNORM_SRGB = SVGA3DBLOCKDESC_RGBA_UNORM |
+					  SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_RGBA_SINT  = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_BLUE |
+				     SVGA3DBLOCKDESC_ALPHA |
+				     SVGA3DBLOCKDESC_SINT |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGBA_SNORM = SVGA3DBLOCKDESC_RGBA_SINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RGBA_FP    = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_BLUE |
+				     SVGA3DBLOCKDESC_ALPHA |
+				     SVGA3DBLOCKDESC_FP |
+				     SVGA3DBLOCKDESC_COLOR,
 	SVGA3DBLOCKDESC_UV         = SVGA3DBLOCKDESC_U |
-	SVGA3DBLOCKDESC_V,
+				     SVGA3DBLOCKDESC_V |
+				     SVGA3DBLOCKDESC_BUMP,
 	SVGA3DBLOCKDESC_UVL        = SVGA3DBLOCKDESC_UV |
-	SVGA3DBLOCKDESC_LUMINANCE,
+				     SVGA3DBLOCKDESC_BUMP_L |
+				     SVGA3DBLOCKDESC_MIXED |
+				     SVGA3DBLOCKDESC_BUMP,
 	SVGA3DBLOCKDESC_UVW        = SVGA3DBLOCKDESC_UV |
-	SVGA3DBLOCKDESC_W,
+				     SVGA3DBLOCKDESC_W |
+				     SVGA3DBLOCKDESC_BUMP,
 	SVGA3DBLOCKDESC_UVWA       = SVGA3DBLOCKDESC_UVW |
-	SVGA3DBLOCKDESC_ALPHA,
+				     SVGA3DBLOCKDESC_ALPHA |
+				     SVGA3DBLOCKDESC_MIXED |
+				     SVGA3DBLOCKDESC_BUMP,
 	SVGA3DBLOCKDESC_UVWQ       = SVGA3DBLOCKDESC_U |
-	SVGA3DBLOCKDESC_V |
-	SVGA3DBLOCKDESC_W |
-	SVGA3DBLOCKDESC_Q,
-	SVGA3DBLOCKDESC_LA         = SVGA3DBLOCKDESC_LUMINANCE |
-	SVGA3DBLOCKDESC_ALPHA,
+				     SVGA3DBLOCKDESC_V |
+				     SVGA3DBLOCKDESC_W |
+				     SVGA3DBLOCKDESC_Q |
+				     SVGA3DBLOCKDESC_BUMP,
+	SVGA3DBLOCKDESC_L_UNORM    = SVGA3DBLOCKDESC_LUMINANCE |
+				     SVGA3DBLOCKDESC_UINT |
+				     SVGA3DBLOCKDESC_NORM |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_LA_UNORM   = SVGA3DBLOCKDESC_LUMINANCE |
+				     SVGA3DBLOCKDESC_ALPHA |
+				     SVGA3DBLOCKDESC_UINT |
+				     SVGA3DBLOCKDESC_NORM |
+				     SVGA3DBLOCKDESC_COLOR,
 	SVGA3DBLOCKDESC_R_FP       = SVGA3DBLOCKDESC_RED |
-	SVGA3DBLOCKDESC_IEEE_FP,
+				     SVGA3DBLOCKDESC_FP |
+				     SVGA3DBLOCKDESC_COLOR,
 	SVGA3DBLOCKDESC_RG_FP      = SVGA3DBLOCKDESC_R_FP |
-	SVGA3DBLOCKDESC_GREEN,
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_COLOR,
 	SVGA3DBLOCKDESC_RGB_FP     = SVGA3DBLOCKDESC_RG_FP |
-	SVGA3DBLOCKDESC_BLUE,
-	SVGA3DBLOCKDESC_RGBA_FP    = SVGA3DBLOCKDESC_RGB_FP |
-	SVGA3DBLOCKDESC_ALPHA,
-	SVGA3DBLOCKDESC_DS         = SVGA3DBLOCKDESC_DEPTH |
-	SVGA3DBLOCKDESC_STENCIL,
-	SVGA3DBLOCKDESC_YUV        = SVGA3DBLOCKDESC_UV_VIDEO |
-	SVGA3DBLOCKDESC_Y,
+				     SVGA3DBLOCKDESC_BLUE |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_YUV        = SVGA3DBLOCKDESC_YUV_VIDEO |
+				     SVGA3DBLOCKDESC_COLOR,
 	SVGA3DBLOCKDESC_AYUV       = SVGA3DBLOCKDESC_ALPHA |
-	SVGA3DBLOCKDESC_Y |
-	SVGA3DBLOCKDESC_U_VIDEO |
-	SVGA3DBLOCKDESC_V_VIDEO,
-	SVGA3DBLOCKDESC_RGBE       = SVGA3DBLOCKDESC_RGB |
-	SVGA3DBLOCKDESC_EXP,
-	SVGA3DBLOCKDESC_COMPRESSED_SRGB = SVGA3DBLOCKDESC_COMPRESSED |
-	SVGA3DBLOCKDESC_SRGB,
-	SVGA3DBLOCKDESC_NV12       = SVGA3DBLOCKDESC_PLANAR_YUV |
-	SVGA3DBLOCKDESC_2PLANAR_YUV,
-	SVGA3DBLOCKDESC_YV12       = SVGA3DBLOCKDESC_PLANAR_YUV |
-	SVGA3DBLOCKDESC_3PLANAR_YUV,
+				     SVGA3DBLOCKDESC_YUV_VIDEO |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGB_EXP       = SVGA3DBLOCKDESC_RED |
+					SVGA3DBLOCKDESC_GREEN |
+					SVGA3DBLOCKDESC_BLUE |
+					SVGA3DBLOCKDESC_EXP |
+					SVGA3DBLOCKDESC_COLOR,
+
+	SVGA3DBLOCKDESC_COMP_TYPELESS = SVGA3DBLOCKDESC_COMPRESSED |
+					SVGA3DBLOCKDESC_TYPELESS,
+	SVGA3DBLOCKDESC_COMP_UNORM = SVGA3DBLOCKDESC_COMPRESSED |
+				     SVGA3DBLOCKDESC_UINT |
+				     SVGA3DBLOCKDESC_NORM |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_COMP_SNORM = SVGA3DBLOCKDESC_COMPRESSED |
+				     SVGA3DBLOCKDESC_SINT |
+				     SVGA3DBLOCKDESC_NORM |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_COMP_UNORM |
+					  SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_BC1_COMP_TYPELESS = SVGA3DBLOCKDESC_BC1 |
+					    SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC1_COMP_UNORM = SVGA3DBLOCKDESC_BC1 |
+					 SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC1_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_BC1_COMP_UNORM |
+					      SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_BC2_COMP_TYPELESS = SVGA3DBLOCKDESC_BC2 |
+					    SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC2_COMP_UNORM = SVGA3DBLOCKDESC_BC2 |
+					 SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC2_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_BC2_COMP_UNORM |
+					      SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_BC3_COMP_TYPELESS = SVGA3DBLOCKDESC_BC3 |
+					    SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC3_COMP_UNORM = SVGA3DBLOCKDESC_BC3 |
+					 SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC3_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_BC3_COMP_UNORM |
+					      SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_BC4_COMP_TYPELESS = SVGA3DBLOCKDESC_BC4 |
+					    SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC4_COMP_UNORM = SVGA3DBLOCKDESC_BC4 |
+					 SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC4_COMP_SNORM = SVGA3DBLOCKDESC_BC4 |
+					 SVGA3DBLOCKDESC_COMP_SNORM,
+	SVGA3DBLOCKDESC_BC5_COMP_TYPELESS = SVGA3DBLOCKDESC_BC5 |
+					    SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC5_COMP_UNORM = SVGA3DBLOCKDESC_BC5 |
+					 SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC5_COMP_SNORM = SVGA3DBLOCKDESC_BC5 |
+					 SVGA3DBLOCKDESC_COMP_SNORM,
+
+	SVGA3DBLOCKDESC_NV12       = SVGA3DBLOCKDESC_YUV_VIDEO |
+				     SVGA3DBLOCKDESC_PLANAR_YUV |
+				     SVGA3DBLOCKDESC_2PLANAR_YUV |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_YV12       = SVGA3DBLOCKDESC_YUV_VIDEO |
+				     SVGA3DBLOCKDESC_PLANAR_YUV |
+				     SVGA3DBLOCKDESC_3PLANAR_YUV |
+				     SVGA3DBLOCKDESC_COLOR,
+
+	SVGA3DBLOCKDESC_DEPTH_UINT = SVGA3DBLOCKDESC_DEPTH |
+				     SVGA3DBLOCKDESC_UINT,
+	SVGA3DBLOCKDESC_DEPTH_UNORM = SVGA3DBLOCKDESC_DEPTH_UINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_DS      =    SVGA3DBLOCKDESC_DEPTH |
+				     SVGA3DBLOCKDESC_STENCIL,
+	SVGA3DBLOCKDESC_DS_UINT =    SVGA3DBLOCKDESC_DEPTH |
+				     SVGA3DBLOCKDESC_STENCIL |
+				     SVGA3DBLOCKDESC_UINT,
+	SVGA3DBLOCKDESC_DS_UNORM =   SVGA3DBLOCKDESC_DS_UINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_DEPTH_FP   = SVGA3DBLOCKDESC_DEPTH |
+				     SVGA3DBLOCKDESC_FP,
+
+	SVGA3DBLOCKDESC_UV_UINT    = SVGA3DBLOCKDESC_UV |
+				     SVGA3DBLOCKDESC_UINT,
+	SVGA3DBLOCKDESC_UV_SNORM   = SVGA3DBLOCKDESC_UV |
+				     SVGA3DBLOCKDESC_SINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_UVCX_SNORM = SVGA3DBLOCKDESC_UV_SNORM |
+				     SVGA3DBLOCKDESC_CX,
+	SVGA3DBLOCKDESC_UVWQ_SNORM = SVGA3DBLOCKDESC_UVWQ |
+				     SVGA3DBLOCKDESC_SINT |
+				     SVGA3DBLOCKDESC_NORM,
 };
 
-/*
- * SVGA3dSurfaceDesc describes the actual pixel data.
- *
- * This structure provides the following information:
- *    1. Block description.
- *    2. Dimensions of a block in the surface.
- *    3. Size of block in bytes.
- *    4. Bit depth of the pixel data.
- *    5. Channel bit depths and masks (if applicable).
- */
 struct svga3d_channel_def {
 	union {
 		u8 blue;
-		u8 u;
+		u8 w_bump;
+		u8 l_bump;
 		u8 uv_video;
 		u8 u_video;
 	};
 	union {
 		u8 green;
-		u8 v;
 		u8 stencil;
+		u8 v_bump;
 		u8 v_video;
 	};
 	union {
 		u8 red;
-		u8 w;
+		u8 u_bump;
 		u8 luminance;
-		u8 y;
+		u8 y_video;
 		u8 depth;
 		u8 data;
 	};
 	union {
 		u8 alpha;
-		u8 q;
+		u8 q_bump;
 		u8 exp;
 	};
 };
 
+/*
+ * struct svga3d_surface_desc - describes the actual pixel data.
+ *
+ * @format: Format
+ * @block_desc: Block description
+ * @block_size: Dimensions in pixels of a block
+ * @bytes_per_block: Size of block in bytes
+ * @pitch_bytes_per_block: Size of a block in bytes for purposes of pitch
+ * @bit_depth: Channel bit depths
+ * @bit_offset: Channel bit masks (in bits offset from the start of the pointer)
+ */
 struct svga3d_surface_desc {
 	SVGA3dSurfaceFormat format;
 	enum svga3d_block_desc block_desc;
+
 	surf_size_struct block_size;
 	u32 bytes_per_block;
 	u32 pitch_bytes_per_block;
 
-	u32 total_bit_depth;
 	struct svga3d_channel_def bit_depth;
 	struct svga3d_channel_def bit_offset;
 };
@@ -215,729 +381,728 @@ struct svga3d_surface_desc {
 static const struct svga3d_surface_desc svga3d_surface_descs[] = {
    {SVGA3D_FORMAT_INVALID, SVGA3DBLOCKDESC_NONE,
       {1, 1, 1},  0, 0,
-      0, {{0}, {0}, {0}, {0}},
+      {{0}, {0}, {0}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_X8R8G8B8, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_X8R8G8B8, SVGA3DBLOCKDESC_RGB_UNORM,
       {1, 1, 1},  4, 4,
-      24, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_A8R8G8B8, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_A8R8G8B8, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_R5G6B5, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_R5G6B5, SVGA3DBLOCKDESC_RGB_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{5}, {6}, {5}, {0}},
+      {{5}, {6}, {5}, {0}},
       {{0}, {5}, {11}, {0}}},
 
-   {SVGA3D_X1R5G5B5, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_X1R5G5B5, SVGA3DBLOCKDESC_RGB_UNORM,
       {1, 1, 1},  2, 2,
-      15, {{5}, {5}, {5}, {0}},
+      {{5}, {5}, {5}, {0}},
       {{0}, {5}, {10}, {0}}},
 
-   {SVGA3D_A1R5G5B5, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_A1R5G5B5, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{5}, {5}, {5}, {1}},
+      {{5}, {5}, {5}, {1}},
       {{0}, {5}, {10}, {15}}},
 
-   {SVGA3D_A4R4G4B4, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_A4R4G4B4, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{4}, {4}, {4}, {4}},
+      {{4}, {4}, {4}, {4}},
       {{0}, {4}, {8}, {12}}},
 
-   {SVGA3D_Z_D32, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_Z_D32, SVGA3DBLOCKDESC_DEPTH_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_Z_D16, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_Z_D16, SVGA3DBLOCKDESC_DEPTH_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_Z_D24S8, SVGA3DBLOCKDESC_DS,
+   {SVGA3D_Z_D24S8, SVGA3DBLOCKDESC_DS_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {8}, {24}, {0}},
-      {{0}, {24}, {0}, {0}}},
+      {{0}, {8}, {24}, {0}},
+      {{0}, {0}, {8}, {0}}},
 
-   {SVGA3D_Z_D15S1, SVGA3DBLOCKDESC_DS,
+   {SVGA3D_Z_D15S1, SVGA3DBLOCKDESC_DS_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {1}, {15}, {0}},
-      {{0}, {15}, {0}, {0}}},
+      {{0}, {1}, {15}, {0}},
+      {{0}, {0}, {1}, {0}}},
 
-   {SVGA3D_LUMINANCE8, SVGA3DBLOCKDESC_LUMINANCE,
+   {SVGA3D_LUMINANCE8, SVGA3DBLOCKDESC_L_UNORM,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_LUMINANCE4_ALPHA4, SVGA3DBLOCKDESC_LA,
-    {1  , 1, 1},  1, 1,
-      8, {{0}, {0}, {4}, {4}},
+   {SVGA3D_LUMINANCE4_ALPHA4, SVGA3DBLOCKDESC_LA_UNORM,
+      {1, 1, 1},  1, 1,
+      {{0}, {0}, {4}, {4}},
       {{0}, {0}, {0}, {4}}},
 
-   {SVGA3D_LUMINANCE16, SVGA3DBLOCKDESC_LUMINANCE,
+   {SVGA3D_LUMINANCE16, SVGA3DBLOCKDESC_L_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_LUMINANCE8_ALPHA8, SVGA3DBLOCKDESC_LA,
+   {SVGA3D_LUMINANCE8_ALPHA8, SVGA3DBLOCKDESC_LA_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {8}, {8}},
+      {{0}, {0}, {8}, {8}},
       {{0}, {0}, {0}, {8}}},
 
-   {SVGA3D_DXT1, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_DXT1, SVGA3DBLOCKDESC_BC1_COMP_UNORM,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_DXT2, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_DXT2, SVGA3DBLOCKDESC_BC2_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_DXT3, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_DXT3, SVGA3DBLOCKDESC_BC2_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_DXT4, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_DXT4, SVGA3DBLOCKDESC_BC3_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_DXT5, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_DXT5, SVGA3DBLOCKDESC_BC3_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BUMPU8V8, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_BUMPU8V8, SVGA3DBLOCKDESC_UV_SNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {8}, {8}},
-      {{0}, {0}, {0}, {8}}},
+      {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {0}, {0}}},
 
    {SVGA3D_BUMPL6V5U5, SVGA3DBLOCKDESC_UVL,
       {1, 1, 1},  2, 2,
-      16, {{5}, {5}, {6}, {0}},
-      {{11}, {6}, {0}, {0}}},
+      {{6}, {5}, {5}, {0}},
+      {{10}, {5}, {0}, {0}}},
 
    {SVGA3D_BUMPX8L8V8U8, SVGA3DBLOCKDESC_UVL,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{16}, {8}, {0}, {0}}},
 
-   {SVGA3D_BUMPL8V8U8, SVGA3DBLOCKDESC_UVL,
+   {SVGA3D_FORMAT_DEAD1, SVGA3DBLOCKDESC_UVL,
       {1, 1, 1},  3, 3,
-      24, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{16}, {8}, {0}, {0}}},
 
    {SVGA3D_ARGB_S10E5, SVGA3DBLOCKDESC_RGBA_FP,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
    {SVGA3D_ARGB_S23E8, SVGA3DBLOCKDESC_RGBA_FP,
       {1, 1, 1},  16, 16,
-      128, {{32}, {32}, {32}, {32}},
+      {{32}, {32}, {32}, {32}},
       {{64}, {32}, {0}, {96}}},
 
-   {SVGA3D_A2R10G10B10, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_A2R10G10B10, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{10}, {10}, {10}, {2}},
+      {{10}, {10}, {10}, {2}},
       {{0}, {10}, {20}, {30}}},
 
-   {SVGA3D_V8U8, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_V8U8, SVGA3DBLOCKDESC_UV_SNORM,
       {1, 1, 1},  2, 2,
-      16, {{8}, {8}, {0}, {0}},
-      {{8}, {0}, {0}, {0}}},
+      {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {0}, {0}}},
 
-   {SVGA3D_Q8W8V8U8, SVGA3DBLOCKDESC_UVWQ,
+   {SVGA3D_Q8W8V8U8, SVGA3DBLOCKDESC_UVWQ_SNORM,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
-      {{24}, {16}, {8}, {0}}},
+      {{8}, {8}, {8}, {8}},
+      {{16}, {8}, {0}, {24}}},
 
-   {SVGA3D_CxV8U8, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_CxV8U8, SVGA3DBLOCKDESC_UVCX_SNORM,
       {1, 1, 1},  2, 2,
-      16, {{8}, {8}, {0}, {0}},
-      {{8}, {0}, {0}, {0}}},
+      {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {0}, {0}}},
 
    {SVGA3D_X8L8V8U8, SVGA3DBLOCKDESC_UVL,
       {1, 1, 1},  4, 4,
-      24, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{16}, {8}, {0}, {0}}},
 
    {SVGA3D_A2W10V10U10, SVGA3DBLOCKDESC_UVWA,
       {1, 1, 1},  4, 4,
-      32, {{10}, {10}, {10}, {2}},
-      {{0}, {10}, {20}, {30}}},
+      {{10}, {10}, {10}, {2}},
+      {{20}, {10}, {0}, {30}}},
 
-   {SVGA3D_ALPHA8, SVGA3DBLOCKDESC_ALPHA,
+   {SVGA3D_ALPHA8, SVGA3DBLOCKDESC_A_UNORM,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {0}, {8}},
+      {{0}, {0}, {0}, {8}},
       {{0}, {0}, {0}, {0}}},
 
    {SVGA3D_R_S10E5, SVGA3DBLOCKDESC_R_FP,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
    {SVGA3D_R_S23E8, SVGA3DBLOCKDESC_R_FP,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
    {SVGA3D_RG_S10E5, SVGA3DBLOCKDESC_RG_FP,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {16}, {0}},
       {{0}, {16}, {0}, {0}}},
 
    {SVGA3D_RG_S23E8, SVGA3DBLOCKDESC_RG_FP,
       {1, 1, 1},  8, 8,
-      64, {{0}, {32}, {32}, {0}},
+      {{0}, {32}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
    {SVGA3D_BUFFER, SVGA3DBLOCKDESC_BUFFER,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_Z_D24X8, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_Z_D24X8, SVGA3DBLOCKDESC_DEPTH_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {24}, {0}},
-      {{0}, {24}, {0}, {0}}},
+      {{0}, {0}, {24}, {0}},
+      {{0}, {0}, {8}, {0}}},
 
-   {SVGA3D_V16U16, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_V16U16, SVGA3DBLOCKDESC_UV_SNORM,
       {1, 1, 1},  4, 4,
-      32, {{16}, {16}, {0}, {0}},
-      {{16}, {0}, {0}, {0}}},
+      {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_G16R16, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_G16R16, SVGA3DBLOCKDESC_RG_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
-      {{0}, {0}, {16}, {0}}},
+      {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_A16B16G16R16, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_A16B16G16R16, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
    {SVGA3D_UYVY, SVGA3DBLOCKDESC_YUV,
-      {1, 1, 1},  2, 2,
-      16, {{8}, {0}, {8}, {0}},
+      {2, 1, 1},  4, 4,
+      {{8}, {0}, {8}, {0}},
       {{0}, {0}, {8}, {0}}},
 
    {SVGA3D_YUY2, SVGA3DBLOCKDESC_YUV,
-      {1, 1, 1},  2, 2,
-      16, {{8}, {0}, {8}, {0}},
+      {2, 1, 1},  4, 4,
+      {{8}, {0}, {8}, {0}},
       {{8}, {0}, {0}, {0}}},
 
    {SVGA3D_NV12, SVGA3DBLOCKDESC_NV12,
       {2, 2, 1},  6, 2,
-      48, {{0}, {0}, {48}, {0}},
+      {{0}, {0}, {48}, {0}},
       {{0}, {0}, {0}, {0}}},
 
    {SVGA3D_AYUV, SVGA3DBLOCKDESC_AYUV,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_R32G32B32A32_TYPELESS, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R32G32B32A32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  16, 16,
-      128, {{32}, {32}, {32}, {32}},
+      {{32}, {32}, {32}, {32}},
       {{64}, {32}, {0}, {96}}},
 
-   {SVGA3D_R32G32B32A32_UINT, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R32G32B32A32_UINT, SVGA3DBLOCKDESC_RGBA_UINT,
       {1, 1, 1},  16, 16,
-      128, {{32}, {32}, {32}, {32}},
+      {{32}, {32}, {32}, {32}},
       {{64}, {32}, {0}, {96}}},
 
-   {SVGA3D_R32G32B32A32_SINT, SVGA3DBLOCKDESC_UVWQ,
+   {SVGA3D_R32G32B32A32_SINT, SVGA3DBLOCKDESC_RGBA_SINT,
       {1, 1, 1},  16, 16,
-      128, {{32}, {32}, {32}, {32}},
+      {{32}, {32}, {32}, {32}},
       {{64}, {32}, {0}, {96}}},
 
-   {SVGA3D_R32G32B32_TYPELESS, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_R32G32B32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  12, 12,
-      96, {{32}, {32}, {32}, {0}},
+      {{32}, {32}, {32}, {0}},
       {{64}, {32}, {0}, {0}}},
 
    {SVGA3D_R32G32B32_FLOAT, SVGA3DBLOCKDESC_RGB_FP,
       {1, 1, 1},  12, 12,
-      96, {{32}, {32}, {32}, {0}},
+      {{32}, {32}, {32}, {0}},
       {{64}, {32}, {0}, {0}}},
 
-   {SVGA3D_R32G32B32_UINT, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_R32G32B32_UINT, SVGA3DBLOCKDESC_RGB_UINT,
       {1, 1, 1},  12, 12,
-      96, {{32}, {32}, {32}, {0}},
+      {{32}, {32}, {32}, {0}},
       {{64}, {32}, {0}, {0}}},
 
-   {SVGA3D_R32G32B32_SINT, SVGA3DBLOCKDESC_UVW,
+   {SVGA3D_R32G32B32_SINT, SVGA3DBLOCKDESC_RGB_SINT,
       {1, 1, 1},  12, 12,
-      96, {{32}, {32}, {32}, {0}},
+      {{32}, {32}, {32}, {0}},
       {{64}, {32}, {0}, {0}}},
 
-   {SVGA3D_R16G16B16A16_TYPELESS, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R16G16B16A16_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
-   {SVGA3D_R16G16B16A16_UINT, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R16G16B16A16_UINT, SVGA3DBLOCKDESC_RGBA_UINT,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
-   {SVGA3D_R16G16B16A16_SNORM, SVGA3DBLOCKDESC_UVWQ,
+   {SVGA3D_R16G16B16A16_SNORM, SVGA3DBLOCKDESC_RGBA_SNORM,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
-   {SVGA3D_R16G16B16A16_SINT, SVGA3DBLOCKDESC_UVWQ,
+   {SVGA3D_R16G16B16A16_SINT, SVGA3DBLOCKDESC_RGBA_SINT,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
-   {SVGA3D_R32G32_TYPELESS, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R32G32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  8, 8,
-      64, {{0}, {32}, {32}, {0}},
+      {{0}, {32}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
-   {SVGA3D_R32G32_UINT, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R32G32_UINT, SVGA3DBLOCKDESC_RG_UINT,
       {1, 1, 1},  8, 8,
-      64, {{0}, {32}, {32}, {0}},
+      {{0}, {32}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
-   {SVGA3D_R32G32_SINT, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_R32G32_SINT, SVGA3DBLOCKDESC_RG_SINT,
       {1, 1, 1},  8, 8,
-      64, {{0}, {32}, {32}, {0}},
+      {{0}, {32}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
-   {SVGA3D_R32G8X24_TYPELESS, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R32G8X24_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  8, 8,
-      64, {{0}, {8}, {32}, {0}},
+      {{0}, {8}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
    {SVGA3D_D32_FLOAT_S8X24_UINT, SVGA3DBLOCKDESC_DS,
       {1, 1, 1},  8, 8,
-      64, {{0}, {8}, {32}, {0}},
+      {{0}, {8}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
-   {SVGA3D_R32_FLOAT_X8X24_TYPELESS, SVGA3DBLOCKDESC_R_FP,
+   {SVGA3D_R32_FLOAT_X8X24, SVGA3DBLOCKDESC_R_FP,
       {1, 1, 1},  8, 8,
-      64, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_X32_TYPELESS_G8X24_UINT, SVGA3DBLOCKDESC_GREEN,
+   {SVGA3D_X32_G8X24_UINT, SVGA3DBLOCKDESC_G_UINT,
       {1, 1, 1},  8, 8,
-      64, {{0}, {8}, {0}, {0}},
+      {{0}, {8}, {0}, {0}},
       {{0}, {32}, {0}, {0}}},
 
-   {SVGA3D_R10G10B10A2_TYPELESS, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R10G10B10A2_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      32, {{10}, {10}, {10}, {2}},
-      {{0}, {10}, {20}, {30}}},
+      {{10}, {10}, {10}, {2}},
+      {{20}, {10}, {0}, {30}}},
 
-   {SVGA3D_R10G10B10A2_UINT, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R10G10B10A2_UINT, SVGA3DBLOCKDESC_RGBA_UINT,
       {1, 1, 1},  4, 4,
-      32, {{10}, {10}, {10}, {2}},
-      {{0}, {10}, {20}, {30}}},
+      {{10}, {10}, {10}, {2}},
+      {{20}, {10}, {0}, {30}}},
 
    {SVGA3D_R11G11B10_FLOAT, SVGA3DBLOCKDESC_RGB_FP,
       {1, 1, 1},  4, 4,
-      32, {{10}, {11}, {11}, {0}},
-      {{0}, {10}, {21}, {0}}},
+      {{10}, {11}, {11}, {0}},
+      {{22}, {11}, {0}, {0}}},
 
-   {SVGA3D_R8G8B8A8_TYPELESS, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R8G8B8A8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{16}, {8}, {0}, {24}}},
 
-   {SVGA3D_R8G8B8A8_UNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R8G8B8A8_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{16}, {8}, {0}, {24}}},
 
-   {SVGA3D_R8G8B8A8_UNORM_SRGB, SVGA3DBLOCKDESC_RGBA_SRGB,
+   {SVGA3D_R8G8B8A8_UNORM_SRGB, SVGA3DBLOCKDESC_RGBA_UNORM_SRGB,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{16}, {8}, {0}, {24}}},
 
-   {SVGA3D_R8G8B8A8_UINT, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R8G8B8A8_UINT, SVGA3DBLOCKDESC_RGBA_UINT,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{16}, {8}, {0}, {24}}},
 
-   {SVGA3D_R8G8B8A8_SINT, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R8G8B8A8_SINT, SVGA3DBLOCKDESC_RGBA_SINT,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{16}, {8}, {0}, {24}}},
 
-   {SVGA3D_R16G16_TYPELESS, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R16G16_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {16}, {0}},
       {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_R16G16_UINT, SVGA3DBLOCKDESC_RG_FP,
+   {SVGA3D_R16G16_UINT, SVGA3DBLOCKDESC_RG_UINT,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {16}, {0}},
       {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_R16G16_SINT, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_R16G16_SINT, SVGA3DBLOCKDESC_RG_SINT,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {16}, {0}},
       {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_R32_TYPELESS, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_D32_FLOAT, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_D32_FLOAT, SVGA3DBLOCKDESC_DEPTH_FP,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R32_UINT, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R32_UINT, SVGA3DBLOCKDESC_R_UINT,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R32_SINT, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R32_SINT, SVGA3DBLOCKDESC_R_SINT,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R24G8_TYPELESS, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R24G8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      32, {{0}, {8}, {24}, {0}},
+      {{0}, {8}, {24}, {0}},
       {{0}, {24}, {0}, {0}}},
 
-   {SVGA3D_D24_UNORM_S8_UINT, SVGA3DBLOCKDESC_DS,
+   {SVGA3D_D24_UNORM_S8_UINT, SVGA3DBLOCKDESC_DS_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {8}, {24}, {0}},
+      {{0}, {8}, {24}, {0}},
       {{0}, {24}, {0}, {0}}},
 
-   {SVGA3D_R24_UNORM_X8_TYPELESS, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R24_UNORM_X8, SVGA3DBLOCKDESC_R_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {24}, {0}},
+      {{0}, {0}, {24}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_X24_TYPELESS_G8_UINT, SVGA3DBLOCKDESC_GREEN,
+   {SVGA3D_X24_G8_UINT, SVGA3DBLOCKDESC_G_UINT,
       {1, 1, 1},  4, 4,
-      32, {{0}, {8}, {0}, {0}},
+      {{0}, {8}, {0}, {0}},
       {{0}, {24}, {0}, {0}}},
 
-   {SVGA3D_R8G8_TYPELESS, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R8G8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  2, 2,
-      16, {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {8}, {0}},
       {{0}, {8}, {0}, {0}}},
 
-   {SVGA3D_R8G8_UNORM, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R8G8_UNORM, SVGA3DBLOCKDESC_RG_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {8}, {0}},
       {{0}, {8}, {0}, {0}}},
 
-   {SVGA3D_R8G8_UINT, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R8G8_UINT, SVGA3DBLOCKDESC_RG_UINT,
       {1, 1, 1},  2, 2,
-      16, {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {8}, {0}},
       {{0}, {8}, {0}, {0}}},
 
-   {SVGA3D_R8G8_SINT, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_R8G8_SINT, SVGA3DBLOCKDESC_RG_SINT,
       {1, 1, 1},  2, 2,
-      16, {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {8}, {0}},
       {{0}, {8}, {0}, {0}}},
 
-   {SVGA3D_R16_TYPELESS, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R16_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R16_UNORM, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R16_UNORM, SVGA3DBLOCKDESC_R_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R16_UINT, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R16_UINT, SVGA3DBLOCKDESC_R_UINT,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R16_SNORM, SVGA3DBLOCKDESC_U,
+   {SVGA3D_R16_SNORM, SVGA3DBLOCKDESC_R_SNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R16_SINT, SVGA3DBLOCKDESC_U,
+   {SVGA3D_R16_SINT, SVGA3DBLOCKDESC_R_SINT,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R8_TYPELESS, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R8_UNORM, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R8_UNORM, SVGA3DBLOCKDESC_R_UNORM,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R8_UINT, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R8_UINT, SVGA3DBLOCKDESC_R_UINT,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R8_SNORM, SVGA3DBLOCKDESC_U,
+   {SVGA3D_R8_SNORM, SVGA3DBLOCKDESC_R_SNORM,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R8_SINT, SVGA3DBLOCKDESC_U,
+   {SVGA3D_R8_SINT, SVGA3DBLOCKDESC_R_SINT,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_P8, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_P8, SVGA3DBLOCKDESC_NONE,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R9G9B9E5_SHAREDEXP, SVGA3DBLOCKDESC_RGBE,
+   {SVGA3D_R9G9B9E5_SHAREDEXP, SVGA3DBLOCKDESC_RGB_EXP,
       {1, 1, 1},  4, 4,
-      32, {{9}, {9}, {9}, {5}},
+      {{9}, {9}, {9}, {5}},
       {{18}, {9}, {0}, {27}}},
 
-   {SVGA3D_R8G8_B8G8_UNORM, SVGA3DBLOCKDESC_RG,
-      {1, 1, 1},  2, 2,
-      16, {{0}, {8}, {8}, {0}},
-      {{0}, {8}, {0}, {0}}},
+   {SVGA3D_R8G8_B8G8_UNORM, SVGA3DBLOCKDESC_NONE,
+      {2, 1, 1},  4, 4,
+      {{0}, {8}, {8}, {0}},
+      {{0}, {0}, {8}, {0}}},
 
-   {SVGA3D_G8R8_G8B8_UNORM, SVGA3DBLOCKDESC_RG,
-      {1, 1, 1},  2, 2,
-      16, {{0}, {8}, {8}, {0}},
+   {SVGA3D_G8R8_G8B8_UNORM, SVGA3DBLOCKDESC_NONE,
+      {2, 1, 1},  4, 4,
+      {{0}, {8}, {8}, {0}},
       {{0}, {8}, {0}, {0}}},
 
-   {SVGA3D_BC1_TYPELESS, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC1_TYPELESS, SVGA3DBLOCKDESC_BC1_COMP_TYPELESS,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC1_UNORM_SRGB, SVGA3DBLOCKDESC_COMPRESSED_SRGB,
+   {SVGA3D_BC1_UNORM_SRGB, SVGA3DBLOCKDESC_BC1_COMP_UNORM_SRGB,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC2_TYPELESS, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC2_TYPELESS, SVGA3DBLOCKDESC_BC2_COMP_TYPELESS,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC2_UNORM_SRGB, SVGA3DBLOCKDESC_COMPRESSED_SRGB,
+   {SVGA3D_BC2_UNORM_SRGB, SVGA3DBLOCKDESC_BC2_COMP_UNORM_SRGB,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC3_TYPELESS, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC3_TYPELESS, SVGA3DBLOCKDESC_BC3_COMP_TYPELESS,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC3_UNORM_SRGB, SVGA3DBLOCKDESC_COMPRESSED_SRGB,
+   {SVGA3D_BC3_UNORM_SRGB, SVGA3DBLOCKDESC_BC3_COMP_UNORM_SRGB,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC4_TYPELESS, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC4_TYPELESS, SVGA3DBLOCKDESC_BC4_COMP_TYPELESS,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_ATI1, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_ATI1, SVGA3DBLOCKDESC_BC4_COMP_UNORM,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC4_SNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC4_SNORM, SVGA3DBLOCKDESC_BC4_COMP_SNORM,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC5_TYPELESS, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC5_TYPELESS, SVGA3DBLOCKDESC_BC5_COMP_TYPELESS,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_ATI2, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_ATI2, SVGA3DBLOCKDESC_BC5_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC5_SNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC5_SNORM, SVGA3DBLOCKDESC_BC5_COMP_SNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R10G10B10_XR_BIAS_A2_UNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R10G10B10_XR_BIAS_A2_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{10}, {10}, {10}, {2}},
-      {{0}, {10}, {20}, {30}}},
+      {{10}, {10}, {10}, {2}},
+     {{20}, {10}, {0}, {30}}},
 
-   {SVGA3D_B8G8R8A8_TYPELESS, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_B8G8R8A8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_B8G8R8A8_UNORM_SRGB, SVGA3DBLOCKDESC_RGBA_SRGB,
+   {SVGA3D_B8G8R8A8_UNORM_SRGB, SVGA3DBLOCKDESC_RGBA_UNORM_SRGB,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_B8G8R8X8_TYPELESS, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_B8G8R8X8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      24, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_B8G8R8X8_UNORM_SRGB, SVGA3DBLOCKDESC_RGB_SRGB,
+   {SVGA3D_B8G8R8X8_UNORM_SRGB, SVGA3DBLOCKDESC_RGB_UNORM_SRGB,
       {1, 1, 1},  4, 4,
-      24, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_Z_DF16, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_Z_DF16, SVGA3DBLOCKDESC_DEPTH_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_Z_DF24, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_Z_DF24, SVGA3DBLOCKDESC_DEPTH_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {8}, {24}, {0}},
-      {{0}, {24}, {0}, {0}}},
+      {{0}, {0}, {24}, {0}},
+      {{0}, {0}, {8}, {0}}},
 
-   {SVGA3D_Z_D24S8_INT, SVGA3DBLOCKDESC_DS,
+   {SVGA3D_Z_D24S8_INT, SVGA3DBLOCKDESC_DS_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {8}, {24}, {0}},
-      {{0}, {24}, {0}, {0}}},
+      {{0}, {8}, {24}, {0}},
+      {{0}, {0}, {8}, {0}}},
 
    {SVGA3D_YV12, SVGA3DBLOCKDESC_YV12,
       {2, 2, 1},  6, 2,
-      48, {{0}, {0}, {48}, {0}},
+      {{0}, {0}, {48}, {0}},
       {{0}, {0}, {0}, {0}}},
 
    {SVGA3D_R32G32B32A32_FLOAT, SVGA3DBLOCKDESC_RGBA_FP,
       {1, 1, 1},  16, 16,
-      128, {{32}, {32}, {32}, {32}},
+      {{32}, {32}, {32}, {32}},
       {{64}, {32}, {0}, {96}}},
 
    {SVGA3D_R16G16B16A16_FLOAT, SVGA3DBLOCKDESC_RGBA_FP,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
-   {SVGA3D_R16G16B16A16_UNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R16G16B16A16_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
    {SVGA3D_R32G32_FLOAT, SVGA3DBLOCKDESC_RG_FP,
       {1, 1, 1},  8, 8,
-      64, {{0}, {32}, {32}, {0}},
+      {{0}, {32}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
-   {SVGA3D_R10G10B10A2_UNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R10G10B10A2_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{10}, {10}, {10}, {2}},
-      {{0}, {10}, {20}, {30}}},
+      {{10}, {10}, {10}, {2}},
+      {{20}, {10}, {0}, {30}}},
 
-   {SVGA3D_R8G8B8A8_SNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R8G8B8A8_SNORM, SVGA3DBLOCKDESC_RGBA_SNORM,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
-      {{24}, {16}, {8}, {0}}},
+      {{8}, {8}, {8}, {8}},
+      {{16}, {8}, {0}, {24}}},
 
    {SVGA3D_R16G16_FLOAT, SVGA3DBLOCKDESC_RG_FP,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {16}, {0}},
       {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_R16G16_UNORM, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R16G16_UNORM, SVGA3DBLOCKDESC_RG_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
-      {{0}, {0}, {16}, {0}}},
+      {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_R16G16_SNORM, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R16G16_SNORM, SVGA3DBLOCKDESC_RG_SNORM,
       {1, 1, 1},  4, 4,
-      32, {{16}, {16}, {0}, {0}},
-      {{16}, {0}, {0}, {0}}},
+      {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {0}, {0}}},
 
    {SVGA3D_R32_FLOAT, SVGA3DBLOCKDESC_R_FP,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R8G8_SNORM, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R8G8_SNORM, SVGA3DBLOCKDESC_RG_SNORM,
       {1, 1, 1},  2, 2,
-      16, {{8}, {8}, {0}, {0}},
-      {{8}, {0}, {0}, {0}}},
+      {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {0}, {0}}},
 
    {SVGA3D_R16_FLOAT, SVGA3DBLOCKDESC_R_FP,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_D16_UNORM, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_D16_UNORM, SVGA3DBLOCKDESC_DEPTH_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_A8_UNORM, SVGA3DBLOCKDESC_ALPHA,
+   {SVGA3D_A8_UNORM, SVGA3DBLOCKDESC_A_UNORM,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {0}, {8}},
+      {{0}, {0}, {0}, {8}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC1_UNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC1_UNORM, SVGA3DBLOCKDESC_BC1_COMP_UNORM,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC2_UNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC2_UNORM, SVGA3DBLOCKDESC_BC2_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC3_UNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC3_UNORM, SVGA3DBLOCKDESC_BC3_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_B5G6R5_UNORM, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_B5G6R5_UNORM, SVGA3DBLOCKDESC_RGB_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{5}, {6}, {5}, {0}},
+      {{5}, {6}, {5}, {0}},
       {{0}, {5}, {11}, {0}}},
 
-   {SVGA3D_B5G5R5A1_UNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_B5G5R5A1_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{5}, {5}, {5}, {1}},
+      {{5}, {5}, {5}, {1}},
       {{0}, {5}, {10}, {15}}},
 
-   {SVGA3D_B8G8R8A8_UNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_B8G8R8A8_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_B8G8R8X8_UNORM, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_B8G8R8X8_UNORM, SVGA3DBLOCKDESC_RGB_UNORM,
       {1, 1, 1},  4, 4,
-      24, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_BC4_UNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC4_UNORM, SVGA3DBLOCKDESC_BC4_COMP_UNORM,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC5_UNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC5_UNORM, SVGA3DBLOCKDESC_BC5_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
-
 };
 
 static inline u32 clamped_umul32(u32 a, u32 b)
@@ -946,6 +1111,10 @@ static inline u32 clamped_umul32(u32 a, u32 b)
 	return (tmp > (uint64_t) ((u32) -1)) ? (u32) -1 : tmp;
 }
 
+/**
+ * svga3dsurface_get_desc - Look up the appropriate SVGA3dSurfaceDesc for the
+ * given format.
+ */
 static inline const struct svga3d_surface_desc *
 svga3dsurface_get_desc(SVGA3dSurfaceFormat format)
 {
@@ -955,23 +1124,10 @@ svga3dsurface_get_desc(SVGA3dSurfaceFormat format)
 	return &svga3d_surface_descs[SVGA3D_FORMAT_INVALID];
 }
 
-/*
- *----------------------------------------------------------------------
- *
- * svga3dsurface_get_mip_size --
- *
- *      Given a base level size and the mip level, compute the size of
- *      the mip level.
- *
- * Results:
- *      See above.
- *
- * Side effects:
- *      None.
- *
- *----------------------------------------------------------------------
+/**
+ * svga3dsurface_get_mip_size -  Given a base level size and the mip level,
+ * compute the size of the mip level.
  */
-
 static inline surf_size_struct
 svga3dsurface_get_mip_size(surf_size_struct base_level, u32 mip_level)
 {
@@ -1018,28 +1174,17 @@ svga3dsurface_calculate_pitch(const struct svga3d_surface_desc *desc,
 	return pitch;
 }
 
-/*
- *-----------------------------------------------------------------------------
- *
- * svga3dsurface_get_image_buffer_size --
- *
- *      Return the number of bytes of buffer space required to store
- *      one image of a surface, optionally using the specified pitch.
- *
- *      If pitch is zero, it is assumed that rows are tightly packed.
+/**
+ * svga3dsurface_get_image_buffer_size - Calculates image buffer size.
  *
- *      This function is overflow-safe. If the result would have
- *      overflowed, instead we return MAX_UINT32.
+ * Return the number of bytes of buffer space required to store one image of a
+ * surface, optionally using the specified pitch.
  *
- * Results:
- *      Byte count.
+ * If pitch is zero, it is assumed that rows are tightly packed.
  *
- * Side effects:
- *      None.
- *
- *-----------------------------------------------------------------------------
+ * This function is overflow-safe. If the result would have overflowed, instead
+ * we return MAX_UINT32.
  */
-
 static inline u32
 svga3dsurface_get_image_buffer_size(const struct svga3d_surface_desc *desc,
 				    const surf_size_struct *size,
@@ -1067,6 +1212,9 @@ svga3dsurface_get_image_buffer_size(const struct svga3d_surface_desc *desc,
 	return total_size;
 }
 
+/**
+ * svga3dsurface_get_serialized_size - Get the serialized size for the image.
+ */
 static inline u32
 svga3dsurface_get_serialized_size(SVGA3dSurfaceFormat format,
 				  surf_size_struct base_level_size,
@@ -1087,6 +1235,26 @@ svga3dsurface_get_serialized_size(SVGA3dSurfaceFormat format,
 	return total_size * num_layers;
 }
 
+/**
+ * svga3dsurface_get_serialized_size_extended - Returns the number of bytes
+ * required for a surface with given parameters. Support for sample count.
+ */
+static inline u32
+svga3dsurface_get_serialized_size_extended(SVGA3dSurfaceFormat format,
+					   surf_size_struct base_level_size,
+					   u32 num_mip_levels,
+					   u32 num_layers,
+					   u32 num_samples)
+{
+	uint64_t total_size =
+		svga3dsurface_get_serialized_size(format,
+						  base_level_size,
+						  num_mip_levels,
+						  num_layers);
+	total_size *= max_t(u32, 1, num_samples);
+
+	return min_t(uint64_t, total_size, (uint64_t)U32_MAX);
+}
 
 /**
  * svga3dsurface_get_pixel_offset - Compute the offset (in bytes) to a pixel
@@ -1206,3 +1374,5 @@ svga3dsurface_is_screen_target_format(SVGA3dSurfaceFormat format)
 	}
 	return svga3dsurface_is_dx_screen_target_format(format);
 }
+
+#endif /* _SVGA3D_SURFACEDEFS_H_ */
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h
index 27b33ba88430..308370665a8e 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2012-2015 VMware, Inc.  All rights reserved.
+ * Copyright 2012-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
@@ -44,9 +45,21 @@
 
 #define SVGA3D_INVALID_ID         ((uint32)-1)
 
+typedef uint8 SVGABool8;   /* 8-bit Bool definition */
 typedef uint32 SVGA3dBool; /* 32-bit Bool definition */
 typedef uint32 SVGA3dColor; /* a, r, g, b */
 
+typedef uint32 SVGA3dSurfaceId;
+
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   uint32 numerator;
+   uint32 denominator;
+}
+#include "vmware_pack_end.h"
+SVGA3dFraction64;
+
 typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dCopyRect {
@@ -145,7 +158,7 @@ typedef enum SVGA3dSurfaceFormat {
    SVGA3D_BUMPU8V8                     = 20,
    SVGA3D_BUMPL6V5U5                   = 21,
    SVGA3D_BUMPX8L8V8U8                 = 22,
-   SVGA3D_BUMPL8V8U8                   = 23,
+   SVGA3D_FORMAT_DEAD1                 = 23,
 
    SVGA3D_ARGB_S10E5                   = 24,   /* 16-bit floating-point ARGB */
    SVGA3D_ARGB_S23E8                   = 25,   /* 32-bit floating-point ARGB */
@@ -204,8 +217,8 @@ typedef enum SVGA3dSurfaceFormat {
    SVGA3D_R32G32_SINT                  = 59,
    SVGA3D_R32G8X24_TYPELESS            = 60,
    SVGA3D_D32_FLOAT_S8X24_UINT         = 61,
-   SVGA3D_R32_FLOAT_X8X24_TYPELESS     = 62,
-   SVGA3D_X32_TYPELESS_G8X24_UINT      = 63,
+   SVGA3D_R32_FLOAT_X8X24              = 62,
+   SVGA3D_X32_G8X24_UINT               = 63,
    SVGA3D_R10G10B10A2_TYPELESS         = 64,
    SVGA3D_R10G10B10A2_UINT             = 65,
    SVGA3D_R11G11B10_FLOAT              = 66,
@@ -223,8 +236,8 @@ typedef enum SVGA3dSurfaceFormat {
    SVGA3D_R32_SINT                     = 78,
    SVGA3D_R24G8_TYPELESS               = 79,
    SVGA3D_D24_UNORM_S8_UINT            = 80,
-   SVGA3D_R24_UNORM_X8_TYPELESS        = 81,
-   SVGA3D_X24_TYPELESS_G8_UINT         = 82,
+   SVGA3D_R24_UNORM_X8                 = 81,
+   SVGA3D_X24_G8_UINT                  = 82,
    SVGA3D_R8G8_TYPELESS                = 83,
    SVGA3D_R8G8_UNORM                   = 84,
    SVGA3D_R8G8_UINT                    = 85,
@@ -296,92 +309,114 @@ typedef enum SVGA3dSurfaceFormat {
    SVGA3D_FORMAT_MAX
 } SVGA3dSurfaceFormat;
 
-typedef enum SVGA3dSurfaceFlags {
-   SVGA3D_SURFACE_CUBEMAP               = (1 << 0),
+/*
+ * SVGA3d Surface Flags --
+ */
+#define SVGA3D_SURFACE_CUBEMAP                (1 << 0)
 
-   /*
-    * HINT flags are not enforced by the device but are useful for
-    * performance.
-    */
-   SVGA3D_SURFACE_HINT_STATIC           = (1 << 1),
-   SVGA3D_SURFACE_HINT_DYNAMIC          = (1 << 2),
-   SVGA3D_SURFACE_HINT_INDEXBUFFER      = (1 << 3),
-   SVGA3D_SURFACE_HINT_VERTEXBUFFER     = (1 << 4),
-   SVGA3D_SURFACE_HINT_TEXTURE          = (1 << 5),
-   SVGA3D_SURFACE_HINT_RENDERTARGET     = (1 << 6),
-   SVGA3D_SURFACE_HINT_DEPTHSTENCIL     = (1 << 7),
-   SVGA3D_SURFACE_HINT_WRITEONLY        = (1 << 8),
-   SVGA3D_SURFACE_MASKABLE_ANTIALIAS    = (1 << 9),
-   SVGA3D_SURFACE_AUTOGENMIPMAPS        = (1 << 10),
-   SVGA3D_SURFACE_DECODE_RENDERTARGET   = (1 << 11),
+/*
+ * HINT flags are not enforced by the device but are useful for
+ * performance.
+ */
+#define SVGA3D_SURFACE_HINT_STATIC            (CONST64U(1) << 1)
+#define SVGA3D_SURFACE_HINT_DYNAMIC           (CONST64U(1) << 2)
+#define SVGA3D_SURFACE_HINT_INDEXBUFFER       (CONST64U(1) << 3)
+#define SVGA3D_SURFACE_HINT_VERTEXBUFFER      (CONST64U(1) << 4)
+#define SVGA3D_SURFACE_HINT_TEXTURE           (CONST64U(1) << 5)
+#define SVGA3D_SURFACE_HINT_RENDERTARGET      (CONST64U(1) << 6)
+#define SVGA3D_SURFACE_HINT_DEPTHSTENCIL      (CONST64U(1) << 7)
+#define SVGA3D_SURFACE_HINT_WRITEONLY         (CONST64U(1) << 8)
+#define SVGA3D_SURFACE_MASKABLE_ANTIALIAS     (CONST64U(1) << 9)
+#define SVGA3D_SURFACE_AUTOGENMIPMAPS         (CONST64U(1) << 10)
+
+#define SVGA3D_SURFACE_DECODE_RENDERTARGET    (CONST64U(1) << 11)
 
-   /*
-    * Is this surface using a base-level pitch for it's mob backing?
-    *
-    * This flag is not intended to be set by guest-drivers, but is instead
-    * set by the device when the surface is bound to a mob with a specified
-    * pitch.
-    */
-   SVGA3D_SURFACE_MOB_PITCH             = (1 << 12),
+/*
+ * Is this surface using a base-level pitch for it's mob backing?
+ *
+ * This flag is not intended to be set by guest-drivers, but is instead
+ * set by the device when the surface is bound to a mob with a specified
+ * pitch.
+ */
+#define SVGA3D_SURFACE_MOB_PITCH              (CONST64U(1) << 12)
 
-   SVGA3D_SURFACE_INACTIVE              = (1 << 13),
-   SVGA3D_SURFACE_HINT_RT_LOCKABLE      = (1 << 14),
-   SVGA3D_SURFACE_VOLUME                = (1 << 15),
+#define SVGA3D_SURFACE_INACTIVE               (CONST64U(1) << 13)
+#define SVGA3D_SURFACE_HINT_RT_LOCKABLE       (CONST64U(1) << 14)
+#define SVGA3D_SURFACE_VOLUME                 (CONST64U(1) << 15)
 
-   /*
-    * Required to be set on a surface to bind it to a screen target.
-    */
-   SVGA3D_SURFACE_SCREENTARGET          = (1 << 16),
+/*
+ * Required to be set on a surface to bind it to a screen target.
+ */
+#define SVGA3D_SURFACE_SCREENTARGET           (CONST64U(1) << 16)
 
-   /*
-    * Align images in the guest-backing mob to 16-bytes.
-    */
-   SVGA3D_SURFACE_ALIGN16               = (1 << 17),
+/*
+ * Align images in the guest-backing mob to 16-bytes.
+ */
+#define SVGA3D_SURFACE_ALIGN16                (CONST64U(1) << 17)
 
-   SVGA3D_SURFACE_1D                    = (1 << 18),
-   SVGA3D_SURFACE_ARRAY                 = (1 << 19),
+#define SVGA3D_SURFACE_1D                     (CONST64U(1) << 18)
+#define SVGA3D_SURFACE_ARRAY                  (CONST64U(1) << 19)
 
-   /*
-    * Bind flags.
-    * These are enforced for any surface defined with DefineGBSurface_v2.
-    */
-   SVGA3D_SURFACE_BIND_VERTEX_BUFFER    = (1 << 20),
-   SVGA3D_SURFACE_BIND_INDEX_BUFFER     = (1 << 21),
-   SVGA3D_SURFACE_BIND_CONSTANT_BUFFER  = (1 << 22),
-   SVGA3D_SURFACE_BIND_SHADER_RESOURCE  = (1 << 23),
-   SVGA3D_SURFACE_BIND_RENDER_TARGET    = (1 << 24),
-   SVGA3D_SURFACE_BIND_DEPTH_STENCIL    = (1 << 25),
-   SVGA3D_SURFACE_BIND_STREAM_OUTPUT    = (1 << 26),
+/*
+ * Bind flags.
+ * These are enforced for any surface defined with DefineGBSurface_v2.
+ */
+#define SVGA3D_SURFACE_BIND_VERTEX_BUFFER     (CONST64U(1) << 20)
+#define SVGA3D_SURFACE_BIND_INDEX_BUFFER      (CONST64U(1) << 21)
+#define SVGA3D_SURFACE_BIND_CONSTANT_BUFFER   (CONST64U(1) << 22)
+#define SVGA3D_SURFACE_BIND_SHADER_RESOURCE   (CONST64U(1) << 23)
+#define SVGA3D_SURFACE_BIND_RENDER_TARGET     (CONST64U(1) << 24)
+#define SVGA3D_SURFACE_BIND_DEPTH_STENCIL     (CONST64U(1) << 25)
+#define SVGA3D_SURFACE_BIND_STREAM_OUTPUT     (CONST64U(1) << 26)
 
-   /*
-    * A note on staging flags:
-    *
-    * The STAGING flags notes that the surface will not be used directly by the
-    * drawing pipeline, i.e. that it will not be bound to any bind point.
-    * Staging surfaces may be used by copy operations to move data in and out
-    * of other surfaces.
-    *
-    * The HINT_INDIRECT_UPDATE flag suggests that the surface will receive
-    * updates indirectly, i.e. the surface will not be updated directly, but
-    * will receive copies from staging surfaces.
-    */
-   SVGA3D_SURFACE_STAGING_UPLOAD        = (1 << 27),
-   SVGA3D_SURFACE_STAGING_DOWNLOAD      = (1 << 28),
-   SVGA3D_SURFACE_HINT_INDIRECT_UPDATE  = (1 << 29),
+/*
+ * The STAGING flags notes that the surface will not be used directly by the
+ * drawing pipeline, i.e. that it will not be bound to any bind point.
+ * Staging surfaces may be used by copy operations to move data in and out
+ * of other surfaces.  No bind flags may be set on surfaces with this flag.
+ *
+ * The HINT_INDIRECT_UPDATE flag suggests that the surface will receive
+ * updates indirectly, i.e. the surface will not be updated directly, but
+ * will receive copies from staging surfaces.
+ */
+#define SVGA3D_SURFACE_STAGING_UPLOAD         (CONST64U(1) << 27)
+#define SVGA3D_SURFACE_STAGING_DOWNLOAD       (CONST64U(1) << 28)
+#define SVGA3D_SURFACE_HINT_INDIRECT_UPDATE   (CONST64U(1) << 29)
 
-   /*
-    * Setting this flag allow this surface to be used with the
-    * SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER command.  It is only valid for
-    * buffer surfaces, an no bind flags are allowed to be set on surfaces
-    * with this flag.
-    */
-   SVGA3D_SURFACE_TRANSFER_FROM_BUFFER  = (1 << 30),
+/*
+ * Setting this flag allow this surface to be used with the
+ * SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER command.  It is only valid for
+ * buffer surfaces, and no bind flags are allowed to be set on surfaces
+ * with this flag.
+ */
+#define SVGA3D_SURFACE_TRANSFER_FROM_BUFFER   (CONST64U(1) << 30)
 
-   /*
-    * Marker for the last defined bit.
-    */
-   SVGA3D_SURFACE_FLAG_MAX              = (1 << 31),
-} SVGA3dSurfaceFlags;
+/*
+ * Reserved for video operations.
+ */
+#define SVGA3D_SURFACE_RESERVED1              (CONST64U(1) << 31)
+
+/*
+ * Specifies that a surface is multisample, and therefore requires the full
+ * mob-backing to store all the samples.
+ */
+#define SVGA3D_SURFACE_MULTISAMPLE            (CONST64U(1) << 32)
+
+#define SVGA3D_SURFACE_FLAG_MAX               (CONST64U(1) << 33)
+
+/*
+ * Surface flags types:
+ *
+ * SVGA3dSurface1Flags:  Lower 32-bits of flags.
+ * SVGA3dSurface2Flags:  Upper 32-bits of flags.
+ * SVGA3dSurfaceAllFlags: Full 64-bits of flags.
+ */
+typedef uint32 SVGA3dSurface1Flags;
+typedef uint32 SVGA3dSurface2Flags;
+typedef uint64 SVGA3dSurfaceAllFlags;
+
+#define SVGA3D_SURFACE_FLAGS1_MASK ((uint64_t)MAX_UINT32)
+#define SVGA3D_SURFACE_FLAGS2_MASK (MAX_UINT64 & ~SVGA3D_SURFACE_FLAGS1_MASK)
 
 #define SVGA3D_SURFACE_HB_DISALLOWED_MASK        \
         (  SVGA3D_SURFACE_MOB_PITCH    |         \
@@ -392,29 +427,41 @@ typedef enum SVGA3dSurfaceFlags {
            SVGA3D_SURFACE_STAGING_UPLOAD |       \
            SVGA3D_SURFACE_STAGING_DOWNLOAD |     \
            SVGA3D_SURFACE_HINT_INDIRECT_UPDATE | \
-           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER   \
+           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | \
+           SVGA3D_SURFACE_MULTISAMPLE            \
+        )
+
+#define SVGA3D_SURFACE_HB_PRESENT_DISALLOWED_MASK   \
+       (   SVGA3D_SURFACE_1D |                      \
+           SVGA3D_SURFACE_MULTISAMPLE               \
         )
 
 #define SVGA3D_SURFACE_2D_DISALLOWED_MASK           \
         (  SVGA3D_SURFACE_CUBEMAP |                 \
            SVGA3D_SURFACE_MASKABLE_ANTIALIAS |      \
            SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
-           SVGA3D_SURFACE_DECODE_RENDERTARGET |     \
            SVGA3D_SURFACE_VOLUME |                  \
            SVGA3D_SURFACE_1D |                      \
-           SVGA3D_SURFACE_ARRAY |                   \
            SVGA3D_SURFACE_BIND_VERTEX_BUFFER |      \
            SVGA3D_SURFACE_BIND_INDEX_BUFFER |       \
            SVGA3D_SURFACE_BIND_CONSTANT_BUFFER |    \
            SVGA3D_SURFACE_BIND_DEPTH_STENCIL |      \
            SVGA3D_SURFACE_BIND_STREAM_OUTPUT |      \
-           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER      \
+           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER |    \
+           SVGA3D_SURFACE_MULTISAMPLE               \
+        )
+
+#define SVGA3D_SURFACE_BASICOPS_DISALLOWED_MASK     \
+        (  SVGA3D_SURFACE_CUBEMAP |                 \
+           SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
+           SVGA3D_SURFACE_VOLUME |                  \
+           SVGA3D_SURFACE_1D |                      \
+           SVGA3D_SURFACE_MULTISAMPLE               \
         )
 
 #define SVGA3D_SURFACE_SCREENTARGET_DISALLOWED_MASK \
         (  SVGA3D_SURFACE_CUBEMAP |                 \
            SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
-           SVGA3D_SURFACE_DECODE_RENDERTARGET |     \
            SVGA3D_SURFACE_VOLUME |                  \
            SVGA3D_SURFACE_1D |                      \
            SVGA3D_SURFACE_BIND_VERTEX_BUFFER |      \
@@ -426,12 +473,36 @@ typedef enum SVGA3dSurfaceFlags {
            SVGA3D_SURFACE_STAGING_UPLOAD |          \
            SVGA3D_SURFACE_STAGING_DOWNLOAD |        \
            SVGA3D_SURFACE_HINT_INDIRECT_UPDATE |    \
-           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER      \
+           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER |    \
+           SVGA3D_SURFACE_MULTISAMPLE               \
+        )
+
+#define SVGA3D_SURFACE_BUFFER_DISALLOWED_MASK       \
+        (  SVGA3D_SURFACE_CUBEMAP |                 \
+           SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
+           SVGA3D_SURFACE_VOLUME |                  \
+           SVGA3D_SURFACE_1D |                      \
+           SVGA3D_SURFACE_MASKABLE_ANTIALIAS |      \
+           SVGA3D_SURFACE_ARRAY |                   \
+           SVGA3D_SURFACE_MULTISAMPLE |             \
+           SVGA3D_SURFACE_MOB_PITCH                 \
+        )
+
+#define SVGA3D_SURFACE_MULTISAMPLE_DISALLOWED_MASK  \
+        (  SVGA3D_SURFACE_CUBEMAP |                 \
+           SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
+           SVGA3D_SURFACE_VOLUME |                  \
+           SVGA3D_SURFACE_1D |                      \
+           SVGA3D_SURFACE_SCREENTARGET |            \
+           SVGA3D_SURFACE_MOB_PITCH                 \
         )
 
 #define SVGA3D_SURFACE_DX_ONLY_MASK             \
         (  SVGA3D_SURFACE_BIND_STREAM_OUTPUT |  \
+           SVGA3D_SURFACE_STAGING_UPLOAD |      \
+           SVGA3D_SURFACE_STAGING_DOWNLOAD |    \
            SVGA3D_SURFACE_TRANSFER_FROM_BUFFER  \
+        )
 
 #define SVGA3D_SURFACE_STAGING_MASK             \
         (  SVGA3D_SURFACE_STAGING_UPLOAD |      \
@@ -487,7 +558,7 @@ typedef enum {
 
 /*
  * Indicates that this format can be converted to any RGB format for which
- * SVGA3DFORMAT_OP_MEMBEROFGROUP_ARGB is specified
+ * SVGA3DFORMAT_OP_MEMBEROFGROUP_ARGB is specified.
  */
    SVGA3DFORMAT_OP_CONVERT_TO_ARGB                       = 0x00002000,
 
@@ -498,22 +569,22 @@ typedef enum {
 
 /*
  * Indicated that this format can be read as an SRGB texture (meaning that the
- * sampler will linearize the looked up data)
+ * sampler will linearize the looked up data).
  */
    SVGA3DFORMAT_OP_SRGBREAD                              = 0x00008000,
 
 /*
- * Indicates that this format can be used in the bumpmap instructions
+ * Indicates that this format can be used in the bumpmap instructions.
  */
    SVGA3DFORMAT_OP_BUMPMAP                               = 0x00010000,
 
 /*
- * Indicates that this format can be sampled by the displacement map sampler
+ * Indicates that this format can be sampled by the displacement map sampler.
  */
    SVGA3DFORMAT_OP_DMAP                                  = 0x00020000,
 
 /*
- * Indicates that this format cannot be used with texture filtering
+ * Indicates that this format cannot be used with texture filtering.
  */
    SVGA3DFORMAT_OP_NOFILTER                              = 0x00040000,
 
@@ -530,18 +601,18 @@ typedef enum {
    SVGA3DFORMAT_OP_SRGBWRITE                             = 0x00100000,
 
 /*
- * Indicates that this format cannot be used with alpha blending
+ * Indicates that this format cannot be used with alpha blending.
  */
    SVGA3DFORMAT_OP_NOALPHABLEND                          = 0x00200000,
 
 /*
  * Indicates that the device can auto-generated sublevels for resources
- * of this format
+ * of this format.
  */
    SVGA3DFORMAT_OP_AUTOGENMIPMAP                         = 0x00400000,
 
 /*
- * Indicates that this format can be used by vertex texture sampler
+ * Indicates that this format can be used by vertex texture sampler.
  */
    SVGA3DFORMAT_OP_VERTEXTEXTURE                         = 0x00800000,
 
@@ -1501,7 +1572,6 @@ union SVGADXQueryResultUnion {
 #include "vmware_pack_end.h"
 SVGADXQueryResultUnion;
 
-
 typedef enum {
    SVGA3D_QUERYSTATE_PENDING     = 0,      /* Query is not finished yet */
    SVGA3D_QUERYSTATE_SUCCEEDED   = 1,      /* Completed successfully */
@@ -1533,9 +1603,9 @@ typedef
 struct {
    union {
       struct {
-	 uint16  function;       /* SVGA3dFogFunction */
-	 uint8   type;           /* SVGA3dFogType */
-	 uint8   base;           /* SVGA3dFogBase */
+         uint16  function;       /* SVGA3dFogFunction */
+         uint8   type;           /* SVGA3dFogType */
+         uint8   base;           /* SVGA3dFogBase */
       };
       uint32     uintValue;
    };
@@ -1547,19 +1617,27 @@ SVGA3dFogMode;
  * Uniquely identify one image (a 1D/2D/3D array) from a surface. This
  * is a surface ID as well as face/mipmap indices.
  */
-
 typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dSurfaceImageId {
-   uint32               sid;
-   uint32               face;
-   uint32               mipmap;
+   uint32 sid;
+   uint32 face;
+   uint32 mipmap;
 }
 #include "vmware_pack_end.h"
 SVGA3dSurfaceImageId;
 
 typedef
 #include "vmware_pack_begin.h"
+struct SVGA3dSubSurfaceId {
+   uint32 sid;
+   uint32 subResourceId;
+}
+#include "vmware_pack_end.h"
+SVGA3dSubSurfaceId;
+
+typedef
+#include "vmware_pack_begin.h"
 struct {
    uint32               width;
    uint32               height;
@@ -1582,13 +1660,18 @@ typedef enum {
    SVGA_OTABLE_DX9_MAX         = 5,
 
    SVGA_OTABLE_DXCONTEXT       = 5,
-   SVGA_OTABLE_MAX             = 6
-} SVGAOTableType;
+   SVGA_OTABLE_DX_MAX          = 6,
 
-/*
- * Deprecated.
- */
-#define SVGA_OTABLE_COUNT 4
+   SVGA_OTABLE_RESERVED1       = 6,
+   SVGA_OTABLE_RESERVED2       = 7,
+
+   /*
+    * Additions to this table need to be tied to HW-version features and
+    * checkpointed accordingly.
+    */
+   SVGA_OTABLE_DEVEL_MAX       = 8,
+   SVGA_OTABLE_MAX             = 8
+} SVGAOTableType;
 
 typedef enum {
    SVGA_COTABLE_MIN             = 0,
@@ -1605,7 +1688,7 @@ typedef enum {
    SVGA_COTABLE_DXSHADER        = 10,
    SVGA_COTABLE_DX10_MAX        = 11,
    SVGA_COTABLE_UAVIEW          = 11,
-   SVGA_COTABLE_MAX
+   SVGA_COTABLE_MAX             = 12,
 } SVGACOTableType;
 
 /*
@@ -1626,8 +1709,37 @@ typedef enum SVGAMobFormat {
    SVGA3D_MOBFMT_PREDX_MAX   = 7,
    SVGA3D_MOBFMT_EMPTY       = 7,
    SVGA3D_MOBFMT_MAX,
+
+   /*
+    * This isn't actually used by the guest, but is a mob-format used
+    * internally by the SVGA device (and is therefore not binary compatible).
+    */
+   SVGA3D_MOBFMT_HB,
 } SVGAMobFormat;
 
 #define SVGA3D_MOB_EMPTY_BASE 1
 
+/*
+ * Multisample pattern types.
+ */
+
+typedef enum SVGA3dMSPattern {
+   SVGA3D_MS_PATTERN_NONE     = 0,
+   SVGA3D_MS_PATTERN_MIN      = 0,
+   SVGA3D_MS_PATTERN_STANDARD = 1,
+   SVGA3D_MS_PATTERN_CENTER   = 2,
+   SVGA3D_MS_PATTERN_MAX      = 3,
+} SVGA3dMSPattern;
+
+/*
+ * Precision settings for each sample.
+ */
+
+typedef enum SVGA3dMSQualityLevel {
+   SVGA3D_MS_QUALITY_NONE = 0,
+   SVGA3D_MS_QUALITY_MIN  = 0,
+   SVGA3D_MS_QUALITY_FULL = 1,
+   SVGA3D_MS_QUALITY_MAX  = 2,
+} SVGA3dMSQualityLevel;
+
 #endif /* _SVGA3D_TYPES_H_ */
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_escape.h b/drivers/gpu/drm/vmwgfx/device_include/svga_escape.h
index 884b1d1fb85f..acb41e28e46f 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga_escape.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga_escape.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2007-2015 VMware, Inc.  All rights reserved.
+ * Copyright 2007-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_overlay.h b/drivers/gpu/drm/vmwgfx/device_include/svga_overlay.h
index faf6d9b2b891..e5385146e7fc 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga_overlay.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga_overlay.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2007-2015 VMware, Inc.  All rights reserved.
+ * Copyright 2007-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h b/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h
index 88e72bf9a534..056f54b35d73 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 1998-2015 VMware, Inc.  All rights reserved.
+ * Copyright 1998-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
@@ -63,16 +64,26 @@ typedef uint32 SVGAMobId;
 #define SVGA_MAX_BITS_PER_PIXEL         32
 #define SVGA_MAX_DEPTH                  24
 #define SVGA_MAX_DISPLAYS               10
+#define SVGA_MAX_SCREEN_SIZE            8192
+#define SVGA_SCREEN_ROOT_LIMIT (SVGA_MAX_SCREEN_SIZE * SVGA_MAX_DISPLAYS)
+
 
 /*
  * Legal values for the SVGA_REG_CURSOR_ON register in old-fashioned
  * cursor bypass mode. This is still supported, but no new guest
  * drivers should use it.
  */
-#define SVGA_CURSOR_ON_HIDE            0x0   /* Must be 0 to maintain backward compatibility */
-#define SVGA_CURSOR_ON_SHOW            0x1   /* Must be 1 to maintain backward compatibility */
-#define SVGA_CURSOR_ON_REMOVE_FROM_FB  0x2   /* Remove the cursor from the framebuffer because we need to see what's under it */
-#define SVGA_CURSOR_ON_RESTORE_TO_FB   0x3   /* Put the cursor back in the framebuffer so the user can see it */
+#define SVGA_CURSOR_ON_HIDE            0x0
+#define SVGA_CURSOR_ON_SHOW            0x1
+
+/*
+ * Remove the cursor from the framebuffer
+ * because we need to see what's under it
+ */
+#define SVGA_CURSOR_ON_REMOVE_FROM_FB  0x2
+
+/* Put the cursor back in the framebuffer so the user can see it */
+#define SVGA_CURSOR_ON_RESTORE_TO_FB   0x3
 
 /*
  * The maximum framebuffer size that can traced for guests unless the
@@ -101,7 +112,10 @@ typedef uint32 SVGAMobId;
 #define SVGA_VERSION_0     0
 #define SVGA_ID_0          SVGA_MAKE_ID(SVGA_VERSION_0)
 
-/* "Invalid" value for all SVGA IDs. (Version ID, screen object ID, surface ID...) */
+/*
+ * "Invalid" value for all SVGA IDs.
+ * (Version ID, screen object ID, surface ID...)
+ */
 #define SVGA_ID_INVALID    0xFFFFFFFF
 
 /* Port offsets, relative to BAR0 */
@@ -154,7 +168,7 @@ enum {
    SVGA_REG_CONFIG_DONE = 20,         /* Set when memory area configured */
    SVGA_REG_SYNC = 21,                /* See "FIFO Synchronization Registers" */
    SVGA_REG_BUSY = 22,                /* See "FIFO Synchronization Registers" */
-   SVGA_REG_GUEST_ID = 23,            /* Set guest OS identifier */
+   SVGA_REG_GUEST_ID = 23,            /* (Deprecated) */
    SVGA_REG_CURSOR_ID = 24,           /* (Deprecated) */
    SVGA_REG_CURSOR_X = 25,            /* (Deprecated) */
    SVGA_REG_CURSOR_Y = 26,            /* (Deprecated) */
@@ -186,7 +200,14 @@ enum {
    SVGA_REG_MEMORY_SIZE = 47,       /* Total dedicated device memory excluding FIFO */
    SVGA_REG_COMMAND_LOW = 48,       /* Lower 32 bits and submits commands */
    SVGA_REG_COMMAND_HIGH = 49,      /* Upper 32 bits of command buffer PA */
-   SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM = 50,   /* Max primary memory */
+
+   /*
+    * Max primary memory.
+    * See SVGA_CAP_NO_BB_RESTRICTION.
+    */
+   SVGA_REG_MAX_PRIMARY_MEM = 50,
+   SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM = 50,
+
    SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB = 51, /* Sugested limit on mob mem */
    SVGA_REG_DEV_CAP = 52,           /* Write dev cap index, read value */
    SVGA_REG_CMD_PREPEND_LOW = 53,
@@ -194,7 +215,10 @@ enum {
    SVGA_REG_SCREENTARGET_MAX_WIDTH = 55,
    SVGA_REG_SCREENTARGET_MAX_HEIGHT = 56,
    SVGA_REG_MOB_MAX_SIZE = 57,
-   SVGA_REG_TOP = 58,               /* Must be 1 more than the last register */
+   SVGA_REG_BLANK_SCREEN_TARGETS = 58,
+   SVGA_REG_CAP2 = 59,
+   SVGA_REG_DEVEL_CAP = 60,
+   SVGA_REG_TOP = 61,               /* Must be 1 more than the last register */
 
    SVGA_PALETTE_BASE = 1024,        /* Base of SVGA color map */
    /* Next 768 (== 256*3) registers exist for colormap */
@@ -392,6 +416,7 @@ typedef enum {
    SVGA_CB_CONTEXT_0      = 0x0,
    SVGA_CB_CONTEXT_1      = 0x1, /* Supported with SVGA_CAP_HP_CMD_QUEUE */
    SVGA_CB_CONTEXT_MAX    = 0x2,
+   SVGA_CB_CONTEXT_HP_MAX = 0x2,
 } SVGACBContext;
 
 
@@ -448,6 +473,18 @@ typedef enum {
     * due to an error.  No IRQ is raised.
     */
    SVGA_CB_STATUS_SUBMISSION_ERROR = 6,
+
+   /*
+    * Written by the host when the host finished a
+    * SVGA_DC_CMD_ASYNC_STOP_QUEUE request for this command buffer
+    * queue.  The offset of the first byte not processed is stored in
+    * the errorOffset field of the command buffer header.  All guest
+    * visible side effects of commands till that point are guaranteed
+    * to be finished before this is written.  The
+    * SVGA_IRQFLAG_COMMAND_BUFFER IRQ is raised as long as the
+    * SVGA_CB_FLAG_NO_IRQ is not set.
+    */
+   SVGA_CB_STATUS_PARTIAL_COMPLETE = 7,
 } SVGACBStatus;
 
 typedef enum {
@@ -460,8 +497,8 @@ typedef enum {
 typedef
 #include "vmware_pack_begin.h"
 struct {
-   volatile SVGACBStatus status;
-   volatile uint32 errorOffset;
+   volatile SVGACBStatus status; /* Modified by device. */
+   volatile uint32 errorOffset;  /* Modified by device. */
    uint64 id;
    SVGACBFlags flags;
    uint32 length;
@@ -472,7 +509,9 @@ struct {
          uint32 mobOffset;
       } mob;
    } ptr;
-   uint32 offset; /* Valid if CMD_BUFFERS_2 cap set, must be zero otherwise */
+   uint32 offset; /* Valid if CMD_BUFFERS_2 cap set, must be zero otherwise,
+                   * modified by device.
+                   */
    uint32 dxContext; /* Valid if DX_CONTEXT flag set, must be zero otherwise */
    uint32 mustBeZero[6];
 }
@@ -483,20 +522,26 @@ typedef enum {
    SVGA_DC_CMD_NOP                   = 0,
    SVGA_DC_CMD_START_STOP_CONTEXT    = 1,
    SVGA_DC_CMD_PREEMPT               = 2,
-   SVGA_DC_CMD_MAX                   = 3,
-   SVGA_DC_CMD_FORCE_UINT            = MAX_UINT32,
+   SVGA_DC_CMD_START_QUEUE           = 3, /* Requires SVGA_CAP_HP_CMD_QUEUE */
+   SVGA_DC_CMD_ASYNC_STOP_QUEUE      = 4, /* Requires SVGA_CAP_HP_CMD_QUEUE */
+   SVGA_DC_CMD_EMPTY_CONTEXT_QUEUE   = 5, /* Requires SVGA_CAP_HP_CMD_QUEUE */
+   SVGA_DC_CMD_MAX                   = 6,
 } SVGADeviceContextCmdId;
 
-typedef struct {
+/*
+ * Starts or stops both SVGA_CB_CONTEXT_0 and SVGA_CB_CONTEXT_1.
+ */
+
+typedef struct SVGADCCmdStartStop {
    uint32 enable;
-   SVGACBContext context;
+   SVGACBContext context; /* Must be zero */
 } SVGADCCmdStartStop;
 
 /*
  * SVGADCCmdPreempt --
  *
  * This command allows the guest to request that all command buffers
- * on the specified context be preempted that can be.  After execution
+ * on SVGA_CB_CONTEXT_0 be preempted that can be.  After execution
  * of this command all command buffers that were preempted will
  * already have SVGA_CB_STATUS_PREEMPTED written into the status
  * field.  The device might still be processing a command buffer,
@@ -506,12 +551,69 @@ typedef struct {
  * command buffer header set to zero.
  */
 
-typedef struct {
-   SVGACBContext context;
+typedef struct SVGADCCmdPreempt {
+   SVGACBContext context; /* Must be zero */
    uint32 ignoreIDZero;
 } SVGADCCmdPreempt;
 
 /*
+ * Starts the requested command buffer processing queue.  Valid only
+ * if the SVGA_CAP_HP_CMD_QUEUE cap is set.
+ *
+ * For a command queue to be considered runnable it must be enabled
+ * and any corresponding higher priority queues must also be enabled.
+ * For example in order for command buffers to be processed on
+ * SVGA_CB_CONTEXT_0 both SVGA_CB_CONTEXT_0 and SVGA_CB_CONTEXT_1 must
+ * be enabled.  But for commands to be runnable on SVGA_CB_CONTEXT_1
+ * only that queue must be enabled.
+ */
+
+typedef struct SVGADCCmdStartQueue {
+   SVGACBContext context;
+} SVGADCCmdStartQueue;
+
+/*
+ * Requests the SVGA device to stop processing the requested command
+ * buffer queue as soon as possible.  The guest knows the stop has
+ * completed when one of the following happens.
+ *
+ * 1) A command buffer status of SVGA_CB_STATUS_PARTIAL_COMPLETE is returned
+ * 2) A command buffer error is encountered with would stop the queue
+ *    regardless of the async stop request.
+ * 3) All command buffers that have been submitted complete successfully.
+ * 4) The stop completes synchronously if no command buffers are
+ *    active on the queue when it is issued.
+ *
+ * If the command queue is not in a runnable state there is no
+ * guarentee this async stop will finish.  For instance if the high
+ * priority queue is not enabled and a stop is requested on the low
+ * priority queue, the high priority queue must be reenabled to
+ * guarantee that the async stop will finish.
+ *
+ * This command along with SVGA_DC_CMD_EMPTY_CONTEXT_QUEUE can be used
+ * to implement mid command buffer preemption.
+ *
+ * Valid only if the SVGA_CAP_HP_CMD_QUEUE cap is set.
+ */
+
+typedef struct SVGADCCmdAsyncStopQueue {
+   SVGACBContext context;
+} SVGADCCmdAsyncStopQueue;
+
+/*
+ * Requests the SVGA device to throw away any full command buffers on
+ * the requested command queue that have not been started.  For a
+ * driver to know which command buffers were thrown away a driver
+ * should only issue this command when the queue is stopped, for
+ * whatever reason.
+ */
+
+typedef struct SVGADCCmdEmptyQueue {
+   SVGACBContext context;
+} SVGADCCmdEmptyQueue;
+
+
+/*
  * SVGAGMRImageFormat --
  *
  *    This is a packed representation of the source 2D image format
@@ -536,7 +638,7 @@ typedef struct SVGAGMRImageFormat {
       struct {
          uint32 bitsPerPixel : 8;
          uint32 colorDepth   : 8;
-	 uint32 reserved     : 16;  /* Must be zero */
+         uint32 reserved     : 16;  /* Must be zero */
       };
 
       uint32 value;
@@ -672,8 +774,36 @@ SVGASignedPoint;
  * SVGA_CAP_GBOBJECTS --
  *    Enable guest-backed objects and surfaces.
  *
- * SVGA_CAP_CMD_BUFFERS_3 --
- *    Enable support for command buffers in a mob.
+ * SVGA_CAP_DX --
+ *    Enable support for DX commands, and command buffers in a mob.
+ *
+ * SVGA_CAP_HP_CMD_QUEUE --
+ *    Enable support for the high priority command queue, and the
+ *    ScreenCopy command.
+ *
+ * SVGA_CAP_NO_BB_RESTRICTION --
+ *    Allow ScreenTargets to be defined without regard to the 32-bpp
+ *    bounding-box memory restrictions. ie:
+ *
+ *    The summed memory usage of all screens (assuming they were defined as
+ *    32-bpp) must always be less than the value of the
+ *    SVGA_REG_MAX_PRIMARY_MEM register.
+ *
+ *    If this cap is not present, the 32-bpp bounding box around all screens
+ *    must additionally be under the value of the SVGA_REG_MAX_PRIMARY_MEM
+ *    register.
+ *
+ *    If the cap is present, the bounding box restriction is lifted (and only
+ *    the screen-sum limit applies).
+ *
+ *    (Note that this is a slight lie... there is still a sanity limit on any
+ *     dimension of the topology to be less than SVGA_SCREEN_ROOT_LIMIT, even
+ *     when SVGA_CAP_NO_BB_RESTRICTION is present, but that should be
+ *     large enough to express any possible topology without holes between
+ *     monitors.)
+ *
+ * SVGA_CAP_CAP2_REGISTER --
+ *    If this cap is present, the SVGA_REG_CAP2 register is supported.
  */
 
 #define SVGA_CAP_NONE               0x00000000
@@ -699,8 +829,30 @@ SVGASignedPoint;
 #define SVGA_CAP_GBOBJECTS          0x08000000
 #define SVGA_CAP_DX                 0x10000000
 #define SVGA_CAP_HP_CMD_QUEUE       0x20000000
+#define SVGA_CAP_NO_BB_RESTRICTION  0x40000000
+#define SVGA_CAP_CAP2_REGISTER      0x80000000
 
-#define SVGA_CAP_CMD_RESERVED       0x80000000
+/*
+ * The SVGA_REG_CAP2 register is an additional set of SVGA capability bits.
+ *
+ * SVGA_CAP2_GROW_OTABLE --
+ *      Allow the GrowOTable/DXGrowCOTable commands.
+ *
+ * SVGA_CAP2_INTRA_SURFACE_COPY --
+ *      Allow the IntraSurfaceCopy command.
+ *
+ * SVGA_CAP2_DX2 --
+ *      Allow the DefineGBSurface_v3, WholeSurfaceCopy.
+ *
+ * SVGA_CAP2_RESERVED --
+ *      Reserve the last bit for extending the SVGA capabilities to some
+ *      future mechanisms.
+ */
+#define SVGA_CAP2_NONE               0x00000000
+#define SVGA_CAP2_GROW_OTABLE        0x00000001
+#define SVGA_CAP2_INTRA_SURFACE_COPY 0x00000002
+#define SVGA_CAP2_DX2                0x00000004
+#define SVGA_CAP2_RESERVED           0x80000000
 
 
 /*
@@ -722,7 +874,8 @@ typedef enum {
    SVGABackdoorCapDeviceCaps = 0,
    SVGABackdoorCapFifoCaps = 1,
    SVGABackdoorCap3dHWVersion = 2,
-   SVGABackdoorCapMax = 3,
+   SVGABackdoorCapDeviceCaps2 = 3,
+   SVGABackdoorCapMax = 4,
 } SVGABackdoorCapType;
 
 
@@ -1914,16 +2067,6 @@ SVGAFifoCmdRemapGMR2;
 
 #define SVGA_VRAM_SIZE_W2K          (64 * 1024 * 1024) /* 64 MB */
 
-/*
- * To simplify autoDetect display configuration, support a minimum of
- * two 1920x1200 monitors, 32bpp, side-by-side, optionally rotated:
- *   numDisplays = 2
- *   maxWidth = numDisplay * 1920 = 3840
- *   maxHeight = rotated width of single monitor = 1920
- *   vramSize = maxWidth * maxHeight * 4 = 29491200
- */
-#define SVGA_VRAM_SIZE_AUTODETECT   (32 * 1024 * 1024)
-
 #if defined(VMX86_SERVER)
 #define SVGA_VRAM_SIZE               (4 * 1024 * 1024)
 #define SVGA_VRAM_SIZE_3D           (64 * 1024 * 1024)
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_types.h b/drivers/gpu/drm/vmwgfx/device_include/svga_types.h
index 2e8ba4df8de9..350bbc6fab02 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga_types.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga_types.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2015 VMware, Inc.  All rights reserved.
+ * Copyright 2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
@@ -40,7 +41,10 @@ typedef uint64 PPN64;
 
 typedef bool Bool;
 
+#define MAX_UINT64 U64_MAX
 #define MAX_UINT32 U32_MAX
 #define MAX_UINT16 U16_MAX
 
+#define CONST64U(x) x##ULL
+
 #endif
diff --git a/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_begin.h b/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_begin.h
index 7e7b0ce34aa2..75308bd0d970 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_begin.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_begin.h
@@ -1,25 +1,2 @@
-/**********************************************************
- * Copyright 2015 VMware, Inc.  All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person
- * obtaining a copy of this software and associated documentation
- * files (the "Software"), to deal in the Software without
- * restriction, including without limitation the rights to use, copy,
- * modify, merge, publish, distribute, sublicense, and/or sell copies
- * of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be
- * included in all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- **********************************************************/
+/* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/compiler.h>
diff --git a/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_end.h b/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_end.h
index e2e440ed3d44..e93d6f28b68c 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_end.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_end.h
@@ -1,25 +1,2 @@
-/**********************************************************
- * Copyright 2015 VMware, Inc.  All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person
- * obtaining a copy of this software and associated documentation
- * files (the "Software"), to deal in the Software without
- * restriction, including without limitation the rights to use, copy,
- * modify, merge, publish, distribute, sublicense, and/or sell copies
- * of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be
- * included in all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- **********************************************************/
+/* SPDX-License-Identifier: GPL-2.0 */
 __packed
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c b/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c
index 55d32ae43aa4..0b9ee7fb45d6 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_binding.h b/drivers/gpu/drm/vmwgfx/vmwgfx_binding.h
index bf2e77ad5a20..6a2a9d69043b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_binding.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_binding.h
@@ -1,7 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
- * Copyright © 2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
index e8c94b19db7b..fc6673cde289 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
@@ -1,6 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2017 VMware, Inc., Palo Alto, CA., USA
+ * Copyright 2017 VMware, Inc., Palo Alto, CA., USA
  * All Rights Reserved.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
new file mode 100644
index 000000000000..2dda03345761
--- /dev/null
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
@@ -0,0 +1,1123 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/**************************************************************************
+ *
+ * Copyright © 2011-2018 VMware, Inc., Palo Alto, CA., USA
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ **************************************************************************/
+
+#include <drm/ttm/ttm_placement.h>
+
+#include <drm/drmP.h>
+#include "vmwgfx_drv.h"
+#include "drm/ttm/ttm_object.h"
+
+
+/**
+ * struct vmw_user_buffer_object - User-space-visible buffer object
+ *
+ * @prime: The prime object providing user visibility.
+ * @vbo: The struct vmw_buffer_object
+ */
+struct vmw_user_buffer_object {
+	struct ttm_prime_object prime;
+	struct vmw_buffer_object vbo;
+};
+
+
+/**
+ * vmw_buffer_object - Convert a struct ttm_buffer_object to a struct
+ * vmw_buffer_object.
+ *
+ * @bo: Pointer to the TTM buffer object.
+ * Return: Pointer to the struct vmw_buffer_object embedding the
+ * TTM buffer object.
+ */
+static struct vmw_buffer_object *
+vmw_buffer_object(struct ttm_buffer_object *bo)
+{
+	return container_of(bo, struct vmw_buffer_object, base);
+}
+
+
+/**
+ * vmw_user_buffer_object - Convert a struct ttm_buffer_object to a struct
+ * vmw_user_buffer_object.
+ *
+ * @bo: Pointer to the TTM buffer object.
+ * Return: Pointer to the struct vmw_buffer_object embedding the TTM buffer
+ * object.
+ */
+static struct vmw_user_buffer_object *
+vmw_user_buffer_object(struct ttm_buffer_object *bo)
+{
+	struct vmw_buffer_object *vmw_bo = vmw_buffer_object(bo);
+
+	return container_of(vmw_bo, struct vmw_user_buffer_object, vbo);
+}
+
+
+/**
+ * vmw_bo_pin_in_placement - Validate a buffer to placement.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to move.
+ * @placement:  The placement to pin it.
+ * @interruptible:  Use interruptible wait.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
+ */
+int vmw_bo_pin_in_placement(struct vmw_private *dev_priv,
+			    struct vmw_buffer_object *buf,
+			    struct ttm_placement *placement,
+			    bool interruptible)
+{
+	struct ttm_operation_ctx ctx = {interruptible, false };
+	struct ttm_buffer_object *bo = &buf->base;
+	int ret;
+	uint32_t new_flags;
+
+	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
+	if (unlikely(ret != 0))
+		return ret;
+
+	vmw_execbuf_release_pinned_bo(dev_priv);
+
+	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
+	if (unlikely(ret != 0))
+		goto err;
+
+	if (buf->pin_count > 0)
+		ret = ttm_bo_mem_compat(placement, &bo->mem,
+					&new_flags) == true ? 0 : -EINVAL;
+	else
+		ret = ttm_bo_validate(bo, placement, &ctx);
+
+	if (!ret)
+		vmw_bo_pin_reserved(buf, true);
+
+	ttm_bo_unreserve(bo);
+
+err:
+	ttm_write_unlock(&dev_priv->reservation_sem);
+	return ret;
+}
+
+
+/**
+ * vmw_bo_pin_in_vram_or_gmr - Move a buffer to vram or gmr.
+ *
+ * This function takes the reservation_sem in write mode.
+ * Flushes and unpins the query bo to avoid failures.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to move.
+ * @pin:  Pin buffer if true.
+ * @interruptible:  Use interruptible wait.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
+ */
+int vmw_bo_pin_in_vram_or_gmr(struct vmw_private *dev_priv,
+			      struct vmw_buffer_object *buf,
+			      bool interruptible)
+{
+	struct ttm_operation_ctx ctx = {interruptible, false };
+	struct ttm_buffer_object *bo = &buf->base;
+	int ret;
+	uint32_t new_flags;
+
+	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
+	if (unlikely(ret != 0))
+		return ret;
+
+	vmw_execbuf_release_pinned_bo(dev_priv);
+
+	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
+	if (unlikely(ret != 0))
+		goto err;
+
+	if (buf->pin_count > 0) {
+		ret = ttm_bo_mem_compat(&vmw_vram_gmr_placement, &bo->mem,
+					&new_flags) == true ? 0 : -EINVAL;
+		goto out_unreserve;
+	}
+
+	ret = ttm_bo_validate(bo, &vmw_vram_gmr_placement, &ctx);
+	if (likely(ret == 0) || ret == -ERESTARTSYS)
+		goto out_unreserve;
+
+	ret = ttm_bo_validate(bo, &vmw_vram_placement, &ctx);
+
+out_unreserve:
+	if (!ret)
+		vmw_bo_pin_reserved(buf, true);
+
+	ttm_bo_unreserve(bo);
+err:
+	ttm_write_unlock(&dev_priv->reservation_sem);
+	return ret;
+}
+
+
+/**
+ * vmw_bo_pin_in_vram - Move a buffer to vram.
+ *
+ * This function takes the reservation_sem in write mode.
+ * Flushes and unpins the query bo to avoid failures.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to move.
+ * @interruptible:  Use interruptible wait.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
+ */
+int vmw_bo_pin_in_vram(struct vmw_private *dev_priv,
+		       struct vmw_buffer_object *buf,
+		       bool interruptible)
+{
+	return vmw_bo_pin_in_placement(dev_priv, buf, &vmw_vram_placement,
+				       interruptible);
+}
+
+
+/**
+ * vmw_bo_pin_in_start_of_vram - Move a buffer to start of vram.
+ *
+ * This function takes the reservation_sem in write mode.
+ * Flushes and unpins the query bo to avoid failures.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to pin.
+ * @interruptible:  Use interruptible wait.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
+ */
+int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv,
+				struct vmw_buffer_object *buf,
+				bool interruptible)
+{
+	struct ttm_operation_ctx ctx = {interruptible, false };
+	struct ttm_buffer_object *bo = &buf->base;
+	struct ttm_placement placement;
+	struct ttm_place place;
+	int ret = 0;
+	uint32_t new_flags;
+
+	place = vmw_vram_placement.placement[0];
+	place.lpfn = bo->num_pages;
+	placement.num_placement = 1;
+	placement.placement = &place;
+	placement.num_busy_placement = 1;
+	placement.busy_placement = &place;
+
+	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
+	if (unlikely(ret != 0))
+		return ret;
+
+	vmw_execbuf_release_pinned_bo(dev_priv);
+	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
+	if (unlikely(ret != 0))
+		goto err_unlock;
+
+	/*
+	 * Is this buffer already in vram but not at the start of it?
+	 * In that case, evict it first because TTM isn't good at handling
+	 * that situation.
+	 */
+	if (bo->mem.mem_type == TTM_PL_VRAM &&
+	    bo->mem.start < bo->num_pages &&
+	    bo->mem.start > 0 &&
+	    buf->pin_count == 0) {
+		ctx.interruptible = false;
+		(void) ttm_bo_validate(bo, &vmw_sys_placement, &ctx);
+	}
+
+	if (buf->pin_count > 0)
+		ret = ttm_bo_mem_compat(&placement, &bo->mem,
+					&new_flags) == true ? 0 : -EINVAL;
+	else
+		ret = ttm_bo_validate(bo, &placement, &ctx);
+
+	/* For some reason we didn't end up at the start of vram */
+	WARN_ON(ret == 0 && bo->offset != 0);
+	if (!ret)
+		vmw_bo_pin_reserved(buf, true);
+
+	ttm_bo_unreserve(bo);
+err_unlock:
+	ttm_write_unlock(&dev_priv->reservation_sem);
+
+	return ret;
+}
+
+
+/**
+ * vmw_bo_unpin - Unpin the buffer given buffer, does not move the buffer.
+ *
+ * This function takes the reservation_sem in write mode.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to unpin.
+ * @interruptible:  Use interruptible wait.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
+ */
+int vmw_bo_unpin(struct vmw_private *dev_priv,
+		 struct vmw_buffer_object *buf,
+		 bool interruptible)
+{
+	struct ttm_buffer_object *bo = &buf->base;
+	int ret;
+
+	ret = ttm_read_lock(&dev_priv->reservation_sem, interruptible);
+	if (unlikely(ret != 0))
+		return ret;
+
+	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
+	if (unlikely(ret != 0))
+		goto err;
+
+	vmw_bo_pin_reserved(buf, false);
+
+	ttm_bo_unreserve(bo);
+
+err:
+	ttm_read_unlock(&dev_priv->reservation_sem);
+	return ret;
+}
+
+/**
+ * vmw_bo_get_guest_ptr - Get the guest ptr representing the current placement
+ * of a buffer.
+ *
+ * @bo: Pointer to a struct ttm_buffer_object. Must be pinned or reserved.
+ * @ptr: SVGAGuestPtr returning the result.
+ */
+void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *bo,
+			  SVGAGuestPtr *ptr)
+{
+	if (bo->mem.mem_type == TTM_PL_VRAM) {
+		ptr->gmrId = SVGA_GMR_FRAMEBUFFER;
+		ptr->offset = bo->offset;
+	} else {
+		ptr->gmrId = bo->mem.start;
+		ptr->offset = 0;
+	}
+}
+
+
+/**
+ * vmw_bo_pin_reserved - Pin or unpin a buffer object without moving it.
+ *
+ * @vbo: The buffer object. Must be reserved.
+ * @pin: Whether to pin or unpin.
+ *
+ */
+void vmw_bo_pin_reserved(struct vmw_buffer_object *vbo, bool pin)
+{
+	struct ttm_operation_ctx ctx = { false, true };
+	struct ttm_place pl;
+	struct ttm_placement placement;
+	struct ttm_buffer_object *bo = &vbo->base;
+	uint32_t old_mem_type = bo->mem.mem_type;
+	int ret;
+
+	lockdep_assert_held(&bo->resv->lock.base);
+
+	if (pin) {
+		if (vbo->pin_count++ > 0)
+			return;
+	} else {
+		WARN_ON(vbo->pin_count <= 0);
+		if (--vbo->pin_count > 0)
+			return;
+	}
+
+	pl.fpfn = 0;
+	pl.lpfn = 0;
+	pl.flags = TTM_PL_FLAG_VRAM | VMW_PL_FLAG_GMR | VMW_PL_FLAG_MOB
+		| TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED;
+	if (pin)
+		pl.flags |= TTM_PL_FLAG_NO_EVICT;
+
+	memset(&placement, 0, sizeof(placement));
+	placement.num_placement = 1;
+	placement.placement = &pl;
+
+	ret = ttm_bo_validate(bo, &placement, &ctx);
+
+	BUG_ON(ret != 0 || bo->mem.mem_type != old_mem_type);
+}
+
+
+/**
+ * vmw_bo_map_and_cache - Map a buffer object and cache the map
+ *
+ * @vbo: The buffer object to map
+ * Return: A kernel virtual address or NULL if mapping failed.
+ *
+ * This function maps a buffer object into the kernel address space, or
+ * returns the virtual kernel address of an already existing map. The virtual
+ * address remains valid as long as the buffer object is pinned or reserved.
+ * The cached map is torn down on either
+ * 1) Buffer object move
+ * 2) Buffer object swapout
+ * 3) Buffer object destruction
+ *
+ */
+void *vmw_bo_map_and_cache(struct vmw_buffer_object *vbo)
+{
+	struct ttm_buffer_object *bo = &vbo->base;
+	bool not_used;
+	void *virtual;
+	int ret;
+
+	virtual = ttm_kmap_obj_virtual(&vbo->map, &not_used);
+	if (virtual)
+		return virtual;
+
+	ret = ttm_bo_kmap(bo, 0, bo->num_pages, &vbo->map);
+	if (ret)
+		DRM_ERROR("Buffer object map failed: %d.\n", ret);
+
+	return ttm_kmap_obj_virtual(&vbo->map, &not_used);
+}
+
+
+/**
+ * vmw_bo_unmap - Tear down a cached buffer object map.
+ *
+ * @vbo: The buffer object whose map we are tearing down.
+ *
+ * This function tears down a cached map set up using
+ * vmw_buffer_object_map_and_cache().
+ */
+void vmw_bo_unmap(struct vmw_buffer_object *vbo)
+{
+	if (vbo->map.bo == NULL)
+		return;
+
+	ttm_bo_kunmap(&vbo->map);
+}
+
+
+/**
+ * vmw_bo_acc_size - Calculate the pinned memory usage of buffers
+ *
+ * @dev_priv: Pointer to a struct vmw_private identifying the device.
+ * @size: The requested buffer size.
+ * @user: Whether this is an ordinary dma buffer or a user dma buffer.
+ */
+static size_t vmw_bo_acc_size(struct vmw_private *dev_priv, size_t size,
+			      bool user)
+{
+	static size_t struct_size, user_struct_size;
+	size_t num_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	size_t page_array_size = ttm_round_pot(num_pages * sizeof(void *));
+
+	if (unlikely(struct_size == 0)) {
+		size_t backend_size = ttm_round_pot(vmw_tt_size);
+
+		struct_size = backend_size +
+			ttm_round_pot(sizeof(struct vmw_buffer_object));
+		user_struct_size = backend_size +
+			ttm_round_pot(sizeof(struct vmw_user_buffer_object));
+	}
+
+	if (dev_priv->map_mode == vmw_dma_alloc_coherent)
+		page_array_size +=
+			ttm_round_pot(num_pages * sizeof(dma_addr_t));
+
+	return ((user) ? user_struct_size : struct_size) +
+		page_array_size;
+}
+
+
+/**
+ * vmw_bo_bo_free - vmw buffer object destructor
+ *
+ * @bo: Pointer to the embedded struct ttm_buffer_object
+ */
+void vmw_bo_bo_free(struct ttm_buffer_object *bo)
+{
+	struct vmw_buffer_object *vmw_bo = vmw_buffer_object(bo);
+
+	vmw_bo_unmap(vmw_bo);
+	kfree(vmw_bo);
+}
+
+
+/**
+ * vmw_user_bo_destroy - vmw buffer object destructor
+ *
+ * @bo: Pointer to the embedded struct ttm_buffer_object
+ */
+static void vmw_user_bo_destroy(struct ttm_buffer_object *bo)
+{
+	struct vmw_user_buffer_object *vmw_user_bo = vmw_user_buffer_object(bo);
+
+	vmw_bo_unmap(&vmw_user_bo->vbo);
+	ttm_prime_object_kfree(vmw_user_bo, prime);
+}
+
+
+/**
+ * vmw_bo_init - Initialize a vmw buffer object
+ *
+ * @dev_priv: Pointer to the device private struct
+ * @vmw_bo: Pointer to the struct vmw_buffer_object to initialize.
+ * @size: Buffer object size in bytes.
+ * @placement: Initial placement.
+ * @interruptible: Whether waits should be performed interruptible.
+ * @bo_free: The buffer object destructor.
+ * Returns: Zero on success, negative error code on error.
+ *
+ * Note that on error, the code will free the buffer object.
+ */
+int vmw_bo_init(struct vmw_private *dev_priv,
+		struct vmw_buffer_object *vmw_bo,
+		size_t size, struct ttm_placement *placement,
+		bool interruptible,
+		void (*bo_free)(struct ttm_buffer_object *bo))
+{
+	struct ttm_bo_device *bdev = &dev_priv->bdev;
+	size_t acc_size;
+	int ret;
+	bool user = (bo_free == &vmw_user_bo_destroy);
+
+	WARN_ON_ONCE(!bo_free && (!user && (bo_free != vmw_bo_bo_free)));
+
+	acc_size = vmw_bo_acc_size(dev_priv, size, user);
+	memset(vmw_bo, 0, sizeof(*vmw_bo));
+
+	INIT_LIST_HEAD(&vmw_bo->res_list);
+
+	ret = ttm_bo_init(bdev, &vmw_bo->base, size,
+			  ttm_bo_type_device, placement,
+			  0, interruptible, acc_size,
+			  NULL, NULL, bo_free);
+	return ret;
+}
+
+
+/**
+ * vmw_user_bo_release - TTM reference base object release callback for
+ * vmw user buffer objects
+ *
+ * @p_base: The TTM base object pointer about to be unreferenced.
+ *
+ * Clears the TTM base object pointer and drops the reference the
+ * base object has on the underlying struct vmw_buffer_object.
+ */
+static void vmw_user_bo_release(struct ttm_base_object **p_base)
+{
+	struct vmw_user_buffer_object *vmw_user_bo;
+	struct ttm_base_object *base = *p_base;
+	struct ttm_buffer_object *bo;
+
+	*p_base = NULL;
+
+	if (unlikely(base == NULL))
+		return;
+
+	vmw_user_bo = container_of(base, struct vmw_user_buffer_object,
+				   prime.base);
+	bo = &vmw_user_bo->vbo.base;
+	ttm_bo_unref(&bo);
+}
+
+
+/**
+ * vmw_user_bo_ref_obj-release - TTM synccpu reference object release callback
+ * for vmw user buffer objects
+ *
+ * @base: Pointer to the TTM base object
+ * @ref_type: Reference type of the reference reaching zero.
+ *
+ * Called when user-space drops its last synccpu reference on the buffer
+ * object, Either explicitly or as part of a cleanup file close.
+ */
+static void vmw_user_bo_ref_obj_release(struct ttm_base_object *base,
+					enum ttm_ref_type ref_type)
+{
+	struct vmw_user_buffer_object *user_bo;
+
+	user_bo = container_of(base, struct vmw_user_buffer_object, prime.base);
+
+	switch (ref_type) {
+	case TTM_REF_SYNCCPU_WRITE:
+		ttm_bo_synccpu_write_release(&user_bo->vbo.base);
+		break;
+	default:
+		WARN_ONCE(true, "Undefined buffer object reference release.\n");
+	}
+}
+
+
+/**
+ * vmw_user_bo_alloc - Allocate a user buffer object
+ *
+ * @dev_priv: Pointer to a struct device private.
+ * @tfile: Pointer to a struct ttm_object_file on which to register the user
+ * object.
+ * @size: Size of the buffer object.
+ * @shareable: Boolean whether the buffer is shareable with other open files.
+ * @handle: Pointer to where the handle value should be assigned.
+ * @p_vbo: Pointer to where the refcounted struct vmw_buffer_object pointer
+ * should be assigned.
+ * Return: Zero on success, negative error code on error.
+ */
+int vmw_user_bo_alloc(struct vmw_private *dev_priv,
+		      struct ttm_object_file *tfile,
+		      uint32_t size,
+		      bool shareable,
+		      uint32_t *handle,
+		      struct vmw_buffer_object **p_vbo,
+		      struct ttm_base_object **p_base)
+{
+	struct vmw_user_buffer_object *user_bo;
+	struct ttm_buffer_object *tmp;
+	int ret;
+
+	user_bo = kzalloc(sizeof(*user_bo), GFP_KERNEL);
+	if (unlikely(!user_bo)) {
+		DRM_ERROR("Failed to allocate a buffer.\n");
+		return -ENOMEM;
+	}
+
+	ret = vmw_bo_init(dev_priv, &user_bo->vbo, size,
+			  (dev_priv->has_mob) ?
+			  &vmw_sys_placement :
+			  &vmw_vram_sys_placement, true,
+			  &vmw_user_bo_destroy);
+	if (unlikely(ret != 0))
+		return ret;
+
+	tmp = ttm_bo_reference(&user_bo->vbo.base);
+	ret = ttm_prime_object_init(tfile,
+				    size,
+				    &user_bo->prime,
+				    shareable,
+				    ttm_buffer_type,
+				    &vmw_user_bo_release,
+				    &vmw_user_bo_ref_obj_release);
+	if (unlikely(ret != 0)) {
+		ttm_bo_unref(&tmp);
+		goto out_no_base_object;
+	}
+
+	*p_vbo = &user_bo->vbo;
+	if (p_base) {
+		*p_base = &user_bo->prime.base;
+		kref_get(&(*p_base)->refcount);
+	}
+	*handle = user_bo->prime.base.hash.key;
+
+out_no_base_object:
+	return ret;
+}
+
+
+/**
+ * vmw_user_bo_verify_access - verify access permissions on this
+ * buffer object.
+ *
+ * @bo: Pointer to the buffer object being accessed
+ * @tfile: Identifying the caller.
+ */
+int vmw_user_bo_verify_access(struct ttm_buffer_object *bo,
+			      struct ttm_object_file *tfile)
+{
+	struct vmw_user_buffer_object *vmw_user_bo;
+
+	if (unlikely(bo->destroy != vmw_user_bo_destroy))
+		return -EPERM;
+
+	vmw_user_bo = vmw_user_buffer_object(bo);
+
+	/* Check that the caller has opened the object. */
+	if (likely(ttm_ref_object_exists(tfile, &vmw_user_bo->prime.base)))
+		return 0;
+
+	DRM_ERROR("Could not grant buffer access.\n");
+	return -EPERM;
+}
+
+
+/**
+ * vmw_user_bo_synccpu_grab - Grab a struct vmw_user_buffer_object for cpu
+ * access, idling previous GPU operations on the buffer and optionally
+ * blocking it for further command submissions.
+ *
+ * @user_bo: Pointer to the buffer object being grabbed for CPU access
+ * @tfile: Identifying the caller.
+ * @flags: Flags indicating how the grab should be performed.
+ * Return: Zero on success, Negative error code on error. In particular,
+ * -EBUSY will be returned if a dontblock operation is requested and the
+ * buffer object is busy, and -ERESTARTSYS will be returned if a wait is
+ * interrupted by a signal.
+ *
+ * A blocking grab will be automatically released when @tfile is closed.
+ */
+static int vmw_user_bo_synccpu_grab(struct vmw_user_buffer_object *user_bo,
+				    struct ttm_object_file *tfile,
+				    uint32_t flags)
+{
+	struct ttm_buffer_object *bo = &user_bo->vbo.base;
+	bool existed;
+	int ret;
+
+	if (flags & drm_vmw_synccpu_allow_cs) {
+		bool nonblock = !!(flags & drm_vmw_synccpu_dontblock);
+		long lret;
+
+		lret = reservation_object_wait_timeout_rcu
+			(bo->resv, true, true,
+			 nonblock ? 0 : MAX_SCHEDULE_TIMEOUT);
+		if (!lret)
+			return -EBUSY;
+		else if (lret < 0)
+			return lret;
+		return 0;
+	}
+
+	ret = ttm_bo_synccpu_write_grab
+		(bo, !!(flags & drm_vmw_synccpu_dontblock));
+	if (unlikely(ret != 0))
+		return ret;
+
+	ret = ttm_ref_object_add(tfile, &user_bo->prime.base,
+				 TTM_REF_SYNCCPU_WRITE, &existed, false);
+	if (ret != 0 || existed)
+		ttm_bo_synccpu_write_release(&user_bo->vbo.base);
+
+	return ret;
+}
+
+/**
+ * vmw_user_bo_synccpu_release - Release a previous grab for CPU access,
+ * and unblock command submission on the buffer if blocked.
+ *
+ * @handle: Handle identifying the buffer object.
+ * @tfile: Identifying the caller.
+ * @flags: Flags indicating the type of release.
+ */
+static int vmw_user_bo_synccpu_release(uint32_t handle,
+					   struct ttm_object_file *tfile,
+					   uint32_t flags)
+{
+	if (!(flags & drm_vmw_synccpu_allow_cs))
+		return ttm_ref_object_base_unref(tfile, handle,
+						 TTM_REF_SYNCCPU_WRITE);
+
+	return 0;
+}
+
+
+/**
+ * vmw_user_bo_synccpu_ioctl - ioctl function implementing the synccpu
+ * functionality.
+ *
+ * @dev: Identifies the drm device.
+ * @data: Pointer to the ioctl argument.
+ * @file_priv: Identifies the caller.
+ * Return: Zero on success, negative error code on error.
+ *
+ * This function checks the ioctl arguments for validity and calls the
+ * relevant synccpu functions.
+ */
+int vmw_user_bo_synccpu_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv)
+{
+	struct drm_vmw_synccpu_arg *arg =
+		(struct drm_vmw_synccpu_arg *) data;
+	struct vmw_buffer_object *vbo;
+	struct vmw_user_buffer_object *user_bo;
+	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+	struct ttm_base_object *buffer_base;
+	int ret;
+
+	if ((arg->flags & (drm_vmw_synccpu_read | drm_vmw_synccpu_write)) == 0
+	    || (arg->flags & ~(drm_vmw_synccpu_read | drm_vmw_synccpu_write |
+			       drm_vmw_synccpu_dontblock |
+			       drm_vmw_synccpu_allow_cs)) != 0) {
+		DRM_ERROR("Illegal synccpu flags.\n");
+		return -EINVAL;
+	}
+
+	switch (arg->op) {
+	case drm_vmw_synccpu_grab:
+		ret = vmw_user_bo_lookup(tfile, arg->handle, &vbo,
+					     &buffer_base);
+		if (unlikely(ret != 0))
+			return ret;
+
+		user_bo = container_of(vbo, struct vmw_user_buffer_object,
+				       vbo);
+		ret = vmw_user_bo_synccpu_grab(user_bo, tfile, arg->flags);
+		vmw_bo_unreference(&vbo);
+		ttm_base_object_unref(&buffer_base);
+		if (unlikely(ret != 0 && ret != -ERESTARTSYS &&
+			     ret != -EBUSY)) {
+			DRM_ERROR("Failed synccpu grab on handle 0x%08x.\n",
+				  (unsigned int) arg->handle);
+			return ret;
+		}
+		break;
+	case drm_vmw_synccpu_release:
+		ret = vmw_user_bo_synccpu_release(arg->handle, tfile,
+						  arg->flags);
+		if (unlikely(ret != 0)) {
+			DRM_ERROR("Failed synccpu release on handle 0x%08x.\n",
+				  (unsigned int) arg->handle);
+			return ret;
+		}
+		break;
+	default:
+		DRM_ERROR("Invalid synccpu operation.\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+
+/**
+ * vmw_bo_alloc_ioctl - ioctl function implementing the buffer object
+ * allocation functionality.
+ *
+ * @dev: Identifies the drm device.
+ * @data: Pointer to the ioctl argument.
+ * @file_priv: Identifies the caller.
+ * Return: Zero on success, negative error code on error.
+ *
+ * This function checks the ioctl arguments for validity and allocates a
+ * struct vmw_user_buffer_object bo.
+ */
+int vmw_bo_alloc_ioctl(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	union drm_vmw_alloc_dmabuf_arg *arg =
+	    (union drm_vmw_alloc_dmabuf_arg *)data;
+	struct drm_vmw_alloc_dmabuf_req *req = &arg->req;
+	struct drm_vmw_dmabuf_rep *rep = &arg->rep;
+	struct vmw_buffer_object *vbo;
+	uint32_t handle;
+	int ret;
+
+	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
+	if (unlikely(ret != 0))
+		return ret;
+
+	ret = vmw_user_bo_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
+				req->size, false, &handle, &vbo,
+				NULL);
+	if (unlikely(ret != 0))
+		goto out_no_bo;
+
+	rep->handle = handle;
+	rep->map_handle = drm_vma_node_offset_addr(&vbo->base.vma_node);
+	rep->cur_gmr_id = handle;
+	rep->cur_gmr_offset = 0;
+
+	vmw_bo_unreference(&vbo);
+
+out_no_bo:
+	ttm_read_unlock(&dev_priv->reservation_sem);
+
+	return ret;
+}
+
+
+/**
+ * vmw_bo_unref_ioctl - Generic handle close ioctl.
+ *
+ * @dev: Identifies the drm device.
+ * @data: Pointer to the ioctl argument.
+ * @file_priv: Identifies the caller.
+ * Return: Zero on success, negative error code on error.
+ *
+ * This function checks the ioctl arguments for validity and closes a
+ * handle to a TTM base object, optionally freeing the object.
+ */
+int vmw_bo_unref_ioctl(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv)
+{
+	struct drm_vmw_unref_dmabuf_arg *arg =
+	    (struct drm_vmw_unref_dmabuf_arg *)data;
+
+	return ttm_ref_object_base_unref(vmw_fpriv(file_priv)->tfile,
+					 arg->handle,
+					 TTM_REF_USAGE);
+}
+
+
+/**
+ * vmw_user_bo_lookup - Look up a vmw user buffer object from a handle.
+ *
+ * @tfile: The TTM object file the handle is registered with.
+ * @handle: The user buffer object handle
+ * @out: Pointer to a where a pointer to the embedded
+ * struct vmw_buffer_object should be placed.
+ * @p_base: Pointer to where a pointer to the TTM base object should be
+ * placed, or NULL if no such pointer is required.
+ * Return: Zero on success, Negative error code on error.
+ *
+ * Both the output base object pointer and the vmw buffer object pointer
+ * will be refcounted.
+ */
+int vmw_user_bo_lookup(struct ttm_object_file *tfile,
+		       uint32_t handle, struct vmw_buffer_object **out,
+		       struct ttm_base_object **p_base)
+{
+	struct vmw_user_buffer_object *vmw_user_bo;
+	struct ttm_base_object *base;
+
+	base = ttm_base_object_lookup(tfile, handle);
+	if (unlikely(base == NULL)) {
+		DRM_ERROR("Invalid buffer object handle 0x%08lx.\n",
+			  (unsigned long)handle);
+		return -ESRCH;
+	}
+
+	if (unlikely(ttm_base_object_type(base) != ttm_buffer_type)) {
+		ttm_base_object_unref(&base);
+		DRM_ERROR("Invalid buffer object handle 0x%08lx.\n",
+			  (unsigned long)handle);
+		return -EINVAL;
+	}
+
+	vmw_user_bo = container_of(base, struct vmw_user_buffer_object,
+				   prime.base);
+	(void)ttm_bo_reference(&vmw_user_bo->vbo.base);
+	if (p_base)
+		*p_base = base;
+	else
+		ttm_base_object_unref(&base);
+	*out = &vmw_user_bo->vbo;
+
+	return 0;
+}
+
+
+/**
+ * vmw_user_bo_reference - Open a handle to a vmw user buffer object.
+ *
+ * @tfile: The TTM object file to register the handle with.
+ * @vbo: The embedded vmw buffer object.
+ * @handle: Pointer to where the new handle should be placed.
+ * Return: Zero on success, Negative error code on error.
+ */
+int vmw_user_bo_reference(struct ttm_object_file *tfile,
+			  struct vmw_buffer_object *vbo,
+			  uint32_t *handle)
+{
+	struct vmw_user_buffer_object *user_bo;
+
+	if (vbo->base.destroy != vmw_user_bo_destroy)
+		return -EINVAL;
+
+	user_bo = container_of(vbo, struct vmw_user_buffer_object, vbo);
+
+	*handle = user_bo->prime.base.hash.key;
+	return ttm_ref_object_add(tfile, &user_bo->prime.base,
+				  TTM_REF_USAGE, NULL, false);
+}
+
+
+/**
+ * vmw_bo_fence_single - Utility function to fence a single TTM buffer
+ *                       object without unreserving it.
+ *
+ * @bo:             Pointer to the struct ttm_buffer_object to fence.
+ * @fence:          Pointer to the fence. If NULL, this function will
+ *                  insert a fence into the command stream..
+ *
+ * Contrary to the ttm_eu version of this function, it takes only
+ * a single buffer object instead of a list, and it also doesn't
+ * unreserve the buffer object, which needs to be done separately.
+ */
+void vmw_bo_fence_single(struct ttm_buffer_object *bo,
+			 struct vmw_fence_obj *fence)
+{
+	struct ttm_bo_device *bdev = bo->bdev;
+
+	struct vmw_private *dev_priv =
+		container_of(bdev, struct vmw_private, bdev);
+
+	if (fence == NULL) {
+		vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL);
+		reservation_object_add_excl_fence(bo->resv, &fence->base);
+		dma_fence_put(&fence->base);
+	} else
+		reservation_object_add_excl_fence(bo->resv, &fence->base);
+}
+
+
+/**
+ * vmw_dumb_create - Create a dumb kms buffer
+ *
+ * @file_priv: Pointer to a struct drm_file identifying the caller.
+ * @dev: Pointer to the drm device.
+ * @args: Pointer to a struct drm_mode_create_dumb structure
+ * Return: Zero on success, negative error code on failure.
+ *
+ * This is a driver callback for the core drm create_dumb functionality.
+ * Note that this is very similar to the vmw_bo_alloc ioctl, except
+ * that the arguments have a different format.
+ */
+int vmw_dumb_create(struct drm_file *file_priv,
+		    struct drm_device *dev,
+		    struct drm_mode_create_dumb *args)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	struct vmw_buffer_object *vbo;
+	int ret;
+
+	args->pitch = args->width * ((args->bpp + 7) / 8);
+	args->size = args->pitch * args->height;
+
+	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
+	if (unlikely(ret != 0))
+		return ret;
+
+	ret = vmw_user_bo_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
+				    args->size, false, &args->handle,
+				    &vbo, NULL);
+	if (unlikely(ret != 0))
+		goto out_no_bo;
+
+	vmw_bo_unreference(&vbo);
+out_no_bo:
+	ttm_read_unlock(&dev_priv->reservation_sem);
+	return ret;
+}
+
+
+/**
+ * vmw_dumb_map_offset - Return the address space offset of a dumb buffer
+ *
+ * @file_priv: Pointer to a struct drm_file identifying the caller.
+ * @dev: Pointer to the drm device.
+ * @handle: Handle identifying the dumb buffer.
+ * @offset: The address space offset returned.
+ * Return: Zero on success, negative error code on failure.
+ *
+ * This is a driver callback for the core drm dumb_map_offset functionality.
+ */
+int vmw_dumb_map_offset(struct drm_file *file_priv,
+			struct drm_device *dev, uint32_t handle,
+			uint64_t *offset)
+{
+	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+	struct vmw_buffer_object *out_buf;
+	int ret;
+
+	ret = vmw_user_bo_lookup(tfile, handle, &out_buf, NULL);
+	if (ret != 0)
+		return -EINVAL;
+
+	*offset = drm_vma_node_offset_addr(&out_buf->base.vma_node);
+	vmw_bo_unreference(&out_buf);
+	return 0;
+}
+
+
+/**
+ * vmw_dumb_destroy - Destroy a dumb boffer
+ *
+ * @file_priv: Pointer to a struct drm_file identifying the caller.
+ * @dev: Pointer to the drm device.
+ * @handle: Handle identifying the dumb buffer.
+ * Return: Zero on success, negative error code on failure.
+ *
+ * This is a driver callback for the core drm dumb_destroy functionality.
+ */
+int vmw_dumb_destroy(struct drm_file *file_priv,
+		     struct drm_device *dev,
+		     uint32_t handle)
+{
+	return ttm_ref_object_base_unref(vmw_fpriv(file_priv)->tfile,
+					 handle, TTM_REF_USAGE);
+}
+
+
+/**
+ * vmw_bo_swap_notify - swapout notify callback.
+ *
+ * @bo: The buffer object to be swapped out.
+ */
+void vmw_bo_swap_notify(struct ttm_buffer_object *bo)
+{
+	/* Is @bo embedded in a struct vmw_buffer_object? */
+	if (bo->destroy != vmw_bo_bo_free &&
+	    bo->destroy != vmw_user_bo_destroy)
+		return;
+
+	/* Kill any cached kernel maps before swapout */
+	vmw_bo_unmap(vmw_buffer_object(bo));
+}
+
+
+/**
+ * vmw_bo_move_notify - TTM move_notify_callback
+ *
+ * @bo: The TTM buffer object about to move.
+ * @mem: The struct ttm_mem_reg indicating to what memory
+ *       region the move is taking place.
+ *
+ * Detaches cached maps and device bindings that require that the
+ * buffer doesn't move.
+ */
+void vmw_bo_move_notify(struct ttm_buffer_object *bo,
+			struct ttm_mem_reg *mem)
+{
+	struct vmw_buffer_object *vbo;
+
+	if (mem == NULL)
+		return;
+
+	/* Make sure @bo is embedded in a struct vmw_buffer_object? */
+	if (bo->destroy != vmw_bo_bo_free &&
+	    bo->destroy != vmw_user_bo_destroy)
+		return;
+
+	vbo = container_of(bo, struct vmw_buffer_object, base);
+
+	/*
+	 * Kill any cached kernel maps before move to or from VRAM.
+	 * With other types of moves, the underlying pages stay the same,
+	 * and the map can be kept.
+	 */
+	if (mem->mem_type == TTM_PL_VRAM || bo->mem.mem_type == TTM_PL_VRAM)
+		vmw_bo_unmap(vbo);
+
+	/*
+	 * If we're moving a backup MOB out of MOB placement, then make sure we
+	 * read back all resource content first, and unbind the MOB from
+	 * the resource.
+	 */
+	if (mem->mem_type != VMW_PL_MOB && bo->mem.mem_type == VMW_PL_MOB)
+		vmw_resource_unbind_list(vbo);
+}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
index 9f45d5004cae..e7e4655d3f36 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
index 36c7b6c839c0..3b75af9bf85f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2014-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2014-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
index 3767ac335aca..7c3cb8efd11a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -38,7 +38,7 @@ struct vmw_user_context {
 	struct vmw_cmdbuf_res_manager *man;
 	struct vmw_resource *cotables[SVGA_COTABLE_DX10_MAX];
 	spinlock_t cotable_lock;
-	struct vmw_dma_buffer *dx_query_mob;
+	struct vmw_buffer_object *dx_query_mob;
 };
 
 static void vmw_user_context_free(struct vmw_resource *res);
@@ -424,7 +424,7 @@ static int vmw_gb_context_unbind(struct vmw_resource *res,
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv,
 					  &fence, NULL);
 
-	vmw_fence_single_bo(bo, fence);
+	vmw_bo_fence_single(bo, fence);
 
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
@@ -648,7 +648,7 @@ static int vmw_dx_context_unbind(struct vmw_resource *res,
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv,
 					  &fence, NULL);
 
-	vmw_fence_single_bo(bo, fence);
+	vmw_bo_fence_single(bo, fence);
 
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
@@ -900,7 +900,7 @@ vmw_context_binding_state(struct vmw_resource *ctx)
  * specified in the parameter.  0 otherwise.
  */
 int vmw_context_bind_dx_query(struct vmw_resource *ctx_res,
-			      struct vmw_dma_buffer *mob)
+			      struct vmw_buffer_object *mob)
 {
 	struct vmw_user_context *uctx =
 		container_of(ctx_res, struct vmw_user_context, res);
@@ -908,7 +908,7 @@ int vmw_context_bind_dx_query(struct vmw_resource *ctx_res,
 	if (mob == NULL) {
 		if (uctx->dx_query_mob) {
 			uctx->dx_query_mob->dx_query_ctx = NULL;
-			vmw_dmabuf_unreference(&uctx->dx_query_mob);
+			vmw_bo_unreference(&uctx->dx_query_mob);
 			uctx->dx_query_mob = NULL;
 		}
 
@@ -922,7 +922,7 @@ int vmw_context_bind_dx_query(struct vmw_resource *ctx_res,
 	mob->dx_query_ctx  = ctx_res;
 
 	if (!uctx->dx_query_mob)
-		uctx->dx_query_mob = vmw_dmabuf_reference(mob);
+		uctx->dx_query_mob = vmw_bo_reference(mob);
 
 	return 0;
 }
@@ -932,7 +932,7 @@ int vmw_context_bind_dx_query(struct vmw_resource *ctx_res,
  *
  * @ctx_res: The context resource
  */
-struct vmw_dma_buffer *
+struct vmw_buffer_object *
 vmw_context_get_dx_query_mob(struct vmw_resource *ctx_res)
 {
 	struct vmw_user_context *uctx =
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
index cbf54ea7b4c0..1d45714e1d5a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2014-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2014-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -324,7 +324,7 @@ static int vmw_cotable_unbind(struct vmw_resource *res,
 		vmw_dx_context_scrub_cotables(vcotbl->ctx, readback);
 	mutex_unlock(&dev_priv->binding_mutex);
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL);
-	vmw_fence_single_bo(bo, fence);
+	vmw_bo_fence_single(bo, fence);
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
 
@@ -367,7 +367,7 @@ static int vmw_cotable_readback(struct vmw_resource *res)
 	}
 
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL);
-	vmw_fence_single_bo(&res->backup->base, fence);
+	vmw_bo_fence_single(&res->backup->base, fence);
 	vmw_fence_obj_unreference(&fence);
 
 	return 0;
@@ -390,7 +390,7 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size)
 	struct ttm_operation_ctx ctx = { false, false };
 	struct vmw_private *dev_priv = res->dev_priv;
 	struct vmw_cotable *vcotbl = vmw_cotable(res);
-	struct vmw_dma_buffer *buf, *old_buf = res->backup;
+	struct vmw_buffer_object *buf, *old_buf = res->backup;
 	struct ttm_buffer_object *bo, *old_bo = &res->backup->base;
 	size_t old_size = res->backup_size;
 	size_t old_size_read_back = vcotbl->size_read_back;
@@ -415,8 +415,8 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size)
 	if (!buf)
 		return -ENOMEM;
 
-	ret = vmw_dmabuf_init(dev_priv, buf, new_size, &vmw_mob_ne_placement,
-			      true, vmw_dmabuf_bo_free);
+	ret = vmw_bo_init(dev_priv, buf, new_size, &vmw_mob_ne_placement,
+			  true, vmw_bo_bo_free);
 	if (ret) {
 		DRM_ERROR("Failed initializing new cotable MOB.\n");
 		return ret;
@@ -482,7 +482,7 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size)
 	/* Let go of the old mob. */
 	list_del(&res->mob_head);
 	list_add_tail(&res->mob_head, &buf->res_list);
-	vmw_dmabuf_unreference(&old_buf);
+	vmw_bo_unreference(&old_buf);
 	res->id = vcotbl->type;
 
 	return 0;
@@ -491,7 +491,7 @@ out_map_new:
 	ttm_bo_kunmap(&old_map);
 out_wait:
 	ttm_bo_unreserve(bo);
-	vmw_dmabuf_unreference(&buf);
+	vmw_bo_unreference(&buf);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
deleted file mode 100644
index d59d9dd16ebc..000000000000
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
+++ /dev/null
@@ -1,376 +0,0 @@
-/**************************************************************************
- *
- * Copyright © 2011-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the
- * "Software"), to deal in the Software without restriction, including
- * without limitation the rights to use, copy, modify, merge, publish,
- * distribute, sub license, and/or sell copies of the Software, and to
- * permit persons to whom the Software is furnished to do so, subject to
- * the following conditions:
- *
- * The above copyright notice and this permission notice (including the
- * next paragraph) shall be included in all copies or substantial portions
- * of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
- * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
- * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
- * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
- * USE OR OTHER DEALINGS IN THE SOFTWARE.
- *
- **************************************************************************/
-
-#include <drm/ttm/ttm_placement.h>
-
-#include <drm/drmP.h>
-#include "vmwgfx_drv.h"
-
-
-/**
- * vmw_dmabuf_pin_in_placement - Validate a buffer to placement.
- *
- * @dev_priv:  Driver private.
- * @buf:  DMA buffer to move.
- * @placement:  The placement to pin it.
- * @interruptible:  Use interruptible wait.
- *
- * Returns
- *  -ERESTARTSYS if interrupted by a signal.
- */
-int vmw_dmabuf_pin_in_placement(struct vmw_private *dev_priv,
-				struct vmw_dma_buffer *buf,
-				struct ttm_placement *placement,
-				bool interruptible)
-{
-	struct ttm_operation_ctx ctx = {interruptible, false };
-	struct ttm_buffer_object *bo = &buf->base;
-	int ret;
-	uint32_t new_flags;
-
-	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
-	if (unlikely(ret != 0))
-		return ret;
-
-	vmw_execbuf_release_pinned_bo(dev_priv);
-
-	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
-	if (unlikely(ret != 0))
-		goto err;
-
-	if (buf->pin_count > 0)
-		ret = ttm_bo_mem_compat(placement, &bo->mem,
-					&new_flags) == true ? 0 : -EINVAL;
-	else
-		ret = ttm_bo_validate(bo, placement, &ctx);
-
-	if (!ret)
-		vmw_bo_pin_reserved(buf, true);
-
-	ttm_bo_unreserve(bo);
-
-err:
-	ttm_write_unlock(&dev_priv->reservation_sem);
-	return ret;
-}
-
-/**
- * vmw_dmabuf_pin_in_vram_or_gmr - Move a buffer to vram or gmr.
- *
- * This function takes the reservation_sem in write mode.
- * Flushes and unpins the query bo to avoid failures.
- *
- * @dev_priv:  Driver private.
- * @buf:  DMA buffer to move.
- * @pin:  Pin buffer if true.
- * @interruptible:  Use interruptible wait.
- *
- * Returns
- * -ERESTARTSYS if interrupted by a signal.
- */
-int vmw_dmabuf_pin_in_vram_or_gmr(struct vmw_private *dev_priv,
-				  struct vmw_dma_buffer *buf,
-				  bool interruptible)
-{
-	struct ttm_operation_ctx ctx = {interruptible, false };
-	struct ttm_buffer_object *bo = &buf->base;
-	int ret;
-	uint32_t new_flags;
-
-	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
-	if (unlikely(ret != 0))
-		return ret;
-
-	vmw_execbuf_release_pinned_bo(dev_priv);
-
-	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
-	if (unlikely(ret != 0))
-		goto err;
-
-	if (buf->pin_count > 0) {
-		ret = ttm_bo_mem_compat(&vmw_vram_gmr_placement, &bo->mem,
-					&new_flags) == true ? 0 : -EINVAL;
-		goto out_unreserve;
-	}
-
-	ret = ttm_bo_validate(bo, &vmw_vram_gmr_placement, &ctx);
-	if (likely(ret == 0) || ret == -ERESTARTSYS)
-		goto out_unreserve;
-
-	ret = ttm_bo_validate(bo, &vmw_vram_placement, &ctx);
-
-out_unreserve:
-	if (!ret)
-		vmw_bo_pin_reserved(buf, true);
-
-	ttm_bo_unreserve(bo);
-err:
-	ttm_write_unlock(&dev_priv->reservation_sem);
-	return ret;
-}
-
-/**
- * vmw_dmabuf_pin_in_vram - Move a buffer to vram.
- *
- * This function takes the reservation_sem in write mode.
- * Flushes and unpins the query bo to avoid failures.
- *
- * @dev_priv:  Driver private.
- * @buf:  DMA buffer to move.
- * @interruptible:  Use interruptible wait.
- *
- * Returns
- * -ERESTARTSYS if interrupted by a signal.
- */
-int vmw_dmabuf_pin_in_vram(struct vmw_private *dev_priv,
-			   struct vmw_dma_buffer *buf,
-			   bool interruptible)
-{
-	return vmw_dmabuf_pin_in_placement(dev_priv, buf, &vmw_vram_placement,
-					   interruptible);
-}
-
-/**
- * vmw_dmabuf_pin_in_start_of_vram - Move a buffer to start of vram.
- *
- * This function takes the reservation_sem in write mode.
- * Flushes and unpins the query bo to avoid failures.
- *
- * @dev_priv:  Driver private.
- * @buf:  DMA buffer to pin.
- * @interruptible:  Use interruptible wait.
- *
- * Returns
- * -ERESTARTSYS if interrupted by a signal.
- */
-int vmw_dmabuf_pin_in_start_of_vram(struct vmw_private *dev_priv,
-				    struct vmw_dma_buffer *buf,
-				    bool interruptible)
-{
-	struct ttm_operation_ctx ctx = {interruptible, false };
-	struct ttm_buffer_object *bo = &buf->base;
-	struct ttm_placement placement;
-	struct ttm_place place;
-	int ret = 0;
-	uint32_t new_flags;
-
-	place = vmw_vram_placement.placement[0];
-	place.lpfn = bo->num_pages;
-	placement.num_placement = 1;
-	placement.placement = &place;
-	placement.num_busy_placement = 1;
-	placement.busy_placement = &place;
-
-	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
-	if (unlikely(ret != 0))
-		return ret;
-
-	vmw_execbuf_release_pinned_bo(dev_priv);
-	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
-	if (unlikely(ret != 0))
-		goto err_unlock;
-
-	/*
-	 * Is this buffer already in vram but not at the start of it?
-	 * In that case, evict it first because TTM isn't good at handling
-	 * that situation.
-	 */
-	if (bo->mem.mem_type == TTM_PL_VRAM &&
-	    bo->mem.start < bo->num_pages &&
-	    bo->mem.start > 0 &&
-	    buf->pin_count == 0) {
-		ctx.interruptible = false;
-		(void) ttm_bo_validate(bo, &vmw_sys_placement, &ctx);
-	}
-
-	if (buf->pin_count > 0)
-		ret = ttm_bo_mem_compat(&placement, &bo->mem,
-					&new_flags) == true ? 0 : -EINVAL;
-	else
-		ret = ttm_bo_validate(bo, &placement, &ctx);
-
-	/* For some reason we didn't end up at the start of vram */
-	WARN_ON(ret == 0 && bo->offset != 0);
-	if (!ret)
-		vmw_bo_pin_reserved(buf, true);
-
-	ttm_bo_unreserve(bo);
-err_unlock:
-	ttm_write_unlock(&dev_priv->reservation_sem);
-
-	return ret;
-}
-
-/**
- * vmw_dmabuf_unpin - Unpin the buffer given buffer, does not move the buffer.
- *
- * This function takes the reservation_sem in write mode.
- *
- * @dev_priv:  Driver private.
- * @buf:  DMA buffer to unpin.
- * @interruptible:  Use interruptible wait.
- *
- * Returns
- * -ERESTARTSYS if interrupted by a signal.
- */
-int vmw_dmabuf_unpin(struct vmw_private *dev_priv,
-		     struct vmw_dma_buffer *buf,
-		     bool interruptible)
-{
-	struct ttm_buffer_object *bo = &buf->base;
-	int ret;
-
-	ret = ttm_read_lock(&dev_priv->reservation_sem, interruptible);
-	if (unlikely(ret != 0))
-		return ret;
-
-	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
-	if (unlikely(ret != 0))
-		goto err;
-
-	vmw_bo_pin_reserved(buf, false);
-
-	ttm_bo_unreserve(bo);
-
-err:
-	ttm_read_unlock(&dev_priv->reservation_sem);
-	return ret;
-}
-
-/**
- * vmw_bo_get_guest_ptr - Get the guest ptr representing the current placement
- * of a buffer.
- *
- * @bo: Pointer to a struct ttm_buffer_object. Must be pinned or reserved.
- * @ptr: SVGAGuestPtr returning the result.
- */
-void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *bo,
-			  SVGAGuestPtr *ptr)
-{
-	if (bo->mem.mem_type == TTM_PL_VRAM) {
-		ptr->gmrId = SVGA_GMR_FRAMEBUFFER;
-		ptr->offset = bo->offset;
-	} else {
-		ptr->gmrId = bo->mem.start;
-		ptr->offset = 0;
-	}
-}
-
-
-/**
- * vmw_bo_pin_reserved - Pin or unpin a buffer object without moving it.
- *
- * @vbo: The buffer object. Must be reserved.
- * @pin: Whether to pin or unpin.
- *
- */
-void vmw_bo_pin_reserved(struct vmw_dma_buffer *vbo, bool pin)
-{
-	struct ttm_operation_ctx ctx = { false, true };
-	struct ttm_place pl;
-	struct ttm_placement placement;
-	struct ttm_buffer_object *bo = &vbo->base;
-	uint32_t old_mem_type = bo->mem.mem_type;
-	int ret;
-
-	lockdep_assert_held(&bo->resv->lock.base);
-
-	if (pin) {
-		if (vbo->pin_count++ > 0)
-			return;
-	} else {
-		WARN_ON(vbo->pin_count <= 0);
-		if (--vbo->pin_count > 0)
-			return;
-	}
-
-	pl.fpfn = 0;
-	pl.lpfn = 0;
-	pl.flags = TTM_PL_FLAG_VRAM | VMW_PL_FLAG_GMR | VMW_PL_FLAG_MOB
-		| TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED;
-	if (pin)
-		pl.flags |= TTM_PL_FLAG_NO_EVICT;
-
-	memset(&placement, 0, sizeof(placement));
-	placement.num_placement = 1;
-	placement.placement = &pl;
-
-	ret = ttm_bo_validate(bo, &placement, &ctx);
-
-	BUG_ON(ret != 0 || bo->mem.mem_type != old_mem_type);
-}
-
-
-/*
- * vmw_dma_buffer_unmap - Tear down a cached buffer object map.
- *
- * @vbo: The buffer object whose map we are tearing down.
- *
- * This function tears down a cached map set up using
- * vmw_dma_buffer_map_and_cache().
- */
-void vmw_dma_buffer_unmap(struct vmw_dma_buffer *vbo)
-{
-	if (vbo->map.bo == NULL)
-		return;
-
-	ttm_bo_kunmap(&vbo->map);
-}
-
-
-/*
- * vmw_dma_buffer_map_and_cache - Map a buffer object and cache the map
- *
- * @vbo: The buffer object to map
- * Return: A kernel virtual address or NULL if mapping failed.
- *
- * This function maps a buffer object into the kernel address space, or
- * returns the virtual kernel address of an already existing map. The virtual
- * address remains valid as long as the buffer object is pinned or reserved.
- * The cached map is torn down on either
- * 1) Buffer object move
- * 2) Buffer object swapout
- * 3) Buffer object destruction
- *
- */
-void *vmw_dma_buffer_map_and_cache(struct vmw_dma_buffer *vbo)
-{
-	struct ttm_buffer_object *bo = &vbo->base;
-	bool not_used;
-	void *virtual;
-	int ret;
-
-	virtual = ttm_kmap_obj_virtual(&vbo->map, &not_used);
-	if (virtual)
-		return virtual;
-
-	ret = ttm_bo_kmap(bo, 0, bo->num_pages, &vbo->map);
-	if (ret)
-		DRM_ERROR("Buffer object map failed: %d.\n", ret);
-
-	return ttm_kmap_obj_virtual(&vbo->map, &not_used);
-}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 09cc721160c4..bb6dbbe18835 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2016 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2016 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -137,6 +137,12 @@
 #define DRM_IOCTL_VMW_CREATE_EXTENDED_CONTEXT			\
 	DRM_IOWR(DRM_COMMAND_BASE + DRM_VMW_CREATE_EXTENDED_CONTEXT,	\
 		struct drm_vmw_context_arg)
+#define DRM_IOCTL_VMW_GB_SURFACE_CREATE_EXT				\
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VMW_GB_SURFACE_CREATE_EXT,	\
+		union drm_vmw_gb_surface_create_ext_arg)
+#define DRM_IOCTL_VMW_GB_SURFACE_REF_EXT				\
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VMW_GB_SURFACE_REF_EXT,		\
+		union drm_vmw_gb_surface_reference_ext_arg)
 
 /**
  * The core DRM version of this macro doesn't account for
@@ -153,9 +159,9 @@
 static const struct drm_ioctl_desc vmw_ioctls[] = {
 	VMW_IOCTL_DEF(VMW_GET_PARAM, vmw_getparam_ioctl,
 		      DRM_AUTH | DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_ALLOC_DMABUF, vmw_dmabuf_alloc_ioctl,
+	VMW_IOCTL_DEF(VMW_ALLOC_DMABUF, vmw_bo_alloc_ioctl,
 		      DRM_AUTH | DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_UNREF_DMABUF, vmw_dmabuf_unref_ioctl,
+	VMW_IOCTL_DEF(VMW_UNREF_DMABUF, vmw_bo_unref_ioctl,
 		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_CURSOR_BYPASS,
 		      vmw_kms_cursor_bypass_ioctl,
@@ -219,11 +225,17 @@ static const struct drm_ioctl_desc vmw_ioctls[] = {
 		      vmw_gb_surface_reference_ioctl,
 		      DRM_AUTH | DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_SYNCCPU,
-		      vmw_user_dmabuf_synccpu_ioctl,
+		      vmw_user_bo_synccpu_ioctl,
 		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_CREATE_EXTENDED_CONTEXT,
 		      vmw_extended_context_define_ioctl,
 		      DRM_AUTH | DRM_RENDER_ALLOW),
+	VMW_IOCTL_DEF(VMW_GB_SURFACE_CREATE_EXT,
+		      vmw_gb_surface_define_ext_ioctl,
+		      DRM_AUTH | DRM_RENDER_ALLOW),
+	VMW_IOCTL_DEF(VMW_GB_SURFACE_REF_EXT,
+		      vmw_gb_surface_reference_ext_ioctl,
+		      DRM_AUTH | DRM_RENDER_ALLOW),
 };
 
 static const struct pci_device_id vmw_pci_id_list[] = {
@@ -258,6 +270,15 @@ MODULE_PARM_DESC(assume_16bpp, "Assume 16-bpp when filtering modes");
 module_param_named(assume_16bpp, vmw_assume_16bpp, int, 0600);
 
 
+static void vmw_print_capabilities2(uint32_t capabilities2)
+{
+	DRM_INFO("Capabilities2:\n");
+	if (capabilities2 & SVGA_CAP2_GROW_OTABLE)
+		DRM_INFO("  Grow oTable.\n");
+	if (capabilities2 & SVGA_CAP2_INTRA_SURFACE_COPY)
+		DRM_INFO("  IntraSurface copy.\n");
+}
+
 static void vmw_print_capabilities(uint32_t capabilities)
 {
 	DRM_INFO("Capabilities:\n");
@@ -321,7 +342,7 @@ static void vmw_print_capabilities(uint32_t capabilities)
 static int vmw_dummy_query_bo_create(struct vmw_private *dev_priv)
 {
 	int ret;
-	struct vmw_dma_buffer *vbo;
+	struct vmw_buffer_object *vbo;
 	struct ttm_bo_kmap_obj map;
 	volatile SVGA3dQueryResult *result;
 	bool dummy;
@@ -335,9 +356,9 @@ static int vmw_dummy_query_bo_create(struct vmw_private *dev_priv)
 	if (!vbo)
 		return -ENOMEM;
 
-	ret = vmw_dmabuf_init(dev_priv, vbo, PAGE_SIZE,
-			      &vmw_sys_ne_placement, false,
-			      &vmw_dmabuf_bo_free);
+	ret = vmw_bo_init(dev_priv, vbo, PAGE_SIZE,
+			  &vmw_sys_ne_placement, false,
+			  &vmw_bo_bo_free);
 	if (unlikely(ret != 0))
 		return ret;
 
@@ -358,7 +379,7 @@ static int vmw_dummy_query_bo_create(struct vmw_private *dev_priv)
 
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Dummy query buffer map failed.\n");
-		vmw_dmabuf_unreference(&vbo);
+		vmw_bo_unreference(&vbo);
 	} else
 		dev_priv->dummy_query_bo = vbo;
 
@@ -460,7 +481,7 @@ static void vmw_release_device_early(struct vmw_private *dev_priv)
 
 	BUG_ON(dev_priv->pinned_bo != NULL);
 
-	vmw_dmabuf_unreference(&dev_priv->dummy_query_bo);
+	vmw_bo_unreference(&dev_priv->dummy_query_bo);
 	if (dev_priv->cman)
 		vmw_cmdbuf_remove_pool(dev_priv->cman);
 
@@ -644,6 +665,7 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	mutex_init(&dev_priv->cmdbuf_mutex);
 	mutex_init(&dev_priv->release_mutex);
 	mutex_init(&dev_priv->binding_mutex);
+	mutex_init(&dev_priv->requested_layout_mutex);
 	mutex_init(&dev_priv->global_kms_state_mutex);
 	rwlock_init(&dev_priv->resource_lock);
 	ttm_lock_init(&dev_priv->reservation_sem);
@@ -683,6 +705,12 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	}
 
 	dev_priv->capabilities = vmw_read(dev_priv, SVGA_REG_CAPABILITIES);
+
+	if (dev_priv->capabilities & SVGA_CAP_CAP2_REGISTER) {
+		dev_priv->capabilities2 = vmw_read(dev_priv, SVGA_REG_CAP2);
+	}
+
+
 	ret = vmw_dma_select_mode(dev_priv);
 	if (unlikely(ret != 0)) {
 		DRM_INFO("Restricting capabilities due to IOMMU setup.\n");
@@ -751,6 +779,8 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	}
 
 	vmw_print_capabilities(dev_priv->capabilities);
+	if (dev_priv->capabilities & SVGA_CAP_CAP2_REGISTER)
+		vmw_print_capabilities2(dev_priv->capabilities2);
 
 	ret = vmw_dma_masks(dev_priv);
 	if (unlikely(ret != 0))
@@ -883,7 +913,7 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 
 	if (dev_priv->has_mob) {
 		spin_lock(&dev_priv->cap_lock);
-		vmw_write(dev_priv, SVGA_REG_DEV_CAP, SVGA3D_DEVCAP_DX);
+		vmw_write(dev_priv, SVGA_REG_DEV_CAP, SVGA3D_DEVCAP_DXCONTEXT);
 		dev_priv->has_dx = !!vmw_read(dev_priv, SVGA_REG_DEV_CAP);
 		spin_unlock(&dev_priv->cap_lock);
 	}
@@ -898,9 +928,23 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	if (ret)
 		goto out_no_fifo;
 
+	if (dev_priv->has_dx) {
+		/*
+		 * SVGA_CAP2_DX2 (DefineGBSurface_v3) is needed for SM4_1
+		 * support
+		 */
+		if ((dev_priv->capabilities2 & SVGA_CAP2_DX2) != 0) {
+			vmw_write(dev_priv, SVGA_REG_DEV_CAP,
+					SVGA3D_DEVCAP_SM41);
+			dev_priv->has_sm4_1 = vmw_read(dev_priv,
+							SVGA_REG_DEV_CAP);
+		}
+	}
+
 	DRM_INFO("DX: %s\n", dev_priv->has_dx ? "yes." : "no.");
-	DRM_INFO("Atomic: %s\n",
-		 (dev->driver->driver_features & DRIVER_ATOMIC) ? "yes" : "no");
+	DRM_INFO("Atomic: %s\n", (dev->driver->driver_features & DRIVER_ATOMIC)
+		 ? "yes." : "no.");
+	DRM_INFO("SM4_1: %s\n", dev_priv->has_sm4_1 ? "yes." : "no.");
 
 	snprintf(host_log, sizeof(host_log), "vmwgfx: %s-%s",
 		VMWGFX_REPO, VMWGFX_GIT_VERSION);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 5fcbe1620d50..1abe21758b0d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -1,7 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -43,10 +43,10 @@
 #include <linux/sync_file.h>
 
 #define VMWGFX_DRIVER_NAME "vmwgfx"
-#define VMWGFX_DRIVER_DATE "20180322"
+#define VMWGFX_DRIVER_DATE "20180704"
 #define VMWGFX_DRIVER_MAJOR 2
-#define VMWGFX_DRIVER_MINOR 14
-#define VMWGFX_DRIVER_PATCHLEVEL 1
+#define VMWGFX_DRIVER_MINOR 15
+#define VMWGFX_DRIVER_PATCHLEVEL 0
 #define VMWGFX_FILE_PAGE_OFFSET 0x00100000
 #define VMWGFX_FIFO_STATIC_SIZE (1024*1024)
 #define VMWGFX_MAX_RELOCATIONS 2048
@@ -83,10 +83,10 @@
 struct vmw_fpriv {
 	struct drm_master *locked_master;
 	struct ttm_object_file *tfile;
-	bool gb_aware;
+	bool gb_aware; /* user-space is guest-backed aware */
 };
 
-struct vmw_dma_buffer {
+struct vmw_buffer_object {
 	struct ttm_buffer_object base;
 	struct list_head res_list;
 	s32 pin_count;
@@ -120,7 +120,7 @@ struct vmw_resource {
 	unsigned long backup_size;
 	bool res_dirty; /* Protected by backup buffer reserved */
 	bool backup_dirty; /* Protected by backup buffer reserved */
-	struct vmw_dma_buffer *backup;
+	struct vmw_buffer_object *backup;
 	unsigned long backup_offset;
 	unsigned long pin_count; /* Protected by resource reserved */
 	const struct vmw_res_func *func;
@@ -166,7 +166,7 @@ struct vmw_surface_offset;
 
 struct vmw_surface {
 	struct vmw_resource res;
-	uint32_t flags;
+	SVGA3dSurfaceAllFlags flags;
 	uint32_t format;
 	uint32_t mip_levels[DRM_VMW_MAX_SURFACE_FACES];
 	struct drm_vmw_size base_size;
@@ -180,6 +180,8 @@ struct vmw_surface {
 	SVGA3dTextureFilter autogen_filter;
 	uint32_t multisample_count;
 	struct list_head view_list;
+	SVGA3dMSPattern multisample_pattern;
+	SVGA3dMSQualityLevel quality_level;
 };
 
 struct vmw_marker_queue {
@@ -304,7 +306,7 @@ struct vmw_sw_context{
 	uint32_t cmd_bounce_size;
 	struct list_head resource_list;
 	struct list_head ctx_resource_list; /* For contexts and cotables */
-	struct vmw_dma_buffer *cur_query_bo;
+	struct vmw_buffer_object *cur_query_bo;
 	struct list_head res_relocations;
 	uint32_t *buf_start;
 	struct vmw_res_cache_entry res_cache[vmw_res_max];
@@ -315,7 +317,7 @@ struct vmw_sw_context{
 	bool staged_bindings_inuse;
 	struct list_head staged_cmd_res;
 	struct vmw_resource_val_node *dx_ctx_node;
-	struct vmw_dma_buffer *dx_query_mob;
+	struct vmw_buffer_object *dx_query_mob;
 	struct vmw_resource *dx_query_ctx;
 	struct vmw_cmdbuf_res_manager *man;
 };
@@ -386,6 +388,7 @@ struct vmw_private {
 	uint32_t initial_height;
 	u32 *mmio_virt;
 	uint32_t capabilities;
+	uint32_t capabilities2;
 	uint32_t max_gmr_ids;
 	uint32_t max_gmr_pages;
 	uint32_t max_mob_pages;
@@ -397,6 +400,7 @@ struct vmw_private {
 	spinlock_t cap_lock;
 	bool has_dx;
 	bool assume_16bpp;
+	bool has_sm4_1;
 
 	/*
 	 * VGA registers.
@@ -412,6 +416,15 @@ struct vmw_private {
 	uint32_t num_displays;
 
 	/*
+	 * Currently requested_layout_mutex is used to protect the gui
+	 * positionig state in display unit. With that use case currently this
+	 * mutex is only taken during layout ioctl and atomic check_modeset.
+	 * Other display unit state can be protected with this mutex but that
+	 * needs careful consideration.
+	 */
+	struct mutex requested_layout_mutex;
+
+	/*
 	 * Framebuffer info.
 	 */
 
@@ -513,8 +526,8 @@ struct vmw_private {
 	 * are protected by the cmdbuf mutex.
 	 */
 
-	struct vmw_dma_buffer *dummy_query_bo;
-	struct vmw_dma_buffer *pinned_bo;
+	struct vmw_buffer_object *dummy_query_bo;
+	struct vmw_buffer_object *pinned_bo;
 	uint32_t query_cid;
 	uint32_t query_cid_valid;
 	bool dummy_query_bo_pinned;
@@ -623,43 +636,13 @@ extern int vmw_user_lookup_handle(struct vmw_private *dev_priv,
 				  struct ttm_object_file *tfile,
 				  uint32_t handle,
 				  struct vmw_surface **out_surf,
-				  struct vmw_dma_buffer **out_buf);
+				  struct vmw_buffer_object **out_buf);
 extern int vmw_user_resource_lookup_handle(
 	struct vmw_private *dev_priv,
 	struct ttm_object_file *tfile,
 	uint32_t handle,
 	const struct vmw_user_resource_conv *converter,
 	struct vmw_resource **p_res);
-extern void vmw_dmabuf_bo_free(struct ttm_buffer_object *bo);
-extern int vmw_dmabuf_init(struct vmw_private *dev_priv,
-			   struct vmw_dma_buffer *vmw_bo,
-			   size_t size, struct ttm_placement *placement,
-			   bool interuptable,
-			   void (*bo_free) (struct ttm_buffer_object *bo));
-extern int vmw_user_dmabuf_verify_access(struct ttm_buffer_object *bo,
-				  struct ttm_object_file *tfile);
-extern int vmw_user_dmabuf_alloc(struct vmw_private *dev_priv,
-				 struct ttm_object_file *tfile,
-				 uint32_t size,
-				 bool shareable,
-				 uint32_t *handle,
-				 struct vmw_dma_buffer **p_dma_buf,
-				 struct ttm_base_object **p_base);
-extern int vmw_user_dmabuf_reference(struct ttm_object_file *tfile,
-				     struct vmw_dma_buffer *dma_buf,
-				     uint32_t *handle);
-extern int vmw_dmabuf_alloc_ioctl(struct drm_device *dev, void *data,
-				  struct drm_file *file_priv);
-extern int vmw_dmabuf_unref_ioctl(struct drm_device *dev, void *data,
-				  struct drm_file *file_priv);
-extern int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data,
-					 struct drm_file *file_priv);
-extern uint32_t vmw_dmabuf_validate_node(struct ttm_buffer_object *bo,
-					 uint32_t cur_validate_node);
-extern void vmw_dmabuf_validate_clear(struct ttm_buffer_object *bo);
-extern int vmw_user_dmabuf_lookup(struct ttm_object_file *tfile,
-				  uint32_t id, struct vmw_dma_buffer **out,
-				  struct ttm_base_object **base);
 extern int vmw_stream_claim_ioctl(struct drm_device *dev, void *data,
 				  struct drm_file *file_priv);
 extern int vmw_stream_unref_ioctl(struct drm_device *dev, void *data,
@@ -670,43 +653,70 @@ extern int vmw_user_stream_lookup(struct vmw_private *dev_priv,
 				  struct vmw_resource **out);
 extern void vmw_resource_unreserve(struct vmw_resource *res,
 				   bool switch_backup,
-				   struct vmw_dma_buffer *new_backup,
+				   struct vmw_buffer_object *new_backup,
 				   unsigned long new_backup_offset);
-extern void vmw_resource_move_notify(struct ttm_buffer_object *bo,
-				     struct ttm_mem_reg *mem);
 extern void vmw_query_move_notify(struct ttm_buffer_object *bo,
 				  struct ttm_mem_reg *mem);
-extern void vmw_resource_swap_notify(struct ttm_buffer_object *bo);
-extern int vmw_query_readback_all(struct vmw_dma_buffer *dx_query_mob);
-extern void vmw_fence_single_bo(struct ttm_buffer_object *bo,
-				struct vmw_fence_obj *fence);
+extern int vmw_query_readback_all(struct vmw_buffer_object *dx_query_mob);
 extern void vmw_resource_evict_all(struct vmw_private *dev_priv);
-
+extern void vmw_resource_unbind_list(struct vmw_buffer_object *vbo);
 
 /**
- * DMA buffer helper routines - vmwgfx_dmabuf.c
+ * Buffer object helper functions - vmwgfx_bo.c
  */
-extern int vmw_dmabuf_pin_in_placement(struct vmw_private *vmw_priv,
-				       struct vmw_dma_buffer *bo,
-				       struct ttm_placement *placement,
+extern int vmw_bo_pin_in_placement(struct vmw_private *vmw_priv,
+				   struct vmw_buffer_object *bo,
+				   struct ttm_placement *placement,
+				   bool interruptible);
+extern int vmw_bo_pin_in_vram(struct vmw_private *dev_priv,
+			      struct vmw_buffer_object *buf,
+			      bool interruptible);
+extern int vmw_bo_pin_in_vram_or_gmr(struct vmw_private *dev_priv,
+				     struct vmw_buffer_object *buf,
+				     bool interruptible);
+extern int vmw_bo_pin_in_start_of_vram(struct vmw_private *vmw_priv,
+				       struct vmw_buffer_object *bo,
 				       bool interruptible);
-extern int vmw_dmabuf_pin_in_vram(struct vmw_private *dev_priv,
-				  struct vmw_dma_buffer *buf,
-				  bool interruptible);
-extern int vmw_dmabuf_pin_in_vram_or_gmr(struct vmw_private *dev_priv,
-					 struct vmw_dma_buffer *buf,
-					 bool interruptible);
-extern int vmw_dmabuf_pin_in_start_of_vram(struct vmw_private *vmw_priv,
-					   struct vmw_dma_buffer *bo,
-					   bool interruptible);
-extern int vmw_dmabuf_unpin(struct vmw_private *vmw_priv,
-			    struct vmw_dma_buffer *bo,
-			    bool interruptible);
+extern int vmw_bo_unpin(struct vmw_private *vmw_priv,
+			struct vmw_buffer_object *bo,
+			bool interruptible);
 extern void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *buf,
 				 SVGAGuestPtr *ptr);
-extern void vmw_bo_pin_reserved(struct vmw_dma_buffer *bo, bool pin);
-extern void *vmw_dma_buffer_map_and_cache(struct vmw_dma_buffer *vbo);
-extern void vmw_dma_buffer_unmap(struct vmw_dma_buffer *vbo);
+extern void vmw_bo_pin_reserved(struct vmw_buffer_object *bo, bool pin);
+extern void vmw_bo_bo_free(struct ttm_buffer_object *bo);
+extern int vmw_bo_init(struct vmw_private *dev_priv,
+		       struct vmw_buffer_object *vmw_bo,
+		       size_t size, struct ttm_placement *placement,
+		       bool interuptable,
+		       void (*bo_free)(struct ttm_buffer_object *bo));
+extern int vmw_user_bo_verify_access(struct ttm_buffer_object *bo,
+				     struct ttm_object_file *tfile);
+extern int vmw_user_bo_alloc(struct vmw_private *dev_priv,
+			     struct ttm_object_file *tfile,
+			     uint32_t size,
+			     bool shareable,
+			     uint32_t *handle,
+			     struct vmw_buffer_object **p_dma_buf,
+			     struct ttm_base_object **p_base);
+extern int vmw_user_bo_reference(struct ttm_object_file *tfile,
+				 struct vmw_buffer_object *dma_buf,
+				 uint32_t *handle);
+extern int vmw_bo_alloc_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv);
+extern int vmw_bo_unref_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv);
+extern int vmw_user_bo_synccpu_ioctl(struct drm_device *dev, void *data,
+				     struct drm_file *file_priv);
+extern int vmw_user_bo_lookup(struct ttm_object_file *tfile,
+			      uint32_t id, struct vmw_buffer_object **out,
+			      struct ttm_base_object **base);
+extern void vmw_bo_fence_single(struct ttm_buffer_object *bo,
+				struct vmw_fence_obj *fence);
+extern void *vmw_bo_map_and_cache(struct vmw_buffer_object *vbo);
+extern void vmw_bo_unmap(struct vmw_buffer_object *vbo);
+extern void vmw_bo_move_notify(struct ttm_buffer_object *bo,
+			       struct ttm_mem_reg *mem);
+extern void vmw_bo_swap_notify(struct ttm_buffer_object *bo);
 
 /**
  * Misc Ioctl functionality - vmwgfx_ioctl.c
@@ -758,7 +768,7 @@ extern void vmw_ttm_global_release(struct vmw_private *dev_priv);
 extern int vmw_mmap(struct file *filp, struct vm_area_struct *vma);
 
 /**
- * TTM buffer object driver - vmwgfx_buffer.c
+ * TTM buffer object driver - vmwgfx_ttm_buffer.c
  */
 
 extern const size_t vmw_tt_size;
@@ -1041,8 +1051,8 @@ vmw_context_binding_state(struct vmw_resource *ctx);
 extern void vmw_dx_context_scrub_cotables(struct vmw_resource *ctx,
 					  bool readback);
 extern int vmw_context_bind_dx_query(struct vmw_resource *ctx_res,
-				     struct vmw_dma_buffer *mob);
-extern struct vmw_dma_buffer *
+				     struct vmw_buffer_object *mob);
+extern struct vmw_buffer_object *
 vmw_context_get_dx_query_mob(struct vmw_resource *ctx_res);
 
 
@@ -1070,14 +1080,22 @@ extern int vmw_surface_validate(struct vmw_private *dev_priv,
 				struct vmw_surface *srf);
 int vmw_surface_gb_priv_define(struct drm_device *dev,
 			       uint32_t user_accounting_size,
-			       uint32_t svga3d_flags,
+			       SVGA3dSurfaceAllFlags svga3d_flags,
 			       SVGA3dSurfaceFormat format,
 			       bool for_scanout,
 			       uint32_t num_mip_levels,
 			       uint32_t multisample_count,
 			       uint32_t array_size,
 			       struct drm_vmw_size size,
+			       SVGA3dMSPattern multisample_pattern,
+			       SVGA3dMSQualityLevel quality_level,
 			       struct vmw_surface **srf_out);
+extern int vmw_gb_surface_define_ext_ioctl(struct drm_device *dev,
+					   void *data,
+					   struct drm_file *file_priv);
+extern int vmw_gb_surface_reference_ext_ioctl(struct drm_device *dev,
+					      void *data,
+					      struct drm_file *file_priv);
 
 /*
  * Shader management - vmwgfx_shader.c
@@ -1224,6 +1242,11 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst,
 		    u32 w, u32 h,
 		    struct vmw_diff_cpy *diff);
 
+/* Host messaging -vmwgfx_msg.c: */
+int vmw_host_get_guestinfo(const char *guest_info_param,
+			   char *buffer, size_t *length);
+int vmw_host_log(const char *log);
+
 /**
  * Inline helper functions
  */
@@ -1243,9 +1266,9 @@ static inline struct vmw_surface *vmw_surface_reference(struct vmw_surface *srf)
 	return srf;
 }
 
-static inline void vmw_dmabuf_unreference(struct vmw_dma_buffer **buf)
+static inline void vmw_bo_unreference(struct vmw_buffer_object **buf)
 {
-	struct vmw_dma_buffer *tmp_buf = *buf;
+	struct vmw_buffer_object *tmp_buf = *buf;
 
 	*buf = NULL;
 	if (tmp_buf != NULL) {
@@ -1255,7 +1278,8 @@ static inline void vmw_dmabuf_unreference(struct vmw_dma_buffer **buf)
 	}
 }
 
-static inline struct vmw_dma_buffer *vmw_dmabuf_reference(struct vmw_dma_buffer *buf)
+static inline struct vmw_buffer_object *
+vmw_bo_reference(struct vmw_buffer_object *buf)
 {
 	if (ttm_bo_reference(&buf->base))
 		return buf;
@@ -1302,10 +1326,4 @@ static inline void vmw_mmio_write(u32 value, u32 *addr)
 {
 	WRITE_ONCE(*addr, value);
 }
-
-/**
- * Add vmw_msg module function
- */
-extern int vmw_host_log(const char *log);
-
 #endif
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index c9d5cc237124..1f134570b759 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009 - 2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009 - 2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -92,7 +92,7 @@ struct vmw_resource_val_node {
 	struct list_head head;
 	struct drm_hash_item hash;
 	struct vmw_resource *res;
-	struct vmw_dma_buffer *new_backup;
+	struct vmw_buffer_object *new_backup;
 	struct vmw_ctx_binding_state *staged_bindings;
 	unsigned long new_backup_offset;
 	u32 first_usage : 1;
@@ -126,9 +126,9 @@ static int vmw_resource_context_res_add(struct vmw_private *dev_priv,
 static int vmw_translate_mob_ptr(struct vmw_private *dev_priv,
 				 struct vmw_sw_context *sw_context,
 				 SVGAMobId *id,
-				 struct vmw_dma_buffer **vmw_bo_p);
+				 struct vmw_buffer_object **vmw_bo_p);
 static int vmw_bo_to_validate_list(struct vmw_sw_context *sw_context,
-				   struct vmw_dma_buffer *vbo,
+				   struct vmw_buffer_object *vbo,
 				   bool validate_as_mob,
 				   uint32_t *p_val_node);
 /**
@@ -185,7 +185,7 @@ static void vmw_resources_unreserve(struct vmw_sw_context *sw_context,
 		}
 		vmw_resource_unreserve(res, switch_backup, val->new_backup,
 				       val->new_backup_offset);
-		vmw_dmabuf_unreference(&val->new_backup);
+		vmw_bo_unreference(&val->new_backup);
 	}
 }
 
@@ -423,7 +423,7 @@ static int vmw_resource_context_res_add(struct vmw_private *dev_priv,
 	}
 
 	if (dev_priv->has_dx && vmw_res_type(ctx) == vmw_res_dx_context) {
-		struct vmw_dma_buffer *dx_query_mob;
+		struct vmw_buffer_object *dx_query_mob;
 
 		dx_query_mob = vmw_context_get_dx_query_mob(ctx);
 		if (dx_query_mob)
@@ -544,7 +544,7 @@ static int vmw_cmd_ok(struct vmw_private *dev_priv,
  * submission is reached.
  */
 static int vmw_bo_to_validate_list(struct vmw_sw_context *sw_context,
-				   struct vmw_dma_buffer *vbo,
+				   struct vmw_buffer_object *vbo,
 				   bool validate_as_mob,
 				   uint32_t *p_val_node)
 {
@@ -616,7 +616,7 @@ static int vmw_resources_reserve(struct vmw_sw_context *sw_context)
 			return ret;
 
 		if (res->backup) {
-			struct vmw_dma_buffer *vbo = res->backup;
+			struct vmw_buffer_object *vbo = res->backup;
 
 			ret = vmw_bo_to_validate_list
 				(sw_context, vbo,
@@ -628,7 +628,7 @@ static int vmw_resources_reserve(struct vmw_sw_context *sw_context)
 	}
 
 	if (sw_context->dx_query_mob) {
-		struct vmw_dma_buffer *expected_dx_query_mob;
+		struct vmw_buffer_object *expected_dx_query_mob;
 
 		expected_dx_query_mob =
 			vmw_context_get_dx_query_mob(sw_context->dx_query_ctx);
@@ -657,7 +657,7 @@ static int vmw_resources_validate(struct vmw_sw_context *sw_context)
 
 	list_for_each_entry(val, &sw_context->resource_list, head) {
 		struct vmw_resource *res = val->res;
-		struct vmw_dma_buffer *backup = res->backup;
+		struct vmw_buffer_object *backup = res->backup;
 
 		ret = vmw_resource_validate(res);
 		if (unlikely(ret != 0)) {
@@ -668,7 +668,7 @@ static int vmw_resources_validate(struct vmw_sw_context *sw_context)
 
 		/* Check if the resource switched backup buffer */
 		if (backup && res->backup && (backup != res->backup)) {
-			struct vmw_dma_buffer *vbo = res->backup;
+			struct vmw_buffer_object *vbo = res->backup;
 
 			ret = vmw_bo_to_validate_list
 				(sw_context, vbo,
@@ -821,7 +821,7 @@ out_no_reloc:
 static int vmw_rebind_all_dx_query(struct vmw_resource *ctx_res)
 {
 	struct vmw_private *dev_priv = ctx_res->dev_priv;
-	struct vmw_dma_buffer *dx_query_mob;
+	struct vmw_buffer_object *dx_query_mob;
 	struct {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdDXBindAllQuery body;
@@ -1152,7 +1152,7 @@ static int vmw_cmd_present_check(struct vmw_private *dev_priv,
  * command batch.
  */
 static int vmw_query_bo_switch_prepare(struct vmw_private *dev_priv,
-				       struct vmw_dma_buffer *new_query_bo,
+				       struct vmw_buffer_object *new_query_bo,
 				       struct vmw_sw_context *sw_context)
 {
 	struct vmw_res_cache_entry *ctx_entry =
@@ -1234,7 +1234,7 @@ static void vmw_query_bo_switch_commit(struct vmw_private *dev_priv,
 	if (dev_priv->pinned_bo != sw_context->cur_query_bo) {
 		if (dev_priv->pinned_bo) {
 			vmw_bo_pin_reserved(dev_priv->pinned_bo, false);
-			vmw_dmabuf_unreference(&dev_priv->pinned_bo);
+			vmw_bo_unreference(&dev_priv->pinned_bo);
 		}
 
 		if (!sw_context->needs_post_query_barrier) {
@@ -1256,7 +1256,7 @@ static void vmw_query_bo_switch_commit(struct vmw_private *dev_priv,
 			dev_priv->query_cid = sw_context->last_query_ctx->id;
 			dev_priv->query_cid_valid = true;
 			dev_priv->pinned_bo =
-				vmw_dmabuf_reference(sw_context->cur_query_bo);
+				vmw_bo_reference(sw_context->cur_query_bo);
 		}
 	}
 }
@@ -1282,15 +1282,14 @@ static void vmw_query_bo_switch_commit(struct vmw_private *dev_priv,
 static int vmw_translate_mob_ptr(struct vmw_private *dev_priv,
 				 struct vmw_sw_context *sw_context,
 				 SVGAMobId *id,
-				 struct vmw_dma_buffer **vmw_bo_p)
+				 struct vmw_buffer_object **vmw_bo_p)
 {
-	struct vmw_dma_buffer *vmw_bo = NULL;
+	struct vmw_buffer_object *vmw_bo = NULL;
 	uint32_t handle = *id;
 	struct vmw_relocation *reloc;
 	int ret;
 
-	ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo,
-				     NULL);
+	ret = vmw_user_bo_lookup(sw_context->fp->tfile, handle, &vmw_bo, NULL);
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Could not find or use MOB buffer.\n");
 		ret = -EINVAL;
@@ -1316,7 +1315,7 @@ static int vmw_translate_mob_ptr(struct vmw_private *dev_priv,
 	return 0;
 
 out_no_reloc:
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	*vmw_bo_p = NULL;
 	return ret;
 }
@@ -1343,15 +1342,14 @@ out_no_reloc:
 static int vmw_translate_guest_ptr(struct vmw_private *dev_priv,
 				   struct vmw_sw_context *sw_context,
 				   SVGAGuestPtr *ptr,
-				   struct vmw_dma_buffer **vmw_bo_p)
+				   struct vmw_buffer_object **vmw_bo_p)
 {
-	struct vmw_dma_buffer *vmw_bo = NULL;
+	struct vmw_buffer_object *vmw_bo = NULL;
 	uint32_t handle = ptr->gmrId;
 	struct vmw_relocation *reloc;
 	int ret;
 
-	ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo,
-				     NULL);
+	ret = vmw_user_bo_lookup(sw_context->fp->tfile, handle, &vmw_bo, NULL);
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Could not find or use GMR region.\n");
 		ret = -EINVAL;
@@ -1376,7 +1374,7 @@ static int vmw_translate_guest_ptr(struct vmw_private *dev_priv,
 	return 0;
 
 out_no_reloc:
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	*vmw_bo_p = NULL;
 	return ret;
 }
@@ -1447,7 +1445,7 @@ static int vmw_cmd_dx_bind_query(struct vmw_private *dev_priv,
 		SVGA3dCmdDXBindQuery q;
 	} *cmd;
 
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	int    ret;
 
 
@@ -1466,7 +1464,7 @@ static int vmw_cmd_dx_bind_query(struct vmw_private *dev_priv,
 	sw_context->dx_query_mob = vmw_bo;
 	sw_context->dx_query_ctx = sw_context->dx_ctx_node->res;
 
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 
 	return ret;
 }
@@ -1549,7 +1547,7 @@ static int vmw_cmd_end_gb_query(struct vmw_private *dev_priv,
 				struct vmw_sw_context *sw_context,
 				SVGA3dCmdHeader *header)
 {
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	struct vmw_query_cmd {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdEndGBQuery q;
@@ -1569,7 +1567,7 @@ static int vmw_cmd_end_gb_query(struct vmw_private *dev_priv,
 
 	ret = vmw_query_bo_switch_prepare(dev_priv, vmw_bo, sw_context);
 
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	return ret;
 }
 
@@ -1584,7 +1582,7 @@ static int vmw_cmd_end_query(struct vmw_private *dev_priv,
 			     struct vmw_sw_context *sw_context,
 			     SVGA3dCmdHeader *header)
 {
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	struct vmw_query_cmd {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdEndQuery q;
@@ -1623,7 +1621,7 @@ static int vmw_cmd_end_query(struct vmw_private *dev_priv,
 
 	ret = vmw_query_bo_switch_prepare(dev_priv, vmw_bo, sw_context);
 
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	return ret;
 }
 
@@ -1638,7 +1636,7 @@ static int vmw_cmd_wait_gb_query(struct vmw_private *dev_priv,
 				 struct vmw_sw_context *sw_context,
 				 SVGA3dCmdHeader *header)
 {
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	struct vmw_query_cmd {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdWaitForGBQuery q;
@@ -1656,7 +1654,7 @@ static int vmw_cmd_wait_gb_query(struct vmw_private *dev_priv,
 	if (unlikely(ret != 0))
 		return ret;
 
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	return 0;
 }
 
@@ -1671,7 +1669,7 @@ static int vmw_cmd_wait_query(struct vmw_private *dev_priv,
 			      struct vmw_sw_context *sw_context,
 			      SVGA3dCmdHeader *header)
 {
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	struct vmw_query_cmd {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdWaitForQuery q;
@@ -1708,7 +1706,7 @@ static int vmw_cmd_wait_query(struct vmw_private *dev_priv,
 	if (unlikely(ret != 0))
 		return ret;
 
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	return 0;
 }
 
@@ -1716,7 +1714,7 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv,
 		       struct vmw_sw_context *sw_context,
 		       SVGA3dCmdHeader *header)
 {
-	struct vmw_dma_buffer *vmw_bo = NULL;
+	struct vmw_buffer_object *vmw_bo = NULL;
 	struct vmw_surface *srf = NULL;
 	struct vmw_dma_cmd {
 		SVGA3dCmdHeader header;
@@ -1768,7 +1766,7 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv,
 			     header);
 
 out_no_surface:
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	return ret;
 }
 
@@ -1887,7 +1885,7 @@ static int vmw_cmd_check_define_gmrfb(struct vmw_private *dev_priv,
 				      struct vmw_sw_context *sw_context,
 				      void *buf)
 {
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	int ret;
 
 	struct {
@@ -1901,7 +1899,7 @@ static int vmw_cmd_check_define_gmrfb(struct vmw_private *dev_priv,
 	if (unlikely(ret != 0))
 		return ret;
 
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 
 	return ret;
 }
@@ -1928,7 +1926,7 @@ static int vmw_cmd_res_switch_backup(struct vmw_private *dev_priv,
 				     uint32_t *buf_id,
 				     unsigned long backup_offset)
 {
-	struct vmw_dma_buffer *dma_buf;
+	struct vmw_buffer_object *dma_buf;
 	int ret;
 
 	ret = vmw_translate_mob_ptr(dev_priv, sw_context, buf_id, &dma_buf);
@@ -1939,7 +1937,7 @@ static int vmw_cmd_res_switch_backup(struct vmw_private *dev_priv,
 	if (val_node->first_usage)
 		val_node->no_buffer_needed = true;
 
-	vmw_dmabuf_unreference(&val_node->new_backup);
+	vmw_bo_unreference(&val_node->new_backup);
 	val_node->new_backup = dma_buf;
 	val_node->new_backup_offset = backup_offset;
 
@@ -3118,6 +3116,32 @@ static int vmw_cmd_dx_transfer_from_buffer(struct vmw_private *dev_priv,
 				 &cmd->body.destSid, NULL);
 }
 
+/**
+ * vmw_cmd_intra_surface_copy -
+ * Validate an SVGA_3D_CMD_INTRA_SURFACE_COPY command
+ *
+ * @dev_priv: Pointer to a device private struct.
+ * @sw_context: The software context being used for this batch.
+ * @header: Pointer to the command header in the command stream.
+ */
+static int vmw_cmd_intra_surface_copy(struct vmw_private *dev_priv,
+					   struct vmw_sw_context *sw_context,
+					   SVGA3dCmdHeader *header)
+{
+	struct {
+		SVGA3dCmdHeader header;
+		SVGA3dCmdIntraSurfaceCopy body;
+	} *cmd = container_of(header, typeof(*cmd), header);
+
+	if (!(dev_priv->capabilities2 & SVGA_CAP2_INTRA_SURFACE_COPY))
+		return -EINVAL;
+
+	return vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface,
+				user_surface_converter,
+				&cmd->body.surface.sid, NULL);
+}
+
+
 static int vmw_cmd_check_not_3d(struct vmw_private *dev_priv,
 				struct vmw_sw_context *sw_context,
 				void *buf, uint32_t *size)
@@ -3232,9 +3256,9 @@ static const struct vmw_cmd_entry vmw_cmd_entries[SVGA_3D_CMD_MAX] = {
 		    false, false, false),
 	VMW_CMD_DEF(SVGA_3D_CMD_SCREEN_DMA, &vmw_cmd_invalid,
 		    false, false, false),
-	VMW_CMD_DEF(SVGA_3D_CMD_SET_UNITY_SURFACE_COOKIE, &vmw_cmd_invalid,
+	VMW_CMD_DEF(SVGA_3D_CMD_DEAD1, &vmw_cmd_invalid,
 		    false, false, false),
-	VMW_CMD_DEF(SVGA_3D_CMD_OPEN_CONTEXT_SURFACE, &vmw_cmd_invalid,
+	VMW_CMD_DEF(SVGA_3D_CMD_DEAD2, &vmw_cmd_invalid,
 		    false, false, false),
 	VMW_CMD_DEF(SVGA_3D_CMD_LOGICOPS_BITBLT, &vmw_cmd_invalid,
 		    false, false, false),
@@ -3473,6 +3497,8 @@ static const struct vmw_cmd_entry vmw_cmd_entries[SVGA_3D_CMD_MAX] = {
 	VMW_CMD_DEF(SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER,
 		    &vmw_cmd_dx_transfer_from_buffer,
 		    true, false, true),
+	VMW_CMD_DEF(SVGA_3D_CMD_INTRA_SURFACE_COPY, &vmw_cmd_intra_surface_copy,
+		    true, false, true),
 };
 
 bool vmw_cmd_describe(const void *buf, u32 *size, char const **cmd)
@@ -3701,8 +3727,8 @@ int vmw_validate_single_buffer(struct vmw_private *dev_priv,
 			       bool interruptible,
 			       bool validate_as_mob)
 {
-	struct vmw_dma_buffer *vbo = container_of(bo, struct vmw_dma_buffer,
-						  base);
+	struct vmw_buffer_object *vbo =
+		container_of(bo, struct vmw_buffer_object, base);
 	struct ttm_operation_ctx ctx = { interruptible, true };
 	int ret;
 
@@ -4423,7 +4449,7 @@ void __vmw_execbuf_release_pinned_bo(struct vmw_private *dev_priv,
 
 	ttm_bo_unref(&query_val.bo);
 	ttm_bo_unref(&pinned_val.bo);
-	vmw_dmabuf_unreference(&dev_priv->pinned_bo);
+	vmw_bo_unreference(&dev_priv->pinned_bo);
 out_unlock:
 	return;
 
@@ -4432,7 +4458,7 @@ out_no_emit:
 out_no_reserve:
 	ttm_bo_unref(&query_val.bo);
 	ttm_bo_unref(&pinned_val.bo);
-	vmw_dmabuf_unreference(&dev_priv->pinned_bo);
+	vmw_bo_unreference(&dev_priv->pinned_bo);
 }
 
 /**
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index 54e300365a5c..b913a56f3426 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -42,7 +42,7 @@ struct vmw_fb_par {
 	void *vmalloc;
 
 	struct mutex bo_mutex;
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	unsigned bo_size;
 	struct drm_framebuffer *set_fb;
 	struct drm_display_mode *set_mode;
@@ -184,7 +184,7 @@ static void vmw_fb_dirty_flush(struct work_struct *work)
 	struct drm_clip_rect clip;
 	struct drm_framebuffer *cur_fb;
 	u8 *src_ptr, *dst_ptr;
-	struct vmw_dma_buffer *vbo = par->vmw_bo;
+	struct vmw_buffer_object *vbo = par->vmw_bo;
 	void *virtual;
 
 	if (!READ_ONCE(par->dirty.active))
@@ -197,7 +197,7 @@ static void vmw_fb_dirty_flush(struct work_struct *work)
 
 	(void) ttm_read_lock(&vmw_priv->reservation_sem, false);
 	(void) ttm_bo_reserve(&vbo->base, false, false, NULL);
-	virtual = vmw_dma_buffer_map_and_cache(vbo);
+	virtual = vmw_bo_map_and_cache(vbo);
 	if (!virtual)
 		goto out_unreserve;
 
@@ -391,9 +391,9 @@ static void vmw_fb_imageblit(struct fb_info *info, const struct fb_image *image)
  */
 
 static int vmw_fb_create_bo(struct vmw_private *vmw_priv,
-			    size_t size, struct vmw_dma_buffer **out)
+			    size_t size, struct vmw_buffer_object **out)
 {
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	int ret;
 
 	(void) ttm_write_lock(&vmw_priv->reservation_sem, false);
@@ -404,10 +404,10 @@ static int vmw_fb_create_bo(struct vmw_private *vmw_priv,
 		goto err_unlock;
 	}
 
-	ret = vmw_dmabuf_init(vmw_priv, vmw_bo, size,
+	ret = vmw_bo_init(vmw_priv, vmw_bo, size,
 			      &vmw_sys_placement,
 			      false,
-			      &vmw_dmabuf_bo_free);
+			      &vmw_bo_bo_free);
 	if (unlikely(ret != 0))
 		goto err_unlock; /* init frees the buffer on failure */
 
@@ -439,38 +439,13 @@ static int vmw_fb_compute_depth(struct fb_var_screeninfo *var,
 static int vmwgfx_set_config_internal(struct drm_mode_set *set)
 {
 	struct drm_crtc *crtc = set->crtc;
-	struct drm_framebuffer *fb;
-	struct drm_crtc *tmp;
-	struct drm_device *dev = set->crtc->dev;
 	struct drm_modeset_acquire_ctx ctx;
 	int ret;
 
 	drm_modeset_acquire_init(&ctx, 0);
 
 restart:
-	/*
-	 * NOTE: ->set_config can also disable other crtcs (if we steal all
-	 * connectors from it), hence we need to refcount the fbs across all
-	 * crtcs. Atomic modeset will have saner semantics ...
-	 */
-	drm_for_each_crtc(tmp, dev)
-		tmp->primary->old_fb = tmp->primary->fb;
-
-	fb = set->fb;
-
 	ret = crtc->funcs->set_config(set, &ctx);
-	if (ret == 0) {
-		crtc->primary->crtc = crtc;
-		crtc->primary->fb = fb;
-	}
-
-	drm_for_each_crtc(tmp, dev) {
-		if (tmp->primary->fb)
-			drm_framebuffer_get(tmp->primary->fb);
-		if (tmp->primary->old_fb)
-			drm_framebuffer_put(tmp->primary->old_fb);
-		tmp->primary->old_fb = NULL;
-	}
 
 	if (ret == -EDEADLK) {
 		drm_modeset_backoff(&ctx);
@@ -516,7 +491,7 @@ static int vmw_fb_kms_detach(struct vmw_fb_par *par,
 	}
 
 	if (par->vmw_bo && detach_bo && unref_bo)
-		vmw_dmabuf_unreference(&par->vmw_bo);
+		vmw_bo_unreference(&par->vmw_bo);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
index 9ed544f8958f..3d546d409334 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2011-2014 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2011-2014 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -175,7 +175,6 @@ static long vmw_fence_wait(struct dma_fence *f, bool intr, signed long timeout)
 	struct vmw_private *dev_priv = fman->dev_priv;
 	struct vmwgfx_wait_cb cb;
 	long ret = timeout;
-	unsigned long irq_flags;
 
 	if (likely(vmw_fence_obj_signaled(fence)))
 		return timeout;
@@ -183,7 +182,7 @@ static long vmw_fence_wait(struct dma_fence *f, bool intr, signed long timeout)
 	vmw_fifo_ping_host(dev_priv, SVGA_SYNC_GENERIC);
 	vmw_seqno_waiter_add(dev_priv);
 
-	spin_lock_irqsave(f->lock, irq_flags);
+	spin_lock(f->lock);
 
 	if (intr && signal_pending(current)) {
 		ret = -ERESTARTSYS;
@@ -194,30 +193,45 @@ static long vmw_fence_wait(struct dma_fence *f, bool intr, signed long timeout)
 	cb.task = current;
 	list_add(&cb.base.node, &f->cb_list);
 
-	while (ret > 0) {
+	for (;;) {
 		__vmw_fences_update(fman);
-		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &f->flags))
-			break;
 
+		/*
+		 * We can use the barrier free __set_current_state() since
+		 * DMA_FENCE_FLAG_SIGNALED_BIT + wakeup is protected by the
+		 * fence spinlock.
+		 */
 		if (intr)
 			__set_current_state(TASK_INTERRUPTIBLE);
 		else
 			__set_current_state(TASK_UNINTERRUPTIBLE);
-		spin_unlock_irqrestore(f->lock, irq_flags);
 
-		ret = schedule_timeout(ret);
+		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &f->flags)) {
+			if (ret == 0 && timeout > 0)
+				ret = 1;
+			break;
+		}
 
-		spin_lock_irqsave(f->lock, irq_flags);
-		if (ret > 0 && intr && signal_pending(current))
+		if (intr && signal_pending(current)) {
 			ret = -ERESTARTSYS;
-	}
+			break;
+		}
 
+		if (ret == 0)
+			break;
+
+		spin_unlock(f->lock);
+
+		ret = schedule_timeout(ret);
+
+		spin_lock(f->lock);
+	}
+	__set_current_state(TASK_RUNNING);
 	if (!list_empty(&cb.base.node))
 		list_del(&cb.base.node);
-	__set_current_state(TASK_RUNNING);
 
 out:
-	spin_unlock_irqrestore(f->lock, irq_flags);
+	spin_unlock(f->lock);
 
 	vmw_seqno_waiter_remove(dev_priv);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.h b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.h
index 20224dba9d8e..c9382933c2b9 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.h
@@ -1,7 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
- * Copyright © 2011-2012 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2011-2012 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
index a1c68e6a689e..d0fd147ef75f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c
index 66ffa1d4759c..007a0cc7f232 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
index f2f9d88131f2..ddb1e9365a3e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright (c) 2007-2010 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2007-2010 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
index c5e8eae0dbe2..172a6ba6539c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -56,6 +56,9 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data,
 	case DRM_VMW_PARAM_HW_CAPS:
 		param->value = dev_priv->capabilities;
 		break;
+	case DRM_VMW_PARAM_HW_CAPS2:
+		param->value = dev_priv->capabilities2;
+		break;
 	case DRM_VMW_PARAM_FIFO_CAPS:
 		param->value = dev_priv->fifo.capabilities;
 		break;
@@ -113,6 +116,9 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data,
 	case DRM_VMW_PARAM_DX:
 		param->value = dev_priv->has_dx;
 		break;
+	case DRM_VMW_PARAM_SM4_1:
+		param->value = dev_priv->has_sm4_1;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -122,15 +128,12 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data,
 
 static u32 vmw_mask_multisample(unsigned int cap, u32 fmt_value)
 {
-	/* If the header is updated, update the format test as well! */
-	BUILD_BUG_ON(SVGA3D_DEVCAP_DXFMT_BC5_UNORM + 1 != SVGA3D_DEVCAP_MAX);
-
-	if (cap >= SVGA3D_DEVCAP_DXFMT_X8R8G8B8 &&
-	    cap <= SVGA3D_DEVCAP_DXFMT_BC5_UNORM)
-		fmt_value &= ~(SVGADX_DXFMT_MULTISAMPLE_2 |
-			       SVGADX_DXFMT_MULTISAMPLE_4 |
-			       SVGADX_DXFMT_MULTISAMPLE_8);
-	else if (cap == SVGA3D_DEVCAP_MULTISAMPLE_MASKABLESAMPLES)
+	/*
+	 * A version of user-space exists which use MULTISAMPLE_MASKABLESAMPLES
+	 * to check the sample count supported by virtual device. Since there
+	 * never was support for multisample count for backing MOB return 0.
+	 */
+	if (cap == SVGA3D_DEVCAP_MULTISAMPLE_MASKABLESAMPLES)
 		return 0;
 
 	return fmt_value;
@@ -377,8 +380,8 @@ int vmw_present_readback_ioctl(struct drm_device *dev, void *data,
 	}
 
 	vfb = vmw_framebuffer_to_vfb(fb);
-	if (!vfb->dmabuf) {
-		DRM_ERROR("Framebuffer not dmabuf backed.\n");
+	if (!vfb->bo) {
+		DRM_ERROR("Framebuffer not buffer backed.\n");
 		ret = -EINVAL;
 		goto out_no_ttm_lock;
 	}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c
index b9239ba067c4..c3ad4478266b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 01f2dc9e6f52..23beff5d8e3c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -85,10 +85,10 @@ static int vmw_cursor_update_image(struct vmw_private *dev_priv,
 	return 0;
 }
 
-static int vmw_cursor_update_dmabuf(struct vmw_private *dev_priv,
-				    struct vmw_dma_buffer *dmabuf,
-				    u32 width, u32 height,
-				    u32 hotspotX, u32 hotspotY)
+static int vmw_cursor_update_bo(struct vmw_private *dev_priv,
+				struct vmw_buffer_object *bo,
+				u32 width, u32 height,
+				u32 hotspotX, u32 hotspotY)
 {
 	struct ttm_bo_kmap_obj map;
 	unsigned long kmap_offset;
@@ -100,13 +100,13 @@ static int vmw_cursor_update_dmabuf(struct vmw_private *dev_priv,
 	kmap_offset = 0;
 	kmap_num = (width*height*4 + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
-	ret = ttm_bo_reserve(&dmabuf->base, true, false, NULL);
+	ret = ttm_bo_reserve(&bo->base, true, false, NULL);
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("reserve failed\n");
 		return -EINVAL;
 	}
 
-	ret = ttm_bo_kmap(&dmabuf->base, kmap_offset, kmap_num, &map);
+	ret = ttm_bo_kmap(&bo->base, kmap_offset, kmap_num, &map);
 	if (unlikely(ret != 0))
 		goto err_unreserve;
 
@@ -116,7 +116,7 @@ static int vmw_cursor_update_dmabuf(struct vmw_private *dev_priv,
 
 	ttm_bo_kunmap(&map);
 err_unreserve:
-	ttm_bo_unreserve(&dmabuf->base);
+	ttm_bo_unreserve(&bo->base);
 
 	return ret;
 }
@@ -352,13 +352,13 @@ vmw_du_cursor_plane_prepare_fb(struct drm_plane *plane,
 	if (vps->surf)
 		vmw_surface_unreference(&vps->surf);
 
-	if (vps->dmabuf)
-		vmw_dmabuf_unreference(&vps->dmabuf);
+	if (vps->bo)
+		vmw_bo_unreference(&vps->bo);
 
 	if (fb) {
-		if (vmw_framebuffer_to_vfb(fb)->dmabuf) {
-			vps->dmabuf = vmw_framebuffer_to_vfbd(fb)->buffer;
-			vmw_dmabuf_reference(vps->dmabuf);
+		if (vmw_framebuffer_to_vfb(fb)->bo) {
+			vps->bo = vmw_framebuffer_to_vfbd(fb)->buffer;
+			vmw_bo_reference(vps->bo);
 		} else {
 			vps->surf = vmw_framebuffer_to_vfbs(fb)->surface;
 			vmw_surface_reference(vps->surf);
@@ -390,7 +390,7 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
 	}
 
 	du->cursor_surface = vps->surf;
-	du->cursor_dmabuf = vps->dmabuf;
+	du->cursor_bo = vps->bo;
 
 	if (vps->surf) {
 		du->cursor_age = du->cursor_surface->snooper.age;
@@ -399,11 +399,11 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
 					      vps->surf->snooper.image,
 					      64, 64, hotspot_x,
 					      hotspot_y);
-	} else if (vps->dmabuf) {
-		ret = vmw_cursor_update_dmabuf(dev_priv, vps->dmabuf,
-					       plane->state->crtc_w,
-					       plane->state->crtc_h,
-					       hotspot_x, hotspot_y);
+	} else if (vps->bo) {
+		ret = vmw_cursor_update_bo(dev_priv, vps->bo,
+					   plane->state->crtc_w,
+					   plane->state->crtc_h,
+					   hotspot_x, hotspot_y);
 	} else {
 		vmw_cursor_update_position(dev_priv, false, 0, 0);
 		return;
@@ -519,7 +519,7 @@ int vmw_du_cursor_plane_atomic_check(struct drm_plane *plane,
 		ret = -EINVAL;
 	}
 
-	if (!vmw_framebuffer_to_vfb(fb)->dmabuf)
+	if (!vmw_framebuffer_to_vfb(fb)->bo)
 		surface = vmw_framebuffer_to_vfbs(fb)->surface;
 
 	if (surface && !surface->snooper.image) {
@@ -535,9 +535,9 @@ int vmw_du_crtc_atomic_check(struct drm_crtc *crtc,
 			     struct drm_crtc_state *new_state)
 {
 	struct vmw_display_unit *du = vmw_crtc_to_du(new_state->crtc);
-	int connector_mask = 1 << drm_connector_index(&du->connector);
+	int connector_mask = drm_connector_mask(&du->connector);
 	bool has_primary = new_state->plane_mask &
-			   BIT(drm_plane_index(crtc->primary));
+			   drm_plane_mask(crtc->primary);
 
 	/* We always want to have an active plane with an active CRTC */
 	if (has_primary != new_state->enable)
@@ -687,8 +687,8 @@ vmw_du_plane_duplicate_state(struct drm_plane *plane)
 	if (vps->surf)
 		(void) vmw_surface_reference(vps->surf);
 
-	if (vps->dmabuf)
-		(void) vmw_dmabuf_reference(vps->dmabuf);
+	if (vps->bo)
+		(void) vmw_bo_reference(vps->bo);
 
 	state = &vps->base;
 
@@ -745,8 +745,8 @@ vmw_du_plane_destroy_state(struct drm_plane *plane,
 	if (vps->surf)
 		vmw_surface_unreference(&vps->surf);
 
-	if (vps->dmabuf)
-		vmw_dmabuf_unreference(&vps->dmabuf);
+	if (vps->bo)
+		vmw_bo_unreference(&vps->bo);
 
 	drm_atomic_helper_plane_destroy_state(plane, state);
 }
@@ -902,12 +902,12 @@ static int vmw_framebuffer_surface_dirty(struct drm_framebuffer *framebuffer,
 
 /**
  * vmw_kms_readback - Perform a readback from the screen system to
- * a dma-buffer backed framebuffer.
+ * a buffer-object backed framebuffer.
  *
  * @dev_priv: Pointer to the device private structure.
  * @file_priv: Pointer to a struct drm_file identifying the caller.
  * Must be set to NULL if @user_fence_rep is NULL.
- * @vfb: Pointer to the dma-buffer backed framebuffer.
+ * @vfb: Pointer to the buffer-object backed framebuffer.
  * @user_fence_rep: User-space provided structure for fence information.
  * Must be set to non-NULL if @file_priv is non-NULL.
  * @vclips: Array of clip rects.
@@ -951,7 +951,7 @@ static int vmw_kms_new_framebuffer_surface(struct vmw_private *dev_priv,
 					   struct vmw_framebuffer **out,
 					   const struct drm_mode_fb_cmd2
 					   *mode_cmd,
-					   bool is_dmabuf_proxy)
+					   bool is_bo_proxy)
 
 {
 	struct drm_device *dev = dev_priv->dev;
@@ -1019,7 +1019,7 @@ static int vmw_kms_new_framebuffer_surface(struct vmw_private *dev_priv,
 	drm_helper_mode_fill_fb_struct(dev, &vfbs->base.base, mode_cmd);
 	vfbs->surface = vmw_surface_reference(surface);
 	vfbs->base.user_handle = mode_cmd->handles[0];
-	vfbs->is_dmabuf_proxy = is_dmabuf_proxy;
+	vfbs->is_bo_proxy = is_bo_proxy;
 
 	*out = &vfbs->base;
 
@@ -1038,30 +1038,30 @@ out_err1:
 }
 
 /*
- * Dmabuf framebuffer code
+ * Buffer-object framebuffer code
  */
 
-static void vmw_framebuffer_dmabuf_destroy(struct drm_framebuffer *framebuffer)
+static void vmw_framebuffer_bo_destroy(struct drm_framebuffer *framebuffer)
 {
-	struct vmw_framebuffer_dmabuf *vfbd =
+	struct vmw_framebuffer_bo *vfbd =
 		vmw_framebuffer_to_vfbd(framebuffer);
 
 	drm_framebuffer_cleanup(framebuffer);
-	vmw_dmabuf_unreference(&vfbd->buffer);
+	vmw_bo_unreference(&vfbd->buffer);
 	if (vfbd->base.user_obj)
 		ttm_base_object_unref(&vfbd->base.user_obj);
 
 	kfree(vfbd);
 }
 
-static int vmw_framebuffer_dmabuf_dirty(struct drm_framebuffer *framebuffer,
-				 struct drm_file *file_priv,
-				 unsigned flags, unsigned color,
-				 struct drm_clip_rect *clips,
-				 unsigned num_clips)
+static int vmw_framebuffer_bo_dirty(struct drm_framebuffer *framebuffer,
+				    struct drm_file *file_priv,
+				    unsigned int flags, unsigned int color,
+				    struct drm_clip_rect *clips,
+				    unsigned int num_clips)
 {
 	struct vmw_private *dev_priv = vmw_priv(framebuffer->dev);
-	struct vmw_framebuffer_dmabuf *vfbd =
+	struct vmw_framebuffer_bo *vfbd =
 		vmw_framebuffer_to_vfbd(framebuffer);
 	struct drm_clip_rect norect;
 	int ret, increment = 1;
@@ -1092,13 +1092,13 @@ static int vmw_framebuffer_dmabuf_dirty(struct drm_framebuffer *framebuffer,
 				       true, true, NULL);
 		break;
 	case vmw_du_screen_object:
-		ret = vmw_kms_sou_do_dmabuf_dirty(dev_priv, &vfbd->base,
-						  clips, NULL, num_clips,
-						  increment, true, NULL, NULL);
+		ret = vmw_kms_sou_do_bo_dirty(dev_priv, &vfbd->base,
+					      clips, NULL, num_clips,
+					      increment, true, NULL, NULL);
 		break;
 	case vmw_du_legacy:
-		ret = vmw_kms_ldu_do_dmabuf_dirty(dev_priv, &vfbd->base, 0, 0,
-						  clips, num_clips, increment);
+		ret = vmw_kms_ldu_do_bo_dirty(dev_priv, &vfbd->base, 0, 0,
+					      clips, num_clips, increment);
 		break;
 	default:
 		ret = -EINVAL;
@@ -1114,23 +1114,23 @@ static int vmw_framebuffer_dmabuf_dirty(struct drm_framebuffer *framebuffer,
 	return ret;
 }
 
-static const struct drm_framebuffer_funcs vmw_framebuffer_dmabuf_funcs = {
-	.destroy = vmw_framebuffer_dmabuf_destroy,
-	.dirty = vmw_framebuffer_dmabuf_dirty,
+static const struct drm_framebuffer_funcs vmw_framebuffer_bo_funcs = {
+	.destroy = vmw_framebuffer_bo_destroy,
+	.dirty = vmw_framebuffer_bo_dirty,
 };
 
 /**
- * Pin the dmabuffer in a location suitable for access by the
+ * Pin the bofer in a location suitable for access by the
  * display system.
  */
 static int vmw_framebuffer_pin(struct vmw_framebuffer *vfb)
 {
 	struct vmw_private *dev_priv = vmw_priv(vfb->base.dev);
-	struct vmw_dma_buffer *buf;
+	struct vmw_buffer_object *buf;
 	struct ttm_placement *placement;
 	int ret;
 
-	buf = vfb->dmabuf ?  vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
+	buf = vfb->bo ?  vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
 		vmw_framebuffer_to_vfbs(&vfb->base)->surface->res.backup;
 
 	if (!buf)
@@ -1139,12 +1139,12 @@ static int vmw_framebuffer_pin(struct vmw_framebuffer *vfb)
 	switch (dev_priv->active_display_unit) {
 	case vmw_du_legacy:
 		vmw_overlay_pause_all(dev_priv);
-		ret = vmw_dmabuf_pin_in_start_of_vram(dev_priv, buf, false);
+		ret = vmw_bo_pin_in_start_of_vram(dev_priv, buf, false);
 		vmw_overlay_resume_all(dev_priv);
 		break;
 	case vmw_du_screen_object:
 	case vmw_du_screen_target:
-		if (vfb->dmabuf) {
+		if (vfb->bo) {
 			if (dev_priv->capabilities & SVGA_CAP_3D) {
 				/*
 				 * Use surface DMA to get content to
@@ -1160,8 +1160,7 @@ static int vmw_framebuffer_pin(struct vmw_framebuffer *vfb)
 			placement = &vmw_mob_placement;
 		}
 
-		return vmw_dmabuf_pin_in_placement(dev_priv, buf, placement,
-						   false);
+		return vmw_bo_pin_in_placement(dev_priv, buf, placement, false);
 	default:
 		return -EINVAL;
 	}
@@ -1172,36 +1171,36 @@ static int vmw_framebuffer_pin(struct vmw_framebuffer *vfb)
 static int vmw_framebuffer_unpin(struct vmw_framebuffer *vfb)
 {
 	struct vmw_private *dev_priv = vmw_priv(vfb->base.dev);
-	struct vmw_dma_buffer *buf;
+	struct vmw_buffer_object *buf;
 
-	buf = vfb->dmabuf ?  vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
+	buf = vfb->bo ?  vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
 		vmw_framebuffer_to_vfbs(&vfb->base)->surface->res.backup;
 
 	if (WARN_ON(!buf))
 		return 0;
 
-	return vmw_dmabuf_unpin(dev_priv, buf, false);
+	return vmw_bo_unpin(dev_priv, buf, false);
 }
 
 /**
- * vmw_create_dmabuf_proxy - create a proxy surface for the DMA buf
+ * vmw_create_bo_proxy - create a proxy surface for the buffer object
  *
  * @dev: DRM device
  * @mode_cmd: parameters for the new surface
- * @dmabuf_mob: MOB backing the DMA buf
+ * @bo_mob: MOB backing the buffer object
  * @srf_out: newly created surface
  *
- * When the content FB is a DMA buf, we create a surface as a proxy to the
+ * When the content FB is a buffer object, we create a surface as a proxy to the
  * same buffer.  This way we can do a surface copy rather than a surface DMA.
  * This is a more efficient approach
  *
  * RETURNS:
  * 0 on success, error code otherwise
  */
-static int vmw_create_dmabuf_proxy(struct drm_device *dev,
-				   const struct drm_mode_fb_cmd2 *mode_cmd,
-				   struct vmw_dma_buffer *dmabuf_mob,
-				   struct vmw_surface **srf_out)
+static int vmw_create_bo_proxy(struct drm_device *dev,
+			       const struct drm_mode_fb_cmd2 *mode_cmd,
+			       struct vmw_buffer_object *bo_mob,
+			       struct vmw_surface **srf_out)
 {
 	uint32_t format;
 	struct drm_vmw_size content_base_size = {0};
@@ -1239,15 +1238,17 @@ static int vmw_create_dmabuf_proxy(struct drm_device *dev,
 	content_base_size.depth  = 1;
 
 	ret = vmw_surface_gb_priv_define(dev,
-			0, /* kernel visible only */
-			0, /* flags */
-			format,
-			true, /* can be a scanout buffer */
-			1, /* num of mip levels */
-			0,
-			0,
-			content_base_size,
-			srf_out);
+					 0, /* kernel visible only */
+					 0, /* flags */
+					 format,
+					 true, /* can be a scanout buffer */
+					 1, /* num of mip levels */
+					 0,
+					 0,
+					 content_base_size,
+					 SVGA3D_MS_PATTERN_NONE,
+					 SVGA3D_MS_QUALITY_NONE,
+					 srf_out);
 	if (ret) {
 		DRM_ERROR("Failed to allocate proxy content buffer\n");
 		return ret;
@@ -1258,8 +1259,8 @@ static int vmw_create_dmabuf_proxy(struct drm_device *dev,
 	/* Reserve and switch the backing mob. */
 	mutex_lock(&res->dev_priv->cmdbuf_mutex);
 	(void) vmw_resource_reserve(res, false, true);
-	vmw_dmabuf_unreference(&res->backup);
-	res->backup = vmw_dmabuf_reference(dmabuf_mob);
+	vmw_bo_unreference(&res->backup);
+	res->backup = vmw_bo_reference(bo_mob);
 	res->backup_offset = 0;
 	vmw_resource_unreserve(res, false, NULL, 0);
 	mutex_unlock(&res->dev_priv->cmdbuf_mutex);
@@ -1269,21 +1270,21 @@ static int vmw_create_dmabuf_proxy(struct drm_device *dev,
 
 
 
-static int vmw_kms_new_framebuffer_dmabuf(struct vmw_private *dev_priv,
-					  struct vmw_dma_buffer *dmabuf,
-					  struct vmw_framebuffer **out,
-					  const struct drm_mode_fb_cmd2
-					  *mode_cmd)
+static int vmw_kms_new_framebuffer_bo(struct vmw_private *dev_priv,
+				      struct vmw_buffer_object *bo,
+				      struct vmw_framebuffer **out,
+				      const struct drm_mode_fb_cmd2
+				      *mode_cmd)
 
 {
 	struct drm_device *dev = dev_priv->dev;
-	struct vmw_framebuffer_dmabuf *vfbd;
+	struct vmw_framebuffer_bo *vfbd;
 	unsigned int requested_size;
 	struct drm_format_name_buf format_name;
 	int ret;
 
 	requested_size = mode_cmd->height * mode_cmd->pitches[0];
-	if (unlikely(requested_size > dmabuf->base.num_pages * PAGE_SIZE)) {
+	if (unlikely(requested_size > bo->base.num_pages * PAGE_SIZE)) {
 		DRM_ERROR("Screen buffer object size is too small "
 			  "for requested mode.\n");
 		return -EINVAL;
@@ -1312,20 +1313,20 @@ static int vmw_kms_new_framebuffer_dmabuf(struct vmw_private *dev_priv,
 	}
 
 	drm_helper_mode_fill_fb_struct(dev, &vfbd->base.base, mode_cmd);
-	vfbd->base.dmabuf = true;
-	vfbd->buffer = vmw_dmabuf_reference(dmabuf);
+	vfbd->base.bo = true;
+	vfbd->buffer = vmw_bo_reference(bo);
 	vfbd->base.user_handle = mode_cmd->handles[0];
 	*out = &vfbd->base;
 
 	ret = drm_framebuffer_init(dev, &vfbd->base.base,
-				   &vmw_framebuffer_dmabuf_funcs);
+				   &vmw_framebuffer_bo_funcs);
 	if (ret)
 		goto out_err2;
 
 	return 0;
 
 out_err2:
-	vmw_dmabuf_unreference(&dmabuf);
+	vmw_bo_unreference(&bo);
 	kfree(vfbd);
 out_err1:
 	return ret;
@@ -1354,57 +1355,57 @@ vmw_kms_srf_ok(struct vmw_private *dev_priv, uint32_t width, uint32_t height)
  * vmw_kms_new_framebuffer - Create a new framebuffer.
  *
  * @dev_priv: Pointer to device private struct.
- * @dmabuf: Pointer to dma buffer to wrap the kms framebuffer around.
- * Either @dmabuf or @surface must be NULL.
+ * @bo: Pointer to buffer object to wrap the kms framebuffer around.
+ * Either @bo or @surface must be NULL.
  * @surface: Pointer to a surface to wrap the kms framebuffer around.
- * Either @dmabuf or @surface must be NULL.
- * @only_2d: No presents will occur to this dma buffer based framebuffer. This
- * Helps the code to do some important optimizations.
+ * Either @bo or @surface must be NULL.
+ * @only_2d: No presents will occur to this buffer object based framebuffer.
+ * This helps the code to do some important optimizations.
  * @mode_cmd: Frame-buffer metadata.
  */
 struct vmw_framebuffer *
 vmw_kms_new_framebuffer(struct vmw_private *dev_priv,
-			struct vmw_dma_buffer *dmabuf,
+			struct vmw_buffer_object *bo,
 			struct vmw_surface *surface,
 			bool only_2d,
 			const struct drm_mode_fb_cmd2 *mode_cmd)
 {
 	struct vmw_framebuffer *vfb = NULL;
-	bool is_dmabuf_proxy = false;
+	bool is_bo_proxy = false;
 	int ret;
 
 	/*
 	 * We cannot use the SurfaceDMA command in an non-accelerated VM,
-	 * therefore, wrap the DMA buf in a surface so we can use the
+	 * therefore, wrap the buffer object in a surface so we can use the
 	 * SurfaceCopy command.
 	 */
 	if (vmw_kms_srf_ok(dev_priv, mode_cmd->width, mode_cmd->height)  &&
-	    dmabuf && only_2d &&
+	    bo && only_2d &&
 	    mode_cmd->width > 64 &&  /* Don't create a proxy for cursor */
 	    dev_priv->active_display_unit == vmw_du_screen_target) {
-		ret = vmw_create_dmabuf_proxy(dev_priv->dev, mode_cmd,
-					      dmabuf, &surface);
+		ret = vmw_create_bo_proxy(dev_priv->dev, mode_cmd,
+					  bo, &surface);
 		if (ret)
 			return ERR_PTR(ret);
 
-		is_dmabuf_proxy = true;
+		is_bo_proxy = true;
 	}
 
 	/* Create the new framebuffer depending one what we have */
 	if (surface) {
 		ret = vmw_kms_new_framebuffer_surface(dev_priv, surface, &vfb,
 						      mode_cmd,
-						      is_dmabuf_proxy);
+						      is_bo_proxy);
 
 		/*
-		 * vmw_create_dmabuf_proxy() adds a reference that is no longer
+		 * vmw_create_bo_proxy() adds a reference that is no longer
 		 * needed
 		 */
-		if (is_dmabuf_proxy)
+		if (is_bo_proxy)
 			vmw_surface_unreference(&surface);
-	} else if (dmabuf) {
-		ret = vmw_kms_new_framebuffer_dmabuf(dev_priv, dmabuf, &vfb,
-						     mode_cmd);
+	} else if (bo) {
+		ret = vmw_kms_new_framebuffer_bo(dev_priv, bo, &vfb,
+						 mode_cmd);
 	} else {
 		BUG();
 	}
@@ -1430,23 +1431,10 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev,
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
 	struct vmw_framebuffer *vfb = NULL;
 	struct vmw_surface *surface = NULL;
-	struct vmw_dma_buffer *bo = NULL;
+	struct vmw_buffer_object *bo = NULL;
 	struct ttm_base_object *user_obj;
 	int ret;
 
-	/**
-	 * This code should be conditioned on Screen Objects not being used.
-	 * If screen objects are used, we can allocate a GMR to hold the
-	 * requested framebuffer.
-	 */
-
-	if (!vmw_kms_validate_mode_vram(dev_priv,
-					mode_cmd->pitches[0],
-					mode_cmd->height)) {
-		DRM_ERROR("Requested mode exceed bounding box limit.\n");
-		return ERR_PTR(-ENOMEM);
-	}
-
 	/*
 	 * Take a reference on the user object of the resource
 	 * backing the kms fb. This ensures that user-space handle
@@ -1466,7 +1454,7 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev,
 	 * End conditioned code.
 	 */
 
-	/* returns either a dmabuf or surface */
+	/* returns either a bo or surface */
 	ret = vmw_user_lookup_handle(dev_priv, tfile,
 				     mode_cmd->handles[0],
 				     &surface, &bo);
@@ -1494,7 +1482,7 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev,
 err_out:
 	/* vmw_user_lookup_handle takes one ref so does new_fb */
 	if (bo)
-		vmw_dmabuf_unreference(&bo);
+		vmw_bo_unreference(&bo);
 	if (surface)
 		vmw_surface_unreference(&surface);
 
@@ -1508,7 +1496,168 @@ err_out:
 	return &vfb->base;
 }
 
+/**
+ * vmw_kms_check_display_memory - Validates display memory required for a
+ * topology
+ * @dev: DRM device
+ * @num_rects: number of drm_rect in rects
+ * @rects: array of drm_rect representing the topology to validate indexed by
+ * crtc index.
+ *
+ * Returns:
+ * 0 on success otherwise negative error code
+ */
+static int vmw_kms_check_display_memory(struct drm_device *dev,
+					uint32_t num_rects,
+					struct drm_rect *rects)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	struct drm_mode_config *mode_config = &dev->mode_config;
+	struct drm_rect bounding_box = {0};
+	u64 total_pixels = 0, pixel_mem, bb_mem;
+	int i;
+
+	for (i = 0; i < num_rects; i++) {
+		/*
+		 * Currently this check is limiting the topology within max
+		 * texture/screentarget size. This should change in future when
+		 * user-space support multiple fb with topology.
+		 */
+		if (rects[i].x1 < 0 ||  rects[i].y1 < 0 ||
+		    rects[i].x2 > mode_config->max_width ||
+		    rects[i].y2 > mode_config->max_height) {
+			DRM_ERROR("Invalid GUI layout.\n");
+			return -EINVAL;
+		}
 
+		/* Bounding box upper left is at (0,0). */
+		if (rects[i].x2 > bounding_box.x2)
+			bounding_box.x2 = rects[i].x2;
+
+		if (rects[i].y2 > bounding_box.y2)
+			bounding_box.y2 = rects[i].y2;
+
+		total_pixels += (u64) drm_rect_width(&rects[i]) *
+			(u64) drm_rect_height(&rects[i]);
+	}
+
+	/* Virtual svga device primary limits are always in 32-bpp. */
+	pixel_mem = total_pixels * 4;
+
+	/*
+	 * For HV10 and below prim_bb_mem is vram size. When
+	 * SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM is not present vram size is
+	 * limit on primary bounding box
+	 */
+	if (pixel_mem > dev_priv->prim_bb_mem) {
+		DRM_ERROR("Combined output size too large.\n");
+		return -EINVAL;
+	}
+
+	/* SVGA_CAP_NO_BB_RESTRICTION is available for STDU only. */
+	if (dev_priv->active_display_unit != vmw_du_screen_target ||
+	    !(dev_priv->capabilities & SVGA_CAP_NO_BB_RESTRICTION)) {
+		bb_mem = (u64) bounding_box.x2 * bounding_box.y2 * 4;
+
+		if (bb_mem > dev_priv->prim_bb_mem) {
+			DRM_ERROR("Topology is beyond supported limits.\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * vmw_kms_check_topology - Validates topology in drm_atomic_state
+ * @dev: DRM device
+ * @state: the driver state object
+ *
+ * Returns:
+ * 0 on success otherwise negative error code
+ */
+static int vmw_kms_check_topology(struct drm_device *dev,
+				  struct drm_atomic_state *state)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
+	struct drm_rect *rects;
+	struct drm_crtc *crtc;
+	uint32_t i;
+	int ret = 0;
+
+	rects = kcalloc(dev->mode_config.num_crtc, sizeof(struct drm_rect),
+			GFP_KERNEL);
+	if (!rects)
+		return -ENOMEM;
+
+	mutex_lock(&dev_priv->requested_layout_mutex);
+
+	drm_for_each_crtc(crtc, dev) {
+		struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
+		struct drm_crtc_state *crtc_state = crtc->state;
+
+		i = drm_crtc_index(crtc);
+
+		if (crtc_state && crtc_state->enable) {
+			rects[i].x1 = du->gui_x;
+			rects[i].y1 = du->gui_y;
+			rects[i].x2 = du->gui_x + crtc_state->mode.hdisplay;
+			rects[i].y2 = du->gui_y + crtc_state->mode.vdisplay;
+		}
+	}
+
+	/* Determine change to topology due to new atomic state */
+	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state,
+				      new_crtc_state, i) {
+		struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
+		struct drm_connector *connector;
+		struct drm_connector_state *conn_state;
+		struct vmw_connector_state *vmw_conn_state;
+
+		if (!new_crtc_state->enable && old_crtc_state->enable) {
+			rects[i].x1 = 0;
+			rects[i].y1 = 0;
+			rects[i].x2 = 0;
+			rects[i].y2 = 0;
+			continue;
+		}
+
+		if (!du->pref_active) {
+			ret = -EINVAL;
+			goto clean;
+		}
+
+		/*
+		 * For vmwgfx each crtc has only one connector attached and it
+		 * is not changed so don't really need to check the
+		 * crtc->connector_mask and iterate over it.
+		 */
+		connector = &du->connector;
+		conn_state = drm_atomic_get_connector_state(state, connector);
+		if (IS_ERR(conn_state)) {
+			ret = PTR_ERR(conn_state);
+			goto clean;
+		}
+
+		vmw_conn_state = vmw_connector_state_to_vcs(conn_state);
+		vmw_conn_state->gui_x = du->gui_x;
+		vmw_conn_state->gui_y = du->gui_y;
+
+		rects[i].x1 = du->gui_x;
+		rects[i].y1 = du->gui_y;
+		rects[i].x2 = du->gui_x + new_crtc_state->mode.hdisplay;
+		rects[i].y2 = du->gui_y + new_crtc_state->mode.vdisplay;
+	}
+
+	ret = vmw_kms_check_display_memory(dev, dev->mode_config.num_crtc,
+					   rects);
+
+clean:
+	mutex_unlock(&dev_priv->requested_layout_mutex);
+	kfree(rects);
+	return ret;
+}
 
 /**
  * vmw_kms_atomic_check_modeset- validate state object for modeset changes
@@ -1520,36 +1669,39 @@ err_out:
  * us to assign a value to mode->crtc_clock so that
  * drm_calc_timestamping_constants() won't throw an error message
  *
- * RETURNS
+ * Returns:
  * Zero for success or -errno
  */
 static int
 vmw_kms_atomic_check_modeset(struct drm_device *dev,
 			     struct drm_atomic_state *state)
 {
-	struct drm_crtc_state *crtc_state;
 	struct drm_crtc *crtc;
-	struct vmw_private *dev_priv = vmw_priv(dev);
-	int i;
-
-	for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
-		unsigned long requested_bb_mem = 0;
+	struct drm_crtc_state *crtc_state;
+	bool need_modeset = false;
+	int i, ret;
 
-		if (dev_priv->active_display_unit == vmw_du_screen_target) {
-			if (crtc->primary->fb) {
-				int cpp = crtc->primary->fb->pitches[0] /
-					  crtc->primary->fb->width;
+	ret = drm_atomic_helper_check(dev, state);
+	if (ret)
+		return ret;
 
-				requested_bb_mem += crtc->mode.hdisplay * cpp *
-						    crtc->mode.vdisplay;
-			}
+	if (!state->allow_modeset)
+		return ret;
 
-			if (requested_bb_mem > dev_priv->prim_bb_mem)
-				return -EINVAL;
-		}
+	/*
+	 * Legacy path do not set allow_modeset properly like
+	 * @drm_atomic_helper_update_plane, This will result in unnecessary call
+	 * to vmw_kms_check_topology. So extra set of check.
+	 */
+	for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
+		if (drm_atomic_crtc_needs_modeset(crtc_state))
+			need_modeset = true;
 	}
 
-	return drm_atomic_helper_check(dev, state);
+	if (need_modeset)
+		return vmw_kms_check_topology(dev, state);
+
+	return ret;
 }
 
 static const struct drm_mode_config_funcs vmw_kms_funcs = {
@@ -1841,40 +1993,49 @@ void vmw_disable_vblank(struct drm_device *dev, unsigned int pipe)
 {
 }
 
-
-/*
- * Small shared kms functions.
+/**
+ * vmw_du_update_layout - Update the display unit with topology from resolution
+ * plugin and generate DRM uevent
+ * @dev_priv: device private
+ * @num_rects: number of drm_rect in rects
+ * @rects: toplogy to update
  */
-
-static int vmw_du_update_layout(struct vmw_private *dev_priv, unsigned num,
-			 struct drm_vmw_rect *rects)
+static int vmw_du_update_layout(struct vmw_private *dev_priv,
+				unsigned int num_rects, struct drm_rect *rects)
 {
 	struct drm_device *dev = dev_priv->dev;
 	struct vmw_display_unit *du;
 	struct drm_connector *con;
+	struct drm_connector_list_iter conn_iter;
 
-	mutex_lock(&dev->mode_config.mutex);
-
-#if 0
-	{
-		unsigned int i;
-
-		DRM_INFO("%s: new layout ", __func__);
-		for (i = 0; i < num; i++)
-			DRM_INFO("(%i, %i %ux%u) ", rects[i].x, rects[i].y,
-				 rects[i].w, rects[i].h);
-		DRM_INFO("\n");
+	/*
+	 * Currently only gui_x/y is protected with requested_layout_mutex.
+	 */
+	mutex_lock(&dev_priv->requested_layout_mutex);
+	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_for_each_connector_iter(con, &conn_iter) {
+		du = vmw_connector_to_du(con);
+		if (num_rects > du->unit) {
+			du->pref_width = drm_rect_width(&rects[du->unit]);
+			du->pref_height = drm_rect_height(&rects[du->unit]);
+			du->pref_active = true;
+			du->gui_x = rects[du->unit].x1;
+			du->gui_y = rects[du->unit].y1;
+		} else {
+			du->pref_width = 800;
+			du->pref_height = 600;
+			du->pref_active = false;
+			du->gui_x = 0;
+			du->gui_y = 0;
+		}
 	}
-#endif
+	drm_connector_list_iter_end(&conn_iter);
+	mutex_unlock(&dev_priv->requested_layout_mutex);
 
+	mutex_lock(&dev->mode_config.mutex);
 	list_for_each_entry(con, &dev->mode_config.connector_list, head) {
 		du = vmw_connector_to_du(con);
-		if (num > du->unit) {
-			du->pref_width = rects[du->unit].w;
-			du->pref_height = rects[du->unit].h;
-			du->pref_active = true;
-			du->gui_x = rects[du->unit].x;
-			du->gui_y = rects[du->unit].y;
+		if (num_rects > du->unit) {
 			drm_object_property_set_value
 			  (&con->base, dev->mode_config.suggested_x_property,
 			   du->gui_x);
@@ -1882,9 +2043,6 @@ static int vmw_du_update_layout(struct vmw_private *dev_priv, unsigned num,
 			  (&con->base, dev->mode_config.suggested_y_property,
 			   du->gui_y);
 		} else {
-			du->pref_width = 800;
-			du->pref_height = 600;
-			du->pref_active = false;
 			drm_object_property_set_value
 			  (&con->base, dev->mode_config.suggested_x_property,
 			   0);
@@ -1894,8 +2052,8 @@ static int vmw_du_update_layout(struct vmw_private *dev_priv, unsigned num,
 		}
 		con->status = vmw_du_connector_detect(con, true);
 	}
-
 	mutex_unlock(&dev->mode_config.mutex);
+
 	drm_sysfs_hotplug_event(dev);
 
 	return 0;
@@ -2110,7 +2268,7 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector,
 		drm_mode_probed_add(connector, mode);
 	}
 
-	drm_mode_connector_list_update(connector);
+	drm_connector_list_update(connector);
 	/* Move the prefered mode first, help apps pick the right mode. */
 	drm_mode_sort(&connector->modes);
 
@@ -2195,7 +2353,25 @@ vmw_du_connector_atomic_get_property(struct drm_connector *connector,
 	return 0;
 }
 
-
+/**
+ * vmw_kms_update_layout_ioctl - Handler for DRM_VMW_UPDATE_LAYOUT ioctl
+ * @dev: drm device for the ioctl
+ * @data: data pointer for the ioctl
+ * @file_priv: drm file for the ioctl call
+ *
+ * Update preferred topology of display unit as per ioctl request. The topology
+ * is expressed as array of drm_vmw_rect.
+ * e.g.
+ * [0 0 640 480] [640 0 800 600] [0 480 640 480]
+ *
+ * NOTE:
+ * The x and y offset (upper left) in drm_vmw_rect cannot be less than 0. Beside
+ * device limit on topology, x + w and y + h (lower right) cannot be greater
+ * than INT_MAX. So topology beyond these limits will return with error.
+ *
+ * Returns:
+ * Zero on success, negative errno on failure.
+ */
 int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *file_priv)
 {
@@ -2204,15 +2380,12 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 		(struct drm_vmw_update_layout_arg *)data;
 	void __user *user_rects;
 	struct drm_vmw_rect *rects;
+	struct drm_rect *drm_rects;
 	unsigned rects_size;
-	int ret;
-	int i;
-	u64 total_pixels = 0;
-	struct drm_mode_config *mode_config = &dev->mode_config;
-	struct drm_vmw_rect bounding_box = {0};
+	int ret, i;
 
 	if (!arg->num_outputs) {
-		struct drm_vmw_rect def_rect = {0, 0, 800, 600};
+		struct drm_rect def_rect = {0, 0, 800, 600};
 		vmw_du_update_layout(dev_priv, 1, &def_rect);
 		return 0;
 	}
@@ -2231,52 +2404,29 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 		goto out_free;
 	}
 
-	for (i = 0; i < arg->num_outputs; ++i) {
-		if (rects[i].x < 0 ||
-		    rects[i].y < 0 ||
-		    rects[i].x + rects[i].w > mode_config->max_width ||
-		    rects[i].y + rects[i].h > mode_config->max_height) {
-			DRM_ERROR("Invalid GUI layout.\n");
-			ret = -EINVAL;
-			goto out_free;
-		}
-
-		/*
-		 * bounding_box.w and bunding_box.h are used as
-		 * lower-right coordinates
-		 */
-		if (rects[i].x + rects[i].w > bounding_box.w)
-			bounding_box.w = rects[i].x + rects[i].w;
-
-		if (rects[i].y + rects[i].h > bounding_box.h)
-			bounding_box.h = rects[i].y + rects[i].h;
+	drm_rects = (struct drm_rect *)rects;
 
-		total_pixels += (u64) rects[i].w * (u64) rects[i].h;
-	}
-
-	if (dev_priv->active_display_unit == vmw_du_screen_target) {
-		/*
-		 * For Screen Targets, the limits for a toplogy are:
-		 *	1. Bounding box (assuming 32bpp) must be < prim_bb_mem
-		 *      2. Total pixels (assuming 32bpp) must be < prim_bb_mem
-		 */
-		u64 bb_mem    = (u64) bounding_box.w * bounding_box.h * 4;
-		u64 pixel_mem = total_pixels * 4;
+	for (i = 0; i < arg->num_outputs; i++) {
+		struct drm_vmw_rect curr_rect;
 
-		if (bb_mem > dev_priv->prim_bb_mem) {
-			DRM_ERROR("Topology is beyond supported limits.\n");
-			ret = -EINVAL;
+		/* Verify user-space for overflow as kernel use drm_rect */
+		if ((rects[i].x + rects[i].w > INT_MAX) ||
+		    (rects[i].y + rects[i].h > INT_MAX)) {
+			ret = -ERANGE;
 			goto out_free;
 		}
 
-		if (pixel_mem > dev_priv->prim_bb_mem) {
-			DRM_ERROR("Combined output size too large\n");
-			ret = -EINVAL;
-			goto out_free;
-		}
+		curr_rect = rects[i];
+		drm_rects[i].x1 = curr_rect.x;
+		drm_rects[i].y1 = curr_rect.y;
+		drm_rects[i].x2 = curr_rect.x + curr_rect.w;
+		drm_rects[i].y2 = curr_rect.y + curr_rect.h;
 	}
 
-	vmw_du_update_layout(dev_priv, arg->num_outputs, rects);
+	ret = vmw_kms_check_display_memory(dev, arg->num_outputs, drm_rects);
+
+	if (ret == 0)
+		vmw_du_update_layout(dev_priv, arg->num_outputs, drm_rects);
 
 out_free:
 	kfree(rects);
@@ -2322,9 +2472,10 @@ int vmw_kms_helper_dirty(struct vmw_private *dev_priv,
 	} else {
 		list_for_each_entry(crtc, &dev_priv->dev->mode_config.crtc_list,
 				    head) {
-			if (crtc->primary->fb != &framebuffer->base)
-				continue;
-			units[num_units++] = vmw_crtc_to_du(crtc);
+			struct drm_plane *plane = crtc->primary;
+
+			if (plane->state->fb == &framebuffer->base)
+				units[num_units++] = vmw_crtc_to_du(crtc);
 		}
 	}
 
@@ -2422,7 +2573,7 @@ int vmw_kms_helper_dirty(struct vmw_private *dev_priv,
  * interrupted by a signal.
  */
 int vmw_kms_helper_buffer_prepare(struct vmw_private *dev_priv,
-				  struct vmw_dma_buffer *buf,
+				  struct vmw_buffer_object *buf,
 				  bool interruptible,
 				  bool validate_as_mob,
 				  bool for_cpu_blit)
@@ -2454,7 +2605,7 @@ int vmw_kms_helper_buffer_prepare(struct vmw_private *dev_priv,
  * Helper to be used if an error forces the caller to undo the actions of
  * vmw_kms_helper_buffer_prepare.
  */
-void vmw_kms_helper_buffer_revert(struct vmw_dma_buffer *buf)
+void vmw_kms_helper_buffer_revert(struct vmw_buffer_object *buf)
 {
 	if (buf)
 		ttm_bo_unreserve(&buf->base);
@@ -2477,7 +2628,7 @@ void vmw_kms_helper_buffer_revert(struct vmw_dma_buffer *buf)
  */
 void vmw_kms_helper_buffer_finish(struct vmw_private *dev_priv,
 				  struct drm_file *file_priv,
-				  struct vmw_dma_buffer *buf,
+				  struct vmw_buffer_object *buf,
 				  struct vmw_fence_obj **out_fence,
 				  struct drm_vmw_fence_rep __user *
 				  user_fence_rep)
@@ -2489,7 +2640,7 @@ void vmw_kms_helper_buffer_finish(struct vmw_private *dev_priv,
 	ret = vmw_execbuf_fence_commands(file_priv, dev_priv, &fence,
 					 file_priv ? &handle : NULL);
 	if (buf)
-		vmw_fence_single_bo(&buf->base, fence);
+		vmw_bo_fence_single(&buf->base, fence);
 	if (file_priv)
 		vmw_execbuf_copy_fence_user(dev_priv, vmw_fpriv(file_priv),
 					    ret, user_fence_rep, fence,
@@ -2517,7 +2668,7 @@ void vmw_kms_helper_resource_revert(struct vmw_validation_ctx *ctx)
 	struct vmw_resource *res = ctx->res;
 
 	vmw_kms_helper_buffer_revert(ctx->buf);
-	vmw_dmabuf_unreference(&ctx->buf);
+	vmw_bo_unreference(&ctx->buf);
 	vmw_resource_unreserve(res, false, NULL, 0);
 	mutex_unlock(&res->dev_priv->cmdbuf_mutex);
 }
@@ -2562,7 +2713,7 @@ int vmw_kms_helper_resource_prepare(struct vmw_resource *res,
 		if (ret)
 			goto out_unreserve;
 
-		ctx->buf = vmw_dmabuf_reference(res->backup);
+		ctx->buf = vmw_bo_reference(res->backup);
 	}
 	ret = vmw_resource_validate(res);
 	if (ret)
@@ -2595,7 +2746,7 @@ void vmw_kms_helper_resource_finish(struct vmw_validation_ctx *ctx,
 		vmw_kms_helper_buffer_finish(res->dev_priv, NULL, ctx->buf,
 					     out_fence, NULL);
 
-	vmw_dmabuf_unreference(&ctx->buf);
+	vmw_bo_unreference(&ctx->buf);
 	vmw_resource_unreserve(res, false, NULL, 0);
 	mutex_unlock(&res->dev_priv->cmdbuf_mutex);
 }
@@ -2806,6 +2957,7 @@ void vmw_kms_update_implicit_fb(struct vmw_private *dev_priv,
 				struct drm_crtc *crtc)
 {
 	struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
+	struct drm_plane *plane = crtc->primary;
 	struct vmw_framebuffer *vfb;
 
 	mutex_lock(&dev_priv->global_kms_state_mutex);
@@ -2813,7 +2965,7 @@ void vmw_kms_update_implicit_fb(struct vmw_private *dev_priv,
 	if (!du->is_implicit)
 		goto out_unlock;
 
-	vfb = vmw_framebuffer_to_vfb(crtc->primary->fb);
+	vfb = vmw_framebuffer_to_vfb(plane->state->fb);
 	WARN_ON_ONCE(dev_priv->num_implicit != 1 &&
 		     dev_priv->implicit_fb != vfb);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
index 6b7c012719f1..31311298ec0b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
@@ -1,7 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -90,7 +90,7 @@ struct vmw_kms_dirty {
 #define vmw_framebuffer_to_vfbs(x) \
 	container_of(x, struct vmw_framebuffer_surface, base.base)
 #define vmw_framebuffer_to_vfbd(x) \
-	container_of(x, struct vmw_framebuffer_dmabuf, base.base)
+	container_of(x, struct vmw_framebuffer_bo, base.base)
 
 /**
  * Base class for framebuffers
@@ -102,7 +102,7 @@ struct vmw_framebuffer {
 	struct drm_framebuffer base;
 	int (*pin)(struct vmw_framebuffer *fb);
 	int (*unpin)(struct vmw_framebuffer *fb);
-	bool dmabuf;
+	bool bo;
 	struct ttm_base_object *user_obj;
 	uint32_t user_handle;
 };
@@ -117,15 +117,15 @@ struct vmw_clip_rect {
 struct vmw_framebuffer_surface {
 	struct vmw_framebuffer base;
 	struct vmw_surface *surface;
-	struct vmw_dma_buffer *buffer;
+	struct vmw_buffer_object *buffer;
 	struct list_head head;
-	bool is_dmabuf_proxy;  /* true if this is proxy surface for DMA buf */
+	bool is_bo_proxy;  /* true if this is proxy surface for DMA buf */
 };
 
 
-struct vmw_framebuffer_dmabuf {
+struct vmw_framebuffer_bo {
 	struct vmw_framebuffer base;
-	struct vmw_dma_buffer *buffer;
+	struct vmw_buffer_object *buffer;
 };
 
 
@@ -161,18 +161,18 @@ struct vmw_crtc_state {
  *
  * @base DRM plane object
  * @surf Display surface for STDU
- * @dmabuf display dmabuf for SOU
+ * @bo display bo for SOU
  * @content_fb_type Used by STDU.
- * @dmabuf_size Size of the dmabuf, used by Screen Object Display Unit
+ * @bo_size Size of the bo, used by Screen Object Display Unit
  * @pinned pin count for STDU display surface
  */
 struct vmw_plane_state {
 	struct drm_plane_state base;
 	struct vmw_surface *surf;
-	struct vmw_dma_buffer *dmabuf;
+	struct vmw_buffer_object *bo;
 
 	int content_fb_type;
-	unsigned long dmabuf_size;
+	unsigned long bo_size;
 
 	int pinned;
 
@@ -192,6 +192,24 @@ struct vmw_connector_state {
 	struct drm_connector_state base;
 
 	bool is_implicit;
+
+	/**
+	 * @gui_x:
+	 *
+	 * vmwgfx connector property representing the x position of this display
+	 * unit (connector is synonymous to display unit) in overall topology.
+	 * This is what the device expect as xRoot while creating screen.
+	 */
+	int gui_x;
+
+	/**
+	 * @gui_y:
+	 *
+	 * vmwgfx connector property representing the y position of this display
+	 * unit (connector is synonymous to display unit) in overall topology.
+	 * This is what the device expect as yRoot while creating screen.
+	 */
+	int gui_y;
 };
 
 /**
@@ -209,7 +227,7 @@ struct vmw_display_unit {
 	struct drm_plane cursor;
 
 	struct vmw_surface *cursor_surface;
-	struct vmw_dma_buffer *cursor_dmabuf;
+	struct vmw_buffer_object *cursor_bo;
 	size_t cursor_age;
 
 	int cursor_x;
@@ -243,7 +261,7 @@ struct vmw_display_unit {
 
 struct vmw_validation_ctx {
 	struct vmw_resource *res;
-	struct vmw_dma_buffer *buf;
+	struct vmw_buffer_object *buf;
 };
 
 #define vmw_crtc_to_du(x) \
@@ -291,14 +309,14 @@ int vmw_kms_helper_dirty(struct vmw_private *dev_priv,
 			 struct vmw_kms_dirty *dirty);
 
 int vmw_kms_helper_buffer_prepare(struct vmw_private *dev_priv,
-				  struct vmw_dma_buffer *buf,
+				  struct vmw_buffer_object *buf,
 				  bool interruptible,
 				  bool validate_as_mob,
 				  bool for_cpu_blit);
-void vmw_kms_helper_buffer_revert(struct vmw_dma_buffer *buf);
+void vmw_kms_helper_buffer_revert(struct vmw_buffer_object *buf);
 void vmw_kms_helper_buffer_finish(struct vmw_private *dev_priv,
 				  struct drm_file *file_priv,
-				  struct vmw_dma_buffer *buf,
+				  struct vmw_buffer_object *buf,
 				  struct vmw_fence_obj **out_fence,
 				  struct drm_vmw_fence_rep __user *
 				  user_fence_rep);
@@ -316,7 +334,7 @@ int vmw_kms_readback(struct vmw_private *dev_priv,
 		     uint32_t num_clips);
 struct vmw_framebuffer *
 vmw_kms_new_framebuffer(struct vmw_private *dev_priv,
-			struct vmw_dma_buffer *dmabuf,
+			struct vmw_buffer_object *bo,
 			struct vmw_surface *surface,
 			bool only_2d,
 			const struct drm_mode_fb_cmd2 *mode_cmd);
@@ -384,11 +402,11 @@ void vmw_du_connector_destroy_state(struct drm_connector *connector,
  */
 int vmw_kms_ldu_init_display(struct vmw_private *dev_priv);
 int vmw_kms_ldu_close_display(struct vmw_private *dev_priv);
-int vmw_kms_ldu_do_dmabuf_dirty(struct vmw_private *dev_priv,
-				struct vmw_framebuffer *framebuffer,
-				unsigned flags, unsigned color,
-				struct drm_clip_rect *clips,
-				unsigned num_clips, int increment);
+int vmw_kms_ldu_do_bo_dirty(struct vmw_private *dev_priv,
+			    struct vmw_framebuffer *framebuffer,
+			    unsigned int flags, unsigned int color,
+			    struct drm_clip_rect *clips,
+			    unsigned int num_clips, int increment);
 int vmw_kms_update_proxy(struct vmw_resource *res,
 			 const struct drm_clip_rect *clips,
 			 unsigned num_clips,
@@ -408,14 +426,14 @@ int vmw_kms_sou_do_surface_dirty(struct vmw_private *dev_priv,
 				 unsigned num_clips, int inc,
 				 struct vmw_fence_obj **out_fence,
 				 struct drm_crtc *crtc);
-int vmw_kms_sou_do_dmabuf_dirty(struct vmw_private *dev_priv,
-				struct vmw_framebuffer *framebuffer,
-				struct drm_clip_rect *clips,
-				struct drm_vmw_rect *vclips,
-				unsigned num_clips, int increment,
-				bool interruptible,
-				struct vmw_fence_obj **out_fence,
-				struct drm_crtc *crtc);
+int vmw_kms_sou_do_bo_dirty(struct vmw_private *dev_priv,
+			    struct vmw_framebuffer *framebuffer,
+			    struct drm_clip_rect *clips,
+			    struct drm_vmw_rect *vclips,
+			    unsigned int num_clips, int increment,
+			    bool interruptible,
+			    struct vmw_fence_obj **out_fence,
+			    struct drm_crtc *crtc);
 int vmw_kms_sou_readback(struct vmw_private *dev_priv,
 			 struct drm_file *file_priv,
 			 struct vmw_framebuffer *vfb,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
index 4a5907e3f560..723578117191 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -438,7 +438,7 @@ static int vmw_ldu_init(struct vmw_private *dev_priv, unsigned unit)
 		goto err_free_connector;
 	}
 
-	(void) drm_mode_connector_attach_encoder(connector, encoder);
+	(void) drm_connector_attach_encoder(connector, encoder);
 	encoder->possible_crtcs = (1 << unit);
 	encoder->possible_clones = 0;
 
@@ -547,11 +547,11 @@ int vmw_kms_ldu_close_display(struct vmw_private *dev_priv)
 }
 
 
-int vmw_kms_ldu_do_dmabuf_dirty(struct vmw_private *dev_priv,
-				struct vmw_framebuffer *framebuffer,
-				unsigned flags, unsigned color,
-				struct drm_clip_rect *clips,
-				unsigned num_clips, int increment)
+int vmw_kms_ldu_do_bo_dirty(struct vmw_private *dev_priv,
+			    struct vmw_framebuffer *framebuffer,
+			    unsigned int flags, unsigned int color,
+			    struct drm_clip_rect *clips,
+			    unsigned int num_clips, int increment)
 {
 	size_t fifo_size;
 	int i;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_marker.c b/drivers/gpu/drm/vmwgfx/vmwgfx_marker.c
index efd1ffd68185..e53bc639a754 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_marker.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_marker.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright (C) 2010 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2010 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
index d07c585e3c1d..7ed179d30ec5 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2012-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2012-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -225,7 +225,7 @@ static void vmw_takedown_otable_base(struct vmw_private *dev_priv,
 		ret = ttm_bo_reserve(bo, false, true, NULL);
 		BUG_ON(ret != 0);
 
-		vmw_fence_single_bo(bo, NULL);
+		vmw_bo_fence_single(bo, NULL);
 		ttm_bo_unreserve(bo);
 	}
 
@@ -362,7 +362,7 @@ static void vmw_otable_batch_takedown(struct vmw_private *dev_priv,
 	ret = ttm_bo_reserve(bo, false, true, NULL);
 	BUG_ON(ret != 0);
 
-	vmw_fence_single_bo(bo, NULL);
+	vmw_bo_fence_single(bo, NULL);
 	ttm_bo_unreserve(bo);
 
 	ttm_bo_unref(&batch->otable_bo);
@@ -620,7 +620,7 @@ void vmw_mob_unbind(struct vmw_private *dev_priv,
 		vmw_fifo_commit(dev_priv, sizeof(*cmd));
 	}
 	if (bo) {
-		vmw_fence_single_bo(bo, NULL);
+		vmw_bo_fence_single(bo, NULL);
 		ttm_bo_unreserve(bo);
 	}
 	vmw_fifo_resource_dec(dev_priv);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index 21d746bdc922..8b9270f31409 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -1,6 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /*
- * Copyright © 2016 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2016 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -31,6 +31,7 @@
 #include <linux/frame.h>
 #include <asm/hypervisor.h>
 #include <drm/drmP.h>
+#include "vmwgfx_drv.h"
 #include "vmwgfx_msg.h"
 
 
@@ -234,7 +235,7 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg,
 
 		if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0 ||
 		    (HIGH_WORD(ecx) & MESSAGE_STATUS_HB) == 0) {
-			DRM_ERROR("Failed to get reply size\n");
+			DRM_ERROR("Failed to get reply size for host message.\n");
 			return -EINVAL;
 		}
 
@@ -245,7 +246,7 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg,
 		reply_len = ebx;
 		reply     = kzalloc(reply_len + 1, GFP_KERNEL);
 		if (!reply) {
-			DRM_ERROR("Cannot allocate memory for reply\n");
+			DRM_ERROR("Cannot allocate memory for host message reply.\n");
 			return -ENOMEM;
 		}
 
@@ -338,7 +339,8 @@ int vmw_host_get_guestinfo(const char *guest_info_param,
 
 	msg = kasprintf(GFP_KERNEL, "info-get %s", guest_info_param);
 	if (!msg) {
-		DRM_ERROR("Cannot allocate memory to get %s", guest_info_param);
+		DRM_ERROR("Cannot allocate memory to get guest info \"%s\".",
+			  guest_info_param);
 		return -ENOMEM;
 	}
 
@@ -374,7 +376,7 @@ out_msg:
 out_open:
 	*length = 0;
 	kfree(msg);
-	DRM_ERROR("Failed to get %s", guest_info_param);
+	DRM_ERROR("Failed to get guest info \"%s\".", guest_info_param);
 
 	return -EINVAL;
 }
@@ -403,7 +405,7 @@ int vmw_host_log(const char *log)
 
 	msg = kasprintf(GFP_KERNEL, "log %s", log);
 	if (!msg) {
-		DRM_ERROR("Cannot allocate memory for log message\n");
+		DRM_ERROR("Cannot allocate memory for host log message.\n");
 		return -ENOMEM;
 	}
 
@@ -422,7 +424,7 @@ out_msg:
 	vmw_close_channel(&channel);
 out_open:
 	kfree(msg);
-	DRM_ERROR("Failed to send log\n");
+	DRM_ERROR("Failed to send host log message.\n");
 
 	return -EINVAL;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h
index 8545488aa0cf..4907e50fb20a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h
@@ -1,16 +1,29 @@
-/*
- * Copyright (C) 2016, VMware, Inc.
+/* SPDX-License-Identifier: GPL-2.0+ OR MIT */
+/**************************************************************************
+ *
+ * Copyright 2016 VMware, Inc., Palo Alto, CA., USA
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
  *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
+ **************************************************************************
  *
  * Based on code from vmware.c and vmmouse.c.
  * Author:
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
index 222c9c2123a1..9f1b9d289bec 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2014 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2014 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -38,7 +38,7 @@
 #define VMW_OVERLAY_CAP_MASK (SVGA_FIFO_CAP_VIDEO | SVGA_FIFO_CAP_ESCAPE)
 
 struct vmw_stream {
-	struct vmw_dma_buffer *buf;
+	struct vmw_buffer_object *buf;
 	bool claimed;
 	bool paused;
 	struct drm_vmw_control_stream_arg saved;
@@ -94,7 +94,7 @@ static inline void fill_flush(struct vmw_escape_video_flush *cmd,
  * -ERESTARTSYS if interrupted by a signal.
  */
 static int vmw_overlay_send_put(struct vmw_private *dev_priv,
-				struct vmw_dma_buffer *buf,
+				struct vmw_buffer_object *buf,
 				struct drm_vmw_control_stream_arg *arg,
 				bool interruptible)
 {
@@ -225,16 +225,16 @@ static int vmw_overlay_send_stop(struct vmw_private *dev_priv,
  * used with GMRs instead of being locked to vram.
  */
 static int vmw_overlay_move_buffer(struct vmw_private *dev_priv,
-				   struct vmw_dma_buffer *buf,
+				   struct vmw_buffer_object *buf,
 				   bool pin, bool inter)
 {
 	if (!pin)
-		return vmw_dmabuf_unpin(dev_priv, buf, inter);
+		return vmw_bo_unpin(dev_priv, buf, inter);
 
 	if (dev_priv->active_display_unit == vmw_du_legacy)
-		return vmw_dmabuf_pin_in_vram(dev_priv, buf, inter);
+		return vmw_bo_pin_in_vram(dev_priv, buf, inter);
 
-	return vmw_dmabuf_pin_in_vram_or_gmr(dev_priv, buf, inter);
+	return vmw_bo_pin_in_vram_or_gmr(dev_priv, buf, inter);
 }
 
 /**
@@ -278,7 +278,7 @@ static int vmw_overlay_stop(struct vmw_private *dev_priv,
 	}
 
 	if (!pause) {
-		vmw_dmabuf_unreference(&stream->buf);
+		vmw_bo_unreference(&stream->buf);
 		stream->paused = false;
 	} else {
 		stream->paused = true;
@@ -297,7 +297,7 @@ static int vmw_overlay_stop(struct vmw_private *dev_priv,
  * -ERESTARTSYS if interrupted.
  */
 static int vmw_overlay_update_stream(struct vmw_private *dev_priv,
-				     struct vmw_dma_buffer *buf,
+				     struct vmw_buffer_object *buf,
 				     struct drm_vmw_control_stream_arg *arg,
 				     bool interruptible)
 {
@@ -347,7 +347,7 @@ static int vmw_overlay_update_stream(struct vmw_private *dev_priv,
 	}
 
 	if (stream->buf != buf)
-		stream->buf = vmw_dmabuf_reference(buf);
+		stream->buf = vmw_bo_reference(buf);
 	stream->saved = *arg;
 	/* stream is no longer stopped/paused */
 	stream->paused = false;
@@ -466,7 +466,7 @@ int vmw_overlay_ioctl(struct drm_device *dev, void *data,
 	struct vmw_overlay *overlay = dev_priv->overlay_priv;
 	struct drm_vmw_control_stream_arg *arg =
 	    (struct drm_vmw_control_stream_arg *)data;
-	struct vmw_dma_buffer *buf;
+	struct vmw_buffer_object *buf;
 	struct vmw_resource *res;
 	int ret;
 
@@ -484,13 +484,13 @@ int vmw_overlay_ioctl(struct drm_device *dev, void *data,
 		goto out_unlock;
 	}
 
-	ret = vmw_user_dmabuf_lookup(tfile, arg->handle, &buf, NULL);
+	ret = vmw_user_bo_lookup(tfile, arg->handle, &buf, NULL);
 	if (ret)
 		goto out_unlock;
 
 	ret = vmw_overlay_update_stream(dev_priv, buf, arg, true);
 
-	vmw_dmabuf_unreference(&buf);
+	vmw_bo_unreference(&buf);
 
 out_unlock:
 	mutex_unlock(&overlay->mutex);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
index 0d42a46521fc..0861c821a7fe 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2013 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2013 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -40,7 +40,6 @@
  */
 
 static int vmw_prime_map_attach(struct dma_buf *dma_buf,
-				struct device *target_dev,
 				struct dma_buf_attachment *attach)
 {
 	return -ENOSYS;
@@ -72,17 +71,6 @@ static void vmw_prime_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
 {
 }
 
-static void *vmw_prime_dmabuf_kmap_atomic(struct dma_buf *dma_buf,
-		unsigned long page_num)
-{
-	return NULL;
-}
-
-static void vmw_prime_dmabuf_kunmap_atomic(struct dma_buf *dma_buf,
-		unsigned long page_num, void *addr)
-{
-
-}
 static void *vmw_prime_dmabuf_kmap(struct dma_buf *dma_buf,
 		unsigned long page_num)
 {
@@ -109,9 +97,7 @@ const struct dma_buf_ops vmw_prime_dmabuf_ops =  {
 	.unmap_dma_buf = vmw_prime_unmap_dma_buf,
 	.release = NULL,
 	.map = vmw_prime_dmabuf_kmap,
-	.map_atomic = vmw_prime_dmabuf_kmap_atomic,
 	.unmap = vmw_prime_dmabuf_kunmap,
-	.unmap_atomic = vmw_prime_dmabuf_kunmap_atomic,
 	.mmap = vmw_prime_dmabuf_mmap,
 	.vmap = vmw_prime_dmabuf_vmap,
 	.vunmap = vmw_prime_dmabuf_vunmap,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_reg.h b/drivers/gpu/drm/vmwgfx/vmwgfx_reg.h
index dce798053a96..e99f6cdbb091 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_reg.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_reg.h
@@ -1,7 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
- * Copyright © 2009-2014 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2014 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 6b3a942b18df..92003ea5a219 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -27,7 +27,6 @@
 
 #include "vmwgfx_drv.h"
 #include <drm/vmwgfx_drm.h>
-#include <drm/ttm/ttm_object.h>
 #include <drm/ttm/ttm_placement.h>
 #include <drm/drmP.h>
 #include "vmwgfx_resource_priv.h"
@@ -35,29 +34,6 @@
 
 #define VMW_RES_EVICT_ERR_COUNT 10
 
-struct vmw_user_dma_buffer {
-	struct ttm_prime_object prime;
-	struct vmw_dma_buffer dma;
-};
-
-struct vmw_bo_user_rep {
-	uint32_t handle;
-	uint64_t map_handle;
-};
-
-static inline struct vmw_dma_buffer *
-vmw_dma_buffer(struct ttm_buffer_object *bo)
-{
-	return container_of(bo, struct vmw_dma_buffer, base);
-}
-
-static inline struct vmw_user_dma_buffer *
-vmw_user_dma_buffer(struct ttm_buffer_object *bo)
-{
-	struct vmw_dma_buffer *vmw_bo = vmw_dma_buffer(bo);
-	return container_of(vmw_bo, struct vmw_user_dma_buffer, dma);
-}
-
 struct vmw_resource *vmw_resource_reference(struct vmw_resource *res)
 {
 	kref_get(&res->kref);
@@ -116,7 +92,7 @@ static void vmw_resource_release(struct kref *kref)
 		res->backup_dirty = false;
 		list_del_init(&res->mob_head);
 		ttm_bo_unreserve(bo);
-		vmw_dmabuf_unreference(&res->backup);
+		vmw_bo_unreference(&res->backup);
 	}
 
 	if (likely(res->hw_destroy != NULL)) {
@@ -287,7 +263,7 @@ out_bad_resource:
 }
 
 /**
- * Helper function that looks either a surface or dmabuf.
+ * Helper function that looks either a surface or bo.
  *
  * The pointer this pointed at by out_surf and out_buf needs to be null.
  */
@@ -295,7 +271,7 @@ int vmw_user_lookup_handle(struct vmw_private *dev_priv,
 			   struct ttm_object_file *tfile,
 			   uint32_t handle,
 			   struct vmw_surface **out_surf,
-			   struct vmw_dma_buffer **out_buf)
+			   struct vmw_buffer_object **out_buf)
 {
 	struct vmw_resource *res;
 	int ret;
@@ -311,513 +287,11 @@ int vmw_user_lookup_handle(struct vmw_private *dev_priv,
 	}
 
 	*out_surf = NULL;
-	ret = vmw_user_dmabuf_lookup(tfile, handle, out_buf, NULL);
+	ret = vmw_user_bo_lookup(tfile, handle, out_buf, NULL);
 	return ret;
 }
 
 /**
- * Buffer management.
- */
-
-/**
- * vmw_dmabuf_acc_size - Calculate the pinned memory usage of buffers
- *
- * @dev_priv: Pointer to a struct vmw_private identifying the device.
- * @size: The requested buffer size.
- * @user: Whether this is an ordinary dma buffer or a user dma buffer.
- */
-static size_t vmw_dmabuf_acc_size(struct vmw_private *dev_priv, size_t size,
-				  bool user)
-{
-	static size_t struct_size, user_struct_size;
-	size_t num_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	size_t page_array_size = ttm_round_pot(num_pages * sizeof(void *));
-
-	if (unlikely(struct_size == 0)) {
-		size_t backend_size = ttm_round_pot(vmw_tt_size);
-
-		struct_size = backend_size +
-			ttm_round_pot(sizeof(struct vmw_dma_buffer));
-		user_struct_size = backend_size +
-			ttm_round_pot(sizeof(struct vmw_user_dma_buffer));
-	}
-
-	if (dev_priv->map_mode == vmw_dma_alloc_coherent)
-		page_array_size +=
-			ttm_round_pot(num_pages * sizeof(dma_addr_t));
-
-	return ((user) ? user_struct_size : struct_size) +
-		page_array_size;
-}
-
-void vmw_dmabuf_bo_free(struct ttm_buffer_object *bo)
-{
-	struct vmw_dma_buffer *vmw_bo = vmw_dma_buffer(bo);
-
-	vmw_dma_buffer_unmap(vmw_bo);
-	kfree(vmw_bo);
-}
-
-static void vmw_user_dmabuf_destroy(struct ttm_buffer_object *bo)
-{
-	struct vmw_user_dma_buffer *vmw_user_bo = vmw_user_dma_buffer(bo);
-
-	vmw_dma_buffer_unmap(&vmw_user_bo->dma);
-	ttm_prime_object_kfree(vmw_user_bo, prime);
-}
-
-int vmw_dmabuf_init(struct vmw_private *dev_priv,
-		    struct vmw_dma_buffer *vmw_bo,
-		    size_t size, struct ttm_placement *placement,
-		    bool interruptible,
-		    void (*bo_free) (struct ttm_buffer_object *bo))
-{
-	struct ttm_bo_device *bdev = &dev_priv->bdev;
-	size_t acc_size;
-	int ret;
-	bool user = (bo_free == &vmw_user_dmabuf_destroy);
-
-	BUG_ON(!bo_free && (!user && (bo_free != vmw_dmabuf_bo_free)));
-
-	acc_size = vmw_dmabuf_acc_size(dev_priv, size, user);
-	memset(vmw_bo, 0, sizeof(*vmw_bo));
-
-	INIT_LIST_HEAD(&vmw_bo->res_list);
-
-	ret = ttm_bo_init(bdev, &vmw_bo->base, size,
-			  ttm_bo_type_device, placement,
-			  0, interruptible, acc_size,
-			  NULL, NULL, bo_free);
-	return ret;
-}
-
-static void vmw_user_dmabuf_release(struct ttm_base_object **p_base)
-{
-	struct vmw_user_dma_buffer *vmw_user_bo;
-	struct ttm_base_object *base = *p_base;
-	struct ttm_buffer_object *bo;
-
-	*p_base = NULL;
-
-	if (unlikely(base == NULL))
-		return;
-
-	vmw_user_bo = container_of(base, struct vmw_user_dma_buffer,
-				   prime.base);
-	bo = &vmw_user_bo->dma.base;
-	ttm_bo_unref(&bo);
-}
-
-static void vmw_user_dmabuf_ref_obj_release(struct ttm_base_object *base,
-					    enum ttm_ref_type ref_type)
-{
-	struct vmw_user_dma_buffer *user_bo;
-	user_bo = container_of(base, struct vmw_user_dma_buffer, prime.base);
-
-	switch (ref_type) {
-	case TTM_REF_SYNCCPU_WRITE:
-		ttm_bo_synccpu_write_release(&user_bo->dma.base);
-		break;
-	default:
-		BUG();
-	}
-}
-
-/**
- * vmw_user_dmabuf_alloc - Allocate a user dma buffer
- *
- * @dev_priv: Pointer to a struct device private.
- * @tfile: Pointer to a struct ttm_object_file on which to register the user
- * object.
- * @size: Size of the dma buffer.
- * @shareable: Boolean whether the buffer is shareable with other open files.
- * @handle: Pointer to where the handle value should be assigned.
- * @p_dma_buf: Pointer to where the refcounted struct vmw_dma_buffer pointer
- * should be assigned.
- */
-int vmw_user_dmabuf_alloc(struct vmw_private *dev_priv,
-			  struct ttm_object_file *tfile,
-			  uint32_t size,
-			  bool shareable,
-			  uint32_t *handle,
-			  struct vmw_dma_buffer **p_dma_buf,
-			  struct ttm_base_object **p_base)
-{
-	struct vmw_user_dma_buffer *user_bo;
-	struct ttm_buffer_object *tmp;
-	int ret;
-
-	user_bo = kzalloc(sizeof(*user_bo), GFP_KERNEL);
-	if (unlikely(!user_bo)) {
-		DRM_ERROR("Failed to allocate a buffer.\n");
-		return -ENOMEM;
-	}
-
-	ret = vmw_dmabuf_init(dev_priv, &user_bo->dma, size,
-			      (dev_priv->has_mob) ?
-			      &vmw_sys_placement :
-			      &vmw_vram_sys_placement, true,
-			      &vmw_user_dmabuf_destroy);
-	if (unlikely(ret != 0))
-		return ret;
-
-	tmp = ttm_bo_reference(&user_bo->dma.base);
-	ret = ttm_prime_object_init(tfile,
-				    size,
-				    &user_bo->prime,
-				    shareable,
-				    ttm_buffer_type,
-				    &vmw_user_dmabuf_release,
-				    &vmw_user_dmabuf_ref_obj_release);
-	if (unlikely(ret != 0)) {
-		ttm_bo_unref(&tmp);
-		goto out_no_base_object;
-	}
-
-	*p_dma_buf = &user_bo->dma;
-	if (p_base) {
-		*p_base = &user_bo->prime.base;
-		kref_get(&(*p_base)->refcount);
-	}
-	*handle = user_bo->prime.base.hash.key;
-
-out_no_base_object:
-	return ret;
-}
-
-/**
- * vmw_user_dmabuf_verify_access - verify access permissions on this
- * buffer object.
- *
- * @bo: Pointer to the buffer object being accessed
- * @tfile: Identifying the caller.
- */
-int vmw_user_dmabuf_verify_access(struct ttm_buffer_object *bo,
-				  struct ttm_object_file *tfile)
-{
-	struct vmw_user_dma_buffer *vmw_user_bo;
-
-	if (unlikely(bo->destroy != vmw_user_dmabuf_destroy))
-		return -EPERM;
-
-	vmw_user_bo = vmw_user_dma_buffer(bo);
-
-	/* Check that the caller has opened the object. */
-	if (likely(ttm_ref_object_exists(tfile, &vmw_user_bo->prime.base)))
-		return 0;
-
-	DRM_ERROR("Could not grant buffer access.\n");
-	return -EPERM;
-}
-
-/**
- * vmw_user_dmabuf_synccpu_grab - Grab a struct vmw_user_dma_buffer for cpu
- * access, idling previous GPU operations on the buffer and optionally
- * blocking it for further command submissions.
- *
- * @user_bo: Pointer to the buffer object being grabbed for CPU access
- * @tfile: Identifying the caller.
- * @flags: Flags indicating how the grab should be performed.
- *
- * A blocking grab will be automatically released when @tfile is closed.
- */
-static int vmw_user_dmabuf_synccpu_grab(struct vmw_user_dma_buffer *user_bo,
-					struct ttm_object_file *tfile,
-					uint32_t flags)
-{
-	struct ttm_buffer_object *bo = &user_bo->dma.base;
-	bool existed;
-	int ret;
-
-	if (flags & drm_vmw_synccpu_allow_cs) {
-		bool nonblock = !!(flags & drm_vmw_synccpu_dontblock);
-		long lret;
-
-		lret = reservation_object_wait_timeout_rcu(bo->resv, true, true,
-							   nonblock ? 0 : MAX_SCHEDULE_TIMEOUT);
-		if (!lret)
-			return -EBUSY;
-		else if (lret < 0)
-			return lret;
-		return 0;
-	}
-
-	ret = ttm_bo_synccpu_write_grab
-		(bo, !!(flags & drm_vmw_synccpu_dontblock));
-	if (unlikely(ret != 0))
-		return ret;
-
-	ret = ttm_ref_object_add(tfile, &user_bo->prime.base,
-				 TTM_REF_SYNCCPU_WRITE, &existed, false);
-	if (ret != 0 || existed)
-		ttm_bo_synccpu_write_release(&user_bo->dma.base);
-
-	return ret;
-}
-
-/**
- * vmw_user_dmabuf_synccpu_release - Release a previous grab for CPU access,
- * and unblock command submission on the buffer if blocked.
- *
- * @handle: Handle identifying the buffer object.
- * @tfile: Identifying the caller.
- * @flags: Flags indicating the type of release.
- */
-static int vmw_user_dmabuf_synccpu_release(uint32_t handle,
-					   struct ttm_object_file *tfile,
-					   uint32_t flags)
-{
-	if (!(flags & drm_vmw_synccpu_allow_cs))
-		return ttm_ref_object_base_unref(tfile, handle,
-						 TTM_REF_SYNCCPU_WRITE);
-
-	return 0;
-}
-
-/**
- * vmw_user_dmabuf_synccpu_release - ioctl function implementing the synccpu
- * functionality.
- *
- * @dev: Identifies the drm device.
- * @data: Pointer to the ioctl argument.
- * @file_priv: Identifies the caller.
- *
- * This function checks the ioctl arguments for validity and calls the
- * relevant synccpu functions.
- */
-int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data,
-				  struct drm_file *file_priv)
-{
-	struct drm_vmw_synccpu_arg *arg =
-		(struct drm_vmw_synccpu_arg *) data;
-	struct vmw_dma_buffer *dma_buf;
-	struct vmw_user_dma_buffer *user_bo;
-	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
-	struct ttm_base_object *buffer_base;
-	int ret;
-
-	if ((arg->flags & (drm_vmw_synccpu_read | drm_vmw_synccpu_write)) == 0
-	    || (arg->flags & ~(drm_vmw_synccpu_read | drm_vmw_synccpu_write |
-			       drm_vmw_synccpu_dontblock |
-			       drm_vmw_synccpu_allow_cs)) != 0) {
-		DRM_ERROR("Illegal synccpu flags.\n");
-		return -EINVAL;
-	}
-
-	switch (arg->op) {
-	case drm_vmw_synccpu_grab:
-		ret = vmw_user_dmabuf_lookup(tfile, arg->handle, &dma_buf,
-					     &buffer_base);
-		if (unlikely(ret != 0))
-			return ret;
-
-		user_bo = container_of(dma_buf, struct vmw_user_dma_buffer,
-				       dma);
-		ret = vmw_user_dmabuf_synccpu_grab(user_bo, tfile, arg->flags);
-		vmw_dmabuf_unreference(&dma_buf);
-		ttm_base_object_unref(&buffer_base);
-		if (unlikely(ret != 0 && ret != -ERESTARTSYS &&
-			     ret != -EBUSY)) {
-			DRM_ERROR("Failed synccpu grab on handle 0x%08x.\n",
-				  (unsigned int) arg->handle);
-			return ret;
-		}
-		break;
-	case drm_vmw_synccpu_release:
-		ret = vmw_user_dmabuf_synccpu_release(arg->handle, tfile,
-						      arg->flags);
-		if (unlikely(ret != 0)) {
-			DRM_ERROR("Failed synccpu release on handle 0x%08x.\n",
-				  (unsigned int) arg->handle);
-			return ret;
-		}
-		break;
-	default:
-		DRM_ERROR("Invalid synccpu operation.\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-int vmw_dmabuf_alloc_ioctl(struct drm_device *dev, void *data,
-			   struct drm_file *file_priv)
-{
-	struct vmw_private *dev_priv = vmw_priv(dev);
-	union drm_vmw_alloc_dmabuf_arg *arg =
-	    (union drm_vmw_alloc_dmabuf_arg *)data;
-	struct drm_vmw_alloc_dmabuf_req *req = &arg->req;
-	struct drm_vmw_dmabuf_rep *rep = &arg->rep;
-	struct vmw_dma_buffer *dma_buf;
-	uint32_t handle;
-	int ret;
-
-	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
-	if (unlikely(ret != 0))
-		return ret;
-
-	ret = vmw_user_dmabuf_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
-				    req->size, false, &handle, &dma_buf,
-				    NULL);
-	if (unlikely(ret != 0))
-		goto out_no_dmabuf;
-
-	rep->handle = handle;
-	rep->map_handle = drm_vma_node_offset_addr(&dma_buf->base.vma_node);
-	rep->cur_gmr_id = handle;
-	rep->cur_gmr_offset = 0;
-
-	vmw_dmabuf_unreference(&dma_buf);
-
-out_no_dmabuf:
-	ttm_read_unlock(&dev_priv->reservation_sem);
-
-	return ret;
-}
-
-int vmw_dmabuf_unref_ioctl(struct drm_device *dev, void *data,
-			   struct drm_file *file_priv)
-{
-	struct drm_vmw_unref_dmabuf_arg *arg =
-	    (struct drm_vmw_unref_dmabuf_arg *)data;
-
-	return ttm_ref_object_base_unref(vmw_fpriv(file_priv)->tfile,
-					 arg->handle,
-					 TTM_REF_USAGE);
-}
-
-int vmw_user_dmabuf_lookup(struct ttm_object_file *tfile,
-			   uint32_t handle, struct vmw_dma_buffer **out,
-			   struct ttm_base_object **p_base)
-{
-	struct vmw_user_dma_buffer *vmw_user_bo;
-	struct ttm_base_object *base;
-
-	base = ttm_base_object_lookup(tfile, handle);
-	if (unlikely(base == NULL)) {
-		pr_err("Invalid buffer object handle 0x%08lx\n",
-		       (unsigned long)handle);
-		return -ESRCH;
-	}
-
-	if (unlikely(ttm_base_object_type(base) != ttm_buffer_type)) {
-		ttm_base_object_unref(&base);
-		pr_err("Invalid buffer object handle 0x%08lx\n",
-		       (unsigned long)handle);
-		return -EINVAL;
-	}
-
-	vmw_user_bo = container_of(base, struct vmw_user_dma_buffer,
-				   prime.base);
-	(void)ttm_bo_reference(&vmw_user_bo->dma.base);
-	if (p_base)
-		*p_base = base;
-	else
-		ttm_base_object_unref(&base);
-	*out = &vmw_user_bo->dma;
-
-	return 0;
-}
-
-int vmw_user_dmabuf_reference(struct ttm_object_file *tfile,
-			      struct vmw_dma_buffer *dma_buf,
-			      uint32_t *handle)
-{
-	struct vmw_user_dma_buffer *user_bo;
-
-	if (dma_buf->base.destroy != vmw_user_dmabuf_destroy)
-		return -EINVAL;
-
-	user_bo = container_of(dma_buf, struct vmw_user_dma_buffer, dma);
-
-	*handle = user_bo->prime.base.hash.key;
-	return ttm_ref_object_add(tfile, &user_bo->prime.base,
-				  TTM_REF_USAGE, NULL, false);
-}
-
-/**
- * vmw_dumb_create - Create a dumb kms buffer
- *
- * @file_priv: Pointer to a struct drm_file identifying the caller.
- * @dev: Pointer to the drm device.
- * @args: Pointer to a struct drm_mode_create_dumb structure
- *
- * This is a driver callback for the core drm create_dumb functionality.
- * Note that this is very similar to the vmw_dmabuf_alloc ioctl, except
- * that the arguments have a different format.
- */
-int vmw_dumb_create(struct drm_file *file_priv,
-		    struct drm_device *dev,
-		    struct drm_mode_create_dumb *args)
-{
-	struct vmw_private *dev_priv = vmw_priv(dev);
-	struct vmw_dma_buffer *dma_buf;
-	int ret;
-
-	args->pitch = args->width * ((args->bpp + 7) / 8);
-	args->size = args->pitch * args->height;
-
-	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
-	if (unlikely(ret != 0))
-		return ret;
-
-	ret = vmw_user_dmabuf_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
-				    args->size, false, &args->handle,
-				    &dma_buf, NULL);
-	if (unlikely(ret != 0))
-		goto out_no_dmabuf;
-
-	vmw_dmabuf_unreference(&dma_buf);
-out_no_dmabuf:
-	ttm_read_unlock(&dev_priv->reservation_sem);
-	return ret;
-}
-
-/**
- * vmw_dumb_map_offset - Return the address space offset of a dumb buffer
- *
- * @file_priv: Pointer to a struct drm_file identifying the caller.
- * @dev: Pointer to the drm device.
- * @handle: Handle identifying the dumb buffer.
- * @offset: The address space offset returned.
- *
- * This is a driver callback for the core drm dumb_map_offset functionality.
- */
-int vmw_dumb_map_offset(struct drm_file *file_priv,
-			struct drm_device *dev, uint32_t handle,
-			uint64_t *offset)
-{
-	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
-	struct vmw_dma_buffer *out_buf;
-	int ret;
-
-	ret = vmw_user_dmabuf_lookup(tfile, handle, &out_buf, NULL);
-	if (ret != 0)
-		return -EINVAL;
-
-	*offset = drm_vma_node_offset_addr(&out_buf->base.vma_node);
-	vmw_dmabuf_unreference(&out_buf);
-	return 0;
-}
-
-/**
- * vmw_dumb_destroy - Destroy a dumb boffer
- *
- * @file_priv: Pointer to a struct drm_file identifying the caller.
- * @dev: Pointer to the drm device.
- * @handle: Handle identifying the dumb buffer.
- *
- * This is a driver callback for the core drm dumb_destroy functionality.
- */
-int vmw_dumb_destroy(struct drm_file *file_priv,
-		     struct drm_device *dev,
-		     uint32_t handle)
-{
-	return ttm_ref_object_base_unref(vmw_fpriv(file_priv)->tfile,
-					 handle, TTM_REF_USAGE);
-}
-
-/**
  * vmw_resource_buf_alloc - Allocate a backup buffer for a resource.
  *
  * @res:            The resource for which to allocate a backup buffer.
@@ -829,7 +303,7 @@ static int vmw_resource_buf_alloc(struct vmw_resource *res,
 {
 	unsigned long size =
 		(res->backup_size + PAGE_SIZE - 1) & PAGE_MASK;
-	struct vmw_dma_buffer *backup;
+	struct vmw_buffer_object *backup;
 	int ret;
 
 	if (likely(res->backup)) {
@@ -841,16 +315,16 @@ static int vmw_resource_buf_alloc(struct vmw_resource *res,
 	if (unlikely(!backup))
 		return -ENOMEM;
 
-	ret = vmw_dmabuf_init(res->dev_priv, backup, res->backup_size,
+	ret = vmw_bo_init(res->dev_priv, backup, res->backup_size,
 			      res->func->backup_placement,
 			      interruptible,
-			      &vmw_dmabuf_bo_free);
+			      &vmw_bo_bo_free);
 	if (unlikely(ret != 0))
-		goto out_no_dmabuf;
+		goto out_no_bo;
 
 	res->backup = backup;
 
-out_no_dmabuf:
+out_no_bo:
 	return ret;
 }
 
@@ -919,7 +393,7 @@ out_bind_failed:
  */
 void vmw_resource_unreserve(struct vmw_resource *res,
 			    bool switch_backup,
-			    struct vmw_dma_buffer *new_backup,
+			    struct vmw_buffer_object *new_backup,
 			    unsigned long new_backup_offset)
 {
 	struct vmw_private *dev_priv = res->dev_priv;
@@ -931,11 +405,11 @@ void vmw_resource_unreserve(struct vmw_resource *res,
 		if (res->backup) {
 			lockdep_assert_held(&res->backup->base.resv->lock.base);
 			list_del_init(&res->mob_head);
-			vmw_dmabuf_unreference(&res->backup);
+			vmw_bo_unreference(&res->backup);
 		}
 
 		if (new_backup) {
-			res->backup = vmw_dmabuf_reference(new_backup);
+			res->backup = vmw_bo_reference(new_backup);
 			lockdep_assert_held(&new_backup->base.resv->lock.base);
 			list_add_tail(&res->mob_head, &new_backup->res_list);
 		} else {
@@ -959,6 +433,7 @@ void vmw_resource_unreserve(struct vmw_resource *res,
  *                             for a resource and in that case, allocate
  *                             one, reserve and validate it.
  *
+ * @ticket:         The ww aqcquire context to use, or NULL if trylocking.
  * @res:            The resource for which to allocate a backup buffer.
  * @interruptible:  Whether any sleeps during allocation should be
  *                  performed while interruptible.
@@ -966,7 +441,8 @@ void vmw_resource_unreserve(struct vmw_resource *res,
  *                  reserved and validated backup buffer.
  */
 static int
-vmw_resource_check_buffer(struct vmw_resource *res,
+vmw_resource_check_buffer(struct ww_acquire_ctx *ticket,
+			  struct vmw_resource *res,
 			  bool interruptible,
 			  struct ttm_validate_buffer *val_buf)
 {
@@ -985,7 +461,7 @@ vmw_resource_check_buffer(struct vmw_resource *res,
 	val_buf->bo = ttm_bo_reference(&res->backup->base);
 	val_buf->shared = false;
 	list_add_tail(&val_buf->head, &val_list);
-	ret = ttm_eu_reserve_buffers(NULL, &val_list, interruptible, NULL);
+	ret = ttm_eu_reserve_buffers(ticket, &val_list, interruptible, NULL);
 	if (unlikely(ret != 0))
 		goto out_no_reserve;
 
@@ -1003,11 +479,11 @@ vmw_resource_check_buffer(struct vmw_resource *res,
 	return 0;
 
 out_no_validate:
-	ttm_eu_backoff_reservation(NULL, &val_list);
+	ttm_eu_backoff_reservation(ticket, &val_list);
 out_no_reserve:
 	ttm_bo_unref(&val_buf->bo);
 	if (backup_dirty)
-		vmw_dmabuf_unreference(&res->backup);
+		vmw_bo_unreference(&res->backup);
 
 	return ret;
 }
@@ -1050,10 +526,12 @@ int vmw_resource_reserve(struct vmw_resource *res, bool interruptible,
  * vmw_resource_backoff_reservation - Unreserve and unreference a
  *                                    backup buffer
  *.
+ * @ticket:         The ww acquire ctx used for reservation.
  * @val_buf:        Backup buffer information.
  */
 static void
-vmw_resource_backoff_reservation(struct ttm_validate_buffer *val_buf)
+vmw_resource_backoff_reservation(struct ww_acquire_ctx *ticket,
+				 struct ttm_validate_buffer *val_buf)
 {
 	struct list_head val_list;
 
@@ -1062,7 +540,7 @@ vmw_resource_backoff_reservation(struct ttm_validate_buffer *val_buf)
 
 	INIT_LIST_HEAD(&val_list);
 	list_add_tail(&val_buf->head, &val_list);
-	ttm_eu_backoff_reservation(NULL, &val_list);
+	ttm_eu_backoff_reservation(ticket, &val_list);
 	ttm_bo_unref(&val_buf->bo);
 }
 
@@ -1070,10 +548,12 @@ vmw_resource_backoff_reservation(struct ttm_validate_buffer *val_buf)
  * vmw_resource_do_evict - Evict a resource, and transfer its data
  *                         to a backup buffer.
  *
+ * @ticket:         The ww acquire ticket to use, or NULL if trylocking.
  * @res:            The resource to evict.
  * @interruptible:  Whether to wait interruptible.
  */
-static int vmw_resource_do_evict(struct vmw_resource *res, bool interruptible)
+static int vmw_resource_do_evict(struct ww_acquire_ctx *ticket,
+				 struct vmw_resource *res, bool interruptible)
 {
 	struct ttm_validate_buffer val_buf;
 	const struct vmw_res_func *func = res->func;
@@ -1083,7 +563,7 @@ static int vmw_resource_do_evict(struct vmw_resource *res, bool interruptible)
 
 	val_buf.bo = NULL;
 	val_buf.shared = false;
-	ret = vmw_resource_check_buffer(res, interruptible, &val_buf);
+	ret = vmw_resource_check_buffer(ticket, res, interruptible, &val_buf);
 	if (unlikely(ret != 0))
 		return ret;
 
@@ -1098,7 +578,7 @@ static int vmw_resource_do_evict(struct vmw_resource *res, bool interruptible)
 	res->backup_dirty = true;
 	res->res_dirty = false;
 out_no_unbind:
-	vmw_resource_backoff_reservation(&val_buf);
+	vmw_resource_backoff_reservation(ticket, &val_buf);
 
 	return ret;
 }
@@ -1152,7 +632,8 @@ int vmw_resource_validate(struct vmw_resource *res)
 
 		write_unlock(&dev_priv->resource_lock);
 
-		ret = vmw_resource_do_evict(evict_res, true);
+		/* Trylock backup buffers with a NULL ticket. */
+		ret = vmw_resource_do_evict(NULL, evict_res, true);
 		if (unlikely(ret != 0)) {
 			write_lock(&dev_priv->resource_lock);
 			list_add_tail(&evict_res->lru_head, lru_list);
@@ -1171,7 +652,7 @@ int vmw_resource_validate(struct vmw_resource *res)
 		goto out_no_validate;
 	else if (!res->func->needs_backup && res->backup) {
 		list_del_init(&res->mob_head);
-		vmw_dmabuf_unreference(&res->backup);
+		vmw_bo_unreference(&res->backup);
 	}
 
 	return 0;
@@ -1180,109 +661,39 @@ out_no_validate:
 	return ret;
 }
 
-/**
- * vmw_fence_single_bo - Utility function to fence a single TTM buffer
- *                       object without unreserving it.
- *
- * @bo:             Pointer to the struct ttm_buffer_object to fence.
- * @fence:          Pointer to the fence. If NULL, this function will
- *                  insert a fence into the command stream..
- *
- * Contrary to the ttm_eu version of this function, it takes only
- * a single buffer object instead of a list, and it also doesn't
- * unreserve the buffer object, which needs to be done separately.
- */
-void vmw_fence_single_bo(struct ttm_buffer_object *bo,
-			 struct vmw_fence_obj *fence)
-{
-	struct ttm_bo_device *bdev = bo->bdev;
-
-	struct vmw_private *dev_priv =
-		container_of(bdev, struct vmw_private, bdev);
-
-	if (fence == NULL) {
-		vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL);
-		reservation_object_add_excl_fence(bo->resv, &fence->base);
-		dma_fence_put(&fence->base);
-	} else
-		reservation_object_add_excl_fence(bo->resv, &fence->base);
-}
 
 /**
- * vmw_resource_move_notify - TTM move_notify_callback
+ * vmw_resource_unbind_list
  *
- * @bo: The TTM buffer object about to move.
- * @mem: The struct ttm_mem_reg indicating to what memory
- *       region the move is taking place.
+ * @vbo: Pointer to the current backing MOB.
  *
  * Evicts the Guest Backed hardware resource if the backup
  * buffer is being moved out of MOB memory.
- * Note that this function should not race with the resource
- * validation code as long as it accesses only members of struct
- * resource that remain static while bo::res is !NULL and
- * while we have @bo reserved. struct resource::backup is *not* a
- * static member. The resource validation code will take care
- * to set @bo::res to NULL, while having @bo reserved when the
- * buffer is no longer bound to the resource, so @bo:res can be
- * used to determine whether there is a need to unbind and whether
- * it is safe to unbind.
+ * Note that this function will not race with the resource
+ * validation code, since resource validation and eviction
+ * both require the backup buffer to be reserved.
  */
-void vmw_resource_move_notify(struct ttm_buffer_object *bo,
-			      struct ttm_mem_reg *mem)
+void vmw_resource_unbind_list(struct vmw_buffer_object *vbo)
 {
-	struct vmw_dma_buffer *dma_buf;
-
-	if (mem == NULL)
-		return;
-
-	if (bo->destroy != vmw_dmabuf_bo_free &&
-	    bo->destroy != vmw_user_dmabuf_destroy)
-		return;
-
-	dma_buf = container_of(bo, struct vmw_dma_buffer, base);
-
-	/*
-	 * Kill any cached kernel maps before move. An optimization could
-	 * be to do this iff source or destination memory type is VRAM.
-	 */
-	vmw_dma_buffer_unmap(dma_buf);
 
-	if (mem->mem_type != VMW_PL_MOB) {
-		struct vmw_resource *res, *n;
-		struct ttm_validate_buffer val_buf;
+	struct vmw_resource *res, *next;
+	struct ttm_validate_buffer val_buf = {
+		.bo = &vbo->base,
+		.shared = false
+	};
 
-		val_buf.bo = bo;
-		val_buf.shared = false;
+	lockdep_assert_held(&vbo->base.resv->lock.base);
+	list_for_each_entry_safe(res, next, &vbo->res_list, mob_head) {
+		if (!res->func->unbind)
+			continue;
 
-		list_for_each_entry_safe(res, n, &dma_buf->res_list, mob_head) {
-
-			if (unlikely(res->func->unbind == NULL))
-				continue;
-
-			(void) res->func->unbind(res, true, &val_buf);
-			res->backup_dirty = true;
-			res->res_dirty = false;
-			list_del_init(&res->mob_head);
-		}
-
-		(void) ttm_bo_wait(bo, false, false);
+		(void) res->func->unbind(res, true, &val_buf);
+		res->backup_dirty = true;
+		res->res_dirty = false;
+		list_del_init(&res->mob_head);
 	}
-}
-
-
-/**
- * vmw_resource_swap_notify - swapout notify callback.
- *
- * @bo: The buffer object to be swapped out.
- */
-void vmw_resource_swap_notify(struct ttm_buffer_object *bo)
-{
-	if (bo->destroy != vmw_dmabuf_bo_free &&
-	    bo->destroy != vmw_user_dmabuf_destroy)
-		return;
 
-	/* Kill any cached kernel maps before swapout */
-	vmw_dma_buffer_unmap(vmw_dma_buffer(bo));
+	(void) ttm_bo_wait(&vbo->base, false, false);
 }
 
 
@@ -1294,7 +705,7 @@ void vmw_resource_swap_notify(struct ttm_buffer_object *bo)
  * Read back cached states from the device if they exist.  This function
  * assumings binding_mutex is held.
  */
-int vmw_query_readback_all(struct vmw_dma_buffer *dx_query_mob)
+int vmw_query_readback_all(struct vmw_buffer_object *dx_query_mob)
 {
 	struct vmw_resource *dx_query_ctx;
 	struct vmw_private *dev_priv;
@@ -1344,7 +755,7 @@ int vmw_query_readback_all(struct vmw_dma_buffer *dx_query_mob)
 void vmw_query_move_notify(struct ttm_buffer_object *bo,
 			   struct ttm_mem_reg *mem)
 {
-	struct vmw_dma_buffer *dx_query_mob;
+	struct vmw_buffer_object *dx_query_mob;
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct vmw_private *dev_priv;
 
@@ -1353,7 +764,7 @@ void vmw_query_move_notify(struct ttm_buffer_object *bo,
 
 	mutex_lock(&dev_priv->binding_mutex);
 
-	dx_query_mob = container_of(bo, struct vmw_dma_buffer, base);
+	dx_query_mob = container_of(bo, struct vmw_buffer_object, base);
 	if (mem == NULL || !dx_query_mob || !dx_query_mob->dx_query_ctx) {
 		mutex_unlock(&dev_priv->binding_mutex);
 		return;
@@ -1368,7 +779,7 @@ void vmw_query_move_notify(struct ttm_buffer_object *bo,
 
 		/* Create a fence and attach the BO to it */
 		(void) vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL);
-		vmw_fence_single_bo(bo, fence);
+		vmw_bo_fence_single(bo, fence);
 
 		if (fence != NULL)
 			vmw_fence_obj_unreference(&fence);
@@ -1405,6 +816,7 @@ static void vmw_resource_evict_type(struct vmw_private *dev_priv,
 	struct vmw_resource *evict_res;
 	unsigned err_count = 0;
 	int ret;
+	struct ww_acquire_ctx ticket;
 
 	do {
 		write_lock(&dev_priv->resource_lock);
@@ -1418,7 +830,8 @@ static void vmw_resource_evict_type(struct vmw_private *dev_priv,
 		list_del_init(&evict_res->lru_head);
 		write_unlock(&dev_priv->resource_lock);
 
-		ret = vmw_resource_do_evict(evict_res, false);
+		/* Wait lock backup buffers with a ticket. */
+		ret = vmw_resource_do_evict(&ticket, evict_res, false);
 		if (unlikely(ret != 0)) {
 			write_lock(&dev_priv->resource_lock);
 			list_add_tail(&evict_res->lru_head, lru_list);
@@ -1481,7 +894,7 @@ int vmw_resource_pin(struct vmw_resource *res, bool interruptible)
 		goto out_no_reserve;
 
 	if (res->pin_count == 0) {
-		struct vmw_dma_buffer *vbo = NULL;
+		struct vmw_buffer_object *vbo = NULL;
 
 		if (res->backup) {
 			vbo = res->backup;
@@ -1539,7 +952,7 @@ void vmw_resource_unpin(struct vmw_resource *res)
 
 	WARN_ON(res->pin_count == 0);
 	if (--res->pin_count == 0 && res->backup) {
-		struct vmw_dma_buffer *vbo = res->backup;
+		struct vmw_buffer_object *vbo = res->backup;
 
 		(void) ttm_bo_reserve(&vbo->base, false, false, NULL);
 		vmw_bo_pin_reserved(vbo, false);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h
index ac05968a832b..a8c1c5ebd71d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h
@@ -1,7 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
- * Copyright © 2012-2014 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2012-2014 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
index 3d667e903beb..ad0de7f0cd60 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2011-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2011-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -66,7 +66,7 @@ struct vmw_kms_sou_readback_blit {
 	SVGAFifoCmdBlitScreenToGMRFB body;
 };
 
-struct vmw_kms_sou_dmabuf_blit {
+struct vmw_kms_sou_bo_blit {
 	uint32 header;
 	SVGAFifoCmdBlitGMRFBToScreen body;
 };
@@ -83,7 +83,7 @@ struct vmw_screen_object_unit {
 	struct vmw_display_unit base;
 
 	unsigned long buffer_size; /**< Size of allocated buffer */
-	struct vmw_dma_buffer *buffer; /**< Backing store buffer */
+	struct vmw_buffer_object *buffer; /**< Backing store buffer */
 
 	bool defined;
 };
@@ -109,7 +109,7 @@ static void vmw_sou_crtc_destroy(struct drm_crtc *crtc)
  */
 static int vmw_sou_fifo_create(struct vmw_private *dev_priv,
 			       struct vmw_screen_object_unit *sou,
-			       uint32_t x, uint32_t y,
+			       int x, int y,
 			       struct drm_display_mode *mode)
 {
 	size_t fifo_size;
@@ -139,13 +139,8 @@ static int vmw_sou_fifo_create(struct vmw_private *dev_priv,
 		(sou->base.unit == 0 ? SVGA_SCREEN_IS_PRIMARY : 0);
 	cmd->obj.size.width = mode->hdisplay;
 	cmd->obj.size.height = mode->vdisplay;
-	if (sou->base.is_implicit) {
-		cmd->obj.root.x = x;
-		cmd->obj.root.y = y;
-	} else {
-		cmd->obj.root.x = sou->base.gui_x;
-		cmd->obj.root.y = sou->base.gui_y;
-	}
+	cmd->obj.root.x = x;
+	cmd->obj.root.y = y;
 	sou->base.set_gui_x = cmd->obj.root.x;
 	sou->base.set_gui_y = cmd->obj.root.y;
 
@@ -222,12 +217,11 @@ static void vmw_sou_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	struct vmw_plane_state *vps;
 	int ret;
 
-
-	sou      = vmw_crtc_to_sou(crtc);
+	sou = vmw_crtc_to_sou(crtc);
 	dev_priv = vmw_priv(crtc->dev);
-	ps       = crtc->primary->state;
-	fb       = ps->fb;
-	vps      = vmw_plane_state_to_vps(ps);
+	ps = crtc->primary->state;
+	fb = ps->fb;
+	vps = vmw_plane_state_to_vps(ps);
 
 	vfb = (fb) ? vmw_framebuffer_to_vfb(fb) : NULL;
 
@@ -240,11 +234,25 @@ static void vmw_sou_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	}
 
 	if (vfb) {
-		sou->buffer = vps->dmabuf;
-		sou->buffer_size = vps->dmabuf_size;
+		struct drm_connector_state *conn_state;
+		struct vmw_connector_state *vmw_conn_state;
+		int x, y;
+
+		sou->buffer = vps->bo;
+		sou->buffer_size = vps->bo_size;
+
+		if (sou->base.is_implicit) {
+			x = crtc->x;
+			y = crtc->y;
+		} else {
+			conn_state = sou->base.connector.state;
+			vmw_conn_state = vmw_connector_state_to_vcs(conn_state);
+
+			x = vmw_conn_state->gui_x;
+			y = vmw_conn_state->gui_y;
+		}
 
-		ret = vmw_sou_fifo_create(dev_priv, sou, crtc->x, crtc->y,
-					  &crtc->mode);
+		ret = vmw_sou_fifo_create(dev_priv, sou, x, y, &crtc->mode);
 		if (ret)
 			DRM_ERROR("Failed to define Screen Object %dx%d\n",
 				  crtc->x, crtc->y);
@@ -408,10 +416,10 @@ vmw_sou_primary_plane_cleanup_fb(struct drm_plane *plane,
 	struct drm_crtc *crtc = plane->state->crtc ?
 		plane->state->crtc : old_state->crtc;
 
-	if (vps->dmabuf)
-		vmw_dmabuf_unpin(vmw_priv(crtc->dev), vps->dmabuf, false);
-	vmw_dmabuf_unreference(&vps->dmabuf);
-	vps->dmabuf_size = 0;
+	if (vps->bo)
+		vmw_bo_unpin(vmw_priv(crtc->dev), vps->bo, false);
+	vmw_bo_unreference(&vps->bo);
+	vps->bo_size = 0;
 
 	vmw_du_plane_cleanup_fb(plane, old_state);
 }
@@ -440,8 +448,8 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane,
 
 
 	if (!new_fb) {
-		vmw_dmabuf_unreference(&vps->dmabuf);
-		vps->dmabuf_size = 0;
+		vmw_bo_unreference(&vps->bo);
+		vps->bo_size = 0;
 
 		return 0;
 	}
@@ -449,22 +457,22 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane,
 	size = new_state->crtc_w * new_state->crtc_h * 4;
 	dev_priv = vmw_priv(crtc->dev);
 
-	if (vps->dmabuf) {
-		if (vps->dmabuf_size == size) {
+	if (vps->bo) {
+		if (vps->bo_size == size) {
 			/*
 			 * Note that this might temporarily up the pin-count
 			 * to 2, until cleanup_fb() is called.
 			 */
-			return vmw_dmabuf_pin_in_vram(dev_priv, vps->dmabuf,
+			return vmw_bo_pin_in_vram(dev_priv, vps->bo,
 						      true);
 		}
 
-		vmw_dmabuf_unreference(&vps->dmabuf);
-		vps->dmabuf_size = 0;
+		vmw_bo_unreference(&vps->bo);
+		vps->bo_size = 0;
 	}
 
-	vps->dmabuf = kzalloc(sizeof(*vps->dmabuf), GFP_KERNEL);
-	if (!vps->dmabuf)
+	vps->bo = kzalloc(sizeof(*vps->bo), GFP_KERNEL);
+	if (!vps->bo)
 		return -ENOMEM;
 
 	vmw_svga_enable(dev_priv);
@@ -473,22 +481,22 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane,
 	 * resume the overlays, this is preferred to failing to alloc.
 	 */
 	vmw_overlay_pause_all(dev_priv);
-	ret = vmw_dmabuf_init(dev_priv, vps->dmabuf, size,
+	ret = vmw_bo_init(dev_priv, vps->bo, size,
 			      &vmw_vram_ne_placement,
-			      false, &vmw_dmabuf_bo_free);
+			      false, &vmw_bo_bo_free);
 	vmw_overlay_resume_all(dev_priv);
 	if (ret) {
-		vps->dmabuf = NULL; /* vmw_dmabuf_init frees on error */
+		vps->bo = NULL; /* vmw_bo_init frees on error */
 		return ret;
 	}
 
-	vps->dmabuf_size = size;
+	vps->bo_size = size;
 
 	/*
 	 * TTM already thinks the buffer is pinned, but make sure the
 	 * pin_count is upped.
 	 */
-	return vmw_dmabuf_pin_in_vram(dev_priv, vps->dmabuf, true);
+	return vmw_bo_pin_in_vram(dev_priv, vps->bo, true);
 }
 
 
@@ -512,10 +520,10 @@ vmw_sou_primary_plane_atomic_update(struct drm_plane *plane,
 		vclips.w = crtc->mode.hdisplay;
 		vclips.h = crtc->mode.vdisplay;
 
-		if (vfb->dmabuf)
-			ret = vmw_kms_sou_do_dmabuf_dirty(dev_priv, vfb, NULL,
-							  &vclips, 1, 1, true,
-							  &fence, crtc);
+		if (vfb->bo)
+			ret = vmw_kms_sou_do_bo_dirty(dev_priv, vfb, NULL,
+						      &vclips, 1, 1, true,
+						      &fence, crtc);
 		else
 			ret = vmw_kms_sou_do_surface_dirty(dev_priv, vfb, NULL,
 							   &vclips, NULL, 0, 0,
@@ -527,8 +535,6 @@ vmw_sou_primary_plane_atomic_update(struct drm_plane *plane,
 		 */
 		if (ret != 0)
 			DRM_ERROR("Failed to update screen.\n");
-
-		crtc->primary->fb = plane->state->fb;
 	} else {
 		/*
 		 * When disabling a plane, CRTC and FB should always be NULL
@@ -697,7 +703,7 @@ static int vmw_sou_init(struct vmw_private *dev_priv, unsigned unit)
 		goto err_free_connector;
 	}
 
-	(void) drm_mode_connector_attach_encoder(connector, encoder);
+	(void) drm_connector_attach_encoder(connector, encoder);
 	encoder->possible_crtcs = (1 << unit);
 	encoder->possible_clones = 0;
 
@@ -777,11 +783,11 @@ int vmw_kms_sou_init_display(struct vmw_private *dev_priv)
 	return 0;
 }
 
-static int do_dmabuf_define_gmrfb(struct vmw_private *dev_priv,
+static int do_bo_define_gmrfb(struct vmw_private *dev_priv,
 				  struct vmw_framebuffer *framebuffer)
 {
-	struct vmw_dma_buffer *buf =
-		container_of(framebuffer, struct vmw_framebuffer_dmabuf,
+	struct vmw_buffer_object *buf =
+		container_of(framebuffer, struct vmw_framebuffer_bo,
 			     base)->buffer;
 	int depth = framebuffer->base.format->depth;
 	struct {
@@ -972,13 +978,13 @@ int vmw_kms_sou_do_surface_dirty(struct vmw_private *dev_priv,
 }
 
 /**
- * vmw_sou_dmabuf_fifo_commit - Callback to submit a set of readback clips.
+ * vmw_sou_bo_fifo_commit - Callback to submit a set of readback clips.
  *
  * @dirty: The closure structure.
  *
  * Commits a previously built command buffer of readback clips.
  */
-static void vmw_sou_dmabuf_fifo_commit(struct vmw_kms_dirty *dirty)
+static void vmw_sou_bo_fifo_commit(struct vmw_kms_dirty *dirty)
 {
 	if (!dirty->num_hits) {
 		vmw_fifo_commit(dirty->dev_priv, 0);
@@ -986,20 +992,20 @@ static void vmw_sou_dmabuf_fifo_commit(struct vmw_kms_dirty *dirty)
 	}
 
 	vmw_fifo_commit(dirty->dev_priv,
-			sizeof(struct vmw_kms_sou_dmabuf_blit) *
+			sizeof(struct vmw_kms_sou_bo_blit) *
 			dirty->num_hits);
 }
 
 /**
- * vmw_sou_dmabuf_clip - Callback to encode a readback cliprect.
+ * vmw_sou_bo_clip - Callback to encode a readback cliprect.
  *
  * @dirty: The closure structure
  *
  * Encodes a BLIT_GMRFB_TO_SCREEN cliprect.
  */
-static void vmw_sou_dmabuf_clip(struct vmw_kms_dirty *dirty)
+static void vmw_sou_bo_clip(struct vmw_kms_dirty *dirty)
 {
-	struct vmw_kms_sou_dmabuf_blit *blit = dirty->cmd;
+	struct vmw_kms_sou_bo_blit *blit = dirty->cmd;
 
 	blit += dirty->num_hits;
 	blit->header = SVGA_CMD_BLIT_GMRFB_TO_SCREEN;
@@ -1014,10 +1020,10 @@ static void vmw_sou_dmabuf_clip(struct vmw_kms_dirty *dirty)
 }
 
 /**
- * vmw_kms_do_dmabuf_dirty - Dirty part of a dma-buffer backed framebuffer
+ * vmw_kms_do_bo_dirty - Dirty part of a buffer-object backed framebuffer
  *
  * @dev_priv: Pointer to the device private structure.
- * @framebuffer: Pointer to the dma-buffer backed framebuffer.
+ * @framebuffer: Pointer to the buffer-object backed framebuffer.
  * @clips: Array of clip rects.
  * @vclips: Alternate array of clip rects. Either @clips or @vclips must
  * be NULL.
@@ -1027,12 +1033,12 @@ static void vmw_sou_dmabuf_clip(struct vmw_kms_dirty *dirty)
  * @out_fence: If non-NULL, will return a ref-counted pointer to a
  * struct vmw_fence_obj. The returned fence pointer may be NULL in which
  * case the device has already synchronized.
- * @crtc: If crtc is passed, perform dmabuf dirty on that crtc only.
+ * @crtc: If crtc is passed, perform bo dirty on that crtc only.
  *
  * Returns 0 on success, negative error code on failure. -ERESTARTSYS if
  * interrupted.
  */
-int vmw_kms_sou_do_dmabuf_dirty(struct vmw_private *dev_priv,
+int vmw_kms_sou_do_bo_dirty(struct vmw_private *dev_priv,
 				struct vmw_framebuffer *framebuffer,
 				struct drm_clip_rect *clips,
 				struct drm_vmw_rect *vclips,
@@ -1041,8 +1047,8 @@ int vmw_kms_sou_do_dmabuf_dirty(struct vmw_private *dev_priv,
 				struct vmw_fence_obj **out_fence,
 				struct drm_crtc *crtc)
 {
-	struct vmw_dma_buffer *buf =
-		container_of(framebuffer, struct vmw_framebuffer_dmabuf,
+	struct vmw_buffer_object *buf =
+		container_of(framebuffer, struct vmw_framebuffer_bo,
 			     base)->buffer;
 	struct vmw_kms_dirty dirty;
 	int ret;
@@ -1052,14 +1058,14 @@ int vmw_kms_sou_do_dmabuf_dirty(struct vmw_private *dev_priv,
 	if (ret)
 		return ret;
 
-	ret = do_dmabuf_define_gmrfb(dev_priv, framebuffer);
+	ret = do_bo_define_gmrfb(dev_priv, framebuffer);
 	if (unlikely(ret != 0))
 		goto out_revert;
 
 	dirty.crtc = crtc;
-	dirty.fifo_commit = vmw_sou_dmabuf_fifo_commit;
-	dirty.clip = vmw_sou_dmabuf_clip;
-	dirty.fifo_reserve_size = sizeof(struct vmw_kms_sou_dmabuf_blit) *
+	dirty.fifo_commit = vmw_sou_bo_fifo_commit;
+	dirty.clip = vmw_sou_bo_clip;
+	dirty.fifo_reserve_size = sizeof(struct vmw_kms_sou_bo_blit) *
 		num_clips;
 	ret = vmw_kms_helper_dirty(dev_priv, framebuffer, clips, vclips,
 				   0, 0, num_clips, increment, &dirty);
@@ -1118,12 +1124,12 @@ static void vmw_sou_readback_clip(struct vmw_kms_dirty *dirty)
 
 /**
  * vmw_kms_sou_readback - Perform a readback from the screen object system to
- * a dma-buffer backed framebuffer.
+ * a buffer-object backed framebuffer.
  *
  * @dev_priv: Pointer to the device private structure.
  * @file_priv: Pointer to a struct drm_file identifying the caller.
  * Must be set to NULL if @user_fence_rep is NULL.
- * @vfb: Pointer to the dma-buffer backed framebuffer.
+ * @vfb: Pointer to the buffer-object backed framebuffer.
  * @user_fence_rep: User-space provided structure for fence information.
  * Must be set to non-NULL if @file_priv is non-NULL.
  * @vclips: Array of clip rects.
@@ -1141,8 +1147,8 @@ int vmw_kms_sou_readback(struct vmw_private *dev_priv,
 			 uint32_t num_clips,
 			 struct drm_crtc *crtc)
 {
-	struct vmw_dma_buffer *buf =
-		container_of(vfb, struct vmw_framebuffer_dmabuf, base)->buffer;
+	struct vmw_buffer_object *buf =
+		container_of(vfb, struct vmw_framebuffer_bo, base)->buffer;
 	struct vmw_kms_dirty dirty;
 	int ret;
 
@@ -1151,7 +1157,7 @@ int vmw_kms_sou_readback(struct vmw_private *dev_priv,
 	if (ret)
 		return ret;
 
-	ret = do_dmabuf_define_gmrfb(dev_priv, vfb);
+	ret = do_bo_define_gmrfb(dev_priv, vfb);
 	if (unlikely(ret != 0))
 		goto out_revert;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
index 73b8e9a16368..fe4842ca3b6e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -159,7 +159,7 @@ static int vmw_gb_shader_init(struct vmw_private *dev_priv,
 			      SVGA3dShaderType type,
 			      uint8_t num_input_sig,
 			      uint8_t num_output_sig,
-			      struct vmw_dma_buffer *byte_code,
+			      struct vmw_buffer_object *byte_code,
 			      void (*res_free) (struct vmw_resource *res))
 {
 	struct vmw_shader *shader = vmw_res_to_shader(res);
@@ -178,7 +178,7 @@ static int vmw_gb_shader_init(struct vmw_private *dev_priv,
 
 	res->backup_size = size;
 	if (byte_code) {
-		res->backup = vmw_dmabuf_reference(byte_code);
+		res->backup = vmw_bo_reference(byte_code);
 		res->backup_offset = offset;
 	}
 	shader->size = size;
@@ -306,7 +306,7 @@ static int vmw_gb_shader_unbind(struct vmw_resource *res,
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv,
 					  &fence, NULL);
 
-	vmw_fence_single_bo(val_buf->bo, fence);
+	vmw_bo_fence_single(val_buf->bo, fence);
 
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
@@ -537,7 +537,7 @@ static int vmw_dx_shader_unbind(struct vmw_resource *res,
 
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv,
 					  &fence, NULL);
-	vmw_fence_single_bo(val_buf->bo, fence);
+	vmw_bo_fence_single(val_buf->bo, fence);
 
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
@@ -723,7 +723,7 @@ int vmw_shader_destroy_ioctl(struct drm_device *dev, void *data,
 }
 
 static int vmw_user_shader_alloc(struct vmw_private *dev_priv,
-				 struct vmw_dma_buffer *buffer,
+				 struct vmw_buffer_object *buffer,
 				 size_t shader_size,
 				 size_t offset,
 				 SVGA3dShaderType shader_type,
@@ -801,7 +801,7 @@ out:
 
 
 static struct vmw_resource *vmw_shader_alloc(struct vmw_private *dev_priv,
-					     struct vmw_dma_buffer *buffer,
+					     struct vmw_buffer_object *buffer,
 					     size_t shader_size,
 					     size_t offset,
 					     SVGA3dShaderType shader_type)
@@ -862,12 +862,12 @@ static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv,
 {
 	struct vmw_private *dev_priv = vmw_priv(dev);
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
-	struct vmw_dma_buffer *buffer = NULL;
+	struct vmw_buffer_object *buffer = NULL;
 	SVGA3dShaderType shader_type;
 	int ret;
 
 	if (buffer_handle != SVGA3D_INVALID_ID) {
-		ret = vmw_user_dmabuf_lookup(tfile, buffer_handle,
+		ret = vmw_user_bo_lookup(tfile, buffer_handle,
 					     &buffer, NULL);
 		if (unlikely(ret != 0)) {
 			DRM_ERROR("Could not find buffer for shader "
@@ -906,7 +906,7 @@ static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv,
 
 	ttm_read_unlock(&dev_priv->reservation_sem);
 out_bad_arg:
-	vmw_dmabuf_unreference(&buffer);
+	vmw_bo_unreference(&buffer);
 	return ret;
 }
 
@@ -983,7 +983,7 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv,
 			  struct list_head *list)
 {
 	struct ttm_operation_ctx ctx = { false, true };
-	struct vmw_dma_buffer *buf;
+	struct vmw_buffer_object *buf;
 	struct ttm_bo_kmap_obj map;
 	bool is_iomem;
 	int ret;
@@ -997,8 +997,8 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv,
 	if (unlikely(!buf))
 		return -ENOMEM;
 
-	ret = vmw_dmabuf_init(dev_priv, buf, size, &vmw_sys_ne_placement,
-			      true, vmw_dmabuf_bo_free);
+	ret = vmw_bo_init(dev_priv, buf, size, &vmw_sys_ne_placement,
+			      true, vmw_bo_bo_free);
 	if (unlikely(ret != 0))
 		goto out;
 
@@ -1031,7 +1031,7 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv,
 				 res, list);
 	vmw_resource_unreference(&res);
 no_reserve:
-	vmw_dmabuf_unreference(&buf);
+	vmw_bo_unreference(&buf);
 out:
 	return ret;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_simple_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_simple_resource.c
index a0cb310665cc..6ebc5affde14 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_simple_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_simple_resource.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2016 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2016 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_so.c b/drivers/gpu/drm/vmwgfx/vmwgfx_so.c
index d3573c37c436..e9b6b7baa009 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_so.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_so.c
@@ -1,6 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
- * Copyright © 2014-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2014-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_so.h b/drivers/gpu/drm/vmwgfx/vmwgfx_so.h
index 268738387b5e..b80c7252f2fd 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_so.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_so.h
@@ -1,6 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
- * Copyright © 2014-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2014-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index 67331f01ef32..93f6b96ca7bb 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /******************************************************************************
  *
- * COPYRIGHT © 2014-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * COPYRIGHT (C) 2014-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -44,7 +44,7 @@
 enum stdu_content_type {
 	SAME_AS_DISPLAY = 0,
 	SEPARATE_SURFACE,
-	SEPARATE_DMA
+	SEPARATE_BO
 };
 
 /**
@@ -58,7 +58,7 @@ enum stdu_content_type {
  * @bottom: Bottom side of bounding box.
  * @fb_left: Left side of the framebuffer/content bounding box
  * @fb_top: Top of the framebuffer/content bounding box
- * @buf: DMA buffer when DMA-ing between buffer and screen targets.
+ * @buf: buffer object when DMA-ing between buffer and screen targets.
  * @sid: Surface ID when copying between surface and screen targets.
  */
 struct vmw_stdu_dirty {
@@ -68,7 +68,7 @@ struct vmw_stdu_dirty {
 	s32 fb_left, fb_top;
 	u32 pitch;
 	union {
-		struct vmw_dma_buffer *buf;
+		struct vmw_buffer_object *buf;
 		u32 sid;
 	};
 };
@@ -178,13 +178,9 @@ static int vmw_stdu_define_st(struct vmw_private *dev_priv,
 	cmd->body.height = mode->vdisplay;
 	cmd->body.flags  = (0 == cmd->body.stid) ? SVGA_STFLAG_PRIMARY : 0;
 	cmd->body.dpi    = 0;
-	if (stdu->base.is_implicit) {
-		cmd->body.xRoot  = crtc_x;
-		cmd->body.yRoot  = crtc_y;
-	} else {
-		cmd->body.xRoot  = stdu->base.gui_x;
-		cmd->body.yRoot  = stdu->base.gui_y;
-	}
+	cmd->body.xRoot  = crtc_x;
+	cmd->body.yRoot  = crtc_y;
+
 	stdu->base.set_gui_x = cmd->body.xRoot;
 	stdu->base.set_gui_y = cmd->body.yRoot;
 
@@ -374,11 +370,14 @@ static void vmw_stdu_crtc_mode_set_nofb(struct drm_crtc *crtc)
 {
 	struct vmw_private *dev_priv;
 	struct vmw_screen_target_display_unit *stdu;
-	int ret;
-
+	struct drm_connector_state *conn_state;
+	struct vmw_connector_state *vmw_conn_state;
+	int x, y, ret;
 
-	stdu     = vmw_crtc_to_stdu(crtc);
+	stdu = vmw_crtc_to_stdu(crtc);
 	dev_priv = vmw_priv(crtc->dev);
+	conn_state = stdu->base.connector.state;
+	vmw_conn_state = vmw_connector_state_to_vcs(conn_state);
 
 	if (stdu->defined) {
 		ret = vmw_stdu_bind_st(dev_priv, stdu, NULL);
@@ -397,8 +396,16 @@ static void vmw_stdu_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	if (!crtc->state->enable)
 		return;
 
+	if (stdu->base.is_implicit) {
+		x = crtc->x;
+		y = crtc->y;
+	} else {
+		x = vmw_conn_state->gui_x;
+		y = vmw_conn_state->gui_y;
+	}
+
 	vmw_svga_enable(dev_priv);
-	ret = vmw_stdu_define_st(dev_priv, stdu, &crtc->mode, crtc->x, crtc->y);
+	ret = vmw_stdu_define_st(dev_priv, stdu, &crtc->mode, x, y);
 
 	if (ret)
 		DRM_ERROR("Failed to define Screen Target of size %dx%d\n",
@@ -414,6 +421,7 @@ static void vmw_stdu_crtc_helper_prepare(struct drm_crtc *crtc)
 static void vmw_stdu_crtc_atomic_enable(struct drm_crtc *crtc,
 					struct drm_crtc_state *old_state)
 {
+	struct drm_plane_state *plane_state = crtc->primary->state;
 	struct vmw_private *dev_priv;
 	struct vmw_screen_target_display_unit *stdu;
 	struct vmw_framebuffer *vfb;
@@ -422,7 +430,7 @@ static void vmw_stdu_crtc_atomic_enable(struct drm_crtc *crtc,
 
 	stdu     = vmw_crtc_to_stdu(crtc);
 	dev_priv = vmw_priv(crtc->dev);
-	fb       = crtc->primary->fb;
+	fb       = plane_state->fb;
 
 	vfb = (fb) ? vmw_framebuffer_to_vfb(fb) : NULL;
 
@@ -507,14 +515,14 @@ static int vmw_stdu_crtc_page_flip(struct drm_crtc *crtc,
 
 
 /**
- * vmw_stdu_dmabuf_clip - Callback to encode a suface DMA command cliprect
+ * vmw_stdu_bo_clip - Callback to encode a suface DMA command cliprect
  *
  * @dirty: The closure structure.
  *
  * Encodes a surface DMA command cliprect and updates the bounding box
  * for the DMA.
  */
-static void vmw_stdu_dmabuf_clip(struct vmw_kms_dirty *dirty)
+static void vmw_stdu_bo_clip(struct vmw_kms_dirty *dirty)
 {
 	struct vmw_stdu_dirty *ddirty =
 		container_of(dirty, struct vmw_stdu_dirty, base);
@@ -542,14 +550,14 @@ static void vmw_stdu_dmabuf_clip(struct vmw_kms_dirty *dirty)
 }
 
 /**
- * vmw_stdu_dmabuf_fifo_commit - Callback to fill in and submit a DMA command.
+ * vmw_stdu_bo_fifo_commit - Callback to fill in and submit a DMA command.
  *
  * @dirty: The closure structure.
  *
  * Fills in the missing fields in a DMA command, and optionally encodes
  * a screen target update command, depending on transfer direction.
  */
-static void vmw_stdu_dmabuf_fifo_commit(struct vmw_kms_dirty *dirty)
+static void vmw_stdu_bo_fifo_commit(struct vmw_kms_dirty *dirty)
 {
 	struct vmw_stdu_dirty *ddirty =
 		container_of(dirty, struct vmw_stdu_dirty, base);
@@ -593,13 +601,13 @@ static void vmw_stdu_dmabuf_fifo_commit(struct vmw_kms_dirty *dirty)
 
 
 /**
- * vmw_stdu_dmabuf_cpu_clip - Callback to encode a CPU blit
+ * vmw_stdu_bo_cpu_clip - Callback to encode a CPU blit
  *
  * @dirty: The closure structure.
  *
  * This function calculates the bounding box for all the incoming clips.
  */
-static void vmw_stdu_dmabuf_cpu_clip(struct vmw_kms_dirty *dirty)
+static void vmw_stdu_bo_cpu_clip(struct vmw_kms_dirty *dirty)
 {
 	struct vmw_stdu_dirty *ddirty =
 		container_of(dirty, struct vmw_stdu_dirty, base);
@@ -623,14 +631,14 @@ static void vmw_stdu_dmabuf_cpu_clip(struct vmw_kms_dirty *dirty)
 
 
 /**
- * vmw_stdu_dmabuf_cpu_commit - Callback to do a CPU blit from DMAbuf
+ * vmw_stdu_bo_cpu_commit - Callback to do a CPU blit from buffer object
  *
  * @dirty: The closure structure.
  *
  * For the special case when we cannot create a proxy surface in a
  * 2D VM, we have to do a CPU blit ourselves.
  */
-static void vmw_stdu_dmabuf_cpu_commit(struct vmw_kms_dirty *dirty)
+static void vmw_stdu_bo_cpu_commit(struct vmw_kms_dirty *dirty)
 {
 	struct vmw_stdu_dirty *ddirty =
 		container_of(dirty, struct vmw_stdu_dirty, base);
@@ -651,7 +659,7 @@ static void vmw_stdu_dmabuf_cpu_commit(struct vmw_kms_dirty *dirty)
 	if (width == 0 || height == 0)
 		return;
 
-	/* Assume we are blitting from Guest (dmabuf) to Host (display_srf) */
+	/* Assume we are blitting from Guest (bo) to Host (display_srf) */
 	dst_pitch = stdu->display_srf->base_size.width * stdu->cpp;
 	dst_bo = &stdu->display_srf->res.backup->base;
 	dst_offset = ddirty->top * dst_pitch + ddirty->left * stdu->cpp;
@@ -711,13 +719,13 @@ out_cleanup:
 }
 
 /**
- * vmw_kms_stdu_dma - Perform a DMA transfer between a dma-buffer backed
+ * vmw_kms_stdu_dma - Perform a DMA transfer between a buffer-object backed
  * framebuffer and the screen target system.
  *
  * @dev_priv: Pointer to the device private structure.
  * @file_priv: Pointer to a struct drm-file identifying the caller. May be
  * set to NULL, but then @user_fence_rep must also be set to NULL.
- * @vfb: Pointer to the dma-buffer backed framebuffer.
+ * @vfb: Pointer to the buffer-object backed framebuffer.
  * @clips: Array of clip rects. Either @clips or @vclips must be NULL.
  * @vclips: Alternate array of clip rects. Either @clips or @vclips must
  * be NULL.
@@ -746,8 +754,8 @@ int vmw_kms_stdu_dma(struct vmw_private *dev_priv,
 		     bool interruptible,
 		     struct drm_crtc *crtc)
 {
-	struct vmw_dma_buffer *buf =
-		container_of(vfb, struct vmw_framebuffer_dmabuf, base)->buffer;
+	struct vmw_buffer_object *buf =
+		container_of(vfb, struct vmw_framebuffer_bo, base)->buffer;
 	struct vmw_stdu_dirty ddirty;
 	int ret;
 	bool cpu_blit = !(dev_priv->capabilities & SVGA_CAP_3D);
@@ -769,8 +777,8 @@ int vmw_kms_stdu_dma(struct vmw_private *dev_priv,
 	ddirty.fb_left = ddirty.fb_top = S32_MAX;
 	ddirty.pitch = vfb->base.pitches[0];
 	ddirty.buf = buf;
-	ddirty.base.fifo_commit = vmw_stdu_dmabuf_fifo_commit;
-	ddirty.base.clip = vmw_stdu_dmabuf_clip;
+	ddirty.base.fifo_commit = vmw_stdu_bo_fifo_commit;
+	ddirty.base.clip = vmw_stdu_bo_clip;
 	ddirty.base.fifo_reserve_size = sizeof(struct vmw_stdu_dma) +
 		num_clips * sizeof(SVGA3dCopyBox) +
 		sizeof(SVGA3dCmdSurfaceDMASuffix);
@@ -779,8 +787,8 @@ int vmw_kms_stdu_dma(struct vmw_private *dev_priv,
 
 
 	if (cpu_blit) {
-		ddirty.base.fifo_commit = vmw_stdu_dmabuf_cpu_commit;
-		ddirty.base.clip = vmw_stdu_dmabuf_cpu_clip;
+		ddirty.base.fifo_commit = vmw_stdu_bo_cpu_commit;
+		ddirty.base.clip = vmw_stdu_bo_cpu_clip;
 		ddirty.base.fifo_reserve_size = 0;
 	}
 
@@ -926,7 +934,7 @@ int vmw_kms_stdu_surface_dirty(struct vmw_private *dev_priv,
 	if (ret)
 		return ret;
 
-	if (vfbs->is_dmabuf_proxy) {
+	if (vfbs->is_bo_proxy) {
 		ret = vmw_kms_update_proxy(srf, clips, num_clips, inc);
 		if (ret)
 			goto out_finish;
@@ -1074,7 +1082,7 @@ vmw_stdu_primary_plane_cleanup_fb(struct drm_plane *plane,
  * @new_state: info on the new plane state, including the FB
  *
  * This function allocates a new display surface if the content is
- * backed by a DMA.  The display surface is pinned here, and it'll
+ * backed by a buffer object.  The display surface is pinned here, and it'll
  * be unpinned in .cleanup_fb()
  *
  * Returns 0 on success
@@ -1104,13 +1112,13 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 	}
 
 	vfb = vmw_framebuffer_to_vfb(new_fb);
-	new_vfbs = (vfb->dmabuf) ? NULL : vmw_framebuffer_to_vfbs(new_fb);
+	new_vfbs = (vfb->bo) ? NULL : vmw_framebuffer_to_vfbs(new_fb);
 
 	if (new_vfbs && new_vfbs->surface->base_size.width == hdisplay &&
 	    new_vfbs->surface->base_size.height == vdisplay)
 		new_content_type = SAME_AS_DISPLAY;
-	else if (vfb->dmabuf)
-		new_content_type = SEPARATE_DMA;
+	else if (vfb->bo)
+		new_content_type = SEPARATE_BO;
 	else
 		new_content_type = SEPARATE_SURFACE;
 
@@ -1123,10 +1131,10 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 		display_base_size.depth  = 1;
 
 		/*
-		 * If content buffer is a DMA buf, then we have to construct
-		 * surface info
+		 * If content buffer is a buffer object, then we have to
+		 * construct surface info
 		 */
-		if (new_content_type == SEPARATE_DMA) {
+		if (new_content_type == SEPARATE_BO) {
 
 			switch (new_fb->format->cpp[0]*8) {
 			case 32:
@@ -1149,6 +1157,9 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 			content_srf.flags             = 0;
 			content_srf.mip_levels[0]     = 1;
 			content_srf.multisample_count = 0;
+			content_srf.multisample_pattern =
+				SVGA3D_MS_PATTERN_NONE;
+			content_srf.quality_level = SVGA3D_MS_QUALITY_NONE;
 		} else {
 			content_srf = *new_vfbs->surface;
 		}
@@ -1177,6 +1188,8 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 				 content_srf.multisample_count,
 				 0,
 				 display_base_size,
+				 content_srf.multisample_pattern,
+				 content_srf.quality_level,
 				 &vps->surf);
 			if (ret != 0) {
 				DRM_ERROR("Couldn't allocate STDU surface.\n");
@@ -1211,12 +1224,12 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 	vps->content_fb_type = new_content_type;
 
 	/*
-	 * This should only happen if the DMA buf is too large to create a
+	 * This should only happen if the buffer object is too large to create a
 	 * proxy surface for.
-	 * If we are a 2D VM with a DMA buffer then we have to use CPU blit
+	 * If we are a 2D VM with a buffer object then we have to use CPU blit
 	 * so cache these mappings
 	 */
-	if (vps->content_fb_type == SEPARATE_DMA &&
+	if (vps->content_fb_type == SEPARATE_BO &&
 	    !(dev_priv->capabilities & SVGA_CAP_3D))
 		vps->cpp = new_fb->pitches[0] / new_fb->width;
 
@@ -1275,7 +1288,7 @@ vmw_stdu_primary_plane_atomic_update(struct drm_plane *plane,
 		if (ret)
 			DRM_ERROR("Failed to bind surface to STDU.\n");
 
-		if (vfb->dmabuf)
+		if (vfb->bo)
 			ret = vmw_kms_stdu_dma(dev_priv, NULL, vfb, NULL, NULL,
 					       &vclips, 1, 1, true, false,
 					       crtc);
@@ -1285,8 +1298,6 @@ vmw_stdu_primary_plane_atomic_update(struct drm_plane *plane,
 							 1, 1, NULL, crtc);
 		if (ret)
 			DRM_ERROR("Failed to update STDU.\n");
-
-		crtc->primary->fb = plane->state->fb;
 	} else {
 		crtc = old_state->crtc;
 		stdu = vmw_crtc_to_stdu(crtc);
@@ -1487,7 +1498,7 @@ static int vmw_stdu_init(struct vmw_private *dev_priv, unsigned unit)
 		goto err_free_connector;
 	}
 
-	(void) drm_mode_connector_attach_encoder(connector, encoder);
+	(void) drm_connector_attach_encoder(connector, encoder);
 	encoder->possible_crtcs = (1 << unit);
 	encoder->possible_clones = 0;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index b236c48bf265..e125233e074b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -33,6 +33,10 @@
 #include "vmwgfx_binding.h"
 #include "device_include/svga3d_surfacedefs.h"
 
+#define SVGA3D_FLAGS_64(upper32, lower32) (((uint64_t)upper32 << 32) | lower32)
+#define SVGA3D_FLAGS_UPPER_32(svga3d_flags) (svga3d_flags >> 32)
+#define SVGA3D_FLAGS_LOWER_32(svga3d_flags) \
+	(svga3d_flags & ((uint64_t)U32_MAX))
 
 /**
  * struct vmw_user_surface - User-space visible surface resource
@@ -81,7 +85,16 @@ static int vmw_gb_surface_unbind(struct vmw_resource *res,
 				 bool readback,
 				 struct ttm_validate_buffer *val_buf);
 static int vmw_gb_surface_destroy(struct vmw_resource *res);
-
+static int
+vmw_gb_surface_define_internal(struct drm_device *dev,
+			       struct drm_vmw_gb_surface_create_ext_req *req,
+			       struct drm_vmw_gb_surface_create_rep *rep,
+			       struct drm_file *file_priv);
+static int
+vmw_gb_surface_reference_internal(struct drm_device *dev,
+				  struct drm_vmw_surface_arg *req,
+				  struct drm_vmw_gb_surface_ref_ext_rep *rep,
+				  struct drm_file *file_priv);
 
 static const struct vmw_user_resource_conv user_surface_conv = {
 	.object_type = VMW_RES_SURFACE,
@@ -224,7 +237,12 @@ static void vmw_surface_define_encode(const struct vmw_surface *srf,
 	cmd->header.id = SVGA_3D_CMD_SURFACE_DEFINE;
 	cmd->header.size = cmd_len;
 	cmd->body.sid = srf->res.id;
-	cmd->body.surfaceFlags = srf->flags;
+	/*
+	 * Downcast of surfaceFlags, was upcasted when received from user-space,
+	 * since driver internally stores as 64 bit.
+	 * For legacy surface define only 32 bit flag is supported.
+	 */
+	cmd->body.surfaceFlags = (SVGA3dSurface1Flags)srf->flags;
 	cmd->body.format = srf->format;
 	for (i = 0; i < DRM_VMW_MAX_SURFACE_FACES; ++i)
 		cmd->body.face[i].numMipLevels = srf->mip_levels[i];
@@ -468,7 +486,7 @@ static int vmw_legacy_srf_dma(struct vmw_resource *res,
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv,
 					  &fence, NULL);
 
-	vmw_fence_single_bo(val_buf->bo, fence);
+	vmw_bo_fence_single(val_buf->bo, fence);
 
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
@@ -760,7 +778,8 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 	srf = &user_srf->srf;
 	res = &srf->res;
 
-	srf->flags = req->flags;
+	/* Driver internally stores as 64-bit flags */
+	srf->flags = (SVGA3dSurfaceAllFlags)req->flags;
 	srf->format = req->format;
 	srf->scanout = req->scanout;
 
@@ -785,6 +804,8 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 	srf->base_size = *srf->sizes;
 	srf->autogen_filter = SVGA3D_TEX_FILTER_NONE;
 	srf->multisample_count = 0;
+	srf->multisample_pattern = SVGA3D_MS_PATTERN_NONE;
+	srf->quality_level = SVGA3D_MS_QUALITY_NONE;
 
 	cur_bo_offset = 0;
 	cur_offset = srf->offsets;
@@ -842,12 +863,12 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 	if (dev_priv->has_mob && req->shareable) {
 		uint32_t backup_handle;
 
-		ret = vmw_user_dmabuf_alloc(dev_priv, tfile,
-					    res->backup_size,
-					    true,
-					    &backup_handle,
-					    &res->backup,
-					    &user_srf->backup_base);
+		ret = vmw_user_bo_alloc(dev_priv, tfile,
+					res->backup_size,
+					true,
+					&backup_handle,
+					&res->backup,
+					&user_srf->backup_base);
 		if (unlikely(ret != 0)) {
 			vmw_resource_unreference(&res);
 			goto out_unlock;
@@ -990,7 +1011,8 @@ int vmw_surface_reference_ioctl(struct drm_device *dev, void *data,
 	user_srf = container_of(base, struct vmw_user_surface, prime.base);
 	srf = &user_srf->srf;
 
-	rep->flags = srf->flags;
+	/* Downcast of flags when sending back to user space */
+	rep->flags = (uint32_t)srf->flags;
 	rep->format = srf->format;
 	memcpy(rep->mip_levels, srf->mip_levels, sizeof(srf->mip_levels));
 	user_sizes = (struct drm_vmw_size __user *)(unsigned long)
@@ -1031,6 +1053,10 @@ static int vmw_gb_surface_create(struct vmw_resource *res)
 		SVGA3dCmdHeader header;
 		SVGA3dCmdDefineGBSurface_v2 body;
 	} *cmd2;
+	struct {
+		SVGA3dCmdHeader header;
+		SVGA3dCmdDefineGBSurface_v3 body;
+	} *cmd3;
 
 	if (likely(res->id != -1))
 		return 0;
@@ -1047,7 +1073,11 @@ static int vmw_gb_surface_create(struct vmw_resource *res)
 		goto out_no_fifo;
 	}
 
-	if (srf->array_size > 0) {
+	if (dev_priv->has_sm4_1 && srf->array_size > 0) {
+		cmd_id = SVGA_3D_CMD_DEFINE_GB_SURFACE_V3;
+		cmd_len = sizeof(cmd3->body);
+		submit_len = sizeof(*cmd3);
+	} else if (srf->array_size > 0) {
 		/* has_dx checked on creation time. */
 		cmd_id = SVGA_3D_CMD_DEFINE_GB_SURFACE_V2;
 		cmd_len = sizeof(cmd2->body);
@@ -1060,6 +1090,7 @@ static int vmw_gb_surface_create(struct vmw_resource *res)
 
 	cmd = vmw_fifo_reserve(dev_priv, submit_len);
 	cmd2 = (typeof(cmd2))cmd;
+	cmd3 = (typeof(cmd3))cmd;
 	if (unlikely(!cmd)) {
 		DRM_ERROR("Failed reserving FIFO space for surface "
 			  "creation.\n");
@@ -1067,12 +1098,27 @@ static int vmw_gb_surface_create(struct vmw_resource *res)
 		goto out_no_fifo;
 	}
 
-	if (srf->array_size > 0) {
+	if (dev_priv->has_sm4_1 && srf->array_size > 0) {
+		cmd3->header.id = cmd_id;
+		cmd3->header.size = cmd_len;
+		cmd3->body.sid = srf->res.id;
+		cmd3->body.surfaceFlags = srf->flags;
+		cmd3->body.format = srf->format;
+		cmd3->body.numMipLevels = srf->mip_levels[0];
+		cmd3->body.multisampleCount = srf->multisample_count;
+		cmd3->body.multisamplePattern = srf->multisample_pattern;
+		cmd3->body.qualityLevel = srf->quality_level;
+		cmd3->body.autogenFilter = srf->autogen_filter;
+		cmd3->body.size.width = srf->base_size.width;
+		cmd3->body.size.height = srf->base_size.height;
+		cmd3->body.size.depth = srf->base_size.depth;
+		cmd3->body.arraySize = srf->array_size;
+	} else if (srf->array_size > 0) {
 		cmd2->header.id = cmd_id;
 		cmd2->header.size = cmd_len;
 		cmd2->body.sid = srf->res.id;
 		cmd2->body.surfaceFlags = srf->flags;
-		cmd2->body.format = cpu_to_le32(srf->format);
+		cmd2->body.format = srf->format;
 		cmd2->body.numMipLevels = srf->mip_levels[0];
 		cmd2->body.multisampleCount = srf->multisample_count;
 		cmd2->body.autogenFilter = srf->autogen_filter;
@@ -1085,7 +1131,7 @@ static int vmw_gb_surface_create(struct vmw_resource *res)
 		cmd->header.size = cmd_len;
 		cmd->body.sid = srf->res.id;
 		cmd->body.surfaceFlags = srf->flags;
-		cmd->body.format = cpu_to_le32(srf->format);
+		cmd->body.format = srf->format;
 		cmd->body.numMipLevels = srf->mip_levels[0];
 		cmd->body.multisampleCount = srf->multisample_count;
 		cmd->body.autogenFilter = srf->autogen_filter;
@@ -1210,7 +1256,7 @@ static int vmw_gb_surface_unbind(struct vmw_resource *res,
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv,
 					  &fence, NULL);
 
-	vmw_fence_single_bo(val_buf->bo, fence);
+	vmw_bo_fence_single(val_buf->bo, fence);
 
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
@@ -1256,194 +1302,55 @@ static int vmw_gb_surface_destroy(struct vmw_resource *res)
 
 /**
  * vmw_gb_surface_define_ioctl - Ioctl function implementing
- *                               the user surface define functionality.
+ * the user surface define functionality.
  *
- * @dev:            Pointer to a struct drm_device.
- * @data:           Pointer to data copied from / to user-space.
- * @file_priv:      Pointer to a drm file private structure.
+ * @dev: Pointer to a struct drm_device.
+ * @data: Pointer to data copied from / to user-space.
+ * @file_priv: Pointer to a drm file private structure.
  */
 int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *file_priv)
 {
-	struct vmw_private *dev_priv = vmw_priv(dev);
-	struct vmw_user_surface *user_srf;
-	struct vmw_surface *srf;
-	struct vmw_resource *res;
-	struct vmw_resource *tmp;
 	union drm_vmw_gb_surface_create_arg *arg =
 	    (union drm_vmw_gb_surface_create_arg *)data;
-	struct drm_vmw_gb_surface_create_req *req = &arg->req;
 	struct drm_vmw_gb_surface_create_rep *rep = &arg->rep;
-	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
-	int ret;
-	uint32_t size;
-	uint32_t backup_handle = 0;
-
-	if (req->multisample_count != 0)
-		return -EINVAL;
-
-	if (req->mip_levels > DRM_VMW_MAX_MIP_LEVELS)
-		return -EINVAL;
+	struct drm_vmw_gb_surface_create_ext_req req_ext;
 
-	if (unlikely(vmw_user_surface_size == 0))
-		vmw_user_surface_size = ttm_round_pot(sizeof(*user_srf)) +
-			128;
-
-	size = vmw_user_surface_size + 128;
-
-	/* Define a surface based on the parameters. */
-	ret = vmw_surface_gb_priv_define(dev,
-			size,
-			req->svga3d_flags,
-			req->format,
-			req->drm_surface_flags & drm_vmw_surface_flag_scanout,
-			req->mip_levels,
-			req->multisample_count,
-			req->array_size,
-			req->base_size,
-			&srf);
-	if (unlikely(ret != 0))
-		return ret;
-
-	user_srf = container_of(srf, struct vmw_user_surface, srf);
-	if (drm_is_primary_client(file_priv))
-		user_srf->master = drm_master_get(file_priv->master);
+	req_ext.base = arg->req;
+	req_ext.version = drm_vmw_gb_surface_v1;
+	req_ext.svga3d_flags_upper_32_bits = 0;
+	req_ext.multisample_pattern = SVGA3D_MS_PATTERN_NONE;
+	req_ext.quality_level = SVGA3D_MS_QUALITY_NONE;
+	req_ext.must_be_zero = 0;
 
-	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
-	if (unlikely(ret != 0))
-		return ret;
-
-	res = &user_srf->srf.res;
-
-
-	if (req->buffer_handle != SVGA3D_INVALID_ID) {
-		ret = vmw_user_dmabuf_lookup(tfile, req->buffer_handle,
-					     &res->backup,
-					     &user_srf->backup_base);
-		if (ret == 0) {
-			if (res->backup->base.num_pages * PAGE_SIZE <
-			    res->backup_size) {
-				DRM_ERROR("Surface backup buffer is too small.\n");
-				vmw_dmabuf_unreference(&res->backup);
-				ret = -EINVAL;
-				goto out_unlock;
-			} else {
-				backup_handle = req->buffer_handle;
-			}
-		}
-	} else if (req->drm_surface_flags & drm_vmw_surface_flag_create_buffer)
-		ret = vmw_user_dmabuf_alloc(dev_priv, tfile,
-					    res->backup_size,
-					    req->drm_surface_flags &
-					    drm_vmw_surface_flag_shareable,
-					    &backup_handle,
-					    &res->backup,
-					    &user_srf->backup_base);
-
-	if (unlikely(ret != 0)) {
-		vmw_resource_unreference(&res);
-		goto out_unlock;
-	}
-
-	tmp = vmw_resource_reference(res);
-	ret = ttm_prime_object_init(tfile, res->backup_size, &user_srf->prime,
-				    req->drm_surface_flags &
-				    drm_vmw_surface_flag_shareable,
-				    VMW_RES_SURFACE,
-				    &vmw_user_surface_base_release, NULL);
-
-	if (unlikely(ret != 0)) {
-		vmw_resource_unreference(&tmp);
-		vmw_resource_unreference(&res);
-		goto out_unlock;
-	}
-
-	rep->handle      = user_srf->prime.base.hash.key;
-	rep->backup_size = res->backup_size;
-	if (res->backup) {
-		rep->buffer_map_handle =
-			drm_vma_node_offset_addr(&res->backup->base.vma_node);
-		rep->buffer_size = res->backup->base.num_pages * PAGE_SIZE;
-		rep->buffer_handle = backup_handle;
-	} else {
-		rep->buffer_map_handle = 0;
-		rep->buffer_size = 0;
-		rep->buffer_handle = SVGA3D_INVALID_ID;
-	}
-
-	vmw_resource_unreference(&res);
-
-out_unlock:
-	ttm_read_unlock(&dev_priv->reservation_sem);
-	return ret;
+	return vmw_gb_surface_define_internal(dev, &req_ext, rep, file_priv);
 }
 
 /**
  * vmw_gb_surface_reference_ioctl - Ioctl function implementing
- *                                  the user surface reference functionality.
+ * the user surface reference functionality.
  *
- * @dev:            Pointer to a struct drm_device.
- * @data:           Pointer to data copied from / to user-space.
- * @file_priv:      Pointer to a drm file private structure.
+ * @dev: Pointer to a struct drm_device.
+ * @data: Pointer to data copied from / to user-space.
+ * @file_priv: Pointer to a drm file private structure.
  */
 int vmw_gb_surface_reference_ioctl(struct drm_device *dev, void *data,
 				   struct drm_file *file_priv)
 {
-	struct vmw_private *dev_priv = vmw_priv(dev);
 	union drm_vmw_gb_surface_reference_arg *arg =
 	    (union drm_vmw_gb_surface_reference_arg *)data;
 	struct drm_vmw_surface_arg *req = &arg->req;
 	struct drm_vmw_gb_surface_ref_rep *rep = &arg->rep;
-	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
-	struct vmw_surface *srf;
-	struct vmw_user_surface *user_srf;
-	struct ttm_base_object *base;
-	uint32_t backup_handle;
-	int ret = -EINVAL;
+	struct drm_vmw_gb_surface_ref_ext_rep rep_ext;
+	int ret;
+
+	ret = vmw_gb_surface_reference_internal(dev, req, &rep_ext, file_priv);
 
-	ret = vmw_surface_handle_reference(dev_priv, file_priv, req->sid,
-					   req->handle_type, &base);
 	if (unlikely(ret != 0))
 		return ret;
 
-	user_srf = container_of(base, struct vmw_user_surface, prime.base);
-	srf = &user_srf->srf;
-	if (!srf->res.backup) {
-		DRM_ERROR("Shared GB surface is missing a backup buffer.\n");
-		goto out_bad_resource;
-	}
-
-	mutex_lock(&dev_priv->cmdbuf_mutex); /* Protect res->backup */
-	ret = vmw_user_dmabuf_reference(tfile, srf->res.backup,
-					&backup_handle);
-	mutex_unlock(&dev_priv->cmdbuf_mutex);
-
-	if (unlikely(ret != 0)) {
-		DRM_ERROR("Could not add a reference to a GB surface "
-			  "backup buffer.\n");
-		(void) ttm_ref_object_base_unref(tfile, base->hash.key,
-						 TTM_REF_USAGE);
-		goto out_bad_resource;
-	}
-
-	rep->creq.svga3d_flags = srf->flags;
-	rep->creq.format = srf->format;
-	rep->creq.mip_levels = srf->mip_levels[0];
-	rep->creq.drm_surface_flags = 0;
-	rep->creq.multisample_count = srf->multisample_count;
-	rep->creq.autogen_filter = srf->autogen_filter;
-	rep->creq.array_size = srf->array_size;
-	rep->creq.buffer_handle = backup_handle;
-	rep->creq.base_size = srf->base_size;
-	rep->crep.handle = user_srf->prime.base.hash.key;
-	rep->crep.backup_size = srf->res.backup_size;
-	rep->crep.buffer_handle = backup_handle;
-	rep->crep.buffer_map_handle =
-		drm_vma_node_offset_addr(&srf->res.backup->base.vma_node);
-	rep->crep.buffer_size = srf->res.backup->base.num_pages * PAGE_SIZE;
-
-out_bad_resource:
-	ttm_base_object_unref(&base);
+	rep->creq = rep_ext.creq.base;
+	rep->crep = rep_ext.crep;
 
 	return ret;
 }
@@ -1461,6 +1368,8 @@ out_bad_resource:
  * @multisample_count:
  * @array_size: Surface array size.
  * @size: width, heigh, depth of the surface requested
+ * @multisample_pattern: Multisampling pattern when msaa is supported
+ * @quality_level: Precision settings
  * @user_srf_out: allocated user_srf.  Set to NULL on failure.
  *
  * GB surfaces allocated by this function will not have a user mode handle, and
@@ -1470,13 +1379,15 @@ out_bad_resource:
  */
 int vmw_surface_gb_priv_define(struct drm_device *dev,
 			       uint32_t user_accounting_size,
-			       uint32_t svga3d_flags,
+			       SVGA3dSurfaceAllFlags svga3d_flags,
 			       SVGA3dSurfaceFormat format,
 			       bool for_scanout,
 			       uint32_t num_mip_levels,
 			       uint32_t multisample_count,
 			       uint32_t array_size,
 			       struct drm_vmw_size size,
+			       SVGA3dMSPattern multisample_pattern,
+			       SVGA3dMSQualityLevel quality_level,
 			       struct vmw_surface **srf_out)
 {
 	struct vmw_private *dev_priv = vmw_priv(dev);
@@ -1487,7 +1398,8 @@ int vmw_surface_gb_priv_define(struct drm_device *dev,
 	};
 	struct vmw_surface *srf;
 	int ret;
-	u32 num_layers;
+	u32 num_layers = 1;
+	u32 sample_count = 1;
 
 	*srf_out = NULL;
 
@@ -1562,19 +1474,23 @@ int vmw_surface_gb_priv_define(struct drm_device *dev,
 	srf->autogen_filter    = SVGA3D_TEX_FILTER_NONE;
 	srf->array_size        = array_size;
 	srf->multisample_count = multisample_count;
+	srf->multisample_pattern = multisample_pattern;
+	srf->quality_level = quality_level;
 
 	if (array_size)
 		num_layers = array_size;
 	else if (svga3d_flags & SVGA3D_SURFACE_CUBEMAP)
 		num_layers = SVGA3D_MAX_SURFACE_FACES;
-	else
-		num_layers = 1;
+
+	if (srf->flags & SVGA3D_SURFACE_MULTISAMPLE)
+		sample_count = srf->multisample_count;
 
 	srf->res.backup_size   =
-		svga3dsurface_get_serialized_size(srf->format,
-						  srf->base_size,
-						  srf->mip_levels[0],
-						  num_layers);
+		svga3dsurface_get_serialized_size_extended(srf->format,
+							   srf->base_size,
+							   srf->mip_levels[0],
+							   num_layers,
+							   sample_count);
 
 	if (srf->flags & SVGA3D_SURFACE_BIND_STREAM_OUTPUT)
 		srf->res.backup_size += sizeof(SVGA3dDXSOState);
@@ -1599,3 +1515,266 @@ out_unlock:
 	ttm_read_unlock(&dev_priv->reservation_sem);
 	return ret;
 }
+
+/**
+ * vmw_gb_surface_define_ext_ioctl - Ioctl function implementing
+ * the user surface define functionality.
+ *
+ * @dev: Pointer to a struct drm_device.
+ * @data: Pointer to data copied from / to user-space.
+ * @file_priv: Pointer to a drm file private structure.
+ */
+int vmw_gb_surface_define_ext_ioctl(struct drm_device *dev, void *data,
+				struct drm_file *file_priv)
+{
+	union drm_vmw_gb_surface_create_ext_arg *arg =
+	    (union drm_vmw_gb_surface_create_ext_arg *)data;
+	struct drm_vmw_gb_surface_create_ext_req *req = &arg->req;
+	struct drm_vmw_gb_surface_create_rep *rep = &arg->rep;
+
+	return vmw_gb_surface_define_internal(dev, req, rep, file_priv);
+}
+
+/**
+ * vmw_gb_surface_reference_ext_ioctl - Ioctl function implementing
+ * the user surface reference functionality.
+ *
+ * @dev: Pointer to a struct drm_device.
+ * @data: Pointer to data copied from / to user-space.
+ * @file_priv: Pointer to a drm file private structure.
+ */
+int vmw_gb_surface_reference_ext_ioctl(struct drm_device *dev, void *data,
+				   struct drm_file *file_priv)
+{
+	union drm_vmw_gb_surface_reference_ext_arg *arg =
+	    (union drm_vmw_gb_surface_reference_ext_arg *)data;
+	struct drm_vmw_surface_arg *req = &arg->req;
+	struct drm_vmw_gb_surface_ref_ext_rep *rep = &arg->rep;
+
+	return vmw_gb_surface_reference_internal(dev, req, rep, file_priv);
+}
+
+/**
+ * vmw_gb_surface_define_internal - Ioctl function implementing
+ * the user surface define functionality.
+ *
+ * @dev: Pointer to a struct drm_device.
+ * @req: Request argument from user-space.
+ * @rep: Response argument to user-space.
+ * @file_priv: Pointer to a drm file private structure.
+ */
+static int
+vmw_gb_surface_define_internal(struct drm_device *dev,
+			       struct drm_vmw_gb_surface_create_ext_req *req,
+			       struct drm_vmw_gb_surface_create_rep *rep,
+			       struct drm_file *file_priv)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	struct vmw_user_surface *user_srf;
+	struct vmw_surface *srf;
+	struct vmw_resource *res;
+	struct vmw_resource *tmp;
+	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+	int ret;
+	uint32_t size;
+	uint32_t backup_handle = 0;
+	SVGA3dSurfaceAllFlags svga3d_flags_64 =
+		SVGA3D_FLAGS_64(req->svga3d_flags_upper_32_bits,
+				req->base.svga3d_flags);
+
+	if (!dev_priv->has_sm4_1) {
+		/*
+		 * If SM4_1 is not support then cannot send 64-bit flag to
+		 * device.
+		 */
+		if (req->svga3d_flags_upper_32_bits != 0)
+			return -EINVAL;
+
+		if (req->base.multisample_count != 0)
+			return -EINVAL;
+
+		if (req->multisample_pattern != SVGA3D_MS_PATTERN_NONE)
+			return -EINVAL;
+
+		if (req->quality_level != SVGA3D_MS_QUALITY_NONE)
+			return -EINVAL;
+	}
+
+	if ((svga3d_flags_64 & SVGA3D_SURFACE_MULTISAMPLE) &&
+	    req->base.multisample_count == 0)
+		return -EINVAL;
+
+	if (req->base.mip_levels > DRM_VMW_MAX_MIP_LEVELS)
+		return -EINVAL;
+
+	if (unlikely(vmw_user_surface_size == 0))
+		vmw_user_surface_size = ttm_round_pot(sizeof(*user_srf)) +
+			128;
+
+	size = vmw_user_surface_size + 128;
+
+	/* Define a surface based on the parameters. */
+	ret = vmw_surface_gb_priv_define(dev,
+					 size,
+					 svga3d_flags_64,
+					 req->base.format,
+					 req->base.drm_surface_flags &
+					 drm_vmw_surface_flag_scanout,
+					 req->base.mip_levels,
+					 req->base.multisample_count,
+					 req->base.array_size,
+					 req->base.base_size,
+					 req->multisample_pattern,
+					 req->quality_level,
+					 &srf);
+	if (unlikely(ret != 0))
+		return ret;
+
+	user_srf = container_of(srf, struct vmw_user_surface, srf);
+	if (drm_is_primary_client(file_priv))
+		user_srf->master = drm_master_get(file_priv->master);
+
+	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
+	if (unlikely(ret != 0))
+		return ret;
+
+	res = &user_srf->srf.res;
+
+	if (req->base.buffer_handle != SVGA3D_INVALID_ID) {
+		ret = vmw_user_bo_lookup(tfile, req->base.buffer_handle,
+					 &res->backup,
+					 &user_srf->backup_base);
+		if (ret == 0) {
+			if (res->backup->base.num_pages * PAGE_SIZE <
+			    res->backup_size) {
+				DRM_ERROR("Surface backup buffer too small.\n");
+				vmw_bo_unreference(&res->backup);
+				ret = -EINVAL;
+				goto out_unlock;
+			} else {
+				backup_handle = req->base.buffer_handle;
+			}
+		}
+	} else if (req->base.drm_surface_flags &
+		   drm_vmw_surface_flag_create_buffer)
+		ret = vmw_user_bo_alloc(dev_priv, tfile,
+					res->backup_size,
+					req->base.drm_surface_flags &
+					drm_vmw_surface_flag_shareable,
+					&backup_handle,
+					&res->backup,
+					&user_srf->backup_base);
+
+	if (unlikely(ret != 0)) {
+		vmw_resource_unreference(&res);
+		goto out_unlock;
+	}
+
+	tmp = vmw_resource_reference(res);
+	ret = ttm_prime_object_init(tfile, res->backup_size, &user_srf->prime,
+				    req->base.drm_surface_flags &
+				    drm_vmw_surface_flag_shareable,
+				    VMW_RES_SURFACE,
+				    &vmw_user_surface_base_release, NULL);
+
+	if (unlikely(ret != 0)) {
+		vmw_resource_unreference(&tmp);
+		vmw_resource_unreference(&res);
+		goto out_unlock;
+	}
+
+	rep->handle      = user_srf->prime.base.hash.key;
+	rep->backup_size = res->backup_size;
+	if (res->backup) {
+		rep->buffer_map_handle =
+			drm_vma_node_offset_addr(&res->backup->base.vma_node);
+		rep->buffer_size = res->backup->base.num_pages * PAGE_SIZE;
+		rep->buffer_handle = backup_handle;
+	} else {
+		rep->buffer_map_handle = 0;
+		rep->buffer_size = 0;
+		rep->buffer_handle = SVGA3D_INVALID_ID;
+	}
+
+	vmw_resource_unreference(&res);
+
+out_unlock:
+	ttm_read_unlock(&dev_priv->reservation_sem);
+	return ret;
+}
+
+/**
+ * vmw_gb_surface_reference_internal - Ioctl function implementing
+ * the user surface reference functionality.
+ *
+ * @dev: Pointer to a struct drm_device.
+ * @req: Pointer to user-space request surface arg.
+ * @rep: Pointer to response to user-space.
+ * @file_priv: Pointer to a drm file private structure.
+ */
+static int
+vmw_gb_surface_reference_internal(struct drm_device *dev,
+				  struct drm_vmw_surface_arg *req,
+				  struct drm_vmw_gb_surface_ref_ext_rep *rep,
+				  struct drm_file *file_priv)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+	struct vmw_surface *srf;
+	struct vmw_user_surface *user_srf;
+	struct ttm_base_object *base;
+	uint32_t backup_handle;
+	int ret = -EINVAL;
+
+	ret = vmw_surface_handle_reference(dev_priv, file_priv, req->sid,
+					   req->handle_type, &base);
+	if (unlikely(ret != 0))
+		return ret;
+
+	user_srf = container_of(base, struct vmw_user_surface, prime.base);
+	srf = &user_srf->srf;
+	if (!srf->res.backup) {
+		DRM_ERROR("Shared GB surface is missing a backup buffer.\n");
+		goto out_bad_resource;
+	}
+
+	mutex_lock(&dev_priv->cmdbuf_mutex); /* Protect res->backup */
+	ret = vmw_user_bo_reference(tfile, srf->res.backup, &backup_handle);
+	mutex_unlock(&dev_priv->cmdbuf_mutex);
+
+	if (unlikely(ret != 0)) {
+		DRM_ERROR("Could not add a reference to a GB surface "
+			  "backup buffer.\n");
+		(void) ttm_ref_object_base_unref(tfile, base->hash.key,
+						 TTM_REF_USAGE);
+		goto out_bad_resource;
+	}
+
+	rep->creq.base.svga3d_flags = SVGA3D_FLAGS_LOWER_32(srf->flags);
+	rep->creq.base.format = srf->format;
+	rep->creq.base.mip_levels = srf->mip_levels[0];
+	rep->creq.base.drm_surface_flags = 0;
+	rep->creq.base.multisample_count = srf->multisample_count;
+	rep->creq.base.autogen_filter = srf->autogen_filter;
+	rep->creq.base.array_size = srf->array_size;
+	rep->creq.base.buffer_handle = backup_handle;
+	rep->creq.base.base_size = srf->base_size;
+	rep->crep.handle = user_srf->prime.base.hash.key;
+	rep->crep.backup_size = srf->res.backup_size;
+	rep->crep.buffer_handle = backup_handle;
+	rep->crep.buffer_map_handle =
+		drm_vma_node_offset_addr(&srf->res.backup->base.vma_node);
+	rep->crep.buffer_size = srf->res.backup->base.num_pages * PAGE_SIZE;
+
+	rep->creq.version = drm_vmw_gb_surface_v1;
+	rep->creq.svga3d_flags_upper_32_bits =
+		SVGA3D_FLAGS_UPPER_32(srf->flags);
+	rep->creq.multisample_pattern = srf->multisample_pattern;
+	rep->creq.quality_level = srf->quality_level;
+	rep->creq.must_be_zero = 0;
+
+out_bad_resource:
+	ttm_base_object_unref(&base);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index 21111fd091f9..31786b200afc 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -798,7 +798,7 @@ static int vmw_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 	struct ttm_object_file *tfile =
 		vmw_fpriv((struct drm_file *)filp->private_data)->tfile;
 
-	return vmw_user_dmabuf_verify_access(bo, tfile);
+	return vmw_user_bo_verify_access(bo, tfile);
 }
 
 static int vmw_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem)
@@ -852,7 +852,7 @@ static void vmw_move_notify(struct ttm_buffer_object *bo,
 			    bool evict,
 			    struct ttm_mem_reg *mem)
 {
-	vmw_resource_move_notify(bo, mem);
+	vmw_bo_move_notify(bo, mem);
 	vmw_query_move_notify(bo, mem);
 }
 
@@ -864,7 +864,7 @@ static void vmw_move_notify(struct ttm_buffer_object *bo,
  */
 static void vmw_swap_notify(struct ttm_buffer_object *bo)
 {
-	vmw_resource_swap_notify(bo);
+	vmw_bo_swap_notify(bo);
 	(void) ttm_bo_wait(bo, false, false);
 }
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c
index e771091d2cd3..7b1e5a5cbd2c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2011 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2011 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_va.c b/drivers/gpu/drm/vmwgfx/vmwgfx_va.c
index b4162fd78600..ebc1d83c34b4 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_va.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_va.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2012-2016 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2012-2016 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c
index b3786c1a4e80..6b6d5ab82ec3 100644
--- a/drivers/gpu/drm/xen/xen_drm_front.c
+++ b/drivers/gpu/drm/xen/xen_drm_front.c
@@ -623,7 +623,7 @@ static int displback_initwait(struct xen_drm_front_info *front_info)
 	if (ret < 0)
 		return ret;
 
-	DRM_INFO("Have %d conector(s)\n", cfg->num_connectors);
+	DRM_INFO("Have %d connector(s)\n", cfg->num_connectors);
 	/* Create event channels for all connectors and publish */
 	ret = xen_drm_front_evtchnl_create_all(front_info);
 	if (ret < 0)
diff --git a/drivers/gpu/drm/xen/xen_drm_front.h b/drivers/gpu/drm/xen/xen_drm_front.h
index 2c2479b571ae..5693b4a4b02b 100644
--- a/drivers/gpu/drm/xen/xen_drm_front.h
+++ b/drivers/gpu/drm/xen/xen_drm_front.h
@@ -126,12 +126,12 @@ struct xen_drm_front_drm_info {
 
 static inline u64 xen_drm_front_fb_to_cookie(struct drm_framebuffer *fb)
 {
-	return (u64)fb;
+	return (uintptr_t)fb;
 }
 
 static inline u64 xen_drm_front_dbuf_to_cookie(struct drm_gem_object *gem_obj)
 {
-	return (u64)gem_obj;
+	return (uintptr_t)gem_obj;
 }
 
 int xen_drm_front_mode_set(struct xen_drm_front_drm_pipeline *pipeline,
diff --git a/drivers/gpu/drm/xen/xen_drm_front_shbuf.c b/drivers/gpu/drm/xen/xen_drm_front_shbuf.c
index 8099cb343ae3..d333b67cc1a0 100644
--- a/drivers/gpu/drm/xen/xen_drm_front_shbuf.c
+++ b/drivers/gpu/drm/xen/xen_drm_front_shbuf.c
@@ -122,7 +122,7 @@ static void guest_calc_num_grefs(struct xen_drm_front_shbuf *buf)
 }
 
 #define xen_page_to_vaddr(page) \
-		((phys_addr_t)pfn_to_kaddr(page_to_xen_pfn(page)))
+		((uintptr_t)pfn_to_kaddr(page_to_xen_pfn(page)))
 
 static int backend_unmap(struct xen_drm_front_shbuf *buf)
 {
diff --git a/drivers/gpu/drm/zte/zx_hdmi.c b/drivers/gpu/drm/zte/zx_hdmi.c
index 13ea90f7a185..78655269d843 100644
--- a/drivers/gpu/drm/zte/zx_hdmi.c
+++ b/drivers/gpu/drm/zte/zx_hdmi.c
@@ -272,7 +272,7 @@ static int zx_hdmi_connector_get_modes(struct drm_connector *connector)
 
 	hdmi->sink_is_hdmi = drm_detect_hdmi_monitor(edid);
 	hdmi->sink_has_audio = drm_detect_monitor_audio(edid);
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
 	kfree(edid);
 
@@ -326,7 +326,7 @@ static int zx_hdmi_register(struct drm_device *drm, struct zx_hdmi *hdmi)
 	drm_connector_helper_add(&hdmi->connector,
 				 &zx_hdmi_connector_helper_funcs);
 
-	drm_mode_connector_attach_encoder(&hdmi->connector, encoder);
+	drm_connector_attach_encoder(&hdmi->connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/zte/zx_plane.c b/drivers/gpu/drm/zte/zx_plane.c
index d1931f5ea0b2..ae8c53b4b261 100644
--- a/drivers/gpu/drm/zte/zx_plane.c
+++ b/drivers/gpu/drm/zte/zx_plane.c
@@ -446,7 +446,7 @@ static const struct drm_plane_helper_funcs zx_gl_plane_helper_funcs = {
 
 static void zx_plane_destroy(struct drm_plane *plane)
 {
-	drm_plane_helper_disable(plane);
+	drm_plane_helper_disable(plane, NULL);
 	drm_plane_cleanup(plane);
 }
 
diff --git a/drivers/gpu/drm/zte/zx_tvenc.c b/drivers/gpu/drm/zte/zx_tvenc.c
index 0de1a71ca4e0..b73afb212fb2 100644
--- a/drivers/gpu/drm/zte/zx_tvenc.c
+++ b/drivers/gpu/drm/zte/zx_tvenc.c
@@ -297,7 +297,7 @@ static int zx_tvenc_register(struct drm_device *drm, struct zx_tvenc *tvenc)
 			   DRM_MODE_CONNECTOR_Composite);
 	drm_connector_helper_add(connector, &zx_tvenc_connector_helper_funcs);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/zte/zx_vga.c b/drivers/gpu/drm/zte/zx_vga.c
index 3e7e33cd3dfa..23d1ff4355a0 100644
--- a/drivers/gpu/drm/zte/zx_vga.c
+++ b/drivers/gpu/drm/zte/zx_vga.c
@@ -109,7 +109,7 @@ static int zx_vga_connector_get_modes(struct drm_connector *connector)
 	 */
 	zx_writel(vga->mmio + VGA_AUTO_DETECT_SEL, VGA_DETECT_SEL_HAS_DEVICE);
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
 	kfree(edid);
 
@@ -175,7 +175,7 @@ static int zx_vga_register(struct drm_device *drm, struct zx_vga *vga)
 
 	drm_connector_helper_add(connector, &zx_vga_connector_helper_funcs);
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret) {
 		DRM_DEV_ERROR(dev, "failed to attach encoder: %d\n", ret);
 		goto clean_connector;
diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 48685cddbad1..474b00e19697 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -122,6 +122,8 @@ enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat)
 	case V4L2_PIX_FMT_NV16:
 	case V4L2_PIX_FMT_NV61:
 		return IPUV3_COLORSPACE_YUV;
+	case V4L2_PIX_FMT_XRGB32:
+	case V4L2_PIX_FMT_XBGR32:
 	case V4L2_PIX_FMT_RGB32:
 	case V4L2_PIX_FMT_BGR32:
 	case V4L2_PIX_FMT_RGB24:
@@ -190,6 +192,8 @@ int ipu_stride_to_bytes(u32 pixel_stride, u32 pixelformat)
 		return (24 * pixel_stride) >> 3;
 	case V4L2_PIX_FMT_BGR32:
 	case V4L2_PIX_FMT_RGB32:
+	case V4L2_PIX_FMT_XBGR32:
+	case V4L2_PIX_FMT_XRGB32:
 		return (32 * pixel_stride) >> 3;
 	default:
 		break;
@@ -1401,6 +1405,8 @@ static int ipu_probe(struct platform_device *pdev)
 		return -ENODEV;
 
 	ipu->id = of_alias_get_id(np, "ipu");
+	if (ipu->id < 0)
+		ipu->id = 0;
 
 	if (of_device_is_compatible(np, "fsl,imx6qp-ipu") &&
 	    IS_ENABLED(CONFIG_DRM)) {
diff --git a/drivers/gpu/ipu-v3/ipu-cpmem.c b/drivers/gpu/ipu-v3/ipu-cpmem.c
index 9f2d9ec42add..a9d2501500a1 100644
--- a/drivers/gpu/ipu-v3/ipu-cpmem.c
+++ b/drivers/gpu/ipu-v3/ipu-cpmem.c
@@ -188,6 +188,12 @@ static int v4l2_pix_fmt_to_drm_fourcc(u32 pixelformat)
 	case V4L2_PIX_FMT_RGB32:
 		/* R G B A <=> [32:0] A:B:G:R */
 		return DRM_FORMAT_XBGR8888;
+	case V4L2_PIX_FMT_XBGR32:
+		/* B G R X <=> [32:0] X:R:G:B */
+		return DRM_FORMAT_XRGB8888;
+	case V4L2_PIX_FMT_XRGB32:
+		/* X R G B <=> [32:0] B:G:R:X */
+		return DRM_FORMAT_BGRX8888;
 	case V4L2_PIX_FMT_UYVY:
 		return DRM_FORMAT_UYVY;
 	case V4L2_PIX_FMT_YUYV:
@@ -269,9 +275,20 @@ EXPORT_SYMBOL_GPL(ipu_cpmem_set_uv_offset);
 
 void ipu_cpmem_interlaced_scan(struct ipuv3_channel *ch, int stride)
 {
+	u32 ilo, sly;
+
+	if (stride < 0) {
+		stride = -stride;
+		ilo = 0x100000 - (stride / 8);
+	} else {
+		ilo = stride / 8;
+	}
+
+	sly = (stride * 2) - 1;
+
 	ipu_ch_param_write_field(ch, IPU_FIELD_SO, 1);
-	ipu_ch_param_write_field(ch, IPU_FIELD_ILO, stride / 8);
-	ipu_ch_param_write_field(ch, IPU_FIELD_SLY, (stride * 2) - 1);
+	ipu_ch_param_write_field(ch, IPU_FIELD_ILO, ilo);
+	ipu_ch_param_write_field(ch, IPU_FIELD_SLY, sly);
 };
 EXPORT_SYMBOL_GPL(ipu_cpmem_interlaced_scan);
 
@@ -530,17 +547,17 @@ static const struct ipu_rgb def_bgra_16 = {
 
 #define Y_OFFSET(pix, x, y)	((x) + pix->width * (y))
 #define U_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
-				 (pix->width * (y) / 4) + (x) / 2)
+				 (pix->width * ((y) / 2) / 2) + (x) / 2)
 #define V_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
 				 (pix->width * pix->height / 4) +	\
-				 (pix->width * (y) / 4) + (x) / 2)
+				 (pix->width * ((y) / 2) / 2) + (x) / 2)
 #define U2_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
 				 (pix->width * (y) / 2) + (x) / 2)
 #define V2_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
 				 (pix->width * pix->height / 2) +	\
 				 (pix->width * (y) / 2) + (x) / 2)
 #define UV_OFFSET(pix, x, y)	((pix->width * pix->height) +	\
-				 (pix->width * (y) / 2) + (x))
+				 (pix->width * ((y) / 2)) + (x))
 #define UV2_OFFSET(pix, x, y)	((pix->width * pix->height) +	\
 				 (pix->width * y) + (x))
 
@@ -776,6 +793,8 @@ int ipu_cpmem_set_image(struct ipuv3_channel *ch, struct ipu_image *image)
 		break;
 	case V4L2_PIX_FMT_RGB32:
 	case V4L2_PIX_FMT_BGR32:
+	case V4L2_PIX_FMT_XRGB32:
+	case V4L2_PIX_FMT_XBGR32:
 		offset = image->rect.left * 4 +
 			image->rect.top * pix->bytesperline;
 		break;
diff --git a/drivers/gpu/ipu-v3/ipu-csi.c b/drivers/gpu/ipu-v3/ipu-csi.c
index 5450a2db1219..954eefe144e2 100644
--- a/drivers/gpu/ipu-v3/ipu-csi.c
+++ b/drivers/gpu/ipu-v3/ipu-csi.c
@@ -224,14 +224,18 @@ static int ipu_csi_set_testgen_mclk(struct ipu_csi *csi, u32 pixel_clk,
  * Find the CSI data format and data width for the given V4L2 media
  * bus pixel format code.
  */
-static int mbus_code_to_bus_cfg(struct ipu_csi_bus_config *cfg, u32 mbus_code)
+static int mbus_code_to_bus_cfg(struct ipu_csi_bus_config *cfg, u32 mbus_code,
+				enum v4l2_mbus_type mbus_type)
 {
 	switch (mbus_code) {
 	case MEDIA_BUS_FMT_BGR565_2X8_BE:
 	case MEDIA_BUS_FMT_BGR565_2X8_LE:
 	case MEDIA_BUS_FMT_RGB565_2X8_BE:
 	case MEDIA_BUS_FMT_RGB565_2X8_LE:
-		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_RGB565;
+		if (mbus_type == V4L2_MBUS_CSI2)
+			cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_RGB565;
+		else
+			cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_BAYER;
 		cfg->mipi_dt = MIPI_DT_RGB565;
 		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
 		break;
@@ -247,6 +251,12 @@ static int mbus_code_to_bus_cfg(struct ipu_csi_bus_config *cfg, u32 mbus_code)
 		cfg->mipi_dt = MIPI_DT_RGB555;
 		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
 		break;
+	case MEDIA_BUS_FMT_RGB888_1X24:
+	case MEDIA_BUS_FMT_BGR888_1X24:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_RGB_YUV444;
+		cfg->mipi_dt = MIPI_DT_RGB888;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
+		break;
 	case MEDIA_BUS_FMT_UYVY8_2X8:
 		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_YUV422_UYVY;
 		cfg->mipi_dt = MIPI_DT_YUV422;
@@ -318,13 +328,17 @@ static int mbus_code_to_bus_cfg(struct ipu_csi_bus_config *cfg, u32 mbus_code)
 /*
  * Fill a CSI bus config struct from mbus_config and mbus_framefmt.
  */
-static void fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg,
+static int fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg,
 				 struct v4l2_mbus_config *mbus_cfg,
 				 struct v4l2_mbus_framefmt *mbus_fmt)
 {
+	int ret;
+
 	memset(csicfg, 0, sizeof(*csicfg));
 
-	mbus_code_to_bus_cfg(csicfg, mbus_fmt->code);
+	ret = mbus_code_to_bus_cfg(csicfg, mbus_fmt->code, mbus_cfg->type);
+	if (ret < 0)
+		return ret;
 
 	switch (mbus_cfg->type) {
 	case V4L2_MBUS_PARALLEL:
@@ -356,6 +370,8 @@ static void fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg,
 		/* will never get here, keep compiler quiet */
 		break;
 	}
+
+	return 0;
 }
 
 int ipu_csi_init_interface(struct ipu_csi *csi,
@@ -365,8 +381,11 @@ int ipu_csi_init_interface(struct ipu_csi *csi,
 	struct ipu_csi_bus_config cfg;
 	unsigned long flags;
 	u32 width, height, data = 0;
+	int ret;
 
-	fill_csi_bus_cfg(&cfg, mbus_cfg, mbus_fmt);
+	ret = fill_csi_bus_cfg(&cfg, mbus_cfg, mbus_fmt);
+	if (ret < 0)
+		return ret;
 
 	/* set default sensor frame width and height */
 	width = mbus_fmt->width;
@@ -587,11 +606,14 @@ int ipu_csi_set_mipi_datatype(struct ipu_csi *csi, u32 vc,
 	struct ipu_csi_bus_config cfg;
 	unsigned long flags;
 	u32 temp;
+	int ret;
 
 	if (vc > 3)
 		return -EINVAL;
 
-	mbus_code_to_bus_cfg(&cfg, mbus_fmt->code);
+	ret = mbus_code_to_bus_cfg(&cfg, mbus_fmt->code, V4L2_MBUS_CSI2);
+	if (ret < 0)
+		return ret;
 
 	spin_lock_irqsave(&csi->lock, flags);
 
diff --git a/drivers/gpu/ipu-v3/ipu-image-convert.c b/drivers/gpu/ipu-v3/ipu-image-convert.c
index 524a717ab28e..f4081962784c 100644
--- a/drivers/gpu/ipu-v3/ipu-image-convert.c
+++ b/drivers/gpu/ipu-v3/ipu-image-convert.c
@@ -227,6 +227,12 @@ static const struct ipu_image_pixfmt image_convert_formats[] = {
 		.fourcc	= V4L2_PIX_FMT_BGR32,
 		.bpp    = 32,
 	}, {
+		.fourcc	= V4L2_PIX_FMT_XRGB32,
+		.bpp    = 32,
+	}, {
+		.fourcc	= V4L2_PIX_FMT_XBGR32,
+		.bpp    = 32,
+	}, {
 		.fourcc	= V4L2_PIX_FMT_YUYV,
 		.bpp    = 16,
 		.uv_width_dec = 2,
diff --git a/drivers/gpu/ipu-v3/ipu-pre.c b/drivers/gpu/ipu-v3/ipu-pre.c
index 0f70e8847540..2f8db9d62551 100644
--- a/drivers/gpu/ipu-v3/ipu-pre.c
+++ b/drivers/gpu/ipu-v3/ipu-pre.c
@@ -128,7 +128,8 @@ ipu_pre_lookup_by_phandle(struct device *dev, const char *name, int index)
 	list_for_each_entry(pre, &ipu_pre_list, list) {
 		if (pre_node == pre->dev->of_node) {
 			mutex_unlock(&ipu_pre_list_mutex);
-			device_link_add(dev, pre->dev, DL_FLAG_AUTOREMOVE);
+			device_link_add(dev, pre->dev,
+					DL_FLAG_AUTOREMOVE_CONSUMER);
 			of_node_put(pre_node);
 			return pre;
 		}
diff --git a/drivers/gpu/ipu-v3/ipu-prg.c b/drivers/gpu/ipu-v3/ipu-prg.c
index 83f9dd934a5d..38a3a9764e49 100644
--- a/drivers/gpu/ipu-v3/ipu-prg.c
+++ b/drivers/gpu/ipu-v3/ipu-prg.c
@@ -100,7 +100,8 @@ ipu_prg_lookup_by_phandle(struct device *dev, const char *name, int ipu_id)
 	list_for_each_entry(prg, &ipu_prg_list, list) {
 		if (prg_node == prg->dev->of_node) {
 			mutex_unlock(&ipu_prg_list_mutex);
-			device_link_add(dev, prg->dev, DL_FLAG_AUTOREMOVE);
+			device_link_add(dev, prg->dev,
+					DL_FLAG_AUTOREMOVE_CONSUMER);
 			prg->id = ipu_id;
 			of_node_put(prg_node);
 			return prg;
diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c
index fc4adf3d34e8..a96bf46bc483 100644
--- a/drivers/gpu/vga/vga_switcheroo.c
+++ b/drivers/gpu/vga/vga_switcheroo.c
@@ -103,9 +103,11 @@
  *	runtime pm. If true, writing ON and OFF to the vga_switcheroo debugfs
  *	interface is a no-op so as not to interfere with runtime pm
  * @list: client list
+ * @vga_dev: pci device, indicate which GPU is bound to current audio client
  *
  * Registered client. A client can be either a GPU or an audio device on a GPU.
- * For audio clients, the @fb_info and @active members are bogus.
+ * For audio clients, the @fb_info and @active members are bogus. For GPU
+ * clients, the @vga_dev is bogus.
  */
 struct vga_switcheroo_client {
 	struct pci_dev *pdev;
@@ -116,6 +118,7 @@ struct vga_switcheroo_client {
 	bool active;
 	bool driver_power_control;
 	struct list_head list;
+	struct pci_dev *vga_dev;
 };
 
 /*
@@ -161,9 +164,8 @@ struct vgasr_priv {
 };
 
 #define ID_BIT_AUDIO		0x100
-#define client_is_audio(c)	((c)->id & ID_BIT_AUDIO)
-#define client_is_vga(c)	((c)->id == VGA_SWITCHEROO_UNKNOWN_ID || \
-				 !client_is_audio(c))
+#define client_is_audio(c)		((c)->id & ID_BIT_AUDIO)
+#define client_is_vga(c)		(!client_is_audio(c))
 #define client_id(c)		((c)->id & ~ID_BIT_AUDIO)
 
 static int vga_switcheroo_debugfs_init(struct vgasr_priv *priv);
@@ -192,14 +194,29 @@ static void vga_switcheroo_enable(void)
 		vgasr_priv.handler->init();
 
 	list_for_each_entry(client, &vgasr_priv.clients, list) {
-		if (client->id != VGA_SWITCHEROO_UNKNOWN_ID)
+		if (!client_is_vga(client) ||
+		     client_id(client) != VGA_SWITCHEROO_UNKNOWN_ID)
 			continue;
+
 		ret = vgasr_priv.handler->get_client_id(client->pdev);
 		if (ret < 0)
 			return;
 
 		client->id = ret;
 	}
+
+	list_for_each_entry(client, &vgasr_priv.clients, list) {
+		if (!client_is_audio(client) ||
+		     client_id(client) != VGA_SWITCHEROO_UNKNOWN_ID)
+			continue;
+
+		ret = vgasr_priv.handler->get_client_id(client->vga_dev);
+		if (ret < 0)
+			return;
+
+		client->id = ret | ID_BIT_AUDIO;
+	}
+
 	vga_switcheroo_debugfs_init(&vgasr_priv);
 	vgasr_priv.active = true;
 }
@@ -272,7 +289,9 @@ EXPORT_SYMBOL(vga_switcheroo_handler_flags);
 
 static int register_client(struct pci_dev *pdev,
 			   const struct vga_switcheroo_client_ops *ops,
-			   enum vga_switcheroo_client_id id, bool active,
+			   enum vga_switcheroo_client_id id,
+			   struct pci_dev *vga_dev,
+			   bool active,
 			   bool driver_power_control)
 {
 	struct vga_switcheroo_client *client;
@@ -287,6 +306,7 @@ static int register_client(struct pci_dev *pdev,
 	client->id = id;
 	client->active = active;
 	client->driver_power_control = driver_power_control;
+	client->vga_dev = vga_dev;
 
 	mutex_lock(&vgasr_mutex);
 	list_add_tail(&client->list, &vgasr_priv.clients);
@@ -319,7 +339,7 @@ int vga_switcheroo_register_client(struct pci_dev *pdev,
 				   const struct vga_switcheroo_client_ops *ops,
 				   bool driver_power_control)
 {
-	return register_client(pdev, ops, VGA_SWITCHEROO_UNKNOWN_ID,
+	return register_client(pdev, ops, VGA_SWITCHEROO_UNKNOWN_ID, NULL,
 			       pdev == vga_default_device(),
 			       driver_power_control);
 }
@@ -329,19 +349,40 @@ EXPORT_SYMBOL(vga_switcheroo_register_client);
  * vga_switcheroo_register_audio_client - register audio client
  * @pdev: client pci device
  * @ops: client callbacks
- * @id: client identifier
+ * @vga_dev:  pci device which is bound to current audio client
  *
  * Register audio client (audio device on a GPU). The client is assumed
  * to use runtime PM. Beforehand, vga_switcheroo_client_probe_defer()
  * shall be called to ensure that all prerequisites are met.
  *
- * Return: 0 on success, -ENOMEM on memory allocation error.
+ * Return: 0 on success, -ENOMEM on memory allocation error, -EINVAL on getting
+ * client id error.
  */
 int vga_switcheroo_register_audio_client(struct pci_dev *pdev,
 			const struct vga_switcheroo_client_ops *ops,
-			enum vga_switcheroo_client_id id)
+			struct pci_dev *vga_dev)
 {
-	return register_client(pdev, ops, id | ID_BIT_AUDIO, false, true);
+	enum vga_switcheroo_client_id id = VGA_SWITCHEROO_UNKNOWN_ID;
+
+	/*
+	 * if vga_switcheroo has enabled, that mean two GPU clients and also
+	 * handler are registered. Get audio client id from bound GPU client
+	 * id directly, otherwise, set it as VGA_SWITCHEROO_UNKNOWN_ID,
+	 * it will set to correct id in later when vga_switcheroo_enable()
+	 * is called.
+	 */
+	mutex_lock(&vgasr_mutex);
+	if (vgasr_priv.active) {
+		id = vgasr_priv.handler->get_client_id(vga_dev);
+		if (id < 0) {
+			mutex_unlock(&vgasr_mutex);
+			return -EINVAL;
+		}
+	}
+	mutex_unlock(&vgasr_mutex);
+
+	return register_client(pdev, ops, id | ID_BIT_AUDIO, vga_dev,
+			       false, true);
 }
 EXPORT_SYMBOL(vga_switcheroo_register_audio_client);
 
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index f10840ad465c..ccf42663a908 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -937,6 +937,18 @@ config SENSORS_MCP3021
 	  This driver can also be built as a module.  If so, the module
 	  will be called mcp3021.
 
+config SENSORS_MLXREG_FAN
+	tristate "Mellanox Mellanox FAN driver"
+	depends on MELLANOX_PLATFORM
+	imply THERMAL
+	select REGMAP
+	help
+	  This option enables support for the FAN control on the Mellanox
+	  Ethernet and InfiniBand switches. The driver can be activated by the
+	  platform device add call. Say Y to enable these. To compile this
+	  driver as a module, choose 'M' here: the module will be called
+	  mlxreg-fan.
+
 config SENSORS_TC654
 	tristate "Microchip TC654/TC655 and compatibles"
 	depends on I2C
@@ -1256,6 +1268,16 @@ config SENSORS_NCT7904
 	  This driver can also be built as a module.  If so, the module
 	  will be called nct7904.
 
+config SENSORS_NPCM7XX
+	tristate "Nuvoton NPCM750 and compatible PWM and Fan controllers"
+	imply THERMAL
+	help
+	  This driver provides support for Nuvoton NPCM750/730/715/705 PWM
+          and Fan controllers.
+
+          This driver can also be built as a module. If so, the module
+          will be called npcm750-pwm-fan.
+
 config SENSORS_NSA320
 	tristate "ZyXEL NSA320 and compatible fan speed and temperature sensors"
 	depends on GPIOLIB && OF
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index e7d52a36e6c4..842c92f83ce6 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -129,11 +129,13 @@ obj-$(CONFIG_SENSORS_MAX31790)	+= max31790.o
 obj-$(CONFIG_SENSORS_MC13783_ADC)+= mc13783-adc.o
 obj-$(CONFIG_SENSORS_MCP3021)	+= mcp3021.o
 obj-$(CONFIG_SENSORS_TC654)	+= tc654.o
+obj-$(CONFIG_SENSORS_MLXREG_FAN) += mlxreg-fan.o
 obj-$(CONFIG_SENSORS_MENF21BMC_HWMON) += menf21bmc_hwmon.o
 obj-$(CONFIG_SENSORS_NCT6683)	+= nct6683.o
 obj-$(CONFIG_SENSORS_NCT6775)	+= nct6775.o
 obj-$(CONFIG_SENSORS_NCT7802)	+= nct7802.o
 obj-$(CONFIG_SENSORS_NCT7904)	+= nct7904.o
+obj-$(CONFIG_SENSORS_NPCM7XX)	+= npcm750-pwm-fan.o
 obj-$(CONFIG_SENSORS_NSA320)	+= nsa320-hwmon.o
 obj-$(CONFIG_SENSORS_NTC_THERMISTOR)	+= ntc_thermistor.o
 obj-$(CONFIG_SENSORS_PC87360)	+= pc87360.o
diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c
index 9ef84998c7f3..90837f7c7d0f 100644
--- a/drivers/hwmon/adt7475.c
+++ b/drivers/hwmon/adt7475.c
@@ -194,8 +194,7 @@ struct adt7475_data {
 	struct mutex lock;
 
 	unsigned long measure_updated;
-	unsigned long limits_updated;
-	char valid;
+	bool valid;
 
 	u8 config4;
 	u8 config5;
@@ -326,6 +325,9 @@ static ssize_t show_voltage(struct device *dev, struct device_attribute *attr,
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 	unsigned short val;
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	switch (sattr->nr) {
 	case ALARM:
 		return sprintf(buf, "%d\n",
@@ -381,6 +383,9 @@ static ssize_t show_temp(struct device *dev, struct device_attribute *attr,
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 	int out;
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	switch (sattr->nr) {
 	case HYSTERSIS:
 		mutex_lock(&data->lock);
@@ -625,6 +630,9 @@ static ssize_t show_point2(struct device *dev, struct device_attribute *attr,
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 	int out, val;
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	mutex_lock(&data->lock);
 	out = (data->range[sattr->index] >> 4) & 0x0F;
 	val = reg2temp(data, data->temp[AUTOMIN][sattr->index]);
@@ -683,6 +691,9 @@ static ssize_t show_tach(struct device *dev, struct device_attribute *attr,
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 	int out;
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	if (sattr->nr == ALARM)
 		out = (data->alarms >> (sattr->index + 10)) & 1;
 	else
@@ -720,6 +731,9 @@ static ssize_t show_pwm(struct device *dev, struct device_attribute *attr,
 	struct adt7475_data *data = adt7475_update_device(dev);
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", data->pwm[sattr->nr][sattr->index]);
 }
 
@@ -729,6 +743,9 @@ static ssize_t show_pwmchan(struct device *dev, struct device_attribute *attr,
 	struct adt7475_data *data = adt7475_update_device(dev);
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", data->pwmchan[sattr->index]);
 }
 
@@ -738,6 +755,9 @@ static ssize_t show_pwmctrl(struct device *dev, struct device_attribute *attr,
 	struct adt7475_data *data = adt7475_update_device(dev);
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", data->pwmctl[sattr->index]);
 }
 
@@ -945,6 +965,9 @@ static ssize_t show_pwmfreq(struct device *dev, struct device_attribute *attr,
 	int i = clamp_val(data->range[sattr->index] & 0xf, 0,
 			  ARRAY_SIZE(pwmfreq_table) - 1);
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", pwmfreq_table[i]);
 }
 
@@ -1035,6 +1058,10 @@ static ssize_t cpu0_vid_show(struct device *dev,
 			     struct device_attribute *devattr, char *buf)
 {
 	struct adt7475_data *data = adt7475_update_device(dev);
+
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
 }
 
@@ -1385,6 +1412,121 @@ static void adt7475_remove_files(struct i2c_client *client,
 		sysfs_remove_group(&client->dev.kobj, &vid_attr_group);
 }
 
+static int adt7475_update_limits(struct i2c_client *client)
+{
+	struct adt7475_data *data = i2c_get_clientdata(client);
+	int i;
+	int ret;
+
+	ret = adt7475_read(REG_CONFIG4);
+	if (ret < 0)
+		return ret;
+	data->config4 = ret;
+
+	ret = adt7475_read(REG_CONFIG5);
+	if (ret < 0)
+		return ret;
+	data->config5 = ret;
+
+	for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
+		if (!(data->has_voltage & (1 << i)))
+			continue;
+		/* Adjust values so they match the input precision */
+		ret = adt7475_read(VOLTAGE_MIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->voltage[MIN][i] = ret << 2;
+
+		ret = adt7475_read(VOLTAGE_MAX_REG(i));
+		if (ret < 0)
+			return ret;
+		data->voltage[MAX][i] = ret << 2;
+	}
+
+	if (data->has_voltage & (1 << 5)) {
+		ret = adt7475_read(REG_VTT_MIN);
+		if (ret < 0)
+			return ret;
+		data->voltage[MIN][5] = ret << 2;
+
+		ret = adt7475_read(REG_VTT_MAX);
+		if (ret < 0)
+			return ret;
+		data->voltage[MAX][5] = ret << 2;
+	}
+
+	for (i = 0; i < ADT7475_TEMP_COUNT; i++) {
+		/* Adjust values so they match the input precision */
+		ret = adt7475_read(TEMP_MIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[MIN][i] = ret << 2;
+
+		ret = adt7475_read(TEMP_MAX_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[MAX][i] = ret << 2;
+
+		ret = adt7475_read(TEMP_TMIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[AUTOMIN][i] = ret << 2;
+
+		ret = adt7475_read(TEMP_THERM_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[THERM][i] = ret << 2;
+
+		ret = adt7475_read(TEMP_OFFSET_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[OFFSET][i] = ret;
+	}
+	adt7475_read_hystersis(client);
+
+	for (i = 0; i < ADT7475_TACH_COUNT; i++) {
+		if (i == 3 && !data->has_fan4)
+			continue;
+		ret = adt7475_read_word(client, TACH_MIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->tach[MIN][i] = ret;
+	}
+
+	for (i = 0; i < ADT7475_PWM_COUNT; i++) {
+		if (i == 1 && !data->has_pwm2)
+			continue;
+		ret = adt7475_read(PWM_MAX_REG(i));
+		if (ret < 0)
+			return ret;
+		data->pwm[MAX][i] = ret;
+
+		ret = adt7475_read(PWM_MIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->pwm[MIN][i] = ret;
+		/* Set the channel and control information */
+		adt7475_read_pwm(client, i);
+	}
+
+	ret = adt7475_read(TEMP_TRANGE_REG(0));
+	if (ret < 0)
+		return ret;
+	data->range[0] = ret;
+
+	ret = adt7475_read(TEMP_TRANGE_REG(1));
+	if (ret < 0)
+		return ret;
+	data->range[1] = ret;
+
+	ret = adt7475_read(TEMP_TRANGE_REG(2));
+	if (ret < 0)
+		return ret;
+	data->range[2] = ret;
+
+	return 0;
+}
+
 static int adt7475_probe(struct i2c_client *client,
 			 const struct i2c_device_id *id)
 {
@@ -1562,6 +1704,11 @@ static int adt7475_probe(struct i2c_client *client,
 			 (data->bypass_attn & (1 << 3)) ? " in3" : "",
 			 (data->bypass_attn & (1 << 4)) ? " in4" : "");
 
+	/* Limits and settings, should never change update more than once */
+	ret = adt7475_update_limits(client);
+	if (ret)
+		goto eremove;
+
 	return 0;
 
 eremove:
@@ -1658,121 +1805,122 @@ static void adt7475_read_pwm(struct i2c_client *client, int index)
 	}
 }
 
-static struct adt7475_data *adt7475_update_device(struct device *dev)
+static int adt7475_update_measure(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct adt7475_data *data = i2c_get_clientdata(client);
 	u16 ext;
 	int i;
+	int ret;
 
-	mutex_lock(&data->lock);
+	ret = adt7475_read(REG_STATUS2);
+	if (ret < 0)
+		return ret;
+	data->alarms = ret << 8;
 
-	/* Measurement values update every 2 seconds */
-	if (time_after(jiffies, data->measure_updated + HZ * 2) ||
-	    !data->valid) {
-		data->alarms = adt7475_read(REG_STATUS2) << 8;
-		data->alarms |= adt7475_read(REG_STATUS1);
-
-		ext = (adt7475_read(REG_EXTEND2) << 8) |
-			adt7475_read(REG_EXTEND1);
-		for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
-			if (!(data->has_voltage & (1 << i)))
-				continue;
-			data->voltage[INPUT][i] =
-				(adt7475_read(VOLTAGE_REG(i)) << 2) |
-				((ext >> (i * 2)) & 3);
-		}
+	ret = adt7475_read(REG_STATUS1);
+	if (ret < 0)
+		return ret;
+	data->alarms |= ret;
 
-		for (i = 0; i < ADT7475_TEMP_COUNT; i++)
-			data->temp[INPUT][i] =
-				(adt7475_read(TEMP_REG(i)) << 2) |
-				((ext >> ((i + 5) * 2)) & 3);
+	ret = adt7475_read(REG_EXTEND2);
+	if (ret < 0)
+		return ret;
 
-		if (data->has_voltage & (1 << 5)) {
-			data->alarms |= adt7475_read(REG_STATUS4) << 24;
-			ext = adt7475_read(REG_EXTEND3);
-			data->voltage[INPUT][5] = adt7475_read(REG_VTT) << 2 |
-				((ext >> 4) & 3);
-		}
+	ext = (ret << 8);
 
-		for (i = 0; i < ADT7475_TACH_COUNT; i++) {
-			if (i == 3 && !data->has_fan4)
-				continue;
-			data->tach[INPUT][i] =
-				adt7475_read_word(client, TACH_REG(i));
-		}
+	ret = adt7475_read(REG_EXTEND1);
+	if (ret < 0)
+		return ret;
 
-		/* Updated by hw when in auto mode */
-		for (i = 0; i < ADT7475_PWM_COUNT; i++) {
-			if (i == 1 && !data->has_pwm2)
-				continue;
-			data->pwm[INPUT][i] = adt7475_read(PWM_REG(i));
-		}
+	ext |= ret;
+
+	for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
+		if (!(data->has_voltage & (1 << i)))
+			continue;
+		ret = adt7475_read(VOLTAGE_REG(i));
+		if (ret < 0)
+			return ret;
+		data->voltage[INPUT][i] =
+			(ret << 2) |
+			((ext >> (i * 2)) & 3);
+	}
 
-		if (data->has_vid)
-			data->vid = adt7475_read(REG_VID) & 0x3f;
+	for (i = 0; i < ADT7475_TEMP_COUNT; i++) {
+		ret = adt7475_read(TEMP_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[INPUT][i] =
+			(ret << 2) |
+			((ext >> ((i + 5) * 2)) & 3);
+	}
 
-		data->measure_updated = jiffies;
+	if (data->has_voltage & (1 << 5)) {
+		ret = adt7475_read(REG_STATUS4);
+		if (ret < 0)
+			return ret;
+		data->alarms |= ret << 24;
+
+		ret = adt7475_read(REG_EXTEND3);
+		if (ret < 0)
+			return ret;
+		ext = ret;
+
+		ret = adt7475_read(REG_VTT);
+		if (ret < 0)
+			return ret;
+		data->voltage[INPUT][5] = ret << 2 |
+			((ext >> 4) & 3);
 	}
 
-	/* Limits and settings, should never change update every 60 seconds */
-	if (time_after(jiffies, data->limits_updated + HZ * 60) ||
-	    !data->valid) {
-		data->config4 = adt7475_read(REG_CONFIG4);
-		data->config5 = adt7475_read(REG_CONFIG5);
-
-		for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
-			if (!(data->has_voltage & (1 << i)))
-				continue;
-			/* Adjust values so they match the input precision */
-			data->voltage[MIN][i] =
-				adt7475_read(VOLTAGE_MIN_REG(i)) << 2;
-			data->voltage[MAX][i] =
-				adt7475_read(VOLTAGE_MAX_REG(i)) << 2;
-		}
+	for (i = 0; i < ADT7475_TACH_COUNT; i++) {
+		if (i == 3 && !data->has_fan4)
+			continue;
+		ret = adt7475_read_word(client, TACH_REG(i));
+		if (ret < 0)
+			return ret;
+		data->tach[INPUT][i] = ret;
+	}
 
-		if (data->has_voltage & (1 << 5)) {
-			data->voltage[MIN][5] = adt7475_read(REG_VTT_MIN) << 2;
-			data->voltage[MAX][5] = adt7475_read(REG_VTT_MAX) << 2;
-		}
+	/* Updated by hw when in auto mode */
+	for (i = 0; i < ADT7475_PWM_COUNT; i++) {
+		if (i == 1 && !data->has_pwm2)
+			continue;
+		ret = adt7475_read(PWM_REG(i));
+		if (ret < 0)
+			return ret;
+		data->pwm[INPUT][i] = ret;
+	}
 
-		for (i = 0; i < ADT7475_TEMP_COUNT; i++) {
-			/* Adjust values so they match the input precision */
-			data->temp[MIN][i] =
-				adt7475_read(TEMP_MIN_REG(i)) << 2;
-			data->temp[MAX][i] =
-				adt7475_read(TEMP_MAX_REG(i)) << 2;
-			data->temp[AUTOMIN][i] =
-				adt7475_read(TEMP_TMIN_REG(i)) << 2;
-			data->temp[THERM][i] =
-				adt7475_read(TEMP_THERM_REG(i)) << 2;
-			data->temp[OFFSET][i] =
-				adt7475_read(TEMP_OFFSET_REG(i));
-		}
-		adt7475_read_hystersis(client);
+	if (data->has_vid) {
+		ret = adt7475_read(REG_VID);
+		if (ret < 0)
+			return ret;
+		data->vid = ret & 0x3f;
+	}
 
-		for (i = 0; i < ADT7475_TACH_COUNT; i++) {
-			if (i == 3 && !data->has_fan4)
-				continue;
-			data->tach[MIN][i] =
-				adt7475_read_word(client, TACH_MIN_REG(i));
-		}
+	return 0;
+}
 
-		for (i = 0; i < ADT7475_PWM_COUNT; i++) {
-			if (i == 1 && !data->has_pwm2)
-				continue;
-			data->pwm[MAX][i] = adt7475_read(PWM_MAX_REG(i));
-			data->pwm[MIN][i] = adt7475_read(PWM_MIN_REG(i));
-			/* Set the channel and control information */
-			adt7475_read_pwm(client, i);
-		}
+static struct adt7475_data *adt7475_update_device(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct adt7475_data *data = i2c_get_clientdata(client);
+	int ret;
 
-		data->range[0] = adt7475_read(TEMP_TRANGE_REG(0));
-		data->range[1] = adt7475_read(TEMP_TRANGE_REG(1));
-		data->range[2] = adt7475_read(TEMP_TRANGE_REG(2));
+	mutex_lock(&data->lock);
 
-		data->limits_updated = jiffies;
-		data->valid = 1;
+	/* Measurement values update every 2 seconds */
+	if (time_after(jiffies, data->measure_updated + HZ * 2) ||
+	    !data->valid) {
+		ret = adt7475_update_measure(dev);
+		if (ret) {
+			data->valid = false;
+			mutex_unlock(&data->lock);
+			return ERR_PTR(ret);
+		}
+		data->measure_updated = jiffies;
+		data->valid = true;
 	}
 
 	mutex_unlock(&data->lock);
diff --git a/drivers/hwmon/emc1403.c b/drivers/hwmon/emc1403.c
index 1ea7ca510f84..aaebeb726d6a 100644
--- a/drivers/hwmon/emc1403.c
+++ b/drivers/hwmon/emc1403.c
@@ -443,8 +443,10 @@ static int emc1403_probe(struct i2c_client *client,
 	switch (id->driver_data) {
 	case emc1404:
 		data->groups[2] = &emc1404_group;
+		/* fall through */
 	case emc1403:
 		data->groups[1] = &emc1403_group;
+		/* fall through */
 	case emc1402:
 		data->groups[0] = &emc1402_group;
 	}
diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index e88c01961948..33d51281272b 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -394,12 +394,16 @@ static const char * const hwmon_power_attr_templates[] = {
 	[hwmon_power_cap_hyst] = "power%d_cap_hyst",
 	[hwmon_power_cap_max] = "power%d_cap_max",
 	[hwmon_power_cap_min] = "power%d_cap_min",
+	[hwmon_power_min] = "power%d_min",
 	[hwmon_power_max] = "power%d_max",
+	[hwmon_power_lcrit] = "power%d_lcrit",
 	[hwmon_power_crit] = "power%d_crit",
 	[hwmon_power_label] = "power%d_label",
 	[hwmon_power_alarm] = "power%d_alarm",
 	[hwmon_power_cap_alarm] = "power%d_cap_alarm",
+	[hwmon_power_min_alarm] = "power%d_min_alarm",
 	[hwmon_power_max_alarm] = "power%d_max_alarm",
+	[hwmon_power_lcrit_alarm] = "power%d_lcrit_alarm",
 	[hwmon_power_crit_alarm] = "power%d_crit_alarm",
 };
 
diff --git a/drivers/hwmon/iio_hwmon.c b/drivers/hwmon/iio_hwmon.c
index 69031a0f7ed2..2f3f875c06ac 100644
--- a/drivers/hwmon/iio_hwmon.c
+++ b/drivers/hwmon/iio_hwmon.c
@@ -22,7 +22,6 @@
  * struct iio_hwmon_state - device instance state
  * @channels:		filled with array of channels from iio
  * @num_channels:	number of channels in channels (saves counting twice)
- * @hwmon_dev:		associated hwmon device
  * @attr_group:		the group of attributes
  * @groups:		null terminated array of attribute groups
  * @attrs:		null terminated array of attribute pointers.
@@ -30,7 +29,6 @@
 struct iio_hwmon_state {
 	struct iio_channel *channels;
 	int num_channels;
-	struct device *hwmon_dev;
 	struct attribute_group attr_group;
 	const struct attribute_group *groups[2];
 	struct attribute **attrs;
@@ -68,12 +66,13 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 	enum iio_chan_type type;
 	struct iio_channel *channels;
 	const char *name = "iio_hwmon";
+	struct device *hwmon_dev;
 	char *sname;
 
 	if (dev->of_node && dev->of_node->name)
 		name = dev->of_node->name;
 
-	channels = iio_channel_get_all(dev);
+	channels = devm_iio_channel_get_all(dev);
 	if (IS_ERR(channels)) {
 		if (PTR_ERR(channels) == -ENODEV)
 			return -EPROBE_DEFER;
@@ -81,10 +80,8 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 	}
 
 	st = devm_kzalloc(dev, sizeof(*st), GFP_KERNEL);
-	if (st == NULL) {
-		ret = -ENOMEM;
-		goto error_release_channels;
-	}
+	if (st == NULL)
+		return -ENOMEM;
 
 	st->channels = channels;
 
@@ -95,22 +92,18 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 	st->attrs = devm_kcalloc(dev,
 				 st->num_channels + 1, sizeof(*st->attrs),
 				 GFP_KERNEL);
-	if (st->attrs == NULL) {
-		ret = -ENOMEM;
-		goto error_release_channels;
-	}
+	if (st->attrs == NULL)
+		return -ENOMEM;
 
 	for (i = 0; i < st->num_channels; i++) {
 		a = devm_kzalloc(dev, sizeof(*a), GFP_KERNEL);
-		if (a == NULL) {
-			ret = -ENOMEM;
-			goto error_release_channels;
-		}
+		if (a == NULL)
+			return -ENOMEM;
 
 		sysfs_attr_init(&a->dev_attr.attr);
 		ret = iio_get_channel_type(&st->channels[i], &type);
 		if (ret < 0)
-			goto error_release_channels;
+			return ret;
 
 		switch (type) {
 		case IIO_VOLTAGE:
@@ -134,13 +127,11 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 							       humidity_i++);
 			break;
 		default:
-			ret = -EINVAL;
-			goto error_release_channels;
-		}
-		if (a->dev_attr.attr.name == NULL) {
-			ret = -ENOMEM;
-			goto error_release_channels;
+			return -EINVAL;
 		}
+		if (a->dev_attr.attr.name == NULL)
+			return -ENOMEM;
+
 		a->dev_attr.show = iio_hwmon_read_val;
 		a->dev_attr.attr.mode = S_IRUGO;
 		a->index = i;
@@ -151,34 +142,13 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 	st->groups[0] = &st->attr_group;
 
 	sname = devm_kstrdup(dev, name, GFP_KERNEL);
-	if (!sname) {
-		ret = -ENOMEM;
-		goto error_release_channels;
-	}
+	if (!sname)
+		return -ENOMEM;
 
 	strreplace(sname, '-', '_');
-	st->hwmon_dev = hwmon_device_register_with_groups(dev, sname, st,
-							  st->groups);
-	if (IS_ERR(st->hwmon_dev)) {
-		ret = PTR_ERR(st->hwmon_dev);
-		goto error_release_channels;
-	}
-	platform_set_drvdata(pdev, st);
-	return 0;
-
-error_release_channels:
-	iio_channel_release_all(channels);
-	return ret;
-}
-
-static int iio_hwmon_remove(struct platform_device *pdev)
-{
-	struct iio_hwmon_state *st = platform_get_drvdata(pdev);
-
-	hwmon_device_unregister(st->hwmon_dev);
-	iio_channel_release_all(st->channels);
-
-	return 0;
+	hwmon_dev = devm_hwmon_device_register_with_groups(dev, sname, st,
+							   st->groups);
+	return PTR_ERR_OR_ZERO(hwmon_dev);
 }
 
 static const struct of_device_id iio_hwmon_of_match[] = {
@@ -193,7 +163,6 @@ static struct platform_driver __refdata iio_hwmon_driver = {
 		.of_match_table = iio_hwmon_of_match,
 	},
 	.probe = iio_hwmon_probe,
-	.remove = iio_hwmon_remove,
 };
 
 module_platform_driver(iio_hwmon_driver);
diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index 17c6460ae351..bb15d7816a29 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -99,12 +99,8 @@ static const struct tctl_offset tctl_offset_table[] = {
 	{ 0x17, "AMD Ryzen 7 1700X", 20000 },
 	{ 0x17, "AMD Ryzen 7 1800X", 20000 },
 	{ 0x17, "AMD Ryzen 7 2700X", 10000 },
-	{ 0x17, "AMD Ryzen Threadripper 1950X", 27000 },
-	{ 0x17, "AMD Ryzen Threadripper 1920X", 27000 },
-	{ 0x17, "AMD Ryzen Threadripper 1900X", 27000 },
-	{ 0x17, "AMD Ryzen Threadripper 1950", 10000 },
-	{ 0x17, "AMD Ryzen Threadripper 1920", 10000 },
-	{ 0x17, "AMD Ryzen Threadripper 1910", 10000 },
+	{ 0x17, "AMD Ryzen Threadripper 19", 27000 }, /* 19{00,20,50}X */
+	{ 0x17, "AMD Ryzen Threadripper 29", 27000 }, /* 29{20,50,70,90}[W]X */
 };
 
 static void read_htcreg_pci(struct pci_dev *pdev, u32 *regval)
diff --git a/drivers/hwmon/mlxreg-fan.c b/drivers/hwmon/mlxreg-fan.c
new file mode 100644
index 000000000000..de46577c7d5a
--- /dev/null
+++ b/drivers/hwmon/mlxreg-fan.c
@@ -0,0 +1,489 @@
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+//
+// Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+// Copyright (c) 2018 Vadim Pasternak <vadimp@mellanox.com>
+
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/hwmon.h>
+#include <linux/module.h>
+#include <linux/platform_data/mlxreg.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/thermal.h>
+
+#define MLXREG_FAN_MAX_TACHO		12
+#define MLXREG_FAN_MAX_STATE		10
+#define MLXREG_FAN_MIN_DUTY		51	/* 20% */
+#define MLXREG_FAN_MAX_DUTY		255	/* 100% */
+/*
+ * Minimum and maximum FAN allowed speed in percent: from 20% to 100%. Values
+ * MLXREG_FAN_MAX_STATE + x, where x is between 2 and 10 are used for
+ * setting FAN speed dynamic minimum. For example, if value is set to 14 (40%)
+ * cooling levels vector will be set to 4, 4, 4, 4, 4, 5, 6, 7, 8, 9, 10 to
+ * introduce PWM speed in percent: 40, 40, 40, 40, 40, 50, 60. 70, 80, 90, 100.
+ */
+#define MLXREG_FAN_SPEED_MIN			(MLXREG_FAN_MAX_STATE + 2)
+#define MLXREG_FAN_SPEED_MAX			(MLXREG_FAN_MAX_STATE * 2)
+#define MLXREG_FAN_SPEED_MIN_LEVEL		2	/* 20 percent */
+#define MLXREG_FAN_TACHO_SAMPLES_PER_PULSE_DEF	44
+#define MLXREG_FAN_TACHO_DIVIDER_DEF		1132
+/*
+ * FAN datasheet defines the formula for RPM calculations as RPM = 15/t-high.
+ * The logic in a programmable device measures the time t-high by sampling the
+ * tachometer every t-sample (with the default value 11.32 uS) and increment
+ * a counter (N) as long as the pulse has not change:
+ * RPM = 15 / (t-sample * (K + Regval)), where:
+ * Regval: is the value read from the programmable device register;
+ *  - 0xff - represents tachometer fault;
+ *  - 0xfe - represents tachometer minimum value , which is 4444 RPM;
+ *  - 0x00 - represents tachometer maximum value , which is 300000 RPM;
+ * K: is 44 and it represents the minimum allowed samples per pulse;
+ * N: is equal K + Regval;
+ * In order to calculate RPM from the register value the following formula is
+ * used: RPM = 15 / ((Regval + K) * 11.32) * 10^(-6)), which in  the
+ * default case is modified to:
+ * RPM = 15000000 * 100 / ((Regval + 44) * 1132);
+ * - for Regval 0x00, RPM will be 15000000 * 100 / (44 * 1132) = 30115;
+ * - for Regval 0xfe, RPM will be 15000000 * 100 / ((254 + 44) * 1132) = 4446;
+ * In common case the formula is modified to:
+ * RPM = 15000000 * 100 / ((Regval + samples) * divider).
+ */
+#define MLXREG_FAN_GET_RPM(rval, d, s)	(DIV_ROUND_CLOSEST(15000000 * 100, \
+					 ((rval) + (s)) * (d)))
+#define MLXREG_FAN_GET_FAULT(val, mask) (!!((val) ^ (mask)))
+#define MLXREG_FAN_PWM_DUTY2STATE(duty)	(DIV_ROUND_CLOSEST((duty) *	\
+					 MLXREG_FAN_MAX_STATE,		\
+					 MLXREG_FAN_MAX_DUTY))
+#define MLXREG_FAN_PWM_STATE2DUTY(stat)	(DIV_ROUND_CLOSEST((stat) *	\
+					 MLXREG_FAN_MAX_DUTY,		\
+					 MLXREG_FAN_MAX_STATE))
+
+/*
+ * struct mlxreg_fan_tacho - tachometer data (internal use):
+ *
+ * @connected: indicates if tachometer is connected;
+ * @reg: register offset;
+ * @mask: fault mask;
+ */
+struct mlxreg_fan_tacho {
+	bool connected;
+	u32 reg;
+	u32 mask;
+};
+
+/*
+ * struct mlxreg_fan_pwm - PWM data (internal use):
+ *
+ * @connected: indicates if PWM is connected;
+ * @reg: register offset;
+ */
+struct mlxreg_fan_pwm {
+	bool connected;
+	u32 reg;
+};
+
+/*
+ * struct mlxreg_fan - private data (internal use):
+ *
+ * @dev: basic device;
+ * @regmap: register map of parent device;
+ * @tacho: tachometer data;
+ * @pwm: PWM data;
+ * @samples: minimum allowed samples per pulse;
+ * @divider: divider value for tachometer RPM calculation;
+ * @cooling: cooling device levels;
+ * @cdev: cooling device;
+ */
+struct mlxreg_fan {
+	struct device *dev;
+	void *regmap;
+	struct mlxreg_core_platform_data *pdata;
+	struct mlxreg_fan_tacho tacho[MLXREG_FAN_MAX_TACHO];
+	struct mlxreg_fan_pwm pwm;
+	int samples;
+	int divider;
+	u8 cooling_levels[MLXREG_FAN_MAX_STATE + 1];
+	struct thermal_cooling_device *cdev;
+};
+
+static int
+mlxreg_fan_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+		int channel, long *val)
+{
+	struct mlxreg_fan *fan = dev_get_drvdata(dev);
+	struct mlxreg_fan_tacho *tacho;
+	u32 regval;
+	int err;
+
+	switch (type) {
+	case hwmon_fan:
+		tacho = &fan->tacho[channel];
+		switch (attr) {
+		case hwmon_fan_input:
+			err = regmap_read(fan->regmap, tacho->reg, &regval);
+			if (err)
+				return err;
+
+			*val = MLXREG_FAN_GET_RPM(regval, fan->divider,
+						  fan->samples);
+			break;
+
+		case hwmon_fan_fault:
+			err = regmap_read(fan->regmap, tacho->reg, &regval);
+			if (err)
+				return err;
+
+			*val = MLXREG_FAN_GET_FAULT(regval, tacho->mask);
+			break;
+
+		default:
+			return -EOPNOTSUPP;
+		}
+		break;
+
+	case hwmon_pwm:
+		switch (attr) {
+		case hwmon_pwm_input:
+			err = regmap_read(fan->regmap, fan->pwm.reg, &regval);
+			if (err)
+				return err;
+
+			*val = regval;
+			break;
+
+		default:
+			return -EOPNOTSUPP;
+		}
+		break;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+mlxreg_fan_write(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+		 int channel, long val)
+{
+	struct mlxreg_fan *fan = dev_get_drvdata(dev);
+
+	switch (type) {
+	case hwmon_pwm:
+		switch (attr) {
+		case hwmon_pwm_input:
+			if (val < MLXREG_FAN_MIN_DUTY ||
+			    val > MLXREG_FAN_MAX_DUTY)
+				return -EINVAL;
+			return regmap_write(fan->regmap, fan->pwm.reg, val);
+		default:
+			return -EOPNOTSUPP;
+		}
+		break;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static umode_t
+mlxreg_fan_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr,
+		      int channel)
+{
+	switch (type) {
+	case hwmon_fan:
+		if (!(((struct mlxreg_fan *)data)->tacho[channel].connected))
+			return 0;
+
+		switch (attr) {
+		case hwmon_fan_input:
+		case hwmon_fan_fault:
+			return 0444;
+		default:
+			break;
+		}
+		break;
+
+	case hwmon_pwm:
+		if (!(((struct mlxreg_fan *)data)->pwm.connected))
+			return 0;
+
+		switch (attr) {
+		case hwmon_pwm_input:
+			return 0644;
+		default:
+			break;
+		}
+		break;
+
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static const u32 mlxreg_fan_hwmon_fan_config[] = {
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	0
+};
+
+static const struct hwmon_channel_info mlxreg_fan_hwmon_fan = {
+	.type = hwmon_fan,
+	.config = mlxreg_fan_hwmon_fan_config,
+};
+
+static const u32 mlxreg_fan_hwmon_pwm_config[] = {
+	HWMON_PWM_INPUT,
+	0
+};
+
+static const struct hwmon_channel_info mlxreg_fan_hwmon_pwm = {
+	.type = hwmon_pwm,
+	.config = mlxreg_fan_hwmon_pwm_config,
+};
+
+static const struct hwmon_channel_info *mlxreg_fan_hwmon_info[] = {
+	&mlxreg_fan_hwmon_fan,
+	&mlxreg_fan_hwmon_pwm,
+	NULL
+};
+
+static const struct hwmon_ops mlxreg_fan_hwmon_hwmon_ops = {
+	.is_visible = mlxreg_fan_is_visible,
+	.read = mlxreg_fan_read,
+	.write = mlxreg_fan_write,
+};
+
+static const struct hwmon_chip_info mlxreg_fan_hwmon_chip_info = {
+	.ops = &mlxreg_fan_hwmon_hwmon_ops,
+	.info = mlxreg_fan_hwmon_info,
+};
+
+static int mlxreg_fan_get_max_state(struct thermal_cooling_device *cdev,
+				    unsigned long *state)
+{
+	*state = MLXREG_FAN_MAX_STATE;
+	return 0;
+}
+
+static int mlxreg_fan_get_cur_state(struct thermal_cooling_device *cdev,
+				    unsigned long *state)
+
+{
+	struct mlxreg_fan *fan = cdev->devdata;
+	u32 regval;
+	int err;
+
+	err = regmap_read(fan->regmap, fan->pwm.reg, &regval);
+	if (err) {
+		dev_err(fan->dev, "Failed to query PWM duty\n");
+		return err;
+	}
+
+	*state = MLXREG_FAN_PWM_DUTY2STATE(regval);
+
+	return 0;
+}
+
+static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev,
+				    unsigned long state)
+
+{
+	struct mlxreg_fan *fan = cdev->devdata;
+	unsigned long cur_state;
+	u32 regval;
+	int i;
+	int err;
+
+	/*
+	 * Verify if this request is for changing allowed FAN dynamical
+	 * minimum. If it is - update cooling levels accordingly and update
+	 * state, if current state is below the newly requested minimum state.
+	 * For example, if current state is 5, and minimal state is to be
+	 * changed from 4 to 6, fan->cooling_levels[0 to 5] will be changed all
+	 * from 4 to 6. And state 5 (fan->cooling_levels[4]) should be
+	 * overwritten.
+	 */
+	if (state >= MLXREG_FAN_SPEED_MIN && state <= MLXREG_FAN_SPEED_MAX) {
+		state -= MLXREG_FAN_MAX_STATE;
+		for (i = 0; i < state; i++)
+			fan->cooling_levels[i] = state;
+		for (i = state; i <= MLXREG_FAN_MAX_STATE; i++)
+			fan->cooling_levels[i] = i;
+
+		err = regmap_read(fan->regmap, fan->pwm.reg, &regval);
+		if (err) {
+			dev_err(fan->dev, "Failed to query PWM duty\n");
+			return err;
+		}
+
+		cur_state = MLXREG_FAN_PWM_DUTY2STATE(regval);
+		if (state < cur_state)
+			return 0;
+
+		state = cur_state;
+	}
+
+	if (state > MLXREG_FAN_MAX_STATE)
+		return -EINVAL;
+
+	/* Normalize the state to the valid speed range. */
+	state = fan->cooling_levels[state];
+	err = regmap_write(fan->regmap, fan->pwm.reg,
+			   MLXREG_FAN_PWM_STATE2DUTY(state));
+	if (err) {
+		dev_err(fan->dev, "Failed to write PWM duty\n");
+		return err;
+	}
+	return 0;
+}
+
+static const struct thermal_cooling_device_ops mlxreg_fan_cooling_ops = {
+	.get_max_state	= mlxreg_fan_get_max_state,
+	.get_cur_state	= mlxreg_fan_get_cur_state,
+	.set_cur_state	= mlxreg_fan_set_cur_state,
+};
+
+static int mlxreg_fan_config(struct mlxreg_fan *fan,
+			     struct mlxreg_core_platform_data *pdata)
+{
+	struct mlxreg_core_data *data = pdata->data;
+	bool configured = false;
+	int tacho_num = 0, i;
+
+	fan->samples = MLXREG_FAN_TACHO_SAMPLES_PER_PULSE_DEF;
+	fan->divider = MLXREG_FAN_TACHO_DIVIDER_DEF;
+	for (i = 0; i < pdata->counter; i++, data++) {
+		if (strnstr(data->label, "tacho", sizeof(data->label))) {
+			if (tacho_num == MLXREG_FAN_MAX_TACHO) {
+				dev_err(fan->dev, "too many tacho entries: %s\n",
+					data->label);
+				return -EINVAL;
+			}
+			fan->tacho[tacho_num].reg = data->reg;
+			fan->tacho[tacho_num].mask = data->mask;
+			fan->tacho[tacho_num++].connected = true;
+		} else if (strnstr(data->label, "pwm", sizeof(data->label))) {
+			if (fan->pwm.connected) {
+				dev_err(fan->dev, "duplicate pwm entry: %s\n",
+					data->label);
+				return -EINVAL;
+			}
+			fan->pwm.reg = data->reg;
+			fan->pwm.connected = true;
+		} else if (strnstr(data->label, "conf", sizeof(data->label))) {
+			if (configured) {
+				dev_err(fan->dev, "duplicate conf entry: %s\n",
+					data->label);
+				return -EINVAL;
+			}
+			/* Validate that conf parameters are not zeros. */
+			if (!data->mask || !data->bit) {
+				dev_err(fan->dev, "invalid conf entry params: %s\n",
+					data->label);
+				return -EINVAL;
+			}
+			fan->samples = data->mask;
+			fan->divider = data->bit;
+			configured = true;
+		} else {
+			dev_err(fan->dev, "invalid label: %s\n", data->label);
+			return -EINVAL;
+		}
+	}
+
+	/* Init cooling levels per PWM state. */
+	for (i = 0; i < MLXREG_FAN_SPEED_MIN_LEVEL; i++)
+		fan->cooling_levels[i] = MLXREG_FAN_SPEED_MIN_LEVEL;
+	for (i = MLXREG_FAN_SPEED_MIN_LEVEL; i <= MLXREG_FAN_MAX_STATE; i++)
+		fan->cooling_levels[i] = i;
+
+	return 0;
+}
+
+static int mlxreg_fan_probe(struct platform_device *pdev)
+{
+	struct mlxreg_core_platform_data *pdata;
+	struct mlxreg_fan *fan;
+	struct device *hwm;
+	int err;
+
+	pdata = dev_get_platdata(&pdev->dev);
+	if (!pdata) {
+		dev_err(&pdev->dev, "Failed to get platform data.\n");
+		return -EINVAL;
+	}
+
+	fan = devm_kzalloc(&pdev->dev, sizeof(*fan), GFP_KERNEL);
+	if (!fan)
+		return -ENOMEM;
+
+	fan->dev = &pdev->dev;
+	fan->regmap = pdata->regmap;
+	platform_set_drvdata(pdev, fan);
+
+	err = mlxreg_fan_config(fan, pdata);
+	if (err)
+		return err;
+
+	hwm = devm_hwmon_device_register_with_info(&pdev->dev, "mlxreg_fan",
+						   fan,
+						   &mlxreg_fan_hwmon_chip_info,
+						   NULL);
+	if (IS_ERR(hwm)) {
+		dev_err(&pdev->dev, "Failed to register hwmon device\n");
+		return PTR_ERR(hwm);
+	}
+
+	if (IS_REACHABLE(CONFIG_THERMAL)) {
+		fan->cdev = thermal_cooling_device_register("mlxreg_fan", fan,
+						&mlxreg_fan_cooling_ops);
+		if (IS_ERR(fan->cdev)) {
+			dev_err(&pdev->dev, "Failed to register cooling device\n");
+			return PTR_ERR(fan->cdev);
+		}
+	}
+
+	return 0;
+}
+
+static int mlxreg_fan_remove(struct platform_device *pdev)
+{
+	struct mlxreg_fan *fan = platform_get_drvdata(pdev);
+
+	if (IS_REACHABLE(CONFIG_THERMAL))
+		thermal_cooling_device_unregister(fan->cdev);
+
+	return 0;
+}
+
+static struct platform_driver mlxreg_fan_driver = {
+	.driver = {
+	    .name = "mlxreg-fan",
+	},
+	.probe = mlxreg_fan_probe,
+	.remove = mlxreg_fan_remove,
+};
+
+module_platform_driver(mlxreg_fan_driver);
+
+MODULE_AUTHOR("Vadim Pasternak <vadimp@mellanox.com>");
+MODULE_DESCRIPTION("Mellanox FAN driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mlxreg-fan");
diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index f9d1349c3286..c6bd61e4695a 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -1050,8 +1050,8 @@ struct nct6775_data {
 	u64 beeps;
 
 	u8 pwm_num;	/* number of pwm */
-	u8 pwm_mode[NUM_FAN];	/* 1->DC variable voltage,
-				 * 0->PWM variable duty cycle
+	u8 pwm_mode[NUM_FAN];	/* 0->DC variable voltage,
+				 * 1->PWM variable duty cycle
 				 */
 	enum pwm_enable pwm_enable[NUM_FAN];
 			/* 0->off
@@ -2541,7 +2541,7 @@ static void pwm_update_registers(struct nct6775_data *data, int nr)
 	case thermal_cruise:
 		nct6775_write_value(data, data->REG_TARGET[nr],
 				    data->target_temp[nr]);
-		/* intentional */
+		/* fall through  */
 	default:
 		reg = nct6775_read_value(data, data->REG_FAN_MODE[nr]);
 		reg = (reg & ~data->tolerance_mask) |
diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c
index 95a68ab175c7..7815ddf149f6 100644
--- a/drivers/hwmon/nct7904.c
+++ b/drivers/hwmon/nct7904.c
@@ -77,7 +77,7 @@ struct nct7904_data {
 };
 
 /* Access functions */
-static int nct7904_bank_lock(struct nct7904_data *data, unsigned bank)
+static int nct7904_bank_lock(struct nct7904_data *data, unsigned int bank)
 {
 	int ret;
 
@@ -99,7 +99,7 @@ static inline void nct7904_bank_release(struct nct7904_data *data)
 
 /* Read 1-byte register. Returns unsigned reg or -ERRNO on error. */
 static int nct7904_read_reg(struct nct7904_data *data,
-			    unsigned bank, unsigned reg)
+			    unsigned int bank, unsigned int reg)
 {
 	struct i2c_client *client = data->client;
 	int ret;
@@ -117,7 +117,7 @@ static int nct7904_read_reg(struct nct7904_data *data,
  * -ERRNO on error.
  */
 static int nct7904_read_reg16(struct nct7904_data *data,
-			      unsigned bank, unsigned reg)
+			      unsigned int bank, unsigned int reg)
 {
 	struct i2c_client *client = data->client;
 	int ret, hi;
@@ -139,7 +139,7 @@ static int nct7904_read_reg16(struct nct7904_data *data,
 
 /* Write 1-byte register. Returns 0 or -ERRNO on error. */
 static int nct7904_write_reg(struct nct7904_data *data,
-			     unsigned bank, unsigned reg, u8 val)
+			     unsigned int bank, unsigned int reg, u8 val)
 {
 	struct i2c_client *client = data->client;
 	int ret;
@@ -159,7 +159,7 @@ static int nct7904_read_fan(struct device *dev, u32 attr, int channel,
 	unsigned int cnt, rpm;
 	int ret;
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_fan_input:
 		ret = nct7904_read_reg16(data, BANK_0,
 					 FANIN1_HV_REG + channel * 2);
@@ -200,7 +200,7 @@ static int nct7904_read_in(struct device *dev, u32 attr, int channel,
 
 	index = nct7904_chan_to_index[channel];
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_in_input:
 		ret = nct7904_read_reg16(data, BANK_0,
 					 VSEN1_HV_REG + index * 2);
@@ -236,7 +236,7 @@ static int nct7904_read_temp(struct device *dev, u32 attr, int channel,
 	struct nct7904_data *data = dev_get_drvdata(dev);
 	int ret, temp;
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_temp_input:
 		if (channel == 0)
 			ret = nct7904_read_reg16(data, BANK_0, LTD_HV_REG);
@@ -276,7 +276,7 @@ static int nct7904_read_pwm(struct device *dev, u32 attr, int channel,
 	struct nct7904_data *data = dev_get_drvdata(dev);
 	int ret;
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_pwm_input:
 		ret = nct7904_read_reg(data, BANK_3, FANCTL1_OUT_REG + channel);
 		if (ret < 0)
@@ -301,7 +301,7 @@ static int nct7904_write_pwm(struct device *dev, u32 attr, int channel,
 	struct nct7904_data *data = dev_get_drvdata(dev);
 	int ret;
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_pwm_input:
 		if (val < 0 || val > 255)
 			return -EINVAL;
@@ -322,7 +322,7 @@ static int nct7904_write_pwm(struct device *dev, u32 attr, int channel,
 
 static umode_t nct7904_pwm_is_visible(const void *_data, u32 attr, int channel)
 {
-	switch(attr) {
+	switch (attr) {
 	case hwmon_pwm_input:
 	case hwmon_pwm_enable:
 		return S_IRUGO | S_IWUSR;
@@ -431,15 +431,15 @@ static const struct hwmon_channel_info nct7904_in = {
 };
 
 static const u32 nct7904_fan_config[] = {
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-	    0
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	0
 };
 
 static const struct hwmon_channel_info nct7904_fan = {
@@ -448,11 +448,11 @@ static const struct hwmon_channel_info nct7904_fan = {
 };
 
 static const u32 nct7904_pwm_config[] = {
-            HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-            HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-            HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-            HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-	    0
+	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+	0
 };
 
 static const struct hwmon_channel_info nct7904_pwm = {
@@ -461,16 +461,16 @@ static const struct hwmon_channel_info nct7904_pwm = {
 };
 
 static const u32 nct7904_temp_config[] = {
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-	    0
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	0
 };
 
 static const struct hwmon_channel_info nct7904_temp = {
diff --git a/drivers/hwmon/npcm750-pwm-fan.c b/drivers/hwmon/npcm750-pwm-fan.c
new file mode 100644
index 000000000000..8474d601aa63
--- /dev/null
+++ b/drivers/hwmon/npcm750-pwm-fan.c
@@ -0,0 +1,1057 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2014-2018 Nuvoton Technology corporation.
+
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+#include <linux/sysfs.h>
+#include <linux/thermal.h>
+
+/* NPCM7XX PWM registers */
+#define NPCM7XX_PWM_REG_BASE(base, n)    ((base) + ((n) * 0x1000L))
+
+#define NPCM7XX_PWM_REG_PR(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x00)
+#define NPCM7XX_PWM_REG_CSR(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x04)
+#define NPCM7XX_PWM_REG_CR(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x08)
+#define NPCM7XX_PWM_REG_CNRx(base, n, ch) \
+			(NPCM7XX_PWM_REG_BASE(base, n) + 0x0C + (12 * (ch)))
+#define NPCM7XX_PWM_REG_CMRx(base, n, ch) \
+			(NPCM7XX_PWM_REG_BASE(base, n) + 0x10 + (12 * (ch)))
+#define NPCM7XX_PWM_REG_PDRx(base, n, ch) \
+			(NPCM7XX_PWM_REG_BASE(base, n) + 0x14 + (12 * (ch)))
+#define NPCM7XX_PWM_REG_PIER(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x3C)
+#define NPCM7XX_PWM_REG_PIIR(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x40)
+
+#define NPCM7XX_PWM_CTRL_CH0_MODE_BIT		BIT(3)
+#define NPCM7XX_PWM_CTRL_CH1_MODE_BIT		BIT(11)
+#define NPCM7XX_PWM_CTRL_CH2_MODE_BIT		BIT(15)
+#define NPCM7XX_PWM_CTRL_CH3_MODE_BIT		BIT(19)
+
+#define NPCM7XX_PWM_CTRL_CH0_INV_BIT		BIT(2)
+#define NPCM7XX_PWM_CTRL_CH1_INV_BIT		BIT(10)
+#define NPCM7XX_PWM_CTRL_CH2_INV_BIT		BIT(14)
+#define NPCM7XX_PWM_CTRL_CH3_INV_BIT		BIT(18)
+
+#define NPCM7XX_PWM_CTRL_CH0_EN_BIT		BIT(0)
+#define NPCM7XX_PWM_CTRL_CH1_EN_BIT		BIT(8)
+#define NPCM7XX_PWM_CTRL_CH2_EN_BIT		BIT(12)
+#define NPCM7XX_PWM_CTRL_CH3_EN_BIT		BIT(16)
+
+/* Define the maximum PWM channel number */
+#define NPCM7XX_PWM_MAX_CHN_NUM			8
+#define NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE	4
+#define NPCM7XX_PWM_MAX_MODULES                 2
+
+/* Define the Counter Register, value = 100 for match 100% */
+#define NPCM7XX_PWM_COUNTER_DEFAULT_NUM		255
+#define NPCM7XX_PWM_CMR_DEFAULT_NUM		127
+#define NPCM7XX_PWM_CMR_MAX			255
+
+/* default all PWM channels PRESCALE2 = 1 */
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH0	0x4
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH1	0x40
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH2	0x400
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH3	0x4000
+
+#define PWM_OUTPUT_FREQ_25KHZ			25000
+#define PWN_CNT_DEFAULT				256
+#define MIN_PRESCALE1				2
+#define NPCM7XX_PWM_PRESCALE_SHIFT_CH01		8
+
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT	(NPCM7XX_PWM_PRESCALE2_DEFAULT_CH0 | \
+					NPCM7XX_PWM_PRESCALE2_DEFAULT_CH1 | \
+					NPCM7XX_PWM_PRESCALE2_DEFAULT_CH2 | \
+					NPCM7XX_PWM_PRESCALE2_DEFAULT_CH3)
+
+#define NPCM7XX_PWM_CTRL_MODE_DEFAULT	(NPCM7XX_PWM_CTRL_CH0_MODE_BIT | \
+					NPCM7XX_PWM_CTRL_CH1_MODE_BIT | \
+					NPCM7XX_PWM_CTRL_CH2_MODE_BIT | \
+					NPCM7XX_PWM_CTRL_CH3_MODE_BIT)
+
+/* NPCM7XX FAN Tacho registers */
+#define NPCM7XX_FAN_REG_BASE(base, n)	((base) + ((n) * 0x1000L))
+
+#define NPCM7XX_FAN_REG_TCNT1(base, n)    (NPCM7XX_FAN_REG_BASE(base, n) + 0x00)
+#define NPCM7XX_FAN_REG_TCRA(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x02)
+#define NPCM7XX_FAN_REG_TCRB(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x04)
+#define NPCM7XX_FAN_REG_TCNT2(base, n)    (NPCM7XX_FAN_REG_BASE(base, n) + 0x06)
+#define NPCM7XX_FAN_REG_TPRSC(base, n)    (NPCM7XX_FAN_REG_BASE(base, n) + 0x08)
+#define NPCM7XX_FAN_REG_TCKC(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x0A)
+#define NPCM7XX_FAN_REG_TMCTRL(base, n)   (NPCM7XX_FAN_REG_BASE(base, n) + 0x0C)
+#define NPCM7XX_FAN_REG_TICTRL(base, n)   (NPCM7XX_FAN_REG_BASE(base, n) + 0x0E)
+#define NPCM7XX_FAN_REG_TICLR(base, n)    (NPCM7XX_FAN_REG_BASE(base, n) + 0x10)
+#define NPCM7XX_FAN_REG_TIEN(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x12)
+#define NPCM7XX_FAN_REG_TCPA(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x14)
+#define NPCM7XX_FAN_REG_TCPB(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x16)
+#define NPCM7XX_FAN_REG_TCPCFG(base, n)   (NPCM7XX_FAN_REG_BASE(base, n) + 0x18)
+#define NPCM7XX_FAN_REG_TINASEL(base, n)  (NPCM7XX_FAN_REG_BASE(base, n) + 0x1A)
+#define NPCM7XX_FAN_REG_TINBSEL(base, n)  (NPCM7XX_FAN_REG_BASE(base, n) + 0x1C)
+
+#define NPCM7XX_FAN_TCKC_CLKX_NONE	0
+#define NPCM7XX_FAN_TCKC_CLK1_APB	BIT(0)
+#define NPCM7XX_FAN_TCKC_CLK2_APB	BIT(3)
+
+#define NPCM7XX_FAN_TMCTRL_TBEN		BIT(6)
+#define NPCM7XX_FAN_TMCTRL_TAEN		BIT(5)
+#define NPCM7XX_FAN_TMCTRL_TBEDG	BIT(4)
+#define NPCM7XX_FAN_TMCTRL_TAEDG	BIT(3)
+#define NPCM7XX_FAN_TMCTRL_MODE_5	BIT(2)
+
+#define NPCM7XX_FAN_TICLR_CLEAR_ALL	GENMASK(5, 0)
+#define NPCM7XX_FAN_TICLR_TFCLR		BIT(5)
+#define NPCM7XX_FAN_TICLR_TECLR		BIT(4)
+#define NPCM7XX_FAN_TICLR_TDCLR		BIT(3)
+#define NPCM7XX_FAN_TICLR_TCCLR		BIT(2)
+#define NPCM7XX_FAN_TICLR_TBCLR		BIT(1)
+#define NPCM7XX_FAN_TICLR_TACLR		BIT(0)
+
+#define NPCM7XX_FAN_TIEN_ENABLE_ALL	GENMASK(5, 0)
+#define NPCM7XX_FAN_TIEN_TFIEN		BIT(5)
+#define NPCM7XX_FAN_TIEN_TEIEN		BIT(4)
+#define NPCM7XX_FAN_TIEN_TDIEN		BIT(3)
+#define NPCM7XX_FAN_TIEN_TCIEN		BIT(2)
+#define NPCM7XX_FAN_TIEN_TBIEN		BIT(1)
+#define NPCM7XX_FAN_TIEN_TAIEN		BIT(0)
+
+#define NPCM7XX_FAN_TICTRL_TFPND	BIT(5)
+#define NPCM7XX_FAN_TICTRL_TEPND	BIT(4)
+#define NPCM7XX_FAN_TICTRL_TDPND	BIT(3)
+#define NPCM7XX_FAN_TICTRL_TCPND	BIT(2)
+#define NPCM7XX_FAN_TICTRL_TBPND	BIT(1)
+#define NPCM7XX_FAN_TICTRL_TAPND	BIT(0)
+
+#define NPCM7XX_FAN_TCPCFG_HIBEN	BIT(7)
+#define NPCM7XX_FAN_TCPCFG_EQBEN	BIT(6)
+#define NPCM7XX_FAN_TCPCFG_LOBEN	BIT(5)
+#define NPCM7XX_FAN_TCPCFG_CPBSEL	BIT(4)
+#define NPCM7XX_FAN_TCPCFG_HIAEN	BIT(3)
+#define NPCM7XX_FAN_TCPCFG_EQAEN	BIT(2)
+#define NPCM7XX_FAN_TCPCFG_LOAEN	BIT(1)
+#define NPCM7XX_FAN_TCPCFG_CPASEL	BIT(0)
+
+/* FAN General Definition */
+/* Define the maximum FAN channel number */
+#define NPCM7XX_FAN_MAX_MODULE			8
+#define NPCM7XX_FAN_MAX_CHN_NUM_IN_A_MODULE	2
+#define NPCM7XX_FAN_MAX_CHN_NUM			16
+
+/*
+ * Get Fan Tach Timeout (base on clock 214843.75Hz, 1 cnt = 4.654us)
+ * Timeout 94ms ~= 0x5000
+ * (The minimum FAN speed could to support ~640RPM/pulse 1,
+ * 320RPM/pulse 2, ...-- 10.6Hz)
+ */
+#define NPCM7XX_FAN_TIMEOUT	0x5000
+#define NPCM7XX_FAN_TCNT	0xFFFF
+#define NPCM7XX_FAN_TCPA	(NPCM7XX_FAN_TCNT - NPCM7XX_FAN_TIMEOUT)
+#define NPCM7XX_FAN_TCPB	(NPCM7XX_FAN_TCNT - NPCM7XX_FAN_TIMEOUT)
+
+#define NPCM7XX_FAN_POLL_TIMER_200MS			200
+#define NPCM7XX_FAN_DEFAULT_PULSE_PER_REVOLUTION	2
+#define NPCM7XX_FAN_TINASEL_FANIN_DEFAULT		0
+#define NPCM7XX_FAN_CLK_PRESCALE			255
+
+#define NPCM7XX_FAN_CMPA				0
+#define NPCM7XX_FAN_CMPB				1
+
+/* Obtain the fan number */
+#define NPCM7XX_FAN_INPUT(fan, cmp)		(((fan) << 1) + (cmp))
+
+/* fan sample status */
+#define FAN_DISABLE				0xFF
+#define FAN_INIT				0x00
+#define FAN_PREPARE_TO_GET_FIRST_CAPTURE	0x01
+#define FAN_ENOUGH_SAMPLE			0x02
+
+struct npcm7xx_fan_dev {
+	u8 fan_st_flg;
+	u8 fan_pls_per_rev;
+	u16 fan_cnt;
+	u32 fan_cnt_tmp;
+};
+
+struct npcm7xx_cooling_device {
+	char name[THERMAL_NAME_LENGTH];
+	struct npcm7xx_pwm_fan_data *data;
+	struct thermal_cooling_device *tcdev;
+	int pwm_port;
+	u8 *cooling_levels;
+	u8 max_state;
+	u8 cur_state;
+};
+
+struct npcm7xx_pwm_fan_data {
+	void __iomem *pwm_base;
+	void __iomem *fan_base;
+	unsigned long pwm_clk_freq;
+	unsigned long fan_clk_freq;
+	struct clk *pwm_clk;
+	struct clk *fan_clk;
+	struct mutex pwm_lock[NPCM7XX_PWM_MAX_MODULES];
+	spinlock_t fan_lock[NPCM7XX_FAN_MAX_MODULE];
+	int fan_irq[NPCM7XX_FAN_MAX_MODULE];
+	bool pwm_present[NPCM7XX_PWM_MAX_CHN_NUM];
+	bool fan_present[NPCM7XX_FAN_MAX_CHN_NUM];
+	u32 input_clk_freq;
+	struct timer_list fan_timer;
+	struct npcm7xx_fan_dev fan_dev[NPCM7XX_FAN_MAX_CHN_NUM];
+	struct npcm7xx_cooling_device *cdev[NPCM7XX_PWM_MAX_CHN_NUM];
+	u8 fan_select;
+};
+
+static int npcm7xx_pwm_config_set(struct npcm7xx_pwm_fan_data *data,
+				  int channel, u16 val)
+{
+	u32 pwm_ch = (channel % NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+	u32 module = (channel / NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+	u32 tmp_buf, ctrl_en_bit, env_bit;
+
+	/*
+	 * Config PWM Comparator register for setting duty cycle
+	 */
+	mutex_lock(&data->pwm_lock[module]);
+
+	/* write new CMR value  */
+	iowrite32(val, NPCM7XX_PWM_REG_CMRx(data->pwm_base, module, pwm_ch));
+	tmp_buf = ioread32(NPCM7XX_PWM_REG_CR(data->pwm_base, module));
+
+	switch (pwm_ch) {
+	case 0:
+		ctrl_en_bit = NPCM7XX_PWM_CTRL_CH0_EN_BIT;
+		env_bit = NPCM7XX_PWM_CTRL_CH0_INV_BIT;
+		break;
+	case 1:
+		ctrl_en_bit = NPCM7XX_PWM_CTRL_CH1_EN_BIT;
+		env_bit = NPCM7XX_PWM_CTRL_CH1_INV_BIT;
+		break;
+	case 2:
+		ctrl_en_bit = NPCM7XX_PWM_CTRL_CH2_EN_BIT;
+		env_bit = NPCM7XX_PWM_CTRL_CH2_INV_BIT;
+		break;
+	case 3:
+		ctrl_en_bit = NPCM7XX_PWM_CTRL_CH3_EN_BIT;
+		env_bit = NPCM7XX_PWM_CTRL_CH3_INV_BIT;
+		break;
+	default:
+		mutex_unlock(&data->pwm_lock[module]);
+		return -ENODEV;
+	}
+
+	if (val == 0) {
+		/* Disable PWM */
+		tmp_buf &= ~ctrl_en_bit;
+		tmp_buf |= env_bit;
+	} else {
+		/* Enable PWM */
+		tmp_buf |= ctrl_en_bit;
+		tmp_buf &= ~env_bit;
+	}
+
+	iowrite32(tmp_buf, NPCM7XX_PWM_REG_CR(data->pwm_base, module));
+	mutex_unlock(&data->pwm_lock[module]);
+
+	return 0;
+}
+
+static inline void npcm7xx_fan_start_capture(struct npcm7xx_pwm_fan_data *data,
+					     u8 fan, u8 cmp)
+{
+	u8 fan_id;
+	u8 reg_mode;
+	u8 reg_int;
+	unsigned long flags;
+
+	fan_id = NPCM7XX_FAN_INPUT(fan, cmp);
+
+	/* to check whether any fan tach is enable */
+	if (data->fan_dev[fan_id].fan_st_flg != FAN_DISABLE) {
+		/* reset status */
+		spin_lock_irqsave(&data->fan_lock[fan], flags);
+
+		data->fan_dev[fan_id].fan_st_flg = FAN_INIT;
+		reg_int = ioread8(NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+		/*
+		 * the interrupt enable bits do not need to be cleared before
+		 * it sets, the interrupt enable bits are cleared only on reset.
+		 * the clock unit control register is behaving in the same
+		 * manner that the interrupt enable register behave.
+		 */
+		if (cmp == NPCM7XX_FAN_CMPA) {
+			/* enable interrupt */
+			iowrite8(reg_int | (NPCM7XX_FAN_TIEN_TAIEN |
+					    NPCM7XX_FAN_TIEN_TEIEN),
+				 NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+			reg_mode = NPCM7XX_FAN_TCKC_CLK1_APB
+				| ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base,
+							       fan));
+
+			/* start to Capture */
+			iowrite8(reg_mode, NPCM7XX_FAN_REG_TCKC(data->fan_base,
+								fan));
+		} else {
+			/* enable interrupt */
+			iowrite8(reg_int | (NPCM7XX_FAN_TIEN_TBIEN |
+					    NPCM7XX_FAN_TIEN_TFIEN),
+				 NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+			reg_mode =
+				NPCM7XX_FAN_TCKC_CLK2_APB
+				| ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base,
+							       fan));
+
+			/* start to Capture */
+			iowrite8(reg_mode,
+				 NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+		}
+
+		spin_unlock_irqrestore(&data->fan_lock[fan], flags);
+	}
+}
+
+/*
+ * Enable a background timer to poll fan tach value, (200ms * 4)
+ * to polling all fan
+ */
+static void npcm7xx_fan_polling(struct timer_list *t)
+{
+	struct npcm7xx_pwm_fan_data *data;
+	int i;
+
+	data = from_timer(data, t, fan_timer);
+
+	/*
+	 * Polling two module per one round,
+	 * FAN01 & FAN89 / FAN23 & FAN1011 / FAN45 & FAN1213 / FAN67 & FAN1415
+	 */
+	for (i = data->fan_select; i < NPCM7XX_FAN_MAX_MODULE;
+	      i = i + 4) {
+		/* clear the flag and reset the counter (TCNT) */
+		iowrite8(NPCM7XX_FAN_TICLR_CLEAR_ALL,
+			 NPCM7XX_FAN_REG_TICLR(data->fan_base, i));
+
+		if (data->fan_present[i * 2]) {
+			iowrite16(NPCM7XX_FAN_TCNT,
+				  NPCM7XX_FAN_REG_TCNT1(data->fan_base, i));
+			npcm7xx_fan_start_capture(data, i, NPCM7XX_FAN_CMPA);
+		}
+		if (data->fan_present[(i * 2) + 1]) {
+			iowrite16(NPCM7XX_FAN_TCNT,
+				  NPCM7XX_FAN_REG_TCNT2(data->fan_base, i));
+			npcm7xx_fan_start_capture(data, i, NPCM7XX_FAN_CMPB);
+		}
+	}
+
+	data->fan_select++;
+	data->fan_select &= 0x3;
+
+	/* reset the timer interval */
+	data->fan_timer.expires = jiffies +
+		msecs_to_jiffies(NPCM7XX_FAN_POLL_TIMER_200MS);
+	add_timer(&data->fan_timer);
+}
+
+static inline void npcm7xx_fan_compute(struct npcm7xx_pwm_fan_data *data,
+				       u8 fan, u8 cmp, u8 fan_id, u8 flag_int,
+				       u8 flag_mode, u8 flag_clear)
+{
+	u8  reg_int;
+	u8  reg_mode;
+	u16 fan_cap;
+
+	if (cmp == NPCM7XX_FAN_CMPA)
+		fan_cap = ioread16(NPCM7XX_FAN_REG_TCRA(data->fan_base, fan));
+	else
+		fan_cap = ioread16(NPCM7XX_FAN_REG_TCRB(data->fan_base, fan));
+
+	/* clear capature flag, H/W will auto reset the NPCM7XX_FAN_TCNTx */
+	iowrite8(flag_clear, NPCM7XX_FAN_REG_TICLR(data->fan_base, fan));
+
+	if (data->fan_dev[fan_id].fan_st_flg == FAN_INIT) {
+		/* First capture, drop it */
+		data->fan_dev[fan_id].fan_st_flg =
+			FAN_PREPARE_TO_GET_FIRST_CAPTURE;
+
+		/* reset counter */
+		data->fan_dev[fan_id].fan_cnt_tmp = 0;
+	} else if (data->fan_dev[fan_id].fan_st_flg < FAN_ENOUGH_SAMPLE) {
+		/*
+		 * collect the enough sample,
+		 * (ex: 2 pulse fan need to get 2 sample)
+		 */
+		data->fan_dev[fan_id].fan_cnt_tmp +=
+			(NPCM7XX_FAN_TCNT - fan_cap);
+
+		data->fan_dev[fan_id].fan_st_flg++;
+	} else {
+		/* get enough sample or fan disable */
+		if (data->fan_dev[fan_id].fan_st_flg == FAN_ENOUGH_SAMPLE) {
+			data->fan_dev[fan_id].fan_cnt_tmp +=
+				(NPCM7XX_FAN_TCNT - fan_cap);
+
+			/* compute finial average cnt per pulse */
+			data->fan_dev[fan_id].fan_cnt =
+				data->fan_dev[fan_id].fan_cnt_tmp /
+				FAN_ENOUGH_SAMPLE;
+
+			data->fan_dev[fan_id].fan_st_flg = FAN_INIT;
+		}
+
+		reg_int =  ioread8(NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+		/* disable interrupt */
+		iowrite8((reg_int & ~flag_int),
+			 NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+		reg_mode =  ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+
+		/* stop capturing */
+		iowrite8((reg_mode & ~flag_mode),
+			 NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+	}
+}
+
+static inline void npcm7xx_check_cmp(struct npcm7xx_pwm_fan_data *data,
+				     u8 fan, u8 cmp, u8 flag)
+{
+	u8 reg_int;
+	u8 reg_mode;
+	u8 flag_timeout;
+	u8 flag_cap;
+	u8 flag_clear;
+	u8 flag_int;
+	u8 flag_mode;
+	u8 fan_id;
+
+	fan_id = NPCM7XX_FAN_INPUT(fan, cmp);
+
+	if (cmp == NPCM7XX_FAN_CMPA) {
+		flag_cap = NPCM7XX_FAN_TICTRL_TAPND;
+		flag_timeout = NPCM7XX_FAN_TICTRL_TEPND;
+		flag_int = NPCM7XX_FAN_TIEN_TAIEN | NPCM7XX_FAN_TIEN_TEIEN;
+		flag_mode = NPCM7XX_FAN_TCKC_CLK1_APB;
+		flag_clear = NPCM7XX_FAN_TICLR_TACLR | NPCM7XX_FAN_TICLR_TECLR;
+	} else {
+		flag_cap = NPCM7XX_FAN_TICTRL_TBPND;
+		flag_timeout = NPCM7XX_FAN_TICTRL_TFPND;
+		flag_int = NPCM7XX_FAN_TIEN_TBIEN | NPCM7XX_FAN_TIEN_TFIEN;
+		flag_mode = NPCM7XX_FAN_TCKC_CLK2_APB;
+		flag_clear = NPCM7XX_FAN_TICLR_TBCLR | NPCM7XX_FAN_TICLR_TFCLR;
+	}
+
+	if (flag & flag_timeout) {
+		reg_int =  ioread8(NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+		/* disable interrupt */
+		iowrite8((reg_int & ~flag_int),
+			 NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+		/* clear interrupt flag */
+		iowrite8(flag_clear,
+			 NPCM7XX_FAN_REG_TICLR(data->fan_base, fan));
+
+		reg_mode =  ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+
+		/* stop capturing */
+		iowrite8((reg_mode & ~flag_mode),
+			 NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+
+		/*
+		 *  If timeout occurs (NPCM7XX_FAN_TIMEOUT), the fan doesn't
+		 *  connect or speed is lower than 10.6Hz (320RPM/pulse2).
+		 *  In these situation, the RPM output should be zero.
+		 */
+		data->fan_dev[fan_id].fan_cnt = 0;
+	} else {
+	    /* input capture is occurred */
+		if (flag & flag_cap)
+			npcm7xx_fan_compute(data, fan, cmp, fan_id, flag_int,
+					    flag_mode, flag_clear);
+	}
+}
+
+static irqreturn_t npcm7xx_fan_isr(int irq, void *dev_id)
+{
+	struct npcm7xx_pwm_fan_data *data = dev_id;
+	unsigned long flags;
+	int module;
+	u8 flag;
+
+	module = irq - data->fan_irq[0];
+	spin_lock_irqsave(&data->fan_lock[module], flags);
+
+	flag = ioread8(NPCM7XX_FAN_REG_TICTRL(data->fan_base, module));
+	if (flag > 0) {
+		npcm7xx_check_cmp(data, module, NPCM7XX_FAN_CMPA, flag);
+		npcm7xx_check_cmp(data, module, NPCM7XX_FAN_CMPB, flag);
+		spin_unlock_irqrestore(&data->fan_lock[module], flags);
+		return IRQ_HANDLED;
+	}
+
+	spin_unlock_irqrestore(&data->fan_lock[module], flags);
+
+	return IRQ_NONE;
+}
+
+static int npcm7xx_read_pwm(struct device *dev, u32 attr, int channel,
+			    long *val)
+{
+	struct npcm7xx_pwm_fan_data *data = dev_get_drvdata(dev);
+	u32 pmw_ch = (channel % NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+	u32 module = (channel / NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+
+	switch (attr) {
+	case hwmon_pwm_input:
+		*val = ioread32
+			(NPCM7XX_PWM_REG_CMRx(data->pwm_base, module, pmw_ch));
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int npcm7xx_write_pwm(struct device *dev, u32 attr, int channel,
+			     long val)
+{
+	struct npcm7xx_pwm_fan_data *data = dev_get_drvdata(dev);
+	int err;
+
+	switch (attr) {
+	case hwmon_pwm_input:
+		if (val < 0 || val > NPCM7XX_PWM_CMR_MAX)
+			return -EINVAL;
+		err = npcm7xx_pwm_config_set(data, channel, (u16)val);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+static umode_t npcm7xx_pwm_is_visible(const void *_data, u32 attr, int channel)
+{
+	const struct npcm7xx_pwm_fan_data *data = _data;
+
+	if (!data->pwm_present[channel])
+		return 0;
+
+	switch (attr) {
+	case hwmon_pwm_input:
+		return 0644;
+	default:
+		return 0;
+	}
+}
+
+static int npcm7xx_read_fan(struct device *dev, u32 attr, int channel,
+			    long *val)
+{
+	struct npcm7xx_pwm_fan_data *data = dev_get_drvdata(dev);
+
+	switch (attr) {
+	case hwmon_fan_input:
+		*val = 0;
+		if (data->fan_dev[channel].fan_cnt <= 0)
+			return data->fan_dev[channel].fan_cnt;
+
+		/* Convert the raw reading to RPM */
+		if (data->fan_dev[channel].fan_cnt > 0 &&
+		    data->fan_dev[channel].fan_pls_per_rev > 0)
+			*val = ((data->input_clk_freq * 60) /
+				(data->fan_dev[channel].fan_cnt *
+				 data->fan_dev[channel].fan_pls_per_rev));
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static umode_t npcm7xx_fan_is_visible(const void *_data, u32 attr, int channel)
+{
+	const struct npcm7xx_pwm_fan_data *data = _data;
+
+	if (!data->fan_present[channel])
+		return 0;
+
+	switch (attr) {
+	case hwmon_fan_input:
+		return 0444;
+	default:
+		return 0;
+	}
+}
+
+static int npcm7xx_read(struct device *dev, enum hwmon_sensor_types type,
+			u32 attr, int channel, long *val)
+{
+	switch (type) {
+	case hwmon_pwm:
+		return npcm7xx_read_pwm(dev, attr, channel, val);
+	case hwmon_fan:
+		return npcm7xx_read_fan(dev, attr, channel, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int npcm7xx_write(struct device *dev, enum hwmon_sensor_types type,
+			 u32 attr, int channel, long val)
+{
+	switch (type) {
+	case hwmon_pwm:
+		return npcm7xx_write_pwm(dev, attr, channel, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static umode_t npcm7xx_is_visible(const void *data,
+				  enum hwmon_sensor_types type,
+				  u32 attr, int channel)
+{
+	switch (type) {
+	case hwmon_pwm:
+		return npcm7xx_pwm_is_visible(data, attr, channel);
+	case hwmon_fan:
+		return npcm7xx_fan_is_visible(data, attr, channel);
+	default:
+		return 0;
+	}
+}
+
+static const u32 npcm7xx_pwm_config[] = {
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	0
+};
+
+static const struct hwmon_channel_info npcm7xx_pwm = {
+	.type = hwmon_pwm,
+	.config = npcm7xx_pwm_config,
+};
+
+static const u32 npcm7xx_fan_config[] = {
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	0
+};
+
+static const struct hwmon_channel_info npcm7xx_fan = {
+	.type = hwmon_fan,
+	.config = npcm7xx_fan_config,
+};
+
+static const struct hwmon_channel_info *npcm7xx_info[] = {
+	&npcm7xx_pwm,
+	&npcm7xx_fan,
+	NULL
+};
+
+static const struct hwmon_ops npcm7xx_hwmon_ops = {
+	.is_visible = npcm7xx_is_visible,
+	.read = npcm7xx_read,
+	.write = npcm7xx_write,
+};
+
+static const struct hwmon_chip_info npcm7xx_chip_info = {
+	.ops = &npcm7xx_hwmon_ops,
+	.info = npcm7xx_info,
+};
+
+static u32 npcm7xx_pwm_init(struct npcm7xx_pwm_fan_data *data)
+{
+	int m, ch;
+	u32 prescale_val, output_freq;
+
+	data->pwm_clk_freq = clk_get_rate(data->pwm_clk);
+
+	/* Adjust NPCM7xx PWMs output frequency to ~25Khz */
+	output_freq = data->pwm_clk_freq / PWN_CNT_DEFAULT;
+	prescale_val = DIV_ROUND_CLOSEST(output_freq, PWM_OUTPUT_FREQ_25KHZ);
+
+	/* If prescale_val = 0, then the prescale output clock is stopped */
+	if (prescale_val < MIN_PRESCALE1)
+		prescale_val = MIN_PRESCALE1;
+	/*
+	 * prescale_val need to decrement in one because in the PWM Prescale
+	 * register the Prescale value increment by one
+	 */
+	prescale_val--;
+
+	/* Setting PWM Prescale Register value register to both modules */
+	prescale_val |= (prescale_val << NPCM7XX_PWM_PRESCALE_SHIFT_CH01);
+
+	for (m = 0; m < NPCM7XX_PWM_MAX_MODULES  ; m++) {
+		iowrite32(prescale_val, NPCM7XX_PWM_REG_PR(data->pwm_base, m));
+		iowrite32(NPCM7XX_PWM_PRESCALE2_DEFAULT,
+			  NPCM7XX_PWM_REG_CSR(data->pwm_base, m));
+		iowrite32(NPCM7XX_PWM_CTRL_MODE_DEFAULT,
+			  NPCM7XX_PWM_REG_CR(data->pwm_base, m));
+
+		for (ch = 0; ch < NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE; ch++) {
+			iowrite32(NPCM7XX_PWM_COUNTER_DEFAULT_NUM,
+				  NPCM7XX_PWM_REG_CNRx(data->pwm_base, m, ch));
+		}
+	}
+
+	return output_freq / ((prescale_val & 0xf) + 1);
+}
+
+static void npcm7xx_fan_init(struct npcm7xx_pwm_fan_data *data)
+{
+	int md;
+	int ch;
+	int i;
+	u32 apb_clk_freq;
+
+	for (md = 0; md < NPCM7XX_FAN_MAX_MODULE; md++) {
+		/* stop FAN0~7 clock */
+		iowrite8(NPCM7XX_FAN_TCKC_CLKX_NONE,
+			 NPCM7XX_FAN_REG_TCKC(data->fan_base, md));
+
+		/* disable all interrupt */
+		iowrite8(0x00, NPCM7XX_FAN_REG_TIEN(data->fan_base, md));
+
+		/* clear all interrupt */
+		iowrite8(NPCM7XX_FAN_TICLR_CLEAR_ALL,
+			 NPCM7XX_FAN_REG_TICLR(data->fan_base, md));
+
+		/* set FAN0~7 clock prescaler */
+		iowrite8(NPCM7XX_FAN_CLK_PRESCALE,
+			 NPCM7XX_FAN_REG_TPRSC(data->fan_base, md));
+
+		/* set FAN0~7 mode (high-to-low transition) */
+		iowrite8((NPCM7XX_FAN_TMCTRL_MODE_5 | NPCM7XX_FAN_TMCTRL_TBEN |
+			  NPCM7XX_FAN_TMCTRL_TAEN),
+			 NPCM7XX_FAN_REG_TMCTRL(data->fan_base, md));
+
+		/* set FAN0~7 Initial Count/Cap */
+		iowrite16(NPCM7XX_FAN_TCNT,
+			  NPCM7XX_FAN_REG_TCNT1(data->fan_base, md));
+		iowrite16(NPCM7XX_FAN_TCNT,
+			  NPCM7XX_FAN_REG_TCNT2(data->fan_base, md));
+
+		/* set FAN0~7 compare (equal to count) */
+		iowrite8((NPCM7XX_FAN_TCPCFG_EQAEN | NPCM7XX_FAN_TCPCFG_EQBEN),
+			 NPCM7XX_FAN_REG_TCPCFG(data->fan_base, md));
+
+		/* set FAN0~7 compare value */
+		iowrite16(NPCM7XX_FAN_TCPA,
+			  NPCM7XX_FAN_REG_TCPA(data->fan_base, md));
+		iowrite16(NPCM7XX_FAN_TCPB,
+			  NPCM7XX_FAN_REG_TCPB(data->fan_base, md));
+
+		/* set FAN0~7 fan input FANIN 0~15 */
+		iowrite8(NPCM7XX_FAN_TINASEL_FANIN_DEFAULT,
+			 NPCM7XX_FAN_REG_TINASEL(data->fan_base, md));
+		iowrite8(NPCM7XX_FAN_TINASEL_FANIN_DEFAULT,
+			 NPCM7XX_FAN_REG_TINBSEL(data->fan_base, md));
+
+		for (i = 0; i < NPCM7XX_FAN_MAX_CHN_NUM_IN_A_MODULE; i++) {
+			ch = md * NPCM7XX_FAN_MAX_CHN_NUM_IN_A_MODULE + i;
+			data->fan_dev[ch].fan_st_flg = FAN_DISABLE;
+			data->fan_dev[ch].fan_pls_per_rev =
+				NPCM7XX_FAN_DEFAULT_PULSE_PER_REVOLUTION;
+			data->fan_dev[ch].fan_cnt = 0;
+		}
+	}
+
+	apb_clk_freq = clk_get_rate(data->fan_clk);
+
+	/* Fan tach input clock = APB clock / prescalar, default is 255. */
+	data->input_clk_freq = apb_clk_freq / (NPCM7XX_FAN_CLK_PRESCALE + 1);
+}
+
+static int
+npcm7xx_pwm_cz_get_max_state(struct thermal_cooling_device *tcdev,
+			     unsigned long *state)
+{
+	struct npcm7xx_cooling_device *cdev = tcdev->devdata;
+
+	*state = cdev->max_state;
+
+	return 0;
+}
+
+static int
+npcm7xx_pwm_cz_get_cur_state(struct thermal_cooling_device *tcdev,
+			     unsigned long *state)
+{
+	struct npcm7xx_cooling_device *cdev = tcdev->devdata;
+
+	*state = cdev->cur_state;
+
+	return 0;
+}
+
+static int
+npcm7xx_pwm_cz_set_cur_state(struct thermal_cooling_device *tcdev,
+			     unsigned long state)
+{
+	struct npcm7xx_cooling_device *cdev = tcdev->devdata;
+	int ret;
+
+	if (state > cdev->max_state)
+		return -EINVAL;
+
+	cdev->cur_state = state;
+	ret = npcm7xx_pwm_config_set(cdev->data, cdev->pwm_port,
+				     cdev->cooling_levels[cdev->cur_state]);
+
+	return ret;
+}
+
+static const struct thermal_cooling_device_ops npcm7xx_pwm_cool_ops = {
+	.get_max_state = npcm7xx_pwm_cz_get_max_state,
+	.get_cur_state = npcm7xx_pwm_cz_get_cur_state,
+	.set_cur_state = npcm7xx_pwm_cz_set_cur_state,
+};
+
+static int npcm7xx_create_pwm_cooling(struct device *dev,
+				      struct device_node *child,
+				      struct npcm7xx_pwm_fan_data *data,
+				      u32 pwm_port, u8 num_levels)
+{
+	int ret;
+	struct npcm7xx_cooling_device *cdev;
+
+	cdev = devm_kzalloc(dev, sizeof(*cdev), GFP_KERNEL);
+	if (!cdev)
+		return -ENOMEM;
+
+	cdev->cooling_levels = devm_kzalloc(dev, num_levels, GFP_KERNEL);
+	if (!cdev->cooling_levels)
+		return -ENOMEM;
+
+	cdev->max_state = num_levels - 1;
+	ret = of_property_read_u8_array(child, "cooling-levels",
+					cdev->cooling_levels,
+					num_levels);
+	if (ret) {
+		dev_err(dev, "Property 'cooling-levels' cannot be read.\n");
+		return ret;
+	}
+	snprintf(cdev->name, THERMAL_NAME_LENGTH, "%s%d", child->name,
+		 pwm_port);
+
+	cdev->tcdev = thermal_of_cooling_device_register(child,
+							 cdev->name,
+							 cdev,
+							 &npcm7xx_pwm_cool_ops);
+	if (IS_ERR(cdev->tcdev))
+		return PTR_ERR(cdev->tcdev);
+
+	cdev->data = data;
+	cdev->pwm_port = pwm_port;
+
+	data->cdev[pwm_port] = cdev;
+
+	return 0;
+}
+
+static int npcm7xx_en_pwm_fan(struct device *dev,
+			      struct device_node *child,
+			      struct npcm7xx_pwm_fan_data *data)
+{
+	u8 *fan_ch;
+	u32 pwm_port;
+	int ret, fan_cnt;
+	u8 index, ch;
+
+	ret = of_property_read_u32(child, "reg", &pwm_port);
+	if (ret)
+		return ret;
+
+	data->pwm_present[pwm_port] = true;
+	ret = npcm7xx_pwm_config_set(data, pwm_port,
+				     NPCM7XX_PWM_CMR_DEFAULT_NUM);
+
+	ret = of_property_count_u8_elems(child, "cooling-levels");
+	if (ret > 0) {
+		ret = npcm7xx_create_pwm_cooling(dev, child, data, pwm_port,
+						 ret);
+		if (ret)
+			return ret;
+	}
+
+	fan_cnt = of_property_count_u8_elems(child, "fan-tach-ch");
+	if (fan_cnt < 1)
+		return -EINVAL;
+
+	fan_ch = devm_kzalloc(dev, sizeof(*fan_ch) * fan_cnt, GFP_KERNEL);
+	if (!fan_ch)
+		return -ENOMEM;
+
+	ret = of_property_read_u8_array(child, "fan-tach-ch", fan_ch, fan_cnt);
+	if (ret)
+		return ret;
+
+	for (ch = 0; ch < fan_cnt; ch++) {
+		index = fan_ch[ch];
+		data->fan_present[index] = true;
+		data->fan_dev[index].fan_st_flg = FAN_INIT;
+	}
+
+	return 0;
+}
+
+static int npcm7xx_pwm_fan_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np, *child;
+	struct npcm7xx_pwm_fan_data *data;
+	struct resource *res;
+	struct device *hwmon;
+	char name[20];
+	int ret, cnt;
+	u32 output_freq;
+	u32 i;
+
+	np = dev->of_node;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "pwm");
+	if (!res) {
+		dev_err(dev, "pwm resource not found\n");
+		return -ENODEV;
+	}
+
+	data->pwm_base = devm_ioremap_resource(dev, res);
+	dev_dbg(dev, "pwm base resource is %pR\n", res);
+	if (IS_ERR(data->pwm_base))
+		return PTR_ERR(data->pwm_base);
+
+	data->pwm_clk = devm_clk_get(dev, "pwm");
+	if (IS_ERR(data->pwm_clk)) {
+		dev_err(dev, "couldn't get pwm clock\n");
+		return PTR_ERR(data->pwm_clk);
+	}
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "fan");
+	if (!res) {
+		dev_err(dev, "fan resource not found\n");
+		return -ENODEV;
+	}
+
+	data->fan_base = devm_ioremap_resource(dev, res);
+	dev_dbg(dev, "fan base resource is %pR\n", res);
+	if (IS_ERR(data->fan_base))
+		return PTR_ERR(data->fan_base);
+
+	data->fan_clk = devm_clk_get(dev, "fan");
+	if (IS_ERR(data->fan_clk)) {
+		dev_err(dev, "couldn't get fan clock\n");
+		return PTR_ERR(data->fan_clk);
+	}
+
+	output_freq = npcm7xx_pwm_init(data);
+	npcm7xx_fan_init(data);
+
+	for (cnt = 0; cnt < NPCM7XX_PWM_MAX_MODULES  ; cnt++)
+		mutex_init(&data->pwm_lock[cnt]);
+
+	for (i = 0; i < NPCM7XX_FAN_MAX_MODULE; i++) {
+		spin_lock_init(&data->fan_lock[i]);
+
+		data->fan_irq[i] = platform_get_irq(pdev, i);
+		if (data->fan_irq[i] < 0) {
+			dev_err(dev, "get IRQ fan%d failed\n", i);
+			return data->fan_irq[i];
+		}
+
+		sprintf(name, "NPCM7XX-FAN-MD%d", i);
+		ret = devm_request_irq(dev, data->fan_irq[i], npcm7xx_fan_isr,
+				       0, name, (void *)data);
+		if (ret) {
+			dev_err(dev, "register IRQ fan%d failed\n", i);
+			return ret;
+		}
+	}
+
+	for_each_child_of_node(np, child) {
+		ret = npcm7xx_en_pwm_fan(dev, child, data);
+		if (ret) {
+			dev_err(dev, "enable pwm and fan failed\n");
+			of_node_put(child);
+			return ret;
+		}
+	}
+
+	hwmon = devm_hwmon_device_register_with_info(dev, "npcm7xx_pwm_fan",
+						     data, &npcm7xx_chip_info,
+						     NULL);
+	if (IS_ERR(hwmon)) {
+		dev_err(dev, "unable to register hwmon device\n");
+		return PTR_ERR(hwmon);
+	}
+
+	for (i = 0; i < NPCM7XX_FAN_MAX_CHN_NUM; i++) {
+		if (data->fan_present[i]) {
+			/* fan timer initialization */
+			data->fan_timer.expires = jiffies +
+				msecs_to_jiffies(NPCM7XX_FAN_POLL_TIMER_200MS);
+			timer_setup(&data->fan_timer,
+				    npcm7xx_fan_polling, 0);
+			add_timer(&data->fan_timer);
+			break;
+		}
+	}
+
+	pr_info("NPCM7XX PWM-FAN Driver probed, output Freq %dHz[PWM], input Freq %dHz[FAN]\n",
+		output_freq, data->input_clk_freq);
+
+	return 0;
+}
+
+static const struct of_device_id of_pwm_fan_match_table[] = {
+	{ .compatible = "nuvoton,npcm750-pwm-fan", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, of_pwm_fan_match_table);
+
+static struct platform_driver npcm7xx_pwm_fan_driver = {
+	.probe		= npcm7xx_pwm_fan_probe,
+	.driver		= {
+		.name	= "npcm7xx_pwm_fan",
+		.of_match_table = of_pwm_fan_match_table,
+	},
+};
+
+module_platform_driver(npcm7xx_pwm_fan_driver);
+
+MODULE_DESCRIPTION("Nuvoton NPCM7XX PWM and Fan Tacho driver");
+MODULE_AUTHOR("Tomer Maimon <tomer.maimon@nuvoton.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/hwmon/pmbus/Kconfig b/drivers/hwmon/pmbus/Kconfig
index e71aec69e76e..a82018aaf473 100644
--- a/drivers/hwmon/pmbus/Kconfig
+++ b/drivers/hwmon/pmbus/Kconfig
@@ -130,7 +130,7 @@ config SENSORS_MAX34440
 	default n
 	help
 	  If you say yes here you get hardware monitoring support for Maxim
-	  MAX34440, MAX34441, MAX34446, MAX34460, and MAX34461.
+	  MAX34440, MAX34441, MAX34446, MAX34451, MAX34460, and MAX34461.
 
 	  This driver can also be built as a module. If so, the module will
 	  be called max34440.
diff --git a/drivers/hwmon/pmbus/max34440.c b/drivers/hwmon/pmbus/max34440.c
index 74a1f6f68fb3..47576c460010 100644
--- a/drivers/hwmon/pmbus/max34440.c
+++ b/drivers/hwmon/pmbus/max34440.c
@@ -27,7 +27,7 @@
 #include <linux/i2c.h>
 #include "pmbus.h"
 
-enum chips { max34440, max34441, max34446, max34460, max34461 };
+enum chips { max34440, max34441, max34446, max34451, max34460, max34461 };
 
 #define MAX34440_MFR_VOUT_PEAK		0xd4
 #define MAX34440_MFR_IOUT_PEAK		0xd5
@@ -44,6 +44,9 @@ enum chips { max34440, max34441, max34446, max34460, max34461 };
 #define MAX34440_STATUS_OT_FAULT	BIT(5)
 #define MAX34440_STATUS_OT_WARN		BIT(6)
 
+#define MAX34451_MFR_CHANNEL_CONFIG	0xe4
+#define MAX34451_MFR_CHANNEL_CONFIG_SEL_MASK	0x3f
+
 struct max34440_data {
 	int id;
 	struct pmbus_driver_info info;
@@ -67,7 +70,7 @@ static int max34440_read_word_data(struct i2c_client *client, int page, int reg)
 					   MAX34440_MFR_VOUT_PEAK);
 		break;
 	case PMBUS_VIRT_READ_IOUT_AVG:
-		if (data->id != max34446)
+		if (data->id != max34446 && data->id != max34451)
 			return -ENXIO;
 		ret = pmbus_read_word_data(client, page,
 					   MAX34446_MFR_IOUT_AVG);
@@ -143,7 +146,7 @@ static int max34440_write_word_data(struct i2c_client *client, int page,
 	case PMBUS_VIRT_RESET_IOUT_HISTORY:
 		ret = pmbus_write_word_data(client, page,
 					    MAX34440_MFR_IOUT_PEAK, 0);
-		if (!ret && data->id == max34446)
+		if (!ret && (data->id == max34446 || data->id == max34451))
 			ret = pmbus_write_word_data(client, page,
 					MAX34446_MFR_IOUT_AVG, 0);
 
@@ -202,6 +205,58 @@ static int max34440_read_byte_data(struct i2c_client *client, int page, int reg)
 	return ret;
 }
 
+static int max34451_set_supported_funcs(struct i2c_client *client,
+					 struct max34440_data *data)
+{
+	/*
+	 * Each of the channel 0-15 can be configured to monitor the following
+	 * functions based on MFR_CHANNEL_CONFIG[5:0]
+	 * 0x10: Sequencing + voltage monitoring (only valid for PAGES 0–11)
+	 * 0x20: Voltage monitoring (no sequencing)
+	 * 0x21: Voltage read only
+	 * 0x22: Current monitoring
+	 * 0x23: Current read only
+	 * 0x30: General-purpose input active low
+	 * 0x34: General-purpose input active high
+	 * 0x00:  Disabled
+	 */
+
+	int page, rv;
+
+	for (page = 0; page < 16; page++) {
+		rv = i2c_smbus_write_byte_data(client, PMBUS_PAGE, page);
+		if (rv < 0)
+			return rv;
+
+		rv = i2c_smbus_read_word_data(client,
+					      MAX34451_MFR_CHANNEL_CONFIG);
+		if (rv < 0)
+			return rv;
+
+		switch (rv & MAX34451_MFR_CHANNEL_CONFIG_SEL_MASK) {
+		case 0x10:
+		case 0x20:
+			data->info.func[page] = PMBUS_HAVE_VOUT |
+				PMBUS_HAVE_STATUS_VOUT;
+			break;
+		case 0x21:
+			data->info.func[page] = PMBUS_HAVE_VOUT;
+			break;
+		case 0x22:
+			data->info.func[page] = PMBUS_HAVE_IOUT |
+				PMBUS_HAVE_STATUS_IOUT;
+			break;
+		case 0x23:
+			data->info.func[page] = PMBUS_HAVE_IOUT;
+			break;
+		default:
+			break;
+		}
+	}
+
+	return 0;
+}
+
 static struct pmbus_driver_info max34440_info[] = {
 	[max34440] = {
 		.pages = 14,
@@ -325,6 +380,30 @@ static struct pmbus_driver_info max34440_info[] = {
 		.read_word_data = max34440_read_word_data,
 		.write_word_data = max34440_write_word_data,
 	},
+	[max34451] = {
+		.pages = 21,
+		.format[PSC_VOLTAGE_OUT] = direct,
+		.format[PSC_TEMPERATURE] = direct,
+		.format[PSC_CURRENT_OUT] = direct,
+		.m[PSC_VOLTAGE_OUT] = 1,
+		.b[PSC_VOLTAGE_OUT] = 0,
+		.R[PSC_VOLTAGE_OUT] = 3,
+		.m[PSC_CURRENT_OUT] = 1,
+		.b[PSC_CURRENT_OUT] = 0,
+		.R[PSC_CURRENT_OUT] = 2,
+		.m[PSC_TEMPERATURE] = 1,
+		.b[PSC_TEMPERATURE] = 0,
+		.R[PSC_TEMPERATURE] = 2,
+		/* func 0-15 is set dynamically before probing */
+		.func[16] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.func[17] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.func[18] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.func[19] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.func[20] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.read_byte_data = max34440_read_byte_data,
+		.read_word_data = max34440_read_word_data,
+		.write_word_data = max34440_write_word_data,
+	},
 	[max34460] = {
 		.pages = 18,
 		.format[PSC_VOLTAGE_OUT] = direct,
@@ -398,6 +477,7 @@ static int max34440_probe(struct i2c_client *client,
 			  const struct i2c_device_id *id)
 {
 	struct max34440_data *data;
+	int rv;
 
 	data = devm_kzalloc(&client->dev, sizeof(struct max34440_data),
 			    GFP_KERNEL);
@@ -406,6 +486,12 @@ static int max34440_probe(struct i2c_client *client,
 	data->id = id->driver_data;
 	data->info = max34440_info[id->driver_data];
 
+	if (data->id == max34451) {
+		rv = max34451_set_supported_funcs(client, data);
+		if (rv)
+			return rv;
+	}
+
 	return pmbus_do_probe(client, id, &data->info);
 }
 
@@ -413,6 +499,7 @@ static const struct i2c_device_id max34440_id[] = {
 	{"max34440", max34440},
 	{"max34441", max34441},
 	{"max34446", max34446},
+	{"max34451", max34451},
 	{"max34460", max34460},
 	{"max34461", max34461},
 	{}
diff --git a/drivers/i2c/i2c-core-smbus.c b/drivers/i2c/i2c-core-smbus.c
index 51970bae3c4a..9cd66cabb84f 100644
--- a/drivers/i2c/i2c-core-smbus.c
+++ b/drivers/i2c/i2c-core-smbus.c
@@ -463,7 +463,7 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr,
 			msg[num-1].len++;
 	}
 
-	status = i2c_transfer(adapter, msg, num);
+	status = __i2c_transfer(adapter, msg, num);
 	if (status < 0)
 		goto cleanup;
 	if (status != num) {
@@ -524,9 +524,24 @@ cleanup:
  * This executes an SMBus protocol operation, and returns a negative
  * errno code else zero on success.
  */
-s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, unsigned short flags,
-		   char read_write, u8 command, int protocol,
-		   union i2c_smbus_data *data)
+s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr,
+		   unsigned short flags, char read_write,
+		   u8 command, int protocol, union i2c_smbus_data *data)
+{
+	s32 res;
+
+	i2c_lock_bus(adapter, I2C_LOCK_SEGMENT);
+	res = __i2c_smbus_xfer(adapter, addr, flags, read_write,
+			       command, protocol, data);
+	i2c_unlock_bus(adapter, I2C_LOCK_SEGMENT);
+
+	return res;
+}
+EXPORT_SYMBOL(i2c_smbus_xfer);
+
+s32 __i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr,
+		     unsigned short flags, char read_write,
+		     u8 command, int protocol, union i2c_smbus_data *data)
 {
 	unsigned long orig_jiffies;
 	int try;
@@ -543,8 +558,6 @@ s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, unsigned short flags,
 	flags &= I2C_M_TEN | I2C_CLIENT_PEC | I2C_CLIENT_SCCB;
 
 	if (adapter->algo->smbus_xfer) {
-		i2c_lock_bus(adapter, I2C_LOCK_SEGMENT);
-
 		/* Retry automatically on arbitration loss */
 		orig_jiffies = jiffies;
 		for (res = 0, try = 0; try <= adapter->retries; try++) {
@@ -557,7 +570,6 @@ s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, unsigned short flags,
 				       orig_jiffies + adapter->timeout))
 				break;
 		}
-		i2c_unlock_bus(adapter, I2C_LOCK_SEGMENT);
 
 		if (res != -EOPNOTSUPP || !adapter->algo->master_xfer)
 			goto trace;
@@ -579,7 +591,7 @@ trace:
 
 	return res;
 }
-EXPORT_SYMBOL(i2c_smbus_xfer);
+EXPORT_SYMBOL(__i2c_smbus_xfer);
 
 /**
  * i2c_smbus_read_i2c_block_data_or_emulated - read block or emulate
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 5f178384876f..44a7a255ef74 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -419,10 +419,11 @@ static void ide_cd_request_sense_fixup(ide_drive_t *drive, struct ide_cmd *cmd)
 
 int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 		    int write, void *buffer, unsigned *bufflen,
-		    struct request_sense *sense, int timeout,
+		    struct scsi_sense_hdr *sshdr, int timeout,
 		    req_flags_t rq_flags)
 {
 	struct cdrom_info *info = drive->driver_data;
+	struct scsi_sense_hdr local_sshdr;
 	int retries = 10;
 	bool failed;
 
@@ -430,6 +431,9 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 				  "rq_flags: 0x%x",
 				  cmd[0], write, timeout, rq_flags);
 
+	if (!sshdr)
+		sshdr = &local_sshdr;
+
 	/* start of retry loop */
 	do {
 		struct request *rq;
@@ -456,8 +460,8 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 
 		if (buffer)
 			*bufflen = scsi_req(rq)->resid_len;
-		if (sense)
-			memcpy(sense, scsi_req(rq)->sense, sizeof(*sense));
+		scsi_normalize_sense(scsi_req(rq)->sense,
+				     scsi_req(rq)->sense_len, sshdr);
 
 		/*
 		 * FIXME: we should probably abort/retry or something in case of
@@ -469,12 +473,10 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 			 * The request failed.  Retry if it was due to a unit
 			 * attention status (usually means media was changed).
 			 */
-			struct request_sense *reqbuf = scsi_req(rq)->sense;
-
-			if (reqbuf->sense_key == UNIT_ATTENTION)
+			if (sshdr->sense_key == UNIT_ATTENTION)
 				cdrom_saw_media_change(drive);
-			else if (reqbuf->sense_key == NOT_READY &&
-				 reqbuf->asc == 4 && reqbuf->ascq != 4) {
+			else if (sshdr->sense_key == NOT_READY &&
+				 sshdr->asc == 4 && sshdr->ascq != 4) {
 				/*
 				 * The drive is in the process of loading
 				 * a disk.  Retry, but wait a little to give
@@ -864,7 +866,7 @@ static void msf_from_bcd(struct atapi_msf *msf)
 	msf->frame  = bcd2bin(msf->frame);
 }
 
-int cdrom_check_status(ide_drive_t *drive, struct request_sense *sense)
+int cdrom_check_status(ide_drive_t *drive, struct scsi_sense_hdr *sshdr)
 {
 	struct cdrom_info *info = drive->driver_data;
 	struct cdrom_device_info *cdi;
@@ -886,12 +888,11 @@ int cdrom_check_status(ide_drive_t *drive, struct request_sense *sense)
 	 */
 	cmd[7] = cdi->sanyo_slot % 3;
 
-	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, sense, 0, RQF_QUIET);
+	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, sshdr, 0, RQF_QUIET);
 }
 
 static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity,
-			       unsigned long *sectors_per_frame,
-			       struct request_sense *sense)
+			       unsigned long *sectors_per_frame)
 {
 	struct {
 		__be32 lba;
@@ -908,7 +909,7 @@ static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity,
 	memset(cmd, 0, BLK_MAX_CDB);
 	cmd[0] = GPCMD_READ_CDVD_CAPACITY;
 
-	stat = ide_cd_queue_pc(drive, cmd, 0, &capbuf, &len, sense, 0,
+	stat = ide_cd_queue_pc(drive, cmd, 0, &capbuf, &len, NULL, 0,
 			       RQF_QUIET);
 	if (stat)
 		return stat;
@@ -944,8 +945,7 @@ static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity,
 }
 
 static int cdrom_read_tocentry(ide_drive_t *drive, int trackno, int msf_flag,
-				int format, char *buf, int buflen,
-				struct request_sense *sense)
+				int format, char *buf, int buflen)
 {
 	unsigned char cmd[BLK_MAX_CDB];
 
@@ -962,11 +962,11 @@ static int cdrom_read_tocentry(ide_drive_t *drive, int trackno, int msf_flag,
 	if (msf_flag)
 		cmd[1] = 2;
 
-	return ide_cd_queue_pc(drive, cmd, 0, buf, &buflen, sense, 0, RQF_QUIET);
+	return ide_cd_queue_pc(drive, cmd, 0, buf, &buflen, NULL, 0, RQF_QUIET);
 }
 
 /* Try to read the entire TOC for the disk into our internal buffer. */
-int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
+int ide_cd_read_toc(ide_drive_t *drive)
 {
 	int stat, ntracks, i;
 	struct cdrom_info *info = drive->driver_data;
@@ -996,14 +996,13 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 	 * Check to see if the existing data is still valid. If it is,
 	 * just return.
 	 */
-	(void) cdrom_check_status(drive, sense);
+	(void) cdrom_check_status(drive, NULL);
 
 	if (drive->atapi_flags & IDE_AFLAG_TOC_VALID)
 		return 0;
 
 	/* try to get the total cdrom capacity and sector size */
-	stat = cdrom_read_capacity(drive, &toc->capacity, &sectors_per_frame,
-				   sense);
+	stat = cdrom_read_capacity(drive, &toc->capacity, &sectors_per_frame);
 	if (stat)
 		toc->capacity = 0x1fffff;
 
@@ -1016,7 +1015,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 
 	/* first read just the header, so we know how long the TOC is */
 	stat = cdrom_read_tocentry(drive, 0, 1, 0, (char *) &toc->hdr,
-				    sizeof(struct atapi_toc_header), sense);
+				    sizeof(struct atapi_toc_header));
 	if (stat)
 		return stat;
 
@@ -1036,7 +1035,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 				  (char *)&toc->hdr,
 				   sizeof(struct atapi_toc_header) +
 				   (ntracks + 1) *
-				   sizeof(struct atapi_toc_entry), sense);
+				   sizeof(struct atapi_toc_entry));
 
 	if (stat && toc->hdr.first_track > 1) {
 		/*
@@ -1056,8 +1055,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 					   (char *)&toc->hdr,
 					   sizeof(struct atapi_toc_header) +
 					   (ntracks + 1) *
-					   sizeof(struct atapi_toc_entry),
-					   sense);
+					   sizeof(struct atapi_toc_entry));
 		if (stat)
 			return stat;
 
@@ -1094,7 +1092,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 	if (toc->hdr.first_track != CDROM_LEADOUT) {
 		/* read the multisession information */
 		stat = cdrom_read_tocentry(drive, 0, 0, 1, (char *)&ms_tmp,
-					   sizeof(ms_tmp), sense);
+					   sizeof(ms_tmp));
 		if (stat)
 			return stat;
 
@@ -1108,7 +1106,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 	if (drive->atapi_flags & IDE_AFLAG_TOCADDR_AS_BCD) {
 		/* re-read multisession information using MSF format */
 		stat = cdrom_read_tocentry(drive, 0, 1, 1, (char *)&ms_tmp,
-					   sizeof(ms_tmp), sense);
+					   sizeof(ms_tmp));
 		if (stat)
 			return stat;
 
@@ -1412,7 +1410,7 @@ static sector_t ide_cdrom_capacity(ide_drive_t *drive)
 {
 	unsigned long capacity, sectors_per_frame;
 
-	if (cdrom_read_capacity(drive, &capacity, &sectors_per_frame, NULL))
+	if (cdrom_read_capacity(drive, &capacity, &sectors_per_frame))
 		return 0;
 
 	return capacity * sectors_per_frame;
@@ -1710,9 +1708,8 @@ static unsigned int idecd_check_events(struct gendisk *disk,
 static int idecd_revalidate_disk(struct gendisk *disk)
 {
 	struct cdrom_info *info = ide_drv_g(disk, cdrom_info);
-	struct request_sense sense;
 
-	ide_cd_read_toc(info->drive, &sense);
+	ide_cd_read_toc(info->drive);
 
 	return  0;
 }
@@ -1736,7 +1733,6 @@ static int ide_cd_probe(ide_drive_t *drive)
 {
 	struct cdrom_info *info;
 	struct gendisk *g;
-	struct request_sense sense;
 
 	ide_debug_log(IDE_DBG_PROBE, "driver_req: %s, media: 0x%x",
 				     drive->driver_req, drive->media);
@@ -1785,7 +1781,7 @@ static int ide_cd_probe(ide_drive_t *drive)
 		goto failed;
 	}
 
-	ide_cd_read_toc(drive, &sense);
+	ide_cd_read_toc(drive);
 	g->fops = &idecd_ops;
 	g->flags |= GENHD_FL_REMOVABLE | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
 	device_add_disk(&drive->gendev, g);
diff --git a/drivers/ide/ide-cd.h b/drivers/ide/ide-cd.h
index 04f0f310a856..a69dc7f61c4d 100644
--- a/drivers/ide/ide-cd.h
+++ b/drivers/ide/ide-cd.h
@@ -98,11 +98,11 @@ void ide_cd_log_error(const char *, struct request *, struct request_sense *);
 
 /* ide-cd.c functions used by ide-cd_ioctl.c */
 int ide_cd_queue_pc(ide_drive_t *, const unsigned char *, int, void *,
-		    unsigned *, struct request_sense *, int, req_flags_t);
-int ide_cd_read_toc(ide_drive_t *, struct request_sense *);
+		    unsigned *, struct scsi_sense_hdr *, int, req_flags_t);
+int ide_cd_read_toc(ide_drive_t *);
 int ide_cdrom_get_capabilities(ide_drive_t *, u8 *);
 void ide_cdrom_update_speed(ide_drive_t *, u8 *);
-int cdrom_check_status(ide_drive_t *, struct request_sense *);
+int cdrom_check_status(ide_drive_t *, struct scsi_sense_hdr *);
 
 /* ide-cd_ioctl.c */
 int ide_cdrom_open_real(struct cdrom_device_info *, int);
diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c
index b1322400887b..4a6e1a413ead 100644
--- a/drivers/ide/ide-cd_ioctl.c
+++ b/drivers/ide/ide-cd_ioctl.c
@@ -43,14 +43,14 @@ int ide_cdrom_drive_status(struct cdrom_device_info *cdi, int slot_nr)
 {
 	ide_drive_t *drive = cdi->handle;
 	struct media_event_desc med;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	int stat;
 
 	if (slot_nr != CDSL_CURRENT)
 		return -EINVAL;
 
-	stat = cdrom_check_status(drive, &sense);
-	if (!stat || sense.sense_key == UNIT_ATTENTION)
+	stat = cdrom_check_status(drive, &sshdr);
+	if (!stat || sshdr.sense_key == UNIT_ATTENTION)
 		return CDS_DISC_OK;
 
 	if (!cdrom_get_media_event(cdi, &med)) {
@@ -62,8 +62,8 @@ int ide_cdrom_drive_status(struct cdrom_device_info *cdi, int slot_nr)
 			return CDS_NO_DISC;
 	}
 
-	if (sense.sense_key == NOT_READY && sense.asc == 0x04
-			&& sense.ascq == 0x04)
+	if (sshdr.sense_key == NOT_READY && sshdr.asc == 0x04
+			&& sshdr.ascq == 0x04)
 		return CDS_DISC_OK;
 
 	/*
@@ -71,8 +71,8 @@ int ide_cdrom_drive_status(struct cdrom_device_info *cdi, int slot_nr)
 	 * just return TRAY_OPEN since ATAPI doesn't provide
 	 * any other way to detect this...
 	 */
-	if (sense.sense_key == NOT_READY) {
-		if (sense.asc == 0x3a && sense.ascq == 1)
+	if (sshdr.sense_key == NOT_READY) {
+		if (sshdr.asc == 0x3a && sshdr.ascq == 1)
 			return CDS_NO_DISC;
 		else
 			return CDS_TRAY_OPEN;
@@ -105,8 +105,7 @@ unsigned int ide_cdrom_check_events_real(struct cdrom_device_info *cdi,
 /* Eject the disk if EJECTFLAG is 0.
    If EJECTFLAG is 1, try to reload the disk. */
 static
-int cdrom_eject(ide_drive_t *drive, int ejectflag,
-		struct request_sense *sense)
+int cdrom_eject(ide_drive_t *drive, int ejectflag)
 {
 	struct cdrom_info *cd = drive->driver_data;
 	struct cdrom_device_info *cdi = &cd->devinfo;
@@ -129,20 +128,16 @@ int cdrom_eject(ide_drive_t *drive, int ejectflag,
 	cmd[0] = GPCMD_START_STOP_UNIT;
 	cmd[4] = loej | (ejectflag != 0);
 
-	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, sense, 0, 0);
+	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, NULL, 0, 0);
 }
 
 /* Lock the door if LOCKFLAG is nonzero; unlock it otherwise. */
 static
-int ide_cd_lockdoor(ide_drive_t *drive, int lockflag,
-		    struct request_sense *sense)
+int ide_cd_lockdoor(ide_drive_t *drive, int lockflag)
 {
-	struct request_sense my_sense;
+	struct scsi_sense_hdr sshdr;
 	int stat;
 
-	if (sense == NULL)
-		sense = &my_sense;
-
 	/* If the drive cannot lock the door, just pretend. */
 	if ((drive->dev_flags & IDE_DFLAG_DOORLOCKING) == 0) {
 		stat = 0;
@@ -155,14 +150,14 @@ int ide_cd_lockdoor(ide_drive_t *drive, int lockflag,
 		cmd[4] = lockflag ? 1 : 0;
 
 		stat = ide_cd_queue_pc(drive, cmd, 0, NULL, NULL,
-				       sense, 0, 0);
+				       &sshdr, 0, 0);
 	}
 
 	/* If we got an illegal field error, the drive
 	   probably cannot lock the door. */
 	if (stat != 0 &&
-	    sense->sense_key == ILLEGAL_REQUEST &&
-	    (sense->asc == 0x24 || sense->asc == 0x20)) {
+	    sshdr.sense_key == ILLEGAL_REQUEST &&
+	    (sshdr.asc == 0x24 || sshdr.asc == 0x20)) {
 		printk(KERN_ERR "%s: door locking not supported\n",
 			drive->name);
 		drive->dev_flags &= ~IDE_DFLAG_DOORLOCKING;
@@ -170,7 +165,7 @@ int ide_cd_lockdoor(ide_drive_t *drive, int lockflag,
 	}
 
 	/* no medium, that's alright. */
-	if (stat != 0 && sense->sense_key == NOT_READY && sense->asc == 0x3a)
+	if (stat != 0 && sshdr.sense_key == NOT_READY && sshdr.asc == 0x3a)
 		stat = 0;
 
 	if (stat == 0) {
@@ -186,23 +181,22 @@ int ide_cd_lockdoor(ide_drive_t *drive, int lockflag,
 int ide_cdrom_tray_move(struct cdrom_device_info *cdi, int position)
 {
 	ide_drive_t *drive = cdi->handle;
-	struct request_sense sense;
 
 	if (position) {
-		int stat = ide_cd_lockdoor(drive, 0, &sense);
+		int stat = ide_cd_lockdoor(drive, 0);
 
 		if (stat)
 			return stat;
 	}
 
-	return cdrom_eject(drive, !position, &sense);
+	return cdrom_eject(drive, !position);
 }
 
 int ide_cdrom_lock_door(struct cdrom_device_info *cdi, int lock)
 {
 	ide_drive_t *drive = cdi->handle;
 
-	return ide_cd_lockdoor(drive, lock, NULL);
+	return ide_cd_lockdoor(drive, lock);
 }
 
 /*
@@ -213,7 +207,6 @@ int ide_cdrom_select_speed(struct cdrom_device_info *cdi, int speed)
 {
 	ide_drive_t *drive = cdi->handle;
 	struct cdrom_info *cd = drive->driver_data;
-	struct request_sense sense;
 	u8 buf[ATAPI_CAPABILITIES_PAGE_SIZE];
 	int stat;
 	unsigned char cmd[BLK_MAX_CDB];
@@ -236,7 +229,7 @@ int ide_cdrom_select_speed(struct cdrom_device_info *cdi, int speed)
 		cmd[5] = speed & 0xff;
 	}
 
-	stat = ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, &sense, 0, 0);
+	stat = ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, NULL, 0, 0);
 
 	if (!ide_cdrom_get_capabilities(drive, buf)) {
 		ide_cdrom_update_speed(drive, buf);
@@ -252,11 +245,10 @@ int ide_cdrom_get_last_session(struct cdrom_device_info *cdi,
 	struct atapi_toc *toc;
 	ide_drive_t *drive = cdi->handle;
 	struct cdrom_info *info = drive->driver_data;
-	struct request_sense sense;
 	int ret;
 
 	if ((drive->atapi_flags & IDE_AFLAG_TOC_VALID) == 0 || !info->toc) {
-		ret = ide_cd_read_toc(drive, &sense);
+		ret = ide_cd_read_toc(drive);
 		if (ret)
 			return ret;
 	}
@@ -300,7 +292,6 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
 {
 	ide_drive_t *drive = cdi->handle;
 	struct cdrom_info *cd = drive->driver_data;
-	struct request_sense sense;
 	struct request *rq;
 	int ret;
 
@@ -315,7 +306,7 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
 	 * lock it again.
 	 */
 	if (drive->atapi_flags & IDE_AFLAG_DOOR_LOCKED)
-		(void)ide_cd_lockdoor(drive, 1, &sense);
+		(void)ide_cd_lockdoor(drive, 1);
 
 	return ret;
 }
@@ -355,7 +346,6 @@ static int ide_cd_fake_play_trkind(ide_drive_t *drive, void *arg)
 	struct atapi_toc_entry *first_toc, *last_toc;
 	unsigned long lba_start, lba_end;
 	int stat;
-	struct request_sense sense;
 	unsigned char cmd[BLK_MAX_CDB];
 
 	stat = ide_cd_get_toc_entry(drive, ti->cdti_trk0, &first_toc);
@@ -380,7 +370,7 @@ static int ide_cd_fake_play_trkind(ide_drive_t *drive, void *arg)
 	lba_to_msf(lba_start,   &cmd[3], &cmd[4], &cmd[5]);
 	lba_to_msf(lba_end - 1, &cmd[6], &cmd[7], &cmd[8]);
 
-	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, &sense, 0, 0);
+	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, NULL, 0, 0);
 }
 
 static int ide_cd_read_tochdr(ide_drive_t *drive, void *arg)
@@ -391,7 +381,7 @@ static int ide_cd_read_tochdr(ide_drive_t *drive, void *arg)
 	int stat;
 
 	/* Make sure our saved TOC is valid. */
-	stat = ide_cd_read_toc(drive, NULL);
+	stat = ide_cd_read_toc(drive);
 	if (stat)
 		return stat;
 
@@ -461,8 +451,8 @@ int ide_cdrom_packet(struct cdrom_device_info *cdi,
 	   layer. the packet must be complete, as we do not
 	   touch it at all. */
 
-	if (cgc->sense)
-		memset(cgc->sense, 0, sizeof(struct request_sense));
+	if (cgc->sshdr)
+		memset(cgc->sshdr, 0, sizeof(*cgc->sshdr));
 
 	if (cgc->quiet)
 		flags |= RQF_QUIET;
@@ -470,7 +460,7 @@ int ide_cdrom_packet(struct cdrom_device_info *cdi,
 	cgc->stat = ide_cd_queue_pc(drive, cgc->cmd,
 				    cgc->data_direction == CGC_DATA_WRITE,
 				    cgc->buffer, &len,
-				    cgc->sense, cgc->timeout, flags);
+				    cgc->sshdr, cgc->timeout, flags);
 	if (!cgc->stat)
 		cgc->buflen -= len;
 	return cgc->stat;
diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c
index 12e7c6c102c1..6eb64c6f0802 100644
--- a/drivers/infiniband/core/rdma_core.c
+++ b/drivers/infiniband/core/rdma_core.c
@@ -79,7 +79,7 @@ static int uverbs_try_lock_object(struct ib_uobject *uobj,
 	 */
 	switch (mode) {
 	case UVERBS_LOOKUP_READ:
-		return __atomic_add_unless(&uobj->usecnt, 1, -1) == -1 ?
+		return atomic_fetch_add_unless(&uobj->usecnt, 1, -1) == -1 ?
 			-EBUSY : 0;
 	case UVERBS_LOOKUP_WRITE:
 		/* lock is exclusive */
diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index de3ee606034c..eec83757d55f 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -900,9 +900,7 @@ static int trigger_sbr(struct hfi1_devdata *dd)
 	 * delay after a reset is required.  Per spec requirements,
 	 * the link is either working or not after that point.
 	 */
-	pci_reset_bridge_secondary_bus(dev->bus->self);
-
-	return 0;
+	return pci_reset_bus(dev);
 }
 
 /*
diff --git a/drivers/infiniband/hw/hfi1/vnic_main.c b/drivers/infiniband/hw/hfi1/vnic_main.c
index ba160f99cf8e..c643d80c5a53 100644
--- a/drivers/infiniband/hw/hfi1/vnic_main.c
+++ b/drivers/infiniband/hw/hfi1/vnic_main.c
@@ -421,7 +421,7 @@ tx_finish:
 
 static u16 hfi1_vnic_select_queue(struct net_device *netdev,
 				  struct sk_buff *skb,
-				  void *accel_priv,
+				  struct net_device *sb_dev,
 				  select_queue_fallback_t fallback)
 {
 	struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
index aa7f2342d4eb..081aa91fc162 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
@@ -1480,7 +1480,7 @@ static int hns_roce_v1_reset(struct hns_roce_dev *hr_dev, bool dereset)
 		}
 		fwnode = &dsaf_node->fwnode;
 	} else if (is_acpi_device_node(dev->fwnode)) {
-		struct acpi_reference_args args;
+		struct fwnode_reference_args args;
 
 		ret = acpi_node_get_property_reference(dev->fwnode,
 						       "dsaf-handle", 0, &args);
@@ -1488,7 +1488,7 @@ static int hns_roce_v1_reset(struct hns_roce_dev *hr_dev, bool dereset)
 			dev_err(dev, "could not find dsaf-handle\n");
 			return ret;
 		}
-		fwnode = acpi_fwnode_handle(args.adev);
+		fwnode = args.fwnode;
 	} else {
 		dev_err(dev, "cannot read data from DT or ACPI\n");
 		return -ENXIO;
@@ -4917,16 +4917,14 @@ static int hns_roce_get_cfg(struct hns_roce_dev *hr_dev)
 				continue;
 			pdev = of_find_device_by_node(net_node);
 		} else if (is_acpi_device_node(dev->fwnode)) {
-			struct acpi_reference_args args;
-			struct fwnode_handle *fwnode;
+			struct fwnode_reference_args args;
 
 			ret = acpi_node_get_property_reference(dev->fwnode,
 							       "eth-handle",
 							       i, &args);
 			if (ret)
 				continue;
-			fwnode = acpi_fwnode_handle(args.adev);
-			pdev = hns_roce_find_pdev(fwnode);
+			pdev = hns_roce_find_pdev(args.fwnode);
 		} else {
 			dev_err(dev, "cannot read data from DT or ACPI\n");
 			return -ENXIO;
diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index a77d020cc89d..009be8889d71 100644
--- a/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/drivers/infiniband/ulp/iser/iser_memory.c
@@ -311,7 +311,7 @@ iser_set_dif_domain(struct scsi_cmnd *sc, struct ib_sig_attrs *sig_attrs,
 {
 	domain->sig_type = IB_SIG_TYPE_T10_DIF;
 	domain->sig.dif.pi_interval = scsi_prot_interval(sc);
-	domain->sig.dif.ref_tag = scsi_prot_ref_tag(sc);
+	domain->sig.dif.ref_tag = t10_pi_ref_tag(sc->request);
 	/*
 	 * At the moment we hard code those, but in the future
 	 * we will take them from sc.
diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c
index 0c8aec62a425..61558788b3fa 100644
--- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c
+++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c
@@ -95,7 +95,7 @@ static netdev_tx_t opa_netdev_start_xmit(struct sk_buff *skb,
 }
 
 static u16 opa_vnic_select_queue(struct net_device *netdev, struct sk_buff *skb,
-				 void *accel_priv,
+				 struct net_device *sb_dev,
 				 select_queue_fallback_t fallback)
 {
 	struct opa_vnic_adapter *adapter = opa_vnic_priv(netdev);
@@ -107,7 +107,7 @@ static u16 opa_vnic_select_queue(struct net_device *netdev, struct sk_buff *skb,
 	mdata->entropy = opa_vnic_calc_entropy(skb);
 	mdata->vl = opa_vnic_get_vl(adapter, skb);
 	rc = adapter->rn_ops->ndo_select_queue(netdev, skb,
-					       accel_priv, fallback);
+					       sb_dev, fallback);
 	skb_pull(skb, sizeof(*mdata));
 	return rc;
 }
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index d73e14699aa9..f37cbad022a2 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -2028,8 +2028,7 @@ static void srpt_release_channel_work(struct work_struct *w)
 	target_sess_cmd_list_set_waiting(se_sess);
 	target_wait_for_sess_cmds(se_sess);
 
-	transport_deregister_session_configfs(se_sess);
-	transport_deregister_session(se_sess);
+	target_remove_session(se_sess);
 	ch->sess = NULL;
 
 	if (ch->using_rdma_cm)
@@ -2220,16 +2219,16 @@ static int srpt_cm_req_recv(struct srpt_device *const sdev,
 	pr_debug("registering session %s\n", ch->sess_name);
 
 	if (sport->port_guid_tpg.se_tpg_wwn)
-		ch->sess = target_alloc_session(&sport->port_guid_tpg, 0, 0,
+		ch->sess = target_setup_session(&sport->port_guid_tpg, 0, 0,
 						TARGET_PROT_NORMAL,
 						ch->sess_name, ch, NULL);
 	if (sport->port_gid_tpg.se_tpg_wwn && IS_ERR_OR_NULL(ch->sess))
-		ch->sess = target_alloc_session(&sport->port_gid_tpg, 0, 0,
+		ch->sess = target_setup_session(&sport->port_gid_tpg, 0, 0,
 					TARGET_PROT_NORMAL, i_port_id, ch,
 					NULL);
 	/* Retry without leading "0x" */
 	if (sport->port_gid_tpg.se_tpg_wwn && IS_ERR_OR_NULL(ch->sess))
-		ch->sess = target_alloc_session(&sport->port_gid_tpg, 0, 0,
+		ch->sess = target_setup_session(&sport->port_gid_tpg, 0, 0,
 						TARGET_PROT_NORMAL,
 						i_port_id + 2, ch, NULL);
 	if (IS_ERR_OR_NULL(ch->sess)) {
@@ -3610,11 +3609,9 @@ static struct configfs_attribute *srpt_tpg_attrs[] = {
 /**
  * srpt_make_tpg - configfs callback invoked for mkdir /sys/kernel/config/target/$driver/$port/$tpg
  * @wwn: Corresponds to $driver/$port.
- * @group: Not used.
  * @name: $tpg.
  */
 static struct se_portal_group *srpt_make_tpg(struct se_wwn *wwn,
-					     struct config_group *group,
 					     const char *name)
 {
 	struct srpt_port *sport = wwn->priv;
diff --git a/drivers/input/keyboard/hilkbd.c b/drivers/input/keyboard/hilkbd.c
index a4e404aaf64b..5c7afdec192c 100644
--- a/drivers/input/keyboard/hilkbd.c
+++ b/drivers/input/keyboard/hilkbd.c
@@ -57,8 +57,8 @@ MODULE_LICENSE("GPL v2");
  #define HIL_DATA		0x1
  #define HIL_CMD		0x3
  #define HIL_IRQ		2
- #define hil_readb(p)		readb(p)
- #define hil_writeb(v,p)	writeb((v),(p))
+ #define hil_readb(p)		readb((const volatile void __iomem *)(p))
+ #define hil_writeb(v, p)	writeb((v), (volatile void __iomem *)(p))
 
 #else
 #error "HIL is not supported on this platform"
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index ddcbbdb5d658..511ff9a1d6d9 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -367,6 +367,9 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
 	if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
 		iova_len = roundup_pow_of_two(iova_len);
 
+	if (dev->bus_dma_mask)
+		dma_limit &= dev->bus_dma_mask;
+
 	if (domain->geometry.force_aperture)
 		dma_limit = min(dma_limit, domain->geometry.aperture_end);
 
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index e9233db16e03..d564d21245c5 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -8,7 +8,7 @@ config ARM_GIC
 	bool
 	select IRQ_DOMAIN
 	select IRQ_DOMAIN_HIERARCHY
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
 
 config ARM_GIC_PM
@@ -34,7 +34,7 @@ config GIC_NON_BANKED
 config ARM_GIC_V3
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select IRQ_DOMAIN_HIERARCHY
 	select PARTITION_PERCPU
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
@@ -66,7 +66,7 @@ config ARM_NVIC
 config ARM_VIC
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 
 config ARM_VIC_NR
 	int
@@ -93,14 +93,14 @@ config ATMEL_AIC_IRQ
 	bool
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 
 config ATMEL_AIC5_IRQ
 	bool
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 
 config I8259
@@ -137,7 +137,7 @@ config DW_APB_ICTL
 config FARADAY_FTINTC010
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 
 config HISILICON_IRQ_MBIGEN
@@ -162,7 +162,7 @@ config CLPS711X_IRQCHIP
 	bool
 	depends on ARCH_CLPS711X
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 	default y
 
@@ -181,7 +181,7 @@ config OMAP_IRQCHIP
 config ORION_IRQCHIP
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 
 config PIC32_EVIC
 	bool
diff --git a/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c b/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c
index 4eca5c763766..606efa64adff 100644
--- a/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c
@@ -45,6 +45,9 @@ static int its_fsl_mc_msi_prepare(struct irq_domain *msi_domain,
 	 */
 	info->scratchpad[0].ul = mc_bus_dev->icid;
 	msi_info = msi_get_domain_info(msi_domain->parent);
+
+	/* Allocate at least 32 MSIs, and always as a power of 2 */
+	nvec = max_t(int, 32, roundup_pow_of_two(nvec));
 	return msi_info->ops->msi_prepare(msi_domain->parent, dev, nvec, info);
 }
 
diff --git a/drivers/irqchip/irq-gic-v3-its-pci-msi.c b/drivers/irqchip/irq-gic-v3-its-pci-msi.c
index 25a98de5cfb2..8d6d009d1d58 100644
--- a/drivers/irqchip/irq-gic-v3-its-pci-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-pci-msi.c
@@ -66,7 +66,7 @@ static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev,
 {
 	struct pci_dev *pdev, *alias_dev;
 	struct msi_domain_info *msi_info;
-	int alias_count = 0;
+	int alias_count = 0, minnvec = 1;
 
 	if (!dev_is_pci(dev))
 		return -EINVAL;
@@ -86,8 +86,18 @@ static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev,
 	/* ITS specific DeviceID, as the core ITS ignores dev. */
 	info->scratchpad[0].ul = pci_msi_domain_get_msi_rid(domain, pdev);
 
-	return msi_info->ops->msi_prepare(domain->parent,
-					  dev, max(nvec, alias_count), info);
+	/*
+	 * Always allocate a power of 2, and special case device 0 for
+	 * broken systems where the DevID is not wired (and all devices
+	 * appear as DevID 0). For that reason, we generously allocate a
+	 * minimum of 32 MSIs for DevID 0. If you want more because all
+	 * your devices are aliasing to DevID 0, consider fixing your HW.
+	 */
+	nvec = max(nvec, alias_count);
+	if (!info->scratchpad[0].ul)
+		minnvec = 32;
+	nvec = max_t(int, minnvec, roundup_pow_of_two(nvec));
+	return msi_info->ops->msi_prepare(domain->parent, dev, nvec, info);
 }
 
 static struct msi_domain_ops its_pci_msi_ops = {
diff --git a/drivers/irqchip/irq-gic-v3-its-platform-msi.c b/drivers/irqchip/irq-gic-v3-its-platform-msi.c
index 8881a053c173..7b8e87b493fe 100644
--- a/drivers/irqchip/irq-gic-v3-its-platform-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-platform-msi.c
@@ -73,6 +73,8 @@ static int its_pmsi_prepare(struct irq_domain *domain, struct device *dev,
 	/* ITS specific DeviceID, as the core ITS ignores dev. */
 	info->scratchpad[0].ul = dev_id;
 
+	/* Allocate at least 32 MSIs, and always as a power of 2 */
+	nvec = max_t(int, 32, roundup_pow_of_two(nvec));
 	return msi_info->ops->msi_prepare(domain->parent,
 					  dev, nvec, info);
 }
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index d7842d312d3e..316a57530f6d 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -23,6 +23,8 @@
 #include <linux/dma-iommu.h>
 #include <linux/interrupt.h>
 #include <linux/irqdomain.h>
+#include <linux/list.h>
+#include <linux/list_sort.h>
 #include <linux/log2.h>
 #include <linux/mm.h>
 #include <linux/msi.h>
@@ -160,7 +162,7 @@ static struct {
 } vpe_proxy;
 
 static LIST_HEAD(its_nodes);
-static DEFINE_SPINLOCK(its_lock);
+static DEFINE_RAW_SPINLOCK(its_lock);
 static struct rdists *gic_rdists;
 static struct irq_domain *its_parent;
 
@@ -1421,112 +1423,176 @@ static struct irq_chip its_irq_chip = {
 	.irq_set_vcpu_affinity	= its_irq_set_vcpu_affinity,
 };
 
+
 /*
  * How we allocate LPIs:
  *
- * The GIC has id_bits bits for interrupt identifiers. From there, we
- * must subtract 8192 which are reserved for SGIs/PPIs/SPIs. Then, as
- * we allocate LPIs by chunks of 32, we can shift the whole thing by 5
- * bits to the right.
+ * lpi_range_list contains ranges of LPIs that are to available to
+ * allocate from. To allocate LPIs, just pick the first range that
+ * fits the required allocation, and reduce it by the required
+ * amount. Once empty, remove the range from the list.
+ *
+ * To free a range of LPIs, add a free range to the list, sort it and
+ * merge the result if the new range happens to be adjacent to an
+ * already free block.
  *
- * This gives us (((1UL << id_bits) - 8192) >> 5) possible allocations.
+ * The consequence of the above is that allocation is cost is low, but
+ * freeing is expensive. We assumes that freeing rarely occurs.
  */
-#define IRQS_PER_CHUNK_SHIFT	5
-#define IRQS_PER_CHUNK		(1UL << IRQS_PER_CHUNK_SHIFT)
-#define ITS_MAX_LPI_NRBITS	16 /* 64K LPIs */
 
-static unsigned long *lpi_bitmap;
-static u32 lpi_chunks;
-static DEFINE_SPINLOCK(lpi_lock);
+static DEFINE_MUTEX(lpi_range_lock);
+static LIST_HEAD(lpi_range_list);
+
+struct lpi_range {
+	struct list_head	entry;
+	u32			base_id;
+	u32			span;
+};
 
-static int its_lpi_to_chunk(int lpi)
+static struct lpi_range *mk_lpi_range(u32 base, u32 span)
 {
-	return (lpi - 8192) >> IRQS_PER_CHUNK_SHIFT;
+	struct lpi_range *range;
+
+	range = kzalloc(sizeof(*range), GFP_KERNEL);
+	if (range) {
+		INIT_LIST_HEAD(&range->entry);
+		range->base_id = base;
+		range->span = span;
+	}
+
+	return range;
 }
 
-static int its_chunk_to_lpi(int chunk)
+static int lpi_range_cmp(void *priv, struct list_head *a, struct list_head *b)
 {
-	return (chunk << IRQS_PER_CHUNK_SHIFT) + 8192;
+	struct lpi_range *ra, *rb;
+
+	ra = container_of(a, struct lpi_range, entry);
+	rb = container_of(b, struct lpi_range, entry);
+
+	return rb->base_id - ra->base_id;
 }
 
-static int __init its_lpi_init(u32 id_bits)
+static void merge_lpi_ranges(void)
 {
-	lpi_chunks = its_lpi_to_chunk(1UL << id_bits);
+	struct lpi_range *range, *tmp;
 
-	lpi_bitmap = kcalloc(BITS_TO_LONGS(lpi_chunks), sizeof(long),
-			     GFP_KERNEL);
-	if (!lpi_bitmap) {
-		lpi_chunks = 0;
-		return -ENOMEM;
+	list_for_each_entry_safe(range, tmp, &lpi_range_list, entry) {
+		if (!list_is_last(&range->entry, &lpi_range_list) &&
+		    (tmp->base_id == (range->base_id + range->span))) {
+			tmp->base_id = range->base_id;
+			tmp->span += range->span;
+			list_del(&range->entry);
+			kfree(range);
+		}
 	}
+}
 
-	pr_info("ITS: Allocated %d chunks for LPIs\n", (int)lpi_chunks);
-	return 0;
+static int alloc_lpi_range(u32 nr_lpis, u32 *base)
+{
+	struct lpi_range *range, *tmp;
+	int err = -ENOSPC;
+
+	mutex_lock(&lpi_range_lock);
+
+	list_for_each_entry_safe(range, tmp, &lpi_range_list, entry) {
+		if (range->span >= nr_lpis) {
+			*base = range->base_id;
+			range->base_id += nr_lpis;
+			range->span -= nr_lpis;
+
+			if (range->span == 0) {
+				list_del(&range->entry);
+				kfree(range);
+			}
+
+			err = 0;
+			break;
+		}
+	}
+
+	mutex_unlock(&lpi_range_lock);
+
+	pr_debug("ITS: alloc %u:%u\n", *base, nr_lpis);
+	return err;
 }
 
-static unsigned long *its_lpi_alloc_chunks(int nr_irqs, int *base, int *nr_ids)
+static int free_lpi_range(u32 base, u32 nr_lpis)
 {
-	unsigned long *bitmap = NULL;
-	int chunk_id;
-	int nr_chunks;
-	int i;
+	struct lpi_range *new;
+	int err = 0;
+
+	mutex_lock(&lpi_range_lock);
+
+	new = mk_lpi_range(base, nr_lpis);
+	if (!new) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	list_add(&new->entry, &lpi_range_list);
+	list_sort(NULL, &lpi_range_list, lpi_range_cmp);
+	merge_lpi_ranges();
+out:
+	mutex_unlock(&lpi_range_lock);
+	return err;
+}
+
+static int __init its_lpi_init(u32 id_bits)
+{
+	u32 lpis = (1UL << id_bits) - 8192;
+	u32 numlpis;
+	int err;
+
+	numlpis = 1UL << GICD_TYPER_NUM_LPIS(gic_rdists->gicd_typer);
+
+	if (numlpis > 2 && !WARN_ON(numlpis > lpis)) {
+		lpis = numlpis;
+		pr_info("ITS: Using hypervisor restricted LPI range [%u]\n",
+			lpis);
+	}
 
-	nr_chunks = DIV_ROUND_UP(nr_irqs, IRQS_PER_CHUNK);
+	/*
+	 * Initializing the allocator is just the same as freeing the
+	 * full range of LPIs.
+	 */
+	err = free_lpi_range(8192, lpis);
+	pr_debug("ITS: Allocator initialized for %u LPIs\n", lpis);
+	return err;
+}
 
-	spin_lock(&lpi_lock);
+static unsigned long *its_lpi_alloc(int nr_irqs, u32 *base, int *nr_ids)
+{
+	unsigned long *bitmap = NULL;
+	int err = 0;
 
 	do {
-		chunk_id = bitmap_find_next_zero_area(lpi_bitmap, lpi_chunks,
-						      0, nr_chunks, 0);
-		if (chunk_id < lpi_chunks)
+		err = alloc_lpi_range(nr_irqs, base);
+		if (!err)
 			break;
 
-		nr_chunks--;
-	} while (nr_chunks > 0);
+		nr_irqs /= 2;
+	} while (nr_irqs > 0);
 
-	if (!nr_chunks)
+	if (err)
 		goto out;
 
-	bitmap = kcalloc(BITS_TO_LONGS(nr_chunks * IRQS_PER_CHUNK),
-			 sizeof(long),
-			 GFP_ATOMIC);
+	bitmap = kcalloc(BITS_TO_LONGS(nr_irqs), sizeof (long), GFP_ATOMIC);
 	if (!bitmap)
 		goto out;
 
-	for (i = 0; i < nr_chunks; i++)
-		set_bit(chunk_id + i, lpi_bitmap);
-
-	*base = its_chunk_to_lpi(chunk_id);
-	*nr_ids = nr_chunks * IRQS_PER_CHUNK;
+	*nr_ids = nr_irqs;
 
 out:
-	spin_unlock(&lpi_lock);
-
 	if (!bitmap)
 		*base = *nr_ids = 0;
 
 	return bitmap;
 }
 
-static void its_lpi_free_chunks(unsigned long *bitmap, int base, int nr_ids)
+static void its_lpi_free(unsigned long *bitmap, u32 base, u32 nr_ids)
 {
-	int lpi;
-
-	spin_lock(&lpi_lock);
-
-	for (lpi = base; lpi < (base + nr_ids); lpi += IRQS_PER_CHUNK) {
-		int chunk = its_lpi_to_chunk(lpi);
-
-		BUG_ON(chunk > lpi_chunks);
-		if (test_bit(chunk, lpi_bitmap)) {
-			clear_bit(chunk, lpi_bitmap);
-		} else {
-			pr_err("Bad LPI chunk %d\n", chunk);
-		}
-	}
-
-	spin_unlock(&lpi_lock);
-
+	WARN_ON(free_lpi_range(base, nr_ids));
 	kfree(bitmap);
 }
 
@@ -1559,7 +1625,7 @@ static int __init its_alloc_lpi_tables(void)
 {
 	phys_addr_t paddr;
 
-	lpi_id_bits = min_t(u32, gic_rdists->id_bits, ITS_MAX_LPI_NRBITS);
+	lpi_id_bits = GICD_TYPER_ID_BITS(gic_rdists->gicd_typer);
 	gic_rdists->prop_page = its_allocate_prop_table(GFP_NOWAIT);
 	if (!gic_rdists->prop_page) {
 		pr_err("Failed to allocate PROPBASE\n");
@@ -1997,12 +2063,12 @@ static void its_cpu_init_collections(void)
 {
 	struct its_node *its;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 
 	list_for_each_entry(its, &its_nodes, entry)
 		its_cpu_init_collection(its);
 
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 }
 
 static struct its_device *its_find_device(struct its_node *its, u32 dev_id)
@@ -2134,17 +2200,20 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 	if (!its_alloc_device_table(its, dev_id))
 		return NULL;
 
+	if (WARN_ON(!is_power_of_2(nvecs)))
+		nvecs = roundup_pow_of_two(nvecs);
+
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	/*
-	 * We allocate at least one chunk worth of LPIs bet device,
-	 * and thus that many ITEs. The device may require less though.
+	 * Even if the device wants a single LPI, the ITT must be
+	 * sized as a power of two (and you need at least one bit...).
 	 */
-	nr_ites = max(IRQS_PER_CHUNK, roundup_pow_of_two(nvecs));
+	nr_ites = max(2, nvecs);
 	sz = nr_ites * its->ite_size;
 	sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1;
 	itt = kzalloc(sz, GFP_KERNEL);
 	if (alloc_lpis) {
-		lpi_map = its_lpi_alloc_chunks(nvecs, &lpi_base, &nr_lpis);
+		lpi_map = its_lpi_alloc(nvecs, &lpi_base, &nr_lpis);
 		if (lpi_map)
 			col_map = kcalloc(nr_lpis, sizeof(*col_map),
 					  GFP_KERNEL);
@@ -2379,9 +2448,9 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq,
 	/* If all interrupts have been freed, start mopping the floor */
 	if (bitmap_empty(its_dev->event_map.lpi_map,
 			 its_dev->event_map.nr_lpis)) {
-		its_lpi_free_chunks(its_dev->event_map.lpi_map,
-				    its_dev->event_map.lpi_base,
-				    its_dev->event_map.nr_lpis);
+		its_lpi_free(its_dev->event_map.lpi_map,
+			     its_dev->event_map.lpi_base,
+			     its_dev->event_map.nr_lpis);
 		kfree(its_dev->event_map.col_map);
 
 		/* Unmap device/itt */
@@ -2780,7 +2849,7 @@ static void its_vpe_irq_domain_free(struct irq_domain *domain,
 	}
 
 	if (bitmap_empty(vm->db_bitmap, vm->nr_db_lpis)) {
-		its_lpi_free_chunks(vm->db_bitmap, vm->db_lpi_base, vm->nr_db_lpis);
+		its_lpi_free(vm->db_bitmap, vm->db_lpi_base, vm->nr_db_lpis);
 		its_free_prop_table(vm->vprop_page);
 	}
 }
@@ -2795,18 +2864,18 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 
 	BUG_ON(!vm);
 
-	bitmap = its_lpi_alloc_chunks(nr_irqs, &base, &nr_ids);
+	bitmap = its_lpi_alloc(roundup_pow_of_two(nr_irqs), &base, &nr_ids);
 	if (!bitmap)
 		return -ENOMEM;
 
 	if (nr_ids < nr_irqs) {
-		its_lpi_free_chunks(bitmap, base, nr_ids);
+		its_lpi_free(bitmap, base, nr_ids);
 		return -ENOMEM;
 	}
 
 	vprop_page = its_allocate_prop_table(GFP_KERNEL);
 	if (!vprop_page) {
-		its_lpi_free_chunks(bitmap, base, nr_ids);
+		its_lpi_free(bitmap, base, nr_ids);
 		return -ENOMEM;
 	}
 
@@ -2833,7 +2902,7 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 		if (i > 0)
 			its_vpe_irq_domain_free(domain, virq, i - 1);
 
-		its_lpi_free_chunks(bitmap, base, nr_ids);
+		its_lpi_free(bitmap, base, nr_ids);
 		its_free_prop_table(vprop_page);
 	}
 
@@ -3070,7 +3139,7 @@ static int its_save_disable(void)
 	struct its_node *its;
 	int err = 0;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 	list_for_each_entry(its, &its_nodes, entry) {
 		void __iomem *base;
 
@@ -3102,7 +3171,7 @@ err:
 			writel_relaxed(its->ctlr_save, base + GITS_CTLR);
 		}
 	}
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 
 	return err;
 }
@@ -3112,7 +3181,7 @@ static void its_restore_enable(void)
 	struct its_node *its;
 	int ret;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 	list_for_each_entry(its, &its_nodes, entry) {
 		void __iomem *base;
 		int i;
@@ -3164,7 +3233,7 @@ static void its_restore_enable(void)
 		    GITS_TYPER_HCC(gic_read_typer(base + GITS_TYPER)))
 			its_cpu_init_collection(its);
 	}
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 }
 
 static struct syscore_ops its_syscore_ops = {
@@ -3398,9 +3467,9 @@ static int __init its_probe_one(struct resource *res,
 	if (err)
 		goto out_free_tables;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 	list_add(&its->entry, &its_nodes);
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 
 	return 0;
 
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 76ea56d779a1..e214181b77b7 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -877,7 +877,7 @@ static struct irq_chip gic_eoimode1_chip = {
 	.flags			= IRQCHIP_SET_TYPE_MASKED,
 };
 
-#define GIC_ID_NR		(1U << gic_data.rdists.id_bits)
+#define GIC_ID_NR	(1U << GICD_TYPER_ID_BITS(gic_data.rdists.gicd_typer))
 
 static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 			      irq_hw_number_t hw)
@@ -1091,7 +1091,7 @@ static int __init gic_init_bases(void __iomem *dist_base,
 	 * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI)
 	 */
 	typer = readl_relaxed(gic_data.dist_base + GICD_TYPER);
-	gic_data.rdists.id_bits = GICD_TYPER_ID_BITS(typer);
+	gic_data.rdists.gicd_typer = typer;
 	gic_irqs = GICD_TYPER_IRQS(typer);
 	if (gic_irqs > 1020)
 		gic_irqs = 1020;
diff --git a/drivers/irqchip/irq-ingenic.c b/drivers/irqchip/irq-ingenic.c
index fc5953dea509..2ff08986b536 100644
--- a/drivers/irqchip/irq-ingenic.c
+++ b/drivers/irqchip/irq-ingenic.c
@@ -165,6 +165,7 @@ static int __init intc_1chip_of_init(struct device_node *node,
 	return ingenic_intc_of_init(node, 1);
 }
 IRQCHIP_DECLARE(jz4740_intc, "ingenic,jz4740-intc", intc_1chip_of_init);
+IRQCHIP_DECLARE(jz4725b_intc, "ingenic,jz4725b-intc", intc_1chip_of_init);
 
 static int __init intc_2chip_of_init(struct device_node *node,
 	struct device_node *parent)
diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c
index 3a7e8905a97e..3df527fcf4e1 100644
--- a/drivers/irqchip/irq-stm32-exti.c
+++ b/drivers/irqchip/irq-stm32-exti.c
@@ -159,6 +159,7 @@ static const struct stm32_exti_bank *stm32mp1_exti_banks[] = {
 };
 
 static const struct stm32_desc_irq stm32mp1_desc_irq[] = {
+	{ .exti = 0, .irq_parent = 6 },
 	{ .exti = 1, .irq_parent = 7 },
 	{ .exti = 2, .irq_parent = 8 },
 	{ .exti = 3, .irq_parent = 9 },
diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c
index 6e0c2814d032..ef5560b848ab 100644
--- a/drivers/isdn/capi/capi.c
+++ b/drivers/isdn/capi/capi.c
@@ -9,6 +9,7 @@
  *
  */
 
+#include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
@@ -1321,7 +1322,7 @@ static inline void capinc_tty_exit(void) { }
  * /proc/capi/capi20:
  *  minor applid nrecvctlpkt nrecvdatapkt nsendctlpkt nsenddatapkt
  */
-static int capi20_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused capi20_proc_show(struct seq_file *m, void *v)
 {
 	struct capidev *cdev;
 	struct list_head *l;
@@ -1344,7 +1345,7 @@ static int capi20_proc_show(struct seq_file *m, void *v)
  * /proc/capi/capi20ncci:
  *  applid ncci
  */
-static int capi20ncci_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused capi20ncci_proc_show(struct seq_file *m, void *v)
 {
 	struct capidev *cdev;
 	struct capincci *np;
diff --git a/drivers/isdn/capi/capidrv.c b/drivers/isdn/capi/capidrv.c
index ee510f901720..e8949f3dcae1 100644
--- a/drivers/isdn/capi/capidrv.c
+++ b/drivers/isdn/capi/capidrv.c
@@ -9,6 +9,7 @@
  *
  */
 
+#include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
@@ -2451,7 +2452,7 @@ lower_callback(struct notifier_block *nb, unsigned long val, void *v)
  * /proc/capi/capidrv:
  * nrecvctlpkt nrecvdatapkt nsendctlpkt nsenddatapkt
  */
-static int capidrv_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused capidrv_proc_show(struct seq_file *m, void *v)
 {
 	seq_printf(m, "%lu %lu %lu %lu\n",
 		   global.ap.nrecvctlpkt,
diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c
index 20d0a080a2b0..ecdeb89645d0 100644
--- a/drivers/isdn/gigaset/bas-gigaset.c
+++ b/drivers/isdn/gigaset/bas-gigaset.c
@@ -739,6 +739,7 @@ static void read_int_callback(struct urb *urb)
 
 	case HD_OPEN_B2CHANNEL_ACK:
 		++channel;
+		/* fall through */
 	case HD_OPEN_B1CHANNEL_ACK:
 		bcs = cs->bcs + channel;
 		update_basstate(ucs, BS_B1OPEN << channel, 0);
@@ -752,6 +753,7 @@ static void read_int_callback(struct urb *urb)
 
 	case HD_CLOSE_B2CHANNEL_ACK:
 		++channel;
+		/* fall through */
 	case HD_CLOSE_B1CHANNEL_ACK:
 		bcs = cs->bcs + channel;
 		update_basstate(ucs, 0, BS_B1OPEN << channel);
@@ -765,6 +767,7 @@ static void read_int_callback(struct urb *urb)
 
 	case HD_B2_FLOW_CONTROL:
 		++channel;
+		/* fall through */
 	case HD_B1_FLOW_CONTROL:
 		bcs = cs->bcs + channel;
 		atomic_add((l - BAS_NORMFRAME) * BAS_CORRFRAMES,
@@ -972,16 +975,14 @@ static int starturbs(struct bc_state *bcs)
 			rc = -EFAULT;
 			goto error;
 		}
+		usb_fill_int_urb(urb, bcs->cs->hw.bas->udev,
+				 usb_rcvisocpipe(urb->dev, 3 + 2 * bcs->channel),
+				 ubc->isoinbuf + k * BAS_INBUFSIZE,
+				 BAS_INBUFSIZE, read_iso_callback, bcs,
+				 BAS_FRAMETIME);
 
-		urb->dev = bcs->cs->hw.bas->udev;
-		urb->pipe = usb_rcvisocpipe(urb->dev, 3 + 2 * bcs->channel);
 		urb->transfer_flags = URB_ISO_ASAP;
-		urb->transfer_buffer = ubc->isoinbuf + k * BAS_INBUFSIZE;
-		urb->transfer_buffer_length = BAS_INBUFSIZE;
 		urb->number_of_packets = BAS_NUMFRAMES;
-		urb->interval = BAS_FRAMETIME;
-		urb->complete = read_iso_callback;
-		urb->context = bcs;
 		for (j = 0; j < BAS_NUMFRAMES; j++) {
 			urb->iso_frame_desc[j].offset = j * BAS_MAXFRAME;
 			urb->iso_frame_desc[j].length = BAS_MAXFRAME;
@@ -1005,15 +1006,15 @@ static int starturbs(struct bc_state *bcs)
 			rc = -EFAULT;
 			goto error;
 		}
-		urb->dev = bcs->cs->hw.bas->udev;
-		urb->pipe = usb_sndisocpipe(urb->dev, 4 + 2 * bcs->channel);
+		usb_fill_int_urb(urb, bcs->cs->hw.bas->udev,
+				 usb_sndisocpipe(urb->dev, 4 + 2 * bcs->channel),
+				 ubc->isooutbuf->data,
+				 sizeof(ubc->isooutbuf->data),
+				 write_iso_callback, &ubc->isoouturbs[k],
+				 BAS_FRAMETIME);
+
 		urb->transfer_flags = URB_ISO_ASAP;
-		urb->transfer_buffer = ubc->isooutbuf->data;
-		urb->transfer_buffer_length = sizeof(ubc->isooutbuf->data);
 		urb->number_of_packets = BAS_NUMFRAMES;
-		urb->interval = BAS_FRAMETIME;
-		urb->complete = write_iso_callback;
-		urb->context = &ubc->isoouturbs[k];
 		for (j = 0; j < BAS_NUMFRAMES; ++j) {
 			urb->iso_frame_desc[j].offset = BAS_OUTBUFSIZE;
 			urb->iso_frame_desc[j].length = BAS_NORMFRAME;
diff --git a/drivers/isdn/hardware/mISDN/avmfritz.c b/drivers/isdn/hardware/mISDN/avmfritz.c
index ae2b2669af1b..8eb28a83832e 100644
--- a/drivers/isdn/hardware/mISDN/avmfritz.c
+++ b/drivers/isdn/hardware/mISDN/avmfritz.c
@@ -361,6 +361,7 @@ modehdlc(struct bchannel *bch, int protocol)
 	switch (protocol) {
 	case -1: /* used for init */
 		bch->state = -1;
+		/* fall through */
 	case ISDN_P_NONE:
 		if (bch->state == ISDN_P_NONE)
 			break;
diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c
index 34c93874af23..ebb3fa2e1d00 100644
--- a/drivers/isdn/hardware/mISDN/hfcpci.c
+++ b/drivers/isdn/hardware/mISDN/hfcpci.c
@@ -1296,6 +1296,7 @@ mode_hfcpci(struct bchannel *bch, int bc, int protocol)
 	case (-1): /* used for init */
 		bch->state = -1;
 		bch->nr = bc;
+		/* fall through */
 	case (ISDN_P_NONE):
 		if (bch->state == ISDN_P_NONE)
 			return 0;
@@ -2219,7 +2220,7 @@ hfc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct hfc_pci	*card;
 	struct _hfc_map	*m = (struct _hfc_map *)ent->driver_data;
 
-	card = kzalloc(sizeof(struct hfc_pci), GFP_ATOMIC);
+	card = kzalloc(sizeof(struct hfc_pci), GFP_KERNEL);
 	if (!card) {
 		printk(KERN_ERR "No kmem for HFC card\n");
 		return err;
diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c
index 17cc879ad2bb..6d05946b445e 100644
--- a/drivers/isdn/hardware/mISDN/hfcsusb.c
+++ b/drivers/isdn/hardware/mISDN/hfcsusb.c
@@ -819,6 +819,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len,
 	int		fifon = fifo->fifonum;
 	int		i;
 	int		hdlc = 0;
+	unsigned long	flags;
 
 	if (debug & DBG_HFC_CALL_TRACE)
 		printk(KERN_DEBUG "%s: %s: fifo(%i) len(%i) "
@@ -835,7 +836,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len,
 		return;
 	}
 
-	spin_lock(&hw->lock);
+	spin_lock_irqsave(&hw->lock, flags);
 	if (fifo->dch) {
 		rx_skb = fifo->dch->rx_skb;
 		maxlen = fifo->dch->maxlen;
@@ -844,7 +845,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len,
 	if (fifo->bch) {
 		if (test_bit(FLG_RX_OFF, &fifo->bch->Flags)) {
 			fifo->bch->dropcnt += len;
-			spin_unlock(&hw->lock);
+			spin_unlock_irqrestore(&hw->lock, flags);
 			return;
 		}
 		maxlen = bchannel_get_rxbuf(fifo->bch, len);
@@ -854,7 +855,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len,
 				skb_trim(rx_skb, 0);
 			pr_warning("%s.B%d: No bufferspace for %d bytes\n",
 				   hw->name, fifo->bch->nr, len);
-			spin_unlock(&hw->lock);
+			spin_unlock_irqrestore(&hw->lock, flags);
 			return;
 		}
 		maxlen = fifo->bch->maxlen;
@@ -878,7 +879,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len,
 			} else {
 				printk(KERN_DEBUG "%s: %s: No mem for rx_skb\n",
 				       hw->name, __func__);
-				spin_unlock(&hw->lock);
+				spin_unlock_irqrestore(&hw->lock, flags);
 				return;
 			}
 		}
@@ -888,7 +889,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len,
 			       "for fifo(%d) HFCUSB_D_RX\n",
 			       hw->name, __func__, fifon);
 			skb_trim(rx_skb, 0);
-			spin_unlock(&hw->lock);
+			spin_unlock_irqrestore(&hw->lock, flags);
 			return;
 		}
 	}
@@ -942,7 +943,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len,
 		/* deliver transparent data to layer2 */
 		recv_Bchannel(fifo->bch, MISDN_ID_ANY, false);
 	}
-	spin_unlock(&hw->lock);
+	spin_unlock_irqrestore(&hw->lock, flags);
 }
 
 static void
@@ -979,18 +980,19 @@ rx_iso_complete(struct urb *urb)
 	__u8 *buf;
 	static __u8 eof[8];
 	__u8 s0_state;
+	unsigned long flags;
 
 	fifon = fifo->fifonum;
 	status = urb->status;
 
-	spin_lock(&hw->lock);
+	spin_lock_irqsave(&hw->lock, flags);
 	if (fifo->stop_gracefull) {
 		fifo->stop_gracefull = 0;
 		fifo->active = 0;
-		spin_unlock(&hw->lock);
+		spin_unlock_irqrestore(&hw->lock, flags);
 		return;
 	}
-	spin_unlock(&hw->lock);
+	spin_unlock_irqrestore(&hw->lock, flags);
 
 	/*
 	 * ISO transfer only partially completed,
@@ -1096,15 +1098,16 @@ rx_int_complete(struct urb *urb)
 	struct usb_fifo *fifo = (struct usb_fifo *) urb->context;
 	struct hfcsusb *hw = fifo->hw;
 	static __u8 eof[8];
+	unsigned long flags;
 
-	spin_lock(&hw->lock);
+	spin_lock_irqsave(&hw->lock, flags);
 	if (fifo->stop_gracefull) {
 		fifo->stop_gracefull = 0;
 		fifo->active = 0;
-		spin_unlock(&hw->lock);
+		spin_unlock_irqrestore(&hw->lock, flags);
 		return;
 	}
-	spin_unlock(&hw->lock);
+	spin_unlock_irqrestore(&hw->lock, flags);
 
 	fifon = fifo->fifonum;
 	if ((!fifo->active) || (urb->status)) {
@@ -1172,12 +1175,13 @@ tx_iso_complete(struct urb *urb)
 	int *tx_idx;
 	int frame_complete, fifon, status, fillempty = 0;
 	__u8 threshbit, *p;
+	unsigned long flags;
 
-	spin_lock(&hw->lock);
+	spin_lock_irqsave(&hw->lock, flags);
 	if (fifo->stop_gracefull) {
 		fifo->stop_gracefull = 0;
 		fifo->active = 0;
-		spin_unlock(&hw->lock);
+		spin_unlock_irqrestore(&hw->lock, flags);
 		return;
 	}
 
@@ -1195,7 +1199,7 @@ tx_iso_complete(struct urb *urb)
 	} else {
 		printk(KERN_DEBUG "%s: %s: neither BCH nor DCH\n",
 		       hw->name, __func__);
-		spin_unlock(&hw->lock);
+		spin_unlock_irqrestore(&hw->lock, flags);
 		return;
 	}
 
@@ -1375,7 +1379,7 @@ tx_iso_complete(struct urb *urb)
 			       hw->name, __func__,
 			       symbolic(urb_errlist, status), status, fifon);
 	}
-	spin_unlock(&hw->lock);
+	spin_unlock_irqrestore(&hw->lock, flags);
 }
 
 /*
diff --git a/drivers/isdn/hardware/mISDN/mISDNinfineon.c b/drivers/isdn/hardware/mISDN/mISDNinfineon.c
index 1fc290659e94..3e01012be4ab 100644
--- a/drivers/isdn/hardware/mISDN/mISDNinfineon.c
+++ b/drivers/isdn/hardware/mISDN/mISDNinfineon.c
@@ -887,6 +887,7 @@ release_card(struct inf_hw *card) {
 				release_card(card->sc[i]);
 			card->sc[i] = NULL;
 		}
+		/* fall through */
 	default:
 		pci_disable_device(card->pdev);
 		pci_set_drvdata(card->pdev, NULL);
diff --git a/drivers/isdn/hardware/mISDN/mISDNisar.c b/drivers/isdn/hardware/mISDN/mISDNisar.c
index b791688d0228..386731ec2489 100644
--- a/drivers/isdn/hardware/mISDN/mISDNisar.c
+++ b/drivers/isdn/hardware/mISDN/mISDNisar.c
@@ -972,6 +972,7 @@ isar_pump_statev_fax(struct isar_ch *ch, u8 devt) {
 				break;
 			case PCTRL_CMD_FTM:
 				p1 = 2;
+				/* fall through */
 			case PCTRL_CMD_FTH:
 				send_mbox(ch->is, dps | ISAR_HIS_PUMPCTRL,
 					  PCTRL_CMD_SILON, 1, &p1);
@@ -1177,6 +1178,7 @@ setup_pump(struct isar_ch *ch) {
 			send_mbox(ch->is, dps | ISAR_HIS_PUMPCFG,
 				  PMOD_DTMF, 1, param);
 		}
+		/* fall through */
 	case ISDN_P_B_MODEM_ASYNC:
 		ctrl = PMOD_DATAMODEM;
 		if (test_bit(FLG_ORIGIN, &ch->bch.Flags)) {
@@ -1268,6 +1270,7 @@ setup_iom2(struct isar_ch *ch) {
 	case ISDN_P_B_MODEM_ASYNC:
 	case ISDN_P_B_T30_FAX:
 		cmsb |= IOM_CTRL_RCV;
+		/* fall through */
 	case ISDN_P_B_L2DTMF:
 		if (test_bit(FLG_DTMFSEND, &ch->bch.Flags))
 			cmsb |= IOM_CTRL_RCV;
@@ -1560,6 +1563,7 @@ isar_l2l1(struct mISDNchannel *ch, struct sk_buff *skb)
 				ich->is->name, hh->id);
 			ret = -EINVAL;
 		}
+		/* fall through */
 	default:
 		pr_info("%s: %s unknown prim(%x,%x)\n",
 			ich->is->name, __func__, hh->prim, hh->id);
diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c
index 89d9ba8ed535..2b317cb63d06 100644
--- a/drivers/isdn/hardware/mISDN/netjet.c
+++ b/drivers/isdn/hardware/mISDN/netjet.c
@@ -1084,7 +1084,7 @@ nj_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return -ENODEV;
 	}
 
-	card = kzalloc(sizeof(struct tiger_hw), GFP_ATOMIC);
+	card = kzalloc(sizeof(struct tiger_hw), GFP_KERNEL);
 	if (!card) {
 		pr_info("No kmem for Netjet\n");
 		return err;
diff --git a/drivers/isdn/hisax/avm_pci.c b/drivers/isdn/hisax/avm_pci.c
index a18b605fb4f2..b161456c942e 100644
--- a/drivers/isdn/hisax/avm_pci.c
+++ b/drivers/isdn/hisax/avm_pci.c
@@ -207,6 +207,7 @@ modehdlc(struct BCState *bcs, int mode, int bc)
 		bcs->mode = 1;
 		bcs->channel = bc;
 		bc = 0;
+		/* fall through */
 	case (L1_MODE_NULL):
 		if (bcs->mode == L1_MODE_NULL)
 			return;
diff --git a/drivers/isdn/hisax/callc.c b/drivers/isdn/hisax/callc.c
index ddec47a911a0..9ee06328784c 100644
--- a/drivers/isdn/hisax/callc.c
+++ b/drivers/isdn/hisax/callc.c
@@ -1012,7 +1012,7 @@ dummy_pstack(struct PStack *st, int pr, void *arg) {
 
 static int
 init_PStack(struct PStack **stp) {
-	*stp = kmalloc(sizeof(struct PStack), GFP_ATOMIC);
+	*stp = kmalloc(sizeof(struct PStack), GFP_KERNEL);
 	if (!*stp)
 		return -ENOMEM;
 	(*stp)->next = NULL;
@@ -1369,6 +1369,7 @@ leased_l1l2(struct PStack *st, int pr, void *arg)
 	case (PH_ACTIVATE | INDICATION):
 	case (PH_ACTIVATE | CONFIRM):
 		event = EV_LEASED;
+		/* fall through */
 	case (PH_DEACTIVATE | INDICATION):
 	case (PH_DEACTIVATE | CONFIRM):
 		if (test_bit(FLG_TWO_DCHAN, &chanp->cs->HW_Flags))
diff --git a/drivers/isdn/hisax/config.c b/drivers/isdn/hisax/config.c
index 7108bdb8742e..b12e6cae26c2 100644
--- a/drivers/isdn/hisax/config.c
+++ b/drivers/isdn/hisax/config.c
@@ -1029,7 +1029,7 @@ static int hisax_cs_new(int cardnr, char *id, struct IsdnCard *card,
 
 	*cs_out = NULL;
 
-	cs = kzalloc(sizeof(struct IsdnCardState), GFP_ATOMIC);
+	cs = kzalloc(sizeof(struct IsdnCardState), GFP_KERNEL);
 	if (!cs) {
 		printk(KERN_WARNING
 		       "HiSax: No memory for IsdnCardState(card %d)\n",
@@ -1059,12 +1059,12 @@ static int hisax_cs_new(int cardnr, char *id, struct IsdnCard *card,
 		       "HiSax: Card Type %d out of range\n", card->typ);
 		goto outf_cs;
 	}
-	if (!(cs->dlog = kmalloc(MAX_DLOG_SPACE, GFP_ATOMIC))) {
+	if (!(cs->dlog = kmalloc(MAX_DLOG_SPACE, GFP_KERNEL))) {
 		printk(KERN_WARNING
 		       "HiSax: No memory for dlog(card %d)\n", cardnr + 1);
 		goto outf_cs;
 	}
-	if (!(cs->status_buf = kmalloc(HISAX_STATUS_BUFSIZE, GFP_ATOMIC))) {
+	if (!(cs->status_buf = kmalloc(HISAX_STATUS_BUFSIZE, GFP_KERNEL))) {
 		printk(KERN_WARNING
 		       "HiSax: No memory for status_buf(card %d)\n",
 		       cardnr + 1);
@@ -1123,7 +1123,7 @@ static int hisax_cs_setup(int cardnr, struct IsdnCard *card,
 {
 	int ret;
 
-	if (!(cs->rcvbuf = kmalloc(MAX_DFRAME_LEN_L1, GFP_ATOMIC))) {
+	if (!(cs->rcvbuf = kmalloc(MAX_DFRAME_LEN_L1, GFP_KERNEL))) {
 		printk(KERN_WARNING "HiSax: No memory for isac rcvbuf\n");
 		ll_unload(cs);
 		goto outf_cs;
@@ -1843,6 +1843,7 @@ static void hisax_b_l2l1(struct PStack *st, int pr, void *arg)
 	case PH_DEACTIVATE | REQUEST:
 		test_and_clear_bit(BC_FLG_BUSY, &bcs->Flag);
 		skb_queue_purge(&bcs->squeue);
+		/* fall through */
 	default:
 		B_L2L1(b_if, pr, arg);
 		break;
diff --git a/drivers/isdn/hisax/gazel.c b/drivers/isdn/hisax/gazel.c
index 35c6df6534ec..a6d8af02354a 100644
--- a/drivers/isdn/hisax/gazel.c
+++ b/drivers/isdn/hisax/gazel.c
@@ -108,6 +108,7 @@ ReadISAC(struct IsdnCardState *cs, u_char offset)
 	switch (cs->subtyp) {
 	case R647:
 		off2 = ((off2 << 8 & 0xf000) | (off2 & 0xf));
+		/* fall through */
 	case R685:
 		return (readreg(cs->hw.gazel.isac, off2));
 	case R753:
@@ -125,6 +126,7 @@ WriteISAC(struct IsdnCardState *cs, u_char offset, u_char value)
 	switch (cs->subtyp) {
 	case R647:
 		off2 = ((off2 << 8 & 0xf000) | (off2 & 0xf));
+		/* fall through */
 	case R685:
 		writereg(cs->hw.gazel.isac, off2, value);
 		break;
@@ -203,6 +205,7 @@ ReadHSCX(struct IsdnCardState *cs, int hscx, u_char offset)
 	switch (cs->subtyp) {
 	case R647:
 		off2 = ((off2 << 8 & 0xf000) | (off2 & 0xf));
+		/* fall through */
 	case R685:
 		return (readreg(cs->hw.gazel.hscx[hscx], off2));
 	case R753:
@@ -220,6 +223,7 @@ WriteHSCX(struct IsdnCardState *cs, int hscx, u_char offset, u_char value)
 	switch (cs->subtyp) {
 	case R647:
 		off2 = ((off2 << 8 & 0xf000) | (off2 & 0xf));
+		/* fall through */
 	case R685:
 		writereg(cs->hw.gazel.hscx[hscx], off2, value);
 		break;
diff --git a/drivers/isdn/hisax/hfc_usb.c b/drivers/isdn/hisax/hfc_usb.c
index 97ecb3073045..1d4cd01d4685 100644
--- a/drivers/isdn/hisax/hfc_usb.c
+++ b/drivers/isdn/hisax/hfc_usb.c
@@ -432,16 +432,12 @@ fill_isoc_urb(struct urb *urb, struct usb_device *dev, unsigned int pipe,
 {
 	int k;
 
-	urb->dev = dev;
-	urb->pipe = pipe;
-	urb->complete = complete;
+	usb_fill_int_urb(urb, dev, pipe, buf, packet_size * num_packets,
+			 complete, context, interval);
+
 	urb->number_of_packets = num_packets;
-	urb->transfer_buffer_length = packet_size * num_packets;
-	urb->context = context;
-	urb->transfer_buffer = buf;
 	urb->transfer_flags = URB_ISO_ASAP;
 	urb->actual_length = 0;
-	urb->interval = interval;
 	for (k = 0; k < num_packets; k++) {
 		urb->iso_frame_desc[k].offset = packet_size * k;
 		urb->iso_frame_desc[k].length = packet_size;
diff --git a/drivers/isdn/hisax/isar.c b/drivers/isdn/hisax/isar.c
index d01ff116797b..82c1879f5664 100644
--- a/drivers/isdn/hisax/isar.c
+++ b/drivers/isdn/hisax/isar.c
@@ -1089,6 +1089,7 @@ isar_pump_statev_fax(struct BCState *bcs, u_char devt) {
 				break;
 			case PCTRL_CMD_FTM:
 				p1 = 2;
+				/* fall through */
 			case PCTRL_CMD_FTH:
 				sendmsg(cs, dps | ISAR_HIS_PUMPCTRL,
 					PCTRL_CMD_SILON, 1, &p1);
@@ -1097,6 +1098,7 @@ isar_pump_statev_fax(struct BCState *bcs, u_char devt) {
 			case PCTRL_CMD_FRM:
 				if (frm_extra_delay)
 					mdelay(frm_extra_delay);
+				/* fall through */
 			case PCTRL_CMD_FRH:
 				p1 = bcs->hw.isar.mod = bcs->hw.isar.newmod;
 				bcs->hw.isar.newmod = 0;
diff --git a/drivers/isdn/hisax/l3_1tr6.c b/drivers/isdn/hisax/l3_1tr6.c
index da0a1c6aa329..98f60d1523f4 100644
--- a/drivers/isdn/hisax/l3_1tr6.c
+++ b/drivers/isdn/hisax/l3_1tr6.c
@@ -88,6 +88,7 @@ l3_1tr6_setup_req(struct l3_process *pc, u_char pr, void *arg)
 			break;
 		case 'C':
 			channel = 0x08;
+			/* fall through */
 		case 'P':
 			channel |= 0x80;
 			teln++;
diff --git a/drivers/isdn/hisax/l3dss1.c b/drivers/isdn/hisax/l3dss1.c
index 18a3484b1f7e..368d152a8f1d 100644
--- a/drivers/isdn/hisax/l3dss1.c
+++ b/drivers/isdn/hisax/l3dss1.c
@@ -1282,6 +1282,7 @@ l3dss1_setup_req(struct l3_process *pc, u_char pr,
 			switch (0x5f & *teln) {
 			case 'C':
 				channel = 0x08;
+				/* fall through */
 			case 'P':
 				channel |= 0x80;
 				teln++;
diff --git a/drivers/isdn/hisax/st5481_usb.c b/drivers/isdn/hisax/st5481_usb.c
index 1cb9930d5e24..f207fda691c7 100644
--- a/drivers/isdn/hisax/st5481_usb.c
+++ b/drivers/isdn/hisax/st5481_usb.c
@@ -408,15 +408,10 @@ fill_isoc_urb(struct urb *urb, struct usb_device *dev,
 {
 	int k;
 
-	urb->dev = dev;
-	urb->pipe = pipe;
-	urb->interval = 1;
-	urb->transfer_buffer = buf;
+	usb_fill_int_urb(urb, dev, pipe, buf, num_packets * packet_size,
+			 complete, context, 1);
+
 	urb->number_of_packets = num_packets;
-	urb->transfer_buffer_length = num_packets * packet_size;
-	urb->actual_length = 0;
-	urb->complete = complete;
-	urb->context = context;
 	urb->transfer_flags = URB_ISO_ASAP;
 	for (k = 0; k < num_packets; k++) {
 		urb->iso_frame_desc[k].offset = packet_size * k;
diff --git a/drivers/isdn/hysdn/hysdn_boot.c b/drivers/isdn/hysdn/hysdn_boot.c
index 4a0425378f37..ba177c3a621b 100644
--- a/drivers/isdn/hysdn/hysdn_boot.c
+++ b/drivers/isdn/hysdn/hysdn_boot.c
@@ -99,6 +99,7 @@ pof_handle_data(hysdn_card *card, int datlen)
 
 	case TAG_CBOOTDTA:
 		DecryptBuf(boot, datlen);	/* we need to encrypt the buffer */
+		/* fall through */
 	case TAG_BOOTDTA:
 		if (card->debug_flags & LOG_POF_RECORD)
 			hysdn_addlog(card, "POF got %s len=%d offs=0x%lx",
@@ -137,6 +138,7 @@ pof_handle_data(hysdn_card *card, int datlen)
 
 	case TAG_CABSDATA:
 		DecryptBuf(boot, datlen);	/* we need to encrypt the buffer */
+		/* fall through */
 	case TAG_ABSDATA:
 		if (card->debug_flags & LOG_POF_RECORD)
 			hysdn_addlog(card, "POF got %s len=%d offs=0x%lx",
diff --git a/drivers/isdn/i4l/isdn_tty.c b/drivers/isdn/i4l/isdn_tty.c
index 960f26348bb5..b730037a0e2d 100644
--- a/drivers/isdn/i4l/isdn_tty.c
+++ b/drivers/isdn/i4l/isdn_tty.c
@@ -787,7 +787,7 @@ isdn_tty_suspend(char *id, modem_info *info, atemu *m)
 		cmd.parm.cmsg.para[3] = 4; /* 16 bit 0x0004 Suspend */
 		cmd.parm.cmsg.para[4] = 0;
 		cmd.parm.cmsg.para[5] = l;
-		strncpy(&cmd.parm.cmsg.para[6], id, l);
+		memcpy(&cmd.parm.cmsg.para[6], id, l);
 		cmd.command = CAPI_PUT_MESSAGE;
 		cmd.driver = info->isdn_driver;
 		cmd.arg = info->isdn_channel;
@@ -877,7 +877,7 @@ isdn_tty_resume(char *id, modem_info *info, atemu *m)
 		cmd.parm.cmsg.para[3] = 5; /* 16 bit 0x0005 Resume */
 		cmd.parm.cmsg.para[4] = 0;
 		cmd.parm.cmsg.para[5] = l;
-		strncpy(&cmd.parm.cmsg.para[6], id, l);
+		memcpy(&cmd.parm.cmsg.para[6], id, l);
 		cmd.command = CAPI_PUT_MESSAGE;
 		info->dialing = 1;
 //		strcpy(dev->num[i], n);
diff --git a/drivers/isdn/i4l/isdn_v110.c b/drivers/isdn/i4l/isdn_v110.c
index 8b74ce412524..2a5f6668756c 100644
--- a/drivers/isdn/i4l/isdn_v110.c
+++ b/drivers/isdn/i4l/isdn_v110.c
@@ -354,6 +354,7 @@ EncodeMatrix(unsigned char *buf, int len, unsigned char *m, int mlen)
 				printk(KERN_WARNING "isdn_v110 (EncodeMatrix): buffer full!\n");
 				return line;
 			}
+			/* else: fall through */
 		case 128:
 			m[line] = 128;	/* leftmost -> set byte to 1000000 */
 			mbit = 64;	/* current bit in the matrix line */
@@ -386,20 +387,28 @@ EncodeMatrix(unsigned char *buf, int len, unsigned char *m, int mlen)
 		switch (++line % 10) {
 		case 1:
 			m[line++] = 0xfe;
+			/* fall through */
 		case 2:
 			m[line++] = 0xfe;
+			/* fall through */
 		case 3:
 			m[line++] = 0xfe;
+			/* fall through */
 		case 4:
 			m[line++] = 0xfe;
+			/* fall through */
 		case 5:
 			m[line++] = 0xbf;
+			/* fall through */
 		case 6:
 			m[line++] = 0xfe;
+			/* fall through */
 		case 7:
 			m[line++] = 0xfe;
+			/* fall through */
 		case 8:
 			m[line++] = 0xfe;
+			/* fall through */
 		case 9:
 			m[line++] = 0xfe;
 		}
diff --git a/drivers/isdn/mISDN/stack.c b/drivers/isdn/mISDN/stack.c
index 422dced7c90a..d97c6dd52223 100644
--- a/drivers/isdn/mISDN/stack.c
+++ b/drivers/isdn/mISDN/stack.c
@@ -539,6 +539,7 @@ create_l2entity(struct mISDNdevice *dev, struct mISDNchannel *ch,
 		rq.protocol = ISDN_P_NT_S0;
 		if (dev->Dprotocols & (1 << ISDN_P_NT_E1))
 			rq.protocol = ISDN_P_NT_E1;
+		/* fall through */
 	case ISDN_P_LAPD_TE:
 		ch->recv = mISDN_queue_message;
 		ch->peer = &dev->D.st->own;
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 6e3a998f3370..44097a3e0fcc 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -57,12 +57,13 @@ config LEDS_AAT1290
 	depends on PINCTRL
 	help
 	 This option enables support for the LEDs on the AAT1290.
+
 config LEDS_APU
-	tristate "Front panel LED support for PC Engines APU/APU2 boards"
+	tristate "Front panel LED support for PC Engines APU/APU2/APU3 boards"
 	depends on LEDS_CLASS
 	depends on X86 && DMI
 	help
-	  This driver makes the PC Engines APU/APU2 front panel LEDs
+	  This driver makes the PC Engines APU/APU2/APU3 front panel LEDs
 	  accessible from userspace programs through the LED subsystem.
 
 	  To compile this driver as a module, choose M here: the
diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c
index 431123b048a2..17d73db1456e 100644
--- a/drivers/leds/led-triggers.c
+++ b/drivers/leds/led-triggers.c
@@ -103,15 +103,16 @@ ssize_t led_trigger_show(struct device *dev, struct device_attribute *attr,
 EXPORT_SYMBOL_GPL(led_trigger_show);
 
 /* Caller must ensure led_cdev->trigger_lock held */
-void led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
+int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
 {
 	unsigned long flags;
 	char *event = NULL;
 	char *envp[2];
 	const char *name;
+	int ret;
 
 	if (!led_cdev->trigger && !trig)
-		return;
+		return 0;
 
 	name = trig ? trig->name : "none";
 	event = kasprintf(GFP_KERNEL, "TRIGGER=%s", name);
@@ -126,7 +127,10 @@ void led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
 		led_stop_software_blink(led_cdev);
 		if (led_cdev->trigger->deactivate)
 			led_cdev->trigger->deactivate(led_cdev);
+		device_remove_groups(led_cdev->dev, led_cdev->trigger->groups);
 		led_cdev->trigger = NULL;
+		led_cdev->trigger_data = NULL;
+		led_cdev->activated = false;
 		led_set_brightness(led_cdev, LED_OFF);
 	}
 	if (trig) {
@@ -134,8 +138,20 @@ void led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
 		list_add_tail(&led_cdev->trig_list, &trig->led_cdevs);
 		write_unlock_irqrestore(&trig->leddev_list_lock, flags);
 		led_cdev->trigger = trig;
+
 		if (trig->activate)
-			trig->activate(led_cdev);
+			ret = trig->activate(led_cdev);
+		else
+			ret = 0;
+
+		if (ret)
+			goto err_activate;
+
+		ret = device_add_groups(led_cdev->dev, trig->groups);
+		if (ret) {
+			dev_err(led_cdev->dev, "Failed to add trigger attributes\n");
+			goto err_add_groups;
+		}
 	}
 
 	if (event) {
@@ -146,6 +162,23 @@ void led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
 				"%s: Error sending uevent\n", __func__);
 		kfree(event);
 	}
+
+	return 0;
+
+err_add_groups:
+
+	if (trig->deactivate)
+		trig->deactivate(led_cdev);
+err_activate:
+
+	led_cdev->trigger = NULL;
+	led_cdev->trigger_data = NULL;
+	write_lock_irqsave(&led_cdev->trigger->leddev_list_lock, flags);
+	list_del(&led_cdev->trig_list);
+	write_unlock_irqrestore(&led_cdev->trigger->leddev_list_lock, flags);
+	led_set_brightness(led_cdev, LED_OFF);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(led_trigger_set);
 
diff --git a/drivers/leds/leds-apu.c b/drivers/leds/leds-apu.c
index 8c93d68964c7..8d42e46e2de3 100644
--- a/drivers/leds/leds-apu.c
+++ b/drivers/leds/leds-apu.c
@@ -102,6 +102,13 @@ static const struct apu_led_profile apu2_led_profile[] = {
 	{ "apu2:green:3", LED_OFF, APU2_FCH_GPIO_BASE + 70 * APU2_IOSIZE },
 };
 
+/* Same as apu2_led_profile, but with "3" in the LED names. */
+static const struct apu_led_profile apu3_led_profile[] = {
+	{ "apu3:green:1", LED_ON,  APU2_FCH_GPIO_BASE + 68 * APU2_IOSIZE },
+	{ "apu3:green:2", LED_OFF, APU2_FCH_GPIO_BASE + 69 * APU2_IOSIZE },
+	{ "apu3:green:3", LED_OFF, APU2_FCH_GPIO_BASE + 70 * APU2_IOSIZE },
+};
+
 static const struct dmi_system_id apu_led_dmi_table[] __initconst = {
 	{
 		.ident = "apu",
@@ -134,6 +141,30 @@ static const struct dmi_system_id apu_led_dmi_table[] __initconst = {
 			DMI_MATCH(DMI_BOARD_NAME, "PC Engines apu2")
 		}
 	},
+	/* PC Engines APU3 with "Legacy" bios < 4.0.8 */
+	{
+		.ident = "apu3",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "PC Engines"),
+			DMI_MATCH(DMI_BOARD_NAME, "APU3")
+		}
+	},
+	/* PC Engines APU3 with "Legacy" bios >= 4.0.8 */
+	{
+		.ident = "apu3",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "PC Engines"),
+			DMI_MATCH(DMI_BOARD_NAME, "apu3")
+		}
+	},
+	/* PC Engines APU2 with "Mainline" bios */
+	{
+		.ident = "apu3",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "PC Engines"),
+			DMI_MATCH(DMI_BOARD_NAME, "PC Engines apu3")
+		}
+	},
 	{}
 };
 MODULE_DEVICE_TABLE(dmi, apu_led_dmi_table);
@@ -235,6 +266,14 @@ static int __init apu_led_probe(struct platform_device *pdev)
 		apu_led->platform = APU2_LED_PLATFORM;
 		apu_led->num_led_instances = ARRAY_SIZE(apu2_led_profile);
 		apu_led->iosize = APU2_IOSIZE;
+	} else if (dmi_match(DMI_BOARD_NAME, "APU3") ||
+		   dmi_match(DMI_BOARD_NAME, "apu3") ||
+		   dmi_match(DMI_BOARD_NAME, "PC Engines apu3")) {
+		apu_led->profile = apu3_led_profile;
+		/* Otherwise identical to APU2. */
+		apu_led->platform = APU2_LED_PLATFORM;
+		apu_led->num_led_instances = ARRAY_SIZE(apu3_led_profile);
+		apu_led->iosize = APU2_IOSIZE;
 	}
 
 	spin_lock_init(&apu_led->lock);
@@ -259,7 +298,10 @@ static int __init apu_led_init(void)
 	if (!(dmi_match(DMI_PRODUCT_NAME, "APU") ||
 	      dmi_match(DMI_PRODUCT_NAME, "APU2") ||
 	      dmi_match(DMI_PRODUCT_NAME, "apu2") ||
-	      dmi_match(DMI_PRODUCT_NAME, "PC Engines apu2"))) {
+	      dmi_match(DMI_PRODUCT_NAME, "PC Engines apu2") ||
+	      dmi_match(DMI_PRODUCT_NAME, "APU3") ||
+	      dmi_match(DMI_PRODUCT_NAME, "apu3") ||
+	      dmi_match(DMI_PRODUCT_NAME, "PC Engines apu3"))) {
 		pr_err("Unknown PC Engines board: %s\n",
 				dmi_get_system_info(DMI_PRODUCT_NAME));
 		return -ENODEV;
diff --git a/drivers/leds/leds-lm3692x.c b/drivers/leds/leds-lm3692x.c
index 437173d1712c..4f413a7c5f05 100644
--- a/drivers/leds/leds-lm3692x.c
+++ b/drivers/leds/leds-lm3692x.c
@@ -1,17 +1,6 @@
-/*
- * TI lm3692x LED Driver
- *
- * Copyright (C) 2017 Texas Instruments
- *
- * Author: Dan Murphy <dmurphy@ti.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * Data sheet is located
- * http://www.ti.com/lit/ds/snvsa29/snvsa29.pdf
- */
+// SPDX-License-Identifier: GPL-2.0
+// TI LM3692x LED chip family driver
+// Copyright (C) 2017-18 Texas Instruments Incorporated - http://www.ti.com/
 
 #include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
@@ -26,6 +15,9 @@
 #include <linux/slab.h>
 #include <uapi/linux/uleds.h>
 
+#define LM36922_MODEL	0
+#define LM36923_MODEL	1
+
 #define LM3692X_REV		0x0
 #define LM3692X_RESET		0x1
 #define LM3692X_EN		0x10
@@ -44,6 +36,9 @@
 #define LM3692X_DEVICE_EN	BIT(0)
 #define LM3692X_LED1_EN		BIT(1)
 #define LM3692X_LED2_EN		BIT(2)
+#define LM36923_LED3_EN		BIT(3)
+#define LM3692X_ENABLE_MASK	(LM3692X_DEVICE_EN | LM3692X_LED1_EN | \
+				 LM3692X_LED2_EN | LM36923_LED3_EN)
 
 /* Brightness Control Bits */
 #define LM3692X_BL_ADJ_POL	BIT(0)
@@ -109,6 +104,8 @@
  * @enable_gpio - VDDIO/EN gpio to enable communication interface
  * @regulator - LED supply regulator pointer
  * @label - LED label
+ * @led_enable - LED sync to be enabled
+ * @model_id - Current device model ID enumerated
  */
 struct lm3692x_led {
 	struct mutex lock;
@@ -118,6 +115,8 @@ struct lm3692x_led {
 	struct gpio_desc *enable_gpio;
 	struct regulator *regulator;
 	char label[LED_MAX_NAME_SIZE];
+	int led_enable;
+	int model_id;
 };
 
 static const struct reg_default lm3692x_reg_defs[] = {
@@ -200,6 +199,7 @@ out:
 
 static int lm3692x_init(struct lm3692x_led *led)
 {
+	int enable_state;
 	int ret;
 
 	if (led->regulator) {
@@ -226,9 +226,25 @@ static int lm3692x_init(struct lm3692x_led *led)
 
 	/*
 	 * For glitch free operation, the following data should
-	 * only be written while device enable bit is 0
+	 * only be written while LEDx enable bits are 0 and the device enable
+	 * bit is set to 1.
 	 * per Section 7.5.14 of the data sheet
 	 */
+	ret = regmap_write(led->regmap, LM3692X_EN, LM3692X_DEVICE_EN);
+	if (ret)
+		goto out;
+
+	/* Set the brightness to 0 so when enabled the LEDs do not come
+	 * on with full brightness.
+	 */
+	ret = regmap_write(led->regmap, LM3692X_BRT_MSB, 0);
+	if (ret)
+		goto out;
+
+	ret = regmap_write(led->regmap, LM3692X_BRT_LSB, 0);
+	if (ret)
+		goto out;
+
 	ret = regmap_write(led->regmap, LM3692X_PWM_CTRL,
 		LM3692X_PWM_FILTER_100 | LM3692X_PWM_SAMP_24MHZ);
 	if (ret)
@@ -258,6 +274,38 @@ static int lm3692x_init(struct lm3692x_led *led)
 	if (ret)
 		goto out;
 
+	switch (led->led_enable) {
+	case 0:
+	default:
+		if (led->model_id == LM36923_MODEL)
+			enable_state = LM3692X_LED1_EN | LM3692X_LED2_EN |
+			       LM36923_LED3_EN;
+		else
+			enable_state = LM3692X_LED1_EN | LM3692X_LED2_EN;
+
+		break;
+	case 1:
+		enable_state = LM3692X_LED1_EN;
+		break;
+	case 2:
+		enable_state = LM3692X_LED2_EN;
+		break;
+
+	case 3:
+		if (led->model_id == LM36923_MODEL) {
+			enable_state = LM36923_LED3_EN;
+			break;
+		}
+
+		ret = -EINVAL;
+		dev_err(&led->client->dev,
+			"LED3 sync not available on this device\n");
+		goto out;
+	}
+
+	ret = regmap_update_bits(led->regmap, LM3692X_EN, LM3692X_ENABLE_MASK,
+				 enable_state | LM3692X_DEVICE_EN);
+
 	return ret;
 out:
 	dev_err(&led->client->dev, "Fail writing initialization values\n");
@@ -274,52 +322,75 @@ out:
 
 	return ret;
 }
-
-static int lm3692x_probe(struct i2c_client *client,
-			const struct i2c_device_id *id)
+static int lm3692x_probe_dt(struct lm3692x_led *led)
 {
-	int ret;
-	struct lm3692x_led *led;
-	struct device_node *np = client->dev.of_node;
-	struct device_node *child_node;
+	struct fwnode_handle *child = NULL;
 	const char *name;
+	int ret;
 
-	led = devm_kzalloc(&client->dev, sizeof(*led), GFP_KERNEL);
-	if (!led)
-		return -ENOMEM;
-
-	for_each_available_child_of_node(np, child_node) {
-		led->led_dev.default_trigger = of_get_property(child_node,
-						    "linux,default-trigger",
-						    NULL);
-
-		ret = of_property_read_string(child_node, "label", &name);
-		if (!ret)
-			snprintf(led->label, sizeof(led->label),
-				 "%s:%s", id->name, name);
-		else
-			snprintf(led->label, sizeof(led->label),
-				 "%s::backlight_cluster", id->name);
-	};
-
-	led->enable_gpio = devm_gpiod_get_optional(&client->dev,
+	led->enable_gpio = devm_gpiod_get_optional(&led->client->dev,
 						   "enable", GPIOD_OUT_LOW);
 	if (IS_ERR(led->enable_gpio)) {
 		ret = PTR_ERR(led->enable_gpio);
-		dev_err(&client->dev, "Failed to get enable gpio: %d\n", ret);
+		dev_err(&led->client->dev, "Failed to get enable gpio: %d\n",
+			ret);
 		return ret;
 	}
 
-	led->regulator = devm_regulator_get(&client->dev, "vled");
+	led->regulator = devm_regulator_get(&led->client->dev, "vled");
 	if (IS_ERR(led->regulator))
 		led->regulator = NULL;
 
-	led->client = client;
+	child = device_get_next_child_node(&led->client->dev, child);
+	if (!child) {
+		dev_err(&led->client->dev, "No LED Child node\n");
+		return -ENODEV;
+	}
+
+	fwnode_property_read_string(child, "linux,default-trigger",
+				    &led->led_dev.default_trigger);
+
+	ret = fwnode_property_read_string(child, "label", &name);
+	if (ret)
+		snprintf(led->label, sizeof(led->label),
+			"%s::", led->client->name);
+	else
+		snprintf(led->label, sizeof(led->label),
+			 "%s:%s", led->client->name, name);
+
+	ret = fwnode_property_read_u32(child, "reg", &led->led_enable);
+	if (ret) {
+		dev_err(&led->client->dev, "reg DT property missing\n");
+		return ret;
+	}
+
 	led->led_dev.name = led->label;
-	led->led_dev.brightness_set_blocking = lm3692x_brightness_set;
 
-	mutex_init(&led->lock);
+	ret = devm_led_classdev_register(&led->client->dev, &led->led_dev);
+	if (ret) {
+		dev_err(&led->client->dev, "led register err: %d\n", ret);
+		return ret;
+	}
+
+	led->led_dev.dev->of_node = to_of_node(child);
+
+	return 0;
+}
 
+static int lm3692x_probe(struct i2c_client *client,
+			const struct i2c_device_id *id)
+{
+	struct lm3692x_led *led;
+	int ret;
+
+	led = devm_kzalloc(&client->dev, sizeof(*led), GFP_KERNEL);
+	if (!led)
+		return -ENOMEM;
+
+	mutex_init(&led->lock);
+	led->client = client;
+	led->led_dev.brightness_set_blocking = lm3692x_brightness_set;
+	led->model_id = id->driver_data;
 	i2c_set_clientdata(client, led);
 
 	led->regmap = devm_regmap_init_i2c(client, &lm3692x_regmap_config);
@@ -330,15 +401,13 @@ static int lm3692x_probe(struct i2c_client *client,
 		return ret;
 	}
 
-	ret = lm3692x_init(led);
+	ret = lm3692x_probe_dt(led);
 	if (ret)
 		return ret;
 
-	ret = devm_led_classdev_register(&client->dev, &led->led_dev);
-	if (ret) {
-		dev_err(&client->dev, "led register err: %d\n", ret);
+	ret = lm3692x_init(led);
+	if (ret)
 		return ret;
-	}
 
 	return 0;
 }
@@ -348,6 +417,12 @@ static int lm3692x_remove(struct i2c_client *client)
 	struct lm3692x_led *led = i2c_get_clientdata(client);
 	int ret;
 
+	ret = regmap_update_bits(led->regmap, LM3692X_EN, LM3692X_DEVICE_EN, 0);
+	if (ret) {
+		dev_err(&led->client->dev, "Failed to disable regulator\n");
+		return ret;
+	}
+
 	if (led->enable_gpio)
 		gpiod_direction_output(led->enable_gpio, 0);
 
@@ -364,8 +439,8 @@ static int lm3692x_remove(struct i2c_client *client)
 }
 
 static const struct i2c_device_id lm3692x_id[] = {
-	{ "lm36922", 0 },
-	{ "lm36923", 1 },
+	{ "lm36922", LM36922_MODEL },
+	{ "lm36923", LM36923_MODEL },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, lm3692x_id);
diff --git a/drivers/leds/leds-lt3593.c b/drivers/leds/leds-lt3593.c
index 5ec730a31b65..de3623e0d094 100644
--- a/drivers/leds/leds-lt3593.c
+++ b/drivers/leds/leds-lt3593.c
@@ -1,32 +1,21 @@
-/*
- * LEDs driver for LT3593 controllers
- *
- * See the datasheet at http://cds.linear.com/docs/Datasheet/3593f.pdf
- *
- * Copyright (c) 2009 Daniel Mack <daniel@caiaq.de>
- *
- * Based on leds-gpio.c,
- *
- *   Copyright (C) 2007 8D Technologies inc.
- *   Raphael Assenat <raph@8d.com>
- *   Copyright (C) 2008 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2009,2018 Daniel Mack <daniel@zonque.org>
 
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/leds.h>
 #include <linux/delay.h>
 #include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/of.h>
+#include <uapi/linux/uleds.h>
 
 struct lt3593_led_data {
+	char name[LED_MAX_NAME_SIZE];
 	struct led_classdev cdev;
-	unsigned gpio;
+	struct gpio_desc *gpiod;
 };
 
 static int lt3593_led_set(struct led_classdev *led_cdev,
@@ -46,137 +35,168 @@ static int lt3593_led_set(struct led_classdev *led_cdev,
 	 */
 
 	if (value == 0) {
-		gpio_set_value_cansleep(led_dat->gpio, 0);
+		gpiod_set_value_cansleep(led_dat->gpiod, 0);
 		return 0;
 	}
 
 	pulses = 32 - (value * 32) / 255;
 
 	if (pulses == 0) {
-		gpio_set_value_cansleep(led_dat->gpio, 0);
+		gpiod_set_value_cansleep(led_dat->gpiod, 0);
 		mdelay(1);
-		gpio_set_value_cansleep(led_dat->gpio, 1);
+		gpiod_set_value_cansleep(led_dat->gpiod, 1);
 		return 0;
 	}
 
-	gpio_set_value_cansleep(led_dat->gpio, 1);
+	gpiod_set_value_cansleep(led_dat->gpiod, 1);
 
 	while (pulses--) {
-		gpio_set_value_cansleep(led_dat->gpio, 0);
+		gpiod_set_value_cansleep(led_dat->gpiod, 0);
 		udelay(1);
-		gpio_set_value_cansleep(led_dat->gpio, 1);
+		gpiod_set_value_cansleep(led_dat->gpiod, 1);
 		udelay(1);
 	}
 
 	return 0;
 }
 
-static int create_lt3593_led(const struct gpio_led *template,
-	struct lt3593_led_data *led_dat, struct device *parent)
+static struct lt3593_led_data *lt3593_led_probe_pdata(struct device *dev)
 {
+	struct gpio_led_platform_data *pdata = dev_get_platdata(dev);
+	const struct gpio_led *template = &pdata->leds[0];
+	struct lt3593_led_data *led_data;
 	int ret, state;
 
-	/* skip leds on GPIOs that aren't available */
-	if (!gpio_is_valid(template->gpio)) {
-		dev_info(parent, "%s: skipping unavailable LT3593 LED at gpio %d (%s)\n",
-				KBUILD_MODNAME, template->gpio, template->name);
-		return 0;
-	}
+	if (pdata->num_leds != 1)
+		return ERR_PTR(-EINVAL);
 
-	led_dat->cdev.name = template->name;
-	led_dat->cdev.default_trigger = template->default_trigger;
-	led_dat->gpio = template->gpio;
+	led_data = devm_kzalloc(dev, sizeof(*led_data), GFP_KERNEL);
+	if (!led_data)
+		return ERR_PTR(-ENOMEM);
 
-	led_dat->cdev.brightness_set_blocking = lt3593_led_set;
+	led_data->cdev.name = template->name;
+	led_data->cdev.default_trigger = template->default_trigger;
+	led_data->cdev.brightness_set_blocking = lt3593_led_set;
 
 	state = (template->default_state == LEDS_GPIO_DEFSTATE_ON);
-	led_dat->cdev.brightness = state ? LED_FULL : LED_OFF;
+	led_data->cdev.brightness = state ? LED_FULL : LED_OFF;
 
 	if (!template->retain_state_suspended)
-		led_dat->cdev.flags |= LED_CORE_SUSPENDRESUME;
+		led_data->cdev.flags |= LED_CORE_SUSPENDRESUME;
 
-	ret = devm_gpio_request_one(parent, template->gpio, state ?
+	ret = devm_gpio_request_one(dev, template->gpio, state ?
 				    GPIOF_OUT_INIT_HIGH : GPIOF_OUT_INIT_LOW,
 				    template->name);
 	if (ret < 0)
-		return ret;
-
-	ret = led_classdev_register(parent, &led_dat->cdev);
-	if (ret < 0)
-		return ret;
+		return ERR_PTR(ret);
 
-	dev_info(parent, "%s: registered LT3593 LED '%s' at GPIO %d\n",
-		KBUILD_MODNAME, template->name, template->gpio);
+	led_data->gpiod = gpio_to_desc(template->gpio);
+	if (!led_data->gpiod)
+		return ERR_PTR(-EPROBE_DEFER);
 
-	return 0;
-}
+	ret = devm_led_classdev_register(dev, &led_data->cdev);
+	if (ret < 0)
+		return ERR_PTR(ret);
 
-static void delete_lt3593_led(struct lt3593_led_data *led)
-{
-	if (!gpio_is_valid(led->gpio))
-		return;
+	dev_info(dev, "registered LT3593 LED '%s' at GPIO %d\n",
+		 template->name, template->gpio);
 
-	led_classdev_unregister(&led->cdev);
+	return led_data;
 }
 
 static int lt3593_led_probe(struct platform_device *pdev)
 {
-	struct gpio_led_platform_data *pdata = dev_get_platdata(&pdev->dev);
-	struct lt3593_led_data *leds_data;
-	int i, ret = 0;
+	struct device *dev = &pdev->dev;
+	struct lt3593_led_data *led_data;
+	struct fwnode_handle *child;
+	int ret, state = LEDS_GPIO_DEFSTATE_OFF;
+	enum gpiod_flags flags = GPIOD_OUT_LOW;
+	const char *tmp;
+
+	if (dev_get_platdata(dev)) {
+		led_data = lt3593_led_probe_pdata(dev);
+		if (IS_ERR(led_data))
+			return PTR_ERR(led_data);
+
+		goto out;
+	}
 
-	if (!pdata)
-		return -EBUSY;
+	if (!dev->of_node)
+		return -ENODEV;
 
-	leds_data = devm_kcalloc(&pdev->dev,
-			pdata->num_leds, sizeof(struct lt3593_led_data),
-			GFP_KERNEL);
-	if (!leds_data)
+	led_data = devm_kzalloc(dev, sizeof(*led_data), GFP_KERNEL);
+	if (!led_data)
 		return -ENOMEM;
 
-	for (i = 0; i < pdata->num_leds; i++) {
-		ret = create_lt3593_led(&pdata->leds[i], &leds_data[i],
-				      &pdev->dev);
-		if (ret < 0)
-			goto err;
+	if (device_get_child_node_count(dev) != 1) {
+		dev_err(dev, "Device must have exactly one LED sub-node.");
+		return -EINVAL;
 	}
 
-	platform_set_drvdata(pdev, leds_data);
+	led_data->gpiod = devm_gpiod_get(dev, "lltc,ctrl", 0);
+	if (IS_ERR(led_data->gpiod))
+		return PTR_ERR(led_data->gpiod);
 
-	return 0;
+	child = device_get_next_child_node(dev, NULL);
 
-err:
-	for (i = i - 1; i >= 0; i--)
-		delete_lt3593_led(&leds_data[i]);
+	ret = fwnode_property_read_string(child, "label", &tmp);
+	if (ret < 0)
+		snprintf(led_data->name, sizeof(led_data->name),
+			 "lt3593::");
+	else
+		snprintf(led_data->name, sizeof(led_data->name),
+			 "lt3593:%s", tmp);
+
+	fwnode_property_read_string(child, "linux,default-trigger",
+				    &led_data->cdev.default_trigger);
+
+	if (!fwnode_property_read_string(child, "default-state", &tmp)) {
+		if (!strcmp(tmp, "keep")) {
+			state = LEDS_GPIO_DEFSTATE_KEEP;
+			flags = GPIOD_ASIS;
+		} else if (!strcmp(tmp, "on")) {
+			state = LEDS_GPIO_DEFSTATE_ON;
+			flags = GPIOD_OUT_HIGH;
+		}
+	}
 
-	return ret;
-}
+	led_data->cdev.name = led_data->name;
+	led_data->cdev.brightness_set_blocking = lt3593_led_set;
+	led_data->cdev.brightness = state ? LED_FULL : LED_OFF;
 
-static int lt3593_led_remove(struct platform_device *pdev)
-{
-	int i;
-	struct gpio_led_platform_data *pdata = dev_get_platdata(&pdev->dev);
-	struct lt3593_led_data *leds_data;
+	ret = devm_led_classdev_register(dev, &led_data->cdev);
+	if (ret < 0) {
+		fwnode_handle_put(child);
+		return ret;
+	}
 
-	leds_data = platform_get_drvdata(pdev);
+	led_data->cdev.dev->of_node = dev->of_node;
 
-	for (i = 0; i < pdata->num_leds; i++)
-		delete_lt3593_led(&leds_data[i]);
+out:
+	platform_set_drvdata(pdev, led_data);
 
 	return 0;
 }
 
+#ifdef CONFIG_OF
+static const struct of_device_id of_lt3593_leds_match[] = {
+	{ .compatible = "lltc,lt3593", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, of_lt3593_leds_match);
+#endif
+
 static struct platform_driver lt3593_led_driver = {
 	.probe		= lt3593_led_probe,
-	.remove		= lt3593_led_remove,
 	.driver		= {
 		.name	= "leds-lt3593",
+		.of_match_table = of_match_ptr(of_lt3593_leds_match),
 	},
 };
 
 module_platform_driver(lt3593_led_driver);
 
-MODULE_AUTHOR("Daniel Mack <daniel@caiaq.de>");
+MODULE_AUTHOR("Daniel Mack <daniel@zonque.org>");
 MODULE_DESCRIPTION("LED driver for LT3593 controllers");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("platform:leds-lt3593");
diff --git a/drivers/leds/leds-max8997.c b/drivers/leds/leds-max8997.c
index 4edf74f1d6d4..8c019c28f9f5 100644
--- a/drivers/leds/leds-max8997.c
+++ b/drivers/leds/leds-max8997.c
@@ -268,7 +268,7 @@ static int max8997_led_probe(struct platform_device *pdev)
 		mode = pdata->led_pdata->mode[led->id];
 		brightness = pdata->led_pdata->brightness[led->id];
 
-		max8997_led_set_mode(led, pdata->led_pdata->mode[led->id]);
+		max8997_led_set_mode(led, mode);
 
 		if (brightness > led->cdev.max_brightness)
 			brightness = led->cdev.max_brightness;
diff --git a/drivers/leds/leds-ns2.c b/drivers/leds/leds-ns2.c
index 14fe5cd43232..a0a7dc2ef87c 100644
--- a/drivers/leds/leds-ns2.c
+++ b/drivers/leds/leds-ns2.c
@@ -42,8 +42,8 @@
 
 struct ns2_led_data {
 	struct led_classdev	cdev;
-	unsigned		cmd;
-	unsigned		slow;
+	unsigned int		cmd;
+	unsigned int		slow;
 	bool			can_sleep;
 	unsigned char		sata; /* True when SATA mode active. */
 	rwlock_t		rw_lock; /* Lock GPIOs. */
diff --git a/drivers/leds/trigger/Kconfig b/drivers/leds/trigger/Kconfig
index a2559b4fdfff..4018af769969 100644
--- a/drivers/leds/trigger/Kconfig
+++ b/drivers/leds/trigger/Kconfig
@@ -10,7 +10,6 @@ if LEDS_TRIGGERS
 
 config LEDS_TRIGGER_TIMER
 	tristate "LED Timer Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled by a programmable timer
 	  via sysfs. Some LED hardware can be programmed to start
@@ -21,7 +20,6 @@ config LEDS_TRIGGER_TIMER
 
 config LEDS_TRIGGER_ONESHOT
 	tristate "LED One-shot Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to blink in one-shot pulses with parameters
 	  controlled via sysfs.  It's useful to notify the user on
@@ -36,7 +34,6 @@ config LEDS_TRIGGER_ONESHOT
 config LEDS_TRIGGER_DISK
 	bool "LED Disk Trigger"
 	depends on IDE_GD_ATA || ATA
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled by disk activity.
 	  If unsure, say Y.
@@ -44,14 +41,12 @@ config LEDS_TRIGGER_DISK
 config LEDS_TRIGGER_MTD
 	bool "LED MTD (NAND/NOR) Trigger"
 	depends on MTD
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled by MTD activity.
 	  If unsure, say N.
 
 config LEDS_TRIGGER_HEARTBEAT
 	tristate "LED Heartbeat Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled by a CPU load average.
 	  The flash frequency is a hyperbolic function of the 1-minute
@@ -60,7 +55,6 @@ config LEDS_TRIGGER_HEARTBEAT
 
 config LEDS_TRIGGER_BACKLIGHT
 	tristate "LED backlight Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled as a backlight device: they
 	  turn off and on when the display is blanked and unblanked.
@@ -69,7 +63,6 @@ config LEDS_TRIGGER_BACKLIGHT
 
 config LEDS_TRIGGER_CPU
 	bool "LED CPU Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled by active CPUs. This shows
 	  the active CPUs across an array of LEDs so you can see which
@@ -79,7 +72,6 @@ config LEDS_TRIGGER_CPU
 
 config LEDS_TRIGGER_ACTIVITY
 	tristate "LED activity Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled by an immediate CPU usage.
 	  The flash frequency and duty cycle varies from faint flashes to
@@ -88,7 +80,6 @@ config LEDS_TRIGGER_ACTIVITY
 
 config LEDS_TRIGGER_GPIO
 	tristate "LED GPIO Trigger"
-	depends on LEDS_TRIGGERS
 	depends on GPIOLIB || COMPILE_TEST
 	help
 	  This allows LEDs to be controlled by gpio events. It's good
@@ -101,7 +92,6 @@ config LEDS_TRIGGER_GPIO
 
 config LEDS_TRIGGER_DEFAULT_ON
 	tristate "LED Default ON Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be initialised in the ON state.
 	  If unsure, say Y.
@@ -111,7 +101,6 @@ comment "iptables trigger is under Netfilter config (LED target)"
 
 config LEDS_TRIGGER_TRANSIENT
 	tristate "LED Transient Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows one time activation of a transient state on
 	  GPIO/PWM based hardware.
@@ -119,7 +108,6 @@ config LEDS_TRIGGER_TRANSIENT
 
 config LEDS_TRIGGER_CAMERA
 	tristate "LED Camera Flash/Torch Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled as a camera flash/torch device.
 	  This enables direct flash/torch on/off by the driver, kernel space.
@@ -127,7 +115,6 @@ config LEDS_TRIGGER_CAMERA
 
 config LEDS_TRIGGER_PANIC
 	bool "LED Panic Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be configured to blink on a kernel panic.
 	  Enabling this option will allow to mark certain LEDs as panic indicators,
@@ -137,7 +124,7 @@ config LEDS_TRIGGER_PANIC
 
 config LEDS_TRIGGER_NETDEV
 	tristate "LED Netdev Trigger"
-	depends on NET && LEDS_TRIGGERS
+	depends on NET
 	help
 	  This allows LEDs to be controlled by network device activity.
 	  If unsure, say Y.
diff --git a/drivers/leds/trigger/ledtrig-activity.c b/drivers/leds/trigger/ledtrig-activity.c
index 5081894082bd..bcbf41c90c30 100644
--- a/drivers/leds/trigger/ledtrig-activity.c
+++ b/drivers/leds/trigger/ledtrig-activity.c
@@ -7,8 +7,8 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
+
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/kernel_stat.h>
@@ -37,7 +37,6 @@ static void led_activity_function(struct timer_list *t)
 	struct activity_data *activity_data = from_timer(activity_data, t,
 							 timer);
 	struct led_classdev *led_cdev = activity_data->led_cdev;
-	struct timespec boot_time;
 	unsigned int target;
 	unsigned int usage;
 	int delay;
@@ -57,8 +56,6 @@ static void led_activity_function(struct timer_list *t)
 		return;
 	}
 
-	get_monotonic_boottime(&boot_time);
-
 	cpus = 0;
 	curr_used = 0;
 
@@ -76,7 +73,7 @@ static void led_activity_function(struct timer_list *t)
 	 * down to 16us, ensuring we won't overflow 32-bit computations below
 	 * even up to 3k CPUs, while keeping divides cheap on smaller systems.
 	 */
-	curr_boot = timespec_to_ns(&boot_time) * cpus;
+	curr_boot = ktime_get_boot_ns() * cpus;
 	diff_boot = (curr_boot - activity_data->last_boot) >> 16;
 	diff_used = (curr_used - activity_data->last_used) >> 16;
 	activity_data->last_boot = curr_boot;
@@ -155,8 +152,7 @@ static void led_activity_function(struct timer_list *t)
 static ssize_t led_invert_show(struct device *dev,
                                struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct activity_data *activity_data = led_cdev->trigger_data;
+	struct activity_data *activity_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", activity_data->invert);
 }
@@ -165,8 +161,7 @@ static ssize_t led_invert_store(struct device *dev,
                                 struct device_attribute *attr,
                                 const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct activity_data *activity_data = led_cdev->trigger_data;
+	struct activity_data *activity_data = led_trigger_get_drvdata(dev);
 	unsigned long state;
 	int ret;
 
@@ -181,21 +176,21 @@ static ssize_t led_invert_store(struct device *dev,
 
 static DEVICE_ATTR(invert, 0644, led_invert_show, led_invert_store);
 
-static void activity_activate(struct led_classdev *led_cdev)
+static struct attribute *activity_led_attrs[] = {
+	&dev_attr_invert.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(activity_led);
+
+static int activity_activate(struct led_classdev *led_cdev)
 {
 	struct activity_data *activity_data;
-	int rc;
 
 	activity_data = kzalloc(sizeof(*activity_data), GFP_KERNEL);
 	if (!activity_data)
-		return;
+		return -ENOMEM;
 
-	led_cdev->trigger_data = activity_data;
-	rc = device_create_file(led_cdev->dev, &dev_attr_invert);
-	if (rc) {
-		kfree(led_cdev->trigger_data);
-		return;
-	}
+	led_set_trigger_data(led_cdev, activity_data);
 
 	activity_data->led_cdev = led_cdev;
 	timer_setup(&activity_data->timer, led_activity_function, 0);
@@ -203,26 +198,24 @@ static void activity_activate(struct led_classdev *led_cdev)
 		led_cdev->blink_brightness = led_cdev->max_brightness;
 	led_activity_function(&activity_data->timer);
 	set_bit(LED_BLINK_SW, &led_cdev->work_flags);
-	led_cdev->activated = true;
+
+	return 0;
 }
 
 static void activity_deactivate(struct led_classdev *led_cdev)
 {
-	struct activity_data *activity_data = led_cdev->trigger_data;
-
-	if (led_cdev->activated) {
-		del_timer_sync(&activity_data->timer);
-		device_remove_file(led_cdev->dev, &dev_attr_invert);
-		kfree(activity_data);
-		clear_bit(LED_BLINK_SW, &led_cdev->work_flags);
-		led_cdev->activated = false;
-	}
+	struct activity_data *activity_data = led_get_trigger_data(led_cdev);
+
+	del_timer_sync(&activity_data->timer);
+	kfree(activity_data);
+	clear_bit(LED_BLINK_SW, &led_cdev->work_flags);
 }
 
 static struct led_trigger activity_led_trigger = {
 	.name       = "activity",
 	.activate   = activity_activate,
 	.deactivate = activity_deactivate,
+	.groups     = activity_led_groups,
 };
 
 static int activity_reboot_notifier(struct notifier_block *nb,
@@ -272,4 +265,4 @@ module_exit(activity_exit);
 
 MODULE_AUTHOR("Willy Tarreau <w@1wt.eu>");
 MODULE_DESCRIPTION("Activity LED trigger");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/trigger/ledtrig-backlight.c b/drivers/leds/trigger/ledtrig-backlight.c
index 1ca1f1608f76..c2b57beef718 100644
--- a/drivers/leds/trigger/ledtrig-backlight.c
+++ b/drivers/leds/trigger/ledtrig-backlight.c
@@ -64,8 +64,7 @@ static int fb_notifier_callback(struct notifier_block *p,
 static ssize_t bl_trig_invert_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct bl_trig_notifier *n = led->trigger_data;
+	struct bl_trig_notifier *n = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", n->invert);
 }
@@ -73,8 +72,8 @@ static ssize_t bl_trig_invert_show(struct device *dev,
 static ssize_t bl_trig_invert_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t num)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct bl_trig_notifier *n = led->trigger_data;
+	struct led_classdev *led = led_trigger_get_led(dev);
+	struct bl_trig_notifier *n = led_trigger_get_drvdata(dev);
 	unsigned long invert;
 	int ret;
 
@@ -97,22 +96,22 @@ static ssize_t bl_trig_invert_store(struct device *dev,
 }
 static DEVICE_ATTR(inverted, 0644, bl_trig_invert_show, bl_trig_invert_store);
 
-static void bl_trig_activate(struct led_classdev *led)
+static struct attribute *bl_trig_attrs[] = {
+	&dev_attr_inverted.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(bl_trig);
+
+static int bl_trig_activate(struct led_classdev *led)
 {
 	int ret;
 
 	struct bl_trig_notifier *n;
 
 	n = kzalloc(sizeof(struct bl_trig_notifier), GFP_KERNEL);
-	led->trigger_data = n;
-	if (!n) {
-		dev_err(led->dev, "unable to allocate backlight trigger\n");
-		return;
-	}
-
-	ret = device_create_file(led->dev, &dev_attr_inverted);
-	if (ret)
-		goto err_invert;
+	if (!n)
+		return -ENOMEM;
+	led_set_trigger_data(led, n);
 
 	n->led = led;
 	n->brightness = led->brightness;
@@ -122,46 +121,25 @@ static void bl_trig_activate(struct led_classdev *led)
 	ret = fb_register_client(&n->notifier);
 	if (ret)
 		dev_err(led->dev, "unable to register backlight trigger\n");
-	led->activated = true;
 
-	return;
-
-err_invert:
-	led->trigger_data = NULL;
-	kfree(n);
+	return 0;
 }
 
 static void bl_trig_deactivate(struct led_classdev *led)
 {
-	struct bl_trig_notifier *n =
-		(struct bl_trig_notifier *) led->trigger_data;
-
-	if (led->activated) {
-		device_remove_file(led->dev, &dev_attr_inverted);
-		fb_unregister_client(&n->notifier);
-		kfree(n);
-		led->activated = false;
-	}
+	struct bl_trig_notifier *n = led_get_trigger_data(led);
+
+	fb_unregister_client(&n->notifier);
+	kfree(n);
 }
 
 static struct led_trigger bl_led_trigger = {
 	.name		= "backlight",
 	.activate	= bl_trig_activate,
-	.deactivate	= bl_trig_deactivate
+	.deactivate	= bl_trig_deactivate,
+	.groups		= bl_trig_groups,
 };
-
-static int __init bl_trig_init(void)
-{
-	return led_trigger_register(&bl_led_trigger);
-}
-
-static void __exit bl_trig_exit(void)
-{
-	led_trigger_unregister(&bl_led_trigger);
-}
-
-module_init(bl_trig_init);
-module_exit(bl_trig_exit);
+module_led_trigger(bl_led_trigger);
 
 MODULE_AUTHOR("Rodolfo Giometti <giometti@linux.it>");
 MODULE_DESCRIPTION("Backlight emulation LED trigger");
diff --git a/drivers/leds/trigger/ledtrig-camera.c b/drivers/leds/trigger/ledtrig-camera.c
index 9bd73a8bad5c..091a09a20c58 100644
--- a/drivers/leds/trigger/ledtrig-camera.c
+++ b/drivers/leds/trigger/ledtrig-camera.c
@@ -10,7 +10,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
 
 #include <linux/module.h>
@@ -54,4 +53,4 @@ module_exit(ledtrig_camera_exit);
 
 MODULE_DESCRIPTION("LED Trigger for Camera Flash/Torch Control");
 MODULE_AUTHOR("Milo Kim");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/trigger/ledtrig-default-on.c b/drivers/leds/trigger/ledtrig-default-on.c
index ff455cb46680..7f6d9219711e 100644
--- a/drivers/leds/trigger/ledtrig-default-on.c
+++ b/drivers/leds/trigger/ledtrig-default-on.c
@@ -8,7 +8,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
 
 #include <linux/module.h>
@@ -17,29 +16,18 @@
 #include <linux/leds.h>
 #include "../leds.h"
 
-static void defon_trig_activate(struct led_classdev *led_cdev)
+static int defon_trig_activate(struct led_classdev *led_cdev)
 {
 	led_set_brightness_nosleep(led_cdev, led_cdev->max_brightness);
+	return 0;
 }
 
 static struct led_trigger defon_led_trigger = {
 	.name     = "default-on",
 	.activate = defon_trig_activate,
 };
-
-static int __init defon_trig_init(void)
-{
-	return led_trigger_register(&defon_led_trigger);
-}
-
-static void __exit defon_trig_exit(void)
-{
-	led_trigger_unregister(&defon_led_trigger);
-}
-
-module_init(defon_trig_init);
-module_exit(defon_trig_exit);
+module_led_trigger(defon_led_trigger);
 
 MODULE_AUTHOR("Nick Forbes <nick.forbes@incepta.com>");
 MODULE_DESCRIPTION("Default-ON LED trigger");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/trigger/ledtrig-gpio.c b/drivers/leds/trigger/ledtrig-gpio.c
index 8891e88d54dd..ed0db8ed825f 100644
--- a/drivers/leds/trigger/ledtrig-gpio.c
+++ b/drivers/leds/trigger/ledtrig-gpio.c
@@ -6,7 +6,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
 
 #include <linux/module.h>
@@ -29,7 +28,7 @@ struct gpio_trig_data {
 static irqreturn_t gpio_trig_irq(int irq, void *_led)
 {
 	struct led_classdev *led = _led;
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct gpio_trig_data *gpio_data = led_get_trigger_data(led);
 	int tmp;
 
 	tmp = gpio_get_value_cansleep(gpio_data->gpio);
@@ -52,8 +51,7 @@ static irqreturn_t gpio_trig_irq(int irq, void *_led)
 static ssize_t gpio_trig_brightness_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", gpio_data->desired_brightness);
 }
@@ -61,8 +59,7 @@ static ssize_t gpio_trig_brightness_show(struct device *dev,
 static ssize_t gpio_trig_brightness_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t n)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 	unsigned desired_brightness;
 	int ret;
 
@@ -82,8 +79,7 @@ static DEVICE_ATTR(desired_brightness, 0644, gpio_trig_brightness_show,
 static ssize_t gpio_trig_inverted_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", gpio_data->inverted);
 }
@@ -91,8 +87,8 @@ static ssize_t gpio_trig_inverted_show(struct device *dev,
 static ssize_t gpio_trig_inverted_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t n)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct led_classdev *led = led_trigger_get_led(dev);
+	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 	unsigned long inverted;
 	int ret;
 
@@ -116,8 +112,7 @@ static DEVICE_ATTR(inverted, 0644, gpio_trig_inverted_show,
 static ssize_t gpio_trig_gpio_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", gpio_data->gpio);
 }
@@ -125,8 +120,8 @@ static ssize_t gpio_trig_gpio_show(struct device *dev,
 static ssize_t gpio_trig_gpio_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t n)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct led_classdev *led = led_trigger_get_led(dev);
+	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 	unsigned gpio;
 	int ret;
 
@@ -163,76 +158,45 @@ static ssize_t gpio_trig_gpio_store(struct device *dev,
 }
 static DEVICE_ATTR(gpio, 0644, gpio_trig_gpio_show, gpio_trig_gpio_store);
 
-static void gpio_trig_activate(struct led_classdev *led)
+static struct attribute *gpio_trig_attrs[] = {
+	&dev_attr_desired_brightness.attr,
+	&dev_attr_inverted.attr,
+	&dev_attr_gpio.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(gpio_trig);
+
+static int gpio_trig_activate(struct led_classdev *led)
 {
 	struct gpio_trig_data *gpio_data;
-	int ret;
 
 	gpio_data = kzalloc(sizeof(*gpio_data), GFP_KERNEL);
 	if (!gpio_data)
-		return;
-
-	ret = device_create_file(led->dev, &dev_attr_gpio);
-	if (ret)
-		goto err_gpio;
-
-	ret = device_create_file(led->dev, &dev_attr_inverted);
-	if (ret)
-		goto err_inverted;
-
-	ret = device_create_file(led->dev, &dev_attr_desired_brightness);
-	if (ret)
-		goto err_brightness;
+		return -ENOMEM;
 
 	gpio_data->led = led;
-	led->trigger_data = gpio_data;
-	led->activated = true;
-
-	return;
-
-err_brightness:
-	device_remove_file(led->dev, &dev_attr_inverted);
+	led_set_trigger_data(led, gpio_data);
 
-err_inverted:
-	device_remove_file(led->dev, &dev_attr_gpio);
-
-err_gpio:
-	kfree(gpio_data);
+	return 0;
 }
 
 static void gpio_trig_deactivate(struct led_classdev *led)
 {
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct gpio_trig_data *gpio_data = led_get_trigger_data(led);
 
-	if (led->activated) {
-		device_remove_file(led->dev, &dev_attr_gpio);
-		device_remove_file(led->dev, &dev_attr_inverted);
-		device_remove_file(led->dev, &dev_attr_desired_brightness);
-		if (gpio_data->gpio != 0)
-			free_irq(gpio_to_irq(gpio_data->gpio), led);
-		kfree(gpio_data);
-		led->activated = false;
-	}
+	if (gpio_data->gpio != 0)
+		free_irq(gpio_to_irq(gpio_data->gpio), led);
+	kfree(gpio_data);
 }
 
 static struct led_trigger gpio_led_trigger = {
 	.name		= "gpio",
 	.activate	= gpio_trig_activate,
 	.deactivate	= gpio_trig_deactivate,
+	.groups		= gpio_trig_groups,
 };
-
-static int __init gpio_trig_init(void)
-{
-	return led_trigger_register(&gpio_led_trigger);
-}
-module_init(gpio_trig_init);
-
-static void __exit gpio_trig_exit(void)
-{
-	led_trigger_unregister(&gpio_led_trigger);
-}
-module_exit(gpio_trig_exit);
+module_led_trigger(gpio_led_trigger);
 
 MODULE_AUTHOR("Felipe Balbi <me@felipebalbi.com>");
 MODULE_DESCRIPTION("GPIO LED trigger");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/trigger/ledtrig-heartbeat.c b/drivers/leds/trigger/ledtrig-heartbeat.c
index f0896de410b8..7a2b12e19329 100644
--- a/drivers/leds/trigger/ledtrig-heartbeat.c
+++ b/drivers/leds/trigger/ledtrig-heartbeat.c
@@ -9,8 +9,8 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
+
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -96,8 +96,8 @@ static void led_heartbeat_function(struct timer_list *t)
 static ssize_t led_invert_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct heartbeat_trig_data *heartbeat_data = led_cdev->trigger_data;
+	struct heartbeat_trig_data *heartbeat_data =
+		led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", heartbeat_data->invert);
 }
@@ -105,8 +105,8 @@ static ssize_t led_invert_show(struct device *dev,
 static ssize_t led_invert_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct heartbeat_trig_data *heartbeat_data = led_cdev->trigger_data;
+	struct heartbeat_trig_data *heartbeat_data =
+		led_trigger_get_drvdata(dev);
 	unsigned long state;
 	int ret;
 
@@ -121,22 +121,22 @@ static ssize_t led_invert_store(struct device *dev,
 
 static DEVICE_ATTR(invert, 0644, led_invert_show, led_invert_store);
 
-static void heartbeat_trig_activate(struct led_classdev *led_cdev)
+static struct attribute *heartbeat_trig_attrs[] = {
+	&dev_attr_invert.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(heartbeat_trig);
+
+static int heartbeat_trig_activate(struct led_classdev *led_cdev)
 {
 	struct heartbeat_trig_data *heartbeat_data;
-	int rc;
 
 	heartbeat_data = kzalloc(sizeof(*heartbeat_data), GFP_KERNEL);
 	if (!heartbeat_data)
-		return;
+		return -ENOMEM;
 
-	led_cdev->trigger_data = heartbeat_data;
+	led_set_trigger_data(led_cdev, heartbeat_data);
 	heartbeat_data->led_cdev = led_cdev;
-	rc = device_create_file(led_cdev->dev, &dev_attr_invert);
-	if (rc) {
-		kfree(led_cdev->trigger_data);
-		return;
-	}
 
 	timer_setup(&heartbeat_data->timer, led_heartbeat_function, 0);
 	heartbeat_data->phase = 0;
@@ -144,26 +144,25 @@ static void heartbeat_trig_activate(struct led_classdev *led_cdev)
 		led_cdev->blink_brightness = led_cdev->max_brightness;
 	led_heartbeat_function(&heartbeat_data->timer);
 	set_bit(LED_BLINK_SW, &led_cdev->work_flags);
-	led_cdev->activated = true;
+
+	return 0;
 }
 
 static void heartbeat_trig_deactivate(struct led_classdev *led_cdev)
 {
-	struct heartbeat_trig_data *heartbeat_data = led_cdev->trigger_data;
-
-	if (led_cdev->activated) {
-		del_timer_sync(&heartbeat_data->timer);
-		device_remove_file(led_cdev->dev, &dev_attr_invert);
-		kfree(heartbeat_data);
-		clear_bit(LED_BLINK_SW, &led_cdev->work_flags);
-		led_cdev->activated = false;
-	}
+	struct heartbeat_trig_data *heartbeat_data =
+		led_get_trigger_data(led_cdev);
+
+	del_timer_sync(&heartbeat_data->timer);
+	kfree(heartbeat_data);
+	clear_bit(LED_BLINK_SW, &led_cdev->work_flags);
 }
 
 static struct led_trigger heartbeat_led_trigger = {
 	.name     = "heartbeat",
 	.activate = heartbeat_trig_activate,
 	.deactivate = heartbeat_trig_deactivate,
+	.groups = heartbeat_trig_groups,
 };
 
 static int heartbeat_reboot_notifier(struct notifier_block *nb,
@@ -213,4 +212,4 @@ module_exit(heartbeat_trig_exit);
 
 MODULE_AUTHOR("Atsushi Nemoto <anemo@mba.ocn.ne.jp>");
 MODULE_DESCRIPTION("Heartbeat LED trigger");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c
index 6df4781a6308..3dd3ed46d473 100644
--- a/drivers/leds/trigger/ledtrig-netdev.c
+++ b/drivers/leds/trigger/ledtrig-netdev.c
@@ -94,8 +94,7 @@ static void set_baseline_state(struct led_netdev_data *trigger_data)
 static ssize_t device_name_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
 	ssize_t len;
 
 	spin_lock_bh(&trigger_data->lock);
@@ -109,8 +108,7 @@ static ssize_t device_name_store(struct device *dev,
 				 struct device_attribute *attr, const char *buf,
 				 size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
 
 	if (size >= IFNAMSIZ)
 		return -EINVAL;
@@ -150,8 +148,7 @@ static DEVICE_ATTR_RW(device_name);
 static ssize_t netdev_led_attr_show(struct device *dev, char *buf,
 	enum netdev_led_attr attr)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
 	int bit;
 
 	switch (attr) {
@@ -174,8 +171,7 @@ static ssize_t netdev_led_attr_show(struct device *dev, char *buf,
 static ssize_t netdev_led_attr_store(struct device *dev, const char *buf,
 	size_t size, enum netdev_led_attr attr)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
 	unsigned long state;
 	int ret;
 	int bit;
@@ -255,8 +251,7 @@ static DEVICE_ATTR_RW(rx);
 static ssize_t interval_show(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n",
 		       jiffies_to_msecs(atomic_read(&trigger_data->interval)));
@@ -266,8 +261,7 @@ static ssize_t interval_store(struct device *dev,
 			      struct device_attribute *attr, const char *buf,
 			      size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
 	unsigned long value;
 	int ret;
 
@@ -288,15 +282,23 @@ static ssize_t interval_store(struct device *dev,
 
 static DEVICE_ATTR_RW(interval);
 
+static struct attribute *netdev_trig_attrs[] = {
+	&dev_attr_device_name.attr,
+	&dev_attr_link.attr,
+	&dev_attr_rx.attr,
+	&dev_attr_tx.attr,
+	&dev_attr_interval.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(netdev_trig);
+
 static int netdev_trig_notify(struct notifier_block *nb,
 			      unsigned long evt, void *dv)
 {
 	struct net_device *dev =
 		netdev_notifier_info_to_dev((struct netdev_notifier_info *)dv);
-	struct led_netdev_data *trigger_data = container_of(nb,
-							    struct
-							    led_netdev_data,
-							    notifier);
+	struct led_netdev_data *trigger_data =
+		container_of(nb, struct led_netdev_data, notifier);
 
 	if (evt != NETDEV_UP && evt != NETDEV_DOWN && evt != NETDEV_CHANGE
 	    && evt != NETDEV_REGISTER && evt != NETDEV_UNREGISTER
@@ -342,10 +344,8 @@ static int netdev_trig_notify(struct notifier_block *nb,
 /* here's the real work! */
 static void netdev_trig_work(struct work_struct *work)
 {
-	struct led_netdev_data *trigger_data = container_of(work,
-							    struct
-							    led_netdev_data,
-							    work.work);
+	struct led_netdev_data *trigger_data =
+		container_of(work, struct led_netdev_data, work.work);
 	struct rtnl_link_stats64 *dev_stats;
 	unsigned int new_activity;
 	struct rtnl_link_stats64 temp;
@@ -388,14 +388,14 @@ static void netdev_trig_work(struct work_struct *work)
 			(atomic_read(&trigger_data->interval)*2));
 }
 
-static void netdev_trig_activate(struct led_classdev *led_cdev)
+static int netdev_trig_activate(struct led_classdev *led_cdev)
 {
 	struct led_netdev_data *trigger_data;
 	int rc;
 
 	trigger_data = kzalloc(sizeof(struct led_netdev_data), GFP_KERNEL);
 	if (!trigger_data)
-		return;
+		return -ENOMEM;
 
 	spin_lock_init(&trigger_data->lock);
 
@@ -412,69 +412,34 @@ static void netdev_trig_activate(struct led_classdev *led_cdev)
 	atomic_set(&trigger_data->interval, msecs_to_jiffies(50));
 	trigger_data->last_activity = 0;
 
-	led_cdev->trigger_data = trigger_data;
+	led_set_trigger_data(led_cdev, trigger_data);
 
-	rc = device_create_file(led_cdev->dev, &dev_attr_device_name);
-	if (rc)
-		goto err_out;
-	rc = device_create_file(led_cdev->dev, &dev_attr_link);
-	if (rc)
-		goto err_out_device_name;
-	rc = device_create_file(led_cdev->dev, &dev_attr_rx);
-	if (rc)
-		goto err_out_link;
-	rc = device_create_file(led_cdev->dev, &dev_attr_tx);
-	if (rc)
-		goto err_out_rx;
-	rc = device_create_file(led_cdev->dev, &dev_attr_interval);
-	if (rc)
-		goto err_out_tx;
 	rc = register_netdevice_notifier(&trigger_data->notifier);
 	if (rc)
-		goto err_out_interval;
-	return;
-
-err_out_interval:
-	device_remove_file(led_cdev->dev, &dev_attr_interval);
-err_out_tx:
-	device_remove_file(led_cdev->dev, &dev_attr_tx);
-err_out_rx:
-	device_remove_file(led_cdev->dev, &dev_attr_rx);
-err_out_link:
-	device_remove_file(led_cdev->dev, &dev_attr_link);
-err_out_device_name:
-	device_remove_file(led_cdev->dev, &dev_attr_device_name);
-err_out:
-	led_cdev->trigger_data = NULL;
-	kfree(trigger_data);
+		kfree(trigger_data);
+
+	return rc;
 }
 
 static void netdev_trig_deactivate(struct led_classdev *led_cdev)
 {
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
-
-	if (trigger_data) {
-		unregister_netdevice_notifier(&trigger_data->notifier);
+	struct led_netdev_data *trigger_data = led_get_trigger_data(led_cdev);
 
-		device_remove_file(led_cdev->dev, &dev_attr_device_name);
-		device_remove_file(led_cdev->dev, &dev_attr_link);
-		device_remove_file(led_cdev->dev, &dev_attr_rx);
-		device_remove_file(led_cdev->dev, &dev_attr_tx);
-		device_remove_file(led_cdev->dev, &dev_attr_interval);
+	unregister_netdevice_notifier(&trigger_data->notifier);
 
-		cancel_delayed_work_sync(&trigger_data->work);
+	cancel_delayed_work_sync(&trigger_data->work);
 
-		if (trigger_data->net_dev)
-			dev_put(trigger_data->net_dev);
+	if (trigger_data->net_dev)
+		dev_put(trigger_data->net_dev);
 
-		kfree(trigger_data);
-	}
+	kfree(trigger_data);
 }
 
 static struct led_trigger netdev_led_trigger = {
 	.name = "netdev",
 	.activate = netdev_trig_activate,
 	.deactivate = netdev_trig_deactivate,
+	.groups = netdev_trig_groups,
 };
 
 static int __init netdev_trig_init(void)
diff --git a/drivers/leds/trigger/ledtrig-oneshot.c b/drivers/leds/trigger/ledtrig-oneshot.c
index b8ea9f0f1e19..95c9be4b6e7e 100644
--- a/drivers/leds/trigger/ledtrig-oneshot.c
+++ b/drivers/leds/trigger/ledtrig-oneshot.c
@@ -8,7 +8,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
 
 #include <linux/module.h>
@@ -29,8 +28,8 @@ struct oneshot_trig_data {
 static ssize_t led_shot(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct oneshot_trig_data *oneshot_data = led_cdev->trigger_data;
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
+	struct oneshot_trig_data *oneshot_data = led_trigger_get_drvdata(dev);
 
 	led_blink_set_oneshot(led_cdev,
 			&led_cdev->blink_delay_on, &led_cdev->blink_delay_off,
@@ -42,8 +41,7 @@ static ssize_t led_shot(struct device *dev,
 static ssize_t led_invert_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct oneshot_trig_data *oneshot_data = led_cdev->trigger_data;
+	struct oneshot_trig_data *oneshot_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", oneshot_data->invert);
 }
@@ -51,8 +49,8 @@ static ssize_t led_invert_show(struct device *dev,
 static ssize_t led_invert_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct oneshot_trig_data *oneshot_data = led_cdev->trigger_data;
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
+	struct oneshot_trig_data *oneshot_data = led_trigger_get_drvdata(dev);
 	unsigned long state;
 	int ret;
 
@@ -73,7 +71,7 @@ static ssize_t led_invert_store(struct device *dev,
 static ssize_t led_delay_on_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 
 	return sprintf(buf, "%lu\n", led_cdev->blink_delay_on);
 }
@@ -81,7 +79,7 @@ static ssize_t led_delay_on_show(struct device *dev,
 static ssize_t led_delay_on_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 	unsigned long state;
 	int ret;
 
@@ -93,10 +91,11 @@ static ssize_t led_delay_on_store(struct device *dev,
 
 	return size;
 }
+
 static ssize_t led_delay_off_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 
 	return sprintf(buf, "%lu\n", led_cdev->blink_delay_off);
 }
@@ -104,7 +103,7 @@ static ssize_t led_delay_off_show(struct device *dev,
 static ssize_t led_delay_off_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 	unsigned long state;
 	int ret;
 
@@ -122,59 +121,36 @@ static DEVICE_ATTR(delay_off, 0644, led_delay_off_show, led_delay_off_store);
 static DEVICE_ATTR(invert, 0644, led_invert_show, led_invert_store);
 static DEVICE_ATTR(shot, 0200, NULL, led_shot);
 
-static void oneshot_trig_activate(struct led_classdev *led_cdev)
+static struct attribute *oneshot_trig_attrs[] = {
+	&dev_attr_delay_on.attr,
+	&dev_attr_delay_off.attr,
+	&dev_attr_invert.attr,
+	&dev_attr_shot.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(oneshot_trig);
+
+static int oneshot_trig_activate(struct led_classdev *led_cdev)
 {
 	struct oneshot_trig_data *oneshot_data;
-	int rc;
 
 	oneshot_data = kzalloc(sizeof(*oneshot_data), GFP_KERNEL);
 	if (!oneshot_data)
-		return;
-
-	led_cdev->trigger_data = oneshot_data;
-
-	rc = device_create_file(led_cdev->dev, &dev_attr_delay_on);
-	if (rc)
-		goto err_out_trig_data;
-	rc = device_create_file(led_cdev->dev, &dev_attr_delay_off);
-	if (rc)
-		goto err_out_delayon;
-	rc = device_create_file(led_cdev->dev, &dev_attr_invert);
-	if (rc)
-		goto err_out_delayoff;
-	rc = device_create_file(led_cdev->dev, &dev_attr_shot);
-	if (rc)
-		goto err_out_invert;
+		return -ENOMEM;
+
+	led_set_trigger_data(led_cdev, oneshot_data);
 
 	led_cdev->blink_delay_on = DEFAULT_DELAY;
 	led_cdev->blink_delay_off = DEFAULT_DELAY;
 
-	led_cdev->activated = true;
-
-	return;
-
-err_out_invert:
-	device_remove_file(led_cdev->dev, &dev_attr_invert);
-err_out_delayoff:
-	device_remove_file(led_cdev->dev, &dev_attr_delay_off);
-err_out_delayon:
-	device_remove_file(led_cdev->dev, &dev_attr_delay_on);
-err_out_trig_data:
-	kfree(led_cdev->trigger_data);
+	return 0;
 }
 
 static void oneshot_trig_deactivate(struct led_classdev *led_cdev)
 {
-	struct oneshot_trig_data *oneshot_data = led_cdev->trigger_data;
+	struct oneshot_trig_data *oneshot_data = led_get_trigger_data(led_cdev);
 
-	if (led_cdev->activated) {
-		device_remove_file(led_cdev->dev, &dev_attr_delay_on);
-		device_remove_file(led_cdev->dev, &dev_attr_delay_off);
-		device_remove_file(led_cdev->dev, &dev_attr_invert);
-		device_remove_file(led_cdev->dev, &dev_attr_shot);
-		kfree(oneshot_data);
-		led_cdev->activated = false;
-	}
+	kfree(oneshot_data);
 
 	/* Stop blinking */
 	led_set_brightness(led_cdev, LED_OFF);
@@ -184,20 +160,9 @@ static struct led_trigger oneshot_led_trigger = {
 	.name     = "oneshot",
 	.activate = oneshot_trig_activate,
 	.deactivate = oneshot_trig_deactivate,
+	.groups = oneshot_trig_groups,
 };
-
-static int __init oneshot_trig_init(void)
-{
-	return led_trigger_register(&oneshot_led_trigger);
-}
-
-static void __exit oneshot_trig_exit(void)
-{
-	led_trigger_unregister(&oneshot_led_trigger);
-}
-
-module_init(oneshot_trig_init);
-module_exit(oneshot_trig_exit);
+module_led_trigger(oneshot_led_trigger);
 
 MODULE_AUTHOR("Fabio Baltieri <fabio.baltieri@gmail.com>");
 MODULE_DESCRIPTION("One-shot LED trigger");
diff --git a/drivers/leds/trigger/ledtrig-timer.c b/drivers/leds/trigger/ledtrig-timer.c
index 8d09327b5719..7c14983781ee 100644
--- a/drivers/leds/trigger/ledtrig-timer.c
+++ b/drivers/leds/trigger/ledtrig-timer.c
@@ -8,7 +8,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
 
 #include <linux/module.h>
@@ -21,7 +20,7 @@
 static ssize_t led_delay_on_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 
 	return sprintf(buf, "%lu\n", led_cdev->blink_delay_on);
 }
@@ -29,7 +28,7 @@ static ssize_t led_delay_on_show(struct device *dev,
 static ssize_t led_delay_on_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 	unsigned long state;
 	ssize_t ret = -EINVAL;
 
@@ -46,7 +45,7 @@ static ssize_t led_delay_on_store(struct device *dev,
 static ssize_t led_delay_off_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 
 	return sprintf(buf, "%lu\n", led_cdev->blink_delay_off);
 }
@@ -54,7 +53,7 @@ static ssize_t led_delay_off_show(struct device *dev,
 static ssize_t led_delay_off_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 	unsigned long state;
 	ssize_t ret = -EINVAL;
 
@@ -71,37 +70,23 @@ static ssize_t led_delay_off_store(struct device *dev,
 static DEVICE_ATTR(delay_on, 0644, led_delay_on_show, led_delay_on_store);
 static DEVICE_ATTR(delay_off, 0644, led_delay_off_show, led_delay_off_store);
 
-static void timer_trig_activate(struct led_classdev *led_cdev)
-{
-	int rc;
-
-	led_cdev->trigger_data = NULL;
-
-	rc = device_create_file(led_cdev->dev, &dev_attr_delay_on);
-	if (rc)
-		return;
-	rc = device_create_file(led_cdev->dev, &dev_attr_delay_off);
-	if (rc)
-		goto err_out_delayon;
+static struct attribute *timer_trig_attrs[] = {
+	&dev_attr_delay_on.attr,
+	&dev_attr_delay_off.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(timer_trig);
 
+static int timer_trig_activate(struct led_classdev *led_cdev)
+{
 	led_blink_set(led_cdev, &led_cdev->blink_delay_on,
 		      &led_cdev->blink_delay_off);
-	led_cdev->activated = true;
 
-	return;
-
-err_out_delayon:
-	device_remove_file(led_cdev->dev, &dev_attr_delay_on);
+	return 0;
 }
 
 static void timer_trig_deactivate(struct led_classdev *led_cdev)
 {
-	if (led_cdev->activated) {
-		device_remove_file(led_cdev->dev, &dev_attr_delay_on);
-		device_remove_file(led_cdev->dev, &dev_attr_delay_off);
-		led_cdev->activated = false;
-	}
-
 	/* Stop blinking */
 	led_set_brightness(led_cdev, LED_OFF);
 }
@@ -110,21 +95,10 @@ static struct led_trigger timer_led_trigger = {
 	.name     = "timer",
 	.activate = timer_trig_activate,
 	.deactivate = timer_trig_deactivate,
+	.groups = timer_trig_groups,
 };
-
-static int __init timer_trig_init(void)
-{
-	return led_trigger_register(&timer_led_trigger);
-}
-
-static void __exit timer_trig_exit(void)
-{
-	led_trigger_unregister(&timer_led_trigger);
-}
-
-module_init(timer_trig_init);
-module_exit(timer_trig_exit);
+module_led_trigger(timer_led_trigger);
 
 MODULE_AUTHOR("Richard Purdie <rpurdie@openedhand.com>");
 MODULE_DESCRIPTION("Timer LED trigger");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/trigger/ledtrig-transient.c b/drivers/leds/trigger/ledtrig-transient.c
index 9d1769073562..a80bb82aacc2 100644
--- a/drivers/leds/trigger/ledtrig-transient.c
+++ b/drivers/leds/trigger/ledtrig-transient.c
@@ -42,8 +42,8 @@ static void transient_timer_function(struct timer_list *t)
 static ssize_t transient_activate_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%d\n", transient_data->activate);
 }
@@ -51,8 +51,9 @@ static ssize_t transient_activate_show(struct device *dev,
 static ssize_t transient_activate_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
 	unsigned long state;
 	ssize_t ret;
 
@@ -94,8 +95,7 @@ static ssize_t transient_activate_store(struct device *dev,
 static ssize_t transient_duration_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct transient_trig_data *transient_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%lu\n", transient_data->duration);
 }
@@ -103,8 +103,8 @@ static ssize_t transient_duration_show(struct device *dev,
 static ssize_t transient_duration_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
 	unsigned long state;
 	ssize_t ret;
 
@@ -119,8 +119,8 @@ static ssize_t transient_duration_store(struct device *dev,
 static ssize_t transient_state_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
 	int state;
 
 	state = (transient_data->state == LED_FULL) ? 1 : 0;
@@ -130,8 +130,8 @@ static ssize_t transient_state_show(struct device *dev,
 static ssize_t transient_state_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
 	unsigned long state;
 	ssize_t ret;
 
@@ -152,82 +152,46 @@ static DEVICE_ATTR(duration, 0644, transient_duration_show,
 		   transient_duration_store);
 static DEVICE_ATTR(state, 0644, transient_state_show, transient_state_store);
 
-static void transient_trig_activate(struct led_classdev *led_cdev)
+static struct attribute *transient_trig_attrs[] = {
+	&dev_attr_activate.attr,
+	&dev_attr_duration.attr,
+	&dev_attr_state.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(transient_trig);
+
+static int transient_trig_activate(struct led_classdev *led_cdev)
 {
-	int rc;
 	struct transient_trig_data *tdata;
 
 	tdata = kzalloc(sizeof(struct transient_trig_data), GFP_KERNEL);
-	if (!tdata) {
-		dev_err(led_cdev->dev,
-			"unable to allocate transient trigger\n");
-		return;
-	}
-	led_cdev->trigger_data = tdata;
-	tdata->led_cdev = led_cdev;
+	if (!tdata)
+		return -ENOMEM;
 
-	rc = device_create_file(led_cdev->dev, &dev_attr_activate);
-	if (rc)
-		goto err_out;
-
-	rc = device_create_file(led_cdev->dev, &dev_attr_duration);
-	if (rc)
-		goto err_out_duration;
-
-	rc = device_create_file(led_cdev->dev, &dev_attr_state);
-	if (rc)
-		goto err_out_state;
+	led_set_trigger_data(led_cdev, tdata);
+	tdata->led_cdev = led_cdev;
 
 	timer_setup(&tdata->timer, transient_timer_function, 0);
-	led_cdev->activated = true;
-
-	return;
-
-err_out_state:
-	device_remove_file(led_cdev->dev, &dev_attr_duration);
-err_out_duration:
-	device_remove_file(led_cdev->dev, &dev_attr_activate);
-err_out:
-	dev_err(led_cdev->dev, "unable to register transient trigger\n");
-	led_cdev->trigger_data = NULL;
-	kfree(tdata);
+
+	return 0;
 }
 
 static void transient_trig_deactivate(struct led_classdev *led_cdev)
 {
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct transient_trig_data *transient_data = led_get_trigger_data(led_cdev);
 
-	if (led_cdev->activated) {
-		del_timer_sync(&transient_data->timer);
-		led_set_brightness_nosleep(led_cdev,
-					transient_data->restore_state);
-		device_remove_file(led_cdev->dev, &dev_attr_activate);
-		device_remove_file(led_cdev->dev, &dev_attr_duration);
-		device_remove_file(led_cdev->dev, &dev_attr_state);
-		led_cdev->trigger_data = NULL;
-		led_cdev->activated = false;
-		kfree(transient_data);
-	}
+	del_timer_sync(&transient_data->timer);
+	led_set_brightness_nosleep(led_cdev, transient_data->restore_state);
+	kfree(transient_data);
 }
 
 static struct led_trigger transient_trigger = {
 	.name     = "transient",
 	.activate = transient_trig_activate,
 	.deactivate = transient_trig_deactivate,
+	.groups = transient_trig_groups,
 };
-
-static int __init transient_trig_init(void)
-{
-	return led_trigger_register(&transient_trigger);
-}
-
-static void __exit transient_trig_exit(void)
-{
-	led_trigger_unregister(&transient_trigger);
-}
-
-module_init(transient_trig_init);
-module_exit(transient_trig_exit);
+module_led_trigger(transient_trigger);
 
 MODULE_AUTHOR("Shuah Khan <shuahkhan@gmail.com>");
 MODULE_DESCRIPTION("Transient LED trigger");
diff --git a/drivers/lightnvm/Kconfig b/drivers/lightnvm/Kconfig
index 9c03f35d9df1..439bf90d084d 100644
--- a/drivers/lightnvm/Kconfig
+++ b/drivers/lightnvm/Kconfig
@@ -17,23 +17,25 @@ menuconfig NVM
 
 if NVM
 
-config NVM_DEBUG
-	bool "Open-Channel SSD debugging support"
-	default n
-	---help---
-	Exposes a debug management interface to create/remove targets at:
+config NVM_PBLK
+	tristate "Physical Block Device Open-Channel SSD target"
+	help
+	  Allows an open-channel SSD to be exposed as a block device to the
+	  host. The target assumes the device exposes raw flash and must be
+	  explicitly managed by the host.
 
-	  /sys/module/lnvm/parameters/configure_debug
+	  Please note the disk format is considered EXPERIMENTAL for now.
 
-	It is required to create/remove targets without IOCTLs.
+if NVM_PBLK
 
-config NVM_PBLK
-	tristate "Physical Block Device Open-Channel SSD target"
-	---help---
-	Allows an open-channel SSD to be exposed as a block device to the
-	host. The target assumes the device exposes raw flash and must be
-	explicitly managed by the host.
+config NVM_PBLK_DEBUG
+	bool "PBlk Debug Support"
+	default n
+	help
+	  Enables debug support for pblk. This includes extra checks, more
+	  vocal error messages, and extra tracking fields in the pblk sysfs
+	  entries.
 
-	Please note the disk format is considered EXPERIMENTAL for now.
+endif # NVM_PBLK_DEBUG
 
 endif # NVM
diff --git a/drivers/lightnvm/pblk-cache.c b/drivers/lightnvm/pblk-cache.c
index b1c6d7eb6115..f565a56b898a 100644
--- a/drivers/lightnvm/pblk-cache.c
+++ b/drivers/lightnvm/pblk-cache.c
@@ -27,7 +27,8 @@ int pblk_write_to_cache(struct pblk *pblk, struct bio *bio, unsigned long flags)
 	int nr_entries = pblk_get_secs(bio);
 	int i, ret;
 
-	generic_start_io_acct(q, WRITE, bio_sectors(bio), &pblk->disk->part0);
+	generic_start_io_acct(q, REQ_OP_WRITE, bio_sectors(bio),
+			      &pblk->disk->part0);
 
 	/* Update the write buffer head (mem) with the entries that we can
 	 * write. The write in itself cannot fail, so there is no need to
@@ -67,7 +68,7 @@ retry:
 
 	atomic64_add(nr_entries, &pblk->user_wa);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(nr_entries, &pblk->inflight_writes);
 	atomic_long_add(nr_entries, &pblk->req_writes);
 #endif
@@ -75,7 +76,7 @@ retry:
 	pblk_rl_inserted(&pblk->rl, nr_entries);
 
 out:
-	generic_end_io_acct(q, WRITE, &pblk->disk->part0, start_time);
+	generic_end_io_acct(q, REQ_OP_WRITE, &pblk->disk->part0, start_time);
 	pblk_write_should_kick(pblk);
 	return ret;
 }
@@ -123,7 +124,7 @@ retry:
 
 	atomic64_add(valid_entries, &pblk->gc_wa);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(valid_entries, &pblk->inflight_writes);
 	atomic_long_add(valid_entries, &pblk->recov_gc_writes);
 #endif
diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index ed9cc977c8b3..00984b486fea 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -35,7 +35,7 @@ static void pblk_line_mark_bb(struct work_struct *work)
 		line = &pblk->lines[pblk_ppa_to_line(*ppa)];
 		pos = pblk_ppa_to_pos(&dev->geo, *ppa);
 
-		pr_err("pblk: failed to mark bb, line:%d, pos:%d\n",
+		pblk_err(pblk, "failed to mark bb, line:%d, pos:%d\n",
 				line->id, pos);
 	}
 
@@ -51,12 +51,12 @@ static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
 	struct ppa_addr *ppa;
 	int pos = pblk_ppa_to_pos(geo, ppa_addr);
 
-	pr_debug("pblk: erase failed: line:%d, pos:%d\n", line->id, pos);
+	pblk_debug(pblk, "erase failed: line:%d, pos:%d\n", line->id, pos);
 	atomic_long_inc(&pblk->erase_failed);
 
 	atomic_dec(&line->blk_in_line);
 	if (test_and_set_bit(pos, line->blk_bitmap))
-		pr_err("pblk: attempted to erase bb: line:%d, pos:%d\n",
+		pblk_err(pblk, "attempted to erase bb: line:%d, pos:%d\n",
 							line->id, pos);
 
 	/* Not necessary to mark bad blocks on 2.0 spec. */
@@ -194,7 +194,7 @@ void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa)
 	u64 paddr;
 	int line_id;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a device address */
 	BUG_ON(pblk_addr_in_cache(ppa));
 	BUG_ON(pblk_ppa_empty(ppa));
@@ -264,6 +264,7 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type)
 	switch (type) {
 	case PBLK_WRITE:
 		kfree(((struct pblk_c_ctx *)nvm_rq_to_pdu(rqd))->lun_bitmap);
+		/* fall through */
 	case PBLK_WRITE_INT:
 		pool = &pblk->w_rq_pool;
 		break;
@@ -274,7 +275,7 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type)
 		pool = &pblk->e_rq_pool;
 		break;
 	default:
-		pr_err("pblk: trying to free unknown rqd type\n");
+		pblk_err(pblk, "trying to free unknown rqd type\n");
 		return;
 	}
 
@@ -310,7 +311,7 @@ int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags,
 
 		ret = bio_add_pc_page(q, bio, page, PBLK_EXPOSED_PAGE_SIZE, 0);
 		if (ret != PBLK_EXPOSED_PAGE_SIZE) {
-			pr_err("pblk: could not add page to bio\n");
+			pblk_err(pblk, "could not add page to bio\n");
 			mempool_free(page, &pblk->page_bio_pool);
 			goto err;
 		}
@@ -410,7 +411,7 @@ struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line)
 		line->state = PBLK_LINESTATE_CORRUPT;
 		line->gc_group = PBLK_LINEGC_NONE;
 		move_list =  &l_mg->corrupt_list;
-		pr_err("pblk: corrupted vsc for line %d, vsc:%d (%d/%d/%d)\n",
+		pblk_err(pblk, "corrupted vsc for line %d, vsc:%d (%d/%d/%d)\n",
 						line->id, vsc,
 						line->sec_in_line,
 						lm->high_thrs, lm->mid_thrs);
@@ -430,7 +431,7 @@ void pblk_discard(struct pblk *pblk, struct bio *bio)
 void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd)
 {
 	atomic_long_inc(&pblk->write_failed);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	pblk_print_failed_rqd(pblk, rqd, rqd->error);
 #endif
 }
@@ -452,9 +453,9 @@ void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd)
 		atomic_long_inc(&pblk->read_failed);
 		break;
 	default:
-		pr_err("pblk: unknown read error:%d\n", rqd->error);
+		pblk_err(pblk, "unknown read error:%d\n", rqd->error);
 	}
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	pblk_print_failed_rqd(pblk, rqd, rqd->error);
 #endif
 }
@@ -470,7 +471,7 @@ int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd)
 
 	atomic_inc(&pblk->inflight_io);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	if (pblk_check_io(pblk, rqd))
 		return NVM_IO_ERR;
 #endif
@@ -484,7 +485,7 @@ int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd)
 
 	atomic_inc(&pblk->inflight_io);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	if (pblk_check_io(pblk, rqd))
 		return NVM_IO_ERR;
 #endif
@@ -517,7 +518,7 @@ struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
 	for (i = 0; i < nr_secs; i++) {
 		page = vmalloc_to_page(kaddr);
 		if (!page) {
-			pr_err("pblk: could not map vmalloc bio\n");
+			pblk_err(pblk, "could not map vmalloc bio\n");
 			bio_put(bio);
 			bio = ERR_PTR(-ENOMEM);
 			goto out;
@@ -525,7 +526,7 @@ struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
 
 		ret = bio_add_pc_page(dev->q, bio, page, PAGE_SIZE, 0);
 		if (ret != PAGE_SIZE) {
-			pr_err("pblk: could not add page to bio\n");
+			pblk_err(pblk, "could not add page to bio\n");
 			bio_put(bio);
 			bio = ERR_PTR(-ENOMEM);
 			goto out;
@@ -711,7 +712,7 @@ next_rq:
 			while (test_bit(pos, line->blk_bitmap)) {
 				paddr += min;
 				if (pblk_boundary_paddr_checks(pblk, paddr)) {
-					pr_err("pblk: corrupt emeta line:%d\n",
+					pblk_err(pblk, "corrupt emeta line:%d\n",
 								line->id);
 					bio_put(bio);
 					ret = -EINTR;
@@ -723,7 +724,7 @@ next_rq:
 			}
 
 			if (pblk_boundary_paddr_checks(pblk, paddr + min)) {
-				pr_err("pblk: corrupt emeta line:%d\n",
+				pblk_err(pblk, "corrupt emeta line:%d\n",
 								line->id);
 				bio_put(bio);
 				ret = -EINTR;
@@ -738,7 +739,7 @@ next_rq:
 
 	ret = pblk_submit_io_sync(pblk, &rqd);
 	if (ret) {
-		pr_err("pblk: emeta I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "emeta I/O submission failed: %d\n", ret);
 		bio_put(bio);
 		goto free_rqd_dma;
 	}
@@ -843,7 +844,7 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
 	 */
 	ret = pblk_submit_io_sync(pblk, &rqd);
 	if (ret) {
-		pr_err("pblk: smeta I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "smeta I/O submission failed: %d\n", ret);
 		bio_put(bio);
 		goto free_ppa_list;
 	}
@@ -905,7 +906,7 @@ static int pblk_blk_erase_sync(struct pblk *pblk, struct ppa_addr ppa)
 		struct nvm_tgt_dev *dev = pblk->dev;
 		struct nvm_geo *geo = &dev->geo;
 
-		pr_err("pblk: could not sync erase line:%d,blk:%d\n",
+		pblk_err(pblk, "could not sync erase line:%d,blk:%d\n",
 					pblk_ppa_to_line(ppa),
 					pblk_ppa_to_pos(geo, ppa));
 
@@ -945,7 +946,7 @@ int pblk_line_erase(struct pblk *pblk, struct pblk_line *line)
 
 		ret = pblk_blk_erase_sync(pblk, ppa);
 		if (ret) {
-			pr_err("pblk: failed to erase line %d\n", line->id);
+			pblk_err(pblk, "failed to erase line %d\n", line->id);
 			return ret;
 		}
 	} while (1);
@@ -1012,7 +1013,7 @@ static int pblk_line_init_metadata(struct pblk *pblk, struct pblk_line *line,
 		list_add_tail(&line->list, &l_mg->bad_list);
 		spin_unlock(&l_mg->free_lock);
 
-		pr_debug("pblk: line %d is bad\n", line->id);
+		pblk_debug(pblk, "line %d is bad\n", line->id);
 
 		return 0;
 	}
@@ -1122,7 +1123,7 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line,
 	line->cur_sec = off + lm->smeta_sec;
 
 	if (init && pblk_line_submit_smeta_io(pblk, line, off, PBLK_WRITE)) {
-		pr_debug("pblk: line smeta I/O failed. Retry\n");
+		pblk_debug(pblk, "line smeta I/O failed. Retry\n");
 		return 0;
 	}
 
@@ -1154,7 +1155,7 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line,
 		spin_unlock(&line->lock);
 
 		list_add_tail(&line->list, &l_mg->bad_list);
-		pr_err("pblk: unexpected line %d is bad\n", line->id);
+		pblk_err(pblk, "unexpected line %d is bad\n", line->id);
 
 		return 0;
 	}
@@ -1299,7 +1300,7 @@ struct pblk_line *pblk_line_get(struct pblk *pblk)
 
 retry:
 	if (list_empty(&l_mg->free_list)) {
-		pr_err("pblk: no free lines\n");
+		pblk_err(pblk, "no free lines\n");
 		return NULL;
 	}
 
@@ -1315,7 +1316,7 @@ retry:
 
 		list_add_tail(&line->list, &l_mg->bad_list);
 
-		pr_debug("pblk: line %d is bad\n", line->id);
+		pblk_debug(pblk, "line %d is bad\n", line->id);
 		goto retry;
 	}
 
@@ -1329,7 +1330,7 @@ retry:
 			list_add(&line->list, &l_mg->corrupt_list);
 			goto retry;
 		default:
-			pr_err("pblk: failed to prepare line %d\n", line->id);
+			pblk_err(pblk, "failed to prepare line %d\n", line->id);
 			list_add(&line->list, &l_mg->free_list);
 			l_mg->nr_free_lines++;
 			return NULL;
@@ -1477,7 +1478,7 @@ static void pblk_line_close_meta_sync(struct pblk *pblk)
 
 			ret = pblk_submit_meta_io(pblk, line);
 			if (ret) {
-				pr_err("pblk: sync meta line %d failed (%d)\n",
+				pblk_err(pblk, "sync meta line %d failed (%d)\n",
 							line->id, ret);
 				return;
 			}
@@ -1507,7 +1508,7 @@ void __pblk_pipeline_flush(struct pblk *pblk)
 
 	ret = pblk_recov_pad(pblk);
 	if (ret) {
-		pr_err("pblk: could not close data on teardown(%d)\n", ret);
+		pblk_err(pblk, "could not close data on teardown(%d)\n", ret);
 		return;
 	}
 
@@ -1687,7 +1688,7 @@ int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr ppa)
 		struct nvm_tgt_dev *dev = pblk->dev;
 		struct nvm_geo *geo = &dev->geo;
 
-		pr_err("pblk: could not async erase line:%d,blk:%d\n",
+		pblk_err(pblk, "could not async erase line:%d,blk:%d\n",
 					pblk_ppa_to_line(ppa),
 					pblk_ppa_to_pos(geo, ppa));
 	}
@@ -1726,7 +1727,7 @@ void pblk_line_close(struct pblk *pblk, struct pblk_line *line)
 	struct list_head *move_list;
 	int i;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	WARN(!bitmap_full(line->map_bitmap, lm->sec_per_line),
 				"pblk: corrupt closed line %d\n", line->id);
 #endif
@@ -1856,7 +1857,7 @@ static void __pblk_down_page(struct pblk *pblk, struct ppa_addr *ppa_list,
 	 * Only send one inflight I/O per LUN. Since we map at a page
 	 * granurality, all ppas in the I/O will map to the same LUN
 	 */
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	int i;
 
 	for (i = 1; i < nr_ppas; i++)
@@ -1866,7 +1867,8 @@ static void __pblk_down_page(struct pblk *pblk, struct ppa_addr *ppa_list,
 
 	ret = down_timeout(&rlun->wr_sem, msecs_to_jiffies(30000));
 	if (ret == -ETIME || ret == -EINTR)
-		pr_err("pblk: taking lun semaphore timed out: err %d\n", -ret);
+		pblk_err(pblk, "taking lun semaphore timed out: err %d\n",
+				-ret);
 }
 
 void pblk_down_page(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas)
@@ -1901,7 +1903,7 @@ void pblk_up_page(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas)
 	struct pblk_lun *rlun;
 	int pos = pblk_ppa_to_pos(geo, ppa_list[0]);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	int i;
 
 	for (i = 1; i < nr_ppas; i++)
@@ -1951,7 +1953,7 @@ void pblk_update_map(struct pblk *pblk, sector_t lba, struct ppa_addr ppa)
 void pblk_update_map_cache(struct pblk *pblk, sector_t lba, struct ppa_addr ppa)
 {
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a cache address */
 	BUG_ON(!pblk_addr_in_cache(ppa));
 	BUG_ON(pblk_rb_pos_oob(&pblk->rwb, pblk_addr_to_cacheline(ppa)));
@@ -1966,7 +1968,7 @@ int pblk_update_map_gc(struct pblk *pblk, sector_t lba, struct ppa_addr ppa_new,
 	struct ppa_addr ppa_l2p, ppa_gc;
 	int ret = 1;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a cache address */
 	BUG_ON(!pblk_addr_in_cache(ppa_new));
 	BUG_ON(pblk_rb_pos_oob(&pblk->rwb, pblk_addr_to_cacheline(ppa_new)));
@@ -2003,14 +2005,14 @@ void pblk_update_map_dev(struct pblk *pblk, sector_t lba,
 {
 	struct ppa_addr ppa_l2p;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a device address */
 	BUG_ON(pblk_addr_in_cache(ppa_mapped));
 #endif
 	/* Invalidate and discard padded entries */
 	if (lba == ADDR_EMPTY) {
 		atomic64_inc(&pblk->pad_wa);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 		atomic_long_inc(&pblk->padded_wb);
 #endif
 		if (!pblk_ppa_empty(ppa_mapped))
@@ -2036,7 +2038,7 @@ void pblk_update_map_dev(struct pblk *pblk, sector_t lba,
 		goto out;
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	WARN_ON(!pblk_addr_in_cache(ppa_l2p) && !pblk_ppa_empty(ppa_l2p));
 #endif
 
diff --git a/drivers/lightnvm/pblk-gc.c b/drivers/lightnvm/pblk-gc.c
index 080469d90b40..157c2567c9e8 100644
--- a/drivers/lightnvm/pblk-gc.c
+++ b/drivers/lightnvm/pblk-gc.c
@@ -90,7 +90,7 @@ static void pblk_gc_line_ws(struct work_struct *work)
 
 	gc_rq->data = vmalloc(array_size(gc_rq->nr_secs, geo->csecs));
 	if (!gc_rq->data) {
-		pr_err("pblk: could not GC line:%d (%d/%d)\n",
+		pblk_err(pblk, "could not GC line:%d (%d/%d)\n",
 					line->id, *line->vsc, gc_rq->nr_secs);
 		goto out;
 	}
@@ -98,7 +98,7 @@ static void pblk_gc_line_ws(struct work_struct *work)
 	/* Read from GC victim block */
 	ret = pblk_submit_read_gc(pblk, gc_rq);
 	if (ret) {
-		pr_err("pblk: failed GC read in line:%d (err:%d)\n",
+		pblk_err(pblk, "failed GC read in line:%d (err:%d)\n",
 								line->id, ret);
 		goto out;
 	}
@@ -146,7 +146,7 @@ static __le64 *get_lba_list_from_emeta(struct pblk *pblk,
 
 	ret = pblk_line_read_emeta(pblk, line, emeta_buf);
 	if (ret) {
-		pr_err("pblk: line %d read emeta failed (%d)\n",
+		pblk_err(pblk, "line %d read emeta failed (%d)\n",
 				line->id, ret);
 		pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
 		return NULL;
@@ -160,7 +160,7 @@ static __le64 *get_lba_list_from_emeta(struct pblk *pblk,
 
 	ret = pblk_recov_check_emeta(pblk, emeta_buf);
 	if (ret) {
-		pr_err("pblk: inconsistent emeta (line %d)\n",
+		pblk_err(pblk, "inconsistent emeta (line %d)\n",
 				line->id);
 		pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
 		return NULL;
@@ -201,7 +201,7 @@ static void pblk_gc_line_prepare_ws(struct work_struct *work)
 	} else {
 		lba_list = get_lba_list_from_emeta(pblk, line);
 		if (!lba_list) {
-			pr_err("pblk: could not interpret emeta (line %d)\n",
+			pblk_err(pblk, "could not interpret emeta (line %d)\n",
 					line->id);
 			goto fail_free_invalid_bitmap;
 		}
@@ -213,7 +213,7 @@ static void pblk_gc_line_prepare_ws(struct work_struct *work)
 	spin_unlock(&line->lock);
 
 	if (sec_left < 0) {
-		pr_err("pblk: corrupted GC line (%d)\n", line->id);
+		pblk_err(pblk, "corrupted GC line (%d)\n", line->id);
 		goto fail_free_lba_list;
 	}
 
@@ -289,7 +289,7 @@ fail_free_ws:
 	kref_put(&line->ref, pblk_line_put);
 	atomic_dec(&gc->read_inflight_gc);
 
-	pr_err("pblk: Failed to GC line %d\n", line->id);
+	pblk_err(pblk, "failed to GC line %d\n", line->id);
 }
 
 static int pblk_gc_line(struct pblk *pblk, struct pblk_line *line)
@@ -297,7 +297,7 @@ static int pblk_gc_line(struct pblk *pblk, struct pblk_line *line)
 	struct pblk_gc *gc = &pblk->gc;
 	struct pblk_line_ws *line_ws;
 
-	pr_debug("pblk: line '%d' being reclaimed for GC\n", line->id);
+	pblk_debug(pblk, "line '%d' being reclaimed for GC\n", line->id);
 
 	line_ws = kmalloc(sizeof(struct pblk_line_ws), GFP_KERNEL);
 	if (!line_ws)
@@ -351,7 +351,7 @@ static int pblk_gc_read(struct pblk *pblk)
 	pblk_gc_kick(pblk);
 
 	if (pblk_gc_line(pblk, line))
-		pr_err("pblk: failed to GC line %d\n", line->id);
+		pblk_err(pblk, "failed to GC line %d\n", line->id);
 
 	return 0;
 }
@@ -522,8 +522,8 @@ static int pblk_gc_reader_ts(void *data)
 		io_schedule();
 	}
 
-#ifdef CONFIG_NVM_DEBUG
-	pr_info("pblk: flushing gc pipeline, %d lines left\n",
+#ifdef CONFIG_NVM_PBLK_DEBUG
+	pblk_info(pblk, "flushing gc pipeline, %d lines left\n",
 		atomic_read(&gc->pipeline_gc));
 #endif
 
@@ -540,7 +540,7 @@ static int pblk_gc_reader_ts(void *data)
 static void pblk_gc_start(struct pblk *pblk)
 {
 	pblk->gc.gc_active = 1;
-	pr_debug("pblk: gc start\n");
+	pblk_debug(pblk, "gc start\n");
 }
 
 void pblk_gc_should_start(struct pblk *pblk)
@@ -605,14 +605,14 @@ int pblk_gc_init(struct pblk *pblk)
 
 	gc->gc_ts = kthread_create(pblk_gc_ts, pblk, "pblk-gc-ts");
 	if (IS_ERR(gc->gc_ts)) {
-		pr_err("pblk: could not allocate GC main kthread\n");
+		pblk_err(pblk, "could not allocate GC main kthread\n");
 		return PTR_ERR(gc->gc_ts);
 	}
 
 	gc->gc_writer_ts = kthread_create(pblk_gc_writer_ts, pblk,
 							"pblk-gc-writer-ts");
 	if (IS_ERR(gc->gc_writer_ts)) {
-		pr_err("pblk: could not allocate GC writer kthread\n");
+		pblk_err(pblk, "could not allocate GC writer kthread\n");
 		ret = PTR_ERR(gc->gc_writer_ts);
 		goto fail_free_main_kthread;
 	}
@@ -620,7 +620,7 @@ int pblk_gc_init(struct pblk *pblk)
 	gc->gc_reader_ts = kthread_create(pblk_gc_reader_ts, pblk,
 							"pblk-gc-reader-ts");
 	if (IS_ERR(gc->gc_reader_ts)) {
-		pr_err("pblk: could not allocate GC reader kthread\n");
+		pblk_err(pblk, "could not allocate GC reader kthread\n");
 		ret = PTR_ERR(gc->gc_reader_ts);
 		goto fail_free_writer_kthread;
 	}
@@ -641,7 +641,7 @@ int pblk_gc_init(struct pblk *pblk)
 	gc->gc_line_reader_wq = alloc_workqueue("pblk-gc-line-reader-wq",
 			WQ_MEM_RECLAIM | WQ_UNBOUND, PBLK_GC_MAX_READERS);
 	if (!gc->gc_line_reader_wq) {
-		pr_err("pblk: could not allocate GC line reader workqueue\n");
+		pblk_err(pblk, "could not allocate GC line reader workqueue\n");
 		ret = -ENOMEM;
 		goto fail_free_reader_kthread;
 	}
@@ -650,7 +650,7 @@ int pblk_gc_init(struct pblk *pblk)
 	gc->gc_reader_wq = alloc_workqueue("pblk-gc-line_wq",
 					WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
 	if (!gc->gc_reader_wq) {
-		pr_err("pblk: could not allocate GC reader workqueue\n");
+		pblk_err(pblk, "could not allocate GC reader workqueue\n");
 		ret = -ENOMEM;
 		goto fail_free_reader_line_wq;
 	}
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index b57f764d6a16..537e98f2b24a 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -91,7 +91,7 @@ static size_t pblk_trans_map_size(struct pblk *pblk)
 	return entry_size * pblk->rl.nr_secs;
 }
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 static u32 pblk_l2p_crc(struct pblk *pblk)
 {
 	size_t map_size;
@@ -117,13 +117,13 @@ static int pblk_l2p_recover(struct pblk *pblk, bool factory_init)
 	} else {
 		line = pblk_recov_l2p(pblk);
 		if (IS_ERR(line)) {
-			pr_err("pblk: could not recover l2p table\n");
+			pblk_err(pblk, "could not recover l2p table\n");
 			return -EFAULT;
 		}
 	}
 
-#ifdef CONFIG_NVM_DEBUG
-	pr_info("pblk init: L2P CRC: %x\n", pblk_l2p_crc(pblk));
+#ifdef CONFIG_NVM_PBLK_DEBUG
+	pblk_info(pblk, "init: L2P CRC: %x\n", pblk_l2p_crc(pblk));
 #endif
 
 	/* Free full lines directly as GC has not been started yet */
@@ -166,7 +166,7 @@ static int pblk_l2p_init(struct pblk *pblk, bool factory_init)
 static void pblk_rwb_free(struct pblk *pblk)
 {
 	if (pblk_rb_tear_down_check(&pblk->rwb))
-		pr_err("pblk: write buffer error on tear down\n");
+		pblk_err(pblk, "write buffer error on tear down\n");
 
 	pblk_rb_data_free(&pblk->rwb);
 	vfree(pblk_rb_entries_ref(&pblk->rwb));
@@ -179,11 +179,14 @@ static int pblk_rwb_init(struct pblk *pblk)
 	struct pblk_rb_entry *entries;
 	unsigned long nr_entries, buffer_size;
 	unsigned int power_size, power_seg_sz;
+	int pgs_in_buffer;
 
-	if (write_buffer_size && (write_buffer_size > pblk->pgs_in_buffer))
+	pgs_in_buffer = max(geo->mw_cunits, geo->ws_opt) * geo->all_luns;
+
+	if (write_buffer_size && (write_buffer_size > pgs_in_buffer))
 		buffer_size = write_buffer_size;
 	else
-		buffer_size = pblk->pgs_in_buffer;
+		buffer_size = pgs_in_buffer;
 
 	nr_entries = pblk_rb_calculate_size(buffer_size);
 
@@ -200,7 +203,8 @@ static int pblk_rwb_init(struct pblk *pblk)
 /* Minimum pages needed within a lun */
 #define ADDR_POOL_SIZE 64
 
-static int pblk_set_addrf_12(struct nvm_geo *geo, struct nvm_addrf_12 *dst)
+static int pblk_set_addrf_12(struct pblk *pblk, struct nvm_geo *geo,
+			     struct nvm_addrf_12 *dst)
 {
 	struct nvm_addrf_12 *src = (struct nvm_addrf_12 *)&geo->addrf;
 	int power_len;
@@ -208,14 +212,14 @@ static int pblk_set_addrf_12(struct nvm_geo *geo, struct nvm_addrf_12 *dst)
 	/* Re-calculate channel and lun format to adapt to configuration */
 	power_len = get_count_order(geo->num_ch);
 	if (1 << power_len != geo->num_ch) {
-		pr_err("pblk: supports only power-of-two channel config.\n");
+		pblk_err(pblk, "supports only power-of-two channel config.\n");
 		return -EINVAL;
 	}
 	dst->ch_len = power_len;
 
 	power_len = get_count_order(geo->num_lun);
 	if (1 << power_len != geo->num_lun) {
-		pr_err("pblk: supports only power-of-two LUN config.\n");
+		pblk_err(pblk, "supports only power-of-two LUN config.\n");
 		return -EINVAL;
 	}
 	dst->lun_len = power_len;
@@ -282,18 +286,19 @@ static int pblk_set_addrf(struct pblk *pblk)
 	case NVM_OCSSD_SPEC_12:
 		div_u64_rem(geo->clba, pblk->min_write_pgs, &mod);
 		if (mod) {
-			pr_err("pblk: bad configuration of sectors/pages\n");
+			pblk_err(pblk, "bad configuration of sectors/pages\n");
 			return -EINVAL;
 		}
 
-		pblk->addrf_len = pblk_set_addrf_12(geo, (void *)&pblk->addrf);
+		pblk->addrf_len = pblk_set_addrf_12(pblk, geo,
+							(void *)&pblk->addrf);
 		break;
 	case NVM_OCSSD_SPEC_20:
 		pblk->addrf_len = pblk_set_addrf_20(geo, (void *)&pblk->addrf,
-								&pblk->uaddrf);
+							&pblk->uaddrf);
 		break;
 	default:
-		pr_err("pblk: OCSSD revision not supported (%d)\n",
+		pblk_err(pblk, "OCSSD revision not supported (%d)\n",
 								geo->version);
 		return -EINVAL;
 	}
@@ -366,15 +371,13 @@ static int pblk_core_init(struct pblk *pblk)
 	atomic64_set(&pblk->nr_flush, 0);
 	pblk->nr_flush_rst = 0;
 
-	pblk->pgs_in_buffer = geo->mw_cunits * geo->all_luns;
-
 	pblk->min_write_pgs = geo->ws_opt * (geo->csecs / PAGE_SIZE);
 	max_write_ppas = pblk->min_write_pgs * geo->all_luns;
 	pblk->max_write_pgs = min_t(int, max_write_ppas, NVM_MAX_VLBA);
 	pblk_set_sec_per_write(pblk, pblk->min_write_pgs);
 
 	if (pblk->max_write_pgs > PBLK_MAX_REQ_ADDRS) {
-		pr_err("pblk: vector list too big(%u > %u)\n",
+		pblk_err(pblk, "vector list too big(%u > %u)\n",
 				pblk->max_write_pgs, PBLK_MAX_REQ_ADDRS);
 		return -EINVAL;
 	}
@@ -607,7 +610,7 @@ static int pblk_luns_init(struct pblk *pblk)
 
 	/* TODO: Implement unbalanced LUN support */
 	if (geo->num_lun < 0) {
-		pr_err("pblk: unbalanced LUN config.\n");
+		pblk_err(pblk, "unbalanced LUN config.\n");
 		return -EINVAL;
 	}
 
@@ -716,10 +719,11 @@ static int pblk_setup_line_meta_12(struct pblk *pblk, struct pblk_line *line,
 
 		/*
 		 * In 1.2 spec. chunk state is not persisted by the device. Thus
-		 * some of the values are reset each time pblk is instantiated.
+		 * some of the values are reset each time pblk is instantiated,
+		 * so we have to assume that the block is closed.
 		 */
 		if (lun_bb_meta[line->id] == NVM_BLK_T_FREE)
-			chunk->state =  NVM_CHK_ST_FREE;
+			chunk->state =  NVM_CHK_ST_CLOSED;
 		else
 			chunk->state = NVM_CHK_ST_OFFLINE;
 
@@ -1026,7 +1030,7 @@ add_emeta_page:
 					lm->emeta_sec[0], geo->clba);
 
 	if (lm->min_blk_line > lm->blk_per_line) {
-		pr_err("pblk: config. not supported. Min. LUN in line:%d\n",
+		pblk_err(pblk, "config. not supported. Min. LUN in line:%d\n",
 							lm->blk_per_line);
 		return -EINVAL;
 	}
@@ -1078,7 +1082,7 @@ static int pblk_lines_init(struct pblk *pblk)
 	}
 
 	if (!nr_free_chks) {
-		pr_err("pblk: too many bad blocks prevent for sane instance\n");
+		pblk_err(pblk, "too many bad blocks prevent for sane instance\n");
 		return -EINTR;
 	}
 
@@ -1108,7 +1112,7 @@ static int pblk_writer_init(struct pblk *pblk)
 		int err = PTR_ERR(pblk->writer_ts);
 
 		if (err != -EINTR)
-			pr_err("pblk: could not allocate writer kthread (%d)\n",
+			pblk_err(pblk, "could not allocate writer kthread (%d)\n",
 					err);
 		return err;
 	}
@@ -1154,7 +1158,7 @@ static void pblk_tear_down(struct pblk *pblk, bool graceful)
 	pblk_rb_sync_l2p(&pblk->rwb);
 	pblk_rl_free(&pblk->rl);
 
-	pr_debug("pblk: consistent tear down (graceful:%d)\n", graceful);
+	pblk_debug(pblk, "consistent tear down (graceful:%d)\n", graceful);
 }
 
 static void pblk_exit(void *private, bool graceful)
@@ -1165,8 +1169,8 @@ static void pblk_exit(void *private, bool graceful)
 	pblk_gc_exit(pblk, graceful);
 	pblk_tear_down(pblk, graceful);
 
-#ifdef CONFIG_NVM_DEBUG
-	pr_info("pblk exit: L2P CRC: %x\n", pblk_l2p_crc(pblk));
+#ifdef CONFIG_NVM_PBLK_DEBUG
+	pblk_info(pblk, "exit: L2P CRC: %x\n", pblk_l2p_crc(pblk));
 #endif
 
 	pblk_free(pblk);
@@ -1189,34 +1193,35 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
 	struct pblk *pblk;
 	int ret;
 
-	/* pblk supports 1.2 and 2.0 versions */
+	pblk = kzalloc(sizeof(struct pblk), GFP_KERNEL);
+	if (!pblk)
+		return ERR_PTR(-ENOMEM);
+
+	pblk->dev = dev;
+	pblk->disk = tdisk;
+	pblk->state = PBLK_STATE_RUNNING;
+	pblk->gc.gc_enabled = 0;
+
 	if (!(geo->version == NVM_OCSSD_SPEC_12 ||
 					geo->version == NVM_OCSSD_SPEC_20)) {
-		pr_err("pblk: OCSSD version not supported (%u)\n",
+		pblk_err(pblk, "OCSSD version not supported (%u)\n",
 							geo->version);
+		kfree(pblk);
 		return ERR_PTR(-EINVAL);
 	}
 
 	if (geo->version == NVM_OCSSD_SPEC_12 && geo->dom & NVM_RSP_L2P) {
-		pr_err("pblk: host-side L2P table not supported. (%x)\n",
+		pblk_err(pblk, "host-side L2P table not supported. (%x)\n",
 							geo->dom);
+		kfree(pblk);
 		return ERR_PTR(-EINVAL);
 	}
 
-	pblk = kzalloc(sizeof(struct pblk), GFP_KERNEL);
-	if (!pblk)
-		return ERR_PTR(-ENOMEM);
-
-	pblk->dev = dev;
-	pblk->disk = tdisk;
-	pblk->state = PBLK_STATE_RUNNING;
-	pblk->gc.gc_enabled = 0;
-
 	spin_lock_init(&pblk->resubmit_lock);
 	spin_lock_init(&pblk->trans_lock);
 	spin_lock_init(&pblk->lock);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_set(&pblk->inflight_writes, 0);
 	atomic_long_set(&pblk->padded_writes, 0);
 	atomic_long_set(&pblk->padded_wb, 0);
@@ -1241,38 +1246,38 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
 
 	ret = pblk_core_init(pblk);
 	if (ret) {
-		pr_err("pblk: could not initialize core\n");
+		pblk_err(pblk, "could not initialize core\n");
 		goto fail;
 	}
 
 	ret = pblk_lines_init(pblk);
 	if (ret) {
-		pr_err("pblk: could not initialize lines\n");
+		pblk_err(pblk, "could not initialize lines\n");
 		goto fail_free_core;
 	}
 
 	ret = pblk_rwb_init(pblk);
 	if (ret) {
-		pr_err("pblk: could not initialize write buffer\n");
+		pblk_err(pblk, "could not initialize write buffer\n");
 		goto fail_free_lines;
 	}
 
 	ret = pblk_l2p_init(pblk, flags & NVM_TARGET_FACTORY);
 	if (ret) {
-		pr_err("pblk: could not initialize maps\n");
+		pblk_err(pblk, "could not initialize maps\n");
 		goto fail_free_rwb;
 	}
 
 	ret = pblk_writer_init(pblk);
 	if (ret) {
 		if (ret != -EINTR)
-			pr_err("pblk: could not initialize write thread\n");
+			pblk_err(pblk, "could not initialize write thread\n");
 		goto fail_free_l2p;
 	}
 
 	ret = pblk_gc_init(pblk);
 	if (ret) {
-		pr_err("pblk: could not initialize gc\n");
+		pblk_err(pblk, "could not initialize gc\n");
 		goto fail_stop_writer;
 	}
 
@@ -1287,8 +1292,7 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
 	blk_queue_max_discard_sectors(tqueue, UINT_MAX >> 9);
 	blk_queue_flag_set(QUEUE_FLAG_DISCARD, tqueue);
 
-	pr_info("pblk(%s): luns:%u, lines:%d, secs:%llu, buf entries:%u\n",
-			tdisk->disk_name,
+	pblk_info(pblk, "luns:%u, lines:%d, secs:%llu, buf entries:%u\n",
 			geo->all_luns, pblk->l_mg.nr_lines,
 			(unsigned long long)pblk->rl.nr_secs,
 			pblk->rwb.nr_entries);
diff --git a/drivers/lightnvm/pblk-rb.c b/drivers/lightnvm/pblk-rb.c
index 55e9442a99e2..f6eec0212dfc 100644
--- a/drivers/lightnvm/pblk-rb.c
+++ b/drivers/lightnvm/pblk-rb.c
@@ -111,7 +111,7 @@ int pblk_rb_init(struct pblk_rb *rb, struct pblk_rb_entry *rb_entry_base,
 	} while (iter > 0);
 	up_write(&pblk_rb_lock);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_set(&rb->inflight_flush_point, 0);
 #endif
 
@@ -308,7 +308,7 @@ void pblk_rb_write_entry_user(struct pblk_rb *rb, void *data,
 
 	entry = &rb->entries[ring_pos];
 	flags = READ_ONCE(entry->w_ctx.flags);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Caller must guarantee that the entry is free */
 	BUG_ON(!(flags & PBLK_WRITABLE_ENTRY));
 #endif
@@ -332,7 +332,7 @@ void pblk_rb_write_entry_gc(struct pblk_rb *rb, void *data,
 
 	entry = &rb->entries[ring_pos];
 	flags = READ_ONCE(entry->w_ctx.flags);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Caller must guarantee that the entry is free */
 	BUG_ON(!(flags & PBLK_WRITABLE_ENTRY));
 #endif
@@ -362,7 +362,7 @@ static int pblk_rb_flush_point_set(struct pblk_rb *rb, struct bio *bio,
 		return 0;
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_inc(&rb->inflight_flush_point);
 #endif
 
@@ -547,7 +547,7 @@ try:
 
 		page = virt_to_page(entry->data);
 		if (!page) {
-			pr_err("pblk: could not allocate write bio page\n");
+			pblk_err(pblk, "could not allocate write bio page\n");
 			flags &= ~PBLK_WRITTEN_DATA;
 			flags |= PBLK_SUBMITTED_ENTRY;
 			/* Release flags on context. Protect from writes */
@@ -557,7 +557,7 @@ try:
 
 		if (bio_add_pc_page(q, bio, page, rb->seg_size, 0) !=
 								rb->seg_size) {
-			pr_err("pblk: could not add page to write bio\n");
+			pblk_err(pblk, "could not add page to write bio\n");
 			flags &= ~PBLK_WRITTEN_DATA;
 			flags |= PBLK_SUBMITTED_ENTRY;
 			/* Release flags on context. Protect from writes */
@@ -576,19 +576,19 @@ try:
 
 	if (pad) {
 		if (pblk_bio_add_pages(pblk, bio, GFP_KERNEL, pad)) {
-			pr_err("pblk: could not pad page in write bio\n");
+			pblk_err(pblk, "could not pad page in write bio\n");
 			return NVM_IO_ERR;
 		}
 
 		if (pad < pblk->min_write_pgs)
 			atomic64_inc(&pblk->pad_dist[pad - 1]);
 		else
-			pr_warn("pblk: padding more than min. sectors\n");
+			pblk_warn(pblk, "padding more than min. sectors\n");
 
 		atomic64_add(pad, &pblk->pad_wa);
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(pad, &pblk->padded_writes);
 #endif
 
@@ -613,7 +613,7 @@ int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba,
 	int ret = 1;
 
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Caller must ensure that the access will not cause an overflow */
 	BUG_ON(pos >= rb->nr_entries);
 #endif
@@ -820,7 +820,7 @@ ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf)
 			rb->subm,
 			rb->sync,
 			rb->l2p_update,
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			atomic_read(&rb->inflight_flush_point),
 #else
 			0,
@@ -838,7 +838,7 @@ ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf)
 			rb->subm,
 			rb->sync,
 			rb->l2p_update,
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			atomic_read(&rb->inflight_flush_point),
 #else
 			0,
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 18694694e5f0..5a46d7f9302f 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -28,7 +28,7 @@ static int pblk_read_from_cache(struct pblk *pblk, struct bio *bio,
 				sector_t lba, struct ppa_addr ppa,
 				int bio_iter, bool advanced_bio)
 {
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a cache address */
 	BUG_ON(pblk_ppa_empty(ppa));
 	BUG_ON(!pblk_addr_in_cache(ppa));
@@ -79,7 +79,7 @@ retry:
 			WARN_ON(test_and_set_bit(i, read_bitmap));
 			meta_list[i].lba = cpu_to_le64(lba);
 			advanced_bio = true;
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			atomic_long_inc(&pblk->cache_reads);
 #endif
 		} else {
@@ -97,7 +97,7 @@ next:
 	else
 		rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(nr_secs, &pblk->inflight_reads);
 #endif
 }
@@ -117,13 +117,13 @@ static void pblk_read_check_seq(struct pblk *pblk, struct nvm_rq *rqd,
 			continue;
 
 		if (lba != blba + i) {
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			struct ppa_addr *p;
 
 			p = (nr_lbas == 1) ? &rqd->ppa_list[i] : &rqd->ppa_addr;
-			print_ppa(&pblk->dev->geo, p, "seq", i);
+			print_ppa(pblk, p, "seq", i);
 #endif
-			pr_err("pblk: corrupted read LBA (%llu/%llu)\n",
+			pblk_err(pblk, "corrupted read LBA (%llu/%llu)\n",
 							lba, (u64)blba + i);
 			WARN_ON(1);
 		}
@@ -149,14 +149,14 @@ static void pblk_read_check_rand(struct pblk *pblk, struct nvm_rq *rqd,
 		meta_lba = le64_to_cpu(meta_lba_list[j].lba);
 
 		if (lba != meta_lba) {
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			struct ppa_addr *p;
 			int nr_ppas = rqd->nr_ppas;
 
 			p = (nr_ppas == 1) ? &rqd->ppa_list[j] : &rqd->ppa_addr;
-			print_ppa(&pblk->dev->geo, p, "seq", j);
+			print_ppa(pblk, p, "seq", j);
 #endif
-			pr_err("pblk: corrupted read LBA (%llu/%llu)\n",
+			pblk_err(pblk, "corrupted read LBA (%llu/%llu)\n",
 								lba, meta_lba);
 			WARN_ON(1);
 		}
@@ -185,7 +185,7 @@ static void pblk_read_put_rqd_kref(struct pblk *pblk, struct nvm_rq *rqd)
 
 static void pblk_end_user_read(struct bio *bio)
 {
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	WARN_ONCE(bio->bi_status, "pblk: corrupted read bio\n");
 #endif
 	bio_endio(bio);
@@ -199,7 +199,7 @@ static void __pblk_end_io_read(struct pblk *pblk, struct nvm_rq *rqd,
 	struct bio *int_bio = rqd->bio;
 	unsigned long start_time = r_ctx->start_time;
 
-	generic_end_io_acct(dev->q, READ, &pblk->disk->part0, start_time);
+	generic_end_io_acct(dev->q, REQ_OP_READ, &pblk->disk->part0, start_time);
 
 	if (rqd->error)
 		pblk_log_read_err(pblk, rqd);
@@ -212,7 +212,7 @@ static void __pblk_end_io_read(struct pblk *pblk, struct nvm_rq *rqd,
 	if (put_line)
 		pblk_read_put_rqd_kref(pblk, rqd);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(rqd->nr_ppas, &pblk->sync_reads);
 	atomic_long_sub(rqd->nr_ppas, &pblk->inflight_reads);
 #endif
@@ -231,74 +231,36 @@ static void pblk_end_io_read(struct nvm_rq *rqd)
 	__pblk_end_io_read(pblk, rqd, true);
 }
 
-static int pblk_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
-			     struct bio *orig_bio, unsigned int bio_init_idx,
-			     unsigned long *read_bitmap)
+static void pblk_end_partial_read(struct nvm_rq *rqd)
 {
-	struct pblk_sec_meta *meta_list = rqd->meta_list;
-	struct bio *new_bio;
+	struct pblk *pblk = rqd->private;
+	struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd);
+	struct pblk_pr_ctx *pr_ctx = r_ctx->private;
+	struct bio *new_bio = rqd->bio;
+	struct bio *bio = pr_ctx->orig_bio;
 	struct bio_vec src_bv, dst_bv;
-	void *ppa_ptr = NULL;
-	void *src_p, *dst_p;
-	dma_addr_t dma_ppa_list = 0;
-	__le64 *lba_list_mem, *lba_list_media;
-	int nr_secs = rqd->nr_ppas;
+	struct pblk_sec_meta *meta_list = rqd->meta_list;
+	int bio_init_idx = pr_ctx->bio_init_idx;
+	unsigned long *read_bitmap = pr_ctx->bitmap;
+	int nr_secs = pr_ctx->orig_nr_secs;
 	int nr_holes = nr_secs - bitmap_weight(read_bitmap, nr_secs);
-	int i, ret, hole;
-
-	/* Re-use allocated memory for intermediate lbas */
-	lba_list_mem = (((void *)rqd->ppa_list) + pblk_dma_ppa_size);
-	lba_list_media = (((void *)rqd->ppa_list) + 2 * pblk_dma_ppa_size);
-
-	new_bio = bio_alloc(GFP_KERNEL, nr_holes);
-
-	if (pblk_bio_add_pages(pblk, new_bio, GFP_KERNEL, nr_holes))
-		goto fail_add_pages;
-
-	if (nr_holes != new_bio->bi_vcnt) {
-		pr_err("pblk: malformed bio\n");
-		goto fail;
-	}
-
-	for (i = 0; i < nr_secs; i++)
-		lba_list_mem[i] = meta_list[i].lba;
-
-	new_bio->bi_iter.bi_sector = 0; /* internal bio */
-	bio_set_op_attrs(new_bio, REQ_OP_READ, 0);
-
-	rqd->bio = new_bio;
-	rqd->nr_ppas = nr_holes;
-	rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
-
-	if (unlikely(nr_holes == 1)) {
-		ppa_ptr = rqd->ppa_list;
-		dma_ppa_list = rqd->dma_ppa_list;
-		rqd->ppa_addr = rqd->ppa_list[0];
-	}
-
-	ret = pblk_submit_io_sync(pblk, rqd);
-	if (ret) {
-		bio_put(rqd->bio);
-		pr_err("pblk: sync read IO submission failed\n");
-		goto fail;
-	}
-
-	if (rqd->error) {
-		atomic_long_inc(&pblk->read_failed);
-#ifdef CONFIG_NVM_DEBUG
-		pblk_print_failed_rqd(pblk, rqd, rqd->error);
-#endif
-	}
+	__le64 *lba_list_mem, *lba_list_media;
+	void *src_p, *dst_p;
+	int hole, i;
 
 	if (unlikely(nr_holes == 1)) {
 		struct ppa_addr ppa;
 
 		ppa = rqd->ppa_addr;
-		rqd->ppa_list = ppa_ptr;
-		rqd->dma_ppa_list = dma_ppa_list;
+		rqd->ppa_list = pr_ctx->ppa_ptr;
+		rqd->dma_ppa_list = pr_ctx->dma_ppa_list;
 		rqd->ppa_list[0] = ppa;
 	}
 
+	/* Re-use allocated memory for intermediate lbas */
+	lba_list_mem = (((void *)rqd->ppa_list) + pblk_dma_ppa_size);
+	lba_list_media = (((void *)rqd->ppa_list) + 2 * pblk_dma_ppa_size);
+
 	for (i = 0; i < nr_secs; i++) {
 		lba_list_media[i] = meta_list[i].lba;
 		meta_list[i].lba = lba_list_mem[i];
@@ -316,7 +278,7 @@ static int pblk_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
 		meta_list[hole].lba = lba_list_media[i];
 
 		src_bv = new_bio->bi_io_vec[i++];
-		dst_bv = orig_bio->bi_io_vec[bio_init_idx + hole];
+		dst_bv = bio->bi_io_vec[bio_init_idx + hole];
 
 		src_p = kmap_atomic(src_bv.bv_page);
 		dst_p = kmap_atomic(dst_bv.bv_page);
@@ -334,19 +296,107 @@ static int pblk_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
 	} while (hole < nr_secs);
 
 	bio_put(new_bio);
+	kfree(pr_ctx);
 
 	/* restore original request */
 	rqd->bio = NULL;
 	rqd->nr_ppas = nr_secs;
 
+	bio_endio(bio);
 	__pblk_end_io_read(pblk, rqd, false);
-	return NVM_IO_DONE;
+}
 
-fail:
-	/* Free allocated pages in new bio */
+static int pblk_setup_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
+			    unsigned int bio_init_idx,
+			    unsigned long *read_bitmap,
+			    int nr_holes)
+{
+	struct pblk_sec_meta *meta_list = rqd->meta_list;
+	struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd);
+	struct pblk_pr_ctx *pr_ctx;
+	struct bio *new_bio, *bio = r_ctx->private;
+	__le64 *lba_list_mem;
+	int nr_secs = rqd->nr_ppas;
+	int i;
+
+	/* Re-use allocated memory for intermediate lbas */
+	lba_list_mem = (((void *)rqd->ppa_list) + pblk_dma_ppa_size);
+
+	new_bio = bio_alloc(GFP_KERNEL, nr_holes);
+
+	if (pblk_bio_add_pages(pblk, new_bio, GFP_KERNEL, nr_holes))
+		goto fail_bio_put;
+
+	if (nr_holes != new_bio->bi_vcnt) {
+		WARN_ONCE(1, "pblk: malformed bio\n");
+		goto fail_free_pages;
+	}
+
+	pr_ctx = kmalloc(sizeof(struct pblk_pr_ctx), GFP_KERNEL);
+	if (!pr_ctx)
+		goto fail_free_pages;
+
+	for (i = 0; i < nr_secs; i++)
+		lba_list_mem[i] = meta_list[i].lba;
+
+	new_bio->bi_iter.bi_sector = 0; /* internal bio */
+	bio_set_op_attrs(new_bio, REQ_OP_READ, 0);
+
+	rqd->bio = new_bio;
+	rqd->nr_ppas = nr_holes;
+	rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
+
+	pr_ctx->ppa_ptr = NULL;
+	pr_ctx->orig_bio = bio;
+	bitmap_copy(pr_ctx->bitmap, read_bitmap, NVM_MAX_VLBA);
+	pr_ctx->bio_init_idx = bio_init_idx;
+	pr_ctx->orig_nr_secs = nr_secs;
+	r_ctx->private = pr_ctx;
+
+	if (unlikely(nr_holes == 1)) {
+		pr_ctx->ppa_ptr = rqd->ppa_list;
+		pr_ctx->dma_ppa_list = rqd->dma_ppa_list;
+		rqd->ppa_addr = rqd->ppa_list[0];
+	}
+	return 0;
+
+fail_free_pages:
 	pblk_bio_free_pages(pblk, new_bio, 0, new_bio->bi_vcnt);
-fail_add_pages:
-	pr_err("pblk: failed to perform partial read\n");
+fail_bio_put:
+	bio_put(new_bio);
+
+	return -ENOMEM;
+}
+
+static int pblk_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
+				 unsigned int bio_init_idx,
+				 unsigned long *read_bitmap, int nr_secs)
+{
+	int nr_holes;
+	int ret;
+
+	nr_holes = nr_secs - bitmap_weight(read_bitmap, nr_secs);
+
+	if (pblk_setup_partial_read(pblk, rqd, bio_init_idx, read_bitmap,
+				    nr_holes))
+		return NVM_IO_ERR;
+
+	rqd->end_io = pblk_end_partial_read;
+
+	ret = pblk_submit_io(pblk, rqd);
+	if (ret) {
+		bio_put(rqd->bio);
+		pblk_err(pblk, "partial read IO submission failed\n");
+		goto err;
+	}
+
+	return NVM_IO_OK;
+
+err:
+	pblk_err(pblk, "failed to perform partial read\n");
+
+	/* Free allocated pages in new bio */
+	pblk_bio_free_pages(pblk, rqd->bio, 0, rqd->bio->bi_vcnt);
 	__pblk_end_io_read(pblk, rqd, false);
 	return NVM_IO_ERR;
 }
@@ -359,7 +409,7 @@ static void pblk_read_rq(struct pblk *pblk, struct nvm_rq *rqd, struct bio *bio,
 
 	pblk_lookup_l2p_seq(pblk, &ppa, lba, 1);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_inc(&pblk->inflight_reads);
 #endif
 
@@ -382,7 +432,7 @@ retry:
 		WARN_ON(test_and_set_bit(0, read_bitmap));
 		meta_list[0].lba = cpu_to_le64(lba);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 		atomic_long_inc(&pblk->cache_reads);
 #endif
 	} else {
@@ -401,7 +451,7 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 	struct pblk_g_ctx *r_ctx;
 	struct nvm_rq *rqd;
 	unsigned int bio_init_idx;
-	unsigned long read_bitmap; /* Max 64 ppas per request */
+	DECLARE_BITMAP(read_bitmap, NVM_MAX_VLBA);
 	int ret = NVM_IO_ERR;
 
 	/* logic error: lba out-of-bounds. Ignore read request */
@@ -411,9 +461,10 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 		return NVM_IO_ERR;
 	}
 
-	generic_start_io_acct(q, READ, bio_sectors(bio), &pblk->disk->part0);
+	generic_start_io_acct(q, REQ_OP_READ, bio_sectors(bio),
+			      &pblk->disk->part0);
 
-	bitmap_zero(&read_bitmap, nr_secs);
+	bitmap_zero(read_bitmap, nr_secs);
 
 	rqd = pblk_alloc_rqd(pblk, PBLK_READ);
 
@@ -436,7 +487,7 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 	rqd->meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
 							&rqd->dma_meta_list);
 	if (!rqd->meta_list) {
-		pr_err("pblk: not able to allocate ppa list\n");
+		pblk_err(pblk, "not able to allocate ppa list\n");
 		goto fail_rqd_free;
 	}
 
@@ -444,32 +495,32 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 		rqd->ppa_list = rqd->meta_list + pblk_dma_meta_size;
 		rqd->dma_ppa_list = rqd->dma_meta_list + pblk_dma_meta_size;
 
-		pblk_read_ppalist_rq(pblk, rqd, bio, blba, &read_bitmap);
+		pblk_read_ppalist_rq(pblk, rqd, bio, blba, read_bitmap);
 	} else {
-		pblk_read_rq(pblk, rqd, bio, blba, &read_bitmap);
+		pblk_read_rq(pblk, rqd, bio, blba, read_bitmap);
 	}
 
-	if (bitmap_full(&read_bitmap, nr_secs)) {
+	if (bitmap_full(read_bitmap, nr_secs)) {
 		atomic_inc(&pblk->inflight_io);
 		__pblk_end_io_read(pblk, rqd, false);
 		return NVM_IO_DONE;
 	}
 
 	/* All sectors are to be read from the device */
-	if (bitmap_empty(&read_bitmap, rqd->nr_ppas)) {
+	if (bitmap_empty(read_bitmap, rqd->nr_ppas)) {
 		struct bio *int_bio = NULL;
 
 		/* Clone read bio to deal with read errors internally */
 		int_bio = bio_clone_fast(bio, GFP_KERNEL, &pblk_bio_set);
 		if (!int_bio) {
-			pr_err("pblk: could not clone read bio\n");
+			pblk_err(pblk, "could not clone read bio\n");
 			goto fail_end_io;
 		}
 
 		rqd->bio = int_bio;
 
 		if (pblk_submit_io(pblk, rqd)) {
-			pr_err("pblk: read IO submission failed\n");
+			pblk_err(pblk, "read IO submission failed\n");
 			ret = NVM_IO_ERR;
 			goto fail_end_io;
 		}
@@ -480,8 +531,15 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 	/* The read bio request could be partially filled by the write buffer,
 	 * but there are some holes that need to be read from the drive.
 	 */
-	return pblk_partial_read(pblk, rqd, bio, bio_init_idx, &read_bitmap);
+	ret = pblk_partial_read_bio(pblk, rqd, bio_init_idx, read_bitmap,
+				    nr_secs);
+	if (ret)
+		goto fail_meta_free;
+
+	return NVM_IO_OK;
 
+fail_meta_free:
+	nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
 fail_rqd_free:
 	pblk_free_rqd(pblk, rqd, PBLK_READ);
 	return ret;
@@ -514,7 +572,7 @@ static int read_ppalist_rq_gc(struct pblk *pblk, struct nvm_rq *rqd,
 		rqd->ppa_list[valid_secs++] = ppa_list_l2p[i];
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(valid_secs, &pblk->inflight_reads);
 #endif
 
@@ -548,7 +606,7 @@ static int read_rq_gc(struct pblk *pblk, struct nvm_rq *rqd,
 	rqd->ppa_addr = ppa_l2p;
 	valid_secs = 1;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_inc(&pblk->inflight_reads);
 #endif
 
@@ -595,7 +653,8 @@ int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
 	bio = pblk_bio_map_addr(pblk, gc_rq->data, gc_rq->secs_to_gc, data_len,
 						PBLK_VMALLOC_META, GFP_KERNEL);
 	if (IS_ERR(bio)) {
-		pr_err("pblk: could not allocate GC bio (%lu)\n", PTR_ERR(bio));
+		pblk_err(pblk, "could not allocate GC bio (%lu)\n",
+				PTR_ERR(bio));
 		goto err_free_dma;
 	}
 
@@ -609,7 +668,7 @@ int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
 
 	if (pblk_submit_io_sync(pblk, &rqd)) {
 		ret = -EIO;
-		pr_err("pblk: GC read request failed\n");
+		pblk_err(pblk, "GC read request failed\n");
 		goto err_free_bio;
 	}
 
@@ -619,12 +678,12 @@ int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
 
 	if (rqd.error) {
 		atomic_long_inc(&pblk->read_failed_gc);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 		pblk_print_failed_rqd(pblk, &rqd, rqd.error);
 #endif
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(gc_rq->secs_to_gc, &pblk->sync_reads);
 	atomic_long_add(gc_rq->secs_to_gc, &pblk->recov_gc_reads);
 	atomic_long_sub(gc_rq->secs_to_gc, &pblk->inflight_reads);
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index 3a5069183859..e232e47e1353 100644
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -77,7 +77,7 @@ static int pblk_recov_l2p_from_emeta(struct pblk *pblk, struct pblk_line *line)
 	}
 
 	if (nr_valid_lbas != nr_lbas)
-		pr_err("pblk: line %d - inconsistent lba list(%llu/%llu)\n",
+		pblk_err(pblk, "line %d - inconsistent lba list(%llu/%llu)\n",
 				line->id, nr_valid_lbas, nr_lbas);
 
 	line->left_msecs = 0;
@@ -184,7 +184,7 @@ next_read_rq:
 	/* If read fails, more padding is needed */
 	ret = pblk_submit_io_sync(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "I/O submission failed: %d\n", ret);
 		return ret;
 	}
 
@@ -194,7 +194,7 @@ next_read_rq:
 	 * we cannot recover from here. Need FTL log.
 	 */
 	if (rqd->error && rqd->error != NVM_RSP_WARN_HIGHECC) {
-		pr_err("pblk: L2P recovery failed (%d)\n", rqd->error);
+		pblk_err(pblk, "L2P recovery failed (%d)\n", rqd->error);
 		return -EINTR;
 	}
 
@@ -273,7 +273,7 @@ static int pblk_recov_pad_oob(struct pblk *pblk, struct pblk_line *line,
 next_pad_rq:
 	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
 	if (rq_ppas < pblk->min_write_pgs) {
-		pr_err("pblk: corrupted pad line %d\n", line->id);
+		pblk_err(pblk, "corrupted pad line %d\n", line->id);
 		goto fail_free_pad;
 	}
 
@@ -342,7 +342,7 @@ next_pad_rq:
 
 	ret = pblk_submit_io(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "I/O submission failed: %d\n", ret);
 		pblk_up_page(pblk, rqd->ppa_list, rqd->nr_ppas);
 		goto fail_free_bio;
 	}
@@ -356,12 +356,12 @@ next_pad_rq:
 
 	if (!wait_for_completion_io_timeout(&pad_rq->wait,
 				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
-		pr_err("pblk: pad write timed out\n");
+		pblk_err(pblk, "pad write timed out\n");
 		ret = -ETIME;
 	}
 
 	if (!pblk_line_is_full(line))
-		pr_err("pblk: corrupted padded line: %d\n", line->id);
+		pblk_err(pblk, "corrupted padded line: %d\n", line->id);
 
 	vfree(data);
 free_rq:
@@ -461,7 +461,7 @@ next_rq:
 
 	ret = pblk_submit_io_sync(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "I/O submission failed: %d\n", ret);
 		return ret;
 	}
 
@@ -501,11 +501,11 @@ next_rq:
 
 		ret = pblk_recov_pad_oob(pblk, line, pad_secs);
 		if (ret)
-			pr_err("pblk: OOB padding failed (err:%d)\n", ret);
+			pblk_err(pblk, "OOB padding failed (err:%d)\n", ret);
 
 		ret = pblk_recov_read_oob(pblk, line, p, r_ptr);
 		if (ret)
-			pr_err("pblk: OOB read failed (err:%d)\n", ret);
+			pblk_err(pblk, "OOB read failed (err:%d)\n", ret);
 
 		left_ppas = 0;
 	}
@@ -592,7 +592,7 @@ next_rq:
 
 	ret = pblk_submit_io_sync(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "I/O submission failed: %d\n", ret);
 		bio_put(bio);
 		return ret;
 	}
@@ -671,14 +671,14 @@ static int pblk_recov_l2p_from_oob(struct pblk *pblk, struct pblk_line *line)
 
 	ret = pblk_recov_scan_oob(pblk, line, p, &done);
 	if (ret) {
-		pr_err("pblk: could not recover L2P from OOB\n");
+		pblk_err(pblk, "could not recover L2P from OOB\n");
 		goto out;
 	}
 
 	if (!done) {
 		ret = pblk_recov_scan_all_oob(pblk, line, p);
 		if (ret) {
-			pr_err("pblk: could not recover L2P from OOB\n");
+			pblk_err(pblk, "could not recover L2P from OOB\n");
 			goto out;
 		}
 	}
@@ -737,14 +737,15 @@ static int pblk_recov_check_line_version(struct pblk *pblk,
 	struct line_header *header = &emeta->header;
 
 	if (header->version_major != EMETA_VERSION_MAJOR) {
-		pr_err("pblk: line major version mismatch: %d, expected: %d\n",
-		       header->version_major, EMETA_VERSION_MAJOR);
+		pblk_err(pblk, "line major version mismatch: %d, expected: %d\n",
+			 header->version_major, EMETA_VERSION_MAJOR);
 		return 1;
 	}
 
-#ifdef NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	if (header->version_minor > EMETA_VERSION_MINOR)
-		pr_info("pblk: newer line minor version found: %d\n", line_v);
+		pblk_info(pblk, "newer line minor version found: %d\n",
+				header->version_minor);
 #endif
 
 	return 0;
@@ -851,7 +852,7 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
 			continue;
 
 		if (smeta_buf->header.version_major != SMETA_VERSION_MAJOR) {
-			pr_err("pblk: found incompatible line version %u\n",
+			pblk_err(pblk, "found incompatible line version %u\n",
 					smeta_buf->header.version_major);
 			return ERR_PTR(-EINVAL);
 		}
@@ -863,7 +864,7 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
 		}
 
 		if (memcmp(pblk->instance_uuid, smeta_buf->header.uuid, 16)) {
-			pr_debug("pblk: ignore line %u due to uuid mismatch\n",
+			pblk_debug(pblk, "ignore line %u due to uuid mismatch\n",
 					i);
 			continue;
 		}
@@ -887,7 +888,7 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
 
 		pblk_recov_line_add_ordered(&recov_list, line);
 		found_lines++;
-		pr_debug("pblk: recovering data line %d, seq:%llu\n",
+		pblk_debug(pblk, "recovering data line %d, seq:%llu\n",
 						line->id, smeta_buf->seq_nr);
 	}
 
@@ -947,7 +948,7 @@ next:
 			line->emeta = NULL;
 		} else {
 			if (open_lines > 1)
-				pr_err("pblk: failed to recover L2P\n");
+				pblk_err(pblk, "failed to recover L2P\n");
 
 			open_lines++;
 			line->meta_line = meta_line;
@@ -976,7 +977,7 @@ next:
 
 out:
 	if (found_lines != recovered_lines)
-		pr_err("pblk: failed to recover all found lines %d/%d\n",
+		pblk_err(pblk, "failed to recover all found lines %d/%d\n",
 						found_lines, recovered_lines);
 
 	return data_line;
@@ -999,7 +1000,7 @@ int pblk_recov_pad(struct pblk *pblk)
 
 	ret = pblk_recov_pad_oob(pblk, line, left_msecs);
 	if (ret) {
-		pr_err("pblk: Tear down padding failed (%d)\n", ret);
+		pblk_err(pblk, "tear down padding failed (%d)\n", ret);
 		return ret;
 	}
 
diff --git a/drivers/lightnvm/pblk-sysfs.c b/drivers/lightnvm/pblk-sysfs.c
index 88a0a7c407aa..9fc3dfa168b4 100644
--- a/drivers/lightnvm/pblk-sysfs.c
+++ b/drivers/lightnvm/pblk-sysfs.c
@@ -268,7 +268,7 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
 	spin_unlock(&l_mg->free_lock);
 
 	if (nr_free_lines != free_line_cnt)
-		pr_err("pblk: corrupted free line list:%d/%d\n",
+		pblk_err(pblk, "corrupted free line list:%d/%d\n",
 						nr_free_lines, free_line_cnt);
 
 	sz = snprintf(page, PAGE_SIZE - sz,
@@ -421,7 +421,7 @@ static ssize_t pblk_sysfs_get_padding_dist(struct pblk *pblk, char *page)
 	return sz;
 }
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 static ssize_t pblk_sysfs_stats_debug(struct pblk *pblk, char *page)
 {
 	return snprintf(page, PAGE_SIZE,
@@ -598,7 +598,7 @@ static struct attribute sys_padding_dist = {
 	.mode = 0644,
 };
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 static struct attribute sys_stats_debug_attr = {
 	.name = "stats",
 	.mode = 0444,
@@ -619,7 +619,7 @@ static struct attribute *pblk_attrs[] = {
 	&sys_write_amp_mileage,
 	&sys_write_amp_trip,
 	&sys_padding_dist,
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	&sys_stats_debug_attr,
 #endif
 	NULL,
@@ -654,7 +654,7 @@ static ssize_t pblk_sysfs_show(struct kobject *kobj, struct attribute *attr,
 		return pblk_sysfs_get_write_amp_trip(pblk, buf);
 	else if (strcmp(attr->name, "padding_dist") == 0)
 		return pblk_sysfs_get_padding_dist(pblk, buf);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	else if (strcmp(attr->name, "stats") == 0)
 		return pblk_sysfs_stats_debug(pblk, buf);
 #endif
@@ -697,8 +697,7 @@ int pblk_sysfs_init(struct gendisk *tdisk)
 					kobject_get(&parent_dev->kobj),
 					"%s", "pblk");
 	if (ret) {
-		pr_err("pblk: could not register %s/pblk\n",
-						tdisk->disk_name);
+		pblk_err(pblk, "could not register\n");
 		return ret;
 	}
 
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index f353e52941f5..ee774a86cf1e 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -38,7 +38,7 @@ static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd,
 			/* Release flags on context. Protect from writes */
 			smp_store_release(&w_ctx->flags, flags);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			atomic_dec(&rwb->inflight_flush_point);
 #endif
 		}
@@ -51,7 +51,7 @@ static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd,
 		pblk_bio_free_pages(pblk, rqd->bio, c_ctx->nr_valid,
 							c_ctx->nr_padded);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(rqd->nr_ppas, &pblk->sync_writes);
 #endif
 
@@ -78,7 +78,7 @@ static void pblk_complete_write(struct pblk *pblk, struct nvm_rq *rqd,
 	unsigned long flags;
 	unsigned long pos;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_sub(c_ctx->nr_valid, &pblk->inflight_writes);
 #endif
 
@@ -196,7 +196,7 @@ static void pblk_queue_resubmit(struct pblk *pblk, struct pblk_c_ctx *c_ctx)
 	list_add_tail(&r_ctx->list, &pblk->resubmit_list);
 	spin_unlock(&pblk->resubmit_lock);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(c_ctx->nr_valid, &pblk->recov_writes);
 #endif
 }
@@ -238,7 +238,7 @@ static void pblk_end_w_fail(struct pblk *pblk, struct nvm_rq *rqd)
 
 	recovery = mempool_alloc(&pblk->rec_pool, GFP_ATOMIC);
 	if (!recovery) {
-		pr_err("pblk: could not allocate recovery work\n");
+		pblk_err(pblk, "could not allocate recovery work\n");
 		return;
 	}
 
@@ -258,7 +258,7 @@ static void pblk_end_io_write(struct nvm_rq *rqd)
 		pblk_end_w_fail(pblk, rqd);
 		return;
 	}
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	else
 		WARN_ONCE(rqd->bio->bi_status, "pblk: corrupted write error\n");
 #endif
@@ -279,7 +279,7 @@ static void pblk_end_io_write_meta(struct nvm_rq *rqd)
 
 	if (rqd->error) {
 		pblk_log_write_err(pblk, rqd);
-		pr_err("pblk: metadata I/O failed. Line %d\n", line->id);
+		pblk_err(pblk, "metadata I/O failed. Line %d\n", line->id);
 		line->w_err_gc->has_write_err = 1;
 	}
 
@@ -356,11 +356,11 @@ static int pblk_calc_secs_to_sync(struct pblk *pblk, unsigned int secs_avail,
 
 	secs_to_sync = pblk_calc_secs(pblk, secs_avail, secs_to_flush);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	if ((!secs_to_sync && secs_to_flush)
 			|| (secs_to_sync < 0)
 			|| (secs_to_sync > secs_avail && !secs_to_flush)) {
-		pr_err("pblk: bad sector calculation (a:%d,s:%d,f:%d)\n",
+		pblk_err(pblk, "bad sector calculation (a:%d,s:%d,f:%d)\n",
 				secs_avail, secs_to_sync, secs_to_flush);
 	}
 #endif
@@ -397,7 +397,7 @@ int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line)
 	bio = pblk_bio_map_addr(pblk, data, rq_ppas, rq_len,
 					l_mg->emeta_alloc_type, GFP_KERNEL);
 	if (IS_ERR(bio)) {
-		pr_err("pblk: failed to map emeta io");
+		pblk_err(pblk, "failed to map emeta io");
 		ret = PTR_ERR(bio);
 		goto fail_free_rqd;
 	}
@@ -428,7 +428,7 @@ int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line)
 
 	ret = pblk_submit_io(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: emeta I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "emeta I/O submission failed: %d\n", ret);
 		goto fail_rollback;
 	}
 
@@ -518,7 +518,7 @@ static int pblk_submit_io_set(struct pblk *pblk, struct nvm_rq *rqd)
 	/* Assign lbas to ppas and populate request structure */
 	err = pblk_setup_w_rq(pblk, rqd, &erase_ppa);
 	if (err) {
-		pr_err("pblk: could not setup write request: %d\n", err);
+		pblk_err(pblk, "could not setup write request: %d\n", err);
 		return NVM_IO_ERR;
 	}
 
@@ -527,7 +527,7 @@ static int pblk_submit_io_set(struct pblk *pblk, struct nvm_rq *rqd)
 	/* Submit data write for current data line */
 	err = pblk_submit_io(pblk, rqd);
 	if (err) {
-		pr_err("pblk: data I/O submission failed: %d\n", err);
+		pblk_err(pblk, "data I/O submission failed: %d\n", err);
 		return NVM_IO_ERR;
 	}
 
@@ -549,7 +549,8 @@ static int pblk_submit_io_set(struct pblk *pblk, struct nvm_rq *rqd)
 		/* Submit metadata write for previous data line */
 		err = pblk_submit_meta_io(pblk, meta_line);
 		if (err) {
-			pr_err("pblk: metadata I/O submission failed: %d", err);
+			pblk_err(pblk, "metadata I/O submission failed: %d",
+					err);
 			return NVM_IO_ERR;
 		}
 	}
@@ -614,7 +615,7 @@ static int pblk_submit_write(struct pblk *pblk)
 		secs_to_sync = pblk_calc_secs_to_sync(pblk, secs_avail,
 					secs_to_flush);
 		if (secs_to_sync > pblk->max_write_pgs) {
-			pr_err("pblk: bad buffer sync calculation\n");
+			pblk_err(pblk, "bad buffer sync calculation\n");
 			return 1;
 		}
 
@@ -633,14 +634,14 @@ static int pblk_submit_write(struct pblk *pblk)
 
 	if (pblk_rb_read_to_bio(&pblk->rwb, rqd, pos, secs_to_sync,
 								secs_avail)) {
-		pr_err("pblk: corrupted write bio\n");
+		pblk_err(pblk, "corrupted write bio\n");
 		goto fail_put_bio;
 	}
 
 	if (pblk_submit_io_set(pblk, rqd))
 		goto fail_free_bio;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(secs_to_sync, &pblk->sub_writes);
 #endif
 
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 34cc1d64a9d4..4760af7b6499 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -119,6 +119,16 @@ struct pblk_g_ctx {
 	u64 lba;
 };
 
+/* partial read context */
+struct pblk_pr_ctx {
+	struct bio *orig_bio;
+	DECLARE_BITMAP(bitmap, NVM_MAX_VLBA);
+	unsigned int orig_nr_secs;
+	unsigned int bio_init_idx;
+	void *ppa_ptr;
+	dma_addr_t dma_ppa_list;
+};
+
 /* Pad context */
 struct pblk_pad_rq {
 	struct pblk *pblk;
@@ -193,7 +203,7 @@ struct pblk_rb {
 	spinlock_t w_lock;		/* Write lock */
 	spinlock_t s_lock;		/* Sync lock */
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_t inflight_flush_point;	/* Not served REQ_FLUSH | REQ_FUA */
 #endif
 };
@@ -608,9 +618,6 @@ struct pblk {
 
 	int min_write_pgs; /* Minimum amount of pages required by controller */
 	int max_write_pgs; /* Maximum amount of pages supported by controller */
-	int pgs_in_buffer; /* Number of pages that need to be held in buffer to
-			    * guarantee successful reads.
-			    */
 
 	sector_t capacity; /* Device capacity when bad blocks are subtracted */
 
@@ -639,7 +646,7 @@ struct pblk {
 	u64 nr_flush_rst;		/* Flushes reset value for pad dist.*/
 	atomic64_t nr_flush;		/* Number of flush/fua I/O */
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Non-persistent debug counters, 4kb sector I/Os */
 	atomic_long_t inflight_writes;	/* Inflight writes (user and gc) */
 	atomic_long_t padded_writes;	/* Sectors padded due to flush/fua */
@@ -706,6 +713,15 @@ struct pblk_line_ws {
 #define pblk_g_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_g_ctx))
 #define pblk_w_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_c_ctx))
 
+#define pblk_err(pblk, fmt, ...)			\
+	pr_err("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
+#define pblk_info(pblk, fmt, ...)			\
+	pr_info("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
+#define pblk_warn(pblk, fmt, ...)			\
+	pr_warn("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
+#define pblk_debug(pblk, fmt, ...)			\
+	pr_debug("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
+
 /*
  * pblk ring buffer operations
  */
@@ -1282,20 +1298,22 @@ static inline int pblk_io_aligned(struct pblk *pblk, int nr_secs)
 	return !(nr_secs % pblk->min_write_pgs);
 }
 
-#ifdef CONFIG_NVM_DEBUG
-static inline void print_ppa(struct nvm_geo *geo, struct ppa_addr *p,
+#ifdef CONFIG_NVM_PBLK_DEBUG
+static inline void print_ppa(struct pblk *pblk, struct ppa_addr *p,
 			     char *msg, int error)
 {
+	struct nvm_geo *geo = &pblk->dev->geo;
+
 	if (p->c.is_cached) {
-		pr_err("ppa: (%s: %x) cache line: %llu\n",
+		pblk_err(pblk, "ppa: (%s: %x) cache line: %llu\n",
 				msg, error, (u64)p->c.line);
 	} else if (geo->version == NVM_OCSSD_SPEC_12) {
-		pr_err("ppa: (%s: %x):ch:%d,lun:%d,blk:%d,pg:%d,pl:%d,sec:%d\n",
+		pblk_err(pblk, "ppa: (%s: %x):ch:%d,lun:%d,blk:%d,pg:%d,pl:%d,sec:%d\n",
 			msg, error,
 			p->g.ch, p->g.lun, p->g.blk,
 			p->g.pg, p->g.pl, p->g.sec);
 	} else {
-		pr_err("ppa: (%s: %x):ch:%d,lun:%d,chk:%d,sec:%d\n",
+		pblk_err(pblk, "ppa: (%s: %x):ch:%d,lun:%d,chk:%d,sec:%d\n",
 			msg, error,
 			p->m.grp, p->m.pu, p->m.chk, p->m.sec);
 	}
@@ -1307,16 +1325,16 @@ static inline void pblk_print_failed_rqd(struct pblk *pblk, struct nvm_rq *rqd,
 	int bit = -1;
 
 	if (rqd->nr_ppas ==  1) {
-		print_ppa(&pblk->dev->geo, &rqd->ppa_addr, "rqd", error);
+		print_ppa(pblk, &rqd->ppa_addr, "rqd", error);
 		return;
 	}
 
 	while ((bit = find_next_bit((void *)&rqd->ppa_status, rqd->nr_ppas,
 						bit + 1)) < rqd->nr_ppas) {
-		print_ppa(&pblk->dev->geo, &rqd->ppa_list[bit], "rqd", error);
+		print_ppa(pblk, &rqd->ppa_list[bit], "rqd", error);
 	}
 
-	pr_err("error:%d, ppa_status:%llx\n", error, rqd->ppa_status);
+	pblk_err(pblk, "error:%d, ppa_status:%llx\n", error, rqd->ppa_status);
 }
 
 static inline int pblk_boundary_ppa_checks(struct nvm_tgt_dev *tgt_dev,
@@ -1347,7 +1365,7 @@ static inline int pblk_boundary_ppa_checks(struct nvm_tgt_dev *tgt_dev,
 				continue;
 		}
 
-		print_ppa(geo, ppa, "boundary", i);
+		print_ppa(tgt_dev->q->queuedata, ppa, "boundary", i);
 
 		return 1;
 	}
@@ -1377,7 +1395,7 @@ static inline int pblk_check_io(struct pblk *pblk, struct nvm_rq *rqd)
 
 			spin_lock(&line->lock);
 			if (line->state != PBLK_LINESTATE_OPEN) {
-				pr_err("pblk: bad ppa: line:%d,state:%d\n",
+				pblk_err(pblk, "bad ppa: line:%d,state:%d\n",
 							line->id, line->state);
 				WARN_ON(1);
 				spin_unlock(&line->lock);
diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig
index e63d29a95e76..841c005d8ebb 100644
--- a/drivers/mailbox/Kconfig
+++ b/drivers/mailbox/Kconfig
@@ -15,6 +15,12 @@ config ARM_MHU
 	  The controller has 3 mailbox channels, the last of which can be
 	  used in Secure mode only.
 
+config IMX_MBOX
+	tristate "i.MX Mailbox"
+	depends on ARCH_MXC || COMPILE_TEST
+	help
+	  Mailbox implementation for i.MX Messaging Unit (MU).
+
 config PLATFORM_MHU
 	tristate "Platform MHU Mailbox"
 	depends on OF
@@ -189,4 +195,14 @@ config STM32_IPCC
 	  Mailbox implementation for STMicroelectonics STM32 family chips
 	  with hardware for Inter-Processor Communication Controller (IPCC)
 	  between processors. Say Y here if you want to have this support.
+
+config MTK_CMDQ_MBOX
+	tristate "MediaTek CMDQ Mailbox Support"
+	depends on ARCH_MEDIATEK || COMPILE_TEST
+	select MTK_INFRACFG
+	help
+	  Say yes here to add support for the MediaTek Command Queue (CMDQ)
+	  mailbox driver. The CMDQ is used to help read/write registers with
+	  critical time limitation, such as updating display configuration
+	  during the vblank.
 endif
diff --git a/drivers/mailbox/Makefile b/drivers/mailbox/Makefile
index 4d501bea7863..c818b5d011ae 100644
--- a/drivers/mailbox/Makefile
+++ b/drivers/mailbox/Makefile
@@ -7,6 +7,8 @@ obj-$(CONFIG_MAILBOX_TEST)	+= mailbox-test.o
 
 obj-$(CONFIG_ARM_MHU)	+= arm_mhu.o
 
+obj-$(CONFIG_IMX_MBOX)	+= imx-mailbox.o
+
 obj-$(CONFIG_PLATFORM_MHU)	+= platform_mhu.o
 
 obj-$(CONFIG_PL320_MBOX)	+= pl320-ipc.o
@@ -40,3 +42,5 @@ obj-$(CONFIG_QCOM_APCS_IPC)	+= qcom-apcs-ipc-mailbox.o
 obj-$(CONFIG_TEGRA_HSP_MBOX)	+= tegra-hsp.o
 
 obj-$(CONFIG_STM32_IPCC) 	+= stm32-ipcc.o
+
+obj-$(CONFIG_MTK_CMDQ_MBOX)	+= mtk-cmdq-mailbox.o
diff --git a/drivers/mailbox/imx-mailbox.c b/drivers/mailbox/imx-mailbox.c
new file mode 100644
index 000000000000..363d35d5e49d
--- /dev/null
+++ b/drivers/mailbox/imx-mailbox.c
@@ -0,0 +1,358 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 Pengutronix, Oleksij Rempel <o.rempel@pengutronix.de>
+ */
+
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/mailbox_controller.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/slab.h>
+
+/* Transmit Register */
+#define IMX_MU_xTRn(x)		(0x00 + 4 * (x))
+/* Receive Register */
+#define IMX_MU_xRRn(x)		(0x10 + 4 * (x))
+/* Status Register */
+#define IMX_MU_xSR		0x20
+#define IMX_MU_xSR_GIPn(x)	BIT(28 + (3 - (x)))
+#define IMX_MU_xSR_RFn(x)	BIT(24 + (3 - (x)))
+#define IMX_MU_xSR_TEn(x)	BIT(20 + (3 - (x)))
+#define IMX_MU_xSR_BRDIP	BIT(9)
+
+/* Control Register */
+#define IMX_MU_xCR		0x24
+/* General Purpose Interrupt Enable */
+#define IMX_MU_xCR_GIEn(x)	BIT(28 + (3 - (x)))
+/* Receive Interrupt Enable */
+#define IMX_MU_xCR_RIEn(x)	BIT(24 + (3 - (x)))
+/* Transmit Interrupt Enable */
+#define IMX_MU_xCR_TIEn(x)	BIT(20 + (3 - (x)))
+/* General Purpose Interrupt Request */
+#define IMX_MU_xCR_GIRn(x)	BIT(16 + (3 - (x)))
+
+#define IMX_MU_CHANS		16
+#define IMX_MU_CHAN_NAME_SIZE	20
+
+enum imx_mu_chan_type {
+	IMX_MU_TYPE_TX,		/* Tx */
+	IMX_MU_TYPE_RX,		/* Rx */
+	IMX_MU_TYPE_TXDB,	/* Tx doorbell */
+	IMX_MU_TYPE_RXDB,	/* Rx doorbell */
+};
+
+struct imx_mu_con_priv {
+	unsigned int		idx;
+	char			irq_desc[IMX_MU_CHAN_NAME_SIZE];
+	enum imx_mu_chan_type	type;
+	struct mbox_chan	*chan;
+	struct tasklet_struct	txdb_tasklet;
+};
+
+struct imx_mu_priv {
+	struct device		*dev;
+	void __iomem		*base;
+	spinlock_t		xcr_lock; /* control register lock */
+
+	struct mbox_controller	mbox;
+	struct mbox_chan	mbox_chans[IMX_MU_CHANS];
+
+	struct imx_mu_con_priv  con_priv[IMX_MU_CHANS];
+	struct clk		*clk;
+	int			irq;
+
+	bool			side_b;
+};
+
+static struct imx_mu_priv *to_imx_mu_priv(struct mbox_controller *mbox)
+{
+	return container_of(mbox, struct imx_mu_priv, mbox);
+}
+
+static void imx_mu_write(struct imx_mu_priv *priv, u32 val, u32 offs)
+{
+	iowrite32(val, priv->base + offs);
+}
+
+static u32 imx_mu_read(struct imx_mu_priv *priv, u32 offs)
+{
+	return ioread32(priv->base + offs);
+}
+
+static u32 imx_mu_xcr_rmw(struct imx_mu_priv *priv, u32 set, u32 clr)
+{
+	unsigned long flags;
+	u32 val;
+
+	spin_lock_irqsave(&priv->xcr_lock, flags);
+	val = imx_mu_read(priv, IMX_MU_xCR);
+	val &= ~clr;
+	val |= set;
+	imx_mu_write(priv, val, IMX_MU_xCR);
+	spin_unlock_irqrestore(&priv->xcr_lock, flags);
+
+	return val;
+}
+
+static void imx_mu_txdb_tasklet(unsigned long data)
+{
+	struct imx_mu_con_priv *cp = (struct imx_mu_con_priv *)data;
+
+	mbox_chan_txdone(cp->chan, 0);
+}
+
+static irqreturn_t imx_mu_isr(int irq, void *p)
+{
+	struct mbox_chan *chan = p;
+	struct imx_mu_priv *priv = to_imx_mu_priv(chan->mbox);
+	struct imx_mu_con_priv *cp = chan->con_priv;
+	u32 val, ctrl, dat;
+
+	ctrl = imx_mu_read(priv, IMX_MU_xCR);
+	val = imx_mu_read(priv, IMX_MU_xSR);
+
+	switch (cp->type) {
+	case IMX_MU_TYPE_TX:
+		val &= IMX_MU_xSR_TEn(cp->idx) &
+			(ctrl & IMX_MU_xCR_TIEn(cp->idx));
+		break;
+	case IMX_MU_TYPE_RX:
+		val &= IMX_MU_xSR_RFn(cp->idx) &
+			(ctrl & IMX_MU_xCR_RIEn(cp->idx));
+		break;
+	case IMX_MU_TYPE_RXDB:
+		val &= IMX_MU_xSR_GIPn(cp->idx) &
+			(ctrl & IMX_MU_xCR_GIEn(cp->idx));
+		break;
+	default:
+		break;
+	}
+
+	if (!val)
+		return IRQ_NONE;
+
+	if (val == IMX_MU_xSR_TEn(cp->idx)) {
+		imx_mu_xcr_rmw(priv, 0, IMX_MU_xCR_TIEn(cp->idx));
+		mbox_chan_txdone(chan, 0);
+	} else if (val == IMX_MU_xSR_RFn(cp->idx)) {
+		dat = imx_mu_read(priv, IMX_MU_xRRn(cp->idx));
+		mbox_chan_received_data(chan, (void *)&dat);
+	} else if (val == IMX_MU_xSR_GIPn(cp->idx)) {
+		imx_mu_write(priv, IMX_MU_xSR_GIPn(cp->idx), IMX_MU_xSR);
+		mbox_chan_received_data(chan, NULL);
+	} else {
+		dev_warn_ratelimited(priv->dev, "Not handled interrupt\n");
+		return IRQ_NONE;
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int imx_mu_send_data(struct mbox_chan *chan, void *data)
+{
+	struct imx_mu_priv *priv = to_imx_mu_priv(chan->mbox);
+	struct imx_mu_con_priv *cp = chan->con_priv;
+	u32 *arg = data;
+
+	switch (cp->type) {
+	case IMX_MU_TYPE_TX:
+		imx_mu_write(priv, *arg, IMX_MU_xTRn(cp->idx));
+		imx_mu_xcr_rmw(priv, IMX_MU_xCR_TIEn(cp->idx), 0);
+		break;
+	case IMX_MU_TYPE_TXDB:
+		imx_mu_xcr_rmw(priv, IMX_MU_xCR_GIRn(cp->idx), 0);
+		tasklet_schedule(&cp->txdb_tasklet);
+		break;
+	default:
+		dev_warn_ratelimited(priv->dev, "Send data on wrong channel type: %d\n", cp->type);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int imx_mu_startup(struct mbox_chan *chan)
+{
+	struct imx_mu_priv *priv = to_imx_mu_priv(chan->mbox);
+	struct imx_mu_con_priv *cp = chan->con_priv;
+	int ret;
+
+	if (cp->type == IMX_MU_TYPE_TXDB) {
+		/* Tx doorbell don't have ACK support */
+		tasklet_init(&cp->txdb_tasklet, imx_mu_txdb_tasklet,
+			     (unsigned long)cp);
+		return 0;
+	}
+
+	ret = request_irq(priv->irq, imx_mu_isr, IRQF_SHARED, cp->irq_desc,
+			  chan);
+	if (ret) {
+		dev_err(priv->dev,
+			"Unable to acquire IRQ %d\n", priv->irq);
+		return ret;
+	}
+
+	switch (cp->type) {
+	case IMX_MU_TYPE_RX:
+		imx_mu_xcr_rmw(priv, IMX_MU_xCR_RIEn(cp->idx), 0);
+		break;
+	case IMX_MU_TYPE_RXDB:
+		imx_mu_xcr_rmw(priv, IMX_MU_xCR_GIEn(cp->idx), 0);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static void imx_mu_shutdown(struct mbox_chan *chan)
+{
+	struct imx_mu_priv *priv = to_imx_mu_priv(chan->mbox);
+	struct imx_mu_con_priv *cp = chan->con_priv;
+
+	if (cp->type == IMX_MU_TYPE_TXDB)
+		tasklet_kill(&cp->txdb_tasklet);
+
+	imx_mu_xcr_rmw(priv, 0,
+		   IMX_MU_xCR_TIEn(cp->idx) | IMX_MU_xCR_RIEn(cp->idx));
+
+	free_irq(priv->irq, chan);
+}
+
+static const struct mbox_chan_ops imx_mu_ops = {
+	.send_data = imx_mu_send_data,
+	.startup = imx_mu_startup,
+	.shutdown = imx_mu_shutdown,
+};
+
+static struct mbox_chan * imx_mu_xlate(struct mbox_controller *mbox,
+				       const struct of_phandle_args *sp)
+{
+	u32 type, idx, chan;
+
+	if (sp->args_count != 2) {
+		dev_err(mbox->dev, "Invalid argument count %d\n", sp->args_count);
+		return ERR_PTR(-EINVAL);
+	}
+
+	type = sp->args[0]; /* channel type */
+	idx = sp->args[1]; /* index */
+	chan = type * 4 + idx;
+
+	if (chan >= mbox->num_chans) {
+		dev_err(mbox->dev, "Not supported channel number: %d. (type: %d, idx: %d)\n", chan, type, idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return &mbox->chans[chan];
+}
+
+static void imx_mu_init_generic(struct imx_mu_priv *priv)
+{
+	if (priv->side_b)
+		return;
+
+	/* Set default MU configuration */
+	imx_mu_write(priv, 0, IMX_MU_xCR);
+}
+
+static int imx_mu_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct resource *iomem;
+	struct imx_mu_priv *priv;
+	unsigned int i;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->dev = dev;
+
+	iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	priv->base = devm_ioremap_resource(&pdev->dev, iomem);
+	if (IS_ERR(priv->base))
+		return PTR_ERR(priv->base);
+
+	priv->irq = platform_get_irq(pdev, 0);
+	if (priv->irq < 0)
+		return priv->irq;
+
+	priv->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(priv->clk)) {
+		if (PTR_ERR(priv->clk) != -ENOENT)
+			return PTR_ERR(priv->clk);
+
+		priv->clk = NULL;
+	}
+
+	ret = clk_prepare_enable(priv->clk);
+	if (ret) {
+		dev_err(dev, "Failed to enable clock\n");
+		return ret;
+	}
+
+	for (i = 0; i < IMX_MU_CHANS; i++) {
+		struct imx_mu_con_priv *cp = &priv->con_priv[i];
+
+		cp->idx = i % 4;
+		cp->type = i >> 2;
+		cp->chan = &priv->mbox_chans[i];
+		priv->mbox_chans[i].con_priv = cp;
+		snprintf(cp->irq_desc, sizeof(cp->irq_desc),
+			 "imx_mu_chan[%i-%i]", cp->type, cp->idx);
+	}
+
+	priv->side_b = of_property_read_bool(np, "fsl,mu-side-b");
+
+	spin_lock_init(&priv->xcr_lock);
+
+	priv->mbox.dev = dev;
+	priv->mbox.ops = &imx_mu_ops;
+	priv->mbox.chans = priv->mbox_chans;
+	priv->mbox.num_chans = IMX_MU_CHANS;
+	priv->mbox.of_xlate = imx_mu_xlate;
+	priv->mbox.txdone_irq = true;
+
+	platform_set_drvdata(pdev, priv);
+
+	imx_mu_init_generic(priv);
+
+	return mbox_controller_register(&priv->mbox);
+}
+
+static int imx_mu_remove(struct platform_device *pdev)
+{
+	struct imx_mu_priv *priv = platform_get_drvdata(pdev);
+
+	mbox_controller_unregister(&priv->mbox);
+	clk_disable_unprepare(priv->clk);
+
+	return 0;
+}
+
+static const struct of_device_id imx_mu_dt_ids[] = {
+	{ .compatible = "fsl,imx6sx-mu" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, imx_mu_dt_ids);
+
+static struct platform_driver imx_mu_driver = {
+	.probe		= imx_mu_probe,
+	.remove		= imx_mu_remove,
+	.driver = {
+		.name	= "imx_mu",
+		.of_match_table = imx_mu_dt_ids,
+	},
+};
+module_platform_driver(imx_mu_driver);
+
+MODULE_AUTHOR("Oleksij Rempel <o.rempel@pengutronix.de>");
+MODULE_DESCRIPTION("Message Unit driver for i.MX");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mailbox/mailbox-xgene-slimpro.c b/drivers/mailbox/mailbox-xgene-slimpro.c
index a7040163dd43..b8b2b3533f46 100644
--- a/drivers/mailbox/mailbox-xgene-slimpro.c
+++ b/drivers/mailbox/mailbox-xgene-slimpro.c
@@ -195,9 +195,9 @@ static int slimpro_mbox_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, ctx);
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	mb_base = devm_ioremap(&pdev->dev, regs->start, resource_size(regs));
-	if (!mb_base)
-		return -ENOMEM;
+	mb_base = devm_ioremap_resource(&pdev->dev, regs);
+	if (IS_ERR(mb_base))
+		return PTR_ERR(mb_base);
 
 	/* Setup mailbox links */
 	for (i = 0; i < MBOX_CNT; i++) {
diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c
new file mode 100644
index 000000000000..aec46d5d3506
--- /dev/null
+++ b/drivers/mailbox/mtk-cmdq-mailbox.c
@@ -0,0 +1,571 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2018 MediaTek Inc.
+
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/dma-mapping.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/mailbox_controller.h>
+#include <linux/mailbox/mtk-cmdq-mailbox.h>
+#include <linux/of_device.h>
+
+#define CMDQ_OP_CODE_MASK		(0xff << CMDQ_OP_CODE_SHIFT)
+#define CMDQ_IRQ_MASK			0xffff
+#define CMDQ_NUM_CMD(t)			(t->cmd_buf_size / CMDQ_INST_SIZE)
+
+#define CMDQ_CURR_IRQ_STATUS		0x10
+#define CMDQ_THR_SLOT_CYCLES		0x30
+#define CMDQ_THR_BASE			0x100
+#define CMDQ_THR_SIZE			0x80
+#define CMDQ_THR_WARM_RESET		0x00
+#define CMDQ_THR_ENABLE_TASK		0x04
+#define CMDQ_THR_SUSPEND_TASK		0x08
+#define CMDQ_THR_CURR_STATUS		0x0c
+#define CMDQ_THR_IRQ_STATUS		0x10
+#define CMDQ_THR_IRQ_ENABLE		0x14
+#define CMDQ_THR_CURR_ADDR		0x20
+#define CMDQ_THR_END_ADDR		0x24
+#define CMDQ_THR_WAIT_TOKEN		0x30
+#define CMDQ_THR_PRIORITY		0x40
+
+#define CMDQ_THR_ACTIVE_SLOT_CYCLES	0x3200
+#define CMDQ_THR_ENABLED		0x1
+#define CMDQ_THR_DISABLED		0x0
+#define CMDQ_THR_SUSPEND		0x1
+#define CMDQ_THR_RESUME			0x0
+#define CMDQ_THR_STATUS_SUSPENDED	BIT(1)
+#define CMDQ_THR_DO_WARM_RESET		BIT(0)
+#define CMDQ_THR_IRQ_DONE		0x1
+#define CMDQ_THR_IRQ_ERROR		0x12
+#define CMDQ_THR_IRQ_EN			(CMDQ_THR_IRQ_ERROR | CMDQ_THR_IRQ_DONE)
+#define CMDQ_THR_IS_WAITING		BIT(31)
+
+#define CMDQ_JUMP_BY_OFFSET		0x10000000
+#define CMDQ_JUMP_BY_PA			0x10000001
+
+struct cmdq_thread {
+	struct mbox_chan	*chan;
+	void __iomem		*base;
+	struct list_head	task_busy_list;
+	u32			priority;
+	bool			atomic_exec;
+};
+
+struct cmdq_task {
+	struct cmdq		*cmdq;
+	struct list_head	list_entry;
+	dma_addr_t		pa_base;
+	struct cmdq_thread	*thread;
+	struct cmdq_pkt		*pkt; /* the packet sent from mailbox client */
+};
+
+struct cmdq {
+	struct mbox_controller	mbox;
+	void __iomem		*base;
+	u32			irq;
+	u32			thread_nr;
+	struct cmdq_thread	*thread;
+	struct clk		*clock;
+	bool			suspended;
+};
+
+static int cmdq_thread_suspend(struct cmdq *cmdq, struct cmdq_thread *thread)
+{
+	u32 status;
+
+	writel(CMDQ_THR_SUSPEND, thread->base + CMDQ_THR_SUSPEND_TASK);
+
+	/* If already disabled, treat as suspended successful. */
+	if (!(readl(thread->base + CMDQ_THR_ENABLE_TASK) & CMDQ_THR_ENABLED))
+		return 0;
+
+	if (readl_poll_timeout_atomic(thread->base + CMDQ_THR_CURR_STATUS,
+			status, status & CMDQ_THR_STATUS_SUSPENDED, 0, 10)) {
+		dev_err(cmdq->mbox.dev, "suspend GCE thread 0x%x failed\n",
+			(u32)(thread->base - cmdq->base));
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+static void cmdq_thread_resume(struct cmdq_thread *thread)
+{
+	writel(CMDQ_THR_RESUME, thread->base + CMDQ_THR_SUSPEND_TASK);
+}
+
+static void cmdq_init(struct cmdq *cmdq)
+{
+	WARN_ON(clk_enable(cmdq->clock) < 0);
+	writel(CMDQ_THR_ACTIVE_SLOT_CYCLES, cmdq->base + CMDQ_THR_SLOT_CYCLES);
+	clk_disable(cmdq->clock);
+}
+
+static int cmdq_thread_reset(struct cmdq *cmdq, struct cmdq_thread *thread)
+{
+	u32 warm_reset;
+
+	writel(CMDQ_THR_DO_WARM_RESET, thread->base + CMDQ_THR_WARM_RESET);
+	if (readl_poll_timeout_atomic(thread->base + CMDQ_THR_WARM_RESET,
+			warm_reset, !(warm_reset & CMDQ_THR_DO_WARM_RESET),
+			0, 10)) {
+		dev_err(cmdq->mbox.dev, "reset GCE thread 0x%x failed\n",
+			(u32)(thread->base - cmdq->base));
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+static void cmdq_thread_disable(struct cmdq *cmdq, struct cmdq_thread *thread)
+{
+	cmdq_thread_reset(cmdq, thread);
+	writel(CMDQ_THR_DISABLED, thread->base + CMDQ_THR_ENABLE_TASK);
+}
+
+/* notify GCE to re-fetch commands by setting GCE thread PC */
+static void cmdq_thread_invalidate_fetched_data(struct cmdq_thread *thread)
+{
+	writel(readl(thread->base + CMDQ_THR_CURR_ADDR),
+	       thread->base + CMDQ_THR_CURR_ADDR);
+}
+
+static void cmdq_task_insert_into_thread(struct cmdq_task *task)
+{
+	struct device *dev = task->cmdq->mbox.dev;
+	struct cmdq_thread *thread = task->thread;
+	struct cmdq_task *prev_task = list_last_entry(
+			&thread->task_busy_list, typeof(*task), list_entry);
+	u64 *prev_task_base = prev_task->pkt->va_base;
+
+	/* let previous task jump to this task */
+	dma_sync_single_for_cpu(dev, prev_task->pa_base,
+				prev_task->pkt->cmd_buf_size, DMA_TO_DEVICE);
+	prev_task_base[CMDQ_NUM_CMD(prev_task->pkt) - 1] =
+		(u64)CMDQ_JUMP_BY_PA << 32 | task->pa_base;
+	dma_sync_single_for_device(dev, prev_task->pa_base,
+				   prev_task->pkt->cmd_buf_size, DMA_TO_DEVICE);
+
+	cmdq_thread_invalidate_fetched_data(thread);
+}
+
+static bool cmdq_command_is_wfe(u64 cmd)
+{
+	u64 wfe_option = CMDQ_WFE_UPDATE | CMDQ_WFE_WAIT | CMDQ_WFE_WAIT_VALUE;
+	u64 wfe_op = (u64)(CMDQ_CODE_WFE << CMDQ_OP_CODE_SHIFT) << 32;
+	u64 wfe_mask = (u64)CMDQ_OP_CODE_MASK << 32 | 0xffffffff;
+
+	return ((cmd & wfe_mask) == (wfe_op | wfe_option));
+}
+
+/* we assume tasks in the same display GCE thread are waiting the same event. */
+static void cmdq_task_remove_wfe(struct cmdq_task *task)
+{
+	struct device *dev = task->cmdq->mbox.dev;
+	u64 *base = task->pkt->va_base;
+	int i;
+
+	dma_sync_single_for_cpu(dev, task->pa_base, task->pkt->cmd_buf_size,
+				DMA_TO_DEVICE);
+	for (i = 0; i < CMDQ_NUM_CMD(task->pkt); i++)
+		if (cmdq_command_is_wfe(base[i]))
+			base[i] = (u64)CMDQ_JUMP_BY_OFFSET << 32 |
+				  CMDQ_JUMP_PASS;
+	dma_sync_single_for_device(dev, task->pa_base, task->pkt->cmd_buf_size,
+				   DMA_TO_DEVICE);
+}
+
+static bool cmdq_thread_is_in_wfe(struct cmdq_thread *thread)
+{
+	return readl(thread->base + CMDQ_THR_WAIT_TOKEN) & CMDQ_THR_IS_WAITING;
+}
+
+static void cmdq_thread_wait_end(struct cmdq_thread *thread,
+				 unsigned long end_pa)
+{
+	struct device *dev = thread->chan->mbox->dev;
+	unsigned long curr_pa;
+
+	if (readl_poll_timeout_atomic(thread->base + CMDQ_THR_CURR_ADDR,
+			curr_pa, curr_pa == end_pa, 1, 20))
+		dev_err(dev, "GCE thread cannot run to end.\n");
+}
+
+static void cmdq_task_exec_done(struct cmdq_task *task, enum cmdq_cb_status sta)
+{
+	struct cmdq_task_cb *cb = &task->pkt->async_cb;
+	struct cmdq_cb_data data;
+
+	WARN_ON(cb->cb == (cmdq_async_flush_cb)NULL);
+	data.sta = sta;
+	data.data = cb->data;
+	cb->cb(data);
+
+	list_del(&task->list_entry);
+}
+
+static void cmdq_task_handle_error(struct cmdq_task *task)
+{
+	struct cmdq_thread *thread = task->thread;
+	struct cmdq_task *next_task;
+
+	dev_err(task->cmdq->mbox.dev, "task 0x%p error\n", task);
+	WARN_ON(cmdq_thread_suspend(task->cmdq, thread) < 0);
+	next_task = list_first_entry_or_null(&thread->task_busy_list,
+			struct cmdq_task, list_entry);
+	if (next_task)
+		writel(next_task->pa_base, thread->base + CMDQ_THR_CURR_ADDR);
+	cmdq_thread_resume(thread);
+}
+
+static void cmdq_thread_irq_handler(struct cmdq *cmdq,
+				    struct cmdq_thread *thread)
+{
+	struct cmdq_task *task, *tmp, *curr_task = NULL;
+	u32 curr_pa, irq_flag, task_end_pa;
+	bool err;
+
+	irq_flag = readl(thread->base + CMDQ_THR_IRQ_STATUS);
+	writel(~irq_flag, thread->base + CMDQ_THR_IRQ_STATUS);
+
+	/*
+	 * When ISR call this function, another CPU core could run
+	 * "release task" right before we acquire the spin lock, and thus
+	 * reset / disable this GCE thread, so we need to check the enable
+	 * bit of this GCE thread.
+	 */
+	if (!(readl(thread->base + CMDQ_THR_ENABLE_TASK) & CMDQ_THR_ENABLED))
+		return;
+
+	if (irq_flag & CMDQ_THR_IRQ_ERROR)
+		err = true;
+	else if (irq_flag & CMDQ_THR_IRQ_DONE)
+		err = false;
+	else
+		return;
+
+	curr_pa = readl(thread->base + CMDQ_THR_CURR_ADDR);
+
+	list_for_each_entry_safe(task, tmp, &thread->task_busy_list,
+				 list_entry) {
+		task_end_pa = task->pa_base + task->pkt->cmd_buf_size;
+		if (curr_pa >= task->pa_base && curr_pa < task_end_pa)
+			curr_task = task;
+
+		if (!curr_task || curr_pa == task_end_pa - CMDQ_INST_SIZE) {
+			cmdq_task_exec_done(task, CMDQ_CB_NORMAL);
+			kfree(task);
+		} else if (err) {
+			cmdq_task_exec_done(task, CMDQ_CB_ERROR);
+			cmdq_task_handle_error(curr_task);
+			kfree(task);
+		}
+
+		if (curr_task)
+			break;
+	}
+
+	if (list_empty(&thread->task_busy_list)) {
+		cmdq_thread_disable(cmdq, thread);
+		clk_disable(cmdq->clock);
+	}
+}
+
+static irqreturn_t cmdq_irq_handler(int irq, void *dev)
+{
+	struct cmdq *cmdq = dev;
+	unsigned long irq_status, flags = 0L;
+	int bit;
+
+	irq_status = readl(cmdq->base + CMDQ_CURR_IRQ_STATUS) & CMDQ_IRQ_MASK;
+	if (!(irq_status ^ CMDQ_IRQ_MASK))
+		return IRQ_NONE;
+
+	for_each_clear_bit(bit, &irq_status, fls(CMDQ_IRQ_MASK)) {
+		struct cmdq_thread *thread = &cmdq->thread[bit];
+
+		spin_lock_irqsave(&thread->chan->lock, flags);
+		cmdq_thread_irq_handler(cmdq, thread);
+		spin_unlock_irqrestore(&thread->chan->lock, flags);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int cmdq_suspend(struct device *dev)
+{
+	struct cmdq *cmdq = dev_get_drvdata(dev);
+	struct cmdq_thread *thread;
+	int i;
+	bool task_running = false;
+
+	cmdq->suspended = true;
+
+	for (i = 0; i < cmdq->thread_nr; i++) {
+		thread = &cmdq->thread[i];
+		if (!list_empty(&thread->task_busy_list)) {
+			task_running = true;
+			break;
+		}
+	}
+
+	if (task_running)
+		dev_warn(dev, "exist running task(s) in suspend\n");
+
+	clk_unprepare(cmdq->clock);
+
+	return 0;
+}
+
+static int cmdq_resume(struct device *dev)
+{
+	struct cmdq *cmdq = dev_get_drvdata(dev);
+
+	WARN_ON(clk_prepare(cmdq->clock) < 0);
+	cmdq->suspended = false;
+	return 0;
+}
+
+static int cmdq_remove(struct platform_device *pdev)
+{
+	struct cmdq *cmdq = platform_get_drvdata(pdev);
+
+	mbox_controller_unregister(&cmdq->mbox);
+	clk_unprepare(cmdq->clock);
+
+	if (cmdq->mbox.chans)
+		devm_kfree(&pdev->dev, cmdq->mbox.chans);
+
+	if (cmdq->thread)
+		devm_kfree(&pdev->dev, cmdq->thread);
+
+	devm_kfree(&pdev->dev, cmdq);
+
+	return 0;
+}
+
+static int cmdq_mbox_send_data(struct mbox_chan *chan, void *data)
+{
+	struct cmdq_pkt *pkt = (struct cmdq_pkt *)data;
+	struct cmdq_thread *thread = (struct cmdq_thread *)chan->con_priv;
+	struct cmdq *cmdq = dev_get_drvdata(chan->mbox->dev);
+	struct cmdq_task *task;
+	unsigned long curr_pa, end_pa;
+
+	/* Client should not flush new tasks if suspended. */
+	WARN_ON(cmdq->suspended);
+
+	task = kzalloc(sizeof(*task), GFP_ATOMIC);
+	task->cmdq = cmdq;
+	INIT_LIST_HEAD(&task->list_entry);
+	task->pa_base = pkt->pa_base;
+	task->thread = thread;
+	task->pkt = pkt;
+
+	if (list_empty(&thread->task_busy_list)) {
+		WARN_ON(clk_enable(cmdq->clock) < 0);
+		WARN_ON(cmdq_thread_reset(cmdq, thread) < 0);
+
+		writel(task->pa_base, thread->base + CMDQ_THR_CURR_ADDR);
+		writel(task->pa_base + pkt->cmd_buf_size,
+		       thread->base + CMDQ_THR_END_ADDR);
+		writel(thread->priority, thread->base + CMDQ_THR_PRIORITY);
+		writel(CMDQ_THR_IRQ_EN, thread->base + CMDQ_THR_IRQ_ENABLE);
+		writel(CMDQ_THR_ENABLED, thread->base + CMDQ_THR_ENABLE_TASK);
+	} else {
+		WARN_ON(cmdq_thread_suspend(cmdq, thread) < 0);
+		curr_pa = readl(thread->base + CMDQ_THR_CURR_ADDR);
+		end_pa = readl(thread->base + CMDQ_THR_END_ADDR);
+
+		/*
+		 * Atomic execution should remove the following wfe, i.e. only
+		 * wait event at first task, and prevent to pause when running.
+		 */
+		if (thread->atomic_exec) {
+			/* GCE is executing if command is not WFE */
+			if (!cmdq_thread_is_in_wfe(thread)) {
+				cmdq_thread_resume(thread);
+				cmdq_thread_wait_end(thread, end_pa);
+				WARN_ON(cmdq_thread_suspend(cmdq, thread) < 0);
+				/* set to this task directly */
+				writel(task->pa_base,
+				       thread->base + CMDQ_THR_CURR_ADDR);
+			} else {
+				cmdq_task_insert_into_thread(task);
+				cmdq_task_remove_wfe(task);
+				smp_mb(); /* modify jump before enable thread */
+			}
+		} else {
+			/* check boundary */
+			if (curr_pa == end_pa - CMDQ_INST_SIZE ||
+			    curr_pa == end_pa) {
+				/* set to this task directly */
+				writel(task->pa_base,
+				       thread->base + CMDQ_THR_CURR_ADDR);
+			} else {
+				cmdq_task_insert_into_thread(task);
+				smp_mb(); /* modify jump before enable thread */
+			}
+		}
+		writel(task->pa_base + pkt->cmd_buf_size,
+		       thread->base + CMDQ_THR_END_ADDR);
+		cmdq_thread_resume(thread);
+	}
+	list_move_tail(&task->list_entry, &thread->task_busy_list);
+
+	return 0;
+}
+
+static int cmdq_mbox_startup(struct mbox_chan *chan)
+{
+	return 0;
+}
+
+static void cmdq_mbox_shutdown(struct mbox_chan *chan)
+{
+}
+
+static const struct mbox_chan_ops cmdq_mbox_chan_ops = {
+	.send_data = cmdq_mbox_send_data,
+	.startup = cmdq_mbox_startup,
+	.shutdown = cmdq_mbox_shutdown,
+};
+
+static struct mbox_chan *cmdq_xlate(struct mbox_controller *mbox,
+		const struct of_phandle_args *sp)
+{
+	int ind = sp->args[0];
+	struct cmdq_thread *thread;
+
+	if (ind >= mbox->num_chans)
+		return ERR_PTR(-EINVAL);
+
+	thread = (struct cmdq_thread *)mbox->chans[ind].con_priv;
+	thread->priority = sp->args[1];
+	thread->atomic_exec = (sp->args[2] != 0);
+	thread->chan = &mbox->chans[ind];
+
+	return &mbox->chans[ind];
+}
+
+static int cmdq_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	struct cmdq *cmdq;
+	int err, i;
+
+	cmdq = devm_kzalloc(dev, sizeof(*cmdq), GFP_KERNEL);
+	if (!cmdq)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	cmdq->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(cmdq->base)) {
+		dev_err(dev, "failed to ioremap gce\n");
+		return PTR_ERR(cmdq->base);
+	}
+
+	cmdq->irq = platform_get_irq(pdev, 0);
+	if (!cmdq->irq) {
+		dev_err(dev, "failed to get irq\n");
+		return -EINVAL;
+	}
+	err = devm_request_irq(dev, cmdq->irq, cmdq_irq_handler, IRQF_SHARED,
+			       "mtk_cmdq", cmdq);
+	if (err < 0) {
+		dev_err(dev, "failed to register ISR (%d)\n", err);
+		return err;
+	}
+
+	dev_dbg(dev, "cmdq device: addr:0x%p, va:0x%p, irq:%d\n",
+		dev, cmdq->base, cmdq->irq);
+
+	cmdq->clock = devm_clk_get(dev, "gce");
+	if (IS_ERR(cmdq->clock)) {
+		dev_err(dev, "failed to get gce clk\n");
+		return PTR_ERR(cmdq->clock);
+	}
+
+	cmdq->thread_nr = (u32)(unsigned long)of_device_get_match_data(dev);
+	cmdq->mbox.dev = dev;
+	cmdq->mbox.chans = devm_kcalloc(dev, cmdq->thread_nr,
+					sizeof(*cmdq->mbox.chans), GFP_KERNEL);
+	if (!cmdq->mbox.chans)
+		return -ENOMEM;
+
+	cmdq->mbox.num_chans = cmdq->thread_nr;
+	cmdq->mbox.ops = &cmdq_mbox_chan_ops;
+	cmdq->mbox.of_xlate = cmdq_xlate;
+
+	/* make use of TXDONE_BY_ACK */
+	cmdq->mbox.txdone_irq = false;
+	cmdq->mbox.txdone_poll = false;
+
+	cmdq->thread = devm_kcalloc(dev, cmdq->thread_nr,
+					sizeof(*cmdq->thread), GFP_KERNEL);
+	if (!cmdq->thread)
+		return -ENOMEM;
+
+	for (i = 0; i < cmdq->thread_nr; i++) {
+		cmdq->thread[i].base = cmdq->base + CMDQ_THR_BASE +
+				CMDQ_THR_SIZE * i;
+		INIT_LIST_HEAD(&cmdq->thread[i].task_busy_list);
+		cmdq->mbox.chans[i].con_priv = (void *)&cmdq->thread[i];
+	}
+
+	err = mbox_controller_register(&cmdq->mbox);
+	if (err < 0) {
+		dev_err(dev, "failed to register mailbox: %d\n", err);
+		return err;
+	}
+
+	platform_set_drvdata(pdev, cmdq);
+	WARN_ON(clk_prepare(cmdq->clock) < 0);
+
+	cmdq_init(cmdq);
+
+	return 0;
+}
+
+static const struct dev_pm_ops cmdq_pm_ops = {
+	.suspend = cmdq_suspend,
+	.resume = cmdq_resume,
+};
+
+static const struct of_device_id cmdq_of_ids[] = {
+	{.compatible = "mediatek,mt8173-gce", .data = (void *)16},
+	{}
+};
+
+static struct platform_driver cmdq_drv = {
+	.probe = cmdq_probe,
+	.remove = cmdq_remove,
+	.driver = {
+		.name = "mtk_cmdq",
+		.pm = &cmdq_pm_ops,
+		.of_match_table = cmdq_of_ids,
+	}
+};
+
+static int __init cmdq_drv_init(void)
+{
+	return platform_driver_register(&cmdq_drv);
+}
+
+static void __exit cmdq_drv_exit(void)
+{
+	platform_driver_unregister(&cmdq_drv);
+}
+
+subsys_initcall(cmdq_drv_init);
+module_exit(cmdq_drv_exit);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mailbox/omap-mailbox.c b/drivers/mailbox/omap-mailbox.c
index e1e2c085e68e..db66e952a871 100644
--- a/drivers/mailbox/omap-mailbox.c
+++ b/drivers/mailbox/omap-mailbox.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * OMAP mailbox driver
  *
@@ -6,15 +7,6 @@
  *
  * Contact: Hiroshi DOYU <Hiroshi.DOYU@nokia.com>
  *          Suman Anna <s-anna@ti.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 
 #include <linux/interrupt.h>
@@ -77,6 +69,10 @@ struct omap_mbox_queue {
 	bool full;
 };
 
+struct omap_mbox_match_data {
+	u32 intr_type;
+};
+
 struct omap_mbox_device {
 	struct device *dev;
 	struct mutex cfg_lock;
@@ -646,18 +642,21 @@ static const struct dev_pm_ops omap_mbox_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(omap_mbox_suspend, omap_mbox_resume)
 };
 
+static const struct omap_mbox_match_data omap2_data = { MBOX_INTR_CFG_TYPE1 };
+static const struct omap_mbox_match_data omap4_data = { MBOX_INTR_CFG_TYPE2 };
+
 static const struct of_device_id omap_mailbox_of_match[] = {
 	{
 		.compatible	= "ti,omap2-mailbox",
-		.data		= (void *)MBOX_INTR_CFG_TYPE1,
+		.data		= &omap2_data,
 	},
 	{
 		.compatible	= "ti,omap3-mailbox",
-		.data		= (void *)MBOX_INTR_CFG_TYPE1,
+		.data		= &omap2_data,
 	},
 	{
 		.compatible	= "ti,omap4-mailbox",
-		.data		= (void *)MBOX_INTR_CFG_TYPE2,
+		.data		= &omap4_data,
 	},
 	{
 		/* end */
@@ -700,7 +699,7 @@ static int omap_mbox_probe(struct platform_device *pdev)
 	struct omap_mbox_fifo *fifo;
 	struct device_node *node = pdev->dev.of_node;
 	struct device_node *child;
-	const struct of_device_id *match;
+	const struct omap_mbox_match_data *match_data;
 	u32 intr_type, info_count;
 	u32 num_users, num_fifos;
 	u32 tmp[3];
@@ -712,10 +711,10 @@ static int omap_mbox_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	match = of_match_device(omap_mailbox_of_match, &pdev->dev);
-	if (!match)
+	match_data = of_device_get_match_data(&pdev->dev);
+	if (!match_data)
 		return -ENODEV;
-	intr_type = (u32)match->data;
+	intr_type = match_data->intr_type;
 
 	if (of_property_read_u32(node, "ti,mbox-num-users", &num_users))
 		return -ENODEV;
diff --git a/drivers/mailbox/ti-msgmgr.c b/drivers/mailbox/ti-msgmgr.c
index 5d04738c3c8a..5bceafbf6699 100644
--- a/drivers/mailbox/ti-msgmgr.c
+++ b/drivers/mailbox/ti-msgmgr.c
@@ -25,6 +25,17 @@
 #define Q_STATE_OFFSET(queue)			((queue) * 0x4)
 #define Q_STATE_ENTRY_COUNT_MASK		(0xFFF000)
 
+#define SPROXY_THREAD_OFFSET(tid) (0x1000 * (tid))
+#define SPROXY_THREAD_DATA_OFFSET(tid, reg) \
+	(SPROXY_THREAD_OFFSET(tid) + ((reg) * 0x4) + 0x4)
+
+#define SPROXY_THREAD_STATUS_OFFSET(tid) (SPROXY_THREAD_OFFSET(tid))
+
+#define SPROXY_THREAD_STATUS_COUNT_MASK (0xFF)
+
+#define SPROXY_THREAD_CTRL_OFFSET(tid) (0x1000 + SPROXY_THREAD_OFFSET(tid))
+#define SPROXY_THREAD_CTRL_DIR_MASK (0x1 << 31)
+
 /**
  * struct ti_msgmgr_valid_queue_desc - SoC valid queues meant for this processor
  * @queue_id:	Queue Number for this path
@@ -42,14 +53,18 @@ struct ti_msgmgr_valid_queue_desc {
  * @queue_count:	Number of Queues
  * @max_message_size:	Message size in bytes
  * @max_messages:	Number of messages
- * @q_slices:		Number of queue engines
- * @q_proxies:		Number of queue proxies per page
  * @data_first_reg:	First data register for proxy data region
  * @data_last_reg:	Last data register for proxy data region
+ * @status_cnt_mask:	Mask for getting the status value
+ * @status_err_mask:	Mask for getting the error value, if applicable
  * @tx_polled:		Do I need to use polled mechanism for tx
  * @tx_poll_timeout_ms: Timeout in ms if polled
  * @valid_queues:	List of Valid queues that the processor can access
+ * @data_region_name:	Name of the proxy data region
+ * @status_region_name:	Name of the proxy status region
+ * @ctrl_region_name:	Name of the proxy control region
  * @num_valid_queues:	Number of valid queues
+ * @is_sproxy:		Is this an Secure Proxy instance?
  *
  * This structure is used in of match data to describe how integration
  * for a specific compatible SoC is done.
@@ -58,14 +73,18 @@ struct ti_msgmgr_desc {
 	u8 queue_count;
 	u8 max_message_size;
 	u8 max_messages;
-	u8 q_slices;
-	u8 q_proxies;
 	u8 data_first_reg;
 	u8 data_last_reg;
+	u32 status_cnt_mask;
+	u32 status_err_mask;
 	bool tx_polled;
 	int tx_poll_timeout_ms;
 	const struct ti_msgmgr_valid_queue_desc *valid_queues;
+	const char *data_region_name;
+	const char *status_region_name;
+	const char *ctrl_region_name;
 	int num_valid_queues;
+	bool is_sproxy;
 };
 
 /**
@@ -78,6 +97,7 @@ struct ti_msgmgr_desc {
  * @queue_buff_start: First register of Data Buffer
  * @queue_buff_end: Last (or confirmation) register of Data buffer
  * @queue_state: Queue status register
+ * @queue_ctrl: Queue Control register
  * @chan:	Mailbox channel
  * @rx_buff:	Receive buffer pointer allocated at probe, max_message_size
  */
@@ -90,6 +110,7 @@ struct ti_queue_inst {
 	void __iomem *queue_buff_start;
 	void __iomem *queue_buff_end;
 	void __iomem *queue_state;
+	void __iomem *queue_ctrl;
 	struct mbox_chan *chan;
 	u32 *rx_buff;
 };
@@ -100,6 +121,7 @@ struct ti_queue_inst {
  * @desc:	Description of the SoC integration
  * @queue_proxy_region:	Queue proxy region where queue buffers are located
  * @queue_state_debug_region:	Queue status register regions
+ * @queue_ctrl_region:	Queue Control register regions
  * @num_valid_queues:	Number of valid queues defined for the processor
  *		Note: other queues are probably reserved for other processors
  *		in the SoC.
@@ -112,6 +134,7 @@ struct ti_msgmgr_inst {
 	const struct ti_msgmgr_desc *desc;
 	void __iomem *queue_proxy_region;
 	void __iomem *queue_state_debug_region;
+	void __iomem *queue_ctrl_region;
 	u8 num_valid_queues;
 	struct ti_queue_inst *qinsts;
 	struct mbox_controller mbox;
@@ -120,25 +143,54 @@ struct ti_msgmgr_inst {
 
 /**
  * ti_msgmgr_queue_get_num_messages() - Get the number of pending messages
+ * @d:		Description of message manager
  * @qinst:	Queue instance for which we check the number of pending messages
  *
  * Return: number of messages pending in the queue (0 == no pending messages)
  */
-static inline int ti_msgmgr_queue_get_num_messages(struct ti_queue_inst *qinst)
+static inline int
+ti_msgmgr_queue_get_num_messages(const struct ti_msgmgr_desc *d,
+				 struct ti_queue_inst *qinst)
 {
 	u32 val;
+	u32 status_cnt_mask = d->status_cnt_mask;
 
 	/*
 	 * We cannot use relaxed operation here - update may happen
 	 * real-time.
 	 */
-	val = readl(qinst->queue_state) & Q_STATE_ENTRY_COUNT_MASK;
-	val >>= __ffs(Q_STATE_ENTRY_COUNT_MASK);
+	val = readl(qinst->queue_state) & status_cnt_mask;
+	val >>= __ffs(status_cnt_mask);
 
 	return val;
 }
 
 /**
+ * ti_msgmgr_queue_is_error() - Check to see if there is queue error
+ * @d:		Description of message manager
+ * @qinst:	Queue instance for which we check the number of pending messages
+ *
+ * Return: true if error, else false
+ */
+static inline bool ti_msgmgr_queue_is_error(const struct ti_msgmgr_desc *d,
+					    struct ti_queue_inst *qinst)
+{
+	u32 val;
+
+	/* Msgmgr has no error detection */
+	if (!d->is_sproxy)
+		return false;
+
+	/*
+	 * We cannot use relaxed operation here - update may happen
+	 * real-time.
+	 */
+	val = readl(qinst->queue_state) & d->status_err_mask;
+
+	return val ? true : false;
+}
+
+/**
  * ti_msgmgr_queue_rx_interrupt() - Interrupt handler for receive Queue
  * @irq:	Interrupt number
  * @p:		Channel Pointer
@@ -171,8 +223,14 @@ static irqreturn_t ti_msgmgr_queue_rx_interrupt(int irq, void *p)
 		return IRQ_NONE;
 	}
 
+	desc = inst->desc;
+	if (ti_msgmgr_queue_is_error(desc, qinst)) {
+		dev_err(dev, "Error on Rx channel %s\n", qinst->name);
+		return IRQ_NONE;
+	}
+
 	/* Do I actually have messages to read? */
-	msg_count = ti_msgmgr_queue_get_num_messages(qinst);
+	msg_count = ti_msgmgr_queue_get_num_messages(desc, qinst);
 	if (!msg_count) {
 		/* Shared IRQ? */
 		dev_dbg(dev, "Spurious event - 0 pending data!\n");
@@ -185,7 +243,6 @@ static irqreturn_t ti_msgmgr_queue_rx_interrupt(int irq, void *p)
 	 * of how many bytes I should be reading. Let the client figure this
 	 * out.. I just read the full message and pass it on..
 	 */
-	desc = inst->desc;
 	message.len = desc->max_message_size;
 	message.buf = (u8 *)qinst->rx_buff;
 
@@ -228,12 +285,20 @@ static irqreturn_t ti_msgmgr_queue_rx_interrupt(int irq, void *p)
 static bool ti_msgmgr_queue_peek_data(struct mbox_chan *chan)
 {
 	struct ti_queue_inst *qinst = chan->con_priv;
+	struct device *dev = chan->mbox->dev;
+	struct ti_msgmgr_inst *inst = dev_get_drvdata(dev);
+	const struct ti_msgmgr_desc *desc = inst->desc;
 	int msg_count;
 
 	if (qinst->is_tx)
 		return false;
 
-	msg_count = ti_msgmgr_queue_get_num_messages(qinst);
+	if (ti_msgmgr_queue_is_error(desc, qinst)) {
+		dev_err(dev, "Error on channel %s\n", qinst->name);
+		return false;
+	}
+
+	msg_count = ti_msgmgr_queue_get_num_messages(desc, qinst);
 
 	return msg_count ? true : false;
 }
@@ -247,12 +312,25 @@ static bool ti_msgmgr_queue_peek_data(struct mbox_chan *chan)
 static bool ti_msgmgr_last_tx_done(struct mbox_chan *chan)
 {
 	struct ti_queue_inst *qinst = chan->con_priv;
+	struct device *dev = chan->mbox->dev;
+	struct ti_msgmgr_inst *inst = dev_get_drvdata(dev);
+	const struct ti_msgmgr_desc *desc = inst->desc;
 	int msg_count;
 
 	if (!qinst->is_tx)
 		return false;
 
-	msg_count = ti_msgmgr_queue_get_num_messages(qinst);
+	if (ti_msgmgr_queue_is_error(desc, qinst)) {
+		dev_err(dev, "Error on channel %s\n", qinst->name);
+		return false;
+	}
+
+	msg_count = ti_msgmgr_queue_get_num_messages(desc, qinst);
+
+	if (desc->is_sproxy) {
+		/* In secure proxy, msg_count indicates how many we can send */
+		return msg_count ? true : false;
+	}
 
 	/* if we have any messages pending.. */
 	return msg_count ? false : true;
@@ -282,6 +360,11 @@ static int ti_msgmgr_send_data(struct mbox_chan *chan, void *data)
 	}
 	desc = inst->desc;
 
+	if (ti_msgmgr_queue_is_error(desc, qinst)) {
+		dev_err(dev, "Error on channel %s\n", qinst->name);
+		return false;
+	}
+
 	if (desc->max_message_size < message->len) {
 		dev_err(dev, "Queue %s message length %zu > max %d\n",
 			qinst->name, message->len, desc->max_message_size);
@@ -315,6 +398,53 @@ static int ti_msgmgr_send_data(struct mbox_chan *chan, void *data)
 }
 
 /**
+ *  ti_msgmgr_queue_rx_irq_req() - RX IRQ request
+ *  @dev:	device pointer
+ *  @d:		descriptor for ti_msgmgr
+ *  @qinst:	Queue instance
+ *  @chan:	Channel pointer
+ */
+static int ti_msgmgr_queue_rx_irq_req(struct device *dev,
+				      const struct ti_msgmgr_desc *d,
+				      struct ti_queue_inst *qinst,
+				      struct mbox_chan *chan)
+{
+	int ret = 0;
+	char of_rx_irq_name[7];
+	struct device_node *np;
+
+	snprintf(of_rx_irq_name, sizeof(of_rx_irq_name),
+		 "rx_%03d", d->is_sproxy ? qinst->proxy_id : qinst->queue_id);
+
+	/* Get the IRQ if not found */
+	if (qinst->irq < 0) {
+		np = of_node_get(dev->of_node);
+		if (!np)
+			return -ENODATA;
+		qinst->irq = of_irq_get_byname(np, of_rx_irq_name);
+		of_node_put(np);
+
+		if (qinst->irq < 0) {
+			dev_err(dev,
+				"QID %d PID %d:No IRQ[%s]: %d\n",
+				qinst->queue_id, qinst->proxy_id,
+				of_rx_irq_name, qinst->irq);
+			return qinst->irq;
+		}
+	}
+
+	/* With the expectation that the IRQ might be shared in SoC */
+	ret = request_irq(qinst->irq, ti_msgmgr_queue_rx_interrupt,
+			  IRQF_SHARED, qinst->name, chan);
+	if (ret) {
+		dev_err(dev, "Unable to get IRQ %d on %s(res=%d)\n",
+			qinst->irq, qinst->name, ret);
+	}
+
+	return ret;
+}
+
+/**
  * ti_msgmgr_queue_startup() - Startup queue
  * @chan:	Channel pointer
  *
@@ -322,19 +452,39 @@ static int ti_msgmgr_send_data(struct mbox_chan *chan, void *data)
  */
 static int ti_msgmgr_queue_startup(struct mbox_chan *chan)
 {
-	struct ti_queue_inst *qinst = chan->con_priv;
 	struct device *dev = chan->mbox->dev;
+	struct ti_msgmgr_inst *inst = dev_get_drvdata(dev);
+	struct ti_queue_inst *qinst = chan->con_priv;
+	const struct ti_msgmgr_desc *d = inst->desc;
 	int ret;
+	int msg_count;
+
+	/*
+	 * If sproxy is starting and can send messages, we are a Tx thread,
+	 * else Rx
+	 */
+	if (d->is_sproxy) {
+		qinst->is_tx = (readl(qinst->queue_ctrl) &
+				SPROXY_THREAD_CTRL_DIR_MASK) ? false : true;
+
+		msg_count = ti_msgmgr_queue_get_num_messages(d, qinst);
+
+		if (!msg_count && qinst->is_tx) {
+			dev_err(dev, "%s: Cannot transmit with 0 credits!\n",
+				qinst->name);
+			return -EINVAL;
+		}
+	}
 
 	if (!qinst->is_tx) {
-		/*
-		 * With the expectation that the IRQ might be shared in SoC
-		 */
-		ret = request_irq(qinst->irq, ti_msgmgr_queue_rx_interrupt,
-				  IRQF_SHARED, qinst->name, chan);
+		/* Allocate usage buffer for rx */
+		qinst->rx_buff = kzalloc(d->max_message_size, GFP_KERNEL);
+		if (!qinst->rx_buff)
+			return -ENOMEM;
+		/* Request IRQ */
+		ret = ti_msgmgr_queue_rx_irq_req(dev, d, qinst, chan);
 		if (ret) {
-			dev_err(dev, "Unable to get IRQ %d on %s(res=%d)\n",
-				qinst->irq, qinst->name, ret);
+			kfree(qinst->rx_buff);
 			return ret;
 		}
 	}
@@ -350,8 +500,10 @@ static void ti_msgmgr_queue_shutdown(struct mbox_chan *chan)
 {
 	struct ti_queue_inst *qinst = chan->con_priv;
 
-	if (!qinst->is_tx)
+	if (!qinst->is_tx) {
 		free_irq(qinst->irq, chan);
+		kfree(qinst->rx_buff);
+	}
 }
 
 /**
@@ -368,20 +520,38 @@ static struct mbox_chan *ti_msgmgr_of_xlate(struct mbox_controller *mbox,
 	struct ti_msgmgr_inst *inst;
 	int req_qid, req_pid;
 	struct ti_queue_inst *qinst;
-	int i;
+	const struct ti_msgmgr_desc *d;
+	int i, ncells;
 
 	inst = container_of(mbox, struct ti_msgmgr_inst, mbox);
 	if (WARN_ON(!inst))
 		return ERR_PTR(-EINVAL);
 
-	/* #mbox-cells is 2 */
-	if (p->args_count != 2) {
-		dev_err(inst->dev, "Invalid arguments in dt[%d] instead of 2\n",
-			p->args_count);
+	d = inst->desc;
+
+	if (d->is_sproxy)
+		ncells = 1;
+	else
+		ncells = 2;
+	if (p->args_count != ncells) {
+		dev_err(inst->dev, "Invalid arguments in dt[%d]. Must be %d\n",
+			p->args_count, ncells);
 		return ERR_PTR(-EINVAL);
 	}
-	req_qid = p->args[0];
-	req_pid = p->args[1];
+	if (ncells == 1) {
+		req_qid = 0;
+		req_pid = p->args[0];
+	} else {
+		req_qid = p->args[0];
+		req_pid = p->args[1];
+	}
+
+	if (d->is_sproxy) {
+		if (req_pid > d->num_valid_queues)
+			goto err;
+		qinst = &inst->qinsts[req_pid];
+		return qinst->chan;
+	}
 
 	for (qinst = inst->qinsts, i = 0; i < inst->num_valid_queues;
 	     i++, qinst++) {
@@ -389,6 +559,7 @@ static struct mbox_chan *ti_msgmgr_of_xlate(struct mbox_controller *mbox,
 			return qinst->chan;
 	}
 
+err:
 	dev_err(inst->dev, "Queue ID %d, Proxy ID %d is wrong on %s\n",
 		req_qid, req_pid, p->np->name);
 	return ERR_PTR(-ENOENT);
@@ -415,6 +586,8 @@ static int ti_msgmgr_queue_setup(int idx, struct device *dev,
 				 struct ti_queue_inst *qinst,
 				 struct mbox_chan *chan)
 {
+	char *dir;
+
 	qinst->proxy_id = qd->proxy_id;
 	qinst->queue_id = qd->queue_id;
 
@@ -424,40 +597,43 @@ static int ti_msgmgr_queue_setup(int idx, struct device *dev,
 		return -ERANGE;
 	}
 
-	qinst->is_tx = qd->is_tx;
-	snprintf(qinst->name, sizeof(qinst->name), "%s %s_%03d_%03d",
-		 dev_name(dev), qinst->is_tx ? "tx" : "rx", qinst->queue_id,
-		 qinst->proxy_id);
-
-	if (!qinst->is_tx) {
-		char of_rx_irq_name[7];
-
-		snprintf(of_rx_irq_name, sizeof(of_rx_irq_name),
-			 "rx_%03d", qinst->queue_id);
-
-		qinst->irq = of_irq_get_byname(np, of_rx_irq_name);
-		if (qinst->irq < 0) {
-			dev_crit(dev,
-				 "[%d]QID %d PID %d:No IRQ[%s]: %d\n",
-				 idx, qinst->queue_id, qinst->proxy_id,
-				 of_rx_irq_name, qinst->irq);
-			return qinst->irq;
-		}
-		/* Allocate usage buffer for rx */
-		qinst->rx_buff = devm_kzalloc(dev,
-					      d->max_message_size, GFP_KERNEL);
-		if (!qinst->rx_buff)
-			return -ENOMEM;
+	if (d->is_sproxy) {
+		qinst->queue_buff_start = inst->queue_proxy_region +
+		    SPROXY_THREAD_DATA_OFFSET(qinst->proxy_id,
+					      d->data_first_reg);
+		qinst->queue_buff_end = inst->queue_proxy_region +
+		    SPROXY_THREAD_DATA_OFFSET(qinst->proxy_id,
+					      d->data_last_reg);
+		qinst->queue_state = inst->queue_state_debug_region +
+		    SPROXY_THREAD_STATUS_OFFSET(qinst->proxy_id);
+		qinst->queue_ctrl = inst->queue_ctrl_region +
+		    SPROXY_THREAD_CTRL_OFFSET(qinst->proxy_id);
+
+		/* XXX: DONOT read registers here!.. Some may be unusable */
+		dir = "thr";
+		snprintf(qinst->name, sizeof(qinst->name), "%s %s_%03d",
+			 dev_name(dev), dir, qinst->proxy_id);
+	} else {
+		qinst->queue_buff_start = inst->queue_proxy_region +
+		    Q_DATA_OFFSET(qinst->proxy_id, qinst->queue_id,
+				  d->data_first_reg);
+		qinst->queue_buff_end = inst->queue_proxy_region +
+		    Q_DATA_OFFSET(qinst->proxy_id, qinst->queue_id,
+				  d->data_last_reg);
+		qinst->queue_state =
+		    inst->queue_state_debug_region +
+		    Q_STATE_OFFSET(qinst->queue_id);
+		qinst->is_tx = qd->is_tx;
+		dir = qinst->is_tx ? "tx" : "rx";
+		snprintf(qinst->name, sizeof(qinst->name), "%s %s_%03d_%03d",
+			 dev_name(dev), dir, qinst->queue_id, qinst->proxy_id);
 	}
 
-	qinst->queue_buff_start = inst->queue_proxy_region +
-	    Q_DATA_OFFSET(qinst->proxy_id, qinst->queue_id, d->data_first_reg);
-	qinst->queue_buff_end = inst->queue_proxy_region +
-	    Q_DATA_OFFSET(qinst->proxy_id, qinst->queue_id, d->data_last_reg);
-	qinst->queue_state = inst->queue_state_debug_region +
-	    Q_STATE_OFFSET(qinst->queue_id);
 	qinst->chan = chan;
 
+	/* Setup an error value for IRQ - Lazy allocation */
+	qinst->irq = -EINVAL;
+
 	chan->con_priv = qinst;
 
 	dev_dbg(dev, "[%d] qidx=%d pidx=%d irq=%d q_s=%p q_e = %p\n",
@@ -494,19 +670,37 @@ static const struct ti_msgmgr_desc k2g_desc = {
 	.queue_count = 64,
 	.max_message_size = 64,
 	.max_messages = 128,
-	.q_slices = 1,
-	.q_proxies = 1,
+	.data_region_name = "queue_proxy_region",
+	.status_region_name = "queue_state_debug_region",
 	.data_first_reg = 16,
 	.data_last_reg = 31,
+	.status_cnt_mask = Q_STATE_ENTRY_COUNT_MASK,
 	.tx_polled = false,
 	.valid_queues = k2g_valid_queues,
 	.num_valid_queues = ARRAY_SIZE(k2g_valid_queues),
+	.is_sproxy = false,
+};
+
+static const struct ti_msgmgr_desc am654_desc = {
+	.queue_count = 190,
+	.num_valid_queues = 190,
+	.max_message_size = 60,
+	.data_region_name = "target_data",
+	.status_region_name = "rt",
+	.ctrl_region_name = "scfg",
+	.data_first_reg = 0,
+	.data_last_reg = 14,
+	.status_cnt_mask = SPROXY_THREAD_STATUS_COUNT_MASK,
+	.tx_polled = false,
+	.is_sproxy = true,
 };
 
 static const struct of_device_id ti_msgmgr_of_match[] = {
 	{.compatible = "ti,k2g-message-manager", .data = &k2g_desc},
+	{.compatible = "ti,am654-secure-proxy", .data = &am654_desc},
 	{ /* Sentinel */ }
 };
+
 MODULE_DEVICE_TABLE(of, ti_msgmgr_of_match);
 
 static int ti_msgmgr_probe(struct platform_device *pdev)
@@ -546,17 +740,25 @@ static int ti_msgmgr_probe(struct platform_device *pdev)
 	inst->desc = desc;
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-					   "queue_proxy_region");
+					   desc->data_region_name);
 	inst->queue_proxy_region = devm_ioremap_resource(dev, res);
 	if (IS_ERR(inst->queue_proxy_region))
 		return PTR_ERR(inst->queue_proxy_region);
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-					   "queue_state_debug_region");
+					   desc->status_region_name);
 	inst->queue_state_debug_region = devm_ioremap_resource(dev, res);
 	if (IS_ERR(inst->queue_state_debug_region))
 		return PTR_ERR(inst->queue_state_debug_region);
 
+	if (desc->is_sproxy) {
+		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						   desc->ctrl_region_name);
+		inst->queue_ctrl_region = devm_ioremap_resource(dev, res);
+		if (IS_ERR(inst->queue_ctrl_region))
+			return PTR_ERR(inst->queue_ctrl_region);
+	}
+
 	dev_dbg(dev, "proxy region=%p, queue_state=%p\n",
 		inst->queue_proxy_region, inst->queue_state_debug_region);
 
@@ -578,12 +780,29 @@ static int ti_msgmgr_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	inst->chans = chans;
 
-	for (i = 0, queue_desc = desc->valid_queues;
-	     i < queue_count; i++, qinst++, chans++, queue_desc++) {
-		ret = ti_msgmgr_queue_setup(i, dev, np, inst,
-					    desc, queue_desc, qinst, chans);
-		if (ret)
-			return ret;
+	if (desc->is_sproxy) {
+		struct ti_msgmgr_valid_queue_desc sproxy_desc;
+
+		/* All proxies may be valid in Secure Proxy instance */
+		for (i = 0; i < queue_count; i++, qinst++, chans++) {
+			sproxy_desc.queue_id = 0;
+			sproxy_desc.proxy_id = i;
+			ret = ti_msgmgr_queue_setup(i, dev, np, inst,
+						    desc, &sproxy_desc, qinst,
+						    chans);
+			if (ret)
+				return ret;
+		}
+	} else {
+		/* Only Some proxies are valid in Message Manager */
+		for (i = 0, queue_desc = desc->valid_queues;
+		     i < queue_count; i++, qinst++, chans++, queue_desc++) {
+			ret = ti_msgmgr_queue_setup(i, dev, np, inst,
+						    desc, queue_desc, qinst,
+						    chans);
+			if (ret)
+				return ret;
+		}
 	}
 
 	mbox = &inst->mbox;
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index d6bf294f3907..05f82ff6f016 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -328,13 +328,6 @@ struct cached_dev {
 	 */
 	atomic_t		has_dirty;
 
-	/*
-	 * Set to zero by things that touch the backing volume-- except
-	 * writeback.  Incremented by writeback.  Used to determine when to
-	 * accelerate idle writeback.
-	 */
-	atomic_t		backing_idle;
-
 	struct bch_ratelimit	writeback_rate;
 	struct delayed_work	writeback_rate_update;
 
@@ -423,9 +416,9 @@ struct cache {
 	/*
 	 * When allocating new buckets, prio_write() gets first dibs - since we
 	 * may not be allocate at all without writing priorities and gens.
-	 * prio_buckets[] contains the last buckets we wrote priorities to (so
-	 * gc can mark them as metadata), prio_next[] contains the buckets
-	 * allocated for the next prio write.
+	 * prio_last_buckets[] contains the last buckets we wrote priorities to
+	 * (so gc can mark them as metadata), prio_buckets[] contains the
+	 * buckets allocated for the next prio write.
 	 */
 	uint64_t		*prio_buckets;
 	uint64_t		*prio_last_buckets;
@@ -474,6 +467,7 @@ struct cache {
 
 struct gc_stat {
 	size_t			nodes;
+	size_t			nodes_pre;
 	size_t			key_bytes;
 
 	size_t			nkeys;
@@ -514,6 +508,8 @@ struct cache_set {
 	struct cache_accounting accounting;
 
 	unsigned long		flags;
+	atomic_t		idle_counter;
+	atomic_t		at_max_writeback_rate;
 
 	struct cache_sb		sb;
 
@@ -523,8 +519,10 @@ struct cache_set {
 
 	struct bcache_device	**devices;
 	unsigned		devices_max_used;
+	atomic_t		attached_dev_nr;
 	struct list_head	cached_devs;
 	uint64_t		cached_dev_sectors;
+	atomic_long_t		flash_dev_dirty_sectors;
 	struct closure		caching;
 
 	struct closure		sb_write;
@@ -603,6 +601,10 @@ struct cache_set {
 	 */
 	atomic_t		rescale;
 	/*
+	 * used for GC, identify if any front side I/Os is inflight
+	 */
+	atomic_t		search_inflight;
+	/*
 	 * When we invalidate buckets, we use both the priority and the amount
 	 * of good data to determine which buckets to reuse first - to weight
 	 * those together consistently we keep track of the smallest nonzero
@@ -995,7 +997,7 @@ void bch_open_buckets_free(struct cache_set *);
 int bch_cache_allocator_start(struct cache *ca);
 
 void bch_debug_exit(void);
-int bch_debug_init(struct kobject *);
+void bch_debug_init(struct kobject *kobj);
 void bch_request_exit(void);
 int bch_request_init(void);
 
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index f3403b45bc28..596c93b44e9b 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -366,6 +366,10 @@ EXPORT_SYMBOL(bch_btree_keys_init);
 
 /* Binary tree stuff for auxiliary search trees */
 
+/*
+ * return array index next to j when does in-order traverse
+ * of a binary tree which is stored in a linear array
+ */
 static unsigned inorder_next(unsigned j, unsigned size)
 {
 	if (j * 2 + 1 < size) {
@@ -379,6 +383,10 @@ static unsigned inorder_next(unsigned j, unsigned size)
 	return j;
 }
 
+/*
+ * return array index previous to j when does in-order traverse
+ * of a binary tree which is stored in a linear array
+ */
 static unsigned inorder_prev(unsigned j, unsigned size)
 {
 	if (j * 2 < size) {
@@ -421,6 +429,10 @@ static unsigned __to_inorder(unsigned j, unsigned size, unsigned extra)
 	return j;
 }
 
+/*
+ * Return the cacheline index in bset_tree->data, where j is index
+ * from a linear array which stores the auxiliar binary tree
+ */
 static unsigned to_inorder(unsigned j, struct bset_tree *t)
 {
 	return __to_inorder(j, t->size, t->extra);
@@ -441,6 +453,10 @@ static unsigned __inorder_to_tree(unsigned j, unsigned size, unsigned extra)
 	return j;
 }
 
+/*
+ * Return an index from a linear array which stores the auxiliar binary
+ * tree, j is the cacheline index of t->data.
+ */
 static unsigned inorder_to_tree(unsigned j, struct bset_tree *t)
 {
 	return __inorder_to_tree(j, t->size, t->extra);
@@ -546,6 +562,20 @@ static inline uint64_t shrd128(uint64_t high, uint64_t low, uint8_t shift)
 	return low;
 }
 
+/*
+ * Calculate mantissa value for struct bkey_float.
+ * If most significant bit of f->exponent is not set, then
+ *  - f->exponent >> 6 is 0
+ *  - p[0] points to bkey->low
+ *  - p[-1] borrows bits from KEY_INODE() of bkey->high
+ * if most isgnificant bits of f->exponent is set, then
+ *  - f->exponent >> 6 is 1
+ *  - p[0] points to bits from KEY_INODE() of bkey->high
+ *  - p[-1] points to other bits from KEY_INODE() of
+ *    bkey->high too.
+ * See make_bfloat() to check when most significant bit of f->exponent
+ * is set or not.
+ */
 static inline unsigned bfloat_mantissa(const struct bkey *k,
 				       struct bkey_float *f)
 {
@@ -570,6 +600,16 @@ static void make_bfloat(struct bset_tree *t, unsigned j)
 	BUG_ON(m < l || m > r);
 	BUG_ON(bkey_next(p) != m);
 
+	/*
+	 * If l and r have different KEY_INODE values (different backing
+	 * device), f->exponent records how many least significant bits
+	 * are different in KEY_INODE values and sets most significant
+	 * bits to 1 (by +64).
+	 * If l and r have same KEY_INODE value, f->exponent records
+	 * how many different bits in least significant bits of bkey->low.
+	 * See bfloat_mantiss() how the most significant bit of
+	 * f->exponent is used to calculate bfloat mantissa value.
+	 */
 	if (KEY_INODE(l) != KEY_INODE(r))
 		f->exponent = fls64(KEY_INODE(r) ^ KEY_INODE(l)) + 64;
 	else
@@ -633,6 +673,15 @@ void bch_bset_init_next(struct btree_keys *b, struct bset *i, uint64_t magic)
 }
 EXPORT_SYMBOL(bch_bset_init_next);
 
+/*
+ * Build auxiliary binary tree 'struct bset_tree *t', this tree is used to
+ * accelerate bkey search in a btree node (pointed by bset_tree->data in
+ * memory). After search in the auxiliar tree by calling bset_search_tree(),
+ * a struct bset_search_iter is returned which indicates range [l, r] from
+ * bset_tree->data where the searching bkey might be inside. Then a followed
+ * linear comparison does the exact search, see __bch_bset_search() for how
+ * the auxiliary tree is used.
+ */
 void bch_bset_build_written_tree(struct btree_keys *b)
 {
 	struct bset_tree *t = bset_tree_last(b);
@@ -898,6 +947,17 @@ static struct bset_search_iter bset_search_tree(struct bset_tree *t,
 	unsigned inorder, j, n = 1;
 
 	do {
+		/*
+		 * A bit trick here.
+		 * If p < t->size, (int)(p - t->size) is a minus value and
+		 * the most significant bit is set, right shifting 31 bits
+		 * gets 1. If p >= t->size, the most significant bit is
+		 * not set, right shifting 31 bits gets 0.
+		 * So the following 2 lines equals to
+		 *	if (p >= t->size)
+		 *		p = 0;
+		 * but a branch instruction is avoided.
+		 */
 		unsigned p = n << 4;
 		p &= ((int) (p - t->size)) >> 31;
 
@@ -907,6 +967,9 @@ static struct bset_search_iter bset_search_tree(struct bset_tree *t,
 		f = &t->tree[j];
 
 		/*
+		 * Similar bit trick, use subtract operation to avoid a branch
+		 * instruction.
+		 *
 		 * n = (f->mantissa > bfloat_mantissa())
 		 *	? j * 2
 		 *	: j * 2 + 1;
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 547c9eedc2f4..c19f7716df88 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -90,6 +90,9 @@
 
 #define MAX_NEED_GC		64
 #define MAX_SAVE_PRIO		72
+#define MAX_GC_TIMES		100
+#define MIN_GC_NODES		100
+#define GC_SLEEP_MS		100
 
 #define PTR_DIRTY_BIT		(((uint64_t) 1 << 36))
 
@@ -1008,6 +1011,13 @@ retry:
 		BUG_ON(b->level != level);
 	}
 
+	if (btree_node_io_error(b)) {
+		rw_unlock(write, b);
+		return ERR_PTR(-EIO);
+	}
+
+	BUG_ON(!b->written);
+
 	b->parent = parent;
 	b->accessed = 1;
 
@@ -1019,13 +1029,6 @@ retry:
 	for (; i <= b->keys.nsets; i++)
 		prefetch(b->keys.set[i].data);
 
-	if (btree_node_io_error(b)) {
-		rw_unlock(write, b);
-		return ERR_PTR(-EIO);
-	}
-
-	BUG_ON(!b->written);
-
 	return b;
 }
 
@@ -1520,6 +1523,32 @@ static unsigned btree_gc_count_keys(struct btree *b)
 	return ret;
 }
 
+static size_t btree_gc_min_nodes(struct cache_set *c)
+{
+	size_t min_nodes;
+
+	/*
+	 * Since incremental GC would stop 100ms when front
+	 * side I/O comes, so when there are many btree nodes,
+	 * if GC only processes constant (100) nodes each time,
+	 * GC would last a long time, and the front side I/Os
+	 * would run out of the buckets (since no new bucket
+	 * can be allocated during GC), and be blocked again.
+	 * So GC should not process constant nodes, but varied
+	 * nodes according to the number of btree nodes, which
+	 * realized by dividing GC into constant(100) times,
+	 * so when there are many btree nodes, GC can process
+	 * more nodes each time, otherwise, GC will process less
+	 * nodes each time (but no less than MIN_GC_NODES)
+	 */
+	min_nodes = c->gc_stats.nodes / MAX_GC_TIMES;
+	if (min_nodes < MIN_GC_NODES)
+		min_nodes = MIN_GC_NODES;
+
+	return min_nodes;
+}
+
+
 static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 			    struct closure *writes, struct gc_stat *gc)
 {
@@ -1585,6 +1614,13 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 		memmove(r + 1, r, sizeof(r[0]) * (GC_MERGE_NODES - 1));
 		r->b = NULL;
 
+		if (atomic_read(&b->c->search_inflight) &&
+		    gc->nodes >= gc->nodes_pre + btree_gc_min_nodes(b->c)) {
+			gc->nodes_pre =  gc->nodes;
+			ret = -EAGAIN;
+			break;
+		}
+
 		if (need_resched()) {
 			ret = -EAGAIN;
 			break;
@@ -1753,7 +1789,10 @@ static void bch_btree_gc(struct cache_set *c)
 		closure_sync(&writes);
 		cond_resched();
 
-		if (ret && ret != -EAGAIN)
+		if (ret == -EAGAIN)
+			schedule_timeout_interruptible(msecs_to_jiffies
+						       (GC_SLEEP_MS));
+		else if (ret)
 			pr_warn("gc failed!");
 	} while (ret && !test_bit(CACHE_SET_IO_DISABLE, &c->flags));
 
@@ -1834,8 +1873,14 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
 		do {
 			k = bch_btree_iter_next_filter(&iter, &b->keys,
 						       bch_ptr_bad);
-			if (k)
+			if (k) {
 				btree_node_prefetch(b, k);
+				/*
+				 * initiallize c->gc_stats.nodes
+				 * for incremental GC
+				 */
+				b->c->gc_stats.nodes++;
+			}
 
 			if (p)
 				ret = btree(check_recurse, p, b, op);
diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h
index d211e2c25b6b..68e9d926134d 100644
--- a/drivers/md/bcache/btree.h
+++ b/drivers/md/bcache/btree.h
@@ -152,7 +152,7 @@ static inline bool btree_node_ ## flag(struct btree *b)			\
 {	return test_bit(BTREE_NODE_ ## flag, &b->flags); }		\
 									\
 static inline void set_btree_node_ ## flag(struct btree *b)		\
-{	set_bit(BTREE_NODE_ ## flag, &b->flags); }			\
+{	set_bit(BTREE_NODE_ ## flag, &b->flags); }
 
 enum btree_flags {
 	BTREE_NODE_io_error,
diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c
index 0e14969182c6..618253683d40 100644
--- a/drivers/md/bcache/closure.c
+++ b/drivers/md/bcache/closure.c
@@ -199,11 +199,16 @@ static const struct file_operations debug_ops = {
 	.release	= single_release
 };
 
-int __init closure_debug_init(void)
+void  __init closure_debug_init(void)
 {
-	closure_debug = debugfs_create_file("closures",
-				0400, bcache_debug, NULL, &debug_ops);
-	return IS_ERR_OR_NULL(closure_debug);
+	if (!IS_ERR_OR_NULL(bcache_debug))
+		/*
+		 * it is unnecessary to check return value of
+		 * debugfs_create_file(), we should not care
+		 * about this.
+		 */
+		closure_debug = debugfs_create_file(
+			"closures", 0400, bcache_debug, NULL, &debug_ops);
 }
 #endif
 
diff --git a/drivers/md/bcache/closure.h b/drivers/md/bcache/closure.h
index 71427eb5fdae..7c2c5bc7c88b 100644
--- a/drivers/md/bcache/closure.h
+++ b/drivers/md/bcache/closure.h
@@ -186,13 +186,13 @@ static inline void closure_sync(struct closure *cl)
 
 #ifdef CONFIG_BCACHE_CLOSURES_DEBUG
 
-int closure_debug_init(void);
+void closure_debug_init(void);
 void closure_debug_create(struct closure *cl);
 void closure_debug_destroy(struct closure *cl);
 
 #else
 
-static inline int closure_debug_init(void) { return 0; }
+static inline void closure_debug_init(void) {}
 static inline void closure_debug_create(struct closure *cl) {}
 static inline void closure_debug_destroy(struct closure *cl) {}
 
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index d030ce3025a6..12034c07257b 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -110,11 +110,15 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio)
 	struct bio_vec bv, cbv;
 	struct bvec_iter iter, citer = { 0 };
 
-	check = bio_clone_kmalloc(bio, GFP_NOIO);
+	check = bio_kmalloc(GFP_NOIO, bio_segments(bio));
 	if (!check)
 		return;
+	check->bi_disk = bio->bi_disk;
 	check->bi_opf = REQ_OP_READ;
+	check->bi_iter.bi_sector = bio->bi_iter.bi_sector;
+	check->bi_iter.bi_size = bio->bi_iter.bi_size;
 
+	bch_bio_map(check, NULL);
 	if (bch_bio_alloc_pages(check, GFP_NOIO))
 		goto out_put;
 
@@ -248,11 +252,12 @@ void bch_debug_exit(void)
 		debugfs_remove_recursive(bcache_debug);
 }
 
-int __init bch_debug_init(struct kobject *kobj)
+void __init bch_debug_init(struct kobject *kobj)
 {
-	if (!IS_ENABLED(CONFIG_DEBUG_FS))
-		return 0;
-
+	/*
+	 * it is unnecessary to check return value of
+	 * debugfs_create_file(), we should not care
+	 * about this.
+	 */
 	bcache_debug = debugfs_create_dir("bcache", NULL);
-	return IS_ERR_OR_NULL(bcache_debug);
 }
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 18f1b5239620..10748c626a1d 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -828,6 +828,7 @@ void bch_journal_free(struct cache_set *c)
 	free_pages((unsigned long) c->journal.w[1].data, JSET_BITS);
 	free_pages((unsigned long) c->journal.w[0].data, JSET_BITS);
 	free_fifo(&c->journal.pin);
+	free_heap(&c->flush_btree);
 }
 
 int bch_journal_alloc(struct cache_set *c)
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index ae67f5fa8047..7dbe8b6316a0 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -107,7 +107,7 @@ static int bch_keylist_realloc(struct keylist *l, unsigned u64s,
 	/*
 	 * The journalling code doesn't handle the case where the keys to insert
 	 * is bigger than an empty write: If we just return -ENOMEM here,
-	 * bio_insert() and bio_invalidate() will insert the keys created so far
+	 * bch_data_insert_keys() will insert the keys created so far
 	 * and finish the rest when the keylist is empty.
 	 */
 	if (newsize * sizeof(uint64_t) > block_bytes(c) - sizeof(struct jset))
@@ -667,8 +667,7 @@ static void backing_request_endio(struct bio *bio)
 static void bio_complete(struct search *s)
 {
 	if (s->orig_bio) {
-		generic_end_io_acct(s->d->disk->queue,
-				    bio_data_dir(s->orig_bio),
+		generic_end_io_acct(s->d->disk->queue, bio_op(s->orig_bio),
 				    &s->d->disk->part0, s->start_time);
 
 		trace_bcache_request_end(s->d, s->orig_bio);
@@ -702,6 +701,8 @@ static void search_free(struct closure *cl)
 {
 	struct search *s = container_of(cl, struct search, cl);
 
+	atomic_dec(&s->d->c->search_inflight);
+
 	if (s->iop.bio)
 		bio_put(s->iop.bio);
 
@@ -719,6 +720,7 @@ static inline struct search *search_alloc(struct bio *bio,
 
 	closure_init(&s->cl, NULL);
 	do_bio_hook(s, bio, request_endio);
+	atomic_inc(&d->c->search_inflight);
 
 	s->orig_bio		= bio;
 	s->cache_miss		= NULL;
@@ -1062,8 +1064,7 @@ static void detached_dev_end_io(struct bio *bio)
 	bio->bi_end_io = ddip->bi_end_io;
 	bio->bi_private = ddip->bi_private;
 
-	generic_end_io_acct(ddip->d->disk->queue,
-			    bio_data_dir(bio),
+	generic_end_io_acct(ddip->d->disk->queue, bio_op(bio),
 			    &ddip->d->disk->part0, ddip->start_time);
 
 	if (bio->bi_status) {
@@ -1102,6 +1103,44 @@ static void detached_dev_do_request(struct bcache_device *d, struct bio *bio)
 		generic_make_request(bio);
 }
 
+static void quit_max_writeback_rate(struct cache_set *c,
+				    struct cached_dev *this_dc)
+{
+	int i;
+	struct bcache_device *d;
+	struct cached_dev *dc;
+
+	/*
+	 * mutex bch_register_lock may compete with other parallel requesters,
+	 * or attach/detach operations on other backing device. Waiting to
+	 * the mutex lock may increase I/O request latency for seconds or more.
+	 * To avoid such situation, if mutext_trylock() failed, only writeback
+	 * rate of current cached device is set to 1, and __update_write_back()
+	 * will decide writeback rate of other cached devices (remember now
+	 * c->idle_counter is 0 already).
+	 */
+	if (mutex_trylock(&bch_register_lock)) {
+		for (i = 0; i < c->devices_max_used; i++) {
+			if (!c->devices[i])
+				continue;
+
+			if (UUID_FLASH_ONLY(&c->uuids[i]))
+				continue;
+
+			d = c->devices[i];
+			dc = container_of(d, struct cached_dev, disk);
+			/*
+			 * set writeback rate to default minimum value,
+			 * then let update_writeback_rate() to decide the
+			 * upcoming rate.
+			 */
+			atomic_long_set(&dc->writeback_rate.rate, 1);
+		}
+		mutex_unlock(&bch_register_lock);
+	} else
+		atomic_long_set(&this_dc->writeback_rate.rate, 1);
+}
+
 /* Cached devices - read & write stuff */
 
 static blk_qc_t cached_dev_make_request(struct request_queue *q,
@@ -1119,8 +1158,25 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q,
 		return BLK_QC_T_NONE;
 	}
 
-	atomic_set(&dc->backing_idle, 0);
-	generic_start_io_acct(q, rw, bio_sectors(bio), &d->disk->part0);
+	if (likely(d->c)) {
+		if (atomic_read(&d->c->idle_counter))
+			atomic_set(&d->c->idle_counter, 0);
+		/*
+		 * If at_max_writeback_rate of cache set is true and new I/O
+		 * comes, quit max writeback rate of all cached devices
+		 * attached to this cache set, and set at_max_writeback_rate
+		 * to false.
+		 */
+		if (unlikely(atomic_read(&d->c->at_max_writeback_rate) == 1)) {
+			atomic_set(&d->c->at_max_writeback_rate, 0);
+			quit_max_writeback_rate(d->c, dc);
+		}
+	}
+
+	generic_start_io_acct(q,
+			      bio_op(bio),
+			      bio_sectors(bio),
+			      &d->disk->part0);
 
 	bio_set_dev(bio, dc->bdev);
 	bio->bi_iter.bi_sector += dc->sb.data_offset;
@@ -1229,7 +1285,6 @@ static blk_qc_t flash_dev_make_request(struct request_queue *q,
 	struct search *s;
 	struct closure *cl;
 	struct bcache_device *d = bio->bi_disk->private_data;
-	int rw = bio_data_dir(bio);
 
 	if (unlikely(d->c && test_bit(CACHE_SET_IO_DISABLE, &d->c->flags))) {
 		bio->bi_status = BLK_STS_IOERR;
@@ -1237,7 +1292,7 @@ static blk_qc_t flash_dev_make_request(struct request_queue *q,
 		return BLK_QC_T_NONE;
 	}
 
-	generic_start_io_acct(q, rw, bio_sectors(bio), &d->disk->part0);
+	generic_start_io_acct(q, bio_op(bio), bio_sectors(bio), &d->disk->part0);
 
 	s = search_alloc(bio, d);
 	cl = &s->cl;
@@ -1254,7 +1309,7 @@ static blk_qc_t flash_dev_make_request(struct request_queue *q,
 				      flash_dev_nodata,
 				      bcache_wq);
 		return BLK_QC_T_NONE;
-	} else if (rw) {
+	} else if (bio_data_dir(bio)) {
 		bch_keybuf_check_overlapping(&s->iop.c->moving_gc_keys,
 					&KEY(d->id, bio->bi_iter.bi_sector, 0),
 					&KEY(d->id, bio_end_sector(bio), 0));
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index fa4058e43202..55a37641aa95 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -181,7 +181,7 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 		goto err;
 	}
 
-	sb->last_mount = get_seconds();
+	sb->last_mount = (u32)ktime_get_real_seconds();
 	err = NULL;
 
 	get_page(bh->b_page);
@@ -696,12 +696,14 @@ static void bcache_device_detach(struct bcache_device *d)
 {
 	lockdep_assert_held(&bch_register_lock);
 
+	atomic_dec(&d->c->attached_dev_nr);
+
 	if (test_bit(BCACHE_DEV_DETACHING, &d->flags)) {
 		struct uuid_entry *u = d->c->uuids + d->id;
 
 		SET_UUID_FLASH_ONLY(u, 0);
 		memcpy(u->uuid, invalid_uuid, 16);
-		u->invalidated = cpu_to_le32(get_seconds());
+		u->invalidated = cpu_to_le32((u32)ktime_get_real_seconds());
 		bch_uuid_write(d->c);
 	}
 
@@ -796,11 +798,12 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 		return idx;
 
 	if (bioset_init(&d->bio_split, 4, offsetof(struct bbio, bio),
-			BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER) ||
-	    !(d->disk = alloc_disk(BCACHE_MINORS))) {
-		ida_simple_remove(&bcache_device_idx, idx);
-		return -ENOMEM;
-	}
+			BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER))
+		goto err;
+
+	d->disk = alloc_disk(BCACHE_MINORS);
+	if (!d->disk)
+		goto err;
 
 	set_capacity(d->disk, sectors);
 	snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", idx);
@@ -834,6 +837,11 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 	blk_queue_write_cache(q, true, true);
 
 	return 0;
+
+err:
+	ida_simple_remove(&bcache_device_idx, idx);
+	return -ENOMEM;
+
 }
 
 /* Cached device */
@@ -1027,7 +1035,7 @@ void bch_cached_dev_detach(struct cached_dev *dc)
 int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 			  uint8_t *set_uuid)
 {
-	uint32_t rtime = cpu_to_le32(get_seconds());
+	uint32_t rtime = cpu_to_le32((u32)ktime_get_real_seconds());
 	struct uuid_entry *u;
 	struct cached_dev *exist_dc, *t;
 
@@ -1070,7 +1078,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 	    (BDEV_STATE(&dc->sb) == BDEV_STATE_STALE ||
 	     BDEV_STATE(&dc->sb) == BDEV_STATE_NONE)) {
 		memcpy(u->uuid, invalid_uuid, 16);
-		u->invalidated = cpu_to_le32(get_seconds());
+		u->invalidated = cpu_to_le32((u32)ktime_get_real_seconds());
 		u = NULL;
 	}
 
@@ -1138,6 +1146,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 
 	bch_cached_dev_run(dc);
 	bcache_device_link(&dc->disk, c, "bdev");
+	atomic_inc(&c->attached_dev_nr);
 
 	/* Allow the writeback thread to proceed */
 	up_write(&dc->writeback_lock);
@@ -1285,6 +1294,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page,
 	pr_info("registered backing device %s", dc->backing_dev_name);
 
 	list_add(&dc->list, &uncached_devices);
+	/* attach to a matched cache set if it exists */
 	list_for_each_entry(c, &bch_cache_sets, list)
 		bch_cached_dev_attach(dc, c, NULL);
 
@@ -1311,6 +1321,8 @@ static void flash_dev_free(struct closure *cl)
 {
 	struct bcache_device *d = container_of(cl, struct bcache_device, cl);
 	mutex_lock(&bch_register_lock);
+	atomic_long_sub(bcache_dev_sectors_dirty(d),
+			&d->c->flash_dev_dirty_sectors);
 	bcache_device_free(d);
 	mutex_unlock(&bch_register_lock);
 	kobject_put(&d->kobj);
@@ -1390,7 +1402,7 @@ int bch_flash_dev_create(struct cache_set *c, uint64_t size)
 
 	get_random_bytes(u->uuid, 16);
 	memset(u->label, 0, 32);
-	u->first_reg = u->last_reg = cpu_to_le32(get_seconds());
+	u->first_reg = u->last_reg = cpu_to_le32((u32)ktime_get_real_seconds());
 
 	SET_UUID_FLASH_ONLY(u, 1);
 	u->sectors = size >> 9;
@@ -1687,6 +1699,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	c->block_bits		= ilog2(sb->block_size);
 	c->nr_uuids		= bucket_bytes(c) / sizeof(struct uuid_entry);
 	c->devices_max_used	= 0;
+	atomic_set(&c->attached_dev_nr, 0);
 	c->btree_pages		= bucket_pages(c);
 	if (c->btree_pages > BTREE_MAX_PAGES)
 		c->btree_pages = max_t(int, c->btree_pages / 4,
@@ -1894,7 +1907,7 @@ static void run_cache_set(struct cache_set *c)
 		goto err;
 
 	closure_sync(&cl);
-	c->sb.last_mount = get_seconds();
+	c->sb.last_mount = (u32)ktime_get_real_seconds();
 	bcache_write_super(c);
 
 	list_for_each_entry_safe(dc, t, &uncached_devices, list)
@@ -2163,8 +2176,12 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 	if (!try_module_get(THIS_MODULE))
 		return -EBUSY;
 
-	if (!(path = kstrndup(buffer, size, GFP_KERNEL)) ||
-	    !(sb = kmalloc(sizeof(struct cache_sb), GFP_KERNEL)))
+	path = kstrndup(buffer, size, GFP_KERNEL);
+	if (!path)
+		goto err;
+
+	sb = kmalloc(sizeof(struct cache_sb), GFP_KERNEL);
+	if (!sb)
 		goto err;
 
 	err = "failed to open device";
@@ -2324,13 +2341,21 @@ static int __init bcache_init(void)
 		return bcache_major;
 	}
 
-	if (!(bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0)) ||
-	    !(bcache_kobj = kobject_create_and_add("bcache", fs_kobj)) ||
-	    bch_request_init() ||
-	    bch_debug_init(bcache_kobj) || closure_debug_init() ||
+	bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0);
+	if (!bcache_wq)
+		goto err;
+
+	bcache_kobj = kobject_create_and_add("bcache", fs_kobj);
+	if (!bcache_kobj)
+		goto err;
+
+	if (bch_request_init() ||
 	    sysfs_create_files(bcache_kobj, files))
 		goto err;
 
+	bch_debug_init(bcache_kobj);
+	closure_debug_init();
+
 	return 0;
 err:
 	bcache_exit();
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 225b15aa0340..81d3520b0702 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -149,6 +149,7 @@ SHOW(__bch_cached_dev)
 	struct cached_dev *dc = container_of(kobj, struct cached_dev,
 					     disk.kobj);
 	const char *states[] = { "no cache", "clean", "dirty", "inconsistent" };
+	int wb = dc->writeback_running;
 
 #define var(stat)		(dc->stat)
 
@@ -170,7 +171,8 @@ SHOW(__bch_cached_dev)
 	var_printf(writeback_running,	"%i");
 	var_print(writeback_delay);
 	var_print(writeback_percent);
-	sysfs_hprint(writeback_rate,	dc->writeback_rate.rate << 9);
+	sysfs_hprint(writeback_rate,
+		     wb ? atomic_long_read(&dc->writeback_rate.rate) << 9 : 0);
 	sysfs_hprint(io_errors,		atomic_read(&dc->io_errors));
 	sysfs_printf(io_error_limit,	"%i", dc->error_limit);
 	sysfs_printf(io_disable,	"%i", dc->io_disable);
@@ -188,15 +190,22 @@ SHOW(__bch_cached_dev)
 		char change[20];
 		s64 next_io;
 
-		bch_hprint(rate,	dc->writeback_rate.rate << 9);
-		bch_hprint(dirty,	bcache_dev_sectors_dirty(&dc->disk) << 9);
-		bch_hprint(target,	dc->writeback_rate_target << 9);
-		bch_hprint(proportional,dc->writeback_rate_proportional << 9);
-		bch_hprint(integral,	dc->writeback_rate_integral_scaled << 9);
-		bch_hprint(change,	dc->writeback_rate_change << 9);
-
-		next_io = div64_s64(dc->writeback_rate.next - local_clock(),
-				    NSEC_PER_MSEC);
+		/*
+		 * Except for dirty and target, other values should
+		 * be 0 if writeback is not running.
+		 */
+		bch_hprint(rate,
+			   wb ? atomic_long_read(&dc->writeback_rate.rate) << 9
+			      : 0);
+		bch_hprint(dirty, bcache_dev_sectors_dirty(&dc->disk) << 9);
+		bch_hprint(target, dc->writeback_rate_target << 9);
+		bch_hprint(proportional,
+			   wb ? dc->writeback_rate_proportional << 9 : 0);
+		bch_hprint(integral,
+			   wb ? dc->writeback_rate_integral_scaled << 9 : 0);
+		bch_hprint(change, wb ? dc->writeback_rate_change << 9 : 0);
+		next_io = wb ? div64_s64(dc->writeback_rate.next-local_clock(),
+					 NSEC_PER_MSEC) : 0;
 
 		return sprintf(buf,
 			       "rate:\t\t%s/sec\n"
@@ -255,8 +264,19 @@ STORE(__cached_dev)
 
 	sysfs_strtoul_clamp(writeback_percent, dc->writeback_percent, 0, 40);
 
-	sysfs_strtoul_clamp(writeback_rate,
-			    dc->writeback_rate.rate, 1, INT_MAX);
+	if (attr == &sysfs_writeback_rate) {
+		ssize_t ret;
+		long int v = atomic_long_read(&dc->writeback_rate.rate);
+
+		ret = strtoul_safe_clamp(buf, v, 1, INT_MAX);
+
+		if (!ret) {
+			atomic_long_set(&dc->writeback_rate.rate, v);
+			ret = size;
+		}
+
+		return ret;
+	}
 
 	sysfs_strtoul_clamp(writeback_rate_update_seconds,
 			    dc->writeback_rate_update_seconds,
@@ -338,8 +358,8 @@ STORE(__cached_dev)
 			if (!v)
 				return size;
 		}
-
-		pr_err("Can't attach %s: cache set not found", buf);
+		if (v == -ENOENT)
+			pr_err("Can't attach %s: cache set not found", buf);
 		return v;
 	}
 
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index fc479b026d6d..b15256bcf0e7 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -200,7 +200,7 @@ uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done)
 {
 	uint64_t now = local_clock();
 
-	d->next += div_u64(done * NSEC_PER_SEC, d->rate);
+	d->next += div_u64(done * NSEC_PER_SEC, atomic_long_read(&d->rate));
 
 	/* Bound the time.  Don't let us fall further than 2 seconds behind
 	 * (this prevents unnecessary backlog that would make it impossible
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index cced87f8eb27..f7b0133c9d2f 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -442,7 +442,7 @@ struct bch_ratelimit {
 	 * Rate at which we want to do work, in units per second
 	 * The units here correspond to the units passed to bch_next_delay()
 	 */
-	uint32_t		rate;
+	atomic_long_t		rate;
 };
 
 static inline void bch_ratelimit_reset(struct bch_ratelimit *d)
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index ad45ebe1a74b..481d4cf38ac0 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -27,7 +27,7 @@ static uint64_t __calc_target_rate(struct cached_dev *dc)
 	 * flash-only devices
 	 */
 	uint64_t cache_sectors = c->nbuckets * c->sb.bucket_size -
-				bcache_flash_devs_sectors_dirty(c);
+				atomic_long_read(&c->flash_dev_dirty_sectors);
 
 	/*
 	 * Unfortunately there is no control of global dirty data.  If the
@@ -104,11 +104,56 @@ static void __update_writeback_rate(struct cached_dev *dc)
 
 	dc->writeback_rate_proportional = proportional_scaled;
 	dc->writeback_rate_integral_scaled = integral_scaled;
-	dc->writeback_rate_change = new_rate - dc->writeback_rate.rate;
-	dc->writeback_rate.rate = new_rate;
+	dc->writeback_rate_change = new_rate -
+			atomic_long_read(&dc->writeback_rate.rate);
+	atomic_long_set(&dc->writeback_rate.rate, new_rate);
 	dc->writeback_rate_target = target;
 }
 
+static bool set_at_max_writeback_rate(struct cache_set *c,
+				       struct cached_dev *dc)
+{
+	/*
+	 * Idle_counter is increased everytime when update_writeback_rate() is
+	 * called. If all backing devices attached to the same cache set have
+	 * identical dc->writeback_rate_update_seconds values, it is about 6
+	 * rounds of update_writeback_rate() on each backing device before
+	 * c->at_max_writeback_rate is set to 1, and then max wrteback rate set
+	 * to each dc->writeback_rate.rate.
+	 * In order to avoid extra locking cost for counting exact dirty cached
+	 * devices number, c->attached_dev_nr is used to calculate the idle
+	 * throushold. It might be bigger if not all cached device are in write-
+	 * back mode, but it still works well with limited extra rounds of
+	 * update_writeback_rate().
+	 */
+	if (atomic_inc_return(&c->idle_counter) <
+	    atomic_read(&c->attached_dev_nr) * 6)
+		return false;
+
+	if (atomic_read(&c->at_max_writeback_rate) != 1)
+		atomic_set(&c->at_max_writeback_rate, 1);
+
+	atomic_long_set(&dc->writeback_rate.rate, INT_MAX);
+
+	/* keep writeback_rate_target as existing value */
+	dc->writeback_rate_proportional = 0;
+	dc->writeback_rate_integral_scaled = 0;
+	dc->writeback_rate_change = 0;
+
+	/*
+	 * Check c->idle_counter and c->at_max_writeback_rate agagain in case
+	 * new I/O arrives during before set_at_max_writeback_rate() returns.
+	 * Then the writeback rate is set to 1, and its new value should be
+	 * decided via __update_writeback_rate().
+	 */
+	if ((atomic_read(&c->idle_counter) <
+	     atomic_read(&c->attached_dev_nr) * 6) ||
+	    !atomic_read(&c->at_max_writeback_rate))
+		return false;
+
+	return true;
+}
+
 static void update_writeback_rate(struct work_struct *work)
 {
 	struct cached_dev *dc = container_of(to_delayed_work(work),
@@ -136,13 +181,20 @@ static void update_writeback_rate(struct work_struct *work)
 		return;
 	}
 
-	down_read(&dc->writeback_lock);
-
-	if (atomic_read(&dc->has_dirty) &&
-	    dc->writeback_percent)
-		__update_writeback_rate(dc);
+	if (atomic_read(&dc->has_dirty) && dc->writeback_percent) {
+		/*
+		 * If the whole cache set is idle, set_at_max_writeback_rate()
+		 * will set writeback rate to a max number. Then it is
+		 * unncessary to update writeback rate for an idle cache set
+		 * in maximum writeback rate number(s).
+		 */
+		if (!set_at_max_writeback_rate(c, dc)) {
+			down_read(&dc->writeback_lock);
+			__update_writeback_rate(dc);
+			up_read(&dc->writeback_lock);
+		}
+	}
 
-	up_read(&dc->writeback_lock);
 
 	/*
 	 * CACHE_SET_IO_DISABLE might be set via sysfs interface,
@@ -422,27 +474,6 @@ static void read_dirty(struct cached_dev *dc)
 
 		delay = writeback_delay(dc, size);
 
-		/* If the control system would wait for at least half a
-		 * second, and there's been no reqs hitting the backing disk
-		 * for awhile: use an alternate mode where we have at most
-		 * one contiguous set of writebacks in flight at a time.  If
-		 * someone wants to do IO it will be quick, as it will only
-		 * have to contend with one operation in flight, and we'll
-		 * be round-tripping data to the backing disk as quickly as
-		 * it can accept it.
-		 */
-		if (delay >= HZ / 2) {
-			/* 3 means at least 1.5 seconds, up to 7.5 if we
-			 * have slowed way down.
-			 */
-			if (atomic_inc_return(&dc->backing_idle) >= 3) {
-				/* Wait for current I/Os to finish */
-				closure_sync(&cl);
-				/* And immediately launch a new set. */
-				delay = 0;
-			}
-		}
-
 		while (!kthread_should_stop() &&
 		       !test_bit(CACHE_SET_IO_DISABLE, &dc->disk.c->flags) &&
 		       delay) {
@@ -476,6 +507,9 @@ void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned inode,
 	if (!d)
 		return;
 
+	if (UUID_FLASH_ONLY(&c->uuids[inode]))
+		atomic_long_add(nr_sectors, &c->flash_dev_dirty_sectors);
+
 	stripe = offset_to_stripe(d, offset);
 	stripe_offset = offset & (d->stripe_size - 1);
 
@@ -673,10 +707,14 @@ static int bch_writeback_thread(void *arg)
 }
 
 /* Init */
+#define INIT_KEYS_EACH_TIME	500000
+#define INIT_KEYS_SLEEP_MS	100
 
 struct sectors_dirty_init {
 	struct btree_op	op;
 	unsigned	inode;
+	size_t		count;
+	struct bkey	start;
 };
 
 static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b,
@@ -691,18 +729,37 @@ static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b,
 		bcache_dev_sectors_dirty_add(b->c, KEY_INODE(k),
 					     KEY_START(k), KEY_SIZE(k));
 
+	op->count++;
+	if (atomic_read(&b->c->search_inflight) &&
+	    !(op->count % INIT_KEYS_EACH_TIME)) {
+		bkey_copy_key(&op->start, k);
+		return -EAGAIN;
+	}
+
 	return MAP_CONTINUE;
 }
 
 void bch_sectors_dirty_init(struct bcache_device *d)
 {
 	struct sectors_dirty_init op;
+	int ret;
 
 	bch_btree_op_init(&op.op, -1);
 	op.inode = d->id;
-
-	bch_btree_map_keys(&op.op, d->c, &KEY(op.inode, 0, 0),
-			   sectors_dirty_init_fn, 0);
+	op.count = 0;
+	op.start = KEY(op.inode, 0, 0);
+
+	do {
+		ret = bch_btree_map_keys(&op.op, d->c, &op.start,
+					 sectors_dirty_init_fn, 0);
+		if (ret == -EAGAIN)
+			schedule_timeout_interruptible(
+				msecs_to_jiffies(INIT_KEYS_SLEEP_MS));
+		else if (ret < 0) {
+			pr_warn("sectors dirty init failed, ret=%d!", ret);
+			break;
+		}
+	} while (ret == -EAGAIN);
 }
 
 void bch_cached_dev_writeback_init(struct cached_dev *dc)
@@ -715,7 +772,7 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc)
 	dc->writeback_running		= true;
 	dc->writeback_percent		= 10;
 	dc->writeback_delay		= 30;
-	dc->writeback_rate.rate		= 1024;
+	atomic_long_set(&dc->writeback_rate.rate, 1024);
 	dc->writeback_rate_minimum	= 8;
 
 	dc->writeback_rate_update_seconds = WRITEBACK_RATE_UPDATE_SECS_DEFAULT;
diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h
index 610fb01de629..3745d7004c47 100644
--- a/drivers/md/bcache/writeback.h
+++ b/drivers/md/bcache/writeback.h
@@ -28,25 +28,6 @@ static inline uint64_t bcache_dev_sectors_dirty(struct bcache_device *d)
 	return ret;
 }
 
-static inline uint64_t  bcache_flash_devs_sectors_dirty(struct cache_set *c)
-{
-	uint64_t i, ret = 0;
-
-	mutex_lock(&bch_register_lock);
-
-	for (i = 0; i < c->devices_max_used; i++) {
-		struct bcache_device *d = c->devices[i];
-
-		if (!d || !UUID_FLASH_ONLY(&c->uuids[i]))
-			continue;
-		ret += bcache_dev_sectors_dirty(d);
-	}
-
-	mutex_unlock(&bch_register_lock);
-
-	return ret;
-}
-
 static inline unsigned offset_to_stripe(struct bcache_device *d,
 					uint64_t offset)
 {
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index b0dd7027848b..20f7e4ef5342 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -609,7 +609,8 @@ static void start_io_acct(struct dm_io *io)
 
 	io->start_time = jiffies;
 
-	generic_start_io_acct(md->queue, rw, bio_sectors(bio), &dm_disk(md)->part0);
+	generic_start_io_acct(md->queue, bio_op(bio), bio_sectors(bio),
+			      &dm_disk(md)->part0);
 
 	atomic_set(&dm_disk(md)->part0.in_flight[rw],
 		   atomic_inc_return(&md->pending[rw]));
@@ -628,7 +629,8 @@ static void end_io_acct(struct dm_io *io)
 	int pending;
 	int rw = bio_data_dir(bio);
 
-	generic_end_io_acct(md->queue, rw, &dm_disk(md)->part0, io->start_time);
+	generic_end_io_acct(md->queue, bio_op(bio), &dm_disk(md)->part0,
+			    io->start_time);
 
 	if (unlikely(dm_stats_used(&md->stats)))
 		dm_stats_account_io(&md->stats, bio_data_dir(bio),
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 021cbf9ef1bf..e8a74e92be30 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -304,15 +304,6 @@ static void recover_bitmaps(struct md_thread *thread)
 	while (cinfo->recovery_map) {
 		slot = fls64((u64)cinfo->recovery_map) - 1;
 
-		/* Clear suspend_area associated with the bitmap */
-		spin_lock_irq(&cinfo->suspend_lock);
-		list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list)
-			if (slot == s->slot) {
-				list_del(&s->list);
-				kfree(s);
-			}
-		spin_unlock_irq(&cinfo->suspend_lock);
-
 		snprintf(str, 64, "bitmap%04d", slot);
 		bm_lockres = lockres_init(mddev, str, NULL, 1);
 		if (!bm_lockres) {
@@ -331,14 +322,30 @@ static void recover_bitmaps(struct md_thread *thread)
 			pr_err("md-cluster: Could not copy data from bitmap %d\n", slot);
 			goto clear_bit;
 		}
+
+		/* Clear suspend_area associated with the bitmap */
+		spin_lock_irq(&cinfo->suspend_lock);
+		list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list)
+			if (slot == s->slot) {
+				list_del(&s->list);
+				kfree(s);
+			}
+		spin_unlock_irq(&cinfo->suspend_lock);
+
 		if (hi > 0) {
 			if (lo < mddev->recovery_cp)
 				mddev->recovery_cp = lo;
 			/* wake up thread to continue resync in case resync
 			 * is not finished */
 			if (mddev->recovery_cp != MaxSector) {
-			    set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-			    md_wakeup_thread(mddev->thread);
+				/*
+				 * clear the REMOTE flag since we will launch
+				 * resync thread in current node.
+				 */
+				clear_bit(MD_RESYNCING_REMOTE,
+					  &mddev->recovery);
+				set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+				md_wakeup_thread(mddev->thread);
 			}
 		}
 clear_bit:
@@ -457,6 +464,11 @@ static void process_suspend_info(struct mddev *mddev,
 	struct suspend_info *s;
 
 	if (!hi) {
+		/*
+		 * clear the REMOTE flag since resync or recovery is finished
+		 * in remote node.
+		 */
+		clear_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
 		remove_suspend_info(mddev, slot);
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 		md_wakeup_thread(mddev->thread);
@@ -585,6 +597,7 @@ static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
 		revalidate_disk(mddev->gendisk);
 		break;
 	case RESYNCING:
+		set_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
 		process_suspend_info(mddev, le32_to_cpu(msg->slot),
 				     le64_to_cpu(msg->low),
 				     le64_to_cpu(msg->high));
@@ -1265,8 +1278,18 @@ static int resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi)
 static int resync_finish(struct mddev *mddev)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
+
+	clear_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
 	dlm_unlock_sync(cinfo->resync_lockres);
-	return resync_info_update(mddev, 0, 0);
+
+	/*
+	 * If resync thread is interrupted so we can't say resync is finished,
+	 * another node will launch resync thread to continue.
+	 */
+	if (test_bit(MD_CLOSING, &mddev->flags))
+		return 0;
+	else
+		return resync_info_update(mddev, 0, 0);
 }
 
 static int area_resyncing(struct mddev *mddev, int direction,
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 994aed2f9dff..724def2f9eaa 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -204,10 +204,6 @@ static int start_readonly;
  */
 static bool create_on_open = true;
 
-/* bio_clone_mddev
- * like bio_clone_bioset, but with a local bio set
- */
-
 struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
 			    struct mddev *mddev)
 {
@@ -335,6 +331,7 @@ EXPORT_SYMBOL(md_handle_request);
 static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int rw = bio_data_dir(bio);
+	const int sgrp = op_stat_group(bio_op(bio));
 	struct mddev *mddev = q->queuedata;
 	unsigned int sectors;
 	int cpu;
@@ -363,8 +360,8 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
 	md_handle_request(mddev, bio);
 
 	cpu = part_stat_lock();
-	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
-	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors);
+	part_stat_inc(cpu, &mddev->gendisk->part0, ios[sgrp]);
+	part_stat_add(cpu, &mddev->gendisk->part0, sectors[sgrp], sectors);
 	part_stat_unlock();
 
 	return BLK_QC_T_NONE;
@@ -7680,6 +7677,23 @@ static int status_resync(struct seq_file *seq, struct mddev *mddev)
 		resync -= atomic_read(&mddev->recovery_active);
 
 	if (resync == 0) {
+		if (test_bit(MD_RESYNCING_REMOTE, &mddev->recovery)) {
+			struct md_rdev *rdev;
+
+			rdev_for_each(rdev, mddev)
+				if (rdev->raid_disk >= 0 &&
+				    !test_bit(Faulty, &rdev->flags) &&
+				    rdev->recovery_offset != MaxSector &&
+				    rdev->recovery_offset) {
+					seq_printf(seq, "\trecover=REMOTE");
+					return 1;
+				}
+			if (mddev->reshape_position != MaxSector)
+				seq_printf(seq, "\treshape=REMOTE");
+			else
+				seq_printf(seq, "\tresync=REMOTE");
+			return 1;
+		}
 		if (mddev->recovery_cp < MaxSector) {
 			seq_printf(seq, "\tresync=PENDING");
 			return 1;
@@ -8046,8 +8060,7 @@ static int is_mddev_idle(struct mddev *mddev, int init)
 	rcu_read_lock();
 	rdev_for_each_rcu(rdev, mddev) {
 		struct gendisk *disk = rdev->bdev->bd_contains->bd_disk;
-		curr_events = (int)part_stat_read(&disk->part0, sectors[0]) +
-			      (int)part_stat_read(&disk->part0, sectors[1]) -
+		curr_events = (int)part_stat_read_accum(&disk->part0, sectors) -
 			      atomic_read(&disk->sync_io);
 		/* sync IO will cause sync_io to increase before the disk_stats
 		 * as sync_io is counted when a request starts, and
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 2d148bdaba74..8afd6bfdbfb9 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -496,6 +496,7 @@ enum recovery_flags {
 	MD_RECOVERY_FROZEN,	/* User request to abort, and not restart, any action */
 	MD_RECOVERY_ERROR,	/* sync-action interrupted because io-error */
 	MD_RECOVERY_WAIT,	/* waiting for pers->start() to finish */
+	MD_RESYNCING_REMOTE,	/* remote node is running resync thread */
 };
 
 static inline int __must_check mddev_lock(struct mddev *mddev)
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 2b775abf377b..7416db70c6cc 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -717,7 +717,6 @@ static void r5c_disable_writeback_async(struct work_struct *work)
 static void r5l_submit_current_io(struct r5l_log *log)
 {
 	struct r5l_io_unit *io = log->current_io;
-	struct bio *bio;
 	struct r5l_meta_block *block;
 	unsigned long flags;
 	u32 crc;
@@ -730,7 +729,6 @@ static void r5l_submit_current_io(struct r5l_log *log)
 	block->meta_size = cpu_to_le32(io->meta_offset);
 	crc = crc32c_le(log->uuid_checksum, block, PAGE_SIZE);
 	block->checksum = cpu_to_le32(crc);
-	bio = io->current_bio;
 
 	log->current_io = NULL;
 	spin_lock_irqsave(&log->io_list_lock, flags);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 2031506a0ecd..81eaa221216c 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -409,16 +409,14 @@ void raid5_release_stripe(struct stripe_head *sh)
 		md_wakeup_thread(conf->mddev->thread);
 	return;
 slow_path:
-	local_irq_save(flags);
 	/* we are ok here if STRIPE_ON_RELEASE_LIST is set or not */
-	if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) {
+	if (atomic_dec_and_lock_irqsave(&sh->count, &conf->device_lock, flags)) {
 		INIT_LIST_HEAD(&list);
 		hash = sh->hash_lock_index;
 		do_release_stripe(conf, sh, &list);
-		spin_unlock(&conf->device_lock);
+		spin_unlock_irqrestore(&conf->device_lock, flags);
 		release_inactive_stripe_list(conf, &list, hash);
 	}
-	local_irq_restore(flags);
 }
 
 static inline void remove_hash(struct stripe_head *sh)
@@ -4521,6 +4519,12 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 			s->failed++;
 			if (rdev && !test_bit(Faulty, &rdev->flags))
 				do_recovery = 1;
+			else if (!rdev) {
+				rdev = rcu_dereference(
+				    conf->disks[i].replacement);
+				if (rdev && !test_bit(Faulty, &rdev->flags))
+					do_recovery = 1;
+			}
 		}
 
 		if (test_bit(R5_InJournal, &dev->flags))
diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c
index b7fad0ec5710..030b2602faf0 100644
--- a/drivers/media/cec/cec-adap.c
+++ b/drivers/media/cec/cec-adap.c
@@ -74,7 +74,7 @@ void cec_queue_event_fh(struct cec_fh *fh,
 			const struct cec_event *new_ev, u64 ts)
 {
 	static const u16 max_events[CEC_NUM_EVENTS] = {
-		1, 1, 800, 800, 8, 8,
+		1, 1, 800, 800, 8, 8, 8, 8
 	};
 	struct cec_event_entry *entry;
 	unsigned int ev_idx = new_ev->event - 1;
@@ -176,6 +176,22 @@ void cec_queue_pin_hpd_event(struct cec_adapter *adap, bool is_high, ktime_t ts)
 }
 EXPORT_SYMBOL_GPL(cec_queue_pin_hpd_event);
 
+/* Notify userspace that the 5V pin changed state at the given time. */
+void cec_queue_pin_5v_event(struct cec_adapter *adap, bool is_high, ktime_t ts)
+{
+	struct cec_event ev = {
+		.event = is_high ? CEC_EVENT_PIN_5V_HIGH :
+				   CEC_EVENT_PIN_5V_LOW,
+	};
+	struct cec_fh *fh;
+
+	mutex_lock(&adap->devnode.lock);
+	list_for_each_entry(fh, &adap->devnode.fhs, list)
+		cec_queue_event_fh(fh, &ev, ktime_to_ns(ts));
+	mutex_unlock(&adap->devnode.lock);
+}
+EXPORT_SYMBOL_GPL(cec_queue_pin_5v_event);
+
 /*
  * Queue a new message for this filehandle.
  *
diff --git a/drivers/media/cec/cec-api.c b/drivers/media/cec/cec-api.c
index 10b67fc40318..b6536bbad530 100644
--- a/drivers/media/cec/cec-api.c
+++ b/drivers/media/cec/cec-api.c
@@ -579,6 +579,14 @@ static int cec_open(struct inode *inode, struct file *filp)
 			cec_queue_event_fh(fh, &ev, 0);
 		}
 	}
+	if (adap->pin && adap->pin->ops->read_5v) {
+		err = adap->pin->ops->read_5v(adap);
+		if (err >= 0) {
+			ev.event = err ? CEC_EVENT_PIN_5V_HIGH :
+					 CEC_EVENT_PIN_5V_LOW;
+			cec_queue_event_fh(fh, &ev, 0);
+		}
+	}
 #endif
 
 	list_add(&fh->list, &devnode->fhs);
diff --git a/drivers/media/common/siano/smsdvb-debugfs.c b/drivers/media/common/siano/smsdvb-debugfs.c
index 40891f4f842b..c95d4583498e 100644
--- a/drivers/media/common/siano/smsdvb-debugfs.c
+++ b/drivers/media/common/siano/smsdvb-debugfs.c
@@ -500,7 +500,7 @@ void smsdvb_debugfs_release(struct smsdvb_client_t *client)
 	client->debugfs = NULL;
 }
 
-int smsdvb_debugfs_register(void)
+void smsdvb_debugfs_register(void)
 {
 	struct dentry *d;
 
@@ -517,15 +517,15 @@ int smsdvb_debugfs_register(void)
 	d = debugfs_create_dir("smsdvb", usb_debug_root);
 	if (IS_ERR_OR_NULL(d)) {
 		pr_err("Couldn't create sysfs node for smsdvb\n");
-		return PTR_ERR(d);
-	} else {
-		smsdvb_debugfs_usb_root = d;
+		return;
 	}
-	return 0;
+	smsdvb_debugfs_usb_root = d;
 }
 
 void smsdvb_debugfs_unregister(void)
 {
+	if (!smsdvb_debugfs_usb_root)
+		return;
 	debugfs_remove_recursive(smsdvb_debugfs_usb_root);
 	smsdvb_debugfs_usb_root = NULL;
 }
diff --git a/drivers/media/common/siano/smsdvb-main.c b/drivers/media/common/siano/smsdvb-main.c
index c0faad1ba428..43cfd1dbda01 100644
--- a/drivers/media/common/siano/smsdvb-main.c
+++ b/drivers/media/common/siano/smsdvb-main.c
@@ -1047,9 +1047,9 @@ static void smsdvb_release(struct dvb_frontend *fe)
 static const struct dvb_frontend_ops smsdvb_fe_ops = {
 	.info = {
 		.name			= "Siano Mobile Digital MDTV Receiver",
-		.frequency_min		= 44250000,
-		.frequency_max		= 867250000,
-		.frequency_stepsize	= 250000,
+		.frequency_min_hz	=  44250 * kHz,
+		.frequency_max_hz	= 867250 * kHz,
+		.frequency_stepsize_hz	=    250 * kHz,
 		.caps = FE_CAN_INVERSION_AUTO |
 			FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/common/siano/smsdvb.h b/drivers/media/common/siano/smsdvb.h
index b15754d95ec0..befeb9817e54 100644
--- a/drivers/media/common/siano/smsdvb.h
+++ b/drivers/media/common/siano/smsdvb.h
@@ -107,7 +107,7 @@ struct RECEPTION_STATISTICS_PER_SLICES_S {
 
 int smsdvb_debugfs_create(struct smsdvb_client_t *client);
 void smsdvb_debugfs_release(struct smsdvb_client_t *client);
-int smsdvb_debugfs_register(void);
+void smsdvb_debugfs_register(void);
 void smsdvb_debugfs_unregister(void);
 
 #else
@@ -119,10 +119,7 @@ static inline int smsdvb_debugfs_create(struct smsdvb_client_t *client)
 
 static inline void smsdvb_debugfs_release(struct smsdvb_client_t *client) {}
 
-static inline int smsdvb_debugfs_register(void)
-{
-	return 0;
-};
+static inline void smsdvb_debugfs_register(void) {}
 
 static inline void smsdvb_debugfs_unregister(void) {};
 
diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c
index f32ec7342ef0..5653e8eebe2b 100644
--- a/drivers/media/common/videobuf2/videobuf2-core.c
+++ b/drivers/media/common/videobuf2/videobuf2-core.c
@@ -1377,6 +1377,11 @@ int vb2_core_qbuf(struct vb2_queue *q, unsigned int index, void *pb)
 	struct vb2_buffer *vb;
 	int ret;
 
+	if (q->error) {
+		dprintk(1, "fatal error occurred on queue\n");
+		return -EIO;
+	}
+
 	vb = q->bufs[index];
 
 	switch (vb->state) {
diff --git a/drivers/media/common/videobuf2/videobuf2-dma-contig.c b/drivers/media/common/videobuf2/videobuf2-dma-contig.c
index f1178f6f434d..aff0ab7bf83d 100644
--- a/drivers/media/common/videobuf2/videobuf2-dma-contig.c
+++ b/drivers/media/common/videobuf2/videobuf2-dma-contig.c
@@ -222,7 +222,7 @@ struct vb2_dc_attachment {
 	enum dma_data_direction dma_dir;
 };
 
-static int vb2_dc_dmabuf_ops_attach(struct dma_buf *dbuf, struct device *dev,
+static int vb2_dc_dmabuf_ops_attach(struct dma_buf *dbuf,
 	struct dma_buf_attachment *dbuf_attach)
 {
 	struct vb2_dc_attachment *attach;
@@ -358,7 +358,6 @@ static const struct dma_buf_ops vb2_dc_dmabuf_ops = {
 	.map_dma_buf = vb2_dc_dmabuf_ops_map,
 	.unmap_dma_buf = vb2_dc_dmabuf_ops_unmap,
 	.map = vb2_dc_dmabuf_ops_kmap,
-	.map_atomic = vb2_dc_dmabuf_ops_kmap,
 	.vmap = vb2_dc_dmabuf_ops_vmap,
 	.mmap = vb2_dc_dmabuf_ops_mmap,
 	.release = vb2_dc_dmabuf_ops_release,
diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c
index 753ed3138dcc..015e737095cd 100644
--- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c
+++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c
@@ -371,7 +371,7 @@ struct vb2_dma_sg_attachment {
 	enum dma_data_direction dma_dir;
 };
 
-static int vb2_dma_sg_dmabuf_ops_attach(struct dma_buf *dbuf, struct device *dev,
+static int vb2_dma_sg_dmabuf_ops_attach(struct dma_buf *dbuf,
 	struct dma_buf_attachment *dbuf_attach)
 {
 	struct vb2_dma_sg_attachment *attach;
@@ -507,7 +507,6 @@ static const struct dma_buf_ops vb2_dma_sg_dmabuf_ops = {
 	.map_dma_buf = vb2_dma_sg_dmabuf_ops_map,
 	.unmap_dma_buf = vb2_dma_sg_dmabuf_ops_unmap,
 	.map = vb2_dma_sg_dmabuf_ops_kmap,
-	.map_atomic = vb2_dma_sg_dmabuf_ops_kmap,
 	.vmap = vb2_dma_sg_dmabuf_ops_vmap,
 	.mmap = vb2_dma_sg_dmabuf_ops_mmap,
 	.release = vb2_dma_sg_dmabuf_ops_release,
diff --git a/drivers/media/common/videobuf2/videobuf2-vmalloc.c b/drivers/media/common/videobuf2/videobuf2-vmalloc.c
index 359fb9804d16..6dfbd5b05907 100644
--- a/drivers/media/common/videobuf2/videobuf2-vmalloc.c
+++ b/drivers/media/common/videobuf2/videobuf2-vmalloc.c
@@ -209,7 +209,7 @@ struct vb2_vmalloc_attachment {
 	enum dma_data_direction dma_dir;
 };
 
-static int vb2_vmalloc_dmabuf_ops_attach(struct dma_buf *dbuf, struct device *dev,
+static int vb2_vmalloc_dmabuf_ops_attach(struct dma_buf *dbuf,
 	struct dma_buf_attachment *dbuf_attach)
 {
 	struct vb2_vmalloc_attachment *attach;
@@ -346,7 +346,6 @@ static const struct dma_buf_ops vb2_vmalloc_dmabuf_ops = {
 	.map_dma_buf = vb2_vmalloc_dmabuf_ops_map,
 	.unmap_dma_buf = vb2_vmalloc_dmabuf_ops_unmap,
 	.map = vb2_vmalloc_dmabuf_ops_kmap,
-	.map_atomic = vb2_vmalloc_dmabuf_ops_kmap,
 	.vmap = vb2_vmalloc_dmabuf_ops_vmap,
 	.mmap = vb2_vmalloc_dmabuf_ops_mmap,
 	.release = vb2_vmalloc_dmabuf_ops_release,
diff --git a/drivers/media/dvb-core/dvb_ca_en50221.c b/drivers/media/dvb-core/dvb_ca_en50221.c
index 1310526b0d49..4d371cea0d5d 100644
--- a/drivers/media/dvb-core/dvb_ca_en50221.c
+++ b/drivers/media/dvb-core/dvb_ca_en50221.c
@@ -1391,7 +1391,7 @@ static int dvb_ca_en50221_io_do_ioctl(struct file *file,
 		struct dvb_ca_slot *sl;
 
 		slot = info->num;
-		if ((slot > ca->slot_count) || (slot < 0)) {
+		if ((slot >= ca->slot_count) || (slot < 0)) {
 			err = -EINVAL;
 			goto out_unlock;
 		}
diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c
index ce25aef39008..c4e7ebfe4d29 100644
--- a/drivers/media/dvb-core/dvb_frontend.c
+++ b/drivers/media/dvb-core/dvb_frontend.c
@@ -894,21 +894,67 @@ static int dvb_frontend_start(struct dvb_frontend *fe)
 }
 
 static void dvb_frontend_get_frequency_limits(struct dvb_frontend *fe,
-					      u32 *freq_min, u32 *freq_max)
+					      u32 *freq_min, u32 *freq_max,
+					      u32 *tolerance)
 {
-	*freq_min = max(fe->ops.info.frequency_min, fe->ops.tuner_ops.info.frequency_min);
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+	u32 tuner_min = fe->ops.tuner_ops.info.frequency_min_hz;
+	u32 tuner_max = fe->ops.tuner_ops.info.frequency_max_hz;
+	u32 frontend_min = fe->ops.info.frequency_min_hz;
+	u32 frontend_max = fe->ops.info.frequency_max_hz;
+
+	*freq_min = max(frontend_min, tuner_min);
 
-	if (fe->ops.info.frequency_max == 0)
-		*freq_max = fe->ops.tuner_ops.info.frequency_max;
-	else if (fe->ops.tuner_ops.info.frequency_max == 0)
-		*freq_max = fe->ops.info.frequency_max;
+	if (frontend_max == 0)
+		*freq_max = tuner_max;
+	else if (tuner_max == 0)
+		*freq_max = frontend_max;
 	else
-		*freq_max = min(fe->ops.info.frequency_max, fe->ops.tuner_ops.info.frequency_max);
+		*freq_max = min(frontend_max, tuner_max);
 
 	if (*freq_min == 0 || *freq_max == 0)
 		dev_warn(fe->dvb->device,
 			 "DVB: adapter %i frontend %u frequency limits undefined - fix the driver\n",
 			 fe->dvb->num, fe->id);
+
+	/* If the standard is for satellite, convert frequencies to kHz */
+	switch (c->delivery_system) {
+	case SYS_DVBS:
+	case SYS_DVBS2:
+	case SYS_TURBO:
+	case SYS_ISDBS:
+		*freq_min /= kHz;
+		*freq_max /= kHz;
+		if (tolerance)
+			*tolerance = fe->ops.info.frequency_tolerance_hz / kHz;
+
+		break;
+	default:
+		if (tolerance)
+			*tolerance = fe->ops.info.frequency_tolerance_hz;
+		break;
+	}
+}
+
+static u32 dvb_frontend_get_stepsize(struct dvb_frontend *fe)
+{
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+	u32 fe_step = fe->ops.info.frequency_stepsize_hz;
+	u32 tuner_step = fe->ops.tuner_ops.info.frequency_step_hz;
+	u32 step = max(fe_step, tuner_step);
+
+	switch (c->delivery_system) {
+	case SYS_DVBS:
+	case SYS_DVBS2:
+	case SYS_TURBO:
+	case SYS_ISDBS:
+		step /= kHz;
+		break;
+	default:
+		break;
+	}
+
+	return step;
 }
 
 static int dvb_frontend_check_parameters(struct dvb_frontend *fe)
@@ -918,7 +964,7 @@ static int dvb_frontend_check_parameters(struct dvb_frontend *fe)
 	u32 freq_max;
 
 	/* range check: frequency */
-	dvb_frontend_get_frequency_limits(fe, &freq_min, &freq_max);
+	dvb_frontend_get_frequency_limits(fe, &freq_min, &freq_max, NULL);
 	if ((freq_min && c->frequency < freq_min) ||
 	    (freq_max && c->frequency > freq_max)) {
 		dev_warn(fe->dvb->device, "DVB: adapter %i frontend %i frequency %u out of range (%u..%u)\n",
@@ -2244,8 +2290,8 @@ static int dtv_set_frontend(struct dvb_frontend *fe)
 		case SYS_ISDBT:
 		case SYS_DTMB:
 			fepriv->min_delay = HZ / 20;
-			fepriv->step_size = fe->ops.info.frequency_stepsize * 2;
-			fepriv->max_drift = (fe->ops.info.frequency_stepsize * 2) + 1;
+			fepriv->step_size = dvb_frontend_get_stepsize(fe) * 2;
+			fepriv->max_drift = (dvb_frontend_get_stepsize(fe) * 2) + 1;
 			break;
 		default:
 			/*
@@ -2374,9 +2420,17 @@ static int dvb_frontend_handle_ioctl(struct file *file,
 
 	case FE_GET_INFO: {
 		struct dvb_frontend_info *info = parg;
-
-		memcpy(info, &fe->ops.info, sizeof(struct dvb_frontend_info));
-		dvb_frontend_get_frequency_limits(fe, &info->frequency_min, &info->frequency_max);
+		memset(info, 0, sizeof(*info));
+
+		strcpy(info->name, fe->ops.info.name);
+		info->symbol_rate_min = fe->ops.info.symbol_rate_min;
+		info->symbol_rate_max = fe->ops.info.symbol_rate_max;
+		info->symbol_rate_tolerance = fe->ops.info.symbol_rate_tolerance;
+		info->caps = fe->ops.info.caps;
+		info->frequency_stepsize = dvb_frontend_get_stepsize(fe);
+		dvb_frontend_get_frequency_limits(fe, &info->frequency_min,
+						  &info->frequency_max,
+						  &info->frequency_tolerance);
 
 		/*
 		 * Associate the 4 delivery systems supported by DVBv3
@@ -2406,10 +2460,10 @@ static int dvb_frontend_handle_ioctl(struct file *file,
 			dev_err(fe->dvb->device,
 				"%s: doesn't know how to handle a DVBv3 call to delivery system %i\n",
 				__func__, c->delivery_system);
-			fe->ops.info.type = FE_OFDM;
+			info->type = FE_OFDM;
 		}
 		dev_dbg(fe->dvb->device, "%s: current delivery system on cache: %d, V3 type: %d\n",
-			__func__, c->delivery_system, fe->ops.info.type);
+			__func__, c->delivery_system, info->type);
 
 		/* Set CAN_INVERSION_AUTO bit on in other than oneshot mode */
 		if (!(fepriv->tune_mode_flags & FE_TUNE_MODE_ONESHOT))
diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c
index 64d6793674b9..3c8778570331 100644
--- a/drivers/media/dvb-core/dvbdev.c
+++ b/drivers/media/dvb-core/dvbdev.c
@@ -440,8 +440,10 @@ static int dvb_register_media_device(struct dvb_device *dvbdev,
 	if (!dvbdev->entity)
 		return 0;
 
-	link = media_create_intf_link(dvbdev->entity, &dvbdev->intf_devnode->intf,
-				      MEDIA_LNK_FL_ENABLED);
+	link = media_create_intf_link(dvbdev->entity,
+				      &dvbdev->intf_devnode->intf,
+				      MEDIA_LNK_FL_ENABLED |
+				      MEDIA_LNK_FL_IMMUTABLE);
 	if (!link)
 		return -ENOMEM;
 #endif
@@ -599,7 +601,8 @@ static int dvb_create_io_intf_links(struct dvb_adapter *adap,
 			if (strncmp(entity->name, name, strlen(name)))
 				continue;
 			link = media_create_intf_link(entity, intf,
-						      MEDIA_LNK_FL_ENABLED);
+						      MEDIA_LNK_FL_ENABLED |
+						      MEDIA_LNK_FL_IMMUTABLE);
 			if (!link)
 				return -ENOMEM;
 		}
@@ -754,14 +757,16 @@ int dvb_create_media_graph(struct dvb_adapter *adap,
 	media_device_for_each_intf(intf, mdev) {
 		if (intf->type == MEDIA_INTF_T_DVB_CA && ca) {
 			link = media_create_intf_link(ca, intf,
-						      MEDIA_LNK_FL_ENABLED);
+						      MEDIA_LNK_FL_ENABLED |
+						      MEDIA_LNK_FL_IMMUTABLE);
 			if (!link)
 				return -ENOMEM;
 		}
 
 		if (intf->type == MEDIA_INTF_T_DVB_FE && tuner) {
 			link = media_create_intf_link(tuner, intf,
-						      MEDIA_LNK_FL_ENABLED);
+						      MEDIA_LNK_FL_ENABLED |
+						      MEDIA_LNK_FL_IMMUTABLE);
 			if (!link)
 				return -ENOMEM;
 		}
@@ -773,7 +778,8 @@ int dvb_create_media_graph(struct dvb_adapter *adap,
 		 */
 		if (intf->type == MEDIA_INTF_T_DVB_DVR && demux) {
 			link = media_create_intf_link(demux, intf,
-						      MEDIA_LNK_FL_ENABLED);
+						      MEDIA_LNK_FL_ENABLED |
+						      MEDIA_LNK_FL_IMMUTABLE);
 			if (!link)
 				return -ENOMEM;
 		}
diff --git a/drivers/media/dvb-frontends/Kconfig b/drivers/media/dvb-frontends/Kconfig
index 9ecaa9d0744a..048285134cdf 100644
--- a/drivers/media/dvb-frontends/Kconfig
+++ b/drivers/media/dvb-frontends/Kconfig
@@ -739,6 +739,16 @@ config DVB_TC90522
 	  Toshiba TC90522 2xISDB-S 8PSK + 2xISDB-T OFDM demodulator.
 	  Say Y when you want to support this frontend.
 
+config DVB_MN88443X
+	tristate "Socionext MN88443x"
+	depends on DVB_CORE && I2C
+	select REGMAP_I2C
+	default m if !MEDIA_SUBDRV_AUTOSELECT
+	help
+	  A driver for Socionext/Panasonic MN884433 and MN884434
+	  ISDB-S + ISDB-T demodulator.
+	  Say Y when you want to support this frontend.
+
 comment "Digital terrestrial only tuners/PLL"
 	depends on DVB_CORE
 
diff --git a/drivers/media/dvb-frontends/Makefile b/drivers/media/dvb-frontends/Makefile
index 67a783fd5ed0..779dfd027b24 100644
--- a/drivers/media/dvb-frontends/Makefile
+++ b/drivers/media/dvb-frontends/Makefile
@@ -125,6 +125,7 @@ obj-$(CONFIG_DVB_AF9033) += af9033.o
 obj-$(CONFIG_DVB_AS102_FE) += as102_fe.o
 obj-$(CONFIG_DVB_GP8PSK_FE) += gp8psk-fe.o
 obj-$(CONFIG_DVB_TC90522) += tc90522.o
+obj-$(CONFIG_DVB_MN88443X) += mn88443x.o
 obj-$(CONFIG_DVB_HORUS3A) += horus3a.o
 obj-$(CONFIG_DVB_ASCOT2E) += ascot2e.o
 obj-$(CONFIG_DVB_HELENE) += helene.o
diff --git a/drivers/media/dvb-frontends/af9013.c b/drivers/media/dvb-frontends/af9013.c
index 482bce49819a..f3acbb57d48c 100644
--- a/drivers/media/dvb-frontends/af9013.c
+++ b/drivers/media/dvb-frontends/af9013.c
@@ -1136,10 +1136,9 @@ static const struct dvb_frontend_ops af9013_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "Afatech AF9013",
-		.frequency_min = 174000000,
-		.frequency_max = 862000000,
-		.frequency_stepsize = 250000,
-		.frequency_tolerance = 0,
+		.frequency_min_hz = 174 * MHz,
+		.frequency_max_hz = 862 * MHz,
+		.frequency_stepsize_hz = 250 * kHz,
 		.caps =	FE_CAN_FEC_1_2 |
 			FE_CAN_FEC_2_3 |
 			FE_CAN_FEC_3_4 |
diff --git a/drivers/media/dvb-frontends/af9033.c b/drivers/media/dvb-frontends/af9033.c
index aaed7cfe5f66..0cd57013ea25 100644
--- a/drivers/media/dvb-frontends/af9033.c
+++ b/drivers/media/dvb-frontends/af9033.c
@@ -1020,10 +1020,9 @@ static const struct dvb_frontend_ops af9033_ops = {
 	.delsys = {SYS_DVBT},
 	.info = {
 		.name = "Afatech AF9033 (DVB-T)",
-		.frequency_min = 174000000,
-		.frequency_max = 862000000,
-		.frequency_stepsize = 250000,
-		.frequency_tolerance = 0,
+		.frequency_min_hz = 174 * MHz,
+		.frequency_max_hz = 862 * MHz,
+		.frequency_stepsize_hz = 250 * kHz,
 		.caps =	FE_CAN_FEC_1_2 |
 			FE_CAN_FEC_2_3 |
 			FE_CAN_FEC_3_4 |
diff --git a/drivers/media/dvb-frontends/as102_fe.c b/drivers/media/dvb-frontends/as102_fe.c
index 9b2f2da1d989..f59a102b0a64 100644
--- a/drivers/media/dvb-frontends/as102_fe.c
+++ b/drivers/media/dvb-frontends/as102_fe.c
@@ -419,9 +419,9 @@ static const struct dvb_frontend_ops as102_fe_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "Abilis AS102 DVB-T",
-		.frequency_min		= 174000000,
-		.frequency_max		= 862000000,
-		.frequency_stepsize	= 166667,
+		.frequency_min_hz	= 174 * MHz,
+		.frequency_max_hz	= 862 * MHz,
+		.frequency_stepsize_hz	= 166667,
 		.caps = FE_CAN_INVERSION_AUTO
 			| FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4
 			| FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO
diff --git a/drivers/media/dvb-frontends/ascot2e.c b/drivers/media/dvb-frontends/ascot2e.c
index 9746c6dd7fb8..52ce0e6e2a15 100644
--- a/drivers/media/dvb-frontends/ascot2e.c
+++ b/drivers/media/dvb-frontends/ascot2e.c
@@ -468,9 +468,9 @@ static int ascot2e_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 static const struct dvb_tuner_ops ascot2e_tuner_ops = {
 	.info = {
 		.name = "Sony ASCOT2E",
-		.frequency_min = 1000000,
-		.frequency_max = 1200000000,
-		.frequency_step = 25000,
+		.frequency_min_hz  =    1 * MHz,
+		.frequency_max_hz  = 1200 * MHz,
+		.frequency_step_hz =   25 * kHz,
 	},
 	.init = ascot2e_init,
 	.release = ascot2e_release,
diff --git a/drivers/media/dvb-frontends/atbm8830.c b/drivers/media/dvb-frontends/atbm8830.c
index 7b0f3239dbba..cbcc65dc9d54 100644
--- a/drivers/media/dvb-frontends/atbm8830.c
+++ b/drivers/media/dvb-frontends/atbm8830.c
@@ -428,9 +428,9 @@ static const struct dvb_frontend_ops atbm8830_ops = {
 	.delsys = { SYS_DTMB },
 	.info = {
 		.name = "AltoBeam ATBM8830/8831 DMB-TH",
-		.frequency_min = 474000000,
-		.frequency_max = 858000000,
-		.frequency_stepsize = 10000,
+		.frequency_min_hz = 474 * MHz,
+		.frequency_max_hz = 858 * MHz,
+		.frequency_stepsize_hz = 10 * kHz,
 		.caps =
 			FE_CAN_FEC_AUTO |
 			FE_CAN_QAM_AUTO |
diff --git a/drivers/media/dvb-frontends/au8522_dig.c b/drivers/media/dvb-frontends/au8522_dig.c
index 8f659bd1c79e..076f737aa8c0 100644
--- a/drivers/media/dvb-frontends/au8522_dig.c
+++ b/drivers/media/dvb-frontends/au8522_dig.c
@@ -897,9 +897,9 @@ static const struct dvb_frontend_ops au8522_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name			= "Auvitek AU8522 QAM/8VSB Frontend",
-		.frequency_min		= 54000000,
-		.frequency_max		= 858000000,
-		.frequency_stepsize	= 62500,
+		.frequency_min_hz	=  54 * MHz,
+		.frequency_max_hz	= 858 * MHz,
+		.frequency_stepsize_hz	= 62500,
 		.caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
 	},
 
diff --git a/drivers/media/dvb-frontends/bcm3510.c b/drivers/media/dvb-frontends/bcm3510.c
index 05df133dc5be..e92542b92d34 100644
--- a/drivers/media/dvb-frontends/bcm3510.c
+++ b/drivers/media/dvb-frontends/bcm3510.c
@@ -840,10 +840,8 @@ static const struct dvb_frontend_ops bcm3510_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name = "Broadcom BCM3510 VSB/QAM frontend",
-		.frequency_min =  54000000,
-		.frequency_max = 803000000,
-		/* stepsize is just a guess */
-		.frequency_stepsize = 0,
+		.frequency_min_hz =  54 * MHz,
+		.frequency_max_hz = 803 * MHz,
 		.caps =
 			FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/cx22700.c b/drivers/media/dvb-frontends/cx22700.c
index 9ffd2c7ac74a..961380162cdd 100644
--- a/drivers/media/dvb-frontends/cx22700.c
+++ b/drivers/media/dvb-frontends/cx22700.c
@@ -412,9 +412,9 @@ static const struct dvb_frontend_ops cx22700_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "Conexant CX22700 DVB-T",
-		.frequency_min		= 470000000,
-		.frequency_max		= 860000000,
-		.frequency_stepsize	= 166667,
+		.frequency_min_hz	= 470 * MHz,
+		.frequency_max_hz	= 860 * MHz,
+		.frequency_stepsize_hz	= 166667,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		      FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 		      FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_64 |
diff --git a/drivers/media/dvb-frontends/cx22702.c b/drivers/media/dvb-frontends/cx22702.c
index e8b1e6b7e7e5..ab9b2924bcca 100644
--- a/drivers/media/dvb-frontends/cx22702.c
+++ b/drivers/media/dvb-frontends/cx22702.c
@@ -622,9 +622,9 @@ static const struct dvb_frontend_ops cx22702_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "Conexant CX22702 DVB-T",
-		.frequency_min		= 177000000,
-		.frequency_max		= 858000000,
-		.frequency_stepsize	= 166666,
+		.frequency_min_hz	= 177 * MHz,
+		.frequency_max_hz	= 858 * MHz,
+		.frequency_stepsize_hz	= 166666,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 		FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_64 | FE_CAN_QAM_AUTO |
diff --git a/drivers/media/dvb-frontends/cx24110.c b/drivers/media/dvb-frontends/cx24110.c
index 2f3a1c237489..9441bdc73097 100644
--- a/drivers/media/dvb-frontends/cx24110.c
+++ b/drivers/media/dvb-frontends/cx24110.c
@@ -629,10 +629,10 @@ static const struct dvb_frontend_ops cx24110_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name = "Conexant CX24110 DVB-S",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_stepsize = 1011,  /* kHz for QPSK frontends */
-		.frequency_tolerance = 29500,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
+		.frequency_stepsize_hz = 1011 * kHz,
+		.frequency_tolerance_hz = 29500 * kHz,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/cx24113.c b/drivers/media/dvb-frontends/cx24113.c
index 037db3e9d2dd..91a5033b6bd7 100644
--- a/drivers/media/dvb-frontends/cx24113.c
+++ b/drivers/media/dvb-frontends/cx24113.c
@@ -533,10 +533,10 @@ static void cx24113_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops cx24113_tuner_ops = {
 	.info = {
-		.name           = "Conexant CX24113",
-		.frequency_min  = 950000,
-		.frequency_max  = 2150000,
-		.frequency_step = 125,
+		.name              = "Conexant CX24113",
+		.frequency_min_hz  =  950 * MHz,
+		.frequency_max_hz  = 2150 * MHz,
+		.frequency_step_hz =  125 * kHz,
 	},
 
 	.release       = cx24113_release,
diff --git a/drivers/media/dvb-frontends/cx24116.c b/drivers/media/dvb-frontends/cx24116.c
index 2dbc7349d870..220f26663647 100644
--- a/drivers/media/dvb-frontends/cx24116.c
+++ b/drivers/media/dvb-frontends/cx24116.c
@@ -1465,10 +1465,10 @@ static const struct dvb_frontend_ops cx24116_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2 },
 	.info = {
 		.name = "Conexant CX24116/CX24118",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_stepsize = 1011, /* kHz for QPSK frontends */
-		.frequency_tolerance = 5000,
+		.frequency_min_hz = 950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
+		.frequency_stepsize_hz = 1011 * kHz,
+		.frequency_tolerance_hz = 5 * MHz,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/cx24117.c b/drivers/media/dvb-frontends/cx24117.c
index ba55d75d916c..667bc8be848d 100644
--- a/drivers/media/dvb-frontends/cx24117.c
+++ b/drivers/media/dvb-frontends/cx24117.c
@@ -1622,10 +1622,10 @@ static const struct dvb_frontend_ops cx24117_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2 },
 	.info = {
 		.name = "Conexant CX24117/CX24132",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_stepsize = 1011, /* kHz for QPSK frontends */
-		.frequency_tolerance = 5000,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
+		.frequency_stepsize_hz = 1011 * kHz,
+		.frequency_tolerance_hz = 5 * MHz,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/cx24120.c b/drivers/media/dvb-frontends/cx24120.c
index ccbabdae6a69..dd3ec316e7c2 100644
--- a/drivers/media/dvb-frontends/cx24120.c
+++ b/drivers/media/dvb-frontends/cx24120.c
@@ -1555,10 +1555,10 @@ static const struct dvb_frontend_ops cx24120_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2 },
 	.info = {
 		.name = "Conexant CX24120/CX24118",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_stepsize = 1011, /* kHz for QPSK frontends */
-		.frequency_tolerance = 5000,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
+		.frequency_stepsize_hz = 1011 * kHz,
+		.frequency_tolerance_hz = 5 * MHz,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.caps =	FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/cx24123.c b/drivers/media/dvb-frontends/cx24123.c
index bf33e7390aaf..e49215020a93 100644
--- a/drivers/media/dvb-frontends/cx24123.c
+++ b/drivers/media/dvb-frontends/cx24123.c
@@ -1111,10 +1111,10 @@ static const struct dvb_frontend_ops cx24123_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name = "Conexant CX24123/CX24109",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_stepsize = 1011, /* kHz for QPSK frontends */
-		.frequency_tolerance = 5000,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
+		.frequency_stepsize_hz = 1011 * kHz,
+		.frequency_tolerance_hz = 5 * MHz,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/cxd2820r_t.c b/drivers/media/dvb-frontends/cxd2820r_t.c
index c2e7caf9b010..eb1d7478fa8d 100644
--- a/drivers/media/dvb-frontends/cxd2820r_t.c
+++ b/drivers/media/dvb-frontends/cxd2820r_t.c
@@ -431,8 +431,8 @@ int cxd2820r_get_tune_settings_t(struct dvb_frontend *fe,
 	struct dvb_frontend_tune_settings *s)
 {
 	s->min_delay_ms = 500;
-	s->step_size = fe->ops.info.frequency_stepsize * 2;
-	s->max_drift = (fe->ops.info.frequency_stepsize * 2) + 1;
+	s->step_size = fe->ops.info.frequency_stepsize_hz * 2;
+	s->max_drift = (fe->ops.info.frequency_stepsize_hz * 2) + 1;
 
 	return 0;
 }
diff --git a/drivers/media/dvb-frontends/cxd2820r_t2.c b/drivers/media/dvb-frontends/cxd2820r_t2.c
index e641fde75379..f330ec1710b4 100644
--- a/drivers/media/dvb-frontends/cxd2820r_t2.c
+++ b/drivers/media/dvb-frontends/cxd2820r_t2.c
@@ -426,8 +426,8 @@ int cxd2820r_get_tune_settings_t2(struct dvb_frontend *fe,
 	struct dvb_frontend_tune_settings *s)
 {
 	s->min_delay_ms = 1500;
-	s->step_size = fe->ops.info.frequency_stepsize * 2;
-	s->max_drift = (fe->ops.info.frequency_stepsize * 2) + 1;
+	s->step_size = fe->ops.info.frequency_stepsize_hz * 2;
+	s->max_drift = (fe->ops.info.frequency_stepsize_hz * 2) + 1;
 
 	return 0;
 }
diff --git a/drivers/media/dvb-frontends/cxd2841er.c b/drivers/media/dvb-frontends/cxd2841er.c
index 85905d3503ff..c98093ed3dd7 100644
--- a/drivers/media/dvb-frontends/cxd2841er.c
+++ b/drivers/media/dvb-frontends/cxd2841er.c
@@ -3942,9 +3942,8 @@ static const struct dvb_frontend_ops cxd2841er_dvbs_s2_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2 },
 	.info = {
 		.name		= "Sony CXD2841ER DVB-S/S2 demodulator",
-		.frequency_min	= 500000,
-		.frequency_max	= 2500000,
-		.frequency_stepsize	= 0,
+		.frequency_min_hz	=  500 * MHz,
+		.frequency_max_hz	= 2500 * MHz,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.symbol_rate_tolerance = 500,
@@ -3988,8 +3987,8 @@ static struct dvb_frontend_ops cxd2841er_t_c_ops = {
 			FE_CAN_HIERARCHY_AUTO |
 			FE_CAN_MUTE_TS |
 			FE_CAN_2G_MODULATION,
-		.frequency_min = 42000000,
-		.frequency_max = 1002000000,
+		.frequency_min_hz =   42 * MHz,
+		.frequency_max_hz = 1002 * MHz,
 		.symbol_rate_min = 870000,
 		.symbol_rate_max = 11700000
 	},
diff --git a/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c b/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c
index bd9101e246d5..f87e27481ea7 100644
--- a/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c
+++ b/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c
@@ -1833,9 +1833,9 @@ static enum dvbfe_algo cxd2880_get_frontend_algo(struct dvb_frontend *fe)
 static struct dvb_frontend_ops cxd2880_dvbt_t2_ops = {
 	.info = {
 		.name = "Sony CXD2880",
-		.frequency_min =  174000000,
-		.frequency_max = 862000000,
-		.frequency_stepsize = 1000,
+		.frequency_min_hz = 174 * MHz,
+		.frequency_max_hz = 862 * MHz,
+		.frequency_stepsize_hz = 1 * kHz,
 		.caps = FE_CAN_INVERSION_AUTO |
 				FE_CAN_FEC_1_2 |
 				FE_CAN_FEC_2_3 |
diff --git a/drivers/media/dvb-frontends/dib0070.c b/drivers/media/dvb-frontends/dib0070.c
index 932d235118e2..37ebd5af8fd4 100644
--- a/drivers/media/dvb-frontends/dib0070.c
+++ b/drivers/media/dvb-frontends/dib0070.c
@@ -726,10 +726,10 @@ static void dib0070_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops dib0070_ops = {
 	.info = {
-		.name           = "DiBcom DiB0070",
-		.frequency_min  =  45000000,
-		.frequency_max  = 860000000,
-		.frequency_step =      1000,
+		.name              = "DiBcom DiB0070",
+		.frequency_min_hz  =  45 * MHz,
+		.frequency_max_hz  = 860 * MHz,
+		.frequency_step_hz =   1 * kHz,
 	},
 	.release       = dib0070_release,
 
diff --git a/drivers/media/dvb-frontends/dib0090.c b/drivers/media/dvb-frontends/dib0090.c
index ee7af34979ed..44a074261e69 100644
--- a/drivers/media/dvb-frontends/dib0090.c
+++ b/drivers/media/dvb-frontends/dib0090.c
@@ -2578,9 +2578,9 @@ static int dib0090_set_params(struct dvb_frontend *fe)
 static const struct dvb_tuner_ops dib0090_ops = {
 	.info = {
 		 .name = "DiBcom DiB0090",
-		 .frequency_min = 45000000,
-		 .frequency_max = 860000000,
-		 .frequency_step = 1000,
+		 .frequency_min_hz  =  45 * MHz,
+		 .frequency_max_hz  = 860 * MHz,
+		 .frequency_step_hz =   1 * kHz,
 		 },
 	.release = dib0090_release,
 
@@ -2593,9 +2593,9 @@ static const struct dvb_tuner_ops dib0090_ops = {
 static const struct dvb_tuner_ops dib0090_fw_ops = {
 	.info = {
 		 .name = "DiBcom DiB0090",
-		 .frequency_min = 45000000,
-		 .frequency_max = 860000000,
-		 .frequency_step = 1000,
+		 .frequency_min_hz  =  45 * MHz,
+		 .frequency_max_hz  = 860 * MHz,
+		 .frequency_step_hz =   1 * kHz,
 		 },
 	.release = dib0090_release,
 
diff --git a/drivers/media/dvb-frontends/dib3000mb.c b/drivers/media/dvb-frontends/dib3000mb.c
index 5861f346db49..bbbd53280477 100644
--- a/drivers/media/dvb-frontends/dib3000mb.c
+++ b/drivers/media/dvb-frontends/dib3000mb.c
@@ -786,9 +786,9 @@ static const struct dvb_frontend_ops dib3000mb_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "DiBcom 3000M-B DVB-T",
-		.frequency_min		= 44250000,
-		.frequency_max		= 867250000,
-		.frequency_stepsize	= 62500,
+		.frequency_min_hz	=  44250 * kHz,
+		.frequency_max_hz	= 867250 * kHz,
+		.frequency_stepsize_hz	= 62500,
 		.caps = FE_CAN_INVERSION_AUTO |
 				FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 				FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/dib3000mc.c b/drivers/media/dvb-frontends/dib3000mc.c
index 7e5d474806a5..c9e1db251723 100644
--- a/drivers/media/dvb-frontends/dib3000mc.c
+++ b/drivers/media/dvb-frontends/dib3000mc.c
@@ -944,9 +944,9 @@ static const struct dvb_frontend_ops dib3000mc_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "DiBcom 3000MC/P",
-		.frequency_min      = 44250000,
-		.frequency_max      = 867250000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz      =  44250 * kHz,
+		.frequency_max_hz      = 867250 * kHz,
+		.frequency_stepsize_hz = 62500,
 		.caps = FE_CAN_INVERSION_AUTO |
 			FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/dib7000m.c b/drivers/media/dvb-frontends/dib7000m.c
index 6a1d357d0c7c..b79358d09de6 100644
--- a/drivers/media/dvb-frontends/dib7000m.c
+++ b/drivers/media/dvb-frontends/dib7000m.c
@@ -1443,9 +1443,9 @@ static const struct dvb_frontend_ops dib7000m_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "DiBcom 7000MA/MB/PA/PB/MC",
-		.frequency_min      = 44250000,
-		.frequency_max      = 867250000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz      =  44250 * kHz,
+		.frequency_max_hz      = 867250 * kHz,
+		.frequency_stepsize_hz = 62500,
 		.caps = FE_CAN_INVERSION_AUTO |
 			FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/dib7000p.c b/drivers/media/dvb-frontends/dib7000p.c
index 5a8dbc0b25fb..58387860b62d 100644
--- a/drivers/media/dvb-frontends/dib7000p.c
+++ b/drivers/media/dvb-frontends/dib7000p.c
@@ -2824,9 +2824,9 @@ static const struct dvb_frontend_ops dib7000p_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		 .name = "DiBcom 7000PC",
-		 .frequency_min = 44250000,
-		 .frequency_max = 867250000,
-		 .frequency_stepsize = 62500,
+		 .frequency_min_hz =  44250 * kHz,
+		 .frequency_max_hz = 867250 * kHz,
+		 .frequency_stepsize_hz = 62500,
 		 .caps = FE_CAN_INVERSION_AUTO |
 		 FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		 FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/dib8000.c b/drivers/media/dvb-frontends/dib8000.c
index 22eec8f65485..3c3f8cb14845 100644
--- a/drivers/media/dvb-frontends/dib8000.c
+++ b/drivers/media/dvb-frontends/dib8000.c
@@ -4390,9 +4390,9 @@ static const struct dvb_frontend_ops dib8000_ops = {
 	.delsys = { SYS_ISDBT },
 	.info = {
 		 .name = "DiBcom 8000 ISDB-T",
-		 .frequency_min = 44250000,
-		 .frequency_max = 867250000,
-		 .frequency_stepsize = 62500,
+		 .frequency_min_hz =  44250 * kHz,
+		 .frequency_max_hz = 867250 * kHz,
+		 .frequency_stepsize_hz = 62500,
 		 .caps = FE_CAN_INVERSION_AUTO |
 		 FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		 FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/dib9000.c b/drivers/media/dvb-frontends/dib9000.c
index b8edb55696bb..0183fb1346ef 100644
--- a/drivers/media/dvb-frontends/dib9000.c
+++ b/drivers/media/dvb-frontends/dib9000.c
@@ -2553,9 +2553,9 @@ static const struct dvb_frontend_ops dib9000_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		 .name = "DiBcom 9000",
-		 .frequency_min = 44250000,
-		 .frequency_max = 867250000,
-		 .frequency_stepsize = 62500,
+		 .frequency_min_hz =  44250 * kHz,
+		 .frequency_max_hz = 867250 * kHz,
+		 .frequency_stepsize_hz = 62500,
 		 .caps = FE_CAN_INVERSION_AUTO |
 		 FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		 FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/drx39xyj/drxj.c b/drivers/media/dvb-frontends/drx39xyj/drxj.c
index 5706898e84cc..9628d4067fe1 100644
--- a/drivers/media/dvb-frontends/drx39xyj/drxj.c
+++ b/drivers/media/dvb-frontends/drx39xyj/drxj.c
@@ -2841,8 +2841,7 @@ ctrl_set_cfg_mpeg_output(struct drx_demod_instance *demod, struct drx_cfg_mpeg_o
 			/* coef = 188/204                          */
 			max_bit_rate =
 			    (ext_attr->curr_symbol_rate / 8) * nr_bits * 188;
-			/* pass through as b/c Annex A/c need following settings */
-			/* fall-through */
+			/* fall-through - as b/c Annex A/C need following settings */
 		case DRX_STANDARD_ITU_B:
 			rc = drxj_dap_write_reg16(dev_addr, FEC_OC_FCT_USAGE__A, FEC_OC_FCT_USAGE__PRE, 0);
 			if (rc != 0) {
@@ -11811,8 +11810,8 @@ static int drx_ctrl_u_code(struct drx_demod_instance *demod,
 		block_hdr.CRC = be16_to_cpu(*(__be16 *)(mc_data));
 		mc_data += sizeof(u16);
 
-		pr_debug("%u: addr %u, size %u, flags 0x%04x, CRC 0x%04x\n",
-			(unsigned)(mc_data - mc_data_init), block_hdr.addr,
+		pr_debug("%zd: addr %u, size %u, flags 0x%04x, CRC 0x%04x\n",
+			(mc_data - mc_data_init), block_hdr.addr,
 			 block_hdr.size, block_hdr.flags, block_hdr.CRC);
 
 		/* Check block header on:
@@ -11842,8 +11841,8 @@ static int drx_ctrl_u_code(struct drx_demod_instance *demod,
 							mc_block_nr_bytes,
 							mc_data, 0x0000)) {
 				rc = -EIO;
-				pr_err("error writing firmware at pos %u\n",
-				       (unsigned)(mc_data - mc_data_init));
+				pr_err("error writing firmware at pos %zd\n",
+				       mc_data - mc_data_init);
 				goto release;
 			}
 			break;
@@ -11866,8 +11865,8 @@ static int drx_ctrl_u_code(struct drx_demod_instance *demod,
 						    (u16)bytes_to_comp,
 						    (u8 *)mc_data_buffer,
 						    0x0000)) {
-					pr_err("error reading firmware at pos %u\n",
-					       (unsigned)(mc_data - mc_data_init));
+					pr_err("error reading firmware at pos %zd\n",
+					       mc_data - mc_data_init);
 					return -EIO;
 				}
 
@@ -11875,8 +11874,8 @@ static int drx_ctrl_u_code(struct drx_demod_instance *demod,
 						bytes_to_comp);
 
 				if (result) {
-					pr_err("error verifying firmware at pos %u\n",
-					       (unsigned)(mc_data - mc_data_init));
+					pr_err("error verifying firmware at pos %zd\n",
+					       mc_data - mc_data_init);
 					return -EIO;
 				}
 
@@ -12374,9 +12373,9 @@ static const struct dvb_frontend_ops drx39xxj_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		 .name = "Micronas DRX39xxj family Frontend",
-		 .frequency_stepsize = 62500,
-		 .frequency_min = 51000000,
-		 .frequency_max = 858000000,
+		 .frequency_min_hz =  51 * MHz,
+		 .frequency_max_hz = 858 * MHz,
+		 .frequency_stepsize_hz = 62500,
 		 .caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
 	},
 
diff --git a/drivers/media/dvb-frontends/drxd_hard.c b/drivers/media/dvb-frontends/drxd_hard.c
index 3b7d31a22d82..684d428efb0d 100644
--- a/drivers/media/dvb-frontends/drxd_hard.c
+++ b/drivers/media/dvb-frontends/drxd_hard.c
@@ -1970,8 +1970,7 @@ static int DRX_Start(struct drxd_state *state, s32 off)
 		switch (p->transmission_mode) {
 		default:	/* Not set, detect it automatically */
 			operationMode |= SC_RA_RAM_OP_AUTO_MODE__M;
-			/* try first guess DRX_FFTMODE_8K */
-			/* fall through */
+			/* fall through - try first guess DRX_FFTMODE_8K */
 		case TRANSMISSION_MODE_8K:
 			transmissionParams |= SC_RA_RAM_OP_PARAM_MODE_8K;
 			if (state->type_A) {
@@ -2144,8 +2143,7 @@ static int DRX_Start(struct drxd_state *state, s32 off)
 		switch (p->modulation) {
 		default:
 			operationMode |= SC_RA_RAM_OP_AUTO_CONST__M;
-			/* try first guess DRX_CONSTELLATION_QAM64 */
-			/* fall through */
+			/* fall through - try first guess DRX_CONSTELLATION_QAM64 */
 		case QAM_64:
 			transmissionParams |= SC_RA_RAM_OP_PARAM_CONST_QAM64;
 			if (state->type_A) {
@@ -2912,10 +2910,9 @@ static const struct dvb_frontend_ops drxd_ops = {
 	.delsys = { SYS_DVBT},
 	.info = {
 		 .name = "Micronas DRXD DVB-T",
-		 .frequency_min = 47125000,
-		 .frequency_max = 855250000,
-		 .frequency_stepsize = 166667,
-		 .frequency_tolerance = 0,
+		 .frequency_min_hz =  47125 * kHz,
+		 .frequency_max_hz = 855250 * kHz,
+		 .frequency_stepsize_hz = 166667,
 		 .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 |
 		 FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 |
 		 FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/drxk_hard.c b/drivers/media/dvb-frontends/drxk_hard.c
index 5a26ad93be10..f1886945a7bc 100644
--- a/drivers/media/dvb-frontends/drxk_hard.c
+++ b/drivers/media/dvb-frontends/drxk_hard.c
@@ -3270,13 +3270,11 @@ static int dvbt_sc_command(struct drxk_state *state,
 	case OFDM_SC_RA_RAM_CMD_SET_PREF_PARAM:
 	case OFDM_SC_RA_RAM_CMD_PROGRAM_PARAM:
 		status |= write16(state, OFDM_SC_RA_RAM_PARAM1__A, param1);
-		/* All commands using 1 parameters */
-		/* fall through */
+		/* fall through - All commands using 1 parameters */
 	case OFDM_SC_RA_RAM_CMD_SET_ECHO_TIMING:
 	case OFDM_SC_RA_RAM_CMD_USER_IO:
 		status |= write16(state, OFDM_SC_RA_RAM_PARAM0__A, param0);
-		/* All commands using 0 parameters */
-		/* fall through */
+		/* fall through - All commands using 0 parameters */
 	case OFDM_SC_RA_RAM_CMD_GET_OP_PARAM:
 	case OFDM_SC_RA_RAM_CMD_NULL:
 		/* Write command */
@@ -3784,8 +3782,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz,
 	case TRANSMISSION_MODE_AUTO:
 	default:
 		operation_mode |= OFDM_SC_RA_RAM_OP_AUTO_MODE__M;
-		/* try first guess DRX_FFTMODE_8K */
-		/* fall through */
+		/* fall through - try first guess DRX_FFTMODE_8K */
 	case TRANSMISSION_MODE_8K:
 		transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_MODE_8K;
 		break;
@@ -3799,8 +3796,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz,
 	default:
 	case GUARD_INTERVAL_AUTO:
 		operation_mode |= OFDM_SC_RA_RAM_OP_AUTO_GUARD__M;
-		/* try first guess DRX_GUARD_1DIV4 */
-		/* fall through */
+		/* fall through - try first guess DRX_GUARD_1DIV4 */
 	case GUARD_INTERVAL_1_4:
 		transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_GUARD_4;
 		break;
@@ -3841,8 +3837,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz,
 	case QAM_AUTO:
 	default:
 		operation_mode |= OFDM_SC_RA_RAM_OP_AUTO_CONST__M;
-		/* try first guess DRX_CONSTELLATION_QAM64 */
-		/* fall through */
+		/* fall through - try first guess DRX_CONSTELLATION_QAM64 */
 	case QAM_64:
 		transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_CONST_QAM64;
 		break;
@@ -3885,8 +3880,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz,
 	case FEC_AUTO:
 	default:
 		operation_mode |= OFDM_SC_RA_RAM_OP_AUTO_RATE__M;
-		/* try first guess DRX_CODERATE_2DIV3 */
-		/* fall through */
+		/* fall through - try first guess DRX_CODERATE_2DIV3 */
 	case FEC_2_3:
 		transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_RATE_2_3;
 		break;
@@ -6744,13 +6738,13 @@ static const struct dvb_frontend_ops drxk_ops = {
 	/* .delsys will be filled dynamically */
 	.info = {
 		.name = "DRXK",
-		.frequency_min = 47000000,
-		.frequency_max = 865000000,
+		.frequency_min_hz =  47 * MHz,
+		.frequency_max_hz = 865 * MHz,
 		 /* For DVB-C */
-		.symbol_rate_min = 870000,
+		.symbol_rate_min =   870000,
 		.symbol_rate_max = 11700000,
 		/* For DVB-T */
-		.frequency_stepsize = 166667,
+		.frequency_stepsize_hz = 166667,
 
 		.caps = FE_CAN_QAM_16 | FE_CAN_QAM_32 | FE_CAN_QAM_64 |
 			FE_CAN_QAM_128 | FE_CAN_QAM_256 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/ds3000.c b/drivers/media/dvb-frontends/ds3000.c
index 2ff90e5eabce..46a55146cb07 100644
--- a/drivers/media/dvb-frontends/ds3000.c
+++ b/drivers/media/dvb-frontends/ds3000.c
@@ -1100,10 +1100,10 @@ static const struct dvb_frontend_ops ds3000_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2 },
 	.info = {
 		.name = "Montage Technology DS3000",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_stepsize = 1011, /* kHz for QPSK frontends */
-		.frequency_tolerance = 5000,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
+		.frequency_stepsize_hz = 1011 * kHz,
+		.frequency_tolerance_hz = 5 * MHz,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/dvb-pll.c b/drivers/media/dvb-frontends/dvb-pll.c
index e3894ff403d7..6d4b2eec67b4 100644
--- a/drivers/media/dvb-frontends/dvb-pll.c
+++ b/drivers/media/dvb-frontends/dvb-pll.c
@@ -799,6 +799,7 @@ struct dvb_frontend *dvb_pll_attach(struct dvb_frontend *fe, int pll_addr,
 	struct dvb_pll_priv *priv = NULL;
 	int ret;
 	const struct dvb_pll_desc *desc;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 
 	b1 = kmalloc(1, GFP_KERNEL);
 	if (!b1)
@@ -844,8 +845,19 @@ struct dvb_frontend *dvb_pll_attach(struct dvb_frontend *fe, int pll_addr,
 
 	strncpy(fe->ops.tuner_ops.info.name, desc->name,
 		sizeof(fe->ops.tuner_ops.info.name));
-	fe->ops.tuner_ops.info.frequency_min = desc->min;
-	fe->ops.tuner_ops.info.frequency_max = desc->max;
+	switch (c->delivery_system) {
+	case SYS_DVBS:
+	case SYS_DVBS2:
+	case SYS_TURBO:
+	case SYS_ISDBS:
+		fe->ops.tuner_ops.info.frequency_min_hz = desc->min * kHz;
+		fe->ops.tuner_ops.info.frequency_max_hz = desc->max * kHz;
+		break;
+	default:
+		fe->ops.tuner_ops.info.frequency_min_hz = desc->min;
+		fe->ops.tuner_ops.info.frequency_max_hz = desc->max;
+	}
+
 	if (!desc->initdata)
 		fe->ops.tuner_ops.init = NULL;
 	if (!desc->sleepdata)
@@ -884,6 +896,17 @@ dvb_pll_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	if (!dvb_pll_attach(fe, client->addr, client->adapter, desc_id))
 		return -ENOMEM;
 
+	/*
+	 * Unset tuner_ops.release (== dvb_pll_release)
+	 * which has been just set in the above dvb_pll_attach(),
+	 * because if tuner_ops.release was left defined,
+	 * this module would be 'put' twice on exit:
+	 * once by dvb_frontend_detach() and another by dvb_module_release().
+	 *
+	 * dvb_pll_release is instead executed in the i2c driver's .remove(),
+	 * keeping dvb_pll_attach untouched for legacy (dvb_attach) drivers.
+	 */
+	fe->ops.tuner_ops.release = NULL;
 	dev_info(&client->dev, "DVB Simple Tuner attached.\n");
 	return 0;
 }
diff --git a/drivers/media/dvb-frontends/dvb_dummy_fe.c b/drivers/media/dvb-frontends/dvb_dummy_fe.c
index 6650d4f61ef2..a4cbcae7967d 100644
--- a/drivers/media/dvb-frontends/dvb_dummy_fe.c
+++ b/drivers/media/dvb-frontends/dvb_dummy_fe.c
@@ -170,9 +170,9 @@ static const struct dvb_frontend_ops dvb_dummy_fe_ofdm_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "Dummy DVB-T",
-		.frequency_min		= 0,
-		.frequency_max		= 863250000,
-		.frequency_stepsize	= 62500,
+		.frequency_min_hz	= 0,
+		.frequency_max_hz	= 863250 * kHz,
+		.frequency_stepsize_hz	= 62500,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 				FE_CAN_FEC_4_5 | FE_CAN_FEC_5_6 | FE_CAN_FEC_6_7 |
 				FE_CAN_FEC_7_8 | FE_CAN_FEC_8_9 | FE_CAN_FEC_AUTO |
@@ -201,11 +201,11 @@ static const struct dvb_frontend_ops dvb_dummy_fe_qam_ops = {
 	.delsys = { SYS_DVBC_ANNEX_A },
 	.info = {
 		.name			= "Dummy DVB-C",
-		.frequency_stepsize	= 62500,
-		.frequency_min		= 51000000,
-		.frequency_max		= 858000000,
-		.symbol_rate_min	= (57840000/2)/64,     /* SACLK/64 == (XIN/2)/64 */
-		.symbol_rate_max	= (57840000/2)/4,      /* SACLK/4 */
+		.frequency_min_hz	=  51 * MHz,
+		.frequency_max_hz	= 858 * MHz,
+		.frequency_stepsize_hz	= 62500,
+		.symbol_rate_min	= (57840000 / 2) / 64,  /* SACLK/64 == (XIN/2)/64 */
+		.symbol_rate_max	= (57840000 / 2) / 4,   /* SACLK/4 */
 		.caps = FE_CAN_QAM_16 | FE_CAN_QAM_32 | FE_CAN_QAM_64 |
 			FE_CAN_QAM_128 | FE_CAN_QAM_256 |
 			FE_CAN_FEC_AUTO | FE_CAN_INVERSION_AUTO
@@ -230,10 +230,10 @@ static const struct dvb_frontend_ops dvb_dummy_fe_qpsk_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "Dummy DVB-S",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 250,           /* kHz for QPSK frontends */
-		.frequency_tolerance	= 29500,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
+		.frequency_stepsize_hz	= 250 * kHz,
+		.frequency_tolerance_hz	= 29500 * kHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/gp8psk-fe.c b/drivers/media/dvb-frontends/gp8psk-fe.c
index a772ef8bfe1c..238f09aa72f2 100644
--- a/drivers/media/dvb-frontends/gp8psk-fe.c
+++ b/drivers/media/dvb-frontends/gp8psk-fe.c
@@ -355,9 +355,9 @@ static const struct dvb_frontend_ops gp8psk_fe_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "Genpix DVB-S",
-		.frequency_min		= 800000,
-		.frequency_max		= 2250000,
-		.frequency_stepsize	= 100,
+		.frequency_min_hz	=  800 * MHz,
+		.frequency_max_hz	= 2250 * MHz,
+		.frequency_stepsize_hz	=  100 * kHz,
 		.symbol_rate_min        = 1000000,
 		.symbol_rate_max        = 45000000,
 		.symbol_rate_tolerance  = 500,  /* ppm */
diff --git a/drivers/media/dvb-frontends/helene.c b/drivers/media/dvb-frontends/helene.c
index a0d0b53c91d7..d7790cb98a0c 100644
--- a/drivers/media/dvb-frontends/helene.c
+++ b/drivers/media/dvb-frontends/helene.c
@@ -666,7 +666,7 @@ static int helene_set_params_s(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int helene_set_params(struct dvb_frontend *fe)
+static int helene_set_params_t(struct dvb_frontend *fe)
 {
 	u8 data[MAX_WRITE_REGSIZE];
 	u32 frequency;
@@ -835,6 +835,19 @@ static int helene_set_params(struct dvb_frontend *fe)
 	return 0;
 }
 
+static int helene_set_params(struct dvb_frontend *fe)
+{
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+
+	if (p->delivery_system == SYS_DVBT ||
+	    p->delivery_system == SYS_DVBT2 ||
+	    p->delivery_system == SYS_ISDBT ||
+	    p->delivery_system == SYS_DVBC_ANNEX_A)
+		return helene_set_params_t(fe);
+
+	return helene_set_params_s(fe);
+}
+
 static int helene_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 {
 	struct helene_priv *priv = fe->tuner_priv;
@@ -843,26 +856,26 @@ static int helene_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 	return 0;
 }
 
-static const struct dvb_tuner_ops helene_tuner_ops = {
+static const struct dvb_tuner_ops helene_tuner_ops_t = {
 	.info = {
 		.name = "Sony HELENE Ter tuner",
-		.frequency_min = 1000000,
-		.frequency_max = 1200000000,
-		.frequency_step = 25000,
+		.frequency_min_hz  =    1 * MHz,
+		.frequency_max_hz  = 1200 * MHz,
+		.frequency_step_hz =   25 * kHz,
 	},
 	.init = helene_init,
 	.release = helene_release,
 	.sleep = helene_sleep,
-	.set_params = helene_set_params,
+	.set_params = helene_set_params_t,
 	.get_frequency = helene_get_frequency,
 };
 
 static const struct dvb_tuner_ops helene_tuner_ops_s = {
 	.info = {
 		.name = "Sony HELENE Sat tuner",
-		.frequency_min = 500000,
-		.frequency_max = 2500000,
-		.frequency_step = 1000,
+		.frequency_min_hz  =  500 * MHz,
+		.frequency_max_hz  = 2500 * MHz,
+		.frequency_step_hz =    1 * MHz,
 	},
 	.init = helene_init,
 	.release = helene_release,
@@ -871,6 +884,20 @@ static const struct dvb_tuner_ops helene_tuner_ops_s = {
 	.get_frequency = helene_get_frequency,
 };
 
+static const struct dvb_tuner_ops helene_tuner_ops = {
+	.info = {
+		.name = "Sony HELENE Sat/Ter tuner",
+		.frequency_min_hz  =    1 * MHz,
+		.frequency_max_hz  = 2500 * MHz,
+		.frequency_step_hz =   25 * kHz,
+	},
+	.init = helene_init,
+	.release = helene_release,
+	.sleep = helene_sleep,
+	.set_params = helene_set_params,
+	.get_frequency = helene_get_frequency,
+};
+
 /* power-on tuner
  * call once after reset
  */
@@ -897,7 +924,10 @@ static int helene_x_pon(struct helene_priv *priv)
 	helene_write_regs(priv, 0x99, cdata, sizeof(cdata));
 
 	/* 0x81 - 0x94 */
-	data[0] = 0x18; /* xtal 24 MHz */
+	if (priv->xtal == SONY_HELENE_XTAL_16000)
+		data[0] = 0x10; /* xtal 16 MHz */
+	else
+		data[0] = 0x18; /* xtal 24 MHz */
 	data[1] = (uint8_t)(0x80 | (0x04 & 0x1F)); /* 4 x 25 = 100uA */
 	data[2] = (uint8_t)(0x80 | (0x26 & 0x7F)); /* 38 x 0.25 = 9.5pF */
 	data[3] = 0x80; /* REFOUT signal output 500mVpp */
@@ -1032,7 +1062,7 @@ struct dvb_frontend *helene_attach(struct dvb_frontend *fe,
 	if (fe->ops.i2c_gate_ctrl)
 		fe->ops.i2c_gate_ctrl(fe, 0);
 
-	memcpy(&fe->ops.tuner_ops, &helene_tuner_ops,
+	memcpy(&fe->ops.tuner_ops, &helene_tuner_ops_t,
 			sizeof(struct dvb_tuner_ops));
 	fe->tuner_priv = priv;
 	dev_info(&priv->i2c->dev,
@@ -1042,6 +1072,59 @@ struct dvb_frontend *helene_attach(struct dvb_frontend *fe,
 }
 EXPORT_SYMBOL(helene_attach);
 
+static int helene_probe(struct i2c_client *client,
+			const struct i2c_device_id *id)
+{
+	struct helene_config *config = client->dev.platform_data;
+	struct dvb_frontend *fe = config->fe;
+	struct device *dev = &client->dev;
+	struct helene_priv *priv;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->i2c_address = client->addr;
+	priv->i2c = client->adapter;
+	priv->set_tuner_data = config->set_tuner_priv;
+	priv->set_tuner = config->set_tuner_callback;
+	priv->xtal = config->xtal;
+
+	if (fe->ops.i2c_gate_ctrl)
+		fe->ops.i2c_gate_ctrl(fe, 1);
+
+	if (helene_x_pon(priv) != 0)
+		return -EINVAL;
+
+	if (fe->ops.i2c_gate_ctrl)
+		fe->ops.i2c_gate_ctrl(fe, 0);
+
+	memcpy(&fe->ops.tuner_ops, &helene_tuner_ops,
+	       sizeof(struct dvb_tuner_ops));
+	fe->tuner_priv = priv;
+	i2c_set_clientdata(client, priv);
+
+	dev_info(dev, "Sony HELENE attached on addr=%x at I2C adapter %p\n",
+		 priv->i2c_address, priv->i2c);
+
+	return 0;
+}
+
+static const struct i2c_device_id helene_id[] = {
+	{ "helene", },
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, helene_id);
+
+static struct i2c_driver helene_driver = {
+	.driver = {
+		.name = "helene",
+	},
+	.probe    = helene_probe,
+	.id_table = helene_id,
+};
+module_i2c_driver(helene_driver);
+
 MODULE_DESCRIPTION("Sony HELENE Sat/Ter tuner driver");
 MODULE_AUTHOR("Abylay Ospan <aospan@netup.ru>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/dvb-frontends/helene.h b/drivers/media/dvb-frontends/helene.h
index c9fc81c7e4e7..8562d01bc93e 100644
--- a/drivers/media/dvb-frontends/helene.h
+++ b/drivers/media/dvb-frontends/helene.h
@@ -39,6 +39,7 @@ enum helene_xtal {
  * @set_tuner_callback:	Callback function that notifies the parent driver
  *			which tuner is active now
  * @xtal: Cristal frequency as described by &enum helene_xtal
+ * @fe: Frontend for which connects this tuner
  */
 struct helene_config {
 	u8	i2c_address;
@@ -46,6 +47,8 @@ struct helene_config {
 	void	*set_tuner_priv;
 	int	(*set_tuner_callback)(void *, int);
 	enum helene_xtal xtal;
+
+	struct dvb_frontend *fe;
 };
 
 #if IS_REACHABLE(CONFIG_DVB_HELENE)
diff --git a/drivers/media/dvb-frontends/horus3a.c b/drivers/media/dvb-frontends/horus3a.c
index 5e7e265a52e6..02bc08081971 100644
--- a/drivers/media/dvb-frontends/horus3a.c
+++ b/drivers/media/dvb-frontends/horus3a.c
@@ -330,9 +330,9 @@ static int horus3a_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 static const struct dvb_tuner_ops horus3a_tuner_ops = {
 	.info = {
 		.name = "Sony Horus3a",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_step = 1000,
+		.frequency_min_hz  =  950 * MHz,
+		.frequency_max_hz  = 2150 * MHz,
+		.frequency_step_hz =    1 * MHz,
 	},
 	.init = horus3a_init,
 	.release = horus3a_release,
diff --git a/drivers/media/dvb-frontends/itd1000.c b/drivers/media/dvb-frontends/itd1000.c
index 04f7f6854f73..c3a6e81ae87f 100644
--- a/drivers/media/dvb-frontends/itd1000.c
+++ b/drivers/media/dvb-frontends/itd1000.c
@@ -353,10 +353,10 @@ static void itd1000_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops itd1000_tuner_ops = {
 	.info = {
-		.name           = "Integrant ITD1000",
-		.frequency_min  = 950000,
-		.frequency_max  = 2150000,
-		.frequency_step = 125,     /* kHz for QPSK frontends */
+		.name              = "Integrant ITD1000",
+		.frequency_min_hz  =  950 * MHz,
+		.frequency_max_hz  = 2150 * MHz,
+		.frequency_step_hz =  125 * kHz,
 	},
 
 	.release       = itd1000_release,
diff --git a/drivers/media/dvb-frontends/ix2505v.c b/drivers/media/dvb-frontends/ix2505v.c
index 965012ad5c59..a30707b61b1f 100644
--- a/drivers/media/dvb-frontends/ix2505v.c
+++ b/drivers/media/dvb-frontends/ix2505v.c
@@ -135,8 +135,8 @@ static int ix2505v_set_params(struct dvb_frontend *fe)
 	u8 gain, cc, ref, psc, local_osc, lpf;
 	u8 data[4] = {0};
 
-	if ((frequency < fe->ops.info.frequency_min)
-	||  (frequency > fe->ops.info.frequency_max))
+	if ((frequency < fe->ops.info.frequency_min_hz / kHz)
+	||  (frequency > fe->ops.info.frequency_max_hz / kHz))
 		return -EINVAL;
 
 	if (state->config->tuner_gain)
@@ -256,8 +256,8 @@ static int ix2505v_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 static const struct dvb_tuner_ops ix2505v_tuner_ops = {
 	.info = {
 		.name = "Sharp IX2505V (B0017)",
-		.frequency_min = 950000,
-		.frequency_max = 2175000
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2175 * MHz
 	},
 	.release = ix2505v_release,
 	.set_params = ix2505v_set_params,
diff --git a/drivers/media/dvb-frontends/l64781.c b/drivers/media/dvb-frontends/l64781.c
index 249c18761e6e..9afb5bf6424b 100644
--- a/drivers/media/dvb-frontends/l64781.c
+++ b/drivers/media/dvb-frontends/l64781.c
@@ -575,10 +575,9 @@ static const struct dvb_frontend_ops l64781_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "LSI L64781 DVB-T",
-	/*	.frequency_min = ???,*/
-	/*	.frequency_max = ???,*/
-		.frequency_stepsize = 166666,
-	/*      .frequency_tolerance = ???,*/
+	/*	.frequency_min_hz = ???,*/
+	/*	.frequency_max_hz = ???,*/
+		.frequency_stepsize_hz = 166666,
 	/*      .symbol_rate_tolerance = ???,*/
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		      FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 |
diff --git a/drivers/media/dvb-frontends/lg2160.c b/drivers/media/dvb-frontends/lg2160.c
index 9854096839ae..408151e33fa7 100644
--- a/drivers/media/dvb-frontends/lg2160.c
+++ b/drivers/media/dvb-frontends/lg2160.c
@@ -1349,9 +1349,9 @@ static const struct dvb_frontend_ops lg2160_ops = {
 	.delsys = { SYS_ATSCMH },
 	.info = {
 		.name = "LG Electronics LG2160 ATSC/MH Frontend",
-		.frequency_min      = 54000000,
-		.frequency_max      = 858000000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz      =  54 * MHz,
+		.frequency_max_hz      = 858 * MHz,
+		.frequency_stepsize_hz = 62500,
 	},
 	.i2c_gate_ctrl        = lg216x_i2c_gate_ctrl,
 #if 0
@@ -1375,9 +1375,9 @@ static const struct dvb_frontend_ops lg2161_ops = {
 	.delsys = { SYS_ATSCMH },
 	.info = {
 		.name = "LG Electronics LG2161 ATSC/MH Frontend",
-		.frequency_min      = 54000000,
-		.frequency_max      = 858000000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz      =  54 * MHz,
+		.frequency_max_hz      = 858 * MHz,
+		.frequency_stepsize_hz = 62500,
 	},
 	.i2c_gate_ctrl        = lg216x_i2c_gate_ctrl,
 #if 0
diff --git a/drivers/media/dvb-frontends/lgdt3305.c b/drivers/media/dvb-frontends/lgdt3305.c
index 735d73060265..857e9b4d69b4 100644
--- a/drivers/media/dvb-frontends/lgdt3305.c
+++ b/drivers/media/dvb-frontends/lgdt3305.c
@@ -1164,9 +1164,9 @@ static const struct dvb_frontend_ops lgdt3304_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name = "LG Electronics LGDT3304 VSB/QAM Frontend",
-		.frequency_min      = 54000000,
-		.frequency_max      = 858000000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz      =  54 * MHz,
+		.frequency_max_hz      = 858 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
 	},
 	.i2c_gate_ctrl        = lgdt3305_i2c_gate_ctrl,
@@ -1187,9 +1187,9 @@ static const struct dvb_frontend_ops lgdt3305_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name = "LG Electronics LGDT3305 VSB/QAM Frontend",
-		.frequency_min      = 54000000,
-		.frequency_max      = 858000000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz      =  54 * MHz,
+		.frequency_max_hz      = 858 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
 	},
 	.i2c_gate_ctrl        = lgdt3305_i2c_gate_ctrl,
diff --git a/drivers/media/dvb-frontends/lgdt3306a.c b/drivers/media/dvb-frontends/lgdt3306a.c
index 32de824476db..0e1f5daaf20c 100644
--- a/drivers/media/dvb-frontends/lgdt3306a.c
+++ b/drivers/media/dvb-frontends/lgdt3306a.c
@@ -2157,9 +2157,9 @@ static const struct dvb_frontend_ops lgdt3306a_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name = "LG Electronics LGDT3306A VSB/QAM Frontend",
-		.frequency_min      = 54000000,
-		.frequency_max      = 858000000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz      =  54 * MHz,
+		.frequency_max_hz      = 858 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.caps = FE_CAN_QAM_AUTO | FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
 	},
 	.i2c_gate_ctrl        = lgdt3306a_i2c_gate_ctrl,
diff --git a/drivers/media/dvb-frontends/lgdt330x.c b/drivers/media/dvb-frontends/lgdt330x.c
index f6731738b073..10d584ce538d 100644
--- a/drivers/media/dvb-frontends/lgdt330x.c
+++ b/drivers/media/dvb-frontends/lgdt330x.c
@@ -944,9 +944,9 @@ static const struct dvb_frontend_ops lgdt3302_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name = "LG Electronics LGDT3302 VSB/QAM Frontend",
-		.frequency_min = 54000000,
-		.frequency_max = 858000000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz =  54 * MHz,
+		.frequency_max_hz = 858 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.symbol_rate_min    = 5056941,	/* QAM 64 */
 		.symbol_rate_max    = 10762000,	/* VSB 8  */
 		.caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
@@ -966,9 +966,9 @@ static const struct dvb_frontend_ops lgdt3303_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name = "LG Electronics LGDT3303 VSB/QAM Frontend",
-		.frequency_min = 54000000,
-		.frequency_max = 858000000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz =  54 * MHz,
+		.frequency_max_hz = 858 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.symbol_rate_min    = 5056941,	/* QAM 64 */
 		.symbol_rate_max    = 10762000,	/* VSB 8  */
 		.caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
diff --git a/drivers/media/dvb-frontends/lgs8gl5.c b/drivers/media/dvb-frontends/lgs8gl5.c
index f47e5a1af16d..07e5bcee9c1e 100644
--- a/drivers/media/dvb-frontends/lgs8gl5.c
+++ b/drivers/media/dvb-frontends/lgs8gl5.c
@@ -416,10 +416,9 @@ static const struct dvb_frontend_ops lgs8gl5_ops = {
 	.delsys = { SYS_DTMB },
 	.info = {
 		.name			= "Legend Silicon LGS-8GL5 DMB-TH",
-		.frequency_min		= 474000000,
-		.frequency_max		= 858000000,
-		.frequency_stepsize	= 10000,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	= 474 * MHz,
+		.frequency_max_hz	= 858 * MHz,
+		.frequency_stepsize_hz	=  10 * kHz,
 		.caps = FE_CAN_FEC_AUTO |
 			FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_32 |
 			FE_CAN_QAM_64 | FE_CAN_QAM_AUTO |
diff --git a/drivers/media/dvb-frontends/lgs8gxx.c b/drivers/media/dvb-frontends/lgs8gxx.c
index 84af8a12f26a..a6bcf1571d10 100644
--- a/drivers/media/dvb-frontends/lgs8gxx.c
+++ b/drivers/media/dvb-frontends/lgs8gxx.c
@@ -985,9 +985,9 @@ static const struct dvb_frontend_ops lgs8gxx_ops = {
 	.delsys = { SYS_DTMB },
 	.info = {
 		.name = "Legend Silicon LGS8913/LGS8GXX DMB-TH",
-		.frequency_min = 474000000,
-		.frequency_max = 858000000,
-		.frequency_stepsize = 10000,
+		.frequency_min_hz = 474 * MHz,
+		.frequency_max_hz = 858 * MHz,
+		.frequency_stepsize_hz = 10 * kHz,
 		.caps =
 			FE_CAN_FEC_AUTO |
 			FE_CAN_QAM_AUTO |
diff --git a/drivers/media/dvb-frontends/m88ds3103.c b/drivers/media/dvb-frontends/m88ds3103.c
index 65d157fe76d1..dffd2d4bf1c8 100644
--- a/drivers/media/dvb-frontends/m88ds3103.c
+++ b/drivers/media/dvb-frontends/m88ds3103.c
@@ -1300,9 +1300,9 @@ static const struct dvb_frontend_ops m88ds3103_ops = {
 	.delsys = {SYS_DVBS, SYS_DVBS2},
 	.info = {
 		.name = "Montage Technology M88DS3103",
-		.frequency_min =  950000,
-		.frequency_max = 2150000,
-		.frequency_tolerance = 5000,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
+		.frequency_tolerance_hz = 5 * MHz,
 		.symbol_rate_min =  1000000,
 		.symbol_rate_max = 45000000,
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/m88rs2000.c b/drivers/media/dvb-frontends/m88rs2000.c
index 496ce27fa63a..d5bc85501f9e 100644
--- a/drivers/media/dvb-frontends/m88rs2000.c
+++ b/drivers/media/dvb-frontends/m88rs2000.c
@@ -759,10 +759,10 @@ static const struct dvb_frontend_ops m88rs2000_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "M88RS2000 DVB-S",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 1000,	 /* kHz for QPSK frontends */
-		.frequency_tolerance	= 5000,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
+		.frequency_stepsize_hz	= 1 * MHz,
+		.frequency_tolerance_hz	= 5 * MHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 		.symbol_rate_tolerance	= 500,	/* ppm */
diff --git a/drivers/media/dvb-frontends/mb86a16.c b/drivers/media/dvb-frontends/mb86a16.c
index 377cd984b069..da505a5d035f 100644
--- a/drivers/media/dvb-frontends/mb86a16.c
+++ b/drivers/media/dvb-frontends/mb86a16.c
@@ -1808,10 +1808,9 @@ static const struct dvb_frontend_ops mb86a16_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "Fujitsu MB86A16 DVB-S",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 3000,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
+		.frequency_stepsize_hz	=    3 * MHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 		.symbol_rate_tolerance	= 500,
diff --git a/drivers/media/dvb-frontends/mb86a20s.c b/drivers/media/dvb-frontends/mb86a20s.c
index c3b1b88e2e7a..66fc77db0e75 100644
--- a/drivers/media/dvb-frontends/mb86a20s.c
+++ b/drivers/media/dvb-frontends/mb86a20s.c
@@ -2111,9 +2111,9 @@ static const struct dvb_frontend_ops mb86a20s_ops = {
 			FE_CAN_TRANSMISSION_MODE_AUTO | FE_CAN_QAM_AUTO |
 			FE_CAN_GUARD_INTERVAL_AUTO    | FE_CAN_HIERARCHY_AUTO,
 		/* Actually, those values depend on the used tuner */
-		.frequency_min = 45000000,
-		.frequency_max = 864000000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz =  45 * MHz,
+		.frequency_max_hz = 864 * MHz,
+		.frequency_stepsize_hz = 62500,
 	},
 
 	.release = mb86a20s_release,
diff --git a/drivers/media/dvb-frontends/mn88443x.c b/drivers/media/dvb-frontends/mn88443x.c
new file mode 100644
index 000000000000..9ec1aeef03d5
--- /dev/null
+++ b/drivers/media/dvb-frontends/mn88443x.c
@@ -0,0 +1,802 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Socionext MN88443x series demodulator driver for ISDB-S/ISDB-T.
+//
+// Copyright (c) 2018 Socionext Inc.
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/of_device.h>
+#include <linux/regmap.h>
+#include <media/dvb_math.h>
+
+#include "mn88443x.h"
+
+/* ISDB-S registers */
+#define ATSIDU_S                                    0x2f
+#define ATSIDL_S                                    0x30
+#define TSSET_S                                     0x31
+#define AGCREAD_S                                   0x5a
+#define CPMON1_S                                    0x5e
+#define   CPMON1_S_FSYNC                              BIT(5)
+#define   CPMON1_S_ERRMON                             BIT(4)
+#define   CPMON1_S_SIGOFF                             BIT(3)
+#define   CPMON1_S_W2LOCK                             BIT(2)
+#define   CPMON1_S_W1LOCK                             BIT(1)
+#define   CPMON1_S_DW1LOCK                            BIT(0)
+#define TRMON_S                                     0x60
+#define BERCNFLG_S                                  0x68
+#define   BERCNFLG_S_BERVRDY                          BIT(5)
+#define   BERCNFLG_S_BERVCHK                          BIT(4)
+#define   BERCNFLG_S_BERDRDY                          BIT(3)
+#define   BERCNFLG_S_BERDCHK                          BIT(2)
+#define CNRDXU_S                                    0x69
+#define CNRDXL_S                                    0x6a
+#define CNRDYU_S                                    0x6b
+#define CNRDYL_S                                    0x6c
+#define BERVRDU_S                                   0x71
+#define BERVRDL_S                                   0x72
+#define DOSET1_S                                    0x73
+
+/* Primary ISDB-T */
+#define PLLASET1                                    0x00
+#define PLLASET2                                    0x01
+#define PLLBSET1                                    0x02
+#define PLLBSET2                                    0x03
+#define PLLSET                                      0x04
+#define OUTCSET                                     0x08
+#define   OUTCSET_CHDRV_8MA                           0xff
+#define   OUTCSET_CHDRV_4MA                           0x00
+#define PLDWSET                                     0x09
+#define   PLDWSET_NORMAL                             0x00
+#define   PLDWSET_PULLDOWN                           0xff
+#define HIZSET1                                     0x0a
+#define HIZSET2                                     0x0b
+
+/* Secondary ISDB-T (for MN884434 only) */
+#define RCVSET                                      0x00
+#define TSSET1_M                                    0x01
+#define TSSET2_M                                    0x02
+#define TSSET3_M                                    0x03
+#define INTACSET                                    0x08
+#define HIZSET3                                     0x0b
+
+/* ISDB-T registers */
+#define TSSET1                                      0x05
+#define   TSSET1_TSASEL_MASK                          GENMASK(4, 3)
+#define   TSSET1_TSASEL_ISDBT                         (0x0 << 3)
+#define   TSSET1_TSASEL_ISDBS                         (0x1 << 3)
+#define   TSSET1_TSASEL_NONE                          (0x2 << 3)
+#define   TSSET1_TSBSEL_MASK                          GENMASK(2, 1)
+#define   TSSET1_TSBSEL_ISDBS                         (0x0 << 1)
+#define   TSSET1_TSBSEL_ISDBT                         (0x1 << 1)
+#define   TSSET1_TSBSEL_NONE                          (0x2 << 1)
+#define TSSET2                                      0x06
+#define TSSET3                                      0x07
+#define   TSSET3_INTASEL_MASK                         GENMASK(7, 6)
+#define   TSSET3_INTASEL_T                            (0x0 << 6)
+#define   TSSET3_INTASEL_S                            (0x1 << 6)
+#define   TSSET3_INTASEL_NONE                         (0x2 << 6)
+#define   TSSET3_INTBSEL_MASK                         GENMASK(5, 4)
+#define   TSSET3_INTBSEL_S                            (0x0 << 4)
+#define   TSSET3_INTBSEL_T                            (0x1 << 4)
+#define   TSSET3_INTBSEL_NONE                         (0x2 << 4)
+#define OUTSET2                                     0x0d
+#define PWDSET                                      0x0f
+#define   PWDSET_OFDMPD_MASK                          GENMASK(3, 2)
+#define   PWDSET_OFDMPD_DOWN                          BIT(3)
+#define   PWDSET_PSKPD_MASK                           GENMASK(1, 0)
+#define   PWDSET_PSKPD_DOWN                           BIT(1)
+#define CLKSET1_T                                   0x11
+#define MDSET_T                                     0x13
+#define   MDSET_T_MDAUTO_MASK                         GENMASK(7, 4)
+#define   MDSET_T_MDAUTO_AUTO                         (0xf << 4)
+#define   MDSET_T_MDAUTO_MANUAL                       (0x0 << 4)
+#define   MDSET_T_FFTS_MASK                           GENMASK(3, 2)
+#define   MDSET_T_FFTS_MODE1                          (0x0 << 2)
+#define   MDSET_T_FFTS_MODE2                          (0x1 << 2)
+#define   MDSET_T_FFTS_MODE3                          (0x2 << 2)
+#define   MDSET_T_GI_MASK                             GENMASK(1, 0)
+#define   MDSET_T_GI_1_32                             (0x0 << 0)
+#define   MDSET_T_GI_1_16                             (0x1 << 0)
+#define   MDSET_T_GI_1_8                              (0x2 << 0)
+#define   MDSET_T_GI_1_4                              (0x3 << 0)
+#define MDASET_T                                    0x14
+#define ADCSET1_T                                   0x20
+#define   ADCSET1_T_REFSEL_MASK                       GENMASK(1, 0)
+#define   ADCSET1_T_REFSEL_2V                         (0x3 << 0)
+#define   ADCSET1_T_REFSEL_1_5V                       (0x2 << 0)
+#define   ADCSET1_T_REFSEL_1V                         (0x1 << 0)
+#define NCOFREQU_T                                  0x24
+#define NCOFREQM_T                                  0x25
+#define NCOFREQL_T                                  0x26
+#define FADU_T                                      0x27
+#define FADM_T                                      0x28
+#define FADL_T                                      0x29
+#define AGCSET2_T                                   0x2c
+#define   AGCSET2_T_IFPOLINV_INC                      BIT(0)
+#define   AGCSET2_T_RFPOLINV_INC                      BIT(1)
+#define AGCV3_T                                     0x3e
+#define MDRD_T                                      0xa2
+#define   MDRD_T_SEGID_MASK                           GENMASK(5, 4)
+#define   MDRD_T_SEGID_13                             (0x0 << 4)
+#define   MDRD_T_SEGID_1                              (0x1 << 4)
+#define   MDRD_T_SEGID_3                              (0x2 << 4)
+#define   MDRD_T_FFTS_MASK                            GENMASK(3, 2)
+#define   MDRD_T_FFTS_MODE1                           (0x0 << 2)
+#define   MDRD_T_FFTS_MODE2                           (0x1 << 2)
+#define   MDRD_T_FFTS_MODE3                           (0x2 << 2)
+#define   MDRD_T_GI_MASK                              GENMASK(1, 0)
+#define   MDRD_T_GI_1_32                              (0x0 << 0)
+#define   MDRD_T_GI_1_16                              (0x1 << 0)
+#define   MDRD_T_GI_1_8                               (0x2 << 0)
+#define   MDRD_T_GI_1_4                               (0x3 << 0)
+#define SSEQRD_T                                    0xa3
+#define   SSEQRD_T_SSEQSTRD_MASK                      GENMASK(3, 0)
+#define   SSEQRD_T_SSEQSTRD_RESET                     (0x0 << 0)
+#define   SSEQRD_T_SSEQSTRD_TUNING                    (0x1 << 0)
+#define   SSEQRD_T_SSEQSTRD_AGC                       (0x2 << 0)
+#define   SSEQRD_T_SSEQSTRD_SEARCH                    (0x3 << 0)
+#define   SSEQRD_T_SSEQSTRD_CLOCK_SYNC                (0x4 << 0)
+#define   SSEQRD_T_SSEQSTRD_FREQ_SYNC                 (0x8 << 0)
+#define   SSEQRD_T_SSEQSTRD_FRAME_SYNC                (0x9 << 0)
+#define   SSEQRD_T_SSEQSTRD_SYNC                      (0xa << 0)
+#define   SSEQRD_T_SSEQSTRD_LOCK                      (0xb << 0)
+#define AGCRDU_T                                    0xa8
+#define AGCRDL_T                                    0xa9
+#define CNRDU_T                                     0xbe
+#define CNRDL_T                                     0xbf
+#define BERFLG_T                                    0xc0
+#define   BERFLG_T_BERDRDY                            BIT(7)
+#define   BERFLG_T_BERDCHK                            BIT(6)
+#define   BERFLG_T_BERVRDYA                           BIT(5)
+#define   BERFLG_T_BERVCHKA                           BIT(4)
+#define   BERFLG_T_BERVRDYB                           BIT(3)
+#define   BERFLG_T_BERVCHKB                           BIT(2)
+#define   BERFLG_T_BERVRDYC                           BIT(1)
+#define   BERFLG_T_BERVCHKC                           BIT(0)
+#define BERRDU_T                                    0xc1
+#define BERRDM_T                                    0xc2
+#define BERRDL_T                                    0xc3
+#define BERLENRDU_T                                 0xc4
+#define BERLENRDL_T                                 0xc5
+#define ERRFLG_T                                    0xc6
+#define   ERRFLG_T_BERDOVF                            BIT(7)
+#define   ERRFLG_T_BERVOVFA                           BIT(6)
+#define   ERRFLG_T_BERVOVFB                           BIT(5)
+#define   ERRFLG_T_BERVOVFC                           BIT(4)
+#define   ERRFLG_T_NERRFA                             BIT(3)
+#define   ERRFLG_T_NERRFB                             BIT(2)
+#define   ERRFLG_T_NERRFC                             BIT(1)
+#define   ERRFLG_T_NERRF                              BIT(0)
+#define DOSET1_T                                    0xcf
+
+#define CLK_LOW            4000000
+#define CLK_DIRECT         20200000
+#define CLK_MAX            25410000
+
+#define S_T_FREQ           8126984 /* 512 / 63 MHz */
+
+struct mn88443x_spec {
+	bool primary;
+};
+
+struct mn88443x_priv {
+	const struct mn88443x_spec *spec;
+
+	struct dvb_frontend fe;
+	struct clk *mclk;
+	struct gpio_desc *reset_gpio;
+	u32 clk_freq;
+	u32 if_freq;
+
+	/* Common */
+	bool use_clkbuf;
+
+	/* ISDB-S */
+	struct i2c_client *client_s;
+	struct regmap *regmap_s;
+
+	/* ISDB-T */
+	struct i2c_client *client_t;
+	struct regmap *regmap_t;
+};
+
+static void mn88443x_cmn_power_on(struct mn88443x_priv *chip)
+{
+	struct regmap *r_t = chip->regmap_t;
+
+	clk_prepare_enable(chip->mclk);
+
+	gpiod_set_value_cansleep(chip->reset_gpio, 1);
+	usleep_range(100, 1000);
+	gpiod_set_value_cansleep(chip->reset_gpio, 0);
+
+	if (chip->spec->primary) {
+		regmap_write(r_t, OUTCSET, OUTCSET_CHDRV_8MA);
+		regmap_write(r_t, PLDWSET, PLDWSET_NORMAL);
+		regmap_write(r_t, HIZSET1, 0x80);
+		regmap_write(r_t, HIZSET2, 0xe0);
+	} else {
+		regmap_write(r_t, HIZSET3, 0x8f);
+	}
+}
+
+static void mn88443x_cmn_power_off(struct mn88443x_priv *chip)
+{
+	gpiod_set_value_cansleep(chip->reset_gpio, 1);
+
+	clk_disable_unprepare(chip->mclk);
+}
+
+static void mn88443x_s_sleep(struct mn88443x_priv *chip)
+{
+	struct regmap *r_t = chip->regmap_t;
+
+	regmap_update_bits(r_t, PWDSET, PWDSET_PSKPD_MASK,
+			   PWDSET_PSKPD_DOWN);
+}
+
+static void mn88443x_s_wake(struct mn88443x_priv *chip)
+{
+	struct regmap *r_t = chip->regmap_t;
+
+	regmap_update_bits(r_t, PWDSET, PWDSET_PSKPD_MASK, 0);
+}
+
+static void mn88443x_s_tune(struct mn88443x_priv *chip,
+			    struct dtv_frontend_properties *c)
+{
+	struct regmap *r_s = chip->regmap_s;
+
+	regmap_write(r_s, ATSIDU_S, c->stream_id >> 8);
+	regmap_write(r_s, ATSIDL_S, c->stream_id);
+	regmap_write(r_s, TSSET_S, 0);
+}
+
+static int mn88443x_s_read_status(struct mn88443x_priv *chip,
+				  struct dtv_frontend_properties *c,
+				  enum fe_status *status)
+{
+	struct regmap *r_s = chip->regmap_s;
+	u32 cpmon, tmpu, tmpl, flg;
+	u64 tmp;
+
+	/* Sync detection */
+	regmap_read(r_s, CPMON1_S, &cpmon);
+
+	*status = 0;
+	if (cpmon & CPMON1_S_FSYNC)
+		*status |= FE_HAS_VITERBI | FE_HAS_SYNC | FE_HAS_LOCK;
+	if (cpmon & CPMON1_S_W2LOCK)
+		*status |= FE_HAS_SIGNAL | FE_HAS_CARRIER;
+
+	/* Signal strength */
+	c->strength.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+
+	if (*status & FE_HAS_SIGNAL) {
+		u32 agc;
+
+		regmap_read(r_s, AGCREAD_S, &tmpu);
+		agc = tmpu << 8;
+
+		c->strength.len = 1;
+		c->strength.stat[0].scale = FE_SCALE_RELATIVE;
+		c->strength.stat[0].uvalue = agc;
+	}
+
+	/* C/N rate */
+	c->cnr.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+
+	if (*status & FE_HAS_VITERBI) {
+		u32 cnr = 0, x, y, d;
+		u64 d_3 = 0;
+
+		regmap_read(r_s, CNRDXU_S, &tmpu);
+		regmap_read(r_s, CNRDXL_S, &tmpl);
+		x = (tmpu << 8) | tmpl;
+		regmap_read(r_s, CNRDYU_S, &tmpu);
+		regmap_read(r_s, CNRDYL_S, &tmpl);
+		y = (tmpu << 8) | tmpl;
+
+		/* CNR[dB]: 10 * log10(D) - 30.74 / D^3 - 3 */
+		/*   D = x^2 / (2^15 * y - x^2) */
+		d = (y << 15) - x * x;
+		if (d > 0) {
+			/* (2^4 * D)^3 = 2^12 * D^3 */
+			/* 3.074 * 2^(12 + 24) = 211243671486 */
+			d_3 = div_u64(16 * x * x, d);
+			d_3 = d_3 * d_3 * d_3;
+			if (d_3)
+				d_3 = div_u64(211243671486ULL, d_3);
+		}
+
+		if (d_3) {
+			/* 0.3 * 2^24 = 5033164 */
+			tmp = (s64)2 * intlog10(x) - intlog10(abs(d)) - d_3
+				- 5033164;
+			cnr = div_u64(tmp * 10000, 1 << 24);
+		}
+
+		if (cnr) {
+			c->cnr.len = 1;
+			c->cnr.stat[0].scale = FE_SCALE_DECIBEL;
+			c->cnr.stat[0].uvalue = cnr;
+		}
+	}
+
+	/* BER */
+	c->post_bit_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	c->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+
+	regmap_read(r_s, BERCNFLG_S, &flg);
+
+	if ((*status & FE_HAS_VITERBI) && (flg & BERCNFLG_S_BERVRDY)) {
+		u32 bit_err, bit_cnt;
+
+		regmap_read(r_s, BERVRDU_S, &tmpu);
+		regmap_read(r_s, BERVRDL_S, &tmpl);
+		bit_err = (tmpu << 8) | tmpl;
+		bit_cnt = (1 << 13) * 204;
+
+		if (bit_cnt) {
+			c->post_bit_error.len = 1;
+			c->post_bit_error.stat[0].scale = FE_SCALE_COUNTER;
+			c->post_bit_error.stat[0].uvalue = bit_err;
+			c->post_bit_count.len = 1;
+			c->post_bit_count.stat[0].scale = FE_SCALE_COUNTER;
+			c->post_bit_count.stat[0].uvalue = bit_cnt;
+		}
+	}
+
+	return 0;
+}
+
+static void mn88443x_t_sleep(struct mn88443x_priv *chip)
+{
+	struct regmap *r_t = chip->regmap_t;
+
+	regmap_update_bits(r_t, PWDSET, PWDSET_OFDMPD_MASK,
+			   PWDSET_OFDMPD_DOWN);
+}
+
+static void mn88443x_t_wake(struct mn88443x_priv *chip)
+{
+	struct regmap *r_t = chip->regmap_t;
+
+	regmap_update_bits(r_t, PWDSET, PWDSET_OFDMPD_MASK, 0);
+}
+
+static bool mn88443x_t_is_valid_clk(u32 adckt, u32 if_freq)
+{
+	if (if_freq == DIRECT_IF_57MHZ) {
+		if (adckt >= CLK_DIRECT && adckt <= 21000000)
+			return true;
+		if (adckt >= 25300000 && adckt <= CLK_MAX)
+			return true;
+	} else if (if_freq == DIRECT_IF_44MHZ) {
+		if (adckt >= 25000000 && adckt <= CLK_MAX)
+			return true;
+	} else if (if_freq >= LOW_IF_4MHZ && if_freq < DIRECT_IF_44MHZ) {
+		if (adckt >= CLK_DIRECT && adckt <= CLK_MAX)
+			return true;
+	}
+
+	return false;
+}
+
+static int mn88443x_t_set_freq(struct mn88443x_priv *chip)
+{
+	struct device *dev = &chip->client_s->dev;
+	struct regmap *r_t = chip->regmap_t;
+	s64 adckt, nco, ad_t;
+	u32 m, v;
+
+	/* Clock buffer (but not supported) or XTAL */
+	if (chip->clk_freq >= CLK_LOW && chip->clk_freq < CLK_DIRECT) {
+		chip->use_clkbuf = true;
+		regmap_write(r_t, CLKSET1_T, 0x07);
+
+		adckt = 0;
+	} else {
+		chip->use_clkbuf = false;
+		regmap_write(r_t, CLKSET1_T, 0x00);
+
+		adckt = chip->clk_freq;
+	}
+	if (!mn88443x_t_is_valid_clk(adckt, chip->if_freq)) {
+		dev_err(dev, "Invalid clock, CLK:%d, ADCKT:%lld, IF:%d\n",
+			chip->clk_freq, adckt, chip->if_freq);
+		return -EINVAL;
+	}
+
+	/* Direct IF or Low IF */
+	if (chip->if_freq == DIRECT_IF_57MHZ ||
+	    chip->if_freq == DIRECT_IF_44MHZ)
+		nco = adckt * 2 - chip->if_freq;
+	else
+		nco = -((s64)chip->if_freq);
+	nco = div_s64(nco << 24, adckt);
+	ad_t = div_s64(adckt << 22, S_T_FREQ);
+
+	regmap_write(r_t, NCOFREQU_T, nco >> 16);
+	regmap_write(r_t, NCOFREQM_T, nco >> 8);
+	regmap_write(r_t, NCOFREQL_T, nco);
+	regmap_write(r_t, FADU_T, ad_t >> 16);
+	regmap_write(r_t, FADM_T, ad_t >> 8);
+	regmap_write(r_t, FADL_T, ad_t);
+
+	/* Level of IF */
+	m = ADCSET1_T_REFSEL_MASK;
+	v = ADCSET1_T_REFSEL_1_5V;
+	regmap_update_bits(r_t, ADCSET1_T, m, v);
+
+	/* Polarity of AGC */
+	v = AGCSET2_T_IFPOLINV_INC | AGCSET2_T_RFPOLINV_INC;
+	regmap_update_bits(r_t, AGCSET2_T, v, v);
+
+	/* Lower output level of AGC */
+	regmap_write(r_t, AGCV3_T, 0x00);
+
+	regmap_write(r_t, MDSET_T, 0xfa);
+
+	return 0;
+}
+
+static void mn88443x_t_tune(struct mn88443x_priv *chip,
+			    struct dtv_frontend_properties *c)
+{
+	struct regmap *r_t = chip->regmap_t;
+	u32 m, v;
+
+	m = MDSET_T_MDAUTO_MASK | MDSET_T_FFTS_MASK | MDSET_T_GI_MASK;
+	v = MDSET_T_MDAUTO_AUTO | MDSET_T_FFTS_MODE3 | MDSET_T_GI_1_8;
+	regmap_update_bits(r_t, MDSET_T, m, v);
+
+	regmap_write(r_t, MDASET_T, 0);
+}
+
+static int mn88443x_t_read_status(struct mn88443x_priv *chip,
+				  struct dtv_frontend_properties *c,
+				  enum fe_status *status)
+{
+	struct regmap *r_t = chip->regmap_t;
+	u32 seqrd, st, flg, tmpu, tmpm, tmpl;
+	u64 tmp;
+
+	/* Sync detection */
+	regmap_read(r_t, SSEQRD_T, &seqrd);
+	st = seqrd & SSEQRD_T_SSEQSTRD_MASK;
+
+	*status = 0;
+	if (st >= SSEQRD_T_SSEQSTRD_SYNC)
+		*status |= FE_HAS_VITERBI | FE_HAS_SYNC | FE_HAS_LOCK;
+	if (st >= SSEQRD_T_SSEQSTRD_FRAME_SYNC)
+		*status |= FE_HAS_SIGNAL | FE_HAS_CARRIER;
+
+	/* Signal strength */
+	c->strength.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+
+	if (*status & FE_HAS_SIGNAL) {
+		u32 agc;
+
+		regmap_read(r_t, AGCRDU_T, &tmpu);
+		regmap_read(r_t, AGCRDL_T, &tmpl);
+		agc = (tmpu << 8) | tmpl;
+
+		c->strength.len = 1;
+		c->strength.stat[0].scale = FE_SCALE_RELATIVE;
+		c->strength.stat[0].uvalue = agc;
+	}
+
+	/* C/N rate */
+	c->cnr.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+
+	if (*status & FE_HAS_VITERBI) {
+		u32 cnr;
+
+		regmap_read(r_t, CNRDU_T, &tmpu);
+		regmap_read(r_t, CNRDL_T, &tmpl);
+
+		if (tmpu || tmpl) {
+			/* CNR[dB]: 10 * (log10(65536 / value) + 0.2) */
+			/* intlog10(65536) = 80807124, 0.2 * 2^24 = 3355443 */
+			tmp = (u64)80807124 - intlog10((tmpu << 8) | tmpl)
+				+ 3355443;
+			cnr = div_u64(tmp * 10000, 1 << 24);
+		} else {
+			cnr = 0;
+		}
+
+		c->cnr.len = 1;
+		c->cnr.stat[0].scale = FE_SCALE_DECIBEL;
+		c->cnr.stat[0].uvalue = cnr;
+	}
+
+	/* BER */
+	c->post_bit_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	c->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+
+	regmap_read(r_t, BERFLG_T, &flg);
+
+	if ((*status & FE_HAS_VITERBI) && (flg & BERFLG_T_BERVRDYA)) {
+		u32 bit_err, bit_cnt;
+
+		regmap_read(r_t, BERRDU_T, &tmpu);
+		regmap_read(r_t, BERRDM_T, &tmpm);
+		regmap_read(r_t, BERRDL_T, &tmpl);
+		bit_err = (tmpu << 16) | (tmpm << 8) | tmpl;
+
+		regmap_read(r_t, BERLENRDU_T, &tmpu);
+		regmap_read(r_t, BERLENRDL_T, &tmpl);
+		bit_cnt = ((tmpu << 8) | tmpl) * 203 * 8;
+
+		if (bit_cnt) {
+			c->post_bit_error.len = 1;
+			c->post_bit_error.stat[0].scale = FE_SCALE_COUNTER;
+			c->post_bit_error.stat[0].uvalue = bit_err;
+			c->post_bit_count.len = 1;
+			c->post_bit_count.stat[0].scale = FE_SCALE_COUNTER;
+			c->post_bit_count.stat[0].uvalue = bit_cnt;
+		}
+	}
+
+	return 0;
+}
+
+static int mn88443x_sleep(struct dvb_frontend *fe)
+{
+	struct mn88443x_priv *chip = fe->demodulator_priv;
+
+	mn88443x_s_sleep(chip);
+	mn88443x_t_sleep(chip);
+
+	return 0;
+}
+
+static int mn88443x_set_frontend(struct dvb_frontend *fe)
+{
+	struct mn88443x_priv *chip = fe->demodulator_priv;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+	struct regmap *r_s = chip->regmap_s;
+	struct regmap *r_t = chip->regmap_t;
+	u8 tssel = 0, intsel = 0;
+
+	if (c->delivery_system == SYS_ISDBS) {
+		mn88443x_s_wake(chip);
+		mn88443x_t_sleep(chip);
+
+		tssel = TSSET1_TSASEL_ISDBS;
+		intsel = TSSET3_INTASEL_S;
+	} else if (c->delivery_system == SYS_ISDBT) {
+		mn88443x_s_sleep(chip);
+		mn88443x_t_wake(chip);
+
+		mn88443x_t_set_freq(chip);
+
+		tssel = TSSET1_TSASEL_ISDBT;
+		intsel = TSSET3_INTASEL_T;
+	}
+
+	regmap_update_bits(r_t, TSSET1,
+			   TSSET1_TSASEL_MASK | TSSET1_TSBSEL_MASK,
+			   tssel | TSSET1_TSBSEL_NONE);
+	regmap_write(r_t, TSSET2, 0);
+	regmap_update_bits(r_t, TSSET3,
+			   TSSET3_INTASEL_MASK | TSSET3_INTBSEL_MASK,
+			   intsel | TSSET3_INTBSEL_NONE);
+
+	regmap_write(r_t, DOSET1_T, 0x95);
+	regmap_write(r_s, DOSET1_S, 0x80);
+
+	if (c->delivery_system == SYS_ISDBS)
+		mn88443x_s_tune(chip, c);
+	else if (c->delivery_system == SYS_ISDBT)
+		mn88443x_t_tune(chip, c);
+
+	if (fe->ops.tuner_ops.set_params) {
+		if (fe->ops.i2c_gate_ctrl)
+			fe->ops.i2c_gate_ctrl(fe, 1);
+		fe->ops.tuner_ops.set_params(fe);
+		if (fe->ops.i2c_gate_ctrl)
+			fe->ops.i2c_gate_ctrl(fe, 0);
+	}
+
+	return 0;
+}
+
+static int mn88443x_get_tune_settings(struct dvb_frontend *fe,
+				      struct dvb_frontend_tune_settings *s)
+{
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+
+	s->min_delay_ms = 850;
+
+	if (c->delivery_system == SYS_ISDBS) {
+		s->max_drift = 30000 * 2 + 1;
+		s->step_size = 30000;
+	} else if (c->delivery_system == SYS_ISDBT) {
+		s->max_drift = 142857 * 2 + 1;
+		s->step_size = 142857 * 2;
+	}
+
+	return 0;
+}
+
+static int mn88443x_read_status(struct dvb_frontend *fe, enum fe_status *status)
+{
+	struct mn88443x_priv *chip = fe->demodulator_priv;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+
+	if (c->delivery_system == SYS_ISDBS)
+		return mn88443x_s_read_status(chip, c, status);
+
+	if (c->delivery_system == SYS_ISDBT)
+		return mn88443x_t_read_status(chip, c, status);
+
+	return -EINVAL;
+}
+
+static const struct dvb_frontend_ops mn88443x_ops = {
+	.delsys = { SYS_ISDBS, SYS_ISDBT },
+	.info = {
+		.name = "Socionext MN88443x",
+		.frequency_min_hz =  470 * MHz,
+		.frequency_max_hz = 2071 * MHz,
+		.symbol_rate_min  = 28860000,
+		.symbol_rate_max  = 28860000,
+		.caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_AUTO |
+			FE_CAN_QAM_AUTO | FE_CAN_TRANSMISSION_MODE_AUTO |
+			FE_CAN_GUARD_INTERVAL_AUTO | FE_CAN_HIERARCHY_AUTO,
+	},
+
+	.sleep                   = mn88443x_sleep,
+	.set_frontend            = mn88443x_set_frontend,
+	.get_tune_settings       = mn88443x_get_tune_settings,
+	.read_status             = mn88443x_read_status,
+};
+
+static const struct regmap_config regmap_config = {
+	.reg_bits   = 8,
+	.val_bits   = 8,
+	.cache_type = REGCACHE_NONE,
+};
+
+static int mn88443x_probe(struct i2c_client *client,
+			  const struct i2c_device_id *id)
+{
+	struct mn88443x_config *conf = client->dev.platform_data;
+	struct mn88443x_priv *chip;
+	struct device *dev = &client->dev;
+	int ret;
+
+	chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	if (dev->of_node)
+		chip->spec = of_device_get_match_data(dev);
+	else
+		chip->spec = (struct mn88443x_spec *)id->driver_data;
+	if (!chip->spec)
+		return -EINVAL;
+
+	chip->mclk = devm_clk_get(dev, "mclk");
+	if (IS_ERR(chip->mclk) && !conf) {
+		dev_err(dev, "Failed to request mclk: %ld\n",
+			PTR_ERR(chip->mclk));
+		return PTR_ERR(chip->mclk);
+	}
+
+	ret = of_property_read_u32(dev->of_node, "if-frequency",
+				   &chip->if_freq);
+	if (ret && !conf) {
+		dev_err(dev, "Failed to load IF frequency: %d.\n", ret);
+		return ret;
+	}
+
+	chip->reset_gpio = devm_gpiod_get_optional(dev, "reset",
+						   GPIOD_OUT_HIGH);
+	if (IS_ERR(chip->reset_gpio)) {
+		dev_err(dev, "Failed to request reset_gpio: %ld\n",
+			PTR_ERR(chip->reset_gpio));
+		return PTR_ERR(chip->reset_gpio);
+	}
+
+	if (conf) {
+		chip->mclk = conf->mclk;
+		chip->if_freq = conf->if_freq;
+		chip->reset_gpio = conf->reset_gpio;
+
+		*conf->fe = &chip->fe;
+	}
+
+	chip->client_s = client;
+	chip->regmap_s = devm_regmap_init_i2c(chip->client_s, &regmap_config);
+	if (IS_ERR(chip->regmap_s))
+		return PTR_ERR(chip->regmap_s);
+
+	/*
+	 * Chip has two I2C addresses for each satellite/terrestrial system.
+	 * ISDB-T uses address ISDB-S + 4, so we register a dummy client.
+	 */
+	chip->client_t = i2c_new_dummy(client->adapter, client->addr + 4);
+	if (!chip->client_t)
+		return -ENODEV;
+
+	chip->regmap_t = devm_regmap_init_i2c(chip->client_t, &regmap_config);
+	if (IS_ERR(chip->regmap_t)) {
+		ret = PTR_ERR(chip->regmap_t);
+		goto err_i2c_t;
+	}
+
+	chip->clk_freq = clk_get_rate(chip->mclk);
+
+	memcpy(&chip->fe.ops, &mn88443x_ops, sizeof(mn88443x_ops));
+	chip->fe.demodulator_priv = chip;
+	i2c_set_clientdata(client, chip);
+
+	mn88443x_cmn_power_on(chip);
+	mn88443x_s_sleep(chip);
+	mn88443x_t_sleep(chip);
+
+	return 0;
+
+err_i2c_t:
+	i2c_unregister_device(chip->client_t);
+
+	return ret;
+}
+
+static int mn88443x_remove(struct i2c_client *client)
+{
+	struct mn88443x_priv *chip = i2c_get_clientdata(client);
+
+	mn88443x_cmn_power_off(chip);
+
+	i2c_unregister_device(chip->client_t);
+
+	return 0;
+}
+
+static const struct mn88443x_spec mn88443x_spec_pri = {
+	.primary = true,
+};
+
+static const struct mn88443x_spec mn88443x_spec_sec = {
+	.primary = false,
+};
+
+static const struct of_device_id mn88443x_of_match[] = {
+	{ .compatible = "socionext,mn884433",   .data = &mn88443x_spec_pri, },
+	{ .compatible = "socionext,mn884434-0", .data = &mn88443x_spec_pri, },
+	{ .compatible = "socionext,mn884434-1", .data = &mn88443x_spec_sec, },
+	{}
+};
+MODULE_DEVICE_TABLE(of, mn88443x_of_match);
+
+static const struct i2c_device_id mn88443x_i2c_id[] = {
+	{ "mn884433",   (kernel_ulong_t)&mn88443x_spec_pri },
+	{ "mn884434-0", (kernel_ulong_t)&mn88443x_spec_pri },
+	{ "mn884434-1", (kernel_ulong_t)&mn88443x_spec_sec },
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, mn88443x_i2c_id);
+
+static struct i2c_driver mn88443x_driver = {
+	.driver = {
+		.name = "mn88443x",
+		.of_match_table = of_match_ptr(mn88443x_of_match),
+	},
+	.probe    = mn88443x_probe,
+	.remove   = mn88443x_remove,
+	.id_table = mn88443x_i2c_id,
+};
+
+module_i2c_driver(mn88443x_driver);
+
+MODULE_AUTHOR("Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>");
+MODULE_DESCRIPTION("Socionext MN88443x series demodulator driver.");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/dvb-frontends/mn88443x.h b/drivers/media/dvb-frontends/mn88443x.h
new file mode 100644
index 000000000000..b19aaf6a1ea3
--- /dev/null
+++ b/drivers/media/dvb-frontends/mn88443x.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Socionext MN88443x series demodulator driver for ISDB-S/ISDB-T.
+ *
+ * Copyright (c) 2018 Socionext Inc.
+ */
+
+#ifndef MN88443X_H
+#define MN88443X_H
+
+#include <media/dvb_frontend.h>
+
+/* ISDB-T IF frequency */
+#define DIRECT_IF_57MHZ    57000000
+#define DIRECT_IF_44MHZ    44000000
+#define LOW_IF_4MHZ        4000000
+
+struct mn88443x_config {
+	struct clk *mclk;
+	u32 if_freq;
+	struct gpio_desc *reset_gpio;
+
+	/* Everything after that is returned by the driver. */
+	struct dvb_frontend **fe;
+};
+
+#endif /* MN88443X_H */
diff --git a/drivers/media/dvb-frontends/mt312.c b/drivers/media/dvb-frontends/mt312.c
index e2a3fc521620..aad07adda37d 100644
--- a/drivers/media/dvb-frontends/mt312.c
+++ b/drivers/media/dvb-frontends/mt312.c
@@ -559,8 +559,8 @@ static int mt312_set_frontend(struct dvb_frontend *fe)
 
 	dprintk("%s: Freq %d\n", __func__, p->frequency);
 
-	if ((p->frequency < fe->ops.info.frequency_min)
-	    || (p->frequency > fe->ops.info.frequency_max))
+	if ((p->frequency < fe->ops.info.frequency_min_hz / kHz)
+	    || (p->frequency > fe->ops.info.frequency_max_hz / kHz))
 		return -EINVAL;
 
 	if (((int)p->inversion < INVERSION_OFF)
@@ -755,10 +755,10 @@ static const struct dvb_frontend_ops mt312_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name = "Zarlink ???? DVB-S",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
 		/* FIXME: adjust freq to real used xtal */
-		.frequency_stepsize = (MT312_PLL_CLK / 1000) / 128,
+		.frequency_stepsize_hz = MT312_PLL_CLK / 128,
 		.symbol_rate_min = MT312_SYS_CLK / 128, /* FIXME as above */
 		.symbol_rate_max = MT312_SYS_CLK / 2,
 		.caps =
diff --git a/drivers/media/dvb-frontends/mt352.c b/drivers/media/dvb-frontends/mt352.c
index a440b76444d3..da3e466d50e2 100644
--- a/drivers/media/dvb-frontends/mt352.c
+++ b/drivers/media/dvb-frontends/mt352.c
@@ -567,10 +567,9 @@ static const struct dvb_frontend_ops mt352_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "Zarlink MT352 DVB-T",
-		.frequency_min		= 174000000,
-		.frequency_max		= 862000000,
-		.frequency_stepsize	= 166667,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	= 174 * MHz,
+		.frequency_max_hz	= 862 * MHz,
+		.frequency_stepsize_hz	= 166667,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 |
 			FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 |
 			FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/mxl5xx.c b/drivers/media/dvb-frontends/mxl5xx.c
index 274d8fca0763..295f37d5f10e 100644
--- a/drivers/media/dvb-frontends/mxl5xx.c
+++ b/drivers/media/dvb-frontends/mxl5xx.c
@@ -784,10 +784,8 @@ static struct dvb_frontend_ops mxl_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2, SYS_DSS },
 	.info = {
 		.name			= "MaxLinear MxL5xx DVB-S/S2 tuner-demodulator",
-		.frequency_min		= 300000,
-		.frequency_max		= 2350000,
-		.frequency_stepsize	= 0,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  300 * MHz,
+		.frequency_max_hz	= 2350 * MHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 		.caps			= FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/nxt200x.c b/drivers/media/dvb-frontends/nxt200x.c
index a6cc4952eb74..0961e686ff68 100644
--- a/drivers/media/dvb-frontends/nxt200x.c
+++ b/drivers/media/dvb-frontends/nxt200x.c
@@ -1212,9 +1212,9 @@ static const struct dvb_frontend_ops nxt200x_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name = "Nextwave NXT200X VSB/QAM frontend",
-		.frequency_min =  54000000,
-		.frequency_max = 860000000,
-		.frequency_stepsize = 166666,	/* stepsize is just a guess */
+		.frequency_min_hz =  54 * MHz,
+		.frequency_max_hz = 860 * MHz,
+		.frequency_stepsize_hz = 166666,	/* stepsize is just a guess */
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 			FE_CAN_8VSB | FE_CAN_QAM_64 | FE_CAN_QAM_256
diff --git a/drivers/media/dvb-frontends/nxt6000.c b/drivers/media/dvb-frontends/nxt6000.c
index 109a635d166a..72e447e8ba64 100644
--- a/drivers/media/dvb-frontends/nxt6000.c
+++ b/drivers/media/dvb-frontends/nxt6000.c
@@ -596,9 +596,9 @@ static const struct dvb_frontend_ops nxt6000_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "NxtWave NXT6000 DVB-T",
-		.frequency_min = 0,
-		.frequency_max = 863250000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz = 0,
+		.frequency_max_hz = 863250 * kHz,
+		.frequency_stepsize_hz = 62500,
 		/*.frequency_tolerance = *//* FIXME: 12% of SR */
 		.symbol_rate_min = 0,	/* FIXME */
 		.symbol_rate_max = 9360000,	/* FIXME */
diff --git a/drivers/media/dvb-frontends/or51132.c b/drivers/media/dvb-frontends/or51132.c
index b4c9aadcb552..fc35f37eb3c0 100644
--- a/drivers/media/dvb-frontends/or51132.c
+++ b/drivers/media/dvb-frontends/or51132.c
@@ -583,9 +583,9 @@ static const struct dvb_frontend_ops or51132_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name			= "Oren OR51132 VSB/QAM Frontend",
-		.frequency_min		= 44000000,
-		.frequency_max		= 958000000,
-		.frequency_stepsize	= 166666,
+		.frequency_min_hz	=  44 * MHz,
+		.frequency_max_hz	= 958 * MHz,
+		.frequency_stepsize_hz	= 166666,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 			FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_QAM_AUTO |
diff --git a/drivers/media/dvb-frontends/or51211.c b/drivers/media/dvb-frontends/or51211.c
index b65ba34fd00a..a39bbd8ff1f0 100644
--- a/drivers/media/dvb-frontends/or51211.c
+++ b/drivers/media/dvb-frontends/or51211.c
@@ -530,10 +530,10 @@ struct dvb_frontend* or51211_attach(const struct or51211_config* config,
 static const struct dvb_frontend_ops or51211_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
-		.name               = "Oren OR51211 VSB Frontend",
-		.frequency_min      = 44000000,
-		.frequency_max      = 958000000,
-		.frequency_stepsize = 166666,
+		.name                  = "Oren OR51211 VSB Frontend",
+		.frequency_min_hz      =  44 * MHz,
+		.frequency_max_hz      = 958 * MHz,
+		.frequency_stepsize_hz = 166666,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 			FE_CAN_8VSB
diff --git a/drivers/media/dvb-frontends/rtl2830.c b/drivers/media/dvb-frontends/rtl2830.c
index 7bbfe11d11ed..adc9046d5a90 100644
--- a/drivers/media/dvb-frontends/rtl2830.c
+++ b/drivers/media/dvb-frontends/rtl2830.c
@@ -159,8 +159,8 @@ static int rtl2830_get_tune_settings(struct dvb_frontend *fe,
 				     struct dvb_frontend_tune_settings *s)
 {
 	s->min_delay_ms = 500;
-	s->step_size = fe->ops.info.frequency_stepsize * 2;
-	s->max_drift = (fe->ops.info.frequency_stepsize * 2) + 1;
+	s->step_size = fe->ops.info.frequency_stepsize_hz * 2;
+	s->max_drift = (fe->ops.info.frequency_stepsize_hz * 2) + 1;
 
 	return 0;
 }
diff --git a/drivers/media/dvb-frontends/rtl2832.c b/drivers/media/dvb-frontends/rtl2832.c
index fa3b8169c1a5..2f1f5cbaf03c 100644
--- a/drivers/media/dvb-frontends/rtl2832.c
+++ b/drivers/media/dvb-frontends/rtl2832.c
@@ -408,8 +408,8 @@ static int rtl2832_get_tune_settings(struct dvb_frontend *fe,
 
 	dev_dbg(&client->dev, "\n");
 	s->min_delay_ms = 1000;
-	s->step_size = fe->ops.info.frequency_stepsize * 2;
-	s->max_drift = (fe->ops.info.frequency_stepsize * 2) + 1;
+	s->step_size = fe->ops.info.frequency_stepsize_hz * 2;
+	s->max_drift = (fe->ops.info.frequency_stepsize_hz * 2) + 1;
 	return 0;
 }
 
@@ -841,9 +841,9 @@ static const struct dvb_frontend_ops rtl2832_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "Realtek RTL2832 (DVB-T)",
-		.frequency_min	  = 174000000,
-		.frequency_max	  = 862000000,
-		.frequency_stepsize = 166667,
+		.frequency_min_hz	= 174 * MHz,
+		.frequency_max_hz	= 862 * MHz,
+		.frequency_stepsize_hz	= 166667,
 		.caps = FE_CAN_FEC_1_2 |
 			FE_CAN_FEC_2_3 |
 			FE_CAN_FEC_3_4 |
diff --git a/drivers/media/dvb-frontends/rtl2832_sdr.c b/drivers/media/dvb-frontends/rtl2832_sdr.c
index c6e78d870ccd..d448d9d4879c 100644
--- a/drivers/media/dvb-frontends/rtl2832_sdr.c
+++ b/drivers/media/dvb-frontends/rtl2832_sdr.c
@@ -301,7 +301,7 @@ static int rtl2832_sdr_submit_urbs(struct rtl2832_sdr_dev *dev)
 
 	for (i = 0; i < dev->urbs_initialized; i++) {
 		dev_dbg(&pdev->dev, "submit urb=%d\n", i);
-		ret = usb_submit_urb(dev->urb_list[i], GFP_ATOMIC);
+		ret = usb_submit_urb(dev->urb_list[i], GFP_KERNEL);
 		if (ret) {
 			dev_err(&pdev->dev,
 				"Could not submit urb no. %d - get them all back\n",
@@ -345,7 +345,7 @@ static int rtl2832_sdr_alloc_stream_bufs(struct rtl2832_sdr_dev *dev)
 
 	for (dev->buf_num = 0; dev->buf_num < MAX_BULK_BUFS; dev->buf_num++) {
 		dev->buf_list[dev->buf_num] = usb_alloc_coherent(dev->udev,
-				BULK_BUFFER_SIZE, GFP_ATOMIC,
+				BULK_BUFFER_SIZE, GFP_KERNEL,
 				&dev->dma_addr[dev->buf_num]);
 		if (!dev->buf_list[dev->buf_num]) {
 			dev_dbg(&pdev->dev, "alloc buf=%d failed\n",
@@ -390,7 +390,7 @@ static int rtl2832_sdr_alloc_urbs(struct rtl2832_sdr_dev *dev)
 	/* allocate the URBs */
 	for (i = 0; i < MAX_BULK_BUFS; i++) {
 		dev_dbg(&pdev->dev, "alloc urb=%d\n", i);
-		dev->urb_list[i] = usb_alloc_urb(0, GFP_ATOMIC);
+		dev->urb_list[i] = usb_alloc_urb(0, GFP_KERNEL);
 		if (!dev->urb_list[i]) {
 			for (j = 0; j < i; j++)
 				usb_free_urb(dev->urb_list[j]);
diff --git a/drivers/media/dvb-frontends/s5h1409.c b/drivers/media/dvb-frontends/s5h1409.c
index a23ba8727218..ceeb0c3551ce 100644
--- a/drivers/media/dvb-frontends/s5h1409.c
+++ b/drivers/media/dvb-frontends/s5h1409.c
@@ -999,9 +999,9 @@ static const struct dvb_frontend_ops s5h1409_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name			= "Samsung S5H1409 QAM/8VSB Frontend",
-		.frequency_min		= 54000000,
-		.frequency_max		= 858000000,
-		.frequency_stepsize	= 62500,
+		.frequency_min_hz	=  54 * MHz,
+		.frequency_max_hz	= 858 * MHz,
+		.frequency_stepsize_hz	= 62500,
 		.caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
 	},
 
diff --git a/drivers/media/dvb-frontends/s5h1411.c b/drivers/media/dvb-frontends/s5h1411.c
index af5962807f2c..98aeed1d2284 100644
--- a/drivers/media/dvb-frontends/s5h1411.c
+++ b/drivers/media/dvb-frontends/s5h1411.c
@@ -918,9 +918,9 @@ static const struct dvb_frontend_ops s5h1411_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name			= "Samsung S5H1411 QAM/8VSB Frontend",
-		.frequency_min		= 54000000,
-		.frequency_max		= 858000000,
-		.frequency_stepsize	= 62500,
+		.frequency_min_hz	=  54 * MHz,
+		.frequency_max_hz	= 858 * MHz,
+		.frequency_stepsize_hz	= 62500,
 		.caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
 	},
 
diff --git a/drivers/media/dvb-frontends/s5h1420.c b/drivers/media/dvb-frontends/s5h1420.c
index 8b2222530227..a65cdf8e8cd9 100644
--- a/drivers/media/dvb-frontends/s5h1420.c
+++ b/drivers/media/dvb-frontends/s5h1420.c
@@ -934,10 +934,10 @@ static const struct dvb_frontend_ops s5h1420_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name     = "Samsung S5H1420/PnpNetwork PN1010 DVB-S",
-		.frequency_min    = 950000,
-		.frequency_max    = 2150000,
-		.frequency_stepsize = 125,     /* kHz for QPSK frontends */
-		.frequency_tolerance  = 29500,
+		.frequency_min_hz    =  950 * MHz,
+		.frequency_max_hz    = 2150 * MHz,
+		.frequency_stepsize_hz = 125 * kHz,
+		.frequency_tolerance_hz  = 29500 * kHz,
 		.symbol_rate_min  = 1000000,
 		.symbol_rate_max  = 45000000,
 		/*  .symbol_rate_tolerance  = ???,*/
diff --git a/drivers/media/dvb-frontends/s5h1432.c b/drivers/media/dvb-frontends/s5h1432.c
index 740a60df0455..4dc3febc0e12 100644
--- a/drivers/media/dvb-frontends/s5h1432.c
+++ b/drivers/media/dvb-frontends/s5h1432.c
@@ -370,9 +370,9 @@ static const struct dvb_frontend_ops s5h1432_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		 .name = "Samsung s5h1432 DVB-T Frontend",
-		 .frequency_min = 177000000,
-		 .frequency_max = 858000000,
-		 .frequency_stepsize = 166666,
+		 .frequency_min_hz = 177 * MHz,
+		 .frequency_max_hz = 858 * MHz,
+		 .frequency_stepsize_hz = 166666,
 		 .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		 FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 		 FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_64 | FE_CAN_QAM_AUTO |
diff --git a/drivers/media/dvb-frontends/s921.c b/drivers/media/dvb-frontends/s921.c
index 6c9015236655..79276871112a 100644
--- a/drivers/media/dvb-frontends/s921.c
+++ b/drivers/media/dvb-frontends/s921.c
@@ -510,15 +510,14 @@ static const struct dvb_frontend_ops s921_ops = {
 	/* Use dib8000 values per default */
 	.info = {
 		.name = "Sharp S921",
-		.frequency_min = 470000000,
+		.frequency_min_hz = 470 * MHz,
 		/*
 		 * Max should be 770MHz instead, according with Sharp docs,
 		 * but Leadership doc says it works up to 806 MHz. This is
 		 * required to get channel 69, used in Brazil
 		 */
-		.frequency_max = 806000000,
-		.frequency_tolerance = 0,
-		 .caps = FE_CAN_INVERSION_AUTO |
+		.frequency_max_hz = 806 * MHz,
+		.caps =  FE_CAN_INVERSION_AUTO |
 			 FE_CAN_FEC_1_2  | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			 FE_CAN_FEC_5_6  | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 			 FE_CAN_QPSK     | FE_CAN_QAM_16 | FE_CAN_QAM_64 |
diff --git a/drivers/media/dvb-frontends/si2165.c b/drivers/media/dvb-frontends/si2165.c
index 2dd336f95cbf..feacd8da421d 100644
--- a/drivers/media/dvb-frontends/si2165.c
+++ b/drivers/media/dvb-frontends/si2165.c
@@ -1120,7 +1120,7 @@ static const struct dvb_frontend_ops si2165_ops = {
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 7200000,
 		/* For DVB-T */
-		.frequency_stepsize = 166667,
+		.frequency_stepsize_hz = 166667,
 		.caps = FE_CAN_FEC_1_2 |
 			FE_CAN_FEC_2_3 |
 			FE_CAN_FEC_3_4 |
diff --git a/drivers/media/dvb-frontends/si21xx.c b/drivers/media/dvb-frontends/si21xx.c
index 9b32a1b3205e..8546a236d452 100644
--- a/drivers/media/dvb-frontends/si21xx.c
+++ b/drivers/media/dvb-frontends/si21xx.c
@@ -870,10 +870,9 @@ static const struct dvb_frontend_ops si21xx_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "SL SI21XX DVB-S",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 125,	 /* kHz for QPSK frontends */
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
+		.frequency_stepsize_hz	=  125 * kHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 		.symbol_rate_tolerance	= 500,	/* ppm */
diff --git a/drivers/media/dvb-frontends/sp8870.c b/drivers/media/dvb-frontends/sp8870.c
index 1d57a20093fc..8d31cf3f4f07 100644
--- a/drivers/media/dvb-frontends/sp8870.c
+++ b/drivers/media/dvb-frontends/sp8870.c
@@ -584,9 +584,9 @@ static const struct dvb_frontend_ops sp8870_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "Spase SP8870 DVB-T",
-		.frequency_min		= 470000000,
-		.frequency_max		= 860000000,
-		.frequency_stepsize	= 166666,
+		.frequency_min_hz	= 470 * MHz,
+		.frequency_max_hz	= 860 * MHz,
+		.frequency_stepsize_hz	= 166666,
 		.caps			= FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 |
 					  FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 |
 					  FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/sp887x.c b/drivers/media/dvb-frontends/sp887x.c
index 57a0d0ae2b48..c02f50995df4 100644
--- a/drivers/media/dvb-frontends/sp887x.c
+++ b/drivers/media/dvb-frontends/sp887x.c
@@ -594,9 +594,9 @@ static const struct dvb_frontend_ops sp887x_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "Spase SP887x DVB-T",
-		.frequency_min =  50500000,
-		.frequency_max = 858000000,
-		.frequency_stepsize = 166666,
+		.frequency_min_hz =  50500 * kHz,
+		.frequency_max_hz = 858000 * kHz,
+		.frequency_stepsize_hz = 166666,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 			FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_64 |
diff --git a/drivers/media/dvb-frontends/stb0899_drv.c b/drivers/media/dvb-frontends/stb0899_drv.c
index 3c654ae16e78..874e9c9125d6 100644
--- a/drivers/media/dvb-frontends/stb0899_drv.c
+++ b/drivers/media/dvb-frontends/stb0899_drv.c
@@ -1584,10 +1584,8 @@ static const struct dvb_frontend_ops stb0899_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2, SYS_DSS },
 	.info = {
 		.name			= "STB0899 Multistandard",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 0,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
 		.symbol_rate_min	=  5000000,
 		.symbol_rate_max	= 45000000,
 
diff --git a/drivers/media/dvb-frontends/stb6000.c b/drivers/media/dvb-frontends/stb6000.c
index 69c03892f2da..786b9eccde00 100644
--- a/drivers/media/dvb-frontends/stb6000.c
+++ b/drivers/media/dvb-frontends/stb6000.c
@@ -188,8 +188,8 @@ static int stb6000_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 static const struct dvb_tuner_ops stb6000_tuner_ops = {
 	.info = {
 		.name = "ST STB6000",
-		.frequency_min = 950000,
-		.frequency_max = 2150000
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz
 	},
 	.release = stb6000_release,
 	.sleep = stb6000_sleep,
diff --git a/drivers/media/dvb-frontends/stb6100.c b/drivers/media/dvb-frontends/stb6100.c
index 3a851f524b16..30ac584dfab3 100644
--- a/drivers/media/dvb-frontends/stb6100.c
+++ b/drivers/media/dvb-frontends/stb6100.c
@@ -527,9 +527,8 @@ static int stb6100_set_params(struct dvb_frontend *fe)
 static const struct dvb_tuner_ops stb6100_ops = {
 	.info = {
 		.name			= "STB6100 Silicon Tuner",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_step		= 0,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
 	},
 
 	.init		= stb6100_init,
diff --git a/drivers/media/dvb-frontends/stv0288.c b/drivers/media/dvb-frontends/stv0288.c
index f947ed947aae..c9a9fa4e2c1b 100644
--- a/drivers/media/dvb-frontends/stv0288.c
+++ b/drivers/media/dvb-frontends/stv0288.c
@@ -533,10 +533,9 @@ static const struct dvb_frontend_ops stv0288_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "ST STV0288 DVB-S",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 1000,	 /* kHz for QPSK frontends */
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
+		.frequency_stepsize_hz	=    1 * MHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 		.symbol_rate_tolerance	= 500,	/* ppm */
diff --git a/drivers/media/dvb-frontends/stv0297.c b/drivers/media/dvb-frontends/stv0297.c
index b823c04e24d3..9a9915f71483 100644
--- a/drivers/media/dvb-frontends/stv0297.c
+++ b/drivers/media/dvb-frontends/stv0297.c
@@ -694,9 +694,9 @@ static const struct dvb_frontend_ops stv0297_ops = {
 	.delsys = { SYS_DVBC_ANNEX_A },
 	.info = {
 		 .name = "ST STV0297 DVB-C",
-		 .frequency_min = 47000000,
-		 .frequency_max = 862000000,
-		 .frequency_stepsize = 62500,
+		 .frequency_min_hz = 470 * MHz,
+		 .frequency_max_hz = 862 * MHz,
+		 .frequency_stepsize_hz = 62500,
 		 .symbol_rate_min = 870000,
 		 .symbol_rate_max = 11700000,
 		 .caps = FE_CAN_QAM_16 | FE_CAN_QAM_32 | FE_CAN_QAM_64 |
diff --git a/drivers/media/dvb-frontends/stv0299.c b/drivers/media/dvb-frontends/stv0299.c
index 633b90e6fe86..4f466394a16c 100644
--- a/drivers/media/dvb-frontends/stv0299.c
+++ b/drivers/media/dvb-frontends/stv0299.c
@@ -717,10 +717,9 @@ static const struct dvb_frontend_ops stv0299_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "ST STV0299 DVB-S",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 125,	 /* kHz for QPSK frontends */
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
+		.frequency_stepsize_hz	=  125 * kHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 		.symbol_rate_tolerance	= 500,	/* ppm */
diff --git a/drivers/media/dvb-frontends/stv0367.c b/drivers/media/dvb-frontends/stv0367.c
index 5435c908e298..5b91e740e135 100644
--- a/drivers/media/dvb-frontends/stv0367.c
+++ b/drivers/media/dvb-frontends/stv0367.c
@@ -1693,10 +1693,9 @@ static const struct dvb_frontend_ops stv0367ter_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "ST STV0367 DVB-T",
-		.frequency_min		= 47000000,
-		.frequency_max		= 862000000,
-		.frequency_stepsize	= 15625,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  47 * MHz,
+		.frequency_max_hz	= 862 * MHz,
+		.frequency_stepsize_hz	= 15625,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 |
 			FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 |
 			FE_CAN_FEC_AUTO |
@@ -2867,9 +2866,9 @@ static const struct dvb_frontend_ops stv0367cab_ops = {
 	.delsys = { SYS_DVBC_ANNEX_A },
 	.info = {
 		.name = "ST STV0367 DVB-C",
-		.frequency_min = 47000000,
-		.frequency_max = 862000000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz =  47 * MHz,
+		.frequency_max_hz = 862 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.symbol_rate_min = 870000,
 		.symbol_rate_max = 11700000,
 		.caps = 0x400 |/* FE_CAN_QAM_4 */
@@ -3273,10 +3272,9 @@ static const struct dvb_frontend_ops stv0367ddb_ops = {
 	.delsys = { SYS_DVBC_ANNEX_A, SYS_DVBT },
 	.info = {
 		.name			= "ST STV0367 DDB DVB-C/T",
-		.frequency_min		= 47000000,
-		.frequency_max		= 865000000,
-		.frequency_stepsize	= 166667,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  47 * MHz,
+		.frequency_max_hz	= 865 * MHz,
+		.frequency_stepsize_hz	= 166667,
 		.symbol_rate_min	= 870000,
 		.symbol_rate_max	= 11700000,
 		.caps = /* DVB-C */
diff --git a/drivers/media/dvb-frontends/stv0900_core.c b/drivers/media/dvb-frontends/stv0900_core.c
index 72f17b97ca04..254618a06140 100644
--- a/drivers/media/dvb-frontends/stv0900_core.c
+++ b/drivers/media/dvb-frontends/stv0900_core.c
@@ -1875,10 +1875,9 @@ static const struct dvb_frontend_ops stv0900_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2, SYS_DSS },
 	.info = {
 		.name			= "STV0900 frontend",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 125,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
+		.frequency_stepsize_hz	=  125 * kHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 		.symbol_rate_tolerance	= 500,
diff --git a/drivers/media/dvb-frontends/stv090x.c b/drivers/media/dvb-frontends/stv090x.c
index 9133f65d4623..a0622bb71803 100644
--- a/drivers/media/dvb-frontends/stv090x.c
+++ b/drivers/media/dvb-frontends/stv090x.c
@@ -4905,10 +4905,8 @@ static const struct dvb_frontend_ops stv090x_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2, SYS_DSS },
 	.info = {
 		.name			= "STV090x Multistandard",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 0,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 		.caps			= FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/stv0910.c b/drivers/media/dvb-frontends/stv0910.c
index 41444fa1c0bb..4c86073f1a8d 100644
--- a/drivers/media/dvb-frontends/stv0910.c
+++ b/drivers/media/dvb-frontends/stv0910.c
@@ -682,8 +682,8 @@ static int get_bit_error_rate_s(struct stv *state, u32 *bernumerator,
 		return -EINVAL;
 
 	if ((regs[0] & 0x80) == 0) {
-		state->last_berdenominator = 1 << ((state->berscale * 2) +
-						  10 + 3);
+		state->last_berdenominator = 1ULL << ((state->berscale * 2) +
+						     10 + 3);
 		state->last_bernumerator = ((u32)(regs[0] & 0x7F) << 16) |
 			((u32)regs[1] << 8) | regs[2];
 		if (state->last_bernumerator < 256 && state->berscale < 6) {
@@ -1724,10 +1724,8 @@ static const struct dvb_frontend_ops stv0910_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2, SYS_DSS },
 	.info = {
 		.name			= "ST STV0910",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 0,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
 		.symbol_rate_min	= 100000,
 		.symbol_rate_max	= 70000000,
 		.caps			= FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/stv6110.c b/drivers/media/dvb-frontends/stv6110.c
index 6aad0efa3174..7db9a5bceccc 100644
--- a/drivers/media/dvb-frontends/stv6110.c
+++ b/drivers/media/dvb-frontends/stv6110.c
@@ -371,9 +371,9 @@ static int stv6110_get_bandwidth(struct dvb_frontend *fe, u32 *bandwidth)
 static const struct dvb_tuner_ops stv6110_tuner_ops = {
 	.info = {
 		.name = "ST STV6110",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_step = 1000,
+		.frequency_min_hz  =  950 * MHz,
+		.frequency_max_hz  = 2150 * MHz,
+		.frequency_step_hz =    1 * MHz,
 	},
 	.init = stv6110_init,
 	.release = stv6110_release,
diff --git a/drivers/media/dvb-frontends/stv6110x.c b/drivers/media/dvb-frontends/stv6110x.c
index d8950028d021..82c002d3833a 100644
--- a/drivers/media/dvb-frontends/stv6110x.c
+++ b/drivers/media/dvb-frontends/stv6110x.c
@@ -347,10 +347,9 @@ static void stv6110x_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops stv6110x_ops = {
 	.info = {
-		.name		= "STV6110(A) Silicon Tuner",
-		.frequency_min	=  950000,
-		.frequency_max	= 2150000,
-		.frequency_step	= 0,
+		.name		  = "STV6110(A) Silicon Tuner",
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
 	},
 	.release		= stv6110x_release
 };
diff --git a/drivers/media/dvb-frontends/stv6111.c b/drivers/media/dvb-frontends/stv6111.c
index 9b715b6fe152..0cf460111acb 100644
--- a/drivers/media/dvb-frontends/stv6111.c
+++ b/drivers/media/dvb-frontends/stv6111.c
@@ -646,9 +646,8 @@ static int get_rf_strength(struct dvb_frontend *fe, u16 *st)
 static const struct dvb_tuner_ops tuner_ops = {
 	.info = {
 		.name		= "ST STV6111",
-		.frequency_min	= 950000,
-		.frequency_max	= 2150000,
-		.frequency_step	= 0
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
 	},
 	.set_params		= set_params,
 	.release		= release,
diff --git a/drivers/media/dvb-frontends/tc90522.c b/drivers/media/dvb-frontends/tc90522.c
index 7abf6b0916ed..2ad81a438d6a 100644
--- a/drivers/media/dvb-frontends/tc90522.c
+++ b/drivers/media/dvb-frontends/tc90522.c
@@ -714,8 +714,8 @@ static const struct dvb_frontend_ops tc90522_ops_sat = {
 	.delsys = { SYS_ISDBS },
 	.info = {
 		.name = "Toshiba TC90522 ISDB-S module",
-		.frequency_min =  950000,
-		.frequency_max = 2150000,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
 		.caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_AUTO |
 			FE_CAN_QAM_AUTO | FE_CAN_TRANSMISSION_MODE_AUTO |
 			FE_CAN_GUARD_INTERVAL_AUTO | FE_CAN_HIERARCHY_AUTO,
@@ -734,9 +734,9 @@ static const struct dvb_frontend_ops tc90522_ops_ter = {
 	.delsys = { SYS_ISDBT },
 	.info = {
 		.name = "Toshiba TC90522 ISDB-T module",
-		.frequency_min = 470000000,
-		.frequency_max = 770000000,
-		.frequency_stepsize = 142857,
+		.frequency_min_hz = 470 * MHz,
+		.frequency_max_hz = 770 * MHz,
+		.frequency_stepsize_hz = 142857,
 		.caps = FE_CAN_INVERSION_AUTO |
 			FE_CAN_FEC_1_2  | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6  | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/tda10021.c b/drivers/media/dvb-frontends/tda10021.c
index 4f588ebde39d..5cd885d4ea04 100644
--- a/drivers/media/dvb-frontends/tda10021.c
+++ b/drivers/media/dvb-frontends/tda10021.c
@@ -487,11 +487,11 @@ static const struct dvb_frontend_ops tda10021_ops = {
 	.delsys = { SYS_DVBC_ANNEX_A, SYS_DVBC_ANNEX_C },
 	.info = {
 		.name = "Philips TDA10021 DVB-C",
-		.frequency_stepsize = 62500,
-		.frequency_min = 47000000,
-		.frequency_max = 862000000,
-		.symbol_rate_min = (XIN/2)/64,     /* SACLK/64 == (XIN/2)/64 */
-		.symbol_rate_max = (XIN/2)/4,      /* SACLK/4 */
+		.frequency_min_hz =  47 * MHz,
+		.frequency_max_hz = 862 * MHz,
+		.frequency_stepsize_hz = 62500,
+		.symbol_rate_min = (XIN / 2) / 64,     /* SACLK/64 == (XIN/2)/64 */
+		.symbol_rate_max = (XIN / 2) / 4,      /* SACLK/4 */
 	#if 0
 		.frequency_tolerance = ???,
 		.symbol_rate_tolerance = ???,  /* ppm */  /* == 8% (spec p. 5) */
diff --git a/drivers/media/dvb-frontends/tda10023.c b/drivers/media/dvb-frontends/tda10023.c
index 6c84916234e3..0a9a54563ebe 100644
--- a/drivers/media/dvb-frontends/tda10023.c
+++ b/drivers/media/dvb-frontends/tda10023.c
@@ -575,9 +575,9 @@ static const struct dvb_frontend_ops tda10023_ops = {
 	.delsys = { SYS_DVBC_ANNEX_A, SYS_DVBC_ANNEX_C },
 	.info = {
 		.name = "Philips TDA10023 DVB-C",
-		.frequency_stepsize = 62500,
-		.frequency_min =  47000000,
-		.frequency_max = 862000000,
+		.frequency_min_hz =  47 * MHz,
+		.frequency_max_hz = 862 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.symbol_rate_min = 0,  /* set in tda10023_attach */
 		.symbol_rate_max = 0,  /* set in tda10023_attach */
 		.caps = 0x400 | //FE_CAN_QAM_4
diff --git a/drivers/media/dvb-frontends/tda10048.c b/drivers/media/dvb-frontends/tda10048.c
index de82a2558e15..c01d60a88af2 100644
--- a/drivers/media/dvb-frontends/tda10048.c
+++ b/drivers/media/dvb-frontends/tda10048.c
@@ -1156,9 +1156,9 @@ static const struct dvb_frontend_ops tda10048_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "NXP TDA10048HN DVB-T",
-		.frequency_min		= 177000000,
-		.frequency_max		= 858000000,
-		.frequency_stepsize	= 166666,
+		.frequency_min_hz	= 177 * MHz,
+		.frequency_max_hz	= 858 * MHz,
+		.frequency_stepsize_hz	= 166666,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 		FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_64 | FE_CAN_QAM_AUTO |
diff --git a/drivers/media/dvb-frontends/tda1004x.c b/drivers/media/dvb-frontends/tda1004x.c
index 7dcfb4a4b2d0..d402e4b722ca 100644
--- a/drivers/media/dvb-frontends/tda1004x.c
+++ b/drivers/media/dvb-frontends/tda1004x.c
@@ -1249,9 +1249,9 @@ static const struct dvb_frontend_ops tda10045_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "Philips TDA10045H DVB-T",
-		.frequency_min = 51000000,
-		.frequency_max = 858000000,
-		.frequency_stepsize = 166667,
+		.frequency_min_hz =  51 * MHz,
+		.frequency_max_hz = 858 * MHz,
+		.frequency_stepsize_hz = 166667,
 		.caps =
 		    FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		    FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
@@ -1319,9 +1319,9 @@ static const struct dvb_frontend_ops tda10046_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "Philips TDA10046H DVB-T",
-		.frequency_min = 51000000,
-		.frequency_max = 858000000,
-		.frequency_stepsize = 166667,
+		.frequency_min_hz =  51 * MHz,
+		.frequency_max_hz = 858 * MHz,
+		.frequency_stepsize_hz = 166667,
 		.caps =
 		    FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		    FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/tda10071.c b/drivers/media/dvb-frontends/tda10071.c
index 1ed67c08e699..097c42d3f8c2 100644
--- a/drivers/media/dvb-frontends/tda10071.c
+++ b/drivers/media/dvb-frontends/tda10071.c
@@ -681,8 +681,8 @@ static int tda10071_set_frontend(struct dvb_frontend *fe)
 	cmd.args[5] = (c->frequency >>  0) & 0xff;
 	cmd.args[6] = ((c->symbol_rate / 1000) >> 8) & 0xff;
 	cmd.args[7] = ((c->symbol_rate / 1000) >> 0) & 0xff;
-	cmd.args[8] = (tda10071_ops.info.frequency_tolerance >> 8) & 0xff;
-	cmd.args[9] = (tda10071_ops.info.frequency_tolerance >> 0) & 0xff;
+	cmd.args[8] = ((tda10071_ops.info.frequency_tolerance_hz / 1000) >> 8) & 0xff;
+	cmd.args[9] = ((tda10071_ops.info.frequency_tolerance_hz / 1000) >> 0) & 0xff;
 	cmd.args[10] = rolloff;
 	cmd.args[11] = inversion;
 	cmd.args[12] = pilot;
@@ -1106,9 +1106,9 @@ static const struct dvb_frontend_ops tda10071_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2 },
 	.info = {
 		.name = "NXP TDA10071",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_tolerance = 5000,
+		.frequency_min_hz    =  950 * MHz,
+		.frequency_max_hz    = 2150 * MHz,
+		.frequency_tolerance_hz = 5 * MHz,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/tda10086.c b/drivers/media/dvb-frontends/tda10086.c
index 1a95c521e97f..8323e4e53d66 100644
--- a/drivers/media/dvb-frontends/tda10086.c
+++ b/drivers/media/dvb-frontends/tda10086.c
@@ -710,9 +710,9 @@ static const struct dvb_frontend_ops tda10086_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name     = "Philips TDA10086 DVB-S",
-		.frequency_min    = 950000,
-		.frequency_max    = 2150000,
-		.frequency_stepsize = 125,     /* kHz for QPSK frontends */
+		.frequency_min_hz      =  950 * MHz,
+		.frequency_max_hz      = 2150 * MHz,
+		.frequency_stepsize_hz =  125 * kHz,
 		.symbol_rate_min  = 1000000,
 		.symbol_rate_max  = 45000000,
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/tda18271c2dd.c b/drivers/media/dvb-frontends/tda18271c2dd.c
index 2e1d36ae943b..5ce58612315d 100644
--- a/drivers/media/dvb-frontends/tda18271c2dd.c
+++ b/drivers/media/dvb-frontends/tda18271c2dd.c
@@ -1154,6 +1154,7 @@ static int set_params(struct dvb_frontend *fe)
 		default:
 			return -EINVAL;
 		}
+		break;
 	case SYS_DVBC_ANNEX_A:
 	case SYS_DVBC_ANNEX_C:
 		if (bw <= 6000000)
@@ -1214,9 +1215,9 @@ static int get_bandwidth(struct dvb_frontend *fe, u32 *bandwidth)
 static const struct dvb_tuner_ops tuner_ops = {
 	.info = {
 		.name = "NXP TDA18271C2D",
-		.frequency_min  =  47125000,
-		.frequency_max  = 865000000,
-		.frequency_step =     62500
+		.frequency_min_hz  =  47125 * kHz,
+		.frequency_max_hz  =    865 * MHz,
+		.frequency_step_hz =  62500
 	},
 	.init              = init,
 	.sleep             = sleep,
diff --git a/drivers/media/dvb-frontends/tda665x.c b/drivers/media/dvb-frontends/tda665x.c
index 3ef7140ed7f3..8766c9ff6680 100644
--- a/drivers/media/dvb-frontends/tda665x.c
+++ b/drivers/media/dvb-frontends/tda665x.c
@@ -231,9 +231,9 @@ struct dvb_frontend *tda665x_attach(struct dvb_frontend *fe,
 	info			 = &fe->ops.tuner_ops.info;
 
 	memcpy(info->name, config->name, sizeof(config->name));
-	info->frequency_min	= config->frequency_min;
-	info->frequency_max	= config->frequency_max;
-	info->frequency_step	= config->frequency_offst;
+	info->frequency_min_hz	= config->frequency_min;
+	info->frequency_max_hz	= config->frequency_max;
+	info->frequency_step_hz	= config->frequency_offst;
 
 	printk(KERN_DEBUG "%s: Attaching TDA665x (%s) tuner\n", __func__, info->name);
 
diff --git a/drivers/media/dvb-frontends/tda8083.c b/drivers/media/dvb-frontends/tda8083.c
index 29b4f64c030c..53b26060db7e 100644
--- a/drivers/media/dvb-frontends/tda8083.c
+++ b/drivers/media/dvb-frontends/tda8083.c
@@ -453,10 +453,9 @@ static const struct dvb_frontend_ops tda8083_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "Philips TDA8083 DVB-S",
-		.frequency_min		= 920000,     /* TDA8060 */
-		.frequency_max		= 2200000,    /* TDA8060 */
-		.frequency_stepsize	= 125,   /* kHz for QPSK frontends */
-	/*      .frequency_tolerance	= ???,*/
+		.frequency_min_hz	=  920 * MHz,     /* TDA8060 */
+		.frequency_max_hz	= 2200 * MHz,    /* TDA8060 */
+		.frequency_stepsize_hz	=  125 * kHz,
 		.symbol_rate_min	= 12000000,
 		.symbol_rate_max	= 30000000,
 	/*      .symbol_rate_tolerance	= ???,*/
diff --git a/drivers/media/dvb-frontends/tda8261.c b/drivers/media/dvb-frontends/tda8261.c
index f72a54e7eb23..500f50b81b66 100644
--- a/drivers/media/dvb-frontends/tda8261.c
+++ b/drivers/media/dvb-frontends/tda8261.c
@@ -163,10 +163,9 @@ static void tda8261_release(struct dvb_frontend *fe)
 static const struct dvb_tuner_ops tda8261_ops = {
 
 	.info = {
-		.name		= "TDA8261",
-		.frequency_min	=  950000,
-		.frequency_max	= 2150000,
-		.frequency_step = 0
+		.name		   = "TDA8261",
+		.frequency_min_hz  =  950 * MHz,
+		.frequency_max_hz  = 2150 * MHz,
 	},
 
 	.set_params	= tda8261_set_params,
@@ -190,7 +189,7 @@ struct dvb_frontend *tda8261_attach(struct dvb_frontend *fe,
 	fe->tuner_priv		= state;
 	fe->ops.tuner_ops	= tda8261_ops;
 
-	fe->ops.tuner_ops.info.frequency_step = div_tab[config->step_size];
+	fe->ops.tuner_ops.info.frequency_step_hz = div_tab[config->step_size] * kHz;
 
 	pr_info("%s: Attaching TDA8261 8PSK/QPSK tuner\n", __func__);
 
diff --git a/drivers/media/dvb-frontends/tda826x.c b/drivers/media/dvb-frontends/tda826x.c
index da427b4c2aaa..100da5d5fdc5 100644
--- a/drivers/media/dvb-frontends/tda826x.c
+++ b/drivers/media/dvb-frontends/tda826x.c
@@ -131,8 +131,8 @@ static int tda826x_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 static const struct dvb_tuner_ops tda826x_tuner_ops = {
 	.info = {
 		.name = "Philips TDA826X",
-		.frequency_min = 950000,
-		.frequency_max = 2175000
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2175 * MHz
 	},
 	.release = tda826x_release,
 	.sleep = tda826x_sleep,
diff --git a/drivers/media/dvb-frontends/ts2020.c b/drivers/media/dvb-frontends/ts2020.c
index c55882a8da06..3e3e40878633 100644
--- a/drivers/media/dvb-frontends/ts2020.c
+++ b/drivers/media/dvb-frontends/ts2020.c
@@ -498,8 +498,8 @@ static int ts2020_read_signal_strength(struct dvb_frontend *fe,
 static const struct dvb_tuner_ops ts2020_tuner_ops = {
 	.info = {
 		.name = "TS2020",
-		.frequency_min = 950000,
-		.frequency_max = 2150000
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz
 	},
 	.init = ts2020_init,
 	.release = ts2020_release,
diff --git a/drivers/media/dvb-frontends/tua6100.c b/drivers/media/dvb-frontends/tua6100.c
index 1d41abd47f04..b233b7be0b84 100644
--- a/drivers/media/dvb-frontends/tua6100.c
+++ b/drivers/media/dvb-frontends/tua6100.c
@@ -155,9 +155,9 @@ static int tua6100_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 static const struct dvb_tuner_ops tua6100_tuner_ops = {
 	.info = {
 		.name = "Infineon TUA6100",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_step = 1000,
+		.frequency_min_hz  =  950 * MHz,
+		.frequency_max_hz  = 2150 * MHz,
+		.frequency_step_hz =    1 * MHz,
 	},
 	.release = tua6100_release,
 	.sleep = tua6100_sleep,
diff --git a/drivers/media/dvb-frontends/ves1820.c b/drivers/media/dvb-frontends/ves1820.c
index 17600989f121..eb1249d81310 100644
--- a/drivers/media/dvb-frontends/ves1820.c
+++ b/drivers/media/dvb-frontends/ves1820.c
@@ -412,9 +412,9 @@ static const struct dvb_frontend_ops ves1820_ops = {
 	.delsys = { SYS_DVBC_ANNEX_A },
 	.info = {
 		.name = "VLSI VES1820 DVB-C",
-		.frequency_stepsize = 62500,
-		.frequency_min = 47000000,
-		.frequency_max = 862000000,
+		.frequency_min_hz =  47 * MHz,
+		.frequency_max_hz = 862 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.caps = FE_CAN_QAM_16 |
 			FE_CAN_QAM_32 |
 			FE_CAN_QAM_64 |
diff --git a/drivers/media/dvb-frontends/ves1x93.c b/drivers/media/dvb-frontends/ves1x93.c
index 0c7b3286b04d..ddc5bfd84cd5 100644
--- a/drivers/media/dvb-frontends/ves1x93.c
+++ b/drivers/media/dvb-frontends/ves1x93.c
@@ -516,10 +516,10 @@ static const struct dvb_frontend_ops ves1x93_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "VLSI VES1x93 DVB-S",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 125,		 /* kHz for QPSK frontends */
-		.frequency_tolerance	= 29500,
+		.frequency_min_hz	=   950 * MHz,
+		.frequency_max_hz	=  2150 * MHz,
+		.frequency_stepsize_hz	=   125 * kHz,
+		.frequency_tolerance_hz	= 29500 * kHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 	/*	.symbol_rate_tolerance	=	???,*/
diff --git a/drivers/media/dvb-frontends/zl10036.c b/drivers/media/dvb-frontends/zl10036.c
index 89dd65ae88ad..f1c92338015d 100644
--- a/drivers/media/dvb-frontends/zl10036.c
+++ b/drivers/media/dvb-frontends/zl10036.c
@@ -311,8 +311,8 @@ static int zl10036_set_params(struct dvb_frontend *fe)
 
 	/* ensure correct values
 	 * maybe redundant as core already checks this */
-	if ((frequency < fe->ops.info.frequency_min)
-	||  (frequency > fe->ops.info.frequency_max))
+	if ((frequency < fe->ops.info.frequency_min_hz / kHz)
+	||  (frequency > fe->ops.info.frequency_max_hz / kHz))
 		return -EINVAL;
 
 	/*
@@ -443,8 +443,8 @@ static int zl10036_init(struct dvb_frontend *fe)
 static const struct dvb_tuner_ops zl10036_tuner_ops = {
 	.info = {
 		.name = "Zarlink ZL10036",
-		.frequency_min = 950000,
-		.frequency_max = 2175000
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2175 * MHz
 	},
 	.init = zl10036_init,
 	.release = zl10036_release,
diff --git a/drivers/media/dvb-frontends/zl10353.c b/drivers/media/dvb-frontends/zl10353.c
index c9901f45deb7..42e63a3fa121 100644
--- a/drivers/media/dvb-frontends/zl10353.c
+++ b/drivers/media/dvb-frontends/zl10353.c
@@ -635,10 +635,9 @@ static const struct dvb_frontend_ops zl10353_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "Zarlink ZL10353 DVB-T",
-		.frequency_min		= 174000000,
-		.frequency_max		= 862000000,
-		.frequency_stepsize	= 166667,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	= 174 * MHz,
+		.frequency_max_hz	= 862 * MHz,
+		.frequency_stepsize_hz	= 166667,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 |
 			FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 |
 			FE_CAN_FEC_AUTO |
diff --git a/drivers/media/firewire/firedtv-fe.c b/drivers/media/firewire/firedtv-fe.c
index a2ef4ede8ebe..69087ae6c1d0 100644
--- a/drivers/media/firewire/firedtv-fe.c
+++ b/drivers/media/firewire/firedtv-fe.c
@@ -152,7 +152,7 @@ static int fdtv_set_frontend(struct dvb_frontend *fe)
 void fdtv_frontend_init(struct firedtv *fdtv, const char *name)
 {
 	struct dvb_frontend_ops *ops = &fdtv->fe.ops;
-	struct dvb_frontend_info *fi = &ops->info;
+	struct dvb_frontend_internal_info *fi = &ops->info;
 
 	ops->init			= fdtv_dvb_init;
 	ops->sleep			= fdtv_sleep;
@@ -174,9 +174,9 @@ void fdtv_frontend_init(struct firedtv *fdtv, const char *name)
 	case FIREDTV_DVB_S:
 		ops->delsys[0]		= SYS_DVBS;
 
-		fi->frequency_min	= 950000;
-		fi->frequency_max	= 2150000;
-		fi->frequency_stepsize	= 125;
+		fi->frequency_min_hz	=   950 * MHz;
+		fi->frequency_max_hz	=  2150 * MHz;
+		fi->frequency_stepsize_hz = 125 * kHz;
 		fi->symbol_rate_min	= 1000000;
 		fi->symbol_rate_max	= 40000000;
 
@@ -194,9 +194,9 @@ void fdtv_frontend_init(struct firedtv *fdtv, const char *name)
 		ops->delsys[0]		= SYS_DVBS;
 		ops->delsys[1]		= SYS_DVBS2;
 
-		fi->frequency_min	= 950000;
-		fi->frequency_max	= 2150000;
-		fi->frequency_stepsize	= 125;
+		fi->frequency_min_hz	=   950 * MHz;
+		fi->frequency_max_hz	=  2150 * MHz;
+		fi->frequency_stepsize_hz = 125 * kHz;
 		fi->symbol_rate_min	= 1000000;
 		fi->symbol_rate_max	= 40000000;
 
@@ -214,9 +214,9 @@ void fdtv_frontend_init(struct firedtv *fdtv, const char *name)
 	case FIREDTV_DVB_C:
 		ops->delsys[0]		= SYS_DVBC_ANNEX_A;
 
-		fi->frequency_min	= 47000000;
-		fi->frequency_max	= 866000000;
-		fi->frequency_stepsize	= 62500;
+		fi->frequency_min_hz	=      47 * MHz;
+		fi->frequency_max_hz	=     866 * MHz;
+		fi->frequency_stepsize_hz = 62500;
 		fi->symbol_rate_min	= 870000;
 		fi->symbol_rate_max	= 6900000;
 
@@ -232,9 +232,9 @@ void fdtv_frontend_init(struct firedtv *fdtv, const char *name)
 	case FIREDTV_DVB_T:
 		ops->delsys[0]		= SYS_DVBT;
 
-		fi->frequency_min	= 49000000;
-		fi->frequency_max	= 861000000;
-		fi->frequency_stepsize	= 62500;
+		fi->frequency_min_hz	=  49 * MHz;
+		fi->frequency_max_hz	= 861 * MHz;
+		fi->frequency_stepsize_hz = 62500;
 
 		fi->caps		= FE_CAN_INVERSION_AUTO		|
 					  FE_CAN_FEC_2_3		|
diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index 341452fe98df..82af97430e5b 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -326,6 +326,16 @@ config VIDEO_AD5820
 	  This is a driver for the AD5820 camera lens voice coil.
 	  It is used for example in Nokia N900 (RX-51).
 
+config VIDEO_AK7375
+	tristate "AK7375 lens voice coil support"
+	depends on I2C && VIDEO_V4L2 && MEDIA_CONTROLLER
+	depends on VIDEO_V4L2_SUBDEV_API
+	help
+	  This is a driver for the AK7375 camera lens voice coil.
+	  AK7375 is a 12 bit DAC with 120mA output current sink
+	  capability. This is designed for linear control of
+	  voice coil motors, controlled via I2C serial interface.
+
 config VIDEO_DW9714
 	tristate "DW9714 lens voice coil support"
 	depends on I2C && VIDEO_V4L2 && MEDIA_CONTROLLER
@@ -336,6 +346,16 @@ config VIDEO_DW9714
 	  capability. This is designed for linear control of
 	  voice coil motors, controlled via I2C serial interface.
 
+config VIDEO_DW9807_VCM
+	tristate "DW9807 lens voice coil support"
+	depends on I2C && VIDEO_V4L2 && MEDIA_CONTROLLER
+	depends on VIDEO_V4L2_SUBDEV_API
+	---help---
+	  This is a driver for the DW9807 camera lens voice coil.
+	  DW9807 is a 10 bit DAC with 100mA output current sink
+	  capability. This is designed for linear control of
+	  voice coil motors, controlled via I2C serial interface.
+
 config VIDEO_SAA7110
 	tristate "Philips SAA7110 video decoder"
 	depends on VIDEO_V4L2 && I2C
@@ -378,7 +398,7 @@ config VIDEO_TVP514X
 	depends on VIDEO_V4L2 && I2C
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the TI TVP5146/47
+	  This is a Video4Linux2 sensor driver for the TI TVP5146/47
 	  decoder. It is currently working with the TI OMAP3 camera
 	  controller.
 
@@ -580,7 +600,7 @@ config VIDEO_IMX258
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the Sony
+	  This is a Video4Linux2 sensor driver for the Sony
 	  IMX258 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -591,7 +611,7 @@ config VIDEO_IMX274
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a V4L2 sensor-level driver for the Sony IMX274
+	  This is a V4L2 sensor driver for the Sony IMX274
 	  CMOS image sensor.
 
 config VIDEO_OV2640
@@ -599,7 +619,7 @@ config VIDEO_OV2640
 	depends on VIDEO_V4L2 && I2C
 	depends on MEDIA_CAMERA_SUPPORT
 	help
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV2640 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -611,19 +631,31 @@ config VIDEO_OV2659
 	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV2659 camera.
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called ov2659.
 
+config VIDEO_OV2680
+	tristate "OmniVision OV2680 sensor support"
+	depends on VIDEO_V4L2 && I2C && MEDIA_CONTROLLER
+	depends on MEDIA_CAMERA_SUPPORT
+	select V4L2_FWNODE
+	---help---
+	  This is a Video4Linux2 sensor driver for the OmniVision
+	  OV2680 camera.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called ov2680.
+
 config VIDEO_OV2685
 	tristate "OmniVision OV2685 sensor support"
 	depends on VIDEO_V4L2 && I2C && MEDIA_CONTROLLER
 	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV2685 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -636,7 +668,7 @@ config VIDEO_OV5640
 	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the Omnivision
+	  This is a Video4Linux2 sensor driver for the Omnivision
 	  OV5640 camera sensor with a MIPI CSI-2 interface.
 
 config VIDEO_OV5645
@@ -646,7 +678,7 @@ config VIDEO_OV5645
 	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV5645 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -658,7 +690,7 @@ config VIDEO_OV5647
 	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV5647 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -669,7 +701,7 @@ config VIDEO_OV6650
 	depends on I2C && VIDEO_V4L2
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV6650 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -682,7 +714,7 @@ config VIDEO_OV5670
 	depends on MEDIA_CONTROLLER
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV5670 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -693,7 +725,7 @@ config VIDEO_OV5695
 	depends on I2C && VIDEO_V4L2
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV5695 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -705,7 +737,7 @@ config VIDEO_OV7251
 	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	help
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV7251 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -716,7 +748,7 @@ config VIDEO_OV772X
 	depends on I2C && VIDEO_V4L2
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV772x camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -727,7 +759,7 @@ config VIDEO_OV7640
 	depends on I2C && VIDEO_V4L2
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV7640 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -739,7 +771,7 @@ config VIDEO_OV7670
 	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV7670 VGA camera.  It currently only works with the M88ALP01
 	  controller.
 
@@ -748,14 +780,14 @@ config VIDEO_OV7740
 	depends on I2C && VIDEO_V4L2
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV7740 VGA camera sensor.
 
 config VIDEO_OV9650
 	tristate "OmniVision OV9650/OV9652 sensor support"
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	---help---
-	  This is a V4L2 sensor-level driver for the Omnivision
+	  This is a V4L2 sensor driver for the Omnivision
 	  OV9650 and OV9652 camera sensors.
 
 config VIDEO_OV13858
@@ -764,7 +796,7 @@ config VIDEO_OV13858
 	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV13858 camera.
 
 config VIDEO_VS6624
@@ -772,7 +804,7 @@ config VIDEO_VS6624
 	depends on VIDEO_V4L2 && I2C
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the ST VS6624
+	  This is a Video4Linux2 sensor driver for the ST VS6624
 	  camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -800,7 +832,7 @@ config VIDEO_MT9P031
 	depends on MEDIA_CAMERA_SUPPORT
 	select VIDEO_APTINA_PLL
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the Aptina
+	  This is a Video4Linux2 sensor driver for the Aptina
 	  (Micron) mt9p031 5 Mpixel camera.
 
 config VIDEO_MT9T001
@@ -808,7 +840,7 @@ config VIDEO_MT9T001
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the Aptina
+	  This is a Video4Linux2 sensor driver for the Aptina
 	  (Micron) mt0t001 3 Mpixel camera.
 
 config VIDEO_MT9T112
@@ -816,7 +848,7 @@ config VIDEO_MT9T112
 	depends on I2C && VIDEO_V4L2
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the Aptina
+	  This is a Video4Linux2 sensor driver for the Aptina
 	  (Micron) MT9T111 and MT9T112 3 Mpixel camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -827,7 +859,7 @@ config VIDEO_MT9V011
 	depends on I2C && VIDEO_V4L2
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the Micron
+	  This is a Video4Linux2 sensor driver for the Micron
 	  mt0v011 1.3 Mpixel camera.  It currently only works with the
 	  em28xx driver.
 
@@ -838,9 +870,20 @@ config VIDEO_MT9V032
 	select REGMAP_I2C
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the Micron
+	  This is a Video4Linux2 sensor driver for the Micron
 	  MT9V032 752x480 CMOS sensor.
 
+config VIDEO_MT9V111
+	tristate "Aptina MT9V111 sensor support"
+	depends on I2C && VIDEO_V4L2
+	depends on MEDIA_CAMERA_SUPPORT
+	help
+	  This is a Video4Linux2 sensor driver for the Aptina/Micron
+	  MT9V111 sensor.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called mt9v111.
+
 config VIDEO_SR030PC30
 	tristate "Siliconfile SR030PC30 sensor support"
 	depends on I2C && VIDEO_V4L2
@@ -857,12 +900,23 @@ config VIDEO_NOON010PC30
 
 source "drivers/media/i2c/m5mols/Kconfig"
 
+config VIDEO_RJ54N1
+	tristate "Sharp RJ54N1CB0C sensor support"
+	depends on I2C && VIDEO_V4L2
+	depends on MEDIA_CAMERA_SUPPORT
+	help
+	  This is a V4L2 sensor driver for Sharp RJ54N1CB0C CMOS image
+	  sensor.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called rj54n1.
+
 config VIDEO_S5K6AA
 	tristate "Samsung S5K6AAFX sensor support"
 	depends on MEDIA_CAMERA_SUPPORT
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	---help---
-	  This is a V4L2 sensor-level driver for Samsung S5K6AA(FX) 1.3M
+	  This is a V4L2 sensor driver for Samsung S5K6AA(FX) 1.3M
 	  camera sensor with an embedded SoC image signal processor.
 
 config VIDEO_S5K6A3
@@ -870,7 +924,7 @@ config VIDEO_S5K6A3
 	depends on MEDIA_CAMERA_SUPPORT
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	---help---
-	  This is a V4L2 sensor-level driver for Samsung S5K6A3 raw
+	  This is a V4L2 sensor driver for Samsung S5K6A3 raw
 	  camera sensor.
 
 config VIDEO_S5K4ECGX
@@ -878,7 +932,7 @@ config VIDEO_S5K4ECGX
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	select CRC32
 	---help---
-	  This is a V4L2 sensor-level driver for Samsung S5K4ECGX 5M
+	  This is a V4L2 sensor driver for Samsung S5K4ECGX 5M
 	  camera sensor with an embedded SoC image signal processor.
 
 config VIDEO_S5K5BAF
@@ -886,7 +940,7 @@ config VIDEO_S5K5BAF
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	select V4L2_FWNODE
 	---help---
-	  This is a V4L2 sensor-level driver for Samsung S5K5BAF 2M
+	  This is a V4L2 sensor driver for Samsung S5K5BAF 2M
 	  camera sensor with an embedded SoC image signal processor.
 
 source "drivers/media/i2c/smiapp/Kconfig"
@@ -897,7 +951,7 @@ config VIDEO_S5C73M3
 	depends on I2C && SPI && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	select V4L2_FWNODE
 	---help---
-	  This is a V4L2 sensor-level driver for Samsung S5C73M3
+	  This is a V4L2 sensor driver for Samsung S5C73M3
 	  8 Mpixel camera.
 
 comment "Flash devices"
@@ -1002,6 +1056,7 @@ config VIDEO_I2C
 	tristate "I2C transport video support"
 	depends on VIDEO_V4L2 && I2C
 	select VIDEOBUF2_VMALLOC
+	imply HWMON
 	---help---
 	  Enable the I2C transport video support which supports the
 	  following:
diff --git a/drivers/media/i2c/Makefile b/drivers/media/i2c/Makefile
index d679d57cd3b3..a94eb03d10d4 100644
--- a/drivers/media/i2c/Makefile
+++ b/drivers/media/i2c/Makefile
@@ -23,7 +23,9 @@ obj-$(CONFIG_VIDEO_SAA7127) += saa7127.o
 obj-$(CONFIG_VIDEO_SAA7185) += saa7185.o
 obj-$(CONFIG_VIDEO_SAA6752HS) += saa6752hs.o
 obj-$(CONFIG_VIDEO_AD5820)  += ad5820.o
+obj-$(CONFIG_VIDEO_AK7375)  += ak7375.o
 obj-$(CONFIG_VIDEO_DW9714)  += dw9714.o
+obj-$(CONFIG_VIDEO_DW9807_VCM)  += dw9807-vcm.o
 obj-$(CONFIG_VIDEO_ADV7170) += adv7170.o
 obj-$(CONFIG_VIDEO_ADV7175) += adv7175.o
 obj-$(CONFIG_VIDEO_ADV7180) += adv7180.o
@@ -63,6 +65,7 @@ obj-$(CONFIG_VIDEO_SONY_BTF_MPX) += sony-btf-mpx.o
 obj-$(CONFIG_VIDEO_UPD64031A) += upd64031a.o
 obj-$(CONFIG_VIDEO_UPD64083) += upd64083.o
 obj-$(CONFIG_VIDEO_OV2640) += ov2640.o
+obj-$(CONFIG_VIDEO_OV2680) += ov2680.o
 obj-$(CONFIG_VIDEO_OV2685) += ov2685.o
 obj-$(CONFIG_VIDEO_OV5640) += ov5640.o
 obj-$(CONFIG_VIDEO_OV5645) += ov5645.o
@@ -84,8 +87,10 @@ obj-$(CONFIG_VIDEO_MT9T001) += mt9t001.o
 obj-$(CONFIG_VIDEO_MT9T112) += mt9t112.o
 obj-$(CONFIG_VIDEO_MT9V011) += mt9v011.o
 obj-$(CONFIG_VIDEO_MT9V032) += mt9v032.o
+obj-$(CONFIG_VIDEO_MT9V111) += mt9v111.o
 obj-$(CONFIG_VIDEO_SR030PC30)	+= sr030pc30.o
 obj-$(CONFIG_VIDEO_NOON010PC30)	+= noon010pc30.o
+obj-$(CONFIG_VIDEO_RJ54N1)	+= rj54n1cb0c.o
 obj-$(CONFIG_VIDEO_S5K6AA)	+= s5k6aa.o
 obj-$(CONFIG_VIDEO_S5K6A3)	+= s5k6a3.o
 obj-$(CONFIG_VIDEO_S5K4ECGX)	+= s5k4ecgx.o
diff --git a/drivers/media/i2c/ad9389b.c b/drivers/media/i2c/ad9389b.c
index 91ff06088572..5b008b0002c0 100644
--- a/drivers/media/i2c/ad9389b.c
+++ b/drivers/media/i2c/ad9389b.c
@@ -1134,6 +1134,7 @@ static int ad9389b_probe(struct i2c_client *client, const struct i2c_device_id *
 		goto err_hdl;
 	}
 	state->pad.flags = MEDIA_PAD_FL_SINK;
+	sd->entity.function = MEDIA_ENT_F_DV_ENCODER;
 	err = media_entity_pads_init(&sd->entity, 1, &state->pad);
 	if (err)
 		goto err_hdl;
diff --git a/drivers/media/i2c/adv7180.c b/drivers/media/i2c/adv7180.c
index 25d24a3f10a7..de10367d550b 100644
--- a/drivers/media/i2c/adv7180.c
+++ b/drivers/media/i2c/adv7180.c
@@ -461,6 +461,22 @@ static int adv7180_g_std(struct v4l2_subdev *sd, v4l2_std_id *norm)
 	return 0;
 }
 
+static int adv7180_g_frame_interval(struct v4l2_subdev *sd,
+				    struct v4l2_subdev_frame_interval *fi)
+{
+	struct adv7180_state *state = to_state(sd);
+
+	if (state->curr_norm & V4L2_STD_525_60) {
+		fi->interval.numerator = 1001;
+		fi->interval.denominator = 30000;
+	} else {
+		fi->interval.numerator = 1;
+		fi->interval.denominator = 25;
+	}
+
+	return 0;
+}
+
 static void adv7180_set_power_pin(struct adv7180_state *state, bool on)
 {
 	if (!state->pwdn_gpio)
@@ -644,6 +660,9 @@ static int adv7180_mbus_fmt(struct v4l2_subdev *sd,
 	fmt->width = 720;
 	fmt->height = state->curr_norm & V4L2_STD_525_60 ? 480 : 576;
 
+	if (state->field == V4L2_FIELD_ALTERNATE)
+		fmt->height /= 2;
+
 	return 0;
 }
 
@@ -711,11 +730,11 @@ static int adv7180_set_pad_format(struct v4l2_subdev *sd,
 
 	switch (format->format.field) {
 	case V4L2_FIELD_NONE:
-		if (!(state->chip_info->flags & ADV7180_FLAG_I2P))
-			format->format.field = V4L2_FIELD_INTERLACED;
-		break;
+		if (state->chip_info->flags & ADV7180_FLAG_I2P)
+			break;
+		/* fall through */
 	default:
-		format->format.field = V4L2_FIELD_INTERLACED;
+		format->format.field = V4L2_FIELD_ALTERNATE;
 		break;
 	}
 
@@ -817,6 +836,7 @@ static int adv7180_subscribe_event(struct v4l2_subdev *sd,
 static const struct v4l2_subdev_video_ops adv7180_video_ops = {
 	.s_std = adv7180_s_std,
 	.g_std = adv7180_g_std,
+	.g_frame_interval = adv7180_g_frame_interval,
 	.querystd = adv7180_querystd,
 	.g_input_status = adv7180_g_input_status,
 	.s_routing = adv7180_s_routing,
@@ -1291,7 +1311,7 @@ static int adv7180_probe(struct i2c_client *client,
 		return -ENOMEM;
 
 	state->client = client;
-	state->field = V4L2_FIELD_INTERLACED;
+	state->field = V4L2_FIELD_ALTERNATE;
 	state->chip_info = (struct adv7180_chip_info *)id->driver_data;
 
 	state->pwdn_gpio = devm_gpiod_get_optional(&client->dev, "powerdown",
@@ -1335,7 +1355,7 @@ static int adv7180_probe(struct i2c_client *client,
 		goto err_unregister_vpp_client;
 
 	state->pad.flags = MEDIA_PAD_FL_SOURCE;
-	sd->entity.flags |= MEDIA_ENT_F_ATV_DECODER;
+	sd->entity.function = MEDIA_ENT_F_ATV_DECODER;
 	ret = media_entity_pads_init(&sd->entity, 1, &state->pad);
 	if (ret)
 		goto err_free_ctrl;
diff --git a/drivers/media/i2c/adv748x/adv748x-csi2.c b/drivers/media/i2c/adv748x/adv748x-csi2.c
index 820b44ed56a8..469be87a3761 100644
--- a/drivers/media/i2c/adv748x/adv748x-csi2.c
+++ b/drivers/media/i2c/adv748x/adv748x-csi2.c
@@ -284,7 +284,7 @@ int adv748x_csi2_init(struct adv748x_state *state, struct adv748x_csi2 *tx)
 	adv748x_csi2_set_virtual_channel(tx, 0);
 
 	adv748x_subdev_init(&tx->sd, state, &adv748x_csi2_ops,
-			    MEDIA_ENT_F_UNKNOWN,
+			    MEDIA_ENT_F_VID_IF_BRIDGE,
 			    is_txa(tx) ? "txa" : "txb");
 
 	/* Ensure that matching is based upon the endpoint fwnodes */
diff --git a/drivers/media/i2c/adv7511.c b/drivers/media/i2c/adv7511.c
index 5731751d3f2a..55c2ea0720d9 100644
--- a/drivers/media/i2c/adv7511.c
+++ b/drivers/media/i2c/adv7511.c
@@ -1847,6 +1847,7 @@ static int adv7511_probe(struct i2c_client *client, const struct i2c_device_id *
 		goto err_hdl;
 	}
 	state->pad.flags = MEDIA_PAD_FL_SINK;
+	sd->entity.function = MEDIA_ENT_F_DV_ENCODER;
 	err = media_entity_pads_init(&sd->entity, 1, &state->pad);
 	if (err)
 		goto err_hdl;
diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c
index cac2081e876e..668be2bca57a 100644
--- a/drivers/media/i2c/adv7604.c
+++ b/drivers/media/i2c/adv7604.c
@@ -3108,12 +3108,9 @@ static int adv76xx_parse_dt(struct adv76xx_state *state)
 		return -EINVAL;
 
 	ret = v4l2_fwnode_endpoint_parse(of_fwnode_handle(endpoint), &bus_cfg);
-	if (ret) {
-		of_node_put(endpoint);
-		return ret;
-	}
-
 	of_node_put(endpoint);
+	if (ret)
+		return ret;
 
 	if (!of_property_read_u32(np, "default-input", &v))
 		state->pdata.default_input = v;
@@ -3502,6 +3499,7 @@ static int adv76xx_probe(struct i2c_client *client,
 	for (i = 0; i < state->source_pad; ++i)
 		state->pads[i].flags = MEDIA_PAD_FL_SINK;
 	state->pads[state->source_pad].flags = MEDIA_PAD_FL_SOURCE;
+	sd->entity.function = MEDIA_ENT_F_DV_DECODER;
 
 	err = media_entity_pads_init(&sd->entity, state->source_pad + 1,
 				state->pads);
diff --git a/drivers/media/i2c/adv7842.c b/drivers/media/i2c/adv7842.c
index fddac32e5051..4f8fbdd00e35 100644
--- a/drivers/media/i2c/adv7842.c
+++ b/drivers/media/i2c/adv7842.c
@@ -3102,7 +3102,7 @@ static int adv7842_ddr_ram_test(struct v4l2_subdev *sd)
 	sdp_write(sd, 0x12, 0x00); /* Disable 3D comb, Frame TBC & 3DNR */
 	io_write(sd, 0xFF, 0x04);  /* Reset memory controller */
 
-	mdelay(5);
+	usleep_range(5000, 6000);
 
 	sdp_write(sd, 0x12, 0x00);    /* Disable 3D Comb, Frame TBC & 3DNR */
 	sdp_io_write(sd, 0x2A, 0x01); /* Memory BIST Initialisation */
@@ -3116,12 +3116,12 @@ static int adv7842_ddr_ram_test(struct v4l2_subdev *sd)
 	sdp_io_write(sd, 0x7d, 0x00); /* Memory BIST Initialisation */
 	sdp_io_write(sd, 0x7e, 0x1a); /* Memory BIST Initialisation */
 
-	mdelay(5);
+	usleep_range(5000, 6000);
 
 	sdp_io_write(sd, 0xd9, 0xd5); /* Enable BIST Test */
 	sdp_write(sd, 0x12, 0x05); /* Enable FRAME TBC & 3D COMB */
 
-	mdelay(20);
+	msleep(20);
 
 	for (i = 0; i < 10; i++) {
 		u8 result = sdp_io_read(sd, 0xdb);
@@ -3132,7 +3132,7 @@ static int adv7842_ddr_ram_test(struct v4l2_subdev *sd)
 			else
 				pass++;
 		}
-		mdelay(20);
+		msleep(20);
 	}
 
 	v4l2_dbg(1, debug, sd,
@@ -3541,6 +3541,7 @@ static int adv7842_probe(struct i2c_client *client,
 	INIT_DELAYED_WORK(&state->delayed_work_enable_hotplug,
 			adv7842_delayed_work_enable_hotplug);
 
+	sd->entity.function = MEDIA_ENT_F_DV_DECODER;
 	state->pad.flags = MEDIA_PAD_FL_SOURCE;
 	err = media_entity_pads_init(&sd->entity, 1, &state->pad);
 	if (err)
diff --git a/drivers/media/i2c/ak7375.c b/drivers/media/i2c/ak7375.c
new file mode 100644
index 000000000000..7b14b11605ca
--- /dev/null
+++ b/drivers/media/i2c/ak7375.c
@@ -0,0 +1,292 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Intel Corporation
+
+#include <linux/acpi.h>
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/pm_runtime.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+
+#define AK7375_MAX_FOCUS_POS	4095
+/*
+ * This sets the minimum granularity for the focus positions.
+ * A value of 1 gives maximum accuracy for a desired focus position
+ */
+#define AK7375_FOCUS_STEPS	1
+/*
+ * This acts as the minimum granularity of lens movement.
+ * Keep this value power of 2, so the control steps can be
+ * uniformly adjusted for gradual lens movement, with desired
+ * number of control steps.
+ */
+#define AK7375_CTRL_STEPS	64
+#define AK7375_CTRL_DELAY_US	1000
+
+#define AK7375_REG_POSITION	0x0
+#define AK7375_REG_CONT		0x2
+#define AK7375_MODE_ACTIVE	0x0
+#define AK7375_MODE_STANDBY	0x40
+
+/* ak7375 device structure */
+struct ak7375_device {
+	struct v4l2_ctrl_handler ctrls_vcm;
+	struct v4l2_subdev sd;
+	struct v4l2_ctrl *focus;
+	/* active or standby mode */
+	bool active;
+};
+
+static inline struct ak7375_device *to_ak7375_vcm(struct v4l2_ctrl *ctrl)
+{
+	return container_of(ctrl->handler, struct ak7375_device, ctrls_vcm);
+}
+
+static inline struct ak7375_device *sd_to_ak7375_vcm(struct v4l2_subdev *subdev)
+{
+	return container_of(subdev, struct ak7375_device, sd);
+}
+
+static int ak7375_i2c_write(struct ak7375_device *ak7375,
+	u8 addr, u16 data, u8 size)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(&ak7375->sd);
+	u8 buf[3];
+	int ret;
+
+	if (size != 1 && size != 2)
+		return -EINVAL;
+	buf[0] = addr;
+	buf[size] = data & 0xff;
+	if (size == 2)
+		buf[1] = (data >> 8) & 0xff;
+	ret = i2c_master_send(client, (const char *)buf, size + 1);
+	if (ret < 0)
+		return ret;
+	if (ret != size + 1)
+		return -EIO;
+
+	return 0;
+}
+
+static int ak7375_set_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct ak7375_device *dev_vcm = to_ak7375_vcm(ctrl);
+
+	if (ctrl->id == V4L2_CID_FOCUS_ABSOLUTE)
+		return ak7375_i2c_write(dev_vcm, AK7375_REG_POSITION,
+					ctrl->val << 4, 2);
+
+	return -EINVAL;
+}
+
+static const struct v4l2_ctrl_ops ak7375_vcm_ctrl_ops = {
+	.s_ctrl = ak7375_set_ctrl,
+};
+
+static int ak7375_open(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
+{
+	int ret;
+
+	ret = pm_runtime_get_sync(sd->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(sd->dev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int ak7375_close(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
+{
+	pm_runtime_put(sd->dev);
+
+	return 0;
+}
+
+static const struct v4l2_subdev_internal_ops ak7375_int_ops = {
+	.open = ak7375_open,
+	.close = ak7375_close,
+};
+
+static const struct v4l2_subdev_ops ak7375_ops = { };
+
+static void ak7375_subdev_cleanup(struct ak7375_device *ak7375_dev)
+{
+	v4l2_async_unregister_subdev(&ak7375_dev->sd);
+	v4l2_ctrl_handler_free(&ak7375_dev->ctrls_vcm);
+	media_entity_cleanup(&ak7375_dev->sd.entity);
+}
+
+static int ak7375_init_controls(struct ak7375_device *dev_vcm)
+{
+	struct v4l2_ctrl_handler *hdl = &dev_vcm->ctrls_vcm;
+	const struct v4l2_ctrl_ops *ops = &ak7375_vcm_ctrl_ops;
+
+	v4l2_ctrl_handler_init(hdl, 1);
+
+	dev_vcm->focus = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_FOCUS_ABSOLUTE,
+		0, AK7375_MAX_FOCUS_POS, AK7375_FOCUS_STEPS, 0);
+
+	if (hdl->error)
+		dev_err(dev_vcm->sd.dev, "%s fail error: 0x%x\n",
+			__func__, hdl->error);
+	dev_vcm->sd.ctrl_handler = hdl;
+
+	return hdl->error;
+}
+
+static int ak7375_probe(struct i2c_client *client)
+{
+	struct ak7375_device *ak7375_dev;
+	int ret;
+
+	ak7375_dev = devm_kzalloc(&client->dev, sizeof(*ak7375_dev),
+				  GFP_KERNEL);
+	if (!ak7375_dev)
+		return -ENOMEM;
+
+	v4l2_i2c_subdev_init(&ak7375_dev->sd, client, &ak7375_ops);
+	ak7375_dev->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
+	ak7375_dev->sd.internal_ops = &ak7375_int_ops;
+	ak7375_dev->sd.entity.function = MEDIA_ENT_F_LENS;
+
+	ret = ak7375_init_controls(ak7375_dev);
+	if (ret)
+		goto err_cleanup;
+
+	ret = media_entity_pads_init(&ak7375_dev->sd.entity, 0, NULL);
+	if (ret < 0)
+		goto err_cleanup;
+
+	ret = v4l2_async_register_subdev(&ak7375_dev->sd);
+	if (ret < 0)
+		goto err_cleanup;
+
+	pm_runtime_set_active(&client->dev);
+	pm_runtime_enable(&client->dev);
+	pm_runtime_idle(&client->dev);
+
+	return 0;
+
+err_cleanup:
+	v4l2_ctrl_handler_free(&ak7375_dev->ctrls_vcm);
+	media_entity_cleanup(&ak7375_dev->sd.entity);
+
+	return ret;
+}
+
+static int ak7375_remove(struct i2c_client *client)
+{
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct ak7375_device *ak7375_dev = sd_to_ak7375_vcm(sd);
+
+	ak7375_subdev_cleanup(ak7375_dev);
+	pm_runtime_disable(&client->dev);
+	pm_runtime_set_suspended(&client->dev);
+
+	return 0;
+}
+
+/*
+ * This function sets the vcm position, so it consumes least current
+ * The lens position is gradually moved in units of AK7375_CTRL_STEPS,
+ * to make the movements smoothly.
+ */
+static int __maybe_unused ak7375_vcm_suspend(struct device *dev)
+{
+
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct ak7375_device *ak7375_dev = sd_to_ak7375_vcm(sd);
+	int ret, val;
+
+	if (!ak7375_dev->active)
+		return 0;
+
+	for (val = ak7375_dev->focus->val & ~(AK7375_CTRL_STEPS - 1);
+	     val >= 0; val -= AK7375_CTRL_STEPS) {
+		ret = ak7375_i2c_write(ak7375_dev, AK7375_REG_POSITION,
+				       val << 4, 2);
+		if (ret)
+			dev_err_once(dev, "%s I2C failure: %d\n",
+				     __func__, ret);
+		usleep_range(AK7375_CTRL_DELAY_US, AK7375_CTRL_DELAY_US + 10);
+	}
+
+	ret = ak7375_i2c_write(ak7375_dev, AK7375_REG_CONT,
+			       AK7375_MODE_STANDBY, 1);
+	if (ret)
+		dev_err(dev, "%s I2C failure: %d\n", __func__, ret);
+
+	ak7375_dev->active = false;
+
+	return 0;
+}
+
+/*
+ * This function sets the vcm position to the value set by the user
+ * through v4l2_ctrl_ops s_ctrl handler
+ * The lens position is gradually moved in units of AK7375_CTRL_STEPS,
+ * to make the movements smoothly.
+ */
+static int __maybe_unused ak7375_vcm_resume(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct ak7375_device *ak7375_dev = sd_to_ak7375_vcm(sd);
+	int ret, val;
+
+	if (ak7375_dev->active)
+		return 0;
+
+	ret = ak7375_i2c_write(ak7375_dev, AK7375_REG_CONT,
+		AK7375_MODE_ACTIVE, 1);
+	if (ret) {
+		dev_err(dev, "%s I2C failure: %d\n", __func__, ret);
+		return ret;
+	}
+
+	for (val = ak7375_dev->focus->val % AK7375_CTRL_STEPS;
+	     val <= ak7375_dev->focus->val;
+	     val += AK7375_CTRL_STEPS) {
+		ret = ak7375_i2c_write(ak7375_dev, AK7375_REG_POSITION,
+				       val << 4, 2);
+		if (ret)
+			dev_err_ratelimited(dev, "%s I2C failure: %d\n",
+						__func__, ret);
+		usleep_range(AK7375_CTRL_DELAY_US, AK7375_CTRL_DELAY_US + 10);
+	}
+
+	ak7375_dev->active = true;
+
+	return 0;
+}
+
+static const struct of_device_id ak7375_of_table[] = {
+	{ .compatible = "asahi-kasei,ak7375" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, ak7375_of_table);
+
+static const struct dev_pm_ops ak7375_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(ak7375_vcm_suspend, ak7375_vcm_resume)
+	SET_RUNTIME_PM_OPS(ak7375_vcm_suspend, ak7375_vcm_resume, NULL)
+};
+
+static struct i2c_driver ak7375_i2c_driver = {
+	.driver = {
+		.name = "ak7375",
+		.pm = &ak7375_pm_ops,
+		.of_match_table = ak7375_of_table,
+	},
+	.probe_new = ak7375_probe,
+	.remove = ak7375_remove,
+};
+module_i2c_driver(ak7375_i2c_driver);
+
+MODULE_AUTHOR("Tianshu Qiu <tian.shu.qiu@intel.com>");
+MODULE_AUTHOR("Bingbu Cao <bingbu.cao@intel.com>");
+MODULE_DESCRIPTION("AK7375 VCM driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/i2c/cx25840/cx25840-core.h b/drivers/media/i2c/cx25840/cx25840-core.h
index fb13a624d2e3..c323b1af1f83 100644
--- a/drivers/media/i2c/cx25840/cx25840-core.h
+++ b/drivers/media/i2c/cx25840/cx25840-core.h
@@ -45,6 +45,35 @@ enum cx25840_media_pads {
 	CX25840_NUM_PADS
 };
 
+/**
+ * struct cx25840_state - a device instance private data
+ * @c:			i2c_client struct representing this device
+ * @sd:		our V4L2 sub-device
+ * @hdl:		our V4L2 control handler
+ * @volume:		audio volume V4L2 control (non-cx2583x devices only)
+ * @mute:		audio mute V4L2 control (non-cx2583x devices only)
+ * @pvr150_workaround:	whether we enable workaround for Hauppauge PVR150
+ *			hardware bug (audio dropping out)
+ * @radio:		set if we are currently in the radio mode, otherwise
+ *			the current mode is non-radio (that is, video)
+ * @std:		currently set video standard
+ * @vid_input:		currently set video input
+ * @aud_input:		currently set audio input
+ * @audclk_freq:	currently set audio sample rate
+ * @audmode:		currently set audio mode (when in non-radio mode)
+ * @vbi_line_offset:	vbi line number offset
+ * @id:		exact device model
+ * @rev:		raw device id read from the chip
+ * @is_initialized:	whether we have already loaded firmware into the chip
+ *			and initialized it
+ * @vbi_regs_offset:	offset of vbi regs
+ * @fw_wait:		wait queue to wake an initalization function up when
+ *			firmware loading (on a separate workqueue) finishes
+ * @fw_work:		a work that actually loads the firmware on a separate
+ *			workqueue
+ * @ir_state:		a pointer to chip IR controller private data
+ * @pads:		array of supported chip pads (currently only a stub)
+ */
 struct cx25840_state {
 	struct i2c_client *c;
 	struct v4l2_subdev sd;
@@ -66,8 +95,8 @@ struct cx25840_state {
 	u32 rev;
 	int is_initialized;
 	unsigned vbi_regs_offset;
-	wait_queue_head_t fw_wait;    /* wake up when the fw load is finished */
-	struct work_struct fw_work;   /* work entry for fw load */
+	wait_queue_head_t fw_wait;
+	struct work_struct fw_work;
 	struct cx25840_ir_state *ir_state;
 #if defined(CONFIG_MEDIA_CONTROLLER)
 	struct media_pad	pads[CX25840_NUM_PADS];
diff --git a/drivers/media/i2c/dw9807-vcm.c b/drivers/media/i2c/dw9807-vcm.c
new file mode 100644
index 000000000000..8ba3920b6e2f
--- /dev/null
+++ b/drivers/media/i2c/dw9807-vcm.c
@@ -0,0 +1,329 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Intel Corporation
+
+#include <linux/acpi.h>
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/pm_runtime.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+
+#define DW9807_MAX_FOCUS_POS	1023
+/*
+ * This sets the minimum granularity for the focus positions.
+ * A value of 1 gives maximum accuracy for a desired focus position.
+ */
+#define DW9807_FOCUS_STEPS	1
+/*
+ * This acts as the minimum granularity of lens movement.
+ * Keep this value power of 2, so the control steps can be
+ * uniformly adjusted for gradual lens movement, with desired
+ * number of control steps.
+ */
+#define DW9807_CTRL_STEPS	16
+#define DW9807_CTRL_DELAY_US	1000
+
+#define DW9807_CTL_ADDR		0x02
+/*
+ * DW9807 separates two registers to control the VCM position.
+ * One for MSB value, another is LSB value.
+ */
+#define DW9807_MSB_ADDR		0x03
+#define DW9807_LSB_ADDR		0x04
+#define DW9807_STATUS_ADDR	0x05
+#define DW9807_MODE_ADDR	0x06
+#define DW9807_RESONANCE_ADDR	0x07
+
+#define MAX_RETRY		10
+
+struct dw9807_device {
+	struct v4l2_ctrl_handler ctrls_vcm;
+	struct v4l2_subdev sd;
+	u16 current_val;
+};
+
+static inline struct dw9807_device *sd_to_dw9807_vcm(
+					struct v4l2_subdev *subdev)
+{
+	return container_of(subdev, struct dw9807_device, sd);
+}
+
+static int dw9807_i2c_check(struct i2c_client *client)
+{
+	const char status_addr = DW9807_STATUS_ADDR;
+	char status_result;
+	int ret;
+
+	ret = i2c_master_send(client, &status_addr, sizeof(status_addr));
+	if (ret < 0) {
+		dev_err(&client->dev, "I2C write STATUS address fail ret = %d\n",
+			ret);
+		return ret;
+	}
+
+	ret = i2c_master_recv(client, &status_result, sizeof(status_result));
+	if (ret < 0) {
+		dev_err(&client->dev, "I2C read STATUS value fail ret = %d\n",
+			ret);
+		return ret;
+	}
+
+	return status_result;
+}
+
+static int dw9807_set_dac(struct i2c_client *client, u16 data)
+{
+	const char tx_data[3] = {
+		DW9807_MSB_ADDR, ((data >> 8) & 0x03), (data & 0xff)
+	};
+	int val, ret;
+
+	/*
+	 * According to the datasheet, need to check the bus status before we
+	 * write VCM position. This ensure that we really write the value
+	 * into the register
+	 */
+	ret = readx_poll_timeout(dw9807_i2c_check, client, val, val <= 0,
+			DW9807_CTRL_DELAY_US, MAX_RETRY * DW9807_CTRL_DELAY_US);
+
+	if (ret || val < 0) {
+		if (ret) {
+			dev_warn(&client->dev,
+				"Cannot do the write operation because VCM is busy\n");
+		}
+
+		return ret ? -EBUSY : val;
+	}
+
+	/* Write VCM position to registers */
+	ret = i2c_master_send(client, tx_data, sizeof(tx_data));
+	if (ret < 0) {
+		dev_err(&client->dev,
+			"I2C write MSB fail ret=%d\n", ret);
+
+		return ret;
+	}
+
+	return 0;
+}
+
+static int dw9807_set_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct dw9807_device *dev_vcm = container_of(ctrl->handler,
+		struct dw9807_device, ctrls_vcm);
+
+	if (ctrl->id == V4L2_CID_FOCUS_ABSOLUTE) {
+		struct i2c_client *client = v4l2_get_subdevdata(&dev_vcm->sd);
+
+		dev_vcm->current_val = ctrl->val;
+		return dw9807_set_dac(client, ctrl->val);
+	}
+
+	return -EINVAL;
+}
+
+static const struct v4l2_ctrl_ops dw9807_vcm_ctrl_ops = {
+	.s_ctrl = dw9807_set_ctrl,
+};
+
+static int dw9807_open(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
+{
+	int rval;
+
+	rval = pm_runtime_get_sync(sd->dev);
+	if (rval < 0) {
+		pm_runtime_put_noidle(sd->dev);
+		return rval;
+	}
+
+	return 0;
+}
+
+static int dw9807_close(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
+{
+	pm_runtime_put(sd->dev);
+
+	return 0;
+}
+
+static const struct v4l2_subdev_internal_ops dw9807_int_ops = {
+	.open = dw9807_open,
+	.close = dw9807_close,
+};
+
+static const struct v4l2_subdev_ops dw9807_ops = { };
+
+static void dw9807_subdev_cleanup(struct dw9807_device *dw9807_dev)
+{
+	v4l2_async_unregister_subdev(&dw9807_dev->sd);
+	v4l2_ctrl_handler_free(&dw9807_dev->ctrls_vcm);
+	media_entity_cleanup(&dw9807_dev->sd.entity);
+}
+
+static int dw9807_init_controls(struct dw9807_device *dev_vcm)
+{
+	struct v4l2_ctrl_handler *hdl = &dev_vcm->ctrls_vcm;
+	const struct v4l2_ctrl_ops *ops = &dw9807_vcm_ctrl_ops;
+	struct i2c_client *client = v4l2_get_subdevdata(&dev_vcm->sd);
+
+	v4l2_ctrl_handler_init(hdl, 1);
+
+	v4l2_ctrl_new_std(hdl, ops, V4L2_CID_FOCUS_ABSOLUTE,
+			  0, DW9807_MAX_FOCUS_POS, DW9807_FOCUS_STEPS, 0);
+
+	dev_vcm->sd.ctrl_handler = hdl;
+	if (hdl->error) {
+		dev_err(&client->dev, "%s fail error: 0x%x\n",
+			__func__, hdl->error);
+		return hdl->error;
+	}
+
+	return 0;
+}
+
+static int dw9807_probe(struct i2c_client *client)
+{
+	struct dw9807_device *dw9807_dev;
+	int rval;
+
+	dw9807_dev = devm_kzalloc(&client->dev, sizeof(*dw9807_dev),
+				  GFP_KERNEL);
+	if (dw9807_dev == NULL)
+		return -ENOMEM;
+
+	v4l2_i2c_subdev_init(&dw9807_dev->sd, client, &dw9807_ops);
+	dw9807_dev->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
+	dw9807_dev->sd.internal_ops = &dw9807_int_ops;
+
+	rval = dw9807_init_controls(dw9807_dev);
+	if (rval)
+		goto err_cleanup;
+
+	rval = media_entity_pads_init(&dw9807_dev->sd.entity, 0, NULL);
+	if (rval < 0)
+		goto err_cleanup;
+
+	dw9807_dev->sd.entity.function = MEDIA_ENT_F_LENS;
+
+	rval = v4l2_async_register_subdev(&dw9807_dev->sd);
+	if (rval < 0)
+		goto err_cleanup;
+
+	pm_runtime_set_active(&client->dev);
+	pm_runtime_enable(&client->dev);
+	pm_runtime_idle(&client->dev);
+
+	return 0;
+
+err_cleanup:
+	dw9807_subdev_cleanup(dw9807_dev);
+
+	return rval;
+}
+
+static int dw9807_remove(struct i2c_client *client)
+{
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct dw9807_device *dw9807_dev = sd_to_dw9807_vcm(sd);
+
+	pm_runtime_disable(&client->dev);
+	pm_runtime_set_suspended(&client->dev);
+
+	dw9807_subdev_cleanup(dw9807_dev);
+
+	return 0;
+}
+
+/*
+ * This function sets the vcm position, so it consumes least current
+ * The lens position is gradually moved in units of DW9807_CTRL_STEPS,
+ * to make the movements smoothly.
+ */
+static int __maybe_unused dw9807_vcm_suspend(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct dw9807_device *dw9807_dev = sd_to_dw9807_vcm(sd);
+	const char tx_data[2] = { DW9807_CTL_ADDR, 0x01 };
+	int ret, val;
+
+	for (val = dw9807_dev->current_val & ~(DW9807_CTRL_STEPS - 1);
+	     val >= 0; val -= DW9807_CTRL_STEPS) {
+		ret = dw9807_set_dac(client, val);
+		if (ret)
+			dev_err_once(dev, "%s I2C failure: %d", __func__, ret);
+		usleep_range(DW9807_CTRL_DELAY_US, DW9807_CTRL_DELAY_US + 10);
+	}
+
+	/* Power down */
+	ret = i2c_master_send(client, tx_data, sizeof(tx_data));
+	if (ret < 0) {
+		dev_err(&client->dev, "I2C write CTL fail ret = %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * This function sets the vcm position to the value set by the user
+ * through v4l2_ctrl_ops s_ctrl handler
+ * The lens position is gradually moved in units of DW9807_CTRL_STEPS,
+ * to make the movements smoothly.
+ */
+static int  __maybe_unused dw9807_vcm_resume(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct dw9807_device *dw9807_dev = sd_to_dw9807_vcm(sd);
+	const char tx_data[2] = { DW9807_CTL_ADDR, 0x00 };
+	int ret, val;
+
+	/* Power on */
+	ret = i2c_master_send(client, tx_data, sizeof(tx_data));
+	if (ret < 0) {
+		dev_err(&client->dev, "I2C write CTL fail ret = %d\n", ret);
+		return ret;
+	}
+
+	for (val = dw9807_dev->current_val % DW9807_CTRL_STEPS;
+	     val < dw9807_dev->current_val + DW9807_CTRL_STEPS - 1;
+	     val += DW9807_CTRL_STEPS) {
+		ret = dw9807_set_dac(client, val);
+		if (ret)
+			dev_err_ratelimited(dev, "%s I2C failure: %d",
+						__func__, ret);
+		usleep_range(DW9807_CTRL_DELAY_US, DW9807_CTRL_DELAY_US + 10);
+	}
+
+	return 0;
+}
+
+static const struct of_device_id dw9807_of_table[] = {
+	{ .compatible = "dongwoon,dw9807-vcm" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, dw9807_of_table);
+
+static const struct dev_pm_ops dw9807_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(dw9807_vcm_suspend, dw9807_vcm_resume)
+	SET_RUNTIME_PM_OPS(dw9807_vcm_suspend, dw9807_vcm_resume, NULL)
+};
+
+static struct i2c_driver dw9807_i2c_driver = {
+	.driver = {
+		.name = "dw9807",
+		.pm = &dw9807_pm_ops,
+		.of_match_table = dw9807_of_table,
+	},
+	.probe_new = dw9807_probe,
+	.remove = dw9807_remove,
+};
+
+module_i2c_driver(dw9807_i2c_driver);
+
+MODULE_AUTHOR("Chiang, Alan <alanx.chiang@intel.com>");
+MODULE_DESCRIPTION("DW9807 VCM driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/i2c/et8ek8/et8ek8_driver.c b/drivers/media/i2c/et8ek8/et8ek8_driver.c
index e9eff9039ef5..37ef38947e01 100644
--- a/drivers/media/i2c/et8ek8/et8ek8_driver.c
+++ b/drivers/media/i2c/et8ek8/et8ek8_driver.c
@@ -1446,6 +1446,7 @@ static int et8ek8_probe(struct i2c_client *client,
 	sensor->subdev.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	sensor->subdev.internal_ops = &et8ek8_internal_ops;
 
+	sensor->subdev.entity.function = MEDIA_ENT_F_CAM_SENSOR;
 	sensor->pad.flags = MEDIA_PAD_FL_SOURCE;
 	ret = media_entity_pads_init(&sensor->subdev.entity, 1, &sensor->pad);
 	if (ret < 0) {
diff --git a/drivers/media/i2c/imx258.c b/drivers/media/i2c/imx258.c
index f3b124723aa0..31a1e2294843 100644
--- a/drivers/media/i2c/imx258.c
+++ b/drivers/media/i2c/imx258.c
@@ -1221,6 +1221,14 @@ static int imx258_probe(struct i2c_client *client)
 	if (val != 19200000)
 		return -EINVAL;
 
+	/*
+	 * Check that the device is mounted upside down. The driver only
+	 * supports a single pixel order right now.
+	 */
+	ret = device_property_read_u32(&client->dev, "rotation", &val);
+	if (ret || val != 180)
+		return -EINVAL;
+
 	imx258 = devm_kzalloc(&client->dev, sizeof(*imx258), GFP_KERNEL);
 	if (!imx258)
 		return -ENOMEM;
diff --git a/drivers/media/i2c/imx274.c b/drivers/media/i2c/imx274.c
index 63fb94e7da37..f8c70f1a34fe 100644
--- a/drivers/media/i2c/imx274.c
+++ b/drivers/media/i2c/imx274.c
@@ -5,6 +5,7 @@
  *
  * Leon Luo <leonl@leopardimaging.com>
  * Edwin Zou <edwinz@leopardimaging.com>
+ * Luca Ceresoli <luca@lucaceresoli.net>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -25,6 +26,7 @@
 #include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
 #include <linux/init.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of_gpio.h>
 #include <linux/regmap.h>
@@ -74,7 +76,7 @@
  */
 #define IMX274_MIN_EXPOSURE_TIME		(4 * 260 / 72)
 
-#define IMX274_DEFAULT_MODE			IMX274_MODE_3840X2160
+#define IMX274_DEFAULT_MODE			IMX274_BINNING_OFF
 #define IMX274_MAX_WIDTH			(3840)
 #define IMX274_MAX_HEIGHT			(2160)
 #define IMX274_MAX_FRAME_RATE			(120)
@@ -111,6 +113,20 @@
 #define IMX274_SHR_REG_LSB			0x300C /* SHR */
 #define IMX274_SVR_REG_MSB			0x300F /* SVR */
 #define IMX274_SVR_REG_LSB			0x300E /* SVR */
+#define IMX274_HTRIM_EN_REG			0x3037
+#define IMX274_HTRIM_START_REG_LSB		0x3038
+#define IMX274_HTRIM_START_REG_MSB		0x3039
+#define IMX274_HTRIM_END_REG_LSB		0x303A
+#define IMX274_HTRIM_END_REG_MSB		0x303B
+#define IMX274_VWIDCUTEN_REG			0x30DD
+#define IMX274_VWIDCUT_REG_LSB			0x30DE
+#define IMX274_VWIDCUT_REG_MSB			0x30DF
+#define IMX274_VWINPOS_REG_LSB			0x30E0
+#define IMX274_VWINPOS_REG_MSB			0x30E1
+#define IMX274_WRITE_VSIZE_REG_LSB		0x3130
+#define IMX274_WRITE_VSIZE_REG_MSB		0x3131
+#define IMX274_Y_OUT_SIZE_REG_LSB		0x3132
+#define IMX274_Y_OUT_SIZE_REG_MSB		0x3133
 #define IMX274_VMAX_REG_1			0x30FA /* VMAX, MSB */
 #define IMX274_VMAX_REG_2			0x30F9 /* VMAX */
 #define IMX274_VMAX_REG_3			0x30F8 /* VMAX, LSB */
@@ -140,17 +156,35 @@ static const struct regmap_config imx274_regmap_config = {
 	.cache_type = REGCACHE_RBTREE,
 };
 
-enum imx274_mode {
-	IMX274_MODE_3840X2160,
-	IMX274_MODE_1920X1080,
-	IMX274_MODE_1280X720,
+enum imx274_binning {
+	IMX274_BINNING_OFF,
+	IMX274_BINNING_2_1,
+	IMX274_BINNING_3_1,
 };
 
 /*
- * imx274 format related structure
+ * Parameters for each imx274 readout mode.
+ *
+ * These are the values to configure the sensor in one of the
+ * implemented modes.
+ *
+ * @init_regs: registers to initialize the mode
+ * @bin_ratio: downscale factor (e.g. 3 for 3:1 binning)
+ * @min_frame_len: Minimum frame length for each mode (see "Frame Rate
+ *                 Adjustment (CSI-2)" in the datasheet)
+ * @min_SHR: Minimum SHR register value (see "Shutter Setting (CSI-2)" in the
+ *           datasheet)
+ * @max_fps: Maximum frames per second
+ * @nocpiop: Number of clocks per internal offset period (see "Integration Time
+ *           in Each Readout Drive Mode (CSI-2)" in the datasheet)
  */
 struct imx274_frmfmt {
-	struct v4l2_frmsize_discrete size;
+	const struct reg_8 *init_regs;
+	unsigned int bin_ratio;
+	int min_frame_len;
+	int min_SHR;
+	int max_fps;
+	int nocpiop;
 };
 
 /*
@@ -197,31 +231,14 @@ static const struct reg_8 imx274_mode1_3840x2160_raw10[] = {
 	{0x3004, 0x01},
 	{0x3005, 0x01},
 	{0x3006, 0x00},
-	{0x3007, 0x02},
+	{0x3007, 0xa2},
 
 	{0x3018, 0xA2}, /* output XVS, HVS */
 
 	{0x306B, 0x05},
 	{0x30E2, 0x01},
-	{0x30F6, 0x07}, /* HMAX, 263 */
-	{0x30F7, 0x01}, /* HMAX */
-
-	{0x30dd, 0x01}, /* crop to 2160 */
-	{0x30de, 0x06},
-	{0x30df, 0x00},
-	{0x30e0, 0x12},
-	{0x30e1, 0x00},
-	{0x3037, 0x01}, /* to crop to 3840 */
-	{0x3038, 0x0c},
-	{0x3039, 0x00},
-	{0x303a, 0x0c},
-	{0x303b, 0x0f},
 
 	{0x30EE, 0x01},
-	{0x3130, 0x86},
-	{0x3131, 0x08},
-	{0x3132, 0x7E},
-	{0x3133, 0x08},
 	{0x3342, 0x0A},
 	{0x3343, 0x00},
 	{0x3344, 0x16},
@@ -255,32 +272,14 @@ static const struct reg_8 imx274_mode3_1920x1080_raw10[] = {
 	{0x3004, 0x02},
 	{0x3005, 0x21},
 	{0x3006, 0x00},
-	{0x3007, 0x11},
+	{0x3007, 0xb1},
 
 	{0x3018, 0xA2}, /* output XVS, HVS */
 
 	{0x306B, 0x05},
 	{0x30E2, 0x02},
 
-	{0x30F6, 0x04}, /* HMAX, 260 */
-	{0x30F7, 0x01}, /* HMAX */
-
-	{0x30dd, 0x01}, /* to crop to 1920x1080 */
-	{0x30de, 0x05},
-	{0x30df, 0x00},
-	{0x30e0, 0x04},
-	{0x30e1, 0x00},
-	{0x3037, 0x01},
-	{0x3038, 0x0c},
-	{0x3039, 0x00},
-	{0x303a, 0x0c},
-	{0x303b, 0x0f},
-
 	{0x30EE, 0x01},
-	{0x3130, 0x4E},
-	{0x3131, 0x04},
-	{0x3132, 0x46},
-	{0x3133, 0x04},
 	{0x3342, 0x0A},
 	{0x3343, 0x00},
 	{0x3344, 0x1A},
@@ -313,31 +312,14 @@ static const struct reg_8 imx274_mode5_1280x720_raw10[] = {
 	{0x3004, 0x03},
 	{0x3005, 0x31},
 	{0x3006, 0x00},
-	{0x3007, 0x09},
+	{0x3007, 0xa9},
 
 	{0x3018, 0xA2}, /* output XVS, HVS */
 
 	{0x306B, 0x05},
 	{0x30E2, 0x03},
 
-	{0x30F6, 0x04}, /* HMAX, 260 */
-	{0x30F7, 0x01}, /* HMAX */
-
-	{0x30DD, 0x01},
-	{0x30DE, 0x07},
-	{0x30DF, 0x00},
-	{0x40E0, 0x04},
-	{0x30E1, 0x00},
-	{0x3030, 0xD4},
-	{0x3031, 0x02},
-	{0x3032, 0xD0},
-	{0x3033, 0x02},
-
 	{0x30EE, 0x01},
-	{0x3130, 0xE2},
-	{0x3131, 0x02},
-	{0x3132, 0xDE},
-	{0x3133, 0x02},
 	{0x3342, 0x0A},
 	{0x3343, 0x00},
 	{0x3344, 0x1B},
@@ -476,58 +458,35 @@ static const struct reg_8 imx274_tp_regs[] = {
 	{IMX274_TABLE_END, 0x00}
 };
 
-static const struct reg_8 *mode_table[] = {
-	[IMX274_MODE_3840X2160]		= imx274_mode1_3840x2160_raw10,
-	[IMX274_MODE_1920X1080]		= imx274_mode3_1920x1080_raw10,
-	[IMX274_MODE_1280X720]		= imx274_mode5_1280x720_raw10,
-};
-
-/*
- * imx274 format related structure
- */
+/* nocpiop happens to be the same number for the implemented modes */
 static const struct imx274_frmfmt imx274_formats[] = {
-	{ {3840, 2160} },
-	{ {1920, 1080} },
-	{ {1280,  720} },
-};
-
-/*
- * minimal frame length for each mode
- * refer to datasheet section "Frame Rate Adjustment (CSI-2)"
- */
-static const int min_frame_len[] = {
-	4550, /* mode 1, 4K */
-	2310, /* mode 3, 1080p */
-	2310 /* mode 5, 720p */
-};
-
-/*
- * minimal numbers of SHR register
- * refer to datasheet table "Shutter Setting (CSI-2)"
- */
-static const int min_SHR[] = {
-	12, /* mode 1, 4K */
-	8, /* mode 3, 1080p */
-	8 /* mode 5, 720p */
-};
-
-static const int max_frame_rate[] = {
-	60, /* mode 1 , 4K */
-	120, /* mode 3, 1080p */
-	120 /* mode 5, 720p */
-};
-
-/*
- * Number of clocks per internal offset period
- * a constant based on mode
- * refer to section "Integration Time in Each Readout Drive Mode (CSI-2)"
- * in the datasheet
- * for the implemented 3 modes, it happens to be the same number
- */
-static const int nocpiop[] = {
-	112, /* mode 1 , 4K */
-	112, /* mode 3, 1080p */
-	112 /* mode 5, 720p */
+	{
+		/* mode 1, 4K */
+		.bin_ratio = 1,
+		.init_regs = imx274_mode1_3840x2160_raw10,
+		.min_frame_len = 4550,
+		.min_SHR = 12,
+		.max_fps = 60,
+		.nocpiop = 112,
+	},
+	{
+		/* mode 3, 1080p */
+		.bin_ratio = 2,
+		.init_regs = imx274_mode3_1920x1080_raw10,
+		.min_frame_len = 2310,
+		.min_SHR = 8,
+		.max_fps = 120,
+		.nocpiop = 112,
+	},
+	{
+		/* mode 5, 720p */
+		.bin_ratio = 3,
+		.init_regs = imx274_mode5_1280x720_raw10,
+		.min_frame_len = 2310,
+		.min_SHR = 8,
+		.max_fps = 120,
+		.nocpiop = 112,
+	},
 };
 
 /*
@@ -549,29 +508,40 @@ struct imx274_ctrls {
 /*
  * struct stim274 - imx274 device structure
  * @sd: V4L2 subdevice structure
- * @pd: Media pad structure
+ * @pad: Media pad structure
  * @client: Pointer to I2C client
  * @ctrls: imx274 control structure
+ * @crop: rect to be captured
+ * @compose: compose rect, i.e. output resolution
  * @format: V4L2 media bus frame format structure
+ *          (width and height are in sync with the compose rect)
  * @frame_rate: V4L2 frame rate structure
  * @regmap: Pointer to regmap structure
  * @reset_gpio: Pointer to reset gpio
  * @lock: Mutex structure
- * @mode_index: Resolution mode index
+ * @mode: Parameters for the selected readout mode
  */
 struct stimx274 {
 	struct v4l2_subdev sd;
 	struct media_pad pad;
 	struct i2c_client *client;
 	struct imx274_ctrls ctrls;
+	struct v4l2_rect crop;
 	struct v4l2_mbus_framefmt format;
 	struct v4l2_fract frame_interval;
 	struct regmap *regmap;
 	struct gpio_desc *reset_gpio;
 	struct mutex lock; /* mutex lock for operations */
-	u32 mode_index;
+	const struct imx274_frmfmt *mode;
 };
 
+#define IMX274_ROUND(dim, step, flags)			\
+	((flags) & V4L2_SEL_FLAG_GE			\
+	 ? roundup((dim), (step))			\
+	 : ((flags) & V4L2_SEL_FLAG_LE			\
+	    ? rounddown((dim), (step))			\
+	    : rounddown((dim) + (step) / 2, (step))))
+
 /*
  * Function declaration
  */
@@ -602,20 +572,18 @@ static inline struct stimx274 *to_imx274(struct v4l2_subdev *sd)
 }
 
 /*
- * imx274_regmap_util_write_table_8 - Function for writing register table
- * @regmap: Pointer to device reg map structure
- * @table: Table containing register values
- * @wait_ms_addr: Flag for performing delay
- * @end_addr: Flag for incating end of table
+ * Writing a register table
+ *
+ * @priv: Pointer to device
+ * @table: Table containing register values (with optional delays)
  *
  * This is used to write register table into sensor's reg map.
  *
  * Return: 0 on success, errors otherwise
  */
-static int imx274_regmap_util_write_table_8(struct regmap *regmap,
-					    const struct reg_8 table[],
-					    u16 wait_ms_addr, u16 end_addr)
+static int imx274_write_table(struct stimx274 *priv, const struct reg_8 table[])
 {
+	struct regmap *regmap = priv->regmap;
 	int err = 0;
 	const struct reg_8 *next;
 	u8 val;
@@ -627,8 +595,8 @@ static int imx274_regmap_util_write_table_8(struct regmap *regmap,
 
 	for (next = table;; next++) {
 		if ((next->addr != range_start + range_count) ||
-		    (next->addr == end_addr) ||
-		    (next->addr == wait_ms_addr) ||
+		    (next->addr == IMX274_TABLE_END) ||
+		    (next->addr == IMX274_TABLE_WAIT_MS) ||
 		    (range_count == max_range_vals)) {
 			if (range_count == 1)
 				err = regmap_write(regmap,
@@ -647,10 +615,10 @@ static int imx274_regmap_util_write_table_8(struct regmap *regmap,
 			range_count = 0;
 
 			/* Handle special address values */
-			if (next->addr == end_addr)
+			if (next->addr == IMX274_TABLE_END)
 				break;
 
-			if (next->addr == wait_ms_addr) {
+			if (next->addr == IMX274_TABLE_WAIT_MS) {
 				msleep_range(next->val);
 				continue;
 			}
@@ -697,25 +665,42 @@ static inline int imx274_write_reg(struct stimx274 *priv, u16 addr, u8 val)
 	return err;
 }
 
-static int imx274_write_table(struct stimx274 *priv, const struct reg_8 table[])
+/**
+ * Write a multibyte register.
+ *
+ * Uses a bulk write where possible.
+ *
+ * @priv: Pointer to device structure
+ * @addr: Address of the LSB register.  Other registers must be
+ *        consecutive, least-to-most significant.
+ * @val: Value to be written to the register (cpu endianness)
+ * @nbytes: Number of bits to write (range: [1..3])
+ */
+static int imx274_write_mbreg(struct stimx274 *priv, u16 addr, u32 val,
+			      size_t nbytes)
 {
-	return imx274_regmap_util_write_table_8(priv->regmap,
-		table, IMX274_TABLE_WAIT_MS, IMX274_TABLE_END);
+	__le32 val_le = cpu_to_le32(val);
+	int err;
+
+	err = regmap_bulk_write(priv->regmap, addr, &val_le, nbytes);
+	if (err)
+		dev_err(&priv->client->dev,
+			"%s : i2c bulk write failed, %x = %x (%zu bytes)\n",
+			__func__, addr, val, nbytes);
+	else
+		dev_dbg(&priv->client->dev,
+			"%s : addr 0x%x, val=0x%x (%zu bytes)\n",
+			__func__, addr, val, nbytes);
+	return err;
 }
 
 /*
- * imx274_mode_regs - Function for set mode registers per mode index
+ * Set mode registers to start stream.
  * @priv: Pointer to device structure
- * @mode: Mode index value
- *
- * This is used to start steam per mode index.
- * mode = 0, start stream for sensor Mode 1: 4K/raw10
- * mode = 1, start stream for sensor Mode 3: 1080p/raw10
- * mode = 2, start stream for sensor Mode 5: 720p/raw10
  *
  * Return: 0 on success, errors otherwise
  */
-static int imx274_mode_regs(struct stimx274 *priv, int mode)
+static int imx274_mode_regs(struct stimx274 *priv)
 {
 	int err = 0;
 
@@ -727,7 +712,7 @@ static int imx274_mode_regs(struct stimx274 *priv, int mode)
 	if (err)
 		return err;
 
-	err = imx274_write_table(priv, mode_table[mode]);
+	err = imx274_write_table(priv, priv->mode->init_regs);
 
 	return err;
 }
@@ -830,6 +815,114 @@ static int imx274_s_ctrl(struct v4l2_ctrl *ctrl)
 	return ret;
 }
 
+static int imx274_binning_goodness(struct stimx274 *imx274,
+				   int w, int ask_w,
+				   int h, int ask_h, u32 flags)
+{
+	struct device *dev = &imx274->client->dev;
+	const int goodness = 100000;
+	int val = 0;
+
+	if (flags & V4L2_SEL_FLAG_GE) {
+		if (w < ask_w)
+			val -= goodness;
+		if (h < ask_h)
+			val -= goodness;
+	}
+
+	if (flags & V4L2_SEL_FLAG_LE) {
+		if (w > ask_w)
+			val -= goodness;
+		if (h > ask_h)
+			val -= goodness;
+	}
+
+	val -= abs(w - ask_w);
+	val -= abs(h - ask_h);
+
+	dev_dbg(dev, "%s: ask %dx%d, size %dx%d, goodness %d\n",
+		__func__, ask_w, ask_h, w, h, val);
+
+	return val;
+}
+
+/**
+ * Helper function to change binning and set both compose and format.
+ *
+ * We have two entry points to change binning: set_fmt and
+ * set_selection(COMPOSE). Both have to compute the new output size
+ * and set it in both the compose rect and the frame format size. We
+ * also need to do the same things after setting cropping to restore
+ * 1:1 binning.
+ *
+ * This function contains the common code for these three cases, it
+ * has many arguments in order to accommodate the needs of all of
+ * them.
+ *
+ * Must be called with imx274->lock locked.
+ *
+ * @imx274: The device object
+ * @cfg:    The pad config we are editing for TRY requests
+ * @which:  V4L2_SUBDEV_FORMAT_ACTIVE or V4L2_SUBDEV_FORMAT_TRY from the caller
+ * @width:  Input-output parameter: set to the desired width before
+ *          the call, contains the chosen value after returning successfully
+ * @height: Input-output parameter for height (see @width)
+ * @flags:  Selection flags from struct v4l2_subdev_selection, or 0 if not
+ *          available (when called from set_fmt)
+ */
+static int __imx274_change_compose(struct stimx274 *imx274,
+				   struct v4l2_subdev_pad_config *cfg,
+				   u32 which,
+				   u32 *width,
+				   u32 *height,
+				   u32 flags)
+{
+	struct device *dev = &imx274->client->dev;
+	const struct v4l2_rect *cur_crop;
+	struct v4l2_mbus_framefmt *tgt_fmt;
+	unsigned int i;
+	const struct imx274_frmfmt *best_mode = &imx274_formats[0];
+	int best_goodness = INT_MIN;
+
+	if (which == V4L2_SUBDEV_FORMAT_TRY) {
+		cur_crop = &cfg->try_crop;
+		tgt_fmt = &cfg->try_fmt;
+	} else {
+		cur_crop = &imx274->crop;
+		tgt_fmt = &imx274->format;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(imx274_formats); i++) {
+		unsigned int ratio = imx274_formats[i].bin_ratio;
+
+		int goodness = imx274_binning_goodness(
+			imx274,
+			cur_crop->width / ratio, *width,
+			cur_crop->height / ratio, *height,
+			flags);
+
+		if (goodness >= best_goodness) {
+			best_goodness = goodness;
+			best_mode = &imx274_formats[i];
+		}
+	}
+
+	*width = cur_crop->width / best_mode->bin_ratio;
+	*height = cur_crop->height / best_mode->bin_ratio;
+
+	if (which == V4L2_SUBDEV_FORMAT_ACTIVE)
+		imx274->mode = best_mode;
+
+	dev_dbg(dev, "%s: selected %u:1 binning\n",
+		__func__, best_mode->bin_ratio);
+
+	tgt_fmt->width = *width;
+	tgt_fmt->height = *height;
+	tgt_fmt->field = V4L2_FIELD_NONE;
+
+	return 0;
+}
+
 /**
  * imx274_get_fmt - Get the pad format
  * @sd: Pointer to V4L2 Sub device structure
@@ -868,45 +961,238 @@ static int imx274_set_fmt(struct v4l2_subdev *sd,
 {
 	struct v4l2_mbus_framefmt *fmt = &format->format;
 	struct stimx274 *imx274 = to_imx274(sd);
-	struct i2c_client *client = imx274->client;
-	int index;
-
-	dev_dbg(&client->dev,
-		"%s: width = %d height = %d code = %d\n",
-		__func__, fmt->width, fmt->height, fmt->code);
+	int err = 0;
 
 	mutex_lock(&imx274->lock);
 
-	for (index = 0; index < ARRAY_SIZE(imx274_formats); index++) {
-		if (imx274_formats[index].size.width == fmt->width &&
-		    imx274_formats[index].size.height == fmt->height)
-			break;
-	}
+	err = __imx274_change_compose(imx274, cfg, format->which,
+				      &fmt->width, &fmt->height, 0);
 
-	if (index >= ARRAY_SIZE(imx274_formats)) {
-		/* default to first format */
-		index = 0;
-	}
-
-	imx274->mode_index = index;
+	if (err)
+		goto out;
 
-	if (fmt->width > IMX274_MAX_WIDTH)
-		fmt->width = IMX274_MAX_WIDTH;
-	if (fmt->height > IMX274_MAX_HEIGHT)
-		fmt->height = IMX274_MAX_HEIGHT;
-	fmt->width = fmt->width & (~IMX274_MASK_LSB_2_BITS);
-	fmt->height = fmt->height & (~IMX274_MASK_LSB_2_BITS);
+	/*
+	 * __imx274_change_compose already set width and height in the
+	 * applicable format, but we need to keep all other format
+	 * values, so do a full copy here
+	 */
 	fmt->field = V4L2_FIELD_NONE;
-
 	if (format->which == V4L2_SUBDEV_FORMAT_TRY)
 		cfg->try_fmt = *fmt;
 	else
 		imx274->format = *fmt;
 
+out:
+	mutex_unlock(&imx274->lock);
+
+	return err;
+}
+
+static int imx274_get_selection(struct v4l2_subdev *sd,
+				struct v4l2_subdev_pad_config *cfg,
+				struct v4l2_subdev_selection *sel)
+{
+	struct stimx274 *imx274 = to_imx274(sd);
+	const struct v4l2_rect *src_crop;
+	const struct v4l2_mbus_framefmt *src_fmt;
+	int ret = 0;
+
+	if (sel->pad != 0)
+		return -EINVAL;
+
+	if (sel->target == V4L2_SEL_TGT_CROP_BOUNDS) {
+		sel->r.left = 0;
+		sel->r.top = 0;
+		sel->r.width = IMX274_MAX_WIDTH;
+		sel->r.height = IMX274_MAX_HEIGHT;
+		return 0;
+	}
+
+	if (sel->which == V4L2_SUBDEV_FORMAT_TRY) {
+		src_crop = &cfg->try_crop;
+		src_fmt = &cfg->try_fmt;
+	} else {
+		src_crop = &imx274->crop;
+		src_fmt = &imx274->format;
+	}
+
+	mutex_lock(&imx274->lock);
+
+	switch (sel->target) {
+	case V4L2_SEL_TGT_CROP:
+		sel->r = *src_crop;
+		break;
+	case V4L2_SEL_TGT_COMPOSE_BOUNDS:
+		sel->r.top = 0;
+		sel->r.left = 0;
+		sel->r.width = src_crop->width;
+		sel->r.height = src_crop->height;
+		break;
+	case V4L2_SEL_TGT_COMPOSE:
+		sel->r.top = 0;
+		sel->r.left = 0;
+		sel->r.width = src_fmt->width;
+		sel->r.height = src_fmt->height;
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	mutex_unlock(&imx274->lock);
+
+	return ret;
+}
+
+static int imx274_set_selection_crop(struct stimx274 *imx274,
+				     struct v4l2_subdev_pad_config *cfg,
+				     struct v4l2_subdev_selection *sel)
+{
+	struct v4l2_rect *tgt_crop;
+	struct v4l2_rect new_crop;
+	bool size_changed;
+
+	/*
+	 * h_step could be 12 or 24 depending on the binning. But we
+	 * won't know the binning until we choose the mode later in
+	 * __imx274_change_compose(). Thus let's be safe and use the
+	 * most conservative value in all cases.
+	 */
+	const u32 h_step = 24;
+
+	new_crop.width = min_t(u32,
+			       IMX274_ROUND(sel->r.width, h_step, sel->flags),
+			       IMX274_MAX_WIDTH);
+
+	/* Constraint: HTRIMMING_END - HTRIMMING_START >= 144 */
+	if (new_crop.width < 144)
+		new_crop.width = 144;
+
+	new_crop.left = min_t(u32,
+			      IMX274_ROUND(sel->r.left, h_step, 0),
+			      IMX274_MAX_WIDTH - new_crop.width);
+
+	new_crop.height = min_t(u32,
+				IMX274_ROUND(sel->r.height, 2, sel->flags),
+				IMX274_MAX_HEIGHT);
+
+	new_crop.top = min_t(u32, IMX274_ROUND(sel->r.top, 2, 0),
+			     IMX274_MAX_HEIGHT - new_crop.height);
+
+	sel->r = new_crop;
+
+	if (sel->which == V4L2_SUBDEV_FORMAT_TRY)
+		tgt_crop = &cfg->try_crop;
+	else
+		tgt_crop = &imx274->crop;
+
+	mutex_lock(&imx274->lock);
+
+	size_changed = (new_crop.width != tgt_crop->width ||
+			new_crop.height != tgt_crop->height);
+
+	/* __imx274_change_compose needs the new size in *tgt_crop */
+	*tgt_crop = new_crop;
+
+	/* if crop size changed then reset the output image size */
+	if (size_changed)
+		__imx274_change_compose(imx274, cfg, sel->which,
+					&new_crop.width, &new_crop.height,
+					sel->flags);
+
 	mutex_unlock(&imx274->lock);
+
 	return 0;
 }
 
+static int imx274_set_selection(struct v4l2_subdev *sd,
+				struct v4l2_subdev_pad_config *cfg,
+				struct v4l2_subdev_selection *sel)
+{
+	struct stimx274 *imx274 = to_imx274(sd);
+
+	if (sel->pad != 0)
+		return -EINVAL;
+
+	if (sel->target == V4L2_SEL_TGT_CROP)
+		return imx274_set_selection_crop(imx274, cfg, sel);
+
+	if (sel->target == V4L2_SEL_TGT_COMPOSE) {
+		int err;
+
+		mutex_lock(&imx274->lock);
+		err =  __imx274_change_compose(imx274, cfg, sel->which,
+					       &sel->r.width, &sel->r.height,
+					       sel->flags);
+		mutex_unlock(&imx274->lock);
+
+		/*
+		 * __imx274_change_compose already set width and
+		 * height in set->r, we still need to set top-left
+		 */
+		if (!err) {
+			sel->r.top = 0;
+			sel->r.left = 0;
+		}
+
+		return err;
+	}
+
+	return -EINVAL;
+}
+
+static int imx274_apply_trimming(struct stimx274 *imx274)
+{
+	u32 h_start;
+	u32 h_end;
+	u32 hmax;
+	u32 v_cut;
+	s32 v_pos;
+	u32 write_v_size;
+	u32 y_out_size;
+	int err;
+
+	h_start = imx274->crop.left + 12;
+	h_end = h_start + imx274->crop.width;
+
+	/* Use the minimum allowed value of HMAX */
+	/* Note: except in mode 1, (width / 16 + 23) is always < hmax_min */
+	/* Note: 260 is the minimum HMAX in all implemented modes */
+	hmax = max_t(u32, 260, (imx274->crop.width) / 16 + 23);
+
+	/* invert v_pos if VFLIP */
+	v_pos = imx274->ctrls.vflip->cur.val ?
+		(-imx274->crop.top / 2) : (imx274->crop.top / 2);
+	v_cut = (IMX274_MAX_HEIGHT - imx274->crop.height) / 2;
+	write_v_size = imx274->crop.height + 22;
+	y_out_size   = imx274->crop.height + 14;
+
+	err = imx274_write_mbreg(imx274, IMX274_HMAX_REG_LSB, hmax, 2);
+	if (!err)
+		err = imx274_write_mbreg(imx274, IMX274_HTRIM_EN_REG, 1, 1);
+	if (!err)
+		err = imx274_write_mbreg(imx274, IMX274_HTRIM_START_REG_LSB,
+					 h_start, 2);
+	if (!err)
+		err = imx274_write_mbreg(imx274, IMX274_HTRIM_END_REG_LSB,
+					 h_end, 2);
+	if (!err)
+		err = imx274_write_mbreg(imx274, IMX274_VWIDCUTEN_REG, 1, 1);
+	if (!err)
+		err = imx274_write_mbreg(imx274, IMX274_VWIDCUT_REG_LSB,
+					 v_cut, 2);
+	if (!err)
+		err = imx274_write_mbreg(imx274, IMX274_VWINPOS_REG_LSB,
+					 v_pos, 2);
+	if (!err)
+		err = imx274_write_mbreg(imx274, IMX274_WRITE_VSIZE_REG_LSB,
+					 write_v_size, 2);
+	if (!err)
+		err = imx274_write_mbreg(imx274, IMX274_Y_OUT_SIZE_REG_LSB,
+					 y_out_size, 2);
+
+	return err;
+}
+
 /**
  * imx274_g_frame_interval - Get the frame interval
  * @sd: Pointer to V4L2 Sub device structure
@@ -1035,14 +1321,19 @@ static int imx274_s_stream(struct v4l2_subdev *sd, int on)
 	struct stimx274 *imx274 = to_imx274(sd);
 	int ret = 0;
 
-	dev_dbg(&imx274->client->dev, "%s : %s, mode index = %d\n", __func__,
-		on ? "Stream Start" : "Stream Stop", imx274->mode_index);
+	dev_dbg(&imx274->client->dev, "%s : %s, mode index = %td\n", __func__,
+		on ? "Stream Start" : "Stream Stop",
+		imx274->mode - &imx274_formats[0]);
 
 	mutex_lock(&imx274->lock);
 
 	if (on) {
 		/* load mode registers */
-		ret = imx274_mode_regs(imx274, imx274->mode_index);
+		ret = imx274_mode_regs(imx274);
+		if (ret)
+			goto fail;
+
+		ret = imx274_apply_trimming(imx274);
 		if (ret)
 			goto fail;
 
@@ -1075,8 +1366,7 @@ static int imx274_s_stream(struct v4l2_subdev *sd, int on)
 	}
 
 	mutex_unlock(&imx274->lock);
-	dev_dbg(&imx274->client->dev,
-		"%s : Done: mode = %d\n", __func__, imx274->mode_index);
+	dev_dbg(&imx274->client->dev, "%s : Done\n", __func__);
 	return 0;
 
 fail:
@@ -1146,14 +1436,14 @@ static int imx274_clamp_coarse_time(struct stimx274 *priv, u32 *val,
 	if (err)
 		return err;
 
-	if (*frame_length < min_frame_len[priv->mode_index])
-		*frame_length = min_frame_len[priv->mode_index];
+	if (*frame_length < priv->mode->min_frame_len)
+		*frame_length =  priv->mode->min_frame_len;
 
 	*val = *frame_length - *val; /* convert to raw shr */
 	if (*val > *frame_length - IMX274_SHR_LIMIT_CONST)
 		*val = *frame_length - IMX274_SHR_LIMIT_CONST;
-	else if (*val < min_SHR[priv->mode_index])
-		*val = min_SHR[priv->mode_index];
+	else if (*val < priv->mode->min_SHR)
+		*val = priv->mode->min_SHR;
 
 	return 0;
 }
@@ -1182,15 +1472,6 @@ static int imx274_set_digital_gain(struct stimx274 *priv, u32 dgain)
 				reg_val & IMX274_MASK_LSB_4_BITS);
 }
 
-static inline void imx274_calculate_gain_regs(struct reg_8 regs[2], u16 gain)
-{
-	regs->addr = IMX274_ANALOG_GAIN_ADDR_MSB;
-	regs->val = (gain >> IMX274_SHIFT_8_BITS) & IMX274_MASK_LSB_3_BITS;
-
-	(regs + 1)->addr = IMX274_ANALOG_GAIN_ADDR_LSB;
-	(regs + 1)->val = (gain) & IMX274_MASK_LSB_8_BITS;
-}
-
 /*
  * imx274_set_gain - Function called when setting gain
  * @priv: Pointer to device structure
@@ -1204,10 +1485,8 @@ static inline void imx274_calculate_gain_regs(struct reg_8 regs[2], u16 gain)
  */
 static int imx274_set_gain(struct stimx274 *priv, struct v4l2_ctrl *ctrl)
 {
-	struct reg_8 reg_list[2];
 	int err;
 	u32 gain, analog_gain, digital_gain, gain_reg;
-	int i;
 
 	gain = (u32)(ctrl->val);
 
@@ -1248,14 +1527,10 @@ static int imx274_set_gain(struct stimx274 *priv, struct v4l2_ctrl *ctrl)
 	if (gain_reg > IMX274_GAIN_REG_MAX)
 		gain_reg = IMX274_GAIN_REG_MAX;
 
-	imx274_calculate_gain_regs(reg_list, (u16)gain_reg);
-
-	for (i = 0; i < ARRAY_SIZE(reg_list); i++) {
-		err = imx274_write_reg(priv, reg_list[i].addr,
-				       reg_list[i].val);
-		if (err)
-			goto fail;
-	}
+	err = imx274_write_mbreg(priv, IMX274_ANALOG_GAIN_ADDR_LSB, gain_reg,
+				 2);
+	if (err)
+		goto fail;
 
 	if (IMX274_GAIN_CONST - gain_reg == 0) {
 		err = -EINVAL;
@@ -1277,16 +1552,6 @@ fail:
 	return err;
 }
 
-static inline void imx274_calculate_coarse_time_regs(struct reg_8 regs[2],
-						     u32 coarse_time)
-{
-	regs->addr = IMX274_SHR_REG_MSB;
-	regs->val = (coarse_time >> IMX274_SHIFT_8_BITS)
-			& IMX274_MASK_LSB_8_BITS;
-	(regs + 1)->addr = IMX274_SHR_REG_LSB;
-	(regs + 1)->val = (coarse_time) & IMX274_MASK_LSB_8_BITS;
-}
-
 /*
  * imx274_set_coarse_time - Function called when setting SHR value
  * @priv: Pointer to device structure
@@ -1298,10 +1563,8 @@ static inline void imx274_calculate_coarse_time_regs(struct reg_8 regs[2],
  */
 static int imx274_set_coarse_time(struct stimx274 *priv, u32 *val)
 {
-	struct reg_8 reg_list[2];
 	int err;
 	u32 coarse_time, frame_length;
-	int i;
 
 	coarse_time = *val;
 
@@ -1310,16 +1573,9 @@ static int imx274_set_coarse_time(struct stimx274 *priv, u32 *val)
 	if (err)
 		goto fail;
 
-	/* prepare SHR registers */
-	imx274_calculate_coarse_time_regs(reg_list, coarse_time);
-
-	/* write to SHR registers */
-	for (i = 0; i < ARRAY_SIZE(reg_list); i++) {
-		err = imx274_write_reg(priv, reg_list[i].addr,
-				       reg_list[i].val);
-		if (err)
-			goto fail;
-	}
+	err = imx274_write_mbreg(priv, IMX274_SHR_REG_LSB, coarse_time, 2);
+	if (err)
+		goto fail;
 
 	*val = frame_length - coarse_time;
 	return 0;
@@ -1365,7 +1621,7 @@ static int imx274_set_exposure(struct stimx274 *priv, int val)
 	}
 
 	coarse_time = (IMX274_PIXCLK_CONST1 / IMX274_PIXCLK_CONST2 * val
-			- nocpiop[priv->mode_index]) / hmax;
+			- priv->mode->nocpiop) / hmax;
 
 	/* step 2: convert exposure_time into SHR value */
 
@@ -1375,7 +1631,7 @@ static int imx274_set_exposure(struct stimx274 *priv, int val)
 		goto fail;
 
 	priv->ctrls.exposure->val =
-			(coarse_time * hmax + nocpiop[priv->mode_index])
+			(coarse_time * hmax + priv->mode->nocpiop)
 			/ (IMX274_PIXCLK_CONST1 / IMX274_PIXCLK_CONST2);
 
 	dev_dbg(&priv->client->dev,
@@ -1448,19 +1704,6 @@ static int imx274_set_test_pattern(struct stimx274 *priv, int val)
 	return err;
 }
 
-static inline void imx274_calculate_frame_length_regs(struct reg_8 regs[3],
-						      u32 frame_length)
-{
-	regs->addr = IMX274_VMAX_REG_1;
-	regs->val = (frame_length >> IMX274_SHIFT_16_BITS)
-			& IMX274_MASK_LSB_4_BITS;
-	(regs + 1)->addr = IMX274_VMAX_REG_2;
-	(regs + 1)->val = (frame_length >> IMX274_SHIFT_8_BITS)
-			& IMX274_MASK_LSB_8_BITS;
-	(regs + 2)->addr = IMX274_VMAX_REG_3;
-	(regs + 2)->val = (frame_length) & IMX274_MASK_LSB_8_BITS;
-}
-
 /*
  * imx274_set_frame_length - Function called when setting frame length
  * @priv: Pointer to device structure
@@ -1472,23 +1715,17 @@ static inline void imx274_calculate_frame_length_regs(struct reg_8 regs[3],
  */
 static int imx274_set_frame_length(struct stimx274 *priv, u32 val)
 {
-	struct reg_8 reg_list[3];
 	int err;
 	u32 frame_length;
-	int i;
 
 	dev_dbg(&priv->client->dev, "%s : input length = %d\n",
 		__func__, val);
 
 	frame_length = (u32)val;
 
-	imx274_calculate_frame_length_regs(reg_list, frame_length);
-	for (i = 0; i < ARRAY_SIZE(reg_list); i++) {
-		err = imx274_write_reg(priv, reg_list[i].addr,
-				       reg_list[i].val);
-		if (err)
-			goto fail;
-	}
+	err = imx274_write_mbreg(priv, IMX274_VMAX_REG_3, frame_length, 3);
+	if (err)
+		goto fail;
 
 	return 0;
 
@@ -1529,10 +1766,9 @@ static int imx274_set_frame_interval(struct stimx274 *priv,
 				/ frame_interval.numerator);
 
 	/* boundary check */
-	if (req_frame_rate > max_frame_rate[priv->mode_index]) {
+	if (req_frame_rate > priv->mode->max_fps) {
 		frame_interval.numerator = 1;
-		frame_interval.denominator =
-					max_frame_rate[priv->mode_index];
+		frame_interval.denominator = priv->mode->max_fps;
 	} else if (req_frame_rate < IMX274_MIN_FRAME_RATE) {
 		frame_interval.numerator = 1;
 		frame_interval.denominator = IMX274_MIN_FRAME_RATE;
@@ -1589,6 +1825,8 @@ fail:
 static const struct v4l2_subdev_pad_ops imx274_pad_ops = {
 	.get_fmt = imx274_get_fmt,
 	.set_fmt = imx274_set_fmt,
+	.get_selection = imx274_get_selection,
+	.set_selection = imx274_set_selection,
 };
 
 static const struct v4l2_subdev_video_ops imx274_video_ops = {
@@ -1632,6 +1870,18 @@ static int imx274_probe(struct i2c_client *client,
 
 	mutex_init(&imx274->lock);
 
+	/* initialize format */
+	imx274->mode = &imx274_formats[IMX274_DEFAULT_MODE];
+	imx274->crop.width = IMX274_MAX_WIDTH;
+	imx274->crop.height = IMX274_MAX_HEIGHT;
+	imx274->format.width = imx274->crop.width / imx274->mode->bin_ratio;
+	imx274->format.height = imx274->crop.height / imx274->mode->bin_ratio;
+	imx274->format.field = V4L2_FIELD_NONE;
+	imx274->format.code = MEDIA_BUS_FMT_SRGGB10_1X10;
+	imx274->format.colorspace = V4L2_COLORSPACE_SRGB;
+	imx274->frame_interval.numerator = 1;
+	imx274->frame_interval.denominator = IMX274_DEF_FRAME_RATE;
+
 	/* initialize regmap */
 	imx274->regmap = devm_regmap_init_i2c(client, &imx274_regmap_config);
 	if (IS_ERR(imx274->regmap)) {
@@ -1720,16 +1970,6 @@ static int imx274_probe(struct i2c_client *client,
 		goto err_ctrls;
 	}
 
-	/* initialize format */
-	imx274->mode_index = IMX274_MODE_3840X2160;
-	imx274->format.width = imx274_formats[0].size.width;
-	imx274->format.height = imx274_formats[0].size.height;
-	imx274->format.field = V4L2_FIELD_NONE;
-	imx274->format.code = MEDIA_BUS_FMT_SRGGB10_1X10;
-	imx274->format.colorspace = V4L2_COLORSPACE_SRGB;
-	imx274->frame_interval.numerator = 1;
-	imx274->frame_interval.denominator = IMX274_DEF_FRAME_RATE;
-
 	/* load default control values */
 	ret = imx274_load_default(imx274);
 	if (ret) {
diff --git a/drivers/media/i2c/lm3560.c b/drivers/media/i2c/lm3560.c
index b600e03aa94b..49c6644cbba7 100644
--- a/drivers/media/i2c/lm3560.c
+++ b/drivers/media/i2c/lm3560.c
@@ -1,6 +1,6 @@
 /*
  * drivers/media/i2c/lm3560.c
- * General device driver for TI lm3560, FLASH LED Driver
+ * General device driver for TI lm3559, lm3560, FLASH LED Driver
  *
  * Copyright (C) 2013 Texas Instruments
  *
@@ -465,6 +465,7 @@ static int lm3560_remove(struct i2c_client *client)
 }
 
 static const struct i2c_device_id lm3560_id_table[] = {
+	{LM3559_NAME, 0},
 	{LM3560_NAME, 0},
 	{}
 };
diff --git a/drivers/media/i2c/mt9m032.c b/drivers/media/i2c/mt9m032.c
index 6a9e068462fd..b385f2b632ad 100644
--- a/drivers/media/i2c/mt9m032.c
+++ b/drivers/media/i2c/mt9m032.c
@@ -793,6 +793,7 @@ static int mt9m032_probe(struct i2c_client *client,
 	v4l2_ctrl_cluster(2, &sensor->hflip);
 
 	sensor->subdev.ctrl_handler = &sensor->ctrls;
+	sensor->subdev.entity.function = MEDIA_ENT_F_CAM_SENSOR;
 	sensor->pad.flags = MEDIA_PAD_FL_SOURCE;
 	ret = media_entity_pads_init(&sensor->subdev.entity, 1, &sensor->pad);
 	if (ret < 0)
diff --git a/drivers/media/i2c/mt9p031.c b/drivers/media/i2c/mt9p031.c
index 91d822fc4443..715be3632b01 100644
--- a/drivers/media/i2c/mt9p031.c
+++ b/drivers/media/i2c/mt9p031.c
@@ -1111,6 +1111,7 @@ static int mt9p031_probe(struct i2c_client *client,
 	v4l2_i2c_subdev_init(&mt9p031->subdev, client, &mt9p031_subdev_ops);
 	mt9p031->subdev.internal_ops = &mt9p031_subdev_internal_ops;
 
+	mt9p031->subdev.entity.function = MEDIA_ENT_F_CAM_SENSOR;
 	mt9p031->pad.flags = MEDIA_PAD_FL_SOURCE;
 	ret = media_entity_pads_init(&mt9p031->subdev.entity, 1, &mt9p031->pad);
 	if (ret < 0)
diff --git a/drivers/media/i2c/mt9t001.c b/drivers/media/i2c/mt9t001.c
index 9d981d9f5686..f683d2cb0486 100644
--- a/drivers/media/i2c/mt9t001.c
+++ b/drivers/media/i2c/mt9t001.c
@@ -943,6 +943,7 @@ static int mt9t001_probe(struct i2c_client *client,
 	mt9t001->subdev.internal_ops = &mt9t001_subdev_internal_ops;
 	mt9t001->subdev.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 
+	mt9t001->subdev.entity.function = MEDIA_ENT_F_CAM_SENSOR;
 	mt9t001->pad.flags = MEDIA_PAD_FL_SOURCE;
 	ret = media_entity_pads_init(&mt9t001->subdev.entity, 1, &mt9t001->pad);
 
diff --git a/drivers/media/i2c/mt9v032.c b/drivers/media/i2c/mt9v032.c
index 4de63b2df334..f74730d24d8f 100644
--- a/drivers/media/i2c/mt9v032.c
+++ b/drivers/media/i2c/mt9v032.c
@@ -1162,6 +1162,7 @@ static int mt9v032_probe(struct i2c_client *client,
 	mt9v032->subdev.internal_ops = &mt9v032_subdev_internal_ops;
 	mt9v032->subdev.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 
+	mt9v032->subdev.entity.function = MEDIA_ENT_F_CAM_SENSOR;
 	mt9v032->pad.flags = MEDIA_PAD_FL_SOURCE;
 	ret = media_entity_pads_init(&mt9v032->subdev.entity, 1, &mt9v032->pad);
 	if (ret < 0)
diff --git a/drivers/media/i2c/mt9v111.c b/drivers/media/i2c/mt9v111.c
new file mode 100644
index 000000000000..b5410aeb5fe2
--- /dev/null
+++ b/drivers/media/i2c/mt9v111.c
@@ -0,0 +1,1298 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * V4L2 sensor driver for Aptina MT9V111 image sensor
+ * Copyright (C) 2018 Jacopo Mondi <jacopo@jmondi.org>
+ *
+ * Based on mt9v032 driver
+ * Copyright (C) 2010, Laurent Pinchart <laurent.pinchart@ideasonboard.com>
+ * Copyright (C) 2008, Guennadi Liakhovetski <kernel@pengutronix.de>
+ *
+ * Based on mt9v011 driver
+ * Copyright (c) 2009 Mauro Carvalho Chehab <mchehab@kernel.org>
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/videodev2.h>
+#include <linux/v4l2-mediabus.h>
+#include <linux/module.h>
+
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-fwnode.h>
+#include <media/v4l2-image-sizes.h>
+#include <media/v4l2-subdev.h>
+
+/*
+ * MT9V111 is a 1/4-Inch CMOS digital image sensor with an integrated
+ * Image Flow Processing (IFP) engine and a sensor core loosely based on
+ * MT9V011.
+ *
+ * The IFP can produce several output image formats from the sensor core
+ * output. This driver currently supports only YUYV format permutations.
+ *
+ * The driver allows manual frame rate control through s_frame_interval subdev
+ * operation or V4L2_CID_V/HBLANK controls, but it is known that the
+ * auto-exposure algorithm might modify the programmed frame rate. While the
+ * driver initially programs the sensor with auto-exposure and
+ * auto-white-balancing enabled, it is possible to disable them and more
+ * precisely control the frame rate.
+ *
+ * While it seems possible to instruct the auto-exposure control algorithm to
+ * respect a programmed frame rate when adjusting the pixel integration time,
+ * registers controlling this feature are not documented in the public
+ * available sensor manual used to develop this driver (09005aef80e90084,
+ * MT9V111_1.fm - Rev. G 1/05 EN).
+ */
+
+#define MT9V111_CHIP_ID_HIGH				0x82
+#define MT9V111_CHIP_ID_LOW				0x3a
+
+#define MT9V111_R01_ADDR_SPACE				0x01
+#define MT9V111_R01_IFP					0x01
+#define MT9V111_R01_CORE				0x04
+
+#define MT9V111_IFP_R06_OPMODE_CTRL			0x06
+#define		MT9V111_IFP_R06_OPMODE_CTRL_AWB_EN	BIT(1)
+#define		MT9V111_IFP_R06_OPMODE_CTRL_AE_EN	BIT(14)
+#define MT9V111_IFP_R07_IFP_RESET			0x07
+#define		MT9V111_IFP_R07_IFP_RESET_MASK		BIT(0)
+#define MT9V111_IFP_R08_OUTFMT_CTRL			0x08
+#define		MT9V111_IFP_R08_OUTFMT_CTRL_FLICKER	BIT(11)
+#define		MT9V111_IFP_R08_OUTFMT_CTRL_PCLK	BIT(5)
+#define MT9V111_IFP_R3A_OUTFMT_CTRL2			0x3a
+#define		MT9V111_IFP_R3A_OUTFMT_CTRL2_SWAP_CBCR	BIT(0)
+#define		MT9V111_IFP_R3A_OUTFMT_CTRL2_SWAP_YC	BIT(1)
+#define		MT9V111_IFP_R3A_OUTFMT_CTRL2_SWAP_MASK	GENMASK(2, 0)
+#define MT9V111_IFP_RA5_HPAN				0xa5
+#define MT9V111_IFP_RA6_HZOOM				0xa6
+#define MT9V111_IFP_RA7_HOUT				0xa7
+#define MT9V111_IFP_RA8_VPAN				0xa8
+#define MT9V111_IFP_RA9_VZOOM				0xa9
+#define MT9V111_IFP_RAA_VOUT				0xaa
+#define MT9V111_IFP_DECIMATION_MASK			GENMASK(9, 0)
+#define MT9V111_IFP_DECIMATION_FREEZE			BIT(15)
+
+#define MT9V111_CORE_R03_WIN_HEIGHT			0x03
+#define		MT9V111_CORE_R03_WIN_V_OFFS		2
+#define MT9V111_CORE_R04_WIN_WIDTH			0x04
+#define		MT9V111_CORE_R04_WIN_H_OFFS		114
+#define MT9V111_CORE_R05_HBLANK				0x05
+#define		MT9V111_CORE_R05_MIN_HBLANK		0x09
+#define		MT9V111_CORE_R05_MAX_HBLANK		GENMASK(9, 0)
+#define		MT9V111_CORE_R05_DEF_HBLANK		0x26
+#define MT9V111_CORE_R06_VBLANK				0x06
+#define		MT9V111_CORE_R06_MIN_VBLANK		0x03
+#define		MT9V111_CORE_R06_MAX_VBLANK		GENMASK(11, 0)
+#define		MT9V111_CORE_R06_DEF_VBLANK		0x04
+#define MT9V111_CORE_R07_OUT_CTRL			0x07
+#define		MT9V111_CORE_R07_OUT_CTRL_SAMPLE	BIT(4)
+#define MT9V111_CORE_R09_PIXEL_INT			0x09
+#define		MT9V111_CORE_R09_PIXEL_INT_MASK		GENMASK(11, 0)
+#define MT9V111_CORE_R0D_CORE_RESET			0x0d
+#define		MT9V111_CORE_R0D_CORE_RESET_MASK	BIT(0)
+#define MT9V111_CORE_RFF_CHIP_VER			0xff
+
+#define MT9V111_PIXEL_ARRAY_WIDTH			640
+#define MT9V111_PIXEL_ARRAY_HEIGHT			480
+
+#define MT9V111_MAX_CLKIN				27000000
+
+/* The default sensor configuration at startup time. */
+static struct v4l2_mbus_framefmt mt9v111_def_fmt = {
+	.width		= 640,
+	.height		= 480,
+	.code		= MEDIA_BUS_FMT_UYVY8_2X8,
+	.field		= V4L2_FIELD_NONE,
+	.colorspace	= V4L2_COLORSPACE_SRGB,
+	.ycbcr_enc	= V4L2_YCBCR_ENC_601,
+	.quantization	= V4L2_QUANTIZATION_LIM_RANGE,
+	.xfer_func	= V4L2_XFER_FUNC_SRGB,
+};
+
+struct mt9v111_dev {
+	struct device *dev;
+	struct i2c_client *client;
+
+	u8 addr_space;
+
+	struct v4l2_subdev sd;
+#if IS_ENABLED(CONFIG_MEDIA_CONTROLLER)
+	struct media_pad pad;
+#endif
+
+	struct v4l2_ctrl *auto_awb;
+	struct v4l2_ctrl *auto_exp;
+	struct v4l2_ctrl *hblank;
+	struct v4l2_ctrl *vblank;
+	struct v4l2_ctrl_handler ctrls;
+
+	/* Output image format and sizes. */
+	struct v4l2_mbus_framefmt fmt;
+	unsigned int fps;
+
+	/* Protects power up/down sequences. */
+	struct mutex pwr_mutex;
+	int pwr_count;
+
+	/* Protects stream on/off sequences. */
+	struct mutex stream_mutex;
+	bool streaming;
+
+	/* Flags to mark HW settings as not yet applied. */
+	bool pending;
+
+	/* Clock provider and system clock frequency. */
+	struct clk *clk;
+	u32 sysclk;
+
+	struct gpio_desc *oe;
+	struct gpio_desc *standby;
+	struct gpio_desc *reset;
+};
+
+#define sd_to_mt9v111(__sd) container_of((__sd), struct mt9v111_dev, sd)
+
+/*
+ * mt9v111_mbus_fmt - List all media bus formats supported by the driver.
+ *
+ * Only list the media bus code here. The image sizes are freely configurable
+ * in the pixel array sizes range.
+ *
+ * The desired frame interval, in the supported frame interval range, is
+ * obtained by configuring blanking as the sensor does not have a PLL but
+ * only a fixed clock divider that generates the output pixel clock.
+ */
+static struct mt9v111_mbus_fmt {
+	u32	code;
+} mt9v111_formats[] = {
+	{
+		.code	= MEDIA_BUS_FMT_UYVY8_2X8,
+	},
+	{
+		.code	= MEDIA_BUS_FMT_YUYV8_2X8,
+	},
+	{
+		.code	= MEDIA_BUS_FMT_VYUY8_2X8,
+	},
+	{
+		.code	= MEDIA_BUS_FMT_YVYU8_2X8,
+	},
+};
+
+static u32 mt9v111_frame_intervals[] = {5, 10, 15, 20, 30};
+
+/*
+ * mt9v111_frame_sizes - List sensor's supported resolutions.
+ *
+ * Resolution generated through decimation in the IFP block from the
+ * full VGA pixel array.
+ */
+static struct v4l2_rect mt9v111_frame_sizes[] = {
+	{
+		.width	= 640,
+		.height	= 480,
+	},
+	{
+		.width	= 352,
+		.height	= 288
+	},
+	{
+		.width	= 320,
+		.height	= 240,
+	},
+	{
+		.width	= 176,
+		.height	= 144,
+	},
+	{
+		.width	= 160,
+		.height	= 120,
+	},
+};
+
+/* --- Device I/O access --- */
+
+static int __mt9v111_read(struct i2c_client *c, u8 reg, u16 *val)
+{
+	struct i2c_msg msg[2];
+	__be16 buf;
+	int ret;
+
+	msg[0].addr = c->addr;
+	msg[0].flags = 0;
+	msg[0].len = 1;
+	msg[0].buf = &reg;
+
+	msg[1].addr = c->addr;
+	msg[1].flags = I2C_M_RD;
+	msg[1].len = 2;
+	msg[1].buf = (char *)&buf;
+
+	ret = i2c_transfer(c->adapter, msg, 2);
+	if (ret < 0) {
+		dev_err(&c->dev, "i2c read transfer error: %d\n", ret);
+		return ret;
+	}
+
+	*val = be16_to_cpu(buf);
+
+	dev_dbg(&c->dev, "%s: %x=%x\n", __func__, reg, *val);
+
+	return 0;
+}
+
+static int __mt9v111_write(struct i2c_client *c, u8 reg, u16 val)
+{
+	struct i2c_msg msg;
+	u8 buf[3] = { 0 };
+	int ret;
+
+	buf[0] = reg;
+	buf[1] = val >> 8;
+	buf[2] = val & 0xff;
+
+	msg.addr = c->addr;
+	msg.flags = 0;
+	msg.len = 3;
+	msg.buf = (char *)buf;
+
+	dev_dbg(&c->dev, "%s: %x = %x%x\n", __func__, reg, buf[1], buf[2]);
+
+	ret = i2c_transfer(c->adapter, &msg, 1);
+	if (ret < 0) {
+		dev_err(&c->dev, "i2c write transfer error: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int __mt9v111_addr_space_select(struct i2c_client *c, u16 addr_space)
+{
+	struct v4l2_subdev *sd = i2c_get_clientdata(c);
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(sd);
+	u16 val;
+	int ret;
+
+	if (mt9v111->addr_space == addr_space)
+		return 0;
+
+	ret = __mt9v111_write(c, MT9V111_R01_ADDR_SPACE, addr_space);
+	if (ret)
+		return ret;
+
+	/* Verify address space has been updated */
+	ret = __mt9v111_read(c, MT9V111_R01_ADDR_SPACE, &val);
+	if (ret)
+		return ret;
+
+	if (val != addr_space)
+		return -EINVAL;
+
+	mt9v111->addr_space = addr_space;
+
+	return 0;
+}
+
+static int mt9v111_read(struct i2c_client *c, u8 addr_space, u8 reg, u16 *val)
+{
+	int ret;
+
+	/* Select register address space first. */
+	ret = __mt9v111_addr_space_select(c, addr_space);
+	if (ret)
+		return ret;
+
+	ret = __mt9v111_read(c, reg, val);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int mt9v111_write(struct i2c_client *c, u8 addr_space, u8 reg, u16 val)
+{
+	int ret;
+
+	/* Select register address space first. */
+	ret = __mt9v111_addr_space_select(c, addr_space);
+	if (ret)
+		return ret;
+
+	ret = __mt9v111_write(c, reg, val);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int mt9v111_update(struct i2c_client *c, u8 addr_space, u8 reg,
+			  u16 mask, u16 val)
+{
+	u16 current_val;
+	int ret;
+
+	/* Select register address space first. */
+	ret = __mt9v111_addr_space_select(c, addr_space);
+	if (ret)
+		return ret;
+
+	/* Read the current register value, then update it. */
+	ret = __mt9v111_read(c, reg, &current_val);
+	if (ret)
+		return ret;
+
+	current_val &= ~mask;
+	current_val |= (val & mask);
+	ret = __mt9v111_write(c, reg, current_val);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/* --- Sensor HW operations --- */
+
+static int __mt9v111_power_on(struct v4l2_subdev *sd)
+{
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(sd);
+	int ret;
+
+	ret = clk_prepare_enable(mt9v111->clk);
+	if (ret)
+		return ret;
+
+	clk_set_rate(mt9v111->clk, mt9v111->sysclk);
+
+	gpiod_set_value(mt9v111->standby, 0);
+	usleep_range(500, 1000);
+
+	gpiod_set_value(mt9v111->oe, 1);
+	usleep_range(500, 1000);
+
+	return 0;
+}
+
+static int __mt9v111_power_off(struct v4l2_subdev *sd)
+{
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(sd);
+
+	gpiod_set_value(mt9v111->oe, 0);
+	usleep_range(500, 1000);
+
+	gpiod_set_value(mt9v111->standby, 1);
+	usleep_range(500, 1000);
+
+	clk_disable_unprepare(mt9v111->clk);
+
+	return 0;
+}
+
+static int __mt9v111_hw_reset(struct mt9v111_dev *mt9v111)
+{
+	if (!mt9v111->reset)
+		return -EINVAL;
+
+	gpiod_set_value(mt9v111->reset, 1);
+	usleep_range(500, 1000);
+
+	gpiod_set_value(mt9v111->reset, 0);
+	usleep_range(500, 1000);
+
+	return 0;
+}
+
+static int __mt9v111_sw_reset(struct mt9v111_dev *mt9v111)
+{
+	struct i2c_client *c = mt9v111->client;
+	int ret;
+
+	/* Software reset core and IFP blocks. */
+
+	ret = mt9v111_update(c, MT9V111_R01_CORE,
+			     MT9V111_CORE_R0D_CORE_RESET,
+			     MT9V111_CORE_R0D_CORE_RESET_MASK, 1);
+	if (ret)
+		return ret;
+	usleep_range(500, 1000);
+
+	ret = mt9v111_update(c, MT9V111_R01_CORE,
+			     MT9V111_CORE_R0D_CORE_RESET,
+			     MT9V111_CORE_R0D_CORE_RESET_MASK, 0);
+	if (ret)
+		return ret;
+	usleep_range(500, 1000);
+
+	ret = mt9v111_update(c, MT9V111_R01_IFP,
+			     MT9V111_IFP_R07_IFP_RESET,
+			     MT9V111_IFP_R07_IFP_RESET_MASK, 1);
+	if (ret)
+		return ret;
+	usleep_range(500, 1000);
+
+	ret = mt9v111_update(c, MT9V111_R01_IFP,
+			     MT9V111_IFP_R07_IFP_RESET,
+			     MT9V111_IFP_R07_IFP_RESET_MASK, 0);
+	if (ret)
+		return ret;
+	usleep_range(500, 1000);
+
+	return 0;
+}
+
+static int mt9v111_calc_frame_rate(struct mt9v111_dev *mt9v111,
+				   struct v4l2_fract *tpf)
+{
+	unsigned int fps = tpf->numerator ?
+			   tpf->denominator / tpf->numerator :
+			   tpf->denominator;
+	unsigned int best_diff;
+	unsigned int frm_cols;
+	unsigned int row_pclk;
+	unsigned int best_fps;
+	unsigned int pclk;
+	unsigned int diff;
+	unsigned int idx;
+	unsigned int hb;
+	unsigned int vb;
+	unsigned int i;
+	int ret;
+
+	/* Approximate to the closest supported frame interval. */
+	best_diff = ~0L;
+	for (i = 0, idx = 0; i < ARRAY_SIZE(mt9v111_frame_intervals); i++) {
+		diff = abs(fps - mt9v111_frame_intervals[i]);
+		if (diff < best_diff) {
+			idx = i;
+			best_diff = diff;
+		}
+	}
+	fps = mt9v111_frame_intervals[idx];
+
+	/*
+	 * The sensor does not provide a PLL circuitry and pixel clock is
+	 * generated dividing the master clock source by two.
+	 *
+	 * Trow = (W + Hblank + 114) * 2 * (1 / SYSCLK)
+	 * TFrame = Trow * (H + Vblank + 2)
+	 *
+	 * FPS = (SYSCLK / 2) / (Trow * (H + Vblank + 2))
+	 *
+	 * This boils down to tune H and V blanks to best approximate the
+	 * above equation.
+	 *
+	 * Test all available H/V blank values, until we reach the
+	 * desired frame rate.
+	 */
+	best_fps = vb = hb = 0;
+	pclk = DIV_ROUND_CLOSEST(mt9v111->sysclk, 2);
+	row_pclk = MT9V111_PIXEL_ARRAY_WIDTH + 7 + MT9V111_CORE_R04_WIN_H_OFFS;
+	frm_cols = MT9V111_PIXEL_ARRAY_HEIGHT + 7 + MT9V111_CORE_R03_WIN_V_OFFS;
+
+	best_diff = ~0L;
+	for (vb = MT9V111_CORE_R06_MIN_VBLANK;
+	     vb < MT9V111_CORE_R06_MAX_VBLANK; vb++) {
+		for (hb = MT9V111_CORE_R05_MIN_HBLANK;
+		     hb < MT9V111_CORE_R05_MAX_HBLANK; hb += 10) {
+			unsigned int t_frame = (row_pclk + hb) *
+					       (frm_cols + vb);
+			unsigned int t_fps = DIV_ROUND_CLOSEST(pclk, t_frame);
+
+			diff = abs(fps - t_fps);
+			if (diff < best_diff) {
+				best_diff = diff;
+				best_fps = t_fps;
+
+				if (diff == 0)
+					break;
+			}
+		}
+
+		if (diff == 0)
+			break;
+	}
+
+	ret = v4l2_ctrl_s_ctrl_int64(mt9v111->hblank, hb);
+	if (ret)
+		return ret;
+
+	ret = v4l2_ctrl_s_ctrl_int64(mt9v111->vblank, vb);
+	if (ret)
+		return ret;
+
+	tpf->numerator = 1;
+	tpf->denominator = best_fps;
+
+	return 0;
+}
+
+static int mt9v111_hw_config(struct mt9v111_dev *mt9v111)
+{
+	struct i2c_client *c = mt9v111->client;
+	unsigned int ret;
+	u16 outfmtctrl2;
+
+	/* Force device reset. */
+	ret = __mt9v111_hw_reset(mt9v111);
+	if (ret == -EINVAL)
+		ret = __mt9v111_sw_reset(mt9v111);
+	if (ret)
+		return ret;
+
+	/* Configure internal clock sample rate. */
+	ret = mt9v111->sysclk < DIV_ROUND_CLOSEST(MT9V111_MAX_CLKIN, 2) ?
+				mt9v111_update(c, MT9V111_R01_CORE,
+					MT9V111_CORE_R07_OUT_CTRL,
+					MT9V111_CORE_R07_OUT_CTRL_SAMPLE, 1) :
+				mt9v111_update(c, MT9V111_R01_CORE,
+					MT9V111_CORE_R07_OUT_CTRL,
+					MT9V111_CORE_R07_OUT_CTRL_SAMPLE, 0);
+	if (ret)
+		return ret;
+
+	/*
+	 * Configure output image format components ordering.
+	 *
+	 * TODO: IFP block can also output several RGB permutations, we only
+	 *	 support YUYV permutations at the moment.
+	 */
+	switch (mt9v111->fmt.code) {
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+			outfmtctrl2 = MT9V111_IFP_R3A_OUTFMT_CTRL2_SWAP_YC;
+			break;
+	case MEDIA_BUS_FMT_VYUY8_2X8:
+			outfmtctrl2 = MT9V111_IFP_R3A_OUTFMT_CTRL2_SWAP_CBCR;
+			break;
+	case MEDIA_BUS_FMT_YVYU8_2X8:
+			outfmtctrl2 = MT9V111_IFP_R3A_OUTFMT_CTRL2_SWAP_YC |
+				      MT9V111_IFP_R3A_OUTFMT_CTRL2_SWAP_CBCR;
+			break;
+	case MEDIA_BUS_FMT_UYVY8_2X8:
+	default:
+			outfmtctrl2 = 0;
+			break;
+	}
+
+	ret = mt9v111_update(c, MT9V111_R01_IFP, MT9V111_IFP_R3A_OUTFMT_CTRL2,
+			     MT9V111_IFP_R3A_OUTFMT_CTRL2_SWAP_MASK,
+			     outfmtctrl2);
+	if (ret)
+		return ret;
+
+	/*
+	 * Do not change default sensor's core configuration:
+	 * output the whole 640x480 pixel array, skip 18 columns and 6 rows.
+	 *
+	 * Instead, control the output image size through IFP block.
+	 *
+	 * TODO: No zoom&pan support. Currently we control the output image
+	 *	 size only through decimation, with no zoom support.
+	 */
+	ret = mt9v111_write(c, MT9V111_R01_IFP, MT9V111_IFP_RA5_HPAN,
+			    MT9V111_IFP_DECIMATION_FREEZE);
+	if (ret)
+		return ret;
+
+	ret = mt9v111_write(c, MT9V111_R01_IFP, MT9V111_IFP_RA8_VPAN,
+			    MT9V111_IFP_DECIMATION_FREEZE);
+	if (ret)
+		return ret;
+
+	ret = mt9v111_write(c, MT9V111_R01_IFP, MT9V111_IFP_RA6_HZOOM,
+			    MT9V111_IFP_DECIMATION_FREEZE |
+			    MT9V111_PIXEL_ARRAY_WIDTH);
+	if (ret)
+		return ret;
+
+	ret = mt9v111_write(c, MT9V111_R01_IFP, MT9V111_IFP_RA9_VZOOM,
+			    MT9V111_IFP_DECIMATION_FREEZE |
+			    MT9V111_PIXEL_ARRAY_HEIGHT);
+	if (ret)
+		return ret;
+
+	ret = mt9v111_write(c, MT9V111_R01_IFP, MT9V111_IFP_RA7_HOUT,
+			    MT9V111_IFP_DECIMATION_FREEZE |
+			    mt9v111->fmt.width);
+	if (ret)
+		return ret;
+
+	ret = mt9v111_write(c, MT9V111_R01_IFP, MT9V111_IFP_RAA_VOUT,
+			    mt9v111->fmt.height);
+	if (ret)
+		return ret;
+
+	/* Apply controls to set auto exp, auto awb and timings */
+	ret = v4l2_ctrl_handler_setup(&mt9v111->ctrls);
+	if (ret)
+		return ret;
+
+	/*
+	 * Set pixel integration time to the whole frame time.
+	 * This value controls the the shutter delay when running with AE
+	 * disabled. If longer than frame time, it affects the output
+	 * frame rate.
+	 */
+	return mt9v111_write(c, MT9V111_R01_CORE, MT9V111_CORE_R09_PIXEL_INT,
+			     MT9V111_PIXEL_ARRAY_HEIGHT);
+}
+
+/* ---  V4L2 subdev operations --- */
+
+static int mt9v111_s_power(struct v4l2_subdev *sd, int on)
+{
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(sd);
+	int pwr_count;
+	int ret = 0;
+
+	mutex_lock(&mt9v111->pwr_mutex);
+
+	/*
+	 * Make sure we're transitioning from 0 to 1, or viceversa,
+	 * before actually changing the power state.
+	 */
+	pwr_count = mt9v111->pwr_count;
+	pwr_count += on ? 1 : -1;
+	if (pwr_count == !!on) {
+		ret = on ? __mt9v111_power_on(sd) :
+			   __mt9v111_power_off(sd);
+		if (!ret)
+			/* All went well, updated power counter. */
+			mt9v111->pwr_count = pwr_count;
+
+		mutex_unlock(&mt9v111->pwr_mutex);
+
+		return ret;
+	}
+
+	/*
+	 * Update power counter to keep track of how many nested calls we
+	 * received.
+	 */
+	WARN_ON(pwr_count < 0 || pwr_count > 1);
+	mt9v111->pwr_count = pwr_count;
+
+	mutex_unlock(&mt9v111->pwr_mutex);
+
+	return ret;
+}
+
+static int mt9v111_s_stream(struct v4l2_subdev *subdev, int enable)
+{
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(subdev);
+	int ret;
+
+	mutex_lock(&mt9v111->stream_mutex);
+
+	if (mt9v111->streaming == enable) {
+		mutex_unlock(&mt9v111->stream_mutex);
+		return 0;
+	}
+
+	ret = mt9v111_s_power(subdev, enable);
+	if (ret)
+		goto error_unlock;
+
+	if (enable && mt9v111->pending) {
+		ret = mt9v111_hw_config(mt9v111);
+		if (ret)
+			goto error_unlock;
+
+		/*
+		 * No need to update control here as far as only H/VBLANK are
+		 * supported and immediately programmed to registers in .s_ctrl
+		 */
+
+		mt9v111->pending = false;
+	}
+
+	mt9v111->streaming = enable ? true : false;
+	mutex_unlock(&mt9v111->stream_mutex);
+
+	return 0;
+
+error_unlock:
+	mutex_unlock(&mt9v111->stream_mutex);
+
+	return ret;
+}
+
+static int mt9v111_s_frame_interval(struct v4l2_subdev *sd,
+				    struct v4l2_subdev_frame_interval *ival)
+{
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(sd);
+	struct v4l2_fract *tpf = &ival->interval;
+	unsigned int fps = tpf->numerator ?
+			   tpf->denominator / tpf->numerator :
+			   tpf->denominator;
+	unsigned int max_fps;
+
+	if (!tpf->numerator)
+		tpf->numerator = 1;
+
+	mutex_lock(&mt9v111->stream_mutex);
+
+	if (mt9v111->streaming) {
+		mutex_unlock(&mt9v111->stream_mutex);
+		return -EBUSY;
+	}
+
+	if (mt9v111->fps == fps) {
+		mutex_unlock(&mt9v111->stream_mutex);
+		return 0;
+	}
+
+	/* Make sure frame rate/image sizes constraints are respected. */
+	if (mt9v111->fmt.width < QVGA_WIDTH &&
+	    mt9v111->fmt.height < QVGA_HEIGHT)
+		max_fps = 90;
+	else if (mt9v111->fmt.width < CIF_WIDTH &&
+		 mt9v111->fmt.height < CIF_HEIGHT)
+		max_fps = 60;
+	else
+		max_fps = mt9v111->sysclk <
+				DIV_ROUND_CLOSEST(MT9V111_MAX_CLKIN, 2) ? 15 :
+									  30;
+
+	if (fps > max_fps) {
+		mutex_unlock(&mt9v111->stream_mutex);
+		return -EINVAL;
+	}
+
+	mt9v111_calc_frame_rate(mt9v111, tpf);
+
+	mt9v111->fps = fps;
+	mt9v111->pending = true;
+
+	mutex_unlock(&mt9v111->stream_mutex);
+
+	return 0;
+}
+
+static int mt9v111_g_frame_interval(struct v4l2_subdev *sd,
+				    struct v4l2_subdev_frame_interval *ival)
+{
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(sd);
+	struct v4l2_fract *tpf = &ival->interval;
+
+	mutex_lock(&mt9v111->stream_mutex);
+
+	tpf->numerator = 1;
+	tpf->denominator = mt9v111->fps;
+
+	mutex_unlock(&mt9v111->stream_mutex);
+
+	return 0;
+}
+
+static struct v4l2_mbus_framefmt *__mt9v111_get_pad_format(
+					struct mt9v111_dev *mt9v111,
+					struct v4l2_subdev_pad_config *cfg,
+					unsigned int pad,
+					enum v4l2_subdev_format_whence which)
+{
+	switch (which) {
+	case V4L2_SUBDEV_FORMAT_TRY:
+#if IS_ENABLED(CONFIG_VIDEO_V4L2_SUBDEV_API)
+		return v4l2_subdev_get_try_format(&mt9v111->sd, cfg, pad);
+#else
+		return &cfg->try_fmt;
+#endif
+	case V4L2_SUBDEV_FORMAT_ACTIVE:
+		return &mt9v111->fmt;
+	default:
+		return NULL;
+	}
+}
+
+static int mt9v111_enum_mbus_code(struct v4l2_subdev *subdev,
+				  struct v4l2_subdev_pad_config *cfg,
+				  struct v4l2_subdev_mbus_code_enum *code)
+{
+	if (code->pad || code->index > ARRAY_SIZE(mt9v111_formats) - 1)
+		return -EINVAL;
+
+	code->code = mt9v111_formats[code->index].code;
+
+	return 0;
+}
+
+static int mt9v111_enum_frame_interval(struct v4l2_subdev *sd,
+				struct v4l2_subdev_pad_config *cfg,
+				struct v4l2_subdev_frame_interval_enum *fie)
+{
+	unsigned int i;
+
+	if (fie->pad || fie->index >= ARRAY_SIZE(mt9v111_frame_intervals))
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(mt9v111_frame_sizes); i++)
+		if (fie->width == mt9v111_frame_sizes[i].width &&
+		    fie->height == mt9v111_frame_sizes[i].height)
+			break;
+
+	if (i == ARRAY_SIZE(mt9v111_frame_sizes))
+		return -EINVAL;
+
+	fie->interval.numerator = 1;
+	fie->interval.denominator = mt9v111_frame_intervals[fie->index];
+
+	return 0;
+}
+
+static int mt9v111_enum_frame_size(struct v4l2_subdev *subdev,
+				   struct v4l2_subdev_pad_config *cfg,
+				   struct v4l2_subdev_frame_size_enum *fse)
+{
+	if (fse->pad || fse->index >= ARRAY_SIZE(mt9v111_frame_sizes))
+		return -EINVAL;
+
+	fse->min_width = mt9v111_frame_sizes[fse->index].width;
+	fse->max_width = mt9v111_frame_sizes[fse->index].width;
+	fse->min_height = mt9v111_frame_sizes[fse->index].height;
+	fse->max_height = mt9v111_frame_sizes[fse->index].height;
+
+	return 0;
+}
+
+static int mt9v111_get_format(struct v4l2_subdev *subdev,
+			      struct v4l2_subdev_pad_config *cfg,
+			      struct v4l2_subdev_format *format)
+{
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(subdev);
+
+	if (format->pad)
+		return -EINVAL;
+
+	mutex_lock(&mt9v111->stream_mutex);
+	format->format = *__mt9v111_get_pad_format(mt9v111, cfg, format->pad,
+						   format->which);
+	mutex_unlock(&mt9v111->stream_mutex);
+
+	return 0;
+}
+
+static int mt9v111_set_format(struct v4l2_subdev *subdev,
+			      struct v4l2_subdev_pad_config *cfg,
+			      struct v4l2_subdev_format *format)
+{
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(subdev);
+	struct v4l2_mbus_framefmt new_fmt;
+	struct v4l2_mbus_framefmt *__fmt;
+	unsigned int best_fit = ~0L;
+	unsigned int idx = 0;
+	unsigned int i;
+
+	mutex_lock(&mt9v111->stream_mutex);
+	if (mt9v111->streaming) {
+		mutex_unlock(&mt9v111->stream_mutex);
+		return -EBUSY;
+	}
+
+	if (format->pad) {
+		mutex_unlock(&mt9v111->stream_mutex);
+		return -EINVAL;
+	}
+
+	/* Update mbus format code and sizes. */
+	for (i = 0; i < ARRAY_SIZE(mt9v111_formats); i++) {
+		if (format->format.code == mt9v111_formats[i].code) {
+			new_fmt.code = mt9v111_formats[i].code;
+			break;
+		}
+	}
+	if (i == ARRAY_SIZE(mt9v111_formats))
+		new_fmt.code = mt9v111_formats[0].code;
+
+	for (i = 0; i < ARRAY_SIZE(mt9v111_frame_sizes); i++) {
+		unsigned int fit = abs(mt9v111_frame_sizes[i].width -
+				       format->format.width) +
+				   abs(mt9v111_frame_sizes[i].height -
+				       format->format.height);
+		if (fit < best_fit) {
+			best_fit = fit;
+			idx = i;
+
+			if (fit == 0)
+				break;
+		}
+	}
+	new_fmt.width = mt9v111_frame_sizes[idx].width;
+	new_fmt.height = mt9v111_frame_sizes[idx].height;
+
+	/* Update the device (or pad) format if it has changed. */
+	__fmt = __mt9v111_get_pad_format(mt9v111, cfg, format->pad,
+					 format->which);
+
+	/* Format hasn't changed, stop here. */
+	if (__fmt->code == new_fmt.code &&
+	    __fmt->width == new_fmt.width &&
+	    __fmt->height == new_fmt.height)
+		goto done;
+
+	/* Update the format and sizes, then  mark changes as pending. */
+	__fmt->code = new_fmt.code;
+	__fmt->width = new_fmt.width;
+	__fmt->height = new_fmt.height;
+
+	if (format->which == V4L2_SUBDEV_FORMAT_ACTIVE)
+		mt9v111->pending = true;
+
+	dev_dbg(mt9v111->dev, "%s: mbus_code: %x - (%ux%u)\n",
+		__func__, __fmt->code, __fmt->width, __fmt->height);
+
+done:
+	format->format = *__fmt;
+
+	mutex_unlock(&mt9v111->stream_mutex);
+
+	return 0;
+}
+
+static int mt9v111_init_cfg(struct v4l2_subdev *subdev,
+			    struct v4l2_subdev_pad_config *cfg)
+{
+	cfg->try_fmt = mt9v111_def_fmt;
+
+	return 0;
+}
+
+static const struct v4l2_subdev_core_ops mt9v111_core_ops = {
+	.s_power		= mt9v111_s_power,
+};
+
+static const struct v4l2_subdev_video_ops mt9v111_video_ops = {
+	.s_stream		= mt9v111_s_stream,
+	.s_frame_interval	= mt9v111_s_frame_interval,
+	.g_frame_interval	= mt9v111_g_frame_interval,
+};
+
+static const struct v4l2_subdev_pad_ops mt9v111_pad_ops = {
+	.init_cfg		= mt9v111_init_cfg,
+	.enum_mbus_code		= mt9v111_enum_mbus_code,
+	.enum_frame_size	= mt9v111_enum_frame_size,
+	.enum_frame_interval	= mt9v111_enum_frame_interval,
+	.get_fmt		= mt9v111_get_format,
+	.set_fmt		= mt9v111_set_format,
+};
+
+static const struct v4l2_subdev_ops mt9v111_ops = {
+	.core	= &mt9v111_core_ops,
+	.video	= &mt9v111_video_ops,
+	.pad	= &mt9v111_pad_ops,
+};
+
+#if IS_ENABLED(CONFIG_MEDIA_CONTROLLER)
+static const struct media_entity_operations mt9v111_subdev_entity_ops = {
+	.link_validate = v4l2_subdev_link_validate,
+};
+#endif
+
+/* --- V4L2 ctrl --- */
+static int mt9v111_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct mt9v111_dev *mt9v111 = container_of(ctrl->handler,
+						   struct mt9v111_dev,
+						   ctrls);
+	int ret;
+
+	mutex_lock(&mt9v111->pwr_mutex);
+	/*
+	 * If sensor is powered down, just cache new control values,
+	 * no actual register access.
+	 */
+	if (!mt9v111->pwr_count) {
+		mt9v111->pending = true;
+		mutex_unlock(&mt9v111->pwr_mutex);
+		return 0;
+	}
+	mutex_unlock(&mt9v111->pwr_mutex);
+
+	/*
+	 * Flickering control gets disabled if both auto exp and auto awb
+	 * are disabled too. If any of the two is enabled, enable it.
+	 *
+	 * Disabling flickering when ae and awb are off allows a more precise
+	 * control of the programmed frame rate.
+	 */
+	if (mt9v111->auto_exp->is_new || mt9v111->auto_awb->is_new) {
+		if (mt9v111->auto_exp->val == V4L2_EXPOSURE_MANUAL &&
+		    mt9v111->auto_awb->val == V4L2_WHITE_BALANCE_MANUAL)
+			ret = mt9v111_update(mt9v111->client, MT9V111_R01_IFP,
+					     MT9V111_IFP_R08_OUTFMT_CTRL,
+					     MT9V111_IFP_R08_OUTFMT_CTRL_FLICKER,
+					     0);
+		else
+			ret = mt9v111_update(mt9v111->client, MT9V111_R01_IFP,
+					     MT9V111_IFP_R08_OUTFMT_CTRL,
+					     MT9V111_IFP_R08_OUTFMT_CTRL_FLICKER,
+					     1);
+		if (ret)
+			return ret;
+	}
+
+	ret = -EINVAL;
+	switch (ctrl->id) {
+	case V4L2_CID_AUTO_WHITE_BALANCE:
+		ret = mt9v111_update(mt9v111->client, MT9V111_R01_IFP,
+				     MT9V111_IFP_R06_OPMODE_CTRL,
+				     MT9V111_IFP_R06_OPMODE_CTRL_AWB_EN,
+				     ctrl->val == V4L2_WHITE_BALANCE_AUTO ?
+				     MT9V111_IFP_R06_OPMODE_CTRL_AWB_EN : 0);
+		break;
+	case V4L2_CID_EXPOSURE_AUTO:
+		ret = mt9v111_update(mt9v111->client, MT9V111_R01_IFP,
+				     MT9V111_IFP_R06_OPMODE_CTRL,
+				     MT9V111_IFP_R06_OPMODE_CTRL_AE_EN,
+				     ctrl->val == V4L2_EXPOSURE_AUTO ?
+				     MT9V111_IFP_R06_OPMODE_CTRL_AE_EN : 0);
+		break;
+	case V4L2_CID_HBLANK:
+		ret = mt9v111_update(mt9v111->client, MT9V111_R01_CORE,
+				     MT9V111_CORE_R05_HBLANK,
+				     MT9V111_CORE_R05_MAX_HBLANK,
+				     mt9v111->hblank->val);
+		break;
+	case V4L2_CID_VBLANK:
+		ret = mt9v111_update(mt9v111->client, MT9V111_R01_CORE,
+				     MT9V111_CORE_R06_VBLANK,
+				     MT9V111_CORE_R06_MAX_VBLANK,
+				     mt9v111->vblank->val);
+		break;
+	}
+
+	return ret;
+}
+
+static const struct v4l2_ctrl_ops mt9v111_ctrl_ops = {
+	.s_ctrl = mt9v111_s_ctrl,
+};
+
+static int mt9v111_chip_probe(struct mt9v111_dev *mt9v111)
+{
+	int ret;
+	u16 val;
+
+	ret = __mt9v111_power_on(&mt9v111->sd);
+	if (ret)
+		return ret;
+
+	ret = mt9v111_read(mt9v111->client, MT9V111_R01_CORE,
+			   MT9V111_CORE_RFF_CHIP_VER, &val);
+	if (ret)
+		goto power_off;
+
+	if ((val >> 8) != MT9V111_CHIP_ID_HIGH &&
+	    (val & 0xff) != MT9V111_CHIP_ID_LOW) {
+		dev_err(mt9v111->dev,
+			"Unable to identify MT9V111 chip: 0x%2x%2x\n",
+			val >> 8, val & 0xff);
+		ret = -EIO;
+		goto power_off;
+	}
+
+	dev_dbg(mt9v111->dev, "Chip identified: 0x%2x%2x\n",
+		val >> 8, val & 0xff);
+
+power_off:
+	__mt9v111_power_off(&mt9v111->sd);
+
+	return ret;
+}
+
+static int mt9v111_probe(struct i2c_client *client)
+{
+	struct mt9v111_dev *mt9v111;
+	struct v4l2_fract tpf;
+	int ret;
+
+	mt9v111 = devm_kzalloc(&client->dev, sizeof(*mt9v111), GFP_KERNEL);
+	if (!mt9v111)
+		return -ENOMEM;
+
+	mt9v111->dev = &client->dev;
+	mt9v111->client = client;
+
+	mt9v111->clk = devm_clk_get(&client->dev, NULL);
+	if (IS_ERR(mt9v111->clk))
+		return PTR_ERR(mt9v111->clk);
+
+	mt9v111->sysclk = clk_get_rate(mt9v111->clk);
+	if (mt9v111->sysclk > MT9V111_MAX_CLKIN)
+		return -EINVAL;
+
+	mt9v111->oe = devm_gpiod_get_optional(&client->dev, "enable",
+					      GPIOD_OUT_LOW);
+	if (IS_ERR(mt9v111->oe)) {
+		dev_err(&client->dev, "Unable to get GPIO \"enable\": %ld\n",
+			PTR_ERR(mt9v111->oe));
+		return PTR_ERR(mt9v111->oe);
+	}
+
+	mt9v111->standby = devm_gpiod_get_optional(&client->dev, "standby",
+						   GPIOD_OUT_HIGH);
+	if (IS_ERR(mt9v111->standby)) {
+		dev_err(&client->dev, "Unable to get GPIO \"standby\": %ld\n",
+			PTR_ERR(mt9v111->standby));
+		return PTR_ERR(mt9v111->standby);
+	}
+
+	mt9v111->reset = devm_gpiod_get_optional(&client->dev, "reset",
+						 GPIOD_OUT_LOW);
+	if (IS_ERR(mt9v111->reset)) {
+		dev_err(&client->dev, "Unable to get GPIO \"reset\": %ld\n",
+			PTR_ERR(mt9v111->reset));
+		return PTR_ERR(mt9v111->reset);
+	}
+
+	mutex_init(&mt9v111->pwr_mutex);
+	mutex_init(&mt9v111->stream_mutex);
+
+	v4l2_ctrl_handler_init(&mt9v111->ctrls, 5);
+
+	mt9v111->auto_awb = v4l2_ctrl_new_std(&mt9v111->ctrls,
+					      &mt9v111_ctrl_ops,
+					      V4L2_CID_AUTO_WHITE_BALANCE,
+					      0, 1, 1,
+					      V4L2_WHITE_BALANCE_AUTO);
+	if (IS_ERR_OR_NULL(mt9v111->auto_awb)) {
+		ret = PTR_ERR(mt9v111->auto_awb);
+		goto error_free_ctrls;
+	}
+
+	mt9v111->auto_exp = v4l2_ctrl_new_std_menu(&mt9v111->ctrls,
+						   &mt9v111_ctrl_ops,
+						   V4L2_CID_EXPOSURE_AUTO,
+						   V4L2_EXPOSURE_MANUAL,
+						   0, V4L2_EXPOSURE_AUTO);
+	if (IS_ERR_OR_NULL(mt9v111->auto_exp)) {
+		ret = PTR_ERR(mt9v111->auto_exp);
+		goto error_free_ctrls;
+	}
+
+	/* Initialize timings */
+	mt9v111->hblank = v4l2_ctrl_new_std(&mt9v111->ctrls, &mt9v111_ctrl_ops,
+					    V4L2_CID_HBLANK,
+					    MT9V111_CORE_R05_MIN_HBLANK,
+					    MT9V111_CORE_R05_MAX_HBLANK, 1,
+					    MT9V111_CORE_R05_DEF_HBLANK);
+	if (IS_ERR_OR_NULL(mt9v111->hblank)) {
+		ret = PTR_ERR(mt9v111->hblank);
+		goto error_free_ctrls;
+	}
+
+	mt9v111->vblank = v4l2_ctrl_new_std(&mt9v111->ctrls, &mt9v111_ctrl_ops,
+					    V4L2_CID_VBLANK,
+					    MT9V111_CORE_R06_MIN_VBLANK,
+					    MT9V111_CORE_R06_MAX_VBLANK, 1,
+					    MT9V111_CORE_R06_DEF_VBLANK);
+	if (IS_ERR_OR_NULL(mt9v111->vblank)) {
+		ret = PTR_ERR(mt9v111->vblank);
+		goto error_free_ctrls;
+	}
+
+	/* PIXEL_RATE is fixed: just expose it to user space. */
+	v4l2_ctrl_new_std(&mt9v111->ctrls, &mt9v111_ctrl_ops,
+			  V4L2_CID_PIXEL_RATE, 0,
+			  DIV_ROUND_CLOSEST(mt9v111->sysclk, 2), 1,
+			  DIV_ROUND_CLOSEST(mt9v111->sysclk, 2));
+
+	mt9v111->sd.ctrl_handler = &mt9v111->ctrls;
+
+	/* Start with default configuration: 640x480 UYVY. */
+	mt9v111->fmt	= mt9v111_def_fmt;
+
+	/* Re-calculate blankings for 640x480@15fps. */
+	mt9v111->fps		= 15;
+	tpf.numerator		= 1;
+	tpf.denominator		= mt9v111->fps;
+	mt9v111_calc_frame_rate(mt9v111, &tpf);
+
+	mt9v111->pwr_count	= 0;
+	mt9v111->addr_space	= MT9V111_R01_IFP;
+	mt9v111->pending	= true;
+
+	v4l2_i2c_subdev_init(&mt9v111->sd, client, &mt9v111_ops);
+
+#if IS_ENABLED(CONFIG_MEDIA_CONTROLLER)
+	mt9v111->sd.flags	|= V4L2_SUBDEV_FL_HAS_DEVNODE;
+	mt9v111->sd.entity.ops	= &mt9v111_subdev_entity_ops;
+	mt9v111->sd.entity.function = MEDIA_ENT_F_CAM_SENSOR;
+
+	mt9v111->pad.flags	= MEDIA_PAD_FL_SOURCE;
+	ret = media_entity_pads_init(&mt9v111->sd.entity, 1, &mt9v111->pad);
+	if (ret)
+		goto error_free_ctrls;
+#endif
+
+	ret = mt9v111_chip_probe(mt9v111);
+	if (ret)
+		goto error_free_ctrls;
+
+	ret = v4l2_async_register_subdev(&mt9v111->sd);
+	if (ret)
+		goto error_free_ctrls;
+
+	return 0;
+
+error_free_ctrls:
+	v4l2_ctrl_handler_free(&mt9v111->ctrls);
+
+#if IS_ENABLED(CONFIG_MEDIA_CONTROLLER)
+	media_entity_cleanup(&mt9v111->sd.entity);
+#endif
+
+	mutex_destroy(&mt9v111->pwr_mutex);
+	mutex_destroy(&mt9v111->stream_mutex);
+
+	return ret;
+}
+
+static int mt9v111_remove(struct i2c_client *client)
+{
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(sd);
+
+	v4l2_async_unregister_subdev(sd);
+
+	v4l2_ctrl_handler_free(&mt9v111->ctrls);
+
+#if IS_ENABLED(CONFIG_MEDIA_CONTROLLER)
+	media_entity_cleanup(&sd->entity);
+#endif
+
+	mutex_destroy(&mt9v111->pwr_mutex);
+	mutex_destroy(&mt9v111->stream_mutex);
+
+	devm_gpiod_put(mt9v111->dev, mt9v111->oe);
+	devm_gpiod_put(mt9v111->dev, mt9v111->standby);
+	devm_gpiod_put(mt9v111->dev, mt9v111->reset);
+
+	devm_clk_put(mt9v111->dev, mt9v111->clk);
+
+	return 0;
+}
+
+static const struct of_device_id mt9v111_of_match[] = {
+	{ .compatible = "aptina,mt9v111", },
+	{ /* sentinel */ },
+};
+
+static struct i2c_driver mt9v111_driver = {
+	.driver = {
+		.name = "mt9v111",
+		.of_match_table = mt9v111_of_match,
+	},
+	.probe_new	= mt9v111_probe,
+	.remove		= mt9v111_remove,
+};
+
+module_i2c_driver(mt9v111_driver);
+
+MODULE_DESCRIPTION("V4L2 sensor driver for Aptina MT9V111");
+MODULE_AUTHOR("Jacopo Mondi <jacopo@jmondi.org>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/i2c/ov2680.c b/drivers/media/i2c/ov2680.c
new file mode 100644
index 000000000000..f753a1c333ef
--- /dev/null
+++ b/drivers/media/i2c/ov2680.c
@@ -0,0 +1,1186 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Omnivision OV2680 CMOS Image Sensor driver
+ *
+ * Copyright (C) 2018 Linaro Ltd
+ *
+ * Based on OV5640 Sensor Driver
+ * Copyright (C) 2011-2013 Freescale Semiconductor, Inc. All Rights Reserved.
+ * Copyright (C) 2014-2017 Mentor Graphics Inc.
+ *
+ */
+
+#include <asm/unaligned.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/gpio/consumer.h>
+#include <linux/regulator/consumer.h>
+
+#include <media/v4l2-common.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-subdev.h>
+
+#define OV2680_XVCLK_VALUE	24000000
+
+#define OV2680_CHIP_ID		0x2680
+
+#define OV2680_REG_STREAM_CTRL		0x0100
+#define OV2680_REG_SOFT_RESET		0x0103
+
+#define OV2680_REG_CHIP_ID_HIGH		0x300a
+#define OV2680_REG_CHIP_ID_LOW		0x300b
+
+#define OV2680_REG_R_MANUAL		0x3503
+#define OV2680_REG_GAIN_PK		0x350a
+#define OV2680_REG_EXPOSURE_PK_HIGH	0x3500
+#define OV2680_REG_TIMING_HTS		0x380c
+#define OV2680_REG_TIMING_VTS		0x380e
+#define OV2680_REG_FORMAT1		0x3820
+#define OV2680_REG_FORMAT2		0x3821
+
+#define OV2680_REG_ISP_CTRL00		0x5080
+
+#define OV2680_FRAME_RATE		30
+
+#define OV2680_REG_VALUE_8BIT		1
+#define OV2680_REG_VALUE_16BIT		2
+#define OV2680_REG_VALUE_24BIT		3
+
+#define OV2680_WIDTH_MAX		1600
+#define OV2680_HEIGHT_MAX		1200
+
+enum ov2680_mode_id {
+	OV2680_MODE_QUXGA_800_600,
+	OV2680_MODE_720P_1280_720,
+	OV2680_MODE_UXGA_1600_1200,
+	OV2680_MODE_MAX,
+};
+
+struct reg_value {
+	u16 reg_addr;
+	u8 val;
+};
+
+static const char * const ov2680_supply_name[] = {
+	"DOVDD",
+	"DVDD",
+	"AVDD",
+};
+
+#define OV2680_NUM_SUPPLIES ARRAY_SIZE(ov2680_supply_name)
+
+struct ov2680_mode_info {
+	const char *name;
+	enum ov2680_mode_id id;
+	u32 width;
+	u32 height;
+	const struct reg_value *reg_data;
+	u32 reg_data_size;
+};
+
+struct ov2680_ctrls {
+	struct v4l2_ctrl_handler handler;
+	struct {
+		struct v4l2_ctrl *auto_exp;
+		struct v4l2_ctrl *exposure;
+	};
+	struct {
+		struct v4l2_ctrl *auto_gain;
+		struct v4l2_ctrl *gain;
+	};
+
+	struct v4l2_ctrl *hflip;
+	struct v4l2_ctrl *vflip;
+	struct v4l2_ctrl *test_pattern;
+};
+
+struct ov2680_dev {
+	struct i2c_client		*i2c_client;
+	struct v4l2_subdev		sd;
+
+	struct media_pad		pad;
+	struct clk			*xvclk;
+	u32				xvclk_freq;
+	struct regulator_bulk_data	supplies[OV2680_NUM_SUPPLIES];
+
+	struct gpio_desc		*reset_gpio;
+	struct mutex			lock; /* protect members */
+
+	bool				mode_pending_changes;
+	bool				is_enabled;
+	bool				is_streaming;
+
+	struct ov2680_ctrls		ctrls;
+	struct v4l2_mbus_framefmt	fmt;
+	struct v4l2_fract		frame_interval;
+
+	const struct ov2680_mode_info	*current_mode;
+};
+
+static const char * const test_pattern_menu[] = {
+	"Disabled",
+	"Color Bars",
+	"Random Data",
+	"Square",
+	"Black Image",
+};
+
+static const int ov2680_hv_flip_bayer_order[] = {
+	MEDIA_BUS_FMT_SBGGR10_1X10,
+	MEDIA_BUS_FMT_SGRBG10_1X10,
+	MEDIA_BUS_FMT_SGBRG10_1X10,
+	MEDIA_BUS_FMT_SRGGB10_1X10,
+};
+
+static const struct reg_value ov2680_setting_30fps_QUXGA_800_600[] = {
+	{0x3086, 0x01}, {0x370a, 0x23}, {0x3808, 0x03}, {0x3809, 0x20},
+	{0x380a, 0x02}, {0x380b, 0x58}, {0x380c, 0x06}, {0x380d, 0xac},
+	{0x380e, 0x02}, {0x380f, 0x84}, {0x3811, 0x04}, {0x3813, 0x04},
+	{0x3814, 0x31}, {0x3815, 0x31}, {0x3820, 0xc0}, {0x4008, 0x00},
+	{0x4009, 0x03}, {0x4837, 0x1e}, {0x3501, 0x4e}, {0x3502, 0xe0},
+};
+
+static const struct reg_value ov2680_setting_30fps_720P_1280_720[] = {
+	{0x3086, 0x00}, {0x3808, 0x05}, {0x3809, 0x00}, {0x380a, 0x02},
+	{0x380b, 0xd0}, {0x380c, 0x06}, {0x380d, 0xa8}, {0x380e, 0x05},
+	{0x380f, 0x0e}, {0x3811, 0x08}, {0x3813, 0x06}, {0x3814, 0x11},
+	{0x3815, 0x11}, {0x3820, 0xc0}, {0x4008, 0x00},
+};
+
+static const struct reg_value ov2680_setting_30fps_UXGA_1600_1200[] = {
+	{0x3086, 0x00}, {0x3501, 0x4e}, {0x3502, 0xe0}, {0x3808, 0x06},
+	{0x3809, 0x40}, {0x380a, 0x04}, {0x380b, 0xb0}, {0x380c, 0x06},
+	{0x380d, 0xa8}, {0x380e, 0x05}, {0x380f, 0x0e}, {0x3811, 0x00},
+	{0x3813, 0x00}, {0x3814, 0x11}, {0x3815, 0x11}, {0x3820, 0xc0},
+	{0x4008, 0x00}, {0x4837, 0x18}
+};
+
+static const struct ov2680_mode_info ov2680_mode_init_data = {
+	"mode_quxga_800_600", OV2680_MODE_QUXGA_800_600, 800, 600,
+	ov2680_setting_30fps_QUXGA_800_600,
+	ARRAY_SIZE(ov2680_setting_30fps_QUXGA_800_600),
+};
+
+static const struct ov2680_mode_info ov2680_mode_data[OV2680_MODE_MAX] = {
+	{"mode_quxga_800_600", OV2680_MODE_QUXGA_800_600,
+	 800, 600, ov2680_setting_30fps_QUXGA_800_600,
+	 ARRAY_SIZE(ov2680_setting_30fps_QUXGA_800_600)},
+	{"mode_720p_1280_720", OV2680_MODE_720P_1280_720,
+	 1280, 720, ov2680_setting_30fps_720P_1280_720,
+	 ARRAY_SIZE(ov2680_setting_30fps_720P_1280_720)},
+	{"mode_uxga_1600_1200", OV2680_MODE_UXGA_1600_1200,
+	 1600, 1200, ov2680_setting_30fps_UXGA_1600_1200,
+	 ARRAY_SIZE(ov2680_setting_30fps_UXGA_1600_1200)},
+};
+
+static struct ov2680_dev *to_ov2680_dev(struct v4l2_subdev *sd)
+{
+	return container_of(sd, struct ov2680_dev, sd);
+}
+
+static struct device *ov2680_to_dev(struct ov2680_dev *sensor)
+{
+	return &sensor->i2c_client->dev;
+}
+
+static inline struct v4l2_subdev *ctrl_to_sd(struct v4l2_ctrl *ctrl)
+{
+	return &container_of(ctrl->handler, struct ov2680_dev,
+			     ctrls.handler)->sd;
+}
+
+static int __ov2680_write_reg(struct ov2680_dev *sensor, u16 reg,
+			      unsigned int len, u32 val)
+{
+	struct i2c_client *client = sensor->i2c_client;
+	u8 buf[6];
+	int ret;
+
+	if (len > 4)
+		return -EINVAL;
+
+	put_unaligned_be16(reg, buf);
+	put_unaligned_be32(val << (8 * (4 - len)), buf + 2);
+	ret = i2c_master_send(client, buf, len + 2);
+	if (ret != len + 2) {
+		dev_err(&client->dev, "write error: reg=0x%4x: %d\n", reg, ret);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+#define ov2680_write_reg(s, r, v) \
+	__ov2680_write_reg(s, r, OV2680_REG_VALUE_8BIT, v)
+
+#define ov2680_write_reg16(s, r, v) \
+	__ov2680_write_reg(s, r, OV2680_REG_VALUE_16BIT, v)
+
+#define ov2680_write_reg24(s, r, v) \
+	__ov2680_write_reg(s, r, OV2680_REG_VALUE_24BIT, v)
+
+static int __ov2680_read_reg(struct ov2680_dev *sensor, u16 reg,
+			     unsigned int len, u32 *val)
+{
+	struct i2c_client *client = sensor->i2c_client;
+	struct i2c_msg msgs[2];
+	u8 addr_buf[2] = { reg >> 8, reg & 0xff };
+	u8 data_buf[4] = { 0, };
+	int ret;
+
+	if (len > 4)
+		return -EINVAL;
+
+	msgs[0].addr = client->addr;
+	msgs[0].flags = 0;
+	msgs[0].len = ARRAY_SIZE(addr_buf);
+	msgs[0].buf = addr_buf;
+
+	msgs[1].addr = client->addr;
+	msgs[1].flags = I2C_M_RD;
+	msgs[1].len = len;
+	msgs[1].buf = &data_buf[4 - len];
+
+	ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs));
+	if (ret != ARRAY_SIZE(msgs)) {
+		dev_err(&client->dev, "read error: reg=0x%4x: %d\n", reg, ret);
+		return -EIO;
+	}
+
+	*val = get_unaligned_be32(data_buf);
+
+	return 0;
+}
+
+#define ov2680_read_reg(s, r, v) \
+	__ov2680_read_reg(s, r, OV2680_REG_VALUE_8BIT, v)
+
+#define ov2680_read_reg16(s, r, v) \
+	__ov2680_read_reg(s, r, OV2680_REG_VALUE_16BIT, v)
+
+#define ov2680_read_reg24(s, r, v) \
+	__ov2680_read_reg(s, r, OV2680_REG_VALUE_24BIT, v)
+
+static int ov2680_mod_reg(struct ov2680_dev *sensor, u16 reg, u8 mask, u8 val)
+{
+	u32 readval;
+	int ret;
+
+	ret = ov2680_read_reg(sensor, reg, &readval);
+	if (ret < 0)
+		return ret;
+
+	readval &= ~mask;
+	val &= mask;
+	val |= readval;
+
+	return ov2680_write_reg(sensor, reg, val);
+}
+
+static int ov2680_load_regs(struct ov2680_dev *sensor,
+			    const struct ov2680_mode_info *mode)
+{
+	const struct reg_value *regs = mode->reg_data;
+	unsigned int i;
+	int ret = 0;
+	u16 reg_addr;
+	u8 val;
+
+	for (i = 0; i < mode->reg_data_size; ++i, ++regs) {
+		reg_addr = regs->reg_addr;
+		val = regs->val;
+
+		ret = ov2680_write_reg(sensor, reg_addr, val);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static void ov2680_power_up(struct ov2680_dev *sensor)
+{
+	if (!sensor->reset_gpio)
+		return;
+
+	gpiod_set_value(sensor->reset_gpio, 0);
+	usleep_range(5000, 10000);
+}
+
+static void ov2680_power_down(struct ov2680_dev *sensor)
+{
+	if (!sensor->reset_gpio)
+		return;
+
+	gpiod_set_value(sensor->reset_gpio, 1);
+	usleep_range(5000, 10000);
+}
+
+static int ov2680_bayer_order(struct ov2680_dev *sensor)
+{
+	u32 format1;
+	u32 format2;
+	u32 hv_flip;
+	int ret;
+
+	ret = ov2680_read_reg(sensor, OV2680_REG_FORMAT1, &format1);
+	if (ret < 0)
+		return ret;
+
+	ret = ov2680_read_reg(sensor, OV2680_REG_FORMAT2, &format2);
+	if (ret < 0)
+		return ret;
+
+	hv_flip = (format2 & BIT(2)  << 1) | (format1 & BIT(2));
+
+	sensor->fmt.code = ov2680_hv_flip_bayer_order[hv_flip];
+
+	return 0;
+}
+
+static int ov2680_vflip_enable(struct ov2680_dev *sensor)
+{
+	int ret;
+
+	ret = ov2680_mod_reg(sensor, OV2680_REG_FORMAT1, BIT(2), BIT(2));
+	if (ret < 0)
+		return ret;
+
+	return ov2680_bayer_order(sensor);
+}
+
+static int ov2680_vflip_disable(struct ov2680_dev *sensor)
+{
+	int ret;
+
+	ret = ov2680_mod_reg(sensor, OV2680_REG_FORMAT1, BIT(2), BIT(0));
+	if (ret < 0)
+		return ret;
+
+	return ov2680_bayer_order(sensor);
+}
+
+static int ov2680_hflip_enable(struct ov2680_dev *sensor)
+{
+	int ret;
+
+	ret = ov2680_mod_reg(sensor, OV2680_REG_FORMAT2, BIT(2), BIT(2));
+	if (ret < 0)
+		return ret;
+
+	return ov2680_bayer_order(sensor);
+}
+
+static int ov2680_hflip_disable(struct ov2680_dev *sensor)
+{
+	int ret;
+
+	ret = ov2680_mod_reg(sensor, OV2680_REG_FORMAT2, BIT(2), BIT(0));
+	if (ret < 0)
+		return ret;
+
+	return ov2680_bayer_order(sensor);
+}
+
+static int ov2680_test_pattern_set(struct ov2680_dev *sensor, int value)
+{
+	int ret;
+
+	if (!value)
+		return ov2680_mod_reg(sensor, OV2680_REG_ISP_CTRL00, BIT(7), 0);
+
+	ret = ov2680_mod_reg(sensor, OV2680_REG_ISP_CTRL00, 0x03, value - 1);
+	if (ret < 0)
+		return ret;
+
+	ret = ov2680_mod_reg(sensor, OV2680_REG_ISP_CTRL00, BIT(7), BIT(7));
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int ov2680_gain_set(struct ov2680_dev *sensor, bool auto_gain)
+{
+	struct ov2680_ctrls *ctrls = &sensor->ctrls;
+	u32 gain;
+	int ret;
+
+	ret = ov2680_mod_reg(sensor, OV2680_REG_R_MANUAL, BIT(1),
+			     auto_gain ? 0 : BIT(1));
+	if (ret < 0)
+		return ret;
+
+	if (auto_gain || !ctrls->gain->is_new)
+		return 0;
+
+	gain = ctrls->gain->val;
+
+	ret = ov2680_write_reg16(sensor, OV2680_REG_GAIN_PK, gain);
+
+	return 0;
+}
+
+static int ov2680_gain_get(struct ov2680_dev *sensor)
+{
+	u32 gain;
+	int ret;
+
+	ret = ov2680_read_reg16(sensor, OV2680_REG_GAIN_PK, &gain);
+	if (ret)
+		return ret;
+
+	return gain;
+}
+
+static int ov2680_exposure_set(struct ov2680_dev *sensor, bool auto_exp)
+{
+	struct ov2680_ctrls *ctrls = &sensor->ctrls;
+	u32 exp;
+	int ret;
+
+	ret = ov2680_mod_reg(sensor, OV2680_REG_R_MANUAL, BIT(0),
+			     auto_exp ? 0 : BIT(0));
+	if (ret < 0)
+		return ret;
+
+	if (auto_exp || !ctrls->exposure->is_new)
+		return 0;
+
+	exp = (u32)ctrls->exposure->val;
+	exp <<= 4;
+
+	return ov2680_write_reg24(sensor, OV2680_REG_EXPOSURE_PK_HIGH, exp);
+}
+
+static int ov2680_exposure_get(struct ov2680_dev *sensor)
+{
+	int ret;
+	u32 exp;
+
+	ret = ov2680_read_reg24(sensor, OV2680_REG_EXPOSURE_PK_HIGH, &exp);
+	if (ret)
+		return ret;
+
+	return exp >> 4;
+}
+
+static int ov2680_stream_enable(struct ov2680_dev *sensor)
+{
+	return ov2680_write_reg(sensor, OV2680_REG_STREAM_CTRL, 1);
+}
+
+static int ov2680_stream_disable(struct ov2680_dev *sensor)
+{
+	return ov2680_write_reg(sensor, OV2680_REG_STREAM_CTRL, 0);
+}
+
+static int ov2680_mode_set(struct ov2680_dev *sensor)
+{
+	struct ov2680_ctrls *ctrls = &sensor->ctrls;
+	int ret;
+
+	ret = ov2680_gain_set(sensor, false);
+	if (ret < 0)
+		return ret;
+
+	ret = ov2680_exposure_set(sensor, false);
+	if (ret < 0)
+		return ret;
+
+	ret = ov2680_load_regs(sensor, sensor->current_mode);
+	if (ret < 0)
+		return ret;
+
+	if (ctrls->auto_gain->val) {
+		ret = ov2680_gain_set(sensor, true);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (ctrls->auto_exp->val == V4L2_EXPOSURE_AUTO) {
+		ret = ov2680_exposure_set(sensor, true);
+		if (ret < 0)
+			return ret;
+	}
+
+	sensor->mode_pending_changes = false;
+
+	return 0;
+}
+
+static int ov2680_mode_restore(struct ov2680_dev *sensor)
+{
+	int ret;
+
+	ret = ov2680_load_regs(sensor, &ov2680_mode_init_data);
+	if (ret < 0)
+		return ret;
+
+	return ov2680_mode_set(sensor);
+}
+
+static int ov2680_power_off(struct ov2680_dev *sensor)
+{
+	if (!sensor->is_enabled)
+		return 0;
+
+	clk_disable_unprepare(sensor->xvclk);
+	ov2680_power_down(sensor);
+	regulator_bulk_disable(OV2680_NUM_SUPPLIES, sensor->supplies);
+	sensor->is_enabled = false;
+
+	return 0;
+}
+
+static int ov2680_power_on(struct ov2680_dev *sensor)
+{
+	struct device *dev = ov2680_to_dev(sensor);
+	int ret;
+
+	if (sensor->is_enabled)
+		return 0;
+
+	ret = regulator_bulk_enable(OV2680_NUM_SUPPLIES, sensor->supplies);
+	if (ret < 0) {
+		dev_err(dev, "failed to enable regulators: %d\n", ret);
+		return ret;
+	}
+
+	if (!sensor->reset_gpio) {
+		ret = ov2680_write_reg(sensor, OV2680_REG_SOFT_RESET, 0x01);
+		if (ret != 0) {
+			dev_err(dev, "sensor soft reset failed\n");
+			return ret;
+		}
+		usleep_range(1000, 2000);
+	} else {
+		ov2680_power_down(sensor);
+		ov2680_power_up(sensor);
+	}
+
+	ret = clk_prepare_enable(sensor->xvclk);
+	if (ret < 0)
+		return ret;
+
+	ret = ov2680_mode_restore(sensor);
+	if (ret < 0)
+		goto disable;
+
+	sensor->is_enabled = true;
+
+	/* Set clock lane into LP-11 state */
+	ov2680_stream_enable(sensor);
+	usleep_range(1000, 2000);
+	ov2680_stream_disable(sensor);
+
+	return 0;
+
+disable:
+	dev_err(dev, "failed to enable sensor: %d\n", ret);
+	ov2680_power_off(sensor);
+
+	return ret;
+}
+
+static int ov2680_s_power(struct v4l2_subdev *sd, int on)
+{
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+	int ret = 0;
+
+	mutex_lock(&sensor->lock);
+
+	if (on)
+		ret = ov2680_power_on(sensor);
+	else
+		ret = ov2680_power_off(sensor);
+
+	mutex_unlock(&sensor->lock);
+
+	if (on && ret == 0) {
+		ret = v4l2_ctrl_handler_setup(&sensor->ctrls.handler);
+		if (ret < 0)
+			return ret;
+	}
+
+	return ret;
+}
+
+static int ov2680_s_g_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_frame_interval *fi)
+{
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+
+	mutex_lock(&sensor->lock);
+	fi->interval = sensor->frame_interval;
+	mutex_unlock(&sensor->lock);
+
+	return 0;
+}
+
+static int ov2680_s_stream(struct v4l2_subdev *sd, int enable)
+{
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+	int ret = 0;
+
+	mutex_lock(&sensor->lock);
+
+	if (sensor->is_streaming == !!enable)
+		goto unlock;
+
+	if (enable && sensor->mode_pending_changes) {
+		ret = ov2680_mode_set(sensor);
+		if (ret < 0)
+			goto unlock;
+	}
+
+	if (enable)
+		ret = ov2680_stream_enable(sensor);
+	else
+		ret = ov2680_stream_disable(sensor);
+
+	sensor->is_streaming = !!enable;
+
+unlock:
+	mutex_unlock(&sensor->lock);
+
+	return ret;
+}
+
+static int ov2680_enum_mbus_code(struct v4l2_subdev *sd,
+				 struct v4l2_subdev_pad_config *cfg,
+				 struct v4l2_subdev_mbus_code_enum *code)
+{
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+
+	if (code->pad != 0 || code->index != 0)
+		return -EINVAL;
+
+	code->code = sensor->fmt.code;
+
+	return 0;
+}
+
+static int ov2680_get_fmt(struct v4l2_subdev *sd,
+			  struct v4l2_subdev_pad_config *cfg,
+			  struct v4l2_subdev_format *format)
+{
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+	struct v4l2_mbus_framefmt *fmt = NULL;
+	int ret = 0;
+
+	if (format->pad != 0)
+		return -EINVAL;
+
+	mutex_lock(&sensor->lock);
+
+	if (format->which == V4L2_SUBDEV_FORMAT_TRY) {
+#ifdef CONFIG_VIDEO_V4L2_SUBDEV_API
+		fmt = v4l2_subdev_get_try_format(&sensor->sd, cfg, format->pad);
+#else
+		ret = -ENOTTY;
+#endif
+	} else {
+		fmt = &sensor->fmt;
+	}
+
+	if (fmt)
+		format->format = *fmt;
+
+	mutex_unlock(&sensor->lock);
+
+	return ret;
+}
+
+static int ov2680_set_fmt(struct v4l2_subdev *sd,
+			  struct v4l2_subdev_pad_config *cfg,
+			  struct v4l2_subdev_format *format)
+{
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+	struct v4l2_mbus_framefmt *fmt = &format->format;
+#ifdef CONFIG_VIDEO_V4L2_SUBDEV_API
+	struct v4l2_mbus_framefmt *try_fmt;
+#endif
+	const struct ov2680_mode_info *mode;
+	int ret = 0;
+
+	if (format->pad != 0)
+		return -EINVAL;
+
+	mutex_lock(&sensor->lock);
+
+	if (sensor->is_streaming) {
+		ret = -EBUSY;
+		goto unlock;
+	}
+
+	mode = v4l2_find_nearest_size(ov2680_mode_data,
+				      ARRAY_SIZE(ov2680_mode_data), width,
+				      height, fmt->width, fmt->height);
+	if (!mode) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	if (format->which == V4L2_SUBDEV_FORMAT_TRY) {
+#ifdef CONFIG_VIDEO_V4L2_SUBDEV_API
+		try_fmt = v4l2_subdev_get_try_format(sd, cfg, 0);
+		format->format = *try_fmt;
+#else
+		ret = -ENOTTY;
+#endif
+
+		goto unlock;
+	}
+
+	fmt->width = mode->width;
+	fmt->height = mode->height;
+	fmt->code = sensor->fmt.code;
+	fmt->colorspace = sensor->fmt.colorspace;
+
+	sensor->current_mode = mode;
+	sensor->fmt = format->format;
+	sensor->mode_pending_changes = true;
+
+unlock:
+	mutex_unlock(&sensor->lock);
+
+	return ret;
+}
+
+static int ov2680_init_cfg(struct v4l2_subdev *sd,
+			   struct v4l2_subdev_pad_config *cfg)
+{
+	struct v4l2_subdev_format fmt = {
+		.which = cfg ? V4L2_SUBDEV_FORMAT_TRY
+				: V4L2_SUBDEV_FORMAT_ACTIVE,
+		.format = {
+			.width = 800,
+			.height = 600,
+		}
+	};
+
+	return ov2680_set_fmt(sd, cfg, &fmt);
+}
+
+static int ov2680_enum_frame_size(struct v4l2_subdev *sd,
+				  struct v4l2_subdev_pad_config *cfg,
+				  struct v4l2_subdev_frame_size_enum *fse)
+{
+	int index = fse->index;
+
+	if (index >= OV2680_MODE_MAX || index < 0)
+		return -EINVAL;
+
+	fse->min_width = ov2680_mode_data[index].width;
+	fse->min_height = ov2680_mode_data[index].height;
+	fse->max_width = ov2680_mode_data[index].width;
+	fse->max_height = ov2680_mode_data[index].height;
+
+	return 0;
+}
+
+static int ov2680_enum_frame_interval(struct v4l2_subdev *sd,
+			      struct v4l2_subdev_pad_config *cfg,
+			      struct v4l2_subdev_frame_interval_enum *fie)
+{
+	struct v4l2_fract tpf;
+
+	if (fie->index >= OV2680_MODE_MAX || fie->width > OV2680_WIDTH_MAX ||
+	    fie->height > OV2680_HEIGHT_MAX ||
+	    fie->which > V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
+	tpf.denominator = OV2680_FRAME_RATE;
+	tpf.numerator = 1;
+
+	fie->interval = tpf;
+
+	return 0;
+}
+
+static int ov2680_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct v4l2_subdev *sd = ctrl_to_sd(ctrl);
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+	struct ov2680_ctrls *ctrls = &sensor->ctrls;
+	int val;
+
+	if (!sensor->is_enabled)
+		return 0;
+
+	switch (ctrl->id) {
+	case V4L2_CID_GAIN:
+		val = ov2680_gain_get(sensor);
+		if (val < 0)
+			return val;
+		ctrls->gain->val = val;
+		break;
+	case V4L2_CID_EXPOSURE:
+		val = ov2680_exposure_get(sensor);
+		if (val < 0)
+			return val;
+		ctrls->exposure->val = val;
+		break;
+	}
+
+	return 0;
+}
+
+static int ov2680_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct v4l2_subdev *sd = ctrl_to_sd(ctrl);
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+	struct ov2680_ctrls *ctrls = &sensor->ctrls;
+
+	if (!sensor->is_enabled)
+		return 0;
+
+	switch (ctrl->id) {
+	case V4L2_CID_AUTOGAIN:
+		return ov2680_gain_set(sensor, !!ctrl->val);
+	case V4L2_CID_GAIN:
+		return ov2680_gain_set(sensor, !!ctrls->auto_gain->val);
+	case V4L2_CID_EXPOSURE_AUTO:
+		return ov2680_exposure_set(sensor, !!ctrl->val);
+	case V4L2_CID_EXPOSURE:
+		return ov2680_exposure_set(sensor, !!ctrls->auto_exp->val);
+	case V4L2_CID_VFLIP:
+		if (sensor->is_streaming)
+			return -EBUSY;
+		if (ctrl->val)
+			return ov2680_vflip_enable(sensor);
+		else
+			return ov2680_vflip_disable(sensor);
+	case V4L2_CID_HFLIP:
+		if (sensor->is_streaming)
+			return -EBUSY;
+		if (ctrl->val)
+			return ov2680_hflip_enable(sensor);
+		else
+			return ov2680_hflip_disable(sensor);
+	case V4L2_CID_TEST_PATTERN:
+		return ov2680_test_pattern_set(sensor, ctrl->val);
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static const struct v4l2_ctrl_ops ov2680_ctrl_ops = {
+	.g_volatile_ctrl = ov2680_g_volatile_ctrl,
+	.s_ctrl = ov2680_s_ctrl,
+};
+
+static const struct v4l2_subdev_core_ops ov2680_core_ops = {
+	.s_power = ov2680_s_power,
+};
+
+static const struct v4l2_subdev_video_ops ov2680_video_ops = {
+	.g_frame_interval	= ov2680_s_g_frame_interval,
+	.s_frame_interval	= ov2680_s_g_frame_interval,
+	.s_stream		= ov2680_s_stream,
+};
+
+static const struct v4l2_subdev_pad_ops ov2680_pad_ops = {
+	.init_cfg		= ov2680_init_cfg,
+	.enum_mbus_code		= ov2680_enum_mbus_code,
+	.get_fmt		= ov2680_get_fmt,
+	.set_fmt		= ov2680_set_fmt,
+	.enum_frame_size	= ov2680_enum_frame_size,
+	.enum_frame_interval	= ov2680_enum_frame_interval,
+};
+
+static const struct v4l2_subdev_ops ov2680_subdev_ops = {
+	.core	= &ov2680_core_ops,
+	.video	= &ov2680_video_ops,
+	.pad	= &ov2680_pad_ops,
+};
+
+static int ov2680_mode_init(struct ov2680_dev *sensor)
+{
+	const struct ov2680_mode_info *init_mode;
+
+	/* set initial mode */
+	sensor->fmt.code = MEDIA_BUS_FMT_SBGGR10_1X10;
+	sensor->fmt.width = 800;
+	sensor->fmt.height = 600;
+	sensor->fmt.field = V4L2_FIELD_NONE;
+	sensor->fmt.colorspace = V4L2_COLORSPACE_SRGB;
+
+	sensor->frame_interval.denominator = OV2680_FRAME_RATE;
+	sensor->frame_interval.numerator = 1;
+
+	init_mode = &ov2680_mode_init_data;
+
+	sensor->current_mode = init_mode;
+
+	sensor->mode_pending_changes = true;
+
+	return 0;
+}
+
+static int ov2680_v4l2_init(struct ov2680_dev *sensor)
+{
+	const struct v4l2_ctrl_ops *ops = &ov2680_ctrl_ops;
+	struct ov2680_ctrls *ctrls = &sensor->ctrls;
+	struct v4l2_ctrl_handler *hdl = &ctrls->handler;
+	int ret = 0;
+
+	v4l2_i2c_subdev_init(&sensor->sd, sensor->i2c_client,
+			     &ov2680_subdev_ops);
+
+#ifdef CONFIG_VIDEO_V4L2_SUBDEV_API
+	sensor->sd.flags = V4L2_SUBDEV_FL_HAS_DEVNODE;
+#endif
+	sensor->pad.flags = MEDIA_PAD_FL_SOURCE;
+	sensor->sd.entity.function = MEDIA_ENT_F_CAM_SENSOR;
+
+	ret = media_entity_pads_init(&sensor->sd.entity, 1, &sensor->pad);
+	if (ret < 0)
+		return ret;
+
+	v4l2_ctrl_handler_init(hdl, 7);
+
+	hdl->lock = &sensor->lock;
+
+	ctrls->vflip = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_VFLIP, 0, 1, 1, 0);
+	ctrls->hflip = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_HFLIP, 0, 1, 1, 0);
+
+	ctrls->test_pattern = v4l2_ctrl_new_std_menu_items(hdl,
+					&ov2680_ctrl_ops, V4L2_CID_TEST_PATTERN,
+					ARRAY_SIZE(test_pattern_menu) - 1,
+					0, 0, test_pattern_menu);
+
+	ctrls->auto_exp = v4l2_ctrl_new_std_menu(hdl, ops,
+						 V4L2_CID_EXPOSURE_AUTO,
+						 V4L2_EXPOSURE_MANUAL, 0,
+						 V4L2_EXPOSURE_AUTO);
+
+	ctrls->exposure = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_EXPOSURE,
+					    0, 32767, 1, 0);
+
+	ctrls->auto_gain = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_AUTOGAIN,
+					     0, 1, 1, 1);
+	ctrls->gain = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_GAIN, 0, 2047, 1, 0);
+
+	if (hdl->error) {
+		ret = hdl->error;
+		goto cleanup_entity;
+	}
+
+	ctrls->gain->flags |= V4L2_CTRL_FLAG_VOLATILE;
+	ctrls->exposure->flags |= V4L2_CTRL_FLAG_VOLATILE;
+
+	v4l2_ctrl_auto_cluster(2, &ctrls->auto_gain, 0, true);
+	v4l2_ctrl_auto_cluster(2, &ctrls->auto_exp, 1, true);
+
+	sensor->sd.ctrl_handler = hdl;
+
+	ret = v4l2_async_register_subdev(&sensor->sd);
+	if (ret < 0)
+		goto cleanup_entity;
+
+	return 0;
+
+cleanup_entity:
+	media_entity_cleanup(&sensor->sd.entity);
+	v4l2_ctrl_handler_free(hdl);
+
+	return ret;
+}
+
+static int ov2680_get_regulators(struct ov2680_dev *sensor)
+{
+	int i;
+
+	for (i = 0; i < OV2680_NUM_SUPPLIES; i++)
+		sensor->supplies[i].supply = ov2680_supply_name[i];
+
+	return devm_regulator_bulk_get(&sensor->i2c_client->dev,
+				       OV2680_NUM_SUPPLIES,
+				       sensor->supplies);
+}
+
+static int ov2680_check_id(struct ov2680_dev *sensor)
+{
+	struct device *dev = ov2680_to_dev(sensor);
+	u32 chip_id;
+	int ret;
+
+	ov2680_power_on(sensor);
+
+	ret = ov2680_read_reg16(sensor, OV2680_REG_CHIP_ID_HIGH, &chip_id);
+	if (ret < 0) {
+		dev_err(dev, "failed to read chip id high\n");
+		return -ENODEV;
+	}
+
+	if (chip_id != OV2680_CHIP_ID) {
+		dev_err(dev, "chip id: 0x%04x does not match expected 0x%04x\n",
+			chip_id, OV2680_CHIP_ID);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int ov2860_parse_dt(struct ov2680_dev *sensor)
+{
+	struct device *dev = ov2680_to_dev(sensor);
+	int ret;
+
+	sensor->reset_gpio = devm_gpiod_get_optional(dev, "reset",
+						     GPIOD_OUT_HIGH);
+	ret = PTR_ERR_OR_ZERO(sensor->reset_gpio);
+	if (ret < 0) {
+		dev_dbg(dev, "error while getting reset gpio: %d\n", ret);
+		return ret;
+	}
+
+	sensor->xvclk = devm_clk_get(dev, "xvclk");
+	if (IS_ERR(sensor->xvclk)) {
+		dev_err(dev, "xvclk clock missing or invalid\n");
+		return PTR_ERR(sensor->xvclk);
+	}
+
+	sensor->xvclk_freq = clk_get_rate(sensor->xvclk);
+	if (sensor->xvclk_freq != OV2680_XVCLK_VALUE) {
+		dev_err(dev, "wrong xvclk frequency %d HZ, expected: %d Hz\n",
+			sensor->xvclk_freq, OV2680_XVCLK_VALUE);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ov2680_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct ov2680_dev *sensor;
+	int ret;
+
+	sensor = devm_kzalloc(dev, sizeof(*sensor), GFP_KERNEL);
+	if (!sensor)
+		return -ENOMEM;
+
+	sensor->i2c_client = client;
+
+	ret = ov2860_parse_dt(sensor);
+	if (ret < 0)
+		return -EINVAL;
+
+	ret = ov2680_mode_init(sensor);
+	if (ret < 0)
+		return ret;
+
+	ret = ov2680_get_regulators(sensor);
+	if (ret < 0) {
+		dev_err(dev, "failed to get regulators\n");
+		return ret;
+	}
+
+	mutex_init(&sensor->lock);
+
+	ret = ov2680_v4l2_init(sensor);
+	if (ret < 0)
+		goto lock_destroy;
+
+	ret = ov2680_check_id(sensor);
+	if (ret < 0)
+		goto error_cleanup;
+
+	dev_info(dev, "ov2680 init correctly\n");
+
+	return 0;
+
+error_cleanup:
+	dev_err(dev, "ov2680 init fail: %d\n", ret);
+
+	media_entity_cleanup(&sensor->sd.entity);
+	v4l2_async_unregister_subdev(&sensor->sd);
+	v4l2_ctrl_handler_free(&sensor->ctrls.handler);
+
+lock_destroy:
+	mutex_destroy(&sensor->lock);
+
+	return ret;
+}
+
+static int ov2680_remove(struct i2c_client *client)
+{
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+
+	v4l2_async_unregister_subdev(&sensor->sd);
+	mutex_destroy(&sensor->lock);
+	media_entity_cleanup(&sensor->sd.entity);
+	v4l2_ctrl_handler_free(&sensor->ctrls.handler);
+
+	return 0;
+}
+
+static int __maybe_unused ov2680_suspend(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+
+	if (sensor->is_streaming)
+		ov2680_stream_disable(sensor);
+
+	return 0;
+}
+
+static int __maybe_unused ov2680_resume(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+	int ret;
+
+	if (sensor->is_streaming) {
+		ret = ov2680_stream_enable(sensor);
+		if (ret < 0)
+			goto stream_disable;
+	}
+
+	return 0;
+
+stream_disable:
+	ov2680_stream_disable(sensor);
+	sensor->is_streaming = false;
+
+	return ret;
+}
+
+static const struct dev_pm_ops ov2680_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(ov2680_suspend, ov2680_resume)
+};
+
+static const struct of_device_id ov2680_dt_ids[] = {
+	{ .compatible = "ovti,ov2680" },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, ov2680_dt_ids);
+
+static struct i2c_driver ov2680_i2c_driver = {
+	.driver = {
+		.name  = "ov2680",
+		.pm = &ov2680_pm_ops,
+		.of_match_table	= of_match_ptr(ov2680_dt_ids),
+	},
+	.probe_new	= ov2680_probe,
+	.remove		= ov2680_remove,
+};
+module_i2c_driver(ov2680_i2c_driver);
+
+MODULE_AUTHOR("Rui Miguel Silva <rui.silva@linaro.org>");
+MODULE_DESCRIPTION("OV2680 CMOS Image Sensor driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c
index f6e40cc9745c..071f4bc240ca 100644
--- a/drivers/media/i2c/ov5640.c
+++ b/drivers/media/i2c/ov5640.c
@@ -30,7 +30,7 @@
 
 /* min/typical/max system clock (xclk) frequencies */
 #define OV5640_XCLK_MIN  6000000
-#define OV5640_XCLK_MAX 24000000
+#define OV5640_XCLK_MAX 54000000
 
 #define OV5640_DEFAULT_SLAVE_ID 0x3c
 
@@ -64,6 +64,7 @@
 #define OV5640_REG_TIMING_DVPVO		0x380a
 #define OV5640_REG_TIMING_HTS		0x380c
 #define OV5640_REG_TIMING_VTS		0x380e
+#define OV5640_REG_TIMING_TC_REG20	0x3820
 #define OV5640_REG_TIMING_TC_REG21	0x3821
 #define OV5640_REG_AEC_CTRL00		0x3a00
 #define OV5640_REG_AEC_B50_STEP		0x3a08
@@ -199,6 +200,8 @@ struct ov5640_ctrls {
 	struct v4l2_ctrl *contrast;
 	struct v4l2_ctrl *hue;
 	struct v4l2_ctrl *test_pattern;
+	struct v4l2_ctrl *hflip;
+	struct v4l2_ctrl *vflip;
 };
 
 struct ov5640_dev {
@@ -212,6 +215,7 @@ struct ov5640_dev {
 	struct regulator_bulk_data supplies[OV5640_NUM_SUPPLIES];
 	struct gpio_desc *reset_gpio;
 	struct gpio_desc *pwdn_gpio;
+	bool   upside_down;
 
 	/* lock to protect all members below */
 	struct mutex lock;
@@ -341,7 +345,7 @@ static const struct reg_value ov5640_init_setting_30fps_VGA[] = {
 static const struct reg_value ov5640_setting_30fps_VGA_640_480[] = {
 	{0x3035, 0x14, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -360,7 +364,7 @@ static const struct reg_value ov5640_setting_30fps_VGA_640_480[] = {
 static const struct reg_value ov5640_setting_15fps_VGA_640_480[] = {
 	{0x3035, 0x22, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -379,7 +383,7 @@ static const struct reg_value ov5640_setting_15fps_VGA_640_480[] = {
 static const struct reg_value ov5640_setting_30fps_XGA_1024_768[] = {
 	{0x3035, 0x14, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -399,7 +403,7 @@ static const struct reg_value ov5640_setting_30fps_XGA_1024_768[] = {
 static const struct reg_value ov5640_setting_15fps_XGA_1024_768[] = {
 	{0x3035, 0x22, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -418,7 +422,7 @@ static const struct reg_value ov5640_setting_15fps_XGA_1024_768[] = {
 static const struct reg_value ov5640_setting_30fps_QVGA_320_240[] = {
 	{0x3035, 0x14, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -437,7 +441,7 @@ static const struct reg_value ov5640_setting_30fps_QVGA_320_240[] = {
 static const struct reg_value ov5640_setting_15fps_QVGA_320_240[] = {
 	{0x3035, 0x22, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -456,7 +460,7 @@ static const struct reg_value ov5640_setting_15fps_QVGA_320_240[] = {
 static const struct reg_value ov5640_setting_30fps_QCIF_176_144[] = {
 	{0x3035, 0x14, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -475,7 +479,7 @@ static const struct reg_value ov5640_setting_30fps_QCIF_176_144[] = {
 static const struct reg_value ov5640_setting_15fps_QCIF_176_144[] = {
 	{0x3035, 0x22, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -494,7 +498,7 @@ static const struct reg_value ov5640_setting_15fps_QCIF_176_144[] = {
 static const struct reg_value ov5640_setting_30fps_NTSC_720_480[] = {
 	{0x3035, 0x12, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -513,7 +517,7 @@ static const struct reg_value ov5640_setting_30fps_NTSC_720_480[] = {
 static const struct reg_value ov5640_setting_15fps_NTSC_720_480[] = {
 	{0x3035, 0x22, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -532,7 +536,7 @@ static const struct reg_value ov5640_setting_15fps_NTSC_720_480[] = {
 static const struct reg_value ov5640_setting_30fps_PAL_720_576[] = {
 	{0x3035, 0x12, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -551,7 +555,7 @@ static const struct reg_value ov5640_setting_30fps_PAL_720_576[] = {
 static const struct reg_value ov5640_setting_15fps_PAL_720_576[] = {
 	{0x3035, 0x22, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -571,7 +575,7 @@ static const struct reg_value ov5640_setting_30fps_720P_1280_720[] = {
 	{0x3008, 0x42, 0, 0},
 	{0x3035, 0x21, 0, 0}, {0x3036, 0x54, 0, 0}, {0x3c07, 0x07, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0xfa, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x06, 0, 0}, {0x3807, 0xa9, 0, 0},
@@ -591,7 +595,7 @@ static const struct reg_value ov5640_setting_30fps_720P_1280_720[] = {
 static const struct reg_value ov5640_setting_15fps_720P_1280_720[] = {
 	{0x3035, 0x41, 0, 0}, {0x3036, 0x54, 0, 0}, {0x3c07, 0x07, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0xfa, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x06, 0, 0}, {0x3807, 0xa9, 0, 0},
@@ -611,7 +615,7 @@ static const struct reg_value ov5640_setting_30fps_1080P_1920_1080[] = {
 	{0x3008, 0x42, 0, 0},
 	{0x3035, 0x21, 0, 0}, {0x3036, 0x54, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x40, 0, 0}, {0x3821, 0x06, 0, 0}, {0x3814, 0x11, 0, 0},
+	{0x3814, 0x11, 0, 0},
 	{0x3815, 0x11, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x00, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9f, 0, 0},
@@ -644,7 +648,7 @@ static const struct reg_value ov5640_setting_15fps_1080P_1920_1080[] = {
 	{0x3008, 0x42, 0, 0},
 	{0x3035, 0x21, 0, 0}, {0x3036, 0x54, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x40, 0, 0}, {0x3821, 0x06, 0, 0}, {0x3814, 0x11, 0, 0},
+	{0x3814, 0x11, 0, 0},
 	{0x3815, 0x11, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x00, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9f, 0, 0},
@@ -673,10 +677,9 @@ static const struct reg_value ov5640_setting_15fps_1080P_1920_1080[] = {
 };
 
 static const struct reg_value ov5640_setting_15fps_QSXGA_2592_1944[] = {
-	{0x3820, 0x40, 0, 0}, {0x3821, 0x06, 0, 0},
 	{0x3035, 0x21, 0, 0}, {0x3036, 0x54, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x40, 0, 0}, {0x3821, 0x06, 0, 0}, {0x3814, 0x11, 0, 0},
+	{0x3814, 0x11, 0, 0},
 	{0x3815, 0x11, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x00, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9f, 0, 0},
@@ -1340,6 +1343,27 @@ static int ov5640_binning_on(struct ov5640_dev *sensor)
 	return temp ? 1 : 0;
 }
 
+static int ov5640_set_binning(struct ov5640_dev *sensor, bool enable)
+{
+	int ret;
+
+	/*
+	 * TIMING TC REG21:
+	 * - [0]:	Horizontal binning enable
+	 */
+	ret = ov5640_mod_reg(sensor, OV5640_REG_TIMING_TC_REG21,
+			     BIT(0), enable ? BIT(0) : 0);
+	if (ret)
+		return ret;
+	/*
+	 * TIMING TC REG20:
+	 * - [0]:	Undocumented, but hardcoded init sequences
+	 *		are always setting REG21/REG20 bit 0 to same value...
+	 */
+	return ov5640_mod_reg(sensor, OV5640_REG_TIMING_TC_REG20,
+			      BIT(0), enable ? BIT(0) : 0);
+}
+
 static int ov5640_set_virtual_channel(struct ov5640_dev *sensor)
 {
 	struct i2c_client *client = sensor->i2c_client;
@@ -1389,24 +1413,16 @@ static const struct ov5640_mode_info *
 ov5640_find_mode(struct ov5640_dev *sensor, enum ov5640_frame_rate fr,
 		 int width, int height, bool nearest)
 {
-	const struct ov5640_mode_info *mode = NULL;
-	int i;
-
-	for (i = OV5640_NUM_MODES - 1; i >= 0; i--) {
-		mode = &ov5640_mode_data[fr][i];
-
-		if (!mode->reg_data)
-			continue;
+	const struct ov5640_mode_info *mode;
 
-		if ((nearest && mode->hact <= width &&
-		     mode->vact <= height) ||
-		    (!nearest && mode->hact == width &&
-		     mode->vact == height))
-			break;
-	}
+	mode = v4l2_find_nearest_size(ov5640_mode_data[fr],
+				      ARRAY_SIZE(ov5640_mode_data[fr]),
+				      hact, vact,
+				      width, height);
 
-	if (nearest && i < 0)
-		mode = &ov5640_mode_data[fr][0];
+	if (!mode ||
+	    (!nearest && (mode->hact != width || mode->vact != height)))
+		return NULL;
 
 	return mode;
 }
@@ -1640,6 +1656,9 @@ static int ov5640_set_mode(struct ov5640_dev *sensor,
 	if (ret < 0)
 		return ret;
 
+	ret = ov5640_set_binning(sensor, dn_mode != SCALING);
+	if (ret < 0)
+		return ret;
 	ret = ov5640_set_ae_target(sensor, sensor->ae_target);
 	if (ret < 0)
 		return ret;
@@ -1947,9 +1966,11 @@ static int ov5640_set_fmt(struct v4l2_subdev *sd,
 		goto out;
 	}
 
-	sensor->current_mode = new_mode;
-	sensor->fmt = *mbus_fmt;
-	sensor->pending_mode_change = true;
+	if (new_mode != sensor->current_mode) {
+		sensor->current_mode = new_mode;
+		sensor->fmt = *mbus_fmt;
+		sensor->pending_mode_change = true;
+	}
 out:
 	mutex_unlock(&sensor->lock);
 	return ret;
@@ -2193,6 +2214,43 @@ static int ov5640_set_ctrl_light_freq(struct ov5640_dev *sensor, int value)
 			      BIT(2) : 0);
 }
 
+static int ov5640_set_ctrl_hflip(struct ov5640_dev *sensor, int value)
+{
+	/*
+	 * If sensor is mounted upside down, mirror logic is inversed.
+	 *
+	 * Sensor is a BSI (Back Side Illuminated) one,
+	 * so image captured is physically mirrored.
+	 * This is why mirror logic is inversed in
+	 * order to cancel this mirror effect.
+	 */
+
+	/*
+	 * TIMING TC REG21:
+	 * - [2]:	ISP mirror
+	 * - [1]:	Sensor mirror
+	 */
+	return ov5640_mod_reg(sensor, OV5640_REG_TIMING_TC_REG21,
+			      BIT(2) | BIT(1),
+			      (!(value ^ sensor->upside_down)) ?
+			      (BIT(2) | BIT(1)) : 0);
+}
+
+static int ov5640_set_ctrl_vflip(struct ov5640_dev *sensor, int value)
+{
+	/* If sensor is mounted upside down, flip logic is inversed */
+
+	/*
+	 * TIMING TC REG20:
+	 * - [2]:	ISP vflip
+	 * - [1]:	Sensor vflip
+	 */
+	return ov5640_mod_reg(sensor, OV5640_REG_TIMING_TC_REG20,
+			      BIT(2) | BIT(1),
+			      (value ^ sensor->upside_down) ?
+			      (BIT(2) | BIT(1)) : 0);
+}
+
 static int ov5640_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
 {
 	struct v4l2_subdev *sd = ctrl_to_sd(ctrl);
@@ -2264,6 +2322,12 @@ static int ov5640_s_ctrl(struct v4l2_ctrl *ctrl)
 	case V4L2_CID_POWER_LINE_FREQUENCY:
 		ret = ov5640_set_ctrl_light_freq(sensor, ctrl->val);
 		break;
+	case V4L2_CID_HFLIP:
+		ret = ov5640_set_ctrl_hflip(sensor, ctrl->val);
+		break;
+	case V4L2_CID_VFLIP:
+		ret = ov5640_set_ctrl_vflip(sensor, ctrl->val);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -2325,6 +2389,10 @@ static int ov5640_init_controls(struct ov5640_dev *sensor)
 		v4l2_ctrl_new_std_menu_items(hdl, ops, V4L2_CID_TEST_PATTERN,
 					     ARRAY_SIZE(test_pattern_menu) - 1,
 					     0, 0, test_pattern_menu);
+	ctrls->hflip = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_HFLIP,
+					 0, 1, 1, 0);
+	ctrls->vflip = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_VFLIP,
+					 0, 1, 1, 0);
 
 	ctrls->light_freq =
 		v4l2_ctrl_new_std_menu(hdl, ops,
@@ -2435,9 +2503,17 @@ static int ov5640_s_frame_interval(struct v4l2_subdev *sd,
 
 	sensor->current_fr = frame_rate;
 	sensor->frame_interval = fi->interval;
-	sensor->current_mode = ov5640_find_mode(sensor, frame_rate, mode->hact,
-						mode->vact, true);
-	sensor->pending_mode_change = true;
+	mode = ov5640_find_mode(sensor, frame_rate, mode->hact,
+				mode->vact, true);
+	if (!mode) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (mode != sensor->current_mode) {
+		sensor->current_mode = mode;
+		sensor->pending_mode_change = true;
+	}
 out:
 	mutex_unlock(&sensor->lock);
 	return ret;
@@ -2558,6 +2634,7 @@ static int ov5640_probe(struct i2c_client *client,
 	struct fwnode_handle *endpoint;
 	struct ov5640_dev *sensor;
 	struct v4l2_mbus_framefmt *fmt;
+	u32 rotation;
 	int ret;
 
 	sensor = devm_kzalloc(dev, sizeof(*sensor), GFP_KERNEL);
@@ -2583,6 +2660,22 @@ static int ov5640_probe(struct i2c_client *client,
 
 	sensor->ae_target = 52;
 
+	/* optional indication of physical rotation of sensor */
+	ret = fwnode_property_read_u32(dev_fwnode(&client->dev), "rotation",
+				       &rotation);
+	if (!ret) {
+		switch (rotation) {
+		case 180:
+			sensor->upside_down = true;
+			/* fall through */
+		case 0:
+			break;
+		default:
+			dev_warn(dev, "%u degrees rotation is not supported, ignoring...\n",
+				 rotation);
+		}
+	}
+
 	endpoint = fwnode_graph_get_next_endpoint(dev_fwnode(&client->dev),
 						  NULL);
 	if (!endpoint) {
diff --git a/drivers/media/i2c/ov5645.c b/drivers/media/i2c/ov5645.c
index b3f762578f7f..1722cdab0daf 100644
--- a/drivers/media/i2c/ov5645.c
+++ b/drivers/media/i2c/ov5645.c
@@ -510,8 +510,8 @@ static const struct reg_value ov5645_setting_full[] = {
 };
 
 static const s64 link_freq[] = {
-	222880000,
-	334320000
+	224000000,
+	336000000
 };
 
 static const struct ov5645_mode_info ov5645_mode_info_data[] = {
@@ -520,7 +520,7 @@ static const struct ov5645_mode_info ov5645_mode_info_data[] = {
 		.height = 960,
 		.data = ov5645_setting_sxga,
 		.data_size = ARRAY_SIZE(ov5645_setting_sxga),
-		.pixel_clock = 111440000,
+		.pixel_clock = 112000000,
 		.link_freq = 0 /* an index in link_freq[] */
 	},
 	{
@@ -528,7 +528,7 @@ static const struct ov5645_mode_info ov5645_mode_info_data[] = {
 		.height = 1080,
 		.data = ov5645_setting_1080p,
 		.data_size = ARRAY_SIZE(ov5645_setting_1080p),
-		.pixel_clock = 167160000,
+		.pixel_clock = 168000000,
 		.link_freq = 1 /* an index in link_freq[] */
 	},
 	{
@@ -536,7 +536,7 @@ static const struct ov5645_mode_info ov5645_mode_info_data[] = {
 		.height = 1944,
 		.data = ov5645_setting_full,
 		.data_size = ARRAY_SIZE(ov5645_setting_full),
-		.pixel_clock = 167160000,
+		.pixel_clock = 168000000,
 		.link_freq = 1 /* an index in link_freq[] */
 	},
 };
@@ -1145,7 +1145,8 @@ static int ov5645_probe(struct i2c_client *client,
 		return ret;
 	}
 
-	if (xclk_freq != 23880000) {
+	/* external clock must be 24MHz, allow 1% tolerance */
+	if (xclk_freq < 23760000 || xclk_freq > 24240000) {
 		dev_err(dev, "external clock frequency %u is not supported\n",
 			xclk_freq);
 		return -EINVAL;
diff --git a/drivers/media/i2c/ov7670.c b/drivers/media/i2c/ov7670.c
index 3474ef832c1e..31bf577b0bd3 100644
--- a/drivers/media/i2c/ov7670.c
+++ b/drivers/media/i2c/ov7670.c
@@ -1744,14 +1744,12 @@ static int ov7670_parse_dt(struct device *dev,
 		return -EINVAL;
 
 	ret = v4l2_fwnode_endpoint_parse(ep, &bus_cfg);
-	if (ret) {
-		fwnode_handle_put(ep);
+	fwnode_handle_put(ep);
+	if (ret)
 		return ret;
-	}
 
 	if (bus_cfg.bus_type != V4L2_MBUS_PARALLEL) {
 		dev_err(dev, "Unsupported media bus type\n");
-		fwnode_handle_put(ep);
 		return ret;
 	}
 	info->mbus_config = bus_cfg.bus.parallel.flags;
diff --git a/drivers/media/i2c/ov772x.c b/drivers/media/i2c/ov772x.c
index e2550708abc8..7158c31d8403 100644
--- a/drivers/media/i2c/ov772x.c
+++ b/drivers/media/i2c/ov772x.c
@@ -419,11 +419,18 @@ struct ov772x_priv {
 	struct gpio_desc		 *rstb_gpio;
 	const struct ov772x_color_format *cfmt;
 	const struct ov772x_win_size     *win;
-	unsigned short                    flag_vflip:1;
-	unsigned short                    flag_hflip:1;
+	struct v4l2_ctrl		 *vflip_ctrl;
+	struct v4l2_ctrl		 *hflip_ctrl;
 	/* band_filter = COM8[5] ? 256 - BDBASE : 0 */
-	unsigned short                    band_filter;
+	struct v4l2_ctrl		 *band_filter_ctrl;
 	unsigned int			  fps;
+	/* lock to protect power_count and streaming */
+	struct mutex			  lock;
+	int				  power_count;
+	int				  streaming;
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct media_pad pad;
+#endif
 };
 
 /*
@@ -542,9 +549,19 @@ static struct ov772x_priv *to_ov772x(struct v4l2_subdev *sd)
 	return container_of(sd, struct ov772x_priv, subdev);
 }
 
-static inline int ov772x_read(struct i2c_client *client, u8 addr)
+static int ov772x_read(struct i2c_client *client, u8 addr)
 {
-	return i2c_smbus_read_byte_data(client, addr);
+	int ret;
+	u8 val;
+
+	ret = i2c_master_send(client, &addr, 1);
+	if (ret < 0)
+		return ret;
+	ret = i2c_master_recv(client, &val, 1);
+	if (ret < 0)
+		return ret;
+
+	return val;
 }
 
 static inline int ov772x_write(struct i2c_client *client, u8 addr, u8 value)
@@ -587,39 +604,40 @@ static int ov772x_s_stream(struct v4l2_subdev *sd, int enable)
 {
 	struct i2c_client *client = v4l2_get_subdevdata(sd);
 	struct ov772x_priv *priv = to_ov772x(sd);
+	int ret = 0;
 
-	if (!enable) {
-		ov772x_mask_set(client, COM2, SOFT_SLEEP_MODE, SOFT_SLEEP_MODE);
-		return 0;
-	}
+	mutex_lock(&priv->lock);
 
-	ov772x_mask_set(client, COM2, SOFT_SLEEP_MODE, 0);
+	if (priv->streaming == enable)
+		goto done;
 
-	dev_dbg(&client->dev, "format %d, win %s\n",
-		priv->cfmt->code, priv->win->name);
+	ret = ov772x_mask_set(client, COM2, SOFT_SLEEP_MODE,
+			      enable ? 0 : SOFT_SLEEP_MODE);
+	if (ret)
+		goto done;
 
-	return 0;
+	if (enable) {
+		dev_dbg(&client->dev, "format %d, win %s\n",
+			priv->cfmt->code, priv->win->name);
+	}
+	priv->streaming = enable;
+
+done:
+	mutex_unlock(&priv->lock);
+
+	return ret;
 }
 
-static int ov772x_set_frame_rate(struct ov772x_priv *priv,
-				 struct v4l2_fract *tpf,
-				 const struct ov772x_color_format *cfmt,
-				 const struct ov772x_win_size *win)
+static unsigned int ov772x_select_fps(struct ov772x_priv *priv,
+				      struct v4l2_fract *tpf)
 {
-	struct i2c_client *client = v4l2_get_subdevdata(&priv->subdev);
-	unsigned long fin = clk_get_rate(priv->clk);
 	unsigned int fps = tpf->numerator ?
 			   tpf->denominator / tpf->numerator :
 			   tpf->denominator;
 	unsigned int best_diff;
-	unsigned int fsize;
-	unsigned int pclk;
 	unsigned int diff;
 	unsigned int idx;
 	unsigned int i;
-	u8 clkrc = 0;
-	u8 com4 = 0;
-	int ret;
 
 	/* Approximate to the closest supported frame interval. */
 	best_diff = ~0L;
@@ -630,7 +648,25 @@ static int ov772x_set_frame_rate(struct ov772x_priv *priv,
 			best_diff = diff;
 		}
 	}
-	fps = ov772x_frame_intervals[idx];
+
+	return ov772x_frame_intervals[idx];
+}
+
+static int ov772x_set_frame_rate(struct ov772x_priv *priv,
+				 unsigned int fps,
+				 const struct ov772x_color_format *cfmt,
+				 const struct ov772x_win_size *win)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(&priv->subdev);
+	unsigned long fin = clk_get_rate(priv->clk);
+	unsigned int best_diff;
+	unsigned int fsize;
+	unsigned int pclk;
+	unsigned int diff;
+	unsigned int i;
+	u8 clkrc = 0;
+	u8 com4 = 0;
+	int ret;
 
 	/* Use image size (with blankings) to calculate desired pixel clock. */
 	switch (cfmt->com7 & OFMT_MASK) {
@@ -695,10 +731,6 @@ static int ov772x_set_frame_rate(struct ov772x_priv *priv,
 	if (ret < 0)
 		return ret;
 
-	tpf->numerator = 1;
-	tpf->denominator = fps;
-	priv->fps = tpf->denominator;
-
 	return 0;
 }
 
@@ -719,8 +751,37 @@ static int ov772x_s_frame_interval(struct v4l2_subdev *sd,
 {
 	struct ov772x_priv *priv = to_ov772x(sd);
 	struct v4l2_fract *tpf = &ival->interval;
+	unsigned int fps;
+	int ret = 0;
+
+	mutex_lock(&priv->lock);
 
-	return ov772x_set_frame_rate(priv, tpf, priv->cfmt, priv->win);
+	if (priv->streaming) {
+		ret = -EBUSY;
+		goto error;
+	}
+
+	fps = ov772x_select_fps(priv, tpf);
+
+	/*
+	 * If the device is not powered up by the host driver do
+	 * not apply any changes to H/W at this time. Instead
+	 * the frame rate will be restored right after power-up.
+	 */
+	if (priv->power_count > 0) {
+		ret = ov772x_set_frame_rate(priv, fps, priv->cfmt, priv->win);
+		if (ret)
+			goto error;
+	}
+
+	tpf->numerator = 1;
+	tpf->denominator = fps;
+	priv->fps = fps;
+
+error:
+	mutex_unlock(&priv->lock);
+
+	return ret;
 }
 
 static int ov772x_s_ctrl(struct v4l2_ctrl *ctrl)
@@ -732,17 +793,25 @@ static int ov772x_s_ctrl(struct v4l2_ctrl *ctrl)
 	int ret = 0;
 	u8 val;
 
+	/* v4l2_ctrl_lock() locks our own mutex */
+
+	/*
+	 * If the device is not powered up by the host driver do
+	 * not apply any controls to H/W at this time. Instead
+	 * the controls will be restored right after power-up.
+	 */
+	if (priv->power_count == 0)
+		return 0;
+
 	switch (ctrl->id) {
 	case V4L2_CID_VFLIP:
 		val = ctrl->val ? VFLIP_IMG : 0x00;
-		priv->flag_vflip = ctrl->val;
-		if (priv->info->flags & OV772X_FLAG_VFLIP)
+		if (priv->info && (priv->info->flags & OV772X_FLAG_VFLIP))
 			val ^= VFLIP_IMG;
 		return ov772x_mask_set(client, COM3, VFLIP_IMG, val);
 	case V4L2_CID_HFLIP:
 		val = ctrl->val ? HFLIP_IMG : 0x00;
-		priv->flag_hflip = ctrl->val;
-		if (priv->info->flags & OV772X_FLAG_HFLIP)
+		if (priv->info && (priv->info->flags & OV772X_FLAG_HFLIP))
 			val ^= HFLIP_IMG;
 		return ov772x_mask_set(client, COM3, HFLIP_IMG, val);
 	case V4L2_CID_BAND_STOP_FILTER:
@@ -761,8 +830,7 @@ static int ov772x_s_ctrl(struct v4l2_ctrl *ctrl)
 				ret = ov772x_mask_set(client, BDBASE,
 						      0xff, val);
 		}
-		if (!ret)
-			priv->band_filter = ctrl->val;
+
 		return ret;
 	}
 
@@ -824,10 +892,10 @@ static int ov772x_power_on(struct ov772x_priv *priv)
 	 * available to handle this cleanly, request the GPIO temporarily
 	 * to avoid conflicts.
 	 */
-	priv->rstb_gpio = gpiod_get_optional(&client->dev, "rstb",
+	priv->rstb_gpio = gpiod_get_optional(&client->dev, "reset",
 					     GPIOD_OUT_LOW);
 	if (IS_ERR(priv->rstb_gpio)) {
-		dev_info(&client->dev, "Unable to get GPIO \"rstb\"");
+		dev_info(&client->dev, "Unable to get GPIO \"reset\"");
 		return PTR_ERR(priv->rstb_gpio);
 	}
 
@@ -855,12 +923,45 @@ static int ov772x_power_off(struct ov772x_priv *priv)
 	return 0;
 }
 
+static int ov772x_set_params(struct ov772x_priv *priv,
+			     const struct ov772x_color_format *cfmt,
+			     const struct ov772x_win_size *win);
+
 static int ov772x_s_power(struct v4l2_subdev *sd, int on)
 {
 	struct ov772x_priv *priv = to_ov772x(sd);
+	int ret = 0;
+
+	mutex_lock(&priv->lock);
+
+	/* If the power count is modified from 0 to != 0 or from != 0 to 0,
+	 * update the power state.
+	 */
+	if (priv->power_count == !on) {
+		if (on) {
+			ret = ov772x_power_on(priv);
+			/*
+			 * Restore the format, the frame rate, and
+			 * the controls
+			 */
+			if (!ret)
+				ret = ov772x_set_params(priv, priv->cfmt,
+							priv->win);
+		} else {
+			ret = ov772x_power_off(priv);
+		}
+	}
 
-	return on ? ov772x_power_on(priv) :
-		    ov772x_power_off(priv);
+	if (!ret) {
+		/* Update the power count. */
+		priv->power_count += on ? 1 : -1;
+		WARN(priv->power_count < 0, "Unbalanced power count\n");
+		WARN(priv->power_count > 1, "Duplicated s_power call\n");
+	}
+
+	mutex_unlock(&priv->lock);
+
+	return ret;
 }
 
 static const struct ov772x_win_size *ov772x_select_win(u32 width, u32 height)
@@ -901,19 +1002,14 @@ static void ov772x_select_params(const struct v4l2_mbus_framefmt *mf,
 	*win = ov772x_select_win(mf->width, mf->height);
 }
 
-static int ov772x_set_params(struct ov772x_priv *priv,
-			     const struct ov772x_color_format *cfmt,
-			     const struct ov772x_win_size *win)
+static int ov772x_edgectrl(struct ov772x_priv *priv)
 {
 	struct i2c_client *client = v4l2_get_subdevdata(&priv->subdev);
-	struct v4l2_fract tpf;
 	int ret;
-	u8  val;
 
-	/* Reset hardware. */
-	ov772x_reset(client);
+	if (!priv->info)
+		return 0;
 
-	/* Edge Ctrl. */
 	if (priv->info->edgectrl.strength & OV772X_MANUAL_EDGE_CTRL) {
 		/*
 		 * Manual Edge Control Mode.
@@ -924,19 +1020,19 @@ static int ov772x_set_params(struct ov772x_priv *priv,
 
 		ret = ov772x_mask_set(client, DSPAUTO, EDGE_ACTRL, 0x00);
 		if (ret < 0)
-			goto ov772x_set_fmt_error;
+			return ret;
 
 		ret = ov772x_mask_set(client,
 				      EDGE_TRSHLD, OV772X_EDGE_THRESHOLD_MASK,
 				      priv->info->edgectrl.threshold);
 		if (ret < 0)
-			goto ov772x_set_fmt_error;
+			return ret;
 
 		ret = ov772x_mask_set(client,
 				      EDGE_STRNGT, OV772X_EDGE_STRENGTH_MASK,
 				      priv->info->edgectrl.strength);
 		if (ret < 0)
-			goto ov772x_set_fmt_error;
+			return ret;
 
 	} else if (priv->info->edgectrl.upper > priv->info->edgectrl.lower) {
 		/*
@@ -948,15 +1044,34 @@ static int ov772x_set_params(struct ov772x_priv *priv,
 				      EDGE_UPPER, OV772X_EDGE_UPPER_MASK,
 				      priv->info->edgectrl.upper);
 		if (ret < 0)
-			goto ov772x_set_fmt_error;
+			return ret;
 
 		ret = ov772x_mask_set(client,
 				      EDGE_LOWER, OV772X_EDGE_LOWER_MASK,
 				      priv->info->edgectrl.lower);
 		if (ret < 0)
-			goto ov772x_set_fmt_error;
+			return ret;
 	}
 
+	return 0;
+}
+
+static int ov772x_set_params(struct ov772x_priv *priv,
+			     const struct ov772x_color_format *cfmt,
+			     const struct ov772x_win_size *win)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(&priv->subdev);
+	int ret;
+	u8  val;
+
+	/* Reset hardware. */
+	ov772x_reset(client);
+
+	/* Edge Ctrl. */
+	ret = ov772x_edgectrl(priv);
+	if (ret < 0)
+		return ret;
+
 	/* Format and window size. */
 	ret = ov772x_write(client, HSTART, win->rect.left >> 2);
 	if (ret < 0)
@@ -1007,13 +1122,13 @@ static int ov772x_set_params(struct ov772x_priv *priv,
 
 	/* Set COM3. */
 	val = cfmt->com3;
-	if (priv->info->flags & OV772X_FLAG_VFLIP)
+	if (priv->info && (priv->info->flags & OV772X_FLAG_VFLIP))
 		val |= VFLIP_IMG;
-	if (priv->info->flags & OV772X_FLAG_HFLIP)
+	if (priv->info && (priv->info->flags & OV772X_FLAG_HFLIP))
 		val |= HFLIP_IMG;
-	if (priv->flag_vflip)
+	if (priv->vflip_ctrl->val)
 		val ^= VFLIP_IMG;
-	if (priv->flag_hflip)
+	if (priv->hflip_ctrl->val)
 		val ^= HFLIP_IMG;
 
 	ret = ov772x_mask_set(client,
@@ -1027,18 +1142,18 @@ static int ov772x_set_params(struct ov772x_priv *priv,
 		goto ov772x_set_fmt_error;
 
 	/* COM4, CLKRC: Set pixel clock and framerate. */
-	tpf.numerator = 1;
-	tpf.denominator = priv->fps;
-	ret = ov772x_set_frame_rate(priv, &tpf, cfmt, win);
+	ret = ov772x_set_frame_rate(priv, priv->fps, cfmt, win);
 	if (ret < 0)
 		goto ov772x_set_fmt_error;
 
 	/* Set COM8. */
-	if (priv->band_filter) {
+	if (priv->band_filter_ctrl->val) {
+		unsigned short band_filter = priv->band_filter_ctrl->val;
+
 		ret = ov772x_mask_set(client, COM8, BNDF_ON_OFF, BNDF_ON_OFF);
 		if (!ret)
 			ret = ov772x_mask_set(client, BDBASE,
-					      0xff, 256 - priv->band_filter);
+					      0xff, 256 - band_filter);
 		if (ret < 0)
 			goto ov772x_set_fmt_error;
 	}
@@ -1102,7 +1217,7 @@ static int ov772x_set_fmt(struct v4l2_subdev *sd,
 	struct v4l2_mbus_framefmt *mf = &format->format;
 	const struct ov772x_color_format *cfmt;
 	const struct ov772x_win_size *win;
-	int ret;
+	int ret = 0;
 
 	if (format->pad)
 		return -EINVAL;
@@ -1123,30 +1238,50 @@ static int ov772x_set_fmt(struct v4l2_subdev *sd,
 		return 0;
 	}
 
-	ret = ov772x_set_params(priv, cfmt, win);
-	if (ret < 0)
-		return ret;
+	mutex_lock(&priv->lock);
+
+	if (priv->streaming) {
+		ret = -EBUSY;
+		goto error;
+	}
 
+	/*
+	 * If the device is not powered up by the host driver do
+	 * not apply any changes to H/W at this time. Instead
+	 * the format will be restored right after power-up.
+	 */
+	if (priv->power_count > 0) {
+		ret = ov772x_set_params(priv, cfmt, win);
+		if (ret < 0)
+			goto error;
+	}
 	priv->win = win;
 	priv->cfmt = cfmt;
 
-	return 0;
+error:
+	mutex_unlock(&priv->lock);
+
+	return ret;
 }
 
 static int ov772x_video_probe(struct ov772x_priv *priv)
 {
 	struct i2c_client  *client = v4l2_get_subdevdata(&priv->subdev);
-	u8                  pid, ver;
+	int		    pid, ver, midh, midl;
 	const char         *devname;
 	int		    ret;
 
-	ret = ov772x_s_power(&priv->subdev, 1);
+	ret = ov772x_power_on(priv);
 	if (ret < 0)
 		return ret;
 
 	/* Check and show product ID and manufacturer ID. */
 	pid = ov772x_read(client, PID);
+	if (pid < 0)
+		return pid;
 	ver = ov772x_read(client, VER);
+	if (ver < 0)
+		return ver;
 
 	switch (VERSION(pid, ver)) {
 	case OV7720:
@@ -1162,17 +1297,21 @@ static int ov772x_video_probe(struct ov772x_priv *priv)
 		goto done;
 	}
 
+	midh = ov772x_read(client, MIDH);
+	if (midh < 0)
+		return midh;
+	midl = ov772x_read(client, MIDL);
+	if (midl < 0)
+		return midl;
+
 	dev_info(&client->dev,
 		 "%s Product ID %0x:%0x Manufacturer ID %x:%x\n",
-		 devname,
-		 pid,
-		 ver,
-		 ov772x_read(client, MIDH),
-		 ov772x_read(client, MIDL));
+		 devname, pid, ver, midh, midl);
+
 	ret = v4l2_ctrl_handler_setup(&priv->hdl);
 
 done:
-	ov772x_s_power(&priv->subdev, 0);
+	ov772x_power_off(priv);
 
 	return ret;
 }
@@ -1250,48 +1389,54 @@ static int ov772x_probe(struct i2c_client *client,
 	struct i2c_adapter	*adapter = client->adapter;
 	int			ret;
 
-	if (!client->dev.platform_data) {
-		dev_err(&client->dev, "Missing ov772x platform data\n");
+	if (!client->dev.of_node && !client->dev.platform_data) {
+		dev_err(&client->dev,
+			"Missing ov772x platform data for non-DT device\n");
 		return -EINVAL;
 	}
 
-	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA |
-					      I2C_FUNC_PROTOCOL_MANGLING)) {
+	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA)) {
 		dev_err(&adapter->dev,
-			"I2C-Adapter doesn't support SMBUS_BYTE_DATA or PROTOCOL_MANGLING\n");
+			"I2C-Adapter doesn't support SMBUS_BYTE_DATA\n");
 		return -EIO;
 	}
-	client->flags |= I2C_CLIENT_SCCB;
 
 	priv = devm_kzalloc(&client->dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
 	priv->info = client->dev.platform_data;
+	mutex_init(&priv->lock);
 
 	v4l2_i2c_subdev_init(&priv->subdev, client, &ov772x_subdev_ops);
+	priv->subdev.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	v4l2_ctrl_handler_init(&priv->hdl, 3);
-	v4l2_ctrl_new_std(&priv->hdl, &ov772x_ctrl_ops,
-			  V4L2_CID_VFLIP, 0, 1, 1, 0);
-	v4l2_ctrl_new_std(&priv->hdl, &ov772x_ctrl_ops,
-			  V4L2_CID_HFLIP, 0, 1, 1, 0);
-	v4l2_ctrl_new_std(&priv->hdl, &ov772x_ctrl_ops,
-			  V4L2_CID_BAND_STOP_FILTER, 0, 256, 1, 0);
+	/* Use our mutex for the controls */
+	priv->hdl.lock = &priv->lock;
+	priv->vflip_ctrl = v4l2_ctrl_new_std(&priv->hdl, &ov772x_ctrl_ops,
+					     V4L2_CID_VFLIP, 0, 1, 1, 0);
+	priv->hflip_ctrl = v4l2_ctrl_new_std(&priv->hdl, &ov772x_ctrl_ops,
+					     V4L2_CID_HFLIP, 0, 1, 1, 0);
+	priv->band_filter_ctrl = v4l2_ctrl_new_std(&priv->hdl, &ov772x_ctrl_ops,
+						   V4L2_CID_BAND_STOP_FILTER,
+						   0, 256, 1, 0);
 	priv->subdev.ctrl_handler = &priv->hdl;
-	if (priv->hdl.error)
-		return priv->hdl.error;
+	if (priv->hdl.error) {
+		ret = priv->hdl.error;
+		goto error_mutex_destroy;
+	}
 
-	priv->clk = clk_get(&client->dev, "xclk");
+	priv->clk = clk_get(&client->dev, NULL);
 	if (IS_ERR(priv->clk)) {
 		dev_err(&client->dev, "Unable to get xclk clock\n");
 		ret = PTR_ERR(priv->clk);
 		goto error_ctrl_free;
 	}
 
-	priv->pwdn_gpio = gpiod_get_optional(&client->dev, "pwdn",
+	priv->pwdn_gpio = gpiod_get_optional(&client->dev, "powerdown",
 					     GPIOD_OUT_LOW);
 	if (IS_ERR(priv->pwdn_gpio)) {
-		dev_info(&client->dev, "Unable to get GPIO \"pwdn\"");
+		dev_info(&client->dev, "Unable to get GPIO \"powerdown\"");
 		ret = PTR_ERR(priv->pwdn_gpio);
 		goto error_clk_put;
 	}
@@ -1300,16 +1445,26 @@ static int ov772x_probe(struct i2c_client *client,
 	if (ret < 0)
 		goto error_gpio_put;
 
+#ifdef CONFIG_MEDIA_CONTROLLER
+	priv->pad.flags = MEDIA_PAD_FL_SOURCE;
+	priv->subdev.entity.function = MEDIA_ENT_F_CAM_SENSOR;
+	ret = media_entity_pads_init(&priv->subdev.entity, 1, &priv->pad);
+	if (ret < 0)
+		goto error_gpio_put;
+#endif
+
 	priv->cfmt = &ov772x_cfmts[0];
 	priv->win = &ov772x_win_sizes[0];
 	priv->fps = 15;
 
 	ret = v4l2_async_register_subdev(&priv->subdev);
 	if (ret)
-		goto error_gpio_put;
+		goto error_entity_cleanup;
 
 	return 0;
 
+error_entity_cleanup:
+	media_entity_cleanup(&priv->subdev.entity);
 error_gpio_put:
 	if (priv->pwdn_gpio)
 		gpiod_put(priv->pwdn_gpio);
@@ -1317,6 +1472,8 @@ error_clk_put:
 	clk_put(priv->clk);
 error_ctrl_free:
 	v4l2_ctrl_handler_free(&priv->hdl);
+error_mutex_destroy:
+	mutex_destroy(&priv->lock);
 
 	return ret;
 }
@@ -1325,11 +1482,13 @@ static int ov772x_remove(struct i2c_client *client)
 {
 	struct ov772x_priv *priv = to_ov772x(i2c_get_clientdata(client));
 
+	media_entity_cleanup(&priv->subdev.entity);
 	clk_put(priv->clk);
 	if (priv->pwdn_gpio)
 		gpiod_put(priv->pwdn_gpio);
 	v4l2_async_unregister_subdev(&priv->subdev);
 	v4l2_ctrl_handler_free(&priv->hdl);
+	mutex_destroy(&priv->lock);
 
 	return 0;
 }
@@ -1340,9 +1499,17 @@ static const struct i2c_device_id ov772x_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ov772x_id);
 
+static const struct of_device_id ov772x_of_match[] = {
+	{ .compatible = "ovti,ov7725", },
+	{ .compatible = "ovti,ov7720", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, ov772x_of_match);
+
 static struct i2c_driver ov772x_i2c_driver = {
 	.driver = {
 		.name = "ov772x",
+		.of_match_table = ov772x_of_match,
 	},
 	.probe    = ov772x_probe,
 	.remove   = ov772x_remove,
diff --git a/drivers/media/i2c/rj54n1cb0c.c b/drivers/media/i2c/rj54n1cb0c.c
new file mode 100644
index 000000000000..6ad998ad1b16
--- /dev/null
+++ b/drivers/media/i2c/rj54n1cb0c.c
@@ -0,0 +1,1437 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Driver for RJ54N1CB0C CMOS Image Sensor from Sharp
+ *
+ * Copyright (C) 2018, Jacopo Mondi <jacopo@jmondi.org>
+ *
+ * Copyright (C) 2009, Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/v4l2-mediabus.h>
+#include <linux/videodev2.h>
+
+#include <media/i2c/rj54n1cb0c.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-subdev.h>
+
+#define RJ54N1_DEV_CODE			0x0400
+#define RJ54N1_DEV_CODE2		0x0401
+#define RJ54N1_OUT_SEL			0x0403
+#define RJ54N1_XY_OUTPUT_SIZE_S_H	0x0404
+#define RJ54N1_X_OUTPUT_SIZE_S_L	0x0405
+#define RJ54N1_Y_OUTPUT_SIZE_S_L	0x0406
+#define RJ54N1_XY_OUTPUT_SIZE_P_H	0x0407
+#define RJ54N1_X_OUTPUT_SIZE_P_L	0x0408
+#define RJ54N1_Y_OUTPUT_SIZE_P_L	0x0409
+#define RJ54N1_LINE_LENGTH_PCK_S_H	0x040a
+#define RJ54N1_LINE_LENGTH_PCK_S_L	0x040b
+#define RJ54N1_LINE_LENGTH_PCK_P_H	0x040c
+#define RJ54N1_LINE_LENGTH_PCK_P_L	0x040d
+#define RJ54N1_RESIZE_N			0x040e
+#define RJ54N1_RESIZE_N_STEP		0x040f
+#define RJ54N1_RESIZE_STEP		0x0410
+#define RJ54N1_RESIZE_HOLD_H		0x0411
+#define RJ54N1_RESIZE_HOLD_L		0x0412
+#define RJ54N1_H_OBEN_OFS		0x0413
+#define RJ54N1_V_OBEN_OFS		0x0414
+#define RJ54N1_RESIZE_CONTROL		0x0415
+#define RJ54N1_STILL_CONTROL		0x0417
+#define RJ54N1_INC_USE_SEL_H		0x0425
+#define RJ54N1_INC_USE_SEL_L		0x0426
+#define RJ54N1_MIRROR_STILL_MODE	0x0427
+#define RJ54N1_INIT_START		0x0428
+#define RJ54N1_SCALE_1_2_LEV		0x0429
+#define RJ54N1_SCALE_4_LEV		0x042a
+#define RJ54N1_Y_GAIN			0x04d8
+#define RJ54N1_APT_GAIN_UP		0x04fa
+#define RJ54N1_RA_SEL_UL		0x0530
+#define RJ54N1_BYTE_SWAP		0x0531
+#define RJ54N1_OUT_SIGPO		0x053b
+#define RJ54N1_WB_SEL_WEIGHT_I		0x054e
+#define RJ54N1_BIT8_WB			0x0569
+#define RJ54N1_HCAPS_WB			0x056a
+#define RJ54N1_VCAPS_WB			0x056b
+#define RJ54N1_HCAPE_WB			0x056c
+#define RJ54N1_VCAPE_WB			0x056d
+#define RJ54N1_EXPOSURE_CONTROL		0x058c
+#define RJ54N1_FRAME_LENGTH_S_H		0x0595
+#define RJ54N1_FRAME_LENGTH_S_L		0x0596
+#define RJ54N1_FRAME_LENGTH_P_H		0x0597
+#define RJ54N1_FRAME_LENGTH_P_L		0x0598
+#define RJ54N1_PEAK_H			0x05b7
+#define RJ54N1_PEAK_50			0x05b8
+#define RJ54N1_PEAK_60			0x05b9
+#define RJ54N1_PEAK_DIFF		0x05ba
+#define RJ54N1_IOC			0x05ef
+#define RJ54N1_TG_BYPASS		0x0700
+#define RJ54N1_PLL_L			0x0701
+#define RJ54N1_PLL_N			0x0702
+#define RJ54N1_PLL_EN			0x0704
+#define RJ54N1_RATIO_TG			0x0706
+#define RJ54N1_RATIO_T			0x0707
+#define RJ54N1_RATIO_R			0x0708
+#define RJ54N1_RAMP_TGCLK_EN		0x0709
+#define RJ54N1_OCLK_DSP			0x0710
+#define RJ54N1_RATIO_OP			0x0711
+#define RJ54N1_RATIO_O			0x0712
+#define RJ54N1_OCLK_SEL_EN		0x0713
+#define RJ54N1_CLK_RST			0x0717
+#define RJ54N1_RESET_STANDBY		0x0718
+#define RJ54N1_FWFLG			0x07fe
+
+#define E_EXCLK				(1 << 7)
+#define SOFT_STDBY			(1 << 4)
+#define SEN_RSTX			(1 << 2)
+#define TG_RSTX				(1 << 1)
+#define DSP_RSTX			(1 << 0)
+
+#define RESIZE_HOLD_SEL			(1 << 2)
+#define RESIZE_GO			(1 << 1)
+
+/*
+ * When cropping, the camera automatically centers the cropped region, there
+ * doesn't seem to be a way to specify an explicit location of the rectangle.
+ */
+#define RJ54N1_COLUMN_SKIP		0
+#define RJ54N1_ROW_SKIP			0
+#define RJ54N1_MAX_WIDTH		1600
+#define RJ54N1_MAX_HEIGHT		1200
+
+#define PLL_L				2
+#define PLL_N				0x31
+
+/* I2C addresses: 0x50, 0x51, 0x60, 0x61 */
+
+/* RJ54N1CB0C has only one fixed colorspace per pixelcode */
+struct rj54n1_datafmt {
+	u32	code;
+	enum v4l2_colorspace		colorspace;
+};
+
+/* Find a data format by a pixel code in an array */
+static const struct rj54n1_datafmt *rj54n1_find_datafmt(
+	u32 code, const struct rj54n1_datafmt *fmt,
+	int n)
+{
+	int i;
+	for (i = 0; i < n; i++)
+		if (fmt[i].code == code)
+			return fmt + i;
+
+	return NULL;
+}
+
+static const struct rj54n1_datafmt rj54n1_colour_fmts[] = {
+	{MEDIA_BUS_FMT_YUYV8_2X8, V4L2_COLORSPACE_JPEG},
+	{MEDIA_BUS_FMT_YVYU8_2X8, V4L2_COLORSPACE_JPEG},
+	{MEDIA_BUS_FMT_RGB565_2X8_LE, V4L2_COLORSPACE_SRGB},
+	{MEDIA_BUS_FMT_RGB565_2X8_BE, V4L2_COLORSPACE_SRGB},
+	{MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE, V4L2_COLORSPACE_SRGB},
+	{MEDIA_BUS_FMT_SBGGR10_2X8_PADLO_LE, V4L2_COLORSPACE_SRGB},
+	{MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_BE, V4L2_COLORSPACE_SRGB},
+	{MEDIA_BUS_FMT_SBGGR10_2X8_PADLO_BE, V4L2_COLORSPACE_SRGB},
+	{MEDIA_BUS_FMT_SBGGR10_1X10, V4L2_COLORSPACE_SRGB},
+};
+
+struct rj54n1_clock_div {
+	u8 ratio_tg;	/* can be 0 or an odd number */
+	u8 ratio_t;
+	u8 ratio_r;
+	u8 ratio_op;
+	u8 ratio_o;
+};
+
+struct rj54n1 {
+	struct v4l2_subdev subdev;
+	struct v4l2_ctrl_handler hdl;
+	struct clk *clk;
+	struct gpio_desc *pwup_gpio;
+	struct gpio_desc *enable_gpio;
+	struct rj54n1_clock_div clk_div;
+	const struct rj54n1_datafmt *fmt;
+	struct v4l2_rect rect;	/* Sensor window */
+	unsigned int tgclk_mhz;
+	bool auto_wb;
+	unsigned short width;	/* Output window */
+	unsigned short height;
+	unsigned short resize;	/* Sensor * 1024 / resize = Output */
+	unsigned short scale;
+	u8 bank;
+};
+
+struct rj54n1_reg_val {
+	u16 reg;
+	u8 val;
+};
+
+static const struct rj54n1_reg_val bank_4[] = {
+	{0x417, 0},
+	{0x42c, 0},
+	{0x42d, 0xf0},
+	{0x42e, 0},
+	{0x42f, 0x50},
+	{0x430, 0xf5},
+	{0x431, 0x16},
+	{0x432, 0x20},
+	{0x433, 0},
+	{0x434, 0xc8},
+	{0x43c, 8},
+	{0x43e, 0x90},
+	{0x445, 0x83},
+	{0x4ba, 0x58},
+	{0x4bb, 4},
+	{0x4bc, 0x20},
+	{0x4db, 4},
+	{0x4fe, 2},
+};
+
+static const struct rj54n1_reg_val bank_5[] = {
+	{0x514, 0},
+	{0x516, 0},
+	{0x518, 0},
+	{0x51a, 0},
+	{0x51d, 0xff},
+	{0x56f, 0x28},
+	{0x575, 0x40},
+	{0x5bc, 0x48},
+	{0x5c1, 6},
+	{0x5e5, 0x11},
+	{0x5e6, 0x43},
+	{0x5e7, 0x33},
+	{0x5e8, 0x21},
+	{0x5e9, 0x30},
+	{0x5ea, 0x0},
+	{0x5eb, 0xa5},
+	{0x5ec, 0xff},
+	{0x5fe, 2},
+};
+
+static const struct rj54n1_reg_val bank_7[] = {
+	{0x70a, 0},
+	{0x714, 0xff},
+	{0x715, 0xff},
+	{0x716, 0x1f},
+	{0x7FE, 2},
+};
+
+static const struct rj54n1_reg_val bank_8[] = {
+	{0x800, 0x00},
+	{0x801, 0x01},
+	{0x802, 0x61},
+	{0x805, 0x00},
+	{0x806, 0x00},
+	{0x807, 0x00},
+	{0x808, 0x00},
+	{0x809, 0x01},
+	{0x80A, 0x61},
+	{0x80B, 0x00},
+	{0x80C, 0x01},
+	{0x80D, 0x00},
+	{0x80E, 0x00},
+	{0x80F, 0x00},
+	{0x810, 0x00},
+	{0x811, 0x01},
+	{0x812, 0x61},
+	{0x813, 0x00},
+	{0x814, 0x11},
+	{0x815, 0x00},
+	{0x816, 0x41},
+	{0x817, 0x00},
+	{0x818, 0x51},
+	{0x819, 0x01},
+	{0x81A, 0x1F},
+	{0x81B, 0x00},
+	{0x81C, 0x01},
+	{0x81D, 0x00},
+	{0x81E, 0x11},
+	{0x81F, 0x00},
+	{0x820, 0x41},
+	{0x821, 0x00},
+	{0x822, 0x51},
+	{0x823, 0x00},
+	{0x824, 0x00},
+	{0x825, 0x00},
+	{0x826, 0x47},
+	{0x827, 0x01},
+	{0x828, 0x4F},
+	{0x829, 0x00},
+	{0x82A, 0x00},
+	{0x82B, 0x00},
+	{0x82C, 0x30},
+	{0x82D, 0x00},
+	{0x82E, 0x40},
+	{0x82F, 0x00},
+	{0x830, 0xB3},
+	{0x831, 0x00},
+	{0x832, 0xE3},
+	{0x833, 0x00},
+	{0x834, 0x00},
+	{0x835, 0x00},
+	{0x836, 0x00},
+	{0x837, 0x00},
+	{0x838, 0x00},
+	{0x839, 0x01},
+	{0x83A, 0x61},
+	{0x83B, 0x00},
+	{0x83C, 0x01},
+	{0x83D, 0x00},
+	{0x83E, 0x00},
+	{0x83F, 0x00},
+	{0x840, 0x00},
+	{0x841, 0x01},
+	{0x842, 0x61},
+	{0x843, 0x00},
+	{0x844, 0x1D},
+	{0x845, 0x00},
+	{0x846, 0x00},
+	{0x847, 0x00},
+	{0x848, 0x00},
+	{0x849, 0x01},
+	{0x84A, 0x1F},
+	{0x84B, 0x00},
+	{0x84C, 0x05},
+	{0x84D, 0x00},
+	{0x84E, 0x19},
+	{0x84F, 0x01},
+	{0x850, 0x21},
+	{0x851, 0x01},
+	{0x852, 0x5D},
+	{0x853, 0x00},
+	{0x854, 0x00},
+	{0x855, 0x00},
+	{0x856, 0x19},
+	{0x857, 0x01},
+	{0x858, 0x21},
+	{0x859, 0x00},
+	{0x85A, 0x00},
+	{0x85B, 0x00},
+	{0x85C, 0x00},
+	{0x85D, 0x00},
+	{0x85E, 0x00},
+	{0x85F, 0x00},
+	{0x860, 0xB3},
+	{0x861, 0x00},
+	{0x862, 0xE3},
+	{0x863, 0x00},
+	{0x864, 0x00},
+	{0x865, 0x00},
+	{0x866, 0x00},
+	{0x867, 0x00},
+	{0x868, 0x00},
+	{0x869, 0xE2},
+	{0x86A, 0x00},
+	{0x86B, 0x01},
+	{0x86C, 0x06},
+	{0x86D, 0x00},
+	{0x86E, 0x00},
+	{0x86F, 0x00},
+	{0x870, 0x60},
+	{0x871, 0x8C},
+	{0x872, 0x10},
+	{0x873, 0x00},
+	{0x874, 0xE0},
+	{0x875, 0x00},
+	{0x876, 0x27},
+	{0x877, 0x01},
+	{0x878, 0x00},
+	{0x879, 0x00},
+	{0x87A, 0x00},
+	{0x87B, 0x03},
+	{0x87C, 0x00},
+	{0x87D, 0x00},
+	{0x87E, 0x00},
+	{0x87F, 0x00},
+	{0x880, 0x00},
+	{0x881, 0x00},
+	{0x882, 0x00},
+	{0x883, 0x00},
+	{0x884, 0x00},
+	{0x885, 0x00},
+	{0x886, 0xF8},
+	{0x887, 0x00},
+	{0x888, 0x03},
+	{0x889, 0x00},
+	{0x88A, 0x64},
+	{0x88B, 0x00},
+	{0x88C, 0x03},
+	{0x88D, 0x00},
+	{0x88E, 0xB1},
+	{0x88F, 0x00},
+	{0x890, 0x03},
+	{0x891, 0x01},
+	{0x892, 0x1D},
+	{0x893, 0x00},
+	{0x894, 0x03},
+	{0x895, 0x01},
+	{0x896, 0x4B},
+	{0x897, 0x00},
+	{0x898, 0xE5},
+	{0x899, 0x00},
+	{0x89A, 0x01},
+	{0x89B, 0x00},
+	{0x89C, 0x01},
+	{0x89D, 0x04},
+	{0x89E, 0xC8},
+	{0x89F, 0x00},
+	{0x8A0, 0x01},
+	{0x8A1, 0x01},
+	{0x8A2, 0x61},
+	{0x8A3, 0x00},
+	{0x8A4, 0x01},
+	{0x8A5, 0x00},
+	{0x8A6, 0x00},
+	{0x8A7, 0x00},
+	{0x8A8, 0x00},
+	{0x8A9, 0x00},
+	{0x8AA, 0x7F},
+	{0x8AB, 0x03},
+	{0x8AC, 0x00},
+	{0x8AD, 0x00},
+	{0x8AE, 0x00},
+	{0x8AF, 0x00},
+	{0x8B0, 0x00},
+	{0x8B1, 0x00},
+	{0x8B6, 0x00},
+	{0x8B7, 0x01},
+	{0x8B8, 0x00},
+	{0x8B9, 0x00},
+	{0x8BA, 0x02},
+	{0x8BB, 0x00},
+	{0x8BC, 0xFF},
+	{0x8BD, 0x00},
+	{0x8FE, 2},
+};
+
+static const struct rj54n1_reg_val bank_10[] = {
+	{0x10bf, 0x69}
+};
+
+/* Clock dividers - these are default register values, divider = register + 1 */
+static const struct rj54n1_clock_div clk_div = {
+	.ratio_tg	= 3 /* default: 5 */,
+	.ratio_t	= 4 /* default: 1 */,
+	.ratio_r	= 4 /* default: 0 */,
+	.ratio_op	= 1 /* default: 5 */,
+	.ratio_o	= 9 /* default: 0 */,
+};
+
+static struct rj54n1 *to_rj54n1(const struct i2c_client *client)
+{
+	return container_of(i2c_get_clientdata(client), struct rj54n1, subdev);
+}
+
+static int reg_read(struct i2c_client *client, const u16 reg)
+{
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+	int ret;
+
+	/* set bank */
+	if (rj54n1->bank != reg >> 8) {
+		dev_dbg(&client->dev, "[0x%x] = 0x%x\n", 0xff, reg >> 8);
+		ret = i2c_smbus_write_byte_data(client, 0xff, reg >> 8);
+		if (ret < 0)
+			return ret;
+		rj54n1->bank = reg >> 8;
+	}
+	return i2c_smbus_read_byte_data(client, reg & 0xff);
+}
+
+static int reg_write(struct i2c_client *client, const u16 reg,
+		     const u8 data)
+{
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+	int ret;
+
+	/* set bank */
+	if (rj54n1->bank != reg >> 8) {
+		dev_dbg(&client->dev, "[0x%x] = 0x%x\n", 0xff, reg >> 8);
+		ret = i2c_smbus_write_byte_data(client, 0xff, reg >> 8);
+		if (ret < 0)
+			return ret;
+		rj54n1->bank = reg >> 8;
+	}
+	dev_dbg(&client->dev, "[0x%x] = 0x%x\n", reg & 0xff, data);
+	return i2c_smbus_write_byte_data(client, reg & 0xff, data);
+}
+
+static int reg_set(struct i2c_client *client, const u16 reg,
+		   const u8 data, const u8 mask)
+{
+	int ret;
+
+	ret = reg_read(client, reg);
+	if (ret < 0)
+		return ret;
+	return reg_write(client, reg, (ret & ~mask) | (data & mask));
+}
+
+static int reg_write_multiple(struct i2c_client *client,
+			      const struct rj54n1_reg_val *rv, const int n)
+{
+	int i, ret;
+
+	for (i = 0; i < n; i++) {
+		ret = reg_write(client, rv->reg, rv->val);
+		if (ret < 0)
+			return ret;
+		rv++;
+	}
+
+	return 0;
+}
+
+static int rj54n1_enum_mbus_code(struct v4l2_subdev *sd,
+		struct v4l2_subdev_pad_config *cfg,
+		struct v4l2_subdev_mbus_code_enum *code)
+{
+	if (code->pad || code->index >= ARRAY_SIZE(rj54n1_colour_fmts))
+		return -EINVAL;
+
+	code->code = rj54n1_colour_fmts[code->index].code;
+	return 0;
+}
+
+static int rj54n1_s_stream(struct v4l2_subdev *sd, int enable)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+
+	/* Switch between preview and still shot modes */
+	return reg_set(client, RJ54N1_STILL_CONTROL, (!enable) << 7, 0x80);
+}
+
+static int rj54n1_set_rect(struct i2c_client *client,
+			   u16 reg_x, u16 reg_y, u16 reg_xy,
+			   u32 width, u32 height)
+{
+	int ret;
+
+	ret = reg_write(client, reg_xy,
+			((width >> 4) & 0x70) |
+			((height >> 8) & 7));
+
+	if (!ret)
+		ret = reg_write(client, reg_x, width & 0xff);
+	if (!ret)
+		ret = reg_write(client, reg_y, height & 0xff);
+
+	return ret;
+}
+
+/*
+ * Some commands, specifically certain initialisation sequences, require
+ * a commit operation.
+ */
+static int rj54n1_commit(struct i2c_client *client)
+{
+	int ret = reg_write(client, RJ54N1_INIT_START, 1);
+	msleep(10);
+	if (!ret)
+		ret = reg_write(client, RJ54N1_INIT_START, 0);
+	return ret;
+}
+
+static int rj54n1_sensor_scale(struct v4l2_subdev *sd, s32 *in_w, s32 *in_h,
+			       s32 *out_w, s32 *out_h);
+
+static int rj54n1_set_selection(struct v4l2_subdev *sd,
+				struct v4l2_subdev_pad_config *cfg,
+				struct v4l2_subdev_selection *sel)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+	const struct v4l2_rect *rect = &sel->r;
+	int output_w, output_h, input_w = rect->width, input_h = rect->height;
+	int ret;
+
+	if (sel->which != V4L2_SUBDEV_FORMAT_ACTIVE ||
+	    sel->target != V4L2_SEL_TGT_CROP)
+		return -EINVAL;
+
+	/* arbitrary minimum width and height, edges unimportant */
+	v4l_bound_align_image(&input_w, 8, RJ54N1_MAX_WIDTH, 0,
+			      &input_h, 8, RJ54N1_MAX_HEIGHT, 0, 0);
+
+	output_w = (input_w * 1024 + rj54n1->resize / 2) / rj54n1->resize;
+	output_h = (input_h * 1024 + rj54n1->resize / 2) / rj54n1->resize;
+
+	dev_dbg(&client->dev, "Scaling for %dx%d : %u = %dx%d\n",
+		input_w, input_h, rj54n1->resize, output_w, output_h);
+
+	ret = rj54n1_sensor_scale(sd, &input_w, &input_h, &output_w, &output_h);
+	if (ret < 0)
+		return ret;
+
+	rj54n1->width		= output_w;
+	rj54n1->height		= output_h;
+	rj54n1->resize		= ret;
+	rj54n1->rect.width	= input_w;
+	rj54n1->rect.height	= input_h;
+
+	return 0;
+}
+
+static int rj54n1_get_selection(struct v4l2_subdev *sd,
+				struct v4l2_subdev_pad_config *cfg,
+				struct v4l2_subdev_selection *sel)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+
+	if (sel->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
+	switch (sel->target) {
+	case V4L2_SEL_TGT_CROP_BOUNDS:
+	case V4L2_SEL_TGT_CROP_DEFAULT:
+		sel->r.left = RJ54N1_COLUMN_SKIP;
+		sel->r.top = RJ54N1_ROW_SKIP;
+		sel->r.width = RJ54N1_MAX_WIDTH;
+		sel->r.height = RJ54N1_MAX_HEIGHT;
+		return 0;
+	case V4L2_SEL_TGT_CROP:
+		sel->r = rj54n1->rect;
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int rj54n1_get_fmt(struct v4l2_subdev *sd,
+		struct v4l2_subdev_pad_config *cfg,
+		struct v4l2_subdev_format *format)
+{
+	struct v4l2_mbus_framefmt *mf = &format->format;
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+
+	if (format->pad)
+		return -EINVAL;
+
+	mf->code	= rj54n1->fmt->code;
+	mf->colorspace	= rj54n1->fmt->colorspace;
+	mf->ycbcr_enc	= V4L2_YCBCR_ENC_601;
+	mf->xfer_func	= V4L2_XFER_FUNC_SRGB;
+	mf->quantization = V4L2_QUANTIZATION_DEFAULT;
+	mf->field	= V4L2_FIELD_NONE;
+	mf->width	= rj54n1->width;
+	mf->height	= rj54n1->height;
+
+	return 0;
+}
+
+/*
+ * The actual geometry configuration routine. It scales the input window into
+ * the output one, updates the window sizes and returns an error or the resize
+ * coefficient on success. Note: we only use the "Fixed Scaling" on this camera.
+ */
+static int rj54n1_sensor_scale(struct v4l2_subdev *sd, s32 *in_w, s32 *in_h,
+			       s32 *out_w, s32 *out_h)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+	unsigned int skip, resize, input_w = *in_w, input_h = *in_h,
+		output_w = *out_w, output_h = *out_h;
+	u16 inc_sel, wb_bit8, wb_left, wb_right, wb_top, wb_bottom;
+	unsigned int peak, peak_50, peak_60;
+	int ret;
+
+	/*
+	 * We have a problem with crops, where the window is larger than 512x384
+	 * and output window is larger than a half of the input one. In this
+	 * case we have to either reduce the input window to equal or below
+	 * 512x384 or the output window to equal or below 1/2 of the input.
+	 */
+	if (output_w > max(512U, input_w / 2)) {
+		if (2 * output_w > RJ54N1_MAX_WIDTH) {
+			input_w = RJ54N1_MAX_WIDTH;
+			output_w = RJ54N1_MAX_WIDTH / 2;
+		} else {
+			input_w = output_w * 2;
+		}
+
+		dev_dbg(&client->dev, "Adjusted output width: in %u, out %u\n",
+			input_w, output_w);
+	}
+
+	if (output_h > max(384U, input_h / 2)) {
+		if (2 * output_h > RJ54N1_MAX_HEIGHT) {
+			input_h = RJ54N1_MAX_HEIGHT;
+			output_h = RJ54N1_MAX_HEIGHT / 2;
+		} else {
+			input_h = output_h * 2;
+		}
+
+		dev_dbg(&client->dev, "Adjusted output height: in %u, out %u\n",
+			input_h, output_h);
+	}
+
+	/* Idea: use the read mode for snapshots, handle separate geometries */
+	ret = rj54n1_set_rect(client, RJ54N1_X_OUTPUT_SIZE_S_L,
+			      RJ54N1_Y_OUTPUT_SIZE_S_L,
+			      RJ54N1_XY_OUTPUT_SIZE_S_H, output_w, output_h);
+	if (!ret)
+		ret = rj54n1_set_rect(client, RJ54N1_X_OUTPUT_SIZE_P_L,
+			      RJ54N1_Y_OUTPUT_SIZE_P_L,
+			      RJ54N1_XY_OUTPUT_SIZE_P_H, output_w, output_h);
+
+	if (ret < 0)
+		return ret;
+
+	if (output_w > input_w && output_h > input_h) {
+		input_w = output_w;
+		input_h = output_h;
+
+		resize = 1024;
+	} else {
+		unsigned int resize_x, resize_y;
+		resize_x = (input_w * 1024 + output_w / 2) / output_w;
+		resize_y = (input_h * 1024 + output_h / 2) / output_h;
+
+		/* We want max(resize_x, resize_y), check if it still fits */
+		if (resize_x > resize_y &&
+		    (output_h * resize_x + 512) / 1024 > RJ54N1_MAX_HEIGHT)
+			resize = (RJ54N1_MAX_HEIGHT * 1024 + output_h / 2) /
+				output_h;
+		else if (resize_y > resize_x &&
+			 (output_w * resize_y + 512) / 1024 > RJ54N1_MAX_WIDTH)
+			resize = (RJ54N1_MAX_WIDTH * 1024 + output_w / 2) /
+				output_w;
+		else
+			resize = max(resize_x, resize_y);
+
+		/* Prohibited value ranges */
+		switch (resize) {
+		case 2040 ... 2047:
+			resize = 2039;
+			break;
+		case 4080 ... 4095:
+			resize = 4079;
+			break;
+		case 8160 ... 8191:
+			resize = 8159;
+			break;
+		case 16320 ... 16384:
+			resize = 16319;
+		}
+	}
+
+	/* Set scaling */
+	ret = reg_write(client, RJ54N1_RESIZE_HOLD_L, resize & 0xff);
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RESIZE_HOLD_H, resize >> 8);
+
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Configure a skipping bitmask. The sensor will select a skipping value
+	 * among set bits automatically. This is very unclear in the datasheet
+	 * too. I was told, in this register one enables all skipping values,
+	 * that are required for a specific resize, and the camera selects
+	 * automatically, which ones to use. But it is unclear how to identify,
+	 * which cropping values are needed. Secondly, why don't we just set all
+	 * bits and let the camera choose? Would it increase processing time and
+	 * reduce the framerate? Using 0xfffc for INC_USE_SEL doesn't seem to
+	 * improve the image quality or stability for larger frames (see comment
+	 * above), but I didn't check the framerate.
+	 */
+	skip = min(resize / 1024, 15U);
+
+	inc_sel = 1 << skip;
+
+	if (inc_sel <= 2)
+		inc_sel = 0xc;
+	else if (resize & 1023 && skip < 15)
+		inc_sel |= 1 << (skip + 1);
+
+	ret = reg_write(client, RJ54N1_INC_USE_SEL_L, inc_sel & 0xfc);
+	if (!ret)
+		ret = reg_write(client, RJ54N1_INC_USE_SEL_H, inc_sel >> 8);
+
+	if (!rj54n1->auto_wb) {
+		/* Auto white balance window */
+		wb_left	  = output_w / 16;
+		wb_right  = (3 * output_w / 4 - 3) / 4;
+		wb_top	  = output_h / 16;
+		wb_bottom = (3 * output_h / 4 - 3) / 4;
+		wb_bit8	  = ((wb_left >> 2) & 0x40) | ((wb_top >> 4) & 0x10) |
+			((wb_right >> 6) & 4) | ((wb_bottom >> 8) & 1);
+
+		if (!ret)
+			ret = reg_write(client, RJ54N1_BIT8_WB, wb_bit8);
+		if (!ret)
+			ret = reg_write(client, RJ54N1_HCAPS_WB, wb_left);
+		if (!ret)
+			ret = reg_write(client, RJ54N1_VCAPS_WB, wb_top);
+		if (!ret)
+			ret = reg_write(client, RJ54N1_HCAPE_WB, wb_right);
+		if (!ret)
+			ret = reg_write(client, RJ54N1_VCAPE_WB, wb_bottom);
+	}
+
+	/* Antiflicker */
+	peak = 12 * RJ54N1_MAX_WIDTH * (1 << 14) * resize / rj54n1->tgclk_mhz /
+		10000;
+	peak_50 = peak / 6;
+	peak_60 = peak / 5;
+
+	if (!ret)
+		ret = reg_write(client, RJ54N1_PEAK_H,
+				((peak_50 >> 4) & 0xf0) | (peak_60 >> 8));
+	if (!ret)
+		ret = reg_write(client, RJ54N1_PEAK_50, peak_50);
+	if (!ret)
+		ret = reg_write(client, RJ54N1_PEAK_60, peak_60);
+	if (!ret)
+		ret = reg_write(client, RJ54N1_PEAK_DIFF, peak / 150);
+
+	/* Start resizing */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RESIZE_CONTROL,
+				RESIZE_HOLD_SEL | RESIZE_GO | 1);
+
+	if (ret < 0)
+		return ret;
+
+	/* Constant taken from manufacturer's example */
+	msleep(230);
+
+	ret = reg_write(client, RJ54N1_RESIZE_CONTROL, RESIZE_HOLD_SEL | 1);
+	if (ret < 0)
+		return ret;
+
+	*in_w = (output_w * resize + 512) / 1024;
+	*in_h = (output_h * resize + 512) / 1024;
+	*out_w = output_w;
+	*out_h = output_h;
+
+	dev_dbg(&client->dev, "Scaled for %dx%d : %u = %ux%u, skip %u\n",
+		*in_w, *in_h, resize, output_w, output_h, skip);
+
+	return resize;
+}
+
+static int rj54n1_set_clock(struct i2c_client *client)
+{
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+	int ret;
+
+	/* Enable external clock */
+	ret = reg_write(client, RJ54N1_RESET_STANDBY, E_EXCLK | SOFT_STDBY);
+	/* Leave stand-by. Note: use this when implementing suspend / resume */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RESET_STANDBY, E_EXCLK);
+
+	if (!ret)
+		ret = reg_write(client, RJ54N1_PLL_L, PLL_L);
+	if (!ret)
+		ret = reg_write(client, RJ54N1_PLL_N, PLL_N);
+
+	/* TGCLK dividers */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RATIO_TG,
+				rj54n1->clk_div.ratio_tg);
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RATIO_T,
+				rj54n1->clk_div.ratio_t);
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RATIO_R,
+				rj54n1->clk_div.ratio_r);
+
+	/* Enable TGCLK & RAMP */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RAMP_TGCLK_EN, 3);
+
+	/* Disable clock output */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_OCLK_DSP, 0);
+
+	/* Set divisors */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RATIO_OP,
+				rj54n1->clk_div.ratio_op);
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RATIO_O,
+				rj54n1->clk_div.ratio_o);
+
+	/* Enable OCLK */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_OCLK_SEL_EN, 1);
+
+	/* Use PLL for Timing Generator, write 2 to reserved bits */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_TG_BYPASS, 2);
+
+	/* Take sensor out of reset */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RESET_STANDBY,
+				E_EXCLK | SEN_RSTX);
+	/* Enable PLL */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_PLL_EN, 1);
+
+	/* Wait for PLL to stabilise */
+	msleep(10);
+
+	/* Enable clock to frequency divider */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_CLK_RST, 1);
+
+	if (!ret)
+		ret = reg_read(client, RJ54N1_CLK_RST);
+	if (ret != 1) {
+		dev_err(&client->dev,
+			"Resetting RJ54N1CB0C clock failed: %d!\n", ret);
+		return -EIO;
+	}
+
+	/* Start the PLL */
+	ret = reg_set(client, RJ54N1_OCLK_DSP, 1, 1);
+
+	/* Enable OCLK */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_OCLK_SEL_EN, 1);
+
+	return ret;
+}
+
+static int rj54n1_reg_init(struct i2c_client *client)
+{
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+	int ret = rj54n1_set_clock(client);
+
+	if (!ret)
+		ret = reg_write_multiple(client, bank_7, ARRAY_SIZE(bank_7));
+	if (!ret)
+		ret = reg_write_multiple(client, bank_10, ARRAY_SIZE(bank_10));
+
+	/* Set binning divisors */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_SCALE_1_2_LEV, 3 | (7 << 4));
+	if (!ret)
+		ret = reg_write(client, RJ54N1_SCALE_4_LEV, 0xf);
+
+	/* Switch to fixed resize mode */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RESIZE_CONTROL,
+				RESIZE_HOLD_SEL | 1);
+
+	/* Set gain */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_Y_GAIN, 0x84);
+
+	/*
+	 * Mirror the image back: default is upside down and left-to-right...
+	 * Set manual preview / still shot switching
+	 */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_MIRROR_STILL_MODE, 0x27);
+
+	if (!ret)
+		ret = reg_write_multiple(client, bank_4, ARRAY_SIZE(bank_4));
+
+	/* Auto exposure area */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_EXPOSURE_CONTROL, 0x80);
+	/* Check current auto WB config */
+	if (!ret)
+		ret = reg_read(client, RJ54N1_WB_SEL_WEIGHT_I);
+	if (ret >= 0) {
+		rj54n1->auto_wb = ret & 0x80;
+		ret = reg_write_multiple(client, bank_5, ARRAY_SIZE(bank_5));
+	}
+	if (!ret)
+		ret = reg_write_multiple(client, bank_8, ARRAY_SIZE(bank_8));
+
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RESET_STANDBY,
+				E_EXCLK | DSP_RSTX | SEN_RSTX);
+
+	/* Commit init */
+	if (!ret)
+		ret = rj54n1_commit(client);
+
+	/* Take DSP, TG, sensor out of reset */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RESET_STANDBY,
+				E_EXCLK | DSP_RSTX | TG_RSTX | SEN_RSTX);
+
+	/* Start register update? Same register as 0x?FE in many bank_* sets */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_FWFLG, 2);
+
+	/* Constant taken from manufacturer's example */
+	msleep(700);
+
+	return ret;
+}
+
+static int rj54n1_set_fmt(struct v4l2_subdev *sd,
+		struct v4l2_subdev_pad_config *cfg,
+		struct v4l2_subdev_format *format)
+{
+	struct v4l2_mbus_framefmt *mf = &format->format;
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+	const struct rj54n1_datafmt *fmt;
+	int output_w, output_h, max_w, max_h,
+		input_w = rj54n1->rect.width, input_h = rj54n1->rect.height;
+	int align = mf->code == MEDIA_BUS_FMT_SBGGR10_1X10 ||
+		mf->code == MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_BE ||
+		mf->code == MEDIA_BUS_FMT_SBGGR10_2X8_PADLO_BE ||
+		mf->code == MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE ||
+		mf->code == MEDIA_BUS_FMT_SBGGR10_2X8_PADLO_LE;
+	int ret;
+
+	if (format->pad)
+		return -EINVAL;
+
+	dev_dbg(&client->dev, "%s: code = %d, width = %u, height = %u\n",
+		__func__, mf->code, mf->width, mf->height);
+
+	fmt = rj54n1_find_datafmt(mf->code, rj54n1_colour_fmts,
+				  ARRAY_SIZE(rj54n1_colour_fmts));
+	if (!fmt) {
+		fmt = rj54n1->fmt;
+		mf->code = fmt->code;
+	}
+
+	mf->field	= V4L2_FIELD_NONE;
+	mf->colorspace	= fmt->colorspace;
+
+	v4l_bound_align_image(&mf->width, 112, RJ54N1_MAX_WIDTH, align,
+			      &mf->height, 84, RJ54N1_MAX_HEIGHT, align, 0);
+
+	if (format->which == V4L2_SUBDEV_FORMAT_TRY) {
+		cfg->try_fmt = *mf;
+		return 0;
+	}
+
+	/*
+	 * Verify if the sensor has just been powered on. TODO: replace this
+	 * with proper PM, when a suitable API is available.
+	 */
+	ret = reg_read(client, RJ54N1_RESET_STANDBY);
+	if (ret < 0)
+		return ret;
+
+	if (!(ret & E_EXCLK)) {
+		ret = rj54n1_reg_init(client);
+		if (ret < 0)
+			return ret;
+	}
+
+	/* RA_SEL_UL is only relevant for raw modes, ignored otherwise. */
+	switch (mf->code) {
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+		ret = reg_write(client, RJ54N1_OUT_SEL, 0);
+		if (!ret)
+			ret = reg_set(client, RJ54N1_BYTE_SWAP, 8, 8);
+		break;
+	case MEDIA_BUS_FMT_YVYU8_2X8:
+		ret = reg_write(client, RJ54N1_OUT_SEL, 0);
+		if (!ret)
+			ret = reg_set(client, RJ54N1_BYTE_SWAP, 0, 8);
+		break;
+	case MEDIA_BUS_FMT_RGB565_2X8_LE:
+		ret = reg_write(client, RJ54N1_OUT_SEL, 0x11);
+		if (!ret)
+			ret = reg_set(client, RJ54N1_BYTE_SWAP, 8, 8);
+		break;
+	case MEDIA_BUS_FMT_RGB565_2X8_BE:
+		ret = reg_write(client, RJ54N1_OUT_SEL, 0x11);
+		if (!ret)
+			ret = reg_set(client, RJ54N1_BYTE_SWAP, 0, 8);
+		break;
+	case MEDIA_BUS_FMT_SBGGR10_2X8_PADLO_LE:
+		ret = reg_write(client, RJ54N1_OUT_SEL, 4);
+		if (!ret)
+			ret = reg_set(client, RJ54N1_BYTE_SWAP, 8, 8);
+		if (!ret)
+			ret = reg_write(client, RJ54N1_RA_SEL_UL, 0);
+		break;
+	case MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE:
+		ret = reg_write(client, RJ54N1_OUT_SEL, 4);
+		if (!ret)
+			ret = reg_set(client, RJ54N1_BYTE_SWAP, 8, 8);
+		if (!ret)
+			ret = reg_write(client, RJ54N1_RA_SEL_UL, 8);
+		break;
+	case MEDIA_BUS_FMT_SBGGR10_2X8_PADLO_BE:
+		ret = reg_write(client, RJ54N1_OUT_SEL, 4);
+		if (!ret)
+			ret = reg_set(client, RJ54N1_BYTE_SWAP, 0, 8);
+		if (!ret)
+			ret = reg_write(client, RJ54N1_RA_SEL_UL, 0);
+		break;
+	case MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_BE:
+		ret = reg_write(client, RJ54N1_OUT_SEL, 4);
+		if (!ret)
+			ret = reg_set(client, RJ54N1_BYTE_SWAP, 0, 8);
+		if (!ret)
+			ret = reg_write(client, RJ54N1_RA_SEL_UL, 8);
+		break;
+	case MEDIA_BUS_FMT_SBGGR10_1X10:
+		ret = reg_write(client, RJ54N1_OUT_SEL, 5);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	/* Special case: a raw mode with 10 bits of data per clock tick */
+	if (!ret)
+		ret = reg_set(client, RJ54N1_OCLK_SEL_EN,
+			      (mf->code == MEDIA_BUS_FMT_SBGGR10_1X10) << 1, 2);
+
+	if (ret < 0)
+		return ret;
+
+	/* Supported scales 1:1 >= scale > 1:16 */
+	max_w = mf->width * (16 * 1024 - 1) / 1024;
+	if (input_w > max_w)
+		input_w = max_w;
+	max_h = mf->height * (16 * 1024 - 1) / 1024;
+	if (input_h > max_h)
+		input_h = max_h;
+
+	output_w = mf->width;
+	output_h = mf->height;
+
+	ret = rj54n1_sensor_scale(sd, &input_w, &input_h, &output_w, &output_h);
+	if (ret < 0)
+		return ret;
+
+	fmt = rj54n1_find_datafmt(mf->code, rj54n1_colour_fmts,
+				  ARRAY_SIZE(rj54n1_colour_fmts));
+
+	rj54n1->fmt		= fmt;
+	rj54n1->resize		= ret;
+	rj54n1->rect.width	= input_w;
+	rj54n1->rect.height	= input_h;
+	rj54n1->width		= output_w;
+	rj54n1->height		= output_h;
+
+	mf->width		= output_w;
+	mf->height		= output_h;
+	mf->field		= V4L2_FIELD_NONE;
+	mf->colorspace		= fmt->colorspace;
+
+	return 0;
+}
+
+#ifdef CONFIG_VIDEO_ADV_DEBUG
+static int rj54n1_g_register(struct v4l2_subdev *sd,
+			     struct v4l2_dbg_register *reg)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+
+	if (reg->reg < 0x400 || reg->reg > 0x1fff)
+		/* Registers > 0x0800 are only available from Sharp support */
+		return -EINVAL;
+
+	reg->size = 1;
+	reg->val = reg_read(client, reg->reg);
+
+	if (reg->val > 0xff)
+		return -EIO;
+
+	return 0;
+}
+
+static int rj54n1_s_register(struct v4l2_subdev *sd,
+			     const struct v4l2_dbg_register *reg)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+
+	if (reg->reg < 0x400 || reg->reg > 0x1fff)
+		/* Registers >= 0x0800 are only available from Sharp support */
+		return -EINVAL;
+
+	if (reg_write(client, reg->reg, reg->val) < 0)
+		return -EIO;
+
+	return 0;
+}
+#endif
+
+static int rj54n1_s_power(struct v4l2_subdev *sd, int on)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+
+	if (on) {
+		if (rj54n1->pwup_gpio)
+			gpiod_set_value(rj54n1->pwup_gpio, 1);
+		if (rj54n1->enable_gpio)
+			gpiod_set_value(rj54n1->enable_gpio, 1);
+
+		msleep(1);
+
+		return clk_prepare_enable(rj54n1->clk);
+	}
+
+	clk_disable_unprepare(rj54n1->clk);
+
+	if (rj54n1->enable_gpio)
+		gpiod_set_value(rj54n1->enable_gpio, 0);
+	if (rj54n1->pwup_gpio)
+		gpiod_set_value(rj54n1->pwup_gpio, 0);
+
+	return 0;
+}
+
+static int rj54n1_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct rj54n1 *rj54n1 = container_of(ctrl->handler, struct rj54n1, hdl);
+	struct v4l2_subdev *sd = &rj54n1->subdev;
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	int data;
+
+	switch (ctrl->id) {
+	case V4L2_CID_VFLIP:
+		if (ctrl->val)
+			data = reg_set(client, RJ54N1_MIRROR_STILL_MODE, 0, 1);
+		else
+			data = reg_set(client, RJ54N1_MIRROR_STILL_MODE, 1, 1);
+		if (data < 0)
+			return -EIO;
+		return 0;
+	case V4L2_CID_HFLIP:
+		if (ctrl->val)
+			data = reg_set(client, RJ54N1_MIRROR_STILL_MODE, 0, 2);
+		else
+			data = reg_set(client, RJ54N1_MIRROR_STILL_MODE, 2, 2);
+		if (data < 0)
+			return -EIO;
+		return 0;
+	case V4L2_CID_GAIN:
+		if (reg_write(client, RJ54N1_Y_GAIN, ctrl->val * 2) < 0)
+			return -EIO;
+		return 0;
+	case V4L2_CID_AUTO_WHITE_BALANCE:
+		/* Auto WB area - whole image */
+		if (reg_set(client, RJ54N1_WB_SEL_WEIGHT_I, ctrl->val << 7,
+			    0x80) < 0)
+			return -EIO;
+		rj54n1->auto_wb = ctrl->val;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static const struct v4l2_ctrl_ops rj54n1_ctrl_ops = {
+	.s_ctrl = rj54n1_s_ctrl,
+};
+
+static const struct v4l2_subdev_core_ops rj54n1_subdev_core_ops = {
+#ifdef CONFIG_VIDEO_ADV_DEBUG
+	.g_register	= rj54n1_g_register,
+	.s_register	= rj54n1_s_register,
+#endif
+	.s_power	= rj54n1_s_power,
+};
+
+static const struct v4l2_subdev_video_ops rj54n1_subdev_video_ops = {
+	.s_stream	= rj54n1_s_stream,
+};
+
+static const struct v4l2_subdev_pad_ops rj54n1_subdev_pad_ops = {
+	.enum_mbus_code = rj54n1_enum_mbus_code,
+	.get_selection	= rj54n1_get_selection,
+	.set_selection	= rj54n1_set_selection,
+	.get_fmt	= rj54n1_get_fmt,
+	.set_fmt	= rj54n1_set_fmt,
+};
+
+static const struct v4l2_subdev_ops rj54n1_subdev_ops = {
+	.core	= &rj54n1_subdev_core_ops,
+	.video	= &rj54n1_subdev_video_ops,
+	.pad	= &rj54n1_subdev_pad_ops,
+};
+
+/*
+ * Interface active, can use i2c. If it fails, it can indeed mean, that
+ * this wasn't our capture interface, so, we wait for the right one
+ */
+static int rj54n1_video_probe(struct i2c_client *client,
+			      struct rj54n1_pdata *priv)
+{
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+	int data1, data2;
+	int ret;
+
+	ret = rj54n1_s_power(&rj54n1->subdev, 1);
+	if (ret < 0)
+		return ret;
+
+	/* Read out the chip version register */
+	data1 = reg_read(client, RJ54N1_DEV_CODE);
+	data2 = reg_read(client, RJ54N1_DEV_CODE2);
+
+	if (data1 != 0x51 || data2 != 0x10) {
+		ret = -ENODEV;
+		dev_info(&client->dev, "No RJ54N1CB0C found, read 0x%x:0x%x\n",
+			 data1, data2);
+		goto done;
+	}
+
+	/* Configure IOCTL polarity from the platform data: 0 or 1 << 7. */
+	ret = reg_write(client, RJ54N1_IOC, priv->ioctl_high << 7);
+	if (ret < 0)
+		goto done;
+
+	dev_info(&client->dev, "Detected a RJ54N1CB0C chip ID 0x%x:0x%x\n",
+		 data1, data2);
+
+	ret = v4l2_ctrl_handler_setup(&rj54n1->hdl);
+
+done:
+	rj54n1_s_power(&rj54n1->subdev, 0);
+	return ret;
+}
+
+static int rj54n1_probe(struct i2c_client *client,
+			const struct i2c_device_id *did)
+{
+	struct rj54n1 *rj54n1;
+	struct i2c_adapter *adapter = client->adapter;
+	struct rj54n1_pdata *rj54n1_priv;
+	int ret;
+
+	if (!client->dev.platform_data) {
+		dev_err(&client->dev, "RJ54N1CB0C: missing platform data!\n");
+		return -EINVAL;
+	}
+
+	rj54n1_priv = client->dev.platform_data;
+
+	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA)) {
+		dev_warn(&adapter->dev,
+			 "I2C-Adapter doesn't support I2C_FUNC_SMBUS_BYTE\n");
+		return -EIO;
+	}
+
+	rj54n1 = devm_kzalloc(&client->dev, sizeof(struct rj54n1), GFP_KERNEL);
+	if (!rj54n1)
+		return -ENOMEM;
+
+	v4l2_i2c_subdev_init(&rj54n1->subdev, client, &rj54n1_subdev_ops);
+	v4l2_ctrl_handler_init(&rj54n1->hdl, 4);
+	v4l2_ctrl_new_std(&rj54n1->hdl, &rj54n1_ctrl_ops,
+			V4L2_CID_VFLIP, 0, 1, 1, 0);
+	v4l2_ctrl_new_std(&rj54n1->hdl, &rj54n1_ctrl_ops,
+			V4L2_CID_HFLIP, 0, 1, 1, 0);
+	v4l2_ctrl_new_std(&rj54n1->hdl, &rj54n1_ctrl_ops,
+			V4L2_CID_GAIN, 0, 127, 1, 66);
+	v4l2_ctrl_new_std(&rj54n1->hdl, &rj54n1_ctrl_ops,
+			V4L2_CID_AUTO_WHITE_BALANCE, 0, 1, 1, 1);
+	rj54n1->subdev.ctrl_handler = &rj54n1->hdl;
+	if (rj54n1->hdl.error)
+		return rj54n1->hdl.error;
+
+	rj54n1->clk_div		= clk_div;
+	rj54n1->rect.left	= RJ54N1_COLUMN_SKIP;
+	rj54n1->rect.top	= RJ54N1_ROW_SKIP;
+	rj54n1->rect.width	= RJ54N1_MAX_WIDTH;
+	rj54n1->rect.height	= RJ54N1_MAX_HEIGHT;
+	rj54n1->width		= RJ54N1_MAX_WIDTH;
+	rj54n1->height		= RJ54N1_MAX_HEIGHT;
+	rj54n1->fmt		= &rj54n1_colour_fmts[0];
+	rj54n1->resize		= 1024;
+	rj54n1->tgclk_mhz	= (rj54n1_priv->mclk_freq / PLL_L * PLL_N) /
+		(clk_div.ratio_tg + 1) / (clk_div.ratio_t + 1);
+
+	rj54n1->clk = clk_get(&client->dev, NULL);
+	if (IS_ERR(rj54n1->clk)) {
+		ret = PTR_ERR(rj54n1->clk);
+		goto err_free_ctrl;
+	}
+
+	rj54n1->pwup_gpio = gpiod_get_optional(&client->dev, "powerup",
+					       GPIOD_OUT_LOW);
+	if (IS_ERR(rj54n1->pwup_gpio)) {
+		dev_info(&client->dev, "Unable to get GPIO \"powerup\": %ld\n",
+			 PTR_ERR(rj54n1->pwup_gpio));
+		ret = PTR_ERR(rj54n1->pwup_gpio);
+		goto err_clk_put;
+	}
+
+	rj54n1->enable_gpio = gpiod_get_optional(&client->dev, "enable",
+						 GPIOD_OUT_LOW);
+	if (IS_ERR(rj54n1->enable_gpio)) {
+		dev_info(&client->dev, "Unable to get GPIO \"enable\": %ld\n",
+			 PTR_ERR(rj54n1->enable_gpio));
+		ret = PTR_ERR(rj54n1->enable_gpio);
+		goto err_gpio_put;
+	}
+
+	ret = rj54n1_video_probe(client, rj54n1_priv);
+	if (ret < 0)
+		goto err_gpio_put;
+
+	ret = v4l2_async_register_subdev(&rj54n1->subdev);
+	if (ret)
+		goto err_gpio_put;
+
+	return 0;
+
+err_gpio_put:
+	if (rj54n1->enable_gpio)
+		gpiod_put(rj54n1->enable_gpio);
+
+	if (rj54n1->pwup_gpio)
+		gpiod_put(rj54n1->pwup_gpio);
+
+err_clk_put:
+	clk_put(rj54n1->clk);
+
+err_free_ctrl:
+	v4l2_ctrl_handler_free(&rj54n1->hdl);
+
+	return ret;
+}
+
+static int rj54n1_remove(struct i2c_client *client)
+{
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+
+	if (rj54n1->enable_gpio)
+		gpiod_put(rj54n1->enable_gpio);
+	if (rj54n1->pwup_gpio)
+		gpiod_put(rj54n1->pwup_gpio);
+
+	clk_put(rj54n1->clk);
+	v4l2_ctrl_handler_free(&rj54n1->hdl);
+	v4l2_async_unregister_subdev(&rj54n1->subdev);
+
+	return 0;
+}
+
+static const struct i2c_device_id rj54n1_id[] = {
+	{ "rj54n1cb0c", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, rj54n1_id);
+
+static struct i2c_driver rj54n1_i2c_driver = {
+	.driver = {
+		.name = "rj54n1cb0c",
+	},
+	.probe		= rj54n1_probe,
+	.remove		= rj54n1_remove,
+	.id_table	= rj54n1_id,
+};
+
+module_i2c_driver(rj54n1_i2c_driver);
+
+MODULE_DESCRIPTION("Sharp RJ54N1CB0C Camera driver");
+MODULE_AUTHOR("Guennadi Liakhovetski <g.liakhovetski@gmx.de>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c
index e1f8208581aa..1236683da8f7 100644
--- a/drivers/media/i2c/smiapp/smiapp-core.c
+++ b/drivers/media/i2c/smiapp/smiapp-core.c
@@ -1892,7 +1892,7 @@ static int scaling_goodness(struct v4l2_subdev *subdev, int w, int ask_w,
 		val -= SCALING_GOODNESS_EXTREME;
 
 	dev_dbg(&client->dev, "w %d ask_w %d h %d ask_h %d goodness %d\n",
-		w, ask_h, h, ask_h, val);
+		w, ask_w, h, ask_h, val);
 
 	return val;
 }
@@ -2764,6 +2764,7 @@ static struct smiapp_hwconfig *smiapp_get_hwconfig(struct device *dev)
 	struct v4l2_fwnode_endpoint *bus_cfg;
 	struct fwnode_handle *ep;
 	struct fwnode_handle *fwnode = dev_fwnode(dev);
+	u32 rotation;
 	int i;
 	int rval;
 
@@ -2800,6 +2801,21 @@ static struct smiapp_hwconfig *smiapp_get_hwconfig(struct device *dev)
 
 	dev_dbg(dev, "lanes %u\n", hwcfg->lanes);
 
+	rval = fwnode_property_read_u32(fwnode, "rotation", &rotation);
+	if (!rval) {
+		switch (rotation) {
+		case 180:
+			hwcfg->module_board_orient =
+				SMIAPP_MODULE_BOARD_ORIENT_180;
+			/* Fall through */
+		case 0:
+			break;
+		default:
+			dev_err(dev, "invalid rotation %u\n", rotation);
+			goto out_err;
+		}
+	}
+
 	/* NVM size is not mandatory */
 	fwnode_property_read_u32(fwnode, "nokia,nvm-size", &hwcfg->nvm_size);
 
@@ -3171,4 +3187,4 @@ module_i2c_driver(smiapp_i2c_driver);
 
 MODULE_AUTHOR("Sakari Ailus <sakari.ailus@iki.fi>");
 MODULE_DESCRIPTION("Generic SMIA/SMIA++ camera module driver");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/i2c/soc_camera/ov772x.c b/drivers/media/i2c/soc_camera/ov772x.c
index 806383500313..14377af7c888 100644
--- a/drivers/media/i2c/soc_camera/ov772x.c
+++ b/drivers/media/i2c/soc_camera/ov772x.c
@@ -834,7 +834,7 @@ static int ov772x_set_params(struct ov772x_priv *priv,
 	 * set COM8
 	 */
 	if (priv->band_filter) {
-		ret = ov772x_mask_set(client, COM8, BNDF_ON_OFF, 1);
+		ret = ov772x_mask_set(client, COM8, BNDF_ON_OFF, BNDF_ON_OFF);
 		if (!ret)
 			ret = ov772x_mask_set(client, BDBASE,
 					      0xff, 256 - priv->band_filter);
diff --git a/drivers/media/i2c/tc358743.c b/drivers/media/i2c/tc358743.c
index 393bbbbbaad7..44c41933415a 100644
--- a/drivers/media/i2c/tc358743.c
+++ b/drivers/media/i2c/tc358743.c
@@ -1918,7 +1918,8 @@ static int tc358743_probe_of(struct tc358743_state *state)
 	endpoint = v4l2_fwnode_endpoint_alloc_parse(of_fwnode_handle(ep));
 	if (IS_ERR(endpoint)) {
 		dev_err(dev, "failed to parse endpoint\n");
-		return PTR_ERR(endpoint);
+		ret = PTR_ERR(endpoint);
+		goto put_node;
 	}
 
 	if (endpoint->bus_type != V4L2_MBUS_CSI2 ||
@@ -2013,6 +2014,8 @@ disable_clk:
 	clk_disable_unprepare(refclk);
 free_endpoint:
 	v4l2_fwnode_endpoint_free(endpoint);
+put_node:
+	of_node_put(ep);
 	return ret;
 }
 #else
diff --git a/drivers/media/i2c/tda1997x.c b/drivers/media/i2c/tda1997x.c
index 039a92c3294a..d114ac5243ec 100644
--- a/drivers/media/i2c/tda1997x.c
+++ b/drivers/media/i2c/tda1997x.c
@@ -2570,7 +2570,7 @@ static int tda1997x_probe(struct i2c_client *client,
 		 id->name, i2c_adapter_id(client->adapter),
 		 client->addr);
 	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE | V4L2_SUBDEV_FL_HAS_EVENTS;
-	sd->entity.function = MEDIA_ENT_F_DTV_DECODER;
+	sd->entity.function = MEDIA_ENT_F_DV_DECODER;
 	sd->entity.ops = &tda1997x_media_ops;
 
 	/* set allowed mbus modes based on chip, bus-type, and bus-width */
diff --git a/drivers/media/i2c/tvp514x.c b/drivers/media/i2c/tvp514x.c
index 6a9890531d01..675b9ae212ab 100644
--- a/drivers/media/i2c/tvp514x.c
+++ b/drivers/media/i2c/tvp514x.c
@@ -1084,7 +1084,7 @@ tvp514x_probe(struct i2c_client *client, const struct i2c_device_id *id)
 #if defined(CONFIG_MEDIA_CONTROLLER)
 	decoder->pad.flags = MEDIA_PAD_FL_SOURCE;
 	decoder->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
-	decoder->sd.entity.flags |= MEDIA_ENT_F_ATV_DECODER;
+	decoder->sd.entity.function = MEDIA_ENT_F_ATV_DECODER;
 
 	ret = media_entity_pads_init(&decoder->sd.entity, 1, &decoder->pad);
 	if (ret < 0) {
diff --git a/drivers/media/i2c/tvp5150.c b/drivers/media/i2c/tvp5150.c
index b162c2fe62c3..76e6bed5a1da 100644
--- a/drivers/media/i2c/tvp5150.c
+++ b/drivers/media/i2c/tvp5150.c
@@ -872,7 +872,7 @@ static int tvp5150_fill_fmt(struct v4l2_subdev *sd,
 	f = &format->format;
 
 	f->width = decoder->rect.width;
-	f->height = decoder->rect.height;
+	f->height = decoder->rect.height / 2;
 
 	f->code = MEDIA_BUS_FMT_UYVY8_2X8;
 	f->field = V4L2_FIELD_ALTERNATE;
diff --git a/drivers/media/i2c/tvp7002.c b/drivers/media/i2c/tvp7002.c
index 4599b7e28a8d..4f5c627579c7 100644
--- a/drivers/media/i2c/tvp7002.c
+++ b/drivers/media/i2c/tvp7002.c
@@ -1010,7 +1010,7 @@ static int tvp7002_probe(struct i2c_client *c, const struct i2c_device_id *id)
 #if defined(CONFIG_MEDIA_CONTROLLER)
 	device->pad.flags = MEDIA_PAD_FL_SOURCE;
 	device->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
-	device->sd.entity.flags |= MEDIA_ENT_F_ATV_DECODER;
+	device->sd.entity.function = MEDIA_ENT_F_ATV_DECODER;
 
 	error = media_entity_pads_init(&device->sd.entity, 1, &device->pad);
 	if (error < 0)
diff --git a/drivers/media/i2c/video-i2c.c b/drivers/media/i2c/video-i2c.c
index 0b347cc19aa5..06d29d8f6be8 100644
--- a/drivers/media/i2c/video-i2c.c
+++ b/drivers/media/i2c/video-i2c.c
@@ -10,6 +10,7 @@
 
 #include <linux/delay.h>
 #include <linux/freezer.h>
+#include <linux/hwmon.h>
 #include <linux/kthread.h>
 #include <linux/i2c.h>
 #include <linux/list.h>
@@ -77,6 +78,9 @@ struct video_i2c_chip {
 
 	/* xfer function */
 	int (*xfer)(struct video_i2c_data *data, char *buf);
+
+	/* hwmon init function */
+	int (*hwmon_init)(struct video_i2c_data *data);
 };
 
 static int amg88xx_xfer(struct video_i2c_data *data, char *buf)
@@ -101,6 +105,74 @@ static int amg88xx_xfer(struct video_i2c_data *data, char *buf)
 	return (ret == 2) ? 0 : -EIO;
 }
 
+#if IS_ENABLED(CONFIG_HWMON)
+
+static const u32 amg88xx_temp_config[] = {
+	HWMON_T_INPUT,
+	0
+};
+
+static const struct hwmon_channel_info amg88xx_temp = {
+	.type = hwmon_temp,
+	.config = amg88xx_temp_config,
+};
+
+static const struct hwmon_channel_info *amg88xx_info[] = {
+	&amg88xx_temp,
+	NULL
+};
+
+static umode_t amg88xx_is_visible(const void *drvdata,
+				  enum hwmon_sensor_types type,
+				  u32 attr, int channel)
+{
+	return 0444;
+}
+
+static int amg88xx_read(struct device *dev, enum hwmon_sensor_types type,
+			u32 attr, int channel, long *val)
+{
+	struct video_i2c_data *data = dev_get_drvdata(dev);
+	struct i2c_client *client = data->client;
+	int tmp = i2c_smbus_read_word_data(client, 0x0e);
+
+	if (tmp < 0)
+		return tmp;
+
+	/*
+	 * Check for sign bit, this isn't a two's complement value but an
+	 * absolute temperature that needs to be inverted in the case of being
+	 * negative.
+	 */
+	if (tmp & BIT(11))
+		tmp = -(tmp & 0x7ff);
+
+	*val = (tmp * 625) / 10;
+
+	return 0;
+}
+
+static const struct hwmon_ops amg88xx_hwmon_ops = {
+	.is_visible = amg88xx_is_visible,
+	.read = amg88xx_read,
+};
+
+static const struct hwmon_chip_info amg88xx_chip_info = {
+	.ops = &amg88xx_hwmon_ops,
+	.info = amg88xx_info,
+};
+
+static int amg88xx_hwmon_init(struct video_i2c_data *data)
+{
+	void *hwmon = devm_hwmon_device_register_with_info(&data->client->dev,
+				"amg88xx", data, &amg88xx_chip_info, NULL);
+
+	return PTR_ERR_OR_ZERO(hwmon);
+}
+#else
+#define	amg88xx_hwmon_init	NULL
+#endif
+
 #define AMG88XX		0
 
 static const struct video_i2c_chip video_i2c_chip[] = {
@@ -111,6 +183,7 @@ static const struct video_i2c_chip video_i2c_chip[] = {
 		.buffer_size	= 128,
 		.bpp		= 16,
 		.xfer		= &amg88xx_xfer,
+		.hwmon_init	= amg88xx_hwmon_init,
 	},
 };
 
@@ -505,6 +578,14 @@ static int video_i2c_probe(struct i2c_client *client,
 	video_set_drvdata(&data->vdev, data);
 	i2c_set_clientdata(client, data);
 
+	if (data->chip->hwmon_init) {
+		ret = data->chip->hwmon_init(data);
+		if (ret < 0) {
+			dev_warn(&client->dev,
+				 "failed to register hwmon device\n");
+		}
+	}
+
 	ret = video_register_device(&data->vdev, VFL_TYPE_GRABBER, -1);
 	if (ret < 0)
 		goto error_unregister_device;
diff --git a/drivers/media/i2c/vs6624.c b/drivers/media/i2c/vs6624.c
index 1658816a9844..bc9825f4a73d 100644
--- a/drivers/media/i2c/vs6624.c
+++ b/drivers/media/i2c/vs6624.c
@@ -770,7 +770,7 @@ static int vs6624_probe(struct i2c_client *client,
 		return ret;
 	}
 	/* wait 100ms before any further i2c writes are performed */
-	mdelay(100);
+	msleep(100);
 
 	sensor = devm_kzalloc(&client->dev, sizeof(*sensor), GFP_KERNEL);
 	if (sensor == NULL)
@@ -782,7 +782,7 @@ static int vs6624_probe(struct i2c_client *client,
 	vs6624_writeregs(sd, vs6624_p1);
 	vs6624_write(sd, VS6624_MICRO_EN, 0x2);
 	vs6624_write(sd, VS6624_DIO_EN, 0x1);
-	mdelay(10);
+	usleep_range(10000, 11000);
 	vs6624_writeregs(sd, vs6624_p2);
 
 	vs6624_writeregs(sd, vs6624_default);
diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c
index ae59c3177555..fcdf3d5dc4b6 100644
--- a/drivers/media/media-device.c
+++ b/drivers/media/media-device.c
@@ -16,9 +16,6 @@
  * GNU General Public License for more details.
  */
 
-/* We need to access legacy defines from linux/media.h */
-#define __NEED_MEDIA_LEGACY_API
-
 #include <linux/compat.h>
 #include <linux/export.h>
 #include <linux/idr.h>
@@ -28,6 +25,7 @@
 #include <linux/types.h>
 #include <linux/pci.h>
 #include <linux/usb.h>
+#include <linux/version.h>
 
 #include <media/media-device.h>
 #include <media/media-devnode.h>
@@ -35,6 +33,16 @@
 
 #ifdef CONFIG_MEDIA_CONTROLLER
 
+/*
+ * Legacy defines from linux/media.h. This is the only place we need this
+ * so we just define it here. The media.h header doesn't expose it to the
+ * kernel to prevent it from being used by drivers, but here (and only here!)
+ * we need it to handle the legacy behavior.
+ */
+#define MEDIA_ENT_SUBTYPE_MASK			0x0000ffff
+#define MEDIA_ENT_T_DEVNODE_UNKNOWN		(MEDIA_ENT_F_OLD_BASE | \
+						 MEDIA_ENT_SUBTYPE_MASK)
+
 /* -----------------------------------------------------------------------------
  * Userspace API
  */
@@ -259,6 +267,7 @@ static long media_device_get_topology(struct media_device *mdev, void *arg)
 		memset(&kentity, 0, sizeof(kentity));
 		kentity.id = entity->graph_obj.id;
 		kentity.function = entity->function;
+		kentity.flags = entity->flags;
 		strlcpy(kentity.name, entity->name,
 			sizeof(kentity.name));
 
@@ -324,6 +333,7 @@ static long media_device_get_topology(struct media_device *mdev, void *arg)
 		kpad.id = pad->graph_obj.id;
 		kpad.entity_id = pad->entity->graph_obj.id;
 		kpad.flags = pad->flags;
+		kpad.index = pad->index;
 
 		if (copy_to_user(upad, &kpad, sizeof(kpad)))
 			ret = -EFAULT;
diff --git a/drivers/media/pci/bt8xx/bttv-driver.c b/drivers/media/pci/bt8xx/bttv-driver.c
index de3f44b8dec6..cf05e11da01b 100644
--- a/drivers/media/pci/bt8xx/bttv-driver.c
+++ b/drivers/media/pci/bt8xx/bttv-driver.c
@@ -3511,7 +3511,7 @@ static void bttv_irq_debug_low_latency(struct bttv *btv, u32 rc)
 	}
 	pr_notice("%d: Uhm. Looks like we have unusual high IRQ latencies\n",
 		  btv->c.nr);
-	pr_notice("%d: Lets try to catch the culpit red-handed ...\n",
+	pr_notice("%d: Lets try to catch the culprit red-handed ...\n",
 		  btv->c.nr);
 	dump_stack();
 }
diff --git a/drivers/media/pci/bt8xx/dst.c b/drivers/media/pci/bt8xx/dst.c
index 2e33b7236672..b98de2a22f78 100644
--- a/drivers/media/pci/bt8xx/dst.c
+++ b/drivers/media/pci/bt8xx/dst.c
@@ -1739,9 +1739,9 @@ static const struct dvb_frontend_ops dst_dvbt_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "DST DVB-T",
-		.frequency_min = 137000000,
-		.frequency_max = 858000000,
-		.frequency_stepsize = 166667,
+		.frequency_min_hz = 137 * MHz,
+		.frequency_max_hz = 858 * MHz,
+		.frequency_stepsize_hz = 166667,
 		.caps = FE_CAN_FEC_AUTO			|
 			FE_CAN_QAM_AUTO			|
 			FE_CAN_QAM_16			|
@@ -1768,10 +1768,10 @@ static const struct dvb_frontend_ops dst_dvbs_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name = "DST DVB-S",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_stepsize = 1000,	/* kHz for QPSK frontends */
-		.frequency_tolerance = 29500,
+		.frequency_min_hz   =  950 * MHz,
+		.frequency_max_hz   = 2150 * MHz,
+		.frequency_stepsize_hz = 1 * MHz,
+		.frequency_tolerance_hz = 29500 * kHz,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 	/*     . symbol_rate_tolerance	=	???,*/
@@ -1797,9 +1797,9 @@ static const struct dvb_frontend_ops dst_dvbc_ops = {
 	.delsys = { SYS_DVBC_ANNEX_A },
 	.info = {
 		.name = "DST DVB-C",
-		.frequency_stepsize = 62500,
-		.frequency_min = 51000000,
-		.frequency_max = 858000000,
+		.frequency_min_hz =  51 * MHz,
+		.frequency_max_hz = 858 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.caps = FE_CAN_FEC_AUTO |
@@ -1826,9 +1826,9 @@ static const struct dvb_frontend_ops dst_atsc_ops = {
 	.delsys = { SYS_ATSC },
 	.info = {
 		.name = "DST ATSC",
-		.frequency_stepsize = 62500,
-		.frequency_min = 510000000,
-		.frequency_max = 858000000,
+		.frequency_min_hz = 510 * MHz,
+		.frequency_max_hz = 858 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.caps = FE_CAN_FEC_AUTO | FE_CAN_QAM_AUTO | FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
diff --git a/drivers/media/pci/bt8xx/dvb-bt8xx.c b/drivers/media/pci/bt8xx/dvb-bt8xx.c
index 5ef6e2051d45..2f810b7130e6 100644
--- a/drivers/media/pci/bt8xx/dvb-bt8xx.c
+++ b/drivers/media/pci/bt8xx/dvb-bt8xx.c
@@ -386,10 +386,6 @@ static int advbt771_samsung_tdtc9251dh0_tuner_calc_regs(struct dvb_frontend *fe,
 		bs = 0x02;
 	else if (c->frequency < 470000000)
 		bs = 0x02;
-	else if (c->frequency < 600000000)
-		bs = 0x08;
-	else if (c->frequency < 730000000)
-		bs = 0x08;
 	else
 		bs = 0x08;
 
@@ -606,8 +602,8 @@ static void frontend_init(struct dvb_bt8xx_card *card, u32 type)
 
 		if (card->fe != NULL) {
 			card->fe->ops.tuner_ops.calc_regs = thomson_dtt7579_tuner_calc_regs;
-			card->fe->ops.info.frequency_min = 174000000;
-			card->fe->ops.info.frequency_max = 862000000;
+			card->fe->ops.info.frequency_min_hz = 174 * MHz;
+			card->fe->ops.info.frequency_max_hz = 862 * MHz;
 		}
 		break;
 
@@ -659,8 +655,8 @@ static void frontend_init(struct dvb_bt8xx_card *card, u32 type)
 		card->fe = dvb_attach(mt352_attach, &advbt771_samsung_tdtc9251dh0_config, card->i2c_adapter);
 		if (card->fe != NULL) {
 			card->fe->ops.tuner_ops.calc_regs = advbt771_samsung_tdtc9251dh0_tuner_calc_regs;
-			card->fe->ops.info.frequency_min = 174000000;
-			card->fe->ops.info.frequency_max = 862000000;
+			card->fe->ops.info.frequency_min_hz = 174 * MHz;
+			card->fe->ops.info.frequency_max_hz = 862 * MHz;
 		}
 		break;
 
diff --git a/drivers/media/pci/cobalt/cobalt-driver.c b/drivers/media/pci/cobalt/cobalt-driver.c
index c8b1a6206c65..4885e833c052 100644
--- a/drivers/media/pci/cobalt/cobalt-driver.c
+++ b/drivers/media/pci/cobalt/cobalt-driver.c
@@ -670,7 +670,7 @@ static int cobalt_probe(struct pci_dev *pci_dev,
 	/* FIXME - module parameter arrays constrain max instances */
 	i = atomic_inc_return(&cobalt_instance) - 1;
 
-	cobalt = kzalloc(sizeof(struct cobalt), GFP_ATOMIC);
+	cobalt = kzalloc(sizeof(struct cobalt), GFP_KERNEL);
 	if (cobalt == NULL)
 		return -ENOMEM;
 	cobalt->pci_dev = pci_dev;
diff --git a/drivers/media/pci/cx18/cx18-driver.c b/drivers/media/pci/cx18/cx18-driver.c
index 8f314ca320c7..0c389a3fb4e5 100644
--- a/drivers/media/pci/cx18/cx18-driver.c
+++ b/drivers/media/pci/cx18/cx18-driver.c
@@ -1134,8 +1134,6 @@ free_mem:
 free_workqueues:
 	destroy_workqueue(cx->in_work_queue);
 err:
-	if (retval == 0)
-		retval = -ENODEV;
 	CX18_ERR("Error %d on initialization\n", retval);
 
 	v4l2_device_unregister(&cx->v4l2_dev);
diff --git a/drivers/media/pci/cx23885/altera-ci.c b/drivers/media/pci/cx23885/altera-ci.c
index 70aec9bb7e95..62bc8049b320 100644
--- a/drivers/media/pci/cx23885/altera-ci.c
+++ b/drivers/media/pci/cx23885/altera-ci.c
@@ -346,7 +346,7 @@ static int altera_ci_slot_reset(struct dvb_ca_en50221 *en50221, int slot)
 	mutex_unlock(&inter->fpga_mutex);
 
 	for (;;) {
-		mdelay(50);
+		msleep(50);
 
 		mutex_lock(&inter->fpga_mutex);
 
diff --git a/drivers/media/pci/cx23885/cx23885-cards.c b/drivers/media/pci/cx23885/cx23885-cards.c
index 9f50748fdf56..ed3210dc50bc 100644
--- a/drivers/media/pci/cx23885/cx23885-cards.c
+++ b/drivers/media/pci/cx23885/cx23885-cards.c
@@ -1497,20 +1497,20 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 
 		/* Put the demod into reset and protect the eeprom */
 		mc417_gpio_clear(dev, GPIO_15 | GPIO_14);
-		mdelay(100);
+		msleep(100);
 
 		/* Bring the demod and blaster out of reset */
 		mc417_gpio_set(dev, GPIO_15 | GPIO_14);
-		mdelay(100);
+		msleep(100);
 
 		/* Force the TDA8295A into reset and back */
 		cx23885_gpio_enable(dev, GPIO_2, 1);
 		cx23885_gpio_set(dev, GPIO_2);
-		mdelay(20);
+		msleep(20);
 		cx23885_gpio_clear(dev, GPIO_2);
-		mdelay(20);
+		msleep(20);
 		cx23885_gpio_set(dev, GPIO_2);
-		mdelay(20);
+		msleep(20);
 		break;
 	case CX23885_BOARD_HAUPPAUGE_HVR1200:
 		/* GPIO-0 tda10048 demodulator reset */
@@ -1518,9 +1518,9 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 
 		/* Put the parts into reset and back */
 		cx_set(GP0_IO, 0x00050000);
-		mdelay(20);
+		msleep(20);
 		cx_clear(GP0_IO, 0x00000005);
-		mdelay(20);
+		msleep(20);
 		cx_set(GP0_IO, 0x00050005);
 		break;
 	case CX23885_BOARD_HAUPPAUGE_HVR1700:
@@ -1539,9 +1539,9 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 
 		/* Put the parts into reset and back */
 		cx_set(GP0_IO, 0x00050000);
-		mdelay(20);
+		msleep(20);
 		cx_clear(GP0_IO, 0x00000005);
-		mdelay(20);
+		msleep(20);
 		cx_set(GP0_IO, 0x00050005);
 		break;
 	case CX23885_BOARD_HAUPPAUGE_HVR1400:
@@ -1551,9 +1551,9 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 
 		/* Put the parts into reset and back */
 		cx_set(GP0_IO, 0x00050000);
-		mdelay(20);
+		msleep(20);
 		cx_clear(GP0_IO, 0x00000005);
-		mdelay(20);
+		msleep(20);
 		cx_set(GP0_IO, 0x00050005);
 		break;
 	case CX23885_BOARD_DVICO_FUSIONHDTV_7_DUAL_EXP:
@@ -1564,9 +1564,9 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 
 		/* Put the parts into reset and back */
 		cx_set(GP0_IO, 0x000f0000);
-		mdelay(20);
+		msleep(20);
 		cx_clear(GP0_IO, 0x0000000f);
-		mdelay(20);
+		msleep(20);
 		cx_set(GP0_IO, 0x000f000f);
 		break;
 	case CX23885_BOARD_DVICO_FUSIONHDTV_DVB_T_DUAL_EXP:
@@ -1578,9 +1578,9 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 
 		/* Put the parts into reset and back */
 		cx_set(GP0_IO, 0x000f0000);
-		mdelay(20);
+		msleep(20);
 		cx_clear(GP0_IO, 0x0000000f);
-		mdelay(20);
+		msleep(20);
 		cx_set(GP0_IO, 0x000f000f);
 		break;
 	case CX23885_BOARD_LEADTEK_WINFAST_PXDVR3200_H:
@@ -1596,9 +1596,9 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 
 		/* Put the parts into reset and back */
 		cx_set(GP0_IO, 0x00040000);
-		mdelay(20);
+		msleep(20);
 		cx_clear(GP0_IO, 0x00000004);
-		mdelay(20);
+		msleep(20);
 		cx_set(GP0_IO, 0x00040004);
 		break;
 	case CX23885_BOARD_TBS_6920:
@@ -1608,11 +1608,11 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 		cx_write(MC417_CTL, 0x00000036);
 		cx_write(MC417_OEN, 0x00001000);
 		cx_set(MC417_RWD, 0x00000002);
-		mdelay(200);
+		msleep(200);
 		cx_clear(MC417_RWD, 0x00000800);
-		mdelay(200);
+		msleep(200);
 		cx_set(MC417_RWD, 0x00000800);
-		mdelay(200);
+		msleep(200);
 		break;
 	case CX23885_BOARD_NETUP_DUAL_DVBS2_CI:
 		/* GPIO-0 INTA from CiMax1
@@ -1630,7 +1630,7 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 		cx_set(GP0_IO, 0x00040000); /* GPIO as out */
 		/* GPIO1 and GPIO2 as INTA and INTB from CiMaxes, reset low */
 		cx_clear(GP0_IO, 0x00030004);
-		mdelay(100);/* reset delay */
+		msleep(100);/* reset delay */
 		cx_set(GP0_IO, 0x00040004); /* GPIO as out, reset high */
 		cx_write(MC417_CTL, 0x00000037);/* enable GPIO3-18 pins */
 		/* GPIO-15 IN as ~ACK, rest as OUT */
@@ -1653,7 +1653,7 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 		cx23885_gpio_enable(dev, GPIO_9 | GPIO_6 | GPIO_5, 1);
 		cx23885_gpio_set(dev, GPIO_9 | GPIO_6 | GPIO_5);
 		cx23885_gpio_clear(dev, GPIO_9);
-		mdelay(20);
+		msleep(20);
 		cx23885_gpio_set(dev, GPIO_9);
 		break;
 	case CX23885_BOARD_MYGICA_X8506:
@@ -1664,18 +1664,18 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 		/* GPIO-2 demod reset */
 		cx23885_gpio_enable(dev, GPIO_0 | GPIO_1 | GPIO_2, 1);
 		cx23885_gpio_clear(dev, GPIO_1 | GPIO_2);
-		mdelay(100);
+		msleep(100);
 		cx23885_gpio_set(dev, GPIO_0 | GPIO_1 | GPIO_2);
-		mdelay(100);
+		msleep(100);
 		break;
 	case CX23885_BOARD_MYGICA_X8558PRO:
 		/* GPIO-0 reset first ATBM8830 */
 		/* GPIO-1 reset second ATBM8830 */
 		cx23885_gpio_enable(dev, GPIO_0 | GPIO_1, 1);
 		cx23885_gpio_clear(dev, GPIO_0 | GPIO_1);
-		mdelay(100);
+		msleep(100);
 		cx23885_gpio_set(dev, GPIO_0 | GPIO_1);
-		mdelay(100);
+		msleep(100);
 		break;
 	case CX23885_BOARD_HAUPPAUGE_HVR1850:
 	case CX23885_BOARD_HAUPPAUGE_HVR1290:
@@ -1699,11 +1699,11 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 
 		/* Put the demod into reset and protect the eeprom */
 		mc417_gpio_clear(dev, GPIO_14 | GPIO_13);
-		mdelay(100);
+		msleep(100);
 
 		/* Bring the demod out of reset */
 		mc417_gpio_set(dev, GPIO_14);
-		mdelay(100);
+		msleep(100);
 
 		/* CX24228 GPIO */
 		/* Connected to IF / Mux */
@@ -1728,7 +1728,7 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 		cx_set(GP0_IO, 0x00060000); /* GPIO-1,2 as out */
 		/* GPIO-0 as INT, reset & TMS low */
 		cx_clear(GP0_IO, 0x00010006);
-		mdelay(100);/* reset delay */
+		msleep(100);/* reset delay */
 		cx_set(GP0_IO, 0x00000004); /* reset high */
 		cx_write(MC417_CTL, 0x00000037);/* enable GPIO-3..18 pins */
 		/* GPIO-17 is TDO in, GPIO-15 is ~RDY in, rest is out */
@@ -1747,36 +1747,36 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 		cx23885_gpio_enable(dev, GPIO_8 | GPIO_9, 1);
 
 		cx23885_gpio_clear(dev, GPIO_8 | GPIO_9);
-		mdelay(100);
+		msleep(100);
 		cx23885_gpio_set(dev, GPIO_8 | GPIO_9);
-		mdelay(100);
+		msleep(100);
 
 		break;
 	case CX23885_BOARD_AVERMEDIA_HC81R:
 		cx_clear(MC417_CTL, 1);
 		/* GPIO-0,1,2 setup direction as output */
 		cx_set(GP0_IO, 0x00070000);
-		mdelay(10);
+		usleep_range(10000, 11000);
 		/* AF9013 demod reset */
 		cx_set(GP0_IO, 0x00010001);
-		mdelay(10);
+		usleep_range(10000, 11000);
 		cx_clear(GP0_IO, 0x00010001);
-		mdelay(10);
+		usleep_range(10000, 11000);
 		cx_set(GP0_IO, 0x00010001);
-		mdelay(10);
+		usleep_range(10000, 11000);
 		/* demod tune? */
 		cx_clear(GP0_IO, 0x00030003);
-		mdelay(10);
+		usleep_range(10000, 11000);
 		cx_set(GP0_IO, 0x00020002);
-		mdelay(10);
+		usleep_range(10000, 11000);
 		cx_set(GP0_IO, 0x00010001);
-		mdelay(10);
+		usleep_range(10000, 11000);
 		cx_clear(GP0_IO, 0x00020002);
 		/* XC3028L tuner reset */
 		cx_set(GP0_IO, 0x00040004);
 		cx_clear(GP0_IO, 0x00040004);
 		cx_set(GP0_IO, 0x00040004);
-		mdelay(60);
+		msleep(60);
 		break;
 	case CX23885_BOARD_DVBSKY_T9580:
 	case CX23885_BOARD_DVBSKY_S952:
@@ -1785,7 +1785,7 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 		cx_write(MC417_CTL, 0x00000037);
 		cx23885_gpio_enable(dev, GPIO_2 | GPIO_11, 1);
 		cx23885_gpio_clear(dev, GPIO_2 | GPIO_11);
-		mdelay(100);
+		msleep(100);
 		cx23885_gpio_set(dev, GPIO_2 | GPIO_11);
 		break;
 	case CX23885_BOARD_DVBSKY_T980C:
@@ -1807,7 +1807,7 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 
 		cx_set(GP0_IO, 0x00060002); /* GPIO 1/2 as output */
 		cx_clear(GP0_IO, 0x00010004); /* GPIO 0 as input */
-		mdelay(100); /* reset delay */
+		msleep(100); /* reset delay */
 		cx_set(GP0_IO, 0x00060004); /* GPIO as out, reset high */
 		cx_clear(GP0_IO, 0x00010002);
 		cx_write(MC417_CTL, 0x00000037); /* enable GPIO3-18 pins */
diff --git a/drivers/media/pci/cx23885/cx23885-core.c b/drivers/media/pci/cx23885/cx23885-core.c
index 94b996ff12a9..39804d830305 100644
--- a/drivers/media/pci/cx23885/cx23885-core.c
+++ b/drivers/media/pci/cx23885/cx23885-core.c
@@ -667,7 +667,7 @@ static void cx23885_reset(struct cx23885_dev *dev)
 
 	/* clear dma in progress */
 	cx23885_clear_bridge_error(dev);
-	mdelay(100);
+	msleep(100);
 
 	cx23885_sram_channel_setup(dev, &dev->sram_channels[SRAM_CH01],
 		720*4, 0);
diff --git a/drivers/media/pci/cx25821/cx25821-audio-upstream.c b/drivers/media/pci/cx25821/cx25821-audio-upstream.c
deleted file mode 100644
index ada26d4acfb4..000000000000
--- a/drivers/media/pci/cx25821/cx25821-audio-upstream.c
+++ /dev/null
@@ -1,679 +0,0 @@
-/*
- *  Driver for the Conexant CX25821 PCIe bridge
- *
- *  Copyright (C) 2009 Conexant Systems Inc.
- *  Authors  <hiep.huynh@conexant.com>, <shu.lin@conexant.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *
- *  GNU General Public License for more details.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include "cx25821-video.h"
-#include "cx25821-audio-upstream.h"
-
-#include <linux/fs.h>
-#include <linux/errno.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/syscalls.h>
-#include <linux/file.h>
-#include <linux/fcntl.h>
-#include <linux/delay.h>
-#include <linux/slab.h>
-#include <linux/uaccess.h>
-
-MODULE_DESCRIPTION("v4l2 driver module for cx25821 based TV cards");
-MODULE_AUTHOR("Hiep Huynh <hiep.huynh@conexant.com>");
-MODULE_LICENSE("GPL");
-
-static int _intr_msk = FLD_AUD_SRC_RISCI1 | FLD_AUD_SRC_OF |
-			FLD_AUD_SRC_SYNC | FLD_AUD_SRC_OPC_ERR;
-
-static int cx25821_sram_channel_setup_upstream_audio(struct cx25821_dev *dev,
-					      const struct sram_channel *ch,
-					      unsigned int bpl, u32 risc)
-{
-	unsigned int i, lines;
-	u32 cdt;
-
-	if (ch->cmds_start == 0) {
-		cx_write(ch->ptr1_reg, 0);
-		cx_write(ch->ptr2_reg, 0);
-		cx_write(ch->cnt2_reg, 0);
-		cx_write(ch->cnt1_reg, 0);
-		return 0;
-	}
-
-	bpl = (bpl + 7) & ~7;	/* alignment */
-	cdt = ch->cdt;
-	lines = ch->fifo_size / bpl;
-
-	if (lines > 3)
-		lines = 3;
-
-	BUG_ON(lines < 2);
-
-	/* write CDT */
-	for (i = 0; i < lines; i++) {
-		cx_write(cdt + 16 * i, ch->fifo_start + bpl * i);
-		cx_write(cdt + 16 * i + 4, 0);
-		cx_write(cdt + 16 * i + 8, 0);
-		cx_write(cdt + 16 * i + 12, 0);
-	}
-
-	/* write CMDS */
-	cx_write(ch->cmds_start + 0, risc);
-
-	cx_write(ch->cmds_start + 4, 0);
-	cx_write(ch->cmds_start + 8, cdt);
-	cx_write(ch->cmds_start + 12, AUDIO_CDT_SIZE_QW);
-	cx_write(ch->cmds_start + 16, ch->ctrl_start);
-
-	/* IQ size */
-	cx_write(ch->cmds_start + 20, AUDIO_IQ_SIZE_DW);
-
-	for (i = 24; i < 80; i += 4)
-		cx_write(ch->cmds_start + i, 0);
-
-	/* fill registers */
-	cx_write(ch->ptr1_reg, ch->fifo_start);
-	cx_write(ch->ptr2_reg, cdt);
-	cx_write(ch->cnt2_reg, AUDIO_CDT_SIZE_QW);
-	cx_write(ch->cnt1_reg, AUDIO_CLUSTER_SIZE_QW - 1);
-
-	return 0;
-}
-
-static __le32 *cx25821_risc_field_upstream_audio(struct cx25821_dev *dev,
-						 __le32 *rp,
-						 dma_addr_t databuf_phys_addr,
-						 unsigned int bpl,
-						 int fifo_enable)
-{
-	unsigned int line;
-	const struct sram_channel *sram_ch =
-		dev->channels[dev->_audio_upstream_channel].sram_channels;
-	int offset = 0;
-
-	/* scan lines */
-	for (line = 0; line < LINES_PER_AUDIO_BUFFER; line++) {
-		*(rp++) = cpu_to_le32(RISC_READ | RISC_SOL | RISC_EOL | bpl);
-		*(rp++) = cpu_to_le32(databuf_phys_addr + offset);
-		*(rp++) = cpu_to_le32(0);	/* bits 63-32 */
-
-		/* Check if we need to enable the FIFO
-		 * after the first 3 lines.
-		 * For the upstream audio channel,
-		 * the risc engine will enable the FIFO */
-		if (fifo_enable && line == 2) {
-			*(rp++) = RISC_WRITECR;
-			*(rp++) = sram_ch->dma_ctl;
-			*(rp++) = sram_ch->fld_aud_fifo_en;
-			*(rp++) = 0x00000020;
-		}
-
-		offset += AUDIO_LINE_SIZE;
-	}
-
-	return rp;
-}
-
-static int cx25821_risc_buffer_upstream_audio(struct cx25821_dev *dev,
-				       struct pci_dev *pci,
-				       unsigned int bpl, unsigned int lines)
-{
-	__le32 *rp;
-	int fifo_enable = 0;
-	int frame = 0, i = 0;
-	int frame_size = AUDIO_DATA_BUF_SZ;
-	int databuf_offset = 0;
-	int risc_flag = RISC_CNT_INC;
-	dma_addr_t risc_phys_jump_addr;
-
-	/* Virtual address of Risc buffer program */
-	rp = dev->_risc_virt_addr;
-
-	/* sync instruction */
-	*(rp++) = cpu_to_le32(RISC_RESYNC | AUDIO_SYNC_LINE);
-
-	for (frame = 0; frame < NUM_AUDIO_FRAMES; frame++) {
-		databuf_offset = frame_size * frame;
-
-		if (frame == 0) {
-			fifo_enable = 1;
-			risc_flag = RISC_CNT_RESET;
-		} else {
-			fifo_enable = 0;
-			risc_flag = RISC_CNT_INC;
-		}
-
-		/* Calculate physical jump address */
-		if ((frame + 1) == NUM_AUDIO_FRAMES) {
-			risc_phys_jump_addr =
-			    dev->_risc_phys_start_addr +
-			    RISC_SYNC_INSTRUCTION_SIZE;
-		} else {
-			risc_phys_jump_addr =
-			    dev->_risc_phys_start_addr +
-			    RISC_SYNC_INSTRUCTION_SIZE +
-			    AUDIO_RISC_DMA_BUF_SIZE * (frame + 1);
-		}
-
-		rp = cx25821_risc_field_upstream_audio(dev, rp,
-				dev->_audiodata_buf_phys_addr + databuf_offset,
-				bpl, fifo_enable);
-
-		if (USE_RISC_NOOP_AUDIO) {
-			for (i = 0; i < NUM_NO_OPS; i++)
-				*(rp++) = cpu_to_le32(RISC_NOOP);
-		}
-
-		/* Loop to (Nth)FrameRISC or to Start of Risc program &
-		 * generate IRQ */
-		*(rp++) = cpu_to_le32(RISC_JUMP | RISC_IRQ1 | risc_flag);
-		*(rp++) = cpu_to_le32(risc_phys_jump_addr);
-		*(rp++) = cpu_to_le32(0);
-
-		/* Recalculate virtual address based on frame index */
-		rp = dev->_risc_virt_addr + RISC_SYNC_INSTRUCTION_SIZE / 4 +
-			(AUDIO_RISC_DMA_BUF_SIZE * (frame + 1) / 4);
-	}
-
-	return 0;
-}
-
-static void cx25821_free_memory_audio(struct cx25821_dev *dev)
-{
-	if (dev->_risc_virt_addr) {
-		pci_free_consistent(dev->pci, dev->_audiorisc_size,
-				    dev->_risc_virt_addr, dev->_risc_phys_addr);
-		dev->_risc_virt_addr = NULL;
-	}
-
-	if (dev->_audiodata_buf_virt_addr) {
-		pci_free_consistent(dev->pci, dev->_audiodata_buf_size,
-				    dev->_audiodata_buf_virt_addr,
-				    dev->_audiodata_buf_phys_addr);
-		dev->_audiodata_buf_virt_addr = NULL;
-	}
-}
-
-void cx25821_stop_upstream_audio(struct cx25821_dev *dev)
-{
-	const struct sram_channel *sram_ch =
-		dev->channels[AUDIO_UPSTREAM_SRAM_CHANNEL_B].sram_channels;
-	u32 tmp = 0;
-
-	if (!dev->_audio_is_running) {
-		printk(KERN_DEBUG
-		       pr_fmt("No audio file is currently running so return!\n"));
-		return;
-	}
-	/* Disable RISC interrupts */
-	cx_write(sram_ch->int_msk, 0);
-
-	/* Turn OFF risc and fifo enable in AUD_DMA_CNTRL */
-	tmp = cx_read(sram_ch->dma_ctl);
-	cx_write(sram_ch->dma_ctl,
-		 tmp & ~(sram_ch->fld_aud_fifo_en | sram_ch->fld_aud_risc_en));
-
-	/* Clear data buffer memory */
-	if (dev->_audiodata_buf_virt_addr)
-		memset(dev->_audiodata_buf_virt_addr, 0,
-		       dev->_audiodata_buf_size);
-
-	dev->_audio_is_running = 0;
-	dev->_is_first_audio_frame = 0;
-	dev->_audioframe_count = 0;
-	dev->_audiofile_status = END_OF_FILE;
-
-	flush_work(&dev->_audio_work_entry);
-
-	kfree(dev->_audiofilename);
-}
-
-void cx25821_free_mem_upstream_audio(struct cx25821_dev *dev)
-{
-	if (dev->_audio_is_running)
-		cx25821_stop_upstream_audio(dev);
-
-	cx25821_free_memory_audio(dev);
-}
-
-static int cx25821_get_audio_data(struct cx25821_dev *dev,
-			   const struct sram_channel *sram_ch)
-{
-	struct file *file;
-	int frame_index_temp = dev->_audioframe_index;
-	int i = 0;
-	int frame_size = AUDIO_DATA_BUF_SZ;
-	int frame_offset = frame_size * frame_index_temp;
-	char mybuf[AUDIO_LINE_SIZE];
-	loff_t file_offset = dev->_audioframe_count * frame_size;
-	char *p = NULL;
-
-	if (dev->_audiofile_status == END_OF_FILE)
-		return 0;
-
-	file = filp_open(dev->_audiofilename, O_RDONLY | O_LARGEFILE, 0);
-	if (IS_ERR(file)) {
-		pr_err("%s(): ERROR opening file(%s) with errno = %ld!\n",
-		       __func__, dev->_audiofilename, -PTR_ERR(file));
-		return PTR_ERR(file);
-	}
-
-	if (dev->_audiodata_buf_virt_addr)
-		p = (char *)dev->_audiodata_buf_virt_addr + frame_offset;
-
-	for (i = 0; i < dev->_audio_lines_count; i++) {
-		int n = kernel_read(file, mybuf, AUDIO_LINE_SIZE, &file_offset);
-		if (n < AUDIO_LINE_SIZE) {
-			pr_info("Done: exit %s() since no more bytes to read from Audio file\n",
-				__func__);
-			dev->_audiofile_status = END_OF_FILE;
-			fput(file);
-			return 0;
-		}
-		dev->_audiofile_status = IN_PROGRESS;
-		if (p) {
-			memcpy(p, mybuf, n);
-			p += n;
-		}
-	}
-	dev->_audioframe_count++;
-	fput(file);
-
-	return 0;
-}
-
-static void cx25821_audioups_handler(struct work_struct *work)
-{
-	struct cx25821_dev *dev = container_of(work, struct cx25821_dev,
-			_audio_work_entry);
-
-	if (!dev) {
-		pr_err("ERROR %s(): since container_of(work_struct) FAILED!\n",
-			__func__);
-		return;
-	}
-
-	cx25821_get_audio_data(dev, dev->channels[dev->_audio_upstream_channel].
-			sram_channels);
-}
-
-static int cx25821_openfile_audio(struct cx25821_dev *dev,
-			   const struct sram_channel *sram_ch)
-{
-	char *p = (void *)dev->_audiodata_buf_virt_addr;
-	struct file *file;
-	loff_t file_offset = 0;
-	int i, j;
-
-	file = filp_open(dev->_audiofilename, O_RDONLY | O_LARGEFILE, 0);
-	if (IS_ERR(file)) {
-		pr_err("%s(): ERROR opening file(%s) with errno = %ld!\n",
-			__func__, dev->_audiofilename, PTR_ERR(file));
-		return PTR_ERR(file);
-	}
-
-	for (j = 0; j < NUM_AUDIO_FRAMES; j++) {
-		for (i = 0; i < dev->_audio_lines_count; i++) {
-			char buf[AUDIO_LINE_SIZE];
-			loff_t offset = file_offset;
-			int n = kernel_read(file, buf, AUDIO_LINE_SIZE, &file_offset);
-
-			if (n < AUDIO_LINE_SIZE) {
-				pr_info("Done: exit %s() since no more bytes to read from Audio file\n",
-					__func__);
-				dev->_audiofile_status = END_OF_FILE;
-				fput(file);
-				return 0;
-			}
-
-			if (p)
-				memcpy(p + offset, buf, n);
-		}
-		dev->_audioframe_count++;
-	}
-	dev->_audiofile_status = IN_PROGRESS;
-	fput(file);
-	return 0;
-}
-
-static int cx25821_audio_upstream_buffer_prepare(struct cx25821_dev *dev,
-						 const struct sram_channel *sram_ch,
-						 int bpl)
-{
-	int ret = 0;
-	dma_addr_t dma_addr;
-	dma_addr_t data_dma_addr;
-
-	cx25821_free_memory_audio(dev);
-
-	dev->_risc_virt_addr = pci_alloc_consistent(dev->pci,
-			dev->audio_upstream_riscbuf_size, &dma_addr);
-	dev->_risc_virt_start_addr = dev->_risc_virt_addr;
-	dev->_risc_phys_start_addr = dma_addr;
-	dev->_risc_phys_addr = dma_addr;
-	dev->_audiorisc_size = dev->audio_upstream_riscbuf_size;
-
-	if (!dev->_risc_virt_addr) {
-		printk(KERN_DEBUG
-			pr_fmt("ERROR: pci_alloc_consistent() FAILED to allocate memory for RISC program! Returning\n"));
-		return -ENOMEM;
-	}
-	/* Clear out memory at address */
-	memset(dev->_risc_virt_addr, 0, dev->_audiorisc_size);
-
-	/* For Audio Data buffer allocation */
-	dev->_audiodata_buf_virt_addr = pci_alloc_consistent(dev->pci,
-			dev->audio_upstream_databuf_size, &data_dma_addr);
-	dev->_audiodata_buf_phys_addr = data_dma_addr;
-	dev->_audiodata_buf_size = dev->audio_upstream_databuf_size;
-
-	if (!dev->_audiodata_buf_virt_addr) {
-		printk(KERN_DEBUG
-			pr_fmt("ERROR: pci_alloc_consistent() FAILED to allocate memory for data buffer! Returning\n"));
-		return -ENOMEM;
-	}
-	/* Clear out memory at address */
-	memset(dev->_audiodata_buf_virt_addr, 0, dev->_audiodata_buf_size);
-
-	ret = cx25821_openfile_audio(dev, sram_ch);
-	if (ret < 0)
-		return ret;
-
-	/* Creating RISC programs */
-	ret = cx25821_risc_buffer_upstream_audio(dev, dev->pci, bpl,
-						dev->_audio_lines_count);
-	if (ret < 0) {
-		printk(KERN_DEBUG
-			pr_fmt("ERROR creating audio upstream RISC programs!\n"));
-		goto error;
-	}
-
-	return 0;
-
-error:
-	return ret;
-}
-
-static int cx25821_audio_upstream_irq(struct cx25821_dev *dev, int chan_num,
-			       u32 status)
-{
-	int i = 0;
-	u32 int_msk_tmp;
-	const struct sram_channel *channel = dev->channels[chan_num].sram_channels;
-	dma_addr_t risc_phys_jump_addr;
-	__le32 *rp;
-
-	if (status & FLD_AUD_SRC_RISCI1) {
-		/* Get interrupt_index of the program that interrupted */
-		u32 prog_cnt = cx_read(channel->gpcnt);
-
-		/* Since we've identified our IRQ, clear our bits from the
-		 * interrupt mask and interrupt status registers */
-		cx_write(channel->int_msk, 0);
-		cx_write(channel->int_stat, cx_read(channel->int_stat));
-
-		spin_lock(&dev->slock);
-
-		while (prog_cnt != dev->_last_index_irq) {
-			/* Update _last_index_irq */
-			if (dev->_last_index_irq < (NUMBER_OF_PROGRAMS - 1))
-				dev->_last_index_irq++;
-			else
-				dev->_last_index_irq = 0;
-
-			dev->_audioframe_index = dev->_last_index_irq;
-
-			schedule_work(&dev->_audio_work_entry);
-		}
-
-		if (dev->_is_first_audio_frame) {
-			dev->_is_first_audio_frame = 0;
-
-			if (dev->_risc_virt_start_addr != NULL) {
-				risc_phys_jump_addr =
-					dev->_risc_phys_start_addr +
-					RISC_SYNC_INSTRUCTION_SIZE +
-					AUDIO_RISC_DMA_BUF_SIZE;
-
-				rp = cx25821_risc_field_upstream_audio(dev,
-						dev->_risc_virt_start_addr + 1,
-						dev->_audiodata_buf_phys_addr,
-						AUDIO_LINE_SIZE, FIFO_DISABLE);
-
-				if (USE_RISC_NOOP_AUDIO) {
-					for (i = 0; i < NUM_NO_OPS; i++) {
-						*(rp++) =
-						    cpu_to_le32(RISC_NOOP);
-					}
-				}
-				/* Jump to 2nd Audio Frame */
-				*(rp++) = cpu_to_le32(RISC_JUMP | RISC_IRQ1 |
-						RISC_CNT_RESET);
-				*(rp++) = cpu_to_le32(risc_phys_jump_addr);
-				*(rp++) = cpu_to_le32(0);
-			}
-		}
-
-		spin_unlock(&dev->slock);
-	} else {
-		if (status & FLD_AUD_SRC_OF)
-			pr_warn("%s(): Audio Received Overflow Error Interrupt!\n",
-				__func__);
-
-		if (status & FLD_AUD_SRC_SYNC)
-			pr_warn("%s(): Audio Received Sync Error Interrupt!\n",
-				__func__);
-
-		if (status & FLD_AUD_SRC_OPC_ERR)
-			pr_warn("%s(): Audio Received OpCode Error Interrupt!\n",
-				__func__);
-
-		/* Read and write back the interrupt status register to clear
-		 * our bits */
-		cx_write(channel->int_stat, cx_read(channel->int_stat));
-	}
-
-	if (dev->_audiofile_status == END_OF_FILE) {
-		pr_warn("EOF Channel Audio Framecount = %d\n",
-			dev->_audioframe_count);
-		return -1;
-	}
-	/* ElSE, set the interrupt mask register, re-enable irq. */
-	int_msk_tmp = cx_read(channel->int_msk);
-	cx_write(channel->int_msk, int_msk_tmp |= _intr_msk);
-
-	return 0;
-}
-
-static irqreturn_t cx25821_upstream_irq_audio(int irq, void *dev_id)
-{
-	struct cx25821_dev *dev = dev_id;
-	u32 audio_status;
-	int handled = 0;
-	const struct sram_channel *sram_ch;
-
-	if (!dev)
-		return -1;
-
-	sram_ch = dev->channels[dev->_audio_upstream_channel].sram_channels;
-
-	audio_status = cx_read(sram_ch->int_stat);
-
-	/* Only deal with our interrupt */
-	if (audio_status) {
-		handled = cx25821_audio_upstream_irq(dev,
-				dev->_audio_upstream_channel, audio_status);
-	}
-
-	if (handled < 0)
-		cx25821_stop_upstream_audio(dev);
-	else
-		handled += handled;
-
-	return IRQ_RETVAL(handled);
-}
-
-static void cx25821_wait_fifo_enable(struct cx25821_dev *dev,
-				     const struct sram_channel *sram_ch)
-{
-	int count = 0;
-	u32 tmp;
-
-	do {
-		/* Wait 10 microsecond before checking to see if the FIFO is
-		 * turned ON. */
-		udelay(10);
-
-		tmp = cx_read(sram_ch->dma_ctl);
-
-		/* 10 millisecond timeout */
-		if (count++ > 1000) {
-			pr_err("ERROR: %s() fifo is NOT turned on. Timeout!\n",
-				__func__);
-			return;
-		}
-
-	} while (!(tmp & sram_ch->fld_aud_fifo_en));
-
-}
-
-static int cx25821_start_audio_dma_upstream(struct cx25821_dev *dev,
-					    const struct sram_channel *sram_ch)
-{
-	u32 tmp = 0;
-	int err = 0;
-
-	/* Set the physical start address of the RISC program in the initial
-	 * program counter(IPC) member of the CMDS. */
-	cx_write(sram_ch->cmds_start + 0, dev->_risc_phys_addr);
-	/* Risc IPC High 64 bits 63-32 */
-	cx_write(sram_ch->cmds_start + 4, 0);
-
-	/* reset counter */
-	cx_write(sram_ch->gpcnt_ctl, 3);
-
-	/* Set the line length       (It looks like we do not need to set the
-	 * line length) */
-	cx_write(sram_ch->aud_length, AUDIO_LINE_SIZE & FLD_AUD_DST_LN_LNGTH);
-
-	/* Set the input mode to 16-bit */
-	tmp = cx_read(sram_ch->aud_cfg);
-	tmp |= FLD_AUD_SRC_ENABLE | FLD_AUD_DST_PK_MODE | FLD_AUD_CLK_ENABLE |
-		FLD_AUD_MASTER_MODE | FLD_AUD_CLK_SELECT_PLL_D |
-		FLD_AUD_SONY_MODE;
-	cx_write(sram_ch->aud_cfg, tmp);
-
-	/* Read and write back the interrupt status register to clear it */
-	tmp = cx_read(sram_ch->int_stat);
-	cx_write(sram_ch->int_stat, tmp);
-
-	/* Clear our bits from the interrupt status register. */
-	cx_write(sram_ch->int_stat, _intr_msk);
-
-	/* Set the interrupt mask register, enable irq. */
-	cx_set(PCI_INT_MSK, cx_read(PCI_INT_MSK) | (1 << sram_ch->irq_bit));
-	tmp = cx_read(sram_ch->int_msk);
-	cx_write(sram_ch->int_msk, tmp |= _intr_msk);
-
-	err = request_irq(dev->pci->irq, cx25821_upstream_irq_audio,
-			IRQF_SHARED, dev->name, dev);
-	if (err < 0) {
-		pr_err("%s: can't get upstream IRQ %d\n", dev->name,
-				dev->pci->irq);
-		goto fail_irq;
-	}
-
-	/* Start the DMA  engine */
-	tmp = cx_read(sram_ch->dma_ctl);
-	cx_set(sram_ch->dma_ctl, tmp | sram_ch->fld_aud_risc_en);
-
-	dev->_audio_is_running = 1;
-	dev->_is_first_audio_frame = 1;
-
-	/* The fifo_en bit turns on by the first Risc program */
-	cx25821_wait_fifo_enable(dev, sram_ch);
-
-	return 0;
-
-fail_irq:
-	cx25821_dev_unregister(dev);
-	return err;
-}
-
-int cx25821_audio_upstream_init(struct cx25821_dev *dev, int channel_select)
-{
-	const struct sram_channel *sram_ch;
-	int err = 0;
-
-	if (dev->_audio_is_running) {
-		pr_warn("Audio Channel is still running so return!\n");
-		return 0;
-	}
-
-	dev->_audio_upstream_channel = channel_select;
-	sram_ch = dev->channels[channel_select].sram_channels;
-
-	/* Work queue */
-	INIT_WORK(&dev->_audio_work_entry, cx25821_audioups_handler);
-
-	dev->_last_index_irq = 0;
-	dev->_audio_is_running = 0;
-	dev->_audioframe_count = 0;
-	dev->_audiofile_status = RESET_STATUS;
-	dev->_audio_lines_count = LINES_PER_AUDIO_BUFFER;
-	_line_size = AUDIO_LINE_SIZE;
-
-	if ((dev->input_audiofilename) &&
-	    (strcmp(dev->input_audiofilename, "") != 0))
-		dev->_audiofilename = kstrdup(dev->input_audiofilename,
-					      GFP_KERNEL);
-	else
-		dev->_audiofilename = kstrdup(_defaultAudioName,
-					      GFP_KERNEL);
-
-	if (!dev->_audiofilename) {
-		err = -ENOMEM;
-		goto error;
-	}
-
-	cx25821_sram_channel_setup_upstream_audio(dev, sram_ch,
-						  _line_size, 0);
-
-	dev->audio_upstream_riscbuf_size =
-		AUDIO_RISC_DMA_BUF_SIZE * NUM_AUDIO_PROGS +
-		RISC_SYNC_INSTRUCTION_SIZE;
-	dev->audio_upstream_databuf_size = AUDIO_DATA_BUF_SZ * NUM_AUDIO_PROGS;
-
-	/* Allocating buffers and prepare RISC program */
-	err = cx25821_audio_upstream_buffer_prepare(dev, sram_ch,
-							_line_size);
-	if (err < 0) {
-		pr_err("%s: Failed to set up Audio upstream buffers!\n",
-			dev->name);
-		goto error;
-	}
-	/* Start RISC engine */
-	cx25821_start_audio_dma_upstream(dev, sram_ch);
-
-	return 0;
-
-error:
-	cx25821_dev_unregister(dev);
-
-	return err;
-}
diff --git a/drivers/media/pci/cx25821/cx25821-audio-upstream.h b/drivers/media/pci/cx25821/cx25821-audio-upstream.h
deleted file mode 100644
index 2bc875d1ec9f..000000000000
--- a/drivers/media/pci/cx25821/cx25821-audio-upstream.h
+++ /dev/null
@@ -1,58 +0,0 @@
-/*
- *  Driver for the Conexant CX25821 PCIe bridge
- *
- *  Copyright (C) 2009 Conexant Systems Inc.
- *  Authors  <hiep.huynh@conexant.com>, <shu.lin@conexant.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *
- *  GNU General Public License for more details.
- */
-
-#include <linux/mutex.h>
-#include <linux/workqueue.h>
-
-#define NUM_AUDIO_PROGS       8
-#define NUM_AUDIO_FRAMES      8
-#define END_OF_FILE           0
-#define IN_PROGRESS           1
-#define RESET_STATUS          -1
-#define FIFO_DISABLE          0
-#define FIFO_ENABLE           1
-#define NUM_NO_OPS            4
-
-#define RISC_READ_INSTRUCTION_SIZE      12
-#define RISC_JUMP_INSTRUCTION_SIZE      12
-#define RISC_WRITECR_INSTRUCTION_SIZE   16
-#define RISC_SYNC_INSTRUCTION_SIZE      4
-#define DWORD_SIZE                      4
-#define AUDIO_SYNC_LINE                 4
-
-#define LINES_PER_AUDIO_BUFFER      15
-#define AUDIO_LINE_SIZE             128
-#define AUDIO_DATA_BUF_SZ           (AUDIO_LINE_SIZE * LINES_PER_AUDIO_BUFFER)
-
-#define USE_RISC_NOOP_AUDIO   1
-
-#ifdef USE_RISC_NOOP_AUDIO
-#define AUDIO_RISC_DMA_BUF_SIZE						\
-	(LINES_PER_AUDIO_BUFFER * RISC_READ_INSTRUCTION_SIZE +		\
-	 RISC_WRITECR_INSTRUCTION_SIZE + NUM_NO_OPS * DWORD_SIZE +	\
-	 RISC_JUMP_INSTRUCTION_SIZE)
-#endif
-
-#ifndef USE_RISC_NOOP_AUDIO
-#define AUDIO_RISC_DMA_BUF_SIZE						\
-	(LINES_PER_AUDIO_BUFFER * RISC_READ_INSTRUCTION_SIZE +		\
-	 RISC_WRITECR_INSTRUCTION_SIZE + RISC_JUMP_INSTRUCTION_SIZE)
-#endif
-
-static int _line_size;
-char *_defaultAudioName = "/root/audioGOOD.wav";
diff --git a/drivers/media/pci/cx25821/cx25821-core.c b/drivers/media/pci/cx25821/cx25821-core.c
index 040c6c251d3a..2f0171134f7e 100644
--- a/drivers/media/pci/cx25821/cx25821-core.c
+++ b/drivers/media/pci/cx25821/cx25821-core.c
@@ -428,7 +428,7 @@ static void cx25821_registers_init(struct cx25821_dev *dev)
 	tmp |= FLD_USE_ALT_PLL_REF;
 	cx_write(CLK_RST, tmp & ~(FLD_VID_I_CLK_NOE | FLD_VID_J_CLK_NOE));
 
-	mdelay(100);
+	msleep(100);
 }
 
 int cx25821_sram_channel_setup(struct cx25821_dev *dev,
@@ -803,7 +803,7 @@ static void cx25821_initialize(struct cx25821_dev *dev)
 	cx_write(CLK_DELAY, cx_read(CLK_DELAY) & 0x80000000);
 	cx_write(PAD_CTRL, 0x12);	/* for I2C */
 	cx25821_registers_init(dev);	/* init Pecos registers */
-	mdelay(100);
+	msleep(100);
 
 	for (i = 0; i < VID_CHANNEL_NUM; i++) {
 		cx25821_set_vip_mode(dev, dev->channels[i].sram_channels);
diff --git a/drivers/media/pci/cx25821/cx25821-gpio.c b/drivers/media/pci/cx25821/cx25821-gpio.c
index 76b8f619e55a..f5ffaf880e5f 100644
--- a/drivers/media/pci/cx25821/cx25821-gpio.c
+++ b/drivers/media/pci/cx25821/cx25821-gpio.c
@@ -88,7 +88,7 @@ void cx25821_gpio_init(struct cx25821_dev *dev)
 	default:
 		/* set GPIO 5 to select the path for Medusa/Athena */
 		cx25821_set_gpiopin_logicvalue(dev, 5, 1);
-		mdelay(20);
+		msleep(20);
 		break;
 	}
 
diff --git a/drivers/media/pci/cx25821/cx25821-video-upstream.c b/drivers/media/pci/cx25821/cx25821-video-upstream.c
deleted file mode 100644
index 6c838c8a7924..000000000000
--- a/drivers/media/pci/cx25821/cx25821-video-upstream.c
+++ /dev/null
@@ -1,673 +0,0 @@
-/*
- *  Driver for the Conexant CX25821 PCIe bridge
- *
- *  Copyright (C) 2009 Conexant Systems Inc.
- *  Authors  <hiep.huynh@conexant.com>, <shu.lin@conexant.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *
- *  GNU General Public License for more details.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include "cx25821-video.h"
-#include "cx25821-video-upstream.h"
-
-#include <linux/errno.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-
-MODULE_DESCRIPTION("v4l2 driver module for cx25821 based TV cards");
-MODULE_AUTHOR("Hiep Huynh <hiep.huynh@conexant.com>");
-MODULE_LICENSE("GPL");
-
-static int _intr_msk = FLD_VID_SRC_RISC1 | FLD_VID_SRC_UF | FLD_VID_SRC_SYNC |
-			FLD_VID_SRC_OPC_ERR;
-
-int cx25821_sram_channel_setup_upstream(struct cx25821_dev *dev,
-					const struct sram_channel *ch,
-					unsigned int bpl, u32 risc)
-{
-	unsigned int i, lines;
-	u32 cdt;
-
-	if (ch->cmds_start == 0) {
-		cx_write(ch->ptr1_reg, 0);
-		cx_write(ch->ptr2_reg, 0);
-		cx_write(ch->cnt2_reg, 0);
-		cx_write(ch->cnt1_reg, 0);
-		return 0;
-	}
-
-	bpl = (bpl + 7) & ~7;	/* alignment */
-	cdt = ch->cdt;
-	lines = ch->fifo_size / bpl;
-
-	if (lines > 4)
-		lines = 4;
-
-	BUG_ON(lines < 2);
-
-	/* write CDT */
-	for (i = 0; i < lines; i++) {
-		cx_write(cdt + 16 * i, ch->fifo_start + bpl * i);
-		cx_write(cdt + 16 * i + 4, 0);
-		cx_write(cdt + 16 * i + 8, 0);
-		cx_write(cdt + 16 * i + 12, 0);
-	}
-
-	/* write CMDS */
-	cx_write(ch->cmds_start + 0, risc);
-
-	cx_write(ch->cmds_start + 4, 0);
-	cx_write(ch->cmds_start + 8, cdt);
-	cx_write(ch->cmds_start + 12, (lines * 16) >> 3);
-	cx_write(ch->cmds_start + 16, ch->ctrl_start);
-
-	cx_write(ch->cmds_start + 20, VID_IQ_SIZE_DW);
-
-	for (i = 24; i < 80; i += 4)
-		cx_write(ch->cmds_start + i, 0);
-
-	/* fill registers */
-	cx_write(ch->ptr1_reg, ch->fifo_start);
-	cx_write(ch->ptr2_reg, cdt);
-	cx_write(ch->cnt2_reg, (lines * 16) >> 3);
-	cx_write(ch->cnt1_reg, (bpl >> 3) - 1);
-
-	return 0;
-}
-
-static __le32 *cx25821_update_riscprogram(struct cx25821_channel *chan,
-					  __le32 *rp, unsigned int offset,
-					  unsigned int bpl, u32 sync_line,
-					  unsigned int lines, int fifo_enable,
-					  int field_type)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	unsigned int line, i;
-	int dist_betwn_starts = bpl * 2;
-
-	*(rp++) = cpu_to_le32(RISC_RESYNC | sync_line);
-
-	if (USE_RISC_NOOP_VIDEO) {
-		for (i = 0; i < NUM_NO_OPS; i++)
-			*(rp++) = cpu_to_le32(RISC_NOOP);
-	}
-
-	/* scan lines */
-	for (line = 0; line < lines; line++) {
-		*(rp++) = cpu_to_le32(RISC_READ | RISC_SOL | RISC_EOL | bpl);
-		*(rp++) = cpu_to_le32(out->_data_buf_phys_addr + offset);
-		*(rp++) = cpu_to_le32(0);	/* bits 63-32 */
-
-		if ((lines <= NTSC_FIELD_HEIGHT)
-		    || (line < (NTSC_FIELD_HEIGHT - 1)) || !(out->is_60hz)) {
-			offset += dist_betwn_starts;
-		}
-	}
-
-	return rp;
-}
-
-static __le32 *cx25821_risc_field_upstream(struct cx25821_channel *chan, __le32 *rp,
-					   dma_addr_t databuf_phys_addr,
-					   unsigned int offset, u32 sync_line,
-					   unsigned int bpl, unsigned int lines,
-					   int fifo_enable, int field_type)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	unsigned int line, i;
-	const struct sram_channel *sram_ch = chan->sram_channels;
-	int dist_betwn_starts = bpl * 2;
-
-	/* sync instruction */
-	if (sync_line != NO_SYNC_LINE)
-		*(rp++) = cpu_to_le32(RISC_RESYNC | sync_line);
-
-	if (USE_RISC_NOOP_VIDEO) {
-		for (i = 0; i < NUM_NO_OPS; i++)
-			*(rp++) = cpu_to_le32(RISC_NOOP);
-	}
-
-	/* scan lines */
-	for (line = 0; line < lines; line++) {
-		*(rp++) = cpu_to_le32(RISC_READ | RISC_SOL | RISC_EOL | bpl);
-		*(rp++) = cpu_to_le32(databuf_phys_addr + offset);
-		*(rp++) = cpu_to_le32(0);	/* bits 63-32 */
-
-		if ((lines <= NTSC_FIELD_HEIGHT)
-		    || (line < (NTSC_FIELD_HEIGHT - 1)) || !(out->is_60hz))
-			/* to skip the other field line */
-			offset += dist_betwn_starts;
-
-		/* check if we need to enable the FIFO after the first 4 lines
-		 * For the upstream video channel, the risc engine will enable
-		 * the FIFO. */
-		if (fifo_enable && line == 3) {
-			*(rp++) = cpu_to_le32(RISC_WRITECR);
-			*(rp++) = cpu_to_le32(sram_ch->dma_ctl);
-			*(rp++) = cpu_to_le32(FLD_VID_FIFO_EN);
-			*(rp++) = cpu_to_le32(0x00000001);
-		}
-	}
-
-	return rp;
-}
-
-static int cx25821_risc_buffer_upstream(struct cx25821_channel *chan,
-					struct pci_dev *pci,
-					unsigned int top_offset,
-					unsigned int bpl, unsigned int lines)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	__le32 *rp;
-	int fifo_enable = 0;
-	/* get line count for single field */
-	int singlefield_lines = lines >> 1;
-	int odd_num_lines = singlefield_lines;
-	int frame = 0;
-	int frame_size = 0;
-	int databuf_offset = 0;
-	int risc_program_size = 0;
-	int risc_flag = RISC_CNT_RESET;
-	unsigned int bottom_offset = bpl;
-	dma_addr_t risc_phys_jump_addr;
-
-	if (out->is_60hz) {
-		odd_num_lines = singlefield_lines + 1;
-		risc_program_size = FRAME1_VID_PROG_SIZE;
-		frame_size = (bpl == Y411_LINE_SZ) ?
-			FRAME_SIZE_NTSC_Y411 : FRAME_SIZE_NTSC_Y422;
-	} else {
-		risc_program_size = PAL_VID_PROG_SIZE;
-		frame_size = (bpl == Y411_LINE_SZ) ?
-			FRAME_SIZE_PAL_Y411 : FRAME_SIZE_PAL_Y422;
-	}
-
-	/* Virtual address of Risc buffer program */
-	rp = out->_dma_virt_addr;
-
-	for (frame = 0; frame < NUM_FRAMES; frame++) {
-		databuf_offset = frame_size * frame;
-
-		if (UNSET != top_offset) {
-			fifo_enable = (frame == 0) ? FIFO_ENABLE : FIFO_DISABLE;
-			rp = cx25821_risc_field_upstream(chan, rp,
-					out->_data_buf_phys_addr +
-					databuf_offset, top_offset, 0, bpl,
-					odd_num_lines, fifo_enable, ODD_FIELD);
-		}
-
-		fifo_enable = FIFO_DISABLE;
-
-		/* Even Field */
-		rp = cx25821_risc_field_upstream(chan, rp,
-						 out->_data_buf_phys_addr +
-						 databuf_offset, bottom_offset,
-						 0x200, bpl, singlefield_lines,
-						 fifo_enable, EVEN_FIELD);
-
-		if (frame == 0) {
-			risc_flag = RISC_CNT_RESET;
-			risc_phys_jump_addr = out->_dma_phys_start_addr +
-				risc_program_size;
-		} else {
-			risc_phys_jump_addr = out->_dma_phys_start_addr;
-			risc_flag = RISC_CNT_INC;
-		}
-
-		/* Loop to 2ndFrameRISC or to Start of Risc
-		 * program & generate IRQ
-		 */
-		*(rp++) = cpu_to_le32(RISC_JUMP | RISC_IRQ1 | risc_flag);
-		*(rp++) = cpu_to_le32(risc_phys_jump_addr);
-		*(rp++) = cpu_to_le32(0);
-	}
-
-	return 0;
-}
-
-void cx25821_stop_upstream_video(struct cx25821_channel *chan)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	struct cx25821_dev *dev = chan->dev;
-	const struct sram_channel *sram_ch = chan->sram_channels;
-	u32 tmp = 0;
-
-	if (!out->_is_running) {
-		pr_info("No video file is currently running so return!\n");
-		return;
-	}
-
-	/* Set the interrupt mask register, disable irq. */
-	cx_set(PCI_INT_MSK, cx_read(PCI_INT_MSK) & ~(1 << sram_ch->irq_bit));
-
-	/* Disable RISC interrupts */
-	tmp = cx_read(sram_ch->int_msk);
-	cx_write(sram_ch->int_msk, tmp & ~_intr_msk);
-
-	/* Turn OFF risc and fifo enable */
-	tmp = cx_read(sram_ch->dma_ctl);
-	cx_write(sram_ch->dma_ctl, tmp & ~(FLD_VID_FIFO_EN | FLD_VID_RISC_EN));
-
-	free_irq(dev->pci->irq, chan);
-
-	/* Clear data buffer memory */
-	if (out->_data_buf_virt_addr)
-		memset(out->_data_buf_virt_addr, 0, out->_data_buf_size);
-
-	out->_is_running = 0;
-	out->_is_first_frame = 0;
-	out->_frame_count = 0;
-	out->_file_status = END_OF_FILE;
-
-	tmp = cx_read(VID_CH_MODE_SEL);
-	cx_write(VID_CH_MODE_SEL, tmp & 0xFFFFFE00);
-}
-
-void cx25821_free_mem_upstream(struct cx25821_channel *chan)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	struct cx25821_dev *dev = chan->dev;
-
-	if (out->_is_running)
-		cx25821_stop_upstream_video(chan);
-
-	if (out->_dma_virt_addr) {
-		pci_free_consistent(dev->pci, out->_risc_size,
-				    out->_dma_virt_addr, out->_dma_phys_addr);
-		out->_dma_virt_addr = NULL;
-	}
-
-	if (out->_data_buf_virt_addr) {
-		pci_free_consistent(dev->pci, out->_data_buf_size,
-				    out->_data_buf_virt_addr,
-				    out->_data_buf_phys_addr);
-		out->_data_buf_virt_addr = NULL;
-	}
-}
-
-int cx25821_write_frame(struct cx25821_channel *chan,
-		const char __user *data, size_t count)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	int line_size = (out->_pixel_format == PIXEL_FRMT_411) ?
-		Y411_LINE_SZ : Y422_LINE_SZ;
-	int frame_size = 0;
-	int frame_offset = 0;
-	int curpos = out->curpos;
-
-	if (out->is_60hz)
-		frame_size = (line_size == Y411_LINE_SZ) ?
-			FRAME_SIZE_NTSC_Y411 : FRAME_SIZE_NTSC_Y422;
-	else
-		frame_size = (line_size == Y411_LINE_SZ) ?
-			FRAME_SIZE_PAL_Y411 : FRAME_SIZE_PAL_Y422;
-
-	if (curpos == 0) {
-		out->cur_frame_index = out->_frame_index;
-		if (wait_event_interruptible(out->waitq, out->cur_frame_index != out->_frame_index))
-			return -EINTR;
-		out->cur_frame_index = out->_frame_index;
-	}
-
-	frame_offset = out->cur_frame_index ? frame_size : 0;
-
-	if (frame_size - curpos < count)
-		count = frame_size - curpos;
-	if (copy_from_user((__force char *)out->_data_buf_virt_addr + frame_offset + curpos,
-				data, count))
-		return -EFAULT;
-	curpos += count;
-	if (curpos == frame_size) {
-		out->_frame_count++;
-		curpos = 0;
-	}
-	out->curpos = curpos;
-
-	return count;
-}
-
-static int cx25821_upstream_buffer_prepare(struct cx25821_channel *chan,
-					   const struct sram_channel *sram_ch,
-					   int bpl)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	struct cx25821_dev *dev = chan->dev;
-	int ret = 0;
-	dma_addr_t dma_addr;
-	dma_addr_t data_dma_addr;
-
-	if (out->_dma_virt_addr != NULL)
-		pci_free_consistent(dev->pci, out->upstream_riscbuf_size,
-				out->_dma_virt_addr, out->_dma_phys_addr);
-
-	out->_dma_virt_addr = pci_alloc_consistent(dev->pci,
-			out->upstream_riscbuf_size, &dma_addr);
-	out->_dma_virt_start_addr = out->_dma_virt_addr;
-	out->_dma_phys_start_addr = dma_addr;
-	out->_dma_phys_addr = dma_addr;
-	out->_risc_size = out->upstream_riscbuf_size;
-
-	if (!out->_dma_virt_addr) {
-		pr_err("FAILED to allocate memory for Risc buffer! Returning\n");
-		return -ENOMEM;
-	}
-
-	/* Clear memory at address */
-	memset(out->_dma_virt_addr, 0, out->_risc_size);
-
-	if (out->_data_buf_virt_addr != NULL)
-		pci_free_consistent(dev->pci, out->upstream_databuf_size,
-				out->_data_buf_virt_addr,
-				out->_data_buf_phys_addr);
-	/* For Video Data buffer allocation */
-	out->_data_buf_virt_addr = pci_alloc_consistent(dev->pci,
-			out->upstream_databuf_size, &data_dma_addr);
-	out->_data_buf_phys_addr = data_dma_addr;
-	out->_data_buf_size = out->upstream_databuf_size;
-
-	if (!out->_data_buf_virt_addr) {
-		pr_err("FAILED to allocate memory for data buffer! Returning\n");
-		return -ENOMEM;
-	}
-
-	/* Clear memory at address */
-	memset(out->_data_buf_virt_addr, 0, out->_data_buf_size);
-
-	/* Create RISC programs */
-	ret = cx25821_risc_buffer_upstream(chan, dev->pci, 0, bpl,
-			out->_lines_count);
-	if (ret < 0) {
-		pr_info("Failed creating Video Upstream Risc programs!\n");
-		goto error;
-	}
-
-	return 0;
-
-error:
-	return ret;
-}
-
-static int cx25821_video_upstream_irq(struct cx25821_channel *chan, u32 status)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	struct cx25821_dev *dev = chan->dev;
-	u32 int_msk_tmp;
-	const struct sram_channel *channel = chan->sram_channels;
-	int singlefield_lines = NTSC_FIELD_HEIGHT;
-	int line_size_in_bytes = Y422_LINE_SZ;
-	int odd_risc_prog_size = 0;
-	dma_addr_t risc_phys_jump_addr;
-	__le32 *rp;
-
-	if (status & FLD_VID_SRC_RISC1) {
-		/* We should only process one program per call */
-		u32 prog_cnt = cx_read(channel->gpcnt);
-
-		/* Since we've identified our IRQ, clear our bits from the
-		 * interrupt mask and interrupt status registers */
-		int_msk_tmp = cx_read(channel->int_msk);
-		cx_write(channel->int_msk, int_msk_tmp & ~_intr_msk);
-		cx_write(channel->int_stat, _intr_msk);
-
-		wake_up(&out->waitq);
-
-		spin_lock(&dev->slock);
-
-		out->_frame_index = prog_cnt;
-
-		if (out->_is_first_frame) {
-			out->_is_first_frame = 0;
-
-			if (out->is_60hz) {
-				singlefield_lines += 1;
-				odd_risc_prog_size = ODD_FLD_NTSC_PROG_SIZE;
-			} else {
-				singlefield_lines = PAL_FIELD_HEIGHT;
-				odd_risc_prog_size = ODD_FLD_PAL_PROG_SIZE;
-			}
-
-			if (out->_dma_virt_start_addr != NULL) {
-				line_size_in_bytes =
-				    (out->_pixel_format ==
-				     PIXEL_FRMT_411) ? Y411_LINE_SZ :
-				    Y422_LINE_SZ;
-				risc_phys_jump_addr =
-				    out->_dma_phys_start_addr +
-				    odd_risc_prog_size;
-
-				rp = cx25821_update_riscprogram(chan,
-					out->_dma_virt_start_addr, TOP_OFFSET,
-					line_size_in_bytes, 0x0,
-					singlefield_lines, FIFO_DISABLE,
-					ODD_FIELD);
-
-				/* Jump to Even Risc program of 1st Frame */
-				*(rp++) = cpu_to_le32(RISC_JUMP);
-				*(rp++) = cpu_to_le32(risc_phys_jump_addr);
-				*(rp++) = cpu_to_le32(0);
-			}
-		}
-
-		spin_unlock(&dev->slock);
-	} else {
-		if (status & FLD_VID_SRC_UF)
-			pr_err("%s(): Video Received Underflow Error Interrupt!\n",
-			       __func__);
-
-		if (status & FLD_VID_SRC_SYNC)
-			pr_err("%s(): Video Received Sync Error Interrupt!\n",
-			       __func__);
-
-		if (status & FLD_VID_SRC_OPC_ERR)
-			pr_err("%s(): Video Received OpCode Error Interrupt!\n",
-			       __func__);
-	}
-
-	if (out->_file_status == END_OF_FILE) {
-		pr_err("EOF Channel 1 Framecount = %d\n", out->_frame_count);
-		return -1;
-	}
-	/* ElSE, set the interrupt mask register, re-enable irq. */
-	int_msk_tmp = cx_read(channel->int_msk);
-	cx_write(channel->int_msk, int_msk_tmp |= _intr_msk);
-
-	return 0;
-}
-
-static irqreturn_t cx25821_upstream_irq(int irq, void *dev_id)
-{
-	struct cx25821_channel *chan = dev_id;
-	struct cx25821_dev *dev = chan->dev;
-	u32 vid_status;
-	int handled = 0;
-	const struct sram_channel *sram_ch;
-
-	if (!dev)
-		return -1;
-
-	sram_ch = chan->sram_channels;
-
-	vid_status = cx_read(sram_ch->int_stat);
-
-	/* Only deal with our interrupt */
-	if (vid_status)
-		handled = cx25821_video_upstream_irq(chan, vid_status);
-
-	return IRQ_RETVAL(handled);
-}
-
-static void cx25821_set_pixelengine(struct cx25821_channel *chan,
-				    const struct sram_channel *ch,
-				    int pix_format)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	struct cx25821_dev *dev = chan->dev;
-	int width = WIDTH_D1;
-	int height = out->_lines_count;
-	int num_lines, odd_num_lines;
-	u32 value;
-	int vip_mode = OUTPUT_FRMT_656;
-
-	value = ((pix_format & 0x3) << 12) | (vip_mode & 0x7);
-	value &= 0xFFFFFFEF;
-	value |= out->is_60hz ? 0 : 0x10;
-	cx_write(ch->vid_fmt_ctl, value);
-
-	/* set number of active pixels in each line.
-	 * Default is 720 pixels in both NTSC and PAL format */
-	cx_write(ch->vid_active_ctl1, width);
-
-	num_lines = (height / 2) & 0x3FF;
-	odd_num_lines = num_lines;
-
-	if (out->is_60hz)
-		odd_num_lines += 1;
-
-	value = (num_lines << 16) | odd_num_lines;
-
-	/* set number of active lines in field 0 (top) and field 1 (bottom) */
-	cx_write(ch->vid_active_ctl2, value);
-
-	cx_write(ch->vid_cdt_size, VID_CDT_SIZE >> 3);
-}
-
-static int cx25821_start_video_dma_upstream(struct cx25821_channel *chan,
-					    const struct sram_channel *sram_ch)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	struct cx25821_dev *dev = chan->dev;
-	u32 tmp = 0;
-	int err = 0;
-
-	/* 656/VIP SRC Upstream Channel I & J and 7 - Host Bus Interface for
-	 * channel A-C
-	 */
-	tmp = cx_read(VID_CH_MODE_SEL);
-	cx_write(VID_CH_MODE_SEL, tmp | 0x1B0001FF);
-
-	/* Set the physical start address of the RISC program in the initial
-	 * program counter(IPC) member of the cmds.
-	 */
-	cx_write(sram_ch->cmds_start + 0, out->_dma_phys_addr);
-	/* Risc IPC High 64 bits 63-32 */
-	cx_write(sram_ch->cmds_start + 4, 0);
-
-	/* reset counter */
-	cx_write(sram_ch->gpcnt_ctl, 3);
-
-	/* Clear our bits from the interrupt status register. */
-	cx_write(sram_ch->int_stat, _intr_msk);
-
-	/* Set the interrupt mask register, enable irq. */
-	cx_set(PCI_INT_MSK, cx_read(PCI_INT_MSK) | (1 << sram_ch->irq_bit));
-	tmp = cx_read(sram_ch->int_msk);
-	cx_write(sram_ch->int_msk, tmp |= _intr_msk);
-
-	err = request_irq(dev->pci->irq, cx25821_upstream_irq,
-			IRQF_SHARED, dev->name, chan);
-	if (err < 0) {
-		pr_err("%s: can't get upstream IRQ %d\n",
-		       dev->name, dev->pci->irq);
-		goto fail_irq;
-	}
-
-	/* Start the DMA  engine */
-	tmp = cx_read(sram_ch->dma_ctl);
-	cx_set(sram_ch->dma_ctl, tmp | FLD_VID_RISC_EN);
-
-	out->_is_running = 1;
-	out->_is_first_frame = 1;
-
-	return 0;
-
-fail_irq:
-	cx25821_dev_unregister(dev);
-	return err;
-}
-
-int cx25821_vidupstream_init(struct cx25821_channel *chan,
-				 int pixel_format)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	struct cx25821_dev *dev = chan->dev;
-	const struct sram_channel *sram_ch;
-	u32 tmp;
-	int err = 0;
-	int data_frame_size = 0;
-	int risc_buffer_size = 0;
-
-	if (out->_is_running) {
-		pr_info("Video Channel is still running so return!\n");
-		return 0;
-	}
-
-	sram_ch = chan->sram_channels;
-
-	out->is_60hz = dev->tvnorm & V4L2_STD_525_60;
-
-	/* 656/VIP SRC Upstream Channel I & J and 7 - Host Bus Interface for
-	 * channel A-C
-	 */
-	tmp = cx_read(VID_CH_MODE_SEL);
-	cx_write(VID_CH_MODE_SEL, tmp | 0x1B0001FF);
-
-	out->_is_running = 0;
-	out->_frame_count = 0;
-	out->_file_status = RESET_STATUS;
-	out->_lines_count = out->is_60hz ? 480 : 576;
-	out->_pixel_format = pixel_format;
-	out->_line_size = (out->_pixel_format == PIXEL_FRMT_422) ?
-		(WIDTH_D1 * 2) : (WIDTH_D1 * 3) / 2;
-	data_frame_size = out->is_60hz ? NTSC_DATA_BUF_SZ : PAL_DATA_BUF_SZ;
-	risc_buffer_size = out->is_60hz ?
-		NTSC_RISC_BUF_SIZE : PAL_RISC_BUF_SIZE;
-
-	out->_is_running = 0;
-	out->_frame_count = 0;
-	out->_file_status = RESET_STATUS;
-	out->_lines_count = out->is_60hz ? 480 : 576;
-	out->_pixel_format = pixel_format;
-	out->_line_size = (out->_pixel_format == PIXEL_FRMT_422) ?
-		(WIDTH_D1 * 2) : (WIDTH_D1 * 3) / 2;
-	out->curpos = 0;
-	init_waitqueue_head(&out->waitq);
-
-	err = cx25821_sram_channel_setup_upstream(dev, sram_ch,
-			out->_line_size, 0);
-
-	/* setup fifo + format */
-	cx25821_set_pixelengine(chan, sram_ch, out->_pixel_format);
-
-	out->upstream_riscbuf_size = risc_buffer_size * 2;
-	out->upstream_databuf_size = data_frame_size * 2;
-
-	/* Allocating buffers and prepare RISC program */
-	err = cx25821_upstream_buffer_prepare(chan, sram_ch, out->_line_size);
-	if (err < 0) {
-		pr_err("%s: Failed to set up Video upstream buffers!\n",
-		       dev->name);
-		goto error;
-	}
-
-	cx25821_start_video_dma_upstream(chan, sram_ch);
-
-	return 0;
-
-error:
-	cx25821_dev_unregister(dev);
-
-	return err;
-}
diff --git a/drivers/media/pci/cx25821/cx25821-video-upstream.h b/drivers/media/pci/cx25821/cx25821-video-upstream.h
deleted file mode 100644
index b6cf95f2d11b..000000000000
--- a/drivers/media/pci/cx25821/cx25821-video-upstream.h
+++ /dev/null
@@ -1,135 +0,0 @@
-/*
- *  Driver for the Conexant CX25821 PCIe bridge
- *
- *  Copyright (C) 2009 Conexant Systems Inc.
- *  Authors  <hiep.huynh@conexant.com>, <shu.lin@conexant.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *
- *  GNU General Public License for more details.
- */
-
-#include <linux/mutex.h>
-#include <linux/workqueue.h>
-
-#define OUTPUT_FRMT_656       0
-#define OPEN_FILE_1           0
-#define NUM_PROGS             8
-#define NUM_FRAMES            2
-#define ODD_FIELD             0
-#define EVEN_FIELD            1
-#define TOP_OFFSET            0
-#define FIFO_DISABLE          0
-#define FIFO_ENABLE           1
-#define TEST_FRAMES           5
-#define END_OF_FILE           0
-#define IN_PROGRESS           1
-#define RESET_STATUS          -1
-#define NUM_NO_OPS            5
-
-/* PAL and NTSC line sizes and number of lines. */
-#define WIDTH_D1              720
-#define NTSC_LINES_PER_FRAME  480
-#define PAL_LINES_PER_FRAME   576
-#define PAL_LINE_SZ           1440
-#define Y422_LINE_SZ          1440
-#define Y411_LINE_SZ          1080
-#define NTSC_FIELD_HEIGHT     240
-#define NTSC_ODD_FLD_LINES    241
-#define PAL_FIELD_HEIGHT      288
-
-#define FRAME_SIZE_NTSC_Y422    (NTSC_LINES_PER_FRAME * Y422_LINE_SZ)
-#define FRAME_SIZE_NTSC_Y411    (NTSC_LINES_PER_FRAME * Y411_LINE_SZ)
-#define FRAME_SIZE_PAL_Y422     (PAL_LINES_PER_FRAME * Y422_LINE_SZ)
-#define FRAME_SIZE_PAL_Y411     (PAL_LINES_PER_FRAME * Y411_LINE_SZ)
-
-#define NTSC_DATA_BUF_SZ        (Y422_LINE_SZ * NTSC_LINES_PER_FRAME)
-#define PAL_DATA_BUF_SZ         (Y422_LINE_SZ * PAL_LINES_PER_FRAME)
-
-#define RISC_WRITECR_INSTRUCTION_SIZE   16
-#define RISC_SYNC_INSTRUCTION_SIZE      4
-#define JUMP_INSTRUCTION_SIZE           12
-#define MAXSIZE_NO_OPS                  36
-#define DWORD_SIZE                      4
-
-#define USE_RISC_NOOP_VIDEO   1
-
-#ifdef USE_RISC_NOOP_VIDEO
-#define PAL_US_VID_PROG_SIZE						\
-	(PAL_FIELD_HEIGHT * 3 * DWORD_SIZE +				\
-	 RISC_WRITECR_INSTRUCTION_SIZE + RISC_SYNC_INSTRUCTION_SIZE +	\
-	 NUM_NO_OPS * DWORD_SIZE)
-
-#define PAL_RISC_BUF_SIZE           (2 * PAL_US_VID_PROG_SIZE)
-
-#define PAL_VID_PROG_SIZE						\
-	((PAL_FIELD_HEIGHT * 2) * 3 * DWORD_SIZE +			\
-	 2 * RISC_SYNC_INSTRUCTION_SIZE + RISC_WRITECR_INSTRUCTION_SIZE + \
-	 JUMP_INSTRUCTION_SIZE + 2 * NUM_NO_OPS * DWORD_SIZE)
-
-#define ODD_FLD_PAL_PROG_SIZE						\
-	(PAL_FIELD_HEIGHT * 3 * DWORD_SIZE +				\
-	 RISC_SYNC_INSTRUCTION_SIZE + RISC_WRITECR_INSTRUCTION_SIZE +	\
-	 NUM_NO_OPS * DWORD_SIZE)
-
-#define ODD_FLD_NTSC_PROG_SIZE						\
-	(NTSC_ODD_FLD_LINES * 3 * DWORD_SIZE +				\
-	 RISC_SYNC_INSTRUCTION_SIZE + RISC_WRITECR_INSTRUCTION_SIZE +	\
-	 NUM_NO_OPS * DWORD_SIZE)
-
-#define NTSC_US_VID_PROG_SIZE						\
-	((NTSC_ODD_FLD_LINES + 1) * 3 * DWORD_SIZE +			\
-	 RISC_WRITECR_INSTRUCTION_SIZE + JUMP_INSTRUCTION_SIZE +	\
-	 NUM_NO_OPS * DWORD_SIZE)
-
-#define NTSC_RISC_BUF_SIZE						\
-	(2 * (RISC_SYNC_INSTRUCTION_SIZE + NTSC_US_VID_PROG_SIZE))
-
-#define FRAME1_VID_PROG_SIZE						\
-	((NTSC_ODD_FLD_LINES + NTSC_FIELD_HEIGHT) * 3 * DWORD_SIZE +	\
-	 2 * RISC_SYNC_INSTRUCTION_SIZE + RISC_WRITECR_INSTRUCTION_SIZE + \
-	 JUMP_INSTRUCTION_SIZE + 2 * NUM_NO_OPS * DWORD_SIZE)
-
-#endif
-
-#ifndef USE_RISC_NOOP_VIDEO
-#define PAL_US_VID_PROG_SIZE						\
-	(PAL_FIELD_HEIGHT * 3 * DWORD_SIZE +				\
-	 RISC_WRITECR_INSTRUCTION_SIZE + RISC_SYNC_INSTRUCTION_SIZE +	\
-	 JUMP_INSTRUCTION_SIZE)
-
-#define PAL_RISC_BUF_SIZE		(2 * PAL_US_VID_PROG_SIZE)
-
-#define PAL_VID_PROG_SIZE						\
-	((PAL_FIELD_HEIGHT * 2) * 3 * DWORD_SIZE +			\
-	 2 * RISC_SYNC_INSTRUCTION_SIZE + RISC_WRITECR_INSTRUCTION_SIZE + \
-	 JUMP_INSTRUCTION_SIZE)
-
-#define ODD_FLD_PAL_PROG_SIZE						\
-	(PAL_FIELD_HEIGHT * 3 * DWORD_SIZE +				\
-	 RISC_SYNC_INSTRUCTION_SIZE + RISC_WRITECR_INSTRUCTION_SIZE)
-
-#define ODD_FLD_NTSC_PROG_SIZE						\
-	(NTSC_ODD_FLD_LINES * 3 * DWORD_SIZE +				\
-	 RISC_SYNC_INSTRUCTION_SIZE + RISC_WRITECR_INSTRUCTION_SIZE)
-
-#define NTSC_US_VID_PROG_SIZE						\
-	((NTSC_ODD_FLD_LINES + 1) * 3 * DWORD_SIZE +			\
-	 RISC_WRITECR_INSTRUCTION_SIZE + JUMP_INSTRUCTION_SIZE)
-
-#define NTSC_RISC_BUF_SIZE						\
-	(2 * (RISC_SYNC_INSTRUCTION_SIZE + NTSC_US_VID_PROG_SIZE))
-
-#define FRAME1_VID_PROG_SIZE						\
-	((NTSC_ODD_FLD_LINES + NTSC_FIELD_HEIGHT) * 3 * DWORD_SIZE +	\
-	 2 * RISC_SYNC_INSTRUCTION_SIZE + RISC_WRITECR_INSTRUCTION_SIZE + \
-	 JUMP_INSTRUCTION_SIZE)
-
-#endif
diff --git a/drivers/media/pci/cx25821/cx25821.h b/drivers/media/pci/cx25821/cx25821.h
index b3eb2dabb30b..25eba4ac4499 100644
--- a/drivers/media/pci/cx25821/cx25821.h
+++ b/drivers/media/pci/cx25821/cx25821.h
@@ -432,18 +432,6 @@ extern int cx25821_sram_channel_setup_audio(struct cx25821_dev *dev,
 					    const struct sram_channel *ch,
 					    unsigned int bpl, u32 risc);
 
-extern int cx25821_vidupstream_init(struct cx25821_channel *chan, int pixel_format);
-extern int cx25821_audio_upstream_init(struct cx25821_dev *dev,
-				       int channel_select);
-extern int cx25821_write_frame(struct cx25821_channel *chan,
-		const char __user *data, size_t count);
-extern void cx25821_free_mem_upstream(struct cx25821_channel *chan);
-extern void cx25821_free_mem_upstream_audio(struct cx25821_dev *dev);
-extern void cx25821_stop_upstream_video(struct cx25821_channel *chan);
-extern void cx25821_stop_upstream_audio(struct cx25821_dev *dev);
-extern int cx25821_sram_channel_setup_upstream(struct cx25821_dev *dev,
-					       const struct sram_channel *ch,
-					       unsigned int bpl, u32 risc);
 extern void cx25821_set_pixel_format(struct cx25821_dev *dev, int channel,
 				     u32 format);
 
diff --git a/drivers/media/pci/cx88/cx88-alsa.c b/drivers/media/pci/cx88/cx88-alsa.c
index e5c3387cd1e8..89a65478ae36 100644
--- a/drivers/media/pci/cx88/cx88-alsa.c
+++ b/drivers/media/pci/cx88/cx88-alsa.c
@@ -962,8 +962,11 @@ static int cx88_audio_initdev(struct pci_dev *pci,
 		goto error;
 
 	/* If there's a wm8775 then add a Line-In ALC switch */
-	if (core->sd_wm8775)
-		snd_ctl_add(card, snd_ctl_new1(&snd_cx88_alc_switch, chip));
+	if (core->sd_wm8775) {
+		err = snd_ctl_add(card, snd_ctl_new1(&snd_cx88_alc_switch, chip));
+		if (err < 0)
+			goto error;
+	}
 
 	strcpy(card->driver, "CX88x");
 	sprintf(card->shortname, "Conexant CX%x", pci->device);
diff --git a/drivers/media/pci/cx88/cx88-cards.c b/drivers/media/pci/cx88/cx88-cards.c
index 4c92d2388c26..07e1483e987d 100644
--- a/drivers/media/pci/cx88/cx88-cards.c
+++ b/drivers/media/pci/cx88/cx88-cards.c
@@ -3307,9 +3307,9 @@ static void cx88_card_setup_pre_i2c(struct cx88_core *core)
 	case CX88_BOARD_PROLINK_PV_GLOBAL_XTREME:
 	case CX88_BOARD_PROLINK_PV_8000GT:
 		cx_write(MO_GP2_IO, 0xcf7);
-		mdelay(50);
+		msleep(50);
 		cx_write(MO_GP2_IO, 0xef5);
-		mdelay(50);
+		msleep(50);
 		cx_write(MO_GP2_IO, 0xcf7);
 		usleep_range(10000, 20000);
 		break;
diff --git a/drivers/media/pci/cx88/cx88-dvb.c b/drivers/media/pci/cx88/cx88-dvb.c
index ccfde28d4af2..90b208747e0f 100644
--- a/drivers/media/pci/cx88/cx88-dvb.c
+++ b/drivers/media/pci/cx88/cx88-dvb.c
@@ -1226,9 +1226,9 @@ static int dvb_register(struct cx8802_dev *dev)
 
 		/* Do a hardware reset of chip before using it. */
 		cx_clear(MO_GP0_IO, 1);
-		mdelay(100);
+		msleep(100);
 		cx_set(MO_GP0_IO, 1);
-		mdelay(200);
+		msleep(200);
 
 		/* Select RF connector callback */
 		fusionhdtv_3_gold.pll_rf_set = lgdt330x_pll_rf_set;
@@ -1248,9 +1248,9 @@ static int dvb_register(struct cx8802_dev *dev)
 
 		/* Do a hardware reset of chip before using it. */
 		cx_clear(MO_GP0_IO, 1);
-		mdelay(100);
+		msleep(100);
 		cx_set(MO_GP0_IO, 9);
-		mdelay(200);
+		msleep(200);
 		fe0->dvb.frontend = dvb_attach(lgdt330x_attach,
 					       &fusionhdtv_3_gold,
 					       0x0e,
@@ -1267,9 +1267,9 @@ static int dvb_register(struct cx8802_dev *dev)
 
 		/* Do a hardware reset of chip before using it. */
 		cx_clear(MO_GP0_IO, 1);
-		mdelay(100);
+		msleep(100);
 		cx_set(MO_GP0_IO, 1);
-		mdelay(200);
+		msleep(200);
 		fe0->dvb.frontend = dvb_attach(lgdt330x_attach,
 					       &fusionhdtv_5_gold,
 					       0x0e,
@@ -1289,9 +1289,9 @@ static int dvb_register(struct cx8802_dev *dev)
 
 		/* Do a hardware reset of chip before using it. */
 		cx_clear(MO_GP0_IO, 1);
-		mdelay(100);
+		msleep(100);
 		cx_set(MO_GP0_IO, 1);
-		mdelay(200);
+		msleep(200);
 		fe0->dvb.frontend = dvb_attach(lgdt330x_attach,
 					       &pchdtv_hd5500,
 					       0x59,
@@ -1583,9 +1583,9 @@ static int dvb_register(struct cx8802_dev *dev)
 		cx_set(MO_GP0_IO, 0x0101);
 
 		cx_clear(MO_GP0_IO, 0x01);
-		mdelay(100);
+		msleep(100);
 		cx_set(MO_GP0_IO, 0x01);
-		mdelay(200);
+		msleep(200);
 
 		fe0->dvb.frontend = dvb_attach(stv0299_attach,
 					       &samsung_stv0299_config,
diff --git a/drivers/media/pci/ddbridge/Makefile b/drivers/media/pci/ddbridge/Makefile
index 9b9e35f171b7..5b6d5bbc38af 100644
--- a/drivers/media/pci/ddbridge/Makefile
+++ b/drivers/media/pci/ddbridge/Makefile
@@ -4,7 +4,8 @@
 #
 
 ddbridge-objs := ddbridge-main.o ddbridge-core.o ddbridge-ci.o \
-		ddbridge-hw.o ddbridge-i2c.o ddbridge-max.o ddbridge-mci.o
+		ddbridge-hw.o ddbridge-i2c.o ddbridge-max.o ddbridge-mci.o \
+		ddbridge-sx8.o
 
 obj-$(CONFIG_DVB_DDBRIDGE) += ddbridge.o
 
diff --git a/drivers/media/pci/ddbridge/ddbridge-core.c b/drivers/media/pci/ddbridge/ddbridge-core.c
index d5b0d1eaf3ad..c1b982e8e6c9 100644
--- a/drivers/media/pci/ddbridge/ddbridge-core.c
+++ b/drivers/media/pci/ddbridge/ddbridge-core.c
@@ -1191,6 +1191,13 @@ static const struct lnbh25_config lnbh25_cfg = {
 	.data2_config = LNBH25_TEN
 };
 
+static int has_lnbh25(struct i2c_adapter *i2c, u8 adr)
+{
+	u8 val;
+
+	return i2c_read_reg(i2c, adr, 0, &val) ? 0 : 1;
+}
+
 static int demod_attach_stv0910(struct ddb_input *input, int type, int tsfast)
 {
 	struct i2c_adapter *i2c = &input->port->i2c->adap;
@@ -1224,14 +1231,15 @@ static int demod_attach_stv0910(struct ddb_input *input, int type, int tsfast)
 	/* attach lnbh25 - leftshift by one as the lnbh25 driver expects 8bit
 	 * i2c addresses
 	 */
-	lnbcfg.i2c_address = (((input->nr & 1) ? 0x0d : 0x0c) << 1);
-	if (!dvb_attach(lnbh25_attach, dvb->fe, &lnbcfg, i2c)) {
+	if (has_lnbh25(i2c, 0x0d))
+		lnbcfg.i2c_address = (((input->nr & 1) ? 0x0d : 0x0c) << 1);
+	else
 		lnbcfg.i2c_address = (((input->nr & 1) ? 0x09 : 0x08) << 1);
-		if (!dvb_attach(lnbh25_attach, dvb->fe, &lnbcfg, i2c)) {
-			dev_err(dev, "No LNBH25 found!\n");
-			dvb_frontend_detach(dvb->fe);
-			return -ENODEV;
-		}
+
+	if (!dvb_attach(lnbh25_attach, dvb->fe, &lnbcfg, i2c)) {
+		dev_err(dev, "No LNBH25 found!\n");
+		dvb_frontend_detach(dvb->fe);
+		return -ENODEV;
 	}
 
 	return 0;
@@ -1584,8 +1592,8 @@ static int dvb_input_attach(struct ddb_input *input)
 		if (demod_attach_dummy(input) < 0)
 			goto err_detach;
 		break;
-	case DDB_TUNER_MCI:
-		if (ddb_fe_attach_mci(input) < 0)
+	case DDB_TUNER_MCI_SX8:
+		if (ddb_fe_attach_mci(input, port->type) < 0)
 			goto err_detach;
 		break;
 	default:
@@ -1842,6 +1850,7 @@ static void ddb_port_probe(struct ddb_port *port)
 {
 	struct ddb *dev = port->dev;
 	u32 l = port->lnr;
+	struct ddb_link *link = &dev->link[l];
 	u8 id, type;
 
 	port->name = "NO MODULE";
@@ -1851,7 +1860,7 @@ static void ddb_port_probe(struct ddb_port *port)
 	/* Handle missing ports and ports without I2C */
 
 	if (dummy_tuner && !port->nr &&
-	    dev->link[0].ids.device == 0x0005) {
+	    link->ids.device == 0x0005) {
 		port->name = "DUMMY";
 		port->class = DDB_PORT_TUNER;
 		port->type = DDB_TUNER_DUMMY;
@@ -1865,14 +1874,14 @@ static void ddb_port_probe(struct ddb_port *port)
 		return;
 	}
 
-	if (port->nr == 1 && dev->link[l].info->type == DDB_OCTOPUS_CI &&
-	    dev->link[l].info->i2c_mask == 1) {
+	if (port->nr == 1 && link->info->type == DDB_OCTOPUS_CI &&
+	    link->info->i2c_mask == 1) {
 		port->name = "NO TAB";
 		port->class = DDB_PORT_NONE;
 		return;
 	}
 
-	if (dev->link[l].info->type == DDB_OCTOPUS_MAX) {
+	if (link->info->type == DDB_OCTOPUS_MAX) {
 		port->name = "DUAL DVB-S2 MAX";
 		port->type_name = "MXL5XX";
 		port->class = DDB_PORT_TUNER;
@@ -1883,17 +1892,17 @@ static void ddb_port_probe(struct ddb_port *port)
 		return;
 	}
 
-	if (dev->link[l].info->type == DDB_OCTOPUS_MCI) {
-		if (port->nr >= dev->link[l].info->mci)
+	if (link->info->type == DDB_OCTOPUS_MCI) {
+		if (port->nr >= link->info->mci_ports)
 			return;
 		port->name = "DUAL MCI";
 		port->type_name = "MCI";
 		port->class = DDB_PORT_TUNER;
-		port->type = DDB_TUNER_MCI;
+		port->type = DDB_TUNER_MCI + link->info->mci_type;
 		return;
 	}
 
-	if (port->nr > 1 && dev->link[l].info->type == DDB_OCTOPUS_CI) {
+	if (port->nr > 1 && link->info->type == DDB_OCTOPUS_CI) {
 		port->name = "CI internal";
 		port->type_name = "INTERNAL";
 		port->class = DDB_PORT_CI;
@@ -1978,7 +1987,7 @@ static void ddb_port_probe(struct ddb_port *port)
 		port->class = DDB_PORT_TUNER;
 		if (id == 0x51) {
 			if (port->nr == 0 &&
-			    dev->link[l].info->ts_quirks & TS_QUIRK_REVERSED)
+			    link->info->ts_quirks & TS_QUIRK_REVERSED)
 				port->type = DDB_TUNER_DVBS_STV0910_PR;
 			else
 				port->type = DDB_TUNER_DVBS_STV0910_P;
diff --git a/drivers/media/pci/ddbridge/ddbridge-hw.c b/drivers/media/pci/ddbridge/ddbridge-hw.c
index 1d3ee6accdd5..f3cbac07b41f 100644
--- a/drivers/media/pci/ddbridge/ddbridge-hw.c
+++ b/drivers/media/pci/ddbridge/ddbridge-hw.c
@@ -318,7 +318,8 @@ static const struct ddb_info ddb_s2x_48 = {
 	.port_num = 4,
 	.i2c_mask = 0x00,
 	.tempmon_irq = 24,
-	.mci      = 4
+	.mci_ports = 4,
+	.mci_type = 0,
 };
 
 /****************************************************************************/
diff --git a/drivers/media/pci/ddbridge/ddbridge-i2c.c b/drivers/media/pci/ddbridge/ddbridge-i2c.c
index 667340c86ea7..5a28d7611713 100644
--- a/drivers/media/pci/ddbridge/ddbridge-i2c.c
+++ b/drivers/media/pci/ddbridge/ddbridge-i2c.c
@@ -73,7 +73,10 @@ static int ddb_i2c_cmd(struct ddb_i2c *i2c, u32 adr, u32 cmd)
 		}
 		return -EIO;
 	}
-	if (val & 0x70000)
+	val &= 0x70000;
+	if (val == 0x20000)
+		dev_err(dev->dev, "I2C bus error\n");
+	if (val)
 		return -EIO;
 	return 0;
 }
diff --git a/drivers/media/pci/ddbridge/ddbridge-max.c b/drivers/media/pci/ddbridge/ddbridge-max.c
index 739e4b444cf4..8da1c7b91577 100644
--- a/drivers/media/pci/ddbridge/ddbridge-max.c
+++ b/drivers/media/pci/ddbridge/ddbridge-max.c
@@ -457,21 +457,29 @@ int ddb_fe_attach_mxl5xx(struct ddb_input *input)
 /******************************************************************************/
 /* MAX MCI related functions */
 
-int ddb_fe_attach_mci(struct ddb_input *input)
+int ddb_fe_attach_mci(struct ddb_input *input, u32 type)
 {
 	struct ddb *dev = input->port->dev;
 	struct ddb_dvb *dvb = &input->port->dvb[input->nr & 1];
 	struct ddb_port *port = input->port;
 	struct ddb_link *link = &dev->link[port->lnr];
 	int demod, tuner;
+	struct mci_cfg cfg;
 
 	demod = input->nr;
 	tuner = demod & 3;
-	if (fmode == 3)
-		tuner = 0;
-	dvb->fe = ddb_mci_attach(input, 0, demod, &dvb->set_input);
+	switch (type) {
+	case DDB_TUNER_MCI_SX8:
+		cfg = ddb_max_sx8_cfg;
+		if (fmode == 3)
+			tuner = 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+	dvb->fe = ddb_mci_attach(input, &cfg, demod, &dvb->set_input);
 	if (!dvb->fe) {
-		dev_err(dev->dev, "No MAXSX8 found!\n");
+		dev_err(dev->dev, "No MCI card found!\n");
 		return -ENODEV;
 	}
 	if (!dvb->set_input) {
diff --git a/drivers/media/pci/ddbridge/ddbridge-max.h b/drivers/media/pci/ddbridge/ddbridge-max.h
index 82efc53baa94..9838c73973b6 100644
--- a/drivers/media/pci/ddbridge/ddbridge-max.h
+++ b/drivers/media/pci/ddbridge/ddbridge-max.h
@@ -25,6 +25,6 @@
 
 int ddb_lnb_init_fmode(struct ddb *dev, struct ddb_link *link, u32 fm);
 int ddb_fe_attach_mxl5xx(struct ddb_input *input);
-int ddb_fe_attach_mci(struct ddb_input *input);
+int ddb_fe_attach_mci(struct ddb_input *input, u32 type);
 
 #endif /* _DDBRIDGE_MAX_H */
diff --git a/drivers/media/pci/ddbridge/ddbridge-mci.c b/drivers/media/pci/ddbridge/ddbridge-mci.c
index 4ac634fc96e4..97384ae9ad27 100644
--- a/drivers/media/pci/ddbridge/ddbridge-mci.c
+++ b/drivers/media/pci/ddbridge/ddbridge-mci.c
@@ -2,9 +2,9 @@
 /*
  * ddbridge-mci.c: Digital Devices microcode interface
  *
- * Copyright (C) 2017 Digital Devices GmbH
- *                    Ralph Metzler <rjkm@metzlerbros.de>
- *                    Marcus Metzler <mocm@metzlerbros.de>
+ * Copyright (C) 2017-2018 Digital Devices GmbH
+ *                         Ralph Metzler <rjkm@metzlerbros.de>
+ *                         Marcus Metzler <mocm@metzlerbros.de>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -22,42 +22,6 @@
 
 static LIST_HEAD(mci_list);
 
-static const u32 MCLK = (1550000000 / 12);
-static const u32 MAX_DEMOD_LDPC_BITRATE = (1550000000 / 6);
-static const u32 MAX_LDPC_BITRATE = (720000000);
-
-struct mci_base {
-	struct list_head     mci_list;
-	void                *key;
-	struct ddb_link     *link;
-	struct completion    completion;
-
-	struct device       *dev;
-	struct mutex         tuner_lock; /* concurrent tuner access lock */
-	u8                   adr;
-	struct mutex         mci_lock; /* concurrent MCI access lock */
-	int                  count;
-
-	u8                   tuner_use_count[MCI_TUNER_MAX];
-	u8                   assigned_demod[MCI_DEMOD_MAX];
-	u32                  used_ldpc_bitrate[MCI_DEMOD_MAX];
-	u8                   demod_in_use[MCI_DEMOD_MAX];
-	u32                  iq_mode;
-};
-
-struct mci {
-	struct mci_base     *base;
-	struct dvb_frontend  fe;
-	int                  nr;
-	int                  demod;
-	int                  tuner;
-	int                  first_time_lock;
-	int                  started;
-	struct mci_result    signal_info;
-
-	u32                  bb_mode;
-};
-
 static int mci_reset(struct mci *state)
 {
 	struct ddb_link *link = state->base->link;
@@ -84,7 +48,7 @@ static int mci_reset(struct mci *state)
 	return 0;
 }
 
-static int mci_config(struct mci *state, u32 config)
+int ddb_mci_config(struct mci *state, u32 config)
 {
 	struct ddb_link *link = state->base->link;
 
@@ -122,16 +86,16 @@ static int _mci_cmd_unlocked(struct mci *state,
 	return 0;
 }
 
-static int mci_cmd(struct mci *state,
-		   struct mci_command *command,
-		   struct mci_result *result)
+int ddb_mci_cmd(struct mci *state,
+		struct mci_command *command,
+		struct mci_result *result)
 {
 	int stat;
 
 	mutex_lock(&state->base->mci_lock);
 	stat = _mci_cmd_unlocked(state,
 				 (u32 *)command, sizeof(*command) / sizeof(u32),
-				 (u32 *)result, sizeof(*result) / sizeof(u32));
+				 (u32 *)result,	sizeof(*result) / sizeof(u32));
 	mutex_unlock(&state->base->mci_lock);
 	return stat;
 }
@@ -143,344 +107,6 @@ static void mci_handler(void *priv)
 	complete(&base->completion);
 }
 
-static void release(struct dvb_frontend *fe)
-{
-	struct mci *state = fe->demodulator_priv;
-
-	state->base->count--;
-	if (state->base->count == 0) {
-		list_del(&state->base->mci_list);
-		kfree(state->base);
-	}
-	kfree(state);
-}
-
-static int read_status(struct dvb_frontend *fe, enum fe_status *status)
-{
-	int stat;
-	struct mci *state = fe->demodulator_priv;
-	struct mci_command cmd;
-	struct mci_result res;
-
-	cmd.command = MCI_CMD_GETSTATUS;
-	cmd.demod = state->demod;
-	stat = mci_cmd(state, &cmd, &res);
-	if (stat)
-		return stat;
-	*status = 0x00;
-	if (res.status == SX8_DEMOD_WAIT_MATYPE)
-		*status = 0x0f;
-	if (res.status == SX8_DEMOD_LOCKED)
-		*status = 0x1f;
-	return stat;
-}
-
-static int mci_set_tuner(struct dvb_frontend *fe, u32 tuner, u32 on)
-{
-	struct mci *state = fe->demodulator_priv;
-	struct mci_command cmd;
-
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.tuner = state->tuner;
-	cmd.command = on ? SX8_CMD_INPUT_ENABLE : SX8_CMD_INPUT_DISABLE;
-	return mci_cmd(state, &cmd, NULL);
-}
-
-static int stop(struct dvb_frontend *fe)
-{
-	struct mci *state = fe->demodulator_priv;
-	struct mci_command cmd;
-	u32 input = state->tuner;
-
-	memset(&cmd, 0, sizeof(cmd));
-	if (state->demod != DEMOD_UNUSED) {
-		cmd.command = MCI_CMD_STOP;
-		cmd.demod = state->demod;
-		mci_cmd(state, &cmd, NULL);
-		if (state->base->iq_mode) {
-			cmd.command = MCI_CMD_STOP;
-			cmd.demod = state->demod;
-			cmd.output = 0;
-			mci_cmd(state, &cmd, NULL);
-			mci_config(state, SX8_TSCONFIG_MODE_NORMAL);
-		}
-	}
-	mutex_lock(&state->base->tuner_lock);
-	state->base->tuner_use_count[input]--;
-	if (!state->base->tuner_use_count[input])
-		mci_set_tuner(fe, input, 0);
-	if (state->demod < MCI_DEMOD_MAX)
-		state->base->demod_in_use[state->demod] = 0;
-	state->base->used_ldpc_bitrate[state->nr] = 0;
-	state->demod = DEMOD_UNUSED;
-	state->base->assigned_demod[state->nr] = DEMOD_UNUSED;
-	state->base->iq_mode = 0;
-	mutex_unlock(&state->base->tuner_lock);
-	state->started = 0;
-	return 0;
-}
-
-static int start(struct dvb_frontend *fe, u32 flags, u32 modmask, u32 ts_config)
-{
-	struct mci *state = fe->demodulator_priv;
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
-	u32 used_ldpc_bitrate = 0, free_ldpc_bitrate;
-	u32 used_demods = 0;
-	struct mci_command cmd;
-	u32 input = state->tuner;
-	u32 bits_per_symbol = 0;
-	int i, stat = 0;
-
-	if (p->symbol_rate >= (MCLK / 2))
-		flags &= ~1;
-	if ((flags & 3) == 0)
-		return -EINVAL;
-
-	if (flags & 2) {
-		u32 tmp = modmask;
-
-		bits_per_symbol = 1;
-		while (tmp & 1) {
-			tmp >>= 1;
-			bits_per_symbol++;
-		}
-	}
-
-	mutex_lock(&state->base->tuner_lock);
-	if (state->base->iq_mode) {
-		stat = -EBUSY;
-		goto unlock;
-	}
-	for (i = 0; i < MCI_DEMOD_MAX; i++) {
-		used_ldpc_bitrate += state->base->used_ldpc_bitrate[i];
-		if (state->base->demod_in_use[i])
-			used_demods++;
-	}
-	if (used_ldpc_bitrate >= MAX_LDPC_BITRATE ||
-	    ((ts_config & SX8_TSCONFIG_MODE_MASK) >
-	     SX8_TSCONFIG_MODE_NORMAL && used_demods > 0)) {
-		stat = -EBUSY;
-		goto unlock;
-	}
-	free_ldpc_bitrate = MAX_LDPC_BITRATE - used_ldpc_bitrate;
-	if (free_ldpc_bitrate > MAX_DEMOD_LDPC_BITRATE)
-		free_ldpc_bitrate = MAX_DEMOD_LDPC_BITRATE;
-
-	while (p->symbol_rate * bits_per_symbol > free_ldpc_bitrate)
-		bits_per_symbol--;
-
-	if (bits_per_symbol < 2) {
-		stat = -EBUSY;
-		goto unlock;
-	}
-	i = (p->symbol_rate > (MCLK / 2)) ? 3 : 7;
-	while (i >= 0 && state->base->demod_in_use[i])
-		i--;
-	if (i < 0) {
-		stat = -EBUSY;
-		goto unlock;
-	}
-	state->base->demod_in_use[i] = 1;
-	state->base->used_ldpc_bitrate[state->nr] = p->symbol_rate
-						    * bits_per_symbol;
-	state->demod = i;
-	state->base->assigned_demod[state->nr] = i;
-
-	if (!state->base->tuner_use_count[input])
-		mci_set_tuner(fe, input, 1);
-	state->base->tuner_use_count[input]++;
-	state->base->iq_mode = (ts_config > 1);
-unlock:
-	mutex_unlock(&state->base->tuner_lock);
-	if (stat)
-		return stat;
-	memset(&cmd, 0, sizeof(cmd));
-
-	if (state->base->iq_mode) {
-		cmd.command = SX8_CMD_SELECT_IQOUT;
-		cmd.demod = state->demod;
-		cmd.output = 0;
-		mci_cmd(state, &cmd, NULL);
-		mci_config(state, ts_config);
-	}
-	if (p->stream_id != NO_STREAM_ID_FILTER && p->stream_id != 0x80000000)
-		flags |= 0x80;
-	dev_dbg(state->base->dev, "MCI-%d: tuner=%d demod=%d\n",
-		state->nr, state->tuner, state->demod);
-	cmd.command = MCI_CMD_SEARCH_DVBS;
-	cmd.dvbs2_search.flags = flags;
-	cmd.dvbs2_search.s2_modulation_mask =
-		modmask & ((1 << (bits_per_symbol - 1)) - 1);
-	cmd.dvbs2_search.retry = 2;
-	cmd.dvbs2_search.frequency = p->frequency * 1000;
-	cmd.dvbs2_search.symbol_rate = p->symbol_rate;
-	cmd.dvbs2_search.scrambling_sequence_index =
-		p->scrambling_sequence_index;
-	cmd.dvbs2_search.input_stream_id =
-		(p->stream_id != NO_STREAM_ID_FILTER) ? p->stream_id : 0;
-	cmd.tuner = state->tuner;
-	cmd.demod = state->demod;
-	cmd.output = state->nr;
-	if (p->stream_id == 0x80000000)
-		cmd.output |= 0x80;
-	stat = mci_cmd(state, &cmd, NULL);
-	if (stat)
-		stop(fe);
-	return stat;
-}
-
-static int start_iq(struct dvb_frontend *fe, u32 ts_config)
-{
-	struct mci *state = fe->demodulator_priv;
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
-	u32 used_demods = 0;
-	struct mci_command cmd;
-	u32 input = state->tuner;
-	int i, stat = 0;
-
-	mutex_lock(&state->base->tuner_lock);
-	if (state->base->iq_mode) {
-		stat = -EBUSY;
-		goto unlock;
-	}
-	for (i = 0; i < MCI_DEMOD_MAX; i++)
-		if (state->base->demod_in_use[i])
-			used_demods++;
-	if (used_demods > 0) {
-		stat = -EBUSY;
-		goto unlock;
-	}
-	state->demod = 0;
-	state->base->assigned_demod[state->nr] = 0;
-	if (!state->base->tuner_use_count[input])
-		mci_set_tuner(fe, input, 1);
-	state->base->tuner_use_count[input]++;
-	state->base->iq_mode = (ts_config > 1);
-unlock:
-	mutex_unlock(&state->base->tuner_lock);
-	if (stat)
-		return stat;
-
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.command = SX8_CMD_START_IQ;
-	cmd.dvbs2_search.frequency = p->frequency * 1000;
-	cmd.dvbs2_search.symbol_rate = p->symbol_rate;
-	cmd.tuner = state->tuner;
-	cmd.demod = state->demod;
-	cmd.output = 7;
-	mci_config(state, ts_config);
-	stat = mci_cmd(state, &cmd, NULL);
-	if (stat)
-		stop(fe);
-	return stat;
-}
-
-static int set_parameters(struct dvb_frontend *fe)
-{
-	int stat = 0;
-	struct mci *state = fe->demodulator_priv;
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
-	u32 ts_config, iq_mode = 0, isi;
-
-	if (state->started)
-		stop(fe);
-
-	isi = p->stream_id;
-	if (isi != NO_STREAM_ID_FILTER)
-		iq_mode = (isi & 0x30000000) >> 28;
-
-	switch (iq_mode) {
-	case 1:
-		ts_config = (SX8_TSCONFIG_TSHEADER | SX8_TSCONFIG_MODE_IQ);
-		break;
-	case 2:
-		ts_config = (SX8_TSCONFIG_TSHEADER | SX8_TSCONFIG_MODE_IQ);
-		break;
-	default:
-		ts_config = SX8_TSCONFIG_MODE_NORMAL;
-		break;
-	}
-
-	if (iq_mode != 2) {
-		u32 flags = 3;
-		u32 mask = 3;
-
-		if (p->modulation == APSK_16 ||
-		    p->modulation == APSK_32) {
-			flags = 2;
-			mask = 15;
-		}
-		stat = start(fe, flags, mask, ts_config);
-	} else {
-		stat = start_iq(fe, ts_config);
-	}
-
-	if (!stat) {
-		state->started = 1;
-		state->first_time_lock = 1;
-		state->signal_info.status = SX8_DEMOD_WAIT_SIGNAL;
-	}
-
-	return stat;
-}
-
-static int tune(struct dvb_frontend *fe, bool re_tune,
-		unsigned int mode_flags,
-		unsigned int *delay, enum fe_status *status)
-{
-	int r;
-
-	if (re_tune) {
-		r = set_parameters(fe);
-		if (r)
-			return r;
-	}
-	r = read_status(fe, status);
-	if (r)
-		return r;
-
-	if (*status & FE_HAS_LOCK)
-		return 0;
-	*delay = HZ / 10;
-	return 0;
-}
-
-static enum dvbfe_algo get_algo(struct dvb_frontend *fe)
-{
-	return DVBFE_ALGO_HW;
-}
-
-static int set_input(struct dvb_frontend *fe, int input)
-{
-	struct mci *state = fe->demodulator_priv;
-
-	state->tuner = input;
-	dev_dbg(state->base->dev, "MCI-%d: input=%d\n", state->nr, input);
-	return 0;
-}
-
-static struct dvb_frontend_ops mci_ops = {
-	.delsys = { SYS_DVBS, SYS_DVBS2 },
-	.info = {
-		.name			= "Digital Devices MaxSX8 MCI DVB-S/S2/S2X",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 0,
-		.frequency_tolerance	= 0,
-		.symbol_rate_min	= 100000,
-		.symbol_rate_max	= 100000000,
-		.caps			= FE_CAN_INVERSION_AUTO |
-					  FE_CAN_FEC_AUTO       |
-					  FE_CAN_QPSK           |
-					  FE_CAN_2G_MODULATION  |
-					  FE_CAN_MULTISTREAM,
-	},
-	.get_frontend_algo		= get_algo,
-	.tune				= tune,
-	.release			= release,
-	.read_status			= read_status,
-};
-
 static struct mci_base *match_base(void *key)
 {
 	struct mci_base *p;
@@ -498,8 +124,7 @@ static int probe(struct mci *state)
 }
 
 struct dvb_frontend
-*ddb_mci_attach(struct ddb_input *input,
-		int mci_type, int nr,
+*ddb_mci_attach(struct ddb_input *input, struct mci_cfg *cfg, int nr,
 		int (**fn_set_input)(struct dvb_frontend *fe, int input))
 {
 	struct ddb_port *port = input->port;
@@ -507,9 +132,9 @@ struct dvb_frontend
 	struct ddb_link *link = &dev->link[port->lnr];
 	struct mci_base *base;
 	struct mci *state;
-	void *key = mci_type ? (void *)port : (void *)link;
+	void *key = cfg->type ? (void *)port : (void *)link;
 
-	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	state = kzalloc(cfg->state_size, GFP_KERNEL);
 	if (!state)
 		return NULL;
 
@@ -518,7 +143,7 @@ struct dvb_frontend
 		base->count++;
 		state->base = base;
 	} else {
-		base = kzalloc(sizeof(*base), GFP_KERNEL);
+		base = kzalloc(cfg->base_size, GFP_KERNEL);
 		if (!base)
 			goto fail;
 		base->key = key;
@@ -535,15 +160,17 @@ struct dvb_frontend
 			goto fail;
 		}
 		list_add(&base->mci_list, &mci_list);
+		if (cfg->base_init)
+			cfg->base_init(base);
 	}
-	state->fe.ops = mci_ops;
+	memcpy(&state->fe.ops, cfg->fe_ops, sizeof(struct dvb_frontend_ops));
 	state->fe.demodulator_priv = state;
 	state->nr = nr;
-	*fn_set_input = set_input;
-
+	*fn_set_input = cfg->set_input;
 	state->tuner = nr;
 	state->demod = nr;
-
+	if (cfg->init)
+		cfg->init(state);
 	return &state->fe;
 fail:
 	kfree(state);
diff --git a/drivers/media/pci/ddbridge/ddbridge-mci.h b/drivers/media/pci/ddbridge/ddbridge-mci.h
index 209cc2b92dff..24241111c634 100644
--- a/drivers/media/pci/ddbridge/ddbridge-mci.h
+++ b/drivers/media/pci/ddbridge/ddbridge-mci.h
@@ -2,9 +2,9 @@
 /*
  * ddbridge-mci.h: Digital Devices micro code interface
  *
- * Copyright (C) 2017 Digital Devices GmbH
- *                    Marcus Metzler <mocm@metzlerbros.de>
- *                    Ralph Metzler <rjkm@metzlerbros.de>
+ * Copyright (C) 2017-2018 Digital Devices GmbH
+ *                         Marcus Metzler <mocm@metzlerbros.de>
+ *                         Ralph Metzler <rjkm@metzlerbros.de>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -42,6 +42,22 @@
 #define SX8_TSCONFIG_MODE_NORMAL            (0x00000001)
 #define SX8_TSCONFIG_MODE_IQ                (0x00000003)
 
+/*
+ * IQMode is only available on MaxSX8 on a single tuner
+ *
+ * IQ_MODE_SAMPLES
+ *       sampling rate is 1550/24 MHz (64.583 MHz)
+ *       channel agc is frozen, to allow stitching the FFT results together
+ *
+ * IQ_MODE_VTM
+ *       sampling rate is the supplied symbolrate
+ *       channel agc is active
+ *
+ * in both cases down sampling is done with a RRC Filter (currently fixed to
+ * alpha = 0.05) which causes some (ca 5%) aliasing at the edges from
+ * outside the spectrum
+ */
+
 #define SX8_TSCONFIG_TSHEADER               (0x00000004)
 #define SX8_TSCONFIG_BURST                  (0x00000008)
 
@@ -51,55 +67,65 @@
 #define SX8_TSCONFIG_BURSTSIZE_8K           (0x00000020)
 #define SX8_TSCONFIG_BURSTSIZE_16K          (0x00000030)
 
-#define SX8_DEMOD_STOPPED       (0)
-#define SX8_DEMOD_IQ_MODE       (1)
-#define SX8_DEMOD_WAIT_SIGNAL   (2)
-#define SX8_DEMOD_WAIT_MATYPE   (3)
-#define SX8_DEMOD_TIMEOUT       (14)
-#define SX8_DEMOD_LOCKED        (15)
-
-#define MCI_CMD_STOP            (0x01)
-#define MCI_CMD_GETSTATUS       (0x02)
-#define MCI_CMD_GETSIGNALINFO   (0x03)
-#define MCI_CMD_RFPOWER         (0x04)
-
-#define MCI_CMD_SEARCH_DVBS     (0x10)
+#define SX8_DEMOD_STOPPED        (0)
+#define SX8_DEMOD_IQ_MODE        (1)
+#define SX8_DEMOD_WAIT_SIGNAL    (2)
+#define SX8_DEMOD_WAIT_MATYPE    (3)
+#define SX8_DEMOD_TIMEOUT        (14)
+#define SX8_DEMOD_LOCKED         (15)
 
-#define MCI_CMD_GET_IQSYMBOL    (0x30)
+#define MCI_CMD_STOP             (0x01)
+#define MCI_CMD_GETSTATUS        (0x02)
+#define MCI_CMD_GETSIGNALINFO    (0x03)
+#define MCI_CMD_RFPOWER          (0x04)
 
-#define SX8_CMD_INPUT_ENABLE    (0x40)
-#define SX8_CMD_INPUT_DISABLE   (0x41)
-#define SX8_CMD_START_IQ        (0x42)
-#define SX8_CMD_STOP_IQ         (0x43)
-#define SX8_CMD_SELECT_IQOUT    (0x44)
-#define SX8_CMD_SELECT_TSOUT    (0x45)
+#define MCI_CMD_SEARCH_DVBS      (0x10)
 
-#define SX8_ERROR_UNSUPPORTED   (0x80)
+#define MCI_CMD_GET_IQSYMBOL     (0x30)
 
-#define SX8_SUCCESS(status)     (status < SX8_ERROR_UNSUPPORTED)
+#define SX8_CMD_INPUT_ENABLE     (0x40)
+#define SX8_CMD_INPUT_DISABLE    (0x41)
+#define SX8_CMD_START_IQ         (0x42)
+#define SX8_CMD_STOP_IQ          (0x43)
+#define SX8_CMD_ENABLE_IQOUTPUT  (0x44)
+#define SX8_CMD_DISABLE_IQOUTPUT (0x45)
 
-#define SX8_CMD_DIAG_READ8      (0xE0)
-#define SX8_CMD_DIAG_READ32     (0xE1)
-#define SX8_CMD_DIAG_WRITE8     (0xE2)
-#define SX8_CMD_DIAG_WRITE32    (0xE3)
+#define MCI_STATUS_OK            (0x00)
+#define MCI_STATUS_UNSUPPORTED   (0x80)
+#define MCI_STATUS_RETRY         (0xFD)
+#define MCI_STATUS_NOT_READY     (0xFE)
+#define MCI_STATUS_ERROR         (0xFF)
 
-#define SX8_CMD_DIAG_READRF     (0xE8)
-#define SX8_CMD_DIAG_WRITERF    (0xE9)
+#define MCI_SUCCESS(status)      ((status & MCI_STATUS_UNSUPPORTED) == 0)
 
 struct mci_command {
 	union {
 		u32 command_word;
 		struct {
-			u8 command;
-			u8 tuner;
-			u8 demod;
-			u8 output;
+			u8  command;
+			u8  tuner;
+			u8  demod;
+			u8  output;
 		};
 	};
 	union {
 		u32 params[31];
 		struct {
+			/*
+			 * Bit 0: DVB-S Enabled
+			 * Bit 1: DVB-S2 Enabled
+			 * Bit 7: InputStreamID
+			 */
 			u8  flags;
+			/*
+			 * Bit 0: QPSK,
+			 * Bit 1: 8PSK/8APSK
+			 * Bit 2: 16APSK
+			 * Bit 3: 32APSK
+			 * Bit 4: 64APSK
+			 * Bit 5: 128APSK
+			 * Bit 6: 256APSK
+			 */
 			u8  s2_modulation_mask;
 			u8  rsvd1;
 			u8  retry;
@@ -108,7 +134,36 @@ struct mci_command {
 			u8  input_stream_id;
 			u8  rsvd2[3];
 			u32 scrambling_sequence_index;
+			u32 frequency_range;
 		} dvbs2_search;
+
+		struct {
+			u8  tap;
+			u8  rsvd;
+			u16 point;
+		} get_iq_symbol;
+
+		struct {
+			/*
+			 * Bit 0: 0=VTM/1=SCAN
+			 * Bit 1: Set Gain
+			 */
+			u8  flags;
+			u8  roll_off;
+			u8  rsvd1;
+			u8  rsvd2;
+			u32 frequency;
+			u32 symbol_rate; /* Only in VTM mode */
+			u16 gain;
+		} sx8_start_iq;
+
+		struct {
+			/*
+			 * Bit 1:0 = STVVGLNA Gain.
+			 *   0 = AGC, 1 = 0dB, 2 = Minimum, 3 = Maximum
+			 */
+			u8  flags;
+		} sx8_input_enable;
 	};
 };
 
@@ -116,41 +171,92 @@ struct mci_result {
 	union {
 		u32 status_word;
 		struct {
-			u8 status;
-			u8 rsvd;
+			u8  status;
+			u8  mode;
 			u16 time;
 		};
 	};
 	union {
 		u32 result[27];
 		struct {
+			/* 1 = DVB-S, 2 = DVB-S2X */
 			u8  standard;
 			/* puncture rate for DVB-S */
 			u8  pls_code;
-			/* 7-6: rolloff, 5-2: rsrvd, 1:short, 0:pilots */
+			/* 2-0: rolloff */
 			u8  roll_off;
 			u8  rsvd;
+			/* actual frequency in Hz */
 			u32 frequency;
+			/* actual symbolrate in Hz */
 			u32 symbol_rate;
+			/* channel power in dBm x 100 */
 			s16 channel_power;
+			/* band power in dBm x 100 */
 			s16 band_power;
+			/*
+			 * SNR in dB x 100
+			 * Note: negative values are valid in DVB-S2
+			 */
 			s16 signal_to_noise;
 			s16 rsvd2;
+			/*
+			 * Counter for packet errors
+			 * (set to 0 on start command)
+			 */
 			u32 packet_errors;
+			/* Bit error rate: PreRS in DVB-S, PreBCH in DVB-S2X */
 			u32 ber_numerator;
 			u32 ber_denominator;
 		} dvbs2_signal_info;
+
 		struct {
-			u8 i_symbol;
-			u8 q_symbol;
-		} dvbs2_signal_iq;
+			s16 i;
+			s16 q;
+		} iq_symbol;
 	};
 	u32 version[4];
 };
 
+struct mci_base {
+	struct list_head     mci_list;
+	void                *key;
+	struct ddb_link     *link;
+	struct completion    completion;
+	struct device       *dev;
+	struct mutex         tuner_lock; /* concurrent tuner access lock */
+	struct mutex         mci_lock; /* concurrent MCI access lock */
+	int                  count;
+	int                  type;
+};
+
+struct mci {
+	struct mci_base     *base;
+	struct dvb_frontend  fe;
+	int                  nr;
+	int                  demod;
+	int                  tuner;
+};
+
+struct mci_cfg {
+	int                  type;
+	struct dvb_frontend_ops *fe_ops;
+	u32                  base_size;
+	u32                  state_size;
+	int (*init)(struct mci *mci);
+	int (*base_init)(struct mci_base *mci_base);
+	int (*set_input)(struct dvb_frontend *fe, int input);
+};
+
+/* defined in ddbridge-sx8.c */
+extern const struct mci_cfg ddb_max_sx8_cfg;
+
+int ddb_mci_cmd(struct mci *state, struct mci_command *command,
+		struct mci_result *result);
+int ddb_mci_config(struct mci *state, u32 config);
+
 struct dvb_frontend
-*ddb_mci_attach(struct ddb_input *input,
-		int mci_type, int nr,
+*ddb_mci_attach(struct ddb_input *input, struct mci_cfg *cfg, int nr,
 		int (**fn_set_input)(struct dvb_frontend *fe, int input));
 
 #endif /* _DDBRIDGE_MCI_H_ */
diff --git a/drivers/media/pci/ddbridge/ddbridge-regs.h b/drivers/media/pci/ddbridge/ddbridge-regs.h
index b978b5991940..f9e1cbb99b53 100644
--- a/drivers/media/pci/ddbridge/ddbridge-regs.h
+++ b/drivers/media/pci/ddbridge/ddbridge-regs.h
@@ -34,14 +34,6 @@
 #define GPIO_DIRECTION   0x28
 
 /* ------------------------------------------------------------------------- */
-/* MDIO */
-
-#define MDIO_CTRL        0x20
-#define MDIO_ADR         0x24
-#define MDIO_REG         0x28
-#define MDIO_VAL         0x2C
-
-/* ------------------------------------------------------------------------- */
 
 #define BOARD_CONTROL    0x30
 
diff --git a/drivers/media/pci/ddbridge/ddbridge-sx8.c b/drivers/media/pci/ddbridge/ddbridge-sx8.c
new file mode 100644
index 000000000000..64f05f5ee039
--- /dev/null
+++ b/drivers/media/pci/ddbridge/ddbridge-sx8.c
@@ -0,0 +1,488 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ddbridge-sx8.c: Digital Devices MAX SX8 driver
+ *
+ * Copyright (C) 2018 Digital Devices GmbH
+ *                    Marcus Metzler <mocm@metzlerbros.de>
+ *                    Ralph Metzler <rjkm@metzlerbros.de>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 only, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include "ddbridge.h"
+#include "ddbridge-io.h"
+#include "ddbridge-mci.h"
+
+static const u32 MCLK = (1550000000 / 12);
+static const u32 MAX_LDPC_BITRATE = (720000000);
+static const u32 MAX_DEMOD_LDPC_BITRATE = (1550000000 / 6);
+
+#define SX8_TUNER_NUM 4
+#define SX8_DEMOD_NUM 8
+#define SX8_DEMOD_NONE 0xff
+
+struct sx8_base {
+	struct mci_base      mci_base;
+
+	u8                   tuner_use_count[SX8_TUNER_NUM];
+	u32                  gain_mode[SX8_TUNER_NUM];
+
+	u32                  used_ldpc_bitrate[SX8_DEMOD_NUM];
+	u8                   demod_in_use[SX8_DEMOD_NUM];
+	u32                  iq_mode;
+	u32                  burst_size;
+	u32                  direct_mode;
+};
+
+struct sx8 {
+	struct mci           mci;
+
+	int                  first_time_lock;
+	int                  started;
+	struct mci_result    signal_info;
+
+	u32                  bb_mode;
+	u32                  local_frequency;
+};
+
+static void release(struct dvb_frontend *fe)
+{
+	struct sx8 *state = fe->demodulator_priv;
+	struct mci_base *mci_base = state->mci.base;
+
+	mci_base->count--;
+	if (mci_base->count == 0) {
+		list_del(&mci_base->mci_list);
+		kfree(mci_base);
+	}
+	kfree(state);
+}
+
+static int get_info(struct dvb_frontend *fe)
+{
+	int stat;
+	struct sx8 *state = fe->demodulator_priv;
+	struct mci_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.command = MCI_CMD_GETSIGNALINFO;
+	cmd.demod = state->mci.demod;
+	stat = ddb_mci_cmd(&state->mci, &cmd, &state->signal_info);
+	return stat;
+}
+
+static int get_snr(struct dvb_frontend *fe)
+{
+	struct sx8 *state = fe->demodulator_priv;
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+
+	p->cnr.len = 1;
+	p->cnr.stat[0].scale = FE_SCALE_DECIBEL;
+	p->cnr.stat[0].svalue =
+		(s64)state->signal_info.dvbs2_signal_info.signal_to_noise
+		     * 10;
+	return 0;
+}
+
+static int get_strength(struct dvb_frontend *fe)
+{
+	struct sx8 *state = fe->demodulator_priv;
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+	s32 str;
+
+	str = 100000 -
+	      (state->signal_info.dvbs2_signal_info.channel_power
+	       * 10 + 108750);
+	p->strength.len = 1;
+	p->strength.stat[0].scale = FE_SCALE_DECIBEL;
+	p->strength.stat[0].svalue = str;
+	return 0;
+}
+
+static int read_status(struct dvb_frontend *fe, enum fe_status *status)
+{
+	int stat;
+	struct sx8 *state = fe->demodulator_priv;
+	struct mci_command cmd;
+	struct mci_result res;
+
+	cmd.command = MCI_CMD_GETSTATUS;
+	cmd.demod = state->mci.demod;
+	stat = ddb_mci_cmd(&state->mci, &cmd, &res);
+	if (stat)
+		return stat;
+	*status = 0x00;
+	get_info(fe);
+	get_strength(fe);
+	if (res.status == SX8_DEMOD_WAIT_MATYPE)
+		*status = 0x0f;
+	if (res.status == SX8_DEMOD_LOCKED) {
+		*status = 0x1f;
+		get_snr(fe);
+	}
+	return stat;
+}
+
+static int mci_set_tuner(struct dvb_frontend *fe, u32 tuner, u32 on)
+{
+	struct sx8 *state = fe->demodulator_priv;
+	struct mci_base *mci_base = state->mci.base;
+	struct sx8_base *sx8_base = (struct sx8_base *)mci_base;
+	struct mci_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.tuner = state->mci.tuner;
+	cmd.command = on ? SX8_CMD_INPUT_ENABLE : SX8_CMD_INPUT_DISABLE;
+	cmd.sx8_input_enable.flags = sx8_base->gain_mode[state->mci.tuner];
+	return ddb_mci_cmd(&state->mci, &cmd, NULL);
+}
+
+static int stop(struct dvb_frontend *fe)
+{
+	struct sx8 *state = fe->demodulator_priv;
+	struct mci_base *mci_base = state->mci.base;
+	struct sx8_base *sx8_base = (struct sx8_base *)mci_base;
+	struct mci_command cmd;
+	u32 input = state->mci.tuner;
+
+	memset(&cmd, 0, sizeof(cmd));
+	if (state->mci.demod != SX8_DEMOD_NONE) {
+		cmd.command = MCI_CMD_STOP;
+		cmd.demod = state->mci.demod;
+		ddb_mci_cmd(&state->mci, &cmd, NULL);
+		if (sx8_base->iq_mode) {
+			cmd.command = SX8_CMD_DISABLE_IQOUTPUT;
+			cmd.demod = state->mci.demod;
+			cmd.output = 0;
+			ddb_mci_cmd(&state->mci, &cmd, NULL);
+			ddb_mci_config(&state->mci, SX8_TSCONFIG_MODE_NORMAL);
+		}
+	}
+	mutex_lock(&mci_base->tuner_lock);
+	sx8_base->tuner_use_count[input]--;
+	if (!sx8_base->tuner_use_count[input])
+		mci_set_tuner(fe, input, 0);
+	if (state->mci.demod < SX8_DEMOD_NUM) {
+		sx8_base->demod_in_use[state->mci.demod] = 0;
+		state->mci.demod = SX8_DEMOD_NONE;
+	}
+	sx8_base->used_ldpc_bitrate[state->mci.nr] = 0;
+	sx8_base->iq_mode = 0;
+	mutex_unlock(&mci_base->tuner_lock);
+	state->started = 0;
+	return 0;
+}
+
+static int start(struct dvb_frontend *fe, u32 flags, u32 modmask, u32 ts_config)
+{
+	struct sx8 *state = fe->demodulator_priv;
+	struct mci_base *mci_base = state->mci.base;
+	struct sx8_base *sx8_base = (struct sx8_base *)mci_base;
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+	u32 used_ldpc_bitrate = 0, free_ldpc_bitrate;
+	u32 used_demods = 0;
+	struct mci_command cmd;
+	u32 input = state->mci.tuner;
+	u32 bits_per_symbol = 0;
+	int i = -1, stat = 0;
+
+	if (p->symbol_rate >= (MCLK / 2))
+		flags &= ~1;
+	if ((flags & 3) == 0)
+		return -EINVAL;
+
+	if (flags & 2) {
+		u32 tmp = modmask;
+
+		bits_per_symbol = 1;
+		while (tmp & 1) {
+			tmp >>= 1;
+			bits_per_symbol++;
+		}
+	}
+
+	mutex_lock(&mci_base->tuner_lock);
+	if (sx8_base->iq_mode) {
+		stat = -EBUSY;
+		goto unlock;
+	}
+
+	if (sx8_base->direct_mode) {
+		if (p->symbol_rate >= MCLK / 2) {
+			if (state->mci.nr < 4)
+				i = state->mci.nr;
+		} else {
+			i = state->mci.nr;
+		}
+	} else {
+		for (i = 0; i < SX8_DEMOD_NUM; i++) {
+			used_ldpc_bitrate += sx8_base->used_ldpc_bitrate[i];
+			if (sx8_base->demod_in_use[i])
+				used_demods++;
+		}
+		if (used_ldpc_bitrate >= MAX_LDPC_BITRATE ||
+		    ((ts_config & SX8_TSCONFIG_MODE_MASK) >
+		     SX8_TSCONFIG_MODE_NORMAL && used_demods > 0)) {
+			stat = -EBUSY;
+			goto unlock;
+		}
+		free_ldpc_bitrate = MAX_LDPC_BITRATE - used_ldpc_bitrate;
+		if (free_ldpc_bitrate > MAX_DEMOD_LDPC_BITRATE)
+			free_ldpc_bitrate = MAX_DEMOD_LDPC_BITRATE;
+
+		while (p->symbol_rate * bits_per_symbol > free_ldpc_bitrate)
+			bits_per_symbol--;
+		if (bits_per_symbol < 2) {
+			stat = -EBUSY;
+			goto unlock;
+		}
+
+		modmask &= ((1 << (bits_per_symbol - 1)) - 1);
+		if (((flags & 0x02) != 0) && modmask == 0) {
+			stat = -EBUSY;
+			goto unlock;
+		}
+
+		i = (p->symbol_rate > (MCLK / 2)) ? 3 : 7;
+		while (i >= 0 && sx8_base->demod_in_use[i])
+			i--;
+	}
+
+	if (i < 0) {
+		stat = -EBUSY;
+		goto unlock;
+	}
+	sx8_base->demod_in_use[i] = 1;
+	sx8_base->used_ldpc_bitrate[state->mci.nr] = p->symbol_rate
+						     * bits_per_symbol;
+	state->mci.demod = i;
+
+	if (!sx8_base->tuner_use_count[input])
+		mci_set_tuner(fe, input, 1);
+	sx8_base->tuner_use_count[input]++;
+	sx8_base->iq_mode = (ts_config > 1);
+unlock:
+	mutex_unlock(&mci_base->tuner_lock);
+	if (stat)
+		return stat;
+	memset(&cmd, 0, sizeof(cmd));
+
+	if (sx8_base->iq_mode) {
+		cmd.command = SX8_CMD_ENABLE_IQOUTPUT;
+		cmd.demod = state->mci.demod;
+		cmd.output = 0;
+		ddb_mci_cmd(&state->mci, &cmd, NULL);
+		ddb_mci_config(&state->mci, ts_config);
+	}
+	if (p->stream_id != NO_STREAM_ID_FILTER && p->stream_id != 0x80000000)
+		flags |= 0x80;
+	dev_dbg(mci_base->dev, "MCI-%d: tuner=%d demod=%d\n",
+		state->mci.nr, state->mci.tuner, state->mci.demod);
+	cmd.command = MCI_CMD_SEARCH_DVBS;
+	cmd.dvbs2_search.flags = flags;
+	cmd.dvbs2_search.s2_modulation_mask = modmask;
+	cmd.dvbs2_search.retry = 2;
+	cmd.dvbs2_search.frequency = p->frequency * 1000;
+	cmd.dvbs2_search.symbol_rate = p->symbol_rate;
+	cmd.dvbs2_search.scrambling_sequence_index =
+		p->scrambling_sequence_index | 0x80000000;
+	cmd.dvbs2_search.input_stream_id =
+		(p->stream_id != NO_STREAM_ID_FILTER) ? p->stream_id : 0;
+	cmd.tuner = state->mci.tuner;
+	cmd.demod = state->mci.demod;
+	cmd.output = state->mci.nr;
+	if (p->stream_id == 0x80000000)
+		cmd.output |= 0x80;
+	stat = ddb_mci_cmd(&state->mci, &cmd, NULL);
+	if (stat)
+		stop(fe);
+	return stat;
+}
+
+static int start_iq(struct dvb_frontend *fe, u32 flags, u32 roll_off,
+		    u32 ts_config)
+{
+	struct sx8 *state = fe->demodulator_priv;
+	struct mci_base *mci_base = state->mci.base;
+	struct sx8_base *sx8_base = (struct sx8_base *)mci_base;
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+	u32 used_demods = 0;
+	struct mci_command cmd;
+	u32 input = state->mci.tuner;
+	int i, stat = 0;
+
+	mutex_lock(&mci_base->tuner_lock);
+	if (sx8_base->iq_mode) {
+		stat = -EBUSY;
+		goto unlock;
+	}
+	for (i = 0; i < SX8_DEMOD_NUM; i++)
+		if (sx8_base->demod_in_use[i])
+			used_demods++;
+	if (used_demods > 0) {
+		stat = -EBUSY;
+		goto unlock;
+	}
+	state->mci.demod = 0;
+	if (!sx8_base->tuner_use_count[input])
+		mci_set_tuner(fe, input, 1);
+	sx8_base->tuner_use_count[input]++;
+	sx8_base->iq_mode = (ts_config > 1);
+unlock:
+	mutex_unlock(&mci_base->tuner_lock);
+	if (stat)
+		return stat;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.command = SX8_CMD_START_IQ;
+	cmd.sx8_start_iq.flags = flags;
+	cmd.sx8_start_iq.roll_off = roll_off;
+	cmd.sx8_start_iq.frequency = p->frequency * 1000;
+	cmd.sx8_start_iq.symbol_rate = p->symbol_rate;
+	cmd.tuner = state->mci.tuner;
+	cmd.demod = state->mci.demod;
+	stat = ddb_mci_cmd(&state->mci, &cmd, NULL);
+	if (stat)
+		stop(fe);
+	ddb_mci_config(&state->mci, ts_config);
+	return stat;
+}
+
+static int set_parameters(struct dvb_frontend *fe)
+{
+	int stat = 0;
+	struct sx8 *state = fe->demodulator_priv;
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+	u32 ts_config = SX8_TSCONFIG_MODE_NORMAL, iq_mode = 0, isi;
+
+	if (state->started)
+		stop(fe);
+
+	isi = p->stream_id;
+	if (isi != NO_STREAM_ID_FILTER)
+		iq_mode = (isi & 0x30000000) >> 28;
+
+	if (iq_mode)
+		ts_config = (SX8_TSCONFIG_TSHEADER | SX8_TSCONFIG_MODE_IQ);
+	if (iq_mode < 3) {
+		u32 mask;
+
+		switch (p->modulation) {
+		/* uncomment whenever these modulations hit the DVB API
+		 *	case APSK_256:
+		 *		mask = 0x7f;
+		 *		break;
+		 *	case APSK_128:
+		 *		mask = 0x3f;
+		 *		break;
+		 *	case APSK_64:
+		 *		mask = 0x1f;
+		 *		break;
+		 */
+		case APSK_32:
+			mask = 0x0f;
+			break;
+		case APSK_16:
+			mask = 0x07;
+			break;
+		default:
+			mask = 0x03;
+			break;
+		}
+		stat = start(fe, 3, mask, ts_config);
+	} else {
+		u32 flags = (iq_mode == 2) ? 1 : 0;
+
+		stat = start_iq(fe, flags, 4, ts_config);
+	}
+	if (!stat) {
+		state->started = 1;
+		state->first_time_lock = 1;
+		state->signal_info.status = SX8_DEMOD_WAIT_SIGNAL;
+	}
+
+	return stat;
+}
+
+static int tune(struct dvb_frontend *fe, bool re_tune,
+		unsigned int mode_flags,
+		unsigned int *delay, enum fe_status *status)
+{
+	int r;
+
+	if (re_tune) {
+		r = set_parameters(fe);
+		if (r)
+			return r;
+	}
+	r = read_status(fe, status);
+	if (r)
+		return r;
+
+	if (*status & FE_HAS_LOCK)
+		return 0;
+	*delay = HZ / 10;
+	return 0;
+}
+
+static enum dvbfe_algo get_algo(struct dvb_frontend *fe)
+{
+	return DVBFE_ALGO_HW;
+}
+
+static int set_input(struct dvb_frontend *fe, int input)
+{
+	struct sx8 *state = fe->demodulator_priv;
+	struct mci_base *mci_base = state->mci.base;
+
+	if (input >= SX8_TUNER_NUM)
+		return -EINVAL;
+
+	state->mci.tuner = input;
+	dev_dbg(mci_base->dev, "MCI-%d: input=%d\n", state->mci.nr, input);
+	return 0;
+}
+
+static struct dvb_frontend_ops sx8_ops = {
+	.delsys = { SYS_DVBS, SYS_DVBS2 },
+	.info = {
+		.name			= "Digital Devices MaxSX8 MCI DVB-S/S2/S2X",
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
+		.symbol_rate_min	= 100000,
+		.symbol_rate_max	= 100000000,
+		.caps			= FE_CAN_INVERSION_AUTO |
+					  FE_CAN_FEC_AUTO       |
+					  FE_CAN_QPSK           |
+					  FE_CAN_2G_MODULATION  |
+					  FE_CAN_MULTISTREAM,
+	},
+	.get_frontend_algo		= get_algo,
+	.tune				= tune,
+	.release			= release,
+	.read_status			= read_status,
+};
+
+static int init(struct mci *mci)
+{
+	struct sx8 *state = (struct sx8 *)mci;
+
+	state->mci.demod = SX8_DEMOD_NONE;
+	return 0;
+}
+
+const struct mci_cfg ddb_max_sx8_cfg = {
+	.type = 0,
+	.fe_ops = &sx8_ops,
+	.base_size = sizeof(struct sx8_base),
+	.state_size = sizeof(struct sx8),
+	.init = init,
+	.set_input = set_input,
+};
diff --git a/drivers/media/pci/ddbridge/ddbridge.h b/drivers/media/pci/ddbridge/ddbridge.h
index a66b1125cc74..8a354dfb6c22 100644
--- a/drivers/media/pci/ddbridge/ddbridge.h
+++ b/drivers/media/pci/ddbridge/ddbridge.h
@@ -120,21 +120,23 @@ struct ddb_info {
 #define DDB_OCTOPUS_MCI     9
 	char *name;
 	u32   i2c_mask;
+	u32   board_control;
+	u32   board_control_2;
+
 	u8    port_num;
 	u8    led_num;
 	u8    fan_num;
 	u8    temp_num;
 	u8    temp_bus;
-	u32   board_control;
-	u32   board_control_2;
-	u8    mdio_num;
 	u8    con_clock; /* use a continuous clock */
 	u8    ts_quirks;
 #define TS_QUIRK_SERIAL   1
 #define TS_QUIRK_REVERSED 2
 #define TS_QUIRK_ALT_OSC  8
+	u8    mci_ports;
+	u8    mci_type;
+
 	u32   tempmon_irq;
-	u8    mci;
 	const struct ddb_regmap *regmap;
 };
 
@@ -255,7 +257,6 @@ struct ddb_port {
 #define DDB_CI_EXTERNAL_XO2_B    13
 #define DDB_TUNER_DVBS_STV0910_PR 14
 #define DDB_TUNER_DVBC2T2I_SONY_P 15
-#define DDB_TUNER_MCI            16
 
 #define DDB_TUNER_XO2            32
 #define DDB_TUNER_DVBS_STV0910   (DDB_TUNER_XO2 + 0)
@@ -265,6 +266,9 @@ struct ddb_port {
 #define DDB_TUNER_ATSC_ST        (DDB_TUNER_XO2 + 4)
 #define DDB_TUNER_DVBC2T2I_SONY  (DDB_TUNER_XO2 + 5)
 
+#define DDB_TUNER_MCI            48
+#define DDB_TUNER_MCI_SX8        (DDB_TUNER_MCI + 0)
+
 	struct ddb_input      *input[2];
 	struct ddb_output     *output;
 	struct dvb_ca_en50221 *en;
diff --git a/drivers/media/pci/dm1105/dm1105.c b/drivers/media/pci/dm1105/dm1105.c
index c9db108751a7..1ddb0576fb7b 100644
--- a/drivers/media/pci/dm1105/dm1105.c
+++ b/drivers/media/pci/dm1105/dm1105.c
@@ -986,6 +986,9 @@ static int dm1105_probe(struct pci_dev *pdev,
 	int ret = -ENOMEM;
 	int i;
 
+	if (dm1105_devcount >= ARRAY_SIZE(card))
+		return -ENODEV;
+
 	dev = kzalloc(sizeof(struct dm1105_dev), GFP_KERNEL);
 	if (!dev)
 		return -ENOMEM;
diff --git a/drivers/media/pci/ivtv/ivtv-driver.c b/drivers/media/pci/ivtv/ivtv-driver.c
index 6b2ffdc96961..dd727098daf4 100644
--- a/drivers/media/pci/ivtv/ivtv-driver.c
+++ b/drivers/media/pci/ivtv/ivtv-driver.c
@@ -999,7 +999,7 @@ static int ivtv_probe(struct pci_dev *pdev, const struct pci_device_id *pci_id)
 	int vbi_buf_size;
 	struct ivtv *itv;
 
-	itv = kzalloc(sizeof(struct ivtv), GFP_ATOMIC);
+	itv = kzalloc(sizeof(struct ivtv), GFP_KERNEL);
 	if (itv == NULL)
 		return -ENOMEM;
 	itv->pdev = pdev;
diff --git a/drivers/media/pci/ivtv/ivtv-i2c.c b/drivers/media/pci/ivtv/ivtv-i2c.c
index 522cd111e399..e9ce54dd5e01 100644
--- a/drivers/media/pci/ivtv/ivtv-i2c.c
+++ b/drivers/media/pci/ivtv/ivtv-i2c.c
@@ -293,6 +293,7 @@ int ivtv_i2c_register(struct ivtv *itv, unsigned idx)
 			.platform_data = &pdata,
 		};
 
+		memset(&pdata, 0, sizeof(pdata));
 		pdata.pvr150_workaround = itv->pvr150_workaround;
 		sd = v4l2_i2c_new_subdev_board(&itv->v4l2_dev, adap,
 				&cx25840_info, NULL);
diff --git a/drivers/media/pci/ivtv/ivtvfb.c b/drivers/media/pci/ivtv/ivtvfb.c
index b19058e36853..5ddaa8ed11a5 100644
--- a/drivers/media/pci/ivtv/ivtvfb.c
+++ b/drivers/media/pci/ivtv/ivtvfb.c
@@ -1178,7 +1178,7 @@ static int ivtvfb_init_card(struct ivtv *itv)
 	}
 
 	itv->osd_info = kzalloc(sizeof(struct osd_info),
-					GFP_ATOMIC|__GFP_NOWARN);
+					GFP_KERNEL|__GFP_NOWARN);
 	if (itv->osd_info == NULL) {
 		IVTVFB_ERR("Failed to allocate memory for osd_info\n");
 		return -ENOMEM;
diff --git a/drivers/media/pci/mantis/mantis_vp3030.c b/drivers/media/pci/mantis/mantis_vp3030.c
index 14f6e153000c..9797c9fd8259 100644
--- a/drivers/media/pci/mantis/mantis_vp3030.c
+++ b/drivers/media/pci/mantis/mantis_vp3030.c
@@ -42,8 +42,8 @@ static struct zl10353_config mantis_vp3030_config = {
 static struct tda665x_config env57h12d5_config = {
 	.name			= "ENV57H12D5 (ET-50DT)",
 	.addr			= 0x60,
-	.frequency_min		=  47000000,
-	.frequency_max		= 862000000,
+	.frequency_min		=  47 * MHz,
+	.frequency_max		= 862 * MHz,
 	.frequency_offst	=   3616667,
 	.ref_multiplier		= 6, /* 1/6 MHz */
 	.ref_divider		= 100000, /* 1/6 MHz */
diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c b/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c
index b13e319d24b7..5f1613aec93c 100644
--- a/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c
+++ b/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c
@@ -214,11 +214,6 @@ static int netup_i2c_xfer(struct i2c_adapter *adap,
 	struct netup_i2c *i2c = i2c_get_adapdata(adap);
 	u16 reg;
 
-	if (num <= 0) {
-		dev_dbg(i2c->adap.dev.parent,
-			"%s(): num == %d\n", __func__, num);
-		return -EINVAL;
-	}
 	spin_lock_irqsave(&i2c->lock, flags);
 	if (i2c->state != STATE_DONE) {
 		dev_dbg(i2c->adap.dev.parent,
diff --git a/drivers/media/pci/pt1/pt1.c b/drivers/media/pci/pt1/pt1.c
index fda969a85684..7f878fc41b7e 100644
--- a/drivers/media/pci/pt1/pt1.c
+++ b/drivers/media/pci/pt1/pt1.c
@@ -1443,9 +1443,7 @@ static struct pci_driver pt1_driver = {
 	.probe		= pt1_probe,
 	.remove		= pt1_remove,
 	.id_table	= pt1_id_table,
-#ifdef CONFIG_PM_SLEEP
 	.driver.pm	= &pt1_pm_ops,
-#endif
 };
 
 module_pci_driver(pt1_driver);
diff --git a/drivers/media/pci/saa7164/saa7164-vbi.c b/drivers/media/pci/saa7164/saa7164-vbi.c
index 64ab91c24c18..221de91a8bae 100644
--- a/drivers/media/pci/saa7164/saa7164-vbi.c
+++ b/drivers/media/pci/saa7164/saa7164-vbi.c
@@ -629,12 +629,12 @@ static __poll_t fops_poll(struct file *file, poll_table *wait)
 		port->last_poll_msecs_diff);
 
 	if (!video_is_registered(port->v4l_device))
-		return -EIO;
+		return EPOLLERR;
 
 	if (atomic_cmpxchg(&fh->v4l_reading, 0, 1) == 0) {
 		if (atomic_inc_return(&port->v4l_reader_count) == 1) {
 			if (saa7164_vbi_initialize(port) < 0)
-				return -EINVAL;
+				return EPOLLERR;
 			saa7164_vbi_start_streaming(port);
 			msleep(200);
 		}
@@ -644,7 +644,7 @@ static __poll_t fops_poll(struct file *file, poll_table *wait)
 	if ((file->f_flags & O_NONBLOCK) == 0) {
 		if (wait_event_interruptible(port->wait_read,
 			saa7164_vbi_next_buf(port))) {
-				return -ERESTARTSYS;
+				return EPOLLERR;
 		}
 	}
 
diff --git a/drivers/media/pci/sta2x11/sta2x11_vip.c b/drivers/media/pci/sta2x11/sta2x11_vip.c
index 069c4a853346..1858efedaf1a 100644
--- a/drivers/media/pci/sta2x11/sta2x11_vip.c
+++ b/drivers/media/pci/sta2x11/sta2x11_vip.c
@@ -116,6 +116,7 @@ static inline struct vip_buffer *to_vip_buffer(struct vb2_v4l2_buffer *vb2)
  * @sequence: sequence number of acquired buffer
  * @active: current active buffer
  * @lock: used in videobuf2 callback
+ * @v4l_lock: serialize its video4linux ioctls
  * @tcount: Number of top frames
  * @bcount: Number of bottom frames
  * @overflow: Number of FIFO overflows
@@ -145,6 +146,7 @@ struct sta2x11_vip {
 	unsigned int sequence;
 	struct vip_buffer *active; /* current active buffer */
 	spinlock_t lock; /* Used in videobuf2 callback */
+	struct mutex v4l_lock;
 
 	/* Interrupt counters */
 	int tcount, bcount;
@@ -385,6 +387,8 @@ static const struct vb2_ops vip_video_qops = {
 	.buf_queue		= buffer_queue,
 	.start_streaming	= start_streaming,
 	.stop_streaming		= stop_streaming,
+	.wait_prepare		= vb2_ops_wait_prepare,
+	.wait_finish		= vb2_ops_wait_finish,
 };
 
 
@@ -870,6 +874,7 @@ static int sta2x11_vip_init_buffer(struct sta2x11_vip *vip)
 	vip->vb_vidq.mem_ops = &vb2_dma_contig_memops;
 	vip->vb_vidq.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	vip->vb_vidq.dev = &vip->pdev->dev;
+	vip->vb_vidq.lock = &vip->v4l_lock;
 	err = vb2_queue_init(&vip->vb_vidq);
 	if (err)
 		return err;
@@ -1034,6 +1039,7 @@ static int sta2x11_vip_init_one(struct pci_dev *pdev,
 	vip->std = V4L2_STD_PAL;
 	vip->format = formats_50[0];
 	vip->config = config;
+	mutex_init(&vip->v4l_lock);
 
 	ret = sta2x11_vip_init_controls(vip);
 	if (ret)
@@ -1080,6 +1086,7 @@ static int sta2x11_vip_init_one(struct pci_dev *pdev,
 	vip->video_dev = video_dev_template;
 	vip->video_dev.v4l2_dev = &vip->v4l2_dev;
 	vip->video_dev.queue = &vip->vb_vidq;
+	vip->video_dev.lock = &vip->v4l_lock;
 	video_set_drvdata(&vip->video_dev, vip);
 
 	ret = video_register_device(&vip->video_dev, VFL_TYPE_GRABBER, -1);
diff --git a/drivers/media/pci/tw686x/tw686x-video.c b/drivers/media/pci/tw686x/tw686x-video.c
index 0ea8dd44026c..3a06c000f97b 100644
--- a/drivers/media/pci/tw686x/tw686x-video.c
+++ b/drivers/media/pci/tw686x/tw686x-video.c
@@ -1190,6 +1190,14 @@ int tw686x_video_init(struct tw686x_dev *dev)
 			return err;
 	}
 
+	/* Initialize vc->dev and vc->ch for the error path */
+	for (ch = 0; ch < max_channels(dev); ch++) {
+		struct tw686x_video_channel *vc = &dev->video_channels[ch];
+
+		vc->dev = dev;
+		vc->ch = ch;
+	}
+
 	for (ch = 0; ch < max_channels(dev); ch++) {
 		struct tw686x_video_channel *vc = &dev->video_channels[ch];
 		struct video_device *vdev;
@@ -1198,9 +1206,6 @@ int tw686x_video_init(struct tw686x_dev *dev)
 		spin_lock_init(&vc->qlock);
 		INIT_LIST_HEAD(&vc->vidq_queued);
 
-		vc->dev = dev;
-		vc->ch = ch;
-
 		/* default settings */
 		err = tw686x_set_standard(vc, V4L2_STD_NTSC);
 		if (err)
diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index 2728376b04b5..b25c8d3c1c31 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -90,7 +90,7 @@ config VIDEO_PXA27x
 	  This is a v4l2 driver for the PXA27x Quick Capture Interface
 
 config VIDEO_QCOM_CAMSS
-	tristate "Qualcomm 8x16 V4L2 Camera Subsystem driver"
+	tristate "Qualcomm V4L2 Camera Subsystem driver"
 	depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	depends on (ARCH_QCOM && IOMMU_DMA) || COMPILE_TEST
 	select VIDEOBUF2_DMA_SG
@@ -384,8 +384,8 @@ config VIDEO_SH_VEU
 config VIDEO_RENESAS_FDP1
 	tristate "Renesas Fine Display Processor"
 	depends on VIDEO_DEV && VIDEO_V4L2
-	depends on ARCH_SHMOBILE || COMPILE_TEST
-	depends on (!ARCH_RENESAS && !VIDEO_RENESAS_FCP) || VIDEO_RENESAS_FCP
+	depends on ARCH_RENESAS || COMPILE_TEST
+	depends on (!ARM64 && !VIDEO_RENESAS_FCP) || VIDEO_RENESAS_FCP
 	select VIDEOBUF2_DMA_CONTIG
 	select V4L2_MEM2MEM_DEV
 	---help---
@@ -514,6 +514,9 @@ config VIDEO_VIM2M
 	---help---
 	  This is a virtual test device for the memory-to-memory driver
 	  framework.
+
+source "drivers/media/platform/vicodec/Kconfig"
+
 endif #V4L_TEST_DRIVERS
 
 menuconfig DVB_PLATFORM_DRIVERS
diff --git a/drivers/media/platform/Makefile b/drivers/media/platform/Makefile
index 04bc1502a30e..08640ba87fc2 100644
--- a/drivers/media/platform/Makefile
+++ b/drivers/media/platform/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_VIDEO_VIU) += fsl-viu.o
 obj-$(CONFIG_VIDEO_VIMC)		+= vimc/
 obj-$(CONFIG_VIDEO_VIVID)		+= vivid/
 obj-$(CONFIG_VIDEO_VIM2M)		+= vim2m.o
+obj-$(CONFIG_VIDEO_VICODEC)		+= vicodec/
 
 obj-$(CONFIG_VIDEO_TI_VPE)		+= ti-vpe/
 
@@ -88,7 +89,7 @@ obj-$(CONFIG_VIDEO_MEDIATEK_MDP)	+= mtk-mdp/
 
 obj-$(CONFIG_VIDEO_MEDIATEK_JPEG)	+= mtk-jpeg/
 
-obj-$(CONFIG_VIDEO_QCOM_CAMSS)		+= qcom/camss-8x16/
+obj-$(CONFIG_VIDEO_QCOM_CAMSS)		+= qcom/camss/
 
 obj-$(CONFIG_VIDEO_QCOM_VENUS)		+= qcom/venus/
 
diff --git a/drivers/media/platform/atmel/atmel-isi.c b/drivers/media/platform/atmel/atmel-isi.c
index e5be21a31640..e8db4df1e7c4 100644
--- a/drivers/media/platform/atmel/atmel-isi.c
+++ b/drivers/media/platform/atmel/atmel-isi.c
@@ -1106,23 +1106,20 @@ static int isi_graph_parse(struct atmel_isi *isi, struct device_node *node)
 	struct device_node *ep = NULL;
 	struct device_node *remote;
 
-	while (1) {
-		ep = of_graph_get_next_endpoint(node, ep);
-		if (!ep)
-			return -EINVAL;
+	ep = of_graph_get_next_endpoint(node, ep);
+	if (!ep)
+		return -EINVAL;
 
-		remote = of_graph_get_remote_port_parent(ep);
-		if (!remote) {
-			of_node_put(ep);
-			return -EINVAL;
-		}
+	remote = of_graph_get_remote_port_parent(ep);
+	of_node_put(ep);
+	if (!remote)
+		return -EINVAL;
 
-		/* Remote node to connect */
-		isi->entity.node = remote;
-		isi->entity.asd.match_type = V4L2_ASYNC_MATCH_FWNODE;
-		isi->entity.asd.match.fwnode = of_fwnode_handle(remote);
-		return 0;
-	}
+	/* Remote node to connect */
+	isi->entity.node = remote;
+	isi->entity.asd.match_type = V4L2_ASYNC_MATCH_FWNODE;
+	isi->entity.asd.match.fwnode = of_fwnode_handle(remote);
+	return 0;
 }
 
 static int isi_graph_init(struct atmel_isi *isi)
diff --git a/drivers/media/platform/cadence/Kconfig b/drivers/media/platform/cadence/Kconfig
index 3bf0f2454384..cf6124da3c54 100644
--- a/drivers/media/platform/cadence/Kconfig
+++ b/drivers/media/platform/cadence/Kconfig
@@ -11,6 +11,7 @@ if VIDEO_CADENCE
 
 config VIDEO_CADENCE_CSI2RX
 	tristate "Cadence MIPI-CSI2 RX Controller"
+	depends on VIDEO_V4L2
 	depends on MEDIA_CONTROLLER
 	depends on VIDEO_V4L2_SUBDEV_API
 	select V4L2_FWNODE
@@ -22,6 +23,7 @@ config VIDEO_CADENCE_CSI2RX
 
 config VIDEO_CADENCE_CSI2TX
 	tristate "Cadence MIPI-CSI2 TX Controller"
+	depends on VIDEO_V4L2
 	depends on MEDIA_CONTROLLER
 	depends on VIDEO_V4L2_SUBDEV_API
 	select V4L2_FWNODE
diff --git a/drivers/media/platform/cadence/cdns-csi2rx.c b/drivers/media/platform/cadence/cdns-csi2rx.c
index a0f02916006b..43e43c7b3e98 100644
--- a/drivers/media/platform/cadence/cdns-csi2rx.c
+++ b/drivers/media/platform/cadence/cdns-csi2rx.c
@@ -13,6 +13,7 @@
 #include <linux/of_graph.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
+#include <linux/slab.h>
 
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/platform/cadence/cdns-csi2tx.c b/drivers/media/platform/cadence/cdns-csi2tx.c
index dfa1d88d955b..40d0de690ff4 100644
--- a/drivers/media/platform/cadence/cdns-csi2tx.c
+++ b/drivers/media/platform/cadence/cdns-csi2tx.c
@@ -13,6 +13,7 @@
 #include <linux/of.h>
 #include <linux/of_graph.h>
 #include <linux/platform_device.h>
+#include <linux/slab.h>
 
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/platform/cec-gpio/cec-gpio.c b/drivers/media/platform/cec-gpio/cec-gpio.c
index 69f8242209c2..d2861749d640 100644
--- a/drivers/media/platform/cec-gpio/cec-gpio.c
+++ b/drivers/media/platform/cec-gpio/cec-gpio.c
@@ -23,6 +23,11 @@ struct cec_gpio {
 	int			hpd_irq;
 	bool			hpd_is_high;
 	ktime_t			hpd_ts;
+
+	struct gpio_desc	*v5_gpio;
+	int			v5_irq;
+	bool			v5_is_high;
+	ktime_t			v5_ts;
 };
 
 static bool cec_gpio_read(struct cec_adapter *adap)
@@ -65,6 +70,26 @@ static irqreturn_t cec_hpd_gpio_irq_handler_thread(int irq, void *priv)
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t cec_5v_gpio_irq_handler(int irq, void *priv)
+{
+	struct cec_gpio *cec = priv;
+	bool is_high = gpiod_get_value(cec->v5_gpio);
+
+	if (is_high == cec->v5_is_high)
+		return IRQ_HANDLED;
+	cec->v5_ts = ktime_get();
+	cec->v5_is_high = is_high;
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t cec_5v_gpio_irq_handler_thread(int irq, void *priv)
+{
+	struct cec_gpio *cec = priv;
+
+	cec_queue_pin_5v_event(cec->adap, cec->v5_is_high, cec->v5_ts);
+	return IRQ_HANDLED;
+}
+
 static irqreturn_t cec_hpd_gpio_irq_handler(int irq, void *priv)
 {
 	struct cec_gpio *cec = priv;
@@ -119,6 +144,9 @@ static void cec_gpio_status(struct cec_adapter *adap, struct seq_file *file)
 	if (cec->hpd_gpio)
 		seq_printf(file, "hpd: %s\n",
 			   cec->hpd_is_high ? "high" : "low");
+	if (cec->v5_gpio)
+		seq_printf(file, "5V: %s\n",
+			   cec->v5_is_high ? "high" : "low");
 }
 
 static int cec_gpio_read_hpd(struct cec_adapter *adap)
@@ -130,6 +158,15 @@ static int cec_gpio_read_hpd(struct cec_adapter *adap)
 	return gpiod_get_value(cec->hpd_gpio);
 }
 
+static int cec_gpio_read_5v(struct cec_adapter *adap)
+{
+	struct cec_gpio *cec = cec_get_drvdata(adap);
+
+	if (!cec->v5_gpio)
+		return -ENOTTY;
+	return gpiod_get_value(cec->v5_gpio);
+}
+
 static void cec_gpio_free(struct cec_adapter *adap)
 {
 	cec_gpio_disable_irq(adap);
@@ -144,6 +181,7 @@ static const struct cec_pin_ops cec_gpio_pin_ops = {
 	.status = cec_gpio_status,
 	.free = cec_gpio_free,
 	.read_hpd = cec_gpio_read_hpd,
+	.read_5v = cec_gpio_read_5v,
 };
 
 static int cec_gpio_probe(struct platform_device *pdev)
@@ -167,6 +205,10 @@ static int cec_gpio_probe(struct platform_device *pdev)
 	if (IS_ERR(cec->hpd_gpio))
 		return PTR_ERR(cec->hpd_gpio);
 
+	cec->v5_gpio = devm_gpiod_get_optional(dev, "v5", GPIOD_IN);
+	if (IS_ERR(cec->v5_gpio))
+		return PTR_ERR(cec->v5_gpio);
+
 	cec->adap = cec_pin_allocate_adapter(&cec_gpio_pin_ops,
 		cec, pdev->name, CEC_CAP_DEFAULTS | CEC_CAP_PHYS_ADDR |
 				 CEC_CAP_MONITOR_ALL | CEC_CAP_MONITOR_PIN);
@@ -185,6 +227,18 @@ static int cec_gpio_probe(struct platform_device *pdev)
 			return ret;
 	}
 
+	if (cec->v5_gpio) {
+		cec->v5_irq = gpiod_to_irq(cec->v5_gpio);
+		ret = devm_request_threaded_irq(dev, cec->v5_irq,
+			cec_5v_gpio_irq_handler,
+			cec_5v_gpio_irq_handler_thread,
+			IRQF_ONESHOT |
+			IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING,
+			"v5-gpio", cec);
+		if (ret)
+			return ret;
+	}
+
 	ret = cec_register_adapter(cec->adap, &pdev->dev);
 	if (ret) {
 		cec_delete_adapter(cec->adap);
diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
index 68ed2a564ad1..d26c2d85a009 100644
--- a/drivers/media/platform/coda/coda-bit.c
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -261,11 +261,12 @@ void coda_fill_bitstream(struct coda_ctx *ctx, struct list_head *buffer_list)
 
 	while (v4l2_m2m_num_src_bufs_ready(ctx->fh.m2m_ctx) > 0) {
 		/*
-		 * Only queue a single JPEG into the bitstream buffer, except
-		 * to increase payload over 512 bytes or if in hold state.
+		 * Only queue two JPEGs into the bitstream buffer to keep
+		 * latency low. We need at least one complete buffer and the
+		 * header of another buffer (for prescan) in the bitstream.
 		 */
 		if (ctx->codec->src_fourcc == V4L2_PIX_FMT_JPEG &&
-		    (coda_get_bitstream_payload(ctx) >= 512) && !ctx->hold)
+		    ctx->num_metas > 1)
 			break;
 
 		src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
@@ -389,32 +390,29 @@ static int coda_alloc_framebuffers(struct coda_ctx *ctx,
 				   struct coda_q_data *q_data, u32 fourcc)
 {
 	struct coda_dev *dev = ctx->dev;
-	int width, height;
-	int ysize;
+	unsigned int ysize, ycbcr_size;
 	int ret;
 	int i;
 
 	if (ctx->codec->src_fourcc == V4L2_PIX_FMT_H264 ||
 	    ctx->codec->dst_fourcc == V4L2_PIX_FMT_H264 ||
 	    ctx->codec->src_fourcc == V4L2_PIX_FMT_MPEG4 ||
-	    ctx->codec->dst_fourcc == V4L2_PIX_FMT_MPEG4) {
-		width = round_up(q_data->width, 16);
-		height = round_up(q_data->height, 16);
-	} else {
-		width = round_up(q_data->width, 8);
-		height = q_data->height;
-	}
-	ysize = width * height;
+	    ctx->codec->dst_fourcc == V4L2_PIX_FMT_MPEG4)
+		ysize = round_up(q_data->rect.width, 16) *
+			round_up(q_data->rect.height, 16);
+	else
+		ysize = round_up(q_data->rect.width, 8) * q_data->rect.height;
+
+	if (ctx->tiled_map_type == GDI_TILED_FRAME_MB_RASTER_MAP)
+		ycbcr_size = round_up(ysize, 4096) + ysize / 2;
+	else
+		ycbcr_size = ysize + ysize / 2;
 
 	/* Allocate frame buffers */
 	for (i = 0; i < ctx->num_internal_frames; i++) {
-		size_t size;
+		size_t size = ycbcr_size;
 		char *name;
 
-		if (ctx->tiled_map_type == GDI_TILED_FRAME_MB_RASTER_MAP)
-			size = round_up(ysize, 4096) + ysize / 2;
-		else
-			size = ysize + ysize / 2;
 		/* Add space for mvcol buffers */
 		if (dev->devtype->product != CODA_DX6 &&
 		    (ctx->codec->src_fourcc == V4L2_PIX_FMT_H264 ||
@@ -499,8 +497,8 @@ static int coda_alloc_context_buffers(struct coda_ctx *ctx,
 
 	if (!ctx->slicebuf.vaddr && q_data->fourcc == V4L2_PIX_FMT_H264) {
 		/* worst case slice size */
-		size = (DIV_ROUND_UP(q_data->width, 16) *
-			DIV_ROUND_UP(q_data->height, 16)) * 3200 / 8 + 512;
+		size = (DIV_ROUND_UP(q_data->rect.width, 16) *
+			DIV_ROUND_UP(q_data->rect.height, 16)) * 3200 / 8 + 512;
 		ret = coda_alloc_context_buf(ctx, &ctx->slicebuf, size,
 					     "slicebuf");
 		if (ret < 0)
@@ -538,6 +536,8 @@ static int coda_encode_header(struct coda_ctx *ctx, struct vb2_v4l2_buffer *buf,
 {
 	struct vb2_buffer *vb = &buf->vb2_buf;
 	struct coda_dev *dev = ctx->dev;
+	struct coda_q_data *q_data_src;
+	struct v4l2_rect *r;
 	size_t bufsize;
 	int ret;
 	int i;
@@ -551,6 +551,23 @@ static int coda_encode_header(struct coda_ctx *ctx, struct vb2_v4l2_buffer *buf,
 	if (dev->devtype->product == CODA_960)
 		bufsize /= 1024;
 	coda_write(dev, bufsize, CODA_CMD_ENC_HEADER_BB_SIZE);
+	if (dev->devtype->product == CODA_960 &&
+	    ctx->codec->dst_fourcc == V4L2_PIX_FMT_H264 &&
+	    header_code == CODA_HEADER_H264_SPS) {
+		q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
+		r = &q_data_src->rect;
+
+		if (r->width % 16 || r->height % 16) {
+			u32 crop_right = round_up(r->width, 16) -  r->width;
+			u32 crop_bottom = round_up(r->height, 16) - r->height;
+
+			coda_write(dev, crop_right,
+				   CODA9_CMD_ENC_HEADER_FRAME_CROP_H);
+			coda_write(dev, crop_bottom,
+				   CODA9_CMD_ENC_HEADER_FRAME_CROP_V);
+			header_code |= CODA9_HEADER_FRAME_CROP;
+		}
+	}
 	coda_write(dev, header_code, CODA_CMD_ENC_HEADER_CODE);
 	ret = coda_command_sync(ctx, CODA_COMMAND_ENCODE_HEADER);
 	if (ret < 0) {
@@ -632,7 +649,7 @@ static void coda_setup_iram(struct coda_ctx *ctx)
 		struct coda_q_data *q_data_src;
 
 		q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
-		mb_width = DIV_ROUND_UP(q_data_src->width, 16);
+		mb_width = DIV_ROUND_UP(q_data_src->rect.width, 16);
 		w128 = mb_width * 128;
 		w64 = mb_width * 64;
 
@@ -721,6 +738,7 @@ static u32 coda_supported_firmwares[] = {
 	CODA_FIRMWARE_VERNUM(CODA_HX4, 1, 4, 50),
 	CODA_FIRMWARE_VERNUM(CODA_7541, 1, 4, 50),
 	CODA_FIRMWARE_VERNUM(CODA_960, 2, 1, 5),
+	CODA_FIRMWARE_VERNUM(CODA_960, 2, 1, 9),
 	CODA_FIRMWARE_VERNUM(CODA_960, 2, 3, 10),
 	CODA_FIRMWARE_VERNUM(CODA_960, 3, 1, 1),
 };
@@ -928,25 +946,25 @@ static int coda_start_encoding(struct coda_ctx *ctx)
 	value = 0;
 	switch (dev->devtype->product) {
 	case CODA_DX6:
-		value = (q_data_src->width & CODADX6_PICWIDTH_MASK)
+		value = (q_data_src->rect.width & CODADX6_PICWIDTH_MASK)
 			<< CODADX6_PICWIDTH_OFFSET;
-		value |= (q_data_src->height & CODADX6_PICHEIGHT_MASK)
+		value |= (q_data_src->rect.height & CODADX6_PICHEIGHT_MASK)
 			 << CODA_PICHEIGHT_OFFSET;
 		break;
 	case CODA_HX4:
 	case CODA_7541:
 		if (dst_fourcc == V4L2_PIX_FMT_H264) {
-			value = (round_up(q_data_src->width, 16) &
+			value = (round_up(q_data_src->rect.width, 16) &
 				 CODA7_PICWIDTH_MASK) << CODA7_PICWIDTH_OFFSET;
-			value |= (round_up(q_data_src->height, 16) &
+			value |= (round_up(q_data_src->rect.height, 16) &
 				 CODA7_PICHEIGHT_MASK) << CODA_PICHEIGHT_OFFSET;
 			break;
 		}
 		/* fallthrough */
 	case CODA_960:
-		value = (q_data_src->width & CODA7_PICWIDTH_MASK)
+		value = (q_data_src->rect.width & CODA7_PICWIDTH_MASK)
 			<< CODA7_PICWIDTH_OFFSET;
-		value |= (q_data_src->height & CODA7_PICHEIGHT_MASK)
+		value |= (q_data_src->rect.height & CODA7_PICHEIGHT_MASK)
 			 << CODA_PICHEIGHT_OFFSET;
 	}
 	coda_write(dev, value, CODA_CMD_ENC_SEQ_SRC_SIZE);
@@ -1198,6 +1216,27 @@ static int coda_start_encoding(struct coda_ctx *ctx)
 			goto out;
 
 		/*
+		 * If visible width or height are not aligned to macroblock
+		 * size, the crop_right and crop_bottom SPS fields must be set
+		 * to the difference between visible and coded size.  This is
+		 * only supported by CODA960 firmware. All others do not allow
+		 * writing frame cropping parameters, so we have to manually
+		 * fix up the SPS RBSP (Sequence Parameter Set Raw Byte
+		 * Sequence Payload) ourselves.
+		 */
+		if (ctx->dev->devtype->product != CODA_960 &&
+		    ((q_data_src->rect.width % 16) ||
+		     (q_data_src->rect.height % 16))) {
+			ret = coda_h264_sps_fixup(ctx, q_data_src->rect.width,
+						  q_data_src->rect.height,
+						  &ctx->vpu_header[0][0],
+						  &ctx->vpu_header_size[0],
+						  sizeof(ctx->vpu_header[0]));
+			if (ret < 0)
+				goto out;
+		}
+
+		/*
 		 * Get PPS in the first frame and copy it to an
 		 * intermediate buffer.
 		 */
@@ -1362,7 +1401,8 @@ static int coda_prepare_encode(struct coda_ctx *ctx)
 
 	if (dev->devtype->product == CODA_960) {
 		coda_write(dev, 4/*FIXME: 0*/, CODA9_CMD_ENC_PIC_SRC_INDEX);
-		coda_write(dev, q_data_src->width, CODA9_CMD_ENC_PIC_SRC_STRIDE);
+		coda_write(dev, q_data_src->bytesperline,
+			   CODA9_CMD_ENC_PIC_SRC_STRIDE);
 		coda_write(dev, 0, CODA9_CMD_ENC_PIC_SUB_FRAME_SYNC);
 
 		reg = CODA9_CMD_ENC_PIC_SRC_ADDR_Y;
@@ -1582,10 +1622,8 @@ static int coda_decoder_reqbufs(struct coda_ctx *ctx,
 
 static bool coda_reorder_enable(struct coda_ctx *ctx)
 {
-	const char * const *profile_names;
-	const char * const *level_names;
 	struct coda_dev *dev = ctx->dev;
-	int profile, level;
+	int profile;
 
 	if (dev->devtype->product != CODA_HX4 &&
 	    dev->devtype->product != CODA_7541 &&
@@ -1599,24 +1637,9 @@ static bool coda_reorder_enable(struct coda_ctx *ctx)
 		return true;
 
 	profile = coda_h264_profile(ctx->params.h264_profile_idc);
-	if (profile < 0) {
-		v4l2_warn(&dev->v4l2_dev, "Invalid H264 Profile: %d\n",
-			 ctx->params.h264_profile_idc);
-		return false;
-	}
-
-	level = coda_h264_level(ctx->params.h264_level_idc);
-	if (level < 0) {
-		v4l2_warn(&dev->v4l2_dev, "Invalid H264 Level: %d\n",
-			 ctx->params.h264_level_idc);
-		return false;
-	}
-
-	profile_names = v4l2_ctrl_get_menu(V4L2_CID_MPEG_VIDEO_H264_PROFILE);
-	level_names = v4l2_ctrl_get_menu(V4L2_CID_MPEG_VIDEO_H264_LEVEL);
-
-	v4l2_dbg(1, coda_debug, &dev->v4l2_dev, "H264 Profile/Level: %s L%s\n",
-		 profile_names[profile], level_names[level]);
+	if (profile < 0)
+		v4l2_warn(&dev->v4l2_dev, "Unknown H264 Profile: %u\n",
+			  ctx->params.h264_profile_idc);
 
 	/* Baseline profile does not support reordering */
 	return profile > V4L2_MPEG_VIDEO_H264_PROFILE_BASELINE;
@@ -1694,6 +1717,8 @@ static int __coda_start_decoding(struct coda_ctx *ctx)
 			coda_write(dev, 512, CODA_CMD_DEC_SEQ_SPP_CHUNK_SIZE);
 		}
 	}
+	if (src_fourcc == V4L2_PIX_FMT_JPEG)
+		coda_write(dev, 0, CODA_CMD_DEC_SEQ_JPG_THUMB_EN);
 	if (dev->devtype->product != CODA_960)
 		coda_write(dev, 0, CODA_CMD_DEC_SEQ_SRC_SIZE);
 
diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c
index c7631e117dd3..726b3b93a486 100644
--- a/drivers/media/platform/coda/coda-common.c
+++ b/drivers/media/platform/coda/coda-common.c
@@ -569,8 +569,6 @@ static int coda_try_fmt(struct coda_ctx *ctx, const struct coda_codec *codec,
 					f->fmt.pix.height * 2;
 		break;
 	case V4L2_PIX_FMT_JPEG:
-		f->fmt.pix.colorspace = V4L2_COLORSPACE_JPEG;
-		/* fallthrough */
 	case V4L2_PIX_FMT_H264:
 	case V4L2_PIX_FMT_MPEG4:
 	case V4L2_PIX_FMT_MPEG2:
@@ -935,6 +933,40 @@ static int coda_g_selection(struct file *file, void *fh,
 	return 0;
 }
 
+static int coda_s_selection(struct file *file, void *fh,
+			    struct v4l2_selection *s)
+{
+	struct coda_ctx *ctx = fh_to_ctx(fh);
+	struct coda_q_data *q_data;
+
+	if (ctx->inst_type == CODA_INST_ENCODER &&
+	    s->type == V4L2_BUF_TYPE_VIDEO_OUTPUT &&
+	    s->target == V4L2_SEL_TGT_CROP) {
+		q_data = get_q_data(ctx, s->type);
+		if (!q_data)
+			return -EINVAL;
+
+		s->r.left = 0;
+		s->r.top = 0;
+		s->r.width = clamp(s->r.width, 2U, q_data->width);
+		s->r.height = clamp(s->r.height, 2U, q_data->height);
+
+		if (s->flags & V4L2_SEL_FLAG_LE) {
+			s->r.width = round_up(s->r.width, 2);
+			s->r.height = round_up(s->r.height, 2);
+		} else {
+			s->r.width = round_down(s->r.width, 2);
+			s->r.height = round_down(s->r.height, 2);
+		}
+
+		q_data->rect = s->r;
+
+		return 0;
+	}
+
+	return coda_g_selection(file, fh, s);
+}
+
 static int coda_try_encoder_cmd(struct file *file, void *fh,
 				struct v4l2_encoder_cmd *ec)
 {
@@ -1148,6 +1180,7 @@ static const struct v4l2_ioctl_ops coda_ioctl_ops = {
 	.vidioc_streamoff	= v4l2_m2m_ioctl_streamoff,
 
 	.vidioc_g_selection	= coda_g_selection,
+	.vidioc_s_selection	= coda_s_selection,
 
 	.vidioc_try_encoder_cmd	= coda_try_encoder_cmd,
 	.vidioc_encoder_cmd	= coda_encoder_cmd,
@@ -1297,28 +1330,10 @@ static void coda_job_abort(void *priv)
 		 "Aborting task\n");
 }
 
-static void coda_lock(void *m2m_priv)
-{
-	struct coda_ctx *ctx = m2m_priv;
-	struct coda_dev *pcdev = ctx->dev;
-
-	mutex_lock(&pcdev->dev_mutex);
-}
-
-static void coda_unlock(void *m2m_priv)
-{
-	struct coda_ctx *ctx = m2m_priv;
-	struct coda_dev *pcdev = ctx->dev;
-
-	mutex_unlock(&pcdev->dev_mutex);
-}
-
 static const struct v4l2_m2m_ops coda_m2m_ops = {
 	.device_run	= coda_device_run,
 	.job_ready	= coda_job_ready,
 	.job_abort	= coda_job_abort,
-	.lock		= coda_lock,
-	.unlock		= coda_unlock,
 };
 
 static void set_default_params(struct coda_ctx *ctx)
@@ -1413,6 +1428,72 @@ static int coda_buf_prepare(struct vb2_buffer *vb)
 	return 0;
 }
 
+static void coda_update_menu_ctrl(struct v4l2_ctrl *ctrl, int value)
+{
+	if (!ctrl)
+		return;
+
+	v4l2_ctrl_lock(ctrl);
+
+	/*
+	 * Extend the control range if the parsed stream contains a known but
+	 * unsupported value or level.
+	 */
+	if (value > ctrl->maximum) {
+		__v4l2_ctrl_modify_range(ctrl, ctrl->minimum, value,
+			ctrl->menu_skip_mask & ~(1 << value),
+			ctrl->default_value);
+	} else if (value < ctrl->minimum) {
+		__v4l2_ctrl_modify_range(ctrl, value, ctrl->maximum,
+			ctrl->menu_skip_mask & ~(1 << value),
+			ctrl->default_value);
+	}
+
+	__v4l2_ctrl_s_ctrl(ctrl, value);
+
+	v4l2_ctrl_unlock(ctrl);
+}
+
+static void coda_update_h264_profile_ctrl(struct coda_ctx *ctx)
+{
+	const char * const *profile_names;
+	int profile;
+
+	profile = coda_h264_profile(ctx->params.h264_profile_idc);
+	if (profile < 0) {
+		v4l2_warn(&ctx->dev->v4l2_dev, "Invalid H264 Profile: %u\n",
+			  ctx->params.h264_profile_idc);
+		return;
+	}
+
+	coda_update_menu_ctrl(ctx->h264_profile_ctrl, profile);
+
+	profile_names = v4l2_ctrl_get_menu(V4L2_CID_MPEG_VIDEO_H264_PROFILE);
+
+	v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev, "Parsed H264 Profile: %s\n",
+		 profile_names[profile]);
+}
+
+static void coda_update_h264_level_ctrl(struct coda_ctx *ctx)
+{
+	const char * const *level_names;
+	int level;
+
+	level = coda_h264_level(ctx->params.h264_level_idc);
+	if (level < 0) {
+		v4l2_warn(&ctx->dev->v4l2_dev, "Invalid H264 Level: %u\n",
+			  ctx->params.h264_level_idc);
+		return;
+	}
+
+	coda_update_menu_ctrl(ctx->h264_level_ctrl, level);
+
+	level_names = v4l2_ctrl_get_menu(V4L2_CID_MPEG_VIDEO_H264_LEVEL);
+
+	v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev, "Parsed H264 Level: %s\n",
+		 level_names[level]);
+}
+
 static void coda_buf_queue(struct vb2_buffer *vb)
 {
 	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
@@ -1441,8 +1522,11 @@ static void coda_buf_queue(struct vb2_buffer *vb)
 			 * whether to enable reordering during sequence
 			 * initialization.
 			 */
-			if (!ctx->params.h264_profile_idc)
+			if (!ctx->params.h264_profile_idc) {
 				coda_sps_parse_profile(ctx, vb);
+				coda_update_h264_profile_ctrl(ctx);
+				coda_update_h264_level_ctrl(ctx);
+			}
 		}
 
 		mutex_lock(&ctx->bitstream_mutex);
@@ -1538,12 +1622,12 @@ static int coda_start_streaming(struct vb2_queue *q, unsigned int count)
 		goto out;
 
 	q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
-	if ((q_data_src->width != q_data_dst->width &&
-	     round_up(q_data_src->width, 16) != q_data_dst->width) ||
-	    (q_data_src->height != q_data_dst->height &&
-	     round_up(q_data_src->height, 16) != q_data_dst->height)) {
+	if ((q_data_src->rect.width != q_data_dst->width &&
+	     round_up(q_data_src->rect.width, 16) != q_data_dst->width) ||
+	    (q_data_src->rect.height != q_data_dst->height &&
+	     round_up(q_data_src->rect.height, 16) != q_data_dst->height)) {
 		v4l2_err(v4l2_dev, "can't convert %dx%d to %dx%d\n",
-			 q_data_src->width, q_data_src->height,
+			 q_data_src->rect.width, q_data_src->rect.height,
 			 q_data_dst->width, q_data_dst->height);
 		ret = -EINVAL;
 		goto err;
@@ -1652,6 +1736,7 @@ static void coda_stop_streaming(struct vb2_queue *q)
 			ctx->bitstream.vaddr, ctx->bitstream.size);
 		ctx->runcounter = 0;
 		ctx->aborting = 0;
+		ctx->hold = false;
 	}
 
 	if (!ctx->streamon_out && !ctx->streamon_cap)
@@ -1880,6 +1965,47 @@ static void coda_jpeg_encode_ctrls(struct coda_ctx *ctx)
 		V4L2_CID_JPEG_RESTART_INTERVAL, 0, 100, 1, 0);
 }
 
+static void coda_decode_ctrls(struct coda_ctx *ctx)
+{
+	u64 mask;
+	u8 max;
+
+	ctx->h264_profile_ctrl = v4l2_ctrl_new_std_menu(&ctx->ctrls,
+		&coda_ctrl_ops, V4L2_CID_MPEG_VIDEO_H264_PROFILE,
+		V4L2_MPEG_VIDEO_H264_PROFILE_HIGH,
+		~((1 << V4L2_MPEG_VIDEO_H264_PROFILE_BASELINE) |
+		  (1 << V4L2_MPEG_VIDEO_H264_PROFILE_MAIN) |
+		  (1 << V4L2_MPEG_VIDEO_H264_PROFILE_HIGH)),
+		V4L2_MPEG_VIDEO_H264_PROFILE_HIGH);
+	if (ctx->h264_profile_ctrl)
+		ctx->h264_profile_ctrl->flags |= V4L2_CTRL_FLAG_READ_ONLY;
+
+	if (ctx->dev->devtype->product == CODA_HX4 ||
+	    ctx->dev->devtype->product == CODA_7541) {
+		max = V4L2_MPEG_VIDEO_H264_LEVEL_4_0;
+		mask = ~((1 << V4L2_MPEG_VIDEO_H264_LEVEL_2_0) |
+			 (1 << V4L2_MPEG_VIDEO_H264_LEVEL_3_0) |
+			 (1 << V4L2_MPEG_VIDEO_H264_LEVEL_3_1) |
+			 (1 << V4L2_MPEG_VIDEO_H264_LEVEL_3_2) |
+			 (1 << V4L2_MPEG_VIDEO_H264_LEVEL_4_0));
+	} else if (ctx->dev->devtype->product == CODA_960) {
+		max = V4L2_MPEG_VIDEO_H264_LEVEL_4_1;
+		mask = ~((1 << V4L2_MPEG_VIDEO_H264_LEVEL_2_0) |
+			 (1 << V4L2_MPEG_VIDEO_H264_LEVEL_3_0) |
+			 (1 << V4L2_MPEG_VIDEO_H264_LEVEL_3_1) |
+			 (1 << V4L2_MPEG_VIDEO_H264_LEVEL_3_2) |
+			 (1 << V4L2_MPEG_VIDEO_H264_LEVEL_4_0) |
+			 (1 << V4L2_MPEG_VIDEO_H264_LEVEL_4_1));
+	} else {
+		return;
+	}
+	ctx->h264_level_ctrl = v4l2_ctrl_new_std_menu(&ctx->ctrls,
+		&coda_ctrl_ops, V4L2_CID_MPEG_VIDEO_H264_LEVEL, max, mask,
+		max);
+	if (ctx->h264_level_ctrl)
+		ctx->h264_level_ctrl->flags |= V4L2_CTRL_FLAG_READ_ONLY;
+}
+
 static int coda_ctrls_setup(struct coda_ctx *ctx)
 {
 	v4l2_ctrl_handler_init(&ctx->ctrls, 2);
@@ -1893,6 +2019,9 @@ static int coda_ctrls_setup(struct coda_ctx *ctx)
 			coda_jpeg_encode_ctrls(ctx);
 		else
 			coda_encode_ctrls(ctx);
+	} else {
+		if (ctx->cvd->src_formats[0] == V4L2_PIX_FMT_H264)
+			coda_decode_ctrls(ctx);
 	}
 
 	if (ctx->ctrls.error) {
@@ -2092,9 +2221,9 @@ static int coda_open(struct file *file)
 	INIT_LIST_HEAD(&ctx->buffer_meta_list);
 	spin_lock_init(&ctx->buffer_meta_lock);
 
-	coda_lock(ctx);
+	mutex_lock(&dev->dev_mutex);
 	list_add(&ctx->list, &dev->instances);
-	coda_unlock(ctx);
+	mutex_unlock(&dev->dev_mutex);
 
 	v4l2_dbg(1, coda_debug, &dev->v4l2_dev, "Created instance %d (%p)\n",
 		 ctx->idx, ctx);
@@ -2142,9 +2271,9 @@ static int coda_release(struct file *file)
 		flush_work(&ctx->seq_end_work);
 	}
 
-	coda_lock(ctx);
+	mutex_lock(&dev->dev_mutex);
 	list_del(&ctx->list);
-	coda_unlock(ctx);
+	mutex_unlock(&dev->dev_mutex);
 
 	if (ctx->dev->devtype->product == CODA_DX6)
 		coda_free_aux_buf(dev, &ctx->workbuf);
diff --git a/drivers/media/platform/coda/coda-h264.c b/drivers/media/platform/coda/coda-h264.c
index 0e27412e01f5..635356a839cf 100644
--- a/drivers/media/platform/coda/coda-h264.c
+++ b/drivers/media/platform/coda/coda-h264.c
@@ -108,6 +108,325 @@ int coda_h264_level(int level_idc)
 	case 32: return V4L2_MPEG_VIDEO_H264_LEVEL_3_2;
 	case 40: return V4L2_MPEG_VIDEO_H264_LEVEL_4_0;
 	case 41: return V4L2_MPEG_VIDEO_H264_LEVEL_4_1;
+	case 42: return V4L2_MPEG_VIDEO_H264_LEVEL_4_2;
+	case 50: return V4L2_MPEG_VIDEO_H264_LEVEL_5_0;
+	case 51: return V4L2_MPEG_VIDEO_H264_LEVEL_5_1;
 	default: return -EINVAL;
 	}
 }
+
+struct rbsp {
+	char *buf;
+	int size;
+	int pos;
+};
+
+static inline int rbsp_read_bit(struct rbsp *rbsp)
+{
+	int shift = 7 - (rbsp->pos % 8);
+	int ofs = rbsp->pos++ / 8;
+
+	if (ofs >= rbsp->size)
+		return -EINVAL;
+
+	return (rbsp->buf[ofs] >> shift) & 1;
+}
+
+static inline int rbsp_write_bit(struct rbsp *rbsp, int bit)
+{
+	int shift = 7 - (rbsp->pos % 8);
+	int ofs = rbsp->pos++ / 8;
+
+	if (ofs >= rbsp->size)
+		return -EINVAL;
+
+	rbsp->buf[ofs] &= ~(1 << shift);
+	rbsp->buf[ofs] |= bit << shift;
+
+	return 0;
+}
+
+static inline int rbsp_read_bits(struct rbsp *rbsp, int num, int *val)
+{
+	int i, ret;
+	int tmp = 0;
+
+	if (num > 32)
+		return -EINVAL;
+
+	for (i = 0; i < num; i++) {
+		ret = rbsp_read_bit(rbsp);
+		if (ret < 0)
+			return ret;
+		tmp |= ret << (num - i - 1);
+	}
+
+	if (val)
+		*val = tmp;
+
+	return 0;
+}
+
+static int rbsp_write_bits(struct rbsp *rbsp, int num, int value)
+{
+	int ret;
+
+	while (num--) {
+		ret = rbsp_write_bit(rbsp, (value >> num) & 1);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int rbsp_read_uev(struct rbsp *rbsp, unsigned int *val)
+{
+	int leading_zero_bits = 0;
+	unsigned int tmp = 0;
+	int ret;
+
+	while ((ret = rbsp_read_bit(rbsp)) == 0)
+		leading_zero_bits++;
+	if (ret < 0)
+		return ret;
+
+	if (leading_zero_bits > 0) {
+		ret = rbsp_read_bits(rbsp, leading_zero_bits, &tmp);
+		if (ret)
+			return ret;
+	}
+
+	if (val)
+		*val = (1 << leading_zero_bits) - 1 + tmp;
+
+	return 0;
+}
+
+static int rbsp_write_uev(struct rbsp *rbsp, unsigned int value)
+{
+	int i;
+	int ret;
+	int tmp = value + 1;
+	int leading_zero_bits = fls(tmp) - 1;
+
+	for (i = 0; i < leading_zero_bits; i++) {
+		ret = rbsp_write_bit(rbsp, 0);
+		if (ret)
+			return ret;
+	}
+
+	return rbsp_write_bits(rbsp, leading_zero_bits + 1, tmp);
+}
+
+static int rbsp_read_sev(struct rbsp *rbsp, int *val)
+{
+	unsigned int tmp;
+	int ret;
+
+	ret = rbsp_read_uev(rbsp, &tmp);
+	if (ret)
+		return ret;
+
+	if (val) {
+		if (tmp & 1)
+			*val = (tmp + 1) / 2;
+		else
+			*val = -(tmp / 2);
+	}
+
+	return 0;
+}
+
+/**
+ * coda_h264_sps_fixup - fixes frame cropping values in h.264 SPS
+ * @ctx: encoder context
+ * @width: visible width
+ * @height: visible height
+ * @buf: buffer containing h.264 SPS RBSP, starting with NAL header
+ * @size: modified RBSP size return value
+ * @max_size: available size in buf
+ *
+ * Rewrites the frame cropping values in an h.264 SPS RBSP correctly for the
+ * given visible width and height.
+ */
+int coda_h264_sps_fixup(struct coda_ctx *ctx, int width, int height, char *buf,
+			int *size, int max_size)
+{
+	int profile_idc;
+	unsigned int pic_order_cnt_type;
+	int pic_width_in_mbs_minus1, pic_height_in_map_units_minus1;
+	int frame_mbs_only_flag, frame_cropping_flag;
+	int vui_parameters_present_flag;
+	unsigned int crop_right, crop_bottom;
+	struct rbsp sps;
+	int pos;
+	int ret;
+
+	if (*size < 8 || *size >= max_size)
+		return -EINVAL;
+
+	sps.buf = buf + 5; /* Skip NAL header */
+	sps.size = *size - 5;
+
+	profile_idc = sps.buf[0];
+	/* Skip constraint_set[0-5]_flag, reserved_zero_2bits */
+	/* Skip level_idc */
+	sps.pos = 24;
+
+	/* seq_parameter_set_id */
+	ret = rbsp_read_uev(&sps, NULL);
+	if (ret)
+		return ret;
+
+	if (profile_idc == 100 || profile_idc == 110 || profile_idc == 122 ||
+	    profile_idc == 244 || profile_idc == 44 || profile_idc == 83 ||
+	    profile_idc == 86 || profile_idc == 118 || profile_idc == 128 ||
+	    profile_idc == 138 || profile_idc == 139 || profile_idc == 134 ||
+	    profile_idc == 135) {
+		dev_err(ctx->fh.vdev->dev_parent,
+			"%s: Handling profile_idc %d not implemented\n",
+			__func__, profile_idc);
+		return -EINVAL;
+	}
+
+	/* log2_max_frame_num_minus4 */
+	ret = rbsp_read_uev(&sps, NULL);
+	if (ret)
+		return ret;
+
+	ret = rbsp_read_uev(&sps, &pic_order_cnt_type);
+	if (ret)
+		return ret;
+
+	if (pic_order_cnt_type == 0) {
+		/* log2_max_pic_order_cnt_lsb_minus4 */
+		ret = rbsp_read_uev(&sps, NULL);
+		if (ret)
+			return ret;
+	} else if (pic_order_cnt_type == 1) {
+		unsigned int i, num_ref_frames_in_pic_order_cnt_cycle;
+
+		/* delta_pic_order_always_zero_flag */
+		ret = rbsp_read_bit(&sps);
+		if (ret < 0)
+			return ret;
+		/* offset_for_non_ref_pic */
+		ret = rbsp_read_sev(&sps, NULL);
+		if (ret)
+			return ret;
+		/* offset_for_top_to_bottom_field */
+		ret = rbsp_read_sev(&sps, NULL);
+		if (ret)
+			return ret;
+
+		ret = rbsp_read_uev(&sps,
+				    &num_ref_frames_in_pic_order_cnt_cycle);
+		if (ret)
+			return ret;
+		for (i = 0; i < num_ref_frames_in_pic_order_cnt_cycle; i++) {
+			/* offset_for_ref_frame */
+			ret = rbsp_read_sev(&sps, NULL);
+			if (ret)
+				return ret;
+		}
+	}
+
+	/* max_num_ref_frames */
+	ret = rbsp_read_uev(&sps, NULL);
+	if (ret)
+		return ret;
+
+	/* gaps_in_frame_num_value_allowed_flag */
+	ret = rbsp_read_bit(&sps);
+	if (ret < 0)
+		return ret;
+	ret = rbsp_read_uev(&sps, &pic_width_in_mbs_minus1);
+	if (ret)
+		return ret;
+	ret = rbsp_read_uev(&sps, &pic_height_in_map_units_minus1);
+	if (ret)
+		return ret;
+	frame_mbs_only_flag = ret = rbsp_read_bit(&sps);
+	if (ret < 0)
+		return ret;
+	if (!frame_mbs_only_flag) {
+		/* mb_adaptive_frame_field_flag */
+		ret = rbsp_read_bit(&sps);
+		if (ret < 0)
+			return ret;
+	}
+	/* direct_8x8_inference_flag */
+	ret = rbsp_read_bit(&sps);
+	if (ret < 0)
+		return ret;
+
+	/* Mark position of the frame cropping flag */
+	pos = sps.pos;
+	frame_cropping_flag = ret = rbsp_read_bit(&sps);
+	if (ret < 0)
+		return ret;
+	if (frame_cropping_flag) {
+		unsigned int crop_left, crop_top;
+
+		ret = rbsp_read_uev(&sps, &crop_left);
+		if (ret)
+			return ret;
+		ret = rbsp_read_uev(&sps, &crop_right);
+		if (ret)
+			return ret;
+		ret = rbsp_read_uev(&sps, &crop_top);
+		if (ret)
+			return ret;
+		ret = rbsp_read_uev(&sps, &crop_bottom);
+		if (ret)
+			return ret;
+	}
+	vui_parameters_present_flag = ret = rbsp_read_bit(&sps);
+	if (ret < 0)
+		return ret;
+	if (vui_parameters_present_flag) {
+		dev_err(ctx->fh.vdev->dev_parent,
+			"%s: Handling vui_parameters not implemented\n",
+			__func__);
+		return -EINVAL;
+	}
+
+	crop_right = round_up(width, 16) - width;
+	crop_bottom = round_up(height, 16) - height;
+	crop_right /= 2;
+	if (frame_mbs_only_flag)
+		crop_bottom /= 2;
+	else
+		crop_bottom /= 4;
+
+
+	sps.size = max_size - 5;
+	sps.pos = pos;
+	frame_cropping_flag = 1;
+	ret = rbsp_write_bit(&sps, frame_cropping_flag);
+	if (ret)
+		return ret;
+	ret = rbsp_write_uev(&sps, 0); /* crop_left */
+	if (ret)
+		return ret;
+	ret = rbsp_write_uev(&sps, crop_right);
+	if (ret)
+		return ret;
+	ret = rbsp_write_uev(&sps, 0); /* crop_top */
+	if (ret)
+		return ret;
+	ret = rbsp_write_uev(&sps, crop_bottom);
+	if (ret)
+		return ret;
+	ret = rbsp_write_bit(&sps, 0); /* vui_parameters_present_flag */
+	if (ret)
+		return ret;
+	ret = rbsp_write_bit(&sps, 1);
+	if (ret)
+		return ret;
+
+	*size = 5 + DIV_ROUND_UP(sps.pos, 8);
+
+	return 0;
+}
diff --git a/drivers/media/platform/coda/coda.h b/drivers/media/platform/coda/coda.h
index c70cfab2433f..19ac0b9dc6eb 100644
--- a/drivers/media/platform/coda/coda.h
+++ b/drivers/media/platform/coda/coda.h
@@ -214,6 +214,8 @@ struct coda_ctx {
 	enum v4l2_quantization		quantization;
 	struct coda_params		params;
 	struct v4l2_ctrl_handler	ctrls;
+	struct v4l2_ctrl		*h264_profile_ctrl;
+	struct v4l2_ctrl		*h264_level_ctrl;
 	struct v4l2_fh			fh;
 	int				gopcounter;
 	int				runcounter;
@@ -303,6 +305,8 @@ int coda_h264_padding(int size, char *p);
 int coda_h264_profile(int profile_idc);
 int coda_h264_level(int level_idc);
 int coda_sps_parse_profile(struct coda_ctx *ctx, struct vb2_buffer *vb);
+int coda_h264_sps_fixup(struct coda_ctx *ctx, int width, int height, char *buf,
+			int *size, int max_size);
 
 bool coda_jpeg_check_buffer(struct coda_ctx *ctx, struct vb2_buffer *vb);
 int coda_jpeg_write_tables(struct coda_ctx *ctx);
diff --git a/drivers/media/platform/coda/coda_regs.h b/drivers/media/platform/coda/coda_regs.h
index 3b650b8aabe9..5e7b00a97671 100644
--- a/drivers/media/platform/coda/coda_regs.h
+++ b/drivers/media/platform/coda/coda_regs.h
@@ -157,6 +157,7 @@
 #define CODA_CMD_DEC_SEQ_START_BYTE		0x190
 #define CODA_CMD_DEC_SEQ_PS_BB_START		0x194
 #define CODA_CMD_DEC_SEQ_PS_BB_SIZE		0x198
+#define CODA_CMD_DEC_SEQ_JPG_THUMB_EN		0x19c
 #define CODA_CMD_DEC_SEQ_MP4_ASP_CLASS		0x19c
 #define		CODA_MP4_CLASS_MPEG4			0
 #define CODA_CMD_DEC_SEQ_X264_MV_EN		0x19c
diff --git a/drivers/media/platform/davinci/vpbe_osd.c b/drivers/media/platform/davinci/vpbe_osd.c
index 7f610320426d..c551a25d90d9 100644
--- a/drivers/media/platform/davinci/vpbe_osd.c
+++ b/drivers/media/platform/davinci/vpbe_osd.c
@@ -18,6 +18,7 @@
  *
  */
 #include <linux/module.h>
+#include <linux/mod_devicetable.h>
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
diff --git a/drivers/media/platform/davinci/vpbe_venc.c b/drivers/media/platform/davinci/vpbe_venc.c
index ba157827192c..ddcad7b3e76c 100644
--- a/drivers/media/platform/davinci/vpbe_venc.c
+++ b/drivers/media/platform/davinci/vpbe_venc.c
@@ -11,6 +11,7 @@
  * GNU General Public License for more details.
  */
 #include <linux/module.h>
+#include <linux/mod_devicetable.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/ctype.h>
diff --git a/drivers/media/platform/davinci/vpif_display.c b/drivers/media/platform/davinci/vpif_display.c
index 7be636237acf..0f324055cc9f 100644
--- a/drivers/media/platform/davinci/vpif_display.c
+++ b/drivers/media/platform/davinci/vpif_display.c
@@ -1114,6 +1114,14 @@ vpif_init_free_channel_objects:
 	return err;
 }
 
+static void free_vpif_objs(void)
+{
+	int i;
+
+	for (i = 0; i < VPIF_DISPLAY_MAX_DEVICES; i++)
+		kfree(vpif_obj.dev[i]);
+}
+
 static int vpif_async_bound(struct v4l2_async_notifier *notifier,
 			    struct v4l2_subdev *subdev,
 			    struct v4l2_async_subdev *asd)
@@ -1255,11 +1263,6 @@ static __init int vpif_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	if (!pdev->dev.platform_data) {
-		dev_warn(&pdev->dev, "Missing platform data.  Giving up.\n");
-		return -EINVAL;
-	}
-
 	vpif_dev = &pdev->dev;
 	err = initialize_vpif();
 
@@ -1271,7 +1274,7 @@ static __init int vpif_probe(struct platform_device *pdev)
 	err = v4l2_device_register(vpif_dev, &vpif_obj.v4l2_dev);
 	if (err) {
 		v4l2_err(vpif_dev->driver, "Error registering v4l2 device\n");
-		return err;
+		goto vpif_free;
 	}
 
 	while ((res = platform_get_resource(pdev, IORESOURCE_IRQ, res_idx))) {
@@ -1314,7 +1317,10 @@ static __init int vpif_probe(struct platform_device *pdev)
 			if (vpif_obj.sd[i])
 				vpif_obj.sd[i]->grp_id = 1 << i;
 		}
-		vpif_probe_complete();
+		err = vpif_probe_complete();
+		if (err) {
+			goto probe_subdev_out;
+		}
 	} else {
 		vpif_obj.notifier.subdevs = vpif_obj.config->asd;
 		vpif_obj.notifier.num_subdevs = vpif_obj.config->asd_sizes[0];
@@ -1334,6 +1340,8 @@ probe_subdev_out:
 	kfree(vpif_obj.sd);
 vpif_unregister:
 	v4l2_device_unregister(&vpif_obj.v4l2_dev);
+vpif_free:
+	free_vpif_objs();
 
 	return err;
 }
@@ -1355,8 +1363,8 @@ static int vpif_remove(struct platform_device *device)
 		ch = vpif_obj.dev[i];
 		/* Unregister video device */
 		video_unregister_device(&ch->video_dev);
-		kfree(vpif_obj.dev[i]);
 	}
+	free_vpif_objs();
 
 	return 0;
 }
diff --git a/drivers/media/platform/exynos-gsc/gsc-m2m.c b/drivers/media/platform/exynos-gsc/gsc-m2m.c
index e9ff27949a91..c9d2f6c5311a 100644
--- a/drivers/media/platform/exynos-gsc/gsc-m2m.c
+++ b/drivers/media/platform/exynos-gsc/gsc-m2m.c
@@ -713,7 +713,7 @@ static __poll_t gsc_m2m_poll(struct file *file,
 	__poll_t ret;
 
 	if (mutex_lock_interruptible(&gsc->lock))
-		return -ERESTARTSYS;
+		return EPOLLERR;
 
 	ret = v4l2_m2m_poll(file, ctx->m2m_ctx, wait);
 	mutex_unlock(&gsc->lock);
diff --git a/drivers/media/platform/exynos4-is/fimc-isp-video.c b/drivers/media/platform/exynos4-is/fimc-isp-video.c
index 55ba696b8cf4..a920164f53f1 100644
--- a/drivers/media/platform/exynos4-is/fimc-isp-video.c
+++ b/drivers/media/platform/exynos4-is/fimc-isp-video.c
@@ -384,12 +384,17 @@ static void __isp_video_try_fmt(struct fimc_isp *isp,
 				struct v4l2_pix_format_mplane *pixm,
 				const struct fimc_fmt **fmt)
 {
-	*fmt = fimc_isp_find_format(&pixm->pixelformat, NULL, 2);
+	const struct fimc_fmt *__fmt;
+
+	__fmt = fimc_isp_find_format(&pixm->pixelformat, NULL, 2);
+
+	if (fmt)
+		*fmt = __fmt;
 
 	pixm->colorspace = V4L2_COLORSPACE_SRGB;
 	pixm->field = V4L2_FIELD_NONE;
-	pixm->num_planes = (*fmt)->memplanes;
-	pixm->pixelformat = (*fmt)->fourcc;
+	pixm->num_planes = __fmt->memplanes;
+	pixm->pixelformat = __fmt->fourcc;
 	/*
 	 * TODO: double check with the docmentation these width/height
 	 * constraints are correct.
diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c
index 78b48a1fa26c..deb499f76412 100644
--- a/drivers/media/platform/exynos4-is/media-dev.c
+++ b/drivers/media/platform/exynos4-is/media-dev.c
@@ -1201,8 +1201,7 @@ static const struct media_device_ops fimc_md_ops = {
 static ssize_t fimc_md_sysfs_show(struct device *dev,
 				  struct device_attribute *attr, char *buf)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct fimc_md *fmd = platform_get_drvdata(pdev);
+	struct fimc_md *fmd = dev_get_drvdata(dev);
 
 	if (fmd->user_subdev_api)
 		return strlcpy(buf, "Sub-device API (sub-dev)\n", PAGE_SIZE);
@@ -1214,8 +1213,7 @@ static ssize_t fimc_md_sysfs_store(struct device *dev,
 				   struct device_attribute *attr,
 				   const char *buf, size_t count)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct fimc_md *fmd = platform_get_drvdata(pdev);
+	struct fimc_md *fmd = dev_get_drvdata(dev);
 	bool subdev_api;
 	int i;
 
diff --git a/drivers/media/platform/exynos4-is/mipi-csis.c b/drivers/media/platform/exynos4-is/mipi-csis.c
index cba46a656338..b4e28a299e26 100644
--- a/drivers/media/platform/exynos4-is/mipi-csis.c
+++ b/drivers/media/platform/exynos4-is/mipi-csis.c
@@ -891,8 +891,7 @@ e_clkput:
 
 static int s5pcsis_pm_suspend(struct device *dev, bool runtime)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct v4l2_subdev *sd = platform_get_drvdata(pdev);
+	struct v4l2_subdev *sd = dev_get_drvdata(dev);
 	struct csis_state *state = sd_to_csis_state(sd);
 	int ret = 0;
 
@@ -921,8 +920,7 @@ static int s5pcsis_pm_suspend(struct device *dev, bool runtime)
 
 static int s5pcsis_pm_resume(struct device *dev, bool runtime)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct v4l2_subdev *sd = platform_get_drvdata(pdev);
+	struct v4l2_subdev *sd = dev_get_drvdata(dev);
 	struct csis_state *state = sd_to_csis_state(sd);
 	int ret = 0;
 
diff --git a/drivers/media/platform/fsl-viu.c b/drivers/media/platform/fsl-viu.c
index e41510ce69a4..0273302aa741 100644
--- a/drivers/media/platform/fsl-viu.c
+++ b/drivers/media/platform/fsl-viu.c
@@ -1414,7 +1414,7 @@ static int viu_of_probe(struct platform_device *op)
 				     sizeof(struct viu_reg), DRV_NAME)) {
 		dev_err(&op->dev, "Error while requesting mem region\n");
 		ret = -EBUSY;
-		goto err;
+		goto err_irq;
 	}
 
 	/* remap registers */
@@ -1422,7 +1422,7 @@ static int viu_of_probe(struct platform_device *op)
 	if (!viu_regs) {
 		dev_err(&op->dev, "Can't map register set\n");
 		ret = -ENOMEM;
-		goto err;
+		goto err_irq;
 	}
 
 	/* Prepare our private structure */
@@ -1430,7 +1430,7 @@ static int viu_of_probe(struct platform_device *op)
 	if (!viu_dev) {
 		dev_err(&op->dev, "Can't allocate private structure\n");
 		ret = -ENOMEM;
-		goto err;
+		goto err_irq;
 	}
 
 	viu_dev->vr = viu_regs;
@@ -1446,16 +1446,21 @@ static int viu_of_probe(struct platform_device *op)
 	ret = v4l2_device_register(viu_dev->dev, &viu_dev->v4l2_dev);
 	if (ret < 0) {
 		dev_err(&op->dev, "v4l2_device_register() failed: %d\n", ret);
-		goto err;
+		goto err_irq;
 	}
 
 	ad = i2c_get_adapter(0);
+	if (!ad) {
+		ret = -EFAULT;
+		dev_err(&op->dev, "couldn't get i2c adapter\n");
+		goto err_v4l2;
+	}
 
 	v4l2_ctrl_handler_init(&viu_dev->hdl, 5);
 	if (viu_dev->hdl.error) {
 		ret = viu_dev->hdl.error;
 		dev_err(&op->dev, "couldn't register control\n");
-		goto err_vdev;
+		goto err_i2c;
 	}
 	/* This control handler will inherit the control(s) from the
 	   sub-device(s). */
@@ -1471,7 +1476,7 @@ static int viu_of_probe(struct platform_device *op)
 	vdev = video_device_alloc();
 	if (vdev == NULL) {
 		ret = -ENOMEM;
-		goto err_vdev;
+		goto err_hdl;
 	}
 
 	*vdev = viu_template;
@@ -1492,7 +1497,7 @@ static int viu_of_probe(struct platform_device *op)
 	ret = video_register_device(viu_dev->vdev, VFL_TYPE_GRABBER, -1);
 	if (ret < 0) {
 		video_device_release(viu_dev->vdev);
-		goto err_vdev;
+		goto err_unlock;
 	}
 
 	/* enable VIU clock */
@@ -1500,12 +1505,12 @@ static int viu_of_probe(struct platform_device *op)
 	if (IS_ERR(clk)) {
 		dev_err(&op->dev, "failed to lookup the clock!\n");
 		ret = PTR_ERR(clk);
-		goto err_clk;
+		goto err_vdev;
 	}
 	ret = clk_prepare_enable(clk);
 	if (ret) {
 		dev_err(&op->dev, "failed to enable the clock!\n");
-		goto err_clk;
+		goto err_vdev;
 	}
 	viu_dev->clk = clk;
 
@@ -1516,7 +1521,7 @@ static int viu_of_probe(struct platform_device *op)
 	if (request_irq(viu_dev->irq, viu_intr, 0, "viu", (void *)viu_dev)) {
 		dev_err(&op->dev, "Request VIU IRQ failed.\n");
 		ret = -ENODEV;
-		goto err_irq;
+		goto err_clk;
 	}
 
 	mutex_unlock(&viu_dev->lock);
@@ -1524,16 +1529,19 @@ static int viu_of_probe(struct platform_device *op)
 	dev_info(&op->dev, "Freescale VIU Video Capture Board\n");
 	return ret;
 
-err_irq:
-	clk_disable_unprepare(viu_dev->clk);
 err_clk:
-	video_unregister_device(viu_dev->vdev);
+	clk_disable_unprepare(viu_dev->clk);
 err_vdev:
-	v4l2_ctrl_handler_free(&viu_dev->hdl);
+	video_unregister_device(viu_dev->vdev);
+err_unlock:
 	mutex_unlock(&viu_dev->lock);
+err_hdl:
+	v4l2_ctrl_handler_free(&viu_dev->hdl);
+err_i2c:
 	i2c_put_adapter(ad);
+err_v4l2:
 	v4l2_device_unregister(&viu_dev->v4l2_dev);
-err:
+err_irq:
 	irq_dispose_mapping(viu_irq);
 	return ret;
 }
diff --git a/drivers/media/platform/m2m-deinterlace.c b/drivers/media/platform/m2m-deinterlace.c
index 1e4195144f39..5f84d2aa47ab 100644
--- a/drivers/media/platform/m2m-deinterlace.c
+++ b/drivers/media/platform/m2m-deinterlace.c
@@ -181,20 +181,6 @@ static void deinterlace_job_abort(void *priv)
 	v4l2_m2m_job_finish(pcdev->m2m_dev, ctx->m2m_ctx);
 }
 
-static void deinterlace_lock(void *priv)
-{
-	struct deinterlace_ctx *ctx = priv;
-	struct deinterlace_dev *pcdev = ctx->dev;
-	mutex_lock(&pcdev->dev_mutex);
-}
-
-static void deinterlace_unlock(void *priv)
-{
-	struct deinterlace_ctx *ctx = priv;
-	struct deinterlace_dev *pcdev = ctx->dev;
-	mutex_unlock(&pcdev->dev_mutex);
-}
-
 static void dma_callback(void *data)
 {
 	struct deinterlace_ctx *curr_ctx = data;
@@ -856,6 +842,8 @@ static const struct vb2_ops deinterlace_qops = {
 	.queue_setup	 = deinterlace_queue_setup,
 	.buf_prepare	 = deinterlace_buf_prepare,
 	.buf_queue	 = deinterlace_buf_queue,
+	.wait_prepare	 = vb2_ops_wait_prepare,
+	.wait_finish	 = vb2_ops_wait_finish,
 };
 
 static int queue_init(void *priv, struct vb2_queue *src_vq,
@@ -872,6 +860,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->mem_ops = &vb2_dma_contig_memops;
 	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	src_vq->dev = ctx->dev->v4l2_dev.dev;
+	src_vq->lock = &ctx->dev->dev_mutex;
 	q_data[V4L2_M2M_SRC].fmt = &formats[0];
 	q_data[V4L2_M2M_SRC].width = 640;
 	q_data[V4L2_M2M_SRC].height = 480;
@@ -890,6 +879,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->mem_ops = &vb2_dma_contig_memops;
 	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	dst_vq->dev = ctx->dev->v4l2_dev.dev;
+	dst_vq->lock = &ctx->dev->dev_mutex;
 	q_data[V4L2_M2M_DST].fmt = &formats[0];
 	q_data[V4L2_M2M_DST].width = 640;
 	q_data[V4L2_M2M_DST].height = 480;
@@ -956,9 +946,9 @@ static __poll_t deinterlace_poll(struct file *file,
 	struct deinterlace_ctx *ctx = file->private_data;
 	__poll_t ret;
 
-	deinterlace_lock(ctx);
+	mutex_lock(&ctx->dev->dev_mutex);
 	ret = v4l2_m2m_poll(file, ctx->m2m_ctx, wait);
-	deinterlace_unlock(ctx);
+	mutex_unlock(&ctx->dev->dev_mutex);
 
 	return ret;
 }
@@ -992,8 +982,6 @@ static const struct v4l2_m2m_ops m2m_ops = {
 	.device_run	= deinterlace_device_run,
 	.job_ready	= deinterlace_job_ready,
 	.job_abort	= deinterlace_job_abort,
-	.lock		= deinterlace_lock,
-	.unlock		= deinterlace_unlock,
 };
 
 static int deinterlace_probe(struct platform_device *pdev)
@@ -1040,7 +1028,6 @@ static int deinterlace_probe(struct platform_device *pdev)
 	}
 
 	video_set_drvdata(vfd, pcdev);
-	snprintf(vfd->name, sizeof(vfd->name), "%s", deinterlace_videodev.name);
 	v4l2_info(&pcdev->v4l2_dev, MEM2MEM_TEST_MODULE_NAME
 			" Device registered as /dev/video%d\n", vfd->num);
 
diff --git a/drivers/media/platform/meson/ao-cec.c b/drivers/media/platform/meson/ao-cec.c
index 8040a6285c3f..cd4be38ab5ac 100644
--- a/drivers/media/platform/meson/ao-cec.c
+++ b/drivers/media/platform/meson/ao-cec.c
@@ -524,7 +524,7 @@ static int meson_ao_cec_transmit(struct cec_adapter *adap, u8 attempts,
 		return ret;
 
 	if (reg == TX_BUSY) {
-		dev_err(&ao_cec->pdev->dev, "%s: busy TX: aborting\n",
+		dev_dbg(&ao_cec->pdev->dev, "%s: busy TX: aborting\n",
 			__func__);
 		meson_ao_cec_write(ao_cec, CEC_TX_MSG_CMD, TX_ABORT, &ret);
 	}
diff --git a/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c b/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c
index 328e8f650d9b..4f24da8afecc 100644
--- a/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c
+++ b/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c
@@ -861,14 +861,9 @@ static int mtk_jpeg_job_ready(void *priv)
 	return (ctx->state == MTK_JPEG_RUNNING) ? 1 : 0;
 }
 
-static void mtk_jpeg_job_abort(void *priv)
-{
-}
-
 static const struct v4l2_m2m_ops mtk_jpeg_m2m_ops = {
 	.device_run = mtk_jpeg_device_run,
 	.job_ready  = mtk_jpeg_job_ready,
-	.job_abort  = mtk_jpeg_job_abort,
 };
 
 static int mtk_jpeg_queue_init(void *priv, struct vb2_queue *src_vq,
diff --git a/drivers/media/platform/mtk-mdp/mtk_mdp_m2m.c b/drivers/media/platform/mtk-mdp/mtk_mdp_m2m.c
index 583d47724ee8..ceffc31cc6eb 100644
--- a/drivers/media/platform/mtk-mdp/mtk_mdp_m2m.c
+++ b/drivers/media/platform/mtk-mdp/mtk_mdp_m2m.c
@@ -394,20 +394,6 @@ static bool mtk_mdp_ctx_state_is_set(struct mtk_mdp_ctx *ctx, u32 mask)
 	return ret;
 }
 
-static void mtk_mdp_ctx_lock(struct vb2_queue *vq)
-{
-	struct mtk_mdp_ctx *ctx = vb2_get_drv_priv(vq);
-
-	mutex_lock(&ctx->mdp_dev->lock);
-}
-
-static void mtk_mdp_ctx_unlock(struct vb2_queue *vq)
-{
-	struct mtk_mdp_ctx *ctx = vb2_get_drv_priv(vq);
-
-	mutex_unlock(&ctx->mdp_dev->lock);
-}
-
 static void mtk_mdp_set_frame_size(struct mtk_mdp_frame *frame, int width,
 				   int height)
 {
@@ -455,10 +441,6 @@ static void mtk_mdp_m2m_stop_streaming(struct vb2_queue *q)
 	pm_runtime_put(&ctx->mdp_dev->pdev->dev);
 }
 
-static void mtk_mdp_m2m_job_abort(void *priv)
-{
-}
-
 /* The color format (num_planes) must be already configured. */
 static void mtk_mdp_prepare_addr(struct mtk_mdp_ctx *ctx,
 				 struct vb2_buffer *vb,
@@ -625,10 +607,10 @@ static const struct vb2_ops mtk_mdp_m2m_qops = {
 	.queue_setup	 = mtk_mdp_m2m_queue_setup,
 	.buf_prepare	 = mtk_mdp_m2m_buf_prepare,
 	.buf_queue	 = mtk_mdp_m2m_buf_queue,
-	.wait_prepare	 = mtk_mdp_ctx_unlock,
-	.wait_finish	 = mtk_mdp_ctx_lock,
 	.stop_streaming	 = mtk_mdp_m2m_stop_streaming,
 	.start_streaming = mtk_mdp_m2m_start_streaming,
+	.wait_prepare	 = vb2_ops_wait_prepare,
+	.wait_finish	 = vb2_ops_wait_finish,
 };
 
 static int mtk_mdp_m2m_querycap(struct file *file, void *fh,
@@ -996,6 +978,7 @@ static int mtk_mdp_m2m_queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
 	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	src_vq->dev = &ctx->mdp_dev->pdev->dev;
+	src_vq->lock = &ctx->mdp_dev->lock;
 
 	ret = vb2_queue_init(src_vq);
 	if (ret)
@@ -1010,6 +993,7 @@ static int mtk_mdp_m2m_queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
 	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	dst_vq->dev = &ctx->mdp_dev->pdev->dev;
+	dst_vq->lock = &ctx->mdp_dev->lock;
 
 	return vb2_queue_init(dst_vq);
 }
@@ -1227,7 +1211,6 @@ static const struct v4l2_file_operations mtk_mdp_m2m_fops = {
 
 static const struct v4l2_m2m_ops mtk_mdp_m2m_ops = {
 	.device_run	= mtk_mdp_m2m_device_run,
-	.job_abort	= mtk_mdp_m2m_job_abort,
 };
 
 int mtk_mdp_register_m2m_device(struct mtk_mdp_dev *mdp)
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c
index 86f0a7134365..0c8a8b4c4e1c 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c
@@ -1400,6 +1400,11 @@ int mtk_vcodec_dec_ctrls_setup(struct mtk_vcodec_ctx *ctx)
 				V4L2_CID_MIN_BUFFERS_FOR_CAPTURE,
 				0, 32, 1, 1);
 	ctrl->flags |= V4L2_CTRL_FLAG_VOLATILE;
+	v4l2_ctrl_new_std_menu(&ctx->ctrl_hdl,
+				&mtk_vcodec_dec_ctrl_ops,
+				V4L2_CID_MPEG_VIDEO_VP9_PROFILE,
+				V4L2_MPEG_VIDEO_VP9_PROFILE_0,
+				0, V4L2_MPEG_VIDEO_VP9_PROFILE_0);
 
 	if (ctx->ctrl_hdl.error) {
 		mtk_v4l2_err("Adding control failed %d",
@@ -1411,28 +1416,10 @@ int mtk_vcodec_dec_ctrls_setup(struct mtk_vcodec_ctx *ctx)
 	return 0;
 }
 
-static void m2mops_vdec_lock(void *m2m_priv)
-{
-	struct mtk_vcodec_ctx *ctx = m2m_priv;
-
-	mtk_v4l2_debug(3, "[%d]", ctx->id);
-	mutex_lock(&ctx->dev->dev_mutex);
-}
-
-static void m2mops_vdec_unlock(void *m2m_priv)
-{
-	struct mtk_vcodec_ctx *ctx = m2m_priv;
-
-	mtk_v4l2_debug(3, "[%d]", ctx->id);
-	mutex_unlock(&ctx->dev->dev_mutex);
-}
-
 const struct v4l2_m2m_ops mtk_vdec_m2m_ops = {
 	.device_run	= m2mops_vdec_device_run,
 	.job_ready	= m2mops_vdec_job_ready,
 	.job_abort	= m2mops_vdec_job_abort,
-	.lock		= m2mops_vdec_lock,
-	.unlock		= m2mops_vdec_unlock,
 };
 
 static const struct vb2_ops mtk_vdec_vb2_ops = {
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c
index 1b1a28abbf1f..6ad408514a99 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c
@@ -1181,26 +1181,10 @@ static void m2mops_venc_job_abort(void *priv)
 	ctx->state = MTK_STATE_ABORT;
 }
 
-static void m2mops_venc_lock(void *m2m_priv)
-{
-	struct mtk_vcodec_ctx *ctx = m2m_priv;
-
-	mutex_lock(&ctx->dev->dev_mutex);
-}
-
-static void m2mops_venc_unlock(void *m2m_priv)
-{
-	struct mtk_vcodec_ctx *ctx = m2m_priv;
-
-	mutex_unlock(&ctx->dev->dev_mutex);
-}
-
 const struct v4l2_m2m_ops mtk_venc_m2m_ops = {
 	.device_run	= m2mops_venc_device_run,
 	.job_ready	= m2mops_venc_job_ready,
 	.job_abort	= m2mops_venc_job_abort,
-	.lock		= m2mops_venc_lock,
-	.unlock		= m2mops_venc_unlock,
 };
 
 void mtk_vcodec_enc_set_default_params(struct mtk_vcodec_ctx *ctx)
diff --git a/drivers/media/platform/mtk-vpu/mtk_vpu.c b/drivers/media/platform/mtk-vpu/mtk_vpu.c
index 1ff6a93262b7..f8d35e3ac1dc 100644
--- a/drivers/media/platform/mtk-vpu/mtk_vpu.c
+++ b/drivers/media/platform/mtk-vpu/mtk_vpu.c
@@ -960,4 +960,4 @@ static struct platform_driver mtk_vpu_driver = {
 module_platform_driver(mtk_vpu_driver);
 
 MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("Mediatek Video Prosessor Unit driver");
+MODULE_DESCRIPTION("Mediatek Video Processor Unit driver");
diff --git a/drivers/media/platform/mx2_emmaprp.c b/drivers/media/platform/mx2_emmaprp.c
index 5a8eff60e95f..64195c4ddeaf 100644
--- a/drivers/media/platform/mx2_emmaprp.c
+++ b/drivers/media/platform/mx2_emmaprp.c
@@ -250,20 +250,6 @@ static void emmaprp_job_abort(void *priv)
 	v4l2_m2m_job_finish(pcdev->m2m_dev, ctx->m2m_ctx);
 }
 
-static void emmaprp_lock(void *priv)
-{
-	struct emmaprp_ctx *ctx = priv;
-	struct emmaprp_dev *pcdev = ctx->dev;
-	mutex_lock(&pcdev->dev_mutex);
-}
-
-static void emmaprp_unlock(void *priv)
-{
-	struct emmaprp_ctx *ctx = priv;
-	struct emmaprp_dev *pcdev = ctx->dev;
-	mutex_unlock(&pcdev->dev_mutex);
-}
-
 static inline void emmaprp_dump_regs(struct emmaprp_dev *pcdev)
 {
 	dprintk(pcdev,
@@ -747,6 +733,8 @@ static const struct vb2_ops emmaprp_qops = {
 	.queue_setup	 = emmaprp_queue_setup,
 	.buf_prepare	 = emmaprp_buf_prepare,
 	.buf_queue	 = emmaprp_buf_queue,
+	.wait_prepare	 = vb2_ops_wait_prepare,
+	.wait_finish	 = vb2_ops_wait_finish,
 };
 
 static int queue_init(void *priv, struct vb2_queue *src_vq,
@@ -763,6 +751,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->mem_ops = &vb2_dma_contig_memops;
 	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	src_vq->dev = ctx->dev->v4l2_dev.dev;
+	src_vq->lock = &ctx->dev->dev_mutex;
 
 	ret = vb2_queue_init(src_vq);
 	if (ret)
@@ -776,6 +765,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->mem_ops = &vb2_dma_contig_memops;
 	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	dst_vq->dev = ctx->dev->v4l2_dev.dev;
+	dst_vq->lock = &ctx->dev->dev_mutex;
 
 	return vb2_queue_init(dst_vq);
 }
@@ -885,8 +875,6 @@ static const struct video_device emmaprp_videodev = {
 static const struct v4l2_m2m_ops m2m_ops = {
 	.device_run	= emmaprp_device_run,
 	.job_abort	= emmaprp_job_abort,
-	.lock		= emmaprp_lock,
-	.unlock		= emmaprp_unlock,
 };
 
 static int emmaprp_probe(struct platform_device *pdev)
@@ -934,7 +922,6 @@ static int emmaprp_probe(struct platform_device *pdev)
 	vfd->v4l2_dev = &pcdev->v4l2_dev;
 
 	video_set_drvdata(vfd, pcdev);
-	snprintf(vfd->name, sizeof(vfd->name), "%s", emmaprp_videodev.name);
 	pcdev->vfd = vfd;
 	v4l2_info(&pcdev->v4l2_dev, EMMAPRP_MODULE_NAME
 		  " Device registered as /dev/video%d\n", vfd->num);
diff --git a/drivers/media/platform/omap/Kconfig b/drivers/media/platform/omap/Kconfig
index d827b6c285a6..4b5e55d41ad4 100644
--- a/drivers/media/platform/omap/Kconfig
+++ b/drivers/media/platform/omap/Kconfig
@@ -8,6 +8,7 @@ config VIDEO_OMAP2_VOUT
 	depends on MMU
 	depends on FB_OMAP2 || (COMPILE_TEST && FB_OMAP2=n)
 	depends on ARCH_OMAP2 || ARCH_OMAP3 || COMPILE_TEST
+	depends on VIDEO_V4L2
 	select VIDEOBUF_GEN
 	select VIDEOBUF_DMA_CONTIG
 	select OMAP2_VRFB if ARCH_OMAP2 || ARCH_OMAP3
diff --git a/drivers/media/platform/omap3isp/isp.c b/drivers/media/platform/omap3isp/isp.c
index f22cf351e3ee..842e2235047d 100644
--- a/drivers/media/platform/omap3isp/isp.c
+++ b/drivers/media/platform/omap3isp/isp.c
@@ -300,7 +300,7 @@ static struct clk *isp_xclk_src_get(struct of_phandle_args *clkspec, void *data)
 static int isp_xclk_init(struct isp_device *isp)
 {
 	struct device_node *np = isp->dev->of_node;
-	struct clk_init_data init;
+	struct clk_init_data init = {};
 	unsigned int i;
 
 	for (i = 0; i < ARRAY_SIZE(isp->xclks); ++i)
@@ -971,7 +971,7 @@ static void isp_resume_module_pipeline(struct media_entity *me)
  * Returns 0 if suspend left in idle state all the submodules properly,
  * or returns 1 if a general Reset is required to suspend the submodules.
  */
-static int isp_suspend_modules(struct isp_device *isp)
+static int __maybe_unused isp_suspend_modules(struct isp_device *isp)
 {
 	unsigned long timeout;
 
@@ -1005,7 +1005,7 @@ static int isp_suspend_modules(struct isp_device *isp)
  * isp_resume_modules - Resume ISP submodules.
  * @isp: OMAP3 ISP device
  */
-static void isp_resume_modules(struct isp_device *isp)
+static void __maybe_unused isp_resume_modules(struct isp_device *isp)
 {
 	omap3isp_stat_resume(&isp->isp_aewb);
 	omap3isp_stat_resume(&isp->isp_af);
diff --git a/drivers/media/platform/pxa_camera.c b/drivers/media/platform/pxa_camera.c
index d85ffbfb7c1f..b6e9e93bde7a 100644
--- a/drivers/media/platform/pxa_camera.c
+++ b/drivers/media/platform/pxa_camera.c
@@ -2375,8 +2375,6 @@ static int pxa_camera_probe(struct platform_device *pdev)
 		.src_maxburst = 8,
 		.direction = DMA_DEV_TO_MEM,
 	};
-	dma_cap_mask_t mask;
-	struct pxad_param params;
 	char clk_name[V4L2_CLK_NAME_SIZE];
 	int irq;
 	int err = 0, i;
@@ -2450,34 +2448,20 @@ static int pxa_camera_probe(struct platform_device *pdev)
 	pcdev->base = base;
 
 	/* request dma */
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_SLAVE, mask);
-	dma_cap_set(DMA_PRIVATE, mask);
-
-	params.prio = 0;
-	params.drcmr = 68;
-	pcdev->dma_chans[0] =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &params, &pdev->dev, "CI_Y");
+	pcdev->dma_chans[0] = dma_request_slave_channel(&pdev->dev, "CI_Y");
 	if (!pcdev->dma_chans[0]) {
 		dev_err(&pdev->dev, "Can't request DMA for Y\n");
 		return -ENODEV;
 	}
 
-	params.drcmr = 69;
-	pcdev->dma_chans[1] =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &params, &pdev->dev, "CI_U");
+	pcdev->dma_chans[1] = dma_request_slave_channel(&pdev->dev, "CI_U");
 	if (!pcdev->dma_chans[1]) {
 		dev_err(&pdev->dev, "Can't request DMA for Y\n");
 		err = -ENODEV;
 		goto exit_free_dma_y;
 	}
 
-	params.drcmr = 70;
-	pcdev->dma_chans[2] =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &params, &pdev->dev, "CI_V");
+	pcdev->dma_chans[2] = dma_request_slave_channel(&pdev->dev, "CI_V");
 	if (!pcdev->dma_chans[2]) {
 		dev_err(&pdev->dev, "Can't request DMA for V\n");
 		err = -ENODEV;
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-vfe.h b/drivers/media/platform/qcom/camss-8x16/camss-vfe.h
deleted file mode 100644
index 53d5b66a9dfb..000000000000
--- a/drivers/media/platform/qcom/camss-8x16/camss-vfe.h
+++ /dev/null
@@ -1,123 +0,0 @@
-/*
- * camss-vfe.h
- *
- * Qualcomm MSM Camera Subsystem - VFE (Video Front End) Module
- *
- * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#ifndef QC_MSM_CAMSS_VFE_H
-#define QC_MSM_CAMSS_VFE_H
-
-#include <linux/clk.h>
-#include <linux/spinlock_types.h>
-#include <media/media-entity.h>
-#include <media/v4l2-device.h>
-#include <media/v4l2-subdev.h>
-
-#include "camss-video.h"
-
-#define MSM_VFE_PAD_SINK 0
-#define MSM_VFE_PAD_SRC 1
-#define MSM_VFE_PADS_NUM 2
-
-#define MSM_VFE_LINE_NUM 4
-#define MSM_VFE_IMAGE_MASTERS_NUM 7
-#define MSM_VFE_COMPOSITE_IRQ_NUM 4
-
-#define MSM_VFE_VFE0_UB_SIZE 1023
-#define MSM_VFE_VFE0_UB_SIZE_RDI (MSM_VFE_VFE0_UB_SIZE / 3)
-#define MSM_VFE_VFE1_UB_SIZE 1535
-#define MSM_VFE_VFE1_UB_SIZE_RDI (MSM_VFE_VFE1_UB_SIZE / 3)
-
-enum vfe_output_state {
-	VFE_OUTPUT_OFF,
-	VFE_OUTPUT_RESERVED,
-	VFE_OUTPUT_SINGLE,
-	VFE_OUTPUT_CONTINUOUS,
-	VFE_OUTPUT_IDLE,
-	VFE_OUTPUT_STOPPING
-};
-
-enum vfe_line_id {
-	VFE_LINE_NONE = -1,
-	VFE_LINE_RDI0 = 0,
-	VFE_LINE_RDI1 = 1,
-	VFE_LINE_RDI2 = 2,
-	VFE_LINE_PIX = 3
-};
-
-struct vfe_output {
-	u8 wm_num;
-	u8 wm_idx[3];
-
-	int active_buf;
-	struct camss_buffer *buf[2];
-	struct camss_buffer *last_buffer;
-	struct list_head pending_bufs;
-
-	unsigned int drop_update_idx;
-
-	enum vfe_output_state state;
-	unsigned int sequence;
-	int wait_sof;
-	int wait_reg_update;
-	struct completion sof;
-	struct completion reg_update;
-};
-
-struct vfe_line {
-	enum vfe_line_id id;
-	struct v4l2_subdev subdev;
-	struct media_pad pads[MSM_VFE_PADS_NUM];
-	struct v4l2_mbus_framefmt fmt[MSM_VFE_PADS_NUM];
-	struct v4l2_rect compose;
-	struct v4l2_rect crop;
-	struct camss_video video_out;
-	struct vfe_output output;
-};
-
-struct vfe_device {
-	u8 id;
-	void __iomem *base;
-	u32 irq;
-	char irq_name[30];
-	struct camss_clock *clock;
-	int nclocks;
-	struct completion reset_complete;
-	struct completion halt_complete;
-	struct mutex power_lock;
-	int power_count;
-	struct mutex stream_lock;
-	int stream_count;
-	spinlock_t output_lock;
-	enum vfe_line_id wm_output_map[MSM_VFE_IMAGE_MASTERS_NUM];
-	struct vfe_line line[MSM_VFE_LINE_NUM];
-	u32 reg_update;
-	u8 was_streaming;
-};
-
-struct resources;
-
-int msm_vfe_subdev_init(struct vfe_device *vfe, const struct resources *res);
-
-int msm_vfe_register_entities(struct vfe_device *vfe,
-			      struct v4l2_device *v4l2_dev);
-
-void msm_vfe_unregister_entities(struct vfe_device *vfe);
-
-void msm_vfe_get_vfe_id(struct media_entity *entity, u8 *id);
-void msm_vfe_get_vfe_line_id(struct media_entity *entity, enum vfe_line_id *id);
-
-void msm_vfe_stop_streaming(struct vfe_device *vfe);
-
-#endif /* QC_MSM_CAMSS_VFE_H */
diff --git a/drivers/media/platform/qcom/camss-8x16/Makefile b/drivers/media/platform/qcom/camss/Makefile
index 3c4024fbb768..f5e6e255f2a1 100644
--- a/drivers/media/platform/qcom/camss-8x16/Makefile
+++ b/drivers/media/platform/qcom/camss/Makefile
@@ -3,8 +3,12 @@
 qcom-camss-objs += \
 		camss.o \
 		camss-csid.o \
+		camss-csiphy-2ph-1-0.o \
+		camss-csiphy-3ph-1-0.o \
 		camss-csiphy.o \
 		camss-ispif.o \
+		camss-vfe-4-1.o \
+		camss-vfe-4-7.o \
 		camss-vfe.o \
 		camss-video.o \
 
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-csid.c b/drivers/media/platform/qcom/camss/camss-csid.c
index 226f36ef7419..729b31891466 100644
--- a/drivers/media/platform/qcom/camss-8x16/camss-csid.c
+++ b/drivers/media/platform/qcom/camss/camss-csid.c
@@ -1,19 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * camss-csid.c
  *
  * Qualcomm MSM Camera Subsystem - CSID (CSI Decoder) Module
  *
  * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ * Copyright (C) 2015-2018 Linaro Ltd.
  */
 #include <linux/clk.h>
 #include <linux/completion.h>
@@ -21,9 +13,11 @@
 #include <linux/kernel.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
 #include <media/media-entity.h>
 #include <media/v4l2-device.h>
+#include <media/v4l2-event.h>
 #include <media/v4l2-subdev.h>
 
 #include "camss-csid.h"
@@ -34,21 +28,35 @@
 #define CAMSS_CSID_HW_VERSION		0x0
 #define CAMSS_CSID_CORE_CTRL_0		0x004
 #define CAMSS_CSID_CORE_CTRL_1		0x008
-#define CAMSS_CSID_RST_CMD		0x00c
-#define CAMSS_CSID_CID_LUT_VC_n(n)	(0x010 + 0x4 * (n))
-#define CAMSS_CSID_CID_n_CFG(n)		(0x020 + 0x4 * (n))
-#define CAMSS_CSID_IRQ_CLEAR_CMD	0x060
-#define CAMSS_CSID_IRQ_MASK		0x064
-#define CAMSS_CSID_IRQ_STATUS		0x068
-#define CAMSS_CSID_TG_CTRL		0x0a0
+#define CAMSS_CSID_RST_CMD(v)		((v) == CAMSS_8x16 ? 0x00c : 0x010)
+#define CAMSS_CSID_CID_LUT_VC_n(v, n)	\
+			(((v) == CAMSS_8x16 ? 0x010 : 0x014) + 0x4 * (n))
+#define CAMSS_CSID_CID_n_CFG(v, n)	\
+			(((v) == CAMSS_8x16 ? 0x020 : 0x024) + 0x4 * (n))
+#define CAMSS_CSID_CID_n_CFG_ISPIF_EN	BIT(0)
+#define CAMSS_CSID_CID_n_CFG_RDI_EN	BIT(1)
+#define CAMSS_CSID_CID_n_CFG_DECODE_FORMAT_SHIFT	4
+#define CAMSS_CSID_CID_n_CFG_PLAIN_FORMAT_8		(0 << 8)
+#define CAMSS_CSID_CID_n_CFG_PLAIN_FORMAT_16		(1 << 8)
+#define CAMSS_CSID_CID_n_CFG_PLAIN_ALIGNMENT_LSB	(0 << 9)
+#define CAMSS_CSID_CID_n_CFG_PLAIN_ALIGNMENT_MSB	(1 << 9)
+#define CAMSS_CSID_CID_n_CFG_RDI_MODE_RAW_DUMP		(0 << 10)
+#define CAMSS_CSID_CID_n_CFG_RDI_MODE_PLAIN_PACKING	(1 << 10)
+#define CAMSS_CSID_IRQ_CLEAR_CMD(v)	((v) == CAMSS_8x16 ? 0x060 : 0x064)
+#define CAMSS_CSID_IRQ_MASK(v)		((v) == CAMSS_8x16 ? 0x064 : 0x068)
+#define CAMSS_CSID_IRQ_STATUS(v)	((v) == CAMSS_8x16 ? 0x068 : 0x06c)
+#define CAMSS_CSID_TG_CTRL(v)		((v) == CAMSS_8x16 ? 0x0a0 : 0x0a8)
 #define CAMSS_CSID_TG_CTRL_DISABLE	0xa06436
 #define CAMSS_CSID_TG_CTRL_ENABLE	0xa06437
-#define CAMSS_CSID_TG_VC_CFG		0x0a4
+#define CAMSS_CSID_TG_VC_CFG(v)		((v) == CAMSS_8x16 ? 0x0a4 : 0x0ac)
 #define CAMSS_CSID_TG_VC_CFG_H_BLANKING		0x3ff
 #define CAMSS_CSID_TG_VC_CFG_V_BLANKING		0x7f
-#define CAMSS_CSID_TG_DT_n_CGG_0(n)	(0x0ac + 0xc * (n))
-#define CAMSS_CSID_TG_DT_n_CGG_1(n)	(0x0b0 + 0xc * (n))
-#define CAMSS_CSID_TG_DT_n_CGG_2(n)	(0x0b4 + 0xc * (n))
+#define CAMSS_CSID_TG_DT_n_CGG_0(v, n)	\
+			(((v) == CAMSS_8x16 ? 0x0ac : 0x0b4) + 0xc * (n))
+#define CAMSS_CSID_TG_DT_n_CGG_1(v, n)	\
+			(((v) == CAMSS_8x16 ? 0x0b0 : 0x0b8) + 0xc * (n))
+#define CAMSS_CSID_TG_DT_n_CGG_2(v, n)	\
+			(((v) == CAMSS_8x16 ? 0x0b4 : 0x0bc) + 0xc * (n))
 
 #define DATA_TYPE_EMBEDDED_DATA_8BIT	0x12
 #define DATA_TYPE_YUV422_8BIT		0x1e
@@ -56,15 +64,17 @@
 #define DATA_TYPE_RAW_8BIT		0x2a
 #define DATA_TYPE_RAW_10BIT		0x2b
 #define DATA_TYPE_RAW_12BIT		0x2c
+#define DATA_TYPE_RAW_14BIT		0x2d
 
 #define DECODE_FORMAT_UNCOMPRESSED_6_BIT	0x0
 #define DECODE_FORMAT_UNCOMPRESSED_8_BIT	0x1
 #define DECODE_FORMAT_UNCOMPRESSED_10_BIT	0x2
 #define DECODE_FORMAT_UNCOMPRESSED_12_BIT	0x3
+#define DECODE_FORMAT_UNCOMPRESSED_14_BIT	0x8
 
 #define CSID_RESET_TIMEOUT_MS 500
 
-struct csid_fmts {
+struct csid_format {
 	u32 code;
 	u8 data_type;
 	u8 decode_format;
@@ -72,7 +82,7 @@ struct csid_fmts {
 	u8 spp; /* bus samples per pixel */
 };
 
-static const struct csid_fmts csid_input_fmts[] = {
+static const struct csid_format csid_formats_8x16[] = {
 	{
 		MEDIA_BUS_FMT_UYVY8_2X8,
 		DATA_TYPE_YUV422_8BIT,
@@ -184,20 +194,241 @@ static const struct csid_fmts csid_input_fmts[] = {
 		DECODE_FORMAT_UNCOMPRESSED_12_BIT,
 		12,
 		1,
-	}
+	},
+	{
+		MEDIA_BUS_FMT_Y10_1X10,
+		DATA_TYPE_RAW_10BIT,
+		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
+		10,
+		1,
+	},
 };
 
-static const struct csid_fmts *csid_get_fmt_entry(u32 code)
+static const struct csid_format csid_formats_8x96[] = {
+	{
+		MEDIA_BUS_FMT_UYVY8_2X8,
+		DATA_TYPE_YUV422_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		2,
+	},
+	{
+		MEDIA_BUS_FMT_VYUY8_2X8,
+		DATA_TYPE_YUV422_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		2,
+	},
+	{
+		MEDIA_BUS_FMT_YUYV8_2X8,
+		DATA_TYPE_YUV422_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		2,
+	},
+	{
+		MEDIA_BUS_FMT_YVYU8_2X8,
+		DATA_TYPE_YUV422_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		2,
+	},
+	{
+		MEDIA_BUS_FMT_SBGGR8_1X8,
+		DATA_TYPE_RAW_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGBRG8_1X8,
+		DATA_TYPE_RAW_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGRBG8_1X8,
+		DATA_TYPE_RAW_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SRGGB8_1X8,
+		DATA_TYPE_RAW_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SBGGR10_1X10,
+		DATA_TYPE_RAW_10BIT,
+		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
+		10,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGBRG10_1X10,
+		DATA_TYPE_RAW_10BIT,
+		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
+		10,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGRBG10_1X10,
+		DATA_TYPE_RAW_10BIT,
+		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
+		10,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SRGGB10_1X10,
+		DATA_TYPE_RAW_10BIT,
+		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
+		10,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SBGGR12_1X12,
+		DATA_TYPE_RAW_12BIT,
+		DECODE_FORMAT_UNCOMPRESSED_12_BIT,
+		12,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGBRG12_1X12,
+		DATA_TYPE_RAW_12BIT,
+		DECODE_FORMAT_UNCOMPRESSED_12_BIT,
+		12,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGRBG12_1X12,
+		DATA_TYPE_RAW_12BIT,
+		DECODE_FORMAT_UNCOMPRESSED_12_BIT,
+		12,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SRGGB12_1X12,
+		DATA_TYPE_RAW_12BIT,
+		DECODE_FORMAT_UNCOMPRESSED_12_BIT,
+		12,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SBGGR14_1X14,
+		DATA_TYPE_RAW_14BIT,
+		DECODE_FORMAT_UNCOMPRESSED_14_BIT,
+		14,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGBRG14_1X14,
+		DATA_TYPE_RAW_14BIT,
+		DECODE_FORMAT_UNCOMPRESSED_14_BIT,
+		14,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGRBG14_1X14,
+		DATA_TYPE_RAW_14BIT,
+		DECODE_FORMAT_UNCOMPRESSED_14_BIT,
+		14,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SRGGB14_1X14,
+		DATA_TYPE_RAW_14BIT,
+		DECODE_FORMAT_UNCOMPRESSED_14_BIT,
+		14,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_Y10_1X10,
+		DATA_TYPE_RAW_10BIT,
+		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
+		10,
+		1,
+	},
+};
+
+static u32 csid_find_code(u32 *code, unsigned int n_code,
+			  unsigned int index, u32 req_code)
+{
+	int i;
+
+	if (!req_code && (index >= n_code))
+		return 0;
+
+	for (i = 0; i < n_code; i++)
+		if (req_code) {
+			if (req_code == code[i])
+				return req_code;
+		} else {
+			if (i == index)
+				return code[i];
+		}
+
+	return code[0];
+}
+
+static u32 csid_src_pad_code(struct csid_device *csid, u32 sink_code,
+			     unsigned int index, u32 src_req_code)
+{
+	if (csid->camss->version == CAMSS_8x16) {
+		if (index > 0)
+			return 0;
+
+		return sink_code;
+	} else if (csid->camss->version == CAMSS_8x96) {
+		switch (sink_code) {
+		case MEDIA_BUS_FMT_SBGGR10_1X10:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_SBGGR10_1X10,
+				MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE,
+			};
+
+			return csid_find_code(src_code, ARRAY_SIZE(src_code),
+					      index, src_req_code);
+		}
+		case MEDIA_BUS_FMT_Y10_1X10:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_Y10_1X10,
+				MEDIA_BUS_FMT_Y10_2X8_PADHI_LE,
+			};
+
+			return csid_find_code(src_code, ARRAY_SIZE(src_code),
+					      index, src_req_code);
+		}
+		default:
+			if (index > 0)
+				return 0;
+
+			return sink_code;
+		}
+	} else {
+		return 0;
+	}
+}
+
+static const struct csid_format *csid_get_fmt_entry(
+					const struct csid_format *formats,
+					unsigned int nformat,
+					u32 code)
 {
 	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(csid_input_fmts); i++)
-		if (code == csid_input_fmts[i].code)
-			return &csid_input_fmts[i];
+	for (i = 0; i < nformat; i++)
+		if (code == formats[i].code)
+			return &formats[i];
 
 	WARN(1, "Unknown format\n");
 
-	return &csid_input_fmts[0];
+	return &formats[0];
 }
 
 /*
@@ -210,10 +441,11 @@ static const struct csid_fmts *csid_get_fmt_entry(u32 code)
 static irqreturn_t csid_isr(int irq, void *dev)
 {
 	struct csid_device *csid = dev;
+	enum camss_version ver = csid->camss->version;
 	u32 value;
 
-	value = readl_relaxed(csid->base + CAMSS_CSID_IRQ_STATUS);
-	writel_relaxed(value, csid->base + CAMSS_CSID_IRQ_CLEAR_CMD);
+	value = readl_relaxed(csid->base + CAMSS_CSID_IRQ_STATUS(ver));
+	writel_relaxed(value, csid->base + CAMSS_CSID_IRQ_CLEAR_CMD(ver));
 
 	if ((value >> 11) & 0x1)
 		complete(&csid->reset_complete);
@@ -227,7 +459,7 @@ static irqreturn_t csid_isr(int irq, void *dev)
  */
 static int csid_set_clock_rates(struct csid_device *csid)
 {
-	struct device *dev = to_device_index(csid, csid->id);
+	struct device *dev = csid->camss->dev;
 	u32 pixel_clock;
 	int i, j;
 	int ret;
@@ -240,11 +472,16 @@ static int csid_set_clock_rates(struct csid_device *csid)
 		struct camss_clock *clock = &csid->clock[i];
 
 		if (!strcmp(clock->name, "csi0") ||
-			!strcmp(clock->name, "csi1")) {
-			u8 bpp = csid_get_fmt_entry(
-				csid->fmt[MSM_CSIPHY_PAD_SINK].code)->bpp;
+		    !strcmp(clock->name, "csi1") ||
+		    !strcmp(clock->name, "csi2") ||
+		    !strcmp(clock->name, "csi3")) {
+			const struct csid_format *f = csid_get_fmt_entry(
+				csid->formats,
+				csid->nformats,
+				csid->fmt[MSM_CSIPHY_PAD_SINK].code);
 			u8 num_lanes = csid->phy.lane_cnt;
-			u64 min_rate = pixel_clock * bpp / (2 * num_lanes * 4);
+			u64 min_rate = pixel_clock * f->bpp /
+							(2 * num_lanes * 4);
 			long rate;
 
 			camss_add_clock_margin(&min_rate);
@@ -294,13 +531,13 @@ static int csid_reset(struct csid_device *csid)
 
 	reinit_completion(&csid->reset_complete);
 
-	writel_relaxed(0x7fff, csid->base + CAMSS_CSID_RST_CMD);
+	writel_relaxed(0x7fff, csid->base +
+		       CAMSS_CSID_RST_CMD(csid->camss->version));
 
 	time = wait_for_completion_timeout(&csid->reset_complete,
 		msecs_to_jiffies(CSID_RESET_TIMEOUT_MS));
 	if (!time) {
-		dev_err(to_device_index(csid, csid->id),
-			"CSID reset timeout\n");
+		dev_err(csid->camss->dev, "CSID reset timeout\n");
 		return -EIO;
 	}
 
@@ -317,25 +554,33 @@ static int csid_reset(struct csid_device *csid)
 static int csid_set_power(struct v4l2_subdev *sd, int on)
 {
 	struct csid_device *csid = v4l2_get_subdevdata(sd);
-	struct device *dev = to_device_index(csid, csid->id);
+	struct device *dev = csid->camss->dev;
 	int ret;
 
 	if (on) {
 		u32 hw_version;
 
-		ret = regulator_enable(csid->vdda);
+		ret = pm_runtime_get_sync(dev);
 		if (ret < 0)
 			return ret;
 
+		ret = regulator_enable(csid->vdda);
+		if (ret < 0) {
+			pm_runtime_put_sync(dev);
+			return ret;
+		}
+
 		ret = csid_set_clock_rates(csid);
 		if (ret < 0) {
 			regulator_disable(csid->vdda);
+			pm_runtime_put_sync(dev);
 			return ret;
 		}
 
 		ret = camss_enable_clocks(csid->nclocks, csid->clock, dev);
 		if (ret < 0) {
 			regulator_disable(csid->vdda);
+			pm_runtime_put_sync(dev);
 			return ret;
 		}
 
@@ -346,6 +591,7 @@ static int csid_set_power(struct v4l2_subdev *sd, int on)
 			disable_irq(csid->irq);
 			camss_disable_clocks(csid->nclocks, csid->clock);
 			regulator_disable(csid->vdda);
+			pm_runtime_put_sync(dev);
 			return ret;
 		}
 
@@ -355,6 +601,7 @@ static int csid_set_power(struct v4l2_subdev *sd, int on)
 		disable_irq(csid->irq);
 		camss_disable_clocks(csid->nclocks, csid->clock);
 		ret = regulator_disable(csid->vdda);
+		pm_runtime_put_sync(dev);
 	}
 
 	return ret;
@@ -373,6 +620,7 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 {
 	struct csid_device *csid = v4l2_get_subdevdata(sd);
 	struct csid_testgen_config *tg = &csid->testgen;
+	enum camss_version ver = csid->camss->version;
 	u32 val;
 
 	if (enable) {
@@ -383,7 +631,7 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 
 		ret = v4l2_ctrl_handler_setup(&csid->ctrls);
 		if (ret < 0) {
-			dev_err(to_device_index(csid, csid->id),
+			dev_err(csid->camss->dev,
 				"could not sync v4l2 controls: %d\n", ret);
 			return ret;
 		}
@@ -392,40 +640,47 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 		    !media_entity_remote_pad(&csid->pads[MSM_CSID_PAD_SINK]))
 			return -ENOLINK;
 
-		dt = csid_get_fmt_entry(csid->fmt[MSM_CSID_PAD_SRC].code)->
-								data_type;
-
 		if (tg->enabled) {
 			/* Config Test Generator */
 			struct v4l2_mbus_framefmt *f =
 					&csid->fmt[MSM_CSID_PAD_SRC];
-			u8 bpp = csid_get_fmt_entry(f->code)->bpp;
-			u8 spp = csid_get_fmt_entry(f->code)->spp;
-			u32 num_bytes_per_line = f->width * bpp * spp / 8;
+			const struct csid_format *format = csid_get_fmt_entry(
+					csid->formats, csid->nformats, f->code);
+			u32 num_bytes_per_line =
+				f->width * format->bpp * format->spp / 8;
 			u32 num_lines = f->height;
 
 			/* 31:24 V blank, 23:13 H blank, 3:2 num of active DT */
 			/* 1:0 VC */
 			val = ((CAMSS_CSID_TG_VC_CFG_V_BLANKING & 0xff) << 24) |
 			      ((CAMSS_CSID_TG_VC_CFG_H_BLANKING & 0x7ff) << 13);
-			writel_relaxed(val, csid->base + CAMSS_CSID_TG_VC_CFG);
+			writel_relaxed(val, csid->base +
+				       CAMSS_CSID_TG_VC_CFG(ver));
 
 			/* 28:16 bytes per lines, 12:0 num of lines */
 			val = ((num_bytes_per_line & 0x1fff) << 16) |
 			      (num_lines & 0x1fff);
 			writel_relaxed(val, csid->base +
-				       CAMSS_CSID_TG_DT_n_CGG_0(0));
+				       CAMSS_CSID_TG_DT_n_CGG_0(ver, 0));
+
+			dt = format->data_type;
 
 			/* 5:0 data type */
 			val = dt;
 			writel_relaxed(val, csid->base +
-				       CAMSS_CSID_TG_DT_n_CGG_1(0));
+				       CAMSS_CSID_TG_DT_n_CGG_1(ver, 0));
 
 			/* 2:0 output test pattern */
 			val = tg->payload_mode;
 			writel_relaxed(val, csid->base +
-				       CAMSS_CSID_TG_DT_n_CGG_2(0));
+				       CAMSS_CSID_TG_DT_n_CGG_2(ver, 0));
+
+			df = format->decode_format;
 		} else {
+			struct v4l2_mbus_framefmt *f =
+					&csid->fmt[MSM_CSID_PAD_SINK];
+			const struct csid_format *format = csid_get_fmt_entry(
+					csid->formats, csid->nformats, f->code);
 			struct csid_phy_config *phy = &csid->phy;
 
 			val = phy->lane_cnt - 1;
@@ -439,30 +694,54 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 
 			writel_relaxed(val,
 				       csid->base + CAMSS_CSID_CORE_CTRL_1);
+
+			dt = format->data_type;
+			df = format->decode_format;
 		}
 
 		/* Config LUT */
 
 		dt_shift = (cid % 4) * 8;
-		df = csid_get_fmt_entry(csid->fmt[MSM_CSID_PAD_SINK].code)->
-								decode_format;
 
-		val = readl_relaxed(csid->base + CAMSS_CSID_CID_LUT_VC_n(vc));
+		val = readl_relaxed(csid->base +
+				    CAMSS_CSID_CID_LUT_VC_n(ver, vc));
 		val &= ~(0xff << dt_shift);
 		val |= dt << dt_shift;
-		writel_relaxed(val, csid->base + CAMSS_CSID_CID_LUT_VC_n(vc));
+		writel_relaxed(val, csid->base +
+			       CAMSS_CSID_CID_LUT_VC_n(ver, vc));
+
+		val = CAMSS_CSID_CID_n_CFG_ISPIF_EN;
+		val |= CAMSS_CSID_CID_n_CFG_RDI_EN;
+		val |= df << CAMSS_CSID_CID_n_CFG_DECODE_FORMAT_SHIFT;
+		val |= CAMSS_CSID_CID_n_CFG_RDI_MODE_RAW_DUMP;
+
+		if (csid->camss->version == CAMSS_8x96) {
+			u32 sink_code = csid->fmt[MSM_CSID_PAD_SINK].code;
+			u32 src_code = csid->fmt[MSM_CSID_PAD_SRC].code;
+
+			if ((sink_code == MEDIA_BUS_FMT_SBGGR10_1X10 &&
+			     src_code == MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE) ||
+			    (sink_code == MEDIA_BUS_FMT_Y10_1X10 &&
+			     src_code == MEDIA_BUS_FMT_Y10_2X8_PADHI_LE)) {
+				val |= CAMSS_CSID_CID_n_CFG_RDI_MODE_PLAIN_PACKING;
+				val |= CAMSS_CSID_CID_n_CFG_PLAIN_FORMAT_16;
+				val |= CAMSS_CSID_CID_n_CFG_PLAIN_ALIGNMENT_LSB;
+			}
+		}
 
-		val = (df << 4) | 0x3;
-		writel_relaxed(val, csid->base + CAMSS_CSID_CID_n_CFG(cid));
+		writel_relaxed(val, csid->base +
+			       CAMSS_CSID_CID_n_CFG(ver, cid));
 
 		if (tg->enabled) {
 			val = CAMSS_CSID_TG_CTRL_ENABLE;
-			writel_relaxed(val, csid->base + CAMSS_CSID_TG_CTRL);
+			writel_relaxed(val, csid->base +
+				       CAMSS_CSID_TG_CTRL(ver));
 		}
 	} else {
 		if (tg->enabled) {
 			val = CAMSS_CSID_TG_CTRL_DISABLE;
-			writel_relaxed(val, csid->base + CAMSS_CSID_TG_CTRL);
+			writel_relaxed(val, csid->base +
+				       CAMSS_CSID_TG_CTRL(ver));
 		}
 	}
 
@@ -510,12 +789,12 @@ static void csid_try_format(struct csid_device *csid,
 	case MSM_CSID_PAD_SINK:
 		/* Set format on sink pad */
 
-		for (i = 0; i < ARRAY_SIZE(csid_input_fmts); i++)
-			if (fmt->code == csid_input_fmts[i].code)
+		for (i = 0; i < csid->nformats; i++)
+			if (fmt->code == csid->formats[i].code)
 				break;
 
 		/* If not found, use UYVY as default */
-		if (i >= ARRAY_SIZE(csid_input_fmts))
+		if (i >= csid->nformats)
 			fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
 
 		fmt->width = clamp_t(u32, fmt->width, 1, 8191);
@@ -528,23 +807,23 @@ static void csid_try_format(struct csid_device *csid,
 
 	case MSM_CSID_PAD_SRC:
 		if (csid->testgen_mode->cur.val == 0) {
-			/* Test generator is disabled, keep pad formats */
-			/* in sync - set and return a format same as sink pad */
-			struct v4l2_mbus_framefmt format;
+			/* Test generator is disabled, */
+			/* keep pad formats in sync */
+			u32 code = fmt->code;
 
-			format = *__csid_get_format(csid, cfg,
-						    MSM_CSID_PAD_SINK, which);
-			*fmt = format;
+			*fmt = *__csid_get_format(csid, cfg,
+						      MSM_CSID_PAD_SINK, which);
+			fmt->code = csid_src_pad_code(csid, fmt->code, 0, code);
 		} else {
-			/* Test generator is enabled, set format on source*/
+			/* Test generator is enabled, set format on source */
 			/* pad to allow test generator usage */
 
-			for (i = 0; i < ARRAY_SIZE(csid_input_fmts); i++)
-				if (csid_input_fmts[i].code == fmt->code)
+			for (i = 0; i < csid->nformats; i++)
+				if (csid->formats[i].code == fmt->code)
 					break;
 
 			/* If not found, use UYVY as default */
-			if (i >= ARRAY_SIZE(csid_input_fmts))
+			if (i >= csid->nformats)
 				fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
 
 			fmt->width = clamp_t(u32, fmt->width, 1, 8191);
@@ -570,27 +849,29 @@ static int csid_enum_mbus_code(struct v4l2_subdev *sd,
 			       struct v4l2_subdev_mbus_code_enum *code)
 {
 	struct csid_device *csid = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt *format;
 
 	if (code->pad == MSM_CSID_PAD_SINK) {
-		if (code->index >= ARRAY_SIZE(csid_input_fmts))
+		if (code->index >= csid->nformats)
 			return -EINVAL;
 
-		code->code = csid_input_fmts[code->index].code;
+		code->code = csid->formats[code->index].code;
 	} else {
 		if (csid->testgen_mode->cur.val == 0) {
-			if (code->index > 0)
-				return -EINVAL;
+			struct v4l2_mbus_framefmt *sink_fmt;
 
-			format = __csid_get_format(csid, cfg, MSM_CSID_PAD_SINK,
-						   code->which);
+			sink_fmt = __csid_get_format(csid, cfg,
+						     MSM_CSID_PAD_SINK,
+						     code->which);
 
-			code->code = format->code;
+			code->code = csid_src_pad_code(csid, sink_fmt->code,
+						       code->index, 0);
+			if (!code->code)
+				return -EINVAL;
 		} else {
-			if (code->index >= ARRAY_SIZE(csid_input_fmts))
+			if (code->index >= csid->nformats)
 				return -EINVAL;
 
-			code->code = csid_input_fmts[code->index].code;
+			code->code = csid->formats[code->index].code;
 		}
 	}
 
@@ -798,17 +1079,30 @@ static const struct v4l2_ctrl_ops csid_ctrl_ops = {
  *
  * Return 0 on success or a negative error code otherwise
  */
-int msm_csid_subdev_init(struct csid_device *csid,
+int msm_csid_subdev_init(struct camss *camss, struct csid_device *csid,
 			 const struct resources *res, u8 id)
 {
-	struct device *dev = to_device_index(csid, id);
+	struct device *dev = camss->dev;
 	struct platform_device *pdev = to_platform_device(dev);
 	struct resource *r;
 	int i, j;
 	int ret;
 
+	csid->camss = camss;
 	csid->id = id;
 
+	if (camss->version == CAMSS_8x16) {
+		csid->formats = csid_formats_8x16;
+		csid->nformats =
+				ARRAY_SIZE(csid_formats_8x16);
+	} else if (camss->version == CAMSS_8x96) {
+		csid->formats = csid_formats_8x96;
+		csid->nformats =
+				ARRAY_SIZE(csid_formats_8x96);
+	} else {
+		return -EINVAL;
+	}
+
 	/* Memory */
 
 	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[0]);
@@ -980,6 +1274,8 @@ static int csid_link_setup(struct media_entity *entity,
 
 static const struct v4l2_subdev_core_ops csid_core_ops = {
 	.s_power = csid_set_power,
+	.subscribe_event = v4l2_ctrl_subdev_subscribe_event,
+	.unsubscribe_event = v4l2_event_subdev_unsubscribe,
 };
 
 static const struct v4l2_subdev_video_ops csid_video_ops = {
@@ -1020,12 +1316,13 @@ int msm_csid_register_entity(struct csid_device *csid,
 {
 	struct v4l2_subdev *sd = &csid->subdev;
 	struct media_pad *pads = csid->pads;
-	struct device *dev = to_device_index(csid, csid->id);
+	struct device *dev = csid->camss->dev;
 	int ret;
 
 	v4l2_subdev_init(sd, &csid_v4l2_ops);
 	sd->internal_ops = &csid_v4l2_internal_ops;
-	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
+	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE |
+		     V4L2_SUBDEV_FL_HAS_EVENTS;
 	snprintf(sd->name, ARRAY_SIZE(sd->name), "%s%d",
 		 MSM_CSID_NAME, csid->id);
 	v4l2_set_subdevdata(sd, csid);
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-csid.h b/drivers/media/platform/qcom/camss/camss-csid.h
index 8682d3081bc3..1824b3745e10 100644
--- a/drivers/media/platform/qcom/camss-8x16/camss-csid.h
+++ b/drivers/media/platform/qcom/camss/camss-csid.h
@@ -1,19 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * camss-csid.h
  *
  * Qualcomm MSM Camera Subsystem - CSID (CSI Decoder) Module
  *
  * Copyright (c) 2011-2014, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ * Copyright (C) 2015-2018 Linaro Ltd.
  */
 #ifndef QC_MSM_CAMSS_CSID_H
 #define QC_MSM_CAMSS_CSID_H
@@ -50,6 +42,7 @@ struct csid_phy_config {
 };
 
 struct csid_device {
+	struct camss *camss;
 	u8 id;
 	struct v4l2_subdev subdev;
 	struct media_pad pads[MSM_CSID_PADS_NUM];
@@ -65,11 +58,13 @@ struct csid_device {
 	struct v4l2_mbus_framefmt fmt[MSM_CSID_PADS_NUM];
 	struct v4l2_ctrl_handler ctrls;
 	struct v4l2_ctrl *testgen_mode;
+	const struct csid_format *formats;
+	unsigned int nformats;
 };
 
 struct resources;
 
-int msm_csid_subdev_init(struct csid_device *csid,
+int msm_csid_subdev_init(struct camss *camss, struct csid_device *csid,
 			 const struct resources *res, u8 id);
 
 int msm_csid_register_entity(struct csid_device *csid,
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy-2ph-1-0.c b/drivers/media/platform/qcom/camss/camss-csiphy-2ph-1-0.c
new file mode 100644
index 000000000000..c832539397d7
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss-csiphy-2ph-1-0.c
@@ -0,0 +1,176 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * camss-csiphy-2ph-1-0.c
+ *
+ * Qualcomm MSM Camera Subsystem - CSIPHY Module 2phase v1.0
+ *
+ * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2016-2018 Linaro Ltd.
+ */
+
+#include "camss-csiphy.h"
+
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+
+#define CAMSS_CSI_PHY_LNn_CFG2(n)		(0x004 + 0x40 * (n))
+#define CAMSS_CSI_PHY_LNn_CFG3(n)		(0x008 + 0x40 * (n))
+#define CAMSS_CSI_PHY_GLBL_RESET		0x140
+#define CAMSS_CSI_PHY_GLBL_PWR_CFG		0x144
+#define CAMSS_CSI_PHY_GLBL_IRQ_CMD		0x164
+#define CAMSS_CSI_PHY_HW_VERSION		0x188
+#define CAMSS_CSI_PHY_INTERRUPT_STATUSn(n)	(0x18c + 0x4 * (n))
+#define CAMSS_CSI_PHY_INTERRUPT_MASKn(n)	(0x1ac + 0x4 * (n))
+#define CAMSS_CSI_PHY_INTERRUPT_CLEARn(n)	(0x1cc + 0x4 * (n))
+#define CAMSS_CSI_PHY_GLBL_T_INIT_CFG0		0x1ec
+#define CAMSS_CSI_PHY_T_WAKEUP_CFG0		0x1f4
+
+static void csiphy_hw_version_read(struct csiphy_device *csiphy,
+				   struct device *dev)
+{
+	u8 hw_version = readl_relaxed(csiphy->base +
+				      CAMSS_CSI_PHY_HW_VERSION);
+
+	dev_dbg(dev, "CSIPHY HW Version = 0x%02x\n", hw_version);
+}
+
+/*
+ * csiphy_reset - Perform software reset on CSIPHY module
+ * @csiphy: CSIPHY device
+ */
+static void csiphy_reset(struct csiphy_device *csiphy)
+{
+	writel_relaxed(0x1, csiphy->base + CAMSS_CSI_PHY_GLBL_RESET);
+	usleep_range(5000, 8000);
+	writel_relaxed(0x0, csiphy->base + CAMSS_CSI_PHY_GLBL_RESET);
+}
+
+/*
+ * csiphy_settle_cnt_calc - Calculate settle count value
+ *
+ * Helper function to calculate settle count value. This is
+ * based on the CSI2 T_hs_settle parameter which in turn
+ * is calculated based on the CSI2 transmitter pixel clock
+ * frequency.
+ *
+ * Return settle count value or 0 if the CSI2 pixel clock
+ * frequency is not available
+ */
+static u8 csiphy_settle_cnt_calc(u32 pixel_clock, u8 bpp, u8 num_lanes,
+				 u32 timer_clk_rate)
+{
+	u32 mipi_clock; /* Hz */
+	u32 ui; /* ps */
+	u32 timer_period; /* ps */
+	u32 t_hs_prepare_max; /* ps */
+	u32 t_hs_prepare_zero_min; /* ps */
+	u32 t_hs_settle; /* ps */
+	u8 settle_cnt;
+
+	mipi_clock = pixel_clock * bpp / (2 * num_lanes);
+	ui = div_u64(1000000000000LL, mipi_clock);
+	ui /= 2;
+	t_hs_prepare_max = 85000 + 6 * ui;
+	t_hs_prepare_zero_min = 145000 + 10 * ui;
+	t_hs_settle = (t_hs_prepare_max + t_hs_prepare_zero_min) / 2;
+
+	timer_period = div_u64(1000000000000LL, timer_clk_rate);
+	settle_cnt = t_hs_settle / timer_period - 1;
+
+	return settle_cnt;
+}
+
+static void csiphy_lanes_enable(struct csiphy_device *csiphy,
+				struct csiphy_config *cfg,
+				u32 pixel_clock, u8 bpp, u8 lane_mask)
+{
+	struct csiphy_lanes_cfg *c = &cfg->csi2->lane_cfg;
+	u8 settle_cnt;
+	u8 val, l = 0;
+	int i = 0;
+
+	settle_cnt = csiphy_settle_cnt_calc(pixel_clock, bpp, c->num_data,
+					    csiphy->timer_clk_rate);
+
+	writel_relaxed(0x1, csiphy->base +
+		       CAMSS_CSI_PHY_GLBL_T_INIT_CFG0);
+	writel_relaxed(0x1, csiphy->base +
+		       CAMSS_CSI_PHY_T_WAKEUP_CFG0);
+
+	val = 0x1;
+	val |= lane_mask << 1;
+	writel_relaxed(val, csiphy->base + CAMSS_CSI_PHY_GLBL_PWR_CFG);
+
+	val = cfg->combo_mode << 4;
+	writel_relaxed(val, csiphy->base + CAMSS_CSI_PHY_GLBL_RESET);
+
+	for (i = 0; i <= c->num_data; i++) {
+		if (i == c->num_data)
+			l = c->clk.pos;
+		else
+			l = c->data[i].pos;
+
+		writel_relaxed(0x10, csiphy->base +
+			       CAMSS_CSI_PHY_LNn_CFG2(l));
+		writel_relaxed(settle_cnt, csiphy->base +
+			       CAMSS_CSI_PHY_LNn_CFG3(l));
+		writel_relaxed(0x3f, csiphy->base +
+			       CAMSS_CSI_PHY_INTERRUPT_MASKn(l));
+		writel_relaxed(0x3f, csiphy->base +
+			       CAMSS_CSI_PHY_INTERRUPT_CLEARn(l));
+	}
+}
+
+static void csiphy_lanes_disable(struct csiphy_device *csiphy,
+				 struct csiphy_config *cfg)
+{
+	struct csiphy_lanes_cfg *c = &cfg->csi2->lane_cfg;
+	u8 l = 0;
+	int i = 0;
+
+	for (i = 0; i <= c->num_data; i++) {
+		if (i == c->num_data)
+			l = c->clk.pos;
+		else
+			l = c->data[i].pos;
+
+		writel_relaxed(0x0, csiphy->base +
+			       CAMSS_CSI_PHY_LNn_CFG2(l));
+	}
+
+	writel_relaxed(0x0, csiphy->base + CAMSS_CSI_PHY_GLBL_PWR_CFG);
+}
+
+/*
+ * csiphy_isr - CSIPHY module interrupt handler
+ * @irq: Interrupt line
+ * @dev: CSIPHY device
+ *
+ * Return IRQ_HANDLED on success
+ */
+static irqreturn_t csiphy_isr(int irq, void *dev)
+{
+	struct csiphy_device *csiphy = dev;
+	u8 i;
+
+	for (i = 0; i < 8; i++) {
+		u8 val = readl_relaxed(csiphy->base +
+				       CAMSS_CSI_PHY_INTERRUPT_STATUSn(i));
+		writel_relaxed(val, csiphy->base +
+			       CAMSS_CSI_PHY_INTERRUPT_CLEARn(i));
+		writel_relaxed(0x1, csiphy->base + CAMSS_CSI_PHY_GLBL_IRQ_CMD);
+		writel_relaxed(0x0, csiphy->base + CAMSS_CSI_PHY_GLBL_IRQ_CMD);
+		writel_relaxed(0x0, csiphy->base +
+			       CAMSS_CSI_PHY_INTERRUPT_CLEARn(i));
+	}
+
+	return IRQ_HANDLED;
+}
+
+const struct csiphy_hw_ops csiphy_ops_2ph_1_0 = {
+	.hw_version_read = csiphy_hw_version_read,
+	.reset = csiphy_reset,
+	.lanes_enable = csiphy_lanes_enable,
+	.lanes_disable = csiphy_lanes_disable,
+	.isr = csiphy_isr,
+};
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c b/drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c
new file mode 100644
index 000000000000..bcd0dfd33618
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c
@@ -0,0 +1,256 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * camss-csiphy-3ph-1-0.c
+ *
+ * Qualcomm MSM Camera Subsystem - CSIPHY Module 3phase v1.0
+ *
+ * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2016-2018 Linaro Ltd.
+ */
+
+#include "camss-csiphy.h"
+
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+
+#define CSIPHY_3PH_LNn_CFG1(n)			(0x000 + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CFG1_SWI_REC_DLY_PRG	(BIT(7) | BIT(6))
+#define CSIPHY_3PH_LNn_CFG2(n)			(0x004 + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CFG2_LP_REC_EN_INT	BIT(3)
+#define CSIPHY_3PH_LNn_CFG3(n)			(0x008 + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CFG4(n)			(0x00c + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CFG4_T_HS_CLK_MISS	0xa4
+#define CSIPHY_3PH_LNn_CFG5(n)			(0x010 + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CFG5_T_HS_DTERM		0x02
+#define CSIPHY_3PH_LNn_CFG5_HS_REC_EQ_FQ_INT	0x50
+#define CSIPHY_3PH_LNn_TEST_IMP(n)		(0x01c + 0x100 * (n))
+#define CSIPHY_3PH_LNn_TEST_IMP_HS_TERM_IMP	0xa
+#define CSIPHY_3PH_LNn_MISC1(n)			(0x028 + 0x100 * (n))
+#define CSIPHY_3PH_LNn_MISC1_IS_CLKLANE		BIT(2)
+#define CSIPHY_3PH_LNn_CFG6(n)			(0x02c + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CFG6_SWI_FORCE_INIT_EXIT	BIT(0)
+#define CSIPHY_3PH_LNn_CFG7(n)			(0x030 + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CFG7_SWI_T_INIT		0x2
+#define CSIPHY_3PH_LNn_CFG8(n)			(0x034 + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CFG8_SWI_SKIP_WAKEUP	BIT(0)
+#define CSIPHY_3PH_LNn_CFG8_SKEW_FILTER_ENABLE	BIT(1)
+#define CSIPHY_3PH_LNn_CFG9(n)			(0x038 + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CFG9_SWI_T_WAKEUP	0x1
+#define CSIPHY_3PH_LNn_CSI_LANE_CTRL15(n)	(0x03c + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CSI_LANE_CTRL15_SWI_SOT_SYMBOL	0xb8
+
+#define CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(n)	(0x800 + 0x4 * (n))
+#define CSIPHY_3PH_CMN_CSI_COMMON_CTRL6_COMMON_PWRDN_B	BIT(0)
+#define CSIPHY_3PH_CMN_CSI_COMMON_CTRL6_SHOW_REV_ID	BIT(1)
+#define CSIPHY_3PH_CMN_CSI_COMMON_STATUSn(n)	(0x8b0 + 0x4 * (n))
+
+static void csiphy_hw_version_read(struct csiphy_device *csiphy,
+				   struct device *dev)
+{
+	u32 hw_version;
+
+	writel(CSIPHY_3PH_CMN_CSI_COMMON_CTRL6_SHOW_REV_ID,
+	       csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(6));
+
+	hw_version = readl_relaxed(csiphy->base +
+				   CSIPHY_3PH_CMN_CSI_COMMON_STATUSn(12));
+	hw_version |= readl_relaxed(csiphy->base +
+				   CSIPHY_3PH_CMN_CSI_COMMON_STATUSn(13)) << 8;
+	hw_version |= readl_relaxed(csiphy->base +
+				   CSIPHY_3PH_CMN_CSI_COMMON_STATUSn(14)) << 16;
+	hw_version |= readl_relaxed(csiphy->base +
+				   CSIPHY_3PH_CMN_CSI_COMMON_STATUSn(15)) << 24;
+
+	dev_err(dev, "CSIPHY 3PH HW Version = 0x%08x\n", hw_version);
+}
+
+/*
+ * csiphy_reset - Perform software reset on CSIPHY module
+ * @csiphy: CSIPHY device
+ */
+static void csiphy_reset(struct csiphy_device *csiphy)
+{
+	writel_relaxed(0x1, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(0));
+	usleep_range(5000, 8000);
+	writel_relaxed(0x0, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(0));
+}
+
+static irqreturn_t csiphy_isr(int irq, void *dev)
+{
+	struct csiphy_device *csiphy = dev;
+	int i;
+
+	for (i = 0; i < 11; i++) {
+		int c = i + 22;
+		u8 val = readl_relaxed(csiphy->base +
+				       CSIPHY_3PH_CMN_CSI_COMMON_STATUSn(i));
+
+		writel_relaxed(val, csiphy->base +
+				    CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(c));
+	}
+
+	writel_relaxed(0x1, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(10));
+	writel_relaxed(0x0, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(10));
+
+	for (i = 22; i < 33; i++)
+		writel_relaxed(0x0, csiphy->base +
+				    CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(i));
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * csiphy_settle_cnt_calc - Calculate settle count value
+ *
+ * Helper function to calculate settle count value. This is
+ * based on the CSI2 T_hs_settle parameter which in turn
+ * is calculated based on the CSI2 transmitter pixel clock
+ * frequency.
+ *
+ * Return settle count value or 0 if the CSI2 pixel clock
+ * frequency is not available
+ */
+static u8 csiphy_settle_cnt_calc(u32 pixel_clock, u8 bpp, u8 num_lanes,
+				 u32 timer_clk_rate)
+{
+	u32 mipi_clock; /* Hz */
+	u32 ui; /* ps */
+	u32 timer_period; /* ps */
+	u32 t_hs_prepare_max; /* ps */
+	u32 t_hs_settle; /* ps */
+	u8 settle_cnt;
+
+	mipi_clock = pixel_clock * bpp / (2 * num_lanes);
+	ui = div_u64(1000000000000LL, mipi_clock);
+	ui /= 2;
+	t_hs_prepare_max = 85000 + 6 * ui;
+	t_hs_settle = t_hs_prepare_max;
+
+	timer_period = div_u64(1000000000000LL, timer_clk_rate);
+	settle_cnt = t_hs_settle / timer_period - 6;
+
+	return settle_cnt;
+}
+
+static void csiphy_lanes_enable(struct csiphy_device *csiphy,
+				struct csiphy_config *cfg,
+				u32 pixel_clock, u8 bpp, u8 lane_mask)
+{
+	struct csiphy_lanes_cfg *c = &cfg->csi2->lane_cfg;
+	u8 settle_cnt;
+	u8 val, l = 0;
+	int i;
+
+	settle_cnt = csiphy_settle_cnt_calc(pixel_clock, bpp, c->num_data,
+					    csiphy->timer_clk_rate);
+
+	val = BIT(c->clk.pos);
+	for (i = 0; i < c->num_data; i++)
+		val |= BIT(c->data[i].pos * 2);
+
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(5));
+
+	val = CSIPHY_3PH_CMN_CSI_COMMON_CTRL6_COMMON_PWRDN_B;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(6));
+
+	for (i = 0; i <= c->num_data; i++) {
+		if (i == c->num_data)
+			l = 7;
+		else
+			l = c->data[i].pos * 2;
+
+		val = CSIPHY_3PH_LNn_CFG1_SWI_REC_DLY_PRG;
+		val |= 0x17;
+		writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG1(l));
+
+		val = CSIPHY_3PH_LNn_CFG2_LP_REC_EN_INT;
+		writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG2(l));
+
+		val = settle_cnt;
+		writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG3(l));
+
+		val = CSIPHY_3PH_LNn_CFG5_T_HS_DTERM |
+			CSIPHY_3PH_LNn_CFG5_HS_REC_EQ_FQ_INT;
+		writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG5(l));
+
+		val = CSIPHY_3PH_LNn_CFG6_SWI_FORCE_INIT_EXIT;
+		writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG6(l));
+
+		val = CSIPHY_3PH_LNn_CFG7_SWI_T_INIT;
+		writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG7(l));
+
+		val = CSIPHY_3PH_LNn_CFG8_SWI_SKIP_WAKEUP |
+			CSIPHY_3PH_LNn_CFG8_SKEW_FILTER_ENABLE;
+		writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG8(l));
+
+		val = CSIPHY_3PH_LNn_CFG9_SWI_T_WAKEUP;
+		writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG9(l));
+
+		val = CSIPHY_3PH_LNn_TEST_IMP_HS_TERM_IMP;
+		writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_TEST_IMP(l));
+
+		val = CSIPHY_3PH_LNn_CSI_LANE_CTRL15_SWI_SOT_SYMBOL;
+		writel_relaxed(val, csiphy->base +
+				    CSIPHY_3PH_LNn_CSI_LANE_CTRL15(l));
+	}
+
+	val = CSIPHY_3PH_LNn_CFG1_SWI_REC_DLY_PRG;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG1(l));
+
+	val = CSIPHY_3PH_LNn_CFG4_T_HS_CLK_MISS;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG4(l));
+
+	val = CSIPHY_3PH_LNn_MISC1_IS_CLKLANE;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_MISC1(l));
+
+	val = 0xff;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(11));
+
+	val = 0xff;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(12));
+
+	val = 0xfb;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(13));
+
+	val = 0xff;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(14));
+
+	val = 0x7f;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(15));
+
+	val = 0xff;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(16));
+
+	val = 0xff;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(17));
+
+	val = 0xef;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(18));
+
+	val = 0xff;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(19));
+
+	val = 0xff;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(20));
+
+	val = 0xff;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(21));
+}
+
+static void csiphy_lanes_disable(struct csiphy_device *csiphy,
+				 struct csiphy_config *cfg)
+{
+	writel_relaxed(0, csiphy->base +
+			  CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(5));
+
+	writel_relaxed(0, csiphy->base +
+			  CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(6));
+}
+
+const struct csiphy_hw_ops csiphy_ops_3ph_1_0 = {
+	.hw_version_read = csiphy_hw_version_read,
+	.reset = csiphy_reset,
+	.lanes_enable = csiphy_lanes_enable,
+	.lanes_disable = csiphy_lanes_disable,
+	.isr = csiphy_isr,
+};
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c
index 7e61caba6a2d..4559f3b1b38c 100644
--- a/drivers/media/platform/qcom/camss-8x16/camss-csiphy.c
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.c
@@ -1,19 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * camss-csiphy.c
  *
  * Qualcomm MSM Camera Subsystem - CSIPHY Module
  *
  * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2016-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ * Copyright (C) 2016-2018 Linaro Ltd.
  */
 #include <linux/clk.h>
 #include <linux/delay.h>
@@ -21,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <media/media-entity.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-subdev.h>
@@ -30,131 +23,75 @@
 
 #define MSM_CSIPHY_NAME "msm_csiphy"
 
-#define CAMSS_CSI_PHY_LNn_CFG2(n)		(0x004 + 0x40 * (n))
-#define CAMSS_CSI_PHY_LNn_CFG3(n)		(0x008 + 0x40 * (n))
-#define CAMSS_CSI_PHY_GLBL_RESET		0x140
-#define CAMSS_CSI_PHY_GLBL_PWR_CFG		0x144
-#define CAMSS_CSI_PHY_GLBL_IRQ_CMD		0x164
-#define CAMSS_CSI_PHY_HW_VERSION		0x188
-#define CAMSS_CSI_PHY_INTERRUPT_STATUSn(n)	(0x18c + 0x4 * (n))
-#define CAMSS_CSI_PHY_INTERRUPT_MASKn(n)	(0x1ac + 0x4 * (n))
-#define CAMSS_CSI_PHY_INTERRUPT_CLEARn(n)	(0x1cc + 0x4 * (n))
-#define CAMSS_CSI_PHY_GLBL_T_INIT_CFG0		0x1ec
-#define CAMSS_CSI_PHY_T_WAKEUP_CFG0		0x1f4
-
-static const struct {
+struct csiphy_format {
 	u32 code;
 	u8 bpp;
-} csiphy_formats[] = {
-	{
-		MEDIA_BUS_FMT_UYVY8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_VYUY8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_YUYV8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_YVYU8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR12_1X12,
-		12,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG12_1X12,
-		12,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG12_1X12,
-		12,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB12_1X12,
-		12,
-	}
+};
+
+static const struct csiphy_format csiphy_formats_8x16[] = {
+	{ MEDIA_BUS_FMT_UYVY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, 8 },
+	{ MEDIA_BUS_FMT_SBGGR8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SGBRG8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SGRBG8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SRGGB8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SBGGR10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SGBRG10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SGRBG10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SRGGB10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SBGGR12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SGBRG12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SGRBG12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SRGGB12_1X12, 12 },
+	{ MEDIA_BUS_FMT_Y10_1X10, 10 },
+};
+
+static const struct csiphy_format csiphy_formats_8x96[] = {
+	{ MEDIA_BUS_FMT_UYVY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, 8 },
+	{ MEDIA_BUS_FMT_SBGGR8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SGBRG8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SGRBG8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SRGGB8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SBGGR10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SGBRG10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SGRBG10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SRGGB10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SBGGR12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SGBRG12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SGRBG12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SRGGB12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SBGGR14_1X14, 14 },
+	{ MEDIA_BUS_FMT_SGBRG14_1X14, 14 },
+	{ MEDIA_BUS_FMT_SGRBG14_1X14, 14 },
+	{ MEDIA_BUS_FMT_SRGGB14_1X14, 14 },
+	{ MEDIA_BUS_FMT_Y10_1X10, 10 },
 };
 
 /*
  * csiphy_get_bpp - map media bus format to bits per pixel
+ * @formats: supported media bus formats array
+ * @nformats: size of @formats array
  * @code: media bus format code
  *
  * Return number of bits per pixel
  */
-static u8 csiphy_get_bpp(u32 code)
+static u8 csiphy_get_bpp(const struct csiphy_format *formats,
+			 unsigned int nformats, u32 code)
 {
 	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(csiphy_formats); i++)
-		if (code == csiphy_formats[i].code)
-			return csiphy_formats[i].bpp;
+	for (i = 0; i < nformats; i++)
+		if (code == formats[i].code)
+			return formats[i].bpp;
 
 	WARN(1, "Unknown format\n");
 
-	return csiphy_formats[0].bpp;
-}
-
-/*
- * csiphy_isr - CSIPHY module interrupt handler
- * @irq: Interrupt line
- * @dev: CSIPHY device
- *
- * Return IRQ_HANDLED on success
- */
-static irqreturn_t csiphy_isr(int irq, void *dev)
-{
-	struct csiphy_device *csiphy = dev;
-	u8 i;
-
-	for (i = 0; i < 8; i++) {
-		u8 val = readl_relaxed(csiphy->base +
-				       CAMSS_CSI_PHY_INTERRUPT_STATUSn(i));
-		writel_relaxed(val, csiphy->base +
-			       CAMSS_CSI_PHY_INTERRUPT_CLEARn(i));
-		writel_relaxed(0x1, csiphy->base + CAMSS_CSI_PHY_GLBL_IRQ_CMD);
-		writel_relaxed(0x0, csiphy->base + CAMSS_CSI_PHY_GLBL_IRQ_CMD);
-		writel_relaxed(0x0, csiphy->base +
-			       CAMSS_CSI_PHY_INTERRUPT_CLEARn(i));
-	}
-
-	return IRQ_HANDLED;
+	return formats[0].bpp;
 }
 
 /*
@@ -163,7 +100,7 @@ static irqreturn_t csiphy_isr(int irq, void *dev)
  */
 static int csiphy_set_clock_rates(struct csiphy_device *csiphy)
 {
-	struct device *dev = to_device_index(csiphy, csiphy->id);
+	struct device *dev = csiphy->camss->dev;
 	u32 pixel_clock;
 	int i, j;
 	int ret;
@@ -176,8 +113,10 @@ static int csiphy_set_clock_rates(struct csiphy_device *csiphy)
 		struct camss_clock *clock = &csiphy->clock[i];
 
 		if (!strcmp(clock->name, "csiphy0_timer") ||
-			!strcmp(clock->name, "csiphy1_timer")) {
-			u8 bpp = csiphy_get_bpp(
+		    !strcmp(clock->name, "csiphy1_timer") ||
+		    !strcmp(clock->name, "csiphy2_timer")) {
+			u8 bpp = csiphy_get_bpp(csiphy->formats,
+					csiphy->nformats,
 					csiphy->fmt[MSM_CSIPHY_PAD_SINK].code);
 			u8 num_lanes = csiphy->cfg.csi2->lane_cfg.num_data;
 			u64 min_rate = pixel_clock * bpp / (2 * num_lanes * 4);
@@ -221,17 +160,6 @@ static int csiphy_set_clock_rates(struct csiphy_device *csiphy)
 }
 
 /*
- * csiphy_reset - Perform software reset on CSIPHY module
- * @csiphy: CSIPHY device
- */
-static void csiphy_reset(struct csiphy_device *csiphy)
-{
-	writel_relaxed(0x1, csiphy->base + CAMSS_CSI_PHY_GLBL_RESET);
-	usleep_range(5000, 8000);
-	writel_relaxed(0x0, csiphy->base + CAMSS_CSI_PHY_GLBL_RESET);
-}
-
-/*
  * csiphy_set_power - Power on/off CSIPHY module
  * @sd: CSIPHY V4L2 subdevice
  * @on: Requested power state
@@ -241,31 +169,38 @@ static void csiphy_reset(struct csiphy_device *csiphy)
 static int csiphy_set_power(struct v4l2_subdev *sd, int on)
 {
 	struct csiphy_device *csiphy = v4l2_get_subdevdata(sd);
-	struct device *dev = to_device_index(csiphy, csiphy->id);
+	struct device *dev = csiphy->camss->dev;
 
 	if (on) {
-		u8 hw_version;
 		int ret;
 
-		ret = csiphy_set_clock_rates(csiphy);
+		ret = pm_runtime_get_sync(dev);
 		if (ret < 0)
 			return ret;
 
+		ret = csiphy_set_clock_rates(csiphy);
+		if (ret < 0) {
+			pm_runtime_put_sync(dev);
+			return ret;
+		}
+
 		ret = camss_enable_clocks(csiphy->nclocks, csiphy->clock, dev);
-		if (ret < 0)
+		if (ret < 0) {
+			pm_runtime_put_sync(dev);
 			return ret;
+		}
 
 		enable_irq(csiphy->irq);
 
-		csiphy_reset(csiphy);
+		csiphy->ops->reset(csiphy);
 
-		hw_version = readl_relaxed(csiphy->base +
-					   CAMSS_CSI_PHY_HW_VERSION);
-		dev_dbg(dev, "CSIPHY HW Version = 0x%02x\n", hw_version);
+		csiphy->ops->hw_version_read(csiphy, dev);
 	} else {
 		disable_irq(csiphy->irq);
 
 		camss_disable_clocks(csiphy->nclocks, csiphy->clock);
+
+		pm_runtime_put_sync(dev);
 	}
 
 	return 0;
@@ -291,58 +226,6 @@ static u8 csiphy_get_lane_mask(struct csiphy_lanes_cfg *lane_cfg)
 }
 
 /*
- * csiphy_settle_cnt_calc - Calculate settle count value
- * @csiphy: CSIPHY device
- *
- * Helper function to calculate settle count value. This is
- * based on the CSI2 T_hs_settle parameter which in turn
- * is calculated based on the CSI2 transmitter pixel clock
- * frequency.
- *
- * Return settle count value or 0 if the CSI2 pixel clock
- * frequency is not available
- */
-static u8 csiphy_settle_cnt_calc(struct csiphy_device *csiphy)
-{
-	u8 bpp = csiphy_get_bpp(
-			csiphy->fmt[MSM_CSIPHY_PAD_SINK].code);
-	u8 num_lanes = csiphy->cfg.csi2->lane_cfg.num_data;
-	u32 pixel_clock; /* Hz */
-	u32 mipi_clock; /* Hz */
-	u32 ui; /* ps */
-	u32 timer_period; /* ps */
-	u32 t_hs_prepare_max; /* ps */
-	u32 t_hs_prepare_zero_min; /* ps */
-	u32 t_hs_settle; /* ps */
-	u8 settle_cnt;
-	int ret;
-
-	ret = camss_get_pixel_clock(&csiphy->subdev.entity, &pixel_clock);
-	if (ret) {
-		dev_err(to_device_index(csiphy, csiphy->id),
-			"Cannot get CSI2 transmitter's pixel clock\n");
-		return 0;
-	}
-	if (!pixel_clock) {
-		dev_err(to_device_index(csiphy, csiphy->id),
-			"Got pixel clock == 0, cannot continue\n");
-		return 0;
-	}
-
-	mipi_clock = pixel_clock * bpp / (2 * num_lanes);
-	ui = div_u64(1000000000000LL, mipi_clock);
-	ui /= 2;
-	t_hs_prepare_max = 85000 + 6 * ui;
-	t_hs_prepare_zero_min = 145000 + 10 * ui;
-	t_hs_settle = (t_hs_prepare_max + t_hs_prepare_zero_min) / 2;
-
-	timer_period = div_u64(1000000000000LL, csiphy->timer_clk_rate);
-	settle_cnt = t_hs_settle / timer_period;
-
-	return settle_cnt;
-}
-
-/*
  * csiphy_stream_on - Enable streaming on CSIPHY module
  * @csiphy: CSIPHY device
  *
@@ -354,14 +237,24 @@ static u8 csiphy_settle_cnt_calc(struct csiphy_device *csiphy)
 static int csiphy_stream_on(struct csiphy_device *csiphy)
 {
 	struct csiphy_config *cfg = &csiphy->cfg;
+	u32 pixel_clock;
 	u8 lane_mask = csiphy_get_lane_mask(&cfg->csi2->lane_cfg);
-	u8 settle_cnt;
+	u8 bpp = csiphy_get_bpp(csiphy->formats, csiphy->nformats,
+				csiphy->fmt[MSM_CSIPHY_PAD_SINK].code);
 	u8 val;
-	int i = 0;
+	int ret;
 
-	settle_cnt = csiphy_settle_cnt_calc(csiphy);
-	if (!settle_cnt)
+	ret = camss_get_pixel_clock(&csiphy->subdev.entity, &pixel_clock);
+	if (ret) {
+		dev_err(csiphy->camss->dev,
+			"Cannot get CSI2 transmitter's pixel clock\n");
 		return -EINVAL;
+	}
+	if (!pixel_clock) {
+		dev_err(csiphy->camss->dev,
+			"Got pixel clock == 0, cannot continue\n");
+		return -EINVAL;
+	}
 
 	val = readl_relaxed(csiphy->base_clk_mux);
 	if (cfg->combo_mode && (lane_mask & 0x18) == 0x18) {
@@ -372,34 +265,9 @@ static int csiphy_stream_on(struct csiphy_device *csiphy)
 		val |= cfg->csid_id;
 	}
 	writel_relaxed(val, csiphy->base_clk_mux);
+	wmb();
 
-	writel_relaxed(0x1, csiphy->base +
-		       CAMSS_CSI_PHY_GLBL_T_INIT_CFG0);
-	writel_relaxed(0x1, csiphy->base +
-		       CAMSS_CSI_PHY_T_WAKEUP_CFG0);
-
-	val = 0x1;
-	val |= lane_mask << 1;
-	writel_relaxed(val, csiphy->base + CAMSS_CSI_PHY_GLBL_PWR_CFG);
-
-	val = cfg->combo_mode << 4;
-	writel_relaxed(val, csiphy->base + CAMSS_CSI_PHY_GLBL_RESET);
-
-	while (lane_mask) {
-		if (lane_mask & 0x1) {
-			writel_relaxed(0x10, csiphy->base +
-				       CAMSS_CSI_PHY_LNn_CFG2(i));
-			writel_relaxed(settle_cnt, csiphy->base +
-				       CAMSS_CSI_PHY_LNn_CFG3(i));
-			writel_relaxed(0x3f, csiphy->base +
-				       CAMSS_CSI_PHY_INTERRUPT_MASKn(i));
-			writel_relaxed(0x3f, csiphy->base +
-				       CAMSS_CSI_PHY_INTERRUPT_CLEARn(i));
-		}
-
-		lane_mask >>= 1;
-		i++;
-	}
+	csiphy->ops->lanes_enable(csiphy, cfg, pixel_clock, bpp, lane_mask);
 
 	return 0;
 }
@@ -412,19 +280,7 @@ static int csiphy_stream_on(struct csiphy_device *csiphy)
  */
 static void csiphy_stream_off(struct csiphy_device *csiphy)
 {
-	u8 lane_mask = csiphy_get_lane_mask(&csiphy->cfg.csi2->lane_cfg);
-	int i = 0;
-
-	while (lane_mask) {
-		if (lane_mask & 0x1)
-			writel_relaxed(0x0, csiphy->base +
-				       CAMSS_CSI_PHY_LNn_CFG2(i));
-
-		lane_mask >>= 1;
-		i++;
-	}
-
-	writel_relaxed(0x0, csiphy->base + CAMSS_CSI_PHY_GLBL_PWR_CFG);
+	csiphy->ops->lanes_disable(csiphy, &csiphy->cfg);
 }
 
 
@@ -489,12 +345,12 @@ static void csiphy_try_format(struct csiphy_device *csiphy,
 	case MSM_CSIPHY_PAD_SINK:
 		/* Set format on sink pad */
 
-		for (i = 0; i < ARRAY_SIZE(csiphy_formats); i++)
-			if (fmt->code == csiphy_formats[i].code)
+		for (i = 0; i < csiphy->nformats; i++)
+			if (fmt->code == csiphy->formats[i].code)
 				break;
 
 		/* If not found, use UYVY as default */
-		if (i >= ARRAY_SIZE(csiphy_formats))
+		if (i >= csiphy->nformats)
 			fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
 
 		fmt->width = clamp_t(u32, fmt->width, 1, 8191);
@@ -530,10 +386,10 @@ static int csiphy_enum_mbus_code(struct v4l2_subdev *sd,
 	struct v4l2_mbus_framefmt *format;
 
 	if (code->pad == MSM_CSIPHY_PAD_SINK) {
-		if (code->index >= ARRAY_SIZE(csiphy_formats))
+		if (code->index >= csiphy->nformats)
 			return -EINVAL;
 
-		code->code = csiphy_formats[code->index].code;
+		code->code = csiphy->formats[code->index].code;
 	} else {
 		if (code->index > 0)
 			return -EINVAL;
@@ -677,18 +533,32 @@ static int csiphy_init_formats(struct v4l2_subdev *sd,
  *
  * Return 0 on success or a negative error code otherwise
  */
-int msm_csiphy_subdev_init(struct csiphy_device *csiphy,
+int msm_csiphy_subdev_init(struct camss *camss,
+			   struct csiphy_device *csiphy,
 			   const struct resources *res, u8 id)
 {
-	struct device *dev = to_device_index(csiphy, id);
+	struct device *dev = camss->dev;
 	struct platform_device *pdev = to_platform_device(dev);
 	struct resource *r;
 	int i, j;
 	int ret;
 
+	csiphy->camss = camss;
 	csiphy->id = id;
 	csiphy->cfg.combo_mode = 0;
 
+	if (camss->version == CAMSS_8x16) {
+		csiphy->ops = &csiphy_ops_2ph_1_0;
+		csiphy->formats = csiphy_formats_8x16;
+		csiphy->nformats = ARRAY_SIZE(csiphy_formats_8x16);
+	} else if (camss->version == CAMSS_8x96) {
+		csiphy->ops = &csiphy_ops_3ph_1_0;
+		csiphy->formats = csiphy_formats_8x96;
+		csiphy->nformats = ARRAY_SIZE(csiphy_formats_8x96);
+	} else {
+		return -EINVAL;
+	}
+
 	/* Memory */
 
 	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[0]);
@@ -717,7 +587,8 @@ int msm_csiphy_subdev_init(struct csiphy_device *csiphy,
 	csiphy->irq = r->start;
 	snprintf(csiphy->irq_name, sizeof(csiphy->irq_name), "%s_%s%d",
 		 dev_name(dev), MSM_CSIPHY_NAME, csiphy->id);
-	ret = devm_request_irq(dev, csiphy->irq, csiphy_isr,
+
+	ret = devm_request_irq(dev, csiphy->irq, csiphy->ops->isr,
 			       IRQF_TRIGGER_RISING, csiphy->irq_name, csiphy);
 	if (ret < 0) {
 		dev_err(dev, "request_irq failed: %d\n", ret);
@@ -846,7 +717,7 @@ int msm_csiphy_register_entity(struct csiphy_device *csiphy,
 {
 	struct v4l2_subdev *sd = &csiphy->subdev;
 	struct media_pad *pads = csiphy->pads;
-	struct device *dev = to_device_index(csiphy, csiphy->id);
+	struct device *dev = csiphy->camss->dev;
 	int ret;
 
 	v4l2_subdev_init(sd, &csiphy_v4l2_ops);
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-csiphy.h b/drivers/media/platform/qcom/camss/camss-csiphy.h
index ba8781122065..376f865ad383 100644
--- a/drivers/media/platform/qcom/camss-8x16/camss-csiphy.h
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.h
@@ -1,24 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * camss-csiphy.h
  *
  * Qualcomm MSM Camera Subsystem - CSIPHY Module
  *
  * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2016-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ * Copyright (C) 2016-2018 Linaro Ltd.
  */
 #ifndef QC_MSM_CAMSS_CSIPHY_H
 #define QC_MSM_CAMSS_CSIPHY_H
 
 #include <linux/clk.h>
+#include <linux/interrupt.h>
 #include <media/media-entity.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-mediabus.h>
@@ -49,7 +42,22 @@ struct csiphy_config {
 	struct csiphy_csi2_cfg *csi2;
 };
 
+struct csiphy_device;
+
+struct csiphy_hw_ops {
+	void (*hw_version_read)(struct csiphy_device *csiphy,
+				struct device *dev);
+	void (*reset)(struct csiphy_device *csiphy);
+	void (*lanes_enable)(struct csiphy_device *csiphy,
+			     struct csiphy_config *cfg,
+			     u32 pixel_clock, u8 bpp, u8 lane_mask);
+	void (*lanes_disable)(struct csiphy_device *csiphy,
+			      struct csiphy_config *cfg);
+	irqreturn_t (*isr)(int irq, void *dev);
+};
+
 struct csiphy_device {
+	struct camss *camss;
 	u8 id;
 	struct v4l2_subdev subdev;
 	struct media_pad pads[MSM_CSIPHY_PADS_NUM];
@@ -62,11 +70,15 @@ struct csiphy_device {
 	u32 timer_clk_rate;
 	struct csiphy_config cfg;
 	struct v4l2_mbus_framefmt fmt[MSM_CSIPHY_PADS_NUM];
+	const struct csiphy_hw_ops *ops;
+	const struct csiphy_format *formats;
+	unsigned int nformats;
 };
 
 struct resources;
 
-int msm_csiphy_subdev_init(struct csiphy_device *csiphy,
+int msm_csiphy_subdev_init(struct camss *camss,
+			   struct csiphy_device *csiphy,
 			   const struct resources *res, u8 id);
 
 int msm_csiphy_register_entity(struct csiphy_device *csiphy,
@@ -74,4 +86,7 @@ int msm_csiphy_register_entity(struct csiphy_device *csiphy,
 
 void msm_csiphy_unregister_entity(struct csiphy_device *csiphy);
 
+extern const struct csiphy_hw_ops csiphy_ops_2ph_1_0;
+extern const struct csiphy_hw_ops csiphy_ops_3ph_1_0;
+
 #endif /* QC_MSM_CAMSS_CSIPHY_H */
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-ispif.c b/drivers/media/platform/qcom/camss/camss-ispif.c
index 9d1af9353c1d..7f269021d08c 100644
--- a/drivers/media/platform/qcom/camss-8x16/camss-ispif.c
+++ b/drivers/media/platform/qcom/camss/camss-ispif.c
@@ -1,19 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * camss-ispif.c
  *
  * Qualcomm MSM Camera Subsystem - ISPIF (ISP Interface) Module
  *
  * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ * Copyright (C) 2015-2018 Linaro Ltd.
  */
 #include <linux/clk.h>
 #include <linux/completion.h>
@@ -22,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/mutex.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <media/media-entity.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-subdev.h>
@@ -31,12 +24,6 @@
 
 #define MSM_ISPIF_NAME "msm_ispif"
 
-#define ispif_line_array(ptr_line)	\
-	((const struct ispif_line (*)[]) &(ptr_line[-(ptr_line->id)]))
-
-#define to_ispif(ptr_line)	\
-	container_of(ispif_line_array(ptr_line), struct ispif_device, ptr_line)
-
 #define ISPIF_RST_CMD_0			0x008
 #define ISPIF_RST_CMD_0_STROBED_RST_EN		(1 << 0)
 #define ISPIF_RST_CMD_0_MISC_LOGIC_RST		(1 << 1)
@@ -89,6 +76,13 @@
 					(0x254 + 0x200 * (m) + 0x4 * (n))
 #define ISPIF_VFE_m_RDI_INTF_n_CID_MASK(m, n)	\
 					(0x264 + 0x200 * (m) + 0x4 * (n))
+/* PACK_CFG registers are 8x96 only */
+#define ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_0(m, n)	\
+					(0x270 + 0x200 * (m) + 0x4 * (n))
+#define ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_1(m, n)	\
+					(0x27c + 0x200 * (m) + 0x4 * (n))
+#define ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_0_CID_c_PLAIN(c)	\
+					(1 << ((cid % 8) * 4))
 #define ISPIF_VFE_m_PIX_INTF_n_STATUS(m, n)	\
 					(0x2c0 + 0x200 * (m) + 0x4 * (n))
 #define ISPIF_VFE_m_RDI_INTF_n_STATUS(m, n)	\
@@ -109,7 +103,7 @@ enum ispif_intf_cmd {
 	CMD_ALL_NO_CHANGE = 0xffffffff,
 };
 
-static const u32 ispif_formats[] = {
+static const u32 ispif_formats_8x16[] = {
 	MEDIA_BUS_FMT_UYVY8_2X8,
 	MEDIA_BUS_FMT_VYUY8_2X8,
 	MEDIA_BUS_FMT_YUYV8_2X8,
@@ -126,16 +120,107 @@ static const u32 ispif_formats[] = {
 	MEDIA_BUS_FMT_SGBRG12_1X12,
 	MEDIA_BUS_FMT_SGRBG12_1X12,
 	MEDIA_BUS_FMT_SRGGB12_1X12,
+	MEDIA_BUS_FMT_Y10_1X10,
+};
+
+static const u32 ispif_formats_8x96[] = {
+	MEDIA_BUS_FMT_UYVY8_2X8,
+	MEDIA_BUS_FMT_VYUY8_2X8,
+	MEDIA_BUS_FMT_YUYV8_2X8,
+	MEDIA_BUS_FMT_YVYU8_2X8,
+	MEDIA_BUS_FMT_SBGGR8_1X8,
+	MEDIA_BUS_FMT_SGBRG8_1X8,
+	MEDIA_BUS_FMT_SGRBG8_1X8,
+	MEDIA_BUS_FMT_SRGGB8_1X8,
+	MEDIA_BUS_FMT_SBGGR10_1X10,
+	MEDIA_BUS_FMT_SGBRG10_1X10,
+	MEDIA_BUS_FMT_SGRBG10_1X10,
+	MEDIA_BUS_FMT_SRGGB10_1X10,
+	MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE,
+	MEDIA_BUS_FMT_SBGGR12_1X12,
+	MEDIA_BUS_FMT_SGBRG12_1X12,
+	MEDIA_BUS_FMT_SGRBG12_1X12,
+	MEDIA_BUS_FMT_SRGGB12_1X12,
+	MEDIA_BUS_FMT_SBGGR14_1X14,
+	MEDIA_BUS_FMT_SGBRG14_1X14,
+	MEDIA_BUS_FMT_SGRBG14_1X14,
+	MEDIA_BUS_FMT_SRGGB14_1X14,
+	MEDIA_BUS_FMT_Y10_1X10,
+	MEDIA_BUS_FMT_Y10_2X8_PADHI_LE,
 };
 
 /*
- * ispif_isr - ISPIF module interrupt handler
+ * ispif_isr_8x96 - ISPIF module interrupt handler for 8x96
  * @irq: Interrupt line
  * @dev: ISPIF device
  *
  * Return IRQ_HANDLED on success
  */
-static irqreturn_t ispif_isr(int irq, void *dev)
+static irqreturn_t ispif_isr_8x96(int irq, void *dev)
+{
+	struct ispif_device *ispif = dev;
+	u32 value0, value1, value2, value3, value4, value5;
+
+	value0 = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_STATUS_0(0));
+	value1 = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_STATUS_1(0));
+	value2 = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_STATUS_2(0));
+	value3 = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_STATUS_0(1));
+	value4 = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_STATUS_1(1));
+	value5 = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_STATUS_2(1));
+
+	writel_relaxed(value0, ispif->base + ISPIF_VFE_m_IRQ_CLEAR_0(0));
+	writel_relaxed(value1, ispif->base + ISPIF_VFE_m_IRQ_CLEAR_1(0));
+	writel_relaxed(value2, ispif->base + ISPIF_VFE_m_IRQ_CLEAR_2(0));
+	writel_relaxed(value3, ispif->base + ISPIF_VFE_m_IRQ_CLEAR_0(1));
+	writel_relaxed(value4, ispif->base + ISPIF_VFE_m_IRQ_CLEAR_1(1));
+	writel_relaxed(value5, ispif->base + ISPIF_VFE_m_IRQ_CLEAR_2(1));
+
+	writel(0x1, ispif->base + ISPIF_IRQ_GLOBAL_CLEAR_CMD);
+
+	if ((value0 >> 27) & 0x1)
+		complete(&ispif->reset_complete);
+
+	if (unlikely(value0 & ISPIF_VFE_m_IRQ_STATUS_0_PIX0_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE0 pix0 overflow\n");
+
+	if (unlikely(value0 & ISPIF_VFE_m_IRQ_STATUS_0_RDI0_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE0 rdi0 overflow\n");
+
+	if (unlikely(value1 & ISPIF_VFE_m_IRQ_STATUS_1_PIX1_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE0 pix1 overflow\n");
+
+	if (unlikely(value1 & ISPIF_VFE_m_IRQ_STATUS_1_RDI1_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE0 rdi1 overflow\n");
+
+	if (unlikely(value2 & ISPIF_VFE_m_IRQ_STATUS_2_RDI2_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE0 rdi2 overflow\n");
+
+	if (unlikely(value3 & ISPIF_VFE_m_IRQ_STATUS_0_PIX0_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE1 pix0 overflow\n");
+
+	if (unlikely(value3 & ISPIF_VFE_m_IRQ_STATUS_0_RDI0_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE1 rdi0 overflow\n");
+
+	if (unlikely(value4 & ISPIF_VFE_m_IRQ_STATUS_1_PIX1_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE1 pix1 overflow\n");
+
+	if (unlikely(value4 & ISPIF_VFE_m_IRQ_STATUS_1_RDI1_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE1 rdi1 overflow\n");
+
+	if (unlikely(value5 & ISPIF_VFE_m_IRQ_STATUS_2_RDI2_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE1 rdi2 overflow\n");
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * ispif_isr_8x16 - ISPIF module interrupt handler for 8x16
+ * @irq: Interrupt line
+ * @dev: ISPIF device
+ *
+ * Return IRQ_HANDLED on success
+ */
+static irqreturn_t ispif_isr_8x16(int irq, void *dev)
 {
 	struct ispif_device *ispif = dev;
 	u32 value0, value1, value2;
@@ -183,6 +268,14 @@ static int ispif_reset(struct ispif_device *ispif)
 	u32 val;
 	int ret;
 
+	ret = camss_pm_domain_on(to_camss(ispif), PM_DOMAIN_VFE0);
+	if (ret < 0)
+		return ret;
+
+	ret = camss_pm_domain_on(to_camss(ispif), PM_DOMAIN_VFE1);
+	if (ret < 0)
+		return ret;
+
 	ret = camss_enable_clocks(ispif->nclocks_for_reset,
 				  ispif->clock_for_reset,
 				  to_device(ispif));
@@ -215,12 +308,15 @@ static int ispif_reset(struct ispif_device *ispif)
 		msecs_to_jiffies(ISPIF_RESET_TIMEOUT_MS));
 	if (!time) {
 		dev_err(to_device(ispif), "ISPIF reset timeout\n");
-		return -EIO;
+		ret = -EIO;
 	}
 
 	camss_disable_clocks(ispif->nclocks_for_reset, ispif->clock_for_reset);
 
-	return 0;
+	camss_pm_domain_off(to_camss(ispif), PM_DOMAIN_VFE0);
+	camss_pm_domain_off(to_camss(ispif), PM_DOMAIN_VFE1);
+
+	return ret;
 }
 
 /*
@@ -233,7 +329,7 @@ static int ispif_reset(struct ispif_device *ispif)
 static int ispif_set_power(struct v4l2_subdev *sd, int on)
 {
 	struct ispif_line *line = v4l2_get_subdevdata(sd);
-	struct ispif_device *ispif = to_ispif(line);
+	struct ispif_device *ispif = line->ispif;
 	struct device *dev = to_device(ispif);
 	int ret = 0;
 
@@ -246,12 +342,19 @@ static int ispif_set_power(struct v4l2_subdev *sd, int on)
 			goto exit;
 		}
 
-		ret = camss_enable_clocks(ispif->nclocks, ispif->clock, dev);
+		ret = pm_runtime_get_sync(dev);
 		if (ret < 0)
 			goto exit;
 
+		ret = camss_enable_clocks(ispif->nclocks, ispif->clock, dev);
+		if (ret < 0) {
+			pm_runtime_put_sync(dev);
+			goto exit;
+		}
+
 		ret = ispif_reset(ispif);
 		if (ret < 0) {
+			pm_runtime_put_sync(dev);
 			camss_disable_clocks(ispif->nclocks, ispif->clock);
 			goto exit;
 		}
@@ -266,6 +369,7 @@ static int ispif_set_power(struct v4l2_subdev *sd, int on)
 			goto exit;
 		} else if (ispif->power_count == 1) {
 			camss_disable_clocks(ispif->nclocks, ispif->clock);
+			pm_runtime_put_sync(dev);
 		}
 
 		ispif->power_count--;
@@ -578,6 +682,55 @@ static void ispif_config_irq(struct ispif_device *ispif, enum ispif_intf intf,
 }
 
 /*
+ * ispif_config_pack - Config packing for PRDI mode
+ * @ispif: ISPIF device
+ * @code: media bus format code
+ * @intf: VFE interface
+ * @cid: desired CID to handle
+ * @vfe: VFE HW module id
+ * @enable: enable or disable
+ */
+static void ispif_config_pack(struct ispif_device *ispif, u32 code,
+			      enum ispif_intf intf, u8 cid, u8 vfe, u8 enable)
+{
+	u32 addr, val;
+
+	if (code != MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE &&
+	    code != MEDIA_BUS_FMT_Y10_2X8_PADHI_LE)
+		return;
+
+	switch (intf) {
+	case RDI0:
+		if (cid < 8)
+			addr = ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_0(vfe, 0);
+		else
+			addr = ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_1(vfe, 0);
+		break;
+	case RDI1:
+		if (cid < 8)
+			addr = ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_0(vfe, 1);
+		else
+			addr = ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_1(vfe, 1);
+		break;
+	case RDI2:
+		if (cid < 8)
+			addr = ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_0(vfe, 2);
+		else
+			addr = ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_1(vfe, 2);
+		break;
+	default:
+		return;
+	}
+
+	if (enable)
+		val = ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_0_CID_c_PLAIN(cid);
+	else
+		val = 0;
+
+	writel_relaxed(val, ispif->base + addr);
+}
+
+/*
  * ispif_set_intf_cmd - Set command to enable/disable interface
  * @ispif: ISPIF device
  * @cmd: interface command
@@ -619,7 +772,7 @@ static void ispif_set_intf_cmd(struct ispif_device *ispif, u8 cmd,
 static int ispif_set_stream(struct v4l2_subdev *sd, int enable)
 {
 	struct ispif_line *line = v4l2_get_subdevdata(sd);
-	struct ispif_device *ispif = to_ispif(line);
+	struct ispif_device *ispif = line->ispif;
 	enum ispif_intf intf = line->interface;
 	u8 csid = line->csid_id;
 	u8 vfe = line->vfe_id;
@@ -645,6 +798,10 @@ static int ispif_set_stream(struct v4l2_subdev *sd, int enable)
 		ispif_select_csid(ispif, intf, csid, vfe, 1);
 		ispif_select_cid(ispif, intf, cid, vfe, 1);
 		ispif_config_irq(ispif, intf, vfe, 1);
+		if (to_camss(ispif)->version == CAMSS_8x96)
+			ispif_config_pack(ispif,
+					  line->fmt[MSM_ISPIF_PAD_SINK].code,
+					  intf, cid, vfe, 1);
 		ispif_set_intf_cmd(ispif, CMD_ENABLE_FRAME_BOUNDARY,
 				   intf, vfe, vc);
 	} else {
@@ -658,6 +815,10 @@ static int ispif_set_stream(struct v4l2_subdev *sd, int enable)
 			return ret;
 
 		mutex_lock(&ispif->config_lock);
+		if (to_camss(ispif)->version == CAMSS_8x96)
+			ispif_config_pack(ispif,
+					  line->fmt[MSM_ISPIF_PAD_SINK].code,
+					  intf, cid, vfe, 0);
 		ispif_config_irq(ispif, intf, vfe, 0);
 		ispif_select_cid(ispif, intf, cid, vfe, 0);
 		ispif_select_csid(ispif, intf, csid, vfe, 0);
@@ -710,12 +871,12 @@ static void ispif_try_format(struct ispif_line *line,
 	case MSM_ISPIF_PAD_SINK:
 		/* Set format on sink pad */
 
-		for (i = 0; i < ARRAY_SIZE(ispif_formats); i++)
-			if (fmt->code == ispif_formats[i])
+		for (i = 0; i < line->nformats; i++)
+			if (fmt->code == line->formats[i])
 				break;
 
 		/* If not found, use UYVY as default */
-		if (i >= ARRAY_SIZE(ispif_formats))
+		if (i >= line->nformats)
 			fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
 
 		fmt->width = clamp_t(u32, fmt->width, 1, 8191);
@@ -753,10 +914,10 @@ static int ispif_enum_mbus_code(struct v4l2_subdev *sd,
 	struct v4l2_mbus_framefmt *format;
 
 	if (code->pad == MSM_ISPIF_PAD_SINK) {
-		if (code->index >= ARRAY_SIZE(ispif_formats))
+		if (code->index >= line->nformats)
 			return -EINVAL;
 
-		code->code = ispif_formats[code->index];
+		code->code = line->formats[code->index];
 	} else {
 		if (code->index > 0)
 			return -EINVAL;
@@ -907,6 +1068,36 @@ int msm_ispif_subdev_init(struct ispif_device *ispif,
 	int i;
 	int ret;
 
+	/* Number of ISPIF lines - same as number of CSID hardware modules */
+	if (to_camss(ispif)->version == CAMSS_8x16)
+		ispif->line_num = 2;
+	else if (to_camss(ispif)->version == CAMSS_8x96)
+		ispif->line_num = 4;
+	else
+		return -EINVAL;
+
+	ispif->line = kcalloc(ispif->line_num, sizeof(*ispif->line),
+			      GFP_KERNEL);
+	if (!ispif->line)
+		return -ENOMEM;
+
+	for (i = 0; i < ispif->line_num; i++) {
+		ispif->line[i].ispif = ispif;
+		ispif->line[i].id = i;
+
+		if (to_camss(ispif)->version == CAMSS_8x16) {
+			ispif->line[i].formats = ispif_formats_8x16;
+			ispif->line[i].nformats =
+					ARRAY_SIZE(ispif_formats_8x16);
+		} else if (to_camss(ispif)->version == CAMSS_8x96) {
+			ispif->line[i].formats = ispif_formats_8x96;
+			ispif->line[i].nformats =
+					ARRAY_SIZE(ispif_formats_8x96);
+		} else {
+			return -EINVAL;
+		}
+	}
+
 	/* Memory */
 
 	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[0]);
@@ -935,8 +1126,14 @@ int msm_ispif_subdev_init(struct ispif_device *ispif,
 	ispif->irq = r->start;
 	snprintf(ispif->irq_name, sizeof(ispif->irq_name), "%s_%s",
 		 dev_name(dev), MSM_ISPIF_NAME);
-	ret = devm_request_irq(dev, ispif->irq, ispif_isr,
+	if (to_camss(ispif)->version == CAMSS_8x16)
+		ret = devm_request_irq(dev, ispif->irq, ispif_isr_8x16,
+			       IRQF_TRIGGER_RISING, ispif->irq_name, ispif);
+	else if (to_camss(ispif)->version == CAMSS_8x96)
+		ret = devm_request_irq(dev, ispif->irq, ispif_isr_8x96,
 			       IRQF_TRIGGER_RISING, ispif->irq_name, ispif);
+	else
+		ret = -EINVAL;
 	if (ret < 0) {
 		dev_err(dev, "request_irq failed: %d\n", ret);
 		return ret;
@@ -987,9 +1184,6 @@ int msm_ispif_subdev_init(struct ispif_device *ispif,
 		clock->nfreqs = 0;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(ispif->line); i++)
-		ispif->line[i].id = i;
-
 	mutex_init(&ispif->power_lock);
 	ispif->power_count = 0;
 
@@ -1108,7 +1302,7 @@ int msm_ispif_register_entities(struct ispif_device *ispif,
 	int ret;
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(ispif->line); i++) {
+	for (i = 0; i < ispif->line_num; i++) {
 		struct v4l2_subdev *sd = &ispif->line[i].subdev;
 		struct media_pad *pads = ispif->line[i].pads;
 
@@ -1169,7 +1363,7 @@ void msm_ispif_unregister_entities(struct ispif_device *ispif)
 	mutex_destroy(&ispif->power_lock);
 	mutex_destroy(&ispif->config_lock);
 
-	for (i = 0; i < ARRAY_SIZE(ispif->line); i++) {
+	for (i = 0; i < ispif->line_num; i++) {
 		struct v4l2_subdev *sd = &ispif->line[i].subdev;
 
 		v4l2_device_unregister_subdev(sd);
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-ispif.h b/drivers/media/platform/qcom/camss/camss-ispif.h
index f668306020c3..1a5ba2425a42 100644
--- a/drivers/media/platform/qcom/camss-8x16/camss-ispif.h
+++ b/drivers/media/platform/qcom/camss/camss-ispif.h
@@ -1,19 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * camss-ispif.h
  *
  * Qualcomm MSM Camera Subsystem - ISPIF (ISP Interface) Module
  *
  * Copyright (c) 2013-2014, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ * Copyright (C) 2015-2018 Linaro Ltd.
  */
 #ifndef QC_MSM_CAMSS_ISPIF_H
 #define QC_MSM_CAMSS_ISPIF_H
@@ -23,14 +15,11 @@
 #include <media/v4l2-device.h>
 #include <media/v4l2-subdev.h>
 
-/* Number of ISPIF lines - same as number of CSID hardware modules */
-#define MSM_ISPIF_LINE_NUM 2
-
 #define MSM_ISPIF_PAD_SINK 0
 #define MSM_ISPIF_PAD_SRC 1
 #define MSM_ISPIF_PADS_NUM 2
 
-#define MSM_ISPIF_VFE_NUM 1
+#define MSM_ISPIF_VFE_NUM 2
 
 enum ispif_intf {
 	PIX0,
@@ -46,6 +35,7 @@ struct ispif_intf_cmd_reg {
 };
 
 struct ispif_line {
+	struct ispif_device *ispif;
 	u8 id;
 	u8 csid_id;
 	u8 vfe_id;
@@ -53,6 +43,8 @@ struct ispif_line {
 	struct v4l2_subdev subdev;
 	struct media_pad pads[MSM_ISPIF_PADS_NUM];
 	struct v4l2_mbus_framefmt fmt[MSM_ISPIF_PADS_NUM];
+	const u32 *formats;
+	unsigned int nformats;
 };
 
 struct ispif_device {
@@ -69,7 +61,8 @@ struct ispif_device {
 	struct mutex power_lock;
 	struct ispif_intf_cmd_reg intf_cmd[MSM_ISPIF_VFE_NUM];
 	struct mutex config_lock;
-	struct ispif_line line[MSM_ISPIF_LINE_NUM];
+	unsigned int line_num;
+	struct ispif_line *line;
 };
 
 struct resources_ispif;
diff --git a/drivers/media/platform/qcom/camss/camss-vfe-4-1.c b/drivers/media/platform/qcom/camss/camss-vfe-4-1.c
new file mode 100644
index 000000000000..da3a9fed9f2d
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss-vfe-4-1.c
@@ -0,0 +1,1018 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * camss-vfe-4-1.c
+ *
+ * Qualcomm MSM Camera Subsystem - VFE (Video Front End) Module v4.1
+ *
+ * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2015-2018 Linaro Ltd.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+
+#include "camss-vfe.h"
+
+#define VFE_0_HW_VERSION		0x000
+
+#define VFE_0_GLOBAL_RESET_CMD		0x00c
+#define VFE_0_GLOBAL_RESET_CMD_CORE	BIT(0)
+#define VFE_0_GLOBAL_RESET_CMD_CAMIF	BIT(1)
+#define VFE_0_GLOBAL_RESET_CMD_BUS	BIT(2)
+#define VFE_0_GLOBAL_RESET_CMD_BUS_BDG	BIT(3)
+#define VFE_0_GLOBAL_RESET_CMD_REGISTER	BIT(4)
+#define VFE_0_GLOBAL_RESET_CMD_TIMER	BIT(5)
+#define VFE_0_GLOBAL_RESET_CMD_PM	BIT(6)
+#define VFE_0_GLOBAL_RESET_CMD_BUS_MISR	BIT(7)
+#define VFE_0_GLOBAL_RESET_CMD_TESTGEN	BIT(8)
+
+#define VFE_0_MODULE_CFG		0x018
+#define VFE_0_MODULE_CFG_DEMUX			BIT(2)
+#define VFE_0_MODULE_CFG_CHROMA_UPSAMPLE	BIT(3)
+#define VFE_0_MODULE_CFG_SCALE_ENC		BIT(23)
+#define VFE_0_MODULE_CFG_CROP_ENC		BIT(27)
+
+#define VFE_0_CORE_CFG			0x01c
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_YCBYCR	0x4
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_YCRYCB	0x5
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_CBYCRY	0x6
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_CRYCBY	0x7
+
+#define VFE_0_IRQ_CMD			0x024
+#define VFE_0_IRQ_CMD_GLOBAL_CLEAR	BIT(0)
+
+#define VFE_0_IRQ_MASK_0		0x028
+#define VFE_0_IRQ_MASK_0_CAMIF_SOF			BIT(0)
+#define VFE_0_IRQ_MASK_0_CAMIF_EOF			BIT(1)
+#define VFE_0_IRQ_MASK_0_RDIn_REG_UPDATE(n)		BIT((n) + 5)
+#define VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(n)		\
+	((n) == VFE_LINE_PIX ? BIT(4) : VFE_0_IRQ_MASK_0_RDIn_REG_UPDATE(n))
+#define VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(n)	BIT((n) + 8)
+#define VFE_0_IRQ_MASK_0_IMAGE_COMPOSITE_DONE_n(n)	BIT((n) + 25)
+#define VFE_0_IRQ_MASK_0_RESET_ACK			BIT(31)
+#define VFE_0_IRQ_MASK_1		0x02c
+#define VFE_0_IRQ_MASK_1_CAMIF_ERROR			BIT(0)
+#define VFE_0_IRQ_MASK_1_VIOLATION			BIT(7)
+#define VFE_0_IRQ_MASK_1_BUS_BDG_HALT_ACK		BIT(8)
+#define VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(n)	BIT((n) + 9)
+#define VFE_0_IRQ_MASK_1_RDIn_SOF(n)			BIT((n) + 29)
+
+#define VFE_0_IRQ_CLEAR_0		0x030
+#define VFE_0_IRQ_CLEAR_1		0x034
+
+#define VFE_0_IRQ_STATUS_0		0x038
+#define VFE_0_IRQ_STATUS_0_CAMIF_SOF			BIT(0)
+#define VFE_0_IRQ_STATUS_0_RDIn_REG_UPDATE(n)		BIT((n) + 5)
+#define VFE_0_IRQ_STATUS_0_line_n_REG_UPDATE(n)		\
+	((n) == VFE_LINE_PIX ? BIT(4) : VFE_0_IRQ_STATUS_0_RDIn_REG_UPDATE(n))
+#define VFE_0_IRQ_STATUS_0_IMAGE_MASTER_n_PING_PONG(n)	BIT((n) + 8)
+#define VFE_0_IRQ_STATUS_0_IMAGE_COMPOSITE_DONE_n(n)	BIT((n) + 25)
+#define VFE_0_IRQ_STATUS_0_RESET_ACK			BIT(31)
+#define VFE_0_IRQ_STATUS_1		0x03c
+#define VFE_0_IRQ_STATUS_1_VIOLATION			BIT(7)
+#define VFE_0_IRQ_STATUS_1_BUS_BDG_HALT_ACK		BIT(8)
+#define VFE_0_IRQ_STATUS_1_RDIn_SOF(n)			BIT((n) + 29)
+
+#define VFE_0_IRQ_COMPOSITE_MASK_0	0x40
+#define VFE_0_VIOLATION_STATUS		0x48
+
+#define VFE_0_BUS_CMD			0x4c
+#define VFE_0_BUS_CMD_Mx_RLD_CMD(x)	BIT(x)
+
+#define VFE_0_BUS_CFG			0x050
+
+#define VFE_0_BUS_XBAR_CFG_x(x)		(0x58 + 0x4 * ((x) / 2))
+#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN			BIT(1)
+#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA	(0x3 << 4)
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT		8
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_LUMA		0
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0	5
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1	6
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2	7
+
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(n)		(0x06c + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT	0
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_FRM_BASED_SHIFT	1
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_PING_ADDR(n)	(0x070 + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_PONG_ADDR(n)	(0x074 + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(n)		(0x078 + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_SHIFT	2
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK	(0x1f << 2)
+
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG(n)		(0x07c + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG_OFFSET_SHIFT	16
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(n)	(0x080 + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(n)	(0x084 + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_FRAMEDROP_PATTERN(n)	\
+							(0x088 + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN(n)	\
+							(0x08c + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN_DEF	0xffffffff
+
+#define VFE_0_BUS_PING_PONG_STATUS	0x268
+
+#define VFE_0_BUS_BDG_CMD		0x2c0
+#define VFE_0_BUS_BDG_CMD_HALT_REQ	1
+
+#define VFE_0_BUS_BDG_QOS_CFG_0		0x2c4
+#define VFE_0_BUS_BDG_QOS_CFG_0_CFG	0xaaa5aaa5
+#define VFE_0_BUS_BDG_QOS_CFG_1		0x2c8
+#define VFE_0_BUS_BDG_QOS_CFG_2		0x2cc
+#define VFE_0_BUS_BDG_QOS_CFG_3		0x2d0
+#define VFE_0_BUS_BDG_QOS_CFG_4		0x2d4
+#define VFE_0_BUS_BDG_QOS_CFG_5		0x2d8
+#define VFE_0_BUS_BDG_QOS_CFG_6		0x2dc
+#define VFE_0_BUS_BDG_QOS_CFG_7		0x2e0
+#define VFE_0_BUS_BDG_QOS_CFG_7_CFG	0x0001aaa5
+
+#define VFE_0_RDI_CFG_x(x)		(0x2e8 + (0x4 * (x)))
+#define VFE_0_RDI_CFG_x_RDI_STREAM_SEL_SHIFT	28
+#define VFE_0_RDI_CFG_x_RDI_STREAM_SEL_MASK	(0xf << 28)
+#define VFE_0_RDI_CFG_x_RDI_M0_SEL_SHIFT	4
+#define VFE_0_RDI_CFG_x_RDI_M0_SEL_MASK		(0xf << 4)
+#define VFE_0_RDI_CFG_x_RDI_EN_BIT		BIT(2)
+#define VFE_0_RDI_CFG_x_MIPI_EN_BITS		0x3
+#define VFE_0_RDI_CFG_x_RDI_Mr_FRAME_BASED_EN(r)	BIT(16 + (r))
+
+#define VFE_0_CAMIF_CMD				0x2f4
+#define VFE_0_CAMIF_CMD_DISABLE_FRAME_BOUNDARY	0
+#define VFE_0_CAMIF_CMD_ENABLE_FRAME_BOUNDARY	1
+#define VFE_0_CAMIF_CMD_NO_CHANGE		3
+#define VFE_0_CAMIF_CMD_CLEAR_CAMIF_STATUS	BIT(2)
+#define VFE_0_CAMIF_CFG				0x2f8
+#define VFE_0_CAMIF_CFG_VFE_OUTPUT_EN		BIT(6)
+#define VFE_0_CAMIF_FRAME_CFG			0x300
+#define VFE_0_CAMIF_WINDOW_WIDTH_CFG		0x304
+#define VFE_0_CAMIF_WINDOW_HEIGHT_CFG		0x308
+#define VFE_0_CAMIF_SUBSAMPLE_CFG_0		0x30c
+#define VFE_0_CAMIF_IRQ_SUBSAMPLE_PATTERN	0x314
+#define VFE_0_CAMIF_STATUS			0x31c
+#define VFE_0_CAMIF_STATUS_HALT			BIT(31)
+
+#define VFE_0_REG_UPDATE			0x378
+#define VFE_0_REG_UPDATE_RDIn(n)		BIT(1 + (n))
+#define VFE_0_REG_UPDATE_line_n(n)		\
+			((n) == VFE_LINE_PIX ? 1 : VFE_0_REG_UPDATE_RDIn(n))
+
+#define VFE_0_DEMUX_CFG				0x424
+#define VFE_0_DEMUX_CFG_PERIOD			0x3
+#define VFE_0_DEMUX_GAIN_0			0x428
+#define VFE_0_DEMUX_GAIN_0_CH0_EVEN		(0x80 << 0)
+#define VFE_0_DEMUX_GAIN_0_CH0_ODD		(0x80 << 16)
+#define VFE_0_DEMUX_GAIN_1			0x42c
+#define VFE_0_DEMUX_GAIN_1_CH1			(0x80 << 0)
+#define VFE_0_DEMUX_GAIN_1_CH2			(0x80 << 16)
+#define VFE_0_DEMUX_EVEN_CFG			0x438
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_YUYV	0x9cac
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_YVYU	0xac9c
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_UYVY	0xc9ca
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_VYUY	0xcac9
+#define VFE_0_DEMUX_ODD_CFG			0x43c
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_YUYV	0x9cac
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_YVYU	0xac9c
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_UYVY	0xc9ca
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_VYUY	0xcac9
+
+#define VFE_0_SCALE_ENC_Y_CFG			0x75c
+#define VFE_0_SCALE_ENC_Y_H_IMAGE_SIZE		0x760
+#define VFE_0_SCALE_ENC_Y_H_PHASE		0x764
+#define VFE_0_SCALE_ENC_Y_V_IMAGE_SIZE		0x76c
+#define VFE_0_SCALE_ENC_Y_V_PHASE		0x770
+#define VFE_0_SCALE_ENC_CBCR_CFG		0x778
+#define VFE_0_SCALE_ENC_CBCR_H_IMAGE_SIZE	0x77c
+#define VFE_0_SCALE_ENC_CBCR_H_PHASE		0x780
+#define VFE_0_SCALE_ENC_CBCR_V_IMAGE_SIZE	0x790
+#define VFE_0_SCALE_ENC_CBCR_V_PHASE		0x794
+
+#define VFE_0_CROP_ENC_Y_WIDTH			0x854
+#define VFE_0_CROP_ENC_Y_HEIGHT			0x858
+#define VFE_0_CROP_ENC_CBCR_WIDTH		0x85c
+#define VFE_0_CROP_ENC_CBCR_HEIGHT		0x860
+
+#define VFE_0_CLAMP_ENC_MAX_CFG			0x874
+#define VFE_0_CLAMP_ENC_MAX_CFG_CH0		(0xff << 0)
+#define VFE_0_CLAMP_ENC_MAX_CFG_CH1		(0xff << 8)
+#define VFE_0_CLAMP_ENC_MAX_CFG_CH2		(0xff << 16)
+#define VFE_0_CLAMP_ENC_MIN_CFG			0x878
+#define VFE_0_CLAMP_ENC_MIN_CFG_CH0		(0x0 << 0)
+#define VFE_0_CLAMP_ENC_MIN_CFG_CH1		(0x0 << 8)
+#define VFE_0_CLAMP_ENC_MIN_CFG_CH2		(0x0 << 16)
+
+#define VFE_0_CGC_OVERRIDE_1			0x974
+#define VFE_0_CGC_OVERRIDE_1_IMAGE_Mx_CGC_OVERRIDE(x)	BIT(x)
+
+#define CAMIF_TIMEOUT_SLEEP_US 1000
+#define CAMIF_TIMEOUT_ALL_US 1000000
+
+#define MSM_VFE_VFE0_UB_SIZE 1023
+#define MSM_VFE_VFE0_UB_SIZE_RDI (MSM_VFE_VFE0_UB_SIZE / 3)
+
+static void vfe_hw_version_read(struct vfe_device *vfe, struct device *dev)
+{
+	u32 hw_version = readl_relaxed(vfe->base + VFE_0_HW_VERSION);
+
+	dev_dbg(dev, "VFE HW Version = 0x%08x\n", hw_version);
+}
+
+static u16 vfe_get_ub_size(u8 vfe_id)
+{
+	if (vfe_id == 0)
+		return MSM_VFE_VFE0_UB_SIZE_RDI;
+
+	return 0;
+}
+
+static inline void vfe_reg_clr(struct vfe_device *vfe, u32 reg, u32 clr_bits)
+{
+	u32 bits = readl_relaxed(vfe->base + reg);
+
+	writel_relaxed(bits & ~clr_bits, vfe->base + reg);
+}
+
+static inline void vfe_reg_set(struct vfe_device *vfe, u32 reg, u32 set_bits)
+{
+	u32 bits = readl_relaxed(vfe->base + reg);
+
+	writel_relaxed(bits | set_bits, vfe->base + reg);
+}
+
+static void vfe_global_reset(struct vfe_device *vfe)
+{
+	u32 reset_bits = VFE_0_GLOBAL_RESET_CMD_TESTGEN		|
+			 VFE_0_GLOBAL_RESET_CMD_BUS_MISR	|
+			 VFE_0_GLOBAL_RESET_CMD_PM		|
+			 VFE_0_GLOBAL_RESET_CMD_TIMER		|
+			 VFE_0_GLOBAL_RESET_CMD_REGISTER	|
+			 VFE_0_GLOBAL_RESET_CMD_BUS_BDG		|
+			 VFE_0_GLOBAL_RESET_CMD_BUS		|
+			 VFE_0_GLOBAL_RESET_CMD_CAMIF		|
+			 VFE_0_GLOBAL_RESET_CMD_CORE;
+
+	writel_relaxed(reset_bits, vfe->base + VFE_0_GLOBAL_RESET_CMD);
+}
+
+static void vfe_halt_request(struct vfe_device *vfe)
+{
+	writel_relaxed(VFE_0_BUS_BDG_CMD_HALT_REQ,
+		       vfe->base + VFE_0_BUS_BDG_CMD);
+}
+
+static void vfe_halt_clear(struct vfe_device *vfe)
+{
+	writel_relaxed(0x0, vfe->base + VFE_0_BUS_BDG_CMD);
+}
+
+static void vfe_wm_enable(struct vfe_device *vfe, u8 wm, u8 enable)
+{
+	if (enable)
+		vfe_reg_set(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
+			    1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT);
+	else
+		vfe_reg_clr(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
+			    1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT);
+}
+
+static void vfe_wm_frame_based(struct vfe_device *vfe, u8 wm, u8 enable)
+{
+	if (enable)
+		vfe_reg_set(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
+			1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_FRM_BASED_SHIFT);
+	else
+		vfe_reg_clr(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
+			1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_FRM_BASED_SHIFT);
+}
+
+#define CALC_WORD(width, M, N) (((width) * (M) + (N) - 1) / (N))
+
+static int vfe_word_per_line(u32 format, u32 pixel_per_line)
+{
+	int val = 0;
+
+	switch (format) {
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV21:
+	case V4L2_PIX_FMT_NV16:
+	case V4L2_PIX_FMT_NV61:
+		val = CALC_WORD(pixel_per_line, 1, 8);
+		break;
+	case V4L2_PIX_FMT_YUYV:
+	case V4L2_PIX_FMT_YVYU:
+	case V4L2_PIX_FMT_UYVY:
+	case V4L2_PIX_FMT_VYUY:
+		val = CALC_WORD(pixel_per_line, 2, 8);
+		break;
+	}
+
+	return val;
+}
+
+static void vfe_get_wm_sizes(struct v4l2_pix_format_mplane *pix, u8 plane,
+			     u16 *width, u16 *height, u16 *bytesperline)
+{
+	switch (pix->pixelformat) {
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV21:
+		*width = pix->width;
+		*height = pix->height;
+		*bytesperline = pix->plane_fmt[0].bytesperline;
+		if (plane == 1)
+			*height /= 2;
+		break;
+	case V4L2_PIX_FMT_NV16:
+	case V4L2_PIX_FMT_NV61:
+		*width = pix->width;
+		*height = pix->height;
+		*bytesperline = pix->plane_fmt[0].bytesperline;
+		break;
+	}
+}
+
+static void vfe_wm_line_based(struct vfe_device *vfe, u32 wm,
+			      struct v4l2_pix_format_mplane *pix,
+			      u8 plane, u32 enable)
+{
+	u32 reg;
+
+	if (enable) {
+		u16 width = 0, height = 0, bytesperline = 0, wpl;
+
+		vfe_get_wm_sizes(pix, plane, &width, &height, &bytesperline);
+
+		wpl = vfe_word_per_line(pix->pixelformat, width);
+
+		reg = height - 1;
+		reg |= ((wpl + 1) / 2 - 1) << 16;
+
+		writel_relaxed(reg, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(wm));
+
+		wpl = vfe_word_per_line(pix->pixelformat, bytesperline);
+
+		reg = 0x3;
+		reg |= (height - 1) << 4;
+		reg |= wpl << 16;
+
+		writel_relaxed(reg, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(wm));
+	} else {
+		writel_relaxed(0, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(wm));
+		writel_relaxed(0, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(wm));
+	}
+}
+
+static void vfe_wm_set_framedrop_period(struct vfe_device *vfe, u8 wm, u8 per)
+{
+	u32 reg;
+
+	reg = readl_relaxed(vfe->base +
+			    VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm));
+
+	reg &= ~(VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK);
+
+	reg |= (per << VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_SHIFT)
+		& VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK;
+
+	writel_relaxed(reg,
+		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm));
+}
+
+static void vfe_wm_set_framedrop_pattern(struct vfe_device *vfe, u8 wm,
+					 u32 pattern)
+{
+	writel_relaxed(pattern,
+	       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_FRAMEDROP_PATTERN(wm));
+}
+
+static void vfe_wm_set_ub_cfg(struct vfe_device *vfe, u8 wm,
+			      u16 offset, u16 depth)
+{
+	u32 reg;
+
+	reg = (offset << VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG_OFFSET_SHIFT) |
+		depth;
+	writel_relaxed(reg, vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG(wm));
+}
+
+static void vfe_bus_reload_wm(struct vfe_device *vfe, u8 wm)
+{
+	wmb();
+	writel_relaxed(VFE_0_BUS_CMD_Mx_RLD_CMD(wm), vfe->base + VFE_0_BUS_CMD);
+	wmb();
+}
+
+static void vfe_wm_set_ping_addr(struct vfe_device *vfe, u8 wm, u32 addr)
+{
+	writel_relaxed(addr,
+		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_PING_ADDR(wm));
+}
+
+static void vfe_wm_set_pong_addr(struct vfe_device *vfe, u8 wm, u32 addr)
+{
+	writel_relaxed(addr,
+		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_PONG_ADDR(wm));
+}
+
+static int vfe_wm_get_ping_pong_status(struct vfe_device *vfe, u8 wm)
+{
+	u32 reg;
+
+	reg = readl_relaxed(vfe->base + VFE_0_BUS_PING_PONG_STATUS);
+
+	return (reg >> wm) & 0x1;
+}
+
+static void vfe_bus_enable_wr_if(struct vfe_device *vfe, u8 enable)
+{
+	if (enable)
+		writel_relaxed(0x10000009, vfe->base + VFE_0_BUS_CFG);
+	else
+		writel_relaxed(0, vfe->base + VFE_0_BUS_CFG);
+}
+
+static void vfe_bus_connect_wm_to_rdi(struct vfe_device *vfe, u8 wm,
+				      enum vfe_line_id id)
+{
+	u32 reg;
+
+	reg = VFE_0_RDI_CFG_x_MIPI_EN_BITS;
+	reg |= VFE_0_RDI_CFG_x_RDI_Mr_FRAME_BASED_EN(id);
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(0), reg);
+
+	reg = VFE_0_RDI_CFG_x_RDI_EN_BIT;
+	reg |= ((3 * id) << VFE_0_RDI_CFG_x_RDI_STREAM_SEL_SHIFT) &
+		VFE_0_RDI_CFG_x_RDI_STREAM_SEL_MASK;
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(id), reg);
+
+	switch (id) {
+	case VFE_LINE_RDI0:
+	default:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI1:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI2:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	}
+
+	if (wm % 2 == 1)
+		reg <<= 16;
+
+	vfe_reg_set(vfe, VFE_0_BUS_XBAR_CFG_x(wm), reg);
+}
+
+static void vfe_wm_set_subsample(struct vfe_device *vfe, u8 wm)
+{
+	writel_relaxed(VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN_DEF,
+		       vfe->base +
+		       VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN(wm));
+}
+
+static void vfe_bus_disconnect_wm_from_rdi(struct vfe_device *vfe, u8 wm,
+					   enum vfe_line_id id)
+{
+	u32 reg;
+
+	reg = VFE_0_RDI_CFG_x_RDI_Mr_FRAME_BASED_EN(id);
+	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(0), reg);
+
+	reg = VFE_0_RDI_CFG_x_RDI_EN_BIT;
+	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(id), reg);
+
+	switch (id) {
+	case VFE_LINE_RDI0:
+	default:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI1:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI2:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	}
+
+	if (wm % 2 == 1)
+		reg <<= 16;
+
+	vfe_reg_clr(vfe, VFE_0_BUS_XBAR_CFG_x(wm), reg);
+}
+
+static void vfe_set_xbar_cfg(struct vfe_device *vfe, struct vfe_output *output,
+			     u8 enable)
+{
+	struct vfe_line *line = container_of(output, struct vfe_line, output);
+	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
+	u32 reg;
+	unsigned int i;
+
+	for (i = 0; i < output->wm_num; i++) {
+		if (i == 0) {
+			reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_LUMA <<
+				VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		} else if (i == 1) {
+			reg = VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN;
+			if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV16)
+				reg |= VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA;
+		} else {
+			/* On current devices output->wm_num is always <= 2 */
+			break;
+		}
+
+		if (output->wm_idx[i] % 2 == 1)
+			reg <<= 16;
+
+		if (enable)
+			vfe_reg_set(vfe,
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[i]),
+				    reg);
+		else
+			vfe_reg_clr(vfe,
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[i]),
+				    reg);
+	}
+}
+
+static void vfe_set_realign_cfg(struct vfe_device *vfe, struct vfe_line *line,
+				u8 enable)
+{
+	/* empty */
+}
+static void vfe_set_rdi_cid(struct vfe_device *vfe, enum vfe_line_id id, u8 cid)
+{
+	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(id),
+		    VFE_0_RDI_CFG_x_RDI_M0_SEL_MASK);
+
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(id),
+		    cid << VFE_0_RDI_CFG_x_RDI_M0_SEL_SHIFT);
+}
+
+static void vfe_reg_update(struct vfe_device *vfe, enum vfe_line_id line_id)
+{
+	vfe->reg_update |= VFE_0_REG_UPDATE_line_n(line_id);
+	wmb();
+	writel_relaxed(vfe->reg_update, vfe->base + VFE_0_REG_UPDATE);
+	wmb();
+}
+
+static inline void vfe_reg_update_clear(struct vfe_device *vfe,
+					enum vfe_line_id line_id)
+{
+	vfe->reg_update &= ~VFE_0_REG_UPDATE_line_n(line_id);
+}
+
+static void vfe_enable_irq_wm_line(struct vfe_device *vfe, u8 wm,
+				   enum vfe_line_id line_id, u8 enable)
+{
+	u32 irq_en0 = VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(wm) |
+		      VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(line_id);
+	u32 irq_en1 = VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(wm) |
+		      VFE_0_IRQ_MASK_1_RDIn_SOF(line_id);
+
+	if (enable) {
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+	} else {
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+	}
+}
+
+static void vfe_enable_irq_pix_line(struct vfe_device *vfe, u8 comp,
+				    enum vfe_line_id line_id, u8 enable)
+{
+	struct vfe_output *output = &vfe->line[line_id].output;
+	unsigned int i;
+	u32 irq_en0;
+	u32 irq_en1;
+	u32 comp_mask = 0;
+
+	irq_en0 = VFE_0_IRQ_MASK_0_CAMIF_SOF;
+	irq_en0 |= VFE_0_IRQ_MASK_0_CAMIF_EOF;
+	irq_en0 |= VFE_0_IRQ_MASK_0_IMAGE_COMPOSITE_DONE_n(comp);
+	irq_en0 |= VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(line_id);
+	irq_en1 = VFE_0_IRQ_MASK_1_CAMIF_ERROR;
+	for (i = 0; i < output->wm_num; i++) {
+		irq_en1 |= VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(
+							output->wm_idx[i]);
+		comp_mask |= (1 << output->wm_idx[i]) << comp * 8;
+	}
+
+	if (enable) {
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+		vfe_reg_set(vfe, VFE_0_IRQ_COMPOSITE_MASK_0, comp_mask);
+	} else {
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+		vfe_reg_clr(vfe, VFE_0_IRQ_COMPOSITE_MASK_0, comp_mask);
+	}
+}
+
+static void vfe_enable_irq_common(struct vfe_device *vfe)
+{
+	u32 irq_en0 = VFE_0_IRQ_MASK_0_RESET_ACK;
+	u32 irq_en1 = VFE_0_IRQ_MASK_1_VIOLATION |
+		      VFE_0_IRQ_MASK_1_BUS_BDG_HALT_ACK;
+
+	vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+	vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+}
+
+static void vfe_set_demux_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 val, even_cfg, odd_cfg;
+
+	writel_relaxed(VFE_0_DEMUX_CFG_PERIOD, vfe->base + VFE_0_DEMUX_CFG);
+
+	val = VFE_0_DEMUX_GAIN_0_CH0_EVEN | VFE_0_DEMUX_GAIN_0_CH0_ODD;
+	writel_relaxed(val, vfe->base + VFE_0_DEMUX_GAIN_0);
+
+	val = VFE_0_DEMUX_GAIN_1_CH1 | VFE_0_DEMUX_GAIN_1_CH2;
+	writel_relaxed(val, vfe->base + VFE_0_DEMUX_GAIN_1);
+
+	switch (line->fmt[MSM_VFE_PAD_SINK].code) {
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_YUYV;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_YUYV;
+		break;
+	case MEDIA_BUS_FMT_YVYU8_2X8:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_YVYU;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_YVYU;
+		break;
+	case MEDIA_BUS_FMT_UYVY8_2X8:
+	default:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_UYVY;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_UYVY;
+		break;
+	case MEDIA_BUS_FMT_VYUY8_2X8:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_VYUY;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_VYUY;
+		break;
+	}
+
+	writel_relaxed(even_cfg, vfe->base + VFE_0_DEMUX_EVEN_CFG);
+	writel_relaxed(odd_cfg, vfe->base + VFE_0_DEMUX_ODD_CFG);
+}
+
+static inline u8 vfe_calc_interp_reso(u16 input, u16 output)
+{
+	if (input / output >= 16)
+		return 0;
+
+	if (input / output >= 8)
+		return 1;
+
+	if (input / output >= 4)
+		return 2;
+
+	return 3;
+}
+
+static void vfe_set_scale_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
+	u32 reg;
+	u16 input, output;
+	u8 interp_reso;
+	u32 phase_mult;
+
+	writel_relaxed(0x3, vfe->base + VFE_0_SCALE_ENC_Y_CFG);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].width;
+	output = line->compose.width;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_H_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (13 + interp_reso)) / output;
+	reg = (interp_reso << 20) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_H_PHASE);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].height;
+	output = line->compose.height;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_V_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (13 + interp_reso)) / output;
+	reg = (interp_reso << 20) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_V_PHASE);
+
+	writel_relaxed(0x3, vfe->base + VFE_0_SCALE_ENC_CBCR_CFG);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].width;
+	output = line->compose.width / 2;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_H_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (13 + interp_reso)) / output;
+	reg = (interp_reso << 20) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_H_PHASE);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].height;
+	output = line->compose.height;
+	if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV21)
+		output = line->compose.height / 2;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_V_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (13 + interp_reso)) / output;
+	reg = (interp_reso << 20) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_V_PHASE);
+}
+
+static void vfe_set_crop_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
+	u32 reg;
+	u16 first, last;
+
+	first = line->crop.left;
+	last = line->crop.left + line->crop.width - 1;
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_Y_WIDTH);
+
+	first = line->crop.top;
+	last = line->crop.top + line->crop.height - 1;
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_Y_HEIGHT);
+
+	first = line->crop.left / 2;
+	last = line->crop.left / 2 + line->crop.width / 2 - 1;
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_CBCR_WIDTH);
+
+	first = line->crop.top;
+	last = line->crop.top + line->crop.height - 1;
+	if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV21) {
+		first = line->crop.top / 2;
+		last = line->crop.top / 2 + line->crop.height / 2 - 1;
+	}
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_CBCR_HEIGHT);
+}
+
+static void vfe_set_clamp_cfg(struct vfe_device *vfe)
+{
+	u32 val = VFE_0_CLAMP_ENC_MAX_CFG_CH0 |
+		VFE_0_CLAMP_ENC_MAX_CFG_CH1 |
+		VFE_0_CLAMP_ENC_MAX_CFG_CH2;
+
+	writel_relaxed(val, vfe->base + VFE_0_CLAMP_ENC_MAX_CFG);
+
+	val = VFE_0_CLAMP_ENC_MIN_CFG_CH0 |
+		VFE_0_CLAMP_ENC_MIN_CFG_CH1 |
+		VFE_0_CLAMP_ENC_MIN_CFG_CH2;
+
+	writel_relaxed(val, vfe->base + VFE_0_CLAMP_ENC_MIN_CFG);
+}
+
+static void vfe_set_qos(struct vfe_device *vfe)
+{
+	u32 val = VFE_0_BUS_BDG_QOS_CFG_0_CFG;
+	u32 val7 = VFE_0_BUS_BDG_QOS_CFG_7_CFG;
+
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_0);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_1);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_2);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_3);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_4);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_5);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_6);
+	writel_relaxed(val7, vfe->base + VFE_0_BUS_BDG_QOS_CFG_7);
+}
+
+static void vfe_set_ds(struct vfe_device *vfe)
+{
+	/* empty */
+}
+
+static void vfe_set_cgc_override(struct vfe_device *vfe, u8 wm, u8 enable)
+{
+	u32 val = VFE_0_CGC_OVERRIDE_1_IMAGE_Mx_CGC_OVERRIDE(wm);
+
+	if (enable)
+		vfe_reg_set(vfe, VFE_0_CGC_OVERRIDE_1, val);
+	else
+		vfe_reg_clr(vfe, VFE_0_CGC_OVERRIDE_1, val);
+
+	wmb();
+}
+
+static void vfe_set_camif_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 val;
+
+	switch (line->fmt[MSM_VFE_PAD_SINK].code) {
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_YCBYCR;
+		break;
+	case MEDIA_BUS_FMT_YVYU8_2X8:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_YCRYCB;
+		break;
+	case MEDIA_BUS_FMT_UYVY8_2X8:
+	default:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_CBYCRY;
+		break;
+	case MEDIA_BUS_FMT_VYUY8_2X8:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_CRYCBY;
+		break;
+	}
+
+	writel_relaxed(val, vfe->base + VFE_0_CORE_CFG);
+
+	val = line->fmt[MSM_VFE_PAD_SINK].width * 2;
+	val |= line->fmt[MSM_VFE_PAD_SINK].height << 16;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_FRAME_CFG);
+
+	val = line->fmt[MSM_VFE_PAD_SINK].width * 2 - 1;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_WINDOW_WIDTH_CFG);
+
+	val = line->fmt[MSM_VFE_PAD_SINK].height - 1;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_WINDOW_HEIGHT_CFG);
+
+	val = 0xffffffff;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_SUBSAMPLE_CFG_0);
+
+	val = 0xffffffff;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_IRQ_SUBSAMPLE_PATTERN);
+
+	val = VFE_0_RDI_CFG_x_MIPI_EN_BITS;
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(0), val);
+
+	val = VFE_0_CAMIF_CFG_VFE_OUTPUT_EN;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_CFG);
+}
+
+static void vfe_set_camif_cmd(struct vfe_device *vfe, u8 enable)
+{
+	u32 cmd;
+
+	cmd = VFE_0_CAMIF_CMD_CLEAR_CAMIF_STATUS | VFE_0_CAMIF_CMD_NO_CHANGE;
+	writel_relaxed(cmd, vfe->base + VFE_0_CAMIF_CMD);
+	wmb();
+
+	if (enable)
+		cmd = VFE_0_CAMIF_CMD_ENABLE_FRAME_BOUNDARY;
+	else
+		cmd = VFE_0_CAMIF_CMD_DISABLE_FRAME_BOUNDARY;
+
+	writel_relaxed(cmd, vfe->base + VFE_0_CAMIF_CMD);
+}
+
+static void vfe_set_module_cfg(struct vfe_device *vfe, u8 enable)
+{
+	u32 val = VFE_0_MODULE_CFG_DEMUX |
+		  VFE_0_MODULE_CFG_CHROMA_UPSAMPLE |
+		  VFE_0_MODULE_CFG_SCALE_ENC |
+		  VFE_0_MODULE_CFG_CROP_ENC;
+
+	if (enable)
+		writel_relaxed(val, vfe->base + VFE_0_MODULE_CFG);
+	else
+		writel_relaxed(0x0, vfe->base + VFE_0_MODULE_CFG);
+}
+
+static int vfe_camif_wait_for_stop(struct vfe_device *vfe, struct device *dev)
+{
+	u32 val;
+	int ret;
+
+	ret = readl_poll_timeout(vfe->base + VFE_0_CAMIF_STATUS,
+				 val,
+				 (val & VFE_0_CAMIF_STATUS_HALT),
+				 CAMIF_TIMEOUT_SLEEP_US,
+				 CAMIF_TIMEOUT_ALL_US);
+	if (ret < 0)
+		dev_err(dev, "%s: camif stop timeout\n", __func__);
+
+	return ret;
+}
+
+static void vfe_isr_read(struct vfe_device *vfe, u32 *value0, u32 *value1)
+{
+	*value0 = readl_relaxed(vfe->base + VFE_0_IRQ_STATUS_0);
+	*value1 = readl_relaxed(vfe->base + VFE_0_IRQ_STATUS_1);
+
+	writel_relaxed(*value0, vfe->base + VFE_0_IRQ_CLEAR_0);
+	writel_relaxed(*value1, vfe->base + VFE_0_IRQ_CLEAR_1);
+
+	wmb();
+	writel_relaxed(VFE_0_IRQ_CMD_GLOBAL_CLEAR, vfe->base + VFE_0_IRQ_CMD);
+}
+
+static void vfe_violation_read(struct vfe_device *vfe)
+{
+	u32 violation = readl_relaxed(vfe->base + VFE_0_VIOLATION_STATUS);
+
+	pr_err_ratelimited("VFE: violation = 0x%08x\n", violation);
+}
+
+/*
+ * vfe_isr - ISPIF module interrupt handler
+ * @irq: Interrupt line
+ * @dev: VFE device
+ *
+ * Return IRQ_HANDLED on success
+ */
+static irqreturn_t vfe_isr(int irq, void *dev)
+{
+	struct vfe_device *vfe = dev;
+	u32 value0, value1;
+	int i, j;
+
+	vfe->ops->isr_read(vfe, &value0, &value1);
+
+	trace_printk("VFE: status0 = 0x%08x, status1 = 0x%08x\n",
+		     value0, value1);
+
+	if (value0 & VFE_0_IRQ_STATUS_0_RESET_ACK)
+		vfe->isr_ops.reset_ack(vfe);
+
+	if (value1 & VFE_0_IRQ_STATUS_1_VIOLATION)
+		vfe->ops->violation_read(vfe);
+
+	if (value1 & VFE_0_IRQ_STATUS_1_BUS_BDG_HALT_ACK)
+		vfe->isr_ops.halt_ack(vfe);
+
+	for (i = VFE_LINE_RDI0; i <= VFE_LINE_PIX; i++)
+		if (value0 & VFE_0_IRQ_STATUS_0_line_n_REG_UPDATE(i))
+			vfe->isr_ops.reg_update(vfe, i);
+
+	if (value0 & VFE_0_IRQ_STATUS_0_CAMIF_SOF)
+		vfe->isr_ops.sof(vfe, VFE_LINE_PIX);
+
+	for (i = VFE_LINE_RDI0; i <= VFE_LINE_RDI2; i++)
+		if (value1 & VFE_0_IRQ_STATUS_1_RDIn_SOF(i))
+			vfe->isr_ops.sof(vfe, i);
+
+	for (i = 0; i < MSM_VFE_COMPOSITE_IRQ_NUM; i++)
+		if (value0 & VFE_0_IRQ_STATUS_0_IMAGE_COMPOSITE_DONE_n(i)) {
+			vfe->isr_ops.comp_done(vfe, i);
+			for (j = 0; j < ARRAY_SIZE(vfe->wm_output_map); j++)
+				if (vfe->wm_output_map[j] == VFE_LINE_PIX)
+					value0 &= ~VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(j);
+		}
+
+	for (i = 0; i < MSM_VFE_IMAGE_MASTERS_NUM; i++)
+		if (value0 & VFE_0_IRQ_STATUS_0_IMAGE_MASTER_n_PING_PONG(i))
+			vfe->isr_ops.wm_done(vfe, i);
+
+	return IRQ_HANDLED;
+}
+
+const struct vfe_hw_ops vfe_ops_4_1 = {
+	.hw_version_read = vfe_hw_version_read,
+	.get_ub_size = vfe_get_ub_size,
+	.global_reset = vfe_global_reset,
+	.halt_request = vfe_halt_request,
+	.halt_clear = vfe_halt_clear,
+	.wm_enable = vfe_wm_enable,
+	.wm_frame_based = vfe_wm_frame_based,
+	.wm_line_based = vfe_wm_line_based,
+	.wm_set_framedrop_period = vfe_wm_set_framedrop_period,
+	.wm_set_framedrop_pattern = vfe_wm_set_framedrop_pattern,
+	.wm_set_ub_cfg = vfe_wm_set_ub_cfg,
+	.bus_reload_wm = vfe_bus_reload_wm,
+	.wm_set_ping_addr = vfe_wm_set_ping_addr,
+	.wm_set_pong_addr = vfe_wm_set_pong_addr,
+	.wm_get_ping_pong_status = vfe_wm_get_ping_pong_status,
+	.bus_enable_wr_if = vfe_bus_enable_wr_if,
+	.bus_connect_wm_to_rdi = vfe_bus_connect_wm_to_rdi,
+	.wm_set_subsample = vfe_wm_set_subsample,
+	.bus_disconnect_wm_from_rdi = vfe_bus_disconnect_wm_from_rdi,
+	.set_xbar_cfg = vfe_set_xbar_cfg,
+	.set_realign_cfg = vfe_set_realign_cfg,
+	.set_rdi_cid = vfe_set_rdi_cid,
+	.reg_update = vfe_reg_update,
+	.reg_update_clear = vfe_reg_update_clear,
+	.enable_irq_wm_line = vfe_enable_irq_wm_line,
+	.enable_irq_pix_line = vfe_enable_irq_pix_line,
+	.enable_irq_common = vfe_enable_irq_common,
+	.set_demux_cfg = vfe_set_demux_cfg,
+	.set_scale_cfg = vfe_set_scale_cfg,
+	.set_crop_cfg = vfe_set_crop_cfg,
+	.set_clamp_cfg = vfe_set_clamp_cfg,
+	.set_qos = vfe_set_qos,
+	.set_ds = vfe_set_ds,
+	.set_cgc_override = vfe_set_cgc_override,
+	.set_camif_cfg = vfe_set_camif_cfg,
+	.set_camif_cmd = vfe_set_camif_cmd,
+	.set_module_cfg = vfe_set_module_cfg,
+	.camif_wait_for_stop = vfe_camif_wait_for_stop,
+	.isr_read = vfe_isr_read,
+	.violation_read = vfe_violation_read,
+	.isr = vfe_isr,
+};
diff --git a/drivers/media/platform/qcom/camss/camss-vfe-4-7.c b/drivers/media/platform/qcom/camss/camss-vfe-4-7.c
new file mode 100644
index 000000000000..4c584bffd179
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss-vfe-4-7.c
@@ -0,0 +1,1140 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * camss-vfe-4-7.c
+ *
+ * Qualcomm MSM Camera Subsystem - VFE (Video Front End) Module v4.7
+ *
+ * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2015-2018 Linaro Ltd.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+
+#include "camss-vfe.h"
+
+#define VFE_0_HW_VERSION		0x000
+
+#define VFE_0_GLOBAL_RESET_CMD		0x018
+#define VFE_0_GLOBAL_RESET_CMD_CORE	BIT(0)
+#define VFE_0_GLOBAL_RESET_CMD_CAMIF	BIT(1)
+#define VFE_0_GLOBAL_RESET_CMD_BUS	BIT(2)
+#define VFE_0_GLOBAL_RESET_CMD_BUS_BDG	BIT(3)
+#define VFE_0_GLOBAL_RESET_CMD_REGISTER	BIT(4)
+#define VFE_0_GLOBAL_RESET_CMD_PM	BIT(5)
+#define VFE_0_GLOBAL_RESET_CMD_BUS_MISR	BIT(6)
+#define VFE_0_GLOBAL_RESET_CMD_TESTGEN	BIT(7)
+#define VFE_0_GLOBAL_RESET_CMD_DSP	BIT(8)
+#define VFE_0_GLOBAL_RESET_CMD_IDLE_CGC	BIT(9)
+
+#define VFE_0_MODULE_LENS_EN		0x040
+#define VFE_0_MODULE_LENS_EN_DEMUX		BIT(2)
+#define VFE_0_MODULE_LENS_EN_CHROMA_UPSAMPLE	BIT(3)
+
+#define VFE_0_MODULE_ZOOM_EN		0x04c
+#define VFE_0_MODULE_ZOOM_EN_SCALE_ENC		BIT(1)
+#define VFE_0_MODULE_ZOOM_EN_CROP_ENC		BIT(2)
+#define VFE_0_MODULE_ZOOM_EN_REALIGN_BUF	BIT(9)
+
+#define VFE_0_CORE_CFG			0x050
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_YCBYCR	0x4
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_YCRYCB	0x5
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_CBYCRY	0x6
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_CRYCBY	0x7
+#define VFE_0_CORE_CFG_COMPOSITE_REG_UPDATE_EN	BIT(4)
+
+#define VFE_0_IRQ_CMD			0x058
+#define VFE_0_IRQ_CMD_GLOBAL_CLEAR	BIT(0)
+
+#define VFE_0_IRQ_MASK_0		0x05c
+#define VFE_0_IRQ_MASK_0_CAMIF_SOF			BIT(0)
+#define VFE_0_IRQ_MASK_0_CAMIF_EOF			BIT(1)
+#define VFE_0_IRQ_MASK_0_RDIn_REG_UPDATE(n)		BIT((n) + 5)
+#define VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(n)		\
+	((n) == VFE_LINE_PIX ? BIT(4) : VFE_0_IRQ_MASK_0_RDIn_REG_UPDATE(n))
+#define VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(n)	BIT((n) + 8)
+#define VFE_0_IRQ_MASK_0_IMAGE_COMPOSITE_DONE_n(n)	BIT((n) + 25)
+#define VFE_0_IRQ_MASK_0_RESET_ACK			BIT(31)
+#define VFE_0_IRQ_MASK_1		0x060
+#define VFE_0_IRQ_MASK_1_CAMIF_ERROR			BIT(0)
+#define VFE_0_IRQ_MASK_1_VIOLATION			BIT(7)
+#define VFE_0_IRQ_MASK_1_BUS_BDG_HALT_ACK		BIT(8)
+#define VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(n)	BIT((n) + 9)
+#define VFE_0_IRQ_MASK_1_RDIn_SOF(n)			BIT((n) + 29)
+
+#define VFE_0_IRQ_CLEAR_0		0x064
+#define VFE_0_IRQ_CLEAR_1		0x068
+
+#define VFE_0_IRQ_STATUS_0		0x06c
+#define VFE_0_IRQ_STATUS_0_CAMIF_SOF			BIT(0)
+#define VFE_0_IRQ_STATUS_0_RDIn_REG_UPDATE(n)		BIT((n) + 5)
+#define VFE_0_IRQ_STATUS_0_line_n_REG_UPDATE(n)		\
+	((n) == VFE_LINE_PIX ? BIT(4) : VFE_0_IRQ_STATUS_0_RDIn_REG_UPDATE(n))
+#define VFE_0_IRQ_STATUS_0_IMAGE_MASTER_n_PING_PONG(n)	BIT((n) + 8)
+#define VFE_0_IRQ_STATUS_0_IMAGE_COMPOSITE_DONE_n(n)	BIT((n) + 25)
+#define VFE_0_IRQ_STATUS_0_RESET_ACK			BIT(31)
+#define VFE_0_IRQ_STATUS_1		0x070
+#define VFE_0_IRQ_STATUS_1_VIOLATION			BIT(7)
+#define VFE_0_IRQ_STATUS_1_BUS_BDG_HALT_ACK		BIT(8)
+#define VFE_0_IRQ_STATUS_1_RDIn_SOF(n)			BIT((n) + 29)
+
+#define VFE_0_IRQ_COMPOSITE_MASK_0	0x074
+#define VFE_0_VIOLATION_STATUS		0x07c
+
+#define VFE_0_BUS_CMD			0x80
+#define VFE_0_BUS_CMD_Mx_RLD_CMD(x)	BIT(x)
+
+#define VFE_0_BUS_CFG			0x084
+
+#define VFE_0_BUS_XBAR_CFG_x(x)		(0x90 + 0x4 * ((x) / 2))
+#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN			BIT(2)
+#define VFE_0_BUS_XBAR_CFG_x_M_REALIGN_BUF_EN			BIT(3)
+#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTRA		(0x1 << 4)
+#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER		(0x2 << 4)
+#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA	(0x3 << 4)
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT		8
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_LUMA		0x0
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0	0xc
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1	0xd
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2	0xe
+
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(n)		(0x0a0 + 0x2c * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT	0
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_PING_ADDR(n)	(0x0a4 + 0x2c * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_PONG_ADDR(n)	(0x0ac + 0x2c * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(n)		(0x0b4 + 0x2c * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_BASED_SHIFT	1
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_SHIFT	2
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK	(0x1f << 2)
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG(n)		(0x0b8 + 0x2c * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG_OFFSET_SHIFT	16
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(n)	(0x0bc + 0x2c * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(n)	(0x0c0 + 0x2c * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_FRAMEDROP_PATTERN(n)	\
+							(0x0c4 + 0x2c * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN(n)	\
+							(0x0c8 + 0x2c * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN_DEF	0xffffffff
+
+#define VFE_0_BUS_PING_PONG_STATUS	0x338
+
+#define VFE_0_BUS_BDG_CMD		0x400
+#define VFE_0_BUS_BDG_CMD_HALT_REQ	1
+
+#define VFE_0_BUS_BDG_QOS_CFG_0		0x404
+#define VFE_0_BUS_BDG_QOS_CFG_0_CFG	0xaaa9aaa9
+#define VFE_0_BUS_BDG_QOS_CFG_1		0x408
+#define VFE_0_BUS_BDG_QOS_CFG_2		0x40c
+#define VFE_0_BUS_BDG_QOS_CFG_3		0x410
+#define VFE_0_BUS_BDG_QOS_CFG_4		0x414
+#define VFE_0_BUS_BDG_QOS_CFG_5		0x418
+#define VFE_0_BUS_BDG_QOS_CFG_6		0x41c
+#define VFE_0_BUS_BDG_QOS_CFG_7		0x420
+#define VFE_0_BUS_BDG_QOS_CFG_7_CFG	0x0001aaa9
+
+#define VFE_0_BUS_BDG_DS_CFG_0		0x424
+#define VFE_0_BUS_BDG_DS_CFG_0_CFG	0xcccc0011
+#define VFE_0_BUS_BDG_DS_CFG_1		0x428
+#define VFE_0_BUS_BDG_DS_CFG_2		0x42c
+#define VFE_0_BUS_BDG_DS_CFG_3		0x430
+#define VFE_0_BUS_BDG_DS_CFG_4		0x434
+#define VFE_0_BUS_BDG_DS_CFG_5		0x438
+#define VFE_0_BUS_BDG_DS_CFG_6		0x43c
+#define VFE_0_BUS_BDG_DS_CFG_7		0x440
+#define VFE_0_BUS_BDG_DS_CFG_8		0x444
+#define VFE_0_BUS_BDG_DS_CFG_9		0x448
+#define VFE_0_BUS_BDG_DS_CFG_10		0x44c
+#define VFE_0_BUS_BDG_DS_CFG_11		0x450
+#define VFE_0_BUS_BDG_DS_CFG_12		0x454
+#define VFE_0_BUS_BDG_DS_CFG_13		0x458
+#define VFE_0_BUS_BDG_DS_CFG_14		0x45c
+#define VFE_0_BUS_BDG_DS_CFG_15		0x460
+#define VFE_0_BUS_BDG_DS_CFG_16		0x464
+#define VFE_0_BUS_BDG_DS_CFG_16_CFG	0x40000103
+
+#define VFE_0_RDI_CFG_x(x)		(0x46c + (0x4 * (x)))
+#define VFE_0_RDI_CFG_x_RDI_STREAM_SEL_SHIFT	28
+#define VFE_0_RDI_CFG_x_RDI_STREAM_SEL_MASK	(0xf << 28)
+#define VFE_0_RDI_CFG_x_RDI_M0_SEL_SHIFT	4
+#define VFE_0_RDI_CFG_x_RDI_M0_SEL_MASK		(0xf << 4)
+#define VFE_0_RDI_CFG_x_RDI_EN_BIT		BIT(2)
+#define VFE_0_RDI_CFG_x_MIPI_EN_BITS		0x3
+
+#define VFE_0_CAMIF_CMD				0x478
+#define VFE_0_CAMIF_CMD_DISABLE_FRAME_BOUNDARY	0
+#define VFE_0_CAMIF_CMD_ENABLE_FRAME_BOUNDARY	1
+#define VFE_0_CAMIF_CMD_NO_CHANGE		3
+#define VFE_0_CAMIF_CMD_CLEAR_CAMIF_STATUS	BIT(2)
+#define VFE_0_CAMIF_CFG				0x47c
+#define VFE_0_CAMIF_CFG_VFE_OUTPUT_EN		BIT(6)
+#define VFE_0_CAMIF_FRAME_CFG			0x484
+#define VFE_0_CAMIF_WINDOW_WIDTH_CFG		0x488
+#define VFE_0_CAMIF_WINDOW_HEIGHT_CFG		0x48c
+#define VFE_0_CAMIF_SUBSAMPLE_CFG		0x490
+#define VFE_0_CAMIF_IRQ_FRAMEDROP_PATTERN	0x498
+#define VFE_0_CAMIF_IRQ_SUBSAMPLE_PATTERN	0x49c
+#define VFE_0_CAMIF_STATUS			0x4a4
+#define VFE_0_CAMIF_STATUS_HALT			BIT(31)
+
+#define VFE_0_REG_UPDATE		0x4ac
+#define VFE_0_REG_UPDATE_RDIn(n)		BIT(1 + (n))
+#define VFE_0_REG_UPDATE_line_n(n)		\
+			((n) == VFE_LINE_PIX ? 1 : VFE_0_REG_UPDATE_RDIn(n))
+
+#define VFE_0_DEMUX_CFG				0x560
+#define VFE_0_DEMUX_CFG_PERIOD			0x3
+#define VFE_0_DEMUX_GAIN_0			0x564
+#define VFE_0_DEMUX_GAIN_0_CH0_EVEN		(0x80 << 0)
+#define VFE_0_DEMUX_GAIN_0_CH0_ODD		(0x80 << 16)
+#define VFE_0_DEMUX_GAIN_1			0x568
+#define VFE_0_DEMUX_GAIN_1_CH1			(0x80 << 0)
+#define VFE_0_DEMUX_GAIN_1_CH2			(0x80 << 16)
+#define VFE_0_DEMUX_EVEN_CFG			0x574
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_YUYV	0x9cac
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_YVYU	0xac9c
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_UYVY	0xc9ca
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_VYUY	0xcac9
+#define VFE_0_DEMUX_ODD_CFG			0x578
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_YUYV	0x9cac
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_YVYU	0xac9c
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_UYVY	0xc9ca
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_VYUY	0xcac9
+
+#define VFE_0_SCALE_ENC_Y_CFG			0x91c
+#define VFE_0_SCALE_ENC_Y_H_IMAGE_SIZE		0x920
+#define VFE_0_SCALE_ENC_Y_H_PHASE		0x924
+#define VFE_0_SCALE_ENC_Y_V_IMAGE_SIZE		0x934
+#define VFE_0_SCALE_ENC_Y_V_PHASE		0x938
+#define VFE_0_SCALE_ENC_CBCR_CFG		0x948
+#define VFE_0_SCALE_ENC_CBCR_H_IMAGE_SIZE	0x94c
+#define VFE_0_SCALE_ENC_CBCR_H_PHASE		0x950
+#define VFE_0_SCALE_ENC_CBCR_V_IMAGE_SIZE	0x960
+#define VFE_0_SCALE_ENC_CBCR_V_PHASE		0x964
+
+#define VFE_0_CROP_ENC_Y_WIDTH			0x974
+#define VFE_0_CROP_ENC_Y_HEIGHT			0x978
+#define VFE_0_CROP_ENC_CBCR_WIDTH		0x97c
+#define VFE_0_CROP_ENC_CBCR_HEIGHT		0x980
+
+#define VFE_0_CLAMP_ENC_MAX_CFG			0x984
+#define VFE_0_CLAMP_ENC_MAX_CFG_CH0		(0xff << 0)
+#define VFE_0_CLAMP_ENC_MAX_CFG_CH1		(0xff << 8)
+#define VFE_0_CLAMP_ENC_MAX_CFG_CH2		(0xff << 16)
+#define VFE_0_CLAMP_ENC_MIN_CFG			0x988
+#define VFE_0_CLAMP_ENC_MIN_CFG_CH0		(0x0 << 0)
+#define VFE_0_CLAMP_ENC_MIN_CFG_CH1		(0x0 << 8)
+#define VFE_0_CLAMP_ENC_MIN_CFG_CH2		(0x0 << 16)
+
+#define VFE_0_REALIGN_BUF_CFG			0xaac
+#define VFE_0_REALIGN_BUF_CFG_CB_ODD_PIXEL     BIT(2)
+#define VFE_0_REALIGN_BUF_CFG_CR_ODD_PIXEL     BIT(3)
+#define VFE_0_REALIGN_BUF_CFG_HSUB_ENABLE      BIT(4)
+
+#define CAMIF_TIMEOUT_SLEEP_US 1000
+#define CAMIF_TIMEOUT_ALL_US 1000000
+
+#define MSM_VFE_VFE0_UB_SIZE 2047
+#define MSM_VFE_VFE0_UB_SIZE_RDI (MSM_VFE_VFE0_UB_SIZE / 3)
+#define MSM_VFE_VFE1_UB_SIZE 1535
+#define MSM_VFE_VFE1_UB_SIZE_RDI (MSM_VFE_VFE1_UB_SIZE / 3)
+
+static void vfe_hw_version_read(struct vfe_device *vfe, struct device *dev)
+{
+	u32 hw_version = readl_relaxed(vfe->base + VFE_0_HW_VERSION);
+
+	dev_err(dev, "VFE HW Version = 0x%08x\n", hw_version);
+}
+
+static u16 vfe_get_ub_size(u8 vfe_id)
+{
+	if (vfe_id == 0)
+		return MSM_VFE_VFE0_UB_SIZE_RDI;
+	else if (vfe_id == 1)
+		return MSM_VFE_VFE1_UB_SIZE_RDI;
+
+	return 0;
+}
+
+static inline void vfe_reg_clr(struct vfe_device *vfe, u32 reg, u32 clr_bits)
+{
+	u32 bits = readl_relaxed(vfe->base + reg);
+
+	writel_relaxed(bits & ~clr_bits, vfe->base + reg);
+}
+
+static inline void vfe_reg_set(struct vfe_device *vfe, u32 reg, u32 set_bits)
+{
+	u32 bits = readl_relaxed(vfe->base + reg);
+
+	writel_relaxed(bits | set_bits, vfe->base + reg);
+}
+
+static void vfe_global_reset(struct vfe_device *vfe)
+{
+	u32 reset_bits = VFE_0_GLOBAL_RESET_CMD_IDLE_CGC	|
+			 VFE_0_GLOBAL_RESET_CMD_DSP		|
+			 VFE_0_GLOBAL_RESET_CMD_TESTGEN		|
+			 VFE_0_GLOBAL_RESET_CMD_BUS_MISR	|
+			 VFE_0_GLOBAL_RESET_CMD_PM		|
+			 VFE_0_GLOBAL_RESET_CMD_REGISTER	|
+			 VFE_0_GLOBAL_RESET_CMD_BUS_BDG		|
+			 VFE_0_GLOBAL_RESET_CMD_BUS		|
+			 VFE_0_GLOBAL_RESET_CMD_CAMIF		|
+			 VFE_0_GLOBAL_RESET_CMD_CORE;
+
+	writel_relaxed(BIT(31), vfe->base + VFE_0_IRQ_MASK_0);
+	wmb();
+	writel_relaxed(reset_bits, vfe->base + VFE_0_GLOBAL_RESET_CMD);
+}
+
+static void vfe_halt_request(struct vfe_device *vfe)
+{
+	writel_relaxed(VFE_0_BUS_BDG_CMD_HALT_REQ,
+		       vfe->base + VFE_0_BUS_BDG_CMD);
+}
+
+static void vfe_halt_clear(struct vfe_device *vfe)
+{
+	writel_relaxed(0x0, vfe->base + VFE_0_BUS_BDG_CMD);
+}
+
+static void vfe_wm_enable(struct vfe_device *vfe, u8 wm, u8 enable)
+{
+	if (enable)
+		vfe_reg_set(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
+			    1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT);
+	else
+		vfe_reg_clr(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
+			    1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT);
+}
+
+static void vfe_wm_frame_based(struct vfe_device *vfe, u8 wm, u8 enable)
+{
+	if (enable)
+		vfe_reg_set(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm),
+			1 << VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_BASED_SHIFT);
+	else
+		vfe_reg_clr(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm),
+			1 << VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_BASED_SHIFT);
+}
+
+#define CALC_WORD(width, M, N) (((width) * (M) + (N) - 1) / (N))
+
+static int vfe_word_per_line_by_pixel(u32 format, u32 pixel_per_line)
+{
+	int val = 0;
+
+	switch (format) {
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV21:
+	case V4L2_PIX_FMT_NV16:
+	case V4L2_PIX_FMT_NV61:
+		val = CALC_WORD(pixel_per_line, 1, 8);
+		break;
+	case V4L2_PIX_FMT_YUYV:
+	case V4L2_PIX_FMT_YVYU:
+	case V4L2_PIX_FMT_UYVY:
+	case V4L2_PIX_FMT_VYUY:
+		val = CALC_WORD(pixel_per_line, 2, 8);
+		break;
+	}
+
+	return val;
+}
+
+static int vfe_word_per_line_by_bytes(u32 bytes_per_line)
+{
+	return CALC_WORD(bytes_per_line, 1, 8);
+}
+
+static void vfe_get_wm_sizes(struct v4l2_pix_format_mplane *pix, u8 plane,
+			     u16 *width, u16 *height, u16 *bytesperline)
+{
+	switch (pix->pixelformat) {
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV21:
+		*width = pix->width;
+		*height = pix->height;
+		*bytesperline = pix->plane_fmt[0].bytesperline;
+		if (plane == 1)
+			*height /= 2;
+		break;
+	case V4L2_PIX_FMT_NV16:
+	case V4L2_PIX_FMT_NV61:
+		*width = pix->width;
+		*height = pix->height;
+		*bytesperline = pix->plane_fmt[0].bytesperline;
+		break;
+	case V4L2_PIX_FMT_YUYV:
+	case V4L2_PIX_FMT_YVYU:
+	case V4L2_PIX_FMT_VYUY:
+	case V4L2_PIX_FMT_UYVY:
+		*width = pix->width;
+		*height = pix->height;
+		*bytesperline = pix->plane_fmt[plane].bytesperline;
+		break;
+
+	}
+}
+
+static void vfe_wm_line_based(struct vfe_device *vfe, u32 wm,
+			      struct v4l2_pix_format_mplane *pix,
+			      u8 plane, u32 enable)
+{
+	u32 reg;
+
+	if (enable) {
+		u16 width = 0, height = 0, bytesperline = 0, wpl;
+
+		vfe_get_wm_sizes(pix, plane, &width, &height, &bytesperline);
+
+		wpl = vfe_word_per_line_by_pixel(pix->pixelformat, width);
+
+		reg = height - 1;
+		reg |= ((wpl + 3) / 4 - 1) << 16;
+
+		writel_relaxed(reg, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(wm));
+
+		wpl = vfe_word_per_line_by_bytes(bytesperline);
+
+		reg = 0x3;
+		reg |= (height - 1) << 2;
+		reg |= ((wpl + 1) / 2) << 16;
+
+		writel_relaxed(reg, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(wm));
+	} else {
+		writel_relaxed(0, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(wm));
+		writel_relaxed(0, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(wm));
+	}
+}
+
+static void vfe_wm_set_framedrop_period(struct vfe_device *vfe, u8 wm, u8 per)
+{
+	u32 reg;
+
+	reg = readl_relaxed(vfe->base +
+			    VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm));
+
+	reg &= ~(VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK);
+
+	reg |= (per << VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_SHIFT)
+		& VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK;
+
+	writel_relaxed(reg,
+		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm));
+}
+
+static void vfe_wm_set_framedrop_pattern(struct vfe_device *vfe, u8 wm,
+					 u32 pattern)
+{
+	writel_relaxed(pattern,
+	       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_FRAMEDROP_PATTERN(wm));
+}
+
+static void vfe_wm_set_ub_cfg(struct vfe_device *vfe, u8 wm,
+			      u16 offset, u16 depth)
+{
+	u32 reg;
+
+	reg = (offset << VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG_OFFSET_SHIFT) |
+		depth;
+	writel_relaxed(reg, vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG(wm));
+}
+
+static void vfe_bus_reload_wm(struct vfe_device *vfe, u8 wm)
+{
+	wmb();
+	writel_relaxed(VFE_0_BUS_CMD_Mx_RLD_CMD(wm), vfe->base + VFE_0_BUS_CMD);
+	wmb();
+}
+
+static void vfe_wm_set_ping_addr(struct vfe_device *vfe, u8 wm, u32 addr)
+{
+	writel_relaxed(addr,
+		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_PING_ADDR(wm));
+}
+
+static void vfe_wm_set_pong_addr(struct vfe_device *vfe, u8 wm, u32 addr)
+{
+	writel_relaxed(addr,
+		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_PONG_ADDR(wm));
+}
+
+static int vfe_wm_get_ping_pong_status(struct vfe_device *vfe, u8 wm)
+{
+	u32 reg;
+
+	reg = readl_relaxed(vfe->base + VFE_0_BUS_PING_PONG_STATUS);
+
+	return (reg >> wm) & 0x1;
+}
+
+static void vfe_bus_enable_wr_if(struct vfe_device *vfe, u8 enable)
+{
+	if (enable)
+		writel_relaxed(0x101, vfe->base + VFE_0_BUS_CFG);
+	else
+		writel_relaxed(0, vfe->base + VFE_0_BUS_CFG);
+}
+
+static void vfe_bus_connect_wm_to_rdi(struct vfe_device *vfe, u8 wm,
+				      enum vfe_line_id id)
+{
+	u32 reg;
+
+	reg = VFE_0_RDI_CFG_x_MIPI_EN_BITS;
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(0), reg);
+
+	reg = VFE_0_RDI_CFG_x_RDI_EN_BIT;
+	reg |= ((3 * id) << VFE_0_RDI_CFG_x_RDI_STREAM_SEL_SHIFT) &
+		VFE_0_RDI_CFG_x_RDI_STREAM_SEL_MASK;
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(id), reg);
+
+	switch (id) {
+	case VFE_LINE_RDI0:
+	default:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI1:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI2:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	}
+
+	if (wm % 2 == 1)
+		reg <<= 16;
+
+	vfe_reg_set(vfe, VFE_0_BUS_XBAR_CFG_x(wm), reg);
+}
+
+static void vfe_wm_set_subsample(struct vfe_device *vfe, u8 wm)
+{
+	writel_relaxed(VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN_DEF,
+	       vfe->base +
+	       VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN(wm));
+}
+
+static void vfe_bus_disconnect_wm_from_rdi(struct vfe_device *vfe, u8 wm,
+					   enum vfe_line_id id)
+{
+	u32 reg;
+
+	reg = VFE_0_RDI_CFG_x_RDI_EN_BIT;
+	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(id), reg);
+
+	switch (id) {
+	case VFE_LINE_RDI0:
+	default:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI1:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI2:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	}
+
+	if (wm % 2 == 1)
+		reg <<= 16;
+
+	vfe_reg_clr(vfe, VFE_0_BUS_XBAR_CFG_x(wm), reg);
+}
+
+static void vfe_set_xbar_cfg(struct vfe_device *vfe, struct vfe_output *output,
+			     u8 enable)
+{
+	struct vfe_line *line = container_of(output, struct vfe_line, output);
+	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
+	u32 reg;
+
+	switch (p) {
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV21:
+	case V4L2_PIX_FMT_NV16:
+	case V4L2_PIX_FMT_NV61:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_LUMA <<
+			VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+
+		if (output->wm_idx[0] % 2 == 1)
+			reg <<= 16;
+
+		if (enable)
+			vfe_reg_set(vfe,
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[0]),
+				    reg);
+		else
+			vfe_reg_clr(vfe,
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[0]),
+				    reg);
+
+		reg = VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN;
+		if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV16)
+			reg |= VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA;
+
+		if (output->wm_idx[1] % 2 == 1)
+			reg <<= 16;
+
+		if (enable)
+			vfe_reg_set(vfe,
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[1]),
+				    reg);
+		else
+			vfe_reg_clr(vfe,
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[1]),
+				    reg);
+		break;
+	case V4L2_PIX_FMT_YUYV:
+	case V4L2_PIX_FMT_YVYU:
+	case V4L2_PIX_FMT_VYUY:
+	case V4L2_PIX_FMT_UYVY:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_REALIGN_BUF_EN;
+		reg |= VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN;
+
+		if (p == V4L2_PIX_FMT_YUYV || p == V4L2_PIX_FMT_YVYU)
+			reg |= VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA;
+
+		if (output->wm_idx[0] % 2 == 1)
+			reg <<= 16;
+
+		if (enable)
+			vfe_reg_set(vfe,
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[0]),
+				    reg);
+		else
+			vfe_reg_clr(vfe,
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[0]),
+				    reg);
+		break;
+	default:
+		break;
+	}
+}
+
+static void vfe_set_realign_cfg(struct vfe_device *vfe, struct vfe_line *line,
+				u8 enable)
+{
+	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
+	u32 val = VFE_0_MODULE_ZOOM_EN_REALIGN_BUF;
+
+	if (p != V4L2_PIX_FMT_YUYV && p != V4L2_PIX_FMT_YVYU &&
+			p != V4L2_PIX_FMT_VYUY && p != V4L2_PIX_FMT_UYVY)
+		return;
+
+	if (enable) {
+		vfe_reg_set(vfe, VFE_0_MODULE_ZOOM_EN, val);
+	} else {
+		vfe_reg_clr(vfe, VFE_0_MODULE_ZOOM_EN, val);
+		return;
+	}
+
+	val = VFE_0_REALIGN_BUF_CFG_HSUB_ENABLE;
+
+	if (p == V4L2_PIX_FMT_UYVY || p == V4L2_PIX_FMT_YUYV)
+		val |= VFE_0_REALIGN_BUF_CFG_CR_ODD_PIXEL;
+	else
+		val |= VFE_0_REALIGN_BUF_CFG_CB_ODD_PIXEL;
+
+	writel_relaxed(val, vfe->base + VFE_0_REALIGN_BUF_CFG);
+}
+
+static void vfe_set_rdi_cid(struct vfe_device *vfe, enum vfe_line_id id, u8 cid)
+{
+	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(id),
+		    VFE_0_RDI_CFG_x_RDI_M0_SEL_MASK);
+
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(id),
+		    cid << VFE_0_RDI_CFG_x_RDI_M0_SEL_SHIFT);
+}
+
+static void vfe_reg_update(struct vfe_device *vfe, enum vfe_line_id line_id)
+{
+	vfe->reg_update |= VFE_0_REG_UPDATE_line_n(line_id);
+	wmb();
+	writel_relaxed(vfe->reg_update, vfe->base + VFE_0_REG_UPDATE);
+	wmb();
+}
+
+static inline void vfe_reg_update_clear(struct vfe_device *vfe,
+					enum vfe_line_id line_id)
+{
+	vfe->reg_update &= ~VFE_0_REG_UPDATE_line_n(line_id);
+}
+
+static void vfe_enable_irq_wm_line(struct vfe_device *vfe, u8 wm,
+				   enum vfe_line_id line_id, u8 enable)
+{
+	u32 irq_en0 = VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(wm) |
+		      VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(line_id);
+	u32 irq_en1 = VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(wm) |
+		      VFE_0_IRQ_MASK_1_RDIn_SOF(line_id);
+
+	if (enable) {
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+	} else {
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+	}
+}
+
+static void vfe_enable_irq_pix_line(struct vfe_device *vfe, u8 comp,
+				    enum vfe_line_id line_id, u8 enable)
+{
+	struct vfe_output *output = &vfe->line[line_id].output;
+	unsigned int i;
+	u32 irq_en0;
+	u32 irq_en1;
+	u32 comp_mask = 0;
+
+	irq_en0 = VFE_0_IRQ_MASK_0_CAMIF_SOF;
+	irq_en0 |= VFE_0_IRQ_MASK_0_CAMIF_EOF;
+	irq_en0 |= VFE_0_IRQ_MASK_0_IMAGE_COMPOSITE_DONE_n(comp);
+	irq_en0 |= VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(line_id);
+	irq_en1 = VFE_0_IRQ_MASK_1_CAMIF_ERROR;
+	for (i = 0; i < output->wm_num; i++) {
+		irq_en1 |= VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(
+							output->wm_idx[i]);
+		comp_mask |= (1 << output->wm_idx[i]) << comp * 8;
+	}
+
+	if (enable) {
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+		vfe_reg_set(vfe, VFE_0_IRQ_COMPOSITE_MASK_0, comp_mask);
+	} else {
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+		vfe_reg_clr(vfe, VFE_0_IRQ_COMPOSITE_MASK_0, comp_mask);
+	}
+}
+
+static void vfe_enable_irq_common(struct vfe_device *vfe)
+{
+	u32 irq_en0 = VFE_0_IRQ_MASK_0_RESET_ACK;
+	u32 irq_en1 = VFE_0_IRQ_MASK_1_VIOLATION |
+		      VFE_0_IRQ_MASK_1_BUS_BDG_HALT_ACK;
+
+	vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+	vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+}
+
+static void vfe_set_demux_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 val, even_cfg, odd_cfg;
+
+	writel_relaxed(VFE_0_DEMUX_CFG_PERIOD, vfe->base + VFE_0_DEMUX_CFG);
+
+	val = VFE_0_DEMUX_GAIN_0_CH0_EVEN | VFE_0_DEMUX_GAIN_0_CH0_ODD;
+	writel_relaxed(val, vfe->base + VFE_0_DEMUX_GAIN_0);
+
+	val = VFE_0_DEMUX_GAIN_1_CH1 | VFE_0_DEMUX_GAIN_1_CH2;
+	writel_relaxed(val, vfe->base + VFE_0_DEMUX_GAIN_1);
+
+	switch (line->fmt[MSM_VFE_PAD_SINK].code) {
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_YUYV;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_YUYV;
+		break;
+	case MEDIA_BUS_FMT_YVYU8_2X8:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_YVYU;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_YVYU;
+		break;
+	case MEDIA_BUS_FMT_UYVY8_2X8:
+	default:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_UYVY;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_UYVY;
+		break;
+	case MEDIA_BUS_FMT_VYUY8_2X8:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_VYUY;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_VYUY;
+		break;
+	}
+
+	writel_relaxed(even_cfg, vfe->base + VFE_0_DEMUX_EVEN_CFG);
+	writel_relaxed(odd_cfg, vfe->base + VFE_0_DEMUX_ODD_CFG);
+}
+
+static inline u8 vfe_calc_interp_reso(u16 input, u16 output)
+{
+	if (input / output >= 16)
+		return 0;
+
+	if (input / output >= 8)
+		return 1;
+
+	if (input / output >= 4)
+		return 2;
+
+	return 3;
+}
+
+static void vfe_set_scale_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
+	u32 reg;
+	u16 input, output;
+	u8 interp_reso;
+	u32 phase_mult;
+
+	writel_relaxed(0x3, vfe->base + VFE_0_SCALE_ENC_Y_CFG);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].width - 1;
+	output = line->compose.width - 1;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_H_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (14 + interp_reso)) / output;
+	reg = (interp_reso << 28) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_H_PHASE);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].height - 1;
+	output = line->compose.height - 1;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_V_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (14 + interp_reso)) / output;
+	reg = (interp_reso << 28) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_V_PHASE);
+
+	writel_relaxed(0x3, vfe->base + VFE_0_SCALE_ENC_CBCR_CFG);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].width - 1;
+	output = line->compose.width / 2 - 1;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_H_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (14 + interp_reso)) / output;
+	reg = (interp_reso << 28) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_H_PHASE);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].height - 1;
+	output = line->compose.height - 1;
+	if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV21)
+		output = line->compose.height / 2 - 1;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_V_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (14 + interp_reso)) / output;
+	reg = (interp_reso << 28) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_V_PHASE);
+}
+
+static void vfe_set_crop_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
+	u32 reg;
+	u16 first, last;
+
+	first = line->crop.left;
+	last = line->crop.left + line->crop.width - 1;
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_Y_WIDTH);
+
+	first = line->crop.top;
+	last = line->crop.top + line->crop.height - 1;
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_Y_HEIGHT);
+
+	first = line->crop.left / 2;
+	last = line->crop.left / 2 + line->crop.width / 2 - 1;
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_CBCR_WIDTH);
+
+	first = line->crop.top;
+	last = line->crop.top + line->crop.height - 1;
+	if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV21) {
+		first = line->crop.top / 2;
+		last = line->crop.top / 2 + line->crop.height / 2 - 1;
+	}
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_CBCR_HEIGHT);
+}
+
+static void vfe_set_clamp_cfg(struct vfe_device *vfe)
+{
+	u32 val = VFE_0_CLAMP_ENC_MAX_CFG_CH0 |
+		VFE_0_CLAMP_ENC_MAX_CFG_CH1 |
+		VFE_0_CLAMP_ENC_MAX_CFG_CH2;
+
+	writel_relaxed(val, vfe->base + VFE_0_CLAMP_ENC_MAX_CFG);
+
+	val = VFE_0_CLAMP_ENC_MIN_CFG_CH0 |
+		VFE_0_CLAMP_ENC_MIN_CFG_CH1 |
+		VFE_0_CLAMP_ENC_MIN_CFG_CH2;
+
+	writel_relaxed(val, vfe->base + VFE_0_CLAMP_ENC_MIN_CFG);
+}
+
+static void vfe_set_qos(struct vfe_device *vfe)
+{
+	u32 val = VFE_0_BUS_BDG_QOS_CFG_0_CFG;
+	u32 val7 = VFE_0_BUS_BDG_QOS_CFG_7_CFG;
+
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_0);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_1);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_2);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_3);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_4);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_5);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_6);
+	writel_relaxed(val7, vfe->base + VFE_0_BUS_BDG_QOS_CFG_7);
+}
+
+static void vfe_set_ds(struct vfe_device *vfe)
+{
+	u32 val = VFE_0_BUS_BDG_DS_CFG_0_CFG;
+	u32 val16 = VFE_0_BUS_BDG_DS_CFG_16_CFG;
+
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_0);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_1);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_2);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_3);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_4);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_5);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_6);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_7);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_8);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_9);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_10);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_11);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_12);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_13);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_14);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_15);
+	writel_relaxed(val16, vfe->base + VFE_0_BUS_BDG_DS_CFG_16);
+}
+
+static void vfe_set_cgc_override(struct vfe_device *vfe, u8 wm, u8 enable)
+{
+	/* empty */
+}
+
+static void vfe_set_camif_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 val;
+
+	switch (line->fmt[MSM_VFE_PAD_SINK].code) {
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_YCBYCR;
+		break;
+	case MEDIA_BUS_FMT_YVYU8_2X8:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_YCRYCB;
+		break;
+	case MEDIA_BUS_FMT_UYVY8_2X8:
+	default:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_CBYCRY;
+		break;
+	case MEDIA_BUS_FMT_VYUY8_2X8:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_CRYCBY;
+		break;
+	}
+
+	val |= VFE_0_CORE_CFG_COMPOSITE_REG_UPDATE_EN;
+	writel_relaxed(val, vfe->base + VFE_0_CORE_CFG);
+
+	val = line->fmt[MSM_VFE_PAD_SINK].width * 2 - 1;
+	val |= (line->fmt[MSM_VFE_PAD_SINK].height - 1) << 16;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_FRAME_CFG);
+
+	val = line->fmt[MSM_VFE_PAD_SINK].width * 2 - 1;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_WINDOW_WIDTH_CFG);
+
+	val = line->fmt[MSM_VFE_PAD_SINK].height - 1;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_WINDOW_HEIGHT_CFG);
+
+	val = 0xffffffff;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_SUBSAMPLE_CFG);
+
+	val = 0xffffffff;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_IRQ_FRAMEDROP_PATTERN);
+
+	val = 0xffffffff;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_IRQ_SUBSAMPLE_PATTERN);
+
+	val = VFE_0_RDI_CFG_x_MIPI_EN_BITS;
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(0), val);
+
+	val = VFE_0_CAMIF_CFG_VFE_OUTPUT_EN;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_CFG);
+}
+
+static void vfe_set_camif_cmd(struct vfe_device *vfe, u8 enable)
+{
+	u32 cmd;
+
+	cmd = VFE_0_CAMIF_CMD_CLEAR_CAMIF_STATUS | VFE_0_CAMIF_CMD_NO_CHANGE;
+	writel_relaxed(cmd, vfe->base + VFE_0_CAMIF_CMD);
+	wmb();
+
+	if (enable)
+		cmd = VFE_0_CAMIF_CMD_ENABLE_FRAME_BOUNDARY;
+	else
+		cmd = VFE_0_CAMIF_CMD_DISABLE_FRAME_BOUNDARY;
+
+	writel_relaxed(cmd, vfe->base + VFE_0_CAMIF_CMD);
+}
+
+static void vfe_set_module_cfg(struct vfe_device *vfe, u8 enable)
+{
+	u32 val_lens = VFE_0_MODULE_LENS_EN_DEMUX |
+		       VFE_0_MODULE_LENS_EN_CHROMA_UPSAMPLE;
+	u32 val_zoom = VFE_0_MODULE_ZOOM_EN_SCALE_ENC |
+		       VFE_0_MODULE_ZOOM_EN_CROP_ENC;
+
+	if (enable) {
+		vfe_reg_set(vfe, VFE_0_MODULE_LENS_EN, val_lens);
+		vfe_reg_set(vfe, VFE_0_MODULE_ZOOM_EN, val_zoom);
+	} else {
+		vfe_reg_clr(vfe, VFE_0_MODULE_LENS_EN, val_lens);
+		vfe_reg_clr(vfe, VFE_0_MODULE_ZOOM_EN, val_zoom);
+	}
+}
+
+static int vfe_camif_wait_for_stop(struct vfe_device *vfe, struct device *dev)
+{
+	u32 val;
+	int ret;
+
+	ret = readl_poll_timeout(vfe->base + VFE_0_CAMIF_STATUS,
+				 val,
+				 (val & VFE_0_CAMIF_STATUS_HALT),
+				 CAMIF_TIMEOUT_SLEEP_US,
+				 CAMIF_TIMEOUT_ALL_US);
+	if (ret < 0)
+		dev_err(dev, "%s: camif stop timeout\n", __func__);
+
+	return ret;
+}
+
+static void vfe_isr_read(struct vfe_device *vfe, u32 *value0, u32 *value1)
+{
+	*value0 = readl_relaxed(vfe->base + VFE_0_IRQ_STATUS_0);
+	*value1 = readl_relaxed(vfe->base + VFE_0_IRQ_STATUS_1);
+
+	writel_relaxed(*value0, vfe->base + VFE_0_IRQ_CLEAR_0);
+	writel_relaxed(*value1, vfe->base + VFE_0_IRQ_CLEAR_1);
+
+	wmb();
+	writel_relaxed(VFE_0_IRQ_CMD_GLOBAL_CLEAR, vfe->base + VFE_0_IRQ_CMD);
+}
+
+static void vfe_violation_read(struct vfe_device *vfe)
+{
+	u32 violation = readl_relaxed(vfe->base + VFE_0_VIOLATION_STATUS);
+
+	pr_err_ratelimited("VFE: violation = 0x%08x\n", violation);
+}
+
+/*
+ * vfe_isr - ISPIF module interrupt handler
+ * @irq: Interrupt line
+ * @dev: VFE device
+ *
+ * Return IRQ_HANDLED on success
+ */
+static irqreturn_t vfe_isr(int irq, void *dev)
+{
+	struct vfe_device *vfe = dev;
+	u32 value0, value1;
+	int i, j;
+
+	vfe->ops->isr_read(vfe, &value0, &value1);
+
+	trace_printk("VFE: status0 = 0x%08x, status1 = 0x%08x\n",
+		     value0, value1);
+
+	if (value0 & VFE_0_IRQ_STATUS_0_RESET_ACK)
+		vfe->isr_ops.reset_ack(vfe);
+
+	if (value1 & VFE_0_IRQ_STATUS_1_VIOLATION)
+		vfe->ops->violation_read(vfe);
+
+	if (value1 & VFE_0_IRQ_STATUS_1_BUS_BDG_HALT_ACK)
+		vfe->isr_ops.halt_ack(vfe);
+
+	for (i = VFE_LINE_RDI0; i <= VFE_LINE_PIX; i++)
+		if (value0 & VFE_0_IRQ_STATUS_0_line_n_REG_UPDATE(i))
+			vfe->isr_ops.reg_update(vfe, i);
+
+	if (value0 & VFE_0_IRQ_STATUS_0_CAMIF_SOF)
+		vfe->isr_ops.sof(vfe, VFE_LINE_PIX);
+
+	for (i = VFE_LINE_RDI0; i <= VFE_LINE_RDI2; i++)
+		if (value1 & VFE_0_IRQ_STATUS_1_RDIn_SOF(i))
+			vfe->isr_ops.sof(vfe, i);
+
+	for (i = 0; i < MSM_VFE_COMPOSITE_IRQ_NUM; i++)
+		if (value0 & VFE_0_IRQ_STATUS_0_IMAGE_COMPOSITE_DONE_n(i)) {
+			vfe->isr_ops.comp_done(vfe, i);
+			for (j = 0; j < ARRAY_SIZE(vfe->wm_output_map); j++)
+				if (vfe->wm_output_map[j] == VFE_LINE_PIX)
+					value0 &= ~VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(j);
+		}
+
+	for (i = 0; i < MSM_VFE_IMAGE_MASTERS_NUM; i++)
+		if (value0 & VFE_0_IRQ_STATUS_0_IMAGE_MASTER_n_PING_PONG(i))
+			vfe->isr_ops.wm_done(vfe, i);
+
+	return IRQ_HANDLED;
+}
+
+const struct vfe_hw_ops vfe_ops_4_7 = {
+	.hw_version_read = vfe_hw_version_read,
+	.get_ub_size = vfe_get_ub_size,
+	.global_reset = vfe_global_reset,
+	.halt_request = vfe_halt_request,
+	.halt_clear = vfe_halt_clear,
+	.wm_enable = vfe_wm_enable,
+	.wm_frame_based = vfe_wm_frame_based,
+	.wm_line_based = vfe_wm_line_based,
+	.wm_set_framedrop_period = vfe_wm_set_framedrop_period,
+	.wm_set_framedrop_pattern = vfe_wm_set_framedrop_pattern,
+	.wm_set_ub_cfg = vfe_wm_set_ub_cfg,
+	.bus_reload_wm = vfe_bus_reload_wm,
+	.wm_set_ping_addr = vfe_wm_set_ping_addr,
+	.wm_set_pong_addr = vfe_wm_set_pong_addr,
+	.wm_get_ping_pong_status = vfe_wm_get_ping_pong_status,
+	.bus_enable_wr_if = vfe_bus_enable_wr_if,
+	.bus_connect_wm_to_rdi = vfe_bus_connect_wm_to_rdi,
+	.wm_set_subsample = vfe_wm_set_subsample,
+	.bus_disconnect_wm_from_rdi = vfe_bus_disconnect_wm_from_rdi,
+	.set_xbar_cfg = vfe_set_xbar_cfg,
+	.set_realign_cfg = vfe_set_realign_cfg,
+	.set_rdi_cid = vfe_set_rdi_cid,
+	.reg_update = vfe_reg_update,
+	.reg_update_clear = vfe_reg_update_clear,
+	.enable_irq_wm_line = vfe_enable_irq_wm_line,
+	.enable_irq_pix_line = vfe_enable_irq_pix_line,
+	.enable_irq_common = vfe_enable_irq_common,
+	.set_demux_cfg = vfe_set_demux_cfg,
+	.set_scale_cfg = vfe_set_scale_cfg,
+	.set_crop_cfg = vfe_set_crop_cfg,
+	.set_clamp_cfg = vfe_set_clamp_cfg,
+	.set_qos = vfe_set_qos,
+	.set_ds = vfe_set_ds,
+	.set_cgc_override = vfe_set_cgc_override,
+	.set_camif_cfg = vfe_set_camif_cfg,
+	.set_camif_cmd = vfe_set_camif_cmd,
+	.set_module_cfg = vfe_set_module_cfg,
+	.camif_wait_for_stop = vfe_camif_wait_for_stop,
+	.isr_read = vfe_isr_read,
+	.violation_read = vfe_violation_read,
+	.isr = vfe_isr,
+};
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c
index a6329a8a7c4a..ed6a557de65d 100644
--- a/drivers/media/platform/qcom/camss-8x16/camss-vfe.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe.c
@@ -1,28 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * camss-vfe.c
  *
  * Qualcomm MSM Camera Subsystem - VFE (Video Front End) Module
  *
  * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ * Copyright (C) 2015-2018 Linaro Ltd.
  */
 #include <linux/clk.h>
 #include <linux/completion.h>
 #include <linux/interrupt.h>
 #include <linux/iommu.h>
-#include <linux/iopoll.h>
 #include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/spinlock_types.h>
 #include <linux/spinlock.h>
 #include <media/media-entity.h>
@@ -38,194 +30,7 @@
 	((const struct vfe_line (*)[]) &(ptr_line[-(ptr_line->id)]))
 
 #define to_vfe(ptr_line)	\
-	container_of(vfe_line_array(ptr_line), struct vfe_device, ptr_line)
-
-#define VFE_0_HW_VERSION		0x000
-
-#define VFE_0_GLOBAL_RESET_CMD		0x00c
-#define VFE_0_GLOBAL_RESET_CMD_CORE	(1 << 0)
-#define VFE_0_GLOBAL_RESET_CMD_CAMIF	(1 << 1)
-#define VFE_0_GLOBAL_RESET_CMD_BUS	(1 << 2)
-#define VFE_0_GLOBAL_RESET_CMD_BUS_BDG	(1 << 3)
-#define VFE_0_GLOBAL_RESET_CMD_REGISTER	(1 << 4)
-#define VFE_0_GLOBAL_RESET_CMD_TIMER	(1 << 5)
-#define VFE_0_GLOBAL_RESET_CMD_PM	(1 << 6)
-#define VFE_0_GLOBAL_RESET_CMD_BUS_MISR	(1 << 7)
-#define VFE_0_GLOBAL_RESET_CMD_TESTGEN	(1 << 8)
-
-#define VFE_0_MODULE_CFG		0x018
-#define VFE_0_MODULE_CFG_DEMUX			(1 << 2)
-#define VFE_0_MODULE_CFG_CHROMA_UPSAMPLE	(1 << 3)
-#define VFE_0_MODULE_CFG_SCALE_ENC		(1 << 23)
-#define VFE_0_MODULE_CFG_CROP_ENC		(1 << 27)
-
-#define VFE_0_CORE_CFG			0x01c
-#define VFE_0_CORE_CFG_PIXEL_PATTERN_YCBYCR	0x4
-#define VFE_0_CORE_CFG_PIXEL_PATTERN_YCRYCB	0x5
-#define VFE_0_CORE_CFG_PIXEL_PATTERN_CBYCRY	0x6
-#define VFE_0_CORE_CFG_PIXEL_PATTERN_CRYCBY	0x7
-
-#define VFE_0_IRQ_CMD			0x024
-#define VFE_0_IRQ_CMD_GLOBAL_CLEAR	(1 << 0)
-
-#define VFE_0_IRQ_MASK_0		0x028
-#define VFE_0_IRQ_MASK_0_CAMIF_SOF			(1 << 0)
-#define VFE_0_IRQ_MASK_0_CAMIF_EOF			(1 << 1)
-#define VFE_0_IRQ_MASK_0_RDIn_REG_UPDATE(n)		(1 << ((n) + 5))
-#define VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(n)		\
-	((n) == VFE_LINE_PIX ? (1 << 4) : VFE_0_IRQ_MASK_0_RDIn_REG_UPDATE(n))
-#define VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(n)	(1 << ((n) + 8))
-#define VFE_0_IRQ_MASK_0_IMAGE_COMPOSITE_DONE_n(n)	(1 << ((n) + 25))
-#define VFE_0_IRQ_MASK_0_RESET_ACK			(1 << 31)
-#define VFE_0_IRQ_MASK_1		0x02c
-#define VFE_0_IRQ_MASK_1_CAMIF_ERROR			(1 << 0)
-#define VFE_0_IRQ_MASK_1_VIOLATION			(1 << 7)
-#define VFE_0_IRQ_MASK_1_BUS_BDG_HALT_ACK		(1 << 8)
-#define VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(n)	(1 << ((n) + 9))
-#define VFE_0_IRQ_MASK_1_RDIn_SOF(n)			(1 << ((n) + 29))
-
-#define VFE_0_IRQ_CLEAR_0		0x030
-#define VFE_0_IRQ_CLEAR_1		0x034
-
-#define VFE_0_IRQ_STATUS_0		0x038
-#define VFE_0_IRQ_STATUS_0_CAMIF_SOF			(1 << 0)
-#define VFE_0_IRQ_STATUS_0_RDIn_REG_UPDATE(n)		(1 << ((n) + 5))
-#define VFE_0_IRQ_STATUS_0_line_n_REG_UPDATE(n)		\
-	((n) == VFE_LINE_PIX ? (1 << 4) : VFE_0_IRQ_STATUS_0_RDIn_REG_UPDATE(n))
-#define VFE_0_IRQ_STATUS_0_IMAGE_MASTER_n_PING_PONG(n)	(1 << ((n) + 8))
-#define VFE_0_IRQ_STATUS_0_IMAGE_COMPOSITE_DONE_n(n)	(1 << ((n) + 25))
-#define VFE_0_IRQ_STATUS_0_RESET_ACK			(1 << 31)
-#define VFE_0_IRQ_STATUS_1		0x03c
-#define VFE_0_IRQ_STATUS_1_VIOLATION			(1 << 7)
-#define VFE_0_IRQ_STATUS_1_BUS_BDG_HALT_ACK		(1 << 8)
-#define VFE_0_IRQ_STATUS_1_RDIn_SOF(n)			(1 << ((n) + 29))
-
-#define VFE_0_IRQ_COMPOSITE_MASK_0	0x40
-#define VFE_0_VIOLATION_STATUS		0x48
-
-#define VFE_0_BUS_CMD			0x4c
-#define VFE_0_BUS_CMD_Mx_RLD_CMD(x)	(1 << (x))
-
-#define VFE_0_BUS_CFG			0x050
-
-#define VFE_0_BUS_XBAR_CFG_x(x)		(0x58 + 0x4 * ((x) / 2))
-#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN			(1 << 1)
-#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA	(0x3 << 4)
-#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT		8
-#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_LUMA		0
-#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0	5
-#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1	6
-#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2	7
-
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(n)		(0x06c + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT	0
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_FRM_BASED_SHIFT	1
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_PING_ADDR(n)	(0x070 + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_PONG_ADDR(n)	(0x074 + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(n)		(0x078 + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_SHIFT	2
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK	(0x1F << 2)
-
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG(n)		(0x07c + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG_OFFSET_SHIFT	16
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(n)	(0x080 + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(n)	(0x084 + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_FRAMEDROP_PATTERN(n)	\
-							(0x088 + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN(n)	\
-							(0x08c + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN_DEF	0xffffffff
-
-#define VFE_0_BUS_PING_PONG_STATUS	0x268
-
-#define VFE_0_BUS_BDG_CMD		0x2c0
-#define VFE_0_BUS_BDG_CMD_HALT_REQ	1
-
-#define VFE_0_BUS_BDG_QOS_CFG_0		0x2c4
-#define VFE_0_BUS_BDG_QOS_CFG_0_CFG	0xaaa5aaa5
-#define VFE_0_BUS_BDG_QOS_CFG_1		0x2c8
-#define VFE_0_BUS_BDG_QOS_CFG_2		0x2cc
-#define VFE_0_BUS_BDG_QOS_CFG_3		0x2d0
-#define VFE_0_BUS_BDG_QOS_CFG_4		0x2d4
-#define VFE_0_BUS_BDG_QOS_CFG_5		0x2d8
-#define VFE_0_BUS_BDG_QOS_CFG_6		0x2dc
-#define VFE_0_BUS_BDG_QOS_CFG_7		0x2e0
-#define VFE_0_BUS_BDG_QOS_CFG_7_CFG	0x0001aaa5
-
-#define VFE_0_RDI_CFG_x(x)		(0x2e8 + (0x4 * (x)))
-#define VFE_0_RDI_CFG_x_RDI_STREAM_SEL_SHIFT	28
-#define VFE_0_RDI_CFG_x_RDI_STREAM_SEL_MASK	(0xf << 28)
-#define VFE_0_RDI_CFG_x_RDI_M0_SEL_SHIFT	4
-#define VFE_0_RDI_CFG_x_RDI_M0_SEL_MASK		(0xf << 4)
-#define VFE_0_RDI_CFG_x_RDI_EN_BIT		(1 << 2)
-#define VFE_0_RDI_CFG_x_MIPI_EN_BITS		0x3
-#define VFE_0_RDI_CFG_x_RDI_Mr_FRAME_BASED_EN(r)	(1 << (16 + (r)))
-
-#define VFE_0_CAMIF_CMD				0x2f4
-#define VFE_0_CAMIF_CMD_DISABLE_FRAME_BOUNDARY	0
-#define VFE_0_CAMIF_CMD_ENABLE_FRAME_BOUNDARY	1
-#define VFE_0_CAMIF_CMD_CLEAR_CAMIF_STATUS	(1 << 2)
-#define VFE_0_CAMIF_CFG				0x2f8
-#define VFE_0_CAMIF_CFG_VFE_OUTPUT_EN		(1 << 6)
-#define VFE_0_CAMIF_FRAME_CFG			0x300
-#define VFE_0_CAMIF_WINDOW_WIDTH_CFG		0x304
-#define VFE_0_CAMIF_WINDOW_HEIGHT_CFG		0x308
-#define VFE_0_CAMIF_SUBSAMPLE_CFG_0		0x30c
-#define VFE_0_CAMIF_IRQ_SUBSAMPLE_PATTERN	0x314
-#define VFE_0_CAMIF_STATUS			0x31c
-#define VFE_0_CAMIF_STATUS_HALT			(1 << 31)
-
-#define VFE_0_REG_UPDATE			0x378
-#define VFE_0_REG_UPDATE_RDIn(n)		(1 << (1 + (n)))
-#define VFE_0_REG_UPDATE_line_n(n)		\
-			((n) == VFE_LINE_PIX ? 1 : VFE_0_REG_UPDATE_RDIn(n))
-
-#define VFE_0_DEMUX_CFG				0x424
-#define VFE_0_DEMUX_CFG_PERIOD			0x3
-#define VFE_0_DEMUX_GAIN_0			0x428
-#define VFE_0_DEMUX_GAIN_0_CH0_EVEN		(0x80 << 0)
-#define VFE_0_DEMUX_GAIN_0_CH0_ODD		(0x80 << 16)
-#define VFE_0_DEMUX_GAIN_1			0x42c
-#define VFE_0_DEMUX_GAIN_1_CH1			(0x80 << 0)
-#define VFE_0_DEMUX_GAIN_1_CH2			(0x80 << 16)
-#define VFE_0_DEMUX_EVEN_CFG			0x438
-#define VFE_0_DEMUX_EVEN_CFG_PATTERN_YUYV	0x9cac
-#define VFE_0_DEMUX_EVEN_CFG_PATTERN_YVYU	0xac9c
-#define VFE_0_DEMUX_EVEN_CFG_PATTERN_UYVY	0xc9ca
-#define VFE_0_DEMUX_EVEN_CFG_PATTERN_VYUY	0xcac9
-#define VFE_0_DEMUX_ODD_CFG			0x43c
-#define VFE_0_DEMUX_ODD_CFG_PATTERN_YUYV	0x9cac
-#define VFE_0_DEMUX_ODD_CFG_PATTERN_YVYU	0xac9c
-#define VFE_0_DEMUX_ODD_CFG_PATTERN_UYVY	0xc9ca
-#define VFE_0_DEMUX_ODD_CFG_PATTERN_VYUY	0xcac9
-
-#define VFE_0_SCALE_ENC_Y_CFG			0x75c
-#define VFE_0_SCALE_ENC_Y_H_IMAGE_SIZE		0x760
-#define VFE_0_SCALE_ENC_Y_H_PHASE		0x764
-#define VFE_0_SCALE_ENC_Y_V_IMAGE_SIZE		0x76c
-#define VFE_0_SCALE_ENC_Y_V_PHASE		0x770
-#define VFE_0_SCALE_ENC_CBCR_CFG		0x778
-#define VFE_0_SCALE_ENC_CBCR_H_IMAGE_SIZE	0x77c
-#define VFE_0_SCALE_ENC_CBCR_H_PHASE		0x780
-#define VFE_0_SCALE_ENC_CBCR_V_IMAGE_SIZE	0x790
-#define VFE_0_SCALE_ENC_CBCR_V_PHASE		0x794
-
-#define VFE_0_CROP_ENC_Y_WIDTH			0x854
-#define VFE_0_CROP_ENC_Y_HEIGHT			0x858
-#define VFE_0_CROP_ENC_CBCR_WIDTH		0x85c
-#define VFE_0_CROP_ENC_CBCR_HEIGHT		0x860
-
-#define VFE_0_CLAMP_ENC_MAX_CFG			0x874
-#define VFE_0_CLAMP_ENC_MAX_CFG_CH0		(0xff << 0)
-#define VFE_0_CLAMP_ENC_MAX_CFG_CH1		(0xff << 8)
-#define VFE_0_CLAMP_ENC_MAX_CFG_CH2		(0xff << 16)
-#define VFE_0_CLAMP_ENC_MIN_CFG			0x878
-#define VFE_0_CLAMP_ENC_MIN_CFG_CH0		(0x0 << 0)
-#define VFE_0_CLAMP_ENC_MIN_CFG_CH1		(0x0 << 8)
-#define VFE_0_CLAMP_ENC_MIN_CFG_CH2		(0x0 << 16)
-
-#define VFE_0_CGC_OVERRIDE_1			0x974
-#define VFE_0_CGC_OVERRIDE_1_IMAGE_Mx_CGC_OVERRIDE(x)	(1 << (x))
+	container_of(vfe_line_array(ptr_line), struct vfe_device, line)
 
 /* VFE reset timeout */
 #define VFE_RESET_TIMEOUT_MS 50
@@ -238,633 +43,230 @@
 
 #define VFE_NEXT_SOF_MS 500
 
-#define CAMIF_TIMEOUT_SLEEP_US 1000
-#define CAMIF_TIMEOUT_ALL_US 1000000
-
 #define SCALER_RATIO_MAX 16
 
-static const struct {
+struct vfe_format {
 	u32 code;
 	u8 bpp;
-} vfe_formats[] = {
-	{
-		MEDIA_BUS_FMT_UYVY8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_VYUY8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_YUYV8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_YVYU8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR12_1X12,
-		12,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG12_1X12,
-		12,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG12_1X12,
-		12,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB12_1X12,
-		12,
-	}
+};
+
+static const struct vfe_format formats_rdi_8x16[] = {
+	{ MEDIA_BUS_FMT_UYVY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, 8 },
+	{ MEDIA_BUS_FMT_SBGGR8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SGBRG8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SGRBG8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SRGGB8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SBGGR10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SGBRG10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SGRBG10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SRGGB10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SBGGR12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SGBRG12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SGRBG12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SRGGB12_1X12, 12 },
+	{ MEDIA_BUS_FMT_Y10_1X10, 10 },
+};
+
+static const struct vfe_format formats_pix_8x16[] = {
+	{ MEDIA_BUS_FMT_UYVY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, 8 },
+};
+
+static const struct vfe_format formats_rdi_8x96[] = {
+	{ MEDIA_BUS_FMT_UYVY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, 8 },
+	{ MEDIA_BUS_FMT_SBGGR8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SGBRG8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SGRBG8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SRGGB8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SBGGR10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SGBRG10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SGRBG10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SRGGB10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE, 16 },
+	{ MEDIA_BUS_FMT_SBGGR12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SGBRG12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SGRBG12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SRGGB12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SBGGR14_1X14, 14 },
+	{ MEDIA_BUS_FMT_SGBRG14_1X14, 14 },
+	{ MEDIA_BUS_FMT_SGRBG14_1X14, 14 },
+	{ MEDIA_BUS_FMT_SRGGB14_1X14, 14 },
+	{ MEDIA_BUS_FMT_Y10_1X10, 10 },
+	{ MEDIA_BUS_FMT_Y10_2X8_PADHI_LE, 16 },
+};
+
+static const struct vfe_format formats_pix_8x96[] = {
+	{ MEDIA_BUS_FMT_UYVY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, 8 },
 };
 
 /*
  * vfe_get_bpp - map media bus format to bits per pixel
+ * @formats: supported media bus formats array
+ * @nformats: size of @formats array
  * @code: media bus format code
  *
  * Return number of bits per pixel
  */
-static u8 vfe_get_bpp(u32 code)
+static u8 vfe_get_bpp(const struct vfe_format *formats,
+		      unsigned int nformats, u32 code)
 {
 	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(vfe_formats); i++)
-		if (code == vfe_formats[i].code)
-			return vfe_formats[i].bpp;
+	for (i = 0; i < nformats; i++)
+		if (code == formats[i].code)
+			return formats[i].bpp;
 
 	WARN(1, "Unknown format\n");
 
-	return vfe_formats[0].bpp;
-}
-
-static inline void vfe_reg_clr(struct vfe_device *vfe, u32 reg, u32 clr_bits)
-{
-	u32 bits = readl_relaxed(vfe->base + reg);
-
-	writel_relaxed(bits & ~clr_bits, vfe->base + reg);
-}
-
-static inline void vfe_reg_set(struct vfe_device *vfe, u32 reg, u32 set_bits)
-{
-	u32 bits = readl_relaxed(vfe->base + reg);
-
-	writel_relaxed(bits | set_bits, vfe->base + reg);
-}
-
-static void vfe_global_reset(struct vfe_device *vfe)
-{
-	u32 reset_bits = VFE_0_GLOBAL_RESET_CMD_TESTGEN		|
-			 VFE_0_GLOBAL_RESET_CMD_BUS_MISR	|
-			 VFE_0_GLOBAL_RESET_CMD_PM		|
-			 VFE_0_GLOBAL_RESET_CMD_TIMER		|
-			 VFE_0_GLOBAL_RESET_CMD_REGISTER	|
-			 VFE_0_GLOBAL_RESET_CMD_BUS_BDG		|
-			 VFE_0_GLOBAL_RESET_CMD_BUS		|
-			 VFE_0_GLOBAL_RESET_CMD_CAMIF		|
-			 VFE_0_GLOBAL_RESET_CMD_CORE;
-
-	writel_relaxed(reset_bits, vfe->base + VFE_0_GLOBAL_RESET_CMD);
-}
-
-static void vfe_wm_enable(struct vfe_device *vfe, u8 wm, u8 enable)
-{
-	if (enable)
-		vfe_reg_set(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
-			    1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT);
-	else
-		vfe_reg_clr(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
-			    1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT);
+	return formats[0].bpp;
 }
 
-static void vfe_wm_frame_based(struct vfe_device *vfe, u8 wm, u8 enable)
-{
-	if (enable)
-		vfe_reg_set(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
-			1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_FRM_BASED_SHIFT);
-	else
-		vfe_reg_clr(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
-			1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_FRM_BASED_SHIFT);
-}
-
-#define CALC_WORD(width, M, N) (((width) * (M) + (N) - 1) / (N))
-
-static int vfe_word_per_line(uint32_t format, uint32_t pixel_per_line)
+static u32 vfe_find_code(u32 *code, unsigned int n_code,
+			 unsigned int index, u32 req_code)
 {
-	int val = 0;
-
-	switch (format) {
-	case V4L2_PIX_FMT_NV12:
-	case V4L2_PIX_FMT_NV21:
-	case V4L2_PIX_FMT_NV16:
-	case V4L2_PIX_FMT_NV61:
-		val = CALC_WORD(pixel_per_line, 1, 8);
-		break;
-	case V4L2_PIX_FMT_YUYV:
-	case V4L2_PIX_FMT_YVYU:
-	case V4L2_PIX_FMT_UYVY:
-	case V4L2_PIX_FMT_VYUY:
-		val = CALC_WORD(pixel_per_line, 2, 8);
-		break;
-	}
-
-	return val;
-}
-
-static void vfe_get_wm_sizes(struct v4l2_pix_format_mplane *pix, u8 plane,
-			     u16 *width, u16 *height, u16 *bytesperline)
-{
-	switch (pix->pixelformat) {
-	case V4L2_PIX_FMT_NV12:
-	case V4L2_PIX_FMT_NV21:
-		*width = pix->width;
-		*height = pix->height;
-		*bytesperline = pix->plane_fmt[0].bytesperline;
-		if (plane == 1)
-			*height /= 2;
-		break;
-	case V4L2_PIX_FMT_NV16:
-	case V4L2_PIX_FMT_NV61:
-		*width = pix->width;
-		*height = pix->height;
-		*bytesperline = pix->plane_fmt[0].bytesperline;
-		break;
-	}
-}
-
-static void vfe_wm_line_based(struct vfe_device *vfe, u32 wm,
-			      struct v4l2_pix_format_mplane *pix,
-			      u8 plane, u32 enable)
-{
-	u32 reg;
-
-	if (enable) {
-		u16 width = 0, height = 0, bytesperline = 0, wpl;
-
-		vfe_get_wm_sizes(pix, plane, &width, &height, &bytesperline);
-
-		wpl = vfe_word_per_line(pix->pixelformat, width);
-
-		reg = height - 1;
-		reg |= ((wpl + 1) / 2 - 1) << 16;
-
-		writel_relaxed(reg, vfe->base +
-			       VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(wm));
-
-		wpl = vfe_word_per_line(pix->pixelformat, bytesperline);
-
-		reg = 0x3;
-		reg |= (height - 1) << 4;
-		reg |= wpl << 16;
-
-		writel_relaxed(reg, vfe->base +
-			       VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(wm));
-	} else {
-		writel_relaxed(0, vfe->base +
-			       VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(wm));
-		writel_relaxed(0, vfe->base +
-			       VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(wm));
-	}
-}
-
-static void vfe_wm_set_framedrop_period(struct vfe_device *vfe, u8 wm, u8 per)
-{
-	u32 reg;
-
-	reg = readl_relaxed(vfe->base +
-			    VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm));
-
-	reg &= ~(VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK);
-
-	reg |= (per << VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_SHIFT)
-		& VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK;
-
-	writel_relaxed(reg,
-		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm));
-}
-
-static void vfe_wm_set_framedrop_pattern(struct vfe_device *vfe, u8 wm,
-					 u32 pattern)
-{
-	writel_relaxed(pattern,
-	       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_FRAMEDROP_PATTERN(wm));
-}
-
-static void vfe_wm_set_ub_cfg(struct vfe_device *vfe, u8 wm, u16 offset,
-			      u16 depth)
-{
-	u32 reg;
-
-	reg = (offset << VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG_OFFSET_SHIFT) |
-		depth;
-	writel_relaxed(reg, vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG(wm));
-}
-
-static void vfe_bus_reload_wm(struct vfe_device *vfe, u8 wm)
-{
-	wmb();
-	writel_relaxed(VFE_0_BUS_CMD_Mx_RLD_CMD(wm), vfe->base + VFE_0_BUS_CMD);
-	wmb();
-}
-
-static void vfe_wm_set_ping_addr(struct vfe_device *vfe, u8 wm, u32 addr)
-{
-	writel_relaxed(addr,
-		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_PING_ADDR(wm));
-}
-
-static void vfe_wm_set_pong_addr(struct vfe_device *vfe, u8 wm, u32 addr)
-{
-	writel_relaxed(addr,
-		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_PONG_ADDR(wm));
-}
-
-static int vfe_wm_get_ping_pong_status(struct vfe_device *vfe, u8 wm)
-{
-	u32 reg;
-
-	reg = readl_relaxed(vfe->base + VFE_0_BUS_PING_PONG_STATUS);
-
-	return (reg >> wm) & 0x1;
-}
-
-static void vfe_bus_enable_wr_if(struct vfe_device *vfe, u8 enable)
-{
-	if (enable)
-		writel_relaxed(0x10000009, vfe->base + VFE_0_BUS_CFG);
-	else
-		writel_relaxed(0, vfe->base + VFE_0_BUS_CFG);
-}
-
-static void vfe_bus_connect_wm_to_rdi(struct vfe_device *vfe, u8 wm,
-				      enum vfe_line_id id)
-{
-	u32 reg;
-
-	reg = VFE_0_RDI_CFG_x_MIPI_EN_BITS;
-	reg |= VFE_0_RDI_CFG_x_RDI_Mr_FRAME_BASED_EN(id);
-	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(0), reg);
-
-	reg = VFE_0_RDI_CFG_x_RDI_EN_BIT;
-	reg |= ((3 * id) << VFE_0_RDI_CFG_x_RDI_STREAM_SEL_SHIFT) &
-		VFE_0_RDI_CFG_x_RDI_STREAM_SEL_MASK;
-	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(id), reg);
-
-	switch (id) {
-	case VFE_LINE_RDI0:
-	default:
-		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0 <<
-		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		break;
-	case VFE_LINE_RDI1:
-		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1 <<
-		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		break;
-	case VFE_LINE_RDI2:
-		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2 <<
-		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		break;
-	}
-
-	if (wm % 2 == 1)
-		reg <<= 16;
-
-	vfe_reg_set(vfe, VFE_0_BUS_XBAR_CFG_x(wm), reg);
-}
-
-static void vfe_wm_set_subsample(struct vfe_device *vfe, u8 wm)
-{
-	writel_relaxed(VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN_DEF,
-	       vfe->base +
-	       VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN(wm));
-}
-
-static void vfe_bus_disconnect_wm_from_rdi(struct vfe_device *vfe, u8 wm,
-					   enum vfe_line_id id)
-{
-	u32 reg;
-
-	reg = VFE_0_RDI_CFG_x_RDI_Mr_FRAME_BASED_EN(id);
-	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(0), reg);
-
-	reg = VFE_0_RDI_CFG_x_RDI_EN_BIT;
-	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(id), reg);
-
-	switch (id) {
-	case VFE_LINE_RDI0:
-	default:
-		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0 <<
-		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		break;
-	case VFE_LINE_RDI1:
-		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1 <<
-		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		break;
-	case VFE_LINE_RDI2:
-		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2 <<
-		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		break;
-	}
-
-	if (wm % 2 == 1)
-		reg <<= 16;
-
-	vfe_reg_clr(vfe, VFE_0_BUS_XBAR_CFG_x(wm), reg);
-}
+	int i;
 
-static void vfe_set_xbar_cfg(struct vfe_device *vfe, struct vfe_output *output,
-			     u8 enable)
-{
-	struct vfe_line *line = container_of(output, struct vfe_line, output);
-	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
-	u32 reg;
-	unsigned int i;
+	if (!req_code && (index >= n_code))
+		return 0;
 
-	for (i = 0; i < output->wm_num; i++) {
-		if (i == 0) {
-			reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_LUMA <<
-				VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		} else if (i == 1) {
-			reg = VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN;
-			if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV16)
-				reg |= VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA;
+	for (i = 0; i < n_code; i++)
+		if (req_code) {
+			if (req_code == code[i])
+				return req_code;
 		} else {
-			/* On current devices output->wm_num is always <= 2 */
-			break;
+			if (i == index)
+				return code[i];
 		}
 
-		if (output->wm_idx[i] % 2 == 1)
-			reg <<= 16;
-
-		if (enable)
-			vfe_reg_set(vfe,
-				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[i]),
-				    reg);
-		else
-			vfe_reg_clr(vfe,
-				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[i]),
-				    reg);
-	}
-}
-
-static void vfe_set_rdi_cid(struct vfe_device *vfe, enum vfe_line_id id, u8 cid)
-{
-	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(id),
-		    VFE_0_RDI_CFG_x_RDI_M0_SEL_MASK);
-
-	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(id),
-		    cid << VFE_0_RDI_CFG_x_RDI_M0_SEL_SHIFT);
+	return code[0];
 }
 
-static void vfe_reg_update(struct vfe_device *vfe, enum vfe_line_id line_id)
+static u32 vfe_src_pad_code(struct vfe_line *line, u32 sink_code,
+			    unsigned int index, u32 src_req_code)
 {
-	vfe->reg_update |= VFE_0_REG_UPDATE_line_n(line_id);
-	wmb();
-	writel_relaxed(vfe->reg_update, vfe->base + VFE_0_REG_UPDATE);
-	wmb();
-}
-
-static void vfe_enable_irq_wm_line(struct vfe_device *vfe, u8 wm,
-				   enum vfe_line_id line_id, u8 enable)
-{
-	u32 irq_en0 = VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(wm) |
-		      VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(line_id);
-	u32 irq_en1 = VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(wm) |
-		      VFE_0_IRQ_MASK_1_RDIn_SOF(line_id);
-
-	if (enable) {
-		vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
-		vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
-	} else {
-		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_0, irq_en0);
-		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_1, irq_en1);
-	}
-}
-
-static void vfe_enable_irq_pix_line(struct vfe_device *vfe, u8 comp,
-				    enum vfe_line_id line_id, u8 enable)
-{
-	struct vfe_output *output = &vfe->line[line_id].output;
-	unsigned int i;
-	u32 irq_en0;
-	u32 irq_en1;
-	u32 comp_mask = 0;
-
-	irq_en0 = VFE_0_IRQ_MASK_0_CAMIF_SOF;
-	irq_en0 |= VFE_0_IRQ_MASK_0_CAMIF_EOF;
-	irq_en0 |= VFE_0_IRQ_MASK_0_IMAGE_COMPOSITE_DONE_n(comp);
-	irq_en0 |= VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(line_id);
-	irq_en1 = VFE_0_IRQ_MASK_1_CAMIF_ERROR;
-	for (i = 0; i < output->wm_num; i++) {
-		irq_en1 |= VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(
-							output->wm_idx[i]);
-		comp_mask |= (1 << output->wm_idx[i]) << comp * 8;
-	}
-
-	if (enable) {
-		vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
-		vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
-		vfe_reg_set(vfe, VFE_0_IRQ_COMPOSITE_MASK_0, comp_mask);
-	} else {
-		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_0, irq_en0);
-		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_1, irq_en1);
-		vfe_reg_clr(vfe, VFE_0_IRQ_COMPOSITE_MASK_0, comp_mask);
-	}
-}
-
-static void vfe_enable_irq_common(struct vfe_device *vfe)
-{
-	u32 irq_en0 = VFE_0_IRQ_MASK_0_RESET_ACK;
-	u32 irq_en1 = VFE_0_IRQ_MASK_1_VIOLATION |
-		      VFE_0_IRQ_MASK_1_BUS_BDG_HALT_ACK;
-
-	vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
-	vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
-}
-
-static void vfe_set_demux_cfg(struct vfe_device *vfe, struct vfe_line *line)
-{
-	u32 val, even_cfg, odd_cfg;
-
-	writel_relaxed(VFE_0_DEMUX_CFG_PERIOD, vfe->base + VFE_0_DEMUX_CFG);
-
-	val = VFE_0_DEMUX_GAIN_0_CH0_EVEN | VFE_0_DEMUX_GAIN_0_CH0_ODD;
-	writel_relaxed(val, vfe->base + VFE_0_DEMUX_GAIN_0);
-
-	val = VFE_0_DEMUX_GAIN_1_CH1 | VFE_0_DEMUX_GAIN_1_CH2;
-	writel_relaxed(val, vfe->base + VFE_0_DEMUX_GAIN_1);
+	struct vfe_device *vfe = to_vfe(line);
 
-	switch (line->fmt[MSM_VFE_PAD_SINK].code) {
-	case MEDIA_BUS_FMT_YUYV8_2X8:
-		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_YUYV;
-		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_YUYV;
-		break;
-	case MEDIA_BUS_FMT_YVYU8_2X8:
-		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_YVYU;
-		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_YVYU;
-		break;
-	case MEDIA_BUS_FMT_UYVY8_2X8:
-	default:
-		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_UYVY;
-		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_UYVY;
-		break;
-	case MEDIA_BUS_FMT_VYUY8_2X8:
-		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_VYUY;
-		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_VYUY;
-		break;
-	}
+	if (vfe->camss->version == CAMSS_8x16)
+		switch (sink_code) {
+		case MEDIA_BUS_FMT_YUYV8_2X8:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_YUYV8_2X8,
+				MEDIA_BUS_FMT_YUYV8_1_5X8,
+			};
+
+			return vfe_find_code(src_code, ARRAY_SIZE(src_code),
+					     index, src_req_code);
+		}
+		case MEDIA_BUS_FMT_YVYU8_2X8:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_YVYU8_2X8,
+				MEDIA_BUS_FMT_YVYU8_1_5X8,
+			};
+
+			return vfe_find_code(src_code, ARRAY_SIZE(src_code),
+					     index, src_req_code);
+		}
+		case MEDIA_BUS_FMT_UYVY8_2X8:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_UYVY8_2X8,
+				MEDIA_BUS_FMT_UYVY8_1_5X8,
+			};
+
+			return vfe_find_code(src_code, ARRAY_SIZE(src_code),
+					     index, src_req_code);
+		}
+		case MEDIA_BUS_FMT_VYUY8_2X8:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_VYUY8_2X8,
+				MEDIA_BUS_FMT_VYUY8_1_5X8,
+			};
+
+			return vfe_find_code(src_code, ARRAY_SIZE(src_code),
+					     index, src_req_code);
+		}
+		default:
+			if (index > 0)
+				return 0;
 
-	writel_relaxed(even_cfg, vfe->base + VFE_0_DEMUX_EVEN_CFG);
-	writel_relaxed(odd_cfg, vfe->base + VFE_0_DEMUX_ODD_CFG);
-}
+			return sink_code;
+		}
+	else if (vfe->camss->version == CAMSS_8x96)
+		switch (sink_code) {
+		case MEDIA_BUS_FMT_YUYV8_2X8:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_YUYV8_2X8,
+				MEDIA_BUS_FMT_YVYU8_2X8,
+				MEDIA_BUS_FMT_UYVY8_2X8,
+				MEDIA_BUS_FMT_VYUY8_2X8,
+				MEDIA_BUS_FMT_YUYV8_1_5X8,
+			};
+
+			return vfe_find_code(src_code, ARRAY_SIZE(src_code),
+					     index, src_req_code);
+		}
+		case MEDIA_BUS_FMT_YVYU8_2X8:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_YVYU8_2X8,
+				MEDIA_BUS_FMT_YUYV8_2X8,
+				MEDIA_BUS_FMT_UYVY8_2X8,
+				MEDIA_BUS_FMT_VYUY8_2X8,
+				MEDIA_BUS_FMT_YVYU8_1_5X8,
+			};
+
+			return vfe_find_code(src_code, ARRAY_SIZE(src_code),
+					     index, src_req_code);
+		}
+		case MEDIA_BUS_FMT_UYVY8_2X8:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_UYVY8_2X8,
+				MEDIA_BUS_FMT_YUYV8_2X8,
+				MEDIA_BUS_FMT_YVYU8_2X8,
+				MEDIA_BUS_FMT_VYUY8_2X8,
+				MEDIA_BUS_FMT_UYVY8_1_5X8,
+			};
+
+			return vfe_find_code(src_code, ARRAY_SIZE(src_code),
+					     index, src_req_code);
+		}
+		case MEDIA_BUS_FMT_VYUY8_2X8:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_VYUY8_2X8,
+				MEDIA_BUS_FMT_YUYV8_2X8,
+				MEDIA_BUS_FMT_YVYU8_2X8,
+				MEDIA_BUS_FMT_UYVY8_2X8,
+				MEDIA_BUS_FMT_VYUY8_1_5X8,
+			};
+
+			return vfe_find_code(src_code, ARRAY_SIZE(src_code),
+					     index, src_req_code);
+		}
+		default:
+			if (index > 0)
+				return 0;
 
-static inline u8 vfe_calc_interp_reso(u16 input, u16 output)
-{
-	if (input / output >= 16)
+			return sink_code;
+		}
+	else
 		return 0;
-
-	if (input / output >= 8)
-		return 1;
-
-	if (input / output >= 4)
-		return 2;
-
-	return 3;
-}
-
-static void vfe_set_scale_cfg(struct vfe_device *vfe, struct vfe_line *line)
-{
-	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
-	u32 reg;
-	u16 input, output;
-	u8 interp_reso;
-	u32 phase_mult;
-
-	writel_relaxed(0x3, vfe->base + VFE_0_SCALE_ENC_Y_CFG);
-
-	input = line->fmt[MSM_VFE_PAD_SINK].width;
-	output = line->compose.width;
-	reg = (output << 16) | input;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_H_IMAGE_SIZE);
-
-	interp_reso = vfe_calc_interp_reso(input, output);
-	phase_mult = input * (1 << (13 + interp_reso)) / output;
-	reg = (interp_reso << 20) | phase_mult;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_H_PHASE);
-
-	input = line->fmt[MSM_VFE_PAD_SINK].height;
-	output = line->compose.height;
-	reg = (output << 16) | input;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_V_IMAGE_SIZE);
-
-	interp_reso = vfe_calc_interp_reso(input, output);
-	phase_mult = input * (1 << (13 + interp_reso)) / output;
-	reg = (interp_reso << 20) | phase_mult;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_V_PHASE);
-
-	writel_relaxed(0x3, vfe->base + VFE_0_SCALE_ENC_CBCR_CFG);
-
-	input = line->fmt[MSM_VFE_PAD_SINK].width;
-	output = line->compose.width / 2;
-	reg = (output << 16) | input;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_H_IMAGE_SIZE);
-
-	interp_reso = vfe_calc_interp_reso(input, output);
-	phase_mult = input * (1 << (13 + interp_reso)) / output;
-	reg = (interp_reso << 20) | phase_mult;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_H_PHASE);
-
-	input = line->fmt[MSM_VFE_PAD_SINK].height;
-	output = line->compose.height;
-	if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV21)
-		output = line->compose.height / 2;
-	reg = (output << 16) | input;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_V_IMAGE_SIZE);
-
-	interp_reso = vfe_calc_interp_reso(input, output);
-	phase_mult = input * (1 << (13 + interp_reso)) / output;
-	reg = (interp_reso << 20) | phase_mult;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_V_PHASE);
-}
-
-static void vfe_set_crop_cfg(struct vfe_device *vfe, struct vfe_line *line)
-{
-	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
-	u32 reg;
-	u16 first, last;
-
-	first = line->crop.left;
-	last = line->crop.left + line->crop.width - 1;
-	reg = (first << 16) | last;
-	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_Y_WIDTH);
-
-	first = line->crop.top;
-	last = line->crop.top + line->crop.height - 1;
-	reg = (first << 16) | last;
-	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_Y_HEIGHT);
-
-	first = line->crop.left / 2;
-	last = line->crop.left / 2 + line->crop.width / 2 - 1;
-	reg = (first << 16) | last;
-	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_CBCR_WIDTH);
-
-	first = line->crop.top;
-	last = line->crop.top + line->crop.height - 1;
-	if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV21) {
-		first = line->crop.top / 2;
-		last = line->crop.top / 2 + line->crop.height / 2 - 1;
-	}
-	reg = (first << 16) | last;
-	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_CBCR_HEIGHT);
-}
-
-static void vfe_set_clamp_cfg(struct vfe_device *vfe)
-{
-	u32 val = VFE_0_CLAMP_ENC_MAX_CFG_CH0 |
-		VFE_0_CLAMP_ENC_MAX_CFG_CH1 |
-		VFE_0_CLAMP_ENC_MAX_CFG_CH2;
-
-	writel_relaxed(val, vfe->base + VFE_0_CLAMP_ENC_MAX_CFG);
-
-	val = VFE_0_CLAMP_ENC_MIN_CFG_CH0 |
-		VFE_0_CLAMP_ENC_MIN_CFG_CH1 |
-		VFE_0_CLAMP_ENC_MIN_CFG_CH2;
-
-	writel_relaxed(val, vfe->base + VFE_0_CLAMP_ENC_MIN_CFG);
 }
 
 /*
@@ -879,12 +281,12 @@ static int vfe_reset(struct vfe_device *vfe)
 
 	reinit_completion(&vfe->reset_complete);
 
-	vfe_global_reset(vfe);
+	vfe->ops->global_reset(vfe);
 
 	time = wait_for_completion_timeout(&vfe->reset_complete,
 		msecs_to_jiffies(VFE_RESET_TIMEOUT_MS));
 	if (!time) {
-		dev_err(to_device(vfe), "VFE reset timeout\n");
+		dev_err(vfe->camss->dev, "VFE reset timeout\n");
 		return -EIO;
 	}
 
@@ -903,13 +305,12 @@ static int vfe_halt(struct vfe_device *vfe)
 
 	reinit_completion(&vfe->halt_complete);
 
-	writel_relaxed(VFE_0_BUS_BDG_CMD_HALT_REQ,
-		       vfe->base + VFE_0_BUS_BDG_CMD);
+	vfe->ops->halt_request(vfe);
 
 	time = wait_for_completion_timeout(&vfe->halt_complete,
 		msecs_to_jiffies(VFE_HALT_TIMEOUT_MS));
 	if (!time) {
-		dev_err(to_device(vfe), "VFE halt timeout\n");
+		dev_err(vfe->camss->dev, "VFE halt timeout\n");
 		return -EIO;
 	}
 
@@ -927,10 +328,6 @@ static void vfe_init_outputs(struct vfe_device *vfe)
 		output->buf[0] = NULL;
 		output->buf[1] = NULL;
 		INIT_LIST_HEAD(&output->pending_bufs);
-
-		output->wm_num = 1;
-		if (vfe->line[i].id == VFE_LINE_PIX)
-			output->wm_num = 2;
 	}
 }
 
@@ -942,115 +339,6 @@ static void vfe_reset_output_maps(struct vfe_device *vfe)
 		vfe->wm_output_map[i] = VFE_LINE_NONE;
 }
 
-static void vfe_set_qos(struct vfe_device *vfe)
-{
-	u32 val = VFE_0_BUS_BDG_QOS_CFG_0_CFG;
-	u32 val7 = VFE_0_BUS_BDG_QOS_CFG_7_CFG;
-
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_0);
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_1);
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_2);
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_3);
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_4);
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_5);
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_6);
-	writel_relaxed(val7, vfe->base + VFE_0_BUS_BDG_QOS_CFG_7);
-}
-
-static void vfe_set_cgc_override(struct vfe_device *vfe, u8 wm, u8 enable)
-{
-	u32 val = VFE_0_CGC_OVERRIDE_1_IMAGE_Mx_CGC_OVERRIDE(wm);
-
-	if (enable)
-		vfe_reg_set(vfe, VFE_0_CGC_OVERRIDE_1, val);
-	else
-		vfe_reg_clr(vfe, VFE_0_CGC_OVERRIDE_1, val);
-
-	wmb();
-}
-
-static void vfe_set_module_cfg(struct vfe_device *vfe, u8 enable)
-{
-	u32 val = VFE_0_MODULE_CFG_DEMUX |
-		  VFE_0_MODULE_CFG_CHROMA_UPSAMPLE |
-		  VFE_0_MODULE_CFG_SCALE_ENC |
-		  VFE_0_MODULE_CFG_CROP_ENC;
-
-	if (enable)
-		writel_relaxed(val, vfe->base + VFE_0_MODULE_CFG);
-	else
-		writel_relaxed(0x0, vfe->base + VFE_0_MODULE_CFG);
-}
-
-static void vfe_set_camif_cfg(struct vfe_device *vfe, struct vfe_line *line)
-{
-	u32 val;
-
-	switch (line->fmt[MSM_VFE_PAD_SINK].code) {
-	case MEDIA_BUS_FMT_YUYV8_2X8:
-		val = VFE_0_CORE_CFG_PIXEL_PATTERN_YCBYCR;
-		break;
-	case MEDIA_BUS_FMT_YVYU8_2X8:
-		val = VFE_0_CORE_CFG_PIXEL_PATTERN_YCRYCB;
-		break;
-	case MEDIA_BUS_FMT_UYVY8_2X8:
-	default:
-		val = VFE_0_CORE_CFG_PIXEL_PATTERN_CBYCRY;
-		break;
-	case MEDIA_BUS_FMT_VYUY8_2X8:
-		val = VFE_0_CORE_CFG_PIXEL_PATTERN_CRYCBY;
-		break;
-	}
-
-	writel_relaxed(val, vfe->base + VFE_0_CORE_CFG);
-
-	val = line->fmt[MSM_VFE_PAD_SINK].width * 2;
-	val |= line->fmt[MSM_VFE_PAD_SINK].height << 16;
-	writel_relaxed(val, vfe->base + VFE_0_CAMIF_FRAME_CFG);
-
-	val = line->fmt[MSM_VFE_PAD_SINK].width * 2 - 1;
-	writel_relaxed(val, vfe->base + VFE_0_CAMIF_WINDOW_WIDTH_CFG);
-
-	val = line->fmt[MSM_VFE_PAD_SINK].height - 1;
-	writel_relaxed(val, vfe->base + VFE_0_CAMIF_WINDOW_HEIGHT_CFG);
-
-	val = 0xffffffff;
-	writel_relaxed(val, vfe->base + VFE_0_CAMIF_SUBSAMPLE_CFG_0);
-
-	val = 0xffffffff;
-	writel_relaxed(val, vfe->base + VFE_0_CAMIF_IRQ_SUBSAMPLE_PATTERN);
-
-	val = VFE_0_RDI_CFG_x_MIPI_EN_BITS;
-	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(0), val);
-
-	val = VFE_0_CAMIF_CFG_VFE_OUTPUT_EN;
-	writel_relaxed(val, vfe->base + VFE_0_CAMIF_CFG);
-}
-
-static void vfe_set_camif_cmd(struct vfe_device *vfe, u32 cmd)
-{
-	writel_relaxed(VFE_0_CAMIF_CMD_CLEAR_CAMIF_STATUS,
-		       vfe->base + VFE_0_CAMIF_CMD);
-
-	writel_relaxed(cmd, vfe->base + VFE_0_CAMIF_CMD);
-}
-
-static int vfe_camif_wait_for_stop(struct vfe_device *vfe)
-{
-	u32 val;
-	int ret;
-
-	ret = readl_poll_timeout(vfe->base + VFE_0_CAMIF_STATUS,
-				 val,
-				 (val & VFE_0_CAMIF_STATUS_HALT),
-				 CAMIF_TIMEOUT_SLEEP_US,
-				 CAMIF_TIMEOUT_ALL_US);
-	if (ret < 0)
-		dev_err(to_device(vfe), "%s: camif stop timeout\n", __func__);
-
-	return ret;
-}
-
 static void vfe_output_init_addrs(struct vfe_device *vfe,
 				  struct vfe_output *output, u8 sync)
 {
@@ -1071,10 +359,10 @@ static void vfe_output_init_addrs(struct vfe_device *vfe,
 		else
 			pong_addr = ping_addr;
 
-		vfe_wm_set_ping_addr(vfe, output->wm_idx[i], ping_addr);
-		vfe_wm_set_pong_addr(vfe, output->wm_idx[i], pong_addr);
+		vfe->ops->wm_set_ping_addr(vfe, output->wm_idx[i], ping_addr);
+		vfe->ops->wm_set_pong_addr(vfe, output->wm_idx[i], pong_addr);
 		if (sync)
-			vfe_bus_reload_wm(vfe, output->wm_idx[i]);
+			vfe->ops->bus_reload_wm(vfe, output->wm_idx[i]);
 	}
 }
 
@@ -1090,9 +378,9 @@ static void vfe_output_update_ping_addr(struct vfe_device *vfe,
 		else
 			addr = 0;
 
-		vfe_wm_set_ping_addr(vfe, output->wm_idx[i], addr);
+		vfe->ops->wm_set_ping_addr(vfe, output->wm_idx[i], addr);
 		if (sync)
-			vfe_bus_reload_wm(vfe, output->wm_idx[i]);
+			vfe->ops->bus_reload_wm(vfe, output->wm_idx[i]);
 	}
 }
 
@@ -1108,9 +396,9 @@ static void vfe_output_update_pong_addr(struct vfe_device *vfe,
 		else
 			addr = 0;
 
-		vfe_wm_set_pong_addr(vfe, output->wm_idx[i], addr);
+		vfe->ops->wm_set_pong_addr(vfe, output->wm_idx[i], addr);
 		if (sync)
-			vfe_bus_reload_wm(vfe, output->wm_idx[i]);
+			vfe->ops->bus_reload_wm(vfe, output->wm_idx[i]);
 	}
 
 }
@@ -1154,12 +442,13 @@ static void vfe_output_frame_drop(struct vfe_device *vfe,
 	drop_period = VFE_FRAME_DROP_VAL + output->drop_update_idx;
 
 	for (i = 0; i < output->wm_num; i++) {
-		vfe_wm_set_framedrop_period(vfe, output->wm_idx[i],
-					    drop_period);
-		vfe_wm_set_framedrop_pattern(vfe, output->wm_idx[i],
-					     drop_pattern);
+		vfe->ops->wm_set_framedrop_period(vfe, output->wm_idx[i],
+						  drop_period);
+		vfe->ops->wm_set_framedrop_pattern(vfe, output->wm_idx[i],
+						   drop_pattern);
 	}
-	vfe_reg_update(vfe, container_of(output, struct vfe_line, output)->id);
+	vfe->ops->reg_update(vfe,
+			     container_of(output, struct vfe_line, output)->id);
 }
 
 static struct camss_buffer *vfe_buf_get_pending(struct vfe_output *output)
@@ -1214,7 +503,7 @@ static void vfe_buf_update_wm_on_next(struct vfe_device *vfe,
 		break;
 	case VFE_OUTPUT_SINGLE:
 	default:
-		dev_err_ratelimited(to_device(vfe),
+		dev_err_ratelimited(vfe->camss->dev,
 				    "Next buf in wrong state! %d\n",
 				    output->state);
 		break;
@@ -1234,7 +523,7 @@ static void vfe_buf_update_wm_on_last(struct vfe_device *vfe,
 		vfe_output_frame_drop(vfe, output, 0);
 		break;
 	default:
-		dev_err_ratelimited(to_device(vfe),
+		dev_err_ratelimited(vfe->camss->dev,
 				    "Last buff in wrong state! %d\n",
 				    output->state);
 		break;
@@ -1263,7 +552,7 @@ static void vfe_buf_update_wm_on_new(struct vfe_device *vfe,
 			output->state = VFE_OUTPUT_CONTINUOUS;
 		} else {
 			vfe_buf_add_pending(output, new_buf);
-			dev_err_ratelimited(to_device(vfe),
+			dev_err_ratelimited(vfe->camss->dev,
 					    "Inactive buffer is busy\n");
 		}
 		break;
@@ -1278,7 +567,7 @@ static void vfe_buf_update_wm_on_new(struct vfe_device *vfe,
 			output->state = VFE_OUTPUT_SINGLE;
 		} else {
 			vfe_buf_add_pending(output, new_buf);
-			dev_err_ratelimited(to_device(vfe),
+			dev_err_ratelimited(vfe->camss->dev,
 					    "Output idle with buffer set!\n");
 		}
 		break;
@@ -1294,6 +583,7 @@ static int vfe_get_output(struct vfe_line *line)
 {
 	struct vfe_device *vfe = to_vfe(line);
 	struct vfe_output *output;
+	struct v4l2_format *f = &line->video_out.active_fmt;
 	unsigned long flags;
 	int i;
 	int wm_idx;
@@ -1302,17 +592,29 @@ static int vfe_get_output(struct vfe_line *line)
 
 	output = &line->output;
 	if (output->state != VFE_OUTPUT_OFF) {
-		dev_err(to_device(vfe), "Output is running\n");
+		dev_err(vfe->camss->dev, "Output is running\n");
 		goto error;
 	}
 	output->state = VFE_OUTPUT_RESERVED;
 
 	output->active_buf = 0;
 
+	switch (f->fmt.pix_mp.pixelformat) {
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV21:
+	case V4L2_PIX_FMT_NV16:
+	case V4L2_PIX_FMT_NV61:
+		output->wm_num = 2;
+		break;
+	default:
+		output->wm_num = 1;
+		break;
+	}
+
 	for (i = 0; i < output->wm_num; i++) {
 		wm_idx = vfe_reserve_wm(vfe, line->id);
 		if (wm_idx < 0) {
-			dev_err(to_device(vfe), "Can not reserve wm\n");
+			dev_err(vfe->camss->dev, "Can not reserve wm\n");
 			goto error_get_wm;
 		}
 		output->wm_idx[i] = wm_idx;
@@ -1356,27 +658,21 @@ static int vfe_enable_output(struct vfe_line *line)
 {
 	struct vfe_device *vfe = to_vfe(line);
 	struct vfe_output *output = &line->output;
+	const struct vfe_hw_ops *ops = vfe->ops;
 	unsigned long flags;
 	unsigned int i;
 	u16 ub_size;
 
-	switch (vfe->id) {
-	case 0:
-		ub_size = MSM_VFE_VFE0_UB_SIZE_RDI;
-		break;
-	case 1:
-		ub_size = MSM_VFE_VFE1_UB_SIZE_RDI;
-		break;
-	default:
+	ub_size = ops->get_ub_size(vfe->id);
+	if (!ub_size)
 		return -EINVAL;
-	}
 
 	spin_lock_irqsave(&vfe->output_lock, flags);
 
-	vfe->reg_update &= ~VFE_0_REG_UPDATE_line_n(line->id);
+	ops->reg_update_clear(vfe, line->id);
 
 	if (output->state != VFE_OUTPUT_RESERVED) {
-		dev_err(to_device(vfe), "Output is not in reserved state %d\n",
+		dev_err(vfe->camss->dev, "Output is not in reserved state %d\n",
 			output->state);
 		spin_unlock_irqrestore(&vfe->output_lock, flags);
 		return -EINVAL;
@@ -1418,42 +714,43 @@ static int vfe_enable_output(struct vfe_line *line)
 	vfe_output_init_addrs(vfe, output, 0);
 
 	if (line->id != VFE_LINE_PIX) {
-		vfe_set_cgc_override(vfe, output->wm_idx[0], 1);
-		vfe_enable_irq_wm_line(vfe, output->wm_idx[0], line->id, 1);
-		vfe_bus_connect_wm_to_rdi(vfe, output->wm_idx[0], line->id);
-		vfe_wm_set_subsample(vfe, output->wm_idx[0]);
-		vfe_set_rdi_cid(vfe, line->id, 0);
-		vfe_wm_set_ub_cfg(vfe, output->wm_idx[0],
-				  (ub_size + 1) * output->wm_idx[0], ub_size);
-		vfe_wm_frame_based(vfe, output->wm_idx[0], 1);
-		vfe_wm_enable(vfe, output->wm_idx[0], 1);
-		vfe_bus_reload_wm(vfe, output->wm_idx[0]);
+		ops->set_cgc_override(vfe, output->wm_idx[0], 1);
+		ops->enable_irq_wm_line(vfe, output->wm_idx[0], line->id, 1);
+		ops->bus_connect_wm_to_rdi(vfe, output->wm_idx[0], line->id);
+		ops->wm_set_subsample(vfe, output->wm_idx[0]);
+		ops->set_rdi_cid(vfe, line->id, 0);
+		ops->wm_set_ub_cfg(vfe, output->wm_idx[0],
+				   (ub_size + 1) * output->wm_idx[0], ub_size);
+		ops->wm_frame_based(vfe, output->wm_idx[0], 1);
+		ops->wm_enable(vfe, output->wm_idx[0], 1);
+		ops->bus_reload_wm(vfe, output->wm_idx[0]);
 	} else {
 		ub_size /= output->wm_num;
 		for (i = 0; i < output->wm_num; i++) {
-			vfe_set_cgc_override(vfe, output->wm_idx[i], 1);
-			vfe_wm_set_subsample(vfe, output->wm_idx[i]);
-			vfe_wm_set_ub_cfg(vfe, output->wm_idx[i],
-					  (ub_size + 1) * output->wm_idx[i],
-					  ub_size);
-			vfe_wm_line_based(vfe, output->wm_idx[i],
+			ops->set_cgc_override(vfe, output->wm_idx[i], 1);
+			ops->wm_set_subsample(vfe, output->wm_idx[i]);
+			ops->wm_set_ub_cfg(vfe, output->wm_idx[i],
+					   (ub_size + 1) * output->wm_idx[i],
+					   ub_size);
+			ops->wm_line_based(vfe, output->wm_idx[i],
 					&line->video_out.active_fmt.fmt.pix_mp,
 					i, 1);
-			vfe_wm_enable(vfe, output->wm_idx[i], 1);
-			vfe_bus_reload_wm(vfe, output->wm_idx[i]);
+			ops->wm_enable(vfe, output->wm_idx[i], 1);
+			ops->bus_reload_wm(vfe, output->wm_idx[i]);
 		}
-		vfe_enable_irq_pix_line(vfe, 0, line->id, 1);
-		vfe_set_module_cfg(vfe, 1);
-		vfe_set_camif_cfg(vfe, line);
-		vfe_set_xbar_cfg(vfe, output, 1);
-		vfe_set_demux_cfg(vfe, line);
-		vfe_set_scale_cfg(vfe, line);
-		vfe_set_crop_cfg(vfe, line);
-		vfe_set_clamp_cfg(vfe);
-		vfe_set_camif_cmd(vfe, VFE_0_CAMIF_CMD_ENABLE_FRAME_BOUNDARY);
+		ops->enable_irq_pix_line(vfe, 0, line->id, 1);
+		ops->set_module_cfg(vfe, 1);
+		ops->set_camif_cfg(vfe, line);
+		ops->set_realign_cfg(vfe, line, 1);
+		ops->set_xbar_cfg(vfe, output, 1);
+		ops->set_demux_cfg(vfe, line);
+		ops->set_scale_cfg(vfe, line);
+		ops->set_crop_cfg(vfe, line);
+		ops->set_clamp_cfg(vfe);
+		ops->set_camif_cmd(vfe, 1);
 	}
 
-	vfe_reg_update(vfe, line->id);
+	ops->reg_update(vfe, line->id);
 
 	spin_unlock_irqrestore(&vfe->output_lock, flags);
 
@@ -1464,6 +761,7 @@ static int vfe_disable_output(struct vfe_line *line)
 {
 	struct vfe_device *vfe = to_vfe(line);
 	struct vfe_output *output = &line->output;
+	const struct vfe_hw_ops *ops = vfe->ops;
 	unsigned long flags;
 	unsigned long time;
 	unsigned int i;
@@ -1476,43 +774,45 @@ static int vfe_disable_output(struct vfe_line *line)
 	time = wait_for_completion_timeout(&output->sof,
 					   msecs_to_jiffies(VFE_NEXT_SOF_MS));
 	if (!time)
-		dev_err(to_device(vfe), "VFE sof timeout\n");
+		dev_err(vfe->camss->dev, "VFE sof timeout\n");
 
 	spin_lock_irqsave(&vfe->output_lock, flags);
 	for (i = 0; i < output->wm_num; i++)
-		vfe_wm_enable(vfe, output->wm_idx[i], 0);
+		ops->wm_enable(vfe, output->wm_idx[i], 0);
 
-	vfe_reg_update(vfe, line->id);
+	ops->reg_update(vfe, line->id);
 	output->wait_reg_update = 1;
 	spin_unlock_irqrestore(&vfe->output_lock, flags);
 
 	time = wait_for_completion_timeout(&output->reg_update,
 					   msecs_to_jiffies(VFE_NEXT_SOF_MS));
 	if (!time)
-		dev_err(to_device(vfe), "VFE reg update timeout\n");
+		dev_err(vfe->camss->dev, "VFE reg update timeout\n");
 
 	spin_lock_irqsave(&vfe->output_lock, flags);
 
 	if (line->id != VFE_LINE_PIX) {
-		vfe_wm_frame_based(vfe, output->wm_idx[0], 0);
-		vfe_bus_disconnect_wm_from_rdi(vfe, output->wm_idx[0], line->id);
-		vfe_enable_irq_wm_line(vfe, output->wm_idx[0], line->id, 0);
-		vfe_set_cgc_override(vfe, output->wm_idx[0], 0);
+		ops->wm_frame_based(vfe, output->wm_idx[0], 0);
+		ops->bus_disconnect_wm_from_rdi(vfe, output->wm_idx[0],
+						line->id);
+		ops->enable_irq_wm_line(vfe, output->wm_idx[0], line->id, 0);
+		ops->set_cgc_override(vfe, output->wm_idx[0], 0);
 		spin_unlock_irqrestore(&vfe->output_lock, flags);
 	} else {
 		for (i = 0; i < output->wm_num; i++) {
-			vfe_wm_line_based(vfe, output->wm_idx[i], NULL, i, 0);
-			vfe_set_cgc_override(vfe, output->wm_idx[i], 0);
+			ops->wm_line_based(vfe, output->wm_idx[i], NULL, i, 0);
+			ops->set_cgc_override(vfe, output->wm_idx[i], 0);
 		}
 
-		vfe_enable_irq_pix_line(vfe, 0, line->id, 0);
-		vfe_set_module_cfg(vfe, 0);
-		vfe_set_xbar_cfg(vfe, output, 0);
+		ops->enable_irq_pix_line(vfe, 0, line->id, 0);
+		ops->set_module_cfg(vfe, 0);
+		ops->set_realign_cfg(vfe, line, 0);
+		ops->set_xbar_cfg(vfe, output, 0);
 
-		vfe_set_camif_cmd(vfe, VFE_0_CAMIF_CMD_DISABLE_FRAME_BOUNDARY);
+		ops->set_camif_cmd(vfe, 0);
 		spin_unlock_irqrestore(&vfe->output_lock, flags);
 
-		vfe_camif_wait_for_stop(vfe);
+		ops->camif_wait_for_stop(vfe, vfe->camss->dev);
 	}
 
 	return 0;
@@ -1532,11 +832,13 @@ static int vfe_enable(struct vfe_line *line)
 	mutex_lock(&vfe->stream_lock);
 
 	if (!vfe->stream_count) {
-		vfe_enable_irq_common(vfe);
+		vfe->ops->enable_irq_common(vfe);
+
+		vfe->ops->bus_enable_wr_if(vfe, 1);
 
-		vfe_bus_enable_wr_if(vfe, 1);
+		vfe->ops->set_qos(vfe);
 
-		vfe_set_qos(vfe);
+		vfe->ops->set_ds(vfe);
 	}
 
 	vfe->stream_count++;
@@ -1563,7 +865,7 @@ error_get_output:
 	mutex_lock(&vfe->stream_lock);
 
 	if (vfe->stream_count == 1)
-		vfe_bus_enable_wr_if(vfe, 0);
+		vfe->ops->bus_enable_wr_if(vfe, 0);
 
 	vfe->stream_count--;
 
@@ -1589,7 +891,7 @@ static int vfe_disable(struct vfe_line *line)
 	mutex_lock(&vfe->stream_lock);
 
 	if (vfe->stream_count == 1)
-		vfe_bus_enable_wr_if(vfe, 0);
+		vfe->ops->bus_enable_wr_if(vfe, 0);
 
 	vfe->stream_count--;
 
@@ -1628,7 +930,7 @@ static void vfe_isr_reg_update(struct vfe_device *vfe, enum vfe_line_id line_id)
 	unsigned long flags;
 
 	spin_lock_irqsave(&vfe->output_lock, flags);
-	vfe->reg_update &= ~VFE_0_REG_UPDATE_line_n(line_id);
+	vfe->ops->reg_update_clear(vfe, line_id);
 
 	output = &vfe->line[line_id].output;
 
@@ -1698,19 +1000,19 @@ static void vfe_isr_wm_done(struct vfe_device *vfe, u8 wm)
 	u64 ts = ktime_get_ns();
 	unsigned int i;
 
-	active_index = vfe_wm_get_ping_pong_status(vfe, wm);
+	active_index = vfe->ops->wm_get_ping_pong_status(vfe, wm);
 
 	spin_lock_irqsave(&vfe->output_lock, flags);
 
 	if (vfe->wm_output_map[wm] == VFE_LINE_NONE) {
-		dev_err_ratelimited(to_device(vfe),
+		dev_err_ratelimited(vfe->camss->dev,
 				    "Received wm done for unmapped index\n");
 		goto out_unlock;
 	}
 	output = &vfe->line[vfe->wm_output_map[wm]].output;
 
 	if (output->active_buf == active_index) {
-		dev_err_ratelimited(to_device(vfe),
+		dev_err_ratelimited(vfe->camss->dev,
 				    "Active buffer mismatch!\n");
 		goto out_unlock;
 	}
@@ -1718,7 +1020,7 @@ static void vfe_isr_wm_done(struct vfe_device *vfe, u8 wm)
 
 	ready_buf = output->buf[!active_index];
 	if (!ready_buf) {
-		dev_err_ratelimited(to_device(vfe),
+		dev_err_ratelimited(vfe->camss->dev,
 				    "Missing ready buf %d %d!\n",
 				    !active_index, output->state);
 		goto out_unlock;
@@ -1740,12 +1042,12 @@ static void vfe_isr_wm_done(struct vfe_device *vfe, u8 wm)
 
 	if (active_index)
 		for (i = 0; i < output->wm_num; i++)
-			vfe_wm_set_ping_addr(vfe, output->wm_idx[i],
-					     new_addr[i]);
+			vfe->ops->wm_set_ping_addr(vfe, output->wm_idx[i],
+						   new_addr[i]);
 	else
 		for (i = 0; i < output->wm_num; i++)
-			vfe_wm_set_pong_addr(vfe, output->wm_idx[i],
-					     new_addr[i]);
+			vfe->ops->wm_set_pong_addr(vfe, output->wm_idx[i],
+						   new_addr[i]);
 
 	spin_unlock_irqrestore(&vfe->output_lock, flags);
 
@@ -1776,67 +1078,15 @@ static void vfe_isr_comp_done(struct vfe_device *vfe, u8 comp)
 		}
 }
 
-/*
- * vfe_isr - ISPIF module interrupt handler
- * @irq: Interrupt line
- * @dev: VFE device
- *
- * Return IRQ_HANDLED on success
- */
-static irqreturn_t vfe_isr(int irq, void *dev)
+static inline void vfe_isr_reset_ack(struct vfe_device *vfe)
 {
-	struct vfe_device *vfe = dev;
-	u32 value0, value1;
-	u32 violation;
-	int i, j;
-
-	value0 = readl_relaxed(vfe->base + VFE_0_IRQ_STATUS_0);
-	value1 = readl_relaxed(vfe->base + VFE_0_IRQ_STATUS_1);
-
-	writel_relaxed(value0, vfe->base + VFE_0_IRQ_CLEAR_0);
-	writel_relaxed(value1, vfe->base + VFE_0_IRQ_CLEAR_1);
-
-	wmb();
-	writel_relaxed(VFE_0_IRQ_CMD_GLOBAL_CLEAR, vfe->base + VFE_0_IRQ_CMD);
-
-	if (value0 & VFE_0_IRQ_STATUS_0_RESET_ACK)
-		complete(&vfe->reset_complete);
-
-	if (value1 & VFE_0_IRQ_STATUS_1_VIOLATION) {
-		violation = readl_relaxed(vfe->base + VFE_0_VIOLATION_STATUS);
-		dev_err_ratelimited(to_device(vfe),
-				    "VFE: violation = 0x%08x\n", violation);
-	}
-
-	if (value1 & VFE_0_IRQ_STATUS_1_BUS_BDG_HALT_ACK) {
-		complete(&vfe->halt_complete);
-		writel_relaxed(0x0, vfe->base + VFE_0_BUS_BDG_CMD);
-	}
-
-	for (i = VFE_LINE_RDI0; i <= VFE_LINE_PIX; i++)
-		if (value0 & VFE_0_IRQ_STATUS_0_line_n_REG_UPDATE(i))
-			vfe_isr_reg_update(vfe, i);
-
-	if (value0 & VFE_0_IRQ_STATUS_0_CAMIF_SOF)
-		vfe_isr_sof(vfe, VFE_LINE_PIX);
-
-	for (i = VFE_LINE_RDI0; i <= VFE_LINE_RDI2; i++)
-		if (value1 & VFE_0_IRQ_STATUS_1_RDIn_SOF(i))
-			vfe_isr_sof(vfe, i);
-
-	for (i = 0; i < MSM_VFE_COMPOSITE_IRQ_NUM; i++)
-		if (value0 & VFE_0_IRQ_STATUS_0_IMAGE_COMPOSITE_DONE_n(i)) {
-			vfe_isr_comp_done(vfe, i);
-			for (j = 0; j < ARRAY_SIZE(vfe->wm_output_map); j++)
-				if (vfe->wm_output_map[j] == VFE_LINE_PIX)
-					value0 &= ~VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(j);
-		}
-
-	for (i = 0; i < MSM_VFE_IMAGE_MASTERS_NUM; i++)
-		if (value0 & VFE_0_IRQ_STATUS_0_IMAGE_MASTER_n_PING_PONG(i))
-			vfe_isr_wm_done(vfe, i);
+	complete(&vfe->reset_complete);
+}
 
-	return IRQ_HANDLED;
+static inline void vfe_isr_halt_ack(struct vfe_device *vfe)
+{
+	complete(&vfe->halt_complete);
+	vfe->ops->halt_clear(vfe);
 }
 
 /*
@@ -1847,7 +1097,7 @@ static irqreturn_t vfe_isr(int irq, void *dev)
  */
 static int vfe_set_clock_rates(struct vfe_device *vfe)
 {
-	struct device *dev = to_device(vfe);
+	struct device *dev = vfe->camss->dev;
 	u32 pixel_clock[MSM_VFE_LINE_NUM];
 	int i, j;
 	int ret;
@@ -1862,7 +1112,8 @@ static int vfe_set_clock_rates(struct vfe_device *vfe)
 	for (i = 0; i < vfe->nclocks; i++) {
 		struct camss_clock *clock = &vfe->clock[i];
 
-		if (!strcmp(clock->name, "camss_vfe_vfe")) {
+		if (!strcmp(clock->name, "vfe0") ||
+		    !strcmp(clock->name, "vfe1")) {
 			u64 min_rate = 0;
 			long rate;
 
@@ -1873,8 +1124,11 @@ static int vfe_set_clock_rates(struct vfe_device *vfe)
 				if (j == VFE_LINE_PIX) {
 					tmp = pixel_clock[j];
 				} else {
-					bpp = vfe_get_bpp(vfe->line[j].
-						fmt[MSM_VFE_PAD_SINK].code);
+					struct vfe_line *l = &vfe->line[j];
+
+					bpp = vfe_get_bpp(l->formats,
+						l->nformats,
+						l->fmt[MSM_VFE_PAD_SINK].code);
 					tmp = pixel_clock[j] * bpp / 64;
 				}
 
@@ -1940,7 +1194,8 @@ static int vfe_check_clock_rates(struct vfe_device *vfe)
 	for (i = 0; i < vfe->nclocks; i++) {
 		struct camss_clock *clock = &vfe->clock[i];
 
-		if (!strcmp(clock->name, "camss_vfe_vfe")) {
+		if (!strcmp(clock->name, "vfe0") ||
+		    !strcmp(clock->name, "vfe1")) {
 			u64 min_rate = 0;
 			unsigned long rate;
 
@@ -1951,8 +1206,11 @@ static int vfe_check_clock_rates(struct vfe_device *vfe)
 				if (j == VFE_LINE_PIX) {
 					tmp = pixel_clock[j];
 				} else {
-					bpp = vfe_get_bpp(vfe->line[j].
-						fmt[MSM_VFE_PAD_SINK].code);
+					struct vfe_line *l = &vfe->line[j];
+
+					bpp = vfe_get_bpp(l->formats,
+						l->nformats,
+						l->fmt[MSM_VFE_PAD_SINK].code);
 					tmp = pixel_clock[j] * bpp / 64;
 				}
 
@@ -1984,12 +1242,20 @@ static int vfe_get(struct vfe_device *vfe)
 	mutex_lock(&vfe->power_lock);
 
 	if (vfe->power_count == 0) {
+		ret = camss_pm_domain_on(vfe->camss, vfe->id);
+		if (ret < 0)
+			goto error_pm_domain;
+
+		ret = pm_runtime_get_sync(vfe->camss->dev);
+		if (ret < 0)
+			goto error_pm_runtime_get;
+
 		ret = vfe_set_clock_rates(vfe);
 		if (ret < 0)
 			goto error_clocks;
 
 		ret = camss_enable_clocks(vfe->nclocks, vfe->clock,
-					  to_device(vfe));
+					  vfe->camss->dev);
 		if (ret < 0)
 			goto error_clocks;
 
@@ -2015,6 +1281,12 @@ error_reset:
 	camss_disable_clocks(vfe->nclocks, vfe->clock);
 
 error_clocks:
+	pm_runtime_put_sync(vfe->camss->dev);
+
+error_pm_runtime_get:
+	camss_pm_domain_off(vfe->camss, vfe->id);
+
+error_pm_domain:
 	mutex_unlock(&vfe->power_lock);
 
 	return ret;
@@ -2029,7 +1301,7 @@ static void vfe_put(struct vfe_device *vfe)
 	mutex_lock(&vfe->power_lock);
 
 	if (vfe->power_count == 0) {
-		dev_err(to_device(vfe), "vfe power off on power_count == 0\n");
+		dev_err(vfe->camss->dev, "vfe power off on power_count == 0\n");
 		goto exit;
 	} else if (vfe->power_count == 1) {
 		if (vfe->was_streaming) {
@@ -2037,6 +1309,8 @@ static void vfe_put(struct vfe_device *vfe)
 			vfe_halt(vfe);
 		}
 		camss_disable_clocks(vfe->nclocks, vfe->clock);
+		pm_runtime_put_sync(vfe->camss->dev);
+		camss_pm_domain_off(vfe->camss, vfe->id);
 	}
 
 	vfe->power_count--;
@@ -2046,26 +1320,6 @@ exit:
 }
 
 /*
- * vfe_video_pad_to_line - Get pointer to VFE line by media pad
- * @pad: Media pad
- *
- * Return pointer to vfe line structure
- */
-static struct vfe_line *vfe_video_pad_to_line(struct media_pad *pad)
-{
-	struct media_pad *vfe_pad;
-	struct v4l2_subdev *subdev;
-
-	vfe_pad = media_entity_remote_pad(pad);
-	if (vfe_pad == NULL)
-		return NULL;
-
-	subdev = media_entity_to_v4l2_subdev(vfe_pad->entity);
-
-	return container_of(subdev, struct vfe_line, subdev);
-}
-
-/*
  * vfe_queue_buffer - Add empty buffer
  * @vid: Video device structure
  * @buf: Buffer to be enqueued
@@ -2078,16 +1332,11 @@ static struct vfe_line *vfe_video_pad_to_line(struct media_pad *pad)
 static int vfe_queue_buffer(struct camss_video *vid,
 			    struct camss_buffer *buf)
 {
-	struct vfe_device *vfe = &vid->camss->vfe;
-	struct vfe_line *line;
+	struct vfe_line *line = container_of(vid, struct vfe_line, video_out);
+	struct vfe_device *vfe = to_vfe(line);
 	struct vfe_output *output;
 	unsigned long flags;
 
-	line = vfe_video_pad_to_line(&vid->pad);
-	if (!line) {
-		dev_err(to_device(vfe), "Can not queue buffer\n");
-		return -1;
-	}
 	output = &line->output;
 
 	spin_lock_irqsave(&vfe->output_lock, flags);
@@ -2112,16 +1361,11 @@ static int vfe_queue_buffer(struct camss_video *vid,
 static int vfe_flush_buffers(struct camss_video *vid,
 			     enum vb2_buffer_state state)
 {
-	struct vfe_device *vfe = &vid->camss->vfe;
-	struct vfe_line *line;
+	struct vfe_line *line = container_of(vid, struct vfe_line, video_out);
+	struct vfe_device *vfe = to_vfe(line);
 	struct vfe_output *output;
 	unsigned long flags;
 
-	line = vfe_video_pad_to_line(&vid->pad);
-	if (!line) {
-		dev_err(to_device(vfe),	"Can not flush buffers\n");
-		return -1;
-	}
 	output = &line->output;
 
 	spin_lock_irqsave(&vfe->output_lock, flags);
@@ -2158,15 +1402,11 @@ static int vfe_set_power(struct v4l2_subdev *sd, int on)
 	int ret;
 
 	if (on) {
-		u32 hw_version;
-
 		ret = vfe_get(vfe);
 		if (ret < 0)
 			return ret;
 
-		hw_version = readl_relaxed(vfe->base + VFE_0_HW_VERSION);
-		dev_dbg(to_device(vfe),
-			"VFE HW Version = 0x%08x\n", hw_version);
+		vfe->ops->hw_version_read(vfe, vfe->camss->dev);
 	} else {
 		vfe_put(vfe);
 	}
@@ -2192,12 +1432,12 @@ static int vfe_set_stream(struct v4l2_subdev *sd, int enable)
 	if (enable) {
 		ret = vfe_enable(line);
 		if (ret < 0)
-			dev_err(to_device(vfe),
+			dev_err(vfe->camss->dev,
 				"Failed to enable vfe outputs\n");
 	} else {
 		ret = vfe_disable(line);
 		if (ret < 0)
-			dev_err(to_device(vfe),
+			dev_err(vfe->camss->dev,
 				"Failed to disable vfe outputs\n");
 	}
 
@@ -2286,12 +1526,12 @@ static void vfe_try_format(struct vfe_line *line,
 	case MSM_VFE_PAD_SINK:
 		/* Set format on sink pad */
 
-		for (i = 0; i < ARRAY_SIZE(vfe_formats); i++)
-			if (fmt->code == vfe_formats[i].code)
+		for (i = 0; i < line->nformats; i++)
+			if (fmt->code == line->formats[i].code)
 				break;
 
 		/* If not found, use UYVY as default */
-		if (i >= ARRAY_SIZE(vfe_formats))
+		if (i >= line->nformats)
 			fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
 
 		fmt->width = clamp_t(u32, fmt->width, 1, 8191);
@@ -2304,11 +1544,11 @@ static void vfe_try_format(struct vfe_line *line,
 
 	case MSM_VFE_PAD_SRC:
 		/* Set and return a format same as sink pad */
-
 		code = fmt->code;
 
-		*fmt = *__vfe_get_format(line, cfg, MSM_VFE_PAD_SINK,
-					 which);
+		*fmt = *__vfe_get_format(line, cfg, MSM_VFE_PAD_SINK, which);
+
+		fmt->code = vfe_src_pad_code(line, fmt->code, 0, code);
 
 		if (line->id == VFE_LINE_PIX) {
 			struct v4l2_rect *rect;
@@ -2317,34 +1557,6 @@ static void vfe_try_format(struct vfe_line *line,
 
 			fmt->width = rect->width;
 			fmt->height = rect->height;
-
-			switch (fmt->code) {
-			case MEDIA_BUS_FMT_YUYV8_2X8:
-				if (code == MEDIA_BUS_FMT_YUYV8_1_5X8)
-					fmt->code = MEDIA_BUS_FMT_YUYV8_1_5X8;
-				else
-					fmt->code = MEDIA_BUS_FMT_YUYV8_2X8;
-				break;
-			case MEDIA_BUS_FMT_YVYU8_2X8:
-				if (code == MEDIA_BUS_FMT_YVYU8_1_5X8)
-					fmt->code = MEDIA_BUS_FMT_YVYU8_1_5X8;
-				else
-					fmt->code = MEDIA_BUS_FMT_YVYU8_2X8;
-				break;
-			case MEDIA_BUS_FMT_UYVY8_2X8:
-			default:
-				if (code == MEDIA_BUS_FMT_UYVY8_1_5X8)
-					fmt->code = MEDIA_BUS_FMT_UYVY8_1_5X8;
-				else
-					fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
-				break;
-			case MEDIA_BUS_FMT_VYUY8_2X8:
-				if (code == MEDIA_BUS_FMT_VYUY8_1_5X8)
-					fmt->code = MEDIA_BUS_FMT_VYUY8_1_5X8;
-				else
-					fmt->code = MEDIA_BUS_FMT_VYUY8_2X8;
-				break;
-			}
 		}
 
 		break;
@@ -2448,21 +1660,22 @@ static int vfe_enum_mbus_code(struct v4l2_subdev *sd,
 			      struct v4l2_subdev_mbus_code_enum *code)
 {
 	struct vfe_line *line = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt *format;
 
 	if (code->pad == MSM_VFE_PAD_SINK) {
-		if (code->index >= ARRAY_SIZE(vfe_formats))
+		if (code->index >= line->nformats)
 			return -EINVAL;
 
-		code->code = vfe_formats[code->index].code;
+		code->code = line->formats[code->index].code;
 	} else {
-		if (code->index > 0)
-			return -EINVAL;
+		struct v4l2_mbus_framefmt *sink_fmt;
 
-		format = __vfe_get_format(line, cfg, MSM_VFE_PAD_SINK,
-					  code->which);
+		sink_fmt = __vfe_get_format(line, cfg, MSM_VFE_PAD_SINK,
+					    code->which);
 
-		code->code = format->code;
+		code->code = vfe_src_pad_code(line, sink_fmt->code,
+					      code->index, 0);
+		if (!code->code)
+			return -EINVAL;
 	}
 
 	return 0;
@@ -2751,15 +1964,29 @@ static int vfe_init_formats(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
  *
  * Return 0 on success or a negative error code otherwise
  */
-int msm_vfe_subdev_init(struct vfe_device *vfe, const struct resources *res)
+int msm_vfe_subdev_init(struct camss *camss, struct vfe_device *vfe,
+			const struct resources *res, u8 id)
 {
-	struct device *dev = to_device(vfe);
+	struct device *dev = camss->dev;
 	struct platform_device *pdev = to_platform_device(dev);
 	struct resource *r;
-	struct camss *camss = to_camss(vfe);
 	int i, j;
 	int ret;
 
+	vfe->isr_ops.reset_ack = vfe_isr_reset_ack;
+	vfe->isr_ops.halt_ack = vfe_isr_halt_ack;
+	vfe->isr_ops.reg_update = vfe_isr_reg_update;
+	vfe->isr_ops.sof = vfe_isr_sof;
+	vfe->isr_ops.comp_done = vfe_isr_comp_done;
+	vfe->isr_ops.wm_done = vfe_isr_wm_done;
+
+	if (camss->version == CAMSS_8x16)
+		vfe->ops = &vfe_ops_4_1;
+	else if (camss->version == CAMSS_8x96)
+		vfe->ops = &vfe_ops_4_7;
+	else
+		return -EINVAL;
+
 	/* Memory */
 
 	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[0]);
@@ -2781,7 +2008,7 @@ int msm_vfe_subdev_init(struct vfe_device *vfe, const struct resources *res)
 	vfe->irq = r->start;
 	snprintf(vfe->irq_name, sizeof(vfe->irq_name), "%s_%s%d",
 		 dev_name(dev), MSM_VFE_NAME, vfe->id);
-	ret = devm_request_irq(dev, vfe->irq, vfe_isr,
+	ret = devm_request_irq(dev, vfe->irq, vfe->ops->isr,
 			       IRQF_TRIGGER_RISING, vfe->irq_name, vfe);
 	if (ret < 0) {
 		dev_err(dev, "request_irq failed: %d\n", ret);
@@ -2836,16 +2063,38 @@ int msm_vfe_subdev_init(struct vfe_device *vfe, const struct resources *res)
 
 	spin_lock_init(&vfe->output_lock);
 
-	vfe->id = 0;
+	vfe->camss = camss;
+	vfe->id = id;
 	vfe->reg_update = 0;
 
 	for (i = VFE_LINE_RDI0; i <= VFE_LINE_PIX; i++) {
-		vfe->line[i].video_out.type =
-					V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
-		vfe->line[i].video_out.camss = camss;
-		vfe->line[i].id = i;
-		init_completion(&vfe->line[i].output.sof);
-		init_completion(&vfe->line[i].output.reg_update);
+		struct vfe_line *l = &vfe->line[i];
+
+		l->video_out.type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
+		l->video_out.camss = camss;
+		l->id = i;
+		init_completion(&l->output.sof);
+		init_completion(&l->output.reg_update);
+
+		if (camss->version == CAMSS_8x16) {
+			if (i == VFE_LINE_PIX) {
+				l->formats = formats_pix_8x16;
+				l->nformats = ARRAY_SIZE(formats_pix_8x16);
+			} else {
+				l->formats = formats_rdi_8x16;
+				l->nformats = ARRAY_SIZE(formats_rdi_8x16);
+			}
+		} else if (camss->version == CAMSS_8x96) {
+			if (i == VFE_LINE_PIX) {
+				l->formats = formats_pix_8x96;
+				l->nformats = ARRAY_SIZE(formats_pix_8x96);
+			} else {
+				l->formats = formats_rdi_8x96;
+				l->nformats = ARRAY_SIZE(formats_rdi_8x96);
+			}
+		} else {
+			return -EINVAL;
+		}
 	}
 
 	init_completion(&vfe->reset_complete);
@@ -2968,7 +2217,7 @@ void msm_vfe_stop_streaming(struct vfe_device *vfe)
 int msm_vfe_register_entities(struct vfe_device *vfe,
 			      struct v4l2_device *v4l2_dev)
 {
-	struct device *dev = to_device(vfe);
+	struct device *dev = vfe->camss->dev;
 	struct v4l2_subdev *sd;
 	struct media_pad *pads;
 	struct camss_video *video_out;
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.h b/drivers/media/platform/qcom/camss/camss-vfe.h
new file mode 100644
index 000000000000..0d10071ae881
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss-vfe.h
@@ -0,0 +1,186 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * camss-vfe.h
+ *
+ * Qualcomm MSM Camera Subsystem - VFE (Video Front End) Module
+ *
+ * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2015-2018 Linaro Ltd.
+ */
+#ifndef QC_MSM_CAMSS_VFE_H
+#define QC_MSM_CAMSS_VFE_H
+
+#include <linux/clk.h>
+#include <linux/spinlock_types.h>
+#include <media/media-entity.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-subdev.h>
+
+#include "camss-video.h"
+
+#define MSM_VFE_PAD_SINK 0
+#define MSM_VFE_PAD_SRC 1
+#define MSM_VFE_PADS_NUM 2
+
+#define MSM_VFE_LINE_NUM 4
+#define MSM_VFE_IMAGE_MASTERS_NUM 7
+#define MSM_VFE_COMPOSITE_IRQ_NUM 4
+
+enum vfe_output_state {
+	VFE_OUTPUT_OFF,
+	VFE_OUTPUT_RESERVED,
+	VFE_OUTPUT_SINGLE,
+	VFE_OUTPUT_CONTINUOUS,
+	VFE_OUTPUT_IDLE,
+	VFE_OUTPUT_STOPPING
+};
+
+enum vfe_line_id {
+	VFE_LINE_NONE = -1,
+	VFE_LINE_RDI0 = 0,
+	VFE_LINE_RDI1 = 1,
+	VFE_LINE_RDI2 = 2,
+	VFE_LINE_PIX = 3
+};
+
+struct vfe_output {
+	u8 wm_num;
+	u8 wm_idx[3];
+
+	int active_buf;
+	struct camss_buffer *buf[2];
+	struct camss_buffer *last_buffer;
+	struct list_head pending_bufs;
+
+	unsigned int drop_update_idx;
+
+	enum vfe_output_state state;
+	unsigned int sequence;
+	int wait_sof;
+	int wait_reg_update;
+	struct completion sof;
+	struct completion reg_update;
+};
+
+struct vfe_line {
+	enum vfe_line_id id;
+	struct v4l2_subdev subdev;
+	struct media_pad pads[MSM_VFE_PADS_NUM];
+	struct v4l2_mbus_framefmt fmt[MSM_VFE_PADS_NUM];
+	struct v4l2_rect compose;
+	struct v4l2_rect crop;
+	struct camss_video video_out;
+	struct vfe_output output;
+	const struct vfe_format *formats;
+	unsigned int nformats;
+};
+
+struct vfe_device;
+
+struct vfe_hw_ops {
+	void (*hw_version_read)(struct vfe_device *vfe, struct device *dev);
+	u16 (*get_ub_size)(u8 vfe_id);
+	void (*global_reset)(struct vfe_device *vfe);
+	void (*halt_request)(struct vfe_device *vfe);
+	void (*halt_clear)(struct vfe_device *vfe);
+	void (*wm_enable)(struct vfe_device *vfe, u8 wm, u8 enable);
+	void (*wm_frame_based)(struct vfe_device *vfe, u8 wm, u8 enable);
+	void (*wm_line_based)(struct vfe_device *vfe, u32 wm,
+			      struct v4l2_pix_format_mplane *pix,
+			      u8 plane, u32 enable);
+	void (*wm_set_framedrop_period)(struct vfe_device *vfe, u8 wm, u8 per);
+	void (*wm_set_framedrop_pattern)(struct vfe_device *vfe, u8 wm,
+					 u32 pattern);
+	void (*wm_set_ub_cfg)(struct vfe_device *vfe, u8 wm, u16 offset,
+			      u16 depth);
+	void (*bus_reload_wm)(struct vfe_device *vfe, u8 wm);
+	void (*wm_set_ping_addr)(struct vfe_device *vfe, u8 wm, u32 addr);
+	void (*wm_set_pong_addr)(struct vfe_device *vfe, u8 wm, u32 addr);
+	int (*wm_get_ping_pong_status)(struct vfe_device *vfe, u8 wm);
+	void (*bus_enable_wr_if)(struct vfe_device *vfe, u8 enable);
+	void (*bus_connect_wm_to_rdi)(struct vfe_device *vfe, u8 wm,
+				      enum vfe_line_id id);
+	void (*wm_set_subsample)(struct vfe_device *vfe, u8 wm);
+	void (*bus_disconnect_wm_from_rdi)(struct vfe_device *vfe, u8 wm,
+					   enum vfe_line_id id);
+	void (*set_xbar_cfg)(struct vfe_device *vfe, struct vfe_output *output,
+			     u8 enable);
+	void (*set_rdi_cid)(struct vfe_device *vfe, enum vfe_line_id id,
+			    u8 cid);
+	void (*set_realign_cfg)(struct vfe_device *vfe, struct vfe_line *line,
+				u8 enable);
+	void (*reg_update)(struct vfe_device *vfe, enum vfe_line_id line_id);
+	void (*reg_update_clear)(struct vfe_device *vfe,
+				 enum vfe_line_id line_id);
+	void (*enable_irq_wm_line)(struct vfe_device *vfe, u8 wm,
+				   enum vfe_line_id line_id, u8 enable);
+	void (*enable_irq_pix_line)(struct vfe_device *vfe, u8 comp,
+				    enum vfe_line_id line_id, u8 enable);
+	void (*enable_irq_common)(struct vfe_device *vfe);
+	void (*set_demux_cfg)(struct vfe_device *vfe, struct vfe_line *line);
+	void (*set_scale_cfg)(struct vfe_device *vfe, struct vfe_line *line);
+	void (*set_crop_cfg)(struct vfe_device *vfe, struct vfe_line *line);
+	void (*set_clamp_cfg)(struct vfe_device *vfe);
+	void (*set_qos)(struct vfe_device *vfe);
+	void (*set_ds)(struct vfe_device *vfe);
+	void (*set_cgc_override)(struct vfe_device *vfe, u8 wm, u8 enable);
+	void (*set_camif_cfg)(struct vfe_device *vfe, struct vfe_line *line);
+	void (*set_camif_cmd)(struct vfe_device *vfe, u8 enable);
+	void (*set_module_cfg)(struct vfe_device *vfe, u8 enable);
+	int (*camif_wait_for_stop)(struct vfe_device *vfe, struct device *dev);
+	void (*isr_read)(struct vfe_device *vfe, u32 *value0, u32 *value1);
+	void (*violation_read)(struct vfe_device *vfe);
+	irqreturn_t (*isr)(int irq, void *dev);
+};
+
+struct vfe_isr_ops {
+	void (*reset_ack)(struct vfe_device *vfe);
+	void (*halt_ack)(struct vfe_device *vfe);
+	void (*reg_update)(struct vfe_device *vfe, enum vfe_line_id line_id);
+	void (*sof)(struct vfe_device *vfe, enum vfe_line_id line_id);
+	void (*comp_done)(struct vfe_device *vfe, u8 comp);
+	void (*wm_done)(struct vfe_device *vfe, u8 wm);
+};
+
+struct vfe_device {
+	struct camss *camss;
+	u8 id;
+	void __iomem *base;
+	u32 irq;
+	char irq_name[30];
+	struct camss_clock *clock;
+	int nclocks;
+	struct completion reset_complete;
+	struct completion halt_complete;
+	struct mutex power_lock;
+	int power_count;
+	struct mutex stream_lock;
+	int stream_count;
+	spinlock_t output_lock;
+	enum vfe_line_id wm_output_map[MSM_VFE_IMAGE_MASTERS_NUM];
+	struct vfe_line line[MSM_VFE_LINE_NUM];
+	u32 reg_update;
+	u8 was_streaming;
+	const struct vfe_hw_ops *ops;
+	struct vfe_isr_ops isr_ops;
+};
+
+struct resources;
+
+int msm_vfe_subdev_init(struct camss *camss, struct vfe_device *vfe,
+			const struct resources *res, u8 id);
+
+int msm_vfe_register_entities(struct vfe_device *vfe,
+			      struct v4l2_device *v4l2_dev);
+
+void msm_vfe_unregister_entities(struct vfe_device *vfe);
+
+void msm_vfe_get_vfe_id(struct media_entity *entity, u8 *id);
+void msm_vfe_get_vfe_line_id(struct media_entity *entity, enum vfe_line_id *id);
+
+void msm_vfe_stop_streaming(struct vfe_device *vfe);
+
+extern const struct vfe_hw_ops vfe_ops_4_1;
+extern const struct vfe_hw_ops vfe_ops_4_7;
+
+#endif /* QC_MSM_CAMSS_VFE_H */
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-video.c b/drivers/media/platform/qcom/camss/camss-video.c
index ffaa2849e0c1..c9bb0d023db4 100644
--- a/drivers/media/platform/qcom/camss-8x16/camss-video.c
+++ b/drivers/media/platform/qcom/camss/camss-video.c
@@ -1,19 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * camss-video.c
  *
  * Qualcomm MSM Camera Subsystem - V4L2 device node
  *
  * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ * Copyright (C) 2015-2018 Linaro Ltd.
  */
 #include <linux/slab.h>
 #include <media/media-entity.h>
@@ -49,7 +41,7 @@ struct camss_format_info {
 	unsigned int bpp[3];
 };
 
-static const struct camss_format_info formats_rdi[] = {
+static const struct camss_format_info formats_rdi_8x16[] = {
 	{ MEDIA_BUS_FMT_UYVY8_2X8, V4L2_PIX_FMT_UYVY, 1,
 	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
 	{ MEDIA_BUS_FMT_VYUY8_2X8, V4L2_PIX_FMT_VYUY, 1,
@@ -82,9 +74,60 @@ static const struct camss_format_info formats_rdi[] = {
 	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
 	{ MEDIA_BUS_FMT_SRGGB12_1X12, V4L2_PIX_FMT_SRGGB12P, 1,
 	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
+	{ MEDIA_BUS_FMT_Y10_1X10, V4L2_PIX_FMT_Y10P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
 };
 
-static const struct camss_format_info formats_pix[] = {
+static const struct camss_format_info formats_rdi_8x96[] = {
+	{ MEDIA_BUS_FMT_UYVY8_2X8, V4L2_PIX_FMT_UYVY, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, V4L2_PIX_FMT_VYUY, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, V4L2_PIX_FMT_YUYV, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, V4L2_PIX_FMT_YVYU, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+	{ MEDIA_BUS_FMT_SBGGR8_1X8, V4L2_PIX_FMT_SBGGR8, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 8 } },
+	{ MEDIA_BUS_FMT_SGBRG8_1X8, V4L2_PIX_FMT_SGBRG8, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 8 } },
+	{ MEDIA_BUS_FMT_SGRBG8_1X8, V4L2_PIX_FMT_SGRBG8, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 8 } },
+	{ MEDIA_BUS_FMT_SRGGB8_1X8, V4L2_PIX_FMT_SRGGB8, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 8 } },
+	{ MEDIA_BUS_FMT_SBGGR10_1X10, V4L2_PIX_FMT_SBGGR10P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
+	{ MEDIA_BUS_FMT_SGBRG10_1X10, V4L2_PIX_FMT_SGBRG10P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
+	{ MEDIA_BUS_FMT_SGRBG10_1X10, V4L2_PIX_FMT_SGRBG10P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
+	{ MEDIA_BUS_FMT_SRGGB10_1X10, V4L2_PIX_FMT_SRGGB10P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
+	{ MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE, V4L2_PIX_FMT_SBGGR10, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+	{ MEDIA_BUS_FMT_SBGGR12_1X12, V4L2_PIX_FMT_SBGGR12P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
+	{ MEDIA_BUS_FMT_SGBRG12_1X12, V4L2_PIX_FMT_SGBRG12P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
+	{ MEDIA_BUS_FMT_SGRBG12_1X12, V4L2_PIX_FMT_SGRBG12P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
+	{ MEDIA_BUS_FMT_SRGGB12_1X12, V4L2_PIX_FMT_SRGGB12P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
+	{ MEDIA_BUS_FMT_SBGGR14_1X14, V4L2_PIX_FMT_SBGGR14P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 14 } },
+	{ MEDIA_BUS_FMT_SGBRG14_1X14, V4L2_PIX_FMT_SGBRG14P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 14 } },
+	{ MEDIA_BUS_FMT_SGRBG14_1X14, V4L2_PIX_FMT_SGRBG14P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 14 } },
+	{ MEDIA_BUS_FMT_SRGGB14_1X14, V4L2_PIX_FMT_SRGGB14P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 14 } },
+	{ MEDIA_BUS_FMT_Y10_1X10, V4L2_PIX_FMT_Y10P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
+	{ MEDIA_BUS_FMT_Y10_2X8_PADHI_LE, V4L2_PIX_FMT_Y10, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+};
+
+static const struct camss_format_info formats_pix_8x16[] = {
 	{ MEDIA_BUS_FMT_YUYV8_1_5X8, V4L2_PIX_FMT_NV12, 1,
 	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
 	{ MEDIA_BUS_FMT_YVYU8_1_5X8, V4L2_PIX_FMT_NV12, 1,
@@ -119,6 +162,49 @@ static const struct camss_format_info formats_pix[] = {
 	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
 };
 
+static const struct camss_format_info formats_pix_8x96[] = {
+	{ MEDIA_BUS_FMT_YUYV8_1_5X8, V4L2_PIX_FMT_NV12, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YVYU8_1_5X8, V4L2_PIX_FMT_NV12, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_UYVY8_1_5X8, V4L2_PIX_FMT_NV12, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_VYUY8_1_5X8, V4L2_PIX_FMT_NV12, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YUYV8_1_5X8, V4L2_PIX_FMT_NV21, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YVYU8_1_5X8, V4L2_PIX_FMT_NV21, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_UYVY8_1_5X8, V4L2_PIX_FMT_NV21, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_VYUY8_1_5X8, V4L2_PIX_FMT_NV21, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, V4L2_PIX_FMT_NV16, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, V4L2_PIX_FMT_NV16, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_UYVY8_2X8, V4L2_PIX_FMT_NV16, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, V4L2_PIX_FMT_NV16, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, V4L2_PIX_FMT_NV61, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, V4L2_PIX_FMT_NV61, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_UYVY8_2X8, V4L2_PIX_FMT_NV61, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, V4L2_PIX_FMT_NV61, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_UYVY8_2X8, V4L2_PIX_FMT_UYVY, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, V4L2_PIX_FMT_VYUY, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, V4L2_PIX_FMT_YUYV, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, V4L2_PIX_FMT_YVYU, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+};
+
 /* -----------------------------------------------------------------------------
  * Helper functions
  */
@@ -798,11 +884,24 @@ int msm_video_register(struct camss_video *video, struct v4l2_device *v4l2_dev,
 
 	mutex_init(&video->lock);
 
-	video->formats = formats_rdi;
-	video->nformats = ARRAY_SIZE(formats_rdi);
-	if (is_pix) {
-		video->formats = formats_pix;
-		video->nformats = ARRAY_SIZE(formats_pix);
+	if (video->camss->version == CAMSS_8x16) {
+		if (is_pix) {
+			video->formats = formats_pix_8x16;
+			video->nformats = ARRAY_SIZE(formats_pix_8x16);
+		} else {
+			video->formats = formats_rdi_8x16;
+			video->nformats = ARRAY_SIZE(formats_rdi_8x16);
+		}
+	} else if (video->camss->version == CAMSS_8x96) {
+		if (is_pix) {
+			video->formats = formats_pix_8x96;
+			video->nformats = ARRAY_SIZE(formats_pix_8x96);
+		} else {
+			video->formats = formats_rdi_8x96;
+			video->nformats = ARRAY_SIZE(formats_rdi_8x96);
+		}
+	} else {
+		goto error_video_register;
 	}
 
 	ret = msm_video_init_format(video);
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-video.h b/drivers/media/platform/qcom/camss/camss-video.h
index 38bd1f2eec54..aa35e8cc6fd5 100644
--- a/drivers/media/platform/qcom/camss-8x16/camss-video.h
+++ b/drivers/media/platform/qcom/camss/camss-video.h
@@ -1,19 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * camss-video.h
  *
  * Qualcomm MSM Camera Subsystem - V4L2 device node
  *
  * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ * Copyright (C) 2015-2018 Linaro Ltd.
  */
 #ifndef QC_MSM_CAMSS_VIDEO_H
 #define QC_MSM_CAMSS_VIDEO_H
diff --git a/drivers/media/platform/qcom/camss-8x16/camss.c b/drivers/media/platform/qcom/camss/camss.c
index 23fda6207a23..dcc0c30ef1b1 100644
--- a/drivers/media/platform/qcom/camss-8x16/camss.c
+++ b/drivers/media/platform/qcom/camss/camss.c
@@ -1,19 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * camss.c
  *
  * Qualcomm MSM Camera Subsystem - Core
  *
  * Copyright (c) 2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ * Copyright (C) 2015-2018 Linaro Ltd.
  */
 #include <linux/clk.h>
 #include <linux/media-bus-format.h>
@@ -22,6 +14,8 @@
 #include <linux/platform_device.h>
 #include <linux/of.h>
 #include <linux/of_graph.h>
+#include <linux/pm_runtime.h>
+#include <linux/pm_domain.h>
 #include <linux/slab.h>
 #include <linux/videodev2.h>
 
@@ -36,12 +30,11 @@
 #define CAMSS_CLOCK_MARGIN_NUMERATOR 105
 #define CAMSS_CLOCK_MARGIN_DENOMINATOR 100
 
-static const struct resources csiphy_res[] = {
+static const struct resources csiphy_res_8x16[] = {
 	/* CSIPHY0 */
 	{
 		.regulator = { NULL },
-		.clock = { "camss_top_ahb", "ispif_ahb",
-			   "camss_ahb", "csiphy0_timer" },
+		.clock = { "top_ahb", "ispif_ahb", "ahb", "csiphy0_timer" },
 		.clock_rate = { { 0 },
 				{ 0 },
 				{ 0 },
@@ -53,8 +46,7 @@ static const struct resources csiphy_res[] = {
 	/* CSIPHY1 */
 	{
 		.regulator = { NULL },
-		.clock = { "camss_top_ahb", "ispif_ahb",
-			   "camss_ahb", "csiphy1_timer" },
+		.clock = { "top_ahb", "ispif_ahb", "ahb", "csiphy1_timer" },
 		.clock_rate = { { 0 },
 				{ 0 },
 				{ 0 },
@@ -64,12 +56,11 @@ static const struct resources csiphy_res[] = {
 	}
 };
 
-static const struct resources csid_res[] = {
+static const struct resources csid_res_8x16[] = {
 	/* CSID0 */
 	{
 		.regulator = { "vdda" },
-		.clock = { "camss_top_ahb", "ispif_ahb",
-			   "csi0_ahb", "camss_ahb",
+		.clock = { "top_ahb", "ispif_ahb", "csi0_ahb", "ahb",
 			   "csi0", "csi0_phy", "csi0_pix", "csi0_rdi" },
 		.clock_rate = { { 0 },
 				{ 0 },
@@ -86,8 +77,7 @@ static const struct resources csid_res[] = {
 	/* CSID1 */
 	{
 		.regulator = { "vdda" },
-		.clock = { "camss_top_ahb", "ispif_ahb",
-			   "csi1_ahb", "camss_ahb",
+		.clock = { "top_ahb", "ispif_ahb", "csi1_ahb", "ahb",
 			   "csi1", "csi1_phy", "csi1_pix", "csi1_rdi" },
 		.clock_rate = { { 0 },
 				{ 0 },
@@ -102,35 +92,195 @@ static const struct resources csid_res[] = {
 	},
 };
 
-static const struct resources_ispif ispif_res = {
+static const struct resources_ispif ispif_res_8x16 = {
 	/* ISPIF */
-	.clock = { "camss_top_ahb", "camss_ahb", "ispif_ahb",
+	.clock = { "top_ahb", "ahb", "ispif_ahb",
 		   "csi0", "csi0_pix", "csi0_rdi",
 		   "csi1", "csi1_pix", "csi1_rdi" },
-	.clock_for_reset = { "camss_vfe_vfe", "camss_csi_vfe" },
+	.clock_for_reset = { "vfe0", "csi_vfe0" },
 	.reg = { "ispif", "csi_clk_mux" },
 	.interrupt = "ispif"
 
 };
 
-static const struct resources vfe_res = {
+static const struct resources vfe_res_8x16[] = {
+	/* VFE0 */
+	{
+		.regulator = { NULL },
+		.clock = { "top_ahb", "vfe0", "csi_vfe0",
+			   "vfe_ahb", "vfe_axi", "ahb" },
+		.clock_rate = { { 0 },
+				{ 50000000, 80000000, 100000000, 160000000,
+				  177780000, 200000000, 266670000, 320000000,
+				  400000000, 465000000 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 } },
+		.reg = { "vfe0" },
+		.interrupt = { "vfe0" }
+	}
+};
+
+static const struct resources csiphy_res_8x96[] = {
+	/* CSIPHY0 */
+	{
+		.regulator = { NULL },
+		.clock = { "top_ahb", "ispif_ahb", "ahb", "csiphy0_timer" },
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 0 },
+				{ 100000000, 200000000, 266666667 } },
+		.reg = { "csiphy0", "csiphy0_clk_mux" },
+		.interrupt = { "csiphy0" }
+	},
+
+	/* CSIPHY1 */
+	{
+		.regulator = { NULL },
+		.clock = { "top_ahb", "ispif_ahb", "ahb", "csiphy1_timer" },
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 0 },
+				{ 100000000, 200000000, 266666667 } },
+		.reg = { "csiphy1", "csiphy1_clk_mux" },
+		.interrupt = { "csiphy1" }
+	},
+
+	/* CSIPHY2 */
+	{
+		.regulator = { NULL },
+		.clock = { "top_ahb", "ispif_ahb", "ahb", "csiphy2_timer" },
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 0 },
+				{ 100000000, 200000000, 266666667 } },
+		.reg = { "csiphy2", "csiphy2_clk_mux" },
+		.interrupt = { "csiphy2" }
+	}
+};
+
+static const struct resources csid_res_8x96[] = {
+	/* CSID0 */
+	{
+		.regulator = { "vdda" },
+		.clock = { "top_ahb", "ispif_ahb", "csi0_ahb", "ahb",
+			   "csi0", "csi0_phy", "csi0_pix", "csi0_rdi" },
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 100000000, 200000000, 266666667 },
+				{ 0 },
+				{ 0 },
+				{ 0 } },
+		.reg = { "csid0" },
+		.interrupt = { "csid0" }
+	},
+
+	/* CSID1 */
+	{
+		.regulator = { "vdda" },
+		.clock = { "top_ahb", "ispif_ahb", "csi1_ahb", "ahb",
+			   "csi1", "csi1_phy", "csi1_pix", "csi1_rdi" },
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 100000000, 200000000, 266666667 },
+				{ 0 },
+				{ 0 },
+				{ 0 } },
+		.reg = { "csid1" },
+		.interrupt = { "csid1" }
+	},
+
+	/* CSID2 */
+	{
+		.regulator = { "vdda" },
+		.clock = { "top_ahb", "ispif_ahb", "csi2_ahb", "ahb",
+			   "csi2", "csi2_phy", "csi2_pix", "csi2_rdi" },
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 100000000, 200000000, 266666667 },
+				{ 0 },
+				{ 0 },
+				{ 0 } },
+		.reg = { "csid2" },
+		.interrupt = { "csid2" }
+	},
+
+	/* CSID3 */
+	{
+		.regulator = { "vdda" },
+		.clock = { "top_ahb", "ispif_ahb", "csi3_ahb", "ahb",
+			   "csi3", "csi3_phy", "csi3_pix", "csi3_rdi" },
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 100000000, 200000000, 266666667 },
+				{ 0 },
+				{ 0 },
+				{ 0 } },
+		.reg = { "csid3" },
+		.interrupt = { "csid3" }
+	}
+};
+
+static const struct resources_ispif ispif_res_8x96 = {
+	/* ISPIF */
+	.clock = { "top_ahb", "ahb", "ispif_ahb",
+		   "csi0", "csi0_pix", "csi0_rdi",
+		   "csi1", "csi1_pix", "csi1_rdi",
+		   "csi2", "csi2_pix", "csi2_rdi",
+		   "csi3", "csi3_pix", "csi3_rdi" },
+	.clock_for_reset = { "vfe0", "csi_vfe0", "vfe1", "csi_vfe1" },
+	.reg = { "ispif", "csi_clk_mux" },
+	.interrupt = "ispif"
+};
+
+static const struct resources vfe_res_8x96[] = {
 	/* VFE0 */
-	.regulator = { NULL },
-	.clock = { "camss_top_ahb", "camss_vfe_vfe", "camss_csi_vfe",
-		   "iface", "bus", "camss_ahb" },
-	.clock_rate = { { 0 },
-			{ 50000000, 80000000, 100000000, 160000000,
-			  177780000, 200000000, 266670000, 320000000,
-			  400000000, 465000000 },
-			{ 0 },
-			{ 0 },
-			{ 0 },
-			{ 0 },
-			{ 0 },
-			{ 0 },
-			{ 0 } },
-	.reg = { "vfe0" },
-	.interrupt = { "vfe0" }
+	{
+		.regulator = { NULL },
+		.clock = { "top_ahb", "ahb", "vfe0", "csi_vfe0", "vfe_ahb",
+			   "vfe0_ahb", "vfe_axi", "vfe0_stream"},
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 75000000, 100000000, 300000000,
+				  320000000, 480000000, 600000000 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 } },
+		.reg = { "vfe0" },
+		.interrupt = { "vfe0" }
+	},
+
+	/* VFE1 */
+	{
+		.regulator = { NULL },
+		.clock = { "top_ahb", "ahb", "vfe1", "csi_vfe1", "vfe_ahb",
+			   "vfe1_ahb", "vfe_axi", "vfe1_stream"},
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 75000000, 100000000, 300000000,
+				  320000000, 480000000, 600000000 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 } },
+		.reg = { "vfe1" },
+		.interrupt = { "vfe1" }
+	}
 };
 
 /*
@@ -245,6 +395,26 @@ int camss_get_pixel_clock(struct media_entity *entity, u32 *pixel_clock)
 	return 0;
 }
 
+int camss_pm_domain_on(struct camss *camss, int id)
+{
+	if (camss->version == CAMSS_8x96) {
+		camss->genpd_link[id] = device_link_add(camss->dev,
+				camss->genpd[id], DL_FLAG_STATELESS |
+				DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE);
+
+		if (!camss->genpd_link[id])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+void camss_pm_domain_off(struct camss *camss, int id)
+{
+	if (camss->version == CAMSS_8x96)
+		device_link_del(camss->genpd_link[id]);
+}
+
 /*
  * camss_of_parse_endpoint_node - Parse port endpoint node
  * @dev: Device
@@ -304,6 +474,7 @@ static int camss_of_parse_ports(struct device *dev,
 		if (of_device_is_available(node))
 			notifier->num_subdevs++;
 
+	of_node_put(node);
 	size = sizeof(*notifier->subdevs) * notifier->num_subdevs;
 	notifier->subdevs = devm_kzalloc(dev, size, GFP_KERNEL);
 	if (!notifier->subdevs) {
@@ -334,16 +505,16 @@ static int camss_of_parse_ports(struct device *dev,
 		}
 
 		remote = of_graph_get_remote_port_parent(node);
-		of_node_put(node);
-
 		if (!remote) {
 			dev_err(dev, "Cannot get remote parent\n");
+			of_node_put(node);
 			return -EINVAL;
 		}
 
 		csd->asd.match_type = V4L2_ASYNC_MATCH_FWNODE;
 		csd->asd.match.fwnode = of_fwnode_handle(remote);
 	}
+	of_node_put(node);
 
 	return notifier->num_subdevs;
 }
@@ -356,11 +527,29 @@ static int camss_of_parse_ports(struct device *dev,
  */
 static int camss_init_subdevices(struct camss *camss)
 {
+	const struct resources *csiphy_res;
+	const struct resources *csid_res;
+	const struct resources_ispif *ispif_res;
+	const struct resources *vfe_res;
 	unsigned int i;
 	int ret;
 
-	for (i = 0; i < ARRAY_SIZE(camss->csiphy); i++) {
-		ret = msm_csiphy_subdev_init(&camss->csiphy[i],
+	if (camss->version == CAMSS_8x16) {
+		csiphy_res = csiphy_res_8x16;
+		csid_res = csid_res_8x16;
+		ispif_res = &ispif_res_8x16;
+		vfe_res = vfe_res_8x16;
+	} else if (camss->version == CAMSS_8x96) {
+		csiphy_res = csiphy_res_8x96;
+		csid_res = csid_res_8x96;
+		ispif_res = &ispif_res_8x96;
+		vfe_res = vfe_res_8x96;
+	} else {
+		return -EINVAL;
+	}
+
+	for (i = 0; i < camss->csiphy_num; i++) {
+		ret = msm_csiphy_subdev_init(camss, &camss->csiphy[i],
 					     &csiphy_res[i], i);
 		if (ret < 0) {
 			dev_err(camss->dev,
@@ -370,8 +559,8 @@ static int camss_init_subdevices(struct camss *camss)
 		}
 	}
 
-	for (i = 0; i < ARRAY_SIZE(camss->csid); i++) {
-		ret = msm_csid_subdev_init(&camss->csid[i],
+	for (i = 0; i < camss->csid_num; i++) {
+		ret = msm_csid_subdev_init(camss, &camss->csid[i],
 					   &csid_res[i], i);
 		if (ret < 0) {
 			dev_err(camss->dev,
@@ -381,17 +570,21 @@ static int camss_init_subdevices(struct camss *camss)
 		}
 	}
 
-	ret = msm_ispif_subdev_init(&camss->ispif, &ispif_res);
+	ret = msm_ispif_subdev_init(&camss->ispif, ispif_res);
 	if (ret < 0) {
 		dev_err(camss->dev, "Failed to init ispif sub-device: %d\n",
 			ret);
 		return ret;
 	}
 
-	ret = msm_vfe_subdev_init(&camss->vfe, &vfe_res);
-	if (ret < 0) {
-		dev_err(camss->dev, "Fail to init vfe sub-device: %d\n", ret);
-		return ret;
+	for (i = 0; i < camss->vfe_num; i++) {
+		ret = msm_vfe_subdev_init(camss, &camss->vfe[i],
+					  &vfe_res[i], i);
+		if (ret < 0) {
+			dev_err(camss->dev,
+				"Fail to init vfe%d sub-device: %d\n", i, ret);
+			return ret;
+		}
 	}
 
 	return 0;
@@ -405,10 +598,10 @@ static int camss_init_subdevices(struct camss *camss)
  */
 static int camss_register_entities(struct camss *camss)
 {
-	int i, j;
+	int i, j, k;
 	int ret;
 
-	for (i = 0; i < ARRAY_SIZE(camss->csiphy); i++) {
+	for (i = 0; i < camss->csiphy_num; i++) {
 		ret = msm_csiphy_register_entity(&camss->csiphy[i],
 						 &camss->v4l2_dev);
 		if (ret < 0) {
@@ -419,7 +612,7 @@ static int camss_register_entities(struct camss *camss)
 		}
 	}
 
-	for (i = 0; i < ARRAY_SIZE(camss->csid); i++) {
+	for (i = 0; i < camss->csid_num; i++) {
 		ret = msm_csid_register_entity(&camss->csid[i],
 					       &camss->v4l2_dev);
 		if (ret < 0) {
@@ -437,15 +630,19 @@ static int camss_register_entities(struct camss *camss)
 		goto err_reg_ispif;
 	}
 
-	ret = msm_vfe_register_entities(&camss->vfe, &camss->v4l2_dev);
-	if (ret < 0) {
-		dev_err(camss->dev, "Failed to register vfe entities: %d\n",
-			ret);
-		goto err_reg_vfe;
+	for (i = 0; i < camss->vfe_num; i++) {
+		ret = msm_vfe_register_entities(&camss->vfe[i],
+						&camss->v4l2_dev);
+		if (ret < 0) {
+			dev_err(camss->dev,
+				"Failed to register vfe%d entities: %d\n",
+				i, ret);
+			goto err_reg_vfe;
+		}
 	}
 
-	for (i = 0; i < ARRAY_SIZE(camss->csiphy); i++) {
-		for (j = 0; j < ARRAY_SIZE(camss->csid); j++) {
+	for (i = 0; i < camss->csiphy_num; i++) {
+		for (j = 0; j < camss->csid_num; j++) {
 			ret = media_create_pad_link(
 				&camss->csiphy[i].subdev.entity,
 				MSM_CSIPHY_PAD_SRC,
@@ -463,8 +660,8 @@ static int camss_register_entities(struct camss *camss)
 		}
 	}
 
-	for (i = 0; i < ARRAY_SIZE(camss->csid); i++) {
-		for (j = 0; j < ARRAY_SIZE(camss->ispif.line); j++) {
+	for (i = 0; i < camss->csid_num; i++) {
+		for (j = 0; j < camss->ispif.line_num; j++) {
 			ret = media_create_pad_link(
 				&camss->csid[i].subdev.entity,
 				MSM_CSID_PAD_SRC,
@@ -482,39 +679,42 @@ static int camss_register_entities(struct camss *camss)
 		}
 	}
 
-	for (i = 0; i < ARRAY_SIZE(camss->ispif.line); i++) {
-		for (j = 0; j < ARRAY_SIZE(camss->vfe.line); j++) {
-			ret = media_create_pad_link(
-				&camss->ispif.line[i].subdev.entity,
-				MSM_ISPIF_PAD_SRC,
-				&camss->vfe.line[j].subdev.entity,
-				MSM_VFE_PAD_SINK,
-				0);
-			if (ret < 0) {
-				dev_err(camss->dev,
-					"Failed to link %s->%s entities: %d\n",
-					camss->ispif.line[i].subdev.entity.name,
-					camss->vfe.line[j].subdev.entity.name,
-					ret);
-				goto err_link;
+	for (i = 0; i < camss->ispif.line_num; i++)
+		for (k = 0; k < camss->vfe_num; k++)
+			for (j = 0; j < ARRAY_SIZE(camss->vfe[k].line); j++) {
+				ret = media_create_pad_link(
+					&camss->ispif.line[i].subdev.entity,
+					MSM_ISPIF_PAD_SRC,
+					&camss->vfe[k].line[j].subdev.entity,
+					MSM_VFE_PAD_SINK,
+					0);
+				if (ret < 0) {
+					dev_err(camss->dev,
+						"Failed to link %s->%s entities: %d\n",
+						camss->ispif.line[i].subdev.entity.name,
+						camss->vfe[k].line[j].subdev.entity.name,
+						ret);
+					goto err_link;
+				}
 			}
-		}
-	}
 
 	return 0;
 
 err_link:
-	msm_vfe_unregister_entities(&camss->vfe);
+	i = camss->vfe_num;
 err_reg_vfe:
+	for (i--; i >= 0; i--)
+		msm_vfe_unregister_entities(&camss->vfe[i]);
+
 	msm_ispif_unregister_entities(&camss->ispif);
 err_reg_ispif:
 
-	i = ARRAY_SIZE(camss->csid);
+	i = camss->csid_num;
 err_reg_csid:
 	for (i--; i >= 0; i--)
 		msm_csid_unregister_entity(&camss->csid[i]);
 
-	i = ARRAY_SIZE(camss->csiphy);
+	i = camss->csiphy_num;
 err_reg_csiphy:
 	for (i--; i >= 0; i--)
 		msm_csiphy_unregister_entity(&camss->csiphy[i]);
@@ -532,14 +732,16 @@ static void camss_unregister_entities(struct camss *camss)
 {
 	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(camss->csiphy); i++)
+	for (i = 0; i < camss->csiphy_num; i++)
 		msm_csiphy_unregister_entity(&camss->csiphy[i]);
 
-	for (i = 0; i < ARRAY_SIZE(camss->csid); i++)
+	for (i = 0; i < camss->csid_num; i++)
 		msm_csid_unregister_entity(&camss->csid[i]);
 
 	msm_ispif_unregister_entities(&camss->ispif);
-	msm_vfe_unregister_entities(&camss->vfe);
+
+	for (i = 0; i < camss->vfe_num; i++)
+		msm_vfe_unregister_entities(&camss->vfe[i]);
 }
 
 static int camss_subdev_notifier_bound(struct v4l2_async_notifier *async,
@@ -631,6 +833,35 @@ static int camss_probe(struct platform_device *pdev)
 	camss->dev = dev;
 	platform_set_drvdata(pdev, camss);
 
+	if (of_device_is_compatible(dev->of_node, "qcom,msm8916-camss")) {
+		camss->version = CAMSS_8x16;
+		camss->csiphy_num = 2;
+		camss->csid_num = 2;
+		camss->vfe_num = 1;
+	} else if (of_device_is_compatible(dev->of_node,
+					   "qcom,msm8996-camss")) {
+		camss->version = CAMSS_8x96;
+		camss->csiphy_num = 3;
+		camss->csid_num = 4;
+		camss->vfe_num = 2;
+	} else {
+		return -EINVAL;
+	}
+
+	camss->csiphy = kcalloc(camss->csiphy_num, sizeof(*camss->csiphy),
+				GFP_KERNEL);
+	if (!camss->csiphy)
+		return -ENOMEM;
+
+	camss->csid = kcalloc(camss->csid_num, sizeof(*camss->csid),
+			      GFP_KERNEL);
+	if (!camss->csid)
+		return -ENOMEM;
+
+	camss->vfe = kcalloc(camss->vfe_num, sizeof(*camss->vfe), GFP_KERNEL);
+	if (!camss->vfe)
+		return -ENOMEM;
+
 	ret = camss_of_parse_ports(dev, &camss->notifier);
 	if (ret < 0)
 		return ret;
@@ -687,6 +918,23 @@ static int camss_probe(struct platform_device *pdev)
 		}
 	}
 
+	if (camss->version == CAMSS_8x96) {
+		camss->genpd[PM_DOMAIN_VFE0] = dev_pm_domain_attach_by_id(
+						camss->dev, PM_DOMAIN_VFE0);
+		if (IS_ERR(camss->genpd[PM_DOMAIN_VFE0]))
+			return PTR_ERR(camss->genpd[PM_DOMAIN_VFE0]);
+
+		camss->genpd[PM_DOMAIN_VFE1] = dev_pm_domain_attach_by_id(
+						camss->dev, PM_DOMAIN_VFE1);
+		if (IS_ERR(camss->genpd[PM_DOMAIN_VFE1])) {
+			dev_pm_domain_detach(camss->genpd[PM_DOMAIN_VFE0],
+					     true);
+			return PTR_ERR(camss->genpd[PM_DOMAIN_VFE1]);
+		}
+	}
+
+	pm_runtime_enable(dev);
+
 	return 0;
 
 err_register_subdevs:
@@ -703,6 +951,13 @@ void camss_delete(struct camss *camss)
 	media_device_unregister(&camss->media_dev);
 	media_device_cleanup(&camss->media_dev);
 
+	pm_runtime_disable(camss->dev);
+
+	if (camss->version == CAMSS_8x96) {
+		dev_pm_domain_detach(camss->genpd[PM_DOMAIN_VFE0], true);
+		dev_pm_domain_detach(camss->genpd[PM_DOMAIN_VFE1], true);
+	}
+
 	kfree(camss);
 }
 
@@ -714,9 +969,12 @@ void camss_delete(struct camss *camss)
  */
 static int camss_remove(struct platform_device *pdev)
 {
+	unsigned int i;
+
 	struct camss *camss = platform_get_drvdata(pdev);
 
-	msm_vfe_stop_streaming(&camss->vfe);
+	for (i = 0; i < camss->vfe_num; i++)
+		msm_vfe_stop_streaming(&camss->vfe[i]);
 
 	v4l2_async_notifier_unregister(&camss->notifier);
 	camss_unregister_entities(camss);
@@ -729,17 +987,35 @@ static int camss_remove(struct platform_device *pdev)
 
 static const struct of_device_id camss_dt_match[] = {
 	{ .compatible = "qcom,msm8916-camss" },
+	{ .compatible = "qcom,msm8996-camss" },
 	{ }
 };
 
 MODULE_DEVICE_TABLE(of, camss_dt_match);
 
+static int camss_runtime_suspend(struct device *dev)
+{
+	return 0;
+}
+
+static int camss_runtime_resume(struct device *dev)
+{
+	return 0;
+}
+
+static const struct dev_pm_ops camss_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+	SET_RUNTIME_PM_OPS(camss_runtime_suspend, camss_runtime_resume, NULL)
+};
+
 static struct platform_driver qcom_camss_driver = {
 	.probe = camss_probe,
 	.remove = camss_remove,
 	.driver = {
 		.name = "qcom-camss",
 		.of_match_table = camss_dt_match,
+		.pm = &camss_pm_ops,
 	},
 };
 
diff --git a/drivers/media/platform/qcom/camss-8x16/camss.h b/drivers/media/platform/qcom/camss/camss.h
index 4ad223443e4b..418996d8dad8 100644
--- a/drivers/media/platform/qcom/camss-8x16/camss.h
+++ b/drivers/media/platform/qcom/camss/camss.h
@@ -1,23 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * camss.h
  *
  * Qualcomm MSM Camera Subsystem - Core
  *
  * Copyright (c) 2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ * Copyright (C) 2015-2018 Linaro Ltd.
  */
 #ifndef QC_MSM_CAMSS_H
 #define QC_MSM_CAMSS_H
 
+#include <linux/device.h>
 #include <linux/types.h>
 #include <media/v4l2-async.h>
 #include <media/v4l2-device.h>
@@ -31,9 +24,6 @@
 #include "camss-ispif.h"
 #include "camss-vfe.h"
 
-#define CAMSS_CSID_NUM 2
-#define CAMSS_CSIPHY_NUM 2
-
 #define to_camss(ptr_module)	\
 	container_of(ptr_module, struct camss, ptr_module)
 
@@ -50,7 +40,7 @@
 #define to_device_index(ptr_module, index)	\
 	(to_camss_index(ptr_module, index)->dev)
 
-#define CAMSS_RES_MAX 15
+#define CAMSS_RES_MAX 17
 
 struct resources {
 	char *regulator[CAMSS_RES_MAX];
@@ -67,16 +57,33 @@ struct resources_ispif {
 	char *interrupt;
 };
 
+enum pm_domain {
+	PM_DOMAIN_VFE0,
+	PM_DOMAIN_VFE1,
+	PM_DOMAIN_COUNT
+};
+
+enum camss_version {
+	CAMSS_8x16,
+	CAMSS_8x96,
+};
+
 struct camss {
+	enum camss_version version;
 	struct v4l2_device v4l2_dev;
 	struct v4l2_async_notifier notifier;
 	struct media_device media_dev;
 	struct device *dev;
-	struct csiphy_device csiphy[CAMSS_CSIPHY_NUM];
-	struct csid_device csid[CAMSS_CSID_NUM];
+	int csiphy_num;
+	struct csiphy_device *csiphy;
+	int csid_num;
+	struct csid_device *csid;
 	struct ispif_device ispif;
-	struct vfe_device vfe;
+	int vfe_num;
+	struct vfe_device *vfe;
 	atomic_t ref_count;
+	struct device *genpd[PM_DOMAIN_COUNT];
+	struct device_link *genpd_link[PM_DOMAIN_COUNT];
 };
 
 struct camss_camera_interface {
@@ -101,6 +108,8 @@ int camss_enable_clocks(int nclocks, struct camss_clock *clock,
 			struct device *dev);
 void camss_disable_clocks(int nclocks, struct camss_clock *clock);
 int camss_get_pixel_clock(struct media_entity *entity, u32 *pixel_clock);
+int camss_pm_domain_on(struct camss *camss, int id);
+void camss_pm_domain_off(struct camss *camss, int id);
 void camss_delete(struct camss *camss);
 
 #endif /* QC_MSM_CAMSS_H */
diff --git a/drivers/media/platform/qcom/venus/Makefile b/drivers/media/platform/qcom/venus/Makefile
index bfd4edf7c83f..b44b11b03e12 100644
--- a/drivers/media/platform/qcom/venus/Makefile
+++ b/drivers/media/platform/qcom/venus/Makefile
@@ -2,7 +2,8 @@
 # Makefile for Qualcomm Venus driver
 
 venus-core-objs += core.o helpers.o firmware.o \
-		   hfi_venus.o hfi_msgs.o hfi_cmds.o hfi.o
+		   hfi_venus.o hfi_msgs.o hfi_cmds.o hfi.o \
+		   hfi_parser.o
 
 venus-dec-objs += vdec.o vdec_ctrls.o
 venus-enc-objs += venc.o venc_ctrls.o
diff --git a/drivers/media/platform/qcom/venus/core.c b/drivers/media/platform/qcom/venus/core.c
index 41eef376eb2d..bb6add9d340e 100644
--- a/drivers/media/platform/qcom/venus/core.c
+++ b/drivers/media/platform/qcom/venus/core.c
@@ -152,6 +152,83 @@ static void venus_clks_disable(struct venus_core *core)
 		clk_disable_unprepare(core->clks[i]);
 }
 
+static u32 to_v4l2_codec_type(u32 codec)
+{
+	switch (codec) {
+	case HFI_VIDEO_CODEC_H264:
+		return V4L2_PIX_FMT_H264;
+	case HFI_VIDEO_CODEC_H263:
+		return V4L2_PIX_FMT_H263;
+	case HFI_VIDEO_CODEC_MPEG1:
+		return V4L2_PIX_FMT_MPEG1;
+	case HFI_VIDEO_CODEC_MPEG2:
+		return V4L2_PIX_FMT_MPEG2;
+	case HFI_VIDEO_CODEC_MPEG4:
+		return V4L2_PIX_FMT_MPEG4;
+	case HFI_VIDEO_CODEC_VC1:
+		return V4L2_PIX_FMT_VC1_ANNEX_G;
+	case HFI_VIDEO_CODEC_VP8:
+		return V4L2_PIX_FMT_VP8;
+	case HFI_VIDEO_CODEC_VP9:
+		return V4L2_PIX_FMT_VP9;
+	case HFI_VIDEO_CODEC_DIVX:
+	case HFI_VIDEO_CODEC_DIVX_311:
+		return V4L2_PIX_FMT_XVID;
+	default:
+		return 0;
+	}
+}
+
+static int venus_enumerate_codecs(struct venus_core *core, u32 type)
+{
+	const struct hfi_inst_ops dummy_ops = {};
+	struct venus_inst *inst;
+	u32 codec, codecs;
+	unsigned int i;
+	int ret;
+
+	if (core->res->hfi_version != HFI_VERSION_1XX)
+		return 0;
+
+	inst = kzalloc(sizeof(*inst), GFP_KERNEL);
+	if (!inst)
+		return -ENOMEM;
+
+	mutex_init(&inst->lock);
+	inst->core = core;
+	inst->session_type = type;
+	if (type == VIDC_SESSION_TYPE_DEC)
+		codecs = core->dec_codecs;
+	else
+		codecs = core->enc_codecs;
+
+	ret = hfi_session_create(inst, &dummy_ops);
+	if (ret)
+		goto err;
+
+	for (i = 0; i < MAX_CODEC_NUM; i++) {
+		codec = (1 << i) & codecs;
+		if (!codec)
+			continue;
+
+		ret = hfi_session_init(inst, to_v4l2_codec_type(codec));
+		if (ret)
+			goto done;
+
+		ret = hfi_session_deinit(inst);
+		if (ret)
+			goto done;
+	}
+
+done:
+	hfi_session_destroy(inst);
+err:
+	mutex_destroy(&inst->lock);
+	kfree(inst);
+
+	return ret;
+}
+
 static int venus_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -219,6 +296,14 @@ static int venus_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_venus_shutdown;
 
+	ret = venus_enumerate_codecs(core, VIDC_SESSION_TYPE_DEC);
+	if (ret)
+		goto err_venus_shutdown;
+
+	ret = venus_enumerate_codecs(core, VIDC_SESSION_TYPE_ENC);
+	if (ret)
+		goto err_venus_shutdown;
+
 	ret = v4l2_device_register(dev, &core->v4l2_dev);
 	if (ret)
 		goto err_core_deinit;
@@ -365,9 +450,31 @@ static const struct venus_resources msm8996_res = {
 	.fwname = "qcom/venus-4.2/venus.mdt",
 };
 
+static const struct freq_tbl sdm845_freq_table[] = {
+	{ 1944000, 380000000 },	/* 4k UHD @ 60 */
+	{  972000, 320000000 },	/* 4k UHD @ 30 */
+	{  489600, 200000000 },	/* 1080p @ 60 */
+	{  244800, 100000000 },	/* 1080p @ 30 */
+};
+
+static const struct venus_resources sdm845_res = {
+	.freq_tbl = sdm845_freq_table,
+	.freq_tbl_size = ARRAY_SIZE(sdm845_freq_table),
+	.clks = {"core", "iface", "bus" },
+	.clks_num = 3,
+	.max_load = 2563200,
+	.hfi_version = HFI_VERSION_4XX,
+	.vmem_id = VIDC_RESOURCE_NONE,
+	.vmem_size = 0,
+	.vmem_addr = 0,
+	.dma_mask = 0xe0000000 - 1,
+	.fwname = "qcom/venus-5.2/venus.mdt",
+};
+
 static const struct of_device_id venus_dt_match[] = {
 	{ .compatible = "qcom,msm8916-venus", .data = &msm8916_res, },
 	{ .compatible = "qcom,msm8996-venus", .data = &msm8996_res, },
+	{ .compatible = "qcom,sdm845-venus", .data = &sdm845_res, },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, venus_dt_match);
diff --git a/drivers/media/platform/qcom/venus/core.h b/drivers/media/platform/qcom/venus/core.h
index 0360d295f4c8..2f02365f4818 100644
--- a/drivers/media/platform/qcom/venus/core.h
+++ b/drivers/media/platform/qcom/venus/core.h
@@ -57,6 +57,30 @@ struct venus_format {
 	u32 type;
 };
 
+#define MAX_PLANES		4
+#define MAX_FMT_ENTRIES		32
+#define MAX_CAP_ENTRIES		32
+#define MAX_ALLOC_MODE_ENTRIES	16
+#define MAX_CODEC_NUM		32
+
+struct raw_formats {
+	u32 buftype;
+	u32 fmt;
+};
+
+struct venus_caps {
+	u32 codec;
+	u32 domain;
+	bool cap_bufs_mode_dynamic;
+	unsigned int num_caps;
+	struct hfi_capability caps[MAX_CAP_ENTRIES];
+	unsigned int num_pl;
+	struct hfi_profile_level pl[HFI_MAX_PROFILE_COUNT];
+	unsigned int num_fmts;
+	struct raw_formats fmts[MAX_FMT_ENTRIES];
+	bool valid;	/* used only for Venus v1xx */
+};
+
 /**
  * struct venus_core - holds core parameters valid for all instances
  *
@@ -65,6 +89,8 @@ struct venus_format {
  * @clks:	an array of struct clk pointers
  * @core0_clk:	a struct clk pointer for core0
  * @core1_clk:	a struct clk pointer for core1
+ * @core0_bus_clk: a struct clk pointer for core0 bus clock
+ * @core1_bus_clk: a struct clk pointer for core1 bus clock
  * @vdev_dec:	a reference to video device structure for decoder instances
  * @vdev_enc:	a reference to video device structure for encoder instances
  * @v4l2_dev:	a holder for v4l2 device structure
@@ -94,6 +120,8 @@ struct venus_core {
 	struct clk *clks[VIDC_CLKS_NUM_MAX];
 	struct clk *core0_clk;
 	struct clk *core1_clk;
+	struct clk *core0_bus_clk;
+	struct clk *core1_bus_clk;
 	struct video_device *vdev_dec;
 	struct video_device *vdev_enc;
 	struct v4l2_device v4l2_dev;
@@ -109,8 +137,8 @@ struct venus_core {
 	unsigned int error;
 	bool sys_error;
 	const struct hfi_core_ops *core_ops;
-	u32 enc_codecs;
-	u32 dec_codecs;
+	unsigned long enc_codecs;
+	unsigned long dec_codecs;
 	unsigned int max_sessions_supported;
 #define ENC_ROTATION_CAPABILITY		0x1
 #define ENC_SCALING_CAPABILITY		0x2
@@ -120,6 +148,8 @@ struct venus_core {
 	void *priv;
 	const struct hfi_ops *ops;
 	struct delayed_work work;
+	struct venus_caps caps[MAX_CODEC_NUM];
+	unsigned int codecs_count;
 };
 
 struct vdec_controls {
@@ -160,10 +190,12 @@ struct venc_controls {
 		u32 mpeg4;
 		u32 h264;
 		u32 vpx;
+		u32 hevc;
 	} profile;
 	struct {
 		u32 mpeg4;
 		u32 h264;
+		u32 hevc;
 	} level;
 };
 
@@ -185,6 +217,7 @@ struct venus_buffer {
  * @list:	used for attach an instance to the core
  * @lock:	instance lock
  * @core:	a reference to the core struct
+ * @dpbbufs:	a list of decoded picture buffers
  * @internalbufs:	a list of internal bufferes
  * @registeredbufs:	a list of registered capture bufferes
  * @delayed_process	a list of delayed buffers
@@ -209,9 +242,15 @@ struct venus_buffer {
  * @num_output_bufs:	holds number of output buffers
  * @input_buf_size	holds input buffer size
  * @output_buf_size:	holds output buffer size
+ * @output2_buf_size:	holds secondary decoder output buffer size
+ * @dpb_buftype:	decoded picture buffer type
+ * @dpb_fmt:		decoded picture buffer raw format
+ * @opb_buftype:	output picture buffer type
+ * @opb_fmt:		output picture buffer raw format
  * @reconfig:	a flag raised by decoder when the stream resolution changed
  * @reconfig_width:	holds the new width
  * @reconfig_height:	holds the new height
+ * @hfi_codec:		current codec for this instance in HFI space
  * @sequence_cap:	a sequence counter for capture queue
  * @sequence_out:	a sequence counter for output queue
  * @m2m_dev:	a reference to m2m device structure
@@ -224,27 +263,12 @@ struct venus_buffer {
  * @priv:	a private for HFI operations callbacks
  * @session_type:	the type of the session (decoder or encoder)
  * @hprop:	a union used as a holder by get property
- * @cap_width:	width capability
- * @cap_height:	height capability
- * @cap_mbs_per_frame:	macroblocks per frame capability
- * @cap_mbs_per_sec:	macroblocks per second capability
- * @cap_framerate:	framerate capability
- * @cap_scale_x:		horizontal scaling capability
- * @cap_scale_y:		vertical scaling capability
- * @cap_bitrate:		bitrate capability
- * @cap_hier_p:		hier capability
- * @cap_ltr_count:	LTR count capability
- * @cap_secure_output2_threshold: secure OUTPUT2 threshold capability
- * @cap_bufs_mode_static:	buffers allocation mode capability
- * @cap_bufs_mode_dynamic:	buffers allocation mode capability
- * @pl_count:	count of supported profiles/levels
- * @pl:		supported profiles/levels
- * @bufreq:	holds buffer requirements
  */
 struct venus_inst {
 	struct list_head list;
 	struct mutex lock;
 	struct venus_core *core;
+	struct list_head dpbbufs;
 	struct list_head internalbufs;
 	struct list_head registeredbufs;
 	struct list_head delayed_process;
@@ -273,9 +297,15 @@ struct venus_inst {
 	unsigned int num_output_bufs;
 	unsigned int input_buf_size;
 	unsigned int output_buf_size;
+	unsigned int output2_buf_size;
+	u32 dpb_buftype;
+	u32 dpb_fmt;
+	u32 opb_buftype;
+	u32 opb_fmt;
 	bool reconfig;
 	u32 reconfig_width;
 	u32 reconfig_height;
+	u32 hfi_codec;
 	u32 sequence_cap;
 	u32 sequence_out;
 	struct v4l2_m2m_dev *m2m_dev;
@@ -287,24 +317,12 @@ struct venus_inst {
 	const struct hfi_inst_ops *ops;
 	u32 session_type;
 	union hfi_get_property hprop;
-	struct hfi_capability cap_width;
-	struct hfi_capability cap_height;
-	struct hfi_capability cap_mbs_per_frame;
-	struct hfi_capability cap_mbs_per_sec;
-	struct hfi_capability cap_framerate;
-	struct hfi_capability cap_scale_x;
-	struct hfi_capability cap_scale_y;
-	struct hfi_capability cap_bitrate;
-	struct hfi_capability cap_hier_p;
-	struct hfi_capability cap_ltr_count;
-	struct hfi_capability cap_secure_output2_threshold;
-	bool cap_bufs_mode_static;
-	bool cap_bufs_mode_dynamic;
-	unsigned int pl_count;
-	struct hfi_profile_level pl[HFI_MAX_PROFILE_COUNT];
-	struct hfi_buffer_requirements bufreq[HFI_BUFFER_TYPE_MAX];
 };
 
+#define IS_V1(core)	((core)->res->hfi_version == HFI_VERSION_1XX)
+#define IS_V3(core)	((core)->res->hfi_version == HFI_VERSION_3XX)
+#define IS_V4(core)	((core)->res->hfi_version == HFI_VERSION_4XX)
+
 #define ctrl_to_inst(ctrl)	\
 	container_of((ctrl)->handler, struct venus_inst, ctrl_handler)
 
@@ -318,4 +336,18 @@ static inline void *to_hfi_priv(struct venus_core *core)
 	return core->priv;
 }
 
+static inline struct venus_caps *
+venus_caps_by_codec(struct venus_core *core, u32 codec, u32 domain)
+{
+	unsigned int c;
+
+	for (c = 0; c < core->codecs_count; c++) {
+		if (core->caps[c].codec == codec &&
+		    core->caps[c].domain == domain)
+			return &core->caps[c];
+	}
+
+	return NULL;
+}
+
 #endif
diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c
index 0ce9559a2924..cd3b96e6f24b 100644
--- a/drivers/media/platform/qcom/venus/helpers.c
+++ b/drivers/media/platform/qcom/venus/helpers.c
@@ -13,6 +13,7 @@
  *
  */
 #include <linux/clk.h>
+#include <linux/iopoll.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/pm_runtime.h>
@@ -24,6 +25,7 @@
 #include "core.h"
 #include "helpers.h"
 #include "hfi_helper.h"
+#include "hfi_venus_io.h"
 
 struct intbuf {
 	struct list_head list;
@@ -69,6 +71,9 @@ bool venus_helper_check_codec(struct venus_inst *inst, u32 v4l2_pixfmt)
 	case V4L2_PIX_FMT_XVID:
 		codec = HFI_VIDEO_CODEC_DIVX;
 		break;
+	case V4L2_PIX_FMT_HEVC:
+		codec = HFI_VIDEO_CODEC_HEVC;
+		break;
 	default:
 		return false;
 	}
@@ -83,6 +88,106 @@ bool venus_helper_check_codec(struct venus_inst *inst, u32 v4l2_pixfmt)
 }
 EXPORT_SYMBOL_GPL(venus_helper_check_codec);
 
+static int venus_helper_queue_dpb_bufs(struct venus_inst *inst)
+{
+	struct intbuf *buf;
+	int ret = 0;
+
+	list_for_each_entry(buf, &inst->dpbbufs, list) {
+		struct hfi_frame_data fdata;
+
+		memset(&fdata, 0, sizeof(fdata));
+		fdata.alloc_len = buf->size;
+		fdata.device_addr = buf->da;
+		fdata.buffer_type = buf->type;
+
+		ret = hfi_session_process_buf(inst, &fdata);
+		if (ret)
+			goto fail;
+	}
+
+fail:
+	return ret;
+}
+
+int venus_helper_free_dpb_bufs(struct venus_inst *inst)
+{
+	struct intbuf *buf, *n;
+
+	list_for_each_entry_safe(buf, n, &inst->dpbbufs, list) {
+		list_del_init(&buf->list);
+		dma_free_attrs(inst->core->dev, buf->size, buf->va, buf->da,
+			       buf->attrs);
+		kfree(buf);
+	}
+
+	INIT_LIST_HEAD(&inst->dpbbufs);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(venus_helper_free_dpb_bufs);
+
+int venus_helper_alloc_dpb_bufs(struct venus_inst *inst)
+{
+	struct venus_core *core = inst->core;
+	struct device *dev = core->dev;
+	enum hfi_version ver = core->res->hfi_version;
+	struct hfi_buffer_requirements bufreq;
+	u32 buftype = inst->dpb_buftype;
+	unsigned int dpb_size = 0;
+	struct intbuf *buf;
+	unsigned int i;
+	u32 count;
+	int ret;
+
+	/* no need to allocate dpb buffers */
+	if (!inst->dpb_fmt)
+		return 0;
+
+	if (inst->dpb_buftype == HFI_BUFFER_OUTPUT)
+		dpb_size = inst->output_buf_size;
+	else if (inst->dpb_buftype == HFI_BUFFER_OUTPUT2)
+		dpb_size = inst->output2_buf_size;
+
+	if (!dpb_size)
+		return 0;
+
+	ret = venus_helper_get_bufreq(inst, buftype, &bufreq);
+	if (ret)
+		return ret;
+
+	count = HFI_BUFREQ_COUNT_MIN(&bufreq, ver);
+
+	for (i = 0; i < count; i++) {
+		buf = kzalloc(sizeof(*buf), GFP_KERNEL);
+		if (!buf) {
+			ret = -ENOMEM;
+			goto fail;
+		}
+
+		buf->type = buftype;
+		buf->size = dpb_size;
+		buf->attrs = DMA_ATTR_WRITE_COMBINE |
+			     DMA_ATTR_NO_KERNEL_MAPPING;
+		buf->va = dma_alloc_attrs(dev, buf->size, &buf->da, GFP_KERNEL,
+					  buf->attrs);
+		if (!buf->va) {
+			kfree(buf);
+			ret = -ENOMEM;
+			goto fail;
+		}
+
+		list_add_tail(&buf->list, &inst->dpbbufs);
+	}
+
+	return 0;
+
+fail:
+	venus_helper_free_dpb_bufs(inst);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(venus_helper_alloc_dpb_bufs);
+
 static int intbufs_set_buffer(struct venus_inst *inst, u32 type)
 {
 	struct venus_core *core = inst->core;
@@ -166,21 +271,38 @@ static int intbufs_unset_buffers(struct venus_inst *inst)
 	return ret;
 }
 
-static const unsigned int intbuf_types[] = {
-	HFI_BUFFER_INTERNAL_SCRATCH,
-	HFI_BUFFER_INTERNAL_SCRATCH_1,
-	HFI_BUFFER_INTERNAL_SCRATCH_2,
+static const unsigned int intbuf_types_1xx[] = {
+	HFI_BUFFER_INTERNAL_SCRATCH(HFI_VERSION_1XX),
+	HFI_BUFFER_INTERNAL_SCRATCH_1(HFI_VERSION_1XX),
+	HFI_BUFFER_INTERNAL_SCRATCH_2(HFI_VERSION_1XX),
+	HFI_BUFFER_INTERNAL_PERSIST,
+	HFI_BUFFER_INTERNAL_PERSIST_1,
+};
+
+static const unsigned int intbuf_types_4xx[] = {
+	HFI_BUFFER_INTERNAL_SCRATCH(HFI_VERSION_4XX),
+	HFI_BUFFER_INTERNAL_SCRATCH_1(HFI_VERSION_4XX),
+	HFI_BUFFER_INTERNAL_SCRATCH_2(HFI_VERSION_4XX),
 	HFI_BUFFER_INTERNAL_PERSIST,
 	HFI_BUFFER_INTERNAL_PERSIST_1,
 };
 
 static int intbufs_alloc(struct venus_inst *inst)
 {
-	unsigned int i;
+	const unsigned int *intbuf;
+	size_t arr_sz, i;
 	int ret;
 
-	for (i = 0; i < ARRAY_SIZE(intbuf_types); i++) {
-		ret = intbufs_set_buffer(inst, intbuf_types[i]);
+	if (IS_V4(inst->core)) {
+		arr_sz = ARRAY_SIZE(intbuf_types_4xx);
+		intbuf = intbuf_types_4xx;
+	} else {
+		arr_sz = ARRAY_SIZE(intbuf_types_1xx);
+		intbuf = intbuf_types_1xx;
+	}
+
+	for (i = 0; i < arr_sz; i++) {
+		ret = intbufs_set_buffer(inst, intbuf[i]);
 		if (ret)
 			goto error;
 	}
@@ -257,20 +379,23 @@ static int load_scale_clocks(struct venus_core *core)
 
 set_freq:
 
-	if (core->res->hfi_version == HFI_VERSION_3XX) {
-		ret = clk_set_rate(clk, freq);
-		ret |= clk_set_rate(core->core0_clk, freq);
-		ret |= clk_set_rate(core->core1_clk, freq);
-	} else {
-		ret = clk_set_rate(clk, freq);
-	}
+	ret = clk_set_rate(clk, freq);
+	if (ret)
+		goto err;
 
-	if (ret) {
-		dev_err(dev, "failed to set clock rate %lu (%d)\n", freq, ret);
-		return ret;
-	}
+	ret = clk_set_rate(core->core0_clk, freq);
+	if (ret)
+		goto err;
+
+	ret = clk_set_rate(core->core1_clk, freq);
+	if (ret)
+		goto err;
 
 	return 0;
+
+err:
+	dev_err(dev, "failed to set clock rate %lu (%d)\n", freq, ret);
+	return ret;
 }
 
 static void fill_buffer_desc(const struct venus_buffer *buf,
@@ -325,7 +450,10 @@ session_process_buf(struct venus_inst *inst, struct vb2_v4l2_buffer *vbuf)
 		if (vbuf->flags & V4L2_BUF_FLAG_LAST || !fdata.filled_len)
 			fdata.flags |= HFI_BUFFERFLAG_EOS;
 	} else if (type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
-		fdata.buffer_type = HFI_BUFFER_OUTPUT;
+		if (inst->session_type == VIDC_SESSION_TYPE_ENC)
+			fdata.buffer_type = HFI_BUFFER_OUTPUT;
+		else
+			fdata.buffer_type = inst->opb_buftype;
 		fdata.filled_len = 0;
 		fdata.offset = 0;
 	}
@@ -337,18 +465,16 @@ session_process_buf(struct venus_inst *inst, struct vb2_v4l2_buffer *vbuf)
 	return 0;
 }
 
-static inline int is_reg_unreg_needed(struct venus_inst *inst)
+static bool is_dynamic_bufmode(struct venus_inst *inst)
 {
-	if (inst->session_type == VIDC_SESSION_TYPE_DEC &&
-	    inst->core->res->hfi_version == HFI_VERSION_3XX)
-		return 0;
+	struct venus_core *core = inst->core;
+	struct venus_caps *caps;
 
-	if (inst->session_type == VIDC_SESSION_TYPE_DEC &&
-	    inst->cap_bufs_mode_dynamic &&
-	    inst->core->res->hfi_version == HFI_VERSION_1XX)
+	caps = venus_caps_by_codec(core, inst->hfi_codec, inst->session_type);
+	if (!caps)
 		return 0;
 
-	return 1;
+	return caps->cap_bufs_mode_dynamic;
 }
 
 static int session_unregister_bufs(struct venus_inst *inst)
@@ -357,7 +483,7 @@ static int session_unregister_bufs(struct venus_inst *inst)
 	struct hfi_buffer_desc bd;
 	int ret = 0;
 
-	if (!is_reg_unreg_needed(inst))
+	if (is_dynamic_bufmode(inst))
 		return 0;
 
 	list_for_each_entry_safe(buf, n, &inst->registeredbufs, reg_list) {
@@ -377,7 +503,7 @@ static int session_register_bufs(struct venus_inst *inst)
 	struct venus_buffer *buf;
 	int ret = 0;
 
-	if (!is_reg_unreg_needed(inst))
+	if (is_dynamic_bufmode(inst))
 		return 0;
 
 	list_for_each_entry(buf, &inst->registeredbufs, reg_list) {
@@ -392,6 +518,20 @@ static int session_register_bufs(struct venus_inst *inst)
 	return ret;
 }
 
+static u32 to_hfi_raw_fmt(u32 v4l2_fmt)
+{
+	switch (v4l2_fmt) {
+	case V4L2_PIX_FMT_NV12:
+		return HFI_COLOR_FORMAT_NV12;
+	case V4L2_PIX_FMT_NV21:
+		return HFI_COLOR_FORMAT_NV21;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 int venus_helper_get_bufreq(struct venus_inst *inst, u32 type,
 			    struct hfi_buffer_requirements *req)
 {
@@ -423,6 +563,104 @@ int venus_helper_get_bufreq(struct venus_inst *inst, u32 type,
 }
 EXPORT_SYMBOL_GPL(venus_helper_get_bufreq);
 
+static u32 get_framesize_raw_nv12(u32 width, u32 height)
+{
+	u32 y_stride, uv_stride, y_plane;
+	u32 y_sclines, uv_sclines, uv_plane;
+	u32 size;
+
+	y_stride = ALIGN(width, 128);
+	uv_stride = ALIGN(width, 128);
+	y_sclines = ALIGN(height, 32);
+	uv_sclines = ALIGN(((height + 1) >> 1), 16);
+
+	y_plane = y_stride * y_sclines;
+	uv_plane = uv_stride * uv_sclines + SZ_4K;
+	size = y_plane + uv_plane + SZ_8K;
+
+	return ALIGN(size, SZ_4K);
+}
+
+static u32 get_framesize_raw_nv12_ubwc(u32 width, u32 height)
+{
+	u32 y_meta_stride, y_meta_plane;
+	u32 y_stride, y_plane;
+	u32 uv_meta_stride, uv_meta_plane;
+	u32 uv_stride, uv_plane;
+	u32 extradata = SZ_16K;
+
+	y_meta_stride = ALIGN(DIV_ROUND_UP(width, 32), 64);
+	y_meta_plane = y_meta_stride * ALIGN(DIV_ROUND_UP(height, 8), 16);
+	y_meta_plane = ALIGN(y_meta_plane, SZ_4K);
+
+	y_stride = ALIGN(width, 128);
+	y_plane = ALIGN(y_stride * ALIGN(height, 32), SZ_4K);
+
+	uv_meta_stride = ALIGN(DIV_ROUND_UP(width / 2, 16), 64);
+	uv_meta_plane = uv_meta_stride * ALIGN(DIV_ROUND_UP(height / 2, 8), 16);
+	uv_meta_plane = ALIGN(uv_meta_plane, SZ_4K);
+
+	uv_stride = ALIGN(width, 128);
+	uv_plane = ALIGN(uv_stride * ALIGN(height / 2, 32), SZ_4K);
+
+	return ALIGN(y_meta_plane + y_plane + uv_meta_plane + uv_plane +
+		     max(extradata, y_stride * 48), SZ_4K);
+}
+
+u32 venus_helper_get_framesz_raw(u32 hfi_fmt, u32 width, u32 height)
+{
+	switch (hfi_fmt) {
+	case HFI_COLOR_FORMAT_NV12:
+	case HFI_COLOR_FORMAT_NV21:
+		return get_framesize_raw_nv12(width, height);
+	case HFI_COLOR_FORMAT_NV12_UBWC:
+		return get_framesize_raw_nv12_ubwc(width, height);
+	default:
+		return 0;
+	}
+}
+EXPORT_SYMBOL_GPL(venus_helper_get_framesz_raw);
+
+u32 venus_helper_get_framesz(u32 v4l2_fmt, u32 width, u32 height)
+{
+	u32 hfi_fmt, sz;
+	bool compressed;
+
+	switch (v4l2_fmt) {
+	case V4L2_PIX_FMT_MPEG:
+	case V4L2_PIX_FMT_H264:
+	case V4L2_PIX_FMT_H264_NO_SC:
+	case V4L2_PIX_FMT_H264_MVC:
+	case V4L2_PIX_FMT_H263:
+	case V4L2_PIX_FMT_MPEG1:
+	case V4L2_PIX_FMT_MPEG2:
+	case V4L2_PIX_FMT_MPEG4:
+	case V4L2_PIX_FMT_XVID:
+	case V4L2_PIX_FMT_VC1_ANNEX_G:
+	case V4L2_PIX_FMT_VC1_ANNEX_L:
+	case V4L2_PIX_FMT_VP8:
+	case V4L2_PIX_FMT_VP9:
+	case V4L2_PIX_FMT_HEVC:
+		compressed = true;
+		break;
+	default:
+		compressed = false;
+		break;
+	}
+
+	if (compressed) {
+		sz = ALIGN(height, 32) * ALIGN(width, 32) * 3 / 2 / 2;
+		return ALIGN(sz, SZ_4K);
+	}
+
+	hfi_fmt = to_hfi_raw_fmt(v4l2_fmt);
+	if (!hfi_fmt)
+		return 0;
+
+	return venus_helper_get_framesz_raw(hfi_fmt, width, height);
+}
+EXPORT_SYMBOL_GPL(venus_helper_get_framesz);
+
 int venus_helper_set_input_resolution(struct venus_inst *inst,
 				      unsigned int width, unsigned int height)
 {
@@ -438,12 +676,13 @@ int venus_helper_set_input_resolution(struct venus_inst *inst,
 EXPORT_SYMBOL_GPL(venus_helper_set_input_resolution);
 
 int venus_helper_set_output_resolution(struct venus_inst *inst,
-				       unsigned int width, unsigned int height)
+				       unsigned int width, unsigned int height,
+				       u32 buftype)
 {
 	u32 ptype = HFI_PROPERTY_PARAM_FRAME_SIZE;
 	struct hfi_framesize fs;
 
-	fs.buffer_type = HFI_BUFFER_OUTPUT;
+	fs.buffer_type = buftype;
 	fs.width = width;
 	fs.height = height;
 
@@ -451,8 +690,37 @@ int venus_helper_set_output_resolution(struct venus_inst *inst,
 }
 EXPORT_SYMBOL_GPL(venus_helper_set_output_resolution);
 
+int venus_helper_set_work_mode(struct venus_inst *inst, u32 mode)
+{
+	const u32 ptype = HFI_PROPERTY_PARAM_WORK_MODE;
+	struct hfi_video_work_mode wm;
+
+	if (!IS_V4(inst->core))
+		return 0;
+
+	wm.video_work_mode = mode;
+
+	return hfi_session_set_property(inst, ptype, &wm);
+}
+EXPORT_SYMBOL_GPL(venus_helper_set_work_mode);
+
+int venus_helper_set_core_usage(struct venus_inst *inst, u32 usage)
+{
+	const u32 ptype = HFI_PROPERTY_CONFIG_VIDEOCORES_USAGE;
+	struct hfi_videocores_usage_type cu;
+
+	if (!IS_V4(inst->core))
+		return 0;
+
+	cu.video_core_enable_mask = usage;
+
+	return hfi_session_set_property(inst, ptype, &cu);
+}
+EXPORT_SYMBOL_GPL(venus_helper_set_core_usage);
+
 int venus_helper_set_num_bufs(struct venus_inst *inst, unsigned int input_bufs,
-			      unsigned int output_bufs)
+			      unsigned int output_bufs,
+			      unsigned int output2_bufs)
 {
 	u32 ptype = HFI_PROPERTY_PARAM_BUFFER_COUNT_ACTUAL;
 	struct hfi_buffer_count_actual buf_count;
@@ -468,41 +736,122 @@ int venus_helper_set_num_bufs(struct venus_inst *inst, unsigned int input_bufs,
 	buf_count.type = HFI_BUFFER_OUTPUT;
 	buf_count.count_actual = output_bufs;
 
-	return hfi_session_set_property(inst, ptype, &buf_count);
+	ret = hfi_session_set_property(inst, ptype, &buf_count);
+	if (ret)
+		return ret;
+
+	if (output2_bufs) {
+		buf_count.type = HFI_BUFFER_OUTPUT2;
+		buf_count.count_actual = output2_bufs;
+
+		ret = hfi_session_set_property(inst, ptype, &buf_count);
+	}
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(venus_helper_set_num_bufs);
 
-int venus_helper_set_color_format(struct venus_inst *inst, u32 pixfmt)
+int venus_helper_set_raw_format(struct venus_inst *inst, u32 hfi_format,
+				u32 buftype)
 {
+	const u32 ptype = HFI_PROPERTY_PARAM_UNCOMPRESSED_FORMAT_SELECT;
 	struct hfi_uncompressed_format_select fmt;
-	u32 ptype = HFI_PROPERTY_PARAM_UNCOMPRESSED_FORMAT_SELECT;
-	int ret;
+
+	fmt.buffer_type = buftype;
+	fmt.format = hfi_format;
+
+	return hfi_session_set_property(inst, ptype, &fmt);
+}
+EXPORT_SYMBOL_GPL(venus_helper_set_raw_format);
+
+int venus_helper_set_color_format(struct venus_inst *inst, u32 pixfmt)
+{
+	u32 hfi_format, buftype;
 
 	if (inst->session_type == VIDC_SESSION_TYPE_DEC)
-		fmt.buffer_type = HFI_BUFFER_OUTPUT;
+		buftype = HFI_BUFFER_OUTPUT;
 	else if (inst->session_type == VIDC_SESSION_TYPE_ENC)
-		fmt.buffer_type = HFI_BUFFER_INPUT;
+		buftype = HFI_BUFFER_INPUT;
 	else
 		return -EINVAL;
 
-	switch (pixfmt) {
-	case V4L2_PIX_FMT_NV12:
-		fmt.format = HFI_COLOR_FORMAT_NV12;
-		break;
-	case V4L2_PIX_FMT_NV21:
-		fmt.format = HFI_COLOR_FORMAT_NV21;
-		break;
-	default:
+	hfi_format = to_hfi_raw_fmt(pixfmt);
+	if (!hfi_format)
 		return -EINVAL;
-	}
 
-	ret = hfi_session_set_property(inst, ptype, &fmt);
+	return venus_helper_set_raw_format(inst, hfi_format, buftype);
+}
+EXPORT_SYMBOL_GPL(venus_helper_set_color_format);
+
+int venus_helper_set_multistream(struct venus_inst *inst, bool out_en,
+				 bool out2_en)
+{
+	struct hfi_multi_stream multi = {0};
+	u32 ptype = HFI_PROPERTY_PARAM_VDEC_MULTI_STREAM;
+	int ret;
+
+	multi.buffer_type = HFI_BUFFER_OUTPUT;
+	multi.enable = out_en;
+
+	ret = hfi_session_set_property(inst, ptype, &multi);
+	if (ret)
+		return ret;
+
+	multi.buffer_type = HFI_BUFFER_OUTPUT2;
+	multi.enable = out2_en;
+
+	return hfi_session_set_property(inst, ptype, &multi);
+}
+EXPORT_SYMBOL_GPL(venus_helper_set_multistream);
+
+int venus_helper_set_dyn_bufmode(struct venus_inst *inst)
+{
+	const u32 ptype = HFI_PROPERTY_PARAM_BUFFER_ALLOC_MODE;
+	struct hfi_buffer_alloc_mode mode;
+	int ret;
+
+	if (!is_dynamic_bufmode(inst))
+		return 0;
+
+	mode.type = HFI_BUFFER_OUTPUT;
+	mode.mode = HFI_BUFFER_MODE_DYNAMIC;
+
+	ret = hfi_session_set_property(inst, ptype, &mode);
 	if (ret)
 		return ret;
 
+	mode.type = HFI_BUFFER_OUTPUT2;
+
+	return hfi_session_set_property(inst, ptype, &mode);
+}
+EXPORT_SYMBOL_GPL(venus_helper_set_dyn_bufmode);
+
+int venus_helper_set_bufsize(struct venus_inst *inst, u32 bufsize, u32 buftype)
+{
+	const u32 ptype = HFI_PROPERTY_PARAM_BUFFER_SIZE_ACTUAL;
+	struct hfi_buffer_size_actual bufsz;
+
+	bufsz.type = buftype;
+	bufsz.size = bufsize;
+
+	return hfi_session_set_property(inst, ptype, &bufsz);
+}
+EXPORT_SYMBOL_GPL(venus_helper_set_bufsize);
+
+unsigned int venus_helper_get_opb_size(struct venus_inst *inst)
+{
+	/* the encoder has only one output */
+	if (inst->session_type == VIDC_SESSION_TYPE_ENC)
+		return inst->output_buf_size;
+
+	if (inst->opb_buftype == HFI_BUFFER_OUTPUT)
+		return inst->output_buf_size;
+	else if (inst->opb_buftype == HFI_BUFFER_OUTPUT2)
+		return inst->output2_buf_size;
+
 	return 0;
 }
-EXPORT_SYMBOL_GPL(venus_helper_set_color_format);
+EXPORT_SYMBOL_GPL(venus_helper_get_opb_size);
 
 static void delayed_process_buf_func(struct work_struct *work)
 {
@@ -602,9 +951,10 @@ EXPORT_SYMBOL_GPL(venus_helper_vb2_buf_init);
 int venus_helper_vb2_buf_prepare(struct vb2_buffer *vb)
 {
 	struct venus_inst *inst = vb2_get_drv_priv(vb->vb2_queue);
+	unsigned int out_buf_size = venus_helper_get_opb_size(inst);
 
 	if (vb->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE &&
-	    vb2_plane_size(vb, 0) < inst->output_buf_size)
+	    vb2_plane_size(vb, 0) < out_buf_size)
 		return -EINVAL;
 	if (vb->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE &&
 	    vb2_plane_size(vb, 0) < inst->input_buf_size)
@@ -674,6 +1024,8 @@ void venus_helper_vb2_stop_streaming(struct vb2_queue *q)
 		if (ret)
 			hfi_session_abort(inst);
 
+		venus_helper_free_dpb_bufs(inst);
+
 		load_scale_clocks(core);
 		INIT_LIST_HEAD(&inst->registeredbufs);
 	}
@@ -712,8 +1064,14 @@ int venus_helper_vb2_start_streaming(struct venus_inst *inst)
 	if (ret)
 		goto err_unload_res;
 
+	ret = venus_helper_queue_dpb_bufs(inst);
+	if (ret)
+		goto err_session_stop;
+
 	return 0;
 
+err_session_stop:
+	hfi_session_stop(inst);
 err_unload_res:
 	hfi_session_unload_res(inst);
 err_unreg_bufs:
@@ -766,3 +1124,113 @@ void venus_helper_init_instance(struct venus_inst *inst)
 	}
 }
 EXPORT_SYMBOL_GPL(venus_helper_init_instance);
+
+static bool find_fmt_from_caps(struct venus_caps *caps, u32 buftype, u32 fmt)
+{
+	unsigned int i;
+
+	for (i = 0; i < caps->num_fmts; i++) {
+		if (caps->fmts[i].buftype == buftype &&
+		    caps->fmts[i].fmt == fmt)
+			return true;
+	}
+
+	return false;
+}
+
+int venus_helper_get_out_fmts(struct venus_inst *inst, u32 v4l2_fmt,
+			      u32 *out_fmt, u32 *out2_fmt, bool ubwc)
+{
+	struct venus_core *core = inst->core;
+	struct venus_caps *caps;
+	u32 ubwc_fmt, fmt = to_hfi_raw_fmt(v4l2_fmt);
+	bool found, found_ubwc;
+
+	*out_fmt = *out2_fmt = 0;
+
+	if (!fmt)
+		return -EINVAL;
+
+	caps = venus_caps_by_codec(core, inst->hfi_codec, inst->session_type);
+	if (!caps)
+		return -EINVAL;
+
+	if (ubwc) {
+		ubwc_fmt = fmt | HFI_COLOR_FORMAT_UBWC_BASE;
+		found_ubwc = find_fmt_from_caps(caps, HFI_BUFFER_OUTPUT,
+						ubwc_fmt);
+		found = find_fmt_from_caps(caps, HFI_BUFFER_OUTPUT2, fmt);
+
+		if (found_ubwc && found) {
+			*out_fmt = ubwc_fmt;
+			*out2_fmt = fmt;
+			return 0;
+		}
+	}
+
+	found = find_fmt_from_caps(caps, HFI_BUFFER_OUTPUT, fmt);
+	if (found) {
+		*out_fmt = fmt;
+		*out2_fmt = 0;
+		return 0;
+	}
+
+	found = find_fmt_from_caps(caps, HFI_BUFFER_OUTPUT2, fmt);
+	if (found) {
+		*out_fmt = 0;
+		*out2_fmt = fmt;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(venus_helper_get_out_fmts);
+
+int venus_helper_power_enable(struct venus_core *core, u32 session_type,
+			      bool enable)
+{
+	void __iomem *ctrl, *stat;
+	u32 val;
+	int ret;
+
+	if (!IS_V3(core) && !IS_V4(core))
+		return 0;
+
+	if (IS_V3(core)) {
+		if (session_type == VIDC_SESSION_TYPE_DEC)
+			ctrl = core->base + WRAPPER_VDEC_VCODEC_POWER_CONTROL;
+		else
+			ctrl = core->base + WRAPPER_VENC_VCODEC_POWER_CONTROL;
+		if (enable)
+			writel(0, ctrl);
+		else
+			writel(1, ctrl);
+
+		return 0;
+	}
+
+	if (session_type == VIDC_SESSION_TYPE_DEC) {
+		ctrl = core->base + WRAPPER_VCODEC0_MMCC_POWER_CONTROL;
+		stat = core->base + WRAPPER_VCODEC0_MMCC_POWER_STATUS;
+	} else {
+		ctrl = core->base + WRAPPER_VCODEC1_MMCC_POWER_CONTROL;
+		stat = core->base + WRAPPER_VCODEC1_MMCC_POWER_STATUS;
+	}
+
+	if (enable) {
+		writel(0, ctrl);
+
+		ret = readl_poll_timeout(stat, val, val & BIT(1), 1, 100);
+		if (ret)
+			return ret;
+	} else {
+		writel(1, ctrl);
+
+		ret = readl_poll_timeout(stat, val, !(val & BIT(1)), 1, 100);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(venus_helper_power_enable);
diff --git a/drivers/media/platform/qcom/venus/helpers.h b/drivers/media/platform/qcom/venus/helpers.h
index 971392be5df5..2475f284f396 100644
--- a/drivers/media/platform/qcom/venus/helpers.h
+++ b/drivers/media/platform/qcom/venus/helpers.h
@@ -33,14 +33,33 @@ void venus_helper_m2m_device_run(void *priv);
 void venus_helper_m2m_job_abort(void *priv);
 int venus_helper_get_bufreq(struct venus_inst *inst, u32 type,
 			    struct hfi_buffer_requirements *req);
+u32 venus_helper_get_framesz_raw(u32 hfi_fmt, u32 width, u32 height);
+u32 venus_helper_get_framesz(u32 v4l2_fmt, u32 width, u32 height);
 int venus_helper_set_input_resolution(struct venus_inst *inst,
 				      unsigned int width, unsigned int height);
 int venus_helper_set_output_resolution(struct venus_inst *inst,
-				       unsigned int width, unsigned int height);
+				       unsigned int width, unsigned int height,
+				       u32 buftype);
+int venus_helper_set_work_mode(struct venus_inst *inst, u32 mode);
+int venus_helper_set_core_usage(struct venus_inst *inst, u32 usage);
 int venus_helper_set_num_bufs(struct venus_inst *inst, unsigned int input_bufs,
-			      unsigned int output_bufs);
+			      unsigned int output_bufs,
+			      unsigned int output2_bufs);
+int venus_helper_set_raw_format(struct venus_inst *inst, u32 hfi_format,
+				u32 buftype);
 int venus_helper_set_color_format(struct venus_inst *inst, u32 fmt);
+int venus_helper_set_dyn_bufmode(struct venus_inst *inst);
+int venus_helper_set_bufsize(struct venus_inst *inst, u32 bufsize, u32 buftype);
+int venus_helper_set_multistream(struct venus_inst *inst, bool out_en,
+				 bool out2_en);
+unsigned int venus_helper_get_opb_size(struct venus_inst *inst);
 void venus_helper_acquire_buf_ref(struct vb2_v4l2_buffer *vbuf);
 void venus_helper_release_buf_ref(struct venus_inst *inst, unsigned int idx);
 void venus_helper_init_instance(struct venus_inst *inst);
+int venus_helper_get_out_fmts(struct venus_inst *inst, u32 fmt, u32 *out_fmt,
+			      u32 *out2_fmt, bool ubwc);
+int venus_helper_alloc_dpb_bufs(struct venus_inst *inst);
+int venus_helper_free_dpb_bufs(struct venus_inst *inst);
+int venus_helper_power_enable(struct venus_core *core, u32 session_type,
+			      bool enable);
 #endif
diff --git a/drivers/media/platform/qcom/venus/hfi.c b/drivers/media/platform/qcom/venus/hfi.c
index bca894a00c07..24207829982f 100644
--- a/drivers/media/platform/qcom/venus/hfi.c
+++ b/drivers/media/platform/qcom/venus/hfi.c
@@ -49,6 +49,8 @@ static u32 to_codec_type(u32 pixfmt)
 		return HFI_VIDEO_CODEC_VP9;
 	case V4L2_PIX_FMT_XVID:
 		return HFI_VIDEO_CODEC_DIVX;
+	case V4L2_PIX_FMT_HEVC:
+		return HFI_VIDEO_CODEC_HEVC;
 	default:
 		return 0;
 	}
@@ -203,13 +205,12 @@ int hfi_session_init(struct venus_inst *inst, u32 pixfmt)
 {
 	struct venus_core *core = inst->core;
 	const struct hfi_ops *ops = core->ops;
-	u32 codec;
 	int ret;
 
-	codec = to_codec_type(pixfmt);
+	inst->hfi_codec = to_codec_type(pixfmt);
 	reinit_completion(&inst->done);
 
-	ret = ops->session_init(inst, inst->session_type, codec);
+	ret = ops->session_init(inst, inst->session_type, inst->hfi_codec);
 	if (ret)
 		return ret;
 
@@ -312,7 +313,7 @@ int hfi_session_continue(struct venus_inst *inst)
 {
 	struct venus_core *core = inst->core;
 
-	if (core->res->hfi_version != HFI_VERSION_3XX)
+	if (core->res->hfi_version == HFI_VERSION_1XX)
 		return 0;
 
 	return core->ops->session_continue(inst);
@@ -473,7 +474,8 @@ int hfi_session_process_buf(struct venus_inst *inst, struct hfi_frame_data *fd)
 
 	if (fd->buffer_type == HFI_BUFFER_INPUT)
 		return ops->session_etb(inst, fd);
-	else if (fd->buffer_type == HFI_BUFFER_OUTPUT)
+	else if (fd->buffer_type == HFI_BUFFER_OUTPUT ||
+		 fd->buffer_type == HFI_BUFFER_OUTPUT2)
 		return ops->session_ftb(inst, fd);
 
 	return -EINVAL;
diff --git a/drivers/media/platform/qcom/venus/hfi.h b/drivers/media/platform/qcom/venus/hfi.h
index 5466b7d60dd0..6038d8e0ab22 100644
--- a/drivers/media/platform/qcom/venus/hfi.h
+++ b/drivers/media/platform/qcom/venus/hfi.h
@@ -74,6 +74,16 @@ struct hfi_event_data {
 	u32 tag;
 	u32 profile;
 	u32 level;
+	/* the following properties start appear from v4 onwards */
+	u32 bit_depth;
+	u32 pic_struct;
+	u32 colour_space;
+	u32 entropy_mode;
+	u32 buf_count;
+	struct {
+		u32 left, top;
+		u32 width, height;
+	} input_crop;
 };
 
 /* define core states */
diff --git a/drivers/media/platform/qcom/venus/hfi_cmds.c b/drivers/media/platform/qcom/venus/hfi_cmds.c
index 1cfeb7743041..e8389d8d8c48 100644
--- a/drivers/media/platform/qcom/venus/hfi_cmds.c
+++ b/drivers/media/platform/qcom/venus/hfi_cmds.c
@@ -1166,6 +1166,63 @@ pkt_session_set_property_3xx(struct hfi_session_set_property_pkt *pkt,
 	return ret;
 }
 
+static int
+pkt_session_set_property_4xx(struct hfi_session_set_property_pkt *pkt,
+			     void *cookie, u32 ptype, void *pdata)
+{
+	void *prop_data;
+
+	if (!pkt || !cookie || !pdata)
+		return -EINVAL;
+
+	prop_data = &pkt->data[1];
+
+	pkt->shdr.hdr.size = sizeof(*pkt);
+	pkt->shdr.hdr.pkt_type = HFI_CMD_SESSION_SET_PROPERTY;
+	pkt->shdr.session_id = hash32_ptr(cookie);
+	pkt->num_properties = 1;
+	pkt->data[0] = ptype;
+
+	/*
+	 * Any session set property which is different in 3XX packetization
+	 * should be added as a new case below. All unchanged session set
+	 * properties will be handled in the default case.
+	 */
+	switch (ptype) {
+	case HFI_PROPERTY_PARAM_BUFFER_COUNT_ACTUAL: {
+		struct hfi_buffer_count_actual *in = pdata;
+		struct hfi_buffer_count_actual_4xx *count = prop_data;
+
+		count->count_actual = in->count_actual;
+		count->type = in->type;
+		count->count_min_host = in->count_actual;
+		pkt->shdr.hdr.size += sizeof(u32) + sizeof(*count);
+		break;
+	}
+	case HFI_PROPERTY_PARAM_WORK_MODE: {
+		struct hfi_video_work_mode *in = pdata, *wm = prop_data;
+
+		wm->video_work_mode = in->video_work_mode;
+		pkt->shdr.hdr.size += sizeof(u32) + sizeof(*wm);
+		break;
+	}
+	case HFI_PROPERTY_CONFIG_VIDEOCORES_USAGE: {
+		struct hfi_videocores_usage_type *in = pdata, *cu = prop_data;
+
+		cu->video_core_enable_mask = in->video_core_enable_mask;
+		pkt->shdr.hdr.size += sizeof(u32) + sizeof(*cu);
+		break;
+	}
+	case HFI_PROPERTY_CONFIG_VENC_MAX_BITRATE:
+		/* not implemented on Venus 4xx */
+		break;
+	default:
+		return pkt_session_set_property_3xx(pkt, cookie, ptype, pdata);
+	}
+
+	return 0;
+}
+
 int pkt_session_get_property(struct hfi_session_get_property_pkt *pkt,
 			     void *cookie, u32 ptype)
 {
@@ -1181,7 +1238,10 @@ int pkt_session_set_property(struct hfi_session_set_property_pkt *pkt,
 	if (hfi_ver == HFI_VERSION_1XX)
 		return pkt_session_set_property_1x(pkt, cookie, ptype, pdata);
 
-	return pkt_session_set_property_3xx(pkt, cookie, ptype, pdata);
+	if (hfi_ver == HFI_VERSION_3XX)
+		return pkt_session_set_property_3xx(pkt, cookie, ptype, pdata);
+
+	return pkt_session_set_property_4xx(pkt, cookie, ptype, pdata);
 }
 
 void pkt_set_version(enum hfi_version version)
diff --git a/drivers/media/platform/qcom/venus/hfi_helper.h b/drivers/media/platform/qcom/venus/hfi_helper.h
index 55d8eb21403a..15804ad7e65d 100644
--- a/drivers/media/platform/qcom/venus/hfi_helper.h
+++ b/drivers/media/platform/qcom/venus/hfi_helper.h
@@ -121,6 +121,7 @@
 #define HFI_EXTRADATA_METADATA_FILLER			0x7fe00002
 
 #define HFI_INDEX_EXTRADATA_INPUT_CROP			0x0700000e
+#define HFI_INDEX_EXTRADATA_OUTPUT_CROP			0x0700000f
 #define HFI_INDEX_EXTRADATA_DIGITAL_ZOOM		0x07000010
 #define HFI_INDEX_EXTRADATA_ASPECT_RATIO		0x7f100003
 
@@ -376,13 +377,18 @@
 #define HFI_BUFFER_OUTPUT2			0x3
 #define HFI_BUFFER_INTERNAL_PERSIST		0x4
 #define HFI_BUFFER_INTERNAL_PERSIST_1		0x5
-#define HFI_BUFFER_INTERNAL_SCRATCH		0x1000001
-#define HFI_BUFFER_EXTRADATA_INPUT		0x1000002
-#define HFI_BUFFER_EXTRADATA_OUTPUT		0x1000003
-#define HFI_BUFFER_EXTRADATA_OUTPUT2		0x1000004
-#define HFI_BUFFER_INTERNAL_SCRATCH_1		0x1000005
-#define HFI_BUFFER_INTERNAL_SCRATCH_2		0x1000006
-
+#define HFI_BUFFER_INTERNAL_SCRATCH(ver)	\
+	(((ver) == HFI_VERSION_4XX) ? 0x6 : 0x1000001)
+#define HFI_BUFFER_INTERNAL_SCRATCH_1(ver)	\
+	(((ver) == HFI_VERSION_4XX) ? 0x7 : 0x1000005)
+#define HFI_BUFFER_INTERNAL_SCRATCH_2(ver)	\
+	(((ver) == HFI_VERSION_4XX) ? 0x8 : 0x1000006)
+#define HFI_BUFFER_EXTRADATA_INPUT(ver)		\
+	(((ver) == HFI_VERSION_4XX) ? 0xc : 0x1000002)
+#define HFI_BUFFER_EXTRADATA_OUTPUT(ver)	\
+	(((ver) == HFI_VERSION_4XX) ? 0xa : 0x1000003)
+#define HFI_BUFFER_EXTRADATA_OUTPUT2(ver)	\
+	(((ver) == HFI_VERSION_4XX) ? 0xb : 0x1000004)
 #define HFI_BUFFER_TYPE_MAX			11
 
 #define HFI_BUFFER_MODE_STATIC			0x1000001
@@ -424,12 +430,14 @@
 #define HFI_PROPERTY_PARAM_CODEC_MASK_SUPPORTED			0x100e
 #define HFI_PROPERTY_PARAM_MVC_BUFFER_LAYOUT			0x100f
 #define HFI_PROPERTY_PARAM_MAX_SESSIONS_SUPPORTED		0x1010
+#define HFI_PROPERTY_PARAM_WORK_MODE				0x1015
 
 /*
  * HFI_PROPERTY_CONFIG_COMMON_START
  * HFI_DOMAIN_BASE_COMMON + HFI_ARCH_COMMON_OFFSET + 0x2000
  */
 #define HFI_PROPERTY_CONFIG_FRAME_RATE				0x2001
+#define HFI_PROPERTY_CONFIG_VIDEOCORES_USAGE			0x2002
 
 /*
  * HFI_PROPERTY_PARAM_VDEC_COMMON_START
@@ -438,6 +446,9 @@
 #define HFI_PROPERTY_PARAM_VDEC_MULTI_STREAM			0x1003001
 #define HFI_PROPERTY_PARAM_VDEC_CONCEAL_COLOR			0x1003002
 #define HFI_PROPERTY_PARAM_VDEC_NONCP_OUTPUT2			0x1003003
+#define HFI_PROPERTY_PARAM_VDEC_PIXEL_BITDEPTH			0x1003007
+#define HFI_PROPERTY_PARAM_VDEC_PIC_STRUCT			0x1003009
+#define HFI_PROPERTY_PARAM_VDEC_COLOUR_SPACE			0x100300a
 
 /*
  * HFI_PROPERTY_CONFIG_VDEC_COMMON_START
@@ -518,6 +529,7 @@
 enum hfi_version {
 	HFI_VERSION_1XX,
 	HFI_VERSION_3XX,
+	HFI_VERSION_4XX
 };
 
 struct hfi_buffer_info {
@@ -767,12 +779,56 @@ struct hfi_framesize {
 	u32 height;
 };
 
+#define VIDC_CORE_ID_DEFAULT	0
+#define VIDC_CORE_ID_1		1
+#define VIDC_CORE_ID_2		2
+#define VIDC_CORE_ID_3		3
+
+struct hfi_videocores_usage_type {
+	u32 video_core_enable_mask;
+};
+
+#define VIDC_WORK_MODE_1	1
+#define VIDC_WORK_MODE_2	2
+
+struct hfi_video_work_mode {
+	u32 video_work_mode;
+};
+
 struct hfi_h264_vui_timing_info {
 	u32 enable;
 	u32 fixed_framerate;
 	u32 time_scale;
 };
 
+struct hfi_bit_depth {
+	u32 buffer_type;
+	u32 bit_depth;
+};
+
+struct hfi_picture_type {
+	u32 is_sync_frame;
+	u32 picture_type;
+};
+
+struct hfi_pic_struct {
+	u32 progressive_only;
+};
+
+struct hfi_colour_space {
+	u32 colour_space;
+};
+
+struct hfi_extradata_input_crop {
+	u32 size;
+	u32 version;
+	u32 port_index;
+	u32 left;
+	u32 top;
+	u32 width;
+	u32 height;
+};
+
 #define HFI_COLOR_FORMAT_MONOCHROME		0x01
 #define HFI_COLOR_FORMAT_NV12			0x02
 #define HFI_COLOR_FORMAT_NV21			0x03
@@ -802,10 +858,23 @@ struct hfi_uncompressed_format_select {
 	u32 format;
 };
 
+struct hfi_uncompressed_plane_constraints {
+	u32 stride_multiples;
+	u32 max_stride;
+	u32 min_plane_buffer_height_multiple;
+	u32 buffer_alignment;
+};
+
+struct hfi_uncompressed_plane_info {
+	u32 format;
+	u32 num_planes;
+	struct hfi_uncompressed_plane_constraints plane_constraints[1];
+};
+
 struct hfi_uncompressed_format_supported {
 	u32 buffer_type;
 	u32 format_entries;
-	u32 format_info[1];
+	struct hfi_uncompressed_plane_info plane_info[1];
 };
 
 struct hfi_uncompressed_plane_actual {
@@ -819,19 +888,6 @@ struct hfi_uncompressed_plane_actual_info {
 	struct hfi_uncompressed_plane_actual plane_format[1];
 };
 
-struct hfi_uncompressed_plane_constraints {
-	u32 stride_multiples;
-	u32 max_stride;
-	u32 min_plane_buffer_height_multiple;
-	u32 buffer_alignment;
-};
-
-struct hfi_uncompressed_plane_info {
-	u32 format;
-	u32 num_planes;
-	struct hfi_uncompressed_plane_constraints plane_format[1];
-};
-
 struct hfi_uncompressed_plane_actual_constraints_info {
 	u32 buffer_type;
 	u32 num_planes;
@@ -961,6 +1017,12 @@ struct hfi_buffer_count_actual {
 	u32 count_actual;
 };
 
+struct hfi_buffer_count_actual_4xx {
+	u32 type;
+	u32 count_actual;
+	u32 count_min_host;
+};
+
 struct hfi_buffer_size_actual {
 	u32 type;
 	u32 size;
@@ -971,6 +1033,14 @@ struct hfi_buffer_display_hold_count_actual {
 	u32 hold_count;
 };
 
+/* HFI 4XX reorder the fields, use these macros */
+#define HFI_BUFREQ_HOLD_COUNT(bufreq, ver)	\
+	((ver) == HFI_VERSION_4XX ? 0 : (bufreq)->hold_count)
+#define HFI_BUFREQ_COUNT_MIN(bufreq, ver)	\
+	((ver) == HFI_VERSION_4XX ? (bufreq)->hold_count : (bufreq)->count_min)
+#define HFI_BUFREQ_COUNT_MIN_HOST(bufreq, ver)	\
+	((ver) == HFI_VERSION_4XX ? (bufreq)->count_min : 0)
+
 struct hfi_buffer_requirements {
 	u32 type;
 	u32 size;
diff --git a/drivers/media/platform/qcom/venus/hfi_msgs.c b/drivers/media/platform/qcom/venus/hfi_msgs.c
index 90c93d9603dc..0ecdaa15c296 100644
--- a/drivers/media/platform/qcom/venus/hfi_msgs.c
+++ b/drivers/media/platform/qcom/venus/hfi_msgs.c
@@ -21,14 +21,21 @@
 #include "hfi.h"
 #include "hfi_helper.h"
 #include "hfi_msgs.h"
+#include "hfi_parser.h"
 
 static void event_seq_changed(struct venus_core *core, struct venus_inst *inst,
 			      struct hfi_msg_event_notify_pkt *pkt)
 {
+	enum hfi_version ver = core->res->hfi_version;
 	struct hfi_event_data event = {0};
 	int num_properties_changed;
 	struct hfi_framesize *frame_sz;
 	struct hfi_profile_level *profile_level;
+	struct hfi_bit_depth *pixel_depth;
+	struct hfi_pic_struct *pic_struct;
+	struct hfi_colour_space *colour_info;
+	struct hfi_buffer_requirements *bufreq;
+	struct hfi_extradata_input_crop *crop;
 	u8 *data_ptr;
 	u32 ptype;
 
@@ -60,14 +67,52 @@ static void event_seq_changed(struct venus_core *core, struct venus_inst *inst,
 			frame_sz = (struct hfi_framesize *)data_ptr;
 			event.width = frame_sz->width;
 			event.height = frame_sz->height;
-			data_ptr += sizeof(frame_sz);
+			data_ptr += sizeof(*frame_sz);
 			break;
 		case HFI_PROPERTY_PARAM_PROFILE_LEVEL_CURRENT:
 			data_ptr += sizeof(u32);
 			profile_level = (struct hfi_profile_level *)data_ptr;
 			event.profile = profile_level->profile;
 			event.level = profile_level->level;
-			data_ptr += sizeof(profile_level);
+			data_ptr += sizeof(*profile_level);
+			break;
+		case HFI_PROPERTY_PARAM_VDEC_PIXEL_BITDEPTH:
+			data_ptr += sizeof(u32);
+			pixel_depth = (struct hfi_bit_depth *)data_ptr;
+			event.bit_depth = pixel_depth->bit_depth;
+			data_ptr += sizeof(*pixel_depth);
+			break;
+		case HFI_PROPERTY_PARAM_VDEC_PIC_STRUCT:
+			data_ptr += sizeof(u32);
+			pic_struct = (struct hfi_pic_struct *)data_ptr;
+			event.pic_struct = pic_struct->progressive_only;
+			data_ptr += sizeof(*pic_struct);
+			break;
+		case HFI_PROPERTY_PARAM_VDEC_COLOUR_SPACE:
+			data_ptr += sizeof(u32);
+			colour_info = (struct hfi_colour_space *)data_ptr;
+			event.colour_space = colour_info->colour_space;
+			data_ptr += sizeof(*colour_info);
+			break;
+		case HFI_PROPERTY_CONFIG_VDEC_ENTROPY:
+			data_ptr += sizeof(u32);
+			event.entropy_mode = *(u32 *)data_ptr;
+			data_ptr += sizeof(u32);
+			break;
+		case HFI_PROPERTY_CONFIG_BUFFER_REQUIREMENTS:
+			data_ptr += sizeof(u32);
+			bufreq = (struct hfi_buffer_requirements *)data_ptr;
+			event.buf_count = HFI_BUFREQ_COUNT_MIN(bufreq, ver);
+			data_ptr += sizeof(*bufreq);
+			break;
+		case HFI_INDEX_EXTRADATA_INPUT_CROP:
+			data_ptr += sizeof(u32);
+			crop = (struct hfi_extradata_input_crop *)data_ptr;
+			event.input_crop.left = crop->left;
+			event.input_crop.top = crop->top;
+			event.input_crop.width = crop->width;
+			event.input_crop.height = crop->height;
+			data_ptr += sizeof(*crop);
 			break;
 		default:
 			break;
@@ -173,81 +218,28 @@ static void hfi_sys_init_done(struct venus_core *core, struct venus_inst *inst,
 			      void *packet)
 {
 	struct hfi_msg_sys_init_done_pkt *pkt = packet;
-	u32 rem_bytes, read_bytes = 0, num_properties;
-	u32 error, ptype;
-	u8 *data;
+	int rem_bytes;
+	u32 error;
 
 	error = pkt->error_type;
 	if (error != HFI_ERR_NONE)
-		goto err_no_prop;
-
-	num_properties = pkt->num_properties;
+		goto done;
 
-	if (!num_properties) {
+	if (!pkt->num_properties) {
 		error = HFI_ERR_SYS_INVALID_PARAMETER;
-		goto err_no_prop;
+		goto done;
 	}
 
 	rem_bytes = pkt->hdr.size - sizeof(*pkt) + sizeof(u32);
-
-	if (!rem_bytes) {
+	if (rem_bytes <= 0) {
 		/* missing property data */
 		error = HFI_ERR_SYS_INSUFFICIENT_RESOURCES;
-		goto err_no_prop;
+		goto done;
 	}
 
-	data = (u8 *)&pkt->data[0];
-
-	if (core->res->hfi_version == HFI_VERSION_3XX)
-		goto err_no_prop;
-
-	while (num_properties && rem_bytes >= sizeof(u32)) {
-		ptype = *((u32 *)data);
-		data += sizeof(u32);
+	error = hfi_parser(core, inst, pkt->data, rem_bytes);
 
-		switch (ptype) {
-		case HFI_PROPERTY_PARAM_CODEC_SUPPORTED: {
-			struct hfi_codec_supported *prop;
-
-			prop = (struct hfi_codec_supported *)data;
-
-			if (rem_bytes < sizeof(*prop)) {
-				error = HFI_ERR_SYS_INSUFFICIENT_RESOURCES;
-				break;
-			}
-
-			read_bytes += sizeof(*prop) + sizeof(u32);
-			core->dec_codecs = prop->dec_codecs;
-			core->enc_codecs = prop->enc_codecs;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_MAX_SESSIONS_SUPPORTED: {
-			struct hfi_max_sessions_supported *prop;
-
-			if (rem_bytes < sizeof(*prop)) {
-				error = HFI_ERR_SYS_INSUFFICIENT_RESOURCES;
-				break;
-			}
-
-			prop = (struct hfi_max_sessions_supported *)data;
-			read_bytes += sizeof(*prop) + sizeof(u32);
-			core->max_sessions_supported = prop->max_sessions;
-			break;
-		}
-		default:
-			error = HFI_ERR_SYS_INVALID_PARAMETER;
-			break;
-		}
-
-		if (error)
-			break;
-
-		rem_bytes -= read_bytes;
-		data += read_bytes;
-		num_properties--;
-	}
-
-err_no_prop:
+done:
 	core->error = error;
 	complete(&core->done);
 }
@@ -325,51 +317,6 @@ static void hfi_sys_pc_prepare_done(struct venus_core *core,
 	dev_dbg(core->dev, "pc prepare done (error %x)\n", pkt->error_type);
 }
 
-static void
-hfi_copy_cap_prop(struct hfi_capability *in, struct venus_inst *inst)
-{
-	if (!in || !inst)
-		return;
-
-	switch (in->capability_type) {
-	case HFI_CAPABILITY_FRAME_WIDTH:
-		inst->cap_width = *in;
-		break;
-	case HFI_CAPABILITY_FRAME_HEIGHT:
-		inst->cap_height = *in;
-		break;
-	case HFI_CAPABILITY_MBS_PER_FRAME:
-		inst->cap_mbs_per_frame = *in;
-		break;
-	case HFI_CAPABILITY_MBS_PER_SECOND:
-		inst->cap_mbs_per_sec = *in;
-		break;
-	case HFI_CAPABILITY_FRAMERATE:
-		inst->cap_framerate = *in;
-		break;
-	case HFI_CAPABILITY_SCALE_X:
-		inst->cap_scale_x = *in;
-		break;
-	case HFI_CAPABILITY_SCALE_Y:
-		inst->cap_scale_y = *in;
-		break;
-	case HFI_CAPABILITY_BITRATE:
-		inst->cap_bitrate = *in;
-		break;
-	case HFI_CAPABILITY_HIER_P_NUM_ENH_LAYERS:
-		inst->cap_hier_p = *in;
-		break;
-	case HFI_CAPABILITY_ENC_LTR_COUNT:
-		inst->cap_ltr_count = *in;
-		break;
-	case HFI_CAPABILITY_CP_OUTPUT2_THRESH:
-		inst->cap_secure_output2_threshold = *in;
-		break;
-	default:
-		break;
-	}
-}
-
 static unsigned int
 session_get_prop_profile_level(struct hfi_msg_session_property_info_pkt *pkt,
 			       struct hfi_profile_level *profile_level)
@@ -459,248 +406,27 @@ done:
 	complete(&inst->done);
 }
 
-static u32 init_done_read_prop(struct venus_core *core, struct venus_inst *inst,
-			       struct hfi_msg_session_init_done_pkt *pkt)
-{
-	struct device *dev = core->dev;
-	u32 rem_bytes, num_props;
-	u32 ptype, next_offset = 0;
-	u32 err;
-	u8 *data;
-
-	rem_bytes = pkt->shdr.hdr.size - sizeof(*pkt) + sizeof(u32);
-	if (!rem_bytes) {
-		dev_err(dev, "%s: missing property info\n", __func__);
-		return HFI_ERR_SESSION_INSUFFICIENT_RESOURCES;
-	}
-
-	err = pkt->error_type;
-	if (err)
-		return err;
-
-	data = (u8 *)&pkt->data[0];
-	num_props = pkt->num_properties;
-
-	while (err == HFI_ERR_NONE && num_props && rem_bytes >= sizeof(u32)) {
-		ptype = *((u32 *)data);
-		next_offset = sizeof(u32);
-
-		switch (ptype) {
-		case HFI_PROPERTY_PARAM_CODEC_MASK_SUPPORTED: {
-			struct hfi_codec_mask_supported *masks =
-				(struct hfi_codec_mask_supported *)
-				(data + next_offset);
-
-			next_offset += sizeof(*masks);
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_CAPABILITY_SUPPORTED: {
-			struct hfi_capabilities *caps;
-			struct hfi_capability *cap;
-			u32 num_caps;
-
-			if ((rem_bytes - next_offset) < sizeof(*cap)) {
-				err = HFI_ERR_SESSION_INVALID_PARAMETER;
-				break;
-			}
-
-			caps = (struct hfi_capabilities *)(data + next_offset);
-
-			num_caps = caps->num_capabilities;
-			cap = &caps->data[0];
-			next_offset += sizeof(u32);
-
-			while (num_caps &&
-			       (rem_bytes - next_offset) >= sizeof(u32)) {
-				hfi_copy_cap_prop(cap, inst);
-				cap++;
-				next_offset += sizeof(*cap);
-				num_caps--;
-			}
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_UNCOMPRESSED_FORMAT_SUPPORTED: {
-			struct hfi_uncompressed_format_supported *prop =
-				(struct hfi_uncompressed_format_supported *)
-				(data + next_offset);
-			u32 num_fmt_entries;
-			u8 *fmt;
-			struct hfi_uncompressed_plane_info *inf;
-
-			if ((rem_bytes - next_offset) < sizeof(*prop)) {
-				err = HFI_ERR_SESSION_INVALID_PARAMETER;
-				break;
-			}
-
-			num_fmt_entries = prop->format_entries;
-			next_offset = sizeof(*prop) - sizeof(u32);
-			fmt = (u8 *)&prop->format_info[0];
-
-			dev_dbg(dev, "uncomm format support num entries:%u\n",
-				num_fmt_entries);
-
-			while (num_fmt_entries) {
-				struct hfi_uncompressed_plane_constraints *cnts;
-				u32 bytes_to_skip;
-
-				inf = (struct hfi_uncompressed_plane_info *)fmt;
-
-				if ((rem_bytes - next_offset) < sizeof(*inf)) {
-					err = HFI_ERR_SESSION_INVALID_PARAMETER;
-					break;
-				}
-
-				dev_dbg(dev, "plane info: fmt:%x, planes:%x\n",
-					inf->format, inf->num_planes);
-
-				cnts = &inf->plane_format[0];
-				dev_dbg(dev, "%u %u %u %u\n",
-					cnts->stride_multiples,
-					cnts->max_stride,
-					cnts->min_plane_buffer_height_multiple,
-					cnts->buffer_alignment);
-
-				bytes_to_skip = sizeof(*inf) - sizeof(*cnts) +
-						inf->num_planes * sizeof(*cnts);
-
-				fmt += bytes_to_skip;
-				next_offset += bytes_to_skip;
-				num_fmt_entries--;
-			}
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_PROPERTIES_SUPPORTED: {
-			struct hfi_properties_supported *prop =
-				(struct hfi_properties_supported *)
-				(data + next_offset);
-
-			next_offset += sizeof(*prop) - sizeof(u32)
-					+ prop->num_properties * sizeof(u32);
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_PROFILE_LEVEL_SUPPORTED: {
-			struct hfi_profile_level_supported *prop =
-				(struct hfi_profile_level_supported *)
-				(data + next_offset);
-			struct hfi_profile_level *pl;
-			unsigned int prop_count = 0;
-			unsigned int count = 0;
-			u8 *ptr;
-
-			ptr = (u8 *)&prop->profile_level[0];
-			prop_count = prop->profile_count;
-
-			if (prop_count > HFI_MAX_PROFILE_COUNT)
-				prop_count = HFI_MAX_PROFILE_COUNT;
-
-			while (prop_count) {
-				ptr++;
-				pl = (struct hfi_profile_level *)ptr;
-
-				inst->pl[count].profile = pl->profile;
-				inst->pl[count].level = pl->level;
-				prop_count--;
-				count++;
-				ptr += sizeof(*pl) / sizeof(u32);
-			}
-
-			inst->pl_count = count;
-			next_offset += sizeof(*prop) - sizeof(*pl) +
-				       prop->profile_count * sizeof(*pl);
-
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_INTERLACE_FORMAT_SUPPORTED: {
-			next_offset +=
-				sizeof(struct hfi_interlace_format_supported);
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_NAL_STREAM_FORMAT_SUPPORTED: {
-			struct hfi_nal_stream_format *nal =
-				(struct hfi_nal_stream_format *)
-				(data + next_offset);
-			dev_dbg(dev, "NAL format: %x\n", nal->format);
-			next_offset += sizeof(*nal);
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_NAL_STREAM_FORMAT_SELECT: {
-			next_offset += sizeof(u32);
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_MAX_SEQUENCE_HEADER_SIZE: {
-			u32 *max_seq_sz = (u32 *)(data + next_offset);
-
-			dev_dbg(dev, "max seq header sz: %x\n", *max_seq_sz);
-			next_offset += sizeof(u32);
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_VENC_INTRA_REFRESH: {
-			next_offset += sizeof(struct hfi_intra_refresh);
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_BUFFER_ALLOC_MODE_SUPPORTED: {
-			struct hfi_buffer_alloc_mode_supported *prop =
-				(struct hfi_buffer_alloc_mode_supported *)
-				(data + next_offset);
-			unsigned int i;
-
-			for (i = 0; i < prop->num_entries; i++) {
-				if (prop->buffer_type == HFI_BUFFER_OUTPUT ||
-				    prop->buffer_type == HFI_BUFFER_OUTPUT2) {
-					switch (prop->data[i]) {
-					case HFI_BUFFER_MODE_STATIC:
-						inst->cap_bufs_mode_static = true;
-						break;
-					case HFI_BUFFER_MODE_DYNAMIC:
-						inst->cap_bufs_mode_dynamic = true;
-						break;
-					default:
-						break;
-					}
-				}
-			}
-			next_offset += sizeof(*prop) -
-				sizeof(u32) + prop->num_entries * sizeof(u32);
-			num_props--;
-			break;
-		}
-		default:
-			dev_dbg(dev, "%s: default case %#x\n", __func__, ptype);
-			break;
-		}
-
-		rem_bytes -= next_offset;
-		data += next_offset;
-	}
-
-	return err;
-}
-
 static void hfi_session_init_done(struct venus_core *core,
 				  struct venus_inst *inst, void *packet)
 {
 	struct hfi_msg_session_init_done_pkt *pkt = packet;
-	unsigned int error;
+	int rem_bytes;
+	u32 error;
 
 	error = pkt->error_type;
 	if (error != HFI_ERR_NONE)
 		goto done;
 
-	if (core->res->hfi_version != HFI_VERSION_1XX)
+	if (!IS_V1(core))
 		goto done;
 
-	error = init_done_read_prop(core, inst, pkt);
+	rem_bytes = pkt->shdr.hdr.size - sizeof(*pkt) + sizeof(u32);
+	if (rem_bytes <= 0) {
+		error = HFI_ERR_SESSION_INSUFFICIENT_RESOURCES;
+		goto done;
+	}
 
+	error = hfi_parser(core, inst, pkt->data, rem_bytes);
 done:
 	inst->error = error;
 	complete(&inst->done);
@@ -779,7 +505,8 @@ static void hfi_session_ftb_done(struct venus_core *core,
 		error = HFI_ERR_SESSION_INVALID_PARAMETER;
 	}
 
-	if (buffer_type != HFI_BUFFER_OUTPUT)
+	if (buffer_type != HFI_BUFFER_OUTPUT &&
+	    buffer_type != HFI_BUFFER_OUTPUT2)
 		goto done;
 
 	if (hfi_flags & HFI_BUFFERFLAG_EOS)
diff --git a/drivers/media/platform/qcom/venus/hfi_parser.c b/drivers/media/platform/qcom/venus/hfi_parser.c
new file mode 100644
index 000000000000..2293d936e49c
--- /dev/null
+++ b/drivers/media/platform/qcom/venus/hfi_parser.c
@@ -0,0 +1,278 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Linaro Ltd.
+ *
+ * Author: Stanimir Varbanov <stanimir.varbanov@linaro.org>
+ */
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+
+#include "core.h"
+#include "hfi_helper.h"
+#include "hfi_parser.h"
+
+typedef void (*func)(struct venus_caps *cap, const void *data,
+		     unsigned int size);
+
+static void init_codecs(struct venus_core *core)
+{
+	struct venus_caps *caps = core->caps, *cap;
+	unsigned long bit;
+
+	for_each_set_bit(bit, &core->dec_codecs, MAX_CODEC_NUM) {
+		cap = &caps[core->codecs_count++];
+		cap->codec = BIT(bit);
+		cap->domain = VIDC_SESSION_TYPE_DEC;
+		cap->valid = false;
+	}
+
+	for_each_set_bit(bit, &core->enc_codecs, MAX_CODEC_NUM) {
+		cap = &caps[core->codecs_count++];
+		cap->codec = BIT(bit);
+		cap->domain = VIDC_SESSION_TYPE_ENC;
+		cap->valid = false;
+	}
+}
+
+static void for_each_codec(struct venus_caps *caps, unsigned int caps_num,
+			   u32 codecs, u32 domain, func cb, void *data,
+			   unsigned int size)
+{
+	struct venus_caps *cap;
+	unsigned int i;
+
+	for (i = 0; i < caps_num; i++) {
+		cap = &caps[i];
+		if (cap->valid && cap->domain == domain)
+			continue;
+		if (cap->codec & codecs && cap->domain == domain)
+			cb(cap, data, size);
+	}
+}
+
+static void
+fill_buf_mode(struct venus_caps *cap, const void *data, unsigned int num)
+{
+	const u32 *type = data;
+
+	if (*type == HFI_BUFFER_MODE_DYNAMIC)
+		cap->cap_bufs_mode_dynamic = true;
+}
+
+static void
+parse_alloc_mode(struct venus_core *core, u32 codecs, u32 domain, void *data)
+{
+	struct hfi_buffer_alloc_mode_supported *mode = data;
+	u32 num_entries = mode->num_entries;
+	u32 *type;
+
+	if (num_entries > MAX_ALLOC_MODE_ENTRIES)
+		return;
+
+	type = mode->data;
+
+	while (num_entries--) {
+		if (mode->buffer_type == HFI_BUFFER_OUTPUT ||
+		    mode->buffer_type == HFI_BUFFER_OUTPUT2)
+			for_each_codec(core->caps, ARRAY_SIZE(core->caps),
+				       codecs, domain, fill_buf_mode, type, 1);
+
+		type++;
+	}
+}
+
+static void fill_profile_level(struct venus_caps *cap, const void *data,
+			       unsigned int num)
+{
+	const struct hfi_profile_level *pl = data;
+
+	memcpy(&cap->pl[cap->num_pl], pl, num * sizeof(*pl));
+	cap->num_pl += num;
+}
+
+static void
+parse_profile_level(struct venus_core *core, u32 codecs, u32 domain, void *data)
+{
+	struct hfi_profile_level_supported *pl = data;
+	struct hfi_profile_level *proflevel = pl->profile_level;
+	struct hfi_profile_level pl_arr[HFI_MAX_PROFILE_COUNT] = {};
+
+	if (pl->profile_count > HFI_MAX_PROFILE_COUNT)
+		return;
+
+	memcpy(pl_arr, proflevel, pl->profile_count * sizeof(*proflevel));
+
+	for_each_codec(core->caps, ARRAY_SIZE(core->caps), codecs, domain,
+		       fill_profile_level, pl_arr, pl->profile_count);
+}
+
+static void
+fill_caps(struct venus_caps *cap, const void *data, unsigned int num)
+{
+	const struct hfi_capability *caps = data;
+
+	memcpy(&cap->caps[cap->num_caps], caps, num * sizeof(*caps));
+	cap->num_caps += num;
+}
+
+static void
+parse_caps(struct venus_core *core, u32 codecs, u32 domain, void *data)
+{
+	struct hfi_capabilities *caps = data;
+	struct hfi_capability *cap = caps->data;
+	u32 num_caps = caps->num_capabilities;
+	struct hfi_capability caps_arr[MAX_CAP_ENTRIES] = {};
+
+	if (num_caps > MAX_CAP_ENTRIES)
+		return;
+
+	memcpy(caps_arr, cap, num_caps * sizeof(*cap));
+
+	for_each_codec(core->caps, ARRAY_SIZE(core->caps), codecs, domain,
+		       fill_caps, caps_arr, num_caps);
+}
+
+static void fill_raw_fmts(struct venus_caps *cap, const void *fmts,
+			  unsigned int num_fmts)
+{
+	const struct raw_formats *formats = fmts;
+
+	memcpy(&cap->fmts[cap->num_fmts], formats, num_fmts * sizeof(*formats));
+	cap->num_fmts += num_fmts;
+}
+
+static void
+parse_raw_formats(struct venus_core *core, u32 codecs, u32 domain, void *data)
+{
+	struct hfi_uncompressed_format_supported *fmt = data;
+	struct hfi_uncompressed_plane_info *pinfo = fmt->plane_info;
+	struct hfi_uncompressed_plane_constraints *constr;
+	struct raw_formats rawfmts[MAX_FMT_ENTRIES] = {};
+	u32 entries = fmt->format_entries;
+	unsigned int i = 0;
+	u32 num_planes;
+
+	while (entries) {
+		num_planes = pinfo->num_planes;
+
+		rawfmts[i].fmt = pinfo->format;
+		rawfmts[i].buftype = fmt->buffer_type;
+		i++;
+
+		if (pinfo->num_planes > MAX_PLANES)
+			break;
+
+		pinfo = (void *)pinfo + sizeof(*constr) * num_planes +
+			2 * sizeof(u32);
+		entries--;
+	}
+
+	for_each_codec(core->caps, ARRAY_SIZE(core->caps), codecs, domain,
+		       fill_raw_fmts, rawfmts, i);
+}
+
+static void parse_codecs(struct venus_core *core, void *data)
+{
+	struct hfi_codec_supported *codecs = data;
+
+	core->dec_codecs = codecs->dec_codecs;
+	core->enc_codecs = codecs->enc_codecs;
+
+	if (IS_V1(core)) {
+		core->dec_codecs &= ~HFI_VIDEO_CODEC_HEVC;
+		core->dec_codecs &= ~HFI_VIDEO_CODEC_SPARK;
+	}
+}
+
+static void parse_max_sessions(struct venus_core *core, const void *data)
+{
+	const struct hfi_max_sessions_supported *sessions = data;
+
+	core->max_sessions_supported = sessions->max_sessions;
+}
+
+static void parse_codecs_mask(u32 *codecs, u32 *domain, void *data)
+{
+	struct hfi_codec_mask_supported *mask = data;
+
+	*codecs = mask->codecs;
+	*domain = mask->video_domains;
+}
+
+static void parser_init(struct venus_inst *inst, u32 *codecs, u32 *domain)
+{
+	if (!inst || !IS_V1(inst->core))
+		return;
+
+	*codecs = inst->hfi_codec;
+	*domain = inst->session_type;
+}
+
+static void parser_fini(struct venus_inst *inst, u32 codecs, u32 domain)
+{
+	struct venus_caps *caps, *cap;
+	unsigned int i;
+	u32 dom;
+
+	if (!inst || !IS_V1(inst->core))
+		return;
+
+	caps = inst->core->caps;
+	dom = inst->session_type;
+
+	for (i = 0; i < MAX_CODEC_NUM; i++) {
+		cap = &caps[i];
+		if (cap->codec & codecs && cap->domain == dom)
+			cap->valid = true;
+	}
+}
+
+u32 hfi_parser(struct venus_core *core, struct venus_inst *inst, void *buf,
+	       u32 size)
+{
+	unsigned int words_count = size >> 2;
+	u32 *word = buf, *data, codecs = 0, domain = 0;
+
+	if (size % 4)
+		return HFI_ERR_SYS_INSUFFICIENT_RESOURCES;
+
+	parser_init(inst, &codecs, &domain);
+
+	while (words_count) {
+		data = word + 1;
+
+		switch (*word) {
+		case HFI_PROPERTY_PARAM_CODEC_SUPPORTED:
+			parse_codecs(core, data);
+			init_codecs(core);
+			break;
+		case HFI_PROPERTY_PARAM_MAX_SESSIONS_SUPPORTED:
+			parse_max_sessions(core, data);
+			break;
+		case HFI_PROPERTY_PARAM_CODEC_MASK_SUPPORTED:
+			parse_codecs_mask(&codecs, &domain, data);
+			break;
+		case HFI_PROPERTY_PARAM_UNCOMPRESSED_FORMAT_SUPPORTED:
+			parse_raw_formats(core, codecs, domain, data);
+			break;
+		case HFI_PROPERTY_PARAM_CAPABILITY_SUPPORTED:
+			parse_caps(core, codecs, domain, data);
+			break;
+		case HFI_PROPERTY_PARAM_PROFILE_LEVEL_SUPPORTED:
+			parse_profile_level(core, codecs, domain, data);
+			break;
+		case HFI_PROPERTY_PARAM_BUFFER_ALLOC_MODE_SUPPORTED:
+			parse_alloc_mode(core, codecs, domain, data);
+			break;
+		default:
+			break;
+		}
+
+		word++;
+		words_count--;
+	}
+
+	parser_fini(inst, codecs, domain);
+
+	return HFI_ERR_NONE;
+}
diff --git a/drivers/media/platform/qcom/venus/hfi_parser.h b/drivers/media/platform/qcom/venus/hfi_parser.h
new file mode 100644
index 000000000000..3e931c747e19
--- /dev/null
+++ b/drivers/media/platform/qcom/venus/hfi_parser.h
@@ -0,0 +1,110 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2018 Linaro Ltd. */
+#ifndef __VENUS_HFI_PARSER_H__
+#define __VENUS_HFI_PARSER_H__
+
+#include "core.h"
+
+u32 hfi_parser(struct venus_core *core, struct venus_inst *inst,
+	       void *buf, u32 size);
+
+#define WHICH_CAP_MIN	0
+#define WHICH_CAP_MAX	1
+#define WHICH_CAP_STEP	2
+
+static inline u32 get_cap(struct venus_inst *inst, u32 type, u32 which)
+{
+	struct venus_core *core = inst->core;
+	struct hfi_capability *cap = NULL;
+	struct venus_caps *caps;
+	unsigned int i;
+
+	caps = venus_caps_by_codec(core, inst->hfi_codec, inst->session_type);
+	if (!caps)
+		return 0;
+
+	for (i = 0; i < caps->num_caps; i++) {
+		if (caps->caps[i].capability_type == type) {
+			cap = &caps->caps[i];
+			break;
+		}
+	}
+
+	if (!cap)
+		return 0;
+
+	switch (which) {
+	case WHICH_CAP_MIN:
+		return cap->min;
+	case WHICH_CAP_MAX:
+		return cap->max;
+	case WHICH_CAP_STEP:
+		return cap->step_size;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static inline u32 cap_min(struct venus_inst *inst, u32 type)
+{
+	return get_cap(inst, type, WHICH_CAP_MIN);
+}
+
+static inline u32 cap_max(struct venus_inst *inst, u32 type)
+{
+	return get_cap(inst, type, WHICH_CAP_MAX);
+}
+
+static inline u32 cap_step(struct venus_inst *inst, u32 type)
+{
+	return get_cap(inst, type, WHICH_CAP_STEP);
+}
+
+static inline u32 frame_width_min(struct venus_inst *inst)
+{
+	return cap_min(inst, HFI_CAPABILITY_FRAME_WIDTH);
+}
+
+static inline u32 frame_width_max(struct venus_inst *inst)
+{
+	return cap_max(inst, HFI_CAPABILITY_FRAME_WIDTH);
+}
+
+static inline u32 frame_width_step(struct venus_inst *inst)
+{
+	return cap_step(inst, HFI_CAPABILITY_FRAME_WIDTH);
+}
+
+static inline u32 frame_height_min(struct venus_inst *inst)
+{
+	return cap_min(inst, HFI_CAPABILITY_FRAME_HEIGHT);
+}
+
+static inline u32 frame_height_max(struct venus_inst *inst)
+{
+	return cap_max(inst, HFI_CAPABILITY_FRAME_HEIGHT);
+}
+
+static inline u32 frame_height_step(struct venus_inst *inst)
+{
+	return cap_step(inst, HFI_CAPABILITY_FRAME_HEIGHT);
+}
+
+static inline u32 frate_min(struct venus_inst *inst)
+{
+	return cap_min(inst, HFI_CAPABILITY_FRAMERATE);
+}
+
+static inline u32 frate_max(struct venus_inst *inst)
+{
+	return cap_max(inst, HFI_CAPABILITY_FRAMERATE);
+}
+
+static inline u32 frate_step(struct venus_inst *inst)
+{
+	return cap_step(inst, HFI_CAPABILITY_FRAMERATE);
+}
+
+#endif
diff --git a/drivers/media/platform/qcom/venus/hfi_venus.c b/drivers/media/platform/qcom/venus/hfi_venus.c
index 734ce11b0ed0..124085556b94 100644
--- a/drivers/media/platform/qcom/venus/hfi_venus.c
+++ b/drivers/media/platform/qcom/venus/hfi_venus.c
@@ -532,6 +532,24 @@ static int venus_halt_axi(struct venus_hfi_device *hdev)
 	u32 val;
 	int ret;
 
+	if (IS_V4(hdev->core)) {
+		val = venus_readl(hdev, WRAPPER_CPU_AXI_HALT);
+		val |= WRAPPER_CPU_AXI_HALT_HALT;
+		venus_writel(hdev, WRAPPER_CPU_AXI_HALT, val);
+
+		ret = readl_poll_timeout(base + WRAPPER_CPU_AXI_HALT_STATUS,
+					 val,
+					 val & WRAPPER_CPU_AXI_HALT_STATUS_IDLE,
+					 POLL_INTERVAL_US,
+					 VBIF_AXI_HALT_ACK_TIMEOUT_US);
+		if (ret) {
+			dev_err(dev, "AXI bus port halt timeout\n");
+			return ret;
+		}
+
+		return 0;
+	}
+
 	/* Halt AXI and AXI IMEM VBIF Access */
 	val = venus_readl(hdev, VBIF_AXI_HALT_CTRL0);
 	val |= VBIF_AXI_HALT_CTRL0_HALT_REQ;
@@ -861,6 +879,14 @@ static int venus_sys_set_default_properties(struct venus_hfi_device *hdev)
 	if (ret)
 		dev_warn(dev, "setting fw debug msg ON failed (%d)\n", ret);
 
+	/*
+	 * Idle indicator is disabled by default on some 4xx firmware versions,
+	 * enable it explicitly in order to make suspend functional by checking
+	 * WFI (wait-for-interrupt) bit.
+	 */
+	if (IS_V4(hdev->core))
+		venus_sys_idle_indicator = true;
+
 	ret = venus_sys_set_idle_message(hdev, venus_sys_idle_indicator);
 	if (ret)
 		dev_warn(dev, "setting idle response ON failed (%d)\n", ret);
@@ -1073,6 +1099,10 @@ static int venus_core_init(struct venus_core *core)
 	if (ret)
 		dev_warn(dev, "failed to send image version pkt to fw\n");
 
+	ret = venus_sys_set_default_properties(hdev);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 
@@ -1117,10 +1147,6 @@ static int venus_session_init(struct venus_inst *inst, u32 session_type,
 	struct hfi_session_init_pkt pkt;
 	int ret;
 
-	ret = venus_sys_set_default_properties(hdev);
-	if (ret)
-		return ret;
-
 	ret = pkt_session_init(&pkt, inst, session_type, codec);
 	if (ret)
 		goto err;
@@ -1426,13 +1452,40 @@ static int venus_suspend_1xx(struct venus_core *core)
 	return 0;
 }
 
+static bool venus_cpu_and_video_core_idle(struct venus_hfi_device *hdev)
+{
+	u32 ctrl_status, cpu_status;
+
+	cpu_status = venus_readl(hdev, WRAPPER_CPU_STATUS);
+	ctrl_status = venus_readl(hdev, CPU_CS_SCIACMDARG0);
+
+	if (cpu_status & WRAPPER_CPU_STATUS_WFI &&
+	    ctrl_status & CPU_CS_SCIACMDARG0_INIT_IDLE_MSG_MASK)
+		return true;
+
+	return false;
+}
+
+static bool venus_cpu_idle_and_pc_ready(struct venus_hfi_device *hdev)
+{
+	u32 ctrl_status, cpu_status;
+
+	cpu_status = venus_readl(hdev, WRAPPER_CPU_STATUS);
+	ctrl_status = venus_readl(hdev, CPU_CS_SCIACMDARG0);
+
+	if (cpu_status & WRAPPER_CPU_STATUS_WFI &&
+	    ctrl_status & CPU_CS_SCIACMDARG0_PC_READY)
+		return true;
+
+	return false;
+}
+
 static int venus_suspend_3xx(struct venus_core *core)
 {
 	struct venus_hfi_device *hdev = to_hfi_priv(core);
 	struct device *dev = core->dev;
-	u32 ctrl_status, wfi_status;
+	bool val;
 	int ret;
-	int cnt = 100;
 
 	if (!hdev->power_enabled || hdev->suspended)
 		return 0;
@@ -1446,29 +1499,30 @@ static int venus_suspend_3xx(struct venus_core *core)
 		return -EINVAL;
 	}
 
-	ctrl_status = venus_readl(hdev, CPU_CS_SCIACMDARG0);
-	if (!(ctrl_status & CPU_CS_SCIACMDARG0_PC_READY)) {
-		wfi_status = venus_readl(hdev, WRAPPER_CPU_STATUS);
-		ctrl_status = venus_readl(hdev, CPU_CS_SCIACMDARG0);
-
-		ret = venus_prepare_power_collapse(hdev, false);
-		if (ret) {
-			dev_err(dev, "prepare for power collapse fail (%d)\n",
-				ret);
-			return ret;
-		}
+	/*
+	 * Power collapse sequence for Venus 3xx and 4xx versions:
+	 * 1. Check for ARM9 and video core to be idle by checking WFI bit
+	 *    (bit 0) in CPU status register and by checking Idle (bit 30) in
+	 *    Control status register for video core.
+	 * 2. Send a command to prepare for power collapse.
+	 * 3. Check for WFI and PC_READY bits.
+	 */
+	ret = readx_poll_timeout(venus_cpu_and_video_core_idle, hdev, val, val,
+				 1500, 100 * 1500);
+	if (ret)
+		return ret;
 
-		cnt = 100;
-		while (cnt--) {
-			wfi_status = venus_readl(hdev, WRAPPER_CPU_STATUS);
-			ctrl_status = venus_readl(hdev, CPU_CS_SCIACMDARG0);
-			if (ctrl_status & CPU_CS_SCIACMDARG0_PC_READY &&
-			    wfi_status & BIT(0))
-				break;
-			usleep_range(1000, 1500);
-		}
+	ret = venus_prepare_power_collapse(hdev, false);
+	if (ret) {
+		dev_err(dev, "prepare for power collapse fail (%d)\n", ret);
+		return ret;
 	}
 
+	ret = readx_poll_timeout(venus_cpu_idle_and_pc_ready, hdev, val, val,
+				 1500, 100 * 1500);
+	if (ret)
+		return ret;
+
 	mutex_lock(&hdev->lock);
 
 	ret = venus_power_off(hdev);
@@ -1487,7 +1541,7 @@ static int venus_suspend_3xx(struct venus_core *core)
 
 static int venus_suspend(struct venus_core *core)
 {
-	if (core->res->hfi_version == HFI_VERSION_3XX)
+	if (IS_V3(core) || IS_V4(core))
 		return venus_suspend_3xx(core);
 
 	return venus_suspend_1xx(core);
diff --git a/drivers/media/platform/qcom/venus/hfi_venus_io.h b/drivers/media/platform/qcom/venus/hfi_venus_io.h
index 98cc350113ab..def0926a6dee 100644
--- a/drivers/media/platform/qcom/venus/hfi_venus_io.h
+++ b/drivers/media/platform/qcom/venus/hfi_venus_io.h
@@ -104,10 +104,20 @@
 
 #define WRAPPER_CPU_CLOCK_CONFIG		(WRAPPER_BASE + 0x2000)
 #define WRAPPER_CPU_AXI_HALT			(WRAPPER_BASE + 0x2008)
+#define WRAPPER_CPU_AXI_HALT_HALT		BIT(16)
 #define WRAPPER_CPU_AXI_HALT_STATUS		(WRAPPER_BASE + 0x200c)
+#define WRAPPER_CPU_AXI_HALT_STATUS_IDLE	BIT(24)
 
 #define WRAPPER_CPU_CGC_DIS			(WRAPPER_BASE + 0x2010)
 #define WRAPPER_CPU_STATUS			(WRAPPER_BASE + 0x2014)
+#define WRAPPER_CPU_STATUS_WFI			BIT(0)
 #define WRAPPER_SW_RESET			(WRAPPER_BASE + 0x3000)
 
+/* Venus 4xx */
+#define WRAPPER_VCODEC0_MMCC_POWER_STATUS	(WRAPPER_BASE + 0x90)
+#define WRAPPER_VCODEC0_MMCC_POWER_CONTROL	(WRAPPER_BASE + 0x94)
+
+#define WRAPPER_VCODEC1_MMCC_POWER_STATUS	(WRAPPER_BASE + 0x110)
+#define WRAPPER_VCODEC1_MMCC_POWER_CONTROL	(WRAPPER_BASE + 0x114)
+
 #endif
diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c
index 49bbd1861d3a..dfbbbf0f746f 100644
--- a/drivers/media/platform/qcom/venus/vdec.c
+++ b/drivers/media/platform/qcom/venus/vdec.c
@@ -14,6 +14,7 @@
  */
 #include <linux/clk.h>
 #include <linux/module.h>
+#include <linux/mod_devicetable.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
@@ -24,33 +25,11 @@
 #include <media/videobuf2-dma-sg.h>
 
 #include "hfi_venus_io.h"
+#include "hfi_parser.h"
 #include "core.h"
 #include "helpers.h"
 #include "vdec.h"
 
-static u32 get_framesize_uncompressed(unsigned int plane, u32 width, u32 height)
-{
-	u32 y_stride, uv_stride, y_plane;
-	u32 y_sclines, uv_sclines, uv_plane;
-	u32 size;
-
-	y_stride = ALIGN(width, 128);
-	uv_stride = ALIGN(width, 128);
-	y_sclines = ALIGN(height, 32);
-	uv_sclines = ALIGN(((height + 1) >> 1), 16);
-
-	y_plane = y_stride * y_sclines;
-	uv_plane = uv_stride * uv_sclines + SZ_4K;
-	size = y_plane + uv_plane + SZ_8K;
-
-	return ALIGN(size, SZ_4K);
-}
-
-static u32 get_framesize_compressed(unsigned int width, unsigned int height)
-{
-	return ((width * height * 3 / 2) / 2) + 128;
-}
-
 /*
  * Three resons to keep MPLANE formats (despite that the number of planes
  * currently is one):
@@ -99,6 +78,10 @@ static const struct venus_format vdec_formats[] = {
 		.pixfmt = V4L2_PIX_FMT_XVID,
 		.num_planes = 1,
 		.type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE,
+	}, {
+		.pixfmt = V4L2_PIX_FMT_HEVC,
+		.num_planes = 1,
+		.type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE,
 	},
 };
 
@@ -159,7 +142,6 @@ vdec_try_fmt_common(struct venus_inst *inst, struct v4l2_format *f)
 	struct v4l2_pix_format_mplane *pixmp = &f->fmt.pix_mp;
 	struct v4l2_plane_pix_format *pfmt = pixmp->plane_fmt;
 	const struct venus_format *fmt;
-	unsigned int p;
 
 	memset(pfmt[0].reserved, 0, sizeof(pfmt[0].reserved));
 	memset(pixmp->reserved, 0, sizeof(pixmp->reserved));
@@ -173,14 +155,12 @@ vdec_try_fmt_common(struct venus_inst *inst, struct v4l2_format *f)
 		else
 			return NULL;
 		fmt = find_format(inst, pixmp->pixelformat, f->type);
-		pixmp->width = 1280;
-		pixmp->height = 720;
 	}
 
-	pixmp->width = clamp(pixmp->width, inst->cap_width.min,
-			     inst->cap_width.max);
-	pixmp->height = clamp(pixmp->height, inst->cap_height.min,
-			      inst->cap_height.max);
+	pixmp->width = clamp(pixmp->width, frame_width_min(inst),
+			     frame_width_max(inst));
+	pixmp->height = clamp(pixmp->height, frame_height_min(inst),
+			      frame_height_max(inst));
 
 	if (f->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE)
 		pixmp->height = ALIGN(pixmp->height, 32);
@@ -190,18 +170,14 @@ vdec_try_fmt_common(struct venus_inst *inst, struct v4l2_format *f)
 	pixmp->num_planes = fmt->num_planes;
 	pixmp->flags = 0;
 
-	if (f->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
-		for (p = 0; p < pixmp->num_planes; p++) {
-			pfmt[p].sizeimage =
-				get_framesize_uncompressed(p, pixmp->width,
-							   pixmp->height);
-			pfmt[p].bytesperline = ALIGN(pixmp->width, 128);
-		}
-	} else {
-		pfmt[0].sizeimage = get_framesize_compressed(pixmp->width,
-							     pixmp->height);
+	pfmt[0].sizeimage = venus_helper_get_framesz(pixmp->pixelformat,
+						     pixmp->width,
+						     pixmp->height);
+
+	if (f->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE)
+		pfmt[0].bytesperline = ALIGN(pixmp->width, 128);
+	else
 		pfmt[0].bytesperline = 0;
-	}
 
 	return fmt;
 }
@@ -442,12 +418,12 @@ static int vdec_enum_framesizes(struct file *file, void *fh,
 
 	fsize->type = V4L2_FRMSIZE_TYPE_STEPWISE;
 
-	fsize->stepwise.min_width = inst->cap_width.min;
-	fsize->stepwise.max_width = inst->cap_width.max;
-	fsize->stepwise.step_width = inst->cap_width.step_size;
-	fsize->stepwise.min_height = inst->cap_height.min;
-	fsize->stepwise.max_height = inst->cap_height.max;
-	fsize->stepwise.step_height = inst->cap_height.step_size;
+	fsize->stepwise.min_width = frame_width_min(inst);
+	fsize->stepwise.max_width = frame_width_max(inst);
+	fsize->stepwise.step_width = frame_width_step(inst);
+	fsize->stepwise.min_height = frame_height_min(inst);
+	fsize->stepwise.max_height = frame_height_max(inst);
+	fsize->stepwise.step_height = frame_height_step(inst);
 
 	return 0;
 }
@@ -544,11 +520,41 @@ static const struct v4l2_ioctl_ops vdec_ioctl_ops = {
 static int vdec_set_properties(struct venus_inst *inst)
 {
 	struct vdec_controls *ctr = &inst->controls.dec;
+	struct hfi_enable en = { .enable = 1 };
+	u32 ptype;
+	int ret;
+
+	if (ctr->post_loop_deb_mode) {
+		ptype = HFI_PROPERTY_CONFIG_VDEC_POST_LOOP_DEBLOCKER;
+		ret = hfi_session_set_property(inst, ptype, &en);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+#define is_ubwc_fmt(fmt) (!!((fmt) & HFI_COLOR_FORMAT_UBWC_BASE))
+
+static int vdec_output_conf(struct venus_inst *inst)
+{
 	struct venus_core *core = inst->core;
 	struct hfi_enable en = { .enable = 1 };
+	u32 width = inst->out_width;
+	u32 height = inst->out_height;
+	u32 out_fmt, out2_fmt;
+	bool ubwc = false;
 	u32 ptype;
 	int ret;
 
+	ret = venus_helper_set_work_mode(inst, VIDC_WORK_MODE_2);
+	if (ret)
+		return ret;
+
+	ret = venus_helper_set_core_usage(inst, VIDC_CORE_ID_1);
+	if (ret)
+		return ret;
+
 	if (core->res->hfi_version == HFI_VERSION_1XX) {
 		ptype = HFI_PROPERTY_PARAM_VDEC_CONTINUE_DATA_TRANSFER;
 		ret = hfi_session_set_property(inst, ptype, &en);
@@ -556,27 +562,84 @@ static int vdec_set_properties(struct venus_inst *inst)
 			return ret;
 	}
 
-	if (core->res->hfi_version == HFI_VERSION_3XX ||
-	    inst->cap_bufs_mode_dynamic) {
-		struct hfi_buffer_alloc_mode mode;
+	/* Force searching UBWC formats for bigger then HD resolutions */
+	if (width > 1920 && height > ALIGN(1080, 32))
+		ubwc = true;
+
+	/* For Venus v4 UBWC format is mandatory */
+	if (IS_V4(core))
+		ubwc = true;
+
+	ret = venus_helper_get_out_fmts(inst, inst->fmt_cap->pixfmt, &out_fmt,
+					&out2_fmt, ubwc);
+	if (ret)
+		return ret;
+
+	inst->output_buf_size =
+			venus_helper_get_framesz_raw(out_fmt, width, height);
+	inst->output2_buf_size =
+			venus_helper_get_framesz_raw(out2_fmt, width, height);
+
+	if (is_ubwc_fmt(out_fmt)) {
+		inst->opb_buftype = HFI_BUFFER_OUTPUT2;
+		inst->opb_fmt = out2_fmt;
+		inst->dpb_buftype = HFI_BUFFER_OUTPUT;
+		inst->dpb_fmt = out_fmt;
+	} else if (is_ubwc_fmt(out2_fmt)) {
+		inst->opb_buftype = HFI_BUFFER_OUTPUT;
+		inst->opb_fmt = out_fmt;
+		inst->dpb_buftype = HFI_BUFFER_OUTPUT2;
+		inst->dpb_fmt = out2_fmt;
+	} else {
+		inst->opb_buftype = HFI_BUFFER_OUTPUT;
+		inst->opb_fmt = out_fmt;
+		inst->dpb_buftype = 0;
+		inst->dpb_fmt = 0;
+	}
+
+	ret = venus_helper_set_raw_format(inst, inst->opb_fmt,
+					  inst->opb_buftype);
+	if (ret)
+		return ret;
 
-		ptype = HFI_PROPERTY_PARAM_BUFFER_ALLOC_MODE;
-		mode.type = HFI_BUFFER_OUTPUT;
-		mode.mode = HFI_BUFFER_MODE_DYNAMIC;
+	if (inst->dpb_fmt) {
+		ret = venus_helper_set_multistream(inst, false, true);
+		if (ret)
+			return ret;
 
-		ret = hfi_session_set_property(inst, ptype, &mode);
+		ret = venus_helper_set_raw_format(inst, inst->dpb_fmt,
+						  inst->dpb_buftype);
 		if (ret)
 			return ret;
-	}
 
-	if (ctr->post_loop_deb_mode) {
-		ptype = HFI_PROPERTY_CONFIG_VDEC_POST_LOOP_DEBLOCKER;
-		en.enable = 1;
-		ret = hfi_session_set_property(inst, ptype, &en);
+		ret = venus_helper_set_output_resolution(inst, width, height,
+							 HFI_BUFFER_OUTPUT2);
 		if (ret)
 			return ret;
 	}
 
+	if (IS_V3(core) || IS_V4(core)) {
+		if (inst->output2_buf_size) {
+			ret = venus_helper_set_bufsize(inst,
+						       inst->output2_buf_size,
+						       HFI_BUFFER_OUTPUT2);
+			if (ret)
+				return ret;
+		}
+
+		if (inst->output_buf_size) {
+			ret = venus_helper_set_bufsize(inst,
+						       inst->output_buf_size,
+						       HFI_BUFFER_OUTPUT);
+			if (ret)
+				return ret;
+		}
+	}
+
+	ret = venus_helper_set_dyn_bufmode(inst);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 
@@ -603,19 +666,32 @@ deinit:
 	return ret;
 }
 
-static int vdec_cap_num_buffers(struct venus_inst *inst, unsigned int *num)
+static int vdec_num_buffers(struct venus_inst *inst, unsigned int *in_num,
+			    unsigned int *out_num)
 {
+	enum hfi_version ver = inst->core->res->hfi_version;
 	struct hfi_buffer_requirements bufreq;
 	int ret;
 
+	*in_num = *out_num = 0;
+
 	ret = vdec_init_session(inst);
 	if (ret)
 		return ret;
 
+	ret = venus_helper_get_bufreq(inst, HFI_BUFFER_INPUT, &bufreq);
+	if (ret)
+		goto deinit;
+
+	*in_num = HFI_BUFREQ_COUNT_MIN(&bufreq, ver);
+
 	ret = venus_helper_get_bufreq(inst, HFI_BUFFER_OUTPUT, &bufreq);
+	if (ret)
+		goto deinit;
 
-	*num = bufreq.count_actual;
+	*out_num = HFI_BUFREQ_COUNT_MIN(&bufreq, ver);
 
+deinit:
 	hfi_session_deinit(inst);
 
 	return ret;
@@ -626,10 +702,12 @@ static int vdec_queue_setup(struct vb2_queue *q,
 			    unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct venus_inst *inst = vb2_get_drv_priv(q);
-	unsigned int p, num;
+	unsigned int in_num, out_num;
 	int ret = 0;
 
 	if (*num_planes) {
+		unsigned int output_buf_size = venus_helper_get_opb_size(inst);
+
 		if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE &&
 		    *num_planes != inst->fmt_out->num_planes)
 			return -EINVAL;
@@ -643,41 +721,35 @@ static int vdec_queue_setup(struct vb2_queue *q,
 			return -EINVAL;
 
 		if (q->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE &&
-		    sizes[0] < inst->output_buf_size)
+		    sizes[0] < output_buf_size)
 			return -EINVAL;
 
 		return 0;
 	}
 
+	ret = vdec_num_buffers(inst, &in_num, &out_num);
+	if (ret)
+		return ret;
+
 	switch (q->type) {
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
 		*num_planes = inst->fmt_out->num_planes;
-		sizes[0] = get_framesize_compressed(inst->out_width,
+		sizes[0] = venus_helper_get_framesz(inst->fmt_out->pixfmt,
+						    inst->out_width,
 						    inst->out_height);
 		inst->input_buf_size = sizes[0];
+		*num_buffers = max(*num_buffers, in_num);
 		inst->num_input_bufs = *num_buffers;
-
-		ret = vdec_cap_num_buffers(inst, &num);
-		if (ret)
-			break;
-
-		inst->num_output_bufs = num;
+		inst->num_output_bufs = out_num;
 		break;
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
 		*num_planes = inst->fmt_cap->num_planes;
-
-		ret = vdec_cap_num_buffers(inst, &num);
-		if (ret)
-			break;
-
-		*num_buffers = max(*num_buffers, num);
-
-		for (p = 0; p < *num_planes; p++)
-			sizes[p] = get_framesize_uncompressed(p, inst->width,
-							      inst->height);
-
-		inst->num_output_bufs = *num_buffers;
+		sizes[0] = venus_helper_get_framesz(inst->fmt_cap->pixfmt,
+						    inst->width,
+						    inst->height);
 		inst->output_buf_size = sizes[0];
+		*num_buffers = max(*num_buffers, out_num);
+		inst->num_output_bufs = *num_buffers;
 		break;
 	default:
 		ret = -EINVAL;
@@ -689,6 +761,7 @@ static int vdec_queue_setup(struct vb2_queue *q,
 
 static int vdec_verify_conf(struct venus_inst *inst)
 {
+	enum hfi_version ver = inst->core->res->hfi_version;
 	struct hfi_buffer_requirements bufreq;
 	int ret;
 
@@ -700,14 +773,14 @@ static int vdec_verify_conf(struct venus_inst *inst)
 		return ret;
 
 	if (inst->num_output_bufs < bufreq.count_actual ||
-	    inst->num_output_bufs < bufreq.count_min)
+	    inst->num_output_bufs < HFI_BUFREQ_COUNT_MIN(&bufreq, ver))
 		return -EINVAL;
 
 	ret = venus_helper_get_bufreq(inst, HFI_BUFFER_INPUT, &bufreq);
 	if (ret)
 		return ret;
 
-	if (inst->num_input_bufs < bufreq.count_min)
+	if (inst->num_input_bufs < HFI_BUFREQ_COUNT_MIN(&bufreq, ver))
 		return -EINVAL;
 
 	return 0;
@@ -716,8 +789,6 @@ static int vdec_verify_conf(struct venus_inst *inst)
 static int vdec_start_streaming(struct vb2_queue *q, unsigned int count)
 {
 	struct venus_inst *inst = vb2_get_drv_priv(q);
-	struct venus_core *core = inst->core;
-	u32 ptype;
 	int ret;
 
 	mutex_lock(&inst->lock);
@@ -746,24 +817,20 @@ static int vdec_start_streaming(struct vb2_queue *q, unsigned int count)
 	if (ret)
 		goto deinit_sess;
 
-	if (core->res->hfi_version == HFI_VERSION_3XX) {
-		struct hfi_buffer_size_actual buf_sz;
-
-		ptype = HFI_PROPERTY_PARAM_BUFFER_SIZE_ACTUAL;
-		buf_sz.type = HFI_BUFFER_OUTPUT;
-		buf_sz.size = inst->output_buf_size;
-
-		ret = hfi_session_set_property(inst, ptype, &buf_sz);
-		if (ret)
-			goto deinit_sess;
-	}
+	ret = vdec_output_conf(inst);
+	if (ret)
+		goto deinit_sess;
 
 	ret = vdec_verify_conf(inst);
 	if (ret)
 		goto deinit_sess;
 
 	ret = venus_helper_set_num_bufs(inst, inst->num_input_bufs,
-					VB2_MAX_FRAME);
+					VB2_MAX_FRAME, VB2_MAX_FRAME);
+	if (ret)
+		goto deinit_sess;
+
+	ret = venus_helper_alloc_dpb_bufs(inst);
 	if (ret)
 		goto deinit_sess;
 
@@ -818,9 +885,11 @@ static void vdec_buf_done(struct venus_inst *inst, unsigned int buf_type,
 	vbuf->field = V4L2_FIELD_NONE;
 
 	if (type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
+		unsigned int opb_sz = venus_helper_get_opb_size(inst);
+
 		vb = &vbuf->vb2_buf;
 		vb->planes[0].bytesused =
-			max_t(unsigned int, inst->output_buf_size, bytesused);
+			max_t(unsigned int, opb_sz, bytesused);
 		vb->planes[0].data_offset = data_offset;
 		vb->timestamp = timestamp_us * NSEC_PER_USEC;
 		vbuf->sequence = inst->sequence_cap++;
@@ -901,22 +970,7 @@ static void vdec_inst_init(struct venus_inst *inst)
 	inst->fps = 30;
 	inst->timeperframe.numerator = 1;
 	inst->timeperframe.denominator = 30;
-
-	inst->cap_width.min = 64;
-	inst->cap_width.max = 1920;
-	if (inst->core->res->hfi_version == HFI_VERSION_3XX)
-		inst->cap_width.max = 3840;
-	inst->cap_width.step_size = 1;
-	inst->cap_height.min = 64;
-	inst->cap_height.max = ALIGN(1080, 32);
-	if (inst->core->res->hfi_version == HFI_VERSION_3XX)
-		inst->cap_height.max = ALIGN(2160, 32);
-	inst->cap_height.step_size = 1;
-	inst->cap_framerate.min = 1;
-	inst->cap_framerate.max = 30;
-	inst->cap_framerate.step_size = 1;
-	inst->cap_mbs_per_frame.min = 16;
-	inst->cap_mbs_per_frame.max = 8160;
+	inst->hfi_codec = HFI_VIDEO_CODEC_H264;
 }
 
 static const struct v4l2_m2m_ops vdec_m2m_ops = {
@@ -973,6 +1027,7 @@ static int vdec_open(struct file *file)
 	if (!inst)
 		return -ENOMEM;
 
+	INIT_LIST_HEAD(&inst->dpbbufs);
 	INIT_LIST_HEAD(&inst->registeredbufs);
 	INIT_LIST_HEAD(&inst->internalbufs);
 	INIT_LIST_HEAD(&inst->list);
@@ -1080,12 +1135,18 @@ static int vdec_probe(struct platform_device *pdev)
 	if (!core)
 		return -EPROBE_DEFER;
 
-	if (core->res->hfi_version == HFI_VERSION_3XX) {
+	if (IS_V3(core) || IS_V4(core)) {
 		core->core0_clk = devm_clk_get(dev, "core");
 		if (IS_ERR(core->core0_clk))
 			return PTR_ERR(core->core0_clk);
 	}
 
+	if (IS_V4(core)) {
+		core->core0_bus_clk = devm_clk_get(dev, "bus");
+		if (IS_ERR(core->core0_bus_clk))
+			return PTR_ERR(core->core0_bus_clk);
+	}
+
 	platform_set_drvdata(pdev, core);
 
 	vdev = video_device_alloc();
@@ -1130,15 +1191,21 @@ static int vdec_remove(struct platform_device *pdev)
 static __maybe_unused int vdec_runtime_suspend(struct device *dev)
 {
 	struct venus_core *core = dev_get_drvdata(dev);
+	int ret;
 
-	if (core->res->hfi_version == HFI_VERSION_1XX)
+	if (IS_V1(core))
 		return 0;
 
-	writel(0, core->base + WRAPPER_VDEC_VCODEC_POWER_CONTROL);
+	ret = venus_helper_power_enable(core, VIDC_SESSION_TYPE_DEC, true);
+	if (ret)
+		return ret;
+
+	if (IS_V4(core))
+		clk_disable_unprepare(core->core0_bus_clk);
+
 	clk_disable_unprepare(core->core0_clk);
-	writel(1, core->base + WRAPPER_VDEC_VCODEC_POWER_CONTROL);
 
-	return 0;
+	return venus_helper_power_enable(core, VIDC_SESSION_TYPE_DEC, false);
 }
 
 static __maybe_unused int vdec_runtime_resume(struct device *dev)
@@ -1146,13 +1213,29 @@ static __maybe_unused int vdec_runtime_resume(struct device *dev)
 	struct venus_core *core = dev_get_drvdata(dev);
 	int ret;
 
-	if (core->res->hfi_version == HFI_VERSION_1XX)
+	if (IS_V1(core))
 		return 0;
 
-	writel(0, core->base + WRAPPER_VDEC_VCODEC_POWER_CONTROL);
+	ret = venus_helper_power_enable(core, VIDC_SESSION_TYPE_DEC, true);
+	if (ret)
+		return ret;
+
 	ret = clk_prepare_enable(core->core0_clk);
-	writel(1, core->base + WRAPPER_VDEC_VCODEC_POWER_CONTROL);
+	if (ret)
+		goto err_power_disable;
 
+	if (IS_V4(core))
+		ret = clk_prepare_enable(core->core0_bus_clk);
+
+	if (ret)
+		goto err_unprepare_core0;
+
+	return venus_helper_power_enable(core, VIDC_SESSION_TYPE_DEC, false);
+
+err_unprepare_core0:
+	clk_disable_unprepare(core->core0_clk);
+err_power_disable:
+	venus_helper_power_enable(core, VIDC_SESSION_TYPE_DEC, false);
 	return ret;
 }
 
diff --git a/drivers/media/platform/qcom/venus/vdec_ctrls.c b/drivers/media/platform/qcom/venus/vdec_ctrls.c
index 032839bbc967..f4604b0cd57e 100644
--- a/drivers/media/platform/qcom/venus/vdec_ctrls.c
+++ b/drivers/media/platform/qcom/venus/vdec_ctrls.c
@@ -29,7 +29,7 @@ static int vdec_op_s_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	case V4L2_CID_MPEG_VIDEO_H264_PROFILE:
 	case V4L2_CID_MPEG_VIDEO_MPEG4_PROFILE:
-	case V4L2_CID_MPEG_VIDEO_VPX_PROFILE:
+	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:
 		ctr->profile = ctrl->val;
 		break;
 	case V4L2_CID_MPEG_VIDEO_H264_LEVEL:
@@ -54,7 +54,7 @@ static int vdec_op_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
 	switch (ctrl->id) {
 	case V4L2_CID_MPEG_VIDEO_H264_PROFILE:
 	case V4L2_CID_MPEG_VIDEO_MPEG4_PROFILE:
-	case V4L2_CID_MPEG_VIDEO_VPX_PROFILE:
+	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:
 		ret = hfi_session_get_property(inst, ptype, &hprop);
 		if (!ret)
 			ctr->profile = hprop.profile_level.profile;
@@ -130,8 +130,10 @@ int vdec_ctrl_init(struct venus_inst *inst)
 	if (ctrl)
 		ctrl->flags |= V4L2_CTRL_FLAG_VOLATILE;
 
-	ctrl = v4l2_ctrl_new_std(&inst->ctrl_handler, &vdec_ctrl_ops,
-				 V4L2_CID_MPEG_VIDEO_VPX_PROFILE, 0, 3, 1, 0);
+	ctrl = v4l2_ctrl_new_std_menu(&inst->ctrl_handler, &vdec_ctrl_ops,
+				      V4L2_CID_MPEG_VIDEO_VP8_PROFILE,
+				      V4L2_MPEG_VIDEO_VP8_PROFILE_3,
+				      0, V4L2_MPEG_VIDEO_VP8_PROFILE_0);
 	if (ctrl)
 		ctrl->flags |= V4L2_CTRL_FLAG_VOLATILE;
 
diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c
index 6b2ce479584e..41249d1443fa 100644
--- a/drivers/media/platform/qcom/venus/venc.c
+++ b/drivers/media/platform/qcom/venus/venc.c
@@ -14,6 +14,7 @@
  */
 #include <linux/clk.h>
 #include <linux/module.h>
+#include <linux/mod_devicetable.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
@@ -24,38 +25,13 @@
 #include <media/v4l2-ctrls.h>
 
 #include "hfi_venus_io.h"
+#include "hfi_parser.h"
 #include "core.h"
 #include "helpers.h"
 #include "venc.h"
 
 #define NUM_B_FRAMES_MAX	4
 
-static u32 get_framesize_uncompressed(unsigned int plane, u32 width, u32 height)
-{
-	u32 y_stride, uv_stride, y_plane;
-	u32 y_sclines, uv_sclines, uv_plane;
-	u32 size;
-
-	y_stride = ALIGN(width, 128);
-	uv_stride = ALIGN(width, 128);
-	y_sclines = ALIGN(height, 32);
-	uv_sclines = ALIGN(((height + 1) >> 1), 16);
-
-	y_plane = y_stride * y_sclines;
-	uv_plane = uv_stride * uv_sclines + SZ_4K;
-	size = y_plane + uv_plane + SZ_8K;
-	size = ALIGN(size, SZ_4K);
-
-	return size;
-}
-
-static u32 get_framesize_compressed(u32 width, u32 height)
-{
-	u32 sz = ALIGN(height, 32) * ALIGN(width, 32) * 3 / 2 / 2;
-
-	return ALIGN(sz, SZ_4K);
-}
-
 /*
  * Three resons to keep MPLANE formats (despite that the number of planes
  * currently is one):
@@ -84,6 +60,10 @@ static const struct venus_format venc_formats[] = {
 		.pixfmt = V4L2_PIX_FMT_VP8,
 		.num_planes = 1,
 		.type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE,
+	}, {
+		.pixfmt = V4L2_PIX_FMT_HEVC,
+		.num_planes = 1,
+		.type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE,
 	},
 };
 
@@ -223,7 +203,7 @@ static int venc_v4l2_to_hfi(int id, int value)
 		case V4L2_MPEG_VIDEO_H264_ENTROPY_MODE_CABAC:
 			return HFI_H264_ENTROPY_CABAC;
 		}
-	case V4L2_CID_MPEG_VIDEO_VPX_PROFILE:
+	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:
 		switch (value) {
 		case 0:
 		default:
@@ -245,6 +225,46 @@ static int venc_v4l2_to_hfi(int id, int value)
 		case V4L2_MPEG_VIDEO_H264_LOOP_FILTER_MODE_DISABLED_AT_SLICE_BOUNDARY:
 			return HFI_H264_DB_MODE_SKIP_SLICE_BOUNDARY;
 		}
+	case V4L2_CID_MPEG_VIDEO_HEVC_PROFILE:
+		switch (value) {
+		case V4L2_MPEG_VIDEO_HEVC_PROFILE_MAIN:
+		default:
+			return HFI_HEVC_PROFILE_MAIN;
+		case V4L2_MPEG_VIDEO_HEVC_PROFILE_MAIN_STILL_PICTURE:
+			return HFI_HEVC_PROFILE_MAIN_STILL_PIC;
+		case V4L2_MPEG_VIDEO_HEVC_PROFILE_MAIN_10:
+			return HFI_HEVC_PROFILE_MAIN10;
+		}
+	case V4L2_CID_MPEG_VIDEO_HEVC_LEVEL:
+		switch (value) {
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_1:
+		default:
+			return HFI_HEVC_LEVEL_1;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_2:
+			return HFI_HEVC_LEVEL_2;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_2_1:
+			return HFI_HEVC_LEVEL_21;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_3:
+			return HFI_HEVC_LEVEL_3;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_3_1:
+			return HFI_HEVC_LEVEL_31;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_4:
+			return HFI_HEVC_LEVEL_4;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_4_1:
+			return HFI_HEVC_LEVEL_41;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_5:
+			return HFI_HEVC_LEVEL_5;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_5_1:
+			return HFI_HEVC_LEVEL_51;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_5_2:
+			return HFI_HEVC_LEVEL_52;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_6:
+			return HFI_HEVC_LEVEL_6;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_6_1:
+			return HFI_HEVC_LEVEL_61;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_6_2:
+			return HFI_HEVC_LEVEL_62;
+		}
 	}
 
 	return 0;
@@ -283,7 +303,6 @@ venc_try_fmt_common(struct venus_inst *inst, struct v4l2_format *f)
 	struct v4l2_pix_format_mplane *pixmp = &f->fmt.pix_mp;
 	struct v4l2_plane_pix_format *pfmt = pixmp->plane_fmt;
 	const struct venus_format *fmt;
-	unsigned int p;
 
 	memset(pfmt[0].reserved, 0, sizeof(pfmt[0].reserved));
 	memset(pixmp->reserved, 0, sizeof(pixmp->reserved));
@@ -297,14 +316,12 @@ venc_try_fmt_common(struct venus_inst *inst, struct v4l2_format *f)
 		else
 			return NULL;
 		fmt = find_format(inst, pixmp->pixelformat, f->type);
-		pixmp->width = 1280;
-		pixmp->height = 720;
 	}
 
-	pixmp->width = clamp(pixmp->width, inst->cap_width.min,
-			     inst->cap_width.max);
-	pixmp->height = clamp(pixmp->height, inst->cap_height.min,
-			      inst->cap_height.max);
+	pixmp->width = clamp(pixmp->width, frame_width_min(inst),
+			     frame_width_max(inst));
+	pixmp->height = clamp(pixmp->height, frame_height_min(inst),
+			      frame_height_max(inst));
 
 	if (f->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE)
 		pixmp->height = ALIGN(pixmp->height, 32);
@@ -317,19 +334,14 @@ venc_try_fmt_common(struct venus_inst *inst, struct v4l2_format *f)
 	pixmp->num_planes = fmt->num_planes;
 	pixmp->flags = 0;
 
-	if (f->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
-		for (p = 0; p < pixmp->num_planes; p++) {
-			pfmt[p].sizeimage =
-				get_framesize_uncompressed(p, pixmp->width,
-							   pixmp->height);
+	pfmt[0].sizeimage = venus_helper_get_framesz(pixmp->pixelformat,
+						     pixmp->width,
+						     pixmp->height);
 
-			pfmt[p].bytesperline = ALIGN(pixmp->width, 128);
-		}
-	} else {
-		pfmt[0].sizeimage = get_framesize_compressed(pixmp->width,
-							     pixmp->height);
+	if (f->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE)
+		pfmt[0].bytesperline = ALIGN(pixmp->width, 128);
+	else
 		pfmt[0].bytesperline = 0;
-	}
 
 	return fmt;
 }
@@ -553,12 +565,12 @@ static int venc_enum_framesizes(struct file *file, void *fh,
 	if (fsize->index)
 		return -EINVAL;
 
-	fsize->stepwise.min_width = inst->cap_width.min;
-	fsize->stepwise.max_width = inst->cap_width.max;
-	fsize->stepwise.step_width = inst->cap_width.step_size;
-	fsize->stepwise.min_height = inst->cap_height.min;
-	fsize->stepwise.max_height = inst->cap_height.max;
-	fsize->stepwise.step_height = inst->cap_height.step_size;
+	fsize->stepwise.min_width = frame_width_min(inst);
+	fsize->stepwise.max_width = frame_width_max(inst);
+	fsize->stepwise.step_width = frame_width_step(inst);
+	fsize->stepwise.min_height = frame_height_min(inst);
+	fsize->stepwise.max_height = frame_height_max(inst);
+	fsize->stepwise.step_height = frame_height_step(inst);
 
 	return 0;
 }
@@ -586,18 +598,18 @@ static int venc_enum_frameintervals(struct file *file, void *fh,
 	if (!fival->width || !fival->height)
 		return -EINVAL;
 
-	if (fival->width > inst->cap_width.max ||
-	    fival->width < inst->cap_width.min ||
-	    fival->height > inst->cap_height.max ||
-	    fival->height < inst->cap_height.min)
+	if (fival->width > frame_width_max(inst) ||
+	    fival->width < frame_width_min(inst) ||
+	    fival->height > frame_height_max(inst) ||
+	    fival->height < frame_height_min(inst))
 		return -EINVAL;
 
 	fival->stepwise.min.numerator = 1;
-	fival->stepwise.min.denominator = inst->cap_framerate.max;
+	fival->stepwise.min.denominator = frate_max(inst);
 	fival->stepwise.max.numerator = 1;
-	fival->stepwise.max.denominator = inst->cap_framerate.min;
+	fival->stepwise.max.denominator = frate_min(inst);
 	fival->stepwise.step.numerator = 1;
-	fival->stepwise.step.denominator = inst->cap_framerate.max;
+	fival->stepwise.step.denominator = frate_max(inst);
 
 	return 0;
 }
@@ -642,6 +654,14 @@ static int venc_set_properties(struct venus_inst *inst)
 	u32 ptype, rate_control, bitrate, profile = 0, level = 0;
 	int ret;
 
+	ret = venus_helper_set_work_mode(inst, VIDC_WORK_MODE_2);
+	if (ret)
+		return ret;
+
+	ret = venus_helper_set_core_usage(inst, VIDC_CORE_ID_2);
+	if (ret)
+		return ret;
+
 	ptype = HFI_PROPERTY_CONFIG_FRAME_RATE;
 	frate.buffer_type = HFI_BUFFER_OUTPUT;
 	frate.framerate = inst->fps * (1 << 16);
@@ -756,7 +776,7 @@ static int venc_set_properties(struct venus_inst *inst)
 		level = venc_v4l2_to_hfi(V4L2_CID_MPEG_VIDEO_H264_LEVEL,
 					 ctr->level.h264);
 	} else if (inst->fmt_cap->pixfmt == V4L2_PIX_FMT_VP8) {
-		profile = venc_v4l2_to_hfi(V4L2_CID_MPEG_VIDEO_VPX_PROFILE,
+		profile = venc_v4l2_to_hfi(V4L2_CID_MPEG_VIDEO_VP8_PROFILE,
 					   ctr->profile.vpx);
 		level = 0;
 	} else if (inst->fmt_cap->pixfmt == V4L2_PIX_FMT_MPEG4) {
@@ -767,6 +787,11 @@ static int venc_set_properties(struct venus_inst *inst)
 	} else if (inst->fmt_cap->pixfmt == V4L2_PIX_FMT_H263) {
 		profile = 0;
 		level = 0;
+	} else if (inst->fmt_cap->pixfmt == V4L2_PIX_FMT_HEVC) {
+		profile = venc_v4l2_to_hfi(V4L2_CID_MPEG_VIDEO_HEVC_PROFILE,
+					   ctr->profile.hevc);
+		level = venc_v4l2_to_hfi(V4L2_CID_MPEG_VIDEO_HEVC_LEVEL,
+					 ctr->level.hevc);
 	}
 
 	ptype = HFI_PROPERTY_PARAM_PROFILE_LEVEL_CURRENT;
@@ -794,7 +819,8 @@ static int venc_init_session(struct venus_inst *inst)
 		goto deinit;
 
 	ret = venus_helper_set_output_resolution(inst, inst->width,
-						 inst->height);
+						 inst->height,
+						 HFI_BUFFER_OUTPUT);
 	if (ret)
 		goto deinit;
 
@@ -835,7 +861,7 @@ static int venc_queue_setup(struct vb2_queue *q,
 			    unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct venus_inst *inst = vb2_get_drv_priv(q);
-	unsigned int p, num, min = 4;
+	unsigned int num, min = 4;
 	int ret = 0;
 
 	if (*num_planes) {
@@ -870,16 +896,18 @@ static int venc_queue_setup(struct vb2_queue *q,
 		*num_buffers = max(*num_buffers, num);
 		inst->num_input_bufs = *num_buffers;
 
-		for (p = 0; p < *num_planes; ++p)
-			sizes[p] = get_framesize_uncompressed(p, inst->width,
-							      inst->height);
+		sizes[0] = venus_helper_get_framesz(inst->fmt_out->pixfmt,
+						    inst->width,
+						    inst->height);
 		inst->input_buf_size = sizes[0];
 		break;
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
 		*num_planes = inst->fmt_cap->num_planes;
 		*num_buffers = max(*num_buffers, min);
 		inst->num_output_bufs = *num_buffers;
-		sizes[0] = get_framesize_compressed(inst->width, inst->height);
+		sizes[0] = venus_helper_get_framesz(inst->fmt_cap->pixfmt,
+						    inst->width,
+						    inst->height);
 		inst->output_buf_size = sizes[0];
 		break;
 	default:
@@ -892,6 +920,7 @@ static int venc_queue_setup(struct vb2_queue *q,
 
 static int venc_verify_conf(struct venus_inst *inst)
 {
+	enum hfi_version ver = inst->core->res->hfi_version;
 	struct hfi_buffer_requirements bufreq;
 	int ret;
 
@@ -903,7 +932,7 @@ static int venc_verify_conf(struct venus_inst *inst)
 		return ret;
 
 	if (inst->num_output_bufs < bufreq.count_actual ||
-	    inst->num_output_bufs < bufreq.count_min)
+	    inst->num_output_bufs < HFI_BUFREQ_COUNT_MIN(&bufreq, ver))
 		return -EINVAL;
 
 	ret = venus_helper_get_bufreq(inst, HFI_BUFFER_INPUT, &bufreq);
@@ -911,7 +940,7 @@ static int venc_verify_conf(struct venus_inst *inst)
 		return ret;
 
 	if (inst->num_input_bufs < bufreq.count_actual ||
-	    inst->num_input_bufs < bufreq.count_min)
+	    inst->num_input_bufs < HFI_BUFREQ_COUNT_MIN(&bufreq, ver))
 		return -EINVAL;
 
 	return 0;
@@ -952,7 +981,7 @@ static int venc_start_streaming(struct vb2_queue *q, unsigned int count)
 		goto deinit_sess;
 
 	ret = venus_helper_set_num_bufs(inst, inst->num_input_bufs,
-					inst->num_output_bufs);
+					inst->num_output_bufs, 0);
 	if (ret)
 		goto deinit_sess;
 
@@ -1090,22 +1119,7 @@ static void venc_inst_init(struct venus_inst *inst)
 	inst->fps = 15;
 	inst->timeperframe.numerator = 1;
 	inst->timeperframe.denominator = 15;
-
-	inst->cap_width.min = 96;
-	inst->cap_width.max = 1920;
-	if (inst->core->res->hfi_version == HFI_VERSION_3XX)
-		inst->cap_width.max = 3840;
-	inst->cap_width.step_size = 2;
-	inst->cap_height.min = 64;
-	inst->cap_height.max = ALIGN(1080, 32);
-	if (inst->core->res->hfi_version == HFI_VERSION_3XX)
-		inst->cap_height.max = ALIGN(2160, 32);
-	inst->cap_height.step_size = 2;
-	inst->cap_framerate.min = 1;
-	inst->cap_framerate.max = 30;
-	inst->cap_framerate.step_size = 1;
-	inst->cap_mbs_per_frame.min = 24;
-	inst->cap_mbs_per_frame.max = 8160;
+	inst->hfi_codec = HFI_VIDEO_CODEC_H264;
 }
 
 static int venc_open(struct file *file)
@@ -1118,6 +1132,7 @@ static int venc_open(struct file *file)
 	if (!inst)
 		return -ENOMEM;
 
+	INIT_LIST_HEAD(&inst->dpbbufs);
 	INIT_LIST_HEAD(&inst->registeredbufs);
 	INIT_LIST_HEAD(&inst->internalbufs);
 	INIT_LIST_HEAD(&inst->list);
@@ -1224,12 +1239,18 @@ static int venc_probe(struct platform_device *pdev)
 	if (!core)
 		return -EPROBE_DEFER;
 
-	if (core->res->hfi_version == HFI_VERSION_3XX) {
+	if (IS_V3(core) || IS_V4(core)) {
 		core->core1_clk = devm_clk_get(dev, "core");
 		if (IS_ERR(core->core1_clk))
 			return PTR_ERR(core->core1_clk);
 	}
 
+	if (IS_V4(core)) {
+		core->core1_bus_clk = devm_clk_get(dev, "bus");
+		if (IS_ERR(core->core1_bus_clk))
+			return PTR_ERR(core->core1_bus_clk);
+	}
+
 	platform_set_drvdata(pdev, core);
 
 	vdev = video_device_alloc();
@@ -1274,15 +1295,21 @@ static int venc_remove(struct platform_device *pdev)
 static __maybe_unused int venc_runtime_suspend(struct device *dev)
 {
 	struct venus_core *core = dev_get_drvdata(dev);
+	int ret;
 
-	if (core->res->hfi_version == HFI_VERSION_1XX)
+	if (IS_V1(core))
 		return 0;
 
-	writel(0, core->base + WRAPPER_VENC_VCODEC_POWER_CONTROL);
+	ret = venus_helper_power_enable(core, VIDC_SESSION_TYPE_ENC, true);
+	if (ret)
+		return ret;
+
+	if (IS_V4(core))
+		clk_disable_unprepare(core->core1_bus_clk);
+
 	clk_disable_unprepare(core->core1_clk);
-	writel(1, core->base + WRAPPER_VENC_VCODEC_POWER_CONTROL);
 
-	return 0;
+	return venus_helper_power_enable(core, VIDC_SESSION_TYPE_ENC, false);
 }
 
 static __maybe_unused int venc_runtime_resume(struct device *dev)
@@ -1290,13 +1317,29 @@ static __maybe_unused int venc_runtime_resume(struct device *dev)
 	struct venus_core *core = dev_get_drvdata(dev);
 	int ret;
 
-	if (core->res->hfi_version == HFI_VERSION_1XX)
+	if (IS_V1(core))
 		return 0;
 
-	writel(0, core->base + WRAPPER_VENC_VCODEC_POWER_CONTROL);
+	ret = venus_helper_power_enable(core, VIDC_SESSION_TYPE_ENC, true);
+	if (ret)
+		return ret;
+
 	ret = clk_prepare_enable(core->core1_clk);
-	writel(1, core->base + WRAPPER_VENC_VCODEC_POWER_CONTROL);
+	if (ret)
+		goto err_power_disable;
+
+	if (IS_V4(core))
+		ret = clk_prepare_enable(core->core1_bus_clk);
+
+	if (ret)
+		goto err_unprepare_core1;
+
+	return venus_helper_power_enable(core, VIDC_SESSION_TYPE_ENC, false);
 
+err_unprepare_core1:
+	clk_disable_unprepare(core->core1_clk);
+err_power_disable:
+	venus_helper_power_enable(core, VIDC_SESSION_TYPE_ENC, false);
 	return ret;
 }
 
diff --git a/drivers/media/platform/qcom/venus/venc_ctrls.c b/drivers/media/platform/qcom/venus/venc_ctrls.c
index 21e938a28662..459101728d26 100644
--- a/drivers/media/platform/qcom/venus/venc_ctrls.c
+++ b/drivers/media/platform/qcom/venus/venc_ctrls.c
@@ -101,7 +101,7 @@ static int venc_op_s_ctrl(struct v4l2_ctrl *ctrl)
 	case V4L2_CID_MPEG_VIDEO_H264_PROFILE:
 		ctr->profile.h264 = ctrl->val;
 		break;
-	case V4L2_CID_MPEG_VIDEO_VPX_PROFILE:
+	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:
 		ctr->profile.vpx = ctrl->val;
 		break;
 	case V4L2_CID_MPEG_VIDEO_MPEG4_LEVEL:
@@ -248,6 +248,11 @@ int venc_ctrl_init(struct venus_inst *inst)
 		V4L2_MPEG_VIDEO_MULTI_SICE_MODE_MAX_BYTES,
 		0, V4L2_MPEG_VIDEO_MULTI_SLICE_MODE_SINGLE);
 
+	v4l2_ctrl_new_std_menu(&inst->ctrl_handler, &venc_ctrl_ops,
+		V4L2_CID_MPEG_VIDEO_VP8_PROFILE,
+		V4L2_MPEG_VIDEO_VP8_PROFILE_3,
+		0, V4L2_MPEG_VIDEO_VP8_PROFILE_0);
+
 	v4l2_ctrl_new_std(&inst->ctrl_handler, &venc_ctrl_ops,
 		V4L2_CID_MPEG_VIDEO_BITRATE, BITRATE_MIN, BITRATE_MAX,
 		BITRATE_STEP, BITRATE_DEFAULT);
@@ -257,9 +262,6 @@ int venc_ctrl_init(struct venus_inst *inst)
 		BITRATE_STEP, BITRATE_DEFAULT_PEAK);
 
 	v4l2_ctrl_new_std(&inst->ctrl_handler, &venc_ctrl_ops,
-		V4L2_CID_MPEG_VIDEO_VPX_PROFILE, 0, 3, 1, 0);
-
-	v4l2_ctrl_new_std(&inst->ctrl_handler, &venc_ctrl_ops,
 		V4L2_CID_MPEG_VIDEO_H264_I_FRAME_QP, 1, 51, 1, 26);
 
 	v4l2_ctrl_new_std(&inst->ctrl_handler, &venc_ctrl_ops,
diff --git a/drivers/media/platform/rcar-fcp.c b/drivers/media/platform/rcar-fcp.c
index 2988031d285d..b47af8eb145a 100644
--- a/drivers/media/platform/rcar-fcp.c
+++ b/drivers/media/platform/rcar-fcp.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * rcar-fcp.c  --  R-Car Frame Compression Processor Driver
  *
  * Copyright (C) 2016 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/device.h>
diff --git a/drivers/media/platform/rcar-vin/Kconfig b/drivers/media/platform/rcar-vin/Kconfig
index baf4eafff6e3..e3eb8fee2536 100644
--- a/drivers/media/platform/rcar-vin/Kconfig
+++ b/drivers/media/platform/rcar-vin/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 config VIDEO_RCAR_CSI2
 	tristate "R-Car MIPI CSI-2 Receiver"
 	depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API && OF
diff --git a/drivers/media/platform/rcar-vin/Makefile b/drivers/media/platform/rcar-vin/Makefile
index 5ab803d3e7c1..00d809f5d2c1 100644
--- a/drivers/media/platform/rcar-vin/Makefile
+++ b/drivers/media/platform/rcar-vin/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 rcar-vin-objs = rcar-core.o rcar-dma.o rcar-v4l2.o
 
 obj-$(CONFIG_VIDEO_RCAR_CSI2) += rcar-csi2.o
diff --git a/drivers/media/platform/rcar-vin/rcar-core.c b/drivers/media/platform/rcar-vin/rcar-core.c
index d3072e166a1c..ce09799976ef 100644
--- a/drivers/media/platform/rcar-vin/rcar-core.c
+++ b/drivers/media/platform/rcar-vin/rcar-core.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Driver for Renesas R-Car VIN
  *
@@ -7,11 +8,6 @@
  * Copyright (C) 2008 Magnus Damm
  *
  * Based on the soc-camera rcar_vin driver
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/module.h>
@@ -46,6 +42,8 @@
  */
 #define rvin_group_id_to_master(vin) ((vin) < 4 ? 0 : 4)
 
+#define v4l2_dev_to_vin(d)	container_of(d, struct rvin_dev, v4l2_dev)
+
 /* -----------------------------------------------------------------------------
  * Media Controller link notification
  */
@@ -169,9 +167,37 @@ static int rvin_group_link_notify(struct media_link *link, u32 flags,
 
 	/* Add the new link to the existing mask and check if it works. */
 	csi_id = rvin_group_entity_to_csi_id(group, link->source->entity);
+
+	if (csi_id == -ENODEV) {
+		struct v4l2_subdev *sd;
+		unsigned int i;
+
+		/*
+		 * Make sure the source entity subdevice is registered as
+		 * a parallel input of one of the enabled VINs if it is not
+		 * one of the CSI-2 subdevices.
+		 *
+		 * No hardware configuration required for parallel inputs,
+		 * we can return here.
+		 */
+		sd = media_entity_to_v4l2_subdev(link->source->entity);
+		for (i = 0; i < RCAR_VIN_NUM; i++) {
+			if (group->vin[i] && group->vin[i]->parallel &&
+			    group->vin[i]->parallel->subdev == sd) {
+				group->vin[i]->is_csi = false;
+				ret = 0;
+				goto out;
+			}
+		}
+
+		vin_err(vin, "Subdevice %s not registered to any VIN\n",
+			link->source->entity->name);
+		ret = -ENODEV;
+		goto out;
+	}
+
 	channel = rvin_group_csi_pad_to_channel(link->source->index);
 	mask_new = mask & rvin_group_get_mask(vin, csi_id, channel);
-
 	vin_dbg(vin, "Try link change mask: 0x%x new: 0x%x\n", mask, mask_new);
 
 	if (!mask_new) {
@@ -181,6 +207,11 @@ static int rvin_group_link_notify(struct media_link *link, u32 flags,
 
 	/* New valid CHSEL found, set the new value. */
 	ret = rvin_set_channel_routing(group->vin[master_id], __ffs(mask_new));
+	if (ret)
+		goto out;
+
+	vin->is_csi = true;
+
 out:
 	mutex_unlock(&group->lock);
 
@@ -359,8 +390,6 @@ out:
  * Async notifier
  */
 
-#define notifier_to_vin(n) container_of(n, struct rvin_dev, notifier)
-
 static int rvin_find_pad(struct v4l2_subdev *sd, int direction)
 {
 	unsigned int pad;
@@ -376,12 +405,12 @@ static int rvin_find_pad(struct v4l2_subdev *sd, int direction)
 }
 
 /* -----------------------------------------------------------------------------
- * Digital async notifier
+ * Parallel async notifier
  */
 
 /* The vin lock should be held when calling the subdevice attach and detach */
-static int rvin_digital_subdevice_attach(struct rvin_dev *vin,
-					 struct v4l2_subdev *subdev)
+static int rvin_parallel_subdevice_attach(struct rvin_dev *vin,
+					  struct v4l2_subdev *subdev)
 {
 	struct v4l2_subdev_mbus_code_enum code = {
 		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
@@ -392,15 +421,20 @@ static int rvin_digital_subdevice_attach(struct rvin_dev *vin,
 	ret = rvin_find_pad(subdev, MEDIA_PAD_FL_SOURCE);
 	if (ret < 0)
 		return ret;
-	vin->digital->source_pad = ret;
+	vin->parallel->source_pad = ret;
 
 	ret = rvin_find_pad(subdev, MEDIA_PAD_FL_SINK);
-	vin->digital->sink_pad = ret < 0 ? 0 : ret;
+	vin->parallel->sink_pad = ret < 0 ? 0 : ret;
+
+	if (vin->info->use_mc) {
+		vin->parallel->subdev = subdev;
+		return 0;
+	}
 
 	/* Find compatible subdevices mbus format */
 	vin->mbus_code = 0;
 	code.index = 0;
-	code.pad = vin->digital->source_pad;
+	code.pad = vin->parallel->source_pad;
 	while (!vin->mbus_code &&
 	       !v4l2_subdev_call(subdev, pad, enum_mbus_code, NULL, &code)) {
 		code.index++;
@@ -450,23 +484,27 @@ static int rvin_digital_subdevice_attach(struct rvin_dev *vin,
 
 	vin->vdev.ctrl_handler = &vin->ctrl_handler;
 
-	vin->digital->subdev = subdev;
+	vin->parallel->subdev = subdev;
 
 	return 0;
 }
 
-static void rvin_digital_subdevice_detach(struct rvin_dev *vin)
+static void rvin_parallel_subdevice_detach(struct rvin_dev *vin)
 {
 	rvin_v4l2_unregister(vin);
-	v4l2_ctrl_handler_free(&vin->ctrl_handler);
+	vin->parallel->subdev = NULL;
 
-	vin->vdev.ctrl_handler = NULL;
-	vin->digital->subdev = NULL;
+	if (!vin->info->use_mc) {
+		v4l2_ctrl_handler_free(&vin->ctrl_handler);
+		vin->vdev.ctrl_handler = NULL;
+	}
 }
 
-static int rvin_digital_notify_complete(struct v4l2_async_notifier *notifier)
+static int rvin_parallel_notify_complete(struct v4l2_async_notifier *notifier)
 {
-	struct rvin_dev *vin = notifier_to_vin(notifier);
+	struct rvin_dev *vin = v4l2_dev_to_vin(notifier->v4l2_dev);
+	struct media_entity *source;
+	struct media_entity *sink;
 	int ret;
 
 	ret = v4l2_device_register_subdev_nodes(&vin->v4l2_dev);
@@ -475,31 +513,50 @@ static int rvin_digital_notify_complete(struct v4l2_async_notifier *notifier)
 		return ret;
 	}
 
-	return rvin_v4l2_register(vin);
+	if (!video_is_registered(&vin->vdev)) {
+		ret = rvin_v4l2_register(vin);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (!vin->info->use_mc)
+		return 0;
+
+	/* If we're running with media-controller, link the subdevs. */
+	source = &vin->parallel->subdev->entity;
+	sink = &vin->vdev.entity;
+
+	ret = media_create_pad_link(source, vin->parallel->source_pad,
+				    sink, vin->parallel->sink_pad, 0);
+	if (ret)
+		vin_err(vin, "Error adding link from %s to %s: %d\n",
+			source->name, sink->name, ret);
+
+	return ret;
 }
 
-static void rvin_digital_notify_unbind(struct v4l2_async_notifier *notifier,
-				       struct v4l2_subdev *subdev,
-				       struct v4l2_async_subdev *asd)
+static void rvin_parallel_notify_unbind(struct v4l2_async_notifier *notifier,
+					struct v4l2_subdev *subdev,
+					struct v4l2_async_subdev *asd)
 {
-	struct rvin_dev *vin = notifier_to_vin(notifier);
+	struct rvin_dev *vin = v4l2_dev_to_vin(notifier->v4l2_dev);
 
-	vin_dbg(vin, "unbind digital subdev %s\n", subdev->name);
+	vin_dbg(vin, "unbind parallel subdev %s\n", subdev->name);
 
 	mutex_lock(&vin->lock);
-	rvin_digital_subdevice_detach(vin);
+	rvin_parallel_subdevice_detach(vin);
 	mutex_unlock(&vin->lock);
 }
 
-static int rvin_digital_notify_bound(struct v4l2_async_notifier *notifier,
-				     struct v4l2_subdev *subdev,
-				     struct v4l2_async_subdev *asd)
+static int rvin_parallel_notify_bound(struct v4l2_async_notifier *notifier,
+				      struct v4l2_subdev *subdev,
+				      struct v4l2_async_subdev *asd)
 {
-	struct rvin_dev *vin = notifier_to_vin(notifier);
+	struct rvin_dev *vin = v4l2_dev_to_vin(notifier->v4l2_dev);
 	int ret;
 
 	mutex_lock(&vin->lock);
-	ret = rvin_digital_subdevice_attach(vin, subdev);
+	ret = rvin_parallel_subdevice_attach(vin, subdev);
 	mutex_unlock(&vin->lock);
 	if (ret)
 		return ret;
@@ -507,70 +564,71 @@ static int rvin_digital_notify_bound(struct v4l2_async_notifier *notifier,
 	v4l2_set_subdev_hostdata(subdev, vin);
 
 	vin_dbg(vin, "bound subdev %s source pad: %u sink pad: %u\n",
-		subdev->name, vin->digital->source_pad,
-		vin->digital->sink_pad);
+		subdev->name, vin->parallel->source_pad,
+		vin->parallel->sink_pad);
 
 	return 0;
 }
 
-static const struct v4l2_async_notifier_operations rvin_digital_notify_ops = {
-	.bound = rvin_digital_notify_bound,
-	.unbind = rvin_digital_notify_unbind,
-	.complete = rvin_digital_notify_complete,
+static const struct v4l2_async_notifier_operations rvin_parallel_notify_ops = {
+	.bound = rvin_parallel_notify_bound,
+	.unbind = rvin_parallel_notify_unbind,
+	.complete = rvin_parallel_notify_complete,
 };
 
-static int rvin_digital_parse_v4l2(struct device *dev,
-				   struct v4l2_fwnode_endpoint *vep,
-				   struct v4l2_async_subdev *asd)
+static int rvin_parallel_parse_v4l2(struct device *dev,
+				    struct v4l2_fwnode_endpoint *vep,
+				    struct v4l2_async_subdev *asd)
 {
 	struct rvin_dev *vin = dev_get_drvdata(dev);
-	struct rvin_graph_entity *rvge =
-		container_of(asd, struct rvin_graph_entity, asd);
+	struct rvin_parallel_entity *rvpe =
+		container_of(asd, struct rvin_parallel_entity, asd);
 
 	if (vep->base.port || vep->base.id)
 		return -ENOTCONN;
 
-	vin->mbus_cfg.type = vep->bus_type;
+	vin->parallel = rvpe;
+	vin->parallel->mbus_type = vep->bus_type;
 
-	switch (vin->mbus_cfg.type) {
+	switch (vin->parallel->mbus_type) {
 	case V4L2_MBUS_PARALLEL:
 		vin_dbg(vin, "Found PARALLEL media bus\n");
-		vin->mbus_cfg.flags = vep->bus.parallel.flags;
+		vin->parallel->mbus_flags = vep->bus.parallel.flags;
 		break;
 	case V4L2_MBUS_BT656:
 		vin_dbg(vin, "Found BT656 media bus\n");
-		vin->mbus_cfg.flags = 0;
+		vin->parallel->mbus_flags = 0;
 		break;
 	default:
 		vin_err(vin, "Unknown media bus type\n");
 		return -EINVAL;
 	}
 
-	vin->digital = rvge;
-
 	return 0;
 }
 
-static int rvin_digital_graph_init(struct rvin_dev *vin)
+static int rvin_parallel_init(struct rvin_dev *vin)
 {
 	int ret;
 
-	ret = v4l2_async_notifier_parse_fwnode_endpoints(
-		vin->dev, &vin->notifier,
-		sizeof(struct rvin_graph_entity), rvin_digital_parse_v4l2);
+	ret = v4l2_async_notifier_parse_fwnode_endpoints_by_port(
+		vin->dev, &vin->notifier, sizeof(struct rvin_parallel_entity),
+		0, rvin_parallel_parse_v4l2);
 	if (ret)
 		return ret;
 
-	if (!vin->digital)
-		return -ENODEV;
+	/* If using mc, it's fine not to have any input registered. */
+	if (!vin->parallel)
+		return vin->info->use_mc ? 0 : -ENODEV;
 
-	vin_dbg(vin, "Found digital subdevice %pOF\n",
-		to_of_node(vin->digital->asd.match.fwnode));
+	vin_dbg(vin, "Found parallel subdevice %pOF\n",
+		to_of_node(vin->parallel->asd.match.fwnode));
 
-	vin->notifier.ops = &rvin_digital_notify_ops;
+	vin->notifier.ops = &rvin_parallel_notify_ops;
 	ret = v4l2_async_notifier_register(&vin->v4l2_dev, &vin->notifier);
 	if (ret < 0) {
 		vin_err(vin, "Notifier registration failed\n");
+		v4l2_async_notifier_cleanup(&vin->group->notifier);
 		return ret;
 	}
 
@@ -583,7 +641,7 @@ static int rvin_digital_graph_init(struct rvin_dev *vin)
 
 static int rvin_group_notify_complete(struct v4l2_async_notifier *notifier)
 {
-	struct rvin_dev *vin = notifier_to_vin(notifier);
+	struct rvin_dev *vin = v4l2_dev_to_vin(notifier->v4l2_dev);
 	const struct rvin_group_route *route;
 	unsigned int i;
 	int ret;
@@ -596,7 +654,8 @@ static int rvin_group_notify_complete(struct v4l2_async_notifier *notifier)
 
 	/* Register all video nodes for the group. */
 	for (i = 0; i < RCAR_VIN_NUM; i++) {
-		if (vin->group->vin[i]) {
+		if (vin->group->vin[i] &&
+		    !video_is_registered(&vin->group->vin[i]->vdev)) {
 			ret = rvin_v4l2_register(vin->group->vin[i]);
 			if (ret)
 				return ret;
@@ -649,7 +708,7 @@ static void rvin_group_notify_unbind(struct v4l2_async_notifier *notifier,
 				     struct v4l2_subdev *subdev,
 				     struct v4l2_async_subdev *asd)
 {
-	struct rvin_dev *vin = notifier_to_vin(notifier);
+	struct rvin_dev *vin = v4l2_dev_to_vin(notifier->v4l2_dev);
 	unsigned int i;
 
 	for (i = 0; i < RCAR_VIN_NUM; i++)
@@ -673,7 +732,7 @@ static int rvin_group_notify_bound(struct v4l2_async_notifier *notifier,
 				   struct v4l2_subdev *subdev,
 				   struct v4l2_async_subdev *asd)
 {
-	struct rvin_dev *vin = notifier_to_vin(notifier);
+	struct rvin_dev *vin = v4l2_dev_to_vin(notifier->v4l2_dev);
 	unsigned int i;
 
 	mutex_lock(&vin->group->lock);
@@ -707,11 +766,9 @@ static int rvin_mc_parse_of_endpoint(struct device *dev,
 		return -EINVAL;
 
 	if (!of_device_is_available(to_of_node(asd->match.fwnode))) {
-
 		vin_dbg(vin, "OF device %pOF disabled, ignoring\n",
 			to_of_node(asd->match.fwnode));
 		return -ENOTCONN;
-
 	}
 
 	if (vin->group->csi[vep->base.id].fwnode) {
@@ -736,12 +793,6 @@ static int rvin_mc_parse_of_graph(struct rvin_dev *vin)
 
 	mutex_lock(&vin->group->lock);
 
-	/* If there already is a notifier something has gone wrong, bail out. */
-	if (WARN_ON(vin->group->notifier)) {
-		mutex_unlock(&vin->group->lock);
-		return -EINVAL;
-	}
-
 	/* If not all VIN's are registered don't register the notifier. */
 	for (i = 0; i < RCAR_VIN_NUM; i++)
 		if (vin->group->vin[i])
@@ -753,19 +804,16 @@ static int rvin_mc_parse_of_graph(struct rvin_dev *vin)
 	}
 
 	/*
-	 * Have all VIN's look for subdevices. Some subdevices will overlap
-	 * but the parser function can handle it, so each subdevice will
-	 * only be registered once with the notifier.
+	 * Have all VIN's look for CSI-2 subdevices. Some subdevices will
+	 * overlap but the parser function can handle it, so each subdevice
+	 * will only be registered once with the group notifier.
 	 */
-
-	vin->group->notifier = &vin->notifier;
-
 	for (i = 0; i < RCAR_VIN_NUM; i++) {
 		if (!vin->group->vin[i])
 			continue;
 
 		ret = v4l2_async_notifier_parse_fwnode_endpoints_by_port(
-				vin->group->vin[i]->dev, vin->group->notifier,
+				vin->group->vin[i]->dev, &vin->group->notifier,
 				sizeof(struct v4l2_async_subdev), 1,
 				rvin_mc_parse_of_endpoint);
 		if (ret) {
@@ -776,11 +824,15 @@ static int rvin_mc_parse_of_graph(struct rvin_dev *vin)
 
 	mutex_unlock(&vin->group->lock);
 
-	vin->group->notifier->ops = &rvin_group_notify_ops;
+	if (!vin->group->notifier.num_subdevs)
+		return 0;
 
-	ret = v4l2_async_notifier_register(&vin->v4l2_dev, &vin->notifier);
+	vin->group->notifier.ops = &rvin_group_notify_ops;
+	ret = v4l2_async_notifier_register(&vin->v4l2_dev,
+					   &vin->group->notifier);
 	if (ret < 0) {
 		vin_err(vin, "Notifier registration failed\n");
+		v4l2_async_notifier_cleanup(&vin->group->notifier);
 		return ret;
 	}
 
@@ -791,10 +843,6 @@ static int rvin_mc_init(struct rvin_dev *vin)
 {
 	int ret;
 
-	/* All our sources are CSI-2 */
-	vin->mbus_cfg.type = V4L2_MBUS_CSI2;
-	vin->mbus_cfg.flags = 0;
-
 	vin->pad.flags = MEDIA_PAD_FL_SINK;
 	ret = media_entity_pads_init(&vin->vdev.entity, 1, &vin->pad);
 	if (ret)
@@ -974,7 +1022,51 @@ static const struct rvin_info rcar_info_r8a7796 = {
 	.routes = rcar_info_r8a7796_routes,
 };
 
-static const struct rvin_group_route _rcar_info_r8a77970_routes[] = {
+static const struct rvin_group_route rcar_info_r8a77965_routes[] = {
+	{ .csi = RVIN_CSI40, .channel = 0, .vin = 0, .mask = BIT(0) | BIT(3) },
+	{ .csi = RVIN_CSI20, .channel = 0, .vin = 0, .mask = BIT(1) | BIT(4) },
+	{ .csi = RVIN_CSI40, .channel = 1, .vin = 0, .mask = BIT(2) },
+	{ .csi = RVIN_CSI20, .channel = 0, .vin = 1, .mask = BIT(0) },
+	{ .csi = RVIN_CSI40, .channel = 1, .vin = 1, .mask = BIT(1) | BIT(3) },
+	{ .csi = RVIN_CSI40, .channel = 0, .vin = 1, .mask = BIT(2) },
+	{ .csi = RVIN_CSI20, .channel = 1, .vin = 1, .mask = BIT(4) },
+	{ .csi = RVIN_CSI20, .channel = 1, .vin = 2, .mask = BIT(0) },
+	{ .csi = RVIN_CSI40, .channel = 0, .vin = 2, .mask = BIT(1) },
+	{ .csi = RVIN_CSI20, .channel = 0, .vin = 2, .mask = BIT(2) },
+	{ .csi = RVIN_CSI40, .channel = 2, .vin = 2, .mask = BIT(3) },
+	{ .csi = RVIN_CSI20, .channel = 2, .vin = 2, .mask = BIT(4) },
+	{ .csi = RVIN_CSI40, .channel = 1, .vin = 3, .mask = BIT(0) },
+	{ .csi = RVIN_CSI20, .channel = 1, .vin = 3, .mask = BIT(1) | BIT(2) },
+	{ .csi = RVIN_CSI40, .channel = 3, .vin = 3, .mask = BIT(3) },
+	{ .csi = RVIN_CSI20, .channel = 3, .vin = 3, .mask = BIT(4) },
+	{ .csi = RVIN_CSI40, .channel = 0, .vin = 4, .mask = BIT(0) | BIT(3) },
+	{ .csi = RVIN_CSI20, .channel = 0, .vin = 4, .mask = BIT(1) | BIT(4) },
+	{ .csi = RVIN_CSI40, .channel = 1, .vin = 4, .mask = BIT(2) },
+	{ .csi = RVIN_CSI20, .channel = 0, .vin = 5, .mask = BIT(0) },
+	{ .csi = RVIN_CSI40, .channel = 1, .vin = 5, .mask = BIT(1) | BIT(3) },
+	{ .csi = RVIN_CSI40, .channel = 0, .vin = 5, .mask = BIT(2) },
+	{ .csi = RVIN_CSI20, .channel = 1, .vin = 5, .mask = BIT(4) },
+	{ .csi = RVIN_CSI20, .channel = 1, .vin = 6, .mask = BIT(0) },
+	{ .csi = RVIN_CSI40, .channel = 0, .vin = 6, .mask = BIT(1) },
+	{ .csi = RVIN_CSI20, .channel = 0, .vin = 6, .mask = BIT(2) },
+	{ .csi = RVIN_CSI40, .channel = 2, .vin = 6, .mask = BIT(3) },
+	{ .csi = RVIN_CSI20, .channel = 2, .vin = 6, .mask = BIT(4) },
+	{ .csi = RVIN_CSI40, .channel = 1, .vin = 7, .mask = BIT(0) },
+	{ .csi = RVIN_CSI20, .channel = 1, .vin = 7, .mask = BIT(1) | BIT(2) },
+	{ .csi = RVIN_CSI40, .channel = 3, .vin = 7, .mask = BIT(3) },
+	{ .csi = RVIN_CSI20, .channel = 3, .vin = 7, .mask = BIT(4) },
+	{ /* Sentinel */ }
+};
+
+static const struct rvin_info rcar_info_r8a77965 = {
+	.model = RCAR_GEN3,
+	.use_mc = true,
+	.max_width = 4096,
+	.max_height = 4096,
+	.routes = rcar_info_r8a77965_routes,
+};
+
+static const struct rvin_group_route rcar_info_r8a77970_routes[] = {
 	{ .csi = RVIN_CSI40, .channel = 0, .vin = 0, .mask = BIT(0) | BIT(3) },
 	{ .csi = RVIN_CSI40, .channel = 0, .vin = 1, .mask = BIT(2) },
 	{ .csi = RVIN_CSI40, .channel = 1, .vin = 1, .mask = BIT(3) },
@@ -990,7 +1082,19 @@ static const struct rvin_info rcar_info_r8a77970 = {
 	.use_mc = true,
 	.max_width = 4096,
 	.max_height = 4096,
-	.routes = _rcar_info_r8a77970_routes,
+	.routes = rcar_info_r8a77970_routes,
+};
+
+static const struct rvin_group_route rcar_info_r8a77995_routes[] = {
+	{ /* Sentinel */ }
+};
+
+static const struct rvin_info rcar_info_r8a77995 = {
+	.model = RCAR_GEN3,
+	.use_mc = true,
+	.max_width = 4096,
+	.max_height = 4096,
+	.routes = rcar_info_r8a77995_routes,
 };
 
 static const struct of_device_id rvin_of_id_table[] = {
@@ -1031,9 +1135,17 @@ static const struct of_device_id rvin_of_id_table[] = {
 		.data = &rcar_info_r8a7796,
 	},
 	{
+		.compatible = "renesas,vin-r8a77965",
+		.data = &rcar_info_r8a77965,
+	},
+	{
 		.compatible = "renesas,vin-r8a77970",
 		.data = &rcar_info_r8a77970,
 	},
+	{
+		.compatible = "renesas,vin-r8a77995",
+		.data = &rcar_info_r8a77995,
+	},
 	{ /* Sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, rvin_of_id_table);
@@ -1085,20 +1197,35 @@ static int rcar_vin_probe(struct platform_device *pdev)
 		return ret;
 
 	platform_set_drvdata(pdev, vin);
-	if (vin->info->use_mc)
+
+	if (vin->info->use_mc) {
 		ret = rvin_mc_init(vin);
-	else
-		ret = rvin_digital_graph_init(vin);
-	if (ret < 0)
-		goto error;
+		if (ret)
+			goto error_dma_unregister;
+	}
+
+	ret = rvin_parallel_init(vin);
+	if (ret)
+		goto error_group_unregister;
 
 	pm_suspend_ignore_children(&pdev->dev, true);
 	pm_runtime_enable(&pdev->dev);
 
 	return 0;
-error:
+
+error_group_unregister:
+	if (vin->info->use_mc) {
+		mutex_lock(&vin->group->lock);
+		if (&vin->v4l2_dev == vin->group->notifier.v4l2_dev) {
+			v4l2_async_notifier_unregister(&vin->group->notifier);
+			v4l2_async_notifier_cleanup(&vin->group->notifier);
+		}
+		mutex_unlock(&vin->group->lock);
+		rvin_group_put(vin);
+	}
+
+error_dma_unregister:
 	rvin_dma_unregister(vin);
-	v4l2_async_notifier_cleanup(&vin->notifier);
 
 	return ret;
 }
@@ -1116,8 +1243,10 @@ static int rcar_vin_remove(struct platform_device *pdev)
 
 	if (vin->info->use_mc) {
 		mutex_lock(&vin->group->lock);
-		if (vin->group->notifier == &vin->notifier)
-			vin->group->notifier = NULL;
+		if (&vin->v4l2_dev == vin->group->notifier.v4l2_dev) {
+			v4l2_async_notifier_unregister(&vin->group->notifier);
+			v4l2_async_notifier_cleanup(&vin->group->notifier);
+		}
 		mutex_unlock(&vin->group->lock);
 		rvin_group_put(vin);
 	} else {
@@ -1142,4 +1271,4 @@ module_platform_driver(rcar_vin_driver);
 
 MODULE_AUTHOR("Niklas Söderlund <niklas.soderlund@ragnatech.se>");
 MODULE_DESCRIPTION("Renesas R-Car VIN camera host driver");
-MODULE_LICENSE("GPL v2");
+MODULE_LICENSE("GPL");
diff --git a/drivers/media/platform/rcar-vin/rcar-csi2.c b/drivers/media/platform/rcar-vin/rcar-csi2.c
index daef72d410a3..dc5ae8025832 100644
--- a/drivers/media/platform/rcar-vin/rcar-csi2.c
+++ b/drivers/media/platform/rcar-vin/rcar-csi2.c
@@ -339,6 +339,7 @@ enum rcar_csi2_pads {
 
 struct rcar_csi2_info {
 	int (*init_phtw)(struct rcar_csi2 *priv, unsigned int mbps);
+	int (*confirm_start)(struct rcar_csi2 *priv);
 	const struct rcsi2_mbps_reg *hsfreqrange;
 	unsigned int csi0clkfreqrange;
 	bool clear_ulps;
@@ -545,6 +546,13 @@ static int rcsi2_start(struct rcar_csi2 *priv)
 	if (ret)
 		return ret;
 
+	/* Confirm start */
+	if (priv->info->confirm_start) {
+		ret = priv->info->confirm_start(priv);
+		if (ret)
+			return ret;
+	}
+
 	/* Clear Ultra Low Power interrupt. */
 	if (priv->info->clear_ulps)
 		rcsi2_write(priv, INTSTATE_REG,
@@ -881,6 +889,11 @@ static int rcsi2_init_phtw_h3_v3h_m3n(struct rcar_csi2 *priv, unsigned int mbps)
 
 static int rcsi2_init_phtw_v3m_e3(struct rcar_csi2 *priv, unsigned int mbps)
 {
+	return rcsi2_phtw_write_mbps(priv, mbps, phtw_mbps_v3m_e3, 0x44);
+}
+
+static int rcsi2_confirm_start_v3m_e3(struct rcar_csi2 *priv)
+{
 	static const struct phtw_value step1[] = {
 		{ .data = 0xed, .code = 0x34 },
 		{ .data = 0xed, .code = 0x44 },
@@ -890,12 +903,6 @@ static int rcsi2_init_phtw_v3m_e3(struct rcar_csi2 *priv, unsigned int mbps)
 		{ /* sentinel */ },
 	};
 
-	int ret;
-
-	ret = rcsi2_phtw_write_mbps(priv, mbps, phtw_mbps_v3m_e3, 0x44);
-	if (ret)
-		return ret;
-
 	return rcsi2_phtw_write_array(priv, step1);
 }
 
@@ -949,6 +956,7 @@ static const struct rcar_csi2_info rcar_csi2_info_r8a77965 = {
 
 static const struct rcar_csi2_info rcar_csi2_info_r8a77970 = {
 	.init_phtw = rcsi2_init_phtw_v3m_e3,
+	.confirm_start = rcsi2_confirm_start_v3m_e3,
 };
 
 static const struct of_device_id rcar_csi2_of_table[] = {
diff --git a/drivers/media/platform/rcar-vin/rcar-dma.c b/drivers/media/platform/rcar-vin/rcar-dma.c
index ac07f99e3516..92323310f735 100644
--- a/drivers/media/platform/rcar-vin/rcar-dma.c
+++ b/drivers/media/platform/rcar-vin/rcar-dma.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Driver for Renesas R-Car VIN
  *
@@ -7,11 +8,6 @@
  * Copyright (C) 2008 Magnus Damm
  *
  * Based on the soc-camera rcar_vin driver
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/delay.h>
@@ -123,6 +119,7 @@
 /* Video n Data Mode Register 2 bits */
 #define VNDMR2_VPS		(1 << 30)
 #define VNDMR2_HPS		(1 << 29)
+#define VNDMR2_CES		(1 << 28)
 #define VNDMR2_FTEV		(1 << 17)
 #define VNDMR2_VLV(n)		((n & 0xf) << 12)
 
@@ -659,8 +656,12 @@ static int rvin_setup(struct rvin_dev *vin)
 		break;
 	case MEDIA_BUS_FMT_UYVY8_2X8:
 		/* BT.656 8bit YCbCr422 or BT.601 8bit YCbCr422 */
-		vnmc |= vin->mbus_cfg.type == V4L2_MBUS_BT656 ?
-			VNMC_INF_YUV8_BT656 : VNMC_INF_YUV8_BT601;
+		if (!vin->is_csi &&
+		    vin->parallel->mbus_type == V4L2_MBUS_BT656)
+			vnmc |= VNMC_INF_YUV8_BT656;
+		else
+			vnmc |= VNMC_INF_YUV8_BT601;
+
 		input_is_yuv = true;
 		break;
 	case MEDIA_BUS_FMT_RGB888_1X24:
@@ -668,8 +669,12 @@ static int rvin_setup(struct rvin_dev *vin)
 		break;
 	case MEDIA_BUS_FMT_UYVY10_2X10:
 		/* BT.656 10bit YCbCr422 or BT.601 10bit YCbCr422 */
-		vnmc |= vin->mbus_cfg.type == V4L2_MBUS_BT656 ?
-			VNMC_INF_YUV10_BT656 : VNMC_INF_YUV10_BT601;
+		if (!vin->is_csi &&
+		    vin->parallel->mbus_type == V4L2_MBUS_BT656)
+			vnmc |= VNMC_INF_YUV10_BT656;
+		else
+			vnmc |= VNMC_INF_YUV10_BT601;
+
 		input_is_yuv = true;
 		break;
 	default:
@@ -682,13 +687,19 @@ static int rvin_setup(struct rvin_dev *vin)
 	else
 		dmr2 = VNDMR2_FTEV | VNDMR2_VLV(1);
 
-	/* Hsync Signal Polarity Select */
-	if (!(vin->mbus_cfg.flags & V4L2_MBUS_HSYNC_ACTIVE_LOW))
-		dmr2 |= VNDMR2_HPS;
+	if (!vin->is_csi) {
+		/* Hsync Signal Polarity Select */
+		if (!(vin->parallel->mbus_flags & V4L2_MBUS_HSYNC_ACTIVE_LOW))
+			dmr2 |= VNDMR2_HPS;
+
+		/* Vsync Signal Polarity Select */
+		if (!(vin->parallel->mbus_flags & V4L2_MBUS_VSYNC_ACTIVE_LOW))
+			dmr2 |= VNDMR2_VPS;
 
-	/* Vsync Signal Polarity Select */
-	if (!(vin->mbus_cfg.flags & V4L2_MBUS_VSYNC_ACTIVE_LOW))
-		dmr2 |= VNDMR2_VPS;
+		/* Data Enable Polarity Select */
+		if (vin->parallel->mbus_flags & V4L2_MBUS_DATA_ENABLE_LOW)
+			dmr2 |= VNDMR2_CES;
+	}
 
 	/*
 	 * Output format
@@ -733,8 +744,8 @@ static int rvin_setup(struct rvin_dev *vin)
 		vnmc |= VNMC_BPS;
 
 	if (vin->info->model == RCAR_GEN3) {
-		/* Select between CSI-2 and Digital input */
-		if (vin->mbus_cfg.type == V4L2_MBUS_CSI2)
+		/* Select between CSI-2 and parallel input */
+		if (vin->is_csi)
 			vnmc &= ~VNMC_DPINE;
 		else
 			vnmc |= VNMC_DPINE;
@@ -856,7 +867,7 @@ static int rvin_capture_start(struct rvin_dev *vin)
 	/* Continuous Frame Capture Mode */
 	rvin_write(vin, VNFC_C_FRAME, VNFC_REG);
 
-	vin->state = RUNNING;
+	vin->state = STARTING;
 
 	return 0;
 }
@@ -910,6 +921,20 @@ static irqreturn_t rvin_irq(int irq, void *data)
 	vnms = rvin_read(vin, VNMS_REG);
 	slot = (vnms & VNMS_FBS_MASK) >> VNMS_FBS_SHIFT;
 
+	/*
+	 * To hand buffers back in a known order to userspace start
+	 * to capture first from slot 0.
+	 */
+	if (vin->state == STARTING) {
+		if (slot != 0) {
+			vin_dbg(vin, "Starting sync slot: %d\n", slot);
+			goto done;
+		}
+
+		vin_dbg(vin, "Capture start synced!\n");
+		vin->state = RUNNING;
+	}
+
 	/* Capture frame */
 	if (vin->queue_buf[slot]) {
 		vin->queue_buf[slot]->field = vin->format.field;
@@ -1074,7 +1099,7 @@ static int rvin_set_stream(struct rvin_dev *vin, int on)
 
 	/* No media controller used, simply pass operation to subdevice. */
 	if (!vin->info->use_mc) {
-		ret = v4l2_subdev_call(vin->digital->subdev, video, s_stream,
+		ret = v4l2_subdev_call(vin->parallel->subdev, video, s_stream,
 				       on);
 
 		return ret == -ENOIOCTLCMD ? 0 : ret;
diff --git a/drivers/media/platform/rcar-vin/rcar-v4l2.c b/drivers/media/platform/rcar-vin/rcar-v4l2.c
index e78fba84d590..5a54779cfc27 100644
--- a/drivers/media/platform/rcar-vin/rcar-v4l2.c
+++ b/drivers/media/platform/rcar-vin/rcar-v4l2.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Driver for Renesas R-Car VIN
  *
@@ -7,11 +8,6 @@
  * Copyright (C) 2008 Magnus Damm
  *
  * Based on the soc-camera rcar_vin driver
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/pm_runtime.h>
@@ -144,7 +140,7 @@ static int rvin_reset_format(struct rvin_dev *vin)
 {
 	struct v4l2_subdev_format fmt = {
 		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
-		.pad = vin->digital->source_pad,
+		.pad = vin->parallel->source_pad,
 	};
 	int ret;
 
@@ -175,7 +171,7 @@ static int rvin_try_format(struct rvin_dev *vin, u32 which,
 	struct v4l2_subdev_pad_config *pad_cfg;
 	struct v4l2_subdev_format format = {
 		.which = which,
-		.pad = vin->digital->source_pad,
+		.pad = vin->parallel->source_pad,
 	};
 	enum v4l2_field field;
 	u32 width, height;
@@ -517,7 +513,7 @@ static int rvin_enum_dv_timings(struct file *file, void *priv_fh,
 	if (timings->pad)
 		return -EINVAL;
 
-	timings->pad = vin->digital->sink_pad;
+	timings->pad = vin->parallel->sink_pad;
 
 	ret = v4l2_subdev_call(sd, pad, enum_dv_timings, timings);
 
@@ -569,7 +565,7 @@ static int rvin_dv_timings_cap(struct file *file, void *priv_fh,
 	if (cap->pad)
 		return -EINVAL;
 
-	cap->pad = vin->digital->sink_pad;
+	cap->pad = vin->parallel->sink_pad;
 
 	ret = v4l2_subdev_call(sd, pad, dv_timings_cap, cap);
 
@@ -587,7 +583,7 @@ static int rvin_g_edid(struct file *file, void *fh, struct v4l2_edid *edid)
 	if (edid->pad)
 		return -EINVAL;
 
-	edid->pad = vin->digital->sink_pad;
+	edid->pad = vin->parallel->sink_pad;
 
 	ret = v4l2_subdev_call(sd, pad, get_edid, edid);
 
@@ -605,7 +601,7 @@ static int rvin_s_edid(struct file *file, void *fh, struct v4l2_edid *edid)
 	if (edid->pad)
 		return -EINVAL;
 
-	edid->pad = vin->digital->sink_pad;
+	edid->pad = vin->parallel->sink_pad;
 
 	ret = v4l2_subdev_call(sd, pad, set_edid, edid);
 
diff --git a/drivers/media/platform/rcar-vin/rcar-vin.h b/drivers/media/platform/rcar-vin/rcar-vin.h
index c2aef789b491..0b13b34d03e3 100644
--- a/drivers/media/platform/rcar-vin/rcar-vin.h
+++ b/drivers/media/platform/rcar-vin/rcar-vin.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * Driver for Renesas R-Car VIN
  *
@@ -7,11 +8,6 @@
  * Copyright (C) 2008 Magnus Damm
  *
  * Based on the soc-camera rcar_vin driver
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #ifndef __RCAR_VIN__
@@ -53,11 +49,13 @@ enum rvin_csi_id {
 
 /**
  * STOPPED  - No operation in progress
+ * STARTING - Capture starting up
  * RUNNING  - Operation in progress have buffers
  * STOPPING - Stopping operation
  */
 enum rvin_dma_state {
 	STOPPED = 0,
+	STARTING,
 	RUNNING,
 	STOPPING,
 };
@@ -73,16 +71,22 @@ struct rvin_video_format {
 };
 
 /**
- * struct rvin_graph_entity - Video endpoint from async framework
+ * struct rvin_parallel_entity - Parallel video input endpoint descriptor
  * @asd:	sub-device descriptor for async framework
  * @subdev:	subdevice matched using async framework
+ * @mbus_type:	media bus type
+ * @mbus_flags:	media bus configuration flags
  * @source_pad:	source pad of remote subdevice
  * @sink_pad:	sink pad of remote subdevice
+ *
  */
-struct rvin_graph_entity {
+struct rvin_parallel_entity {
 	struct v4l2_async_subdev asd;
 	struct v4l2_subdev *subdev;
 
+	enum v4l2_mbus_type mbus_type;
+	unsigned int mbus_flags;
+
 	unsigned int source_pad;
 	unsigned int sink_pad;
 };
@@ -146,7 +150,8 @@ struct rvin_info {
  * @v4l2_dev:		V4L2 device
  * @ctrl_handler:	V4L2 control handler
  * @notifier:		V4L2 asynchronous subdevs notifier
- * @digital:		entity in the DT for local digital subdevice
+ *
+ * @parallel:		parallel input subdevice descriptor
  *
  * @group:		Gen3 CSI group
  * @id:			Gen3 group id for this VIN
@@ -164,7 +169,8 @@ struct rvin_info {
  * @sequence:		V4L2 buffers sequence number
  * @state:		keeps track of operation state
  *
- * @mbus_cfg:		media bus configuration from DT
+ * @is_csi:		flag to mark the VIN as using a CSI-2 subdevice
+ *
  * @mbus_code:		media bus format code
  * @format:		active V4L2 pixel format
  *
@@ -182,7 +188,8 @@ struct rvin_dev {
 	struct v4l2_device v4l2_dev;
 	struct v4l2_ctrl_handler ctrl_handler;
 	struct v4l2_async_notifier notifier;
-	struct rvin_graph_entity *digital;
+
+	struct rvin_parallel_entity *parallel;
 
 	struct rvin_group *group;
 	unsigned int id;
@@ -199,7 +206,8 @@ struct rvin_dev {
 	unsigned int sequence;
 	enum rvin_dma_state state;
 
-	struct v4l2_mbus_config mbus_cfg;
+	bool is_csi;
+
 	u32 mbus_code;
 	struct v4l2_pix_format format;
 
@@ -209,7 +217,7 @@ struct rvin_dev {
 	v4l2_std_id std;
 };
 
-#define vin_to_source(vin)		((vin)->digital->subdev)
+#define vin_to_source(vin)		((vin)->parallel->subdev)
 
 /* Debug */
 #define vin_dbg(d, fmt, arg...)		dev_dbg(d->dev, fmt, ##arg)
@@ -225,8 +233,7 @@ struct rvin_dev {
  *
  * @lock:		protects the count, notifier, vin and csi members
  * @count:		number of enabled VIN instances found in DT
- * @notifier:		pointer to the notifier of a VIN which handles the
- *			groups async sub-devices.
+ * @notifier:		group notifier for CSI-2 async subdevices
  * @vin:		VIN instances which are part of the group
  * @csi:		array of pairs of fwnode and subdev pointers
  *			to all CSI-2 subdevices.
@@ -238,7 +245,7 @@ struct rvin_group {
 
 	struct mutex lock;
 	unsigned int count;
-	struct v4l2_async_notifier *notifier;
+	struct v4l2_async_notifier notifier;
 	struct rvin_dev *vin[RCAR_VIN_NUM];
 
 	struct {
diff --git a/drivers/media/platform/rcar_drif.c b/drivers/media/platform/rcar_drif.c
index dc7e280c91b4..81413ab52475 100644
--- a/drivers/media/platform/rcar_drif.c
+++ b/drivers/media/platform/rcar_drif.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * R-Car Gen3 Digital Radio Interface (DRIF) driver
  *
  * Copyright (C) 2017 Renesas Electronics Corporation
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
  * This program is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
@@ -1499,5 +1495,5 @@ module_platform_driver(rcar_drif_driver);
 
 MODULE_DESCRIPTION("Renesas R-Car Gen3 DRIF driver");
 MODULE_ALIAS("platform:" RCAR_DRIF_DRV_NAME);
-MODULE_LICENSE("GPL v2");
+MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Ramesh Shanmugasundaram <ramesh.shanmugasundaram@bp.renesas.com>");
diff --git a/drivers/media/platform/rcar_fdp1.c b/drivers/media/platform/rcar_fdp1.c
index b13dec3081e5..2a15b7cca338 100644
--- a/drivers/media/platform/rcar_fdp1.c
+++ b/drivers/media/platform/rcar_fdp1.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Renesas R-Car Fine Display Processor
  *
@@ -8,11 +9,6 @@
  *
  * This code is developed and inspired from the vim2m, rcar_jpu,
  * m2m-deinterlace, and vsp1 drivers.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the
- * License, or (at your option) any later version
  */
 
 #include <linux/clk.h>
diff --git a/drivers/media/platform/rcar_jpu.c b/drivers/media/platform/rcar_jpu.c
index 8b44a849ab41..e5c882423f57 100644
--- a/drivers/media/platform/rcar_jpu.c
+++ b/drivers/media/platform/rcar_jpu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Author: Mikhail Ulyanov
  * Copyright (C) 2014-2015 Cogent Embedded, Inc.  <source@cogentembedded.com>
@@ -11,10 +12,6 @@
  *      1) Rotation
  *      2) Cropping
  *      3) V4L2_CID_JPEG_ACTIVE_MARKER
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <asm/unaligned.h>
@@ -198,7 +195,6 @@
  * @vfd_decoder: video device node for decoder mem2mem mode
  * @m2m_dev: v4l2 mem2mem device data
  * @curr: pointer to current context
- * @irq_queue:	interrupt handler waitqueue
  * @regs: JPEG IP registers mapping
  * @irq: JPEG IP irq
  * @clk: JPEG IP clock
@@ -213,7 +209,6 @@ struct jpu {
 	struct video_device	vfd_decoder;
 	struct v4l2_m2m_dev	*m2m_dev;
 	struct jpu_ctx		*curr;
-	wait_queue_head_t	irq_queue;
 
 	void __iomem		*regs;
 	unsigned int		irq;
@@ -1494,24 +1489,8 @@ static void jpu_device_run(void *priv)
 	spin_unlock_irqrestore(&ctx->jpu->lock, flags);
 }
 
-static int jpu_job_ready(void *priv)
-{
-	return 1;
-}
-
-static void jpu_job_abort(void *priv)
-{
-	struct jpu_ctx *ctx = priv;
-
-	if (!wait_event_timeout(ctx->jpu->irq_queue, !ctx->jpu->curr,
-				msecs_to_jiffies(JPU_JOB_TIMEOUT)))
-		jpu_cleanup(ctx, true);
-}
-
 static const struct v4l2_m2m_ops jpu_m2m_ops = {
 	.device_run	= jpu_device_run,
-	.job_ready	= jpu_job_ready,
-	.job_abort	= jpu_job_abort,
 };
 
 /*
@@ -1592,9 +1571,6 @@ static irqreturn_t jpu_irq_handler(int irq, void *dev_id)
 
 	v4l2_m2m_job_finish(jpu->m2m_dev, curr_ctx->fh.m2m_ctx);
 
-	/* ...wakeup abort routine if needed */
-	wake_up(&jpu->irq_queue);
-
 	return IRQ_HANDLED;
 
 handled:
@@ -1628,7 +1604,6 @@ static int jpu_probe(struct platform_device *pdev)
 	if (!jpu)
 		return -ENOMEM;
 
-	init_waitqueue_head(&jpu->irq_queue);
 	mutex_init(&jpu->mutex);
 	spin_lock_init(&jpu->lock);
 	jpu->dev = &pdev->dev;
diff --git a/drivers/media/platform/renesas-ceu.c b/drivers/media/platform/renesas-ceu.c
index fe4fe944592d..ad782901cd7a 100644
--- a/drivers/media/platform/renesas-ceu.c
+++ b/drivers/media/platform/renesas-ceu.c
@@ -254,6 +254,18 @@ static const struct ceu_fmt ceu_fmt_list[] = {
 		.fourcc	= V4L2_PIX_FMT_YUYV,
 		.bpp	= 16,
 	},
+	{
+		.fourcc	= V4L2_PIX_FMT_UYVY,
+		.bpp	= 16,
+	},
+	{
+		.fourcc	= V4L2_PIX_FMT_YVYU,
+		.bpp	= 16,
+	},
+	{
+		.fourcc	= V4L2_PIX_FMT_VYUY,
+		.bpp	= 16,
+	},
 };
 
 static const struct ceu_fmt *get_ceu_fmt_from_fourcc(unsigned int fourcc)
@@ -272,6 +284,9 @@ static bool ceu_fmt_mplane(struct v4l2_pix_format_mplane *pix)
 {
 	switch (pix->pixelformat) {
 	case V4L2_PIX_FMT_YUYV:
+	case V4L2_PIX_FMT_UYVY:
+	case V4L2_PIX_FMT_YVYU:
+	case V4L2_PIX_FMT_VYUY:
 		return false;
 	case V4L2_PIX_FMT_NV16:
 	case V4L2_PIX_FMT_NV61:
@@ -380,7 +395,9 @@ static int ceu_hw_config(struct ceu_device *ceudev)
 	switch (pix->pixelformat) {
 	/* Data fetch sync mode */
 	case V4L2_PIX_FMT_YUYV:
-		/* TODO: handle YUYV permutations through DTARY bits. */
+	case V4L2_PIX_FMT_YVYU:
+	case V4L2_PIX_FMT_UYVY:
+	case V4L2_PIX_FMT_VYUY:
 		camcr	= CEU_CAMCR_JPEG;
 		cdocr	|= CEU_CDOCR_NO_DOWSAMPLE;
 		cfzsr	= (pix->height << 16) | pix->width;
@@ -568,6 +585,9 @@ static void ceu_calc_plane_sizes(struct ceu_device *ceudev,
 
 	switch (pix->pixelformat) {
 	case V4L2_PIX_FMT_YUYV:
+	case V4L2_PIX_FMT_UYVY:
+	case V4L2_PIX_FMT_YVYU:
+	case V4L2_PIX_FMT_VYUY:
 		pix->num_planes	= 1;
 		bpl		= pix->width * ceu_fmt->bpp / 8;
 		szimage		= pix->height * bpl;
@@ -762,42 +782,59 @@ static const struct vb2_ops ceu_vb2_ops = {
 /* --- CEU image formats handling --- */
 
 /*
- * ceu_try_fmt() - test format on CEU and sensor
+ * __ceu_try_fmt() - test format on CEU and sensor
  * @ceudev: The CEU device.
  * @v4l2_fmt: format to test.
+ * @sd_mbus_code: the media bus code accepted by the subdevice; output param.
  *
  * Returns 0 for success, < 0 for errors.
  */
-static int ceu_try_fmt(struct ceu_device *ceudev, struct v4l2_format *v4l2_fmt)
+static int __ceu_try_fmt(struct ceu_device *ceudev, struct v4l2_format *v4l2_fmt,
+			 u32 *sd_mbus_code)
 {
 	struct ceu_subdev *ceu_sd = ceudev->sd;
 	struct v4l2_pix_format_mplane *pix = &v4l2_fmt->fmt.pix_mp;
 	struct v4l2_subdev *v4l2_sd = ceu_sd->v4l2_sd;
 	struct v4l2_subdev_pad_config pad_cfg;
 	const struct ceu_fmt *ceu_fmt;
+	u32 mbus_code_old;
+	u32 mbus_code;
 	int ret;
 
 	/*
 	 * Set format on sensor sub device: bus format used to produce memory
-	 * format is selected at initialization time.
+	 * format is selected depending on YUV component ordering or
+	 * at initialization time.
 	 */
 	struct v4l2_subdev_format sd_format = {
 		.which	= V4L2_SUBDEV_FORMAT_TRY,
-		.format	= {
-			.code = ceu_sd->mbus_fmt.mbus_code,
-		},
 	};
 
+	mbus_code_old = ceu_sd->mbus_fmt.mbus_code;
+
 	switch (pix->pixelformat) {
 	case V4L2_PIX_FMT_YUYV:
+		mbus_code = MEDIA_BUS_FMT_YUYV8_2X8;
+		break;
+	case V4L2_PIX_FMT_UYVY:
+		mbus_code = MEDIA_BUS_FMT_UYVY8_2X8;
+		break;
+	case V4L2_PIX_FMT_YVYU:
+		mbus_code = MEDIA_BUS_FMT_YVYU8_2X8;
+		break;
+	case V4L2_PIX_FMT_VYUY:
+		mbus_code = MEDIA_BUS_FMT_VYUY8_2X8;
+		break;
 	case V4L2_PIX_FMT_NV16:
 	case V4L2_PIX_FMT_NV61:
 	case V4L2_PIX_FMT_NV12:
 	case V4L2_PIX_FMT_NV21:
+		mbus_code = ceu_sd->mbus_fmt.mbus_code;
 		break;
 
 	default:
 		pix->pixelformat = V4L2_PIX_FMT_NV16;
+		mbus_code = ceu_sd->mbus_fmt.mbus_code;
 		break;
 	}
 
@@ -808,9 +845,25 @@ static int ceu_try_fmt(struct ceu_device *ceudev, struct v4l2_format *v4l2_fmt)
 			      &pix->height, 4, CEU_MAX_HEIGHT, 4, 0);
 
 	v4l2_fill_mbus_format_mplane(&sd_format.format, pix);
+
+	/*
+	 * Try with the mbus_code matching YUYV components ordering first,
+	 * if that one fails, fallback to default selected at initialization
+	 * time.
+	 */
+	sd_format.format.code = mbus_code;
 	ret = v4l2_subdev_call(v4l2_sd, pad, set_fmt, &pad_cfg, &sd_format);
-	if (ret)
-		return ret;
+	if (ret) {
+		if (ret == -EINVAL) {
+			/* fallback */
+			sd_format.format.code = mbus_code_old;
+			ret = v4l2_subdev_call(v4l2_sd, pad, set_fmt,
+					       &pad_cfg, &sd_format);
+		}
+
+		if (ret)
+			return ret;
+	}
 
 	/* Apply size returned by sensor as the CEU can't scale. */
 	v4l2_fill_pix_format_mplane(pix, &sd_format.format);
@@ -818,16 +871,30 @@ static int ceu_try_fmt(struct ceu_device *ceudev, struct v4l2_format *v4l2_fmt)
 	/* Calculate per-plane sizes based on image format. */
 	ceu_calc_plane_sizes(ceudev, ceu_fmt, pix);
 
+	/* Report to caller the configured mbus format. */
+	*sd_mbus_code = sd_format.format.code;
+
 	return 0;
 }
 
 /*
+ * ceu_try_fmt() - Wrapper for __ceu_try_fmt; discard configured mbus_fmt
+ */
+static int ceu_try_fmt(struct ceu_device *ceudev, struct v4l2_format *v4l2_fmt)
+{
+	u32 mbus_code;
+
+	return __ceu_try_fmt(ceudev, v4l2_fmt, &mbus_code);
+}
+
+/*
  * ceu_set_fmt() - Apply the supplied format to both sensor and CEU
  */
 static int ceu_set_fmt(struct ceu_device *ceudev, struct v4l2_format *v4l2_fmt)
 {
 	struct ceu_subdev *ceu_sd = ceudev->sd;
 	struct v4l2_subdev *v4l2_sd = ceu_sd->v4l2_sd;
+	u32 mbus_code;
 	int ret;
 
 	/*
@@ -836,15 +903,13 @@ static int ceu_set_fmt(struct ceu_device *ceudev, struct v4l2_format *v4l2_fmt)
 	 */
 	struct v4l2_subdev_format format = {
 		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
-		.format	= {
-			.code = ceu_sd->mbus_fmt.mbus_code,
-		},
 	};
 
-	ret = ceu_try_fmt(ceudev, v4l2_fmt);
+	ret = __ceu_try_fmt(ceudev, v4l2_fmt, &mbus_code);
 	if (ret)
 		return ret;
 
+	format.format.code = mbus_code;
 	v4l2_fill_mbus_format_mplane(&format.format, &v4l2_fmt->fmt.pix_mp);
 	ret = v4l2_subdev_call(v4l2_sd, pad, set_fmt, NULL, &format);
 	if (ret)
diff --git a/drivers/media/platform/rockchip/rga/rga-buf.c b/drivers/media/platform/rockchip/rga/rga-buf.c
index fa1ba98c96dc..356821c2dacf 100644
--- a/drivers/media/platform/rockchip/rga/rga-buf.c
+++ b/drivers/media/platform/rockchip/rga/rga-buf.c
@@ -64,43 +64,44 @@ static void rga_buf_queue(struct vb2_buffer *vb)
 	v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf);
 }
 
+static void rga_buf_return_buffers(struct vb2_queue *q,
+				   enum vb2_buffer_state state)
+{
+	struct rga_ctx *ctx = vb2_get_drv_priv(q);
+	struct vb2_v4l2_buffer *vbuf;
+
+	for (;;) {
+		if (V4L2_TYPE_IS_OUTPUT(q->type))
+			vbuf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
+		else
+			vbuf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
+		if (!vbuf)
+			break;
+		v4l2_m2m_buf_done(vbuf, state);
+	}
+}
+
 static int rga_buf_start_streaming(struct vb2_queue *q, unsigned int count)
 {
 	struct rga_ctx *ctx = vb2_get_drv_priv(q);
 	struct rockchip_rga *rga = ctx->rga;
-	int ret, i;
+	int ret;
 
 	ret = pm_runtime_get_sync(rga->dev);
-
-	if (!ret)
-		return 0;
-
-	for (i = 0; i < q->num_buffers; ++i) {
-		if (q->bufs[i]->state == VB2_BUF_STATE_ACTIVE) {
-			v4l2_m2m_buf_done(to_vb2_v4l2_buffer(q->bufs[i]),
-					  VB2_BUF_STATE_QUEUED);
-		}
+	if (ret < 0) {
+		rga_buf_return_buffers(q, VB2_BUF_STATE_QUEUED);
+		return ret;
 	}
 
-	return ret;
+	return 0;
 }
 
 static void rga_buf_stop_streaming(struct vb2_queue *q)
 {
 	struct rga_ctx *ctx = vb2_get_drv_priv(q);
 	struct rockchip_rga *rga = ctx->rga;
-	struct vb2_v4l2_buffer *vbuf;
-
-	for (;;) {
-		if (V4L2_TYPE_IS_OUTPUT(q->type))
-			vbuf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
-		else
-			vbuf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
-		if (!vbuf)
-			break;
-		v4l2_m2m_buf_done(vbuf, VB2_BUF_STATE_ERROR);
-	}
 
+	rga_buf_return_buffers(q, VB2_BUF_STATE_ERROR);
 	pm_runtime_put(rga->dev);
 }
 
diff --git a/drivers/media/platform/rockchip/rga/rga.c b/drivers/media/platform/rockchip/rga/rga.c
index d508a8ba6f89..ab5a6f95044a 100644
--- a/drivers/media/platform/rockchip/rga/rga.c
+++ b/drivers/media/platform/rockchip/rga/rga.c
@@ -39,18 +39,6 @@
 static int debug;
 module_param(debug, int, 0644);
 
-static void job_abort(void *prv)
-{
-	struct rga_ctx *ctx = prv;
-	struct rockchip_rga *rga = ctx->rga;
-
-	if (!rga->curr)	/* No job currently running */
-		return;
-
-	wait_event_timeout(rga->irq_queue,
-			   !rga->curr, msecs_to_jiffies(RGA_TIMEOUT));
-}
-
 static void device_run(void *prv)
 {
 	struct rga_ctx *ctx = prv;
@@ -104,8 +92,6 @@ static irqreturn_t rga_isr(int irq, void *prv)
 		v4l2_m2m_buf_done(src, VB2_BUF_STATE_DONE);
 		v4l2_m2m_buf_done(dst, VB2_BUF_STATE_DONE);
 		v4l2_m2m_job_finish(rga->m2m_dev, ctx->fh.m2m_ctx);
-
-		wake_up(&rga->irq_queue);
 	}
 
 	return IRQ_HANDLED;
@@ -113,7 +99,6 @@ static irqreturn_t rga_isr(int irq, void *prv)
 
 static struct v4l2_m2m_ops rga_m2m_ops = {
 	.device_run = device_run,
-	.job_abort = job_abort,
 };
 
 static int
@@ -838,8 +823,6 @@ static int rga_probe(struct platform_device *pdev)
 	spin_lock_init(&rga->ctrl_lock);
 	mutex_init(&rga->mutex);
 
-	init_waitqueue_head(&rga->irq_queue);
-
 	ret = rga_parse_dt(rga);
 	if (ret)
 		dev_err(&pdev->dev, "Unable to parse OF data\n");
@@ -882,7 +865,6 @@ static int rga_probe(struct platform_device *pdev)
 	vfd->v4l2_dev = &rga->v4l2_dev;
 
 	video_set_drvdata(vfd, rga);
-	snprintf(vfd->name, sizeof(vfd->name), "%s", rga_videodev.name);
 	rga->vfd = vfd;
 
 	platform_set_drvdata(pdev, rga);
@@ -943,7 +925,7 @@ static int rga_remove(struct platform_device *pdev)
 {
 	struct rockchip_rga *rga = platform_get_drvdata(pdev);
 
-	dma_free_attrs(rga->dev, RGA_CMDBUF_SIZE, &rga->cmdbuf_virt,
+	dma_free_attrs(rga->dev, RGA_CMDBUF_SIZE, rga->cmdbuf_virt,
 		       rga->cmdbuf_phy, DMA_ATTR_WRITE_COMBINE);
 
 	free_pages((unsigned long)rga->src_mmu_pages, 3);
diff --git a/drivers/media/platform/rockchip/rga/rga.h b/drivers/media/platform/rockchip/rga/rga.h
index 5d43e7ea88af..72d8a159fa7b 100644
--- a/drivers/media/platform/rockchip/rga/rga.h
+++ b/drivers/media/platform/rockchip/rga/rga.h
@@ -86,8 +86,6 @@ struct rockchip_rga {
 	/* ctrl parm lock */
 	spinlock_t ctrl_lock;
 
-	wait_queue_head_t irq_queue;
-
 	struct rga_ctx *curr;
 	dma_addr_t cmdbuf_phy;
 	void *cmdbuf_virt;
diff --git a/drivers/media/platform/s3c-camif/camif-capture.c b/drivers/media/platform/s3c-camif/camif-capture.c
index 9ab8e7ee2e1e..c02dce8b4c6c 100644
--- a/drivers/media/platform/s3c-camif/camif-capture.c
+++ b/drivers/media/platform/s3c-camif/camif-capture.c
@@ -117,6 +117,8 @@ static int sensor_set_power(struct camif_dev *camif, int on)
 
 	if (camif->sensor.power_count == !on)
 		err = v4l2_subdev_call(sensor->sd, core, s_power, on);
+	if (err == -ENOIOCTLCMD)
+		err = 0;
 	if (!err)
 		sensor->power_count += on ? 1 : -1;
 
@@ -599,7 +601,7 @@ static __poll_t s3c_camif_poll(struct file *file,
 
 	mutex_lock(&camif->lock);
 	if (vp->owner && vp->owner != file->private_data)
-		ret = -EBUSY;
+		ret = EPOLLERR;
 	else
 		ret = vb2_poll(&vp->vb_queue, file, wait);
 
diff --git a/drivers/media/platform/s5p-g2d/g2d.c b/drivers/media/platform/s5p-g2d/g2d.c
index 66aa8cf1d048..e901201b6fcc 100644
--- a/drivers/media/platform/s5p-g2d/g2d.c
+++ b/drivers/media/platform/s5p-g2d/g2d.c
@@ -142,6 +142,8 @@ static const struct vb2_ops g2d_qops = {
 	.queue_setup	= g2d_queue_setup,
 	.buf_prepare	= g2d_buf_prepare,
 	.buf_queue	= g2d_buf_queue,
+	.wait_prepare	= vb2_ops_wait_prepare,
+	.wait_finish	= vb2_ops_wait_finish,
 };
 
 static int queue_init(void *priv, struct vb2_queue *src_vq,
@@ -481,19 +483,6 @@ static int vidioc_s_crop(struct file *file, void *prv, const struct v4l2_crop *c
 	return 0;
 }
 
-static void job_abort(void *prv)
-{
-	struct g2d_ctx *ctx = prv;
-	struct g2d_dev *dev = ctx->dev;
-
-	if (dev->curr == NULL) /* No job currently running */
-		return;
-
-	wait_event_timeout(dev->irq_queue,
-			   dev->curr == NULL,
-			   msecs_to_jiffies(G2D_TIMEOUT));
-}
-
 static void device_run(void *prv)
 {
 	struct g2d_ctx *ctx = prv;
@@ -563,7 +552,6 @@ static irqreturn_t g2d_isr(int irq, void *prv)
 	v4l2_m2m_job_finish(dev->m2m_dev, ctx->fh.m2m_ctx);
 
 	dev->curr = NULL;
-	wake_up(&dev->irq_queue);
 	return IRQ_HANDLED;
 }
 
@@ -613,7 +601,6 @@ static const struct video_device g2d_videodev = {
 
 static const struct v4l2_m2m_ops g2d_m2m_ops = {
 	.device_run	= device_run,
-	.job_abort	= job_abort,
 };
 
 static const struct of_device_id exynos_g2d_match[];
@@ -633,7 +620,6 @@ static int g2d_probe(struct platform_device *pdev)
 	spin_lock_init(&dev->ctrl_lock);
 	mutex_init(&dev->mutex);
 	atomic_set(&dev->num_inst, 0);
-	init_waitqueue_head(&dev->irq_queue);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 
@@ -702,7 +688,6 @@ static int g2d_probe(struct platform_device *pdev)
 		goto rel_vdev;
 	}
 	video_set_drvdata(vfd, dev);
-	snprintf(vfd->name, sizeof(vfd->name), "%s", g2d_videodev.name);
 	dev->vfd = vfd;
 	v4l2_info(&dev->v4l2_dev, "device registered as /dev/video%d\n",
 								vfd->num);
diff --git a/drivers/media/platform/s5p-g2d/g2d.h b/drivers/media/platform/s5p-g2d/g2d.h
index dd812b557e87..9ffb458a1b93 100644
--- a/drivers/media/platform/s5p-g2d/g2d.h
+++ b/drivers/media/platform/s5p-g2d/g2d.h
@@ -31,7 +31,6 @@ struct g2d_dev {
 	struct g2d_ctx		*curr;
 	struct g2d_variant	*variant;
 	int irq;
-	wait_queue_head_t	irq_queue;
 };
 
 struct g2d_frame {
diff --git a/drivers/media/platform/s5p-jpeg/jpeg-core.c b/drivers/media/platform/s5p-jpeg/jpeg-core.c
index 79b63da27f53..04fd2e0493c0 100644
--- a/drivers/media/platform/s5p-jpeg/jpeg-core.c
+++ b/drivers/media/platform/s5p-jpeg/jpeg-core.c
@@ -2467,26 +2467,19 @@ static int s5p_jpeg_job_ready(void *priv)
 	return 1;
 }
 
-static void s5p_jpeg_job_abort(void *priv)
-{
-}
-
 static struct v4l2_m2m_ops s5p_jpeg_m2m_ops = {
 	.device_run	= s5p_jpeg_device_run,
 	.job_ready	= s5p_jpeg_job_ready,
-	.job_abort	= s5p_jpeg_job_abort,
 };
 
 static struct v4l2_m2m_ops exynos3250_jpeg_m2m_ops = {
 	.device_run	= exynos3250_jpeg_device_run,
 	.job_ready	= s5p_jpeg_job_ready,
-	.job_abort	= s5p_jpeg_job_abort,
 };
 
 static struct v4l2_m2m_ops exynos4_jpeg_m2m_ops = {
 	.device_run	= exynos4_jpeg_device_run,
 	.job_ready	= s5p_jpeg_job_ready,
-	.job_abort	= s5p_jpeg_job_abort,
 };
 
 /*
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc.c b/drivers/media/platform/s5p-mfc/s5p_mfc.c
index a80251ed3143..927a1235408d 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc.c
@@ -254,24 +254,24 @@ static void s5p_mfc_handle_frame_all_extracted(struct s5p_mfc_ctx *ctx)
 static void s5p_mfc_handle_frame_copy_time(struct s5p_mfc_ctx *ctx)
 {
 	struct s5p_mfc_dev *dev = ctx->dev;
-	struct s5p_mfc_buf  *dst_buf, *src_buf;
-	size_t dec_y_addr;
+	struct s5p_mfc_buf *dst_buf, *src_buf;
+	u32 dec_y_addr;
 	unsigned int frame_type;
 
 	/* Make sure we actually have a new frame before continuing. */
 	frame_type = s5p_mfc_hw_call(dev->mfc_ops, get_dec_frame_type, dev);
 	if (frame_type == S5P_FIMV_DECODE_FRAME_SKIPPED)
 		return;
-	dec_y_addr = s5p_mfc_hw_call(dev->mfc_ops, get_dec_y_adr, dev);
+	dec_y_addr = (u32)s5p_mfc_hw_call(dev->mfc_ops, get_dec_y_adr, dev);
 
 	/* Copy timestamp / timecode from decoded src to dst and set
 	   appropriate flags. */
 	src_buf = list_entry(ctx->src_queue.next, struct s5p_mfc_buf, list);
 	list_for_each_entry(dst_buf, &ctx->dst_queue, list) {
-		if (vb2_dma_contig_plane_dma_addr(&dst_buf->b->vb2_buf, 0)
-				== dec_y_addr) {
-			dst_buf->b->timecode =
-						src_buf->b->timecode;
+		u32 addr = (u32)vb2_dma_contig_plane_dma_addr(&dst_buf->b->vb2_buf, 0);
+
+		if (addr == dec_y_addr) {
+			dst_buf->b->timecode = src_buf->b->timecode;
 			dst_buf->b->vb2_buf.timestamp =
 						src_buf->b->vb2_buf.timestamp;
 			dst_buf->b->flags &=
@@ -307,10 +307,10 @@ static void s5p_mfc_handle_frame_new(struct s5p_mfc_ctx *ctx, unsigned int err)
 {
 	struct s5p_mfc_dev *dev = ctx->dev;
 	struct s5p_mfc_buf  *dst_buf;
-	size_t dspl_y_addr;
+	u32 dspl_y_addr;
 	unsigned int frame_type;
 
-	dspl_y_addr = s5p_mfc_hw_call(dev->mfc_ops, get_dspl_y_adr, dev);
+	dspl_y_addr = (u32)s5p_mfc_hw_call(dev->mfc_ops, get_dspl_y_adr, dev);
 	if (IS_MFCV6_PLUS(dev))
 		frame_type = s5p_mfc_hw_call(dev->mfc_ops,
 			get_disp_frame_type, ctx);
@@ -329,9 +329,10 @@ static void s5p_mfc_handle_frame_new(struct s5p_mfc_ctx *ctx, unsigned int err)
 	/* The MFC returns address of the buffer, now we have to
 	 * check which videobuf does it correspond to */
 	list_for_each_entry(dst_buf, &ctx->dst_queue, list) {
+		u32 addr = (u32)vb2_dma_contig_plane_dma_addr(&dst_buf->b->vb2_buf, 0);
+
 		/* Check if this is the buffer we're looking for */
-		if (vb2_dma_contig_plane_dma_addr(&dst_buf->b->vb2_buf, 0)
-				== dspl_y_addr) {
+		if (addr == dspl_y_addr) {
 			list_del(&dst_buf->list);
 			ctx->dst_queue_cnt--;
 			dst_buf->b->sequence = ctx->sequence;
@@ -1449,8 +1450,7 @@ static int s5p_mfc_remove(struct platform_device *pdev)
 
 static int s5p_mfc_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct s5p_mfc_dev *m_dev = platform_get_drvdata(pdev);
+	struct s5p_mfc_dev *m_dev = dev_get_drvdata(dev);
 	int ret;
 
 	if (m_dev->num_inst == 0)
@@ -1484,8 +1484,7 @@ static int s5p_mfc_suspend(struct device *dev)
 
 static int s5p_mfc_resume(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct s5p_mfc_dev *m_dev = platform_get_drvdata(pdev);
+	struct s5p_mfc_dev *m_dev = dev_get_drvdata(dev);
 
 	if (m_dev->num_inst == 0)
 		return 0;
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
index 570f391f2cfd..3ad4f5073002 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
@@ -692,12 +692,12 @@ static struct mfc_control controls[] = {
 		.default_value = 10,
 	},
 	{
-		.id = V4L2_CID_MPEG_VIDEO_VPX_PROFILE,
-		.type = V4L2_CTRL_TYPE_INTEGER,
-		.minimum = 0,
-		.maximum = 3,
-		.step = 1,
-		.default_value = 0,
+		.id = V4L2_CID_MPEG_VIDEO_VP8_PROFILE,
+		.type = V4L2_CTRL_TYPE_MENU,
+		.minimum = V4L2_MPEG_VIDEO_VP8_PROFILE_0,
+		.maximum = V4L2_MPEG_VIDEO_VP8_PROFILE_3,
+		.default_value = V4L2_MPEG_VIDEO_VP8_PROFILE_0,
+		.menu_skip_mask = 0,
 	},
 	{
 		.id = V4L2_CID_MPEG_VIDEO_HEVC_I_FRAME_QP,
@@ -2057,7 +2057,7 @@ static int s5p_mfc_enc_s_ctrl(struct v4l2_ctrl *ctrl)
 	case V4L2_CID_MPEG_VIDEO_VPX_P_FRAME_QP:
 		p->codec.vp8.rc_p_frame_qp = ctrl->val;
 		break;
-	case V4L2_CID_MPEG_VIDEO_VPX_PROFILE:
+	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:
 		p->codec.vp8.profile = ctrl->val;
 		break;
 	case V4L2_CID_MPEG_VIDEO_HEVC_I_FRAME_QP:
@@ -2711,4 +2711,3 @@ void s5p_mfc_enc_init(struct s5p_mfc_ctx *ctx)
 	f.fmt.pix_mp.pixelformat = DEF_DST_FMT_ENC;
 	ctx->dst_fmt = find_format(&f, MFC_FMT_ENC);
 }
-
diff --git a/drivers/media/platform/sh_veu.c b/drivers/media/platform/sh_veu.c
index 1a0cde017fdf..1d274c64de09 100644
--- a/drivers/media/platform/sh_veu.c
+++ b/drivers/media/platform/sh_veu.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * sh-mobile VEU mem2mem driver
  *
  * Copyright (C) 2012 Renesas Electronics Corporation
  * Author: Guennadi Liakhovetski, <g.liakhovetski@gmx.de>
  * Copyright (C) 2008 Magnus Damm
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the version 2 of the GNU General Public License as
- * published by the Free Software Foundation
  */
 
 #include <linux/err.h>
diff --git a/drivers/media/platform/sh_vou.c b/drivers/media/platform/sh_vou.c
index 4dccf29e9d78..6135e13e24d4 100644
--- a/drivers/media/platform/sh_vou.c
+++ b/drivers/media/platform/sh_vou.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SuperH Video Output Unit (VOU) driver
  *
  * Copyright (C) 2010, Guennadi Liakhovetski <g.liakhovetski@gmx.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/dma-mapping.h>
diff --git a/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c b/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c
index 9897213f2618..0a2c0daaffef 100644
--- a/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c
+++ b/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * V4L2 Driver for SuperH Mobile CEU interface
  *
@@ -7,11 +8,6 @@
  *
  * Copyright (C) 2006, Sascha Hauer, Pengutronix
  * Copyright (C) 2008, Guennadi Liakhovetski <kernel@pengutronix.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/init.h>
diff --git a/drivers/media/platform/soc_camera/soc_camera_platform.c b/drivers/media/platform/soc_camera/soc_camera_platform.c
index ce00e90d4e3c..6745a6e3f464 100644
--- a/drivers/media/platform/soc_camera/soc_camera_platform.c
+++ b/drivers/media/platform/soc_camera/soc_camera_platform.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Generic Platform Camera Driver
  *
  * Copyright (C) 2008 Magnus Damm
  * Based on mt9m001 driver,
  * Copyright (C) 2008, Guennadi Liakhovetski <kernel@pengutronix.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/init.h>
diff --git a/drivers/media/platform/sti/delta/delta-v4l2.c b/drivers/media/platform/sti/delta/delta-v4l2.c
index 232d508c5b66..0b42acd4e3a6 100644
--- a/drivers/media/platform/sti/delta/delta-v4l2.c
+++ b/drivers/media/platform/sti/delta/delta-v4l2.c
@@ -339,22 +339,6 @@ static void register_decoders(struct delta_dev *delta)
 	}
 }
 
-static void delta_lock(void *priv)
-{
-	struct delta_ctx *ctx = priv;
-	struct delta_dev *delta = ctx->dev;
-
-	mutex_lock(&delta->lock);
-}
-
-static void delta_unlock(void *priv)
-{
-	struct delta_ctx *ctx = priv;
-	struct delta_dev *delta = ctx->dev;
-
-	mutex_unlock(&delta->lock);
-}
-
 static int delta_open_decoder(struct delta_ctx *ctx, u32 streamformat,
 			      u32 pixelformat, const struct delta_dec **pdec)
 {
@@ -1099,8 +1083,6 @@ static const struct v4l2_m2m_ops delta_m2m_ops = {
 	.device_run     = delta_device_run,
 	.job_ready	= delta_job_ready,
 	.job_abort      = delta_job_abort,
-	.lock		= delta_lock,
-	.unlock		= delta_unlock,
 };
 
 /*
diff --git a/drivers/media/platform/sti/hva/hva-v4l2.c b/drivers/media/platform/sti/hva/hva-v4l2.c
index 15080cb00fa7..5a807c7c5e79 100644
--- a/drivers/media/platform/sti/hva/hva-v4l2.c
+++ b/drivers/media/platform/sti/hva/hva-v4l2.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/mod_devicetable.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <media/v4l2-event.h>
diff --git a/drivers/media/platform/stm32/stm32-dcmi.c b/drivers/media/platform/stm32/stm32-dcmi.c
index 2e1933d872ee..721564176d8c 100644
--- a/drivers/media/platform/stm32/stm32-dcmi.c
+++ b/drivers/media/platform/stm32/stm32-dcmi.c
@@ -22,7 +22,9 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/of_graph.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/reset.h>
 #include <linux/videodev2.h>
 
@@ -84,19 +86,14 @@
 
 enum state {
 	STOPPED = 0,
+	WAIT_FOR_BUFFER,
 	RUNNING,
-	STOPPING,
 };
 
 #define MIN_WIDTH	16U
-#define MAX_WIDTH	2048U
+#define MAX_WIDTH	2592U
 #define MIN_HEIGHT	16U
-#define MAX_HEIGHT	2048U
-
-#define MIN_JPEG_WIDTH	16U
-#define MAX_JPEG_WIDTH	2592U
-#define MIN_JPEG_HEIGHT	16U
-#define MAX_JPEG_HEIGHT	2592U
+#define MAX_HEIGHT	2592U
 
 #define TIMEOUT_MS	1000
 
@@ -194,7 +191,7 @@ static inline void reg_clear(void __iomem *base, u32 reg, u32 mask)
 	reg_write(base, reg, reg_read(base, reg) & ~mask);
 }
 
-static int dcmi_start_capture(struct stm32_dcmi *dcmi);
+static int dcmi_start_capture(struct stm32_dcmi *dcmi, struct dcmi_buf *buf);
 
 static void dcmi_buffer_done(struct stm32_dcmi *dcmi,
 			     struct dcmi_buf *buf,
@@ -206,6 +203,8 @@ static void dcmi_buffer_done(struct stm32_dcmi *dcmi,
 	if (!buf)
 		return;
 
+	list_del_init(&buf->list);
+
 	vbuf = &buf->vb;
 
 	vbuf->sequence = dcmi->sequence++;
@@ -223,6 +222,8 @@ static void dcmi_buffer_done(struct stm32_dcmi *dcmi,
 
 static int dcmi_restart_capture(struct stm32_dcmi *dcmi)
 {
+	struct dcmi_buf *buf;
+
 	spin_lock_irq(&dcmi->irqlock);
 
 	if (dcmi->state != RUNNING) {
@@ -232,34 +233,30 @@ static int dcmi_restart_capture(struct stm32_dcmi *dcmi)
 
 	/* Restart a new DMA transfer with next buffer */
 	if (list_empty(&dcmi->buffers)) {
-		dev_err(dcmi->dev, "%s: No more buffer queued, cannot capture buffer\n",
-			__func__);
-		dcmi->errors_count++;
-		dcmi->active = NULL;
-
+		dev_dbg(dcmi->dev, "Capture restart is deferred to next buffer queueing\n");
+		dcmi->state = WAIT_FOR_BUFFER;
 		spin_unlock_irq(&dcmi->irqlock);
-		return -EINVAL;
+		return 0;
 	}
-
-	dcmi->active = list_entry(dcmi->buffers.next,
-				  struct dcmi_buf, list);
-	list_del_init(&dcmi->active->list);
+	buf = list_entry(dcmi->buffers.next, struct dcmi_buf, list);
+	dcmi->active = buf;
 
 	spin_unlock_irq(&dcmi->irqlock);
 
-	return dcmi_start_capture(dcmi);
+	return dcmi_start_capture(dcmi, buf);
 }
 
 static void dcmi_dma_callback(void *param)
 {
 	struct stm32_dcmi *dcmi = (struct stm32_dcmi *)param;
-	struct dma_chan *chan = dcmi->dma_chan;
 	struct dma_tx_state state;
 	enum dma_status status;
 	struct dcmi_buf *buf = dcmi->active;
 
+	spin_lock_irq(&dcmi->irqlock);
+
 	/* Check DMA status */
-	status = dmaengine_tx_status(chan, dcmi->dma_cookie, &state);
+	status = dmaengine_tx_status(dcmi->dma_chan, dcmi->dma_cookie, &state);
 
 	switch (status) {
 	case DMA_IN_PROGRESS:
@@ -270,6 +267,9 @@ static void dcmi_dma_callback(void *param)
 		break;
 	case DMA_ERROR:
 		dev_err(dcmi->dev, "%s: Received DMA_ERROR\n", __func__);
+
+		/* Return buffer to V4L2 in error state */
+		dcmi_buffer_done(dcmi, buf, 0, -EIO);
 		break;
 	case DMA_COMPLETE:
 		dev_dbg(dcmi->dev, "%s: Received DMA_COMPLETE\n", __func__);
@@ -277,15 +277,19 @@ static void dcmi_dma_callback(void *param)
 		/* Return buffer to V4L2 */
 		dcmi_buffer_done(dcmi, buf, buf->size, 0);
 
+		spin_unlock_irq(&dcmi->irqlock);
+
 		/* Restart capture */
 		if (dcmi_restart_capture(dcmi))
 			dev_err(dcmi->dev, "%s: Cannot restart capture on DMA complete\n",
 				__func__);
-		break;
+		return;
 	default:
 		dev_err(dcmi->dev, "%s: Received unknown status\n", __func__);
 		break;
 	}
+
+	spin_unlock_irq(&dcmi->irqlock);
 }
 
 static int dcmi_start_dma(struct stm32_dcmi *dcmi,
@@ -313,10 +317,11 @@ static int dcmi_start_dma(struct stm32_dcmi *dcmi,
 	/* Prepare a DMA transaction */
 	desc = dmaengine_prep_slave_single(dcmi->dma_chan, buf->paddr,
 					   buf->size,
-					   DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT);
+					   DMA_DEV_TO_MEM,
+					   DMA_PREP_INTERRUPT);
 	if (!desc) {
-		dev_err(dcmi->dev, "%s: DMA dmaengine_prep_slave_single failed for buffer size %zu\n",
-			__func__, buf->size);
+		dev_err(dcmi->dev, "%s: DMA dmaengine_prep_slave_single failed for buffer phy=%pad size=%zu\n",
+			__func__, &buf->paddr, buf->size);
 		return -EINVAL;
 	}
 
@@ -336,10 +341,9 @@ static int dcmi_start_dma(struct stm32_dcmi *dcmi,
 	return 0;
 }
 
-static int dcmi_start_capture(struct stm32_dcmi *dcmi)
+static int dcmi_start_capture(struct stm32_dcmi *dcmi, struct dcmi_buf *buf)
 {
 	int ret;
-	struct dcmi_buf *buf = dcmi->active;
 
 	if (!buf)
 		return -EINVAL;
@@ -382,7 +386,6 @@ static void dcmi_process_jpeg(struct stm32_dcmi *dcmi)
 {
 	struct dma_tx_state state;
 	enum dma_status status;
-	struct dma_chan *chan = dcmi->dma_chan;
 	struct dcmi_buf *buf = dcmi->active;
 
 	if (!buf)
@@ -390,8 +393,7 @@ static void dcmi_process_jpeg(struct stm32_dcmi *dcmi)
 
 	/*
 	 * Because of variable JPEG buffer size sent by sensor,
-	 * DMA transfer never completes due to transfer size
-	 * never reached.
+	 * DMA transfer never completes due to transfer size never reached.
 	 * In order to ensure that all the JPEG data are transferred
 	 * in active buffer memory, DMA is drained.
 	 * Then DMA tx status gives the amount of data transferred
@@ -400,10 +402,10 @@ static void dcmi_process_jpeg(struct stm32_dcmi *dcmi)
 	 */
 
 	/* Drain DMA */
-	dmaengine_synchronize(chan);
+	dmaengine_synchronize(dcmi->dma_chan);
 
 	/* Get DMA residue to get JPEG size */
-	status = dmaengine_tx_status(chan, dcmi->dma_cookie, &state);
+	status = dmaengine_tx_status(dcmi->dma_chan, dcmi->dma_cookie, &state);
 	if (status != DMA_ERROR && state.residue < buf->size) {
 		/* Return JPEG buffer to V4L2 with received JPEG buffer size */
 		dcmi_buffer_done(dcmi, buf, buf->size - state.residue, 0);
@@ -430,18 +432,6 @@ static irqreturn_t dcmi_irq_thread(int irq, void *arg)
 
 	spin_lock_irq(&dcmi->irqlock);
 
-	/* Stop capture is required */
-	if (dcmi->state == STOPPING) {
-		reg_clear(dcmi->regs, DCMI_IER, IT_FRAME | IT_OVR | IT_ERR);
-
-		dcmi->state = STOPPED;
-
-		complete(&dcmi->complete);
-
-		spin_unlock_irq(&dcmi->irqlock);
-		return IRQ_HANDLED;
-	}
-
 	if ((dcmi->misr & IT_OVR) || (dcmi->misr & IT_ERR)) {
 		dcmi->errors_count++;
 		if (dcmi->misr & IT_OVR)
@@ -495,8 +485,6 @@ static int dcmi_queue_setup(struct vb2_queue *vq,
 	*nplanes = 1;
 	sizes[0] = size;
 
-	dcmi->active = NULL;
-
 	dev_dbg(dcmi->dev, "Setup queue, count=%d, size=%d\n",
 		*nbuffers, size);
 
@@ -554,21 +542,24 @@ static void dcmi_buf_queue(struct vb2_buffer *vb)
 
 	spin_lock_irq(&dcmi->irqlock);
 
-	if (dcmi->state == RUNNING && !dcmi->active) {
+	/* Enqueue to video buffers list */
+	list_add_tail(&buf->list, &dcmi->buffers);
+
+	if (dcmi->state == WAIT_FOR_BUFFER) {
+		dcmi->state = RUNNING;
 		dcmi->active = buf;
 
 		dev_dbg(dcmi->dev, "Starting capture on buffer[%d] queued\n",
 			buf->vb.vb2_buf.index);
 
 		spin_unlock_irq(&dcmi->irqlock);
-		if (dcmi_start_capture(dcmi))
+		if (dcmi_start_capture(dcmi, buf))
 			dev_err(dcmi->dev, "%s: Cannot restart capture on overflow or error\n",
 				__func__);
-	} else {
-		/* Enqueue to video buffers list */
-		list_add_tail(&buf->list, &dcmi->buffers);
-		spin_unlock_irq(&dcmi->irqlock);
+		return;
 	}
+
+	spin_unlock_irq(&dcmi->irqlock);
 }
 
 static int dcmi_start_streaming(struct vb2_queue *vq, unsigned int count)
@@ -578,9 +569,9 @@ static int dcmi_start_streaming(struct vb2_queue *vq, unsigned int count)
 	u32 val = 0;
 	int ret;
 
-	ret = clk_enable(dcmi->mclk);
+	ret = pm_runtime_get_sync(dcmi->dev);
 	if (ret) {
-		dev_err(dcmi->dev, "%s: Failed to start streaming, cannot enable clock\n",
+		dev_err(dcmi->dev, "%s: Failed to start streaming, cannot get sync\n",
 			__func__);
 		goto err_release_buffers;
 	}
@@ -590,7 +581,7 @@ static int dcmi_start_streaming(struct vb2_queue *vq, unsigned int count)
 	if (ret && ret != -ENOIOCTLCMD) {
 		dev_err(dcmi->dev, "%s: Failed to start streaming, subdev streamon error",
 			__func__);
-		goto err_disable_clock;
+		goto err_pm_put;
 	}
 
 	spin_lock_irq(&dcmi->irqlock);
@@ -636,13 +627,10 @@ static int dcmi_start_streaming(struct vb2_queue *vq, unsigned int count)
 	/* Enable dcmi */
 	reg_set(dcmi->regs, DCMI_CR, CR_ENABLE);
 
-	dcmi->state = RUNNING;
-
 	dcmi->sequence = 0;
 	dcmi->errors_count = 0;
 	dcmi->overrun_count = 0;
 	dcmi->buffers_count = 0;
-	dcmi->active = NULL;
 
 	/*
 	 * Start transfer if at least one buffer has been queued,
@@ -650,17 +638,20 @@ static int dcmi_start_streaming(struct vb2_queue *vq, unsigned int count)
 	 */
 	if (list_empty(&dcmi->buffers)) {
 		dev_dbg(dcmi->dev, "Start streaming is deferred to next buffer queueing\n");
+		dcmi->state = WAIT_FOR_BUFFER;
 		spin_unlock_irq(&dcmi->irqlock);
 		return 0;
 	}
 
-	dcmi->active = list_entry(dcmi->buffers.next, struct dcmi_buf, list);
-	list_del_init(&dcmi->active->list);
+	buf = list_entry(dcmi->buffers.next, struct dcmi_buf, list);
+	dcmi->active = buf;
+
+	dcmi->state = RUNNING;
 
 	dev_dbg(dcmi->dev, "Start streaming, starting capture\n");
 
 	spin_unlock_irq(&dcmi->irqlock);
-	ret = dcmi_start_capture(dcmi);
+	ret = dcmi_start_capture(dcmi, buf);
 	if (ret) {
 		dev_err(dcmi->dev, "%s: Start streaming failed, cannot start capture\n",
 			__func__);
@@ -675,8 +666,8 @@ static int dcmi_start_streaming(struct vb2_queue *vq, unsigned int count)
 err_subdev_streamoff:
 	v4l2_subdev_call(dcmi->entity.subdev, video, s_stream, 0);
 
-err_disable_clock:
-	clk_disable(dcmi->mclk);
+err_pm_put:
+	pm_runtime_put(dcmi->dev);
 
 err_release_buffers:
 	spin_lock_irq(&dcmi->irqlock);
@@ -684,15 +675,11 @@ err_release_buffers:
 	 * Return all buffers to vb2 in QUEUED state.
 	 * This will give ownership back to userspace
 	 */
-	if (dcmi->active) {
-		buf = dcmi->active;
-		vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED);
-		dcmi->active = NULL;
-	}
 	list_for_each_entry_safe(buf, node, &dcmi->buffers, list) {
 		list_del_init(&buf->list);
 		vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED);
 	}
+	dcmi->active = NULL;
 	spin_unlock_irq(&dcmi->irqlock);
 
 	return ret;
@@ -702,8 +689,6 @@ static void dcmi_stop_streaming(struct vb2_queue *vq)
 {
 	struct stm32_dcmi *dcmi = vb2_get_drv_priv(vq);
 	struct dcmi_buf *buf, *node;
-	unsigned long time_ms = msecs_to_jiffies(TIMEOUT_MS);
-	long timeout;
 	int ret;
 
 	/* Disable stream on the sub device */
@@ -713,13 +698,6 @@ static void dcmi_stop_streaming(struct vb2_queue *vq)
 			__func__, ret);
 
 	spin_lock_irq(&dcmi->irqlock);
-	dcmi->state = STOPPING;
-	spin_unlock_irq(&dcmi->irqlock);
-
-	timeout = wait_for_completion_interruptible_timeout(&dcmi->complete,
-							    time_ms);
-
-	spin_lock_irq(&dcmi->irqlock);
 
 	/* Disable interruptions */
 	reg_clear(dcmi->regs, DCMI_IER, IT_FRAME | IT_OVR | IT_ERR);
@@ -727,29 +705,21 @@ static void dcmi_stop_streaming(struct vb2_queue *vq)
 	/* Disable DCMI */
 	reg_clear(dcmi->regs, DCMI_CR, CR_ENABLE);
 
-	if (!timeout) {
-		dev_err(dcmi->dev, "%s: Timeout during stop streaming\n",
-			__func__);
-		dcmi->state = STOPPED;
-	}
-
 	/* Return all queued buffers to vb2 in ERROR state */
-	if (dcmi->active) {
-		buf = dcmi->active;
-		vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR);
-		dcmi->active = NULL;
-	}
 	list_for_each_entry_safe(buf, node, &dcmi->buffers, list) {
 		list_del_init(&buf->list);
 		vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR);
 	}
 
+	dcmi->active = NULL;
+	dcmi->state = STOPPED;
+
 	spin_unlock_irq(&dcmi->irqlock);
 
 	/* Stop all pending DMA operations */
 	dmaengine_terminate_all(dcmi->dma_chan);
 
-	clk_disable(dcmi->mclk);
+	pm_runtime_put(dcmi->dev);
 
 	if (dcmi->errors_count)
 		dev_warn(dcmi->dev, "Some errors found while streaming: errors=%d (overrun=%d), buffers=%d\n",
@@ -843,14 +813,8 @@ static int dcmi_try_fmt(struct stm32_dcmi *dcmi, struct v4l2_format *f,
 	}
 
 	/* Limit to hardware capabilities */
-	if (pix->pixelformat == V4L2_PIX_FMT_JPEG) {
-		pix->width = clamp(pix->width, MIN_JPEG_WIDTH, MAX_JPEG_WIDTH);
-		pix->height =
-			clamp(pix->height, MIN_JPEG_HEIGHT, MAX_JPEG_HEIGHT);
-	} else {
-		pix->width = clamp(pix->width, MIN_WIDTH, MAX_WIDTH);
-		pix->height = clamp(pix->height, MIN_HEIGHT, MAX_HEIGHT);
-	}
+	pix->width = clamp(pix->width, MIN_WIDTH, MAX_WIDTH);
+	pix->height = clamp(pix->height, MIN_HEIGHT, MAX_HEIGHT);
 
 	/* No crop if JPEG is requested */
 	do_crop = dcmi->do_crop && (pix->pixelformat != V4L2_PIX_FMT_JPEG);
@@ -1605,23 +1569,20 @@ static int dcmi_graph_parse(struct stm32_dcmi *dcmi, struct device_node *node)
 	struct device_node *ep = NULL;
 	struct device_node *remote;
 
-	while (1) {
-		ep = of_graph_get_next_endpoint(node, ep);
-		if (!ep)
-			return -EINVAL;
+	ep = of_graph_get_next_endpoint(node, ep);
+	if (!ep)
+		return -EINVAL;
 
-		remote = of_graph_get_remote_port_parent(ep);
-		if (!remote) {
-			of_node_put(ep);
-			return -EINVAL;
-		}
+	remote = of_graph_get_remote_port_parent(ep);
+	of_node_put(ep);
+	if (!remote)
+		return -EINVAL;
 
-		/* Remote node to connect */
-		dcmi->entity.node = remote;
-		dcmi->entity.asd.match_type = V4L2_ASYNC_MATCH_FWNODE;
-		dcmi->entity.asd.match.fwnode = of_fwnode_handle(remote);
-		return 0;
-	}
+	/* Remote node to connect */
+	dcmi->entity.node = remote;
+	dcmi->entity.asd.match_type = V4L2_ASYNC_MATCH_FWNODE;
+	dcmi->entity.asd.match.fwnode = of_fwnode_handle(remote);
+	return 0;
 }
 
 static int dcmi_graph_init(struct stm32_dcmi *dcmi)
@@ -1696,23 +1657,20 @@ static int dcmi_probe(struct platform_device *pdev)
 	}
 
 	ret = v4l2_fwnode_endpoint_parse(of_fwnode_handle(np), &ep);
+	of_node_put(np);
 	if (ret) {
 		dev_err(&pdev->dev, "Could not parse the endpoint\n");
-		of_node_put(np);
 		return -ENODEV;
 	}
 
 	if (ep.bus_type == V4L2_MBUS_CSI2) {
 		dev_err(&pdev->dev, "CSI bus not supported\n");
-		of_node_put(np);
 		return -ENODEV;
 	}
 	dcmi->bus.flags = ep.bus.parallel.flags;
 	dcmi->bus.bus_width = ep.bus.parallel.bus_width;
 	dcmi->bus.data_shift = ep.bus.parallel.data_shift;
 
-	of_node_put(np);
-
 	irq = platform_get_irq(pdev, 0);
 	if (irq <= 0) {
 		dev_err(&pdev->dev, "Could not get irq\n");
@@ -1751,12 +1709,6 @@ static int dcmi_probe(struct platform_device *pdev)
 		return -EPROBE_DEFER;
 	}
 
-	ret = clk_prepare(mclk);
-	if (ret) {
-		dev_err(&pdev->dev, "Unable to prepare mclk %p\n", mclk);
-		goto err_dma_release;
-	}
-
 	spin_lock_init(&dcmi->irqlock);
 	mutex_init(&dcmi->lock);
 	init_completion(&dcmi->complete);
@@ -1772,7 +1724,7 @@ static int dcmi_probe(struct platform_device *pdev)
 	/* Initialize the top-level structure */
 	ret = v4l2_device_register(&pdev->dev, &dcmi->v4l2_dev);
 	if (ret)
-		goto err_clk_unprepare;
+		goto err_dma_release;
 
 	dcmi->vdev = video_device_alloc();
 	if (!dcmi->vdev) {
@@ -1832,14 +1784,15 @@ static int dcmi_probe(struct platform_device *pdev)
 	dev_info(&pdev->dev, "Probe done\n");
 
 	platform_set_drvdata(pdev, dcmi);
+
+	pm_runtime_enable(&pdev->dev);
+
 	return 0;
 
 err_device_release:
 	video_device_release(dcmi->vdev);
 err_device_unregister:
 	v4l2_device_unregister(&dcmi->v4l2_dev);
-err_clk_unprepare:
-	clk_unprepare(dcmi->mclk);
 err_dma_release:
 	dma_release_channel(dcmi->dma_chan);
 
@@ -1850,20 +1803,72 @@ static int dcmi_remove(struct platform_device *pdev)
 {
 	struct stm32_dcmi *dcmi = platform_get_drvdata(pdev);
 
+	pm_runtime_disable(&pdev->dev);
+
 	v4l2_async_notifier_unregister(&dcmi->notifier);
 	v4l2_device_unregister(&dcmi->v4l2_dev);
-	clk_unprepare(dcmi->mclk);
+
 	dma_release_channel(dcmi->dma_chan);
 
 	return 0;
 }
 
+static __maybe_unused int dcmi_runtime_suspend(struct device *dev)
+{
+	struct stm32_dcmi *dcmi = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(dcmi->mclk);
+
+	return 0;
+}
+
+static __maybe_unused int dcmi_runtime_resume(struct device *dev)
+{
+	struct stm32_dcmi *dcmi = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(dcmi->mclk);
+	if (ret)
+		dev_err(dev, "%s: Failed to prepare_enable clock\n", __func__);
+
+	return ret;
+}
+
+static __maybe_unused int dcmi_suspend(struct device *dev)
+{
+	/* disable clock */
+	pm_runtime_force_suspend(dev);
+
+	/* change pinctrl state */
+	pinctrl_pm_select_sleep_state(dev);
+
+	return 0;
+}
+
+static __maybe_unused int dcmi_resume(struct device *dev)
+{
+	/* restore pinctl default state */
+	pinctrl_pm_select_default_state(dev);
+
+	/* clock enable */
+	pm_runtime_force_resume(dev);
+
+	return 0;
+}
+
+static const struct dev_pm_ops dcmi_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(dcmi_suspend, dcmi_resume)
+	SET_RUNTIME_PM_OPS(dcmi_runtime_suspend,
+			   dcmi_runtime_resume, NULL)
+};
+
 static struct platform_driver stm32_dcmi_driver = {
 	.probe		= dcmi_probe,
 	.remove		= dcmi_remove,
 	.driver		= {
 		.name = DRV_NAME,
 		.of_match_table = of_match_ptr(stm32_dcmi_of_match),
+		.pm = &dcmi_pm_ops,
 	},
 };
 
diff --git a/drivers/media/platform/ti-vpe/vpe.c b/drivers/media/platform/ti-vpe/vpe.c
index e395aa85c8ad..d70871d0ad2d 100644
--- a/drivers/media/platform/ti-vpe/vpe.c
+++ b/drivers/media/platform/ti-vpe/vpe.c
@@ -953,23 +953,6 @@ static void job_abort(void *priv)
 	ctx->aborting = 1;
 }
 
-/*
- * Lock access to the device
- */
-static void vpe_lock(void *priv)
-{
-	struct vpe_ctx *ctx = priv;
-	struct vpe_dev *dev = ctx->dev;
-	mutex_lock(&dev->dev_mutex);
-}
-
-static void vpe_unlock(void *priv)
-{
-	struct vpe_ctx *ctx = priv;
-	struct vpe_dev *dev = ctx->dev;
-	mutex_unlock(&dev->dev_mutex);
-}
-
 static void vpe_dump_regs(struct vpe_dev *dev)
 {
 #define DUMPREG(r) vpe_dbg(dev, "%-35s %08x\n", #r, read_reg(dev, VPE_##r))
@@ -2434,8 +2417,6 @@ static const struct v4l2_m2m_ops m2m_ops = {
 	.device_run	= device_run,
 	.job_ready	= job_ready,
 	.job_abort	= job_abort,
-	.lock		= vpe_lock,
-	.unlock		= vpe_unlock,
 };
 
 static int vpe_runtime_get(struct platform_device *pdev)
@@ -2485,7 +2466,6 @@ static void vpe_fw_cb(struct platform_device *pdev)
 	}
 
 	video_set_drvdata(vfd, dev);
-	snprintf(vfd->name, sizeof(vfd->name), "%s", vpe_videodev.name);
 	dev_info(dev->v4l2_dev.dev, "Device registered as /dev/video%d\n",
 		vfd->num);
 }
diff --git a/drivers/media/platform/vicodec/Kconfig b/drivers/media/platform/vicodec/Kconfig
new file mode 100644
index 000000000000..2503bcb1529f
--- /dev/null
+++ b/drivers/media/platform/vicodec/Kconfig
@@ -0,0 +1,13 @@
+config VIDEO_VICODEC
+	tristate "Virtual Codec Driver"
+	depends on VIDEO_DEV && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
+	select VIDEOBUF2_VMALLOC
+	select V4L2_MEM2MEM_DEV
+	default n
+	help
+	  Driver for a Virtual Codec
+
+	  This driver can be compared to the vim2m driver for emulating
+	  a video device node that exposes an emulated hardware codec.
+
+	  When in doubt, say N.
diff --git a/drivers/media/platform/vicodec/Makefile b/drivers/media/platform/vicodec/Makefile
new file mode 100644
index 000000000000..197229428953
--- /dev/null
+++ b/drivers/media/platform/vicodec/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+vicodec-objs := vicodec-core.o vicodec-codec.o
+
+obj-$(CONFIG_VIDEO_VICODEC) += vicodec.o
diff --git a/drivers/media/platform/vicodec/vicodec-codec.c b/drivers/media/platform/vicodec/vicodec-codec.c
new file mode 100644
index 000000000000..2d047646f614
--- /dev/null
+++ b/drivers/media/platform/vicodec/vicodec-codec.c
@@ -0,0 +1,797 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright 2016 Tom aan de Wiel
+ * Copyright 2018 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * 8x8 Fast Walsh Hadamard Transform in sequency order based on the paper:
+ *
+ * A Recursive Algorithm for Sequency-Ordered Fast Walsh Transforms,
+ * R.D. Brown, 1977
+ */
+
+#include <linux/string.h>
+#include "vicodec-codec.h"
+
+#define ALL_ZEROS 15
+#define DEADZONE_WIDTH 20
+
+static const uint8_t zigzag[64] = {
+	0,
+	1,  8,
+	2,  9, 16,
+	3, 10, 17, 24,
+	4, 11, 18, 25, 32,
+	5, 12, 19, 26, 33, 40,
+	6, 13, 20, 27, 34, 41, 48,
+	7, 14, 21, 28, 35, 42, 49, 56,
+	15, 22, 29, 36, 43, 50, 57,
+	23, 30, 37, 44, 51, 58,
+	31, 38, 45, 52, 59,
+	39, 46, 53, 60,
+	47, 54, 61,
+	55, 62,
+	63,
+};
+
+
+static int rlc(const s16 *in, __be16 *output, int blocktype)
+{
+	s16 block[8 * 8];
+	s16 *wp = block;
+	int i = 0;
+	int x, y;
+	int ret = 0;
+
+	/* read in block from framebuffer */
+	int lastzero_run = 0;
+	int to_encode;
+
+	for (y = 0; y < 8; y++) {
+		for (x = 0; x < 8; x++) {
+			*wp = in[x + y * 8];
+			wp++;
+		}
+	}
+
+	/* keep track of amount of trailing zeros */
+	for (i = 63; i >= 0 && !block[zigzag[i]]; i--)
+		lastzero_run++;
+
+	*output++ = (blocktype == PBLOCK ? htons(PFRAME_BIT) : 0);
+	ret++;
+
+	to_encode = 8 * 8 - (lastzero_run > 14 ? lastzero_run : 0);
+
+	i = 0;
+	while (i < to_encode) {
+		int cnt = 0;
+		int tmp;
+
+		/* count leading zeros */
+		while ((tmp = block[zigzag[i]]) == 0 && cnt < 14) {
+			cnt++;
+			i++;
+			if (i == to_encode) {
+				cnt--;
+				break;
+			}
+		}
+		/* 4 bits for run, 12 for coefficient (quantization by 4) */
+		*output++ = htons((cnt | tmp << 4));
+		i++;
+		ret++;
+	}
+	if (lastzero_run > 14) {
+		*output = htons(ALL_ZEROS | 0);
+		ret++;
+	}
+
+	return ret;
+}
+
+/*
+ * This function will worst-case increase rlc_in by 65*2 bytes:
+ * one s16 value for the header and 8 * 8 coefficients of type s16.
+ */
+static s16 derlc(const __be16 **rlc_in, s16 *dwht_out)
+{
+	/* header */
+	const __be16 *input = *rlc_in;
+	s16 ret = ntohs(*input++);
+	int dec_count = 0;
+	s16 block[8 * 8 + 16];
+	s16 *wp = block;
+	int i;
+
+	/*
+	 * Now de-compress, it expands one byte to up to 15 bytes
+	 * (or fills the remainder of the 64 bytes with zeroes if it
+	 * is the last byte to expand).
+	 *
+	 * So block has to be 8 * 8 + 16 bytes, the '+ 16' is to
+	 * allow for overflow if the incoming data was malformed.
+	 */
+	while (dec_count < 8 * 8) {
+		s16 in = ntohs(*input++);
+		int length = in & 0xf;
+		int coeff = in >> 4;
+
+		/* fill remainder with zeros */
+		if (length == 15) {
+			for (i = 0; i < 64 - dec_count; i++)
+				*wp++ = 0;
+			break;
+		}
+
+		for (i = 0; i < length; i++)
+			*wp++ = 0;
+		*wp++ = coeff;
+		dec_count += length + 1;
+	}
+
+	wp = block;
+
+	for (i = 0; i < 64; i++) {
+		int pos = zigzag[i];
+		int y = pos / 8;
+		int x = pos % 8;
+
+		dwht_out[x + y * 8] = *wp++;
+	}
+	*rlc_in = input;
+	return ret;
+}
+
+static const int quant_table[] = {
+	2, 2, 2, 2, 2, 2,  2,  2,
+	2, 2, 2, 2, 2, 2,  2,  2,
+	2, 2, 2, 2, 2, 2,  2,  3,
+	2, 2, 2, 2, 2, 2,  3,  6,
+	2, 2, 2, 2, 2, 3,  6,  6,
+	2, 2, 2, 2, 3, 6,  6,  6,
+	2, 2, 2, 3, 6, 6,  6,  6,
+	2, 2, 3, 6, 6, 6,  6,  8,
+};
+
+static const int quant_table_p[] = {
+	3, 3, 3, 3, 3, 3,  3,  3,
+	3, 3, 3, 3, 3, 3,  3,  3,
+	3, 3, 3, 3, 3, 3,  3,  3,
+	3, 3, 3, 3, 3, 3,  3,  6,
+	3, 3, 3, 3, 3, 3,  6,  6,
+	3, 3, 3, 3, 3, 6,  6,  9,
+	3, 3, 3, 3, 6, 6,  9,  9,
+	3, 3, 3, 6, 6, 9,  9,  10,
+};
+
+static void quantize_intra(s16 *coeff, s16 *de_coeff)
+{
+	const int *quant = quant_table;
+	int i, j;
+
+	for (j = 0; j < 8; j++) {
+		for (i = 0; i < 8; i++, quant++, coeff++, de_coeff++) {
+			*coeff >>= *quant;
+			if (*coeff >= -DEADZONE_WIDTH &&
+			    *coeff <= DEADZONE_WIDTH)
+				*coeff = *de_coeff = 0;
+			else
+				*de_coeff = *coeff << *quant;
+		}
+	}
+}
+
+static void dequantize_intra(s16 *coeff)
+{
+	const int *quant = quant_table;
+	int i, j;
+
+	for (j = 0; j < 8; j++)
+		for (i = 0; i < 8; i++, quant++, coeff++)
+			*coeff <<= *quant;
+}
+
+static void quantize_inter(s16 *coeff, s16 *de_coeff)
+{
+	const int *quant = quant_table_p;
+	int i, j;
+
+	for (j = 0; j < 8; j++) {
+		for (i = 0; i < 8; i++, quant++, coeff++, de_coeff++) {
+			*coeff >>= *quant;
+			if (*coeff >= -DEADZONE_WIDTH &&
+			    *coeff <= DEADZONE_WIDTH)
+				*coeff = *de_coeff = 0;
+			else
+				*de_coeff = *coeff << *quant;
+		}
+	}
+}
+
+static void dequantize_inter(s16 *coeff)
+{
+	const int *quant = quant_table_p;
+	int i, j;
+
+	for (j = 0; j < 8; j++)
+		for (i = 0; i < 8; i++, quant++, coeff++)
+			*coeff <<= *quant;
+}
+
+static void fwht(const u8 *block, s16 *output_block, unsigned int stride,
+		 unsigned int input_step, bool intra)
+{
+	/* we'll need more than 8 bits for the transformed coefficients */
+	s32 workspace1[8], workspace2[8];
+	const u8 *tmp = block;
+	s16 *out = output_block;
+	int add = intra ? 256 : 0;
+	unsigned int i;
+
+	/* stage 1 */
+	stride *= input_step;
+
+	for (i = 0; i < 8; i++, tmp += stride, out += 8) {
+		if (input_step == 1) {
+			workspace1[0]  = tmp[0] + tmp[1] - add;
+			workspace1[1]  = tmp[0] - tmp[1];
+
+			workspace1[2]  = tmp[2] + tmp[3] - add;
+			workspace1[3]  = tmp[2] - tmp[3];
+
+			workspace1[4]  = tmp[4] + tmp[5] - add;
+			workspace1[5]  = tmp[4] - tmp[5];
+
+			workspace1[6]  = tmp[6] + tmp[7] - add;
+			workspace1[7]  = tmp[6] - tmp[7];
+		} else {
+			workspace1[0]  = tmp[0] + tmp[2] - add;
+			workspace1[1]  = tmp[0] - tmp[2];
+
+			workspace1[2]  = tmp[4] + tmp[6] - add;
+			workspace1[3]  = tmp[4] - tmp[6];
+
+			workspace1[4]  = tmp[8] + tmp[10] - add;
+			workspace1[5]  = tmp[8] - tmp[10];
+
+			workspace1[6]  = tmp[12] + tmp[14] - add;
+			workspace1[7]  = tmp[12] - tmp[14];
+		}
+
+		/* stage 2 */
+		workspace2[0] = workspace1[0] + workspace1[2];
+		workspace2[1] = workspace1[0] - workspace1[2];
+		workspace2[2] = workspace1[1] - workspace1[3];
+		workspace2[3] = workspace1[1] + workspace1[3];
+
+		workspace2[4] = workspace1[4] + workspace1[6];
+		workspace2[5] = workspace1[4] - workspace1[6];
+		workspace2[6] = workspace1[5] - workspace1[7];
+		workspace2[7] = workspace1[5] + workspace1[7];
+
+		/* stage 3 */
+		out[0] = workspace2[0] + workspace2[4];
+		out[1] = workspace2[0] - workspace2[4];
+		out[2] = workspace2[1] - workspace2[5];
+		out[3] = workspace2[1] + workspace2[5];
+		out[4] = workspace2[2] + workspace2[6];
+		out[5] = workspace2[2] - workspace2[6];
+		out[6] = workspace2[3] - workspace2[7];
+		out[7] = workspace2[3] + workspace2[7];
+	}
+
+	out = output_block;
+
+	for (i = 0; i < 8; i++, out++) {
+		/* stage 1 */
+		workspace1[0]  = out[0] + out[1 * 8];
+		workspace1[1]  = out[0] - out[1 * 8];
+
+		workspace1[2]  = out[2 * 8] + out[3 * 8];
+		workspace1[3]  = out[2 * 8] - out[3 * 8];
+
+		workspace1[4]  = out[4 * 8] + out[5 * 8];
+		workspace1[5]  = out[4 * 8] - out[5 * 8];
+
+		workspace1[6]  = out[6 * 8] + out[7 * 8];
+		workspace1[7]  = out[6 * 8] - out[7 * 8];
+
+		/* stage 2 */
+		workspace2[0] = workspace1[0] + workspace1[2];
+		workspace2[1] = workspace1[0] - workspace1[2];
+		workspace2[2] = workspace1[1] - workspace1[3];
+		workspace2[3] = workspace1[1] + workspace1[3];
+
+		workspace2[4] = workspace1[4] + workspace1[6];
+		workspace2[5] = workspace1[4] - workspace1[6];
+		workspace2[6] = workspace1[5] - workspace1[7];
+		workspace2[7] = workspace1[5] + workspace1[7];
+		/* stage 3 */
+		out[0 * 8] = workspace2[0] + workspace2[4];
+		out[1 * 8] = workspace2[0] - workspace2[4];
+		out[2 * 8] = workspace2[1] - workspace2[5];
+		out[3 * 8] = workspace2[1] + workspace2[5];
+		out[4 * 8] = workspace2[2] + workspace2[6];
+		out[5 * 8] = workspace2[2] - workspace2[6];
+		out[6 * 8] = workspace2[3] - workspace2[7];
+		out[7 * 8] = workspace2[3] + workspace2[7];
+	}
+}
+
+/*
+ * Not the nicest way of doing it, but P-blocks get twice the range of
+ * that of the I-blocks. Therefore we need a type bigger than 8 bits.
+ * Furthermore values can be negative... This is just a version that
+ * works with 16 signed data
+ */
+static void fwht16(const s16 *block, s16 *output_block, int stride, int intra)
+{
+	/* we'll need more than 8 bits for the transformed coefficients */
+	s32 workspace1[8], workspace2[8];
+	const s16 *tmp = block;
+	s16 *out = output_block;
+	int i;
+
+	for (i = 0; i < 8; i++, tmp += stride, out += 8) {
+		/* stage 1 */
+		workspace1[0]  = tmp[0] + tmp[1];
+		workspace1[1]  = tmp[0] - tmp[1];
+
+		workspace1[2]  = tmp[2] + tmp[3];
+		workspace1[3]  = tmp[2] - tmp[3];
+
+		workspace1[4]  = tmp[4] + tmp[5];
+		workspace1[5]  = tmp[4] - tmp[5];
+
+		workspace1[6]  = tmp[6] + tmp[7];
+		workspace1[7]  = tmp[6] - tmp[7];
+
+		/* stage 2 */
+		workspace2[0] = workspace1[0] + workspace1[2];
+		workspace2[1] = workspace1[0] - workspace1[2];
+		workspace2[2] = workspace1[1] - workspace1[3];
+		workspace2[3] = workspace1[1] + workspace1[3];
+
+		workspace2[4] = workspace1[4] + workspace1[6];
+		workspace2[5] = workspace1[4] - workspace1[6];
+		workspace2[6] = workspace1[5] - workspace1[7];
+		workspace2[7] = workspace1[5] + workspace1[7];
+
+		/* stage 3 */
+		out[0] = workspace2[0] + workspace2[4];
+		out[1] = workspace2[0] - workspace2[4];
+		out[2] = workspace2[1] - workspace2[5];
+		out[3] = workspace2[1] + workspace2[5];
+		out[4] = workspace2[2] + workspace2[6];
+		out[5] = workspace2[2] - workspace2[6];
+		out[6] = workspace2[3] - workspace2[7];
+		out[7] = workspace2[3] + workspace2[7];
+	}
+
+	out = output_block;
+
+	for (i = 0; i < 8; i++, out++) {
+		/* stage 1 */
+		workspace1[0]  = out[0] + out[1*8];
+		workspace1[1]  = out[0] - out[1*8];
+
+		workspace1[2]  = out[2*8] + out[3*8];
+		workspace1[3]  = out[2*8] - out[3*8];
+
+		workspace1[4]  = out[4*8] + out[5*8];
+		workspace1[5]  = out[4*8] - out[5*8];
+
+		workspace1[6]  = out[6*8] + out[7*8];
+		workspace1[7]  = out[6*8] - out[7*8];
+
+		/* stage 2 */
+		workspace2[0] = workspace1[0] + workspace1[2];
+		workspace2[1] = workspace1[0] - workspace1[2];
+		workspace2[2] = workspace1[1] - workspace1[3];
+		workspace2[3] = workspace1[1] + workspace1[3];
+
+		workspace2[4] = workspace1[4] + workspace1[6];
+		workspace2[5] = workspace1[4] - workspace1[6];
+		workspace2[6] = workspace1[5] - workspace1[7];
+		workspace2[7] = workspace1[5] + workspace1[7];
+
+		/* stage 3 */
+		out[0*8] = workspace2[0] + workspace2[4];
+		out[1*8] = workspace2[0] - workspace2[4];
+		out[2*8] = workspace2[1] - workspace2[5];
+		out[3*8] = workspace2[1] + workspace2[5];
+		out[4*8] = workspace2[2] + workspace2[6];
+		out[5*8] = workspace2[2] - workspace2[6];
+		out[6*8] = workspace2[3] - workspace2[7];
+		out[7*8] = workspace2[3] + workspace2[7];
+	}
+}
+
+static void ifwht(const s16 *block, s16 *output_block, int intra)
+{
+	/*
+	 * we'll need more than 8 bits for the transformed coefficients
+	 * use native unit of cpu
+	 */
+	int workspace1[8], workspace2[8];
+	int inter = intra ? 0 : 1;
+	const s16 *tmp = block;
+	s16 *out = output_block;
+	int i;
+
+	for (i = 0; i < 8; i++, tmp += 8, out += 8) {
+		/* stage 1 */
+		workspace1[0]  = tmp[0] + tmp[1];
+		workspace1[1]  = tmp[0] - tmp[1];
+
+		workspace1[2]  = tmp[2] + tmp[3];
+		workspace1[3]  = tmp[2] - tmp[3];
+
+		workspace1[4]  = tmp[4] + tmp[5];
+		workspace1[5]  = tmp[4] - tmp[5];
+
+		workspace1[6]  = tmp[6] + tmp[7];
+		workspace1[7]  = tmp[6] - tmp[7];
+
+		/* stage 2 */
+		workspace2[0] = workspace1[0] + workspace1[2];
+		workspace2[1] = workspace1[0] - workspace1[2];
+		workspace2[2] = workspace1[1] - workspace1[3];
+		workspace2[3] = workspace1[1] + workspace1[3];
+
+		workspace2[4] = workspace1[4] + workspace1[6];
+		workspace2[5] = workspace1[4] - workspace1[6];
+		workspace2[6] = workspace1[5] - workspace1[7];
+		workspace2[7] = workspace1[5] + workspace1[7];
+
+		/* stage 3 */
+		out[0] = workspace2[0] + workspace2[4];
+		out[1] = workspace2[0] - workspace2[4];
+		out[2] = workspace2[1] - workspace2[5];
+		out[3] = workspace2[1] + workspace2[5];
+		out[4] = workspace2[2] + workspace2[6];
+		out[5] = workspace2[2] - workspace2[6];
+		out[6] = workspace2[3] - workspace2[7];
+		out[7] = workspace2[3] + workspace2[7];
+	}
+
+	out = output_block;
+
+	for (i = 0; i < 8; i++, out++) {
+		/* stage 1 */
+		workspace1[0]  = out[0] + out[1 * 8];
+		workspace1[1]  = out[0] - out[1 * 8];
+
+		workspace1[2]  = out[2 * 8] + out[3 * 8];
+		workspace1[3]  = out[2 * 8] - out[3 * 8];
+
+		workspace1[4]  = out[4 * 8] + out[5 * 8];
+		workspace1[5]  = out[4 * 8] - out[5 * 8];
+
+		workspace1[6]  = out[6 * 8] + out[7 * 8];
+		workspace1[7]  = out[6 * 8] - out[7 * 8];
+
+		/* stage 2 */
+		workspace2[0] = workspace1[0] + workspace1[2];
+		workspace2[1] = workspace1[0] - workspace1[2];
+		workspace2[2] = workspace1[1] - workspace1[3];
+		workspace2[3] = workspace1[1] + workspace1[3];
+
+		workspace2[4] = workspace1[4] + workspace1[6];
+		workspace2[5] = workspace1[4] - workspace1[6];
+		workspace2[6] = workspace1[5] - workspace1[7];
+		workspace2[7] = workspace1[5] + workspace1[7];
+
+		/* stage 3 */
+		if (inter) {
+			int d;
+
+			out[0 * 8] = workspace2[0] + workspace2[4];
+			out[1 * 8] = workspace2[0] - workspace2[4];
+			out[2 * 8] = workspace2[1] - workspace2[5];
+			out[3 * 8] = workspace2[1] + workspace2[5];
+			out[4 * 8] = workspace2[2] + workspace2[6];
+			out[5 * 8] = workspace2[2] - workspace2[6];
+			out[6 * 8] = workspace2[3] - workspace2[7];
+			out[7 * 8] = workspace2[3] + workspace2[7];
+
+			for (d = 0; d < 8; d++)
+				out[8 * d] >>= 6;
+		} else {
+			int d;
+
+			out[0 * 8] = workspace2[0] + workspace2[4];
+			out[1 * 8] = workspace2[0] - workspace2[4];
+			out[2 * 8] = workspace2[1] - workspace2[5];
+			out[3 * 8] = workspace2[1] + workspace2[5];
+			out[4 * 8] = workspace2[2] + workspace2[6];
+			out[5 * 8] = workspace2[2] - workspace2[6];
+			out[6 * 8] = workspace2[3] - workspace2[7];
+			out[7 * 8] = workspace2[3] + workspace2[7];
+
+			for (d = 0; d < 8; d++) {
+				out[8 * d] >>= 6;
+				out[8 * d] += 128;
+			}
+		}
+	}
+}
+
+static void fill_encoder_block(const u8 *input, s16 *dst,
+			       unsigned int stride, unsigned int input_step)
+{
+	int i, j;
+
+	for (i = 0; i < 8; i++) {
+		for (j = 0; j < 8; j++, input += input_step)
+			*dst++ = *input;
+		input += (stride - 8) * input_step;
+	}
+}
+
+static int var_intra(const s16 *input)
+{
+	int32_t mean = 0;
+	int32_t ret = 0;
+	const s16 *tmp = input;
+	int i;
+
+	for (i = 0; i < 8 * 8; i++, tmp++)
+		mean += *tmp;
+	mean /= 64;
+	tmp = input;
+	for (i = 0; i < 8 * 8; i++, tmp++)
+		ret += (*tmp - mean) < 0 ? -(*tmp - mean) : (*tmp - mean);
+	return ret;
+}
+
+static int var_inter(const s16 *old, const s16 *new)
+{
+	int32_t ret = 0;
+	int i;
+
+	for (i = 0; i < 8 * 8; i++, old++, new++)
+		ret += (*old - *new) < 0 ? -(*old - *new) : (*old - *new);
+	return ret;
+}
+
+static int decide_blocktype(const u8 *cur, const u8 *reference,
+			    s16 *deltablock, unsigned int stride,
+			    unsigned int input_step)
+{
+	s16 tmp[64];
+	s16 old[64];
+	s16 *work = tmp;
+	unsigned int k, l;
+	int vari;
+	int vard;
+
+	fill_encoder_block(cur, tmp, stride, input_step);
+	fill_encoder_block(reference, old, 8, 1);
+	vari = var_intra(tmp);
+
+	for (k = 0; k < 8; k++) {
+		for (l = 0; l < 8; l++) {
+			*deltablock = *work - *reference;
+			deltablock++;
+			work++;
+			reference++;
+		}
+	}
+	deltablock -= 64;
+	vard = var_inter(old, tmp);
+	return vari <= vard ? IBLOCK : PBLOCK;
+}
+
+static void fill_decoder_block(u8 *dst, const s16 *input, int stride)
+{
+	int i, j;
+
+	for (i = 0; i < 8; i++) {
+		for (j = 0; j < 8; j++)
+			*dst++ = *input++;
+		dst += stride - 8;
+	}
+}
+
+static void add_deltas(s16 *deltas, const u8 *ref, int stride)
+{
+	int k, l;
+
+	for (k = 0; k < 8; k++) {
+		for (l = 0; l < 8; l++) {
+			*deltas += *ref++;
+			/*
+			 * Due to quantizing, it might possible that the
+			 * decoded coefficients are slightly out of range
+			 */
+			if (*deltas < 0)
+				*deltas = 0;
+			else if (*deltas > 255)
+				*deltas = 255;
+			deltas++;
+		}
+		ref += stride - 8;
+	}
+}
+
+static u32 encode_plane(u8 *input, u8 *refp, __be16 **rlco, __be16 *rlco_max,
+			struct cframe *cf, u32 height, u32 width,
+			unsigned int input_step,
+			bool is_intra, bool next_is_intra)
+{
+	u8 *input_start = input;
+	__be16 *rlco_start = *rlco;
+	s16 deltablock[64];
+	__be16 pframe_bit = htons(PFRAME_BIT);
+	u32 encoding = 0;
+	unsigned int last_size = 0;
+	unsigned int i, j;
+
+	for (j = 0; j < height / 8; j++) {
+		for (i = 0; i < width / 8; i++) {
+			/* intra code, first frame is always intra coded. */
+			int blocktype = IBLOCK;
+			unsigned int size;
+
+			if (!is_intra)
+				blocktype = decide_blocktype(input, refp,
+					deltablock, width, input_step);
+			if (is_intra || blocktype == IBLOCK) {
+				fwht(input, cf->coeffs, width, input_step, 1);
+				quantize_intra(cf->coeffs, cf->de_coeffs);
+				blocktype = IBLOCK;
+			} else {
+				/* inter code */
+				encoding |= FRAME_PCODED;
+				fwht16(deltablock, cf->coeffs, 8, 0);
+				quantize_inter(cf->coeffs, cf->de_coeffs);
+			}
+			if (!next_is_intra) {
+				ifwht(cf->de_coeffs, cf->de_fwht, blocktype);
+
+				if (blocktype == PBLOCK)
+					add_deltas(cf->de_fwht, refp, 8);
+				fill_decoder_block(refp, cf->de_fwht, 8);
+			}
+
+			input += 8 * input_step;
+			refp += 8 * 8;
+
+			if (encoding & FRAME_UNENCODED)
+				continue;
+
+			size = rlc(cf->coeffs, *rlco, blocktype);
+			if (last_size == size &&
+			    !memcmp(*rlco + 1, *rlco - size + 1, 2 * size - 2)) {
+				__be16 *last_rlco = *rlco - size;
+				s16 hdr = ntohs(*last_rlco);
+
+				if (!((*last_rlco ^ **rlco) & pframe_bit) &&
+				    (hdr & DUPS_MASK) < DUPS_MASK)
+					*last_rlco = htons(hdr + 2);
+				else
+					*rlco += size;
+			} else {
+				*rlco += size;
+			}
+			if (*rlco >= rlco_max)
+				encoding |= FRAME_UNENCODED;
+			last_size = size;
+		}
+		input += width * 7 * input_step;
+	}
+	if (encoding & FRAME_UNENCODED) {
+		u8 *out = (u8 *)rlco_start;
+
+		input = input_start;
+		/*
+		 * The compressed stream should never contain the magic
+		 * header, so when we copy the YUV data we replace 0xff
+		 * by 0xfe. Since YUV is limited range such values
+		 * shouldn't appear anyway.
+		 */
+		for (i = 0; i < height * width; i++, input += input_step)
+			*out++ = (*input == 0xff) ? 0xfe : *input;
+		*rlco = (__be16 *)out;
+	}
+	return encoding;
+}
+
+u32 encode_frame(struct raw_frame *frm, struct raw_frame *ref_frm,
+		 struct cframe *cf, bool is_intra, bool next_is_intra)
+{
+	unsigned int size = frm->height * frm->width;
+	__be16 *rlco = cf->rlc_data;
+	__be16 *rlco_max;
+	u32 encoding;
+
+	rlco_max = rlco + size / 2 - 256;
+	encoding = encode_plane(frm->luma, ref_frm->luma, &rlco, rlco_max, cf,
+				  frm->height, frm->width,
+				  1, is_intra, next_is_intra);
+	if (encoding & FRAME_UNENCODED)
+		encoding |= LUMA_UNENCODED;
+	encoding &= ~FRAME_UNENCODED;
+	rlco_max = rlco + size / 8 - 256;
+	encoding |= encode_plane(frm->cb, ref_frm->cb, &rlco, rlco_max, cf,
+				   frm->height / 2, frm->width / 2,
+				   frm->chroma_step, is_intra, next_is_intra);
+	if (encoding & FRAME_UNENCODED)
+		encoding |= CB_UNENCODED;
+	encoding &= ~FRAME_UNENCODED;
+	rlco_max = rlco + size / 8 - 256;
+	encoding |= encode_plane(frm->cr, ref_frm->cr, &rlco, rlco_max, cf,
+				   frm->height / 2, frm->width / 2,
+				   frm->chroma_step, is_intra, next_is_intra);
+	if (encoding & FRAME_UNENCODED)
+		encoding |= CR_UNENCODED;
+	encoding &= ~FRAME_UNENCODED;
+	cf->size = (rlco - cf->rlc_data) * sizeof(*rlco);
+	return encoding;
+}
+
+static void decode_plane(struct cframe *cf, const __be16 **rlco, u8 *ref,
+			 u32 height, u32 width, bool uncompressed)
+{
+	unsigned int copies = 0;
+	s16 copy[8 * 8];
+	s16 stat;
+	unsigned int i, j;
+
+	if (uncompressed) {
+		memcpy(ref, *rlco, width * height);
+		*rlco += width * height / 2;
+		return;
+	}
+
+	/*
+	 * When decoding each macroblock the rlco pointer will be increased
+	 * by 65 * 2 bytes worst-case.
+	 * To avoid overflow the buffer has to be 65/64th of the actual raw
+	 * image size, just in case someone feeds it malicious data.
+	 */
+	for (j = 0; j < height / 8; j++) {
+		for (i = 0; i < width / 8; i++) {
+			u8 *refp = ref + j * 8 * width + i * 8;
+
+			if (copies) {
+				memcpy(cf->de_fwht, copy, sizeof(copy));
+				if (stat & PFRAME_BIT)
+					add_deltas(cf->de_fwht, refp, width);
+				fill_decoder_block(refp, cf->de_fwht, width);
+				copies--;
+				continue;
+			}
+
+			stat = derlc(rlco, cf->coeffs);
+
+			if (stat & PFRAME_BIT)
+				dequantize_inter(cf->coeffs);
+			else
+				dequantize_intra(cf->coeffs);
+
+			ifwht(cf->coeffs, cf->de_fwht,
+			      (stat & PFRAME_BIT) ? 0 : 1);
+
+			copies = (stat & DUPS_MASK) >> 1;
+			if (copies)
+				memcpy(copy, cf->de_fwht, sizeof(copy));
+			if (stat & PFRAME_BIT)
+				add_deltas(cf->de_fwht, refp, width);
+			fill_decoder_block(refp, cf->de_fwht, width);
+		}
+	}
+}
+
+void decode_frame(struct cframe *cf, struct raw_frame *ref, u32 hdr_flags)
+{
+	const __be16 *rlco = cf->rlc_data;
+
+	decode_plane(cf, &rlco, ref->luma, cf->height, cf->width,
+		     hdr_flags & VICODEC_FL_LUMA_IS_UNCOMPRESSED);
+	decode_plane(cf, &rlco, ref->cb, cf->height / 2, cf->width / 2,
+		     hdr_flags & VICODEC_FL_CB_IS_UNCOMPRESSED);
+	decode_plane(cf, &rlco, ref->cr, cf->height / 2, cf->width / 2,
+		     hdr_flags & VICODEC_FL_CR_IS_UNCOMPRESSED);
+}
diff --git a/drivers/media/platform/vicodec/vicodec-codec.h b/drivers/media/platform/vicodec/vicodec-codec.h
new file mode 100644
index 000000000000..cdfad1332a3e
--- /dev/null
+++ b/drivers/media/platform/vicodec/vicodec-codec.h
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright 2016 Tom aan de Wiel
+ * Copyright 2018 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ */
+
+#ifndef VICODEC_RLC_H
+#define VICODEC_RLC_H
+
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <asm/byteorder.h>
+
+/*
+ * The compressed format consists of a cframe_hdr struct followed by the
+ * compressed frame data. The header contains the size of that data.
+ * Each Y, Cb and Cr plane is compressed separately. If the compressed
+ * size of each plane becomes larger than the uncompressed size, then
+ * that plane is stored uncompressed and the corresponding bit is set
+ * in the flags field of the header.
+ *
+ * Each compressed plane consists of macroblocks and each macroblock
+ * is run-length-encoded. Each macroblock starts with a 16 bit value.
+ * Bit 15 indicates if this is a P-coded macroblock (1) or not (0).
+ * P-coded macroblocks contain a delta against the previous frame.
+ *
+ * Bits 1-12 contain a number. If non-zero, then this same macroblock
+ * repeats that number of times. This results in a high degree of
+ * compression for generated images like colorbars.
+ *
+ * Following this macroblock header the MB coefficients are run-length
+ * encoded: the top 12 bits contain the coefficient, the bottom 4 bits
+ * tell how many times this coefficient occurs. The value 0xf indicates
+ * that the remainder of the macroblock should be filled with zeroes.
+ *
+ * All 16 and 32 bit values are stored in big-endian (network) order.
+ *
+ * Each cframe_hdr starts with an 8 byte magic header that is
+ * guaranteed not to occur in the compressed frame data. This header
+ * can be used to sync to the next frame.
+ *
+ * This codec uses the Fast Walsh Hadamard Transform. Tom aan de Wiel
+ * developed this as part of a university project, specifically for use
+ * with this driver. His project report can be found here:
+ *
+ * https://hverkuil.home.xs4all.nl/fwht.pdf
+ */
+
+/*
+ * Note: bit 0 of the header must always be 0. Otherwise it cannot
+ * be guaranteed that the magic 8 byte sequence (see below) can
+ * never occur in the rlc output.
+ */
+#define PFRAME_BIT (1 << 15)
+#define DUPS_MASK 0x1ffe
+
+/*
+ * This is a sequence of 8 bytes with the low 4 bits set to 0xf.
+ *
+ * This sequence cannot occur in the encoded data
+ */
+#define VICODEC_MAGIC1 0x4f4f4f4f
+#define VICODEC_MAGIC2 0xffffffff
+
+#define VICODEC_VERSION 1
+
+#define VICODEC_MAX_WIDTH 3840
+#define VICODEC_MAX_HEIGHT 2160
+#define VICODEC_MIN_WIDTH 640
+#define VICODEC_MIN_HEIGHT 480
+
+#define PBLOCK 0
+#define IBLOCK 1
+
+/* Set if this is an interlaced format */
+#define VICODEC_FL_IS_INTERLACED	BIT(0)
+/* Set if this is a bottom-first (NTSC) interlaced format */
+#define VICODEC_FL_IS_BOTTOM_FIRST	BIT(1)
+/* Set if each 'frame' contains just one field */
+#define VICODEC_FL_IS_ALTERNATE		BIT(2)
+/*
+ * If VICODEC_FL_IS_ALTERNATE was set, then this is set if this
+ * 'frame' is the bottom field, else it is the top field.
+ */
+#define VICODEC_FL_IS_BOTTOM_FIELD	BIT(3)
+/* Set if this frame is uncompressed */
+#define VICODEC_FL_LUMA_IS_UNCOMPRESSED	BIT(4)
+#define VICODEC_FL_CB_IS_UNCOMPRESSED	BIT(5)
+#define VICODEC_FL_CR_IS_UNCOMPRESSED	BIT(6)
+
+struct cframe_hdr {
+	u32 magic1;
+	u32 magic2;
+	__be32 version;
+	__be32 width, height;
+	__be32 flags;
+	__be32 colorspace;
+	__be32 xfer_func;
+	__be32 ycbcr_enc;
+	__be32 quantization;
+	__be32 size;
+};
+
+struct cframe {
+	unsigned int width, height;
+	__be16 *rlc_data;
+	s16 coeffs[8 * 8];
+	s16 de_coeffs[8 * 8];
+	s16 de_fwht[8 * 8];
+	u32 size;
+};
+
+struct raw_frame {
+	unsigned int width, height;
+	unsigned int chroma_step;
+	u8 *luma, *cb, *cr;
+};
+
+#define FRAME_PCODED	BIT(0)
+#define FRAME_UNENCODED	BIT(1)
+#define LUMA_UNENCODED	BIT(2)
+#define CB_UNENCODED	BIT(3)
+#define CR_UNENCODED	BIT(4)
+
+u32 encode_frame(struct raw_frame *frm, struct raw_frame *ref_frm,
+		 struct cframe *cf, bool is_intra, bool next_is_intra);
+void decode_frame(struct cframe *cf, struct raw_frame *ref, u32 hdr_flags);
+
+#endif
diff --git a/drivers/media/platform/vicodec/vicodec-core.c b/drivers/media/platform/vicodec/vicodec-core.c
new file mode 100644
index 000000000000..408cd55d3580
--- /dev/null
+++ b/drivers/media/platform/vicodec/vicodec-core.c
@@ -0,0 +1,1506 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * A virtual codec example device.
+ *
+ * Copyright 2018 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This is a virtual codec device driver for testing the codec framework.
+ * It simulates a device that uses memory buffers for both source and
+ * destination and encodes or decodes the data.
+ */
+
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include <linux/platform_device.h>
+#include <media/v4l2-mem2mem.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-ioctl.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-event.h>
+#include <media/videobuf2-vmalloc.h>
+
+#include "vicodec-codec.h"
+
+MODULE_DESCRIPTION("Virtual codec device");
+MODULE_AUTHOR("Hans Verkuil <hans.verkuil@cisco.com>");
+MODULE_LICENSE("GPL v2");
+
+static bool multiplanar;
+module_param(multiplanar, bool, 0444);
+MODULE_PARM_DESC(multiplanar,
+		 " use multi-planar API instead of single-planar API");
+
+static unsigned int debug;
+module_param(debug, uint, 0644);
+MODULE_PARM_DESC(debug, " activates debug info");
+
+#define VICODEC_NAME		"vicodec"
+#define MAX_WIDTH		4096U
+#define MIN_WIDTH		640U
+#define MAX_HEIGHT		2160U
+#define MIN_HEIGHT		480U
+
+#define dprintk(dev, fmt, arg...) \
+	v4l2_dbg(1, debug, &dev->v4l2_dev, "%s: " fmt, __func__, ## arg)
+
+
+static void vicodec_dev_release(struct device *dev)
+{
+}
+
+static struct platform_device vicodec_pdev = {
+	.name		= VICODEC_NAME,
+	.dev.release	= vicodec_dev_release,
+};
+
+/* Per-queue, driver-specific private data */
+struct vicodec_q_data {
+	unsigned int		width;
+	unsigned int		height;
+	unsigned int		flags;
+	unsigned int		sizeimage;
+	unsigned int		sequence;
+	u32			fourcc;
+};
+
+enum {
+	V4L2_M2M_SRC = 0,
+	V4L2_M2M_DST = 1,
+};
+
+struct vicodec_dev {
+	struct v4l2_device	v4l2_dev;
+	struct video_device	enc_vfd;
+	struct video_device	dec_vfd;
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct media_device	mdev;
+#endif
+
+	struct mutex		enc_mutex;
+	struct mutex		dec_mutex;
+	spinlock_t		enc_lock;
+	spinlock_t		dec_lock;
+
+	struct v4l2_m2m_dev	*enc_dev;
+	struct v4l2_m2m_dev	*dec_dev;
+};
+
+struct vicodec_ctx {
+	struct v4l2_fh		fh;
+	struct vicodec_dev	*dev;
+	bool			is_enc;
+	spinlock_t		*lock;
+
+	struct v4l2_ctrl_handler hdl;
+	struct v4l2_ctrl	*ctrl_gop_size;
+	unsigned int		gop_size;
+	unsigned int		gop_cnt;
+
+	/* Abort requested by m2m */
+	int			aborting;
+	struct vb2_v4l2_buffer *last_src_buf;
+	struct vb2_v4l2_buffer *last_dst_buf;
+
+	enum v4l2_colorspace	colorspace;
+	enum v4l2_ycbcr_encoding ycbcr_enc;
+	enum v4l2_xfer_func	xfer_func;
+	enum v4l2_quantization	quantization;
+
+	/* Source and destination queue data */
+	struct vicodec_q_data   q_data[2];
+	struct raw_frame	ref_frame;
+	u8			*compressed_frame;
+	u32			cur_buf_offset;
+	u32			comp_max_size;
+	u32			comp_size;
+	u32			comp_magic_cnt;
+	u32			comp_frame_size;
+	bool			comp_has_frame;
+	bool			comp_has_next_frame;
+};
+
+static const u32 pixfmts_yuv[] = {
+	V4L2_PIX_FMT_YUV420,
+	V4L2_PIX_FMT_YVU420,
+	V4L2_PIX_FMT_NV12,
+	V4L2_PIX_FMT_NV21,
+};
+
+static inline struct vicodec_ctx *file2ctx(struct file *file)
+{
+	return container_of(file->private_data, struct vicodec_ctx, fh);
+}
+
+static struct vicodec_q_data *get_q_data(struct vicodec_ctx *ctx,
+					 enum v4l2_buf_type type)
+{
+	switch (type) {
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
+		return &ctx->q_data[V4L2_M2M_SRC];
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
+		return &ctx->q_data[V4L2_M2M_DST];
+	default:
+		WARN_ON(1);
+		break;
+	}
+	return NULL;
+}
+
+static void encode(struct vicodec_ctx *ctx,
+		   struct vicodec_q_data *q_data,
+		   u8 *p_in, u8 *p_out)
+{
+	unsigned int size = q_data->width * q_data->height;
+	struct cframe_hdr *p_hdr;
+	struct cframe cf;
+	struct raw_frame rf;
+	u32 encoding;
+
+	rf.width = q_data->width;
+	rf.height = q_data->height;
+	rf.luma = p_in;
+
+	switch (q_data->fourcc) {
+	case V4L2_PIX_FMT_YUV420:
+		rf.cb = rf.luma + size;
+		rf.cr = rf.cb + size / 4;
+		rf.chroma_step = 1;
+		break;
+	case V4L2_PIX_FMT_YVU420:
+		rf.cr = rf.luma + size;
+		rf.cb = rf.cr + size / 4;
+		rf.chroma_step = 1;
+		break;
+	case V4L2_PIX_FMT_NV12:
+		rf.cb = rf.luma + size;
+		rf.cr = rf.cb + 1;
+		rf.chroma_step = 2;
+		break;
+	case V4L2_PIX_FMT_NV21:
+		rf.cr = rf.luma + size;
+		rf.cb = rf.cr + 1;
+		rf.chroma_step = 2;
+		break;
+	}
+
+	cf.width = q_data->width;
+	cf.height = q_data->height;
+	cf.rlc_data = (__be16 *)(p_out + sizeof(*p_hdr));
+
+	encoding = encode_frame(&rf, &ctx->ref_frame, &cf, !ctx->gop_cnt,
+				ctx->gop_cnt == ctx->gop_size - 1);
+	if (encoding != FRAME_PCODED)
+		ctx->gop_cnt = 0;
+	if (++ctx->gop_cnt == ctx->gop_size)
+		ctx->gop_cnt = 0;
+
+	p_hdr = (struct cframe_hdr *)p_out;
+	p_hdr->magic1 = VICODEC_MAGIC1;
+	p_hdr->magic2 = VICODEC_MAGIC2;
+	p_hdr->version = htonl(VICODEC_VERSION);
+	p_hdr->width = htonl(cf.width);
+	p_hdr->height = htonl(cf.height);
+	p_hdr->flags = htonl(q_data->flags);
+	if (encoding & LUMA_UNENCODED)
+		p_hdr->flags |= htonl(VICODEC_FL_LUMA_IS_UNCOMPRESSED);
+	if (encoding & CB_UNENCODED)
+		p_hdr->flags |= htonl(VICODEC_FL_CB_IS_UNCOMPRESSED);
+	if (encoding & CR_UNENCODED)
+		p_hdr->flags |= htonl(VICODEC_FL_CR_IS_UNCOMPRESSED);
+	p_hdr->colorspace = htonl(ctx->colorspace);
+	p_hdr->xfer_func = htonl(ctx->xfer_func);
+	p_hdr->ycbcr_enc = htonl(ctx->ycbcr_enc);
+	p_hdr->quantization = htonl(ctx->quantization);
+	p_hdr->size = htonl(cf.size);
+	ctx->ref_frame.width = cf.width;
+	ctx->ref_frame.height = cf.height;
+}
+
+static int decode(struct vicodec_ctx *ctx,
+		  struct vicodec_q_data *q_data,
+		  u8 *p_in, u8 *p_out)
+{
+	unsigned int size = q_data->width * q_data->height;
+	unsigned int i;
+	struct cframe_hdr *p_hdr;
+	struct cframe cf;
+	u8 *p;
+
+	p_hdr = (struct cframe_hdr *)p_in;
+	cf.width = ntohl(p_hdr->width);
+	cf.height = ntohl(p_hdr->height);
+	q_data->flags = ntohl(p_hdr->flags);
+	ctx->colorspace = ntohl(p_hdr->colorspace);
+	ctx->xfer_func = ntohl(p_hdr->xfer_func);
+	ctx->ycbcr_enc = ntohl(p_hdr->ycbcr_enc);
+	ctx->quantization = ntohl(p_hdr->quantization);
+	cf.rlc_data = (__be16 *)(p_in + sizeof(*p_hdr));
+
+	if (p_hdr->magic1 != VICODEC_MAGIC1 ||
+	    p_hdr->magic2 != VICODEC_MAGIC2 ||
+	    ntohl(p_hdr->version) != VICODEC_VERSION ||
+	    cf.width < VICODEC_MIN_WIDTH ||
+	    cf.width > VICODEC_MAX_WIDTH ||
+	    cf.height < VICODEC_MIN_HEIGHT ||
+	    cf.height > VICODEC_MAX_HEIGHT ||
+	    (cf.width & 7) || (cf.height & 7))
+		return -EINVAL;
+
+	/* TODO: support resolution changes */
+	if (cf.width != q_data->width || cf.height != q_data->height)
+		return -EINVAL;
+
+	decode_frame(&cf, &ctx->ref_frame, q_data->flags);
+	memcpy(p_out, ctx->ref_frame.luma, size);
+	p_out += size;
+
+	switch (q_data->fourcc) {
+	case V4L2_PIX_FMT_YUV420:
+		memcpy(p_out, ctx->ref_frame.cb, size / 4);
+		p_out += size / 4;
+		memcpy(p_out, ctx->ref_frame.cr, size / 4);
+		break;
+	case V4L2_PIX_FMT_YVU420:
+		memcpy(p_out, ctx->ref_frame.cr, size / 4);
+		p_out += size / 4;
+		memcpy(p_out, ctx->ref_frame.cb, size / 4);
+		break;
+	case V4L2_PIX_FMT_NV12:
+		for (i = 0, p = p_out; i < size / 4; i++, p += 2)
+			*p = ctx->ref_frame.cb[i];
+		for (i = 0, p = p_out + 1; i < size / 4; i++, p += 2)
+			*p = ctx->ref_frame.cr[i];
+		break;
+	case V4L2_PIX_FMT_NV21:
+		for (i = 0, p = p_out; i < size / 4; i++, p += 2)
+			*p = ctx->ref_frame.cr[i];
+		for (i = 0, p = p_out + 1; i < size / 4; i++, p += 2)
+			*p = ctx->ref_frame.cb[i];
+		break;
+	}
+	return 0;
+}
+
+static int device_process(struct vicodec_ctx *ctx,
+			  struct vb2_v4l2_buffer *in_vb,
+			  struct vb2_v4l2_buffer *out_vb)
+{
+	struct vicodec_dev *dev = ctx->dev;
+	struct vicodec_q_data *q_out, *q_cap;
+	u8 *p_in, *p_out;
+	int ret;
+
+	q_out = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
+	q_cap = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
+	if (ctx->is_enc)
+		p_in = vb2_plane_vaddr(&in_vb->vb2_buf, 0);
+	else
+		p_in = ctx->compressed_frame;
+	p_out = vb2_plane_vaddr(&out_vb->vb2_buf, 0);
+	if (!p_in || !p_out) {
+		v4l2_err(&dev->v4l2_dev,
+			 "Acquiring kernel pointers to buffers failed\n");
+		return -EFAULT;
+	}
+
+	if (ctx->is_enc) {
+		struct cframe_hdr *p_hdr = (struct cframe_hdr *)p_out;
+
+		encode(ctx, q_out, p_in, p_out);
+		vb2_set_plane_payload(&out_vb->vb2_buf, 0,
+				      sizeof(*p_hdr) + ntohl(p_hdr->size));
+	} else {
+		ret = decode(ctx, q_cap, p_in, p_out);
+		if (ret)
+			return ret;
+		vb2_set_plane_payload(&out_vb->vb2_buf, 0,
+				      q_cap->width * q_cap->height * 3 / 2);
+	}
+
+	out_vb->sequence = q_cap->sequence++;
+	out_vb->vb2_buf.timestamp = in_vb->vb2_buf.timestamp;
+
+	if (in_vb->flags & V4L2_BUF_FLAG_TIMECODE)
+		out_vb->timecode = in_vb->timecode;
+	out_vb->field = in_vb->field;
+	out_vb->flags &= ~V4L2_BUF_FLAG_LAST;
+	out_vb->flags |= in_vb->flags &
+		(V4L2_BUF_FLAG_TIMECODE |
+		 V4L2_BUF_FLAG_KEYFRAME |
+		 V4L2_BUF_FLAG_PFRAME |
+		 V4L2_BUF_FLAG_BFRAME |
+		 V4L2_BUF_FLAG_TSTAMP_SRC_MASK);
+
+	return 0;
+}
+
+/*
+ * mem2mem callbacks
+ */
+
+/* device_run() - prepares and starts the device */
+static void device_run(void *priv)
+{
+	static const struct v4l2_event eos_event = {
+		.type = V4L2_EVENT_EOS
+	};
+	struct vicodec_ctx *ctx = priv;
+	struct vicodec_dev *dev = ctx->dev;
+	struct vb2_v4l2_buffer *src_buf, *dst_buf;
+	struct vicodec_q_data *q_out;
+	u32 state;
+
+	src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
+	dst_buf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
+	q_out = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
+
+	state = VB2_BUF_STATE_DONE;
+	if (device_process(ctx, src_buf, dst_buf))
+		state = VB2_BUF_STATE_ERROR;
+	ctx->last_dst_buf = dst_buf;
+
+	spin_lock(ctx->lock);
+	if (!ctx->comp_has_next_frame && src_buf == ctx->last_src_buf) {
+		dst_buf->flags |= V4L2_BUF_FLAG_LAST;
+		v4l2_event_queue_fh(&ctx->fh, &eos_event);
+	}
+	if (ctx->is_enc) {
+		src_buf->sequence = q_out->sequence++;
+		src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
+		v4l2_m2m_buf_done(src_buf, state);
+	} else if (vb2_get_plane_payload(&src_buf->vb2_buf, 0) == ctx->cur_buf_offset) {
+		src_buf->sequence = q_out->sequence++;
+		src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
+		v4l2_m2m_buf_done(src_buf, state);
+		ctx->cur_buf_offset = 0;
+		ctx->comp_has_next_frame = false;
+	}
+	v4l2_m2m_buf_done(dst_buf, state);
+	ctx->comp_size = 0;
+	ctx->comp_magic_cnt = 0;
+	ctx->comp_has_frame = false;
+	spin_unlock(ctx->lock);
+
+	if (ctx->is_enc)
+		v4l2_m2m_job_finish(dev->enc_dev, ctx->fh.m2m_ctx);
+	else
+		v4l2_m2m_job_finish(dev->dec_dev, ctx->fh.m2m_ctx);
+}
+
+static void job_remove_out_buf(struct vicodec_ctx *ctx, u32 state)
+{
+	struct vb2_v4l2_buffer *src_buf;
+	struct vicodec_q_data *q_out;
+
+	q_out = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
+	spin_lock(ctx->lock);
+	src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
+	src_buf->sequence = q_out->sequence++;
+	v4l2_m2m_buf_done(src_buf, state);
+	ctx->cur_buf_offset = 0;
+	spin_unlock(ctx->lock);
+}
+
+static int job_ready(void *priv)
+{
+	static const u8 magic[] = {
+		0x4f, 0x4f, 0x4f, 0x4f, 0xff, 0xff, 0xff, 0xff
+	};
+	struct vicodec_ctx *ctx = priv;
+	struct vb2_v4l2_buffer *src_buf;
+	u8 *p_out;
+	u8 *p;
+	u32 sz;
+	u32 state;
+
+	if (ctx->is_enc || ctx->comp_has_frame)
+		return 1;
+
+restart:
+	ctx->comp_has_next_frame = false;
+	src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
+	if (!src_buf)
+		return 0;
+	p_out = vb2_plane_vaddr(&src_buf->vb2_buf, 0);
+	sz = vb2_get_plane_payload(&src_buf->vb2_buf, 0);
+	p = p_out + ctx->cur_buf_offset;
+
+	state = VB2_BUF_STATE_DONE;
+
+	if (!ctx->comp_size) {
+		state = VB2_BUF_STATE_ERROR;
+		for (; p < p_out + sz; p++) {
+			u32 copy;
+
+			p = memchr(p, magic[ctx->comp_magic_cnt], sz);
+			if (!p) {
+				ctx->comp_magic_cnt = 0;
+				break;
+			}
+			copy = sizeof(magic) - ctx->comp_magic_cnt;
+			if (p_out + sz - p < copy)
+				copy = p_out + sz - p;
+			memcpy(ctx->compressed_frame + ctx->comp_magic_cnt,
+			       p, copy);
+			ctx->comp_magic_cnt += copy;
+			if (!memcmp(ctx->compressed_frame, magic, ctx->comp_magic_cnt)) {
+				p += copy;
+				state = VB2_BUF_STATE_DONE;
+				break;
+			}
+			ctx->comp_magic_cnt = 0;
+		}
+		if (ctx->comp_magic_cnt < sizeof(magic)) {
+			job_remove_out_buf(ctx, state);
+			goto restart;
+		}
+		ctx->comp_size = sizeof(magic);
+	}
+	if (ctx->comp_size < sizeof(struct cframe_hdr)) {
+		struct cframe_hdr *p_hdr = (struct cframe_hdr *)ctx->compressed_frame;
+		u32 copy = sizeof(struct cframe_hdr) - ctx->comp_size;
+
+		if (copy > p_out + sz - p)
+			copy = p_out + sz - p;
+		memcpy(ctx->compressed_frame + ctx->comp_size,
+		       p, copy);
+		p += copy;
+		ctx->comp_size += copy;
+		if (ctx->comp_size < sizeof(struct cframe_hdr)) {
+			job_remove_out_buf(ctx, state);
+			goto restart;
+		}
+		ctx->comp_frame_size = ntohl(p_hdr->size) + sizeof(*p_hdr);
+		if (ctx->comp_frame_size > ctx->comp_max_size)
+			ctx->comp_frame_size = ctx->comp_max_size;
+	}
+	if (ctx->comp_size < ctx->comp_frame_size) {
+		u32 copy = ctx->comp_frame_size - ctx->comp_size;
+
+		if (copy > p_out + sz - p)
+			copy = p_out + sz - p;
+		memcpy(ctx->compressed_frame + ctx->comp_size,
+		       p, copy);
+		p += copy;
+		ctx->comp_size += copy;
+		if (ctx->comp_size < ctx->comp_frame_size) {
+			job_remove_out_buf(ctx, state);
+			goto restart;
+		}
+	}
+	ctx->cur_buf_offset = p - p_out;
+	ctx->comp_has_frame = true;
+	ctx->comp_has_next_frame = false;
+	if (sz - ctx->cur_buf_offset >= sizeof(struct cframe_hdr)) {
+		struct cframe_hdr *p_hdr = (struct cframe_hdr *)p;
+		u32 frame_size = ntohl(p_hdr->size);
+		u32 remaining = sz - ctx->cur_buf_offset - sizeof(*p_hdr);
+
+		if (!memcmp(p, magic, sizeof(magic)))
+			ctx->comp_has_next_frame = remaining >= frame_size;
+	}
+	return 1;
+}
+
+static void job_abort(void *priv)
+{
+	struct vicodec_ctx *ctx = priv;
+
+	/* Will cancel the transaction in the next interrupt handler */
+	ctx->aborting = 1;
+}
+
+/*
+ * video ioctls
+ */
+
+static u32 find_fmt(u32 fmt)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(pixfmts_yuv); i++)
+		if (pixfmts_yuv[i] == fmt)
+			return fmt;
+	return pixfmts_yuv[0];
+}
+
+static int vidioc_querycap(struct file *file, void *priv,
+			   struct v4l2_capability *cap)
+{
+	strncpy(cap->driver, VICODEC_NAME, sizeof(cap->driver) - 1);
+	strncpy(cap->card, VICODEC_NAME, sizeof(cap->card) - 1);
+	snprintf(cap->bus_info, sizeof(cap->bus_info),
+			"platform:%s", VICODEC_NAME);
+	cap->device_caps =  V4L2_CAP_STREAMING |
+			    (multiplanar ?
+			     V4L2_CAP_VIDEO_M2M_MPLANE :
+			     V4L2_CAP_VIDEO_M2M);
+	cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS;
+	return 0;
+}
+
+static int enum_fmt(struct v4l2_fmtdesc *f, bool is_enc, bool is_out)
+{
+	bool is_yuv = (is_enc && is_out) || (!is_enc && !is_out);
+
+	if (V4L2_TYPE_IS_MULTIPLANAR(f->type) && !multiplanar)
+		return -EINVAL;
+	if (!V4L2_TYPE_IS_MULTIPLANAR(f->type) && multiplanar)
+		return -EINVAL;
+	if (f->index >= (is_yuv ? ARRAY_SIZE(pixfmts_yuv) : 1))
+		return -EINVAL;
+
+	if (is_yuv)
+		f->pixelformat = pixfmts_yuv[f->index];
+	else
+		f->pixelformat = V4L2_PIX_FMT_FWHT;
+	return 0;
+}
+
+static int vidioc_enum_fmt_vid_cap(struct file *file, void *priv,
+				   struct v4l2_fmtdesc *f)
+{
+	struct vicodec_ctx *ctx = file2ctx(file);
+
+	return enum_fmt(f, ctx->is_enc, false);
+}
+
+static int vidioc_enum_fmt_vid_out(struct file *file, void *priv,
+				   struct v4l2_fmtdesc *f)
+{
+	struct vicodec_ctx *ctx = file2ctx(file);
+
+	return enum_fmt(f, ctx->is_enc, true);
+}
+
+static int vidioc_g_fmt(struct vicodec_ctx *ctx, struct v4l2_format *f)
+{
+	struct vb2_queue *vq;
+	struct vicodec_q_data *q_data;
+	struct v4l2_pix_format_mplane *pix_mp;
+	struct v4l2_pix_format *pix;
+
+	vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type);
+	if (!vq)
+		return -EINVAL;
+
+	q_data = get_q_data(ctx, f->type);
+
+	switch (f->type) {
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
+		if (multiplanar)
+			return -EINVAL;
+		pix = &f->fmt.pix;
+		pix->width = q_data->width;
+		pix->height = q_data->height;
+		pix->field = V4L2_FIELD_NONE;
+		pix->pixelformat = q_data->fourcc;
+		if (q_data->fourcc == V4L2_PIX_FMT_FWHT)
+			pix->bytesperline = 0;
+		else
+			pix->bytesperline = q_data->width;
+		pix->sizeimage = q_data->sizeimage;
+		pix->colorspace = ctx->colorspace;
+		pix->xfer_func = ctx->xfer_func;
+		pix->ycbcr_enc = ctx->ycbcr_enc;
+		pix->quantization = ctx->quantization;
+		break;
+
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
+		if (!multiplanar)
+			return -EINVAL;
+		pix_mp = &f->fmt.pix_mp;
+		pix_mp->width = q_data->width;
+		pix_mp->height = q_data->height;
+		pix_mp->field = V4L2_FIELD_NONE;
+		pix_mp->pixelformat = q_data->fourcc;
+		pix_mp->num_planes = 1;
+		if (q_data->fourcc == V4L2_PIX_FMT_FWHT)
+			pix_mp->plane_fmt[0].bytesperline = 0;
+		else
+			pix_mp->plane_fmt[0].bytesperline = q_data->width;
+		pix_mp->plane_fmt[0].sizeimage = q_data->sizeimage;
+		pix_mp->colorspace = ctx->colorspace;
+		pix_mp->xfer_func = ctx->xfer_func;
+		pix_mp->ycbcr_enc = ctx->ycbcr_enc;
+		pix_mp->quantization = ctx->quantization;
+		memset(pix_mp->reserved, 0, sizeof(pix_mp->reserved));
+		memset(pix_mp->plane_fmt[0].reserved, 0,
+		       sizeof(pix_mp->plane_fmt[0].reserved));
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int vidioc_g_fmt_vid_out(struct file *file, void *priv,
+				struct v4l2_format *f)
+{
+	return vidioc_g_fmt(file2ctx(file), f);
+}
+
+static int vidioc_g_fmt_vid_cap(struct file *file, void *priv,
+				struct v4l2_format *f)
+{
+	return vidioc_g_fmt(file2ctx(file), f);
+}
+
+static int vidioc_try_fmt(struct vicodec_ctx *ctx, struct v4l2_format *f)
+{
+	struct v4l2_pix_format_mplane *pix_mp;
+	struct v4l2_pix_format *pix;
+
+	switch (f->type) {
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
+		pix = &f->fmt.pix;
+		pix->width = clamp(pix->width, MIN_WIDTH, MAX_WIDTH) & ~7;
+		pix->height = clamp(pix->height, MIN_HEIGHT, MAX_HEIGHT) & ~7;
+		pix->bytesperline = pix->width;
+		pix->sizeimage = pix->width * pix->height * 3 / 2;
+		pix->field = V4L2_FIELD_NONE;
+		if (pix->pixelformat == V4L2_PIX_FMT_FWHT) {
+			pix->bytesperline = 0;
+			pix->sizeimage += sizeof(struct cframe_hdr);
+		}
+		break;
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
+		pix_mp = &f->fmt.pix_mp;
+		pix_mp->width = clamp(pix_mp->width, MIN_WIDTH, MAX_WIDTH) & ~7;
+		pix_mp->height =
+			clamp(pix_mp->height, MIN_HEIGHT, MAX_HEIGHT) & ~7;
+		pix_mp->plane_fmt[0].bytesperline = pix_mp->width;
+		pix_mp->plane_fmt[0].sizeimage =
+			pix_mp->width * pix_mp->height * 3 / 2;
+		pix_mp->field = V4L2_FIELD_NONE;
+		pix_mp->num_planes = 1;
+		if (pix_mp->pixelformat == V4L2_PIX_FMT_FWHT) {
+			pix_mp->plane_fmt[0].bytesperline = 0;
+			pix_mp->plane_fmt[0].sizeimage +=
+					sizeof(struct cframe_hdr);
+		}
+		memset(pix_mp->reserved, 0, sizeof(pix_mp->reserved));
+		memset(pix_mp->plane_fmt[0].reserved, 0,
+		       sizeof(pix_mp->plane_fmt[0].reserved));
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int vidioc_try_fmt_vid_cap(struct file *file, void *priv,
+				  struct v4l2_format *f)
+{
+	struct vicodec_ctx *ctx = file2ctx(file);
+	struct v4l2_pix_format_mplane *pix_mp;
+	struct v4l2_pix_format *pix;
+
+	switch (f->type) {
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
+		if (multiplanar)
+			return -EINVAL;
+		pix = &f->fmt.pix;
+		pix->pixelformat = ctx->is_enc ? V4L2_PIX_FMT_FWHT :
+				   find_fmt(f->fmt.pix.pixelformat);
+		pix->colorspace = ctx->colorspace;
+		pix->xfer_func = ctx->xfer_func;
+		pix->ycbcr_enc = ctx->ycbcr_enc;
+		pix->quantization = ctx->quantization;
+		break;
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
+		if (!multiplanar)
+			return -EINVAL;
+		pix_mp = &f->fmt.pix_mp;
+		pix_mp->pixelformat = ctx->is_enc ? V4L2_PIX_FMT_FWHT :
+				      find_fmt(pix_mp->pixelformat);
+		pix_mp->colorspace = ctx->colorspace;
+		pix_mp->xfer_func = ctx->xfer_func;
+		pix_mp->ycbcr_enc = ctx->ycbcr_enc;
+		pix_mp->quantization = ctx->quantization;
+		memset(pix_mp->reserved, 0, sizeof(pix_mp->reserved));
+		memset(pix_mp->plane_fmt[0].reserved, 0,
+		       sizeof(pix_mp->plane_fmt[0].reserved));
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return vidioc_try_fmt(ctx, f);
+}
+
+static int vidioc_try_fmt_vid_out(struct file *file, void *priv,
+				  struct v4l2_format *f)
+{
+	struct vicodec_ctx *ctx = file2ctx(file);
+	struct v4l2_pix_format_mplane *pix_mp;
+	struct v4l2_pix_format *pix;
+
+	switch (f->type) {
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
+		if (multiplanar)
+			return -EINVAL;
+		pix = &f->fmt.pix;
+		pix->pixelformat = !ctx->is_enc ? V4L2_PIX_FMT_FWHT :
+				   find_fmt(pix->pixelformat);
+		if (!pix->colorspace)
+			pix->colorspace = V4L2_COLORSPACE_REC709;
+		break;
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
+		if (!multiplanar)
+			return -EINVAL;
+		pix_mp = &f->fmt.pix_mp;
+		pix_mp->pixelformat = !ctx->is_enc ? V4L2_PIX_FMT_FWHT :
+				      find_fmt(pix_mp->pixelformat);
+		if (!pix_mp->colorspace)
+			pix_mp->colorspace = V4L2_COLORSPACE_REC709;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return vidioc_try_fmt(ctx, f);
+}
+
+static int vidioc_s_fmt(struct vicodec_ctx *ctx, struct v4l2_format *f)
+{
+	struct vicodec_q_data *q_data;
+	struct vb2_queue *vq;
+	bool fmt_changed = true;
+	struct v4l2_pix_format_mplane *pix_mp;
+	struct v4l2_pix_format *pix;
+
+	vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type);
+	if (!vq)
+		return -EINVAL;
+
+	q_data = get_q_data(ctx, f->type);
+	if (!q_data)
+		return -EINVAL;
+
+	switch (f->type) {
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
+		pix = &f->fmt.pix;
+		if (ctx->is_enc && V4L2_TYPE_IS_OUTPUT(f->type))
+			fmt_changed =
+				q_data->fourcc != pix->pixelformat ||
+				q_data->width != pix->width ||
+				q_data->height != pix->height;
+
+		if (vb2_is_busy(vq) && fmt_changed)
+			return -EBUSY;
+
+		q_data->fourcc = pix->pixelformat;
+		q_data->width = pix->width;
+		q_data->height = pix->height;
+		q_data->sizeimage = pix->sizeimage;
+		break;
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
+		pix_mp = &f->fmt.pix_mp;
+		if (ctx->is_enc && V4L2_TYPE_IS_OUTPUT(f->type))
+			fmt_changed =
+				q_data->fourcc != pix_mp->pixelformat ||
+				q_data->width != pix_mp->width ||
+				q_data->height != pix_mp->height;
+
+		if (vb2_is_busy(vq) && fmt_changed)
+			return -EBUSY;
+
+		q_data->fourcc = pix_mp->pixelformat;
+		q_data->width = pix_mp->width;
+		q_data->height = pix_mp->height;
+		q_data->sizeimage = pix_mp->plane_fmt[0].sizeimage;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	dprintk(ctx->dev,
+		"Setting format for type %d, wxh: %dx%d, fourcc: %08x\n",
+		f->type, q_data->width, q_data->height, q_data->fourcc);
+
+	return 0;
+}
+
+static int vidioc_s_fmt_vid_cap(struct file *file, void *priv,
+				struct v4l2_format *f)
+{
+	int ret;
+
+	ret = vidioc_try_fmt_vid_cap(file, priv, f);
+	if (ret)
+		return ret;
+
+	return vidioc_s_fmt(file2ctx(file), f);
+}
+
+static int vidioc_s_fmt_vid_out(struct file *file, void *priv,
+				struct v4l2_format *f)
+{
+	struct vicodec_ctx *ctx = file2ctx(file);
+	struct v4l2_pix_format_mplane *pix_mp;
+	struct v4l2_pix_format *pix;
+	int ret;
+
+	ret = vidioc_try_fmt_vid_out(file, priv, f);
+	if (ret)
+		return ret;
+
+	ret = vidioc_s_fmt(file2ctx(file), f);
+	if (!ret) {
+		switch (f->type) {
+		case V4L2_BUF_TYPE_VIDEO_CAPTURE:
+		case V4L2_BUF_TYPE_VIDEO_OUTPUT:
+			pix = &f->fmt.pix;
+			ctx->colorspace = pix->colorspace;
+			ctx->xfer_func = pix->xfer_func;
+			ctx->ycbcr_enc = pix->ycbcr_enc;
+			ctx->quantization = pix->quantization;
+			break;
+		case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
+		case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
+			pix_mp = &f->fmt.pix_mp;
+			ctx->colorspace = pix_mp->colorspace;
+			ctx->xfer_func = pix_mp->xfer_func;
+			ctx->ycbcr_enc = pix_mp->ycbcr_enc;
+			ctx->quantization = pix_mp->quantization;
+			break;
+		default:
+			break;
+		}
+	}
+	return ret;
+}
+
+static void vicodec_mark_last_buf(struct vicodec_ctx *ctx)
+{
+	static const struct v4l2_event eos_event = {
+		.type = V4L2_EVENT_EOS
+	};
+
+	spin_lock(ctx->lock);
+	ctx->last_src_buf = v4l2_m2m_last_src_buf(ctx->fh.m2m_ctx);
+	if (!ctx->last_src_buf && ctx->last_dst_buf) {
+		ctx->last_dst_buf->flags |= V4L2_BUF_FLAG_LAST;
+		v4l2_event_queue_fh(&ctx->fh, &eos_event);
+	}
+	spin_unlock(ctx->lock);
+}
+
+static int vicodec_try_encoder_cmd(struct file *file, void *fh,
+				struct v4l2_encoder_cmd *ec)
+{
+	if (ec->cmd != V4L2_ENC_CMD_STOP)
+		return -EINVAL;
+
+	if (ec->flags & V4L2_ENC_CMD_STOP_AT_GOP_END)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int vicodec_encoder_cmd(struct file *file, void *fh,
+			    struct v4l2_encoder_cmd *ec)
+{
+	struct vicodec_ctx *ctx = file2ctx(file);
+	int ret;
+
+	ret = vicodec_try_encoder_cmd(file, fh, ec);
+	if (ret < 0)
+		return ret;
+
+	vicodec_mark_last_buf(ctx);
+	return 0;
+}
+
+static int vicodec_try_decoder_cmd(struct file *file, void *fh,
+				struct v4l2_decoder_cmd *dc)
+{
+	if (dc->cmd != V4L2_DEC_CMD_STOP)
+		return -EINVAL;
+
+	if (dc->flags & V4L2_DEC_CMD_STOP_TO_BLACK)
+		return -EINVAL;
+
+	if (!(dc->flags & V4L2_DEC_CMD_STOP_IMMEDIATELY) && (dc->stop.pts != 0))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int vicodec_decoder_cmd(struct file *file, void *fh,
+			    struct v4l2_decoder_cmd *dc)
+{
+	struct vicodec_ctx *ctx = file2ctx(file);
+	int ret;
+
+	ret = vicodec_try_decoder_cmd(file, fh, dc);
+	if (ret < 0)
+		return ret;
+
+	vicodec_mark_last_buf(ctx);
+	return 0;
+}
+
+static int vicodec_enum_framesizes(struct file *file, void *fh,
+				   struct v4l2_frmsizeenum *fsize)
+{
+	switch (fsize->pixel_format) {
+	case V4L2_PIX_FMT_FWHT:
+		break;
+	default:
+		if (find_fmt(fsize->pixel_format) == fsize->pixel_format)
+			break;
+		return -EINVAL;
+	}
+
+	if (fsize->index)
+		return -EINVAL;
+
+	fsize->type = V4L2_FRMSIZE_TYPE_STEPWISE;
+
+	fsize->stepwise.min_width = MIN_WIDTH;
+	fsize->stepwise.max_width = MAX_WIDTH;
+	fsize->stepwise.step_width = 8;
+	fsize->stepwise.min_height = MIN_HEIGHT;
+	fsize->stepwise.max_height = MAX_HEIGHT;
+	fsize->stepwise.step_height = 8;
+
+	return 0;
+}
+
+static int vicodec_subscribe_event(struct v4l2_fh *fh,
+				const struct v4l2_event_subscription *sub)
+{
+	switch (sub->type) {
+	case V4L2_EVENT_EOS:
+		return v4l2_event_subscribe(fh, sub, 0, NULL);
+	default:
+		return v4l2_ctrl_subscribe_event(fh, sub);
+	}
+}
+
+static const struct v4l2_ioctl_ops vicodec_ioctl_ops = {
+	.vidioc_querycap	= vidioc_querycap,
+
+	.vidioc_enum_fmt_vid_cap = vidioc_enum_fmt_vid_cap,
+	.vidioc_g_fmt_vid_cap	= vidioc_g_fmt_vid_cap,
+	.vidioc_try_fmt_vid_cap	= vidioc_try_fmt_vid_cap,
+	.vidioc_s_fmt_vid_cap	= vidioc_s_fmt_vid_cap,
+
+	.vidioc_enum_fmt_vid_cap_mplane = vidioc_enum_fmt_vid_cap,
+	.vidioc_g_fmt_vid_cap_mplane	= vidioc_g_fmt_vid_cap,
+	.vidioc_try_fmt_vid_cap_mplane	= vidioc_try_fmt_vid_cap,
+	.vidioc_s_fmt_vid_cap_mplane	= vidioc_s_fmt_vid_cap,
+
+	.vidioc_enum_fmt_vid_out = vidioc_enum_fmt_vid_out,
+	.vidioc_g_fmt_vid_out	= vidioc_g_fmt_vid_out,
+	.vidioc_try_fmt_vid_out	= vidioc_try_fmt_vid_out,
+	.vidioc_s_fmt_vid_out	= vidioc_s_fmt_vid_out,
+
+	.vidioc_enum_fmt_vid_out_mplane = vidioc_enum_fmt_vid_out,
+	.vidioc_g_fmt_vid_out_mplane	= vidioc_g_fmt_vid_out,
+	.vidioc_try_fmt_vid_out_mplane	= vidioc_try_fmt_vid_out,
+	.vidioc_s_fmt_vid_out_mplane	= vidioc_s_fmt_vid_out,
+
+	.vidioc_reqbufs		= v4l2_m2m_ioctl_reqbufs,
+	.vidioc_querybuf	= v4l2_m2m_ioctl_querybuf,
+	.vidioc_qbuf		= v4l2_m2m_ioctl_qbuf,
+	.vidioc_dqbuf		= v4l2_m2m_ioctl_dqbuf,
+	.vidioc_prepare_buf	= v4l2_m2m_ioctl_prepare_buf,
+	.vidioc_create_bufs	= v4l2_m2m_ioctl_create_bufs,
+	.vidioc_expbuf		= v4l2_m2m_ioctl_expbuf,
+
+	.vidioc_streamon	= v4l2_m2m_ioctl_streamon,
+	.vidioc_streamoff	= v4l2_m2m_ioctl_streamoff,
+
+	.vidioc_try_encoder_cmd	= vicodec_try_encoder_cmd,
+	.vidioc_encoder_cmd	= vicodec_encoder_cmd,
+	.vidioc_try_decoder_cmd	= vicodec_try_decoder_cmd,
+	.vidioc_decoder_cmd	= vicodec_decoder_cmd,
+	.vidioc_enum_framesizes = vicodec_enum_framesizes,
+
+	.vidioc_subscribe_event = vicodec_subscribe_event,
+	.vidioc_unsubscribe_event = v4l2_event_unsubscribe,
+};
+
+
+/*
+ * Queue operations
+ */
+
+static int vicodec_queue_setup(struct vb2_queue *vq, unsigned int *nbuffers,
+			       unsigned int *nplanes, unsigned int sizes[],
+			       struct device *alloc_devs[])
+{
+	struct vicodec_ctx *ctx = vb2_get_drv_priv(vq);
+	struct vicodec_q_data *q_data = get_q_data(ctx, vq->type);
+	unsigned int size = q_data->sizeimage;
+
+	if (*nplanes)
+		return sizes[0] < size ? -EINVAL : 0;
+
+	*nplanes = 1;
+	sizes[0] = size;
+	return 0;
+}
+
+static int vicodec_buf_prepare(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct vicodec_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+	struct vicodec_q_data *q_data;
+
+	dprintk(ctx->dev, "type: %d\n", vb->vb2_queue->type);
+
+	q_data = get_q_data(ctx, vb->vb2_queue->type);
+	if (V4L2_TYPE_IS_OUTPUT(vb->vb2_queue->type)) {
+		if (vbuf->field == V4L2_FIELD_ANY)
+			vbuf->field = V4L2_FIELD_NONE;
+		if (vbuf->field != V4L2_FIELD_NONE) {
+			dprintk(ctx->dev, "%s field isn't supported\n",
+					__func__);
+			return -EINVAL;
+		}
+	}
+
+	if (vb2_plane_size(vb, 0) < q_data->sizeimage) {
+		dprintk(ctx->dev,
+			"%s data will not fit into plane (%lu < %lu)\n",
+			__func__, vb2_plane_size(vb, 0),
+			(long)q_data->sizeimage);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void vicodec_buf_queue(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct vicodec_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+
+	v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf);
+}
+
+static void vicodec_return_bufs(struct vb2_queue *q, u32 state)
+{
+	struct vicodec_ctx *ctx = vb2_get_drv_priv(q);
+	struct vb2_v4l2_buffer *vbuf;
+
+	for (;;) {
+		if (V4L2_TYPE_IS_OUTPUT(q->type))
+			vbuf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
+		else
+			vbuf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
+		if (vbuf == NULL)
+			return;
+		spin_lock(ctx->lock);
+		v4l2_m2m_buf_done(vbuf, state);
+		spin_unlock(ctx->lock);
+	}
+}
+
+static int vicodec_start_streaming(struct vb2_queue *q,
+				   unsigned int count)
+{
+	struct vicodec_ctx *ctx = vb2_get_drv_priv(q);
+	struct vicodec_q_data *q_data = get_q_data(ctx, q->type);
+	unsigned int size = q_data->width * q_data->height;
+
+	q_data->sequence = 0;
+
+	if (!V4L2_TYPE_IS_OUTPUT(q->type))
+		return 0;
+
+	ctx->ref_frame.width = ctx->ref_frame.height = 0;
+	ctx->ref_frame.luma = kvmalloc(size * 3 / 2, GFP_KERNEL);
+	ctx->comp_max_size = size * 3 / 2 + sizeof(struct cframe_hdr);
+	ctx->compressed_frame = kvmalloc(ctx->comp_max_size, GFP_KERNEL);
+	if (!ctx->ref_frame.luma || !ctx->compressed_frame) {
+		kvfree(ctx->ref_frame.luma);
+		kvfree(ctx->compressed_frame);
+		vicodec_return_bufs(q, VB2_BUF_STATE_QUEUED);
+		return -ENOMEM;
+	}
+	ctx->ref_frame.cb = ctx->ref_frame.luma + size;
+	ctx->ref_frame.cr = ctx->ref_frame.cb + size / 4;
+	ctx->last_src_buf = NULL;
+	ctx->last_dst_buf = NULL;
+	v4l2_ctrl_grab(ctx->ctrl_gop_size, true);
+	ctx->gop_size = v4l2_ctrl_g_ctrl(ctx->ctrl_gop_size);
+	ctx->gop_cnt = 0;
+	ctx->cur_buf_offset = 0;
+	ctx->comp_size = 0;
+	ctx->comp_magic_cnt = 0;
+	ctx->comp_has_frame = false;
+
+	return 0;
+}
+
+static void vicodec_stop_streaming(struct vb2_queue *q)
+{
+	struct vicodec_ctx *ctx = vb2_get_drv_priv(q);
+
+	vicodec_return_bufs(q, VB2_BUF_STATE_ERROR);
+
+	if (!V4L2_TYPE_IS_OUTPUT(q->type))
+		return;
+
+	kvfree(ctx->ref_frame.luma);
+	kvfree(ctx->compressed_frame);
+	v4l2_ctrl_grab(ctx->ctrl_gop_size, false);
+}
+
+static const struct vb2_ops vicodec_qops = {
+	.queue_setup	 = vicodec_queue_setup,
+	.buf_prepare	 = vicodec_buf_prepare,
+	.buf_queue	 = vicodec_buf_queue,
+	.start_streaming = vicodec_start_streaming,
+	.stop_streaming  = vicodec_stop_streaming,
+	.wait_prepare	 = vb2_ops_wait_prepare,
+	.wait_finish	 = vb2_ops_wait_finish,
+};
+
+static int queue_init(void *priv, struct vb2_queue *src_vq,
+		      struct vb2_queue *dst_vq)
+{
+	struct vicodec_ctx *ctx = priv;
+	int ret;
+
+	src_vq->type = (multiplanar ?
+			V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE :
+			V4L2_BUF_TYPE_VIDEO_OUTPUT);
+	src_vq->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF;
+	src_vq->drv_priv = ctx;
+	src_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
+	src_vq->ops = &vicodec_qops;
+	src_vq->mem_ops = &vb2_vmalloc_memops;
+	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+	src_vq->lock = ctx->is_enc ? &ctx->dev->enc_mutex :
+		&ctx->dev->dec_mutex;
+
+	ret = vb2_queue_init(src_vq);
+	if (ret)
+		return ret;
+
+	dst_vq->type = (multiplanar ?
+			V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE :
+			V4L2_BUF_TYPE_VIDEO_CAPTURE);
+	dst_vq->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF;
+	dst_vq->drv_priv = ctx;
+	dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
+	dst_vq->ops = &vicodec_qops;
+	dst_vq->mem_ops = &vb2_vmalloc_memops;
+	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+	dst_vq->lock = src_vq->lock;
+
+	return vb2_queue_init(dst_vq);
+}
+
+/*
+ * File operations
+ */
+static int vicodec_open(struct file *file)
+{
+	struct video_device *vfd = video_devdata(file);
+	struct vicodec_dev *dev = video_drvdata(file);
+	struct vicodec_ctx *ctx = NULL;
+	struct v4l2_ctrl_handler *hdl;
+	unsigned int size;
+	int rc = 0;
+
+	if (mutex_lock_interruptible(vfd->lock))
+		return -ERESTARTSYS;
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx) {
+		rc = -ENOMEM;
+		goto open_unlock;
+	}
+
+	if (vfd == &dev->enc_vfd)
+		ctx->is_enc = true;
+
+	v4l2_fh_init(&ctx->fh, video_devdata(file));
+	file->private_data = &ctx->fh;
+	ctx->dev = dev;
+	hdl = &ctx->hdl;
+	v4l2_ctrl_handler_init(hdl, 4);
+	ctx->ctrl_gop_size = v4l2_ctrl_new_std(hdl, NULL,
+					       V4L2_CID_MPEG_VIDEO_GOP_SIZE,
+					       1, 16, 1, 10);
+	if (hdl->error) {
+		rc = hdl->error;
+		v4l2_ctrl_handler_free(hdl);
+		kfree(ctx);
+		goto open_unlock;
+	}
+	ctx->fh.ctrl_handler = hdl;
+	v4l2_ctrl_handler_setup(hdl);
+
+	ctx->q_data[V4L2_M2M_SRC].fourcc =
+		ctx->is_enc ? V4L2_PIX_FMT_YUV420 : V4L2_PIX_FMT_FWHT;
+	ctx->q_data[V4L2_M2M_SRC].width = 1280;
+	ctx->q_data[V4L2_M2M_SRC].height = 720;
+	size = 1280 * 720 * 3 / 2;
+	ctx->q_data[V4L2_M2M_SRC].sizeimage = size;
+	ctx->q_data[V4L2_M2M_DST] = ctx->q_data[V4L2_M2M_SRC];
+	ctx->q_data[V4L2_M2M_DST].fourcc =
+		ctx->is_enc ? V4L2_PIX_FMT_FWHT : V4L2_PIX_FMT_YUV420;
+	ctx->colorspace = V4L2_COLORSPACE_REC709;
+
+	size += sizeof(struct cframe_hdr);
+	if (ctx->is_enc) {
+		ctx->q_data[V4L2_M2M_DST].sizeimage = size;
+		ctx->fh.m2m_ctx = v4l2_m2m_ctx_init(dev->enc_dev, ctx,
+						    &queue_init);
+		ctx->lock = &dev->enc_lock;
+	} else {
+		ctx->q_data[V4L2_M2M_SRC].sizeimage = size;
+		ctx->fh.m2m_ctx = v4l2_m2m_ctx_init(dev->dec_dev, ctx,
+						    &queue_init);
+		ctx->lock = &dev->dec_lock;
+	}
+
+	if (IS_ERR(ctx->fh.m2m_ctx)) {
+		rc = PTR_ERR(ctx->fh.m2m_ctx);
+
+		v4l2_ctrl_handler_free(hdl);
+		v4l2_fh_exit(&ctx->fh);
+		kfree(ctx);
+		goto open_unlock;
+	}
+
+	v4l2_fh_add(&ctx->fh);
+
+open_unlock:
+	mutex_unlock(vfd->lock);
+	return rc;
+}
+
+static int vicodec_release(struct file *file)
+{
+	struct video_device *vfd = video_devdata(file);
+	struct vicodec_ctx *ctx = file2ctx(file);
+
+	v4l2_fh_del(&ctx->fh);
+	v4l2_fh_exit(&ctx->fh);
+	v4l2_ctrl_handler_free(&ctx->hdl);
+	mutex_lock(vfd->lock);
+	v4l2_m2m_ctx_release(ctx->fh.m2m_ctx);
+	mutex_unlock(vfd->lock);
+	kfree(ctx);
+
+	return 0;
+}
+
+static const struct v4l2_file_operations vicodec_fops = {
+	.owner		= THIS_MODULE,
+	.open		= vicodec_open,
+	.release	= vicodec_release,
+	.poll		= v4l2_m2m_fop_poll,
+	.unlocked_ioctl	= video_ioctl2,
+	.mmap		= v4l2_m2m_fop_mmap,
+};
+
+static const struct video_device vicodec_videodev = {
+	.name		= VICODEC_NAME,
+	.vfl_dir	= VFL_DIR_M2M,
+	.fops		= &vicodec_fops,
+	.ioctl_ops	= &vicodec_ioctl_ops,
+	.minor		= -1,
+	.release	= video_device_release_empty,
+};
+
+static const struct v4l2_m2m_ops m2m_ops = {
+	.device_run	= device_run,
+	.job_abort	= job_abort,
+	.job_ready	= job_ready,
+};
+
+static int vicodec_probe(struct platform_device *pdev)
+{
+	struct vicodec_dev *dev;
+	struct video_device *vfd;
+	int ret;
+
+	dev = devm_kzalloc(&pdev->dev, sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	spin_lock_init(&dev->enc_lock);
+	spin_lock_init(&dev->dec_lock);
+
+	ret = v4l2_device_register(&pdev->dev, &dev->v4l2_dev);
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+	dev->mdev.dev = &pdev->dev;
+	strlcpy(dev->mdev.model, "vicodec", sizeof(dev->mdev.model));
+	media_device_init(&dev->mdev);
+	dev->v4l2_dev.mdev = &dev->mdev;
+#endif
+
+	mutex_init(&dev->enc_mutex);
+	mutex_init(&dev->dec_mutex);
+
+	platform_set_drvdata(pdev, dev);
+
+	dev->enc_dev = v4l2_m2m_init(&m2m_ops);
+	if (IS_ERR(dev->enc_dev)) {
+		v4l2_err(&dev->v4l2_dev, "Failed to init vicodec device\n");
+		ret = PTR_ERR(dev->enc_dev);
+		goto unreg_dev;
+	}
+
+	dev->dec_dev = v4l2_m2m_init(&m2m_ops);
+	if (IS_ERR(dev->dec_dev)) {
+		v4l2_err(&dev->v4l2_dev, "Failed to init vicodec device\n");
+		ret = PTR_ERR(dev->dec_dev);
+		goto err_enc_m2m;
+	}
+
+	dev->enc_vfd = vicodec_videodev;
+	vfd = &dev->enc_vfd;
+	vfd->lock = &dev->enc_mutex;
+	vfd->v4l2_dev = &dev->v4l2_dev;
+	strlcpy(vfd->name, "vicodec-enc", sizeof(vfd->name));
+	v4l2_disable_ioctl(vfd, VIDIOC_DECODER_CMD);
+	v4l2_disable_ioctl(vfd, VIDIOC_TRY_DECODER_CMD);
+	video_set_drvdata(vfd, dev);
+
+	ret = video_register_device(vfd, VFL_TYPE_GRABBER, 0);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev, "Failed to register video device\n");
+		goto err_dec_m2m;
+	}
+	v4l2_info(&dev->v4l2_dev,
+			"Device registered as /dev/video%d\n", vfd->num);
+
+	dev->dec_vfd = vicodec_videodev;
+	vfd = &dev->dec_vfd;
+	vfd->lock = &dev->dec_mutex;
+	vfd->v4l2_dev = &dev->v4l2_dev;
+	strlcpy(vfd->name, "vicodec-dec", sizeof(vfd->name));
+	v4l2_disable_ioctl(vfd, VIDIOC_ENCODER_CMD);
+	v4l2_disable_ioctl(vfd, VIDIOC_TRY_ENCODER_CMD);
+	video_set_drvdata(vfd, dev);
+
+	ret = video_register_device(vfd, VFL_TYPE_GRABBER, 0);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev, "Failed to register video device\n");
+		goto unreg_enc;
+	}
+	v4l2_info(&dev->v4l2_dev,
+			"Device registered as /dev/video%d\n", vfd->num);
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+	ret = v4l2_m2m_register_media_controller(dev->enc_dev,
+			&dev->enc_vfd, MEDIA_ENT_F_PROC_VIDEO_ENCODER);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev, "Failed to init mem2mem media controller\n");
+		goto unreg_m2m;
+	}
+
+	ret = v4l2_m2m_register_media_controller(dev->dec_dev,
+			&dev->dec_vfd, MEDIA_ENT_F_PROC_VIDEO_DECODER);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev, "Failed to init mem2mem media controller\n");
+		goto unreg_m2m_enc_mc;
+	}
+
+	ret = media_device_register(&dev->mdev);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev, "Failed to register mem2mem media device\n");
+		goto unreg_m2m_dec_mc;
+	}
+#endif
+	return 0;
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+unreg_m2m_dec_mc:
+	v4l2_m2m_unregister_media_controller(dev->dec_dev);
+unreg_m2m_enc_mc:
+	v4l2_m2m_unregister_media_controller(dev->enc_dev);
+unreg_m2m:
+	video_unregister_device(&dev->dec_vfd);
+#endif
+unreg_enc:
+	video_unregister_device(&dev->enc_vfd);
+err_dec_m2m:
+	v4l2_m2m_release(dev->dec_dev);
+err_enc_m2m:
+	v4l2_m2m_release(dev->enc_dev);
+unreg_dev:
+	v4l2_device_unregister(&dev->v4l2_dev);
+
+	return ret;
+}
+
+static int vicodec_remove(struct platform_device *pdev)
+{
+	struct vicodec_dev *dev = platform_get_drvdata(pdev);
+
+	v4l2_info(&dev->v4l2_dev, "Removing " VICODEC_NAME);
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+	media_device_unregister(&dev->mdev);
+	v4l2_m2m_unregister_media_controller(dev->enc_dev);
+	v4l2_m2m_unregister_media_controller(dev->dec_dev);
+	media_device_cleanup(&dev->mdev);
+#endif
+
+	v4l2_m2m_release(dev->enc_dev);
+	v4l2_m2m_release(dev->dec_dev);
+	video_unregister_device(&dev->enc_vfd);
+	video_unregister_device(&dev->dec_vfd);
+	v4l2_device_unregister(&dev->v4l2_dev);
+
+	return 0;
+}
+
+static struct platform_driver vicodec_pdrv = {
+	.probe		= vicodec_probe,
+	.remove		= vicodec_remove,
+	.driver		= {
+		.name	= VICODEC_NAME,
+	},
+};
+
+static void __exit vicodec_exit(void)
+{
+	platform_driver_unregister(&vicodec_pdrv);
+	platform_device_unregister(&vicodec_pdev);
+}
+
+static int __init vicodec_init(void)
+{
+	int ret;
+
+	ret = platform_device_register(&vicodec_pdev);
+	if (ret)
+		return ret;
+
+	ret = platform_driver_register(&vicodec_pdrv);
+	if (ret)
+		platform_device_unregister(&vicodec_pdev);
+
+	return ret;
+}
+
+module_init(vicodec_init);
+module_exit(vicodec_exit);
diff --git a/drivers/media/platform/video-mux.c b/drivers/media/platform/video-mux.c
index 1fb887293337..c01e1592ad0a 100644
--- a/drivers/media/platform/video-mux.c
+++ b/drivers/media/platform/video-mux.c
@@ -34,6 +34,13 @@ struct video_mux {
 	int active;
 };
 
+static const struct v4l2_mbus_framefmt video_mux_format_mbus_default = {
+	.width = 1,
+	.height = 1,
+	.code = MEDIA_BUS_FMT_Y8_1X8,
+	.field = V4L2_FIELD_NONE,
+};
+
 static inline struct video_mux *v4l2_subdev_to_video_mux(struct v4l2_subdev *sd)
 {
 	return container_of(sd, struct video_mux, subdev);
@@ -180,6 +187,88 @@ static int video_mux_set_format(struct v4l2_subdev *sd,
 	if (!source_mbusformat)
 		return -EINVAL;
 
+	/* No size limitations except V4L2 compliance requirements */
+	v4l_bound_align_image(&sdformat->format.width, 1, 65536, 0,
+			      &sdformat->format.height, 1, 65536, 0, 0);
+
+	/* All formats except LVDS and vendor specific formats are acceptable */
+	switch (sdformat->format.code) {
+	case MEDIA_BUS_FMT_RGB444_1X12:
+	case MEDIA_BUS_FMT_RGB444_2X8_PADHI_BE:
+	case MEDIA_BUS_FMT_RGB444_2X8_PADHI_LE:
+	case MEDIA_BUS_FMT_RGB555_2X8_PADHI_BE:
+	case MEDIA_BUS_FMT_RGB555_2X8_PADHI_LE:
+	case MEDIA_BUS_FMT_RGB565_1X16:
+	case MEDIA_BUS_FMT_BGR565_2X8_BE:
+	case MEDIA_BUS_FMT_BGR565_2X8_LE:
+	case MEDIA_BUS_FMT_RGB565_2X8_BE:
+	case MEDIA_BUS_FMT_RGB565_2X8_LE:
+	case MEDIA_BUS_FMT_RGB666_1X18:
+	case MEDIA_BUS_FMT_RBG888_1X24:
+	case MEDIA_BUS_FMT_RGB666_1X24_CPADHI:
+	case MEDIA_BUS_FMT_BGR888_1X24:
+	case MEDIA_BUS_FMT_GBR888_1X24:
+	case MEDIA_BUS_FMT_RGB888_1X24:
+	case MEDIA_BUS_FMT_RGB888_2X12_BE:
+	case MEDIA_BUS_FMT_RGB888_2X12_LE:
+	case MEDIA_BUS_FMT_ARGB8888_1X32:
+	case MEDIA_BUS_FMT_RGB888_1X32_PADHI:
+	case MEDIA_BUS_FMT_RGB101010_1X30:
+	case MEDIA_BUS_FMT_RGB121212_1X36:
+	case MEDIA_BUS_FMT_RGB161616_1X48:
+	case MEDIA_BUS_FMT_Y8_1X8:
+	case MEDIA_BUS_FMT_UV8_1X8:
+	case MEDIA_BUS_FMT_UYVY8_1_5X8:
+	case MEDIA_BUS_FMT_VYUY8_1_5X8:
+	case MEDIA_BUS_FMT_YUYV8_1_5X8:
+	case MEDIA_BUS_FMT_YVYU8_1_5X8:
+	case MEDIA_BUS_FMT_UYVY8_2X8:
+	case MEDIA_BUS_FMT_VYUY8_2X8:
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+	case MEDIA_BUS_FMT_YVYU8_2X8:
+	case MEDIA_BUS_FMT_Y10_1X10:
+	case MEDIA_BUS_FMT_UYVY10_2X10:
+	case MEDIA_BUS_FMT_VYUY10_2X10:
+	case MEDIA_BUS_FMT_YUYV10_2X10:
+	case MEDIA_BUS_FMT_YVYU10_2X10:
+	case MEDIA_BUS_FMT_Y12_1X12:
+	case MEDIA_BUS_FMT_UYVY12_2X12:
+	case MEDIA_BUS_FMT_VYUY12_2X12:
+	case MEDIA_BUS_FMT_YUYV12_2X12:
+	case MEDIA_BUS_FMT_YVYU12_2X12:
+	case MEDIA_BUS_FMT_UYVY8_1X16:
+	case MEDIA_BUS_FMT_VYUY8_1X16:
+	case MEDIA_BUS_FMT_YUYV8_1X16:
+	case MEDIA_BUS_FMT_YVYU8_1X16:
+	case MEDIA_BUS_FMT_YDYUYDYV8_1X16:
+	case MEDIA_BUS_FMT_UYVY10_1X20:
+	case MEDIA_BUS_FMT_VYUY10_1X20:
+	case MEDIA_BUS_FMT_YUYV10_1X20:
+	case MEDIA_BUS_FMT_YVYU10_1X20:
+	case MEDIA_BUS_FMT_VUY8_1X24:
+	case MEDIA_BUS_FMT_YUV8_1X24:
+	case MEDIA_BUS_FMT_UYYVYY8_0_5X24:
+	case MEDIA_BUS_FMT_UYVY12_1X24:
+	case MEDIA_BUS_FMT_VYUY12_1X24:
+	case MEDIA_BUS_FMT_YUYV12_1X24:
+	case MEDIA_BUS_FMT_YVYU12_1X24:
+	case MEDIA_BUS_FMT_YUV10_1X30:
+	case MEDIA_BUS_FMT_UYYVYY10_0_5X30:
+	case MEDIA_BUS_FMT_AYUV8_1X32:
+	case MEDIA_BUS_FMT_UYYVYY12_0_5X36:
+	case MEDIA_BUS_FMT_YUV12_1X36:
+	case MEDIA_BUS_FMT_YUV16_1X48:
+	case MEDIA_BUS_FMT_UYYVYY16_0_5X48:
+	case MEDIA_BUS_FMT_JPEG_1X8:
+	case MEDIA_BUS_FMT_AHSV8888_1X32:
+		break;
+	default:
+		sdformat->format.code = MEDIA_BUS_FMT_Y8_1X8;
+		break;
+	}
+	if (sdformat->format.field == V4L2_FIELD_ANY)
+		sdformat->format.field = V4L2_FIELD_NONE;
+
 	mutex_lock(&vmux->lock);
 
 	/* Source pad mirrors active sink pad, no limitations on sink pads */
@@ -197,7 +286,27 @@ static int video_mux_set_format(struct v4l2_subdev *sd,
 	return 0;
 }
 
+static int video_mux_init_cfg(struct v4l2_subdev *sd,
+			      struct v4l2_subdev_pad_config *cfg)
+{
+	struct video_mux *vmux = v4l2_subdev_to_video_mux(sd);
+	struct v4l2_mbus_framefmt *mbusformat;
+	unsigned int i;
+
+	mutex_lock(&vmux->lock);
+
+	for (i = 0; i < sd->entity.num_pads; i++) {
+		mbusformat = v4l2_subdev_get_try_format(sd, cfg, i);
+		*mbusformat = video_mux_format_mbus_default;
+	}
+
+	mutex_unlock(&vmux->lock);
+
+	return 0;
+}
+
 static const struct v4l2_subdev_pad_ops video_mux_pad_ops = {
+	.init_cfg = video_mux_init_cfg,
 	.get_fmt = video_mux_get_format,
 	.set_fmt = video_mux_set_format,
 };
@@ -214,8 +323,8 @@ static int video_mux_probe(struct platform_device *pdev)
 	struct device_node *ep;
 	struct video_mux *vmux;
 	unsigned int num_pads = 0;
+	unsigned int i;
 	int ret;
-	int i;
 
 	vmux = devm_kzalloc(dev, sizeof(*vmux), GFP_KERNEL);
 	if (!vmux)
@@ -260,9 +369,11 @@ static int video_mux_probe(struct platform_device *pdev)
 					 sizeof(*vmux->format_mbus),
 					 GFP_KERNEL);
 
-	for (i = 0; i < num_pads - 1; i++)
-		vmux->pads[i].flags = MEDIA_PAD_FL_SINK;
-	vmux->pads[num_pads - 1].flags = MEDIA_PAD_FL_SOURCE;
+	for (i = 0; i < num_pads; i++) {
+		vmux->pads[i].flags = (i < num_pads - 1) ? MEDIA_PAD_FL_SINK
+							 : MEDIA_PAD_FL_SOURCE;
+		vmux->format_mbus[i] = video_mux_format_mbus_default;
+	}
 
 	vmux->subdev.entity.function = MEDIA_ENT_F_VID_MUX;
 	ret = media_entity_pads_init(&vmux->subdev.entity, num_pads,
diff --git a/drivers/media/platform/vim2m.c b/drivers/media/platform/vim2m.c
index 065483e62db4..462099a141e4 100644
--- a/drivers/media/platform/vim2m.c
+++ b/drivers/media/platform/vim2m.c
@@ -140,6 +140,9 @@ static struct vim2m_fmt *find_format(struct v4l2_format *f)
 struct vim2m_dev {
 	struct v4l2_device	v4l2_dev;
 	struct video_device	vfd;
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct media_device	mdev;
+#endif
 
 	atomic_t		num_inst;
 	struct mutex		dev_mutex;
@@ -1016,11 +1019,10 @@ static int vim2m_probe(struct platform_device *pdev)
 	ret = video_register_device(vfd, VFL_TYPE_GRABBER, 0);
 	if (ret) {
 		v4l2_err(&dev->v4l2_dev, "Failed to register video device\n");
-		goto unreg_dev;
+		goto unreg_v4l2;
 	}
 
 	video_set_drvdata(vfd, dev);
-	snprintf(vfd->name, sizeof(vfd->name), "%s", vim2m_videodev.name);
 	v4l2_info(&dev->v4l2_dev,
 			"Device registered as /dev/video%d\n", vfd->num);
 
@@ -1031,15 +1033,39 @@ static int vim2m_probe(struct platform_device *pdev)
 	if (IS_ERR(dev->m2m_dev)) {
 		v4l2_err(&dev->v4l2_dev, "Failed to init mem2mem device\n");
 		ret = PTR_ERR(dev->m2m_dev);
-		goto err_m2m;
+		goto unreg_dev;
+	}
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+	dev->mdev.dev = &pdev->dev;
+	strlcpy(dev->mdev.model, "vim2m", sizeof(dev->mdev.model));
+	media_device_init(&dev->mdev);
+	dev->v4l2_dev.mdev = &dev->mdev;
+
+	ret = v4l2_m2m_register_media_controller(dev->m2m_dev,
+			vfd, MEDIA_ENT_F_PROC_VIDEO_SCALER);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev, "Failed to init mem2mem media controller\n");
+		goto unreg_m2m;
 	}
 
+	ret = media_device_register(&dev->mdev);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev, "Failed to register mem2mem media device\n");
+		goto unreg_m2m_mc;
+	}
+#endif
 	return 0;
 
-err_m2m:
+#ifdef CONFIG_MEDIA_CONTROLLER
+unreg_m2m_mc:
+	v4l2_m2m_unregister_media_controller(dev->m2m_dev);
+unreg_m2m:
 	v4l2_m2m_release(dev->m2m_dev);
-	video_unregister_device(&dev->vfd);
+#endif
 unreg_dev:
+	video_unregister_device(&dev->vfd);
+unreg_v4l2:
 	v4l2_device_unregister(&dev->v4l2_dev);
 
 	return ret;
@@ -1050,6 +1076,12 @@ static int vim2m_remove(struct platform_device *pdev)
 	struct vim2m_dev *dev = platform_get_drvdata(pdev);
 
 	v4l2_info(&dev->v4l2_dev, "Removing " MEM2MEM_NAME);
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+	media_device_unregister(&dev->mdev);
+	v4l2_m2m_unregister_media_controller(dev->m2m_dev);
+	media_device_cleanup(&dev->mdev);
+#endif
 	v4l2_m2m_release(dev->m2m_dev);
 	del_timer_sync(&dev->timer);
 	video_unregister_device(&dev->vfd);
diff --git a/drivers/media/platform/vimc/vimc-core.c b/drivers/media/platform/vimc/vimc-core.c
index fe088a953860..9246f265de31 100644
--- a/drivers/media/platform/vimc/vimc-core.c
+++ b/drivers/media/platform/vimc/vimc-core.c
@@ -328,7 +328,6 @@ static int vimc_probe(struct platform_device *pdev)
 	if (ret) {
 		media_device_cleanup(&vimc->mdev);
 		vimc_rm_subdevs(vimc);
-		kfree(vimc);
 		return ret;
 	}
 
diff --git a/drivers/media/platform/vivid/vivid-ctrls.c b/drivers/media/platform/vivid/vivid-ctrls.c
index 6b0bfa091592..5429193fbb91 100644
--- a/drivers/media/platform/vivid/vivid-ctrls.c
+++ b/drivers/media/platform/vivid/vivid-ctrls.c
@@ -295,7 +295,7 @@ static int vivid_user_vid_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
 
 	switch (ctrl->id) {
 	case V4L2_CID_AUTOGAIN:
-		dev->gain->val = dev->jiffies_vid_cap & 0xff;
+		dev->gain->val = (jiffies_to_msecs(jiffies) / 1000) & 0xff;
 		break;
 	}
 	return 0;
diff --git a/drivers/media/platform/vivid/vivid-kthread-cap.c b/drivers/media/platform/vivid/vivid-kthread-cap.c
index 3fdb280c36ca..f06003bb8e42 100644
--- a/drivers/media/platform/vivid/vivid-kthread-cap.c
+++ b/drivers/media/platform/vivid/vivid-kthread-cap.c
@@ -477,7 +477,7 @@ static void vivid_fillbuff(struct vivid_dev *dev, struct vivid_buffer *buf)
 
 	/* Updates stream time, only update at the start of a new frame. */
 	if (dev->field_cap != V4L2_FIELD_ALTERNATE ||
-			(buf->vb.sequence & 1) == 0)
+			(dev->vid_cap_seq_count & 1) == 0)
 		dev->ms_vid_cap =
 			jiffies_to_msecs(jiffies - dev->jiffies_vid_cap);
 
diff --git a/drivers/media/platform/vsp1/vsp1.h b/drivers/media/platform/vsp1/vsp1.h
index 33f632331474..56c62122a81a 100644
--- a/drivers/media/platform/vsp1/vsp1.h
+++ b/drivers/media/platform/vsp1/vsp1.h
@@ -53,6 +53,7 @@ struct vsp1_uif;
 #define VSP1_HAS_HGO		(1 << 7)
 #define VSP1_HAS_HGT		(1 << 8)
 #define VSP1_HAS_BRS		(1 << 9)
+#define VSP1_HAS_EXT_DL		(1 << 10)
 
 struct vsp1_device_info {
 	u32 version;
@@ -68,6 +69,8 @@ struct vsp1_device_info {
 	bool uapi;
 };
 
+#define vsp1_feature(vsp1, f) ((vsp1)->info->features & (f))
+
 struct vsp1_device {
 	struct device *dev;
 	const struct vsp1_device_info *info;
diff --git a/drivers/media/platform/vsp1/vsp1_dl.c b/drivers/media/platform/vsp1/vsp1_dl.c
index d9b9cdd8fbe2..26289adaf658 100644
--- a/drivers/media/platform/vsp1/vsp1_dl.c
+++ b/drivers/media/platform/vsp1/vsp1_dl.c
@@ -22,29 +22,79 @@
 #define VSP1_DLH_INT_ENABLE		(1 << 1)
 #define VSP1_DLH_AUTO_START		(1 << 0)
 
+#define VSP1_DLH_EXT_PRE_CMD_EXEC	(1 << 9)
+#define VSP1_DLH_EXT_POST_CMD_EXEC	(1 << 8)
+
 struct vsp1_dl_header_list {
 	u32 num_bytes;
 	u32 addr;
-} __attribute__((__packed__));
+} __packed;
 
 struct vsp1_dl_header {
 	u32 num_lists;
 	struct vsp1_dl_header_list lists[8];
 	u32 next_header;
 	u32 flags;
-} __attribute__((__packed__));
+} __packed;
+
+/**
+ * struct vsp1_dl_ext_header - Extended display list header
+ * @padding: padding zero bytes for alignment
+ * @pre_ext_dl_num_cmd: number of pre-extended command bodies to parse
+ * @flags: enables or disables execution of the pre and post command
+ * @pre_ext_dl_plist: start address of pre-extended display list bodies
+ * @post_ext_dl_num_cmd: number of post-extended command bodies to parse
+ * @post_ext_dl_plist: start address of post-extended display list bodies
+ */
+struct vsp1_dl_ext_header {
+	u32 padding;
+
+	/*
+	 * The datasheet represents flags as stored before pre_ext_dl_num_cmd,
+	 * expecting 32-bit accesses. The flags are appropriate to the whole
+	 * header, not just the pre_ext command, and thus warrant being
+	 * separated out. Due to byte ordering, and representing as 16 bit
+	 * values here, the flags must be positioned after the
+	 * pre_ext_dl_num_cmd.
+	 */
+	u16 pre_ext_dl_num_cmd;
+	u16 flags;
+	u32 pre_ext_dl_plist;
+
+	u32 post_ext_dl_num_cmd;
+	u32 post_ext_dl_plist;
+} __packed;
+
+struct vsp1_dl_header_extended {
+	struct vsp1_dl_header header;
+	struct vsp1_dl_ext_header ext;
+} __packed;
 
 struct vsp1_dl_entry {
 	u32 addr;
 	u32 data;
-} __attribute__((__packed__));
+} __packed;
+
+/**
+ * struct vsp1_pre_ext_dl_body - Pre Extended Display List Body
+ * @opcode: Extended display list command operation code
+ * @flags: Pre-extended command flags. These are specific to each command
+ * @address_set: Source address set pointer. Must have 16-byte alignment
+ * @reserved: Zero bits for alignment.
+ */
+struct vsp1_pre_ext_dl_body {
+	u32 opcode;
+	u32 flags;
+	u32 address_set;
+	u32 reserved;
+} __packed;
 
 /**
  * struct vsp1_dl_body - Display list body
  * @list: entry in the display list list of bodies
  * @free: entry in the pool free body list
+ * @refcnt: reference tracking for the body
  * @pool: pool to which this body belongs
- * @vsp1: the VSP1 device
  * @entries: array of entries
  * @dma: DMA address of the entries
  * @size: size of the DMA memory in bytes
@@ -58,7 +108,6 @@ struct vsp1_dl_body {
 	refcount_t refcnt;
 
 	struct vsp1_dl_body_pool *pool;
-	struct vsp1_device *vsp1;
 
 	struct vsp1_dl_entry *entries;
 	dma_addr_t dma;
@@ -93,13 +142,40 @@ struct vsp1_dl_body_pool {
 };
 
 /**
+ * struct vsp1_cmd_pool - Display List commands pool
+ * @dma: DMA address of the entries
+ * @size: size of the full DMA memory pool in bytes
+ * @mem: CPU memory pointer for the pool
+ * @cmds: Array of command structures for the pool
+ * @free: Free pool entries
+ * @lock: Protects the free list
+ * @vsp1: the VSP1 device
+ */
+struct vsp1_dl_cmd_pool {
+	/* DMA allocation */
+	dma_addr_t dma;
+	size_t size;
+	void *mem;
+
+	struct vsp1_dl_ext_cmd *cmds;
+	struct list_head free;
+
+	spinlock_t lock;
+
+	struct vsp1_device *vsp1;
+};
+
+/**
  * struct vsp1_dl_list - Display list
  * @list: entry in the display list manager lists
  * @dlm: the display list manager
- * @header: display list header, NULL for headerless lists
+ * @header: display list header
+ * @extension: extended display list header. NULL for normal lists
  * @dma: DMA address for the header
  * @body0: first display list body
  * @bodies: list of extra display list bodies
+ * @pre_cmd: pre command to be issued through extended dl header
+ * @post_cmd: post command to be issued through extended dl header
  * @has_chain: if true, indicates that there's a partition chain
  * @chain: entry in the display list partition chain
  * @internal: whether the display list is used for internal purpose
@@ -109,26 +185,24 @@ struct vsp1_dl_list {
 	struct vsp1_dl_manager *dlm;
 
 	struct vsp1_dl_header *header;
+	struct vsp1_dl_ext_header *extension;
 	dma_addr_t dma;
 
 	struct vsp1_dl_body *body0;
 	struct list_head bodies;
 
+	struct vsp1_dl_ext_cmd *pre_cmd;
+	struct vsp1_dl_ext_cmd *post_cmd;
+
 	bool has_chain;
 	struct list_head chain;
 
 	bool internal;
 };
 
-enum vsp1_dl_mode {
-	VSP1_DL_MODE_HEADER,
-	VSP1_DL_MODE_HEADERLESS,
-};
-
 /**
  * struct vsp1_dl_manager - Display List manager
  * @index: index of the related WPF
- * @mode: display list operation mode (header or headerless)
  * @singleshot: execute the display list in single-shot mode
  * @vsp1: the VSP1 device
  * @lock: protects the free, active, queued, and pending lists
@@ -137,10 +211,10 @@ enum vsp1_dl_mode {
  * @queued: list queued to the hardware (written to the DL registers)
  * @pending: list waiting to be queued to the hardware
  * @pool: body pool for the display list bodies
+ * @cmdpool: commands pool for extended display list
  */
 struct vsp1_dl_manager {
 	unsigned int index;
-	enum vsp1_dl_mode mode;
 	bool singleshot;
 	struct vsp1_device *vsp1;
 
@@ -151,6 +225,7 @@ struct vsp1_dl_manager {
 	struct vsp1_dl_list *pending;
 
 	struct vsp1_dl_body_pool *pool;
+	struct vsp1_dl_cmd_pool *cmdpool;
 };
 
 /* -----------------------------------------------------------------------------
@@ -314,12 +389,164 @@ void vsp1_dl_body_write(struct vsp1_dl_body *dlb, u32 reg, u32 data)
 }
 
 /* -----------------------------------------------------------------------------
+ * Display List Extended Command Management
+ */
+
+enum vsp1_extcmd_type {
+	VSP1_EXTCMD_AUTODISP,
+	VSP1_EXTCMD_AUTOFLD,
+};
+
+struct vsp1_extended_command_info {
+	u16 opcode;
+	size_t body_size;
+};
+
+static const struct vsp1_extended_command_info vsp1_extended_commands[] = {
+	[VSP1_EXTCMD_AUTODISP] = { 0x02, 96 },
+	[VSP1_EXTCMD_AUTOFLD]  = { 0x03, 160 },
+};
+
+/**
+ * vsp1_dl_cmd_pool_create - Create a pool of commands from a single allocation
+ * @vsp1: The VSP1 device
+ * @type: The command pool type
+ * @num_cmds: The number of commands to allocate
+ *
+ * Allocate a pool of commands each with enough memory to contain the private
+ * data of each command. The allocation sizes are dependent upon the command
+ * type.
+ *
+ * Return a pointer to the pool on success or NULL if memory can't be allocated.
+ */
+static struct vsp1_dl_cmd_pool *
+vsp1_dl_cmd_pool_create(struct vsp1_device *vsp1, enum vsp1_extcmd_type type,
+			unsigned int num_cmds)
+{
+	struct vsp1_dl_cmd_pool *pool;
+	unsigned int i;
+	size_t cmd_size;
+
+	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
+	if (!pool)
+		return NULL;
+
+	spin_lock_init(&pool->lock);
+	INIT_LIST_HEAD(&pool->free);
+
+	pool->cmds = kcalloc(num_cmds, sizeof(*pool->cmds), GFP_KERNEL);
+	if (!pool->cmds) {
+		kfree(pool);
+		return NULL;
+	}
+
+	cmd_size = sizeof(struct vsp1_pre_ext_dl_body) +
+		   vsp1_extended_commands[type].body_size;
+	cmd_size = ALIGN(cmd_size, 16);
+
+	pool->size = cmd_size * num_cmds;
+	pool->mem = dma_alloc_wc(vsp1->bus_master, pool->size, &pool->dma,
+				 GFP_KERNEL);
+	if (!pool->mem) {
+		kfree(pool->cmds);
+		kfree(pool);
+		return NULL;
+	}
+
+	for (i = 0; i < num_cmds; ++i) {
+		struct vsp1_dl_ext_cmd *cmd = &pool->cmds[i];
+		size_t cmd_offset = i * cmd_size;
+		/* data_offset must be 16 byte aligned for DMA. */
+		size_t data_offset = sizeof(struct vsp1_pre_ext_dl_body) +
+				     cmd_offset;
+
+		cmd->pool = pool;
+		cmd->opcode = vsp1_extended_commands[type].opcode;
+
+		/*
+		 * TODO: Auto-disp can utilise more than one extended body
+		 * command per cmd.
+		 */
+		cmd->num_cmds = 1;
+		cmd->cmds = pool->mem + cmd_offset;
+		cmd->cmd_dma = pool->dma + cmd_offset;
+
+		cmd->data = pool->mem + data_offset;
+		cmd->data_dma = pool->dma + data_offset;
+
+		list_add_tail(&cmd->free, &pool->free);
+	}
+
+	return pool;
+}
+
+static
+struct vsp1_dl_ext_cmd *vsp1_dl_ext_cmd_get(struct vsp1_dl_cmd_pool *pool)
+{
+	struct vsp1_dl_ext_cmd *cmd = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pool->lock, flags);
+
+	if (!list_empty(&pool->free)) {
+		cmd = list_first_entry(&pool->free, struct vsp1_dl_ext_cmd,
+				       free);
+		list_del(&cmd->free);
+	}
+
+	spin_unlock_irqrestore(&pool->lock, flags);
+
+	return cmd;
+}
+
+static void vsp1_dl_ext_cmd_put(struct vsp1_dl_ext_cmd *cmd)
+{
+	unsigned long flags;
+
+	if (!cmd)
+		return;
+
+	/* Reset flags, these mark data usage. */
+	cmd->flags = 0;
+
+	spin_lock_irqsave(&cmd->pool->lock, flags);
+	list_add_tail(&cmd->free, &cmd->pool->free);
+	spin_unlock_irqrestore(&cmd->pool->lock, flags);
+}
+
+static void vsp1_dl_ext_cmd_pool_destroy(struct vsp1_dl_cmd_pool *pool)
+{
+	if (!pool)
+		return;
+
+	if (pool->mem)
+		dma_free_wc(pool->vsp1->bus_master, pool->size, pool->mem,
+			    pool->dma);
+
+	kfree(pool->cmds);
+	kfree(pool);
+}
+
+struct vsp1_dl_ext_cmd *vsp1_dl_get_pre_cmd(struct vsp1_dl_list *dl)
+{
+	struct vsp1_dl_manager *dlm = dl->dlm;
+
+	if (dl->pre_cmd)
+		return dl->pre_cmd;
+
+	dl->pre_cmd = vsp1_dl_ext_cmd_get(dlm->cmdpool);
+
+	return dl->pre_cmd;
+}
+
+/* ----------------------------------------------------------------------------
  * Display List Transaction Management
  */
 
 static struct vsp1_dl_list *vsp1_dl_list_alloc(struct vsp1_dl_manager *dlm)
 {
 	struct vsp1_dl_list *dl;
+	size_t header_offset;
 
 	dl = kzalloc(sizeof(*dl), GFP_KERNEL);
 	if (!dl)
@@ -332,16 +559,14 @@ static struct vsp1_dl_list *vsp1_dl_list_alloc(struct vsp1_dl_manager *dlm)
 	dl->body0 = vsp1_dl_body_get(dlm->pool);
 	if (!dl->body0)
 		return NULL;
-	if (dlm->mode == VSP1_DL_MODE_HEADER) {
-		size_t header_offset = dl->body0->max_entries
-				     * sizeof(*dl->body0->entries);
 
-		dl->header = ((void *)dl->body0->entries) + header_offset;
-		dl->dma = dl->body0->dma + header_offset;
+	header_offset = dl->body0->max_entries * sizeof(*dl->body0->entries);
 
-		memset(dl->header, 0, sizeof(*dl->header));
-		dl->header->lists[0].addr = dl->body0->dma;
-	}
+	dl->header = ((void *)dl->body0->entries) + header_offset;
+	dl->dma = dl->body0->dma + header_offset;
+
+	memset(dl->header, 0, sizeof(*dl->header));
+	dl->header->lists[0].addr = dl->body0->dma;
 
 	return dl;
 }
@@ -398,7 +623,7 @@ struct vsp1_dl_list *vsp1_dl_list_get(struct vsp1_dl_manager *dlm)
 /* This function must be called with the display list manager lock held.*/
 static void __vsp1_dl_list_put(struct vsp1_dl_list *dl)
 {
-	struct vsp1_dl_list *dl_child;
+	struct vsp1_dl_list *dl_next;
 
 	if (!dl)
 		return;
@@ -408,14 +633,20 @@ static void __vsp1_dl_list_put(struct vsp1_dl_list *dl)
 	 * hardware operation.
 	 */
 	if (dl->has_chain) {
-		list_for_each_entry(dl_child, &dl->chain, chain)
-			__vsp1_dl_list_put(dl_child);
+		list_for_each_entry(dl_next, &dl->chain, chain)
+			__vsp1_dl_list_put(dl_next);
 	}
 
 	dl->has_chain = false;
 
 	vsp1_dl_list_bodies_put(dl);
 
+	vsp1_dl_ext_cmd_put(dl->pre_cmd);
+	vsp1_dl_ext_cmd_put(dl->post_cmd);
+
+	dl->pre_cmd = NULL;
+	dl->post_cmd = NULL;
+
 	/*
 	 * body0 is reused as as an optimisation as presently every display list
 	 * has at least one body, thus we reinitialise the entries list.
@@ -473,16 +704,9 @@ struct vsp1_dl_body *vsp1_dl_list_get_body0(struct vsp1_dl_list *dl)
  *
  * The reference must be explicitly released by a call to vsp1_dl_body_put()
  * when the body isn't needed anymore.
- *
- * Additional bodies are only usable for display lists in header mode.
- * Attempting to add a body to a header-less display list will return an error.
  */
 int vsp1_dl_list_add_body(struct vsp1_dl_list *dl, struct vsp1_dl_body *dlb)
 {
-	/* Multi-body lists are only available in header mode. */
-	if (dl->dlm->mode != VSP1_DL_MODE_HEADER)
-		return -EINVAL;
-
 	refcount_inc(&dlb->refcnt);
 
 	list_add_tail(&dlb->list, &dl->bodies);
@@ -503,22 +727,23 @@ int vsp1_dl_list_add_body(struct vsp1_dl_list *dl, struct vsp1_dl_body *dlb)
  * Adding a display list to a chain passes ownership of the display list to
  * the head display list item. The chain is released when the head dl item is
  * put back with __vsp1_dl_list_put().
- *
- * Chained display lists are only usable in header mode. Attempts to add a
- * display list to a chain in header-less mode will return an error.
  */
 int vsp1_dl_list_add_chain(struct vsp1_dl_list *head,
 			   struct vsp1_dl_list *dl)
 {
-	/* Chained lists are only available in header mode. */
-	if (head->dlm->mode != VSP1_DL_MODE_HEADER)
-		return -EINVAL;
-
 	head->has_chain = true;
 	list_add_tail(&dl->chain, &head->chain);
 	return 0;
 }
 
+static void vsp1_dl_ext_cmd_fill_header(struct vsp1_dl_ext_cmd *cmd)
+{
+	cmd->cmds[0].opcode = cmd->opcode;
+	cmd->cmds[0].flags = cmd->flags;
+	cmd->cmds[0].address_set = cmd->data_dma;
+	cmd->cmds[0].reserved = 0;
+}
+
 static void vsp1_dl_list_fill_header(struct vsp1_dl_list *dl, bool is_last)
 {
 	struct vsp1_dl_manager *dlm = dl->dlm;
@@ -571,6 +796,27 @@ static void vsp1_dl_list_fill_header(struct vsp1_dl_list *dl, bool is_last)
 		 */
 		dl->header->flags = VSP1_DLH_INT_ENABLE;
 	}
+
+	if (!dl->extension)
+		return;
+
+	dl->extension->flags = 0;
+
+	if (dl->pre_cmd) {
+		dl->extension->pre_ext_dl_plist = dl->pre_cmd->cmd_dma;
+		dl->extension->pre_ext_dl_num_cmd = dl->pre_cmd->num_cmds;
+		dl->extension->flags |= VSP1_DLH_EXT_PRE_CMD_EXEC;
+
+		vsp1_dl_ext_cmd_fill_header(dl->pre_cmd);
+	}
+
+	if (dl->post_cmd) {
+		dl->extension->post_ext_dl_plist = dl->post_cmd->cmd_dma;
+		dl->extension->post_ext_dl_num_cmd = dl->post_cmd->num_cmds;
+		dl->extension->flags |= VSP1_DLH_EXT_POST_CMD_EXEC;
+
+		vsp1_dl_ext_cmd_fill_header(dl->post_cmd);
+	}
 }
 
 static bool vsp1_dl_list_hw_update_pending(struct vsp1_dl_manager *dlm)
@@ -581,17 +827,10 @@ static bool vsp1_dl_list_hw_update_pending(struct vsp1_dl_manager *dlm)
 		return false;
 
 	/*
-	 * Check whether the VSP1 has taken the update. In headerless mode the
-	 * hardware indicates this by clearing the UPD bit in the DL_BODY_SIZE
-	 * register, and in header mode by clearing the UPDHDR bit in the CMD
-	 * register.
+	 * Check whether the VSP1 has taken the update. The hardware indicates
+	 * this by clearing the UPDHDR bit in the CMD register.
 	 */
-	if (dlm->mode == VSP1_DL_MODE_HEADERLESS)
-		return !!(vsp1_read(vsp1, VI6_DL_BODY_SIZE)
-			  & VI6_DL_BODY_SIZE_UPD);
-	else
-		return !!(vsp1_read(vsp1, VI6_CMD(dlm->index))
-			  & VI6_CMD_UPDHDR);
+	return !!(vsp1_read(vsp1, VI6_CMD(dlm->index)) & VI6_CMD_UPDHDR);
 }
 
 static void vsp1_dl_list_hw_enqueue(struct vsp1_dl_list *dl)
@@ -599,26 +838,14 @@ static void vsp1_dl_list_hw_enqueue(struct vsp1_dl_list *dl)
 	struct vsp1_dl_manager *dlm = dl->dlm;
 	struct vsp1_device *vsp1 = dlm->vsp1;
 
-	if (dlm->mode == VSP1_DL_MODE_HEADERLESS) {
-		/*
-		 * In headerless mode, program the hardware directly with the
-		 * display list body address and size and set the UPD bit. The
-		 * bit will be cleared by the hardware when the display list
-		 * processing starts.
-		 */
-		vsp1_write(vsp1, VI6_DL_HDR_ADDR(0), dl->body0->dma);
-		vsp1_write(vsp1, VI6_DL_BODY_SIZE, VI6_DL_BODY_SIZE_UPD |
-			(dl->body0->num_entries * sizeof(*dl->header->lists)));
-	} else {
-		/*
-		 * In header mode, program the display list header address. If
-		 * the hardware is idle (single-shot mode or first frame in
-		 * continuous mode) it will then be started independently. If
-		 * the hardware is operating, the VI6_DL_HDR_REF_ADDR register
-		 * will be updated with the display list address.
-		 */
-		vsp1_write(vsp1, VI6_DL_HDR_ADDR(dlm->index), dl->dma);
-	}
+	/*
+	 * Program the display list header address. If the hardware is idle
+	 * (single-shot mode or first frame in continuous mode) it will then be
+	 * started independently. If the hardware is operating, the
+	 * VI6_DL_HDR_REF_ADDR register will be updated with the display list
+	 * address.
+	 */
+	vsp1_write(vsp1, VI6_DL_HDR_ADDR(dlm->index), dl->dma);
 }
 
 static void vsp1_dl_list_commit_continuous(struct vsp1_dl_list *dl)
@@ -673,18 +900,16 @@ static void vsp1_dl_list_commit_singleshot(struct vsp1_dl_list *dl)
 void vsp1_dl_list_commit(struct vsp1_dl_list *dl, bool internal)
 {
 	struct vsp1_dl_manager *dlm = dl->dlm;
-	struct vsp1_dl_list *dl_child;
+	struct vsp1_dl_list *dl_next;
 	unsigned long flags;
 
-	if (dlm->mode == VSP1_DL_MODE_HEADER) {
-		/* Fill the header for the head and chained display lists. */
-		vsp1_dl_list_fill_header(dl, list_empty(&dl->chain));
+	/* Fill the header for the head and chained display lists. */
+	vsp1_dl_list_fill_header(dl, list_empty(&dl->chain));
 
-		list_for_each_entry(dl_child, &dl->chain, chain) {
-			bool last = list_is_last(&dl_child->chain, &dl->chain);
+	list_for_each_entry(dl_next, &dl->chain, chain) {
+		bool last = list_is_last(&dl_next->chain, &dl->chain);
 
-			vsp1_dl_list_fill_header(dl_child, last);
-		}
+		vsp1_dl_list_fill_header(dl_next, last);
 	}
 
 	dl->internal = internal;
@@ -713,7 +938,7 @@ void vsp1_dl_list_commit(struct vsp1_dl_list *dl, bool internal)
  * has completed at frame end. If the flag is not returned display list
  * completion has been delayed by one frame because the display list commit
  * raced with the frame end interrupt. The function always returns with the flag
- * set in header mode as display list processing is then not continuous and
+ * set in single-shot mode as display list processing is then not continuous and
  * races never occur.
  *
  * The VSP1_DL_FRAME_END_INTERNAL flag indicates that the previous display list
@@ -722,6 +947,8 @@ void vsp1_dl_list_commit(struct vsp1_dl_list *dl, bool internal)
  */
 unsigned int vsp1_dlm_irq_frame_end(struct vsp1_dl_manager *dlm)
 {
+	struct vsp1_device *vsp1 = dlm->vsp1;
+	u32 status = vsp1_read(vsp1, VI6_STATUS);
 	unsigned int flags = 0;
 
 	spin_lock(&dlm->lock);
@@ -747,6 +974,14 @@ unsigned int vsp1_dlm_irq_frame_end(struct vsp1_dl_manager *dlm)
 		goto done;
 
 	/*
+	 * Progressive streams report only TOP fields. If we have a BOTTOM
+	 * field, we are interlaced, and expect the frame to complete on the
+	 * next frame end interrupt.
+	 */
+	if (status & VI6_STATUS_FLD_STD(dlm->index))
+		goto done;
+
+	/*
 	 * The device starts processing the queued display list right after the
 	 * frame end interrupt. The display list thus becomes active.
 	 */
@@ -781,16 +1016,17 @@ done:
 /* Hardware Setup */
 void vsp1_dlm_setup(struct vsp1_device *vsp1)
 {
+	unsigned int i;
 	u32 ctrl = (256 << VI6_DL_CTRL_AR_WAIT_SHIFT)
 		 | VI6_DL_CTRL_DC2 | VI6_DL_CTRL_DC1 | VI6_DL_CTRL_DC0
 		 | VI6_DL_CTRL_DLE;
+	u32 ext_dl = (0x02 << VI6_DL_EXT_CTRL_POLINT_SHIFT)
+		   | VI6_DL_EXT_CTRL_DLPRI | VI6_DL_EXT_CTRL_EXT;
 
-	/*
-	 * The DRM pipeline operates with display lists in Continuous Frame
-	 * Mode, all other pipelines use manual start.
-	 */
-	if (vsp1->drm)
-		ctrl |= VI6_DL_CTRL_CFM0 | VI6_DL_CTRL_NH0;
+	if (vsp1_feature(vsp1, VSP1_HAS_EXT_DL)) {
+		for (i = 0; i < vsp1->info->wpf_count; ++i)
+			vsp1_write(vsp1, VI6_DL_EXT_CTRL(i), ext_dl);
+	}
 
 	vsp1_write(vsp1, VI6_DL_CTRL, ctrl);
 	vsp1_write(vsp1, VI6_DL_SWAP, VI6_DL_SWAP_LWS);
@@ -831,8 +1067,6 @@ struct vsp1_dl_manager *vsp1_dlm_create(struct vsp1_device *vsp1,
 		return NULL;
 
 	dlm->index = index;
-	dlm->mode = index == 0 && !vsp1->info->uapi
-		  ? VSP1_DL_MODE_HEADERLESS : VSP1_DL_MODE_HEADER;
 	dlm->singleshot = vsp1->info->uapi;
 	dlm->vsp1 = vsp1;
 
@@ -841,14 +1075,16 @@ struct vsp1_dl_manager *vsp1_dlm_create(struct vsp1_device *vsp1,
 
 	/*
 	 * Initialize the display list body and allocate DMA memory for the body
-	 * and the optional header. Both are allocated together to avoid memory
+	 * and the header. Both are allocated together to avoid memory
 	 * fragmentation, with the header located right after the body in
 	 * memory. An extra body is allocated on top of the prealloc to account
 	 * for the cached body used by the vsp1_pipeline object.
 	 */
-	header_size = dlm->mode == VSP1_DL_MODE_HEADER
-		    ? ALIGN(sizeof(struct vsp1_dl_header), 8)
-		    : 0;
+	header_size = vsp1_feature(vsp1, VSP1_HAS_EXT_DL) ?
+			sizeof(struct vsp1_dl_header_extended) :
+			sizeof(struct vsp1_dl_header);
+
+	header_size = ALIGN(header_size, 8);
 
 	dlm->pool = vsp1_dl_body_pool_create(vsp1, prealloc + 1,
 					     VSP1_DL_NUM_ENTRIES, header_size);
@@ -859,12 +1095,28 @@ struct vsp1_dl_manager *vsp1_dlm_create(struct vsp1_device *vsp1,
 		struct vsp1_dl_list *dl;
 
 		dl = vsp1_dl_list_alloc(dlm);
-		if (!dl)
+		if (!dl) {
+			vsp1_dlm_destroy(dlm);
 			return NULL;
+		}
+
+		/* The extended header immediately follows the header. */
+		if (vsp1_feature(vsp1, VSP1_HAS_EXT_DL))
+			dl->extension = (void *)dl->header
+				      + sizeof(*dl->header);
 
 		list_add_tail(&dl->list, &dlm->free);
 	}
 
+	if (vsp1_feature(vsp1, VSP1_HAS_EXT_DL)) {
+		dlm->cmdpool = vsp1_dl_cmd_pool_create(vsp1,
+					VSP1_EXTCMD_AUTOFLD, prealloc);
+		if (!dlm->cmdpool) {
+			vsp1_dlm_destroy(dlm);
+			return NULL;
+		}
+	}
+
 	return dlm;
 }
 
@@ -881,4 +1133,5 @@ void vsp1_dlm_destroy(struct vsp1_dl_manager *dlm)
 	}
 
 	vsp1_dl_body_pool_destroy(dlm->pool);
+	vsp1_dl_ext_cmd_pool_destroy(dlm->cmdpool);
 }
diff --git a/drivers/media/platform/vsp1/vsp1_dl.h b/drivers/media/platform/vsp1/vsp1_dl.h
index 7dba0469c92e..125750dc8b5c 100644
--- a/drivers/media/platform/vsp1/vsp1_dl.h
+++ b/drivers/media/platform/vsp1/vsp1_dl.h
@@ -20,6 +20,33 @@ struct vsp1_dl_manager;
 #define VSP1_DL_FRAME_END_COMPLETED		BIT(0)
 #define VSP1_DL_FRAME_END_INTERNAL		BIT(1)
 
+/**
+ * struct vsp1_dl_ext_cmd - Extended Display command
+ * @pool: pool to which this command belongs
+ * @free: entry in the pool of free commands list
+ * @opcode: command type opcode
+ * @flags: flags used by the command
+ * @cmds: array of command bodies for this extended cmd
+ * @num_cmds: quantity of commands in @cmds array
+ * @cmd_dma: DMA address of the command body
+ * @data: memory allocation for command-specific data
+ * @data_dma: DMA address for command-specific data
+ */
+struct vsp1_dl_ext_cmd {
+	struct vsp1_dl_cmd_pool *pool;
+	struct list_head free;
+
+	u8 opcode;
+	u32 flags;
+
+	struct vsp1_pre_ext_dl_body *cmds;
+	unsigned int num_cmds;
+	dma_addr_t cmd_dma;
+
+	void *data;
+	dma_addr_t data_dma;
+};
+
 void vsp1_dlm_setup(struct vsp1_device *vsp1);
 
 struct vsp1_dl_manager *vsp1_dlm_create(struct vsp1_device *vsp1,
@@ -33,6 +60,7 @@ struct vsp1_dl_body *vsp1_dlm_dl_body_get(struct vsp1_dl_manager *dlm);
 struct vsp1_dl_list *vsp1_dl_list_get(struct vsp1_dl_manager *dlm);
 void vsp1_dl_list_put(struct vsp1_dl_list *dl);
 struct vsp1_dl_body *vsp1_dl_list_get_body0(struct vsp1_dl_list *dl);
+struct vsp1_dl_ext_cmd *vsp1_dl_get_pre_cmd(struct vsp1_dl_list *dl);
 void vsp1_dl_list_commit(struct vsp1_dl_list *dl, bool internal);
 
 struct vsp1_dl_body_pool *
diff --git a/drivers/media/platform/vsp1/vsp1_drm.c b/drivers/media/platform/vsp1/vsp1_drm.c
index a99fc0ced7a7..b9c0f695d002 100644
--- a/drivers/media/platform/vsp1/vsp1_drm.c
+++ b/drivers/media/platform/vsp1/vsp1_drm.c
@@ -670,9 +670,11 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int pipe_index,
 
 	drm_pipe->width = cfg->width;
 	drm_pipe->height = cfg->height;
+	pipe->interlaced = cfg->interlaced;
 
-	dev_dbg(vsp1->dev, "%s: configuring LIF%u with format %ux%u\n",
-		__func__, pipe_index, cfg->width, cfg->height);
+	dev_dbg(vsp1->dev, "%s: configuring LIF%u with format %ux%u%s\n",
+		__func__, pipe_index, cfg->width, cfg->height,
+		pipe->interlaced ? "i" : "");
 
 	mutex_lock(&vsp1->drm->lock);
 
@@ -803,7 +805,7 @@ int vsp1_du_atomic_update(struct device *dev, unsigned int pipe_index,
 	 */
 	fmtinfo = vsp1_get_format_info(vsp1, cfg->pixelformat);
 	if (!fmtinfo) {
-		dev_dbg(vsp1->dev, "Unsupport pixel format %08x for RPF\n",
+		dev_dbg(vsp1->dev, "Unsupported pixel format %08x for RPF\n",
 			cfg->pixelformat);
 		return -EINVAL;
 	}
diff --git a/drivers/media/platform/vsp1/vsp1_drv.c b/drivers/media/platform/vsp1/vsp1_drv.c
index 5d82f6ee56ea..b6619c9c18bb 100644
--- a/drivers/media/platform/vsp1/vsp1_drv.c
+++ b/drivers/media/platform/vsp1/vsp1_drv.c
@@ -265,7 +265,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 	}
 
 	/* Instantiate all the entities. */
-	if (vsp1->info->features & VSP1_HAS_BRS) {
+	if (vsp1_feature(vsp1, VSP1_HAS_BRS)) {
 		vsp1->brs = vsp1_brx_create(vsp1, VSP1_ENTITY_BRS);
 		if (IS_ERR(vsp1->brs)) {
 			ret = PTR_ERR(vsp1->brs);
@@ -275,7 +275,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 		list_add_tail(&vsp1->brs->entity.list_dev, &vsp1->entities);
 	}
 
-	if (vsp1->info->features & VSP1_HAS_BRU) {
+	if (vsp1_feature(vsp1, VSP1_HAS_BRU)) {
 		vsp1->bru = vsp1_brx_create(vsp1, VSP1_ENTITY_BRU);
 		if (IS_ERR(vsp1->bru)) {
 			ret = PTR_ERR(vsp1->bru);
@@ -285,7 +285,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 		list_add_tail(&vsp1->bru->entity.list_dev, &vsp1->entities);
 	}
 
-	if (vsp1->info->features & VSP1_HAS_CLU) {
+	if (vsp1_feature(vsp1, VSP1_HAS_CLU)) {
 		vsp1->clu = vsp1_clu_create(vsp1);
 		if (IS_ERR(vsp1->clu)) {
 			ret = PTR_ERR(vsp1->clu);
@@ -311,7 +311,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 
 	list_add_tail(&vsp1->hst->entity.list_dev, &vsp1->entities);
 
-	if (vsp1->info->features & VSP1_HAS_HGO && vsp1->info->uapi) {
+	if (vsp1_feature(vsp1, VSP1_HAS_HGO) && vsp1->info->uapi) {
 		vsp1->hgo = vsp1_hgo_create(vsp1);
 		if (IS_ERR(vsp1->hgo)) {
 			ret = PTR_ERR(vsp1->hgo);
@@ -322,7 +322,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 			      &vsp1->entities);
 	}
 
-	if (vsp1->info->features & VSP1_HAS_HGT && vsp1->info->uapi) {
+	if (vsp1_feature(vsp1, VSP1_HAS_HGT) && vsp1->info->uapi) {
 		vsp1->hgt = vsp1_hgt_create(vsp1);
 		if (IS_ERR(vsp1->hgt)) {
 			ret = PTR_ERR(vsp1->hgt);
@@ -353,7 +353,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 		}
 	}
 
-	if (vsp1->info->features & VSP1_HAS_LUT) {
+	if (vsp1_feature(vsp1, VSP1_HAS_LUT)) {
 		vsp1->lut = vsp1_lut_create(vsp1);
 		if (IS_ERR(vsp1->lut)) {
 			ret = PTR_ERR(vsp1->lut);
@@ -387,7 +387,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 		}
 	}
 
-	if (vsp1->info->features & VSP1_HAS_SRU) {
+	if (vsp1_feature(vsp1, VSP1_HAS_SRU)) {
 		vsp1->sru = vsp1_sru_create(vsp1);
 		if (IS_ERR(vsp1->sru)) {
 			ret = PTR_ERR(vsp1->sru);
@@ -537,7 +537,7 @@ static int vsp1_device_init(struct vsp1_device *vsp1)
 	vsp1_write(vsp1, VI6_DPR_HSI_ROUTE, VI6_DPR_NODE_UNUSED);
 	vsp1_write(vsp1, VI6_DPR_BRU_ROUTE, VI6_DPR_NODE_UNUSED);
 
-	if (vsp1->info->features & VSP1_HAS_BRS)
+	if (vsp1_feature(vsp1, VSP1_HAS_BRS))
 		vsp1_write(vsp1, VI6_DPR_ILV_BRS_ROUTE, VI6_DPR_NODE_UNUSED);
 
 	vsp1_write(vsp1, VI6_DPR_HGO_SMPPT, (7 << VI6_DPR_SMPPT_TGW_SHIFT) |
@@ -754,7 +754,7 @@ static const struct vsp1_device_info vsp1_device_infos[] = {
 		.version = VI6_IP_VERSION_MODEL_VSPD_GEN3,
 		.model = "VSP2-D",
 		.gen = 3,
-		.features = VSP1_HAS_BRU | VSP1_HAS_WPF_VFLIP,
+		.features = VSP1_HAS_BRU | VSP1_HAS_WPF_VFLIP | VSP1_HAS_EXT_DL,
 		.lif_count = 1,
 		.rpf_count = 5,
 		.uif_count = 1,
@@ -774,7 +774,7 @@ static const struct vsp1_device_info vsp1_device_infos[] = {
 		.version = VI6_IP_VERSION_MODEL_VSPDL_GEN3,
 		.model = "VSP2-DL",
 		.gen = 3,
-		.features = VSP1_HAS_BRS | VSP1_HAS_BRU,
+		.features = VSP1_HAS_BRS | VSP1_HAS_BRU | VSP1_HAS_EXT_DL,
 		.lif_count = 2,
 		.rpf_count = 5,
 		.uif_count = 2,
diff --git a/drivers/media/platform/vsp1/vsp1_pipe.h b/drivers/media/platform/vsp1/vsp1_pipe.h
index 743d8f0db45c..ae646c9ef337 100644
--- a/drivers/media/platform/vsp1/vsp1_pipe.h
+++ b/drivers/media/platform/vsp1/vsp1_pipe.h
@@ -104,6 +104,7 @@ struct vsp1_partition {
  * @entities: list of entities in the pipeline
  * @stream_config: cached stream configuration for video pipelines
  * @configured: when false the @stream_config shall be written to the hardware
+ * @interlaced: True when the pipeline is configured in interlaced mode
  * @partitions: The number of partitions used to process one frame
  * @partition: The current partition for configuration to process
  * @part_table: The pre-calculated partitions used by the pipeline
@@ -142,6 +143,7 @@ struct vsp1_pipeline {
 
 	struct vsp1_dl_body *stream_config;
 	bool configured;
+	bool interlaced;
 
 	unsigned int partitions;
 	struct vsp1_partition *partition;
diff --git a/drivers/media/platform/vsp1/vsp1_regs.h b/drivers/media/platform/vsp1/vsp1_regs.h
index 0d249ff9f564..3738ff2f7b85 100644
--- a/drivers/media/platform/vsp1/vsp1_regs.h
+++ b/drivers/media/platform/vsp1/vsp1_regs.h
@@ -28,6 +28,7 @@
 #define VI6_SRESET_SRTS(n)		(1 << (n))
 
 #define VI6_STATUS			0x0038
+#define VI6_STATUS_FLD_STD(n)		(1 << ((n) + 28))
 #define VI6_STATUS_SYS_ACT(n)		(1 << ((n) + 8))
 
 #define VI6_WPF_IRQ_ENB(n)		(0x0048 + (n) * 12)
@@ -72,7 +73,7 @@
 #define VI6_DL_SWAP_WDS			(1 << 1)
 #define VI6_DL_SWAP_BTS			(1 << 0)
 
-#define VI6_DL_EXT_CTRL			0x011c
+#define VI6_DL_EXT_CTRL(n)		(0x011c + (n) * 36)
 #define VI6_DL_EXT_CTRL_NWE		(1 << 16)
 #define VI6_DL_EXT_CTRL_POLINT_MASK	(0x3f << 8)
 #define VI6_DL_EXT_CTRL_POLINT_SHIFT	8
@@ -80,6 +81,8 @@
 #define VI6_DL_EXT_CTRL_EXPRI		(1 << 4)
 #define VI6_DL_EXT_CTRL_EXT		(1 << 0)
 
+#define VI6_DL_EXT_AUTOFLD_INT		BIT(0)
+
 #define VI6_DL_BODY_SIZE		0x0120
 #define VI6_DL_BODY_SIZE_UPD		(1 << 24)
 #define VI6_DL_BODY_SIZE_BS_MASK	(0x1ffff << 0)
diff --git a/drivers/media/platform/vsp1/vsp1_rpf.c b/drivers/media/platform/vsp1/vsp1_rpf.c
index 69e5fe6e6b50..f8005b60b9d2 100644
--- a/drivers/media/platform/vsp1/vsp1_rpf.c
+++ b/drivers/media/platform/vsp1/vsp1_rpf.c
@@ -20,6 +20,18 @@
 #define RPF_MAX_WIDTH				8190
 #define RPF_MAX_HEIGHT				8190
 
+/* Pre extended display list command data structure. */
+struct vsp1_extcmd_auto_fld_body {
+	u32 top_y0;
+	u32 bottom_y0;
+	u32 top_c0;
+	u32 bottom_c0;
+	u32 top_c1;
+	u32 bottom_c1;
+	u32 reserved0;
+	u32 reserved1;
+} __packed;
+
 /* -----------------------------------------------------------------------------
  * Device Access
  */
@@ -64,6 +76,14 @@ static void rpf_configure_stream(struct vsp1_entity *entity,
 		pstride |= format->plane_fmt[1].bytesperline
 			<< VI6_RPF_SRCM_PSTRIDE_C_SHIFT;
 
+	/*
+	 * pstride has both STRIDE_Y and STRIDE_C, but multiplying the whole
+	 * of pstride by 2 is conveniently OK here as we are multiplying both
+	 * values.
+	 */
+	if (pipe->interlaced)
+		pstride *= 2;
+
 	vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_PSTRIDE, pstride);
 
 	/* Format */
@@ -100,6 +120,9 @@ static void rpf_configure_stream(struct vsp1_entity *entity,
 		top = compose->top;
 	}
 
+	if (pipe->interlaced)
+		top /= 2;
+
 	vsp1_rpf_write(rpf, dlb, VI6_RPF_LOC,
 		       (left << VI6_RPF_LOC_HCOORD_SHIFT) |
 		       (top << VI6_RPF_LOC_VCOORD_SHIFT));
@@ -169,6 +192,36 @@ static void rpf_configure_stream(struct vsp1_entity *entity,
 
 }
 
+static void vsp1_rpf_configure_autofld(struct vsp1_rwpf *rpf,
+				       struct vsp1_dl_list *dl)
+{
+	const struct v4l2_pix_format_mplane *format = &rpf->format;
+	struct vsp1_dl_ext_cmd *cmd;
+	struct vsp1_extcmd_auto_fld_body *auto_fld;
+	u32 offset_y, offset_c;
+
+	cmd = vsp1_dl_get_pre_cmd(dl);
+	if (WARN_ONCE(!cmd, "Failed to obtain an autofld cmd"))
+		return;
+
+	/* Re-index our auto_fld to match the current RPF. */
+	auto_fld = cmd->data;
+	auto_fld = &auto_fld[rpf->entity.index];
+
+	auto_fld->top_y0 = rpf->mem.addr[0];
+	auto_fld->top_c0 = rpf->mem.addr[1];
+	auto_fld->top_c1 = rpf->mem.addr[2];
+
+	offset_y = format->plane_fmt[0].bytesperline;
+	offset_c = format->plane_fmt[1].bytesperline;
+
+	auto_fld->bottom_y0 = rpf->mem.addr[0] + offset_y;
+	auto_fld->bottom_c0 = rpf->mem.addr[1] + offset_c;
+	auto_fld->bottom_c1 = rpf->mem.addr[2] + offset_c;
+
+	cmd->flags |= VI6_DL_EXT_AUTOFLD_INT | BIT(16 + rpf->entity.index);
+}
+
 static void rpf_configure_frame(struct vsp1_entity *entity,
 				struct vsp1_pipeline *pipe,
 				struct vsp1_dl_list *dl,
@@ -221,6 +274,11 @@ static void rpf_configure_partition(struct vsp1_entity *entity,
 		crop.left += pipe->partition->rpf.left;
 	}
 
+	if (pipe->interlaced) {
+		crop.height = round_down(crop.height / 2, fmtinfo->vsub);
+		crop.top = round_down(crop.top / 2, fmtinfo->vsub);
+	}
+
 	vsp1_rpf_write(rpf, dlb, VI6_RPF_SRC_BSIZE,
 		       (crop.width << VI6_RPF_SRC_BSIZE_BHSIZE_SHIFT) |
 		       (crop.height << VI6_RPF_SRC_BSIZE_BVSIZE_SHIFT));
@@ -249,9 +307,17 @@ static void rpf_configure_partition(struct vsp1_entity *entity,
 	    fmtinfo->swap_uv)
 		swap(mem.addr[1], mem.addr[2]);
 
-	vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_ADDR_Y, mem.addr[0]);
-	vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_ADDR_C0, mem.addr[1]);
-	vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_ADDR_C1, mem.addr[2]);
+	/*
+	 * Interlaced pipelines will use the extended pre-cmd to process
+	 * SRCM_ADDR_{Y,C0,C1}
+	 */
+	if (pipe->interlaced) {
+		vsp1_rpf_configure_autofld(rpf, dl);
+	} else {
+		vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_ADDR_Y, mem.addr[0]);
+		vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_ADDR_C0, mem.addr[1]);
+		vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_ADDR_C1, mem.addr[2]);
+	}
 }
 
 static void rpf_partition(struct vsp1_entity *entity,
diff --git a/drivers/media/platform/vsp1/vsp1_wpf.c b/drivers/media/platform/vsp1/vsp1_wpf.c
index 23c8f706b3f2..c2a1a7f97e26 100644
--- a/drivers/media/platform/vsp1/vsp1_wpf.c
+++ b/drivers/media/platform/vsp1/vsp1_wpf.c
@@ -141,13 +141,13 @@ static int wpf_init_controls(struct vsp1_rwpf *wpf)
 	if (wpf->entity.index != 0) {
 		/* Only WPF0 supports flipping. */
 		num_flip_ctrls = 0;
-	} else if (vsp1->info->features & VSP1_HAS_WPF_HFLIP) {
+	} else if (vsp1_feature(vsp1, VSP1_HAS_WPF_HFLIP)) {
 		/*
 		 * When horizontal flip is supported the WPF implements three
 		 * controls (horizontal flip, vertical flip and rotation).
 		 */
 		num_flip_ctrls = 3;
-	} else if (vsp1->info->features & VSP1_HAS_WPF_VFLIP) {
+	} else if (vsp1_feature(vsp1, VSP1_HAS_WPF_VFLIP)) {
 		/*
 		 * When only vertical flip is supported the WPF implements a
 		 * single control (vertical flip).
@@ -276,7 +276,7 @@ static void wpf_configure_stream(struct vsp1_entity *entity,
 
 		vsp1_wpf_write(wpf, dlb, VI6_WPF_DSWAP, fmtinfo->swap);
 
-		if (vsp1->info->features & VSP1_HAS_WPF_HFLIP &&
+		if (vsp1_feature(vsp1, VSP1_HAS_WPF_HFLIP) &&
 		    wpf->entity.index == 0)
 			vsp1_wpf_write(wpf, dlb, VI6_WPF_ROT_CTRL,
 				       VI6_WPF_ROT_CTRL_LN16 |
diff --git a/drivers/media/radio/radio-wl1273.c b/drivers/media/radio/radio-wl1273.c
index 8f9f8dfc3497..11aa94f189cb 100644
--- a/drivers/media/radio/radio-wl1273.c
+++ b/drivers/media/radio/radio-wl1273.c
@@ -1096,7 +1096,7 @@ static __poll_t wl1273_fm_fops_poll(struct file *file,
 	struct wl1273_core *core = radio->core;
 
 	if (radio->owner && radio->owner != file)
-		return -EBUSY;
+		return EPOLLERR;
 
 	radio->owner = file;
 
diff --git a/drivers/media/radio/si4713/radio-usb-si4713.c b/drivers/media/radio/si4713/radio-usb-si4713.c
index 05c66701a899..1ebbf0217142 100644
--- a/drivers/media/radio/si4713/radio-usb-si4713.c
+++ b/drivers/media/radio/si4713/radio-usb-si4713.c
@@ -370,9 +370,6 @@ static int si4713_transfer(struct i2c_adapter *i2c_adapter,
 	int retval = -EINVAL;
 	int i;
 
-	if (num <= 0)
-		return 0;
-
 	for (i = 0; i < num; i++) {
 		if (msgs[i].flags & I2C_M_RD)
 			retval = si4713_i2c_read(radio, msgs[i].buf, msgs[i].len);
diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c
index 81b150e5dfdb..8b97fd1f0cea 100644
--- a/drivers/media/rc/bpf-lirc.c
+++ b/drivers/media/rc/bpf-lirc.c
@@ -196,14 +196,16 @@ void lirc_bpf_run(struct rc_dev *rcdev, u32 sample)
  */
 void lirc_bpf_free(struct rc_dev *rcdev)
 {
-	struct bpf_prog **progs;
+	struct bpf_prog_array_item *item;
 
 	if (!rcdev->raw->progs)
 		return;
 
-	progs = rcu_dereference(rcdev->raw->progs)->progs;
-	while (*progs)
-		bpf_prog_put(*progs++);
+	item = rcu_dereference(rcdev->raw->progs)->items;
+	while (item->prog) {
+		bpf_prog_put(item->prog);
+		item++;
+	}
 
 	bpf_prog_array_free(rcdev->raw->progs);
 }
diff --git a/drivers/media/tuners/e4000.c b/drivers/media/tuners/e4000.c
index b5b9d87ba75c..fbec1a13dc6a 100644
--- a/drivers/media/tuners/e4000.c
+++ b/drivers/media/tuners/e4000.c
@@ -610,9 +610,9 @@ static int e4000_dvb_get_if_frequency(struct dvb_frontend *fe, u32 *frequency)
 
 static const struct dvb_tuner_ops e4000_dvb_tuner_ops = {
 	.info = {
-		.name           = "Elonics E4000",
-		.frequency_min  = 174000000,
-		.frequency_max  = 862000000,
+		.name              = "Elonics E4000",
+		.frequency_min_hz  = 174 * MHz,
+		.frequency_max_hz  = 862 * MHz,
 	},
 
 	.init = e4000_dvb_init,
diff --git a/drivers/media/tuners/fc0011.c b/drivers/media/tuners/fc0011.c
index 145407dee3db..a983899c6b0b 100644
--- a/drivers/media/tuners/fc0011.c
+++ b/drivers/media/tuners/fc0011.c
@@ -472,10 +472,10 @@ static int fc0011_get_bandwidth(struct dvb_frontend *fe, u32 *bandwidth)
 
 static const struct dvb_tuner_ops fc0011_tuner_ops = {
 	.info = {
-		.name		= "Fitipower FC0011",
+		.name		  = "Fitipower FC0011",
 
-		.frequency_min	= 45000000,
-		.frequency_max	= 1000000000,
+		.frequency_min_hz =   45 * MHz,
+		.frequency_max_hz = 1000 * MHz,
 	},
 
 	.release		= fc0011_release,
diff --git a/drivers/media/tuners/fc0012.c b/drivers/media/tuners/fc0012.c
index 625ac6f51c39..e992b98ae5bc 100644
--- a/drivers/media/tuners/fc0012.c
+++ b/drivers/media/tuners/fc0012.c
@@ -415,11 +415,10 @@ exit:
 
 static const struct dvb_tuner_ops fc0012_tuner_ops = {
 	.info = {
-		.name           = "Fitipower FC0012",
+		.name              = "Fitipower FC0012",
 
-		.frequency_min  = 37000000,	/* estimate */
-		.frequency_max  = 862000000,	/* estimate */
-		.frequency_step = 0,
+		.frequency_min_hz  =  37 * MHz,	/* estimate */
+		.frequency_max_hz  = 862 * MHz,	/* estimate */
 	},
 
 	.release	= fc0012_release,
diff --git a/drivers/media/tuners/fc0013.c b/drivers/media/tuners/fc0013.c
index e606118d1a9b..fc62afb1450d 100644
--- a/drivers/media/tuners/fc0013.c
+++ b/drivers/media/tuners/fc0013.c
@@ -574,11 +574,10 @@ exit:
 
 static const struct dvb_tuner_ops fc0013_tuner_ops = {
 	.info = {
-		.name		= "Fitipower FC0013",
+		.name		  = "Fitipower FC0013",
 
-		.frequency_min	= 37000000,	/* estimate */
-		.frequency_max	= 1680000000,	/* CHECK */
-		.frequency_step	= 0,
+		.frequency_min_hz =   37 * MHz,	/* estimate */
+		.frequency_max_hz = 1680 * MHz,	/* CHECK */
 	},
 
 	.release	= fc0013_release,
diff --git a/drivers/media/tuners/fc2580.c b/drivers/media/tuners/fc2580.c
index 743184ae0d26..db26892aac84 100644
--- a/drivers/media/tuners/fc2580.c
+++ b/drivers/media/tuners/fc2580.c
@@ -355,9 +355,9 @@ static int fc2580_dvb_get_if_frequency(struct dvb_frontend *fe, u32 *frequency)
 
 static const struct dvb_tuner_ops fc2580_dvb_tuner_ops = {
 	.info = {
-		.name           = "FCI FC2580",
-		.frequency_min  = 174000000,
-		.frequency_max  = 862000000,
+		.name             = "FCI FC2580",
+		.frequency_min_hz = 174 * MHz,
+		.frequency_max_hz = 862 * MHz,
 	},
 
 	.init = fc2580_dvb_init,
diff --git a/drivers/media/tuners/it913x.c b/drivers/media/tuners/it913x.c
index 27e5bc1c3cb5..b5eb39921e95 100644
--- a/drivers/media/tuners/it913x.c
+++ b/drivers/media/tuners/it913x.c
@@ -375,9 +375,9 @@ err:
 
 static const struct dvb_tuner_ops it913x_tuner_ops = {
 	.info = {
-		.name           = "ITE IT913X",
-		.frequency_min  = 174000000,
-		.frequency_max  = 862000000,
+		.name             = "ITE IT913X",
+		.frequency_min_hz = 174 * MHz,
+		.frequency_max_hz = 862 * MHz,
 	},
 
 	.init = it913x_init,
diff --git a/drivers/media/tuners/m88rs6000t.c b/drivers/media/tuners/m88rs6000t.c
index 9f3e0fd4cad9..3df2f23a40be 100644
--- a/drivers/media/tuners/m88rs6000t.c
+++ b/drivers/media/tuners/m88rs6000t.c
@@ -569,9 +569,9 @@ err:
 
 static const struct dvb_tuner_ops m88rs6000t_tuner_ops = {
 	.info = {
-		.name          = "Montage M88RS6000 Internal Tuner",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
+		.name             = "Montage M88RS6000 Internal Tuner",
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
 	},
 
 	.init = m88rs6000t_init,
diff --git a/drivers/media/tuners/max2165.c b/drivers/media/tuners/max2165.c
index 20ceb72e530b..721d8f722efb 100644
--- a/drivers/media/tuners/max2165.c
+++ b/drivers/media/tuners/max2165.c
@@ -377,10 +377,10 @@ static void max2165_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops max2165_tuner_ops = {
 	.info = {
-		.name           = "Maxim MAX2165",
-		.frequency_min  = 470000000,
-		.frequency_max  = 862000000,
-		.frequency_step =     50000,
+		.name              = "Maxim MAX2165",
+		.frequency_min_hz  = 470 * MHz,
+		.frequency_max_hz  = 862 * MHz,
+		.frequency_step_hz =  50 * kHz,
 	},
 
 	.release	   = max2165_release,
diff --git a/drivers/media/tuners/mc44s803.c b/drivers/media/tuners/mc44s803.c
index 403c6b2aa53b..2023e081d9ad 100644
--- a/drivers/media/tuners/mc44s803.c
+++ b/drivers/media/tuners/mc44s803.c
@@ -300,10 +300,10 @@ static int mc44s803_get_if_frequency(struct dvb_frontend *fe, u32 *frequency)
 
 static const struct dvb_tuner_ops mc44s803_tuner_ops = {
 	.info = {
-		.name           = "Freescale MC44S803",
-		.frequency_min  =   48000000,
-		.frequency_max  = 1000000000,
-		.frequency_step =     100000,
+		.name              = "Freescale MC44S803",
+		.frequency_min_hz  =   48 * MHz,
+		.frequency_max_hz  = 1000 * MHz,
+		.frequency_step_hz =  100 * kHz,
 	},
 
 	.release       = mc44s803_release,
diff --git a/drivers/media/tuners/mt2060.c b/drivers/media/tuners/mt2060.c
index 3d3c6815b6a7..4ace77cfe285 100644
--- a/drivers/media/tuners/mt2060.c
+++ b/drivers/media/tuners/mt2060.c
@@ -395,10 +395,10 @@ static void mt2060_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops mt2060_tuner_ops = {
 	.info = {
-		.name           = "Microtune MT2060",
-		.frequency_min  =  48000000,
-		.frequency_max  = 860000000,
-		.frequency_step =     50000,
+		.name              = "Microtune MT2060",
+		.frequency_min_hz  =  48 * MHz,
+		.frequency_max_hz  = 860 * MHz,
+		.frequency_step_hz =  50 * kHz,
 	},
 
 	.release       = mt2060_release,
diff --git a/drivers/media/tuners/mt2063.c b/drivers/media/tuners/mt2063.c
index 80dc3e241b4a..f4c8a7293ebb 100644
--- a/drivers/media/tuners/mt2063.c
+++ b/drivers/media/tuners/mt2063.c
@@ -2200,10 +2200,9 @@ static int mt2063_get_bandwidth(struct dvb_frontend *fe, u32 *bw)
 static const struct dvb_tuner_ops mt2063_ops = {
 	.info = {
 		 .name = "MT2063 Silicon Tuner",
-		 .frequency_min = 45000000,
-		 .frequency_max = 865000000,
-		 .frequency_step = 0,
-		 },
+		 .frequency_min_hz  =  45 * MHz,
+		 .frequency_max_hz  = 865 * MHz,
+	 },
 
 	.init = mt2063_init,
 	.sleep = MT2063_Sleep,
diff --git a/drivers/media/tuners/mt2131.c b/drivers/media/tuners/mt2131.c
index 659bf19dc434..086a7b7cf634 100644
--- a/drivers/media/tuners/mt2131.c
+++ b/drivers/media/tuners/mt2131.c
@@ -235,10 +235,10 @@ static void mt2131_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops mt2131_tuner_ops = {
 	.info = {
-		.name           = "Microtune MT2131",
-		.frequency_min  =  48000000,
-		.frequency_max  = 860000000,
-		.frequency_step =     50000,
+		.name              = "Microtune MT2131",
+		.frequency_min_hz  =  48 * MHz,
+		.frequency_max_hz  = 860 * MHz,
+		.frequency_step_hz =  50 * kHz,
 	},
 
 	.release       = mt2131_release,
diff --git a/drivers/media/tuners/mt2266.c b/drivers/media/tuners/mt2266.c
index f4545b7f5da2..e6cc78720de4 100644
--- a/drivers/media/tuners/mt2266.c
+++ b/drivers/media/tuners/mt2266.c
@@ -304,10 +304,10 @@ static void mt2266_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops mt2266_tuner_ops = {
 	.info = {
-		.name           = "Microtune MT2266",
-		.frequency_min  = 174000000,
-		.frequency_max  = 862000000,
-		.frequency_step =     50000,
+		.name              = "Microtune MT2266",
+		.frequency_min_hz  = 174 * MHz,
+		.frequency_max_hz  = 862 * MHz,
+		.frequency_step_hz =  50 * kHz,
 	},
 	.release       = mt2266_release,
 	.init          = mt2266_init,
diff --git a/drivers/media/tuners/mxl301rf.c b/drivers/media/tuners/mxl301rf.c
index 57b0e4862aaf..c628435a1b06 100644
--- a/drivers/media/tuners/mxl301rf.c
+++ b/drivers/media/tuners/mxl301rf.c
@@ -271,8 +271,8 @@ static const struct dvb_tuner_ops mxl301rf_ops = {
 	.info = {
 		.name = "MaxLinear MxL301RF",
 
-		.frequency_min =  93000000,
-		.frequency_max = 803142857,
+		.frequency_min_hz =  93 * MHz,
+		.frequency_max_hz = 803 * MHz + 142857,
 	},
 
 	.init = mxl301rf_init,
diff --git a/drivers/media/tuners/mxl5005s.c b/drivers/media/tuners/mxl5005s.c
index 355ef2959b7d..ec584316c812 100644
--- a/drivers/media/tuners/mxl5005s.c
+++ b/drivers/media/tuners/mxl5005s.c
@@ -4075,10 +4075,10 @@ static void mxl5005s_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops mxl5005s_tuner_ops = {
 	.info = {
-		.name           = "MaxLinear MXL5005S",
-		.frequency_min  =  48000000,
-		.frequency_max  = 860000000,
-		.frequency_step =     50000,
+		.name              = "MaxLinear MXL5005S",
+		.frequency_min_hz  =  48 * MHz,
+		.frequency_max_hz  = 860 * MHz,
+		.frequency_step_hz =  50 * kHz,
 	},
 
 	.release       = mxl5005s_release,
diff --git a/drivers/media/tuners/mxl5007t.c b/drivers/media/tuners/mxl5007t.c
index 4081fd97c3b2..54d9226aaff7 100644
--- a/drivers/media/tuners/mxl5007t.c
+++ b/drivers/media/tuners/mxl5007t.c
@@ -59,8 +59,6 @@ MODULE_PARM_DESC(debug, "set debug level");
 
 /* ------------------------------------------------------------------------- */
 
-#define MHz 1000000
-
 enum mxl5007t_mode {
 	MxL_MODE_ISDBT     =    0,
 	MxL_MODE_DVBT      =    1,
diff --git a/drivers/media/tuners/qm1d1b0004.c b/drivers/media/tuners/qm1d1b0004.c
index b4495cc1626b..008ad870c00f 100644
--- a/drivers/media/tuners/qm1d1b0004.c
+++ b/drivers/media/tuners/qm1d1b0004.c
@@ -186,8 +186,8 @@ static const struct dvb_tuner_ops qm1d1b0004_ops = {
 	.info = {
 		.name = "Sharp qm1d1b0004",
 
-		.frequency_min =  950000,
-		.frequency_max = 2150000,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
 	},
 
 	.init = qm1d1b0004_init,
diff --git a/drivers/media/tuners/qm1d1c0042.c b/drivers/media/tuners/qm1d1c0042.c
index 642a065b9a07..83ca5dc047ea 100644
--- a/drivers/media/tuners/qm1d1c0042.c
+++ b/drivers/media/tuners/qm1d1c0042.c
@@ -388,8 +388,8 @@ static const struct dvb_tuner_ops qm1d1c0042_ops = {
 	.info = {
 		.name = "Sharp QM1D1C0042",
 
-		.frequency_min =  950000,
-		.frequency_max = 2150000,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
 	},
 
 	.init = qm1d1c0042_init,
diff --git a/drivers/media/tuners/qt1010.c b/drivers/media/tuners/qt1010.c
index b92be882ab3c..4565c06b1617 100644
--- a/drivers/media/tuners/qt1010.c
+++ b/drivers/media/tuners/qt1010.c
@@ -394,10 +394,10 @@ static int qt1010_get_if_frequency(struct dvb_frontend *fe, u32 *frequency)
 
 static const struct dvb_tuner_ops qt1010_tuner_ops = {
 	.info = {
-		.name           = "Quantek QT1010",
-		.frequency_min  = QT1010_MIN_FREQ,
-		.frequency_max  = QT1010_MAX_FREQ,
-		.frequency_step = QT1010_STEP,
+		.name              = "Quantek QT1010",
+		.frequency_min_hz  = QT1010_MIN_FREQ,
+		.frequency_max_hz  = QT1010_MAX_FREQ,
+		.frequency_step_hz = QT1010_STEP,
 	},
 
 	.release       = qt1010_release,
diff --git a/drivers/media/tuners/qt1010_priv.h b/drivers/media/tuners/qt1010_priv.h
index 4cb78ecc8985..f25324c63067 100644
--- a/drivers/media/tuners/qt1010_priv.h
+++ b/drivers/media/tuners/qt1010_priv.h
@@ -71,12 +71,14 @@ reg def meaning
 2f  00  ? not used?
 */
 
-#define QT1010_STEP         125000 /*  125 kHz used by Windows drivers,
-				      hw could be more precise but we don't
-				      know how to use */
-#define QT1010_MIN_FREQ   48000000 /*   48 MHz */
-#define QT1010_MAX_FREQ  860000000 /*  860 MHz */
-#define QT1010_OFFSET   1246000000 /* 1246 MHz */
+#define QT1010_STEP         (125 * kHz) /*
+					 * used by Windows drivers,
+				         * hw could be more precise but we don't
+				         * know how to use
+					 */
+#define QT1010_MIN_FREQ   (48 * MHz)
+#define QT1010_MAX_FREQ  (860 * MHz)
+#define QT1010_OFFSET   (1246 * MHz)
 
 #define QT1010_WR 0
 #define QT1010_RD 1
diff --git a/drivers/media/tuners/r820t.c b/drivers/media/tuners/r820t.c
index 3e14b9e2e763..ba4be08a8551 100644
--- a/drivers/media/tuners/r820t.c
+++ b/drivers/media/tuners/r820t.c
@@ -2297,9 +2297,9 @@ static void r820t_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops r820t_tuner_ops = {
 	.info = {
-		.name           = "Rafael Micro R820T",
-		.frequency_min  =   42000000,
-		.frequency_max  = 1002000000,
+		.name             = "Rafael Micro R820T",
+		.frequency_min_hz =   42 * MHz,
+		.frequency_max_hz = 1002 * MHz,
 	},
 	.init = r820t_init,
 	.release = r820t_release,
diff --git a/drivers/media/tuners/si2157.c b/drivers/media/tuners/si2157.c
index 9e34d31d724d..a08d8fe2bb1b 100644
--- a/drivers/media/tuners/si2157.c
+++ b/drivers/media/tuners/si2157.c
@@ -387,9 +387,9 @@ static int si2157_get_if_frequency(struct dvb_frontend *fe, u32 *frequency)
 
 static const struct dvb_tuner_ops si2157_ops = {
 	.info = {
-		.name           = "Silicon Labs Si2141/Si2146/2147/2148/2157/2158",
-		.frequency_min  = 42000000,
-		.frequency_max  = 870000000,
+		.name             = "Silicon Labs Si2141/Si2146/2147/2148/2157/2158",
+		.frequency_min_hz =  42 * MHz,
+		.frequency_max_hz = 870 * MHz,
 	},
 
 	.init = si2157_init,
diff --git a/drivers/media/tuners/tda18212.c b/drivers/media/tuners/tda18212.c
index 7b8068354fea..8326106ec2e3 100644
--- a/drivers/media/tuners/tda18212.c
+++ b/drivers/media/tuners/tda18212.c
@@ -175,11 +175,11 @@ static int tda18212_get_if_frequency(struct dvb_frontend *fe, u32 *frequency)
 
 static const struct dvb_tuner_ops tda18212_tuner_ops = {
 	.info = {
-		.name           = "NXP TDA18212",
+		.name              = "NXP TDA18212",
 
-		.frequency_min  =  48000000,
-		.frequency_max  = 864000000,
-		.frequency_step =      1000,
+		.frequency_min_hz  =  48 * MHz,
+		.frequency_max_hz  = 864 * MHz,
+		.frequency_step_hz =   1 * kHz,
 	},
 
 	.set_params    = tda18212_set_params,
diff --git a/drivers/media/tuners/tda18218.c b/drivers/media/tuners/tda18218.c
index c56fcf5d48e3..cbbd4d5e15da 100644
--- a/drivers/media/tuners/tda18218.c
+++ b/drivers/media/tuners/tda18218.c
@@ -269,11 +269,11 @@ static void tda18218_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops tda18218_tuner_ops = {
 	.info = {
-		.name           = "NXP TDA18218",
+		.name              = "NXP TDA18218",
 
-		.frequency_min  = 174000000,
-		.frequency_max  = 864000000,
-		.frequency_step =      1000,
+		.frequency_min_hz  = 174 * MHz,
+		.frequency_max_hz  = 864 * MHz,
+		.frequency_step_hz =   1 * kHz,
 	},
 
 	.release       = tda18218_release,
diff --git a/drivers/media/tuners/tda18250.c b/drivers/media/tuners/tda18250.c
index 20d12b063380..20d10ef45ab6 100644
--- a/drivers/media/tuners/tda18250.c
+++ b/drivers/media/tuners/tda18250.c
@@ -740,9 +740,9 @@ static int tda18250_sleep(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops tda18250_ops = {
 	.info = {
-		.name           = "NXP TDA18250",
-		.frequency_min  = 42000000,
-		.frequency_max  = 870000000,
+		.name              = "NXP TDA18250",
+		.frequency_min_hz  =  42 * MHz,
+		.frequency_max_hz  = 870 * MHz,
 	},
 
 	.init = tda18250_init,
diff --git a/drivers/media/tuners/tda18271-fe.c b/drivers/media/tuners/tda18271-fe.c
index 147155553648..4d69029229e4 100644
--- a/drivers/media/tuners/tda18271-fe.c
+++ b/drivers/media/tuners/tda18271-fe.c
@@ -1240,9 +1240,9 @@ static int tda18271_set_config(struct dvb_frontend *fe, void *priv_cfg)
 static const struct dvb_tuner_ops tda18271_tuner_ops = {
 	.info = {
 		.name = "NXP TDA18271HD",
-		.frequency_min  =  45000000,
-		.frequency_max  = 864000000,
-		.frequency_step =     62500
+		.frequency_min_hz  =  45 * MHz,
+		.frequency_max_hz  = 864 * MHz,
+		.frequency_step_hz = 62500
 	},
 	.init              = tda18271_init,
 	.sleep             = tda18271_sleep,
diff --git a/drivers/media/tuners/tda827x.c b/drivers/media/tuners/tda827x.c
index 8400808f8f7f..4391dabba510 100644
--- a/drivers/media/tuners/tda827x.c
+++ b/drivers/media/tuners/tda827x.c
@@ -816,9 +816,9 @@ static int tda827x_initial_sleep(struct dvb_frontend *fe)
 static const struct dvb_tuner_ops tda827xo_tuner_ops = {
 	.info = {
 		.name = "Philips TDA827X",
-		.frequency_min  =  55000000,
-		.frequency_max  = 860000000,
-		.frequency_step =    250000
+		.frequency_min_hz  =  55 * MHz,
+		.frequency_max_hz  = 860 * MHz,
+		.frequency_step_hz = 250 * kHz
 	},
 	.release = tda827x_release,
 	.init = tda827x_initial_init,
@@ -832,9 +832,9 @@ static const struct dvb_tuner_ops tda827xo_tuner_ops = {
 static const struct dvb_tuner_ops tda827xa_tuner_ops = {
 	.info = {
 		.name = "Philips TDA827XA",
-		.frequency_min  =  44000000,
-		.frequency_max  = 906000000,
-		.frequency_step =     62500
+		.frequency_min_hz  =  44 * MHz,
+		.frequency_max_hz  = 906 * MHz,
+		.frequency_step_hz = 62500
 	},
 	.release = tda827x_release,
 	.init = tda827x_init,
diff --git a/drivers/media/tuners/tua9001.c b/drivers/media/tuners/tua9001.c
index 9d70378fe2d3..5c89a130b47d 100644
--- a/drivers/media/tuners/tua9001.c
+++ b/drivers/media/tuners/tua9001.c
@@ -164,9 +164,9 @@ static int tua9001_get_if_frequency(struct dvb_frontend *fe, u32 *frequency)
 
 static const struct dvb_tuner_ops tua9001_tuner_ops = {
 	.info = {
-		.name           = "Infineon TUA9001",
-		.frequency_min  = 170000000,
-		.frequency_max  = 862000000,
+		.name             = "Infineon TUA9001",
+		.frequency_min_hz = 170 * MHz,
+		.frequency_max_hz = 862 * MHz,
 	},
 
 	.init = tua9001_init,
diff --git a/drivers/media/tuners/tuner-simple.c b/drivers/media/tuners/tuner-simple.c
index 36b88f820239..29c1473f2e9f 100644
--- a/drivers/media/tuners/tuner-simple.c
+++ b/drivers/media/tuners/tuner-simple.c
@@ -670,6 +670,7 @@ static int simple_set_radio_freq(struct dvb_frontend *fe,
 	int rc, j;
 	struct tuner_params *t_params;
 	unsigned int freq = params->frequency;
+	bool mono = params->audmode == V4L2_TUNER_MODE_MONO;
 
 	tun = priv->tun;
 
@@ -736,8 +737,8 @@ static int simple_set_radio_freq(struct dvb_frontend *fe,
 			config |= TDA9887_PORT2_ACTIVE;
 		if (t_params->intercarrier_mode)
 			config |= TDA9887_INTERCARRIER;
-/*		if (t_params->port1_set_for_fm_mono)
-			config &= ~TDA9887_PORT1_ACTIVE;*/
+		if (t_params->port1_set_for_fm_mono && mono)
+			config &= ~TDA9887_PORT1_ACTIVE;
 		if (t_params->fm_gain_normal)
 			config |= TDA9887_GAIN_NORMAL;
 		if (t_params->radio_if == 2)
diff --git a/drivers/media/tuners/tuner-xc2028.c b/drivers/media/tuners/tuner-xc2028.c
index 84744e138982..aa6861dcd3fd 100644
--- a/drivers/media/tuners/tuner-xc2028.c
+++ b/drivers/media/tuners/tuner-xc2028.c
@@ -376,9 +376,8 @@ static int load_all_firmwares(struct dvb_frontend *fe,
 			tuner_err("Firmware type ");
 			dump_firm_type(type);
 			printk(KERN_CONT
-			       "(%x), id %llx is corrupted (size=%d, expected %d)\n",
-			       type, (unsigned long long)id,
-			       (unsigned)(endp - p), size);
+			       "(%x), id %llx is corrupted (size=%zd, expected %d)\n",
+			       type, (unsigned long long)id, (endp - p), size);
 			goto corrupt;
 		}
 
@@ -616,8 +615,8 @@ static int load_firmware(struct dvb_frontend *fe, unsigned int type,
 		}
 
 		if ((size + p > endp)) {
-			tuner_err("missing bytes: need %d, have %d\n",
-				   size, (int)(endp - p));
+			tuner_err("missing bytes: need %d, have %zd\n",
+				   size, (endp - p));
 			return -EINVAL;
 		}
 
@@ -1440,9 +1439,9 @@ unlock:
 static const struct dvb_tuner_ops xc2028_dvb_tuner_ops = {
 	.info = {
 		 .name = "Xceive XC3028",
-		 .frequency_min = 42000000,
-		 .frequency_max = 864000000,
-		 .frequency_step = 50000,
+		 .frequency_min_hz  =  42 * MHz,
+		 .frequency_max_hz  = 864 * MHz,
+		 .frequency_step_hz =  50 * kHz,
 		 },
 
 	.set_config	   = xc2028_set_config,
diff --git a/drivers/media/tuners/xc4000.c b/drivers/media/tuners/xc4000.c
index f0fa8da08afa..eb6d65dae748 100644
--- a/drivers/media/tuners/xc4000.c
+++ b/drivers/media/tuners/xc4000.c
@@ -398,8 +398,8 @@ static int xc_set_rf_frequency(struct xc4000_priv *priv, u32 freq_hz)
 
 	dprintk(1, "%s(%u)\n", __func__, freq_hz);
 
-	if ((freq_hz > xc4000_tuner_ops.info.frequency_max) ||
-	    (freq_hz < xc4000_tuner_ops.info.frequency_min))
+	if ((freq_hz > xc4000_tuner_ops.info.frequency_max_hz) ||
+	    (freq_hz < xc4000_tuner_ops.info.frequency_min_hz))
 		return -EINVAL;
 
 	freq_code = (u16)(freq_hz / 15625);
@@ -815,9 +815,9 @@ static int xc4000_fwupload(struct dvb_frontend *fe)
 		p += sizeof(size);
 
 		if (!size || size > endp - p) {
-			printk(KERN_ERR "Firmware type (%x), id %llx is corrupted (size=%d, expected %d)\n",
+			printk(KERN_ERR "Firmware type (%x), id %llx is corrupted (size=%zd, expected %d)\n",
 			       type, (unsigned long long)id,
-			       (unsigned)(endp - p), size);
+			       endp - p, size);
 			goto corrupt;
 		}
 
@@ -1635,10 +1635,10 @@ static void xc4000_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops xc4000_tuner_ops = {
 	.info = {
-		.name           = "Xceive XC4000",
-		.frequency_min  =    1000000,
-		.frequency_max  = 1023000000,
-		.frequency_step =      50000,
+		.name              = "Xceive XC4000",
+		.frequency_min_hz  =    1 * MHz,
+		.frequency_max_hz  = 1023 * MHz,
+		.frequency_step_hz =   50 * kHz,
 	},
 
 	.release	   = xc4000_release,
diff --git a/drivers/media/tuners/xc5000.c b/drivers/media/tuners/xc5000.c
index f7a8d05d1758..f6b65278e502 100644
--- a/drivers/media/tuners/xc5000.c
+++ b/drivers/media/tuners/xc5000.c
@@ -460,8 +460,8 @@ static int xc_set_rf_frequency(struct xc5000_priv *priv, u32 freq_hz)
 
 	dprintk(1, "%s(%u)\n", __func__, freq_hz);
 
-	if ((freq_hz > xc5000_tuner_ops.info.frequency_max) ||
-		(freq_hz < xc5000_tuner_ops.info.frequency_min))
+	if ((freq_hz > xc5000_tuner_ops.info.frequency_max_hz) ||
+		(freq_hz < xc5000_tuner_ops.info.frequency_min_hz))
 		return -EINVAL;
 
 	freq_code = (u16)(freq_hz / 15625);
@@ -1350,10 +1350,10 @@ static int xc5000_set_config(struct dvb_frontend *fe, void *priv_cfg)
 
 static const struct dvb_tuner_ops xc5000_tuner_ops = {
 	.info = {
-		.name           = "Xceive XC5000",
-		.frequency_min  =    1000000,
-		.frequency_max  = 1023000000,
-		.frequency_step =      50000,
+		.name              = "Xceive XC5000",
+		.frequency_min_hz  =    1 * MHz,
+		.frequency_max_hz  = 1023 * MHz,
+		.frequency_step_hz =   50 * kHz,
 	},
 
 	.release	   = xc5000_release,
diff --git a/drivers/media/usb/au0828/au0828-video.c b/drivers/media/usb/au0828/au0828-video.c
index 70e187971590..62b45062b1e6 100644
--- a/drivers/media/usb/au0828/au0828-video.c
+++ b/drivers/media/usb/au0828/au0828-video.c
@@ -133,7 +133,7 @@ static void au0828_irq_callback(struct urb *urb)
 		au0828_isocdbg("au0828_irq_callback called: status kill\n");
 		return;
 	default:            /* unknown error */
-		au0828_isocdbg("urb completition error %d.\n", urb->status);
+		au0828_isocdbg("urb completion error %d.\n", urb->status);
 		break;
 	}
 
diff --git a/drivers/media/usb/cx231xx/Kconfig b/drivers/media/usb/cx231xx/Kconfig
index 0f13192634c7..9e5b3e7c3ef5 100644
--- a/drivers/media/usb/cx231xx/Kconfig
+++ b/drivers/media/usb/cx231xx/Kconfig
@@ -15,7 +15,7 @@ config VIDEO_CX231XX
 
 config VIDEO_CX231XX_RC
 	bool "Conexant cx231xx Remote Controller additional support"
-	depends on RC_CORE
+	depends on RC_CORE=y || RC_CORE=VIDEO_CX231XX
 	depends on VIDEO_CX231XX
 	default y
 	---help---
diff --git a/drivers/media/usb/cx231xx/cx231xx-audio.c b/drivers/media/usb/cx231xx/cx231xx-audio.c
index c4a84fb930b6..32ee7b3f21c9 100644
--- a/drivers/media/usb/cx231xx/cx231xx-audio.c
+++ b/drivers/media/usb/cx231xx/cx231xx-audio.c
@@ -112,7 +112,7 @@ static void cx231xx_audio_isocirq(struct urb *urb)
 	case -ESHUTDOWN:
 		return;
 	default:		/* error */
-		dev_dbg(dev->dev, "urb completition error %d.\n",
+		dev_dbg(dev->dev, "urb completion error %d.\n",
 			urb->status);
 		break;
 	}
@@ -126,6 +126,7 @@ static void cx231xx_audio_isocirq(struct urb *urb)
 		stride = runtime->frame_bits >> 3;
 
 		for (i = 0; i < urb->number_of_packets; i++) {
+			unsigned long flags;
 			int length = urb->iso_frame_desc[i].actual_length /
 				     stride;
 			cp = (unsigned char *)urb->transfer_buffer +
@@ -148,7 +149,7 @@ static void cx231xx_audio_isocirq(struct urb *urb)
 				       length * stride);
 			}
 
-			snd_pcm_stream_lock(substream);
+			snd_pcm_stream_lock_irqsave(substream, flags);
 
 			dev->adev.hwptr_done_capture += length;
 			if (dev->adev.hwptr_done_capture >=
@@ -163,7 +164,7 @@ static void cx231xx_audio_isocirq(struct urb *urb)
 						runtime->period_size;
 				period_elapsed = 1;
 			}
-			snd_pcm_stream_unlock(substream);
+			snd_pcm_stream_unlock_irqrestore(substream, flags);
 		}
 		if (period_elapsed)
 			snd_pcm_period_elapsed(substream);
@@ -202,7 +203,7 @@ static void cx231xx_audio_bulkirq(struct urb *urb)
 	case -ESHUTDOWN:
 		return;
 	default:		/* error */
-		dev_dbg(dev->dev, "urb completition error %d.\n",
+		dev_dbg(dev->dev, "urb completion error %d.\n",
 			urb->status);
 		break;
 	}
@@ -216,6 +217,7 @@ static void cx231xx_audio_bulkirq(struct urb *urb)
 		stride = runtime->frame_bits >> 3;
 
 		if (1) {
+			unsigned long flags;
 			int length = urb->actual_length /
 				     stride;
 			cp = (unsigned char *)urb->transfer_buffer;
@@ -234,7 +236,7 @@ static void cx231xx_audio_bulkirq(struct urb *urb)
 				       length * stride);
 			}
 
-			snd_pcm_stream_lock(substream);
+			snd_pcm_stream_lock_irqsave(substream, flags);
 
 			dev->adev.hwptr_done_capture += length;
 			if (dev->adev.hwptr_done_capture >=
@@ -249,7 +251,7 @@ static void cx231xx_audio_bulkirq(struct urb *urb)
 						runtime->period_size;
 				period_elapsed = 1;
 			}
-			snd_pcm_stream_unlock(substream);
+			snd_pcm_stream_unlock_irqrestore(substream, flags);
 		}
 		if (period_elapsed)
 			snd_pcm_period_elapsed(substream);
diff --git a/drivers/media/usb/cx231xx/cx231xx-core.c b/drivers/media/usb/cx231xx/cx231xx-core.c
index 53d846dea3d2..493c2dca6244 100644
--- a/drivers/media/usb/cx231xx/cx231xx-core.c
+++ b/drivers/media/usb/cx231xx/cx231xx-core.c
@@ -799,6 +799,7 @@ static void cx231xx_isoc_irq_callback(struct urb *urb)
 	struct cx231xx_video_mode *vmode =
 	    container_of(dma_q, struct cx231xx_video_mode, vidq);
 	struct cx231xx *dev = container_of(vmode, struct cx231xx, video_mode);
+	unsigned long flags;
 	int i;
 
 	switch (urb->status) {
@@ -815,9 +816,9 @@ static void cx231xx_isoc_irq_callback(struct urb *urb)
 	}
 
 	/* Copy data from URB */
-	spin_lock(&dev->video_mode.slock);
+	spin_lock_irqsave(&dev->video_mode.slock, flags);
 	dev->video_mode.isoc_ctl.isoc_copy(dev, urb);
-	spin_unlock(&dev->video_mode.slock);
+	spin_unlock_irqrestore(&dev->video_mode.slock, flags);
 
 	/* Reset urb buffers */
 	for (i = 0; i < urb->number_of_packets; i++) {
@@ -844,6 +845,7 @@ static void cx231xx_bulk_irq_callback(struct urb *urb)
 	struct cx231xx_video_mode *vmode =
 	    container_of(dma_q, struct cx231xx_video_mode, vidq);
 	struct cx231xx *dev = container_of(vmode, struct cx231xx, video_mode);
+	unsigned long flags;
 
 	switch (urb->status) {
 	case 0:		/* success */
@@ -862,9 +864,9 @@ static void cx231xx_bulk_irq_callback(struct urb *urb)
 	}
 
 	/* Copy data from URB */
-	spin_lock(&dev->video_mode.slock);
+	spin_lock_irqsave(&dev->video_mode.slock, flags);
 	dev->video_mode.bulk_ctl.bulk_copy(dev, urb);
-	spin_unlock(&dev->video_mode.slock);
+	spin_unlock_irqrestore(&dev->video_mode.slock, flags);
 
 	/* Reset urb buffers */
 	urb->status = usb_submit_urb(urb, GFP_ATOMIC);
diff --git a/drivers/media/usb/cx231xx/cx231xx-i2c.c b/drivers/media/usb/cx231xx/cx231xx-i2c.c
index 6e1bef2a45bb..15a91169e749 100644
--- a/drivers/media/usb/cx231xx/cx231xx-i2c.c
+++ b/drivers/media/usb/cx231xx/cx231xx-i2c.c
@@ -376,8 +376,6 @@ static int cx231xx_i2c_xfer(struct i2c_adapter *i2c_adap,
 	struct cx231xx *dev = bus->dev;
 	int addr, rc, i, byte;
 
-	if (num <= 0)
-		return 0;
 	mutex_lock(&dev->i2c_lock);
 	for (i = 0; i < num; i++) {
 
diff --git a/drivers/media/usb/cx231xx/cx231xx-vbi.c b/drivers/media/usb/cx231xx/cx231xx-vbi.c
index b621cf1aa96b..10b2eb7338ad 100644
--- a/drivers/media/usb/cx231xx/cx231xx-vbi.c
+++ b/drivers/media/usb/cx231xx/cx231xx-vbi.c
@@ -305,6 +305,7 @@ static void cx231xx_irq_vbi_callback(struct urb *urb)
 	struct cx231xx_video_mode *vmode =
 	    container_of(dma_q, struct cx231xx_video_mode, vidq);
 	struct cx231xx *dev = container_of(vmode, struct cx231xx, vbi_mode);
+	unsigned long flags;
 
 	switch (urb->status) {
 	case 0:		/* success */
@@ -316,14 +317,14 @@ static void cx231xx_irq_vbi_callback(struct urb *urb)
 		return;
 	default:		/* error */
 		dev_err(dev->dev,
-			"urb completition error %d.\n",	urb->status);
+			"urb completion error %d.\n", urb->status);
 		break;
 	}
 
 	/* Copy data from URB */
-	spin_lock(&dev->vbi_mode.slock);
+	spin_lock_irqsave(&dev->vbi_mode.slock, flags);
 	dev->vbi_mode.bulk_ctl.bulk_copy(dev, urb);
-	spin_unlock(&dev->vbi_mode.slock);
+	spin_unlock_irqrestore(&dev->vbi_mode.slock, flags);
 
 	/* Reset status */
 	urb->status = 0;
diff --git a/drivers/media/usb/dvb-usb-v2/Kconfig b/drivers/media/usb/dvb-usb-v2/Kconfig
index 082b8d67244b..df4412245a8a 100644
--- a/drivers/media/usb/dvb-usb-v2/Kconfig
+++ b/drivers/media/usb/dvb-usb-v2/Kconfig
@@ -96,10 +96,13 @@ config DVB_USB_GL861
 	tristate "Genesys Logic GL861 USB2.0 support"
 	depends on DVB_USB_V2
 	select DVB_ZL10353 if MEDIA_SUBDRV_AUTOSELECT
+	select DVB_TC90522 if MEDIA_SUBDRV_AUTOSELECT
 	select MEDIA_TUNER_QT1010 if MEDIA_SUBDRV_AUTOSELECT
+	select DVB_PLL if MEDIA_SUBDRV_AUTOSELECT
 	help
 	  Say Y here to support the MSI Megasky 580 (55801) DVB-T USB2.0
-	  receiver with USB ID 0db0:5581.
+	  receiver with USB ID 0db0:5581, Friio White ISDB-T receiver
+	  with USB ID 0x7a69:0001.
 
 config DVB_USB_LME2510
 	tristate "LME DM04/QQBOX DVB-S USB2.0 support"
diff --git a/drivers/media/usb/dvb-usb-v2/gl861.c b/drivers/media/usb/dvb-usb-v2/gl861.c
index 9d154fdae45b..3338b21d8b25 100644
--- a/drivers/media/usb/dvb-usb-v2/gl861.c
+++ b/drivers/media/usb/dvb-usb-v2/gl861.c
@@ -6,10 +6,14 @@
  *
  * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
  */
+#include <linux/string.h>
+
 #include "gl861.h"
 
 #include "zl10353.h"
 #include "qt1010.h"
+#include "tc90522.h"
+#include "dvb-pll.h"
 
 DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
 
@@ -26,10 +30,14 @@ static int gl861_i2c_msg(struct dvb_usb_device *d, u8 addr,
 	if (wo) {
 		req = GL861_REQ_I2C_WRITE;
 		type = GL861_WRITE;
+		buf = kmemdup(wbuf, wlen, GFP_KERNEL);
 	} else { /* rw */
 		req = GL861_REQ_I2C_READ;
 		type = GL861_READ;
+		buf = kmalloc(rlen, GFP_KERNEL);
 	}
+	if (!buf)
+		return -ENOMEM;
 
 	switch (wlen) {
 	case 1:
@@ -42,24 +50,19 @@ static int gl861_i2c_msg(struct dvb_usb_device *d, u8 addr,
 	default:
 		dev_err(&d->udev->dev, "%s: wlen=%d, aborting\n",
 				KBUILD_MODNAME, wlen);
+		kfree(buf);
 		return -EINVAL;
 	}
-	buf = NULL;
-	if (rlen > 0) {
-		buf = kmalloc(rlen, GFP_KERNEL);
-		if (!buf)
-			return -ENOMEM;
-	}
+
 	usleep_range(1000, 2000); /* avoid I2C errors */
 
 	ret = usb_control_msg(d->udev, usb_rcvctrlpipe(d->udev, 0), req, type,
 			      value, index, buf, rlen, 2000);
-	if (rlen > 0) {
-		if (ret > 0)
-			memcpy(rbuf, buf, rlen);
-		kfree(buf);
-	}
 
+	if (!wo && ret > 0)
+		memcpy(rbuf, buf, rlen);
+
+	kfree(buf);
 	return ret;
 }
 
@@ -162,11 +165,478 @@ static struct dvb_usb_device_properties gl861_props = {
 	}
 };
 
+
+/*
+ * For Friio
+ */
+
+struct friio_priv {
+	struct i2c_adapter *demod_sub_i2c;
+	struct i2c_client  *i2c_client_demod;
+	struct i2c_client  *i2c_client_tuner;
+	struct i2c_adapter tuner_adap;
+};
+
+struct friio_config {
+	struct i2c_board_info demod_info;
+	struct tc90522_config demod_cfg;
+
+	struct i2c_board_info tuner_info;
+	struct dvb_pll_config tuner_cfg;
+};
+
+static const struct friio_config friio_config = {
+	.demod_info = { I2C_BOARD_INFO(TC90522_I2C_DEV_TER, 0x18), },
+	.tuner_info = { I2C_BOARD_INFO("tua6034_friio", 0x60), },
+};
+
+/* For another type of I2C:
+ * message sent by a USB control-read/write transaction with data stage.
+ * Used in init/config of Friio.
+ */
+static int
+gl861_i2c_write_ex(struct dvb_usb_device *d, u8 addr, u8 *wbuf, u16 wlen)
+{
+	u8 *buf;
+	int ret;
+
+	buf = kmalloc(wlen, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	memcpy(buf, wbuf, wlen);
+	ret = usb_control_msg(d->udev, usb_sndctrlpipe(d->udev, 0),
+				 GL861_REQ_I2C_RAW, GL861_WRITE,
+				 addr << (8 + 1), 0x0100, buf, wlen, 2000);
+	kfree(buf);
+	return ret;
+}
+
+static int
+gl861_i2c_read_ex(struct dvb_usb_device *d, u8 addr, u8 *rbuf, u16 rlen)
+{
+	u8 *buf;
+	int ret;
+
+	buf = kmalloc(rlen, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = usb_control_msg(d->udev, usb_rcvctrlpipe(d->udev, 0),
+				 GL861_REQ_I2C_READ, GL861_READ,
+				 addr << (8 + 1), 0x0100, buf, rlen, 2000);
+	if (ret > 0 && rlen > 0)
+		memcpy(buf, rbuf, rlen);
+	kfree(buf);
+	return ret;
+}
+
+/* For I2C transactions to the tuner of Friio (dvb_pll).
+ *
+ * Friio uses irregular USB encapsulation for tuner i2c transactions:
+ * write transacions are encapsulated with a different USB 'request' value.
+ *
+ * Although all transactions are sent via the demod(tc90522)
+ * and the demod provides an i2c adapter for them, it cannot be used in Friio
+ * since it assumes using the same parent adapter with the demod,
+ * which does not use the request value and uses same one for both read/write.
+ * So we define a dedicated i2c adapter here.
+ */
+
+static int
+friio_i2c_tuner_read(struct dvb_usb_device *d, struct i2c_msg *msg)
+{
+	struct friio_priv *priv;
+	u8 addr;
+
+	priv = d_to_priv(d);
+	addr = priv->i2c_client_demod->addr;
+	return gl861_i2c_read_ex(d, addr, msg->buf, msg->len);
+}
+
+static int
+friio_i2c_tuner_write(struct dvb_usb_device *d, struct i2c_msg *msg)
+{
+	u8 *buf;
+	int ret;
+	struct friio_priv *priv;
+
+	priv = d_to_priv(d);
+
+	if (msg->len < 1)
+		return -EINVAL;
+
+	buf = kmalloc(msg->len + 1, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+	buf[0] = msg->addr << 1;
+	memcpy(buf + 1, msg->buf, msg->len);
+
+	ret = usb_control_msg(d->udev, usb_sndctrlpipe(d->udev, 0),
+				 GL861_REQ_I2C_RAW, GL861_WRITE,
+				 priv->i2c_client_demod->addr << (8 + 1),
+				 0xFE, buf, msg->len + 1, 2000);
+	kfree(buf);
+	return ret;
+}
+
+static int friio_tuner_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[],
+				int num)
+{
+	struct dvb_usb_device *d = i2c_get_adapdata(adap);
+	int i;
+
+	if (num > 2)
+		return -EINVAL;
+
+	if (mutex_lock_interruptible(&d->i2c_mutex) < 0)
+		return -EAGAIN;
+
+	for (i = 0; i < num; i++) {
+		int ret;
+
+		if (msg[i].flags & I2C_M_RD)
+			ret = friio_i2c_tuner_read(d, &msg[i]);
+		else
+			ret = friio_i2c_tuner_write(d, &msg[i]);
+
+		if (ret < 0)
+			break;
+
+		usleep_range(1000, 2000); /* avoid I2C errors */
+	}
+
+	mutex_unlock(&d->i2c_mutex);
+	return i;
+}
+
+static struct i2c_algorithm friio_tuner_i2c_algo = {
+	.master_xfer   = friio_tuner_i2c_xfer,
+	.functionality = gl861_i2c_func,
+};
+
+/* GPIO control in Friio */
+
+#define FRIIO_CTL_LNB (1 << 0)
+#define FRIIO_CTL_STROBE (1 << 1)
+#define FRIIO_CTL_CLK (1 << 2)
+#define FRIIO_CTL_LED (1 << 3)
+
+#define FRIIO_LED_RUNNING 0x6400ff64
+#define FRIIO_LED_STOPPED 0x96ff00ff
+
+/* control PIC16F676 attached to Friio */
+static int friio_ext_ctl(struct dvb_usb_device *d,
+			    u32 sat_color, int power_on)
+{
+	int i, ret;
+	struct i2c_msg msg;
+	u8 *buf;
+	u32 mask;
+	u8 power = (power_on) ? FRIIO_CTL_LNB : 0;
+
+	buf = kmalloc(2, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	msg.addr = 0x00;
+	msg.flags = 0;
+	msg.len = 2;
+	msg.buf = buf;
+	buf[0] = 0x00;
+
+	/* send 2bit header (&B10) */
+	buf[1] = power | FRIIO_CTL_LED | FRIIO_CTL_STROBE;
+	ret = i2c_transfer(&d->i2c_adap, &msg, 1);
+	buf[1] |= FRIIO_CTL_CLK;
+	ret += i2c_transfer(&d->i2c_adap, &msg, 1);
+
+	buf[1] = power | FRIIO_CTL_STROBE;
+	ret += i2c_transfer(&d->i2c_adap, &msg, 1);
+	buf[1] |= FRIIO_CTL_CLK;
+	ret += i2c_transfer(&d->i2c_adap, &msg, 1);
+
+	/* send 32bit(satur, R, G, B) data in serial */
+	mask = 1 << 31;
+	for (i = 0; i < 32; i++) {
+		buf[1] = power | FRIIO_CTL_STROBE;
+		if (sat_color & mask)
+			buf[1] |= FRIIO_CTL_LED;
+		ret += i2c_transfer(&d->i2c_adap, &msg, 1);
+		buf[1] |= FRIIO_CTL_CLK;
+		ret += i2c_transfer(&d->i2c_adap, &msg, 1);
+		mask >>= 1;
+	}
+
+	/* set the strobe off */
+	buf[1] = power;
+	ret += i2c_transfer(&d->i2c_adap, &msg, 1);
+	buf[1] |= FRIIO_CTL_CLK;
+	ret += i2c_transfer(&d->i2c_adap, &msg, 1);
+
+	kfree(buf);
+	return (ret == 70) ? 0 : -EREMOTEIO;
+}
+
+/* init/config of gl861 for Friio */
+/* NOTE:
+ * This function cannot be moved to friio_init()/dvb_usbv2_init(),
+ * because the init defined here must be done before any activities like I2C,
+ * but friio_init() is called by dvb-usbv2 after {_frontend, _tuner}_attach(),
+ * where I2C communication is used.
+ * Thus this function is set to be called from _power_ctl().
+ *
+ * Since it will be called on the early init stage
+ * where the i2c adapter is not initialized yet,
+ * we cannot use i2c_transfer() here.
+ */
+static int friio_reset(struct dvb_usb_device *d)
+{
+	int i, ret;
+	u8 wbuf[2], rbuf[2];
+
+	static const u8 friio_init_cmds[][2] = {
+		{0x33, 0x08}, {0x37, 0x40}, {0x3a, 0x1f}, {0x3b, 0xff},
+		{0x3c, 0x1f}, {0x3d, 0xff}, {0x38, 0x00}, {0x35, 0x00},
+		{0x39, 0x00}, {0x36, 0x00},
+	};
+
+	ret = usb_set_interface(d->udev, 0, 0);
+	if (ret < 0)
+		return ret;
+
+	wbuf[0] = 0x11;
+	wbuf[1] = 0x02;
+	ret = gl861_i2c_msg(d, 0x00, wbuf, 2, NULL, 0);
+	if (ret < 0)
+		return ret;
+	usleep_range(2000, 3000);
+
+	wbuf[0] = 0x11;
+	wbuf[1] = 0x00;
+	ret = gl861_i2c_msg(d, 0x00, wbuf, 2, NULL, 0);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Check if the dev is really a Friio White, since it might be
+	 * another device, Friio Black, with the same VID/PID.
+	 */
+
+	usleep_range(1000, 2000);
+	wbuf[0] = 0x03;
+	wbuf[1] = 0x80;
+	ret = gl861_i2c_write_ex(d, 0x09, wbuf, 2);
+	if (ret < 0)
+		return ret;
+
+	usleep_range(2000, 3000);
+	ret = gl861_i2c_read_ex(d, 0x09, rbuf, 2);
+	if (ret < 0)
+		return ret;
+	if (rbuf[0] != 0xff || rbuf[1] != 0xff)
+		return -ENODEV;
+
+
+	usleep_range(1000, 2000);
+	ret = gl861_i2c_write_ex(d, 0x48, wbuf, 2);
+	if (ret < 0)
+		return ret;
+
+	usleep_range(2000, 3000);
+	ret = gl861_i2c_read_ex(d, 0x48, rbuf, 2);
+	if (ret < 0)
+		return ret;
+	if (rbuf[0] != 0xff || rbuf[1] != 0xff)
+		return -ENODEV;
+
+	wbuf[0] = 0x30;
+	wbuf[1] = 0x04;
+	ret = gl861_i2c_msg(d, 0x00, wbuf, 2, NULL, 0);
+	if (ret < 0)
+		return ret;
+
+	wbuf[0] = 0x00;
+	wbuf[1] = 0x01;
+	ret = gl861_i2c_msg(d, 0x00, wbuf, 2, NULL, 0);
+	if (ret < 0)
+		return ret;
+
+	wbuf[0] = 0x06;
+	wbuf[1] = 0x0f;
+	ret = gl861_i2c_msg(d, 0x00, wbuf, 2, NULL, 0);
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; i < ARRAY_SIZE(friio_init_cmds); i++) {
+		ret = gl861_i2c_msg(d, 0x00, (u8 *)friio_init_cmds[i], 2,
+				      NULL, 0);
+		if (ret < 0)
+			return ret;
+	}
+	return 0;
+}
+
+/*
+ * DVB callbacks for Friio
+ */
+
+static int friio_power_ctrl(struct dvb_usb_device *d, int onoff)
+{
+	return onoff ? friio_reset(d) : 0;
+}
+
+static int friio_frontend_attach(struct dvb_usb_adapter *adap)
+{
+	const struct i2c_board_info *info;
+	struct dvb_usb_device *d;
+	struct tc90522_config cfg;
+	struct i2c_client *cl;
+	struct friio_priv *priv;
+
+	info = &friio_config.demod_info;
+	d = adap_to_d(adap);
+	cl = dvb_module_probe("tc90522", info->type,
+			      &d->i2c_adap, info->addr, &cfg);
+	if (!cl)
+		return -ENODEV;
+	adap->fe[0] = cfg.fe;
+
+	/* ignore cfg.tuner_i2c and create new one */
+	priv = adap_to_priv(adap);
+	priv->i2c_client_demod = cl;
+	priv->tuner_adap.algo = &friio_tuner_i2c_algo;
+	priv->tuner_adap.dev.parent = &d->udev->dev;
+	strlcpy(priv->tuner_adap.name, d->name, sizeof(priv->tuner_adap.name));
+	strlcat(priv->tuner_adap.name, "-tuner", sizeof(priv->tuner_adap.name));
+	priv->demod_sub_i2c = &priv->tuner_adap;
+	i2c_set_adapdata(&priv->tuner_adap, d);
+
+	return i2c_add_adapter(&priv->tuner_adap);
+}
+
+static int friio_frontend_detach(struct dvb_usb_adapter *adap)
+{
+	struct friio_priv *priv;
+
+	priv = adap_to_priv(adap);
+	i2c_del_adapter(&priv->tuner_adap);
+	dvb_module_release(priv->i2c_client_demod);
+	return 0;
+}
+
+static int friio_tuner_attach(struct dvb_usb_adapter *adap)
+{
+	const struct i2c_board_info *info;
+	struct dvb_pll_config cfg;
+	struct i2c_client *cl;
+	struct friio_priv *priv;
+
+	priv = adap_to_priv(adap);
+	info = &friio_config.tuner_info;
+	cfg = friio_config.tuner_cfg;
+	cfg.fe = adap->fe[0];
+
+	cl = dvb_module_probe("dvb_pll", info->type,
+			      priv->demod_sub_i2c, info->addr, &cfg);
+	if (!cl)
+		return -ENODEV;
+	priv->i2c_client_tuner = cl;
+	return 0;
+}
+
+static int friio_tuner_detach(struct dvb_usb_adapter *adap)
+{
+	struct friio_priv *priv;
+
+	priv = adap_to_priv(adap);
+	dvb_module_release(priv->i2c_client_tuner);
+	return 0;
+}
+
+static int friio_init(struct dvb_usb_device *d)
+{
+	int i;
+	int ret;
+	struct friio_priv *priv;
+
+	static const u8 demod_init[][2] = {
+		{0x01, 0x40}, {0x04, 0x38}, {0x05, 0x40}, {0x07, 0x40},
+		{0x0f, 0x4f}, {0x11, 0x21}, {0x12, 0x0b}, {0x13, 0x2f},
+		{0x14, 0x31}, {0x16, 0x02}, {0x21, 0xc4}, {0x22, 0x20},
+		{0x2c, 0x79}, {0x2d, 0x34}, {0x2f, 0x00}, {0x30, 0x28},
+		{0x31, 0x31}, {0x32, 0xdf}, {0x38, 0x01}, {0x39, 0x78},
+		{0x3b, 0x33}, {0x3c, 0x33}, {0x48, 0x90}, {0x51, 0x68},
+		{0x5e, 0x38}, {0x71, 0x00}, {0x72, 0x08}, {0x77, 0x00},
+		{0xc0, 0x21}, {0xc1, 0x10}, {0xe4, 0x1a}, {0xea, 0x1f},
+		{0x77, 0x00}, {0x71, 0x00}, {0x71, 0x00}, {0x76, 0x0c},
+	};
+
+	/* power on LNA? */
+	ret = friio_ext_ctl(d, FRIIO_LED_STOPPED, true);
+	if (ret < 0)
+		return ret;
+	msleep(20);
+
+	/* init/config demod */
+	priv = d_to_priv(d);
+	for (i = 0; i < ARRAY_SIZE(demod_init); i++) {
+		int ret;
+
+		ret = i2c_master_send(priv->i2c_client_demod, demod_init[i], 2);
+		if (ret < 0)
+			return ret;
+	}
+	msleep(100);
+	return 0;
+}
+
+static void friio_exit(struct dvb_usb_device *d)
+{
+	friio_ext_ctl(d, FRIIO_LED_STOPPED, false);
+}
+
+static int friio_streaming_ctrl(struct dvb_frontend *fe, int onoff)
+{
+	u32 led_color;
+
+	led_color = onoff ? FRIIO_LED_RUNNING : FRIIO_LED_STOPPED;
+	return friio_ext_ctl(fe_to_d(fe), led_color, true);
+}
+
+
+static struct dvb_usb_device_properties friio_props = {
+	.driver_name = KBUILD_MODNAME,
+	.owner = THIS_MODULE,
+	.adapter_nr = adapter_nr,
+
+	.size_of_priv = sizeof(struct friio_priv),
+
+	.i2c_algo = &gl861_i2c_algo,
+	.power_ctrl = friio_power_ctrl,
+	.frontend_attach = friio_frontend_attach,
+	.frontend_detach = friio_frontend_detach,
+	.tuner_attach = friio_tuner_attach,
+	.tuner_detach = friio_tuner_detach,
+	.init = friio_init,
+	.exit = friio_exit,
+	.streaming_ctrl = friio_streaming_ctrl,
+
+	.num_adapters = 1,
+	.adapter = {
+		{
+			.stream = DVB_USB_STREAM_BULK(0x01, 8, 16384),
+		}
+	}
+};
+
 static const struct usb_device_id gl861_id_table[] = {
 	{ DVB_USB_DEVICE(USB_VID_MSI, USB_PID_MSI_MEGASKY580_55801,
 		&gl861_props, "MSI Mega Sky 55801 DVB-T USB2.0", NULL) },
 	{ DVB_USB_DEVICE(USB_VID_ALINK, USB_VID_ALINK_DTU,
 		&gl861_props, "A-LINK DTU DVB-T USB2.0", NULL) },
+	{ DVB_USB_DEVICE(USB_VID_774, USB_PID_FRIIO_WHITE,
+		&friio_props, "774 Friio White ISDB-T USB2.0", NULL) },
 	{ }
 };
 MODULE_DEVICE_TABLE(usb, gl861_id_table);
diff --git a/drivers/media/usb/dvb-usb-v2/gl861.h b/drivers/media/usb/dvb-usb-v2/gl861.h
index b651b857e034..02c00e10748a 100644
--- a/drivers/media/usb/dvb-usb-v2/gl861.h
+++ b/drivers/media/usb/dvb-usb-v2/gl861.h
@@ -9,5 +9,6 @@
 
 #define GL861_REQ_I2C_WRITE	0x01
 #define GL861_REQ_I2C_READ	0x02
+#define GL861_REQ_I2C_RAW	0x03
 
 #endif
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c
index 221cf46b4140..9f74453799a2 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c
@@ -554,9 +554,9 @@ static const struct dvb_frontend_ops mxl111sf_demod_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name               = "MaxLinear MxL111SF DVB-T demodulator",
-		.frequency_min      = 177000000,
-		.frequency_max      = 858000000,
-		.frequency_stepsize = 166666,
+		.frequency_min_hz      = 177 * MHz,
+		.frequency_max_hz      = 858 * MHz,
+		.frequency_stepsize_hz = 166666,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 			FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_64 |
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c
index 240d736bf1bb..92b3b9221a21 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c
@@ -465,9 +465,9 @@ static const struct dvb_tuner_ops mxl111sf_tuner_tuner_ops = {
 	.info = {
 		.name = "MaxLinear MxL111SF",
 #if 0
-		.frequency_min  = ,
-		.frequency_max  = ,
-		.frequency_step = ,
+		.frequency_min_hz  = ,
+		.frequency_max_hz  = ,
+		.frequency_step_hz = ,
 #endif
 	},
 #if 0
diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
index c76e78f9638a..a970224a94bd 100644
--- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
+++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
@@ -1732,7 +1732,7 @@ static int rtl2832u_rc_query(struct dvb_usb_device *d)
 		goto exit;
 
 	ret = rtl28xxu_rd_reg(d, IR_RX_BC, &buf[0]);
-	if (ret)
+	if (ret || buf[0] > sizeof(buf))
 		goto err;
 
 	len = buf[0];
diff --git a/drivers/media/usb/dvb-usb-v2/usb_urb.c b/drivers/media/usb/dvb-usb-v2/usb_urb.c
index b0499f95ec45..024c751eb165 100644
--- a/drivers/media/usb/dvb-usb-v2/usb_urb.c
+++ b/drivers/media/usb/dvb-usb-v2/usb_urb.c
@@ -40,7 +40,7 @@ static void usb_urb_complete(struct urb *urb)
 		return;
 	default:        /* error */
 		dev_dbg_ratelimited(&stream->udev->dev,
-				"%s: urb completition failed=%d\n",
+				"%s: urb completion failed=%d\n",
 				__func__, urb->status);
 		break;
 	}
@@ -69,7 +69,7 @@ static void usb_urb_complete(struct urb *urb)
 		break;
 	default:
 		dev_err(&stream->udev->dev,
-				"%s: unknown endpoint type in completition handler\n",
+				"%s: unknown endpoint type in completion handler\n",
 				KBUILD_MODNAME);
 		return;
 	}
diff --git a/drivers/media/usb/dvb-usb/Kconfig b/drivers/media/usb/dvb-usb/Kconfig
index b8a1c62a0682..513df955eaa3 100644
--- a/drivers/media/usb/dvb-usb/Kconfig
+++ b/drivers/media/usb/dvb-usb/Kconfig
@@ -312,12 +312,6 @@ config DVB_USB_DTV5100
 	help
 	  Say Y here to support the AME DTV-5100 USB2.0 DVB-T receiver.
 
-config DVB_USB_FRIIO
-	tristate "Friio ISDB-T USB2.0 Receiver support"
-	depends on DVB_USB
-	help
-	  Say Y here to support the Japanese DTV receiver Friio.
-
 config DVB_USB_AZ6027
 	tristate "Azurewave DVB-S/S2 USB2.0 AZ6027 support"
 	depends on DVB_USB
diff --git a/drivers/media/usb/dvb-usb/Makefile b/drivers/media/usb/dvb-usb/Makefile
index 9ad2618408ef..407d90ca8be0 100644
--- a/drivers/media/usb/dvb-usb/Makefile
+++ b/drivers/media/usb/dvb-usb/Makefile
@@ -71,9 +71,6 @@ obj-$(CONFIG_DVB_USB_DTV5100) += dvb-usb-dtv5100.o
 dvb-usb-cinergyT2-objs := cinergyT2-core.o cinergyT2-fe.o
 obj-$(CONFIG_DVB_USB_CINERGY_T2) += dvb-usb-cinergyT2.o
 
-dvb-usb-friio-objs := friio.o friio-fe.o
-obj-$(CONFIG_DVB_USB_FRIIO) += dvb-usb-friio.o
-
 dvb-usb-az6027-objs := az6027.o
 obj-$(CONFIG_DVB_USB_AZ6027) += dvb-usb-az6027.o
 
diff --git a/drivers/media/usb/dvb-usb/af9005-fe.c b/drivers/media/usb/dvb-usb/af9005-fe.c
index 7fbbc954da16..09cc3a21af65 100644
--- a/drivers/media/usb/dvb-usb/af9005-fe.c
+++ b/drivers/media/usb/dvb-usb/af9005-fe.c
@@ -1455,9 +1455,9 @@ static const struct dvb_frontend_ops af9005_fe_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		 .name = "AF9005 USB DVB-T",
-		 .frequency_min = 44250000,
-		 .frequency_max = 867250000,
-		 .frequency_stepsize = 250000,
+		 .frequency_min_hz =    44250 * kHz,
+		 .frequency_max_hz =   867250 * kHz,
+		 .frequency_stepsize_hz = 250 * kHz,
 		 .caps = FE_CAN_INVERSION_AUTO |
 		 FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		 FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/usb/dvb-usb/cinergyT2-fe.c b/drivers/media/usb/dvb-usb/cinergyT2-fe.c
index 5a2f81311fb7..df71df7ed524 100644
--- a/drivers/media/usb/dvb-usb/cinergyT2-fe.c
+++ b/drivers/media/usb/dvb-usb/cinergyT2-fe.c
@@ -295,9 +295,9 @@ static const struct dvb_frontend_ops cinergyt2_fe_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= DRIVER_NAME,
-		.frequency_min		= 174000000,
-		.frequency_max		= 862000000,
-		.frequency_stepsize	= 166667,
+		.frequency_min_hz	= 174 * MHz,
+		.frequency_max_hz	= 862 * MHz,
+		.frequency_stepsize_hz	= 166667,
 		.caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_1_2
 			| FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4
 			| FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8
diff --git a/drivers/media/usb/dvb-usb/dib0700_devices.c b/drivers/media/usb/dvb-usb/dib0700_devices.c
index c53a969bc6be..091389fdf89e 100644
--- a/drivers/media/usb/dvb-usb/dib0700_devices.c
+++ b/drivers/media/usb/dvb-usb/dib0700_devices.c
@@ -1745,6 +1745,7 @@ static int dib809x_tuner_attach(struct dvb_usb_adapter *adap)
 		if (dvb_attach(dib0090_register, adap->fe_adap[0].fe, tun_i2c, &dib809x_dib0090_config) == NULL)
 			return -ENODEV;
 	} else {
+		/* FIXME: check if it is fe_adap[1] */
 		if (dvb_attach(dib0090_register, adap->fe_adap[0].fe, tun_i2c, &dib809x_dib0090_config) == NULL)
 			return -ENODEV;
 	}
diff --git a/drivers/media/usb/dvb-usb/dtt200u-fe.c b/drivers/media/usb/dvb-usb/dtt200u-fe.c
index 7e75aae34fb8..1ca3a51b2ae3 100644
--- a/drivers/media/usb/dvb-usb/dtt200u-fe.c
+++ b/drivers/media/usb/dvb-usb/dtt200u-fe.c
@@ -230,9 +230,9 @@ static const struct dvb_frontend_ops dtt200u_fe_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "WideView USB DVB-T",
-		.frequency_min		= 44250000,
-		.frequency_max		= 867250000,
-		.frequency_stepsize	= 250000,
+		.frequency_min_hz	=  44250 * kHz,
+		.frequency_max_hz	= 867250 * kHz,
+		.frequency_stepsize_hz	=    250 * kHz,
 		.caps = FE_CAN_INVERSION_AUTO |
 				FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 				FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c
index 0d4fdd34a710..9ce8b4d79d1f 100644
--- a/drivers/media/usb/dvb-usb/dw2102.c
+++ b/drivers/media/usb/dvb-usb/dw2102.c
@@ -2101,14 +2101,12 @@ static struct dvb_usb_device_properties s6x0_properties = {
 	}
 };
 
-static struct dvb_usb_device_properties *p1100;
 static const struct dvb_usb_device_description d1100 = {
 	"Prof 1100 USB ",
 	{&dw2102_table[PROF_1100], NULL},
 	{NULL},
 };
 
-static struct dvb_usb_device_properties *s660;
 static const struct dvb_usb_device_description d660 = {
 	"TeVii S660 USB",
 	{&dw2102_table[TEVII_S660], NULL},
@@ -2127,14 +2125,12 @@ static const struct dvb_usb_device_description d480_2 = {
 	{NULL},
 };
 
-static struct dvb_usb_device_properties *p7500;
 static const struct dvb_usb_device_description d7500 = {
 	"Prof 7500 USB DVB-S2",
 	{&dw2102_table[PROF_7500], NULL},
 	{NULL},
 };
 
-static struct dvb_usb_device_properties *s421;
 static const struct dvb_usb_device_description d421 = {
 	"TeVii S421 PCI",
 	{&dw2102_table[TEVII_S421], NULL},
@@ -2334,6 +2330,11 @@ static int dw2102_probe(struct usb_interface *intf,
 		const struct usb_device_id *id)
 {
 	int retval = -ENOMEM;
+	struct dvb_usb_device_properties *p1100;
+	struct dvb_usb_device_properties *s660;
+	struct dvb_usb_device_properties *p7500;
+	struct dvb_usb_device_properties *s421;
+
 	p1100 = kmemdup(&s6x0_properties,
 			sizeof(struct dvb_usb_device_properties), GFP_KERNEL);
 	if (!p1100)
@@ -2402,8 +2403,16 @@ static int dw2102_probe(struct usb_interface *intf,
 	    0 == dvb_usb_device_init(intf, &t220_properties,
 			 THIS_MODULE, NULL, adapter_nr) ||
 	    0 == dvb_usb_device_init(intf, &tt_s2_4600_properties,
-			 THIS_MODULE, NULL, adapter_nr))
+			 THIS_MODULE, NULL, adapter_nr)) {
+
+		/* clean up copied properties */
+		kfree(s421);
+		kfree(p7500);
+		kfree(s660);
+		kfree(p1100);
+
 		return 0;
+	}
 
 	retval = -ENODEV;
 	kfree(s421);
diff --git a/drivers/media/usb/dvb-usb/friio-fe.c b/drivers/media/usb/dvb-usb/friio-fe.c
index 932f262452eb..e6bd0ed8d789 100644
--- a/drivers/media/usb/dvb-usb/friio-fe.c
+++ b/drivers/media/usb/dvb-usb/friio-fe.c
@@ -133,10 +133,10 @@ static int jdvbt90502_pll_set_freq(struct jdvbt90502_state *state, u32 freq)
 	u32 f;
 
 	deb_fe("%s: freq=%d, step=%d\n", __func__, freq,
-	       state->frontend.ops.info.frequency_stepsize);
+	       state->frontend.ops.info.frequency_stepsize_hz);
 	/* freq -> oscilator frequency conversion. */
 	/* freq: 473,000,000 + n*6,000,000 [+ 142857 (center freq. shift)] */
-	f = freq / state->frontend.ops.info.frequency_stepsize;
+	f = freq / state->frontend.ops.info.frequency_stepsize_hz;
 	/* add 399[1/7 MHZ] = 57MHz for the IF  */
 	f += 399;
 	/* add center frequency shift if necessary */
@@ -413,10 +413,9 @@ static const struct dvb_frontend_ops jdvbt90502_ops = {
 	.delsys = { SYS_ISDBT },
 	.info = {
 		.name			= "Comtech JDVBT90502 ISDB-T",
-		.frequency_min		= 473000000, /* UHF 13ch, center */
-		.frequency_max		= 767142857, /* UHF 62ch, center */
-		.frequency_stepsize	= JDVBT90502_PLL_CLK / JDVBT90502_PLL_DIVIDER,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	= 473000000, /* UHF 13ch, center */
+		.frequency_max_hz	= 767142857, /* UHF 62ch, center */
+		.frequency_stepsize_hz	= JDVBT90502_PLL_CLK / JDVBT90502_PLL_DIVIDER,
 
 		/* NOTE: this driver ignores all parameters but frequency. */
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/usb/dvb-usb/m920x.c b/drivers/media/usb/dvb-usb/m920x.c
index 51b026fa6bfb..22554d9abd43 100644
--- a/drivers/media/usb/dvb-usb/m920x.c
+++ b/drivers/media/usb/dvb-usb/m920x.c
@@ -255,9 +255,6 @@ static int m920x_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int nu
 	int i, j;
 	int ret = 0;
 
-	if (!num)
-		return -EINVAL;
-
 	if (mutex_lock_interruptible(&d->i2c_mutex) < 0)
 		return -EAGAIN;
 
diff --git a/drivers/media/usb/dvb-usb/usb-urb.c b/drivers/media/usb/dvb-usb/usb-urb.c
index 5e05963f4220..9771f0954c69 100644
--- a/drivers/media/usb/dvb-usb/usb-urb.c
+++ b/drivers/media/usb/dvb-usb/usb-urb.c
@@ -33,7 +33,7 @@ static void usb_urb_complete(struct urb *urb)
 		case -ESHUTDOWN:
 			return;
 		default:        /* error */
-			deb_ts("urb completition error %d.\n", urb->status);
+			deb_ts("urb completion error %d.\n", urb->status);
 			break;
 	}
 
@@ -57,7 +57,7 @@ static void usb_urb_complete(struct urb *urb)
 				stream->complete(stream, b, urb->actual_length);
 			break;
 		default:
-			err("unknown endpoint type in completition handler.");
+			err("unknown endpoint type in completion handler.");
 			return;
 	}
 	usb_submit_urb(urb,GFP_ATOMIC);
diff --git a/drivers/media/usb/dvb-usb/vp702x-fe.c b/drivers/media/usb/dvb-usb/vp702x-fe.c
index ae48146e005c..9eb811452f2e 100644
--- a/drivers/media/usb/dvb-usb/vp702x-fe.c
+++ b/drivers/media/usb/dvb-usb/vp702x-fe.c
@@ -349,10 +349,9 @@ static const struct dvb_frontend_ops vp702x_fe_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name           = "Twinhan DST-like frontend (VP7021/VP7020) DVB-S",
-		.frequency_min       = 950000,
-		.frequency_max       = 2150000,
-		.frequency_stepsize  = 1000,   /* kHz for QPSK frontends */
-		.frequency_tolerance = 0,
+		.frequency_min_hz       =  950 * MHz,
+		.frequency_max_hz       = 2150 * MHz,
+		.frequency_stepsize_hz  =    1 * MHz,
 		.symbol_rate_min     = 1000000,
 		.symbol_rate_max     = 45000000,
 		.symbol_rate_tolerance = 500,  /* ppm */
diff --git a/drivers/media/usb/dvb-usb/vp7045-fe.c b/drivers/media/usb/dvb-usb/vp7045-fe.c
index f86040173b8d..1173ae29885b 100644
--- a/drivers/media/usb/dvb-usb/vp7045-fe.c
+++ b/drivers/media/usb/dvb-usb/vp7045-fe.c
@@ -162,9 +162,9 @@ static const struct dvb_frontend_ops vp7045_fe_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "Twinhan VP7045/46 USB DVB-T",
-		.frequency_min		= 44250000,
-		.frequency_max		= 867250000,
-		.frequency_stepsize	= 1000,
+		.frequency_min_hz	=  44250 * kHz,
+		.frequency_max_hz	= 867250 * kHz,
+		.frequency_stepsize_hz	=      1 * kHz,
 		.caps = FE_CAN_INVERSION_AUTO |
 				FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 				FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c
index 6c8438311d3b..71c829f31d3b 100644
--- a/drivers/media/usb/em28xx/em28xx-cards.c
+++ b/drivers/media/usb/em28xx/em28xx-cards.c
@@ -543,7 +543,7 @@ static const struct em28xx_reg_seq hauppauge_dualhd_dvb[] = {
 	{EM2874_R80_GPIO_P0_CTRL,      0xff, 0xff,    100},
 	{EM2874_R80_GPIO_P0_CTRL,      0xdf, 0xff,    100}, /* demod 2 reset */
 	{EM2874_R80_GPIO_P0_CTRL,      0xff, 0xff,    100},
-	{EM2874_R5F_TS_ENABLE,         0x44, 0xff,     50},
+	{EM2874_R5F_TS_ENABLE,         0x00, 0xff,     50}, /* disable TS filters */
 	{EM2874_R5D_TS1_PKT_SIZE,      0x05, 0xff,     50},
 	{EM2874_R5E_TS2_PKT_SIZE,      0x05, 0xff,     50},
 	{-1,                             -1,   -1,     -1},
@@ -2688,8 +2688,6 @@ struct usb_device_id em28xx_id_table[] = {
 			.driver_info = EM28178_BOARD_PCTV_292E },
 	{ USB_DEVICE(0x2040, 0x8268), /* Hauppauge Retail WinTV-soloHD Bulk */
 			.driver_info = EM28178_BOARD_PCTV_292E },
-	{ USB_DEVICE(0x2040, 0x8268), /* Hauppauge WinTV-soloHD alt. PID */
-			.driver_info = EM28178_BOARD_PCTV_292E },
 	{ USB_DEVICE(0x0413, 0x6f07),
 			.driver_info = EM2861_BOARD_LEADTEK_VC100 },
 	{ USB_DEVICE(0xeb1a, 0x8179),
@@ -2854,13 +2852,13 @@ static void em28xx_pre_card_setup(struct em28xx *dev)
 		em28xx_write_reg(dev, EM2880_R04_GPO, 0x01);
 		usleep_range(10000, 11000);
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfd);
-		mdelay(70);
+		msleep(70);
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfc);
-		mdelay(70);
+		msleep(70);
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xdc);
-		mdelay(70);
+		msleep(70);
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfc);
-		mdelay(70);
+		msleep(70);
 		break;
 	case EM2870_BOARD_TERRATEC_XS_MT2060:
 		/*
@@ -2868,11 +2866,11 @@ static void em28xx_pre_card_setup(struct em28xx *dev)
 		 * demod work
 		 */
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfe);
-		mdelay(70);
+		msleep(70);
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xde);
-		mdelay(70);
+		msleep(70);
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfe);
-		mdelay(70);
+		msleep(70);
 		break;
 	case EM2870_BOARD_PINNACLE_PCTV_DVB:
 		/*
@@ -2880,11 +2878,11 @@ static void em28xx_pre_card_setup(struct em28xx *dev)
 		 * DVB-T demod work
 		 */
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfe);
-		mdelay(70);
+		msleep(70);
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xde);
-		mdelay(70);
+		msleep(70);
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfe);
-		mdelay(70);
+		msleep(70);
 		break;
 	case EM2820_BOARD_GADMEI_UTV310:
 	case EM2820_BOARD_MSI_VOX_USB_2:
@@ -3376,7 +3374,9 @@ void em28xx_free_device(struct kref *ref)
 	if (!dev->disconnected)
 		em28xx_release_resources(dev);
 
-	kfree(dev->alt_max_pkt_size_isoc);
+	if (dev->ts == PRIMARY_TS)
+		kfree(dev->alt_max_pkt_size_isoc);
+
 	kfree(dev);
 }
 EXPORT_SYMBOL_GPL(em28xx_free_device);
@@ -3861,6 +3861,17 @@ static int em28xx_usb_probe(struct usb_interface *intf,
 		dev->has_video = false;
 	}
 
+	if (dev->board.has_dual_ts &&
+	    (dev->tuner_type != TUNER_ABSENT || INPUT(0)->type)) {
+		/*
+		 * The logic with sets alternate is not ready for dual-tuners
+		 * which analog modes.
+		 */
+		dev_err(&intf->dev,
+			"We currently don't support analog TV or stream capture on dual tuners.\n");
+		has_video = false;
+	}
+
 	/* Select USB transfer types to use */
 	if (has_video) {
 		if (!dev->analog_ep_isoc || (try_bulk && dev->analog_ep_bulk))
diff --git a/drivers/media/usb/em28xx/em28xx-core.c b/drivers/media/usb/em28xx/em28xx-core.c
index f70845e7d8c6..5657f8710ca6 100644
--- a/drivers/media/usb/em28xx/em28xx-core.c
+++ b/drivers/media/usb/em28xx/em28xx-core.c
@@ -655,12 +655,12 @@ int em28xx_capture_start(struct em28xx *dev, int start)
 			rc = em28xx_write_reg_bits(dev,
 						   EM2874_R5F_TS_ENABLE,
 						   start ? EM2874_TS1_CAPTURE_ENABLE : 0x00,
-						   EM2874_TS1_CAPTURE_ENABLE);
+						   EM2874_TS1_CAPTURE_ENABLE | EM2874_TS1_FILTER_ENABLE | EM2874_TS1_NULL_DISCARD);
 		else
 			rc = em28xx_write_reg_bits(dev,
 						   EM2874_R5F_TS_ENABLE,
 						   start ? EM2874_TS2_CAPTURE_ENABLE : 0x00,
-						   EM2874_TS2_CAPTURE_ENABLE);
+						   EM2874_TS2_CAPTURE_ENABLE | EM2874_TS2_FILTER_ENABLE | EM2874_TS2_NULL_DISCARD);
 	} else {
 		/* FIXME: which is the best order? */
 		/* video registers are sampled by VREF */
@@ -1053,7 +1053,7 @@ int em28xx_init_usb_xfer(struct em28xx *dev, enum em28xx_mode mode,
 
 	/* submit urbs and enables IRQ */
 	for (i = 0; i < usb_bufs->num_bufs; i++) {
-		rc = usb_submit_urb(usb_bufs->urb[i], GFP_ATOMIC);
+		rc = usb_submit_urb(usb_bufs->urb[i], GFP_KERNEL);
 		if (rc) {
 			dev_err(&dev->intf->dev,
 				"submit of urb %i failed (error=%i)\n", i, rc);
diff --git a/drivers/media/usb/em28xx/em28xx-dvb.c b/drivers/media/usb/em28xx/em28xx-dvb.c
index b778d8a1983e..a73faf12f7e4 100644
--- a/drivers/media/usb/em28xx/em28xx-dvb.c
+++ b/drivers/media/usb/em28xx/em28xx-dvb.c
@@ -218,7 +218,9 @@ static int em28xx_start_streaming(struct em28xx_dvb *dvb)
 		dvb_alt = dev->dvb_alt_isoc;
 	}
 
-	usb_set_interface(udev, dev->ifnum, dvb_alt);
+	if (!dev->board.has_dual_ts)
+		usb_set_interface(udev, dev->ifnum, dvb_alt);
+
 	rc = em28xx_set_mode(dev, EM28XX_DIGITAL_MODE);
 	if (rc < 0)
 		return rc;
diff --git a/drivers/media/usb/em28xx/em28xx-i2c.c b/drivers/media/usb/em28xx/em28xx-i2c.c
index 6458682bc6e2..e19d6342e0d0 100644
--- a/drivers/media/usb/em28xx/em28xx-i2c.c
+++ b/drivers/media/usb/em28xx/em28xx-i2c.c
@@ -559,10 +559,6 @@ static int em28xx_i2c_xfer(struct i2c_adapter *i2c_adap,
 		dev->cur_i2c_bus = bus;
 	}
 
-	if (num <= 0) {
-		rt_mutex_unlock(&dev->i2c_bus_lock);
-		return 0;
-	}
 	for (i = 0; i < num; i++) {
 		addr = msgs[i].addr << 1;
 		if (!msgs[i].len) {
diff --git a/drivers/media/usb/go7007/go7007-driver.c b/drivers/media/usb/go7007/go7007-driver.c
index 05b1126f263e..62aeebcdd7f7 100644
--- a/drivers/media/usb/go7007/go7007-driver.c
+++ b/drivers/media/usb/go7007/go7007-driver.c
@@ -448,13 +448,14 @@ static struct go7007_buffer *frame_boundary(struct go7007 *go, struct go7007_buf
 {
 	u32 *bytesused;
 	struct go7007_buffer *vb_tmp = NULL;
+	unsigned long flags;
 
 	if (vb == NULL) {
-		spin_lock(&go->spinlock);
+		spin_lock_irqsave(&go->spinlock, flags);
 		if (!list_empty(&go->vidq_active))
 			vb = go->active_buf =
 				list_first_entry(&go->vidq_active, struct go7007_buffer, list);
-		spin_unlock(&go->spinlock);
+		spin_unlock_irqrestore(&go->spinlock, flags);
 		go->next_seq++;
 		return vb;
 	}
@@ -468,7 +469,7 @@ static struct go7007_buffer *frame_boundary(struct go7007 *go, struct go7007_buf
 
 	vb->vb.vb2_buf.timestamp = ktime_get_ns();
 	vb_tmp = vb;
-	spin_lock(&go->spinlock);
+	spin_lock_irqsave(&go->spinlock, flags);
 	list_del(&vb->list);
 	if (list_empty(&go->vidq_active))
 		vb = NULL;
@@ -476,7 +477,7 @@ static struct go7007_buffer *frame_boundary(struct go7007 *go, struct go7007_buf
 		vb = list_first_entry(&go->vidq_active,
 				struct go7007_buffer, list);
 	go->active_buf = vb;
-	spin_unlock(&go->spinlock);
+	spin_unlock_irqrestore(&go->spinlock, flags);
 	vb2_buffer_done(&vb_tmp->vb.vb2_buf, VB2_BUF_STATE_DONE);
 	return vb;
 }
diff --git a/drivers/media/usb/go7007/snd-go7007.c b/drivers/media/usb/go7007/snd-go7007.c
index f84a2130f033..137fc253b122 100644
--- a/drivers/media/usb/go7007/snd-go7007.c
+++ b/drivers/media/usb/go7007/snd-go7007.c
@@ -75,13 +75,14 @@ static void parse_audio_stream_data(struct go7007 *go, u8 *buf, int length)
 	struct go7007_snd *gosnd = go->snd_context;
 	struct snd_pcm_runtime *runtime = gosnd->substream->runtime;
 	int frames = bytes_to_frames(runtime, length);
+	unsigned long flags;
 
-	spin_lock(&gosnd->lock);
+	spin_lock_irqsave(&gosnd->lock, flags);
 	gosnd->hw_ptr += frames;
 	if (gosnd->hw_ptr >= runtime->buffer_size)
 		gosnd->hw_ptr -= runtime->buffer_size;
 	gosnd->avail += frames;
-	spin_unlock(&gosnd->lock);
+	spin_unlock_irqrestore(&gosnd->lock, flags);
 	if (gosnd->w_idx + length > runtime->dma_bytes) {
 		int cpy = runtime->dma_bytes - gosnd->w_idx;
 
@@ -92,13 +93,13 @@ static void parse_audio_stream_data(struct go7007 *go, u8 *buf, int length)
 	}
 	memcpy(runtime->dma_area + gosnd->w_idx, buf, length);
 	gosnd->w_idx += length;
-	spin_lock(&gosnd->lock);
+	spin_lock_irqsave(&gosnd->lock, flags);
 	if (gosnd->avail < runtime->period_size) {
-		spin_unlock(&gosnd->lock);
+		spin_unlock_irqrestore(&gosnd->lock, flags);
 		return;
 	}
 	gosnd->avail -= runtime->period_size;
-	spin_unlock(&gosnd->lock);
+	spin_unlock_irqrestore(&gosnd->lock, flags);
 	if (gosnd->capturing)
 		snd_pcm_period_elapsed(gosnd->substream);
 }
diff --git a/drivers/media/usb/gspca/kinect.c b/drivers/media/usb/gspca/kinect.c
index 0cfdf8a1e19d..f993f6280c56 100644
--- a/drivers/media/usb/gspca/kinect.c
+++ b/drivers/media/usb/gspca/kinect.c
@@ -163,7 +163,7 @@ static int send_cmd(struct gspca_dev *gspca_dev, uint16_t cmd, void *cmdbuf,
 		actual_len = kinect_read(udev, ibuf, 0x200);
 	} while (actual_len == 0);
 	gspca_dbg(gspca_dev, D_USBO, "Control reply: %d\n", actual_len);
-	if (actual_len < sizeof(*rhdr)) {
+	if (actual_len < (int)sizeof(*rhdr)) {
 		pr_err("send_cmd: Input control transfer failed (%d)\n",
 		       actual_len);
 		return actual_len < 0 ? actual_len : -EREMOTEIO;
diff --git a/drivers/media/usb/hackrf/hackrf.c b/drivers/media/usb/hackrf/hackrf.c
index 6d692fb3e8dd..34085a0b15a1 100644
--- a/drivers/media/usb/hackrf/hackrf.c
+++ b/drivers/media/usb/hackrf/hackrf.c
@@ -597,7 +597,7 @@ static int hackrf_submit_urbs(struct hackrf_dev *dev)
 
 	for (i = 0; i < dev->urbs_initialized; i++) {
 		dev_dbg(dev->dev, "submit urb=%d\n", i);
-		ret = usb_submit_urb(dev->urb_list[i], GFP_ATOMIC);
+		ret = usb_submit_urb(dev->urb_list[i], GFP_KERNEL);
 		if (ret) {
 			dev_err(dev->dev, "Could not submit URB no. %d - get them all back\n",
 					i);
@@ -636,7 +636,7 @@ static int hackrf_alloc_stream_bufs(struct hackrf_dev *dev)
 
 	for (dev->buf_num = 0; dev->buf_num < MAX_BULK_BUFS; dev->buf_num++) {
 		dev->buf_list[dev->buf_num] = usb_alloc_coherent(dev->udev,
-				BULK_BUFFER_SIZE, GFP_ATOMIC,
+				BULK_BUFFER_SIZE, GFP_KERNEL,
 				&dev->dma_addr[dev->buf_num]);
 		if (!dev->buf_list[dev->buf_num]) {
 			dev_dbg(dev->dev, "alloc buf=%d failed\n",
@@ -689,7 +689,7 @@ static int hackrf_alloc_urbs(struct hackrf_dev *dev, bool rcv)
 	/* allocate the URBs */
 	for (i = 0; i < MAX_BULK_BUFS; i++) {
 		dev_dbg(dev->dev, "alloc urb=%d\n", i);
-		dev->urb_list[i] = usb_alloc_urb(0, GFP_ATOMIC);
+		dev->urb_list[i] = usb_alloc_urb(0, GFP_KERNEL);
 		if (!dev->urb_list[i]) {
 			for (j = 0; j < i; j++)
 				usb_free_urb(dev->urb_list[j]);
diff --git a/drivers/media/usb/hdpvr/hdpvr-i2c.c b/drivers/media/usb/hdpvr/hdpvr-i2c.c
index c71ddefd2e58..5a3cb614a211 100644
--- a/drivers/media/usb/hdpvr/hdpvr-i2c.c
+++ b/drivers/media/usb/hdpvr/hdpvr-i2c.c
@@ -117,9 +117,6 @@ static int hdpvr_transfer(struct i2c_adapter *i2c_adapter, struct i2c_msg *msgs,
 	struct hdpvr_device *dev = i2c_get_adapdata(i2c_adapter);
 	int retval = 0, addr;
 
-	if (num <= 0)
-		return 0;
-
 	mutex_lock(&dev->i2c_mutex);
 
 	addr = msgs[0].addr << 1;
diff --git a/drivers/media/usb/stk1160/stk1160-v4l.c b/drivers/media/usb/stk1160/stk1160-v4l.c
index 77b759a0bcd9..504e413edcd2 100644
--- a/drivers/media/usb/stk1160/stk1160-v4l.c
+++ b/drivers/media/usb/stk1160/stk1160-v4l.c
@@ -802,6 +802,7 @@ int stk1160_vb2_setup(struct stk1160 *dev)
 	q->buf_struct_size = sizeof(struct stk1160_buffer);
 	q->ops = &stk1160_video_qops;
 	q->mem_ops = &vb2_vmalloc_memops;
+	q->lock = &dev->vb_queue_lock;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 
 	rc = vb2_queue_init(q);
@@ -827,7 +828,6 @@ int stk1160_video_register(struct stk1160 *dev)
 	 * It will be used to protect *only* v4l2 ioctls.
 	 */
 	dev->vdev.lock = &dev->v4l_lock;
-	dev->vdev.queue->lock = &dev->vb_queue_lock;
 
 	/* This will be used to set video_device parent */
 	dev->vdev.v4l2_dev = &dev->v4l2_dev;
diff --git a/drivers/media/usb/tm6000/tm6000-dvb.c b/drivers/media/usb/tm6000/tm6000-dvb.c
index c811fc6cf48a..3a4e545c6037 100644
--- a/drivers/media/usb/tm6000/tm6000-dvb.c
+++ b/drivers/media/usb/tm6000/tm6000-dvb.c
@@ -266,6 +266,11 @@ static int register_dvb(struct tm6000_core *dev)
 
 	ret = dvb_register_adapter(&dvb->adapter, "Trident TVMaster 6000 DVB-T",
 					THIS_MODULE, &dev->udev->dev, adapter_nr);
+	if (ret < 0) {
+		pr_err("tm6000: couldn't register the adapter!\n");
+		goto err;
+	}
+
 	dvb->adapter.priv = dev;
 
 	if (dvb->frontend) {
diff --git a/drivers/media/usb/tm6000/tm6000-i2c.c b/drivers/media/usb/tm6000/tm6000-i2c.c
index 659b63febf85..ccd1adf862b1 100644
--- a/drivers/media/usb/tm6000/tm6000-i2c.c
+++ b/drivers/media/usb/tm6000/tm6000-i2c.c
@@ -145,8 +145,6 @@ static int tm6000_i2c_xfer(struct i2c_adapter *i2c_adap,
 	struct tm6000_core *dev = i2c_adap->algo_data;
 	int addr, rc, i, byte;
 
-	if (num <= 0)
-		return 0;
 	for (i = 0; i < num; i++) {
 		addr = (msgs[i].addr << 1) & 0xff;
 		i2c_dprintk(2, "%s %s addr=0x%x len=%d:",
diff --git a/drivers/media/usb/ttusb-dec/ttusbdecfe.c b/drivers/media/usb/ttusb-dec/ttusbdecfe.c
index 6ea05d909024..278bf6c5855b 100644
--- a/drivers/media/usb/ttusb-dec/ttusbdecfe.c
+++ b/drivers/media/usb/ttusb-dec/ttusbdecfe.c
@@ -247,9 +247,9 @@ static const struct dvb_frontend_ops ttusbdecfe_dvbt_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "TechnoTrend/Hauppauge DEC2000-t Frontend",
-		.frequency_min		= 51000000,
-		.frequency_max		= 858000000,
-		.frequency_stepsize	= 62500,
+		.frequency_min_hz	=  51 * MHz,
+		.frequency_max_hz	= 858 * MHz,
+		.frequency_stepsize_hz	= 62500,
 		.caps =	FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 			FE_CAN_QAM_16 | FE_CAN_QAM_64 | FE_CAN_QAM_AUTO |
@@ -270,9 +270,9 @@ static const struct dvb_frontend_ops ttusbdecfe_dvbs_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "TechnoTrend/Hauppauge DEC3000-s Frontend",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 125,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
+		.frequency_stepsize_hz	=  125 * kHz,
 		.symbol_rate_min        = 1000000,  /* guessed */
 		.symbol_rate_max        = 45000000, /* guessed */
 		.caps =	FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
diff --git a/drivers/media/usb/usbtv/usbtv-audio.c b/drivers/media/usb/usbtv/usbtv-audio.c
index 2c2ca77fa01f..4ce38246ed64 100644
--- a/drivers/media/usb/usbtv/usbtv-audio.c
+++ b/drivers/media/usb/usbtv/usbtv-audio.c
@@ -126,6 +126,7 @@ static void usbtv_audio_urb_received(struct urb *urb)
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	size_t i, frame_bytes, chunk_length, buffer_pos, period_pos;
 	int period_elapsed;
+	unsigned long flags;
 	void *urb_current;
 
 	switch (urb->status) {
@@ -179,12 +180,12 @@ static void usbtv_audio_urb_received(struct urb *urb)
 		}
 	}
 
-	snd_pcm_stream_lock(substream);
+	snd_pcm_stream_lock_irqsave(substream, flags);
 
 	chip->snd_buffer_pos = buffer_pos;
 	chip->snd_period_pos = period_pos;
 
-	snd_pcm_stream_unlock(substream);
+	snd_pcm_stream_unlock_irqrestore(substream, flags);
 
 	if (period_elapsed)
 		snd_pcm_period_elapsed(substream);
diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c
index a36b4fb949fa..c2ad102bd693 100644
--- a/drivers/media/usb/uvc/uvc_ctrl.c
+++ b/drivers/media/usb/uvc/uvc_ctrl.c
@@ -20,6 +20,7 @@
 #include <linux/videodev2.h>
 #include <linux/vmalloc.h>
 #include <linux/wait.h>
+#include <linux/workqueue.h>
 #include <linux/atomic.h>
 #include <media/v4l2-ctrls.h>
 
@@ -971,12 +972,30 @@ static int uvc_ctrl_populate_cache(struct uvc_video_chain *chain,
 	return 0;
 }
 
+static s32 __uvc_ctrl_get_value(struct uvc_control_mapping *mapping,
+				const u8 *data)
+{
+	s32 value = mapping->get(mapping, UVC_GET_CUR, data);
+
+	if (mapping->v4l2_type == V4L2_CTRL_TYPE_MENU) {
+		struct uvc_menu_info *menu = mapping->menu_info;
+		unsigned int i;
+
+		for (i = 0; i < mapping->menu_count; ++i, ++menu) {
+			if (menu->value == value) {
+				value = i;
+				break;
+			}
+		}
+	}
+
+	return value;
+}
+
 static int __uvc_ctrl_get(struct uvc_video_chain *chain,
 	struct uvc_control *ctrl, struct uvc_control_mapping *mapping,
 	s32 *value)
 {
-	struct uvc_menu_info *menu;
-	unsigned int i;
 	int ret;
 
 	if ((ctrl->info.flags & UVC_CTRL_FLAG_GET_CUR) == 0)
@@ -993,18 +1012,8 @@ static int __uvc_ctrl_get(struct uvc_video_chain *chain,
 		ctrl->loaded = 1;
 	}
 
-	*value = mapping->get(mapping, UVC_GET_CUR,
-		uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT));
-
-	if (mapping->v4l2_type == V4L2_CTRL_TYPE_MENU) {
-		menu = mapping->menu_info;
-		for (i = 0; i < mapping->menu_count; ++i, ++menu) {
-			if (menu->value == *value) {
-				*value = i;
-				break;
-			}
-		}
-	}
+	*value = __uvc_ctrl_get_value(mapping,
+				uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT));
 
 	return 0;
 }
@@ -1125,7 +1134,7 @@ done:
 }
 
 /*
- * Mapping V4L2 controls to UVC controls can be straighforward if done well.
+ * Mapping V4L2 controls to UVC controls can be straightforward if done well.
  * Most of the UVC controls exist in V4L2, and can be mapped directly. Some
  * must be grouped (for instance the Red Balance, Blue Balance and Do White
  * Balance V4L2 controls use the White Balance Component UVC control) or
@@ -1216,53 +1225,135 @@ static void uvc_ctrl_fill_event(struct uvc_video_chain *chain,
 	ev->u.ctrl.default_value = v4l2_ctrl.default_value;
 }
 
-static void uvc_ctrl_send_event(struct uvc_fh *handle,
-	struct uvc_control *ctrl, struct uvc_control_mapping *mapping,
-	s32 value, u32 changes)
+/*
+ * Send control change events to all subscribers for the @ctrl control. By
+ * default the subscriber that generated the event, as identified by @handle,
+ * is not notified unless it has set the V4L2_EVENT_SUB_FL_ALLOW_FEEDBACK flag.
+ * @handle can be NULL for asynchronous events related to auto-update controls,
+ * in which case all subscribers are notified.
+ */
+static void uvc_ctrl_send_event(struct uvc_video_chain *chain,
+	struct uvc_fh *handle, struct uvc_control *ctrl,
+	struct uvc_control_mapping *mapping, s32 value, u32 changes)
 {
+	struct v4l2_fh *originator = handle ? &handle->vfh : NULL;
 	struct v4l2_subscribed_event *sev;
 	struct v4l2_event ev;
 
 	if (list_empty(&mapping->ev_subs))
 		return;
 
-	uvc_ctrl_fill_event(handle->chain, &ev, ctrl, mapping, value, changes);
+	uvc_ctrl_fill_event(chain, &ev, ctrl, mapping, value, changes);
 
 	list_for_each_entry(sev, &mapping->ev_subs, node) {
-		if (sev->fh && (sev->fh != &handle->vfh ||
+		if (sev->fh != originator ||
 		    (sev->flags & V4L2_EVENT_SUB_FL_ALLOW_FEEDBACK) ||
-		    (changes & V4L2_EVENT_CTRL_CH_FLAGS)))
+		    (changes & V4L2_EVENT_CTRL_CH_FLAGS))
 			v4l2_event_queue_fh(sev->fh, &ev);
 	}
 }
 
-static void uvc_ctrl_send_slave_event(struct uvc_fh *handle,
-	struct uvc_control *master, u32 slave_id,
-	const struct v4l2_ext_control *xctrls, unsigned int xctrls_count)
+/*
+ * Send control change events for the slave of the @master control identified
+ * by the V4L2 ID @slave_id. The @handle identifies the event subscriber that
+ * generated the event and may be NULL for auto-update events.
+ */
+static void uvc_ctrl_send_slave_event(struct uvc_video_chain *chain,
+	struct uvc_fh *handle, struct uvc_control *master, u32 slave_id)
 {
 	struct uvc_control_mapping *mapping = NULL;
 	struct uvc_control *ctrl = NULL;
 	u32 changes = V4L2_EVENT_CTRL_CH_FLAGS;
-	unsigned int i;
 	s32 val = 0;
 
-	/*
-	 * We can skip sending an event for the slave if the slave
-	 * is being modified in the same transaction.
-	 */
-	for (i = 0; i < xctrls_count; i++) {
-		if (xctrls[i].id == slave_id)
-			return;
-	}
-
 	__uvc_find_control(master->entity, slave_id, &mapping, &ctrl, 0);
 	if (ctrl == NULL)
 		return;
 
-	if (__uvc_ctrl_get(handle->chain, ctrl, mapping, &val) == 0)
+	if (__uvc_ctrl_get(chain, ctrl, mapping, &val) == 0)
 		changes |= V4L2_EVENT_CTRL_CH_VALUE;
 
-	uvc_ctrl_send_event(handle, ctrl, mapping, val, changes);
+	uvc_ctrl_send_event(chain, handle, ctrl, mapping, val, changes);
+}
+
+static void uvc_ctrl_status_event_work(struct work_struct *work)
+{
+	struct uvc_device *dev = container_of(work, struct uvc_device,
+					      async_ctrl.work);
+	struct uvc_ctrl_work *w = &dev->async_ctrl;
+	struct uvc_video_chain *chain = w->chain;
+	struct uvc_control_mapping *mapping;
+	struct uvc_control *ctrl = w->ctrl;
+	struct uvc_fh *handle;
+	unsigned int i;
+	int ret;
+
+	mutex_lock(&chain->ctrl_mutex);
+
+	handle = ctrl->handle;
+	ctrl->handle = NULL;
+
+	list_for_each_entry(mapping, &ctrl->info.mappings, list) {
+		s32 value = __uvc_ctrl_get_value(mapping, w->data);
+
+		/*
+		 * handle may be NULL here if the device sends auto-update
+		 * events without a prior related control set from userspace.
+		 */
+		for (i = 0; i < ARRAY_SIZE(mapping->slave_ids); ++i) {
+			if (!mapping->slave_ids[i])
+				break;
+
+			uvc_ctrl_send_slave_event(chain, handle, ctrl,
+						  mapping->slave_ids[i]);
+		}
+
+		uvc_ctrl_send_event(chain, handle, ctrl, mapping, value,
+				    V4L2_EVENT_CTRL_CH_VALUE);
+	}
+
+	mutex_unlock(&chain->ctrl_mutex);
+
+	/* Resubmit the URB. */
+	w->urb->interval = dev->int_ep->desc.bInterval;
+	ret = usb_submit_urb(w->urb, GFP_KERNEL);
+	if (ret < 0)
+		uvc_printk(KERN_ERR, "Failed to resubmit status URB (%d).\n",
+			   ret);
+}
+
+bool uvc_ctrl_status_event(struct urb *urb, struct uvc_video_chain *chain,
+			   struct uvc_control *ctrl, const u8 *data)
+{
+	struct uvc_device *dev = chain->dev;
+	struct uvc_ctrl_work *w = &dev->async_ctrl;
+
+	if (list_empty(&ctrl->info.mappings)) {
+		ctrl->handle = NULL;
+		return false;
+	}
+
+	w->data = data;
+	w->urb = urb;
+	w->chain = chain;
+	w->ctrl = ctrl;
+
+	schedule_work(&w->work);
+
+	return true;
+}
+
+static bool uvc_ctrl_xctrls_has_control(const struct v4l2_ext_control *xctrls,
+					unsigned int xctrls_count, u32 id)
+{
+	unsigned int i;
+
+	for (i = 0; i < xctrls_count; ++i) {
+		if (xctrls[i].id == id)
+			return true;
+	}
+
+	return false;
 }
 
 static void uvc_ctrl_send_events(struct uvc_fh *handle,
@@ -1277,29 +1368,39 @@ static void uvc_ctrl_send_events(struct uvc_fh *handle,
 	for (i = 0; i < xctrls_count; ++i) {
 		ctrl = uvc_find_control(handle->chain, xctrls[i].id, &mapping);
 
+		if (ctrl->info.flags & UVC_CTRL_FLAG_ASYNCHRONOUS)
+			/* Notification will be sent from an Interrupt event. */
+			continue;
+
 		for (j = 0; j < ARRAY_SIZE(mapping->slave_ids); ++j) {
-			if (!mapping->slave_ids[j])
+			u32 slave_id = mapping->slave_ids[j];
+
+			if (!slave_id)
 				break;
-			uvc_ctrl_send_slave_event(handle, ctrl,
-						  mapping->slave_ids[j],
-						  xctrls, xctrls_count);
+
+			/*
+			 * We can skip sending an event for the slave if the
+			 * slave is being modified in the same transaction.
+			 */
+			if (uvc_ctrl_xctrls_has_control(xctrls, xctrls_count,
+							slave_id))
+				continue;
+
+			uvc_ctrl_send_slave_event(handle->chain, handle, ctrl,
+						  slave_id);
 		}
 
 		/*
 		 * If the master is being modified in the same transaction
 		 * flags may change too.
 		 */
-		if (mapping->master_id) {
-			for (j = 0; j < xctrls_count; j++) {
-				if (xctrls[j].id == mapping->master_id) {
-					changes |= V4L2_EVENT_CTRL_CH_FLAGS;
-					break;
-				}
-			}
-		}
+		if (mapping->master_id &&
+		    uvc_ctrl_xctrls_has_control(xctrls, xctrls_count,
+						mapping->master_id))
+			changes |= V4L2_EVENT_CTRL_CH_FLAGS;
 
-		uvc_ctrl_send_event(handle, ctrl, mapping, xctrls[i].value,
-				    changes);
+		uvc_ctrl_send_event(handle->chain, handle, ctrl, mapping,
+				    xctrls[i].value, changes);
 	}
 }
 
@@ -1472,9 +1573,10 @@ int uvc_ctrl_get(struct uvc_video_chain *chain,
 	return __uvc_ctrl_get(chain, ctrl, mapping, &xctrl->value);
 }
 
-int uvc_ctrl_set(struct uvc_video_chain *chain,
+int uvc_ctrl_set(struct uvc_fh *handle,
 	struct v4l2_ext_control *xctrl)
 {
+	struct uvc_video_chain *chain = handle->chain;
 	struct uvc_control *ctrl;
 	struct uvc_control_mapping *mapping;
 	s32 value;
@@ -1581,6 +1683,9 @@ int uvc_ctrl_set(struct uvc_video_chain *chain,
 	mapping->set(mapping, value,
 		uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT));
 
+	if (ctrl->info.flags & UVC_CTRL_FLAG_ASYNCHRONOUS)
+		ctrl->handle = handle;
+
 	ctrl->dirty = 1;
 	ctrl->modified = 1;
 	return 0;
@@ -1612,7 +1717,9 @@ static int uvc_ctrl_get_flags(struct uvc_device *dev,
 			    |  (data[0] & UVC_CONTROL_CAP_SET ?
 				UVC_CTRL_FLAG_SET_CUR : 0)
 			    |  (data[0] & UVC_CONTROL_CAP_AUTOUPDATE ?
-				UVC_CTRL_FLAG_AUTO_UPDATE : 0);
+				UVC_CTRL_FLAG_AUTO_UPDATE : 0)
+			    |  (data[0] & UVC_CONTROL_CAP_ASYNCHRONOUS ?
+				UVC_CTRL_FLAG_ASYNCHRONOUS : 0);
 
 	kfree(data);
 	return ret;
@@ -2173,6 +2280,8 @@ int uvc_ctrl_init_device(struct uvc_device *dev)
 	struct uvc_entity *entity;
 	unsigned int i;
 
+	INIT_WORK(&dev->async_ctrl.work, uvc_ctrl_status_event_work);
+
 	/* Walk the entities list and instantiate controls */
 	list_for_each_entry(entity, &dev->entities, list) {
 		struct uvc_control *ctrl;
@@ -2241,6 +2350,8 @@ void uvc_ctrl_cleanup_device(struct uvc_device *dev)
 	struct uvc_entity *entity;
 	unsigned int i;
 
+	cancel_work_sync(&dev->async_ctrl.work);
+
 	/* Free controls and control mappings for all entities. */
 	list_for_each_entry(entity, &dev->entities, list) {
 		for (i = 0; i < entity->ncontrols; ++i) {
diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index 8e138201330f..d46dc432456c 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -100,6 +100,11 @@ static struct uvc_format_desc uvc_fmts[] = {
 		.fcc		= V4L2_PIX_FMT_GREY,
 	},
 	{
+		.name		= "IR 8-bit (L8_IR)",
+		.guid		= UVC_GUID_FORMAT_KSMEDIA_L8_IR,
+		.fcc		= V4L2_PIX_FMT_GREY,
+	},
+	{
 		.name		= "Greyscale 10-bit (Y10 )",
 		.guid		= UVC_GUID_FORMAT_Y10,
 		.fcc		= V4L2_PIX_FMT_Y10,
diff --git a/drivers/media/usb/uvc/uvc_status.c b/drivers/media/usb/uvc/uvc_status.c
index 7b710410584a..0722dc684378 100644
--- a/drivers/media/usb/uvc/uvc_status.c
+++ b/drivers/media/usb/uvc/uvc_status.c
@@ -78,7 +78,24 @@ static void uvc_input_report_key(struct uvc_device *dev, unsigned int code,
 /* --------------------------------------------------------------------------
  * Status interrupt endpoint
  */
-static void uvc_event_streaming(struct uvc_device *dev, u8 *data, int len)
+struct uvc_streaming_status {
+	u8	bStatusType;
+	u8	bOriginator;
+	u8	bEvent;
+	u8	bValue[];
+} __packed;
+
+struct uvc_control_status {
+	u8	bStatusType;
+	u8	bOriginator;
+	u8	bEvent;
+	u8	bSelector;
+	u8	bAttribute;
+	u8	bValue[];
+} __packed;
+
+static void uvc_event_streaming(struct uvc_device *dev,
+				struct uvc_streaming_status *status, int len)
 {
 	if (len < 3) {
 		uvc_trace(UVC_TRACE_STATUS, "Invalid streaming status event "
@@ -86,31 +103,97 @@ static void uvc_event_streaming(struct uvc_device *dev, u8 *data, int len)
 		return;
 	}
 
-	if (data[2] == 0) {
+	if (status->bEvent == 0) {
 		if (len < 4)
 			return;
 		uvc_trace(UVC_TRACE_STATUS, "Button (intf %u) %s len %d\n",
-			data[1], data[3] ? "pressed" : "released", len);
-		uvc_input_report_key(dev, KEY_CAMERA, data[3]);
+			  status->bOriginator,
+			  status->bValue[0] ? "pressed" : "released", len);
+		uvc_input_report_key(dev, KEY_CAMERA, status->bValue[0]);
 	} else {
 		uvc_trace(UVC_TRACE_STATUS,
 			  "Stream %u error event %02x len %d.\n",
-			  data[1], data[2], len);
+			  status->bOriginator, status->bEvent, len);
 	}
 }
 
-static void uvc_event_control(struct uvc_device *dev, u8 *data, int len)
+#define UVC_CTRL_VALUE_CHANGE	0
+#define UVC_CTRL_INFO_CHANGE	1
+#define UVC_CTRL_FAILURE_CHANGE	2
+#define UVC_CTRL_MIN_CHANGE	3
+#define UVC_CTRL_MAX_CHANGE	4
+
+static struct uvc_control *uvc_event_entity_find_ctrl(struct uvc_entity *entity,
+						      u8 selector)
 {
-	char *attrs[3] = { "value", "info", "failure" };
+	struct uvc_control *ctrl;
+	unsigned int i;
+
+	for (i = 0, ctrl = entity->controls; i < entity->ncontrols; i++, ctrl++)
+		if (ctrl->info.selector == selector)
+			return ctrl;
+
+	return NULL;
+}
 
-	if (len < 6 || data[2] != 0 || data[4] > 2) {
+static struct uvc_control *uvc_event_find_ctrl(struct uvc_device *dev,
+					const struct uvc_control_status *status,
+					struct uvc_video_chain **chain)
+{
+	list_for_each_entry((*chain), &dev->chains, list) {
+		struct uvc_entity *entity;
+		struct uvc_control *ctrl;
+
+		list_for_each_entry(entity, &(*chain)->entities, chain) {
+			if (entity->id != status->bOriginator)
+				continue;
+
+			ctrl = uvc_event_entity_find_ctrl(entity,
+							  status->bSelector);
+			if (ctrl)
+				return ctrl;
+		}
+	}
+
+	return NULL;
+}
+
+static bool uvc_event_control(struct urb *urb,
+			      const struct uvc_control_status *status, int len)
+{
+	static const char *attrs[] = { "value", "info", "failure", "min", "max" };
+	struct uvc_device *dev = urb->context;
+	struct uvc_video_chain *chain;
+	struct uvc_control *ctrl;
+
+	if (len < 6 || status->bEvent != 0 ||
+	    status->bAttribute >= ARRAY_SIZE(attrs)) {
 		uvc_trace(UVC_TRACE_STATUS, "Invalid control status event "
 				"received.\n");
-		return;
+		return false;
 	}
 
 	uvc_trace(UVC_TRACE_STATUS, "Control %u/%u %s change len %d.\n",
-		data[1], data[3], attrs[data[4]], len);
+		  status->bOriginator, status->bSelector,
+		  attrs[status->bAttribute], len);
+
+	/* Find the control. */
+	ctrl = uvc_event_find_ctrl(dev, status, &chain);
+	if (!ctrl)
+		return false;
+
+	switch (status->bAttribute) {
+	case UVC_CTRL_VALUE_CHANGE:
+		return uvc_ctrl_status_event(urb, chain, ctrl, status->bValue);
+
+	case UVC_CTRL_INFO_CHANGE:
+	case UVC_CTRL_FAILURE_CHANGE:
+	case UVC_CTRL_MIN_CHANGE:
+	case UVC_CTRL_MAX_CHANGE:
+		break;
+	}
+
+	return false;
 }
 
 static void uvc_status_complete(struct urb *urb)
@@ -138,13 +221,23 @@ static void uvc_status_complete(struct urb *urb)
 	len = urb->actual_length;
 	if (len > 0) {
 		switch (dev->status[0] & 0x0f) {
-		case UVC_STATUS_TYPE_CONTROL:
-			uvc_event_control(dev, dev->status, len);
+		case UVC_STATUS_TYPE_CONTROL: {
+			struct uvc_control_status *status =
+				(struct uvc_control_status *)dev->status;
+
+			if (uvc_event_control(urb, status, len))
+				/* The URB will be resubmitted in work context. */
+				return;
 			break;
+		}
 
-		case UVC_STATUS_TYPE_STREAMING:
-			uvc_event_streaming(dev, dev->status, len);
+		case UVC_STATUS_TYPE_STREAMING: {
+			struct uvc_streaming_status *status =
+				(struct uvc_streaming_status *)dev->status;
+
+			uvc_event_streaming(dev, status, len);
 			break;
+		}
 
 		default:
 			uvc_trace(UVC_TRACE_STATUS, "Unknown status event "
diff --git a/drivers/media/usb/uvc/uvc_v4l2.c b/drivers/media/usb/uvc/uvc_v4l2.c
index bd32914259ae..18a7384b50ee 100644
--- a/drivers/media/usb/uvc/uvc_v4l2.c
+++ b/drivers/media/usb/uvc/uvc_v4l2.c
@@ -994,7 +994,7 @@ static int uvc_ioctl_s_ctrl(struct file *file, void *fh,
 	if (ret < 0)
 		return ret;
 
-	ret = uvc_ctrl_set(chain, &xctrl);
+	ret = uvc_ctrl_set(handle, &xctrl);
 	if (ret < 0) {
 		uvc_ctrl_rollback(handle);
 		return ret;
@@ -1069,7 +1069,7 @@ static int uvc_ioctl_s_try_ext_ctrls(struct uvc_fh *handle,
 		return ret;
 
 	for (i = 0; i < ctrls->count; ++ctrl, ++i) {
-		ret = uvc_ctrl_set(chain, ctrl);
+		ret = uvc_ctrl_set(handle, ctrl);
 		if (ret < 0) {
 			uvc_ctrl_rollback(handle);
 			ctrls->error_idx = commit ? ctrls->count : i;
diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c
index a88b2e51a666..86a99f461fd8 100644
--- a/drivers/media/usb/uvc/uvc_video.c
+++ b/drivers/media/usb/uvc/uvc_video.c
@@ -73,17 +73,57 @@ int uvc_query_ctrl(struct uvc_device *dev, u8 query, u8 unit,
 			u8 intfnum, u8 cs, void *data, u16 size)
 {
 	int ret;
+	u8 error;
+	u8 tmp;
 
 	ret = __uvc_query_ctrl(dev, query, unit, intfnum, cs, data, size,
 				UVC_CTRL_CONTROL_TIMEOUT);
-	if (ret != size) {
-		uvc_printk(KERN_ERR, "Failed to query (%s) UVC control %u on "
-			"unit %u: %d (exp. %u).\n", uvc_query_name(query), cs,
-			unit, ret, size);
-		return -EIO;
+	if (likely(ret == size))
+		return 0;
+
+	uvc_printk(KERN_ERR,
+		   "Failed to query (%s) UVC control %u on unit %u: %d (exp. %u).\n",
+		   uvc_query_name(query), cs, unit, ret, size);
+
+	if (ret != -EPIPE)
+		return ret;
+
+	tmp = *(u8 *)data;
+
+	ret = __uvc_query_ctrl(dev, UVC_GET_CUR, 0, intfnum,
+			       UVC_VC_REQUEST_ERROR_CODE_CONTROL, data, 1,
+			       UVC_CTRL_CONTROL_TIMEOUT);
+
+	error = *(u8 *)data;
+	*(u8 *)data = tmp;
+
+	if (ret != 1)
+		return ret < 0 ? ret : -EPIPE;
+
+	uvc_trace(UVC_TRACE_CONTROL, "Control error %u\n", error);
+
+	switch (error) {
+	case 0:
+		/* Cannot happen - we received a STALL */
+		return -EPIPE;
+	case 1: /* Not ready */
+		return -EBUSY;
+	case 2: /* Wrong state */
+		return -EILSEQ;
+	case 3: /* Power */
+		return -EREMOTE;
+	case 4: /* Out of range */
+		return -ERANGE;
+	case 5: /* Invalid unit */
+	case 6: /* Invalid control */
+	case 7: /* Invalid Request */
+	case 8: /* Invalid value within range */
+		return -EINVAL;
+	default: /* reserved or unknown */
+		break;
 	}
 
-	return 0;
+	return -EPIPE;
 }
 
 static void uvc_fixup_video_ctrl(struct uvc_streaming *stream,
@@ -1232,6 +1272,8 @@ static void uvc_video_validate_buffer(const struct uvc_streaming *stream,
 static void uvc_video_next_buffers(struct uvc_streaming *stream,
 		struct uvc_buffer **video_buf, struct uvc_buffer **meta_buf)
 {
+	uvc_video_validate_buffer(stream, *video_buf);
+
 	if (*meta_buf) {
 		struct vb2_v4l2_buffer *vb2_meta = &(*meta_buf)->buf;
 		const struct vb2_v4l2_buffer *vb2_video = &(*video_buf)->buf;
@@ -1270,10 +1312,8 @@ static void uvc_video_decode_isoc(struct urb *urb, struct uvc_streaming *stream,
 		do {
 			ret = uvc_video_decode_start(stream, buf, mem,
 				urb->iso_frame_desc[i].actual_length);
-			if (ret == -EAGAIN) {
-				uvc_video_validate_buffer(stream, buf);
+			if (ret == -EAGAIN)
 				uvc_video_next_buffers(stream, &buf, &meta_buf);
-			}
 		} while (ret == -EAGAIN);
 
 		if (ret < 0)
@@ -1289,10 +1329,8 @@ static void uvc_video_decode_isoc(struct urb *urb, struct uvc_streaming *stream,
 		uvc_video_decode_end(stream, buf, mem,
 			urb->iso_frame_desc[i].actual_length);
 
-		if (buf->state == UVC_BUF_STATE_READY) {
-			uvc_video_validate_buffer(stream, buf);
+		if (buf->state == UVC_BUF_STATE_READY)
 			uvc_video_next_buffers(stream, &buf, &meta_buf);
-		}
 	}
 }
 
diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h
index be5cf179228b..e5f5d84f1d1d 100644
--- a/drivers/media/usb/uvc/uvcvideo.h
+++ b/drivers/media/usb/uvc/uvcvideo.h
@@ -12,6 +12,7 @@
 #include <linux/usb/video.h>
 #include <linux/uvcvideo.h>
 #include <linux/videodev2.h>
+#include <linux/workqueue.h>
 #include <media/media-device.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-event.h>
@@ -157,6 +158,9 @@
 #define UVC_GUID_FORMAT_D3DFMT_L8 \
 	{0x32, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x00, \
 	 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
+#define UVC_GUID_FORMAT_KSMEDIA_L8_IR \
+	{0x32, 0x00, 0x00, 0x00, 0x02, 0x00, 0x10, 0x00, \
+	 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
 
 
 /* ------------------------------------------------------------------------
@@ -256,6 +260,8 @@ struct uvc_control {
 	   initialized:1;
 
 	u8 *uvc_data;
+
+	struct uvc_fh *handle;	/* File handle that last changed the control. */
 };
 
 struct uvc_format_desc {
@@ -600,6 +606,14 @@ struct uvc_device {
 	u8 *status;
 	struct input_dev *input;
 	char input_phys[64];
+
+	struct uvc_ctrl_work {
+		struct work_struct work;
+		struct urb *urb;
+		struct uvc_video_chain *chain;
+		struct uvc_control *ctrl;
+		const void *data;
+	} async_ctrl;
 };
 
 enum uvc_handle_state {
@@ -753,6 +767,8 @@ int uvc_ctrl_add_mapping(struct uvc_video_chain *chain,
 int uvc_ctrl_init_device(struct uvc_device *dev);
 void uvc_ctrl_cleanup_device(struct uvc_device *dev);
 int uvc_ctrl_restore_values(struct uvc_device *dev);
+bool uvc_ctrl_status_event(struct urb *urb, struct uvc_video_chain *chain,
+			   struct uvc_control *ctrl, const u8 *data);
 
 int uvc_ctrl_begin(struct uvc_video_chain *chain);
 int __uvc_ctrl_commit(struct uvc_fh *handle, int rollback,
@@ -770,7 +786,7 @@ static inline int uvc_ctrl_rollback(struct uvc_fh *handle)
 }
 
 int uvc_ctrl_get(struct uvc_video_chain *chain, struct v4l2_ext_control *xctrl);
-int uvc_ctrl_set(struct uvc_video_chain *chain, struct v4l2_ext_control *xctrl);
+int uvc_ctrl_set(struct uvc_fh *handle, struct v4l2_ext_control *xctrl);
 
 int uvc_xu_ctrl_query(struct uvc_video_chain *chain,
 		      struct uvc_xu_control_query *xqry);
diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index d29e45516eb7..599c1cbff3b9 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -431,6 +431,20 @@ const char * const *v4l2_ctrl_get_menu(u32 id)
 		"Use Previous Specific Frame",
 		NULL,
 	};
+	static const char * const vp8_profile[] = {
+		"0",
+		"1",
+		"2",
+		"3",
+		NULL,
+	};
+	static const char * const vp9_profile[] = {
+		"0",
+		"1",
+		"2",
+		"3",
+		NULL,
+	};
 
 	static const char * const flash_led_mode[] = {
 		"Off",
@@ -614,6 +628,10 @@ const char * const *v4l2_ctrl_get_menu(u32 id)
 		return mpeg4_profile;
 	case V4L2_CID_MPEG_VIDEO_VPX_GOLDEN_FRAME_SEL:
 		return vpx_golden_frame_sel;
+	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:
+		return vp8_profile;
+	case V4L2_CID_MPEG_VIDEO_VP9_PROFILE:
+		return vp9_profile;
 	case V4L2_CID_JPEG_CHROMA_SUBSAMPLING:
 		return jpeg_chroma_subsampling;
 	case V4L2_CID_DV_TX_MODE:
@@ -839,7 +857,8 @@ const char *v4l2_ctrl_get_name(u32 id)
 	case V4L2_CID_MPEG_VIDEO_VPX_MAX_QP:			return "VPX Maximum QP Value";
 	case V4L2_CID_MPEG_VIDEO_VPX_I_FRAME_QP:		return "VPX I-Frame QP Value";
 	case V4L2_CID_MPEG_VIDEO_VPX_P_FRAME_QP:		return "VPX P-Frame QP Value";
-	case V4L2_CID_MPEG_VIDEO_VPX_PROFILE:			return "VPX Profile";
+	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:			return "VP8 Profile";
+	case V4L2_CID_MPEG_VIDEO_VP9_PROFILE:			return "VP9 Profile";
 
 	/* HEVC controls */
 	case V4L2_CID_MPEG_VIDEO_HEVC_I_FRAME_QP:		return "HEVC I-Frame QP Value";
@@ -1180,6 +1199,8 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type,
 	case V4L2_CID_DEINTERLACING_MODE:
 	case V4L2_CID_TUNE_DEEMPHASIS:
 	case V4L2_CID_MPEG_VIDEO_VPX_GOLDEN_FRAME_SEL:
+	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:
+	case V4L2_CID_MPEG_VIDEO_VP9_PROFILE:
 	case V4L2_CID_DETECT_MD_MODE:
 	case V4L2_CID_MPEG_VIDEO_HEVC_PROFILE:
 	case V4L2_CID_MPEG_VIDEO_HEVC_LEVEL:
@@ -3137,9 +3158,22 @@ static int try_or_set_cluster(struct v4l2_fh *fh, struct v4l2_ctrl *master,
 
 	/* If OK, then make the new values permanent. */
 	update_flag = is_cur_manual(master) != is_new_manual(master);
-	for (i = 0; i < master->ncontrols; i++)
+
+	for (i = 0; i < master->ncontrols; i++) {
+		/*
+		 * If we switch from auto to manual mode, and this cluster
+		 * contains volatile controls, then all non-master controls
+		 * have to be marked as changed. The 'new' value contains
+		 * the volatile value (obtained by update_from_auto_cluster),
+		 * which now has to become the current value.
+		 */
+		if (i && update_flag && is_new_manual(master) &&
+		    master->has_volatiles && master->cluster[i])
+			master->cluster[i]->has_changed = true;
+
 		new_to_cur(fh, master->cluster[i], ch_flags |
 			((update_flag && i > 0) ? V4L2_EVENT_CTRL_CH_FLAGS : 0));
+	}
 	return 0;
 }
 
diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c
index 4ffd7d60a901..69e775930fc4 100644
--- a/drivers/media/v4l2-core/v4l2-dev.c
+++ b/drivers/media/v4l2-core/v4l2-dev.c
@@ -202,7 +202,7 @@ static void v4l2_device_release(struct device *cd)
 	mutex_unlock(&videodev_lock);
 
 #if defined(CONFIG_MEDIA_CONTROLLER)
-	if (v4l2_dev->mdev) {
+	if (v4l2_dev->mdev && vdev->vfl_dir != VFL_DIR_M2M) {
 		/* Remove interfaces and interface links */
 		media_devnode_remove(vdev->intf_devnode);
 		if (vdev->entity.function != MEDIA_ENT_F_UNKNOWN)
@@ -733,19 +733,22 @@ static void determine_valid_ioctls(struct video_device *vdev)
 			BASE_VIDIOC_PRIVATE);
 }
 
-static int video_register_media_controller(struct video_device *vdev, int type)
+static int video_register_media_controller(struct video_device *vdev)
 {
 #if defined(CONFIG_MEDIA_CONTROLLER)
 	u32 intf_type;
 	int ret;
 
-	if (!vdev->v4l2_dev->mdev)
+	/* Memory-to-memory devices are more complex and use
+	 * their own function to register its mc entities.
+	 */
+	if (!vdev->v4l2_dev->mdev || vdev->vfl_dir == VFL_DIR_M2M)
 		return 0;
 
 	vdev->entity.obj_type = MEDIA_ENTITY_TYPE_VIDEO_DEVICE;
 	vdev->entity.function = MEDIA_ENT_F_UNKNOWN;
 
-	switch (type) {
+	switch (vdev->vfl_type) {
 	case VFL_TYPE_GRABBER:
 		intf_type = MEDIA_INTF_T_V4L_VIDEO;
 		vdev->entity.function = MEDIA_ENT_F_IO_V4L;
@@ -808,7 +811,8 @@ static int video_register_media_controller(struct video_device *vdev, int type)
 
 		link = media_create_intf_link(&vdev->entity,
 					      &vdev->intf_devnode->intf,
-					      MEDIA_LNK_FL_ENABLED);
+					      MEDIA_LNK_FL_ENABLED |
+					      MEDIA_LNK_FL_IMMUTABLE);
 		if (!link) {
 			media_devnode_remove(vdev->intf_devnode);
 			media_device_unregister_entity(&vdev->entity);
@@ -993,7 +997,7 @@ int __video_register_device(struct video_device *vdev,
 	v4l2_device_get(vdev->v4l2_dev);
 
 	/* Part 5: Register the entity. */
-	ret = video_register_media_controller(vdev, type);
+	ret = video_register_media_controller(vdev);
 
 	/* Part 6: Activate this minor. The char device can now be used. */
 	set_bit(V4L2_FL_REGISTERED, &vdev->flags);
diff --git a/drivers/media/v4l2-core/v4l2-device.c b/drivers/media/v4l2-core/v4l2-device.c
index 937c6de85606..3940e55c72f1 100644
--- a/drivers/media/v4l2-core/v4l2-device.c
+++ b/drivers/media/v4l2-core/v4l2-device.c
@@ -267,7 +267,8 @@ int v4l2_device_register_subdev_nodes(struct v4l2_device *v4l2_dev)
 
 			link = media_create_intf_link(&sd->entity,
 						      &vdev->intf_devnode->intf,
-						      MEDIA_LNK_FL_ENABLED);
+						      MEDIA_LNK_FL_ENABLED |
+						      MEDIA_LNK_FL_IMMUTABLE);
 			if (!link) {
 				err = -ENOMEM;
 				goto clean_up;
diff --git a/drivers/media/v4l2-core/v4l2-fwnode.c b/drivers/media/v4l2-core/v4l2-fwnode.c
index 3f77aa318035..169bdbb1f61a 100644
--- a/drivers/media/v4l2-core/v4l2-fwnode.c
+++ b/drivers/media/v4l2-core/v4l2-fwnode.c
@@ -154,6 +154,10 @@ static void v4l2_fwnode_endpoint_parse_parallel_bus(
 		flags |= v ? V4L2_MBUS_VIDEO_SOG_ACTIVE_HIGH :
 			V4L2_MBUS_VIDEO_SOG_ACTIVE_LOW;
 
+	if (!fwnode_property_read_u32(fwnode, "data-enable-active", &v))
+		flags |= v ? V4L2_MBUS_DATA_ENABLE_HIGH :
+			V4L2_MBUS_DATA_ENABLE_LOW;
+
 	bus->flags = flags;
 
 }
@@ -739,7 +743,7 @@ static struct fwnode_handle *v4l2_fwnode_reference_get_int_prop(
 	const char * const *props, unsigned int nprops)
 {
 	struct fwnode_reference_args fwnode_args;
-	unsigned int *args = fwnode_args.args;
+	u64 *args = fwnode_args.args;
 	struct fwnode_handle *child;
 	int ret;
 
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index dd210067151f..54afc9c7ee6e 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -29,6 +29,7 @@
 #include <media/v4l2-device.h>
 #include <media/videobuf2-v4l2.h>
 #include <media/v4l2-mc.h>
+#include <media/v4l2-mem2mem.h>
 
 #include <trace/events/v4l2.h>
 
@@ -125,6 +126,42 @@ int v4l2_video_std_construct(struct v4l2_standard *vs,
 }
 EXPORT_SYMBOL(v4l2_video_std_construct);
 
+/* Fill in the fields of a v4l2_standard structure according to the
+ * 'id' and 'vs->index' parameters. Returns negative on error. */
+int v4l_video_std_enumstd(struct v4l2_standard *vs, v4l2_std_id id)
+{
+	v4l2_std_id curr_id = 0;
+	unsigned int index = vs->index, i, j = 0;
+	const char *descr = "";
+
+	/* Return -ENODATA if the id for the current input
+	   or output is 0, meaning that it doesn't support this API. */
+	if (id == 0)
+		return -ENODATA;
+
+	/* Return norm array in a canonical way */
+	for (i = 0; i <= index && id; i++) {
+		/* last std value in the standards array is 0, so this
+		   while always ends there since (id & 0) == 0. */
+		while ((id & standards[j].std) != standards[j].std)
+			j++;
+		curr_id = standards[j].std;
+		descr = standards[j].descr;
+		j++;
+		if (curr_id == 0)
+			break;
+		if (curr_id != V4L2_STD_PAL &&
+				curr_id != V4L2_STD_SECAM &&
+				curr_id != V4L2_STD_NTSC)
+			id &= ~curr_id;
+	}
+	if (i <= index)
+		return -EINVAL;
+
+	v4l2_video_std_construct(vs, curr_id, descr);
+	return 0;
+}
+
 /* ----------------------------------------------------------------- */
 /* some arrays for pretty-printing debug messages of enum types      */
 
@@ -1147,6 +1184,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt)
 	case V4L2_PIX_FMT_Y16:		descr = "16-bit Greyscale"; break;
 	case V4L2_PIX_FMT_Y16_BE:	descr = "16-bit Greyscale BE"; break;
 	case V4L2_PIX_FMT_Y10BPACK:	descr = "10-bit Greyscale (Packed)"; break;
+	case V4L2_PIX_FMT_Y10P:		descr = "10-bit Greyscale (MIPI Packed)"; break;
 	case V4L2_PIX_FMT_Y8I:		descr = "Interleaved 8-bit Greyscale"; break;
 	case V4L2_PIX_FMT_Y12I:		descr = "Interleaved 12-bit Greyscale"; break;
 	case V4L2_PIX_FMT_Z16:		descr = "16-bit Depth"; break;
@@ -1222,6 +1260,10 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt)
 	case V4L2_PIX_FMT_SGBRG12P:	descr = "12-bit Bayer GBGB/RGRG Packed"; break;
 	case V4L2_PIX_FMT_SGRBG12P:	descr = "12-bit Bayer GRGR/BGBG Packed"; break;
 	case V4L2_PIX_FMT_SRGGB12P:	descr = "12-bit Bayer RGRG/GBGB Packed"; break;
+	case V4L2_PIX_FMT_SBGGR14P:	descr = "14-bit Bayer BGBG/GRGR Packed"; break;
+	case V4L2_PIX_FMT_SGBRG14P:	descr = "14-bit Bayer GBGB/RGRG Packed"; break;
+	case V4L2_PIX_FMT_SGRBG14P:	descr = "14-bit Bayer GRGR/BGBG Packed"; break;
+	case V4L2_PIX_FMT_SRGGB14P:	descr = "14-bit Bayer RGRG/GBGB Packed"; break;
 	case V4L2_PIX_FMT_SBGGR16:	descr = "16-bit Bayer BGBG/GRGR"; break;
 	case V4L2_PIX_FMT_SGBRG16:	descr = "16-bit Bayer GBGB/RGRG"; break;
 	case V4L2_PIX_FMT_SGRBG16:	descr = "16-bit Bayer GRGR/BGBG"; break;
@@ -1274,6 +1316,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt)
 		case V4L2_PIX_FMT_VP8:		descr = "VP8"; break;
 		case V4L2_PIX_FMT_VP9:		descr = "VP9"; break;
 		case V4L2_PIX_FMT_HEVC:		descr = "HEVC"; break; /* aka H.265 */
+		case V4L2_PIX_FMT_FWHT:		descr = "FWHT"; break; /* used in vicodec */
 		case V4L2_PIX_FMT_CPIA1:	descr = "GSPCA CPiA YUV"; break;
 		case V4L2_PIX_FMT_WNVA:		descr = "WNVA"; break;
 		case V4L2_PIX_FMT_SN9C10X:	descr = "GSPCA SN9C10X"; break;
@@ -1753,36 +1796,8 @@ static int v4l_enumstd(const struct v4l2_ioctl_ops *ops,
 {
 	struct video_device *vfd = video_devdata(file);
 	struct v4l2_standard *p = arg;
-	v4l2_std_id id = vfd->tvnorms, curr_id = 0;
-	unsigned int index = p->index, i, j = 0;
-	const char *descr = "";
-
-	/* Return -ENODATA if the tvnorms for the current input
-	   or output is 0, meaning that it doesn't support this API. */
-	if (id == 0)
-		return -ENODATA;
 
-	/* Return norm array in a canonical way */
-	for (i = 0; i <= index && id; i++) {
-		/* last std value in the standards array is 0, so this
-		   while always ends there since (id & 0) == 0. */
-		while ((id & standards[j].std) != standards[j].std)
-			j++;
-		curr_id = standards[j].std;
-		descr = standards[j].descr;
-		j++;
-		if (curr_id == 0)
-			break;
-		if (curr_id != V4L2_STD_PAL &&
-				curr_id != V4L2_STD_SECAM &&
-				curr_id != V4L2_STD_NTSC)
-			id &= ~curr_id;
-	}
-	if (i <= index)
-		return -EINVAL;
-
-	v4l2_video_std_construct(p, curr_id, descr);
-	return 0;
+	return v4l_video_std_enumstd(p, vfd->tvnorms);
 }
 
 static int v4l_s_std(const struct v4l2_ioctl_ops *ops,
@@ -2662,11 +2677,62 @@ static bool v4l2_is_known_ioctl(unsigned int cmd)
 	return v4l2_ioctls[_IOC_NR(cmd)].ioctl == cmd;
 }
 
+#if IS_ENABLED(CONFIG_V4L2_MEM2MEM_DEV)
+static bool v4l2_ioctl_m2m_queue_is_output(unsigned int cmd, void *arg)
+{
+	switch (cmd) {
+	case VIDIOC_CREATE_BUFS: {
+		struct v4l2_create_buffers *cbufs = arg;
+
+		return V4L2_TYPE_IS_OUTPUT(cbufs->format.type);
+	}
+	case VIDIOC_REQBUFS: {
+		struct v4l2_requestbuffers *rbufs = arg;
+
+		return V4L2_TYPE_IS_OUTPUT(rbufs->type);
+	}
+	case VIDIOC_QBUF:
+	case VIDIOC_DQBUF:
+	case VIDIOC_QUERYBUF:
+	case VIDIOC_PREPARE_BUF: {
+		struct v4l2_buffer *buf = arg;
+
+		return V4L2_TYPE_IS_OUTPUT(buf->type);
+	}
+	case VIDIOC_EXPBUF: {
+		struct v4l2_exportbuffer *expbuf = arg;
+
+		return V4L2_TYPE_IS_OUTPUT(expbuf->type);
+	}
+	case VIDIOC_STREAMON:
+	case VIDIOC_STREAMOFF: {
+		int *type = arg;
+
+		return V4L2_TYPE_IS_OUTPUT(*type);
+	}
+	default:
+		return false;
+	}
+}
+#endif
+
 static struct mutex *v4l2_ioctl_get_lock(struct video_device *vdev,
-					 unsigned int cmd)
+					 struct v4l2_fh *vfh, unsigned int cmd,
+					 void *arg)
 {
 	if (_IOC_NR(cmd) >= V4L2_IOCTLS)
 		return vdev->lock;
+#if IS_ENABLED(CONFIG_V4L2_MEM2MEM_DEV)
+	if (vfh && vfh->m2m_ctx &&
+	    (v4l2_ioctls[_IOC_NR(cmd)].flags & INFO_FL_QUEUE)) {
+		bool is_output = v4l2_ioctl_m2m_queue_is_output(cmd, arg);
+		struct v4l2_m2m_queue_ctx *ctx = is_output ?
+			&vfh->m2m_ctx->out_q_ctx : &vfh->m2m_ctx->cap_q_ctx;
+
+		if (ctx->q.lock)
+			return ctx->q.lock;
+	}
+#endif
 	if (vdev->queue && vdev->queue->lock &&
 			(v4l2_ioctls[_IOC_NR(cmd)].flags & INFO_FL_QUEUE))
 		return vdev->queue->lock;
@@ -2733,7 +2799,7 @@ static long __video_do_ioctl(struct file *file,
 	if (test_bit(V4L2_FL_USES_V4L2_FH, &vfd->flags))
 		vfh = file->private_data;
 
-	lock = v4l2_ioctl_get_lock(vfd, cmd);
+	lock = v4l2_ioctl_get_lock(vfd, vfh, cmd, arg);
 
 	if (lock && mutex_lock_interruptible(lock))
 		return -ERESTARTSYS;
diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c
index c4f963d96a79..ce9bd1b91210 100644
--- a/drivers/media/v4l2-core/v4l2-mem2mem.c
+++ b/drivers/media/v4l2-core/v4l2-mem2mem.c
@@ -17,9 +17,11 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 
+#include <media/media-device.h>
 #include <media/videobuf2-v4l2.h>
 #include <media/v4l2-mem2mem.h>
 #include <media/v4l2-dev.h>
+#include <media/v4l2-device.h>
 #include <media/v4l2-fh.h>
 #include <media/v4l2-event.h>
 
@@ -50,9 +52,38 @@ module_param(debug, bool, 0644);
  * offsets but for different queues */
 #define DST_QUEUE_OFF_BASE	(1 << 30)
 
+enum v4l2_m2m_entity_type {
+	MEM2MEM_ENT_TYPE_SOURCE,
+	MEM2MEM_ENT_TYPE_SINK,
+	MEM2MEM_ENT_TYPE_PROC
+};
+
+static const char * const m2m_entity_name[] = {
+	"source",
+	"sink",
+	"proc"
+};
 
 /**
  * struct v4l2_m2m_dev - per-device context
+ * @source:		&struct media_entity pointer with the source entity
+ *			Used only when the M2M device is registered via
+ *			v4l2_m2m_unregister_media_controller().
+ * @source_pad:		&struct media_pad with the source pad.
+ *			Used only when the M2M device is registered via
+ *			v4l2_m2m_unregister_media_controller().
+ * @sink:		&struct media_entity pointer with the sink entity
+ *			Used only when the M2M device is registered via
+ *			v4l2_m2m_unregister_media_controller().
+ * @sink_pad:		&struct media_pad with the sink pad.
+ *			Used only when the M2M device is registered via
+ *			v4l2_m2m_unregister_media_controller().
+ * @proc:		&struct media_entity pointer with the M2M device itself.
+ * @proc_pads:		&struct media_pad with the @proc pads.
+ *			Used only when the M2M device is registered via
+ *			v4l2_m2m_unregister_media_controller().
+ * @intf_devnode:	&struct media_intf devnode pointer with the interface
+ *			with controls the M2M device.
  * @curr_ctx:		currently running instance
  * @job_queue:		instances queued to run
  * @job_spinlock:	protects job_queue
@@ -60,6 +91,15 @@ module_param(debug, bool, 0644);
  */
 struct v4l2_m2m_dev {
 	struct v4l2_m2m_ctx	*curr_ctx;
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct media_entity	*source;
+	struct media_pad	source_pad;
+	struct media_entity	sink;
+	struct media_pad	sink_pad;
+	struct media_entity	proc;
+	struct media_pad	proc_pads[2];
+	struct media_intf_devnode *intf_devnode;
+#endif
 
 	struct list_head	job_queue;
 	spinlock_t		job_spinlock;
@@ -107,6 +147,24 @@ void *v4l2_m2m_next_buf(struct v4l2_m2m_queue_ctx *q_ctx)
 }
 EXPORT_SYMBOL_GPL(v4l2_m2m_next_buf);
 
+void *v4l2_m2m_last_buf(struct v4l2_m2m_queue_ctx *q_ctx)
+{
+	struct v4l2_m2m_buffer *b;
+	unsigned long flags;
+
+	spin_lock_irqsave(&q_ctx->rdy_spinlock, flags);
+
+	if (list_empty(&q_ctx->rdy_queue)) {
+		spin_unlock_irqrestore(&q_ctx->rdy_spinlock, flags);
+		return NULL;
+	}
+
+	b = list_last_entry(&q_ctx->rdy_queue, struct v4l2_m2m_buffer, list);
+	spin_unlock_irqrestore(&q_ctx->rdy_spinlock, flags);
+	return &b->vb;
+}
+EXPORT_SYMBOL_GPL(v4l2_m2m_last_buf);
+
 void *v4l2_m2m_buf_remove(struct v4l2_m2m_queue_ctx *q_ctx)
 {
 	struct v4l2_m2m_buffer *b;
@@ -209,15 +267,24 @@ static void v4l2_m2m_try_run(struct v4l2_m2m_dev *m2m_dev)
 	m2m_dev->curr_ctx->job_flags |= TRANS_RUNNING;
 	spin_unlock_irqrestore(&m2m_dev->job_spinlock, flags);
 
+	dprintk("Running job on m2m_ctx: %p\n", m2m_dev->curr_ctx);
 	m2m_dev->m2m_ops->device_run(m2m_dev->curr_ctx->priv);
 }
 
-void v4l2_m2m_try_schedule(struct v4l2_m2m_ctx *m2m_ctx)
+/*
+ * __v4l2_m2m_try_queue() - queue a job
+ * @m2m_dev: m2m device
+ * @m2m_ctx: m2m context
+ *
+ * Check if this context is ready to queue a job.
+ *
+ * This function can run in interrupt context.
+ */
+static void __v4l2_m2m_try_queue(struct v4l2_m2m_dev *m2m_dev,
+				 struct v4l2_m2m_ctx *m2m_ctx)
 {
-	struct v4l2_m2m_dev *m2m_dev;
 	unsigned long flags_job, flags_out, flags_cap;
 
-	m2m_dev = m2m_ctx->m2m_dev;
 	dprintk("Trying to schedule a job for m2m_ctx: %p\n", m2m_ctx);
 
 	if (!m2m_ctx->out_q_ctx.q.streaming
@@ -275,7 +342,25 @@ void v4l2_m2m_try_schedule(struct v4l2_m2m_ctx *m2m_ctx)
 	m2m_ctx->job_flags |= TRANS_QUEUED;
 
 	spin_unlock_irqrestore(&m2m_dev->job_spinlock, flags_job);
+}
 
+/**
+ * v4l2_m2m_try_schedule() - schedule and possibly run a job for any context
+ * @m2m_ctx: m2m context
+ *
+ * Check if this context is ready to queue a job. If suitable,
+ * run the next queued job on the mem2mem device.
+ *
+ * This function shouldn't run in interrupt context.
+ *
+ * Note that v4l2_m2m_try_schedule() can schedule one job for this context,
+ * and then run another job for another context.
+ */
+void v4l2_m2m_try_schedule(struct v4l2_m2m_ctx *m2m_ctx)
+{
+	struct v4l2_m2m_dev *m2m_dev = m2m_ctx->m2m_dev;
+
+	__v4l2_m2m_try_queue(m2m_dev, m2m_ctx);
 	v4l2_m2m_try_run(m2m_dev);
 }
 EXPORT_SYMBOL_GPL(v4l2_m2m_try_schedule);
@@ -300,7 +385,8 @@ static void v4l2_m2m_cancel_job(struct v4l2_m2m_ctx *m2m_ctx)
 	m2m_ctx->job_flags |= TRANS_ABORT;
 	if (m2m_ctx->job_flags & TRANS_RUNNING) {
 		spin_unlock_irqrestore(&m2m_dev->job_spinlock, flags);
-		m2m_dev->m2m_ops->job_abort(m2m_ctx->priv);
+		if (m2m_dev->m2m_ops->job_abort)
+			m2m_dev->m2m_ops->job_abort(m2m_ctx->priv);
 		dprintk("m2m_ctx %p running, will wait to complete", m2m_ctx);
 		wait_event(m2m_ctx->finished,
 				!(m2m_ctx->job_flags & TRANS_RUNNING));
@@ -339,7 +425,6 @@ void v4l2_m2m_job_finish(struct v4l2_m2m_dev *m2m_dev,
 	 * allow more than one job on the job_queue per instance, each has
 	 * to be scheduled separately after the previous one finishes. */
 	v4l2_m2m_try_schedule(m2m_ctx);
-	v4l2_m2m_try_run(m2m_dev);
 }
 EXPORT_SYMBOL(v4l2_m2m_job_finish);
 
@@ -595,12 +680,179 @@ int v4l2_m2m_mmap(struct file *file, struct v4l2_m2m_ctx *m2m_ctx,
 }
 EXPORT_SYMBOL(v4l2_m2m_mmap);
 
+#if defined(CONFIG_MEDIA_CONTROLLER)
+void v4l2_m2m_unregister_media_controller(struct v4l2_m2m_dev *m2m_dev)
+{
+	media_remove_intf_links(&m2m_dev->intf_devnode->intf);
+	media_devnode_remove(m2m_dev->intf_devnode);
+
+	media_entity_remove_links(m2m_dev->source);
+	media_entity_remove_links(&m2m_dev->sink);
+	media_entity_remove_links(&m2m_dev->proc);
+	media_device_unregister_entity(m2m_dev->source);
+	media_device_unregister_entity(&m2m_dev->sink);
+	media_device_unregister_entity(&m2m_dev->proc);
+	kfree(m2m_dev->source->name);
+	kfree(m2m_dev->sink.name);
+	kfree(m2m_dev->proc.name);
+}
+EXPORT_SYMBOL_GPL(v4l2_m2m_unregister_media_controller);
+
+static int v4l2_m2m_register_entity(struct media_device *mdev,
+	struct v4l2_m2m_dev *m2m_dev, enum v4l2_m2m_entity_type type,
+	struct video_device *vdev, int function)
+{
+	struct media_entity *entity;
+	struct media_pad *pads;
+	char *name;
+	unsigned int len;
+	int num_pads;
+	int ret;
+
+	switch (type) {
+	case MEM2MEM_ENT_TYPE_SOURCE:
+		entity = m2m_dev->source;
+		pads = &m2m_dev->source_pad;
+		pads[0].flags = MEDIA_PAD_FL_SOURCE;
+		num_pads = 1;
+		break;
+	case MEM2MEM_ENT_TYPE_SINK:
+		entity = &m2m_dev->sink;
+		pads = &m2m_dev->sink_pad;
+		pads[0].flags = MEDIA_PAD_FL_SINK;
+		num_pads = 1;
+		break;
+	case MEM2MEM_ENT_TYPE_PROC:
+		entity = &m2m_dev->proc;
+		pads = m2m_dev->proc_pads;
+		pads[0].flags = MEDIA_PAD_FL_SINK;
+		pads[1].flags = MEDIA_PAD_FL_SOURCE;
+		num_pads = 2;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	entity->obj_type = MEDIA_ENTITY_TYPE_BASE;
+	if (type != MEM2MEM_ENT_TYPE_PROC) {
+		entity->info.dev.major = VIDEO_MAJOR;
+		entity->info.dev.minor = vdev->minor;
+	}
+	len = strlen(vdev->name) + 2 + strlen(m2m_entity_name[type]);
+	name = kmalloc(len, GFP_KERNEL);
+	if (!name)
+		return -ENOMEM;
+	snprintf(name, len, "%s-%s", vdev->name, m2m_entity_name[type]);
+	entity->name = name;
+	entity->function = function;
+
+	ret = media_entity_pads_init(entity, num_pads, pads);
+	if (ret)
+		return ret;
+	ret = media_device_register_entity(mdev, entity);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+int v4l2_m2m_register_media_controller(struct v4l2_m2m_dev *m2m_dev,
+		struct video_device *vdev, int function)
+{
+	struct media_device *mdev = vdev->v4l2_dev->mdev;
+	struct media_link *link;
+	int ret;
+
+	if (!mdev)
+		return 0;
+
+	/* A memory-to-memory device consists in two
+	 * DMA engine and one video processing entities.
+	 * The DMA engine entities are linked to a V4L interface
+	 */
+
+	/* Create the three entities with their pads */
+	m2m_dev->source = &vdev->entity;
+	ret = v4l2_m2m_register_entity(mdev, m2m_dev,
+			MEM2MEM_ENT_TYPE_SOURCE, vdev, MEDIA_ENT_F_IO_V4L);
+	if (ret)
+		return ret;
+	ret = v4l2_m2m_register_entity(mdev, m2m_dev,
+			MEM2MEM_ENT_TYPE_PROC, vdev, function);
+	if (ret)
+		goto err_rel_entity0;
+	ret = v4l2_m2m_register_entity(mdev, m2m_dev,
+			MEM2MEM_ENT_TYPE_SINK, vdev, MEDIA_ENT_F_IO_V4L);
+	if (ret)
+		goto err_rel_entity1;
+
+	/* Connect the three entities */
+	ret = media_create_pad_link(m2m_dev->source, 0, &m2m_dev->proc, 1,
+			MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED);
+	if (ret)
+		goto err_rel_entity2;
+
+	ret = media_create_pad_link(&m2m_dev->proc, 0, &m2m_dev->sink, 0,
+			MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED);
+	if (ret)
+		goto err_rm_links0;
+
+	/* Create video interface */
+	m2m_dev->intf_devnode = media_devnode_create(mdev,
+			MEDIA_INTF_T_V4L_VIDEO, 0,
+			VIDEO_MAJOR, vdev->minor);
+	if (!m2m_dev->intf_devnode) {
+		ret = -ENOMEM;
+		goto err_rm_links1;
+	}
+
+	/* Connect the two DMA engines to the interface */
+	link = media_create_intf_link(m2m_dev->source,
+			&m2m_dev->intf_devnode->intf,
+			MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED);
+	if (!link) {
+		ret = -ENOMEM;
+		goto err_rm_devnode;
+	}
+
+	link = media_create_intf_link(&m2m_dev->sink,
+			&m2m_dev->intf_devnode->intf,
+			MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED);
+	if (!link) {
+		ret = -ENOMEM;
+		goto err_rm_intf_link;
+	}
+	return 0;
+
+err_rm_intf_link:
+	media_remove_intf_links(&m2m_dev->intf_devnode->intf);
+err_rm_devnode:
+	media_devnode_remove(m2m_dev->intf_devnode);
+err_rm_links1:
+	media_entity_remove_links(&m2m_dev->sink);
+err_rm_links0:
+	media_entity_remove_links(&m2m_dev->proc);
+	media_entity_remove_links(m2m_dev->source);
+err_rel_entity2:
+	media_device_unregister_entity(&m2m_dev->proc);
+	kfree(m2m_dev->proc.name);
+err_rel_entity1:
+	media_device_unregister_entity(&m2m_dev->sink);
+	kfree(m2m_dev->sink.name);
+err_rel_entity0:
+	media_device_unregister_entity(m2m_dev->source);
+	kfree(m2m_dev->source->name);
+	return ret;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(v4l2_m2m_register_media_controller);
+#endif
+
 struct v4l2_m2m_dev *v4l2_m2m_init(const struct v4l2_m2m_ops *m2m_ops)
 {
 	struct v4l2_m2m_dev *m2m_dev;
 
-	if (!m2m_ops || WARN_ON(!m2m_ops->device_run) ||
-			WARN_ON(!m2m_ops->job_abort))
+	if (!m2m_ops || WARN_ON(!m2m_ops->device_run))
 		return ERR_PTR(-EINVAL);
 
 	m2m_dev = kzalloc(sizeof *m2m_dev, GFP_KERNEL);
diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c
index 6a7f7f75dfd7..2b63fa6b6fc9 100644
--- a/drivers/media/v4l2-core/v4l2-subdev.c
+++ b/drivers/media/v4l2-core/v4l2-subdev.c
@@ -494,6 +494,28 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg)
 
 	case VIDIOC_SUBDEV_S_DV_TIMINGS:
 		return v4l2_subdev_call(sd, video, s_dv_timings, arg);
+
+	case VIDIOC_SUBDEV_G_STD:
+		return v4l2_subdev_call(sd, video, g_std, arg);
+
+	case VIDIOC_SUBDEV_S_STD: {
+		v4l2_std_id *std = arg;
+
+		return v4l2_subdev_call(sd, video, s_std, *std);
+	}
+
+	case VIDIOC_SUBDEV_ENUMSTD: {
+		struct v4l2_standard *p = arg;
+		v4l2_std_id id;
+
+		if (v4l2_subdev_call(sd, video, g_tvnorms, &id))
+			return -EINVAL;
+
+		return v4l_video_std_enumstd(p, id);
+	}
+
+	case VIDIOC_SUBDEV_QUERYSTD:
+		return v4l2_subdev_call(sd, video, querystd, arg);
 #endif
 	default:
 		return v4l2_subdev_call(sd, core, ioctl, cmd, arg);
diff --git a/drivers/memory/Kconfig b/drivers/memory/Kconfig
index 8d731d6c3e54..63389f075f1d 100644
--- a/drivers/memory/Kconfig
+++ b/drivers/memory/Kconfig
@@ -116,12 +116,14 @@ config FSL_CORENET_CF
 
 config FSL_IFC
 	bool
-	depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A
+	depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A || COMPILE_TEST
+	depends on HAS_IOMEM
 
 config JZ4780_NEMC
 	bool "Ingenic JZ4780 SoC NEMC driver"
 	default y
-	depends on MACH_JZ4780
+	depends on MACH_JZ4780 || COMPILE_TEST
+	depends on HAS_IOMEM && OF
 	help
 	  This driver is for the NAND/External Memory Controller (NEMC) in
 	  the Ingenic JZ4780. This controller is used to handle external
diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c
index a625ac4e2872..e6b4ae558767 100644
--- a/drivers/message/fusion/mptbase.c
+++ b/drivers/message/fusion/mptbase.c
@@ -642,6 +642,7 @@ mptbase_reply(MPT_ADAPTER *ioc, MPT_FRAME_HDR *req, MPT_FRAME_HDR *reply)
 			freereq = 0;
 		if (event != MPI_EVENT_EVENT_CHANGE)
 			break;
+		/* else: fall through */
 	case MPI_FUNCTION_CONFIG:
 	case MPI_FUNCTION_SAS_IO_UNIT_CONTROL:
 		ioc->mptbase_cmds.status |= MPT_MGMT_STATUS_COMMAND_GOOD;
@@ -1779,7 +1780,7 @@ mpt_attach(struct pci_dev *pdev, const struct pci_device_id *id)
 	struct proc_dir_entry *dent;
 #endif
 
-	ioc = kzalloc(sizeof(MPT_ADAPTER), GFP_ATOMIC);
+	ioc = kzalloc(sizeof(MPT_ADAPTER), GFP_KERNEL);
 	if (ioc == NULL) {
 		printk(KERN_ERR MYNAM ": ERROR - Insufficient memory to add adapter!\n");
 		return -ENOMEM;
@@ -1886,6 +1887,7 @@ mpt_attach(struct pci_dev *pdev, const struct pci_device_id *id)
 	case MPI_MANUFACTPAGE_DEVICEID_FC939X:
 	case MPI_MANUFACTPAGE_DEVICEID_FC949X:
 		ioc->errata_flag_1064 = 1;
+		/* fall through */
 	case MPI_MANUFACTPAGE_DEVICEID_FC909:
 	case MPI_MANUFACTPAGE_DEVICEID_FC929:
 	case MPI_MANUFACTPAGE_DEVICEID_FC919:
@@ -1930,6 +1932,7 @@ mpt_attach(struct pci_dev *pdev, const struct pci_device_id *id)
 			pcixcmd &= 0x8F;
 			pci_write_config_byte(pdev, 0x6a, pcixcmd);
 		}
+		/* fall through */
 
 	case MPI_MANUFACTPAGE_DEVID_1030_53C1035:
 		ioc->bus_type = SPI;
diff --git a/drivers/message/fusion/mptctl.c b/drivers/message/fusion/mptctl.c
index 4470630dd545..8d22d6134a89 100644
--- a/drivers/message/fusion/mptctl.c
+++ b/drivers/message/fusion/mptctl.c
@@ -2514,8 +2514,8 @@ mptctl_hp_hostinfo(unsigned long arg, unsigned int data_size)
 				if (mpt_config(ioc, &cfg) == 0) {
 					ManufacturingPage0_t *pdata = (ManufacturingPage0_t *) pbuf;
 					if (strlen(pdata->BoardTracerNumber) > 1) {
-						strncpy(karg.serial_number, 									    pdata->BoardTracerNumber, 24);
-						karg.serial_number[24-1]='\0';
+						strlcpy(karg.serial_number,
+							pdata->BoardTracerNumber, 24);
 					}
 				}
 				pci_free_consistent(ioc->pcidev, hdr.PageLength * 4, pbuf, buf_dma);
diff --git a/drivers/message/fusion/mptfc.c b/drivers/message/fusion/mptfc.c
index 06b175420be9..b15fdc626fb8 100644
--- a/drivers/message/fusion/mptfc.c
+++ b/drivers/message/fusion/mptfc.c
@@ -1292,7 +1292,7 @@ mptfc_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	/* SCSI needs scsi_cmnd lookup table!
 	 * (with size equal to req_depth*PtrSz!)
 	 */
-	ioc->ScsiLookup = kcalloc(ioc->req_depth, sizeof(void *), GFP_ATOMIC);
+	ioc->ScsiLookup = kcalloc(ioc->req_depth, sizeof(void *), GFP_KERNEL);
 	if (!ioc->ScsiLookup) {
 		error = -ENOMEM;
 		goto out_mptfc_probe;
diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c
index 76a66da33996..b8cf2658649e 100644
--- a/drivers/message/fusion/mptsas.c
+++ b/drivers/message/fusion/mptsas.c
@@ -4327,6 +4327,7 @@ mptsas_hotplug_work(MPT_ADAPTER *ioc, struct fw_event_work *fw_event,
 			}
 		}
 		mpt_findImVolumes(ioc);
+		/* fall through */
 
 	case MPTSAS_ADD_DEVICE:
 		memset(&sas_device, 0, sizeof(struct mptsas_devinfo));
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 6b16946f9b05..8fd5ec4d6042 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -67,10 +67,8 @@ static struct file *cxl_getfile(const char *name,
 				const struct file_operations *fops,
 				void *priv, int flags)
 {
-	struct qstr this;
-	struct path path;
 	struct file *file;
-	struct inode *inode = NULL;
+	struct inode *inode;
 	int rc;
 
 	/* strongly inspired by anon_inode_getfile() */
@@ -91,23 +89,11 @@ static struct file *cxl_getfile(const char *name,
 		goto err_fs;
 	}
 
-	file = ERR_PTR(-ENOMEM);
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0;
-	path.dentry = d_alloc_pseudo(cxl_vfs_mount->mnt_sb, &this);
-	if (!path.dentry)
+	file = alloc_file_pseudo(inode, cxl_vfs_mount, name,
+				 flags & (O_ACCMODE | O_NONBLOCK), fops);
+	if (IS_ERR(file))
 		goto err_inode;
 
-	path.mnt = mntget(cxl_vfs_mount);
-	d_instantiate(path.dentry, inode);
-
-	file = alloc_file(&path, OPEN_FMODE(flags), fops);
-	if (IS_ERR(file)) {
-		path_put(&path);
-		goto err_fs;
-	}
-	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
 	file->private_data = priv;
 
 	return file;
diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c
index 7b370466a227..896e2df9400f 100644
--- a/drivers/misc/pci_endpoint_test.c
+++ b/drivers/misc/pci_endpoint_test.c
@@ -35,38 +35,45 @@
 
 #include <uapi/linux/pcitest.h>
 
-#define DRV_MODULE_NAME			"pci-endpoint-test"
-
-#define PCI_ENDPOINT_TEST_MAGIC		0x0
-
-#define PCI_ENDPOINT_TEST_COMMAND	0x4
-#define COMMAND_RAISE_LEGACY_IRQ	BIT(0)
-#define COMMAND_RAISE_MSI_IRQ		BIT(1)
-#define MSI_NUMBER_SHIFT		2
-/* 6 bits for MSI number */
-#define COMMAND_READ                    BIT(8)
-#define COMMAND_WRITE                   BIT(9)
-#define COMMAND_COPY                    BIT(10)
-
-#define PCI_ENDPOINT_TEST_STATUS	0x8
-#define STATUS_READ_SUCCESS             BIT(0)
-#define STATUS_READ_FAIL                BIT(1)
-#define STATUS_WRITE_SUCCESS            BIT(2)
-#define STATUS_WRITE_FAIL               BIT(3)
-#define STATUS_COPY_SUCCESS             BIT(4)
-#define STATUS_COPY_FAIL                BIT(5)
-#define STATUS_IRQ_RAISED               BIT(6)
-#define STATUS_SRC_ADDR_INVALID         BIT(7)
-#define STATUS_DST_ADDR_INVALID         BIT(8)
-
-#define PCI_ENDPOINT_TEST_LOWER_SRC_ADDR	0xc
+#define DRV_MODULE_NAME				"pci-endpoint-test"
+
+#define IRQ_TYPE_UNDEFINED			-1
+#define IRQ_TYPE_LEGACY				0
+#define IRQ_TYPE_MSI				1
+#define IRQ_TYPE_MSIX				2
+
+#define PCI_ENDPOINT_TEST_MAGIC			0x0
+
+#define PCI_ENDPOINT_TEST_COMMAND		0x4
+#define COMMAND_RAISE_LEGACY_IRQ		BIT(0)
+#define COMMAND_RAISE_MSI_IRQ			BIT(1)
+#define COMMAND_RAISE_MSIX_IRQ			BIT(2)
+#define COMMAND_READ				BIT(3)
+#define COMMAND_WRITE				BIT(4)
+#define COMMAND_COPY				BIT(5)
+
+#define PCI_ENDPOINT_TEST_STATUS		0x8
+#define STATUS_READ_SUCCESS			BIT(0)
+#define STATUS_READ_FAIL			BIT(1)
+#define STATUS_WRITE_SUCCESS			BIT(2)
+#define STATUS_WRITE_FAIL			BIT(3)
+#define STATUS_COPY_SUCCESS			BIT(4)
+#define STATUS_COPY_FAIL			BIT(5)
+#define STATUS_IRQ_RAISED			BIT(6)
+#define STATUS_SRC_ADDR_INVALID			BIT(7)
+#define STATUS_DST_ADDR_INVALID			BIT(8)
+
+#define PCI_ENDPOINT_TEST_LOWER_SRC_ADDR	0x0c
 #define PCI_ENDPOINT_TEST_UPPER_SRC_ADDR	0x10
 
 #define PCI_ENDPOINT_TEST_LOWER_DST_ADDR	0x14
 #define PCI_ENDPOINT_TEST_UPPER_DST_ADDR	0x18
 
-#define PCI_ENDPOINT_TEST_SIZE		0x1c
-#define PCI_ENDPOINT_TEST_CHECKSUM	0x20
+#define PCI_ENDPOINT_TEST_SIZE			0x1c
+#define PCI_ENDPOINT_TEST_CHECKSUM		0x20
+
+#define PCI_ENDPOINT_TEST_IRQ_TYPE		0x24
+#define PCI_ENDPOINT_TEST_IRQ_NUMBER		0x28
 
 static DEFINE_IDA(pci_endpoint_test_ida);
 
@@ -77,6 +84,10 @@ static bool no_msi;
 module_param(no_msi, bool, 0444);
 MODULE_PARM_DESC(no_msi, "Disable MSI interrupt in pci_endpoint_test");
 
+static int irq_type = IRQ_TYPE_MSI;
+module_param(irq_type, int, 0444);
+MODULE_PARM_DESC(irq_type, "IRQ mode selection in pci_endpoint_test (0 - Legacy, 1 - MSI, 2 - MSI-X)");
+
 enum pci_barno {
 	BAR_0,
 	BAR_1,
@@ -103,7 +114,7 @@ struct pci_endpoint_test {
 struct pci_endpoint_test_data {
 	enum pci_barno test_reg_bar;
 	size_t alignment;
-	bool no_msi;
+	int irq_type;
 };
 
 static inline u32 pci_endpoint_test_readl(struct pci_endpoint_test *test,
@@ -147,6 +158,100 @@ static irqreturn_t pci_endpoint_test_irqhandler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static void pci_endpoint_test_free_irq_vectors(struct pci_endpoint_test *test)
+{
+	struct pci_dev *pdev = test->pdev;
+
+	pci_free_irq_vectors(pdev);
+}
+
+static bool pci_endpoint_test_alloc_irq_vectors(struct pci_endpoint_test *test,
+						int type)
+{
+	int irq = -1;
+	struct pci_dev *pdev = test->pdev;
+	struct device *dev = &pdev->dev;
+	bool res = true;
+
+	switch (type) {
+	case IRQ_TYPE_LEGACY:
+		irq = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_LEGACY);
+		if (irq < 0)
+			dev_err(dev, "Failed to get Legacy interrupt\n");
+		break;
+	case IRQ_TYPE_MSI:
+		irq = pci_alloc_irq_vectors(pdev, 1, 32, PCI_IRQ_MSI);
+		if (irq < 0)
+			dev_err(dev, "Failed to get MSI interrupts\n");
+		break;
+	case IRQ_TYPE_MSIX:
+		irq = pci_alloc_irq_vectors(pdev, 1, 2048, PCI_IRQ_MSIX);
+		if (irq < 0)
+			dev_err(dev, "Failed to get MSI-X interrupts\n");
+		break;
+	default:
+		dev_err(dev, "Invalid IRQ type selected\n");
+	}
+
+	if (irq < 0) {
+		irq = 0;
+		res = false;
+	}
+	test->num_irqs = irq;
+
+	return res;
+}
+
+static void pci_endpoint_test_release_irq(struct pci_endpoint_test *test)
+{
+	int i;
+	struct pci_dev *pdev = test->pdev;
+	struct device *dev = &pdev->dev;
+
+	for (i = 0; i < test->num_irqs; i++)
+		devm_free_irq(dev, pci_irq_vector(pdev, i), test);
+
+	test->num_irqs = 0;
+}
+
+static bool pci_endpoint_test_request_irq(struct pci_endpoint_test *test)
+{
+	int i;
+	int err;
+	struct pci_dev *pdev = test->pdev;
+	struct device *dev = &pdev->dev;
+
+	for (i = 0; i < test->num_irqs; i++) {
+		err = devm_request_irq(dev, pci_irq_vector(pdev, i),
+				       pci_endpoint_test_irqhandler,
+				       IRQF_SHARED, DRV_MODULE_NAME, test);
+		if (err)
+			goto fail;
+	}
+
+	return true;
+
+fail:
+	switch (irq_type) {
+	case IRQ_TYPE_LEGACY:
+		dev_err(dev, "Failed to request IRQ %d for Legacy\n",
+			pci_irq_vector(pdev, i));
+		break;
+	case IRQ_TYPE_MSI:
+		dev_err(dev, "Failed to request IRQ %d for MSI %d\n",
+			pci_irq_vector(pdev, i),
+			i + 1);
+		break;
+	case IRQ_TYPE_MSIX:
+		dev_err(dev, "Failed to request IRQ %d for MSI-X %d\n",
+			pci_irq_vector(pdev, i),
+			i + 1);
+		break;
+	}
+
+	return false;
+}
+
 static bool pci_endpoint_test_bar(struct pci_endpoint_test *test,
 				  enum pci_barno barno)
 {
@@ -179,6 +284,9 @@ static bool pci_endpoint_test_legacy_irq(struct pci_endpoint_test *test)
 {
 	u32 val;
 
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE,
+				 IRQ_TYPE_LEGACY);
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, 0);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND,
 				 COMMAND_RAISE_LEGACY_IRQ);
 	val = wait_for_completion_timeout(&test->irq_raised,
@@ -190,14 +298,18 @@ static bool pci_endpoint_test_legacy_irq(struct pci_endpoint_test *test)
 }
 
 static bool pci_endpoint_test_msi_irq(struct pci_endpoint_test *test,
-				      u8 msi_num)
+				       u16 msi_num, bool msix)
 {
 	u32 val;
 	struct pci_dev *pdev = test->pdev;
 
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE,
+				 msix == false ? IRQ_TYPE_MSI :
+				 IRQ_TYPE_MSIX);
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, msi_num);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND,
-				 msi_num << MSI_NUMBER_SHIFT |
-				 COMMAND_RAISE_MSI_IRQ);
+				 msix == false ? COMMAND_RAISE_MSI_IRQ :
+				 COMMAND_RAISE_MSIX_IRQ);
 	val = wait_for_completion_timeout(&test->irq_raised,
 					  msecs_to_jiffies(1000));
 	if (!val)
@@ -230,6 +342,11 @@ static bool pci_endpoint_test_copy(struct pci_endpoint_test *test, size_t size)
 	if (size > SIZE_MAX - alignment)
 		goto err;
 
+	if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) {
+		dev_err(dev, "Invalid IRQ type option\n");
+		goto err;
+	}
+
 	orig_src_addr = dma_alloc_coherent(dev, size + alignment,
 					   &orig_src_phys_addr, GFP_KERNEL);
 	if (!orig_src_addr) {
@@ -281,8 +398,10 @@ static bool pci_endpoint_test_copy(struct pci_endpoint_test *test, size_t size)
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_SIZE,
 				 size);
 
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE, irq_type);
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, 1);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND,
-				 1 << MSI_NUMBER_SHIFT | COMMAND_COPY);
+				 COMMAND_COPY);
 
 	wait_for_completion(&test->irq_raised);
 
@@ -318,6 +437,11 @@ static bool pci_endpoint_test_write(struct pci_endpoint_test *test, size_t size)
 	if (size > SIZE_MAX - alignment)
 		goto err;
 
+	if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) {
+		dev_err(dev, "Invalid IRQ type option\n");
+		goto err;
+	}
+
 	orig_addr = dma_alloc_coherent(dev, size + alignment, &orig_phys_addr,
 				       GFP_KERNEL);
 	if (!orig_addr) {
@@ -348,8 +472,10 @@ static bool pci_endpoint_test_write(struct pci_endpoint_test *test, size_t size)
 
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_SIZE, size);
 
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE, irq_type);
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, 1);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND,
-				 1 << MSI_NUMBER_SHIFT | COMMAND_READ);
+				 COMMAND_READ);
 
 	wait_for_completion(&test->irq_raised);
 
@@ -379,6 +505,11 @@ static bool pci_endpoint_test_read(struct pci_endpoint_test *test, size_t size)
 	if (size > SIZE_MAX - alignment)
 		goto err;
 
+	if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) {
+		dev_err(dev, "Invalid IRQ type option\n");
+		goto err;
+	}
+
 	orig_addr = dma_alloc_coherent(dev, size + alignment, &orig_phys_addr,
 				       GFP_KERNEL);
 	if (!orig_addr) {
@@ -403,8 +534,10 @@ static bool pci_endpoint_test_read(struct pci_endpoint_test *test, size_t size)
 
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_SIZE, size);
 
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE, irq_type);
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, 1);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND,
-				 1 << MSI_NUMBER_SHIFT | COMMAND_WRITE);
+				 COMMAND_WRITE);
 
 	wait_for_completion(&test->irq_raised);
 
@@ -417,6 +550,38 @@ err:
 	return ret;
 }
 
+static bool pci_endpoint_test_set_irq(struct pci_endpoint_test *test,
+				      int req_irq_type)
+{
+	struct pci_dev *pdev = test->pdev;
+	struct device *dev = &pdev->dev;
+
+	if (req_irq_type < IRQ_TYPE_LEGACY || req_irq_type > IRQ_TYPE_MSIX) {
+		dev_err(dev, "Invalid IRQ type option\n");
+		return false;
+	}
+
+	if (irq_type == req_irq_type)
+		return true;
+
+	pci_endpoint_test_release_irq(test);
+	pci_endpoint_test_free_irq_vectors(test);
+
+	if (!pci_endpoint_test_alloc_irq_vectors(test, req_irq_type))
+		goto err;
+
+	if (!pci_endpoint_test_request_irq(test))
+		goto err;
+
+	irq_type = req_irq_type;
+	return true;
+
+err:
+	pci_endpoint_test_free_irq_vectors(test);
+	irq_type = IRQ_TYPE_UNDEFINED;
+	return false;
+}
+
 static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd,
 				    unsigned long arg)
 {
@@ -436,7 +601,8 @@ static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd,
 		ret = pci_endpoint_test_legacy_irq(test);
 		break;
 	case PCITEST_MSI:
-		ret = pci_endpoint_test_msi_irq(test, arg);
+	case PCITEST_MSIX:
+		ret = pci_endpoint_test_msi_irq(test, arg, cmd == PCITEST_MSIX);
 		break;
 	case PCITEST_WRITE:
 		ret = pci_endpoint_test_write(test, arg);
@@ -447,6 +613,12 @@ static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd,
 	case PCITEST_COPY:
 		ret = pci_endpoint_test_copy(test, arg);
 		break;
+	case PCITEST_SET_IRQTYPE:
+		ret = pci_endpoint_test_set_irq(test, arg);
+		break;
+	case PCITEST_GET_IRQTYPE:
+		ret = irq_type;
+		break;
 	}
 
 ret:
@@ -462,9 +634,7 @@ static const struct file_operations pci_endpoint_test_fops = {
 static int pci_endpoint_test_probe(struct pci_dev *pdev,
 				   const struct pci_device_id *ent)
 {
-	int i;
 	int err;
-	int irq = 0;
 	int id;
 	char name[20];
 	enum pci_barno bar;
@@ -486,11 +656,14 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 	test->alignment = 0;
 	test->pdev = pdev;
 
+	if (no_msi)
+		irq_type = IRQ_TYPE_LEGACY;
+
 	data = (struct pci_endpoint_test_data *)ent->driver_data;
 	if (data) {
 		test_reg_bar = data->test_reg_bar;
 		test->alignment = data->alignment;
-		no_msi = data->no_msi;
+		irq_type = data->irq_type;
 	}
 
 	init_completion(&test->irq_raised);
@@ -510,28 +683,11 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 
 	pci_set_master(pdev);
 
-	if (!no_msi) {
-		irq = pci_alloc_irq_vectors(pdev, 1, 32, PCI_IRQ_MSI);
-		if (irq < 0)
-			dev_err(dev, "Failed to get MSI interrupts\n");
-		test->num_irqs = irq;
-	}
-
-	err = devm_request_irq(dev, pdev->irq, pci_endpoint_test_irqhandler,
-			       IRQF_SHARED, DRV_MODULE_NAME, test);
-	if (err) {
-		dev_err(dev, "Failed to request IRQ %d\n", pdev->irq);
-		goto err_disable_msi;
-	}
+	if (!pci_endpoint_test_alloc_irq_vectors(test, irq_type))
+		goto err_disable_irq;
 
-	for (i = 1; i < irq; i++) {
-		err = devm_request_irq(dev, pci_irq_vector(pdev, i),
-				       pci_endpoint_test_irqhandler,
-				       IRQF_SHARED, DRV_MODULE_NAME, test);
-		if (err)
-			dev_err(dev, "failed to request IRQ %d for MSI %d\n",
-				pci_irq_vector(pdev, i), i + 1);
-	}
+	if (!pci_endpoint_test_request_irq(test))
+		goto err_disable_irq;
 
 	for (bar = BAR_0; bar <= BAR_5; bar++) {
 		if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) {
@@ -590,12 +746,10 @@ err_iounmap:
 		if (test->bar[bar])
 			pci_iounmap(pdev, test->bar[bar]);
 	}
+	pci_endpoint_test_release_irq(test);
 
-	for (i = 0; i < irq; i++)
-		devm_free_irq(&pdev->dev, pci_irq_vector(pdev, i), test);
-
-err_disable_msi:
-	pci_disable_msi(pdev);
+err_disable_irq:
+	pci_endpoint_test_free_irq_vectors(test);
 	pci_release_regions(pdev);
 
 err_disable_pdev:
@@ -607,7 +761,6 @@ err_disable_pdev:
 static void pci_endpoint_test_remove(struct pci_dev *pdev)
 {
 	int id;
-	int i;
 	enum pci_barno bar;
 	struct pci_endpoint_test *test = pci_get_drvdata(pdev);
 	struct miscdevice *misc_device = &test->miscdev;
@@ -624,9 +777,10 @@ static void pci_endpoint_test_remove(struct pci_dev *pdev)
 		if (test->bar[bar])
 			pci_iounmap(pdev, test->bar[bar]);
 	}
-	for (i = 0; i < test->num_irqs; i++)
-		devm_free_irq(&pdev->dev, pci_irq_vector(pdev, i), test);
-	pci_disable_msi(pdev);
+
+	pci_endpoint_test_release_irq(test);
+	pci_endpoint_test_free_irq_vectors(test);
+
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
 }
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index c763b404510f..6c94474e36f4 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -24,7 +24,6 @@
 #include <linux/interrupt.h>
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
-#include <linux/dma/pxa-dma.h>
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/mmc/host.h>
@@ -637,10 +636,8 @@ static int pxamci_probe(struct platform_device *pdev)
 {
 	struct mmc_host *mmc;
 	struct pxamci_host *host = NULL;
-	struct resource *r, *dmarx, *dmatx;
-	struct pxad_param param_rx, param_tx;
+	struct resource *r;
 	int ret, irq, gpio_cd = -1, gpio_ro = -1, gpio_power = -1;
-	dma_cap_mask_t mask;
 
 	ret = pxamci_of_init(pdev);
 	if (ret)
@@ -739,34 +736,14 @@ static int pxamci_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, mmc);
 
-	if (!pdev->dev.of_node) {
-		dmarx = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-		dmatx = platform_get_resource(pdev, IORESOURCE_DMA, 1);
-		if (!dmarx || !dmatx) {
-			ret = -ENXIO;
-			goto out;
-		}
-		param_rx.prio = PXAD_PRIO_LOWEST;
-		param_rx.drcmr = dmarx->start;
-		param_tx.prio = PXAD_PRIO_LOWEST;
-		param_tx.drcmr = dmatx->start;
-	}
-
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_SLAVE, mask);
-
-	host->dma_chan_rx =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &param_rx, &pdev->dev, "rx");
+	host->dma_chan_rx = dma_request_slave_channel(&pdev->dev, "rx");
 	if (host->dma_chan_rx == NULL) {
 		dev_err(&pdev->dev, "unable to request rx dma channel\n");
 		ret = -ENODEV;
 		goto out;
 	}
 
-	host->dma_chan_tx =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &param_tx,  &pdev->dev, "tx");
+	host->dma_chan_tx = dma_request_slave_channel(&pdev->dev, "tx");
 	if (host->dma_chan_tx == NULL) {
 		dev_err(&pdev->dev, "unable to request tx dma channel\n");
 		ret = -ENODEV;
diff --git a/drivers/mtd/Kconfig b/drivers/mtd/Kconfig
index 46ab7feec6b6..c77f537323ec 100644
--- a/drivers/mtd/Kconfig
+++ b/drivers/mtd/Kconfig
@@ -24,7 +24,7 @@ config MTD_TESTS
 
 config MTD_REDBOOT_PARTS
 	tristate "RedBoot partition table parsing"
-	---help---
+	help
 	  RedBoot is a ROM monitor and bootloader which deals with multiple
 	  'images' in flash devices by putting a table one of the erase
 	  blocks on the device, similar to a partition table, which gives
@@ -45,7 +45,7 @@ if MTD_REDBOOT_PARTS
 config MTD_REDBOOT_DIRECTORY_BLOCK
 	int "Location of RedBoot partition table"
 	default "-1"
-	---help---
+	help
 	  This option is the Linux counterpart to the
 	  CYGNUM_REDBOOT_FIS_DIRECTORY_BLOCK RedBoot compile time
 	  option.
@@ -75,7 +75,7 @@ endif # MTD_REDBOOT_PARTS
 config MTD_CMDLINE_PARTS
 	tristate "Command line partition table parsing"
 	depends on MTD
-	---help---
+	help
 	  Allow generic configuration of the MTD partition tables via the kernel
 	  command line. Multiple flash resources are supported for hardware where
 	  different kinds of flash memory are available.
@@ -112,7 +112,7 @@ config MTD_CMDLINE_PARTS
 config MTD_AFS_PARTS
 	tristate "ARM Firmware Suite partition parsing"
 	depends on (ARM || ARM64)
-	---help---
+	help
 	  The ARM Firmware Suite allows the user to divide flash devices into
 	  multiple 'images'. Each such image has a header containing its name
 	  and offset/size etc.
@@ -136,7 +136,7 @@ config MTD_OF_PARTS
 
 config MTD_AR7_PARTS
 	tristate "TI AR7 partitioning support"
-	---help---
+	help
 	  TI AR7 partitioning support
 
 config MTD_BCM63XX_PARTS
@@ -170,7 +170,7 @@ config MTD_BLOCK
 	tristate "Caching block device access to MTD devices"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  Although most flash chips have an erase size too large to be useful
 	  as block devices, it is possible to use MTD devices which are based
 	  on RAM chips in this manner. This block device is a user of MTD
@@ -205,7 +205,7 @@ config FTL
 	tristate "FTL (Flash Translation Layer) support"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  This provides support for the original Flash Translation Layer which
 	  is part of the PCMCIA specification. It uses a kind of pseudo-
 	  file system on a flash device to emulate a block device with
@@ -222,7 +222,7 @@ config NFTL
 	tristate "NFTL (NAND Flash Translation Layer) support"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  This provides support for the NAND Flash Translation Layer which is
 	  used on M-Systems' DiskOnChip devices. It uses a kind of pseudo-
 	  file system on a flash device to emulate a block device with
@@ -246,7 +246,7 @@ config INFTL
 	tristate "INFTL (Inverse NAND Flash Translation Layer) support"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  This provides support for the Inverse NAND Flash Translation
 	  Layer which is used on M-Systems' newer DiskOnChip devices. It
 	  uses a kind of pseudo-file system on a flash device to emulate
@@ -261,10 +261,10 @@ config INFTL
 	  not use it.
 
 config RFD_FTL
-        tristate "Resident Flash Disk (Flash Translation Layer) support"
+	tristate "Resident Flash Disk (Flash Translation Layer) support"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  This provides support for the flash translation layer known
 	  as the Resident Flash Disk (RFD), as used by the Embedded BIOS
 	  of General Software. There is a blurb at:
@@ -308,7 +308,7 @@ config MTD_SWAP
 	select MTD_BLKDEVS
 	help
 	  Provides volatile block device driver on top of mtd partition
-          suitable for swapping.  The mapping of written blocks is not saved.
+	  suitable for swapping.  The mapping of written blocks is not saved.
 	  The driver provides wear leveling by storing erase counter into the
 	  OOB.
 
diff --git a/drivers/mtd/chips/Kconfig b/drivers/mtd/chips/Kconfig
index bbfa1f129266..39ec32a29051 100644
--- a/drivers/mtd/chips/Kconfig
+++ b/drivers/mtd/chips/Kconfig
@@ -44,7 +44,7 @@ choice
 	prompt "Flash cmd/query data swapping"
 	depends on MTD_CFI_ADV_OPTIONS
 	default MTD_CFI_NOSWAP
-	---help---
+	help
 	  This option defines the way in which the CPU attempts to arrange
 	  data bits when writing the 'magic' commands to the chips. Saying
 	  'NO', which is the default when CONFIG_MTD_CFI_ADV_OPTIONS isn't
diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c
index 1b64ac8c5bc8..72428b6bfc47 100644
--- a/drivers/mtd/chips/cfi_cmdset_0002.c
+++ b/drivers/mtd/chips/cfi_cmdset_0002.c
@@ -1216,7 +1216,6 @@ static inline int do_read_secsi_onechip(struct map_info *map,
 					size_t grouplen)
 {
 	DECLARE_WAITQUEUE(wait, current);
-	unsigned long timeo = jiffies + HZ;
 
  retry:
 	mutex_lock(&chip->mutex);
@@ -1229,7 +1228,6 @@ static inline int do_read_secsi_onechip(struct map_info *map,
 
 		schedule();
 		remove_wait_queue(&chip->wq, &wait);
-		timeo = jiffies + HZ;
 
 		goto retry;
 	}
diff --git a/drivers/mtd/chips/gen_probe.c b/drivers/mtd/chips/gen_probe.c
index b57ceea21513..837b04ab96a9 100644
--- a/drivers/mtd/chips/gen_probe.c
+++ b/drivers/mtd/chips/gen_probe.c
@@ -202,16 +202,19 @@ static inline struct mtd_info *cfi_cmdset_unknown(struct map_info *map,
 	struct cfi_private *cfi = map->fldrv_priv;
 	__u16 type = primary?cfi->cfiq->P_ID:cfi->cfiq->A_ID;
 #ifdef CONFIG_MODULES
-	char probename[sizeof(VMLINUX_SYMBOL_STR(cfi_cmdset_%4.4X))];
 	cfi_cmdset_fn_t *probe_function;
+	char *probename;
 
-	sprintf(probename, VMLINUX_SYMBOL_STR(cfi_cmdset_%4.4X), type);
+	probename = kasprintf(GFP_KERNEL, "cfi_cmdset_%4.4X", type);
+	if (!probename)
+		return NULL;
 
 	probe_function = __symbol_get(probename);
 	if (!probe_function) {
 		request_module("cfi_cmdset_%4.4X", type);
 		probe_function = __symbol_get(probename);
 	}
+	kfree(probename);
 
 	if (probe_function) {
 		struct mtd_info *mtd;
diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig
index 57b02c4b3f63..e514d57a0419 100644
--- a/drivers/mtd/devices/Kconfig
+++ b/drivers/mtd/devices/Kconfig
@@ -5,7 +5,7 @@ menu "Self-contained MTD device drivers"
 config MTD_PMC551
 	tristate "Ramix PMC551 PCI Mezzanine RAM card support"
 	depends on PCI
-	---help---
+	help
 	  This provides a MTD device driver for the Ramix PMC551 RAM PCI card
 	  from Ramix Inc. <http://www.ramix.com/products/memory/pmc551.html>.
 	  These devices come in memory configurations from 32M - 1G.  If you
@@ -209,7 +209,7 @@ config MTD_DOCG3
 	select BCH
 	select BCH_CONST_PARAMS
 	select BITREVERSE
-	---help---
+	help
 	  This provides an MTD device driver for the M-Systems DiskOnChip
 	  G3 devices.
 
diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index e84563d2067f..cbfafc453274 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -28,11 +28,9 @@
 #include <linux/spi/flash.h>
 #include <linux/mtd/spi-nor.h>
 
-#define	MAX_CMD_SIZE		6
 struct m25p {
 	struct spi_mem		*spimem;
 	struct spi_nor		spi_nor;
-	u8			command[MAX_CMD_SIZE];
 };
 
 static int m25p80_read_reg(struct spi_nor *nor, u8 code, u8 *val, int len)
@@ -70,7 +68,7 @@ static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len,
 	struct spi_mem_op op =
 			SPI_MEM_OP(SPI_MEM_OP_CMD(nor->program_opcode, 1),
 				   SPI_MEM_OP_ADDR(nor->addr_width, to, 1),
-				   SPI_MEM_OP_DUMMY(0, 1),
+				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_DATA_OUT(len, buf, 1));
 	size_t remaining = len;
 	int ret;
@@ -78,7 +76,6 @@ static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len,
 	/* get transfer protocols. */
 	op.cmd.buswidth = spi_nor_get_protocol_inst_nbits(nor->write_proto);
 	op.addr.buswidth = spi_nor_get_protocol_addr_nbits(nor->write_proto);
-	op.dummy.buswidth = op.addr.buswidth;
 	op.data.buswidth = spi_nor_get_protocol_data_nbits(nor->write_proto);
 
 	if (nor->program_opcode == SPINOR_OP_AAI_WP && nor->sst_write_second)
@@ -202,6 +199,9 @@ static int m25p_probe(struct spi_mem *spimem)
 	if (data && data->name)
 		nor->mtd.name = data->name;
 
+	if (!nor->mtd.name)
+		nor->mtd.name = spi_mem_get_name(spimem);
+
 	/* For some (historical?) reason many platforms provide two different
 	 * names in flash_platform_data: "name" and "type". Quite often name is
 	 * set to "m25p80" and then "type" provides a real chip name.
diff --git a/drivers/mtd/devices/powernv_flash.c b/drivers/mtd/devices/powernv_flash.c
index c1312b141ae0..33593122e49b 100644
--- a/drivers/mtd/devices/powernv_flash.c
+++ b/drivers/mtd/devices/powernv_flash.c
@@ -223,6 +223,7 @@ static int powernv_flash_set_driver_info(struct device *dev,
 	mtd->_read = powernv_flash_read;
 	mtd->_write = powernv_flash_write;
 	mtd->dev.parent = dev;
+	mtd_set_of_node(mtd, dev->of_node);
 	return 0;
 }
 
diff --git a/drivers/mtd/devices/sst25l.c b/drivers/mtd/devices/sst25l.c
index 1897f33fe3e7..10d24efb4629 100644
--- a/drivers/mtd/devices/sst25l.c
+++ b/drivers/mtd/devices/sst25l.c
@@ -394,9 +394,8 @@ static int sst25l_probe(struct spi_device *spi)
 	      flash->mtd.numeraseregions);
 
 
-	ret = mtd_device_parse_register(&flash->mtd, NULL, NULL,
-					data ? data->parts : NULL,
-					data ? data->nr_parts : 0);
+	ret = mtd_device_register(&flash->mtd, data ? data->parts : NULL,
+				  data ? data->nr_parts : 0);
 	if (ret)
 		return -ENODEV;
 
diff --git a/drivers/mtd/lpddr/Kconfig b/drivers/mtd/lpddr/Kconfig
index 3a19cbee24d7..a5a332fbd593 100644
--- a/drivers/mtd/lpddr/Kconfig
+++ b/drivers/mtd/lpddr/Kconfig
@@ -13,10 +13,10 @@ config MTD_QINFO_PROBE
 	depends on MTD_LPDDR
 	tristate "Detect flash chips by QINFO probe"
 	help
-	    Device Information for LPDDR chips is offered through the Overlay
-	    Window QINFO interface, permits software to be used for entire
-	    families of devices. This serves similar purpose of CFI on legacy
-	    Flash products
+	  Device Information for LPDDR chips is offered through the Overlay
+	  Window QINFO interface, permits software to be used for entire
+	  families of devices. This serves similar purpose of CFI on legacy
+	  Flash products
 
 config MTD_LPDDR2_NVM
 	# ARM dependency is only for writel_relaxed()
diff --git a/drivers/mtd/lpddr/lpddr2_nvm.c b/drivers/mtd/lpddr/lpddr2_nvm.c
index 5d73db2a496d..c950c880ad59 100644
--- a/drivers/mtd/lpddr/lpddr2_nvm.c
+++ b/drivers/mtd/lpddr/lpddr2_nvm.c
@@ -476,7 +476,7 @@ static int lpddr2_nvm_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 	/* Parse partitions and register the MTD device */
-	return mtd_device_parse_register(mtd, NULL, NULL, NULL, 0);
+	return mtd_device_register(mtd, NULL, 0);
 }
 
 /*
diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig
index bdc1283f30fb..afb36bff13a7 100644
--- a/drivers/mtd/maps/Kconfig
+++ b/drivers/mtd/maps/Kconfig
@@ -207,13 +207,13 @@ config MTD_ICHXROM
 	  BE VERY CAREFUL.
 
 config MTD_ESB2ROM
-        tristate "BIOS flash chip on Intel ESB Controller Hub 2"
-        depends on X86 && MTD_JEDECPROBE && PCI
-        help
-          Support for treating the BIOS flash chip on ESB2 motherboards
-          as an MTD device - with this you can reprogram your BIOS.
+	tristate "BIOS flash chip on Intel ESB Controller Hub 2"
+	depends on X86 && MTD_JEDECPROBE && PCI
+	help
+	  Support for treating the BIOS flash chip on ESB2 motherboards
+	  as an MTD device - with this you can reprogram your BIOS.
 
-          BE VERY CAREFUL.
+	  BE VERY CAREFUL.
 
 config MTD_CK804XROM
 	tristate "BIOS flash chip on Nvidia CK804"
@@ -401,12 +401,12 @@ config MTD_PISMO
 	  When built as a module, it will be called pismo.ko
 
 config MTD_LATCH_ADDR
-        tristate "Latch-assisted Flash Chip Support"
-        depends on MTD_COMPLEX_MAPPINGS
-        help
-          Map driver which allows flashes to be partially physically addressed
-          and have the upper address lines set by a board specific code.
+	tristate "Latch-assisted Flash Chip Support"
+	depends on MTD_COMPLEX_MAPPINGS
+	help
+	  Map driver which allows flashes to be partially physically addressed
+	  and have the upper address lines set by a board specific code.
 
-          If compiled as a module, it will be called latch-addr-flash.
+	  If compiled as a module, it will be called latch-addr-flash.
 
 endmenu
diff --git a/drivers/mtd/maps/gpio-addr-flash.c b/drivers/mtd/maps/gpio-addr-flash.c
index 385305e66fd1..9d9723693217 100644
--- a/drivers/mtd/maps/gpio-addr-flash.c
+++ b/drivers/mtd/maps/gpio-addr-flash.c
@@ -239,6 +239,9 @@ static int gpio_flash_probe(struct platform_device *pdev)
 	state->map.bankwidth  = pdata->width;
 	state->map.size       = state->win_size * (1 << state->gpio_count);
 	state->map.virt       = ioremap_nocache(memory->start, state->map.size);
+	if (!state->map.virt)
+		return -ENOMEM;
+
 	state->map.phys       = NO_XIP;
 	state->map.map_priv_1 = (unsigned long)state;
 
diff --git a/drivers/mtd/maps/impa7.c b/drivers/mtd/maps/impa7.c
index a0b8fa7849a9..815e2db87955 100644
--- a/drivers/mtd/maps/impa7.c
+++ b/drivers/mtd/maps/impa7.c
@@ -88,9 +88,8 @@ static int __init init_impa7(void)
 		if (impa7_mtd[i]) {
 			impa7_mtd[i]->owner = THIS_MODULE;
 			devicesfound++;
-			mtd_device_parse_register(impa7_mtd[i], NULL, NULL,
-						  partitions,
-						  ARRAY_SIZE(partitions));
+			mtd_device_register(impa7_mtd[i], partitions,
+					    ARRAY_SIZE(partitions));
 		} else {
 			iounmap((void __iomem *)impa7_map[i].virt);
 		}
diff --git a/drivers/mtd/maps/intel_vr_nor.c b/drivers/mtd/maps/intel_vr_nor.c
index dd5d6855f543..69503aef981e 100644
--- a/drivers/mtd/maps/intel_vr_nor.c
+++ b/drivers/mtd/maps/intel_vr_nor.c
@@ -71,7 +71,7 @@ static int vr_nor_init_partitions(struct vr_nor_mtd *p)
 {
 	/* register the flash bank */
 	/* partition the flash bank */
-	return mtd_device_parse_register(p->info, NULL, NULL, NULL, 0);
+	return mtd_device_register(p->info, NULL, 0);
 }
 
 static void vr_nor_destroy_mtd_setup(struct vr_nor_mtd *p)
diff --git a/drivers/mtd/maps/latch-addr-flash.c b/drivers/mtd/maps/latch-addr-flash.c
index 6dc97aa667dc..51db24b7f88d 100644
--- a/drivers/mtd/maps/latch-addr-flash.c
+++ b/drivers/mtd/maps/latch-addr-flash.c
@@ -197,9 +197,8 @@ static int latch_addr_flash_probe(struct platform_device *dev)
 	}
 	info->mtd->dev.parent = &dev->dev;
 
-	mtd_device_parse_register(info->mtd, NULL, NULL,
-				  latch_addr_data->parts,
-				  latch_addr_data->nr_parts);
+	mtd_device_register(info->mtd, latch_addr_data->parts,
+			    latch_addr_data->nr_parts);
 	return 0;
 
 iounmap:
diff --git a/drivers/mtd/maps/rbtx4939-flash.c b/drivers/mtd/maps/rbtx4939-flash.c
index 3a06ecfc55ff..80a187167c92 100644
--- a/drivers/mtd/maps/rbtx4939-flash.c
+++ b/drivers/mtd/maps/rbtx4939-flash.c
@@ -97,8 +97,7 @@ static int rbtx4939_flash_probe(struct platform_device *dev)
 		goto err_out;
 	}
 	info->mtd->dev.parent = &dev->dev;
-	err = mtd_device_parse_register(info->mtd, NULL, NULL, pdata->parts,
-					pdata->nr_parts);
+	err = mtd_device_register(info->mtd, pdata->parts, pdata->nr_parts);
 
 	if (err)
 		goto err_out;
diff --git a/drivers/mtd/maps/solutionengine.c b/drivers/mtd/maps/solutionengine.c
index bb580bc16445..c07f21b20463 100644
--- a/drivers/mtd/maps/solutionengine.c
+++ b/drivers/mtd/maps/solutionengine.c
@@ -59,9 +59,9 @@ static int __init init_soleng_maps(void)
 			return -ENXIO;
 		}
 	}
-	printk(KERN_NOTICE "Solution Engine: Flash at 0x%08lx, EPROM at 0x%08lx\n",
-	       soleng_flash_map.phys & 0x1fffffff,
-	       soleng_eprom_map.phys & 0x1fffffff);
+	printk(KERN_NOTICE "Solution Engine: Flash at 0x%pap, EPROM at 0x%pap\n",
+	       &soleng_flash_map.phys,
+	       &soleng_eprom_map.phys);
 	flash_mtd->owner = THIS_MODULE;
 
 	eprom_mtd = do_map_probe("map_rom", &soleng_eprom_map);
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index cd67c85cc87d..02389528f622 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -160,8 +160,12 @@ static ssize_t mtdchar_read(struct file *file, char __user *buf, size_t count,
 
 	pr_debug("MTD_read\n");
 
-	if (*ppos + count > mtd->size)
-		count = mtd->size - *ppos;
+	if (*ppos + count > mtd->size) {
+		if (*ppos < mtd->size)
+			count = mtd->size - *ppos;
+		else
+			count = 0;
+	}
 
 	if (!count)
 		return 0;
@@ -246,7 +250,7 @@ static ssize_t mtdchar_write(struct file *file, const char __user *buf, size_t c
 
 	pr_debug("MTD_write\n");
 
-	if (*ppos == mtd->size)
+	if (*ppos >= mtd->size)
 		return -ENOSPC;
 
 	if (*ppos + count > mtd->size)
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 42395df06be9..97ac219c082e 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -1155,21 +1155,29 @@ int mtd_read_oob(struct mtd_info *mtd, loff_t from, struct mtd_oob_ops *ops)
 {
 	int ret_code;
 	ops->retlen = ops->oobretlen = 0;
-	if (!mtd->_read_oob)
-		return -EOPNOTSUPP;
 
 	ret_code = mtd_check_oob_ops(mtd, from, ops);
 	if (ret_code)
 		return ret_code;
 
 	ledtrig_mtd_activity();
+
+	/* Check the validity of a potential fallback on mtd->_read */
+	if (!mtd->_read_oob && (!mtd->_read || ops->oobbuf))
+		return -EOPNOTSUPP;
+
+	if (mtd->_read_oob)
+		ret_code = mtd->_read_oob(mtd, from, ops);
+	else
+		ret_code = mtd->_read(mtd, from, ops->len, &ops->retlen,
+				      ops->datbuf);
+
 	/*
 	 * In cases where ops->datbuf != NULL, mtd->_read_oob() has semantics
 	 * similar to mtd->_read(), returning a non-negative integer
 	 * representing max bitflips. In other cases, mtd->_read_oob() may
 	 * return -EUCLEAN. In all cases, perform similar logic to mtd_read().
 	 */
-	ret_code = mtd->_read_oob(mtd, from, ops);
 	if (unlikely(ret_code < 0))
 		return ret_code;
 	if (mtd->ecc_strength == 0)
@@ -1184,8 +1192,7 @@ int mtd_write_oob(struct mtd_info *mtd, loff_t to,
 	int ret;
 
 	ops->retlen = ops->oobretlen = 0;
-	if (!mtd->_write_oob)
-		return -EOPNOTSUPP;
+
 	if (!(mtd->flags & MTD_WRITEABLE))
 		return -EROFS;
 
@@ -1194,7 +1201,16 @@ int mtd_write_oob(struct mtd_info *mtd, loff_t to,
 		return ret;
 
 	ledtrig_mtd_activity();
-	return mtd->_write_oob(mtd, to, ops);
+
+	/* Check the validity of a potential fallback on mtd->_write */
+	if (!mtd->_write_oob && (!mtd->_write || ops->oobbuf))
+		return -EOPNOTSUPP;
+
+	if (mtd->_write_oob)
+		return mtd->_write_oob(mtd, to, ops);
+	else
+		return mtd->_write(mtd, to, ops->len, &ops->retlen,
+				   ops->datbuf);
 }
 EXPORT_SYMBOL_GPL(mtd_write_oob);
 
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index f8d3a015cdad..52e2cb35fc79 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -322,22 +322,6 @@ static inline void free_partition(struct mtd_part *p)
 	kfree(p);
 }
 
-/**
- * mtd_parse_part - parse MTD partition looking for subpartitions
- *
- * @slave: part that is supposed to be a container and should be parsed
- * @types: NULL-terminated array with names of partition parsers to try
- *
- * Some partitions are kind of containers with extra subpartitions (volumes).
- * There can be various formats of such containers. This function tries to use
- * specified parsers to analyze given partition and registers found
- * subpartitions on success.
- */
-static int mtd_parse_part(struct mtd_part *slave, const char *const *types)
-{
-	return parse_mtd_partitions(&slave->mtd, types, NULL);
-}
-
 static struct mtd_part *allocate_partition(struct mtd_info *parent,
 			const struct mtd_partition *part, int partno,
 			uint64_t cur_offset)
@@ -735,8 +719,8 @@ int add_mtd_partitions(struct mtd_info *master,
 
 		add_mtd_device(&slave->mtd);
 		mtd_add_partition_attrs(slave);
-		if (parts[i].types)
-			mtd_parse_part(slave, parts[i].types);
+		/* Look for subpartitions */
+		parse_mtd_partitions(&slave->mtd, parts[i].types, NULL);
 
 		cur_offset = slave->offset + slave->mtd.size;
 	}
@@ -812,6 +796,12 @@ static const char * const default_mtd_part_types[] = {
 	NULL
 };
 
+/* Check DT only when looking for subpartitions. */
+static const char * const default_subpartition_types[] = {
+	"ofpart",
+	NULL
+};
+
 static int mtd_part_do_parse(struct mtd_part_parser *parser,
 			     struct mtd_info *master,
 			     struct mtd_partitions *pparts,
@@ -882,7 +872,9 @@ static int mtd_part_of_parse(struct mtd_info *master,
 	const char *fixed = "fixed-partitions";
 	int ret, err = 0;
 
-	np = of_get_child_by_name(mtd_get_of_node(master), "partitions");
+	np = mtd_get_of_node(master);
+	if (!mtd_is_partition(master))
+		np = of_get_child_by_name(np, "partitions");
 	of_property_for_each_string(np, "compatible", prop, compat) {
 		parser = mtd_part_get_compatible_parser(compat);
 		if (!parser)
@@ -945,7 +937,8 @@ int parse_mtd_partitions(struct mtd_info *master, const char *const *types,
 	int ret, err = 0;
 
 	if (!types)
-		types = default_mtd_part_types;
+		types = mtd_is_partition(master) ? default_subpartition_types :
+			default_mtd_part_types;
 
 	for ( ; *types; types++) {
 		/*
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 88c7d3b4ff8b..9033215e62ea 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -4,3 +4,4 @@ config MTD_NAND_CORE
 source "drivers/mtd/nand/onenand/Kconfig"
 
 source "drivers/mtd/nand/raw/Kconfig"
+source "drivers/mtd/nand/spi/Kconfig"
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index 3f0cb87f1a57..7ecd80c0a66e 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -5,3 +5,4 @@ obj-$(CONFIG_MTD_NAND_CORE) += nandcore.o
 
 obj-y	+= onenand/
 obj-y	+= raw/
+obj-y	+= spi/
diff --git a/drivers/mtd/nand/onenand/generic.c b/drivers/mtd/nand/onenand/generic.c
index d5ccaf943b91..acad17ec6581 100644
--- a/drivers/mtd/nand/onenand/generic.c
+++ b/drivers/mtd/nand/onenand/generic.c
@@ -66,9 +66,8 @@ static int generic_onenand_probe(struct platform_device *pdev)
 		goto out_iounmap;
 	}
 
-	err = mtd_device_parse_register(&info->mtd, NULL, NULL,
-					pdata ? pdata->parts : NULL,
-					pdata ? pdata->nr_parts : 0);
+	err = mtd_device_register(&info->mtd, pdata ? pdata->parts : NULL,
+				  pdata ? pdata->nr_parts : 0);
 
 	platform_set_drvdata(pdev, info);
 
diff --git a/drivers/mtd/nand/onenand/samsung.c b/drivers/mtd/nand/onenand/samsung.c
index 4cce4c0311ca..e64d0fdf7eb5 100644
--- a/drivers/mtd/nand/onenand/samsung.c
+++ b/drivers/mtd/nand/onenand/samsung.c
@@ -933,9 +933,8 @@ static int s3c_onenand_probe(struct platform_device *pdev)
 	if (s3c_read_reg(MEM_CFG_OFFSET) & ONENAND_SYS_CFG1_SYNC_READ)
 		dev_info(&onenand->pdev->dev, "OneNAND Sync. Burst Read enabled\n");
 
-	err = mtd_device_parse_register(mtd, NULL, NULL,
-					pdata ? pdata->parts : NULL,
-					pdata ? pdata->nr_parts : 0);
+	err = mtd_device_register(mtd, pdata ? pdata->parts : NULL,
+				  pdata ? pdata->nr_parts : 0);
 	if (err) {
 		dev_err(&pdev->dev, "failed to parse partitions and register the MTD device\n");
 		onenand_release(mtd);
diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 6871ff0fd300..5fc9a1bde4ac 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -44,12 +44,12 @@ config MTD_NAND_DENALI
 	tristate
 
 config MTD_NAND_DENALI_PCI
-        tristate "Support Denali NAND controller on Intel Moorestown"
+	tristate "Support Denali NAND controller on Intel Moorestown"
 	select MTD_NAND_DENALI
 	depends on PCI
-        help
-          Enable the driver for NAND flash on Intel Moorestown, using the
-          Denali NAND controller core.
+	help
+	  Enable the driver for NAND flash on Intel Moorestown, using the
+	  Denali NAND controller core.
 
 config MTD_NAND_DENALI_DT
 	tristate "Support Denali NAND controller as a DT device"
@@ -77,9 +77,10 @@ config MTD_NAND_AMS_DELTA
 
 config MTD_NAND_OMAP2
 	tristate "NAND Flash device on OMAP2, OMAP3, OMAP4 and Keystone"
-	depends on (ARCH_OMAP2PLUS || ARCH_KEYSTONE)
+	depends on ARCH_OMAP2PLUS || ARCH_KEYSTONE || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
-          Support for NAND flash on Texas Instruments OMAP2, OMAP3, OMAP4
+	  Support for NAND flash on Texas Instruments OMAP2, OMAP3, OMAP4
 	  and Keystone platforms.
 
 config MTD_NAND_OMAP_BCH
@@ -137,7 +138,7 @@ config MTD_NAND_NDFC
 	depends on 4xx
 	select MTD_NAND_ECC_SMC
 	help
-	 NDFC Nand Flash Controllers are integrated in IBM/AMCC's 4xx SoCs
+	  NDFC Nand Flash Controllers are integrated in IBM/AMCC's 4xx SoCs
 
 config MTD_NAND_S3C2410_CLKSTOP
 	bool "Samsung S3C NAND IDLE clock stop"
@@ -152,6 +153,7 @@ config MTD_NAND_S3C2410_CLKSTOP
 config MTD_NAND_TANGO
 	tristate "NAND Flash support for Tango chips"
 	depends on ARCH_TANGO || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables the NAND Flash controller on Tango chips.
 
@@ -168,40 +170,40 @@ config MTD_NAND_DISKONCHIP
 	  these devices.
 
 config MTD_NAND_DISKONCHIP_PROBE_ADVANCED
-        bool "Advanced detection options for DiskOnChip"
-        depends on MTD_NAND_DISKONCHIP
-        help
-          This option allows you to specify nonstandard address at which to
-          probe for a DiskOnChip, or to change the detection options.  You
-          are unlikely to need any of this unless you are using LinuxBIOS.
-          Say 'N'.
+	bool "Advanced detection options for DiskOnChip"
+	depends on MTD_NAND_DISKONCHIP
+	help
+	  This option allows you to specify nonstandard address at which to
+	  probe for a DiskOnChip, or to change the detection options.  You
+	  are unlikely to need any of this unless you are using LinuxBIOS.
+	  Say 'N'.
 
 config MTD_NAND_DISKONCHIP_PROBE_ADDRESS
-        hex "Physical address of DiskOnChip" if MTD_NAND_DISKONCHIP_PROBE_ADVANCED
-        depends on MTD_NAND_DISKONCHIP
-        default "0"
-        ---help---
-        By default, the probe for DiskOnChip devices will look for a
-        DiskOnChip at every multiple of 0x2000 between 0xC8000 and 0xEE000.
-        This option allows you to specify a single address at which to probe
-        for the device, which is useful if you have other devices in that
-        range which get upset when they are probed.
-
-        (Note that on PowerPC, the normal probe will only check at
-        0xE4000000.)
-
-        Normally, you should leave this set to zero, to allow the probe at
-        the normal addresses.
+	hex "Physical address of DiskOnChip" if MTD_NAND_DISKONCHIP_PROBE_ADVANCED
+	depends on MTD_NAND_DISKONCHIP
+	default "0"
+	help
+	  By default, the probe for DiskOnChip devices will look for a
+	  DiskOnChip at every multiple of 0x2000 between 0xC8000 and 0xEE000.
+	  This option allows you to specify a single address at which to probe
+	  for the device, which is useful if you have other devices in that
+	  range which get upset when they are probed.
+
+	  (Note that on PowerPC, the normal probe will only check at
+	  0xE4000000.)
+
+	  Normally, you should leave this set to zero, to allow the probe at
+	  the normal addresses.
 
 config MTD_NAND_DISKONCHIP_PROBE_HIGH
-        bool "Probe high addresses"
-        depends on MTD_NAND_DISKONCHIP_PROBE_ADVANCED
-        help
-          By default, the probe for DiskOnChip devices will look for a
-          DiskOnChip at every multiple of 0x2000 between 0xC8000 and 0xEE000.
-          This option changes to make it probe between 0xFFFC8000 and
-          0xFFFEE000.  Unless you are using LinuxBIOS, this is unlikely to be
-          useful to you.  Say 'N'.
+	bool "Probe high addresses"
+	depends on MTD_NAND_DISKONCHIP_PROBE_ADVANCED
+	help
+	  By default, the probe for DiskOnChip devices will look for a
+	  DiskOnChip at every multiple of 0x2000 between 0xC8000 and 0xEE000.
+	  This option changes to make it probe between 0xFFFC8000 and
+	  0xFFFEE000.  Unless you are using LinuxBIOS, this is unlikely to be
+	  useful to you.  Say 'N'.
 
 config MTD_NAND_DISKONCHIP_BBTWRITE
 	bool "Allow BBT writes on DiskOnChip Millennium and 2000TSOP"
@@ -247,7 +249,8 @@ config MTD_NAND_DOCG4
 
 config MTD_NAND_SHARPSL
 	tristate "Support for NAND Flash on Sharp SL Series (C7xx + others)"
-	depends on ARCH_PXA
+	depends on ARCH_PXA || COMPILE_TEST
+	depends on HAS_IOMEM
 
 config MTD_NAND_CAFE
 	tristate "NAND support for OLPC CAFÉ chip"
@@ -274,7 +277,9 @@ config MTD_NAND_CS553X
 
 config MTD_NAND_ATMEL
 	tristate "Support for NAND Flash / SmartMedia on AT91"
-	depends on ARCH_AT91
+	depends on ARCH_AT91 || COMPILE_TEST
+	depends on HAS_IOMEM
+	select GENERIC_ALLOCATOR
 	select MFD_ATMEL_SMC
 	help
 	  Enables support for NAND Flash / Smart Media Card interface
@@ -294,7 +299,8 @@ config MTD_NAND_MARVELL
 
 config MTD_NAND_SLC_LPC32XX
 	tristate "NXP LPC32xx SLC Controller"
-	depends on ARCH_LPC32XX
+	depends on ARCH_LPC32XX || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NXP's LPC32XX SLC (i.e. for Single Level Cell
 	  chips) NAND controller. This is the default for the PHYTEC 3250
@@ -305,7 +311,8 @@ config MTD_NAND_SLC_LPC32XX
 
 config MTD_NAND_MLC_LPC32XX
 	tristate "NXP LPC32xx MLC Controller"
-	depends on ARCH_LPC32XX
+	depends on ARCH_LPC32XX || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Uses the LPC32XX MLC (i.e. for Multi Level Cell chips) NAND
 	  controller. This is the default for the WORK92105 controller
@@ -339,17 +346,18 @@ config MTD_NAND_NANDSIM
 	  MTD nand layer.
 
 config MTD_NAND_GPMI_NAND
-        tristate "GPMI NAND Flash Controller driver"
-        depends on MTD_NAND && MXS_DMA
-        help
-	 Enables NAND Flash support for IMX23, IMX28 or IMX6.
-	 The GPMI controller is very powerful, with the help of BCH
-	 module, it can do the hardware ECC. The GPMI supports several
-	 NAND flashs at the same time.
+	tristate "GPMI NAND Flash Controller driver"
+	depends on MXS_DMA
+	help
+	  Enables NAND Flash support for IMX23, IMX28 or IMX6.
+	  The GPMI controller is very powerful, with the help of BCH
+	  module, it can do the hardware ECC. The GPMI supports several
+	  NAND flashs at the same time.
 
 config MTD_NAND_BRCMNAND
 	tristate "Broadcom STB NAND controller"
-	depends on ARM || ARM64 || MIPS
+	depends on ARM || ARM64 || MIPS || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables the Broadcom NAND controller driver. The controller was
 	  originally designed for Set-Top Box but is used on various BCM7xxx,
@@ -358,6 +366,7 @@ config MTD_NAND_BRCMNAND
 config MTD_NAND_BCM47XXNFLASH
 	tristate "Support for NAND flash on BCM4706 BCMA bus"
 	depends on BCMA_NFLASH
+	depends on BCMA
 	help
 	  BCMA bus can have various flash memories attached, they are
 	  registered by bcma as platform devices. This enables driver for
@@ -399,7 +408,8 @@ config MTD_NAND_FSL_ELBC
 
 config MTD_NAND_FSL_IFC
 	tristate "NAND support for Freescale IFC controller"
-	depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A
+	depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A || COMPILE_TEST
+	depends on HAS_IOMEM
 	select FSL_IFC
 	select MEMORY
 	help
@@ -437,7 +447,8 @@ config MTD_NAND_VF610_NFC
 
 config MTD_NAND_MXC
 	tristate "MXC NAND support"
-	depends on ARCH_MXC
+	depends on ARCH_MXC || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  This enables the driver for the NAND flash controller on the
 	  MXC processors.
@@ -451,15 +462,17 @@ config MTD_NAND_SH_FLCTL
 	  for NAND Flash using FLCTL.
 
 config MTD_NAND_DAVINCI
-        tristate "Support NAND on DaVinci/Keystone SoC"
-        depends on ARCH_DAVINCI || (ARCH_KEYSTONE && TI_AEMIF)
-        help
+	tristate "Support NAND on DaVinci/Keystone SoC"
+	depends on ARCH_DAVINCI || (ARCH_KEYSTONE && TI_AEMIF) || COMPILE_TEST
+	depends on HAS_IOMEM
+	help
 	  Enable the driver for NAND flash chips on Texas Instruments
 	  DaVinci/Keystone processors.
 
 config MTD_NAND_TXX9NDFMC
 	tristate "NAND Flash support for TXx9 SoC"
-	depends on SOC_TX4938 || SOC_TX4939
+	depends on SOC_TX4938 || SOC_TX4939 || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  This enables the NAND flash controller on the TXx9 SoCs.
 
@@ -471,28 +484,31 @@ config MTD_NAND_SOCRATES
 
 config MTD_NAND_NUC900
 	tristate "Support for NAND on Nuvoton NUC9xx/w90p910 evaluation boards."
-	depends on ARCH_W90X900
+	depends on ARCH_W90X900 || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  This enables the driver for the NAND Flash on evaluation board based
 	  on w90p910 / NUC9xx.
 
 config MTD_NAND_JZ4740
 	tristate "Support for JZ4740 SoC NAND controller"
-	depends on MACH_JZ4740
+	depends on MACH_JZ4740 || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
-		Enables support for NAND Flash on JZ4740 SoC based boards.
+	  Enables support for NAND Flash on JZ4740 SoC based boards.
 
 config MTD_NAND_JZ4780
 	tristate "Support for NAND on JZ4780 SoC"
-	depends on MACH_JZ4780 && JZ4780_NEMC
+	depends on JZ4780_NEMC
 	help
 	  Enables support for NAND Flash connected to the NEMC on JZ4780 SoC
 	  based boards, using the BCH controller for hardware error correction.
 
 config MTD_NAND_FSMC
 	tristate "Support for NAND on ST Micros FSMC"
-	depends on OF
-	depends on PLAT_SPEAR || ARCH_NOMADIK || ARCH_U8500 || MACH_U300
+	depends on OF && HAS_IOMEM
+	depends on PLAT_SPEAR || ARCH_NOMADIK || ARCH_U8500 || MACH_U300 || \
+		   COMPILE_TEST
 	help
 	  Enables support for NAND Flash chips on the ST Microelectronics
 	  Flexible Static Memory Controller (FSMC)
@@ -506,19 +522,22 @@ config MTD_NAND_XWAY
 
 config MTD_NAND_SUNXI
 	tristate "Support for NAND on Allwinner SoCs"
-	depends on ARCH_SUNXI
+	depends on ARCH_SUNXI || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NAND Flash chips on Allwinner SoCs.
 
 config MTD_NAND_HISI504
 	tristate "Support for NAND controller on Hisilicon SoC Hip04"
 	depends on ARCH_HISI || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NAND controller on Hisilicon SoC Hip04.
 
 config MTD_NAND_QCOM
 	tristate "Support for NAND on QCOM SoCs"
-	depends on ARCH_QCOM
+	depends on ARCH_QCOM || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NAND flash chips on SoCs containing the EBI2 NAND
 	  controller. This controller is found on IPQ806x SoC.
@@ -526,8 +545,20 @@ config MTD_NAND_QCOM
 config MTD_NAND_MTK
 	tristate "Support for NAND controller on MTK SoCs"
 	depends on ARCH_MEDIATEK || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NAND controller on MTK SoCs.
 	  This controller is found on mt27xx, mt81xx, mt65xx SoCs.
 
+config MTD_NAND_TEGRA
+	tristate "Support for NAND controller on NVIDIA Tegra"
+	depends on ARCH_TEGRA || COMPILE_TEST
+	depends on HAS_IOMEM
+	help
+	  Enables support for NAND flash controller on NVIDIA Tegra SoC.
+	  The driver has been developed and tested on a Tegra 2 SoC. DMA
+	  support, raw read/write page as well as HW ECC read/write page
+	  is supported. Extra OOB bytes when using HW ECC are currently
+	  not supported.
+
 endif # MTD_NAND
diff --git a/drivers/mtd/nand/raw/Makefile b/drivers/mtd/nand/raw/Makefile
index 165b7ef9e9a1..d5a5f9832b88 100644
--- a/drivers/mtd/nand/raw/Makefile
+++ b/drivers/mtd/nand/raw/Makefile
@@ -56,6 +56,7 @@ obj-$(CONFIG_MTD_NAND_HISI504)	        += hisi504_nand.o
 obj-$(CONFIG_MTD_NAND_BRCMNAND)		+= brcmnand/
 obj-$(CONFIG_MTD_NAND_QCOM)		+= qcom_nandc.o
 obj-$(CONFIG_MTD_NAND_MTK)		+= mtk_ecc.o mtk_nand.o
+obj-$(CONFIG_MTD_NAND_TEGRA)		+= tegra_nand.o
 
 nand-objs := nand_base.o nand_bbt.o nand_timings.o nand_ids.o
 nand-objs += nand_amd.o
diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index 12f6753d47ae..a068b214ebaa 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -52,7 +52,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
 #include <linux/genalloc.h>
-#include <linux/gpio.h>
 #include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
 #include <linux/mfd/syscon.h>
@@ -129,6 +128,11 @@
 #define DEFAULT_TIMEOUT_MS			1000
 #define MIN_DMA_LEN				128
 
+static bool atmel_nand_avoid_dma __read_mostly;
+
+MODULE_PARM_DESC(avoiddma, "Avoid using DMA");
+module_param_named(avoiddma, atmel_nand_avoid_dma, bool, 0400);
+
 enum atmel_nand_rb_type {
 	ATMEL_NAND_NO_RB,
 	ATMEL_NAND_NATIVE_RB,
@@ -197,7 +201,7 @@ struct atmel_nand_controller_ops {
 	int (*remove)(struct atmel_nand_controller *nc);
 	void (*nand_init)(struct atmel_nand_controller *nc,
 			  struct atmel_nand *nand);
-	int (*ecc_init)(struct atmel_nand *nand);
+	int (*ecc_init)(struct nand_chip *chip);
 	int (*setup_data_interface)(struct atmel_nand *nand, int csline,
 				    const struct nand_data_interface *conf);
 };
@@ -211,7 +215,7 @@ struct atmel_nand_controller_caps {
 };
 
 struct atmel_nand_controller {
-	struct nand_hw_control base;
+	struct nand_controller base;
 	const struct atmel_nand_controller_caps *caps;
 	struct device *dev;
 	struct regmap *smc;
@@ -222,7 +226,7 @@ struct atmel_nand_controller {
 };
 
 static inline struct atmel_nand_controller *
-to_nand_controller(struct nand_hw_control *ctl)
+to_nand_controller(struct nand_controller *ctl)
 {
 	return container_of(ctl, struct atmel_nand_controller, base);
 }
@@ -234,7 +238,7 @@ struct atmel_smc_nand_controller {
 };
 
 static inline struct atmel_smc_nand_controller *
-to_smc_nand_controller(struct nand_hw_control *ctl)
+to_smc_nand_controller(struct nand_controller *ctl)
 {
 	return container_of(to_nand_controller(ctl),
 			    struct atmel_smc_nand_controller, base);
@@ -258,7 +262,7 @@ struct atmel_hsmc_nand_controller {
 };
 
 static inline struct atmel_hsmc_nand_controller *
-to_hsmc_nand_controller(struct nand_hw_control *ctl)
+to_hsmc_nand_controller(struct nand_controller *ctl)
 {
 	return container_of(to_nand_controller(ctl),
 			    struct atmel_hsmc_nand_controller, base);
@@ -1128,9 +1132,8 @@ static int atmel_nand_pmecc_init(struct nand_chip *chip)
 	return 0;
 }
 
-static int atmel_nand_ecc_init(struct atmel_nand *nand)
+static int atmel_nand_ecc_init(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &nand->base;
 	struct atmel_nand_controller *nc;
 	int ret;
 
@@ -1165,12 +1168,11 @@ static int atmel_nand_ecc_init(struct atmel_nand *nand)
 	return 0;
 }
 
-static int atmel_hsmc_nand_ecc_init(struct atmel_nand *nand)
+static int atmel_hsmc_nand_ecc_init(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &nand->base;
 	int ret;
 
-	ret = atmel_nand_ecc_init(nand);
+	ret = atmel_nand_ecc_init(chip);
 	if (ret)
 		return ret;
 
@@ -1553,23 +1555,7 @@ static void atmel_hsmc_nand_init(struct atmel_nand_controller *nc,
 	chip->select_chip = atmel_hsmc_nand_select_chip;
 }
 
-static int atmel_nand_detect(struct atmel_nand *nand)
-{
-	struct nand_chip *chip = &nand->base;
-	struct mtd_info *mtd = nand_to_mtd(chip);
-	struct atmel_nand_controller *nc;
-	int ret;
-
-	nc = to_nand_controller(chip->controller);
-
-	ret = nand_scan_ident(mtd, nand->numcs, NULL);
-	if (ret)
-		dev_err(nc->dev, "nand_scan_ident() failed: %d\n", ret);
-
-	return ret;
-}
-
-static int atmel_nand_unregister(struct atmel_nand *nand)
+static int atmel_nand_controller_remove_nand(struct atmel_nand *nand)
 {
 	struct nand_chip *chip = &nand->base;
 	struct mtd_info *mtd = nand_to_mtd(chip);
@@ -1585,60 +1571,6 @@ static int atmel_nand_unregister(struct atmel_nand *nand)
 	return 0;
 }
 
-static int atmel_nand_register(struct atmel_nand *nand)
-{
-	struct nand_chip *chip = &nand->base;
-	struct mtd_info *mtd = nand_to_mtd(chip);
-	struct atmel_nand_controller *nc;
-	int ret;
-
-	nc = to_nand_controller(chip->controller);
-
-	if (nc->caps->legacy_of_bindings || !nc->dev->of_node) {
-		/*
-		 * We keep the MTD name unchanged to avoid breaking platforms
-		 * where the MTD cmdline parser is used and the bootloader
-		 * has not been updated to use the new naming scheme.
-		 */
-		mtd->name = "atmel_nand";
-	} else if (!mtd->name) {
-		/*
-		 * If the new bindings are used and the bootloader has not been
-		 * updated to pass a new mtdparts parameter on the cmdline, you
-		 * should define the following property in your nand node:
-		 *
-		 *	label = "atmel_nand";
-		 *
-		 * This way, mtd->name will be set by the core when
-		 * nand_set_flash_node() is called.
-		 */
-		mtd->name = devm_kasprintf(nc->dev, GFP_KERNEL,
-					   "%s:nand.%d", dev_name(nc->dev),
-					   nand->cs[0].id);
-		if (!mtd->name) {
-			dev_err(nc->dev, "Failed to allocate mtd->name\n");
-			return -ENOMEM;
-		}
-	}
-
-	ret = nand_scan_tail(mtd);
-	if (ret) {
-		dev_err(nc->dev, "nand_scan_tail() failed: %d\n", ret);
-		return ret;
-	}
-
-	ret = mtd_device_register(mtd, NULL, 0);
-	if (ret) {
-		dev_err(nc->dev, "Failed to register mtd device: %d\n", ret);
-		nand_cleanup(chip);
-		return ret;
-	}
-
-	list_add_tail(&nand->node, &nc->chips);
-
-	return 0;
-}
-
 static struct atmel_nand *atmel_nand_create(struct atmel_nand_controller *nc,
 					    struct device_node *np,
 					    int reg_cells)
@@ -1750,6 +1682,8 @@ static int
 atmel_nand_controller_add_nand(struct atmel_nand_controller *nc,
 			       struct atmel_nand *nand)
 {
+	struct nand_chip *chip = &nand->base;
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	int ret;
 
 	/* No card inserted, skip this NAND. */
@@ -1760,15 +1694,22 @@ atmel_nand_controller_add_nand(struct atmel_nand_controller *nc,
 
 	nc->caps->ops->nand_init(nc, nand);
 
-	ret = atmel_nand_detect(nand);
-	if (ret)
+	ret = nand_scan(mtd, nand->numcs);
+	if (ret) {
+		dev_err(nc->dev, "NAND scan failed: %d\n", ret);
 		return ret;
+	}
 
-	ret = nc->caps->ops->ecc_init(nand);
-	if (ret)
+	ret = mtd_device_register(mtd, NULL, 0);
+	if (ret) {
+		dev_err(nc->dev, "Failed to register mtd device: %d\n", ret);
+		nand_cleanup(chip);
 		return ret;
+	}
+
+	list_add_tail(&nand->node, &nc->chips);
 
-	return atmel_nand_register(nand);
+	return 0;
 }
 
 static int
@@ -1778,7 +1719,7 @@ atmel_nand_controller_remove_nands(struct atmel_nand_controller *nc)
 	int ret;
 
 	list_for_each_entry_safe(nand, tmp, &nc->chips, node) {
-		ret = atmel_nand_unregister(nand);
+		ret = atmel_nand_controller_remove_nand(nand);
 		if (ret)
 			return ret;
 	}
@@ -1953,6 +1894,51 @@ static const struct of_device_id atmel_matrix_of_ids[] = {
 	{ /* sentinel */ },
 };
 
+static int atmel_nand_attach_chip(struct nand_chip *chip)
+{
+	struct atmel_nand_controller *nc = to_nand_controller(chip->controller);
+	struct atmel_nand *nand = to_atmel_nand(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	int ret;
+
+	ret = nc->caps->ops->ecc_init(chip);
+	if (ret)
+		return ret;
+
+	if (nc->caps->legacy_of_bindings || !nc->dev->of_node) {
+		/*
+		 * We keep the MTD name unchanged to avoid breaking platforms
+		 * where the MTD cmdline parser is used and the bootloader
+		 * has not been updated to use the new naming scheme.
+		 */
+		mtd->name = "atmel_nand";
+	} else if (!mtd->name) {
+		/*
+		 * If the new bindings are used and the bootloader has not been
+		 * updated to pass a new mtdparts parameter on the cmdline, you
+		 * should define the following property in your nand node:
+		 *
+		 *	label = "atmel_nand";
+		 *
+		 * This way, mtd->name will be set by the core when
+		 * nand_set_flash_node() is called.
+		 */
+		mtd->name = devm_kasprintf(nc->dev, GFP_KERNEL,
+					   "%s:nand.%d", dev_name(nc->dev),
+					   nand->cs[0].id);
+		if (!mtd->name) {
+			dev_err(nc->dev, "Failed to allocate mtd->name\n");
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops atmel_nand_controller_ops = {
+	.attach_chip = atmel_nand_attach_chip,
+};
+
 static int atmel_nand_controller_init(struct atmel_nand_controller *nc,
 				struct platform_device *pdev,
 				const struct atmel_nand_controller_caps *caps)
@@ -1961,7 +1947,8 @@ static int atmel_nand_controller_init(struct atmel_nand_controller *nc,
 	struct device_node *np = dev->of_node;
 	int ret;
 
-	nand_hw_control_init(&nc->base);
+	nand_controller_init(&nc->base);
+	nc->base.ops = &atmel_nand_controller_ops;
 	INIT_LIST_HEAD(&nc->chips);
 	nc->dev = dev;
 	nc->caps = caps;
@@ -1977,7 +1964,7 @@ static int atmel_nand_controller_init(struct atmel_nand_controller *nc,
 		return ret;
 	}
 
-	if (nc->caps->has_dma) {
+	if (nc->caps->has_dma && !atmel_nand_avoid_dma) {
 		dma_cap_mask_t mask;
 
 		dma_cap_zero(mask);
@@ -2045,7 +2032,7 @@ atmel_smc_nand_controller_init(struct atmel_smc_nand_controller *nc)
 		return ret;
 	}
 
-	nc->ebi_csa_offs = (unsigned int)match->data;
+	nc->ebi_csa_offs = (uintptr_t)match->data;
 
 	/*
 	 * The at91sam9263 has 2 EBIs, if the NAND controller is under EBI1
@@ -2214,9 +2201,9 @@ atmel_hsmc_nand_controller_init(struct atmel_hsmc_nand_controller *nc)
 		return -ENOMEM;
 	}
 
-	nc->sram.virt = gen_pool_dma_alloc(nc->sram.pool,
-					    ATMEL_NFC_SRAM_SIZE,
-					    &nc->sram.dma);
+	nc->sram.virt = (void __iomem *)gen_pool_dma_alloc(nc->sram.pool,
+							   ATMEL_NFC_SRAM_SIZE,
+							   &nc->sram.dma);
 	if (!nc->sram.virt) {
 		dev_err(nc->base.dev,
 			"Could not allocate memory from the NFC SRAM pool\n");
diff --git a/drivers/mtd/nand/raw/au1550nd.c b/drivers/mtd/nand/raw/au1550nd.c
index df0ef1f1e2f5..35f5c84cd331 100644
--- a/drivers/mtd/nand/raw/au1550nd.c
+++ b/drivers/mtd/nand/raw/au1550nd.c
@@ -8,7 +8,6 @@
  */
 
 #include <linux/slab.h>
-#include <linux/gpio.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/mtd/mtd.h>
diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
index 1306aaa7a8bf..4b90d5b380c2 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
@@ -114,7 +114,7 @@ enum {
 
 struct brcmnand_controller {
 	struct device		*dev;
-	struct nand_hw_control	controller;
+	struct nand_controller	controller;
 	void __iomem		*nand_base;
 	void __iomem		*nand_fc; /* flash cache */
 	void __iomem		*flash_dma_base;
@@ -2208,6 +2208,40 @@ static int brcmnand_setup_dev(struct brcmnand_host *host)
 	return 0;
 }
 
+static int brcmnand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct brcmnand_host *host = nand_get_controller_data(chip);
+	int ret;
+
+	chip->options |= NAND_NO_SUBPAGE_WRITE;
+	/*
+	 * Avoid (for instance) kmap()'d buffers from JFFS2, which we can't DMA
+	 * to/from, and have nand_base pass us a bounce buffer instead, as
+	 * needed.
+	 */
+	chip->options |= NAND_USE_BOUNCE_BUFFER;
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+	if (brcmnand_setup_dev(host))
+		return -ENXIO;
+
+	chip->ecc.size = host->hwcfg.sector_size_1k ? 1024 : 512;
+
+	/* only use our internal HW threshold */
+	mtd->bitflip_threshold = 1;
+
+	ret = brcmstb_choose_ecc_layout(host);
+
+	return ret;
+}
+
+static const struct nand_controller_ops brcmnand_controller_ops = {
+	.attach_chip = brcmnand_attach_chip,
+};
+
 static int brcmnand_init_cs(struct brcmnand_host *host, struct device_node *dn)
 {
 	struct brcmnand_controller *ctrl = host->ctrl;
@@ -2267,33 +2301,7 @@ static int brcmnand_init_cs(struct brcmnand_host *host, struct device_node *dn)
 	nand_writereg(ctrl, cfg_offs,
 		      nand_readreg(ctrl, cfg_offs) & ~CFG_BUS_WIDTH);
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		return ret;
-
-	chip->options |= NAND_NO_SUBPAGE_WRITE;
-	/*
-	 * Avoid (for instance) kmap()'d buffers from JFFS2, which we can't DMA
-	 * to/from, and have nand_base pass us a bounce buffer instead, as
-	 * needed.
-	 */
-	chip->options |= NAND_USE_BOUNCE_BUFFER;
-
-	if (chip->bbt_options & NAND_BBT_USE_FLASH)
-		chip->bbt_options |= NAND_BBT_NO_OOB;
-
-	if (brcmnand_setup_dev(host))
-		return -ENXIO;
-
-	chip->ecc.size = host->hwcfg.sector_size_1k ? 1024 : 512;
-	/* only use our internal HW threshold */
-	mtd->bitflip_threshold = 1;
-
-	ret = brcmstb_choose_ecc_layout(host);
-	if (ret)
-		return ret;
-
-	ret = nand_scan_tail(mtd);
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		return ret;
 
@@ -2433,7 +2441,8 @@ int brcmnand_probe(struct platform_device *pdev, struct brcmnand_soc *soc)
 
 	init_completion(&ctrl->done);
 	init_completion(&ctrl->dma_done);
-	nand_hw_control_init(&ctrl->controller);
+	nand_controller_init(&ctrl->controller);
+	ctrl->controller.ops = &brcmnand_controller_ops;
 	INIT_LIST_HEAD(&ctrl->host_list);
 
 	/* NAND register range */
diff --git a/drivers/mtd/nand/raw/cafe_nand.c b/drivers/mtd/nand/raw/cafe_nand.c
index d721f489b38b..1dbe43adcfe7 100644
--- a/drivers/mtd/nand/raw/cafe_nand.c
+++ b/drivers/mtd/nand/raw/cafe_nand.c
@@ -67,6 +67,7 @@ struct cafe_priv {
 	int nr_data;
 	int data_pos;
 	int page_addr;
+	bool usedma;
 	dma_addr_t dmaaddr;
 	unsigned char *dmabuf;
 };
@@ -121,7 +122,7 @@ static void cafe_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len)
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	struct cafe_priv *cafe = nand_get_controller_data(chip);
 
-	if (usedma)
+	if (cafe->usedma)
 		memcpy(cafe->dmabuf + cafe->datalen, buf, len);
 	else
 		memcpy_toio(cafe->mmio + CAFE_NAND_WRITE_DATA + cafe->datalen, buf, len);
@@ -137,7 +138,7 @@ static void cafe_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	struct cafe_priv *cafe = nand_get_controller_data(chip);
 
-	if (usedma)
+	if (cafe->usedma)
 		memcpy(buf, cafe->dmabuf + cafe->datalen, len);
 	else
 		memcpy_fromio(buf, cafe->mmio + CAFE_NAND_READ_DATA + cafe->datalen, len);
@@ -253,7 +254,7 @@ static void cafe_nand_cmdfunc(struct mtd_info *mtd, unsigned command,
 	/* NB: The datasheet lies -- we really should be subtracting 1 here */
 	cafe_writel(cafe, cafe->datalen, NAND_DATA_LEN);
 	cafe_writel(cafe, 0x90000000, NAND_IRQ);
-	if (usedma && (ctl1 & (3<<25))) {
+	if (cafe->usedma && (ctl1 & (3<<25))) {
 		uint32_t dmactl = 0xc0000000 + cafe->datalen;
 		/* If WR or RD bits set, set up DMA */
 		if (ctl1 & (1<<26)) {
@@ -345,11 +346,6 @@ static irqreturn_t cafe_nand_interrupt(int irq, void *id)
 	return IRQ_HANDLED;
 }
 
-static void cafe_nand_bug(struct mtd_info *mtd)
-{
-	BUG();
-}
-
 static int cafe_nand_write_oob(struct mtd_info *mtd,
 			       struct nand_chip *chip, int page)
 {
@@ -598,6 +594,76 @@ static int cafe_mul(int x)
 	return gf4096_mul(x, 0xe01);
 }
 
+static int cafe_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct cafe_priv *cafe = nand_get_controller_data(chip);
+	int err = 0;
+
+	cafe->dmabuf = dma_alloc_coherent(&cafe->pdev->dev, 2112,
+					  &cafe->dmaaddr, GFP_KERNEL);
+	if (!cafe->dmabuf)
+		return -ENOMEM;
+
+	/* Set up DMA address */
+	cafe_writel(cafe, lower_32_bits(cafe->dmaaddr), NAND_DMA_ADDR0);
+	cafe_writel(cafe, upper_32_bits(cafe->dmaaddr), NAND_DMA_ADDR1);
+
+	cafe_dev_dbg(&cafe->pdev->dev, "Set DMA address to %x (virt %p)\n",
+		     cafe_readl(cafe, NAND_DMA_ADDR0), cafe->dmabuf);
+
+	/* Restore the DMA flag */
+	cafe->usedma = usedma;
+
+	cafe->ctl2 = BIT(27); /* Reed-Solomon ECC */
+	if (mtd->writesize == 2048)
+		cafe->ctl2 |= BIT(29); /* 2KiB page size */
+
+	/* Set up ECC according to the type of chip we found */
+	mtd_set_ooblayout(mtd, &cafe_ooblayout_ops);
+	if (mtd->writesize == 2048) {
+		cafe->nand.bbt_td = &cafe_bbt_main_descr_2048;
+		cafe->nand.bbt_md = &cafe_bbt_mirror_descr_2048;
+	} else if (mtd->writesize == 512) {
+		cafe->nand.bbt_td = &cafe_bbt_main_descr_512;
+		cafe->nand.bbt_md = &cafe_bbt_mirror_descr_512;
+	} else {
+		dev_warn(&cafe->pdev->dev,
+			 "Unexpected NAND flash writesize %d. Aborting\n",
+			 mtd->writesize);
+		err = -ENOTSUPP;
+		goto out_free_dma;
+	}
+
+	cafe->nand.ecc.mode = NAND_ECC_HW_SYNDROME;
+	cafe->nand.ecc.size = mtd->writesize;
+	cafe->nand.ecc.bytes = 14;
+	cafe->nand.ecc.strength = 4;
+	cafe->nand.ecc.write_page = cafe_nand_write_page_lowlevel;
+	cafe->nand.ecc.write_oob = cafe_nand_write_oob;
+	cafe->nand.ecc.read_page = cafe_nand_read_page;
+	cafe->nand.ecc.read_oob = cafe_nand_read_oob;
+
+	return 0;
+
+ out_free_dma:
+	dma_free_coherent(&cafe->pdev->dev, 2112, cafe->dmabuf, cafe->dmaaddr);
+
+	return err;
+}
+
+static void cafe_nand_detach_chip(struct nand_chip *chip)
+{
+	struct cafe_priv *cafe = nand_get_controller_data(chip);
+
+	dma_free_coherent(&cafe->pdev->dev, 2112, cafe->dmabuf, cafe->dmaaddr);
+}
+
+static const struct nand_controller_ops cafe_nand_controller_ops = {
+	.attach_chip = cafe_nand_attach_chip,
+	.detach_chip = cafe_nand_detach_chip,
+};
+
 static int cafe_nand_probe(struct pci_dev *pdev,
 				     const struct pci_device_id *ent)
 {
@@ -605,7 +671,6 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 	struct cafe_priv *cafe;
 	uint32_t ctrl;
 	int err = 0;
-	int old_dma;
 
 	/* Very old versions shared the same PCI ident for all three
 	   functions on the chip. Verify the class too... */
@@ -713,65 +778,15 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 		cafe_readl(cafe, GLOBAL_CTRL),
 		cafe_readl(cafe, GLOBAL_IRQ_MASK));
 
-	/* Do not use the DMA for the nand_scan_ident() */
-	old_dma = usedma;
-	usedma = 0;
+	/* Do not use the DMA during the NAND identification */
+	cafe->usedma = 0;
 
 	/* Scan to find existence of the device */
-	err = nand_scan_ident(mtd, 2, NULL);
+	cafe->nand.dummy_controller.ops = &cafe_nand_controller_ops;
+	err = nand_scan(mtd, 2);
 	if (err)
 		goto out_irq;
 
-	cafe->dmabuf = dma_alloc_coherent(&cafe->pdev->dev, 2112,
-					  &cafe->dmaaddr, GFP_KERNEL);
-	if (!cafe->dmabuf) {
-		err = -ENOMEM;
-		goto out_irq;
-	}
-
-	/* Set up DMA address */
-	cafe_writel(cafe, lower_32_bits(cafe->dmaaddr), NAND_DMA_ADDR0);
-	cafe_writel(cafe, upper_32_bits(cafe->dmaaddr), NAND_DMA_ADDR1);
-
-	cafe_dev_dbg(&cafe->pdev->dev, "Set DMA address to %x (virt %p)\n",
-		cafe_readl(cafe, NAND_DMA_ADDR0), cafe->dmabuf);
-
-	/* Restore the DMA flag */
-	usedma = old_dma;
-
-	cafe->ctl2 = 1<<27; /* Reed-Solomon ECC */
-	if (mtd->writesize == 2048)
-		cafe->ctl2 |= 1<<29; /* 2KiB page size */
-
-	/* Set up ECC according to the type of chip we found */
-	mtd_set_ooblayout(mtd, &cafe_ooblayout_ops);
-	if (mtd->writesize == 2048) {
-		cafe->nand.bbt_td = &cafe_bbt_main_descr_2048;
-		cafe->nand.bbt_md = &cafe_bbt_mirror_descr_2048;
-	} else if (mtd->writesize == 512) {
-		cafe->nand.bbt_td = &cafe_bbt_main_descr_512;
-		cafe->nand.bbt_md = &cafe_bbt_mirror_descr_512;
-	} else {
-		pr_warn("Unexpected NAND flash writesize %d. Aborting\n",
-			mtd->writesize);
-		goto out_free_dma;
-	}
-	cafe->nand.ecc.mode = NAND_ECC_HW_SYNDROME;
-	cafe->nand.ecc.size = mtd->writesize;
-	cafe->nand.ecc.bytes = 14;
-	cafe->nand.ecc.strength = 4;
-	cafe->nand.ecc.hwctl  = (void *)cafe_nand_bug;
-	cafe->nand.ecc.calculate = (void *)cafe_nand_bug;
-	cafe->nand.ecc.correct  = (void *)cafe_nand_bug;
-	cafe->nand.ecc.write_page = cafe_nand_write_page_lowlevel;
-	cafe->nand.ecc.write_oob = cafe_nand_write_oob;
-	cafe->nand.ecc.read_page = cafe_nand_read_page;
-	cafe->nand.ecc.read_oob = cafe_nand_read_oob;
-
-	err = nand_scan_tail(mtd);
-	if (err)
-		goto out_free_dma;
-
 	pci_set_drvdata(pdev, mtd);
 
 	mtd->name = "cafe_nand";
@@ -783,8 +798,6 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 
  out_cleanup_nand:
 	nand_cleanup(&cafe->nand);
- out_free_dma:
-	dma_free_coherent(&cafe->pdev->dev, 2112, cafe->dmabuf, cafe->dmaaddr);
  out_irq:
 	/* Disable NAND IRQ in global IRQ mask register */
 	cafe_writel(cafe, ~1 & cafe_readl(cafe, GLOBAL_IRQ_MASK), GLOBAL_IRQ_MASK);
diff --git a/drivers/mtd/nand/raw/cmx270_nand.c b/drivers/mtd/nand/raw/cmx270_nand.c
index 02d6751e9efe..b66e254b6802 100644
--- a/drivers/mtd/nand/raw/cmx270_nand.c
+++ b/drivers/mtd/nand/raw/cmx270_nand.c
@@ -200,8 +200,8 @@ static int __init cmx270_init(void)
 	}
 
 	/* Register the partitions */
-	ret = mtd_device_parse_register(cmx270_nand_mtd, NULL, NULL,
-					partition_info, NUM_PARTITIONS);
+	ret = mtd_device_register(cmx270_nand_mtd, partition_info,
+				  NUM_PARTITIONS);
 	if (ret)
 		goto err_scan;
 
diff --git a/drivers/mtd/nand/raw/cs553x_nand.c b/drivers/mtd/nand/raw/cs553x_nand.c
index 82269fde9e66..beafad62e7d5 100644
--- a/drivers/mtd/nand/raw/cs553x_nand.c
+++ b/drivers/mtd/nand/raw/cs553x_nand.c
@@ -310,8 +310,7 @@ static int __init cs553x_init(void)
 	for (i = 0; i < NR_CS553X_CONTROLLERS; i++) {
 		if (cs553x_mtd[i]) {
 			/* If any devices registered, return success. Else the last error. */
-			mtd_device_parse_register(cs553x_mtd[i], NULL, NULL,
-						  NULL, 0);
+			mtd_device_register(cs553x_mtd[i], NULL, 0);
 			err = 0;
 		}
 	}
diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c
index cd12e5abafde..40145e206a6b 100644
--- a/drivers/mtd/nand/raw/davinci_nand.c
+++ b/drivers/mtd/nand/raw/davinci_nand.c
@@ -53,15 +53,14 @@
 struct davinci_nand_info {
 	struct nand_chip	chip;
 
-	struct device		*dev;
+	struct platform_device	*pdev;
 
 	bool			is_readmode;
 
 	void __iomem		*base;
 	void __iomem		*vaddr;
 
-	uint32_t		ioaddr;
-	uint32_t		current_cs;
+	void __iomem		*current_cs;
 
 	uint32_t		mask_chipsel;
 	uint32_t		mask_ale;
@@ -102,17 +101,17 @@ static void nand_davinci_hwcontrol(struct mtd_info *mtd, int cmd,
 				   unsigned int ctrl)
 {
 	struct davinci_nand_info	*info = to_davinci_nand(mtd);
-	uint32_t			addr = info->current_cs;
+	void __iomem			*addr = info->current_cs;
 	struct nand_chip		*nand = mtd_to_nand(mtd);
 
 	/* Did the control lines change? */
 	if (ctrl & NAND_CTRL_CHANGE) {
 		if ((ctrl & NAND_CTRL_CLE) == NAND_CTRL_CLE)
-			addr |= info->mask_cle;
+			addr += info->mask_cle;
 		else if ((ctrl & NAND_CTRL_ALE) == NAND_CTRL_ALE)
-			addr |= info->mask_ale;
+			addr += info->mask_ale;
 
-		nand->IO_ADDR_W = (void __iomem __force *)addr;
+		nand->IO_ADDR_W = addr;
 	}
 
 	if (cmd != NAND_CMD_NONE)
@@ -122,14 +121,14 @@ static void nand_davinci_hwcontrol(struct mtd_info *mtd, int cmd,
 static void nand_davinci_select_chip(struct mtd_info *mtd, int chip)
 {
 	struct davinci_nand_info	*info = to_davinci_nand(mtd);
-	uint32_t			addr = info->ioaddr;
+
+	info->current_cs = info->vaddr;
 
 	/* maybe kick in a second chipselect */
 	if (chip > 0)
-		addr |= info->mask_chipsel;
-	info->current_cs = addr;
+		info->current_cs += info->mask_chipsel;
 
-	info->chip.IO_ADDR_W = (void __iomem __force *)addr;
+	info->chip.IO_ADDR_W = info->current_cs;
 	info->chip.IO_ADDR_R = info->chip.IO_ADDR_W;
 }
 
@@ -319,7 +318,7 @@ static int nand_davinci_correct_4bit(struct mtd_info *mtd,
 	/* Unpack ten bytes into eight 10 bit values.  We know we're
 	 * little-endian, and use type punning for less shifting/masking.
 	 */
-	if (WARN_ON(0x01 & (unsigned) ecc_code))
+	if (WARN_ON(0x01 & (uintptr_t)ecc_code))
 		return -EINVAL;
 	ecc16 = (unsigned short *)ecc_code;
 
@@ -441,9 +440,9 @@ static void nand_davinci_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
 
-	if ((0x03 & ((unsigned)buf)) == 0 && (0x03 & len) == 0)
+	if ((0x03 & ((uintptr_t)buf)) == 0 && (0x03 & len) == 0)
 		ioread32_rep(chip->IO_ADDR_R, buf, len >> 2);
-	else if ((0x01 & ((unsigned)buf)) == 0 && (0x01 & len) == 0)
+	else if ((0x01 & ((uintptr_t)buf)) == 0 && (0x01 & len) == 0)
 		ioread16_rep(chip->IO_ADDR_R, buf, len >> 1);
 	else
 		ioread8_rep(chip->IO_ADDR_R, buf, len);
@@ -454,9 +453,9 @@ static void nand_davinci_write_buf(struct mtd_info *mtd,
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
 
-	if ((0x03 & ((unsigned)buf)) == 0 && (0x03 & len) == 0)
+	if ((0x03 & ((uintptr_t)buf)) == 0 && (0x03 & len) == 0)
 		iowrite32_rep(chip->IO_ADDR_R, buf, len >> 2);
-	else if ((0x01 & ((unsigned)buf)) == 0 && (0x01 & len) == 0)
+	else if ((0x01 & ((uintptr_t)buf)) == 0 && (0x01 & len) == 0)
 		iowrite16_rep(chip->IO_ADDR_R, buf, len >> 1);
 	else
 		iowrite8_rep(chip->IO_ADDR_R, buf, len);
@@ -606,6 +605,104 @@ static struct davinci_nand_pdata
 }
 #endif
 
+static int davinci_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct davinci_nand_info *info = to_davinci_nand(mtd);
+	struct davinci_nand_pdata *pdata = nand_davinci_get_pdata(info->pdev);
+	int ret = 0;
+
+	if (IS_ERR(pdata))
+		return PTR_ERR(pdata);
+
+	switch (info->chip.ecc.mode) {
+	case NAND_ECC_NONE:
+		pdata->ecc_bits = 0;
+		break;
+	case NAND_ECC_SOFT:
+		pdata->ecc_bits = 0;
+		/*
+		 * This driver expects Hamming based ECC when ecc_mode is set
+		 * to NAND_ECC_SOFT. Force ecc.algo to NAND_ECC_HAMMING to
+		 * avoid adding an extra ->ecc_algo field to
+		 * davinci_nand_pdata.
+		 */
+		info->chip.ecc.algo = NAND_ECC_HAMMING;
+		break;
+	case NAND_ECC_HW:
+		if (pdata->ecc_bits == 4) {
+			/*
+			 * No sanity checks:  CPUs must support this,
+			 * and the chips may not use NAND_BUSWIDTH_16.
+			 */
+
+			/* No sharing 4-bit hardware between chipselects yet */
+			spin_lock_irq(&davinci_nand_lock);
+			if (ecc4_busy)
+				ret = -EBUSY;
+			else
+				ecc4_busy = true;
+			spin_unlock_irq(&davinci_nand_lock);
+
+			if (ret == -EBUSY)
+				return ret;
+
+			info->chip.ecc.calculate = nand_davinci_calculate_4bit;
+			info->chip.ecc.correct = nand_davinci_correct_4bit;
+			info->chip.ecc.hwctl = nand_davinci_hwctl_4bit;
+			info->chip.ecc.bytes = 10;
+			info->chip.ecc.options = NAND_ECC_GENERIC_ERASED_CHECK;
+			info->chip.ecc.algo = NAND_ECC_BCH;
+		} else {
+			/* 1bit ecc hamming */
+			info->chip.ecc.calculate = nand_davinci_calculate_1bit;
+			info->chip.ecc.correct = nand_davinci_correct_1bit;
+			info->chip.ecc.hwctl = nand_davinci_hwctl_1bit;
+			info->chip.ecc.bytes = 3;
+			info->chip.ecc.algo = NAND_ECC_HAMMING;
+		}
+		info->chip.ecc.size = 512;
+		info->chip.ecc.strength = pdata->ecc_bits;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/*
+	 * Update ECC layout if needed ... for 1-bit HW ECC, the default
+	 * is OK, but it allocates 6 bytes when only 3 are needed (for
+	 * each 512 bytes).  For the 4-bit HW ECC, that default is not
+	 * usable:  10 bytes are needed, not 6.
+	 */
+	if (pdata->ecc_bits == 4) {
+		int chunks = mtd->writesize / 512;
+
+		if (!chunks || mtd->oobsize < 16) {
+			dev_dbg(&info->pdev->dev, "too small\n");
+			return -EINVAL;
+		}
+
+		/* For small page chips, preserve the manufacturer's
+		 * badblock marking data ... and make sure a flash BBT
+		 * table marker fits in the free bytes.
+		 */
+		if (chunks == 1) {
+			mtd_set_ooblayout(mtd, &hwecc4_small_ooblayout_ops);
+		} else if (chunks == 4 || chunks == 8) {
+			mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+			info->chip.ecc.mode = NAND_ECC_HW_OOB_FIRST;
+		} else {
+			return -EIO;
+		}
+	}
+
+	return ret;
+}
+
+static const struct nand_controller_ops davinci_nand_controller_ops = {
+	.attach_chip = davinci_nand_attach_chip,
+};
+
 static int nand_davinci_probe(struct platform_device *pdev)
 {
 	struct davinci_nand_pdata	*pdata;
@@ -659,7 +756,7 @@ static int nand_davinci_probe(struct platform_device *pdev)
 		return -EADDRNOTAVAIL;
 	}
 
-	info->dev		= &pdev->dev;
+	info->pdev		= pdev;
 	info->base		= base;
 	info->vaddr		= vaddr;
 
@@ -680,9 +777,7 @@ static int nand_davinci_probe(struct platform_device *pdev)
 	info->chip.bbt_md	= pdata->bbt_md;
 	info->timing		= pdata->timing;
 
-	info->ioaddr		= (uint32_t __force) vaddr;
-
-	info->current_cs	= info->ioaddr;
+	info->current_cs	= info->vaddr;
 	info->core_chipsel	= pdata->core_chipsel;
 	info->mask_chipsel	= pdata->mask_chipsel;
 
@@ -711,100 +806,15 @@ static int nand_davinci_probe(struct platform_device *pdev)
 	spin_unlock_irq(&davinci_nand_lock);
 
 	/* Scan to find existence of the device(s) */
-	ret = nand_scan_ident(mtd, pdata->mask_chipsel ? 2 : 1, NULL);
+	info->chip.dummy_controller.ops = &davinci_nand_controller_ops;
+	ret = nand_scan(mtd, pdata->mask_chipsel ? 2 : 1);
 	if (ret < 0) {
 		dev_dbg(&pdev->dev, "no NAND chip(s) found\n");
 		return ret;
 	}
 
-	switch (info->chip.ecc.mode) {
-	case NAND_ECC_NONE:
-		pdata->ecc_bits = 0;
-		break;
-	case NAND_ECC_SOFT:
-		pdata->ecc_bits = 0;
-		/*
-		 * This driver expects Hamming based ECC when ecc_mode is set
-		 * to NAND_ECC_SOFT. Force ecc.algo to NAND_ECC_HAMMING to
-		 * avoid adding an extra ->ecc_algo field to
-		 * davinci_nand_pdata.
-		 */
-		info->chip.ecc.algo = NAND_ECC_HAMMING;
-		break;
-	case NAND_ECC_HW:
-		if (pdata->ecc_bits == 4) {
-			/* No sanity checks:  CPUs must support this,
-			 * and the chips may not use NAND_BUSWIDTH_16.
-			 */
-
-			/* No sharing 4-bit hardware between chipselects yet */
-			spin_lock_irq(&davinci_nand_lock);
-			if (ecc4_busy)
-				ret = -EBUSY;
-			else
-				ecc4_busy = true;
-			spin_unlock_irq(&davinci_nand_lock);
-
-			if (ret == -EBUSY)
-				return ret;
-
-			info->chip.ecc.calculate = nand_davinci_calculate_4bit;
-			info->chip.ecc.correct = nand_davinci_correct_4bit;
-			info->chip.ecc.hwctl = nand_davinci_hwctl_4bit;
-			info->chip.ecc.bytes = 10;
-			info->chip.ecc.options = NAND_ECC_GENERIC_ERASED_CHECK;
-			info->chip.ecc.algo = NAND_ECC_BCH;
-		} else {
-			/* 1bit ecc hamming */
-			info->chip.ecc.calculate = nand_davinci_calculate_1bit;
-			info->chip.ecc.correct = nand_davinci_correct_1bit;
-			info->chip.ecc.hwctl = nand_davinci_hwctl_1bit;
-			info->chip.ecc.bytes = 3;
-			info->chip.ecc.algo = NAND_ECC_HAMMING;
-		}
-		info->chip.ecc.size = 512;
-		info->chip.ecc.strength = pdata->ecc_bits;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	/* Update ECC layout if needed ... for 1-bit HW ECC, the default
-	 * is OK, but it allocates 6 bytes when only 3 are needed (for
-	 * each 512 bytes).  For the 4-bit HW ECC, that default is not
-	 * usable:  10 bytes are needed, not 6.
-	 */
-	if (pdata->ecc_bits == 4) {
-		int	chunks = mtd->writesize / 512;
-
-		if (!chunks || mtd->oobsize < 16) {
-			dev_dbg(&pdev->dev, "too small\n");
-			ret = -EINVAL;
-			goto err;
-		}
-
-		/* For small page chips, preserve the manufacturer's
-		 * badblock marking data ... and make sure a flash BBT
-		 * table marker fits in the free bytes.
-		 */
-		if (chunks == 1) {
-			mtd_set_ooblayout(mtd, &hwecc4_small_ooblayout_ops);
-		} else if (chunks == 4 || chunks == 8) {
-			mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
-			info->chip.ecc.mode = NAND_ECC_HW_OOB_FIRST;
-		} else {
-			ret = -EIO;
-			goto err;
-		}
-	}
-
-	ret = nand_scan_tail(mtd);
-	if (ret < 0)
-		goto err;
-
 	if (pdata->parts)
-		ret = mtd_device_parse_register(mtd, NULL, NULL,
-					pdata->parts, pdata->nr_parts);
+		ret = mtd_device_register(mtd, pdata->parts, pdata->nr_parts);
 	else
 		ret = mtd_device_register(mtd, NULL, 0);
 	if (ret < 0)
@@ -819,11 +829,6 @@ static int nand_davinci_probe(struct platform_device *pdev)
 err_cleanup_nand:
 	nand_cleanup(&info->chip);
 
-err:
-	spin_lock_irq(&davinci_nand_lock);
-	if (info->chip.ecc.mode == NAND_ECC_HW_SYNDROME)
-		ecc4_busy = false;
-	spin_unlock_irq(&davinci_nand_lock);
 	return ret;
 }
 
diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c
index 2a302a1d1430..ca18612c4201 100644
--- a/drivers/mtd/nand/raw/denali.c
+++ b/drivers/mtd/nand/raw/denali.c
@@ -51,14 +51,6 @@ MODULE_LICENSE("GPL");
 #define DENALI_INVALID_BANK	-1
 #define DENALI_NR_BANKS		4
 
-/*
- * The bus interface clock, clk_x, is phase aligned with the core clock.  The
- * clk_x is an integral multiple N of the core clk.  The value N is configured
- * at IP delivery time, and its available value is 4, 5, or 6.  We need to align
- * to the largest value to make it work with any possible configuration.
- */
-#define DENALI_CLK_X_MULT	6
-
 static inline struct denali_nand_info *mtd_to_denali(struct mtd_info *mtd)
 {
 	return container_of(mtd_to_nand(mtd), struct denali_nand_info, nand);
@@ -954,7 +946,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
 	const struct nand_sdr_timings *timings;
-	unsigned long t_clk;
+	unsigned long t_x, mult_x;
 	int acc_clks, re_2_we, re_2_re, we_2_re, addr_2_data;
 	int rdwr_en_lo, rdwr_en_hi, rdwr_en_lo_hi, cs_setup;
 	int addr_2_data_mask;
@@ -965,15 +957,24 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 		return PTR_ERR(timings);
 
 	/* clk_x period in picoseconds */
-	t_clk = DIV_ROUND_DOWN_ULL(1000000000000ULL, denali->clk_x_rate);
-	if (!t_clk)
+	t_x = DIV_ROUND_DOWN_ULL(1000000000000ULL, denali->clk_x_rate);
+	if (!t_x)
+		return -EINVAL;
+
+	/*
+	 * The bus interface clock, clk_x, is phase aligned with the core clock.
+	 * The clk_x is an integral multiple N of the core clk.  The value N is
+	 * configured at IP delivery time, and its available value is 4, 5, 6.
+	 */
+	mult_x = DIV_ROUND_CLOSEST_ULL(denali->clk_x_rate, denali->clk_rate);
+	if (mult_x < 4 || mult_x > 6)
 		return -EINVAL;
 
 	if (chipnr == NAND_DATA_IFACE_CHECK_ONLY)
 		return 0;
 
 	/* tREA -> ACC_CLKS */
-	acc_clks = DIV_ROUND_UP(timings->tREA_max, t_clk);
+	acc_clks = DIV_ROUND_UP(timings->tREA_max, t_x);
 	acc_clks = min_t(int, acc_clks, ACC_CLKS__VALUE);
 
 	tmp = ioread32(denali->reg + ACC_CLKS);
@@ -982,7 +983,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	iowrite32(tmp, denali->reg + ACC_CLKS);
 
 	/* tRWH -> RE_2_WE */
-	re_2_we = DIV_ROUND_UP(timings->tRHW_min, t_clk);
+	re_2_we = DIV_ROUND_UP(timings->tRHW_min, t_x);
 	re_2_we = min_t(int, re_2_we, RE_2_WE__VALUE);
 
 	tmp = ioread32(denali->reg + RE_2_WE);
@@ -991,7 +992,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	iowrite32(tmp, denali->reg + RE_2_WE);
 
 	/* tRHZ -> RE_2_RE */
-	re_2_re = DIV_ROUND_UP(timings->tRHZ_max, t_clk);
+	re_2_re = DIV_ROUND_UP(timings->tRHZ_max, t_x);
 	re_2_re = min_t(int, re_2_re, RE_2_RE__VALUE);
 
 	tmp = ioread32(denali->reg + RE_2_RE);
@@ -1005,8 +1006,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	 * With WE_2_RE properly set, the Denali controller automatically takes
 	 * care of the delay; the driver need not set NAND_WAIT_TCCS.
 	 */
-	we_2_re = DIV_ROUND_UP(max(timings->tCCS_min, timings->tWHR_min),
-			       t_clk);
+	we_2_re = DIV_ROUND_UP(max(timings->tCCS_min, timings->tWHR_min), t_x);
 	we_2_re = min_t(int, we_2_re, TWHR2_AND_WE_2_RE__WE_2_RE);
 
 	tmp = ioread32(denali->reg + TWHR2_AND_WE_2_RE);
@@ -1021,7 +1021,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	if (denali->revision < 0x0501)
 		addr_2_data_mask >>= 1;
 
-	addr_2_data = DIV_ROUND_UP(timings->tADL_min, t_clk);
+	addr_2_data = DIV_ROUND_UP(timings->tADL_min, t_x);
 	addr_2_data = min_t(int, addr_2_data, addr_2_data_mask);
 
 	tmp = ioread32(denali->reg + TCWAW_AND_ADDR_2_DATA);
@@ -1031,7 +1031,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 
 	/* tREH, tWH -> RDWR_EN_HI_CNT */
 	rdwr_en_hi = DIV_ROUND_UP(max(timings->tREH_min, timings->tWH_min),
-				  t_clk);
+				  t_x);
 	rdwr_en_hi = min_t(int, rdwr_en_hi, RDWR_EN_HI_CNT__VALUE);
 
 	tmp = ioread32(denali->reg + RDWR_EN_HI_CNT);
@@ -1040,11 +1040,10 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	iowrite32(tmp, denali->reg + RDWR_EN_HI_CNT);
 
 	/* tRP, tWP -> RDWR_EN_LO_CNT */
-	rdwr_en_lo = DIV_ROUND_UP(max(timings->tRP_min, timings->tWP_min),
-				  t_clk);
+	rdwr_en_lo = DIV_ROUND_UP(max(timings->tRP_min, timings->tWP_min), t_x);
 	rdwr_en_lo_hi = DIV_ROUND_UP(max(timings->tRC_min, timings->tWC_min),
-				     t_clk);
-	rdwr_en_lo_hi = max(rdwr_en_lo_hi, DENALI_CLK_X_MULT);
+				     t_x);
+	rdwr_en_lo_hi = max_t(int, rdwr_en_lo_hi, mult_x);
 	rdwr_en_lo = max(rdwr_en_lo, rdwr_en_lo_hi - rdwr_en_hi);
 	rdwr_en_lo = min_t(int, rdwr_en_lo, RDWR_EN_LO_CNT__VALUE);
 
@@ -1054,8 +1053,8 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	iowrite32(tmp, denali->reg + RDWR_EN_LO_CNT);
 
 	/* tCS, tCEA -> CS_SETUP_CNT */
-	cs_setup = max3((int)DIV_ROUND_UP(timings->tCS_min, t_clk) - rdwr_en_lo,
-			(int)DIV_ROUND_UP(timings->tCEA_max, t_clk) - acc_clks,
+	cs_setup = max3((int)DIV_ROUND_UP(timings->tCS_min, t_x) - rdwr_en_lo,
+			(int)DIV_ROUND_UP(timings->tCEA_max, t_x) - acc_clks,
 			0);
 	cs_setup = min_t(int, cs_setup, CS_SETUP_CNT__VALUE);
 
@@ -1120,33 +1119,6 @@ int denali_calc_ecc_bytes(int step_size, int strength)
 }
 EXPORT_SYMBOL(denali_calc_ecc_bytes);
 
-static int denali_ecc_setup(struct mtd_info *mtd, struct nand_chip *chip,
-			    struct denali_nand_info *denali)
-{
-	int oobavail = mtd->oobsize - denali->oob_skip_bytes;
-	int ret;
-
-	/*
-	 * If .size and .strength are already set (usually by DT),
-	 * check if they are supported by this controller.
-	 */
-	if (chip->ecc.size && chip->ecc.strength)
-		return nand_check_ecc_caps(chip, denali->ecc_caps, oobavail);
-
-	/*
-	 * We want .size and .strength closest to the chip's requirement
-	 * unless NAND_ECC_MAXIMIZE is requested.
-	 */
-	if (!(chip->ecc.options & NAND_ECC_MAXIMIZE)) {
-		ret = nand_match_ecc_req(chip, denali->ecc_caps, oobavail);
-		if (!ret)
-			return 0;
-	}
-
-	/* Max ECC strength is the last thing we can do */
-	return nand_maximize_ecc(chip, denali->ecc_caps, oobavail);
-}
-
 static int denali_ooblayout_ecc(struct mtd_info *mtd, int section,
 				struct mtd_oob_region *oobregion)
 {
@@ -1233,62 +1205,12 @@ static int denali_multidev_fixup(struct denali_nand_info *denali)
 	return 0;
 }
 
-int denali_init(struct denali_nand_info *denali)
+static int denali_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &denali->nand;
 	struct mtd_info *mtd = nand_to_mtd(chip);
-	u32 features = ioread32(denali->reg + FEATURES);
+	struct denali_nand_info *denali = mtd_to_denali(mtd);
 	int ret;
 
-	mtd->dev.parent = denali->dev;
-	denali_hw_init(denali);
-
-	init_completion(&denali->complete);
-	spin_lock_init(&denali->irq_lock);
-
-	denali_clear_irq_all(denali);
-
-	ret = devm_request_irq(denali->dev, denali->irq, denali_isr,
-			       IRQF_SHARED, DENALI_NAND_NAME, denali);
-	if (ret) {
-		dev_err(denali->dev, "Unable to request IRQ\n");
-		return ret;
-	}
-
-	denali_enable_irq(denali);
-	denali_reset_banks(denali);
-
-	denali->active_bank = DENALI_INVALID_BANK;
-
-	nand_set_flash_node(chip, denali->dev->of_node);
-	/* Fallback to the default name if DT did not give "label" property */
-	if (!mtd->name)
-		mtd->name = "denali-nand";
-
-	chip->select_chip = denali_select_chip;
-	chip->read_byte = denali_read_byte;
-	chip->write_byte = denali_write_byte;
-	chip->read_word = denali_read_word;
-	chip->cmd_ctrl = denali_cmd_ctrl;
-	chip->dev_ready = denali_dev_ready;
-	chip->waitfunc = denali_waitfunc;
-
-	if (features & FEATURES__INDEX_ADDR) {
-		denali->host_read = denali_indexed_read;
-		denali->host_write = denali_indexed_write;
-	} else {
-		denali->host_read = denali_direct_read;
-		denali->host_write = denali_direct_write;
-	}
-
-	/* clk rate info is needed for setup_data_interface */
-	if (denali->clk_x_rate)
-		chip->setup_data_interface = denali_setup_data_interface;
-
-	ret = nand_scan_ident(mtd, denali->max_banks, NULL);
-	if (ret)
-		goto disable_irq;
-
 	if (ioread32(denali->reg + FEATURES) & FEATURES__DMA)
 		denali->dma_avail = 1;
 
@@ -1317,10 +1239,11 @@ int denali_init(struct denali_nand_info *denali)
 	chip->ecc.mode = NAND_ECC_HW_SYNDROME;
 	chip->options |= NAND_NO_SUBPAGE_WRITE;
 
-	ret = denali_ecc_setup(mtd, chip, denali);
+	ret = nand_ecc_choose_conf(chip, denali->ecc_caps,
+				   mtd->oobsize - denali->oob_skip_bytes);
 	if (ret) {
 		dev_err(denali->dev, "Failed to setup ECC settings.\n");
-		goto disable_irq;
+		return ret;
 	}
 
 	dev_dbg(denali->dev,
@@ -1364,7 +1287,7 @@ int denali_init(struct denali_nand_info *denali)
 
 	ret = denali_multidev_fixup(denali);
 	if (ret)
-		goto disable_irq;
+		return ret;
 
 	/*
 	 * This buffer is DMA-mapped by denali_{read,write}_page_raw.  Do not
@@ -1372,26 +1295,92 @@ int denali_init(struct denali_nand_info *denali)
 	 * guarantee DMA-safe alignment.
 	 */
 	denali->buf = kmalloc(mtd->writesize + mtd->oobsize, GFP_KERNEL);
-	if (!denali->buf) {
-		ret = -ENOMEM;
-		goto disable_irq;
+	if (!denali->buf)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void denali_detach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct denali_nand_info *denali = mtd_to_denali(mtd);
+
+	kfree(denali->buf);
+}
+
+static const struct nand_controller_ops denali_controller_ops = {
+	.attach_chip = denali_attach_chip,
+	.detach_chip = denali_detach_chip,
+};
+
+int denali_init(struct denali_nand_info *denali)
+{
+	struct nand_chip *chip = &denali->nand;
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	u32 features = ioread32(denali->reg + FEATURES);
+	int ret;
+
+	mtd->dev.parent = denali->dev;
+	denali_hw_init(denali);
+
+	init_completion(&denali->complete);
+	spin_lock_init(&denali->irq_lock);
+
+	denali_clear_irq_all(denali);
+
+	ret = devm_request_irq(denali->dev, denali->irq, denali_isr,
+			       IRQF_SHARED, DENALI_NAND_NAME, denali);
+	if (ret) {
+		dev_err(denali->dev, "Unable to request IRQ\n");
+		return ret;
 	}
 
-	ret = nand_scan_tail(mtd);
+	denali_enable_irq(denali);
+	denali_reset_banks(denali);
+
+	denali->active_bank = DENALI_INVALID_BANK;
+
+	nand_set_flash_node(chip, denali->dev->of_node);
+	/* Fallback to the default name if DT did not give "label" property */
+	if (!mtd->name)
+		mtd->name = "denali-nand";
+
+	chip->select_chip = denali_select_chip;
+	chip->read_byte = denali_read_byte;
+	chip->write_byte = denali_write_byte;
+	chip->read_word = denali_read_word;
+	chip->cmd_ctrl = denali_cmd_ctrl;
+	chip->dev_ready = denali_dev_ready;
+	chip->waitfunc = denali_waitfunc;
+
+	if (features & FEATURES__INDEX_ADDR) {
+		denali->host_read = denali_indexed_read;
+		denali->host_write = denali_indexed_write;
+	} else {
+		denali->host_read = denali_direct_read;
+		denali->host_write = denali_direct_write;
+	}
+
+	/* clk rate info is needed for setup_data_interface */
+	if (denali->clk_rate && denali->clk_x_rate)
+		chip->setup_data_interface = denali_setup_data_interface;
+
+	chip->dummy_controller.ops = &denali_controller_ops;
+	ret = nand_scan(mtd, denali->max_banks);
 	if (ret)
-		goto free_buf;
+		goto disable_irq;
 
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(denali->dev, "Failed to register MTD: %d\n", ret);
 		goto cleanup_nand;
 	}
+
 	return 0;
 
 cleanup_nand:
 	nand_cleanup(chip);
-free_buf:
-	kfree(denali->buf);
 disable_irq:
 	denali_disable_irq(denali);
 
@@ -1404,7 +1393,6 @@ void denali_remove(struct denali_nand_info *denali)
 	struct mtd_info *mtd = nand_to_mtd(&denali->nand);
 
 	nand_release(mtd);
-	kfree(denali->buf);
 	denali_disable_irq(denali);
 }
 EXPORT_SYMBOL(denali_remove);
diff --git a/drivers/mtd/nand/raw/denali.h b/drivers/mtd/nand/raw/denali.h
index 9ad33d237378..1f8feaf924eb 100644
--- a/drivers/mtd/nand/raw/denali.h
+++ b/drivers/mtd/nand/raw/denali.h
@@ -300,6 +300,7 @@
 
 struct denali_nand_info {
 	struct nand_chip nand;
+	unsigned long clk_rate;		/* core clock rate */
 	unsigned long clk_x_rate;	/* bus interface clock rate */
 	int active_bank;		/* currently selected bank */
 	struct device *dev;
diff --git a/drivers/mtd/nand/raw/denali_dt.c b/drivers/mtd/nand/raw/denali_dt.c
index 5869e90cc14b..0faaad032e5f 100644
--- a/drivers/mtd/nand/raw/denali_dt.c
+++ b/drivers/mtd/nand/raw/denali_dt.c
@@ -27,7 +27,9 @@
 
 struct denali_dt {
 	struct denali_nand_info	denali;
-	struct clk		*clk;
+	struct clk *clk;	/* core clock */
+	struct clk *clk_x;	/* bus interface clock */
+	struct clk *clk_ecc;	/* ECC circuit clock */
 };
 
 struct denali_dt_data {
@@ -79,63 +81,99 @@ MODULE_DEVICE_TABLE(of, denali_nand_dt_ids);
 
 static int denali_dt_probe(struct platform_device *pdev)
 {
+	struct device *dev = &pdev->dev;
 	struct resource *res;
 	struct denali_dt *dt;
 	const struct denali_dt_data *data;
 	struct denali_nand_info *denali;
 	int ret;
 
-	dt = devm_kzalloc(&pdev->dev, sizeof(*dt), GFP_KERNEL);
+	dt = devm_kzalloc(dev, sizeof(*dt), GFP_KERNEL);
 	if (!dt)
 		return -ENOMEM;
 	denali = &dt->denali;
 
-	data = of_device_get_match_data(&pdev->dev);
+	data = of_device_get_match_data(dev);
 	if (data) {
 		denali->revision = data->revision;
 		denali->caps = data->caps;
 		denali->ecc_caps = data->ecc_caps;
 	}
 
-	denali->dev = &pdev->dev;
+	denali->dev = dev;
 	denali->irq = platform_get_irq(pdev, 0);
 	if (denali->irq < 0) {
-		dev_err(&pdev->dev, "no irq defined\n");
+		dev_err(dev, "no irq defined\n");
 		return denali->irq;
 	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "denali_reg");
-	denali->reg = devm_ioremap_resource(&pdev->dev, res);
+	denali->reg = devm_ioremap_resource(dev, res);
 	if (IS_ERR(denali->reg))
 		return PTR_ERR(denali->reg);
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand_data");
-	denali->host = devm_ioremap_resource(&pdev->dev, res);
+	denali->host = devm_ioremap_resource(dev, res);
 	if (IS_ERR(denali->host))
 		return PTR_ERR(denali->host);
 
-	dt->clk = devm_clk_get(&pdev->dev, NULL);
+	/*
+	 * A single anonymous clock is supported for the backward compatibility.
+	 * New platforms should support all the named clocks.
+	 */
+	dt->clk = devm_clk_get(dev, "nand");
+	if (IS_ERR(dt->clk))
+		dt->clk = devm_clk_get(dev, NULL);
 	if (IS_ERR(dt->clk)) {
-		dev_err(&pdev->dev, "no clk available\n");
+		dev_err(dev, "no clk available\n");
 		return PTR_ERR(dt->clk);
 	}
+
+	dt->clk_x = devm_clk_get(dev, "nand_x");
+	if (IS_ERR(dt->clk_x))
+		dt->clk_x = NULL;
+
+	dt->clk_ecc = devm_clk_get(dev, "ecc");
+	if (IS_ERR(dt->clk_ecc))
+		dt->clk_ecc = NULL;
+
 	ret = clk_prepare_enable(dt->clk);
 	if (ret)
 		return ret;
 
-	/*
-	 * Hardcode the clock rate for the backward compatibility.
-	 * This works for both SOCFPGA and UniPhier.
-	 */
-	denali->clk_x_rate = 200000000;
+	ret = clk_prepare_enable(dt->clk_x);
+	if (ret)
+		goto out_disable_clk;
+
+	ret = clk_prepare_enable(dt->clk_ecc);
+	if (ret)
+		goto out_disable_clk_x;
+
+	if (dt->clk_x) {
+		denali->clk_rate = clk_get_rate(dt->clk);
+		denali->clk_x_rate = clk_get_rate(dt->clk_x);
+	} else {
+		/*
+		 * Hardcode the clock rates for the backward compatibility.
+		 * This works for both SOCFPGA and UniPhier.
+		 */
+		dev_notice(dev,
+			   "necessary clock is missing. default clock rates are used.\n");
+		denali->clk_rate = 50000000;
+		denali->clk_x_rate = 200000000;
+	}
 
 	ret = denali_init(denali);
 	if (ret)
-		goto out_disable_clk;
+		goto out_disable_clk_ecc;
 
 	platform_set_drvdata(pdev, dt);
 	return 0;
 
+out_disable_clk_ecc:
+	clk_disable_unprepare(dt->clk_ecc);
+out_disable_clk_x:
+	clk_disable_unprepare(dt->clk_x);
 out_disable_clk:
 	clk_disable_unprepare(dt->clk);
 
@@ -147,6 +185,8 @@ static int denali_dt_remove(struct platform_device *pdev)
 	struct denali_dt *dt = platform_get_drvdata(pdev);
 
 	denali_remove(&dt->denali);
+	clk_disable_unprepare(dt->clk_ecc);
+	clk_disable_unprepare(dt->clk_x);
 	clk_disable_unprepare(dt->clk);
 
 	return 0;
diff --git a/drivers/mtd/nand/raw/denali_pci.c b/drivers/mtd/nand/raw/denali_pci.c
index 49cb3e1f8bd0..7c8efc4c7bdf 100644
--- a/drivers/mtd/nand/raw/denali_pci.c
+++ b/drivers/mtd/nand/raw/denali_pci.c
@@ -73,6 +73,7 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	denali->irq = dev->irq;
 	denali->ecc_caps = &denali_pci_ecc_caps;
 	denali->nand.ecc.options |= NAND_ECC_MAXIMIZE;
+	denali->clk_rate = 50000000;		/* 50 MHz */
 	denali->clk_x_rate = 200000000;		/* 200 MHz */
 
 	ret = pci_request_regions(dev, DENALI_NAND_NAME);
diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c
index 8d10061abb4b..3c46188dd6d2 100644
--- a/drivers/mtd/nand/raw/diskonchip.c
+++ b/drivers/mtd/nand/raw/diskonchip.c
@@ -1291,7 +1291,7 @@ static int __init nftl_scan_bbt(struct mtd_info *mtd)
 		this->bbt_md = NULL;
 	}
 
-	ret = this->scan_bbt(mtd);
+	ret = nand_create_bbt(this);
 	if (ret)
 		return ret;
 
@@ -1338,7 +1338,7 @@ static int __init inftl_scan_bbt(struct mtd_info *mtd)
 		this->bbt_md->pattern = "TBB_SYSM";
 	}
 
-	ret = this->scan_bbt(mtd);
+	ret = nand_create_bbt(this);
 	if (ret)
 		return ret;
 
diff --git a/drivers/mtd/nand/raw/docg4.c b/drivers/mtd/nand/raw/docg4.c
index 1314aa99b9ab..a3f04315c05c 100644
--- a/drivers/mtd/nand/raw/docg4.c
+++ b/drivers/mtd/nand/raw/docg4.c
@@ -1227,10 +1227,9 @@ static void __init init_mtd_structs(struct mtd_info *mtd)
 	 * required within a nand driver because they are performed by the nand
 	 * infrastructure code as part of nand_scan().  In this case they need
 	 * to be initialized here because we skip call to nand_scan_ident() (the
-	 * first half of nand_scan()).  The call to nand_scan_ident() is skipped
-	 * because for this device the chip id is not read in the manner of a
-	 * standard nand device.  Unfortunately, nand_scan_ident() does other
-	 * things as well, such as call nand_set_defaults().
+	 * first half of nand_scan()).  The call to nand_scan_ident() could be
+	 * skipped because for this device the chip id is not read in the manner
+	 * of a standard nand device.
 	 */
 
 	struct nand_chip *nand = mtd_to_nand(mtd);
@@ -1257,8 +1256,8 @@ static void __init init_mtd_structs(struct mtd_info *mtd)
 	nand->ecc.strength = DOCG4_T;
 	nand->options = NAND_BUSWIDTH_16 | NAND_NO_SUBPAGE_WRITE;
 	nand->IO_ADDR_R = nand->IO_ADDR_W = doc->virtadr + DOC_IOSPACE_DATA;
-	nand->controller = &nand->hwcontrol;
-	nand_hw_control_init(nand->controller);
+	nand->controller = &nand->dummy_controller;
+	nand_controller_init(nand->controller);
 
 	/* methods */
 	nand->cmdfunc = docg4_command;
@@ -1315,6 +1314,40 @@ static int __init read_id_reg(struct mtd_info *mtd)
 
 static char const *part_probes[] = { "cmdlinepart", "saftlpart", NULL };
 
+static int docg4_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct docg4_priv *doc = (struct docg4_priv *)(chip + 1);
+	int ret;
+
+	init_mtd_structs(mtd);
+
+	/* Initialize kernel BCH algorithm */
+	doc->bch = init_bch(DOCG4_M, DOCG4_T, DOCG4_PRIMITIVE_POLY);
+	if (!doc->bch)
+		return -EINVAL;
+
+	reset(mtd);
+
+	ret = read_id_reg(mtd);
+	if (ret)
+		free_bch(doc->bch);
+
+	return ret;
+}
+
+static void docg4_detach_chip(struct nand_chip *chip)
+{
+	struct docg4_priv *doc = (struct docg4_priv *)(chip + 1);
+
+	free_bch(doc->bch);
+}
+
+static const struct nand_controller_ops docg4_controller_ops = {
+	.attach_chip = docg4_attach_chip,
+	.detach_chip = docg4_detach_chip,
+};
+
 static int __init probe_docg4(struct platform_device *pdev)
 {
 	struct mtd_info *mtd;
@@ -1341,7 +1374,7 @@ static int __init probe_docg4(struct platform_device *pdev)
 	nand = kzalloc(len, GFP_KERNEL);
 	if (nand == NULL) {
 		retval = -ENOMEM;
-		goto fail_unmap;
+		goto unmap;
 	}
 
 	mtd = nand_to_mtd(nand);
@@ -1350,46 +1383,35 @@ static int __init probe_docg4(struct platform_device *pdev)
 	mtd->dev.parent = &pdev->dev;
 	doc->virtadr = virtadr;
 	doc->dev = dev;
-
-	init_mtd_structs(mtd);
-
-	/* initialize kernel bch algorithm */
-	doc->bch = init_bch(DOCG4_M, DOCG4_T, DOCG4_PRIMITIVE_POLY);
-	if (doc->bch == NULL) {
-		retval = -EINVAL;
-		goto fail;
-	}
-
 	platform_set_drvdata(pdev, doc);
 
-	reset(mtd);
-	retval = read_id_reg(mtd);
-	if (retval == -ENODEV) {
-		dev_warn(dev, "No diskonchip G4 device found.\n");
-		goto fail;
-	}
-
-	retval = nand_scan_tail(mtd);
+	/*
+	 * Running nand_scan() with maxchips == 0 will skip nand_scan_ident(),
+	 * which is a specific operation with this driver and done in the
+	 * ->attach_chip callback.
+	 */
+	nand->dummy_controller.ops = &docg4_controller_ops;
+	retval = nand_scan(mtd, 0);
 	if (retval)
-		goto fail;
+		goto free_nand;
 
 	retval = read_factory_bbt(mtd);
 	if (retval)
-		goto fail;
+		goto cleanup_nand;
 
 	retval = mtd_device_parse_register(mtd, part_probes, NULL, NULL, 0);
 	if (retval)
-		goto fail;
+		goto cleanup_nand;
 
 	doc->mtd = mtd;
+
 	return 0;
 
-fail:
-	nand_release(mtd); /* deletes partitions and mtd devices */
-	free_bch(doc->bch);
+cleanup_nand:
+	nand_cleanup(nand);
+free_nand:
 	kfree(nand);
-
-fail_unmap:
+unmap:
 	iounmap(virtadr);
 
 	return retval;
@@ -1399,7 +1421,6 @@ static int __exit cleanup_docg4(struct platform_device *pdev)
 {
 	struct docg4_priv *doc = platform_get_drvdata(pdev);
 	nand_release(doc->mtd);
-	free_bch(doc->bch);
 	kfree(mtd_to_nand(doc->mtd));
 	iounmap(doc->virtadr);
 	return 0;
diff --git a/drivers/mtd/nand/raw/fsl_elbc_nand.c b/drivers/mtd/nand/raw/fsl_elbc_nand.c
index 51f0b340bc0d..55f449b711fd 100644
--- a/drivers/mtd/nand/raw/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_elbc_nand.c
@@ -61,7 +61,7 @@ struct fsl_elbc_mtd {
 /* Freescale eLBC FCM controller information */
 
 struct fsl_elbc_fcm_ctrl {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct fsl_elbc_mtd *chips[MAX_BANKS];
 
 	u8 __iomem *addr;        /* Address of assigned FCM buffer        */
@@ -637,9 +637,9 @@ static int fsl_elbc_wait(struct mtd_info *mtd, struct nand_chip *chip)
 	return (elbc_fcm_ctrl->mdr & 0xff) | NAND_STATUS_WP;
 }
 
-static int fsl_elbc_chip_init_tail(struct mtd_info *mtd)
+static int fsl_elbc_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct fsl_elbc_mtd *priv = nand_get_controller_data(chip);
 	struct fsl_lbc_ctrl *ctrl = priv->ctrl;
 	struct fsl_lbc_regs __iomem *lbc = ctrl->regs;
@@ -700,12 +700,16 @@ static int fsl_elbc_chip_init_tail(struct mtd_info *mtd)
 		dev_err(priv->dev,
 		        "fsl_elbc_init: page size %d is not supported\n",
 		        mtd->writesize);
-		return -1;
+		return -ENOTSUPP;
 	}
 
 	return 0;
 }
 
+static const struct nand_controller_ops fsl_elbc_controller_ops = {
+	.attach_chip = fsl_elbc_attach_chip,
+};
+
 static int fsl_elbc_read_page(struct mtd_info *mtd, struct nand_chip *chip,
 			      uint8_t *buf, int oob_required, int page)
 {
@@ -879,7 +883,7 @@ static int fsl_elbc_nand_probe(struct platform_device *pdev)
 		}
 		elbc_fcm_ctrl->counter++;
 
-		nand_hw_control_init(&elbc_fcm_ctrl->controller);
+		nand_controller_init(&elbc_fcm_ctrl->controller);
 		fsl_lbc_ctrl_dev->nand = elbc_fcm_ctrl;
 	} else {
 		elbc_fcm_ctrl = fsl_lbc_ctrl_dev->nand;
@@ -910,15 +914,8 @@ static int fsl_elbc_nand_probe(struct platform_device *pdev)
 	if (ret)
 		goto err;
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		goto err;
-
-	ret = fsl_elbc_chip_init_tail(mtd);
-	if (ret)
-		goto err;
-
-	ret = nand_scan_tail(mtd);
+	priv->chip.controller->ops = &fsl_elbc_controller_ops;
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		goto err;
 
diff --git a/drivers/mtd/nand/raw/fsl_ifc_nand.c b/drivers/mtd/nand/raw/fsl_ifc_nand.c
index 382b67e97174..24f59d0066af 100644
--- a/drivers/mtd/nand/raw/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_ifc_nand.c
@@ -51,7 +51,7 @@ struct fsl_ifc_mtd {
 
 /* overview of the fsl ifc controller */
 struct fsl_ifc_nand_ctrl {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct fsl_ifc_mtd *chips[FSL_IFC_BANK_COUNT];
 
 	void __iomem *addr;	/* Address of assigned IFC buffer	*/
@@ -225,7 +225,7 @@ static void fsl_ifc_run_command(struct mtd_info *mtd)
 		int bufnum = nctrl->page & priv->bufnum_mask;
 		int sector_start = bufnum * chip->ecc.steps;
 		int sector_end = sector_start + chip->ecc.steps - 1;
-		__be32 *eccstat_regs;
+		__be32 __iomem *eccstat_regs;
 
 		eccstat_regs = ifc->ifc_nand.nand_eccstat;
 		eccstat = ifc_in32(&eccstat_regs[sector_start / 4]);
@@ -714,9 +714,9 @@ static int fsl_ifc_write_page(struct mtd_info *mtd, struct nand_chip *chip,
 	return nand_prog_page_end_op(chip);
 }
 
-static int fsl_ifc_chip_init_tail(struct mtd_info *mtd)
+static int fsl_ifc_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct fsl_ifc_mtd *priv = nand_get_controller_data(chip);
 
 	dev_dbg(priv->dev, "%s: nand->numchips = %d\n", __func__,
@@ -757,6 +757,10 @@ static int fsl_ifc_chip_init_tail(struct mtd_info *mtd)
 	return 0;
 }
 
+static const struct nand_controller_ops fsl_ifc_controller_ops = {
+	.attach_chip = fsl_ifc_attach_chip,
+};
+
 static void fsl_ifc_sram_init(struct fsl_ifc_mtd *priv)
 {
 	struct fsl_ifc_ctrl *ctrl = priv->ctrl;
@@ -1004,7 +1008,7 @@ static int fsl_ifc_nand_probe(struct platform_device *dev)
 		ifc_nand_ctrl->addr = NULL;
 		fsl_ifc_ctrl_dev->nand = ifc_nand_ctrl;
 
-		nand_hw_control_init(&ifc_nand_ctrl->controller);
+		nand_controller_init(&ifc_nand_ctrl->controller);
 	} else {
 		ifc_nand_ctrl = fsl_ifc_ctrl_dev->nand;
 	}
@@ -1046,15 +1050,8 @@ static int fsl_ifc_nand_probe(struct platform_device *dev)
 	if (ret)
 		goto err;
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		goto err;
-
-	ret = fsl_ifc_chip_init_tail(mtd);
-	if (ret)
-		goto err;
-
-	ret = nand_scan_tail(mtd);
+	priv->chip.controller->ops = &fsl_ifc_controller_ops;
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		goto err;
 
diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c
index f4a5a317d4ae..f418236fa020 100644
--- a/drivers/mtd/nand/raw/fsmc_nand.c
+++ b/drivers/mtd/nand/raw/fsmc_nand.c
@@ -62,7 +62,7 @@
 						reg)
 
 /* fsmc controller registers for NAND flash */
-#define PC			0x00
+#define FSMC_PC			0x00
 	/* pc register definitions */
 	#define FSMC_RESET		(1 << 0)
 	#define FSMC_WAITON		(1 << 1)
@@ -273,12 +273,13 @@ static void fsmc_nand_setup(struct fsmc_nand_data *host,
 	tset = (tims->tset & FSMC_TSET_MASK) << FSMC_TSET_SHIFT;
 
 	if (host->nand.options & NAND_BUSWIDTH_16)
-		writel_relaxed(value | FSMC_DEVWID_16, host->regs_va + PC);
+		writel_relaxed(value | FSMC_DEVWID_16,
+			       host->regs_va + FSMC_PC);
 	else
-		writel_relaxed(value | FSMC_DEVWID_8, host->regs_va + PC);
+		writel_relaxed(value | FSMC_DEVWID_8, host->regs_va + FSMC_PC);
 
-	writel_relaxed(readl(host->regs_va + PC) | tclr | tar,
-		       host->regs_va + PC);
+	writel_relaxed(readl(host->regs_va + FSMC_PC) | tclr | tar,
+		       host->regs_va + FSMC_PC);
 	writel_relaxed(thiz | thold | twait | tset, host->regs_va + COMM);
 	writel_relaxed(thiz | thold | twait | tset, host->regs_va + ATTRIB);
 }
@@ -371,12 +372,12 @@ static void fsmc_enable_hwecc(struct mtd_info *mtd, int mode)
 {
 	struct fsmc_nand_data *host = mtd_to_fsmc(mtd);
 
-	writel_relaxed(readl(host->regs_va + PC) & ~FSMC_ECCPLEN_256,
-		       host->regs_va + PC);
-	writel_relaxed(readl(host->regs_va + PC) & ~FSMC_ECCEN,
-		       host->regs_va + PC);
-	writel_relaxed(readl(host->regs_va + PC) | FSMC_ECCEN,
-		       host->regs_va + PC);
+	writel_relaxed(readl(host->regs_va + FSMC_PC) & ~FSMC_ECCPLEN_256,
+		       host->regs_va + FSMC_PC);
+	writel_relaxed(readl(host->regs_va + FSMC_PC) & ~FSMC_ECCEN,
+		       host->regs_va + FSMC_PC);
+	writel_relaxed(readl(host->regs_va + FSMC_PC) | FSMC_ECCEN,
+		       host->regs_va + FSMC_PC);
 }
 
 /*
@@ -546,7 +547,7 @@ static void fsmc_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len)
 	struct fsmc_nand_data *host  = mtd_to_fsmc(mtd);
 	int i;
 
-	if (IS_ALIGNED((uint32_t)buf, sizeof(uint32_t)) &&
+	if (IS_ALIGNED((uintptr_t)buf, sizeof(uint32_t)) &&
 			IS_ALIGNED(len, sizeof(uint32_t))) {
 		uint32_t *p = (uint32_t *)buf;
 		len = len >> 2;
@@ -569,7 +570,7 @@ static void fsmc_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 	struct fsmc_nand_data *host  = mtd_to_fsmc(mtd);
 	int i;
 
-	if (IS_ALIGNED((uint32_t)buf, sizeof(uint32_t)) &&
+	if (IS_ALIGNED((uintptr_t)buf, sizeof(uint32_t)) &&
 			IS_ALIGNED(len, sizeof(uint32_t))) {
 		uint32_t *p = (uint32_t *)buf;
 		len = len >> 2;
@@ -618,11 +619,11 @@ static void fsmc_select_chip(struct mtd_info *mtd, int chipnr)
 	if (chipnr > 0)
 		return;
 
-	pc = readl(host->regs_va + PC);
+	pc = readl(host->regs_va + FSMC_PC);
 	if (chipnr < 0)
-		writel_relaxed(pc & ~FSMC_ENABLE, host->regs_va + PC);
+		writel_relaxed(pc & ~FSMC_ENABLE, host->regs_va + FSMC_PC);
 	else
-		writel_relaxed(pc | FSMC_ENABLE, host->regs_va + PC);
+		writel_relaxed(pc | FSMC_ENABLE, host->regs_va + FSMC_PC);
 
 	/* nCE line must be asserted before starting any operation */
 	mb();
@@ -740,7 +741,7 @@ static int fsmc_read_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip,
 	for (i = 0, s = 0; s < eccsteps; s++, i += eccbytes, p += eccsize) {
 		nand_read_page_op(chip, page, s * eccsize, NULL, 0);
 		chip->ecc.hwctl(mtd, NAND_ECC_READ);
-		chip->read_buf(mtd, p, eccsize);
+		nand_read_data_op(chip, p, eccsize, false);
 
 		for (j = 0; j < eccbytes;) {
 			struct mtd_oob_region oobregion;
@@ -918,6 +919,82 @@ static int fsmc_nand_probe_config_dt(struct platform_device *pdev,
 	return 0;
 }
 
+static int fsmc_nand_attach_chip(struct nand_chip *nand)
+{
+	struct mtd_info *mtd = nand_to_mtd(nand);
+	struct fsmc_nand_data *host = mtd_to_fsmc(mtd);
+
+	if (AMBA_REV_BITS(host->pid) >= 8) {
+		switch (mtd->oobsize) {
+		case 16:
+		case 64:
+		case 128:
+		case 224:
+		case 256:
+			break;
+		default:
+			dev_warn(host->dev,
+				 "No oob scheme defined for oobsize %d\n",
+				 mtd->oobsize);
+			return -EINVAL;
+		}
+
+		mtd_set_ooblayout(mtd, &fsmc_ecc4_ooblayout_ops);
+
+		return 0;
+	}
+
+	switch (nand->ecc.mode) {
+	case NAND_ECC_HW:
+		dev_info(host->dev, "Using 1-bit HW ECC scheme\n");
+		nand->ecc.calculate = fsmc_read_hwecc_ecc1;
+		nand->ecc.correct = nand_correct_data;
+		nand->ecc.bytes = 3;
+		nand->ecc.strength = 1;
+		break;
+
+	case NAND_ECC_SOFT:
+		if (nand->ecc.algo == NAND_ECC_BCH) {
+			dev_info(host->dev,
+				 "Using 4-bit SW BCH ECC scheme\n");
+			break;
+		}
+
+	case NAND_ECC_ON_DIE:
+		break;
+
+	default:
+		dev_err(host->dev, "Unsupported ECC mode!\n");
+		return -ENOTSUPP;
+	}
+
+	/*
+	 * Don't set layout for BCH4 SW ECC. This will be
+	 * generated later in nand_bch_init() later.
+	 */
+	if (nand->ecc.mode == NAND_ECC_HW) {
+		switch (mtd->oobsize) {
+		case 16:
+		case 64:
+		case 128:
+			mtd_set_ooblayout(mtd,
+					  &fsmc_ecc1_ooblayout_ops);
+			break;
+		default:
+			dev_warn(host->dev,
+				 "No oob scheme defined for oobsize %d\n",
+				 mtd->oobsize);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops fsmc_nand_controller_ops = {
+	.attach_chip = fsmc_nand_attach_chip,
+};
+
 /*
  * fsmc_nand_probe - Probe function
  * @pdev:       platform device structure
@@ -1047,76 +1124,8 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
 	/*
 	 * Scan to find existence of the device
 	 */
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret) {
-		dev_err(&pdev->dev, "No NAND Device found!\n");
-		goto release_dma_write_chan;
-	}
-
-	if (AMBA_REV_BITS(host->pid) >= 8) {
-		switch (mtd->oobsize) {
-		case 16:
-		case 64:
-		case 128:
-		case 224:
-		case 256:
-			break;
-		default:
-			dev_warn(&pdev->dev, "No oob scheme defined for oobsize %d\n",
-				 mtd->oobsize);
-			ret = -EINVAL;
-			goto release_dma_write_chan;
-		}
-
-		mtd_set_ooblayout(mtd, &fsmc_ecc4_ooblayout_ops);
-	} else {
-		switch (nand->ecc.mode) {
-		case NAND_ECC_HW:
-			dev_info(&pdev->dev, "Using 1-bit HW ECC scheme\n");
-			nand->ecc.calculate = fsmc_read_hwecc_ecc1;
-			nand->ecc.correct = nand_correct_data;
-			nand->ecc.bytes = 3;
-			nand->ecc.strength = 1;
-			break;
-
-		case NAND_ECC_SOFT:
-			if (nand->ecc.algo == NAND_ECC_BCH) {
-				dev_info(&pdev->dev, "Using 4-bit SW BCH ECC scheme\n");
-				break;
-			}
-
-		case NAND_ECC_ON_DIE:
-			break;
-
-		default:
-			dev_err(&pdev->dev, "Unsupported ECC mode!\n");
-			goto release_dma_write_chan;
-		}
-
-		/*
-		 * Don't set layout for BCH4 SW ECC. This will be
-		 * generated later in nand_bch_init() later.
-		 */
-		if (nand->ecc.mode == NAND_ECC_HW) {
-			switch (mtd->oobsize) {
-			case 16:
-			case 64:
-			case 128:
-				mtd_set_ooblayout(mtd,
-						  &fsmc_ecc1_ooblayout_ops);
-				break;
-			default:
-				dev_warn(&pdev->dev,
-					 "No oob scheme defined for oobsize %d\n",
-					 mtd->oobsize);
-				ret = -EINVAL;
-				goto release_dma_write_chan;
-			}
-		}
-	}
-
-	/* Second stage of scan to fill MTD data-structures */
-	ret = nand_scan_tail(mtd);
+	nand->dummy_controller.ops = &fsmc_nand_controller_ops;
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		goto release_dma_write_chan;
 
diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c
index 83697b8df871..88ea2203e263 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Freescale GPMI NAND Flash Driver
  *
  * Copyright (C) 2008-2011 Freescale Semiconductor, Inc.
  * Copyright (C) 2008 Embedded Alley Solutions, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 #include <linux/delay.h>
 #include <linux/clk.h>
diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
index f6aa358a3452..1c1ebbc82824 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Freescale GPMI NAND Flash Driver
  *
  * Copyright (C) 2010-2015 Freescale Semiconductor, Inc.
  * Copyright (C) 2008 Embedded Alley Solutions, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 #include <linux/clk.h>
 #include <linux/slab.h>
@@ -757,9 +744,9 @@ static int gpmi_alloc_dma_buffer(struct gpmi_nand_data *this)
 	 * [2] Allocate a read/write data buffer.
 	 *     The gpmi_alloc_dma_buffer can be called twice.
 	 *     We allocate a PAGE_SIZE length buffer if gpmi_alloc_dma_buffer
-	 *     is called before the nand_scan_ident; and we allocate a buffer
-	 *     of the real NAND page size when the gpmi_alloc_dma_buffer is
-	 *     called after the nand_scan_ident.
+	 *     is called before the NAND identification; and we allocate a
+	 *     buffer of the real NAND page size when the gpmi_alloc_dma_buffer
+	 *     is called after.
 	 */
 	this->data_buffer_dma = kzalloc(mtd->writesize ?: PAGE_SIZE,
 					GFP_DMA | GFP_KERNEL);
@@ -957,7 +944,6 @@ static int gpmi_ecc_read_page_data(struct nand_chip *chip,
 	struct gpmi_nand_data *this = nand_get_controller_data(chip);
 	struct bch_geometry *nfc_geo = &this->bch_geometry;
 	struct mtd_info *mtd = nand_to_mtd(chip);
-	void          *payload_virt;
 	dma_addr_t    payload_phys;
 	unsigned int  i;
 	unsigned char *status;
@@ -967,7 +953,6 @@ static int gpmi_ecc_read_page_data(struct nand_chip *chip,
 
 	dev_dbg(this->dev, "page number is : %d\n", page);
 
-	payload_virt = this->payload_virt;
 	payload_phys = this->payload_phys;
 
 	if (virt_addr_valid(buf)) {
@@ -976,7 +961,6 @@ static int gpmi_ecc_read_page_data(struct nand_chip *chip,
 		dest_phys = dma_map_single(this->dev, buf, nfc_geo->payload_size,
 					   DMA_FROM_DEVICE);
 		if (!dma_mapping_error(this->dev, dest_phys)) {
-			payload_virt = buf;
 			payload_phys = dest_phys;
 			direct = true;
 		}
@@ -1881,6 +1865,34 @@ static int gpmi_init_last(struct gpmi_nand_data *this)
 	return 0;
 }
 
+static int gpmi_nand_attach_chip(struct nand_chip *chip)
+{
+	struct gpmi_nand_data *this = nand_get_controller_data(chip);
+	int ret;
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+		if (of_property_read_bool(this->dev->of_node,
+					  "fsl,no-blockmark-swap"))
+			this->swap_block_mark = false;
+	}
+	dev_dbg(this->dev, "Blockmark swapping %sabled\n",
+		this->swap_block_mark ? "en" : "dis");
+
+	ret = gpmi_init_last(this);
+	if (ret)
+		return ret;
+
+	chip->options |= NAND_SKIP_BBTSCAN;
+
+	return 0;
+}
+
+static const struct nand_controller_ops gpmi_nand_controller_ops = {
+	.attach_chip = gpmi_nand_attach_chip,
+};
+
 static int gpmi_nand_init(struct gpmi_nand_data *this)
 {
 	struct nand_chip *chip = &this->nand;
@@ -1921,33 +1933,15 @@ static int gpmi_nand_init(struct gpmi_nand_data *this)
 	if (ret)
 		goto err_out;
 
-	ret = nand_scan_ident(mtd, GPMI_IS_MX6(this) ? 2 : 1, NULL);
-	if (ret)
-		goto err_out;
-
-	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
-		chip->bbt_options |= NAND_BBT_NO_OOB;
-
-		if (of_property_read_bool(this->dev->of_node,
-						"fsl,no-blockmark-swap"))
-			this->swap_block_mark = false;
-	}
-	dev_dbg(this->dev, "Blockmark swapping %sabled\n",
-		this->swap_block_mark ? "en" : "dis");
-
-	ret = gpmi_init_last(this);
-	if (ret)
-		goto err_out;
-
-	chip->options |= NAND_SKIP_BBTSCAN;
-	ret = nand_scan_tail(mtd);
+	chip->dummy_controller.ops = &gpmi_nand_controller_ops;
+	ret = nand_scan(mtd, GPMI_IS_MX6(this) ? 2 : 1);
 	if (ret)
 		goto err_out;
 
 	ret = nand_boot_init(this);
 	if (ret)
 		goto err_nand_cleanup;
-	ret = chip->scan_bbt(mtd);
+	ret = nand_create_bbt(chip);
 	if (ret)
 		goto err_nand_cleanup;
 
diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h
index 6aa10d6962d6..69cd0cbde4f2 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h
@@ -1,18 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * Freescale GPMI NAND Flash Driver
  *
  * Copyright (C) 2010-2011 Freescale Semiconductor, Inc.
  * Copyright (C) 2008 Embedded Alley Solutions, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #ifndef __DRIVERS_MTD_NAND_GPMI_NAND_H
 #define __DRIVERS_MTD_NAND_GPMI_NAND_H
diff --git a/drivers/mtd/nand/raw/hisi504_nand.c b/drivers/mtd/nand/raw/hisi504_nand.c
index a1e009c8e556..950dc7789296 100644
--- a/drivers/mtd/nand/raw/hisi504_nand.c
+++ b/drivers/mtd/nand/raw/hisi504_nand.c
@@ -709,9 +709,50 @@ static int hisi_nfc_ecc_probe(struct hinfc_host *host)
 	return 0;
 }
 
+static int hisi_nfc_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct hinfc_host *host = nand_get_controller_data(chip);
+	int flag;
+
+	host->buffer = dmam_alloc_coherent(host->dev,
+					   mtd->writesize + mtd->oobsize,
+					   &host->dma_buffer, GFP_KERNEL);
+	if (!host->buffer)
+		return -ENOMEM;
+
+	host->dma_oob = host->dma_buffer + mtd->writesize;
+	memset(host->buffer, 0xff, mtd->writesize + mtd->oobsize);
+
+	flag = hinfc_read(host, HINFC504_CON);
+	flag &= ~(HINFC504_CON_PAGESIZE_MASK << HINFC504_CON_PAGEISZE_SHIFT);
+	switch (mtd->writesize) {
+	case 2048:
+		flag |= (0x001 << HINFC504_CON_PAGEISZE_SHIFT);
+		break;
+	/*
+	 * TODO: add more pagesize support,
+	 * default pagesize has been set in hisi_nfc_host_init
+	 */
+	default:
+		dev_err(host->dev, "NON-2KB page size nand flash\n");
+		return -EINVAL;
+	}
+	hinfc_write(host, flag, HINFC504_CON);
+
+	if (chip->ecc.mode == NAND_ECC_HW)
+		hisi_nfc_ecc_probe(host);
+
+	return 0;
+}
+
+static const struct nand_controller_ops hisi_nfc_controller_ops = {
+	.attach_chip = hisi_nfc_attach_chip,
+};
+
 static int hisi_nfc_probe(struct platform_device *pdev)
 {
-	int ret = 0, irq, flag, max_chips = HINFC504_MAX_CHIP;
+	int ret = 0, irq, max_chips = HINFC504_MAX_CHIP;
 	struct device *dev = &pdev->dev;
 	struct hinfc_host *host;
 	struct nand_chip  *chip;
@@ -769,42 +810,11 @@ static int hisi_nfc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = nand_scan_ident(mtd, max_chips, NULL);
+	chip->dummy_controller.ops = &hisi_nfc_controller_ops;
+	ret = nand_scan(mtd, max_chips);
 	if (ret)
 		return ret;
 
-	host->buffer = dmam_alloc_coherent(dev, mtd->writesize + mtd->oobsize,
-		&host->dma_buffer, GFP_KERNEL);
-	if (!host->buffer)
-		return -ENOMEM;
-
-	host->dma_oob = host->dma_buffer + mtd->writesize;
-	memset(host->buffer, 0xff, mtd->writesize + mtd->oobsize);
-
-	flag = hinfc_read(host, HINFC504_CON);
-	flag &= ~(HINFC504_CON_PAGESIZE_MASK << HINFC504_CON_PAGEISZE_SHIFT);
-	switch (mtd->writesize) {
-	case 2048:
-		flag |= (0x001 << HINFC504_CON_PAGEISZE_SHIFT); break;
-	/*
-	 * TODO: add more pagesize support,
-	 * default pagesize has been set in hisi_nfc_host_init
-	 */
-	default:
-		dev_err(dev, "NON-2KB page size nand flash\n");
-		return -EINVAL;
-	}
-	hinfc_write(host, flag, HINFC504_CON);
-
-	if (chip->ecc.mode == NAND_ECC_HW)
-		hisi_nfc_ecc_probe(host);
-
-	ret = nand_scan_tail(mtd);
-	if (ret) {
-		dev_err(dev, "nand_scan_tail failed: %d\n", ret);
-		return ret;
-	}
-
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(dev, "Err MTD partition=%d\n", ret);
diff --git a/drivers/mtd/nand/raw/jz4740_nand.c b/drivers/mtd/nand/raw/jz4740_nand.c
index 613b00a9604b..a7515452bc59 100644
--- a/drivers/mtd/nand/raw/jz4740_nand.c
+++ b/drivers/mtd/nand/raw/jz4740_nand.c
@@ -13,6 +13,7 @@
  *
  */
 
+#include <linux/io.h>
 #include <linux/ioport.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -23,9 +24,9 @@
 #include <linux/mtd/rawnand.h>
 #include <linux/mtd/partitions.h>
 
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 
-#include <asm/mach-jz4740/jz4740_nand.h>
+#include <linux/platform_data/jz4740/jz4740_nand.h>
 
 #define JZ_REG_NAND_CTRL	0x50
 #define JZ_REG_NAND_ECC_CTRL	0x100
@@ -330,7 +331,7 @@ static int jz_nand_detect_bank(struct platform_device *pdev,
 
 	if (chipnr == 0) {
 		/* Detect first chip. */
-		ret = nand_scan_ident(mtd, 1, NULL);
+		ret = nand_scan(mtd, 1);
 		if (ret)
 			goto notfound_id;
 
@@ -355,7 +356,7 @@ static int jz_nand_detect_bank(struct platform_device *pdev,
 		mtd->size += chip->chipsize;
 	}
 
-	dev_info(&pdev->dev, "Found chip %i on bank %i\n", chipnr, bank);
+	dev_info(&pdev->dev, "Found chip %zu on bank %i\n", chipnr, bank);
 	return 0;
 
 notfound_id:
@@ -367,6 +368,24 @@ notfound_id:
 	return ret;
 }
 
+static int jz_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct device *dev = mtd->dev.parent;
+	struct jz_nand_platform_data *pdata = dev_get_platdata(dev);
+	struct platform_device *pdev = to_platform_device(dev);
+
+	if (pdata && pdata->ident_callback)
+		pdata->ident_callback(pdev, mtd, &pdata->partitions,
+				      &pdata->num_partitions);
+
+	return 0;
+}
+
+static const struct nand_controller_ops jz_nand_controller_ops = {
+	.attach_chip = jz_nand_attach_chip,
+};
+
 static int jz_nand_probe(struct platform_device *pdev)
 {
 	int ret;
@@ -410,6 +429,7 @@ static int jz_nand_probe(struct platform_device *pdev)
 	chip->chip_delay = 50;
 	chip->cmd_ctrl = jz_nand_cmd_ctrl;
 	chip->select_chip = jz_nand_select_chip;
+	chip->dummy_controller.ops = &jz_nand_controller_ops;
 
 	if (nand->busy_gpio)
 		chip->dev_ready = jz_nand_dev_ready;
@@ -455,33 +475,20 @@ static int jz_nand_probe(struct platform_device *pdev)
 		goto err_iounmap_mmio;
 	}
 
-	if (pdata && pdata->ident_callback) {
-		pdata->ident_callback(pdev, mtd, &pdata->partitions,
-					&pdata->num_partitions);
-	}
-
-	ret = nand_scan_tail(mtd);
-	if (ret) {
-		dev_err(&pdev->dev,  "Failed to scan NAND\n");
-		goto err_unclaim_banks;
-	}
-
-	ret = mtd_device_parse_register(mtd, NULL, NULL,
-					pdata ? pdata->partitions : NULL,
-					pdata ? pdata->num_partitions : 0);
+	ret = mtd_device_register(mtd, pdata ? pdata->partitions : NULL,
+				  pdata ? pdata->num_partitions : 0);
 
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to add mtd device\n");
-		goto err_nand_release;
+		goto err_cleanup_nand;
 	}
 
 	dev_info(&pdev->dev, "Successfully registered JZ4740 NAND driver\n");
 
 	return 0;
 
-err_nand_release:
-	nand_release(mtd);
-err_unclaim_banks:
+err_cleanup_nand:
+	nand_cleanup(chip);
 	while (chipnr--) {
 		unsigned char bank = nand->banks[chipnr];
 		jz_nand_iounmap_resource(nand->bank_mem[bank - 1],
diff --git a/drivers/mtd/nand/raw/jz4780_nand.c b/drivers/mtd/nand/raw/jz4780_nand.c
index e69f6ae4c539..db4fa60bd52a 100644
--- a/drivers/mtd/nand/raw/jz4780_nand.c
+++ b/drivers/mtd/nand/raw/jz4780_nand.c
@@ -44,7 +44,7 @@ struct jz4780_nand_cs {
 struct jz4780_nand_controller {
 	struct device *dev;
 	struct jz4780_bch *bch;
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	unsigned int num_banks;
 	struct list_head chips;
 	int selected;
@@ -65,7 +65,8 @@ static inline struct jz4780_nand_chip *to_jz4780_nand_chip(struct mtd_info *mtd)
 	return container_of(mtd_to_nand(mtd), struct jz4780_nand_chip, chip);
 }
 
-static inline struct jz4780_nand_controller *to_jz4780_nand_controller(struct nand_hw_control *ctrl)
+static inline struct jz4780_nand_controller
+*to_jz4780_nand_controller(struct nand_controller *ctrl)
 {
 	return container_of(ctrl, struct jz4780_nand_controller, controller);
 }
@@ -157,9 +158,8 @@ static int jz4780_nand_ecc_correct(struct mtd_info *mtd, u8 *dat,
 	return jz4780_bch_correct(nfc->bch, &params, dat, read_ecc);
 }
 
-static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *dev)
+static int jz4780_nand_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &nand->chip;
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct jz4780_nand_controller *nfc = to_jz4780_nand_controller(chip->controller);
 	int eccbytes;
@@ -170,7 +170,8 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
 	switch (chip->ecc.mode) {
 	case NAND_ECC_HW:
 		if (!nfc->bch) {
-			dev_err(dev, "HW BCH selected, but BCH controller not found\n");
+			dev_err(nfc->dev,
+				"HW BCH selected, but BCH controller not found\n");
 			return -ENODEV;
 		}
 
@@ -179,15 +180,16 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
 		chip->ecc.correct = jz4780_nand_ecc_correct;
 		/* fall through */
 	case NAND_ECC_SOFT:
-		dev_info(dev, "using %s (strength %d, size %d, bytes %d)\n",
-			(nfc->bch) ? "hardware BCH" : "software ECC",
-			chip->ecc.strength, chip->ecc.size, chip->ecc.bytes);
+		dev_info(nfc->dev, "using %s (strength %d, size %d, bytes %d)\n",
+			 (nfc->bch) ? "hardware BCH" : "software ECC",
+			 chip->ecc.strength, chip->ecc.size, chip->ecc.bytes);
 		break;
 	case NAND_ECC_NONE:
-		dev_info(dev, "not using ECC\n");
+		dev_info(nfc->dev, "not using ECC\n");
 		break;
 	default:
-		dev_err(dev, "ECC mode %d not supported\n", chip->ecc.mode);
+		dev_err(nfc->dev, "ECC mode %d not supported\n",
+			chip->ecc.mode);
 		return -EINVAL;
 	}
 
@@ -199,7 +201,7 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
 	eccbytes = mtd->writesize / chip->ecc.size * chip->ecc.bytes;
 
 	if (eccbytes > mtd->oobsize - 2) {
-		dev_err(dev,
+		dev_err(nfc->dev,
 			"invalid ECC config: required %d ECC bytes, but only %d are available",
 			eccbytes, mtd->oobsize - 2);
 		return -EINVAL;
@@ -210,6 +212,10 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
 	return 0;
 }
 
+static const struct nand_controller_ops jz4780_nand_controller_ops = {
+	.attach_chip = jz4780_nand_attach_chip,
+};
+
 static int jz4780_nand_init_chip(struct platform_device *pdev,
 				struct jz4780_nand_controller *nfc,
 				struct device_node *np,
@@ -279,15 +285,8 @@ static int jz4780_nand_init_chip(struct platform_device *pdev,
 	chip->controller = &nfc->controller;
 	nand_set_flash_node(chip, np);
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		return ret;
-
-	ret = jz4780_nand_init_ecc(nand, dev);
-	if (ret)
-		return ret;
-
-	ret = nand_scan_tail(mtd);
+	chip->controller->ops = &jz4780_nand_controller_ops;
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		return ret;
 
@@ -368,7 +367,7 @@ static int jz4780_nand_probe(struct platform_device *pdev)
 	nfc->dev = dev;
 	nfc->num_banks = num_banks;
 
-	nand_hw_control_init(&nfc->controller);
+	nand_controller_init(&nfc->controller);
 	INIT_LIST_HEAD(&nfc->chips);
 
 	ret = jz4780_nand_init_chips(nfc, pdev);
diff --git a/drivers/mtd/nand/raw/lpc32xx_mlc.c b/drivers/mtd/nand/raw/lpc32xx_mlc.c
index 052d123a8304..e82abada130a 100644
--- a/drivers/mtd/nand/raw/lpc32xx_mlc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_mlc.c
@@ -184,6 +184,7 @@ static struct nand_bbt_descr lpc32xx_nand_bbt_mirror = {
 };
 
 struct lpc32xx_nand_host {
+	struct platform_device	*pdev;
 	struct nand_chip	nand_chip;
 	struct lpc32xx_mlc_platform_data *pdata;
 	struct clk		*clk;
@@ -653,6 +654,32 @@ static struct lpc32xx_nand_cfg_mlc *lpc32xx_parse_dt(struct device *dev)
 	return ncfg;
 }
 
+static int lpc32xx_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct lpc32xx_nand_host *host = nand_get_controller_data(chip);
+	struct device *dev = &host->pdev->dev;
+
+	host->dma_buf = devm_kzalloc(dev, mtd->writesize, GFP_KERNEL);
+	if (!host->dma_buf)
+		return -ENOMEM;
+
+	host->dummy_buf = devm_kzalloc(dev, mtd->writesize, GFP_KERNEL);
+	if (!host->dummy_buf)
+		return -ENOMEM;
+
+	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.size = 512;
+	mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
+	host->mlcsubpages = mtd->writesize / 512;
+
+	return 0;
+}
+
+static const struct nand_controller_ops lpc32xx_nand_controller_ops = {
+	.attach_chip = lpc32xx_nand_attach_chip,
+};
+
 /*
  * Probe for NAND controller
  */
@@ -669,6 +696,8 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	if (!host)
 		return -ENOMEM;
 
+	host->pdev = pdev;
+
 	rc = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	host->io_base = devm_ioremap_resource(&pdev->dev, rc);
 	if (IS_ERR(host->io_base))
@@ -748,31 +777,6 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 		}
 	}
 
-	/*
-	 * Scan to find existance of the device and
-	 * Get the type of NAND device SMALL block or LARGE block
-	 */
-	res = nand_scan_ident(mtd, 1, NULL);
-	if (res)
-		goto release_dma_chan;
-
-	host->dma_buf = devm_kzalloc(&pdev->dev, mtd->writesize, GFP_KERNEL);
-	if (!host->dma_buf) {
-		res = -ENOMEM;
-		goto release_dma_chan;
-	}
-
-	host->dummy_buf = devm_kzalloc(&pdev->dev, mtd->writesize, GFP_KERNEL);
-	if (!host->dummy_buf) {
-		res = -ENOMEM;
-		goto release_dma_chan;
-	}
-
-	nand_chip->ecc.mode = NAND_ECC_HW;
-	nand_chip->ecc.size = 512;
-	mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
-	host->mlcsubpages = mtd->writesize / 512;
-
 	/* initially clear interrupt status */
 	readb(MLC_IRQ_SR(host->io_base));
 
@@ -794,10 +798,11 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	}
 
 	/*
-	 * Fills out all the uninitialized function pointers with the defaults
-	 * And scans for a bad block table if appropriate.
+	 * Scan to find existence of the device and get the type of NAND device:
+	 * SMALL block or LARGE block.
 	 */
-	res = nand_scan_tail(mtd);
+	nand_chip->dummy_controller.ops = &lpc32xx_nand_controller_ops;
+	res = nand_scan(mtd, 1);
 	if (res)
 		goto free_irq;
 
diff --git a/drivers/mtd/nand/raw/lpc32xx_slc.c b/drivers/mtd/nand/raw/lpc32xx_slc.c
index 42820aa1abab..a4e8b7e75135 100644
--- a/drivers/mtd/nand/raw/lpc32xx_slc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_slc.c
@@ -779,6 +779,46 @@ static struct lpc32xx_nand_cfg_slc *lpc32xx_parse_dt(struct device *dev)
 	return ncfg;
 }
 
+static int lpc32xx_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct lpc32xx_nand_host *host = nand_get_controller_data(chip);
+
+	/* OOB and ECC CPU and DMA work areas */
+	host->ecc_buf = (uint32_t *)(host->data_buf + LPC32XX_DMA_DATA_SIZE);
+
+	/*
+	 * Small page FLASH has a unique OOB layout, but large and huge
+	 * page FLASH use the standard layout. Small page FLASH uses a
+	 * custom BBT marker layout.
+	 */
+	if (mtd->writesize <= 512)
+		mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
+
+	/* These sizes remain the same regardless of page size */
+	chip->ecc.size = 256;
+	chip->ecc.bytes = LPC32XX_SLC_DEV_ECC_BYTES;
+	chip->ecc.prepad = 0;
+	chip->ecc.postpad = 0;
+
+	/*
+	 * Use a custom BBT marker setup for small page FLASH that
+	 * won't interfere with the ECC layout. Large and huge page
+	 * FLASH use the standard layout.
+	 */
+	if ((chip->bbt_options & NAND_BBT_USE_FLASH) &&
+	    mtd->writesize <= 512) {
+		chip->bbt_td = &bbt_smallpage_main_descr;
+		chip->bbt_md = &bbt_smallpage_mirror_descr;
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops lpc32xx_nand_controller_ops = {
+	.attach_chip = lpc32xx_nand_attach_chip,
+};
+
 /*
  * Probe for NAND controller
  */
@@ -884,41 +924,8 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	}
 
 	/* Find NAND device */
-	res = nand_scan_ident(mtd, 1, NULL);
-	if (res)
-		goto release_dma;
-
-	/* OOB and ECC CPU and DMA work areas */
-	host->ecc_buf = (uint32_t *)(host->data_buf + LPC32XX_DMA_DATA_SIZE);
-
-	/*
-	 * Small page FLASH has a unique OOB layout, but large and huge
-	 * page FLASH use the standard layout. Small page FLASH uses a
-	 * custom BBT marker layout.
-	 */
-	if (mtd->writesize <= 512)
-		mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
-
-	/* These sizes remain the same regardless of page size */
-	chip->ecc.size = 256;
-	chip->ecc.bytes = LPC32XX_SLC_DEV_ECC_BYTES;
-	chip->ecc.prepad = chip->ecc.postpad = 0;
-
-	/*
-	 * Use a custom BBT marker setup for small page FLASH that
-	 * won't interfere with the ECC layout. Large and huge page
-	 * FLASH use the standard layout.
-	 */
-	if ((chip->bbt_options & NAND_BBT_USE_FLASH) &&
-	    mtd->writesize <= 512) {
-		chip->bbt_td = &bbt_smallpage_main_descr;
-		chip->bbt_md = &bbt_smallpage_mirror_descr;
-	}
-
-	/*
-	 * Fills out all the uninitialized function pointers with the defaults
-	 */
-	res = nand_scan_tail(mtd);
+	chip->dummy_controller.ops = &lpc32xx_nand_controller_ops;
+	res = nand_scan(mtd, 1);
 	if (res)
 		goto release_dma;
 
diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index ebb1d141b900..7af4d6213ee5 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -318,7 +318,7 @@ struct marvell_nfc_caps {
  * @dma_buf:		32-bit aligned buffer for DMA transfers (NFCv1 only)
  */
 struct marvell_nfc {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct device *dev;
 	void __iomem *regs;
 	struct clk *core_clk;
@@ -335,7 +335,7 @@ struct marvell_nfc {
 	u8 *dma_buf;
 };
 
-static inline struct marvell_nfc *to_marvell_nfc(struct nand_hw_control *ctrl)
+static inline struct marvell_nfc *to_marvell_nfc(struct nand_controller *ctrl)
 {
 	return container_of(ctrl, struct marvell_nfc, controller);
 }
@@ -650,11 +650,6 @@ static void marvell_nfc_select_chip(struct mtd_info *mtd, int die_nr)
 		return;
 	}
 
-	/*
-	 * Do not change the timing registers when using the DT property
-	 * marvell,nand-keep-config; in that case ->ndtr0 and ->ndtr1 from the
-	 * marvell_nand structure are supposedly empty.
-	 */
 	writel_relaxed(marvell_nand->ndtr0, nfc->regs + NDTR0);
 	writel_relaxed(marvell_nand->ndtr1, nfc->regs + NDTR1);
 
@@ -2157,6 +2152,7 @@ static int marvell_nand_ecc_init(struct mtd_info *mtd,
 		break;
 	case NAND_ECC_NONE:
 	case NAND_ECC_SOFT:
+	case NAND_ECC_ON_DIE:
 		if (!nfc->caps->is_nfcv2 && mtd->writesize != SZ_512 &&
 		    mtd->writesize != SZ_2K) {
 			dev_err(nfc->dev, "NFCv1 cannot write %d bytes pages\n",
@@ -2294,6 +2290,111 @@ static int marvell_nfc_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	return 0;
 }
 
+static int marvell_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct marvell_nand_chip *marvell_nand = to_marvell_nand(chip);
+	struct marvell_nfc *nfc = to_marvell_nfc(chip->controller);
+	struct pxa3xx_nand_platform_data *pdata = dev_get_platdata(nfc->dev);
+	int ret;
+
+	if (pdata && pdata->flash_bbt)
+		chip->bbt_options |= NAND_BBT_USE_FLASH;
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
+		/*
+		 * We'll use a bad block table stored in-flash and don't
+		 * allow writing the bad block marker to the flash.
+		 */
+		chip->bbt_options |= NAND_BBT_NO_OOB_BBM;
+		chip->bbt_td = &bbt_main_descr;
+		chip->bbt_md = &bbt_mirror_descr;
+	}
+
+	/* Save the chip-specific fields of NDCR */
+	marvell_nand->ndcr = NDCR_PAGE_SZ(mtd->writesize);
+	if (chip->options & NAND_BUSWIDTH_16)
+		marvell_nand->ndcr |= NDCR_DWIDTH_M | NDCR_DWIDTH_C;
+
+	/*
+	 * On small page NANDs, only one cycle is needed to pass the
+	 * column address.
+	 */
+	if (mtd->writesize <= 512) {
+		marvell_nand->addr_cyc = 1;
+	} else {
+		marvell_nand->addr_cyc = 2;
+		marvell_nand->ndcr |= NDCR_RA_START;
+	}
+
+	/*
+	 * Now add the number of cycles needed to pass the row
+	 * address.
+	 *
+	 * Addressing a chip using CS 2 or 3 should also need the third row
+	 * cycle but due to inconsistance in the documentation and lack of
+	 * hardware to test this situation, this case is not supported.
+	 */
+	if (chip->options & NAND_ROW_ADDR_3)
+		marvell_nand->addr_cyc += 3;
+	else
+		marvell_nand->addr_cyc += 2;
+
+	if (pdata) {
+		chip->ecc.size = pdata->ecc_step_size;
+		chip->ecc.strength = pdata->ecc_strength;
+	}
+
+	ret = marvell_nand_ecc_init(mtd, &chip->ecc);
+	if (ret) {
+		dev_err(nfc->dev, "ECC init failed: %d\n", ret);
+		return ret;
+	}
+
+	if (chip->ecc.mode == NAND_ECC_HW) {
+		/*
+		 * Subpage write not available with hardware ECC, prohibit also
+		 * subpage read as in userspace subpage access would still be
+		 * allowed and subpage write, if used, would lead to numerous
+		 * uncorrectable ECC errors.
+		 */
+		chip->options |= NAND_NO_SUBPAGE_WRITE;
+	}
+
+	if (pdata || nfc->caps->legacy_of_bindings) {
+		/*
+		 * We keep the MTD name unchanged to avoid breaking platforms
+		 * where the MTD cmdline parser is used and the bootloader
+		 * has not been updated to use the new naming scheme.
+		 */
+		mtd->name = "pxa3xx_nand-0";
+	} else if (!mtd->name) {
+		/*
+		 * If the new bindings are used and the bootloader has not been
+		 * updated to pass a new mtdparts parameter on the cmdline, you
+		 * should define the following property in your NAND node, ie:
+		 *
+		 *	label = "main-storage";
+		 *
+		 * This way, mtd->name will be set by the core when
+		 * nand_set_flash_node() is called.
+		 */
+		mtd->name = devm_kasprintf(nfc->dev, GFP_KERNEL,
+					   "%s:nand.%d", dev_name(nfc->dev),
+					   marvell_nand->sels[0].cs);
+		if (!mtd->name) {
+			dev_err(nfc->dev, "Failed to allocate mtd->name\n");
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops marvell_nand_controller_ops = {
+	.attach_chip = marvell_nand_attach_chip,
+};
+
 static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc,
 				  struct device_node *np)
 {
@@ -2436,105 +2537,10 @@ static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc,
 	marvell_nand->ndtr1 = readl_relaxed(nfc->regs + NDTR1);
 
 	chip->options |= NAND_BUSWIDTH_AUTO;
-	ret = nand_scan_ident(mtd, marvell_nand->nsels, NULL);
-	if (ret) {
-		dev_err(dev, "could not identify the nand chip\n");
-		return ret;
-	}
-
-	if (pdata && pdata->flash_bbt)
-		chip->bbt_options |= NAND_BBT_USE_FLASH;
 
-	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
-		/*
-		 * We'll use a bad block table stored in-flash and don't
-		 * allow writing the bad block marker to the flash.
-		 */
-		chip->bbt_options |= NAND_BBT_NO_OOB_BBM;
-		chip->bbt_td = &bbt_main_descr;
-		chip->bbt_md = &bbt_mirror_descr;
-	}
-
-	/* Save the chip-specific fields of NDCR */
-	marvell_nand->ndcr = NDCR_PAGE_SZ(mtd->writesize);
-	if (chip->options & NAND_BUSWIDTH_16)
-		marvell_nand->ndcr |= NDCR_DWIDTH_M | NDCR_DWIDTH_C;
-
-	/*
-	 * On small page NANDs, only one cycle is needed to pass the
-	 * column address.
-	 */
-	if (mtd->writesize <= 512) {
-		marvell_nand->addr_cyc = 1;
-	} else {
-		marvell_nand->addr_cyc = 2;
-		marvell_nand->ndcr |= NDCR_RA_START;
-	}
-
-	/*
-	 * Now add the number of cycles needed to pass the row
-	 * address.
-	 *
-	 * Addressing a chip using CS 2 or 3 should also need the third row
-	 * cycle but due to inconsistance in the documentation and lack of
-	 * hardware to test this situation, this case is not supported.
-	 */
-	if (chip->options & NAND_ROW_ADDR_3)
-		marvell_nand->addr_cyc += 3;
-	else
-		marvell_nand->addr_cyc += 2;
-
-	if (pdata) {
-		chip->ecc.size = pdata->ecc_step_size;
-		chip->ecc.strength = pdata->ecc_strength;
-	}
-
-	ret = marvell_nand_ecc_init(mtd, &chip->ecc);
-	if (ret) {
-		dev_err(dev, "ECC init failed: %d\n", ret);
-		return ret;
-	}
-
-	if (chip->ecc.mode == NAND_ECC_HW) {
-		/*
-		 * Subpage write not available with hardware ECC, prohibit also
-		 * subpage read as in userspace subpage access would still be
-		 * allowed and subpage write, if used, would lead to numerous
-		 * uncorrectable ECC errors.
-		 */
-		chip->options |= NAND_NO_SUBPAGE_WRITE;
-	}
-
-	if (pdata || nfc->caps->legacy_of_bindings) {
-		/*
-		 * We keep the MTD name unchanged to avoid breaking platforms
-		 * where the MTD cmdline parser is used and the bootloader
-		 * has not been updated to use the new naming scheme.
-		 */
-		mtd->name = "pxa3xx_nand-0";
-	} else if (!mtd->name) {
-		/*
-		 * If the new bindings are used and the bootloader has not been
-		 * updated to pass a new mtdparts parameter on the cmdline, you
-		 * should define the following property in your NAND node, ie:
-		 *
-		 *	label = "main-storage";
-		 *
-		 * This way, mtd->name will be set by the core when
-		 * nand_set_flash_node() is called.
-		 */
-		mtd->name = devm_kasprintf(nfc->dev, GFP_KERNEL,
-					   "%s:nand.%d", dev_name(nfc->dev),
-					   marvell_nand->sels[0].cs);
-		if (!mtd->name) {
-			dev_err(nfc->dev, "Failed to allocate mtd->name\n");
-			return -ENOMEM;
-		}
-	}
-
-	ret = nand_scan_tail(mtd);
+	ret = nand_scan(mtd, marvell_nand->nsels);
 	if (ret) {
-		dev_err(dev, "nand_scan_tail failed: %d\n", ret);
+		dev_err(dev, "could not scan the nand chip\n");
 		return ret;
 	}
 
@@ -2612,8 +2618,6 @@ static int marvell_nfc_init_dma(struct marvell_nfc *nfc)
 						    dev);
 	struct dma_slave_config config = {};
 	struct resource *r;
-	dma_cap_mask_t mask;
-	struct pxad_param param;
 	int ret;
 
 	if (!IS_ENABLED(CONFIG_PXA_DMA)) {
@@ -2626,20 +2630,7 @@ static int marvell_nfc_init_dma(struct marvell_nfc *nfc)
 	if (ret)
 		return ret;
 
-	r = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-	if (!r) {
-		dev_err(nfc->dev, "No resource defined for data DMA\n");
-		return -ENXIO;
-	}
-
-	param.drcmr = r->start;
-	param.prio = PXAD_PRIO_LOWEST;
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_SLAVE, mask);
-	nfc->dma_chan =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &param, nfc->dev,
-						 "data");
+	nfc->dma_chan =	dma_request_slave_channel(nfc->dev, "data");
 	if (!nfc->dma_chan) {
 		dev_err(nfc->dev,
 			"Unable to request data DMA channel\n");
@@ -2677,6 +2668,21 @@ static int marvell_nfc_init_dma(struct marvell_nfc *nfc)
 	return 0;
 }
 
+static void marvell_nfc_reset(struct marvell_nfc *nfc)
+{
+	/*
+	 * ECC operations and interruptions are only enabled when specifically
+	 * needed. ECC shall not be activated in the early stages (fails probe).
+	 * Arbiter flag, even if marked as "reserved", must be set (empirical).
+	 * SPARE_EN bit must always be set or ECC bytes will not be at the same
+	 * offset in the read page and this will fail the protection.
+	 */
+	writel_relaxed(NDCR_ALL_INT | NDCR_ND_ARB_EN | NDCR_SPARE_EN |
+		       NDCR_RD_ID_CNT(NFCV1_READID_LEN), nfc->regs + NDCR);
+	writel_relaxed(0xFFFFFFFF, nfc->regs + NDSR);
+	writel_relaxed(0, nfc->regs + NDECCCTRL);
+}
+
 static int marvell_nfc_init(struct marvell_nfc *nfc)
 {
 	struct device_node *np = nfc->dev->of_node;
@@ -2715,17 +2721,7 @@ static int marvell_nfc_init(struct marvell_nfc *nfc)
 	if (!nfc->caps->is_nfcv2)
 		marvell_nfc_init_dma(nfc);
 
-	/*
-	 * ECC operations and interruptions are only enabled when specifically
-	 * needed. ECC shall not be activated in the early stages (fails probe).
-	 * Arbiter flag, even if marked as "reserved", must be set (empirical).
-	 * SPARE_EN bit must always be set or ECC bytes will not be at the same
-	 * offset in the read page and this will fail the protection.
-	 */
-	writel_relaxed(NDCR_ALL_INT | NDCR_ND_ARB_EN | NDCR_SPARE_EN |
-		       NDCR_RD_ID_CNT(NFCV1_READID_LEN), nfc->regs + NDCR);
-	writel_relaxed(0xFFFFFFFF, nfc->regs + NDSR);
-	writel_relaxed(0, nfc->regs + NDECCCTRL);
+	marvell_nfc_reset(nfc);
 
 	return 0;
 }
@@ -2744,7 +2740,8 @@ static int marvell_nfc_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	nfc->dev = dev;
-	nand_hw_control_init(&nfc->controller);
+	nand_controller_init(&nfc->controller);
+	nfc->controller.ops = &marvell_nand_controller_ops;
 	INIT_LIST_HEAD(&nfc->chips);
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -2772,17 +2769,19 @@ static int marvell_nfc_probe(struct platform_device *pdev)
 		return ret;
 
 	nfc->reg_clk = devm_clk_get(&pdev->dev, "reg");
-	if (PTR_ERR(nfc->reg_clk) != -ENOENT) {
-		if (!IS_ERR(nfc->reg_clk)) {
-			ret = clk_prepare_enable(nfc->reg_clk);
-			if (ret)
-				goto unprepare_core_clk;
-		} else {
+	if (IS_ERR(nfc->reg_clk)) {
+		if (PTR_ERR(nfc->reg_clk) != -ENOENT) {
 			ret = PTR_ERR(nfc->reg_clk);
 			goto unprepare_core_clk;
 		}
+
+		nfc->reg_clk = NULL;
 	}
 
+	ret = clk_prepare_enable(nfc->reg_clk);
+	if (ret)
+		goto unprepare_core_clk;
+
 	marvell_nfc_disable_int(nfc, NDCR_ALL_INT);
 	marvell_nfc_clear_int(nfc, NDCR_ALL_INT);
 	ret = devm_request_irq(dev, irq, marvell_nfc_isr,
@@ -2840,6 +2839,49 @@ static int marvell_nfc_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static int __maybe_unused marvell_nfc_suspend(struct device *dev)
+{
+	struct marvell_nfc *nfc = dev_get_drvdata(dev);
+	struct marvell_nand_chip *chip;
+
+	list_for_each_entry(chip, &nfc->chips, node)
+		marvell_nfc_wait_ndrun(&chip->chip);
+
+	clk_disable_unprepare(nfc->reg_clk);
+	clk_disable_unprepare(nfc->core_clk);
+
+	return 0;
+}
+
+static int __maybe_unused marvell_nfc_resume(struct device *dev)
+{
+	struct marvell_nfc *nfc = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(nfc->core_clk);
+	if (ret < 0)
+		return ret;
+
+	ret = clk_prepare_enable(nfc->reg_clk);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Reset nfc->selected_chip so the next command will cause the timing
+	 * registers to be restored in marvell_nfc_select_chip().
+	 */
+	nfc->selected_chip = NULL;
+
+	/* Reset registers that have lost their contents */
+	marvell_nfc_reset(nfc);
+
+	return 0;
+}
+
+static const struct dev_pm_ops marvell_nfc_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(marvell_nfc_suspend, marvell_nfc_resume)
+};
+
 static const struct marvell_nfc_caps marvell_armada_8k_nfc_caps = {
 	.max_cs_nb = 4,
 	.max_rb_nb = 2,
@@ -2924,6 +2966,7 @@ static struct platform_driver marvell_nfc_driver = {
 	.driver	= {
 		.name		= "marvell-nfc",
 		.of_match_table = marvell_nfc_of_ids,
+		.pm		= &marvell_nfc_pm_ops,
 	},
 	.id_table = marvell_nfc_platform_ids,
 	.probe = marvell_nfc_probe,
diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c
index 75c845adb050..57b5ed1699e3 100644
--- a/drivers/mtd/nand/raw/mtk_nand.c
+++ b/drivers/mtd/nand/raw/mtk_nand.c
@@ -145,7 +145,7 @@ struct mtk_nfc_clk {
 };
 
 struct mtk_nfc {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct mtk_ecc_config ecc_cfg;
 	struct mtk_nfc_clk clk;
 	struct mtk_ecc *ecc;
@@ -1250,13 +1250,54 @@ static int mtk_nfc_ecc_init(struct device *dev, struct mtd_info *mtd)
 	return 0;
 }
 
+static int mtk_nfc_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct device *dev = mtd->dev.parent;
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip);
+	int len;
+	int ret;
+
+	if (chip->options & NAND_BUSWIDTH_16) {
+		dev_err(dev, "16bits buswidth not supported");
+		return -EINVAL;
+	}
+
+	/* store bbt magic in page, cause OOB is not protected */
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+	ret = mtk_nfc_ecc_init(dev, mtd);
+	if (ret)
+		return ret;
+
+	ret = mtk_nfc_set_spare_per_sector(&mtk_nand->spare_per_sector, mtd);
+	if (ret)
+		return ret;
+
+	mtk_nfc_set_fdm(&mtk_nand->fdm, mtd);
+	mtk_nfc_set_bad_mark_ctl(&mtk_nand->bad_mark, mtd);
+
+	len = mtd->writesize + mtd->oobsize;
+	nfc->buffer = devm_kzalloc(dev, len, GFP_KERNEL);
+	if (!nfc->buffer)
+		return  -ENOMEM;
+
+	return 0;
+}
+
+static const struct nand_controller_ops mtk_nfc_controller_ops = {
+	.attach_chip = mtk_nfc_attach_chip,
+};
+
 static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc,
 				  struct device_node *np)
 {
 	struct mtk_nfc_nand_chip *chip;
 	struct nand_chip *nand;
 	struct mtd_info *mtd;
-	int nsels, len;
+	int nsels;
 	u32 tmp;
 	int ret;
 	int i;
@@ -1324,40 +1365,11 @@ static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc,
 
 	mtk_nfc_hw_init(nfc);
 
-	ret = nand_scan_ident(mtd, nsels, NULL);
-	if (ret)
-		return ret;
-
-	/* store bbt magic in page, cause OOB is not protected */
-	if (nand->bbt_options & NAND_BBT_USE_FLASH)
-		nand->bbt_options |= NAND_BBT_NO_OOB;
-
-	ret = mtk_nfc_ecc_init(dev, mtd);
-	if (ret)
-		return -EINVAL;
-
-	if (nand->options & NAND_BUSWIDTH_16) {
-		dev_err(dev, "16bits buswidth not supported");
-		return -EINVAL;
-	}
-
-	ret = mtk_nfc_set_spare_per_sector(&chip->spare_per_sector, mtd);
-	if (ret)
-		return ret;
-
-	mtk_nfc_set_fdm(&chip->fdm, mtd);
-	mtk_nfc_set_bad_mark_ctl(&chip->bad_mark, mtd);
-
-	len = mtd->writesize + mtd->oobsize;
-	nfc->buffer = devm_kzalloc(dev, len, GFP_KERNEL);
-	if (!nfc->buffer)
-		return  -ENOMEM;
-
-	ret = nand_scan_tail(mtd);
+	ret = nand_scan(mtd, nsels);
 	if (ret)
 		return ret;
 
-	ret = mtd_device_parse_register(mtd, NULL, NULL, NULL, 0);
+	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(dev, "mtd parse partition error\n");
 		nand_release(mtd);
@@ -1443,6 +1455,7 @@ static int mtk_nfc_probe(struct platform_device *pdev)
 	spin_lock_init(&nfc->controller.lock);
 	init_waitqueue_head(&nfc->controller.wq);
 	INIT_LIST_HEAD(&nfc->chips);
+	nfc->controller.ops = &mtk_nfc_controller_ops;
 
 	/* probe defer if not ready */
 	nfc->ecc = of_mtk_ecc_get(np);
diff --git a/drivers/mtd/nand/raw/mxc_nand.c b/drivers/mtd/nand/raw/mxc_nand.c
index 26cef218bb43..4c9214dea424 100644
--- a/drivers/mtd/nand/raw/mxc_nand.c
+++ b/drivers/mtd/nand/raw/mxc_nand.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
  * Copyright 2008 Sascha Hauer, kernel@pengutronix.de
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
  */
 
 #include <linux/delay.h>
@@ -34,8 +21,6 @@
 #include <linux/completion.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-
-#include <asm/mach/flash.h>
 #include <linux/platform_data/mtd-mxc_nand.h>
 
 #define DRIVER_NAME "mxc_nand"
@@ -1686,7 +1671,7 @@ static const struct of_device_id mxcnd_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, mxcnd_dt_ids);
 
-static int __init mxcnd_probe_dt(struct mxc_nand_host *host)
+static int mxcnd_probe_dt(struct mxc_nand_host *host)
 {
 	struct device_node *np = host->dev->of_node;
 	const struct of_device_id *of_id =
@@ -1700,12 +1685,80 @@ static int __init mxcnd_probe_dt(struct mxc_nand_host *host)
 	return 0;
 }
 #else
-static int __init mxcnd_probe_dt(struct mxc_nand_host *host)
+static int mxcnd_probe_dt(struct mxc_nand_host *host)
 {
 	return 1;
 }
 #endif
 
+static int mxcnd_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct mxc_nand_host *host = nand_get_controller_data(chip);
+	struct device *dev = mtd->dev.parent;
+
+	switch (chip->ecc.mode) {
+	case NAND_ECC_HW:
+		chip->ecc.read_page = mxc_nand_read_page;
+		chip->ecc.read_page_raw = mxc_nand_read_page_raw;
+		chip->ecc.read_oob = mxc_nand_read_oob;
+		chip->ecc.write_page = mxc_nand_write_page_ecc;
+		chip->ecc.write_page_raw = mxc_nand_write_page_raw;
+		chip->ecc.write_oob = mxc_nand_write_oob;
+		break;
+
+	case NAND_ECC_SOFT:
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
+		chip->bbt_td = &bbt_main_descr;
+		chip->bbt_md = &bbt_mirror_descr;
+	}
+
+	/* Allocate the right size buffer now */
+	devm_kfree(dev, (void *)host->data_buf);
+	host->data_buf = devm_kzalloc(dev, mtd->writesize + mtd->oobsize,
+				      GFP_KERNEL);
+	if (!host->data_buf)
+		return -ENOMEM;
+
+	/* Call preset again, with correct writesize chip time */
+	host->devtype_data->preset(mtd);
+
+	if (!chip->ecc.bytes) {
+		if (host->eccsize == 8)
+			chip->ecc.bytes = 18;
+		else if (host->eccsize == 4)
+			chip->ecc.bytes = 9;
+	}
+
+	/*
+	 * Experimentation shows that i.MX NFC can only handle up to 218 oob
+	 * bytes. Limit used_oobsize to 218 so as to not confuse copy_spare()
+	 * into copying invalid data to/from the spare IO buffer, as this
+	 * might cause ECC data corruption when doing sub-page write to a
+	 * partially written page.
+	 */
+	host->used_oobsize = min(mtd->oobsize, 218U);
+
+	if (chip->ecc.mode == NAND_ECC_HW) {
+		if (is_imx21_nfc(host) || is_imx27_nfc(host))
+			chip->ecc.strength = 1;
+		else
+			chip->ecc.strength = (host->eccsize == 4) ? 4 : 8;
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops mxcnd_controller_ops = {
+	.attach_chip = mxcnd_attach_chip,
+};
+
 static int mxcnd_probe(struct platform_device *pdev)
 {
 	struct nand_chip *this;
@@ -1845,71 +1898,9 @@ static int mxcnd_probe(struct platform_device *pdev)
 		host->devtype_data->irq_control(host, 1);
 	}
 
-	/* first scan to find the device and get the page size */
-	err = nand_scan_ident(mtd, is_imx25_nfc(host) ? 4 : 1, NULL);
-	if (err)
-		goto escan;
-
-	switch (this->ecc.mode) {
-	case NAND_ECC_HW:
-		this->ecc.read_page = mxc_nand_read_page;
-		this->ecc.read_page_raw = mxc_nand_read_page_raw;
-		this->ecc.read_oob = mxc_nand_read_oob;
-		this->ecc.write_page = mxc_nand_write_page_ecc;
-		this->ecc.write_page_raw = mxc_nand_write_page_raw;
-		this->ecc.write_oob = mxc_nand_write_oob;
-		break;
-
-	case NAND_ECC_SOFT:
-		break;
-
-	default:
-		err = -EINVAL;
-		goto escan;
-	}
-
-	if (this->bbt_options & NAND_BBT_USE_FLASH) {
-		this->bbt_td = &bbt_main_descr;
-		this->bbt_md = &bbt_mirror_descr;
-	}
-
-	/* allocate the right size buffer now */
-	devm_kfree(&pdev->dev, (void *)host->data_buf);
-	host->data_buf = devm_kzalloc(&pdev->dev, mtd->writesize + mtd->oobsize,
-					GFP_KERNEL);
-	if (!host->data_buf) {
-		err = -ENOMEM;
-		goto escan;
-	}
-
-	/* Call preset again, with correct writesize this time */
-	host->devtype_data->preset(mtd);
-
-	if (!this->ecc.bytes) {
-		if (host->eccsize == 8)
-			this->ecc.bytes = 18;
-		else if (host->eccsize == 4)
-			this->ecc.bytes = 9;
-	}
-
-	/*
-	 * Experimentation shows that i.MX NFC can only handle up to 218 oob
-	 * bytes. Limit used_oobsize to 218 so as to not confuse copy_spare()
-	 * into copying invalid data to/from the spare IO buffer, as this
-	 * might cause ECC data corruption when doing sub-page write to a
-	 * partially written page.
-	 */
-	host->used_oobsize = min(mtd->oobsize, 218U);
-
-	if (this->ecc.mode == NAND_ECC_HW) {
-		if (is_imx21_nfc(host) || is_imx27_nfc(host))
-			this->ecc.strength = 1;
-		else
-			this->ecc.strength = (host->eccsize == 4) ? 4 : 8;
-	}
-
-	/* second phase scan */
-	err = nand_scan_tail(mtd);
+	/* Scan the NAND device */
+	this->dummy_controller.ops = &mxcnd_controller_ops;
+	err = nand_scan(mtd, is_imx25_nfc(host) ? 4 : 1);
 	if (err)
 		goto escan;
 
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index b01d15ec4c56..d527e448ce19 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -2668,8 +2668,8 @@ static bool nand_subop_instr_is_valid(const struct nand_subop *subop,
 	return subop && instr_idx < subop->ninstrs;
 }
 
-static int nand_subop_get_start_off(const struct nand_subop *subop,
-				    unsigned int instr_idx)
+static unsigned int nand_subop_get_start_off(const struct nand_subop *subop,
+					     unsigned int instr_idx)
 {
 	if (instr_idx)
 		return 0;
@@ -2688,12 +2688,12 @@ static int nand_subop_get_start_off(const struct nand_subop *subop,
  *
  * Given an address instruction, returns the offset of the first cycle to issue.
  */
-int nand_subop_get_addr_start_off(const struct nand_subop *subop,
-				  unsigned int instr_idx)
+unsigned int nand_subop_get_addr_start_off(const struct nand_subop *subop,
+					   unsigned int instr_idx)
 {
-	if (!nand_subop_instr_is_valid(subop, instr_idx) ||
-	    subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR)
-		return -EINVAL;
+	if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) ||
+		    subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR))
+		return 0;
 
 	return nand_subop_get_start_off(subop, instr_idx);
 }
@@ -2710,14 +2710,14 @@ EXPORT_SYMBOL_GPL(nand_subop_get_addr_start_off);
  *
  * Given an address instruction, returns the number of address cycle to issue.
  */
-int nand_subop_get_num_addr_cyc(const struct nand_subop *subop,
-				unsigned int instr_idx)
+unsigned int nand_subop_get_num_addr_cyc(const struct nand_subop *subop,
+					 unsigned int instr_idx)
 {
 	int start_off, end_off;
 
-	if (!nand_subop_instr_is_valid(subop, instr_idx) ||
-	    subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR)
-		return -EINVAL;
+	if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) ||
+		    subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR))
+		return 0;
 
 	start_off = nand_subop_get_addr_start_off(subop, instr_idx);
 
@@ -2742,12 +2742,12 @@ EXPORT_SYMBOL_GPL(nand_subop_get_num_addr_cyc);
  *
  * Given a data instruction, returns the offset to start from.
  */
-int nand_subop_get_data_start_off(const struct nand_subop *subop,
-				  unsigned int instr_idx)
+unsigned int nand_subop_get_data_start_off(const struct nand_subop *subop,
+					   unsigned int instr_idx)
 {
-	if (!nand_subop_instr_is_valid(subop, instr_idx) ||
-	    !nand_instr_is_data(&subop->instrs[instr_idx]))
-		return -EINVAL;
+	if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) ||
+		    !nand_instr_is_data(&subop->instrs[instr_idx])))
+		return 0;
 
 	return nand_subop_get_start_off(subop, instr_idx);
 }
@@ -2764,14 +2764,14 @@ EXPORT_SYMBOL_GPL(nand_subop_get_data_start_off);
  *
  * Returns the length of the chunk of data to send/receive.
  */
-int nand_subop_get_data_len(const struct nand_subop *subop,
-			    unsigned int instr_idx)
+unsigned int nand_subop_get_data_len(const struct nand_subop *subop,
+				     unsigned int instr_idx)
 {
 	int start_off = 0, end_off;
 
-	if (!nand_subop_instr_is_valid(subop, instr_idx) ||
-	    !nand_instr_is_data(&subop->instrs[instr_idx]))
-		return -EINVAL;
+	if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) ||
+		    !nand_instr_is_data(&subop->instrs[instr_idx])))
+		return 0;
 
 	start_off = nand_subop_get_data_start_off(subop, instr_idx);
 
@@ -2967,6 +2967,23 @@ int nand_check_erased_ecc_chunk(void *data, int datalen,
 EXPORT_SYMBOL(nand_check_erased_ecc_chunk);
 
 /**
+ * nand_read_page_raw_notsupp - dummy read raw page function
+ * @mtd: mtd info structure
+ * @chip: nand chip info structure
+ * @buf: buffer to store read data
+ * @oob_required: caller requires OOB data read to chip->oob_poi
+ * @page: page number to read
+ *
+ * Returns -ENOTSUPP unconditionally.
+ */
+int nand_read_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip,
+			       u8 *buf, int oob_required, int page)
+{
+	return -ENOTSUPP;
+}
+EXPORT_SYMBOL(nand_read_page_raw_notsupp);
+
+/**
  * nand_read_page_raw - [INTERN] read raw page data without ecc
  * @mtd: mtd info structure
  * @chip: nand chip info structure
@@ -3960,6 +3977,22 @@ static int nand_read_oob(struct mtd_info *mtd, loff_t from,
 	return ret;
 }
 
+/**
+ * nand_write_page_raw_notsupp - dummy raw page write function
+ * @mtd: mtd info structure
+ * @chip: nand chip info structure
+ * @buf: data buffer
+ * @oob_required: must write chip->oob_poi to OOB
+ * @page: page number to write
+ *
+ * Returns -ENOTSUPP unconditionally.
+ */
+int nand_write_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip,
+				const u8 *buf, int oob_required, int page)
+{
+	return -ENOTSUPP;
+}
+EXPORT_SYMBOL(nand_write_page_raw_notsupp);
 
 /**
  * nand_write_page_raw - [INTERN] raw page write function
@@ -4965,12 +4998,10 @@ static void nand_set_defaults(struct nand_chip *chip)
 		chip->write_byte = busw ? nand_write_byte16 : nand_write_byte;
 	if (!chip->read_buf || chip->read_buf == nand_read_buf)
 		chip->read_buf = busw ? nand_read_buf16 : nand_read_buf;
-	if (!chip->scan_bbt)
-		chip->scan_bbt = nand_default_bbt;
 
 	if (!chip->controller) {
-		chip->controller = &chip->hwcontrol;
-		nand_hw_control_init(chip->controller);
+		chip->controller = &chip->dummy_controller;
+		nand_controller_init(chip->controller);
 	}
 
 	if (!chip->buf_align)
@@ -5120,6 +5151,8 @@ static int nand_flash_detect_onfi(struct nand_chip *chip)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct nand_onfi_params *p;
+	struct onfi_params *onfi;
+	int onfi_version = 0;
 	char id[4];
 	int i, ret, val;
 
@@ -5168,30 +5201,35 @@ static int nand_flash_detect_onfi(struct nand_chip *chip)
 		}
 	}
 
+	if (chip->manufacturer.desc && chip->manufacturer.desc->ops &&
+	    chip->manufacturer.desc->ops->fixup_onfi_param_page)
+		chip->manufacturer.desc->ops->fixup_onfi_param_page(chip, p);
+
 	/* Check version */
 	val = le16_to_cpu(p->revision);
-	if (val & (1 << 5))
-		chip->parameters.onfi.version = 23;
-	else if (val & (1 << 4))
-		chip->parameters.onfi.version = 22;
-	else if (val & (1 << 3))
-		chip->parameters.onfi.version = 21;
-	else if (val & (1 << 2))
-		chip->parameters.onfi.version = 20;
-	else if (val & (1 << 1))
-		chip->parameters.onfi.version = 10;
-
-	if (!chip->parameters.onfi.version) {
+	if (val & ONFI_VERSION_2_3)
+		onfi_version = 23;
+	else if (val & ONFI_VERSION_2_2)
+		onfi_version = 22;
+	else if (val & ONFI_VERSION_2_1)
+		onfi_version = 21;
+	else if (val & ONFI_VERSION_2_0)
+		onfi_version = 20;
+	else if (val & ONFI_VERSION_1_0)
+		onfi_version = 10;
+
+	if (!onfi_version) {
 		pr_info("unsupported ONFI version: %d\n", val);
 		goto free_onfi_param_page;
-	} else {
-		ret = 1;
 	}
 
 	sanitize_string(p->manufacturer, sizeof(p->manufacturer));
 	sanitize_string(p->model, sizeof(p->model));
-	strncpy(chip->parameters.model, p->model,
-		sizeof(chip->parameters.model) - 1);
+	chip->parameters.model = kstrdup(p->model, GFP_KERNEL);
+	if (!chip->parameters.model) {
+		ret = -ENOMEM;
+		goto free_onfi_param_page;
+	}
 
 	mtd->writesize = le32_to_cpu(p->byte_per_page);
 
@@ -5219,7 +5257,7 @@ static int nand_flash_detect_onfi(struct nand_chip *chip)
 	if (p->ecc_bits != 0xff) {
 		chip->ecc_strength_ds = p->ecc_bits;
 		chip->ecc_step_ds = 512;
-	} else if (chip->parameters.onfi.version >= 21 &&
+	} else if (onfi_version >= 21 &&
 		(le16_to_cpu(p->features) & ONFI_FEATURE_EXT_PARAM_PAGE)) {
 
 		/*
@@ -5246,19 +5284,33 @@ static int nand_flash_detect_onfi(struct nand_chip *chip)
 		bitmap_set(chip->parameters.set_feature_list,
 			   ONFI_FEATURE_ADDR_TIMING_MODE, 1);
 	}
-	chip->parameters.onfi.tPROG = le16_to_cpu(p->t_prog);
-	chip->parameters.onfi.tBERS = le16_to_cpu(p->t_bers);
-	chip->parameters.onfi.tR = le16_to_cpu(p->t_r);
-	chip->parameters.onfi.tCCS = le16_to_cpu(p->t_ccs);
-	chip->parameters.onfi.async_timing_mode =
-		le16_to_cpu(p->async_timing_mode);
-	chip->parameters.onfi.vendor_revision =
-		le16_to_cpu(p->vendor_revision);
-	memcpy(chip->parameters.onfi.vendor, p->vendor,
-	       sizeof(p->vendor));
 
+	onfi = kzalloc(sizeof(*onfi), GFP_KERNEL);
+	if (!onfi) {
+		ret = -ENOMEM;
+		goto free_model;
+	}
+
+	onfi->version = onfi_version;
+	onfi->tPROG = le16_to_cpu(p->t_prog);
+	onfi->tBERS = le16_to_cpu(p->t_bers);
+	onfi->tR = le16_to_cpu(p->t_r);
+	onfi->tCCS = le16_to_cpu(p->t_ccs);
+	onfi->async_timing_mode = le16_to_cpu(p->async_timing_mode);
+	onfi->vendor_revision = le16_to_cpu(p->vendor_revision);
+	memcpy(onfi->vendor, p->vendor, sizeof(p->vendor));
+	chip->parameters.onfi = onfi;
+
+	/* Identification done, free the full ONFI parameter page and exit */
+	kfree(p);
+
+	return 1;
+
+free_model:
+	kfree(chip->parameters.model);
 free_onfi_param_page:
 	kfree(p);
+
 	return ret;
 }
 
@@ -5321,8 +5373,11 @@ static int nand_flash_detect_jedec(struct nand_chip *chip)
 
 	sanitize_string(p->manufacturer, sizeof(p->manufacturer));
 	sanitize_string(p->model, sizeof(p->model));
-	strncpy(chip->parameters.model, p->model,
-		sizeof(chip->parameters.model) - 1);
+	chip->parameters.model = kstrdup(p->model, GFP_KERNEL);
+	if (!chip->parameters.model) {
+		ret = -ENOMEM;
+		goto free_jedec_param_page;
+	}
 
 	mtd->writesize = le32_to_cpu(p->byte_per_page);
 
@@ -5511,8 +5566,9 @@ static bool find_full_id_nand(struct nand_chip *chip,
 		chip->onfi_timing_mode_default =
 					type->onfi_timing_mode_default;
 
-		strncpy(chip->parameters.model, type->name,
-			sizeof(chip->parameters.model) - 1);
+		chip->parameters.model = kstrdup(type->name, GFP_KERNEL);
+		if (!chip->parameters.model)
+			return false;
 
 		return true;
 	}
@@ -5651,7 +5707,6 @@ static int nand_detect(struct nand_chip *chip, struct nand_flash_dev *type)
 		}
 	}
 
-	chip->parameters.onfi.version = 0;
 	if (!type->name || !type->pagesize) {
 		/* Check if the chip is ONFI compliant */
 		ret = nand_flash_detect_onfi(chip);
@@ -5671,8 +5726,9 @@ static int nand_detect(struct nand_chip *chip, struct nand_flash_dev *type)
 	if (!type->name)
 		return -ENODEV;
 
-	strncpy(chip->parameters.model, type->name,
-		sizeof(chip->parameters.model) - 1);
+	chip->parameters.model = kstrdup(type->name, GFP_KERNEL);
+	if (!chip->parameters.model)
+		return -ENOMEM;
 
 	chip->chipsize = (uint64_t)type->chipsize << 20;
 
@@ -5702,7 +5758,9 @@ ident_done:
 			mtd->name);
 		pr_warn("bus width %d instead of %d bits\n", busw ? 16 : 8,
 			(chip->options & NAND_BUSWIDTH_16) ? 16 : 8);
-		return -EINVAL;
+		ret = -EINVAL;
+
+		goto free_detect_allocation;
 	}
 
 	nand_decode_bbm_options(chip);
@@ -5739,6 +5797,11 @@ ident_done:
 		(int)(chip->chipsize >> 20), nand_is_slc(chip) ? "SLC" : "MLC",
 		mtd->erasesize >> 10, mtd->writesize, mtd->oobsize);
 	return 0;
+
+free_detect_allocation:
+	kfree(chip->parameters.model);
+
+	return ret;
 }
 
 static const char * const nand_ecc_modes[] = {
@@ -5777,6 +5840,7 @@ static int of_get_nand_ecc_mode(struct device_node *np)
 static const char * const nand_ecc_algos[] = {
 	[NAND_ECC_HAMMING]	= "hamming",
 	[NAND_ECC_BCH]		= "bch",
+	[NAND_ECC_RS]		= "rs",
 };
 
 static int of_get_nand_ecc_algo(struct device_node *np)
@@ -5858,6 +5922,9 @@ static int nand_dt_init(struct nand_chip *chip)
 	if (of_get_nand_bus_width(dn) == 16)
 		chip->options |= NAND_BUSWIDTH_16;
 
+	if (of_property_read_bool(dn, "nand-is-boot-medium"))
+		chip->options |= NAND_IS_BOOT_MEDIUM;
+
 	if (of_get_nand_on_flash_bbt(dn))
 		chip->bbt_options |= NAND_BBT_USE_FLASH;
 
@@ -5885,7 +5952,7 @@ static int nand_dt_init(struct nand_chip *chip)
 }
 
 /**
- * nand_scan_ident - [NAND Interface] Scan for the NAND device
+ * nand_scan_ident - Scan for the NAND device
  * @mtd: MTD device structure
  * @maxchips: number of chips to scan for
  * @table: alternative NAND ID table
@@ -5893,9 +5960,13 @@ static int nand_dt_init(struct nand_chip *chip)
  * This is the first phase of the normal nand_scan() function. It reads the
  * flash ID and sets up MTD fields accordingly.
  *
+ * This helper used to be called directly from controller drivers that needed
+ * to tweak some ECC-related parameters before nand_scan_tail(). This separation
+ * prevented dynamic allocations during this phase which was unconvenient and
+ * as been banned for the benefit of the ->init_ecc()/cleanup_ecc() hooks.
  */
-int nand_scan_ident(struct mtd_info *mtd, int maxchips,
-		    struct nand_flash_dev *table)
+static int nand_scan_ident(struct mtd_info *mtd, int maxchips,
+			   struct nand_flash_dev *table)
 {
 	int i, nand_maf_id, nand_dev_id;
 	struct nand_chip *chip = mtd_to_nand(mtd);
@@ -5969,7 +6040,12 @@ int nand_scan_ident(struct mtd_info *mtd, int maxchips,
 
 	return 0;
 }
-EXPORT_SYMBOL(nand_scan_ident);
+
+static void nand_scan_ident_cleanup(struct nand_chip *chip)
+{
+	kfree(chip->parameters.model);
+	kfree(chip->parameters.onfi);
+}
 
 static int nand_set_ecc_soft_ops(struct mtd_info *mtd)
 {
@@ -6077,24 +6153,17 @@ static int nand_set_ecc_soft_ops(struct mtd_info *mtd)
  * by the controller and the calculated ECC bytes fit within the chip's OOB.
  * On success, the calculated ECC bytes is set.
  */
-int nand_check_ecc_caps(struct nand_chip *chip,
-			const struct nand_ecc_caps *caps, int oobavail)
+static int
+nand_check_ecc_caps(struct nand_chip *chip,
+		    const struct nand_ecc_caps *caps, int oobavail)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	const struct nand_ecc_step_info *stepinfo;
 	int preset_step = chip->ecc.size;
 	int preset_strength = chip->ecc.strength;
-	int nsteps, ecc_bytes;
+	int ecc_bytes, nsteps = mtd->writesize / preset_step;
 	int i, j;
 
-	if (WARN_ON(oobavail < 0))
-		return -EINVAL;
-
-	if (!preset_step || !preset_strength)
-		return -ENODATA;
-
-	nsteps = mtd->writesize / preset_step;
-
 	for (i = 0; i < caps->nstepinfos; i++) {
 		stepinfo = &caps->stepinfos[i];
 
@@ -6127,7 +6196,6 @@ int nand_check_ecc_caps(struct nand_chip *chip,
 
 	return -ENOTSUPP;
 }
-EXPORT_SYMBOL_GPL(nand_check_ecc_caps);
 
 /**
  * nand_match_ecc_req - meet the chip's requirement with least ECC bytes
@@ -6139,8 +6207,9 @@ EXPORT_SYMBOL_GPL(nand_check_ecc_caps);
  * number of ECC bytes (i.e. with the largest number of OOB-free bytes).
  * On success, the chosen ECC settings are set.
  */
-int nand_match_ecc_req(struct nand_chip *chip,
-		       const struct nand_ecc_caps *caps, int oobavail)
+static int
+nand_match_ecc_req(struct nand_chip *chip,
+		   const struct nand_ecc_caps *caps, int oobavail)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	const struct nand_ecc_step_info *stepinfo;
@@ -6151,9 +6220,6 @@ int nand_match_ecc_req(struct nand_chip *chip,
 	int best_ecc_bytes_total = INT_MAX;
 	int i, j;
 
-	if (WARN_ON(oobavail < 0))
-		return -EINVAL;
-
 	/* No information provided by the NAND chip */
 	if (!req_step || !req_strength)
 		return -ENOTSUPP;
@@ -6212,7 +6278,6 @@ int nand_match_ecc_req(struct nand_chip *chip,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(nand_match_ecc_req);
 
 /**
  * nand_maximize_ecc - choose the max ECC strength available
@@ -6223,8 +6288,9 @@ EXPORT_SYMBOL_GPL(nand_match_ecc_req);
  * Choose the max ECC strength that is supported on the controller, and can fit
  * within the chip's OOB.  On success, the chosen ECC settings are set.
  */
-int nand_maximize_ecc(struct nand_chip *chip,
-		      const struct nand_ecc_caps *caps, int oobavail)
+static int
+nand_maximize_ecc(struct nand_chip *chip,
+		  const struct nand_ecc_caps *caps, int oobavail)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	const struct nand_ecc_step_info *stepinfo;
@@ -6234,9 +6300,6 @@ int nand_maximize_ecc(struct nand_chip *chip,
 	int best_strength, best_ecc_bytes;
 	int i, j;
 
-	if (WARN_ON(oobavail < 0))
-		return -EINVAL;
-
 	for (i = 0; i < caps->nstepinfos; i++) {
 		stepinfo = &caps->stepinfos[i];
 		step_size = stepinfo->stepsize;
@@ -6285,7 +6348,44 @@ int nand_maximize_ecc(struct nand_chip *chip,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(nand_maximize_ecc);
+
+/**
+ * nand_ecc_choose_conf - Set the ECC strength and ECC step size
+ * @chip: nand chip info structure
+ * @caps: ECC engine caps info structure
+ * @oobavail: OOB size that the ECC engine can use
+ *
+ * Choose the ECC configuration according to following logic
+ *
+ * 1. If both ECC step size and ECC strength are already set (usually by DT)
+ *    then check if it is supported by this controller.
+ * 2. If NAND_ECC_MAXIMIZE is set, then select maximum ECC strength.
+ * 3. Otherwise, try to match the ECC step size and ECC strength closest
+ *    to the chip's requirement. If available OOB size can't fit the chip
+ *    requirement then fallback to the maximum ECC step size and ECC strength.
+ *
+ * On success, the chosen ECC settings are set.
+ */
+int nand_ecc_choose_conf(struct nand_chip *chip,
+			 const struct nand_ecc_caps *caps, int oobavail)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+
+	if (WARN_ON(oobavail < 0 || oobavail > mtd->oobsize))
+		return -EINVAL;
+
+	if (chip->ecc.size && chip->ecc.strength)
+		return nand_check_ecc_caps(chip, caps, oobavail);
+
+	if (chip->ecc.options & NAND_ECC_MAXIMIZE)
+		return nand_maximize_ecc(chip, caps, oobavail);
+
+	if (!nand_match_ecc_req(chip, caps, oobavail))
+		return 0;
+
+	return nand_maximize_ecc(chip, caps, oobavail);
+}
+EXPORT_SYMBOL_GPL(nand_ecc_choose_conf);
 
 /*
  * Check if the chip configuration meet the datasheet requirements.
@@ -6322,14 +6422,14 @@ static bool nand_ecc_strength_good(struct mtd_info *mtd)
 }
 
 /**
- * nand_scan_tail - [NAND Interface] Scan for the NAND device
+ * nand_scan_tail - Scan for the NAND device
  * @mtd: MTD device structure
  *
  * This is the second phase of the normal nand_scan() function. It fills out
  * all the uninitialized function pointers with the defaults and scans for a
  * bad block table if appropriate.
  */
-int nand_scan_tail(struct mtd_info *mtd)
+static int nand_scan_tail(struct mtd_info *mtd)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
@@ -6636,7 +6736,7 @@ int nand_scan_tail(struct mtd_info *mtd)
 		return 0;
 
 	/* Build bad block table */
-	ret = chip->scan_bbt(mtd);
+	ret = nand_create_bbt(chip);
 	if (ret)
 		goto err_nand_manuf_cleanup;
 
@@ -6653,24 +6753,27 @@ err_free_buf:
 
 	return ret;
 }
-EXPORT_SYMBOL(nand_scan_tail);
 
-/*
- * is_module_text_address() isn't exported, and it's mostly a pointless
- * test if this is a module _anyway_ -- they'd have to try _really_ hard
- * to call us from in-kernel code if the core NAND support is modular.
- */
-#ifdef MODULE
-#define caller_is_module() (1)
-#else
-#define caller_is_module() \
-	is_module_text_address((unsigned long)__builtin_return_address(0))
-#endif
+static int nand_attach(struct nand_chip *chip)
+{
+	if (chip->controller->ops && chip->controller->ops->attach_chip)
+		return chip->controller->ops->attach_chip(chip);
+
+	return 0;
+}
+
+static void nand_detach(struct nand_chip *chip)
+{
+	if (chip->controller->ops && chip->controller->ops->detach_chip)
+		chip->controller->ops->detach_chip(chip);
+}
 
 /**
  * nand_scan_with_ids - [NAND Interface] Scan for the NAND device
  * @mtd: MTD device structure
- * @maxchips: number of chips to scan for
+ * @maxchips: number of chips to scan for. @nand_scan_ident() will not be run if
+ *	      this parameter is zero (useful for specific drivers that must
+ *	      handle this part of the process themselves, e.g docg4).
  * @ids: optional flash IDs table
  *
  * This fills out all the uninitialized function pointers with the defaults.
@@ -6680,11 +6783,30 @@ EXPORT_SYMBOL(nand_scan_tail);
 int nand_scan_with_ids(struct mtd_info *mtd, int maxchips,
 		       struct nand_flash_dev *ids)
 {
+	struct nand_chip *chip = mtd_to_nand(mtd);
 	int ret;
 
-	ret = nand_scan_ident(mtd, maxchips, ids);
-	if (!ret)
-		ret = nand_scan_tail(mtd);
+	if (maxchips) {
+		ret = nand_scan_ident(mtd, maxchips, ids);
+		if (ret)
+			return ret;
+	}
+
+	ret = nand_attach(chip);
+	if (ret)
+		goto cleanup_ident;
+
+	ret = nand_scan_tail(mtd);
+	if (ret)
+		goto detach_chip;
+
+	return 0;
+
+detach_chip:
+	nand_detach(chip);
+cleanup_ident:
+	nand_scan_ident_cleanup(chip);
+
 	return ret;
 }
 EXPORT_SYMBOL(nand_scan_with_ids);
@@ -6712,7 +6834,14 @@ void nand_cleanup(struct nand_chip *chip)
 
 	/* Free manufacturer priv data. */
 	nand_manufacturer_cleanup(chip);
+
+	/* Free controller specific allocations after chip identification */
+	nand_detach(chip);
+
+	/* Free identification phase allocations */
+	nand_scan_ident_cleanup(chip);
 }
+
 EXPORT_SYMBOL_GPL(nand_cleanup);
 
 /**
diff --git a/drivers/mtd/nand/raw/nand_bbt.c b/drivers/mtd/nand/raw/nand_bbt.c
index d9f4ceff2568..39db352f8757 100644
--- a/drivers/mtd/nand/raw/nand_bbt.c
+++ b/drivers/mtd/nand/raw/nand_bbt.c
@@ -1349,15 +1349,14 @@ static int nand_create_badblock_pattern(struct nand_chip *this)
 }
 
 /**
- * nand_default_bbt - [NAND Interface] Select a default bad block table for the device
- * @mtd: MTD device structure
+ * nand_create_bbt - [NAND Interface] Select a default bad block table for the device
+ * @this: NAND chip object
  *
  * This function selects the default bad block table support for the device and
  * calls the nand_scan_bbt function.
  */
-int nand_default_bbt(struct mtd_info *mtd)
+int nand_create_bbt(struct nand_chip *this)
 {
-	struct nand_chip *this = mtd_to_nand(mtd);
 	int ret;
 
 	/* Is a flash based bad block table requested? */
@@ -1383,8 +1382,9 @@ int nand_default_bbt(struct mtd_info *mtd)
 			return ret;
 	}
 
-	return nand_scan_bbt(mtd, this->badblock_pattern);
+	return nand_scan_bbt(nand_to_mtd(this), this->badblock_pattern);
 }
+EXPORT_SYMBOL(nand_create_bbt);
 
 /**
  * nand_isreserved_bbt - [NAND Interface] Check if a block is reserved
diff --git a/drivers/mtd/nand/raw/nand_hynix.c b/drivers/mtd/nand/raw/nand_hynix.c
index d542908a0ebb..4ffbb26e76d6 100644
--- a/drivers/mtd/nand/raw/nand_hynix.c
+++ b/drivers/mtd/nand/raw/nand_hynix.c
@@ -100,6 +100,16 @@ static int hynix_nand_reg_write_op(struct nand_chip *chip, u8 addr, u8 val)
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	u16 column = ((u16)addr << 8) | addr;
 
+	if (chip->exec_op) {
+		struct nand_op_instr instrs[] = {
+			NAND_OP_ADDR(1, &addr, 0),
+			NAND_OP_8BIT_DATA_OUT(1, &val, 0),
+		};
+		struct nand_operation op = NAND_OPERATION(instrs);
+
+		return nand_exec_op(chip, &op);
+	}
+
 	chip->cmdfunc(mtd, NAND_CMD_NONE, column, -1);
 	chip->write_byte(mtd, val);
 
@@ -473,6 +483,19 @@ static void hynix_nand_extract_oobsize(struct nand_chip *chip,
 			WARN(1, "Invalid OOB size");
 			break;
 		}
+
+		/*
+		 * The datasheet of H27UCG8T2BTR mentions that the "Redundant
+		 * Area Size" is encoded "per 8KB" (page size). This chip uses
+		 * a page size of 16KiB. The datasheet mentions an OOB size of
+		 * 1.280 bytes, but the OOB size encoded in the ID bytes (using
+		 * the existing logic above) is 640 bytes.
+		 * Update the OOB size for this chip by taking the value
+		 * determined above and scaling it to the actual page size (so
+		 * the actual OOB size for this chip is: 640 * 16k / 8k).
+		 */
+		if (chip->id.data[1] == 0xde)
+			mtd->oobsize *= mtd->writesize / SZ_8K;
 	}
 }
 
diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c
index 5ec4c90a637d..f5dc0a7a2456 100644
--- a/drivers/mtd/nand/raw/nand_micron.c
+++ b/drivers/mtd/nand/raw/nand_micron.c
@@ -16,12 +16,33 @@
  */
 
 #include <linux/mtd/rawnand.h>
+#include <linux/slab.h>
 
 /*
- * Special Micron status bit that indicates when the block has been
- * corrected by on-die ECC and should be rewritten
+ * Special Micron status bit 3 indicates that the block has been
+ * corrected by on-die ECC and should be rewritten.
  */
-#define NAND_STATUS_WRITE_RECOMMENDED	BIT(3)
+#define NAND_ECC_STATUS_WRITE_RECOMMENDED	BIT(3)
+
+/*
+ * On chips with 8-bit ECC and additional bit can be used to distinguish
+ * cases where a errors were corrected without needing a rewrite
+ *
+ * Bit 4 Bit 3 Bit 0 Description
+ * ----- ----- ----- -----------
+ * 0     0     0     No Errors
+ * 0     0     1     Multiple uncorrected errors
+ * 0     1     0     4 - 6 errors corrected, recommend rewrite
+ * 0     1     1     Reserved
+ * 1     0     0     1 - 3 errors corrected
+ * 1     0     1     Reserved
+ * 1     1     0     7 - 8 errors corrected, recommend rewrite
+ */
+#define NAND_ECC_STATUS_MASK		(BIT(4) | BIT(3) | BIT(0))
+#define NAND_ECC_STATUS_UNCORRECTABLE	BIT(0)
+#define NAND_ECC_STATUS_4_6_CORRECTED	BIT(3)
+#define NAND_ECC_STATUS_1_3_CORRECTED	BIT(4)
+#define NAND_ECC_STATUS_7_8_CORRECTED	(BIT(4) | BIT(3))
 
 struct nand_onfi_vendor_micron {
 	u8 two_plane_read;
@@ -43,6 +64,16 @@ struct nand_onfi_vendor_micron {
 	u8 param_revision;
 } __packed;
 
+struct micron_on_die_ecc {
+	bool forced;
+	bool enabled;
+	void *rawbuf;
+};
+
+struct micron_nand {
+	struct micron_on_die_ecc ecc;
+};
+
 static int micron_nand_setup_read_retry(struct mtd_info *mtd, int retry_mode)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
@@ -57,9 +88,10 @@ static int micron_nand_setup_read_retry(struct mtd_info *mtd, int retry_mode)
 static int micron_nand_onfi_init(struct nand_chip *chip)
 {
 	struct nand_parameters *p = &chip->parameters;
-	struct nand_onfi_vendor_micron *micron = (void *)p->onfi.vendor;
 
-	if (chip->parameters.onfi.version && p->onfi.vendor_revision) {
+	if (p->onfi) {
+		struct nand_onfi_vendor_micron *micron = (void *)p->onfi->vendor;
+
 		chip->read_retries = micron->read_retry_options;
 		chip->setup_read_retry = micron_nand_setup_read_retry;
 	}
@@ -74,8 +106,9 @@ static int micron_nand_onfi_init(struct nand_chip *chip)
 	return 0;
 }
 
-static int micron_nand_on_die_ooblayout_ecc(struct mtd_info *mtd, int section,
-					    struct mtd_oob_region *oobregion)
+static int micron_nand_on_die_4_ooblayout_ecc(struct mtd_info *mtd,
+					      int section,
+					      struct mtd_oob_region *oobregion)
 {
 	if (section >= 4)
 		return -ERANGE;
@@ -86,8 +119,9 @@ static int micron_nand_on_die_ooblayout_ecc(struct mtd_info *mtd, int section,
 	return 0;
 }
 
-static int micron_nand_on_die_ooblayout_free(struct mtd_info *mtd, int section,
-					     struct mtd_oob_region *oobregion)
+static int micron_nand_on_die_4_ooblayout_free(struct mtd_info *mtd,
+					       int section,
+					       struct mtd_oob_region *oobregion)
 {
 	if (section >= 4)
 		return -ERANGE;
@@ -98,19 +132,161 @@ static int micron_nand_on_die_ooblayout_free(struct mtd_info *mtd, int section,
 	return 0;
 }
 
-static const struct mtd_ooblayout_ops micron_nand_on_die_ooblayout_ops = {
-	.ecc = micron_nand_on_die_ooblayout_ecc,
-	.free = micron_nand_on_die_ooblayout_free,
+static const struct mtd_ooblayout_ops micron_nand_on_die_4_ooblayout_ops = {
+	.ecc = micron_nand_on_die_4_ooblayout_ecc,
+	.free = micron_nand_on_die_4_ooblayout_free,
+};
+
+static int micron_nand_on_die_8_ooblayout_ecc(struct mtd_info *mtd,
+					      int section,
+					      struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+
+	if (section)
+		return -ERANGE;
+
+	oobregion->offset = mtd->oobsize - chip->ecc.total;
+	oobregion->length = chip->ecc.total;
+
+	return 0;
+}
+
+static int micron_nand_on_die_8_ooblayout_free(struct mtd_info *mtd,
+					       int section,
+					       struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+
+	if (section)
+		return -ERANGE;
+
+	oobregion->offset = 2;
+	oobregion->length = mtd->oobsize - chip->ecc.total - 2;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops micron_nand_on_die_8_ooblayout_ops = {
+	.ecc = micron_nand_on_die_8_ooblayout_ecc,
+	.free = micron_nand_on_die_8_ooblayout_free,
 };
 
 static int micron_nand_on_die_ecc_setup(struct nand_chip *chip, bool enable)
 {
+	struct micron_nand *micron = nand_get_manufacturer_data(chip);
 	u8 feature[ONFI_SUBFEATURE_PARAM_LEN] = { 0, };
+	int ret;
+
+	if (micron->ecc.forced)
+		return 0;
+
+	if (micron->ecc.enabled == enable)
+		return 0;
 
 	if (enable)
 		feature[0] |= ONFI_FEATURE_ON_DIE_ECC_EN;
 
-	return nand_set_features(chip, ONFI_FEATURE_ON_DIE_ECC, feature);
+	ret = nand_set_features(chip, ONFI_FEATURE_ON_DIE_ECC, feature);
+	if (!ret)
+		micron->ecc.enabled = enable;
+
+	return ret;
+}
+
+static int micron_nand_on_die_ecc_status_4(struct nand_chip *chip, u8 status,
+					   void *buf, int page,
+					   int oob_required)
+{
+	struct micron_nand *micron = nand_get_manufacturer_data(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	unsigned int step, max_bitflips = 0;
+	int ret;
+
+	if (!(status & NAND_ECC_STATUS_WRITE_RECOMMENDED)) {
+		if (status & NAND_STATUS_FAIL)
+			mtd->ecc_stats.failed++;
+
+		return 0;
+	}
+
+	/*
+	 * The internal ECC doesn't tell us the number of bitflips that have
+	 * been corrected, but tells us if it recommends to rewrite the block.
+	 * If it's the case, we need to read the page in raw mode and compare
+	 * its content to the corrected version to extract the actual number of
+	 * bitflips.
+	 * But before we do that, we must make sure we have all OOB bytes read
+	 * in non-raw mode, even if the user did not request those bytes.
+	 */
+	if (!oob_required) {
+		ret = nand_read_data_op(chip, chip->oob_poi, mtd->oobsize,
+					false);
+		if (ret)
+			return ret;
+	}
+
+	micron_nand_on_die_ecc_setup(chip, false);
+
+	ret = nand_read_page_op(chip, page, 0, micron->ecc.rawbuf,
+				mtd->writesize + mtd->oobsize);
+	if (ret)
+		return ret;
+
+	for (step = 0; step < chip->ecc.steps; step++) {
+		unsigned int offs, i, nbitflips = 0;
+		u8 *rawbuf, *corrbuf;
+
+		offs = step * chip->ecc.size;
+		rawbuf = micron->ecc.rawbuf + offs;
+		corrbuf = buf + offs;
+
+		for (i = 0; i < chip->ecc.size; i++)
+			nbitflips += hweight8(corrbuf[i] ^ rawbuf[i]);
+
+		offs = (step * 16) + 4;
+		rawbuf = micron->ecc.rawbuf + mtd->writesize + offs;
+		corrbuf = chip->oob_poi + offs;
+
+		for (i = 0; i < chip->ecc.bytes + 4; i++)
+			nbitflips += hweight8(corrbuf[i] ^ rawbuf[i]);
+
+		if (WARN_ON(nbitflips > chip->ecc.strength))
+			return -EINVAL;
+
+		max_bitflips = max(nbitflips, max_bitflips);
+		mtd->ecc_stats.corrected += nbitflips;
+	}
+
+	return max_bitflips;
+}
+
+static int micron_nand_on_die_ecc_status_8(struct nand_chip *chip, u8 status)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+
+	/*
+	 * With 8/512 we have more information but still don't know precisely
+	 * how many bit-flips were seen.
+	 */
+	switch (status & NAND_ECC_STATUS_MASK) {
+	case NAND_ECC_STATUS_UNCORRECTABLE:
+		mtd->ecc_stats.failed++;
+		return 0;
+	case NAND_ECC_STATUS_1_3_CORRECTED:
+		mtd->ecc_stats.corrected += 3;
+		return 3;
+	case NAND_ECC_STATUS_4_6_CORRECTED:
+		mtd->ecc_stats.corrected += 6;
+		/* rewrite recommended */
+		return 6;
+	case NAND_ECC_STATUS_7_8_CORRECTED:
+		mtd->ecc_stats.corrected += 8;
+		/* rewrite recommended */
+		return 8;
+	default:
+		return 0;
+	}
 }
 
 static int
@@ -137,24 +313,18 @@ micron_nand_read_page_on_die_ecc(struct mtd_info *mtd, struct nand_chip *chip,
 	if (ret)
 		goto out;
 
-	if (status & NAND_STATUS_FAIL)
-		mtd->ecc_stats.failed++;
-
-	/*
-	 * The internal ECC doesn't tell us the number of bitflips
-	 * that have been corrected, but tells us if it recommends to
-	 * rewrite the block. If it's the case, then we pretend we had
-	 * a number of bitflips equal to the ECC strength, which will
-	 * hint the NAND core to rewrite the block.
-	 */
-	else if (status & NAND_STATUS_WRITE_RECOMMENDED)
-		max_bitflips = chip->ecc.strength;
-
 	ret = nand_read_data_op(chip, buf, mtd->writesize, false);
 	if (!ret && oob_required)
 		ret = nand_read_data_op(chip, chip->oob_poi, mtd->oobsize,
 					false);
 
+	if (chip->ecc.strength == 4)
+		max_bitflips = micron_nand_on_die_ecc_status_4(chip, status,
+							       buf, page,
+							       oob_required);
+	else
+		max_bitflips = micron_nand_on_die_ecc_status_8(chip, status);
+
 out:
 	micron_nand_on_die_ecc_setup(chip, false);
 
@@ -195,6 +365,9 @@ enum {
 	MICRON_ON_DIE_MANDATORY,
 };
 
+#define MICRON_ID_INTERNAL_ECC_MASK	GENMASK(1, 0)
+#define MICRON_ID_ECC_ENABLED		BIT(7)
+
 /*
  * Try to detect if the NAND support on-die ECC. To do this, we enable
  * the feature, and read back if it has been enabled as expected. We
@@ -207,42 +380,52 @@ enum {
  */
 static int micron_supports_on_die_ecc(struct nand_chip *chip)
 {
-	u8 feature[ONFI_SUBFEATURE_PARAM_LEN] = { 0, };
+	u8 id[5];
 	int ret;
 
-	if (!chip->parameters.onfi.version)
+	if (!chip->parameters.onfi)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
 	if (chip->bits_per_cell != 1)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
+	/*
+	 * We only support on-die ECC of 4/512 or 8/512
+	 */
+	if  (chip->ecc_strength_ds != 4 && chip->ecc_strength_ds != 8)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
+	/* 0x2 means on-die ECC is available. */
+	if (chip->id.len != 5 ||
+	    (chip->id.data[4] & MICRON_ID_INTERNAL_ECC_MASK) != 0x2)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
 	ret = micron_nand_on_die_ecc_setup(chip, true);
 	if (ret)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
-	ret = nand_get_features(chip, ONFI_FEATURE_ON_DIE_ECC, feature);
-	if (ret < 0)
-		return ret;
+	ret = nand_readid_op(chip, 0, id, sizeof(id));
+	if (ret)
+		return MICRON_ON_DIE_UNSUPPORTED;
 
-	if ((feature[0] & ONFI_FEATURE_ON_DIE_ECC_EN) == 0)
+	if (!(id[4] & MICRON_ID_ECC_ENABLED))
 		return MICRON_ON_DIE_UNSUPPORTED;
 
 	ret = micron_nand_on_die_ecc_setup(chip, false);
 	if (ret)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
-	ret = nand_get_features(chip, ONFI_FEATURE_ON_DIE_ECC, feature);
-	if (ret < 0)
-		return ret;
+	ret = nand_readid_op(chip, 0, id, sizeof(id));
+	if (ret)
+		return MICRON_ON_DIE_UNSUPPORTED;
 
-	if (feature[0] & ONFI_FEATURE_ON_DIE_ECC_EN)
+	if (id[4] & MICRON_ID_ECC_ENABLED)
 		return MICRON_ON_DIE_MANDATORY;
 
 	/*
-	 * Some Micron NANDs have an on-die ECC of 4/512, some other
-	 * 8/512. We only support the former.
+	 * We only support on-die ECC of 4/512 or 8/512
 	 */
-	if (chip->ecc_strength_ds != 4)
+	if  (chip->ecc_strength_ds != 4 && chip->ecc_strength_ds != 8)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
 	return MICRON_ON_DIE_SUPPORTED;
@@ -251,44 +434,116 @@ static int micron_supports_on_die_ecc(struct nand_chip *chip)
 static int micron_nand_init(struct nand_chip *chip)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct micron_nand *micron;
 	int ondie;
 	int ret;
 
+	micron = kzalloc(sizeof(*micron), GFP_KERNEL);
+	if (!micron)
+		return -ENOMEM;
+
+	nand_set_manufacturer_data(chip, micron);
+
 	ret = micron_nand_onfi_init(chip);
 	if (ret)
-		return ret;
+		goto err_free_manuf_data;
 
 	if (mtd->writesize == 2048)
 		chip->bbt_options |= NAND_BBT_SCAN2NDPAGE;
 
 	ondie = micron_supports_on_die_ecc(chip);
 
-	if (ondie == MICRON_ON_DIE_MANDATORY) {
+	if (ondie == MICRON_ON_DIE_MANDATORY &&
+	    chip->ecc.mode != NAND_ECC_ON_DIE) {
 		pr_err("On-die ECC forcefully enabled, not supported\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_free_manuf_data;
 	}
 
 	if (chip->ecc.mode == NAND_ECC_ON_DIE) {
 		if (ondie == MICRON_ON_DIE_UNSUPPORTED) {
 			pr_err("On-die ECC selected but not supported\n");
-			return -EINVAL;
+			ret = -EINVAL;
+			goto err_free_manuf_data;
+		}
+
+		if (ondie == MICRON_ON_DIE_MANDATORY) {
+			micron->ecc.forced = true;
+			micron->ecc.enabled = true;
+		}
+
+		/*
+		 * In case of 4bit on-die ECC, we need a buffer to store a
+		 * page dumped in raw mode so that we can compare its content
+		 * to the same page after ECC correction happened and extract
+		 * the real number of bitflips from this comparison.
+		 * That's not needed for 8-bit ECC, because the status expose
+		 * a better approximation of the number of bitflips in a page.
+		 */
+		if (chip->ecc_strength_ds == 4) {
+			micron->ecc.rawbuf = kmalloc(mtd->writesize +
+						     mtd->oobsize,
+						     GFP_KERNEL);
+			if (!micron->ecc.rawbuf) {
+				ret = -ENOMEM;
+				goto err_free_manuf_data;
+			}
 		}
 
-		chip->ecc.bytes = 8;
+		if (chip->ecc_strength_ds == 4)
+			mtd_set_ooblayout(mtd,
+					  &micron_nand_on_die_4_ooblayout_ops);
+		else
+			mtd_set_ooblayout(mtd,
+					  &micron_nand_on_die_8_ooblayout_ops);
+
+		chip->ecc.bytes = chip->ecc_strength_ds * 2;
 		chip->ecc.size = 512;
-		chip->ecc.strength = 4;
+		chip->ecc.strength = chip->ecc_strength_ds;
 		chip->ecc.algo = NAND_ECC_BCH;
 		chip->ecc.read_page = micron_nand_read_page_on_die_ecc;
 		chip->ecc.write_page = micron_nand_write_page_on_die_ecc;
-		chip->ecc.read_page_raw = nand_read_page_raw;
-		chip->ecc.write_page_raw = nand_write_page_raw;
 
-		mtd_set_ooblayout(mtd, &micron_nand_on_die_ooblayout_ops);
+		if (ondie == MICRON_ON_DIE_MANDATORY) {
+			chip->ecc.read_page_raw = nand_read_page_raw_notsupp;
+			chip->ecc.write_page_raw = nand_write_page_raw_notsupp;
+		} else {
+			chip->ecc.read_page_raw = nand_read_page_raw;
+			chip->ecc.write_page_raw = nand_write_page_raw;
+		}
 	}
 
 	return 0;
+
+err_free_manuf_data:
+	kfree(micron->ecc.rawbuf);
+	kfree(micron);
+
+	return ret;
+}
+
+static void micron_nand_cleanup(struct nand_chip *chip)
+{
+	struct micron_nand *micron = nand_get_manufacturer_data(chip);
+
+	kfree(micron->ecc.rawbuf);
+	kfree(micron);
+}
+
+static void micron_fixup_onfi_param_page(struct nand_chip *chip,
+					 struct nand_onfi_params *p)
+{
+	/*
+	 * MT29F1G08ABAFAWP-ITE:F and possibly others report 00 00 for the
+	 * revision number field of the ONFI parameter page. Assume ONFI
+	 * version 1.0 if the revision number is 00 00.
+	 */
+	if (le16_to_cpu(p->revision) == 0)
+		p->revision = cpu_to_le16(ONFI_VERSION_1_0);
 }
 
 const struct nand_manufacturer_ops micron_nand_manuf_ops = {
 	.init = micron_nand_init,
+	.cleanup = micron_nand_cleanup,
+	.fixup_onfi_param_page = micron_fixup_onfi_param_page,
 };
diff --git a/drivers/mtd/nand/raw/nand_timings.c b/drivers/mtd/nand/raw/nand_timings.c
index 7c4e4a371bbc..ebc7b5f76f77 100644
--- a/drivers/mtd/nand/raw/nand_timings.c
+++ b/drivers/mtd/nand/raw/nand_timings.c
@@ -13,6 +13,8 @@
 #include <linux/export.h>
 #include <linux/mtd/rawnand.h>
 
+#define ONFI_DYN_TIMING_MAX U16_MAX
+
 static const struct nand_data_interface onfi_sdr_timings[] = {
 	/* Mode 0 */
 	{
@@ -292,6 +294,7 @@ int onfi_fill_data_interface(struct nand_chip *chip,
 			     int timing_mode)
 {
 	struct nand_data_interface *iface = &chip->data_interface;
+	struct onfi_params *onfi = chip->parameters.onfi;
 
 	if (type != NAND_SDR_IFACE)
 		return -EINVAL;
@@ -303,20 +306,35 @@ int onfi_fill_data_interface(struct nand_chip *chip,
 
 	/*
 	 * Initialize timings that cannot be deduced from timing mode:
-	 * tR, tPROG, tCCS, ...
+	 * tPROG, tBERS, tR and tCCS.
 	 * These information are part of the ONFI parameter page.
 	 */
-	if (chip->parameters.onfi.version) {
-		struct nand_parameters *params = &chip->parameters;
+	if (onfi) {
+		struct nand_sdr_timings *timings = &iface->timings.sdr;
+
+		/* microseconds -> picoseconds */
+		timings->tPROG_max = 1000000ULL * onfi->tPROG;
+		timings->tBERS_max = 1000000ULL * onfi->tBERS;
+		timings->tR_max = 1000000ULL * onfi->tR;
+
+		/* nanoseconds -> picoseconds */
+		timings->tCCS_min = 1000UL * onfi->tCCS;
+	} else {
 		struct nand_sdr_timings *timings = &iface->timings.sdr;
+		/*
+		 * For non-ONFI chips we use the highest possible value for
+		 * tPROG and tBERS. tR and tCCS will take the default values
+		 * precised in the ONFI specification for timing mode 0,
+		 * respectively 200us and 500ns.
+		 */
 
 		/* microseconds -> picoseconds */
-		timings->tPROG_max = 1000000ULL * params->onfi.tPROG;
-		timings->tBERS_max = 1000000ULL * params->onfi.tBERS;
-		timings->tR_max = 1000000ULL * params->onfi.tR;
+		timings->tPROG_max = 1000000ULL * ONFI_DYN_TIMING_MAX;
+		timings->tBERS_max = 1000000ULL * ONFI_DYN_TIMING_MAX;
+		timings->tR_max = 1000000ULL * 200000000ULL;
 
 		/* nanoseconds -> picoseconds */
-		timings->tCCS_min = 1000UL * params->onfi.tCCS;
+		timings->tCCS_min = 1000UL * 500000;
 	}
 
 	return 0;
diff --git a/drivers/mtd/nand/raw/nandsim.c b/drivers/mtd/nand/raw/nandsim.c
index f8edacde49ab..71ac034aee9c 100644
--- a/drivers/mtd/nand/raw/nandsim.c
+++ b/drivers/mtd/nand/raw/nandsim.c
@@ -2192,6 +2192,48 @@ static void ns_nand_read_buf(struct mtd_info *mtd, u_char *buf, int len)
 	return;
 }
 
+static int ns_attach_chip(struct nand_chip *chip)
+{
+	unsigned int eccsteps, eccbytes;
+
+	if (!bch)
+		return 0;
+
+	if (!mtd_nand_has_bch()) {
+		NS_ERR("BCH ECC support is disabled\n");
+		return -EINVAL;
+	}
+
+	/* Use 512-byte ecc blocks */
+	eccsteps = nsmtd->writesize / 512;
+	eccbytes = ((bch * 13) + 7) / 8;
+
+	/* Do not bother supporting small page devices */
+	if (nsmtd->oobsize < 64 || !eccsteps) {
+		NS_ERR("BCH not available on small page devices\n");
+		return -EINVAL;
+	}
+
+	if (((eccbytes * eccsteps) + 2) > nsmtd->oobsize) {
+		NS_ERR("Invalid BCH value %u\n", bch);
+		return -EINVAL;
+	}
+
+	chip->ecc.mode = NAND_ECC_SOFT;
+	chip->ecc.algo = NAND_ECC_BCH;
+	chip->ecc.size = 512;
+	chip->ecc.strength = bch;
+	chip->ecc.bytes = eccbytes;
+
+	NS_INFO("Using %u-bit/%u bytes BCH ECC\n", bch, chip->ecc.size);
+
+	return 0;
+}
+
+static const struct nand_controller_ops ns_controller_ops = {
+	.attach_chip = ns_attach_chip,
+};
+
 /*
  * Module initialization function
  */
@@ -2276,44 +2318,10 @@ static int __init ns_init_module(void)
 	if ((retval = parse_gravepages()) != 0)
 		goto error;
 
-	retval = nand_scan_ident(nsmtd, 1, NULL);
-	if (retval) {
-		NS_ERR("cannot scan NAND Simulator device\n");
-		goto error;
-	}
-
-	if (bch) {
-		unsigned int eccsteps, eccbytes;
-		if (!mtd_nand_has_bch()) {
-			NS_ERR("BCH ECC support is disabled\n");
-			retval = -EINVAL;
-			goto error;
-		}
-		/* use 512-byte ecc blocks */
-		eccsteps = nsmtd->writesize/512;
-		eccbytes = (bch*13+7)/8;
-		/* do not bother supporting small page devices */
-		if ((nsmtd->oobsize < 64) || !eccsteps) {
-			NS_ERR("bch not available on small page devices\n");
-			retval = -EINVAL;
-			goto error;
-		}
-		if ((eccbytes*eccsteps+2) > nsmtd->oobsize) {
-			NS_ERR("invalid bch value %u\n", bch);
-			retval = -EINVAL;
-			goto error;
-		}
-		chip->ecc.mode = NAND_ECC_SOFT;
-		chip->ecc.algo = NAND_ECC_BCH;
-		chip->ecc.size = 512;
-		chip->ecc.strength = bch;
-		chip->ecc.bytes = eccbytes;
-		NS_INFO("using %u-bit/%u bytes BCH ECC\n", bch, chip->ecc.size);
-	}
-
-	retval = nand_scan_tail(nsmtd);
+	chip->dummy_controller.ops = &ns_controller_ops;
+	retval = nand_scan(nsmtd, 1);
 	if (retval) {
-		NS_ERR("can't register NAND Simulator\n");
+		NS_ERR("Could not scan NAND Simulator device\n");
 		goto error;
 	}
 
@@ -2337,7 +2345,7 @@ static int __init ns_init_module(void)
 	if ((retval = init_nandsim(nsmtd)) != 0)
 		goto err_exit;
 
-	if ((retval = chip->scan_bbt(nsmtd)) != 0)
+	if ((retval = nand_create_bbt(chip)) != 0)
 		goto err_exit;
 
 	if ((retval = parse_badblocks(nand, nsmtd)) != 0)
diff --git a/drivers/mtd/nand/raw/ndfc.c b/drivers/mtd/nand/raw/ndfc.c
index d8a806894937..540fa1a0ea24 100644
--- a/drivers/mtd/nand/raw/ndfc.c
+++ b/drivers/mtd/nand/raw/ndfc.c
@@ -39,7 +39,7 @@ struct ndfc_controller {
 	void __iomem *ndfcbase;
 	struct nand_chip chip;
 	int chip_select;
-	struct nand_hw_control ndfc_control;
+	struct nand_controller ndfc_control;
 };
 
 static struct ndfc_controller ndfc_ctrl[NDFC_MAX_CS];
@@ -218,7 +218,7 @@ static int ndfc_probe(struct platform_device *ofdev)
 	ndfc = &ndfc_ctrl[cs];
 	ndfc->chip_select = cs;
 
-	nand_hw_control_init(&ndfc->ndfc_control);
+	nand_controller_init(&ndfc->ndfc_control);
 	ndfc->ofdev = ofdev;
 	dev_set_drvdata(&ofdev->dev, ndfc);
 
diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c
index e50c64adc3c8..4546ac0bed4a 100644
--- a/drivers/mtd/nand/raw/omap2.c
+++ b/drivers/mtd/nand/raw/omap2.c
@@ -144,12 +144,6 @@ static u_char bch8_vector[] = {0xf3, 0xdb, 0x14, 0x16, 0x8b, 0xd2, 0xbe, 0xcc,
 	0xac, 0x6b, 0xff, 0x99, 0x7b};
 static u_char bch4_vector[] = {0x00, 0x6b, 0x31, 0xdd, 0x41, 0xbc, 0x10};
 
-/* Shared among all NAND instances to synchronize access to the ECC Engine */
-static struct nand_hw_control omap_gpmc_controller = {
-	.lock = __SPIN_LOCK_UNLOCKED(omap_gpmc_controller.lock),
-	.wq = __WAIT_QUEUE_HEAD_INITIALIZER(omap_gpmc_controller.wq),
-};
-
 struct omap_nand_info {
 	struct nand_chip		nand;
 	struct platform_device		*pdev;
@@ -1915,106 +1909,26 @@ static const struct mtd_ooblayout_ops omap_sw_ooblayout_ops = {
 	.free = omap_sw_ooblayout_free,
 };
 
-static int omap_nand_probe(struct platform_device *pdev)
+static int omap_nand_attach_chip(struct nand_chip *chip)
 {
-	struct omap_nand_info		*info;
-	struct mtd_info			*mtd;
-	struct nand_chip		*nand_chip;
-	int				err;
-	dma_cap_mask_t			mask;
-	struct resource			*res;
-	struct device			*dev = &pdev->dev;
-	int				min_oobbytes = BADBLOCK_MARKER_LENGTH;
-	int				oobbytes_per_step;
-
-	info = devm_kzalloc(&pdev->dev, sizeof(struct omap_nand_info),
-				GFP_KERNEL);
-	if (!info)
-		return -ENOMEM;
-
-	info->pdev = pdev;
-
-	err = omap_get_dt_info(dev, info);
-	if (err)
-		return err;
-
-	info->ops = gpmc_omap_get_nand_ops(&info->reg, info->gpmc_cs);
-	if (!info->ops) {
-		dev_err(&pdev->dev, "Failed to get GPMC->NAND interface\n");
-		return -ENODEV;
-	}
-
-	nand_chip		= &info->nand;
-	mtd			= nand_to_mtd(nand_chip);
-	mtd->dev.parent		= &pdev->dev;
-	nand_chip->ecc.priv	= NULL;
-	nand_set_flash_node(nand_chip, dev->of_node);
-
-	if (!mtd->name) {
-		mtd->name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
-					   "omap2-nand.%d", info->gpmc_cs);
-		if (!mtd->name) {
-			dev_err(&pdev->dev, "Failed to set MTD name\n");
-			return -ENOMEM;
-		}
-	}
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	nand_chip->IO_ADDR_R = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(nand_chip->IO_ADDR_R))
-		return PTR_ERR(nand_chip->IO_ADDR_R);
-
-	info->phys_base = res->start;
-
-	nand_chip->controller = &omap_gpmc_controller;
-
-	nand_chip->IO_ADDR_W = nand_chip->IO_ADDR_R;
-	nand_chip->cmd_ctrl  = omap_hwcontrol;
-
-	info->ready_gpiod = devm_gpiod_get_optional(&pdev->dev, "rb",
-						    GPIOD_IN);
-	if (IS_ERR(info->ready_gpiod)) {
-		dev_err(dev, "failed to get ready gpio\n");
-		return PTR_ERR(info->ready_gpiod);
-	}
-
-	/*
-	 * If RDY/BSY line is connected to OMAP then use the omap ready
-	 * function and the generic nand_wait function which reads the status
-	 * register after monitoring the RDY/BSY line. Otherwise use a standard
-	 * chip delay which is slightly more than tR (AC Timing) of the NAND
-	 * device and read status register until you get a failure or success
-	 */
-	if (info->ready_gpiod) {
-		nand_chip->dev_ready = omap_dev_ready;
-		nand_chip->chip_delay = 0;
-	} else {
-		nand_chip->waitfunc = omap_wait;
-		nand_chip->chip_delay = 50;
-	}
-
-	if (info->flash_bbt)
-		nand_chip->bbt_options |= NAND_BBT_USE_FLASH;
-
-	/* scan NAND device connected to chip controller */
-	nand_chip->options |= info->devsize & NAND_BUSWIDTH_16;
-	err = nand_scan_ident(mtd, 1, NULL);
-	if (err) {
-		dev_err(&info->pdev->dev,
-			"scan failed, may be bus-width mismatch\n");
-		goto return_error;
-	}
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct omap_nand_info *info = mtd_to_omap(mtd);
+	struct device *dev = &info->pdev->dev;
+	int min_oobbytes = BADBLOCK_MARKER_LENGTH;
+	int oobbytes_per_step;
+	dma_cap_mask_t mask;
+	int err;
 
-	if (nand_chip->bbt_options & NAND_BBT_USE_FLASH)
-		nand_chip->bbt_options |= NAND_BBT_NO_OOB;
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
 	else
-		nand_chip->options |= NAND_SKIP_BBTSCAN;
+		chip->options |= NAND_SKIP_BBTSCAN;
 
-	/* re-populate low-level callbacks based on xfer modes */
+	/* Re-populate low-level callbacks based on xfer modes */
 	switch (info->xfer_type) {
 	case NAND_OMAP_PREFETCH_POLLED:
-		nand_chip->read_buf   = omap_read_buf_pref;
-		nand_chip->write_buf  = omap_write_buf_pref;
+		chip->read_buf = omap_read_buf_pref;
+		chip->write_buf = omap_write_buf_pref;
 		break;
 
 	case NAND_OMAP_POLLED:
@@ -2024,12 +1938,11 @@ static int omap_nand_probe(struct platform_device *pdev)
 	case NAND_OMAP_PREFETCH_DMA:
 		dma_cap_zero(mask);
 		dma_cap_set(DMA_SLAVE, mask);
-		info->dma = dma_request_chan(pdev->dev.parent, "rxtx");
+		info->dma = dma_request_chan(dev, "rxtx");
 
 		if (IS_ERR(info->dma)) {
-			dev_err(&pdev->dev, "DMA engine request failed\n");
-			err = PTR_ERR(info->dma);
-			goto return_error;
+			dev_err(dev, "DMA engine request failed\n");
+			return PTR_ERR(info->dma);
 		} else {
 			struct dma_slave_config cfg;
 
@@ -2042,222 +1955,306 @@ static int omap_nand_probe(struct platform_device *pdev)
 			cfg.dst_maxburst = 16;
 			err = dmaengine_slave_config(info->dma, &cfg);
 			if (err) {
-				dev_err(&pdev->dev, "DMA engine slave config failed: %d\n",
+				dev_err(dev,
+					"DMA engine slave config failed: %d\n",
 					err);
-				goto return_error;
+				return err;
 			}
-			nand_chip->read_buf   = omap_read_buf_dma_pref;
-			nand_chip->write_buf  = omap_write_buf_dma_pref;
+			chip->read_buf = omap_read_buf_dma_pref;
+			chip->write_buf = omap_write_buf_dma_pref;
 		}
 		break;
 
 	case NAND_OMAP_PREFETCH_IRQ:
-		info->gpmc_irq_fifo = platform_get_irq(pdev, 0);
+		info->gpmc_irq_fifo = platform_get_irq(info->pdev, 0);
 		if (info->gpmc_irq_fifo <= 0) {
-			dev_err(&pdev->dev, "error getting fifo irq\n");
-			err = -ENODEV;
-			goto return_error;
+			dev_err(dev, "Error getting fifo IRQ\n");
+			return -ENODEV;
 		}
-		err = devm_request_irq(&pdev->dev, info->gpmc_irq_fifo,
-					omap_nand_irq, IRQF_SHARED,
-					"gpmc-nand-fifo", info);
+		err = devm_request_irq(dev, info->gpmc_irq_fifo,
+				       omap_nand_irq, IRQF_SHARED,
+				       "gpmc-nand-fifo", info);
 		if (err) {
-			dev_err(&pdev->dev, "requesting irq(%d) error:%d",
-						info->gpmc_irq_fifo, err);
+			dev_err(dev, "Requesting IRQ %d, error %d\n",
+				info->gpmc_irq_fifo, err);
 			info->gpmc_irq_fifo = 0;
-			goto return_error;
+			return err;
 		}
 
-		info->gpmc_irq_count = platform_get_irq(pdev, 1);
+		info->gpmc_irq_count = platform_get_irq(info->pdev, 1);
 		if (info->gpmc_irq_count <= 0) {
-			dev_err(&pdev->dev, "error getting count irq\n");
-			err = -ENODEV;
-			goto return_error;
+			dev_err(dev, "Error getting IRQ count\n");
+			return -ENODEV;
 		}
-		err = devm_request_irq(&pdev->dev, info->gpmc_irq_count,
-					omap_nand_irq, IRQF_SHARED,
-					"gpmc-nand-count", info);
+		err = devm_request_irq(dev, info->gpmc_irq_count,
+				       omap_nand_irq, IRQF_SHARED,
+				       "gpmc-nand-count", info);
 		if (err) {
-			dev_err(&pdev->dev, "requesting irq(%d) error:%d",
-						info->gpmc_irq_count, err);
+			dev_err(dev, "Requesting IRQ %d, error %d\n",
+				info->gpmc_irq_count, err);
 			info->gpmc_irq_count = 0;
-			goto return_error;
+			return err;
 		}
 
-		nand_chip->read_buf  = omap_read_buf_irq_pref;
-		nand_chip->write_buf = omap_write_buf_irq_pref;
+		chip->read_buf = omap_read_buf_irq_pref;
+		chip->write_buf = omap_write_buf_irq_pref;
 
 		break;
 
 	default:
-		dev_err(&pdev->dev,
-			"xfer_type(%d) not supported!\n", info->xfer_type);
-		err = -EINVAL;
-		goto return_error;
+		dev_err(dev, "xfer_type %d not supported!\n", info->xfer_type);
+		return -EINVAL;
 	}
 
-	if (!omap2_nand_ecc_check(info)) {
-		err = -EINVAL;
-		goto return_error;
-	}
+	if (!omap2_nand_ecc_check(info))
+		return -EINVAL;
 
 	/*
 	 * Bail out earlier to let NAND_ECC_SOFT code create its own
 	 * ooblayout instead of using ours.
 	 */
 	if (info->ecc_opt == OMAP_ECC_HAM1_CODE_SW) {
-		nand_chip->ecc.mode = NAND_ECC_SOFT;
-		nand_chip->ecc.algo = NAND_ECC_HAMMING;
-		goto scan_tail;
+		chip->ecc.mode = NAND_ECC_SOFT;
+		chip->ecc.algo = NAND_ECC_HAMMING;
+		return 0;
 	}
 
-	/* populate MTD interface based on ECC scheme */
+	/* Populate MTD interface based on ECC scheme */
 	switch (info->ecc_opt) {
 	case OMAP_ECC_HAM1_CODE_HW:
-		pr_info("nand: using OMAP_ECC_HAM1_CODE_HW\n");
-		nand_chip->ecc.mode             = NAND_ECC_HW;
-		nand_chip->ecc.bytes            = 3;
-		nand_chip->ecc.size             = 512;
-		nand_chip->ecc.strength         = 1;
-		nand_chip->ecc.calculate        = omap_calculate_ecc;
-		nand_chip->ecc.hwctl            = omap_enable_hwecc;
-		nand_chip->ecc.correct          = omap_correct_data;
+		dev_info(dev, "nand: using OMAP_ECC_HAM1_CODE_HW\n");
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.bytes		= 3;
+		chip->ecc.size		= 512;
+		chip->ecc.strength	= 1;
+		chip->ecc.calculate	= omap_calculate_ecc;
+		chip->ecc.hwctl		= omap_enable_hwecc;
+		chip->ecc.correct	= omap_correct_data;
 		mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
-		oobbytes_per_step		= nand_chip->ecc.bytes;
+		oobbytes_per_step	= chip->ecc.bytes;
 
-		if (!(nand_chip->options & NAND_BUSWIDTH_16))
-			min_oobbytes		= 1;
+		if (!(chip->options & NAND_BUSWIDTH_16))
+			min_oobbytes	= 1;
 
 		break;
 
 	case OMAP_ECC_BCH4_CODE_HW_DETECTION_SW:
 		pr_info("nand: using OMAP_ECC_BCH4_CODE_HW_DETECTION_SW\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
-		nand_chip->ecc.bytes		= 7;
-		nand_chip->ecc.strength		= 4;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= nand_bch_correct_data;
-		nand_chip->ecc.calculate	= omap_calculate_ecc_bch_sw;
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
+		chip->ecc.bytes		= 7;
+		chip->ecc.strength	= 4;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= nand_bch_correct_data;
+		chip->ecc.calculate	= omap_calculate_ecc_bch_sw;
 		mtd_set_ooblayout(mtd, &omap_sw_ooblayout_ops);
 		/* Reserve one byte for the OMAP marker */
-		oobbytes_per_step		= nand_chip->ecc.bytes + 1;
-		/* software bch library is used for locating errors */
-		nand_chip->ecc.priv		= nand_bch_init(mtd);
-		if (!nand_chip->ecc.priv) {
-			dev_err(&info->pdev->dev, "unable to use BCH library\n");
-			err = -EINVAL;
-			goto return_error;
+		oobbytes_per_step	= chip->ecc.bytes + 1;
+		/* Software BCH library is used for locating errors */
+		chip->ecc.priv		= nand_bch_init(mtd);
+		if (!chip->ecc.priv) {
+			dev_err(dev, "Unable to use BCH library\n");
+			return -EINVAL;
 		}
 		break;
 
 	case OMAP_ECC_BCH4_CODE_HW:
 		pr_info("nand: using OMAP_ECC_BCH4_CODE_HW ECC scheme\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
 		/* 14th bit is kept reserved for ROM-code compatibility */
-		nand_chip->ecc.bytes		= 7 + 1;
-		nand_chip->ecc.strength		= 4;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= omap_elm_correct_data;
-		nand_chip->ecc.read_page	= omap_read_page_bch;
-		nand_chip->ecc.write_page	= omap_write_page_bch;
-		nand_chip->ecc.write_subpage	= omap_write_subpage_bch;
+		chip->ecc.bytes		= 7 + 1;
+		chip->ecc.strength	= 4;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= omap_elm_correct_data;
+		chip->ecc.read_page	= omap_read_page_bch;
+		chip->ecc.write_page	= omap_write_page_bch;
+		chip->ecc.write_subpage	= omap_write_subpage_bch;
 		mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
-		oobbytes_per_step		= nand_chip->ecc.bytes;
+		oobbytes_per_step	= chip->ecc.bytes;
 
 		err = elm_config(info->elm_dev, BCH4_ECC,
-				 mtd->writesize / nand_chip->ecc.size,
-				 nand_chip->ecc.size, nand_chip->ecc.bytes);
+				 mtd->writesize / chip->ecc.size,
+				 chip->ecc.size, chip->ecc.bytes);
 		if (err < 0)
-			goto return_error;
+			return err;
 		break;
 
 	case OMAP_ECC_BCH8_CODE_HW_DETECTION_SW:
 		pr_info("nand: using OMAP_ECC_BCH8_CODE_HW_DETECTION_SW\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
-		nand_chip->ecc.bytes		= 13;
-		nand_chip->ecc.strength		= 8;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= nand_bch_correct_data;
-		nand_chip->ecc.calculate	= omap_calculate_ecc_bch_sw;
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
+		chip->ecc.bytes		= 13;
+		chip->ecc.strength	= 8;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= nand_bch_correct_data;
+		chip->ecc.calculate	= omap_calculate_ecc_bch_sw;
 		mtd_set_ooblayout(mtd, &omap_sw_ooblayout_ops);
 		/* Reserve one byte for the OMAP marker */
-		oobbytes_per_step		= nand_chip->ecc.bytes + 1;
-		/* software bch library is used for locating errors */
-		nand_chip->ecc.priv		= nand_bch_init(mtd);
-		if (!nand_chip->ecc.priv) {
-			dev_err(&info->pdev->dev, "unable to use BCH library\n");
-			err = -EINVAL;
-			goto return_error;
+		oobbytes_per_step	= chip->ecc.bytes + 1;
+		/* Software BCH library is used for locating errors */
+		chip->ecc.priv		= nand_bch_init(mtd);
+		if (!chip->ecc.priv) {
+			dev_err(dev, "unable to use BCH library\n");
+			return -EINVAL;
 		}
 		break;
 
 	case OMAP_ECC_BCH8_CODE_HW:
 		pr_info("nand: using OMAP_ECC_BCH8_CODE_HW ECC scheme\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
 		/* 14th bit is kept reserved for ROM-code compatibility */
-		nand_chip->ecc.bytes		= 13 + 1;
-		nand_chip->ecc.strength		= 8;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= omap_elm_correct_data;
-		nand_chip->ecc.read_page	= omap_read_page_bch;
-		nand_chip->ecc.write_page	= omap_write_page_bch;
-		nand_chip->ecc.write_subpage	= omap_write_subpage_bch;
+		chip->ecc.bytes		= 13 + 1;
+		chip->ecc.strength	= 8;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= omap_elm_correct_data;
+		chip->ecc.read_page	= omap_read_page_bch;
+		chip->ecc.write_page	= omap_write_page_bch;
+		chip->ecc.write_subpage	= omap_write_subpage_bch;
 		mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
-		oobbytes_per_step		= nand_chip->ecc.bytes;
+		oobbytes_per_step	= chip->ecc.bytes;
 
 		err = elm_config(info->elm_dev, BCH8_ECC,
-				 mtd->writesize / nand_chip->ecc.size,
-				 nand_chip->ecc.size, nand_chip->ecc.bytes);
+				 mtd->writesize / chip->ecc.size,
+				 chip->ecc.size, chip->ecc.bytes);
 		if (err < 0)
-			goto return_error;
+			return err;
 
 		break;
 
 	case OMAP_ECC_BCH16_CODE_HW:
-		pr_info("using OMAP_ECC_BCH16_CODE_HW ECC scheme\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
-		nand_chip->ecc.bytes		= 26;
-		nand_chip->ecc.strength		= 16;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= omap_elm_correct_data;
-		nand_chip->ecc.read_page	= omap_read_page_bch;
-		nand_chip->ecc.write_page	= omap_write_page_bch;
-		nand_chip->ecc.write_subpage	= omap_write_subpage_bch;
+		pr_info("Using OMAP_ECC_BCH16_CODE_HW ECC scheme\n");
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
+		chip->ecc.bytes		= 26;
+		chip->ecc.strength	= 16;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= omap_elm_correct_data;
+		chip->ecc.read_page	= omap_read_page_bch;
+		chip->ecc.write_page	= omap_write_page_bch;
+		chip->ecc.write_subpage	= omap_write_subpage_bch;
 		mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
-		oobbytes_per_step		= nand_chip->ecc.bytes;
+		oobbytes_per_step	= chip->ecc.bytes;
 
 		err = elm_config(info->elm_dev, BCH16_ECC,
-				 mtd->writesize / nand_chip->ecc.size,
-				 nand_chip->ecc.size, nand_chip->ecc.bytes);
+				 mtd->writesize / chip->ecc.size,
+				 chip->ecc.size, chip->ecc.bytes);
 		if (err < 0)
-			goto return_error;
+			return err;
 
 		break;
 	default:
-		dev_err(&info->pdev->dev, "invalid or unsupported ECC scheme\n");
-		err = -EINVAL;
-		goto return_error;
+		dev_err(dev, "Invalid or unsupported ECC scheme\n");
+		return -EINVAL;
 	}
 
-	/* check if NAND device's OOB is enough to store ECC signatures */
+	/* Check if NAND device's OOB is enough to store ECC signatures */
 	min_oobbytes += (oobbytes_per_step *
-			 (mtd->writesize / nand_chip->ecc.size));
+			 (mtd->writesize / chip->ecc.size));
 	if (mtd->oobsize < min_oobbytes) {
-		dev_err(&info->pdev->dev,
-			"not enough OOB bytes required = %d, available=%d\n",
+		dev_err(dev,
+			"Not enough OOB bytes: required = %d, available=%d\n",
 			min_oobbytes, mtd->oobsize);
-		err = -EINVAL;
-		goto return_error;
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops omap_nand_controller_ops = {
+	.attach_chip = omap_nand_attach_chip,
+};
+
+/* Shared among all NAND instances to synchronize access to the ECC Engine */
+static struct nand_controller omap_gpmc_controller = {
+	.lock = __SPIN_LOCK_UNLOCKED(omap_gpmc_controller.lock),
+	.wq = __WAIT_QUEUE_HEAD_INITIALIZER(omap_gpmc_controller.wq),
+	.ops = &omap_nand_controller_ops,
+};
+
+static int omap_nand_probe(struct platform_device *pdev)
+{
+	struct omap_nand_info		*info;
+	struct mtd_info			*mtd;
+	struct nand_chip		*nand_chip;
+	int				err;
+	struct resource			*res;
+	struct device			*dev = &pdev->dev;
+
+	info = devm_kzalloc(&pdev->dev, sizeof(struct omap_nand_info),
+				GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->pdev = pdev;
+
+	err = omap_get_dt_info(dev, info);
+	if (err)
+		return err;
+
+	info->ops = gpmc_omap_get_nand_ops(&info->reg, info->gpmc_cs);
+	if (!info->ops) {
+		dev_err(&pdev->dev, "Failed to get GPMC->NAND interface\n");
+		return -ENODEV;
 	}
 
-scan_tail:
-	/* second phase scan */
-	err = nand_scan_tail(mtd);
+	nand_chip		= &info->nand;
+	mtd			= nand_to_mtd(nand_chip);
+	mtd->dev.parent		= &pdev->dev;
+	nand_chip->ecc.priv	= NULL;
+	nand_set_flash_node(nand_chip, dev->of_node);
+
+	if (!mtd->name) {
+		mtd->name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+					   "omap2-nand.%d", info->gpmc_cs);
+		if (!mtd->name) {
+			dev_err(&pdev->dev, "Failed to set MTD name\n");
+			return -ENOMEM;
+		}
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	nand_chip->IO_ADDR_R = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(nand_chip->IO_ADDR_R))
+		return PTR_ERR(nand_chip->IO_ADDR_R);
+
+	info->phys_base = res->start;
+
+	nand_chip->controller = &omap_gpmc_controller;
+
+	nand_chip->IO_ADDR_W = nand_chip->IO_ADDR_R;
+	nand_chip->cmd_ctrl  = omap_hwcontrol;
+
+	info->ready_gpiod = devm_gpiod_get_optional(&pdev->dev, "rb",
+						    GPIOD_IN);
+	if (IS_ERR(info->ready_gpiod)) {
+		dev_err(dev, "failed to get ready gpio\n");
+		return PTR_ERR(info->ready_gpiod);
+	}
+
+	/*
+	 * If RDY/BSY line is connected to OMAP then use the omap ready
+	 * function and the generic nand_wait function which reads the status
+	 * register after monitoring the RDY/BSY line. Otherwise use a standard
+	 * chip delay which is slightly more than tR (AC Timing) of the NAND
+	 * device and read status register until you get a failure or success
+	 */
+	if (info->ready_gpiod) {
+		nand_chip->dev_ready = omap_dev_ready;
+		nand_chip->chip_delay = 0;
+	} else {
+		nand_chip->waitfunc = omap_wait;
+		nand_chip->chip_delay = 50;
+	}
+
+	if (info->flash_bbt)
+		nand_chip->bbt_options |= NAND_BBT_USE_FLASH;
+
+	/* scan NAND device connected to chip controller */
+	nand_chip->options |= info->devsize & NAND_BUSWIDTH_16;
+
+	err = nand_scan(mtd, 1);
 	if (err)
 		goto return_error;
 
diff --git a/drivers/mtd/nand/raw/orion_nand.c b/drivers/mtd/nand/raw/orion_nand.c
index 7825fd3ce66b..52d435285a3f 100644
--- a/drivers/mtd/nand/raw/orion_nand.c
+++ b/drivers/mtd/nand/raw/orion_nand.c
@@ -18,7 +18,7 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/io.h>
-#include <asm/sizes.h>
+#include <linux/sizes.h>
 #include <linux/platform_data/mtd-orion_nand.h>
 
 struct orion_nand_info {
@@ -52,7 +52,7 @@ static void orion_nand_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	void __iomem *io_base = chip->IO_ADDR_R;
-#if __LINUX_ARM_ARCH__ >= 5
+#if defined(__LINUX_ARM_ARCH__) && __LINUX_ARM_ARCH__ >= 5
 	uint64_t *buf64;
 #endif
 	int i = 0;
@@ -61,7 +61,7 @@ static void orion_nand_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 		*buf++ = readb(io_base);
 		len--;
 	}
-#if __LINUX_ARM_ARCH__ >= 5
+#if defined(__LINUX_ARM_ARCH__) && __LINUX_ARM_ARCH__ >= 5
 	buf64 = (uint64_t *)buf;
 	while (i < len/8) {
 		/*
@@ -153,9 +153,6 @@ static int __init orion_nand_probe(struct platform_device *pdev)
 	if (board->width == 16)
 		nc->options |= NAND_BUSWIDTH_16;
 
-	if (board->dev_ready)
-		nc->dev_ready = board->dev_ready;
-
 	platform_set_drvdata(pdev, info);
 
 	/* Not all platforms can gate the clock, so it is not
diff --git a/drivers/mtd/nand/raw/oxnas_nand.c b/drivers/mtd/nand/raw/oxnas_nand.c
index d649d5944826..01b00bb69c1e 100644
--- a/drivers/mtd/nand/raw/oxnas_nand.c
+++ b/drivers/mtd/nand/raw/oxnas_nand.c
@@ -32,7 +32,7 @@
 #define OXNAS_NAND_MAX_CHIPS	1
 
 struct oxnas_nand_ctrl {
-	struct nand_hw_control base;
+	struct nand_controller base;
 	void __iomem *io_base;
 	struct clk *clk;
 	struct nand_chip *chips[OXNAS_NAND_MAX_CHIPS];
@@ -96,7 +96,7 @@ static int oxnas_nand_probe(struct platform_device *pdev)
 	if (!oxnas)
 		return -ENOMEM;
 
-	nand_hw_control_init(&oxnas->base);
+	nand_controller_init(&oxnas->base);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	oxnas->io_base = devm_ioremap_resource(&pdev->dev, res);
diff --git a/drivers/mtd/nand/raw/plat_nand.c b/drivers/mtd/nand/raw/plat_nand.c
index 925a1323604d..222626df4b96 100644
--- a/drivers/mtd/nand/raw/plat_nand.c
+++ b/drivers/mtd/nand/raw/plat_nand.c
@@ -67,12 +67,10 @@ static int plat_nand_probe(struct platform_device *pdev)
 	data->chip.select_chip = pdata->ctrl.select_chip;
 	data->chip.write_buf = pdata->ctrl.write_buf;
 	data->chip.read_buf = pdata->ctrl.read_buf;
-	data->chip.read_byte = pdata->ctrl.read_byte;
 	data->chip.chip_delay = pdata->chip.chip_delay;
 	data->chip.options |= pdata->chip.options;
 	data->chip.bbt_options |= pdata->chip.bbt_options;
 
-	data->chip.ecc.hwctl = pdata->ctrl.hwcontrol;
 	data->chip.ecc.mode = NAND_ECC_SOFT;
 	data->chip.ecc.algo = NAND_ECC_HAMMING;
 
diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index 6a5519f0ff25..d1d470bb32e4 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -213,6 +213,8 @@ nandc_set_reg(nandc, NAND_READ_LOCATION_##reg,			\
 #define QPIC_PER_CW_CMD_SGL		32
 #define QPIC_PER_CW_DATA_SGL		8
 
+#define QPIC_NAND_COMPLETION_TIMEOUT	msecs_to_jiffies(2000)
+
 /*
  * Flags used in DMA descriptor preparation helper functions
  * (i.e. read_reg_dma/write_reg_dma/read_data_dma/write_data_dma)
@@ -245,6 +247,11 @@ nandc_set_reg(nandc, NAND_READ_LOCATION_##reg,			\
  * @tx_sgl_start - start index in data sgl for tx.
  * @rx_sgl_pos - current index in data sgl for rx.
  * @rx_sgl_start - start index in data sgl for rx.
+ * @wait_second_completion - wait for second DMA desc completion before making
+ *			     the NAND transfer completion.
+ * @txn_done - completion for NAND transfer.
+ * @last_data_desc - last DMA desc in data channel (tx/rx).
+ * @last_cmd_desc - last DMA desc in command channel.
  */
 struct bam_transaction {
 	struct bam_cmd_element *bam_ce;
@@ -258,6 +265,10 @@ struct bam_transaction {
 	u32 tx_sgl_start;
 	u32 rx_sgl_pos;
 	u32 rx_sgl_start;
+	bool wait_second_completion;
+	struct completion txn_done;
+	struct dma_async_tx_descriptor *last_data_desc;
+	struct dma_async_tx_descriptor *last_cmd_desc;
 };
 
 /*
@@ -354,7 +365,7 @@ struct nandc_regs {
  *				from all connected NAND devices pagesize
  */
 struct qcom_nand_controller {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct list_head host_list;
 
 	struct device *dev;
@@ -504,6 +515,8 @@ alloc_bam_transaction(struct qcom_nand_controller *nandc)
 
 	bam_txn->data_sgl = bam_txn_buf;
 
+	init_completion(&bam_txn->txn_done);
+
 	return bam_txn;
 }
 
@@ -523,11 +536,33 @@ static void clear_bam_transaction(struct qcom_nand_controller *nandc)
 	bam_txn->tx_sgl_start = 0;
 	bam_txn->rx_sgl_pos = 0;
 	bam_txn->rx_sgl_start = 0;
+	bam_txn->last_data_desc = NULL;
+	bam_txn->wait_second_completion = false;
 
 	sg_init_table(bam_txn->cmd_sgl, nandc->max_cwperpage *
 		      QPIC_PER_CW_CMD_SGL);
 	sg_init_table(bam_txn->data_sgl, nandc->max_cwperpage *
 		      QPIC_PER_CW_DATA_SGL);
+
+	reinit_completion(&bam_txn->txn_done);
+}
+
+/* Callback for DMA descriptor completion */
+static void qpic_bam_dma_done(void *data)
+{
+	struct bam_transaction *bam_txn = data;
+
+	/*
+	 * In case of data transfer with NAND, 2 callbacks will be generated.
+	 * One for command channel and another one for data channel.
+	 * If current transaction has data descriptors
+	 * (i.e. wait_second_completion is true), then set this to false
+	 * and wait for second DMA descriptor completion.
+	 */
+	if (bam_txn->wait_second_completion)
+		bam_txn->wait_second_completion = false;
+	else
+		complete(&bam_txn->txn_done);
 }
 
 static inline struct qcom_nand_host *to_qcom_nand_host(struct nand_chip *chip)
@@ -756,6 +791,12 @@ static int prepare_bam_async_desc(struct qcom_nand_controller *nandc,
 
 	desc->dma_desc = dma_desc;
 
+	/* update last data/command descriptor */
+	if (chan == nandc->cmd_chan)
+		bam_txn->last_cmd_desc = dma_desc;
+	else
+		bam_txn->last_data_desc = dma_desc;
+
 	list_add_tail(&desc->node, &nandc->desc_list);
 
 	return 0;
@@ -1055,7 +1096,8 @@ static void config_nand_page_read(struct qcom_nand_controller *nandc)
  * Helper to prepare DMA descriptors for configuring registers
  * before reading each codeword in NAND page.
  */
-static void config_nand_cw_read(struct qcom_nand_controller *nandc)
+static void
+config_nand_cw_read(struct qcom_nand_controller *nandc, bool use_ecc)
 {
 	if (nandc->props->is_bam)
 		write_reg_dma(nandc, NAND_READ_LOCATION_0, 4,
@@ -1064,19 +1106,25 @@ static void config_nand_cw_read(struct qcom_nand_controller *nandc)
 	write_reg_dma(nandc, NAND_FLASH_CMD, 1, NAND_BAM_NEXT_SGL);
 	write_reg_dma(nandc, NAND_EXEC_CMD, 1, NAND_BAM_NEXT_SGL);
 
-	read_reg_dma(nandc, NAND_FLASH_STATUS, 2, 0);
-	read_reg_dma(nandc, NAND_ERASED_CW_DETECT_STATUS, 1,
-		     NAND_BAM_NEXT_SGL);
+	if (use_ecc) {
+		read_reg_dma(nandc, NAND_FLASH_STATUS, 2, 0);
+		read_reg_dma(nandc, NAND_ERASED_CW_DETECT_STATUS, 1,
+			     NAND_BAM_NEXT_SGL);
+	} else {
+		read_reg_dma(nandc, NAND_FLASH_STATUS, 1, NAND_BAM_NEXT_SGL);
+	}
 }
 
 /*
  * Helper to prepare dma descriptors to configure registers needed for reading a
  * single codeword in page
  */
-static void config_nand_single_cw_page_read(struct qcom_nand_controller *nandc)
+static void
+config_nand_single_cw_page_read(struct qcom_nand_controller *nandc,
+				bool use_ecc)
 {
 	config_nand_page_read(nandc);
-	config_nand_cw_read(nandc);
+	config_nand_cw_read(nandc, use_ecc);
 }
 
 /*
@@ -1157,7 +1205,7 @@ static int nandc_param(struct qcom_nand_host *host)
 	nandc->buf_count = 512;
 	memset(nandc->data_buffer, 0xff, nandc->buf_count);
 
-	config_nand_single_cw_page_read(nandc);
+	config_nand_single_cw_page_read(nandc, false);
 
 	read_data_dma(nandc, FLASH_BUF_ACC, nandc->data_buffer,
 		      nandc->buf_count, 0);
@@ -1273,10 +1321,20 @@ static int submit_descs(struct qcom_nand_controller *nandc)
 		cookie = dmaengine_submit(desc->dma_desc);
 
 	if (nandc->props->is_bam) {
+		bam_txn->last_cmd_desc->callback = qpic_bam_dma_done;
+		bam_txn->last_cmd_desc->callback_param = bam_txn;
+		if (bam_txn->last_data_desc) {
+			bam_txn->last_data_desc->callback = qpic_bam_dma_done;
+			bam_txn->last_data_desc->callback_param = bam_txn;
+			bam_txn->wait_second_completion = true;
+		}
+
 		dma_async_issue_pending(nandc->tx_chan);
 		dma_async_issue_pending(nandc->rx_chan);
+		dma_async_issue_pending(nandc->cmd_chan);
 
-		if (dma_sync_wait(nandc->cmd_chan, cookie) != DMA_COMPLETE)
+		if (!wait_for_completion_timeout(&bam_txn->txn_done,
+						 QPIC_NAND_COMPLETION_TIMEOUT))
 			return -ETIMEDOUT;
 	} else {
 		if (dma_sync_wait(nandc->chan, cookie) != DMA_COMPLETE)
@@ -1512,20 +1570,180 @@ struct read_stats {
 	__le32 erased_cw;
 };
 
+/* reads back FLASH_STATUS register set by the controller */
+static int check_flash_errors(struct qcom_nand_host *host, int cw_cnt)
+{
+	struct nand_chip *chip = &host->chip;
+	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
+	int i;
+
+	for (i = 0; i < cw_cnt; i++) {
+		u32 flash = le32_to_cpu(nandc->reg_read_buf[i]);
+
+		if (flash & (FS_OP_ERR | FS_MPU_ERR))
+			return -EIO;
+	}
+
+	return 0;
+}
+
+/* performs raw read for one codeword */
+static int
+qcom_nandc_read_cw_raw(struct mtd_info *mtd, struct nand_chip *chip,
+		       u8 *data_buf, u8 *oob_buf, int page, int cw)
+{
+	struct qcom_nand_host *host = to_qcom_nand_host(chip);
+	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
+	struct nand_ecc_ctrl *ecc = &chip->ecc;
+	int data_size1, data_size2, oob_size1, oob_size2;
+	int ret, reg_off = FLASH_BUF_ACC, read_loc = 0;
+
+	nand_read_page_op(chip, page, 0, NULL, 0);
+	host->use_ecc = false;
+
+	clear_bam_transaction(nandc);
+	set_address(host, host->cw_size * cw, page);
+	update_rw_regs(host, 1, true);
+	config_nand_page_read(nandc);
+
+	data_size1 = mtd->writesize - host->cw_size * (ecc->steps - 1);
+	oob_size1 = host->bbm_size;
+
+	if (cw == (ecc->steps - 1)) {
+		data_size2 = ecc->size - data_size1 -
+			     ((ecc->steps - 1) * 4);
+		oob_size2 = (ecc->steps * 4) + host->ecc_bytes_hw +
+			    host->spare_bytes;
+	} else {
+		data_size2 = host->cw_data - data_size1;
+		oob_size2 = host->ecc_bytes_hw + host->spare_bytes;
+	}
+
+	if (nandc->props->is_bam) {
+		nandc_set_read_loc(nandc, 0, read_loc, data_size1, 0);
+		read_loc += data_size1;
+
+		nandc_set_read_loc(nandc, 1, read_loc, oob_size1, 0);
+		read_loc += oob_size1;
+
+		nandc_set_read_loc(nandc, 2, read_loc, data_size2, 0);
+		read_loc += data_size2;
+
+		nandc_set_read_loc(nandc, 3, read_loc, oob_size2, 1);
+	}
+
+	config_nand_cw_read(nandc, false);
+
+	read_data_dma(nandc, reg_off, data_buf, data_size1, 0);
+	reg_off += data_size1;
+
+	read_data_dma(nandc, reg_off, oob_buf, oob_size1, 0);
+	reg_off += oob_size1;
+
+	read_data_dma(nandc, reg_off, data_buf + data_size1, data_size2, 0);
+	reg_off += data_size2;
+
+	read_data_dma(nandc, reg_off, oob_buf + oob_size1, oob_size2, 0);
+
+	ret = submit_descs(nandc);
+	free_descs(nandc);
+	if (ret) {
+		dev_err(nandc->dev, "failure to read raw cw %d\n", cw);
+		return ret;
+	}
+
+	return check_flash_errors(host, 1);
+}
+
+/*
+ * Bitflips can happen in erased codewords also so this function counts the
+ * number of 0 in each CW for which ECC engine returns the uncorrectable
+ * error. The page will be assumed as erased if this count is less than or
+ * equal to the ecc->strength for each CW.
+ *
+ * 1. Both DATA and OOB need to be checked for number of 0. The
+ *    top-level API can be called with only data buf or OOB buf so use
+ *    chip->data_buf if data buf is null and chip->oob_poi if oob buf
+ *    is null for copying the raw bytes.
+ * 2. Perform raw read for all the CW which has uncorrectable errors.
+ * 3. For each CW, check the number of 0 in cw_data and usable OOB bytes.
+ *    The BBM and spare bytes bit flip won’t affect the ECC so don’t check
+ *    the number of bitflips in this area.
+ */
+static int
+check_for_erased_page(struct qcom_nand_host *host, u8 *data_buf,
+		      u8 *oob_buf, unsigned long uncorrectable_cws,
+		      int page, unsigned int max_bitflips)
+{
+	struct nand_chip *chip = &host->chip;
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct nand_ecc_ctrl *ecc = &chip->ecc;
+	u8 *cw_data_buf, *cw_oob_buf;
+	int cw, data_size, oob_size, ret = 0;
+
+	if (!data_buf) {
+		data_buf = chip->data_buf;
+		chip->pagebuf = -1;
+	}
+
+	if (!oob_buf) {
+		oob_buf = chip->oob_poi;
+		chip->pagebuf = -1;
+	}
+
+	for_each_set_bit(cw, &uncorrectable_cws, ecc->steps) {
+		if (cw == (ecc->steps - 1)) {
+			data_size = ecc->size - ((ecc->steps - 1) * 4);
+			oob_size = (ecc->steps * 4) + host->ecc_bytes_hw;
+		} else {
+			data_size = host->cw_data;
+			oob_size = host->ecc_bytes_hw;
+		}
+
+		/* determine starting buffer address for current CW */
+		cw_data_buf = data_buf + (cw * host->cw_data);
+		cw_oob_buf = oob_buf + (cw * ecc->bytes);
+
+		ret = qcom_nandc_read_cw_raw(mtd, chip, cw_data_buf,
+					     cw_oob_buf, page, cw);
+		if (ret)
+			return ret;
+
+		/*
+		 * make sure it isn't an erased page reported
+		 * as not-erased by HW because of a few bitflips
+		 */
+		ret = nand_check_erased_ecc_chunk(cw_data_buf, data_size,
+						  cw_oob_buf + host->bbm_size,
+						  oob_size, NULL,
+						  0, ecc->strength);
+		if (ret < 0) {
+			mtd->ecc_stats.failed++;
+		} else {
+			mtd->ecc_stats.corrected += ret;
+			max_bitflips = max_t(unsigned int, max_bitflips, ret);
+		}
+	}
+
+	return max_bitflips;
+}
+
 /*
  * reads back status registers set by the controller to notify page read
  * errors. this is equivalent to what 'ecc->correct()' would do.
  */
 static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
-			     u8 *oob_buf)
+			     u8 *oob_buf, int page)
 {
 	struct nand_chip *chip = &host->chip;
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
-	unsigned int max_bitflips = 0;
+	unsigned int max_bitflips = 0, uncorrectable_cws = 0;
 	struct read_stats *buf;
+	bool flash_op_err = false, erased;
 	int i;
+	u8 *data_buf_start = data_buf, *oob_buf_start = oob_buf;
 
 	buf = (struct read_stats *)nandc->reg_read_buf;
 	nandc_read_buffer_sync(nandc, true);
@@ -1546,48 +1764,49 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
 		buffer = le32_to_cpu(buf->buffer);
 		erased_cw = le32_to_cpu(buf->erased_cw);
 
-		if (flash & (FS_OP_ERR | FS_MPU_ERR)) {
-			bool erased;
-
-			/* ignore erased codeword errors */
+		/*
+		 * Check ECC failure for each codeword. ECC failure can
+		 * happen in either of the following conditions
+		 * 1. If number of bitflips are greater than ECC engine
+		 *    capability.
+		 * 2. If this codeword contains all 0xff for which erased
+		 *    codeword detection check will be done.
+		 */
+		if ((flash & FS_OP_ERR) && (buffer & BS_UNCORRECTABLE_BIT)) {
+			/*
+			 * For BCH ECC, ignore erased codeword errors, if
+			 * ERASED_CW bits are set.
+			 */
 			if (host->bch_enabled) {
 				erased = (erased_cw & ERASED_CW) == ERASED_CW ?
 					 true : false;
-			} else {
+			/*
+			 * For RS ECC, HW reports the erased CW by placing
+			 * special characters at certain offsets in the buffer.
+			 * These special characters will be valid only if
+			 * complete page is read i.e. data_buf is not NULL.
+			 */
+			} else if (data_buf) {
 				erased = erased_chunk_check_and_fixup(data_buf,
 								      data_len);
+			} else {
+				erased = false;
 			}
 
-			if (erased) {
-				data_buf += data_len;
-				if (oob_buf)
-					oob_buf += oob_len + ecc->bytes;
-				continue;
-			}
-
-			if (buffer & BS_UNCORRECTABLE_BIT) {
-				int ret, ecclen, extraooblen;
-				void *eccbuf;
-
-				eccbuf = oob_buf ? oob_buf + oob_len : NULL;
-				ecclen = oob_buf ? host->ecc_bytes_hw : 0;
-				extraooblen = oob_buf ? oob_len : 0;
-
-				/*
-				 * make sure it isn't an erased page reported
-				 * as not-erased by HW because of a few bitflips
-				 */
-				ret = nand_check_erased_ecc_chunk(data_buf,
-					data_len, eccbuf, ecclen, oob_buf,
-					extraooblen, ecc->strength);
-				if (ret < 0) {
-					mtd->ecc_stats.failed++;
-				} else {
-					mtd->ecc_stats.corrected += ret;
-					max_bitflips =
-						max_t(unsigned int, max_bitflips, ret);
-				}
-			}
+			if (!erased)
+				uncorrectable_cws |= BIT(i);
+		/*
+		 * Check if MPU or any other operational error (timeout,
+		 * device failure, etc.) happened for this codeword and
+		 * make flash_op_err true. If flash_op_err is set, then
+		 * EIO will be returned for page read.
+		 */
+		} else if (flash & (FS_OP_ERR | FS_MPU_ERR)) {
+			flash_op_err = true;
+		/*
+		 * No ECC or operational errors happened. Check the number of
+		 * bits corrected and update the ecc_stats.corrected.
+		 */
 		} else {
 			unsigned int stat;
 
@@ -1596,12 +1815,21 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
 			max_bitflips = max(max_bitflips, stat);
 		}
 
-		data_buf += data_len;
+		if (data_buf)
+			data_buf += data_len;
 		if (oob_buf)
 			oob_buf += oob_len + ecc->bytes;
 	}
 
-	return max_bitflips;
+	if (flash_op_err)
+		return -EIO;
+
+	if (!uncorrectable_cws)
+		return max_bitflips;
+
+	return check_for_erased_page(host, data_buf_start, oob_buf_start,
+				     uncorrectable_cws, page,
+				     max_bitflips);
 }
 
 /*
@@ -1609,11 +1837,12 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
  * ecc->read_oob()
  */
 static int read_page_ecc(struct qcom_nand_host *host, u8 *data_buf,
-			 u8 *oob_buf)
+			 u8 *oob_buf, int page)
 {
 	struct nand_chip *chip = &host->chip;
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
+	u8 *data_buf_start = data_buf, *oob_buf_start = oob_buf;
 	int i, ret;
 
 	config_nand_page_read(nandc);
@@ -1644,7 +1873,7 @@ static int read_page_ecc(struct qcom_nand_host *host, u8 *data_buf,
 			}
 		}
 
-		config_nand_cw_read(nandc);
+		config_nand_cw_read(nandc, true);
 
 		if (data_buf)
 			read_data_dma(nandc, FLASH_BUF_ACC, data_buf,
@@ -1674,12 +1903,14 @@ static int read_page_ecc(struct qcom_nand_host *host, u8 *data_buf,
 	}
 
 	ret = submit_descs(nandc);
-	if (ret)
-		dev_err(nandc->dev, "failure to read page/oob\n");
-
 	free_descs(nandc);
 
-	return ret;
+	if (ret) {
+		dev_err(nandc->dev, "failure to read page/oob\n");
+		return ret;
+	}
+
+	return parse_read_errors(host, data_buf_start, oob_buf_start, page);
 }
 
 /*
@@ -1704,7 +1935,7 @@ static int copy_last_cw(struct qcom_nand_host *host, int page)
 	set_address(host, host->cw_size * (ecc->steps - 1), page);
 	update_rw_regs(host, 1, true);
 
-	config_nand_single_cw_page_read(nandc);
+	config_nand_single_cw_page_read(nandc, host->use_ecc);
 
 	read_data_dma(nandc, FLASH_BUF_ACC, nandc->data_buffer, size, 0);
 
@@ -1724,20 +1955,14 @@ static int qcom_nandc_read_page(struct mtd_info *mtd, struct nand_chip *chip,
 	struct qcom_nand_host *host = to_qcom_nand_host(chip);
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	u8 *data_buf, *oob_buf = NULL;
-	int ret;
 
 	nand_read_page_op(chip, page, 0, NULL, 0);
 	data_buf = buf;
 	oob_buf = oob_required ? chip->oob_poi : NULL;
 
 	clear_bam_transaction(nandc);
-	ret = read_page_ecc(host, data_buf, oob_buf);
-	if (ret) {
-		dev_err(nandc->dev, "failure to read page\n");
-		return ret;
-	}
 
-	return parse_read_errors(host, data_buf, oob_buf);
+	return read_page_ecc(host, data_buf, oob_buf, page);
 }
 
 /* implements ecc->read_page_raw() */
@@ -1746,77 +1971,20 @@ static int qcom_nandc_read_page_raw(struct mtd_info *mtd,
 				    int oob_required, int page)
 {
 	struct qcom_nand_host *host = to_qcom_nand_host(chip);
-	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
-	u8 *data_buf, *oob_buf;
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
-	int i, ret;
-	int read_loc;
-
-	nand_read_page_op(chip, page, 0, NULL, 0);
-	data_buf = buf;
-	oob_buf = chip->oob_poi;
-
-	host->use_ecc = false;
+	int cw, ret;
+	u8 *data_buf = buf, *oob_buf = chip->oob_poi;
 
-	clear_bam_transaction(nandc);
-	update_rw_regs(host, ecc->steps, true);
-	config_nand_page_read(nandc);
-
-	for (i = 0; i < ecc->steps; i++) {
-		int data_size1, data_size2, oob_size1, oob_size2;
-		int reg_off = FLASH_BUF_ACC;
-
-		data_size1 = mtd->writesize - host->cw_size * (ecc->steps - 1);
-		oob_size1 = host->bbm_size;
-
-		if (i == (ecc->steps - 1)) {
-			data_size2 = ecc->size - data_size1 -
-				     ((ecc->steps - 1) << 2);
-			oob_size2 = (ecc->steps << 2) + host->ecc_bytes_hw +
-				    host->spare_bytes;
-		} else {
-			data_size2 = host->cw_data - data_size1;
-			oob_size2 = host->ecc_bytes_hw + host->spare_bytes;
-		}
-
-		if (nandc->props->is_bam) {
-			read_loc = 0;
-			nandc_set_read_loc(nandc, 0, read_loc, data_size1, 0);
-			read_loc += data_size1;
-
-			nandc_set_read_loc(nandc, 1, read_loc, oob_size1, 0);
-			read_loc += oob_size1;
-
-			nandc_set_read_loc(nandc, 2, read_loc, data_size2, 0);
-			read_loc += data_size2;
-
-			nandc_set_read_loc(nandc, 3, read_loc, oob_size2, 1);
-		}
-
-		config_nand_cw_read(nandc);
-
-		read_data_dma(nandc, reg_off, data_buf, data_size1, 0);
-		reg_off += data_size1;
-		data_buf += data_size1;
-
-		read_data_dma(nandc, reg_off, oob_buf, oob_size1, 0);
-		reg_off += oob_size1;
-		oob_buf += oob_size1;
-
-		read_data_dma(nandc, reg_off, data_buf, data_size2, 0);
-		reg_off += data_size2;
-		data_buf += data_size2;
+	for (cw = 0; cw < ecc->steps; cw++) {
+		ret = qcom_nandc_read_cw_raw(mtd, chip, data_buf, oob_buf,
+					     page, cw);
+		if (ret)
+			return ret;
 
-		read_data_dma(nandc, reg_off, oob_buf, oob_size2, 0);
-		oob_buf += oob_size2;
+		data_buf += host->cw_data;
+		oob_buf += ecc->bytes;
 	}
 
-	ret = submit_descs(nandc);
-	if (ret)
-		dev_err(nandc->dev, "failure to read raw page\n");
-
-	free_descs(nandc);
-
 	return 0;
 }
 
@@ -1827,7 +1995,6 @@ static int qcom_nandc_read_oob(struct mtd_info *mtd, struct nand_chip *chip,
 	struct qcom_nand_host *host = to_qcom_nand_host(chip);
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
-	int ret;
 
 	clear_read_regs(nandc);
 	clear_bam_transaction(nandc);
@@ -1836,11 +2003,7 @@ static int qcom_nandc_read_oob(struct mtd_info *mtd, struct nand_chip *chip,
 	set_address(host, 0, page);
 	update_rw_regs(host, ecc->steps, true);
 
-	ret = read_page_ecc(host, NULL, chip->oob_poi);
-	if (ret)
-		dev_err(nandc->dev, "failure to read oob\n");
-
-	return ret;
+	return read_page_ecc(host, NULL, chip->oob_poi, page);
 }
 
 /* implements ecc->write_page() */
@@ -1988,11 +2151,9 @@ static int qcom_nandc_write_page_raw(struct mtd_info *mtd,
 /*
  * implements ecc->write_oob()
  *
- * the NAND controller cannot write only data or only oob within a codeword,
- * since ecc is calculated for the combined codeword. we first copy the
- * entire contents for the last codeword(data + oob), replace the old oob
- * with the new one in chip->oob_poi, and then write the entire codeword.
- * this read-copy-write operation results in a slight performance loss.
+ * the NAND controller cannot write only data or only OOB within a codeword
+ * since ECC is calculated for the combined codeword. So update the OOB from
+ * chip->oob_poi, and pad the data area with OxFF before writing.
  */
 static int qcom_nandc_write_oob(struct mtd_info *mtd, struct nand_chip *chip,
 				int page)
@@ -2005,19 +2166,13 @@ static int qcom_nandc_write_oob(struct mtd_info *mtd, struct nand_chip *chip,
 	int ret;
 
 	host->use_ecc = true;
-
-	clear_bam_transaction(nandc);
-	ret = copy_last_cw(host, page);
-	if (ret)
-		return ret;
-
-	clear_read_regs(nandc);
 	clear_bam_transaction(nandc);
 
 	/* calculate the data and oob size for the last codeword/step */
 	data_size = ecc->size - ((ecc->steps - 1) << 2);
 	oob_size = mtd->oobavail;
 
+	memset(nandc->data_buffer, 0xff, host->cw_data);
 	/* override new oob content to last codeword */
 	mtd_ooblayout_get_databytes(mtd, nandc->data_buffer + data_size, oob,
 				    0, mtd->oobavail);
@@ -2049,7 +2204,6 @@ static int qcom_nandc_block_bad(struct mtd_info *mtd, loff_t ofs)
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
 	int page, ret, bbpos, bad = 0;
-	u32 flash_status;
 
 	page = (int)(ofs >> chip->page_shift) & chip->pagemask;
 
@@ -2066,9 +2220,7 @@ static int qcom_nandc_block_bad(struct mtd_info *mtd, loff_t ofs)
 	if (ret)
 		goto err;
 
-	flash_status = le32_to_cpu(nandc->reg_read_buf[0]);
-
-	if (flash_status & (FS_OP_ERR | FS_MPU_ERR)) {
+	if (check_flash_errors(host, 1)) {
 		dev_warn(nandc->dev, "error when trying to read BBM\n");
 		goto err;
 	}
@@ -2315,27 +2467,40 @@ static const struct mtd_ooblayout_ops qcom_nand_ooblayout_ops = {
 	.free = qcom_nand_ooblayout_free,
 };
 
-static int qcom_nand_host_setup(struct qcom_nand_host *host)
+static int
+qcom_nandc_calc_ecc_bytes(int step_size, int strength)
+{
+	return strength == 4 ? 12 : 16;
+}
+NAND_ECC_CAPS_SINGLE(qcom_nandc_ecc_caps, qcom_nandc_calc_ecc_bytes,
+		     NANDC_STEP_SIZE, 4, 8);
+
+static int qcom_nand_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &host->chip;
 	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct qcom_nand_host *host = to_qcom_nand_host(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
-	int cwperpage, bad_block_byte;
+	int cwperpage, bad_block_byte, ret;
 	bool wide_bus;
 	int ecc_mode = 1;
 
+	/* controller only supports 512 bytes data steps */
+	ecc->size = NANDC_STEP_SIZE;
+	wide_bus = chip->options & NAND_BUSWIDTH_16 ? true : false;
+	cwperpage = mtd->writesize / NANDC_STEP_SIZE;
+
 	/*
-	 * the controller requires each step consists of 512 bytes of data.
-	 * bail out if DT has populated a wrong step size.
+	 * Each CW has 4 available OOB bytes which will be protected with ECC
+	 * so remaining bytes can be used for ECC.
 	 */
-	if (ecc->size != NANDC_STEP_SIZE) {
-		dev_err(nandc->dev, "invalid ecc size\n");
-		return -EINVAL;
+	ret = nand_ecc_choose_conf(chip, &qcom_nandc_ecc_caps,
+				   mtd->oobsize - (cwperpage * 4));
+	if (ret) {
+		dev_err(nandc->dev, "No valid ECC settings possible\n");
+		return ret;
 	}
 
-	wide_bus = chip->options & NAND_BUSWIDTH_16 ? true : false;
-
 	if (ecc->strength >= 8) {
 		/* 8 bit ECC defaults to BCH ECC on all platforms */
 		host->bch_enabled = true;
@@ -2403,7 +2568,6 @@ static int qcom_nand_host_setup(struct qcom_nand_host *host)
 
 	mtd_set_ooblayout(mtd, &qcom_nand_ooblayout_ops);
 
-	cwperpage = mtd->writesize / ecc->size;
 	nandc->max_cwperpage = max_t(unsigned int, nandc->max_cwperpage,
 				     cwperpage);
 
@@ -2419,12 +2583,6 @@ static int qcom_nand_host_setup(struct qcom_nand_host *host)
 	 * for 8 bit ECC
 	 */
 	host->cw_size = host->cw_data + ecc->bytes;
-
-	if (ecc->bytes * (mtd->writesize / ecc->size) > mtd->oobsize) {
-		dev_err(nandc->dev, "ecc data doesn't fit in OOB area\n");
-		return -EINVAL;
-	}
-
 	bad_block_byte = mtd->writesize - host->cw_size * (cwperpage - 1) + 1;
 
 	host->cfg0 = (cwperpage - 1) << CW_PER_PAGE
@@ -2482,6 +2640,10 @@ static int qcom_nand_host_setup(struct qcom_nand_host *host)
 	return 0;
 }
 
+static const struct nand_controller_ops qcom_nandc_ops = {
+	.attach_chip = qcom_nand_attach_chip,
+};
+
 static int qcom_nandc_alloc(struct qcom_nand_controller *nandc)
 {
 	int ret;
@@ -2570,7 +2732,8 @@ static int qcom_nandc_alloc(struct qcom_nand_controller *nandc)
 	INIT_LIST_HEAD(&nandc->desc_list);
 	INIT_LIST_HEAD(&nandc->host_list);
 
-	nand_hw_control_init(&nandc->controller);
+	nand_controller_init(&nandc->controller);
+	nandc->controller.ops = &qcom_nandc_ops;
 
 	return 0;
 }
@@ -2623,9 +2786,9 @@ static int qcom_nandc_setup(struct qcom_nand_controller *nandc)
 	return 0;
 }
 
-static int qcom_nand_host_init(struct qcom_nand_controller *nandc,
-			       struct qcom_nand_host *host,
-			       struct device_node *dn)
+static int qcom_nand_host_init_and_register(struct qcom_nand_controller *nandc,
+					    struct qcom_nand_host *host,
+					    struct device_node *dn)
 {
 	struct nand_chip *chip = &host->chip;
 	struct mtd_info *mtd = nand_to_mtd(chip);
@@ -2672,30 +2835,13 @@ static int qcom_nand_host_init(struct qcom_nand_controller *nandc,
 	/* set up initial status value */
 	host->status = NAND_STATUS_READY | NAND_STATUS_WP;
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		return ret;
-
-	ret = qcom_nand_host_setup(host);
-
-	return ret;
-}
-
-static int qcom_nand_mtd_register(struct qcom_nand_controller *nandc,
-				  struct qcom_nand_host *host,
-				  struct device_node *dn)
-{
-	struct nand_chip *chip = &host->chip;
-	struct mtd_info *mtd = nand_to_mtd(chip);
-	int ret;
-
-	ret = nand_scan_tail(mtd);
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		return ret;
 
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret)
-		nand_cleanup(mtd_to_nand(mtd));
+		nand_cleanup(chip);
 
 	return ret;
 }
@@ -2704,28 +2850,9 @@ static int qcom_probe_nand_devices(struct qcom_nand_controller *nandc)
 {
 	struct device *dev = nandc->dev;
 	struct device_node *dn = dev->of_node, *child;
-	struct qcom_nand_host *host, *tmp;
+	struct qcom_nand_host *host;
 	int ret;
 
-	for_each_available_child_of_node(dn, child) {
-		host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL);
-		if (!host) {
-			of_node_put(child);
-			return -ENOMEM;
-		}
-
-		ret = qcom_nand_host_init(nandc, host, child);
-		if (ret) {
-			devm_kfree(dev, host);
-			continue;
-		}
-
-		list_add_tail(&host->node, &nandc->host_list);
-	}
-
-	if (list_empty(&nandc->host_list))
-		return -ENODEV;
-
 	if (nandc->props->is_bam) {
 		free_bam_transaction(nandc);
 		nandc->bam_txn = alloc_bam_transaction(nandc);
@@ -2736,12 +2863,20 @@ static int qcom_probe_nand_devices(struct qcom_nand_controller *nandc)
 		}
 	}
 
-	list_for_each_entry_safe(host, tmp, &nandc->host_list, node) {
-		ret = qcom_nand_mtd_register(nandc, host, child);
+	for_each_available_child_of_node(dn, child) {
+		host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL);
+		if (!host) {
+			of_node_put(child);
+			return -ENOMEM;
+		}
+
+		ret = qcom_nand_host_init_and_register(nandc, host, child);
 		if (ret) {
-			list_del(&host->node);
 			devm_kfree(dev, host);
+			continue;
 		}
+
+		list_add_tail(&host->node, &nandc->host_list);
 	}
 
 	if (list_empty(&nandc->host_list))
@@ -2799,14 +2934,6 @@ static int qcom_nandc_probe(struct platform_device *pdev)
 
 	nandc->props = dev_data;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	nandc->base = devm_ioremap_resource(dev, res);
-	if (IS_ERR(nandc->base))
-		return PTR_ERR(nandc->base);
-
-	nandc->base_phys = res->start;
-	nandc->base_dma = phys_to_dma(dev, (phys_addr_t)res->start);
-
 	nandc->core_clk = devm_clk_get(dev, "core");
 	if (IS_ERR(nandc->core_clk))
 		return PTR_ERR(nandc->core_clk);
@@ -2819,9 +2946,21 @@ static int qcom_nandc_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	nandc->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(nandc->base))
+		return PTR_ERR(nandc->base);
+
+	nandc->base_phys = res->start;
+	nandc->base_dma = dma_map_resource(dev, res->start,
+					   resource_size(res),
+					   DMA_BIDIRECTIONAL, 0);
+	if (!nandc->base_dma)
+		return -ENXIO;
+
 	ret = qcom_nandc_alloc(nandc);
 	if (ret)
-		goto err_core_clk;
+		goto err_nandc_alloc;
 
 	ret = clk_prepare_enable(nandc->core_clk);
 	if (ret)
@@ -2847,6 +2986,9 @@ err_aon_clk:
 	clk_disable_unprepare(nandc->core_clk);
 err_core_clk:
 	qcom_nandc_unalloc(nandc);
+err_nandc_alloc:
+	dma_unmap_resource(dev, res->start, resource_size(res),
+			   DMA_BIDIRECTIONAL, 0);
 
 	return ret;
 }
@@ -2854,16 +2996,21 @@ err_core_clk:
 static int qcom_nandc_remove(struct platform_device *pdev)
 {
 	struct qcom_nand_controller *nandc = platform_get_drvdata(pdev);
+	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	struct qcom_nand_host *host;
 
 	list_for_each_entry(host, &nandc->host_list, node)
 		nand_release(nand_to_mtd(&host->chip));
 
+
 	qcom_nandc_unalloc(nandc);
 
 	clk_disable_unprepare(nandc->aon_clk);
 	clk_disable_unprepare(nandc->core_clk);
 
+	dma_unmap_resource(&pdev->dev, nandc->base_dma, resource_size(res),
+			   DMA_BIDIRECTIONAL, 0);
+
 	return 0;
 }
 
diff --git a/drivers/mtd/nand/raw/s3c2410.c b/drivers/mtd/nand/raw/s3c2410.c
index 19661c5d3220..c21e8892394a 100644
--- a/drivers/mtd/nand/raw/s3c2410.c
+++ b/drivers/mtd/nand/raw/s3c2410.c
@@ -162,7 +162,7 @@ enum s3c_nand_clk_state {
  */
 struct s3c2410_nand_info {
 	/* mtd info */
-	struct nand_hw_control		controller;
+	struct nand_controller		controller;
 	struct s3c2410_nand_mtd		*mtds;
 	struct s3c2410_platform_nand	*platform;
 
@@ -802,8 +802,8 @@ static int s3c2410_nand_add_partition(struct s3c2410_nand_info *info,
 
 		mtdinfo->name = set->name;
 
-		return mtd_device_parse_register(mtdinfo, NULL, NULL,
-					 set->partitions, set->nr_partitions);
+		return mtd_device_register(mtdinfo, set->partitions,
+					   set->nr_partitions);
 	}
 
 	return -ENODEV;
@@ -915,20 +915,19 @@ static void s3c2410_nand_init_chip(struct s3c2410_nand_info *info,
 }
 
 /**
- * s3c2410_nand_update_chip - post probe update
- * @info: The controller instance.
- * @nmtd: The driver version of the MTD instance.
+ * s3c2410_nand_attach_chip - Init the ECC engine after NAND scan
+ * @chip: The NAND chip
  *
- * This routine is called after the chip probe has successfully completed
- * and the relevant per-chip information updated. This call ensure that
+ * This hook is called by the core after the identification of the NAND chip,
+ * once the relevant per-chip information is up to date.. This call ensure that
  * we update the internal state accordingly.
  *
  * The internal state is currently limited to the ECC state information.
 */
-static int s3c2410_nand_update_chip(struct s3c2410_nand_info *info,
-				    struct s3c2410_nand_mtd *nmtd)
+static int s3c2410_nand_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &nmtd->chip;
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct s3c2410_nand_info *info = s3c2410_nand_mtd_toinfo(mtd);
 
 	switch (chip->ecc.mode) {
 
@@ -998,6 +997,10 @@ static int s3c2410_nand_update_chip(struct s3c2410_nand_info *info,
 	return 0;
 }
 
+static const struct nand_controller_ops s3c24xx_nand_controller_ops = {
+	.attach_chip = s3c2410_nand_attach_chip,
+};
+
 static const struct of_device_id s3c24xx_nand_dt_ids[] = {
 	{
 		.compatible = "samsung,s3c2410-nand",
@@ -1094,7 +1097,8 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, info);
 
-	nand_hw_control_init(&info->controller);
+	nand_controller_init(&info->controller);
+	info->controller.ops = &s3c24xx_nand_controller_ops;
 
 	/* get the clock source and enable it */
 
@@ -1134,8 +1138,13 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 
 	dev_dbg(&pdev->dev, "mapped registers at %p\n", info->regs);
 
-	sets = (plat != NULL) ? plat->sets : NULL;
-	nr_sets = (plat != NULL) ? plat->nr_sets : 1;
+	if (!plat->sets || plat->nr_sets < 1) {
+		err = -EINVAL;
+		goto exit_error;
+	}
+
+	sets = plat->sets;
+	nr_sets = plat->nr_sets;
 
 	info->mtd_count = nr_sets;
 
@@ -1152,7 +1161,7 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 
 	nmtd = info->mtds;
 
-	for (setno = 0; setno < nr_sets; setno++, nmtd++) {
+	for (setno = 0; setno < nr_sets; setno++, nmtd++, sets++) {
 		struct mtd_info *mtd = nand_to_mtd(&nmtd->chip);
 
 		pr_debug("initialising set %d (%p, info %p)\n",
@@ -1161,22 +1170,11 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 		mtd->dev.parent = &pdev->dev;
 		s3c2410_nand_init_chip(info, nmtd, sets);
 
-		err = nand_scan_ident(mtd, (sets) ? sets->nr_chips : 1, NULL);
-		if (err)
-			goto exit_error;
-
-		err = s3c2410_nand_update_chip(info, nmtd);
-		if (err < 0)
-			goto exit_error;
-
-		err = nand_scan_tail(mtd);
+		err = nand_scan(mtd, sets ? sets->nr_chips : 1);
 		if (err)
 			goto exit_error;
 
 		s3c2410_nand_add_partition(info, nmtd, sets);
-
-		if (sets != NULL)
-			sets++;
 	}
 
 	/* initialise the hardware */
diff --git a/drivers/mtd/nand/raw/sh_flctl.c b/drivers/mtd/nand/raw/sh_flctl.c
index c7abceffcc40..bb8866e05ff7 100644
--- a/drivers/mtd/nand/raw/sh_flctl.c
+++ b/drivers/mtd/nand/raw/sh_flctl.c
@@ -1002,10 +1002,17 @@ static void flctl_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 	flctl->index += len;
 }
 
-static int flctl_chip_init_tail(struct mtd_info *mtd)
+static int flctl_chip_attach_chip(struct nand_chip *chip)
 {
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct sh_flctl *flctl = mtd_to_flctl(mtd);
-	struct nand_chip *chip = &flctl->chip;
+
+	/*
+	 * NAND_BUSWIDTH_16 may have been set by nand_scan_ident().
+	 * Add the SEL_16BIT flag in flctl->flcmncr_base.
+	 */
+	if (chip->options & NAND_BUSWIDTH_16)
+		flctl->flcmncr_base |= SEL_16BIT;
 
 	if (mtd->writesize == 512) {
 		flctl->page_size = 0;
@@ -1063,6 +1070,10 @@ static int flctl_chip_init_tail(struct mtd_info *mtd)
 	return 0;
 }
 
+static const struct nand_controller_ops flctl_nand_controller_ops = {
+	.attach_chip = flctl_chip_attach_chip,
+};
+
 static irqreturn_t flctl_handle_flste(int irq, void *dev_id)
 {
 	struct sh_flctl *flctl = dev_id;
@@ -1191,25 +1202,8 @@ static int flctl_probe(struct platform_device *pdev)
 
 	flctl_setup_dma(flctl);
 
-	ret = nand_scan_ident(flctl_mtd, 1, NULL);
-	if (ret)
-		goto err_chip;
-
-	if (nand->options & NAND_BUSWIDTH_16) {
-		/*
-		 * NAND_BUSWIDTH_16 may have been set by nand_scan_ident().
-		 * Add the SEL_16BIT flag in pdata->flcmncr_val and re-assign
-		 * flctl->flcmncr_base to pdata->flcmncr_val.
-		 */
-		pdata->flcmncr_val |= SEL_16BIT;
-		flctl->flcmncr_base = pdata->flcmncr_val;
-	}
-
-	ret = flctl_chip_init_tail(flctl_mtd);
-	if (ret)
-		goto err_chip;
-
-	ret = nand_scan_tail(flctl_mtd);
+	nand->dummy_controller.ops = &flctl_nand_controller_ops;
+	ret = nand_scan(flctl_mtd, 1);
 	if (ret)
 		goto err_chip;
 
diff --git a/drivers/mtd/nand/raw/sharpsl.c b/drivers/mtd/nand/raw/sharpsl.c
index e93df02c825e..fc171b17a39b 100644
--- a/drivers/mtd/nand/raw/sharpsl.c
+++ b/drivers/mtd/nand/raw/sharpsl.c
@@ -21,10 +21,7 @@
 #include <linux/mtd/sharpsl.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
-
-#include <asm/io.h>
-#include <mach/hardware.h>
-#include <asm/mach-types.h>
+#include <linux/io.h>
 
 struct sharpsl_nand {
 	struct nand_chip	chip;
diff --git a/drivers/mtd/nand/raw/sm_common.c b/drivers/mtd/nand/raw/sm_common.c
index 7f5044a79f01..73aafe8c3ef3 100644
--- a/drivers/mtd/nand/raw/sm_common.c
+++ b/drivers/mtd/nand/raw/sm_common.c
@@ -160,19 +160,9 @@ static struct nand_flash_dev nand_xd_flash_ids[] = {
 	{NULL}
 };
 
-int sm_register_device(struct mtd_info *mtd, int smartmedia)
+static int sm_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = mtd_to_nand(mtd);
-	int ret;
-
-	chip->options |= NAND_SKIP_BBTSCAN;
-
-	/* Scan for card properties */
-	ret = nand_scan_ident(mtd, 1, smartmedia ?
-		nand_smartmedia_flash_ids : nand_xd_flash_ids);
-
-	if (ret)
-		return ret;
+	struct mtd_info *mtd = nand_to_mtd(chip);
 
 	/* Bad block marker position */
 	chip->badblockpos = 0x05;
@@ -187,12 +177,33 @@ int sm_register_device(struct mtd_info *mtd, int smartmedia)
 	else
 		return -ENODEV;
 
-	ret = nand_scan_tail(mtd);
+	return 0;
+}
+
+static const struct nand_controller_ops sm_controller_ops = {
+	.attach_chip = sm_attach_chip,
+};
+
+int sm_register_device(struct mtd_info *mtd, int smartmedia)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct nand_flash_dev *flash_ids;
+	int ret;
+
+	chip->options |= NAND_SKIP_BBTSCAN;
 
+	/* Scan for card properties */
+	chip->dummy_controller.ops = &sm_controller_ops;
+	flash_ids = smartmedia ? nand_smartmedia_flash_ids : nand_xd_flash_ids;
+	ret = nand_scan_with_ids(mtd, 1, flash_ids);
 	if (ret)
 		return ret;
 
-	return mtd_device_register(mtd, NULL, 0);
+	ret = mtd_device_register(mtd, NULL, 0);
+	if (ret)
+		nand_cleanup(chip);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(sm_register_device);
 
diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c
index d831a141a196..1f0b7ee38df5 100644
--- a/drivers/mtd/nand/raw/sunxi_nand.c
+++ b/drivers/mtd/nand/raw/sunxi_nand.c
@@ -29,14 +29,12 @@
 #include <linux/platform_device.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-#include <linux/of_gpio.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
 #include <linux/mtd/partitions.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/dmaengine.h>
-#include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/iopoll.h>
 #include <linux/reset.h>
@@ -127,7 +125,7 @@
 #define NFC_CMD_TYPE_MSK	GENMASK(31, 30)
 #define NFC_NORMAL_OP		(0 << 30)
 #define NFC_ECC_OP		(1 << 30)
-#define NFC_PAGE_OP		(2 << 30)
+#define NFC_PAGE_OP		(2U << 30)
 
 /* define bit use in NFC_RCMD_SET */
 #define NFC_READ_CMD_MSK	GENMASK(7, 0)
@@ -234,7 +232,7 @@ static inline struct sunxi_nand_chip *to_sunxi_nand(struct nand_chip *nand)
  *			controller events
  */
 struct sunxi_nfc {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct device *dev;
 	void __iomem *regs;
 	struct clk *ahb_clk;
@@ -247,7 +245,7 @@ struct sunxi_nfc {
 	struct dma_chan *dmac;
 };
 
-static inline struct sunxi_nfc *to_sunxi_nfc(struct nand_hw_control *ctrl)
+static inline struct sunxi_nfc *to_sunxi_nfc(struct nand_controller *ctrl)
 {
 	return container_of(ctrl, struct sunxi_nfc, controller);
 }
@@ -544,7 +542,7 @@ static void sunxi_nfc_write_buf(struct mtd_info *mtd, const uint8_t *buf,
 
 static uint8_t sunxi_nfc_read_byte(struct mtd_info *mtd)
 {
-	uint8_t ret;
+	uint8_t ret = 0;
 
 	sunxi_nfc_read_buf(mtd, &ret, 1);
 
@@ -1816,12 +1814,21 @@ static void sunxi_nand_ecc_cleanup(struct nand_ecc_ctrl *ecc)
 	}
 }
 
-static int sunxi_nand_ecc_init(struct mtd_info *mtd, struct nand_ecc_ctrl *ecc,
-			       struct device_node *np)
+static int sunxi_nand_attach_chip(struct nand_chip *nand)
 {
-	struct nand_chip *nand = mtd_to_nand(mtd);
+	struct mtd_info *mtd = nand_to_mtd(nand);
+	struct nand_ecc_ctrl *ecc = &nand->ecc;
+	struct device_node *np = nand_get_flash_node(nand);
 	int ret;
 
+	if (nand->bbt_options & NAND_BBT_USE_FLASH)
+		nand->bbt_options |= NAND_BBT_NO_OOB;
+
+	if (nand->options & NAND_NEED_SCRAMBLING)
+		nand->options |= NAND_NO_SUBPAGE_WRITE;
+
+	nand->options |= NAND_SUBPAGE_READ;
+
 	if (!ecc->size) {
 		ecc->size = nand->ecc_step_ds;
 		ecc->strength = nand->ecc_strength_ds;
@@ -1846,6 +1853,10 @@ static int sunxi_nand_ecc_init(struct mtd_info *mtd, struct nand_ecc_ctrl *ecc,
 	return 0;
 }
 
+static const struct nand_controller_ops sunxi_nand_controller_ops = {
+	.attach_chip = sunxi_nand_attach_chip,
+};
+
 static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc,
 				struct device_node *np)
 {
@@ -1911,6 +1922,8 @@ static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc,
 	/* Default tR value specified in the ONFI spec (chapter 4.15.1) */
 	nand->chip_delay = 200;
 	nand->controller = &nfc->controller;
+	nand->controller->ops = &sunxi_nand_controller_ops;
+
 	/*
 	 * Set the ECC mode to the default value in case nothing is specified
 	 * in the DT.
@@ -1927,30 +1940,10 @@ static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc,
 	mtd = nand_to_mtd(nand);
 	mtd->dev.parent = dev;
 
-	ret = nand_scan_ident(mtd, nsels, NULL);
+	ret = nand_scan(mtd, nsels);
 	if (ret)
 		return ret;
 
-	if (nand->bbt_options & NAND_BBT_USE_FLASH)
-		nand->bbt_options |= NAND_BBT_NO_OOB;
-
-	if (nand->options & NAND_NEED_SCRAMBLING)
-		nand->options |= NAND_NO_SUBPAGE_WRITE;
-
-	nand->options |= NAND_SUBPAGE_READ;
-
-	ret = sunxi_nand_ecc_init(mtd, &nand->ecc, np);
-	if (ret) {
-		dev_err(dev, "ECC init failed: %d\n", ret);
-		return ret;
-	}
-
-	ret = nand_scan_tail(mtd);
-	if (ret) {
-		dev_err(dev, "nand_scan_tail failed: %d\n", ret);
-		return ret;
-	}
-
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(dev, "failed to register mtd device: %d\n", ret);
@@ -2012,7 +2005,7 @@ static int sunxi_nfc_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	nfc->dev = dev;
-	nand_hw_control_init(&nfc->controller);
+	nand_controller_init(&nfc->controller);
 	INIT_LIST_HEAD(&nfc->chips);
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/mtd/nand/raw/tango_nand.c b/drivers/mtd/nand/raw/tango_nand.c
index f2052fae21c7..72698691727d 100644
--- a/drivers/mtd/nand/raw/tango_nand.c
+++ b/drivers/mtd/nand/raw/tango_nand.c
@@ -83,7 +83,7 @@
 #define MAX_CS		4
 
 struct tango_nfc {
-	struct nand_hw_control hw;
+	struct nand_controller hw;
 	void __iomem *reg_base;
 	void __iomem *mem_base;
 	void __iomem *pbus_base;
@@ -517,6 +517,28 @@ static int tango_set_timings(struct mtd_info *mtd, int csline,
 	return 0;
 }
 
+static int tango_attach_chip(struct nand_chip *chip)
+{
+	struct nand_ecc_ctrl *ecc = &chip->ecc;
+
+	ecc->mode = NAND_ECC_HW;
+	ecc->algo = NAND_ECC_BCH;
+	ecc->bytes = DIV_ROUND_UP(ecc->strength * FIELD_ORDER, BITS_PER_BYTE);
+
+	ecc->read_page_raw = tango_read_page_raw;
+	ecc->write_page_raw = tango_write_page_raw;
+	ecc->read_page = tango_read_page;
+	ecc->write_page = tango_write_page;
+	ecc->read_oob = tango_read_oob;
+	ecc->write_oob = tango_write_oob;
+
+	return 0;
+}
+
+static const struct nand_controller_ops tango_controller_ops = {
+	.attach_chip = tango_attach_chip,
+};
+
 static int chip_init(struct device *dev, struct device_node *np)
 {
 	u32 cs;
@@ -566,22 +588,7 @@ static int chip_init(struct device *dev, struct device_node *np)
 	mtd_set_ooblayout(mtd, &tango_nand_ooblayout_ops);
 	mtd->dev.parent = dev;
 
-	err = nand_scan_ident(mtd, 1, NULL);
-	if (err)
-		return err;
-
-	ecc->mode = NAND_ECC_HW;
-	ecc->algo = NAND_ECC_BCH;
-	ecc->bytes = DIV_ROUND_UP(ecc->strength * FIELD_ORDER, BITS_PER_BYTE);
-
-	ecc->read_page_raw = tango_read_page_raw;
-	ecc->write_page_raw = tango_write_page_raw;
-	ecc->read_page = tango_read_page;
-	ecc->write_page = tango_write_page;
-	ecc->read_oob = tango_read_oob;
-	ecc->write_oob = tango_write_oob;
-
-	err = nand_scan_tail(mtd);
+	err = nand_scan(mtd, 1);
 	if (err)
 		return err;
 
@@ -654,7 +661,8 @@ static int tango_nand_probe(struct platform_device *pdev)
 		return PTR_ERR(nfc->chan);
 
 	platform_set_drvdata(pdev, nfc);
-	nand_hw_control_init(&nfc->hw);
+	nand_controller_init(&nfc->hw);
+	nfc->hw.ops = &tango_controller_ops;
 	nfc->freq_kHz = clk_get_rate(clk) / 1000;
 
 	for_each_child_of_node(pdev->dev.of_node, np) {
diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c
new file mode 100644
index 000000000000..79da1efc88d1
--- /dev/null
+++ b/drivers/mtd/nand/raw/tegra_nand.c
@@ -0,0 +1,1246 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Stefan Agner <stefan@agner.ch>
+ * Copyright (C) 2014-2015 Lucas Stach <dev@lynxeye.de>
+ * Copyright (C) 2012 Avionic Design GmbH
+ */
+
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/rawnand.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+
+#define COMMAND					0x00
+#define   COMMAND_GO				BIT(31)
+#define   COMMAND_CLE				BIT(30)
+#define   COMMAND_ALE				BIT(29)
+#define   COMMAND_PIO				BIT(28)
+#define   COMMAND_TX				BIT(27)
+#define   COMMAND_RX				BIT(26)
+#define   COMMAND_SEC_CMD			BIT(25)
+#define   COMMAND_AFT_DAT			BIT(24)
+#define   COMMAND_TRANS_SIZE(size)		((((size) - 1) & 0xf) << 20)
+#define   COMMAND_A_VALID			BIT(19)
+#define   COMMAND_B_VALID			BIT(18)
+#define   COMMAND_RD_STATUS_CHK			BIT(17)
+#define   COMMAND_RBSY_CHK			BIT(16)
+#define   COMMAND_CE(x)				BIT(8 + ((x) & 0x7))
+#define   COMMAND_CLE_SIZE(size)		((((size) - 1) & 0x3) << 4)
+#define   COMMAND_ALE_SIZE(size)		((((size) - 1) & 0xf) << 0)
+
+#define STATUS					0x04
+
+#define ISR					0x08
+#define   ISR_CORRFAIL_ERR			BIT(24)
+#define   ISR_UND				BIT(7)
+#define   ISR_OVR				BIT(6)
+#define   ISR_CMD_DONE				BIT(5)
+#define   ISR_ECC_ERR				BIT(4)
+
+#define IER					0x0c
+#define   IER_ERR_TRIG_VAL(x)			(((x) & 0xf) << 16)
+#define   IER_UND				BIT(7)
+#define   IER_OVR				BIT(6)
+#define   IER_CMD_DONE				BIT(5)
+#define   IER_ECC_ERR				BIT(4)
+#define   IER_GIE				BIT(0)
+
+#define CONFIG					0x10
+#define   CONFIG_HW_ECC				BIT(31)
+#define   CONFIG_ECC_SEL			BIT(30)
+#define   CONFIG_ERR_COR			BIT(29)
+#define   CONFIG_PIPE_EN			BIT(28)
+#define   CONFIG_TVAL_4				(0 << 24)
+#define   CONFIG_TVAL_6				(1 << 24)
+#define   CONFIG_TVAL_8				(2 << 24)
+#define   CONFIG_SKIP_SPARE			BIT(23)
+#define   CONFIG_BUS_WIDTH_16			BIT(21)
+#define   CONFIG_COM_BSY			BIT(20)
+#define   CONFIG_PS_256				(0 << 16)
+#define   CONFIG_PS_512				(1 << 16)
+#define   CONFIG_PS_1024			(2 << 16)
+#define   CONFIG_PS_2048			(3 << 16)
+#define   CONFIG_PS_4096			(4 << 16)
+#define   CONFIG_SKIP_SPARE_SIZE_4		(0 << 14)
+#define   CONFIG_SKIP_SPARE_SIZE_8		(1 << 14)
+#define   CONFIG_SKIP_SPARE_SIZE_12		(2 << 14)
+#define   CONFIG_SKIP_SPARE_SIZE_16		(3 << 14)
+#define   CONFIG_TAG_BYTE_SIZE(x)			((x) & 0xff)
+
+#define TIMING_1				0x14
+#define   TIMING_TRP_RESP(x)			(((x) & 0xf) << 28)
+#define   TIMING_TWB(x)				(((x) & 0xf) << 24)
+#define   TIMING_TCR_TAR_TRR(x)			(((x) & 0xf) << 20)
+#define   TIMING_TWHR(x)			(((x) & 0xf) << 16)
+#define   TIMING_TCS(x)				(((x) & 0x3) << 14)
+#define   TIMING_TWH(x)				(((x) & 0x3) << 12)
+#define   TIMING_TWP(x)				(((x) & 0xf) <<  8)
+#define   TIMING_TRH(x)				(((x) & 0x3) <<  4)
+#define   TIMING_TRP(x)				(((x) & 0xf) <<  0)
+
+#define RESP					0x18
+
+#define TIMING_2				0x1c
+#define   TIMING_TADL(x)			((x) & 0xf)
+
+#define CMD_REG1				0x20
+#define CMD_REG2				0x24
+#define ADDR_REG1				0x28
+#define ADDR_REG2				0x2c
+
+#define DMA_MST_CTRL				0x30
+#define   DMA_MST_CTRL_GO			BIT(31)
+#define   DMA_MST_CTRL_IN			(0 << 30)
+#define   DMA_MST_CTRL_OUT			BIT(30)
+#define   DMA_MST_CTRL_PERF_EN			BIT(29)
+#define   DMA_MST_CTRL_IE_DONE			BIT(28)
+#define   DMA_MST_CTRL_REUSE			BIT(27)
+#define   DMA_MST_CTRL_BURST_1			(2 << 24)
+#define   DMA_MST_CTRL_BURST_4			(3 << 24)
+#define   DMA_MST_CTRL_BURST_8			(4 << 24)
+#define   DMA_MST_CTRL_BURST_16			(5 << 24)
+#define   DMA_MST_CTRL_IS_DONE			BIT(20)
+#define   DMA_MST_CTRL_EN_A			BIT(2)
+#define   DMA_MST_CTRL_EN_B			BIT(1)
+
+#define DMA_CFG_A				0x34
+#define DMA_CFG_B				0x38
+
+#define FIFO_CTRL				0x3c
+#define   FIFO_CTRL_CLR_ALL			BIT(3)
+
+#define DATA_PTR				0x40
+#define TAG_PTR					0x44
+#define ECC_PTR					0x48
+
+#define DEC_STATUS				0x4c
+#define   DEC_STATUS_A_ECC_FAIL			BIT(1)
+#define   DEC_STATUS_ERR_COUNT_MASK		0x00ff0000
+#define   DEC_STATUS_ERR_COUNT_SHIFT		16
+
+#define HWSTATUS_CMD				0x50
+#define HWSTATUS_MASK				0x54
+#define   HWSTATUS_RDSTATUS_MASK(x)		(((x) & 0xff) << 24)
+#define   HWSTATUS_RDSTATUS_VALUE(x)		(((x) & 0xff) << 16)
+#define   HWSTATUS_RBSY_MASK(x)			(((x) & 0xff) << 8)
+#define   HWSTATUS_RBSY_VALUE(x)		(((x) & 0xff) << 0)
+
+#define BCH_CONFIG				0xcc
+#define   BCH_ENABLE				BIT(0)
+#define   BCH_TVAL_4				(0 << 4)
+#define   BCH_TVAL_8				(1 << 4)
+#define   BCH_TVAL_14				(2 << 4)
+#define   BCH_TVAL_16				(3 << 4)
+
+#define DEC_STAT_RESULT				0xd0
+#define DEC_STAT_BUF				0xd4
+#define   DEC_STAT_BUF_FAIL_SEC_FLAG_MASK	0xff000000
+#define   DEC_STAT_BUF_FAIL_SEC_FLAG_SHIFT	24
+#define   DEC_STAT_BUF_CORR_SEC_FLAG_MASK	0x00ff0000
+#define   DEC_STAT_BUF_CORR_SEC_FLAG_SHIFT	16
+#define   DEC_STAT_BUF_MAX_CORR_CNT_MASK	0x00001f00
+#define   DEC_STAT_BUF_MAX_CORR_CNT_SHIFT	8
+
+#define OFFSET(val, off)	((val) < (off) ? 0 : (val) - (off))
+
+#define SKIP_SPARE_BYTES	4
+#define BITS_PER_STEP_RS	18
+#define BITS_PER_STEP_BCH	13
+
+#define INT_MASK		(IER_UND | IER_OVR | IER_CMD_DONE | IER_GIE)
+#define HWSTATUS_CMD_DEFAULT	NAND_STATUS_READY
+#define HWSTATUS_MASK_DEFAULT	(HWSTATUS_RDSTATUS_MASK(1) | \
+				HWSTATUS_RDSTATUS_VALUE(0) | \
+				HWSTATUS_RBSY_MASK(NAND_STATUS_READY) | \
+				HWSTATUS_RBSY_VALUE(NAND_STATUS_READY))
+
+struct tegra_nand_controller {
+	struct nand_controller controller;
+	struct device *dev;
+	void __iomem *regs;
+	int irq;
+	struct clk *clk;
+	struct completion command_complete;
+	struct completion dma_complete;
+	bool last_read_error;
+	int cur_cs;
+	struct nand_chip *chip;
+};
+
+struct tegra_nand_chip {
+	struct nand_chip chip;
+	struct gpio_desc *wp_gpio;
+	struct mtd_oob_region ecc;
+	u32 config;
+	u32 config_ecc;
+	u32 bch_config;
+	int cs[1];
+};
+
+static inline struct tegra_nand_controller *
+			to_tegra_ctrl(struct nand_controller *hw_ctrl)
+{
+	return container_of(hw_ctrl, struct tegra_nand_controller, controller);
+}
+
+static inline struct tegra_nand_chip *to_tegra_chip(struct nand_chip *chip)
+{
+	return container_of(chip, struct tegra_nand_chip, chip);
+}
+
+static int tegra_nand_ooblayout_rs_ecc(struct mtd_info *mtd, int section,
+				       struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	int bytes_per_step = DIV_ROUND_UP(BITS_PER_STEP_RS * chip->ecc.strength,
+					  BITS_PER_BYTE);
+
+	if (section > 0)
+		return -ERANGE;
+
+	oobregion->offset = SKIP_SPARE_BYTES;
+	oobregion->length = round_up(bytes_per_step * chip->ecc.steps, 4);
+
+	return 0;
+}
+
+static int tegra_nand_ooblayout_no_free(struct mtd_info *mtd, int section,
+					struct mtd_oob_region *oobregion)
+{
+	return -ERANGE;
+}
+
+static const struct mtd_ooblayout_ops tegra_nand_oob_rs_ops = {
+	.ecc = tegra_nand_ooblayout_rs_ecc,
+	.free = tegra_nand_ooblayout_no_free,
+};
+
+static int tegra_nand_ooblayout_bch_ecc(struct mtd_info *mtd, int section,
+					struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	int bytes_per_step = DIV_ROUND_UP(BITS_PER_STEP_BCH * chip->ecc.strength,
+					  BITS_PER_BYTE);
+
+	if (section > 0)
+		return -ERANGE;
+
+	oobregion->offset = SKIP_SPARE_BYTES;
+	oobregion->length = round_up(bytes_per_step * chip->ecc.steps, 4);
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops tegra_nand_oob_bch_ops = {
+	.ecc = tegra_nand_ooblayout_bch_ecc,
+	.free = tegra_nand_ooblayout_no_free,
+};
+
+static irqreturn_t tegra_nand_irq(int irq, void *data)
+{
+	struct tegra_nand_controller *ctrl = data;
+	u32 isr, dma;
+
+	isr = readl_relaxed(ctrl->regs + ISR);
+	dma = readl_relaxed(ctrl->regs + DMA_MST_CTRL);
+	dev_dbg(ctrl->dev, "isr %08x\n", isr);
+
+	if (!isr && !(dma & DMA_MST_CTRL_IS_DONE))
+		return IRQ_NONE;
+
+	/*
+	 * The bit name is somewhat missleading: This is also set when
+	 * HW ECC was successful. The data sheet states:
+	 * Correctable OR Un-correctable errors occurred in the DMA transfer...
+	 */
+	if (isr & ISR_CORRFAIL_ERR)
+		ctrl->last_read_error = true;
+
+	if (isr & ISR_CMD_DONE)
+		complete(&ctrl->command_complete);
+
+	if (isr & ISR_UND)
+		dev_err(ctrl->dev, "FIFO underrun\n");
+
+	if (isr & ISR_OVR)
+		dev_err(ctrl->dev, "FIFO overrun\n");
+
+	/* handle DMA interrupts */
+	if (dma & DMA_MST_CTRL_IS_DONE) {
+		writel_relaxed(dma, ctrl->regs + DMA_MST_CTRL);
+		complete(&ctrl->dma_complete);
+	}
+
+	/* clear interrupts */
+	writel_relaxed(isr, ctrl->regs + ISR);
+
+	return IRQ_HANDLED;
+}
+
+static const char * const tegra_nand_reg_names[] = {
+	"COMMAND",
+	"STATUS",
+	"ISR",
+	"IER",
+	"CONFIG",
+	"TIMING",
+	NULL,
+	"TIMING2",
+	"CMD_REG1",
+	"CMD_REG2",
+	"ADDR_REG1",
+	"ADDR_REG2",
+	"DMA_MST_CTRL",
+	"DMA_CFG_A",
+	"DMA_CFG_B",
+	"FIFO_CTRL",
+};
+
+static void tegra_nand_dump_reg(struct tegra_nand_controller *ctrl)
+{
+	u32 reg;
+	int i;
+
+	dev_err(ctrl->dev, "Tegra NAND controller register dump\n");
+	for (i = 0; i < ARRAY_SIZE(tegra_nand_reg_names); i++) {
+		const char *reg_name = tegra_nand_reg_names[i];
+
+		if (!reg_name)
+			continue;
+
+		reg = readl_relaxed(ctrl->regs + (i * 4));
+		dev_err(ctrl->dev, "%s: 0x%08x\n", reg_name, reg);
+	}
+}
+
+static void tegra_nand_controller_abort(struct tegra_nand_controller *ctrl)
+{
+	u32 isr, dma;
+
+	disable_irq(ctrl->irq);
+
+	/* Abort current command/DMA operation */
+	writel_relaxed(0, ctrl->regs + DMA_MST_CTRL);
+	writel_relaxed(0, ctrl->regs + COMMAND);
+
+	/* clear interrupts */
+	isr = readl_relaxed(ctrl->regs + ISR);
+	writel_relaxed(isr, ctrl->regs + ISR);
+	dma = readl_relaxed(ctrl->regs + DMA_MST_CTRL);
+	writel_relaxed(dma, ctrl->regs + DMA_MST_CTRL);
+
+	reinit_completion(&ctrl->command_complete);
+	reinit_completion(&ctrl->dma_complete);
+
+	enable_irq(ctrl->irq);
+}
+
+static int tegra_nand_cmd(struct nand_chip *chip,
+			  const struct nand_subop *subop)
+{
+	const struct nand_op_instr *instr;
+	const struct nand_op_instr *instr_data_in = NULL;
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	unsigned int op_id, size = 0, offset = 0;
+	bool first_cmd = true;
+	u32 reg, cmd = 0;
+	int ret;
+
+	for (op_id = 0; op_id < subop->ninstrs; op_id++) {
+		unsigned int naddrs, i;
+		const u8 *addrs;
+		u32 addr1 = 0, addr2 = 0;
+
+		instr = &subop->instrs[op_id];
+
+		switch (instr->type) {
+		case NAND_OP_CMD_INSTR:
+			if (first_cmd) {
+				cmd |= COMMAND_CLE;
+				writel_relaxed(instr->ctx.cmd.opcode,
+					       ctrl->regs + CMD_REG1);
+			} else {
+				cmd |= COMMAND_SEC_CMD;
+				writel_relaxed(instr->ctx.cmd.opcode,
+					       ctrl->regs + CMD_REG2);
+			}
+			first_cmd = false;
+			break;
+
+		case NAND_OP_ADDR_INSTR:
+			offset = nand_subop_get_addr_start_off(subop, op_id);
+			naddrs = nand_subop_get_num_addr_cyc(subop, op_id);
+			addrs = &instr->ctx.addr.addrs[offset];
+
+			cmd |= COMMAND_ALE | COMMAND_ALE_SIZE(naddrs);
+			for (i = 0; i < min_t(unsigned int, 4, naddrs); i++)
+				addr1 |= *addrs++ << (BITS_PER_BYTE * i);
+			naddrs -= i;
+			for (i = 0; i < min_t(unsigned int, 4, naddrs); i++)
+				addr2 |= *addrs++ << (BITS_PER_BYTE * i);
+
+			writel_relaxed(addr1, ctrl->regs + ADDR_REG1);
+			writel_relaxed(addr2, ctrl->regs + ADDR_REG2);
+			break;
+
+		case NAND_OP_DATA_IN_INSTR:
+			size = nand_subop_get_data_len(subop, op_id);
+			offset = nand_subop_get_data_start_off(subop, op_id);
+
+			cmd |= COMMAND_TRANS_SIZE(size) | COMMAND_PIO |
+				COMMAND_RX | COMMAND_A_VALID;
+
+			instr_data_in = instr;
+			break;
+
+		case NAND_OP_DATA_OUT_INSTR:
+			size = nand_subop_get_data_len(subop, op_id);
+			offset = nand_subop_get_data_start_off(subop, op_id);
+
+			cmd |= COMMAND_TRANS_SIZE(size) | COMMAND_PIO |
+				COMMAND_TX | COMMAND_A_VALID;
+			memcpy(&reg, instr->ctx.data.buf.out + offset, size);
+
+			writel_relaxed(reg, ctrl->regs + RESP);
+			break;
+
+		case NAND_OP_WAITRDY_INSTR:
+			cmd |= COMMAND_RBSY_CHK;
+			break;
+		}
+	}
+
+	cmd |= COMMAND_GO | COMMAND_CE(ctrl->cur_cs);
+	writel_relaxed(cmd, ctrl->regs + COMMAND);
+	ret = wait_for_completion_timeout(&ctrl->command_complete,
+					  msecs_to_jiffies(500));
+	if (!ret) {
+		dev_err(ctrl->dev, "COMMAND timeout\n");
+		tegra_nand_dump_reg(ctrl);
+		tegra_nand_controller_abort(ctrl);
+		return -ETIMEDOUT;
+	}
+
+	if (instr_data_in) {
+		reg = readl_relaxed(ctrl->regs + RESP);
+		memcpy(instr_data_in->ctx.data.buf.in + offset, &reg, size);
+	}
+
+	return 0;
+}
+
+static const struct nand_op_parser tegra_nand_op_parser = NAND_OP_PARSER(
+	NAND_OP_PARSER_PATTERN(tegra_nand_cmd,
+		NAND_OP_PARSER_PAT_CMD_ELEM(true),
+		NAND_OP_PARSER_PAT_ADDR_ELEM(true, 8),
+		NAND_OP_PARSER_PAT_CMD_ELEM(true),
+		NAND_OP_PARSER_PAT_WAITRDY_ELEM(true)),
+	NAND_OP_PARSER_PATTERN(tegra_nand_cmd,
+		NAND_OP_PARSER_PAT_DATA_OUT_ELEM(false, 4)),
+	NAND_OP_PARSER_PATTERN(tegra_nand_cmd,
+		NAND_OP_PARSER_PAT_CMD_ELEM(true),
+		NAND_OP_PARSER_PAT_ADDR_ELEM(true, 8),
+		NAND_OP_PARSER_PAT_CMD_ELEM(true),
+		NAND_OP_PARSER_PAT_WAITRDY_ELEM(true),
+		NAND_OP_PARSER_PAT_DATA_IN_ELEM(true, 4)),
+	);
+
+static int tegra_nand_exec_op(struct nand_chip *chip,
+			      const struct nand_operation *op,
+			      bool check_only)
+{
+	return nand_op_parser_exec_op(chip, &tegra_nand_op_parser, op,
+				      check_only);
+}
+
+static void tegra_nand_select_chip(struct mtd_info *mtd, int die_nr)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct tegra_nand_chip *nand = to_tegra_chip(chip);
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+
+	WARN_ON(die_nr >= (int)ARRAY_SIZE(nand->cs));
+
+	if (die_nr < 0 || die_nr > 0) {
+		ctrl->cur_cs = -1;
+		return;
+	}
+
+	ctrl->cur_cs = nand->cs[die_nr];
+}
+
+static void tegra_nand_hw_ecc(struct tegra_nand_controller *ctrl,
+			      struct nand_chip *chip, bool enable)
+{
+	struct tegra_nand_chip *nand = to_tegra_chip(chip);
+
+	if (chip->ecc.algo == NAND_ECC_BCH && enable)
+		writel_relaxed(nand->bch_config, ctrl->regs + BCH_CONFIG);
+	else
+		writel_relaxed(0, ctrl->regs + BCH_CONFIG);
+
+	if (enable)
+		writel_relaxed(nand->config_ecc, ctrl->regs + CONFIG);
+	else
+		writel_relaxed(nand->config, ctrl->regs + CONFIG);
+}
+
+static int tegra_nand_page_xfer(struct mtd_info *mtd, struct nand_chip *chip,
+				void *buf, void *oob_buf, int oob_len, int page,
+				bool read)
+{
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	enum dma_data_direction dir = read ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+	dma_addr_t dma_addr = 0, dma_addr_oob = 0;
+	u32 addr1, cmd, dma_ctrl;
+	int ret;
+
+	if (read) {
+		writel_relaxed(NAND_CMD_READ0, ctrl->regs + CMD_REG1);
+		writel_relaxed(NAND_CMD_READSTART, ctrl->regs + CMD_REG2);
+	} else {
+		writel_relaxed(NAND_CMD_SEQIN, ctrl->regs + CMD_REG1);
+		writel_relaxed(NAND_CMD_PAGEPROG, ctrl->regs + CMD_REG2);
+	}
+	cmd = COMMAND_CLE | COMMAND_SEC_CMD;
+
+	/* Lower 16-bits are column, by default 0 */
+	addr1 = page << 16;
+
+	if (!buf)
+		addr1 |= mtd->writesize;
+	writel_relaxed(addr1, ctrl->regs + ADDR_REG1);
+
+	if (chip->options & NAND_ROW_ADDR_3) {
+		writel_relaxed(page >> 16, ctrl->regs + ADDR_REG2);
+		cmd |= COMMAND_ALE | COMMAND_ALE_SIZE(5);
+	} else {
+		cmd |= COMMAND_ALE | COMMAND_ALE_SIZE(4);
+	}
+
+	if (buf) {
+		dma_addr = dma_map_single(ctrl->dev, buf, mtd->writesize, dir);
+		ret = dma_mapping_error(ctrl->dev, dma_addr);
+		if (ret) {
+			dev_err(ctrl->dev, "dma mapping error\n");
+			return -EINVAL;
+		}
+
+		writel_relaxed(mtd->writesize - 1, ctrl->regs + DMA_CFG_A);
+		writel_relaxed(dma_addr, ctrl->regs + DATA_PTR);
+	}
+
+	if (oob_buf) {
+		dma_addr_oob = dma_map_single(ctrl->dev, oob_buf, mtd->oobsize,
+					      dir);
+		ret = dma_mapping_error(ctrl->dev, dma_addr_oob);
+		if (ret) {
+			dev_err(ctrl->dev, "dma mapping error\n");
+			ret = -EINVAL;
+			goto err_unmap_dma_page;
+		}
+
+		writel_relaxed(oob_len - 1, ctrl->regs + DMA_CFG_B);
+		writel_relaxed(dma_addr_oob, ctrl->regs + TAG_PTR);
+	}
+
+	dma_ctrl = DMA_MST_CTRL_GO | DMA_MST_CTRL_PERF_EN |
+		   DMA_MST_CTRL_IE_DONE | DMA_MST_CTRL_IS_DONE |
+		   DMA_MST_CTRL_BURST_16;
+
+	if (buf)
+		dma_ctrl |= DMA_MST_CTRL_EN_A;
+	if (oob_buf)
+		dma_ctrl |= DMA_MST_CTRL_EN_B;
+
+	if (read)
+		dma_ctrl |= DMA_MST_CTRL_IN | DMA_MST_CTRL_REUSE;
+	else
+		dma_ctrl |= DMA_MST_CTRL_OUT;
+
+	writel_relaxed(dma_ctrl, ctrl->regs + DMA_MST_CTRL);
+
+	cmd |= COMMAND_GO | COMMAND_RBSY_CHK | COMMAND_TRANS_SIZE(9) |
+	       COMMAND_CE(ctrl->cur_cs);
+
+	if (buf)
+		cmd |= COMMAND_A_VALID;
+	if (oob_buf)
+		cmd |= COMMAND_B_VALID;
+
+	if (read)
+		cmd |= COMMAND_RX;
+	else
+		cmd |= COMMAND_TX | COMMAND_AFT_DAT;
+
+	writel_relaxed(cmd, ctrl->regs + COMMAND);
+
+	ret = wait_for_completion_timeout(&ctrl->command_complete,
+					  msecs_to_jiffies(500));
+	if (!ret) {
+		dev_err(ctrl->dev, "COMMAND timeout\n");
+		tegra_nand_dump_reg(ctrl);
+		tegra_nand_controller_abort(ctrl);
+		ret = -ETIMEDOUT;
+		goto err_unmap_dma;
+	}
+
+	ret = wait_for_completion_timeout(&ctrl->dma_complete,
+					  msecs_to_jiffies(500));
+	if (!ret) {
+		dev_err(ctrl->dev, "DMA timeout\n");
+		tegra_nand_dump_reg(ctrl);
+		tegra_nand_controller_abort(ctrl);
+		ret = -ETIMEDOUT;
+		goto err_unmap_dma;
+	}
+	ret = 0;
+
+err_unmap_dma:
+	if (oob_buf)
+		dma_unmap_single(ctrl->dev, dma_addr_oob, mtd->oobsize, dir);
+err_unmap_dma_page:
+	if (buf)
+		dma_unmap_single(ctrl->dev, dma_addr, mtd->writesize, dir);
+
+	return ret;
+}
+
+static int tegra_nand_read_page_raw(struct mtd_info *mtd,
+				    struct nand_chip *chip, u8 *buf,
+				    int oob_required, int page)
+{
+	void *oob_buf = oob_required ? chip->oob_poi : NULL;
+
+	return tegra_nand_page_xfer(mtd, chip, buf, oob_buf,
+				    mtd->oobsize, page, true);
+}
+
+static int tegra_nand_write_page_raw(struct mtd_info *mtd,
+				     struct nand_chip *chip, const u8 *buf,
+				     int oob_required, int page)
+{
+	void *oob_buf = oob_required ? chip->oob_poi : NULL;
+
+	return tegra_nand_page_xfer(mtd, chip, (void *)buf, oob_buf,
+				     mtd->oobsize, page, false);
+}
+
+static int tegra_nand_read_oob(struct mtd_info *mtd, struct nand_chip *chip,
+			       int page)
+{
+	return tegra_nand_page_xfer(mtd, chip, NULL, chip->oob_poi,
+				    mtd->oobsize, page, true);
+}
+
+static int tegra_nand_write_oob(struct mtd_info *mtd, struct nand_chip *chip,
+				int page)
+{
+	return tegra_nand_page_xfer(mtd, chip, NULL, chip->oob_poi,
+				    mtd->oobsize, page, false);
+}
+
+static int tegra_nand_read_page_hwecc(struct mtd_info *mtd,
+				      struct nand_chip *chip, u8 *buf,
+				      int oob_required, int page)
+{
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	struct tegra_nand_chip *nand = to_tegra_chip(chip);
+	void *oob_buf = oob_required ? chip->oob_poi : NULL;
+	u32 dec_stat, max_corr_cnt;
+	unsigned long fail_sec_flag;
+	int ret;
+
+	tegra_nand_hw_ecc(ctrl, chip, true);
+	ret = tegra_nand_page_xfer(mtd, chip, buf, oob_buf, 0, page, true);
+	tegra_nand_hw_ecc(ctrl, chip, false);
+	if (ret)
+		return ret;
+
+	/* No correctable or un-correctable errors, page must have 0 bitflips */
+	if (!ctrl->last_read_error)
+		return 0;
+
+	/*
+	 * Correctable or un-correctable errors occurred. Use DEC_STAT_BUF
+	 * which contains information for all ECC selections.
+	 *
+	 * Note that since we do not use Command Queues DEC_RESULT does not
+	 * state the number of pages we can read from the DEC_STAT_BUF. But
+	 * since CORRFAIL_ERR did occur during page read we do have a valid
+	 * result in DEC_STAT_BUF.
+	 */
+	ctrl->last_read_error = false;
+	dec_stat = readl_relaxed(ctrl->regs + DEC_STAT_BUF);
+
+	fail_sec_flag = (dec_stat & DEC_STAT_BUF_FAIL_SEC_FLAG_MASK) >>
+			DEC_STAT_BUF_FAIL_SEC_FLAG_SHIFT;
+
+	max_corr_cnt = (dec_stat & DEC_STAT_BUF_MAX_CORR_CNT_MASK) >>
+		       DEC_STAT_BUF_MAX_CORR_CNT_SHIFT;
+
+	if (fail_sec_flag) {
+		int bit, max_bitflips = 0;
+
+		/*
+		 * Since we do not support subpage writes, a complete page
+		 * is either written or not. We can take a shortcut here by
+		 * checking wheather any of the sector has been successful
+		 * read. If at least one sectors has been read successfully,
+		 * the page must have been a written previously. It cannot
+		 * be an erased page.
+		 *
+		 * E.g. controller might return fail_sec_flag with 0x4, which
+		 * would mean only the third sector failed to correct. The
+		 * page must have been written and the third sector is really
+		 * not correctable anymore.
+		 */
+		if (fail_sec_flag ^ GENMASK(chip->ecc.steps - 1, 0)) {
+			mtd->ecc_stats.failed += hweight8(fail_sec_flag);
+			return max_corr_cnt;
+		}
+
+		/*
+		 * All sectors failed to correct, but the ECC isn't smart
+		 * enough to figure out if a page is really just erased.
+		 * Read OOB data and check whether data/OOB is completely
+		 * erased or if error correction just failed for all sub-
+		 * pages.
+		 */
+		ret = tegra_nand_read_oob(mtd, chip, page);
+		if (ret < 0)
+			return ret;
+
+		for_each_set_bit(bit, &fail_sec_flag, chip->ecc.steps) {
+			u8 *data = buf + (chip->ecc.size * bit);
+			u8 *oob = chip->oob_poi + nand->ecc.offset +
+				  (chip->ecc.bytes * bit);
+
+			ret = nand_check_erased_ecc_chunk(data, chip->ecc.size,
+							  oob, chip->ecc.bytes,
+							  NULL, 0,
+							  chip->ecc.strength);
+			if (ret < 0) {
+				mtd->ecc_stats.failed++;
+			} else {
+				mtd->ecc_stats.corrected += ret;
+				max_bitflips = max(ret, max_bitflips);
+			}
+		}
+
+		return max_t(unsigned int, max_corr_cnt, max_bitflips);
+	} else {
+		int corr_sec_flag;
+
+		corr_sec_flag = (dec_stat & DEC_STAT_BUF_CORR_SEC_FLAG_MASK) >>
+				DEC_STAT_BUF_CORR_SEC_FLAG_SHIFT;
+
+		/*
+		 * The value returned in the register is the maximum of
+		 * bitflips encountered in any of the ECC regions. As there is
+		 * no way to get the number of bitflips in a specific regions
+		 * we are not able to deliver correct stats but instead
+		 * overestimate the number of corrected bitflips by assuming
+		 * that all regions where errors have been corrected
+		 * encountered the maximum number of bitflips.
+		 */
+		mtd->ecc_stats.corrected += max_corr_cnt * hweight8(corr_sec_flag);
+
+		return max_corr_cnt;
+	}
+}
+
+static int tegra_nand_write_page_hwecc(struct mtd_info *mtd,
+				       struct nand_chip *chip, const u8 *buf,
+				       int oob_required, int page)
+{
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	void *oob_buf = oob_required ? chip->oob_poi : NULL;
+	int ret;
+
+	tegra_nand_hw_ecc(ctrl, chip, true);
+	ret = tegra_nand_page_xfer(mtd, chip, (void *)buf, oob_buf,
+				   0, page, false);
+	tegra_nand_hw_ecc(ctrl, chip, false);
+
+	return ret;
+}
+
+static void tegra_nand_setup_timing(struct tegra_nand_controller *ctrl,
+				    const struct nand_sdr_timings *timings)
+{
+	/*
+	 * The period (and all other timings in this function) is in ps,
+	 * so need to take care here to avoid integer overflows.
+	 */
+	unsigned int rate = clk_get_rate(ctrl->clk) / 1000000;
+	unsigned int period = DIV_ROUND_UP(1000000, rate);
+	u32 val, reg = 0;
+
+	val = DIV_ROUND_UP(max3(timings->tAR_min, timings->tRR_min,
+				timings->tRC_min), period);
+	reg |= TIMING_TCR_TAR_TRR(OFFSET(val, 3));
+
+	val = DIV_ROUND_UP(max(max(timings->tCS_min, timings->tCH_min),
+			       max(timings->tALS_min, timings->tALH_min)),
+			   period);
+	reg |= TIMING_TCS(OFFSET(val, 2));
+
+	val = DIV_ROUND_UP(max(timings->tRP_min, timings->tREA_max) + 6000,
+			   period);
+	reg |= TIMING_TRP(OFFSET(val, 1)) | TIMING_TRP_RESP(OFFSET(val, 1));
+
+	reg |= TIMING_TWB(OFFSET(DIV_ROUND_UP(timings->tWB_max, period), 1));
+	reg |= TIMING_TWHR(OFFSET(DIV_ROUND_UP(timings->tWHR_min, period), 1));
+	reg |= TIMING_TWH(OFFSET(DIV_ROUND_UP(timings->tWH_min, period), 1));
+	reg |= TIMING_TWP(OFFSET(DIV_ROUND_UP(timings->tWP_min, period), 1));
+	reg |= TIMING_TRH(OFFSET(DIV_ROUND_UP(timings->tREH_min, period), 1));
+
+	writel_relaxed(reg, ctrl->regs + TIMING_1);
+
+	val = DIV_ROUND_UP(timings->tADL_min, period);
+	reg = TIMING_TADL(OFFSET(val, 3));
+
+	writel_relaxed(reg, ctrl->regs + TIMING_2);
+}
+
+static int tegra_nand_setup_data_interface(struct mtd_info *mtd, int csline,
+					const struct nand_data_interface *conf)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	const struct nand_sdr_timings *timings;
+
+	timings = nand_get_sdr_timings(conf);
+	if (IS_ERR(timings))
+		return PTR_ERR(timings);
+
+	if (csline == NAND_DATA_IFACE_CHECK_ONLY)
+		return 0;
+
+	tegra_nand_setup_timing(ctrl, timings);
+
+	return 0;
+}
+
+static const int rs_strength_bootable[] = { 4 };
+static const int rs_strength[] = { 4, 6, 8 };
+static const int bch_strength_bootable[] = { 8, 16 };
+static const int bch_strength[] = { 4, 8, 14, 16 };
+
+static int tegra_nand_get_strength(struct nand_chip *chip, const int *strength,
+				   int strength_len, int bits_per_step,
+				   int oobsize)
+{
+	bool maximize = chip->ecc.options & NAND_ECC_MAXIMIZE;
+	int i;
+
+	/*
+	 * Loop through available strengths. Backwards in case we try to
+	 * maximize the BCH strength.
+	 */
+	for (i = 0; i < strength_len; i++) {
+		int strength_sel, bytes_per_step, bytes_per_page;
+
+		if (maximize) {
+			strength_sel = strength[strength_len - i - 1];
+		} else {
+			strength_sel = strength[i];
+
+			if (strength_sel < chip->ecc_strength_ds)
+				continue;
+		}
+
+		bytes_per_step = DIV_ROUND_UP(bits_per_step * strength_sel,
+					      BITS_PER_BYTE);
+		bytes_per_page = round_up(bytes_per_step * chip->ecc.steps, 4);
+
+		/* Check whether strength fits OOB */
+		if (bytes_per_page < (oobsize - SKIP_SPARE_BYTES))
+			return strength_sel;
+	}
+
+	return -EINVAL;
+}
+
+static int tegra_nand_select_strength(struct nand_chip *chip, int oobsize)
+{
+	const int *strength;
+	int strength_len, bits_per_step;
+
+	switch (chip->ecc.algo) {
+	case NAND_ECC_RS:
+		bits_per_step = BITS_PER_STEP_RS;
+		if (chip->options & NAND_IS_BOOT_MEDIUM) {
+			strength = rs_strength_bootable;
+			strength_len = ARRAY_SIZE(rs_strength_bootable);
+		} else {
+			strength = rs_strength;
+			strength_len = ARRAY_SIZE(rs_strength);
+		}
+		break;
+	case NAND_ECC_BCH:
+		bits_per_step = BITS_PER_STEP_BCH;
+		if (chip->options & NAND_IS_BOOT_MEDIUM) {
+			strength = bch_strength_bootable;
+			strength_len = ARRAY_SIZE(bch_strength_bootable);
+		} else {
+			strength = bch_strength;
+			strength_len = ARRAY_SIZE(bch_strength);
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return tegra_nand_get_strength(chip, strength, strength_len,
+				       bits_per_step, oobsize);
+}
+
+static int tegra_nand_attach_chip(struct nand_chip *chip)
+{
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	struct tegra_nand_chip *nand = to_tegra_chip(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	int bits_per_step;
+	int ret;
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.size = 512;
+	chip->ecc.steps = mtd->writesize / chip->ecc.size;
+	if (chip->ecc_step_ds != 512) {
+		dev_err(ctrl->dev, "Unsupported step size %d\n",
+			chip->ecc_step_ds);
+		return -EINVAL;
+	}
+
+	chip->ecc.read_page = tegra_nand_read_page_hwecc;
+	chip->ecc.write_page = tegra_nand_write_page_hwecc;
+	chip->ecc.read_page_raw = tegra_nand_read_page_raw;
+	chip->ecc.write_page_raw = tegra_nand_write_page_raw;
+	chip->ecc.read_oob = tegra_nand_read_oob;
+	chip->ecc.write_oob = tegra_nand_write_oob;
+
+	if (chip->options & NAND_BUSWIDTH_16)
+		nand->config |= CONFIG_BUS_WIDTH_16;
+
+	if (chip->ecc.algo == NAND_ECC_UNKNOWN) {
+		if (mtd->writesize < 2048)
+			chip->ecc.algo = NAND_ECC_RS;
+		else
+			chip->ecc.algo = NAND_ECC_BCH;
+	}
+
+	if (chip->ecc.algo == NAND_ECC_BCH && mtd->writesize < 2048) {
+		dev_err(ctrl->dev, "BCH supports 2K or 4K page size only\n");
+		return -EINVAL;
+	}
+
+	if (!chip->ecc.strength) {
+		ret = tegra_nand_select_strength(chip, mtd->oobsize);
+		if (ret < 0) {
+			dev_err(ctrl->dev,
+				"No valid strength found, minimum %d\n",
+				chip->ecc_strength_ds);
+			return ret;
+		}
+
+		chip->ecc.strength = ret;
+	}
+
+	nand->config_ecc = CONFIG_PIPE_EN | CONFIG_SKIP_SPARE |
+			   CONFIG_SKIP_SPARE_SIZE_4;
+
+	switch (chip->ecc.algo) {
+	case NAND_ECC_RS:
+		bits_per_step = BITS_PER_STEP_RS * chip->ecc.strength;
+		mtd_set_ooblayout(mtd, &tegra_nand_oob_rs_ops);
+		nand->config_ecc |= CONFIG_HW_ECC | CONFIG_ECC_SEL |
+				    CONFIG_ERR_COR;
+		switch (chip->ecc.strength) {
+		case 4:
+			nand->config_ecc |= CONFIG_TVAL_4;
+			break;
+		case 6:
+			nand->config_ecc |= CONFIG_TVAL_6;
+			break;
+		case 8:
+			nand->config_ecc |= CONFIG_TVAL_8;
+			break;
+		default:
+			dev_err(ctrl->dev, "ECC strength %d not supported\n",
+				chip->ecc.strength);
+			return -EINVAL;
+		}
+		break;
+	case NAND_ECC_BCH:
+		bits_per_step = BITS_PER_STEP_BCH * chip->ecc.strength;
+		mtd_set_ooblayout(mtd, &tegra_nand_oob_bch_ops);
+		nand->bch_config = BCH_ENABLE;
+		switch (chip->ecc.strength) {
+		case 4:
+			nand->bch_config |= BCH_TVAL_4;
+			break;
+		case 8:
+			nand->bch_config |= BCH_TVAL_8;
+			break;
+		case 14:
+			nand->bch_config |= BCH_TVAL_14;
+			break;
+		case 16:
+			nand->bch_config |= BCH_TVAL_16;
+			break;
+		default:
+			dev_err(ctrl->dev, "ECC strength %d not supported\n",
+				chip->ecc.strength);
+			return -EINVAL;
+		}
+		break;
+	default:
+		dev_err(ctrl->dev, "ECC algorithm not supported\n");
+		return -EINVAL;
+	}
+
+	dev_info(ctrl->dev, "Using %s with strength %d per 512 byte step\n",
+		 chip->ecc.algo == NAND_ECC_BCH ? "BCH" : "RS",
+		 chip->ecc.strength);
+
+	chip->ecc.bytes = DIV_ROUND_UP(bits_per_step, BITS_PER_BYTE);
+
+	switch (mtd->writesize) {
+	case 256:
+		nand->config |= CONFIG_PS_256;
+		break;
+	case 512:
+		nand->config |= CONFIG_PS_512;
+		break;
+	case 1024:
+		nand->config |= CONFIG_PS_1024;
+		break;
+	case 2048:
+		nand->config |= CONFIG_PS_2048;
+		break;
+	case 4096:
+		nand->config |= CONFIG_PS_4096;
+		break;
+	default:
+		dev_err(ctrl->dev, "Unsupported writesize %d\n",
+			mtd->writesize);
+		return -ENODEV;
+	}
+
+	/* Store complete configuration for HW ECC in config_ecc */
+	nand->config_ecc |= nand->config;
+
+	/* Non-HW ECC read/writes complete OOB */
+	nand->config |= CONFIG_TAG_BYTE_SIZE(mtd->oobsize - 1);
+	writel_relaxed(nand->config, ctrl->regs + CONFIG);
+
+	return 0;
+}
+
+static const struct nand_controller_ops tegra_nand_controller_ops = {
+	.attach_chip = &tegra_nand_attach_chip,
+};
+
+static int tegra_nand_chips_init(struct device *dev,
+				 struct tegra_nand_controller *ctrl)
+{
+	struct device_node *np = dev->of_node;
+	struct device_node *np_nand;
+	int nsels, nchips = of_get_child_count(np);
+	struct tegra_nand_chip *nand;
+	struct mtd_info *mtd;
+	struct nand_chip *chip;
+	int ret;
+	u32 cs;
+
+	if (nchips != 1) {
+		dev_err(dev, "Currently only one NAND chip supported\n");
+		return -EINVAL;
+	}
+
+	np_nand = of_get_next_child(np, NULL);
+
+	nsels = of_property_count_elems_of_size(np_nand, "reg", sizeof(u32));
+	if (nsels != 1) {
+		dev_err(dev, "Missing/invalid reg property\n");
+		return -EINVAL;
+	}
+
+	/* Retrieve CS id, currently only single die NAND supported */
+	ret = of_property_read_u32(np_nand, "reg", &cs);
+	if (ret) {
+		dev_err(dev, "could not retrieve reg property: %d\n", ret);
+		return ret;
+	}
+
+	nand = devm_kzalloc(dev, sizeof(*nand), GFP_KERNEL);
+	if (!nand)
+		return -ENOMEM;
+
+	nand->cs[0] = cs;
+
+	nand->wp_gpio = devm_gpiod_get_optional(dev, "wp", GPIOD_OUT_LOW);
+
+	if (IS_ERR(nand->wp_gpio)) {
+		ret = PTR_ERR(nand->wp_gpio);
+		dev_err(dev, "Failed to request WP GPIO: %d\n", ret);
+		return ret;
+	}
+
+	chip = &nand->chip;
+	chip->controller = &ctrl->controller;
+
+	mtd = nand_to_mtd(chip);
+
+	mtd->dev.parent = dev;
+	mtd->owner = THIS_MODULE;
+
+	nand_set_flash_node(chip, np_nand);
+
+	if (!mtd->name)
+		mtd->name = "tegra_nand";
+
+	chip->options = NAND_NO_SUBPAGE_WRITE | NAND_USE_BOUNCE_BUFFER;
+	chip->exec_op = tegra_nand_exec_op;
+	chip->select_chip = tegra_nand_select_chip;
+	chip->setup_data_interface = tegra_nand_setup_data_interface;
+
+	ret = nand_scan(mtd, 1);
+	if (ret)
+		return ret;
+
+	mtd_ooblayout_ecc(mtd, 0, &nand->ecc);
+
+	ret = mtd_device_register(mtd, NULL, 0);
+	if (ret) {
+		dev_err(dev, "Failed to register mtd device: %d\n", ret);
+		nand_cleanup(chip);
+		return ret;
+	}
+
+	ctrl->chip = chip;
+
+	return 0;
+}
+
+static int tegra_nand_probe(struct platform_device *pdev)
+{
+	struct reset_control *rst;
+	struct tegra_nand_controller *ctrl;
+	struct resource *res;
+	int err = 0;
+
+	ctrl = devm_kzalloc(&pdev->dev, sizeof(*ctrl), GFP_KERNEL);
+	if (!ctrl)
+		return -ENOMEM;
+
+	ctrl->dev = &pdev->dev;
+	nand_controller_init(&ctrl->controller);
+	ctrl->controller.ops = &tegra_nand_controller_ops;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ctrl->regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(ctrl->regs))
+		return PTR_ERR(ctrl->regs);
+
+	rst = devm_reset_control_get(&pdev->dev, "nand");
+	if (IS_ERR(rst))
+		return PTR_ERR(rst);
+
+	ctrl->clk = devm_clk_get(&pdev->dev, "nand");
+	if (IS_ERR(ctrl->clk))
+		return PTR_ERR(ctrl->clk);
+
+	err = clk_prepare_enable(ctrl->clk);
+	if (err)
+		return err;
+
+	err = reset_control_reset(rst);
+	if (err) {
+		dev_err(ctrl->dev, "Failed to reset HW: %d\n", err);
+		goto err_disable_clk;
+	}
+
+	writel_relaxed(HWSTATUS_CMD_DEFAULT, ctrl->regs + HWSTATUS_CMD);
+	writel_relaxed(HWSTATUS_MASK_DEFAULT, ctrl->regs + HWSTATUS_MASK);
+	writel_relaxed(INT_MASK, ctrl->regs + IER);
+
+	init_completion(&ctrl->command_complete);
+	init_completion(&ctrl->dma_complete);
+
+	ctrl->irq = platform_get_irq(pdev, 0);
+	err = devm_request_irq(&pdev->dev, ctrl->irq, tegra_nand_irq, 0,
+			       dev_name(&pdev->dev), ctrl);
+	if (err) {
+		dev_err(ctrl->dev, "Failed to get IRQ: %d\n", err);
+		goto err_disable_clk;
+	}
+
+	writel_relaxed(DMA_MST_CTRL_IS_DONE, ctrl->regs + DMA_MST_CTRL);
+
+	err = tegra_nand_chips_init(ctrl->dev, ctrl);
+	if (err)
+		goto err_disable_clk;
+
+	platform_set_drvdata(pdev, ctrl);
+
+	return 0;
+
+err_disable_clk:
+	clk_disable_unprepare(ctrl->clk);
+	return err;
+}
+
+static int tegra_nand_remove(struct platform_device *pdev)
+{
+	struct tegra_nand_controller *ctrl = platform_get_drvdata(pdev);
+	struct nand_chip *chip = ctrl->chip;
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	int ret;
+
+	ret = mtd_device_unregister(mtd);
+	if (ret)
+		return ret;
+
+	nand_cleanup(chip);
+
+	clk_disable_unprepare(ctrl->clk);
+
+	return 0;
+}
+
+static const struct of_device_id tegra_nand_of_match[] = {
+	{ .compatible = "nvidia,tegra20-nand" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, tegra_nand_of_match);
+
+static struct platform_driver tegra_nand_driver = {
+	.driver = {
+		.name = "tegra-nand",
+		.of_match_table = tegra_nand_of_match,
+	},
+	.probe = tegra_nand_probe,
+	.remove = tegra_nand_remove,
+};
+module_platform_driver(tegra_nand_driver);
+
+MODULE_DESCRIPTION("NVIDIA Tegra NAND driver");
+MODULE_AUTHOR("Thierry Reding <thierry.reding@nvidia.com>");
+MODULE_AUTHOR("Lucas Stach <dev@lynxeye.de>");
+MODULE_AUTHOR("Stefan Agner <stefan@agner.ch>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c
index b567d212fe7d..4d61a14fcb65 100644
--- a/drivers/mtd/nand/raw/txx9ndfmc.c
+++ b/drivers/mtd/nand/raw/txx9ndfmc.c
@@ -20,7 +20,7 @@
 #include <linux/mtd/nand_ecc.h>
 #include <linux/mtd/partitions.h>
 #include <linux/io.h>
-#include <asm/txx9/ndfmc.h>
+#include <linux/platform_data/txx9/ndfmc.h>
 
 /* TXX9 NDFMC Registers */
 #define TXX9_NDFDTR	0x00
@@ -73,7 +73,7 @@ struct txx9ndfmc_drvdata {
 	void __iomem *base;
 	unsigned char hold;	/* in gbusclock */
 	unsigned char spw;	/* in gbusclock */
-	struct nand_hw_control hw_control;
+	struct nand_controller controller;
 };
 
 static struct platform_device *mtd_to_platdev(struct mtd_info *mtd)
@@ -254,23 +254,25 @@ static void txx9ndfmc_initialize(struct platform_device *dev)
 #define TXX9NDFMC_NS_TO_CYC(gbusclk, ns) \
 	DIV_ROUND_UP((ns) * DIV_ROUND_UP(gbusclk, 1000), 1000000)
 
-static int txx9ndfmc_nand_scan(struct mtd_info *mtd)
+static int txx9ndfmc_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = mtd_to_nand(mtd);
-	int ret;
-
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (!ret) {
-		if (mtd->writesize >= 512) {
-			/* Hardware ECC 6 byte ECC per 512 Byte data */
-			chip->ecc.size = 512;
-			chip->ecc.bytes = 6;
-		}
-		ret = nand_scan_tail(mtd);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+
+	if (mtd->writesize >= 512) {
+		chip->ecc.size = 512;
+		chip->ecc.bytes = 6;
+	} else {
+		chip->ecc.size = 256;
+		chip->ecc.bytes = 3;
 	}
-	return ret;
+
+	return 0;
 }
 
+static const struct nand_controller_ops txx9ndfmc_controller_ops = {
+	.attach_chip = txx9ndfmc_attach_chip,
+};
+
 static int __init txx9ndfmc_probe(struct platform_device *dev)
 {
 	struct txx9ndfmc_platform_data *plat = dev_get_platdata(&dev->dev);
@@ -303,7 +305,8 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 	dev_info(&dev->dev, "CLK:%ldMHz HOLD:%d SPW:%d\n",
 		 (gbusclk + 500000) / 1000000, hold, spw);
 
-	nand_hw_control_init(&drvdata->hw_control);
+	nand_controller_init(&drvdata->controller);
+	drvdata->controller.ops = &txx9ndfmc_controller_ops;
 
 	platform_set_drvdata(dev, drvdata);
 	txx9ndfmc_initialize(dev);
@@ -332,12 +335,9 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 		chip->ecc.correct = txx9ndfmc_correct_data;
 		chip->ecc.hwctl = txx9ndfmc_enable_hwecc;
 		chip->ecc.mode = NAND_ECC_HW;
-		/* txx9ndfmc_nand_scan will overwrite ecc.size and ecc.bytes */
-		chip->ecc.size = 256;
-		chip->ecc.bytes = 3;
 		chip->ecc.strength = 1;
 		chip->chip_delay = 100;
-		chip->controller = &drvdata->hw_control;
+		chip->controller = &drvdata->controller;
 
 		nand_set_controller_data(chip, txx9_priv);
 		txx9_priv->dev = dev;
@@ -359,14 +359,14 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 		if (plat->wide_mask & (1 << i))
 			chip->options |= NAND_BUSWIDTH_16;
 
-		if (txx9ndfmc_nand_scan(mtd)) {
+		if (nand_scan(mtd, 1)) {
 			kfree(txx9_priv->mtdname);
 			kfree(txx9_priv);
 			continue;
 		}
 		mtd->name = txx9_priv->mtdname;
 
-		mtd_device_parse_register(mtd, NULL, NULL, NULL, 0);
+		mtd_device_register(mtd, NULL, 0);
 		drvdata->mtds[i] = mtd;
 	}
 
diff --git a/drivers/mtd/nand/raw/vf610_nfc.c b/drivers/mtd/nand/raw/vf610_nfc.c
index d5a22fc96878..6f6dcbf9095b 100644
--- a/drivers/mtd/nand/raw/vf610_nfc.c
+++ b/drivers/mtd/nand/raw/vf610_nfc.c
@@ -747,6 +747,69 @@ static void vf610_nfc_init_controller(struct vf610_nfc *nfc)
 	}
 }
 
+static int vf610_nfc_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct vf610_nfc *nfc = mtd_to_nfc(mtd);
+
+	vf610_nfc_init_controller(nfc);
+
+	/* Bad block options. */
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+	/* Single buffer only, max 256 OOB minus ECC status */
+	if (mtd->writesize + mtd->oobsize > PAGE_2K + OOB_MAX - 8) {
+		dev_err(nfc->dev, "Unsupported flash page size\n");
+		return -ENXIO;
+	}
+
+	if (chip->ecc.mode != NAND_ECC_HW)
+		return 0;
+
+	if (mtd->writesize != PAGE_2K && mtd->oobsize < 64) {
+		dev_err(nfc->dev, "Unsupported flash with hwecc\n");
+		return -ENXIO;
+	}
+
+	if (chip->ecc.size != mtd->writesize) {
+		dev_err(nfc->dev, "Step size needs to be page size\n");
+		return -ENXIO;
+	}
+
+	/* Only 64 byte ECC layouts known */
+	if (mtd->oobsize > 64)
+		mtd->oobsize = 64;
+
+	/* Use default large page ECC layout defined in NAND core */
+	mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+	if (chip->ecc.strength == 32) {
+		nfc->ecc_mode = ECC_60_BYTE;
+		chip->ecc.bytes = 60;
+	} else if (chip->ecc.strength == 24) {
+		nfc->ecc_mode = ECC_45_BYTE;
+		chip->ecc.bytes = 45;
+	} else {
+		dev_err(nfc->dev, "Unsupported ECC strength\n");
+		return -ENXIO;
+	}
+
+	chip->ecc.read_page = vf610_nfc_read_page;
+	chip->ecc.write_page = vf610_nfc_write_page;
+	chip->ecc.read_page_raw = vf610_nfc_read_page_raw;
+	chip->ecc.write_page_raw = vf610_nfc_write_page_raw;
+	chip->ecc.read_oob = vf610_nfc_read_oob;
+	chip->ecc.write_oob = vf610_nfc_write_oob;
+
+	chip->ecc.size = PAGE_2K;
+
+	return 0;
+}
+
+static const struct nand_controller_ops vf610_nfc_controller_ops = {
+	.attach_chip = vf610_nfc_attach_chip,
+};
+
 static int vf610_nfc_probe(struct platform_device *pdev)
 {
 	struct vf610_nfc *nfc;
@@ -827,67 +890,9 @@ static int vf610_nfc_probe(struct platform_device *pdev)
 
 	vf610_nfc_preinit_controller(nfc);
 
-	/* first scan to find the device and get the page size */
-	err = nand_scan_ident(mtd, 1, NULL);
-	if (err)
-		goto err_disable_clk;
-
-	vf610_nfc_init_controller(nfc);
-
-	/* Bad block options. */
-	if (chip->bbt_options & NAND_BBT_USE_FLASH)
-		chip->bbt_options |= NAND_BBT_NO_OOB;
-
-	/* Single buffer only, max 256 OOB minus ECC status */
-	if (mtd->writesize + mtd->oobsize > PAGE_2K + OOB_MAX - 8) {
-		dev_err(nfc->dev, "Unsupported flash page size\n");
-		err = -ENXIO;
-		goto err_disable_clk;
-	}
-
-	if (chip->ecc.mode == NAND_ECC_HW) {
-		if (mtd->writesize != PAGE_2K && mtd->oobsize < 64) {
-			dev_err(nfc->dev, "Unsupported flash with hwecc\n");
-			err = -ENXIO;
-			goto err_disable_clk;
-		}
-
-		if (chip->ecc.size != mtd->writesize) {
-			dev_err(nfc->dev, "Step size needs to be page size\n");
-			err = -ENXIO;
-			goto err_disable_clk;
-		}
-
-		/* Only 64 byte ECC layouts known */
-		if (mtd->oobsize > 64)
-			mtd->oobsize = 64;
-
-		/* Use default large page ECC layout defined in NAND core */
-		mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
-		if (chip->ecc.strength == 32) {
-			nfc->ecc_mode = ECC_60_BYTE;
-			chip->ecc.bytes = 60;
-		} else if (chip->ecc.strength == 24) {
-			nfc->ecc_mode = ECC_45_BYTE;
-			chip->ecc.bytes = 45;
-		} else {
-			dev_err(nfc->dev, "Unsupported ECC strength\n");
-			err = -ENXIO;
-			goto err_disable_clk;
-		}
-
-		chip->ecc.read_page = vf610_nfc_read_page;
-		chip->ecc.write_page = vf610_nfc_write_page;
-		chip->ecc.read_page_raw = vf610_nfc_read_page_raw;
-		chip->ecc.write_page_raw = vf610_nfc_write_page_raw;
-		chip->ecc.read_oob = vf610_nfc_read_oob;
-		chip->ecc.write_oob = vf610_nfc_write_oob;
-
-		chip->ecc.size = PAGE_2K;
-	}
-
-	/* second phase scan */
-	err = nand_scan_tail(mtd);
+	/* Scan the NAND chip */
+	chip->dummy_controller.ops = &vf610_nfc_controller_ops;
+	err = nand_scan(mtd, 1);
 	if (err)
 		goto err_disable_clk;
 
diff --git a/drivers/mtd/nand/spi/Kconfig b/drivers/mtd/nand/spi/Kconfig
new file mode 100644
index 000000000000..7c37d2929b68
--- /dev/null
+++ b/drivers/mtd/nand/spi/Kconfig
@@ -0,0 +1,7 @@
+menuconfig MTD_SPI_NAND
+	tristate "SPI NAND device Support"
+	select MTD_NAND_CORE
+	depends on SPI_MASTER
+	select SPI_MEM
+	help
+	  This is the framework for the SPI NAND device drivers.
diff --git a/drivers/mtd/nand/spi/Makefile b/drivers/mtd/nand/spi/Makefile
new file mode 100644
index 000000000000..b74e074b363a
--- /dev/null
+++ b/drivers/mtd/nand/spi/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+spinand-objs := core.o macronix.o micron.o winbond.o
+obj-$(CONFIG_MTD_SPI_NAND) += spinand.o
diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
new file mode 100644
index 000000000000..30f83649c481
--- /dev/null
+++ b/drivers/mtd/nand/spi/core.c
@@ -0,0 +1,1155 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2016-2017 Micron Technology, Inc.
+ *
+ * Authors:
+ *	Peter Pan <peterpandong@micron.com>
+ *	Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+
+#define pr_fmt(fmt)	"spi-nand: " fmt
+
+#include <linux/device.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mtd/spinand.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
+
+static void spinand_cache_op_adjust_colum(struct spinand_device *spinand,
+					  const struct nand_page_io_req *req,
+					  u16 *column)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int shift;
+
+	if (nand->memorg.planes_per_lun < 2)
+		return;
+
+	/* The plane number is passed in MSB just above the column address */
+	shift = fls(nand->memorg.pagesize);
+	*column |= req->pos.plane << shift;
+}
+
+static int spinand_read_reg_op(struct spinand_device *spinand, u8 reg, u8 *val)
+{
+	struct spi_mem_op op = SPINAND_GET_FEATURE_OP(reg,
+						      spinand->scratchbuf);
+	int ret;
+
+	ret = spi_mem_exec_op(spinand->spimem, &op);
+	if (ret)
+		return ret;
+
+	*val = *spinand->scratchbuf;
+	return 0;
+}
+
+static int spinand_write_reg_op(struct spinand_device *spinand, u8 reg, u8 val)
+{
+	struct spi_mem_op op = SPINAND_SET_FEATURE_OP(reg,
+						      spinand->scratchbuf);
+
+	*spinand->scratchbuf = val;
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_read_status(struct spinand_device *spinand, u8 *status)
+{
+	return spinand_read_reg_op(spinand, REG_STATUS, status);
+}
+
+static int spinand_get_cfg(struct spinand_device *spinand, u8 *cfg)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+
+	if (WARN_ON(spinand->cur_target < 0 ||
+		    spinand->cur_target >= nand->memorg.ntargets))
+		return -EINVAL;
+
+	*cfg = spinand->cfg_cache[spinand->cur_target];
+	return 0;
+}
+
+static int spinand_set_cfg(struct spinand_device *spinand, u8 cfg)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	int ret;
+
+	if (WARN_ON(spinand->cur_target < 0 ||
+		    spinand->cur_target >= nand->memorg.ntargets))
+		return -EINVAL;
+
+	if (spinand->cfg_cache[spinand->cur_target] == cfg)
+		return 0;
+
+	ret = spinand_write_reg_op(spinand, REG_CFG, cfg);
+	if (ret)
+		return ret;
+
+	spinand->cfg_cache[spinand->cur_target] = cfg;
+	return 0;
+}
+
+/**
+ * spinand_upd_cfg() - Update the configuration register
+ * @spinand: the spinand device
+ * @mask: the mask encoding the bits to update in the config reg
+ * @val: the new value to apply
+ *
+ * Update the configuration register.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+int spinand_upd_cfg(struct spinand_device *spinand, u8 mask, u8 val)
+{
+	int ret;
+	u8 cfg;
+
+	ret = spinand_get_cfg(spinand, &cfg);
+	if (ret)
+		return ret;
+
+	cfg &= ~mask;
+	cfg |= val;
+
+	return spinand_set_cfg(spinand, cfg);
+}
+
+/**
+ * spinand_select_target() - Select a specific NAND target/die
+ * @spinand: the spinand device
+ * @target: the target/die to select
+ *
+ * Select a new target/die. If chip only has one die, this function is a NOOP.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+int spinand_select_target(struct spinand_device *spinand, unsigned int target)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	int ret;
+
+	if (WARN_ON(target >= nand->memorg.ntargets))
+		return -EINVAL;
+
+	if (spinand->cur_target == target)
+		return 0;
+
+	if (nand->memorg.ntargets == 1) {
+		spinand->cur_target = target;
+		return 0;
+	}
+
+	ret = spinand->select_target(spinand, target);
+	if (ret)
+		return ret;
+
+	spinand->cur_target = target;
+	return 0;
+}
+
+static int spinand_init_cfg_cache(struct spinand_device *spinand)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	struct device *dev = &spinand->spimem->spi->dev;
+	unsigned int target;
+	int ret;
+
+	spinand->cfg_cache = devm_kcalloc(dev,
+					  nand->memorg.ntargets,
+					  sizeof(*spinand->cfg_cache),
+					  GFP_KERNEL);
+	if (!spinand->cfg_cache)
+		return -ENOMEM;
+
+	for (target = 0; target < nand->memorg.ntargets; target++) {
+		ret = spinand_select_target(spinand, target);
+		if (ret)
+			return ret;
+
+		/*
+		 * We use spinand_read_reg_op() instead of spinand_get_cfg()
+		 * here to bypass the config cache.
+		 */
+		ret = spinand_read_reg_op(spinand, REG_CFG,
+					  &spinand->cfg_cache[target]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int spinand_init_quad_enable(struct spinand_device *spinand)
+{
+	bool enable = false;
+
+	if (!(spinand->flags & SPINAND_HAS_QE_BIT))
+		return 0;
+
+	if (spinand->op_templates.read_cache->data.buswidth == 4 ||
+	    spinand->op_templates.write_cache->data.buswidth == 4 ||
+	    spinand->op_templates.update_cache->data.buswidth == 4)
+		enable = true;
+
+	return spinand_upd_cfg(spinand, CFG_QUAD_ENABLE,
+			       enable ? CFG_QUAD_ENABLE : 0);
+}
+
+static int spinand_ecc_enable(struct spinand_device *spinand,
+			      bool enable)
+{
+	return spinand_upd_cfg(spinand, CFG_ECC_ENABLE,
+			       enable ? CFG_ECC_ENABLE : 0);
+}
+
+static int spinand_write_enable_op(struct spinand_device *spinand)
+{
+	struct spi_mem_op op = SPINAND_WR_EN_DIS_OP(true);
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_load_page_op(struct spinand_device *spinand,
+				const struct nand_page_io_req *req)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int row = nanddev_pos_to_row(nand, &req->pos);
+	struct spi_mem_op op = SPINAND_PAGE_READ_OP(row);
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_read_from_cache_op(struct spinand_device *spinand,
+				      const struct nand_page_io_req *req)
+{
+	struct spi_mem_op op = *spinand->op_templates.read_cache;
+	struct nand_device *nand = spinand_to_nand(spinand);
+	struct mtd_info *mtd = nanddev_to_mtd(nand);
+	struct nand_page_io_req adjreq = *req;
+	unsigned int nbytes = 0;
+	void *buf = NULL;
+	u16 column = 0;
+	int ret;
+
+	if (req->datalen) {
+		adjreq.datalen = nanddev_page_size(nand);
+		adjreq.dataoffs = 0;
+		adjreq.databuf.in = spinand->databuf;
+		buf = spinand->databuf;
+		nbytes = adjreq.datalen;
+	}
+
+	if (req->ooblen) {
+		adjreq.ooblen = nanddev_per_page_oobsize(nand);
+		adjreq.ooboffs = 0;
+		adjreq.oobbuf.in = spinand->oobbuf;
+		nbytes += nanddev_per_page_oobsize(nand);
+		if (!buf) {
+			buf = spinand->oobbuf;
+			column = nanddev_page_size(nand);
+		}
+	}
+
+	spinand_cache_op_adjust_colum(spinand, &adjreq, &column);
+	op.addr.val = column;
+
+	/*
+	 * Some controllers are limited in term of max RX data size. In this
+	 * case, just repeat the READ_CACHE operation after updating the
+	 * column.
+	 */
+	while (nbytes) {
+		op.data.buf.in = buf;
+		op.data.nbytes = nbytes;
+		ret = spi_mem_adjust_op_size(spinand->spimem, &op);
+		if (ret)
+			return ret;
+
+		ret = spi_mem_exec_op(spinand->spimem, &op);
+		if (ret)
+			return ret;
+
+		buf += op.data.nbytes;
+		nbytes -= op.data.nbytes;
+		op.addr.val += op.data.nbytes;
+	}
+
+	if (req->datalen)
+		memcpy(req->databuf.in, spinand->databuf + req->dataoffs,
+		       req->datalen);
+
+	if (req->ooblen) {
+		if (req->mode == MTD_OPS_AUTO_OOB)
+			mtd_ooblayout_get_databytes(mtd, req->oobbuf.in,
+						    spinand->oobbuf,
+						    req->ooboffs,
+						    req->ooblen);
+		else
+			memcpy(req->oobbuf.in, spinand->oobbuf + req->ooboffs,
+			       req->ooblen);
+	}
+
+	return 0;
+}
+
+static int spinand_write_to_cache_op(struct spinand_device *spinand,
+				     const struct nand_page_io_req *req)
+{
+	struct spi_mem_op op = *spinand->op_templates.write_cache;
+	struct nand_device *nand = spinand_to_nand(spinand);
+	struct mtd_info *mtd = nanddev_to_mtd(nand);
+	struct nand_page_io_req adjreq = *req;
+	unsigned int nbytes = 0;
+	void *buf = NULL;
+	u16 column = 0;
+	int ret;
+
+	memset(spinand->databuf, 0xff,
+	       nanddev_page_size(nand) +
+	       nanddev_per_page_oobsize(nand));
+
+	if (req->datalen) {
+		memcpy(spinand->databuf + req->dataoffs, req->databuf.out,
+		       req->datalen);
+		adjreq.dataoffs = 0;
+		adjreq.datalen = nanddev_page_size(nand);
+		adjreq.databuf.out = spinand->databuf;
+		nbytes = adjreq.datalen;
+		buf = spinand->databuf;
+	}
+
+	if (req->ooblen) {
+		if (req->mode == MTD_OPS_AUTO_OOB)
+			mtd_ooblayout_set_databytes(mtd, req->oobbuf.out,
+						    spinand->oobbuf,
+						    req->ooboffs,
+						    req->ooblen);
+		else
+			memcpy(spinand->oobbuf + req->ooboffs, req->oobbuf.out,
+			       req->ooblen);
+
+		adjreq.ooblen = nanddev_per_page_oobsize(nand);
+		adjreq.ooboffs = 0;
+		nbytes += nanddev_per_page_oobsize(nand);
+		if (!buf) {
+			buf = spinand->oobbuf;
+			column = nanddev_page_size(nand);
+		}
+	}
+
+	spinand_cache_op_adjust_colum(spinand, &adjreq, &column);
+
+	op = *spinand->op_templates.write_cache;
+	op.addr.val = column;
+
+	/*
+	 * Some controllers are limited in term of max TX data size. In this
+	 * case, split the operation into one LOAD CACHE and one or more
+	 * LOAD RANDOM CACHE.
+	 */
+	while (nbytes) {
+		op.data.buf.out = buf;
+		op.data.nbytes = nbytes;
+
+		ret = spi_mem_adjust_op_size(spinand->spimem, &op);
+		if (ret)
+			return ret;
+
+		ret = spi_mem_exec_op(spinand->spimem, &op);
+		if (ret)
+			return ret;
+
+		buf += op.data.nbytes;
+		nbytes -= op.data.nbytes;
+		op.addr.val += op.data.nbytes;
+
+		/*
+		 * We need to use the RANDOM LOAD CACHE operation if there's
+		 * more than one iteration, because the LOAD operation resets
+		 * the cache to 0xff.
+		 */
+		if (nbytes) {
+			column = op.addr.val;
+			op = *spinand->op_templates.update_cache;
+			op.addr.val = column;
+		}
+	}
+
+	return 0;
+}
+
+static int spinand_program_op(struct spinand_device *spinand,
+			      const struct nand_page_io_req *req)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int row = nanddev_pos_to_row(nand, &req->pos);
+	struct spi_mem_op op = SPINAND_PROG_EXEC_OP(row);
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_erase_op(struct spinand_device *spinand,
+			    const struct nand_pos *pos)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int row = nanddev_pos_to_row(nand, pos);
+	struct spi_mem_op op = SPINAND_BLK_ERASE_OP(row);
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_wait(struct spinand_device *spinand, u8 *s)
+{
+	unsigned long timeo =  jiffies + msecs_to_jiffies(400);
+	u8 status;
+	int ret;
+
+	do {
+		ret = spinand_read_status(spinand, &status);
+		if (ret)
+			return ret;
+
+		if (!(status & STATUS_BUSY))
+			goto out;
+	} while (time_before(jiffies, timeo));
+
+	/*
+	 * Extra read, just in case the STATUS_READY bit has changed
+	 * since our last check
+	 */
+	ret = spinand_read_status(spinand, &status);
+	if (ret)
+		return ret;
+
+out:
+	if (s)
+		*s = status;
+
+	return status & STATUS_BUSY ? -ETIMEDOUT : 0;
+}
+
+static int spinand_read_id_op(struct spinand_device *spinand, u8 *buf)
+{
+	struct spi_mem_op op = SPINAND_READID_OP(0, spinand->scratchbuf,
+						 SPINAND_MAX_ID_LEN);
+	int ret;
+
+	ret = spi_mem_exec_op(spinand->spimem, &op);
+	if (!ret)
+		memcpy(buf, spinand->scratchbuf, SPINAND_MAX_ID_LEN);
+
+	return ret;
+}
+
+static int spinand_reset_op(struct spinand_device *spinand)
+{
+	struct spi_mem_op op = SPINAND_RESET_OP;
+	int ret;
+
+	ret = spi_mem_exec_op(spinand->spimem, &op);
+	if (ret)
+		return ret;
+
+	return spinand_wait(spinand, NULL);
+}
+
+static int spinand_lock_block(struct spinand_device *spinand, u8 lock)
+{
+	return spinand_write_reg_op(spinand, REG_BLOCK_LOCK, lock);
+}
+
+static int spinand_check_ecc_status(struct spinand_device *spinand, u8 status)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+
+	if (spinand->eccinfo.get_status)
+		return spinand->eccinfo.get_status(spinand, status);
+
+	switch (status & STATUS_ECC_MASK) {
+	case STATUS_ECC_NO_BITFLIPS:
+		return 0;
+
+	case STATUS_ECC_HAS_BITFLIPS:
+		/*
+		 * We have no way to know exactly how many bitflips have been
+		 * fixed, so let's return the maximum possible value so that
+		 * wear-leveling layers move the data immediately.
+		 */
+		return nand->eccreq.strength;
+
+	case STATUS_ECC_UNCOR_ERROR:
+		return -EBADMSG;
+
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static int spinand_read_page(struct spinand_device *spinand,
+			     const struct nand_page_io_req *req,
+			     bool ecc_enabled)
+{
+	u8 status;
+	int ret;
+
+	ret = spinand_load_page_op(spinand, req);
+	if (ret)
+		return ret;
+
+	ret = spinand_wait(spinand, &status);
+	if (ret < 0)
+		return ret;
+
+	ret = spinand_read_from_cache_op(spinand, req);
+	if (ret)
+		return ret;
+
+	if (!ecc_enabled)
+		return 0;
+
+	return spinand_check_ecc_status(spinand, status);
+}
+
+static int spinand_write_page(struct spinand_device *spinand,
+			      const struct nand_page_io_req *req)
+{
+	u8 status;
+	int ret;
+
+	ret = spinand_write_enable_op(spinand);
+	if (ret)
+		return ret;
+
+	ret = spinand_write_to_cache_op(spinand, req);
+	if (ret)
+		return ret;
+
+	ret = spinand_program_op(spinand, req);
+	if (ret)
+		return ret;
+
+	ret = spinand_wait(spinand, &status);
+	if (!ret && (status & STATUS_PROG_FAILED))
+		ret = -EIO;
+
+	return ret;
+}
+
+static int spinand_mtd_read(struct mtd_info *mtd, loff_t from,
+			    struct mtd_oob_ops *ops)
+{
+	struct spinand_device *spinand = mtd_to_spinand(mtd);
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	unsigned int max_bitflips = 0;
+	struct nand_io_iter iter;
+	bool enable_ecc = false;
+	bool ecc_failed = false;
+	int ret = 0;
+
+	if (ops->mode != MTD_OPS_RAW && spinand->eccinfo.ooblayout)
+		enable_ecc = true;
+
+	mutex_lock(&spinand->lock);
+
+	nanddev_io_for_each_page(nand, from, ops, &iter) {
+		ret = spinand_select_target(spinand, iter.req.pos.target);
+		if (ret)
+			break;
+
+		ret = spinand_ecc_enable(spinand, enable_ecc);
+		if (ret)
+			break;
+
+		ret = spinand_read_page(spinand, &iter.req, enable_ecc);
+		if (ret < 0 && ret != -EBADMSG)
+			break;
+
+		if (ret == -EBADMSG) {
+			ecc_failed = true;
+			mtd->ecc_stats.failed++;
+			ret = 0;
+		} else {
+			mtd->ecc_stats.corrected += ret;
+			max_bitflips = max_t(unsigned int, max_bitflips, ret);
+		}
+
+		ops->retlen += iter.req.datalen;
+		ops->oobretlen += iter.req.ooblen;
+	}
+
+	mutex_unlock(&spinand->lock);
+
+	if (ecc_failed && !ret)
+		ret = -EBADMSG;
+
+	return ret ? ret : max_bitflips;
+}
+
+static int spinand_mtd_write(struct mtd_info *mtd, loff_t to,
+			     struct mtd_oob_ops *ops)
+{
+	struct spinand_device *spinand = mtd_to_spinand(mtd);
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	struct nand_io_iter iter;
+	bool enable_ecc = false;
+	int ret = 0;
+
+	if (ops->mode != MTD_OPS_RAW && mtd->ooblayout)
+		enable_ecc = true;
+
+	mutex_lock(&spinand->lock);
+
+	nanddev_io_for_each_page(nand, to, ops, &iter) {
+		ret = spinand_select_target(spinand, iter.req.pos.target);
+		if (ret)
+			break;
+
+		ret = spinand_ecc_enable(spinand, enable_ecc);
+		if (ret)
+			break;
+
+		ret = spinand_write_page(spinand, &iter.req);
+		if (ret)
+			break;
+
+		ops->retlen += iter.req.datalen;
+		ops->oobretlen += iter.req.ooblen;
+	}
+
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static bool spinand_isbad(struct nand_device *nand, const struct nand_pos *pos)
+{
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	struct nand_page_io_req req = {
+		.pos = *pos,
+		.ooblen = 2,
+		.ooboffs = 0,
+		.oobbuf.in = spinand->oobbuf,
+		.mode = MTD_OPS_RAW,
+	};
+
+	memset(spinand->oobbuf, 0, 2);
+	spinand_select_target(spinand, pos->target);
+	spinand_read_page(spinand, &req, false);
+	if (spinand->oobbuf[0] != 0xff || spinand->oobbuf[1] != 0xff)
+		return true;
+
+	return false;
+}
+
+static int spinand_mtd_block_isbad(struct mtd_info *mtd, loff_t offs)
+{
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	struct nand_pos pos;
+	int ret;
+
+	nanddev_offs_to_pos(nand, offs, &pos);
+	mutex_lock(&spinand->lock);
+	ret = nanddev_isbad(nand, &pos);
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static int spinand_markbad(struct nand_device *nand, const struct nand_pos *pos)
+{
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	struct nand_page_io_req req = {
+		.pos = *pos,
+		.ooboffs = 0,
+		.ooblen = 2,
+		.oobbuf.out = spinand->oobbuf,
+	};
+	int ret;
+
+	/* Erase block before marking it bad. */
+	ret = spinand_select_target(spinand, pos->target);
+	if (ret)
+		return ret;
+
+	ret = spinand_write_enable_op(spinand);
+	if (ret)
+		return ret;
+
+	spinand_erase_op(spinand, pos);
+
+	memset(spinand->oobbuf, 0, 2);
+	return spinand_write_page(spinand, &req);
+}
+
+static int spinand_mtd_block_markbad(struct mtd_info *mtd, loff_t offs)
+{
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	struct nand_pos pos;
+	int ret;
+
+	nanddev_offs_to_pos(nand, offs, &pos);
+	mutex_lock(&spinand->lock);
+	ret = nanddev_markbad(nand, &pos);
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static int spinand_erase(struct nand_device *nand, const struct nand_pos *pos)
+{
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	u8 status;
+	int ret;
+
+	ret = spinand_select_target(spinand, pos->target);
+	if (ret)
+		return ret;
+
+	ret = spinand_write_enable_op(spinand);
+	if (ret)
+		return ret;
+
+	ret = spinand_erase_op(spinand, pos);
+	if (ret)
+		return ret;
+
+	ret = spinand_wait(spinand, &status);
+	if (!ret && (status & STATUS_ERASE_FAILED))
+		ret = -EIO;
+
+	return ret;
+}
+
+static int spinand_mtd_erase(struct mtd_info *mtd,
+			     struct erase_info *einfo)
+{
+	struct spinand_device *spinand = mtd_to_spinand(mtd);
+	int ret;
+
+	mutex_lock(&spinand->lock);
+	ret = nanddev_mtd_erase(mtd, einfo);
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static int spinand_mtd_block_isreserved(struct mtd_info *mtd, loff_t offs)
+{
+	struct spinand_device *spinand = mtd_to_spinand(mtd);
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	struct nand_pos pos;
+	int ret;
+
+	nanddev_offs_to_pos(nand, offs, &pos);
+	mutex_lock(&spinand->lock);
+	ret = nanddev_isreserved(nand, &pos);
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static const struct nand_ops spinand_ops = {
+	.erase = spinand_erase,
+	.markbad = spinand_markbad,
+	.isbad = spinand_isbad,
+};
+
+static const struct spinand_manufacturer *spinand_manufacturers[] = {
+	&macronix_spinand_manufacturer,
+	&micron_spinand_manufacturer,
+	&winbond_spinand_manufacturer,
+};
+
+static int spinand_manufacturer_detect(struct spinand_device *spinand)
+{
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < ARRAY_SIZE(spinand_manufacturers); i++) {
+		ret = spinand_manufacturers[i]->ops->detect(spinand);
+		if (ret > 0) {
+			spinand->manufacturer = spinand_manufacturers[i];
+			return 0;
+		} else if (ret < 0) {
+			return ret;
+		}
+	}
+
+	return -ENOTSUPP;
+}
+
+static int spinand_manufacturer_init(struct spinand_device *spinand)
+{
+	if (spinand->manufacturer->ops->init)
+		return spinand->manufacturer->ops->init(spinand);
+
+	return 0;
+}
+
+static void spinand_manufacturer_cleanup(struct spinand_device *spinand)
+{
+	/* Release manufacturer private data */
+	if (spinand->manufacturer->ops->cleanup)
+		return spinand->manufacturer->ops->cleanup(spinand);
+}
+
+static const struct spi_mem_op *
+spinand_select_op_variant(struct spinand_device *spinand,
+			  const struct spinand_op_variants *variants)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int i;
+
+	for (i = 0; i < variants->nops; i++) {
+		struct spi_mem_op op = variants->ops[i];
+		unsigned int nbytes;
+		int ret;
+
+		nbytes = nanddev_per_page_oobsize(nand) +
+			 nanddev_page_size(nand);
+
+		while (nbytes) {
+			op.data.nbytes = nbytes;
+			ret = spi_mem_adjust_op_size(spinand->spimem, &op);
+			if (ret)
+				break;
+
+			if (!spi_mem_supports_op(spinand->spimem, &op))
+				break;
+
+			nbytes -= op.data.nbytes;
+		}
+
+		if (!nbytes)
+			return &variants->ops[i];
+	}
+
+	return NULL;
+}
+
+/**
+ * spinand_match_and_init() - Try to find a match between a device ID and an
+ *			      entry in a spinand_info table
+ * @spinand: SPI NAND object
+ * @table: SPI NAND device description table
+ * @table_size: size of the device description table
+ *
+ * Should be used by SPI NAND manufacturer drivers when they want to find a
+ * match between a device ID retrieved through the READ_ID command and an
+ * entry in the SPI NAND description table. If a match is found, the spinand
+ * object will be initialized with information provided by the matching
+ * spinand_info entry.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+int spinand_match_and_init(struct spinand_device *spinand,
+			   const struct spinand_info *table,
+			   unsigned int table_size, u8 devid)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int i;
+
+	for (i = 0; i < table_size; i++) {
+		const struct spinand_info *info = &table[i];
+		const struct spi_mem_op *op;
+
+		if (devid != info->devid)
+			continue;
+
+		nand->memorg = table[i].memorg;
+		nand->eccreq = table[i].eccreq;
+		spinand->eccinfo = table[i].eccinfo;
+		spinand->flags = table[i].flags;
+		spinand->select_target = table[i].select_target;
+
+		op = spinand_select_op_variant(spinand,
+					       info->op_variants.read_cache);
+		if (!op)
+			return -ENOTSUPP;
+
+		spinand->op_templates.read_cache = op;
+
+		op = spinand_select_op_variant(spinand,
+					       info->op_variants.write_cache);
+		if (!op)
+			return -ENOTSUPP;
+
+		spinand->op_templates.write_cache = op;
+
+		op = spinand_select_op_variant(spinand,
+					       info->op_variants.update_cache);
+		spinand->op_templates.update_cache = op;
+
+		return 0;
+	}
+
+	return -ENOTSUPP;
+}
+
+static int spinand_detect(struct spinand_device *spinand)
+{
+	struct device *dev = &spinand->spimem->spi->dev;
+	struct nand_device *nand = spinand_to_nand(spinand);
+	int ret;
+
+	ret = spinand_reset_op(spinand);
+	if (ret)
+		return ret;
+
+	ret = spinand_read_id_op(spinand, spinand->id.data);
+	if (ret)
+		return ret;
+
+	spinand->id.len = SPINAND_MAX_ID_LEN;
+
+	ret = spinand_manufacturer_detect(spinand);
+	if (ret) {
+		dev_err(dev, "unknown raw ID %*phN\n", SPINAND_MAX_ID_LEN,
+			spinand->id.data);
+		return ret;
+	}
+
+	if (nand->memorg.ntargets > 1 && !spinand->select_target) {
+		dev_err(dev,
+			"SPI NANDs with more than one die must implement ->select_target()\n");
+		return -EINVAL;
+	}
+
+	dev_info(&spinand->spimem->spi->dev,
+		 "%s SPI NAND was found.\n", spinand->manufacturer->name);
+	dev_info(&spinand->spimem->spi->dev,
+		 "%llu MiB, block size: %zu KiB, page size: %zu, OOB size: %u\n",
+		 nanddev_size(nand) >> 20, nanddev_eraseblock_size(nand) >> 10,
+		 nanddev_page_size(nand), nanddev_per_page_oobsize(nand));
+
+	return 0;
+}
+
+static int spinand_noecc_ooblayout_ecc(struct mtd_info *mtd, int section,
+				       struct mtd_oob_region *region)
+{
+	return -ERANGE;
+}
+
+static int spinand_noecc_ooblayout_free(struct mtd_info *mtd, int section,
+					struct mtd_oob_region *region)
+{
+	if (section)
+		return -ERANGE;
+
+	/* Reserve 2 bytes for the BBM. */
+	region->offset = 2;
+	region->length = 62;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops spinand_noecc_ooblayout = {
+	.ecc = spinand_noecc_ooblayout_ecc,
+	.free = spinand_noecc_ooblayout_free,
+};
+
+static int spinand_init(struct spinand_device *spinand)
+{
+	struct device *dev = &spinand->spimem->spi->dev;
+	struct mtd_info *mtd = spinand_to_mtd(spinand);
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	int ret, i;
+
+	/*
+	 * We need a scratch buffer because the spi_mem interface requires that
+	 * buf passed in spi_mem_op->data.buf be DMA-able.
+	 */
+	spinand->scratchbuf = kzalloc(SPINAND_MAX_ID_LEN, GFP_KERNEL);
+	if (!spinand->scratchbuf)
+		return -ENOMEM;
+
+	ret = spinand_detect(spinand);
+	if (ret)
+		goto err_free_bufs;
+
+	/*
+	 * Use kzalloc() instead of devm_kzalloc() here, because some drivers
+	 * may use this buffer for DMA access.
+	 * Memory allocated by devm_ does not guarantee DMA-safe alignment.
+	 */
+	spinand->databuf = kzalloc(nanddev_page_size(nand) +
+			       nanddev_per_page_oobsize(nand),
+			       GFP_KERNEL);
+	if (!spinand->databuf) {
+		ret = -ENOMEM;
+		goto err_free_bufs;
+	}
+
+	spinand->oobbuf = spinand->databuf + nanddev_page_size(nand);
+
+	ret = spinand_init_cfg_cache(spinand);
+	if (ret)
+		goto err_free_bufs;
+
+	ret = spinand_init_quad_enable(spinand);
+	if (ret)
+		goto err_free_bufs;
+
+	ret = spinand_upd_cfg(spinand, CFG_OTP_ENABLE, 0);
+	if (ret)
+		goto err_free_bufs;
+
+	ret = spinand_manufacturer_init(spinand);
+	if (ret) {
+		dev_err(dev,
+			"Failed to initialize the SPI NAND chip (err = %d)\n",
+			ret);
+		goto err_free_bufs;
+	}
+
+	/* After power up, all blocks are locked, so unlock them here. */
+	for (i = 0; i < nand->memorg.ntargets; i++) {
+		ret = spinand_select_target(spinand, i);
+		if (ret)
+			goto err_free_bufs;
+
+		ret = spinand_lock_block(spinand, BL_ALL_UNLOCKED);
+		if (ret)
+			goto err_free_bufs;
+	}
+
+	ret = nanddev_init(nand, &spinand_ops, THIS_MODULE);
+	if (ret)
+		goto err_manuf_cleanup;
+
+	/*
+	 * Right now, we don't support ECC, so let the whole oob
+	 * area is available for user.
+	 */
+	mtd->_read_oob = spinand_mtd_read;
+	mtd->_write_oob = spinand_mtd_write;
+	mtd->_block_isbad = spinand_mtd_block_isbad;
+	mtd->_block_markbad = spinand_mtd_block_markbad;
+	mtd->_block_isreserved = spinand_mtd_block_isreserved;
+	mtd->_erase = spinand_mtd_erase;
+
+	if (spinand->eccinfo.ooblayout)
+		mtd_set_ooblayout(mtd, spinand->eccinfo.ooblayout);
+	else
+		mtd_set_ooblayout(mtd, &spinand_noecc_ooblayout);
+
+	ret = mtd_ooblayout_count_freebytes(mtd);
+	if (ret < 0)
+		goto err_cleanup_nanddev;
+
+	mtd->oobavail = ret;
+
+	return 0;
+
+err_cleanup_nanddev:
+	nanddev_cleanup(nand);
+
+err_manuf_cleanup:
+	spinand_manufacturer_cleanup(spinand);
+
+err_free_bufs:
+	kfree(spinand->databuf);
+	kfree(spinand->scratchbuf);
+	return ret;
+}
+
+static void spinand_cleanup(struct spinand_device *spinand)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+
+	nanddev_cleanup(nand);
+	spinand_manufacturer_cleanup(spinand);
+	kfree(spinand->databuf);
+	kfree(spinand->scratchbuf);
+}
+
+static int spinand_probe(struct spi_mem *mem)
+{
+	struct spinand_device *spinand;
+	struct mtd_info *mtd;
+	int ret;
+
+	spinand = devm_kzalloc(&mem->spi->dev, sizeof(*spinand),
+			       GFP_KERNEL);
+	if (!spinand)
+		return -ENOMEM;
+
+	spinand->spimem = mem;
+	spi_mem_set_drvdata(mem, spinand);
+	spinand_set_of_node(spinand, mem->spi->dev.of_node);
+	mutex_init(&spinand->lock);
+	mtd = spinand_to_mtd(spinand);
+	mtd->dev.parent = &mem->spi->dev;
+
+	ret = spinand_init(spinand);
+	if (ret)
+		return ret;
+
+	ret = mtd_device_register(mtd, NULL, 0);
+	if (ret)
+		goto err_spinand_cleanup;
+
+	return 0;
+
+err_spinand_cleanup:
+	spinand_cleanup(spinand);
+
+	return ret;
+}
+
+static int spinand_remove(struct spi_mem *mem)
+{
+	struct spinand_device *spinand;
+	struct mtd_info *mtd;
+	int ret;
+
+	spinand = spi_mem_get_drvdata(mem);
+	mtd = spinand_to_mtd(spinand);
+
+	ret = mtd_device_unregister(mtd);
+	if (ret)
+		return ret;
+
+	spinand_cleanup(spinand);
+
+	return 0;
+}
+
+static const struct spi_device_id spinand_ids[] = {
+	{ .name = "spi-nand" },
+	{ /* sentinel */ },
+};
+
+#ifdef CONFIG_OF
+static const struct of_device_id spinand_of_ids[] = {
+	{ .compatible = "spi-nand" },
+	{ /* sentinel */ },
+};
+#endif
+
+static struct spi_mem_driver spinand_drv = {
+	.spidrv = {
+		.id_table = spinand_ids,
+		.driver = {
+			.name = "spi-nand",
+			.of_match_table = of_match_ptr(spinand_of_ids),
+		},
+	},
+	.probe = spinand_probe,
+	.remove = spinand_remove,
+};
+module_spi_mem_driver(spinand_drv);
+
+MODULE_DESCRIPTION("SPI NAND framework");
+MODULE_AUTHOR("Peter Pan<peterpandong@micron.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mtd/nand/spi/macronix.c b/drivers/mtd/nand/spi/macronix.c
new file mode 100644
index 000000000000..98f6b9c4b684
--- /dev/null
+++ b/drivers/mtd/nand/spi/macronix.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 Macronix
+ *
+ * Author: Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/mtd/spinand.h>
+
+#define SPINAND_MFR_MACRONIX		0xC2
+
+static SPINAND_OP_VARIANTS(read_cache_variants,
+		SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0));
+
+static SPINAND_OP_VARIANTS(write_cache_variants,
+		SPINAND_PROG_LOAD_X4(true, 0, NULL, 0),
+		SPINAND_PROG_LOAD(true, 0, NULL, 0));
+
+static SPINAND_OP_VARIANTS(update_cache_variants,
+		SPINAND_PROG_LOAD_X4(false, 0, NULL, 0),
+		SPINAND_PROG_LOAD(false, 0, NULL, 0));
+
+static int mx35lfxge4ab_ooblayout_ecc(struct mtd_info *mtd, int section,
+				      struct mtd_oob_region *region)
+{
+	return -ERANGE;
+}
+
+static int mx35lfxge4ab_ooblayout_free(struct mtd_info *mtd, int section,
+				       struct mtd_oob_region *region)
+{
+	if (section)
+		return -ERANGE;
+
+	region->offset = 2;
+	region->length = mtd->oobsize - 2;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops mx35lfxge4ab_ooblayout = {
+	.ecc = mx35lfxge4ab_ooblayout_ecc,
+	.free = mx35lfxge4ab_ooblayout_free,
+};
+
+static int mx35lf1ge4ab_get_eccsr(struct spinand_device *spinand, u8 *eccsr)
+{
+	struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(0x7c, 1),
+					  SPI_MEM_OP_NO_ADDR,
+					  SPI_MEM_OP_DUMMY(1, 1),
+					  SPI_MEM_OP_DATA_IN(1, eccsr, 1));
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int mx35lf1ge4ab_ecc_get_status(struct spinand_device *spinand,
+				       u8 status)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	u8 eccsr;
+
+	switch (status & STATUS_ECC_MASK) {
+	case STATUS_ECC_NO_BITFLIPS:
+		return 0;
+
+	case STATUS_ECC_UNCOR_ERROR:
+		return -EBADMSG;
+
+	case STATUS_ECC_HAS_BITFLIPS:
+		/*
+		 * Let's try to retrieve the real maximum number of bitflips
+		 * in order to avoid forcing the wear-leveling layer to move
+		 * data around if it's not necessary.
+		 */
+		if (mx35lf1ge4ab_get_eccsr(spinand, &eccsr))
+			return nand->eccreq.strength;
+
+		if (WARN_ON(eccsr > nand->eccreq.strength || !eccsr))
+			return nand->eccreq.strength;
+
+		return eccsr;
+
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static const struct spinand_info macronix_spinand_table[] = {
+	SPINAND_INFO("MX35LF1GE4AB", 0x12,
+		     NAND_MEMORG(1, 2048, 64, 64, 1024, 1, 1, 1),
+		     NAND_ECCREQ(4, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     SPINAND_HAS_QE_BIT,
+		     SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout,
+				     mx35lf1ge4ab_ecc_get_status)),
+	SPINAND_INFO("MX35LF2GE4AB", 0x22,
+		     NAND_MEMORG(1, 2048, 64, 64, 2048, 2, 1, 1),
+		     NAND_ECCREQ(4, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     SPINAND_HAS_QE_BIT,
+		     SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout, NULL)),
+};
+
+static int macronix_spinand_detect(struct spinand_device *spinand)
+{
+	u8 *id = spinand->id.data;
+	int ret;
+
+	/*
+	 * Macronix SPI NAND read ID needs a dummy byte, so the first byte in
+	 * raw_id is garbage.
+	 */
+	if (id[1] != SPINAND_MFR_MACRONIX)
+		return 0;
+
+	ret = spinand_match_and_init(spinand, macronix_spinand_table,
+				     ARRAY_SIZE(macronix_spinand_table),
+				     id[2]);
+	if (ret)
+		return ret;
+
+	return 1;
+}
+
+static const struct spinand_manufacturer_ops macronix_spinand_manuf_ops = {
+	.detect = macronix_spinand_detect,
+};
+
+const struct spinand_manufacturer macronix_spinand_manufacturer = {
+	.id = SPINAND_MFR_MACRONIX,
+	.name = "Macronix",
+	.ops = &macronix_spinand_manuf_ops,
+};
diff --git a/drivers/mtd/nand/spi/micron.c b/drivers/mtd/nand/spi/micron.c
new file mode 100644
index 000000000000..9c4381d6847b
--- /dev/null
+++ b/drivers/mtd/nand/spi/micron.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2016-2017 Micron Technology, Inc.
+ *
+ * Authors:
+ *	Peter Pan <peterpandong@micron.com>
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/mtd/spinand.h>
+
+#define SPINAND_MFR_MICRON		0x2c
+
+#define MICRON_STATUS_ECC_MASK		GENMASK(7, 4)
+#define MICRON_STATUS_ECC_NO_BITFLIPS	(0 << 4)
+#define MICRON_STATUS_ECC_1TO3_BITFLIPS	(1 << 4)
+#define MICRON_STATUS_ECC_4TO6_BITFLIPS	(3 << 4)
+#define MICRON_STATUS_ECC_7TO8_BITFLIPS	(5 << 4)
+
+static SPINAND_OP_VARIANTS(read_cache_variants,
+		SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 2, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0));
+
+static SPINAND_OP_VARIANTS(write_cache_variants,
+		SPINAND_PROG_LOAD_X4(true, 0, NULL, 0),
+		SPINAND_PROG_LOAD(true, 0, NULL, 0));
+
+static SPINAND_OP_VARIANTS(update_cache_variants,
+		SPINAND_PROG_LOAD_X4(false, 0, NULL, 0),
+		SPINAND_PROG_LOAD(false, 0, NULL, 0));
+
+static int mt29f2g01abagd_ooblayout_ecc(struct mtd_info *mtd, int section,
+					struct mtd_oob_region *region)
+{
+	if (section)
+		return -ERANGE;
+
+	region->offset = 64;
+	region->length = 64;
+
+	return 0;
+}
+
+static int mt29f2g01abagd_ooblayout_free(struct mtd_info *mtd, int section,
+					 struct mtd_oob_region *region)
+{
+	if (section)
+		return -ERANGE;
+
+	/* Reserve 2 bytes for the BBM. */
+	region->offset = 2;
+	region->length = 62;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops mt29f2g01abagd_ooblayout = {
+	.ecc = mt29f2g01abagd_ooblayout_ecc,
+	.free = mt29f2g01abagd_ooblayout_free,
+};
+
+static int mt29f2g01abagd_ecc_get_status(struct spinand_device *spinand,
+					 u8 status)
+{
+	switch (status & MICRON_STATUS_ECC_MASK) {
+	case STATUS_ECC_NO_BITFLIPS:
+		return 0;
+
+	case STATUS_ECC_UNCOR_ERROR:
+		return -EBADMSG;
+
+	case MICRON_STATUS_ECC_1TO3_BITFLIPS:
+		return 3;
+
+	case MICRON_STATUS_ECC_4TO6_BITFLIPS:
+		return 6;
+
+	case MICRON_STATUS_ECC_7TO8_BITFLIPS:
+		return 8;
+
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static const struct spinand_info micron_spinand_table[] = {
+	SPINAND_INFO("MT29F2G01ABAGD", 0x24,
+		     NAND_MEMORG(1, 2048, 128, 64, 2048, 2, 1, 1),
+		     NAND_ECCREQ(8, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     0,
+		     SPINAND_ECCINFO(&mt29f2g01abagd_ooblayout,
+				     mt29f2g01abagd_ecc_get_status)),
+};
+
+static int micron_spinand_detect(struct spinand_device *spinand)
+{
+	u8 *id = spinand->id.data;
+	int ret;
+
+	/*
+	 * Micron SPI NAND read ID need a dummy byte,
+	 * so the first byte in raw_id is dummy.
+	 */
+	if (id[1] != SPINAND_MFR_MICRON)
+		return 0;
+
+	ret = spinand_match_and_init(spinand, micron_spinand_table,
+				     ARRAY_SIZE(micron_spinand_table), id[2]);
+	if (ret)
+		return ret;
+
+	return 1;
+}
+
+static const struct spinand_manufacturer_ops micron_spinand_manuf_ops = {
+	.detect = micron_spinand_detect,
+};
+
+const struct spinand_manufacturer micron_spinand_manufacturer = {
+	.id = SPINAND_MFR_MICRON,
+	.name = "Micron",
+	.ops = &micron_spinand_manuf_ops,
+};
diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c
new file mode 100644
index 000000000000..67baa1b32c00
--- /dev/null
+++ b/drivers/mtd/nand/spi/winbond.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017 exceet electronics GmbH
+ *
+ * Authors:
+ *	Frieder Schrempf <frieder.schrempf@exceet.de>
+ *	Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/mtd/spinand.h>
+
+#define SPINAND_MFR_WINBOND		0xEF
+
+#define WINBOND_CFG_BUF_READ		BIT(3)
+
+static SPINAND_OP_VARIANTS(read_cache_variants,
+		SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 2, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0));
+
+static SPINAND_OP_VARIANTS(write_cache_variants,
+		SPINAND_PROG_LOAD_X4(true, 0, NULL, 0),
+		SPINAND_PROG_LOAD(true, 0, NULL, 0));
+
+static SPINAND_OP_VARIANTS(update_cache_variants,
+		SPINAND_PROG_LOAD_X4(false, 0, NULL, 0),
+		SPINAND_PROG_LOAD(false, 0, NULL, 0));
+
+static int w25m02gv_ooblayout_ecc(struct mtd_info *mtd, int section,
+				  struct mtd_oob_region *region)
+{
+	if (section > 3)
+		return -ERANGE;
+
+	region->offset = (16 * section) + 8;
+	region->length = 8;
+
+	return 0;
+}
+
+static int w25m02gv_ooblayout_free(struct mtd_info *mtd, int section,
+				   struct mtd_oob_region *region)
+{
+	if (section > 3)
+		return -ERANGE;
+
+	region->offset = (16 * section) + 2;
+	region->length = 6;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops w25m02gv_ooblayout = {
+	.ecc = w25m02gv_ooblayout_ecc,
+	.free = w25m02gv_ooblayout_free,
+};
+
+static int w25m02gv_select_target(struct spinand_device *spinand,
+				  unsigned int target)
+{
+	struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(0xc2, 1),
+					  SPI_MEM_OP_NO_ADDR,
+					  SPI_MEM_OP_NO_DUMMY,
+					  SPI_MEM_OP_DATA_OUT(1,
+							spinand->scratchbuf,
+							1));
+
+	*spinand->scratchbuf = target;
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static const struct spinand_info winbond_spinand_table[] = {
+	SPINAND_INFO("W25M02GV", 0xAB,
+		     NAND_MEMORG(1, 2048, 64, 64, 1024, 1, 1, 2),
+		     NAND_ECCREQ(1, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     0,
+		     SPINAND_ECCINFO(&w25m02gv_ooblayout, NULL),
+		     SPINAND_SELECT_TARGET(w25m02gv_select_target)),
+};
+
+/**
+ * winbond_spinand_detect - initialize device related part in spinand_device
+ * struct if it is a Winbond device.
+ * @spinand: SPI NAND device structure
+ */
+static int winbond_spinand_detect(struct spinand_device *spinand)
+{
+	u8 *id = spinand->id.data;
+	int ret;
+
+	/*
+	 * Winbond SPI NAND read ID need a dummy byte,
+	 * so the first byte in raw_id is dummy.
+	 */
+	if (id[1] != SPINAND_MFR_WINBOND)
+		return 0;
+
+	ret = spinand_match_and_init(spinand, winbond_spinand_table,
+				     ARRAY_SIZE(winbond_spinand_table), id[2]);
+	if (ret)
+		return ret;
+
+	return 1;
+}
+
+static int winbond_spinand_init(struct spinand_device *spinand)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int i;
+
+	/*
+	 * Make sure all dies are in buffer read mode and not continuous read
+	 * mode.
+	 */
+	for (i = 0; i < nand->memorg.ntargets; i++) {
+		spinand_select_target(spinand, i);
+		spinand_upd_cfg(spinand, WINBOND_CFG_BUF_READ,
+				WINBOND_CFG_BUF_READ);
+	}
+
+	return 0;
+}
+
+static const struct spinand_manufacturer_ops winbond_spinand_manuf_ops = {
+	.detect = winbond_spinand_detect,
+	.init = winbond_spinand_init,
+};
+
+const struct spinand_manufacturer winbond_spinand_manufacturer = {
+	.id = SPINAND_MFR_WINBOND,
+	.name = "Winbond",
+	.ops = &winbond_spinand_manuf_ops,
+};
diff --git a/drivers/mtd/nftlmount.c b/drivers/mtd/nftlmount.c
index 27184e3874db..91b7fb326f9a 100644
--- a/drivers/mtd/nftlmount.c
+++ b/drivers/mtd/nftlmount.c
@@ -577,7 +577,7 @@ static int get_fold_mark(struct NFTLrecord *nftl, unsigned int block)
 int NFTL_mount(struct NFTLrecord *s)
 {
 	int i;
-	unsigned int first_logical_block, logical_block, rep_block, nb_erases, erase_mark;
+	unsigned int first_logical_block, logical_block, rep_block, erase_mark;
 	unsigned int block, first_block, is_first_block;
 	int chain_length, do_format_chain;
 	struct nftl_uci0 h0;
@@ -621,7 +621,6 @@ int NFTL_mount(struct NFTLrecord *s)
 
 				logical_block = le16_to_cpu ((h0.VirtUnitNum | h0.SpareVirtUnitNum));
 				rep_block = le16_to_cpu ((h0.ReplUnitNum | h0.SpareReplUnitNum));
-				nb_erases = le32_to_cpu (h1.WearInfo);
 				erase_mark = le16_to_cpu ((h1.EraseMark | h1.EraseMark1));
 
 				is_first_block = !(logical_block >> 15);
diff --git a/drivers/mtd/parsers/parser_trx.c b/drivers/mtd/parsers/parser_trx.c
index 17ac33599783..4a89a68622fe 100644
--- a/drivers/mtd/parsers/parser_trx.c
+++ b/drivers/mtd/parsers/parser_trx.c
@@ -116,9 +116,16 @@ static int parser_trx_parse(struct mtd_info *mtd,
 	return i;
 };
 
+static const struct of_device_id mtd_parser_trx_of_match_table[] = {
+	{ .compatible = "brcm,trx" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, mtd_parser_trx_of_match_table);
+
 static struct mtd_part_parser mtd_parser_trx = {
 	.parse_fn = parser_trx_parse,
 	.name = "trx",
+	.of_match_table = mtd_parser_trx_of_match_table,
 };
 module_mtd_part_parser(mtd_parser_trx);
 
diff --git a/drivers/mtd/spi-nor/atmel-quadspi.c b/drivers/mtd/spi-nor/atmel-quadspi.c
index 6c5708bacad8..820048726b4f 100644
--- a/drivers/mtd/spi-nor/atmel-quadspi.c
+++ b/drivers/mtd/spi-nor/atmel-quadspi.c
@@ -34,7 +34,7 @@
 #include <linux/of.h>
 
 #include <linux/io.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 
 /* QSPI register offsets */
 #define QSPI_CR      0x0000  /* Control Register */
@@ -737,6 +737,26 @@ static int atmel_qspi_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static int __maybe_unused atmel_qspi_suspend(struct device *dev)
+{
+	struct atmel_qspi *aq = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(aq->clk);
+
+	return 0;
+}
+
+static int __maybe_unused atmel_qspi_resume(struct device *dev)
+{
+	struct atmel_qspi *aq = dev_get_drvdata(dev);
+
+	clk_prepare_enable(aq->clk);
+
+	return atmel_qspi_init(aq);
+}
+
+static SIMPLE_DEV_PM_OPS(atmel_qspi_pm_ops, atmel_qspi_suspend,
+			 atmel_qspi_resume);
 
 static const struct of_device_id atmel_qspi_dt_ids[] = {
 	{ .compatible = "atmel,sama5d2-qspi" },
@@ -749,6 +769,7 @@ static struct platform_driver atmel_qspi_driver = {
 	.driver = {
 		.name	= "atmel_qspi",
 		.of_match_table	= atmel_qspi_dt_ids,
+		.pm	= &atmel_qspi_pm_ops,
 	},
 	.probe		= atmel_qspi_probe,
 	.remove		= atmel_qspi_remove,
diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c
index d7e10b36a0b9..8e714fbfa521 100644
--- a/drivers/mtd/spi-nor/cadence-quadspi.c
+++ b/drivers/mtd/spi-nor/cadence-quadspi.c
@@ -525,15 +525,14 @@ static int cqspi_indirect_read_execute(struct spi_nor *nor, u8 *rxbuf,
 	       reg_base + CQSPI_REG_INDIRECTRD);
 
 	while (remaining > 0) {
-		ret = wait_for_completion_timeout(&cqspi->transfer_complete,
-						  msecs_to_jiffies
-						  (CQSPI_READ_TIMEOUT_MS));
+		if (!wait_for_completion_timeout(&cqspi->transfer_complete,
+				msecs_to_jiffies(CQSPI_READ_TIMEOUT_MS)))
+			ret = -ETIMEDOUT;
 
 		bytes_to_read = cqspi_get_rd_sram_level(cqspi);
 
-		if (!ret && bytes_to_read == 0) {
+		if (ret && bytes_to_read == 0) {
 			dev_err(nor->dev, "Indirect read timeout, no bytes\n");
-			ret = -ETIMEDOUT;
 			goto failrd;
 		}
 
@@ -649,10 +648,8 @@ static int cqspi_indirect_write_execute(struct spi_nor *nor, loff_t to_addr,
 		iowrite32_rep(cqspi->ahb_base, txbuf,
 			      DIV_ROUND_UP(write_bytes, 4));
 
-		ret = wait_for_completion_timeout(&cqspi->transfer_complete,
-						  msecs_to_jiffies
-						  (CQSPI_TIMEOUT_MS));
-		if (!ret) {
+		if (!wait_for_completion_timeout(&cqspi->transfer_complete,
+					msecs_to_jiffies(CQSPI_TIMEOUT_MS))) {
 			dev_err(nor->dev, "Indirect write timeout\n");
 			ret = -ETIMEDOUT;
 			goto failwr;
@@ -988,9 +985,8 @@ static int cqspi_direct_read_execute(struct spi_nor *nor, u_char *buf,
 	}
 
 	dma_async_issue_pending(cqspi->rx_chan);
-	ret = wait_for_completion_timeout(&cqspi->rx_dma_complete,
-					  msecs_to_jiffies(len));
-	if (ret <= 0) {
+	if (!wait_for_completion_timeout(&cqspi->rx_dma_complete,
+					 msecs_to_jiffies(len))) {
 		dmaengine_terminate_sync(cqspi->rx_chan);
 		dev_err(nor->dev, "DMA wait_for_completion_timeout\n");
 		ret = -ETIMEDOUT;
diff --git a/drivers/mtd/spi-nor/intel-spi.c b/drivers/mtd/spi-nor/intel-spi.c
index d2cbfc27826e..af0a22019516 100644
--- a/drivers/mtd/spi-nor/intel-spi.c
+++ b/drivers/mtd/spi-nor/intel-spi.c
@@ -908,7 +908,7 @@ struct intel_spi *intel_spi_probe(struct device *dev,
 	if (!ispi->writeable || !writeable)
 		ispi->nor.mtd.flags &= ~MTD_WRITEABLE;
 
-	ret = mtd_device_parse_register(&ispi->nor.mtd, NULL, NULL, &part, 1);
+	ret = mtd_device_register(&ispi->nor.mtd, &part, 1);
 	if (ret)
 		return ERR_PTR(ret);
 
diff --git a/drivers/mtd/spi-nor/nxp-spifi.c b/drivers/mtd/spi-nor/nxp-spifi.c
index 15374216d4d9..0c9094ec5966 100644
--- a/drivers/mtd/spi-nor/nxp-spifi.c
+++ b/drivers/mtd/spi-nor/nxp-spifi.c
@@ -436,6 +436,7 @@ static int nxp_spifi_probe(struct platform_device *pdev)
 	}
 
 	ret = nxp_spifi_setup_flash(spifi, flash_np);
+	of_node_put(flash_np);
 	if (ret) {
 		dev_err(&pdev->dev, "unable to setup flash chip\n");
 		goto dis_clks;
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index d9c368c44194..f028277fb1ce 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -2757,8 +2757,18 @@ static int spi_nor_init(struct spi_nor *nor)
 
 	if ((nor->addr_width == 4) &&
 	    (JEDEC_MFR(nor->info) != SNOR_MFR_SPANSION) &&
-	    !(nor->info->flags & SPI_NOR_4B_OPCODES))
+	    !(nor->info->flags & SPI_NOR_4B_OPCODES)) {
+		/*
+		 * If the RESET# pin isn't hooked up properly, or the system
+		 * otherwise doesn't perform a reset command in the boot
+		 * sequence, it's impossible to 100% protect against unexpected
+		 * reboots (e.g., crashes). Warn the user (or hopefully, system
+		 * designer) that this is bad.
+		 */
+		WARN_ONCE(nor->flags & SNOR_F_BROKEN_RESET,
+			  "enabling reset hack; may not recover from unexpected reboots\n");
 		set_4byte(nor, nor->info, 1);
+	}
 
 	return 0;
 }
@@ -2781,7 +2791,8 @@ void spi_nor_restore(struct spi_nor *nor)
 	/* restore the addressing mode */
 	if ((nor->addr_width == 4) &&
 	    (JEDEC_MFR(nor->info) != SNOR_MFR_SPANSION) &&
-	    !(nor->info->flags & SPI_NOR_4B_OPCODES))
+	    !(nor->info->flags & SPI_NOR_4B_OPCODES) &&
+	    (nor->flags & SNOR_F_BROKEN_RESET))
 		set_4byte(nor, nor->info, 0);
 }
 EXPORT_SYMBOL_GPL(spi_nor_restore);
@@ -2911,6 +2922,9 @@ int spi_nor_scan(struct spi_nor *nor, const char *name,
 		params.hwcaps.mask |= SNOR_HWCAPS_READ_FAST;
 	}
 
+	if (of_property_read_bool(np, "broken-flash-reset"))
+		nor->flags |= SNOR_F_BROKEN_RESET;
+
 	/* Some devices cannot do fast-read, no matter what DT tells us */
 	if (info->flags & SPI_NOR_NO_FR)
 		params.hwcaps.mask &= ~SNOR_HWCAPS_READ_FAST;
diff --git a/drivers/mtd/spi-nor/stm32-quadspi.c b/drivers/mtd/spi-nor/stm32-quadspi.c
index 72553506a00b..13e9fc961d3b 100644
--- a/drivers/mtd/spi-nor/stm32-quadspi.c
+++ b/drivers/mtd/spi-nor/stm32-quadspi.c
@@ -355,7 +355,7 @@ static int stm32_qspi_read_reg(struct spi_nor *nor,
 	struct device *dev = flash->qspi->dev;
 	struct stm32_qspi_cmd cmd;
 
-	dev_dbg(dev, "read_reg: cmd:%#.2x buf:%p len:%#x\n", opcode, buf, len);
+	dev_dbg(dev, "read_reg: cmd:%#.2x buf:%pK len:%#x\n", opcode, buf, len);
 
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.opcode = opcode;
@@ -376,7 +376,7 @@ static int stm32_qspi_write_reg(struct spi_nor *nor, u8 opcode,
 	struct device *dev = flash->qspi->dev;
 	struct stm32_qspi_cmd cmd;
 
-	dev_dbg(dev, "write_reg: cmd:%#.2x buf:%p len:%#x\n", opcode, buf, len);
+	dev_dbg(dev, "write_reg: cmd:%#.2x buf:%pK len:%#x\n", opcode, buf, len);
 
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.opcode = opcode;
@@ -398,7 +398,7 @@ static ssize_t stm32_qspi_read(struct spi_nor *nor, loff_t from, size_t len,
 	struct stm32_qspi_cmd cmd;
 	int err;
 
-	dev_dbg(qspi->dev, "read(%#.2x): buf:%p from:%#.8x len:%#zx\n",
+	dev_dbg(qspi->dev, "read(%#.2x): buf:%pK from:%#.8x len:%#zx\n",
 		nor->read_opcode, buf, (u32)from, len);
 
 	memset(&cmd, 0, sizeof(cmd));
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 217b790d22ed..a764a83f99da 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4102,7 +4102,8 @@ static inline int bond_slave_override(struct bonding *bond,
 
 
 static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     void *accel_priv, select_queue_fallback_t fallback)
+			     struct net_device *sb_dev,
+			     select_queue_fallback_t fallback)
 {
 	/* This helper function exists to help dev_pick_tx get the correct
 	 * destination queue.  Using a helper function skips a call to
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 6096440e96ea..35847250da5a 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -160,14 +160,19 @@ static ssize_t bonding_sysfs_store_option(struct device *d,
 {
 	struct bonding *bond = to_bond(d);
 	const struct bond_option *opt;
+	char *buffer_clone;
 	int ret;
 
 	opt = bond_opt_get_by_name(attr->attr.name);
 	if (WARN_ON(!opt))
 		return -ENOENT;
-	ret = bond_opt_tryset_rtnl(bond, opt->id, (char *)buffer);
+	buffer_clone = kstrndup(buffer, count, GFP_KERNEL);
+	if (!buffer_clone)
+		return -ENOMEM;
+	ret = bond_opt_tryset_rtnl(bond, opt->id, buffer_clone);
 	if (!ret)
 		ret = count;
+	kfree(buffer_clone);
 
 	return ret;
 }
diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index 2cb75988b328..7cdd0cead693 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -73,6 +73,12 @@ config CAN_CALC_BITTIMING
 config CAN_LEDS
 	bool "Enable LED triggers for Netlink based drivers"
 	depends on LEDS_CLASS
+	# The netdev trigger (LEDS_TRIGGER_NETDEV) should be able to do
+	# everything that this driver is doing. This is marked as broken
+	# because it uses stuff that is intended to be changed or removed.
+	# Please consider switching to the netdev trigger and confirm it
+	# fulfills your needs instead of fixing this driver.
+	depends on BROKEN
 	select LEDS_TRIGGERS
 	---help---
 	  This option adds two LED triggers for packet receive and transmit
diff --git a/drivers/net/can/cc770/cc770.c b/drivers/net/can/cc770/cc770.c
index d4dd4da23997..da636a22c542 100644
--- a/drivers/net/can/cc770/cc770.c
+++ b/drivers/net/can/cc770/cc770.c
@@ -73,7 +73,7 @@ MODULE_PARM_DESC(msgobj15_eff, "Extended 29-bit frames for message object 15 "
 
 static int i82527_compat;
 module_param(i82527_compat, int, 0444);
-MODULE_PARM_DESC(i82527_compat, "Strict Intel 82527 comptibility mode "
+MODULE_PARM_DESC(i82527_compat, "Strict Intel 82527 compatibility mode "
 		 "without using additional functions");
 
 /*
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 3c71f1cb205f..49163570a63a 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -649,8 +649,7 @@ struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf)
 	can_skb_prv(skb)->ifindex = dev->ifindex;
 	can_skb_prv(skb)->skbcnt = 0;
 
-	*cf = skb_put(skb, sizeof(struct can_frame));
-	memset(*cf, 0, sizeof(struct can_frame));
+	*cf = skb_put_zero(skb, sizeof(struct can_frame));
 
 	return skb;
 }
@@ -678,8 +677,7 @@ struct sk_buff *alloc_canfd_skb(struct net_device *dev,
 	can_skb_prv(skb)->ifindex = dev->ifindex;
 	can_skb_prv(skb)->skbcnt = 0;
 
-	*cfd = skb_put(skb, sizeof(struct canfd_frame));
-	memset(*cfd, 0, sizeof(struct canfd_frame));
+	*cfd = skb_put_zero(skb, sizeof(struct canfd_frame));
 
 	return skb;
 }
@@ -703,7 +701,8 @@ EXPORT_SYMBOL_GPL(alloc_can_err_skb);
 /*
  * Allocate and setup space for the CAN network device
  */
-struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max)
+struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max,
+				    unsigned int txqs, unsigned int rxqs)
 {
 	struct net_device *dev;
 	struct can_priv *priv;
@@ -715,7 +714,8 @@ struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max)
 	else
 		size = sizeof_priv;
 
-	dev = alloc_netdev(size, "can%d", NET_NAME_UNKNOWN, can_setup);
+	dev = alloc_netdev_mqs(size, "can%d", NET_NAME_UNKNOWN, can_setup,
+			       txqs, rxqs);
 	if (!dev)
 		return NULL;
 
@@ -734,7 +734,7 @@ struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max)
 
 	return dev;
 }
-EXPORT_SYMBOL_GPL(alloc_candev);
+EXPORT_SYMBOL_GPL(alloc_candev_mqs);
 
 /*
  * Free space of the CAN network device
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index d53a45bf2a72..8e972ef08637 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -1,24 +1,13 @@
-/*
- * flexcan.c - FLEXCAN CAN controller driver
- *
- * Copyright (c) 2005-2006 Varma Electronics Oy
- * Copyright (c) 2009 Sascha Hauer, Pengutronix
- * Copyright (c) 2010-2017 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de>
- * Copyright (c) 2014 David Jander, Protonic Holland
- *
- * Based on code originally by Andrey Volkov <avolkov@varma-el.com>
- *
- * LICENCE:
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// flexcan.c - FLEXCAN CAN controller driver
+//
+// Copyright (c) 2005-2006 Varma Electronics Oy
+// Copyright (c) 2009 Sascha Hauer, Pengutronix
+// Copyright (c) 2010-2017 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de>
+// Copyright (c) 2014 David Jander, Protonic Holland
+//
+// Based on code originally by Andrey Volkov <avolkov@varma-el.com>
 
 #include <linux/netdevice.h>
 #include <linux/can.h>
@@ -523,7 +512,7 @@ static int flexcan_get_berr_counter(const struct net_device *dev,
 	return err;
 }
 
-static int flexcan_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t flexcan_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	const struct flexcan_priv *priv = netdev_priv(dev);
 	struct can_frame *cf = (struct can_frame *)skb->data;
diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c
index adfdb66a486e..02042cb09bd2 100644
--- a/drivers/net/can/janz-ican3.c
+++ b/drivers/net/can/janz-ican3.c
@@ -1684,7 +1684,7 @@ static int ican3_stop(struct net_device *ndev)
 	return 0;
 }
 
-static int ican3_xmit(struct sk_buff *skb, struct net_device *ndev)
+static netdev_tx_t ican3_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
 	struct ican3_dev *mod = netdev_priv(ndev);
 	struct can_frame *cf = (struct can_frame *)skb->data;
diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c
index ed8561d4a90f..5696d7e80751 100644
--- a/drivers/net/can/peak_canfd/peak_canfd.c
+++ b/drivers/net/can/peak_canfd/peak_canfd.c
@@ -486,7 +486,7 @@ int peak_canfd_handle_msgs_list(struct peak_canfd_priv *priv,
 		if (msg_size <= 0)
 			break;
 
-		msg_ptr += msg_size;
+		msg_ptr += ALIGN(msg_size, 4);
 	}
 
 	if (msg_size < 0)
diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c
index 455a3797a200..c458d5fdc8d3 100644
--- a/drivers/net/can/peak_canfd/peak_pciefd_main.c
+++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c
@@ -174,9 +174,6 @@ struct pciefd_page {
 	u32 size;
 };
 
-#define CANFD_IRQ_SET		0x00000001
-#define CANFD_TX_PATH_SET	0x00000002
-
 /* CAN-FD channel object */
 struct pciefd_board;
 struct pciefd_can {
@@ -418,7 +415,7 @@ static int pciefd_pre_cmd(struct peak_canfd_priv *ucan)
 			break;
 
 		/* going into operational mode: setup IRQ handler */
-		err = request_irq(priv->board->pci_dev->irq,
+		err = request_irq(priv->ucan.ndev->irq,
 				  pciefd_irq_handler,
 				  IRQF_SHARED,
 				  PCIEFD_DRV_NAME,
@@ -491,15 +488,18 @@ static int pciefd_post_cmd(struct peak_canfd_priv *ucan)
 
 		/* controller now in reset mode: */
 
+		/* disable IRQ for this CAN */
+		pciefd_can_writereg(priv, CANFD_CTL_IEN_BIT,
+				    PCIEFD_REG_CAN_RX_CTL_CLR);
+
 		/* stop and reset DMA addresses in Tx/Rx engines */
 		pciefd_can_clear_tx_dma(priv);
 		pciefd_can_clear_rx_dma(priv);
 
-		/* disable IRQ for this CAN */
-		pciefd_can_writereg(priv, CANFD_CTL_IEN_BIT,
-				    PCIEFD_REG_CAN_RX_CTL_CLR);
+		/* wait for above commands to complete (read cycle) */
+		(void)pciefd_sys_readreg(priv->board, PCIEFD_REG_SYS_VER1);
 
-		free_irq(priv->board->pci_dev->irq, priv);
+		free_irq(priv->ucan.ndev->irq, priv);
 
 		ucan->can.state = CAN_STATE_STOPPED;
 
@@ -638,7 +638,7 @@ static int pciefd_can_probe(struct pciefd_board *pciefd)
 						 GFP_KERNEL);
 	if (!priv->tx_dma_vaddr) {
 		dev_err(&pciefd->pci_dev->dev,
-			"Tx dmaim_alloc_coherent(%u) failure\n",
+			"Tx dmam_alloc_coherent(%u) failure\n",
 			PCIEFD_TX_DMA_SIZE);
 		goto err_free_candev;
 	}
@@ -691,7 +691,7 @@ static int pciefd_can_probe(struct pciefd_board *pciefd)
 	pciefd->can[pciefd->can_count] = priv;
 
 	dev_info(&pciefd->pci_dev->dev, "%s at reg_base=0x%p irq=%d\n",
-		 ndev->name, priv->reg_base, pciefd->pci_dev->irq);
+		 ndev->name, priv->reg_base, ndev->irq);
 
 	return 0;
 
diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c
index 5adc95c922ee..a97b81d1d0da 100644
--- a/drivers/net/can/sja1000/peak_pci.c
+++ b/drivers/net/can/sja1000/peak_pci.c
@@ -608,7 +608,7 @@ static int peak_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	writeb(0x00, cfg_base + PITA_GPIOICR);
 	/* Toggle reset */
 	writeb(0x05, cfg_base + PITA_MISC + 3);
-	mdelay(5);
+	usleep_range(5000, 6000);
 	/* Leave parport mux mode */
 	writeb(0x04, cfg_base + PITA_MISC + 3);
 
diff --git a/drivers/net/can/sja1000/peak_pcmcia.c b/drivers/net/can/sja1000/peak_pcmcia.c
index 485b19c9ae47..b8c39ede7cd5 100644
--- a/drivers/net/can/sja1000/peak_pcmcia.c
+++ b/drivers/net/can/sja1000/peak_pcmcia.c
@@ -530,7 +530,7 @@ static int pcan_add_channels(struct pcan_pccard *card)
 	pcan_write_reg(card, PCC_CCR, ccr);
 
 	/* wait 2ms before unresetting channels */
-	mdelay(2);
+	usleep_range(2000, 3000);
 
 	ccr &= ~PCC_CCR_RST_ALL;
 	pcan_write_reg(card, PCC_CCR, ccr);
diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c
index 1ac2090a1721..093fc9a529f0 100644
--- a/drivers/net/can/sun4i_can.c
+++ b/drivers/net/can/sun4i_can.c
@@ -409,7 +409,7 @@ static int sun4ican_set_mode(struct net_device *dev, enum can_mode mode)
  * xx xx xx xx         ff         ll 00 11 22 33 44 55 66 77
  * [ can_id ] [flags] [len] [can data (up to 8 bytes]
  */
-static int sun4ican_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t sun4ican_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct sun4ican_priv *priv = netdev_priv(dev);
 	struct can_frame *cf = (struct can_frame *)skb->data;
diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig
index c36f4bdcbf4f..750d04d9e2ae 100644
--- a/drivers/net/can/usb/Kconfig
+++ b/drivers/net/can/usb/Kconfig
@@ -1,6 +1,12 @@
 menu "CAN USB interfaces"
 	depends on USB
 
+config CAN_8DEV_USB
+	tristate "8 devices USB2CAN interface"
+	---help---
+	  This driver supports the USB2CAN interface
+	  from 8 devices (http://www.8devices.com).
+
 config CAN_EMS_USB
 	tristate "EMS CPC-USB/ARM7 CAN/USB interface"
 	---help---
@@ -26,7 +32,7 @@ config CAN_KVASER_USB
 	tristate "Kvaser CAN/USB interface"
 	---help---
 	  This driver adds support for Kvaser CAN/USB devices like Kvaser
-	  Leaf Light and Kvaser USBcan II.
+	  Leaf Light, Kvaser USBcan II and Kvaser Memorator Pro 5xHS.
 
 	  The driver provides support for the following devices:
 	    - Kvaser Leaf Light
@@ -55,12 +61,30 @@ config CAN_KVASER_USB
 	    - Kvaser Memorator HS/HS
 	    - Kvaser Memorator HS/LS
 	    - Scania VCI2 (if you have the Kvaser logo on top)
+	    - Kvaser BlackBird v2
+	    - Kvaser Leaf Pro HS v2
+	    - Kvaser Hybrid 2xCAN/LIN
+	    - Kvaser Hybrid Pro 2xCAN/LIN
+	    - Kvaser Memorator 2xHS v2
+	    - Kvaser Memorator Pro 2xHS v2
+	    - Kvaser Memorator Pro 5xHS
+	    - Kvaser USBcan Light 4xHS
+	    - Kvaser USBcan Pro 2xHS v2
+	    - Kvaser USBcan Pro 5xHS
+	    - ATI Memorator Pro 2xHS v2
+	    - ATI USBcan Pro 2xHS v2
 
 	  If unsure, say N.
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called kvaser_usb.
 
+config CAN_MCBA_USB
+	tristate "Microchip CAN BUS Analyzer interface"
+	---help---
+	  This driver supports the CAN BUS Analyzer interface
+	  from Microchip (http://www.microchip.com/development-tools/).
+
 config CAN_PEAK_USB
 	tristate "PEAK PCAN-USB/USB Pro interfaces for CAN 2.0b/CAN-FD"
 	---help---
@@ -77,16 +101,26 @@ config CAN_PEAK_USB
 
 	  (see also http://www.peak-system.com).
 
-config CAN_8DEV_USB
-	tristate "8 devices USB2CAN interface"
-	---help---
-	  This driver supports the USB2CAN interface
-	  from 8 devices (http://www.8devices.com).
-
 config CAN_MCBA_USB
 	tristate "Microchip CAN BUS Analyzer interface"
 	---help---
 	  This driver supports the CAN BUS Analyzer interface
 	  from Microchip (http://www.microchip.com/development-tools/).
 
+config CAN_UCAN
+	tristate "Theobroma Systems UCAN interface"
+	---help---
+	  This driver supports the Theobroma Systems
+	  UCAN USB-CAN interface.
+
+	  The UCAN driver supports the microcontroller-based USB/CAN
+	  adapters from Theobroma Systems. There are two form-factors
+	  that run essentially the same firmware:
+
+	  * Seal: standalone USB stick
+	          https://www.theobroma-systems.com/seal)
+	  * Mule: integrated on the PCB of various System-on-Modules
+	          from Theobroma Systems like the A31-µQ7 and the RK3399-Q7
+	          (https://www.theobroma-systems.com/rk3399-q7)
+
 endmenu
diff --git a/drivers/net/can/usb/Makefile b/drivers/net/can/usb/Makefile
index 49ac7b99ba32..aa0f17c0b2ed 100644
--- a/drivers/net/can/usb/Makefile
+++ b/drivers/net/can/usb/Makefile
@@ -3,10 +3,11 @@
 #  Makefile for the Linux Controller Area Network USB drivers.
 #
 
+obj-$(CONFIG_CAN_8DEV_USB) += usb_8dev.o
 obj-$(CONFIG_CAN_EMS_USB) += ems_usb.o
 obj-$(CONFIG_CAN_ESD_USB2) += esd_usb2.o
 obj-$(CONFIG_CAN_GS_USB) += gs_usb.o
-obj-$(CONFIG_CAN_KVASER_USB) += kvaser_usb.o
-obj-$(CONFIG_CAN_PEAK_USB) += peak_usb/
-obj-$(CONFIG_CAN_8DEV_USB) += usb_8dev.o
+obj-$(CONFIG_CAN_KVASER_USB) += kvaser_usb/
 obj-$(CONFIG_CAN_MCBA_USB) += mcba_usb.o
+obj-$(CONFIG_CAN_PEAK_USB) += peak_usb/
+obj-$(CONFIG_CAN_UCAN) += ucan.o
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
deleted file mode 100644
index daed57d3d209..000000000000
--- a/drivers/net/can/usb/kvaser_usb.c
+++ /dev/null
@@ -1,2085 +0,0 @@
-/*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * Parts of this driver are based on the following:
- *  - Kvaser linux leaf driver (version 4.78)
- *  - CAN driver for esd CAN-USB/2
- *  - Kvaser linux usbcanII driver (version 5.3)
- *
- * Copyright (C) 2002-2006 KVASER AB, Sweden. All rights reserved.
- * Copyright (C) 2010 Matthias Fuchs <matthias.fuchs@esd.eu>, esd gmbh
- * Copyright (C) 2012 Olivier Sobrie <olivier@sobrie.be>
- * Copyright (C) 2015 Valeo S.A.
- */
-
-#include <linux/spinlock.h>
-#include <linux/kernel.h>
-#include <linux/completion.h>
-#include <linux/module.h>
-#include <linux/netdevice.h>
-#include <linux/usb.h>
-
-#include <linux/can.h>
-#include <linux/can/dev.h>
-#include <linux/can/error.h>
-
-#define MAX_RX_URBS			4
-#define START_TIMEOUT			1000 /* msecs */
-#define STOP_TIMEOUT			1000 /* msecs */
-#define USB_SEND_TIMEOUT		1000 /* msecs */
-#define USB_RECV_TIMEOUT		1000 /* msecs */
-#define RX_BUFFER_SIZE			3072
-#define CAN_USB_CLOCK			8000000
-#define MAX_NET_DEVICES			3
-#define MAX_USBCAN_NET_DEVICES		2
-
-/* Kvaser Leaf USB devices */
-#define KVASER_VENDOR_ID		0x0bfd
-#define USB_LEAF_DEVEL_PRODUCT_ID	10
-#define USB_LEAF_LITE_PRODUCT_ID	11
-#define USB_LEAF_PRO_PRODUCT_ID		12
-#define USB_LEAF_SPRO_PRODUCT_ID	14
-#define USB_LEAF_PRO_LS_PRODUCT_ID	15
-#define USB_LEAF_PRO_SWC_PRODUCT_ID	16
-#define USB_LEAF_PRO_LIN_PRODUCT_ID	17
-#define USB_LEAF_SPRO_LS_PRODUCT_ID	18
-#define USB_LEAF_SPRO_SWC_PRODUCT_ID	19
-#define USB_MEMO2_DEVEL_PRODUCT_ID	22
-#define USB_MEMO2_HSHS_PRODUCT_ID	23
-#define USB_UPRO_HSHS_PRODUCT_ID	24
-#define USB_LEAF_LITE_GI_PRODUCT_ID	25
-#define USB_LEAF_PRO_OBDII_PRODUCT_ID	26
-#define USB_MEMO2_HSLS_PRODUCT_ID	27
-#define USB_LEAF_LITE_CH_PRODUCT_ID	28
-#define USB_BLACKBIRD_SPRO_PRODUCT_ID	29
-#define USB_OEM_MERCURY_PRODUCT_ID	34
-#define USB_OEM_LEAF_PRODUCT_ID		35
-#define USB_CAN_R_PRODUCT_ID		39
-#define USB_LEAF_LITE_V2_PRODUCT_ID	288
-#define USB_MINI_PCIE_HS_PRODUCT_ID	289
-#define USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID 290
-#define USB_USBCAN_LIGHT_2HS_PRODUCT_ID	291
-#define USB_MINI_PCIE_2HS_PRODUCT_ID	292
-
-static inline bool kvaser_is_leaf(const struct usb_device_id *id)
-{
-	return id->idProduct >= USB_LEAF_DEVEL_PRODUCT_ID &&
-	       id->idProduct <= USB_MINI_PCIE_2HS_PRODUCT_ID;
-}
-
-/* Kvaser USBCan-II devices */
-#define USB_USBCAN_REVB_PRODUCT_ID	2
-#define USB_VCI2_PRODUCT_ID		3
-#define USB_USBCAN2_PRODUCT_ID		4
-#define USB_MEMORATOR_PRODUCT_ID	5
-
-static inline bool kvaser_is_usbcan(const struct usb_device_id *id)
-{
-	return id->idProduct >= USB_USBCAN_REVB_PRODUCT_ID &&
-	       id->idProduct <= USB_MEMORATOR_PRODUCT_ID;
-}
-
-/* USB devices features */
-#define KVASER_HAS_SILENT_MODE		BIT(0)
-#define KVASER_HAS_TXRX_ERRORS		BIT(1)
-
-/* Message header size */
-#define MSG_HEADER_LEN			2
-
-/* Can message flags */
-#define MSG_FLAG_ERROR_FRAME		BIT(0)
-#define MSG_FLAG_OVERRUN		BIT(1)
-#define MSG_FLAG_NERR			BIT(2)
-#define MSG_FLAG_WAKEUP			BIT(3)
-#define MSG_FLAG_REMOTE_FRAME		BIT(4)
-#define MSG_FLAG_RESERVED		BIT(5)
-#define MSG_FLAG_TX_ACK			BIT(6)
-#define MSG_FLAG_TX_REQUEST		BIT(7)
-
-/* Can states (M16C CxSTRH register) */
-#define M16C_STATE_BUS_RESET		BIT(0)
-#define M16C_STATE_BUS_ERROR		BIT(4)
-#define M16C_STATE_BUS_PASSIVE		BIT(5)
-#define M16C_STATE_BUS_OFF		BIT(6)
-
-/* Can msg ids */
-#define CMD_RX_STD_MESSAGE		12
-#define CMD_TX_STD_MESSAGE		13
-#define CMD_RX_EXT_MESSAGE		14
-#define CMD_TX_EXT_MESSAGE		15
-#define CMD_SET_BUS_PARAMS		16
-#define CMD_GET_BUS_PARAMS		17
-#define CMD_GET_BUS_PARAMS_REPLY	18
-#define CMD_GET_CHIP_STATE		19
-#define CMD_CHIP_STATE_EVENT		20
-#define CMD_SET_CTRL_MODE		21
-#define CMD_GET_CTRL_MODE		22
-#define CMD_GET_CTRL_MODE_REPLY		23
-#define CMD_RESET_CHIP			24
-#define CMD_RESET_CARD			25
-#define CMD_START_CHIP			26
-#define CMD_START_CHIP_REPLY		27
-#define CMD_STOP_CHIP			28
-#define CMD_STOP_CHIP_REPLY		29
-
-#define CMD_LEAF_GET_CARD_INFO2		32
-#define CMD_USBCAN_RESET_CLOCK		32
-#define CMD_USBCAN_CLOCK_OVERFLOW_EVENT	33
-
-#define CMD_GET_CARD_INFO		34
-#define CMD_GET_CARD_INFO_REPLY		35
-#define CMD_GET_SOFTWARE_INFO		38
-#define CMD_GET_SOFTWARE_INFO_REPLY	39
-#define CMD_ERROR_EVENT			45
-#define CMD_FLUSH_QUEUE			48
-#define CMD_RESET_ERROR_COUNTER		49
-#define CMD_TX_ACKNOWLEDGE		50
-#define CMD_CAN_ERROR_EVENT		51
-#define CMD_FLUSH_QUEUE_REPLY		68
-
-#define CMD_LEAF_USB_THROTTLE		77
-#define CMD_LEAF_LOG_MESSAGE		106
-
-/* error factors */
-#define M16C_EF_ACKE			BIT(0)
-#define M16C_EF_CRCE			BIT(1)
-#define M16C_EF_FORME			BIT(2)
-#define M16C_EF_STFE			BIT(3)
-#define M16C_EF_BITE0			BIT(4)
-#define M16C_EF_BITE1			BIT(5)
-#define M16C_EF_RCVE			BIT(6)
-#define M16C_EF_TRE			BIT(7)
-
-/* Only Leaf-based devices can report M16C error factors,
- * thus define our own error status flags for USBCANII
- */
-#define USBCAN_ERROR_STATE_NONE		0
-#define USBCAN_ERROR_STATE_TX_ERROR	BIT(0)
-#define USBCAN_ERROR_STATE_RX_ERROR	BIT(1)
-#define USBCAN_ERROR_STATE_BUSERROR	BIT(2)
-
-/* bittiming parameters */
-#define KVASER_USB_TSEG1_MIN		1
-#define KVASER_USB_TSEG1_MAX		16
-#define KVASER_USB_TSEG2_MIN		1
-#define KVASER_USB_TSEG2_MAX		8
-#define KVASER_USB_SJW_MAX		4
-#define KVASER_USB_BRP_MIN		1
-#define KVASER_USB_BRP_MAX		64
-#define KVASER_USB_BRP_INC		1
-
-/* ctrl modes */
-#define KVASER_CTRL_MODE_NORMAL		1
-#define KVASER_CTRL_MODE_SILENT		2
-#define KVASER_CTRL_MODE_SELFRECEPTION	3
-#define KVASER_CTRL_MODE_OFF		4
-
-/* Extended CAN identifier flag */
-#define KVASER_EXTENDED_FRAME		BIT(31)
-
-/* Kvaser USB CAN dongles are divided into two major families:
- * - Leaf: Based on Renesas M32C, running firmware labeled as 'filo'
- * - UsbcanII: Based on Renesas M16C, running firmware labeled as 'helios'
- */
-enum kvaser_usb_family {
-	KVASER_LEAF,
-	KVASER_USBCAN,
-};
-
-struct kvaser_msg_simple {
-	u8 tid;
-	u8 channel;
-} __packed;
-
-struct kvaser_msg_cardinfo {
-	u8 tid;
-	u8 nchannels;
-	union {
-		struct {
-			__le32 serial_number;
-			__le32 padding;
-		} __packed leaf0;
-		struct {
-			__le32 serial_number_low;
-			__le32 serial_number_high;
-		} __packed usbcan0;
-	} __packed;
-	__le32 clock_resolution;
-	__le32 mfgdate;
-	u8 ean[8];
-	u8 hw_revision;
-	union {
-		struct {
-			u8 usb_hs_mode;
-		} __packed leaf1;
-		struct {
-			u8 padding;
-		} __packed usbcan1;
-	} __packed;
-	__le16 padding;
-} __packed;
-
-struct kvaser_msg_cardinfo2 {
-	u8 tid;
-	u8 reserved;
-	u8 pcb_id[24];
-	__le32 oem_unlock_code;
-} __packed;
-
-struct leaf_msg_softinfo {
-	u8 tid;
-	u8 padding0;
-	__le32 sw_options;
-	__le32 fw_version;
-	__le16 max_outstanding_tx;
-	__le16 padding1[9];
-} __packed;
-
-struct usbcan_msg_softinfo {
-	u8 tid;
-	u8 fw_name[5];
-	__le16 max_outstanding_tx;
-	u8 padding[6];
-	__le32 fw_version;
-	__le16 checksum;
-	__le16 sw_options;
-} __packed;
-
-struct kvaser_msg_busparams {
-	u8 tid;
-	u8 channel;
-	__le32 bitrate;
-	u8 tseg1;
-	u8 tseg2;
-	u8 sjw;
-	u8 no_samp;
-} __packed;
-
-struct kvaser_msg_tx_can {
-	u8 channel;
-	u8 tid;
-	u8 msg[14];
-	union {
-		struct {
-			u8 padding;
-			u8 flags;
-		} __packed leaf;
-		struct {
-			u8 flags;
-			u8 padding;
-		} __packed usbcan;
-	} __packed;
-} __packed;
-
-struct kvaser_msg_rx_can_header {
-	u8 channel;
-	u8 flag;
-} __packed;
-
-struct leaf_msg_rx_can {
-	u8 channel;
-	u8 flag;
-
-	__le16 time[3];
-	u8 msg[14];
-} __packed;
-
-struct usbcan_msg_rx_can {
-	u8 channel;
-	u8 flag;
-
-	u8 msg[14];
-	__le16 time;
-} __packed;
-
-struct leaf_msg_chip_state_event {
-	u8 tid;
-	u8 channel;
-
-	__le16 time[3];
-	u8 tx_errors_count;
-	u8 rx_errors_count;
-
-	u8 status;
-	u8 padding[3];
-} __packed;
-
-struct usbcan_msg_chip_state_event {
-	u8 tid;
-	u8 channel;
-
-	u8 tx_errors_count;
-	u8 rx_errors_count;
-	__le16 time;
-
-	u8 status;
-	u8 padding[3];
-} __packed;
-
-struct kvaser_msg_tx_acknowledge_header {
-	u8 channel;
-	u8 tid;
-} __packed;
-
-struct leaf_msg_tx_acknowledge {
-	u8 channel;
-	u8 tid;
-
-	__le16 time[3];
-	u8 flags;
-	u8 time_offset;
-} __packed;
-
-struct usbcan_msg_tx_acknowledge {
-	u8 channel;
-	u8 tid;
-
-	__le16 time;
-	__le16 padding;
-} __packed;
-
-struct leaf_msg_error_event {
-	u8 tid;
-	u8 flags;
-	__le16 time[3];
-	u8 channel;
-	u8 padding;
-	u8 tx_errors_count;
-	u8 rx_errors_count;
-	u8 status;
-	u8 error_factor;
-} __packed;
-
-struct usbcan_msg_error_event {
-	u8 tid;
-	u8 padding;
-	u8 tx_errors_count_ch0;
-	u8 rx_errors_count_ch0;
-	u8 tx_errors_count_ch1;
-	u8 rx_errors_count_ch1;
-	u8 status_ch0;
-	u8 status_ch1;
-	__le16 time;
-} __packed;
-
-struct kvaser_msg_ctrl_mode {
-	u8 tid;
-	u8 channel;
-	u8 ctrl_mode;
-	u8 padding[3];
-} __packed;
-
-struct kvaser_msg_flush_queue {
-	u8 tid;
-	u8 channel;
-	u8 flags;
-	u8 padding[3];
-} __packed;
-
-struct leaf_msg_log_message {
-	u8 channel;
-	u8 flags;
-	__le16 time[3];
-	u8 dlc;
-	u8 time_offset;
-	__le32 id;
-	u8 data[8];
-} __packed;
-
-struct kvaser_msg {
-	u8 len;
-	u8 id;
-	union	{
-		struct kvaser_msg_simple simple;
-		struct kvaser_msg_cardinfo cardinfo;
-		struct kvaser_msg_cardinfo2 cardinfo2;
-		struct kvaser_msg_busparams busparams;
-
-		struct kvaser_msg_rx_can_header rx_can_header;
-		struct kvaser_msg_tx_acknowledge_header tx_acknowledge_header;
-
-		union {
-			struct leaf_msg_softinfo softinfo;
-			struct leaf_msg_rx_can rx_can;
-			struct leaf_msg_chip_state_event chip_state_event;
-			struct leaf_msg_tx_acknowledge tx_acknowledge;
-			struct leaf_msg_error_event error_event;
-			struct leaf_msg_log_message log_message;
-		} __packed leaf;
-
-		union {
-			struct usbcan_msg_softinfo softinfo;
-			struct usbcan_msg_rx_can rx_can;
-			struct usbcan_msg_chip_state_event chip_state_event;
-			struct usbcan_msg_tx_acknowledge tx_acknowledge;
-			struct usbcan_msg_error_event error_event;
-		} __packed usbcan;
-
-		struct kvaser_msg_tx_can tx_can;
-		struct kvaser_msg_ctrl_mode ctrl_mode;
-		struct kvaser_msg_flush_queue flush_queue;
-	} u;
-} __packed;
-
-/* Summary of a kvaser error event, for a unified Leaf/Usbcan error
- * handling. Some discrepancies between the two families exist:
- *
- * - USBCAN firmware does not report M16C "error factors"
- * - USBCAN controllers has difficulties reporting if the raised error
- *   event is for ch0 or ch1. They leave such arbitration to the OS
- *   driver by letting it compare error counters with previous values
- *   and decide the error event's channel. Thus for USBCAN, the channel
- *   field is only advisory.
- */
-struct kvaser_usb_error_summary {
-	u8 channel, status, txerr, rxerr;
-	union {
-		struct {
-			u8 error_factor;
-		} leaf;
-		struct {
-			u8 other_ch_status;
-			u8 error_state;
-		} usbcan;
-	};
-};
-
-/* Context for an outstanding, not yet ACKed, transmission */
-struct kvaser_usb_tx_urb_context {
-	struct kvaser_usb_net_priv *priv;
-	u32 echo_index;
-	int dlc;
-};
-
-struct kvaser_usb {
-	struct usb_device *udev;
-	struct kvaser_usb_net_priv *nets[MAX_NET_DEVICES];
-
-	struct usb_endpoint_descriptor *bulk_in, *bulk_out;
-	struct usb_anchor rx_submitted;
-
-	/* @max_tx_urbs: Firmware-reported maximum number of outstanding,
-	 * not yet ACKed, transmissions on this device. This value is
-	 * also used as a sentinel for marking free tx contexts.
-	 */
-	u32 fw_version;
-	unsigned int nchannels;
-	unsigned int max_tx_urbs;
-	enum kvaser_usb_family family;
-
-	bool rxinitdone;
-	void *rxbuf[MAX_RX_URBS];
-	dma_addr_t rxbuf_dma[MAX_RX_URBS];
-};
-
-struct kvaser_usb_net_priv {
-	struct can_priv can;
-	struct can_berr_counter bec;
-
-	struct kvaser_usb *dev;
-	struct net_device *netdev;
-	int channel;
-
-	struct completion start_comp, stop_comp;
-	struct usb_anchor tx_submitted;
-
-	spinlock_t tx_contexts_lock;
-	int active_tx_contexts;
-	struct kvaser_usb_tx_urb_context tx_contexts[];
-};
-
-static const struct usb_device_id kvaser_usb_table[] = {
-	/* Leaf family IDs */
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_DEVEL_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_LS_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_SWC_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_LIN_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_LS_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_SWC_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_DEVEL_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_HSHS_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_UPRO_HSHS_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_GI_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_OBDII_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_HSLS_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_CH_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_BLACKBIRD_SPRO_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_OEM_MERCURY_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_OEM_LEAF_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_CAN_R_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_V2_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_HS_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_LIGHT_2HS_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_2HS_PRODUCT_ID) },
-
-	/* USBCANII family IDs */
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN2_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_REVB_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMORATOR_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_VCI2_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-
-	{ }
-};
-MODULE_DEVICE_TABLE(usb, kvaser_usb_table);
-
-static inline int kvaser_usb_send_msg(const struct kvaser_usb *dev,
-				      struct kvaser_msg *msg)
-{
-	int actual_len;
-
-	return usb_bulk_msg(dev->udev,
-			    usb_sndbulkpipe(dev->udev,
-					dev->bulk_out->bEndpointAddress),
-			    msg, msg->len, &actual_len,
-			    USB_SEND_TIMEOUT);
-}
-
-static int kvaser_usb_wait_msg(const struct kvaser_usb *dev, u8 id,
-			       struct kvaser_msg *msg)
-{
-	struct kvaser_msg *tmp;
-	void *buf;
-	int actual_len;
-	int err;
-	int pos;
-	unsigned long to = jiffies + msecs_to_jiffies(USB_RECV_TIMEOUT);
-
-	buf = kzalloc(RX_BUFFER_SIZE, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	do {
-		err = usb_bulk_msg(dev->udev,
-				   usb_rcvbulkpipe(dev->udev,
-					dev->bulk_in->bEndpointAddress),
-				   buf, RX_BUFFER_SIZE, &actual_len,
-				   USB_RECV_TIMEOUT);
-		if (err < 0)
-			goto end;
-
-		pos = 0;
-		while (pos <= actual_len - MSG_HEADER_LEN) {
-			tmp = buf + pos;
-
-			/* Handle messages crossing the USB endpoint max packet
-			 * size boundary. Check kvaser_usb_read_bulk_callback()
-			 * for further details.
-			 */
-			if (tmp->len == 0) {
-				pos = round_up(pos, le16_to_cpu(dev->bulk_in->
-								wMaxPacketSize));
-				continue;
-			}
-
-			if (pos + tmp->len > actual_len) {
-				dev_err_ratelimited(dev->udev->dev.parent,
-						    "Format error\n");
-				break;
-			}
-
-			if (tmp->id == id) {
-				memcpy(msg, tmp, tmp->len);
-				goto end;
-			}
-
-			pos += tmp->len;
-		}
-	} while (time_before(jiffies, to));
-
-	err = -EINVAL;
-
-end:
-	kfree(buf);
-
-	return err;
-}
-
-static int kvaser_usb_send_simple_msg(const struct kvaser_usb *dev,
-				      u8 msg_id, int channel)
-{
-	struct kvaser_msg *msg;
-	int rc;
-
-	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	msg->id = msg_id;
-	msg->len = MSG_HEADER_LEN + sizeof(struct kvaser_msg_simple);
-	msg->u.simple.channel = channel;
-	msg->u.simple.tid = 0xff;
-
-	rc = kvaser_usb_send_msg(dev, msg);
-
-	kfree(msg);
-	return rc;
-}
-
-static int kvaser_usb_get_software_info(struct kvaser_usb *dev)
-{
-	struct kvaser_msg msg;
-	int err;
-
-	err = kvaser_usb_send_simple_msg(dev, CMD_GET_SOFTWARE_INFO, 0);
-	if (err)
-		return err;
-
-	err = kvaser_usb_wait_msg(dev, CMD_GET_SOFTWARE_INFO_REPLY, &msg);
-	if (err)
-		return err;
-
-	switch (dev->family) {
-	case KVASER_LEAF:
-		dev->fw_version = le32_to_cpu(msg.u.leaf.softinfo.fw_version);
-		dev->max_tx_urbs =
-			le16_to_cpu(msg.u.leaf.softinfo.max_outstanding_tx);
-		break;
-	case KVASER_USBCAN:
-		dev->fw_version = le32_to_cpu(msg.u.usbcan.softinfo.fw_version);
-		dev->max_tx_urbs =
-			le16_to_cpu(msg.u.usbcan.softinfo.max_outstanding_tx);
-		break;
-	}
-
-	return 0;
-}
-
-static int kvaser_usb_get_card_info(struct kvaser_usb *dev)
-{
-	struct kvaser_msg msg;
-	int err;
-
-	err = kvaser_usb_send_simple_msg(dev, CMD_GET_CARD_INFO, 0);
-	if (err)
-		return err;
-
-	err = kvaser_usb_wait_msg(dev, CMD_GET_CARD_INFO_REPLY, &msg);
-	if (err)
-		return err;
-
-	dev->nchannels = msg.u.cardinfo.nchannels;
-	if ((dev->nchannels > MAX_NET_DEVICES) ||
-	    (dev->family == KVASER_USBCAN &&
-	     dev->nchannels > MAX_USBCAN_NET_DEVICES))
-		return -EINVAL;
-
-	return 0;
-}
-
-static void kvaser_usb_tx_acknowledge(const struct kvaser_usb *dev,
-				      const struct kvaser_msg *msg)
-{
-	struct net_device_stats *stats;
-	struct kvaser_usb_tx_urb_context *context;
-	struct kvaser_usb_net_priv *priv;
-	struct sk_buff *skb;
-	struct can_frame *cf;
-	unsigned long flags;
-	u8 channel, tid;
-
-	channel = msg->u.tx_acknowledge_header.channel;
-	tid = msg->u.tx_acknowledge_header.tid;
-
-	if (channel >= dev->nchannels) {
-		dev_err(dev->udev->dev.parent,
-			"Invalid channel number (%d)\n", channel);
-		return;
-	}
-
-	priv = dev->nets[channel];
-
-	if (!netif_device_present(priv->netdev))
-		return;
-
-	stats = &priv->netdev->stats;
-
-	context = &priv->tx_contexts[tid % dev->max_tx_urbs];
-
-	/* Sometimes the state change doesn't come after a bus-off event */
-	if (priv->can.restart_ms &&
-	    (priv->can.state >= CAN_STATE_BUS_OFF)) {
-		skb = alloc_can_err_skb(priv->netdev, &cf);
-		if (skb) {
-			cf->can_id |= CAN_ERR_RESTARTED;
-
-			stats->rx_packets++;
-			stats->rx_bytes += cf->can_dlc;
-			netif_rx(skb);
-		} else {
-			netdev_err(priv->netdev,
-				   "No memory left for err_skb\n");
-		}
-
-		priv->can.can_stats.restarts++;
-		netif_carrier_on(priv->netdev);
-
-		priv->can.state = CAN_STATE_ERROR_ACTIVE;
-	}
-
-	stats->tx_packets++;
-	stats->tx_bytes += context->dlc;
-
-	spin_lock_irqsave(&priv->tx_contexts_lock, flags);
-
-	can_get_echo_skb(priv->netdev, context->echo_index);
-	context->echo_index = dev->max_tx_urbs;
-	--priv->active_tx_contexts;
-	netif_wake_queue(priv->netdev);
-
-	spin_unlock_irqrestore(&priv->tx_contexts_lock, flags);
-}
-
-static void kvaser_usb_simple_msg_callback(struct urb *urb)
-{
-	struct net_device *netdev = urb->context;
-
-	kfree(urb->transfer_buffer);
-
-	if (urb->status)
-		netdev_warn(netdev, "urb status received: %d\n",
-			    urb->status);
-}
-
-static int kvaser_usb_simple_msg_async(struct kvaser_usb_net_priv *priv,
-				       u8 msg_id)
-{
-	struct kvaser_usb *dev = priv->dev;
-	struct net_device *netdev = priv->netdev;
-	struct kvaser_msg *msg;
-	struct urb *urb;
-	void *buf;
-	int err;
-
-	urb = usb_alloc_urb(0, GFP_ATOMIC);
-	if (!urb)
-		return -ENOMEM;
-
-	buf = kmalloc(sizeof(struct kvaser_msg), GFP_ATOMIC);
-	if (!buf) {
-		usb_free_urb(urb);
-		return -ENOMEM;
-	}
-
-	msg = (struct kvaser_msg *)buf;
-	msg->len = MSG_HEADER_LEN + sizeof(struct kvaser_msg_simple);
-	msg->id = msg_id;
-	msg->u.simple.channel = priv->channel;
-
-	usb_fill_bulk_urb(urb, dev->udev,
-			  usb_sndbulkpipe(dev->udev,
-					  dev->bulk_out->bEndpointAddress),
-			  buf, msg->len,
-			  kvaser_usb_simple_msg_callback, netdev);
-	usb_anchor_urb(urb, &priv->tx_submitted);
-
-	err = usb_submit_urb(urb, GFP_ATOMIC);
-	if (err) {
-		netdev_err(netdev, "Error transmitting URB\n");
-		usb_unanchor_urb(urb);
-		kfree(buf);
-		usb_free_urb(urb);
-		return err;
-	}
-
-	usb_free_urb(urb);
-
-	return 0;
-}
-
-static void kvaser_usb_rx_error_update_can_state(struct kvaser_usb_net_priv *priv,
-						 const struct kvaser_usb_error_summary *es,
-						 struct can_frame *cf)
-{
-	struct kvaser_usb *dev = priv->dev;
-	struct net_device_stats *stats = &priv->netdev->stats;
-	enum can_state cur_state, new_state, tx_state, rx_state;
-
-	netdev_dbg(priv->netdev, "Error status: 0x%02x\n", es->status);
-
-	new_state = cur_state = priv->can.state;
-
-	if (es->status & (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET))
-		new_state = CAN_STATE_BUS_OFF;
-	else if (es->status & M16C_STATE_BUS_PASSIVE)
-		new_state = CAN_STATE_ERROR_PASSIVE;
-	else if (es->status & M16C_STATE_BUS_ERROR) {
-		/* Guard against spurious error events after a busoff */
-		if (cur_state < CAN_STATE_BUS_OFF) {
-			if ((es->txerr >= 128) || (es->rxerr >= 128))
-				new_state = CAN_STATE_ERROR_PASSIVE;
-			else if ((es->txerr >= 96) || (es->rxerr >= 96))
-				new_state = CAN_STATE_ERROR_WARNING;
-			else if (cur_state > CAN_STATE_ERROR_ACTIVE)
-				new_state = CAN_STATE_ERROR_ACTIVE;
-		}
-	}
-
-	if (!es->status)
-		new_state = CAN_STATE_ERROR_ACTIVE;
-
-	if (new_state != cur_state) {
-		tx_state = (es->txerr >= es->rxerr) ? new_state : 0;
-		rx_state = (es->txerr <= es->rxerr) ? new_state : 0;
-
-		can_change_state(priv->netdev, cf, tx_state, rx_state);
-	}
-
-	if (priv->can.restart_ms &&
-	    (cur_state >= CAN_STATE_BUS_OFF) &&
-	    (new_state < CAN_STATE_BUS_OFF)) {
-		priv->can.can_stats.restarts++;
-	}
-
-	switch (dev->family) {
-	case KVASER_LEAF:
-		if (es->leaf.error_factor) {
-			priv->can.can_stats.bus_error++;
-			stats->rx_errors++;
-		}
-		break;
-	case KVASER_USBCAN:
-		if (es->usbcan.error_state & USBCAN_ERROR_STATE_TX_ERROR)
-			stats->tx_errors++;
-		if (es->usbcan.error_state & USBCAN_ERROR_STATE_RX_ERROR)
-			stats->rx_errors++;
-		if (es->usbcan.error_state & USBCAN_ERROR_STATE_BUSERROR) {
-			priv->can.can_stats.bus_error++;
-		}
-		break;
-	}
-
-	priv->bec.txerr = es->txerr;
-	priv->bec.rxerr = es->rxerr;
-}
-
-static void kvaser_usb_rx_error(const struct kvaser_usb *dev,
-				const struct kvaser_usb_error_summary *es)
-{
-	struct can_frame *cf, tmp_cf = { .can_id = CAN_ERR_FLAG, .can_dlc = CAN_ERR_DLC };
-	struct sk_buff *skb;
-	struct net_device_stats *stats;
-	struct kvaser_usb_net_priv *priv;
-	enum can_state old_state, new_state;
-
-	if (es->channel >= dev->nchannels) {
-		dev_err(dev->udev->dev.parent,
-			"Invalid channel number (%d)\n", es->channel);
-		return;
-	}
-
-	priv = dev->nets[es->channel];
-	stats = &priv->netdev->stats;
-
-	/* Update all of the can interface's state and error counters before
-	 * trying any memory allocation that can actually fail with -ENOMEM.
-	 *
-	 * We send a temporary stack-allocated error can frame to
-	 * can_change_state() for the very same reason.
-	 *
-	 * TODO: Split can_change_state() responsibility between updating the
-	 * can interface's state and counters, and the setting up of can error
-	 * frame ID and data to userspace. Remove stack allocation afterwards.
-	 */
-	old_state = priv->can.state;
-	kvaser_usb_rx_error_update_can_state(priv, es, &tmp_cf);
-	new_state = priv->can.state;
-
-	skb = alloc_can_err_skb(priv->netdev, &cf);
-	if (!skb) {
-		stats->rx_dropped++;
-		return;
-	}
-	memcpy(cf, &tmp_cf, sizeof(*cf));
-
-	if (new_state != old_state) {
-		if (es->status &
-		    (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) {
-			if (!priv->can.restart_ms)
-				kvaser_usb_simple_msg_async(priv, CMD_STOP_CHIP);
-			netif_carrier_off(priv->netdev);
-		}
-
-		if (priv->can.restart_ms &&
-		    (old_state >= CAN_STATE_BUS_OFF) &&
-		    (new_state < CAN_STATE_BUS_OFF)) {
-			cf->can_id |= CAN_ERR_RESTARTED;
-			netif_carrier_on(priv->netdev);
-		}
-	}
-
-	switch (dev->family) {
-	case KVASER_LEAF:
-		if (es->leaf.error_factor) {
-			cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT;
-
-			if (es->leaf.error_factor & M16C_EF_ACKE)
-				cf->data[3] = CAN_ERR_PROT_LOC_ACK;
-			if (es->leaf.error_factor & M16C_EF_CRCE)
-				cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
-			if (es->leaf.error_factor & M16C_EF_FORME)
-				cf->data[2] |= CAN_ERR_PROT_FORM;
-			if (es->leaf.error_factor & M16C_EF_STFE)
-				cf->data[2] |= CAN_ERR_PROT_STUFF;
-			if (es->leaf.error_factor & M16C_EF_BITE0)
-				cf->data[2] |= CAN_ERR_PROT_BIT0;
-			if (es->leaf.error_factor & M16C_EF_BITE1)
-				cf->data[2] |= CAN_ERR_PROT_BIT1;
-			if (es->leaf.error_factor & M16C_EF_TRE)
-				cf->data[2] |= CAN_ERR_PROT_TX;
-		}
-		break;
-	case KVASER_USBCAN:
-		if (es->usbcan.error_state & USBCAN_ERROR_STATE_BUSERROR) {
-			cf->can_id |= CAN_ERR_BUSERROR;
-		}
-		break;
-	}
-
-	cf->data[6] = es->txerr;
-	cf->data[7] = es->rxerr;
-
-	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
-	netif_rx(skb);
-}
-
-/* For USBCAN, report error to userspace iff the channels's errors counter
- * has changed, or we're the only channel seeing a bus error state.
- */
-static void kvaser_usbcan_conditionally_rx_error(const struct kvaser_usb *dev,
-						 struct kvaser_usb_error_summary *es)
-{
-	struct kvaser_usb_net_priv *priv;
-	int channel;
-	bool report_error;
-
-	channel = es->channel;
-	if (channel >= dev->nchannels) {
-		dev_err(dev->udev->dev.parent,
-			"Invalid channel number (%d)\n", channel);
-		return;
-	}
-
-	priv = dev->nets[channel];
-	report_error = false;
-
-	if (es->txerr != priv->bec.txerr) {
-		es->usbcan.error_state |= USBCAN_ERROR_STATE_TX_ERROR;
-		report_error = true;
-	}
-	if (es->rxerr != priv->bec.rxerr) {
-		es->usbcan.error_state |= USBCAN_ERROR_STATE_RX_ERROR;
-		report_error = true;
-	}
-	if ((es->status & M16C_STATE_BUS_ERROR) &&
-	    !(es->usbcan.other_ch_status & M16C_STATE_BUS_ERROR)) {
-		es->usbcan.error_state |= USBCAN_ERROR_STATE_BUSERROR;
-		report_error = true;
-	}
-
-	if (report_error)
-		kvaser_usb_rx_error(dev, es);
-}
-
-static void kvaser_usbcan_rx_error(const struct kvaser_usb *dev,
-				   const struct kvaser_msg *msg)
-{
-	struct kvaser_usb_error_summary es = { };
-
-	switch (msg->id) {
-	/* Sometimes errors are sent as unsolicited chip state events */
-	case CMD_CHIP_STATE_EVENT:
-		es.channel = msg->u.usbcan.chip_state_event.channel;
-		es.status =  msg->u.usbcan.chip_state_event.status;
-		es.txerr = msg->u.usbcan.chip_state_event.tx_errors_count;
-		es.rxerr = msg->u.usbcan.chip_state_event.rx_errors_count;
-		kvaser_usbcan_conditionally_rx_error(dev, &es);
-		break;
-
-	case CMD_CAN_ERROR_EVENT:
-		es.channel = 0;
-		es.status = msg->u.usbcan.error_event.status_ch0;
-		es.txerr = msg->u.usbcan.error_event.tx_errors_count_ch0;
-		es.rxerr = msg->u.usbcan.error_event.rx_errors_count_ch0;
-		es.usbcan.other_ch_status =
-			msg->u.usbcan.error_event.status_ch1;
-		kvaser_usbcan_conditionally_rx_error(dev, &es);
-
-		/* The USBCAN firmware supports up to 2 channels.
-		 * Now that ch0 was checked, check if ch1 has any errors.
-		 */
-		if (dev->nchannels == MAX_USBCAN_NET_DEVICES) {
-			es.channel = 1;
-			es.status = msg->u.usbcan.error_event.status_ch1;
-			es.txerr = msg->u.usbcan.error_event.tx_errors_count_ch1;
-			es.rxerr = msg->u.usbcan.error_event.rx_errors_count_ch1;
-			es.usbcan.other_ch_status =
-				msg->u.usbcan.error_event.status_ch0;
-			kvaser_usbcan_conditionally_rx_error(dev, &es);
-		}
-		break;
-
-	default:
-		dev_err(dev->udev->dev.parent, "Invalid msg id (%d)\n",
-			msg->id);
-	}
-}
-
-static void kvaser_leaf_rx_error(const struct kvaser_usb *dev,
-				 const struct kvaser_msg *msg)
-{
-	struct kvaser_usb_error_summary es = { };
-
-	switch (msg->id) {
-	case CMD_CAN_ERROR_EVENT:
-		es.channel = msg->u.leaf.error_event.channel;
-		es.status =  msg->u.leaf.error_event.status;
-		es.txerr = msg->u.leaf.error_event.tx_errors_count;
-		es.rxerr = msg->u.leaf.error_event.rx_errors_count;
-		es.leaf.error_factor = msg->u.leaf.error_event.error_factor;
-		break;
-	case CMD_LEAF_LOG_MESSAGE:
-		es.channel = msg->u.leaf.log_message.channel;
-		es.status = msg->u.leaf.log_message.data[0];
-		es.txerr = msg->u.leaf.log_message.data[2];
-		es.rxerr = msg->u.leaf.log_message.data[3];
-		es.leaf.error_factor = msg->u.leaf.log_message.data[1];
-		break;
-	case CMD_CHIP_STATE_EVENT:
-		es.channel = msg->u.leaf.chip_state_event.channel;
-		es.status =  msg->u.leaf.chip_state_event.status;
-		es.txerr = msg->u.leaf.chip_state_event.tx_errors_count;
-		es.rxerr = msg->u.leaf.chip_state_event.rx_errors_count;
-		es.leaf.error_factor = 0;
-		break;
-	default:
-		dev_err(dev->udev->dev.parent, "Invalid msg id (%d)\n",
-			msg->id);
-		return;
-	}
-
-	kvaser_usb_rx_error(dev, &es);
-}
-
-static void kvaser_usb_rx_can_err(const struct kvaser_usb_net_priv *priv,
-				  const struct kvaser_msg *msg)
-{
-	struct can_frame *cf;
-	struct sk_buff *skb;
-	struct net_device_stats *stats = &priv->netdev->stats;
-
-	if (msg->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME |
-					 MSG_FLAG_NERR)) {
-		netdev_err(priv->netdev, "Unknown error (flags: 0x%02x)\n",
-			   msg->u.rx_can_header.flag);
-
-		stats->rx_errors++;
-		return;
-	}
-
-	if (msg->u.rx_can_header.flag & MSG_FLAG_OVERRUN) {
-		stats->rx_over_errors++;
-		stats->rx_errors++;
-
-		skb = alloc_can_err_skb(priv->netdev, &cf);
-		if (!skb) {
-			stats->rx_dropped++;
-			return;
-		}
-
-		cf->can_id |= CAN_ERR_CRTL;
-		cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
-
-		stats->rx_packets++;
-		stats->rx_bytes += cf->can_dlc;
-		netif_rx(skb);
-	}
-}
-
-static void kvaser_usb_rx_can_msg(const struct kvaser_usb *dev,
-				  const struct kvaser_msg *msg)
-{
-	struct kvaser_usb_net_priv *priv;
-	struct can_frame *cf;
-	struct sk_buff *skb;
-	struct net_device_stats *stats;
-	u8 channel = msg->u.rx_can_header.channel;
-	const u8 *rx_msg = NULL;	/* GCC */
-
-	if (channel >= dev->nchannels) {
-		dev_err(dev->udev->dev.parent,
-			"Invalid channel number (%d)\n", channel);
-		return;
-	}
-
-	priv = dev->nets[channel];
-	stats = &priv->netdev->stats;
-
-	if ((msg->u.rx_can_header.flag & MSG_FLAG_ERROR_FRAME) &&
-	    (dev->family == KVASER_LEAF && msg->id == CMD_LEAF_LOG_MESSAGE)) {
-		kvaser_leaf_rx_error(dev, msg);
-		return;
-	} else if (msg->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME |
-						MSG_FLAG_NERR |
-						MSG_FLAG_OVERRUN)) {
-		kvaser_usb_rx_can_err(priv, msg);
-		return;
-	} else if (msg->u.rx_can_header.flag & ~MSG_FLAG_REMOTE_FRAME) {
-		netdev_warn(priv->netdev,
-			    "Unhandled frame (flags: 0x%02x)",
-			    msg->u.rx_can_header.flag);
-		return;
-	}
-
-	switch (dev->family) {
-	case KVASER_LEAF:
-		rx_msg = msg->u.leaf.rx_can.msg;
-		break;
-	case KVASER_USBCAN:
-		rx_msg = msg->u.usbcan.rx_can.msg;
-		break;
-	}
-
-	skb = alloc_can_skb(priv->netdev, &cf);
-	if (!skb) {
-		stats->rx_dropped++;
-		return;
-	}
-
-	if (dev->family == KVASER_LEAF && msg->id == CMD_LEAF_LOG_MESSAGE) {
-		cf->can_id = le32_to_cpu(msg->u.leaf.log_message.id);
-		if (cf->can_id & KVASER_EXTENDED_FRAME)
-			cf->can_id &= CAN_EFF_MASK | CAN_EFF_FLAG;
-		else
-			cf->can_id &= CAN_SFF_MASK;
-
-		cf->can_dlc = get_can_dlc(msg->u.leaf.log_message.dlc);
-
-		if (msg->u.leaf.log_message.flags & MSG_FLAG_REMOTE_FRAME)
-			cf->can_id |= CAN_RTR_FLAG;
-		else
-			memcpy(cf->data, &msg->u.leaf.log_message.data,
-			       cf->can_dlc);
-	} else {
-		cf->can_id = ((rx_msg[0] & 0x1f) << 6) | (rx_msg[1] & 0x3f);
-
-		if (msg->id == CMD_RX_EXT_MESSAGE) {
-			cf->can_id <<= 18;
-			cf->can_id |= ((rx_msg[2] & 0x0f) << 14) |
-				      ((rx_msg[3] & 0xff) << 6) |
-				      (rx_msg[4] & 0x3f);
-			cf->can_id |= CAN_EFF_FLAG;
-		}
-
-		cf->can_dlc = get_can_dlc(rx_msg[5]);
-
-		if (msg->u.rx_can_header.flag & MSG_FLAG_REMOTE_FRAME)
-			cf->can_id |= CAN_RTR_FLAG;
-		else
-			memcpy(cf->data, &rx_msg[6],
-			       cf->can_dlc);
-	}
-
-	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
-	netif_rx(skb);
-}
-
-static void kvaser_usb_start_chip_reply(const struct kvaser_usb *dev,
-					const struct kvaser_msg *msg)
-{
-	struct kvaser_usb_net_priv *priv;
-	u8 channel = msg->u.simple.channel;
-
-	if (channel >= dev->nchannels) {
-		dev_err(dev->udev->dev.parent,
-			"Invalid channel number (%d)\n", channel);
-		return;
-	}
-
-	priv = dev->nets[channel];
-
-	if (completion_done(&priv->start_comp) &&
-	    netif_queue_stopped(priv->netdev)) {
-		netif_wake_queue(priv->netdev);
-	} else {
-		netif_start_queue(priv->netdev);
-		complete(&priv->start_comp);
-	}
-}
-
-static void kvaser_usb_stop_chip_reply(const struct kvaser_usb *dev,
-				       const struct kvaser_msg *msg)
-{
-	struct kvaser_usb_net_priv *priv;
-	u8 channel = msg->u.simple.channel;
-
-	if (channel >= dev->nchannels) {
-		dev_err(dev->udev->dev.parent,
-			"Invalid channel number (%d)\n", channel);
-		return;
-	}
-
-	priv = dev->nets[channel];
-
-	complete(&priv->stop_comp);
-}
-
-static void kvaser_usb_handle_message(const struct kvaser_usb *dev,
-				      const struct kvaser_msg *msg)
-{
-	switch (msg->id) {
-	case CMD_START_CHIP_REPLY:
-		kvaser_usb_start_chip_reply(dev, msg);
-		break;
-
-	case CMD_STOP_CHIP_REPLY:
-		kvaser_usb_stop_chip_reply(dev, msg);
-		break;
-
-	case CMD_RX_STD_MESSAGE:
-	case CMD_RX_EXT_MESSAGE:
-		kvaser_usb_rx_can_msg(dev, msg);
-		break;
-
-	case CMD_LEAF_LOG_MESSAGE:
-		if (dev->family != KVASER_LEAF)
-			goto warn;
-		kvaser_usb_rx_can_msg(dev, msg);
-		break;
-
-	case CMD_CHIP_STATE_EVENT:
-	case CMD_CAN_ERROR_EVENT:
-		if (dev->family == KVASER_LEAF)
-			kvaser_leaf_rx_error(dev, msg);
-		else
-			kvaser_usbcan_rx_error(dev, msg);
-		break;
-
-	case CMD_TX_ACKNOWLEDGE:
-		kvaser_usb_tx_acknowledge(dev, msg);
-		break;
-
-	/* Ignored messages */
-	case CMD_USBCAN_CLOCK_OVERFLOW_EVENT:
-		if (dev->family != KVASER_USBCAN)
-			goto warn;
-		break;
-
-	case CMD_FLUSH_QUEUE_REPLY:
-		if (dev->family != KVASER_LEAF)
-			goto warn;
-		break;
-
-	default:
-warn:		dev_warn(dev->udev->dev.parent,
-			 "Unhandled message (%d)\n", msg->id);
-		break;
-	}
-}
-
-static void kvaser_usb_read_bulk_callback(struct urb *urb)
-{
-	struct kvaser_usb *dev = urb->context;
-	struct kvaser_msg *msg;
-	int pos = 0;
-	int err, i;
-
-	switch (urb->status) {
-	case 0:
-		break;
-	case -ENOENT:
-	case -EPIPE:
-	case -EPROTO:
-	case -ESHUTDOWN:
-		return;
-	default:
-		dev_info(dev->udev->dev.parent, "Rx URB aborted (%d)\n",
-			 urb->status);
-		goto resubmit_urb;
-	}
-
-	while (pos <= (int)(urb->actual_length - MSG_HEADER_LEN)) {
-		msg = urb->transfer_buffer + pos;
-
-		/* The Kvaser firmware can only read and write messages that
-		 * does not cross the USB's endpoint wMaxPacketSize boundary.
-		 * If a follow-up command crosses such boundary, firmware puts
-		 * a placeholder zero-length command in its place then aligns
-		 * the real command to the next max packet size.
-		 *
-		 * Handle such cases or we're going to miss a significant
-		 * number of events in case of a heavy rx load on the bus.
-		 */
-		if (msg->len == 0) {
-			pos = round_up(pos, le16_to_cpu(dev->bulk_in->
-							wMaxPacketSize));
-			continue;
-		}
-
-		if (pos + msg->len > urb->actual_length) {
-			dev_err_ratelimited(dev->udev->dev.parent,
-					    "Format error\n");
-			break;
-		}
-
-		kvaser_usb_handle_message(dev, msg);
-		pos += msg->len;
-	}
-
-resubmit_urb:
-	usb_fill_bulk_urb(urb, dev->udev,
-			  usb_rcvbulkpipe(dev->udev,
-					  dev->bulk_in->bEndpointAddress),
-			  urb->transfer_buffer, RX_BUFFER_SIZE,
-			  kvaser_usb_read_bulk_callback, dev);
-
-	err = usb_submit_urb(urb, GFP_ATOMIC);
-	if (err == -ENODEV) {
-		for (i = 0; i < dev->nchannels; i++) {
-			if (!dev->nets[i])
-				continue;
-
-			netif_device_detach(dev->nets[i]->netdev);
-		}
-	} else if (err) {
-		dev_err(dev->udev->dev.parent,
-			"Failed resubmitting read bulk urb: %d\n", err);
-	}
-
-	return;
-}
-
-static int kvaser_usb_setup_rx_urbs(struct kvaser_usb *dev)
-{
-	int i, err = 0;
-
-	if (dev->rxinitdone)
-		return 0;
-
-	for (i = 0; i < MAX_RX_URBS; i++) {
-		struct urb *urb = NULL;
-		u8 *buf = NULL;
-		dma_addr_t buf_dma;
-
-		urb = usb_alloc_urb(0, GFP_KERNEL);
-		if (!urb) {
-			err = -ENOMEM;
-			break;
-		}
-
-		buf = usb_alloc_coherent(dev->udev, RX_BUFFER_SIZE,
-					 GFP_KERNEL, &buf_dma);
-		if (!buf) {
-			dev_warn(dev->udev->dev.parent,
-				 "No memory left for USB buffer\n");
-			usb_free_urb(urb);
-			err = -ENOMEM;
-			break;
-		}
-
-		usb_fill_bulk_urb(urb, dev->udev,
-				  usb_rcvbulkpipe(dev->udev,
-					  dev->bulk_in->bEndpointAddress),
-				  buf, RX_BUFFER_SIZE,
-				  kvaser_usb_read_bulk_callback,
-				  dev);
-		urb->transfer_dma = buf_dma;
-		urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
-		usb_anchor_urb(urb, &dev->rx_submitted);
-
-		err = usb_submit_urb(urb, GFP_KERNEL);
-		if (err) {
-			usb_unanchor_urb(urb);
-			usb_free_coherent(dev->udev, RX_BUFFER_SIZE, buf,
-					  buf_dma);
-			usb_free_urb(urb);
-			break;
-		}
-
-		dev->rxbuf[i] = buf;
-		dev->rxbuf_dma[i] = buf_dma;
-
-		usb_free_urb(urb);
-	}
-
-	if (i == 0) {
-		dev_warn(dev->udev->dev.parent,
-			 "Cannot setup read URBs, error %d\n", err);
-		return err;
-	} else if (i < MAX_RX_URBS) {
-		dev_warn(dev->udev->dev.parent,
-			 "RX performances may be slow\n");
-	}
-
-	dev->rxinitdone = true;
-
-	return 0;
-}
-
-static int kvaser_usb_set_opt_mode(const struct kvaser_usb_net_priv *priv)
-{
-	struct kvaser_msg *msg;
-	int rc;
-
-	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	msg->id = CMD_SET_CTRL_MODE;
-	msg->len = MSG_HEADER_LEN + sizeof(struct kvaser_msg_ctrl_mode);
-	msg->u.ctrl_mode.tid = 0xff;
-	msg->u.ctrl_mode.channel = priv->channel;
-
-	if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
-		msg->u.ctrl_mode.ctrl_mode = KVASER_CTRL_MODE_SILENT;
-	else
-		msg->u.ctrl_mode.ctrl_mode = KVASER_CTRL_MODE_NORMAL;
-
-	rc = kvaser_usb_send_msg(priv->dev, msg);
-
-	kfree(msg);
-	return rc;
-}
-
-static int kvaser_usb_start_chip(struct kvaser_usb_net_priv *priv)
-{
-	int err;
-
-	init_completion(&priv->start_comp);
-
-	err = kvaser_usb_send_simple_msg(priv->dev, CMD_START_CHIP,
-					 priv->channel);
-	if (err)
-		return err;
-
-	if (!wait_for_completion_timeout(&priv->start_comp,
-					 msecs_to_jiffies(START_TIMEOUT)))
-		return -ETIMEDOUT;
-
-	return 0;
-}
-
-static int kvaser_usb_open(struct net_device *netdev)
-{
-	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
-	struct kvaser_usb *dev = priv->dev;
-	int err;
-
-	err = open_candev(netdev);
-	if (err)
-		return err;
-
-	err = kvaser_usb_setup_rx_urbs(dev);
-	if (err)
-		goto error;
-
-	err = kvaser_usb_set_opt_mode(priv);
-	if (err)
-		goto error;
-
-	err = kvaser_usb_start_chip(priv);
-	if (err) {
-		netdev_warn(netdev, "Cannot start device, error %d\n", err);
-		goto error;
-	}
-
-	priv->can.state = CAN_STATE_ERROR_ACTIVE;
-
-	return 0;
-
-error:
-	close_candev(netdev);
-	return err;
-}
-
-static void kvaser_usb_reset_tx_urb_contexts(struct kvaser_usb_net_priv *priv)
-{
-	int i, max_tx_urbs;
-
-	max_tx_urbs = priv->dev->max_tx_urbs;
-
-	priv->active_tx_contexts = 0;
-	for (i = 0; i < max_tx_urbs; i++)
-		priv->tx_contexts[i].echo_index = max_tx_urbs;
-}
-
-/* This method might sleep. Do not call it in the atomic context
- * of URB completions.
- */
-static void kvaser_usb_unlink_tx_urbs(struct kvaser_usb_net_priv *priv)
-{
-	usb_kill_anchored_urbs(&priv->tx_submitted);
-	kvaser_usb_reset_tx_urb_contexts(priv);
-}
-
-static void kvaser_usb_unlink_all_urbs(struct kvaser_usb *dev)
-{
-	int i;
-
-	usb_kill_anchored_urbs(&dev->rx_submitted);
-
-	for (i = 0; i < MAX_RX_URBS; i++)
-		usb_free_coherent(dev->udev, RX_BUFFER_SIZE,
-				  dev->rxbuf[i],
-				  dev->rxbuf_dma[i]);
-
-	for (i = 0; i < dev->nchannels; i++) {
-		struct kvaser_usb_net_priv *priv = dev->nets[i];
-
-		if (priv)
-			kvaser_usb_unlink_tx_urbs(priv);
-	}
-}
-
-static int kvaser_usb_stop_chip(struct kvaser_usb_net_priv *priv)
-{
-	int err;
-
-	init_completion(&priv->stop_comp);
-
-	err = kvaser_usb_send_simple_msg(priv->dev, CMD_STOP_CHIP,
-					 priv->channel);
-	if (err)
-		return err;
-
-	if (!wait_for_completion_timeout(&priv->stop_comp,
-					 msecs_to_jiffies(STOP_TIMEOUT)))
-		return -ETIMEDOUT;
-
-	return 0;
-}
-
-static int kvaser_usb_flush_queue(struct kvaser_usb_net_priv *priv)
-{
-	struct kvaser_msg *msg;
-	int rc;
-
-	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	msg->id = CMD_FLUSH_QUEUE;
-	msg->len = MSG_HEADER_LEN + sizeof(struct kvaser_msg_flush_queue);
-	msg->u.flush_queue.channel = priv->channel;
-	msg->u.flush_queue.flags = 0x00;
-
-	rc = kvaser_usb_send_msg(priv->dev, msg);
-
-	kfree(msg);
-	return rc;
-}
-
-static int kvaser_usb_close(struct net_device *netdev)
-{
-	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
-	struct kvaser_usb *dev = priv->dev;
-	int err;
-
-	netif_stop_queue(netdev);
-
-	err = kvaser_usb_flush_queue(priv);
-	if (err)
-		netdev_warn(netdev, "Cannot flush queue, error %d\n", err);
-
-	err = kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, priv->channel);
-	if (err)
-		netdev_warn(netdev, "Cannot reset card, error %d\n", err);
-
-	err = kvaser_usb_stop_chip(priv);
-	if (err)
-		netdev_warn(netdev, "Cannot stop device, error %d\n", err);
-
-	/* reset tx contexts */
-	kvaser_usb_unlink_tx_urbs(priv);
-
-	priv->can.state = CAN_STATE_STOPPED;
-	close_candev(priv->netdev);
-
-	return 0;
-}
-
-static void kvaser_usb_write_bulk_callback(struct urb *urb)
-{
-	struct kvaser_usb_tx_urb_context *context = urb->context;
-	struct kvaser_usb_net_priv *priv;
-	struct net_device *netdev;
-
-	if (WARN_ON(!context))
-		return;
-
-	priv = context->priv;
-	netdev = priv->netdev;
-
-	kfree(urb->transfer_buffer);
-
-	if (!netif_device_present(netdev))
-		return;
-
-	if (urb->status)
-		netdev_info(netdev, "Tx URB aborted (%d)\n", urb->status);
-}
-
-static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb,
-					 struct net_device *netdev)
-{
-	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
-	struct kvaser_usb *dev = priv->dev;
-	struct net_device_stats *stats = &netdev->stats;
-	struct can_frame *cf = (struct can_frame *)skb->data;
-	struct kvaser_usb_tx_urb_context *context = NULL;
-	struct urb *urb;
-	void *buf;
-	struct kvaser_msg *msg;
-	int i, err, ret = NETDEV_TX_OK;
-	u8 *msg_tx_can_flags = NULL;		/* GCC */
-	unsigned long flags;
-
-	if (can_dropped_invalid_skb(netdev, skb))
-		return NETDEV_TX_OK;
-
-	urb = usb_alloc_urb(0, GFP_ATOMIC);
-	if (!urb) {
-		stats->tx_dropped++;
-		dev_kfree_skb(skb);
-		return NETDEV_TX_OK;
-	}
-
-	buf = kmalloc(sizeof(struct kvaser_msg), GFP_ATOMIC);
-	if (!buf) {
-		stats->tx_dropped++;
-		dev_kfree_skb(skb);
-		goto freeurb;
-	}
-
-	msg = buf;
-	msg->len = MSG_HEADER_LEN + sizeof(struct kvaser_msg_tx_can);
-	msg->u.tx_can.channel = priv->channel;
-
-	switch (dev->family) {
-	case KVASER_LEAF:
-		msg_tx_can_flags = &msg->u.tx_can.leaf.flags;
-		break;
-	case KVASER_USBCAN:
-		msg_tx_can_flags = &msg->u.tx_can.usbcan.flags;
-		break;
-	}
-
-	*msg_tx_can_flags = 0;
-
-	if (cf->can_id & CAN_EFF_FLAG) {
-		msg->id = CMD_TX_EXT_MESSAGE;
-		msg->u.tx_can.msg[0] = (cf->can_id >> 24) & 0x1f;
-		msg->u.tx_can.msg[1] = (cf->can_id >> 18) & 0x3f;
-		msg->u.tx_can.msg[2] = (cf->can_id >> 14) & 0x0f;
-		msg->u.tx_can.msg[3] = (cf->can_id >> 6) & 0xff;
-		msg->u.tx_can.msg[4] = cf->can_id & 0x3f;
-	} else {
-		msg->id = CMD_TX_STD_MESSAGE;
-		msg->u.tx_can.msg[0] = (cf->can_id >> 6) & 0x1f;
-		msg->u.tx_can.msg[1] = cf->can_id & 0x3f;
-	}
-
-	msg->u.tx_can.msg[5] = cf->can_dlc;
-	memcpy(&msg->u.tx_can.msg[6], cf->data, cf->can_dlc);
-
-	if (cf->can_id & CAN_RTR_FLAG)
-		*msg_tx_can_flags |= MSG_FLAG_REMOTE_FRAME;
-
-	spin_lock_irqsave(&priv->tx_contexts_lock, flags);
-	for (i = 0; i < dev->max_tx_urbs; i++) {
-		if (priv->tx_contexts[i].echo_index == dev->max_tx_urbs) {
-			context = &priv->tx_contexts[i];
-
-			context->echo_index = i;
-			can_put_echo_skb(skb, netdev, context->echo_index);
-			++priv->active_tx_contexts;
-			if (priv->active_tx_contexts >= dev->max_tx_urbs)
-				netif_stop_queue(netdev);
-
-			break;
-		}
-	}
-	spin_unlock_irqrestore(&priv->tx_contexts_lock, flags);
-
-	/* This should never happen; it implies a flow control bug */
-	if (!context) {
-		netdev_warn(netdev, "cannot find free context\n");
-
-		kfree(buf);
-		ret =  NETDEV_TX_BUSY;
-		goto freeurb;
-	}
-
-	context->priv = priv;
-	context->dlc = cf->can_dlc;
-
-	msg->u.tx_can.tid = context->echo_index;
-
-	usb_fill_bulk_urb(urb, dev->udev,
-			  usb_sndbulkpipe(dev->udev,
-					  dev->bulk_out->bEndpointAddress),
-			  buf, msg->len,
-			  kvaser_usb_write_bulk_callback, context);
-	usb_anchor_urb(urb, &priv->tx_submitted);
-
-	err = usb_submit_urb(urb, GFP_ATOMIC);
-	if (unlikely(err)) {
-		spin_lock_irqsave(&priv->tx_contexts_lock, flags);
-
-		can_free_echo_skb(netdev, context->echo_index);
-		context->echo_index = dev->max_tx_urbs;
-		--priv->active_tx_contexts;
-		netif_wake_queue(netdev);
-
-		spin_unlock_irqrestore(&priv->tx_contexts_lock, flags);
-
-		usb_unanchor_urb(urb);
-		kfree(buf);
-
-		stats->tx_dropped++;
-
-		if (err == -ENODEV)
-			netif_device_detach(netdev);
-		else
-			netdev_warn(netdev, "Failed tx_urb %d\n", err);
-
-		goto freeurb;
-	}
-
-	ret = NETDEV_TX_OK;
-
-freeurb:
-	usb_free_urb(urb);
-	return ret;
-}
-
-static const struct net_device_ops kvaser_usb_netdev_ops = {
-	.ndo_open = kvaser_usb_open,
-	.ndo_stop = kvaser_usb_close,
-	.ndo_start_xmit = kvaser_usb_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
-};
-
-static const struct can_bittiming_const kvaser_usb_bittiming_const = {
-	.name = "kvaser_usb",
-	.tseg1_min = KVASER_USB_TSEG1_MIN,
-	.tseg1_max = KVASER_USB_TSEG1_MAX,
-	.tseg2_min = KVASER_USB_TSEG2_MIN,
-	.tseg2_max = KVASER_USB_TSEG2_MAX,
-	.sjw_max = KVASER_USB_SJW_MAX,
-	.brp_min = KVASER_USB_BRP_MIN,
-	.brp_max = KVASER_USB_BRP_MAX,
-	.brp_inc = KVASER_USB_BRP_INC,
-};
-
-static int kvaser_usb_set_bittiming(struct net_device *netdev)
-{
-	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
-	struct can_bittiming *bt = &priv->can.bittiming;
-	struct kvaser_usb *dev = priv->dev;
-	struct kvaser_msg *msg;
-	int rc;
-
-	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	msg->id = CMD_SET_BUS_PARAMS;
-	msg->len = MSG_HEADER_LEN + sizeof(struct kvaser_msg_busparams);
-	msg->u.busparams.channel = priv->channel;
-	msg->u.busparams.tid = 0xff;
-	msg->u.busparams.bitrate = cpu_to_le32(bt->bitrate);
-	msg->u.busparams.sjw = bt->sjw;
-	msg->u.busparams.tseg1 = bt->prop_seg + bt->phase_seg1;
-	msg->u.busparams.tseg2 = bt->phase_seg2;
-
-	if (priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES)
-		msg->u.busparams.no_samp = 3;
-	else
-		msg->u.busparams.no_samp = 1;
-
-	rc = kvaser_usb_send_msg(dev, msg);
-
-	kfree(msg);
-	return rc;
-}
-
-static int kvaser_usb_set_mode(struct net_device *netdev,
-			       enum can_mode mode)
-{
-	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
-	int err;
-
-	switch (mode) {
-	case CAN_MODE_START:
-		err = kvaser_usb_simple_msg_async(priv, CMD_START_CHIP);
-		if (err)
-			return err;
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
-static int kvaser_usb_get_berr_counter(const struct net_device *netdev,
-				       struct can_berr_counter *bec)
-{
-	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
-
-	*bec = priv->bec;
-
-	return 0;
-}
-
-static void kvaser_usb_remove_interfaces(struct kvaser_usb *dev)
-{
-	int i;
-
-	for (i = 0; i < dev->nchannels; i++) {
-		if (!dev->nets[i])
-			continue;
-
-		unregister_candev(dev->nets[i]->netdev);
-	}
-
-	kvaser_usb_unlink_all_urbs(dev);
-
-	for (i = 0; i < dev->nchannels; i++) {
-		if (!dev->nets[i])
-			continue;
-
-		free_candev(dev->nets[i]->netdev);
-	}
-}
-
-static int kvaser_usb_init_one(struct usb_interface *intf,
-			       const struct usb_device_id *id, int channel)
-{
-	struct kvaser_usb *dev = usb_get_intfdata(intf);
-	struct net_device *netdev;
-	struct kvaser_usb_net_priv *priv;
-	int err;
-
-	err = kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, channel);
-	if (err)
-		return err;
-
-	netdev = alloc_candev(sizeof(*priv) +
-			      dev->max_tx_urbs * sizeof(*priv->tx_contexts),
-			      dev->max_tx_urbs);
-	if (!netdev) {
-		dev_err(&intf->dev, "Cannot alloc candev\n");
-		return -ENOMEM;
-	}
-
-	priv = netdev_priv(netdev);
-
-	init_usb_anchor(&priv->tx_submitted);
-	init_completion(&priv->start_comp);
-	init_completion(&priv->stop_comp);
-
-	priv->dev = dev;
-	priv->netdev = netdev;
-	priv->channel = channel;
-
-	spin_lock_init(&priv->tx_contexts_lock);
-	kvaser_usb_reset_tx_urb_contexts(priv);
-
-	priv->can.state = CAN_STATE_STOPPED;
-	priv->can.clock.freq = CAN_USB_CLOCK;
-	priv->can.bittiming_const = &kvaser_usb_bittiming_const;
-	priv->can.do_set_bittiming = kvaser_usb_set_bittiming;
-	priv->can.do_set_mode = kvaser_usb_set_mode;
-	if (id->driver_info & KVASER_HAS_TXRX_ERRORS)
-		priv->can.do_get_berr_counter = kvaser_usb_get_berr_counter;
-	priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES;
-	if (id->driver_info & KVASER_HAS_SILENT_MODE)
-		priv->can.ctrlmode_supported |= CAN_CTRLMODE_LISTENONLY;
-
-	netdev->flags |= IFF_ECHO;
-
-	netdev->netdev_ops = &kvaser_usb_netdev_ops;
-
-	SET_NETDEV_DEV(netdev, &intf->dev);
-	netdev->dev_id = channel;
-
-	dev->nets[channel] = priv;
-
-	err = register_candev(netdev);
-	if (err) {
-		dev_err(&intf->dev, "Failed to register can device\n");
-		free_candev(netdev);
-		dev->nets[channel] = NULL;
-		return err;
-	}
-
-	netdev_dbg(netdev, "device registered\n");
-
-	return 0;
-}
-
-static int kvaser_usb_get_endpoints(const struct usb_interface *intf,
-				    struct usb_endpoint_descriptor **in,
-				    struct usb_endpoint_descriptor **out)
-{
-	const struct usb_host_interface *iface_desc;
-	struct usb_endpoint_descriptor *endpoint;
-	int i;
-
-	iface_desc = &intf->altsetting[0];
-
-	for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) {
-		endpoint = &iface_desc->endpoint[i].desc;
-
-		if (!*in && usb_endpoint_is_bulk_in(endpoint))
-			*in = endpoint;
-
-		if (!*out && usb_endpoint_is_bulk_out(endpoint))
-			*out = endpoint;
-
-		/* use first bulk endpoint for in and out */
-		if (*in && *out)
-			return 0;
-	}
-
-	return -ENODEV;
-}
-
-static int kvaser_usb_probe(struct usb_interface *intf,
-			    const struct usb_device_id *id)
-{
-	struct kvaser_usb *dev;
-	int err = -ENOMEM;
-	int i, retry = 3;
-
-	dev = devm_kzalloc(&intf->dev, sizeof(*dev), GFP_KERNEL);
-	if (!dev)
-		return -ENOMEM;
-
-	if (kvaser_is_leaf(id)) {
-		dev->family = KVASER_LEAF;
-	} else if (kvaser_is_usbcan(id)) {
-		dev->family = KVASER_USBCAN;
-	} else {
-		dev_err(&intf->dev,
-			"Product ID (%d) does not belong to any known Kvaser USB family",
-			id->idProduct);
-		return -ENODEV;
-	}
-
-	err = kvaser_usb_get_endpoints(intf, &dev->bulk_in, &dev->bulk_out);
-	if (err) {
-		dev_err(&intf->dev, "Cannot get usb endpoint(s)");
-		return err;
-	}
-
-	dev->udev = interface_to_usbdev(intf);
-
-	init_usb_anchor(&dev->rx_submitted);
-
-	usb_set_intfdata(intf, dev);
-
-	/* On some x86 laptops, plugging a Kvaser device again after
-	 * an unplug makes the firmware always ignore the very first
-	 * command. For such a case, provide some room for retries
-	 * instead of completely exiting the driver.
-	 */
-	do {
-		err = kvaser_usb_get_software_info(dev);
-	} while (--retry && err == -ETIMEDOUT);
-
-	if (err) {
-		dev_err(&intf->dev,
-			"Cannot get software infos, error %d\n", err);
-		return err;
-	}
-
-	dev_dbg(&intf->dev, "Firmware version: %d.%d.%d\n",
-		((dev->fw_version >> 24) & 0xff),
-		((dev->fw_version >> 16) & 0xff),
-		(dev->fw_version & 0xffff));
-
-	dev_dbg(&intf->dev, "Max outstanding tx = %d URBs\n", dev->max_tx_urbs);
-
-	err = kvaser_usb_get_card_info(dev);
-	if (err) {
-		dev_err(&intf->dev,
-			"Cannot get card infos, error %d\n", err);
-		return err;
-	}
-
-	for (i = 0; i < dev->nchannels; i++) {
-		err = kvaser_usb_init_one(intf, id, i);
-		if (err) {
-			kvaser_usb_remove_interfaces(dev);
-			return err;
-		}
-	}
-
-	return 0;
-}
-
-static void kvaser_usb_disconnect(struct usb_interface *intf)
-{
-	struct kvaser_usb *dev = usb_get_intfdata(intf);
-
-	usb_set_intfdata(intf, NULL);
-
-	if (!dev)
-		return;
-
-	kvaser_usb_remove_interfaces(dev);
-}
-
-static struct usb_driver kvaser_usb_driver = {
-	.name = "kvaser_usb",
-	.probe = kvaser_usb_probe,
-	.disconnect = kvaser_usb_disconnect,
-	.id_table = kvaser_usb_table,
-};
-
-module_usb_driver(kvaser_usb_driver);
-
-MODULE_AUTHOR("Olivier Sobrie <olivier@sobrie.be>");
-MODULE_DESCRIPTION("CAN driver for Kvaser CAN/USB devices");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/can/usb/kvaser_usb/Makefile b/drivers/net/can/usb/kvaser_usb/Makefile
new file mode 100644
index 000000000000..9f41ddab6a5a
--- /dev/null
+++ b/drivers/net/can/usb/kvaser_usb/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_CAN_KVASER_USB) += kvaser_usb.o
+kvaser_usb-y = kvaser_usb_core.o kvaser_usb_leaf.o kvaser_usb_hydra.o
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
new file mode 100644
index 000000000000..390b6bde883c
--- /dev/null
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
@@ -0,0 +1,188 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Parts of this driver are based on the following:
+ *  - Kvaser linux leaf driver (version 4.78)
+ *  - CAN driver for esd CAN-USB/2
+ *  - Kvaser linux usbcanII driver (version 5.3)
+ *  - Kvaser linux mhydra driver (version 5.24)
+ *
+ * Copyright (C) 2002-2018 KVASER AB, Sweden. All rights reserved.
+ * Copyright (C) 2010 Matthias Fuchs <matthias.fuchs@esd.eu>, esd gmbh
+ * Copyright (C) 2012 Olivier Sobrie <olivier@sobrie.be>
+ * Copyright (C) 2015 Valeo S.A.
+ */
+
+#ifndef KVASER_USB_H
+#define KVASER_USB_H
+
+/* Kvaser USB CAN dongles are divided into three major platforms:
+ * - Hydra: Running firmware labeled as 'mhydra'
+ * - Leaf: Based on Renesas M32C or Freescale i.MX28, running firmware labeled
+ *         as 'filo'
+ * - UsbcanII: Based on Renesas M16C, running firmware labeled as 'helios'
+ */
+
+#include <linux/completion.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/usb.h>
+
+#include <linux/can.h>
+#include <linux/can/dev.h>
+
+#define KVASER_USB_MAX_RX_URBS			4
+#define KVASER_USB_MAX_TX_URBS			128
+#define KVASER_USB_TIMEOUT			1000 /* msecs */
+#define KVASER_USB_RX_BUFFER_SIZE		3072
+#define KVASER_USB_MAX_NET_DEVICES		5
+
+/* USB devices features */
+#define KVASER_USB_HAS_SILENT_MODE		BIT(0)
+#define KVASER_USB_HAS_TXRX_ERRORS		BIT(1)
+
+/* Device capabilities */
+#define KVASER_USB_CAP_BERR_CAP			0x01
+#define KVASER_USB_CAP_EXT_CAP			0x02
+#define KVASER_USB_HYDRA_CAP_EXT_CMD		0x04
+
+struct kvaser_usb_dev_cfg;
+
+enum kvaser_usb_leaf_family {
+	KVASER_LEAF,
+	KVASER_USBCAN,
+};
+
+#define KVASER_USB_HYDRA_MAX_CMD_LEN		128
+struct kvaser_usb_dev_card_data_hydra {
+	u8 channel_to_he[KVASER_USB_MAX_NET_DEVICES];
+	u8 sysdbg_he;
+	spinlock_t transid_lock; /* lock for transid */
+	u16 transid;
+	/* lock for usb_rx_leftover and usb_rx_leftover_len */
+	spinlock_t usb_rx_leftover_lock;
+	u8 usb_rx_leftover[KVASER_USB_HYDRA_MAX_CMD_LEN];
+	u8 usb_rx_leftover_len;
+};
+struct kvaser_usb_dev_card_data {
+	u32 ctrlmode_supported;
+	u32 capabilities;
+	union {
+		struct {
+			enum kvaser_usb_leaf_family family;
+		} leaf;
+		struct kvaser_usb_dev_card_data_hydra hydra;
+	};
+};
+
+/* Context for an outstanding, not yet ACKed, transmission */
+struct kvaser_usb_tx_urb_context {
+	struct kvaser_usb_net_priv *priv;
+	u32 echo_index;
+	int dlc;
+};
+
+struct kvaser_usb {
+	struct usb_device *udev;
+	struct usb_interface *intf;
+	struct kvaser_usb_net_priv *nets[KVASER_USB_MAX_NET_DEVICES];
+	const struct kvaser_usb_dev_ops *ops;
+	const struct kvaser_usb_dev_cfg *cfg;
+
+	struct usb_endpoint_descriptor *bulk_in, *bulk_out;
+	struct usb_anchor rx_submitted;
+
+	/* @max_tx_urbs: Firmware-reported maximum number of outstanding,
+	 * not yet ACKed, transmissions on this device. This value is
+	 * also used as a sentinel for marking free tx contexts.
+	 */
+	u32 fw_version;
+	unsigned int nchannels;
+	unsigned int max_tx_urbs;
+	struct kvaser_usb_dev_card_data card_data;
+
+	bool rxinitdone;
+	void *rxbuf[KVASER_USB_MAX_RX_URBS];
+	dma_addr_t rxbuf_dma[KVASER_USB_MAX_RX_URBS];
+};
+
+struct kvaser_usb_net_priv {
+	struct can_priv can;
+	struct can_berr_counter bec;
+
+	struct kvaser_usb *dev;
+	struct net_device *netdev;
+	int channel;
+
+	struct completion start_comp, stop_comp, flush_comp;
+	struct usb_anchor tx_submitted;
+
+	spinlock_t tx_contexts_lock; /* lock for active_tx_contexts */
+	int active_tx_contexts;
+	struct kvaser_usb_tx_urb_context tx_contexts[];
+};
+
+/**
+ * struct kvaser_usb_dev_ops - Device specific functions
+ * @dev_set_mode:		used for can.do_set_mode
+ * @dev_set_bittiming:		used for can.do_set_bittiming
+ * @dev_set_data_bittiming:	used for can.do_set_data_bittiming
+ * @dev_get_berr_counter:	used for can.do_get_berr_counter
+ *
+ * @dev_setup_endpoints:	setup USB in and out endpoints
+ * @dev_init_card:		initialize card
+ * @dev_get_software_info:	get software info
+ * @dev_get_software_details:	get software details
+ * @dev_get_card_info:		get card info
+ * @dev_get_capabilities:	discover device capabilities
+ *
+ * @dev_set_opt_mode:		set ctrlmod
+ * @dev_start_chip:		start the CAN controller
+ * @dev_stop_chip:		stop the CAN controller
+ * @dev_reset_chip:		reset the CAN controller
+ * @dev_flush_queue:		flush outstanding CAN messages
+ * @dev_read_bulk_callback:	handle incoming commands
+ * @dev_frame_to_cmd:		translate struct can_frame into device command
+ */
+struct kvaser_usb_dev_ops {
+	int (*dev_set_mode)(struct net_device *netdev, enum can_mode mode);
+	int (*dev_set_bittiming)(struct net_device *netdev);
+	int (*dev_set_data_bittiming)(struct net_device *netdev);
+	int (*dev_get_berr_counter)(const struct net_device *netdev,
+				    struct can_berr_counter *bec);
+	int (*dev_setup_endpoints)(struct kvaser_usb *dev);
+	int (*dev_init_card)(struct kvaser_usb *dev);
+	int (*dev_get_software_info)(struct kvaser_usb *dev);
+	int (*dev_get_software_details)(struct kvaser_usb *dev);
+	int (*dev_get_card_info)(struct kvaser_usb *dev);
+	int (*dev_get_capabilities)(struct kvaser_usb *dev);
+	int (*dev_set_opt_mode)(const struct kvaser_usb_net_priv *priv);
+	int (*dev_start_chip)(struct kvaser_usb_net_priv *priv);
+	int (*dev_stop_chip)(struct kvaser_usb_net_priv *priv);
+	int (*dev_reset_chip)(struct kvaser_usb *dev, int channel);
+	int (*dev_flush_queue)(struct kvaser_usb_net_priv *priv);
+	void (*dev_read_bulk_callback)(struct kvaser_usb *dev, void *buf,
+				       int len);
+	void *(*dev_frame_to_cmd)(const struct kvaser_usb_net_priv *priv,
+				  const struct sk_buff *skb, int *frame_len,
+				  int *cmd_len, u16 transid);
+};
+
+struct kvaser_usb_dev_cfg {
+	const struct can_clock clock;
+	const unsigned int timestamp_freq;
+	const struct can_bittiming_const * const bittiming_const;
+	const struct can_bittiming_const * const data_bittiming_const;
+};
+
+extern const struct kvaser_usb_dev_ops kvaser_usb_hydra_dev_ops;
+extern const struct kvaser_usb_dev_ops kvaser_usb_leaf_dev_ops;
+
+int kvaser_usb_recv_cmd(const struct kvaser_usb *dev, void *cmd, int len,
+			int *actual_len);
+
+int kvaser_usb_send_cmd(const struct kvaser_usb *dev, void *cmd, int len);
+
+int kvaser_usb_send_cmd_async(struct kvaser_usb_net_priv *priv, void *cmd,
+			      int len);
+
+int kvaser_usb_can_rx_over_error(struct net_device *netdev);
+#endif /* KVASER_USB_H */
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
new file mode 100644
index 000000000000..b939a4c10b84
--- /dev/null
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
@@ -0,0 +1,835 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Parts of this driver are based on the following:
+ *  - Kvaser linux leaf driver (version 4.78)
+ *  - CAN driver for esd CAN-USB/2
+ *  - Kvaser linux usbcanII driver (version 5.3)
+ *  - Kvaser linux mhydra driver (version 5.24)
+ *
+ * Copyright (C) 2002-2018 KVASER AB, Sweden. All rights reserved.
+ * Copyright (C) 2010 Matthias Fuchs <matthias.fuchs@esd.eu>, esd gmbh
+ * Copyright (C) 2012 Olivier Sobrie <olivier@sobrie.be>
+ * Copyright (C) 2015 Valeo S.A.
+ */
+
+#include <linux/completion.h>
+#include <linux/device.h>
+#include <linux/gfp.h>
+#include <linux/if.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/usb.h>
+
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/error.h>
+#include <linux/can/netlink.h>
+
+#include "kvaser_usb.h"
+
+/* Kvaser USB vendor id. */
+#define KVASER_VENDOR_ID			0x0bfd
+
+/* Kvaser Leaf USB devices product ids */
+#define USB_LEAF_DEVEL_PRODUCT_ID		10
+#define USB_LEAF_LITE_PRODUCT_ID		11
+#define USB_LEAF_PRO_PRODUCT_ID			12
+#define USB_LEAF_SPRO_PRODUCT_ID		14
+#define USB_LEAF_PRO_LS_PRODUCT_ID		15
+#define USB_LEAF_PRO_SWC_PRODUCT_ID		16
+#define USB_LEAF_PRO_LIN_PRODUCT_ID		17
+#define USB_LEAF_SPRO_LS_PRODUCT_ID		18
+#define USB_LEAF_SPRO_SWC_PRODUCT_ID		19
+#define USB_MEMO2_DEVEL_PRODUCT_ID		22
+#define USB_MEMO2_HSHS_PRODUCT_ID		23
+#define USB_UPRO_HSHS_PRODUCT_ID		24
+#define USB_LEAF_LITE_GI_PRODUCT_ID		25
+#define USB_LEAF_PRO_OBDII_PRODUCT_ID		26
+#define USB_MEMO2_HSLS_PRODUCT_ID		27
+#define USB_LEAF_LITE_CH_PRODUCT_ID		28
+#define USB_BLACKBIRD_SPRO_PRODUCT_ID		29
+#define USB_OEM_MERCURY_PRODUCT_ID		34
+#define USB_OEM_LEAF_PRODUCT_ID			35
+#define USB_CAN_R_PRODUCT_ID			39
+#define USB_LEAF_LITE_V2_PRODUCT_ID		288
+#define USB_MINI_PCIE_HS_PRODUCT_ID		289
+#define USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID	290
+#define USB_USBCAN_LIGHT_2HS_PRODUCT_ID		291
+#define USB_MINI_PCIE_2HS_PRODUCT_ID		292
+
+/* Kvaser USBCan-II devices product ids */
+#define USB_USBCAN_REVB_PRODUCT_ID		2
+#define USB_VCI2_PRODUCT_ID			3
+#define USB_USBCAN2_PRODUCT_ID			4
+#define USB_MEMORATOR_PRODUCT_ID		5
+
+/* Kvaser Minihydra USB devices product ids */
+#define USB_BLACKBIRD_V2_PRODUCT_ID		258
+#define USB_MEMO_PRO_5HS_PRODUCT_ID		260
+#define USB_USBCAN_PRO_5HS_PRODUCT_ID		261
+#define USB_USBCAN_LIGHT_4HS_PRODUCT_ID		262
+#define USB_LEAF_PRO_HS_V2_PRODUCT_ID		263
+#define USB_USBCAN_PRO_2HS_V2_PRODUCT_ID	264
+#define USB_MEMO_2HS_PRODUCT_ID			265
+#define USB_MEMO_PRO_2HS_V2_PRODUCT_ID		266
+#define USB_HYBRID_CANLIN_PRODUCT_ID		267
+#define USB_ATI_USBCAN_PRO_2HS_V2_PRODUCT_ID	268
+#define USB_ATI_MEMO_PRO_2HS_V2_PRODUCT_ID	269
+#define USB_HYBRID_PRO_CANLIN_PRODUCT_ID	270
+
+static inline bool kvaser_is_leaf(const struct usb_device_id *id)
+{
+	return (id->idProduct >= USB_LEAF_DEVEL_PRODUCT_ID &&
+		id->idProduct <= USB_CAN_R_PRODUCT_ID) ||
+		(id->idProduct >= USB_LEAF_LITE_V2_PRODUCT_ID &&
+		 id->idProduct <= USB_MINI_PCIE_2HS_PRODUCT_ID);
+}
+
+static inline bool kvaser_is_usbcan(const struct usb_device_id *id)
+{
+	return id->idProduct >= USB_USBCAN_REVB_PRODUCT_ID &&
+	       id->idProduct <= USB_MEMORATOR_PRODUCT_ID;
+}
+
+static inline bool kvaser_is_hydra(const struct usb_device_id *id)
+{
+	return id->idProduct >= USB_BLACKBIRD_V2_PRODUCT_ID &&
+	       id->idProduct <= USB_HYBRID_PRO_CANLIN_PRODUCT_ID;
+}
+
+static const struct usb_device_id kvaser_usb_table[] = {
+	/* Leaf USB product IDs */
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_DEVEL_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_LS_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_SWC_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_LIN_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_LS_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_SWC_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_DEVEL_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_HSHS_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_UPRO_HSHS_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_GI_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_OBDII_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_HSLS_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_CH_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_BLACKBIRD_SPRO_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_OEM_MERCURY_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_OEM_LEAF_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_CAN_R_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_V2_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_HS_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_LIGHT_2HS_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_2HS_PRODUCT_ID) },
+
+	/* USBCANII USB product IDs */
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN2_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_REVB_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMORATOR_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_VCI2_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+
+	/* Minihydra USB product IDs */
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_BLACKBIRD_V2_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO_PRO_5HS_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_5HS_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_LIGHT_4HS_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_HS_V2_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_2HS_V2_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO_2HS_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO_PRO_2HS_V2_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_CANLIN_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_ATI_USBCAN_PRO_2HS_V2_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_ATI_MEMO_PRO_2HS_V2_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_PRO_CANLIN_PRODUCT_ID) },
+	{ }
+};
+MODULE_DEVICE_TABLE(usb, kvaser_usb_table);
+
+int kvaser_usb_send_cmd(const struct kvaser_usb *dev, void *cmd, int len)
+{
+	int actual_len; /* Not used */
+
+	return usb_bulk_msg(dev->udev,
+			    usb_sndbulkpipe(dev->udev,
+					    dev->bulk_out->bEndpointAddress),
+			    cmd, len, &actual_len, KVASER_USB_TIMEOUT);
+}
+
+int kvaser_usb_recv_cmd(const struct kvaser_usb *dev, void *cmd, int len,
+			int *actual_len)
+{
+	return usb_bulk_msg(dev->udev,
+			    usb_rcvbulkpipe(dev->udev,
+					    dev->bulk_in->bEndpointAddress),
+			    cmd, len, actual_len, KVASER_USB_TIMEOUT);
+}
+
+static void kvaser_usb_send_cmd_callback(struct urb *urb)
+{
+	struct net_device *netdev = urb->context;
+
+	kfree(urb->transfer_buffer);
+
+	if (urb->status)
+		netdev_warn(netdev, "urb status received: %d\n", urb->status);
+}
+
+int kvaser_usb_send_cmd_async(struct kvaser_usb_net_priv *priv, void *cmd,
+			      int len)
+{
+	struct kvaser_usb *dev = priv->dev;
+	struct net_device *netdev = priv->netdev;
+	struct urb *urb;
+	int err;
+
+	urb = usb_alloc_urb(0, GFP_ATOMIC);
+	if (!urb)
+		return -ENOMEM;
+
+	usb_fill_bulk_urb(urb, dev->udev,
+			  usb_sndbulkpipe(dev->udev,
+					  dev->bulk_out->bEndpointAddress),
+			  cmd, len, kvaser_usb_send_cmd_callback, netdev);
+	usb_anchor_urb(urb, &priv->tx_submitted);
+
+	err = usb_submit_urb(urb, GFP_ATOMIC);
+	if (err) {
+		netdev_err(netdev, "Error transmitting URB\n");
+		usb_unanchor_urb(urb);
+	}
+	usb_free_urb(urb);
+
+	return 0;
+}
+
+int kvaser_usb_can_rx_over_error(struct net_device *netdev)
+{
+	struct net_device_stats *stats = &netdev->stats;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+
+	stats->rx_over_errors++;
+	stats->rx_errors++;
+
+	skb = alloc_can_err_skb(netdev, &cf);
+	if (!skb) {
+		stats->rx_dropped++;
+		netdev_warn(netdev, "No memory left for err_skb\n");
+		return -ENOMEM;
+	}
+
+	cf->can_id |= CAN_ERR_CRTL;
+	cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
+
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
+
+	return 0;
+}
+
+static void kvaser_usb_read_bulk_callback(struct urb *urb)
+{
+	struct kvaser_usb *dev = urb->context;
+	int err;
+	unsigned int i;
+
+	switch (urb->status) {
+	case 0:
+		break;
+	case -ENOENT:
+	case -EPIPE:
+	case -EPROTO:
+	case -ESHUTDOWN:
+		return;
+	default:
+		dev_info(&dev->intf->dev, "Rx URB aborted (%d)\n", urb->status);
+		goto resubmit_urb;
+	}
+
+	dev->ops->dev_read_bulk_callback(dev, urb->transfer_buffer,
+					 urb->actual_length);
+
+resubmit_urb:
+	usb_fill_bulk_urb(urb, dev->udev,
+			  usb_rcvbulkpipe(dev->udev,
+					  dev->bulk_in->bEndpointAddress),
+			  urb->transfer_buffer, KVASER_USB_RX_BUFFER_SIZE,
+			  kvaser_usb_read_bulk_callback, dev);
+
+	err = usb_submit_urb(urb, GFP_ATOMIC);
+	if (err == -ENODEV) {
+		for (i = 0; i < dev->nchannels; i++) {
+			if (!dev->nets[i])
+				continue;
+
+			netif_device_detach(dev->nets[i]->netdev);
+		}
+	} else if (err) {
+		dev_err(&dev->intf->dev,
+			"Failed resubmitting read bulk urb: %d\n", err);
+	}
+}
+
+static int kvaser_usb_setup_rx_urbs(struct kvaser_usb *dev)
+{
+	int i, err = 0;
+
+	if (dev->rxinitdone)
+		return 0;
+
+	for (i = 0; i < KVASER_USB_MAX_RX_URBS; i++) {
+		struct urb *urb = NULL;
+		u8 *buf = NULL;
+		dma_addr_t buf_dma;
+
+		urb = usb_alloc_urb(0, GFP_KERNEL);
+		if (!urb) {
+			err = -ENOMEM;
+			break;
+		}
+
+		buf = usb_alloc_coherent(dev->udev, KVASER_USB_RX_BUFFER_SIZE,
+					 GFP_KERNEL, &buf_dma);
+		if (!buf) {
+			dev_warn(&dev->intf->dev,
+				 "No memory left for USB buffer\n");
+			usb_free_urb(urb);
+			err = -ENOMEM;
+			break;
+		}
+
+		usb_fill_bulk_urb(urb, dev->udev,
+				  usb_rcvbulkpipe
+					(dev->udev,
+					 dev->bulk_in->bEndpointAddress),
+				  buf, KVASER_USB_RX_BUFFER_SIZE,
+				  kvaser_usb_read_bulk_callback, dev);
+		urb->transfer_dma = buf_dma;
+		urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
+		usb_anchor_urb(urb, &dev->rx_submitted);
+
+		err = usb_submit_urb(urb, GFP_KERNEL);
+		if (err) {
+			usb_unanchor_urb(urb);
+			usb_free_coherent(dev->udev,
+					  KVASER_USB_RX_BUFFER_SIZE, buf,
+					  buf_dma);
+			usb_free_urb(urb);
+			break;
+		}
+
+		dev->rxbuf[i] = buf;
+		dev->rxbuf_dma[i] = buf_dma;
+
+		usb_free_urb(urb);
+	}
+
+	if (i == 0) {
+		dev_warn(&dev->intf->dev, "Cannot setup read URBs, error %d\n",
+			 err);
+		return err;
+	} else if (i < KVASER_USB_MAX_RX_URBS) {
+		dev_warn(&dev->intf->dev, "RX performances may be slow\n");
+	}
+
+	dev->rxinitdone = true;
+
+	return 0;
+}
+
+static int kvaser_usb_open(struct net_device *netdev)
+{
+	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
+	struct kvaser_usb *dev = priv->dev;
+	int err;
+
+	err = open_candev(netdev);
+	if (err)
+		return err;
+
+	err = kvaser_usb_setup_rx_urbs(dev);
+	if (err)
+		goto error;
+
+	err = dev->ops->dev_set_opt_mode(priv);
+	if (err)
+		goto error;
+
+	err = dev->ops->dev_start_chip(priv);
+	if (err) {
+		netdev_warn(netdev, "Cannot start device, error %d\n", err);
+		goto error;
+	}
+
+	priv->can.state = CAN_STATE_ERROR_ACTIVE;
+
+	return 0;
+
+error:
+	close_candev(netdev);
+	return err;
+}
+
+static void kvaser_usb_reset_tx_urb_contexts(struct kvaser_usb_net_priv *priv)
+{
+	int i, max_tx_urbs;
+
+	max_tx_urbs = priv->dev->max_tx_urbs;
+
+	priv->active_tx_contexts = 0;
+	for (i = 0; i < max_tx_urbs; i++)
+		priv->tx_contexts[i].echo_index = max_tx_urbs;
+}
+
+/* This method might sleep. Do not call it in the atomic context
+ * of URB completions.
+ */
+static void kvaser_usb_unlink_tx_urbs(struct kvaser_usb_net_priv *priv)
+{
+	usb_kill_anchored_urbs(&priv->tx_submitted);
+	kvaser_usb_reset_tx_urb_contexts(priv);
+}
+
+static void kvaser_usb_unlink_all_urbs(struct kvaser_usb *dev)
+{
+	int i;
+
+	usb_kill_anchored_urbs(&dev->rx_submitted);
+
+	for (i = 0; i < KVASER_USB_MAX_RX_URBS; i++)
+		usb_free_coherent(dev->udev, KVASER_USB_RX_BUFFER_SIZE,
+				  dev->rxbuf[i], dev->rxbuf_dma[i]);
+
+	for (i = 0; i < dev->nchannels; i++) {
+		struct kvaser_usb_net_priv *priv = dev->nets[i];
+
+		if (priv)
+			kvaser_usb_unlink_tx_urbs(priv);
+	}
+}
+
+static int kvaser_usb_close(struct net_device *netdev)
+{
+	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
+	struct kvaser_usb *dev = priv->dev;
+	int err;
+
+	netif_stop_queue(netdev);
+
+	err = dev->ops->dev_flush_queue(priv);
+	if (err)
+		netdev_warn(netdev, "Cannot flush queue, error %d\n", err);
+
+	if (dev->ops->dev_reset_chip) {
+		err = dev->ops->dev_reset_chip(dev, priv->channel);
+		if (err)
+			netdev_warn(netdev, "Cannot reset card, error %d\n",
+				    err);
+	}
+
+	err = dev->ops->dev_stop_chip(priv);
+	if (err)
+		netdev_warn(netdev, "Cannot stop device, error %d\n", err);
+
+	/* reset tx contexts */
+	kvaser_usb_unlink_tx_urbs(priv);
+
+	priv->can.state = CAN_STATE_STOPPED;
+	close_candev(priv->netdev);
+
+	return 0;
+}
+
+static void kvaser_usb_write_bulk_callback(struct urb *urb)
+{
+	struct kvaser_usb_tx_urb_context *context = urb->context;
+	struct kvaser_usb_net_priv *priv;
+	struct net_device *netdev;
+
+	if (WARN_ON(!context))
+		return;
+
+	priv = context->priv;
+	netdev = priv->netdev;
+
+	kfree(urb->transfer_buffer);
+
+	if (!netif_device_present(netdev))
+		return;
+
+	if (urb->status)
+		netdev_info(netdev, "Tx URB aborted (%d)\n", urb->status);
+}
+
+static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb,
+					 struct net_device *netdev)
+{
+	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
+	struct kvaser_usb *dev = priv->dev;
+	struct net_device_stats *stats = &netdev->stats;
+	struct kvaser_usb_tx_urb_context *context = NULL;
+	struct urb *urb;
+	void *buf;
+	int cmd_len = 0;
+	int err, ret = NETDEV_TX_OK;
+	unsigned int i;
+	unsigned long flags;
+
+	if (can_dropped_invalid_skb(netdev, skb))
+		return NETDEV_TX_OK;
+
+	urb = usb_alloc_urb(0, GFP_ATOMIC);
+	if (!urb) {
+		stats->tx_dropped++;
+		dev_kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
+
+	spin_lock_irqsave(&priv->tx_contexts_lock, flags);
+	for (i = 0; i < dev->max_tx_urbs; i++) {
+		if (priv->tx_contexts[i].echo_index == dev->max_tx_urbs) {
+			context = &priv->tx_contexts[i];
+
+			context->echo_index = i;
+			can_put_echo_skb(skb, netdev, context->echo_index);
+			++priv->active_tx_contexts;
+			if (priv->active_tx_contexts >= (int)dev->max_tx_urbs)
+				netif_stop_queue(netdev);
+
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&priv->tx_contexts_lock, flags);
+
+	/* This should never happen; it implies a flow control bug */
+	if (!context) {
+		netdev_warn(netdev, "cannot find free context\n");
+
+		ret = NETDEV_TX_BUSY;
+		goto freeurb;
+	}
+
+	buf = dev->ops->dev_frame_to_cmd(priv, skb, &context->dlc, &cmd_len,
+					 context->echo_index);
+	if (!buf) {
+		stats->tx_dropped++;
+		dev_kfree_skb(skb);
+		spin_lock_irqsave(&priv->tx_contexts_lock, flags);
+
+		can_free_echo_skb(netdev, context->echo_index);
+		context->echo_index = dev->max_tx_urbs;
+		--priv->active_tx_contexts;
+		netif_wake_queue(netdev);
+
+		spin_unlock_irqrestore(&priv->tx_contexts_lock, flags);
+		goto freeurb;
+	}
+
+	context->priv = priv;
+
+	usb_fill_bulk_urb(urb, dev->udev,
+			  usb_sndbulkpipe(dev->udev,
+					  dev->bulk_out->bEndpointAddress),
+			  buf, cmd_len, kvaser_usb_write_bulk_callback,
+			  context);
+	usb_anchor_urb(urb, &priv->tx_submitted);
+
+	err = usb_submit_urb(urb, GFP_ATOMIC);
+	if (unlikely(err)) {
+		spin_lock_irqsave(&priv->tx_contexts_lock, flags);
+
+		can_free_echo_skb(netdev, context->echo_index);
+		context->echo_index = dev->max_tx_urbs;
+		--priv->active_tx_contexts;
+		netif_wake_queue(netdev);
+
+		spin_unlock_irqrestore(&priv->tx_contexts_lock, flags);
+
+		usb_unanchor_urb(urb);
+		kfree(buf);
+
+		stats->tx_dropped++;
+
+		if (err == -ENODEV)
+			netif_device_detach(netdev);
+		else
+			netdev_warn(netdev, "Failed tx_urb %d\n", err);
+
+		goto freeurb;
+	}
+
+	ret = NETDEV_TX_OK;
+
+freeurb:
+	usb_free_urb(urb);
+	return ret;
+}
+
+static const struct net_device_ops kvaser_usb_netdev_ops = {
+	.ndo_open = kvaser_usb_open,
+	.ndo_stop = kvaser_usb_close,
+	.ndo_start_xmit = kvaser_usb_start_xmit,
+	.ndo_change_mtu = can_change_mtu,
+};
+
+static void kvaser_usb_remove_interfaces(struct kvaser_usb *dev)
+{
+	int i;
+
+	for (i = 0; i < dev->nchannels; i++) {
+		if (!dev->nets[i])
+			continue;
+
+		unregister_candev(dev->nets[i]->netdev);
+	}
+
+	kvaser_usb_unlink_all_urbs(dev);
+
+	for (i = 0; i < dev->nchannels; i++) {
+		if (!dev->nets[i])
+			continue;
+
+		free_candev(dev->nets[i]->netdev);
+	}
+}
+
+static int kvaser_usb_init_one(struct kvaser_usb *dev,
+			       const struct usb_device_id *id, int channel)
+{
+	struct net_device *netdev;
+	struct kvaser_usb_net_priv *priv;
+	int err;
+
+	if (dev->ops->dev_reset_chip) {
+		err = dev->ops->dev_reset_chip(dev, channel);
+		if (err)
+			return err;
+	}
+
+	netdev = alloc_candev(sizeof(*priv) +
+			      dev->max_tx_urbs * sizeof(*priv->tx_contexts),
+			      dev->max_tx_urbs);
+	if (!netdev) {
+		dev_err(&dev->intf->dev, "Cannot alloc candev\n");
+		return -ENOMEM;
+	}
+
+	priv = netdev_priv(netdev);
+
+	init_usb_anchor(&priv->tx_submitted);
+	init_completion(&priv->start_comp);
+	init_completion(&priv->stop_comp);
+	priv->can.ctrlmode_supported = 0;
+
+	priv->dev = dev;
+	priv->netdev = netdev;
+	priv->channel = channel;
+
+	spin_lock_init(&priv->tx_contexts_lock);
+	kvaser_usb_reset_tx_urb_contexts(priv);
+
+	priv->can.state = CAN_STATE_STOPPED;
+	priv->can.clock.freq = dev->cfg->clock.freq;
+	priv->can.bittiming_const = dev->cfg->bittiming_const;
+	priv->can.do_set_bittiming = dev->ops->dev_set_bittiming;
+	priv->can.do_set_mode = dev->ops->dev_set_mode;
+	if ((id->driver_info & KVASER_USB_HAS_TXRX_ERRORS) ||
+	    (priv->dev->card_data.capabilities & KVASER_USB_CAP_BERR_CAP))
+		priv->can.do_get_berr_counter = dev->ops->dev_get_berr_counter;
+	if (id->driver_info & KVASER_USB_HAS_SILENT_MODE)
+		priv->can.ctrlmode_supported |= CAN_CTRLMODE_LISTENONLY;
+
+	priv->can.ctrlmode_supported |= dev->card_data.ctrlmode_supported;
+
+	if (priv->can.ctrlmode_supported & CAN_CTRLMODE_FD) {
+		priv->can.data_bittiming_const = dev->cfg->data_bittiming_const;
+		priv->can.do_set_data_bittiming =
+					dev->ops->dev_set_data_bittiming;
+	}
+
+	netdev->flags |= IFF_ECHO;
+
+	netdev->netdev_ops = &kvaser_usb_netdev_ops;
+
+	SET_NETDEV_DEV(netdev, &dev->intf->dev);
+	netdev->dev_id = channel;
+
+	dev->nets[channel] = priv;
+
+	err = register_candev(netdev);
+	if (err) {
+		dev_err(&dev->intf->dev, "Failed to register CAN device\n");
+		free_candev(netdev);
+		dev->nets[channel] = NULL;
+		return err;
+	}
+
+	netdev_dbg(netdev, "device registered\n");
+
+	return 0;
+}
+
+static int kvaser_usb_probe(struct usb_interface *intf,
+			    const struct usb_device_id *id)
+{
+	struct kvaser_usb *dev;
+	int err;
+	int i;
+
+	dev = devm_kzalloc(&intf->dev, sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	if (kvaser_is_leaf(id)) {
+		dev->card_data.leaf.family = KVASER_LEAF;
+		dev->ops = &kvaser_usb_leaf_dev_ops;
+	} else if (kvaser_is_usbcan(id)) {
+		dev->card_data.leaf.family = KVASER_USBCAN;
+		dev->ops = &kvaser_usb_leaf_dev_ops;
+	} else if (kvaser_is_hydra(id)) {
+		dev->ops = &kvaser_usb_hydra_dev_ops;
+	} else {
+		dev_err(&intf->dev,
+			"Product ID (%d) is not a supported Kvaser USB device\n",
+			id->idProduct);
+		return -ENODEV;
+	}
+
+	dev->intf = intf;
+
+	err = dev->ops->dev_setup_endpoints(dev);
+	if (err) {
+		dev_err(&intf->dev, "Cannot get usb endpoint(s)");
+		return err;
+	}
+
+	dev->udev = interface_to_usbdev(intf);
+
+	init_usb_anchor(&dev->rx_submitted);
+
+	usb_set_intfdata(intf, dev);
+
+	dev->card_data.ctrlmode_supported = 0;
+	dev->card_data.capabilities = 0;
+	err = dev->ops->dev_init_card(dev);
+	if (err) {
+		dev_err(&intf->dev,
+			"Failed to initialize card, error %d\n", err);
+		return err;
+	}
+
+	err = dev->ops->dev_get_software_info(dev);
+	if (err) {
+		dev_err(&intf->dev,
+			"Cannot get software info, error %d\n", err);
+		return err;
+	}
+
+	if (dev->ops->dev_get_software_details) {
+		err = dev->ops->dev_get_software_details(dev);
+		if (err) {
+			dev_err(&intf->dev,
+				"Cannot get software details, error %d\n", err);
+			return err;
+		}
+	}
+
+	if (WARN_ON(!dev->cfg))
+		return -ENODEV;
+
+	dev_dbg(&intf->dev, "Firmware version: %d.%d.%d\n",
+		((dev->fw_version >> 24) & 0xff),
+		((dev->fw_version >> 16) & 0xff),
+		(dev->fw_version & 0xffff));
+
+	dev_dbg(&intf->dev, "Max outstanding tx = %d URBs\n", dev->max_tx_urbs);
+
+	err = dev->ops->dev_get_card_info(dev);
+	if (err) {
+		dev_err(&intf->dev, "Cannot get card info, error %d\n", err);
+		return err;
+	}
+
+	if (dev->ops->dev_get_capabilities) {
+		err = dev->ops->dev_get_capabilities(dev);
+		if (err) {
+			dev_err(&intf->dev,
+				"Cannot get capabilities, error %d\n", err);
+			kvaser_usb_remove_interfaces(dev);
+			return err;
+		}
+	}
+
+	for (i = 0; i < dev->nchannels; i++) {
+		err = kvaser_usb_init_one(dev, id, i);
+		if (err) {
+			kvaser_usb_remove_interfaces(dev);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static void kvaser_usb_disconnect(struct usb_interface *intf)
+{
+	struct kvaser_usb *dev = usb_get_intfdata(intf);
+
+	usb_set_intfdata(intf, NULL);
+
+	if (!dev)
+		return;
+
+	kvaser_usb_remove_interfaces(dev);
+}
+
+static struct usb_driver kvaser_usb_driver = {
+	.name = "kvaser_usb",
+	.probe = kvaser_usb_probe,
+	.disconnect = kvaser_usb_disconnect,
+	.id_table = kvaser_usb_table,
+};
+
+module_usb_driver(kvaser_usb_driver);
+
+MODULE_AUTHOR("Olivier Sobrie <olivier@sobrie.be>");
+MODULE_AUTHOR("Kvaser AB <support@kvaser.com>");
+MODULE_DESCRIPTION("CAN driver for Kvaser CAN/USB devices");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
new file mode 100644
index 000000000000..c084bae5ec0a
--- /dev/null
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
@@ -0,0 +1,2028 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Parts of this driver are based on the following:
+ *  - Kvaser linux mhydra driver (version 5.24)
+ *  - CAN driver for esd CAN-USB/2
+ *
+ * Copyright (C) 2018 KVASER AB, Sweden. All rights reserved.
+ * Copyright (C) 2010 Matthias Fuchs <matthias.fuchs@esd.eu>, esd gmbh
+ *
+ * Known issues:
+ *  - Transition from CAN_STATE_ERROR_WARNING to CAN_STATE_ERROR_ACTIVE is only
+ *    reported after a call to do_get_berr_counter(), since firmware does not
+ *    distinguish between ERROR_WARNING and ERROR_ACTIVE.
+ *  - Hardware timestamps are not set for CAN Tx frames.
+ */
+
+#include <linux/completion.h>
+#include <linux/device.h>
+#include <linux/gfp.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/usb.h>
+
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/error.h>
+#include <linux/can/netlink.h>
+
+#include "kvaser_usb.h"
+
+/* Forward declarations */
+static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_kcan;
+static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_flexc;
+
+#define KVASER_USB_HYDRA_BULK_EP_IN_ADDR	0x82
+#define KVASER_USB_HYDRA_BULK_EP_OUT_ADDR	0x02
+
+#define KVASER_USB_HYDRA_MAX_TRANSID		0xff
+#define KVASER_USB_HYDRA_MIN_TRANSID		0x01
+
+/* Minihydra command IDs */
+#define CMD_SET_BUSPARAMS_REQ			16
+#define CMD_GET_CHIP_STATE_REQ			19
+#define CMD_CHIP_STATE_EVENT			20
+#define CMD_SET_DRIVERMODE_REQ			21
+#define CMD_START_CHIP_REQ			26
+#define CMD_START_CHIP_RESP			27
+#define CMD_STOP_CHIP_REQ			28
+#define CMD_STOP_CHIP_RESP			29
+#define CMD_TX_CAN_MESSAGE			33
+#define CMD_GET_CARD_INFO_REQ			34
+#define CMD_GET_CARD_INFO_RESP			35
+#define CMD_GET_SOFTWARE_INFO_REQ		38
+#define CMD_GET_SOFTWARE_INFO_RESP		39
+#define CMD_ERROR_EVENT				45
+#define CMD_FLUSH_QUEUE				48
+#define CMD_TX_ACKNOWLEDGE			50
+#define CMD_FLUSH_QUEUE_RESP			66
+#define CMD_SET_BUSPARAMS_FD_REQ		69
+#define CMD_SET_BUSPARAMS_FD_RESP		70
+#define CMD_SET_BUSPARAMS_RESP			85
+#define CMD_GET_CAPABILITIES_REQ		95
+#define CMD_GET_CAPABILITIES_RESP		96
+#define CMD_RX_MESSAGE				106
+#define CMD_MAP_CHANNEL_REQ			200
+#define CMD_MAP_CHANNEL_RESP			201
+#define CMD_GET_SOFTWARE_DETAILS_REQ		202
+#define CMD_GET_SOFTWARE_DETAILS_RESP		203
+#define CMD_EXTENDED				255
+
+/* Minihydra extended command IDs */
+#define CMD_TX_CAN_MESSAGE_FD			224
+#define CMD_TX_ACKNOWLEDGE_FD			225
+#define CMD_RX_MESSAGE_FD			226
+
+/* Hydra commands are handled by different threads in firmware.
+ * The threads are denoted hydra entity (HE). Each HE got a unique 6-bit
+ * address. The address is used in hydra commands to get/set source and
+ * destination HE. There are two predefined HE addresses, the remaining
+ * addresses are different between devices and firmware versions. Hence, we need
+ * to enumerate the addresses (see kvaser_usb_hydra_map_channel()).
+ */
+
+/* Well-known HE addresses */
+#define KVASER_USB_HYDRA_HE_ADDRESS_ROUTER	0x00
+#define KVASER_USB_HYDRA_HE_ADDRESS_ILLEGAL	0x3e
+
+#define KVASER_USB_HYDRA_TRANSID_CANHE		0x40
+#define KVASER_USB_HYDRA_TRANSID_SYSDBG		0x61
+
+struct kvaser_cmd_map_ch_req {
+	char name[16];
+	u8 channel;
+	u8 reserved[11];
+} __packed;
+
+struct kvaser_cmd_map_ch_res {
+	u8 he_addr;
+	u8 channel;
+	u8 reserved[26];
+} __packed;
+
+struct kvaser_cmd_card_info {
+	__le32 serial_number;
+	__le32 clock_res;
+	__le32 mfg_date;
+	__le32 ean[2];
+	u8 hw_version;
+	u8 usb_mode;
+	u8 hw_type;
+	u8 reserved0;
+	u8 nchannels;
+	u8 reserved1[3];
+} __packed;
+
+struct kvaser_cmd_sw_info {
+	u8 reserved0[8];
+	__le16 max_outstanding_tx;
+	u8 reserved1[18];
+} __packed;
+
+struct kvaser_cmd_sw_detail_req {
+	u8 use_ext_cmd;
+	u8 reserved[27];
+} __packed;
+
+/* Software detail flags */
+#define KVASER_USB_HYDRA_SW_FLAG_FW_BETA	BIT(2)
+#define KVASER_USB_HYDRA_SW_FLAG_FW_BAD		BIT(4)
+#define KVASER_USB_HYDRA_SW_FLAG_FREQ_80M	BIT(5)
+#define KVASER_USB_HYDRA_SW_FLAG_EXT_CMD	BIT(9)
+#define KVASER_USB_HYDRA_SW_FLAG_CANFD		BIT(10)
+#define KVASER_USB_HYDRA_SW_FLAG_NONISO		BIT(11)
+#define KVASER_USB_HYDRA_SW_FLAG_EXT_CAP	BIT(12)
+struct kvaser_cmd_sw_detail_res {
+	__le32 sw_flags;
+	__le32 sw_version;
+	__le32 sw_name;
+	__le32 ean[2];
+	__le32 max_bitrate;
+	u8 reserved[4];
+} __packed;
+
+/* Sub commands for cap_req and cap_res */
+#define KVASER_USB_HYDRA_CAP_CMD_LISTEN_MODE	0x02
+#define KVASER_USB_HYDRA_CAP_CMD_ERR_REPORT	0x05
+#define KVASER_USB_HYDRA_CAP_CMD_ONE_SHOT	0x06
+struct kvaser_cmd_cap_req {
+	__le16 cap_cmd;
+	u8 reserved[26];
+} __packed;
+
+/* Status codes for cap_res */
+#define KVASER_USB_HYDRA_CAP_STAT_OK		0x00
+#define KVASER_USB_HYDRA_CAP_STAT_NOT_IMPL	0x01
+#define KVASER_USB_HYDRA_CAP_STAT_UNAVAIL	0x02
+struct kvaser_cmd_cap_res {
+	__le16 cap_cmd;
+	__le16 status;
+	__le32 mask;
+	__le32 value;
+	u8 reserved[16];
+} __packed;
+
+/* CMD_ERROR_EVENT error codes */
+#define KVASER_USB_HYDRA_ERROR_EVENT_CAN	0x01
+#define KVASER_USB_HYDRA_ERROR_EVENT_PARAM	0x09
+struct kvaser_cmd_error_event {
+	__le16 timestamp[3];
+	u8 reserved;
+	u8 error_code;
+	__le16 info1;
+	__le16 info2;
+} __packed;
+
+/* Chip state status flags. Used for chip_state_event and err_frame_data. */
+#define KVASER_USB_HYDRA_BUS_ERR_ACT		0x00
+#define KVASER_USB_HYDRA_BUS_ERR_PASS		BIT(5)
+#define KVASER_USB_HYDRA_BUS_BUS_OFF		BIT(6)
+struct kvaser_cmd_chip_state_event {
+	__le16 timestamp[3];
+	u8 tx_err_counter;
+	u8 rx_err_counter;
+	u8 bus_status;
+	u8 reserved[19];
+} __packed;
+
+/* Busparam modes */
+#define KVASER_USB_HYDRA_BUS_MODE_CAN		0x00
+#define KVASER_USB_HYDRA_BUS_MODE_CANFD_ISO	0x01
+#define KVASER_USB_HYDRA_BUS_MODE_NONISO	0x02
+struct kvaser_cmd_set_busparams {
+	__le32 bitrate;
+	u8 tseg1;
+	u8 tseg2;
+	u8 sjw;
+	u8 nsamples;
+	u8 reserved0[4];
+	__le32 bitrate_d;
+	u8 tseg1_d;
+	u8 tseg2_d;
+	u8 sjw_d;
+	u8 nsamples_d;
+	u8 canfd_mode;
+	u8 reserved1[7];
+} __packed;
+
+/* Ctrl modes */
+#define KVASER_USB_HYDRA_CTRLMODE_NORMAL	0x01
+#define KVASER_USB_HYDRA_CTRLMODE_LISTEN	0x02
+struct kvaser_cmd_set_ctrlmode {
+	u8 mode;
+	u8 reserved[27];
+} __packed;
+
+struct kvaser_err_frame_data {
+	u8 bus_status;
+	u8 reserved0;
+	u8 tx_err_counter;
+	u8 rx_err_counter;
+	u8 reserved1[4];
+} __packed;
+
+struct kvaser_cmd_rx_can {
+	u8 cmd_len;
+	u8 cmd_no;
+	u8 channel;
+	u8 flags;
+	__le16 timestamp[3];
+	u8 dlc;
+	u8 padding;
+	__le32 id;
+	union {
+		u8 data[8];
+		struct kvaser_err_frame_data err_frame_data;
+	};
+} __packed;
+
+/* Extended CAN ID flag. Used in rx_can and tx_can */
+#define KVASER_USB_HYDRA_EXTENDED_FRAME_ID	BIT(31)
+struct kvaser_cmd_tx_can {
+	__le32 id;
+	u8 data[8];
+	u8 dlc;
+	u8 flags;
+	__le16 transid;
+	u8 channel;
+	u8 reserved[11];
+} __packed;
+
+struct kvaser_cmd_header {
+	u8 cmd_no;
+	/* The destination HE address is stored in 0..5 of he_addr.
+	 * The upper part of source HE address is stored in 6..7 of he_addr, and
+	 * the lower part is stored in 12..15 of transid.
+	 */
+	u8 he_addr;
+	__le16 transid;
+} __packed;
+
+struct kvaser_cmd {
+	struct kvaser_cmd_header header;
+	union {
+		struct kvaser_cmd_map_ch_req map_ch_req;
+		struct kvaser_cmd_map_ch_res map_ch_res;
+
+		struct kvaser_cmd_card_info card_info;
+		struct kvaser_cmd_sw_info sw_info;
+		struct kvaser_cmd_sw_detail_req sw_detail_req;
+		struct kvaser_cmd_sw_detail_res sw_detail_res;
+
+		struct kvaser_cmd_cap_req cap_req;
+		struct kvaser_cmd_cap_res cap_res;
+
+		struct kvaser_cmd_error_event error_event;
+
+		struct kvaser_cmd_set_busparams set_busparams_req;
+
+		struct kvaser_cmd_chip_state_event chip_state_event;
+
+		struct kvaser_cmd_set_ctrlmode set_ctrlmode;
+
+		struct kvaser_cmd_rx_can rx_can;
+		struct kvaser_cmd_tx_can tx_can;
+	} __packed;
+} __packed;
+
+/* CAN frame flags. Used in rx_can, ext_rx_can, tx_can and ext_tx_can */
+#define KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME	BIT(0)
+#define KVASER_USB_HYDRA_CF_FLAG_OVERRUN	BIT(1)
+#define KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME	BIT(4)
+#define KVASER_USB_HYDRA_CF_FLAG_EXTENDED_ID	BIT(5)
+/* CAN frame flags. Used in ext_rx_can and ext_tx_can */
+#define KVASER_USB_HYDRA_CF_FLAG_OSM_NACK	BIT(12)
+#define KVASER_USB_HYDRA_CF_FLAG_ABL		BIT(13)
+#define KVASER_USB_HYDRA_CF_FLAG_FDF		BIT(16)
+#define KVASER_USB_HYDRA_CF_FLAG_BRS		BIT(17)
+#define KVASER_USB_HYDRA_CF_FLAG_ESI		BIT(18)
+
+/* KCAN packet header macros. Used in ext_rx_can and ext_tx_can */
+#define KVASER_USB_KCAN_DATA_DLC_BITS		4
+#define KVASER_USB_KCAN_DATA_DLC_SHIFT		8
+#define KVASER_USB_KCAN_DATA_DLC_MASK \
+				GENMASK(KVASER_USB_KCAN_DATA_DLC_BITS - 1 + \
+				KVASER_USB_KCAN_DATA_DLC_SHIFT, \
+				KVASER_USB_KCAN_DATA_DLC_SHIFT)
+
+#define KVASER_USB_KCAN_DATA_BRS		BIT(14)
+#define KVASER_USB_KCAN_DATA_FDF		BIT(15)
+#define KVASER_USB_KCAN_DATA_OSM		BIT(16)
+#define KVASER_USB_KCAN_DATA_AREQ		BIT(31)
+#define KVASER_USB_KCAN_DATA_SRR		BIT(31)
+#define KVASER_USB_KCAN_DATA_RTR		BIT(29)
+#define KVASER_USB_KCAN_DATA_IDE		BIT(30)
+struct kvaser_cmd_ext_rx_can {
+	__le32 flags;
+	__le32 id;
+	__le32 kcan_id;
+	__le32 kcan_header;
+	__le64 timestamp;
+	union {
+		u8 kcan_payload[64];
+		struct kvaser_err_frame_data err_frame_data;
+	};
+} __packed;
+
+struct kvaser_cmd_ext_tx_can {
+	__le32 flags;
+	__le32 id;
+	__le32 kcan_id;
+	__le32 kcan_header;
+	u8 databytes;
+	u8 dlc;
+	u8 reserved[6];
+	u8 kcan_payload[64];
+} __packed;
+
+struct kvaser_cmd_ext_tx_ack {
+	__le32 flags;
+	u8 reserved0[4];
+	__le64 timestamp;
+	u8 reserved1[8];
+} __packed;
+
+/* struct for extended commands (CMD_EXTENDED) */
+struct kvaser_cmd_ext {
+	struct kvaser_cmd_header header;
+	__le16 len;
+	u8 cmd_no_ext;
+	u8 reserved;
+
+	union {
+		struct kvaser_cmd_ext_rx_can rx_can;
+		struct kvaser_cmd_ext_tx_can tx_can;
+		struct kvaser_cmd_ext_tx_ack tx_ack;
+	} __packed;
+} __packed;
+
+static const struct can_bittiming_const kvaser_usb_hydra_kcan_bittiming_c = {
+	.name = "kvaser_usb_kcan",
+	.tseg1_min = 1,
+	.tseg1_max = 255,
+	.tseg2_min = 1,
+	.tseg2_max = 32,
+	.sjw_max = 16,
+	.brp_min = 1,
+	.brp_max = 4096,
+	.brp_inc = 1,
+};
+
+static const struct can_bittiming_const kvaser_usb_hydra_flexc_bittiming_c = {
+	.name = "kvaser_usb_flex",
+	.tseg1_min = 4,
+	.tseg1_max = 16,
+	.tseg2_min = 2,
+	.tseg2_max = 8,
+	.sjw_max = 4,
+	.brp_min = 1,
+	.brp_max = 256,
+	.brp_inc = 1,
+};
+
+#define KVASER_USB_HYDRA_TRANSID_BITS		12
+#define KVASER_USB_HYDRA_TRANSID_MASK \
+				GENMASK(KVASER_USB_HYDRA_TRANSID_BITS - 1, 0)
+#define KVASER_USB_HYDRA_HE_ADDR_SRC_MASK	GENMASK(7, 6)
+#define KVASER_USB_HYDRA_HE_ADDR_DEST_MASK	GENMASK(5, 0)
+#define KVASER_USB_HYDRA_HE_ADDR_SRC_BITS	2
+static inline u16 kvaser_usb_hydra_get_cmd_transid(const struct kvaser_cmd *cmd)
+{
+	return le16_to_cpu(cmd->header.transid) & KVASER_USB_HYDRA_TRANSID_MASK;
+}
+
+static inline void kvaser_usb_hydra_set_cmd_transid(struct kvaser_cmd *cmd,
+						    u16 transid)
+{
+	cmd->header.transid =
+			cpu_to_le16(transid & KVASER_USB_HYDRA_TRANSID_MASK);
+}
+
+static inline u8 kvaser_usb_hydra_get_cmd_src_he(const struct kvaser_cmd *cmd)
+{
+	return (cmd->header.he_addr & KVASER_USB_HYDRA_HE_ADDR_SRC_MASK) >>
+		KVASER_USB_HYDRA_HE_ADDR_SRC_BITS |
+		le16_to_cpu(cmd->header.transid) >>
+		KVASER_USB_HYDRA_TRANSID_BITS;
+}
+
+static inline void kvaser_usb_hydra_set_cmd_dest_he(struct kvaser_cmd *cmd,
+						    u8 dest_he)
+{
+	cmd->header.he_addr =
+		(cmd->header.he_addr & KVASER_USB_HYDRA_HE_ADDR_SRC_MASK) |
+		(dest_he & KVASER_USB_HYDRA_HE_ADDR_DEST_MASK);
+}
+
+static u8 kvaser_usb_hydra_channel_from_cmd(const struct kvaser_usb *dev,
+					    const struct kvaser_cmd *cmd)
+{
+	int i;
+	u8 channel = 0xff;
+	u8 src_he = kvaser_usb_hydra_get_cmd_src_he(cmd);
+
+	for (i = 0; i < KVASER_USB_MAX_NET_DEVICES; i++) {
+		if (dev->card_data.hydra.channel_to_he[i] == src_he) {
+			channel = i;
+			break;
+		}
+	}
+
+	return channel;
+}
+
+static u16 kvaser_usb_hydra_get_next_transid(struct kvaser_usb *dev)
+{
+	unsigned long flags;
+	u16 transid;
+	struct kvaser_usb_dev_card_data_hydra *card_data =
+							&dev->card_data.hydra;
+
+	spin_lock_irqsave(&card_data->transid_lock, flags);
+	transid = card_data->transid;
+	if (transid >= KVASER_USB_HYDRA_MAX_TRANSID)
+		transid = KVASER_USB_HYDRA_MIN_TRANSID;
+	else
+		transid++;
+	card_data->transid = transid;
+	spin_unlock_irqrestore(&card_data->transid_lock, flags);
+
+	return transid;
+}
+
+static size_t kvaser_usb_hydra_cmd_size(struct kvaser_cmd *cmd)
+{
+	size_t ret;
+
+	if (cmd->header.cmd_no == CMD_EXTENDED)
+		ret = le16_to_cpu(((struct kvaser_cmd_ext *)cmd)->len);
+	else
+		ret = sizeof(struct kvaser_cmd);
+
+	return ret;
+}
+
+static struct kvaser_usb_net_priv *
+kvaser_usb_hydra_net_priv_from_cmd(const struct kvaser_usb *dev,
+				   const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_net_priv *priv = NULL;
+	u8 channel = kvaser_usb_hydra_channel_from_cmd(dev, cmd);
+
+	if (channel >= dev->nchannels)
+		dev_err(&dev->intf->dev,
+			"Invalid channel number (%d)\n", channel);
+	else
+		priv = dev->nets[channel];
+
+	return priv;
+}
+
+static ktime_t
+kvaser_usb_hydra_ktime_from_rx_cmd(const struct kvaser_usb_dev_cfg *cfg,
+				   const struct kvaser_cmd *cmd)
+{
+	u64 ticks;
+
+	if (cmd->header.cmd_no == CMD_EXTENDED) {
+		struct kvaser_cmd_ext *cmd_ext = (struct kvaser_cmd_ext *)cmd;
+
+		ticks = le64_to_cpu(cmd_ext->rx_can.timestamp);
+	} else {
+		ticks = le16_to_cpu(cmd->rx_can.timestamp[0]);
+		ticks += (u64)(le16_to_cpu(cmd->rx_can.timestamp[1])) << 16;
+		ticks += (u64)(le16_to_cpu(cmd->rx_can.timestamp[2])) << 32;
+	}
+
+	return ns_to_ktime(div_u64(ticks * 1000, cfg->timestamp_freq));
+}
+
+static int kvaser_usb_hydra_send_simple_cmd(struct kvaser_usb *dev,
+					    u8 cmd_no, int channel)
+{
+	struct kvaser_cmd *cmd;
+	int err;
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->header.cmd_no = cmd_no;
+	if (channel < 0) {
+		kvaser_usb_hydra_set_cmd_dest_he
+				(cmd, KVASER_USB_HYDRA_HE_ADDRESS_ILLEGAL);
+	} else {
+		if (channel >= KVASER_USB_MAX_NET_DEVICES) {
+			dev_err(&dev->intf->dev, "channel (%d) out of range.\n",
+				channel);
+			err = -EINVAL;
+			goto end;
+		}
+		kvaser_usb_hydra_set_cmd_dest_he
+			(cmd, dev->card_data.hydra.channel_to_he[channel]);
+	}
+	kvaser_usb_hydra_set_cmd_transid
+				(cmd, kvaser_usb_hydra_get_next_transid(dev));
+
+	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+	if (err)
+		goto end;
+
+end:
+	kfree(cmd);
+
+	return err;
+}
+
+static int
+kvaser_usb_hydra_send_simple_cmd_async(struct kvaser_usb_net_priv *priv,
+				       u8 cmd_no)
+{
+	struct kvaser_cmd *cmd;
+	struct kvaser_usb *dev = priv->dev;
+	int err;
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_ATOMIC);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->header.cmd_no = cmd_no;
+
+	kvaser_usb_hydra_set_cmd_dest_he
+		(cmd, dev->card_data.hydra.channel_to_he[priv->channel]);
+	kvaser_usb_hydra_set_cmd_transid
+				(cmd, kvaser_usb_hydra_get_next_transid(dev));
+
+	err = kvaser_usb_send_cmd_async(priv, cmd,
+					kvaser_usb_hydra_cmd_size(cmd));
+	if (err)
+		kfree(cmd);
+
+	return err;
+}
+
+/* This function is used for synchronously waiting on hydra control commands.
+ * Note: Compared to kvaser_usb_hydra_read_bulk_callback(), we never need to
+ *       handle partial hydra commands. Since hydra control commands are always
+ *       non-extended commands.
+ */
+static int kvaser_usb_hydra_wait_cmd(const struct kvaser_usb *dev, u8 cmd_no,
+				     struct kvaser_cmd *cmd)
+{
+	void *buf;
+	int err;
+	unsigned long timeout = jiffies + msecs_to_jiffies(KVASER_USB_TIMEOUT);
+
+	if (cmd->header.cmd_no == CMD_EXTENDED) {
+		dev_err(&dev->intf->dev, "Wait for CMD_EXTENDED not allowed\n");
+		return -EINVAL;
+	}
+
+	buf = kzalloc(KVASER_USB_RX_BUFFER_SIZE, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	do {
+		int actual_len = 0;
+		int pos = 0;
+
+		err = kvaser_usb_recv_cmd(dev, buf, KVASER_USB_RX_BUFFER_SIZE,
+					  &actual_len);
+		if (err < 0)
+			goto end;
+
+		while (pos < actual_len) {
+			struct kvaser_cmd *tmp_cmd;
+			size_t cmd_len;
+
+			tmp_cmd = buf + pos;
+			cmd_len = kvaser_usb_hydra_cmd_size(tmp_cmd);
+			if (pos + cmd_len > actual_len) {
+				dev_err_ratelimited(&dev->intf->dev,
+						    "Format error\n");
+				break;
+			}
+
+			if (tmp_cmd->header.cmd_no == cmd_no) {
+				memcpy(cmd, tmp_cmd, cmd_len);
+				goto end;
+			}
+			pos += cmd_len;
+		}
+	} while (time_before(jiffies, timeout));
+
+	err = -EINVAL;
+
+end:
+	kfree(buf);
+
+	return err;
+}
+
+static int kvaser_usb_hydra_map_channel_resp(struct kvaser_usb *dev,
+					     const struct kvaser_cmd *cmd)
+{
+	u8 he, channel;
+	u16 transid = kvaser_usb_hydra_get_cmd_transid(cmd);
+	struct kvaser_usb_dev_card_data_hydra *card_data =
+							&dev->card_data.hydra;
+
+	if (transid > 0x007f || transid < 0x0040) {
+		dev_err(&dev->intf->dev,
+			"CMD_MAP_CHANNEL_RESP, invalid transid: 0x%x\n",
+			transid);
+		return -EINVAL;
+	}
+
+	switch (transid) {
+	case KVASER_USB_HYDRA_TRANSID_CANHE:
+	case KVASER_USB_HYDRA_TRANSID_CANHE + 1:
+	case KVASER_USB_HYDRA_TRANSID_CANHE + 2:
+	case KVASER_USB_HYDRA_TRANSID_CANHE + 3:
+	case KVASER_USB_HYDRA_TRANSID_CANHE + 4:
+		channel = transid & 0x000f;
+		he = cmd->map_ch_res.he_addr;
+		card_data->channel_to_he[channel] = he;
+		break;
+	case KVASER_USB_HYDRA_TRANSID_SYSDBG:
+		card_data->sysdbg_he = cmd->map_ch_res.he_addr;
+		break;
+	default:
+		dev_warn(&dev->intf->dev,
+			 "Unknown CMD_MAP_CHANNEL_RESP transid=0x%x\n",
+			 transid);
+		break;
+	}
+
+	return 0;
+}
+
+static int kvaser_usb_hydra_map_channel(struct kvaser_usb *dev, u16 transid,
+					u8 channel, const char *name)
+{
+	struct kvaser_cmd *cmd;
+	int err;
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	strcpy(cmd->map_ch_req.name, name);
+	cmd->header.cmd_no = CMD_MAP_CHANNEL_REQ;
+	kvaser_usb_hydra_set_cmd_dest_he
+				(cmd, KVASER_USB_HYDRA_HE_ADDRESS_ROUTER);
+	cmd->map_ch_req.channel = channel;
+
+	kvaser_usb_hydra_set_cmd_transid(cmd, transid);
+
+	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+	if (err)
+		goto end;
+
+	err = kvaser_usb_hydra_wait_cmd(dev, CMD_MAP_CHANNEL_RESP, cmd);
+	if (err)
+		goto end;
+
+	err = kvaser_usb_hydra_map_channel_resp(dev, cmd);
+	if (err)
+		goto end;
+
+end:
+	kfree(cmd);
+
+	return err;
+}
+
+static int kvaser_usb_hydra_get_single_capability(struct kvaser_usb *dev,
+						  u16 cap_cmd_req, u16 *status)
+{
+	struct kvaser_usb_dev_card_data *card_data = &dev->card_data;
+	struct kvaser_cmd *cmd;
+	u32 value = 0;
+	u32 mask = 0;
+	u16 cap_cmd_res;
+	int err;
+	int i;
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->header.cmd_no = CMD_GET_CAPABILITIES_REQ;
+	cmd->cap_req.cap_cmd = cpu_to_le16(cap_cmd_req);
+
+	kvaser_usb_hydra_set_cmd_dest_he(cmd, card_data->hydra.sysdbg_he);
+	kvaser_usb_hydra_set_cmd_transid
+				(cmd, kvaser_usb_hydra_get_next_transid(dev));
+
+	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+	if (err)
+		goto end;
+
+	err = kvaser_usb_hydra_wait_cmd(dev, CMD_GET_CAPABILITIES_RESP, cmd);
+	if (err)
+		goto end;
+
+	*status = le16_to_cpu(cmd->cap_res.status);
+
+	if (*status != KVASER_USB_HYDRA_CAP_STAT_OK)
+		goto end;
+
+	cap_cmd_res = le16_to_cpu(cmd->cap_res.cap_cmd);
+	switch (cap_cmd_res) {
+	case KVASER_USB_HYDRA_CAP_CMD_LISTEN_MODE:
+	case KVASER_USB_HYDRA_CAP_CMD_ERR_REPORT:
+	case KVASER_USB_HYDRA_CAP_CMD_ONE_SHOT:
+		value = le32_to_cpu(cmd->cap_res.value);
+		mask = le32_to_cpu(cmd->cap_res.mask);
+		break;
+	default:
+		dev_warn(&dev->intf->dev, "Unknown capability command %u\n",
+			 cap_cmd_res);
+		break;
+	}
+
+	for (i = 0; i < dev->nchannels; i++) {
+		if (BIT(i) & (value & mask)) {
+			switch (cap_cmd_res) {
+			case KVASER_USB_HYDRA_CAP_CMD_LISTEN_MODE:
+				card_data->ctrlmode_supported |=
+						CAN_CTRLMODE_LISTENONLY;
+				break;
+			case KVASER_USB_HYDRA_CAP_CMD_ERR_REPORT:
+				card_data->capabilities |=
+						KVASER_USB_CAP_BERR_CAP;
+				break;
+			case KVASER_USB_HYDRA_CAP_CMD_ONE_SHOT:
+				card_data->ctrlmode_supported |=
+						CAN_CTRLMODE_ONE_SHOT;
+				break;
+			}
+		}
+	}
+
+end:
+	kfree(cmd);
+
+	return err;
+}
+
+static void kvaser_usb_hydra_start_chip_reply(const struct kvaser_usb *dev,
+					      const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_net_priv *priv;
+
+	priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd);
+	if (!priv)
+		return;
+
+	if (completion_done(&priv->start_comp) &&
+	    netif_queue_stopped(priv->netdev)) {
+		netif_wake_queue(priv->netdev);
+	} else {
+		netif_start_queue(priv->netdev);
+		complete(&priv->start_comp);
+	}
+}
+
+static void kvaser_usb_hydra_stop_chip_reply(const struct kvaser_usb *dev,
+					     const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_net_priv *priv;
+
+	priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd);
+	if (!priv)
+		return;
+
+	complete(&priv->stop_comp);
+}
+
+static void kvaser_usb_hydra_flush_queue_reply(const struct kvaser_usb *dev,
+					       const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_net_priv *priv;
+
+	priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd);
+	if (!priv)
+		return;
+
+	complete(&priv->flush_comp);
+}
+
+static void
+kvaser_usb_hydra_bus_status_to_can_state(const struct kvaser_usb_net_priv *priv,
+					 u8 bus_status,
+					 const struct can_berr_counter *bec,
+					 enum can_state *new_state)
+{
+	if (bus_status & KVASER_USB_HYDRA_BUS_BUS_OFF) {
+		*new_state = CAN_STATE_BUS_OFF;
+	} else if (bus_status & KVASER_USB_HYDRA_BUS_ERR_PASS) {
+		*new_state = CAN_STATE_ERROR_PASSIVE;
+	} else if (bus_status == KVASER_USB_HYDRA_BUS_ERR_ACT) {
+		if (bec->txerr >= 128 || bec->rxerr >= 128) {
+			netdev_warn(priv->netdev,
+				    "ERR_ACTIVE but err tx=%u or rx=%u >=128\n",
+				    bec->txerr, bec->rxerr);
+			*new_state = CAN_STATE_ERROR_PASSIVE;
+		} else if (bec->txerr >= 96 || bec->rxerr >= 96) {
+			*new_state = CAN_STATE_ERROR_WARNING;
+		} else {
+			*new_state = CAN_STATE_ERROR_ACTIVE;
+		}
+	}
+}
+
+static void kvaser_usb_hydra_update_state(struct kvaser_usb_net_priv *priv,
+					  u8 bus_status,
+					  const struct can_berr_counter *bec)
+{
+	struct net_device *netdev = priv->netdev;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	struct net_device_stats *stats;
+	enum can_state new_state, old_state;
+
+	old_state = priv->can.state;
+
+	kvaser_usb_hydra_bus_status_to_can_state(priv, bus_status, bec,
+						 &new_state);
+
+	if (new_state == old_state)
+		return;
+
+	/* Ignore state change if previous state was STOPPED and the new state
+	 * is BUS_OFF. Firmware always report this as BUS_OFF, since firmware
+	 * does not distinguish between BUS_OFF and STOPPED.
+	 */
+	if (old_state == CAN_STATE_STOPPED && new_state == CAN_STATE_BUS_OFF)
+		return;
+
+	skb = alloc_can_err_skb(netdev, &cf);
+	if (skb) {
+		enum can_state tx_state, rx_state;
+
+		tx_state = (bec->txerr >= bec->rxerr) ?
+					new_state : CAN_STATE_ERROR_ACTIVE;
+		rx_state = (bec->txerr <= bec->rxerr) ?
+					new_state : CAN_STATE_ERROR_ACTIVE;
+		can_change_state(netdev, cf, tx_state, rx_state);
+	}
+
+	if (new_state == CAN_STATE_BUS_OFF && old_state < CAN_STATE_BUS_OFF) {
+		if (!priv->can.restart_ms)
+			kvaser_usb_hydra_send_simple_cmd_async
+						(priv, CMD_STOP_CHIP_REQ);
+
+		can_bus_off(netdev);
+	}
+
+	if (!skb) {
+		netdev_warn(netdev, "No memory left for err_skb\n");
+		return;
+	}
+
+	if (priv->can.restart_ms &&
+	    old_state >= CAN_STATE_BUS_OFF &&
+	    new_state < CAN_STATE_BUS_OFF)
+		priv->can.can_stats.restarts++;
+
+	cf->data[6] = bec->txerr;
+	cf->data[7] = bec->rxerr;
+
+	stats = &netdev->stats;
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
+}
+
+static void kvaser_usb_hydra_state_event(const struct kvaser_usb *dev,
+					 const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_net_priv *priv;
+	struct can_berr_counter bec;
+	u8 bus_status;
+
+	priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd);
+	if (!priv)
+		return;
+
+	bus_status = cmd->chip_state_event.bus_status;
+	bec.txerr = cmd->chip_state_event.tx_err_counter;
+	bec.rxerr = cmd->chip_state_event.rx_err_counter;
+
+	kvaser_usb_hydra_update_state(priv, bus_status, &bec);
+	priv->bec.txerr = bec.txerr;
+	priv->bec.rxerr = bec.rxerr;
+}
+
+static void kvaser_usb_hydra_error_event_parameter(const struct kvaser_usb *dev,
+						   const struct kvaser_cmd *cmd)
+{
+	/* info1 will contain the offending cmd_no */
+	switch (le16_to_cpu(cmd->error_event.info1)) {
+	case CMD_START_CHIP_REQ:
+		dev_warn(&dev->intf->dev,
+			 "CMD_START_CHIP_REQ error in parameter\n");
+		break;
+
+	case CMD_STOP_CHIP_REQ:
+		dev_warn(&dev->intf->dev,
+			 "CMD_STOP_CHIP_REQ error in parameter\n");
+		break;
+
+	case CMD_FLUSH_QUEUE:
+		dev_warn(&dev->intf->dev,
+			 "CMD_FLUSH_QUEUE error in parameter\n");
+		break;
+
+	case CMD_SET_BUSPARAMS_REQ:
+		dev_warn(&dev->intf->dev,
+			 "Set bittiming failed. Error in parameter\n");
+		break;
+
+	case CMD_SET_BUSPARAMS_FD_REQ:
+		dev_warn(&dev->intf->dev,
+			 "Set data bittiming failed. Error in parameter\n");
+		break;
+
+	default:
+		dev_warn(&dev->intf->dev,
+			 "Unhandled parameter error event cmd_no (%u)\n",
+			 le16_to_cpu(cmd->error_event.info1));
+		break;
+	}
+}
+
+static void kvaser_usb_hydra_error_event(const struct kvaser_usb *dev,
+					 const struct kvaser_cmd *cmd)
+{
+	switch (cmd->error_event.error_code) {
+	case KVASER_USB_HYDRA_ERROR_EVENT_PARAM:
+		kvaser_usb_hydra_error_event_parameter(dev, cmd);
+		break;
+
+	case KVASER_USB_HYDRA_ERROR_EVENT_CAN:
+		/* Wrong channel mapping?! This should never happen!
+		 * info1 will contain the offending cmd_no
+		 */
+		dev_err(&dev->intf->dev,
+			"Received CAN error event for cmd_no (%u)\n",
+			le16_to_cpu(cmd->error_event.info1));
+		break;
+
+	default:
+		dev_warn(&dev->intf->dev,
+			 "Unhandled error event (%d)\n",
+			 cmd->error_event.error_code);
+		break;
+	}
+}
+
+static void
+kvaser_usb_hydra_error_frame(struct kvaser_usb_net_priv *priv,
+			     const struct kvaser_err_frame_data *err_frame_data,
+			     ktime_t hwtstamp)
+{
+	struct net_device *netdev = priv->netdev;
+	struct net_device_stats *stats = &netdev->stats;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	struct skb_shared_hwtstamps *shhwtstamps;
+	struct can_berr_counter bec;
+	enum can_state new_state, old_state;
+	u8 bus_status;
+
+	priv->can.can_stats.bus_error++;
+	stats->rx_errors++;
+
+	bus_status = err_frame_data->bus_status;
+	bec.txerr = err_frame_data->tx_err_counter;
+	bec.rxerr = err_frame_data->rx_err_counter;
+
+	old_state = priv->can.state;
+	kvaser_usb_hydra_bus_status_to_can_state(priv, bus_status, &bec,
+						 &new_state);
+
+	skb = alloc_can_err_skb(netdev, &cf);
+
+	if (new_state != old_state) {
+		if (skb) {
+			enum can_state tx_state, rx_state;
+
+			tx_state = (bec.txerr >= bec.rxerr) ?
+					new_state : CAN_STATE_ERROR_ACTIVE;
+			rx_state = (bec.txerr <= bec.rxerr) ?
+					new_state : CAN_STATE_ERROR_ACTIVE;
+
+			can_change_state(netdev, cf, tx_state, rx_state);
+		}
+
+		if (new_state == CAN_STATE_BUS_OFF) {
+			if (!priv->can.restart_ms)
+				kvaser_usb_hydra_send_simple_cmd_async
+						(priv, CMD_STOP_CHIP_REQ);
+
+			can_bus_off(netdev);
+		}
+
+		if (priv->can.restart_ms &&
+		    old_state >= CAN_STATE_BUS_OFF &&
+		    new_state < CAN_STATE_BUS_OFF)
+			cf->can_id |= CAN_ERR_RESTARTED;
+	}
+
+	if (!skb) {
+		stats->rx_dropped++;
+		netdev_warn(netdev, "No memory left for err_skb\n");
+		return;
+	}
+
+	shhwtstamps = skb_hwtstamps(skb);
+	shhwtstamps->hwtstamp = hwtstamp;
+
+	cf->can_id |= CAN_ERR_BUSERROR;
+	cf->data[6] = bec.txerr;
+	cf->data[7] = bec.rxerr;
+
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
+
+	priv->bec.txerr = bec.txerr;
+	priv->bec.rxerr = bec.rxerr;
+}
+
+static void kvaser_usb_hydra_one_shot_fail(struct kvaser_usb_net_priv *priv,
+					   const struct kvaser_cmd_ext *cmd)
+{
+	struct net_device *netdev = priv->netdev;
+	struct net_device_stats *stats = &netdev->stats;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	u32 flags;
+
+	skb = alloc_can_err_skb(netdev, &cf);
+	if (!skb) {
+		stats->rx_dropped++;
+		netdev_warn(netdev, "No memory left for err_skb\n");
+		return;
+	}
+
+	cf->can_id |= CAN_ERR_BUSERROR;
+	flags = le32_to_cpu(cmd->tx_ack.flags);
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_OSM_NACK)
+		cf->can_id |= CAN_ERR_ACK;
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_ABL) {
+		cf->can_id |= CAN_ERR_LOSTARB;
+		priv->can.can_stats.arbitration_lost++;
+	}
+
+	stats->tx_errors++;
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
+}
+
+static void kvaser_usb_hydra_tx_acknowledge(const struct kvaser_usb *dev,
+					    const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_tx_urb_context *context;
+	struct kvaser_usb_net_priv *priv;
+	unsigned long irq_flags;
+	bool one_shot_fail = false;
+	u16 transid = kvaser_usb_hydra_get_cmd_transid(cmd);
+
+	priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd);
+	if (!priv)
+		return;
+
+	if (!netif_device_present(priv->netdev))
+		return;
+
+	if (cmd->header.cmd_no == CMD_EXTENDED) {
+		struct kvaser_cmd_ext *cmd_ext = (struct kvaser_cmd_ext *)cmd;
+		u32 flags = le32_to_cpu(cmd_ext->tx_ack.flags);
+
+		if (flags & (KVASER_USB_HYDRA_CF_FLAG_OSM_NACK |
+			     KVASER_USB_HYDRA_CF_FLAG_ABL)) {
+			kvaser_usb_hydra_one_shot_fail(priv, cmd_ext);
+			one_shot_fail = true;
+		}
+	}
+
+	context = &priv->tx_contexts[transid % dev->max_tx_urbs];
+	if (!one_shot_fail) {
+		struct net_device_stats *stats = &priv->netdev->stats;
+
+		stats->tx_packets++;
+		stats->tx_bytes += can_dlc2len(context->dlc);
+	}
+
+	spin_lock_irqsave(&priv->tx_contexts_lock, irq_flags);
+
+	can_get_echo_skb(priv->netdev, context->echo_index);
+	context->echo_index = dev->max_tx_urbs;
+	--priv->active_tx_contexts;
+	netif_wake_queue(priv->netdev);
+
+	spin_unlock_irqrestore(&priv->tx_contexts_lock, irq_flags);
+}
+
+static void kvaser_usb_hydra_rx_msg_std(const struct kvaser_usb *dev,
+					const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_net_priv *priv = NULL;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	struct skb_shared_hwtstamps *shhwtstamps;
+	struct net_device_stats *stats;
+	u8 flags;
+	ktime_t hwtstamp;
+
+	priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd);
+	if (!priv)
+		return;
+
+	stats = &priv->netdev->stats;
+
+	flags = cmd->rx_can.flags;
+	hwtstamp = kvaser_usb_hydra_ktime_from_rx_cmd(dev->cfg, cmd);
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME) {
+		kvaser_usb_hydra_error_frame(priv, &cmd->rx_can.err_frame_data,
+					     hwtstamp);
+		return;
+	}
+
+	skb = alloc_can_skb(priv->netdev, &cf);
+	if (!skb) {
+		stats->rx_dropped++;
+		return;
+	}
+
+	shhwtstamps = skb_hwtstamps(skb);
+	shhwtstamps->hwtstamp = hwtstamp;
+
+	cf->can_id = le32_to_cpu(cmd->rx_can.id);
+
+	if (cf->can_id &  KVASER_USB_HYDRA_EXTENDED_FRAME_ID) {
+		cf->can_id &= CAN_EFF_MASK;
+		cf->can_id |= CAN_EFF_FLAG;
+	} else {
+		cf->can_id &= CAN_SFF_MASK;
+	}
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_OVERRUN)
+		kvaser_usb_can_rx_over_error(priv->netdev);
+
+	cf->can_dlc = get_can_dlc(cmd->rx_can.dlc);
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME)
+		cf->can_id |= CAN_RTR_FLAG;
+	else
+		memcpy(cf->data, cmd->rx_can.data, cf->can_dlc);
+
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
+}
+
+static void kvaser_usb_hydra_rx_msg_ext(const struct kvaser_usb *dev,
+					const struct kvaser_cmd_ext *cmd)
+{
+	struct kvaser_cmd *std_cmd = (struct kvaser_cmd *)cmd;
+	struct kvaser_usb_net_priv *priv;
+	struct canfd_frame *cf;
+	struct sk_buff *skb;
+	struct skb_shared_hwtstamps *shhwtstamps;
+	struct net_device_stats *stats;
+	u32 flags;
+	u8 dlc;
+	u32 kcan_header;
+	ktime_t hwtstamp;
+
+	priv = kvaser_usb_hydra_net_priv_from_cmd(dev, std_cmd);
+	if (!priv)
+		return;
+
+	stats = &priv->netdev->stats;
+
+	kcan_header = le32_to_cpu(cmd->rx_can.kcan_header);
+	dlc = (kcan_header & KVASER_USB_KCAN_DATA_DLC_MASK) >>
+		KVASER_USB_KCAN_DATA_DLC_SHIFT;
+
+	flags = le32_to_cpu(cmd->rx_can.flags);
+	hwtstamp = kvaser_usb_hydra_ktime_from_rx_cmd(dev->cfg, std_cmd);
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME) {
+		kvaser_usb_hydra_error_frame(priv, &cmd->rx_can.err_frame_data,
+					     hwtstamp);
+		return;
+	}
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_FDF)
+		skb = alloc_canfd_skb(priv->netdev, &cf);
+	else
+		skb = alloc_can_skb(priv->netdev, (struct can_frame **)&cf);
+
+	if (!skb) {
+		stats->rx_dropped++;
+		return;
+	}
+
+	shhwtstamps = skb_hwtstamps(skb);
+	shhwtstamps->hwtstamp = hwtstamp;
+
+	cf->can_id = le32_to_cpu(cmd->rx_can.id);
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_EXTENDED_ID) {
+		cf->can_id &= CAN_EFF_MASK;
+		cf->can_id |= CAN_EFF_FLAG;
+	} else {
+		cf->can_id &= CAN_SFF_MASK;
+	}
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_OVERRUN)
+		kvaser_usb_can_rx_over_error(priv->netdev);
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_FDF) {
+		cf->len = can_dlc2len(get_canfd_dlc(dlc));
+		if (flags & KVASER_USB_HYDRA_CF_FLAG_BRS)
+			cf->flags |= CANFD_BRS;
+		if (flags & KVASER_USB_HYDRA_CF_FLAG_ESI)
+			cf->flags |= CANFD_ESI;
+	} else {
+		cf->len = get_can_dlc(dlc);
+	}
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME)
+		cf->can_id |= CAN_RTR_FLAG;
+	else
+		memcpy(cf->data, cmd->rx_can.kcan_payload, cf->len);
+
+	stats->rx_packets++;
+	stats->rx_bytes += cf->len;
+	netif_rx(skb);
+}
+
+static void kvaser_usb_hydra_handle_cmd_std(const struct kvaser_usb *dev,
+					    const struct kvaser_cmd *cmd)
+{
+	switch (cmd->header.cmd_no) {
+	case CMD_START_CHIP_RESP:
+		kvaser_usb_hydra_start_chip_reply(dev, cmd);
+		break;
+
+	case CMD_STOP_CHIP_RESP:
+		kvaser_usb_hydra_stop_chip_reply(dev, cmd);
+		break;
+
+	case CMD_FLUSH_QUEUE_RESP:
+		kvaser_usb_hydra_flush_queue_reply(dev, cmd);
+		break;
+
+	case CMD_CHIP_STATE_EVENT:
+		kvaser_usb_hydra_state_event(dev, cmd);
+		break;
+
+	case CMD_ERROR_EVENT:
+		kvaser_usb_hydra_error_event(dev, cmd);
+		break;
+
+	case CMD_TX_ACKNOWLEDGE:
+		kvaser_usb_hydra_tx_acknowledge(dev, cmd);
+		break;
+
+	case CMD_RX_MESSAGE:
+		kvaser_usb_hydra_rx_msg_std(dev, cmd);
+		break;
+
+	/* Ignored commands */
+	case CMD_SET_BUSPARAMS_RESP:
+	case CMD_SET_BUSPARAMS_FD_RESP:
+		break;
+
+	default:
+		dev_warn(&dev->intf->dev, "Unhandled command (%d)\n",
+			 cmd->header.cmd_no);
+		break;
+	}
+}
+
+static void kvaser_usb_hydra_handle_cmd_ext(const struct kvaser_usb *dev,
+					    const struct kvaser_cmd_ext *cmd)
+{
+	switch (cmd->cmd_no_ext) {
+	case CMD_TX_ACKNOWLEDGE_FD:
+		kvaser_usb_hydra_tx_acknowledge(dev, (struct kvaser_cmd *)cmd);
+		break;
+
+	case CMD_RX_MESSAGE_FD:
+		kvaser_usb_hydra_rx_msg_ext(dev, cmd);
+		break;
+
+	default:
+		dev_warn(&dev->intf->dev, "Unhandled extended command (%d)\n",
+			 cmd->header.cmd_no);
+		break;
+	}
+}
+
+static void kvaser_usb_hydra_handle_cmd(const struct kvaser_usb *dev,
+					const struct kvaser_cmd *cmd)
+{
+		if (cmd->header.cmd_no == CMD_EXTENDED)
+			kvaser_usb_hydra_handle_cmd_ext
+					(dev, (struct kvaser_cmd_ext *)cmd);
+		else
+			kvaser_usb_hydra_handle_cmd_std(dev, cmd);
+}
+
+static void *
+kvaser_usb_hydra_frame_to_cmd_ext(const struct kvaser_usb_net_priv *priv,
+				  const struct sk_buff *skb, int *frame_len,
+				  int *cmd_len, u16 transid)
+{
+	struct kvaser_usb *dev = priv->dev;
+	struct kvaser_cmd_ext *cmd;
+	struct canfd_frame *cf = (struct canfd_frame *)skb->data;
+	u8 dlc = can_len2dlc(cf->len);
+	u8 nbr_of_bytes = cf->len;
+	u32 flags;
+	u32 id;
+	u32 kcan_id;
+	u32 kcan_header;
+
+	*frame_len = nbr_of_bytes;
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd_ext), GFP_ATOMIC);
+	if (!cmd)
+		return NULL;
+
+	kvaser_usb_hydra_set_cmd_dest_he
+			((struct kvaser_cmd *)cmd,
+			 dev->card_data.hydra.channel_to_he[priv->channel]);
+	kvaser_usb_hydra_set_cmd_transid((struct kvaser_cmd *)cmd, transid);
+
+	cmd->header.cmd_no = CMD_EXTENDED;
+	cmd->cmd_no_ext = CMD_TX_CAN_MESSAGE_FD;
+
+	*cmd_len = ALIGN(sizeof(struct kvaser_cmd_ext) -
+			 sizeof(cmd->tx_can.kcan_payload) + nbr_of_bytes,
+			 8);
+
+	cmd->len = cpu_to_le16(*cmd_len);
+
+	cmd->tx_can.databytes = nbr_of_bytes;
+	cmd->tx_can.dlc = dlc;
+
+	if (cf->can_id & CAN_EFF_FLAG) {
+		id = cf->can_id & CAN_EFF_MASK;
+		flags = KVASER_USB_HYDRA_CF_FLAG_EXTENDED_ID;
+		kcan_id = (cf->can_id & CAN_EFF_MASK) |
+			  KVASER_USB_KCAN_DATA_IDE | KVASER_USB_KCAN_DATA_SRR;
+	} else {
+		id = cf->can_id & CAN_SFF_MASK;
+		flags = 0;
+		kcan_id = cf->can_id & CAN_SFF_MASK;
+	}
+
+	if (cf->can_id & CAN_ERR_FLAG)
+		flags |= KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME;
+
+	kcan_header = ((dlc << KVASER_USB_KCAN_DATA_DLC_SHIFT) &
+				KVASER_USB_KCAN_DATA_DLC_MASK) |
+			KVASER_USB_KCAN_DATA_AREQ |
+			(priv->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT ?
+				KVASER_USB_KCAN_DATA_OSM : 0);
+
+	if (can_is_canfd_skb(skb)) {
+		kcan_header |= KVASER_USB_KCAN_DATA_FDF |
+			       (cf->flags & CANFD_BRS ?
+					KVASER_USB_KCAN_DATA_BRS : 0);
+	} else {
+		if (cf->can_id & CAN_RTR_FLAG) {
+			kcan_id |= KVASER_USB_KCAN_DATA_RTR;
+			cmd->tx_can.databytes = 0;
+			flags |= KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME;
+		}
+	}
+
+	cmd->tx_can.kcan_id = cpu_to_le32(kcan_id);
+	cmd->tx_can.id = cpu_to_le32(id);
+	cmd->tx_can.flags = cpu_to_le32(flags);
+	cmd->tx_can.kcan_header = cpu_to_le32(kcan_header);
+
+	memcpy(cmd->tx_can.kcan_payload, cf->data, nbr_of_bytes);
+
+	return cmd;
+}
+
+static void *
+kvaser_usb_hydra_frame_to_cmd_std(const struct kvaser_usb_net_priv *priv,
+				  const struct sk_buff *skb, int *frame_len,
+				  int *cmd_len, u16 transid)
+{
+	struct kvaser_usb *dev = priv->dev;
+	struct kvaser_cmd *cmd;
+	struct can_frame *cf = (struct can_frame *)skb->data;
+	u32 flags;
+	u32 id;
+
+	*frame_len = cf->can_dlc;
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_ATOMIC);
+	if (!cmd)
+		return NULL;
+
+	kvaser_usb_hydra_set_cmd_dest_he
+		(cmd, dev->card_data.hydra.channel_to_he[priv->channel]);
+	kvaser_usb_hydra_set_cmd_transid(cmd, transid);
+
+	cmd->header.cmd_no = CMD_TX_CAN_MESSAGE;
+
+	*cmd_len = ALIGN(sizeof(struct kvaser_cmd), 8);
+
+	if (cf->can_id & CAN_EFF_FLAG) {
+		id = (cf->can_id & CAN_EFF_MASK);
+		id |= KVASER_USB_HYDRA_EXTENDED_FRAME_ID;
+	} else {
+		id = cf->can_id & CAN_SFF_MASK;
+	}
+
+	cmd->tx_can.dlc = cf->can_dlc;
+
+	flags = (cf->can_id & CAN_EFF_FLAG ?
+		 KVASER_USB_HYDRA_CF_FLAG_EXTENDED_ID : 0);
+
+	if (cf->can_id & CAN_RTR_FLAG)
+		flags |= KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME;
+
+	flags |= (cf->can_id & CAN_ERR_FLAG ?
+		  KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME : 0);
+
+	cmd->tx_can.id = cpu_to_le32(id);
+	cmd->tx_can.flags = flags;
+
+	memcpy(cmd->tx_can.data, cf->data, *frame_len);
+
+	return cmd;
+}
+
+static int kvaser_usb_hydra_set_mode(struct net_device *netdev,
+				     enum can_mode mode)
+{
+	int err = 0;
+
+	switch (mode) {
+	case CAN_MODE_START:
+		/* CAN controller automatically recovers from BUS_OFF */
+		break;
+	default:
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+static int kvaser_usb_hydra_set_bittiming(struct net_device *netdev)
+{
+	struct kvaser_cmd *cmd;
+	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
+	struct can_bittiming *bt = &priv->can.bittiming;
+	struct kvaser_usb *dev = priv->dev;
+	int tseg1 = bt->prop_seg + bt->phase_seg1;
+	int tseg2 = bt->phase_seg2;
+	int sjw = bt->sjw;
+	int err;
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->header.cmd_no = CMD_SET_BUSPARAMS_REQ;
+	cmd->set_busparams_req.bitrate = cpu_to_le32(bt->bitrate);
+	cmd->set_busparams_req.sjw = (u8)sjw;
+	cmd->set_busparams_req.tseg1 = (u8)tseg1;
+	cmd->set_busparams_req.tseg2 = (u8)tseg2;
+	cmd->set_busparams_req.nsamples = 1;
+
+	kvaser_usb_hydra_set_cmd_dest_he
+		(cmd, dev->card_data.hydra.channel_to_he[priv->channel]);
+	kvaser_usb_hydra_set_cmd_transid
+				(cmd, kvaser_usb_hydra_get_next_transid(dev));
+
+	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+
+	kfree(cmd);
+
+	return err;
+}
+
+static int kvaser_usb_hydra_set_data_bittiming(struct net_device *netdev)
+{
+	struct kvaser_cmd *cmd;
+	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
+	struct can_bittiming *dbt = &priv->can.data_bittiming;
+	struct kvaser_usb *dev = priv->dev;
+	int tseg1 = dbt->prop_seg + dbt->phase_seg1;
+	int tseg2 = dbt->phase_seg2;
+	int sjw = dbt->sjw;
+	int err;
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->header.cmd_no = CMD_SET_BUSPARAMS_FD_REQ;
+	cmd->set_busparams_req.bitrate_d = cpu_to_le32(dbt->bitrate);
+	cmd->set_busparams_req.sjw_d = (u8)sjw;
+	cmd->set_busparams_req.tseg1_d = (u8)tseg1;
+	cmd->set_busparams_req.tseg2_d = (u8)tseg2;
+	cmd->set_busparams_req.nsamples_d = 1;
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_FD) {
+		if (priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO)
+			cmd->set_busparams_req.canfd_mode =
+					KVASER_USB_HYDRA_BUS_MODE_NONISO;
+		else
+			cmd->set_busparams_req.canfd_mode =
+					KVASER_USB_HYDRA_BUS_MODE_CANFD_ISO;
+	}
+
+	kvaser_usb_hydra_set_cmd_dest_he
+		(cmd, dev->card_data.hydra.channel_to_he[priv->channel]);
+	kvaser_usb_hydra_set_cmd_transid
+				(cmd, kvaser_usb_hydra_get_next_transid(dev));
+
+	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+
+	kfree(cmd);
+
+	return err;
+}
+
+static int kvaser_usb_hydra_get_berr_counter(const struct net_device *netdev,
+					     struct can_berr_counter *bec)
+{
+	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
+	int err;
+
+	err = kvaser_usb_hydra_send_simple_cmd(priv->dev,
+					       CMD_GET_CHIP_STATE_REQ,
+					       priv->channel);
+	if (err)
+		return err;
+
+	*bec = priv->bec;
+
+	return 0;
+}
+
+static int kvaser_usb_hydra_setup_endpoints(struct kvaser_usb *dev)
+{
+	const struct usb_host_interface *iface_desc;
+	struct usb_endpoint_descriptor *ep;
+	int i;
+
+	iface_desc = &dev->intf->altsetting[0];
+
+	for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) {
+		ep = &iface_desc->endpoint[i].desc;
+
+		if (!dev->bulk_in && usb_endpoint_is_bulk_in(ep) &&
+		    ep->bEndpointAddress == KVASER_USB_HYDRA_BULK_EP_IN_ADDR)
+			dev->bulk_in = ep;
+
+		if (!dev->bulk_out && usb_endpoint_is_bulk_out(ep) &&
+		    ep->bEndpointAddress == KVASER_USB_HYDRA_BULK_EP_OUT_ADDR)
+			dev->bulk_out = ep;
+
+		if (dev->bulk_in && dev->bulk_out)
+			return 0;
+	}
+
+	return -ENODEV;
+}
+
+static int kvaser_usb_hydra_init_card(struct kvaser_usb *dev)
+{
+	int err;
+	unsigned int i;
+	struct kvaser_usb_dev_card_data_hydra *card_data =
+							&dev->card_data.hydra;
+
+	card_data->transid = KVASER_USB_HYDRA_MIN_TRANSID;
+	spin_lock_init(&card_data->transid_lock);
+
+	memset(card_data->usb_rx_leftover, 0, KVASER_USB_HYDRA_MAX_CMD_LEN);
+	card_data->usb_rx_leftover_len = 0;
+	spin_lock_init(&card_data->usb_rx_leftover_lock);
+
+	memset(card_data->channel_to_he, KVASER_USB_HYDRA_HE_ADDRESS_ILLEGAL,
+	       sizeof(card_data->channel_to_he));
+	card_data->sysdbg_he = 0;
+
+	for (i = 0; i < KVASER_USB_MAX_NET_DEVICES; i++) {
+		err = kvaser_usb_hydra_map_channel
+					(dev,
+					 (KVASER_USB_HYDRA_TRANSID_CANHE | i),
+					 i, "CAN");
+		if (err) {
+			dev_err(&dev->intf->dev,
+				"CMD_MAP_CHANNEL_REQ failed for CAN%u\n", i);
+			return err;
+		}
+	}
+
+	err = kvaser_usb_hydra_map_channel(dev, KVASER_USB_HYDRA_TRANSID_SYSDBG,
+					   0, "SYSDBG");
+	if (err) {
+		dev_err(&dev->intf->dev,
+			"CMD_MAP_CHANNEL_REQ failed for SYSDBG\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static int kvaser_usb_hydra_get_software_info(struct kvaser_usb *dev)
+{
+	struct kvaser_cmd cmd;
+	int err;
+
+	err = kvaser_usb_hydra_send_simple_cmd(dev, CMD_GET_SOFTWARE_INFO_REQ,
+					       -1);
+	if (err)
+		return err;
+
+	memset(&cmd, 0, sizeof(struct kvaser_cmd));
+	err = kvaser_usb_hydra_wait_cmd(dev, CMD_GET_SOFTWARE_INFO_RESP, &cmd);
+	if (err)
+		return err;
+
+	dev->max_tx_urbs = min_t(unsigned int, KVASER_USB_MAX_TX_URBS,
+				 le16_to_cpu(cmd.sw_info.max_outstanding_tx));
+
+	return 0;
+}
+
+static int kvaser_usb_hydra_get_software_details(struct kvaser_usb *dev)
+{
+	struct kvaser_cmd *cmd;
+	int err;
+	u32 flags;
+	struct kvaser_usb_dev_card_data *card_data = &dev->card_data;
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->header.cmd_no = CMD_GET_SOFTWARE_DETAILS_REQ;
+	cmd->sw_detail_req.use_ext_cmd = 1;
+	kvaser_usb_hydra_set_cmd_dest_he
+				(cmd, KVASER_USB_HYDRA_HE_ADDRESS_ILLEGAL);
+
+	kvaser_usb_hydra_set_cmd_transid
+				(cmd, kvaser_usb_hydra_get_next_transid(dev));
+
+	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+	if (err)
+		goto end;
+
+	err = kvaser_usb_hydra_wait_cmd(dev, CMD_GET_SOFTWARE_DETAILS_RESP,
+					cmd);
+	if (err)
+		goto end;
+
+	dev->fw_version = le32_to_cpu(cmd->sw_detail_res.sw_version);
+	flags = le32_to_cpu(cmd->sw_detail_res.sw_flags);
+
+	if (flags & KVASER_USB_HYDRA_SW_FLAG_FW_BAD) {
+		dev_err(&dev->intf->dev,
+			"Bad firmware, device refuse to run!\n");
+		err = -EINVAL;
+		goto end;
+	}
+
+	if (flags & KVASER_USB_HYDRA_SW_FLAG_FW_BETA)
+		dev_info(&dev->intf->dev, "Beta firmware in use\n");
+
+	if (flags & KVASER_USB_HYDRA_SW_FLAG_EXT_CAP)
+		card_data->capabilities |= KVASER_USB_CAP_EXT_CAP;
+
+	if (flags & KVASER_USB_HYDRA_SW_FLAG_EXT_CMD)
+		card_data->capabilities |= KVASER_USB_HYDRA_CAP_EXT_CMD;
+
+	if (flags & KVASER_USB_HYDRA_SW_FLAG_CANFD)
+		card_data->ctrlmode_supported |= CAN_CTRLMODE_FD;
+
+	if (flags & KVASER_USB_HYDRA_SW_FLAG_NONISO)
+		card_data->ctrlmode_supported |= CAN_CTRLMODE_FD_NON_ISO;
+
+	if (flags &  KVASER_USB_HYDRA_SW_FLAG_FREQ_80M)
+		dev->cfg = &kvaser_usb_hydra_dev_cfg_kcan;
+	else
+		dev->cfg = &kvaser_usb_hydra_dev_cfg_flexc;
+
+end:
+	kfree(cmd);
+
+	return err;
+}
+
+static int kvaser_usb_hydra_get_card_info(struct kvaser_usb *dev)
+{
+	struct kvaser_cmd cmd;
+	int err;
+
+	err = kvaser_usb_hydra_send_simple_cmd(dev, CMD_GET_CARD_INFO_REQ, -1);
+	if (err)
+		return err;
+
+	memset(&cmd, 0, sizeof(struct kvaser_cmd));
+	err = kvaser_usb_hydra_wait_cmd(dev, CMD_GET_CARD_INFO_RESP, &cmd);
+	if (err)
+		return err;
+
+	dev->nchannels = cmd.card_info.nchannels;
+	if (dev->nchannels > KVASER_USB_MAX_NET_DEVICES)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int kvaser_usb_hydra_get_capabilities(struct kvaser_usb *dev)
+{
+	int err;
+	u16 status;
+
+	if (!(dev->card_data.capabilities & KVASER_USB_CAP_EXT_CAP)) {
+		dev_info(&dev->intf->dev,
+			 "No extended capability support. Upgrade your device.\n");
+		return 0;
+	}
+
+	err = kvaser_usb_hydra_get_single_capability
+					(dev,
+					 KVASER_USB_HYDRA_CAP_CMD_LISTEN_MODE,
+					 &status);
+	if (err)
+		return err;
+	if (status)
+		dev_info(&dev->intf->dev,
+			 "KVASER_USB_HYDRA_CAP_CMD_LISTEN_MODE failed %u\n",
+			 status);
+
+	err = kvaser_usb_hydra_get_single_capability
+					(dev,
+					 KVASER_USB_HYDRA_CAP_CMD_ERR_REPORT,
+					 &status);
+	if (err)
+		return err;
+	if (status)
+		dev_info(&dev->intf->dev,
+			 "KVASER_USB_HYDRA_CAP_CMD_ERR_REPORT failed %u\n",
+			 status);
+
+	err = kvaser_usb_hydra_get_single_capability
+					(dev, KVASER_USB_HYDRA_CAP_CMD_ONE_SHOT,
+					 &status);
+	if (err)
+		return err;
+	if (status)
+		dev_info(&dev->intf->dev,
+			 "KVASER_USB_HYDRA_CAP_CMD_ONE_SHOT failed %u\n",
+			 status);
+
+	return 0;
+}
+
+static int kvaser_usb_hydra_set_opt_mode(const struct kvaser_usb_net_priv *priv)
+{
+	struct kvaser_usb *dev = priv->dev;
+	struct kvaser_cmd *cmd;
+	int err;
+
+	if ((priv->can.ctrlmode &
+	    (CAN_CTRLMODE_FD | CAN_CTRLMODE_FD_NON_ISO)) ==
+	    CAN_CTRLMODE_FD_NON_ISO) {
+		netdev_warn(priv->netdev,
+			    "CTRLMODE_FD shall be on if CTRLMODE_FD_NON_ISO is on\n");
+		return -EINVAL;
+	}
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->header.cmd_no = CMD_SET_DRIVERMODE_REQ;
+	kvaser_usb_hydra_set_cmd_dest_he
+		(cmd, dev->card_data.hydra.channel_to_he[priv->channel]);
+	kvaser_usb_hydra_set_cmd_transid
+				(cmd, kvaser_usb_hydra_get_next_transid(dev));
+	if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
+		cmd->set_ctrlmode.mode = KVASER_USB_HYDRA_CTRLMODE_LISTEN;
+	else
+		cmd->set_ctrlmode.mode = KVASER_USB_HYDRA_CTRLMODE_NORMAL;
+
+	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+	kfree(cmd);
+
+	return err;
+}
+
+static int kvaser_usb_hydra_start_chip(struct kvaser_usb_net_priv *priv)
+{
+	int err;
+
+	init_completion(&priv->start_comp);
+
+	err = kvaser_usb_hydra_send_simple_cmd(priv->dev, CMD_START_CHIP_REQ,
+					       priv->channel);
+	if (err)
+		return err;
+
+	if (!wait_for_completion_timeout(&priv->start_comp,
+					 msecs_to_jiffies(KVASER_USB_TIMEOUT)))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int kvaser_usb_hydra_stop_chip(struct kvaser_usb_net_priv *priv)
+{
+	int err;
+
+	init_completion(&priv->stop_comp);
+
+	/* Make sure we do not report invalid BUS_OFF from CMD_CHIP_STATE_EVENT
+	 * see comment in kvaser_usb_hydra_update_state()
+	 */
+	priv->can.state = CAN_STATE_STOPPED;
+
+	err = kvaser_usb_hydra_send_simple_cmd(priv->dev, CMD_STOP_CHIP_REQ,
+					       priv->channel);
+	if (err)
+		return err;
+
+	if (!wait_for_completion_timeout(&priv->stop_comp,
+					 msecs_to_jiffies(KVASER_USB_TIMEOUT)))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int kvaser_usb_hydra_flush_queue(struct kvaser_usb_net_priv *priv)
+{
+	int err;
+
+	init_completion(&priv->flush_comp);
+
+	err = kvaser_usb_hydra_send_simple_cmd(priv->dev, CMD_FLUSH_QUEUE,
+					       priv->channel);
+	if (err)
+		return err;
+
+	if (!wait_for_completion_timeout(&priv->flush_comp,
+					 msecs_to_jiffies(KVASER_USB_TIMEOUT)))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+/* A single extended hydra command can be transmitted in multiple transfers
+ * We have to buffer partial hydra commands, and handle them on next callback.
+ */
+static void kvaser_usb_hydra_read_bulk_callback(struct kvaser_usb *dev,
+						void *buf, int len)
+{
+	unsigned long irq_flags;
+	struct kvaser_cmd *cmd;
+	int pos = 0;
+	size_t cmd_len;
+	struct kvaser_usb_dev_card_data_hydra *card_data =
+							&dev->card_data.hydra;
+	int usb_rx_leftover_len;
+	spinlock_t *usb_rx_leftover_lock = &card_data->usb_rx_leftover_lock;
+
+	spin_lock_irqsave(usb_rx_leftover_lock, irq_flags);
+	usb_rx_leftover_len = card_data->usb_rx_leftover_len;
+	if (usb_rx_leftover_len) {
+		int remaining_bytes;
+
+		cmd = (struct kvaser_cmd *)card_data->usb_rx_leftover;
+
+		cmd_len = kvaser_usb_hydra_cmd_size(cmd);
+
+		remaining_bytes = min_t(unsigned int, len,
+					cmd_len - usb_rx_leftover_len);
+		/* Make sure we do not overflow usb_rx_leftover */
+		if (remaining_bytes + usb_rx_leftover_len >
+						KVASER_USB_HYDRA_MAX_CMD_LEN) {
+			dev_err(&dev->intf->dev, "Format error\n");
+			spin_unlock_irqrestore(usb_rx_leftover_lock, irq_flags);
+			return;
+		}
+
+		memcpy(card_data->usb_rx_leftover + usb_rx_leftover_len, buf,
+		       remaining_bytes);
+		pos += remaining_bytes;
+
+		if (remaining_bytes + usb_rx_leftover_len == cmd_len) {
+			kvaser_usb_hydra_handle_cmd(dev, cmd);
+			usb_rx_leftover_len = 0;
+		} else {
+			/* Command still not complete */
+			usb_rx_leftover_len += remaining_bytes;
+		}
+		card_data->usb_rx_leftover_len = usb_rx_leftover_len;
+	}
+	spin_unlock_irqrestore(usb_rx_leftover_lock, irq_flags);
+
+	while (pos < len) {
+		cmd = buf + pos;
+
+		cmd_len = kvaser_usb_hydra_cmd_size(cmd);
+
+		if (pos + cmd_len > len) {
+			/* We got first part of a command */
+			int leftover_bytes;
+
+			leftover_bytes = len - pos;
+			/* Make sure we do not overflow usb_rx_leftover */
+			if (leftover_bytes > KVASER_USB_HYDRA_MAX_CMD_LEN) {
+				dev_err(&dev->intf->dev, "Format error\n");
+				return;
+			}
+			spin_lock_irqsave(usb_rx_leftover_lock, irq_flags);
+			memcpy(card_data->usb_rx_leftover, buf + pos,
+			       leftover_bytes);
+			card_data->usb_rx_leftover_len = leftover_bytes;
+			spin_unlock_irqrestore(usb_rx_leftover_lock, irq_flags);
+			break;
+		}
+
+		kvaser_usb_hydra_handle_cmd(dev, cmd);
+		pos += cmd_len;
+	}
+}
+
+static void *
+kvaser_usb_hydra_frame_to_cmd(const struct kvaser_usb_net_priv *priv,
+			      const struct sk_buff *skb, int *frame_len,
+			      int *cmd_len, u16 transid)
+{
+	void *buf;
+
+	if (priv->dev->card_data.capabilities & KVASER_USB_HYDRA_CAP_EXT_CMD)
+		buf = kvaser_usb_hydra_frame_to_cmd_ext(priv, skb, frame_len,
+							cmd_len, transid);
+	else
+		buf = kvaser_usb_hydra_frame_to_cmd_std(priv, skb, frame_len,
+							cmd_len, transid);
+
+	return buf;
+}
+
+const struct kvaser_usb_dev_ops kvaser_usb_hydra_dev_ops = {
+	.dev_set_mode = kvaser_usb_hydra_set_mode,
+	.dev_set_bittiming = kvaser_usb_hydra_set_bittiming,
+	.dev_set_data_bittiming = kvaser_usb_hydra_set_data_bittiming,
+	.dev_get_berr_counter = kvaser_usb_hydra_get_berr_counter,
+	.dev_setup_endpoints = kvaser_usb_hydra_setup_endpoints,
+	.dev_init_card = kvaser_usb_hydra_init_card,
+	.dev_get_software_info = kvaser_usb_hydra_get_software_info,
+	.dev_get_software_details = kvaser_usb_hydra_get_software_details,
+	.dev_get_card_info = kvaser_usb_hydra_get_card_info,
+	.dev_get_capabilities = kvaser_usb_hydra_get_capabilities,
+	.dev_set_opt_mode = kvaser_usb_hydra_set_opt_mode,
+	.dev_start_chip = kvaser_usb_hydra_start_chip,
+	.dev_stop_chip = kvaser_usb_hydra_stop_chip,
+	.dev_reset_chip = NULL,
+	.dev_flush_queue = kvaser_usb_hydra_flush_queue,
+	.dev_read_bulk_callback = kvaser_usb_hydra_read_bulk_callback,
+	.dev_frame_to_cmd = kvaser_usb_hydra_frame_to_cmd,
+};
+
+static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_kcan = {
+	.clock = {
+		.freq = 80000000,
+	},
+	.timestamp_freq = 80,
+	.bittiming_const = &kvaser_usb_hydra_kcan_bittiming_c,
+	.data_bittiming_const = &kvaser_usb_hydra_kcan_bittiming_c,
+};
+
+static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_flexc = {
+	.clock = {
+		.freq = 24000000,
+	},
+	.timestamp_freq = 1,
+	.bittiming_const = &kvaser_usb_hydra_flexc_bittiming_c,
+};
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
new file mode 100644
index 000000000000..07d2f3aa2c02
--- /dev/null
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -0,0 +1,1358 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Parts of this driver are based on the following:
+ *  - Kvaser linux leaf driver (version 4.78)
+ *  - CAN driver for esd CAN-USB/2
+ *  - Kvaser linux usbcanII driver (version 5.3)
+ *
+ * Copyright (C) 2002-2018 KVASER AB, Sweden. All rights reserved.
+ * Copyright (C) 2010 Matthias Fuchs <matthias.fuchs@esd.eu>, esd gmbh
+ * Copyright (C) 2012 Olivier Sobrie <olivier@sobrie.be>
+ * Copyright (C) 2015 Valeo S.A.
+ */
+
+#include <linux/completion.h>
+#include <linux/device.h>
+#include <linux/gfp.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/usb.h>
+
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/error.h>
+#include <linux/can/netlink.h>
+
+#include "kvaser_usb.h"
+
+/* Forward declaration */
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg;
+
+#define CAN_USB_CLOCK			8000000
+#define MAX_USBCAN_NET_DEVICES		2
+
+/* Command header size */
+#define CMD_HEADER_LEN			2
+
+/* Kvaser CAN message flags */
+#define MSG_FLAG_ERROR_FRAME		BIT(0)
+#define MSG_FLAG_OVERRUN		BIT(1)
+#define MSG_FLAG_NERR			BIT(2)
+#define MSG_FLAG_WAKEUP			BIT(3)
+#define MSG_FLAG_REMOTE_FRAME		BIT(4)
+#define MSG_FLAG_RESERVED		BIT(5)
+#define MSG_FLAG_TX_ACK			BIT(6)
+#define MSG_FLAG_TX_REQUEST		BIT(7)
+
+/* CAN states (M16C CxSTRH register) */
+#define M16C_STATE_BUS_RESET		BIT(0)
+#define M16C_STATE_BUS_ERROR		BIT(4)
+#define M16C_STATE_BUS_PASSIVE		BIT(5)
+#define M16C_STATE_BUS_OFF		BIT(6)
+
+/* Leaf/usbcan command ids */
+#define CMD_RX_STD_MESSAGE		12
+#define CMD_TX_STD_MESSAGE		13
+#define CMD_RX_EXT_MESSAGE		14
+#define CMD_TX_EXT_MESSAGE		15
+#define CMD_SET_BUS_PARAMS		16
+#define CMD_CHIP_STATE_EVENT		20
+#define CMD_SET_CTRL_MODE		21
+#define CMD_RESET_CHIP			24
+#define CMD_START_CHIP			26
+#define CMD_START_CHIP_REPLY		27
+#define CMD_STOP_CHIP			28
+#define CMD_STOP_CHIP_REPLY		29
+
+#define CMD_USBCAN_CLOCK_OVERFLOW_EVENT	33
+
+#define CMD_GET_CARD_INFO		34
+#define CMD_GET_CARD_INFO_REPLY		35
+#define CMD_GET_SOFTWARE_INFO		38
+#define CMD_GET_SOFTWARE_INFO_REPLY	39
+#define CMD_FLUSH_QUEUE			48
+#define CMD_TX_ACKNOWLEDGE		50
+#define CMD_CAN_ERROR_EVENT		51
+#define CMD_FLUSH_QUEUE_REPLY		68
+
+#define CMD_LEAF_LOG_MESSAGE		106
+
+/* error factors */
+#define M16C_EF_ACKE			BIT(0)
+#define M16C_EF_CRCE			BIT(1)
+#define M16C_EF_FORME			BIT(2)
+#define M16C_EF_STFE			BIT(3)
+#define M16C_EF_BITE0			BIT(4)
+#define M16C_EF_BITE1			BIT(5)
+#define M16C_EF_RCVE			BIT(6)
+#define M16C_EF_TRE			BIT(7)
+
+/* Only Leaf-based devices can report M16C error factors,
+ * thus define our own error status flags for USBCANII
+ */
+#define USBCAN_ERROR_STATE_NONE		0
+#define USBCAN_ERROR_STATE_TX_ERROR	BIT(0)
+#define USBCAN_ERROR_STATE_RX_ERROR	BIT(1)
+#define USBCAN_ERROR_STATE_BUSERROR	BIT(2)
+
+/* bittiming parameters */
+#define KVASER_USB_TSEG1_MIN		1
+#define KVASER_USB_TSEG1_MAX		16
+#define KVASER_USB_TSEG2_MIN		1
+#define KVASER_USB_TSEG2_MAX		8
+#define KVASER_USB_SJW_MAX		4
+#define KVASER_USB_BRP_MIN		1
+#define KVASER_USB_BRP_MAX		64
+#define KVASER_USB_BRP_INC		1
+
+/* ctrl modes */
+#define KVASER_CTRL_MODE_NORMAL		1
+#define KVASER_CTRL_MODE_SILENT		2
+#define KVASER_CTRL_MODE_SELFRECEPTION	3
+#define KVASER_CTRL_MODE_OFF		4
+
+/* Extended CAN identifier flag */
+#define KVASER_EXTENDED_FRAME		BIT(31)
+
+struct kvaser_cmd_simple {
+	u8 tid;
+	u8 channel;
+} __packed;
+
+struct kvaser_cmd_cardinfo {
+	u8 tid;
+	u8 nchannels;
+	__le32 serial_number;
+	__le32 padding0;
+	__le32 clock_resolution;
+	__le32 mfgdate;
+	u8 ean[8];
+	u8 hw_revision;
+	union {
+		struct {
+			u8 usb_hs_mode;
+		} __packed leaf1;
+		struct {
+			u8 padding;
+		} __packed usbcan1;
+	} __packed;
+	__le16 padding1;
+} __packed;
+
+struct leaf_cmd_softinfo {
+	u8 tid;
+	u8 padding0;
+	__le32 sw_options;
+	__le32 fw_version;
+	__le16 max_outstanding_tx;
+	__le16 padding1[9];
+} __packed;
+
+struct usbcan_cmd_softinfo {
+	u8 tid;
+	u8 fw_name[5];
+	__le16 max_outstanding_tx;
+	u8 padding[6];
+	__le32 fw_version;
+	__le16 checksum;
+	__le16 sw_options;
+} __packed;
+
+struct kvaser_cmd_busparams {
+	u8 tid;
+	u8 channel;
+	__le32 bitrate;
+	u8 tseg1;
+	u8 tseg2;
+	u8 sjw;
+	u8 no_samp;
+} __packed;
+
+struct kvaser_cmd_tx_can {
+	u8 channel;
+	u8 tid;
+	u8 data[14];
+	union {
+		struct {
+			u8 padding;
+			u8 flags;
+		} __packed leaf;
+		struct {
+			u8 flags;
+			u8 padding;
+		} __packed usbcan;
+	} __packed;
+} __packed;
+
+struct kvaser_cmd_rx_can_header {
+	u8 channel;
+	u8 flag;
+} __packed;
+
+struct leaf_cmd_rx_can {
+	u8 channel;
+	u8 flag;
+
+	__le16 time[3];
+	u8 data[14];
+} __packed;
+
+struct usbcan_cmd_rx_can {
+	u8 channel;
+	u8 flag;
+
+	u8 data[14];
+	__le16 time;
+} __packed;
+
+struct leaf_cmd_chip_state_event {
+	u8 tid;
+	u8 channel;
+
+	__le16 time[3];
+	u8 tx_errors_count;
+	u8 rx_errors_count;
+
+	u8 status;
+	u8 padding[3];
+} __packed;
+
+struct usbcan_cmd_chip_state_event {
+	u8 tid;
+	u8 channel;
+
+	u8 tx_errors_count;
+	u8 rx_errors_count;
+	__le16 time;
+
+	u8 status;
+	u8 padding[3];
+} __packed;
+
+struct kvaser_cmd_tx_acknowledge_header {
+	u8 channel;
+	u8 tid;
+} __packed;
+
+struct leaf_cmd_error_event {
+	u8 tid;
+	u8 flags;
+	__le16 time[3];
+	u8 channel;
+	u8 padding;
+	u8 tx_errors_count;
+	u8 rx_errors_count;
+	u8 status;
+	u8 error_factor;
+} __packed;
+
+struct usbcan_cmd_error_event {
+	u8 tid;
+	u8 padding;
+	u8 tx_errors_count_ch0;
+	u8 rx_errors_count_ch0;
+	u8 tx_errors_count_ch1;
+	u8 rx_errors_count_ch1;
+	u8 status_ch0;
+	u8 status_ch1;
+	__le16 time;
+} __packed;
+
+struct kvaser_cmd_ctrl_mode {
+	u8 tid;
+	u8 channel;
+	u8 ctrl_mode;
+	u8 padding[3];
+} __packed;
+
+struct kvaser_cmd_flush_queue {
+	u8 tid;
+	u8 channel;
+	u8 flags;
+	u8 padding[3];
+} __packed;
+
+struct leaf_cmd_log_message {
+	u8 channel;
+	u8 flags;
+	__le16 time[3];
+	u8 dlc;
+	u8 time_offset;
+	__le32 id;
+	u8 data[8];
+} __packed;
+
+struct kvaser_cmd {
+	u8 len;
+	u8 id;
+	union	{
+		struct kvaser_cmd_simple simple;
+		struct kvaser_cmd_cardinfo cardinfo;
+		struct kvaser_cmd_busparams busparams;
+
+		struct kvaser_cmd_rx_can_header rx_can_header;
+		struct kvaser_cmd_tx_acknowledge_header tx_acknowledge_header;
+
+		union {
+			struct leaf_cmd_softinfo softinfo;
+			struct leaf_cmd_rx_can rx_can;
+			struct leaf_cmd_chip_state_event chip_state_event;
+			struct leaf_cmd_error_event error_event;
+			struct leaf_cmd_log_message log_message;
+		} __packed leaf;
+
+		union {
+			struct usbcan_cmd_softinfo softinfo;
+			struct usbcan_cmd_rx_can rx_can;
+			struct usbcan_cmd_chip_state_event chip_state_event;
+			struct usbcan_cmd_error_event error_event;
+		} __packed usbcan;
+
+		struct kvaser_cmd_tx_can tx_can;
+		struct kvaser_cmd_ctrl_mode ctrl_mode;
+		struct kvaser_cmd_flush_queue flush_queue;
+	} u;
+} __packed;
+
+/* Summary of a kvaser error event, for a unified Leaf/Usbcan error
+ * handling. Some discrepancies between the two families exist:
+ *
+ * - USBCAN firmware does not report M16C "error factors"
+ * - USBCAN controllers has difficulties reporting if the raised error
+ *   event is for ch0 or ch1. They leave such arbitration to the OS
+ *   driver by letting it compare error counters with previous values
+ *   and decide the error event's channel. Thus for USBCAN, the channel
+ *   field is only advisory.
+ */
+struct kvaser_usb_err_summary {
+	u8 channel, status, txerr, rxerr;
+	union {
+		struct {
+			u8 error_factor;
+		} leaf;
+		struct {
+			u8 other_ch_status;
+			u8 error_state;
+		} usbcan;
+	};
+};
+
+static void *
+kvaser_usb_leaf_frame_to_cmd(const struct kvaser_usb_net_priv *priv,
+			     const struct sk_buff *skb, int *frame_len,
+			     int *cmd_len, u16 transid)
+{
+	struct kvaser_usb *dev = priv->dev;
+	struct kvaser_cmd *cmd;
+	u8 *cmd_tx_can_flags = NULL;		/* GCC */
+	struct can_frame *cf = (struct can_frame *)skb->data;
+
+	*frame_len = cf->can_dlc;
+
+	cmd = kmalloc(sizeof(*cmd), GFP_ATOMIC);
+	if (cmd) {
+		cmd->u.tx_can.tid = transid & 0xff;
+		cmd->len = *cmd_len = CMD_HEADER_LEN +
+				      sizeof(struct kvaser_cmd_tx_can);
+		cmd->u.tx_can.channel = priv->channel;
+
+		switch (dev->card_data.leaf.family) {
+		case KVASER_LEAF:
+			cmd_tx_can_flags = &cmd->u.tx_can.leaf.flags;
+			break;
+		case KVASER_USBCAN:
+			cmd_tx_can_flags = &cmd->u.tx_can.usbcan.flags;
+			break;
+		}
+
+		*cmd_tx_can_flags = 0;
+
+		if (cf->can_id & CAN_EFF_FLAG) {
+			cmd->id = CMD_TX_EXT_MESSAGE;
+			cmd->u.tx_can.data[0] = (cf->can_id >> 24) & 0x1f;
+			cmd->u.tx_can.data[1] = (cf->can_id >> 18) & 0x3f;
+			cmd->u.tx_can.data[2] = (cf->can_id >> 14) & 0x0f;
+			cmd->u.tx_can.data[3] = (cf->can_id >> 6) & 0xff;
+			cmd->u.tx_can.data[4] = cf->can_id & 0x3f;
+		} else {
+			cmd->id = CMD_TX_STD_MESSAGE;
+			cmd->u.tx_can.data[0] = (cf->can_id >> 6) & 0x1f;
+			cmd->u.tx_can.data[1] = cf->can_id & 0x3f;
+		}
+
+		cmd->u.tx_can.data[5] = cf->can_dlc;
+		memcpy(&cmd->u.tx_can.data[6], cf->data, cf->can_dlc);
+
+		if (cf->can_id & CAN_RTR_FLAG)
+			*cmd_tx_can_flags |= MSG_FLAG_REMOTE_FRAME;
+	}
+	return cmd;
+}
+
+static int kvaser_usb_leaf_wait_cmd(const struct kvaser_usb *dev, u8 id,
+				    struct kvaser_cmd *cmd)
+{
+	struct kvaser_cmd *tmp;
+	void *buf;
+	int actual_len;
+	int err;
+	int pos;
+	unsigned long to = jiffies + msecs_to_jiffies(KVASER_USB_TIMEOUT);
+
+	buf = kzalloc(KVASER_USB_RX_BUFFER_SIZE, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	do {
+		err = kvaser_usb_recv_cmd(dev, buf, KVASER_USB_RX_BUFFER_SIZE,
+					  &actual_len);
+		if (err < 0)
+			goto end;
+
+		pos = 0;
+		while (pos <= actual_len - CMD_HEADER_LEN) {
+			tmp = buf + pos;
+
+			/* Handle commands crossing the USB endpoint max packet
+			 * size boundary. Check kvaser_usb_read_bulk_callback()
+			 * for further details.
+			 */
+			if (tmp->len == 0) {
+				pos = round_up(pos,
+					       le16_to_cpu
+						(dev->bulk_in->wMaxPacketSize));
+				continue;
+			}
+
+			if (pos + tmp->len > actual_len) {
+				dev_err_ratelimited(&dev->intf->dev,
+						    "Format error\n");
+				break;
+			}
+
+			if (tmp->id == id) {
+				memcpy(cmd, tmp, tmp->len);
+				goto end;
+			}
+
+			pos += tmp->len;
+		}
+	} while (time_before(jiffies, to));
+
+	err = -EINVAL;
+
+end:
+	kfree(buf);
+
+	return err;
+}
+
+static int kvaser_usb_leaf_send_simple_cmd(const struct kvaser_usb *dev,
+					   u8 cmd_id, int channel)
+{
+	struct kvaser_cmd *cmd;
+	int rc;
+
+	cmd = kmalloc(sizeof(*cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->id = cmd_id;
+	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_simple);
+	cmd->u.simple.channel = channel;
+	cmd->u.simple.tid = 0xff;
+
+	rc = kvaser_usb_send_cmd(dev, cmd, cmd->len);
+
+	kfree(cmd);
+	return rc;
+}
+
+static int kvaser_usb_leaf_get_software_info_inner(struct kvaser_usb *dev)
+{
+	struct kvaser_cmd cmd;
+	int err;
+
+	err = kvaser_usb_leaf_send_simple_cmd(dev, CMD_GET_SOFTWARE_INFO, 0);
+	if (err)
+		return err;
+
+	err = kvaser_usb_leaf_wait_cmd(dev, CMD_GET_SOFTWARE_INFO_REPLY, &cmd);
+	if (err)
+		return err;
+
+	switch (dev->card_data.leaf.family) {
+	case KVASER_LEAF:
+		dev->fw_version = le32_to_cpu(cmd.u.leaf.softinfo.fw_version);
+		dev->max_tx_urbs =
+			le16_to_cpu(cmd.u.leaf.softinfo.max_outstanding_tx);
+		break;
+	case KVASER_USBCAN:
+		dev->fw_version = le32_to_cpu(cmd.u.usbcan.softinfo.fw_version);
+		dev->max_tx_urbs =
+			le16_to_cpu(cmd.u.usbcan.softinfo.max_outstanding_tx);
+		break;
+	}
+
+	return 0;
+}
+
+static int kvaser_usb_leaf_get_software_info(struct kvaser_usb *dev)
+{
+	int err;
+	int retry = 3;
+
+	/* On some x86 laptops, plugging a Kvaser device again after
+	 * an unplug makes the firmware always ignore the very first
+	 * command. For such a case, provide some room for retries
+	 * instead of completely exiting the driver.
+	 */
+	do {
+		err = kvaser_usb_leaf_get_software_info_inner(dev);
+	} while (--retry && err == -ETIMEDOUT);
+
+	return err;
+}
+
+static int kvaser_usb_leaf_get_card_info(struct kvaser_usb *dev)
+{
+	struct kvaser_cmd cmd;
+	int err;
+
+	err = kvaser_usb_leaf_send_simple_cmd(dev, CMD_GET_CARD_INFO, 0);
+	if (err)
+		return err;
+
+	err = kvaser_usb_leaf_wait_cmd(dev, CMD_GET_CARD_INFO_REPLY, &cmd);
+	if (err)
+		return err;
+
+	dev->nchannels = cmd.u.cardinfo.nchannels;
+	if (dev->nchannels > KVASER_USB_MAX_NET_DEVICES ||
+	    (dev->card_data.leaf.family == KVASER_USBCAN &&
+	     dev->nchannels > MAX_USBCAN_NET_DEVICES))
+		return -EINVAL;
+
+	return 0;
+}
+
+static void kvaser_usb_leaf_tx_acknowledge(const struct kvaser_usb *dev,
+					   const struct kvaser_cmd *cmd)
+{
+	struct net_device_stats *stats;
+	struct kvaser_usb_tx_urb_context *context;
+	struct kvaser_usb_net_priv *priv;
+	unsigned long flags;
+	u8 channel, tid;
+
+	channel = cmd->u.tx_acknowledge_header.channel;
+	tid = cmd->u.tx_acknowledge_header.tid;
+
+	if (channel >= dev->nchannels) {
+		dev_err(&dev->intf->dev,
+			"Invalid channel number (%d)\n", channel);
+		return;
+	}
+
+	priv = dev->nets[channel];
+
+	if (!netif_device_present(priv->netdev))
+		return;
+
+	stats = &priv->netdev->stats;
+
+	context = &priv->tx_contexts[tid % dev->max_tx_urbs];
+
+	/* Sometimes the state change doesn't come after a bus-off event */
+	if (priv->can.restart_ms && priv->can.state >= CAN_STATE_BUS_OFF) {
+		struct sk_buff *skb;
+		struct can_frame *cf;
+
+		skb = alloc_can_err_skb(priv->netdev, &cf);
+		if (skb) {
+			cf->can_id |= CAN_ERR_RESTARTED;
+
+			stats->rx_packets++;
+			stats->rx_bytes += cf->can_dlc;
+			netif_rx(skb);
+		} else {
+			netdev_err(priv->netdev,
+				   "No memory left for err_skb\n");
+		}
+
+		priv->can.can_stats.restarts++;
+		netif_carrier_on(priv->netdev);
+
+		priv->can.state = CAN_STATE_ERROR_ACTIVE;
+	}
+
+	stats->tx_packets++;
+	stats->tx_bytes += context->dlc;
+
+	spin_lock_irqsave(&priv->tx_contexts_lock, flags);
+
+	can_get_echo_skb(priv->netdev, context->echo_index);
+	context->echo_index = dev->max_tx_urbs;
+	--priv->active_tx_contexts;
+	netif_wake_queue(priv->netdev);
+
+	spin_unlock_irqrestore(&priv->tx_contexts_lock, flags);
+}
+
+static int kvaser_usb_leaf_simple_cmd_async(struct kvaser_usb_net_priv *priv,
+					    u8 cmd_id)
+{
+	struct kvaser_cmd *cmd;
+	int err;
+
+	cmd = kmalloc(sizeof(*cmd), GFP_ATOMIC);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_simple);
+	cmd->id = cmd_id;
+	cmd->u.simple.channel = priv->channel;
+
+	err = kvaser_usb_send_cmd_async(priv, cmd, cmd->len);
+	if (err)
+		kfree(cmd);
+
+	return err;
+}
+
+static void
+kvaser_usb_leaf_rx_error_update_can_state(struct kvaser_usb_net_priv *priv,
+					const struct kvaser_usb_err_summary *es,
+					struct can_frame *cf)
+{
+	struct kvaser_usb *dev = priv->dev;
+	struct net_device_stats *stats = &priv->netdev->stats;
+	enum can_state cur_state, new_state, tx_state, rx_state;
+
+	netdev_dbg(priv->netdev, "Error status: 0x%02x\n", es->status);
+
+	new_state = priv->can.state;
+	cur_state = priv->can.state;
+
+	if (es->status & (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) {
+		new_state = CAN_STATE_BUS_OFF;
+	} else if (es->status & M16C_STATE_BUS_PASSIVE) {
+		new_state = CAN_STATE_ERROR_PASSIVE;
+	} else if (es->status & M16C_STATE_BUS_ERROR) {
+		/* Guard against spurious error events after a busoff */
+		if (cur_state < CAN_STATE_BUS_OFF) {
+			if (es->txerr >= 128 || es->rxerr >= 128)
+				new_state = CAN_STATE_ERROR_PASSIVE;
+			else if (es->txerr >= 96 || es->rxerr >= 96)
+				new_state = CAN_STATE_ERROR_WARNING;
+			else if (cur_state > CAN_STATE_ERROR_ACTIVE)
+				new_state = CAN_STATE_ERROR_ACTIVE;
+		}
+	}
+
+	if (!es->status)
+		new_state = CAN_STATE_ERROR_ACTIVE;
+
+	if (new_state != cur_state) {
+		tx_state = (es->txerr >= es->rxerr) ? new_state : 0;
+		rx_state = (es->txerr <= es->rxerr) ? new_state : 0;
+
+		can_change_state(priv->netdev, cf, tx_state, rx_state);
+	}
+
+	if (priv->can.restart_ms &&
+	    cur_state >= CAN_STATE_BUS_OFF &&
+	    new_state < CAN_STATE_BUS_OFF)
+		priv->can.can_stats.restarts++;
+
+	switch (dev->card_data.leaf.family) {
+	case KVASER_LEAF:
+		if (es->leaf.error_factor) {
+			priv->can.can_stats.bus_error++;
+			stats->rx_errors++;
+		}
+		break;
+	case KVASER_USBCAN:
+		if (es->usbcan.error_state & USBCAN_ERROR_STATE_TX_ERROR)
+			stats->tx_errors++;
+		if (es->usbcan.error_state & USBCAN_ERROR_STATE_RX_ERROR)
+			stats->rx_errors++;
+		if (es->usbcan.error_state & USBCAN_ERROR_STATE_BUSERROR)
+			priv->can.can_stats.bus_error++;
+		break;
+	}
+
+	priv->bec.txerr = es->txerr;
+	priv->bec.rxerr = es->rxerr;
+}
+
+static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev,
+				     const struct kvaser_usb_err_summary *es)
+{
+	struct can_frame *cf;
+	struct can_frame tmp_cf = { .can_id = CAN_ERR_FLAG,
+				    .can_dlc = CAN_ERR_DLC };
+	struct sk_buff *skb;
+	struct net_device_stats *stats;
+	struct kvaser_usb_net_priv *priv;
+	enum can_state old_state, new_state;
+
+	if (es->channel >= dev->nchannels) {
+		dev_err(&dev->intf->dev,
+			"Invalid channel number (%d)\n", es->channel);
+		return;
+	}
+
+	priv = dev->nets[es->channel];
+	stats = &priv->netdev->stats;
+
+	/* Update all of the CAN interface's state and error counters before
+	 * trying any memory allocation that can actually fail with -ENOMEM.
+	 *
+	 * We send a temporary stack-allocated error CAN frame to
+	 * can_change_state() for the very same reason.
+	 *
+	 * TODO: Split can_change_state() responsibility between updating the
+	 * CAN interface's state and counters, and the setting up of CAN error
+	 * frame ID and data to userspace. Remove stack allocation afterwards.
+	 */
+	old_state = priv->can.state;
+	kvaser_usb_leaf_rx_error_update_can_state(priv, es, &tmp_cf);
+	new_state = priv->can.state;
+
+	skb = alloc_can_err_skb(priv->netdev, &cf);
+	if (!skb) {
+		stats->rx_dropped++;
+		return;
+	}
+	memcpy(cf, &tmp_cf, sizeof(*cf));
+
+	if (new_state != old_state) {
+		if (es->status &
+		    (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) {
+			if (!priv->can.restart_ms)
+				kvaser_usb_leaf_simple_cmd_async(priv,
+								 CMD_STOP_CHIP);
+			netif_carrier_off(priv->netdev);
+		}
+
+		if (priv->can.restart_ms &&
+		    old_state >= CAN_STATE_BUS_OFF &&
+		    new_state < CAN_STATE_BUS_OFF) {
+			cf->can_id |= CAN_ERR_RESTARTED;
+			netif_carrier_on(priv->netdev);
+		}
+	}
+
+	switch (dev->card_data.leaf.family) {
+	case KVASER_LEAF:
+		if (es->leaf.error_factor) {
+			cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT;
+
+			if (es->leaf.error_factor & M16C_EF_ACKE)
+				cf->data[3] = CAN_ERR_PROT_LOC_ACK;
+			if (es->leaf.error_factor & M16C_EF_CRCE)
+				cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
+			if (es->leaf.error_factor & M16C_EF_FORME)
+				cf->data[2] |= CAN_ERR_PROT_FORM;
+			if (es->leaf.error_factor & M16C_EF_STFE)
+				cf->data[2] |= CAN_ERR_PROT_STUFF;
+			if (es->leaf.error_factor & M16C_EF_BITE0)
+				cf->data[2] |= CAN_ERR_PROT_BIT0;
+			if (es->leaf.error_factor & M16C_EF_BITE1)
+				cf->data[2] |= CAN_ERR_PROT_BIT1;
+			if (es->leaf.error_factor & M16C_EF_TRE)
+				cf->data[2] |= CAN_ERR_PROT_TX;
+		}
+		break;
+	case KVASER_USBCAN:
+		if (es->usbcan.error_state & USBCAN_ERROR_STATE_BUSERROR)
+			cf->can_id |= CAN_ERR_BUSERROR;
+		break;
+	}
+
+	cf->data[6] = es->txerr;
+	cf->data[7] = es->rxerr;
+
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
+}
+
+/* For USBCAN, report error to userspace if the channels's errors counter
+ * has changed, or we're the only channel seeing a bus error state.
+ */
+static void
+kvaser_usb_leaf_usbcan_conditionally_rx_error(const struct kvaser_usb *dev,
+					      struct kvaser_usb_err_summary *es)
+{
+	struct kvaser_usb_net_priv *priv;
+	unsigned int channel;
+	bool report_error;
+
+	channel = es->channel;
+	if (channel >= dev->nchannels) {
+		dev_err(&dev->intf->dev,
+			"Invalid channel number (%d)\n", channel);
+		return;
+	}
+
+	priv = dev->nets[channel];
+	report_error = false;
+
+	if (es->txerr != priv->bec.txerr) {
+		es->usbcan.error_state |= USBCAN_ERROR_STATE_TX_ERROR;
+		report_error = true;
+	}
+	if (es->rxerr != priv->bec.rxerr) {
+		es->usbcan.error_state |= USBCAN_ERROR_STATE_RX_ERROR;
+		report_error = true;
+	}
+	if ((es->status & M16C_STATE_BUS_ERROR) &&
+	    !(es->usbcan.other_ch_status & M16C_STATE_BUS_ERROR)) {
+		es->usbcan.error_state |= USBCAN_ERROR_STATE_BUSERROR;
+		report_error = true;
+	}
+
+	if (report_error)
+		kvaser_usb_leaf_rx_error(dev, es);
+}
+
+static void kvaser_usb_leaf_usbcan_rx_error(const struct kvaser_usb *dev,
+					    const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_err_summary es = { };
+
+	switch (cmd->id) {
+	/* Sometimes errors are sent as unsolicited chip state events */
+	case CMD_CHIP_STATE_EVENT:
+		es.channel = cmd->u.usbcan.chip_state_event.channel;
+		es.status = cmd->u.usbcan.chip_state_event.status;
+		es.txerr = cmd->u.usbcan.chip_state_event.tx_errors_count;
+		es.rxerr = cmd->u.usbcan.chip_state_event.rx_errors_count;
+		kvaser_usb_leaf_usbcan_conditionally_rx_error(dev, &es);
+		break;
+
+	case CMD_CAN_ERROR_EVENT:
+		es.channel = 0;
+		es.status = cmd->u.usbcan.error_event.status_ch0;
+		es.txerr = cmd->u.usbcan.error_event.tx_errors_count_ch0;
+		es.rxerr = cmd->u.usbcan.error_event.rx_errors_count_ch0;
+		es.usbcan.other_ch_status =
+			cmd->u.usbcan.error_event.status_ch1;
+		kvaser_usb_leaf_usbcan_conditionally_rx_error(dev, &es);
+
+		/* The USBCAN firmware supports up to 2 channels.
+		 * Now that ch0 was checked, check if ch1 has any errors.
+		 */
+		if (dev->nchannels == MAX_USBCAN_NET_DEVICES) {
+			es.channel = 1;
+			es.status = cmd->u.usbcan.error_event.status_ch1;
+			es.txerr =
+				cmd->u.usbcan.error_event.tx_errors_count_ch1;
+			es.rxerr =
+				cmd->u.usbcan.error_event.rx_errors_count_ch1;
+			es.usbcan.other_ch_status =
+				cmd->u.usbcan.error_event.status_ch0;
+			kvaser_usb_leaf_usbcan_conditionally_rx_error(dev, &es);
+		}
+		break;
+
+	default:
+		dev_err(&dev->intf->dev, "Invalid cmd id (%d)\n", cmd->id);
+	}
+}
+
+static void kvaser_usb_leaf_leaf_rx_error(const struct kvaser_usb *dev,
+					  const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_err_summary es = { };
+
+	switch (cmd->id) {
+	case CMD_CAN_ERROR_EVENT:
+		es.channel = cmd->u.leaf.error_event.channel;
+		es.status = cmd->u.leaf.error_event.status;
+		es.txerr = cmd->u.leaf.error_event.tx_errors_count;
+		es.rxerr = cmd->u.leaf.error_event.rx_errors_count;
+		es.leaf.error_factor = cmd->u.leaf.error_event.error_factor;
+		break;
+	case CMD_LEAF_LOG_MESSAGE:
+		es.channel = cmd->u.leaf.log_message.channel;
+		es.status = cmd->u.leaf.log_message.data[0];
+		es.txerr = cmd->u.leaf.log_message.data[2];
+		es.rxerr = cmd->u.leaf.log_message.data[3];
+		es.leaf.error_factor = cmd->u.leaf.log_message.data[1];
+		break;
+	case CMD_CHIP_STATE_EVENT:
+		es.channel = cmd->u.leaf.chip_state_event.channel;
+		es.status = cmd->u.leaf.chip_state_event.status;
+		es.txerr = cmd->u.leaf.chip_state_event.tx_errors_count;
+		es.rxerr = cmd->u.leaf.chip_state_event.rx_errors_count;
+		es.leaf.error_factor = 0;
+		break;
+	default:
+		dev_err(&dev->intf->dev, "Invalid cmd id (%d)\n", cmd->id);
+		return;
+	}
+
+	kvaser_usb_leaf_rx_error(dev, &es);
+}
+
+static void kvaser_usb_leaf_rx_can_err(const struct kvaser_usb_net_priv *priv,
+				       const struct kvaser_cmd *cmd)
+{
+	if (cmd->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME |
+					 MSG_FLAG_NERR)) {
+		struct net_device_stats *stats = &priv->netdev->stats;
+
+		netdev_err(priv->netdev, "Unknown error (flags: 0x%02x)\n",
+			   cmd->u.rx_can_header.flag);
+
+		stats->rx_errors++;
+		return;
+	}
+
+	if (cmd->u.rx_can_header.flag & MSG_FLAG_OVERRUN)
+		kvaser_usb_can_rx_over_error(priv->netdev);
+}
+
+static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev,
+				       const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_net_priv *priv;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	struct net_device_stats *stats;
+	u8 channel = cmd->u.rx_can_header.channel;
+	const u8 *rx_data = NULL;	/* GCC */
+
+	if (channel >= dev->nchannels) {
+		dev_err(&dev->intf->dev,
+			"Invalid channel number (%d)\n", channel);
+		return;
+	}
+
+	priv = dev->nets[channel];
+	stats = &priv->netdev->stats;
+
+	if ((cmd->u.rx_can_header.flag & MSG_FLAG_ERROR_FRAME) &&
+	    (dev->card_data.leaf.family == KVASER_LEAF &&
+	     cmd->id == CMD_LEAF_LOG_MESSAGE)) {
+		kvaser_usb_leaf_leaf_rx_error(dev, cmd);
+		return;
+	} else if (cmd->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME |
+						MSG_FLAG_NERR |
+						MSG_FLAG_OVERRUN)) {
+		kvaser_usb_leaf_rx_can_err(priv, cmd);
+		return;
+	} else if (cmd->u.rx_can_header.flag & ~MSG_FLAG_REMOTE_FRAME) {
+		netdev_warn(priv->netdev,
+			    "Unhandled frame (flags: 0x%02x)\n",
+			    cmd->u.rx_can_header.flag);
+		return;
+	}
+
+	switch (dev->card_data.leaf.family) {
+	case KVASER_LEAF:
+		rx_data = cmd->u.leaf.rx_can.data;
+		break;
+	case KVASER_USBCAN:
+		rx_data = cmd->u.usbcan.rx_can.data;
+		break;
+	}
+
+	skb = alloc_can_skb(priv->netdev, &cf);
+	if (!skb) {
+		stats->rx_dropped++;
+		return;
+	}
+
+	if (dev->card_data.leaf.family == KVASER_LEAF && cmd->id ==
+	    CMD_LEAF_LOG_MESSAGE) {
+		cf->can_id = le32_to_cpu(cmd->u.leaf.log_message.id);
+		if (cf->can_id & KVASER_EXTENDED_FRAME)
+			cf->can_id &= CAN_EFF_MASK | CAN_EFF_FLAG;
+		else
+			cf->can_id &= CAN_SFF_MASK;
+
+		cf->can_dlc = get_can_dlc(cmd->u.leaf.log_message.dlc);
+
+		if (cmd->u.leaf.log_message.flags & MSG_FLAG_REMOTE_FRAME)
+			cf->can_id |= CAN_RTR_FLAG;
+		else
+			memcpy(cf->data, &cmd->u.leaf.log_message.data,
+			       cf->can_dlc);
+	} else {
+		cf->can_id = ((rx_data[0] & 0x1f) << 6) | (rx_data[1] & 0x3f);
+
+		if (cmd->id == CMD_RX_EXT_MESSAGE) {
+			cf->can_id <<= 18;
+			cf->can_id |= ((rx_data[2] & 0x0f) << 14) |
+				      ((rx_data[3] & 0xff) << 6) |
+				      (rx_data[4] & 0x3f);
+			cf->can_id |= CAN_EFF_FLAG;
+		}
+
+		cf->can_dlc = get_can_dlc(rx_data[5]);
+
+		if (cmd->u.rx_can_header.flag & MSG_FLAG_REMOTE_FRAME)
+			cf->can_id |= CAN_RTR_FLAG;
+		else
+			memcpy(cf->data, &rx_data[6], cf->can_dlc);
+	}
+
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
+}
+
+static void kvaser_usb_leaf_start_chip_reply(const struct kvaser_usb *dev,
+					     const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_net_priv *priv;
+	u8 channel = cmd->u.simple.channel;
+
+	if (channel >= dev->nchannels) {
+		dev_err(&dev->intf->dev,
+			"Invalid channel number (%d)\n", channel);
+		return;
+	}
+
+	priv = dev->nets[channel];
+
+	if (completion_done(&priv->start_comp) &&
+	    netif_queue_stopped(priv->netdev)) {
+		netif_wake_queue(priv->netdev);
+	} else {
+		netif_start_queue(priv->netdev);
+		complete(&priv->start_comp);
+	}
+}
+
+static void kvaser_usb_leaf_stop_chip_reply(const struct kvaser_usb *dev,
+					    const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_net_priv *priv;
+	u8 channel = cmd->u.simple.channel;
+
+	if (channel >= dev->nchannels) {
+		dev_err(&dev->intf->dev,
+			"Invalid channel number (%d)\n", channel);
+		return;
+	}
+
+	priv = dev->nets[channel];
+
+	complete(&priv->stop_comp);
+}
+
+static void kvaser_usb_leaf_handle_command(const struct kvaser_usb *dev,
+					   const struct kvaser_cmd *cmd)
+{
+	switch (cmd->id) {
+	case CMD_START_CHIP_REPLY:
+		kvaser_usb_leaf_start_chip_reply(dev, cmd);
+		break;
+
+	case CMD_STOP_CHIP_REPLY:
+		kvaser_usb_leaf_stop_chip_reply(dev, cmd);
+		break;
+
+	case CMD_RX_STD_MESSAGE:
+	case CMD_RX_EXT_MESSAGE:
+		kvaser_usb_leaf_rx_can_msg(dev, cmd);
+		break;
+
+	case CMD_LEAF_LOG_MESSAGE:
+		if (dev->card_data.leaf.family != KVASER_LEAF)
+			goto warn;
+		kvaser_usb_leaf_rx_can_msg(dev, cmd);
+		break;
+
+	case CMD_CHIP_STATE_EVENT:
+	case CMD_CAN_ERROR_EVENT:
+		if (dev->card_data.leaf.family == KVASER_LEAF)
+			kvaser_usb_leaf_leaf_rx_error(dev, cmd);
+		else
+			kvaser_usb_leaf_usbcan_rx_error(dev, cmd);
+		break;
+
+	case CMD_TX_ACKNOWLEDGE:
+		kvaser_usb_leaf_tx_acknowledge(dev, cmd);
+		break;
+
+	/* Ignored commands */
+	case CMD_USBCAN_CLOCK_OVERFLOW_EVENT:
+		if (dev->card_data.leaf.family != KVASER_USBCAN)
+			goto warn;
+		break;
+
+	case CMD_FLUSH_QUEUE_REPLY:
+		if (dev->card_data.leaf.family != KVASER_LEAF)
+			goto warn;
+		break;
+
+	default:
+warn:		dev_warn(&dev->intf->dev, "Unhandled command (%d)\n", cmd->id);
+		break;
+	}
+}
+
+static void kvaser_usb_leaf_read_bulk_callback(struct kvaser_usb *dev,
+					       void *buf, int len)
+{
+	struct kvaser_cmd *cmd;
+	int pos = 0;
+
+	while (pos <= len - CMD_HEADER_LEN) {
+		cmd = buf + pos;
+
+		/* The Kvaser firmware can only read and write commands that
+		 * does not cross the USB's endpoint wMaxPacketSize boundary.
+		 * If a follow-up command crosses such boundary, firmware puts
+		 * a placeholder zero-length command in its place then aligns
+		 * the real command to the next max packet size.
+		 *
+		 * Handle such cases or we're going to miss a significant
+		 * number of events in case of a heavy rx load on the bus.
+		 */
+		if (cmd->len == 0) {
+			pos = round_up(pos, le16_to_cpu
+						(dev->bulk_in->wMaxPacketSize));
+			continue;
+		}
+
+		if (pos + cmd->len > len) {
+			dev_err_ratelimited(&dev->intf->dev, "Format error\n");
+			break;
+		}
+
+		kvaser_usb_leaf_handle_command(dev, cmd);
+		pos += cmd->len;
+	}
+}
+
+static int kvaser_usb_leaf_set_opt_mode(const struct kvaser_usb_net_priv *priv)
+{
+	struct kvaser_cmd *cmd;
+	int rc;
+
+	cmd = kmalloc(sizeof(*cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->id = CMD_SET_CTRL_MODE;
+	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_ctrl_mode);
+	cmd->u.ctrl_mode.tid = 0xff;
+	cmd->u.ctrl_mode.channel = priv->channel;
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
+		cmd->u.ctrl_mode.ctrl_mode = KVASER_CTRL_MODE_SILENT;
+	else
+		cmd->u.ctrl_mode.ctrl_mode = KVASER_CTRL_MODE_NORMAL;
+
+	rc = kvaser_usb_send_cmd(priv->dev, cmd, cmd->len);
+
+	kfree(cmd);
+	return rc;
+}
+
+static int kvaser_usb_leaf_start_chip(struct kvaser_usb_net_priv *priv)
+{
+	int err;
+
+	init_completion(&priv->start_comp);
+
+	err = kvaser_usb_leaf_send_simple_cmd(priv->dev, CMD_START_CHIP,
+					      priv->channel);
+	if (err)
+		return err;
+
+	if (!wait_for_completion_timeout(&priv->start_comp,
+					 msecs_to_jiffies(KVASER_USB_TIMEOUT)))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int kvaser_usb_leaf_stop_chip(struct kvaser_usb_net_priv *priv)
+{
+	int err;
+
+	init_completion(&priv->stop_comp);
+
+	err = kvaser_usb_leaf_send_simple_cmd(priv->dev, CMD_STOP_CHIP,
+					      priv->channel);
+	if (err)
+		return err;
+
+	if (!wait_for_completion_timeout(&priv->stop_comp,
+					 msecs_to_jiffies(KVASER_USB_TIMEOUT)))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int kvaser_usb_leaf_reset_chip(struct kvaser_usb *dev, int channel)
+{
+	return kvaser_usb_leaf_send_simple_cmd(dev, CMD_RESET_CHIP, channel);
+}
+
+static int kvaser_usb_leaf_flush_queue(struct kvaser_usb_net_priv *priv)
+{
+	struct kvaser_cmd *cmd;
+	int rc;
+
+	cmd = kmalloc(sizeof(*cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->id = CMD_FLUSH_QUEUE;
+	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_flush_queue);
+	cmd->u.flush_queue.channel = priv->channel;
+	cmd->u.flush_queue.flags = 0x00;
+
+	rc = kvaser_usb_send_cmd(priv->dev, cmd, cmd->len);
+
+	kfree(cmd);
+	return rc;
+}
+
+static int kvaser_usb_leaf_init_card(struct kvaser_usb *dev)
+{
+	struct kvaser_usb_dev_card_data *card_data = &dev->card_data;
+
+	dev->cfg = &kvaser_usb_leaf_dev_cfg;
+	card_data->ctrlmode_supported |= CAN_CTRLMODE_3_SAMPLES;
+
+	return 0;
+}
+
+static const struct can_bittiming_const kvaser_usb_leaf_bittiming_const = {
+	.name = "kvaser_usb",
+	.tseg1_min = KVASER_USB_TSEG1_MIN,
+	.tseg1_max = KVASER_USB_TSEG1_MAX,
+	.tseg2_min = KVASER_USB_TSEG2_MIN,
+	.tseg2_max = KVASER_USB_TSEG2_MAX,
+	.sjw_max = KVASER_USB_SJW_MAX,
+	.brp_min = KVASER_USB_BRP_MIN,
+	.brp_max = KVASER_USB_BRP_MAX,
+	.brp_inc = KVASER_USB_BRP_INC,
+};
+
+static int kvaser_usb_leaf_set_bittiming(struct net_device *netdev)
+{
+	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
+	struct can_bittiming *bt = &priv->can.bittiming;
+	struct kvaser_usb *dev = priv->dev;
+	struct kvaser_cmd *cmd;
+	int rc;
+
+	cmd = kmalloc(sizeof(*cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->id = CMD_SET_BUS_PARAMS;
+	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_busparams);
+	cmd->u.busparams.channel = priv->channel;
+	cmd->u.busparams.tid = 0xff;
+	cmd->u.busparams.bitrate = cpu_to_le32(bt->bitrate);
+	cmd->u.busparams.sjw = bt->sjw;
+	cmd->u.busparams.tseg1 = bt->prop_seg + bt->phase_seg1;
+	cmd->u.busparams.tseg2 = bt->phase_seg2;
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES)
+		cmd->u.busparams.no_samp = 3;
+	else
+		cmd->u.busparams.no_samp = 1;
+
+	rc = kvaser_usb_send_cmd(dev, cmd, cmd->len);
+
+	kfree(cmd);
+	return rc;
+}
+
+static int kvaser_usb_leaf_set_mode(struct net_device *netdev,
+				    enum can_mode mode)
+{
+	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
+	int err;
+
+	switch (mode) {
+	case CAN_MODE_START:
+		err = kvaser_usb_leaf_simple_cmd_async(priv, CMD_START_CHIP);
+		if (err)
+			return err;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int kvaser_usb_leaf_get_berr_counter(const struct net_device *netdev,
+					    struct can_berr_counter *bec)
+{
+	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
+
+	*bec = priv->bec;
+
+	return 0;
+}
+
+static int kvaser_usb_leaf_setup_endpoints(struct kvaser_usb *dev)
+{
+	const struct usb_host_interface *iface_desc;
+	struct usb_endpoint_descriptor *endpoint;
+	int i;
+
+	iface_desc = &dev->intf->altsetting[0];
+
+	for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) {
+		endpoint = &iface_desc->endpoint[i].desc;
+
+		if (!dev->bulk_in && usb_endpoint_is_bulk_in(endpoint))
+			dev->bulk_in = endpoint;
+
+		if (!dev->bulk_out && usb_endpoint_is_bulk_out(endpoint))
+			dev->bulk_out = endpoint;
+
+		/* use first bulk endpoint for in and out */
+		if (dev->bulk_in && dev->bulk_out)
+			return 0;
+	}
+
+	return -ENODEV;
+}
+
+const struct kvaser_usb_dev_ops kvaser_usb_leaf_dev_ops = {
+	.dev_set_mode = kvaser_usb_leaf_set_mode,
+	.dev_set_bittiming = kvaser_usb_leaf_set_bittiming,
+	.dev_set_data_bittiming = NULL,
+	.dev_get_berr_counter = kvaser_usb_leaf_get_berr_counter,
+	.dev_setup_endpoints = kvaser_usb_leaf_setup_endpoints,
+	.dev_init_card = kvaser_usb_leaf_init_card,
+	.dev_get_software_info = kvaser_usb_leaf_get_software_info,
+	.dev_get_software_details = NULL,
+	.dev_get_card_info = kvaser_usb_leaf_get_card_info,
+	.dev_get_capabilities = NULL,
+	.dev_set_opt_mode = kvaser_usb_leaf_set_opt_mode,
+	.dev_start_chip = kvaser_usb_leaf_start_chip,
+	.dev_stop_chip = kvaser_usb_leaf_stop_chip,
+	.dev_reset_chip = kvaser_usb_leaf_reset_chip,
+	.dev_flush_queue = kvaser_usb_leaf_flush_queue,
+	.dev_read_bulk_callback = kvaser_usb_leaf_read_bulk_callback,
+	.dev_frame_to_cmd = kvaser_usb_leaf_frame_to_cmd,
+};
+
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg = {
+	.clock = {
+		.freq = CAN_USB_CLOCK,
+	},
+	.timestamp_freq = 1,
+	.bittiming_const = &kvaser_usb_leaf_bittiming_const,
+};
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c
index f530a80f5051..13238a72a338 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb.c
@@ -423,6 +423,7 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n,
 			new_state = CAN_STATE_ERROR_WARNING;
 			break;
 		}
+		/* else: fall through */
 
 	case CAN_STATE_ERROR_WARNING:
 		if (n & PCAN_USB_ERROR_BUS_HEAVY) {
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index 50e911428638..611f9d31be5d 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -353,6 +353,7 @@ static netdev_tx_t peak_usb_ndo_start_xmit(struct sk_buff *skb,
 		default:
 			netdev_warn(netdev, "tx urb submitting failed err=%d\n",
 				    err);
+			/* fall through */
 		case -ENOENT:
 			/* cable unplugged */
 			stats->tx_dropped++;
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
index 0105fbfea273..d516def846ab 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
@@ -141,8 +141,10 @@ static int pcan_msg_add_rec(struct pcan_usb_pro_msg *pm, u8 id, ...)
 	switch (id) {
 	case PCAN_USBPRO_TXMSG8:
 		i += 4;
+		/* fall through */
 	case PCAN_USBPRO_TXMSG4:
 		i += 4;
+		/* fall through */
 	case PCAN_USBPRO_TXMSG0:
 		*pc++ = va_arg(ap, int);
 		*pc++ = va_arg(ap, int);
diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c
new file mode 100644
index 000000000000..0678a38b1af4
--- /dev/null
+++ b/drivers/net/can/usb/ucan.c
@@ -0,0 +1,1613 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Driver for Theobroma Systems UCAN devices, Protocol Version 3
+ *
+ * Copyright (C) 2018 Theobroma Systems Design und Consulting GmbH
+ *
+ *
+ * General Description:
+ *
+ * The USB Device uses three Endpoints:
+ *
+ *   CONTROL Endpoint: Is used the setup the device (start, stop,
+ *   info, configure).
+ *
+ *   IN Endpoint: The device sends CAN Frame Messages and Device
+ *   Information using the IN endpoint.
+ *
+ *   OUT Endpoint: The driver sends configuration requests, and CAN
+ *   Frames on the out endpoint.
+ *
+ * Error Handling:
+ *
+ *   If error reporting is turned on the device encodes error into CAN
+ *   error frames (see uapi/linux/can/error.h) and sends it using the
+ *   IN Endpoint. The driver updates statistics and forward it.
+ */
+
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/error.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/signal.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/usb.h>
+
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/error.h>
+
+#define UCAN_DRIVER_NAME "ucan"
+#define UCAN_MAX_RX_URBS 8
+/* the CAN controller needs a while to enable/disable the bus */
+#define UCAN_USB_CTL_PIPE_TIMEOUT 1000
+/* this driver currently supports protocol version 3 only */
+#define UCAN_PROTOCOL_VERSION_MIN 3
+#define UCAN_PROTOCOL_VERSION_MAX 3
+
+/* UCAN Message Definitions
+ * ------------------------
+ *
+ *  ucan_message_out_t and ucan_message_in_t define the messages
+ *  transmitted on the OUT and IN endpoint.
+ *
+ *  Multibyte fields are transmitted with little endianness
+ *
+ *  INTR Endpoint: a single uint32_t storing the current space in the fifo
+ *
+ *  OUT Endpoint: single message of type ucan_message_out_t is
+ *    transmitted on the out endpoint
+ *
+ *  IN Endpoint: multiple messages ucan_message_in_t concateted in
+ *    the following way:
+ *
+ *	m[n].len <=> the length if message n(including the header in bytes)
+ *	m[n] is is aligned to a 4 byte boundary, hence
+ *	  offset(m[0])	 := 0;
+ *	  offset(m[n+1]) := offset(m[n]) + (m[n].len + 3) & 3
+ *
+ *	this implies that
+ *	  offset(m[n]) % 4 <=> 0
+ */
+
+/* Device Global Commands */
+enum {
+	UCAN_DEVICE_GET_FW_STRING = 0,
+};
+
+/* UCAN Commands */
+enum {
+	/* start the can transceiver - val defines the operation mode */
+	UCAN_COMMAND_START = 0,
+	/* cancel pending transmissions and stop the can transceiver */
+	UCAN_COMMAND_STOP = 1,
+	/* send can transceiver into low-power sleep mode */
+	UCAN_COMMAND_SLEEP = 2,
+	/* wake up can transceiver from low-power sleep mode */
+	UCAN_COMMAND_WAKEUP = 3,
+	/* reset the can transceiver */
+	UCAN_COMMAND_RESET = 4,
+	/* get piece of info from the can transceiver - subcmd defines what
+	 * piece
+	 */
+	UCAN_COMMAND_GET = 5,
+	/* clear or disable hardware filter - subcmd defines which of the two */
+	UCAN_COMMAND_FILTER = 6,
+	/* Setup bittiming */
+	UCAN_COMMAND_SET_BITTIMING = 7,
+	/* recover from bus-off state */
+	UCAN_COMMAND_RESTART = 8,
+};
+
+/* UCAN_COMMAND_START and UCAN_COMMAND_GET_INFO operation modes (bitmap).
+ * Undefined bits must be set to 0.
+ */
+enum {
+	UCAN_MODE_LOOPBACK = BIT(0),
+	UCAN_MODE_SILENT = BIT(1),
+	UCAN_MODE_3_SAMPLES = BIT(2),
+	UCAN_MODE_ONE_SHOT = BIT(3),
+	UCAN_MODE_BERR_REPORT = BIT(4),
+};
+
+/* UCAN_COMMAND_GET subcommands */
+enum {
+	UCAN_COMMAND_GET_INFO = 0,
+	UCAN_COMMAND_GET_PROTOCOL_VERSION = 1,
+};
+
+/* UCAN_COMMAND_FILTER subcommands */
+enum {
+	UCAN_FILTER_CLEAR = 0,
+	UCAN_FILTER_DISABLE = 1,
+	UCAN_FILTER_ENABLE = 2,
+};
+
+/* OUT endpoint message types */
+enum {
+	UCAN_OUT_TX = 2,     /* transmit a CAN frame */
+};
+
+/* IN endpoint message types */
+enum {
+	UCAN_IN_TX_COMPLETE = 1,  /* CAN frame transmission completed */
+	UCAN_IN_RX = 2,           /* CAN frame received */
+};
+
+struct ucan_ctl_cmd_start {
+	__le16 mode;         /* OR-ing any of UCAN_MODE_* */
+} __packed;
+
+struct ucan_ctl_cmd_set_bittiming {
+	__le32 tq;           /* Time quanta (TQ) in nanoseconds */
+	__le16 brp;          /* TQ Prescaler */
+	__le16 sample_point; /* Samplepoint on tenth percent */
+	u8 prop_seg;         /* Propagation segment in TQs */
+	u8 phase_seg1;       /* Phase buffer segment 1 in TQs */
+	u8 phase_seg2;       /* Phase buffer segment 2 in TQs */
+	u8 sjw;              /* Synchronisation jump width in TQs */
+} __packed;
+
+struct ucan_ctl_cmd_device_info {
+	__le32 freq;         /* Clock Frequency for tq generation */
+	u8 tx_fifo;          /* Size of the transmission fifo */
+	u8 sjw_max;          /* can_bittiming fields... */
+	u8 tseg1_min;
+	u8 tseg1_max;
+	u8 tseg2_min;
+	u8 tseg2_max;
+	__le16 brp_inc;
+	__le32 brp_min;
+	__le32 brp_max;      /* ...can_bittiming fields */
+	__le16 ctrlmodes;    /* supported control modes */
+	__le16 hwfilter;     /* Number of HW filter banks */
+	__le16 rxmboxes;     /* Number of receive Mailboxes */
+} __packed;
+
+struct ucan_ctl_cmd_get_protocol_version {
+	__le32 version;
+} __packed;
+
+union ucan_ctl_payload {
+	/* Setup Bittiming
+	 * bmRequest == UCAN_COMMAND_START
+	 */
+	struct ucan_ctl_cmd_start cmd_start;
+	/* Setup Bittiming
+	 * bmRequest == UCAN_COMMAND_SET_BITTIMING
+	 */
+	struct ucan_ctl_cmd_set_bittiming cmd_set_bittiming;
+	/* Get Device Information
+	 * bmRequest == UCAN_COMMAND_GET; wValue = UCAN_COMMAND_GET_INFO
+	 */
+	struct ucan_ctl_cmd_device_info cmd_get_device_info;
+	/* Get Protocol Version
+	 * bmRequest == UCAN_COMMAND_GET;
+	 * wValue = UCAN_COMMAND_GET_PROTOCOL_VERSION
+	 */
+	struct ucan_ctl_cmd_get_protocol_version cmd_get_protocol_version;
+
+	u8 raw[128];
+} __packed;
+
+enum {
+	UCAN_TX_COMPLETE_SUCCESS = BIT(0),
+};
+
+/* Transmission Complete within ucan_message_in */
+struct ucan_tx_complete_entry_t {
+	u8 echo_index;
+	u8 flags;
+} __packed __aligned(0x2);
+
+/* CAN Data message format within ucan_message_in/out */
+struct ucan_can_msg {
+	/* note DLC is computed by
+	 *    msg.len - sizeof (msg.len)
+	 *            - sizeof (msg.type)
+	 *            - sizeof (msg.can_msg.id)
+	 */
+	__le32 id;
+
+	union {
+		u8 data[CAN_MAX_DLEN];  /* Data of CAN frames */
+		u8 dlc;                 /* RTR dlc */
+	};
+} __packed;
+
+/* OUT Endpoint, outbound messages */
+struct ucan_message_out {
+	__le16 len; /* Length of the content include header */
+	u8 type;    /* UCAN_OUT_TX and friends */
+	u8 subtype; /* command sub type */
+
+	union {
+		/* Transmit CAN frame
+		 * (type == UCAN_TX) && ((msg.can_msg.id & CAN_RTR_FLAG) == 0)
+		 * subtype stores the echo id
+		 */
+		struct ucan_can_msg can_msg;
+	} msg;
+} __packed __aligned(0x4);
+
+/* IN Endpoint, inbound messages */
+struct ucan_message_in {
+	__le16 len; /* Length of the content include header */
+	u8 type;    /* UCAN_IN_RX and friends */
+	u8 subtype; /* command sub type */
+
+	union {
+		/* CAN Frame received
+		 * (type == UCAN_IN_RX)
+		 * && ((msg.can_msg.id & CAN_RTR_FLAG) == 0)
+		 */
+		struct ucan_can_msg can_msg;
+
+		/* CAN transmission complete
+		 * (type == UCAN_IN_TX_COMPLETE)
+		 */
+		struct ucan_tx_complete_entry_t can_tx_complete_msg[0];
+	} __aligned(0x4) msg;
+} __packed;
+
+/* Macros to calculate message lengths */
+#define UCAN_OUT_HDR_SIZE offsetof(struct ucan_message_out, msg)
+
+#define UCAN_IN_HDR_SIZE offsetof(struct ucan_message_in, msg)
+#define UCAN_IN_LEN(member) (UCAN_OUT_HDR_SIZE + sizeof(member))
+
+struct ucan_priv;
+
+/* Context Information for transmission URBs */
+struct ucan_urb_context {
+	struct ucan_priv *up;
+	u8 dlc;
+	bool allocated;
+};
+
+/* Information reported by the USB device */
+struct ucan_device_info {
+	struct can_bittiming_const bittiming_const;
+	u8 tx_fifo;
+};
+
+/* Driver private data */
+struct ucan_priv {
+	/* must be the first member */
+	struct can_priv can;
+
+	/* linux USB device structures */
+	struct usb_device *udev;
+	struct usb_interface *intf;
+	struct net_device *netdev;
+
+	/* lock for can->echo_skb (used around
+	 * can_put/get/free_echo_skb
+	 */
+	spinlock_t echo_skb_lock;
+
+	/* usb device information information */
+	u8 intf_index;
+	u8 in_ep_addr;
+	u8 out_ep_addr;
+	u16 in_ep_size;
+
+	/* transmission and reception buffers */
+	struct usb_anchor rx_urbs;
+	struct usb_anchor tx_urbs;
+
+	union ucan_ctl_payload *ctl_msg_buffer;
+	struct ucan_device_info device_info;
+
+	/* transmission control information and locks */
+	spinlock_t context_lock;
+	unsigned int available_tx_urbs;
+	struct ucan_urb_context *context_array;
+};
+
+static u8 ucan_get_can_dlc(struct ucan_can_msg *msg, u16 len)
+{
+	if (le32_to_cpu(msg->id) & CAN_RTR_FLAG)
+		return get_can_dlc(msg->dlc);
+	else
+		return get_can_dlc(len - (UCAN_IN_HDR_SIZE + sizeof(msg->id)));
+}
+
+static void ucan_release_context_array(struct ucan_priv *up)
+{
+	if (!up->context_array)
+		return;
+
+	/* lock is not needed because, driver is currently opening or closing */
+	up->available_tx_urbs = 0;
+
+	kfree(up->context_array);
+	up->context_array = NULL;
+}
+
+static int ucan_alloc_context_array(struct ucan_priv *up)
+{
+	int i;
+
+	/* release contexts if any */
+	ucan_release_context_array(up);
+
+	up->context_array = kcalloc(up->device_info.tx_fifo,
+				    sizeof(*up->context_array),
+				    GFP_KERNEL);
+	if (!up->context_array) {
+		netdev_err(up->netdev,
+			   "Not enough memory to allocate tx contexts\n");
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < up->device_info.tx_fifo; i++) {
+		up->context_array[i].allocated = false;
+		up->context_array[i].up = up;
+	}
+
+	/* lock is not needed because, driver is currently opening */
+	up->available_tx_urbs = up->device_info.tx_fifo;
+
+	return 0;
+}
+
+static struct ucan_urb_context *ucan_alloc_context(struct ucan_priv *up)
+{
+	int i;
+	unsigned long flags;
+	struct ucan_urb_context *ret = NULL;
+
+	if (WARN_ON_ONCE(!up->context_array))
+		return NULL;
+
+	/* execute context operation atomically */
+	spin_lock_irqsave(&up->context_lock, flags);
+
+	for (i = 0; i < up->device_info.tx_fifo; i++) {
+		if (!up->context_array[i].allocated) {
+			/* update context */
+			ret = &up->context_array[i];
+			up->context_array[i].allocated = true;
+
+			/* stop queue if necessary */
+			up->available_tx_urbs--;
+			if (!up->available_tx_urbs)
+				netif_stop_queue(up->netdev);
+
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&up->context_lock, flags);
+	return ret;
+}
+
+static bool ucan_release_context(struct ucan_priv *up,
+				 struct ucan_urb_context *ctx)
+{
+	unsigned long flags;
+	bool ret = false;
+
+	if (WARN_ON_ONCE(!up->context_array))
+		return false;
+
+	/* execute context operation atomically */
+	spin_lock_irqsave(&up->context_lock, flags);
+
+	/* context was not allocated, maybe the device sent garbage */
+	if (ctx->allocated) {
+		ctx->allocated = false;
+
+		/* check if the queue needs to be woken */
+		if (!up->available_tx_urbs)
+			netif_wake_queue(up->netdev);
+		up->available_tx_urbs++;
+
+		ret = true;
+	}
+
+	spin_unlock_irqrestore(&up->context_lock, flags);
+	return ret;
+}
+
+static int ucan_ctrl_command_out(struct ucan_priv *up,
+				 u8 cmd, u16 subcmd, u16 datalen)
+{
+	return usb_control_msg(up->udev,
+			       usb_sndctrlpipe(up->udev, 0),
+			       cmd,
+			       USB_DIR_OUT | USB_TYPE_VENDOR |
+						USB_RECIP_INTERFACE,
+			       subcmd,
+			       up->intf_index,
+			       up->ctl_msg_buffer,
+			       datalen,
+			       UCAN_USB_CTL_PIPE_TIMEOUT);
+}
+
+static int ucan_device_request_in(struct ucan_priv *up,
+				  u8 cmd, u16 subcmd, u16 datalen)
+{
+	return usb_control_msg(up->udev,
+			       usb_rcvctrlpipe(up->udev, 0),
+			       cmd,
+			       USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
+			       subcmd,
+			       0,
+			       up->ctl_msg_buffer,
+			       datalen,
+			       UCAN_USB_CTL_PIPE_TIMEOUT);
+}
+
+/* Parse the device information structure reported by the device and
+ * setup private variables accordingly
+ */
+static void ucan_parse_device_info(struct ucan_priv *up,
+				   struct ucan_ctl_cmd_device_info *device_info)
+{
+	struct can_bittiming_const *bittiming =
+		&up->device_info.bittiming_const;
+	u16 ctrlmodes;
+
+	/* store the data */
+	up->can.clock.freq = le32_to_cpu(device_info->freq);
+	up->device_info.tx_fifo = device_info->tx_fifo;
+	strcpy(bittiming->name, "ucan");
+	bittiming->tseg1_min = device_info->tseg1_min;
+	bittiming->tseg1_max = device_info->tseg1_max;
+	bittiming->tseg2_min = device_info->tseg2_min;
+	bittiming->tseg2_max = device_info->tseg2_max;
+	bittiming->sjw_max = device_info->sjw_max;
+	bittiming->brp_min = le32_to_cpu(device_info->brp_min);
+	bittiming->brp_max = le32_to_cpu(device_info->brp_max);
+	bittiming->brp_inc = le16_to_cpu(device_info->brp_inc);
+
+	ctrlmodes = le16_to_cpu(device_info->ctrlmodes);
+
+	up->can.ctrlmode_supported = 0;
+
+	if (ctrlmodes & UCAN_MODE_LOOPBACK)
+		up->can.ctrlmode_supported |= CAN_CTRLMODE_LOOPBACK;
+	if (ctrlmodes & UCAN_MODE_SILENT)
+		up->can.ctrlmode_supported |= CAN_CTRLMODE_LISTENONLY;
+	if (ctrlmodes & UCAN_MODE_3_SAMPLES)
+		up->can.ctrlmode_supported |= CAN_CTRLMODE_3_SAMPLES;
+	if (ctrlmodes & UCAN_MODE_ONE_SHOT)
+		up->can.ctrlmode_supported |= CAN_CTRLMODE_ONE_SHOT;
+	if (ctrlmodes & UCAN_MODE_BERR_REPORT)
+		up->can.ctrlmode_supported |= CAN_CTRLMODE_BERR_REPORTING;
+}
+
+/* Handle a CAN error frame that we have received from the device.
+ * Returns true if the can state has changed.
+ */
+static bool ucan_handle_error_frame(struct ucan_priv *up,
+				    struct ucan_message_in *m,
+				    canid_t canid)
+{
+	enum can_state new_state = up->can.state;
+	struct net_device_stats *net_stats = &up->netdev->stats;
+	struct can_device_stats *can_stats = &up->can.can_stats;
+
+	if (canid & CAN_ERR_LOSTARB)
+		can_stats->arbitration_lost++;
+
+	if (canid & CAN_ERR_BUSERROR)
+		can_stats->bus_error++;
+
+	if (canid & CAN_ERR_ACK)
+		net_stats->tx_errors++;
+
+	if (canid & CAN_ERR_BUSOFF)
+		new_state = CAN_STATE_BUS_OFF;
+
+	/* controller problems, details in data[1] */
+	if (canid & CAN_ERR_CRTL) {
+		u8 d1 = m->msg.can_msg.data[1];
+
+		if (d1 & CAN_ERR_CRTL_RX_OVERFLOW)
+			net_stats->rx_over_errors++;
+
+		/* controller state bits: if multiple are set the worst wins */
+		if (d1 & CAN_ERR_CRTL_ACTIVE)
+			new_state = CAN_STATE_ERROR_ACTIVE;
+
+		if (d1 & (CAN_ERR_CRTL_RX_WARNING | CAN_ERR_CRTL_TX_WARNING))
+			new_state = CAN_STATE_ERROR_WARNING;
+
+		if (d1 & (CAN_ERR_CRTL_RX_PASSIVE | CAN_ERR_CRTL_TX_PASSIVE))
+			new_state = CAN_STATE_ERROR_PASSIVE;
+	}
+
+	/* protocol error, details in data[2] */
+	if (canid & CAN_ERR_PROT) {
+		u8 d2 = m->msg.can_msg.data[2];
+
+		if (d2 & CAN_ERR_PROT_TX)
+			net_stats->tx_errors++;
+		else
+			net_stats->rx_errors++;
+	}
+
+	/* no state change - we are done */
+	if (up->can.state == new_state)
+		return false;
+
+	/* we switched into a better state */
+	if (up->can.state > new_state) {
+		up->can.state = new_state;
+		return true;
+	}
+
+	/* we switched into a worse state */
+	up->can.state = new_state;
+	switch (new_state) {
+	case CAN_STATE_BUS_OFF:
+		can_stats->bus_off++;
+		can_bus_off(up->netdev);
+		break;
+	case CAN_STATE_ERROR_PASSIVE:
+		can_stats->error_passive++;
+		break;
+	case CAN_STATE_ERROR_WARNING:
+		can_stats->error_warning++;
+		break;
+	default:
+		break;
+	}
+	return true;
+}
+
+/* Callback on reception of a can frame via the IN endpoint
+ *
+ * This function allocates an skb and transferres it to the Linux
+ * network stack
+ */
+static void ucan_rx_can_msg(struct ucan_priv *up, struct ucan_message_in *m)
+{
+	int len;
+	canid_t canid;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	struct net_device_stats *stats = &up->netdev->stats;
+
+	/* get the contents of the length field */
+	len = le16_to_cpu(m->len);
+
+	/* check sanity */
+	if (len < UCAN_IN_HDR_SIZE + sizeof(m->msg.can_msg.id)) {
+		netdev_warn(up->netdev, "invalid input message len: %d\n", len);
+		return;
+	}
+
+	/* handle error frames */
+	canid = le32_to_cpu(m->msg.can_msg.id);
+	if (canid & CAN_ERR_FLAG) {
+		bool busstate_changed = ucan_handle_error_frame(up, m, canid);
+
+		/* if berr-reporting is off only state changes get through */
+		if (!(up->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) &&
+		    !busstate_changed)
+			return;
+	} else {
+		canid_t canid_mask;
+		/* compute the mask for canid */
+		canid_mask = CAN_RTR_FLAG;
+		if (canid & CAN_EFF_FLAG)
+			canid_mask |= CAN_EFF_MASK | CAN_EFF_FLAG;
+		else
+			canid_mask |= CAN_SFF_MASK;
+
+		if (canid & ~canid_mask)
+			netdev_warn(up->netdev,
+				    "unexpected bits set (canid %x, mask %x)",
+				    canid, canid_mask);
+
+		canid &= canid_mask;
+	}
+
+	/* allocate skb */
+	skb = alloc_can_skb(up->netdev, &cf);
+	if (!skb)
+		return;
+
+	/* fill the can frame */
+	cf->can_id = canid;
+
+	/* compute DLC taking RTR_FLAG into account */
+	cf->can_dlc = ucan_get_can_dlc(&m->msg.can_msg, len);
+
+	/* copy the payload of non RTR frames */
+	if (!(cf->can_id & CAN_RTR_FLAG) || (cf->can_id & CAN_ERR_FLAG))
+		memcpy(cf->data, m->msg.can_msg.data, cf->can_dlc);
+
+	/* don't count error frames as real packets */
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+
+	/* pass it to Linux */
+	netif_rx(skb);
+}
+
+/* callback indicating completed transmission */
+static void ucan_tx_complete_msg(struct ucan_priv *up,
+				 struct ucan_message_in *m)
+{
+	unsigned long flags;
+	u16 count, i;
+	u8 echo_index, dlc;
+	u16 len = le16_to_cpu(m->len);
+
+	struct ucan_urb_context *context;
+
+	if (len < UCAN_IN_HDR_SIZE || (len % 2 != 0)) {
+		netdev_err(up->netdev, "invalid tx complete length\n");
+		return;
+	}
+
+	count = (len - UCAN_IN_HDR_SIZE) / 2;
+	for (i = 0; i < count; i++) {
+		/* we did not submit such echo ids */
+		echo_index = m->msg.can_tx_complete_msg[i].echo_index;
+		if (echo_index >= up->device_info.tx_fifo) {
+			up->netdev->stats.tx_errors++;
+			netdev_err(up->netdev,
+				   "invalid echo_index %d received\n",
+				   echo_index);
+			continue;
+		}
+
+		/* gather information from the context */
+		context = &up->context_array[echo_index];
+		dlc = READ_ONCE(context->dlc);
+
+		/* Release context and restart queue if necessary.
+		 * Also check if the context was allocated
+		 */
+		if (!ucan_release_context(up, context))
+			continue;
+
+		spin_lock_irqsave(&up->echo_skb_lock, flags);
+		if (m->msg.can_tx_complete_msg[i].flags &
+		    UCAN_TX_COMPLETE_SUCCESS) {
+			/* update statistics */
+			up->netdev->stats.tx_packets++;
+			up->netdev->stats.tx_bytes += dlc;
+			can_get_echo_skb(up->netdev, echo_index);
+		} else {
+			up->netdev->stats.tx_dropped++;
+			can_free_echo_skb(up->netdev, echo_index);
+		}
+		spin_unlock_irqrestore(&up->echo_skb_lock, flags);
+	}
+}
+
+/* callback on reception of a USB message */
+static void ucan_read_bulk_callback(struct urb *urb)
+{
+	int ret;
+	int pos;
+	struct ucan_priv *up = urb->context;
+	struct net_device *netdev = up->netdev;
+	struct ucan_message_in *m;
+
+	/* the device is not up and the driver should not receive any
+	 * data on the bulk in pipe
+	 */
+	if (WARN_ON(!up->context_array)) {
+		usb_free_coherent(up->udev,
+				  up->in_ep_size,
+				  urb->transfer_buffer,
+				  urb->transfer_dma);
+		return;
+	}
+
+	/* check URB status */
+	switch (urb->status) {
+	case 0:
+		break;
+	case -ENOENT:
+	case -EPIPE:
+	case -EPROTO:
+	case -ESHUTDOWN:
+	case -ETIME:
+		/* urb is not resubmitted -> free dma data */
+		usb_free_coherent(up->udev,
+				  up->in_ep_size,
+				  urb->transfer_buffer,
+				  urb->transfer_dma);
+		netdev_dbg(up->netdev, "not resumbmitting urb; status: %d\n",
+			   urb->status);
+		return;
+	default:
+		goto resubmit;
+	}
+
+	/* sanity check */
+	if (!netif_device_present(netdev))
+		return;
+
+	/* iterate over input */
+	pos = 0;
+	while (pos < urb->actual_length) {
+		int len;
+
+		/* check sanity (length of header) */
+		if ((urb->actual_length - pos) < UCAN_IN_HDR_SIZE) {
+			netdev_warn(up->netdev,
+				    "invalid message (short; no hdr; l:%d)\n",
+				    urb->actual_length);
+			goto resubmit;
+		}
+
+		/* setup the message address */
+		m = (struct ucan_message_in *)
+			((u8 *)urb->transfer_buffer + pos);
+		len = le16_to_cpu(m->len);
+
+		/* check sanity (length of content) */
+		if (urb->actual_length - pos < len) {
+			netdev_warn(up->netdev,
+				    "invalid message (short; no data; l:%d)\n",
+				    urb->actual_length);
+			print_hex_dump(KERN_WARNING,
+				       "raw data: ",
+				       DUMP_PREFIX_ADDRESS,
+				       16,
+				       1,
+				       urb->transfer_buffer,
+				       urb->actual_length,
+				       true);
+
+			goto resubmit;
+		}
+
+		switch (m->type) {
+		case UCAN_IN_RX:
+			ucan_rx_can_msg(up, m);
+			break;
+		case UCAN_IN_TX_COMPLETE:
+			ucan_tx_complete_msg(up, m);
+			break;
+		default:
+			netdev_warn(up->netdev,
+				    "invalid message (type; t:%d)\n",
+				    m->type);
+			break;
+		}
+
+		/* proceed to next message */
+		pos += len;
+		/* align to 4 byte boundary */
+		pos = round_up(pos, 4);
+	}
+
+resubmit:
+	/* resubmit urb when done */
+	usb_fill_bulk_urb(urb, up->udev,
+			  usb_rcvbulkpipe(up->udev,
+					  up->in_ep_addr),
+			  urb->transfer_buffer,
+			  up->in_ep_size,
+			  ucan_read_bulk_callback,
+			  up);
+
+	usb_anchor_urb(urb, &up->rx_urbs);
+	ret = usb_submit_urb(urb, GFP_KERNEL);
+
+	if (ret < 0) {
+		netdev_err(up->netdev,
+			   "failed resubmitting read bulk urb: %d\n",
+			   ret);
+
+		usb_unanchor_urb(urb);
+		usb_free_coherent(up->udev,
+				  up->in_ep_size,
+				  urb->transfer_buffer,
+				  urb->transfer_dma);
+
+		if (ret == -ENODEV)
+			netif_device_detach(netdev);
+	}
+}
+
+/* callback after transmission of a USB message */
+static void ucan_write_bulk_callback(struct urb *urb)
+{
+	unsigned long flags;
+	struct ucan_priv *up;
+	struct ucan_urb_context *context = urb->context;
+
+	/* get the urb context */
+	if (WARN_ON_ONCE(!context))
+		return;
+
+	/* free up our allocated buffer */
+	usb_free_coherent(urb->dev,
+			  sizeof(struct ucan_message_out),
+			  urb->transfer_buffer,
+			  urb->transfer_dma);
+
+	up = context->up;
+	if (WARN_ON_ONCE(!up))
+		return;
+
+	/* sanity check */
+	if (!netif_device_present(up->netdev))
+		return;
+
+	/* transmission failed (USB - the device will not send a TX complete) */
+	if (urb->status) {
+		netdev_warn(up->netdev,
+			    "failed to transmit USB message to device: %d\n",
+			     urb->status);
+
+		/* update counters an cleanup */
+		spin_lock_irqsave(&up->echo_skb_lock, flags);
+		can_free_echo_skb(up->netdev, context - up->context_array);
+		spin_unlock_irqrestore(&up->echo_skb_lock, flags);
+
+		up->netdev->stats.tx_dropped++;
+
+		/* release context and restart the queue if necessary */
+		if (!ucan_release_context(up, context))
+			netdev_err(up->netdev,
+				   "urb failed, failed to release context\n");
+	}
+}
+
+static void ucan_cleanup_rx_urbs(struct ucan_priv *up, struct urb **urbs)
+{
+	int i;
+
+	for (i = 0; i < UCAN_MAX_RX_URBS; i++) {
+		if (urbs[i]) {
+			usb_unanchor_urb(urbs[i]);
+			usb_free_coherent(up->udev,
+					  up->in_ep_size,
+					  urbs[i]->transfer_buffer,
+					  urbs[i]->transfer_dma);
+			usb_free_urb(urbs[i]);
+		}
+	}
+
+	memset(urbs, 0, sizeof(*urbs) * UCAN_MAX_RX_URBS);
+}
+
+static int ucan_prepare_and_anchor_rx_urbs(struct ucan_priv *up,
+					   struct urb **urbs)
+{
+	int i;
+
+	memset(urbs, 0, sizeof(*urbs) * UCAN_MAX_RX_URBS);
+
+	for (i = 0; i < UCAN_MAX_RX_URBS; i++) {
+		void *buf;
+
+		urbs[i] = usb_alloc_urb(0, GFP_KERNEL);
+		if (!urbs[i])
+			goto err;
+
+		buf = usb_alloc_coherent(up->udev,
+					 up->in_ep_size,
+					 GFP_KERNEL, &urbs[i]->transfer_dma);
+		if (!buf) {
+			/* cleanup this urb */
+			usb_free_urb(urbs[i]);
+			urbs[i] = NULL;
+			goto err;
+		}
+
+		usb_fill_bulk_urb(urbs[i], up->udev,
+				  usb_rcvbulkpipe(up->udev,
+						  up->in_ep_addr),
+				  buf,
+				  up->in_ep_size,
+				  ucan_read_bulk_callback,
+				  up);
+
+		urbs[i]->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
+
+		usb_anchor_urb(urbs[i], &up->rx_urbs);
+	}
+	return 0;
+
+err:
+	/* cleanup other unsubmitted urbs */
+	ucan_cleanup_rx_urbs(up, urbs);
+	return -ENOMEM;
+}
+
+/* Submits rx urbs with the semantic: Either submit all, or cleanup
+ * everything. I case of errors submitted urbs are killed and all urbs in
+ * the array are freed. I case of no errors every entry in the urb
+ * array is set to NULL.
+ */
+static int ucan_submit_rx_urbs(struct ucan_priv *up, struct urb **urbs)
+{
+	int i, ret;
+
+	/* Iterate over all urbs to submit. On success remove the urb
+	 * from the list.
+	 */
+	for (i = 0; i < UCAN_MAX_RX_URBS; i++) {
+		ret = usb_submit_urb(urbs[i], GFP_KERNEL);
+		if (ret) {
+			netdev_err(up->netdev,
+				   "could not submit urb; code: %d\n",
+				   ret);
+			goto err;
+		}
+
+		/* Anchor URB and drop reference, USB core will take
+		 * care of freeing it
+		 */
+		usb_free_urb(urbs[i]);
+		urbs[i] = NULL;
+	}
+	return 0;
+
+err:
+	/* Cleanup unsubmitted urbs */
+	ucan_cleanup_rx_urbs(up, urbs);
+
+	/* Kill urbs that are already submitted */
+	usb_kill_anchored_urbs(&up->rx_urbs);
+
+	return ret;
+}
+
+/* Open the network device */
+static int ucan_open(struct net_device *netdev)
+{
+	int ret, ret_cleanup;
+	u16 ctrlmode;
+	struct urb *urbs[UCAN_MAX_RX_URBS];
+	struct ucan_priv *up = netdev_priv(netdev);
+
+	ret = ucan_alloc_context_array(up);
+	if (ret)
+		return ret;
+
+	/* Allocate and prepare IN URBS - allocated and anchored
+	 * urbs are stored in urbs[] for clean
+	 */
+	ret = ucan_prepare_and_anchor_rx_urbs(up, urbs);
+	if (ret)
+		goto err_contexts;
+
+	/* Check the control mode */
+	ctrlmode = 0;
+	if (up->can.ctrlmode & CAN_CTRLMODE_LOOPBACK)
+		ctrlmode |= UCAN_MODE_LOOPBACK;
+	if (up->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
+		ctrlmode |= UCAN_MODE_SILENT;
+	if (up->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES)
+		ctrlmode |= UCAN_MODE_3_SAMPLES;
+	if (up->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT)
+		ctrlmode |= UCAN_MODE_ONE_SHOT;
+
+	/* Enable this in any case - filtering is down within the
+	 * receive path
+	 */
+	ctrlmode |= UCAN_MODE_BERR_REPORT;
+	up->ctl_msg_buffer->cmd_start.mode = cpu_to_le16(ctrlmode);
+
+	/* Driver is ready to receive data - start the USB device */
+	ret = ucan_ctrl_command_out(up, UCAN_COMMAND_START, 0, 2);
+	if (ret < 0) {
+		netdev_err(up->netdev,
+			   "could not start device, code: %d\n",
+			   ret);
+		goto err_reset;
+	}
+
+	/* Call CAN layer open */
+	ret = open_candev(netdev);
+	if (ret)
+		goto err_stop;
+
+	/* Driver is ready to receive data. Submit RX URBS */
+	ret = ucan_submit_rx_urbs(up, urbs);
+	if (ret)
+		goto err_stop;
+
+	up->can.state = CAN_STATE_ERROR_ACTIVE;
+
+	/* Start the network queue */
+	netif_start_queue(netdev);
+
+	return 0;
+
+err_stop:
+	/* The device have started already stop it */
+	ret_cleanup = ucan_ctrl_command_out(up, UCAN_COMMAND_STOP, 0, 0);
+	if (ret_cleanup < 0)
+		netdev_err(up->netdev,
+			   "could not stop device, code: %d\n",
+			   ret_cleanup);
+
+err_reset:
+	/* The device might have received data, reset it for
+	 * consistent state
+	 */
+	ret_cleanup = ucan_ctrl_command_out(up, UCAN_COMMAND_RESET, 0, 0);
+	if (ret_cleanup < 0)
+		netdev_err(up->netdev,
+			   "could not reset device, code: %d\n",
+			   ret_cleanup);
+
+	/* clean up unsubmitted urbs */
+	ucan_cleanup_rx_urbs(up, urbs);
+
+err_contexts:
+	ucan_release_context_array(up);
+	return ret;
+}
+
+static struct urb *ucan_prepare_tx_urb(struct ucan_priv *up,
+				       struct ucan_urb_context *context,
+				       struct can_frame *cf,
+				       u8 echo_index)
+{
+	int mlen;
+	struct urb *urb;
+	struct ucan_message_out *m;
+
+	/* create a URB, and a buffer for it, and copy the data to the URB */
+	urb = usb_alloc_urb(0, GFP_ATOMIC);
+	if (!urb) {
+		netdev_err(up->netdev, "no memory left for URBs\n");
+		return NULL;
+	}
+
+	m = usb_alloc_coherent(up->udev,
+			       sizeof(struct ucan_message_out),
+			       GFP_ATOMIC,
+			       &urb->transfer_dma);
+	if (!m) {
+		netdev_err(up->netdev, "no memory left for USB buffer\n");
+		usb_free_urb(urb);
+		return NULL;
+	}
+
+	/* build the USB message */
+	m->type = UCAN_OUT_TX;
+	m->msg.can_msg.id = cpu_to_le32(cf->can_id);
+
+	if (cf->can_id & CAN_RTR_FLAG) {
+		mlen = UCAN_OUT_HDR_SIZE +
+			offsetof(struct ucan_can_msg, dlc) +
+			sizeof(m->msg.can_msg.dlc);
+		m->msg.can_msg.dlc = cf->can_dlc;
+	} else {
+		mlen = UCAN_OUT_HDR_SIZE +
+			sizeof(m->msg.can_msg.id) + cf->can_dlc;
+		memcpy(m->msg.can_msg.data, cf->data, cf->can_dlc);
+	}
+	m->len = cpu_to_le16(mlen);
+
+	context->dlc = cf->can_dlc;
+
+	m->subtype = echo_index;
+
+	/* build the urb */
+	usb_fill_bulk_urb(urb, up->udev,
+			  usb_sndbulkpipe(up->udev,
+					  up->out_ep_addr),
+			  m, mlen, ucan_write_bulk_callback, context);
+	urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
+
+	return urb;
+}
+
+static void ucan_clean_up_tx_urb(struct ucan_priv *up, struct urb *urb)
+{
+	usb_free_coherent(up->udev, sizeof(struct ucan_message_out),
+			  urb->transfer_buffer, urb->transfer_dma);
+	usb_free_urb(urb);
+}
+
+/* callback when Linux needs to send a can frame */
+static netdev_tx_t ucan_start_xmit(struct sk_buff *skb,
+				   struct net_device *netdev)
+{
+	unsigned long flags;
+	int ret;
+	u8 echo_index;
+	struct urb *urb;
+	struct ucan_urb_context *context;
+	struct ucan_priv *up = netdev_priv(netdev);
+	struct can_frame *cf = (struct can_frame *)skb->data;
+
+	/* check skb */
+	if (can_dropped_invalid_skb(netdev, skb))
+		return NETDEV_TX_OK;
+
+	/* allocate a context and slow down tx path, if fifo state is low */
+	context = ucan_alloc_context(up);
+	echo_index = context - up->context_array;
+
+	if (WARN_ON_ONCE(!context))
+		return NETDEV_TX_BUSY;
+
+	/* prepare urb for transmission */
+	urb = ucan_prepare_tx_urb(up, context, cf, echo_index);
+	if (!urb)
+		goto drop;
+
+	/* put the skb on can loopback stack */
+	spin_lock_irqsave(&up->echo_skb_lock, flags);
+	can_put_echo_skb(skb, up->netdev, echo_index);
+	spin_unlock_irqrestore(&up->echo_skb_lock, flags);
+
+	/* transmit it */
+	usb_anchor_urb(urb, &up->tx_urbs);
+	ret = usb_submit_urb(urb, GFP_ATOMIC);
+
+	/* cleanup urb */
+	if (ret) {
+		/* on error, clean up */
+		usb_unanchor_urb(urb);
+		ucan_clean_up_tx_urb(up, urb);
+		if (!ucan_release_context(up, context))
+			netdev_err(up->netdev,
+				   "xmit err: failed to release context\n");
+
+		/* remove the skb from the echo stack - this also
+		 * frees the skb
+		 */
+		spin_lock_irqsave(&up->echo_skb_lock, flags);
+		can_free_echo_skb(up->netdev, echo_index);
+		spin_unlock_irqrestore(&up->echo_skb_lock, flags);
+
+		if (ret == -ENODEV) {
+			netif_device_detach(up->netdev);
+		} else {
+			netdev_warn(up->netdev,
+				    "xmit err: failed to submit urb %d\n",
+				    ret);
+			up->netdev->stats.tx_dropped++;
+		}
+		return NETDEV_TX_OK;
+	}
+
+	netif_trans_update(netdev);
+
+	/* release ref, as we do not need the urb anymore */
+	usb_free_urb(urb);
+
+	return NETDEV_TX_OK;
+
+drop:
+	if (!ucan_release_context(up, context))
+		netdev_err(up->netdev,
+			   "xmit drop: failed to release context\n");
+	dev_kfree_skb(skb);
+	up->netdev->stats.tx_dropped++;
+
+	return NETDEV_TX_OK;
+}
+
+/* Device goes down
+ *
+ * Clean up used resources
+ */
+static int ucan_close(struct net_device *netdev)
+{
+	int ret;
+	struct ucan_priv *up = netdev_priv(netdev);
+
+	up->can.state = CAN_STATE_STOPPED;
+
+	/* stop sending data */
+	usb_kill_anchored_urbs(&up->tx_urbs);
+
+	/* stop receiving data */
+	usb_kill_anchored_urbs(&up->rx_urbs);
+
+	/* stop and reset can device */
+	ret = ucan_ctrl_command_out(up, UCAN_COMMAND_STOP, 0, 0);
+	if (ret < 0)
+		netdev_err(up->netdev,
+			   "could not stop device, code: %d\n",
+			   ret);
+
+	ret = ucan_ctrl_command_out(up, UCAN_COMMAND_RESET, 0, 0);
+	if (ret < 0)
+		netdev_err(up->netdev,
+			   "could not reset device, code: %d\n",
+			   ret);
+
+	netif_stop_queue(netdev);
+
+	ucan_release_context_array(up);
+
+	close_candev(up->netdev);
+	return 0;
+}
+
+/* CAN driver callbacks */
+static const struct net_device_ops ucan_netdev_ops = {
+	.ndo_open = ucan_open,
+	.ndo_stop = ucan_close,
+	.ndo_start_xmit = ucan_start_xmit,
+	.ndo_change_mtu = can_change_mtu,
+};
+
+/* Request to set bittiming
+ *
+ * This function generates an USB set bittiming message and transmits
+ * it to the device
+ */
+static int ucan_set_bittiming(struct net_device *netdev)
+{
+	int ret;
+	struct ucan_priv *up = netdev_priv(netdev);
+	struct ucan_ctl_cmd_set_bittiming *cmd_set_bittiming;
+
+	cmd_set_bittiming = &up->ctl_msg_buffer->cmd_set_bittiming;
+	cmd_set_bittiming->tq = cpu_to_le32(up->can.bittiming.tq);
+	cmd_set_bittiming->brp = cpu_to_le16(up->can.bittiming.brp);
+	cmd_set_bittiming->sample_point =
+	    cpu_to_le16(up->can.bittiming.sample_point);
+	cmd_set_bittiming->prop_seg = up->can.bittiming.prop_seg;
+	cmd_set_bittiming->phase_seg1 = up->can.bittiming.phase_seg1;
+	cmd_set_bittiming->phase_seg2 = up->can.bittiming.phase_seg2;
+	cmd_set_bittiming->sjw = up->can.bittiming.sjw;
+
+	ret = ucan_ctrl_command_out(up, UCAN_COMMAND_SET_BITTIMING, 0,
+				    sizeof(*cmd_set_bittiming));
+	return (ret < 0) ? ret : 0;
+}
+
+/* Restart the device to get it out of BUS-OFF state.
+ * Called when the user runs "ip link set can1 type can restart".
+ */
+static int ucan_set_mode(struct net_device *netdev, enum can_mode mode)
+{
+	int ret;
+	unsigned long flags;
+	struct ucan_priv *up = netdev_priv(netdev);
+
+	switch (mode) {
+	case CAN_MODE_START:
+		netdev_dbg(up->netdev, "restarting device\n");
+
+		ret = ucan_ctrl_command_out(up, UCAN_COMMAND_RESTART, 0, 0);
+		up->can.state = CAN_STATE_ERROR_ACTIVE;
+
+		/* check if queue can be restarted,
+		 * up->available_tx_urbs must be protected by the
+		 * lock
+		 */
+		spin_lock_irqsave(&up->context_lock, flags);
+
+		if (up->available_tx_urbs > 0)
+			netif_wake_queue(up->netdev);
+
+		spin_unlock_irqrestore(&up->context_lock, flags);
+
+		return ret;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+/* Probe the device, reset it and gather general device information */
+static int ucan_probe(struct usb_interface *intf,
+		      const struct usb_device_id *id)
+{
+	int ret;
+	int i;
+	u32 protocol_version;
+	struct usb_device *udev;
+	struct net_device *netdev;
+	struct usb_host_interface *iface_desc;
+	struct ucan_priv *up;
+	struct usb_endpoint_descriptor *ep;
+	u16 in_ep_size;
+	u16 out_ep_size;
+	u8 in_ep_addr;
+	u8 out_ep_addr;
+	union ucan_ctl_payload *ctl_msg_buffer;
+	char firmware_str[sizeof(union ucan_ctl_payload) + 1];
+
+	udev = interface_to_usbdev(intf);
+
+	/* Stage 1 - Interface Parsing
+	 * ---------------------------
+	 *
+	 * Identifie the device USB interface descriptor and its
+	 * endpoints. Probing is aborted on errors.
+	 */
+
+	/* check if the interface is sane */
+	iface_desc = intf->cur_altsetting;
+	if (!iface_desc)
+		return -ENODEV;
+
+	dev_info(&udev->dev,
+		 "%s: probing device on interface #%d\n",
+		 UCAN_DRIVER_NAME,
+		 iface_desc->desc.bInterfaceNumber);
+
+	/* interface sanity check */
+	if (iface_desc->desc.bNumEndpoints != 2) {
+		dev_err(&udev->dev,
+			"%s: invalid EP count (%d)",
+			UCAN_DRIVER_NAME, iface_desc->desc.bNumEndpoints);
+		goto err_firmware_needs_update;
+	}
+
+	/* check interface endpoints */
+	in_ep_addr = 0;
+	out_ep_addr = 0;
+	in_ep_size = 0;
+	out_ep_size = 0;
+	for (i = 0; i < iface_desc->desc.bNumEndpoints; i++) {
+		ep = &iface_desc->endpoint[i].desc;
+
+		if (((ep->bEndpointAddress & USB_ENDPOINT_DIR_MASK) != 0) &&
+		    ((ep->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) ==
+		     USB_ENDPOINT_XFER_BULK)) {
+			/* In Endpoint */
+			in_ep_addr = ep->bEndpointAddress;
+			in_ep_addr &= USB_ENDPOINT_NUMBER_MASK;
+			in_ep_size = le16_to_cpu(ep->wMaxPacketSize);
+		} else if (((ep->bEndpointAddress & USB_ENDPOINT_DIR_MASK) ==
+			    0) &&
+			   ((ep->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) ==
+			    USB_ENDPOINT_XFER_BULK)) {
+			/* Out Endpoint */
+			out_ep_addr = ep->bEndpointAddress;
+			out_ep_addr &= USB_ENDPOINT_NUMBER_MASK;
+			out_ep_size = le16_to_cpu(ep->wMaxPacketSize);
+		}
+	}
+
+	/* check if interface is sane */
+	if (!in_ep_addr || !out_ep_addr) {
+		dev_err(&udev->dev, "%s: invalid endpoint configuration\n",
+			UCAN_DRIVER_NAME);
+		goto err_firmware_needs_update;
+	}
+	if (in_ep_size < sizeof(struct ucan_message_in)) {
+		dev_err(&udev->dev, "%s: invalid in_ep MaxPacketSize\n",
+			UCAN_DRIVER_NAME);
+		goto err_firmware_needs_update;
+	}
+	if (out_ep_size < sizeof(struct ucan_message_out)) {
+		dev_err(&udev->dev, "%s: invalid out_ep MaxPacketSize\n",
+			UCAN_DRIVER_NAME);
+		goto err_firmware_needs_update;
+	}
+
+	/* Stage 2 - Device Identification
+	 * -------------------------------
+	 *
+	 * The device interface seems to be a ucan device. Do further
+	 * compatibility checks. On error probing is aborted, on
+	 * success this stage leaves the ctl_msg_buffer with the
+	 * reported contents of a GET_INFO command (supported
+	 * bittimings, tx_fifo depth). This information is used in
+	 * Stage 3 for the final driver initialisation.
+	 */
+
+	/* Prepare Memory for control transferes */
+	ctl_msg_buffer = devm_kzalloc(&udev->dev,
+				      sizeof(union ucan_ctl_payload),
+				      GFP_KERNEL);
+	if (!ctl_msg_buffer) {
+		dev_err(&udev->dev,
+			"%s: failed to allocate control pipe memory\n",
+			UCAN_DRIVER_NAME);
+		return -ENOMEM;
+	}
+
+	/* get protocol version
+	 *
+	 * note: ucan_ctrl_command_* wrappers cannot be used yet
+	 * because `up` is initialised in Stage 3
+	 */
+	ret = usb_control_msg(udev,
+			      usb_rcvctrlpipe(udev, 0),
+			      UCAN_COMMAND_GET,
+			      USB_DIR_IN | USB_TYPE_VENDOR |
+					USB_RECIP_INTERFACE,
+			      UCAN_COMMAND_GET_PROTOCOL_VERSION,
+			      iface_desc->desc.bInterfaceNumber,
+			      ctl_msg_buffer,
+			      sizeof(union ucan_ctl_payload),
+			      UCAN_USB_CTL_PIPE_TIMEOUT);
+
+	/* older firmware version do not support this command - those
+	 * are not supported by this drive
+	 */
+	if (ret != 4) {
+		dev_err(&udev->dev,
+			"%s: could not read protocol version, ret=%d\n",
+			UCAN_DRIVER_NAME, ret);
+		if (ret >= 0)
+			ret = -EINVAL;
+		goto err_firmware_needs_update;
+	}
+
+	/* this driver currently supports protocol version 3 only */
+	protocol_version =
+		le32_to_cpu(ctl_msg_buffer->cmd_get_protocol_version.version);
+	if (protocol_version < UCAN_PROTOCOL_VERSION_MIN ||
+	    protocol_version > UCAN_PROTOCOL_VERSION_MAX) {
+		dev_err(&udev->dev,
+			"%s: device protocol version %d is not supported\n",
+			UCAN_DRIVER_NAME, protocol_version);
+		goto err_firmware_needs_update;
+	}
+
+	/* request the device information and store it in ctl_msg_buffer
+	 *
+	 * note: ucan_ctrl_command_* wrappers connot be used yet
+	 * because `up` is initialised in Stage 3
+	 */
+	ret = usb_control_msg(udev,
+			      usb_rcvctrlpipe(udev, 0),
+			      UCAN_COMMAND_GET,
+			      USB_DIR_IN | USB_TYPE_VENDOR |
+					USB_RECIP_INTERFACE,
+			      UCAN_COMMAND_GET_INFO,
+			      iface_desc->desc.bInterfaceNumber,
+			      ctl_msg_buffer,
+			      sizeof(ctl_msg_buffer->cmd_get_device_info),
+			      UCAN_USB_CTL_PIPE_TIMEOUT);
+
+	if (ret < 0) {
+		dev_err(&udev->dev, "%s: failed to retrieve device info\n",
+			UCAN_DRIVER_NAME);
+		goto err_firmware_needs_update;
+	}
+	if (ret < sizeof(ctl_msg_buffer->cmd_get_device_info)) {
+		dev_err(&udev->dev, "%s: device reported invalid device info\n",
+			UCAN_DRIVER_NAME);
+		goto err_firmware_needs_update;
+	}
+	if (ctl_msg_buffer->cmd_get_device_info.tx_fifo == 0) {
+		dev_err(&udev->dev,
+			"%s: device reported invalid tx-fifo size\n",
+			UCAN_DRIVER_NAME);
+		goto err_firmware_needs_update;
+	}
+
+	/* Stage 3 - Driver Initialisation
+	 * -------------------------------
+	 *
+	 * Register device to Linux, prepare private structures and
+	 * reset the device.
+	 */
+
+	/* allocate driver resources */
+	netdev = alloc_candev(sizeof(struct ucan_priv),
+			      ctl_msg_buffer->cmd_get_device_info.tx_fifo);
+	if (!netdev) {
+		dev_err(&udev->dev,
+			"%s: cannot allocate candev\n", UCAN_DRIVER_NAME);
+		return -ENOMEM;
+	}
+
+	up = netdev_priv(netdev);
+
+	/* initialze data */
+	up->udev = udev;
+	up->intf = intf;
+	up->netdev = netdev;
+	up->intf_index = iface_desc->desc.bInterfaceNumber;
+	up->in_ep_addr = in_ep_addr;
+	up->out_ep_addr = out_ep_addr;
+	up->in_ep_size = in_ep_size;
+	up->ctl_msg_buffer = ctl_msg_buffer;
+	up->context_array = NULL;
+	up->available_tx_urbs = 0;
+
+	up->can.state = CAN_STATE_STOPPED;
+	up->can.bittiming_const = &up->device_info.bittiming_const;
+	up->can.do_set_bittiming = ucan_set_bittiming;
+	up->can.do_set_mode = &ucan_set_mode;
+	spin_lock_init(&up->context_lock);
+	spin_lock_init(&up->echo_skb_lock);
+	netdev->netdev_ops = &ucan_netdev_ops;
+
+	usb_set_intfdata(intf, up);
+	SET_NETDEV_DEV(netdev, &intf->dev);
+
+	/* parse device information
+	 * the data retrieved in Stage 2 is still available in
+	 * up->ctl_msg_buffer
+	 */
+	ucan_parse_device_info(up, &ctl_msg_buffer->cmd_get_device_info);
+
+	/* just print some device information - if available */
+	ret = ucan_device_request_in(up, UCAN_DEVICE_GET_FW_STRING, 0,
+				     sizeof(union ucan_ctl_payload));
+	if (ret > 0) {
+		/* copy string while ensuring zero terminiation */
+		strncpy(firmware_str, up->ctl_msg_buffer->raw,
+			sizeof(union ucan_ctl_payload));
+		firmware_str[sizeof(union ucan_ctl_payload)] = '\0';
+	} else {
+		strcpy(firmware_str, "unknown");
+	}
+
+	/* device is compatible, reset it */
+	ret = ucan_ctrl_command_out(up, UCAN_COMMAND_RESET, 0, 0);
+	if (ret < 0)
+		goto err_free_candev;
+
+	init_usb_anchor(&up->rx_urbs);
+	init_usb_anchor(&up->tx_urbs);
+
+	up->can.state = CAN_STATE_STOPPED;
+
+	/* register the device */
+	ret = register_candev(netdev);
+	if (ret)
+		goto err_free_candev;
+
+	/* initialisation complete, log device info */
+	netdev_info(up->netdev, "registered device\n");
+	netdev_info(up->netdev, "firmware string: %s\n", firmware_str);
+
+	/* success */
+	return 0;
+
+err_free_candev:
+	free_candev(netdev);
+	return ret;
+
+err_firmware_needs_update:
+	dev_err(&udev->dev,
+		"%s: probe failed; try to update the device firmware\n",
+		UCAN_DRIVER_NAME);
+	return -ENODEV;
+}
+
+/* disconnect the device */
+static void ucan_disconnect(struct usb_interface *intf)
+{
+	struct usb_device *udev;
+	struct ucan_priv *up = usb_get_intfdata(intf);
+
+	udev = interface_to_usbdev(intf);
+
+	usb_set_intfdata(intf, NULL);
+
+	if (up) {
+		unregister_netdev(up->netdev);
+		free_candev(up->netdev);
+	}
+}
+
+static struct usb_device_id ucan_table[] = {
+	/* Mule (soldered onto compute modules) */
+	{USB_DEVICE_INTERFACE_NUMBER(0x2294, 0x425a, 0)},
+	/* Seal (standalone USB stick) */
+	{USB_DEVICE_INTERFACE_NUMBER(0x2294, 0x425b, 0)},
+	{} /* Terminating entry */
+};
+
+MODULE_DEVICE_TABLE(usb, ucan_table);
+/* driver callbacks */
+static struct usb_driver ucan_driver = {
+	.name = UCAN_DRIVER_NAME,
+	.probe = ucan_probe,
+	.disconnect = ucan_disconnect,
+	.id_table = ucan_table,
+};
+
+module_usb_driver(ucan_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Martin Elshuber <martin.elshuber@theobroma-systems.com>");
+MODULE_AUTHOR("Jakob Unterwurzacher <jakob.unterwurzacher@theobroma-systems.com>");
+MODULE_DESCRIPTION("Driver for Theobroma Systems UCAN devices");
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 5a24039733ef..045f0845e665 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -2,7 +2,7 @@
  *
  * Copyright (C) 2012 - 2014 Xilinx, Inc.
  * Copyright (C) 2009 PetaLogix. All rights reserved.
- * Copyright (C) 2017 Sandvik Mining and Construction Oy
+ * Copyright (C) 2017 - 2018 Sandvik Mining and Construction Oy
  *
  * Description:
  * This driver is developed for Axi CAN IP and for Zynq CANPS Controller.
@@ -51,16 +51,34 @@ enum xcan_reg {
 	XCAN_ISR_OFFSET		= 0x1C, /* Interrupt status */
 	XCAN_IER_OFFSET		= 0x20, /* Interrupt enable */
 	XCAN_ICR_OFFSET		= 0x24, /* Interrupt clear */
-	XCAN_TXFIFO_ID_OFFSET	= 0x30,/* TX FIFO ID */
-	XCAN_TXFIFO_DLC_OFFSET	= 0x34, /* TX FIFO DLC */
-	XCAN_TXFIFO_DW1_OFFSET	= 0x38, /* TX FIFO Data Word 1 */
-	XCAN_TXFIFO_DW2_OFFSET	= 0x3C, /* TX FIFO Data Word 2 */
-	XCAN_RXFIFO_ID_OFFSET	= 0x50, /* RX FIFO ID */
-	XCAN_RXFIFO_DLC_OFFSET	= 0x54, /* RX FIFO DLC */
-	XCAN_RXFIFO_DW1_OFFSET	= 0x58, /* RX FIFO Data Word 1 */
-	XCAN_RXFIFO_DW2_OFFSET	= 0x5C, /* RX FIFO Data Word 2 */
+
+	/* not on CAN FD cores */
+	XCAN_TXFIFO_OFFSET	= 0x30, /* TX FIFO base */
+	XCAN_RXFIFO_OFFSET	= 0x50, /* RX FIFO base */
+	XCAN_AFR_OFFSET		= 0x60, /* Acceptance Filter */
+
+	/* only on CAN FD cores */
+	XCAN_TRR_OFFSET		= 0x0090, /* TX Buffer Ready Request */
+	XCAN_AFR_EXT_OFFSET	= 0x00E0, /* Acceptance Filter */
+	XCAN_FSR_OFFSET		= 0x00E8, /* RX FIFO Status */
+	XCAN_TXMSG_BASE_OFFSET	= 0x0100, /* TX Message Space */
+	XCAN_RXMSG_BASE_OFFSET	= 0x1100, /* RX Message Space */
 };
 
+#define XCAN_FRAME_ID_OFFSET(frame_base)	((frame_base) + 0x00)
+#define XCAN_FRAME_DLC_OFFSET(frame_base)	((frame_base) + 0x04)
+#define XCAN_FRAME_DW1_OFFSET(frame_base)	((frame_base) + 0x08)
+#define XCAN_FRAME_DW2_OFFSET(frame_base)	((frame_base) + 0x0C)
+
+#define XCAN_CANFD_FRAME_SIZE		0x48
+#define XCAN_TXMSG_FRAME_OFFSET(n)	(XCAN_TXMSG_BASE_OFFSET + \
+					 XCAN_CANFD_FRAME_SIZE * (n))
+#define XCAN_RXMSG_FRAME_OFFSET(n)	(XCAN_RXMSG_BASE_OFFSET + \
+					 XCAN_CANFD_FRAME_SIZE * (n))
+
+/* the single TX mailbox used by this driver on CAN FD HW */
+#define XCAN_TX_MAILBOX_IDX		0
+
 /* CAN register bit masks - XCAN_<REG>_<BIT>_MASK */
 #define XCAN_SRR_CEN_MASK		0x00000002 /* CAN enable */
 #define XCAN_SRR_RESET_MASK		0x00000001 /* Soft Reset the CAN core */
@@ -70,6 +88,9 @@ enum xcan_reg {
 #define XCAN_BTR_SJW_MASK		0x00000180 /* Synchronous jump width */
 #define XCAN_BTR_TS2_MASK		0x00000070 /* Time segment 2 */
 #define XCAN_BTR_TS1_MASK		0x0000000F /* Time segment 1 */
+#define XCAN_BTR_SJW_MASK_CANFD		0x000F0000 /* Synchronous jump width */
+#define XCAN_BTR_TS2_MASK_CANFD		0x00000F00 /* Time segment 2 */
+#define XCAN_BTR_TS1_MASK_CANFD		0x0000003F /* Time segment 1 */
 #define XCAN_ECR_REC_MASK		0x0000FF00 /* Receive error counter */
 #define XCAN_ECR_TEC_MASK		0x000000FF /* Transmit error counter */
 #define XCAN_ESR_ACKER_MASK		0x00000010 /* ACK error */
@@ -83,6 +104,7 @@ enum xcan_reg {
 #define XCAN_SR_NORMAL_MASK		0x00000008 /* Normal mode */
 #define XCAN_SR_LBACK_MASK		0x00000002 /* Loop back mode */
 #define XCAN_SR_CONFIG_MASK		0x00000001 /* Configuration mode */
+#define XCAN_IXR_RXMNF_MASK		0x00020000 /* RX match not finished */
 #define XCAN_IXR_TXFEMP_MASK		0x00004000 /* TX FIFO Empty */
 #define XCAN_IXR_WKUP_MASK		0x00000800 /* Wake up interrupt */
 #define XCAN_IXR_SLP_MASK		0x00000400 /* Sleep interrupt */
@@ -100,15 +122,15 @@ enum xcan_reg {
 #define XCAN_IDR_ID2_MASK		0x0007FFFE /* Extended message ident */
 #define XCAN_IDR_RTR_MASK		0x00000001 /* Remote TX request */
 #define XCAN_DLCR_DLC_MASK		0xF0000000 /* Data length code */
-
-#define XCAN_INTR_ALL		(XCAN_IXR_TXOK_MASK | XCAN_IXR_BSOFF_MASK |\
-				 XCAN_IXR_WKUP_MASK | XCAN_IXR_SLP_MASK | \
-				 XCAN_IXR_RXNEMP_MASK | XCAN_IXR_ERROR_MASK | \
-				 XCAN_IXR_RXOFLW_MASK | XCAN_IXR_ARBLST_MASK)
+#define XCAN_FSR_FL_MASK		0x00003F00 /* RX Fill Level */
+#define XCAN_FSR_IRI_MASK		0x00000080 /* RX Increment Read Index */
+#define XCAN_FSR_RI_MASK		0x0000001F /* RX Read Index */
 
 /* CAN register bit shift - XCAN_<REG>_<BIT>_SHIFT */
 #define XCAN_BTR_SJW_SHIFT		7  /* Synchronous jump width */
 #define XCAN_BTR_TS2_SHIFT		4  /* Time segment 2 */
+#define XCAN_BTR_SJW_SHIFT_CANFD	16 /* Synchronous jump width */
+#define XCAN_BTR_TS2_SHIFT_CANFD	8  /* Time segment 2 */
 #define XCAN_IDR_ID1_SHIFT		21 /* Standard Messg Identifier */
 #define XCAN_IDR_ID2_SHIFT		1  /* Extended Message Identifier */
 #define XCAN_DLCR_DLC_SHIFT		28 /* Data length code */
@@ -118,6 +140,27 @@ enum xcan_reg {
 #define XCAN_FRAME_MAX_DATA_LEN		8
 #define XCAN_TIMEOUT			(1 * HZ)
 
+/* TX-FIFO-empty interrupt available */
+#define XCAN_FLAG_TXFEMP	0x0001
+/* RX Match Not Finished interrupt available */
+#define XCAN_FLAG_RXMNF		0x0002
+/* Extended acceptance filters with control at 0xE0 */
+#define XCAN_FLAG_EXT_FILTERS	0x0004
+/* TX mailboxes instead of TX FIFO */
+#define XCAN_FLAG_TX_MAILBOXES	0x0008
+/* RX FIFO with each buffer in separate registers at 0x1100
+ * instead of the regular FIFO at 0x50
+ */
+#define XCAN_FLAG_RX_FIFO_MULTI	0x0010
+
+struct xcan_devtype_data {
+	unsigned int flags;
+	const struct can_bittiming_const *bittiming_const;
+	const char *bus_clk_name;
+	unsigned int btr_ts2_shift;
+	unsigned int btr_sjw_shift;
+};
+
 /**
  * struct xcan_priv - This definition define CAN driver instance
  * @can:			CAN private data structure.
@@ -133,6 +176,7 @@ enum xcan_reg {
  * @irq_flags:			For request_irq()
  * @bus_clk:			Pointer to struct clk
  * @can_clk:			Pointer to struct clk
+ * @devtype:			Device type specific constants
  */
 struct xcan_priv {
 	struct can_priv can;
@@ -149,6 +193,7 @@ struct xcan_priv {
 	unsigned long irq_flags;
 	struct clk *bus_clk;
 	struct clk *can_clk;
+	struct xcan_devtype_data devtype;
 };
 
 /* CAN Bittiming constants as per Xilinx CAN specs */
@@ -164,9 +209,16 @@ static const struct can_bittiming_const xcan_bittiming_const = {
 	.brp_inc = 1,
 };
 
-#define XCAN_CAP_WATERMARK	0x0001
-struct xcan_devtype_data {
-	unsigned int caps;
+static const struct can_bittiming_const xcan_bittiming_const_canfd = {
+	.name = DRIVER_NAME,
+	.tseg1_min = 1,
+	.tseg1_max = 64,
+	.tseg2_min = 1,
+	.tseg2_max = 16,
+	.sjw_max = 16,
+	.brp_min = 1,
+	.brp_max = 256,
+	.brp_inc = 1,
 };
 
 /**
@@ -224,6 +276,23 @@ static u32 xcan_read_reg_be(const struct xcan_priv *priv, enum xcan_reg reg)
 }
 
 /**
+ * xcan_rx_int_mask - Get the mask for the receive interrupt
+ * @priv:	Driver private data structure
+ *
+ * Return: The receive interrupt mask used by the driver on this HW
+ */
+static u32 xcan_rx_int_mask(const struct xcan_priv *priv)
+{
+	/* RXNEMP is better suited for our use case as it cannot be cleared
+	 * while the FIFO is non-empty, but CAN FD HW does not have it
+	 */
+	if (priv->devtype.flags & XCAN_FLAG_RX_FIFO_MULTI)
+		return XCAN_IXR_RXOK_MASK;
+	else
+		return XCAN_IXR_RXNEMP_MASK;
+}
+
+/**
  * set_reset_mode - Resets the CAN device mode
  * @ndev:	Pointer to net_device structure
  *
@@ -287,10 +356,10 @@ static int xcan_set_bittiming(struct net_device *ndev)
 	btr1 = (bt->prop_seg + bt->phase_seg1 - 1);
 
 	/* Setting Time Segment 2 in BTR Register */
-	btr1 |= (bt->phase_seg2 - 1) << XCAN_BTR_TS2_SHIFT;
+	btr1 |= (bt->phase_seg2 - 1) << priv->devtype.btr_ts2_shift;
 
 	/* Setting Synchronous jump width in BTR Register */
-	btr1 |= (bt->sjw - 1) << XCAN_BTR_SJW_SHIFT;
+	btr1 |= (bt->sjw - 1) << priv->devtype.btr_sjw_shift;
 
 	priv->write_reg(priv, XCAN_BRPR_OFFSET, btr0);
 	priv->write_reg(priv, XCAN_BTR_OFFSET, btr1);
@@ -318,6 +387,7 @@ static int xcan_chip_start(struct net_device *ndev)
 	u32 reg_msr, reg_sr_mask;
 	int err;
 	unsigned long timeout;
+	u32 ier;
 
 	/* Check if it is in reset mode */
 	err = set_reset_mode(ndev);
@@ -329,7 +399,15 @@ static int xcan_chip_start(struct net_device *ndev)
 		return err;
 
 	/* Enable interrupts */
-	priv->write_reg(priv, XCAN_IER_OFFSET, XCAN_INTR_ALL);
+	ier = XCAN_IXR_TXOK_MASK | XCAN_IXR_BSOFF_MASK |
+		XCAN_IXR_WKUP_MASK | XCAN_IXR_SLP_MASK |
+		XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK |
+		XCAN_IXR_ARBLST_MASK | xcan_rx_int_mask(priv);
+
+	if (priv->devtype.flags & XCAN_FLAG_RXMNF)
+		ier |= XCAN_IXR_RXMNF_MASK;
+
+	priv->write_reg(priv, XCAN_IER_OFFSET, ier);
 
 	/* Check whether it is loopback mode or normal mode  */
 	if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK) {
@@ -340,6 +418,12 @@ static int xcan_chip_start(struct net_device *ndev)
 		reg_sr_mask = XCAN_SR_NORMAL_MASK;
 	}
 
+	/* enable the first extended filter, if any, as cores with extended
+	 * filtering default to non-receipt if all filters are disabled
+	 */
+	if (priv->devtype.flags & XCAN_FLAG_EXT_FILTERS)
+		priv->write_reg(priv, XCAN_AFR_EXT_OFFSET, 0x00000001);
+
 	priv->write_reg(priv, XCAN_MSR_OFFSET, reg_msr);
 	priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_CEN_MASK);
 
@@ -390,34 +474,15 @@ static int xcan_do_set_mode(struct net_device *ndev, enum can_mode mode)
 }
 
 /**
- * xcan_start_xmit - Starts the transmission
- * @skb:	sk_buff pointer that contains data to be Txed
- * @ndev:	Pointer to net_device structure
- *
- * This function is invoked from upper layers to initiate transmission. This
- * function uses the next available free txbuff and populates their fields to
- * start the transmission.
- *
- * Return: 0 on success and failure value on error
+ * xcan_write_frame - Write a frame to HW
+ * @skb:		sk_buff pointer that contains data to be Txed
+ * @frame_offset:	Register offset to write the frame to
  */
-static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+static void xcan_write_frame(struct xcan_priv *priv, struct sk_buff *skb,
+			     int frame_offset)
 {
-	struct xcan_priv *priv = netdev_priv(ndev);
-	struct net_device_stats *stats = &ndev->stats;
-	struct can_frame *cf = (struct can_frame *)skb->data;
 	u32 id, dlc, data[2] = {0, 0};
-	unsigned long flags;
-
-	if (can_dropped_invalid_skb(ndev, skb))
-		return NETDEV_TX_OK;
-
-	/* Check if the TX buffer is full */
-	if (unlikely(priv->read_reg(priv, XCAN_SR_OFFSET) &
-			XCAN_SR_TXFLL_MASK)) {
-		netif_stop_queue(ndev);
-		netdev_err(ndev, "BUG!, TX FIFO full when queue awake!\n");
-		return NETDEV_TX_BUSY;
-	}
+	struct can_frame *cf = (struct can_frame *)skb->data;
 
 	/* Watch carefully on the bit sequence */
 	if (cf->can_id & CAN_EFF_FLAG) {
@@ -453,24 +518,44 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	if (cf->can_dlc > 4)
 		data[1] = be32_to_cpup((__be32 *)(cf->data + 4));
 
+	priv->write_reg(priv, XCAN_FRAME_ID_OFFSET(frame_offset), id);
+	/* If the CAN frame is RTR frame this write triggers transmission
+	 * (not on CAN FD)
+	 */
+	priv->write_reg(priv, XCAN_FRAME_DLC_OFFSET(frame_offset), dlc);
+	if (!(cf->can_id & CAN_RTR_FLAG)) {
+		priv->write_reg(priv, XCAN_FRAME_DW1_OFFSET(frame_offset),
+				data[0]);
+		/* If the CAN frame is Standard/Extended frame this
+		 * write triggers transmission (not on CAN FD)
+		 */
+		priv->write_reg(priv, XCAN_FRAME_DW2_OFFSET(frame_offset),
+				data[1]);
+	}
+}
+
+/**
+ * xcan_start_xmit_fifo - Starts the transmission (FIFO mode)
+ *
+ * Return: 0 on success, -ENOSPC if FIFO is full.
+ */
+static int xcan_start_xmit_fifo(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	unsigned long flags;
+
+	/* Check if the TX buffer is full */
+	if (unlikely(priv->read_reg(priv, XCAN_SR_OFFSET) &
+			XCAN_SR_TXFLL_MASK))
+		return -ENOSPC;
+
 	can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max);
 
 	spin_lock_irqsave(&priv->tx_lock, flags);
 
 	priv->tx_head++;
 
-	/* Write the Frame to Xilinx CAN TX FIFO */
-	priv->write_reg(priv, XCAN_TXFIFO_ID_OFFSET, id);
-	/* If the CAN frame is RTR frame this write triggers tranmission */
-	priv->write_reg(priv, XCAN_TXFIFO_DLC_OFFSET, dlc);
-	if (!(cf->can_id & CAN_RTR_FLAG)) {
-		priv->write_reg(priv, XCAN_TXFIFO_DW1_OFFSET, data[0]);
-		/* If the CAN frame is Standard/Extended frame this
-		 * write triggers tranmission
-		 */
-		priv->write_reg(priv, XCAN_TXFIFO_DW2_OFFSET, data[1]);
-		stats->tx_bytes += cf->can_dlc;
-	}
+	xcan_write_frame(priv, skb, XCAN_TXFIFO_OFFSET);
 
 	/* Clear TX-FIFO-empty interrupt for xcan_tx_interrupt() */
 	if (priv->tx_max > 1)
@@ -482,6 +567,70 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 
 	spin_unlock_irqrestore(&priv->tx_lock, flags);
 
+	return 0;
+}
+
+/**
+ * xcan_start_xmit_mailbox - Starts the transmission (mailbox mode)
+ *
+ * Return: 0 on success, -ENOSPC if there is no space
+ */
+static int xcan_start_xmit_mailbox(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	unsigned long flags;
+
+	if (unlikely(priv->read_reg(priv, XCAN_TRR_OFFSET) &
+		     BIT(XCAN_TX_MAILBOX_IDX)))
+		return -ENOSPC;
+
+	can_put_echo_skb(skb, ndev, 0);
+
+	spin_lock_irqsave(&priv->tx_lock, flags);
+
+	priv->tx_head++;
+
+	xcan_write_frame(priv, skb,
+			 XCAN_TXMSG_FRAME_OFFSET(XCAN_TX_MAILBOX_IDX));
+
+	/* Mark buffer as ready for transmit */
+	priv->write_reg(priv, XCAN_TRR_OFFSET, BIT(XCAN_TX_MAILBOX_IDX));
+
+	netif_stop_queue(ndev);
+
+	spin_unlock_irqrestore(&priv->tx_lock, flags);
+
+	return 0;
+}
+
+/**
+ * xcan_start_xmit - Starts the transmission
+ * @skb:	sk_buff pointer that contains data to be Txed
+ * @ndev:	Pointer to net_device structure
+ *
+ * This function is invoked from upper layers to initiate transmission.
+ *
+ * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY when the tx queue is full
+ */
+static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	int ret;
+
+	if (can_dropped_invalid_skb(ndev, skb))
+		return NETDEV_TX_OK;
+
+	if (priv->devtype.flags & XCAN_FLAG_TX_MAILBOXES)
+		ret = xcan_start_xmit_mailbox(skb, ndev);
+	else
+		ret = xcan_start_xmit_fifo(skb, ndev);
+
+	if (ret < 0) {
+		netdev_err(ndev, "BUG!, TX full when queue awake!\n");
+		netif_stop_queue(ndev);
+		return NETDEV_TX_BUSY;
+	}
+
 	return NETDEV_TX_OK;
 }
 
@@ -489,13 +638,14 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
  * xcan_rx -  Is called from CAN isr to complete the received
  *		frame  processing
  * @ndev:	Pointer to net_device structure
+ * @frame_base:	Register offset to the frame to be read
  *
  * This function is invoked from the CAN isr(poll) to process the Rx frames. It
  * does minimal processing and invokes "netif_receive_skb" to complete further
  * processing.
  * Return: 1 on success and 0 on failure.
  */
-static int xcan_rx(struct net_device *ndev)
+static int xcan_rx(struct net_device *ndev, int frame_base)
 {
 	struct xcan_priv *priv = netdev_priv(ndev);
 	struct net_device_stats *stats = &ndev->stats;
@@ -510,9 +660,9 @@ static int xcan_rx(struct net_device *ndev)
 	}
 
 	/* Read a frame from Xilinx zynq CANPS */
-	id_xcan = priv->read_reg(priv, XCAN_RXFIFO_ID_OFFSET);
-	dlc = priv->read_reg(priv, XCAN_RXFIFO_DLC_OFFSET) >>
-				XCAN_DLCR_DLC_SHIFT;
+	id_xcan = priv->read_reg(priv, XCAN_FRAME_ID_OFFSET(frame_base));
+	dlc = priv->read_reg(priv, XCAN_FRAME_DLC_OFFSET(frame_base)) >>
+				   XCAN_DLCR_DLC_SHIFT;
 
 	/* Change Xilinx CAN data length format to socketCAN data format */
 	cf->can_dlc = get_can_dlc(dlc);
@@ -535,8 +685,8 @@ static int xcan_rx(struct net_device *ndev)
 	}
 
 	/* DW1/DW2 must always be read to remove message from RXFIFO */
-	data[0] = priv->read_reg(priv, XCAN_RXFIFO_DW1_OFFSET);
-	data[1] = priv->read_reg(priv, XCAN_RXFIFO_DW2_OFFSET);
+	data[0] = priv->read_reg(priv, XCAN_FRAME_DW1_OFFSET(frame_base));
+	data[1] = priv->read_reg(priv, XCAN_FRAME_DW2_OFFSET(frame_base));
 
 	if (!(cf->can_id & CAN_RTR_FLAG)) {
 		/* Change Xilinx CAN data format to socketCAN data format */
@@ -594,39 +744,19 @@ static void xcan_set_error_state(struct net_device *ndev,
 	u32 ecr = priv->read_reg(priv, XCAN_ECR_OFFSET);
 	u32 txerr = ecr & XCAN_ECR_TEC_MASK;
 	u32 rxerr = (ecr & XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT;
+	enum can_state tx_state = txerr >= rxerr ? new_state : 0;
+	enum can_state rx_state = txerr <= rxerr ? new_state : 0;
+
+	/* non-ERROR states are handled elsewhere */
+	if (WARN_ON(new_state > CAN_STATE_ERROR_PASSIVE))
+		return;
 
-	priv->can.state = new_state;
+	can_change_state(ndev, cf, tx_state, rx_state);
 
 	if (cf) {
-		cf->can_id |= CAN_ERR_CRTL;
 		cf->data[6] = txerr;
 		cf->data[7] = rxerr;
 	}
-
-	switch (new_state) {
-	case CAN_STATE_ERROR_PASSIVE:
-		priv->can.can_stats.error_passive++;
-		if (cf)
-			cf->data[1] = (rxerr > 127) ?
-					CAN_ERR_CRTL_RX_PASSIVE :
-					CAN_ERR_CRTL_TX_PASSIVE;
-		break;
-	case CAN_STATE_ERROR_WARNING:
-		priv->can.can_stats.error_warning++;
-		if (cf)
-			cf->data[1] |= (txerr > rxerr) ?
-					CAN_ERR_CRTL_TX_WARNING :
-					CAN_ERR_CRTL_RX_WARNING;
-		break;
-	case CAN_STATE_ERROR_ACTIVE:
-		if (cf)
-			cf->data[1] |= CAN_ERR_CRTL_ACTIVE;
-		break;
-	default:
-		/* non-ERROR states are handled elsewhere */
-		WARN_ON(1);
-		break;
-	}
 }
 
 /**
@@ -703,7 +833,8 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
 	} else {
 		enum can_state new_state = xcan_current_error_state(ndev);
 
-		xcan_set_error_state(ndev, new_state, skb ? cf : NULL);
+		if (new_state != priv->can.state)
+			xcan_set_error_state(ndev, new_state, skb ? cf : NULL);
 	}
 
 	/* Check for Arbitration lost interrupt */
@@ -725,6 +856,17 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
 		}
 	}
 
+	/* Check for RX Match Not Finished interrupt */
+	if (isr & XCAN_IXR_RXMNF_MASK) {
+		stats->rx_dropped++;
+		stats->rx_errors++;
+		netdev_err(ndev, "RX match not finished, frame discarded\n");
+		if (skb) {
+			cf->can_id |= CAN_ERR_CRTL;
+			cf->data[1] |= CAN_ERR_CRTL_UNSPEC;
+		}
+	}
+
 	/* Check for error interrupt */
 	if (isr & XCAN_IXR_ERROR_MASK) {
 		if (skb)
@@ -809,6 +951,44 @@ static void xcan_state_interrupt(struct net_device *ndev, u32 isr)
 }
 
 /**
+ * xcan_rx_fifo_get_next_frame - Get register offset of next RX frame
+ *
+ * Return: Register offset of the next frame in RX FIFO.
+ */
+static int xcan_rx_fifo_get_next_frame(struct xcan_priv *priv)
+{
+	int offset;
+
+	if (priv->devtype.flags & XCAN_FLAG_RX_FIFO_MULTI) {
+		u32 fsr;
+
+		/* clear RXOK before the is-empty check so that any newly
+		 * received frame will reassert it without a race
+		 */
+		priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_RXOK_MASK);
+
+		fsr = priv->read_reg(priv, XCAN_FSR_OFFSET);
+
+		/* check if RX FIFO is empty */
+		if (!(fsr & XCAN_FSR_FL_MASK))
+			return -ENOENT;
+
+		offset = XCAN_RXMSG_FRAME_OFFSET(fsr & XCAN_FSR_RI_MASK);
+
+	} else {
+		/* check if RX FIFO is empty */
+		if (!(priv->read_reg(priv, XCAN_ISR_OFFSET) &
+		      XCAN_IXR_RXNEMP_MASK))
+			return -ENOENT;
+
+		/* frames are read from a static offset */
+		offset = XCAN_RXFIFO_OFFSET;
+	}
+
+	return offset;
+}
+
+/**
  * xcan_rx_poll - Poll routine for rx packets (NAPI)
  * @napi:	napi structure pointer
  * @quota:	Max number of rx packets to be processed.
@@ -822,14 +1002,24 @@ static int xcan_rx_poll(struct napi_struct *napi, int quota)
 {
 	struct net_device *ndev = napi->dev;
 	struct xcan_priv *priv = netdev_priv(ndev);
-	u32 isr, ier;
+	u32 ier;
 	int work_done = 0;
-
-	isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
-	while ((isr & XCAN_IXR_RXNEMP_MASK) && (work_done < quota)) {
-		work_done += xcan_rx(ndev);
-		priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_RXNEMP_MASK);
-		isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
+	int frame_offset;
+
+	while ((frame_offset = xcan_rx_fifo_get_next_frame(priv)) >= 0 &&
+	       (work_done < quota)) {
+		work_done += xcan_rx(ndev, frame_offset);
+
+		if (priv->devtype.flags & XCAN_FLAG_RX_FIFO_MULTI)
+			/* increment read index */
+			priv->write_reg(priv, XCAN_FSR_OFFSET,
+					XCAN_FSR_IRI_MASK);
+		else
+			/* clear rx-not-empty (will actually clear only if
+			 * empty)
+			 */
+			priv->write_reg(priv, XCAN_ICR_OFFSET,
+					XCAN_IXR_RXNEMP_MASK);
 	}
 
 	if (work_done) {
@@ -840,7 +1030,7 @@ static int xcan_rx_poll(struct napi_struct *napi, int quota)
 	if (work_done < quota) {
 		napi_complete_done(napi, work_done);
 		ier = priv->read_reg(priv, XCAN_IER_OFFSET);
-		ier |= XCAN_IXR_RXNEMP_MASK;
+		ier |= xcan_rx_int_mask(priv);
 		priv->write_reg(priv, XCAN_IER_OFFSET, ier);
 	}
 	return work_done;
@@ -908,8 +1098,8 @@ static void xcan_tx_interrupt(struct net_device *ndev, u32 isr)
 	}
 
 	while (frames_sent--) {
-		can_get_echo_skb(ndev, priv->tx_tail %
-					priv->tx_max);
+		stats->tx_bytes += can_get_echo_skb(ndev, priv->tx_tail %
+						    priv->tx_max);
 		priv->tx_tail++;
 		stats->tx_packets++;
 	}
@@ -939,6 +1129,7 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id)
 	struct xcan_priv *priv = netdev_priv(ndev);
 	u32 isr, ier;
 	u32 isr_errors;
+	u32 rx_int_mask = xcan_rx_int_mask(priv);
 
 	/* Get the interrupt status from Xilinx CAN */
 	isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
@@ -958,16 +1149,17 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id)
 
 	/* Check for the type of error interrupt and Processing it */
 	isr_errors = isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK |
-			    XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK);
+			    XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK |
+			    XCAN_IXR_RXMNF_MASK);
 	if (isr_errors) {
 		priv->write_reg(priv, XCAN_ICR_OFFSET, isr_errors);
 		xcan_err_interrupt(ndev, isr);
 	}
 
 	/* Check for the type of receive interrupt and Processing it */
-	if (isr & XCAN_IXR_RXNEMP_MASK) {
+	if (isr & rx_int_mask) {
 		ier = priv->read_reg(priv, XCAN_IER_OFFSET);
-		ier &= ~XCAN_IXR_RXNEMP_MASK;
+		ier &= ~rx_int_mask;
 		priv->write_reg(priv, XCAN_IER_OFFSET, ier);
 		napi_schedule(&priv->napi);
 	}
@@ -1214,13 +1406,35 @@ static const struct dev_pm_ops xcan_dev_pm_ops = {
 };
 
 static const struct xcan_devtype_data xcan_zynq_data = {
-	.caps = XCAN_CAP_WATERMARK,
+	.bittiming_const = &xcan_bittiming_const,
+	.btr_ts2_shift = XCAN_BTR_TS2_SHIFT,
+	.btr_sjw_shift = XCAN_BTR_SJW_SHIFT,
+	.bus_clk_name = "pclk",
+};
+
+static const struct xcan_devtype_data xcan_axi_data = {
+	.bittiming_const = &xcan_bittiming_const,
+	.btr_ts2_shift = XCAN_BTR_TS2_SHIFT,
+	.btr_sjw_shift = XCAN_BTR_SJW_SHIFT,
+	.bus_clk_name = "s_axi_aclk",
+};
+
+static const struct xcan_devtype_data xcan_canfd_data = {
+	.flags = XCAN_FLAG_EXT_FILTERS |
+		 XCAN_FLAG_RXMNF |
+		 XCAN_FLAG_TX_MAILBOXES |
+		 XCAN_FLAG_RX_FIFO_MULTI,
+	.bittiming_const = &xcan_bittiming_const,
+	.btr_ts2_shift = XCAN_BTR_TS2_SHIFT_CANFD,
+	.btr_sjw_shift = XCAN_BTR_SJW_SHIFT_CANFD,
+	.bus_clk_name = "s_axi_aclk",
 };
 
 /* Match table for OF platform binding */
 static const struct of_device_id xcan_of_match[] = {
 	{ .compatible = "xlnx,zynq-can-1.0", .data = &xcan_zynq_data },
-	{ .compatible = "xlnx,axi-can-1.00.a", },
+	{ .compatible = "xlnx,axi-can-1.00.a", .data = &xcan_axi_data },
+	{ .compatible = "xlnx,canfd-1.0", .data = &xcan_canfd_data },
 	{ /* end of list */ },
 };
 MODULE_DEVICE_TABLE(of, xcan_of_match);
@@ -1240,9 +1454,12 @@ static int xcan_probe(struct platform_device *pdev)
 	struct net_device *ndev;
 	struct xcan_priv *priv;
 	const struct of_device_id *of_id;
-	int caps = 0;
+	const struct xcan_devtype_data *devtype = &xcan_axi_data;
 	void __iomem *addr;
-	int ret, rx_max, tx_max, tx_fifo_depth;
+	int ret;
+	int rx_max, tx_max;
+	int hw_tx_max, hw_rx_max;
+	const char *hw_tx_max_property;
 
 	/* Get the virtual base address for the device */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -1252,25 +1469,33 @@ static int xcan_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth",
-				   &tx_fifo_depth);
-	if (ret < 0)
-		goto err;
+	of_id = of_match_device(xcan_of_match, &pdev->dev);
+	if (of_id && of_id->data)
+		devtype = of_id->data;
 
-	ret = of_property_read_u32(pdev->dev.of_node, "rx-fifo-depth", &rx_max);
-	if (ret < 0)
-		goto err;
+	hw_tx_max_property = devtype->flags & XCAN_FLAG_TX_MAILBOXES ?
+			     "tx-mailbox-count" : "tx-fifo-depth";
 
-	of_id = of_match_device(xcan_of_match, &pdev->dev);
-	if (of_id) {
-		const struct xcan_devtype_data *devtype_data = of_id->data;
+	ret = of_property_read_u32(pdev->dev.of_node, hw_tx_max_property,
+				   &hw_tx_max);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "missing %s property\n",
+			hw_tx_max_property);
+		goto err;
+	}
 
-		if (devtype_data)
-			caps = devtype_data->caps;
+	ret = of_property_read_u32(pdev->dev.of_node, "rx-fifo-depth",
+				   &hw_rx_max);
+	if (ret < 0) {
+		dev_err(&pdev->dev,
+			"missing rx-fifo-depth property (mailbox mode is not supported)\n");
+		goto err;
 	}
 
-	/* There is no way to directly figure out how many frames have been
-	 * sent when the TXOK interrupt is processed. If watermark programming
+	/* With TX FIFO:
+	 *
+	 * There is no way to directly figure out how many frames have been
+	 * sent when the TXOK interrupt is processed. If TXFEMP
 	 * is supported, we can have 2 frames in the FIFO and use TXFEMP
 	 * to determine if 1 or 2 frames have been sent.
 	 * Theoretically we should be able to use TXFWMEMP to determine up
@@ -1279,12 +1504,20 @@ static int xcan_probe(struct platform_device *pdev)
 	 * than 2 frames in FIFO) is set anyway with no TXOK (a frame was
 	 * sent), which is not a sensible state - possibly TXFWMEMP is not
 	 * completely synchronized with the rest of the bits?
+	 *
+	 * With TX mailboxes:
+	 *
+	 * HW sends frames in CAN ID priority order. To preserve FIFO ordering
+	 * we submit frames one at a time.
 	 */
-	if (caps & XCAN_CAP_WATERMARK)
-		tx_max = min(tx_fifo_depth, 2);
+	if (!(devtype->flags & XCAN_FLAG_TX_MAILBOXES) &&
+	    (devtype->flags & XCAN_FLAG_TXFEMP))
+		tx_max = min(hw_tx_max, 2);
 	else
 		tx_max = 1;
 
+	rx_max = hw_rx_max;
+
 	/* Create a CAN device instance */
 	ndev = alloc_candev(sizeof(struct xcan_priv), tx_max);
 	if (!ndev)
@@ -1292,13 +1525,14 @@ static int xcan_probe(struct platform_device *pdev)
 
 	priv = netdev_priv(ndev);
 	priv->dev = &pdev->dev;
-	priv->can.bittiming_const = &xcan_bittiming_const;
+	priv->can.bittiming_const = devtype->bittiming_const;
 	priv->can.do_set_mode = xcan_do_set_mode;
 	priv->can.do_get_berr_counter = xcan_get_berr_counter;
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
 					CAN_CTRLMODE_BERR_REPORTING;
 	priv->reg_base = addr;
 	priv->tx_max = tx_max;
+	priv->devtype = *devtype;
 	spin_lock_init(&priv->tx_lock);
 
 	/* Get IRQ for the device */
@@ -1316,22 +1550,12 @@ static int xcan_probe(struct platform_device *pdev)
 		ret = PTR_ERR(priv->can_clk);
 		goto err_free;
 	}
-	/* Check for type of CAN device */
-	if (of_device_is_compatible(pdev->dev.of_node,
-				    "xlnx,zynq-can-1.0")) {
-		priv->bus_clk = devm_clk_get(&pdev->dev, "pclk");
-		if (IS_ERR(priv->bus_clk)) {
-			dev_err(&pdev->dev, "bus clock not found\n");
-			ret = PTR_ERR(priv->bus_clk);
-			goto err_free;
-		}
-	} else {
-		priv->bus_clk = devm_clk_get(&pdev->dev, "s_axi_aclk");
-		if (IS_ERR(priv->bus_clk)) {
-			dev_err(&pdev->dev, "bus clock not found\n");
-			ret = PTR_ERR(priv->bus_clk);
-			goto err_free;
-		}
+
+	priv->bus_clk = devm_clk_get(&pdev->dev, devtype->bus_clk_name);
+	if (IS_ERR(priv->bus_clk)) {
+		dev_err(&pdev->dev, "bus clock not found\n");
+		ret = PTR_ERR(priv->bus_clk);
+		goto err_free;
 	}
 
 	priv->write_reg = xcan_write_reg_le;
@@ -1364,9 +1588,9 @@ static int xcan_probe(struct platform_device *pdev)
 
 	pm_runtime_put(&pdev->dev);
 
-	netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth: actual %d, using %d\n",
-			priv->reg_base, ndev->irq, priv->can.clock.freq,
-			tx_fifo_depth, priv->tx_max);
+	netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx buffers: actual %d, using %d\n",
+		   priv->reg_base, ndev->irq, priv->can.clock.freq,
+		   hw_tx_max, priv->tx_max);
 
 	return 0;
 
diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index 2b81b97e994f..d3ce1e4cb4d3 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -5,7 +5,7 @@ source "drivers/net/dsa/b53/Kconfig"
 
 config NET_DSA_BCM_SF2
 	tristate "Broadcom Starfighter 2 Ethernet switch support"
-	depends on HAS_IOMEM && NET_DSA && OF_MDIO
+	depends on HAS_IOMEM && NET_DSA
 	select NET_DSA_TAG_BRCM
 	select FIXED_PHY
 	select BCM7XXX_PHY
@@ -52,6 +52,17 @@ config NET_DSA_QCA8K
 	  This enables support for the Qualcomm Atheros QCA8K Ethernet
 	  switch chips.
 
+config NET_DSA_REALTEK_SMI
+	tristate "Realtek SMI Ethernet switch family support"
+	depends on NET_DSA
+	select FIXED_PHY
+	select IRQ_DOMAIN
+	select REALTEK_PHY
+	select REGMAP
+	---help---
+	  This enables support for the Realtek SMI-based switch
+	  chips, currently only RTL8366RB.
+
 config NET_DSA_SMSC_LAN9303
 	tristate
 	select NET_DSA_TAG_LAN9303
@@ -76,4 +87,15 @@ config NET_DSA_SMSC_LAN9303_MDIO
 	  Enable access functions if the SMSC/Microchip LAN9303 is configured
 	  for MDIO managed mode.
 
+config NET_DSA_VITESSE_VSC73XX
+	tristate "Vitesse VSC7385/7388/7395/7398 support"
+	depends on OF && SPI
+	depends on NET_DSA
+	select FIXED_PHY
+	select VITESSE_PHY
+	select GPIOLIB
+	---help---
+	  This enables support for the Vitesse VSC7385, VSC7388,
+	  VSC7395 and VSC7398 SparX integrated ethernet switches.
+
 endmenu
diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile
index 15c2a831edf1..46c1cba91ffe 100644
--- a/drivers/net/dsa/Makefile
+++ b/drivers/net/dsa/Makefile
@@ -8,9 +8,12 @@ endif
 obj-$(CONFIG_NET_DSA_MT7530)	+= mt7530.o
 obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o
 obj-$(CONFIG_NET_DSA_QCA8K)	+= qca8k.o
+obj-$(CONFIG_NET_DSA_REALTEK_SMI) += realtek.o
+realtek-objs			:= realtek-smi.o rtl8366.o rtl8366rb.o
 obj-$(CONFIG_NET_DSA_SMSC_LAN9303) += lan9303-core.o
 obj-$(CONFIG_NET_DSA_SMSC_LAN9303_I2C) += lan9303_i2c.o
 obj-$(CONFIG_NET_DSA_SMSC_LAN9303_MDIO) += lan9303_mdio.o
+obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX) += vitesse-vsc73xx.o
 obj-y				+= b53/
 obj-y				+= microchip/
 obj-y				+= mv88e6xxx/
diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c
index 8247481eaa06..91de2ba99ad1 100644
--- a/drivers/net/dsa/b53/b53_srab.c
+++ b/drivers/net/dsa/b53/b53_srab.c
@@ -374,6 +374,7 @@ static const struct of_device_id b53_srab_of_match[] = {
 	{ .compatible = "brcm,bcm88312-srab", .data = (void *)BCM58XX_DEVICE_ID },
 	{ .compatible = "brcm,cygnus-srab", .data = (void *)BCM583XX_DEVICE_ID },
 	{ .compatible = "brcm,nsp-srab", .data = (void *)BCM58XX_DEVICE_ID },
+	{ .compatible = "brcm,omega-srab", .data = (void *)BCM583XX_DEVICE_ID },
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, b53_srab_of_match);
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 02e8982519ce..e0066adcd2f3 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -166,6 +166,11 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port,
 	reg &= ~P_TXQ_PSM_VDD(port);
 	core_writel(priv, reg, CORE_MEM_PSM_VDD_CTRL);
 
+	/* Enable learning */
+	reg = core_readl(priv, CORE_DIS_LEARN);
+	reg &= ~BIT(port);
+	core_writel(priv, reg, CORE_DIS_LEARN);
+
 	/* Enable Broadcom tags for that port if requested */
 	if (priv->brcm_tag_mask & BIT(port))
 		b53_brcm_hdr_setup(ds, port);
@@ -220,10 +225,15 @@ static void bcm_sf2_port_disable(struct dsa_switch *ds, int port,
 				 struct phy_device *phy)
 {
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
-	u32 off, reg;
+	u32 reg;
 
-	if (priv->wol_ports_mask & (1 << port))
+	/* Disable learning while in WoL mode */
+	if (priv->wol_ports_mask & (1 << port)) {
+		reg = core_readl(priv, CORE_DIS_LEARN);
+		reg |= BIT(port);
+		core_writel(priv, reg, CORE_DIS_LEARN);
 		return;
+	}
 
 	if (port == priv->moca_port)
 		bcm_sf2_port_intr_disable(priv, port);
@@ -231,11 +241,6 @@ static void bcm_sf2_port_disable(struct dsa_switch *ds, int port,
 	if (priv->int_phy_mask & 1 << port && priv->hw_params.num_gphy == 1)
 		bcm_sf2_gphy_enable_set(ds, false);
 
-	if (dsa_is_cpu_port(ds, port))
-		off = CORE_IMP_CTL;
-	else
-		off = CORE_G_PCTL_PORT(port);
-
 	b53_disable_port(ds, port, phy);
 
 	/* Power down the port memory */
diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index b89acaee12d4..47c5f272a084 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -732,6 +732,8 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 				struct ethtool_rx_flow_spec *fs)
 {
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
+	s8 cpu_port = ds->ports[port].cpu_dp->index;
+	__u64 ring_cookie = fs->ring_cookie;
 	unsigned int queue_num, port_num;
 	int ret = -EINVAL;
 
@@ -748,21 +750,28 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 	    fs->location > bcm_sf2_cfp_rule_size(priv))
 		return -EINVAL;
 
+	/* This rule is a Wake-on-LAN filter and we must specifically
+	 * target the CPU port in order for it to be working.
+	 */
+	if (ring_cookie == RX_CLS_FLOW_WAKE)
+		ring_cookie = cpu_port * SF2_NUM_EGRESS_QUEUES;
+
 	/* We do not support discarding packets, check that the
 	 * destination port is enabled and that we are within the
 	 * number of ports supported by the switch
 	 */
-	port_num = fs->ring_cookie / SF2_NUM_EGRESS_QUEUES;
+	port_num = ring_cookie / SF2_NUM_EGRESS_QUEUES;
 
-	if (fs->ring_cookie == RX_CLS_FLOW_DISC ||
-	    !dsa_is_user_port(ds, port_num) ||
+	if (ring_cookie == RX_CLS_FLOW_DISC ||
+	    !(dsa_is_user_port(ds, port_num) ||
+	      dsa_is_cpu_port(ds, port_num)) ||
 	    port_num >= priv->hw_params.num_ports)
 		return -EINVAL;
 	/*
 	 * We have a small oddity where Port 6 just does not have a
 	 * valid bit here (so we substract by one).
 	 */
-	queue_num = fs->ring_cookie % SF2_NUM_EGRESS_QUEUES;
+	queue_num = ring_cookie % SF2_NUM_EGRESS_QUEUES;
 	if (port_num >= 7)
 		port_num -= 1;
 
@@ -1187,6 +1196,7 @@ static int bcm_sf2_cfp_rule_get_all(struct bcm_sf2_priv *priv,
 int bcm_sf2_get_rxnfc(struct dsa_switch *ds, int port,
 		      struct ethtool_rxnfc *nfc, u32 *rule_locs)
 {
+	struct net_device *p = ds->ports[port].cpu_dp->master;
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
 	int ret = 0;
 
@@ -1213,12 +1223,23 @@ int bcm_sf2_get_rxnfc(struct dsa_switch *ds, int port,
 
 	mutex_unlock(&priv->cfp.lock);
 
+	if (ret)
+		return ret;
+
+	/* Pass up the commands to the attached master network device */
+	if (p->ethtool_ops->get_rxnfc) {
+		ret = p->ethtool_ops->get_rxnfc(p, nfc, rule_locs);
+		if (ret == -EOPNOTSUPP)
+			ret = 0;
+	}
+
 	return ret;
 }
 
 int bcm_sf2_set_rxnfc(struct dsa_switch *ds, int port,
 		      struct ethtool_rxnfc *nfc)
 {
+	struct net_device *p = ds->ports[port].cpu_dp->master;
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
 	int ret = 0;
 
@@ -1239,6 +1260,23 @@ int bcm_sf2_set_rxnfc(struct dsa_switch *ds, int port,
 
 	mutex_unlock(&priv->cfp.lock);
 
+	if (ret)
+		return ret;
+
+	/* Pass up the commands to the attached master network device.
+	 * This can fail, so rollback the operation if we need to.
+	 */
+	if (p->ethtool_ops->set_rxnfc) {
+		ret = p->ethtool_ops->set_rxnfc(p, nfc);
+		if (ret && ret != -EOPNOTSUPP) {
+			mutex_lock(&priv->cfp.lock);
+			bcm_sf2_cfp_rule_del(priv, port, nfc->fs.location);
+			mutex_unlock(&priv->cfp.lock);
+		} else {
+			ret = 0;
+		}
+	}
+
 	return ret;
 }
 
diff --git a/drivers/net/dsa/bcm_sf2_regs.h b/drivers/net/dsa/bcm_sf2_regs.h
index 3ccd5a865dcb..0a1e530d52b7 100644
--- a/drivers/net/dsa/bcm_sf2_regs.h
+++ b/drivers/net/dsa/bcm_sf2_regs.h
@@ -168,6 +168,8 @@ enum bcm_sf2_reg_offs {
 #define CORE_SWITCH_CTRL		0x00088
 #define  MII_DUMB_FWDG_EN		(1 << 6)
 
+#define CORE_DIS_LEARN			0x000f0
+
 #define CORE_SFT_LRN_CTRL		0x000f8
 #define  SW_LEARN_CNTL(x)		(1 << (x))
 
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index bb28c701381a..8da3d39e3218 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -524,7 +524,7 @@ int mv88e6xxx_update(struct mv88e6xxx_chip *chip, int addr, int reg, u16 update)
 }
 
 static int mv88e6xxx_port_setup_mac(struct mv88e6xxx_chip *chip, int port,
-				    int link, int speed, int duplex,
+				    int link, int speed, int duplex, int pause,
 				    phy_interface_t mode)
 {
 	int err;
@@ -543,6 +543,12 @@ static int mv88e6xxx_port_setup_mac(struct mv88e6xxx_chip *chip, int port,
 			goto restore_link;
 	}
 
+	if (chip->info->ops->port_set_pause) {
+		err = chip->info->ops->port_set_pause(chip, port, pause);
+		if (err)
+			goto restore_link;
+	}
+
 	if (chip->info->ops->port_set_duplex) {
 		err = chip->info->ops->port_set_duplex(chip, port, duplex);
 		if (err && err != -EOPNOTSUPP)
@@ -584,17 +590,100 @@ static void mv88e6xxx_adjust_link(struct dsa_switch *ds, int port,
 
 	mutex_lock(&chip->reg_lock);
 	err = mv88e6xxx_port_setup_mac(chip, port, phydev->link, phydev->speed,
-				       phydev->duplex, phydev->interface);
+				       phydev->duplex, phydev->pause,
+				       phydev->interface);
 	mutex_unlock(&chip->reg_lock);
 
 	if (err && err != -EOPNOTSUPP)
 		dev_err(ds->dev, "p%d: failed to configure MAC\n", port);
 }
 
+static void mv88e6065_phylink_validate(struct mv88e6xxx_chip *chip, int port,
+				       unsigned long *mask,
+				       struct phylink_link_state *state)
+{
+	if (!phy_interface_mode_is_8023z(state->interface)) {
+		/* 10M and 100M are only supported in non-802.3z mode */
+		phylink_set(mask, 10baseT_Half);
+		phylink_set(mask, 10baseT_Full);
+		phylink_set(mask, 100baseT_Half);
+		phylink_set(mask, 100baseT_Full);
+	}
+}
+
+static void mv88e6185_phylink_validate(struct mv88e6xxx_chip *chip, int port,
+				       unsigned long *mask,
+				       struct phylink_link_state *state)
+{
+	/* FIXME: if the port is in 1000Base-X mode, then it only supports
+	 * 1000M FD speeds.  In this case, CMODE will indicate 5.
+	 */
+	phylink_set(mask, 1000baseT_Full);
+	phylink_set(mask, 1000baseX_Full);
+
+	mv88e6065_phylink_validate(chip, port, mask, state);
+}
+
+static void mv88e6352_phylink_validate(struct mv88e6xxx_chip *chip, int port,
+				       unsigned long *mask,
+				       struct phylink_link_state *state)
+{
+	/* No ethtool bits for 200Mbps */
+	phylink_set(mask, 1000baseT_Full);
+	phylink_set(mask, 1000baseX_Full);
+
+	mv88e6065_phylink_validate(chip, port, mask, state);
+}
+
+static void mv88e6390_phylink_validate(struct mv88e6xxx_chip *chip, int port,
+				       unsigned long *mask,
+				       struct phylink_link_state *state)
+{
+	if (port >= 9)
+		phylink_set(mask, 2500baseX_Full);
+
+	/* No ethtool bits for 200Mbps */
+	phylink_set(mask, 1000baseT_Full);
+	phylink_set(mask, 1000baseX_Full);
+
+	mv88e6065_phylink_validate(chip, port, mask, state);
+}
+
+static void mv88e6390x_phylink_validate(struct mv88e6xxx_chip *chip, int port,
+					unsigned long *mask,
+					struct phylink_link_state *state)
+{
+	if (port >= 9) {
+		phylink_set(mask, 10000baseT_Full);
+		phylink_set(mask, 10000baseKR_Full);
+	}
+
+	mv88e6390_phylink_validate(chip, port, mask, state);
+}
+
 static void mv88e6xxx_validate(struct dsa_switch *ds, int port,
 			       unsigned long *supported,
 			       struct phylink_link_state *state)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
+	struct mv88e6xxx_chip *chip = ds->priv;
+
+	/* Allow all the expected bits */
+	phylink_set(mask, Autoneg);
+	phylink_set(mask, Pause);
+	phylink_set_port_modes(mask);
+
+	if (chip->info->ops->phylink_validate)
+		chip->info->ops->phylink_validate(chip, port, mask, state);
+
+	bitmap_and(supported, supported, mask, __ETHTOOL_LINK_MODE_MASK_NBITS);
+	bitmap_and(state->advertising, state->advertising, mask,
+		   __ETHTOOL_LINK_MODE_MASK_NBITS);
+
+	/* We can only operate at 2500BaseX or 1000BaseX.  If requested
+	 * to advertise both, only report advertising at 2500BaseX.
+	 */
+	phylink_helper_basex_speed(state);
 }
 
 static int mv88e6xxx_link_state(struct dsa_switch *ds, int port,
@@ -604,7 +693,10 @@ static int mv88e6xxx_link_state(struct dsa_switch *ds, int port,
 	int err;
 
 	mutex_lock(&chip->reg_lock);
-	err = mv88e6xxx_port_link_state(chip, port, state);
+	if (chip->info->ops->port_link_state)
+		err = chip->info->ops->port_link_state(chip, port, state);
+	else
+		err = -EOPNOTSUPP;
 	mutex_unlock(&chip->reg_lock);
 
 	return err;
@@ -615,7 +707,7 @@ static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port,
 				 const struct phylink_link_state *state)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
-	int speed, duplex, link, err;
+	int speed, duplex, link, pause, err;
 
 	if (mode == MLO_AN_PHY)
 		return;
@@ -629,9 +721,10 @@ static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port,
 		duplex = DUPLEX_UNFORCED;
 		link = LINK_UNFORCED;
 	}
+	pause = !!phylink_test(state->advertising, Pause);
 
 	mutex_lock(&chip->reg_lock);
-	err = mv88e6xxx_port_setup_mac(chip, port, link, speed, duplex,
+	err = mv88e6xxx_port_setup_mac(chip, port, link, speed, duplex, pause,
 				       state->interface);
 	mutex_unlock(&chip->reg_lock);
 
@@ -2080,6 +2173,9 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
 	int err;
 	u16 reg;
 
+	chip->ports[port].chip = chip;
+	chip->ports[port].port = port;
+
 	/* MAC Forcing register: don't force link, speed, duplex or flow control
 	 * state to any particular values on physical ports, but force the CPU
 	 * port and all DSA ports to their maximum bandwidth and full duplex.
@@ -2087,10 +2183,12 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
 	if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))
 		err = mv88e6xxx_port_setup_mac(chip, port, LINK_FORCED_UP,
 					       SPEED_MAX, DUPLEX_FULL,
+					       PAUSE_OFF,
 					       PHY_INTERFACE_MODE_NA);
 	else
 		err = mv88e6xxx_port_setup_mac(chip, port, LINK_UNFORCED,
 					       SPEED_UNFORCED, DUPLEX_UNFORCED,
+					       PAUSE_ON,
 					       PHY_INTERFACE_MODE_NA);
 	if (err)
 		return err;
@@ -2239,7 +2337,12 @@ static int mv88e6xxx_port_enable(struct dsa_switch *ds, int port,
 	int err;
 
 	mutex_lock(&chip->reg_lock);
+
 	err = mv88e6xxx_serdes_power(chip, port, true);
+
+	if (!err && chip->info->ops->serdes_irq_setup)
+		err = chip->info->ops->serdes_irq_setup(chip, port);
+
 	mutex_unlock(&chip->reg_lock);
 
 	return err;
@@ -2251,8 +2354,13 @@ static void mv88e6xxx_port_disable(struct dsa_switch *ds, int port,
 	struct mv88e6xxx_chip *chip = ds->priv;
 
 	mutex_lock(&chip->reg_lock);
+
+	if (chip->info->ops->serdes_irq_free)
+		chip->info->ops->serdes_irq_free(chip, port);
+
 	if (mv88e6xxx_serdes_power(chip, port, false))
 		dev_err(chip->dev, "failed to power off SERDES\n");
+
 	mutex_unlock(&chip->reg_lock);
 }
 
@@ -2286,6 +2394,7 @@ static int mv88e6xxx_stats_setup(struct mv88e6xxx_chip *chip)
 static int mv88e6xxx_setup(struct dsa_switch *ds)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
+	u8 cmode;
 	int err;
 	int i;
 
@@ -2294,6 +2403,17 @@ static int mv88e6xxx_setup(struct dsa_switch *ds)
 
 	mutex_lock(&chip->reg_lock);
 
+	/* Cache the cmode of each port. */
+	for (i = 0; i < mv88e6xxx_num_ports(chip); i++) {
+		if (chip->info->ops->port_get_cmode) {
+			err = chip->info->ops->port_get_cmode(chip, i, &cmode);
+			if (err)
+				goto unlock;
+
+			chip->ports[i].cmode = cmode;
+		}
+	}
+
 	/* Setup Switch Port Registers */
 	for (i = 0; i < mv88e6xxx_num_ports(chip); i++) {
 		if (dsa_is_unused_port(ds, i))
@@ -2601,6 +2721,8 @@ static const struct mv88e6xxx_ops mv88e6085_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6185_port_get_cmode,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2617,6 +2739,7 @@ static const struct mv88e6xxx_ops mv88e6085_ops = {
 	.rmu_disable = mv88e6085_g1_rmu_disable,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6095_ops = {
@@ -2632,6 +2755,8 @@ static const struct mv88e6xxx_ops mv88e6095_ops = {
 	.port_set_frame_mode = mv88e6085_port_set_frame_mode,
 	.port_set_egress_floods = mv88e6185_port_set_egress_floods,
 	.port_set_upstream_port = mv88e6095_port_set_upstream_port,
+	.port_link_state = mv88e6185_port_link_state,
+	.port_get_cmode = mv88e6185_port_get_cmode,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2643,6 +2768,7 @@ static const struct mv88e6xxx_ops mv88e6095_ops = {
 	.reset = mv88e6185_g1_reset,
 	.vtu_getnext = mv88e6185_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6097_ops = {
@@ -2665,6 +2791,8 @@ static const struct mv88e6xxx_ops mv88e6097_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6185_port_get_cmode,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2679,6 +2807,7 @@ static const struct mv88e6xxx_ops mv88e6097_ops = {
 	.rmu_disable = mv88e6085_g1_rmu_disable,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6123_ops = {
@@ -2696,6 +2825,8 @@ static const struct mv88e6xxx_ops mv88e6123_ops = {
 	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6185_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2709,6 +2840,7 @@ static const struct mv88e6xxx_ops mv88e6123_ops = {
 	.reset = mv88e6352_g1_reset,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6131_ops = {
@@ -2729,6 +2861,9 @@ static const struct mv88e6xxx_ops mv88e6131_ops = {
 	.port_set_jumbo_size = mv88e6165_port_set_jumbo_size,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_limit = mv88e6097_port_pause_limit,
+	.port_set_pause = mv88e6185_port_set_pause,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6185_port_get_cmode,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2744,6 +2879,7 @@ static const struct mv88e6xxx_ops mv88e6131_ops = {
 	.reset = mv88e6185_g1_reset,
 	.vtu_getnext = mv88e6185_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6141_ops = {
@@ -2769,6 +2905,8 @@ static const struct mv88e6xxx_ops mv88e6141_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -2784,6 +2922,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.serdes_power = mv88e6341_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
+	.phylink_validate = mv88e6390_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6161_ops = {
@@ -2806,6 +2945,8 @@ static const struct mv88e6xxx_ops mv88e6161_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6185_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2819,6 +2960,9 @@ static const struct mv88e6xxx_ops mv88e6161_ops = {
 	.reset = mv88e6352_g1_reset,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.avb_ops = &mv88e6165_avb_ops,
+	.ptp_ops = &mv88e6165_ptp_ops,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6165_ops = {
@@ -2834,6 +2978,8 @@ static const struct mv88e6xxx_ops mv88e6165_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6185_port_get_cmode,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2847,6 +2993,9 @@ static const struct mv88e6xxx_ops mv88e6165_ops = {
 	.reset = mv88e6352_g1_reset,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.avb_ops = &mv88e6165_avb_ops,
+	.ptp_ops = &mv88e6165_ptp_ops,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6171_ops = {
@@ -2870,6 +3019,8 @@ static const struct mv88e6xxx_ops mv88e6171_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2883,6 +3034,7 @@ static const struct mv88e6xxx_ops mv88e6171_ops = {
 	.reset = mv88e6352_g1_reset,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6172_ops = {
@@ -2908,6 +3060,8 @@ static const struct mv88e6xxx_ops mv88e6172_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2924,6 +3078,7 @@ static const struct mv88e6xxx_ops mv88e6172_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.serdes_power = mv88e6352_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
+	.phylink_validate = mv88e6352_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6175_ops = {
@@ -2947,6 +3102,8 @@ static const struct mv88e6xxx_ops mv88e6175_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2960,6 +3117,7 @@ static const struct mv88e6xxx_ops mv88e6175_ops = {
 	.reset = mv88e6352_g1_reset,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6176_ops = {
@@ -2985,6 +3143,8 @@ static const struct mv88e6xxx_ops mv88e6176_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3001,6 +3161,7 @@ static const struct mv88e6xxx_ops mv88e6176_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.serdes_power = mv88e6352_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
+	.phylink_validate = mv88e6352_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6185_ops = {
@@ -3017,6 +3178,9 @@ static const struct mv88e6xxx_ops mv88e6185_ops = {
 	.port_set_egress_floods = mv88e6185_port_set_egress_floods,
 	.port_egress_rate_limiting = mv88e6095_port_egress_rate_limiting,
 	.port_set_upstream_port = mv88e6095_port_set_upstream_port,
+	.port_set_pause = mv88e6185_port_set_pause,
+	.port_link_state = mv88e6185_port_link_state,
+	.port_get_cmode = mv88e6185_port_get_cmode,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3032,6 +3196,7 @@ static const struct mv88e6xxx_ops mv88e6185_ops = {
 	.reset = mv88e6185_g1_reset,
 	.vtu_getnext = mv88e6185_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6190_ops = {
@@ -3053,6 +3218,8 @@ static const struct mv88e6xxx_ops mv88e6190_ops = {
 	.port_pause_limit = mv88e6390_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3068,7 +3235,10 @@ static const struct mv88e6xxx_ops mv88e6190_ops = {
 	.vtu_getnext = mv88e6390_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.serdes_power = mv88e6390_serdes_power,
+	.serdes_irq_setup = mv88e6390_serdes_irq_setup,
+	.serdes_irq_free = mv88e6390_serdes_irq_free,
 	.gpio_ops = &mv88e6352_gpio_ops,
+	.phylink_validate = mv88e6390_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6190x_ops = {
@@ -3090,6 +3260,8 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
 	.port_pause_limit = mv88e6390_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3104,8 +3276,11 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
 	.rmu_disable = mv88e6390_g1_rmu_disable,
 	.vtu_getnext = mv88e6390_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
-	.serdes_power = mv88e6390_serdes_power,
+	.serdes_power = mv88e6390x_serdes_power,
+	.serdes_irq_setup = mv88e6390_serdes_irq_setup,
+	.serdes_irq_free = mv88e6390_serdes_irq_free,
 	.gpio_ops = &mv88e6352_gpio_ops,
+	.phylink_validate = mv88e6390x_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6191_ops = {
@@ -3127,6 +3302,8 @@ static const struct mv88e6xxx_ops mv88e6191_ops = {
 	.port_pause_limit = mv88e6390_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3142,6 +3319,11 @@ static const struct mv88e6xxx_ops mv88e6191_ops = {
 	.vtu_getnext = mv88e6390_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.serdes_power = mv88e6390_serdes_power,
+	.serdes_irq_setup = mv88e6390_serdes_irq_setup,
+	.serdes_irq_free = mv88e6390_serdes_irq_free,
+	.avb_ops = &mv88e6390_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
+	.phylink_validate = mv88e6390_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6240_ops = {
@@ -3167,6 +3349,8 @@ static const struct mv88e6xxx_ops mv88e6240_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3184,6 +3368,8 @@ static const struct mv88e6xxx_ops mv88e6240_ops = {
 	.serdes_power = mv88e6352_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
+	.phylink_validate = mv88e6352_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6290_ops = {
@@ -3206,6 +3392,8 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 	.port_set_cmode = mv88e6390x_port_set_cmode,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3221,8 +3409,12 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 	.vtu_getnext = mv88e6390_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.serdes_power = mv88e6390_serdes_power,
+	.serdes_irq_setup = mv88e6390_serdes_irq_setup,
+	.serdes_irq_free = mv88e6390_serdes_irq_free,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
+	.phylink_validate = mv88e6390_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6320_ops = {
@@ -3247,6 +3439,8 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3261,6 +3455,8 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6321_ops = {
@@ -3285,6 +3481,8 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3297,6 +3495,8 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
 	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6341_ops = {
@@ -3322,6 +3522,8 @@ static const struct mv88e6xxx_ops mv88e6341_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3338,6 +3540,8 @@ static const struct mv88e6xxx_ops mv88e6341_ops = {
 	.serdes_power = mv88e6341_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
+	.phylink_validate = mv88e6390_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6350_ops = {
@@ -3361,6 +3565,8 @@ static const struct mv88e6xxx_ops mv88e6350_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3374,6 +3580,7 @@ static const struct mv88e6xxx_ops mv88e6350_ops = {
 	.reset = mv88e6352_g1_reset,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6351_ops = {
@@ -3397,6 +3604,8 @@ static const struct mv88e6xxx_ops mv88e6351_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3411,6 +3620,8 @@ static const struct mv88e6xxx_ops mv88e6351_ops = {
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.avb_ops = &mv88e6352_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6352_ops = {
@@ -3436,6 +3647,8 @@ static const struct mv88e6xxx_ops mv88e6352_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3453,9 +3666,11 @@ static const struct mv88e6xxx_ops mv88e6352_ops = {
 	.serdes_power = mv88e6352_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
 	.serdes_get_sset_count = mv88e6352_serdes_get_sset_count,
 	.serdes_get_strings = mv88e6352_serdes_get_strings,
 	.serdes_get_stats = mv88e6352_serdes_get_stats,
+	.phylink_validate = mv88e6352_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6390_ops = {
@@ -3480,6 +3695,8 @@ static const struct mv88e6xxx_ops mv88e6390_ops = {
 	.port_set_cmode = mv88e6390x_port_set_cmode,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3495,8 +3712,12 @@ static const struct mv88e6xxx_ops mv88e6390_ops = {
 	.vtu_getnext = mv88e6390_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.serdes_power = mv88e6390_serdes_power,
+	.serdes_irq_setup = mv88e6390_serdes_irq_setup,
+	.serdes_irq_free = mv88e6390_serdes_irq_free,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
+	.phylink_validate = mv88e6390_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6390x_ops = {
@@ -3521,6 +3742,8 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.port_set_cmode = mv88e6390x_port_set_cmode,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3535,9 +3758,13 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.rmu_disable = mv88e6390_g1_rmu_disable,
 	.vtu_getnext = mv88e6390_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
-	.serdes_power = mv88e6390_serdes_power,
+	.serdes_power = mv88e6390x_serdes_power,
+	.serdes_irq_setup = mv88e6390_serdes_irq_setup,
+	.serdes_irq_free = mv88e6390_serdes_irq_free,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
+	.phylink_validate = mv88e6390x_phylink_validate,
 };
 
 static const struct mv88e6xxx_info mv88e6xxx_table[] = {
@@ -3689,6 +3916,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.pvt = true,
 		.multi_chip = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
+		.ptp_support = true,
 		.ops = &mv88e6161_ops,
 	},
 
@@ -3711,6 +3939,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.pvt = true,
 		.multi_chip = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
+		.ptp_support = true,
 		.ops = &mv88e6165_ops,
 	},
 
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index 8ac3fbb15352..f9ecb7872d32 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -155,6 +155,7 @@ struct mv88e6xxx_bus_ops;
 struct mv88e6xxx_irq_ops;
 struct mv88e6xxx_gpio_ops;
 struct mv88e6xxx_avb_ops;
+struct mv88e6xxx_ptp_ops;
 
 struct mv88e6xxx_irq {
 	u16 masked;
@@ -190,12 +191,16 @@ struct mv88e6xxx_port_hwtstamp {
 };
 
 struct mv88e6xxx_port {
+	struct mv88e6xxx_chip *chip;
+	int port;
 	u64 serdes_stats[2];
 	u64 atu_member_violation;
 	u64 atu_miss_violation;
 	u64 atu_full_violation;
 	u64 vtu_member_violation;
 	u64 vtu_miss_violation;
+	u8 cmode;
+	int serdes_irq;
 };
 
 struct mv88e6xxx_chip {
@@ -273,6 +278,7 @@ struct mv88e6xxx_chip {
 	struct ptp_pin_desc	pin_config[MV88E6XXX_MAX_GPIO];
 	u16 trig_config;
 	u16 evcap_config;
+	u16 enable_count;
 
 	/* Per-port timestamping resources. */
 	struct mv88e6xxx_port_hwtstamp port_hwtstamp[DSA_MAX_PORTS];
@@ -349,6 +355,13 @@ struct mv88e6xxx_ops {
 	 */
 	int (*port_set_duplex)(struct mv88e6xxx_chip *chip, int port, int dup);
 
+#define PAUSE_ON		1
+#define PAUSE_OFF		0
+
+	/* Enable/disable sending Pause */
+	int (*port_set_pause)(struct mv88e6xxx_chip *chip, int port,
+			      int pause);
+
 #define SPEED_MAX		INT_MAX
 #define SPEED_UNFORCED		-2
 
@@ -381,12 +394,16 @@ struct mv88e6xxx_ops {
 	 */
 	int (*port_set_cmode)(struct mv88e6xxx_chip *chip, int port,
 			      phy_interface_t mode);
+	int (*port_get_cmode)(struct mv88e6xxx_chip *chip, int port, u8 *cmode);
 
 	/* Some devices have a per port register indicating what is
 	 * the upstream port this port should forward to.
 	 */
 	int (*port_set_upstream_port)(struct mv88e6xxx_chip *chip, int port,
 				      int upstream_port);
+	/* Return the port link state, as required by phylink */
+	int (*port_link_state)(struct mv88e6xxx_chip *chip, int port,
+			       struct phylink_link_state *state);
 
 	/* Snapshot the statistics for a port. The statistics can then
 	 * be read back a leisure but still with a consistent view.
@@ -418,6 +435,10 @@ struct mv88e6xxx_ops {
 	/* Power on/off a SERDES interface */
 	int (*serdes_power)(struct mv88e6xxx_chip *chip, int port, bool on);
 
+	/* SERDES interrupt handling */
+	int (*serdes_irq_setup)(struct mv88e6xxx_chip *chip, int port);
+	void (*serdes_irq_free)(struct mv88e6xxx_chip *chip, int port);
+
 	/* Statistics from the SERDES interface */
 	int (*serdes_get_sset_count)(struct mv88e6xxx_chip *chip, int port);
 	int (*serdes_get_strings)(struct mv88e6xxx_chip *chip,  int port,
@@ -439,6 +460,14 @@ struct mv88e6xxx_ops {
 
 	/* Remote Management Unit operations */
 	int (*rmu_disable)(struct mv88e6xxx_chip *chip);
+
+	/* Precision Time Protocol operations */
+	const struct mv88e6xxx_ptp_ops *ptp_ops;
+
+	/* Phylink */
+	void (*phylink_validate)(struct mv88e6xxx_chip *chip, int port,
+				 unsigned long *mask,
+				 struct phylink_link_state *state);
 };
 
 struct mv88e6xxx_irq_ops {
@@ -486,6 +515,24 @@ struct mv88e6xxx_avb_ops {
 	int (*tai_write)(struct mv88e6xxx_chip *chip, int addr, u16 data);
 };
 
+struct mv88e6xxx_ptp_ops {
+	u64 (*clock_read)(const struct cyclecounter *cc);
+	int (*ptp_enable)(struct ptp_clock_info *ptp,
+			  struct ptp_clock_request *rq, int on);
+	int (*ptp_verify)(struct ptp_clock_info *ptp, unsigned int pin,
+			  enum ptp_pin_function func, unsigned int chan);
+	void (*event_work)(struct work_struct *ugly);
+	int (*port_enable)(struct mv88e6xxx_chip *chip, int port);
+	int (*port_disable)(struct mv88e6xxx_chip *chip, int port);
+	int (*global_enable)(struct mv88e6xxx_chip *chip);
+	int (*global_disable)(struct mv88e6xxx_chip *chip);
+	int n_ext_ts;
+	int arr0_sts_reg;
+	int arr1_sts_reg;
+	int dep_sts_reg;
+	u32 rx_filters;
+};
+
 #define STATS_TYPE_PORT		BIT(0)
 #define STATS_TYPE_BANK0	BIT(1)
 #define STATS_TYPE_BANK1	BIT(2)
diff --git a/drivers/net/dsa/mv88e6xxx/global2.h b/drivers/net/dsa/mv88e6xxx/global2.h
index 37e8ce2c72a0..194660d8c783 100644
--- a/drivers/net/dsa/mv88e6xxx/global2.h
+++ b/drivers/net/dsa/mv88e6xxx/global2.h
@@ -160,6 +160,7 @@
 #define MV88E6390_G2_AVB_CMD_OP_WRITE		0x6000
 #define MV88E6352_G2_AVB_CMD_PORT_MASK		0x0f00
 #define MV88E6352_G2_AVB_CMD_PORT_TAIGLOBAL	0xe
+#define MV88E6165_G2_AVB_CMD_PORT_PTPGLOBAL	0xf
 #define MV88E6352_G2_AVB_CMD_PORT_PTPGLOBAL	0xf
 #define MV88E6390_G2_AVB_CMD_PORT_MASK		0x1f00
 #define MV88E6390_G2_AVB_CMD_PORT_TAIGLOBAL	0x1e
@@ -335,6 +336,7 @@ int mv88e6xxx_g2_device_mapping_write(struct mv88e6xxx_chip *chip, int target,
 extern const struct mv88e6xxx_irq_ops mv88e6097_watchdog_ops;
 extern const struct mv88e6xxx_irq_ops mv88e6390_watchdog_ops;
 
+extern const struct mv88e6xxx_avb_ops mv88e6165_avb_ops;
 extern const struct mv88e6xxx_avb_ops mv88e6352_avb_ops;
 extern const struct mv88e6xxx_avb_ops mv88e6390_avb_ops;
 
@@ -484,6 +486,7 @@ static inline int mv88e6xxx_g2_pot_clear(struct mv88e6xxx_chip *chip)
 static const struct mv88e6xxx_irq_ops mv88e6097_watchdog_ops = {};
 static const struct mv88e6xxx_irq_ops mv88e6390_watchdog_ops = {};
 
+static const struct mv88e6xxx_avb_ops mv88e6165_avb_ops = {};
 static const struct mv88e6xxx_avb_ops mv88e6352_avb_ops = {};
 static const struct mv88e6xxx_avb_ops mv88e6390_avb_ops = {};
 
diff --git a/drivers/net/dsa/mv88e6xxx/global2_avb.c b/drivers/net/dsa/mv88e6xxx/global2_avb.c
index 2e398ccb88ca..672b503a67e1 100644
--- a/drivers/net/dsa/mv88e6xxx/global2_avb.c
+++ b/drivers/net/dsa/mv88e6xxx/global2_avb.c
@@ -130,6 +130,31 @@ const struct mv88e6xxx_avb_ops mv88e6352_avb_ops = {
 	.tai_write		= mv88e6352_g2_avb_tai_write,
 };
 
+static int mv88e6165_g2_avb_tai_read(struct mv88e6xxx_chip *chip, int addr,
+				     u16 *data, int len)
+{
+	return mv88e6352_g2_avb_port_ptp_read(chip,
+					MV88E6165_G2_AVB_CMD_PORT_PTPGLOBAL,
+					addr, data, len);
+}
+
+static int mv88e6165_g2_avb_tai_write(struct mv88e6xxx_chip *chip, int addr,
+				      u16 data)
+{
+	return mv88e6352_g2_avb_port_ptp_write(chip,
+					MV88E6165_G2_AVB_CMD_PORT_PTPGLOBAL,
+					addr, data);
+}
+
+const struct mv88e6xxx_avb_ops mv88e6165_avb_ops = {
+	.port_ptp_read		= mv88e6352_g2_avb_port_ptp_read,
+	.port_ptp_write		= mv88e6352_g2_avb_port_ptp_write,
+	.ptp_read		= mv88e6352_g2_avb_ptp_read,
+	.ptp_write		= mv88e6352_g2_avb_ptp_write,
+	.tai_read		= mv88e6165_g2_avb_tai_read,
+	.tai_write		= mv88e6165_g2_avb_tai_write,
+};
+
 static int mv88e6390_g2_avb_port_ptp_read(struct mv88e6xxx_chip *chip,
 					  int port, int addr, u16 *data,
 					  int len)
diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.c b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
index a036c490b7ce..a17c16a2ab78 100644
--- a/drivers/net/dsa/mv88e6xxx/hwtstamp.c
+++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
@@ -51,17 +51,30 @@ static int mv88e6xxx_ptp_write(struct mv88e6xxx_chip *chip, int addr,
 	return chip->info->ops->avb_ops->ptp_write(chip, addr, data);
 }
 
+static int mv88e6xxx_ptp_read(struct mv88e6xxx_chip *chip, int addr,
+			      u16 *data)
+{
+	if (!chip->info->ops->avb_ops->ptp_read)
+		return -EOPNOTSUPP;
+
+	return chip->info->ops->avb_ops->ptp_read(chip, addr, data, 1);
+}
+
 /* TX_TSTAMP_TIMEOUT: This limits the time spent polling for a TX
  * timestamp. When working properly, hardware will produce a timestamp
  * within 1ms. Software may enounter delays due to MDIO contention, so
  * the timeout is set accordingly.
  */
-#define TX_TSTAMP_TIMEOUT	msecs_to_jiffies(20)
+#define TX_TSTAMP_TIMEOUT	msecs_to_jiffies(40)
 
 int mv88e6xxx_get_ts_info(struct dsa_switch *ds, int port,
 			  struct ethtool_ts_info *info)
 {
-	struct mv88e6xxx_chip *chip = ds->priv;
+	const struct mv88e6xxx_ptp_ops *ptp_ops;
+	struct mv88e6xxx_chip *chip;
+
+	chip = ds->priv;
+	ptp_ops = chip->info->ops->ptp_ops;
 
 	if (!chip->info->ptp_support)
 		return -EOPNOTSUPP;
@@ -74,17 +87,7 @@ int mv88e6xxx_get_ts_info(struct dsa_switch *ds, int port,
 	info->tx_types =
 		(1 << HWTSTAMP_TX_OFF) |
 		(1 << HWTSTAMP_TX_ON);
-	info->rx_filters =
-		(1 << HWTSTAMP_FILTER_NONE) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_EVENT) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_SYNC) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ);
+	info->rx_filters = ptp_ops->rx_filters;
 
 	return 0;
 }
@@ -92,10 +95,9 @@ int mv88e6xxx_get_ts_info(struct dsa_switch *ds, int port,
 static int mv88e6xxx_set_hwtstamp_config(struct mv88e6xxx_chip *chip, int port,
 					 struct hwtstamp_config *config)
 {
+	const struct mv88e6xxx_ptp_ops *ptp_ops = chip->info->ops->ptp_ops;
 	struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port];
 	bool tstamp_enable = false;
-	u16 port_config0;
-	int err;
 
 	/* Prevent the TX/RX paths from trying to interact with the
 	 * timestamp hardware while we reconfigure it.
@@ -120,6 +122,14 @@ static int mv88e6xxx_set_hwtstamp_config(struct mv88e6xxx_chip *chip, int port,
 	/* The switch supports timestamping both L2 and L4; one cannot be
 	 * disabled independently of the other.
 	 */
+
+	if (!(BIT(config->rx_filter) & ptp_ops->rx_filters)) {
+		config->rx_filter = HWTSTAMP_FILTER_NONE;
+		dev_dbg(chip->dev, "Unsupported rx_filter %d\n",
+			config->rx_filter);
+		return -ERANGE;
+	}
+
 	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		tstamp_enable = false;
@@ -141,24 +151,22 @@ static int mv88e6xxx_set_hwtstamp_config(struct mv88e6xxx_chip *chip, int port,
 		return -ERANGE;
 	}
 
+	mutex_lock(&chip->reg_lock);
 	if (tstamp_enable) {
-		/* Disable transportSpecific value matching, so that packets
-		 * with either 1588 (0) and 802.1AS (1) will be timestamped.
-		 */
-		port_config0 = MV88E6XXX_PORT_PTP_CFG0_DISABLE_TSPEC_MATCH;
+		chip->enable_count += 1;
+		if (chip->enable_count == 1 && ptp_ops->global_enable)
+			ptp_ops->global_enable(chip);
+		if (ptp_ops->port_enable)
+			ptp_ops->port_enable(chip, port);
 	} else {
-		/* Disable PTP. This disables both RX and TX timestamping. */
-		port_config0 = MV88E6XXX_PORT_PTP_CFG0_DISABLE_PTP;
+		if (ptp_ops->port_disable)
+			ptp_ops->port_disable(chip, port);
+		chip->enable_count -= 1;
+		if (chip->enable_count == 0 && ptp_ops->global_disable)
+			ptp_ops->global_disable(chip);
 	}
-
-	mutex_lock(&chip->reg_lock);
-	err = mv88e6xxx_port_ptp_write(chip, port, MV88E6XXX_PORT_PTP_CFG0,
-				       port_config0);
 	mutex_unlock(&chip->reg_lock);
 
-	if (err < 0)
-		return err;
-
 	/* Once hardware has been configured, enable timestamp checks
 	 * in the RX/TX paths.
 	 */
@@ -338,17 +346,18 @@ static void mv88e6xxx_get_rxts(struct mv88e6xxx_chip *chip,
 static void mv88e6xxx_rxtstamp_work(struct mv88e6xxx_chip *chip,
 				    struct mv88e6xxx_port_hwtstamp *ps)
 {
+	const struct mv88e6xxx_ptp_ops *ptp_ops = chip->info->ops->ptp_ops;
 	struct sk_buff *skb;
 
 	skb = skb_dequeue(&ps->rx_queue);
 
 	if (skb)
-		mv88e6xxx_get_rxts(chip, ps, skb, MV88E6XXX_PORT_PTP_ARR0_STS,
+		mv88e6xxx_get_rxts(chip, ps, skb, ptp_ops->arr0_sts_reg,
 				   &ps->rx_queue);
 
 	skb = skb_dequeue(&ps->rx_queue2);
 	if (skb)
-		mv88e6xxx_get_rxts(chip, ps, skb, MV88E6XXX_PORT_PTP_ARR1_STS,
+		mv88e6xxx_get_rxts(chip, ps, skb, ptp_ops->arr1_sts_reg,
 				   &ps->rx_queue2);
 }
 
@@ -389,6 +398,7 @@ bool mv88e6xxx_port_rxtstamp(struct dsa_switch *ds, int port,
 static int mv88e6xxx_txtstamp_work(struct mv88e6xxx_chip *chip,
 				   struct mv88e6xxx_port_hwtstamp *ps)
 {
+	const struct mv88e6xxx_ptp_ops *ptp_ops = chip->info->ops->ptp_ops;
 	struct skb_shared_hwtstamps shhwtstamps;
 	u16 departure_block[4], status;
 	struct sk_buff *tmp_skb;
@@ -401,7 +411,7 @@ static int mv88e6xxx_txtstamp_work(struct mv88e6xxx_chip *chip,
 
 	mutex_lock(&chip->reg_lock);
 	err = mv88e6xxx_port_ptp_read(chip, ps->port_id,
-				      MV88E6XXX_PORT_PTP_DEP_STS,
+				      ptp_ops->dep_sts_reg,
 				      departure_block,
 				      ARRAY_SIZE(departure_block));
 	mutex_unlock(&chip->reg_lock);
@@ -425,8 +435,7 @@ static int mv88e6xxx_txtstamp_work(struct mv88e6xxx_chip *chip,
 
 	/* We have the timestamp; go ahead and clear valid now */
 	mutex_lock(&chip->reg_lock);
-	mv88e6xxx_port_ptp_write(chip, ps->port_id,
-				 MV88E6XXX_PORT_PTP_DEP_STS, 0);
+	mv88e6xxx_port_ptp_write(chip, ps->port_id, ptp_ops->dep_sts_reg, 0);
 	mutex_unlock(&chip->reg_lock);
 
 	status = departure_block[0] & MV88E6XXX_PTP_TS_STATUS_MASK;
@@ -522,8 +531,48 @@ bool mv88e6xxx_port_txtstamp(struct dsa_switch *ds, int port,
 	return true;
 }
 
+int mv88e6165_global_disable(struct mv88e6xxx_chip *chip)
+{
+	u16 val;
+	int err;
+
+	err = mv88e6xxx_ptp_read(chip, MV88E6165_PTP_CFG, &val);
+	if (err)
+		return err;
+	val |= MV88E6165_PTP_CFG_DISABLE_PTP;
+
+	return mv88e6xxx_ptp_write(chip, MV88E6165_PTP_CFG, val);
+}
+
+int mv88e6165_global_enable(struct mv88e6xxx_chip *chip)
+{
+	u16 val;
+	int err;
+
+	err = mv88e6xxx_ptp_read(chip, MV88E6165_PTP_CFG, &val);
+	if (err)
+		return err;
+
+	val &= ~(MV88E6165_PTP_CFG_DISABLE_PTP | MV88E6165_PTP_CFG_TSPEC_MASK);
+
+	return mv88e6xxx_ptp_write(chip, MV88E6165_PTP_CFG, val);
+}
+
+int mv88e6352_hwtstamp_port_disable(struct mv88e6xxx_chip *chip, int port)
+{
+	return mv88e6xxx_port_ptp_write(chip, port, MV88E6XXX_PORT_PTP_CFG0,
+					MV88E6XXX_PORT_PTP_CFG0_DISABLE_PTP);
+}
+
+int mv88e6352_hwtstamp_port_enable(struct mv88e6xxx_chip *chip, int port)
+{
+	return mv88e6xxx_port_ptp_write(chip, port, MV88E6XXX_PORT_PTP_CFG0,
+					MV88E6XXX_PORT_PTP_CFG0_DISABLE_TSPEC_MATCH);
+}
+
 static int mv88e6xxx_hwtstamp_port_setup(struct mv88e6xxx_chip *chip, int port)
 {
+	const struct mv88e6xxx_ptp_ops *ptp_ops = chip->info->ops->ptp_ops;
 	struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port];
 
 	ps->port_id = port;
@@ -531,12 +580,15 @@ static int mv88e6xxx_hwtstamp_port_setup(struct mv88e6xxx_chip *chip, int port)
 	skb_queue_head_init(&ps->rx_queue);
 	skb_queue_head_init(&ps->rx_queue2);
 
-	return mv88e6xxx_port_ptp_write(chip, port, MV88E6XXX_PORT_PTP_CFG0,
-					MV88E6XXX_PORT_PTP_CFG0_DISABLE_PTP);
+	if (ptp_ops->port_disable)
+		return ptp_ops->port_disable(chip, port);
+
+	return 0;
 }
 
 int mv88e6xxx_hwtstamp_setup(struct mv88e6xxx_chip *chip)
 {
+	const struct mv88e6xxx_ptp_ops *ptp_ops = chip->info->ops->ptp_ops;
 	int err;
 	int i;
 
@@ -547,6 +599,18 @@ int mv88e6xxx_hwtstamp_setup(struct mv88e6xxx_chip *chip)
 			return err;
 	}
 
+	/* Disable PTP globally */
+	if (ptp_ops->global_disable) {
+		err = ptp_ops->global_disable(chip);
+		if (err)
+			return err;
+	}
+
+	/* Set the ethertype of L2 PTP messages */
+	err = mv88e6xxx_ptp_write(chip, MV88E6XXX_PTP_GC_ETYPE, ETH_P_1588);
+	if (err)
+		return err;
+
 	/* MV88E6XXX_PTP_MSG_TYPE is a mask of PTP message types to
 	 * timestamp. This affects all ports that have timestamping enabled,
 	 * but the timestamp config is per-port; thus we configure all events
diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.h b/drivers/net/dsa/mv88e6xxx/hwtstamp.h
index bc71c9212a08..b9a72661bcc4 100644
--- a/drivers/net/dsa/mv88e6xxx/hwtstamp.h
+++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.h
@@ -19,7 +19,7 @@
 
 #include "chip.h"
 
-/* Global PTP registers */
+/* Global 6352 PTP registers */
 /* Offset 0x00: PTP EtherType */
 #define MV88E6XXX_PTP_ETHERTYPE	0x00
 
@@ -34,6 +34,12 @@
 /* Offset 0x02: Timestamp Arrival Capture Pointers */
 #define MV88E6XXX_PTP_TS_ARRIVAL_PTR	0x02
 
+/* Offset 0x05: PTP Global Configuration */
+#define MV88E6165_PTP_CFG			0x05
+#define MV88E6165_PTP_CFG_TSPEC_MASK		0xf000
+#define MV88E6165_PTP_CFG_DISABLE_TS_OVERWRITE	BIT(1)
+#define MV88E6165_PTP_CFG_DISABLE_PTP		BIT(0)
+
 /* Offset 0x07: PTP Global Configuration */
 #define MV88E6341_PTP_CFG			0x07
 #define MV88E6341_PTP_CFG_UPDATE		0x8000
@@ -46,7 +52,7 @@
 /* Offset 0x08: PTP Interrupt Status */
 #define MV88E6XXX_PTP_IRQ_STATUS	0x08
 
-/* Per-Port PTP Registers */
+/* Per-Port 6352 PTP Registers */
 /* Offset 0x00: PTP Configuration 0 */
 #define MV88E6XXX_PORT_PTP_CFG0				0x00
 #define MV88E6XXX_PORT_PTP_CFG0_TSPEC_SHIFT		12
@@ -123,6 +129,10 @@ int mv88e6xxx_get_ts_info(struct dsa_switch *ds, int port,
 
 int mv88e6xxx_hwtstamp_setup(struct mv88e6xxx_chip *chip);
 void mv88e6xxx_hwtstamp_free(struct mv88e6xxx_chip *chip);
+int mv88e6352_hwtstamp_port_enable(struct mv88e6xxx_chip *chip, int port);
+int mv88e6352_hwtstamp_port_disable(struct mv88e6xxx_chip *chip, int port);
+int mv88e6165_global_enable(struct mv88e6xxx_chip *chip);
+int mv88e6165_global_disable(struct mv88e6xxx_chip *chip);
 
 #else /* !CONFIG_NET_DSA_MV88E6XXX_PTP */
 
diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index 429d0ebcd5b1..92945841c8e8 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -19,6 +19,7 @@
 
 #include "chip.h"
 #include "port.h"
+#include "serdes.h"
 
 int mv88e6xxx_port_read(struct mv88e6xxx_chip *chip, int port, int reg,
 			u16 *val)
@@ -36,6 +37,29 @@ int mv88e6xxx_port_write(struct mv88e6xxx_chip *chip, int port, int reg,
 	return mv88e6xxx_write(chip, addr, reg, val);
 }
 
+/* Offset 0x00: MAC (or PCS or Physical) Status Register
+ *
+ * For most devices, this is read only. However the 6185 has the MyPause
+ * bit read/write.
+ */
+int mv88e6185_port_set_pause(struct mv88e6xxx_chip *chip, int port,
+			     int pause)
+{
+	u16 reg;
+	int err;
+
+	err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, &reg);
+	if (err)
+		return err;
+
+	if (pause)
+		reg |= MV88E6XXX_PORT_STS_MY_PAUSE;
+	else
+		reg &= ~MV88E6XXX_PORT_STS_MY_PAUSE;
+
+	return mv88e6xxx_port_write(chip, port, MV88E6XXX_PORT_STS, reg);
+}
+
 /* Offset 0x01: MAC (or PCS or Physical) Control Register
  *
  * Link, Duplex and Flow Control have one force bit, one value bit.
@@ -318,8 +342,9 @@ int mv88e6390x_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed)
 int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 			      phy_interface_t mode)
 {
-	u16 reg;
+	int lane;
 	u16 cmode;
+	u16 reg;
 	int err;
 
 	if (mode == PHY_INTERFACE_MODE_NA)
@@ -349,6 +374,20 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 		cmode = 0;
 	}
 
+	lane = mv88e6390x_serdes_get_lane(chip, port);
+	if (lane < 0)
+		return lane;
+
+	if (chip->ports[port].serdes_irq) {
+		err = mv88e6390_serdes_irq_disable(chip, port, lane);
+		if (err)
+			return err;
+	}
+
+	err = mv88e6390_serdes_power(chip, port, false);
+	if (err)
+		return err;
+
 	if (cmode) {
 		err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, &reg);
 		if (err)
@@ -360,12 +399,38 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 		err = mv88e6xxx_port_write(chip, port, MV88E6XXX_PORT_STS, reg);
 		if (err)
 			return err;
+
+		err = mv88e6390_serdes_power(chip, port, true);
+		if (err)
+			return err;
+
+		if (chip->ports[port].serdes_irq) {
+			err = mv88e6390_serdes_irq_enable(chip, port, lane);
+			if (err)
+				return err;
+		}
 	}
 
+	chip->ports[port].cmode = cmode;
+
 	return 0;
 }
 
-int mv88e6xxx_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode)
+int mv88e6185_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode)
+{
+	int err;
+	u16 reg;
+
+	err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, &reg);
+	if (err)
+		return err;
+
+	*cmode = reg & MV88E6185_PORT_STS_CMODE_MASK;
+
+	return 0;
+}
+
+int mv88e6352_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode)
 {
 	int err;
 	u16 reg;
@@ -379,7 +444,7 @@ int mv88e6xxx_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode)
 	return 0;
 }
 
-int mv88e6xxx_port_link_state(struct mv88e6xxx_chip *chip, int port,
+int mv88e6352_port_link_state(struct mv88e6xxx_chip *chip, int port,
 			      struct phylink_link_state *state)
 {
 	int err;
@@ -400,7 +465,7 @@ int mv88e6xxx_port_link_state(struct mv88e6xxx_chip *chip, int port,
 		state->speed = SPEED_1000;
 		break;
 	case MV88E6XXX_PORT_STS_SPEED_10000:
-		if ((reg &MV88E6XXX_PORT_STS_CMODE_MASK) ==
+		if ((reg & MV88E6XXX_PORT_STS_CMODE_MASK) ==
 		    MV88E6XXX_PORT_STS_CMODE_2500BASEX)
 			state->speed = SPEED_2500;
 		else
@@ -417,6 +482,42 @@ int mv88e6xxx_port_link_state(struct mv88e6xxx_chip *chip, int port,
 	return 0;
 }
 
+int mv88e6185_port_link_state(struct mv88e6xxx_chip *chip, int port,
+			      struct phylink_link_state *state)
+{
+	if (state->interface == PHY_INTERFACE_MODE_1000BASEX) {
+		u8 cmode = chip->ports[port].cmode;
+
+		/* When a port is in "Cross-chip serdes" mode, it uses
+		 * 1000Base-X full duplex mode, but there is no automatic
+		 * link detection. Use the sync OK status for link (as it
+		 * would do for 1000Base-X mode.)
+		 */
+		if (cmode == MV88E6185_PORT_STS_CMODE_SERDES) {
+			u16 mac;
+			int err;
+
+			err = mv88e6xxx_port_read(chip, port,
+						  MV88E6XXX_PORT_MAC_CTL, &mac);
+			if (err)
+				return err;
+
+			state->link = !!(mac & MV88E6185_PORT_MAC_CTL_SYNC_OK);
+			state->an_enabled = 1;
+			state->an_complete =
+				!!(mac & MV88E6185_PORT_MAC_CTL_AN_DONE);
+			state->duplex =
+				state->link ? DUPLEX_FULL : DUPLEX_UNKNOWN;
+			state->speed =
+				state->link ? SPEED_1000 : SPEED_UNKNOWN;
+
+			return 0;
+		}
+	}
+
+	return mv88e6352_port_link_state(chip, port, state);
+}
+
 /* Offset 0x02: Jamming Control
  *
  * Do not limit the period of time that this port can be paused for by
diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h
index 5e1db1b221ca..f32f56af8e35 100644
--- a/drivers/net/dsa/mv88e6xxx/port.h
+++ b/drivers/net/dsa/mv88e6xxx/port.h
@@ -42,14 +42,28 @@
 #define MV88E6XXX_PORT_STS_CMODE_2500BASEX	0x000b
 #define MV88E6XXX_PORT_STS_CMODE_XAUI		0x000c
 #define MV88E6XXX_PORT_STS_CMODE_RXAUI		0x000d
+#define MV88E6185_PORT_STS_CDUPLEX		0x0008
+#define MV88E6185_PORT_STS_CMODE_MASK		0x0007
+#define MV88E6185_PORT_STS_CMODE_GMII_FD	0x0000
+#define MV88E6185_PORT_STS_CMODE_MII_100_FD_PS	0x0001
+#define MV88E6185_PORT_STS_CMODE_MII_100	0x0002
+#define MV88E6185_PORT_STS_CMODE_MII_10		0x0003
+#define MV88E6185_PORT_STS_CMODE_SERDES		0x0004
+#define MV88E6185_PORT_STS_CMODE_1000BASE_X	0x0005
+#define MV88E6185_PORT_STS_CMODE_PHY		0x0006
+#define MV88E6185_PORT_STS_CMODE_DISABLED	0x0007
 
 /* Offset 0x01: MAC (or PCS or Physical) Control Register */
 #define MV88E6XXX_PORT_MAC_CTL				0x01
 #define MV88E6XXX_PORT_MAC_CTL_RGMII_DELAY_RXCLK	0x8000
 #define MV88E6XXX_PORT_MAC_CTL_RGMII_DELAY_TXCLK	0x4000
+#define MV88E6185_PORT_MAC_CTL_SYNC_OK			0x4000
 #define MV88E6390_PORT_MAC_CTL_FORCE_SPEED		0x2000
 #define MV88E6390_PORT_MAC_CTL_ALTSPEED			0x1000
 #define MV88E6352_PORT_MAC_CTL_200BASE			0x1000
+#define MV88E6185_PORT_MAC_CTL_AN_EN			0x0400
+#define MV88E6185_PORT_MAC_CTL_AN_RESTART		0x0200
+#define MV88E6185_PORT_MAC_CTL_AN_DONE			0x0100
 #define MV88E6XXX_PORT_MAC_CTL_FC			0x0080
 #define MV88E6XXX_PORT_MAC_CTL_FORCE_FC			0x0040
 #define MV88E6XXX_PORT_MAC_CTL_LINK_UP			0x0020
@@ -242,6 +256,8 @@ int mv88e6xxx_port_read(struct mv88e6xxx_chip *chip, int port, int reg,
 int mv88e6xxx_port_write(struct mv88e6xxx_chip *chip, int port, int reg,
 			 u16 val);
 
+int mv88e6185_port_set_pause(struct mv88e6xxx_chip *chip, int port,
+			     int pause);
 int mv88e6352_port_set_rgmii_delay(struct mv88e6xxx_chip *chip, int port,
 				   phy_interface_t mode);
 int mv88e6390_port_set_rgmii_delay(struct mv88e6xxx_chip *chip, int port,
@@ -295,8 +311,11 @@ int mv88e6390_port_pause_limit(struct mv88e6xxx_chip *chip, int port, u8 in,
 			       u8 out);
 int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 			      phy_interface_t mode);
-int mv88e6xxx_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode);
-int mv88e6xxx_port_link_state(struct mv88e6xxx_chip *chip, int port,
+int mv88e6185_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode);
+int mv88e6352_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode);
+int mv88e6185_port_link_state(struct mv88e6xxx_chip *chip, int port,
+			      struct phylink_link_state *state);
+int mv88e6352_port_link_state(struct mv88e6xxx_chip *chip, int port,
 			      struct phylink_link_state *state);
 int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port);
 int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port,
diff --git a/drivers/net/dsa/mv88e6xxx/ptp.c b/drivers/net/dsa/mv88e6xxx/ptp.c
index bd85e2c390e1..4b336d8d4c67 100644
--- a/drivers/net/dsa/mv88e6xxx/ptp.c
+++ b/drivers/net/dsa/mv88e6xxx/ptp.c
@@ -16,6 +16,7 @@
 
 #include "chip.h"
 #include "global2.h"
+#include "hwtstamp.h"
 #include "ptp.h"
 
 /* Raw timestamps are in units of 8-ns clock periods. */
@@ -50,7 +51,7 @@ static int mv88e6xxx_tai_write(struct mv88e6xxx_chip *chip, int addr, u16 data)
 }
 
 /* TODO: places where this are called should be using pinctrl */
-static int mv88e6xxx_set_gpio_func(struct mv88e6xxx_chip *chip, int pin,
+static int mv88e6352_set_gpio_func(struct mv88e6xxx_chip *chip, int pin,
 				   int func, int input)
 {
 	int err;
@@ -65,7 +66,7 @@ static int mv88e6xxx_set_gpio_func(struct mv88e6xxx_chip *chip, int pin,
 	return chip->info->ops->gpio_ops->set_pctl(chip, pin, func);
 }
 
-static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc)
+static u64 mv88e6352_ptp_clock_read(const struct cyclecounter *cc)
 {
 	struct mv88e6xxx_chip *chip = cc_to_chip(cc);
 	u16 phc_time[2];
@@ -79,13 +80,27 @@ static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc)
 		return ((u32)phc_time[1] << 16) | phc_time[0];
 }
 
-/* mv88e6xxx_config_eventcap - configure TAI event capture
+static u64 mv88e6165_ptp_clock_read(const struct cyclecounter *cc)
+{
+	struct mv88e6xxx_chip *chip = cc_to_chip(cc);
+	u16 phc_time[2];
+	int err;
+
+	err = mv88e6xxx_tai_read(chip, MV88E6XXX_PTP_GC_TIME_LO, phc_time,
+				 ARRAY_SIZE(phc_time));
+	if (err)
+		return 0;
+	else
+		return ((u32)phc_time[1] << 16) | phc_time[0];
+}
+
+/* mv88e6352_config_eventcap - configure TAI event capture
  * @event: PTP_CLOCK_PPS (internal) or PTP_CLOCK_EXTTS (external)
  * @rising: zero for falling-edge trigger, else rising-edge trigger
  *
  * This will also reset the capture sequence counter.
  */
-static int mv88e6xxx_config_eventcap(struct mv88e6xxx_chip *chip, int event,
+static int mv88e6352_config_eventcap(struct mv88e6xxx_chip *chip, int event,
 				     int rising)
 {
 	u16 global_config;
@@ -118,7 +133,7 @@ static int mv88e6xxx_config_eventcap(struct mv88e6xxx_chip *chip, int event,
 	return err;
 }
 
-static void mv88e6xxx_tai_event_work(struct work_struct *ugly)
+static void mv88e6352_tai_event_work(struct work_struct *ugly)
 {
 	struct delayed_work *dw = to_delayed_work(ugly);
 	struct mv88e6xxx_chip *chip = dw_tai_event_to_chip(dw);
@@ -232,7 +247,7 @@ static int mv88e6xxx_ptp_settime(struct ptp_clock_info *ptp,
 	return 0;
 }
 
-static int mv88e6xxx_ptp_enable_extts(struct mv88e6xxx_chip *chip,
+static int mv88e6352_ptp_enable_extts(struct mv88e6xxx_chip *chip,
 				      struct ptp_clock_request *rq, int on)
 {
 	int rising = (rq->extts.flags & PTP_RISING_EDGE);
@@ -250,18 +265,18 @@ static int mv88e6xxx_ptp_enable_extts(struct mv88e6xxx_chip *chip,
 	if (on) {
 		func = MV88E6352_G2_SCRATCH_GPIO_PCTL_EVREQ;
 
-		err = mv88e6xxx_set_gpio_func(chip, pin, func, true);
+		err = mv88e6352_set_gpio_func(chip, pin, func, true);
 		if (err)
 			goto out;
 
 		schedule_delayed_work(&chip->tai_event_work,
 				      TAI_EVENT_WORK_INTERVAL);
 
-		err = mv88e6xxx_config_eventcap(chip, PTP_CLOCK_EXTTS, rising);
+		err = mv88e6352_config_eventcap(chip, PTP_CLOCK_EXTTS, rising);
 	} else {
 		func = MV88E6352_G2_SCRATCH_GPIO_PCTL_GPIO;
 
-		err = mv88e6xxx_set_gpio_func(chip, pin, func, true);
+		err = mv88e6352_set_gpio_func(chip, pin, func, true);
 
 		cancel_delayed_work_sync(&chip->tai_event_work);
 	}
@@ -272,20 +287,20 @@ out:
 	return err;
 }
 
-static int mv88e6xxx_ptp_enable(struct ptp_clock_info *ptp,
+static int mv88e6352_ptp_enable(struct ptp_clock_info *ptp,
 				struct ptp_clock_request *rq, int on)
 {
 	struct mv88e6xxx_chip *chip = ptp_to_chip(ptp);
 
 	switch (rq->type) {
 	case PTP_CLK_REQ_EXTTS:
-		return mv88e6xxx_ptp_enable_extts(chip, rq, on);
+		return mv88e6352_ptp_enable_extts(chip, rq, on);
 	default:
 		return -EOPNOTSUPP;
 	}
 }
 
-static int mv88e6xxx_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin,
+static int mv88e6352_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin,
 				enum ptp_pin_function func, unsigned int chan)
 {
 	switch (func) {
@@ -299,6 +314,55 @@ static int mv88e6xxx_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin,
 	return 0;
 }
 
+const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = {
+	.clock_read = mv88e6352_ptp_clock_read,
+	.ptp_enable = mv88e6352_ptp_enable,
+	.ptp_verify = mv88e6352_ptp_verify,
+	.event_work = mv88e6352_tai_event_work,
+	.port_enable = mv88e6352_hwtstamp_port_enable,
+	.port_disable = mv88e6352_hwtstamp_port_disable,
+	.n_ext_ts = 1,
+	.arr0_sts_reg = MV88E6XXX_PORT_PTP_ARR0_STS,
+	.arr1_sts_reg = MV88E6XXX_PORT_PTP_ARR1_STS,
+	.dep_sts_reg = MV88E6XXX_PORT_PTP_DEP_STS,
+	.rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_EVENT) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_SYNC) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ),
+};
+
+const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops = {
+	.clock_read = mv88e6165_ptp_clock_read,
+	.global_enable = mv88e6165_global_enable,
+	.global_disable = mv88e6165_global_disable,
+	.arr0_sts_reg = MV88E6165_PORT_PTP_ARR0_STS,
+	.arr1_sts_reg = MV88E6165_PORT_PTP_ARR1_STS,
+	.dep_sts_reg = MV88E6165_PORT_PTP_DEP_STS,
+	.rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_EVENT) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_SYNC) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ),
+};
+
+static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc)
+{
+	struct mv88e6xxx_chip *chip = cc_to_chip(cc);
+
+	if (chip->info->ops->ptp_ops->clock_read)
+		return chip->info->ops->ptp_ops->clock_read(cc);
+
+	return 0;
+}
+
 /* With a 125MHz input clock, the 32-bit timestamp counter overflows in ~34.3
  * seconds; this task forces periodic reads so that we don't miss any.
  */
@@ -317,6 +381,7 @@ static void mv88e6xxx_ptp_overflow_check(struct work_struct *work)
 
 int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip)
 {
+	const struct mv88e6xxx_ptp_ops *ptp_ops = chip->info->ops->ptp_ops;
 	int i;
 
 	/* Set up the cycle counter */
@@ -330,14 +395,15 @@ int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip)
 			 ktime_to_ns(ktime_get_real()));
 
 	INIT_DELAYED_WORK(&chip->overflow_work, mv88e6xxx_ptp_overflow_check);
-	INIT_DELAYED_WORK(&chip->tai_event_work, mv88e6xxx_tai_event_work);
+	if (ptp_ops->event_work)
+		INIT_DELAYED_WORK(&chip->tai_event_work, ptp_ops->event_work);
 
 	chip->ptp_clock_info.owner = THIS_MODULE;
 	snprintf(chip->ptp_clock_info.name, sizeof(chip->ptp_clock_info.name),
 		 dev_name(chip->dev));
 	chip->ptp_clock_info.max_adj	= 1000000;
 
-	chip->ptp_clock_info.n_ext_ts	= 1;
+	chip->ptp_clock_info.n_ext_ts	= ptp_ops->n_ext_ts;
 	chip->ptp_clock_info.n_per_out	= 0;
 	chip->ptp_clock_info.n_pins	= mv88e6xxx_num_gpio(chip);
 	chip->ptp_clock_info.pps	= 0;
@@ -355,8 +421,8 @@ int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip)
 	chip->ptp_clock_info.adjtime	= mv88e6xxx_ptp_adjtime;
 	chip->ptp_clock_info.gettime64	= mv88e6xxx_ptp_gettime;
 	chip->ptp_clock_info.settime64	= mv88e6xxx_ptp_settime;
-	chip->ptp_clock_info.enable	= mv88e6xxx_ptp_enable;
-	chip->ptp_clock_info.verify	= mv88e6xxx_ptp_verify;
+	chip->ptp_clock_info.enable	= ptp_ops->ptp_enable;
+	chip->ptp_clock_info.verify	= ptp_ops->ptp_verify;
 	chip->ptp_clock_info.do_aux_work = mv88e6xxx_hwtstamp_work;
 
 	chip->ptp_clock = ptp_clock_register(&chip->ptp_clock_info, chip->dev);
@@ -373,7 +439,8 @@ void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip)
 {
 	if (chip->ptp_clock) {
 		cancel_delayed_work_sync(&chip->overflow_work);
-		cancel_delayed_work_sync(&chip->tai_event_work);
+		if (chip->info->ops->ptp_ops->event_work)
+			cancel_delayed_work_sync(&chip->tai_event_work);
 
 		ptp_clock_unregister(chip->ptp_clock);
 		chip->ptp_clock = NULL;
diff --git a/drivers/net/dsa/mv88e6xxx/ptp.h b/drivers/net/dsa/mv88e6xxx/ptp.h
index 10f271ab650d..28a030840517 100644
--- a/drivers/net/dsa/mv88e6xxx/ptp.h
+++ b/drivers/net/dsa/mv88e6xxx/ptp.h
@@ -78,6 +78,71 @@
 /* Offset 0x12: Lock Status */
 #define MV88E6XXX_TAI_LOCK_STATUS		0x12
 
+/* Offset 0x00: Ether Type */
+#define MV88E6XXX_PTP_GC_ETYPE			0x00
+
+/* 6165 Global Control Registers */
+/* Offset 0x00: Ether Type */
+#define MV88E6XXX_PTP_GC_ETYPE			0x00
+
+/* Offset 0x01: Message ID */
+#define MV88E6XXX_PTP_GC_MESSAGE_ID		0x01
+
+/* Offset 0x02: Time Stamp Arrive Time */
+#define MV88E6XXX_PTP_GC_TS_ARR_PTR		0x02
+
+/* Offset 0x03: Port Arrival Interrupt Enable */
+#define MV88E6XXX_PTP_GC_PORT_ARR_INT_EN	0x03
+
+/* Offset 0x04: Port Departure Interrupt Enable */
+#define MV88E6XXX_PTP_GC_PORT_DEP_INT_EN	0x04
+
+/* Offset 0x05: Configuration */
+#define MV88E6XXX_PTP_GC_CONFIG			0x05
+#define MV88E6XXX_PTP_GC_CONFIG_DIS_OVERWRITE	BIT(1)
+#define MV88E6XXX_PTP_GC_CONFIG_DIS_TS		BIT(0)
+
+/* Offset 0x8: Interrupt Status */
+#define MV88E6XXX_PTP_GC_INT_STATUS		0x08
+
+/* Offset 0x9/0xa: Global Time */
+#define MV88E6XXX_PTP_GC_TIME_LO		0x09
+#define MV88E6XXX_PTP_GC_TIME_HI		0x0A
+
+/* 6165 Per Port Registers */
+/* Offset 0: Arrival Time 0 Status */
+#define MV88E6165_PORT_PTP_ARR0_STS	0x00
+
+/* Offset 0x01/0x02: PTP Arrival 0 Time */
+#define MV88E6165_PORT_PTP_ARR0_TIME_LO	0x01
+#define MV88E6165_PORT_PTP_ARR0_TIME_HI	0x02
+
+/* Offset 0x03: PTP Arrival 0 Sequence ID */
+#define MV88E6165_PORT_PTP_ARR0_SEQID	0x03
+
+/* Offset 0x04: PTP Arrival 1 Status */
+#define MV88E6165_PORT_PTP_ARR1_STS	0x04
+
+/* Offset 0x05/0x6E: PTP Arrival 1 Time */
+#define MV88E6165_PORT_PTP_ARR1_TIME_LO	0x05
+#define MV88E6165_PORT_PTP_ARR1_TIME_HI	0x06
+
+/* Offset 0x07: PTP Arrival 1 Sequence ID */
+#define MV88E6165_PORT_PTP_ARR1_SEQID	0x07
+
+/* Offset 0x08: PTP Departure Status */
+#define MV88E6165_PORT_PTP_DEP_STS	0x08
+
+/* Offset 0x09/0x0a: PTP Deperture Time */
+#define MV88E6165_PORT_PTP_DEP_TIME_LO	0x09
+#define MV88E6165_PORT_PTP_DEP_TIME_HI	0x0a
+
+/* Offset 0x0b: PTP Departure Sequence ID */
+#define MV88E6165_PORT_PTP_DEP_SEQID	0x0b
+
+/* Offset 0x0d: Port Status */
+#define MV88E6164_PORT_STATUS		0x0d
+
 #ifdef CONFIG_NET_DSA_MV88E6XXX_PTP
 
 long mv88e6xxx_hwtstamp_work(struct ptp_clock_info *ptp);
@@ -87,6 +152,9 @@ void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip);
 #define ptp_to_chip(ptp) container_of(ptp, struct mv88e6xxx_chip,	\
 				      ptp_clock_info)
 
+extern const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops;
+extern const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops;
+
 #else /* !CONFIG_NET_DSA_MV88E6XXX_PTP */
 
 static inline long mv88e6xxx_hwtstamp_work(struct ptp_clock_info *ptp)
@@ -103,6 +171,9 @@ static inline void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip)
 {
 }
 
+static const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = {};
+static const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops = {};
+
 #endif /* CONFIG_NET_DSA_MV88E6XXX_PTP */
 
 #endif /* _MV88E6XXX_PTP_H */
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index 880b2cf0a530..e82983975754 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -11,6 +11,8 @@
  * (at your option) any later version.
  */
 
+#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
 #include <linux/mii.h>
 
 #include "chip.h"
@@ -35,6 +37,22 @@ static int mv88e6352_serdes_write(struct mv88e6xxx_chip *chip, int reg,
 					reg, val);
 }
 
+static int mv88e6390_serdes_read(struct mv88e6xxx_chip *chip,
+				 int lane, int device, int reg, u16 *val)
+{
+	int reg_c45 = MII_ADDR_C45 | device << 16 | reg;
+
+	return mv88e6xxx_phy_read(chip, lane, reg_c45, val);
+}
+
+static int mv88e6390_serdes_write(struct mv88e6xxx_chip *chip,
+				  int lane, int device, int reg, u16 val)
+{
+	int reg_c45 = MII_ADDR_C45 | device << 16 | reg;
+
+	return mv88e6xxx_phy_write(chip, lane, reg_c45, val);
+}
+
 static int mv88e6352_serdes_power_set(struct mv88e6xxx_chip *chip, bool on)
 {
 	u16 val, new_val;
@@ -57,14 +75,7 @@ static int mv88e6352_serdes_power_set(struct mv88e6xxx_chip *chip, bool on)
 
 static bool mv88e6352_port_has_serdes(struct mv88e6xxx_chip *chip, int port)
 {
-	u8 cmode;
-	int err;
-
-	err = mv88e6xxx_port_get_cmode(chip, port, &cmode);
-	if (err) {
-		dev_err(chip->dev, "failed to read cmode\n");
-		return false;
-	}
+	u8 cmode = chip->ports[port].cmode;
 
 	if ((cmode == MV88E6XXX_PORT_STS_CMODE_100BASE_X) ||
 	    (cmode == MV88E6XXX_PORT_STS_CMODE_1000BASE_X) ||
@@ -174,16 +185,121 @@ int mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port,
 	return ARRAY_SIZE(mv88e6352_serdes_hw_stats);
 }
 
+/* Return the SERDES lane address a port is using. Only Ports 9 and 10
+ * have SERDES lanes. Returns -ENODEV if a port does not have a lane.
+ */
+static int mv88e6390_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
+{
+	u8 cmode = chip->ports[port].cmode;
+
+	switch (port) {
+	case 9:
+		if (cmode == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode == MV88E6XXX_PORT_STS_CMODE_2500BASEX)
+			return MV88E6390_PORT9_LANE0;
+		return -ENODEV;
+	case 10:
+		if (cmode == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode == MV88E6XXX_PORT_STS_CMODE_2500BASEX)
+			return MV88E6390_PORT10_LANE0;
+		return -ENODEV;
+	default:
+		return -ENODEV;
+	}
+}
+
+/* Return the SERDES lane address a port is using. Ports 9 and 10 can
+ * use multiple lanes. If so, return the first lane the port uses.
+ * Returns -ENODEV if a port does not have a lane.
+ */
+int mv88e6390x_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
+{
+	u8 cmode_port9, cmode_port10, cmode_port;
+
+	cmode_port9 = chip->ports[9].cmode;
+	cmode_port10 = chip->ports[10].cmode;
+	cmode_port = chip->ports[port].cmode;
+
+	switch (port) {
+	case 2:
+		if (cmode_port9 == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_2500BASEX)
+			if (cmode_port == MV88E6XXX_PORT_STS_CMODE_1000BASE_X)
+				return MV88E6390_PORT9_LANE1;
+		return -ENODEV;
+	case 3:
+		if (cmode_port9 == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_2500BASEX ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_RXAUI)
+			if (cmode_port == MV88E6XXX_PORT_STS_CMODE_1000BASE_X)
+				return MV88E6390_PORT9_LANE2;
+		return -ENODEV;
+	case 4:
+		if (cmode_port9 == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_2500BASEX ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_RXAUI)
+			if (cmode_port == MV88E6XXX_PORT_STS_CMODE_1000BASE_X)
+				return MV88E6390_PORT9_LANE3;
+		return -ENODEV;
+	case 5:
+		if (cmode_port10 == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_2500BASEX)
+			if (cmode_port == MV88E6XXX_PORT_STS_CMODE_1000BASE_X)
+				return MV88E6390_PORT10_LANE1;
+		return -ENODEV;
+	case 6:
+		if (cmode_port10 == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_2500BASEX ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_RXAUI)
+			if (cmode_port == MV88E6XXX_PORT_STS_CMODE_1000BASE_X)
+				return MV88E6390_PORT10_LANE2;
+		return -ENODEV;
+	case 7:
+		if (cmode_port10 == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_2500BASEX ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_RXAUI)
+			if (cmode_port == MV88E6XXX_PORT_STS_CMODE_1000BASE_X)
+				return MV88E6390_PORT10_LANE3;
+		return -ENODEV;
+	case 9:
+		if (cmode_port9 == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_2500BASEX ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_XAUI ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_RXAUI)
+			return MV88E6390_PORT9_LANE0;
+		return -ENODEV;
+	case 10:
+		if (cmode_port10 == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_2500BASEX ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_XAUI ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_RXAUI)
+			return MV88E6390_PORT10_LANE0;
+		return -ENODEV;
+	default:
+		return -ENODEV;
+	}
+}
+
 /* Set the power on/off for 10GBASE-R and 10GBASE-X4/X2 */
-static int mv88e6390_serdes_10g(struct mv88e6xxx_chip *chip, int addr, bool on)
+static int mv88e6390_serdes_power_10g(struct mv88e6xxx_chip *chip, int lane,
+				      bool on)
 {
 	u16 val, new_val;
-	int reg_c45;
 	int err;
 
-	reg_c45 = MII_ADDR_C45 | MV88E6390_SERDES_DEVICE |
-		MV88E6390_PCS_CONTROL_1;
-	err = mv88e6xxx_phy_read(chip, addr, reg_c45, &val);
+	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
+				    MV88E6390_PCS_CONTROL_1, &val);
+
 	if (err)
 		return err;
 
@@ -195,22 +311,21 @@ static int mv88e6390_serdes_10g(struct mv88e6xxx_chip *chip, int addr, bool on)
 		new_val = val | MV88E6390_PCS_CONTROL_1_PDOWN;
 
 	if (val != new_val)
-		err = mv88e6xxx_phy_write(chip, addr, reg_c45, new_val);
+		err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
+					     MV88E6390_PCS_CONTROL_1, new_val);
 
 	return err;
 }
 
-/* Set the power on/off for 10GBASE-R and 10GBASE-X4/X2 */
-static int mv88e6390_serdes_sgmii(struct mv88e6xxx_chip *chip, int addr,
-				  bool on)
+/* Set the power on/off for SGMII and 1000Base-X */
+static int mv88e6390_serdes_power_sgmii(struct mv88e6xxx_chip *chip, int lane,
+					bool on)
 {
 	u16 val, new_val;
-	int reg_c45;
 	int err;
 
-	reg_c45 = MII_ADDR_C45 | MV88E6390_SERDES_DEVICE |
-		MV88E6390_SGMII_CONTROL;
-	err = mv88e6xxx_phy_read(chip, addr, reg_c45, &val);
+	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
+				    MV88E6390_SGMII_CONTROL, &val);
 	if (err)
 		return err;
 
@@ -222,127 +337,261 @@ static int mv88e6390_serdes_sgmii(struct mv88e6xxx_chip *chip, int addr,
 		new_val = val | MV88E6390_SGMII_CONTROL_PDOWN;
 
 	if (val != new_val)
-		err = mv88e6xxx_phy_write(chip, addr, reg_c45, new_val);
+		err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
+					     MV88E6390_SGMII_CONTROL, new_val);
 
 	return err;
 }
 
-static int mv88e6390_serdes_lower(struct mv88e6xxx_chip *chip, u8 cmode,
-				  int port_donor, int lane, bool rxaui, bool on)
+static int mv88e6390_serdes_power_lane(struct mv88e6xxx_chip *chip, int port,
+				       int lane, bool on)
 {
-	int err;
-	u8 cmode_donor;
-
-	err = mv88e6xxx_port_get_cmode(chip, port_donor, &cmode_donor);
-	if (err)
-		return err;
+	u8 cmode = chip->ports[port].cmode;
 
-	switch (cmode_donor) {
-	case MV88E6XXX_PORT_STS_CMODE_RXAUI:
-		if (!rxaui)
-			break;
-		/* Fall through */
-	case MV88E6XXX_PORT_STS_CMODE_1000BASE_X:
+	switch (cmode) {
 	case MV88E6XXX_PORT_STS_CMODE_SGMII:
+	case MV88E6XXX_PORT_STS_CMODE_1000BASE_X:
 	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
-		if (cmode == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
-		    cmode == MV88E6XXX_PORT_STS_CMODE_SGMII)
-			return	mv88e6390_serdes_sgmii(chip, lane, on);
+		return mv88e6390_serdes_power_sgmii(chip, lane, on);
+	case MV88E6XXX_PORT_STS_CMODE_XAUI:
+	case MV88E6XXX_PORT_STS_CMODE_RXAUI:
+		return mv88e6390_serdes_power_10g(chip, lane, on);
+	}
+
+	return 0;
+}
+
+int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on)
+{
+	int lane;
+
+	lane = mv88e6390_serdes_get_lane(chip, port);
+	if (lane == -ENODEV)
+		return 0;
+
+	if (lane < 0)
+		return lane;
+
+	switch (port) {
+	case 9 ... 10:
+		return mv88e6390_serdes_power_lane(chip, port, lane, on);
 	}
+
+	return 0;
+}
+
+int mv88e6390x_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on)
+{
+	int lane;
+
+	lane = mv88e6390x_serdes_get_lane(chip, port);
+	if (lane == -ENODEV)
+		return 0;
+
+	if (lane < 0)
+		return lane;
+
+	switch (port) {
+	case 2 ... 4:
+	case 5 ... 7:
+	case 9 ... 10:
+		return mv88e6390_serdes_power_lane(chip, port, lane, on);
+	}
+
 	return 0;
 }
 
-static int mv88e6390_serdes_port9(struct mv88e6xxx_chip *chip, u8 cmode,
-				  bool on)
+static void mv88e6390_serdes_irq_link_sgmii(struct mv88e6xxx_chip *chip,
+					    int port, int lane)
 {
+	struct dsa_switch *ds = chip->ds;
+	u16 status;
+	bool up;
+
+	mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
+			      MV88E6390_SGMII_STATUS, &status);
+
+	/* Status must be read twice in order to give the current link
+	 * status. Otherwise the change in link status since the last
+	 * read of the register is returned.
+	 */
+	mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
+			      MV88E6390_SGMII_STATUS, &status);
+	up = status & MV88E6390_SGMII_STATUS_LINK;
+
+	dsa_port_phylink_mac_change(ds, port, up);
+}
+
+static int mv88e6390_serdes_irq_enable_sgmii(struct mv88e6xxx_chip *chip,
+					     int lane)
+{
+	return mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
+				      MV88E6390_SGMII_INT_ENABLE,
+				      MV88E6390_SGMII_INT_LINK_DOWN |
+				      MV88E6390_SGMII_INT_LINK_UP);
+}
+
+static int mv88e6390_serdes_irq_disable_sgmii(struct mv88e6xxx_chip *chip,
+					      int lane)
+{
+	return mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
+				      MV88E6390_SGMII_INT_ENABLE, 0);
+}
+
+int mv88e6390_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port,
+				int lane)
+{
+	u8 cmode = chip->ports[port].cmode;
+	int err = 0;
+
 	switch (cmode) {
-	case MV88E6XXX_PORT_STS_CMODE_1000BASE_X:
 	case MV88E6XXX_PORT_STS_CMODE_SGMII:
-		return mv88e6390_serdes_sgmii(chip, MV88E6390_PORT9_LANE0, on);
-	case MV88E6XXX_PORT_STS_CMODE_XAUI:
-	case MV88E6XXX_PORT_STS_CMODE_RXAUI:
+	case MV88E6XXX_PORT_STS_CMODE_1000BASE_X:
 	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
-		return mv88e6390_serdes_10g(chip, MV88E6390_PORT9_LANE0, on);
+		err = mv88e6390_serdes_irq_enable_sgmii(chip, lane);
 	}
 
-	return 0;
+	return err;
 }
 
-static int mv88e6390_serdes_port10(struct mv88e6xxx_chip *chip, u8 cmode,
-				   bool on)
+int mv88e6390_serdes_irq_disable(struct mv88e6xxx_chip *chip, int port,
+				 int lane)
 {
+	u8 cmode = chip->ports[port].cmode;
+	int err = 0;
+
 	switch (cmode) {
 	case MV88E6XXX_PORT_STS_CMODE_SGMII:
-		return mv88e6390_serdes_sgmii(chip, MV88E6390_PORT10_LANE0, on);
-	case MV88E6XXX_PORT_STS_CMODE_XAUI:
-	case MV88E6XXX_PORT_STS_CMODE_RXAUI:
 	case MV88E6XXX_PORT_STS_CMODE_1000BASE_X:
 	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
-		return mv88e6390_serdes_10g(chip, MV88E6390_PORT10_LANE0, on);
+		err = mv88e6390_serdes_irq_disable_sgmii(chip, lane);
 	}
 
-	return 0;
+	return err;
 }
 
-int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on)
+static int mv88e6390_serdes_irq_status_sgmii(struct mv88e6xxx_chip *chip,
+					     int lane, u16 *status)
 {
-	u8 cmode;
 	int err;
 
-	err = mv88e6xxx_port_get_cmode(chip, port, &cmode);
-	if (err)
-		return err;
+	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
+				    MV88E6390_SGMII_INT_STATUS, status);
 
-	switch (port) {
-	case 2:
-		return mv88e6390_serdes_lower(chip, cmode, 9,
-					      MV88E6390_PORT9_LANE1,
-					      false, on);
-	case 3:
-		return mv88e6390_serdes_lower(chip, cmode, 9,
-					      MV88E6390_PORT9_LANE2,
-					      true, on);
-	case 4:
-		return mv88e6390_serdes_lower(chip, cmode, 9,
-					      MV88E6390_PORT9_LANE3,
-					      true, on);
-	case 5:
-		return mv88e6390_serdes_lower(chip, cmode, 10,
-					      MV88E6390_PORT10_LANE1,
-					      false, on);
-	case 6:
-		return mv88e6390_serdes_lower(chip, cmode, 10,
-					      MV88E6390_PORT10_LANE2,
-					      true, on);
-	case 7:
-		return mv88e6390_serdes_lower(chip, cmode, 10,
-					      MV88E6390_PORT10_LANE3,
-					      true, on);
-	case 9:
-		return mv88e6390_serdes_port9(chip, cmode, on);
-	case 10:
-		return mv88e6390_serdes_port10(chip, cmode, on);
+	return err;
+}
+
+static irqreturn_t mv88e6390_serdes_thread_fn(int irq, void *dev_id)
+{
+	struct mv88e6xxx_port *port = dev_id;
+	struct mv88e6xxx_chip *chip = port->chip;
+	irqreturn_t ret = IRQ_NONE;
+	u8 cmode = port->cmode;
+	u16 status;
+	int lane;
+	int err;
+
+	lane = mv88e6390x_serdes_get_lane(chip, port->port);
+
+	mutex_lock(&chip->reg_lock);
+
+	switch (cmode) {
+	case MV88E6XXX_PORT_STS_CMODE_SGMII:
+	case MV88E6XXX_PORT_STS_CMODE_1000BASE_X:
+	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
+		err = mv88e6390_serdes_irq_status_sgmii(chip, lane, &status);
+		if (err)
+			goto out;
+		if (status & (MV88E6390_SGMII_INT_LINK_DOWN |
+			      MV88E6390_SGMII_INT_LINK_UP)) {
+			ret = IRQ_HANDLED;
+			mv88e6390_serdes_irq_link_sgmii(chip, port->port, lane);
+		}
 	}
+out:
+	mutex_unlock(&chip->reg_lock);
 
-	return 0;
+	return ret;
 }
 
-int mv88e6341_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on)
+int mv88e6390_serdes_irq_setup(struct mv88e6xxx_chip *chip, int port)
 {
+	int lane;
 	int err;
-	u8 cmode;
 
-	if (port != 5)
+	/* Only support ports 9 and 10 at the moment */
+	if (port < 9)
 		return 0;
 
-	err = mv88e6xxx_port_get_cmode(chip, port, &cmode);
-	if (err)
+	lane = mv88e6390x_serdes_get_lane(chip, port);
+
+	if (lane == -ENODEV)
+		return 0;
+
+	if (lane < 0)
+		return lane;
+
+	chip->ports[port].serdes_irq = irq_find_mapping(chip->g2_irq.domain,
+							port);
+	if (chip->ports[port].serdes_irq < 0) {
+		dev_err(chip->dev, "Unable to map SERDES irq: %d\n",
+			chip->ports[port].serdes_irq);
+		return chip->ports[port].serdes_irq;
+	}
+
+	/* Requesting the IRQ will trigger irq callbacks. So we cannot
+	 * hold the reg_lock.
+	 */
+	mutex_unlock(&chip->reg_lock);
+	err = request_threaded_irq(chip->ports[port].serdes_irq, NULL,
+				   mv88e6390_serdes_thread_fn,
+				   IRQF_ONESHOT, "mv88e6xxx-serdes",
+				   &chip->ports[port]);
+	mutex_lock(&chip->reg_lock);
+
+	if (err) {
+		dev_err(chip->dev, "Unable to request SERDES interrupt: %d\n",
+			err);
 		return err;
+	}
+
+	return mv88e6390_serdes_irq_enable(chip, port, lane);
+}
+
+void mv88e6390_serdes_irq_free(struct mv88e6xxx_chip *chip, int port)
+{
+	int lane = mv88e6390x_serdes_get_lane(chip, port);
+
+	if (port < 9)
+		return;
+
+	if (lane < 0)
+		return;
+
+	mv88e6390_serdes_irq_disable(chip, port, lane);
+
+	/* Freeing the IRQ will trigger irq callbacks. So we cannot
+	 * hold the reg_lock.
+	 */
+	mutex_unlock(&chip->reg_lock);
+	free_irq(chip->ports[port].serdes_irq, &chip->ports[port]);
+	mutex_lock(&chip->reg_lock);
+
+	chip->ports[port].serdes_irq = 0;
+}
+
+int mv88e6341_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on)
+{
+	u8 cmode = chip->ports[port].cmode;
+
+	if (port != 5)
+		return 0;
 
 	if (cmode == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
 	    cmode == MV88E6XXX_PORT_STS_CMODE_SGMII ||
 	    cmode == MV88E6XXX_PORT_STS_CMODE_2500BASEX)
-		return mv88e6390_serdes_sgmii(chip, MV88E6341_ADDR_SERDES, on);
+		return mv88e6390_serdes_power_sgmii(chip, MV88E6341_ADDR_SERDES,
+						    on);
 
 	return 0;
 }
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h
index b6e5fbd46b5e..b1496de9c6fe 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.h
+++ b/drivers/net/dsa/mv88e6xxx/serdes.h
@@ -29,7 +29,6 @@
 #define MV88E6390_PORT10_LANE1		0x15
 #define MV88E6390_PORT10_LANE2		0x16
 #define MV88E6390_PORT10_LANE3		0x17
-#define MV88E6390_SERDES_DEVICE		(4 << 16)
 
 /* 10GBASE-R and 10GBASE-X4/X2 */
 #define MV88E6390_PCS_CONTROL_1		0x1000
@@ -43,13 +42,36 @@
 #define MV88E6390_SGMII_CONTROL_RESET		BIT(15)
 #define MV88E6390_SGMII_CONTROL_LOOPBACK	BIT(14)
 #define MV88E6390_SGMII_CONTROL_PDOWN		BIT(11)
+#define MV88E6390_SGMII_STATUS		0x2001
+#define MV88E6390_SGMII_STATUS_AN_DONE		BIT(5)
+#define MV88E6390_SGMII_STATUS_REMOTE_FAULT	BIT(4)
+#define MV88E6390_SGMII_STATUS_LINK		BIT(2)
+#define MV88E6390_SGMII_INT_ENABLE	0xa001
+#define MV88E6390_SGMII_INT_SPEED_CHANGE	BIT(14)
+#define MV88E6390_SGMII_INT_DUPLEX_CHANGE	BIT(13)
+#define MV88E6390_SGMII_INT_PAGE_RX		BIT(12)
+#define MV88E6390_SGMII_INT_AN_COMPLETE		BIT(11)
+#define MV88E6390_SGMII_INT_LINK_DOWN		BIT(10)
+#define MV88E6390_SGMII_INT_LINK_UP		BIT(9)
+#define MV88E6390_SGMII_INT_SYMBOL_ERROR	BIT(8)
+#define MV88E6390_SGMII_INT_FALSE_CARRIER	BIT(7)
+#define MV88E6390_SGMII_INT_STATUS	0xa002
 
+int mv88e6390x_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
 int mv88e6341_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
 int mv88e6352_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
 int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
+int mv88e6390x_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
+int mv88e6390_serdes_irq_setup(struct mv88e6xxx_chip *chip, int port);
+void mv88e6390_serdes_irq_free(struct mv88e6xxx_chip *chip, int port);
 int mv88e6352_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port);
 int mv88e6352_serdes_get_strings(struct mv88e6xxx_chip *chip,
 				 int port, uint8_t *data);
 int mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port,
 			       uint64_t *data);
+int mv88e6390_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port,
+				int lane);
+int mv88e6390_serdes_irq_disable(struct mv88e6xxx_chip *chip, int port,
+				 int lane);
+
 #endif
diff --git a/drivers/net/dsa/realtek-smi.c b/drivers/net/dsa/realtek-smi.c
new file mode 100644
index 000000000000..b4b839a1d095
--- /dev/null
+++ b/drivers/net/dsa/realtek-smi.c
@@ -0,0 +1,489 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Realtek Simple Management Interface (SMI) driver
+ * It can be discussed how "simple" this interface is.
+ *
+ * The SMI protocol piggy-backs the MDIO MDC and MDIO signals levels
+ * but the protocol is not MDIO at all. Instead it is a Realtek
+ * pecularity that need to bit-bang the lines in a special way to
+ * communicate with the switch.
+ *
+ * ASICs we intend to support with this driver:
+ *
+ * RTL8366   - The original version, apparently
+ * RTL8369   - Similar enough to have the same datsheet as RTL8366
+ * RTL8366RB - Probably reads out "RTL8366 revision B", has a quite
+ *             different register layout from the other two
+ * RTL8366S  - Is this "RTL8366 super"?
+ * RTL8367   - Has an OpenWRT driver as well
+ * RTL8368S  - Seems to be an alternative name for RTL8366RB
+ * RTL8370   - Also uses SMI
+ *
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ * Copyright (C) 2010 Antti Seppälä <a.seppala@gmail.com>
+ * Copyright (C) 2010 Roman Yeryomin <roman@advem.lv>
+ * Copyright (C) 2011 Colin Leitner <colin.leitner@googlemail.com>
+ * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/spinlock.h>
+#include <linux/skbuff.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_mdio.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/bitops.h>
+#include <linux/if_bridge.h>
+
+#include "realtek-smi.h"
+
+#define REALTEK_SMI_ACK_RETRY_COUNT		5
+#define REALTEK_SMI_HW_STOP_DELAY		25	/* msecs */
+#define REALTEK_SMI_HW_START_DELAY		100	/* msecs */
+
+static inline void realtek_smi_clk_delay(struct realtek_smi *smi)
+{
+	ndelay(smi->clk_delay);
+}
+
+static void realtek_smi_start(struct realtek_smi *smi)
+{
+	/* Set GPIO pins to output mode, with initial state:
+	 * SCK = 0, SDA = 1
+	 */
+	gpiod_direction_output(smi->mdc, 0);
+	gpiod_direction_output(smi->mdio, 1);
+	realtek_smi_clk_delay(smi);
+
+	/* CLK 1: 0 -> 1, 1 -> 0 */
+	gpiod_set_value(smi->mdc, 1);
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdc, 0);
+	realtek_smi_clk_delay(smi);
+
+	/* CLK 2: */
+	gpiod_set_value(smi->mdc, 1);
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdio, 0);
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdc, 0);
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdio, 1);
+}
+
+static void realtek_smi_stop(struct realtek_smi *smi)
+{
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdio, 0);
+	gpiod_set_value(smi->mdc, 1);
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdio, 1);
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdc, 1);
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdc, 0);
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdc, 1);
+
+	/* Add a click */
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdc, 0);
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdc, 1);
+
+	/* Set GPIO pins to input mode */
+	gpiod_direction_input(smi->mdio);
+	gpiod_direction_input(smi->mdc);
+}
+
+static void realtek_smi_write_bits(struct realtek_smi *smi, u32 data, u32 len)
+{
+	for (; len > 0; len--) {
+		realtek_smi_clk_delay(smi);
+
+		/* Prepare data */
+		gpiod_set_value(smi->mdio, !!(data & (1 << (len - 1))));
+		realtek_smi_clk_delay(smi);
+
+		/* Clocking */
+		gpiod_set_value(smi->mdc, 1);
+		realtek_smi_clk_delay(smi);
+		gpiod_set_value(smi->mdc, 0);
+	}
+}
+
+static void realtek_smi_read_bits(struct realtek_smi *smi, u32 len, u32 *data)
+{
+	gpiod_direction_input(smi->mdio);
+
+	for (*data = 0; len > 0; len--) {
+		u32 u;
+
+		realtek_smi_clk_delay(smi);
+
+		/* Clocking */
+		gpiod_set_value(smi->mdc, 1);
+		realtek_smi_clk_delay(smi);
+		u = !!gpiod_get_value(smi->mdio);
+		gpiod_set_value(smi->mdc, 0);
+
+		*data |= (u << (len - 1));
+	}
+
+	gpiod_direction_output(smi->mdio, 0);
+}
+
+static int realtek_smi_wait_for_ack(struct realtek_smi *smi)
+{
+	int retry_cnt;
+
+	retry_cnt = 0;
+	do {
+		u32 ack;
+
+		realtek_smi_read_bits(smi, 1, &ack);
+		if (ack == 0)
+			break;
+
+		if (++retry_cnt > REALTEK_SMI_ACK_RETRY_COUNT) {
+			dev_err(smi->dev, "ACK timeout\n");
+			return -ETIMEDOUT;
+		}
+	} while (1);
+
+	return 0;
+}
+
+static int realtek_smi_write_byte(struct realtek_smi *smi, u8 data)
+{
+	realtek_smi_write_bits(smi, data, 8);
+	return realtek_smi_wait_for_ack(smi);
+}
+
+static int realtek_smi_write_byte_noack(struct realtek_smi *smi, u8 data)
+{
+	realtek_smi_write_bits(smi, data, 8);
+	return 0;
+}
+
+static int realtek_smi_read_byte0(struct realtek_smi *smi, u8 *data)
+{
+	u32 t;
+
+	/* Read data */
+	realtek_smi_read_bits(smi, 8, &t);
+	*data = (t & 0xff);
+
+	/* Send an ACK */
+	realtek_smi_write_bits(smi, 0x00, 1);
+
+	return 0;
+}
+
+static int realtek_smi_read_byte1(struct realtek_smi *smi, u8 *data)
+{
+	u32 t;
+
+	/* Read data */
+	realtek_smi_read_bits(smi, 8, &t);
+	*data = (t & 0xff);
+
+	/* Send an ACK */
+	realtek_smi_write_bits(smi, 0x01, 1);
+
+	return 0;
+}
+
+static int realtek_smi_read_reg(struct realtek_smi *smi, u32 addr, u32 *data)
+{
+	unsigned long flags;
+	u8 lo = 0;
+	u8 hi = 0;
+	int ret;
+
+	spin_lock_irqsave(&smi->lock, flags);
+
+	realtek_smi_start(smi);
+
+	/* Send READ command */
+	ret = realtek_smi_write_byte(smi, smi->cmd_read);
+	if (ret)
+		goto out;
+
+	/* Set ADDR[7:0] */
+	ret = realtek_smi_write_byte(smi, addr & 0xff);
+	if (ret)
+		goto out;
+
+	/* Set ADDR[15:8] */
+	ret = realtek_smi_write_byte(smi, addr >> 8);
+	if (ret)
+		goto out;
+
+	/* Read DATA[7:0] */
+	realtek_smi_read_byte0(smi, &lo);
+	/* Read DATA[15:8] */
+	realtek_smi_read_byte1(smi, &hi);
+
+	*data = ((u32)lo) | (((u32)hi) << 8);
+
+	ret = 0;
+
+ out:
+	realtek_smi_stop(smi);
+	spin_unlock_irqrestore(&smi->lock, flags);
+
+	return ret;
+}
+
+static int realtek_smi_write_reg(struct realtek_smi *smi,
+				 u32 addr, u32 data, bool ack)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&smi->lock, flags);
+
+	realtek_smi_start(smi);
+
+	/* Send WRITE command */
+	ret = realtek_smi_write_byte(smi, smi->cmd_write);
+	if (ret)
+		goto out;
+
+	/* Set ADDR[7:0] */
+	ret = realtek_smi_write_byte(smi, addr & 0xff);
+	if (ret)
+		goto out;
+
+	/* Set ADDR[15:8] */
+	ret = realtek_smi_write_byte(smi, addr >> 8);
+	if (ret)
+		goto out;
+
+	/* Write DATA[7:0] */
+	ret = realtek_smi_write_byte(smi, data & 0xff);
+	if (ret)
+		goto out;
+
+	/* Write DATA[15:8] */
+	if (ack)
+		ret = realtek_smi_write_byte(smi, data >> 8);
+	else
+		ret = realtek_smi_write_byte_noack(smi, data >> 8);
+	if (ret)
+		goto out;
+
+	ret = 0;
+
+ out:
+	realtek_smi_stop(smi);
+	spin_unlock_irqrestore(&smi->lock, flags);
+
+	return ret;
+}
+
+/* There is one single case when we need to use this accessor and that
+ * is when issueing soft reset. Since the device reset as soon as we write
+ * that bit, no ACK will come back for natural reasons.
+ */
+int realtek_smi_write_reg_noack(struct realtek_smi *smi, u32 addr,
+				u32 data)
+{
+	return realtek_smi_write_reg(smi, addr, data, false);
+}
+EXPORT_SYMBOL_GPL(realtek_smi_write_reg_noack);
+
+/* Regmap accessors */
+
+static int realtek_smi_write(void *ctx, u32 reg, u32 val)
+{
+	struct realtek_smi *smi = ctx;
+
+	return realtek_smi_write_reg(smi, reg, val, true);
+}
+
+static int realtek_smi_read(void *ctx, u32 reg, u32 *val)
+{
+	struct realtek_smi *smi = ctx;
+
+	return realtek_smi_read_reg(smi, reg, val);
+}
+
+static const struct regmap_config realtek_smi_mdio_regmap_config = {
+	.reg_bits = 10, /* A4..A0 R4..R0 */
+	.val_bits = 16,
+	.reg_stride = 1,
+	/* PHY regs are at 0x8000 */
+	.max_register = 0xffff,
+	.reg_format_endian = REGMAP_ENDIAN_BIG,
+	.reg_read = realtek_smi_read,
+	.reg_write = realtek_smi_write,
+	.cache_type = REGCACHE_NONE,
+};
+
+static int realtek_smi_mdio_read(struct mii_bus *bus, int addr, int regnum)
+{
+	struct realtek_smi *smi = bus->priv;
+
+	return smi->ops->phy_read(smi, addr, regnum);
+}
+
+static int realtek_smi_mdio_write(struct mii_bus *bus, int addr, int regnum,
+				  u16 val)
+{
+	struct realtek_smi *smi = bus->priv;
+
+	return smi->ops->phy_write(smi, addr, regnum, val);
+}
+
+int realtek_smi_setup_mdio(struct realtek_smi *smi)
+{
+	struct device_node *mdio_np;
+	int ret;
+
+	mdio_np = of_find_compatible_node(smi->dev->of_node, NULL,
+					  "realtek,smi-mdio");
+	if (!mdio_np) {
+		dev_err(smi->dev, "no MDIO bus node\n");
+		return -ENODEV;
+	}
+
+	smi->slave_mii_bus = devm_mdiobus_alloc(smi->dev);
+	if (!smi->slave_mii_bus)
+		return -ENOMEM;
+	smi->slave_mii_bus->priv = smi;
+	smi->slave_mii_bus->name = "SMI slave MII";
+	smi->slave_mii_bus->read = realtek_smi_mdio_read;
+	smi->slave_mii_bus->write = realtek_smi_mdio_write;
+	snprintf(smi->slave_mii_bus->id, MII_BUS_ID_SIZE, "SMI-%d",
+		 smi->ds->index);
+	smi->slave_mii_bus->dev.of_node = mdio_np;
+	smi->slave_mii_bus->parent = smi->dev;
+	smi->ds->slave_mii_bus = smi->slave_mii_bus;
+
+	ret = of_mdiobus_register(smi->slave_mii_bus, mdio_np);
+	if (ret) {
+		dev_err(smi->dev, "unable to register MDIO bus %s\n",
+			smi->slave_mii_bus->id);
+		of_node_put(mdio_np);
+	}
+
+	return 0;
+}
+
+static int realtek_smi_probe(struct platform_device *pdev)
+{
+	const struct realtek_smi_variant *var;
+	struct device *dev = &pdev->dev;
+	struct realtek_smi *smi;
+	struct device_node *np;
+	int ret;
+
+	var = of_device_get_match_data(dev);
+	np = dev->of_node;
+
+	smi = devm_kzalloc(dev, sizeof(*smi), GFP_KERNEL);
+	if (!smi)
+		return -ENOMEM;
+	smi->map = devm_regmap_init(dev, NULL, smi,
+				    &realtek_smi_mdio_regmap_config);
+	if (IS_ERR(smi->map)) {
+		ret = PTR_ERR(smi->map);
+		dev_err(dev, "regmap init failed: %d\n", ret);
+		return ret;
+	}
+
+	/* Link forward and backward */
+	smi->dev = dev;
+	smi->clk_delay = var->clk_delay;
+	smi->cmd_read = var->cmd_read;
+	smi->cmd_write = var->cmd_write;
+	smi->ops = var->ops;
+
+	dev_set_drvdata(dev, smi);
+	spin_lock_init(&smi->lock);
+
+	/* TODO: if power is software controlled, set up any regulators here */
+
+	/* Assert then deassert RESET */
+	smi->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(smi->reset)) {
+		dev_err(dev, "failed to get RESET GPIO\n");
+		return PTR_ERR(smi->reset);
+	}
+	msleep(REALTEK_SMI_HW_STOP_DELAY);
+	gpiod_set_value(smi->reset, 0);
+	msleep(REALTEK_SMI_HW_START_DELAY);
+	dev_info(dev, "deasserted RESET\n");
+
+	/* Fetch MDIO pins */
+	smi->mdc = devm_gpiod_get_optional(dev, "mdc", GPIOD_OUT_LOW);
+	if (IS_ERR(smi->mdc))
+		return PTR_ERR(smi->mdc);
+	smi->mdio = devm_gpiod_get_optional(dev, "mdio", GPIOD_OUT_LOW);
+	if (IS_ERR(smi->mdio))
+		return PTR_ERR(smi->mdio);
+
+	smi->leds_disabled = of_property_read_bool(np, "realtek,disable-leds");
+
+	ret = smi->ops->detect(smi);
+	if (ret) {
+		dev_err(dev, "unable to detect switch\n");
+		return ret;
+	}
+
+	smi->ds = dsa_switch_alloc(dev, smi->num_ports);
+	if (!smi->ds)
+		return -ENOMEM;
+	smi->ds->priv = smi;
+
+	smi->ds->ops = var->ds_ops;
+	ret = dsa_register_switch(smi->ds);
+	if (ret) {
+		dev_err(dev, "unable to register switch ret = %d\n", ret);
+		return ret;
+	}
+	return 0;
+}
+
+static int realtek_smi_remove(struct platform_device *pdev)
+{
+	struct realtek_smi *smi = dev_get_drvdata(&pdev->dev);
+
+	dsa_unregister_switch(smi->ds);
+	gpiod_set_value(smi->reset, 1);
+
+	return 0;
+}
+
+static const struct of_device_id realtek_smi_of_match[] = {
+	{
+		.compatible = "realtek,rtl8366rb",
+		.data = &rtl8366rb_variant,
+	},
+	{
+		/* FIXME: add support for RTL8366S and more */
+		.compatible = "realtek,rtl8366s",
+		.data = NULL,
+	},
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, realtek_smi_of_match);
+
+static struct platform_driver realtek_smi_driver = {
+	.driver = {
+		.name = "realtek-smi",
+		.of_match_table = of_match_ptr(realtek_smi_of_match),
+	},
+	.probe  = realtek_smi_probe,
+	.remove = realtek_smi_remove,
+};
+module_platform_driver(realtek_smi_driver);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/dsa/realtek-smi.h b/drivers/net/dsa/realtek-smi.h
new file mode 100644
index 000000000000..9a63b51e1d82
--- /dev/null
+++ b/drivers/net/dsa/realtek-smi.h
@@ -0,0 +1,144 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Realtek SMI interface driver defines
+ *
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org>
+ */
+
+#ifndef _REALTEK_SMI_H
+#define _REALTEK_SMI_H
+
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+#include <linux/gpio/consumer.h>
+#include <net/dsa.h>
+
+struct realtek_smi_ops;
+struct dentry;
+struct inode;
+struct file;
+
+struct rtl8366_mib_counter {
+	unsigned int	base;
+	unsigned int	offset;
+	unsigned int	length;
+	const char	*name;
+};
+
+struct rtl8366_vlan_mc {
+	u16	vid;
+	u16	untag;
+	u16	member;
+	u8	fid;
+	u8	priority;
+};
+
+struct rtl8366_vlan_4k {
+	u16	vid;
+	u16	untag;
+	u16	member;
+	u8	fid;
+};
+
+struct realtek_smi {
+	struct device		*dev;
+	struct gpio_desc	*reset;
+	struct gpio_desc	*mdc;
+	struct gpio_desc	*mdio;
+	struct regmap		*map;
+	struct mii_bus		*slave_mii_bus;
+
+	unsigned int		clk_delay;
+	u8			cmd_read;
+	u8			cmd_write;
+	spinlock_t		lock; /* Locks around command writes */
+	struct dsa_switch	*ds;
+	struct irq_domain	*irqdomain;
+	bool			leds_disabled;
+
+	unsigned int		cpu_port;
+	unsigned int		num_ports;
+	unsigned int		num_vlan_mc;
+	unsigned int		num_mib_counters;
+	struct rtl8366_mib_counter *mib_counters;
+
+	const struct realtek_smi_ops *ops;
+
+	int			vlan_enabled;
+	int			vlan4k_enabled;
+
+	char			buf[4096];
+};
+
+/**
+ * struct realtek_smi_ops - vtable for the per-SMI-chiptype operations
+ * @detect: detects the chiptype
+ */
+struct realtek_smi_ops {
+	int	(*detect)(struct realtek_smi *smi);
+	int	(*reset_chip)(struct realtek_smi *smi);
+	int	(*setup)(struct realtek_smi *smi);
+	void	(*cleanup)(struct realtek_smi *smi);
+	int	(*get_mib_counter)(struct realtek_smi *smi,
+				   int port,
+				   struct rtl8366_mib_counter *mib,
+				   u64 *mibvalue);
+	int	(*get_vlan_mc)(struct realtek_smi *smi, u32 index,
+			       struct rtl8366_vlan_mc *vlanmc);
+	int	(*set_vlan_mc)(struct realtek_smi *smi, u32 index,
+			       const struct rtl8366_vlan_mc *vlanmc);
+	int	(*get_vlan_4k)(struct realtek_smi *smi, u32 vid,
+			       struct rtl8366_vlan_4k *vlan4k);
+	int	(*set_vlan_4k)(struct realtek_smi *smi,
+			       const struct rtl8366_vlan_4k *vlan4k);
+	int	(*get_mc_index)(struct realtek_smi *smi, int port, int *val);
+	int	(*set_mc_index)(struct realtek_smi *smi, int port, int index);
+	bool	(*is_vlan_valid)(struct realtek_smi *smi, unsigned int vlan);
+	int	(*enable_vlan)(struct realtek_smi *smi, bool enable);
+	int	(*enable_vlan4k)(struct realtek_smi *smi, bool enable);
+	int	(*enable_port)(struct realtek_smi *smi, int port, bool enable);
+	int	(*phy_read)(struct realtek_smi *smi, int phy, int regnum);
+	int	(*phy_write)(struct realtek_smi *smi, int phy, int regnum,
+			     u16 val);
+};
+
+struct realtek_smi_variant {
+	const struct dsa_switch_ops *ds_ops;
+	const struct realtek_smi_ops *ops;
+	unsigned int clk_delay;
+	u8 cmd_read;
+	u8 cmd_write;
+};
+
+/* SMI core calls */
+int realtek_smi_write_reg_noack(struct realtek_smi *smi, u32 addr,
+				u32 data);
+int realtek_smi_setup_mdio(struct realtek_smi *smi);
+
+/* RTL8366 library helpers */
+int rtl8366_mc_is_used(struct realtek_smi *smi, int mc_index, int *used);
+int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member,
+		     u32 untag, u32 fid);
+int rtl8366_get_pvid(struct realtek_smi *smi, int port, int *val);
+int rtl8366_set_pvid(struct realtek_smi *smi, unsigned int port,
+		     unsigned int vid);
+int rtl8366_enable_vlan4k(struct realtek_smi *smi, bool enable);
+int rtl8366_enable_vlan(struct realtek_smi *smi, bool enable);
+int rtl8366_reset_vlan(struct realtek_smi *smi);
+int rtl8366_init_vlan(struct realtek_smi *smi);
+int rtl8366_vlan_filtering(struct dsa_switch *ds, int port,
+			   bool vlan_filtering);
+int rtl8366_vlan_prepare(struct dsa_switch *ds, int port,
+			 const struct switchdev_obj_port_vlan *vlan);
+void rtl8366_vlan_add(struct dsa_switch *ds, int port,
+		      const struct switchdev_obj_port_vlan *vlan);
+int rtl8366_vlan_del(struct dsa_switch *ds, int port,
+		     const struct switchdev_obj_port_vlan *vlan);
+void rtl8366_get_strings(struct dsa_switch *ds, int port, u32 stringset,
+			 uint8_t *data);
+int rtl8366_get_sset_count(struct dsa_switch *ds, int port, int sset);
+void rtl8366_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data);
+
+extern const struct realtek_smi_variant rtl8366rb_variant;
+
+#endif /*  _REALTEK_SMI_H */
diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c
new file mode 100644
index 000000000000..6dedd43442cc
--- /dev/null
+++ b/drivers/net/dsa/rtl8366.c
@@ -0,0 +1,515 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Realtek SMI library helpers for the RTL8366x variants
+ * RTL8366RB and RTL8366S
+ *
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org>
+ * Copyright (C) 2010 Antti Seppälä <a.seppala@gmail.com>
+ * Copyright (C) 2010 Roman Yeryomin <roman@advem.lv>
+ * Copyright (C) 2011 Colin Leitner <colin.leitner@googlemail.com>
+ */
+#include <linux/if_bridge.h>
+#include <net/dsa.h>
+
+#include "realtek-smi.h"
+
+int rtl8366_mc_is_used(struct realtek_smi *smi, int mc_index, int *used)
+{
+	int ret;
+	int i;
+
+	*used = 0;
+	for (i = 0; i < smi->num_ports; i++) {
+		int index = 0;
+
+		ret = smi->ops->get_mc_index(smi, i, &index);
+		if (ret)
+			return ret;
+
+		if (mc_index == index) {
+			*used = 1;
+			break;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_mc_is_used);
+
+int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member,
+		     u32 untag, u32 fid)
+{
+	struct rtl8366_vlan_4k vlan4k;
+	int ret;
+	int i;
+
+	/* Update the 4K table */
+	ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k);
+	if (ret)
+		return ret;
+
+	vlan4k.member = member;
+	vlan4k.untag = untag;
+	vlan4k.fid = fid;
+	ret = smi->ops->set_vlan_4k(smi, &vlan4k);
+	if (ret)
+		return ret;
+
+	/* Try to find an existing MC entry for this VID */
+	for (i = 0; i < smi->num_vlan_mc; i++) {
+		struct rtl8366_vlan_mc vlanmc;
+
+		ret = smi->ops->get_vlan_mc(smi, i, &vlanmc);
+		if (ret)
+			return ret;
+
+		if (vid == vlanmc.vid) {
+			/* update the MC entry */
+			vlanmc.member = member;
+			vlanmc.untag = untag;
+			vlanmc.fid = fid;
+
+			ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+			break;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(rtl8366_set_vlan);
+
+int rtl8366_get_pvid(struct realtek_smi *smi, int port, int *val)
+{
+	struct rtl8366_vlan_mc vlanmc;
+	int ret;
+	int index;
+
+	ret = smi->ops->get_mc_index(smi, port, &index);
+	if (ret)
+		return ret;
+
+	ret = smi->ops->get_vlan_mc(smi, index, &vlanmc);
+	if (ret)
+		return ret;
+
+	*val = vlanmc.vid;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_get_pvid);
+
+int rtl8366_set_pvid(struct realtek_smi *smi, unsigned int port,
+		     unsigned int vid)
+{
+	struct rtl8366_vlan_mc vlanmc;
+	struct rtl8366_vlan_4k vlan4k;
+	int ret;
+	int i;
+
+	/* Try to find an existing MC entry for this VID */
+	for (i = 0; i < smi->num_vlan_mc; i++) {
+		ret = smi->ops->get_vlan_mc(smi, i, &vlanmc);
+		if (ret)
+			return ret;
+
+		if (vid == vlanmc.vid) {
+			ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+			if (ret)
+				return ret;
+
+			ret = smi->ops->set_mc_index(smi, port, i);
+			return ret;
+		}
+	}
+
+	/* We have no MC entry for this VID, try to find an empty one */
+	for (i = 0; i < smi->num_vlan_mc; i++) {
+		ret = smi->ops->get_vlan_mc(smi, i, &vlanmc);
+		if (ret)
+			return ret;
+
+		if (vlanmc.vid == 0 && vlanmc.member == 0) {
+			/* Update the entry from the 4K table */
+			ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k);
+			if (ret)
+				return ret;
+
+			vlanmc.vid = vid;
+			vlanmc.member = vlan4k.member;
+			vlanmc.untag = vlan4k.untag;
+			vlanmc.fid = vlan4k.fid;
+			ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+			if (ret)
+				return ret;
+
+			ret = smi->ops->set_mc_index(smi, port, i);
+			return ret;
+		}
+	}
+
+	/* MC table is full, try to find an unused entry and replace it */
+	for (i = 0; i < smi->num_vlan_mc; i++) {
+		int used;
+
+		ret = rtl8366_mc_is_used(smi, i, &used);
+		if (ret)
+			return ret;
+
+		if (!used) {
+			/* Update the entry from the 4K table */
+			ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k);
+			if (ret)
+				return ret;
+
+			vlanmc.vid = vid;
+			vlanmc.member = vlan4k.member;
+			vlanmc.untag = vlan4k.untag;
+			vlanmc.fid = vlan4k.fid;
+			ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+			if (ret)
+				return ret;
+
+			ret = smi->ops->set_mc_index(smi, port, i);
+			return ret;
+		}
+	}
+
+	dev_err(smi->dev,
+		"all VLAN member configurations are in use\n");
+
+	return -ENOSPC;
+}
+EXPORT_SYMBOL_GPL(rtl8366_set_pvid);
+
+int rtl8366_enable_vlan4k(struct realtek_smi *smi, bool enable)
+{
+	int ret;
+
+	/* To enable 4k VLAN, ordinary VLAN must be enabled first,
+	 * but if we disable 4k VLAN it is fine to leave ordinary
+	 * VLAN enabled.
+	 */
+	if (enable) {
+		/* Make sure VLAN is ON */
+		ret = smi->ops->enable_vlan(smi, true);
+		if (ret)
+			return ret;
+
+		smi->vlan_enabled = true;
+	}
+
+	ret = smi->ops->enable_vlan4k(smi, enable);
+	if (ret)
+		return ret;
+
+	smi->vlan4k_enabled = enable;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_enable_vlan4k);
+
+int rtl8366_enable_vlan(struct realtek_smi *smi, bool enable)
+{
+	int ret;
+
+	ret = smi->ops->enable_vlan(smi, enable);
+	if (ret)
+		return ret;
+
+	smi->vlan_enabled = enable;
+
+	/* If we turn VLAN off, make sure that we turn off
+	 * 4k VLAN as well, if that happened to be on.
+	 */
+	if (!enable) {
+		smi->vlan4k_enabled = false;
+		ret = smi->ops->enable_vlan4k(smi, false);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(rtl8366_enable_vlan);
+
+int rtl8366_reset_vlan(struct realtek_smi *smi)
+{
+	struct rtl8366_vlan_mc vlanmc;
+	int ret;
+	int i;
+
+	rtl8366_enable_vlan(smi, false);
+	rtl8366_enable_vlan4k(smi, false);
+
+	/* Clear the 16 VLAN member configurations */
+	vlanmc.vid = 0;
+	vlanmc.priority = 0;
+	vlanmc.member = 0;
+	vlanmc.untag = 0;
+	vlanmc.fid = 0;
+	for (i = 0; i < smi->num_vlan_mc; i++) {
+		ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_reset_vlan);
+
+int rtl8366_init_vlan(struct realtek_smi *smi)
+{
+	int port;
+	int ret;
+
+	ret = rtl8366_reset_vlan(smi);
+	if (ret)
+		return ret;
+
+	/* Loop over the available ports, for each port, associate
+	 * it with the VLAN (port+1)
+	 */
+	for (port = 0; port < smi->num_ports; port++) {
+		u32 mask;
+
+		if (port == smi->cpu_port)
+			/* For the CPU port, make all ports members of this
+			 * VLAN.
+			 */
+			mask = GENMASK(smi->num_ports - 1, 0);
+		else
+			/* For all other ports, enable itself plus the
+			 * CPU port.
+			 */
+			mask = BIT(port) | BIT(smi->cpu_port);
+
+		/* For each port, set the port as member of VLAN (port+1)
+		 * and untagged, except for the CPU port: the CPU port (5) is
+		 * member of VLAN 6 and so are ALL the other ports as well.
+		 * Use filter 0 (no filter).
+		 */
+		dev_info(smi->dev, "VLAN%d port mask for port %d, %08x\n",
+			 (port + 1), port, mask);
+		ret = rtl8366_set_vlan(smi, (port + 1), mask, mask, 0);
+		if (ret)
+			return ret;
+
+		dev_info(smi->dev, "VLAN%d port %d, PVID set to %d\n",
+			 (port + 1), port, (port + 1));
+		ret = rtl8366_set_pvid(smi, port, (port + 1));
+		if (ret)
+			return ret;
+	}
+
+	return rtl8366_enable_vlan(smi, true);
+}
+EXPORT_SYMBOL_GPL(rtl8366_init_vlan);
+
+int rtl8366_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering)
+{
+	struct realtek_smi *smi = ds->priv;
+	struct rtl8366_vlan_4k vlan4k;
+	int ret;
+
+	if (!smi->ops->is_vlan_valid(smi, port))
+		return -EINVAL;
+
+	dev_info(smi->dev, "%s filtering on port %d\n",
+		 vlan_filtering ? "enable" : "disable",
+		 port);
+
+	/* TODO:
+	 * The hardware support filter ID (FID) 0..7, I have no clue how to
+	 * support this in the driver when the callback only says on/off.
+	 */
+	ret = smi->ops->get_vlan_4k(smi, port, &vlan4k);
+	if (ret)
+		return ret;
+
+	/* Just set the filter to FID 1 for now then */
+	ret = rtl8366_set_vlan(smi, port,
+			       vlan4k.member,
+			       vlan4k.untag,
+			       1);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_vlan_filtering);
+
+int rtl8366_vlan_prepare(struct dsa_switch *ds, int port,
+			 const struct switchdev_obj_port_vlan *vlan)
+{
+	struct realtek_smi *smi = ds->priv;
+	int ret;
+
+	if (!smi->ops->is_vlan_valid(smi, port))
+		return -EINVAL;
+
+	dev_info(smi->dev, "prepare VLANs %04x..%04x\n",
+		 vlan->vid_begin, vlan->vid_end);
+
+	/* Enable VLAN in the hardware
+	 * FIXME: what's with this 4k business?
+	 * Just rtl8366_enable_vlan() seems inconclusive.
+	 */
+	ret = rtl8366_enable_vlan4k(smi, true);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_vlan_prepare);
+
+void rtl8366_vlan_add(struct dsa_switch *ds, int port,
+		      const struct switchdev_obj_port_vlan *vlan)
+{
+	bool untagged = !!(vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED);
+	bool pvid = !!(vlan->flags & BRIDGE_VLAN_INFO_PVID);
+	struct realtek_smi *smi = ds->priv;
+	u32 member = 0;
+	u32 untag = 0;
+	u16 vid;
+	int ret;
+
+	if (!smi->ops->is_vlan_valid(smi, port))
+		return;
+
+	dev_info(smi->dev, "add VLAN on port %d, %s, %s\n",
+		 port,
+		 untagged ? "untagged" : "tagged",
+		 pvid ? " PVID" : "no PVID");
+
+	if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port))
+		dev_err(smi->dev, "port is DSA or CPU port\n");
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+		int pvid_val = 0;
+
+		dev_info(smi->dev, "add VLAN %04x\n", vid);
+		member |= BIT(port);
+
+		if (untagged)
+			untag |= BIT(port);
+
+		/* To ensure that we have a valid MC entry for this VLAN,
+		 * initialize the port VLAN ID here.
+		 */
+		ret = rtl8366_get_pvid(smi, port, &pvid_val);
+		if (ret < 0) {
+			dev_err(smi->dev, "could not lookup PVID for port %d\n",
+				port);
+			return;
+		}
+		if (pvid_val == 0) {
+			ret = rtl8366_set_pvid(smi, port, vid);
+			if (ret < 0)
+				return;
+		}
+	}
+
+	ret = rtl8366_set_vlan(smi, port, member, untag, 0);
+	if (ret)
+		dev_err(smi->dev,
+			"failed to set up VLAN %04x",
+			vid);
+}
+EXPORT_SYMBOL_GPL(rtl8366_vlan_add);
+
+int rtl8366_vlan_del(struct dsa_switch *ds, int port,
+		     const struct switchdev_obj_port_vlan *vlan)
+{
+	struct realtek_smi *smi = ds->priv;
+	u16 vid;
+	int ret;
+
+	dev_info(smi->dev, "del VLAN on port %d\n", port);
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+		int i;
+
+		dev_info(smi->dev, "del VLAN %04x\n", vid);
+
+		for (i = 0; i < smi->num_vlan_mc; i++) {
+			struct rtl8366_vlan_mc vlanmc;
+
+			ret = smi->ops->get_vlan_mc(smi, i, &vlanmc);
+			if (ret)
+				return ret;
+
+			if (vid == vlanmc.vid) {
+				/* clear VLAN member configurations */
+				vlanmc.vid = 0;
+				vlanmc.priority = 0;
+				vlanmc.member = 0;
+				vlanmc.untag = 0;
+				vlanmc.fid = 0;
+
+				ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+				if (ret) {
+					dev_err(smi->dev,
+						"failed to remove VLAN %04x\n",
+						vid);
+					return ret;
+				}
+				break;
+			}
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_vlan_del);
+
+void rtl8366_get_strings(struct dsa_switch *ds, int port, u32 stringset,
+			 uint8_t *data)
+{
+	struct realtek_smi *smi = ds->priv;
+	struct rtl8366_mib_counter *mib;
+	int i;
+
+	if (port >= smi->num_ports)
+		return;
+
+	for (i = 0; i < smi->num_mib_counters; i++) {
+		mib = &smi->mib_counters[i];
+		strncpy(data + i * ETH_GSTRING_LEN,
+			mib->name, ETH_GSTRING_LEN);
+	}
+}
+EXPORT_SYMBOL_GPL(rtl8366_get_strings);
+
+int rtl8366_get_sset_count(struct dsa_switch *ds, int port, int sset)
+{
+	struct realtek_smi *smi = ds->priv;
+
+	/* We only support SS_STATS */
+	if (sset != ETH_SS_STATS)
+		return 0;
+	if (port >= smi->num_ports)
+		return -EINVAL;
+
+	return smi->num_mib_counters;
+}
+EXPORT_SYMBOL_GPL(rtl8366_get_sset_count);
+
+void rtl8366_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data)
+{
+	struct realtek_smi *smi = ds->priv;
+	int i;
+	int ret;
+
+	if (port >= smi->num_ports)
+		return;
+
+	for (i = 0; i < smi->num_mib_counters; i++) {
+		struct rtl8366_mib_counter *mib;
+		u64 mibvalue = 0;
+
+		mib = &smi->mib_counters[i];
+		ret = smi->ops->get_mib_counter(smi, port, mib, &mibvalue);
+		if (ret) {
+			dev_err(smi->dev, "error reading MIB counter %s\n",
+				mib->name);
+		}
+		data[i] = mibvalue;
+	}
+}
+EXPORT_SYMBOL_GPL(rtl8366_get_ethtool_stats);
diff --git a/drivers/net/dsa/rtl8366rb.c b/drivers/net/dsa/rtl8366rb.c
new file mode 100644
index 000000000000..a4d5049df692
--- /dev/null
+++ b/drivers/net/dsa/rtl8366rb.c
@@ -0,0 +1,1454 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Realtek SMI subdriver for the Realtek RTL8366RB ethernet switch
+ *
+ * This is a sparsely documented chip, the only viable documentation seems
+ * to be a patched up code drop from the vendor that appear in various
+ * GPL source trees.
+ *
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org>
+ * Copyright (C) 2010 Antti Seppälä <a.seppala@gmail.com>
+ * Copyright (C) 2010 Roman Yeryomin <roman@advem.lv>
+ * Copyright (C) 2011 Colin Leitner <colin.leitner@googlemail.com>
+ */
+
+#include <linux/bitops.h>
+#include <linux/etherdevice.h>
+#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/of_irq.h>
+#include <linux/regmap.h>
+
+#include "realtek-smi.h"
+
+#define RTL8366RB_PORT_NUM_CPU		5
+#define RTL8366RB_NUM_PORTS		6
+#define RTL8366RB_PHY_NO_MAX		4
+#define RTL8366RB_PHY_ADDR_MAX		31
+
+/* Switch Global Configuration register */
+#define RTL8366RB_SGCR				0x0000
+#define RTL8366RB_SGCR_EN_BC_STORM_CTRL		BIT(0)
+#define RTL8366RB_SGCR_MAX_LENGTH(a)		((a) << 4)
+#define RTL8366RB_SGCR_MAX_LENGTH_MASK		RTL8366RB_SGCR_MAX_LENGTH(0x3)
+#define RTL8366RB_SGCR_MAX_LENGTH_1522		RTL8366RB_SGCR_MAX_LENGTH(0x0)
+#define RTL8366RB_SGCR_MAX_LENGTH_1536		RTL8366RB_SGCR_MAX_LENGTH(0x1)
+#define RTL8366RB_SGCR_MAX_LENGTH_1552		RTL8366RB_SGCR_MAX_LENGTH(0x2)
+#define RTL8366RB_SGCR_MAX_LENGTH_9216		RTL8366RB_SGCR_MAX_LENGTH(0x3)
+#define RTL8366RB_SGCR_EN_VLAN			BIT(13)
+#define RTL8366RB_SGCR_EN_VLAN_4KTB		BIT(14)
+
+/* Port Enable Control register */
+#define RTL8366RB_PECR				0x0001
+
+/* Switch Security Control registers */
+#define RTL8366RB_SSCR0				0x0002
+#define RTL8366RB_SSCR1				0x0003
+#define RTL8366RB_SSCR2				0x0004
+#define RTL8366RB_SSCR2_DROP_UNKNOWN_DA		BIT(0)
+
+/* Port Mode Control registers */
+#define RTL8366RB_PMC0				0x0005
+#define RTL8366RB_PMC0_SPI			BIT(0)
+#define RTL8366RB_PMC0_EN_AUTOLOAD		BIT(1)
+#define RTL8366RB_PMC0_PROBE			BIT(2)
+#define RTL8366RB_PMC0_DIS_BISR			BIT(3)
+#define RTL8366RB_PMC0_ADCTEST			BIT(4)
+#define RTL8366RB_PMC0_SRAM_DIAG		BIT(5)
+#define RTL8366RB_PMC0_EN_SCAN			BIT(6)
+#define RTL8366RB_PMC0_P4_IOMODE_SHIFT		7
+#define RTL8366RB_PMC0_P4_IOMODE_MASK		GENMASK(9, 7)
+#define RTL8366RB_PMC0_P5_IOMODE_SHIFT		10
+#define RTL8366RB_PMC0_P5_IOMODE_MASK		GENMASK(12, 10)
+#define RTL8366RB_PMC0_SDSMODE_SHIFT		13
+#define RTL8366RB_PMC0_SDSMODE_MASK		GENMASK(15, 13)
+#define RTL8366RB_PMC1				0x0006
+
+/* Port Mirror Control Register */
+#define RTL8366RB_PMCR				0x0007
+#define RTL8366RB_PMCR_SOURCE_PORT(a)		(a)
+#define RTL8366RB_PMCR_SOURCE_PORT_MASK		0x000f
+#define RTL8366RB_PMCR_MONITOR_PORT(a)		((a) << 4)
+#define RTL8366RB_PMCR_MONITOR_PORT_MASK	0x00f0
+#define RTL8366RB_PMCR_MIRROR_RX		BIT(8)
+#define RTL8366RB_PMCR_MIRROR_TX		BIT(9)
+#define RTL8366RB_PMCR_MIRROR_SPC		BIT(10)
+#define RTL8366RB_PMCR_MIRROR_ISO		BIT(11)
+
+/* bits 0..7 = port 0, bits 8..15 = port 1 */
+#define RTL8366RB_PAACR0		0x0010
+/* bits 0..7 = port 2, bits 8..15 = port 3 */
+#define RTL8366RB_PAACR1		0x0011
+/* bits 0..7 = port 4, bits 8..15 = port 5 */
+#define RTL8366RB_PAACR2		0x0012
+#define RTL8366RB_PAACR_SPEED_10M	0
+#define RTL8366RB_PAACR_SPEED_100M	1
+#define RTL8366RB_PAACR_SPEED_1000M	2
+#define RTL8366RB_PAACR_FULL_DUPLEX	BIT(2)
+#define RTL8366RB_PAACR_LINK_UP		BIT(4)
+#define RTL8366RB_PAACR_TX_PAUSE	BIT(5)
+#define RTL8366RB_PAACR_RX_PAUSE	BIT(6)
+#define RTL8366RB_PAACR_AN		BIT(7)
+
+#define RTL8366RB_PAACR_CPU_PORT	(RTL8366RB_PAACR_SPEED_1000M | \
+					 RTL8366RB_PAACR_FULL_DUPLEX | \
+					 RTL8366RB_PAACR_LINK_UP | \
+					 RTL8366RB_PAACR_TX_PAUSE | \
+					 RTL8366RB_PAACR_RX_PAUSE)
+
+/* bits 0..7 = port 0, bits 8..15 = port 1 */
+#define RTL8366RB_PSTAT0		0x0014
+/* bits 0..7 = port 2, bits 8..15 = port 3 */
+#define RTL8366RB_PSTAT1		0x0015
+/* bits 0..7 = port 4, bits 8..15 = port 5 */
+#define RTL8366RB_PSTAT2		0x0016
+
+#define RTL8366RB_POWER_SAVING_REG	0x0021
+
+/* CPU port control reg */
+#define RTL8368RB_CPU_CTRL_REG		0x0061
+#define RTL8368RB_CPU_PORTS_MSK		0x00FF
+/* Enables inserting custom tag length/type 0x8899 */
+#define RTL8368RB_CPU_INSTAG		BIT(15)
+
+#define RTL8366RB_SMAR0			0x0070 /* bits 0..15 */
+#define RTL8366RB_SMAR1			0x0071 /* bits 16..31 */
+#define RTL8366RB_SMAR2			0x0072 /* bits 32..47 */
+
+#define RTL8366RB_RESET_CTRL_REG		0x0100
+#define RTL8366RB_CHIP_CTRL_RESET_HW		BIT(0)
+#define RTL8366RB_CHIP_CTRL_RESET_SW		BIT(1)
+
+#define RTL8366RB_CHIP_ID_REG			0x0509
+#define RTL8366RB_CHIP_ID_8366			0x5937
+#define RTL8366RB_CHIP_VERSION_CTRL_REG		0x050A
+#define RTL8366RB_CHIP_VERSION_MASK		0xf
+
+/* PHY registers control */
+#define RTL8366RB_PHY_ACCESS_CTRL_REG		0x8000
+#define RTL8366RB_PHY_CTRL_READ			BIT(0)
+#define RTL8366RB_PHY_CTRL_WRITE		0
+#define RTL8366RB_PHY_ACCESS_BUSY_REG		0x8001
+#define RTL8366RB_PHY_INT_BUSY			BIT(0)
+#define RTL8366RB_PHY_EXT_BUSY			BIT(4)
+#define RTL8366RB_PHY_ACCESS_DATA_REG		0x8002
+#define RTL8366RB_PHY_EXT_CTRL_REG		0x8010
+#define RTL8366RB_PHY_EXT_WRDATA_REG		0x8011
+#define RTL8366RB_PHY_EXT_RDDATA_REG		0x8012
+
+#define RTL8366RB_PHY_REG_MASK			0x1f
+#define RTL8366RB_PHY_PAGE_OFFSET		5
+#define RTL8366RB_PHY_PAGE_MASK			(0xf << 5)
+#define RTL8366RB_PHY_NO_OFFSET			9
+#define RTL8366RB_PHY_NO_MASK			(0x1f << 9)
+
+#define RTL8366RB_VLAN_INGRESS_CTRL2_REG	0x037f
+
+/* LED control registers */
+#define RTL8366RB_LED_BLINKRATE_REG		0x0430
+#define RTL8366RB_LED_BLINKRATE_MASK		0x0007
+#define RTL8366RB_LED_BLINKRATE_28MS		0x0000
+#define RTL8366RB_LED_BLINKRATE_56MS		0x0001
+#define RTL8366RB_LED_BLINKRATE_84MS		0x0002
+#define RTL8366RB_LED_BLINKRATE_111MS		0x0003
+#define RTL8366RB_LED_BLINKRATE_222MS		0x0004
+#define RTL8366RB_LED_BLINKRATE_446MS		0x0005
+
+#define RTL8366RB_LED_CTRL_REG			0x0431
+#define RTL8366RB_LED_OFF			0x0
+#define RTL8366RB_LED_DUP_COL			0x1
+#define RTL8366RB_LED_LINK_ACT			0x2
+#define RTL8366RB_LED_SPD1000			0x3
+#define RTL8366RB_LED_SPD100			0x4
+#define RTL8366RB_LED_SPD10			0x5
+#define RTL8366RB_LED_SPD1000_ACT		0x6
+#define RTL8366RB_LED_SPD100_ACT		0x7
+#define RTL8366RB_LED_SPD10_ACT			0x8
+#define RTL8366RB_LED_SPD100_10_ACT		0x9
+#define RTL8366RB_LED_FIBER			0xa
+#define RTL8366RB_LED_AN_FAULT			0xb
+#define RTL8366RB_LED_LINK_RX			0xc
+#define RTL8366RB_LED_LINK_TX			0xd
+#define RTL8366RB_LED_MASTER			0xe
+#define RTL8366RB_LED_FORCE			0xf
+#define RTL8366RB_LED_0_1_CTRL_REG		0x0432
+#define RTL8366RB_LED_1_OFFSET			6
+#define RTL8366RB_LED_2_3_CTRL_REG		0x0433
+#define RTL8366RB_LED_3_OFFSET			6
+
+#define RTL8366RB_MIB_COUNT			33
+#define RTL8366RB_GLOBAL_MIB_COUNT		1
+#define RTL8366RB_MIB_COUNTER_PORT_OFFSET	0x0050
+#define RTL8366RB_MIB_COUNTER_BASE		0x1000
+#define RTL8366RB_MIB_CTRL_REG			0x13F0
+#define RTL8366RB_MIB_CTRL_USER_MASK		0x0FFC
+#define RTL8366RB_MIB_CTRL_BUSY_MASK		BIT(0)
+#define RTL8366RB_MIB_CTRL_RESET_MASK		BIT(1)
+#define RTL8366RB_MIB_CTRL_PORT_RESET(_p)	BIT(2 + (_p))
+#define RTL8366RB_MIB_CTRL_GLOBAL_RESET		BIT(11)
+
+#define RTL8366RB_PORT_VLAN_CTRL_BASE		0x0063
+#define RTL8366RB_PORT_VLAN_CTRL_REG(_p)  \
+		(RTL8366RB_PORT_VLAN_CTRL_BASE + (_p) / 4)
+#define RTL8366RB_PORT_VLAN_CTRL_MASK		0xf
+#define RTL8366RB_PORT_VLAN_CTRL_SHIFT(_p)	(4 * ((_p) % 4))
+
+#define RTL8366RB_VLAN_TABLE_READ_BASE		0x018C
+#define RTL8366RB_VLAN_TABLE_WRITE_BASE		0x0185
+
+#define RTL8366RB_TABLE_ACCESS_CTRL_REG		0x0180
+#define RTL8366RB_TABLE_VLAN_READ_CTRL		0x0E01
+#define RTL8366RB_TABLE_VLAN_WRITE_CTRL		0x0F01
+
+#define RTL8366RB_VLAN_MC_BASE(_x)		(0x0020 + (_x) * 3)
+
+#define RTL8366RB_PORT_LINK_STATUS_BASE		0x0014
+#define RTL8366RB_PORT_STATUS_SPEED_MASK	0x0003
+#define RTL8366RB_PORT_STATUS_DUPLEX_MASK	0x0004
+#define RTL8366RB_PORT_STATUS_LINK_MASK		0x0010
+#define RTL8366RB_PORT_STATUS_TXPAUSE_MASK	0x0020
+#define RTL8366RB_PORT_STATUS_RXPAUSE_MASK	0x0040
+#define RTL8366RB_PORT_STATUS_AN_MASK		0x0080
+
+#define RTL8366RB_NUM_VLANS		16
+#define RTL8366RB_NUM_LEDGROUPS		4
+#define RTL8366RB_NUM_VIDS		4096
+#define RTL8366RB_PRIORITYMAX		7
+#define RTL8366RB_FIDMAX		7
+
+#define RTL8366RB_PORT_1		BIT(0) /* In userspace port 0 */
+#define RTL8366RB_PORT_2		BIT(1) /* In userspace port 1 */
+#define RTL8366RB_PORT_3		BIT(2) /* In userspace port 2 */
+#define RTL8366RB_PORT_4		BIT(3) /* In userspace port 3 */
+#define RTL8366RB_PORT_5		BIT(4) /* In userspace port 4 */
+
+#define RTL8366RB_PORT_CPU		BIT(5) /* CPU port */
+
+#define RTL8366RB_PORT_ALL		(RTL8366RB_PORT_1 |	\
+					 RTL8366RB_PORT_2 |	\
+					 RTL8366RB_PORT_3 |	\
+					 RTL8366RB_PORT_4 |	\
+					 RTL8366RB_PORT_5 |	\
+					 RTL8366RB_PORT_CPU)
+
+#define RTL8366RB_PORT_ALL_BUT_CPU	(RTL8366RB_PORT_1 |	\
+					 RTL8366RB_PORT_2 |	\
+					 RTL8366RB_PORT_3 |	\
+					 RTL8366RB_PORT_4 |	\
+					 RTL8366RB_PORT_5)
+
+#define RTL8366RB_PORT_ALL_EXTERNAL	(RTL8366RB_PORT_1 |	\
+					 RTL8366RB_PORT_2 |	\
+					 RTL8366RB_PORT_3 |	\
+					 RTL8366RB_PORT_4)
+
+#define RTL8366RB_PORT_ALL_INTERNAL	 RTL8366RB_PORT_CPU
+
+/* First configuration word per member config, VID and prio */
+#define RTL8366RB_VLAN_VID_MASK		0xfff
+#define RTL8366RB_VLAN_PRIORITY_SHIFT	12
+#define RTL8366RB_VLAN_PRIORITY_MASK	0x7
+/* Second configuration word per member config, member and untagged */
+#define RTL8366RB_VLAN_UNTAG_SHIFT	8
+#define RTL8366RB_VLAN_UNTAG_MASK	0xff
+#define RTL8366RB_VLAN_MEMBER_MASK	0xff
+/* Third config word per member config, STAG currently unused */
+#define RTL8366RB_VLAN_STAG_MBR_MASK	0xff
+#define RTL8366RB_VLAN_STAG_MBR_SHIFT	8
+#define RTL8366RB_VLAN_STAG_IDX_MASK	0x7
+#define RTL8366RB_VLAN_STAG_IDX_SHIFT	5
+#define RTL8366RB_VLAN_FID_MASK		0x7
+
+/* Port ingress bandwidth control */
+#define RTL8366RB_IB_BASE		0x0200
+#define RTL8366RB_IB_REG(pnum)		(RTL8366RB_IB_BASE + (pnum))
+#define RTL8366RB_IB_BDTH_MASK		0x3fff
+#define RTL8366RB_IB_PREIFG		BIT(14)
+
+/* Port egress bandwidth control */
+#define RTL8366RB_EB_BASE		0x02d1
+#define RTL8366RB_EB_REG(pnum)		(RTL8366RB_EB_BASE + (pnum))
+#define RTL8366RB_EB_BDTH_MASK		0x3fff
+#define RTL8366RB_EB_PREIFG_REG		0x02f8
+#define RTL8366RB_EB_PREIFG		BIT(9)
+
+#define RTL8366RB_BDTH_SW_MAX		1048512 /* 1048576? */
+#define RTL8366RB_BDTH_UNIT		64
+#define RTL8366RB_BDTH_REG_DEFAULT	16383
+
+/* QOS */
+#define RTL8366RB_QOS			BIT(15)
+/* Include/Exclude Preamble and IFG (20 bytes). 0:Exclude, 1:Include. */
+#define RTL8366RB_QOS_DEFAULT_PREIFG	1
+
+/* Interrupt handling */
+#define RTL8366RB_INTERRUPT_CONTROL_REG	0x0440
+#define RTL8366RB_INTERRUPT_POLARITY	BIT(0)
+#define RTL8366RB_P4_RGMII_LED		BIT(2)
+#define RTL8366RB_INTERRUPT_MASK_REG	0x0441
+#define RTL8366RB_INTERRUPT_LINK_CHGALL	GENMASK(11, 0)
+#define RTL8366RB_INTERRUPT_ACLEXCEED	BIT(8)
+#define RTL8366RB_INTERRUPT_STORMEXCEED	BIT(9)
+#define RTL8366RB_INTERRUPT_P4_FIBER	BIT(12)
+#define RTL8366RB_INTERRUPT_P4_UTP	BIT(13)
+#define RTL8366RB_INTERRUPT_VALID	(RTL8366RB_INTERRUPT_LINK_CHGALL | \
+					 RTL8366RB_INTERRUPT_ACLEXCEED | \
+					 RTL8366RB_INTERRUPT_STORMEXCEED | \
+					 RTL8366RB_INTERRUPT_P4_FIBER | \
+					 RTL8366RB_INTERRUPT_P4_UTP)
+#define RTL8366RB_INTERRUPT_STATUS_REG	0x0442
+#define RTL8366RB_NUM_INTERRUPT		14 /* 0..13 */
+
+/* bits 0..5 enable force when cleared */
+#define RTL8366RB_MAC_FORCE_CTRL_REG	0x0F11
+
+#define RTL8366RB_OAM_PARSER_REG	0x0F14
+#define RTL8366RB_OAM_MULTIPLEXER_REG	0x0F15
+
+#define RTL8366RB_GREEN_FEATURE_REG	0x0F51
+#define RTL8366RB_GREEN_FEATURE_MSK	0x0007
+#define RTL8366RB_GREEN_FEATURE_TX	BIT(0)
+#define RTL8366RB_GREEN_FEATURE_RX	BIT(2)
+
+static struct rtl8366_mib_counter rtl8366rb_mib_counters[] = {
+	{ 0,  0, 4, "IfInOctets"				},
+	{ 0,  4, 4, "EtherStatsOctets"				},
+	{ 0,  8, 2, "EtherStatsUnderSizePkts"			},
+	{ 0, 10, 2, "EtherFragments"				},
+	{ 0, 12, 2, "EtherStatsPkts64Octets"			},
+	{ 0, 14, 2, "EtherStatsPkts65to127Octets"		},
+	{ 0, 16, 2, "EtherStatsPkts128to255Octets"		},
+	{ 0, 18, 2, "EtherStatsPkts256to511Octets"		},
+	{ 0, 20, 2, "EtherStatsPkts512to1023Octets"		},
+	{ 0, 22, 2, "EtherStatsPkts1024to1518Octets"		},
+	{ 0, 24, 2, "EtherOversizeStats"			},
+	{ 0, 26, 2, "EtherStatsJabbers"				},
+	{ 0, 28, 2, "IfInUcastPkts"				},
+	{ 0, 30, 2, "EtherStatsMulticastPkts"			},
+	{ 0, 32, 2, "EtherStatsBroadcastPkts"			},
+	{ 0, 34, 2, "EtherStatsDropEvents"			},
+	{ 0, 36, 2, "Dot3StatsFCSErrors"			},
+	{ 0, 38, 2, "Dot3StatsSymbolErrors"			},
+	{ 0, 40, 2, "Dot3InPauseFrames"				},
+	{ 0, 42, 2, "Dot3ControlInUnknownOpcodes"		},
+	{ 0, 44, 4, "IfOutOctets"				},
+	{ 0, 48, 2, "Dot3StatsSingleCollisionFrames"		},
+	{ 0, 50, 2, "Dot3StatMultipleCollisionFrames"		},
+	{ 0, 52, 2, "Dot3sDeferredTransmissions"		},
+	{ 0, 54, 2, "Dot3StatsLateCollisions"			},
+	{ 0, 56, 2, "EtherStatsCollisions"			},
+	{ 0, 58, 2, "Dot3StatsExcessiveCollisions"		},
+	{ 0, 60, 2, "Dot3OutPauseFrames"			},
+	{ 0, 62, 2, "Dot1dBasePortDelayExceededDiscards"	},
+	{ 0, 64, 2, "Dot1dTpPortInDiscards"			},
+	{ 0, 66, 2, "IfOutUcastPkts"				},
+	{ 0, 68, 2, "IfOutMulticastPkts"			},
+	{ 0, 70, 2, "IfOutBroadcastPkts"			},
+};
+
+static int rtl8366rb_get_mib_counter(struct realtek_smi *smi,
+				     int port,
+				     struct rtl8366_mib_counter *mib,
+				     u64 *mibvalue)
+{
+	u32 addr, val;
+	int ret;
+	int i;
+
+	addr = RTL8366RB_MIB_COUNTER_BASE +
+		RTL8366RB_MIB_COUNTER_PORT_OFFSET * (port) +
+		mib->offset;
+
+	/* Writing access counter address first
+	 * then ASIC will prepare 64bits counter wait for being retrived
+	 */
+	ret = regmap_write(smi->map, addr, 0); /* Write whatever */
+	if (ret)
+		return ret;
+
+	/* Read MIB control register */
+	ret = regmap_read(smi->map, RTL8366RB_MIB_CTRL_REG, &val);
+	if (ret)
+		return -EIO;
+
+	if (val & RTL8366RB_MIB_CTRL_BUSY_MASK)
+		return -EBUSY;
+
+	if (val & RTL8366RB_MIB_CTRL_RESET_MASK)
+		return -EIO;
+
+	/* Read each individual MIB 16 bits at the time */
+	*mibvalue = 0;
+	for (i = mib->length; i > 0; i--) {
+		ret = regmap_read(smi->map, addr + (i - 1), &val);
+		if (ret)
+			return ret;
+		*mibvalue = (*mibvalue << 16) | (val & 0xFFFF);
+	}
+	return 0;
+}
+
+static u32 rtl8366rb_get_irqmask(struct irq_data *d)
+{
+	int line = irqd_to_hwirq(d);
+	u32 val;
+
+	/* For line interrupts we combine link down in bits
+	 * 6..11 with link up in bits 0..5 into one interrupt.
+	 */
+	if (line < 12)
+		val = BIT(line) | BIT(line + 6);
+	else
+		val = BIT(line);
+	return val;
+}
+
+static void rtl8366rb_mask_irq(struct irq_data *d)
+{
+	struct realtek_smi *smi = irq_data_get_irq_chip_data(d);
+	int ret;
+
+	ret = regmap_update_bits(smi->map, RTL8366RB_INTERRUPT_MASK_REG,
+				 rtl8366rb_get_irqmask(d), 0);
+	if (ret)
+		dev_err(smi->dev, "could not mask IRQ\n");
+}
+
+static void rtl8366rb_unmask_irq(struct irq_data *d)
+{
+	struct realtek_smi *smi = irq_data_get_irq_chip_data(d);
+	int ret;
+
+	ret = regmap_update_bits(smi->map, RTL8366RB_INTERRUPT_MASK_REG,
+				 rtl8366rb_get_irqmask(d),
+				 rtl8366rb_get_irqmask(d));
+	if (ret)
+		dev_err(smi->dev, "could not unmask IRQ\n");
+}
+
+static irqreturn_t rtl8366rb_irq(int irq, void *data)
+{
+	struct realtek_smi *smi = data;
+	u32 stat;
+	int ret;
+
+	/* This clears the IRQ status register */
+	ret = regmap_read(smi->map, RTL8366RB_INTERRUPT_STATUS_REG,
+			  &stat);
+	if (ret) {
+		dev_err(smi->dev, "can't read interrupt status\n");
+		return IRQ_NONE;
+	}
+	stat &= RTL8366RB_INTERRUPT_VALID;
+	if (!stat)
+		return IRQ_NONE;
+	while (stat) {
+		int line = __ffs(stat);
+		int child_irq;
+
+		stat &= ~BIT(line);
+		/* For line interrupts we combine link down in bits
+		 * 6..11 with link up in bits 0..5 into one interrupt.
+		 */
+		if (line < 12 && line > 5)
+			line -= 5;
+		child_irq = irq_find_mapping(smi->irqdomain, line);
+		handle_nested_irq(child_irq);
+	}
+	return IRQ_HANDLED;
+}
+
+static struct irq_chip rtl8366rb_irq_chip = {
+	.name = "RTL8366RB",
+	.irq_mask = rtl8366rb_mask_irq,
+	.irq_unmask = rtl8366rb_unmask_irq,
+};
+
+static int rtl8366rb_irq_map(struct irq_domain *domain, unsigned int irq,
+			     irq_hw_number_t hwirq)
+{
+	irq_set_chip_data(irq, domain->host_data);
+	irq_set_chip_and_handler(irq, &rtl8366rb_irq_chip, handle_simple_irq);
+	irq_set_nested_thread(irq, 1);
+	irq_set_noprobe(irq);
+
+	return 0;
+}
+
+static void rtl8366rb_irq_unmap(struct irq_domain *d, unsigned int irq)
+{
+	irq_set_nested_thread(irq, 0);
+	irq_set_chip_and_handler(irq, NULL, NULL);
+	irq_set_chip_data(irq, NULL);
+}
+
+static const struct irq_domain_ops rtl8366rb_irqdomain_ops = {
+	.map = rtl8366rb_irq_map,
+	.unmap = rtl8366rb_irq_unmap,
+	.xlate  = irq_domain_xlate_onecell,
+};
+
+static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi)
+{
+	struct device_node *intc;
+	unsigned long irq_trig;
+	int irq;
+	int ret;
+	u32 val;
+	int i;
+
+	intc = of_get_child_by_name(smi->dev->of_node, "interrupt-controller");
+	if (!intc) {
+		dev_err(smi->dev, "missing child interrupt-controller node\n");
+		return -EINVAL;
+	}
+	/* RB8366RB IRQs cascade off this one */
+	irq = of_irq_get(intc, 0);
+	if (irq <= 0) {
+		dev_err(smi->dev, "failed to get parent IRQ\n");
+		return irq ? irq : -EINVAL;
+	}
+
+	/* This clears the IRQ status register */
+	ret = regmap_read(smi->map, RTL8366RB_INTERRUPT_STATUS_REG,
+			  &val);
+	if (ret) {
+		dev_err(smi->dev, "can't read interrupt status\n");
+		return ret;
+	}
+
+	/* Fetch IRQ edge information from the descriptor */
+	irq_trig = irqd_get_trigger_type(irq_get_irq_data(irq));
+	switch (irq_trig) {
+	case IRQF_TRIGGER_RISING:
+	case IRQF_TRIGGER_HIGH:
+		dev_info(smi->dev, "active high/rising IRQ\n");
+		val = 0;
+		break;
+	case IRQF_TRIGGER_FALLING:
+	case IRQF_TRIGGER_LOW:
+		dev_info(smi->dev, "active low/falling IRQ\n");
+		val = RTL8366RB_INTERRUPT_POLARITY;
+		break;
+	}
+	ret = regmap_update_bits(smi->map, RTL8366RB_INTERRUPT_CONTROL_REG,
+				 RTL8366RB_INTERRUPT_POLARITY,
+				 val);
+	if (ret) {
+		dev_err(smi->dev, "could not configure IRQ polarity\n");
+		return ret;
+	}
+
+	ret = devm_request_threaded_irq(smi->dev, irq, NULL,
+					rtl8366rb_irq, IRQF_ONESHOT,
+					"RTL8366RB", smi);
+	if (ret) {
+		dev_err(smi->dev, "unable to request irq: %d\n", ret);
+		return ret;
+	}
+	smi->irqdomain = irq_domain_add_linear(intc,
+					       RTL8366RB_NUM_INTERRUPT,
+					       &rtl8366rb_irqdomain_ops,
+					       smi);
+	if (!smi->irqdomain) {
+		dev_err(smi->dev, "failed to create IRQ domain\n");
+		return -EINVAL;
+	}
+	for (i = 0; i < smi->num_ports; i++)
+		irq_set_parent(irq_create_mapping(smi->irqdomain, i), irq);
+
+	return 0;
+}
+
+static int rtl8366rb_set_addr(struct realtek_smi *smi)
+{
+	u8 addr[ETH_ALEN];
+	u16 val;
+	int ret;
+
+	eth_random_addr(addr);
+
+	dev_info(smi->dev, "set MAC: %02X:%02X:%02X:%02X:%02X:%02X\n",
+		 addr[0], addr[1], addr[2], addr[3], addr[4], addr[5]);
+	val = addr[0] << 8 | addr[1];
+	ret = regmap_write(smi->map, RTL8366RB_SMAR0, val);
+	if (ret)
+		return ret;
+	val = addr[2] << 8 | addr[3];
+	ret = regmap_write(smi->map, RTL8366RB_SMAR1, val);
+	if (ret)
+		return ret;
+	val = addr[4] << 8 | addr[5];
+	ret = regmap_write(smi->map, RTL8366RB_SMAR2, val);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/* Found in a vendor driver */
+
+/* For the "version 0" early silicon, appear in most source releases */
+static const u16 rtl8366rb_init_jam_ver_0[] = {
+	0x000B, 0x0001, 0x03A6, 0x0100, 0x03A7, 0x0001, 0x02D1, 0x3FFF,
+	0x02D2, 0x3FFF, 0x02D3, 0x3FFF, 0x02D4, 0x3FFF, 0x02D5, 0x3FFF,
+	0x02D6, 0x3FFF, 0x02D7, 0x3FFF, 0x02D8, 0x3FFF, 0x022B, 0x0688,
+	0x022C, 0x0FAC, 0x03D0, 0x4688, 0x03D1, 0x01F5, 0x0000, 0x0830,
+	0x02F9, 0x0200, 0x02F7, 0x7FFF, 0x02F8, 0x03FF, 0x0080, 0x03E8,
+	0x0081, 0x00CE, 0x0082, 0x00DA, 0x0083, 0x0230, 0xBE0F, 0x2000,
+	0x0231, 0x422A, 0x0232, 0x422A, 0x0233, 0x422A, 0x0234, 0x422A,
+	0x0235, 0x422A, 0x0236, 0x422A, 0x0237, 0x422A, 0x0238, 0x422A,
+	0x0239, 0x422A, 0x023A, 0x422A, 0x023B, 0x422A, 0x023C, 0x422A,
+	0x023D, 0x422A, 0x023E, 0x422A, 0x023F, 0x422A, 0x0240, 0x422A,
+	0x0241, 0x422A, 0x0242, 0x422A, 0x0243, 0x422A, 0x0244, 0x422A,
+	0x0245, 0x422A, 0x0246, 0x422A, 0x0247, 0x422A, 0x0248, 0x422A,
+	0x0249, 0x0146, 0x024A, 0x0146, 0x024B, 0x0146, 0xBE03, 0xC961,
+	0x024D, 0x0146, 0x024E, 0x0146, 0x024F, 0x0146, 0x0250, 0x0146,
+	0xBE64, 0x0226, 0x0252, 0x0146, 0x0253, 0x0146, 0x024C, 0x0146,
+	0x0251, 0x0146, 0x0254, 0x0146, 0xBE62, 0x3FD0, 0x0084, 0x0320,
+	0x0255, 0x0146, 0x0256, 0x0146, 0x0257, 0x0146, 0x0258, 0x0146,
+	0x0259, 0x0146, 0x025A, 0x0146, 0x025B, 0x0146, 0x025C, 0x0146,
+	0x025D, 0x0146, 0x025E, 0x0146, 0x025F, 0x0146, 0x0260, 0x0146,
+	0x0261, 0xA23F, 0x0262, 0x0294, 0x0263, 0xA23F, 0x0264, 0x0294,
+	0x0265, 0xA23F, 0x0266, 0x0294, 0x0267, 0xA23F, 0x0268, 0x0294,
+	0x0269, 0xA23F, 0x026A, 0x0294, 0x026B, 0xA23F, 0x026C, 0x0294,
+	0x026D, 0xA23F, 0x026E, 0x0294, 0x026F, 0xA23F, 0x0270, 0x0294,
+	0x02F5, 0x0048, 0xBE09, 0x0E00, 0xBE1E, 0x0FA0, 0xBE14, 0x8448,
+	0xBE15, 0x1007, 0xBE4A, 0xA284, 0xC454, 0x3F0B, 0xC474, 0x3F0B,
+	0xBE48, 0x3672, 0xBE4B, 0x17A7, 0xBE4C, 0x0B15, 0xBE52, 0x0EDD,
+	0xBE49, 0x8C00, 0xBE5B, 0x785C, 0xBE5C, 0x785C, 0xBE5D, 0x785C,
+	0xBE61, 0x368A, 0xBE63, 0x9B84, 0xC456, 0xCC13, 0xC476, 0xCC13,
+	0xBE65, 0x307D, 0xBE6D, 0x0005, 0xBE6E, 0xE120, 0xBE2E, 0x7BAF,
+};
+
+/* This v1 init sequence is from Belkin F5D8235 U-Boot release */
+static const u16 rtl8366rb_init_jam_ver_1[] = {
+	0x0000, 0x0830, 0x0001, 0x8000, 0x0400, 0x8130, 0xBE78, 0x3C3C,
+	0x0431, 0x5432, 0xBE37, 0x0CE4, 0x02FA, 0xFFDF, 0x02FB, 0xFFE0,
+	0xC44C, 0x1585, 0xC44C, 0x1185, 0xC44C, 0x1585, 0xC46C, 0x1585,
+	0xC46C, 0x1185, 0xC46C, 0x1585, 0xC451, 0x2135, 0xC471, 0x2135,
+	0xBE10, 0x8140, 0xBE15, 0x0007, 0xBE6E, 0xE120, 0xBE69, 0xD20F,
+	0xBE6B, 0x0320, 0xBE24, 0xB000, 0xBE23, 0xFF51, 0xBE22, 0xDF20,
+	0xBE21, 0x0140, 0xBE20, 0x00BB, 0xBE24, 0xB800, 0xBE24, 0x0000,
+	0xBE24, 0x7000, 0xBE23, 0xFF51, 0xBE22, 0xDF60, 0xBE21, 0x0140,
+	0xBE20, 0x0077, 0xBE24, 0x7800, 0xBE24, 0x0000, 0xBE2E, 0x7B7A,
+	0xBE36, 0x0CE4, 0x02F5, 0x0048, 0xBE77, 0x2940, 0x000A, 0x83E0,
+	0xBE79, 0x3C3C, 0xBE00, 0x1340,
+};
+
+/* This v2 init sequence is from Belkin F5D8235 U-Boot release */
+static const u16 rtl8366rb_init_jam_ver_2[] = {
+	0x0450, 0x0000, 0x0400, 0x8130, 0x000A, 0x83ED, 0x0431, 0x5432,
+	0xC44F, 0x6250, 0xC46F, 0x6250, 0xC456, 0x0C14, 0xC476, 0x0C14,
+	0xC44C, 0x1C85, 0xC44C, 0x1885, 0xC44C, 0x1C85, 0xC46C, 0x1C85,
+	0xC46C, 0x1885, 0xC46C, 0x1C85, 0xC44C, 0x0885, 0xC44C, 0x0881,
+	0xC44C, 0x0885, 0xC46C, 0x0885, 0xC46C, 0x0881, 0xC46C, 0x0885,
+	0xBE2E, 0x7BA7, 0xBE36, 0x1000, 0xBE37, 0x1000, 0x8000, 0x0001,
+	0xBE69, 0xD50F, 0x8000, 0x0000, 0xBE69, 0xD50F, 0xBE6E, 0x0320,
+	0xBE77, 0x2940, 0xBE78, 0x3C3C, 0xBE79, 0x3C3C, 0xBE6E, 0xE120,
+	0x8000, 0x0001, 0xBE15, 0x1007, 0x8000, 0x0000, 0xBE15, 0x1007,
+	0xBE14, 0x0448, 0xBE1E, 0x00A0, 0xBE10, 0x8160, 0xBE10, 0x8140,
+	0xBE00, 0x1340, 0x0F51, 0x0010,
+};
+
+/* Appears in a DDWRT code dump */
+static const u16 rtl8366rb_init_jam_ver_3[] = {
+	0x0000, 0x0830, 0x0400, 0x8130, 0x000A, 0x83ED, 0x0431, 0x5432,
+	0x0F51, 0x0017, 0x02F5, 0x0048, 0x02FA, 0xFFDF, 0x02FB, 0xFFE0,
+	0xC456, 0x0C14, 0xC476, 0x0C14, 0xC454, 0x3F8B, 0xC474, 0x3F8B,
+	0xC450, 0x2071, 0xC470, 0x2071, 0xC451, 0x226B, 0xC471, 0x226B,
+	0xC452, 0xA293, 0xC472, 0xA293, 0xC44C, 0x1585, 0xC44C, 0x1185,
+	0xC44C, 0x1585, 0xC46C, 0x1585, 0xC46C, 0x1185, 0xC46C, 0x1585,
+	0xC44C, 0x0185, 0xC44C, 0x0181, 0xC44C, 0x0185, 0xC46C, 0x0185,
+	0xC46C, 0x0181, 0xC46C, 0x0185, 0xBE24, 0xB000, 0xBE23, 0xFF51,
+	0xBE22, 0xDF20, 0xBE21, 0x0140, 0xBE20, 0x00BB, 0xBE24, 0xB800,
+	0xBE24, 0x0000, 0xBE24, 0x7000, 0xBE23, 0xFF51, 0xBE22, 0xDF60,
+	0xBE21, 0x0140, 0xBE20, 0x0077, 0xBE24, 0x7800, 0xBE24, 0x0000,
+	0xBE2E, 0x7BA7, 0xBE36, 0x1000, 0xBE37, 0x1000, 0x8000, 0x0001,
+	0xBE69, 0xD50F, 0x8000, 0x0000, 0xBE69, 0xD50F, 0xBE6B, 0x0320,
+	0xBE77, 0x2800, 0xBE78, 0x3C3C, 0xBE79, 0x3C3C, 0xBE6E, 0xE120,
+	0x8000, 0x0001, 0xBE10, 0x8140, 0x8000, 0x0000, 0xBE10, 0x8140,
+	0xBE15, 0x1007, 0xBE14, 0x0448, 0xBE1E, 0x00A0, 0xBE10, 0x8160,
+	0xBE10, 0x8140, 0xBE00, 0x1340, 0x0450, 0x0000, 0x0401, 0x0000,
+};
+
+/* Belkin F5D8235 v1, "belkin,f5d8235-v1" */
+static const u16 rtl8366rb_init_jam_f5d8235[] = {
+	0x0242, 0x02BF, 0x0245, 0x02BF, 0x0248, 0x02BF, 0x024B, 0x02BF,
+	0x024E, 0x02BF, 0x0251, 0x02BF, 0x0254, 0x0A3F, 0x0256, 0x0A3F,
+	0x0258, 0x0A3F, 0x025A, 0x0A3F, 0x025C, 0x0A3F, 0x025E, 0x0A3F,
+	0x0263, 0x007C, 0x0100, 0x0004, 0xBE5B, 0x3500, 0x800E, 0x200F,
+	0xBE1D, 0x0F00, 0x8001, 0x5011, 0x800A, 0xA2F4, 0x800B, 0x17A3,
+	0xBE4B, 0x17A3, 0xBE41, 0x5011, 0xBE17, 0x2100, 0x8000, 0x8304,
+	0xBE40, 0x8304, 0xBE4A, 0xA2F4, 0x800C, 0xA8D5, 0x8014, 0x5500,
+	0x8015, 0x0004, 0xBE4C, 0xA8D5, 0xBE59, 0x0008, 0xBE09, 0x0E00,
+	0xBE36, 0x1036, 0xBE37, 0x1036, 0x800D, 0x00FF, 0xBE4D, 0x00FF,
+};
+
+/* DGN3500, "netgear,dgn3500", "netgear,dgn3500b" */
+static const u16 rtl8366rb_init_jam_dgn3500[] = {
+	0x0000, 0x0830, 0x0400, 0x8130, 0x000A, 0x83ED, 0x0F51, 0x0017,
+	0x02F5, 0x0048, 0x02FA, 0xFFDF, 0x02FB, 0xFFE0, 0x0450, 0x0000,
+	0x0401, 0x0000, 0x0431, 0x0960,
+};
+
+/* This jam table activates "green ethernet", which means low power mode
+ * and is claimed to detect the cable length and not use more power than
+ * necessary, and the ports should enter power saving mode 10 seconds after
+ * a cable is disconnected. Seems to always be the same.
+ */
+static const u16 rtl8366rb_green_jam[][2] = {
+	{0xBE78, 0x323C}, {0xBE77, 0x5000}, {0xBE2E, 0x7BA7},
+	{0xBE59, 0x3459}, {0xBE5A, 0x745A}, {0xBE5B, 0x785C},
+	{0xBE5C, 0x785C}, {0xBE6E, 0xE120}, {0xBE79, 0x323C},
+};
+
+static int rtl8366rb_setup(struct dsa_switch *ds)
+{
+	struct realtek_smi *smi = ds->priv;
+	const u16 *jam_table;
+	u32 chip_ver = 0;
+	u32 chip_id = 0;
+	int jam_size;
+	u32 val;
+	int ret;
+	int i;
+
+	ret = regmap_read(smi->map, RTL8366RB_CHIP_ID_REG, &chip_id);
+	if (ret) {
+		dev_err(smi->dev, "unable to read chip id\n");
+		return ret;
+	}
+
+	switch (chip_id) {
+	case RTL8366RB_CHIP_ID_8366:
+		break;
+	default:
+		dev_err(smi->dev, "unknown chip id (%04x)\n", chip_id);
+		return -ENODEV;
+	}
+
+	ret = regmap_read(smi->map, RTL8366RB_CHIP_VERSION_CTRL_REG,
+			  &chip_ver);
+	if (ret) {
+		dev_err(smi->dev, "unable to read chip version\n");
+		return ret;
+	}
+
+	dev_info(smi->dev, "RTL%04x ver %u chip found\n",
+		 chip_id, chip_ver & RTL8366RB_CHIP_VERSION_MASK);
+
+	/* Do the init dance using the right jam table */
+	switch (chip_ver) {
+	case 0:
+		jam_table = rtl8366rb_init_jam_ver_0;
+		jam_size = ARRAY_SIZE(rtl8366rb_init_jam_ver_0);
+		break;
+	case 1:
+		jam_table = rtl8366rb_init_jam_ver_1;
+		jam_size = ARRAY_SIZE(rtl8366rb_init_jam_ver_1);
+		break;
+	case 2:
+		jam_table = rtl8366rb_init_jam_ver_2;
+		jam_size = ARRAY_SIZE(rtl8366rb_init_jam_ver_2);
+		break;
+	default:
+		jam_table = rtl8366rb_init_jam_ver_3;
+		jam_size = ARRAY_SIZE(rtl8366rb_init_jam_ver_3);
+		break;
+	}
+
+	/* Special jam tables for special routers
+	 * TODO: are these necessary? Maintainers, please test
+	 * without them, using just the off-the-shelf tables.
+	 */
+	if (of_machine_is_compatible("belkin,f5d8235-v1")) {
+		jam_table = rtl8366rb_init_jam_f5d8235;
+		jam_size = ARRAY_SIZE(rtl8366rb_init_jam_f5d8235);
+	}
+	if (of_machine_is_compatible("netgear,dgn3500") ||
+	    of_machine_is_compatible("netgear,dgn3500b")) {
+		jam_table = rtl8366rb_init_jam_dgn3500;
+		jam_size = ARRAY_SIZE(rtl8366rb_init_jam_dgn3500);
+	}
+
+	i = 0;
+	while (i < jam_size) {
+		if ((jam_table[i] & 0xBE00) == 0xBE00) {
+			ret = regmap_read(smi->map,
+					  RTL8366RB_PHY_ACCESS_BUSY_REG,
+					  &val);
+			if (ret)
+				return ret;
+			if (!(val & RTL8366RB_PHY_INT_BUSY)) {
+				ret = regmap_write(smi->map,
+						RTL8366RB_PHY_ACCESS_CTRL_REG,
+						RTL8366RB_PHY_CTRL_WRITE);
+				if (ret)
+					return ret;
+			}
+		}
+		dev_dbg(smi->dev, "jam %04x into register %04x\n",
+			jam_table[i + 1],
+			jam_table[i]);
+		ret = regmap_write(smi->map,
+				   jam_table[i],
+				   jam_table[i + 1]);
+		if (ret)
+			return ret;
+		i += 2;
+	}
+
+	/* Set up the "green ethernet" feature */
+	i = 0;
+	while (i < ARRAY_SIZE(rtl8366rb_green_jam)) {
+		ret = regmap_read(smi->map, RTL8366RB_PHY_ACCESS_BUSY_REG,
+				  &val);
+		if (ret)
+			return ret;
+		if (!(val & RTL8366RB_PHY_INT_BUSY)) {
+			ret = regmap_write(smi->map,
+					   RTL8366RB_PHY_ACCESS_CTRL_REG,
+					   RTL8366RB_PHY_CTRL_WRITE);
+			if (ret)
+				return ret;
+			ret = regmap_write(smi->map,
+					   rtl8366rb_green_jam[i][0],
+					   rtl8366rb_green_jam[i][1]);
+			if (ret)
+				return ret;
+			i++;
+		}
+	}
+	ret = regmap_write(smi->map,
+			   RTL8366RB_GREEN_FEATURE_REG,
+			   (chip_ver == 1) ? 0x0007 : 0x0003);
+	if (ret)
+		return ret;
+
+	/* Vendor driver sets 0x240 in registers 0xc and 0xd (undocumented) */
+	ret = regmap_write(smi->map, 0x0c, 0x240);
+	if (ret)
+		return ret;
+	ret = regmap_write(smi->map, 0x0d, 0x240);
+	if (ret)
+		return ret;
+
+	/* Set some random MAC address */
+	ret = rtl8366rb_set_addr(smi);
+	if (ret)
+		return ret;
+
+	/* Enable CPU port and enable inserting CPU tag
+	 *
+	 * Disabling RTL8368RB_CPU_INSTAG here will change the behaviour
+	 * of the switch totally and it will start talking Realtek RRCP
+	 * internally. It is probably possible to experiment with this,
+	 * but then the kernel needs to understand and handle RRCP first.
+	 */
+	ret = regmap_update_bits(smi->map, RTL8368RB_CPU_CTRL_REG,
+				 0xFFFF,
+				 RTL8368RB_CPU_INSTAG | BIT(smi->cpu_port));
+	if (ret)
+		return ret;
+
+	/* Make sure we default-enable the fixed CPU port */
+	ret = regmap_update_bits(smi->map, RTL8366RB_PECR,
+				 BIT(smi->cpu_port),
+				 0);
+	if (ret)
+		return ret;
+
+	/* Set maximum packet length to 1536 bytes */
+	ret = regmap_update_bits(smi->map, RTL8366RB_SGCR,
+				 RTL8366RB_SGCR_MAX_LENGTH_MASK,
+				 RTL8366RB_SGCR_MAX_LENGTH_1536);
+	if (ret)
+		return ret;
+
+	/* Enable learning for all ports */
+	ret = regmap_write(smi->map, RTL8366RB_SSCR0, 0);
+	if (ret)
+		return ret;
+
+	/* Enable auto ageing for all ports */
+	ret = regmap_write(smi->map, RTL8366RB_SSCR1, 0);
+	if (ret)
+		return ret;
+
+	/* Port 4 setup: this enables Port 4, usually the WAN port,
+	 * common PHY IO mode is apparently mode 0, and this is not what
+	 * the port is initialized to. There is no explanation of the
+	 * IO modes in the Realtek source code, if your WAN port is
+	 * connected to something exotic such as fiber, then this might
+	 * be worth experimenting with.
+	 */
+	ret = regmap_update_bits(smi->map, RTL8366RB_PMC0,
+				 RTL8366RB_PMC0_P4_IOMODE_MASK,
+				 0 << RTL8366RB_PMC0_P4_IOMODE_SHIFT);
+	if (ret)
+		return ret;
+
+	/* Discard VLAN tagged packets if the port is not a member of
+	 * the VLAN with which the packets is associated.
+	 */
+	ret = regmap_write(smi->map, RTL8366RB_VLAN_INGRESS_CTRL2_REG,
+			   RTL8366RB_PORT_ALL);
+	if (ret)
+		return ret;
+
+	/* Don't drop packets whose DA has not been learned */
+	ret = regmap_update_bits(smi->map, RTL8366RB_SSCR2,
+				 RTL8366RB_SSCR2_DROP_UNKNOWN_DA, 0);
+	if (ret)
+		return ret;
+
+	/* Set blinking, TODO: make this configurable */
+	ret = regmap_update_bits(smi->map, RTL8366RB_LED_BLINKRATE_REG,
+				 RTL8366RB_LED_BLINKRATE_MASK,
+				 RTL8366RB_LED_BLINKRATE_56MS);
+	if (ret)
+		return ret;
+
+	/* Set up LED activity:
+	 * Each port has 4 LEDs, we configure all ports to the same
+	 * behaviour (no individual config) but we can set up each
+	 * LED separately.
+	 */
+	if (smi->leds_disabled) {
+		/* Turn everything off */
+		regmap_update_bits(smi->map,
+				   RTL8366RB_LED_0_1_CTRL_REG,
+				   0x0FFF, 0);
+		regmap_update_bits(smi->map,
+				   RTL8366RB_LED_2_3_CTRL_REG,
+				   0x0FFF, 0);
+		regmap_update_bits(smi->map,
+				   RTL8366RB_INTERRUPT_CONTROL_REG,
+				   RTL8366RB_P4_RGMII_LED,
+				   0);
+		val = RTL8366RB_LED_OFF;
+	} else {
+		/* TODO: make this configurable per LED */
+		val = RTL8366RB_LED_FORCE;
+	}
+	for (i = 0; i < 4; i++) {
+		ret = regmap_update_bits(smi->map,
+					 RTL8366RB_LED_CTRL_REG,
+					 0xf << (i * 4),
+					 val << (i * 4));
+		if (ret)
+			return ret;
+	}
+
+	ret = rtl8366_init_vlan(smi);
+	if (ret)
+		return ret;
+
+	ret = rtl8366rb_setup_cascaded_irq(smi);
+	if (ret)
+		dev_info(smi->dev, "no interrupt support\n");
+
+	ret = realtek_smi_setup_mdio(smi);
+	if (ret) {
+		dev_info(smi->dev, "could not set up MDIO bus\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static enum dsa_tag_protocol rtl8366_get_tag_protocol(struct dsa_switch *ds,
+						      int port)
+{
+	/* For now, the RTL switches are handled without any custom tags.
+	 *
+	 * It is possible to turn on "custom tags" by removing the
+	 * RTL8368RB_CPU_INSTAG flag when enabling the port but what it
+	 * does is unfamiliar to DSA: ethernet frames of type 8899, the Realtek
+	 * Remote Control Protocol (RRCP) start to appear on the CPU port of
+	 * the device. So this is not the ordinary few extra bytes in the
+	 * frame. Instead it appears that the switch starts to talk Realtek
+	 * RRCP internally which means a pretty complex RRCP implementation
+	 * decoding and responding the RRCP protocol is needed to exploit this.
+	 *
+	 * The OpenRRCP project (dormant since 2009) have reverse-egineered
+	 * parts of the protocol.
+	 */
+	return DSA_TAG_PROTO_NONE;
+}
+
+static void rtl8366rb_adjust_link(struct dsa_switch *ds, int port,
+				  struct phy_device *phydev)
+{
+	struct realtek_smi *smi = ds->priv;
+	int ret;
+
+	if (port != smi->cpu_port)
+		return;
+
+	dev_info(smi->dev, "adjust link on CPU port (%d)\n", port);
+
+	/* Force the fixed CPU port into 1Gbit mode, no autonegotiation */
+	ret = regmap_update_bits(smi->map, RTL8366RB_MAC_FORCE_CTRL_REG,
+				 BIT(port), BIT(port));
+	if (ret)
+		return;
+
+	ret = regmap_update_bits(smi->map, RTL8366RB_PAACR2,
+				 0xFF00U,
+				 RTL8366RB_PAACR_CPU_PORT << 8);
+	if (ret)
+		return;
+
+	/* Enable the CPU port */
+	ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port),
+				 0);
+	if (ret)
+		return;
+}
+
+static void rb8366rb_set_port_led(struct realtek_smi *smi,
+				  int port, bool enable)
+{
+	u16 val = enable ? 0x3f : 0;
+	int ret;
+
+	if (smi->leds_disabled)
+		return;
+
+	switch (port) {
+	case 0:
+		ret = regmap_update_bits(smi->map,
+					 RTL8366RB_LED_0_1_CTRL_REG,
+					 0x3F, val);
+		break;
+	case 1:
+		ret = regmap_update_bits(smi->map,
+					 RTL8366RB_LED_0_1_CTRL_REG,
+					 0x3F << RTL8366RB_LED_1_OFFSET,
+					 val << RTL8366RB_LED_1_OFFSET);
+		break;
+	case 2:
+		ret = regmap_update_bits(smi->map,
+					 RTL8366RB_LED_2_3_CTRL_REG,
+					 0x3F, val);
+		break;
+	case 3:
+		ret = regmap_update_bits(smi->map,
+					 RTL8366RB_LED_2_3_CTRL_REG,
+					 0x3F << RTL8366RB_LED_3_OFFSET,
+					 val << RTL8366RB_LED_3_OFFSET);
+		break;
+	case 4:
+		ret = regmap_update_bits(smi->map,
+					 RTL8366RB_INTERRUPT_CONTROL_REG,
+					 RTL8366RB_P4_RGMII_LED,
+					 enable ? RTL8366RB_P4_RGMII_LED : 0);
+		break;
+	default:
+		dev_err(smi->dev, "no LED for port %d\n", port);
+		return;
+	}
+	if (ret)
+		dev_err(smi->dev, "error updating LED on port %d\n", port);
+}
+
+static int
+rtl8366rb_port_enable(struct dsa_switch *ds, int port,
+		      struct phy_device *phy)
+{
+	struct realtek_smi *smi = ds->priv;
+	int ret;
+
+	dev_dbg(smi->dev, "enable port %d\n", port);
+	ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port),
+				 0);
+	if (ret)
+		return ret;
+
+	rb8366rb_set_port_led(smi, port, true);
+	return 0;
+}
+
+static void
+rtl8366rb_port_disable(struct dsa_switch *ds, int port,
+		       struct phy_device *phy)
+{
+	struct realtek_smi *smi = ds->priv;
+	int ret;
+
+	dev_dbg(smi->dev, "disable port %d\n", port);
+	ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port),
+				 BIT(port));
+	if (ret)
+		return;
+
+	rb8366rb_set_port_led(smi, port, false);
+}
+
+static int rtl8366rb_get_vlan_4k(struct realtek_smi *smi, u32 vid,
+				 struct rtl8366_vlan_4k *vlan4k)
+{
+	u32 data[3];
+	int ret;
+	int i;
+
+	memset(vlan4k, '\0', sizeof(struct rtl8366_vlan_4k));
+
+	if (vid >= RTL8366RB_NUM_VIDS)
+		return -EINVAL;
+
+	/* write VID */
+	ret = regmap_write(smi->map, RTL8366RB_VLAN_TABLE_WRITE_BASE,
+			   vid & RTL8366RB_VLAN_VID_MASK);
+	if (ret)
+		return ret;
+
+	/* write table access control word */
+	ret = regmap_write(smi->map, RTL8366RB_TABLE_ACCESS_CTRL_REG,
+			   RTL8366RB_TABLE_VLAN_READ_CTRL);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < 3; i++) {
+		ret = regmap_read(smi->map,
+				  RTL8366RB_VLAN_TABLE_READ_BASE + i,
+				  &data[i]);
+		if (ret)
+			return ret;
+	}
+
+	vlan4k->vid = vid;
+	vlan4k->untag = (data[1] >> RTL8366RB_VLAN_UNTAG_SHIFT) &
+			RTL8366RB_VLAN_UNTAG_MASK;
+	vlan4k->member = data[1] & RTL8366RB_VLAN_MEMBER_MASK;
+	vlan4k->fid = data[2] & RTL8366RB_VLAN_FID_MASK;
+
+	return 0;
+}
+
+static int rtl8366rb_set_vlan_4k(struct realtek_smi *smi,
+				 const struct rtl8366_vlan_4k *vlan4k)
+{
+	u32 data[3];
+	int ret;
+	int i;
+
+	if (vlan4k->vid >= RTL8366RB_NUM_VIDS ||
+	    vlan4k->member > RTL8366RB_VLAN_MEMBER_MASK ||
+	    vlan4k->untag > RTL8366RB_VLAN_UNTAG_MASK ||
+	    vlan4k->fid > RTL8366RB_FIDMAX)
+		return -EINVAL;
+
+	data[0] = vlan4k->vid & RTL8366RB_VLAN_VID_MASK;
+	data[1] = (vlan4k->member & RTL8366RB_VLAN_MEMBER_MASK) |
+		  ((vlan4k->untag & RTL8366RB_VLAN_UNTAG_MASK) <<
+			RTL8366RB_VLAN_UNTAG_SHIFT);
+	data[2] = vlan4k->fid & RTL8366RB_VLAN_FID_MASK;
+
+	for (i = 0; i < 3; i++) {
+		ret = regmap_write(smi->map,
+				   RTL8366RB_VLAN_TABLE_WRITE_BASE + i,
+				   data[i]);
+		if (ret)
+			return ret;
+	}
+
+	/* write table access control word */
+	ret = regmap_write(smi->map, RTL8366RB_TABLE_ACCESS_CTRL_REG,
+			   RTL8366RB_TABLE_VLAN_WRITE_CTRL);
+
+	return ret;
+}
+
+static int rtl8366rb_get_vlan_mc(struct realtek_smi *smi, u32 index,
+				 struct rtl8366_vlan_mc *vlanmc)
+{
+	u32 data[3];
+	int ret;
+	int i;
+
+	memset(vlanmc, '\0', sizeof(struct rtl8366_vlan_mc));
+
+	if (index >= RTL8366RB_NUM_VLANS)
+		return -EINVAL;
+
+	for (i = 0; i < 3; i++) {
+		ret = regmap_read(smi->map,
+				  RTL8366RB_VLAN_MC_BASE(index) + i,
+				  &data[i]);
+		if (ret)
+			return ret;
+	}
+
+	vlanmc->vid = data[0] & RTL8366RB_VLAN_VID_MASK;
+	vlanmc->priority = (data[0] >> RTL8366RB_VLAN_PRIORITY_SHIFT) &
+		RTL8366RB_VLAN_PRIORITY_MASK;
+	vlanmc->untag = (data[1] >> RTL8366RB_VLAN_UNTAG_SHIFT) &
+		RTL8366RB_VLAN_UNTAG_MASK;
+	vlanmc->member = data[1] & RTL8366RB_VLAN_MEMBER_MASK;
+	vlanmc->fid = data[2] & RTL8366RB_VLAN_FID_MASK;
+
+	return 0;
+}
+
+static int rtl8366rb_set_vlan_mc(struct realtek_smi *smi, u32 index,
+				 const struct rtl8366_vlan_mc *vlanmc)
+{
+	u32 data[3];
+	int ret;
+	int i;
+
+	if (index >= RTL8366RB_NUM_VLANS ||
+	    vlanmc->vid >= RTL8366RB_NUM_VIDS ||
+	    vlanmc->priority > RTL8366RB_PRIORITYMAX ||
+	    vlanmc->member > RTL8366RB_VLAN_MEMBER_MASK ||
+	    vlanmc->untag > RTL8366RB_VLAN_UNTAG_MASK ||
+	    vlanmc->fid > RTL8366RB_FIDMAX)
+		return -EINVAL;
+
+	data[0] = (vlanmc->vid & RTL8366RB_VLAN_VID_MASK) |
+		  ((vlanmc->priority & RTL8366RB_VLAN_PRIORITY_MASK) <<
+			RTL8366RB_VLAN_PRIORITY_SHIFT);
+	data[1] = (vlanmc->member & RTL8366RB_VLAN_MEMBER_MASK) |
+		  ((vlanmc->untag & RTL8366RB_VLAN_UNTAG_MASK) <<
+			RTL8366RB_VLAN_UNTAG_SHIFT);
+	data[2] = vlanmc->fid & RTL8366RB_VLAN_FID_MASK;
+
+	for (i = 0; i < 3; i++) {
+		ret = regmap_write(smi->map,
+				   RTL8366RB_VLAN_MC_BASE(index) + i,
+				   data[i]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int rtl8366rb_get_mc_index(struct realtek_smi *smi, int port, int *val)
+{
+	u32 data;
+	int ret;
+
+	if (port >= smi->num_ports)
+		return -EINVAL;
+
+	ret = regmap_read(smi->map, RTL8366RB_PORT_VLAN_CTRL_REG(port),
+			  &data);
+	if (ret)
+		return ret;
+
+	*val = (data >> RTL8366RB_PORT_VLAN_CTRL_SHIFT(port)) &
+		RTL8366RB_PORT_VLAN_CTRL_MASK;
+
+	return 0;
+}
+
+static int rtl8366rb_set_mc_index(struct realtek_smi *smi, int port, int index)
+{
+	if (port >= smi->num_ports || index >= RTL8366RB_NUM_VLANS)
+		return -EINVAL;
+
+	return regmap_update_bits(smi->map, RTL8366RB_PORT_VLAN_CTRL_REG(port),
+				RTL8366RB_PORT_VLAN_CTRL_MASK <<
+					RTL8366RB_PORT_VLAN_CTRL_SHIFT(port),
+				(index & RTL8366RB_PORT_VLAN_CTRL_MASK) <<
+					RTL8366RB_PORT_VLAN_CTRL_SHIFT(port));
+}
+
+static bool rtl8366rb_is_vlan_valid(struct realtek_smi *smi, unsigned int vlan)
+{
+	unsigned int max = RTL8366RB_NUM_VLANS;
+
+	if (smi->vlan4k_enabled)
+		max = RTL8366RB_NUM_VIDS - 1;
+
+	if (vlan == 0 || vlan >= max)
+		return false;
+
+	return true;
+}
+
+static int rtl8366rb_enable_vlan(struct realtek_smi *smi, bool enable)
+{
+	dev_dbg(smi->dev, "%s VLAN\n", enable ? "enable" : "disable");
+	return regmap_update_bits(smi->map,
+				  RTL8366RB_SGCR, RTL8366RB_SGCR_EN_VLAN,
+				  enable ? RTL8366RB_SGCR_EN_VLAN : 0);
+}
+
+static int rtl8366rb_enable_vlan4k(struct realtek_smi *smi, bool enable)
+{
+	dev_dbg(smi->dev, "%s VLAN 4k\n", enable ? "enable" : "disable");
+	return regmap_update_bits(smi->map, RTL8366RB_SGCR,
+				  RTL8366RB_SGCR_EN_VLAN_4KTB,
+				  enable ? RTL8366RB_SGCR_EN_VLAN_4KTB : 0);
+}
+
+static int rtl8366rb_phy_read(struct realtek_smi *smi, int phy, int regnum)
+{
+	u32 val;
+	u32 reg;
+	int ret;
+
+	if (phy > RTL8366RB_PHY_NO_MAX)
+		return -EINVAL;
+
+	ret = regmap_write(smi->map, RTL8366RB_PHY_ACCESS_CTRL_REG,
+			   RTL8366RB_PHY_CTRL_READ);
+	if (ret)
+		return ret;
+
+	reg = 0x8000 | (1 << (phy + RTL8366RB_PHY_NO_OFFSET)) | regnum;
+
+	ret = regmap_write(smi->map, reg, 0);
+	if (ret) {
+		dev_err(smi->dev,
+			"failed to write PHY%d reg %04x @ %04x, ret %d\n",
+			phy, regnum, reg, ret);
+		return ret;
+	}
+
+	ret = regmap_read(smi->map, RTL8366RB_PHY_ACCESS_DATA_REG, &val);
+	if (ret)
+		return ret;
+
+	dev_dbg(smi->dev, "read PHY%d register 0x%04x @ %08x, val <- %04x\n",
+		phy, regnum, reg, val);
+
+	return val;
+}
+
+static int rtl8366rb_phy_write(struct realtek_smi *smi, int phy, int regnum,
+			       u16 val)
+{
+	u32 reg;
+	int ret;
+
+	if (phy > RTL8366RB_PHY_NO_MAX)
+		return -EINVAL;
+
+	ret = regmap_write(smi->map, RTL8366RB_PHY_ACCESS_CTRL_REG,
+			   RTL8366RB_PHY_CTRL_WRITE);
+	if (ret)
+		return ret;
+
+	reg = 0x8000 | (1 << (phy + RTL8366RB_PHY_NO_OFFSET)) | regnum;
+
+	dev_dbg(smi->dev, "write PHY%d register 0x%04x @ %04x, val -> %04x\n",
+		phy, regnum, reg, val);
+
+	ret = regmap_write(smi->map, reg, val);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int rtl8366rb_reset_chip(struct realtek_smi *smi)
+{
+	int timeout = 10;
+	u32 val;
+	int ret;
+
+	realtek_smi_write_reg_noack(smi, RTL8366RB_RESET_CTRL_REG,
+				    RTL8366RB_CHIP_CTRL_RESET_HW);
+	do {
+		usleep_range(20000, 25000);
+		ret = regmap_read(smi->map, RTL8366RB_RESET_CTRL_REG, &val);
+		if (ret)
+			return ret;
+
+		if (!(val & RTL8366RB_CHIP_CTRL_RESET_HW))
+			break;
+	} while (--timeout);
+
+	if (!timeout) {
+		dev_err(smi->dev, "timeout waiting for the switch to reset\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int rtl8366rb_detect(struct realtek_smi *smi)
+{
+	struct device *dev = smi->dev;
+	int ret;
+	u32 val;
+
+	/* Detect device */
+	ret = regmap_read(smi->map, 0x5c, &val);
+	if (ret) {
+		dev_err(dev, "can't get chip ID (%d)\n", ret);
+		return ret;
+	}
+
+	switch (val) {
+	case 0x6027:
+		dev_info(dev, "found an RTL8366S switch\n");
+		dev_err(dev, "this switch is not yet supported, submit patches!\n");
+		return -ENODEV;
+	case 0x5937:
+		dev_info(dev, "found an RTL8366RB switch\n");
+		smi->cpu_port = RTL8366RB_PORT_NUM_CPU;
+		smi->num_ports = RTL8366RB_NUM_PORTS;
+		smi->num_vlan_mc = RTL8366RB_NUM_VLANS;
+		smi->mib_counters = rtl8366rb_mib_counters;
+		smi->num_mib_counters = ARRAY_SIZE(rtl8366rb_mib_counters);
+		break;
+	default:
+		dev_info(dev, "found an Unknown Realtek switch (id=0x%04x)\n",
+			 val);
+		break;
+	}
+
+	ret = rtl8366rb_reset_chip(smi);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static const struct dsa_switch_ops rtl8366rb_switch_ops = {
+	.get_tag_protocol = rtl8366_get_tag_protocol,
+	.setup = rtl8366rb_setup,
+	.adjust_link = rtl8366rb_adjust_link,
+	.get_strings = rtl8366_get_strings,
+	.get_ethtool_stats = rtl8366_get_ethtool_stats,
+	.get_sset_count = rtl8366_get_sset_count,
+	.port_vlan_filtering = rtl8366_vlan_filtering,
+	.port_vlan_prepare = rtl8366_vlan_prepare,
+	.port_vlan_add = rtl8366_vlan_add,
+	.port_vlan_del = rtl8366_vlan_del,
+	.port_enable = rtl8366rb_port_enable,
+	.port_disable = rtl8366rb_port_disable,
+};
+
+static const struct realtek_smi_ops rtl8366rb_smi_ops = {
+	.detect		= rtl8366rb_detect,
+	.get_vlan_mc	= rtl8366rb_get_vlan_mc,
+	.set_vlan_mc	= rtl8366rb_set_vlan_mc,
+	.get_vlan_4k	= rtl8366rb_get_vlan_4k,
+	.set_vlan_4k	= rtl8366rb_set_vlan_4k,
+	.get_mc_index	= rtl8366rb_get_mc_index,
+	.set_mc_index	= rtl8366rb_set_mc_index,
+	.get_mib_counter = rtl8366rb_get_mib_counter,
+	.is_vlan_valid	= rtl8366rb_is_vlan_valid,
+	.enable_vlan	= rtl8366rb_enable_vlan,
+	.enable_vlan4k	= rtl8366rb_enable_vlan4k,
+	.phy_read	= rtl8366rb_phy_read,
+	.phy_write	= rtl8366rb_phy_write,
+};
+
+const struct realtek_smi_variant rtl8366rb_variant = {
+	.ds_ops = &rtl8366rb_switch_ops,
+	.ops = &rtl8366rb_smi_ops,
+	.clk_delay = 10,
+	.cmd_read = 0xa9,
+	.cmd_write = 0xa8,
+};
+EXPORT_SYMBOL_GPL(rtl8366rb_variant);
diff --git a/drivers/net/dsa/vitesse-vsc73xx.c b/drivers/net/dsa/vitesse-vsc73xx.c
new file mode 100644
index 000000000000..9f1b5f2e8a64
--- /dev/null
+++ b/drivers/net/dsa/vitesse-vsc73xx.c
@@ -0,0 +1,1365 @@
+// SPDX-License-Identifier: GPL-2.0
+/* DSA driver for:
+ * Vitesse VSC7385 SparX-G5 5+1-port Integrated Gigabit Ethernet Switch
+ * Vitesse VSC7388 SparX-G8 8-port Integrated Gigabit Ethernet Switch
+ * Vitesse VSC7395 SparX-G5e 5+1-port Integrated Gigabit Ethernet Switch
+ * Vitesse VSC7398 SparX-G8e 8-port Integrated Gigabit Ethernet Switch
+ *
+ * These switches have a built-in 8051 CPU and can download and execute a
+ * firmware in this CPU. They can also be configured to use an external CPU
+ * handling the switch in a memory-mapped manner by connecting to that external
+ * CPU's memory bus.
+ *
+ * This driver (currently) only takes control of the switch chip over SPI and
+ * configures it to route packages around when connected to a CPU port. The
+ * chip has embedded PHYs and VLAN support so we model it using DSA.
+ *
+ * Copyright (C) 2018 Linus Wallej <linus.walleij@linaro.org>
+ * Includes portions of code from the firmware uploader by:
+ * Copyright (C) 2009 Gabor Juhos <juhosg@openwrt.org>
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_mdio.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+#include <linux/bitops.h>
+#include <linux/if_bridge.h>
+#include <linux/etherdevice.h>
+#include <linux/gpio/consumer.h>
+#include <linux/gpio/driver.h>
+#include <linux/random.h>
+#include <net/dsa.h>
+
+#define VSC73XX_BLOCK_MAC	0x1 /* Subblocks 0-4, 6 (CPU port) */
+#define VSC73XX_BLOCK_ANALYZER	0x2 /* Only subblock 0 */
+#define VSC73XX_BLOCK_MII	0x3 /* Subblocks 0 and 1 */
+#define VSC73XX_BLOCK_MEMINIT	0x3 /* Only subblock 2 */
+#define VSC73XX_BLOCK_CAPTURE	0x4 /* Only subblock 2 */
+#define VSC73XX_BLOCK_ARBITER	0x5 /* Only subblock 0 */
+#define VSC73XX_BLOCK_SYSTEM	0x7 /* Only subblock 0 */
+
+#define CPU_PORT	6 /* CPU port */
+
+/* MAC Block registers */
+#define VSC73XX_MAC_CFG		0x00
+#define VSC73XX_MACHDXGAP	0x02
+#define VSC73XX_FCCONF		0x04
+#define VSC73XX_FCMACHI		0x08
+#define VSC73XX_FCMACLO		0x0c
+#define VSC73XX_MAXLEN		0x10
+#define VSC73XX_ADVPORTM	0x19
+#define VSC73XX_TXUPDCFG	0x24
+#define VSC73XX_TXQ_SELECT_CFG	0x28
+#define VSC73XX_RXOCT		0x50
+#define VSC73XX_TXOCT		0x51
+#define VSC73XX_C_RX0		0x52
+#define VSC73XX_C_RX1		0x53
+#define VSC73XX_C_RX2		0x54
+#define VSC73XX_C_TX0		0x55
+#define VSC73XX_C_TX1		0x56
+#define VSC73XX_C_TX2		0x57
+#define VSC73XX_C_CFG		0x58
+#define VSC73XX_CAT_DROP	0x6e
+#define VSC73XX_CAT_PR_MISC_L2	0x6f
+#define VSC73XX_CAT_PR_USR_PRIO	0x75
+#define VSC73XX_Q_MISC_CONF	0xdf
+
+/* MAC_CFG register bits */
+#define VSC73XX_MAC_CFG_WEXC_DIS	BIT(31)
+#define VSC73XX_MAC_CFG_PORT_RST	BIT(29)
+#define VSC73XX_MAC_CFG_TX_EN		BIT(28)
+#define VSC73XX_MAC_CFG_SEED_LOAD	BIT(27)
+#define VSC73XX_MAC_CFG_SEED_MASK	GENMASK(26, 19)
+#define VSC73XX_MAC_CFG_SEED_OFFSET	19
+#define VSC73XX_MAC_CFG_FDX		BIT(18)
+#define VSC73XX_MAC_CFG_GIGA_MODE	BIT(17)
+#define VSC73XX_MAC_CFG_RX_EN		BIT(16)
+#define VSC73XX_MAC_CFG_VLAN_DBLAWR	BIT(15)
+#define VSC73XX_MAC_CFG_VLAN_AWR	BIT(14)
+#define VSC73XX_MAC_CFG_100_BASE_T	BIT(13) /* Not in manual */
+#define VSC73XX_MAC_CFG_TX_IPG_MASK	GENMASK(10, 6)
+#define VSC73XX_MAC_CFG_TX_IPG_OFFSET	6
+#define VSC73XX_MAC_CFG_TX_IPG_1000M	(6 << VSC73XX_MAC_CFG_TX_IPG_OFFSET)
+#define VSC73XX_MAC_CFG_TX_IPG_100_10M	(17 << VSC73XX_MAC_CFG_TX_IPG_OFFSET)
+#define VSC73XX_MAC_CFG_MAC_RX_RST	BIT(5)
+#define VSC73XX_MAC_CFG_MAC_TX_RST	BIT(4)
+#define VSC73XX_MAC_CFG_CLK_SEL_MASK	GENMASK(2, 0)
+#define VSC73XX_MAC_CFG_CLK_SEL_OFFSET	0
+#define VSC73XX_MAC_CFG_CLK_SEL_1000M	1
+#define VSC73XX_MAC_CFG_CLK_SEL_100M	2
+#define VSC73XX_MAC_CFG_CLK_SEL_10M	3
+#define VSC73XX_MAC_CFG_CLK_SEL_EXT	4
+
+#define VSC73XX_MAC_CFG_1000M_F_PHY	(VSC73XX_MAC_CFG_FDX | \
+					 VSC73XX_MAC_CFG_GIGA_MODE | \
+					 VSC73XX_MAC_CFG_TX_IPG_1000M | \
+					 VSC73XX_MAC_CFG_CLK_SEL_EXT)
+#define VSC73XX_MAC_CFG_100_10M_F_PHY	(VSC73XX_MAC_CFG_FDX | \
+					 VSC73XX_MAC_CFG_TX_IPG_100_10M | \
+					 VSC73XX_MAC_CFG_CLK_SEL_EXT)
+#define VSC73XX_MAC_CFG_100_10M_H_PHY	(VSC73XX_MAC_CFG_TX_IPG_100_10M | \
+					 VSC73XX_MAC_CFG_CLK_SEL_EXT)
+#define VSC73XX_MAC_CFG_1000M_F_RGMII	(VSC73XX_MAC_CFG_FDX | \
+					 VSC73XX_MAC_CFG_GIGA_MODE | \
+					 VSC73XX_MAC_CFG_TX_IPG_1000M | \
+					 VSC73XX_MAC_CFG_CLK_SEL_1000M)
+#define VSC73XX_MAC_CFG_RESET		(VSC73XX_MAC_CFG_PORT_RST | \
+					 VSC73XX_MAC_CFG_MAC_RX_RST | \
+					 VSC73XX_MAC_CFG_MAC_TX_RST)
+
+/* Flow control register bits */
+#define VSC73XX_FCCONF_ZERO_PAUSE_EN	BIT(17)
+#define VSC73XX_FCCONF_FLOW_CTRL_OBEY	BIT(16)
+#define VSC73XX_FCCONF_PAUSE_VAL_MASK	GENMASK(15, 0)
+
+/* ADVPORTM advanced port setup register bits */
+#define VSC73XX_ADVPORTM_IFG_PPM	BIT(7)
+#define VSC73XX_ADVPORTM_EXC_COL_CONT	BIT(6)
+#define VSC73XX_ADVPORTM_EXT_PORT	BIT(5)
+#define VSC73XX_ADVPORTM_INV_GTX	BIT(4)
+#define VSC73XX_ADVPORTM_ENA_GTX	BIT(3)
+#define VSC73XX_ADVPORTM_DDR_MODE	BIT(2)
+#define VSC73XX_ADVPORTM_IO_LOOPBACK	BIT(1)
+#define VSC73XX_ADVPORTM_HOST_LOOPBACK	BIT(0)
+
+/* CAT_DROP categorizer frame dropping register bits */
+#define VSC73XX_CAT_DROP_DROP_MC_SMAC_ENA	BIT(6)
+#define VSC73XX_CAT_DROP_FWD_CTRL_ENA		BIT(4)
+#define VSC73XX_CAT_DROP_FWD_PAUSE_ENA		BIT(3)
+#define VSC73XX_CAT_DROP_UNTAGGED_ENA		BIT(2)
+#define VSC73XX_CAT_DROP_TAGGED_ENA		BIT(1)
+#define VSC73XX_CAT_DROP_NULL_MAC_ENA		BIT(0)
+
+#define VSC73XX_Q_MISC_CONF_EXTENT_MEM		BIT(31)
+#define VSC73XX_Q_MISC_CONF_EARLY_TX_MASK	GENMASK(4, 1)
+#define VSC73XX_Q_MISC_CONF_EARLY_TX_512	(1 << 1)
+#define VSC73XX_Q_MISC_CONF_MAC_PAUSE_MODE	BIT(0)
+
+/* Frame analyzer block 2 registers */
+#define VSC73XX_STORMLIMIT	0x02
+#define VSC73XX_ADVLEARN	0x03
+#define VSC73XX_IFLODMSK	0x04
+#define VSC73XX_VLANMASK	0x05
+#define VSC73XX_MACHDATA	0x06
+#define VSC73XX_MACLDATA	0x07
+#define VSC73XX_ANMOVED		0x08
+#define VSC73XX_ANAGEFIL	0x09
+#define VSC73XX_ANEVENTS	0x0a
+#define VSC73XX_ANCNTMASK	0x0b
+#define VSC73XX_ANCNTVAL	0x0c
+#define VSC73XX_LEARNMASK	0x0d
+#define VSC73XX_UFLODMASK	0x0e
+#define VSC73XX_MFLODMASK	0x0f
+#define VSC73XX_RECVMASK	0x10
+#define VSC73XX_AGGRCTRL	0x20
+#define VSC73XX_AGGRMSKS	0x30 /* Until 0x3f */
+#define VSC73XX_DSTMASKS	0x40 /* Until 0x7f */
+#define VSC73XX_SRCMASKS	0x80 /* Until 0x87 */
+#define VSC73XX_CAPENAB		0xa0
+#define VSC73XX_MACACCESS	0xb0
+#define VSC73XX_IPMCACCESS	0xb1
+#define VSC73XX_MACTINDX	0xc0
+#define VSC73XX_VLANACCESS	0xd0
+#define VSC73XX_VLANTIDX	0xe0
+#define VSC73XX_AGENCTRL	0xf0
+#define VSC73XX_CAPRST		0xff
+
+#define VSC73XX_MACACCESS_CPU_COPY		BIT(14)
+#define VSC73XX_MACACCESS_FWD_KILL		BIT(13)
+#define VSC73XX_MACACCESS_IGNORE_VLAN		BIT(12)
+#define VSC73XX_MACACCESS_AGED_FLAG		BIT(11)
+#define VSC73XX_MACACCESS_VALID			BIT(10)
+#define VSC73XX_MACACCESS_LOCKED		BIT(9)
+#define VSC73XX_MACACCESS_DEST_IDX_MASK		GENMASK(8, 3)
+#define VSC73XX_MACACCESS_CMD_MASK		GENMASK(2, 0)
+#define VSC73XX_MACACCESS_CMD_IDLE		0
+#define VSC73XX_MACACCESS_CMD_LEARN		1
+#define VSC73XX_MACACCESS_CMD_FORGET		2
+#define VSC73XX_MACACCESS_CMD_AGE_TABLE		3
+#define VSC73XX_MACACCESS_CMD_FLUSH_TABLE	4
+#define VSC73XX_MACACCESS_CMD_CLEAR_TABLE	5
+#define VSC73XX_MACACCESS_CMD_READ_ENTRY	6
+#define VSC73XX_MACACCESS_CMD_WRITE_ENTRY	7
+
+#define VSC73XX_VLANACCESS_LEARN_DISABLED	BIT(30)
+#define VSC73XX_VLANACCESS_VLAN_MIRROR		BIT(29)
+#define VSC73XX_VLANACCESS_VLAN_SRC_CHECK	BIT(28)
+#define VSC73XX_VLANACCESS_VLAN_PORT_MASK	GENMASK(9, 2)
+#define VSC73XX_VLANACCESS_VLAN_TBL_CMD_MASK	GENMASK(2, 0)
+#define VSC73XX_VLANACCESS_VLAN_TBL_CMD_IDLE	0
+#define VSC73XX_VLANACCESS_VLAN_TBL_CMD_READ_ENTRY	1
+#define VSC73XX_VLANACCESS_VLAN_TBL_CMD_WRITE_ENTRY	2
+#define VSC73XX_VLANACCESS_VLAN_TBL_CMD_CLEAR_TABLE	3
+
+/* MII block 3 registers */
+#define VSC73XX_MII_STAT	0x0
+#define VSC73XX_MII_CMD		0x1
+#define VSC73XX_MII_DATA	0x2
+
+/* Arbiter block 5 registers */
+#define VSC73XX_ARBEMPTY		0x0c
+#define VSC73XX_ARBDISC			0x0e
+#define VSC73XX_SBACKWDROP		0x12
+#define VSC73XX_DBACKWDROP		0x13
+#define VSC73XX_ARBBURSTPROB		0x15
+
+/* System block 7 registers */
+#define VSC73XX_ICPU_SIPAD		0x01
+#define VSC73XX_GMIIDELAY		0x05
+#define VSC73XX_ICPU_CTRL		0x10
+#define VSC73XX_ICPU_ADDR		0x11
+#define VSC73XX_ICPU_SRAM		0x12
+#define VSC73XX_HWSEM			0x13
+#define VSC73XX_GLORESET		0x14
+#define VSC73XX_ICPU_MBOX_VAL		0x15
+#define VSC73XX_ICPU_MBOX_SET		0x16
+#define VSC73XX_ICPU_MBOX_CLR		0x17
+#define VSC73XX_CHIPID			0x18
+#define VSC73XX_GPIO			0x34
+
+#define VSC73XX_GMIIDELAY_GMII0_GTXDELAY_NONE	0
+#define VSC73XX_GMIIDELAY_GMII0_GTXDELAY_1_4_NS	1
+#define VSC73XX_GMIIDELAY_GMII0_GTXDELAY_1_7_NS	2
+#define VSC73XX_GMIIDELAY_GMII0_GTXDELAY_2_0_NS	3
+
+#define VSC73XX_GMIIDELAY_GMII0_RXDELAY_NONE	(0 << 4)
+#define VSC73XX_GMIIDELAY_GMII0_RXDELAY_1_4_NS	(1 << 4)
+#define VSC73XX_GMIIDELAY_GMII0_RXDELAY_1_7_NS	(2 << 4)
+#define VSC73XX_GMIIDELAY_GMII0_RXDELAY_2_0_NS	(3 << 4)
+
+#define VSC73XX_ICPU_CTRL_WATCHDOG_RST	BIT(31)
+#define VSC73XX_ICPU_CTRL_CLK_DIV_MASK	GENMASK(12, 8)
+#define VSC73XX_ICPU_CTRL_SRST_HOLD	BIT(7)
+#define VSC73XX_ICPU_CTRL_ICPU_PI_EN	BIT(6)
+#define VSC73XX_ICPU_CTRL_BOOT_EN	BIT(3)
+#define VSC73XX_ICPU_CTRL_EXT_ACC_EN	BIT(2)
+#define VSC73XX_ICPU_CTRL_CLK_EN	BIT(1)
+#define VSC73XX_ICPU_CTRL_SRST		BIT(0)
+
+#define VSC73XX_CHIPID_ID_SHIFT		12
+#define VSC73XX_CHIPID_ID_MASK		0xffff
+#define VSC73XX_CHIPID_REV_SHIFT	28
+#define VSC73XX_CHIPID_REV_MASK		0xf
+#define VSC73XX_CHIPID_ID_7385		0x7385
+#define VSC73XX_CHIPID_ID_7388		0x7388
+#define VSC73XX_CHIPID_ID_7395		0x7395
+#define VSC73XX_CHIPID_ID_7398		0x7398
+
+#define VSC73XX_GLORESET_STROBE		BIT(4)
+#define VSC73XX_GLORESET_ICPU_LOCK	BIT(3)
+#define VSC73XX_GLORESET_MEM_LOCK	BIT(2)
+#define VSC73XX_GLORESET_PHY_RESET	BIT(1)
+#define VSC73XX_GLORESET_MASTER_RESET	BIT(0)
+
+#define VSC73XX_CMD_MODE_READ		0
+#define VSC73XX_CMD_MODE_WRITE		1
+#define VSC73XX_CMD_MODE_SHIFT		4
+#define VSC73XX_CMD_BLOCK_SHIFT		5
+#define VSC73XX_CMD_BLOCK_MASK		0x7
+#define VSC73XX_CMD_SUBBLOCK_MASK	0xf
+
+#define VSC7385_CLOCK_DELAY		((3 << 4) | 3)
+#define VSC7385_CLOCK_DELAY_MASK	((3 << 4) | 3)
+
+#define VSC73XX_ICPU_CTRL_STOP	(VSC73XX_ICPU_CTRL_SRST_HOLD | \
+				 VSC73XX_ICPU_CTRL_BOOT_EN | \
+				 VSC73XX_ICPU_CTRL_EXT_ACC_EN)
+
+#define VSC73XX_ICPU_CTRL_START	(VSC73XX_ICPU_CTRL_CLK_DIV | \
+				 VSC73XX_ICPU_CTRL_BOOT_EN | \
+				 VSC73XX_ICPU_CTRL_CLK_EN | \
+				 VSC73XX_ICPU_CTRL_SRST)
+
+/**
+ * struct vsc73xx - VSC73xx state container
+ */
+struct vsc73xx {
+	struct device		*dev;
+	struct gpio_desc	*reset;
+	struct spi_device	*spi;
+	struct dsa_switch	*ds;
+	struct gpio_chip	gc;
+	u16			chipid;
+	u8			addr[ETH_ALEN];
+	struct mutex		lock; /* Protects SPI traffic */
+};
+
+#define IS_7385(a) ((a)->chipid == VSC73XX_CHIPID_ID_7385)
+#define IS_7388(a) ((a)->chipid == VSC73XX_CHIPID_ID_7388)
+#define IS_7395(a) ((a)->chipid == VSC73XX_CHIPID_ID_7395)
+#define IS_7398(a) ((a)->chipid == VSC73XX_CHIPID_ID_7398)
+#define IS_739X(a) (IS_7395(a) || IS_7398(a))
+
+struct vsc73xx_counter {
+	u8 counter;
+	const char *name;
+};
+
+/* Counters are named according to the MIB standards where applicable.
+ * Some counters are custom, non-standard. The standard counters are
+ * named in accordance with RFC2819, RFC2021 and IEEE Std 802.3-2002 Annex
+ * 30A Counters.
+ */
+static const struct vsc73xx_counter vsc73xx_rx_counters[] = {
+	{ 0, "RxEtherStatsPkts" },
+	{ 1, "RxBroadcast+MulticastPkts" }, /* non-standard counter */
+	{ 2, "RxTotalErrorPackets" }, /* non-standard counter */
+	{ 3, "RxEtherStatsBroadcastPkts" },
+	{ 4, "RxEtherStatsMulticastPkts" },
+	{ 5, "RxEtherStatsPkts64Octets" },
+	{ 6, "RxEtherStatsPkts65to127Octets" },
+	{ 7, "RxEtherStatsPkts128to255Octets" },
+	{ 8, "RxEtherStatsPkts256to511Octets" },
+	{ 9, "RxEtherStatsPkts512to1023Octets" },
+	{ 10, "RxEtherStatsPkts1024to1518Octets" },
+	{ 11, "RxJumboFrames" }, /* non-standard counter */
+	{ 12, "RxaPauseMACControlFramesTransmitted" },
+	{ 13, "RxFIFODrops" }, /* non-standard counter */
+	{ 14, "RxBackwardDrops" }, /* non-standard counter */
+	{ 15, "RxClassifierDrops" }, /* non-standard counter */
+	{ 16, "RxEtherStatsCRCAlignErrors" },
+	{ 17, "RxEtherStatsUndersizePkts" },
+	{ 18, "RxEtherStatsOversizePkts" },
+	{ 19, "RxEtherStatsFragments" },
+	{ 20, "RxEtherStatsJabbers" },
+	{ 21, "RxaMACControlFramesReceived" },
+	/* 22-24 are undefined */
+	{ 25, "RxaFramesReceivedOK" },
+	{ 26, "RxQoSClass0" }, /* non-standard counter */
+	{ 27, "RxQoSClass1" }, /* non-standard counter */
+	{ 28, "RxQoSClass2" }, /* non-standard counter */
+	{ 29, "RxQoSClass3" }, /* non-standard counter */
+};
+
+static const struct vsc73xx_counter vsc73xx_tx_counters[] = {
+	{ 0, "TxEtherStatsPkts" },
+	{ 1, "TxBroadcast+MulticastPkts" }, /* non-standard counter */
+	{ 2, "TxTotalErrorPackets" }, /* non-standard counter */
+	{ 3, "TxEtherStatsBroadcastPkts" },
+	{ 4, "TxEtherStatsMulticastPkts" },
+	{ 5, "TxEtherStatsPkts64Octets" },
+	{ 6, "TxEtherStatsPkts65to127Octets" },
+	{ 7, "TxEtherStatsPkts128to255Octets" },
+	{ 8, "TxEtherStatsPkts256to511Octets" },
+	{ 9, "TxEtherStatsPkts512to1023Octets" },
+	{ 10, "TxEtherStatsPkts1024to1518Octets" },
+	{ 11, "TxJumboFrames" }, /* non-standard counter */
+	{ 12, "TxaPauseMACControlFramesTransmitted" },
+	{ 13, "TxFIFODrops" }, /* non-standard counter */
+	{ 14, "TxDrops" }, /* non-standard counter */
+	{ 15, "TxEtherStatsCollisions" },
+	{ 16, "TxEtherStatsCRCAlignErrors" },
+	{ 17, "TxEtherStatsUndersizePkts" },
+	{ 18, "TxEtherStatsOversizePkts" },
+	{ 19, "TxEtherStatsFragments" },
+	{ 20, "TxEtherStatsJabbers" },
+	/* 21-24 are undefined */
+	{ 25, "TxaFramesReceivedOK" },
+	{ 26, "TxQoSClass0" }, /* non-standard counter */
+	{ 27, "TxQoSClass1" }, /* non-standard counter */
+	{ 28, "TxQoSClass2" }, /* non-standard counter */
+	{ 29, "TxQoSClass3" }, /* non-standard counter */
+};
+
+static int vsc73xx_is_addr_valid(u8 block, u8 subblock)
+{
+	switch (block) {
+	case VSC73XX_BLOCK_MAC:
+		switch (subblock) {
+		case 0 ... 4:
+		case 6:
+			return 1;
+		}
+		break;
+
+	case VSC73XX_BLOCK_ANALYZER:
+	case VSC73XX_BLOCK_SYSTEM:
+		switch (subblock) {
+		case 0:
+			return 1;
+		}
+		break;
+
+	case VSC73XX_BLOCK_MII:
+	case VSC73XX_BLOCK_CAPTURE:
+	case VSC73XX_BLOCK_ARBITER:
+		switch (subblock) {
+		case 0 ... 1:
+			return 1;
+		}
+		break;
+	}
+
+	return 0;
+}
+
+static u8 vsc73xx_make_addr(u8 mode, u8 block, u8 subblock)
+{
+	u8 ret;
+
+	ret = (block & VSC73XX_CMD_BLOCK_MASK) << VSC73XX_CMD_BLOCK_SHIFT;
+	ret |= (mode & 1) << VSC73XX_CMD_MODE_SHIFT;
+	ret |= subblock & VSC73XX_CMD_SUBBLOCK_MASK;
+
+	return ret;
+}
+
+static int vsc73xx_read(struct vsc73xx *vsc, u8 block, u8 subblock, u8 reg,
+			u32 *val)
+{
+	struct spi_transfer t[2];
+	struct spi_message m;
+	u8 cmd[4];
+	u8 buf[4];
+	int ret;
+
+	if (!vsc73xx_is_addr_valid(block, subblock))
+		return -EINVAL;
+
+	spi_message_init(&m);
+
+	memset(&t, 0, sizeof(t));
+
+	t[0].tx_buf = cmd;
+	t[0].len = sizeof(cmd);
+	spi_message_add_tail(&t[0], &m);
+
+	t[1].rx_buf = buf;
+	t[1].len = sizeof(buf);
+	spi_message_add_tail(&t[1], &m);
+
+	cmd[0] = vsc73xx_make_addr(VSC73XX_CMD_MODE_READ, block, subblock);
+	cmd[1] = reg;
+	cmd[2] = 0;
+	cmd[3] = 0;
+
+	mutex_lock(&vsc->lock);
+	ret = spi_sync(vsc->spi, &m);
+	mutex_unlock(&vsc->lock);
+
+	if (ret)
+		return ret;
+
+	*val = (buf[0] << 24) | (buf[1] << 16) | (buf[2] << 8) | buf[3];
+
+	return 0;
+}
+
+static int vsc73xx_write(struct vsc73xx *vsc, u8 block, u8 subblock, u8 reg,
+			 u32 val)
+{
+	struct spi_transfer t[2];
+	struct spi_message m;
+	u8 cmd[2];
+	u8 buf[4];
+	int ret;
+
+	if (!vsc73xx_is_addr_valid(block, subblock))
+		return -EINVAL;
+
+	spi_message_init(&m);
+
+	memset(&t, 0, sizeof(t));
+
+	t[0].tx_buf = cmd;
+	t[0].len = sizeof(cmd);
+	spi_message_add_tail(&t[0], &m);
+
+	t[1].tx_buf = buf;
+	t[1].len = sizeof(buf);
+	spi_message_add_tail(&t[1], &m);
+
+	cmd[0] = vsc73xx_make_addr(VSC73XX_CMD_MODE_WRITE, block, subblock);
+	cmd[1] = reg;
+
+	buf[0] = (val >> 24) & 0xff;
+	buf[1] = (val >> 16) & 0xff;
+	buf[2] = (val >> 8) & 0xff;
+	buf[3] = val & 0xff;
+
+	mutex_lock(&vsc->lock);
+	ret = spi_sync(vsc->spi, &m);
+	mutex_unlock(&vsc->lock);
+
+	return ret;
+}
+
+static int vsc73xx_update_bits(struct vsc73xx *vsc, u8 block, u8 subblock,
+			       u8 reg, u32 mask, u32 val)
+{
+	u32 tmp, orig;
+	int ret;
+
+	/* Same read-modify-write algorithm as e.g. regmap */
+	ret = vsc73xx_read(vsc, block, subblock, reg, &orig);
+	if (ret)
+		return ret;
+	tmp = orig & ~mask;
+	tmp |= val & mask;
+	return vsc73xx_write(vsc, block, subblock, reg, tmp);
+}
+
+static int vsc73xx_detect(struct vsc73xx *vsc)
+{
+	bool icpu_si_boot_en;
+	bool icpu_pi_en;
+	u32 val;
+	u32 rev;
+	int ret;
+	u32 id;
+
+	ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+			   VSC73XX_ICPU_MBOX_VAL, &val);
+	if (ret) {
+		dev_err(vsc->dev, "unable to read mailbox (%d)\n", ret);
+		return ret;
+	}
+
+	if (val == 0xffffffff) {
+		dev_info(vsc->dev, "chip seems dead, assert reset\n");
+		gpiod_set_value_cansleep(vsc->reset, 1);
+		/* Reset pulse should be 20ns minimum, according to datasheet
+		 * table 245, so 10us should be fine
+		 */
+		usleep_range(10, 100);
+		gpiod_set_value_cansleep(vsc->reset, 0);
+		/* Wait 20ms according to datasheet table 245 */
+		msleep(20);
+
+		ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+				   VSC73XX_ICPU_MBOX_VAL, &val);
+		if (val == 0xffffffff) {
+			dev_err(vsc->dev, "seems not to help, giving up\n");
+			return -ENODEV;
+		}
+	}
+
+	ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+			   VSC73XX_CHIPID, &val);
+	if (ret) {
+		dev_err(vsc->dev, "unable to read chip id (%d)\n", ret);
+		return ret;
+	}
+
+	id = (val >> VSC73XX_CHIPID_ID_SHIFT) &
+		VSC73XX_CHIPID_ID_MASK;
+	switch (id) {
+	case VSC73XX_CHIPID_ID_7385:
+	case VSC73XX_CHIPID_ID_7388:
+	case VSC73XX_CHIPID_ID_7395:
+	case VSC73XX_CHIPID_ID_7398:
+		break;
+	default:
+		dev_err(vsc->dev, "unsupported chip, id=%04x\n", id);
+		return -ENODEV;
+	}
+
+	vsc->chipid = id;
+	rev = (val >> VSC73XX_CHIPID_REV_SHIFT) &
+		VSC73XX_CHIPID_REV_MASK;
+	dev_info(vsc->dev, "VSC%04X (rev: %d) switch found\n", id, rev);
+
+	ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+			   VSC73XX_ICPU_CTRL, &val);
+	if (ret) {
+		dev_err(vsc->dev, "unable to read iCPU control\n");
+		return ret;
+	}
+
+	/* The iCPU can always be used but can boot in different ways.
+	 * If it is initially disabled and has no external memory,
+	 * we are in control and can do whatever we like, else we
+	 * are probably in trouble (we need some way to communicate
+	 * with the running firmware) so we bail out for now.
+	 */
+	icpu_pi_en = !!(val & VSC73XX_ICPU_CTRL_ICPU_PI_EN);
+	icpu_si_boot_en = !!(val & VSC73XX_ICPU_CTRL_BOOT_EN);
+	if (icpu_si_boot_en && icpu_pi_en) {
+		dev_err(vsc->dev,
+			"iCPU enabled boots from SI, has external memory\n");
+		dev_err(vsc->dev, "no idea how to deal with this\n");
+		return -ENODEV;
+	}
+	if (icpu_si_boot_en && !icpu_pi_en) {
+		dev_err(vsc->dev,
+			"iCPU enabled boots from SI, no external memory\n");
+		dev_err(vsc->dev, "no idea how to deal with this\n");
+		return -ENODEV;
+	}
+	if (!icpu_si_boot_en && icpu_pi_en) {
+		dev_err(vsc->dev,
+			"iCPU enabled, boots from PI external memory\n");
+		dev_err(vsc->dev, "no idea how to deal with this\n");
+		return -ENODEV;
+	}
+	/* !icpu_si_boot_en && !cpu_pi_en */
+	dev_info(vsc->dev, "iCPU disabled, no external memory\n");
+
+	return 0;
+}
+
+static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum)
+{
+	struct vsc73xx *vsc = ds->priv;
+	u32 cmd;
+	u32 val;
+	int ret;
+
+	/* Setting bit 26 means "read" */
+	cmd = BIT(26) | (phy << 21) | (regnum << 16);
+	ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd);
+	if (ret)
+		return ret;
+	msleep(2);
+	ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MII, 0, 2, &val);
+	if (ret)
+		return ret;
+	if (val & BIT(16)) {
+		dev_err(vsc->dev, "reading reg %02x from phy%d failed\n",
+			regnum, phy);
+		return -EIO;
+	}
+	val &= 0xFFFFU;
+
+	dev_dbg(vsc->dev, "read reg %02x from phy%d = %04x\n",
+		regnum, phy, val);
+
+	return val;
+}
+
+static int vsc73xx_phy_write(struct dsa_switch *ds, int phy, int regnum,
+			     u16 val)
+{
+	struct vsc73xx *vsc = ds->priv;
+	u32 cmd;
+	int ret;
+
+	/* It was found through tedious experiments that this router
+	 * chip really hates to have it's PHYs reset. They
+	 * never recover if that happens: autonegotiation stops
+	 * working after a reset. Just filter out this command.
+	 * (Resetting the whole chip is OK.)
+	 */
+	if (regnum == 0 && (val & BIT(15))) {
+		dev_info(vsc->dev, "reset PHY - disallowed\n");
+		return 0;
+	}
+
+	cmd = (phy << 21) | (regnum << 16);
+	ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd);
+	if (ret)
+		return ret;
+
+	dev_dbg(vsc->dev, "write %04x to reg %02x in phy%d\n",
+		val, regnum, phy);
+	return 0;
+}
+
+static enum dsa_tag_protocol vsc73xx_get_tag_protocol(struct dsa_switch *ds,
+						      int port)
+{
+	/* The switch internally uses a 8 byte header with length,
+	 * source port, tag, LPA and priority. This is supposedly
+	 * only accessible when operating the switch using the internal
+	 * CPU or with an external CPU mapping the device in, but not
+	 * when operating the switch over SPI and putting frames in/out
+	 * on port 6 (the CPU port). So far we must assume that we
+	 * cannot access the tag. (See "Internal frame header" section
+	 * 3.9.1 in the manual.)
+	 */
+	return DSA_TAG_PROTO_NONE;
+}
+
+static int vsc73xx_setup(struct dsa_switch *ds)
+{
+	struct vsc73xx *vsc = ds->priv;
+	int i;
+
+	dev_info(vsc->dev, "set up the switch\n");
+
+	/* Issue RESET */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_SYSTEM, 0, VSC73XX_GLORESET,
+		      VSC73XX_GLORESET_MASTER_RESET);
+	usleep_range(125, 200);
+
+	/* Initialize memory, initialize RAM bank 0..15 except 6 and 7
+	 * This sequence appears in the
+	 * VSC7385 SparX-G5 datasheet section 6.6.1
+	 * VSC7395 SparX-G5e datasheet section 6.6.1
+	 * "initialization sequence".
+	 * No explanation is given to the 0x1010400 magic number.
+	 */
+	for (i = 0; i <= 15; i++) {
+		if (i != 6 && i != 7) {
+			vsc73xx_write(vsc, VSC73XX_BLOCK_MEMINIT,
+				      2,
+				      0, 0x1010400 + i);
+			mdelay(1);
+		}
+	}
+	mdelay(30);
+
+	/* Clear MAC table */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_ANALYZER, 0,
+		      VSC73XX_MACACCESS,
+		      VSC73XX_MACACCESS_CMD_CLEAR_TABLE);
+
+	/* Clear VLAN table */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_ANALYZER, 0,
+		      VSC73XX_VLANACCESS,
+		      VSC73XX_VLANACCESS_VLAN_TBL_CMD_CLEAR_TABLE);
+
+	msleep(40);
+
+	/* Use 20KiB buffers on all ports on VSC7395
+	 * The VSC7385 has 16KiB buffers and that is the
+	 * default if we don't set this up explicitly.
+	 * Port "31" is "all ports".
+	 */
+	if (IS_739X(vsc))
+		vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, 0x1f,
+			      VSC73XX_Q_MISC_CONF,
+			      VSC73XX_Q_MISC_CONF_EXTENT_MEM);
+
+	/* Put all ports into reset until enabled */
+	for (i = 0; i < 7; i++) {
+		if (i == 5)
+			continue;
+		vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, 4,
+			      VSC73XX_MAC_CFG, VSC73XX_MAC_CFG_RESET);
+	}
+
+	/* MII delay, set both GTX and RX delay to 2 ns */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_SYSTEM, 0, VSC73XX_GMIIDELAY,
+		      VSC73XX_GMIIDELAY_GMII0_GTXDELAY_2_0_NS |
+		      VSC73XX_GMIIDELAY_GMII0_RXDELAY_2_0_NS);
+	/* Enable reception of frames on all ports */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_ANALYZER, 0, VSC73XX_RECVMASK,
+		      0x5f);
+	/* IP multicast flood mask (table 144) */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_ANALYZER, 0, VSC73XX_IFLODMSK,
+		      0xff);
+
+	mdelay(50);
+
+	/* Release reset from the internal PHYs */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_SYSTEM, 0, VSC73XX_GLORESET,
+		      VSC73XX_GLORESET_PHY_RESET);
+
+	udelay(4);
+
+	return 0;
+}
+
+static void vsc73xx_init_port(struct vsc73xx *vsc, int port)
+{
+	u32 val;
+
+	/* MAC configure, first reset the port and then write defaults */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+		      port,
+		      VSC73XX_MAC_CFG,
+		      VSC73XX_MAC_CFG_RESET);
+
+	/* Take up the port in 1Gbit mode by default, this will be
+	 * augmented after auto-negotiation on the PHY-facing
+	 * ports.
+	 */
+	if (port == CPU_PORT)
+		val = VSC73XX_MAC_CFG_1000M_F_RGMII;
+	else
+		val = VSC73XX_MAC_CFG_1000M_F_PHY;
+
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+		      port,
+		      VSC73XX_MAC_CFG,
+		      val |
+		      VSC73XX_MAC_CFG_TX_EN |
+		      VSC73XX_MAC_CFG_RX_EN);
+
+	/* Max length, we can do up to 9.6 KiB, so allow that.
+	 * According to application not "VSC7398 Jumbo Frames" setting
+	 * up the MTU to 9.6 KB does not affect the performance on standard
+	 * frames, so just enable it. It is clear from the application note
+	 * that "9.6 kilobytes" == 9600 bytes.
+	 */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+		      port,
+		      VSC73XX_MAXLEN, 9600);
+
+	/* Flow control for the CPU port:
+	 * Use a zero delay pause frame when pause condition is left
+	 * Obey pause control frames
+	 */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+		      port,
+		      VSC73XX_FCCONF,
+		      VSC73XX_FCCONF_ZERO_PAUSE_EN |
+		      VSC73XX_FCCONF_FLOW_CTRL_OBEY);
+
+	/* Issue pause control frames on PHY facing ports.
+	 * Allow early initiation of MAC transmission if the amount
+	 * of egress data is below 512 bytes on CPU port.
+	 * FIXME: enable 20KiB buffers?
+	 */
+	if (port == CPU_PORT)
+		val = VSC73XX_Q_MISC_CONF_EARLY_TX_512;
+	else
+		val = VSC73XX_Q_MISC_CONF_MAC_PAUSE_MODE;
+	val |= VSC73XX_Q_MISC_CONF_EXTENT_MEM;
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+		      port,
+		      VSC73XX_Q_MISC_CONF,
+		      val);
+
+	/* Flow control MAC: a MAC address used in flow control frames */
+	val = (vsc->addr[5] << 16) | (vsc->addr[4] << 8) | (vsc->addr[3]);
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+		      port,
+		      VSC73XX_FCMACHI,
+		      val);
+	val = (vsc->addr[2] << 16) | (vsc->addr[1] << 8) | (vsc->addr[0]);
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+		      port,
+		      VSC73XX_FCMACLO,
+		      val);
+
+	/* Tell the categorizer to forward pause frames, not control
+	 * frame. Do not drop anything.
+	 */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+		      port,
+		      VSC73XX_CAT_DROP,
+		      VSC73XX_CAT_DROP_FWD_PAUSE_ENA);
+
+	/* Clear all counters */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+		      port, VSC73XX_C_RX0, 0);
+}
+
+static void vsc73xx_adjust_enable_port(struct vsc73xx *vsc,
+				       int port, struct phy_device *phydev,
+				       u32 initval)
+{
+	u32 val = initval;
+	u8 seed;
+
+	/* Reset this port FIXME: break out subroutine */
+	val |= VSC73XX_MAC_CFG_RESET;
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, port, VSC73XX_MAC_CFG, val);
+
+	/* Seed the port randomness with randomness */
+	get_random_bytes(&seed, 1);
+	val |= seed << VSC73XX_MAC_CFG_SEED_OFFSET;
+	val |= VSC73XX_MAC_CFG_SEED_LOAD;
+	val |= VSC73XX_MAC_CFG_WEXC_DIS;
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, port, VSC73XX_MAC_CFG, val);
+
+	/* Flow control for the PHY facing ports:
+	 * Use a zero delay pause frame when pause condition is left
+	 * Obey pause control frames
+	 * When generating pause frames, use 0xff as pause value
+	 */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, port, VSC73XX_FCCONF,
+		      VSC73XX_FCCONF_ZERO_PAUSE_EN |
+		      VSC73XX_FCCONF_FLOW_CTRL_OBEY |
+		      0xff);
+
+	/* Disallow backward dropping of frames from this port */
+	vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ARBITER, 0,
+			    VSC73XX_SBACKWDROP, BIT(port), 0);
+
+	/* Enable TX, RX, deassert reset, stop loading seed */
+	vsc73xx_update_bits(vsc, VSC73XX_BLOCK_MAC, port,
+			    VSC73XX_MAC_CFG,
+			    VSC73XX_MAC_CFG_RESET | VSC73XX_MAC_CFG_SEED_LOAD |
+			    VSC73XX_MAC_CFG_TX_EN | VSC73XX_MAC_CFG_RX_EN,
+			    VSC73XX_MAC_CFG_TX_EN | VSC73XX_MAC_CFG_RX_EN);
+}
+
+static void vsc73xx_adjust_link(struct dsa_switch *ds, int port,
+				struct phy_device *phydev)
+{
+	struct vsc73xx *vsc = ds->priv;
+	u32 val;
+
+	/* Special handling of the CPU-facing port */
+	if (port == CPU_PORT) {
+		/* Other ports are already initialized but not this one */
+		vsc73xx_init_port(vsc, CPU_PORT);
+		/* Select the external port for this interface (EXT_PORT)
+		 * Enable the GMII GTX external clock
+		 * Use double data rate (DDR mode)
+		 */
+		vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+			      CPU_PORT,
+			      VSC73XX_ADVPORTM,
+			      VSC73XX_ADVPORTM_EXT_PORT |
+			      VSC73XX_ADVPORTM_ENA_GTX |
+			      VSC73XX_ADVPORTM_DDR_MODE);
+	}
+
+	/* This is the MAC confiuration that always need to happen
+	 * after a PHY or the CPU port comes up or down.
+	 */
+	if (!phydev->link) {
+		int maxloop = 10;
+
+		dev_dbg(vsc->dev, "port %d: went down\n",
+			port);
+
+		/* Disable RX on this port */
+		vsc73xx_update_bits(vsc, VSC73XX_BLOCK_MAC, port,
+				    VSC73XX_MAC_CFG,
+				    VSC73XX_MAC_CFG_RX_EN, 0);
+
+		/* Discard packets */
+		vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ARBITER, 0,
+				    VSC73XX_ARBDISC, BIT(port), BIT(port));
+
+		/* Wait until queue is empty */
+		vsc73xx_read(vsc, VSC73XX_BLOCK_ARBITER, 0,
+			     VSC73XX_ARBEMPTY, &val);
+		while (!(val & BIT(port))) {
+			msleep(1);
+			vsc73xx_read(vsc, VSC73XX_BLOCK_ARBITER, 0,
+				     VSC73XX_ARBEMPTY, &val);
+			if (--maxloop == 0) {
+				dev_err(vsc->dev,
+					"timeout waiting for block arbiter\n");
+				/* Continue anyway */
+				break;
+			}
+		}
+
+		/* Put this port into reset */
+		vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, port, VSC73XX_MAC_CFG,
+			      VSC73XX_MAC_CFG_RESET);
+
+		/* Accept packets again */
+		vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ARBITER, 0,
+				    VSC73XX_ARBDISC, BIT(port), 0);
+
+		/* Allow backward dropping of frames from this port */
+		vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ARBITER, 0,
+				    VSC73XX_SBACKWDROP, BIT(port), BIT(port));
+
+		/* Receive mask (disable forwarding) */
+		vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ANALYZER, 0,
+				    VSC73XX_RECVMASK, BIT(port), 0);
+
+		return;
+	}
+
+	/* Figure out what speed was negotiated */
+	if (phydev->speed == SPEED_1000) {
+		dev_dbg(vsc->dev, "port %d: 1000 Mbit mode full duplex\n",
+			port);
+
+		/* Set up default for internal port or external RGMII */
+		if (phydev->interface == PHY_INTERFACE_MODE_RGMII)
+			val = VSC73XX_MAC_CFG_1000M_F_RGMII;
+		else
+			val = VSC73XX_MAC_CFG_1000M_F_PHY;
+		vsc73xx_adjust_enable_port(vsc, port, phydev, val);
+	} else if (phydev->speed == SPEED_100) {
+		if (phydev->duplex == DUPLEX_FULL) {
+			val = VSC73XX_MAC_CFG_100_10M_F_PHY;
+			dev_dbg(vsc->dev,
+				"port %d: 100 Mbit full duplex mode\n",
+				port);
+		} else {
+			val = VSC73XX_MAC_CFG_100_10M_H_PHY;
+			dev_dbg(vsc->dev,
+				"port %d: 100 Mbit half duplex mode\n",
+				port);
+		}
+		vsc73xx_adjust_enable_port(vsc, port, phydev, val);
+	} else if (phydev->speed == SPEED_10) {
+		if (phydev->duplex == DUPLEX_FULL) {
+			val = VSC73XX_MAC_CFG_100_10M_F_PHY;
+			dev_dbg(vsc->dev,
+				"port %d: 10 Mbit full duplex mode\n",
+				port);
+		} else {
+			val = VSC73XX_MAC_CFG_100_10M_H_PHY;
+			dev_dbg(vsc->dev,
+				"port %d: 10 Mbit half duplex mode\n",
+				port);
+		}
+		vsc73xx_adjust_enable_port(vsc, port, phydev, val);
+	} else {
+		dev_err(vsc->dev,
+			"could not adjust link: unknown speed\n");
+	}
+
+	/* Enable port (forwarding) in the receieve mask */
+	vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ANALYZER, 0,
+			    VSC73XX_RECVMASK, BIT(port), BIT(port));
+}
+
+static int vsc73xx_port_enable(struct dsa_switch *ds, int port,
+			       struct phy_device *phy)
+{
+	struct vsc73xx *vsc = ds->priv;
+
+	dev_info(vsc->dev, "enable port %d\n", port);
+	vsc73xx_init_port(vsc, port);
+
+	return 0;
+}
+
+static void vsc73xx_port_disable(struct dsa_switch *ds, int port,
+				 struct phy_device *phy)
+{
+	struct vsc73xx *vsc = ds->priv;
+
+	/* Just put the port into reset */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, port,
+		      VSC73XX_MAC_CFG, VSC73XX_MAC_CFG_RESET);
+}
+
+static const struct vsc73xx_counter *
+vsc73xx_find_counter(struct vsc73xx *vsc,
+		     u8 counter,
+		     bool tx)
+{
+	const struct vsc73xx_counter *cnts;
+	int num_cnts;
+	int i;
+
+	if (tx) {
+		cnts = vsc73xx_tx_counters;
+		num_cnts = ARRAY_SIZE(vsc73xx_tx_counters);
+	} else {
+		cnts = vsc73xx_rx_counters;
+		num_cnts = ARRAY_SIZE(vsc73xx_rx_counters);
+	}
+
+	for (i = 0; i < num_cnts; i++) {
+		const struct vsc73xx_counter *cnt;
+
+		cnt = &cnts[i];
+		if (cnt->counter == counter)
+			return cnt;
+	}
+
+	return NULL;
+}
+
+static void vsc73xx_get_strings(struct dsa_switch *ds, int port, u32 stringset,
+				uint8_t *data)
+{
+	const struct vsc73xx_counter *cnt;
+	struct vsc73xx *vsc = ds->priv;
+	u8 indices[6];
+	int i, j;
+	u32 val;
+	int ret;
+
+	if (stringset != ETH_SS_STATS)
+		return;
+
+	ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MAC, port,
+			   VSC73XX_C_CFG, &val);
+	if (ret)
+		return;
+
+	indices[0] = (val & 0x1f); /* RX counter 0 */
+	indices[1] = ((val >> 5) & 0x1f); /* RX counter 1 */
+	indices[2] = ((val >> 10) & 0x1f); /* RX counter 2 */
+	indices[3] = ((val >> 16) & 0x1f); /* TX counter 0 */
+	indices[4] = ((val >> 21) & 0x1f); /* TX counter 1 */
+	indices[5] = ((val >> 26) & 0x1f); /* TX counter 2 */
+
+	/* The first counters is the RX octets */
+	j = 0;
+	strncpy(data + j * ETH_GSTRING_LEN,
+		"RxEtherStatsOctets", ETH_GSTRING_LEN);
+	j++;
+
+	/* Each port supports recording 3 RX counters and 3 TX counters,
+	 * figure out what counters we use in this set-up and return the
+	 * names of them. The hardware default counters will be number of
+	 * packets on RX/TX, combined broadcast+multicast packets RX/TX and
+	 * total error packets RX/TX.
+	 */
+	for (i = 0; i < 3; i++) {
+		cnt = vsc73xx_find_counter(vsc, indices[i], false);
+		if (cnt)
+			strncpy(data + j * ETH_GSTRING_LEN,
+				cnt->name, ETH_GSTRING_LEN);
+		j++;
+	}
+
+	/* TX stats begins with the number of TX octets */
+	strncpy(data + j * ETH_GSTRING_LEN,
+		"TxEtherStatsOctets", ETH_GSTRING_LEN);
+	j++;
+
+	for (i = 3; i < 6; i++) {
+		cnt = vsc73xx_find_counter(vsc, indices[i], true);
+		if (cnt)
+			strncpy(data + j * ETH_GSTRING_LEN,
+				cnt->name, ETH_GSTRING_LEN);
+		j++;
+	}
+}
+
+static int vsc73xx_get_sset_count(struct dsa_switch *ds, int port, int sset)
+{
+	/* We only support SS_STATS */
+	if (sset != ETH_SS_STATS)
+		return 0;
+	/* RX and TX packets, then 3 RX counters, 3 TX counters */
+	return 8;
+}
+
+static void vsc73xx_get_ethtool_stats(struct dsa_switch *ds, int port,
+				      uint64_t *data)
+{
+	struct vsc73xx *vsc = ds->priv;
+	u8 regs[] = {
+		VSC73XX_RXOCT,
+		VSC73XX_C_RX0,
+		VSC73XX_C_RX1,
+		VSC73XX_C_RX2,
+		VSC73XX_TXOCT,
+		VSC73XX_C_TX0,
+		VSC73XX_C_TX1,
+		VSC73XX_C_TX2,
+	};
+	u32 val;
+	int ret;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(regs); i++) {
+		ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MAC, port,
+				   regs[i], &val);
+		if (ret) {
+			dev_err(vsc->dev, "error reading counter %d\n", i);
+			return;
+		}
+		data[i] = val;
+	}
+}
+
+static const struct dsa_switch_ops vsc73xx_ds_ops = {
+	.get_tag_protocol = vsc73xx_get_tag_protocol,
+	.setup = vsc73xx_setup,
+	.phy_read = vsc73xx_phy_read,
+	.phy_write = vsc73xx_phy_write,
+	.adjust_link = vsc73xx_adjust_link,
+	.get_strings = vsc73xx_get_strings,
+	.get_ethtool_stats = vsc73xx_get_ethtool_stats,
+	.get_sset_count = vsc73xx_get_sset_count,
+	.port_enable = vsc73xx_port_enable,
+	.port_disable = vsc73xx_port_disable,
+};
+
+static int vsc73xx_gpio_get(struct gpio_chip *chip, unsigned int offset)
+{
+	struct vsc73xx *vsc = gpiochip_get_data(chip);
+	u32 val;
+	int ret;
+
+	ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+			   VSC73XX_GPIO, &val);
+	if (ret)
+		return ret;
+
+	return !!(val & BIT(offset));
+}
+
+static void vsc73xx_gpio_set(struct gpio_chip *chip, unsigned int offset,
+			     int val)
+{
+	struct vsc73xx *vsc = gpiochip_get_data(chip);
+	u32 tmp = val ? BIT(offset) : 0;
+
+	vsc73xx_update_bits(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+			    VSC73XX_GPIO, BIT(offset), tmp);
+}
+
+static int vsc73xx_gpio_direction_output(struct gpio_chip *chip,
+					 unsigned int offset, int val)
+{
+	struct vsc73xx *vsc = gpiochip_get_data(chip);
+	u32 tmp = val ? BIT(offset) : 0;
+
+	return vsc73xx_update_bits(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+				   VSC73XX_GPIO, BIT(offset + 4) | BIT(offset),
+				   BIT(offset + 4) | tmp);
+}
+
+static int vsc73xx_gpio_direction_input(struct gpio_chip *chip,
+					unsigned int offset)
+{
+	struct vsc73xx *vsc = gpiochip_get_data(chip);
+
+	return  vsc73xx_update_bits(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+				    VSC73XX_GPIO, BIT(offset + 4),
+				    0);
+}
+
+static int vsc73xx_gpio_get_direction(struct gpio_chip *chip,
+				      unsigned int offset)
+{
+	struct vsc73xx *vsc = gpiochip_get_data(chip);
+	u32 val;
+	int ret;
+
+	ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+			   VSC73XX_GPIO, &val);
+	if (ret)
+		return ret;
+
+	return !(val & BIT(offset + 4));
+}
+
+static int vsc73xx_gpio_probe(struct vsc73xx *vsc)
+{
+	int ret;
+
+	vsc->gc.label = devm_kasprintf(vsc->dev, GFP_KERNEL, "VSC%04x",
+				       vsc->chipid);
+	vsc->gc.ngpio = 4;
+	vsc->gc.owner = THIS_MODULE;
+	vsc->gc.parent = vsc->dev;
+	vsc->gc.of_node = vsc->dev->of_node;
+	vsc->gc.base = -1;
+	vsc->gc.get = vsc73xx_gpio_get;
+	vsc->gc.set = vsc73xx_gpio_set;
+	vsc->gc.direction_input = vsc73xx_gpio_direction_input;
+	vsc->gc.direction_output = vsc73xx_gpio_direction_output;
+	vsc->gc.get_direction = vsc73xx_gpio_get_direction;
+	vsc->gc.can_sleep = true;
+	ret = devm_gpiochip_add_data(vsc->dev, &vsc->gc, vsc);
+	if (ret) {
+		dev_err(vsc->dev, "unable to register GPIO chip\n");
+		return ret;
+	}
+	return 0;
+}
+
+static int vsc73xx_probe(struct spi_device *spi)
+{
+	struct device *dev = &spi->dev;
+	struct vsc73xx *vsc;
+	int ret;
+
+	vsc = devm_kzalloc(dev, sizeof(*vsc), GFP_KERNEL);
+	if (!vsc)
+		return -ENOMEM;
+
+	spi_set_drvdata(spi, vsc);
+	vsc->spi = spi_dev_get(spi);
+	vsc->dev = dev;
+	mutex_init(&vsc->lock);
+
+	/* Release reset, if any */
+	vsc->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(vsc->reset)) {
+		dev_err(dev, "failed to get RESET GPIO\n");
+		return PTR_ERR(vsc->reset);
+	}
+	if (vsc->reset)
+		/* Wait 20ms according to datasheet table 245 */
+		msleep(20);
+
+	spi->mode = SPI_MODE_0;
+	spi->bits_per_word = 8;
+	ret = spi_setup(spi);
+	if (ret < 0) {
+		dev_err(dev, "spi setup failed.\n");
+		return ret;
+	}
+
+	ret = vsc73xx_detect(vsc);
+	if (ret) {
+		dev_err(dev, "no chip found (%d)\n", ret);
+		return -ENODEV;
+	}
+
+	eth_random_addr(vsc->addr);
+	dev_info(vsc->dev,
+		 "MAC for control frames: %02X:%02X:%02X:%02X:%02X:%02X\n",
+		 vsc->addr[0], vsc->addr[1], vsc->addr[2],
+		 vsc->addr[3], vsc->addr[4], vsc->addr[5]);
+
+	/* The VSC7395 switch chips have 5+1 ports which means 5
+	 * ordinary ports and a sixth CPU port facing the processor
+	 * with an RGMII interface. These ports are numbered 0..4
+	 * and 6, so they leave a "hole" in the port map for port 5,
+	 * which is invalid.
+	 *
+	 * The VSC7398 has 8 ports, port 7 is again the CPU port.
+	 *
+	 * We allocate 8 ports and avoid access to the nonexistant
+	 * ports.
+	 */
+	vsc->ds = dsa_switch_alloc(dev, 8);
+	if (!vsc->ds)
+		return -ENOMEM;
+	vsc->ds->priv = vsc;
+
+	vsc->ds->ops = &vsc73xx_ds_ops;
+	ret = dsa_register_switch(vsc->ds);
+	if (ret) {
+		dev_err(dev, "unable to register switch (%d)\n", ret);
+		return ret;
+	}
+
+	ret = vsc73xx_gpio_probe(vsc);
+	if (ret) {
+		dsa_unregister_switch(vsc->ds);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int vsc73xx_remove(struct spi_device *spi)
+{
+	struct vsc73xx *vsc = spi_get_drvdata(spi);
+
+	dsa_unregister_switch(vsc->ds);
+	gpiod_set_value(vsc->reset, 1);
+
+	return 0;
+}
+
+static const struct of_device_id vsc73xx_of_match[] = {
+	{
+		.compatible = "vitesse,vsc7385",
+	},
+	{
+		.compatible = "vitesse,vsc7388",
+	},
+	{
+		.compatible = "vitesse,vsc7395",
+	},
+	{
+		.compatible = "vitesse,vsc7398",
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, vsc73xx_of_match);
+
+static struct spi_driver vsc73xx_driver = {
+	.probe = vsc73xx_probe,
+	.remove = vsc73xx_remove,
+	.driver = {
+		.name = "vsc73xx",
+		.of_match_table = vsc73xx_of_match,
+	},
+};
+module_spi_driver(vsc73xx_driver);
+
+MODULE_AUTHOR("Linus Walleij <linus.walleij@linaro.org>");
+MODULE_DESCRIPTION("Vitesse VSC7385/7388/7395/7398 driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c
index d422a124cd7c..0b6bbf63f7ca 100644
--- a/drivers/net/ethernet/8390/axnet_cs.c
+++ b/drivers/net/ethernet/8390/axnet_cs.c
@@ -610,6 +610,7 @@ static int axnet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
     switch (cmd) {
     case SIOCGMIIPHY:
 	data->phy_id = info->phy_id;
+	/* Fall through */
     case SIOCGMIIREG:		/* Read MII PHY register. */
 	data->val_out = mdio_read(mii_addr, data->phy_id, data->reg_num & 0x1f);
 	return 0;
diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c
index b6d735bf8011..342ae08ec3c2 100644
--- a/drivers/net/ethernet/8390/mac8390.c
+++ b/drivers/net/ethernet/8390/mac8390.c
@@ -153,9 +153,6 @@ static void dayna_block_input(struct net_device *dev, int count,
 static void dayna_block_output(struct net_device *dev, int count,
 			       const unsigned char *buf, int start_page);
 
-#define memcpy_fromio(a, b, c)	memcpy((a), (void *)(b), (c))
-#define memcpy_toio(a, b, c)	memcpy((void *)(a), (b), (c))
-
 #define memcmp_withio(a, b, c)	memcmp((a), (void *)(b), (c))
 
 /* Slow Sane (16-bit chunk memory read/write) Cabletron uses this */
@@ -239,7 +236,7 @@ static enum mac8390_access mac8390_testio(unsigned long membase)
 	unsigned long outdata = 0xA5A0B5B0;
 	unsigned long indata =  0x00000000;
 	/* Try writing 32 bits */
-	memcpy_toio(membase, &outdata, 4);
+	memcpy_toio((void __iomem *)membase, &outdata, 4);
 	/* Now compare them */
 	if (memcmp_withio(&outdata, membase, 4) == 0)
 		return ACCESS_32;
@@ -711,7 +708,7 @@ static void sane_get_8390_hdr(struct net_device *dev,
 			      struct e8390_pkt_hdr *hdr, int ring_page)
 {
 	unsigned long hdr_start = (ring_page - WD_START_PG)<<8;
-	memcpy_fromio(hdr, dev->mem_start + hdr_start, 4);
+	memcpy_fromio(hdr, (void __iomem *)dev->mem_start + hdr_start, 4);
 	/* Fix endianness */
 	hdr->count = swab16(hdr->count);
 }
@@ -725,13 +722,16 @@ static void sane_block_input(struct net_device *dev, int count,
 	if (xfer_start + count > ei_status.rmem_end) {
 		/* We must wrap the input move. */
 		int semi_count = ei_status.rmem_end - xfer_start;
-		memcpy_fromio(skb->data, dev->mem_start + xfer_base,
+		memcpy_fromio(skb->data,
+			      (void __iomem *)dev->mem_start + xfer_base,
 			      semi_count);
 		count -= semi_count;
-		memcpy_fromio(skb->data + semi_count, ei_status.rmem_start,
-			      count);
+		memcpy_fromio(skb->data + semi_count,
+			      (void __iomem *)ei_status.rmem_start, count);
 	} else {
-		memcpy_fromio(skb->data, dev->mem_start + xfer_base, count);
+		memcpy_fromio(skb->data,
+			      (void __iomem *)dev->mem_start + xfer_base,
+			      count);
 	}
 }
 
@@ -740,7 +740,7 @@ static void sane_block_output(struct net_device *dev, int count,
 {
 	long shmem = (start_page - WD_START_PG)<<8;
 
-	memcpy_toio(dev->mem_start + shmem, buf, count);
+	memcpy_toio((void __iomem *)dev->mem_start + shmem, buf, count);
 }
 
 /* dayna block input/output */
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index af766fd61151..6fde68aa13a4 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -81,7 +81,6 @@ source "drivers/net/ethernet/huawei/Kconfig"
 source "drivers/net/ethernet/i825xx/Kconfig"
 source "drivers/net/ethernet/ibm/Kconfig"
 source "drivers/net/ethernet/intel/Kconfig"
-source "drivers/net/ethernet/neterion/Kconfig"
 source "drivers/net/ethernet/xscale/Kconfig"
 
 config JME
@@ -128,6 +127,7 @@ config FEALNX
 	  cards. <http://www.myson.com.tw/>
 
 source "drivers/net/ethernet/natsemi/Kconfig"
+source "drivers/net/ethernet/neterion/Kconfig"
 source "drivers/net/ethernet/netronome/Kconfig"
 source "drivers/net/ethernet/ni/Kconfig"
 source "drivers/net/ethernet/8390/Kconfig"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 8fbfe9ce2fa5..b45d5f626b59 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -20,7 +20,7 @@ obj-$(CONFIG_NET_VENDOR_AQUANTIA) += aquantia/
 obj-$(CONFIG_NET_VENDOR_ARC) += arc/
 obj-$(CONFIG_NET_VENDOR_ATHEROS) += atheros/
 obj-$(CONFIG_NET_VENDOR_AURORA) += aurora/
-obj-$(CONFIG_NET_CADENCE) += cadence/
+obj-$(CONFIG_NET_VENDOR_CADENCE) += cadence/
 obj-$(CONFIG_NET_VENDOR_BROADCOM) += broadcom/
 obj-$(CONFIG_NET_VENDOR_BROCADE) += brocade/
 obj-$(CONFIG_NET_CALXEDA_XGMAC) += calxeda/
@@ -36,7 +36,6 @@ obj-$(CONFIG_NET_VENDOR_DEC) += dec/
 obj-$(CONFIG_NET_VENDOR_DLINK) += dlink/
 obj-$(CONFIG_NET_VENDOR_EMULEX) += emulex/
 obj-$(CONFIG_NET_VENDOR_EZCHIP) += ezchip/
-obj-$(CONFIG_NET_VENDOR_EXAR) += neterion/
 obj-$(CONFIG_NET_VENDOR_FARADAY) += faraday/
 obj-$(CONFIG_NET_VENDOR_FREESCALE) += freescale/
 obj-$(CONFIG_NET_VENDOR_FUJITSU) += fujitsu/
@@ -60,6 +59,7 @@ obj-$(CONFIG_NET_VENDOR_MOXART) += moxa/
 obj-$(CONFIG_NET_VENDOR_MYRI) += myricom/
 obj-$(CONFIG_FEALNX) += fealnx.o
 obj-$(CONFIG_NET_VENDOR_NATSEMI) += natsemi/
+obj-$(CONFIG_NET_VENDOR_NETERION) += neterion/
 obj-$(CONFIG_NET_VENDOR_NETRONOME) += netronome/
 obj-$(CONFIG_NET_VENDOR_NI) += ni/
 obj-$(CONFIG_NET_NETX) += netx-eth.o
@@ -68,7 +68,7 @@ obj-$(CONFIG_NET_VENDOR_NVIDIA) += nvidia/
 obj-$(CONFIG_LPC_ENET) += nxp/
 obj-$(CONFIG_NET_VENDOR_OKI) += oki-semi/
 obj-$(CONFIG_ETHOC) += ethoc.o
-obj-$(CONFIG_NET_PACKET_ENGINE) += packetengines/
+obj-$(CONFIG_NET_VENDOR_PACKET_ENGINES) += packetengines/
 obj-$(CONFIG_NET_VENDOR_PASEMI) += pasemi/
 obj-$(CONFIG_NET_VENDOR_QLOGIC) += qlogic/
 obj-$(CONFIG_NET_VENDOR_QUALCOMM) += qualcomm/
@@ -80,8 +80,7 @@ obj-$(CONFIG_NET_VENDOR_SAMSUNG) += samsung/
 obj-$(CONFIG_NET_VENDOR_SEEQ) += seeq/
 obj-$(CONFIG_NET_VENDOR_SILAN) += silan/
 obj-$(CONFIG_NET_VENDOR_SIS) += sis/
-obj-$(CONFIG_SFC) += sfc/
-obj-$(CONFIG_SFC_FALCON) += sfc/falcon/
+obj-$(CONFIG_NET_VENDOR_SOLARFLARE) += sfc/
 obj-$(CONFIG_NET_VENDOR_SGI) += sgi/
 obj-$(CONFIG_NET_VENDOR_SMSC) += smsc/
 obj-$(CONFIG_NET_VENDOR_SOCIONEXT) += socionext/
diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c
index 3872ab96b80a..097467f44b0d 100644
--- a/drivers/net/ethernet/adaptec/starfire.c
+++ b/drivers/net/ethernet/adaptec/starfire.c
@@ -802,7 +802,7 @@ static int starfire_init_one(struct pci_dev *pdev,
 		int mii_status;
 		for (phy = 0; phy < 32 && phy_idx < PHY_CNT; phy++) {
 			mdio_write(dev, phy, MII_BMCR, BMCR_RESET);
-			mdelay(100);
+			msleep(100);
 			boguscnt = 1000;
 			while (--boguscnt > 0)
 				if ((mdio_read(dev, phy, MII_BMCR) & BMCR_RESET) == 0)
diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c
index 8f71b79b4949..4f11f98347ed 100644
--- a/drivers/net/ethernet/alteon/acenic.c
+++ b/drivers/net/ethernet/alteon/acenic.c
@@ -551,6 +551,7 @@ static int acenic_probe_one(struct pci_dev *pdev,
 			       ap->name);
 			break;
 		}
+		/* Fall through */
 	case PCI_VENDOR_ID_SGI:
 		printk(KERN_INFO "%s: SGI AceNIC ", ap->name);
 		break;
@@ -1933,7 +1934,7 @@ static void ace_rx_int(struct net_device *dev, u32 rxretprd, u32 rxretcsm)
 	while (idx != rxretprd) {
 		struct ring_info *rip;
 		struct sk_buff *skb;
-		struct rx_desc *rxdesc, *retdesc;
+		struct rx_desc *retdesc;
 		u32 skbidx;
 		int bd_flags, desc_type, mapsize;
 		u16 csum;
@@ -1959,19 +1960,16 @@ static void ace_rx_int(struct net_device *dev, u32 rxretprd, u32 rxretcsm)
 		case 0:
 			rip = &ap->skb->rx_std_skbuff[skbidx];
 			mapsize = ACE_STD_BUFSIZE;
-			rxdesc = &ap->rx_std_ring[skbidx];
 			std_count++;
 			break;
 		case BD_FLG_JUMBO:
 			rip = &ap->skb->rx_jumbo_skbuff[skbidx];
 			mapsize = ACE_JUMBO_BUFSIZE;
-			rxdesc = &ap->rx_jumbo_ring[skbidx];
 			atomic_dec(&ap->cur_jumbo_bufs);
 			break;
 		case BD_FLG_MINI:
 			rip = &ap->skb->rx_mini_skbuff[skbidx];
 			mapsize = ACE_MINI_BUFSIZE;
-			rxdesc = &ap->rx_mini_ring[skbidx];
 			mini_count++;
 			break;
 		default:
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index f2af87d70594..c673ac2df65b 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2213,7 +2213,8 @@ static void ena_netpoll(struct net_device *netdev)
 #endif /* CONFIG_NET_POLL_CONTROLLER */
 
 static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    void *accel_priv, select_queue_fallback_t fallback)
+			    struct net_device *sb_dev,
+			    select_queue_fallback_t fallback)
 {
 	u16 qid;
 	/* we suspect that this is good for in--kernel network services that
@@ -2223,7 +2224,7 @@ static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb,
 	if (skb_rx_queue_recorded(skb))
 		qid = skb_get_rx_queue(skb);
 	else
-		qid = fallback(dev, skb);
+		qid = fallback(dev, skb, NULL);
 
 	return qid;
 }
diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index be198cc0b10c..f5ad12c10934 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -2036,22 +2036,22 @@ static int pcnet32_alloc_ring(struct net_device *dev, const char *name)
 	}
 
 	lp->tx_dma_addr = kcalloc(lp->tx_ring_size, sizeof(dma_addr_t),
-				  GFP_ATOMIC);
+				  GFP_KERNEL);
 	if (!lp->tx_dma_addr)
 		return -ENOMEM;
 
 	lp->rx_dma_addr = kcalloc(lp->rx_ring_size, sizeof(dma_addr_t),
-				  GFP_ATOMIC);
+				  GFP_KERNEL);
 	if (!lp->rx_dma_addr)
 		return -ENOMEM;
 
 	lp->tx_skbuff = kcalloc(lp->tx_ring_size, sizeof(struct sk_buff *),
-				GFP_ATOMIC);
+				GFP_KERNEL);
 	if (!lp->tx_skbuff)
 		return -ENOMEM;
 
 	lp->rx_skbuff = kcalloc(lp->rx_ring_size, sizeof(struct sk_buff *),
-				GFP_ATOMIC);
+				GFP_KERNEL);
 	if (!lp->rx_skbuff)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
index cc1e4f820e64..533094233659 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
@@ -289,7 +289,7 @@ static int xgbe_alloc_pages(struct xgbe_prv_data *pdata,
 	struct page *pages = NULL;
 	dma_addr_t pages_dma;
 	gfp_t gfp;
-	int order, ret;
+	int order;
 
 again:
 	order = alloc_order;
@@ -316,10 +316,9 @@ again:
 	/* Map the pages */
 	pages_dma = dma_map_page(pdata->dev, pages, 0,
 				 PAGE_SIZE << order, DMA_FROM_DEVICE);
-	ret = dma_mapping_error(pdata->dev, pages_dma);
-	if (ret) {
+	if (dma_mapping_error(pdata->dev, pages_dma)) {
 		put_page(pages);
-		return ret;
+		return -ENOMEM;
 	}
 
 	pa->pages = pages;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index e107e180e2c8..1e929a1e4ca7 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -119,6 +119,7 @@
 #include <linux/clk.h>
 #include <linux/bitrev.h>
 #include <linux/crc32.h>
+#include <linux/crc32poly.h>
 
 #include "xgbe.h"
 #include "xgbe-common.h"
@@ -887,7 +888,6 @@ static int xgbe_disable_rx_vlan_filtering(struct xgbe_prv_data *pdata)
 
 static u32 xgbe_vid_crc32_le(__le16 vid_le)
 {
-	u32 poly = 0xedb88320;	/* CRCPOLY_LE */
 	u32 crc = ~0;
 	u32 temp = 0;
 	unsigned char *data = (unsigned char *)&vid_le;
@@ -904,7 +904,7 @@ static u32 xgbe_vid_crc32_le(__le16 vid_le)
 		data_byte >>= 1;
 
 		if (temp)
-			crc ^= poly;
+			crc ^= CRC32_POLY_LE;
 	}
 
 	return crc;
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
index 3188f553da35..078a04dc1182 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
@@ -836,19 +836,19 @@ static void xgene_enet_adjust_link(struct net_device *ndev)
 #ifdef CONFIG_ACPI
 static struct acpi_device *acpi_phy_find_device(struct device *dev)
 {
-	struct acpi_reference_args args;
+	struct fwnode_reference_args args;
 	struct fwnode_handle *fw_node;
 	int status;
 
 	fw_node = acpi_fwnode_handle(ACPI_COMPANION(dev));
 	status = acpi_node_get_property_reference(fw_node, "phy-handle", 0,
 						  &args);
-	if (ACPI_FAILURE(status)) {
+	if (ACPI_FAILURE(status) || !is_acpi_device_node(args.fwnode)) {
 		dev_dbg(dev, "No matching phy in ACPI table\n");
 		return NULL;
 	}
 
-	return args.adev;
+	return to_acpi_device_node(args.fwnode);
 }
 #endif
 
diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c
index 5a655d289dd5..024998d6d8c6 100644
--- a/drivers/net/ethernet/apple/bmac.c
+++ b/drivers/net/ethernet/apple/bmac.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/crc32.h>
+#include <linux/crc32poly.h>
 #include <linux/bitrev.h>
 #include <linux/ethtool.h>
 #include <linux/slab.h>
@@ -37,11 +38,6 @@
 #define trunc_page(x)	((void *)(((unsigned long)(x)) & ~((unsigned long)(PAGE_SIZE - 1))))
 #define round_page(x)	trunc_page(((unsigned long)(x)) + ((unsigned long)(PAGE_SIZE - 1)))
 
-/*
- * CRC polynomial - used in working out multicast filter bits.
- */
-#define ENET_CRCPOLY 0x04c11db7
-
 /* switch to use multicast code lifted from sunhme driver */
 #define SUNHME_MULTICAST
 
@@ -838,7 +834,7 @@ crc416(unsigned int curval, unsigned short nxtval)
 		next = next >> 1;
 
 		/* do the XOR */
-		if (high_crc_set ^ low_data_set) cur = cur ^ ENET_CRCPOLY;
+		if (high_crc_set ^ low_data_set) cur = cur ^ CRC32_POLY_BE;
 	}
 	return cur;
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index f2d8063a2cef..08c9fa6ca71f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -11,6 +11,7 @@
 
 #include "aq_ethtool.h"
 #include "aq_nic.h"
+#include "aq_vec.h"
 
 static void aq_ethtool_get_regs(struct net_device *ndev,
 				struct ethtool_regs *regs, void *p)
@@ -284,6 +285,117 @@ static int aq_ethtool_set_coalesce(struct net_device *ndev,
 	return aq_nic_update_interrupt_moderation_settings(aq_nic);
 }
 
+static int aq_ethtool_nway_reset(struct net_device *ndev)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+
+	if (unlikely(!aq_nic->aq_fw_ops->renegotiate))
+		return -EOPNOTSUPP;
+
+	if (netif_running(ndev))
+		return aq_nic->aq_fw_ops->renegotiate(aq_nic->aq_hw);
+
+	return 0;
+}
+
+static void aq_ethtool_get_pauseparam(struct net_device *ndev,
+				      struct ethtool_pauseparam *pause)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+
+	pause->autoneg = 0;
+
+	if (aq_nic->aq_hw->aq_nic_cfg->flow_control & AQ_NIC_FC_RX)
+		pause->rx_pause = 1;
+	if (aq_nic->aq_hw->aq_nic_cfg->flow_control & AQ_NIC_FC_TX)
+		pause->tx_pause = 1;
+}
+
+static int aq_ethtool_set_pauseparam(struct net_device *ndev,
+				     struct ethtool_pauseparam *pause)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+	int err = 0;
+
+	if (!aq_nic->aq_fw_ops->set_flow_control)
+		return -EOPNOTSUPP;
+
+	if (pause->autoneg == AUTONEG_ENABLE)
+		return -EOPNOTSUPP;
+
+	if (pause->rx_pause)
+		aq_nic->aq_hw->aq_nic_cfg->flow_control |= AQ_NIC_FC_RX;
+	else
+		aq_nic->aq_hw->aq_nic_cfg->flow_control &= ~AQ_NIC_FC_RX;
+
+	if (pause->tx_pause)
+		aq_nic->aq_hw->aq_nic_cfg->flow_control |= AQ_NIC_FC_TX;
+	else
+		aq_nic->aq_hw->aq_nic_cfg->flow_control &= ~AQ_NIC_FC_TX;
+
+	err = aq_nic->aq_fw_ops->set_flow_control(aq_nic->aq_hw);
+
+	return err;
+}
+
+static void aq_get_ringparam(struct net_device *ndev,
+			     struct ethtool_ringparam *ring)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+	struct aq_nic_cfg_s *aq_nic_cfg = aq_nic_get_cfg(aq_nic);
+
+	ring->rx_pending = aq_nic_cfg->rxds;
+	ring->tx_pending = aq_nic_cfg->txds;
+
+	ring->rx_max_pending = aq_nic_cfg->aq_hw_caps->rxds_max;
+	ring->tx_max_pending = aq_nic_cfg->aq_hw_caps->txds_max;
+}
+
+static int aq_set_ringparam(struct net_device *ndev,
+			    struct ethtool_ringparam *ring)
+{
+	int err = 0;
+	bool ndev_running = false;
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+	struct aq_nic_cfg_s *aq_nic_cfg = aq_nic_get_cfg(aq_nic);
+	const struct aq_hw_caps_s *hw_caps = aq_nic_cfg->aq_hw_caps;
+
+	if (ring->rx_mini_pending || ring->rx_jumbo_pending) {
+		err = -EOPNOTSUPP;
+		goto err_exit;
+	}
+
+	if (netif_running(ndev)) {
+		ndev_running = true;
+		dev_close(ndev);
+	}
+
+	aq_nic_free_vectors(aq_nic);
+
+	aq_nic_cfg->rxds = max(ring->rx_pending, hw_caps->rxds_min);
+	aq_nic_cfg->rxds = min(aq_nic_cfg->rxds, hw_caps->rxds_max);
+	aq_nic_cfg->rxds = ALIGN(aq_nic_cfg->rxds, AQ_HW_RXD_MULTIPLE);
+
+	aq_nic_cfg->txds = max(ring->tx_pending, hw_caps->txds_min);
+	aq_nic_cfg->txds = min(aq_nic_cfg->txds, hw_caps->txds_max);
+	aq_nic_cfg->txds = ALIGN(aq_nic_cfg->txds, AQ_HW_TXD_MULTIPLE);
+
+	for (aq_nic->aq_vecs = 0; aq_nic->aq_vecs < aq_nic_cfg->vecs;
+	     aq_nic->aq_vecs++) {
+		aq_nic->aq_vec[aq_nic->aq_vecs] =
+		    aq_vec_alloc(aq_nic, aq_nic->aq_vecs, aq_nic_cfg);
+		if (unlikely(!aq_nic->aq_vec[aq_nic->aq_vecs])) {
+			err = -ENOMEM;
+			goto err_exit;
+		}
+	}
+	if (ndev_running)
+		err = dev_open(ndev);
+
+err_exit:
+	return err;
+}
+
 const struct ethtool_ops aq_ethtool_ops = {
 	.get_link            = aq_ethtool_get_link,
 	.get_regs_len        = aq_ethtool_get_regs_len,
@@ -291,6 +403,11 @@ const struct ethtool_ops aq_ethtool_ops = {
 	.get_drvinfo         = aq_ethtool_get_drvinfo,
 	.get_strings         = aq_ethtool_get_strings,
 	.get_rxfh_indir_size = aq_ethtool_get_rss_indir_size,
+	.nway_reset          = aq_ethtool_nway_reset,
+	.get_ringparam       = aq_get_ringparam,
+	.set_ringparam       = aq_set_ringparam,
+	.get_pauseparam      = aq_ethtool_get_pauseparam,
+	.set_pauseparam      = aq_ethtool_set_pauseparam,
 	.get_rxfh_key_size   = aq_ethtool_get_rss_key_size,
 	.get_rxfh            = aq_ethtool_get_rss,
 	.get_rxnfc           = aq_ethtool_get_rxnfc,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index 2c6ebd91a9f2..5c00671f248d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -24,8 +24,10 @@ struct aq_hw_caps_s {
 	u64 link_speed_msk;
 	unsigned int hw_priv_flags;
 	u32 media_type;
-	u32 rxds;
-	u32 txds;
+	u32 rxds_max;
+	u32 txds_max;
+	u32 rxds_min;
+	u32 txds_min;
 	u32 txhwb_alignment;
 	u32 irq_mask;
 	u32 vecs;
@@ -98,6 +100,9 @@ struct aq_stats_s {
 #define AQ_HW_MEDIA_TYPE_TP    1U
 #define AQ_HW_MEDIA_TYPE_FIBRE 2U
 
+#define AQ_HW_TXD_MULTIPLE 8U
+#define AQ_HW_RXD_MULTIPLE 8U
+
 #define AQ_HW_MULTICAST_ADDRESS_MAX     32U
 
 struct aq_hw_s {
@@ -199,25 +204,30 @@ struct aq_hw_ops {
 
 	int (*hw_get_fw_version)(struct aq_hw_s *self, u32 *fw_version);
 
-	int (*hw_deinit)(struct aq_hw_s *self);
-
 	int (*hw_set_power)(struct aq_hw_s *self, unsigned int power_state);
 };
 
 struct aq_fw_ops {
 	int (*init)(struct aq_hw_s *self);
 
+	int (*deinit)(struct aq_hw_s *self);
+
 	int (*reset)(struct aq_hw_s *self);
 
+	int (*renegotiate)(struct aq_hw_s *self);
+
 	int (*get_mac_permanent)(struct aq_hw_s *self, u8 *mac);
 
 	int (*set_link_speed)(struct aq_hw_s *self, u32 speed);
 
-	int (*set_state)(struct aq_hw_s *self, enum hal_atl_utils_fw_state_e state);
+	int (*set_state)(struct aq_hw_s *self,
+			 enum hal_atl_utils_fw_state_e state);
 
 	int (*update_link_status)(struct aq_hw_s *self);
 
 	int (*update_stats)(struct aq_hw_s *self);
+
+	int (*set_flow_control)(struct aq_hw_s *self);
 };
 
 #endif /* AQ_HW_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 7a22d0257e04..26dc6782b475 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -89,8 +89,8 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 	aq_nic_rss_init(self, cfg->num_rss_queues);
 
 	/*descriptors */
-	cfg->rxds = min(cfg->aq_hw_caps->rxds, AQ_CFG_RXDS_DEF);
-	cfg->txds = min(cfg->aq_hw_caps->txds, AQ_CFG_TXDS_DEF);
+	cfg->rxds = min(cfg->aq_hw_caps->rxds_max, AQ_CFG_RXDS_DEF);
+	cfg->txds = min(cfg->aq_hw_caps->txds_max, AQ_CFG_TXDS_DEF);
 
 	/*rss rings */
 	cfg->vecs = min(cfg->aq_hw_caps->vecs, AQ_CFG_VECS_DEF);
@@ -768,10 +768,14 @@ void aq_nic_get_link_ksettings(struct aq_nic_s *self,
 		ethtool_link_ksettings_add_link_mode(cmd, advertising,
 						     100baseT_Full);
 
-	if (self->aq_nic_cfg.flow_control)
+	if (self->aq_nic_cfg.flow_control & AQ_NIC_FC_RX)
 		ethtool_link_ksettings_add_link_mode(cmd, advertising,
 						     Pause);
 
+	if (self->aq_nic_cfg.flow_control & AQ_NIC_FC_TX)
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Asym_Pause);
+
 	if (self->aq_nic_cfg.aq_hw_caps->media_type == AQ_HW_MEDIA_TYPE_FIBRE)
 		ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE);
 	else
@@ -886,7 +890,7 @@ void aq_nic_deinit(struct aq_nic_s *self)
 		aq_vec_deinit(aq_vec);
 
 	if (self->power_state == AQ_HW_POWER_STATE_D0) {
-		(void)self->aq_hw_ops->hw_deinit(self->aq_hw);
+		(void)self->aq_fw_ops->deinit(self->aq_hw);
 	} else {
 		(void)self->aq_hw_ops->hw_set_power(self->aq_hw,
 						   self->power_state);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index 8cc6abadc03b..97addfa6f895 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -19,29 +19,31 @@
 #include "hw_atl_a0_internal.h"
 
 #define DEFAULT_A0_BOARD_BASIC_CAPABILITIES \
-	.is_64_dma = true, \
-	.msix_irqs = 4U, \
-	.irq_mask = ~0U, \
-	.vecs = HW_ATL_A0_RSS_MAX, \
-	.tcs = HW_ATL_A0_TC_MAX, \
-	.rxd_alignment = 1U, \
-	.rxd_size = HW_ATL_A0_RXD_SIZE, \
-	.rxds = 248U, \
-	.txd_alignment = 1U, \
-	.txd_size = HW_ATL_A0_TXD_SIZE, \
-	.txds = 8U * 1024U, \
-	.txhwb_alignment = 4096U, \
-	.tx_rings = HW_ATL_A0_TX_RINGS, \
-	.rx_rings = HW_ATL_A0_RX_RINGS, \
-	.hw_features = NETIF_F_HW_CSUM | \
-			NETIF_F_RXHASH | \
-			NETIF_F_RXCSUM | \
-			NETIF_F_SG | \
-			NETIF_F_TSO, \
+	.is_64_dma = true,		  \
+	.msix_irqs = 4U,		  \
+	.irq_mask = ~0U,		  \
+	.vecs = HW_ATL_A0_RSS_MAX,	  \
+	.tcs = HW_ATL_A0_TC_MAX,	  \
+	.rxd_alignment = 1U,		  \
+	.rxd_size = HW_ATL_A0_RXD_SIZE,   \
+	.rxds_max = HW_ATL_A0_MAX_RXD,    \
+	.rxds_min = HW_ATL_A0_MIN_RXD,    \
+	.txd_alignment = 1U,		  \
+	.txd_size = HW_ATL_A0_TXD_SIZE,   \
+	.txds_max = HW_ATL_A0_MAX_TXD,    \
+	.txds_min = HW_ATL_A0_MIN_RXD,    \
+	.txhwb_alignment = 4096U,	  \
+	.tx_rings = HW_ATL_A0_TX_RINGS,   \
+	.rx_rings = HW_ATL_A0_RX_RINGS,   \
+	.hw_features = NETIF_F_HW_CSUM |  \
+			NETIF_F_RXHASH |  \
+			NETIF_F_RXCSUM |  \
+			NETIF_F_SG |	  \
+			NETIF_F_TSO,	  \
 	.hw_priv_flags = IFF_UNICAST_FLT, \
-	.flow_control = true, \
-	.mtu = HW_ATL_A0_MTU_JUMBO, \
-	.mac_regs_count = 88, \
+	.flow_control = true,		  \
+	.mtu = HW_ATL_A0_MTU_JUMBO,       \
+	.mac_regs_count = 88,		  \
 	.hw_alive_check_addr = 0x10U
 
 const struct aq_hw_caps_s hw_atl_a0_caps_aqc100 = {
@@ -875,7 +877,6 @@ static int hw_atl_a0_hw_ring_rx_stop(struct aq_hw_s *self,
 const struct aq_hw_ops hw_atl_ops_a0 = {
 	.hw_set_mac_address   = hw_atl_a0_hw_mac_addr_set,
 	.hw_init              = hw_atl_a0_hw_init,
-	.hw_deinit            = hw_atl_utils_hw_deinit,
 	.hw_set_power         = hw_atl_utils_hw_set_power,
 	.hw_reset             = hw_atl_a0_hw_reset,
 	.hw_start             = hw_atl_a0_hw_start,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h
index 1d8855558d74..3c94cff57876 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h
@@ -88,4 +88,12 @@
 
 #define HW_ATL_A0_FW_VER_EXPECTED 0x01050006U
 
+#define HW_ATL_A0_MIN_RXD \
+	(ALIGN(AQ_CFG_SKB_FRAGS_MAX + 1U, AQ_HW_RXD_MULTIPLE))
+#define HW_ATL_A0_MIN_TXD \
+	(ALIGN(AQ_CFG_SKB_FRAGS_MAX + 1U, AQ_HW_TXD_MULTIPLE))
+
+#define HW_ATL_A0_MAX_RXD 8184U
+#define HW_ATL_A0_MAX_TXD 8184U
+
 #endif /* HW_ATL_A0_INTERNAL_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 3bdab972420b..1d44a386e7d3 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -20,30 +20,32 @@
 #include "hw_atl_llh_internal.h"
 
 #define DEFAULT_B0_BOARD_BASIC_CAPABILITIES \
-	.is_64_dma = true,	\
-	.msix_irqs = 4U,	\
-	.irq_mask = ~0U,	\
-	.vecs = HW_ATL_B0_RSS_MAX,	\
-	.tcs = HW_ATL_B0_TC_MAX,	\
-	.rxd_alignment = 1U,		\
-	.rxd_size = HW_ATL_B0_RXD_SIZE, \
-	.rxds = 4U * 1024U,		\
-	.txd_alignment = 1U,		\
-	.txd_size = HW_ATL_B0_TXD_SIZE, \
-	.txds = 8U * 1024U,		\
-	.txhwb_alignment = 4096U,	\
-	.tx_rings = HW_ATL_B0_TX_RINGS, \
-	.rx_rings = HW_ATL_B0_RX_RINGS, \
-	.hw_features = NETIF_F_HW_CSUM | \
-			NETIF_F_RXCSUM | \
-			NETIF_F_RXHASH | \
-			NETIF_F_SG |  \
-			NETIF_F_TSO | \
-			NETIF_F_LRO,  \
-	.hw_priv_flags = IFF_UNICAST_FLT,   \
-	.flow_control = true,		\
-	.mtu = HW_ATL_B0_MTU_JUMBO,	\
-	.mac_regs_count = 88,		\
+	.is_64_dma = true,		  \
+	.msix_irqs = 4U,		  \
+	.irq_mask = ~0U,		  \
+	.vecs = HW_ATL_B0_RSS_MAX,	  \
+	.tcs = HW_ATL_B0_TC_MAX,	  \
+	.rxd_alignment = 1U,		  \
+	.rxd_size = HW_ATL_B0_RXD_SIZE,   \
+	.rxds_max = HW_ATL_B0_MAX_RXD,    \
+	.rxds_min = HW_ATL_B0_MIN_RXD,    \
+	.txd_alignment = 1U,		  \
+	.txd_size = HW_ATL_B0_TXD_SIZE,   \
+	.txds_max = HW_ATL_B0_MAX_TXD,    \
+	.txds_min = HW_ATL_B0_MIN_TXD,    \
+	.txhwb_alignment = 4096U,	  \
+	.tx_rings = HW_ATL_B0_TX_RINGS,   \
+	.rx_rings = HW_ATL_B0_RX_RINGS,   \
+	.hw_features = NETIF_F_HW_CSUM |  \
+			NETIF_F_RXCSUM |  \
+			NETIF_F_RXHASH |  \
+			NETIF_F_SG |      \
+			NETIF_F_TSO |     \
+			NETIF_F_LRO,      \
+	.hw_priv_flags = IFF_UNICAST_FLT, \
+	.flow_control = true,		  \
+	.mtu = HW_ATL_B0_MTU_JUMBO,	  \
+	.mac_regs_count = 88,		  \
 	.hw_alive_check_addr = 0x10U
 
 const struct aq_hw_caps_s hw_atl_b0_caps_aqc100 = {
@@ -933,7 +935,6 @@ static int hw_atl_b0_hw_ring_rx_stop(struct aq_hw_s *self,
 const struct aq_hw_ops hw_atl_ops_b0 = {
 	.hw_set_mac_address   = hw_atl_b0_hw_mac_addr_set,
 	.hw_init              = hw_atl_b0_hw_init,
-	.hw_deinit            = hw_atl_utils_hw_deinit,
 	.hw_set_power         = hw_atl_utils_hw_set_power,
 	.hw_reset             = hw_atl_b0_hw_reset,
 	.hw_start             = hw_atl_b0_hw_start,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
index 405d1455c222..28568f5fa74b 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
@@ -142,6 +142,14 @@
 #define HW_ATL_INTR_MODER_MAX  0x1FF
 #define HW_ATL_INTR_MODER_MIN  0xFF
 
+#define HW_ATL_B0_MIN_RXD \
+	(ALIGN(AQ_CFG_SKB_FRAGS_MAX + 1U, AQ_HW_RXD_MULTIPLE))
+#define HW_ATL_B0_MIN_TXD \
+	(ALIGN(AQ_CFG_SKB_FRAGS_MAX + 1U, AQ_HW_TXD_MULTIPLE))
+
+#define HW_ATL_B0_MAX_RXD 8184U
+#define HW_ATL_B0_MAX_TXD 8184U
+
 /* HW layer capabilities */
 
 #endif /* HW_ATL_B0_INTERNAL_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index e652d86b87d4..c965e65d07db 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -30,10 +30,11 @@
 #define HW_ATL_MPI_CONTROL_ADR  0x0368U
 #define HW_ATL_MPI_STATE_ADR    0x036CU
 
-#define HW_ATL_MPI_STATE_MSK    0x00FFU
-#define HW_ATL_MPI_STATE_SHIFT  0U
-#define HW_ATL_MPI_SPEED_MSK    0xFFFF0000U
-#define HW_ATL_MPI_SPEED_SHIFT  16U
+#define HW_ATL_MPI_STATE_MSK      0x00FFU
+#define HW_ATL_MPI_STATE_SHIFT    0U
+#define HW_ATL_MPI_SPEED_MSK      0x00FF0000U
+#define HW_ATL_MPI_SPEED_SHIFT    16U
+#define HW_ATL_MPI_DIRTY_WAKE_MSK 0x02000000U
 
 #define HW_ATL_MPI_DAISY_CHAIN_STATUS	0x704
 #define HW_ATL_MPI_BOOT_EXIT_CODE	0x388
@@ -525,19 +526,20 @@ static int hw_atl_utils_mpi_set_speed(struct aq_hw_s *self, u32 speed)
 {
 	u32 val = aq_hw_read_reg(self, HW_ATL_MPI_CONTROL_ADR);
 
-	val = (val & HW_ATL_MPI_STATE_MSK) | (speed << HW_ATL_MPI_SPEED_SHIFT);
+	val = val & ~HW_ATL_MPI_SPEED_MSK;
+	val |= speed << HW_ATL_MPI_SPEED_SHIFT;
 	aq_hw_write_reg(self, HW_ATL_MPI_CONTROL_ADR, val);
 
 	return 0;
 }
 
-void hw_atl_utils_mpi_set(struct aq_hw_s *self,
-			  enum hal_atl_utils_fw_state_e state,
-			  u32 speed)
+static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self,
+				      enum hal_atl_utils_fw_state_e state)
 {
 	int err = 0;
 	u32 transaction_id = 0;
 	struct hw_aq_atl_utils_mbox_header mbox;
+	u32 val = aq_hw_read_reg(self, HW_ATL_MPI_CONTROL_ADR);
 
 	if (state == MPI_RESET) {
 		hw_atl_utils_mpi_read_mbox(self, &mbox);
@@ -551,21 +553,21 @@ void hw_atl_utils_mpi_set(struct aq_hw_s *self,
 		if (err < 0)
 			goto err_exit;
 	}
+	/* On interface DEINIT we disable DW (raise bit)
+	 * Otherwise enable DW (clear bit)
+	 */
+	if (state == MPI_DEINIT || state == MPI_POWER)
+		val |= HW_ATL_MPI_DIRTY_WAKE_MSK;
+	else
+		val &= ~HW_ATL_MPI_DIRTY_WAKE_MSK;
 
-	aq_hw_write_reg(self, HW_ATL_MPI_CONTROL_ADR,
-			(speed << HW_ATL_MPI_SPEED_SHIFT) | state);
-
-err_exit:;
-}
-
-static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self,
-				      enum hal_atl_utils_fw_state_e state)
-{
-	u32 val = aq_hw_read_reg(self, HW_ATL_MPI_CONTROL_ADR);
+	/* Set new state bits */
+	val = val & ~HW_ATL_MPI_STATE_MSK;
+	val |= state & HW_ATL_MPI_STATE_MSK;
 
-	val = state | (val & HW_ATL_MPI_SPEED_MSK);
 	aq_hw_write_reg(self, HW_ATL_MPI_CONTROL_ADR, val);
-	return 0;
+err_exit:
+	return err;
 }
 
 int hw_atl_utils_mpi_get_link_status(struct aq_hw_s *self)
@@ -721,16 +723,18 @@ void hw_atl_utils_hw_chip_features_init(struct aq_hw_s *self, u32 *p)
 	*p = chip_features;
 }
 
-int hw_atl_utils_hw_deinit(struct aq_hw_s *self)
+static int hw_atl_fw1x_deinit(struct aq_hw_s *self)
 {
-	hw_atl_utils_mpi_set(self, MPI_DEINIT, 0x0U);
+	hw_atl_utils_mpi_set_speed(self, 0);
+	hw_atl_utils_mpi_set_state(self, MPI_DEINIT);
 	return 0;
 }
 
 int hw_atl_utils_hw_set_power(struct aq_hw_s *self,
 			      unsigned int power_state)
 {
-	hw_atl_utils_mpi_set(self, MPI_POWER, 0x0U);
+	hw_atl_utils_mpi_set_speed(self, 0);
+	hw_atl_utils_mpi_set_state(self, MPI_POWER);
 	return 0;
 }
 
@@ -823,10 +827,12 @@ int hw_atl_utils_get_fw_version(struct aq_hw_s *self, u32 *fw_version)
 
 const struct aq_fw_ops aq_fw_1x_ops = {
 	.init = hw_atl_utils_mpi_create,
+	.deinit = hw_atl_fw1x_deinit,
 	.reset = NULL,
 	.get_mac_permanent = hw_atl_utils_get_mac_permanent,
 	.set_link_speed = hw_atl_utils_mpi_set_speed,
 	.set_state = hw_atl_utils_mpi_set_state,
 	.update_link_status = hw_atl_utils_mpi_get_link_status,
 	.update_stats = hw_atl_utils_update_stats,
+	.set_flow_control = NULL,
 };
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
index cd8f18f39c61..b875590efcbd 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
@@ -239,6 +239,41 @@ enum hw_atl_fw2x_caps_hi {
 	CAPS_HI_TRANSACTION_ID,
 };
 
+enum hw_atl_fw2x_ctrl {
+	CTRL_RESERVED1 = 0x00,
+	CTRL_RESERVED2,
+	CTRL_RESERVED3,
+	CTRL_PAUSE,
+	CTRL_ASYMMETRIC_PAUSE,
+	CTRL_RESERVED4,
+	CTRL_RESERVED5,
+	CTRL_RESERVED6,
+	CTRL_1GBASET_FD_EEE,
+	CTRL_2P5GBASET_FD_EEE,
+	CTRL_5GBASET_FD_EEE,
+	CTRL_10GBASET_FD_EEE,
+	CTRL_THERMAL_SHUTDOWN,
+	CTRL_PHY_LOGS,
+	CTRL_EEE_AUTO_DISABLE,
+	CTRL_PFC,
+	CTRL_WAKE_ON_LINK,
+	CTRL_CABLE_DIAG,
+	CTRL_TEMPERATURE,
+	CTRL_DOWNSHIFT,
+	CTRL_PTP_AVB,
+	CTRL_RESERVED7,
+	CTRL_LINK_DROP,
+	CTRL_SLEEP_PROXY,
+	CTRL_WOL,
+	CTRL_MAC_STOP,
+	CTRL_EXT_LOOPBACK,
+	CTRL_INT_LOOPBACK,
+	CTRL_RESERVED8,
+	CTRL_WOL_TIMER,
+	CTRL_STATISTICS,
+	CTRL_FORCE_RECONNECT,
+};
+
 struct aq_hw_s;
 struct aq_fw_ops;
 struct aq_hw_caps_s;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
index 39cd3a27fe77..e37943760a58 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
@@ -28,6 +28,10 @@
 #define HW_ATL_FW2X_MPI_STATE_ADDR	0x370
 #define HW_ATL_FW2X_MPI_STATE2_ADDR	0x374
 
+static int aq_fw2x_set_link_speed(struct aq_hw_s *self, u32 speed);
+static int aq_fw2x_set_state(struct aq_hw_s *self,
+			     enum hal_atl_utils_fw_state_e state);
+
 static int aq_fw2x_init(struct aq_hw_s *self)
 {
 	int err = 0;
@@ -39,6 +43,16 @@ static int aq_fw2x_init(struct aq_hw_s *self)
 	return err;
 }
 
+static int aq_fw2x_deinit(struct aq_hw_s *self)
+{
+	int err = aq_fw2x_set_link_speed(self, 0);
+
+	if (!err)
+		err = aq_fw2x_set_state(self, MPI_DEINIT);
+
+	return err;
+}
+
 static enum hw_atl_fw2x_rate link_speed_mask_2fw2x_ratemask(u32 speed)
 {
 	enum hw_atl_fw2x_rate rate = 0;
@@ -73,10 +87,38 @@ static int aq_fw2x_set_link_speed(struct aq_hw_s *self, u32 speed)
 	return 0;
 }
 
+static void aq_fw2x_set_mpi_flow_control(struct aq_hw_s *self, u32 *mpi_state)
+{
+	if (self->aq_nic_cfg->flow_control & AQ_NIC_FC_RX)
+		*mpi_state |= BIT(CAPS_HI_PAUSE);
+	else
+		*mpi_state &= ~BIT(CAPS_HI_PAUSE);
+
+	if (self->aq_nic_cfg->flow_control & AQ_NIC_FC_TX)
+		*mpi_state |= BIT(CAPS_HI_ASYMMETRIC_PAUSE);
+	else
+		*mpi_state &= ~BIT(CAPS_HI_ASYMMETRIC_PAUSE);
+}
+
 static int aq_fw2x_set_state(struct aq_hw_s *self,
 			     enum hal_atl_utils_fw_state_e state)
 {
-	/* No explicit state in 2x fw */
+	u32 mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR);
+
+	switch (state) {
+	case MPI_INIT:
+		mpi_state &= ~BIT(CAPS_HI_LINK_DROP);
+		aq_fw2x_set_mpi_flow_control(self, &mpi_state);
+		break;
+	case MPI_DEINIT:
+		mpi_state |= BIT(CAPS_HI_LINK_DROP);
+		break;
+	case MPI_RESET:
+	case MPI_POWER:
+		/* No actions */
+		break;
+	}
+	aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_state);
 	return 0;
 }
 
@@ -173,12 +215,37 @@ static int aq_fw2x_update_stats(struct aq_hw_s *self)
 	return hw_atl_utils_update_stats(self);
 }
 
+static int aq_fw2x_renegotiate(struct aq_hw_s *self)
+{
+	u32 mpi_opts = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR);
+
+	mpi_opts |= BIT(CTRL_FORCE_RECONNECT);
+
+	aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts);
+
+	return 0;
+}
+
+static int aq_fw2x_set_flow_control(struct aq_hw_s *self)
+{
+	u32 mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR);
+
+	aq_fw2x_set_mpi_flow_control(self, &mpi_state);
+
+	aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_state);
+
+	return 0;
+}
+
 const struct aq_fw_ops aq_fw_2x_ops = {
 	.init = aq_fw2x_init,
+	.deinit = aq_fw2x_deinit,
 	.reset = NULL,
+	.renegotiate = aq_fw2x_renegotiate,
 	.get_mac_permanent = aq_fw2x_get_mac_permanent,
 	.set_link_speed = aq_fw2x_set_link_speed,
 	.set_state = aq_fw2x_set_state,
 	.update_link_status = aq_fw2x_update_link_status,
 	.update_stats = aq_fw2x_update_stats,
+	.set_flow_control   = aq_fw2x_set_flow_control,
 };
diff --git a/drivers/net/ethernet/aquantia/atlantic/ver.h b/drivers/net/ethernet/aquantia/atlantic/ver.h
index a445de6837a6..94efc6477bdc 100644
--- a/drivers/net/ethernet/aquantia/atlantic/ver.h
+++ b/drivers/net/ethernet/aquantia/atlantic/ver.h
@@ -12,8 +12,8 @@
 
 #define NIC_MAJOR_DRIVER_VERSION           2
 #define NIC_MINOR_DRIVER_VERSION           0
-#define NIC_BUILD_DRIVER_VERSION           2
-#define NIC_REVISION_DRIVER_VERSION        1
+#define NIC_BUILD_DRIVER_VERSION           3
+#define NIC_REVISION_DRIVER_VERSION        0
 
 #define AQ_CFG_DRV_VERSION_SUFFIX "-kern"
 
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 5e5022fa1d04..6d3221134927 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1279,7 +1279,6 @@ static void alx_check_link(struct alx_priv *alx)
 	struct alx_hw *hw = &alx->hw;
 	unsigned long flags;
 	int old_speed;
-	u8 old_duplex;
 	int err;
 
 	/* clear PHY internal interrupt status, otherwise the main
@@ -1288,7 +1287,6 @@ static void alx_check_link(struct alx_priv *alx)
 	alx_clear_phy_intr(hw);
 
 	old_speed = hw->link_speed;
-	old_duplex = hw->duplex;
 	err = alx_read_phy_link(hw);
 	if (err < 0)
 		goto reset;
diff --git a/drivers/net/ethernet/aurora/Kconfig b/drivers/net/ethernet/aurora/Kconfig
index 8ba7f8ff3434..392f564d8fd4 100644
--- a/drivers/net/ethernet/aurora/Kconfig
+++ b/drivers/net/ethernet/aurora/Kconfig
@@ -1,5 +1,6 @@
 config NET_VENDOR_AURORA
 	bool "Aurora VLSI devices"
+	default y
 	help
 	  If you have a network (Ethernet) device belonging to this class,
 	  say Y.
diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
index e94159507847..c8d1f8fa4713 100644
--- a/drivers/net/ethernet/aurora/nb8800.c
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -304,12 +304,10 @@ static int nb8800_poll(struct napi_struct *napi, int budget)
 
 again:
 	do {
-		struct nb8800_rx_buf *rxb;
 		unsigned int len;
 
 		next = (last + 1) % RX_DESC_COUNT;
 
-		rxb = &priv->rx_bufs[next];
 		rxd = &priv->rx_descs[next];
 
 		if (!rxd->report)
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 4c3bfde6e8de..c1d3ee9baf7e 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -61,7 +61,7 @@ config BCM63XX_ENET
 
 config BCMGENET
 	tristate "Broadcom GENET internal MAC support"
-	depends on OF && HAS_IOMEM
+	depends on HAS_IOMEM
 	select MII
 	select PHYLIB
 	select FIXED_PHY
@@ -181,7 +181,7 @@ config BGMAC_PLATFORM
 
 config SYSTEMPORT
 	tristate "Broadcom SYSTEMPORT internal MAC support"
-	depends on OF
+	depends on HAS_IOMEM
 	depends on NET_DSA || !NET_DSA
 	select MII
 	select PHYLIB
@@ -230,4 +230,12 @@ config BNXT_DCB
 
 	  If unsure, say N.
 
+config BNXT_HWMON
+	bool "Broadcom NetXtreme-C/E HWMON support"
+	default y
+	depends on BNXT && HWMON && !(BNXT=y && HWMON=m)
+	---help---
+	  Say Y if you want to expose the thermal sensor data on NetXtreme-C/E
+	  devices, via the hwmon sysfs interface.
+
 endif # NET_VENDOR_BROADCOM
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index a1f60f89e059..147045757b10 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -521,7 +521,7 @@ static void bcm_sysport_get_wol(struct net_device *dev,
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	u32 reg;
 
-	wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE;
+	wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER;
 	wol->wolopts = priv->wolopts;
 
 	if (!(priv->wolopts & WAKE_MAGICSECURE))
@@ -539,7 +539,7 @@ static int bcm_sysport_set_wol(struct net_device *dev,
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	struct device *kdev = &priv->pdev->dev;
-	u32 supported = WAKE_MAGIC | WAKE_MAGICSECURE;
+	u32 supported = WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER;
 
 	if (!device_can_wakeup(kdev))
 		return -ENOTSUPP;
@@ -1041,17 +1041,45 @@ static int bcm_sysport_poll(struct napi_struct *napi, int budget)
 	return work_done;
 }
 
+static void mpd_enable_set(struct bcm_sysport_priv *priv, bool enable)
+{
+	u32 reg, bit;
+
+	reg = umac_readl(priv, UMAC_MPD_CTRL);
+	if (enable)
+		reg |= MPD_EN;
+	else
+		reg &= ~MPD_EN;
+	umac_writel(priv, reg, UMAC_MPD_CTRL);
+
+	if (priv->is_lite)
+		bit = RBUF_ACPI_EN_LITE;
+	else
+		bit = RBUF_ACPI_EN;
+
+	reg = rbuf_readl(priv, RBUF_CONTROL);
+	if (enable)
+		reg |= bit;
+	else
+		reg &= ~bit;
+	rbuf_writel(priv, reg, RBUF_CONTROL);
+}
+
 static void bcm_sysport_resume_from_wol(struct bcm_sysport_priv *priv)
 {
 	u32 reg;
 
 	/* Stop monitoring MPD interrupt */
-	intrl2_0_mask_set(priv, INTRL2_0_MPD);
+	intrl2_0_mask_set(priv, INTRL2_0_MPD | INTRL2_0_BRCM_MATCH_TAG);
+
+	/* Disable RXCHK, active filters and Broadcom tag matching */
+	reg = rxchk_readl(priv, RXCHK_CONTROL);
+	reg &= ~(RXCHK_BRCM_TAG_MATCH_MASK <<
+		 RXCHK_BRCM_TAG_MATCH_SHIFT | RXCHK_EN | RXCHK_BRCM_TAG_EN);
+	rxchk_writel(priv, reg, RXCHK_CONTROL);
 
 	/* Clear the MagicPacket detection logic */
-	reg = umac_readl(priv, UMAC_MPD_CTRL);
-	reg &= ~MPD_EN;
-	umac_writel(priv, reg, UMAC_MPD_CTRL);
+	mpd_enable_set(priv, false);
 
 	netif_dbg(priv, wol, priv->netdev, "resumed from WOL\n");
 }
@@ -1077,6 +1105,7 @@ static irqreturn_t bcm_sysport_rx_isr(int irq, void *dev_id)
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	struct bcm_sysport_tx_ring *txr;
 	unsigned int ring, ring_bit;
+	u32 reg;
 
 	priv->irq0_stat = intrl2_0_readl(priv, INTRL2_CPU_STATUS) &
 			  ~intrl2_0_readl(priv, INTRL2_CPU_MASK_STATUS);
@@ -1102,9 +1131,14 @@ static irqreturn_t bcm_sysport_rx_isr(int irq, void *dev_id)
 	if (priv->irq0_stat & INTRL2_0_TX_RING_FULL)
 		bcm_sysport_tx_reclaim_all(priv);
 
-	if (priv->irq0_stat & INTRL2_0_MPD) {
-		netdev_info(priv->netdev, "Wake-on-LAN interrupt!\n");
-		bcm_sysport_resume_from_wol(priv);
+	if (priv->irq0_stat & INTRL2_0_MPD)
+		netdev_info(priv->netdev, "Wake-on-LAN (MPD) interrupt!\n");
+
+	if (priv->irq0_stat & INTRL2_0_BRCM_MATCH_TAG) {
+		reg = rxchk_readl(priv, RXCHK_BRCM_TAG_MATCH_STATUS) &
+				  RXCHK_BRCM_TAG_MATCH_MASK;
+		netdev_info(priv->netdev,
+			    "Wake-on-LAN (filters 0x%02x) interrupt!\n", reg);
 	}
 
 	if (!priv->is_lite)
@@ -2090,6 +2124,132 @@ static int bcm_sysport_stop(struct net_device *dev)
 	return 0;
 }
 
+static int bcm_sysport_rule_find(struct bcm_sysport_priv *priv,
+				 u64 location)
+{
+	unsigned int index;
+	u32 reg;
+
+	for_each_set_bit(index, priv->filters, RXCHK_BRCM_TAG_MAX) {
+		reg = rxchk_readl(priv, RXCHK_BRCM_TAG(index));
+		reg >>= RXCHK_BRCM_TAG_CID_SHIFT;
+		reg &= RXCHK_BRCM_TAG_CID_MASK;
+		if (reg == location)
+			return index;
+	}
+
+	return -EINVAL;
+}
+
+static int bcm_sysport_rule_get(struct bcm_sysport_priv *priv,
+				struct ethtool_rxnfc *nfc)
+{
+	int index;
+
+	/* This is not a rule that we know about */
+	index = bcm_sysport_rule_find(priv, nfc->fs.location);
+	if (index < 0)
+		return -EOPNOTSUPP;
+
+	nfc->fs.ring_cookie = RX_CLS_FLOW_WAKE;
+
+	return 0;
+}
+
+static int bcm_sysport_rule_set(struct bcm_sysport_priv *priv,
+				struct ethtool_rxnfc *nfc)
+{
+	unsigned int index;
+	u32 reg;
+
+	/* We cannot match locations greater than what the classification ID
+	 * permits (256 entries)
+	 */
+	if (nfc->fs.location > RXCHK_BRCM_TAG_CID_MASK)
+		return -E2BIG;
+
+	/* We cannot support flows that are not destined for a wake-up */
+	if (nfc->fs.ring_cookie != RX_CLS_FLOW_WAKE)
+		return -EOPNOTSUPP;
+
+	/* All filters are already in use, we cannot match more rules */
+	if (bitmap_weight(priv->filters, RXCHK_BRCM_TAG_MAX) ==
+	    RXCHK_BRCM_TAG_MAX)
+		return -ENOSPC;
+
+	index = find_first_zero_bit(priv->filters, RXCHK_BRCM_TAG_MAX);
+	if (index > RXCHK_BRCM_TAG_MAX)
+		return -ENOSPC;
+
+	/* Location is the classification ID, and index is the position
+	 * within one of our 8 possible filters to be programmed
+	 */
+	reg = rxchk_readl(priv, RXCHK_BRCM_TAG(index));
+	reg &= ~(RXCHK_BRCM_TAG_CID_MASK << RXCHK_BRCM_TAG_CID_SHIFT);
+	reg |= nfc->fs.location << RXCHK_BRCM_TAG_CID_SHIFT;
+	rxchk_writel(priv, reg, RXCHK_BRCM_TAG(index));
+	rxchk_writel(priv, 0xff00ffff, RXCHK_BRCM_TAG_MASK(index));
+
+	set_bit(index, priv->filters);
+
+	return 0;
+}
+
+static int bcm_sysport_rule_del(struct bcm_sysport_priv *priv,
+				u64 location)
+{
+	int index;
+
+	/* This is not a rule that we know about */
+	index = bcm_sysport_rule_find(priv, location);
+	if (index < 0)
+		return -EOPNOTSUPP;
+
+	/* No need to disable this filter if it was enabled, this will
+	 * be taken care of during suspend time by bcm_sysport_suspend_to_wol
+	 */
+	clear_bit(index, priv->filters);
+
+	return 0;
+}
+
+static int bcm_sysport_get_rxnfc(struct net_device *dev,
+				 struct ethtool_rxnfc *nfc, u32 *rule_locs)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	int ret = -EOPNOTSUPP;
+
+	switch (nfc->cmd) {
+	case ETHTOOL_GRXCLSRULE:
+		ret = bcm_sysport_rule_get(priv, nfc);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static int bcm_sysport_set_rxnfc(struct net_device *dev,
+				 struct ethtool_rxnfc *nfc)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	int ret = -EOPNOTSUPP;
+
+	switch (nfc->cmd) {
+	case ETHTOOL_SRXCLSRLINS:
+		ret = bcm_sysport_rule_set(priv, nfc);
+		break;
+	case ETHTOOL_SRXCLSRLDEL:
+		ret = bcm_sysport_rule_del(priv, nfc->fs.location);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
 static const struct ethtool_ops bcm_sysport_ethtool_ops = {
 	.get_drvinfo		= bcm_sysport_get_drvinfo,
 	.get_msglevel		= bcm_sysport_get_msglvl,
@@ -2104,10 +2264,12 @@ static const struct ethtool_ops bcm_sysport_ethtool_ops = {
 	.set_coalesce		= bcm_sysport_set_coalesce,
 	.get_link_ksettings     = phy_ethtool_get_link_ksettings,
 	.set_link_ksettings     = phy_ethtool_set_link_ksettings,
+	.get_rxnfc		= bcm_sysport_get_rxnfc,
+	.set_rxnfc		= bcm_sysport_set_rxnfc,
 };
 
 static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb,
-				    void *accel_priv,
+				    struct net_device *sb_dev,
 				    select_queue_fallback_t fallback)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
@@ -2116,7 +2278,7 @@ static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb,
 	unsigned int q, port;
 
 	if (!netdev_uses_dsa(dev))
-		return fallback(dev, skb);
+		return fallback(dev, skb, NULL);
 
 	/* DSA tagging layer will have configured the correct queue */
 	q = BRCM_TAG_GET_QUEUE(queue);
@@ -2124,7 +2286,7 @@ static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb,
 	tx_ring = priv->ring_map[q + port * priv->per_port_num_tx_queues];
 
 	if (unlikely(!tx_ring))
-		return fallback(dev, skb);
+		return fallback(dev, skb, NULL);
 
 	return tx_ring->index;
 }
@@ -2423,21 +2585,43 @@ static int bcm_sysport_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
 static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv)
 {
 	struct net_device *ndev = priv->netdev;
 	unsigned int timeout = 1000;
+	unsigned int index, i = 0;
 	u32 reg;
 
 	/* Password has already been programmed */
 	reg = umac_readl(priv, UMAC_MPD_CTRL);
-	reg |= MPD_EN;
+	if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE))
+		reg |= MPD_EN;
 	reg &= ~PSW_EN;
 	if (priv->wolopts & WAKE_MAGICSECURE)
 		reg |= PSW_EN;
 	umac_writel(priv, reg, UMAC_MPD_CTRL);
 
+	if (priv->wolopts & WAKE_FILTER) {
+		/* Turn on ACPI matching to steal packets from RBUF */
+		reg = rbuf_readl(priv, RBUF_CONTROL);
+		if (priv->is_lite)
+			reg |= RBUF_ACPI_EN_LITE;
+		else
+			reg |= RBUF_ACPI_EN;
+		rbuf_writel(priv, reg, RBUF_CONTROL);
+
+		/* Enable RXCHK, active filters and Broadcom tag matching */
+		reg = rxchk_readl(priv, RXCHK_CONTROL);
+		reg &= ~(RXCHK_BRCM_TAG_MATCH_MASK <<
+			 RXCHK_BRCM_TAG_MATCH_SHIFT);
+		for_each_set_bit(index, priv->filters, RXCHK_BRCM_TAG_MAX) {
+			reg |= BIT(RXCHK_BRCM_TAG_MATCH_SHIFT + i);
+			i++;
+		}
+		reg |= RXCHK_EN | RXCHK_BRCM_TAG_EN;
+		rxchk_writel(priv, reg, RXCHK_CONTROL);
+	}
+
 	/* Make sure RBUF entered WoL mode as result */
 	do {
 		reg = rbuf_readl(priv, RBUF_STATUS);
@@ -2449,9 +2633,7 @@ static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv)
 
 	/* Do not leave the UniMAC RBUF matching only MPD packets */
 	if (!timeout) {
-		reg = umac_readl(priv, UMAC_MPD_CTRL);
-		reg &= ~MPD_EN;
-		umac_writel(priv, reg, UMAC_MPD_CTRL);
+		mpd_enable_set(priv, false);
 		netif_err(priv, wol, ndev, "failed to enter WOL mode\n");
 		return -ETIMEDOUT;
 	}
@@ -2460,14 +2642,14 @@ static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv)
 	umac_enable_set(priv, CMD_RX_EN, 1);
 
 	/* Enable the interrupt wake-up source */
-	intrl2_0_mask_clear(priv, INTRL2_0_MPD);
+	intrl2_0_mask_clear(priv, INTRL2_0_MPD | INTRL2_0_BRCM_MATCH_TAG);
 
 	netif_dbg(priv, wol, ndev, "entered WOL mode\n");
 
 	return 0;
 }
 
-static int bcm_sysport_suspend(struct device *d)
+static int __maybe_unused bcm_sysport_suspend(struct device *d)
 {
 	struct net_device *dev = dev_get_drvdata(d);
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
@@ -2529,7 +2711,7 @@ static int bcm_sysport_suspend(struct device *d)
 	return ret;
 }
 
-static int bcm_sysport_resume(struct device *d)
+static int __maybe_unused bcm_sysport_resume(struct device *d)
 {
 	struct net_device *dev = dev_get_drvdata(d);
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
@@ -2622,7 +2804,6 @@ out_free_tx_rings:
 		bcm_sysport_fini_tx_ring(priv, i);
 	return ret;
 }
-#endif
 
 static SIMPLE_DEV_PM_OPS(bcm_sysport_pm_ops,
 		bcm_sysport_suspend, bcm_sysport_resume);
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index cf440b91fd04..046c6c1d97fd 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -11,6 +11,7 @@
 #ifndef __BCM_SYSPORT_H
 #define __BCM_SYSPORT_H
 
+#include <linux/bitmap.h>
 #include <linux/if_vlan.h>
 #include <linux/net_dim.h>
 
@@ -155,14 +156,18 @@ struct bcm_rsb {
 #define  RXCHK_PARSE_AUTH		(1 << 22)
 
 #define RXCHK_BRCM_TAG0			0x04
-#define RXCHK_BRCM_TAG(i)		((i) * RXCHK_BRCM_TAG0)
+#define RXCHK_BRCM_TAG(i)		((i) * 0x4 + RXCHK_BRCM_TAG0)
 #define RXCHK_BRCM_TAG0_MASK		0x24
-#define RXCHK_BRCM_TAG_MASK(i)		((i) * RXCHK_BRCM_TAG0_MASK)
+#define RXCHK_BRCM_TAG_MASK(i)		((i) * 0x4 + RXCHK_BRCM_TAG0_MASK)
 #define RXCHK_BRCM_TAG_MATCH_STATUS	0x44
 #define RXCHK_ETHERTYPE			0x48
 #define RXCHK_BAD_CSUM_CNTR		0x4C
 #define RXCHK_OTHER_DISC_CNTR		0x50
 
+#define RXCHK_BRCM_TAG_MAX		8
+#define RXCHK_BRCM_TAG_CID_SHIFT	16
+#define RXCHK_BRCM_TAG_CID_MASK		0xff
+
 /* TXCHCK offsets and defines */
 #define SYS_PORT_TXCHK_OFFSET		0x380
 #define TXCHK_PKT_RDY_THRESH		0x00
@@ -185,6 +190,7 @@ struct bcm_rsb {
 #define  RBUF_RSB_SWAP0			(1 << 22)
 #define  RBUF_RSB_SWAP1			(1 << 23)
 #define  RBUF_ACPI_EN			(1 << 23)
+#define  RBUF_ACPI_EN_LITE		(1 << 24)
 
 #define RBUF_PKT_RDY_THRESH		0x04
 
@@ -777,6 +783,7 @@ struct bcm_sysport_priv {
 
 	/* Ethtool */
 	u32			msg_enable;
+	DECLARE_BITMAP(filters, RXCHK_BRCM_TAG_MAX);
 
 	struct bcm_sysport_stats64	stats64;
 
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index e6ea8e61f96d..4c94d9218bba 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -236,7 +236,6 @@ static void bgmac_dma_tx_free(struct bgmac *bgmac, struct bgmac_dma_ring *ring)
 {
 	struct device *dma_dev = bgmac->dma_dev;
 	int empty_slot;
-	bool freed = false;
 	unsigned bytes_compl = 0, pkts_compl = 0;
 
 	/* The last slot that hardware didn't consume yet */
@@ -279,7 +278,6 @@ static void bgmac_dma_tx_free(struct bgmac *bgmac, struct bgmac_dma_ring *ring)
 
 		slot->dma_addr = 0;
 		ring->start++;
-		freed = true;
 	}
 
 	if (!pkts_compl)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index af7b5a4d8ba0..5a727d4729da 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1910,7 +1910,8 @@ void bnx2x_netif_stop(struct bnx2x *bp, int disable_hw)
 }
 
 u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv, select_queue_fallback_t fallback)
+		       struct net_device *sb_dev,
+		       select_queue_fallback_t fallback)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 
@@ -1932,7 +1933,8 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	/* select a non-FCoE queue */
-	return fallback(dev, skb) % (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos);
+	return fallback(dev, skb, NULL) %
+	       (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos);
 }
 
 void bnx2x_set_num_queues(struct bnx2x *bp)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index a8ce5c55bbb0..0e508e5defce 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -497,7 +497,8 @@ int bnx2x_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos,
 
 /* select_queue callback */
 u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv, select_queue_fallback_t fallback);
+		       struct net_device *sb_dev,
+		       select_queue_fallback_t fallback);
 
 static inline void bnx2x_update_rx_prod(struct bnx2x *bp,
 					struct bnx2x_fastpath *fp,
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 22243c480a05..98d4c5a3ff21 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -6339,6 +6339,7 @@ int bnx2x_set_led(struct link_params *params,
 		 */
 		if (!vars->link_up)
 			break;
+		/* else: fall through */
 	case LED_MODE_ON:
 		if (((params->phy[EXT_PHY1].type ==
 			  PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8727) ||
@@ -12521,11 +12522,13 @@ static void bnx2x_phy_def_cfg(struct link_params *params,
 	switch (link_config  & PORT_FEATURE_LINK_SPEED_MASK) {
 	case PORT_FEATURE_LINK_SPEED_10M_HALF:
 		phy->req_duplex = DUPLEX_HALF;
+		/* fall through */
 	case PORT_FEATURE_LINK_SPEED_10M_FULL:
 		phy->req_line_speed = SPEED_10;
 		break;
 	case PORT_FEATURE_LINK_SPEED_100M_HALF:
 		phy->req_duplex = DUPLEX_HALF;
+		/* fall through */
 	case PORT_FEATURE_LINK_SPEED_100M_FULL:
 		phy->req_line_speed = SPEED_100;
 		break;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 57348f2b49a3..71362b7f6040 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -8561,11 +8561,11 @@ int bnx2x_set_int_mode(struct bnx2x *bp)
 			       bp->num_queues,
 			       1 + bp->num_cnic_queues);
 
-		/* falling through... */
+		/* fall through */
 	case BNX2X_INT_MODE_MSI:
 		bnx2x_enable_msi(bp);
 
-		/* falling through... */
+		/* fall through */
 	case BNX2X_INT_MODE_INTX:
 		bp->num_ethernet_queues = 1;
 		bp->num_queues = bp->num_ethernet_queues + bp->num_cnic_queues;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 8baf9d3eb4b1..3f4d2c8da21a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -3258,7 +3258,7 @@ static int bnx2x_mcast_validate_e2(struct bnx2x *bp,
 	/* DEL command deletes all currently configured MACs */
 	case BNX2X_MCAST_CMD_DEL:
 		o->set_registry_size(o, 0);
-		/* Don't break */
+		/* fall through */
 
 	/* RESTORE command will restore the entire multicast configuration */
 	case BNX2X_MCAST_CMD_RESTORE:
@@ -3592,7 +3592,7 @@ static int bnx2x_mcast_validate_e1(struct bnx2x *bp,
 	/* DEL command deletes all currently configured MACs */
 	case BNX2X_MCAST_CMD_DEL:
 		o->set_registry_size(o, 0);
-		/* Don't break */
+		/* fall through */
 
 	/* RESTORE command will restore the entire multicast configuration */
 	case BNX2X_MCAST_CMD_RESTORE:
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index dc77bfded865..62da46537734 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -1827,6 +1827,7 @@ get_vf:
 		DP(BNX2X_MSG_IOV, "got VF [%d:%d] RSS update ramrod\n",
 		   vf->abs_vfid, qidx);
 		bnx2x_vf_handle_rss_update_eqe(bp, vf);
+		/* fall through */
 	case EVENT_RING_OPCODE_VF_FLR:
 		/* Do nothing for now */
 		return 0;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 4394c1162be4..8bb1e38b1681 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -51,6 +51,8 @@
 #include <linux/cpu_rmap.h>
 #include <linux/cpumask.h>
 #include <net/pkt_cls.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
@@ -1115,7 +1117,7 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 		tpa_info->hash_type = PKT_HASH_TYPE_L4;
 		tpa_info->gso_type = SKB_GSO_TCPV4;
 		/* RSS profiles 1 and 3 with extract code 0 for inner 4-tuple */
-		if (hash_type == 3)
+		if (hash_type == 3 || TPA_START_IS_IPV6(tpa_start1))
 			tpa_info->gso_type = SKB_GSO_TCPV6;
 		tpa_info->rss_hash =
 			le32_to_cpu(tpa_start->rx_tpa_start_cmp_rss_hash);
@@ -1727,8 +1729,8 @@ static int bnxt_async_event_process(struct bnxt *bp,
 					    speed);
 		}
 		set_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT, &bp->sp_event);
-		/* fall thru */
 	}
+	/* fall through */
 	case ASYNC_EVENT_CMPL_EVENT_ID_LINK_STATUS_CHANGE:
 		set_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event);
 		break;
@@ -3012,13 +3014,6 @@ static void bnxt_free_hwrm_resources(struct bnxt *bp)
 			  bp->hwrm_cmd_resp_dma_addr);
 
 	bp->hwrm_cmd_resp_addr = NULL;
-	if (bp->hwrm_dbg_resp_addr) {
-		dma_free_coherent(&pdev->dev, HWRM_DBG_REG_BUF_SIZE,
-				  bp->hwrm_dbg_resp_addr,
-				  bp->hwrm_dbg_resp_dma_addr);
-
-		bp->hwrm_dbg_resp_addr = NULL;
-	}
 }
 
 static int bnxt_alloc_hwrm_resources(struct bnxt *bp)
@@ -3030,12 +3025,6 @@ static int bnxt_alloc_hwrm_resources(struct bnxt *bp)
 						   GFP_KERNEL);
 	if (!bp->hwrm_cmd_resp_addr)
 		return -ENOMEM;
-	bp->hwrm_dbg_resp_addr = dma_alloc_coherent(&pdev->dev,
-						    HWRM_DBG_REG_BUF_SIZE,
-						    &bp->hwrm_dbg_resp_dma_addr,
-						    GFP_KERNEL);
-	if (!bp->hwrm_dbg_resp_addr)
-		netdev_warn(bp->dev, "fail to alloc debug register dma mem\n");
 
 	return 0;
 }
@@ -3458,7 +3447,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	cp_ring_id = le16_to_cpu(req->cmpl_ring);
 	intr_process = (cp_ring_id == INVALID_HW_RING_ID) ? 0 : 1;
 
-	if (bp->flags & BNXT_FLAG_SHORT_CMD) {
+	if (bp->fw_cap & BNXT_FW_CAP_SHORT_CMD) {
 		void *short_cmd_req = bp->hwrm_short_cmd_req_addr;
 
 		memcpy(short_cmd_req, req, msg_len);
@@ -3651,7 +3640,9 @@ int bnxt_hwrm_func_rgtr_async_events(struct bnxt *bp, unsigned long *bmap,
 
 static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp)
 {
+	struct hwrm_func_drv_rgtr_output *resp = bp->hwrm_cmd_resp_addr;
 	struct hwrm_func_drv_rgtr_input req = {0};
+	int rc;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_DRV_RGTR, -1, -1);
 
@@ -3689,7 +3680,15 @@ static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp)
 			cpu_to_le32(FUNC_DRV_RGTR_REQ_ENABLES_VF_REQ_FWD);
 	}
 
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		rc = -EIO;
+	else if (resp->flags &
+		 cpu_to_le32(FUNC_DRV_RGTR_RESP_FLAGS_IF_CHANGE_SUPPORTED))
+		bp->fw_cap |= BNXT_FW_CAP_IF_CHANGE;
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
 }
 
 static int bnxt_hwrm_func_drv_unrgtr(struct bnxt *bp)
@@ -3994,6 +3993,7 @@ static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss)
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_RSS_CFG, -1, -1);
 	if (set_rss) {
 		req.hash_type = cpu_to_le32(bp->rss_hash_cfg);
+		req.hash_mode_flags = VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT;
 		if (vnic->flags & BNXT_VNIC_RSS_FLAG) {
 			if (BNXT_CHIP_TYPE_NITRO_A0(bp))
 				max_rings = bp->rx_nr_rings - 1;
@@ -4591,7 +4591,7 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp)
 	}
 
 	hw_resc->resv_tx_rings = le16_to_cpu(resp->alloc_tx_rings);
-	if (bp->flags & BNXT_FLAG_NEW_RM) {
+	if (BNXT_NEW_RM(bp)) {
 		u16 cp, stats;
 
 		hw_resc->resv_rx_rings = le16_to_cpu(resp->alloc_rx_rings);
@@ -4637,7 +4637,7 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, struct hwrm_func_cfg_input *req,
 	req->fid = cpu_to_le16(0xffff);
 	enables |= tx_rings ? FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS : 0;
 	req->num_tx_rings = cpu_to_le16(tx_rings);
-	if (bp->flags & BNXT_FLAG_NEW_RM) {
+	if (BNXT_NEW_RM(bp)) {
 		enables |= rx_rings ? FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS : 0;
 		enables |= cp_rings ? FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
 				      FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
@@ -4710,7 +4710,7 @@ bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 	struct hwrm_func_vf_cfg_input req = {0};
 	int rc;
 
-	if (!(bp->flags & BNXT_FLAG_NEW_RM)) {
+	if (!BNXT_NEW_RM(bp)) {
 		bp->hw_resc.resv_tx_rings = tx_rings;
 		return 0;
 	}
@@ -4770,7 +4770,7 @@ static bool bnxt_need_reserve_rings(struct bnxt *bp)
 		vnic = rx + 1;
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx <<= 1;
-	if ((bp->flags & BNXT_FLAG_NEW_RM) &&
+	if (BNXT_NEW_RM(bp) &&
 	    (hw_resc->resv_rx_rings != rx || hw_resc->resv_cp_rings != cp ||
 	     hw_resc->resv_hw_ring_grps != grp || hw_resc->resv_vnics != vnic))
 		return true;
@@ -4806,7 +4806,7 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 		return rc;
 
 	tx = hw_resc->resv_tx_rings;
-	if (bp->flags & BNXT_FLAG_NEW_RM) {
+	if (BNXT_NEW_RM(bp)) {
 		rx = hw_resc->resv_rx_rings;
 		cp = hw_resc->resv_cp_rings;
 		grp = hw_resc->resv_hw_ring_grps;
@@ -4850,7 +4850,7 @@ static int bnxt_hwrm_check_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 	u32 flags;
 	int rc;
 
-	if (!(bp->flags & BNXT_FLAG_NEW_RM))
+	if (!BNXT_NEW_RM(bp))
 		return 0;
 
 	__bnxt_hwrm_reserve_vf_rings(bp, &req, tx_rings, rx_rings, ring_grps,
@@ -4879,7 +4879,7 @@ static int bnxt_hwrm_check_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 	__bnxt_hwrm_reserve_pf_rings(bp, &req, tx_rings, rx_rings, ring_grps,
 				     cp_rings, vnics);
 	flags = FUNC_CFG_REQ_FLAGS_TX_ASSETS_TEST;
-	if (bp->flags & BNXT_FLAG_NEW_RM)
+	if (BNXT_NEW_RM(bp))
 		flags |= FUNC_CFG_REQ_FLAGS_RX_ASSETS_TEST |
 			 FUNC_CFG_REQ_FLAGS_CMPL_ASSETS_TEST |
 			 FUNC_CFG_REQ_FLAGS_RING_GRP_ASSETS_TEST |
@@ -5101,9 +5101,9 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 	flags = le16_to_cpu(resp->flags);
 	if (flags & (FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED |
 		     FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED)) {
-		bp->flags |= BNXT_FLAG_FW_LLDP_AGENT;
+		bp->fw_cap |= BNXT_FW_CAP_LLDP_AGENT;
 		if (flags & FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED)
-			bp->flags |= BNXT_FLAG_FW_DCBX_AGENT;
+			bp->fw_cap |= BNXT_FW_CAP_DCBX_AGENT;
 	}
 	if (BNXT_PF(bp) && (flags & FUNC_QCFG_RESP_FLAGS_MULTI_HOST))
 		bp->flags |= BNXT_FLAG_MULTI_HOST;
@@ -5175,7 +5175,7 @@ int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all)
 
 		pf->vf_resv_strategy =
 			le16_to_cpu(resp->vf_reservation_strategy);
-		if (pf->vf_resv_strategy > BNXT_VF_RESV_STRATEGY_MINIMAL)
+		if (pf->vf_resv_strategy > BNXT_VF_RESV_STRATEGY_MINIMAL_STATIC)
 			pf->vf_resv_strategy = BNXT_VF_RESV_STRATEGY_MAXIMAL;
 	}
 hwrm_func_resc_qcaps_exit:
@@ -5261,7 +5261,7 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp)
 	if (bp->hwrm_spec_code >= 0x10803) {
 		rc = bnxt_hwrm_func_resc_qcaps(bp, true);
 		if (!rc)
-			bp->flags |= BNXT_FLAG_NEW_RM;
+			bp->fw_cap |= BNXT_FW_CAP_NEW_RM;
 	}
 	return 0;
 }
@@ -5281,7 +5281,8 @@ static int bnxt_hwrm_queue_qportcfg(struct bnxt *bp)
 	int rc = 0;
 	struct hwrm_queue_qportcfg_input req = {0};
 	struct hwrm_queue_qportcfg_output *resp = bp->hwrm_cmd_resp_addr;
-	u8 i, *qptr;
+	u8 i, j, *qptr;
+	bool no_rdma;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_QPORTCFG, -1, -1);
 
@@ -5299,19 +5300,24 @@ static int bnxt_hwrm_queue_qportcfg(struct bnxt *bp)
 	if (bp->max_tc > BNXT_MAX_QUEUE)
 		bp->max_tc = BNXT_MAX_QUEUE;
 
+	no_rdma = !(bp->flags & BNXT_FLAG_ROCE_CAP);
+	qptr = &resp->queue_id0;
+	for (i = 0, j = 0; i < bp->max_tc; i++) {
+		bp->q_info[j].queue_id = *qptr++;
+		bp->q_info[j].queue_profile = *qptr++;
+		bp->tc_to_qidx[j] = j;
+		if (!BNXT_CNPQ(bp->q_info[j].queue_profile) ||
+		    (no_rdma && BNXT_PF(bp)))
+			j++;
+	}
+	bp->max_tc = max_t(u8, j, 1);
+
 	if (resp->queue_cfg_info & QUEUE_QPORTCFG_RESP_QUEUE_CFG_INFO_ASYM_CFG)
 		bp->max_tc = 1;
 
 	if (bp->max_lltc > bp->max_tc)
 		bp->max_lltc = bp->max_tc;
 
-	qptr = &resp->queue_id0;
-	for (i = 0; i < bp->max_tc; i++) {
-		bp->q_info[i].queue_id = *qptr++;
-		bp->q_info[i].queue_profile = *qptr++;
-		bp->tc_to_qidx[i] = i;
-	}
-
 qportcfg_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
@@ -5364,7 +5370,7 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 	dev_caps_cfg = le32_to_cpu(resp->dev_caps_cfg);
 	if ((dev_caps_cfg & VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_SUPPORTED) &&
 	    (dev_caps_cfg & VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_REQUIRED))
-		bp->flags |= BNXT_FLAG_SHORT_CMD;
+		bp->fw_cap |= BNXT_FW_CAP_SHORT_CMD;
 
 hwrm_ver_get_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
@@ -5933,7 +5939,7 @@ int bnxt_get_avail_msix(struct bnxt *bp, int num)
 
 	max_idx = min_t(int, bp->total_irqs, max_cp);
 	avail_msix = max_idx - bp->cp_nr_rings;
-	if (!(bp->flags & BNXT_FLAG_NEW_RM) || avail_msix >= num)
+	if (!BNXT_NEW_RM(bp) || avail_msix >= num)
 		return avail_msix;
 
 	if (max_irq < total_req) {
@@ -5946,7 +5952,7 @@ int bnxt_get_avail_msix(struct bnxt *bp, int num)
 
 static int bnxt_get_num_msix(struct bnxt *bp)
 {
-	if (!(bp->flags & BNXT_FLAG_NEW_RM))
+	if (!BNXT_NEW_RM(bp))
 		return bnxt_get_max_func_irqs(bp);
 
 	return bnxt_cp_rings_in_use(bp);
@@ -6069,8 +6075,7 @@ int bnxt_reserve_rings(struct bnxt *bp)
 		netdev_err(bp->dev, "ring reservation failure rc: %d\n", rc);
 		return rc;
 	}
-	if ((bp->flags & BNXT_FLAG_NEW_RM) &&
-	    (bnxt_get_num_msix(bp) != bp->total_irqs)) {
+	if (BNXT_NEW_RM(bp) && (bnxt_get_num_msix(bp) != bp->total_irqs)) {
 		bnxt_ulp_irq_stop(bp);
 		bnxt_clear_int_mode(bp);
 		rc = bnxt_init_int_mode(bp);
@@ -6350,6 +6355,10 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp)
 		bp->lpi_tmr_hi = le32_to_cpu(resp->valid_tx_lpi_timer_high) &
 				 PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_HIGH_MASK;
 	}
+	if (resp->flags & PORT_PHY_QCAPS_RESP_FLAGS_EXTERNAL_LPBK_SUPPORTED) {
+		if (bp->test_info)
+			bp->test_info->flags |= BNXT_TEST_FL_EXT_LPBK;
+	}
 	if (resp->supported_speeds_auto_mode)
 		link_info->support_auto_speeds =
 			le16_to_cpu(resp->supported_speeds_auto_mode);
@@ -6646,6 +6655,39 @@ static int bnxt_hwrm_shutdown_link(struct bnxt *bp)
 	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 }
 
+static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
+{
+	struct hwrm_func_drv_if_change_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_func_drv_if_change_input req = {0};
+	bool resc_reinit = false;
+	int rc;
+
+	if (!(bp->fw_cap & BNXT_FW_CAP_IF_CHANGE))
+		return 0;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_DRV_IF_CHANGE, -1, -1);
+	if (up)
+		req.flags = cpu_to_le32(FUNC_DRV_IF_CHANGE_REQ_FLAGS_UP);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc && (resp->flags &
+		    cpu_to_le32(FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE)))
+		resc_reinit = true;
+	mutex_unlock(&bp->hwrm_cmd_lock);
+
+	if (up && resc_reinit && BNXT_NEW_RM(bp)) {
+		struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
+
+		rc = bnxt_hwrm_func_resc_qcaps(bp, true);
+		hw_resc->resv_cp_rings = 0;
+		hw_resc->resv_tx_rings = 0;
+		hw_resc->resv_rx_rings = 0;
+		hw_resc->resv_hw_ring_grps = 0;
+		hw_resc->resv_vnics = 0;
+	}
+	return rc;
+}
+
 static int bnxt_hwrm_port_led_qcaps(struct bnxt *bp)
 {
 	struct hwrm_port_led_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
@@ -6755,6 +6797,62 @@ static void bnxt_get_wol_settings(struct bnxt *bp)
 	} while (handle && handle != 0xffff);
 }
 
+#ifdef CONFIG_BNXT_HWMON
+static ssize_t bnxt_show_temp(struct device *dev,
+			      struct device_attribute *devattr, char *buf)
+{
+	struct hwrm_temp_monitor_query_input req = {0};
+	struct hwrm_temp_monitor_query_output *resp;
+	struct bnxt *bp = dev_get_drvdata(dev);
+	u32 temp = 0;
+
+	resp = bp->hwrm_cmd_resp_addr;
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	if (!_hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT))
+		temp = resp->temp * 1000; /* display millidegree */
+	mutex_unlock(&bp->hwrm_cmd_lock);
+
+	return sprintf(buf, "%u\n", temp);
+}
+static SENSOR_DEVICE_ATTR(temp1_input, 0444, bnxt_show_temp, NULL, 0);
+
+static struct attribute *bnxt_attrs[] = {
+	&sensor_dev_attr_temp1_input.dev_attr.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(bnxt);
+
+static void bnxt_hwmon_close(struct bnxt *bp)
+{
+	if (bp->hwmon_dev) {
+		hwmon_device_unregister(bp->hwmon_dev);
+		bp->hwmon_dev = NULL;
+	}
+}
+
+static void bnxt_hwmon_open(struct bnxt *bp)
+{
+	struct pci_dev *pdev = bp->pdev;
+
+	bp->hwmon_dev = hwmon_device_register_with_groups(&pdev->dev,
+							  DRV_MODULE_NAME, bp,
+							  bnxt_groups);
+	if (IS_ERR(bp->hwmon_dev)) {
+		bp->hwmon_dev = NULL;
+		dev_warn(&pdev->dev, "Cannot register hwmon device\n");
+	}
+}
+#else
+static void bnxt_hwmon_close(struct bnxt *bp)
+{
+}
+
+static void bnxt_hwmon_open(struct bnxt *bp)
+{
+}
+#endif
+
 static bool bnxt_eee_config_ok(struct bnxt *bp)
 {
 	struct ethtool_eee *eee = &bp->eee;
@@ -6907,8 +7005,14 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 		mutex_lock(&bp->link_lock);
 		rc = bnxt_update_phy_setting(bp);
 		mutex_unlock(&bp->link_lock);
-		if (rc)
+		if (rc) {
 			netdev_warn(bp->dev, "failed to update phy settings\n");
+			if (BNXT_SINGLE_PF(bp)) {
+				bp->link_info.phy_retry = true;
+				bp->link_info.phy_retry_expires =
+					jiffies + 5 * HZ;
+			}
+		}
 	}
 
 	if (irq_re_init)
@@ -6994,8 +7098,16 @@ void bnxt_half_close_nic(struct bnxt *bp)
 static int bnxt_open(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
+	int rc;
+
+	bnxt_hwrm_if_change(bp, true);
+	rc = __bnxt_open_nic(bp, true, true);
+	if (rc)
+		bnxt_hwrm_if_change(bp, false);
+
+	bnxt_hwmon_open(bp);
 
-	return __bnxt_open_nic(bp, true, true);
+	return rc;
 }
 
 static bool bnxt_drv_busy(struct bnxt *bp)
@@ -7057,8 +7169,10 @@ static int bnxt_close(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
 
+	bnxt_hwmon_close(bp);
 	bnxt_close_nic(bp, true, true);
 	bnxt_hwrm_shutdown_link(bp);
+	bnxt_hwrm_if_change(bp, false);
 	return 0;
 }
 
@@ -7308,7 +7422,7 @@ skip_uc:
 static bool bnxt_can_reserve_rings(struct bnxt *bp)
 {
 #ifdef CONFIG_BNXT_SRIOV
-	if ((bp->flags & BNXT_FLAG_NEW_RM) && BNXT_VF(bp)) {
+	if (BNXT_NEW_RM(bp) && BNXT_VF(bp)) {
 		struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 
 		/* No minimum rings were provisioned by the PF.  Don't
@@ -7358,7 +7472,7 @@ static bool bnxt_rfs_capable(struct bnxt *bp)
 		return false;
 	}
 
-	if (!(bp->flags & BNXT_FLAG_NEW_RM))
+	if (!BNXT_NEW_RM(bp))
 		return true;
 
 	if (vnics == bp->hw_resc.resv_vnics)
@@ -7592,6 +7706,16 @@ static void bnxt_timer(struct timer_list *t)
 		set_bit(BNXT_FLOW_STATS_SP_EVENT, &bp->sp_event);
 		bnxt_queue_sp_work(bp);
 	}
+
+	if (bp->link_info.phy_retry) {
+		if (time_after(jiffies, bp->link_info.phy_retry_expires)) {
+			bp->link_info.phy_retry = 0;
+			netdev_warn(bp->dev, "failed to update phy settings after maximum retries.\n");
+		} else {
+			set_bit(BNXT_UPDATE_PHY_SP_EVENT, &bp->sp_event);
+			bnxt_queue_sp_work(bp);
+		}
+	}
 bnxt_restart_timer:
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
 }
@@ -7679,6 +7803,19 @@ static void bnxt_sp_task(struct work_struct *work)
 			netdev_err(bp->dev, "SP task can't update link (rc: %x)\n",
 				   rc);
 	}
+	if (test_and_clear_bit(BNXT_UPDATE_PHY_SP_EVENT, &bp->sp_event)) {
+		int rc;
+
+		mutex_lock(&bp->link_lock);
+		rc = bnxt_update_phy_setting(bp);
+		mutex_unlock(&bp->link_lock);
+		if (rc) {
+			netdev_warn(bp->dev, "update phy settings retry failed\n");
+		} else {
+			bp->link_info.phy_retry = false;
+			netdev_info(bp->dev, "update phy settings retry succeeded\n");
+		}
+	}
 	if (test_and_clear_bit(BNXT_HWRM_PORT_MODULE_SP_EVENT, &bp->sp_event)) {
 		mutex_lock(&bp->link_lock);
 		bnxt_get_port_module_status(bp);
@@ -7731,7 +7868,7 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx_rings <<= 1;
 	cp = sh ? max_t(int, tx_rings_needed, rx) : tx_rings_needed + rx;
-	if (bp->flags & BNXT_FLAG_NEW_RM)
+	if (BNXT_NEW_RM(bp))
 		cp += bnxt_get_ulp_msix_num(bp);
 	return bnxt_hwrm_check_rings(bp, tx_rings_needed, rx_rings, rx, cp,
 				     vnics);
@@ -7991,7 +8128,7 @@ static int bnxt_setup_tc_block(struct net_device *dev,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, bnxt_setup_tc_block_cb,
-					     bp, bp);
+					     bp, bp, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, bnxt_setup_tc_block_cb, bp);
 		return 0;
@@ -8740,7 +8877,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err_pci_clean;
 
-	if (bp->flags & BNXT_FLAG_SHORT_CMD) {
+	if (bp->fw_cap & BNXT_FW_CAP_SHORT_CMD) {
 		rc = bnxt_alloc_hwrm_short_cmd_req(bp);
 		if (rc)
 			goto init_err_pci_clean;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 91575ef97c8c..fefa011320e0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -12,11 +12,11 @@
 #define BNXT_H
 
 #define DRV_MODULE_NAME		"bnxt_en"
-#define DRV_MODULE_VERSION	"1.9.1"
+#define DRV_MODULE_VERSION	"1.9.2"
 
 #define DRV_VER_MAJ	1
 #define DRV_VER_MIN	9
-#define DRV_VER_UPD	1
+#define DRV_VER_UPD	2
 
 #include <linux/interrupt.h>
 #include <linux/rhashtable.h>
@@ -326,6 +326,10 @@ struct rx_tpa_start_cmp_ext {
 	((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_cfa_code_v2) &	\
 	 RX_TPA_START_CMP_CFA_CODE) >> RX_TPA_START_CMPL_CFA_CODE_SHIFT)
 
+#define TPA_START_IS_IPV6(rx_tpa_start)				\
+	(!!((rx_tpa_start)->rx_tpa_start_cmp_flags2 &		\
+	    cpu_to_le32(RX_TPA_START_CMP_FLAGS2_IP_TYPE)))
+
 struct rx_tpa_end_cmp {
 	__le32 rx_tpa_end_cmp_len_flags_type;
 	#define RX_TPA_END_CMP_TYPE				(0x3f << 0)
@@ -862,6 +866,7 @@ struct bnxt_pf_info {
 	u8	vf_resv_strategy;
 #define BNXT_VF_RESV_STRATEGY_MAXIMAL	0
 #define BNXT_VF_RESV_STRATEGY_MINIMAL	1
+#define BNXT_VF_RESV_STRATEGY_MINIMAL_STATIC	2
 	void			*hwrm_cmd_req_addr[4];
 	dma_addr_t		hwrm_cmd_req_dma_addr[4];
 	struct bnxt_vf_info	*vf;
@@ -959,6 +964,9 @@ struct bnxt_link_info {
 	u16			advertising;	/* user adv setting */
 	bool			force_link_chng;
 
+	bool			phy_retry;
+	unsigned long		phy_retry_expires;
+
 	/* a copy of phy_qcfg output used to report link
 	 * info to VF
 	 */
@@ -990,6 +998,8 @@ struct bnxt_led_info {
 
 struct bnxt_test_info {
 	u8 offline_mask;
+	u8 flags;
+#define BNXT_TEST_FL_EXT_LPBK	0x1
 	u16 timeout;
 	char string[BNXT_MAX_TEST][ETH_GSTRING_LEN];
 };
@@ -1134,7 +1144,6 @@ struct bnxt {
 	atomic_t		intr_sem;
 
 	u32			flags;
-	#define BNXT_FLAG_DCB_ENABLED	0x1
 	#define BNXT_FLAG_VF		0x2
 	#define BNXT_FLAG_LRO		0x4
 #ifdef CONFIG_INET
@@ -1163,15 +1172,11 @@ struct bnxt {
 					 BNXT_FLAG_ROCEV2_CAP)
 	#define BNXT_FLAG_NO_AGG_RINGS	0x20000
 	#define BNXT_FLAG_RX_PAGE_MODE	0x40000
-	#define BNXT_FLAG_FW_LLDP_AGENT	0x80000
 	#define BNXT_FLAG_MULTI_HOST	0x100000
-	#define BNXT_FLAG_SHORT_CMD	0x200000
 	#define BNXT_FLAG_DOUBLE_DB	0x400000
-	#define BNXT_FLAG_FW_DCBX_AGENT	0x800000
 	#define BNXT_FLAG_CHIP_NITRO_A0	0x1000000
 	#define BNXT_FLAG_DIM		0x2000000
 	#define BNXT_FLAG_ROCE_MIRROR_CAP	0x4000000
-	#define BNXT_FLAG_NEW_RM	0x8000000
 	#define BNXT_FLAG_PORT_STATS_EXT	0x10000000
 
 	#define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA |		\
@@ -1276,10 +1281,19 @@ struct bnxt {
 	struct ieee_ets		*ieee_ets;
 	u8			dcbx_cap;
 	u8			default_pri;
+	u8			max_dscp_value;
 #endif /* CONFIG_BNXT_DCB */
 
 	u32			msg_enable;
 
+	u32			fw_cap;
+	#define BNXT_FW_CAP_SHORT_CMD	0x00000001
+	#define BNXT_FW_CAP_LLDP_AGENT	0x00000002
+	#define BNXT_FW_CAP_DCBX_AGENT	0x00000004
+	#define BNXT_FW_CAP_NEW_RM	0x00000008
+	#define BNXT_FW_CAP_IF_CHANGE	0x00000010
+
+#define BNXT_NEW_RM(bp)		((bp)->fw_cap & BNXT_FW_CAP_NEW_RM)
 	u32			hwrm_spec_code;
 	u16			hwrm_cmd_seq;
 	u32			hwrm_intr_seq_id;
@@ -1287,9 +1301,6 @@ struct bnxt {
 	dma_addr_t		hwrm_short_cmd_req_dma_addr;
 	void			*hwrm_cmd_resp_addr;
 	dma_addr_t		hwrm_cmd_resp_dma_addr;
-	void			*hwrm_dbg_resp_addr;
-	dma_addr_t		hwrm_dbg_resp_dma_addr;
-#define HWRM_DBG_REG_BUF_SIZE	128
 
 	struct rx_port_stats	*hw_rx_port_stats;
 	struct tx_port_stats	*hw_tx_port_stats;
@@ -1345,6 +1356,7 @@ struct bnxt {
 #define BNXT_GENEVE_DEL_PORT_SP_EVENT	13
 #define BNXT_LINK_SPEED_CHNG_SP_EVENT	14
 #define BNXT_FLOW_STATS_SP_EVENT	15
+#define BNXT_UPDATE_PHY_SP_EVENT	16
 
 	struct bnxt_hw_resc	hw_resc;
 	struct bnxt_pf_info	pf;
@@ -1400,6 +1412,7 @@ struct bnxt {
 	struct bnxt_tc_info	*tc_info;
 	struct dentry		*debugfs_pdev;
 	struct dentry		*debugfs_dim;
+	struct device		*hwmon_dev;
 };
 
 #define BNXT_RX_STATS_OFFSET(counter)			\
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h
new file mode 100644
index 000000000000..09c22f8fe399
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h
@@ -0,0 +1,66 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2018 Broadcom Inc
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#ifndef BNXT_COREDUMP_H
+#define BNXT_COREDUMP_H
+
+struct bnxt_coredump_segment_hdr {
+	__u8 signature[4];
+	__le32 component_id;
+	__le32 segment_id;
+	__le32 flags;
+	__u8 low_version;
+	__u8 high_version;
+	__le16 function_id;
+	__le32 offset;
+	__le32 length;
+	__le32 status;
+	__le32 duration;
+	__le32 data_offset;
+	__le32 instance;
+	__le32 rsvd[5];
+};
+
+struct bnxt_coredump_record {
+	__u8 signature[4];
+	__le32 flags;
+	__u8 low_version;
+	__u8 high_version;
+	__u8 asic_state;
+	__u8 rsvd0[5];
+	char system_name[32];
+	__le16 year;
+	__le16 month;
+	__le16 day;
+	__le16 hour;
+	__le16 minute;
+	__le16 second;
+	__le16 utc_bias;
+	__le16 rsvd1;
+	char commandline[256];
+	__le32 total_segments;
+	__le32 os_ver_major;
+	__le32 os_ver_minor;
+	__le32 rsvd2;
+	char os_name[32];
+	__le16 end_year;
+	__le16 end_month;
+	__le16 end_day;
+	__le16 end_hour;
+	__le16 end_minute;
+	__le16 end_second;
+	__le16 end_utc_bias;
+	__le32 asic_id1;
+	__le32 asic_id2;
+	__le32 coredump_status;
+	__u8 ioctl_low_version;
+	__u8 ioctl_high_version;
+	__le16 rsvd3[313];
+};
+#endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index d5bc72cecde3..ddc98c359488 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -385,6 +385,61 @@ set_app_exit:
 	return rc;
 }
 
+static int bnxt_hwrm_queue_dscp_qcaps(struct bnxt *bp)
+{
+	struct hwrm_queue_dscp_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_queue_dscp_qcaps_input req = {0};
+	int rc;
+
+	if (bp->hwrm_spec_code < 0x10800 || BNXT_VF(bp))
+		return 0;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_DSCP_QCAPS, -1, -1);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc) {
+		bp->max_dscp_value = (1 << resp->num_dscp_bits) - 1;
+		if (bp->max_dscp_value < 0x3f)
+			bp->max_dscp_value = 0;
+	}
+
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
+static int bnxt_hwrm_queue_dscp2pri_cfg(struct bnxt *bp, struct dcb_app *app,
+					bool add)
+{
+	struct hwrm_queue_dscp2pri_cfg_input req = {0};
+	struct bnxt_dscp2pri_entry *dscp2pri;
+	dma_addr_t mapping;
+	int rc;
+
+	if (bp->hwrm_spec_code < 0x10800)
+		return 0;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_DSCP2PRI_CFG, -1, -1);
+	dscp2pri = dma_alloc_coherent(&bp->pdev->dev, sizeof(*dscp2pri),
+				      &mapping, GFP_KERNEL);
+	if (!dscp2pri)
+		return -ENOMEM;
+
+	req.src_data_addr = cpu_to_le64(mapping);
+	dscp2pri->dscp = app->protocol;
+	if (add)
+		dscp2pri->mask = 0x3f;
+	else
+		dscp2pri->mask = 0;
+	dscp2pri->pri = app->priority;
+	req.entry_cnt = cpu_to_le16(1);
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		rc = -EIO;
+	dma_free_coherent(&bp->pdev->dev, sizeof(*dscp2pri), dscp2pri,
+			  mapping);
+	return rc;
+}
+
 static int bnxt_ets_validate(struct bnxt *bp, struct ieee_ets *ets, u8 *tc)
 {
 	int total_ets_bw = 0;
@@ -551,15 +606,30 @@ static int bnxt_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc)
 	return rc;
 }
 
+static int bnxt_dcbnl_ieee_dscp_app_prep(struct bnxt *bp, struct dcb_app *app)
+{
+	if (app->selector == IEEE_8021QAZ_APP_SEL_DSCP) {
+		if (!bp->max_dscp_value)
+			return -ENOTSUPP;
+		if (app->protocol > bp->max_dscp_value)
+			return -EINVAL;
+	}
+	return 0;
+}
+
 static int bnxt_dcbnl_ieee_setapp(struct net_device *dev, struct dcb_app *app)
 {
 	struct bnxt *bp = netdev_priv(dev);
-	int rc = -EINVAL;
+	int rc;
 
 	if (!(bp->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) ||
 	    !(bp->dcbx_cap & DCB_CAP_DCBX_HOST))
 		return -EINVAL;
 
+	rc = bnxt_dcbnl_ieee_dscp_app_prep(bp, app);
+	if (rc)
+		return rc;
+
 	rc = dcb_ieee_setapp(dev, app);
 	if (rc)
 		return rc;
@@ -570,6 +640,9 @@ static int bnxt_dcbnl_ieee_setapp(struct net_device *dev, struct dcb_app *app)
 	     app->protocol == ROCE_V2_UDP_DPORT))
 		rc = bnxt_hwrm_set_dcbx_app(bp, app, true);
 
+	if (app->selector == IEEE_8021QAZ_APP_SEL_DSCP)
+		rc = bnxt_hwrm_queue_dscp2pri_cfg(bp, app, true);
+
 	return rc;
 }
 
@@ -582,6 +655,10 @@ static int bnxt_dcbnl_ieee_delapp(struct net_device *dev, struct dcb_app *app)
 	    !(bp->dcbx_cap & DCB_CAP_DCBX_HOST))
 		return -EINVAL;
 
+	rc = bnxt_dcbnl_ieee_dscp_app_prep(bp, app);
+	if (rc)
+		return rc;
+
 	rc = dcb_ieee_delapp(dev, app);
 	if (rc)
 		return rc;
@@ -591,6 +668,9 @@ static int bnxt_dcbnl_ieee_delapp(struct net_device *dev, struct dcb_app *app)
 	     app->protocol == ROCE_V2_UDP_DPORT))
 		rc = bnxt_hwrm_set_dcbx_app(bp, app, false);
 
+	if (app->selector == IEEE_8021QAZ_APP_SEL_DSCP)
+		rc = bnxt_hwrm_queue_dscp2pri_cfg(bp, app, false);
+
 	return rc;
 }
 
@@ -610,7 +690,7 @@ static u8 bnxt_dcbnl_setdcbx(struct net_device *dev, u8 mode)
 		return 1;
 
 	if (mode & DCB_CAP_DCBX_HOST) {
-		if (BNXT_VF(bp) || (bp->flags & BNXT_FLAG_FW_LLDP_AGENT))
+		if (BNXT_VF(bp) || (bp->fw_cap & BNXT_FW_CAP_LLDP_AGENT))
 			return 1;
 
 		/* only support IEEE */
@@ -642,10 +722,11 @@ void bnxt_dcb_init(struct bnxt *bp)
 	if (bp->hwrm_spec_code < 0x10501)
 		return;
 
+	bnxt_hwrm_queue_dscp_qcaps(bp);
 	bp->dcbx_cap = DCB_CAP_DCBX_VER_IEEE;
-	if (BNXT_PF(bp) && !(bp->flags & BNXT_FLAG_FW_LLDP_AGENT))
+	if (BNXT_PF(bp) && !(bp->fw_cap & BNXT_FW_CAP_LLDP_AGENT))
 		bp->dcbx_cap |= DCB_CAP_DCBX_HOST;
-	else if (bp->flags & BNXT_FLAG_FW_DCBX_AGENT)
+	else if (bp->fw_cap & BNXT_FW_CAP_DCBX_AGENT)
 		bp->dcbx_cap |= DCB_CAP_DCBX_LLD_MANAGED;
 	bp->dev->dcbnl_ops = &dcbnl_ops;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h
index 69efde785f23..6eed231de565 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h
@@ -33,10 +33,20 @@ struct bnxt_cos2bw_cfg {
 	u8			unused;
 };
 
+struct bnxt_dscp2pri_entry {
+	u8	dscp;
+	u8	mask;
+	u8	pri;
+};
+
 #define BNXT_LLQ(q_profile)	\
 	((q_profile) ==		\
 	 QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS_ROCE)
 
+#define BNXT_CNPQ(q_profile)	\
+	((q_profile) ==		\
+	 QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSY_ROCE_CNP)
+
 #define HWRM_STRUCT_DATA_SUBTYPE_HOST_OPERATIONAL	0x0300
 
 void bnxt_dcb_init(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index 402fa32f7a88..f3b9fbcc705b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -21,16 +21,99 @@ static const struct devlink_ops bnxt_dl_ops = {
 #endif /* CONFIG_BNXT_SRIOV */
 };
 
+static const struct bnxt_dl_nvm_param nvm_params[] = {
+	{DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV, NVM_OFF_ENABLE_SRIOV,
+	 BNXT_NVM_SHARED_CFG, 1},
+};
+
+static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
+			     int msg_len, union devlink_param_value *val)
+{
+	struct hwrm_nvm_get_variable_input *req = msg;
+	void *data_addr = NULL, *buf = NULL;
+	struct bnxt_dl_nvm_param nvm_param;
+	int bytesize, idx = 0, rc, i;
+	dma_addr_t data_dma_addr;
+
+	/* Get/Set NVM CFG parameter is supported only on PFs */
+	if (BNXT_VF(bp))
+		return -EPERM;
+
+	for (i = 0; i < ARRAY_SIZE(nvm_params); i++) {
+		if (nvm_params[i].id == param_id) {
+			nvm_param = nvm_params[i];
+			break;
+		}
+	}
+
+	if (nvm_param.dir_type == BNXT_NVM_PORT_CFG)
+		idx = bp->pf.port_id;
+	else if (nvm_param.dir_type == BNXT_NVM_FUNC_CFG)
+		idx = bp->pf.fw_fid - BNXT_FIRST_PF_FID;
+
+	bytesize = roundup(nvm_param.num_bits, BITS_PER_BYTE) / BITS_PER_BYTE;
+	if (nvm_param.num_bits == 1)
+		buf = &val->vbool;
+
+	data_addr = dma_zalloc_coherent(&bp->pdev->dev, bytesize,
+					&data_dma_addr, GFP_KERNEL);
+	if (!data_addr)
+		return -ENOMEM;
+
+	req->dest_data_addr = cpu_to_le64(data_dma_addr);
+	req->data_len = cpu_to_le16(nvm_param.num_bits);
+	req->option_num = cpu_to_le16(nvm_param.offset);
+	req->index_0 = cpu_to_le16(idx);
+	if (idx)
+		req->dimensions = cpu_to_le16(1);
+
+	if (req->req_type == cpu_to_le16(HWRM_NVM_SET_VARIABLE))
+		memcpy(data_addr, buf, bytesize);
+
+	rc = hwrm_send_message(bp, msg, msg_len, HWRM_CMD_TIMEOUT);
+	if (!rc && req->req_type == cpu_to_le16(HWRM_NVM_GET_VARIABLE))
+		memcpy(buf, data_addr, bytesize);
+
+	dma_free_coherent(&bp->pdev->dev, bytesize, data_addr, data_dma_addr);
+	if (rc)
+		return -EIO;
+	return 0;
+}
+
+static int bnxt_dl_nvm_param_get(struct devlink *dl, u32 id,
+				 struct devlink_param_gset_ctx *ctx)
+{
+	struct hwrm_nvm_get_variable_input req = {0};
+	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_GET_VARIABLE, -1, -1);
+	return bnxt_hwrm_nvm_req(bp, id, &req, sizeof(req), &ctx->val);
+}
+
+static int bnxt_dl_nvm_param_set(struct devlink *dl, u32 id,
+				 struct devlink_param_gset_ctx *ctx)
+{
+	struct hwrm_nvm_set_variable_input req = {0};
+	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_SET_VARIABLE, -1, -1);
+	return bnxt_hwrm_nvm_req(bp, id, &req, sizeof(req), &ctx->val);
+}
+
+static const struct devlink_param bnxt_dl_params[] = {
+	DEVLINK_PARAM_GENERIC(ENABLE_SRIOV,
+			      BIT(DEVLINK_PARAM_CMODE_PERMANENT),
+			      bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set,
+			      NULL),
+};
+
 int bnxt_dl_register(struct bnxt *bp)
 {
 	struct devlink *dl;
 	int rc;
 
-	if (!pci_find_ext_capability(bp->pdev, PCI_EXT_CAP_ID_SRIOV))
-		return 0;
-
-	if (bp->hwrm_spec_code < 0x10803) {
-		netdev_warn(bp->dev, "Firmware does not support SR-IOV E-Switch SWITCHDEV mode.\n");
+	if (bp->hwrm_spec_code < 0x10600) {
+		netdev_warn(bp->dev, "Firmware does not support NVM params");
 		return -ENOTSUPP;
 	}
 
@@ -41,16 +124,34 @@ int bnxt_dl_register(struct bnxt *bp)
 	}
 
 	bnxt_link_bp_to_dl(bp, dl);
-	bp->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY;
+
+	/* Add switchdev eswitch mode setting, if SRIOV supported */
+	if (pci_find_ext_capability(bp->pdev, PCI_EXT_CAP_ID_SRIOV) &&
+	    bp->hwrm_spec_code > 0x10803)
+		bp->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY;
+
 	rc = devlink_register(dl, &bp->pdev->dev);
 	if (rc) {
-		bnxt_link_bp_to_dl(bp, NULL);
-		devlink_free(dl);
 		netdev_warn(bp->dev, "devlink_register failed. rc=%d", rc);
-		return rc;
+		goto err_dl_free;
+	}
+
+	rc = devlink_params_register(dl, bnxt_dl_params,
+				     ARRAY_SIZE(bnxt_dl_params));
+	if (rc) {
+		netdev_warn(bp->dev, "devlink_params_register failed. rc=%d",
+			    rc);
+		goto err_dl_unreg;
 	}
 
 	return 0;
+
+err_dl_unreg:
+	devlink_unregister(dl);
+err_dl_free:
+	bnxt_link_bp_to_dl(bp, NULL);
+	devlink_free(dl);
+	return rc;
 }
 
 void bnxt_dl_unregister(struct bnxt *bp)
@@ -60,6 +161,8 @@ void bnxt_dl_unregister(struct bnxt *bp)
 	if (!dl)
 		return;
 
+	devlink_params_unregister(dl, bnxt_dl_params,
+				  ARRAY_SIZE(bnxt_dl_params));
 	devlink_unregister(dl);
 	devlink_free(dl);
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
index e92a35d8b642..2f68dc048390 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
@@ -33,6 +33,21 @@ static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl)
 	}
 }
 
+#define NVM_OFF_ENABLE_SRIOV		401
+
+enum bnxt_nvm_dir_type {
+	BNXT_NVM_SHARED_CFG = 40,
+	BNXT_NVM_PORT_CFG,
+	BNXT_NVM_FUNC_CFG,
+};
+
+struct bnxt_dl_nvm_param {
+	u16 id;
+	u16 offset;
+	u16 dir_type;
+	u16 num_bits;
+};
+
 int bnxt_dl_register(struct bnxt *bp);
 void bnxt_dl_unregister(struct bnxt *bp);
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 7270c8b0cef3..e52d7af3ab3e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -16,12 +16,15 @@
 #include <linux/etherdevice.h>
 #include <linux/crc32.h>
 #include <linux/firmware.h>
+#include <linux/utsname.h>
+#include <linux/time.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_xdp.h"
 #include "bnxt_ethtool.h"
 #include "bnxt_nvm_defs.h"	/* NVRAM content constant and structure defs */
 #include "bnxt_fw_hdr.h"	/* Firmware hdr constant and structure defs */
+#include "bnxt_coredump.h"
 #define FLASH_NVRAM_TIMEOUT	((HWRM_CMD_TIMEOUT) * 100)
 #define FLASH_PACKAGE_TIMEOUT	((HWRM_CMD_TIMEOUT) * 200)
 #define INSTALL_PACKAGE_TIMEOUT	((HWRM_CMD_TIMEOUT) * 200)
@@ -112,6 +115,11 @@ static int bnxt_set_coalesce(struct net_device *dev,
 					      BNXT_MAX_STATS_COAL_TICKS);
 		stats_ticks = rounddown(stats_ticks, BNXT_MIN_STATS_COAL_TICKS);
 		bp->stats_coal_ticks = stats_ticks;
+		if (bp->stats_coal_ticks)
+			bp->current_interval =
+				bp->stats_coal_ticks * HZ / 1000000;
+		else
+			bp->current_interval = BNXT_TIMER_INTERVAL;
 		update_stats = true;
 	}
 
@@ -162,7 +170,7 @@ static const struct {
 	BNXT_RX_STATS_ENTRY(rx_128b_255b_frames),
 	BNXT_RX_STATS_ENTRY(rx_256b_511b_frames),
 	BNXT_RX_STATS_ENTRY(rx_512b_1023b_frames),
-	BNXT_RX_STATS_ENTRY(rx_1024b_1518_frames),
+	BNXT_RX_STATS_ENTRY(rx_1024b_1518b_frames),
 	BNXT_RX_STATS_ENTRY(rx_good_vlan_frames),
 	BNXT_RX_STATS_ENTRY(rx_1519b_2047b_frames),
 	BNXT_RX_STATS_ENTRY(rx_2048b_4095b_frames),
@@ -205,9 +213,9 @@ static const struct {
 	BNXT_TX_STATS_ENTRY(tx_128b_255b_frames),
 	BNXT_TX_STATS_ENTRY(tx_256b_511b_frames),
 	BNXT_TX_STATS_ENTRY(tx_512b_1023b_frames),
-	BNXT_TX_STATS_ENTRY(tx_1024b_1518_frames),
+	BNXT_TX_STATS_ENTRY(tx_1024b_1518b_frames),
 	BNXT_TX_STATS_ENTRY(tx_good_vlan_frames),
-	BNXT_TX_STATS_ENTRY(tx_1519b_2047_frames),
+	BNXT_TX_STATS_ENTRY(tx_1519b_2047b_frames),
 	BNXT_TX_STATS_ENTRY(tx_2048b_4095b_frames),
 	BNXT_TX_STATS_ENTRY(tx_4096b_9216b_frames),
 	BNXT_TX_STATS_ENTRY(tx_9217b_16383b_frames),
@@ -463,7 +471,7 @@ static void bnxt_get_channels(struct net_device *dev,
 	int max_tx_sch_inputs;
 
 	/* Get the most up-to-date max_tx_sch_inputs. */
-	if (bp->flags & BNXT_FLAG_NEW_RM)
+	if (BNXT_NEW_RM(bp))
 		bnxt_hwrm_func_resc_qcaps(bp, false);
 	max_tx_sch_inputs = hw_resc->max_tx_sch_inputs;
 
@@ -2392,7 +2400,7 @@ static int bnxt_disable_an_for_lpbk(struct bnxt *bp,
 	return rc;
 }
 
-static int bnxt_hwrm_phy_loopback(struct bnxt *bp, bool enable)
+static int bnxt_hwrm_phy_loopback(struct bnxt *bp, bool enable, bool ext)
 {
 	struct hwrm_port_phy_cfg_input req = {0};
 
@@ -2400,7 +2408,10 @@ static int bnxt_hwrm_phy_loopback(struct bnxt *bp, bool enable)
 
 	if (enable) {
 		bnxt_disable_an_for_lpbk(bp, &req);
-		req.lpbk = PORT_PHY_CFG_REQ_LPBK_LOCAL;
+		if (ext)
+			req.lpbk = PORT_PHY_CFG_REQ_LPBK_EXTERNAL;
+		else
+			req.lpbk = PORT_PHY_CFG_REQ_LPBK_LOCAL;
 	} else {
 		req.lpbk = PORT_PHY_CFG_REQ_LPBK_NONE;
 	}
@@ -2533,15 +2544,17 @@ static int bnxt_run_fw_tests(struct bnxt *bp, u8 test_mask, u8 *test_results)
 	return rc;
 }
 
-#define BNXT_DRV_TESTS			3
+#define BNXT_DRV_TESTS			4
 #define BNXT_MACLPBK_TEST_IDX		(bp->num_tests - BNXT_DRV_TESTS)
 #define BNXT_PHYLPBK_TEST_IDX		(BNXT_MACLPBK_TEST_IDX + 1)
-#define BNXT_IRQ_TEST_IDX		(BNXT_MACLPBK_TEST_IDX + 2)
+#define BNXT_EXTLPBK_TEST_IDX		(BNXT_MACLPBK_TEST_IDX + 2)
+#define BNXT_IRQ_TEST_IDX		(BNXT_MACLPBK_TEST_IDX + 3)
 
 static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 			   u64 *buf)
 {
 	struct bnxt *bp = netdev_priv(dev);
+	bool do_ext_lpbk = false;
 	bool offline = false;
 	u8 test_results = 0;
 	u8 test_mask = 0;
@@ -2555,6 +2568,10 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 		return;
 	}
 
+	if ((etest->flags & ETH_TEST_FL_EXTERNAL_LB) &&
+	    (bp->test_info->flags & BNXT_TEST_FL_EXT_LPBK))
+		do_ext_lpbk = true;
+
 	if (etest->flags & ETH_TEST_FL_OFFLINE) {
 		if (bp->pf.active_vfs) {
 			etest->flags |= ETH_TEST_FL_FAILED;
@@ -2595,13 +2612,22 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 			buf[BNXT_MACLPBK_TEST_IDX] = 0;
 
 		bnxt_hwrm_mac_loopback(bp, false);
-		bnxt_hwrm_phy_loopback(bp, true);
+		bnxt_hwrm_phy_loopback(bp, true, false);
 		msleep(1000);
 		if (bnxt_run_loopback(bp)) {
 			buf[BNXT_PHYLPBK_TEST_IDX] = 1;
 			etest->flags |= ETH_TEST_FL_FAILED;
 		}
-		bnxt_hwrm_phy_loopback(bp, false);
+		if (do_ext_lpbk) {
+			etest->flags |= ETH_TEST_FL_EXTERNAL_LB_DONE;
+			bnxt_hwrm_phy_loopback(bp, true, true);
+			msleep(1000);
+			if (bnxt_run_loopback(bp)) {
+				buf[BNXT_EXTLPBK_TEST_IDX] = 1;
+				etest->flags |= ETH_TEST_FL_FAILED;
+			}
+		}
+		bnxt_hwrm_phy_loopback(bp, false, false);
 		bnxt_half_close_nic(bp);
 		bnxt_open_nic(bp, false, true);
 	}
@@ -2662,6 +2688,331 @@ static int bnxt_reset(struct net_device *dev, u32 *flags)
 	return rc;
 }
 
+static int bnxt_hwrm_dbg_dma_data(struct bnxt *bp, void *msg, int msg_len,
+				  struct bnxt_hwrm_dbg_dma_info *info)
+{
+	struct hwrm_dbg_cmn_output *cmn_resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_dbg_cmn_input *cmn_req = msg;
+	__le16 *seq_ptr = msg + info->seq_off;
+	u16 seq = 0, len, segs_off;
+	void *resp = cmn_resp;
+	dma_addr_t dma_handle;
+	int rc, off = 0;
+	void *dma_buf;
+
+	dma_buf = dma_alloc_coherent(&bp->pdev->dev, info->dma_len, &dma_handle,
+				     GFP_KERNEL);
+	if (!dma_buf)
+		return -ENOMEM;
+
+	segs_off = offsetof(struct hwrm_dbg_coredump_list_output,
+			    total_segments);
+	cmn_req->host_dest_addr = cpu_to_le64(dma_handle);
+	cmn_req->host_buf_len = cpu_to_le32(info->dma_len);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	while (1) {
+		*seq_ptr = cpu_to_le16(seq);
+		rc = _hwrm_send_message(bp, msg, msg_len, HWRM_CMD_TIMEOUT);
+		if (rc)
+			break;
+
+		len = le16_to_cpu(*((__le16 *)(resp + info->data_len_off)));
+		if (!seq &&
+		    cmn_req->req_type == cpu_to_le16(HWRM_DBG_COREDUMP_LIST)) {
+			info->segs = le16_to_cpu(*((__le16 *)(resp +
+							      segs_off)));
+			if (!info->segs) {
+				rc = -EIO;
+				break;
+			}
+
+			info->dest_buf_size = info->segs *
+					sizeof(struct coredump_segment_record);
+			info->dest_buf = kmalloc(info->dest_buf_size,
+						 GFP_KERNEL);
+			if (!info->dest_buf) {
+				rc = -ENOMEM;
+				break;
+			}
+		}
+
+		if (info->dest_buf)
+			memcpy(info->dest_buf + off, dma_buf, len);
+
+		if (cmn_req->req_type ==
+				cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE))
+			info->dest_buf_size += len;
+
+		if (!(cmn_resp->flags & HWRM_DBG_CMN_FLAGS_MORE))
+			break;
+
+		seq++;
+		off += len;
+	}
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	dma_free_coherent(&bp->pdev->dev, info->dma_len, dma_buf, dma_handle);
+	return rc;
+}
+
+static int bnxt_hwrm_dbg_coredump_list(struct bnxt *bp,
+				       struct bnxt_coredump *coredump)
+{
+	struct hwrm_dbg_coredump_list_input req = {0};
+	struct bnxt_hwrm_dbg_dma_info info = {NULL};
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_DBG_COREDUMP_LIST, -1, -1);
+
+	info.dma_len = COREDUMP_LIST_BUF_LEN;
+	info.seq_off = offsetof(struct hwrm_dbg_coredump_list_input, seq_no);
+	info.data_len_off = offsetof(struct hwrm_dbg_coredump_list_output,
+				     data_len);
+
+	rc = bnxt_hwrm_dbg_dma_data(bp, &req, sizeof(req), &info);
+	if (!rc) {
+		coredump->data = info.dest_buf;
+		coredump->data_size = info.dest_buf_size;
+		coredump->total_segs = info.segs;
+	}
+	return rc;
+}
+
+static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 component_id,
+					   u16 segment_id)
+{
+	struct hwrm_dbg_coredump_initiate_input req = {0};
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_DBG_COREDUMP_INITIATE, -1, -1);
+	req.component_id = cpu_to_le16(component_id);
+	req.segment_id = cpu_to_le16(segment_id);
+
+	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+}
+
+static int bnxt_hwrm_dbg_coredump_retrieve(struct bnxt *bp, u16 component_id,
+					   u16 segment_id, u32 *seg_len,
+					   void *buf, u32 offset)
+{
+	struct hwrm_dbg_coredump_retrieve_input req = {0};
+	struct bnxt_hwrm_dbg_dma_info info = {NULL};
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_DBG_COREDUMP_RETRIEVE, -1, -1);
+	req.component_id = cpu_to_le16(component_id);
+	req.segment_id = cpu_to_le16(segment_id);
+
+	info.dma_len = COREDUMP_RETRIEVE_BUF_LEN;
+	info.seq_off = offsetof(struct hwrm_dbg_coredump_retrieve_input,
+				seq_no);
+	info.data_len_off = offsetof(struct hwrm_dbg_coredump_retrieve_output,
+				     data_len);
+	if (buf)
+		info.dest_buf = buf + offset;
+
+	rc = bnxt_hwrm_dbg_dma_data(bp, &req, sizeof(req), &info);
+	if (!rc)
+		*seg_len = info.dest_buf_size;
+
+	return rc;
+}
+
+static void
+bnxt_fill_coredump_seg_hdr(struct bnxt *bp,
+			   struct bnxt_coredump_segment_hdr *seg_hdr,
+			   struct coredump_segment_record *seg_rec, u32 seg_len,
+			   int status, u32 duration, u32 instance)
+{
+	memset(seg_hdr, 0, sizeof(*seg_hdr));
+	memcpy(seg_hdr->signature, "sEgM", 4);
+	if (seg_rec) {
+		seg_hdr->component_id = (__force __le32)seg_rec->component_id;
+		seg_hdr->segment_id = (__force __le32)seg_rec->segment_id;
+		seg_hdr->low_version = seg_rec->version_low;
+		seg_hdr->high_version = seg_rec->version_hi;
+	} else {
+		/* For hwrm_ver_get response Component id = 2
+		 * and Segment id = 0
+		 */
+		seg_hdr->component_id = cpu_to_le32(2);
+		seg_hdr->segment_id = 0;
+	}
+	seg_hdr->function_id = cpu_to_le16(bp->pdev->devfn);
+	seg_hdr->length = cpu_to_le32(seg_len);
+	seg_hdr->status = cpu_to_le32(status);
+	seg_hdr->duration = cpu_to_le32(duration);
+	seg_hdr->data_offset = cpu_to_le32(sizeof(*seg_hdr));
+	seg_hdr->instance = cpu_to_le32(instance);
+}
+
+static void
+bnxt_fill_coredump_record(struct bnxt *bp, struct bnxt_coredump_record *record,
+			  time64_t start, s16 start_utc, u16 total_segs,
+			  int status)
+{
+	time64_t end = ktime_get_real_seconds();
+	u32 os_ver_major = 0, os_ver_minor = 0;
+	struct tm tm;
+
+	time64_to_tm(start, 0, &tm);
+	memset(record, 0, sizeof(*record));
+	memcpy(record->signature, "cOrE", 4);
+	record->flags = 0;
+	record->low_version = 0;
+	record->high_version = 1;
+	record->asic_state = 0;
+	strlcpy(record->system_name, utsname()->nodename,
+		sizeof(record->system_name));
+	record->year = cpu_to_le16(tm.tm_year);
+	record->month = cpu_to_le16(tm.tm_mon);
+	record->day = cpu_to_le16(tm.tm_mday);
+	record->hour = cpu_to_le16(tm.tm_hour);
+	record->minute = cpu_to_le16(tm.tm_min);
+	record->second = cpu_to_le16(tm.tm_sec);
+	record->utc_bias = cpu_to_le16(start_utc);
+	strcpy(record->commandline, "ethtool -w");
+	record->total_segments = cpu_to_le32(total_segs);
+
+	sscanf(utsname()->release, "%u.%u", &os_ver_major, &os_ver_minor);
+	record->os_ver_major = cpu_to_le32(os_ver_major);
+	record->os_ver_minor = cpu_to_le32(os_ver_minor);
+
+	strlcpy(record->os_name, utsname()->sysname, 32);
+	time64_to_tm(end, 0, &tm);
+	record->end_year = cpu_to_le16(tm.tm_year + 1900);
+	record->end_month = cpu_to_le16(tm.tm_mon + 1);
+	record->end_day = cpu_to_le16(tm.tm_mday);
+	record->end_hour = cpu_to_le16(tm.tm_hour);
+	record->end_minute = cpu_to_le16(tm.tm_min);
+	record->end_second = cpu_to_le16(tm.tm_sec);
+	record->end_utc_bias = cpu_to_le16(sys_tz.tz_minuteswest * 60);
+	record->asic_id1 = cpu_to_le32(bp->chip_num << 16 |
+				       bp->ver_resp.chip_rev << 8 |
+				       bp->ver_resp.chip_metal);
+	record->asic_id2 = 0;
+	record->coredump_status = cpu_to_le32(status);
+	record->ioctl_low_version = 0;
+	record->ioctl_high_version = 0;
+}
+
+static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len)
+{
+	u32 ver_get_resp_len = sizeof(struct hwrm_ver_get_output);
+	struct coredump_segment_record *seg_record = NULL;
+	u32 offset = 0, seg_hdr_len, seg_record_len;
+	struct bnxt_coredump_segment_hdr seg_hdr;
+	struct bnxt_coredump coredump = {NULL};
+	time64_t start_time;
+	u16 start_utc;
+	int rc = 0, i;
+
+	start_time = ktime_get_real_seconds();
+	start_utc = sys_tz.tz_minuteswest * 60;
+	seg_hdr_len = sizeof(seg_hdr);
+
+	/* First segment should be hwrm_ver_get response */
+	*dump_len = seg_hdr_len + ver_get_resp_len;
+	if (buf) {
+		bnxt_fill_coredump_seg_hdr(bp, &seg_hdr, NULL, ver_get_resp_len,
+					   0, 0, 0);
+		memcpy(buf + offset, &seg_hdr, seg_hdr_len);
+		offset += seg_hdr_len;
+		memcpy(buf + offset, &bp->ver_resp, ver_get_resp_len);
+		offset += ver_get_resp_len;
+	}
+
+	rc = bnxt_hwrm_dbg_coredump_list(bp, &coredump);
+	if (rc) {
+		netdev_err(bp->dev, "Failed to get coredump segment list\n");
+		goto err;
+	}
+
+	*dump_len += seg_hdr_len * coredump.total_segs;
+
+	seg_record = (struct coredump_segment_record *)coredump.data;
+	seg_record_len = sizeof(*seg_record);
+
+	for (i = 0; i < coredump.total_segs; i++) {
+		u16 comp_id = le16_to_cpu(seg_record->component_id);
+		u16 seg_id = le16_to_cpu(seg_record->segment_id);
+		u32 duration = 0, seg_len = 0;
+		unsigned long start, end;
+
+		start = jiffies;
+
+		rc = bnxt_hwrm_dbg_coredump_initiate(bp, comp_id, seg_id);
+		if (rc) {
+			netdev_err(bp->dev,
+				   "Failed to initiate coredump for seg = %d\n",
+				   seg_record->segment_id);
+			goto next_seg;
+		}
+
+		/* Write segment data into the buffer */
+		rc = bnxt_hwrm_dbg_coredump_retrieve(bp, comp_id, seg_id,
+						     &seg_len, buf,
+						     offset + seg_hdr_len);
+		if (rc)
+			netdev_err(bp->dev,
+				   "Failed to retrieve coredump for seg = %d\n",
+				   seg_record->segment_id);
+
+next_seg:
+		end = jiffies;
+		duration = jiffies_to_msecs(end - start);
+		bnxt_fill_coredump_seg_hdr(bp, &seg_hdr, seg_record, seg_len,
+					   rc, duration, 0);
+
+		if (buf) {
+			/* Write segment header into the buffer */
+			memcpy(buf + offset, &seg_hdr, seg_hdr_len);
+			offset += seg_hdr_len + seg_len;
+		}
+
+		*dump_len += seg_len;
+		seg_record =
+			(struct coredump_segment_record *)((u8 *)seg_record +
+							   seg_record_len);
+	}
+
+err:
+	if (buf)
+		bnxt_fill_coredump_record(bp, buf + offset, start_time,
+					  start_utc, coredump.total_segs + 1,
+					  rc);
+	kfree(coredump.data);
+	*dump_len += sizeof(struct bnxt_coredump_record);
+
+	return rc;
+}
+
+static int bnxt_get_dump_flag(struct net_device *dev, struct ethtool_dump *dump)
+{
+	struct bnxt *bp = netdev_priv(dev);
+
+	if (bp->hwrm_spec_code < 0x10801)
+		return -EOPNOTSUPP;
+
+	dump->version = bp->ver_resp.hwrm_fw_maj_8b << 24 |
+			bp->ver_resp.hwrm_fw_min_8b << 16 |
+			bp->ver_resp.hwrm_fw_bld_8b << 8 |
+			bp->ver_resp.hwrm_fw_rsvd_8b;
+
+	return bnxt_get_coredump(bp, NULL, &dump->len);
+}
+
+static int bnxt_get_dump_data(struct net_device *dev, struct ethtool_dump *dump,
+			      void *buf)
+{
+	struct bnxt *bp = netdev_priv(dev);
+
+	if (bp->hwrm_spec_code < 0x10801)
+		return -EOPNOTSUPP;
+
+	memset(buf, 0, dump->len);
+
+	return bnxt_get_coredump(bp, buf, &dump->len);
+}
+
 void bnxt_ethtool_init(struct bnxt *bp)
 {
 	struct hwrm_selftest_qlist_output *resp = bp->hwrm_cmd_resp_addr;
@@ -2702,6 +3053,8 @@ void bnxt_ethtool_init(struct bnxt *bp)
 			strcpy(str, "Mac loopback test (offline)");
 		} else if (i == BNXT_PHYLPBK_TEST_IDX) {
 			strcpy(str, "Phy loopback test (offline)");
+		} else if (i == BNXT_EXTLPBK_TEST_IDX) {
+			strcpy(str, "Ext loopback test (offline)");
 		} else if (i == BNXT_IRQ_TEST_IDX) {
 			strcpy(str, "Interrupt_test (offline)");
 		} else {
@@ -2763,4 +3116,6 @@ const struct ethtool_ops bnxt_ethtool_ops = {
 	.set_phys_id		= bnxt_set_phys_id,
 	.self_test		= bnxt_self_test,
 	.reset			= bnxt_reset,
+	.get_dump_flag		= bnxt_get_dump_flag,
+	.get_dump_data		= bnxt_get_dump_data,
 };
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
index 836ef682f24c..b5b65b3f8534 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
@@ -22,6 +22,43 @@ struct bnxt_led_cfg {
 	u8 rsvd;
 };
 
+#define COREDUMP_LIST_BUF_LEN		2048
+#define COREDUMP_RETRIEVE_BUF_LEN	4096
+
+struct bnxt_coredump {
+	void		*data;
+	int		data_size;
+	u16		total_segs;
+};
+
+struct bnxt_hwrm_dbg_dma_info {
+	void *dest_buf;
+	int dest_buf_size;
+	u16 dma_len;
+	u16 seq_off;
+	u16 data_len_off;
+	u16 segs;
+};
+
+struct hwrm_dbg_cmn_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le64 host_dest_addr;
+	__le32 host_buf_len;
+};
+
+struct hwrm_dbg_cmn_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	u8 flags;
+	#define HWRM_DBG_CMN_FLAGS_MORE	1
+};
+
 #define BNXT_LED_DFLT_ENA				\
 	(PORT_LED_CFG_REQ_ENABLES_LED0_ID |		\
 	 PORT_LED_CFG_REQ_ENABLES_LED0_STATE |		\
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index 0fe0ea8dce6c..971ace5d0d4a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -96,6 +96,7 @@ struct hwrm_short_input {
 struct cmd_nums {
 	__le16	req_type;
 	#define HWRM_VER_GET                              0x0UL
+	#define HWRM_FUNC_DRV_IF_CHANGE                   0xdUL
 	#define HWRM_FUNC_BUF_UNRGTR                      0xeUL
 	#define HWRM_FUNC_VF_CFG                          0xfUL
 	#define HWRM_RESERVED1                            0x10UL
@@ -159,6 +160,7 @@ struct cmd_nums {
 	#define HWRM_RING_FREE                            0x51UL
 	#define HWRM_RING_CMPL_RING_QAGGINT_PARAMS        0x52UL
 	#define HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS     0x53UL
+	#define HWRM_RING_AGGINT_QCAPS                    0x54UL
 	#define HWRM_RING_RESET                           0x5eUL
 	#define HWRM_RING_GRP_ALLOC                       0x60UL
 	#define HWRM_RING_GRP_FREE                        0x61UL
@@ -191,6 +193,8 @@ struct cmd_nums {
 	#define HWRM_PORT_QSTATS_EXT                      0xb4UL
 	#define HWRM_FW_RESET                             0xc0UL
 	#define HWRM_FW_QSTATUS                           0xc1UL
+	#define HWRM_FW_HEALTH_CHECK                      0xc2UL
+	#define HWRM_FW_SYNC                              0xc3UL
 	#define HWRM_FW_SET_TIME                          0xc8UL
 	#define HWRM_FW_GET_TIME                          0xc9UL
 	#define HWRM_FW_SET_STRUCTURED_DATA               0xcaUL
@@ -269,6 +273,11 @@ struct cmd_nums {
 	#define HWRM_ENGINE_ON_DIE_RQE_CREDITS            0x164UL
 	#define HWRM_FUNC_RESOURCE_QCAPS                  0x190UL
 	#define HWRM_FUNC_VF_RESOURCE_CFG                 0x191UL
+	#define HWRM_FUNC_BACKING_STORE_QCAPS             0x192UL
+	#define HWRM_FUNC_BACKING_STORE_CFG               0x193UL
+	#define HWRM_FUNC_BACKING_STORE_QCFG              0x194UL
+	#define HWRM_FUNC_VF_BW_CFG                       0x195UL
+	#define HWRM_FUNC_VF_BW_QCFG                      0x196UL
 	#define HWRM_SELFTEST_QLIST                       0x200UL
 	#define HWRM_SELFTEST_EXEC                        0x201UL
 	#define HWRM_SELFTEST_IRQ                         0x202UL
@@ -284,6 +293,8 @@ struct cmd_nums {
 	#define HWRM_DBG_COREDUMP_LIST                    0xff17UL
 	#define HWRM_DBG_COREDUMP_INITIATE                0xff18UL
 	#define HWRM_DBG_COREDUMP_RETRIEVE                0xff19UL
+	#define HWRM_DBG_FW_CLI                           0xff1aUL
+	#define HWRM_DBG_I2C_CMD                          0xff1bUL
 	#define HWRM_NVM_FACTORY_DEFAULTS                 0xffeeUL
 	#define HWRM_NVM_VALIDATE_OPTION                  0xffefUL
 	#define HWRM_NVM_FLUSH                            0xfff0UL
@@ -318,6 +329,7 @@ struct ret_codes {
 	#define HWRM_ERR_CODE_INVALID_ENABLES        0x6UL
 	#define HWRM_ERR_CODE_UNSUPPORTED_TLV        0x7UL
 	#define HWRM_ERR_CODE_NO_BUFFER              0x8UL
+	#define HWRM_ERR_CODE_UNSUPPORTED_OPTION_ERR 0x9UL
 	#define HWRM_ERR_CODE_HWRM_ERROR             0xfUL
 	#define HWRM_ERR_CODE_UNKNOWN_ERR            0xfffeUL
 	#define HWRM_ERR_CODE_CMD_NOT_SUPPORTED      0xffffUL
@@ -344,9 +356,9 @@ struct hwrm_err_output {
 #define HWRM_RESP_VALID_KEY 1
 #define HWRM_VERSION_MAJOR 1
 #define HWRM_VERSION_MINOR 9
-#define HWRM_VERSION_UPDATE 1
-#define HWRM_VERSION_RSVD 15
-#define HWRM_VERSION_STR "1.9.1.15"
+#define HWRM_VERSION_UPDATE 2
+#define HWRM_VERSION_RSVD 25
+#define HWRM_VERSION_STR "1.9.2.25"
 
 /* hwrm_ver_get_input (size:192b/24B) */
 struct hwrm_ver_get_input {
@@ -526,6 +538,7 @@ struct hwrm_async_event_cmpl {
 	#define ASYNC_EVENT_CMPL_EVENT_ID_PF_VF_COMM_STATUS_CHANGE   0x32UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_CFG_CHANGE              0x33UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_LLFC_PFC_CHANGE            0x34UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_DEFAULT_VNIC_CHANGE        0x35UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR                 0xffUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_LAST                      ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR
 	__le32	event_data2;
@@ -564,6 +577,8 @@ struct hwrm_async_event_cmpl_link_status_change {
 	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_SFT        1
 	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_ID_MASK    0xffff0UL
 	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_ID_SFT     4
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PF_ID_MASK      0xff00000UL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PF_ID_SFT       20
 };
 
 /* hwrm_async_event_cmpl_port_conn_not_allowed (size:128b/16B) */
@@ -817,23 +832,26 @@ struct hwrm_func_qcaps_output {
 	__le16	fid;
 	__le16	port_id;
 	__le32	flags;
-	#define FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED            0x1UL
-	#define FUNC_QCAPS_RESP_FLAGS_GLOBAL_MSIX_AUTOMASKING        0x2UL
-	#define FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED                  0x4UL
-	#define FUNC_QCAPS_RESP_FLAGS_ROCE_V1_SUPPORTED              0x8UL
-	#define FUNC_QCAPS_RESP_FLAGS_ROCE_V2_SUPPORTED              0x10UL
-	#define FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED         0x20UL
-	#define FUNC_QCAPS_RESP_FLAGS_WOL_BMP_SUPPORTED              0x40UL
-	#define FUNC_QCAPS_RESP_FLAGS_TX_RING_RL_SUPPORTED           0x80UL
-	#define FUNC_QCAPS_RESP_FLAGS_TX_BW_CFG_SUPPORTED            0x100UL
-	#define FUNC_QCAPS_RESP_FLAGS_VF_TX_RING_RL_SUPPORTED        0x200UL
-	#define FUNC_QCAPS_RESP_FLAGS_VF_BW_CFG_SUPPORTED            0x400UL
-	#define FUNC_QCAPS_RESP_FLAGS_STD_TX_RING_MODE_SUPPORTED     0x800UL
-	#define FUNC_QCAPS_RESP_FLAGS_GENEVE_TUN_FLAGS_SUPPORTED     0x1000UL
-	#define FUNC_QCAPS_RESP_FLAGS_NVGRE_TUN_FLAGS_SUPPORTED      0x2000UL
-	#define FUNC_QCAPS_RESP_FLAGS_GRE_TUN_FLAGS_SUPPORTED        0x4000UL
-	#define FUNC_QCAPS_RESP_FLAGS_MPLS_TUN_FLAGS_SUPPORTED       0x8000UL
-	#define FUNC_QCAPS_RESP_FLAGS_PCIE_STATS_SUPPORTED           0x10000UL
+	#define FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED             0x1UL
+	#define FUNC_QCAPS_RESP_FLAGS_GLOBAL_MSIX_AUTOMASKING         0x2UL
+	#define FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED                   0x4UL
+	#define FUNC_QCAPS_RESP_FLAGS_ROCE_V1_SUPPORTED               0x8UL
+	#define FUNC_QCAPS_RESP_FLAGS_ROCE_V2_SUPPORTED               0x10UL
+	#define FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED          0x20UL
+	#define FUNC_QCAPS_RESP_FLAGS_WOL_BMP_SUPPORTED               0x40UL
+	#define FUNC_QCAPS_RESP_FLAGS_TX_RING_RL_SUPPORTED            0x80UL
+	#define FUNC_QCAPS_RESP_FLAGS_TX_BW_CFG_SUPPORTED             0x100UL
+	#define FUNC_QCAPS_RESP_FLAGS_VF_TX_RING_RL_SUPPORTED         0x200UL
+	#define FUNC_QCAPS_RESP_FLAGS_VF_BW_CFG_SUPPORTED             0x400UL
+	#define FUNC_QCAPS_RESP_FLAGS_STD_TX_RING_MODE_SUPPORTED      0x800UL
+	#define FUNC_QCAPS_RESP_FLAGS_GENEVE_TUN_FLAGS_SUPPORTED      0x1000UL
+	#define FUNC_QCAPS_RESP_FLAGS_NVGRE_TUN_FLAGS_SUPPORTED       0x2000UL
+	#define FUNC_QCAPS_RESP_FLAGS_GRE_TUN_FLAGS_SUPPORTED         0x4000UL
+	#define FUNC_QCAPS_RESP_FLAGS_MPLS_TUN_FLAGS_SUPPORTED        0x8000UL
+	#define FUNC_QCAPS_RESP_FLAGS_PCIE_STATS_SUPPORTED            0x10000UL
+	#define FUNC_QCAPS_RESP_FLAGS_ADOPTED_PF_SUPPORTED            0x20000UL
+	#define FUNC_QCAPS_RESP_FLAGS_ADMIN_PF_SUPPORTED              0x40000UL
+	#define FUNC_QCAPS_RESP_FLAGS_LINK_ADMIN_STATUS_SUPPORTED     0x80000UL
 	u8	mac_address[6];
 	__le16	max_rsscos_ctx;
 	__le16	max_cmpl_rings;
@@ -947,58 +965,26 @@ struct hwrm_func_qcfg_output {
 	#define FUNC_QCFG_RESP_EVB_MODE_VEPA   0x2UL
 	#define FUNC_QCFG_RESP_EVB_MODE_LAST  FUNC_QCFG_RESP_EVB_MODE_VEPA
 	u8	options;
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_MASK    0x3UL
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SFT     0
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_64   0x0UL
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128  0x1UL
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_LAST     FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128
-	#define FUNC_QCFG_RESP_OPTIONS_RSVD_MASK              0xfcUL
-	#define FUNC_QCFG_RESP_OPTIONS_RSVD_SFT               2
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_MASK         0x3UL
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SFT          0
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_64        0x0UL
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128       0x1UL
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_LAST          FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_MASK       0xcUL
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_SFT        2
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_FORCED_DOWN  (0x0UL << 2)
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_FORCED_UP    (0x1UL << 2)
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_AUTO         (0x2UL << 2)
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_LAST        FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_AUTO
+	#define FUNC_QCFG_RESP_OPTIONS_RSVD_MASK                   0xf0UL
+	#define FUNC_QCFG_RESP_OPTIONS_RSVD_SFT                    4
 	__le16	alloc_vfs;
 	__le32	alloc_mcast_filters;
 	__le32	alloc_hw_ring_grps;
 	__le16	alloc_sp_tx_rings;
 	__le16	alloc_stat_ctx;
-	u8	unused_2[7];
-	u8	valid;
-};
-
-/* hwrm_func_vlan_cfg_input (size:384b/48B) */
-struct hwrm_func_vlan_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	u8	unused_0[2];
-	__le32	enables;
-	#define FUNC_VLAN_CFG_REQ_ENABLES_STAG_VID      0x1UL
-	#define FUNC_VLAN_CFG_REQ_ENABLES_CTAG_VID      0x2UL
-	#define FUNC_VLAN_CFG_REQ_ENABLES_STAG_PCP      0x4UL
-	#define FUNC_VLAN_CFG_REQ_ENABLES_CTAG_PCP      0x8UL
-	#define FUNC_VLAN_CFG_REQ_ENABLES_STAG_TPID     0x10UL
-	#define FUNC_VLAN_CFG_REQ_ENABLES_CTAG_TPID     0x20UL
-	__le16	stag_vid;
-	u8	stag_pcp;
-	u8	unused_1;
-	__be16	stag_tpid;
-	__le16	ctag_vid;
-	u8	ctag_pcp;
-	u8	unused_2;
-	__be16	ctag_tpid;
-	__le32	rsvd1;
-	__le32	rsvd2;
-	u8	unused_3[4];
-};
-
-/* hwrm_func_vlan_cfg_output (size:128b/16B) */
-struct hwrm_func_vlan_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
+	__le16	alloc_msix;
+	u8	unused_2[5];
 	u8	valid;
 };
 
@@ -1010,7 +996,7 @@ struct hwrm_func_cfg_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	__le16	fid;
-	u8	unused_0[2];
+	__le16	num_msix;
 	__le32	flags;
 	#define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE     0x1UL
 	#define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE      0x2UL
@@ -1050,6 +1036,8 @@ struct hwrm_func_cfg_input {
 	#define FUNC_CFG_REQ_ENABLES_NUM_MCAST_FILTERS       0x40000UL
 	#define FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS        0x80000UL
 	#define FUNC_CFG_REQ_ENABLES_CACHE_LINESIZE          0x100000UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_MSIX                0x200000UL
+	#define FUNC_CFG_REQ_ENABLES_ADMIN_LINK_STATE        0x400000UL
 	__le16	mtu;
 	__le16	mru;
 	__le16	num_rsscos_ctxs;
@@ -1109,13 +1097,19 @@ struct hwrm_func_cfg_input {
 	#define FUNC_CFG_REQ_EVB_MODE_VEPA   0x2UL
 	#define FUNC_CFG_REQ_EVB_MODE_LAST  FUNC_CFG_REQ_EVB_MODE_VEPA
 	u8	options;
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_MASK    0x3UL
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SFT     0
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_64   0x0UL
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128  0x1UL
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_LAST     FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128
-	#define FUNC_CFG_REQ_OPTIONS_RSVD_MASK              0xfcUL
-	#define FUNC_CFG_REQ_OPTIONS_RSVD_SFT               2
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_MASK         0x3UL
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SFT          0
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_64        0x0UL
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128       0x1UL
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_LAST          FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_MASK       0xcUL
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_SFT        2
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_FORCED_DOWN  (0x0UL << 2)
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_FORCED_UP    (0x1UL << 2)
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_AUTO         (0x2UL << 2)
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_LAST        FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_AUTO
+	#define FUNC_CFG_REQ_OPTIONS_RSVD_MASK                   0xf0UL
+	#define FUNC_CFG_REQ_OPTIONS_RSVD_SFT                    4
 	__le16	num_mcast_filters;
 };
 
@@ -1212,30 +1206,6 @@ struct hwrm_func_vf_resc_free_output {
 	u8	valid;
 };
 
-/* hwrm_func_vf_vnic_ids_query_input (size:256b/32B) */
-struct hwrm_func_vf_vnic_ids_query_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	vf_id;
-	u8	unused_0[2];
-	__le32	max_vnic_id_cnt;
-	__le64	vnic_id_tbl_addr;
-};
-
-/* hwrm_func_vf_vnic_ids_query_output (size:128b/16B) */
-struct hwrm_func_vf_vnic_ids_query_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	vnic_id_cnt;
-	u8	unused_0[3];
-	u8	valid;
-};
-
 /* hwrm_func_drv_rgtr_input (size:896b/112B) */
 struct hwrm_func_drv_rgtr_input {
 	__le16	req_type;
@@ -1286,7 +1256,9 @@ struct hwrm_func_drv_rgtr_output {
 	__le16	req_type;
 	__le16	seq_id;
 	__le16	resp_len;
-	u8	unused_0[7];
+	__le32	flags;
+	#define FUNC_DRV_RGTR_RESP_FLAGS_IF_CHANGE_SUPPORTED     0x1UL
+	u8	unused_0[3];
 	u8	valid;
 };
 
@@ -1372,7 +1344,7 @@ struct hwrm_func_drv_qver_input {
 	u8	unused_0[2];
 };
 
-/* hwrm_func_drv_qver_output (size:192b/24B) */
+/* hwrm_func_drv_qver_output (size:256b/32B) */
 struct hwrm_func_drv_qver_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -1394,12 +1366,13 @@ struct hwrm_func_drv_qver_output {
 	u8	ver_maj_8b;
 	u8	ver_min_8b;
 	u8	ver_upd_8b;
-	u8	unused_0[2];
-	u8	valid;
+	u8	unused_0[3];
 	__le16	ver_maj;
 	__le16	ver_min;
 	__le16	ver_upd;
 	__le16	ver_patch;
+	u8	unused_1[7];
+	u8	valid;
 };
 
 /* hwrm_func_resource_qcaps_input (size:192b/24B) */
@@ -1493,6 +1466,410 @@ struct hwrm_func_vf_resource_cfg_output {
 	u8	valid;
 };
 
+/* hwrm_func_backing_store_qcaps_input (size:128b/16B) */
+struct hwrm_func_backing_store_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_func_backing_store_qcaps_output (size:576b/72B) */
+struct hwrm_func_backing_store_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	qp_max_entries;
+	__le16	qp_min_qp1_entries;
+	__le16	qp_max_l2_entries;
+	__le16	qp_entry_size;
+	__le16	srq_max_l2_entries;
+	__le32	srq_max_entries;
+	__le16	srq_entry_size;
+	__le16	cq_max_l2_entries;
+	__le32	cq_max_entries;
+	__le16	cq_entry_size;
+	__le16	vnic_max_vnic_entries;
+	__le16	vnic_max_ring_table_entries;
+	__le16	vnic_entry_size;
+	__le32	stat_max_entries;
+	__le16	stat_entry_size;
+	__le16	tqm_entry_size;
+	__le32	tqm_min_entries_per_ring;
+	__le32	tqm_max_entries_per_ring;
+	__le32	mrav_max_entries;
+	__le16	mrav_entry_size;
+	__le16	tim_entry_size;
+	__le32	tim_max_entries;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_func_backing_store_cfg_input (size:2048b/256B) */
+struct hwrm_func_backing_store_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define FUNC_BACKING_STORE_CFG_REQ_FLAGS_PREBOOT_MODE     0x1UL
+	__le32	enables;
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP            0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_SRQ           0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_CQ            0x4UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_VNIC          0x8UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_STAT          0x10UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP        0x20UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING0     0x40UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING1     0x80UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING2     0x100UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING3     0x200UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING4     0x400UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING5     0x800UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING6     0x1000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING7     0x2000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV          0x4000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM           0x8000UL
+	u8	qpc_pg_size_qpc_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_1G
+	u8	srq_pg_size_srq_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_1G
+	u8	cq_pg_size_cq_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_1G
+	u8	vnic_pg_size_vnic_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_1G
+	u8	stat_pg_size_stat_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_1G
+	u8	tqm_sp_pg_size_tqm_sp_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_1G
+	u8	tqm_ring0_pg_size_tqm_ring0_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_1G
+	u8	tqm_ring1_pg_size_tqm_ring1_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_1G
+	u8	tqm_ring2_pg_size_tqm_ring2_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_1G
+	u8	tqm_ring3_pg_size_tqm_ring3_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_1G
+	u8	tqm_ring4_pg_size_tqm_ring4_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_1G
+	u8	tqm_ring5_pg_size_tqm_ring5_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_1G
+	u8	tqm_ring6_pg_size_tqm_ring6_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_1G
+	u8	tqm_ring7_pg_size_tqm_ring7_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_1G
+	u8	mrav_pg_size_mrav_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_1G
+	u8	tim_pg_size_tim_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_1G
+	__le64	qpc_page_dir;
+	__le64	srq_page_dir;
+	__le64	cq_page_dir;
+	__le64	vnic_page_dir;
+	__le64	stat_page_dir;
+	__le64	tqm_sp_page_dir;
+	__le64	tqm_ring0_page_dir;
+	__le64	tqm_ring1_page_dir;
+	__le64	tqm_ring2_page_dir;
+	__le64	tqm_ring3_page_dir;
+	__le64	tqm_ring4_page_dir;
+	__le64	tqm_ring5_page_dir;
+	__le64	tqm_ring6_page_dir;
+	__le64	tqm_ring7_page_dir;
+	__le64	mrav_page_dir;
+	__le64	tim_page_dir;
+	__le32	qp_num_entries;
+	__le32	srq_num_entries;
+	__le32	cq_num_entries;
+	__le32	stat_num_entries;
+	__le32	tqm_sp_num_entries;
+	__le32	tqm_ring0_num_entries;
+	__le32	tqm_ring1_num_entries;
+	__le32	tqm_ring2_num_entries;
+	__le32	tqm_ring3_num_entries;
+	__le32	tqm_ring4_num_entries;
+	__le32	tqm_ring5_num_entries;
+	__le32	tqm_ring6_num_entries;
+	__le32	tqm_ring7_num_entries;
+	__le32	mrav_num_entries;
+	__le32	tim_num_entries;
+	__le16	qp_num_qp1_entries;
+	__le16	qp_num_l2_entries;
+	__le16	qp_entry_size;
+	__le16	srq_num_l2_entries;
+	__le16	srq_entry_size;
+	__le16	cq_num_l2_entries;
+	__le16	cq_entry_size;
+	__le16	vnic_num_vnic_entries;
+	__le16	vnic_num_ring_table_entries;
+	__le16	vnic_entry_size;
+	__le16	stat_entry_size;
+	__le16	tqm_entry_size;
+	__le16	mrav_entry_size;
+	__le16	tim_entry_size;
+};
+
+/* hwrm_func_backing_store_cfg_output (size:128b/16B) */
+struct hwrm_func_backing_store_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_drv_if_change_input (size:192b/24B) */
+struct hwrm_func_drv_if_change_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define FUNC_DRV_IF_CHANGE_REQ_FLAGS_UP     0x1UL
+	__le32	unused;
+};
+
+/* hwrm_func_drv_if_change_output (size:128b/16B) */
+struct hwrm_func_drv_if_change_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE     0x1UL
+	u8	unused_0[3];
+	u8	valid;
+};
+
 /* hwrm_port_phy_cfg_input (size:448b/56B) */
 struct hwrm_port_phy_cfg_input {
 	__le16	req_type;
@@ -1592,10 +1969,11 @@ struct hwrm_port_phy_cfg_input {
 	#define PORT_PHY_CFG_REQ_WIRESPEED_ON  0x1UL
 	#define PORT_PHY_CFG_REQ_WIRESPEED_LAST PORT_PHY_CFG_REQ_WIRESPEED_ON
 	u8	lpbk;
-	#define PORT_PHY_CFG_REQ_LPBK_NONE   0x0UL
-	#define PORT_PHY_CFG_REQ_LPBK_LOCAL  0x1UL
-	#define PORT_PHY_CFG_REQ_LPBK_REMOTE 0x2UL
-	#define PORT_PHY_CFG_REQ_LPBK_LAST  PORT_PHY_CFG_REQ_LPBK_REMOTE
+	#define PORT_PHY_CFG_REQ_LPBK_NONE     0x0UL
+	#define PORT_PHY_CFG_REQ_LPBK_LOCAL    0x1UL
+	#define PORT_PHY_CFG_REQ_LPBK_REMOTE   0x2UL
+	#define PORT_PHY_CFG_REQ_LPBK_EXTERNAL 0x3UL
+	#define PORT_PHY_CFG_REQ_LPBK_LAST    PORT_PHY_CFG_REQ_LPBK_EXTERNAL
 	u8	force_pause;
 	#define PORT_PHY_CFG_REQ_FORCE_PAUSE_TX     0x1UL
 	#define PORT_PHY_CFG_REQ_FORCE_PAUSE_RX     0x2UL
@@ -1751,10 +2129,11 @@ struct hwrm_port_phy_qcfg_output {
 	#define PORT_PHY_QCFG_RESP_WIRESPEED_ON  0x1UL
 	#define PORT_PHY_QCFG_RESP_WIRESPEED_LAST PORT_PHY_QCFG_RESP_WIRESPEED_ON
 	u8	lpbk;
-	#define PORT_PHY_QCFG_RESP_LPBK_NONE   0x0UL
-	#define PORT_PHY_QCFG_RESP_LPBK_LOCAL  0x1UL
-	#define PORT_PHY_QCFG_RESP_LPBK_REMOTE 0x2UL
-	#define PORT_PHY_QCFG_RESP_LPBK_LAST  PORT_PHY_QCFG_RESP_LPBK_REMOTE
+	#define PORT_PHY_QCFG_RESP_LPBK_NONE     0x0UL
+	#define PORT_PHY_QCFG_RESP_LPBK_LOCAL    0x1UL
+	#define PORT_PHY_QCFG_RESP_LPBK_REMOTE   0x2UL
+	#define PORT_PHY_QCFG_RESP_LPBK_EXTERNAL 0x3UL
+	#define PORT_PHY_QCFG_RESP_LPBK_LAST    PORT_PHY_QCFG_RESP_LPBK_EXTERNAL
 	u8	force_pause;
 	#define PORT_PHY_QCFG_RESP_FORCE_PAUSE_TX     0x1UL
 	#define PORT_PHY_QCFG_RESP_FORCE_PAUSE_RX     0x2UL
@@ -2014,6 +2393,131 @@ struct hwrm_port_mac_ptp_qcfg_output {
 	u8	valid;
 };
 
+/* tx_port_stats (size:3264b/408B) */
+struct tx_port_stats {
+	__le64	tx_64b_frames;
+	__le64	tx_65b_127b_frames;
+	__le64	tx_128b_255b_frames;
+	__le64	tx_256b_511b_frames;
+	__le64	tx_512b_1023b_frames;
+	__le64	tx_1024b_1518b_frames;
+	__le64	tx_good_vlan_frames;
+	__le64	tx_1519b_2047b_frames;
+	__le64	tx_2048b_4095b_frames;
+	__le64	tx_4096b_9216b_frames;
+	__le64	tx_9217b_16383b_frames;
+	__le64	tx_good_frames;
+	__le64	tx_total_frames;
+	__le64	tx_ucast_frames;
+	__le64	tx_mcast_frames;
+	__le64	tx_bcast_frames;
+	__le64	tx_pause_frames;
+	__le64	tx_pfc_frames;
+	__le64	tx_jabber_frames;
+	__le64	tx_fcs_err_frames;
+	__le64	tx_control_frames;
+	__le64	tx_oversz_frames;
+	__le64	tx_single_dfrl_frames;
+	__le64	tx_multi_dfrl_frames;
+	__le64	tx_single_coll_frames;
+	__le64	tx_multi_coll_frames;
+	__le64	tx_late_coll_frames;
+	__le64	tx_excessive_coll_frames;
+	__le64	tx_frag_frames;
+	__le64	tx_err;
+	__le64	tx_tagged_frames;
+	__le64	tx_dbl_tagged_frames;
+	__le64	tx_runt_frames;
+	__le64	tx_fifo_underruns;
+	__le64	tx_pfc_ena_frames_pri0;
+	__le64	tx_pfc_ena_frames_pri1;
+	__le64	tx_pfc_ena_frames_pri2;
+	__le64	tx_pfc_ena_frames_pri3;
+	__le64	tx_pfc_ena_frames_pri4;
+	__le64	tx_pfc_ena_frames_pri5;
+	__le64	tx_pfc_ena_frames_pri6;
+	__le64	tx_pfc_ena_frames_pri7;
+	__le64	tx_eee_lpi_events;
+	__le64	tx_eee_lpi_duration;
+	__le64	tx_llfc_logical_msgs;
+	__le64	tx_hcfc_msgs;
+	__le64	tx_total_collisions;
+	__le64	tx_bytes;
+	__le64	tx_xthol_frames;
+	__le64	tx_stat_discard;
+	__le64	tx_stat_error;
+};
+
+/* rx_port_stats (size:4224b/528B) */
+struct rx_port_stats {
+	__le64	rx_64b_frames;
+	__le64	rx_65b_127b_frames;
+	__le64	rx_128b_255b_frames;
+	__le64	rx_256b_511b_frames;
+	__le64	rx_512b_1023b_frames;
+	__le64	rx_1024b_1518b_frames;
+	__le64	rx_good_vlan_frames;
+	__le64	rx_1519b_2047b_frames;
+	__le64	rx_2048b_4095b_frames;
+	__le64	rx_4096b_9216b_frames;
+	__le64	rx_9217b_16383b_frames;
+	__le64	rx_total_frames;
+	__le64	rx_ucast_frames;
+	__le64	rx_mcast_frames;
+	__le64	rx_bcast_frames;
+	__le64	rx_fcs_err_frames;
+	__le64	rx_ctrl_frames;
+	__le64	rx_pause_frames;
+	__le64	rx_pfc_frames;
+	__le64	rx_unsupported_opcode_frames;
+	__le64	rx_unsupported_da_pausepfc_frames;
+	__le64	rx_wrong_sa_frames;
+	__le64	rx_align_err_frames;
+	__le64	rx_oor_len_frames;
+	__le64	rx_code_err_frames;
+	__le64	rx_false_carrier_frames;
+	__le64	rx_ovrsz_frames;
+	__le64	rx_jbr_frames;
+	__le64	rx_mtu_err_frames;
+	__le64	rx_match_crc_frames;
+	__le64	rx_promiscuous_frames;
+	__le64	rx_tagged_frames;
+	__le64	rx_double_tagged_frames;
+	__le64	rx_trunc_frames;
+	__le64	rx_good_frames;
+	__le64	rx_pfc_xon2xoff_frames_pri0;
+	__le64	rx_pfc_xon2xoff_frames_pri1;
+	__le64	rx_pfc_xon2xoff_frames_pri2;
+	__le64	rx_pfc_xon2xoff_frames_pri3;
+	__le64	rx_pfc_xon2xoff_frames_pri4;
+	__le64	rx_pfc_xon2xoff_frames_pri5;
+	__le64	rx_pfc_xon2xoff_frames_pri6;
+	__le64	rx_pfc_xon2xoff_frames_pri7;
+	__le64	rx_pfc_ena_frames_pri0;
+	__le64	rx_pfc_ena_frames_pri1;
+	__le64	rx_pfc_ena_frames_pri2;
+	__le64	rx_pfc_ena_frames_pri3;
+	__le64	rx_pfc_ena_frames_pri4;
+	__le64	rx_pfc_ena_frames_pri5;
+	__le64	rx_pfc_ena_frames_pri6;
+	__le64	rx_pfc_ena_frames_pri7;
+	__le64	rx_sch_crc_err_frames;
+	__le64	rx_undrsz_frames;
+	__le64	rx_frag_frames;
+	__le64	rx_eee_lpi_events;
+	__le64	rx_eee_lpi_duration;
+	__le64	rx_llfc_physical_msgs;
+	__le64	rx_llfc_logical_msgs;
+	__le64	rx_llfc_msgs_with_crc_err;
+	__le64	rx_hcfc_msgs;
+	__le64	rx_hcfc_msgs_with_crc_err;
+	__le64	rx_bytes;
+	__le64	rx_runt_bytes;
+	__le64	rx_runt_frames;
+	__le64	rx_stat_discard;
+	__le64	rx_stat_err;
+};
+
 /* hwrm_port_qstats_input (size:320b/40B) */
 struct hwrm_port_qstats_input {
 	__le16	req_type;
@@ -2039,6 +2543,83 @@ struct hwrm_port_qstats_output {
 	u8	valid;
 };
 
+/* tx_port_stats_ext (size:2048b/256B) */
+struct tx_port_stats_ext {
+	__le64	tx_bytes_cos0;
+	__le64	tx_bytes_cos1;
+	__le64	tx_bytes_cos2;
+	__le64	tx_bytes_cos3;
+	__le64	tx_bytes_cos4;
+	__le64	tx_bytes_cos5;
+	__le64	tx_bytes_cos6;
+	__le64	tx_bytes_cos7;
+	__le64	tx_packets_cos0;
+	__le64	tx_packets_cos1;
+	__le64	tx_packets_cos2;
+	__le64	tx_packets_cos3;
+	__le64	tx_packets_cos4;
+	__le64	tx_packets_cos5;
+	__le64	tx_packets_cos6;
+	__le64	tx_packets_cos7;
+	__le64	pfc_pri0_tx_duration_us;
+	__le64	pfc_pri0_tx_transitions;
+	__le64	pfc_pri1_tx_duration_us;
+	__le64	pfc_pri1_tx_transitions;
+	__le64	pfc_pri2_tx_duration_us;
+	__le64	pfc_pri2_tx_transitions;
+	__le64	pfc_pri3_tx_duration_us;
+	__le64	pfc_pri3_tx_transitions;
+	__le64	pfc_pri4_tx_duration_us;
+	__le64	pfc_pri4_tx_transitions;
+	__le64	pfc_pri5_tx_duration_us;
+	__le64	pfc_pri5_tx_transitions;
+	__le64	pfc_pri6_tx_duration_us;
+	__le64	pfc_pri6_tx_transitions;
+	__le64	pfc_pri7_tx_duration_us;
+	__le64	pfc_pri7_tx_transitions;
+};
+
+/* rx_port_stats_ext (size:2368b/296B) */
+struct rx_port_stats_ext {
+	__le64	link_down_events;
+	__le64	continuous_pause_events;
+	__le64	resume_pause_events;
+	__le64	continuous_roce_pause_events;
+	__le64	resume_roce_pause_events;
+	__le64	rx_bytes_cos0;
+	__le64	rx_bytes_cos1;
+	__le64	rx_bytes_cos2;
+	__le64	rx_bytes_cos3;
+	__le64	rx_bytes_cos4;
+	__le64	rx_bytes_cos5;
+	__le64	rx_bytes_cos6;
+	__le64	rx_bytes_cos7;
+	__le64	rx_packets_cos0;
+	__le64	rx_packets_cos1;
+	__le64	rx_packets_cos2;
+	__le64	rx_packets_cos3;
+	__le64	rx_packets_cos4;
+	__le64	rx_packets_cos5;
+	__le64	rx_packets_cos6;
+	__le64	rx_packets_cos7;
+	__le64	pfc_pri0_rx_duration_us;
+	__le64	pfc_pri0_rx_transitions;
+	__le64	pfc_pri1_rx_duration_us;
+	__le64	pfc_pri1_rx_transitions;
+	__le64	pfc_pri2_rx_duration_us;
+	__le64	pfc_pri2_rx_transitions;
+	__le64	pfc_pri3_rx_duration_us;
+	__le64	pfc_pri3_rx_transitions;
+	__le64	pfc_pri4_rx_duration_us;
+	__le64	pfc_pri4_rx_transitions;
+	__le64	pfc_pri5_rx_duration_us;
+	__le64	pfc_pri5_rx_transitions;
+	__le64	pfc_pri6_rx_duration_us;
+	__le64	pfc_pri6_rx_transitions;
+	__le64	pfc_pri7_rx_duration_us;
+	__le64	pfc_pri7_rx_transitions;
+};
+
 /* hwrm_port_qstats_ext_input (size:320b/40B) */
 struct hwrm_port_qstats_ext_input {
 	__le16	req_type;
@@ -2062,7 +2643,8 @@ struct hwrm_port_qstats_ext_output {
 	__le16	resp_len;
 	__le16	tx_stat_size;
 	__le16	rx_stat_size;
-	u8	unused_0[3];
+	__le16	total_active_cos_queues;
+	u8	unused_0;
 	u8	valid;
 };
 
@@ -2153,9 +2735,10 @@ struct hwrm_port_phy_qcaps_output {
 	__le16	seq_id;
 	__le16	resp_len;
 	u8	flags;
-	#define PORT_PHY_QCAPS_RESP_FLAGS_EEE_SUPPORTED     0x1UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_MASK        0xfeUL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_SFT         1
+	#define PORT_PHY_QCAPS_RESP_FLAGS_EEE_SUPPORTED               0x1UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_EXTERNAL_LPBK_SUPPORTED     0x2UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_MASK                  0xfcUL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_SFT                   2
 	u8	port_cnt;
 	#define PORT_PHY_QCAPS_RESP_PORT_CNT_UNKNOWN 0x0UL
 	#define PORT_PHY_QCAPS_RESP_PORT_CNT_1       0x1UL
@@ -2612,6 +3195,7 @@ struct hwrm_queue_qportcfg_output {
 	u8	queue_id0;
 	u8	queue_id0_service_profile;
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS       0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
@@ -2620,6 +3204,7 @@ struct hwrm_queue_qportcfg_output {
 	u8	queue_id1;
 	u8	queue_id1_service_profile;
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS       0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
@@ -2628,6 +3213,7 @@ struct hwrm_queue_qportcfg_output {
 	u8	queue_id2;
 	u8	queue_id2_service_profile;
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS       0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
@@ -2636,6 +3222,7 @@ struct hwrm_queue_qportcfg_output {
 	u8	queue_id3;
 	u8	queue_id3_service_profile;
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS       0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
@@ -2644,6 +3231,7 @@ struct hwrm_queue_qportcfg_output {
 	u8	queue_id4;
 	u8	queue_id4_service_profile;
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS       0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
@@ -2652,6 +3240,7 @@ struct hwrm_queue_qportcfg_output {
 	u8	queue_id5;
 	u8	queue_id5_service_profile;
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS       0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
@@ -2660,6 +3249,7 @@ struct hwrm_queue_qportcfg_output {
 	u8	queue_id6;
 	u8	queue_id6_service_profile;
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS       0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
@@ -2668,6 +3258,7 @@ struct hwrm_queue_qportcfg_output {
 	u8	queue_id7;
 	u8	queue_id7_service_profile;
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS       0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
@@ -3689,18 +4280,21 @@ struct hwrm_vnic_cfg_input {
 	#define VNIC_CFG_REQ_FLAGS_RSS_DFLT_CR_MODE                     0x20UL
 	#define VNIC_CFG_REQ_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_MODE     0x40UL
 	__le32	enables;
-	#define VNIC_CFG_REQ_ENABLES_DFLT_RING_GRP     0x1UL
-	#define VNIC_CFG_REQ_ENABLES_RSS_RULE          0x2UL
-	#define VNIC_CFG_REQ_ENABLES_COS_RULE          0x4UL
-	#define VNIC_CFG_REQ_ENABLES_LB_RULE           0x8UL
-	#define VNIC_CFG_REQ_ENABLES_MRU               0x10UL
+	#define VNIC_CFG_REQ_ENABLES_DFLT_RING_GRP            0x1UL
+	#define VNIC_CFG_REQ_ENABLES_RSS_RULE                 0x2UL
+	#define VNIC_CFG_REQ_ENABLES_COS_RULE                 0x4UL
+	#define VNIC_CFG_REQ_ENABLES_LB_RULE                  0x8UL
+	#define VNIC_CFG_REQ_ENABLES_MRU                      0x10UL
+	#define VNIC_CFG_REQ_ENABLES_DEFAULT_RX_RING_ID       0x20UL
+	#define VNIC_CFG_REQ_ENABLES_DEFAULT_CMPL_RING_ID     0x40UL
 	__le16	vnic_id;
 	__le16	dflt_ring_grp;
 	__le16	rss_rule;
 	__le16	cos_rule;
 	__le16	lb_rule;
 	__le16	mru;
-	u8	unused_0[4];
+	__le16	default_rx_ring_id;
+	__le16	default_cmpl_ring_id;
 };
 
 /* hwrm_vnic_cfg_output (size:128b/16B) */
@@ -3740,6 +4334,7 @@ struct hwrm_vnic_qcaps_output {
 	#define VNIC_QCAPS_RESP_FLAGS_ROCE_ONLY_VNIC_CAP                  0x10UL
 	#define VNIC_QCAPS_RESP_FLAGS_RSS_DFLT_CR_CAP                     0x20UL
 	#define VNIC_QCAPS_RESP_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_CAP     0x40UL
+	#define VNIC_QCAPS_RESP_FLAGS_OUTERMOST_RSS_CAP                   0x80UL
 	u8	unused_1[7];
 	u8	valid;
 };
@@ -3857,7 +4452,14 @@ struct hwrm_vnic_rss_cfg_input {
 	#define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6         0x8UL
 	#define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6     0x10UL
 	#define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6     0x20UL
-	u8	unused_0[4];
+	__le16	vnic_id;
+	u8	ring_table_pair_index;
+	u8	hash_mode_flags;
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT         0x1UL
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_INNERMOST_4     0x2UL
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_INNERMOST_2     0x4UL
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_OUTERMOST_4     0x8UL
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_OUTERMOST_2     0x10UL
 	__le64	ring_grp_tbl_addr;
 	__le64	hash_key_tbl_addr;
 	__le16	rss_ctx_idx;
@@ -3950,7 +4552,7 @@ struct hwrm_vnic_rss_cos_lb_ctx_free_output {
 	u8	valid;
 };
 
-/* hwrm_ring_alloc_input (size:640b/80B) */
+/* hwrm_ring_alloc_input (size:704b/88B) */
 struct hwrm_ring_alloc_input {
 	__le16	req_type;
 	__le16	cmpl_ring;
@@ -3961,12 +4563,17 @@ struct hwrm_ring_alloc_input {
 	#define RING_ALLOC_REQ_ENABLES_RING_ARB_CFG          0x2UL
 	#define RING_ALLOC_REQ_ENABLES_STAT_CTX_ID_VALID     0x8UL
 	#define RING_ALLOC_REQ_ENABLES_MAX_BW_VALID          0x20UL
+	#define RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID      0x40UL
+	#define RING_ALLOC_REQ_ENABLES_NQ_RING_ID_VALID      0x80UL
+	#define RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID     0x100UL
 	u8	ring_type;
 	#define RING_ALLOC_REQ_RING_TYPE_L2_CMPL   0x0UL
 	#define RING_ALLOC_REQ_RING_TYPE_TX        0x1UL
 	#define RING_ALLOC_REQ_RING_TYPE_RX        0x2UL
 	#define RING_ALLOC_REQ_RING_TYPE_ROCE_CMPL 0x3UL
-	#define RING_ALLOC_REQ_RING_TYPE_LAST     RING_ALLOC_REQ_RING_TYPE_ROCE_CMPL
+	#define RING_ALLOC_REQ_RING_TYPE_RX_AGG    0x4UL
+	#define RING_ALLOC_REQ_RING_TYPE_NQ        0x5UL
+	#define RING_ALLOC_REQ_RING_TYPE_LAST     RING_ALLOC_REQ_RING_TYPE_NQ
 	u8	unused_0[3];
 	__le64	page_tbl_addr;
 	__le32	fbo;
@@ -3977,8 +4584,9 @@ struct hwrm_ring_alloc_input {
 	__le16	logical_id;
 	__le16	cmpl_ring_id;
 	__le16	queue_id;
-	u8	unused_2[2];
-	__le32	reserved1;
+	__le16	rx_buf_size;
+	__le16	rx_ring_id;
+	__le16	nq_ring_id;
 	__le16	ring_arb_cfg;
 	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_MASK      0xfUL
 	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_SFT       0
@@ -4016,6 +4624,7 @@ struct hwrm_ring_alloc_input {
 	#define RING_ALLOC_REQ_INT_MODE_POLL   0x3UL
 	#define RING_ALLOC_REQ_INT_MODE_LAST  RING_ALLOC_REQ_INT_MODE_POLL
 	u8	unused_4[3];
+	__le64	cq_handle;
 };
 
 /* hwrm_ring_alloc_output (size:128b/16B) */
@@ -4042,7 +4651,9 @@ struct hwrm_ring_free_input {
 	#define RING_FREE_REQ_RING_TYPE_TX        0x1UL
 	#define RING_FREE_REQ_RING_TYPE_RX        0x2UL
 	#define RING_FREE_REQ_RING_TYPE_ROCE_CMPL 0x3UL
-	#define RING_FREE_REQ_RING_TYPE_LAST     RING_FREE_REQ_RING_TYPE_ROCE_CMPL
+	#define RING_FREE_REQ_RING_TYPE_RX_AGG    0x4UL
+	#define RING_FREE_REQ_RING_TYPE_NQ        0x5UL
+	#define RING_FREE_REQ_RING_TYPE_LAST     RING_FREE_REQ_RING_TYPE_NQ
 	u8	unused_0;
 	__le16	ring_id;
 	u8	unused_1[4];
@@ -4058,6 +4669,52 @@ struct hwrm_ring_free_output {
 	u8	valid;
 };
 
+/* hwrm_ring_aggint_qcaps_input (size:128b/16B) */
+struct hwrm_ring_aggint_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_ring_aggint_qcaps_output (size:384b/48B) */
+struct hwrm_ring_aggint_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	cmpl_params;
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_INT_LAT_TMR_MIN                  0x1UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_INT_LAT_TMR_MAX                  0x2UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_TIMER_RESET                      0x4UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_RING_IDLE                        0x8UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_DMA_AGGR                0x10UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_DMA_AGGR_DURING_INT     0x20UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_CMPL_AGGR_DMA_TMR                0x40UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_CMPL_AGGR_DMA_TMR_DURING_INT     0x80UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_AGGR_INT                0x100UL
+	__le32	nq_params;
+	#define RING_AGGINT_QCAPS_RESP_NQ_PARAMS_INT_LAT_TMR_MIN     0x1UL
+	__le16	num_cmpl_dma_aggr_min;
+	__le16	num_cmpl_dma_aggr_max;
+	__le16	num_cmpl_dma_aggr_during_int_min;
+	__le16	num_cmpl_dma_aggr_during_int_max;
+	__le16	cmpl_aggr_dma_tmr_min;
+	__le16	cmpl_aggr_dma_tmr_max;
+	__le16	cmpl_aggr_dma_tmr_during_int_min;
+	__le16	cmpl_aggr_dma_tmr_during_int_max;
+	__le16	int_lat_tmr_min_min;
+	__le16	int_lat_tmr_min_max;
+	__le16	int_lat_tmr_max_min;
+	__le16	int_lat_tmr_max_max;
+	__le16	num_cmpl_aggr_int_min;
+	__le16	num_cmpl_aggr_int_max;
+	__le16	timer_units;
+	u8	unused_0[1];
+	u8	valid;
+};
+
 /* hwrm_ring_cmpl_ring_qaggint_params_input (size:192b/24B) */
 struct hwrm_ring_cmpl_ring_qaggint_params_input {
 	__le16	req_type;
@@ -4100,6 +4757,7 @@ struct hwrm_ring_cmpl_ring_cfg_aggint_params_input {
 	__le16	flags;
 	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_TIMER_RESET     0x1UL
 	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_RING_IDLE       0x2UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_IS_NQ           0x4UL
 	__le16	num_cmpl_dma_aggr;
 	__le16	num_cmpl_dma_aggr_during_int;
 	__le16	cmpl_aggr_dma_tmr;
@@ -4107,7 +4765,14 @@ struct hwrm_ring_cmpl_ring_cfg_aggint_params_input {
 	__le16	int_lat_tmr_min;
 	__le16	int_lat_tmr_max;
 	__le16	num_cmpl_aggr_int;
-	u8	unused_0[6];
+	__le16	enables;
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_DMA_AGGR                0x1UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_DMA_AGGR_DURING_INT     0x2UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_CMPL_AGGR_DMA_TMR                0x4UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_INT_LAT_TMR_MIN                  0x8UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_INT_LAT_TMR_MAX                  0x10UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_AGGR_INT                0x20UL
+	u8	unused_0[4];
 };
 
 /* hwrm_ring_cmpl_ring_cfg_aggint_params_output (size:128b/16B) */
@@ -4120,34 +4785,6 @@ struct hwrm_ring_cmpl_ring_cfg_aggint_params_output {
 	u8	valid;
 };
 
-/* hwrm_ring_reset_input (size:192b/24B) */
-struct hwrm_ring_reset_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	ring_type;
-	#define RING_RESET_REQ_RING_TYPE_L2_CMPL   0x0UL
-	#define RING_RESET_REQ_RING_TYPE_TX        0x1UL
-	#define RING_RESET_REQ_RING_TYPE_RX        0x2UL
-	#define RING_RESET_REQ_RING_TYPE_ROCE_CMPL 0x3UL
-	#define RING_RESET_REQ_RING_TYPE_LAST     RING_RESET_REQ_RING_TYPE_ROCE_CMPL
-	u8	unused_0;
-	__le16	ring_id;
-	u8	unused_1[4];
-};
-
-/* hwrm_ring_reset_output (size:128b/16B) */
-struct hwrm_ring_reset_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
 /* hwrm_ring_grp_alloc_input (size:192b/24B) */
 struct hwrm_ring_grp_alloc_input {
 	__le16	req_type;
@@ -5032,7 +5669,8 @@ struct hwrm_tunnel_dst_port_query_input {
 	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN    0x1UL
 	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GENEVE   0x5UL
 	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST    TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST    TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE_V1
 	u8	unused_0[7];
 };
 
@@ -5059,7 +5697,8 @@ struct hwrm_tunnel_dst_port_alloc_input {
 	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN    0x1UL
 	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE   0x5UL
 	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST    TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST    TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1
 	u8	unused_0;
 	__be16	tunnel_dst_port_val;
 	u8	unused_1[4];
@@ -5087,7 +5726,8 @@ struct hwrm_tunnel_dst_port_free_input {
 	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN    0x1UL
 	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE   0x5UL
 	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST    TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST    TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE_V1
 	u8	unused_0;
 	__le16	tunnel_dst_port_id;
 	u8	unused_1[4];
@@ -5259,140 +5899,6 @@ struct hwrm_pcie_qstats_output {
 	u8	valid;
 };
 
-/* tx_port_stats (size:3264b/408B) */
-struct tx_port_stats {
-	__le64	tx_64b_frames;
-	__le64	tx_65b_127b_frames;
-	__le64	tx_128b_255b_frames;
-	__le64	tx_256b_511b_frames;
-	__le64	tx_512b_1023b_frames;
-	__le64	tx_1024b_1518_frames;
-	__le64	tx_good_vlan_frames;
-	__le64	tx_1519b_2047_frames;
-	__le64	tx_2048b_4095b_frames;
-	__le64	tx_4096b_9216b_frames;
-	__le64	tx_9217b_16383b_frames;
-	__le64	tx_good_frames;
-	__le64	tx_total_frames;
-	__le64	tx_ucast_frames;
-	__le64	tx_mcast_frames;
-	__le64	tx_bcast_frames;
-	__le64	tx_pause_frames;
-	__le64	tx_pfc_frames;
-	__le64	tx_jabber_frames;
-	__le64	tx_fcs_err_frames;
-	__le64	tx_control_frames;
-	__le64	tx_oversz_frames;
-	__le64	tx_single_dfrl_frames;
-	__le64	tx_multi_dfrl_frames;
-	__le64	tx_single_coll_frames;
-	__le64	tx_multi_coll_frames;
-	__le64	tx_late_coll_frames;
-	__le64	tx_excessive_coll_frames;
-	__le64	tx_frag_frames;
-	__le64	tx_err;
-	__le64	tx_tagged_frames;
-	__le64	tx_dbl_tagged_frames;
-	__le64	tx_runt_frames;
-	__le64	tx_fifo_underruns;
-	__le64	tx_pfc_ena_frames_pri0;
-	__le64	tx_pfc_ena_frames_pri1;
-	__le64	tx_pfc_ena_frames_pri2;
-	__le64	tx_pfc_ena_frames_pri3;
-	__le64	tx_pfc_ena_frames_pri4;
-	__le64	tx_pfc_ena_frames_pri5;
-	__le64	tx_pfc_ena_frames_pri6;
-	__le64	tx_pfc_ena_frames_pri7;
-	__le64	tx_eee_lpi_events;
-	__le64	tx_eee_lpi_duration;
-	__le64	tx_llfc_logical_msgs;
-	__le64	tx_hcfc_msgs;
-	__le64	tx_total_collisions;
-	__le64	tx_bytes;
-	__le64	tx_xthol_frames;
-	__le64	tx_stat_discard;
-	__le64	tx_stat_error;
-};
-
-/* rx_port_stats (size:4224b/528B) */
-struct rx_port_stats {
-	__le64	rx_64b_frames;
-	__le64	rx_65b_127b_frames;
-	__le64	rx_128b_255b_frames;
-	__le64	rx_256b_511b_frames;
-	__le64	rx_512b_1023b_frames;
-	__le64	rx_1024b_1518_frames;
-	__le64	rx_good_vlan_frames;
-	__le64	rx_1519b_2047b_frames;
-	__le64	rx_2048b_4095b_frames;
-	__le64	rx_4096b_9216b_frames;
-	__le64	rx_9217b_16383b_frames;
-	__le64	rx_total_frames;
-	__le64	rx_ucast_frames;
-	__le64	rx_mcast_frames;
-	__le64	rx_bcast_frames;
-	__le64	rx_fcs_err_frames;
-	__le64	rx_ctrl_frames;
-	__le64	rx_pause_frames;
-	__le64	rx_pfc_frames;
-	__le64	rx_unsupported_opcode_frames;
-	__le64	rx_unsupported_da_pausepfc_frames;
-	__le64	rx_wrong_sa_frames;
-	__le64	rx_align_err_frames;
-	__le64	rx_oor_len_frames;
-	__le64	rx_code_err_frames;
-	__le64	rx_false_carrier_frames;
-	__le64	rx_ovrsz_frames;
-	__le64	rx_jbr_frames;
-	__le64	rx_mtu_err_frames;
-	__le64	rx_match_crc_frames;
-	__le64	rx_promiscuous_frames;
-	__le64	rx_tagged_frames;
-	__le64	rx_double_tagged_frames;
-	__le64	rx_trunc_frames;
-	__le64	rx_good_frames;
-	__le64	rx_pfc_xon2xoff_frames_pri0;
-	__le64	rx_pfc_xon2xoff_frames_pri1;
-	__le64	rx_pfc_xon2xoff_frames_pri2;
-	__le64	rx_pfc_xon2xoff_frames_pri3;
-	__le64	rx_pfc_xon2xoff_frames_pri4;
-	__le64	rx_pfc_xon2xoff_frames_pri5;
-	__le64	rx_pfc_xon2xoff_frames_pri6;
-	__le64	rx_pfc_xon2xoff_frames_pri7;
-	__le64	rx_pfc_ena_frames_pri0;
-	__le64	rx_pfc_ena_frames_pri1;
-	__le64	rx_pfc_ena_frames_pri2;
-	__le64	rx_pfc_ena_frames_pri3;
-	__le64	rx_pfc_ena_frames_pri4;
-	__le64	rx_pfc_ena_frames_pri5;
-	__le64	rx_pfc_ena_frames_pri6;
-	__le64	rx_pfc_ena_frames_pri7;
-	__le64	rx_sch_crc_err_frames;
-	__le64	rx_undrsz_frames;
-	__le64	rx_frag_frames;
-	__le64	rx_eee_lpi_events;
-	__le64	rx_eee_lpi_duration;
-	__le64	rx_llfc_physical_msgs;
-	__le64	rx_llfc_logical_msgs;
-	__le64	rx_llfc_msgs_with_crc_err;
-	__le64	rx_hcfc_msgs;
-	__le64	rx_hcfc_msgs_with_crc_err;
-	__le64	rx_bytes;
-	__le64	rx_runt_bytes;
-	__le64	rx_runt_frames;
-	__le64	rx_stat_discard;
-	__le64	rx_stat_err;
-};
-
-/* rx_port_stats_ext (size:320b/40B) */
-struct rx_port_stats_ext {
-	__le64	link_down_events;
-	__le64	continuous_pause_events;
-	__le64	resume_pause_events;
-	__le64	continuous_roce_pause_events;
-	__le64	resume_roce_pause_events;
-};
-
 /* pcie_ctx_hw_stats (size:768b/96B) */
 struct pcie_ctx_hw_stats {
 	__le64	pcie_pl_signal_integrity;
@@ -5884,6 +6390,114 @@ struct hwrm_wol_reason_qcfg_output {
 	u8	valid;
 };
 
+/* coredump_segment_record (size:128b/16B) */
+struct coredump_segment_record {
+	__le16	component_id;
+	__le16	segment_id;
+	__le16	max_instances;
+	u8	version_hi;
+	u8	version_low;
+	u8	seg_flags;
+	u8	unused_0[7];
+};
+
+/* hwrm_dbg_coredump_list_input (size:256b/32B) */
+struct hwrm_dbg_coredump_list_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	host_dest_addr;
+	__le32	host_buf_len;
+	__le16	seq_no;
+	u8	unused_0[2];
+};
+
+/* hwrm_dbg_coredump_list_output (size:128b/16B) */
+struct hwrm_dbg_coredump_list_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define DBG_COREDUMP_LIST_RESP_FLAGS_MORE     0x1UL
+	u8	unused_0;
+	__le16	total_segments;
+	__le16	data_len;
+	u8	unused_1;
+	u8	valid;
+};
+
+/* hwrm_dbg_coredump_initiate_input (size:256b/32B) */
+struct hwrm_dbg_coredump_initiate_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	component_id;
+	__le16	segment_id;
+	__le16	instance;
+	__le16	unused_0;
+	u8	seg_flags;
+	u8	unused_1[7];
+};
+
+/* hwrm_dbg_coredump_initiate_output (size:128b/16B) */
+struct hwrm_dbg_coredump_initiate_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* coredump_data_hdr (size:128b/16B) */
+struct coredump_data_hdr {
+	__le32	address;
+	__le32	flags_length;
+	__le32	instance;
+	__le32	next_offset;
+};
+
+/* hwrm_dbg_coredump_retrieve_input (size:448b/56B) */
+struct hwrm_dbg_coredump_retrieve_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	host_dest_addr;
+	__le32	host_buf_len;
+	__le32	unused_0;
+	__le16	component_id;
+	__le16	segment_id;
+	__le16	instance;
+	__le16	unused_1;
+	u8	seg_flags;
+	u8	unused_2;
+	__le16	unused_3;
+	__le32	unused_4;
+	__le32	seq_no;
+	__le32	unused_5;
+};
+
+/* hwrm_dbg_coredump_retrieve_output (size:128b/16B) */
+struct hwrm_dbg_coredump_retrieve_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define DBG_COREDUMP_RETRIEVE_RESP_FLAGS_MORE     0x1UL
+	u8	unused_0;
+	__le16	data_len;
+	u8	unused_1[3];
+	u8	valid;
+};
+
 /* hwrm_nvm_read_input (size:320b/40B) */
 struct hwrm_nvm_read_input {
 	__le16	req_type;
@@ -6269,12 +6883,14 @@ struct hwrm_nvm_set_variable_input {
 	__le16	index_2;
 	__le16	index_3;
 	u8	flags;
-	#define NVM_SET_VARIABLE_REQ_FLAGS_FORCE_FLUSH           0x1UL
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_MASK     0xeUL
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_SFT      1
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_NONE       (0x0UL << 1)
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1  (0x1UL << 1)
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_LAST      NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1
+	#define NVM_SET_VARIABLE_REQ_FLAGS_FORCE_FLUSH                0x1UL
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_MASK          0xeUL
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_SFT           1
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_NONE            (0x0UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1       (0x1UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_AES256          (0x2UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1_AUTH  (0x3UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_LAST           NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1_AUTH
 	u8	unused_0;
 };
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index a64910892c25..6d583bcd2a81 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -447,7 +447,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs)
 	u16 vf_tx_rings, vf_rx_rings, vf_cp_rings;
 	u16 vf_stat_ctx, vf_vnics, vf_ring_grps;
 	struct bnxt_pf_info *pf = &bp->pf;
-	int i, rc = 0;
+	int i, rc = 0, min = 1;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_VF_RESOURCE_CFG, -1, -1);
 
@@ -464,14 +464,19 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs)
 
 	req.min_rsscos_ctx = cpu_to_le16(BNXT_VF_MIN_RSS_CTX);
 	req.max_rsscos_ctx = cpu_to_le16(BNXT_VF_MAX_RSS_CTX);
-	if (pf->vf_resv_strategy == BNXT_VF_RESV_STRATEGY_MINIMAL) {
-		req.min_cmpl_rings = cpu_to_le16(1);
-		req.min_tx_rings = cpu_to_le16(1);
-		req.min_rx_rings = cpu_to_le16(1);
-		req.min_l2_ctxs = cpu_to_le16(BNXT_VF_MIN_L2_CTX);
-		req.min_vnics = cpu_to_le16(1);
-		req.min_stat_ctx = cpu_to_le16(1);
-		req.min_hw_ring_grps = cpu_to_le16(1);
+	if (pf->vf_resv_strategy == BNXT_VF_RESV_STRATEGY_MINIMAL_STATIC) {
+		min = 0;
+		req.min_rsscos_ctx = cpu_to_le16(min);
+	}
+	if (pf->vf_resv_strategy == BNXT_VF_RESV_STRATEGY_MINIMAL ||
+	    pf->vf_resv_strategy == BNXT_VF_RESV_STRATEGY_MINIMAL_STATIC) {
+		req.min_cmpl_rings = cpu_to_le16(min);
+		req.min_tx_rings = cpu_to_le16(min);
+		req.min_rx_rings = cpu_to_le16(min);
+		req.min_l2_ctxs = cpu_to_le16(min);
+		req.min_vnics = cpu_to_le16(min);
+		req.min_stat_ctx = cpu_to_le16(min);
+		req.min_hw_ring_grps = cpu_to_le16(min);
 	} else {
 		vf_cp_rings /= num_vfs;
 		vf_tx_rings /= num_vfs;
@@ -618,7 +623,7 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs)
 
 static int bnxt_func_cfg(struct bnxt *bp, int num_vfs)
 {
-	if (bp->flags & BNXT_FLAG_NEW_RM)
+	if (BNXT_NEW_RM(bp))
 		return bnxt_hwrm_func_vf_resc_cfg(bp, num_vfs);
 	else
 		return bnxt_hwrm_func_cfg(bp, num_vfs);
@@ -956,9 +961,13 @@ static int bnxt_vf_validate_set_mac(struct bnxt *bp, struct bnxt_vf_info *vf)
 	} else if (is_valid_ether_addr(vf->vf_mac_addr)) {
 		if (ether_addr_equal((const u8 *)req->l2_addr, vf->vf_mac_addr))
 			mac_ok = true;
-	} else if (bp->hwrm_spec_code < 0x10202) {
-		mac_ok = true;
 	} else {
+		/* There are two cases:
+		 * 1.If firmware spec < 0x10202,VF MAC address is not forwarded
+		 *   to the PF and so it doesn't have to match
+		 * 2.Allow VF to modify it's own MAC when PF has not assigned a
+		 *   valid MAC address and firmware spec >= 0x10202
+		 */
 		mac_ok = true;
 	}
 	if (mac_ok)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index 491bd40a254d..139d96c5a023 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -1568,22 +1568,16 @@ void bnxt_tc_flow_stats_work(struct bnxt *bp)
 int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
 			 struct tc_cls_flower_offload *cls_flower)
 {
-	int rc = 0;
-
 	switch (cls_flower->command) {
 	case TC_CLSFLOWER_REPLACE:
-		rc = bnxt_tc_add_flow(bp, src_fid, cls_flower);
-		break;
-
+		return bnxt_tc_add_flow(bp, src_fid, cls_flower);
 	case TC_CLSFLOWER_DESTROY:
-		rc = bnxt_tc_del_flow(bp, cls_flower);
-		break;
-
+		return bnxt_tc_del_flow(bp, cls_flower);
 	case TC_CLSFLOWER_STATS:
-		rc = bnxt_tc_get_flow_stats(bp, cls_flower);
-		break;
+		return bnxt_tc_get_flow_stats(bp, cls_flower);
+	default:
+		return -EOPNOTSUPP;
 	}
-	return rc;
 }
 
 static const struct rhashtable_params bnxt_tc_flow_ht_params = {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 840f6e505f73..c37b2842f972 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -141,7 +141,7 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id,
 	if (avail_msix > num_msix)
 		avail_msix = num_msix;
 
-	if (bp->flags & BNXT_FLAG_NEW_RM) {
+	if (BNXT_NEW_RM(bp)) {
 		idx = bp->cp_nr_rings;
 	} else {
 		max_idx = min_t(int, bp->total_irqs, max_cp_rings);
@@ -162,7 +162,7 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id,
 		return -EAGAIN;
 	}
 
-	if (bp->flags & BNXT_FLAG_NEW_RM) {
+	if (BNXT_NEW_RM(bp)) {
 		struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 
 		avail_msix = hw_resc->resv_cp_rings - bp->cp_nr_rings;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
index 05d405905906..e31f5d803c13 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -173,7 +173,7 @@ static int bnxt_vf_rep_setup_tc_block(struct net_device *dev,
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block,
 					     bnxt_vf_rep_setup_tc_block_cb,
-					     vf_rep, vf_rep);
+					     vf_rep, vf_rep, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block,
 					bnxt_vf_rep_setup_tc_block_cb, vf_rep);
@@ -543,9 +543,14 @@ int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode)
 		break;
 
 	case DEVLINK_ESWITCH_MODE_SWITCHDEV:
+		if (bp->hwrm_spec_code < 0x10803) {
+			netdev_warn(bp->dev, "FW does not support SRIOV E-Switch SWITCHDEV mode\n");
+			rc = -ENOTSUPP;
+			goto done;
+		}
+
 		if (pci_num_vf(bp->pdev) == 0) {
-			netdev_info(bp->dev,
-				    "Enable VFs before setting switchdev mode");
+			netdev_info(bp->dev, "Enable VFs before setting switchdev mode");
 			rc = -EPERM;
 			goto done;
 		}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 1f0e872d0667..0584d07c8c33 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -219,7 +219,6 @@ int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		rc = bnxt_xdp_set(bp, xdp->prog);
 		break;
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!bp->xdp_prog;
 		xdp->prog_id = bp->xdp_prog ? bp->xdp_prog->aux->id : 0;
 		rc = 0;
 		break;
diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index 4fd829b5e65d..d83233ae4a15 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -2562,7 +2562,6 @@ static void cnic_bnx2x_delete_wait(struct cnic_dev *dev, u32 start_cid)
 
 static int cnic_bnx2x_fcoe_fw_destroy(struct cnic_dev *dev, struct kwqe *kwqe)
 {
-	struct fcoe_kwqe_destroy *req;
 	union l5cm_specific_data l5_data;
 	struct cnic_local *cp = dev->cnic_priv;
 	struct bnx2x *bp = netdev_priv(dev->netdev);
@@ -2571,7 +2570,6 @@ static int cnic_bnx2x_fcoe_fw_destroy(struct cnic_dev *dev, struct kwqe *kwqe)
 
 	cnic_bnx2x_delete_wait(dev, MAX_ISCSI_TBL_SZ);
 
-	req = (struct fcoe_kwqe_destroy *) kwqe;
 	cid = BNX2X_HW_CID(bp, cp->fcoe_init_cid);
 
 	memset(&l5_data, 0, sizeof(l5_data));
@@ -4090,7 +4088,7 @@ static void cnic_cm_free_mem(struct cnic_dev *dev)
 {
 	struct cnic_local *cp = dev->cnic_priv;
 
-	kfree(cp->csk_tbl);
+	kvfree(cp->csk_tbl);
 	cp->csk_tbl = NULL;
 	cnic_free_id_tbl(&cp->csk_port_tbl);
 }
@@ -4100,8 +4098,8 @@ static int cnic_cm_alloc_mem(struct cnic_dev *dev)
 	struct cnic_local *cp = dev->cnic_priv;
 	u32 port_id;
 
-	cp->csk_tbl = kcalloc(MAX_CM_SK_TBL_SZ, sizeof(struct cnic_sock),
-			      GFP_KERNEL);
+	cp->csk_tbl = kvcalloc(MAX_CM_SK_TBL_SZ, sizeof(struct cnic_sock),
+			       GFP_KERNEL);
 	if (!cp->csk_tbl)
 		return -ENOMEM;
 
@@ -5091,13 +5089,12 @@ static int cnic_start_bnx2x_hw(struct cnic_dev *dev)
 	struct cnic_local *cp = dev->cnic_priv;
 	struct bnx2x *bp = netdev_priv(dev->netdev);
 	struct cnic_eth_dev *ethdev = cp->ethdev;
-	int func, ret;
+	int ret;
 	u32 pfid;
 
 	dev->stats_addr = ethdev->addr_drv_info_to_mcp;
 	cp->func = bp->pf_num;
 
-	func = CNIC_FUNC(cp);
 	pfid = bp->pfid;
 
 	ret = cnic_init_id_tbl(&cp->cid_tbl, MAX_ISCSI_TBL_SZ,
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index aa1374d0af93..e6f28c7942ab 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -54,6 +54,7 @@
 #include <linux/ssb/ssb_driver_gige.h>
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
+#include <linux/crc32poly.h>
 
 #include <net/checksum.h>
 #include <net/ip.h>
@@ -725,6 +726,7 @@ static int tg3_ape_lock(struct tg3 *tp, int locknum)
 	case TG3_APE_LOCK_GPIO:
 		if (tg3_asic_rev(tp) == ASIC_REV_5761)
 			return 0;
+		/* else: fall through */
 	case TG3_APE_LOCK_GRC:
 	case TG3_APE_LOCK_MEM:
 		if (!tp->pci_fn)
@@ -785,6 +787,7 @@ static void tg3_ape_unlock(struct tg3 *tp, int locknum)
 	case TG3_APE_LOCK_GPIO:
 		if (tg3_asic_rev(tp) == ASIC_REV_5761)
 			return;
+		/* else: fall through */
 	case TG3_APE_LOCK_GRC:
 	case TG3_APE_LOCK_MEM:
 		if (!tp->pci_fn)
@@ -9720,7 +9723,7 @@ static inline u32 calc_crc(unsigned char *buf, int len)
 			reg >>= 1;
 
 			if (tmp)
-				reg ^= 0xedb88320;
+				reg ^= CRC32_POLY_LE;
 		}
 	}
 
@@ -10719,28 +10722,40 @@ static int tg3_reset_hw(struct tg3 *tp, bool reset_phy)
 	switch (limit) {
 	case 16:
 		tw32(MAC_RCV_RULE_15,  0); tw32(MAC_RCV_VALUE_15,  0);
+		/* fall through */
 	case 15:
 		tw32(MAC_RCV_RULE_14,  0); tw32(MAC_RCV_VALUE_14,  0);
+		/* fall through */
 	case 14:
 		tw32(MAC_RCV_RULE_13,  0); tw32(MAC_RCV_VALUE_13,  0);
+		/* fall through */
 	case 13:
 		tw32(MAC_RCV_RULE_12,  0); tw32(MAC_RCV_VALUE_12,  0);
+		/* fall through */
 	case 12:
 		tw32(MAC_RCV_RULE_11,  0); tw32(MAC_RCV_VALUE_11,  0);
+		/* fall through */
 	case 11:
 		tw32(MAC_RCV_RULE_10,  0); tw32(MAC_RCV_VALUE_10,  0);
+		/* fall through */
 	case 10:
 		tw32(MAC_RCV_RULE_9,  0); tw32(MAC_RCV_VALUE_9,  0);
+		/* fall through */
 	case 9:
 		tw32(MAC_RCV_RULE_8,  0); tw32(MAC_RCV_VALUE_8,  0);
+		/* fall through */
 	case 8:
 		tw32(MAC_RCV_RULE_7,  0); tw32(MAC_RCV_VALUE_7,  0);
+		/* fall through */
 	case 7:
 		tw32(MAC_RCV_RULE_6,  0); tw32(MAC_RCV_VALUE_6,  0);
+		/* fall through */
 	case 6:
 		tw32(MAC_RCV_RULE_5,  0); tw32(MAC_RCV_VALUE_5,  0);
+		/* fall through */
 	case 5:
 		tw32(MAC_RCV_RULE_4,  0); tw32(MAC_RCV_VALUE_4,  0);
+		/* fall through */
 	case 4:
 		/* tw32(MAC_RCV_RULE_3,  0); tw32(MAC_RCV_VALUE_3,  0); */
 	case 3:
diff --git a/drivers/net/ethernet/cadence/Kconfig b/drivers/net/ethernet/cadence/Kconfig
index 427d65a1a126..b9984015ca8c 100644
--- a/drivers/net/ethernet/cadence/Kconfig
+++ b/drivers/net/ethernet/cadence/Kconfig
@@ -2,7 +2,7 @@
 # Atmel device configuration
 #
 
-config NET_CADENCE
+config NET_VENDOR_CADENCE
 	bool "Cadence devices"
 	depends on HAS_IOMEM
 	default y
@@ -16,7 +16,7 @@ config NET_CADENCE
 	  the remaining Atmel network card questions. If you say Y, you will be
 	  asked for your specific card in the following questions.
 
-if NET_CADENCE
+if NET_VENDOR_CADENCE
 
 config MACB
 	tristate "Cadence MACB/GEM support"
@@ -48,4 +48,4 @@ config MACB_PCI
 	  To compile this driver as a module, choose M here: the module
 	  will be called macb_pci.
 
-endif # NET_CADENCE
+endif # NET_VENDOR_CADENCE
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index a6c911bb5ce2..dc09f9a8a49b 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -10,6 +10,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 #include <linux/clk.h>
+#include <linux/crc32.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/kernel.h>
@@ -1565,6 +1566,9 @@ static unsigned int macb_tx_map(struct macb *bp,
 		if (i == queue->tx_head) {
 			ctrl |= MACB_BF(TX_LSO, lso_ctrl);
 			ctrl |= MACB_BF(TX_TCP_SEQ_SRC, seq_ctrl);
+			if ((bp->dev->features & NETIF_F_HW_CSUM) &&
+			    skb->ip_summed != CHECKSUM_PARTIAL && !lso_ctrl)
+				ctrl |= MACB_BIT(TX_NOCRC);
 		} else
 			/* Only set MSS/MFS on payload descriptors
 			 * (second or later descriptor)
@@ -1651,7 +1655,68 @@ static inline int macb_clear_csum(struct sk_buff *skb)
 	return 0;
 }
 
-static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev)
+{
+	bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb);
+	int padlen = ETH_ZLEN - (*skb)->len;
+	int headroom = skb_headroom(*skb);
+	int tailroom = skb_tailroom(*skb);
+	struct sk_buff *nskb;
+	u32 fcs;
+
+	if (!(ndev->features & NETIF_F_HW_CSUM) ||
+	    !((*skb)->ip_summed != CHECKSUM_PARTIAL) ||
+	    skb_shinfo(*skb)->gso_size)	/* Not available for GSO */
+		return 0;
+
+	if (padlen <= 0) {
+		/* FCS could be appeded to tailroom. */
+		if (tailroom >= ETH_FCS_LEN)
+			goto add_fcs;
+		/* FCS could be appeded by moving data to headroom. */
+		else if (!cloned && headroom + tailroom >= ETH_FCS_LEN)
+			padlen = 0;
+		/* No room for FCS, need to reallocate skb. */
+		else
+			padlen = ETH_FCS_LEN - tailroom;
+	} else {
+		/* Add room for FCS. */
+		padlen += ETH_FCS_LEN;
+	}
+
+	if (!cloned && headroom + tailroom >= padlen) {
+		(*skb)->data = memmove((*skb)->head, (*skb)->data, (*skb)->len);
+		skb_set_tail_pointer(*skb, (*skb)->len);
+	} else {
+		nskb = skb_copy_expand(*skb, 0, padlen, GFP_ATOMIC);
+		if (!nskb)
+			return -ENOMEM;
+
+		dev_kfree_skb_any(*skb);
+		*skb = nskb;
+	}
+
+	if (padlen) {
+		if (padlen >= ETH_FCS_LEN)
+			skb_put_zero(*skb, padlen - ETH_FCS_LEN);
+		else
+			skb_trim(*skb, ETH_FCS_LEN - padlen);
+	}
+
+add_fcs:
+	/* set FCS to packet */
+	fcs = crc32_le(~0, (*skb)->data, (*skb)->len);
+	fcs = ~fcs;
+
+	skb_put_u8(*skb, fcs		& 0xff);
+	skb_put_u8(*skb, (fcs >> 8)	& 0xff);
+	skb_put_u8(*skb, (fcs >> 16)	& 0xff);
+	skb_put_u8(*skb, (fcs >> 24)	& 0xff);
+
+	return 0;
+}
+
+static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	u16 queue_index = skb_get_queue_mapping(skb);
 	struct macb *bp = netdev_priv(dev);
@@ -1660,6 +1725,17 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	unsigned int desc_cnt, nr_frags, frag_size, f;
 	unsigned int hdrlen;
 	bool is_lso, is_udp = 0;
+	netdev_tx_t ret = NETDEV_TX_OK;
+
+	if (macb_clear_csum(skb)) {
+		dev_kfree_skb_any(skb);
+		return ret;
+	}
+
+	if (macb_pad_and_fcs(&skb, dev)) {
+		dev_kfree_skb_any(skb);
+		return ret;
+	}
 
 	is_lso = (skb_shinfo(skb)->gso_size != 0);
 
@@ -1716,11 +1792,6 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_BUSY;
 	}
 
-	if (macb_clear_csum(skb)) {
-		dev_kfree_skb_any(skb);
-		goto unlock;
-	}
-
 	/* Map socket buffer for DMA transfer */
 	if (!macb_tx_map(bp, queue, skb, hdrlen)) {
 		dev_kfree_skb_any(skb);
@@ -1739,7 +1810,7 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 unlock:
 	spin_unlock_irqrestore(&bp->lock, flags);
 
-	return NETDEV_TX_OK;
+	return ret;
 }
 
 static void macb_init_rx_buffer_size(struct macb *bp, size_t size)
@@ -3549,7 +3620,8 @@ static int at91ether_close(struct net_device *dev)
 }
 
 /* Transmit packet */
-static int at91ether_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t at91ether_start_xmit(struct sk_buff *skb,
+					struct net_device *dev)
 {
 	struct macb *lp = netdev_priv(dev);
 
diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c
index 678835136bf8..cd5296b84229 100644
--- a/drivers/net/ethernet/cadence/macb_ptp.c
+++ b/drivers/net/ethernet/cadence/macb_ptp.c
@@ -466,6 +466,7 @@ int gem_set_hwtst(struct net_device *dev, struct ifreq *ifr, int cmd)
 	case HWTSTAMP_TX_ONESTEP_SYNC:
 		if (gem_ptp_set_one_step_sync(bp, 1) != 0)
 			return -ERANGE;
+		/* fall through */
 	case HWTSTAMP_TX_ON:
 		tx_bd_control = TSTAMP_ALL_FRAMES;
 		break;
diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index 92d88c5f76fb..5f03199a3acf 100644
--- a/drivers/net/ethernet/cavium/Kconfig
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -4,7 +4,6 @@
 
 config NET_VENDOR_CAVIUM
 	bool "Cavium ethernet drivers"
-	depends on PCI
 	default y
 	---help---
 	  Select this option if you want enable Cavium network support.
@@ -36,7 +35,7 @@ config	THUNDER_NIC_BGX
 	tristate "Thunder MAC interface driver (BGX)"
 	depends on 64BIT && PCI
 	select PHYLIB
-	select MDIO_THUNDER
+	select MDIO_THUNDER if PCI
 	select THUNDER_NIC_RGX
 	---help---
 	  This driver supports programming and controlling of MAC
@@ -46,7 +45,7 @@ config	THUNDER_NIC_RGX
 	tristate "Thunder MAC interface driver (RGX)"
 	depends on 64BIT && PCI
 	select PHYLIB
-	select MDIO_THUNDER
+	select MDIO_THUNDER if PCI
 	---help---
 	  This driver supports configuring XCV block of RGX interface
 	  present on CN81XX chip.
@@ -67,6 +66,7 @@ config LIQUIDIO
 	tristate "Cavium LiquidIO support"
 	depends on 64BIT && PCI
 	depends on MAY_USE_DEVLINK
+	depends on PCI
 	imply PTP_1588_CLOCK
 	select FW_LOADER
 	select LIBCRC32C
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
index 929d485a3a2f..9f4f3c1d5043 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
@@ -493,6 +493,9 @@ static void cn23xx_pf_setup_global_output_regs(struct octeon_device *oct)
 	for (q_no = srn; q_no < ern; q_no++) {
 		reg_val = octeon_read_csr(oct, CN23XX_SLI_OQ_PKT_CONTROL(q_no));
 
+		/* clear IPTR */
+		reg_val &= ~CN23XX_PKT_OUTPUT_CTL_IPTR;
+
 		/* set DPTR */
 		reg_val |= CN23XX_PKT_OUTPUT_CTL_DPTR;
 
@@ -1414,50 +1417,6 @@ int validate_cn23xx_pf_config_info(struct octeon_device *oct,
 	return 0;
 }
 
-void cn23xx_dump_iq_regs(struct octeon_device *oct)
-{
-	u32 regval, q_no;
-
-	dev_dbg(&oct->pci_dev->dev, "SLI_IQ_DOORBELL_0 [0x%x]: 0x%016llx\n",
-		CN23XX_SLI_IQ_DOORBELL(0),
-		CVM_CAST64(octeon_read_csr64
-			(oct, CN23XX_SLI_IQ_DOORBELL(0))));
-
-	dev_dbg(&oct->pci_dev->dev, "SLI_IQ_BASEADDR_0 [0x%x]: 0x%016llx\n",
-		CN23XX_SLI_IQ_BASE_ADDR64(0),
-		CVM_CAST64(octeon_read_csr64
-			(oct, CN23XX_SLI_IQ_BASE_ADDR64(0))));
-
-	dev_dbg(&oct->pci_dev->dev, "SLI_IQ_FIFO_RSIZE_0 [0x%x]: 0x%016llx\n",
-		CN23XX_SLI_IQ_SIZE(0),
-		CVM_CAST64(octeon_read_csr64(oct, CN23XX_SLI_IQ_SIZE(0))));
-
-	dev_dbg(&oct->pci_dev->dev, "SLI_CTL_STATUS [0x%x]: 0x%016llx\n",
-		CN23XX_SLI_CTL_STATUS,
-		CVM_CAST64(octeon_read_csr64(oct, CN23XX_SLI_CTL_STATUS)));
-
-	for (q_no = 0; q_no < CN23XX_MAX_INPUT_QUEUES; q_no++) {
-		dev_dbg(&oct->pci_dev->dev, "SLI_PKT[%d]_INPUT_CTL [0x%x]: 0x%016llx\n",
-			q_no, CN23XX_SLI_IQ_PKT_CONTROL64(q_no),
-			CVM_CAST64(octeon_read_csr64
-				(oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no))));
-	}
-
-	pci_read_config_dword(oct->pci_dev, CN23XX_CONFIG_PCIE_DEVCTL, &regval);
-	dev_dbg(&oct->pci_dev->dev, "Config DevCtl [0x%x]: 0x%08x\n",
-		CN23XX_CONFIG_PCIE_DEVCTL, regval);
-
-	dev_dbg(&oct->pci_dev->dev, "SLI_PRT[%d]_CFG [0x%llx]: 0x%016llx\n",
-		oct->pcie_port, CN23XX_DPI_SLI_PRTX_CFG(oct->pcie_port),
-		CVM_CAST64(lio_pci_readq(
-			oct, CN23XX_DPI_SLI_PRTX_CFG(oct->pcie_port))));
-
-	dev_dbg(&oct->pci_dev->dev, "SLI_S2M_PORT[%d]_CTL [0x%x]: 0x%016llx\n",
-		oct->pcie_port, CN23XX_SLI_S2M_PORTX_CTL(oct->pcie_port),
-		CVM_CAST64(octeon_read_csr64(
-			oct, CN23XX_SLI_S2M_PORTX_CTL(oct->pcie_port))));
-}
-
 int cn23xx_fw_loaded(struct octeon_device *oct)
 {
 	u64 val;
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c
index 9338a0008378..962bb62933db 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c
@@ -165,6 +165,9 @@ static void cn23xx_vf_setup_global_output_regs(struct octeon_device *oct)
 		reg_val =
 		    octeon_read_csr(oct, CN23XX_VF_SLI_OQ_PKT_CONTROL(q_no));
 
+		/* clear IPTR */
+		reg_val &= ~CN23XX_PKT_OUTPUT_CTL_IPTR;
+
 		/* set DPTR */
 		reg_val |= CN23XX_PKT_OUTPUT_CTL_DPTR;
 
@@ -379,7 +382,7 @@ void cn23xx_vf_ask_pf_to_do_flr(struct octeon_device *oct)
 	mbox_cmd.recv_len = 0;
 	mbox_cmd.recv_status = 0;
 	mbox_cmd.fn = NULL;
-	mbox_cmd.fn_arg = 0;
+	mbox_cmd.fn_arg = NULL;
 
 	octeon_mbox_write(oct, &mbox_cmd);
 }
@@ -679,33 +682,3 @@ int cn23xx_setup_octeon_vf_device(struct octeon_device *oct)
 
 	return 0;
 }
-
-void cn23xx_dump_vf_iq_regs(struct octeon_device *oct)
-{
-	u32 regval, q_no;
-
-	dev_dbg(&oct->pci_dev->dev, "SLI_IQ_DOORBELL_0 [0x%x]: 0x%016llx\n",
-		CN23XX_VF_SLI_IQ_DOORBELL(0),
-		CVM_CAST64(octeon_read_csr64(
-					oct, CN23XX_VF_SLI_IQ_DOORBELL(0))));
-
-	dev_dbg(&oct->pci_dev->dev, "SLI_IQ_BASEADDR_0 [0x%x]: 0x%016llx\n",
-		CN23XX_VF_SLI_IQ_BASE_ADDR64(0),
-		CVM_CAST64(octeon_read_csr64(
-			oct, CN23XX_VF_SLI_IQ_BASE_ADDR64(0))));
-
-	dev_dbg(&oct->pci_dev->dev, "SLI_IQ_FIFO_RSIZE_0 [0x%x]: 0x%016llx\n",
-		CN23XX_VF_SLI_IQ_SIZE(0),
-		CVM_CAST64(octeon_read_csr64(oct, CN23XX_VF_SLI_IQ_SIZE(0))));
-
-	for (q_no = 0; q_no < oct->sriov_info.rings_per_vf; q_no++) {
-		dev_dbg(&oct->pci_dev->dev, "SLI_PKT[%d]_INPUT_CTL [0x%x]: 0x%016llx\n",
-			q_no, CN23XX_VF_SLI_IQ_PKT_CONTROL64(q_no),
-			CVM_CAST64(octeon_read_csr64(
-				oct, CN23XX_VF_SLI_IQ_PKT_CONTROL64(q_no))));
-	}
-
-	pci_read_config_dword(oct->pci_dev, CN23XX_CONFIG_PCIE_DEVCTL, &regval);
-	dev_dbg(&oct->pci_dev->dev, "Config DevCtl [0x%x]: 0x%08x\n",
-		CN23XX_CONFIG_PCIE_DEVCTL, regval);
-}
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
index 06f7449c569d..8e05afd5e39c 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
@@ -389,18 +389,14 @@ static int lio_set_link_ksettings(struct net_device *netdev,
 	struct lio *lio = GET_LIO(netdev);
 	struct oct_link_info *linfo;
 	struct octeon_device *oct;
-	u32 is25G = 0;
 
 	oct = lio->oct_dev;
 
 	linfo = &lio->linfo;
 
-	if (oct->subsystem_id == OCTEON_CN2350_25GB_SUBSYS_ID ||
-	    oct->subsystem_id == OCTEON_CN2360_25GB_SUBSYS_ID) {
-		is25G = 1;
-	} else {
+	if (!(oct->subsystem_id == OCTEON_CN2350_25GB_SUBSYS_ID ||
+	      oct->subsystem_id == OCTEON_CN2360_25GB_SUBSYS_ID))
 		return -EOPNOTSUPP;
-	}
 
 	if (oct->no_speed_setting) {
 		dev_err(&oct->pci_dev->dev, "%s: Changing speed is not supported\n",
@@ -857,7 +853,14 @@ static int lio_set_phys_id(struct net_device *netdev,
 {
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
+	struct oct_link_info *linfo;
 	int value, ret;
+	u32 cur_ver;
+
+	linfo = &lio->linfo;
+	cur_ver = OCT_FW_VER(oct->fw_info.ver.maj,
+			     oct->fw_info.ver.min,
+			     oct->fw_info.ver.rev);
 
 	switch (state) {
 	case ETHTOOL_ID_ACTIVE:
@@ -896,16 +899,22 @@ static int lio_set_phys_id(struct net_device *netdev,
 				return ret;
 		} else if (oct->chip_id == OCTEON_CN23XX_PF_VID) {
 			octnet_id_active(netdev, LED_IDENTIFICATION_ON);
-
-			/* returns 0 since updates are asynchronous */
-			return 0;
+			if (linfo->link.s.phy_type == LIO_PHY_PORT_TP &&
+			    cur_ver > OCT_FW_VER(1, 7, 2))
+				return 2;
+			else
+				return 0;
 		} else {
 			return -EINVAL;
 		}
 		break;
 
 	case ETHTOOL_ID_ON:
-		if (oct->chip_id == OCTEON_CN66XX)
+		if (oct->chip_id == OCTEON_CN23XX_PF_VID &&
+		    linfo->link.s.phy_type == LIO_PHY_PORT_TP &&
+		    cur_ver > OCT_FW_VER(1, 7, 2))
+			octnet_id_active(netdev, LED_IDENTIFICATION_ON);
+		else if (oct->chip_id == OCTEON_CN66XX)
 			octnet_gpio_access(netdev, VITESSE_PHY_GPIO_CFG,
 					   VITESSE_PHY_GPIO_HIGH);
 		else
@@ -914,7 +923,11 @@ static int lio_set_phys_id(struct net_device *netdev,
 		break;
 
 	case ETHTOOL_ID_OFF:
-		if (oct->chip_id == OCTEON_CN66XX)
+		if (oct->chip_id == OCTEON_CN23XX_PF_VID &&
+		    linfo->link.s.phy_type == LIO_PHY_PORT_TP &&
+		    cur_ver > OCT_FW_VER(1, 7, 2))
+			octnet_id_active(netdev, LED_IDENTIFICATION_OFF);
+		else if (oct->chip_id == OCTEON_CN66XX)
 			octnet_gpio_access(netdev, VITESSE_PHY_GPIO_CFG,
 					   VITESSE_PHY_GPIO_LOW);
 		else
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 7e8454d3b1ad..6fb13fa73b27 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -687,7 +687,7 @@ static void lio_sync_octeon_time(struct work_struct *work)
 	lt = (struct lio_time *)sc->virtdptr;
 
 	/* Get time of the day */
-	getnstimeofday64(&ts);
+	ktime_get_real_ts64(&ts);
 	lt->sec = ts.tv_sec;
 	lt->nsec = ts.tv_nsec;
 	octeon_swap_8B_data((u64 *)lt, (sizeof(struct lio_time)) / 8);
@@ -2209,6 +2209,7 @@ static int liquidio_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 	case SIOCSHWTSTAMP:
 		if (lio->oct_dev->ptp_enable)
 			return hwtstamp_ioctl(netdev, ifr);
+		/* fall through */
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -2631,7 +2632,7 @@ static int liquidio_vlan_rx_kill_vid(struct net_device *netdev,
 
 	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
 	if (ret < 0) {
-		dev_err(&oct->pci_dev->dev, "Add VLAN filter failed in core (ret: 0x%x)\n",
+		dev_err(&oct->pci_dev->dev, "Del VLAN filter failed in core (ret: 0x%x)\n",
 			ret);
 	}
 	return ret;
@@ -2909,7 +2910,7 @@ static int liquidio_set_vf_vlan(struct net_device *netdev, int vfidx,
 	    vfidx + 1; /* vfidx is 0 based, but vf_num (param2) is 1 based */
 	nctrl.ncmd.s.more = 0;
 	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
-	nctrl.cb_fn = 0;
+	nctrl.cb_fn = NULL;
 	nctrl.wait_time = LIO_CMD_WAIT_TM;
 
 	octnet_send_nic_ctrl_pkt(oct, &nctrl);
@@ -3068,7 +3069,7 @@ static int liquidio_set_vf_link_state(struct net_device *netdev, int vfidx,
 	nctrl.ncmd.s.param2 = linkstate;
 	nctrl.ncmd.s.more = 0;
 	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
-	nctrl.cb_fn = 0;
+	nctrl.cb_fn = NULL;
 	nctrl.wait_time = LIO_CMD_WAIT_TM;
 
 	octnet_send_nic_ctrl_pkt(oct, &nctrl);
@@ -3302,7 +3303,9 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 {
 	struct lio *lio = NULL;
 	struct net_device *netdev;
-	u8 mac[6], i, j, *fw_ver;
+	u8 mac[6], i, j, *fw_ver, *micro_ver;
+	unsigned long micro;
+	u32 cur_ver;
 	struct octeon_soft_command *sc;
 	struct liquidio_if_cfg_context *ctx;
 	struct liquidio_if_cfg_resp *resp;
@@ -3432,6 +3435,14 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 				 fw_ver);
 		}
 
+		/* extract micro version field; point past '<maj>.<min>.' */
+		micro_ver = fw_ver + strlen(LIQUIDIO_BASE_VERSION) + 1;
+		if (kstrtoul(micro_ver, 10, &micro) != 0)
+			micro = 0;
+		octeon_dev->fw_info.ver.maj = LIQUIDIO_BASE_MAJOR_VERSION;
+		octeon_dev->fw_info.ver.min = LIQUIDIO_BASE_MINOR_VERSION;
+		octeon_dev->fw_info.ver.rev = micro;
+
 		octeon_swap_8B_data((u64 *)(&resp->cfg_info),
 				    (sizeof(struct liquidio_if_cfg_info)) >> 3);
 
@@ -3572,9 +3583,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 		for (j = 0; j < octeon_dev->sriov_info.max_vfs; j++) {
 			u8 vfmac[ETH_ALEN];
 
-			random_ether_addr(&vfmac[0]);
-			if (__liquidio_set_vf_mac(netdev, j,
-						  &vfmac[0], false)) {
+			eth_random_addr(vfmac);
+			if (__liquidio_set_vf_mac(netdev, j, vfmac, false)) {
 				dev_err(&octeon_dev->pci_dev->dev,
 					"Error setting VF%d MAC address\n",
 					j);
@@ -3675,7 +3685,19 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 			OCTEON_CN2350_25GB_SUBSYS_ID ||
 		    octeon_dev->subsystem_id ==
 			OCTEON_CN2360_25GB_SUBSYS_ID) {
-			liquidio_get_speed(lio);
+			cur_ver = OCT_FW_VER(octeon_dev->fw_info.ver.maj,
+					     octeon_dev->fw_info.ver.min,
+					     octeon_dev->fw_info.ver.rev);
+
+			/* speed control unsupported in f/w older than 1.7.2 */
+			if (cur_ver < OCT_FW_VER(1, 7, 2)) {
+				dev_info(&octeon_dev->pci_dev->dev,
+					 "speed setting not supported by f/w.");
+				octeon_dev->speed_setting = 25;
+				octeon_dev->no_speed_setting = 1;
+			} else {
+				liquidio_get_speed(lio);
+			}
 
 			if (octeon_dev->speed_setting == 0) {
 				octeon_dev->speed_setting = 25;
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
index 7fa0212873ac..b77835724dc8 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
@@ -1693,7 +1693,7 @@ liquidio_vlan_rx_kill_vid(struct net_device *netdev,
 
 	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
 	if (ret < 0) {
-		dev_err(&oct->pci_dev->dev, "Add VLAN filter failed in core (ret: 0x%x)\n",
+		dev_err(&oct->pci_dev->dev, "Del VLAN filter failed in core (ret: 0x%x)\n",
 			ret);
 	}
 	return ret;
diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
index 690424b6781a..7407fcd338e9 100644
--- a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
+++ b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
@@ -907,6 +907,7 @@ static inline int opcode_slow_path(union octeon_rh *rh)
 #define VITESSE_PHY_GPIO_LOW      0x3
 #define LED_IDENTIFICATION_ON     0x1
 #define LED_IDENTIFICATION_OFF    0x0
+#define LIO23XX_COPPERHEAD_LED_GPIO 0x2
 
 struct oct_mdio_cmd {
 	u64 op;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_console.c b/drivers/net/ethernet/cavium/liquidio/octeon_console.c
index 7f97ae48efed..0cc2338d8d2a 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_console.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_console.c
@@ -902,7 +902,7 @@ int octeon_download_firmware(struct octeon_device *oct, const u8 *data,
 	 *
 	 * Octeon always uses UTC time. so timezone information is not sent.
 	 */
-	getnstimeofday64(&ts);
+	ktime_get_real_ts64(&ts);
 	ret = snprintf(boottime, MAX_BOOTTIME_SIZE,
 		       " time_sec=%lld time_nsec=%ld",
 		       (s64)ts.tv_sec, ts.tv_nsec);
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
index 94a4ed88d618..d99ca6ba23a4 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
@@ -288,8 +288,17 @@ struct oct_fw_info {
 	 */
 	u32 app_mode;
 	char   liquidio_firmware_version[32];
+	/* Fields extracted from legacy string 'liquidio_firmware_version' */
+	struct {
+		u8  maj;
+		u8  min;
+		u8  rev;
+	} ver;
 };
 
+#define OCT_FW_VER(maj, min, rev) \
+	(((u32)(maj) << 16) | ((u32)(min) << 8) | ((u32)(rev)))
+
 /* wrappers around work structs */
 struct cavium_wk {
 	struct delayed_work work;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
index 5fed7b63223e..2327062e8af6 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
@@ -82,6 +82,16 @@ struct octeon_instr_queue {
 	/** A spinlock to protect while posting on the ring.  */
 	spinlock_t post_lock;
 
+	/** This flag indicates if the queue can be used for soft commands.
+	 *  If this flag is set, post_lock must be acquired before posting
+	 *  a command to the queue.
+	 *  If this flag is clear, post_lock is invalid for the queue.
+	 *  All control commands (soft commands) will go through only Queue 0
+	 *  (control and data queue). So only queue-0 needs post_lock,
+	 *  other queues are only data queues and does not need post_lock
+	 */
+	bool allow_soft_cmds;
+
 	u32 pkt_in_done;
 
 	/** A spinlock to protect access to the input ring.*/
diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c
index 1f2e75da28f8..8f746e1348d4 100644
--- a/drivers/net/ethernet/cavium/liquidio/request_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c
@@ -110,8 +110,8 @@ int octeon_init_instr_queue(struct octeon_device *oct,
 
 	memset(iq->request_list, 0, sizeof(*iq->request_list) * num_descs);
 
-	dev_dbg(&oct->pci_dev->dev, "IQ[%d]: base: %p basedma: %llx count: %d\n",
-		iq_no, iq->base_addr, iq->base_addr_dma, iq->max_count);
+	dev_dbg(&oct->pci_dev->dev, "IQ[%d]: base: %p basedma: %pad count: %d\n",
+		iq_no, iq->base_addr, &iq->base_addr_dma, iq->max_count);
 
 	iq->txpciq.u64 = txpciq.u64;
 	iq->fill_threshold = (u32)conf->db_min;
@@ -126,7 +126,12 @@ int octeon_init_instr_queue(struct octeon_device *oct,
 
 	/* Initialize the spinlock for this instruction queue */
 	spin_lock_init(&iq->lock);
-	spin_lock_init(&iq->post_lock);
+	if (iq_no == 0) {
+		iq->allow_soft_cmds = true;
+		spin_lock_init(&iq->post_lock);
+	} else {
+		iq->allow_soft_cmds = false;
+	}
 
 	spin_lock_init(&iq->iq_flush_running_lock);
 
@@ -566,7 +571,8 @@ octeon_send_command(struct octeon_device *oct, u32 iq_no,
 	/* Get the lock and prevent other tasks and tx interrupt handler from
 	 * running.
 	 */
-	spin_lock_bh(&iq->post_lock);
+	if (iq->allow_soft_cmds)
+		spin_lock_bh(&iq->post_lock);
 
 	st = __post_command2(iq, cmd);
 
@@ -583,7 +589,8 @@ octeon_send_command(struct octeon_device *oct, u32 iq_no,
 		INCR_INSTRQUEUE_PKT_COUNT(oct, iq_no, instr_dropped, 1);
 	}
 
-	spin_unlock_bh(&iq->post_lock);
+	if (iq->allow_soft_cmds)
+		spin_unlock_bh(&iq->post_lock);
 
 	/* This is only done here to expedite packets being flushed
 	 * for cases where there are no IQ completion interrupts.
@@ -702,11 +709,20 @@ octeon_prepare_soft_command(struct octeon_device *oct,
 int octeon_send_soft_command(struct octeon_device *oct,
 			     struct octeon_soft_command *sc)
 {
+	struct octeon_instr_queue *iq;
 	struct octeon_instr_ih2 *ih2;
 	struct octeon_instr_ih3 *ih3;
 	struct octeon_instr_irh *irh;
 	u32 len;
 
+	iq = oct->instr_queue[sc->iq_no];
+	if (!iq->allow_soft_cmds) {
+		dev_err(&oct->pci_dev->dev, "Soft commands are not allowed on Queue %d\n",
+			sc->iq_no);
+		INCR_INSTRQUEUE_PKT_COUNT(oct, sc->iq_no, instr_dropped, 1);
+		return IQ_SEND_FAILED;
+	}
+
 	if (OCTEON_CN23XX_PF(oct) || OCTEON_CN23XX_VF(oct)) {
 		ih3 =  (struct octeon_instr_ih3 *)&sc->cmd.cmd3.ih3;
 		if (ih3->dlengsz) {
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index 5603f5ab1fee..92ba958e204e 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -527,6 +527,7 @@ static int nicvf_get_rss_hash_opts(struct nicvf *nic,
 	case SCTP_V4_FLOW:
 	case SCTP_V6_FLOW:
 		info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		/* Fall through */
 	case IPV4_FLOW:
 	case IPV6_FLOW:
 		info->data |= RXH_IP_SRC | RXH_IP_DST;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 135766c4296b..768f584f8392 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1848,7 +1848,6 @@ static int nicvf_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 	case XDP_SETUP_PROG:
 		return nicvf_xdp_setup(nic, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!nic->xdp_prog;
 		xdp->prog_id = nic->xdp_prog ? nic->xdp_prog->aux->id : 0;
 		return 0;
 	default:
diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
index 8623be13bf86..0ccdde366ae1 100644
--- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
+++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
@@ -109,10 +109,6 @@ static int disable_msi = 0;
 module_param(disable_msi, int, 0);
 MODULE_PARM_DESC(disable_msi, "Disable Message Signaled Interrupt (MSI)");
 
-static const char pci_speed[][4] = {
-	"33", "66", "100", "133"
-};
-
 /*
  * Setup MAC to receive the types of packets we want.
  */
diff --git a/drivers/net/ethernet/chelsio/cxgb3/l2t.c b/drivers/net/ethernet/chelsio/cxgb3/l2t.c
index 248e40c6966c..0e9182d3f02c 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/l2t.c
@@ -136,6 +136,7 @@ again:
 		if (e->state == L2T_STATE_STALE)
 			e->state = L2T_STATE_VALID;
 		spin_unlock_bh(&e->lock);
+		/* fall through */
 	case L2T_STATE_VALID:	/* fast-path, send the packet on */
 		return cxgb3_ofld_send(dev, skb);
 	case L2T_STATE_RESOLVING:
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
index 3c5057868ab3..36d25883d123 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
@@ -120,6 +120,8 @@ struct cudbg_mem_desc {
 	u32 idx;
 };
 
+#define CUDBG_MEMINFO_REV 1
+
 struct cudbg_meminfo {
 	struct cudbg_mem_desc avail[4];
 	struct cudbg_mem_desc mem[ARRAY_SIZE(cudbg_region) + 3];
@@ -137,6 +139,9 @@ struct cudbg_meminfo {
 	u32 port_alloc[4];
 	u32 loopback_used[NCHAN];
 	u32 loopback_alloc[NCHAN];
+	u32 p_structs_free_cnt;
+	u32 free_rx_cnt;
+	u32 free_tx_cnt;
 };
 
 struct cudbg_cim_pif_la {
@@ -281,12 +286,18 @@ struct cudbg_tid_data {
 
 #define CUDBG_NUM_ULPTX 11
 #define CUDBG_NUM_ULPTX_READ 512
+#define CUDBG_NUM_ULPTX_ASIC 6
+#define CUDBG_NUM_ULPTX_ASIC_READ 128
+
+#define CUDBG_ULPTX_LA_REV 1
 
 struct cudbg_ulptx_la {
 	u32 rdptr[CUDBG_NUM_ULPTX];
 	u32 wrptr[CUDBG_NUM_ULPTX];
 	u32 rddata[CUDBG_NUM_ULPTX];
 	u32 rd_data[CUDBG_NUM_ULPTX][CUDBG_NUM_ULPTX_READ];
+	u32 rdptr_asic[CUDBG_NUM_ULPTX_ASIC_READ];
+	u32 rddata_asic[CUDBG_NUM_ULPTX_ASIC_READ][CUDBG_NUM_ULPTX_ASIC];
 };
 
 #define CUDBG_CHAC_PBT_ADDR 0x2800
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
index 0afcfe99bff3..d97e0d7e541a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
@@ -349,6 +349,11 @@ int cudbg_fill_meminfo(struct adapter *padap,
 	meminfo_buff->up_extmem2_hi = hi;
 
 	lo = t4_read_reg(padap, TP_PMM_RX_MAX_PAGE_A);
+	for (i = 0, meminfo_buff->free_rx_cnt = 0; i < 2; i++)
+		meminfo_buff->free_rx_cnt +=
+			FREERXPAGECOUNT_G(t4_read_reg(padap,
+						      TP_FLM_FREE_RX_CNT_A));
+
 	meminfo_buff->rx_pages_data[0] =  PMRXMAXPAGE_G(lo);
 	meminfo_buff->rx_pages_data[1] =
 		t4_read_reg(padap, TP_PMM_RX_PAGE_SIZE_A) >> 10;
@@ -356,6 +361,11 @@ int cudbg_fill_meminfo(struct adapter *padap,
 
 	lo = t4_read_reg(padap, TP_PMM_TX_MAX_PAGE_A);
 	hi = t4_read_reg(padap, TP_PMM_TX_PAGE_SIZE_A);
+	for (i = 0, meminfo_buff->free_tx_cnt = 0; i < 4; i++)
+		meminfo_buff->free_tx_cnt +=
+			FREETXPAGECOUNT_G(t4_read_reg(padap,
+						      TP_FLM_FREE_TX_CNT_A));
+
 	meminfo_buff->tx_pages_data[0] = PMTXMAXPAGE_G(lo);
 	meminfo_buff->tx_pages_data[1] =
 		hi >= (1 << 20) ? (hi >> 20) : (hi >> 10);
@@ -364,6 +374,8 @@ int cudbg_fill_meminfo(struct adapter *padap,
 	meminfo_buff->tx_pages_data[3] = 1 << PMTXNUMCHN_G(lo);
 
 	meminfo_buff->p_structs = t4_read_reg(padap, TP_CMM_MM_MAX_PSTRUCT_A);
+	meminfo_buff->p_structs_free_cnt =
+		FREEPSTRUCTCOUNT_G(t4_read_reg(padap, TP_FLM_FREE_PS_CNT_A));
 
 	for (i = 0; i < 4; i++) {
 		if (CHELSIO_CHIP_VERSION(padap->params.chip) > CHELSIO_T5)
@@ -1465,14 +1477,23 @@ int cudbg_collect_meminfo(struct cudbg_init *pdbg_init,
 	struct adapter *padap = pdbg_init->adap;
 	struct cudbg_buffer temp_buff = { 0 };
 	struct cudbg_meminfo *meminfo_buff;
+	struct cudbg_ver_hdr *ver_hdr;
 	int rc;
 
-	rc = cudbg_get_buff(pdbg_init, dbg_buff, sizeof(struct cudbg_meminfo),
+	rc = cudbg_get_buff(pdbg_init, dbg_buff,
+			    sizeof(struct cudbg_ver_hdr) +
+			    sizeof(struct cudbg_meminfo),
 			    &temp_buff);
 	if (rc)
 		return rc;
 
-	meminfo_buff = (struct cudbg_meminfo *)temp_buff.data;
+	ver_hdr = (struct cudbg_ver_hdr *)temp_buff.data;
+	ver_hdr->signature = CUDBG_ENTITY_SIGNATURE;
+	ver_hdr->revision = CUDBG_MEMINFO_REV;
+	ver_hdr->size = sizeof(struct cudbg_meminfo);
+
+	meminfo_buff = (struct cudbg_meminfo *)(temp_buff.data +
+						sizeof(*ver_hdr));
 	rc = cudbg_fill_meminfo(padap, meminfo_buff);
 	if (rc) {
 		cudbg_err->sys_err = rc;
@@ -2586,15 +2607,24 @@ int cudbg_collect_ulptx_la(struct cudbg_init *pdbg_init,
 	struct adapter *padap = pdbg_init->adap;
 	struct cudbg_buffer temp_buff = { 0 };
 	struct cudbg_ulptx_la *ulptx_la_buff;
+	struct cudbg_ver_hdr *ver_hdr;
 	u32 i, j;
 	int rc;
 
-	rc = cudbg_get_buff(pdbg_init, dbg_buff, sizeof(struct cudbg_ulptx_la),
+	rc = cudbg_get_buff(pdbg_init, dbg_buff,
+			    sizeof(struct cudbg_ver_hdr) +
+			    sizeof(struct cudbg_ulptx_la),
 			    &temp_buff);
 	if (rc)
 		return rc;
 
-	ulptx_la_buff = (struct cudbg_ulptx_la *)temp_buff.data;
+	ver_hdr = (struct cudbg_ver_hdr *)temp_buff.data;
+	ver_hdr->signature = CUDBG_ENTITY_SIGNATURE;
+	ver_hdr->revision = CUDBG_ULPTX_LA_REV;
+	ver_hdr->size = sizeof(struct cudbg_ulptx_la);
+
+	ulptx_la_buff = (struct cudbg_ulptx_la *)(temp_buff.data +
+						  sizeof(*ver_hdr));
 	for (i = 0; i < CUDBG_NUM_ULPTX; i++) {
 		ulptx_la_buff->rdptr[i] = t4_read_reg(padap,
 						      ULP_TX_LA_RDPTR_0_A +
@@ -2610,6 +2640,25 @@ int cudbg_collect_ulptx_la(struct cudbg_init *pdbg_init,
 				t4_read_reg(padap,
 					    ULP_TX_LA_RDDATA_0_A + 0x10 * i);
 	}
+
+	for (i = 0; i < CUDBG_NUM_ULPTX_ASIC_READ; i++) {
+		t4_write_reg(padap, ULP_TX_ASIC_DEBUG_CTRL_A, 0x1);
+		ulptx_la_buff->rdptr_asic[i] =
+				t4_read_reg(padap, ULP_TX_ASIC_DEBUG_CTRL_A);
+		ulptx_la_buff->rddata_asic[i][0] =
+				t4_read_reg(padap, ULP_TX_ASIC_DEBUG_0_A);
+		ulptx_la_buff->rddata_asic[i][1] =
+				t4_read_reg(padap, ULP_TX_ASIC_DEBUG_1_A);
+		ulptx_la_buff->rddata_asic[i][2] =
+				t4_read_reg(padap, ULP_TX_ASIC_DEBUG_2_A);
+		ulptx_la_buff->rddata_asic[i][3] =
+				t4_read_reg(padap, ULP_TX_ASIC_DEBUG_3_A);
+		ulptx_la_buff->rddata_asic[i][4] =
+				t4_read_reg(padap, ULP_TX_ASIC_DEBUG_4_A);
+		ulptx_la_buff->rddata_asic[i][5] =
+				t4_read_reg(padap, PM_RX_BASE_ADDR);
+	}
+
 	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 0dbe2d9e22d6..76d16747f513 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -46,6 +46,7 @@
 #include <linux/spinlock.h>
 #include <linux/timer.h>
 #include <linux/vmalloc.h>
+#include <linux/rhashtable.h>
 #include <linux/etherdevice.h>
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
@@ -319,6 +320,21 @@ struct vpd_params {
 	u8 na[MACADDR_LEN + 1];
 };
 
+/* Maximum resources provisioned for a PCI PF.
+ */
+struct pf_resources {
+	unsigned int nvi;		/* N virtual interfaces */
+	unsigned int neq;		/* N egress Qs */
+	unsigned int nethctrl;		/* N egress ETH or CTRL Qs */
+	unsigned int niqflint;		/* N ingress Qs/w free list(s) & intr */
+	unsigned int niq;		/* N ingress Qs */
+	unsigned int tc;		/* PCI-E traffic class */
+	unsigned int pmask;		/* port access rights mask */
+	unsigned int nexactf;		/* N exact MPS filters */
+	unsigned int r_caps;		/* read capabilities */
+	unsigned int wx_caps;		/* write/execute capabilities */
+};
+
 struct pci_params {
 	unsigned int vpd_cap_addr;
 	unsigned char speed;
@@ -346,6 +362,7 @@ struct adapter_params {
 	struct sge_params sge;
 	struct tp_params  tp;
 	struct vpd_params vpd;
+	struct pf_resources pfres;
 	struct pci_params pci;
 	struct devlog_params devlog;
 	enum pcie_memwin drv_memwin;
@@ -521,6 +538,15 @@ enum {
 	MAX_INGQ = MAX_ETH_QSETS + INGQ_EXTRAS,
 };
 
+enum {
+	PRIV_FLAG_PORT_TX_VM_BIT,
+};
+
+#define PRIV_FLAG_PORT_TX_VM		BIT(PRIV_FLAG_PORT_TX_VM_BIT)
+
+#define PRIV_FLAGS_ADAP			0
+#define PRIV_FLAGS_PORT			PRIV_FLAG_PORT_TX_VM
+
 struct adapter;
 struct sge_rspq;
 
@@ -557,6 +583,7 @@ struct port_info {
 	struct hwtstamp_config tstamp_config;
 	bool ptp_enable;
 	struct sched_table *sched_tbl;
+	u32 eth_flags;
 };
 
 struct dentry;
@@ -867,6 +894,7 @@ struct adapter {
 	unsigned int flags;
 	unsigned int adap_idx;
 	enum chip_type chip;
+	u32 eth_flags;
 
 	int msg_enable;
 	__be16 vxlan_port;
@@ -956,6 +984,7 @@ struct adapter {
 	struct chcr_stats_debug chcr_stats;
 
 	/* TC flower offload */
+	bool tc_flower_initialized;
 	struct rhashtable flower_tbl;
 	struct rhashtable_params flower_ht_params;
 	struct timer_list flower_stats_timer;
@@ -1333,7 +1362,7 @@ void t4_os_link_changed(struct adapter *adap, int port_id, int link_stat);
 void t4_free_sge_resources(struct adapter *adap);
 void t4_free_ofld_rxqs(struct adapter *adap, int n, struct sge_ofld_rxq *q);
 irq_handler_t t4_intr_handler(struct adapter *adap);
-netdev_tx_t t4_eth_xmit(struct sk_buff *skb, struct net_device *dev);
+netdev_tx_t t4_start_xmit(struct sk_buff *skb, struct net_device *dev);
 int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp,
 		     const struct pkt_gl *gl);
 int t4_mgmt_tx(struct adapter *adap, struct sk_buff *skb);
@@ -1555,6 +1584,7 @@ int t4_eeprom_ptov(unsigned int phys_addr, unsigned int fn, unsigned int sz);
 int t4_seeprom_wp(struct adapter *adapter, bool enable);
 int t4_get_raw_vpd_params(struct adapter *adapter, struct vpd_params *p);
 int t4_get_vpd_params(struct adapter *adapter, struct vpd_params *p);
+int t4_get_pfres(struct adapter *adapter);
 int t4_read_flash(struct adapter *adapter, unsigned int addr,
 		  unsigned int nwords, u32 *data, int byte_oriented);
 int t4_load_fw(struct adapter *adapter, const u8 *fw_data, unsigned int size);
@@ -1823,4 +1853,5 @@ void cxgb4_write_sgl(const struct sk_buff *skb, struct sge_txq *q,
 void cxgb4_ring_tx_db(struct adapter *adap, struct sge_txq *q, int n);
 int t4_set_vlan_acl(struct adapter *adap, unsigned int mbox, unsigned int vf,
 		    u16 vlan);
+int cxgb4_dcb_enabled(const struct net_device *dev);
 #endif /* __CXGB4_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
index 8d751efcb90e..5f01c0a7fd98 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
@@ -224,7 +224,8 @@ static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity)
 		len = sizeof(struct cudbg_tp_la) + TPLA_SIZE * sizeof(u64);
 		break;
 	case CUDBG_MEMINFO:
-		len = sizeof(struct cudbg_meminfo);
+		len = sizeof(struct cudbg_ver_hdr) +
+		      sizeof(struct cudbg_meminfo);
 		break;
 	case CUDBG_CIM_PIF_LA:
 		len = sizeof(struct cudbg_cim_pif_la);
@@ -273,7 +274,8 @@ static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity)
 		}
 		break;
 	case CUDBG_ULPTX_LA:
-		len = sizeof(struct cudbg_ulptx_la);
+		len = sizeof(struct cudbg_ver_hdr) +
+		      sizeof(struct cudbg_ulptx_la);
 		break;
 	case CUDBG_UP_CIM_INDIRECT:
 		n = 0;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c
index 4e7f72b17e82..b34f0f077a31 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c
@@ -22,7 +22,7 @@
 
 /* DCBx version control
  */
-static const char * const dcb_ver_array[] = {
+const char * const dcb_ver_array[] = {
 	"Unknown",
 	"DCBx-CIN",
 	"DCBx-CEE 1.01",
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index c301aaf79d64..0f72f9c4ec74 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -2414,6 +2414,234 @@ static const struct file_operations rss_vf_config_debugfs_fops = {
 	.release = seq_release_private
 };
 
+#ifdef CONFIG_CHELSIO_T4_DCB
+extern char *dcb_ver_array[];
+
+/* Data Center Briging information for each port.
+ */
+static int dcb_info_show(struct seq_file *seq, void *v)
+{
+	struct adapter *adap = seq->private;
+
+	if (v == SEQ_START_TOKEN) {
+		seq_puts(seq, "Data Center Bridging Information\n");
+	} else {
+		int port = (uintptr_t)v - 2;
+		struct net_device *dev = adap->port[port];
+		struct port_info *pi = netdev2pinfo(dev);
+		struct port_dcb_info *dcb = &pi->dcb;
+
+		seq_puts(seq, "\n");
+		seq_printf(seq, "Port: %d (DCB negotiated: %s)\n",
+			   port,
+			   cxgb4_dcb_enabled(dev) ? "yes" : "no");
+
+		if (cxgb4_dcb_enabled(dev))
+			seq_printf(seq, "[ DCBx Version %s ]\n",
+				   dcb_ver_array[dcb->dcb_version]);
+
+		if (dcb->msgs) {
+			int i;
+
+			seq_puts(seq, "\n  Index\t\t\t  :\t");
+			for (i = 0; i < 8; i++)
+				seq_printf(seq, " %3d", i);
+			seq_puts(seq, "\n\n");
+		}
+
+		if (dcb->msgs & CXGB4_DCB_FW_PGID) {
+			int prio, pgid;
+
+			seq_puts(seq, "  Priority Group IDs\t  :\t");
+			for (prio = 0; prio < 8; prio++) {
+				pgid = (dcb->pgid >> 4 * (7 - prio)) & 0xf;
+				seq_printf(seq, " %3d", pgid);
+			}
+			seq_puts(seq, "\n");
+		}
+
+		if (dcb->msgs & CXGB4_DCB_FW_PGRATE) {
+			int pg;
+
+			seq_puts(seq, "  Priority Group BW(%)\t  :\t");
+			for (pg = 0; pg < 8; pg++)
+				seq_printf(seq, " %3d", dcb->pgrate[pg]);
+			seq_puts(seq, "\n");
+
+			if (dcb->dcb_version == FW_PORT_DCB_VER_IEEE) {
+				seq_puts(seq, "  TSA Algorithm\t\t  :\t");
+				for (pg = 0; pg < 8; pg++)
+					seq_printf(seq, " %3d", dcb->tsa[pg]);
+				seq_puts(seq, "\n");
+			}
+
+			seq_printf(seq, "  Max PG Traffic Classes  [%3d  ]\n",
+				   dcb->pg_num_tcs_supported);
+
+			seq_puts(seq, "\n");
+		}
+
+		if (dcb->msgs & CXGB4_DCB_FW_PRIORATE) {
+			int prio;
+
+			seq_puts(seq, "  Priority Rate\t:\t");
+			for (prio = 0; prio < 8; prio++)
+				seq_printf(seq, " %3d", dcb->priorate[prio]);
+			seq_puts(seq, "\n");
+		}
+
+		if (dcb->msgs & CXGB4_DCB_FW_PFC) {
+			int prio;
+
+			seq_puts(seq, "  Priority Flow Control   :\t");
+			for (prio = 0; prio < 8; prio++) {
+				int pfcen = (dcb->pfcen >> 1 * (7 - prio))
+					    & 0x1;
+				seq_printf(seq, " %3d", pfcen);
+			}
+			seq_puts(seq, "\n");
+
+			seq_printf(seq, "  Max PFC Traffic Classes [%3d  ]\n",
+				   dcb->pfc_num_tcs_supported);
+
+			seq_puts(seq, "\n");
+		}
+
+		if (dcb->msgs & CXGB4_DCB_FW_APP_ID) {
+			int app, napps;
+
+			seq_puts(seq, "  Application Information:\n");
+			seq_puts(seq, "  App    Priority    Selection         Protocol\n");
+			seq_puts(seq, "  Index  Map         Field             ID\n");
+			for (app = 0, napps = 0;
+			     app < CXGB4_MAX_DCBX_APP_SUPPORTED; app++) {
+				struct app_priority *ap;
+				static const char * const sel_names[] = {
+					"Ethertype",
+					"Socket TCP",
+					"Socket UDP",
+					"Socket All",
+				};
+				const char *sel_name;
+
+				ap = &dcb->app_priority[app];
+				/* skip empty slots */
+				if (ap->protocolid == 0)
+					continue;
+				napps++;
+
+				if (ap->sel_field < ARRAY_SIZE(sel_names))
+					sel_name = sel_names[ap->sel_field];
+				else
+					sel_name = "UNKNOWN";
+
+				seq_printf(seq, "  %3d    %#04x        %-10s (%d)    %#06x (%d)\n",
+					   app,
+					   ap->user_prio_map,
+					   sel_name, ap->sel_field,
+					   ap->protocolid, ap->protocolid);
+			}
+			if (napps == 0)
+				seq_puts(seq, "    --- None ---\n");
+		}
+	}
+	return 0;
+}
+
+static inline void *dcb_info_get_idx(struct adapter *adap, loff_t pos)
+{
+	return (pos <= adap->params.nports
+		? (void *)((uintptr_t)pos + 1)
+		: NULL);
+}
+
+static void *dcb_info_start(struct seq_file *seq, loff_t *pos)
+{
+	struct adapter *adap = seq->private;
+
+	return (*pos
+		? dcb_info_get_idx(adap, *pos)
+		: SEQ_START_TOKEN);
+}
+
+static void dcb_info_stop(struct seq_file *seq, void *v)
+{
+}
+
+static void *dcb_info_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct adapter *adap = seq->private;
+
+	(*pos)++;
+	return dcb_info_get_idx(adap, *pos);
+}
+
+static const struct seq_operations dcb_info_seq_ops = {
+	.start = dcb_info_start,
+	.next  = dcb_info_next,
+	.stop  = dcb_info_stop,
+	.show  = dcb_info_show
+};
+
+static int dcb_info_open(struct inode *inode, struct file *file)
+{
+	int res = seq_open(file, &dcb_info_seq_ops);
+
+	if (!res) {
+		struct seq_file *seq = file->private_data;
+
+		seq->private = inode->i_private;
+	}
+	return res;
+}
+
+static const struct file_operations dcb_info_debugfs_fops = {
+	.owner   = THIS_MODULE,
+	.open    = dcb_info_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release,
+};
+#endif /* CONFIG_CHELSIO_T4_DCB */
+
+static int resources_show(struct seq_file *seq, void *v)
+{
+	struct adapter *adapter = seq->private;
+	struct pf_resources *pfres = &adapter->params.pfres;
+
+	#define S(desc, fmt, var) \
+		seq_printf(seq, "%-60s " fmt "\n", \
+			   desc " (" #var "):", pfres->var)
+
+	S("Virtual Interfaces", "%d", nvi);
+	S("Egress Queues", "%d", neq);
+	S("Ethernet Control", "%d", nethctrl);
+	S("Ingress Queues/w Free Lists/Interrupts", "%d", niqflint);
+	S("Ingress Queues", "%d", niq);
+	S("Traffic Class", "%d", tc);
+	S("Port Access Rights Mask", "%#x", pmask);
+	S("MAC Address Filters", "%d", nexactf);
+	S("Firmware Command Read Capabilities", "%#x", r_caps);
+	S("Firmware Command Write/Execute Capabilities", "%#x", wx_caps);
+
+	#undef S
+
+	return 0;
+}
+
+static int resources_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, resources_show, inode->i_private);
+}
+
+static const struct file_operations resources_debugfs_fops = {
+	.owner   = THIS_MODULE,
+	.open    = resources_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release,
+};
+
 /**
  * ethqset2pinfo - return port_info of an Ethernet Queue Set
  * @adap: the adapter
@@ -2436,16 +2664,64 @@ static inline struct port_info *ethqset2pinfo(struct adapter *adap, int qset)
 	return NULL;
 }
 
+static int sge_qinfo_uld_txq_entries(const struct adapter *adap, int uld)
+{
+	const struct sge_uld_txq_info *utxq_info = adap->sge.uld_txq_info[uld];
+
+	if (!utxq_info)
+		return 0;
+
+	return DIV_ROUND_UP(utxq_info->ntxq, 4);
+}
+
+static int sge_qinfo_uld_rspq_entries(const struct adapter *adap, int uld,
+				      bool ciq)
+{
+	const struct sge_uld_rxq_info *urxq_info = adap->sge.uld_rxq_info[uld];
+
+	if (!urxq_info)
+		return 0;
+
+	return ciq ? DIV_ROUND_UP(urxq_info->nciq, 4) :
+		     DIV_ROUND_UP(urxq_info->nrxq, 4);
+}
+
+static int sge_qinfo_uld_rxq_entries(const struct adapter *adap, int uld)
+{
+	return sge_qinfo_uld_rspq_entries(adap, uld, false);
+}
+
+static int sge_qinfo_uld_ciq_entries(const struct adapter *adap, int uld)
+{
+	return sge_qinfo_uld_rspq_entries(adap, uld, true);
+}
+
 static int sge_qinfo_show(struct seq_file *seq, void *v)
 {
+	int uld_rxq_entries[CXGB4_ULD_MAX] = { 0 };
+	int uld_ciq_entries[CXGB4_ULD_MAX] = { 0 };
+	int uld_txq_entries[CXGB4_TX_MAX] = { 0 };
+	const struct sge_uld_txq_info *utxq_info;
+	const struct sge_uld_rxq_info *urxq_info;
 	struct adapter *adap = seq->private;
-	int eth_entries = DIV_ROUND_UP(adap->sge.ethqsets, 4);
-	int ofld_entries = DIV_ROUND_UP(adap->sge.ofldqsets, 4);
-	int ctrl_entries = DIV_ROUND_UP(MAX_CTRL_QUEUES, 4);
-	int i, r = (uintptr_t)v - 1;
-	int ofld_idx = r - eth_entries;
-	int ctrl_idx =  ofld_idx - ofld_entries;
-	int fq_idx =  ctrl_idx - ctrl_entries;
+	int i, n, r = (uintptr_t)v - 1;
+	int eth_entries, ctrl_entries;
+	struct sge *s = &adap->sge;
+
+	eth_entries = DIV_ROUND_UP(adap->sge.ethqsets, 4);
+	ctrl_entries = DIV_ROUND_UP(MAX_CTRL_QUEUES, 4);
+
+	mutex_lock(&uld_mutex);
+	if (s->uld_txq_info)
+		for (i = 0; i < ARRAY_SIZE(uld_txq_entries); i++)
+			uld_txq_entries[i] = sge_qinfo_uld_txq_entries(adap, i);
+
+	if (s->uld_rxq_info) {
+		for (i = 0; i < ARRAY_SIZE(uld_rxq_entries); i++) {
+			uld_rxq_entries[i] = sge_qinfo_uld_rxq_entries(adap, i);
+			uld_ciq_entries[i] = sge_qinfo_uld_ciq_entries(adap, i);
+		}
+	}
 
 	if (r)
 		seq_putc(seq, '\n');
@@ -2467,9 +2743,10 @@ do { \
 
 	if (r < eth_entries) {
 		int base_qset = r * 4;
-		const struct sge_eth_rxq *rx = &adap->sge.ethrxq[base_qset];
-		const struct sge_eth_txq *tx = &adap->sge.ethtxq[base_qset];
-		int n = min(4, adap->sge.ethqsets - 4 * r);
+		const struct sge_eth_rxq *rx = &s->ethrxq[base_qset];
+		const struct sge_eth_txq *tx = &s->ethtxq[base_qset];
+
+		n = min(4, s->ethqsets - 4 * r);
 
 		S("QType:", "Ethernet");
 		S("Interface:",
@@ -2494,8 +2771,7 @@ do { \
 		R("RspQ CIDX:", rspq.cidx);
 		R("RspQ Gen:", rspq.gen);
 		S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq));
-		S3("u", "Intr pktcnt:",
-		   adap->sge.counter_val[rx[i].rspq.pktcnt_idx]);
+		S3("u", "Intr pktcnt:", s->counter_val[rx[i].rspq.pktcnt_idx]);
 		R("FL ID:", fl.cntxt_id);
 		R("FL size:", fl.size - 8);
 		R("FL pend:", fl.pend_cred);
@@ -2520,9 +2796,196 @@ do { \
 		RL("FLLow:", fl.low);
 		RL("FLStarving:", fl.starving);
 
-	} else if (ctrl_idx < ctrl_entries) {
-		const struct sge_ctrl_txq *tx = &adap->sge.ctrlq[ctrl_idx * 4];
-		int n = min(4, adap->params.nports - 4 * ctrl_idx);
+		goto unlock;
+	}
+
+	r -= eth_entries;
+	if (r < uld_txq_entries[CXGB4_TX_OFLD]) {
+		const struct sge_uld_txq *tx;
+
+		utxq_info = s->uld_txq_info[CXGB4_TX_OFLD];
+		tx = &utxq_info->uldtxq[r * 4];
+		n = min(4, utxq_info->ntxq - 4 * r);
+
+		S("QType:", "OFLD-TXQ");
+		T("TxQ ID:", q.cntxt_id);
+		T("TxQ size:", q.size);
+		T("TxQ inuse:", q.in_use);
+		T("TxQ CIDX:", q.cidx);
+		T("TxQ PIDX:", q.pidx);
+
+		goto unlock;
+	}
+
+	r -= uld_txq_entries[CXGB4_TX_OFLD];
+	if (r < uld_rxq_entries[CXGB4_ULD_RDMA]) {
+		const struct sge_ofld_rxq *rx;
+
+		urxq_info = s->uld_rxq_info[CXGB4_ULD_RDMA];
+		rx = &urxq_info->uldrxq[r * 4];
+		n = min(4, urxq_info->nrxq - 4 * r);
+
+		S("QType:", "RDMA-CPL");
+		S("Interface:",
+		  rx[i].rspq.netdev ? rx[i].rspq.netdev->name : "N/A");
+		R("RspQ ID:", rspq.abs_id);
+		R("RspQ size:", rspq.size);
+		R("RspQE size:", rspq.iqe_len);
+		R("RspQ CIDX:", rspq.cidx);
+		R("RspQ Gen:", rspq.gen);
+		S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq));
+		S3("u", "Intr pktcnt:",	s->counter_val[rx[i].rspq.pktcnt_idx]);
+		R("FL ID:", fl.cntxt_id);
+		R("FL size:", fl.size - 8);
+		R("FL pend:", fl.pend_cred);
+		R("FL avail:", fl.avail);
+		R("FL PIDX:", fl.pidx);
+		R("FL CIDX:", fl.cidx);
+
+		goto unlock;
+	}
+
+	r -= uld_rxq_entries[CXGB4_ULD_RDMA];
+	if (r < uld_ciq_entries[CXGB4_ULD_RDMA]) {
+		const struct sge_ofld_rxq *rx;
+		int ciq_idx = 0;
+
+		urxq_info = s->uld_rxq_info[CXGB4_ULD_RDMA];
+		ciq_idx = urxq_info->nrxq + (r * 4);
+		rx = &urxq_info->uldrxq[ciq_idx];
+		n = min(4, urxq_info->nciq - 4 * r);
+
+		S("QType:", "RDMA-CIQ");
+		S("Interface:",
+		  rx[i].rspq.netdev ? rx[i].rspq.netdev->name : "N/A");
+		R("RspQ ID:", rspq.abs_id);
+		R("RspQ size:", rspq.size);
+		R("RspQE size:", rspq.iqe_len);
+		R("RspQ CIDX:", rspq.cidx);
+		R("RspQ Gen:", rspq.gen);
+		S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq));
+		S3("u", "Intr pktcnt:",	s->counter_val[rx[i].rspq.pktcnt_idx]);
+
+		goto unlock;
+	}
+
+	r -= uld_ciq_entries[CXGB4_ULD_RDMA];
+	if (r < uld_rxq_entries[CXGB4_ULD_ISCSI]) {
+		const struct sge_ofld_rxq *rx;
+
+		urxq_info = s->uld_rxq_info[CXGB4_ULD_ISCSI];
+		rx = &urxq_info->uldrxq[r * 4];
+		n = min(4, urxq_info->nrxq - 4 * r);
+
+		S("QType:", "iSCSI");
+		R("RspQ ID:", rspq.abs_id);
+		R("RspQ size:", rspq.size);
+		R("RspQE size:", rspq.iqe_len);
+		R("RspQ CIDX:", rspq.cidx);
+		R("RspQ Gen:", rspq.gen);
+		S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq));
+		S3("u", "Intr pktcnt:",	s->counter_val[rx[i].rspq.pktcnt_idx]);
+		R("FL ID:", fl.cntxt_id);
+		R("FL size:", fl.size - 8);
+		R("FL pend:", fl.pend_cred);
+		R("FL avail:", fl.avail);
+		R("FL PIDX:", fl.pidx);
+		R("FL CIDX:", fl.cidx);
+
+		goto unlock;
+	}
+
+	r -= uld_rxq_entries[CXGB4_ULD_ISCSI];
+	if (r < uld_rxq_entries[CXGB4_ULD_ISCSIT]) {
+		const struct sge_ofld_rxq *rx;
+
+		urxq_info = s->uld_rxq_info[CXGB4_ULD_ISCSIT];
+		rx = &urxq_info->uldrxq[r * 4];
+		n = min(4, urxq_info->nrxq - 4 * r);
+
+		S("QType:", "iSCSIT");
+		R("RspQ ID:", rspq.abs_id);
+		R("RspQ size:", rspq.size);
+		R("RspQE size:", rspq.iqe_len);
+		R("RspQ CIDX:", rspq.cidx);
+		R("RspQ Gen:", rspq.gen);
+		S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq));
+		S3("u", "Intr pktcnt:",	s->counter_val[rx[i].rspq.pktcnt_idx]);
+		R("FL ID:", fl.cntxt_id);
+		R("FL size:", fl.size - 8);
+		R("FL pend:", fl.pend_cred);
+		R("FL avail:", fl.avail);
+		R("FL PIDX:", fl.pidx);
+		R("FL CIDX:", fl.cidx);
+
+		goto unlock;
+	}
+
+	r -= uld_rxq_entries[CXGB4_ULD_ISCSIT];
+	if (r < uld_rxq_entries[CXGB4_ULD_TLS]) {
+		const struct sge_ofld_rxq *rx;
+
+		urxq_info = s->uld_rxq_info[CXGB4_ULD_TLS];
+		rx = &urxq_info->uldrxq[r * 4];
+		n = min(4, urxq_info->nrxq - 4 * r);
+
+		S("QType:", "TLS");
+		R("RspQ ID:", rspq.abs_id);
+		R("RspQ size:", rspq.size);
+		R("RspQE size:", rspq.iqe_len);
+		R("RspQ CIDX:", rspq.cidx);
+		R("RspQ Gen:", rspq.gen);
+		S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq));
+		S3("u", "Intr pktcnt:",	s->counter_val[rx[i].rspq.pktcnt_idx]);
+		R("FL ID:", fl.cntxt_id);
+		R("FL size:", fl.size - 8);
+		R("FL pend:", fl.pend_cred);
+		R("FL avail:", fl.avail);
+		R("FL PIDX:", fl.pidx);
+		R("FL CIDX:", fl.cidx);
+
+		goto unlock;
+	}
+
+	r -= uld_rxq_entries[CXGB4_ULD_TLS];
+	if (r < uld_txq_entries[CXGB4_TX_CRYPTO]) {
+		const struct sge_ofld_rxq *rx;
+		const struct sge_uld_txq *tx;
+
+		utxq_info = s->uld_txq_info[CXGB4_TX_CRYPTO];
+		urxq_info = s->uld_rxq_info[CXGB4_ULD_CRYPTO];
+		tx = &utxq_info->uldtxq[r * 4];
+		rx = &urxq_info->uldrxq[r * 4];
+		n = min(4, utxq_info->ntxq - 4 * r);
+
+		S("QType:", "Crypto");
+		T("TxQ ID:", q.cntxt_id);
+		T("TxQ size:", q.size);
+		T("TxQ inuse:", q.in_use);
+		T("TxQ CIDX:", q.cidx);
+		T("TxQ PIDX:", q.pidx);
+		R("RspQ ID:", rspq.abs_id);
+		R("RspQ size:", rspq.size);
+		R("RspQE size:", rspq.iqe_len);
+		R("RspQ CIDX:", rspq.cidx);
+		R("RspQ Gen:", rspq.gen);
+		S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq));
+		S3("u", "Intr pktcnt:",	s->counter_val[rx[i].rspq.pktcnt_idx]);
+		R("FL ID:", fl.cntxt_id);
+		R("FL size:", fl.size - 8);
+		R("FL pend:", fl.pend_cred);
+		R("FL avail:", fl.avail);
+		R("FL PIDX:", fl.pidx);
+		R("FL CIDX:", fl.cidx);
+
+		goto unlock;
+	}
+
+	r -= uld_txq_entries[CXGB4_TX_CRYPTO];
+	if (r < ctrl_entries) {
+		const struct sge_ctrl_txq *tx = &s->ctrlq[r * 4];
+
+		n = min(4, adap->params.nports - 4 * r);
 
 		S("QType:", "Control");
 		T("TxQ ID:", q.cntxt_id);
@@ -2532,8 +2995,13 @@ do { \
 		T("TxQ PIDX:", q.pidx);
 		TL("TxQFull:", q.stops);
 		TL("TxQRestarts:", q.restarts);
-	} else if (fq_idx == 0) {
-		const struct sge_rspq *evtq = &adap->sge.fw_evtq;
+
+		goto unlock;
+	}
+
+	r -= ctrl_entries;
+	if (r < 1) {
+		const struct sge_rspq *evtq = &s->fw_evtq;
 
 		seq_printf(seq, "%-12s %16s\n", "QType:", "FW event queue");
 		seq_printf(seq, "%-12s %16u\n", "RspQ ID:", evtq->abs_id);
@@ -2544,8 +3012,13 @@ do { \
 		seq_printf(seq, "%-12s %16u\n", "Intr delay:",
 			   qtimer_val(adap, evtq));
 		seq_printf(seq, "%-12s %16u\n", "Intr pktcnt:",
-			   adap->sge.counter_val[evtq->pktcnt_idx]);
+			   s->counter_val[evtq->pktcnt_idx]);
+
+		goto unlock;
 	}
+
+unlock:
+	mutex_unlock(&uld_mutex);
 #undef R
 #undef RL
 #undef T
@@ -2559,8 +3032,21 @@ do { \
 
 static int sge_queue_entries(const struct adapter *adap)
 {
+	int tot_uld_entries = 0;
+	int i;
+
+	mutex_lock(&uld_mutex);
+	for (i = 0; i < CXGB4_TX_MAX; i++)
+		tot_uld_entries += sge_qinfo_uld_txq_entries(adap, i);
+
+	for (i = 0; i < CXGB4_ULD_MAX; i++) {
+		tot_uld_entries += sge_qinfo_uld_rxq_entries(adap, i);
+		tot_uld_entries += sge_qinfo_uld_ciq_entries(adap, i);
+	}
+	mutex_unlock(&uld_mutex);
+
 	return DIV_ROUND_UP(adap->sge.ethqsets, 4) +
-	       DIV_ROUND_UP(adap->sge.ofldqsets, 4) +
+	       tot_uld_entries +
 	       DIV_ROUND_UP(MAX_CTRL_QUEUES, 4) + 1;
 }
 
@@ -2851,15 +3337,17 @@ static int meminfo_show(struct seq_file *seq, void *v)
 	mem_region_show(seq, "uP Extmem2:", meminfo.up_extmem2_lo,
 			meminfo.up_extmem2_hi);
 
-	seq_printf(seq, "\n%u Rx pages of size %uKiB for %u channels\n",
-		   meminfo.rx_pages_data[0], meminfo.rx_pages_data[1],
-		   meminfo.rx_pages_data[2]);
+	seq_printf(seq, "\n%u Rx pages (%u free) of size %uKiB for %u channels\n",
+		   meminfo.rx_pages_data[0], meminfo.free_rx_cnt,
+		   meminfo.rx_pages_data[1], meminfo.rx_pages_data[2]);
 
-	seq_printf(seq, "%u Tx pages of size %u%ciB for %u channels\n",
-		   meminfo.tx_pages_data[0], meminfo.tx_pages_data[1],
-		   meminfo.tx_pages_data[2], meminfo.tx_pages_data[3]);
+	seq_printf(seq, "%u Tx pages (%u free) of size %u%ciB for %u channels\n",
+		   meminfo.tx_pages_data[0], meminfo.free_tx_cnt,
+		   meminfo.tx_pages_data[1], meminfo.tx_pages_data[2],
+		   meminfo.tx_pages_data[3]);
 
-	seq_printf(seq, "%u p-structs\n\n", meminfo.p_structs);
+	seq_printf(seq, "%u p-structs (%u free)\n\n",
+		   meminfo.p_structs, meminfo.p_structs_free_cnt);
 
 	for (i = 0; i < 4; i++)
 		/* For T6 these are MAC buffer groups */
@@ -2924,6 +3412,169 @@ static const struct file_operations chcr_stats_debugfs_fops = {
         .llseek  = seq_lseek,
         .release = single_release,
 };
+
+#define PRINT_ADAP_STATS(string, value) \
+	seq_printf(seq, "%-25s %-20llu\n", (string), \
+		   (unsigned long long)(value))
+
+#define PRINT_CH_STATS(string, value) \
+do { \
+	seq_printf(seq, "%-25s ", (string)); \
+	for (i = 0; i < adap->params.arch.nchan; i++) \
+		seq_printf(seq, "%-20llu ", \
+			   (unsigned long long)stats.value[i]); \
+	seq_printf(seq, "\n"); \
+} while (0)
+
+#define PRINT_CH_STATS2(string, value) \
+do { \
+	seq_printf(seq, "%-25s ", (string)); \
+	for (i = 0; i < adap->params.arch.nchan; i++) \
+		seq_printf(seq, "%-20llu ", \
+			   (unsigned long long)stats[i].value); \
+	seq_printf(seq, "\n"); \
+} while (0)
+
+static void show_tcp_stats(struct seq_file *seq)
+{
+	struct adapter *adap = seq->private;
+	struct tp_tcp_stats v4, v6;
+
+	spin_lock(&adap->stats_lock);
+	t4_tp_get_tcp_stats(adap, &v4, &v6, false);
+	spin_unlock(&adap->stats_lock);
+
+	PRINT_ADAP_STATS("tcp_ipv4_out_rsts:", v4.tcp_out_rsts);
+	PRINT_ADAP_STATS("tcp_ipv4_in_segs:", v4.tcp_in_segs);
+	PRINT_ADAP_STATS("tcp_ipv4_out_segs:", v4.tcp_out_segs);
+	PRINT_ADAP_STATS("tcp_ipv4_retrans_segs:", v4.tcp_retrans_segs);
+	PRINT_ADAP_STATS("tcp_ipv6_out_rsts:", v6.tcp_out_rsts);
+	PRINT_ADAP_STATS("tcp_ipv6_in_segs:", v6.tcp_in_segs);
+	PRINT_ADAP_STATS("tcp_ipv6_out_segs:", v6.tcp_out_segs);
+	PRINT_ADAP_STATS("tcp_ipv6_retrans_segs:", v6.tcp_retrans_segs);
+}
+
+static void show_ddp_stats(struct seq_file *seq)
+{
+	struct adapter *adap = seq->private;
+	struct tp_usm_stats stats;
+
+	spin_lock(&adap->stats_lock);
+	t4_get_usm_stats(adap, &stats, false);
+	spin_unlock(&adap->stats_lock);
+
+	PRINT_ADAP_STATS("usm_ddp_frames:", stats.frames);
+	PRINT_ADAP_STATS("usm_ddp_octets:", stats.octets);
+	PRINT_ADAP_STATS("usm_ddp_drops:", stats.drops);
+}
+
+static void show_rdma_stats(struct seq_file *seq)
+{
+	struct adapter *adap = seq->private;
+	struct tp_rdma_stats stats;
+
+	spin_lock(&adap->stats_lock);
+	t4_tp_get_rdma_stats(adap, &stats, false);
+	spin_unlock(&adap->stats_lock);
+
+	PRINT_ADAP_STATS("rdma_no_rqe_mod_defer:", stats.rqe_dfr_mod);
+	PRINT_ADAP_STATS("rdma_no_rqe_pkt_defer:", stats.rqe_dfr_pkt);
+}
+
+static void show_tp_err_adapter_stats(struct seq_file *seq)
+{
+	struct adapter *adap = seq->private;
+	struct tp_err_stats stats;
+
+	spin_lock(&adap->stats_lock);
+	t4_tp_get_err_stats(adap, &stats, false);
+	spin_unlock(&adap->stats_lock);
+
+	PRINT_ADAP_STATS("tp_err_ofld_no_neigh:", stats.ofld_no_neigh);
+	PRINT_ADAP_STATS("tp_err_ofld_cong_defer:", stats.ofld_cong_defer);
+}
+
+static void show_cpl_stats(struct seq_file *seq)
+{
+	struct adapter *adap = seq->private;
+	struct tp_cpl_stats stats;
+	u8 i;
+
+	spin_lock(&adap->stats_lock);
+	t4_tp_get_cpl_stats(adap, &stats, false);
+	spin_unlock(&adap->stats_lock);
+
+	PRINT_CH_STATS("tp_cpl_requests:", req);
+	PRINT_CH_STATS("tp_cpl_responses:", rsp);
+}
+
+static void show_tp_err_channel_stats(struct seq_file *seq)
+{
+	struct adapter *adap = seq->private;
+	struct tp_err_stats stats;
+	u8 i;
+
+	spin_lock(&adap->stats_lock);
+	t4_tp_get_err_stats(adap, &stats, false);
+	spin_unlock(&adap->stats_lock);
+
+	PRINT_CH_STATS("tp_mac_in_errs:", mac_in_errs);
+	PRINT_CH_STATS("tp_hdr_in_errs:", hdr_in_errs);
+	PRINT_CH_STATS("tp_tcp_in_errs:", tcp_in_errs);
+	PRINT_CH_STATS("tp_tcp6_in_errs:", tcp6_in_errs);
+	PRINT_CH_STATS("tp_tnl_cong_drops:", tnl_cong_drops);
+	PRINT_CH_STATS("tp_tnl_tx_drops:", tnl_tx_drops);
+	PRINT_CH_STATS("tp_ofld_vlan_drops:", ofld_vlan_drops);
+	PRINT_CH_STATS("tp_ofld_chan_drops:", ofld_chan_drops);
+}
+
+static void show_fcoe_stats(struct seq_file *seq)
+{
+	struct adapter *adap = seq->private;
+	struct tp_fcoe_stats stats[NCHAN];
+	u8 i;
+
+	spin_lock(&adap->stats_lock);
+	for (i = 0; i < adap->params.arch.nchan; i++)
+		t4_get_fcoe_stats(adap, i, &stats[i], false);
+	spin_unlock(&adap->stats_lock);
+
+	PRINT_CH_STATS2("fcoe_octets_ddp", octets_ddp);
+	PRINT_CH_STATS2("fcoe_frames_ddp", frames_ddp);
+	PRINT_CH_STATS2("fcoe_frames_drop", frames_drop);
+}
+
+#undef PRINT_CH_STATS2
+#undef PRINT_CH_STATS
+#undef PRINT_ADAP_STATS
+
+static int tp_stats_show(struct seq_file *seq, void *v)
+{
+	struct adapter *adap = seq->private;
+
+	seq_puts(seq, "\n--------Adapter Stats--------\n");
+	show_tcp_stats(seq);
+	show_ddp_stats(seq);
+	show_rdma_stats(seq);
+	show_tp_err_adapter_stats(seq);
+
+	seq_puts(seq, "\n-------- Channel Stats --------\n");
+	if (adap->params.arch.nchan == NCHAN)
+		seq_printf(seq, "%-25s %-20s %-20s %-20s %-20s\n",
+			   " ", "channel 0", "channel 1",
+			   "channel 2", "channel 3");
+	else
+		seq_printf(seq, "%-25s %-20s %-20s\n",
+			   " ", "channel 0", "channel 1");
+	show_cpl_stats(seq);
+	show_tp_err_channel_stats(seq);
+	show_fcoe_stats(seq);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_DEBUGFS_FILE(tp_stats);
+
 /* Add an array of Debug FS files.
  */
 void add_debugfs_files(struct adapter *adap,
@@ -2973,6 +3624,10 @@ int t4_setup_debugfs(struct adapter *adap)
 		{ "rss_key", &rss_key_debugfs_fops, 0400, 0 },
 		{ "rss_pf_config", &rss_pf_config_debugfs_fops, 0400, 0 },
 		{ "rss_vf_config", &rss_vf_config_debugfs_fops, 0400, 0 },
+		{ "resources", &resources_debugfs_fops, 0400, 0 },
+#ifdef CONFIG_CHELSIO_T4_DCB
+		{ "dcb_info", &dcb_info_debugfs_fops, 0400, 0 },
+#endif
 		{ "sge_qinfo", &sge_qinfo_debugfs_fops, 0400, 0 },
 		{ "ibq_tp0",  &cim_ibq_fops, 0400, 0 },
 		{ "ibq_tp1",  &cim_ibq_fops, 0400, 1 },
@@ -2999,6 +3654,7 @@ int t4_setup_debugfs(struct adapter *adap)
 		{ "blocked_fl", &blocked_fl_fops, 0600, 0 },
 		{ "meminfo", &meminfo_fops, 0400, 0 },
 		{ "crypto", &chcr_stats_debugfs_fops, 0400, 0 },
+		{ "tp_stats", &tp_stats_debugfs_fops, 0400, 0 },
 	};
 
 	/* Debug FS nodes common to all T5 and later adapters.
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index f7eef93ffc87..d07230c892a5 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -115,42 +115,10 @@ static char adapter_stats_strings[][ETH_GSTRING_LEN] = {
 	"db_drop                ",
 	"db_full                ",
 	"db_empty               ",
-	"tcp_ipv4_out_rsts      ",
-	"tcp_ipv4_in_segs       ",
-	"tcp_ipv4_out_segs      ",
-	"tcp_ipv4_retrans_segs  ",
-	"tcp_ipv6_out_rsts      ",
-	"tcp_ipv6_in_segs       ",
-	"tcp_ipv6_out_segs      ",
-	"tcp_ipv6_retrans_segs  ",
-	"usm_ddp_frames         ",
-	"usm_ddp_octets         ",
-	"usm_ddp_drops          ",
-	"rdma_no_rqe_mod_defer  ",
-	"rdma_no_rqe_pkt_defer  ",
-	"tp_err_ofld_no_neigh   ",
-	"tp_err_ofld_cong_defer ",
 	"write_coal_success     ",
 	"write_coal_fail        ",
 };
 
-static char channel_stats_strings[][ETH_GSTRING_LEN] = {
-	"--------Channel--------- ",
-	"tp_cpl_requests        ",
-	"tp_cpl_responses       ",
-	"tp_mac_in_errs         ",
-	"tp_hdr_in_errs         ",
-	"tp_tcp_in_errs         ",
-	"tp_tcp6_in_errs        ",
-	"tp_tnl_cong_drops      ",
-	"tp_tnl_tx_drops        ",
-	"tp_ofld_vlan_drops     ",
-	"tp_ofld_chan_drops     ",
-	"fcoe_octets_ddp        ",
-	"fcoe_frames_ddp        ",
-	"fcoe_frames_drop       ",
-};
-
 static char loopback_stats_strings[][ETH_GSTRING_LEN] = {
 	"-------Loopback----------- ",
 	"octets_ok              ",
@@ -177,14 +145,19 @@ static char loopback_stats_strings[][ETH_GSTRING_LEN] = {
 	"bg3_frames_trunc       ",
 };
 
+static const char cxgb4_priv_flags_strings[][ETH_GSTRING_LEN] = {
+	[PRIV_FLAG_PORT_TX_VM_BIT] = "port_tx_vm_wr",
+};
+
 static int get_sset_count(struct net_device *dev, int sset)
 {
 	switch (sset) {
 	case ETH_SS_STATS:
 		return ARRAY_SIZE(stats_strings) +
 		       ARRAY_SIZE(adapter_stats_strings) +
-		       ARRAY_SIZE(channel_stats_strings) +
 		       ARRAY_SIZE(loopback_stats_strings);
+	case ETH_SS_PRIV_FLAGS:
+		return ARRAY_SIZE(cxgb4_priv_flags_strings);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -235,6 +208,7 @@ static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 			 FW_HDR_FW_VER_MINOR_G(exprom_vers),
 			 FW_HDR_FW_VER_MICRO_G(exprom_vers),
 			 FW_HDR_FW_VER_BUILD_G(exprom_vers));
+	info->n_priv_flags = ARRAY_SIZE(cxgb4_priv_flags_strings);
 }
 
 static void get_strings(struct net_device *dev, u32 stringset, u8 *data)
@@ -245,11 +219,11 @@ static void get_strings(struct net_device *dev, u32 stringset, u8 *data)
 		memcpy(data, adapter_stats_strings,
 		       sizeof(adapter_stats_strings));
 		data += sizeof(adapter_stats_strings);
-		memcpy(data, channel_stats_strings,
-		       sizeof(channel_stats_strings));
-		data += sizeof(channel_stats_strings);
 		memcpy(data, loopback_stats_strings,
 		       sizeof(loopback_stats_strings));
+	} else if (stringset == ETH_SS_PRIV_FLAGS) {
+		memcpy(data, cxgb4_priv_flags_strings,
+		       sizeof(cxgb4_priv_flags_strings));
 	}
 }
 
@@ -270,41 +244,10 @@ struct adapter_stats {
 	u64 db_drop;
 	u64 db_full;
 	u64 db_empty;
-	u64 tcp_v4_out_rsts;
-	u64 tcp_v4_in_segs;
-	u64 tcp_v4_out_segs;
-	u64 tcp_v4_retrans_segs;
-	u64 tcp_v6_out_rsts;
-	u64 tcp_v6_in_segs;
-	u64 tcp_v6_out_segs;
-	u64 tcp_v6_retrans_segs;
-	u64 frames;
-	u64 octets;
-	u64 drops;
-	u64 rqe_dfr_mod;
-	u64 rqe_dfr_pkt;
-	u64 ofld_no_neigh;
-	u64 ofld_cong_defer;
 	u64 wc_success;
 	u64 wc_fail;
 };
 
-struct channel_stats {
-	u64 cpl_req;
-	u64 cpl_rsp;
-	u64 mac_in_errs;
-	u64 hdr_in_errs;
-	u64 tcp_in_errs;
-	u64 tcp6_in_errs;
-	u64 tnl_cong_drops;
-	u64 tnl_tx_drops;
-	u64 ofld_vlan_drops;
-	u64 ofld_chan_drops;
-	u64 octets_ddp;
-	u64 frames_ddp;
-	u64 frames_drop;
-};
-
 static void collect_sge_port_stats(const struct adapter *adap,
 				   const struct port_info *p,
 				   struct queue_port_stats *s)
@@ -327,45 +270,14 @@ static void collect_sge_port_stats(const struct adapter *adap,
 
 static void collect_adapter_stats(struct adapter *adap, struct adapter_stats *s)
 {
-	struct tp_tcp_stats v4, v6;
-	struct tp_rdma_stats rdma_stats;
-	struct tp_err_stats err_stats;
-	struct tp_usm_stats usm_stats;
 	u64 val1, val2;
 
 	memset(s, 0, sizeof(*s));
 
-	spin_lock(&adap->stats_lock);
-	t4_tp_get_tcp_stats(adap, &v4, &v6, false);
-	t4_tp_get_rdma_stats(adap, &rdma_stats, false);
-	t4_get_usm_stats(adap, &usm_stats, false);
-	t4_tp_get_err_stats(adap, &err_stats, false);
-	spin_unlock(&adap->stats_lock);
-
 	s->db_drop = adap->db_stats.db_drop;
 	s->db_full = adap->db_stats.db_full;
 	s->db_empty = adap->db_stats.db_empty;
 
-	s->tcp_v4_out_rsts = v4.tcp_out_rsts;
-	s->tcp_v4_in_segs = v4.tcp_in_segs;
-	s->tcp_v4_out_segs = v4.tcp_out_segs;
-	s->tcp_v4_retrans_segs = v4.tcp_retrans_segs;
-	s->tcp_v6_out_rsts = v6.tcp_out_rsts;
-	s->tcp_v6_in_segs = v6.tcp_in_segs;
-	s->tcp_v6_out_segs = v6.tcp_out_segs;
-	s->tcp_v6_retrans_segs = v6.tcp_retrans_segs;
-
-	if (is_offload(adap)) {
-		s->frames = usm_stats.frames;
-		s->octets = usm_stats.octets;
-		s->drops = usm_stats.drops;
-		s->rqe_dfr_mod = rdma_stats.rqe_dfr_mod;
-		s->rqe_dfr_pkt = rdma_stats.rqe_dfr_pkt;
-	}
-
-	s->ofld_no_neigh = err_stats.ofld_no_neigh;
-	s->ofld_cong_defer = err_stats.ofld_cong_defer;
-
 	if (!is_t4(adap->params.chip)) {
 		int v;
 
@@ -379,36 +291,6 @@ static void collect_adapter_stats(struct adapter *adap, struct adapter_stats *s)
 	}
 }
 
-static void collect_channel_stats(struct adapter *adap, struct channel_stats *s,
-				  u8 i)
-{
-	struct tp_cpl_stats cpl_stats;
-	struct tp_err_stats err_stats;
-	struct tp_fcoe_stats fcoe_stats;
-
-	memset(s, 0, sizeof(*s));
-
-	spin_lock(&adap->stats_lock);
-	t4_tp_get_cpl_stats(adap, &cpl_stats, false);
-	t4_tp_get_err_stats(adap, &err_stats, false);
-	t4_get_fcoe_stats(adap, i, &fcoe_stats, false);
-	spin_unlock(&adap->stats_lock);
-
-	s->cpl_req = cpl_stats.req[i];
-	s->cpl_rsp = cpl_stats.rsp[i];
-	s->mac_in_errs = err_stats.mac_in_errs[i];
-	s->hdr_in_errs = err_stats.hdr_in_errs[i];
-	s->tcp_in_errs = err_stats.tcp_in_errs[i];
-	s->tcp6_in_errs = err_stats.tcp6_in_errs[i];
-	s->tnl_cong_drops = err_stats.tnl_cong_drops[i];
-	s->tnl_tx_drops = err_stats.tnl_tx_drops[i];
-	s->ofld_vlan_drops = err_stats.ofld_vlan_drops[i];
-	s->ofld_chan_drops = err_stats.ofld_chan_drops[i];
-	s->octets_ddp = fcoe_stats.octets_ddp;
-	s->frames_ddp = fcoe_stats.frames_ddp;
-	s->frames_drop = fcoe_stats.frames_drop;
-}
-
 static void get_stats(struct net_device *dev, struct ethtool_stats *stats,
 		      u64 *data)
 {
@@ -429,11 +311,6 @@ static void get_stats(struct net_device *dev, struct ethtool_stats *stats,
 	data += sizeof(struct adapter_stats) / sizeof(u64);
 
 	*data++ = (u64)pi->port_id;
-	collect_channel_stats(adapter, (struct channel_stats *)data,
-			      pi->port_id);
-	data += sizeof(struct channel_stats) / sizeof(u64);
-
-	*data++ = (u64)pi->port_id;
 	memset(&s, 0, sizeof(s));
 	t4_get_lb_stats(adapter, pi->port_id, &s);
 
@@ -751,13 +628,10 @@ static int get_link_ksettings(struct net_device *dev,
 	fw_caps_to_lmm(pi->port_type, pi->link_cfg.lpacaps,
 		       link_ksettings->link_modes.lp_advertising);
 
-	if (netif_carrier_ok(dev)) {
-		base->speed = pi->link_cfg.speed;
-		base->duplex = DUPLEX_FULL;
-	} else {
-		base->speed = SPEED_UNKNOWN;
-		base->duplex = DUPLEX_UNKNOWN;
-	}
+	base->speed = (netif_carrier_ok(dev)
+		       ? pi->link_cfg.speed
+		       : SPEED_UNKNOWN);
+	base->duplex = DUPLEX_FULL;
 
 	if (pi->link_cfg.fc & PAUSE_RX) {
 		if (pi->link_cfg.fc & PAUSE_TX) {
@@ -1499,6 +1373,36 @@ static int cxgb4_get_module_eeprom(struct net_device *dev,
 			 offset, len, &data[eprom->len - len]);
 }
 
+static u32 cxgb4_get_priv_flags(struct net_device *netdev)
+{
+	struct port_info *pi = netdev_priv(netdev);
+	struct adapter *adapter = pi->adapter;
+
+	return (adapter->eth_flags | pi->eth_flags);
+}
+
+/**
+ *	set_flags - set/unset specified flags if passed in new_flags
+ *	@cur_flags: pointer to current flags
+ *	@new_flags: new incoming flags
+ *	@flags: set of flags to set/unset
+ */
+static inline void set_flags(u32 *cur_flags, u32 new_flags, u32 flags)
+{
+	*cur_flags = (*cur_flags & ~flags) | (new_flags & flags);
+}
+
+static int cxgb4_set_priv_flags(struct net_device *netdev, u32 flags)
+{
+	struct port_info *pi = netdev_priv(netdev);
+	struct adapter *adapter = pi->adapter;
+
+	set_flags(&adapter->eth_flags, flags, PRIV_FLAGS_ADAP);
+	set_flags(&pi->eth_flags, flags, PRIV_FLAGS_PORT);
+
+	return 0;
+}
+
 static const struct ethtool_ops cxgb_ethtool_ops = {
 	.get_link_ksettings = get_link_ksettings,
 	.set_link_ksettings = set_link_ksettings,
@@ -1535,6 +1439,8 @@ static const struct ethtool_ops cxgb_ethtool_ops = {
 	.get_dump_data     = get_dump_data,
 	.get_module_info   = cxgb4_get_module_info,
 	.get_module_eeprom = cxgb4_get_module_eeprom,
+	.get_priv_flags    = cxgb4_get_priv_flags,
+	.set_priv_flags    = cxgb4_set_priv_flags,
 };
 
 void cxgb4_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index a8926e97935e..961e3087d1d3 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -267,7 +267,7 @@ static void dcb_tx_queue_prio_enable(struct net_device *dev, int enable)
 	}
 }
 
-static int cxgb4_dcb_enabled(const struct net_device *dev)
+int cxgb4_dcb_enabled(const struct net_device *dev)
 {
 	struct port_info *pi = netdev_priv(dev);
 
@@ -554,10 +554,9 @@ static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp,
 
 			dev = q->adap->port[q->adap->chan_map[port]];
 			dcbxdis = (action == FW_PORT_ACTION_GET_PORT_INFO
-				   ? !!(pcmd->u.info.dcbxdis_pkd &
-					FW_PORT_CMD_DCBXDIS_F)
-				   : !!(pcmd->u.info32.lstatus32_to_cbllen32 &
-					FW_PORT_CMD_DCBXDIS32_F));
+			  ? !!(pcmd->u.info.dcbxdis_pkd & FW_PORT_CMD_DCBXDIS_F)
+			  : !!(be32_to_cpu(pcmd->u.info32.lstatus32_to_cbllen32)
+			       & FW_PORT_CMD_DCBXDIS32_F));
 			state_input = (dcbxdis
 				       ? CXGB4_DCB_INPUT_FW_DISABLED
 				       : CXGB4_DCB_INPUT_FW_ENABLED);
@@ -924,12 +923,14 @@ static int setup_sge_queues(struct adapter *adap)
 		     QUEUENUMBER_V(s->ethrxq[0].rspq.abs_id));
 	return 0;
 freeout:
+	dev_err(adap->pdev_dev, "Can't allocate queues, err=%d\n", -err);
 	t4_free_sge_resources(adap);
 	return err;
 }
 
 static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     void *accel_priv, select_queue_fallback_t fallback)
+			     struct net_device *sb_dev,
+			     select_queue_fallback_t fallback)
 {
 	int txq;
 
@@ -971,7 +972,7 @@ static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb,
 		return txq;
 	}
 
-	return fallback(dev, skb) % dev->real_num_tx_queues;
+	return fallback(dev, skb, NULL) % dev->real_num_tx_queues;
 }
 
 static int closest_timer(const struct sge *s, int time)
@@ -3016,7 +3017,7 @@ static int cxgb_setup_tc_block(struct net_device *dev,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, cxgb_setup_tc_block_cb,
-					     pi, dev);
+					     pi, dev, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, cxgb_setup_tc_block_cb, pi);
 		return 0;
@@ -3219,7 +3220,7 @@ static netdev_features_t cxgb_fix_features(struct net_device *dev,
 static const struct net_device_ops cxgb4_netdev_ops = {
 	.ndo_open             = cxgb_open,
 	.ndo_stop             = cxgb_close,
-	.ndo_start_xmit       = t4_eth_xmit,
+	.ndo_start_xmit       = t4_start_xmit,
 	.ndo_select_queue     =	cxgb_select_queue,
 	.ndo_get_stats64      = cxgb_get_stats,
 	.ndo_set_rx_mode      = cxgb_set_rxmode,
@@ -3538,6 +3539,16 @@ static int adap_init1(struct adapter *adap, struct fw_caps_config_cmd *c)
 	u32 v;
 	int ret;
 
+	/* Now that we've successfully configured and initialized the adapter
+	 * can ask the Firmware what resources it has provisioned for us.
+	 */
+	ret = t4_get_pfres(adap);
+	if (ret) {
+		dev_err(adap->pdev_dev,
+			"Unable to retrieve resource provisioning information\n");
+		return ret;
+	}
+
 	/* get device capabilities */
 	memset(c, 0, sizeof(*c));
 	c->op_to_write = htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) |
@@ -4172,32 +4183,6 @@ static int adap_init0(struct adapter *adap)
 			goto bye;
 	}
 
-	/*
-	 * Grab VPD parameters.  This should be done after we establish a
-	 * connection to the firmware since some of the VPD parameters
-	 * (notably the Core Clock frequency) are retrieved via requests to
-	 * the firmware.  On the other hand, we need these fairly early on
-	 * so we do this right after getting ahold of the firmware.
-	 */
-	ret = t4_get_vpd_params(adap, &adap->params.vpd);
-	if (ret < 0)
-		goto bye;
-
-	/*
-	 * Find out what ports are available to us.  Note that we need to do
-	 * this before calling adap_init0_no_config() since it needs nports
-	 * and portvec ...
-	 */
-	v =
-	    FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
-	    FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_PORTVEC);
-	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, &v, &port_vec);
-	if (ret < 0)
-		goto bye;
-
-	adap->params.nports = hweight32(port_vec);
-	adap->params.portvec = port_vec;
-
 	/* If the firmware is initialized already, emit a simply note to that
 	 * effect. Otherwise, it's time to try initializing the adapter.
 	 */
@@ -4248,6 +4233,45 @@ static int adap_init0(struct adapter *adap)
 		}
 	}
 
+	/* Now that we've successfully configured and initialized the adapter
+	 * (or found it already initialized), we can ask the Firmware what
+	 * resources it has provisioned for us.
+	 */
+	ret = t4_get_pfres(adap);
+	if (ret) {
+		dev_err(adap->pdev_dev,
+			"Unable to retrieve resource provisioning information\n");
+		goto bye;
+	}
+
+	/* Grab VPD parameters.  This should be done after we establish a
+	 * connection to the firmware since some of the VPD parameters
+	 * (notably the Core Clock frequency) are retrieved via requests to
+	 * the firmware.  On the other hand, we need these fairly early on
+	 * so we do this right after getting ahold of the firmware.
+	 *
+	 * We need to do this after initializing the adapter because someone
+	 * could have FLASHed a new VPD which won't be read by the firmware
+	 * until we do the RESET ...
+	 */
+	ret = t4_get_vpd_params(adap, &adap->params.vpd);
+	if (ret < 0)
+		goto bye;
+
+	/* Find out what ports are available to us.  Note that we need to do
+	 * this before calling adap_init0_no_config() since it needs nports
+	 * and portvec ...
+	 */
+	v =
+	    FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
+	    FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_PORTVEC);
+	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, &v, &port_vec);
+	if (ret < 0)
+		goto bye;
+
+	adap->params.nports = hweight32(port_vec);
+	adap->params.portvec = port_vec;
+
 	/* Give the SGE code a chance to pull in anything that it needs ...
 	 * Note that this must be called after we retrieve our VPD parameters
 	 * in order to know how to convert core ticks to seconds, etc.
@@ -4799,10 +4823,12 @@ static inline bool is_x_10g_port(const struct link_config *lc)
  * of ports we found and the number of available CPUs.  Most settings can be
  * modified by the admin prior to actual use.
  */
-static void cfg_queues(struct adapter *adap)
+static int cfg_queues(struct adapter *adap)
 {
 	struct sge *s = &adap->sge;
-	int i = 0, n10g = 0, qidx = 0;
+	int i, n10g = 0, qidx = 0;
+	int niqflint, neq, avail_eth_qsets;
+	int max_eth_qsets = 32;
 #ifndef CONFIG_CHELSIO_T4_DCB
 	int q10g = 0;
 #endif
@@ -4814,16 +4840,46 @@ static void cfg_queues(struct adapter *adap)
 		adap->params.crypto = 0;
 	}
 
-	n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg);
+	/* Calculate the number of Ethernet Queue Sets available based on
+	 * resources provisioned for us.  We always have an Asynchronous
+	 * Firmware Event Ingress Queue.  If we're operating in MSI or Legacy
+	 * IRQ Pin Interrupt mode, then we'll also have a Forwarded Interrupt
+	 * Ingress Queue.  Meanwhile, we need two Egress Queues for each
+	 * Queue Set: one for the Free List and one for the Ethernet TX Queue.
+	 *
+	 * Note that we should also take into account all of the various
+	 * Offload Queues.  But, in any situation where we're operating in
+	 * a Resource Constrained Provisioning environment, doing any Offload
+	 * at all is problematic ...
+	 */
+	niqflint = adap->params.pfres.niqflint - 1;
+	if (!(adap->flags & USING_MSIX))
+		niqflint--;
+	neq = adap->params.pfres.neq / 2;
+	avail_eth_qsets = min(niqflint, neq);
+
+	if (avail_eth_qsets > max_eth_qsets)
+		avail_eth_qsets = max_eth_qsets;
+
+	if (avail_eth_qsets < adap->params.nports) {
+		dev_err(adap->pdev_dev, "avail_eth_qsets=%d < nports=%d\n",
+			avail_eth_qsets, adap->params.nports);
+		return -ENOMEM;
+	}
+
+	/* Count the number of 10Gb/s or better ports */
+	for_each_port(adap, i)
+		n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg);
+
 #ifdef CONFIG_CHELSIO_T4_DCB
 	/* For Data Center Bridging support we need to be able to support up
 	 * to 8 Traffic Priorities; each of which will be assigned to its
 	 * own TX Queue in order to prevent Head-Of-Line Blocking.
 	 */
-	if (adap->params.nports * 8 > MAX_ETH_QSETS) {
-		dev_err(adap->pdev_dev, "MAX_ETH_QSETS=%d < %d!\n",
-			MAX_ETH_QSETS, adap->params.nports * 8);
-		BUG_ON(1);
+	if (adap->params.nports * 8 > avail_eth_qsets) {
+		dev_err(adap->pdev_dev, "DCB avail_eth_qsets=%d < %d!\n",
+			avail_eth_qsets, adap->params.nports * 8);
+		return -ENOMEM;
 	}
 
 	for_each_port(adap, i) {
@@ -4839,7 +4895,7 @@ static void cfg_queues(struct adapter *adap)
 	 * per 10G port.
 	 */
 	if (n10g)
-		q10g = (MAX_ETH_QSETS - (adap->params.nports - n10g)) / n10g;
+		q10g = (avail_eth_qsets - (adap->params.nports - n10g)) / n10g;
 	if (q10g > netif_get_num_default_rss_queues())
 		q10g = netif_get_num_default_rss_queues();
 
@@ -4890,6 +4946,8 @@ static void cfg_queues(struct adapter *adap)
 
 	init_rspq(adap, &s->fw_evtq, 0, 1, 1024, 64);
 	init_rspq(adap, &s->intrq, 0, 1, 512, 64);
+
+	return 0;
 }
 
 /*
@@ -5086,17 +5144,9 @@ static void print_port_info(const struct net_device *dev)
 {
 	char buf[80];
 	char *bufp = buf;
-	const char *spd = "";
 	const struct port_info *pi = netdev_priv(dev);
 	const struct adapter *adap = pi->adapter;
 
-	if (adap->params.pci.speed == PCI_EXP_LNKSTA_CLS_2_5GB)
-		spd = " 2.5 GT/s";
-	else if (adap->params.pci.speed == PCI_EXP_LNKSTA_CLS_5_0GB)
-		spd = " 5 GT/s";
-	else if (adap->params.pci.speed == PCI_EXP_LNKSTA_CLS_8_0GB)
-		spd = " 8 GT/s";
-
 	if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_100M)
 		bufp += sprintf(bufp, "100M/");
 	if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_1G)
@@ -5600,6 +5650,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 #ifdef CONFIG_CHELSIO_T4_DCB
 		netdev->dcbnl_ops = &cxgb4_dcb_ops;
 		cxgb4_dcb_state_init(netdev);
+		cxgb4_dcb_version_init(netdev);
 #endif
 		cxgb4_set_ethtool_ops(netdev);
 	}
@@ -5630,10 +5681,15 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		}
 	}
 
+	if (!(adapter->flags & FW_OK))
+		goto fw_attach_fail;
+
 	/* Configure queues and allocate tables now, they can be needed as
 	 * soon as the first register_netdev completes.
 	 */
-	cfg_queues(adapter);
+	err = cfg_queues(adapter);
+	if (err)
+		goto out_free_dev;
 
 	adapter->smt = t4_init_smt();
 	if (!adapter->smt) {
@@ -5705,7 +5761,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		if (t4_read_reg(adapter, LE_DB_CONFIG_A) & HASHEN_F) {
 			u32 hash_base, hash_reg;
 
-			if (chip <= CHELSIO_T5) {
+			if (chip_ver <= CHELSIO_T5) {
 				hash_reg = LE_DB_TID_HASHBASE_A;
 				hash_base = t4_read_reg(adapter, hash_reg);
 				adapter->tids.hash_base = hash_base / 4;
@@ -5740,6 +5796,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto out_free_dev;
 	}
 
+fw_attach_fail:
 	/*
 	 * The card is now ready to go.  If any errors occur during device
 	 * registration we do not fail the whole card but rather proceed only
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
index 3ddd2c4acf68..623f73dd7738 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
@@ -874,6 +874,9 @@ int cxgb4_init_tc_flower(struct adapter *adap)
 {
 	int ret;
 
+	if (adap->tc_flower_initialized)
+		return -EEXIST;
+
 	adap->flower_ht_params = cxgb4_tc_flower_ht_params;
 	ret = rhashtable_init(&adap->flower_tbl, &adap->flower_ht_params);
 	if (ret)
@@ -882,13 +885,18 @@ int cxgb4_init_tc_flower(struct adapter *adap)
 	INIT_WORK(&adap->flower_stats_work, ch_flower_stats_handler);
 	timer_setup(&adap->flower_stats_timer, ch_flower_stats_cb, 0);
 	mod_timer(&adap->flower_stats_timer, jiffies + STATS_CHECK_PERIOD);
+	adap->tc_flower_initialized = true;
 	return 0;
 }
 
 void cxgb4_cleanup_tc_flower(struct adapter *adap)
 {
+	if (!adap->tc_flower_initialized)
+		return;
+
 	if (adap->flower_stats_timer.function)
 		del_timer_sync(&adap->flower_stats_timer);
 	cancel_work_sync(&adap->flower_stats_work);
 	rhashtable_destroy(&adap->flower_tbl);
+	adap->tc_flower_initialized = false;
 }
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
index 77c2c538b1fd..301c4df8a566 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
@@ -231,6 +231,7 @@ again:
 		if (e->state == L2T_STATE_STALE)
 			e->state = L2T_STATE_VALID;
 		spin_unlock_bh(&e->lock);
+		/* fall through */
 	case L2T_STATE_VALID:     /* fast-path, send the packet on */
 		return t4_ofld_send(adap, skb);
 	case L2T_STATE_RESOLVING:
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.c b/drivers/net/ethernet/chelsio/cxgb4/sched.c
index 9148abb7994c..7fc656680299 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sched.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sched.c
@@ -539,6 +539,9 @@ void t4_cleanup_sched(struct adapter *adap)
 		struct port_info *pi = netdev2pinfo(adap->port[j]);
 
 		s = pi->sched_tbl;
+		if (!s)
+			continue;
+
 		for (i = 0; i < s->sched_size; i++) {
 			struct sched_class *e;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 395e2a0e8d7f..6807bc3a44fb 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -1288,13 +1288,13 @@ static inline void t6_fill_tnl_lso(struct sk_buff *skb,
 }
 
 /**
- *	t4_eth_xmit - add a packet to an Ethernet Tx queue
+ *	cxgb4_eth_xmit - add a packet to an Ethernet Tx queue
  *	@skb: the packet
  *	@dev: the egress net device
  *
  *	Add a packet to an SGE Ethernet Tx queue.  Runs with softirqs disabled.
  */
-netdev_tx_t t4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	u32 wr_mid, ctrl0, op;
 	u64 cntrl, *end, *sgl;
@@ -1547,6 +1547,374 @@ out_free:	dev_kfree_skb_any(skb);
 	return NETDEV_TX_OK;
 }
 
+/* Constants ... */
+enum {
+	/* Egress Queue sizes, producer and consumer indices are all in units
+	 * of Egress Context Units bytes.  Note that as far as the hardware is
+	 * concerned, the free list is an Egress Queue (the host produces free
+	 * buffers which the hardware consumes) and free list entries are
+	 * 64-bit PCI DMA addresses.
+	 */
+	EQ_UNIT = SGE_EQ_IDXSIZE,
+	FL_PER_EQ_UNIT = EQ_UNIT / sizeof(__be64),
+	TXD_PER_EQ_UNIT = EQ_UNIT / sizeof(__be64),
+
+	T4VF_ETHTXQ_MAX_HDR = (sizeof(struct fw_eth_tx_pkt_vm_wr) +
+			       sizeof(struct cpl_tx_pkt_lso_core) +
+			       sizeof(struct cpl_tx_pkt_core)) / sizeof(__be64),
+};
+
+/**
+ *	t4vf_is_eth_imm - can an Ethernet packet be sent as immediate data?
+ *	@skb: the packet
+ *
+ *	Returns whether an Ethernet packet is small enough to fit completely as
+ *	immediate data.
+ */
+static inline int t4vf_is_eth_imm(const struct sk_buff *skb)
+{
+	/* The VF Driver uses the FW_ETH_TX_PKT_VM_WR firmware Work Request
+	 * which does not accommodate immediate data.  We could dike out all
+	 * of the support code for immediate data but that would tie our hands
+	 * too much if we ever want to enhace the firmware.  It would also
+	 * create more differences between the PF and VF Drivers.
+	 */
+	return false;
+}
+
+/**
+ *	t4vf_calc_tx_flits - calculate the number of flits for a packet TX WR
+ *	@skb: the packet
+ *
+ *	Returns the number of flits needed for a TX Work Request for the
+ *	given Ethernet packet, including the needed WR and CPL headers.
+ */
+static inline unsigned int t4vf_calc_tx_flits(const struct sk_buff *skb)
+{
+	unsigned int flits;
+
+	/* If the skb is small enough, we can pump it out as a work request
+	 * with only immediate data.  In that case we just have to have the
+	 * TX Packet header plus the skb data in the Work Request.
+	 */
+	if (t4vf_is_eth_imm(skb))
+		return DIV_ROUND_UP(skb->len + sizeof(struct cpl_tx_pkt),
+				    sizeof(__be64));
+
+	/* Otherwise, we're going to have to construct a Scatter gather list
+	 * of the skb body and fragments.  We also include the flits necessary
+	 * for the TX Packet Work Request and CPL.  We always have a firmware
+	 * Write Header (incorporated as part of the cpl_tx_pkt_lso and
+	 * cpl_tx_pkt structures), followed by either a TX Packet Write CPL
+	 * message or, if we're doing a Large Send Offload, an LSO CPL message
+	 * with an embedded TX Packet Write CPL message.
+	 */
+	flits = sgl_len(skb_shinfo(skb)->nr_frags + 1);
+	if (skb_shinfo(skb)->gso_size)
+		flits += (sizeof(struct fw_eth_tx_pkt_vm_wr) +
+			  sizeof(struct cpl_tx_pkt_lso_core) +
+			  sizeof(struct cpl_tx_pkt_core)) / sizeof(__be64);
+	else
+		flits += (sizeof(struct fw_eth_tx_pkt_vm_wr) +
+			  sizeof(struct cpl_tx_pkt_core)) / sizeof(__be64);
+	return flits;
+}
+
+/**
+ *	cxgb4_vf_eth_xmit - add a packet to an Ethernet TX queue
+ *	@skb: the packet
+ *	@dev: the egress net device
+ *
+ *	Add a packet to an SGE Ethernet TX queue.  Runs with softirqs disabled.
+ */
+static netdev_tx_t cxgb4_vf_eth_xmit(struct sk_buff *skb,
+				     struct net_device *dev)
+{
+	dma_addr_t addr[MAX_SKB_FRAGS + 1];
+	const struct skb_shared_info *ssi;
+	struct fw_eth_tx_pkt_vm_wr *wr;
+	int qidx, credits, max_pkt_len;
+	struct cpl_tx_pkt_core *cpl;
+	const struct port_info *pi;
+	unsigned int flits, ndesc;
+	struct sge_eth_txq *txq;
+	struct adapter *adapter;
+	u64 cntrl, *end;
+	u32 wr_mid;
+	const size_t fw_hdr_copy_len = sizeof(wr->ethmacdst) +
+				       sizeof(wr->ethmacsrc) +
+				       sizeof(wr->ethtype) +
+				       sizeof(wr->vlantci);
+
+	/* The chip minimum packet length is 10 octets but the firmware
+	 * command that we are using requires that we copy the Ethernet header
+	 * (including the VLAN tag) into the header so we reject anything
+	 * smaller than that ...
+	 */
+	if (unlikely(skb->len < fw_hdr_copy_len))
+		goto out_free;
+
+	/* Discard the packet if the length is greater than mtu */
+	max_pkt_len = ETH_HLEN + dev->mtu;
+	if (skb_vlan_tag_present(skb))
+		max_pkt_len += VLAN_HLEN;
+	if (!skb_shinfo(skb)->gso_size && (unlikely(skb->len > max_pkt_len)))
+		goto out_free;
+
+	/* Figure out which TX Queue we're going to use. */
+	pi = netdev_priv(dev);
+	adapter = pi->adapter;
+	qidx = skb_get_queue_mapping(skb);
+	WARN_ON(qidx >= pi->nqsets);
+	txq = &adapter->sge.ethtxq[pi->first_qset + qidx];
+
+	/* Take this opportunity to reclaim any TX Descriptors whose DMA
+	 * transfers have completed.
+	 */
+	cxgb4_reclaim_completed_tx(adapter, &txq->q, true);
+
+	/* Calculate the number of flits and TX Descriptors we're going to
+	 * need along with how many TX Descriptors will be left over after
+	 * we inject our Work Request.
+	 */
+	flits = t4vf_calc_tx_flits(skb);
+	ndesc = flits_to_desc(flits);
+	credits = txq_avail(&txq->q) - ndesc;
+
+	if (unlikely(credits < 0)) {
+		/* Not enough room for this packet's Work Request.  Stop the
+		 * TX Queue and return a "busy" condition.  The queue will get
+		 * started later on when the firmware informs us that space
+		 * has opened up.
+		 */
+		eth_txq_stop(txq);
+		dev_err(adapter->pdev_dev,
+			"%s: TX ring %u full while queue awake!\n",
+			dev->name, qidx);
+		return NETDEV_TX_BUSY;
+	}
+
+	if (!t4vf_is_eth_imm(skb) &&
+	    unlikely(cxgb4_map_skb(adapter->pdev_dev, skb, addr) < 0)) {
+		/* We need to map the skb into PCI DMA space (because it can't
+		 * be in-lined directly into the Work Request) and the mapping
+		 * operation failed.  Record the error and drop the packet.
+		 */
+		txq->mapping_err++;
+		goto out_free;
+	}
+
+	wr_mid = FW_WR_LEN16_V(DIV_ROUND_UP(flits, 2));
+	if (unlikely(credits < ETHTXQ_STOP_THRES)) {
+		/* After we're done injecting the Work Request for this
+		 * packet, we'll be below our "stop threshold" so stop the TX
+		 * Queue now and schedule a request for an SGE Egress Queue
+		 * Update message.  The queue will get started later on when
+		 * the firmware processes this Work Request and sends us an
+		 * Egress Queue Status Update message indicating that space
+		 * has opened up.
+		 */
+		eth_txq_stop(txq);
+		wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+	}
+
+	/* Start filling in our Work Request.  Note that we do _not_ handle
+	 * the WR Header wrapping around the TX Descriptor Ring.  If our
+	 * maximum header size ever exceeds one TX Descriptor, we'll need to
+	 * do something else here.
+	 */
+	WARN_ON(DIV_ROUND_UP(T4VF_ETHTXQ_MAX_HDR, TXD_PER_EQ_UNIT) > 1);
+	wr = (void *)&txq->q.desc[txq->q.pidx];
+	wr->equiq_to_len16 = cpu_to_be32(wr_mid);
+	wr->r3[0] = cpu_to_be32(0);
+	wr->r3[1] = cpu_to_be32(0);
+	skb_copy_from_linear_data(skb, (void *)wr->ethmacdst, fw_hdr_copy_len);
+	end = (u64 *)wr + flits;
+
+	/* If this is a Large Send Offload packet we'll put in an LSO CPL
+	 * message with an encapsulated TX Packet CPL message.  Otherwise we
+	 * just use a TX Packet CPL message.
+	 */
+	ssi = skb_shinfo(skb);
+	if (ssi->gso_size) {
+		struct cpl_tx_pkt_lso_core *lso = (void *)(wr + 1);
+		bool v6 = (ssi->gso_type & SKB_GSO_TCPV6) != 0;
+		int l3hdr_len = skb_network_header_len(skb);
+		int eth_xtra_len = skb_network_offset(skb) - ETH_HLEN;
+
+		wr->op_immdlen =
+			cpu_to_be32(FW_WR_OP_V(FW_ETH_TX_PKT_VM_WR) |
+				    FW_WR_IMMDLEN_V(sizeof(*lso) +
+						    sizeof(*cpl)));
+		 /* Fill in the LSO CPL message. */
+		lso->lso_ctrl =
+			cpu_to_be32(LSO_OPCODE_V(CPL_TX_PKT_LSO) |
+				    LSO_FIRST_SLICE_F |
+				    LSO_LAST_SLICE_F |
+				    LSO_IPV6_V(v6) |
+				    LSO_ETHHDR_LEN_V(eth_xtra_len / 4) |
+				    LSO_IPHDR_LEN_V(l3hdr_len / 4) |
+				    LSO_TCPHDR_LEN_V(tcp_hdr(skb)->doff));
+		lso->ipid_ofst = cpu_to_be16(0);
+		lso->mss = cpu_to_be16(ssi->gso_size);
+		lso->seqno_offset = cpu_to_be32(0);
+		if (is_t4(adapter->params.chip))
+			lso->len = cpu_to_be32(skb->len);
+		else
+			lso->len = cpu_to_be32(LSO_T5_XFER_SIZE_V(skb->len));
+
+		/* Set up TX Packet CPL pointer, control word and perform
+		 * accounting.
+		 */
+		cpl = (void *)(lso + 1);
+
+		if (CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5)
+			cntrl = TXPKT_ETHHDR_LEN_V(eth_xtra_len);
+		else
+			cntrl = T6_TXPKT_ETHHDR_LEN_V(eth_xtra_len);
+
+		cntrl |= TXPKT_CSUM_TYPE_V(v6 ?
+					   TX_CSUM_TCPIP6 : TX_CSUM_TCPIP) |
+			 TXPKT_IPHDR_LEN_V(l3hdr_len);
+		txq->tso++;
+		txq->tx_cso += ssi->gso_segs;
+	} else {
+		int len;
+
+		len = (t4vf_is_eth_imm(skb)
+		       ? skb->len + sizeof(*cpl)
+		       : sizeof(*cpl));
+		wr->op_immdlen =
+			cpu_to_be32(FW_WR_OP_V(FW_ETH_TX_PKT_VM_WR) |
+				    FW_WR_IMMDLEN_V(len));
+
+		/* Set up TX Packet CPL pointer, control word and perform
+		 * accounting.
+		 */
+		cpl = (void *)(wr + 1);
+		if (skb->ip_summed == CHECKSUM_PARTIAL) {
+			cntrl = hwcsum(adapter->params.chip, skb) |
+				TXPKT_IPCSUM_DIS_F;
+			txq->tx_cso++;
+		} else {
+			cntrl = TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F;
+		}
+	}
+
+	/* If there's a VLAN tag present, add that to the list of things to
+	 * do in this Work Request.
+	 */
+	if (skb_vlan_tag_present(skb)) {
+		txq->vlan_ins++;
+		cntrl |= TXPKT_VLAN_VLD_F | TXPKT_VLAN_V(skb_vlan_tag_get(skb));
+	}
+
+	 /* Fill in the TX Packet CPL message header. */
+	cpl->ctrl0 = cpu_to_be32(TXPKT_OPCODE_V(CPL_TX_PKT_XT) |
+				 TXPKT_INTF_V(pi->port_id) |
+				 TXPKT_PF_V(0));
+	cpl->pack = cpu_to_be16(0);
+	cpl->len = cpu_to_be16(skb->len);
+	cpl->ctrl1 = cpu_to_be64(cntrl);
+
+	/* Fill in the body of the TX Packet CPL message with either in-lined
+	 * data or a Scatter/Gather List.
+	 */
+	if (t4vf_is_eth_imm(skb)) {
+		/* In-line the packet's data and free the skb since we don't
+		 * need it any longer.
+		 */
+		cxgb4_inline_tx_skb(skb, &txq->q, cpl + 1);
+		dev_consume_skb_any(skb);
+	} else {
+		/* Write the skb's Scatter/Gather list into the TX Packet CPL
+		 * message and retain a pointer to the skb so we can free it
+		 * later when its DMA completes.  (We store the skb pointer
+		 * in the Software Descriptor corresponding to the last TX
+		 * Descriptor used by the Work Request.)
+		 *
+		 * The retained skb will be freed when the corresponding TX
+		 * Descriptors are reclaimed after their DMAs complete.
+		 * However, this could take quite a while since, in general,
+		 * the hardware is set up to be lazy about sending DMA
+		 * completion notifications to us and we mostly perform TX
+		 * reclaims in the transmit routine.
+		 *
+		 * This is good for performamce but means that we rely on new
+		 * TX packets arriving to run the destructors of completed
+		 * packets, which open up space in their sockets' send queues.
+		 * Sometimes we do not get such new packets causing TX to
+		 * stall.  A single UDP transmitter is a good example of this
+		 * situation.  We have a clean up timer that periodically
+		 * reclaims completed packets but it doesn't run often enough
+		 * (nor do we want it to) to prevent lengthy stalls.  A
+		 * solution to this problem is to run the destructor early,
+		 * after the packet is queued but before it's DMAd.  A con is
+		 * that we lie to socket memory accounting, but the amount of
+		 * extra memory is reasonable (limited by the number of TX
+		 * descriptors), the packets do actually get freed quickly by
+		 * new packets almost always, and for protocols like TCP that
+		 * wait for acks to really free up the data the extra memory
+		 * is even less.  On the positive side we run the destructors
+		 * on the sending CPU rather than on a potentially different
+		 * completing CPU, usually a good thing.
+		 *
+		 * Run the destructor before telling the DMA engine about the
+		 * packet to make sure it doesn't complete and get freed
+		 * prematurely.
+		 */
+		struct ulptx_sgl *sgl = (struct ulptx_sgl *)(cpl + 1);
+		struct sge_txq *tq = &txq->q;
+		int last_desc;
+
+		/* If the Work Request header was an exact multiple of our TX
+		 * Descriptor length, then it's possible that the starting SGL
+		 * pointer lines up exactly with the end of our TX Descriptor
+		 * ring.  If that's the case, wrap around to the beginning
+		 * here ...
+		 */
+		if (unlikely((void *)sgl == (void *)tq->stat)) {
+			sgl = (void *)tq->desc;
+			end = (void *)((void *)tq->desc +
+				       ((void *)end - (void *)tq->stat));
+		}
+
+		cxgb4_write_sgl(skb, tq, sgl, end, 0, addr);
+		skb_orphan(skb);
+
+		last_desc = tq->pidx + ndesc - 1;
+		if (last_desc >= tq->size)
+			last_desc -= tq->size;
+		tq->sdesc[last_desc].skb = skb;
+		tq->sdesc[last_desc].sgl = sgl;
+	}
+
+	/* Advance our internal TX Queue state, tell the hardware about
+	 * the new TX descriptors and return success.
+	 */
+	txq_advance(&txq->q, ndesc);
+
+	cxgb4_ring_tx_db(adapter, &txq->q, ndesc);
+	return NETDEV_TX_OK;
+
+out_free:
+	/* An error of some sort happened.  Free the TX skb and tell the
+	 * OS that we've "dealt" with the packet ...
+	 */
+	dev_kfree_skb_any(skb);
+	return NETDEV_TX_OK;
+}
+
+netdev_tx_t t4_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct port_info *pi = netdev_priv(dev);
+
+	if (unlikely(pi->eth_flags & PRIV_FLAG_PORT_TX_VM))
+		return cxgb4_vf_eth_xmit(skb, dev);
+
+	return cxgb4_eth_xmit(skb, dev);
+}
+
 /**
  *	reclaim_completed_tx_imm - reclaim completed control-queue Tx descs
  *	@q: the SGE control Tx queue
@@ -3044,7 +3412,9 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 	c.iqsize = htons(iq->size);
 	c.iqaddr = cpu_to_be64(iq->phys_addr);
 	if (cong >= 0)
-		c.iqns_to_fl0congen = htonl(FW_IQ_CMD_IQFLINTCONGEN_F);
+		c.iqns_to_fl0congen = htonl(FW_IQ_CMD_IQFLINTCONGEN_F |
+				FW_IQ_CMD_IQTYPE_V(cong ? FW_IQ_IQTYPE_NIC
+							:  FW_IQ_IQTYPE_OFLD));
 
 	if (fl) {
 		enum chip_type chip = CHELSIO_CHIP_VERSION(adap->params.chip);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 3720c3e11ebb..5fe5d16dee72 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -2882,6 +2882,57 @@ int t4_get_vpd_params(struct adapter *adapter, struct vpd_params *p)
 	return 0;
 }
 
+/**
+ *	t4_get_pfres - retrieve VF resource limits
+ *	@adapter: the adapter
+ *
+ *	Retrieves configured resource limits and capabilities for a physical
+ *	function.  The results are stored in @adapter->pfres.
+ */
+int t4_get_pfres(struct adapter *adapter)
+{
+	struct pf_resources *pfres = &adapter->params.pfres;
+	struct fw_pfvf_cmd cmd, rpl;
+	int v;
+	u32 word;
+
+	/* Execute PFVF Read command to get VF resource limits; bail out early
+	 * with error on command failure.
+	 */
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.op_to_vfn = cpu_to_be32(FW_CMD_OP_V(FW_PFVF_CMD) |
+				    FW_CMD_REQUEST_F |
+				    FW_CMD_READ_F |
+				    FW_PFVF_CMD_PFN_V(adapter->pf) |
+				    FW_PFVF_CMD_VFN_V(0));
+	cmd.retval_len16 = cpu_to_be32(FW_LEN16(cmd));
+	v = t4_wr_mbox(adapter, adapter->mbox, &cmd, sizeof(cmd), &rpl);
+	if (v != FW_SUCCESS)
+		return v;
+
+	/* Extract PF resource limits and return success.
+	 */
+	word = be32_to_cpu(rpl.niqflint_niq);
+	pfres->niqflint = FW_PFVF_CMD_NIQFLINT_G(word);
+	pfres->niq = FW_PFVF_CMD_NIQ_G(word);
+
+	word = be32_to_cpu(rpl.type_to_neq);
+	pfres->neq = FW_PFVF_CMD_NEQ_G(word);
+	pfres->pmask = FW_PFVF_CMD_PMASK_G(word);
+
+	word = be32_to_cpu(rpl.tc_to_nexactf);
+	pfres->tc = FW_PFVF_CMD_TC_G(word);
+	pfres->nvi = FW_PFVF_CMD_NVI_G(word);
+	pfres->nexactf = FW_PFVF_CMD_NEXACTF_G(word);
+
+	word = be32_to_cpu(rpl.r_caps_to_nethctrl);
+	pfres->r_caps = FW_PFVF_CMD_R_CAPS_G(word);
+	pfres->wx_caps = FW_PFVF_CMD_WX_CAPS_G(word);
+	pfres->nethctrl = FW_PFVF_CMD_NETHCTRL_G(word);
+
+	return 0;
+}
+
 /* serial flash and firmware constants */
 enum {
 	SF_ATTEMPTS = 10,             /* max retries for SF operations */
@@ -7453,10 +7504,13 @@ int t4_alloc_vi(struct adapter *adap, unsigned int mbox, unsigned int port,
 		switch (nmac) {
 		case 5:
 			memcpy(mac + 24, c.nmac3, sizeof(c.nmac3));
+			/* Fall through */
 		case 4:
 			memcpy(mac + 18, c.nmac2, sizeof(c.nmac2));
+			/* Fall through */
 		case 3:
 			memcpy(mac + 12, c.nmac1, sizeof(c.nmac1));
+			/* Fall through */
 		case 2:
 			memcpy(mac + 6,  c.nmac0, sizeof(c.nmac0));
 		}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
index c7f8d0441278..60df66f4d21c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
@@ -188,6 +188,9 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
 	CH_PCI_ID_TABLE_FENTRY(0x50ab), /* Custom T520-CR */
 	CH_PCI_ID_TABLE_FENTRY(0x50ac), /* Custom T540-BT */
 	CH_PCI_ID_TABLE_FENTRY(0x50ad), /* Custom T520-CR */
+	CH_PCI_ID_TABLE_FENTRY(0x50ae), /* Custom T540-XL-SO */
+	CH_PCI_ID_TABLE_FENTRY(0x50af), /* Custom T580-KR-SO */
+	CH_PCI_ID_TABLE_FENTRY(0x50b0), /* Custom T520-CR-LOM */
 
 	/* T6 adapters:
 	 */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index 6b55aa2eb2a5..eb222d40ddbf 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -1502,6 +1502,25 @@
 #define TP_MIB_DATA_A	0x7e54
 #define TP_INT_CAUSE_A	0x7e74
 
+#define TP_FLM_FREE_PS_CNT_A 0x7e80
+#define TP_FLM_FREE_RX_CNT_A 0x7e84
+
+#define FREEPSTRUCTCOUNT_S    0
+#define FREEPSTRUCTCOUNT_M    0x1fffffU
+#define FREEPSTRUCTCOUNT_G(x) (((x) >> FREEPSTRUCTCOUNT_S) & FREEPSTRUCTCOUNT_M)
+
+#define FREERXPAGECOUNT_S    0
+#define FREERXPAGECOUNT_M    0x1fffffU
+#define FREERXPAGECOUNT_V(x) ((x) << FREERXPAGECOUNT_S)
+#define FREERXPAGECOUNT_G(x) (((x) >> FREERXPAGECOUNT_S) & FREERXPAGECOUNT_M)
+
+#define TP_FLM_FREE_TX_CNT_A 0x7e88
+
+#define FREETXPAGECOUNT_S    0
+#define FREETXPAGECOUNT_M    0x1fffffU
+#define FREETXPAGECOUNT_V(x) ((x) << FREETXPAGECOUNT_S)
+#define FREETXPAGECOUNT_G(x) (((x) >> FREETXPAGECOUNT_S) & FREETXPAGECOUNT_M)
+
 #define FLMTXFLSTEMPTY_S    30
 #define FLMTXFLSTEMPTY_V(x) ((x) << FLMTXFLSTEMPTY_S)
 #define FLMTXFLSTEMPTY_F    FLMTXFLSTEMPTY_V(1U)
@@ -1683,6 +1702,16 @@
 #define ULP_TX_LA_RDPTR_0_A 0x8ec0
 #define ULP_TX_LA_RDDATA_0_A 0x8ec4
 #define ULP_TX_LA_WRPTR_0_A 0x8ec8
+#define ULP_TX_ASIC_DEBUG_CTRL_A 0x8f70
+
+#define ULP_TX_ASIC_DEBUG_0_A 0x8f74
+#define ULP_TX_ASIC_DEBUG_1_A 0x8f78
+#define ULP_TX_ASIC_DEBUG_2_A 0x8f7c
+#define ULP_TX_ASIC_DEBUG_3_A 0x8f80
+#define ULP_TX_ASIC_DEBUG_4_A 0x8f84
+
+/* registers for module PM_RX */
+#define PM_RX_BASE_ADDR 0x8fc0
 
 #define PMRX_E_PCMD_PAR_ERROR_S    0
 #define PMRX_E_PCMD_PAR_ERROR_V(x) ((x) << PMRX_E_PCMD_PAR_ERROR_S)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
index f1967cf6d43c..5dc6c4154af8 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
@@ -1472,6 +1472,12 @@ enum fw_iq_type {
 	FW_IQ_TYPE_NO_FL_INT_CAP
 };
 
+enum fw_iq_iqtype {
+	FW_IQ_IQTYPE_OTHER,
+	FW_IQ_IQTYPE_NIC,
+	FW_IQ_IQTYPE_OFLD,
+};
+
 struct fw_iq_cmd {
 	__be32 op_to_vfn;
 	__be32 alloc_to_len16;
@@ -1586,6 +1592,12 @@ struct fw_iq_cmd {
 #define FW_IQ_CMD_IQFLINTISCSIC_S	26
 #define FW_IQ_CMD_IQFLINTISCSIC_V(x)	((x) << FW_IQ_CMD_IQFLINTISCSIC_S)
 
+#define FW_IQ_CMD_IQTYPE_S		24
+#define FW_IQ_CMD_IQTYPE_M		0x3
+#define FW_IQ_CMD_IQTYPE_V(x)		((x) << FW_IQ_CMD_IQTYPE_S)
+#define FW_IQ_CMD_IQTYPE_G(x)		\
+	(((x) >> FW_IQ_CMD_IQTYPE_S) & FW_IQ_CMD_IQTYPE_M)
+
 #define FW_IQ_CMD_FL0CNGCHMAP_S		20
 #define FW_IQ_CMD_FL0CNGCHMAP_V(x)	((x) << FW_IQ_CMD_FL0CNGCHMAP_S)
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
index 4eb15ceddca3..a844296135b4 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
@@ -36,8 +36,8 @@
 #define __T4FW_VERSION_H__
 
 #define T4FW_VERSION_MAJOR 0x01
-#define T4FW_VERSION_MINOR 0x13
-#define T4FW_VERSION_MICRO 0x01
+#define T4FW_VERSION_MINOR 0x14
+#define T4FW_VERSION_MICRO 0x08
 #define T4FW_VERSION_BUILD 0x00
 
 #define T4FW_MIN_VERSION_MAJOR 0x01
@@ -45,8 +45,8 @@
 #define T4FW_MIN_VERSION_MICRO 0x00
 
 #define T5FW_VERSION_MAJOR 0x01
-#define T5FW_VERSION_MINOR 0x13
-#define T5FW_VERSION_MICRO 0x01
+#define T5FW_VERSION_MINOR 0x14
+#define T5FW_VERSION_MICRO 0x08
 #define T5FW_VERSION_BUILD 0x00
 
 #define T5FW_MIN_VERSION_MAJOR 0x00
@@ -54,8 +54,8 @@
 #define T5FW_MIN_VERSION_MICRO 0x00
 
 #define T6FW_VERSION_MAJOR 0x01
-#define T6FW_VERSION_MINOR 0x13
-#define T6FW_VERSION_MICRO 0x01
+#define T6FW_VERSION_MINOR 0x14
+#define T6FW_VERSION_MICRO 0x08
 #define T6FW_VERSION_BUILD 0x00
 
 #define T6FW_MIN_VERSION_MAJOR 0x00
diff --git a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c
index 0ed161642371..74849be5f004 100644
--- a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c
+++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c
@@ -412,12 +412,10 @@ int cxgbi_ppm_init(void **ppm_pp, struct net_device *ndev,
 			ppmax * (sizeof(struct cxgbi_ppod_data)) +
 			ppod_bmap_size * sizeof(unsigned long);
 
-	ppm = vmalloc(alloc_sz);
+	ppm = vzalloc(alloc_sz);
 	if (!ppm)
 		goto release_ppm_pool;
 
-	memset(ppm, 0, alloc_sz);
-
 	ppm->ppod_bmap = (unsigned long *)(&ppm->ppod_data[ppmax]);
 
 	if ((ppod_bmap_size >> 3) > (ppmax - ppmax_pool)) {
diff --git a/drivers/net/ethernet/cisco/enic/vnic_dev.c b/drivers/net/ethernet/cisco/enic/vnic_dev.c
index e9db811df59c..901e44b0b795 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_dev.c
+++ b/drivers/net/ethernet/cisco/enic/vnic_dev.c
@@ -1071,7 +1071,7 @@ struct vnic_dev *vnic_dev_register(struct vnic_dev *vdev,
 	unsigned int num_bars)
 {
 	if (!vdev) {
-		vdev = kzalloc(sizeof(struct vnic_dev), GFP_ATOMIC);
+		vdev = kzalloc(sizeof(struct vnic_dev), GFP_KERNEL);
 		if (!vdev)
 			return NULL;
 	}
diff --git a/drivers/net/ethernet/cisco/enic/vnic_rq.c b/drivers/net/ethernet/cisco/enic/vnic_rq.c
index f8aa326d1d58..a3e7b003ada1 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_rq.c
+++ b/drivers/net/ethernet/cisco/enic/vnic_rq.c
@@ -35,7 +35,7 @@ static int vnic_rq_alloc_bufs(struct vnic_rq *rq)
 	unsigned int blks = VNIC_RQ_BUF_BLKS_NEEDED(count);
 
 	for (i = 0; i < blks; i++) {
-		rq->bufs[i] = kzalloc(VNIC_RQ_BUF_BLK_SZ(count), GFP_ATOMIC);
+		rq->bufs[i] = kzalloc(VNIC_RQ_BUF_BLK_SZ(count), GFP_KERNEL);
 		if (!rq->bufs[i])
 			return -ENOMEM;
 	}
diff --git a/drivers/net/ethernet/cisco/enic/vnic_wq.c b/drivers/net/ethernet/cisco/enic/vnic_wq.c
index 090cc65658a3..eb75891974df 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_wq.c
+++ b/drivers/net/ethernet/cisco/enic/vnic_wq.c
@@ -35,7 +35,7 @@ static int vnic_wq_alloc_bufs(struct vnic_wq *wq)
 	unsigned int blks = VNIC_WQ_BUF_BLKS_NEEDED(count);
 
 	for (i = 0; i < blks; i++) {
-		wq->bufs[i] = kzalloc(VNIC_WQ_BUF_BLK_SZ(count), GFP_ATOMIC);
+		wq->bufs[i] = kzalloc(VNIC_WQ_BUF_BLK_SZ(count), GFP_KERNEL);
 		if (!wq->bufs[i])
 			return -ENOMEM;
 	}
diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 6d7404f66f84..1c9ad3630c77 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -46,6 +46,11 @@
 #define DRV_NAME		"gmac-gemini"
 #define DRV_VERSION		"1.0"
 
+#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
+static int debug = -1;
+module_param(debug, int, 0);
+MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
+
 #define HSIZE_8			0x00
 #define HSIZE_16		0x01
 #define HSIZE_32		0x02
@@ -146,6 +151,7 @@ struct gemini_ethernet {
 	void __iomem *base;
 	struct gemini_ethernet_port *port0;
 	struct gemini_ethernet_port *port1;
+	bool initialized;
 
 	spinlock_t	irq_lock; /* Locks IRQ-related registers */
 	unsigned int	freeq_order;
@@ -300,23 +306,26 @@ static void gmac_speed_set(struct net_device *netdev)
 		status.bits.speed = GMAC_SPEED_1000;
 		if (phydev->interface == PHY_INTERFACE_MODE_RGMII)
 			status.bits.mii_rmii = GMAC_PHY_RGMII_1000;
-		netdev_info(netdev, "connect to RGMII @ 1Gbit\n");
+		netdev_dbg(netdev, "connect %s to RGMII @ 1Gbit\n",
+			   phydev_name(phydev));
 		break;
 	case 100:
 		status.bits.speed = GMAC_SPEED_100;
 		if (phydev->interface == PHY_INTERFACE_MODE_RGMII)
 			status.bits.mii_rmii = GMAC_PHY_RGMII_100_10;
-		netdev_info(netdev, "connect to RGMII @ 100 Mbit\n");
+		netdev_dbg(netdev, "connect %s to RGMII @ 100 Mbit\n",
+			   phydev_name(phydev));
 		break;
 	case 10:
 		status.bits.speed = GMAC_SPEED_10;
 		if (phydev->interface == PHY_INTERFACE_MODE_RGMII)
 			status.bits.mii_rmii = GMAC_PHY_RGMII_100_10;
-		netdev_info(netdev, "connect to RGMII @ 10 Mbit\n");
+		netdev_dbg(netdev, "connect %s to RGMII @ 10 Mbit\n",
+			   phydev_name(phydev));
 		break;
 	default:
-		netdev_warn(netdev, "Not supported PHY speed (%d)\n",
-			    phydev->speed);
+		netdev_warn(netdev, "Unsupported PHY speed (%d) on %s\n",
+			    phydev->speed, phydev_name(phydev));
 	}
 
 	if (phydev->duplex == DUPLEX_FULL) {
@@ -363,12 +372,6 @@ static int gmac_setup_phy(struct net_device *netdev)
 		return -ENODEV;
 	netdev->phydev = phy;
 
-	netdev_info(netdev, "connected to PHY \"%s\"\n",
-		    phydev_name(phy));
-	phy_attached_print(phy, "phy_id=0x%.8lx, phy_mode=%s\n",
-			   (unsigned long)phy->phy_id,
-			   phy_modes(phy->interface));
-
 	phy->supported &= PHY_GBIT_FEATURES;
 	phy->supported |= SUPPORTED_Asym_Pause | SUPPORTED_Pause;
 	phy->advertising = phy->supported;
@@ -376,19 +379,19 @@ static int gmac_setup_phy(struct net_device *netdev)
 	/* set PHY interface type */
 	switch (phy->interface) {
 	case PHY_INTERFACE_MODE_MII:
-		netdev_info(netdev, "set GMAC0 to GMII mode, GMAC1 disabled\n");
+		netdev_dbg(netdev,
+			   "MII: set GMAC0 to GMII mode, GMAC1 disabled\n");
 		status.bits.mii_rmii = GMAC_PHY_MII;
-		netdev_info(netdev, "connect to MII\n");
 		break;
 	case PHY_INTERFACE_MODE_GMII:
-		netdev_info(netdev, "set GMAC0 to GMII mode, GMAC1 disabled\n");
+		netdev_dbg(netdev,
+			   "GMII: set GMAC0 to GMII mode, GMAC1 disabled\n");
 		status.bits.mii_rmii = GMAC_PHY_GMII;
-		netdev_info(netdev, "connect to GMII\n");
 		break;
 	case PHY_INTERFACE_MODE_RGMII:
-		dev_info(dev, "set GMAC0 and GMAC1 to MII/RGMII mode\n");
+		netdev_dbg(netdev,
+			   "RGMII: set GMAC0 and GMAC1 to MII/RGMII mode\n");
 		status.bits.mii_rmii = GMAC_PHY_RGMII_100_10;
-		netdev_info(netdev, "connect to RGMII\n");
 		break;
 	default:
 		netdev_err(netdev, "Unsupported MII interface\n");
@@ -398,29 +401,63 @@ static int gmac_setup_phy(struct net_device *netdev)
 	}
 	writel(status.bits32, port->gmac_base + GMAC_STATUS);
 
+	if (netif_msg_link(port))
+		phy_attached_info(phy);
+
 	return 0;
 }
 
-static int gmac_pick_rx_max_len(int max_l3_len)
-{
-	/* index = CONFIG_MAXLEN_XXX values */
-	static const int max_len[8] = {
-		1536, 1518, 1522, 1542,
-		9212, 10236, 1518, 1518
-	};
-	int i, n = 5;
+/* The maximum frame length is not logically enumerated in the
+ * hardware, so we do a table lookup to find the applicable max
+ * frame length.
+ */
+struct gmac_max_framelen {
+	unsigned int max_l3_len;
+	u8 val;
+};
+
+static const struct gmac_max_framelen gmac_maxlens[] = {
+	{
+		.max_l3_len = 1518,
+		.val = CONFIG0_MAXLEN_1518,
+	},
+	{
+		.max_l3_len = 1522,
+		.val = CONFIG0_MAXLEN_1522,
+	},
+	{
+		.max_l3_len = 1536,
+		.val = CONFIG0_MAXLEN_1536,
+	},
+	{
+		.max_l3_len = 1542,
+		.val = CONFIG0_MAXLEN_1542,
+	},
+	{
+		.max_l3_len = 9212,
+		.val = CONFIG0_MAXLEN_9k,
+	},
+	{
+		.max_l3_len = 10236,
+		.val = CONFIG0_MAXLEN_10k,
+	},
+};
 
-	max_l3_len += ETH_HLEN + VLAN_HLEN;
+static int gmac_pick_rx_max_len(unsigned int max_l3_len)
+{
+	const struct gmac_max_framelen *maxlen;
+	int maxtot;
+	int i;
 
-	if (max_l3_len > max_len[n])
-		return -1;
+	maxtot = max_l3_len + ETH_HLEN + VLAN_HLEN;
 
-	for (i = 0; i < 5; i++) {
-		if (max_len[i] >= max_l3_len && max_len[i] < max_len[n])
-			n = i;
+	for (i = 0; i < ARRAY_SIZE(gmac_maxlens); i++) {
+		maxlen = &gmac_maxlens[i];
+		if (maxtot <= maxlen->max_l3_len)
+			return maxlen->val;
 	}
 
-	return n;
+	return -1;
 }
 
 static int gmac_init(struct net_device *netdev)
@@ -1276,8 +1313,8 @@ static void gmac_enable_irq(struct net_device *netdev, int enable)
 	unsigned long flags;
 	u32 val, mask;
 
-	netdev_info(netdev, "%s device %d %s\n", __func__,
-		    netdev->dev_id, enable ? "enable" : "disable");
+	netdev_dbg(netdev, "%s device %d %s\n", __func__,
+		   netdev->dev_id, enable ? "enable" : "disable");
 	spin_lock_irqsave(&geth->irq_lock, flags);
 
 	mask = GMAC0_IRQ0_2 << (netdev->dev_id * 2);
@@ -1753,7 +1790,10 @@ static int gmac_open(struct net_device *netdev)
 	phy_start(netdev->phydev);
 
 	err = geth_resize_freeq(port);
-	if (err) {
+	/* It's fine if it's just busy, the other port has set up
+	 * the freeq in that case.
+	 */
+	if (err && (err != -EBUSY)) {
 		netdev_err(netdev, "could not resize freeq\n");
 		goto err_stop_phy;
 	}
@@ -1782,7 +1822,7 @@ static int gmac_open(struct net_device *netdev)
 		     HRTIMER_MODE_REL);
 	port->rx_coalesce_timer.function = &gmac_coalesce_delay_expired;
 
-	netdev_info(netdev, "opened\n");
+	netdev_dbg(netdev, "opened\n");
 
 	return 0;
 
@@ -2264,6 +2304,14 @@ static void gemini_port_remove(struct gemini_ethernet_port *port)
 
 static void gemini_ethernet_init(struct gemini_ethernet *geth)
 {
+	/* Only do this once both ports are online */
+	if (geth->initialized)
+		return;
+	if (geth->port0 && geth->port1)
+		geth->initialized = true;
+	else
+		return;
+
 	writel(0, geth->base + GLOBAL_INTERRUPT_ENABLE_0_REG);
 	writel(0, geth->base + GLOBAL_INTERRUPT_ENABLE_1_REG);
 	writel(0, geth->base + GLOBAL_INTERRUPT_ENABLE_2_REG);
@@ -2354,6 +2402,7 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 	port->id = id;
 	port->geth = geth;
 	port->dev = dev;
+	port->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
 
 	/* DMA memory */
 	dmares = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -2410,6 +2459,10 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 		geth->port0 = port;
 	else
 		geth->port1 = port;
+
+	/* This will just be done once both ports are up and reset */
+	gemini_ethernet_init(geth);
+
 	platform_set_drvdata(pdev, port);
 
 	/* Set up and register the netdev */
@@ -2423,6 +2476,11 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 
 	netdev->hw_features = GMAC_OFFLOAD_FEATURES;
 	netdev->features |= GMAC_OFFLOAD_FEATURES | NETIF_F_GRO;
+	/* We can handle jumbo frames up to 10236 bytes so, let's accept
+	 * payloads of 10236 bytes minus VLAN and ethernet header
+	 */
+	netdev->min_mtu = ETH_MIN_MTU;
+	netdev->max_mtu = 10236 - VLAN_ETH_HLEN;
 
 	port->freeq_refill = 0;
 	netif_napi_add(netdev, &port->napi, gmac_napi_poll,
@@ -2435,7 +2493,7 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 			port->mac_addr[0], port->mac_addr[1],
 			port->mac_addr[2]);
 		dev_info(dev, "using a random ethernet address\n");
-		random_ether_addr(netdev->dev_addr);
+		eth_random_addr(netdev->dev_addr);
 	}
 	gmac_write_mac_address(netdev);
 
@@ -2527,7 +2585,6 @@ static int gemini_ethernet_probe(struct platform_device *pdev)
 
 	spin_lock_init(&geth->irq_lock);
 	spin_lock_init(&geth->freeq_lock);
-	gemini_ethernet_init(geth);
 
 	/* The children will use this */
 	platform_set_drvdata(pdev, geth);
@@ -2540,8 +2597,8 @@ static int gemini_ethernet_remove(struct platform_device *pdev)
 {
 	struct gemini_ethernet *geth = platform_get_drvdata(pdev);
 
-	gemini_ethernet_init(geth);
 	geth_cleanup_freeq(geth);
+	geth->initialized = false;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c
index a31b4df3e7ff..66535d1653f6 100644
--- a/drivers/net/ethernet/dec/tulip/de4x5.c
+++ b/drivers/net/ethernet/dec/tulip/de4x5.c
@@ -3204,6 +3204,8 @@ srom_map_media(struct net_device *dev)
       case SROM_10BASETF:
 	if (!lp->params.fdx) return -1;
 	lp->fdx = true;
+	/* fall through */
+
       case SROM_10BASET:
 	if (lp->params.fdx && !lp->fdx) return -1;
 	if ((lp->chipset == DC21140) || ((lp->chipset & ~0x00ff) == DC2114x)) {
@@ -3224,6 +3226,8 @@ srom_map_media(struct net_device *dev)
       case SROM_100BASETF:
         if (!lp->params.fdx) return -1;
 	lp->fdx = true;
+	/* fall through */
+
       case SROM_100BASET:
 	if (lp->params.fdx && !lp->fdx) return -1;
 	lp->media = _100Mb;
@@ -3236,6 +3240,8 @@ srom_map_media(struct net_device *dev)
       case SROM_100BASEFF:
 	if (!lp->params.fdx) return -1;
 	lp->fdx = true;
+	/* fall through */
+
       case SROM_100BASEF:
 	if (lp->params.fdx && !lp->fdx) return -1;
 	lp->media = _100Mb;
diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c
index 00d02a0967d0..3e3e08698876 100644
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -923,6 +923,7 @@ static int private_ioctl (struct net_device *dev, struct ifreq *rq, int cmd)
 			data->phy_id = 1;
 		else
 			return -ENODEV;
+		/* Fall through */
 
 	case SIOCGMIIREG:		/* Read MII PHY register. */
 		if (data->phy_id == 32 && (tp->flags & HAS_NWAY)) {
diff --git a/drivers/net/ethernet/emulex/benet/Kconfig b/drivers/net/ethernet/emulex/benet/Kconfig
index b4853ec9de8d..8cf794edd3c3 100644
--- a/drivers/net/ethernet/emulex/benet/Kconfig
+++ b/drivers/net/ethernet/emulex/benet/Kconfig
@@ -1,7 +1,7 @@
 config BE2NET
 	tristate "ServerEngines' 10Gbps NIC - BladeEngine"
 	depends on PCI
-	---help---
+	help
 	  This driver implements the NIC functionality for ServerEngines'
 	  10Gbps network adapter - BladeEngine.
 
@@ -10,6 +10,42 @@ config BE2NET_HWMON
 	depends on BE2NET && HWMON
 	depends on !(BE2NET=y && HWMON=m)
 	default y
-	---help---
+	help
 	  Say Y here if you want to expose thermal sensor data on
 	  be2net network adapter.
+
+config BE2NET_BE2
+	bool "Support for BE2 chipsets"
+	depends on BE2NET
+	default y
+	help
+	  Say Y here if you want to use devices based on BE2
+	  chipsets. (e.g. OneConnect OCe10xxx)
+
+config BE2NET_BE3
+	bool "Support for BE3 chipsets"
+	depends on BE2NET
+	default y
+	help
+	  Say Y here if you want to use devices based on BE3
+	  chipsets. (e.g. OneConnect OCe11xxx)
+
+config BE2NET_LANCER
+	bool "Support for Lancer chipsets"
+	depends on BE2NET
+	default y
+	help
+	  Say Y here if you want to use devices based on Lancer
+	  chipsets. (e.g LightPulse LPe12xxx)
+
+config BE2NET_SKYHAWK
+	bool "Support for Skyhawk chipsets"
+	depends on BE2NET
+	default y
+	help
+	  Say Y here if you want to use devices based on Skyhawk
+	  chipsets. (e.g. OneConnect OCe14xxx)
+
+comment "WARNING: be2net is useless without any enabled chip"
+        depends on BE2NET_BE2=n && BE2NET_BE3=n && BE2NET_LANCER=n && \
+	BE2NET_SKYHAWK=n && BE2NET
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 382891f81e09..58bcee8f0a58 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -37,7 +37,7 @@
 #include "be_hw.h"
 #include "be_roce.h"
 
-#define DRV_VER			"11.4.0.0"
+#define DRV_VER			"12.0.0.0"
 #define DRV_NAME		"be2net"
 #define BE_NAME			"Emulex BladeEngine2"
 #define BE3_NAME		"Emulex BladeEngine3"
@@ -185,34 +185,13 @@ static inline void queue_tail_inc(struct be_queue_info *q)
 
 struct be_eq_obj {
 	struct be_queue_info q;
-	char desc[32];
-
-	/* Adaptive interrupt coalescing (AIC) info */
-	bool enable_aic;
-	u32 min_eqd;		/* in usecs */
-	u32 max_eqd;		/* in usecs */
-	u32 eqd;		/* configured val when aic is off */
-	u32 cur_eqd;		/* in usecs */
 
+	struct be_adapter *adapter;
+	struct napi_struct napi;
 	u8 idx;			/* array index */
 	u8 msix_idx;
 	u16 spurious_intr;
-	struct napi_struct napi;
-	struct be_adapter *adapter;
 	cpumask_var_t  affinity_mask;
-
-#ifdef CONFIG_NET_RX_BUSY_POLL
-#define BE_EQ_IDLE		0
-#define BE_EQ_NAPI		1	/* napi owns this EQ */
-#define BE_EQ_POLL		2	/* poll owns this EQ */
-#define BE_EQ_LOCKED		(BE_EQ_NAPI | BE_EQ_POLL)
-#define BE_EQ_NAPI_YIELD	4	/* napi yielded this EQ */
-#define BE_EQ_POLL_YIELD	8	/* poll yielded this EQ */
-#define BE_EQ_YIELD		(BE_EQ_NAPI_YIELD | BE_EQ_POLL_YIELD)
-#define BE_EQ_USER_PEND		(BE_EQ_POLL | BE_EQ_POLL_YIELD)
-	unsigned int state;
-	spinlock_t lock;	/* lock to serialize napi and busy-poll */
-#endif  /* CONFIG_NET_RX_BUSY_POLL */
 } ____cacheline_aligned_in_smp;
 
 struct be_aic_obj {		/* Adaptive interrupt coalescing (AIC) info */
@@ -238,7 +217,6 @@ struct be_tx_stats {
 	u64 tx_vxlan_offload_pkts;
 	u64 tx_reqs;
 	u64 tx_compl;
-	ulong tx_jiffies;
 	u32 tx_stops;
 	u32 tx_drv_drops;	/* pkts dropped by driver */
 	/* the error counters are described in be_ethtool.c */
@@ -261,9 +239,9 @@ struct be_tx_compl_info {
 
 struct be_tx_obj {
 	u32 db_offset;
+	struct be_tx_compl_info txcp;
 	struct be_queue_info q;
 	struct be_queue_info cq;
-	struct be_tx_compl_info txcp;
 	/* Remember the skbs that were transmitted */
 	struct sk_buff *sent_skb_list[TX_Q_LEN];
 	struct be_tx_stats stats;
@@ -458,10 +436,10 @@ struct be_port_resources {
 #define be_is_os2bmc_enabled(adapter) (adapter->flags & BE_FLAGS_OS2BMC)
 
 struct rss_info {
-	u64 rss_flags;
 	u8 rsstable[RSS_INDIR_TABLE_LEN];
 	u8 rss_queue[RSS_INDIR_TABLE_LEN];
 	u8 rss_hkey[RSS_HASH_KEY_LEN];
+	u64 rss_flags;
 };
 
 #define BE_INVALID_DIE_TEMP	0xFF
@@ -544,11 +522,13 @@ enum {
 };
 
 struct be_error_recovery {
-	/* Lancer error recovery variables */
-	u8 recovery_retries;
+	union {
+		u8 recovery_retries;	/* used for Lancer		*/
+		u8 recovery_state;	/* used for BEx and Skyhawk	*/
+	};
 
 	/* BEx/Skyhawk error recovery variables */
-	u8 recovery_state;
+	bool recovery_supported;
 	u16 ue_to_reset_time;		/* Time after UE, to soft reset
 					 * the chip - PF0 only
 					 */
@@ -556,7 +536,6 @@ struct be_error_recovery {
 					 * of SLIPORT_SEMAPHORE reg
 					 */
 	u16 last_err_code;
-	bool recovery_supported;
 	unsigned long probe_time;
 	unsigned long last_recovery_time;
 
@@ -773,17 +752,33 @@ static inline u16 be_max_any_irqs(struct be_adapter *adapter)
 /* Is BE in QNQ multi-channel mode */
 #define be_is_qnq_mode(adapter)		(adapter->function_mode & QNQ_MODE)
 
+#ifdef CONFIG_BE2NET_LANCER
 #define lancer_chip(adapter)	(adapter->pdev->device == OC_DEVICE_ID3 || \
 				 adapter->pdev->device == OC_DEVICE_ID4)
+#else
+#define lancer_chip(adapter)	(0)
+#endif /* CONFIG_BE2NET_LANCER */
 
+#ifdef CONFIG_BE2NET_SKYHAWK
 #define skyhawk_chip(adapter)	(adapter->pdev->device == OC_DEVICE_ID5 || \
 				 adapter->pdev->device == OC_DEVICE_ID6)
+#else
+#define skyhawk_chip(adapter)	(0)
+#endif /* CONFIG_BE2NET_SKYHAWK */
 
+#ifdef CONFIG_BE2NET_BE3
 #define BE3_chip(adapter)	(adapter->pdev->device == BE_DEVICE_ID2 || \
 				 adapter->pdev->device == OC_DEVICE_ID2)
+#else
+#define BE3_chip(adapter)	(0)
+#endif /* CONFIG_BE2NET_BE3 */
 
+#ifdef CONFIG_BE2NET_BE2
 #define BE2_chip(adapter)	(adapter->pdev->device == BE_DEVICE_ID1 || \
 				 adapter->pdev->device == OC_DEVICE_ID1)
+#else
+#define BE2_chip(adapter)	(0)
+#endif /* CONFIG_BE2NET_BE2 */
 
 #define BEx_chip(adapter)	(BE3_chip(adapter) || BE2_chip(adapter))
 
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index 7f7e206f95f8..3f6749fc889f 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -575,6 +575,7 @@ static u32 convert_to_et_setting(struct be_adapter *adapter, u32 if_speeds)
 				break;
 			}
 		}
+		/* fall through */
 	case PHY_TYPE_SFP_PLUS_10GB:
 	case PHY_TYPE_XFP_10GB:
 	case PHY_TYPE_SFP_1GB:
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 8f755009ff38..74d122616e76 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -47,14 +47,22 @@ MODULE_PARM_DESC(rx_frag_size, "Size of a fragment that holds rcvd data.");
 static struct workqueue_struct *be_err_recovery_workq;
 
 static const struct pci_device_id be_dev_ids[] = {
+#ifdef CONFIG_BE2NET_BE2
 	{ PCI_DEVICE(BE_VENDOR_ID, BE_DEVICE_ID1) },
-	{ PCI_DEVICE(BE_VENDOR_ID, BE_DEVICE_ID2) },
 	{ PCI_DEVICE(BE_VENDOR_ID, OC_DEVICE_ID1) },
+#endif /* CONFIG_BE2NET_BE2 */
+#ifdef CONFIG_BE2NET_BE3
+	{ PCI_DEVICE(BE_VENDOR_ID, BE_DEVICE_ID2) },
 	{ PCI_DEVICE(BE_VENDOR_ID, OC_DEVICE_ID2) },
+#endif /* CONFIG_BE2NET_BE3 */
+#ifdef CONFIG_BE2NET_LANCER
 	{ PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID3)},
 	{ PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID4)},
+#endif /* CONFIG_BE2NET_LANCER */
+#ifdef CONFIG_BE2NET_SKYHAWK
 	{ PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID5)},
 	{ PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID6)},
+#endif /* CONFIG_BE2NET_SKYHAWK */
 	{ 0 }
 };
 MODULE_DEVICE_TABLE(pci, be_dev_ids);
@@ -1412,6 +1420,83 @@ drop:
 	return NETDEV_TX_OK;
 }
 
+static void be_tx_timeout(struct net_device *netdev)
+{
+	struct be_adapter *adapter = netdev_priv(netdev);
+	struct device *dev = &adapter->pdev->dev;
+	struct be_tx_obj *txo;
+	struct sk_buff *skb;
+	struct tcphdr *tcphdr;
+	struct udphdr *udphdr;
+	u32 *entry;
+	int status;
+	int i, j;
+
+	for_all_tx_queues(adapter, txo, i) {
+		dev_info(dev, "TXQ Dump: %d H: %d T: %d used: %d, qid: 0x%x\n",
+			 i, txo->q.head, txo->q.tail,
+			 atomic_read(&txo->q.used), txo->q.id);
+
+		entry = txo->q.dma_mem.va;
+		for (j = 0; j < TX_Q_LEN * 4; j += 4) {
+			if (entry[j] != 0 || entry[j + 1] != 0 ||
+			    entry[j + 2] != 0 || entry[j + 3] != 0) {
+				dev_info(dev, "Entry %d 0x%x 0x%x 0x%x 0x%x\n",
+					 j, entry[j], entry[j + 1],
+					 entry[j + 2], entry[j + 3]);
+			}
+		}
+
+		entry = txo->cq.dma_mem.va;
+		dev_info(dev, "TXCQ Dump: %d  H: %d T: %d used: %d\n",
+			 i, txo->cq.head, txo->cq.tail,
+			 atomic_read(&txo->cq.used));
+		for (j = 0; j < TX_CQ_LEN * 4; j += 4) {
+			if (entry[j] != 0 || entry[j + 1] != 0 ||
+			    entry[j + 2] != 0 || entry[j + 3] != 0) {
+				dev_info(dev, "Entry %d 0x%x 0x%x 0x%x 0x%x\n",
+					 j, entry[j], entry[j + 1],
+					 entry[j + 2], entry[j + 3]);
+			}
+		}
+
+		for (j = 0; j < TX_Q_LEN; j++) {
+			if (txo->sent_skb_list[j]) {
+				skb = txo->sent_skb_list[j];
+				if (ip_hdr(skb)->protocol == IPPROTO_TCP) {
+					tcphdr = tcp_hdr(skb);
+					dev_info(dev, "TCP source port %d\n",
+						 ntohs(tcphdr->source));
+					dev_info(dev, "TCP dest port %d\n",
+						 ntohs(tcphdr->dest));
+					dev_info(dev, "TCP sequence num %d\n",
+						 ntohs(tcphdr->seq));
+					dev_info(dev, "TCP ack_seq %d\n",
+						 ntohs(tcphdr->ack_seq));
+				} else if (ip_hdr(skb)->protocol ==
+					   IPPROTO_UDP) {
+					udphdr = udp_hdr(skb);
+					dev_info(dev, "UDP source port %d\n",
+						 ntohs(udphdr->source));
+					dev_info(dev, "UDP dest port %d\n",
+						 ntohs(udphdr->dest));
+				}
+				dev_info(dev, "skb[%d] %p len %d proto 0x%x\n",
+					 j, skb, skb->len, skb->protocol);
+			}
+		}
+	}
+
+	if (lancer_chip(adapter)) {
+		dev_info(dev, "Initiating reset due to tx timeout\n");
+		dev_info(dev, "Resetting adapter\n");
+		status = lancer_physdev_ctrl(adapter,
+					     PHYSDEV_CONTROL_FW_RESET_MASK);
+		if (status)
+			dev_err(dev, "Reset failed .. Reboot server\n");
+	}
+}
+
 static inline bool be_in_all_promisc(struct be_adapter *adapter)
 {
 	return (adapter->if_flags & BE_IF_FLAGS_ALL_PROMISCUOUS) ==
@@ -3274,7 +3359,7 @@ void be_detect_error(struct be_adapter *adapter)
 			/* Do not log error messages if its a FW reset */
 			if (sliport_err1 == SLIPORT_ERROR_FW_RESET1 &&
 			    sliport_err2 == SLIPORT_ERROR_FW_RESET2) {
-				dev_info(dev, "Firmware update in progress\n");
+				dev_info(dev, "Reset is in progress\n");
 			} else {
 				dev_err(dev, "Error detected in the card\n");
 				dev_err(dev, "ERR: sliport status 0x%x\n",
@@ -3403,9 +3488,11 @@ static int be_msix_register(struct be_adapter *adapter)
 	int status, i, vec;
 
 	for_all_evt_queues(adapter, eqo, i) {
-		sprintf(eqo->desc, "%s-q%d", netdev->name, i);
+		char irq_name[IFNAMSIZ+4];
+
+		snprintf(irq_name, sizeof(irq_name), "%s-q%d", netdev->name, i);
 		vec = be_msix_vec_get(adapter, eqo);
-		status = request_irq(vec, be_msix, 0, eqo->desc, eqo);
+		status = request_irq(vec, be_msix, 0, irq_name, eqo);
 		if (status)
 			goto err_msix;
 
@@ -5216,6 +5303,7 @@ static const struct net_device_ops be_netdev_ops = {
 	.ndo_get_vf_config	= be_get_vf_config,
 	.ndo_set_vf_link_state  = be_set_vf_link_state,
 	.ndo_set_vf_spoofchk    = be_set_vf_spoofchk,
+	.ndo_tx_timeout		= be_tx_timeout,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= be_netpoll,
 #endif
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index ab02057ac730..65a22cd9aef2 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -1171,7 +1171,7 @@ static int dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq,
 	buf_prefix_content.priv_data_size = buf_layout->priv_data_size;
 	buf_prefix_content.pass_prs_result = true;
 	buf_prefix_content.pass_hash_result = true;
-	buf_prefix_content.pass_time_stamp = false;
+	buf_prefix_content.pass_time_stamp = true;
 	buf_prefix_content.data_align = DPAA_FD_DATA_ALIGNMENT;
 
 	params.specific_params.non_rx_params.err_fqid = errq->fqid;
@@ -1213,7 +1213,7 @@ static int dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps,
 	buf_prefix_content.priv_data_size = buf_layout->priv_data_size;
 	buf_prefix_content.pass_prs_result = true;
 	buf_prefix_content.pass_hash_result = true;
-	buf_prefix_content.pass_time_stamp = false;
+	buf_prefix_content.pass_time_stamp = true;
 	buf_prefix_content.data_align = DPAA_FD_DATA_ALIGNMENT;
 
 	rx_p = &params.specific_params.rx_params;
@@ -1610,14 +1610,28 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv,
 {
 	const enum dma_data_direction dma_dir = DMA_TO_DEVICE;
 	struct device *dev = priv->net_dev->dev.parent;
+	struct skb_shared_hwtstamps shhwtstamps;
 	dma_addr_t addr = qm_fd_addr(fd);
 	const struct qm_sg_entry *sgt;
 	struct sk_buff **skbh, *skb;
 	int nr_frags, i;
+	u64 ns;
 
 	skbh = (struct sk_buff **)phys_to_virt(addr);
 	skb = *skbh;
 
+	if (priv->tx_tstamp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) {
+		memset(&shhwtstamps, 0, sizeof(shhwtstamps));
+
+		if (!fman_port_get_tstamp(priv->mac_dev->port[TX], (void *)skbh,
+					  &ns)) {
+			shhwtstamps.hwtstamp = ns_to_ktime(ns);
+			skb_tstamp_tx(skb, &shhwtstamps);
+		} else {
+			dev_warn(dev, "fman_port_get_tstamp failed!\n");
+		}
+	}
+
 	if (unlikely(qm_fd_get_format(fd) == qm_fd_sg)) {
 		nr_frags = skb_shinfo(skb)->nr_frags;
 		dma_unmap_single(dev, addr,
@@ -2087,6 +2101,11 @@ static int dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev)
 	if (unlikely(err < 0))
 		goto skb_to_fd_failed;
 
+	if (priv->tx_tstamp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) {
+		fd.cmd |= cpu_to_be32(FM_FD_CMD_UPD);
+		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+	}
+
 	if (likely(dpaa_xmit(priv, percpu_stats, queue_mapping, &fd) == 0))
 		return NETDEV_TX_OK;
 
@@ -2228,6 +2247,7 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal,
 						struct qman_fq *fq,
 						const struct qm_dqrr_entry *dq)
 {
+	struct skb_shared_hwtstamps *shhwtstamps;
 	struct rtnl_link_stats64 *percpu_stats;
 	struct dpaa_percpu_priv *percpu_priv;
 	const struct qm_fd *fd = &dq->fd;
@@ -2241,6 +2261,7 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal,
 	struct sk_buff *skb;
 	int *count_ptr;
 	void *vaddr;
+	u64 ns;
 
 	fd_status = be32_to_cpu(fd->status);
 	fd_format = qm_fd_get_format(fd);
@@ -2305,6 +2326,16 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal,
 	if (!skb)
 		return qman_cb_dqrr_consume;
 
+	if (priv->rx_tstamp) {
+		shhwtstamps = skb_hwtstamps(skb);
+		memset(shhwtstamps, 0, sizeof(*shhwtstamps));
+
+		if (!fman_port_get_tstamp(priv->mac_dev->port[RX], vaddr, &ns))
+			shhwtstamps->hwtstamp = ns_to_ktime(ns);
+		else
+			dev_warn(net_dev->dev.parent, "fman_port_get_tstamp failed!\n");
+	}
+
 	skb->protocol = eth_type_trans(skb, net_dev);
 
 	if (net_dev->features & NETIF_F_RXHASH && priv->keygen_in_use &&
@@ -2524,11 +2555,58 @@ static int dpaa_eth_stop(struct net_device *net_dev)
 	return err;
 }
 
+static int dpaa_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+{
+	struct dpaa_priv *priv = netdev_priv(dev);
+	struct hwtstamp_config config;
+
+	if (copy_from_user(&config, rq->ifr_data, sizeof(config)))
+		return -EFAULT;
+
+	switch (config.tx_type) {
+	case HWTSTAMP_TX_OFF:
+		/* Couldn't disable rx/tx timestamping separately.
+		 * Do nothing here.
+		 */
+		priv->tx_tstamp = false;
+		break;
+	case HWTSTAMP_TX_ON:
+		priv->mac_dev->set_tstamp(priv->mac_dev->fman_mac, true);
+		priv->tx_tstamp = true;
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	if (config.rx_filter == HWTSTAMP_FILTER_NONE) {
+		/* Couldn't disable rx/tx timestamping separately.
+		 * Do nothing here.
+		 */
+		priv->rx_tstamp = false;
+	} else {
+		priv->mac_dev->set_tstamp(priv->mac_dev->fman_mac, true);
+		priv->rx_tstamp = true;
+		/* TS is set for all frame types, not only those requested */
+		config.rx_filter = HWTSTAMP_FILTER_ALL;
+	}
+
+	return copy_to_user(rq->ifr_data, &config, sizeof(config)) ?
+			-EFAULT : 0;
+}
+
 static int dpaa_ioctl(struct net_device *net_dev, struct ifreq *rq, int cmd)
 {
-	if (!net_dev->phydev)
-		return -EINVAL;
-	return phy_mii_ioctl(net_dev->phydev, rq, cmd);
+	int ret = -EINVAL;
+
+	if (cmd == SIOCGMIIREG) {
+		if (net_dev->phydev)
+			return phy_mii_ioctl(net_dev->phydev, rq, cmd);
+	}
+
+	if (cmd == SIOCSHWTSTAMP)
+		return dpaa_ts_ioctl(net_dev, rq, cmd);
+
+	return ret;
 }
 
 static const struct net_device_ops dpaa_ops = {
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
index bd9422082f83..af320f83c742 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
@@ -182,6 +182,9 @@ struct dpaa_priv {
 
 	struct dpaa_buffer_layout buf_layout[2];
 	u16 rx_headroom;
+
+	bool tx_tstamp; /* Tx timestamping enabled */
+	bool rx_tstamp; /* Rx timestamping enabled */
 };
 
 /* from dpaa_ethtool.c */
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
index 2f933b6b2f4e..3184c8f7cdd0 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
@@ -32,6 +32,9 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/string.h>
+#include <linux/of_platform.h>
+#include <linux/net_tstamp.h>
+#include <linux/fsl/ptp_qoriq.h>
 
 #include "dpaa_eth.h"
 #include "mac.h"
@@ -515,6 +518,41 @@ static int dpaa_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 	return ret;
 }
 
+static int dpaa_get_ts_info(struct net_device *net_dev,
+			    struct ethtool_ts_info *info)
+{
+	struct device *dev = net_dev->dev.parent;
+	struct device_node *mac_node = dev->of_node;
+	struct device_node *fman_node = NULL, *ptp_node = NULL;
+	struct platform_device *ptp_dev = NULL;
+	struct qoriq_ptp *ptp = NULL;
+
+	info->phc_index = -1;
+
+	fman_node = of_get_parent(mac_node);
+	if (fman_node)
+		ptp_node = of_parse_phandle(fman_node, "ptimer-handle", 0);
+
+	if (ptp_node)
+		ptp_dev = of_find_device_by_node(ptp_node);
+
+	if (ptp_dev)
+		ptp = platform_get_drvdata(ptp_dev);
+
+	if (ptp)
+		info->phc_index = ptp->phc_index;
+
+	info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
+				SOF_TIMESTAMPING_RX_HARDWARE |
+				SOF_TIMESTAMPING_RAW_HARDWARE;
+	info->tx_types = (1 << HWTSTAMP_TX_OFF) |
+			 (1 << HWTSTAMP_TX_ON);
+	info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
+			   (1 << HWTSTAMP_FILTER_ALL);
+
+	return 0;
+}
+
 const struct ethtool_ops dpaa_ethtool_ops = {
 	.get_drvinfo = dpaa_get_drvinfo,
 	.get_msglevel = dpaa_get_msglevel,
@@ -530,4 +568,5 @@ const struct ethtool_ops dpaa_ethtool_ops = {
 	.set_link_ksettings = dpaa_set_link_ksettings,
 	.get_rxnfc = dpaa_get_rxnfc,
 	.set_rxnfc = dpaa_set_rxnfc,
+	.get_ts_info = dpaa_get_ts_info,
 };
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index c729665107f5..2708297e7795 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -48,6 +48,7 @@
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/clk.h>
+#include <linux/crc32.h>
 #include <linux/platform_device.h>
 #include <linux/mdio.h>
 #include <linux/phy.h>
@@ -2949,13 +2950,12 @@ fec_enet_close(struct net_device *ndev)
  */
 
 #define FEC_HASH_BITS	6		/* #bits in hash */
-#define CRC32_POLY	0xEDB88320
 
 static void set_multicast_list(struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	struct netdev_hw_addr *ha;
-	unsigned int i, bit, data, crc, tmp;
+	unsigned int crc, tmp;
 	unsigned char hash;
 	unsigned int hash_high = 0, hash_low = 0;
 
@@ -2983,15 +2983,7 @@ static void set_multicast_list(struct net_device *ndev)
 	/* Add the addresses in hash register */
 	netdev_for_each_mc_addr(ha, ndev) {
 		/* calculate crc32 value of mac address */
-		crc = 0xffffffff;
-
-		for (i = 0; i < ndev->addr_len; i++) {
-			data = ha->addr[i];
-			for (bit = 0; bit < 8; bit++, data >>= 1) {
-				crc = (crc >> 1) ^
-				(((crc ^ data) & 1) ? CRC32_POLY : 0);
-			}
-		}
+		crc = ether_crc_le(ndev->addr_len, ha->addr);
 
 		/* only upper 6 bits (FEC_HASH_BITS) are used
 		 * which point to specific bit in the hash registers
@@ -3136,6 +3128,7 @@ static int fec_enet_init(struct net_device *ndev)
 	unsigned dsize = fep->bufdesc_ex ? sizeof(struct bufdesc_ex) :
 			sizeof(struct bufdesc);
 	unsigned dsize_log2 = __fls(dsize);
+	int ret;
 
 	WARN_ON(dsize != (1 << dsize_log2));
 #if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
@@ -3146,6 +3139,13 @@ static int fec_enet_init(struct net_device *ndev)
 	fep->tx_align = 0x3;
 #endif
 
+	/* Check mask of the streaming and coherent API */
+	ret = dma_set_mask_and_coherent(&fep->pdev->dev, DMA_BIT_MASK(32));
+	if (ret < 0) {
+		dev_warn(&fep->pdev->dev, "No suitable DMA available\n");
+		return ret;
+	}
+
 	fec_enet_alloc_queue(ndev);
 
 	bd_size = (fep->total_tx_ring_size + fep->total_rx_ring_size) * dsize;
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 36c2d7d6ee1b..7e892b1cbd3d 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -99,7 +99,6 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable)
 {
 	unsigned long flags;
 	u32 val, tempval;
-	int inc;
 	struct timespec64 ts;
 	u64 ns;
 	val = 0;
@@ -114,7 +113,6 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable)
 
 	fep->pps_channel = DEFAULT_PPS_CHANNEL;
 	fep->reload_period = PPS_OUPUT_RELOAD_PERIOD;
-	inc = fep->ptp_inc;
 
 	spin_lock_irqsave(&fep->tmreg_lock, flags);
 
diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c
index 9530405030a7..c415ac67cb7b 100644
--- a/drivers/net/ethernet/freescale/fman/fman.c
+++ b/drivers/net/ethernet/freescale/fman/fman.c
@@ -2801,7 +2801,8 @@ static struct fman *read_dts_node(struct platform_device *of_dev)
 	of_node_put(muram_node);
 	of_node_put(fm_node);
 
-	err = devm_request_irq(&of_dev->dev, irq, fman_irq, 0, "fman", fman);
+	err = devm_request_irq(&of_dev->dev, irq, fman_irq, IRQF_SHARED,
+			       "fman", fman);
 	if (err < 0) {
 		dev_err(&of_dev->dev, "%s: irq %d allocation failed (error = %d)\n",
 			__func__, irq, err);
diff --git a/drivers/net/ethernet/freescale/fman/fman.h b/drivers/net/ethernet/freescale/fman/fman.h
index bfa02e0014ae..935c317fa696 100644
--- a/drivers/net/ethernet/freescale/fman/fman.h
+++ b/drivers/net/ethernet/freescale/fman/fman.h
@@ -41,6 +41,7 @@
 /* Frame queue Context Override */
 #define FM_FD_CMD_FCO                   0x80000000
 #define FM_FD_CMD_RPD                   0x40000000  /* Read Prepended Data */
+#define FM_FD_CMD_UPD			0x20000000  /* Update Prepended Data */
 #define FM_FD_CMD_DTC                   0x10000000  /* Do L4 Checksum */
 
 /* TX-Port: Unsupported Format */
diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
index 57b1e2b47c0a..1ca543ac8f2c 100644
--- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c
+++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
@@ -123,11 +123,13 @@
 #define DTSEC_ECNTRL_R100M		0x00000008
 #define DTSEC_ECNTRL_QSGMIIM		0x00000001
 
+#define TCTRL_TTSE			0x00000040
 #define TCTRL_GTS			0x00000020
 
 #define RCTRL_PAL_MASK			0x001f0000
 #define RCTRL_PAL_SHIFT			16
 #define RCTRL_GHTX			0x00000400
+#define RCTRL_RTSE			0x00000040
 #define RCTRL_GRS			0x00000020
 #define RCTRL_MPROM			0x00000008
 #define RCTRL_RSF			0x00000004
@@ -1136,6 +1138,31 @@ int dtsec_set_allmulti(struct fman_mac *dtsec, bool enable)
 	return 0;
 }
 
+int dtsec_set_tstamp(struct fman_mac *dtsec, bool enable)
+{
+	struct dtsec_regs __iomem *regs = dtsec->regs;
+	u32 rctrl, tctrl;
+
+	if (!is_init_done(dtsec->dtsec_drv_param))
+		return -EINVAL;
+
+	rctrl = ioread32be(&regs->rctrl);
+	tctrl = ioread32be(&regs->tctrl);
+
+	if (enable) {
+		rctrl |= RCTRL_RTSE;
+		tctrl |= TCTRL_TTSE;
+	} else {
+		rctrl &= ~RCTRL_RTSE;
+		tctrl &= ~TCTRL_TTSE;
+	}
+
+	iowrite32be(rctrl, &regs->rctrl);
+	iowrite32be(tctrl, &regs->tctrl);
+
+	return 0;
+}
+
 int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr)
 {
 	struct dtsec_regs __iomem *regs = dtsec->regs;
diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.h b/drivers/net/ethernet/freescale/fman/fman_dtsec.h
index 1a689adf5a22..5149d96ec2c1 100644
--- a/drivers/net/ethernet/freescale/fman/fman_dtsec.h
+++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.h
@@ -56,5 +56,6 @@ int dtsec_add_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr);
 int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr);
 int dtsec_get_version(struct fman_mac *dtsec, u32 *mac_version);
 int dtsec_set_allmulti(struct fman_mac *dtsec, bool enable);
+int dtsec_set_tstamp(struct fman_mac *dtsec, bool enable);
 
 #endif /* __DTSEC_H */
diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c
index 446a97b792e3..bc6eb30aa20f 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.c
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.c
@@ -964,6 +964,11 @@ int memac_set_allmulti(struct fman_mac *memac, bool enable)
 	return 0;
 }
 
+int memac_set_tstamp(struct fman_mac *memac, bool enable)
+{
+	return 0; /* Always enabled. */
+}
+
 int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr)
 {
 	struct memac_regs __iomem *regs = memac->regs;
diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.h b/drivers/net/ethernet/freescale/fman/fman_memac.h
index b5a50338ed9a..b2c671ec0ce7 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.h
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.h
@@ -58,5 +58,6 @@ int memac_set_exception(struct fman_mac *memac,
 int memac_add_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr);
 int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr);
 int memac_set_allmulti(struct fman_mac *memac, bool enable);
+int memac_set_tstamp(struct fman_mac *memac, bool enable);
 
 #endif /* __MEMAC_H */
diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c
index ecbf6187e13a..ee82ee1384eb 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.c
+++ b/drivers/net/ethernet/freescale/fman/fman_port.c
@@ -1739,6 +1739,18 @@ int fman_port_get_hash_result_offset(struct fman_port *port, u32 *offset)
 }
 EXPORT_SYMBOL(fman_port_get_hash_result_offset);
 
+int fman_port_get_tstamp(struct fman_port *port, const void *data, u64 *tstamp)
+{
+	if (port->buffer_offsets.time_stamp_offset == ILLEGAL_BASE)
+		return -EINVAL;
+
+	*tstamp = be64_to_cpu(*(__be64 *)(data +
+			port->buffer_offsets.time_stamp_offset));
+
+	return 0;
+}
+EXPORT_SYMBOL(fman_port_get_tstamp);
+
 static int fman_port_probe(struct platform_device *of_dev)
 {
 	struct fman_port *port;
diff --git a/drivers/net/ethernet/freescale/fman/fman_port.h b/drivers/net/ethernet/freescale/fman/fman_port.h
index e86ca6a34e4e..9dbb69f40121 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.h
+++ b/drivers/net/ethernet/freescale/fman/fman_port.h
@@ -153,6 +153,8 @@ u32 fman_port_get_qman_channel_id(struct fman_port *port);
 
 int fman_port_get_hash_result_offset(struct fman_port *port, u32 *offset);
 
+int fman_port_get_tstamp(struct fman_port *port, const void *data, u64 *tstamp);
+
 struct fman_port *fman_port_bind(struct device *dev);
 
 #endif /* __FMAN_PORT_H */
diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.c b/drivers/net/ethernet/freescale/fman/fman_tgec.c
index 284735d4ebe9..40705938eecc 100644
--- a/drivers/net/ethernet/freescale/fman/fman_tgec.c
+++ b/drivers/net/ethernet/freescale/fman/fman_tgec.c
@@ -44,6 +44,7 @@
 #define TGEC_TX_IPG_LENGTH_MASK	0x000003ff
 
 /* Command and Configuration Register (COMMAND_CONFIG) */
+#define CMD_CFG_EN_TIMESTAMP		0x00100000
 #define CMD_CFG_NO_LEN_CHK		0x00020000
 #define CMD_CFG_PAUSE_IGNORE		0x00000100
 #define CMF_CFG_CRC_FWD			0x00000040
@@ -588,6 +589,26 @@ int tgec_set_allmulti(struct fman_mac *tgec, bool enable)
 	return 0;
 }
 
+int tgec_set_tstamp(struct fman_mac *tgec, bool enable)
+{
+	struct tgec_regs __iomem *regs = tgec->regs;
+	u32 tmp;
+
+	if (!is_init_done(tgec->cfg))
+		return -EINVAL;
+
+	tmp = ioread32be(&regs->command_config);
+
+	if (enable)
+		tmp |= CMD_CFG_EN_TIMESTAMP;
+	else
+		tmp &= ~CMD_CFG_EN_TIMESTAMP;
+
+	iowrite32be(tmp, &regs->command_config);
+
+	return 0;
+}
+
 int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr)
 {
 	struct tgec_regs __iomem *regs = tgec->regs;
diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.h b/drivers/net/ethernet/freescale/fman/fman_tgec.h
index cbbd3b422a98..3bfd1062b386 100644
--- a/drivers/net/ethernet/freescale/fman/fman_tgec.h
+++ b/drivers/net/ethernet/freescale/fman/fman_tgec.h
@@ -52,5 +52,6 @@ int tgec_add_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr);
 int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr);
 int tgec_get_version(struct fman_mac *tgec, u32 *mac_version);
 int tgec_set_allmulti(struct fman_mac *tgec, bool enable);
+int tgec_set_tstamp(struct fman_mac *tgec, bool enable);
 
 #endif /* __TGEC_H */
diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c
index 7b5b95f52c09..a847b9c3b31a 100644
--- a/drivers/net/ethernet/freescale/fman/mac.c
+++ b/drivers/net/ethernet/freescale/fman/mac.c
@@ -471,6 +471,7 @@ static void setup_dtsec(struct mac_device *mac_dev)
 	mac_dev->set_rx_pause		= dtsec_accept_rx_pause_frames;
 	mac_dev->set_exception		= dtsec_set_exception;
 	mac_dev->set_allmulti		= dtsec_set_allmulti;
+	mac_dev->set_tstamp		= dtsec_set_tstamp;
 	mac_dev->set_multi		= set_multi;
 	mac_dev->start			= start;
 	mac_dev->stop			= stop;
@@ -490,6 +491,7 @@ static void setup_tgec(struct mac_device *mac_dev)
 	mac_dev->set_rx_pause		= tgec_accept_rx_pause_frames;
 	mac_dev->set_exception		= tgec_set_exception;
 	mac_dev->set_allmulti		= tgec_set_allmulti;
+	mac_dev->set_tstamp		= tgec_set_tstamp;
 	mac_dev->set_multi		= set_multi;
 	mac_dev->start			= start;
 	mac_dev->stop			= stop;
@@ -509,6 +511,7 @@ static void setup_memac(struct mac_device *mac_dev)
 	mac_dev->set_rx_pause		= memac_accept_rx_pause_frames;
 	mac_dev->set_exception		= memac_set_exception;
 	mac_dev->set_allmulti		= memac_set_allmulti;
+	mac_dev->set_tstamp		= memac_set_tstamp;
 	mac_dev->set_multi		= set_multi;
 	mac_dev->start			= start;
 	mac_dev->stop			= stop;
diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h
index b520cec120ee..824a81a9f350 100644
--- a/drivers/net/ethernet/freescale/fman/mac.h
+++ b/drivers/net/ethernet/freescale/fman/mac.h
@@ -68,6 +68,7 @@ struct mac_device {
 	int (*set_promisc)(struct fman_mac *mac_dev, bool enable);
 	int (*change_addr)(struct fman_mac *mac_dev, enet_addr_t *enet_addr);
 	int (*set_allmulti)(struct fman_mac *mac_dev, bool enable);
+	int (*set_tstamp)(struct fman_mac *mac_dev, bool enable);
 	int (*set_multi)(struct net_device *net_dev,
 			 struct mac_device *mac_dev);
 	int (*set_rx_pause)(struct fman_mac *mac_dev, bool en);
diff --git a/drivers/net/ethernet/freescale/fs_enet/fec.h b/drivers/net/ethernet/freescale/fs_enet/fec.h
index 7832db71dcb9..1dbee5d898b3 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fec.h
+++ b/drivers/net/ethernet/freescale/fs_enet/fec.h
@@ -2,9 +2,6 @@
 #ifndef FS_ENET_FEC_H
 #define FS_ENET_FEC_H
 
-/* CRC polynomium used by the FEC for the multicast group filtering */
-#define FEC_CRC_POLY   0x04C11DB7
-
 #define FEC_MAX_MULTICAST_ADDRS	64
 
 /* Interrupt events/masks.
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
index 1fc27c97e3b2..99fe2c210d0f 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
@@ -18,6 +18,7 @@
 #include <linux/string.h>
 #include <linux/ptrace.h>
 #include <linux/errno.h>
+#include <linux/crc32.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
@@ -176,21 +177,10 @@ static void set_multicast_start(struct net_device *dev)
 static void set_multicast_one(struct net_device *dev, const u8 *mac)
 {
 	struct fs_enet_private *fep = netdev_priv(dev);
-	int temp, hash_index, i, j;
+	int temp, hash_index;
 	u32 crc, csrVal;
-	u8 byte, msb;
-
-	crc = 0xffffffff;
-	for (i = 0; i < 6; i++) {
-		byte = mac[i];
-		for (j = 0; j < 8; j++) {
-			msb = crc >> 31;
-			crc <<= 1;
-			if (msb ^ (byte & 0x1))
-				crc ^= FEC_CRC_POLY;
-			byte >>= 1;
-		}
-	}
+
+	crc = ether_crc(6, mac);
 
 	temp = (crc & 0x3f) >> 1;
 	hash_index = ((temp & 0x01) << 4) |
diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index 8cb98cae0a6f..395a5266ea30 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -740,7 +740,6 @@ static void ethflow_to_filer_rules (struct gfar_private *priv, u64 ethflow)
 static int gfar_ethflow_to_filer_table(struct gfar_private *priv, u64 ethflow,
 				       u64 class)
 {
-	unsigned int last_rule_idx = priv->cur_filer_idx;
 	unsigned int cmp_rqfpr;
 	unsigned int *local_rqfpr;
 	unsigned int *local_rqfcr;
@@ -819,7 +818,6 @@ static int gfar_ethflow_to_filer_table(struct gfar_private *priv, u64 ethflow,
 	}
 
 	priv->cur_filer_idx = l - 1;
-	last_rule_idx = l;
 
 	/* hash rules */
 	ethflow_to_filer_rules(priv, ethflow);
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 42fca3208c0b..22a817da861e 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -3096,6 +3096,7 @@ static int ucc_geth_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	ugeth_vdbg("%s: IN", __func__);
 
+	netdev_sent_queue(dev, skb->len);
 	spin_lock_irqsave(&ugeth->lock, flags);
 
 	dev->stats.tx_bytes += skb->len;
@@ -3240,6 +3241,8 @@ static int ucc_geth_tx(struct net_device *dev, u8 txQ)
 {
 	/* Start from the next BD that should be filled */
 	struct ucc_geth_private *ugeth = netdev_priv(dev);
+	unsigned int bytes_sent = 0;
+	int howmany = 0;
 	u8 __iomem *bd;		/* BD pointer */
 	u32 bd_status;
 
@@ -3257,7 +3260,8 @@ static int ucc_geth_tx(struct net_device *dev, u8 txQ)
 		skb = ugeth->tx_skbuff[txQ][ugeth->skb_dirtytx[txQ]];
 		if (!skb)
 			break;
-
+		howmany++;
+		bytes_sent += skb->len;
 		dev->stats.tx_packets++;
 
 		dev_consume_skb_any(skb);
@@ -3279,6 +3283,7 @@ static int ucc_geth_tx(struct net_device *dev, u8 txQ)
 		bd_status = in_be32((u32 __iomem *)bd);
 	}
 	ugeth->confBd[txQ] = bd;
+	netdev_completed_queue(dev, howmany, bytes_sent);
 	return 0;
 }
 
@@ -3479,6 +3484,7 @@ static int ucc_geth_open(struct net_device *dev)
 
 	phy_start(ugeth->phydev);
 	napi_enable(&ugeth->napi);
+	netdev_reset_queue(dev);
 	netif_start_queue(dev);
 
 	device_set_wakeup_capable(&dev->dev,
@@ -3509,6 +3515,7 @@ static int ucc_geth_close(struct net_device *dev)
 	free_irq(ugeth->ug_info->uf_info.irq, ugeth->ndev);
 
 	netif_stop_queue(dev);
+	netdev_reset_queue(dev);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index fb1a7251f45d..25152715396b 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -85,10 +85,12 @@ config HNS3
 	  drivers(like ODP)to register with HNAE devices and their associated
 	  operations.
 
+if HNS3
+
 config HNS3_HCLGE
 	tristate "Hisilicon HNS3 HCLGE Acceleration Engine & Compatibility Layer Support"
+	default m
 	depends on PCI_MSI
-	depends on HNS3
 	---help---
 	  This selects the HNS3_HCLGE network acceleration engine & its hardware
 	  compatibility layer. The engine would be used in Hisilicon hip08 family of
@@ -97,16 +99,15 @@ config HNS3_HCLGE
 config HNS3_DCB
 	bool "Hisilicon HNS3 Data Center Bridge Support"
 	default n
-	depends on HNS3 && HNS3_HCLGE && DCB
+	depends on HNS3_HCLGE && DCB
 	---help---
 	  Say Y here if you want to use Data Center Bridging (DCB) in the HNS3 driver.
 
 	  If unsure, say N.
 
 config HNS3_HCLGEVF
-    tristate "Hisilicon HNS3VF Acceleration Engine & Compatibility Layer Support"
-    depends on PCI_MSI
-    depends on HNS3
+	tristate "Hisilicon HNS3VF Acceleration Engine & Compatibility Layer Support"
+	depends on PCI_MSI
 	depends on HNS3_HCLGE
     ---help---
 	  This selects the HNS3 VF drivers network acceleration engine & its hardware
@@ -115,11 +116,13 @@ config HNS3_HCLGEVF
 
 config HNS3_ENET
 	tristate "Hisilicon HNS3 Ethernet Device Support"
+	default m
 	depends on 64BIT && PCI
-	depends on HNS3
 	---help---
 	  This selects the Ethernet Driver for Hisilicon Network Subsystem 3 for hip08
 	  family of SoCs. This module depends upon HNAE3 driver to access the HNAE3
 	  devices and their associated operations.
 
+endif #HNS3
+
 endif # NET_VENDOR_HISILICON
diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index 340e28211135..14374a856d30 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -904,7 +904,7 @@ static int hip04_mac_probe(struct platform_device *pdev)
 		hip04_config_port(ndev, SPEED_100, DUPLEX_FULL);
 
 	hip04_config_fifo(priv);
-	random_ether_addr(ndev->dev_addr);
+	eth_random_addr(ndev->dev_addr);
 	hip04_update_mac_address(ndev);
 
 	ret = hip04_alloc_ring(ndev, d);
diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
index 25a6c8722eca..c5727003af8c 100644
--- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
+++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
@@ -1006,12 +1006,11 @@ static int hix5hd2_init_hw_desc_queue(struct hix5hd2_priv *priv)
 
 	for (i = 0; i < QUEUE_NUMS; i++) {
 		size = priv->pool[i].count * sizeof(struct hix5hd2_desc);
-		virt_addr = dma_alloc_coherent(dev, size, &phys_addr,
-					       GFP_KERNEL);
+		virt_addr = dma_zalloc_coherent(dev, size, &phys_addr,
+						GFP_KERNEL);
 		if (virt_addr == NULL)
 			goto error_free_pool;
 
-		memset(virt_addr, 0, size);
 		priv->pool[i].size = size;
 		priv->pool[i].desc = virt_addr;
 		priv->pool[i].phys_addr = phys_addr;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
index bd68379d2bea..e6aad30e7e69 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
@@ -70,8 +70,8 @@ static struct ring_pair_cb *hns_ae_get_ring_pair(struct hnae_queue *q)
 	return container_of(q, struct ring_pair_cb, q);
 }
 
-struct hnae_handle *hns_ae_get_handle(struct hnae_ae_dev *dev,
-				      u32 port_id)
+static struct hnae_handle *hns_ae_get_handle(struct hnae_ae_dev *dev,
+					     u32 port_id)
 {
 	int vfnum_per_port;
 	int qnum_per_vf;
@@ -329,7 +329,7 @@ static int hns_ae_start(struct hnae_handle *handle)
 	return 0;
 }
 
-void hns_ae_stop(struct hnae_handle *handle)
+static void hns_ae_stop(struct hnae_handle *handle)
 {
 	struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle);
 
@@ -357,7 +357,7 @@ static void hns_ae_reset(struct hnae_handle *handle)
 	}
 }
 
-void hns_ae_toggle_ring_irq(struct hnae_ring *ring, u32 mask)
+static void hns_ae_toggle_ring_irq(struct hnae_ring *ring, u32 mask)
 {
 	u32 flag;
 
@@ -577,8 +577,8 @@ static void hns_ae_get_coalesce_range(struct hnae_handle *handle,
 	*rx_usecs_high  = HNS_RCB_RX_USECS_HIGH;
 }
 
-void hns_ae_update_stats(struct hnae_handle *handle,
-			 struct net_device_stats *net_stats)
+static void hns_ae_update_stats(struct hnae_handle *handle,
+				struct net_device_stats *net_stats)
 {
 	int port;
 	int idx;
@@ -660,7 +660,7 @@ void hns_ae_update_stats(struct hnae_handle *handle,
 	net_stats->multicast = mac_cb->hw_stats.rx_mc_pkts;
 }
 
-void hns_ae_get_stats(struct hnae_handle *handle, u64 *data)
+static void hns_ae_get_stats(struct hnae_handle *handle, u64 *data)
 {
 	int idx;
 	struct hns_mac_cb *mac_cb;
@@ -692,8 +692,8 @@ void hns_ae_get_stats(struct hnae_handle *handle, u64 *data)
 		hns_dsaf_get_stats(vf_cb->dsaf_dev, p, vf_cb->port_index);
 }
 
-void hns_ae_get_strings(struct hnae_handle *handle,
-			u32 stringset, u8 *data)
+static void hns_ae_get_strings(struct hnae_handle *handle,
+			       u32 stringset, u8 *data)
 {
 	int port;
 	int idx;
@@ -725,7 +725,7 @@ void hns_ae_get_strings(struct hnae_handle *handle,
 		hns_dsaf_get_strings(stringset, p, port, dsaf_dev);
 }
 
-int hns_ae_get_sset_count(struct hnae_handle *handle, int stringset)
+static int hns_ae_get_sset_count(struct hnae_handle *handle, int stringset)
 {
 	u32 sset_count = 0;
 	struct hns_mac_cb *mac_cb;
@@ -771,7 +771,7 @@ static int hns_ae_config_loopback(struct hnae_handle *handle,
 	return ret;
 }
 
-void hns_ae_update_led_status(struct hnae_handle *handle)
+static void hns_ae_update_led_status(struct hnae_handle *handle)
 {
 	struct hns_mac_cb *mac_cb;
 
@@ -783,8 +783,8 @@ void hns_ae_update_led_status(struct hnae_handle *handle)
 	hns_set_led_opt(mac_cb);
 }
 
-int hns_ae_cpld_set_led_id(struct hnae_handle *handle,
-			   enum hnae_led_state status)
+static int hns_ae_cpld_set_led_id(struct hnae_handle *handle,
+				  enum hnae_led_state status)
 {
 	struct hns_mac_cb *mac_cb;
 
@@ -795,7 +795,7 @@ int hns_ae_cpld_set_led_id(struct hnae_handle *handle,
 	return hns_cpld_led_set_id(mac_cb, status);
 }
 
-void hns_ae_get_regs(struct hnae_handle *handle, void *data)
+static void hns_ae_get_regs(struct hnae_handle *handle, void *data)
 {
 	u32 *p = data;
 	int i;
@@ -820,7 +820,7 @@ void hns_ae_get_regs(struct hnae_handle *handle, void *data)
 		hns_dsaf_get_regs(vf_cb->dsaf_dev, vf_cb->port_index, p);
 }
 
-int hns_ae_get_regs_len(struct hnae_handle *handle)
+static int hns_ae_get_regs_len(struct hnae_handle *handle)
 {
 	u32 total_num;
 	struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
index 74bd260ca02a..5488c6e89f21 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
@@ -339,7 +339,7 @@ static void hns_gmac_init(void *mac_drv)
 			   GMAC_TX_WATER_LINE_SHIFT, 8);
 }
 
-void hns_gmac_update_stats(void *mac_drv)
+static void hns_gmac_update_stats(void *mac_drv)
 {
 	struct mac_hw_stats *hw_stats = NULL;
 	struct mac_driver *drv = (struct mac_driver *)mac_drv;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index 9dcc5765f11f..1c2326bd76e2 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -458,11 +458,6 @@ int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu, u32 buf_size)
 {
 	struct mac_driver *drv = hns_mac_get_drv(mac_cb);
 	u32 new_frm = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
-	u32 max_frm = AE_IS_VER1(mac_cb->dsaf_dev->dsaf_ver) ?
-			MAC_MAX_MTU : MAC_MAX_MTU_V2;
-
-	if (mac_cb->mac_type == HNAE_PORT_DEBUG)
-		max_frm = MAC_MAX_MTU_DBG;
 
 	if (new_frm > HNS_RCB_RING_MAX_BD_PER_PKT * buf_size)
 		return -EINVAL;
@@ -708,7 +703,7 @@ hns_mac_register_phydev(struct mii_bus *mdio, struct hns_mac_cb *mac_cb,
 
 static int hns_mac_register_phy(struct hns_mac_cb *mac_cb)
 {
-	struct acpi_reference_args args;
+	struct fwnode_reference_args args;
 	struct platform_device *pdev;
 	struct mii_bus *mii_bus;
 	int rc;
@@ -722,13 +717,15 @@ static int hns_mac_register_phy(struct hns_mac_cb *mac_cb)
 			mac_cb->fw_port, "mdio-node", 0, &args);
 	if (rc)
 		return rc;
+	if (!is_acpi_device_node(args.fwnode))
+		return -EINVAL;
 
 	addr = hns_mac_phy_parse_addr(mac_cb->dev, mac_cb->fw_port);
 	if (addr < 0)
 		return addr;
 
 	/* dev address in adev */
-	pdev = hns_dsaf_find_platform_device(acpi_fwnode_handle(args.adev));
+	pdev = hns_dsaf_find_platform_device(args.fwnode);
 	if (!pdev) {
 		dev_err(mac_cb->dev, "mac%d mdio pdev is NULL\n",
 			mac_cb->mac_id);
@@ -931,8 +928,9 @@ static int hns_mac_get_mode(phy_interface_t phy_if)
 	}
 }
 
-u8 __iomem *hns_mac_get_vaddr(struct dsaf_device *dsaf_dev,
-			      struct hns_mac_cb *mac_cb, u32 mac_mode_idx)
+static u8 __iomem *
+hns_mac_get_vaddr(struct dsaf_device *dsaf_dev,
+		  struct hns_mac_cb *mac_cb, u32 mac_mode_idx)
 {
 	u8 __iomem *base = dsaf_dev->io_base;
 	int mac_id = mac_cb->mac_id;
@@ -950,7 +948,8 @@ u8 __iomem *hns_mac_get_vaddr(struct dsaf_device *dsaf_dev,
  * @mac_cb: mac control block
  * return 0 - success , negative --fail
  */
-int hns_mac_get_cfg(struct dsaf_device *dsaf_dev, struct hns_mac_cb *mac_cb)
+static int
+hns_mac_get_cfg(struct dsaf_device *dsaf_dev, struct hns_mac_cb *mac_cb)
 {
 	int ret;
 	u32 mac_mode_idx;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index 0ce07f6eb1e6..ca50c2553a9c 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -28,7 +28,7 @@
 #include "hns_dsaf_rcb.h"
 #include "hns_dsaf_misc.h"
 
-const char *g_dsaf_mode_match[DSAF_MODE_MAX] = {
+const static char *g_dsaf_mode_match[DSAF_MODE_MAX] = {
 	[DSAF_MODE_DISABLE_2PORT_64VM] = "2port-64vf",
 	[DSAF_MODE_DISABLE_6PORT_0VM] = "6port-16rss",
 	[DSAF_MODE_DISABLE_6PORT_16VM] = "6port-16vf",
@@ -42,7 +42,7 @@ static const struct acpi_device_id hns_dsaf_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, hns_dsaf_acpi_match);
 
-int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev)
+static int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev)
 {
 	int ret, i;
 	u32 desc_num;
@@ -959,7 +959,8 @@ static void hns_dsaf_tcam_mc_invld(struct dsaf_device *dsaf_dev, u32 address)
 	spin_unlock_bh(&dsaf_dev->tcam_lock);
 }
 
-void hns_dsaf_tcam_addr_get(struct dsaf_drv_tbl_tcam_key *mac_key, u8 *addr)
+static void
+hns_dsaf_tcam_addr_get(struct dsaf_drv_tbl_tcam_key *mac_key, u8 *addr)
 {
 	addr[0] = mac_key->high.bits.mac_0;
 	addr[1] = mac_key->high.bits.mac_1;
@@ -1682,7 +1683,6 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev,
 	struct dsaf_tbl_tcam_mcast_cfg mac_data;
 	struct dsaf_drv_priv *priv = hns_dsaf_dev_priv(dsaf_dev);
 	struct dsaf_drv_soft_mac_tbl *soft_mac_entry = priv->soft_mac_tbl;
-	struct dsaf_drv_tbl_tcam_key tmp_mac_key;
 	struct dsaf_tbl_tcam_data tcam_data;
 	u8 mc_addr[ETH_ALEN];
 	int mskid;
@@ -1739,10 +1739,6 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev,
 		/* if exist, add in */
 		hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data,
 				     &mac_data);
-
-		tmp_mac_key.high.val =
-			le32_to_cpu(tcam_data.tbl_tcam_data_high);
-		tmp_mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
 	}
 
 	/* config hardware entry */
@@ -1852,7 +1848,7 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev,
 	struct dsaf_tbl_tcam_data tcam_data;
 	int mskid;
 	const u8 empty_msk[sizeof(mac_data.tbl_mcast_port_msk)] = {0};
-	struct dsaf_drv_tbl_tcam_key mask_key, tmp_mac_key;
+	struct dsaf_drv_tbl_tcam_key mask_key;
 	struct dsaf_tbl_tcam_data *pmask_key = NULL;
 	u8 mc_addr[ETH_ALEN];
 
@@ -1915,9 +1911,6 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev,
 	/* read entry */
 	hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data, &mac_data);
 
-	tmp_mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high);
-	tmp_mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
-
 	/*del the port*/
 	if (mac_entry->port_num < DSAF_SERVICE_NW_NUM) {
 		mskid = mac_entry->port_num;
@@ -2084,8 +2077,9 @@ static void hns_dsaf_pfc_unit_cnt(struct dsaf_device *dsaf_dev, int  mac_id,
  * @dsaf_id: dsa fabric id
  * @xge_ge_work_mode
  */
-void hns_dsaf_port_work_rate_cfg(struct dsaf_device *dsaf_dev, int mac_id,
-				 enum dsaf_port_rate_mode rate_mode)
+static void
+hns_dsaf_port_work_rate_cfg(struct dsaf_device *dsaf_dev, int mac_id,
+			    enum dsaf_port_rate_mode rate_mode)
 {
 	u32 port_work_mode;
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
index acf29633ec79..16294cd3c954 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
@@ -340,7 +340,8 @@ static void hns_dsaf_xge_srst_by_port_acpi(struct dsaf_device *dsaf_dev,
  * bit18-19 for com/dfx
  * @enable: false - request reset , true - drop reset
  */
-void hns_dsaf_srst_chns(struct dsaf_device *dsaf_dev, u32 msk, bool dereset)
+static void
+hns_dsaf_srst_chns(struct dsaf_device *dsaf_dev, u32 msk, bool dereset)
 {
 	u32 reg_addr;
 
@@ -362,7 +363,7 @@ void hns_dsaf_srst_chns(struct dsaf_device *dsaf_dev, u32 msk, bool dereset)
  * bit18-19 for com/dfx
  * @enable: false - request reset , true - drop reset
  */
-void
+static void
 hns_dsaf_srst_chns_acpi(struct dsaf_device *dsaf_dev, u32 msk, bool dereset)
 {
 	hns_dsaf_acpi_srst_by_port(dsaf_dev, HNS_OP_RESET_FUNC,
@@ -370,7 +371,7 @@ hns_dsaf_srst_chns_acpi(struct dsaf_device *dsaf_dev, u32 msk, bool dereset)
 				   msk, dereset);
 }
 
-void hns_dsaf_roce_srst(struct dsaf_device *dsaf_dev, bool dereset)
+static void hns_dsaf_roce_srst(struct dsaf_device *dsaf_dev, bool dereset)
 {
 	if (!dereset) {
 		dsaf_write_sub(dsaf_dev, DSAF_SUB_SC_ROCEE_RESET_REQ_REG, 1);
@@ -384,7 +385,7 @@ void hns_dsaf_roce_srst(struct dsaf_device *dsaf_dev, bool dereset)
 	}
 }
 
-void hns_dsaf_roce_srst_acpi(struct dsaf_device *dsaf_dev, bool dereset)
+static void hns_dsaf_roce_srst_acpi(struct dsaf_device *dsaf_dev, bool dereset)
 {
 	hns_dsaf_acpi_srst_by_port(dsaf_dev, HNS_OP_RESET_FUNC,
 				   HNS_ROCE_RESET_FUNC, 0, dereset);
@@ -568,7 +569,7 @@ static phy_interface_t hns_mac_get_phy_if_acpi(struct hns_mac_cb *mac_cb)
 	return phy_if;
 }
 
-int hns_mac_get_sfp_prsnt(struct hns_mac_cb *mac_cb, int *sfp_prsnt)
+static int hns_mac_get_sfp_prsnt(struct hns_mac_cb *mac_cb, int *sfp_prsnt)
 {
 	u32 val = 0;
 	int ret;
@@ -586,7 +587,7 @@ int hns_mac_get_sfp_prsnt(struct hns_mac_cb *mac_cb, int *sfp_prsnt)
 	return 0;
 }
 
-int hns_mac_get_sfp_prsnt_acpi(struct hns_mac_cb *mac_cb, int *sfp_prsnt)
+static int hns_mac_get_sfp_prsnt_acpi(struct hns_mac_cb *mac_cb, int *sfp_prsnt)
 {
 	union acpi_object *obj;
 	union acpi_object obj_args, argv4;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
index 93e71e27401b..d160d8c9e45b 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
@@ -73,7 +73,7 @@ hns_ppe_common_get_ioaddr(struct ppe_common_cb *ppe_common)
  * comm_index: common index
  * retuen 0 - success , negative --fail
  */
-int hns_ppe_common_get_cfg(struct dsaf_device *dsaf_dev, int comm_index)
+static int hns_ppe_common_get_cfg(struct dsaf_device *dsaf_dev, int comm_index)
 {
 	struct ppe_common_cb *ppe_common;
 	int ppe_num;
@@ -104,7 +104,8 @@ int hns_ppe_common_get_cfg(struct dsaf_device *dsaf_dev, int comm_index)
 	return 0;
 }
 
-void hns_ppe_common_free_cfg(struct dsaf_device *dsaf_dev, u32 comm_index)
+static void
+hns_ppe_common_free_cfg(struct dsaf_device *dsaf_dev, u32 comm_index)
 {
 	dsaf_dev->ppe_common[comm_index] = NULL;
 }
@@ -203,9 +204,9 @@ static int hns_ppe_common_init_hw(struct ppe_common_cb *ppe_common)
 	enum dsaf_mode dsaf_mode = dsaf_dev->dsaf_mode;
 
 	dsaf_dev->misc_op->ppe_comm_srst(dsaf_dev, 0);
-	mdelay(100);
+	msleep(100);
 	dsaf_dev->misc_op->ppe_comm_srst(dsaf_dev, 1);
-	mdelay(100);
+	msleep(100);
 
 	if (ppe_common->ppe_mode == PPE_COMMON_MODE_SERVICE) {
 		switch (dsaf_mode) {
@@ -337,7 +338,7 @@ static void hns_ppe_uninit_hw(struct hns_ppe_cb *ppe_cb)
 	}
 }
 
-void hns_ppe_uninit_ex(struct ppe_common_cb *ppe_common)
+static void hns_ppe_uninit_ex(struct ppe_common_cb *ppe_common)
 {
 	u32 i;
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
index e2e28532e4dc..9d76e2e54f9d 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
@@ -705,7 +705,7 @@ void hns_rcb_get_queue_mode(enum dsaf_mode dsaf_mode, u16 *max_vfn,
 	}
 }
 
-int hns_rcb_get_ring_num(struct dsaf_device *dsaf_dev)
+static int hns_rcb_get_ring_num(struct dsaf_device *dsaf_dev)
 {
 	switch (dsaf_dev->dsaf_mode) {
 	case DSAF_MODE_ENABLE_FIX:
@@ -741,7 +741,7 @@ int hns_rcb_get_ring_num(struct dsaf_device *dsaf_dev)
 	}
 }
 
-void __iomem *hns_rcb_common_get_vaddr(struct rcb_common_cb *rcb_common)
+static void __iomem *hns_rcb_common_get_vaddr(struct rcb_common_cb *rcb_common)
 {
 	struct dsaf_device *dsaf_dev = rcb_common->dsaf_dev;
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
index 51e7e9f5af49..ba4316910dea 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
@@ -215,10 +215,10 @@ static void hns_xgmac_init(void *mac_drv)
 	u32 port = drv->mac_id;
 
 	dsaf_dev->misc_op->xge_srst(dsaf_dev, port, 0);
-	mdelay(100);
+	msleep(100);
 	dsaf_dev->misc_op->xge_srst(dsaf_dev, port, 1);
 
-	mdelay(100);
+	msleep(100);
 	hns_xgmac_lf_rf_control_init(drv);
 	hns_xgmac_exc_irq_en(drv, 0);
 
@@ -311,7 +311,7 @@ static void hns_xgmac_config_max_frame_length(void *mac_drv, u16 newval)
 	dsaf_write_dev(drv, XGMAC_MAC_MAX_PKT_SIZE_REG, newval);
 }
 
-void hns_xgmac_update_stats(void *mac_drv)
+static void hns_xgmac_update_stats(void *mac_drv)
 {
 	struct mac_driver *drv = (struct mac_driver *)mac_drv;
 	struct mac_hw_stats *hw_stats = &drv->mac_cb->hw_stats;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index ef9ef703d13a..9f2b552aee33 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -1300,7 +1300,7 @@ static int hns_nic_net_set_mac_address(struct net_device *ndev, void *p)
 	return 0;
 }
 
-void hns_nic_update_stats(struct net_device *netdev)
+static void hns_nic_update_stats(struct net_device *netdev)
 {
 	struct hns_nic_priv *priv = netdev_priv(netdev);
 	struct hnae_handle *h = priv->ae_handle;
@@ -1582,7 +1582,7 @@ static int hns_nic_do_ioctl(struct net_device *netdev, struct ifreq *ifr,
 
 /* use only for netconsole to poll with the device without interrupt */
 #ifdef CONFIG_NET_POLL_CONTROLLER
-void hns_nic_poll_controller(struct net_device *ndev)
+static void hns_nic_poll_controller(struct net_device *ndev)
 {
 	struct hns_nic_priv *priv = netdev_priv(ndev);
 	unsigned long flags;
@@ -1935,7 +1935,7 @@ static int hns_nic_uc_unsync(struct net_device *netdev,
  *
  * return void
  */
-void hns_set_multicast_list(struct net_device *ndev)
+static void hns_set_multicast_list(struct net_device *ndev)
 {
 	struct hns_nic_priv *priv = netdev_priv(ndev);
 	struct hnae_handle *h = priv->ae_handle;
@@ -1957,7 +1957,7 @@ void hns_set_multicast_list(struct net_device *ndev)
 	}
 }
 
-void hns_nic_set_rx_mode(struct net_device *ndev)
+static void hns_nic_set_rx_mode(struct net_device *ndev)
 {
 	struct hns_nic_priv *priv = netdev_priv(ndev);
 	struct hnae_handle *h = priv->ae_handle;
@@ -2022,7 +2022,8 @@ static void hns_nic_get_stats64(struct net_device *ndev,
 
 static u16
 hns_nic_select_queue(struct net_device *ndev, struct sk_buff *skb,
-		     void *accel_priv, select_queue_fallback_t fallback)
+		     struct net_device *sb_dev,
+		     select_queue_fallback_t fallback)
 {
 	struct ethhdr *eth_hdr = (struct ethhdr *)skb->data;
 	struct hns_nic_priv *priv = netdev_priv(ndev);
@@ -2032,7 +2033,7 @@ hns_nic_select_queue(struct net_device *ndev, struct sk_buff *skb,
 	    is_multicast_ether_addr(eth_hdr->h_dest))
 		return 0;
 	else
-		return fallback(ndev, skb);
+		return fallback(ndev, skb, NULL);
 }
 
 static const struct net_device_ops hns_nic_netdev_ops = {
@@ -2377,7 +2378,7 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
 		}
 		priv->fwnode = &ae_node->fwnode;
 	} else if (is_acpi_node(dev->fwnode)) {
-		struct acpi_reference_args args;
+		struct fwnode_reference_args args;
 
 		if (acpi_dev_found(hns_enet_acpi_match[0].id))
 			priv->enet_ver = AE_VERSION_1;
@@ -2393,7 +2394,11 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
 			dev_err(dev, "not find ae-handle\n");
 			goto out_read_prop_fail;
 		}
-		priv->fwnode = acpi_fwnode_handle(args.adev);
+		if (!is_acpi_device_node(args.fwnode)) {
+			ret = -EINVAL;
+			goto out_read_prop_fail;
+		}
+		priv->fwnode = args.fwnode;
 	} else {
 		dev_err(dev, "cannot read cfg data from OF or acpi\n");
 		return -ENXIO;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 2e14a3ae1d8b..08f3c4743f74 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -307,6 +307,7 @@ static int __lb_setup(struct net_device *ndev,
 		break;
 	case MAC_LOOP_PHY_NONE:
 		ret = hns_nic_config_phy_loopback(phy_dev, 0x0);
+		/* fall through */
 	case MAC_LOOP_NONE:
 		if (!ret && h->dev->ops->set_loopback) {
 			if (priv->ae_handle->phy_if != PHY_INTERFACE_MODE_XGMII)
@@ -658,8 +659,8 @@ static void hns_nic_get_drvinfo(struct net_device *net_dev,
  * @dev: net device
  * @param: ethtool parameter
  */
-void hns_get_ringparam(struct net_device *net_dev,
-		       struct ethtool_ringparam *param)
+static void hns_get_ringparam(struct net_device *net_dev,
+			      struct ethtool_ringparam *param)
 {
 	struct hns_nic_priv *priv = netdev_priv(net_dev);
 	struct hnae_ae_ops *ops;
@@ -808,7 +809,8 @@ static int hns_set_coalesce(struct net_device *net_dev,
  * @dev: net device
  * @ch: channel info.
  */
-void hns_get_channels(struct net_device *net_dev, struct ethtool_channels *ch)
+static void
+hns_get_channels(struct net_device *net_dev, struct ethtool_channels *ch)
 {
 	struct hns_nic_priv *priv = netdev_priv(net_dev);
 
@@ -825,8 +827,8 @@ void hns_get_channels(struct net_device *net_dev, struct ethtool_channels *ch)
  * @stats: statistics info.
  * @data: statistics data.
  */
-void hns_get_ethtool_stats(struct net_device *netdev,
-			   struct ethtool_stats *stats, u64 *data)
+static void hns_get_ethtool_stats(struct net_device *netdev,
+				  struct ethtool_stats *stats, u64 *data)
 {
 	u64 *p = data;
 	struct hns_nic_priv *priv = netdev_priv(netdev);
@@ -883,7 +885,7 @@ void hns_get_ethtool_stats(struct net_device *netdev,
  * @stats: string set ID.
  * @data: objects data.
  */
-void hns_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
+static void hns_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 {
 	struct hns_nic_priv *priv = netdev_priv(netdev);
 	struct hnae_handle *h = priv->ae_handle;
@@ -973,7 +975,7 @@ void hns_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
  *
  * Return string set count.
  */
-int hns_get_sset_count(struct net_device *netdev, int stringset)
+static int hns_get_sset_count(struct net_device *netdev, int stringset)
 {
 	struct hns_nic_priv *priv = netdev_priv(netdev);
 	struct hnae_handle *h = priv->ae_handle;
@@ -1007,7 +1009,7 @@ int hns_get_sset_count(struct net_device *netdev, int stringset)
  *
  * Return 0 on success, negative on failure.
  */
-int hns_phy_led_set(struct net_device *netdev, int value)
+static int hns_phy_led_set(struct net_device *netdev, int value)
 {
 	int retval;
 	struct phy_device *phy_dev = netdev->phydev;
@@ -1029,7 +1031,8 @@ int hns_phy_led_set(struct net_device *netdev, int value)
  *
  * Return 0 on success, negative on failure.
  */
-int hns_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state)
+static int
+hns_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state)
 {
 	struct hns_nic_priv *priv = netdev_priv(netdev);
 	struct hnae_handle *h = priv->ae_handle;
@@ -1103,8 +1106,8 @@ int hns_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state)
  * @cmd: ethtool cmd
  * @date: register data
  */
-void hns_get_regs(struct net_device *net_dev, struct ethtool_regs *cmd,
-		  void *data)
+static void hns_get_regs(struct net_device *net_dev, struct ethtool_regs *cmd,
+			 void *data)
 {
 	struct hns_nic_priv *priv = netdev_priv(net_dev);
 	struct hnae_ae_ops *ops;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
index 9d79dad2c6aa..fff5be8078ac 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
@@ -1,14 +1,7 @@
-/*
- * Copyright (c) 2016-2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include <linux/list.h>
-#include <linux/slab.h>
 #include <linux/spinlock.h>
 
 #include "hnae3.h"
@@ -41,13 +34,13 @@ static void hnae3_set_client_init_flag(struct hnae3_client *client,
 {
 	switch (client->type) {
 	case HNAE3_CLIENT_KNIC:
-		hnae_set_bit(ae_dev->flag, HNAE3_KNIC_CLIENT_INITED_B, inited);
+		hnae3_set_bit(ae_dev->flag, HNAE3_KNIC_CLIENT_INITED_B, inited);
 		break;
 	case HNAE3_CLIENT_UNIC:
-		hnae_set_bit(ae_dev->flag, HNAE3_UNIC_CLIENT_INITED_B, inited);
+		hnae3_set_bit(ae_dev->flag, HNAE3_UNIC_CLIENT_INITED_B, inited);
 		break;
 	case HNAE3_CLIENT_ROCE:
-		hnae_set_bit(ae_dev->flag, HNAE3_ROCE_CLIENT_INITED_B, inited);
+		hnae3_set_bit(ae_dev->flag, HNAE3_ROCE_CLIENT_INITED_B, inited);
 		break;
 	default:
 		break;
@@ -61,16 +54,16 @@ static int hnae3_get_client_init_flag(struct hnae3_client *client,
 
 	switch (client->type) {
 	case HNAE3_CLIENT_KNIC:
-		inited = hnae_get_bit(ae_dev->flag,
+		inited = hnae3_get_bit(ae_dev->flag,
 				       HNAE3_KNIC_CLIENT_INITED_B);
 		break;
 	case HNAE3_CLIENT_UNIC:
-		inited = hnae_get_bit(ae_dev->flag,
+		inited = hnae3_get_bit(ae_dev->flag,
 				       HNAE3_UNIC_CLIENT_INITED_B);
 		break;
 	case HNAE3_CLIENT_ROCE:
-		inited = hnae_get_bit(ae_dev->flag,
-				      HNAE3_ROCE_CLIENT_INITED_B);
+		inited = hnae3_get_bit(ae_dev->flag,
+				       HNAE3_ROCE_CLIENT_INITED_B);
 		break;
 	default:
 		break;
@@ -86,7 +79,7 @@ static int hnae3_match_n_instantiate(struct hnae3_client *client,
 
 	/* check if this client matches the type of ae_dev */
 	if (!(hnae3_client_match(client->type, ae_dev->dev_type) &&
-	      hnae_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))) {
+	      hnae3_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))) {
 		return 0;
 	}
 
@@ -95,7 +88,7 @@ static int hnae3_match_n_instantiate(struct hnae3_client *client,
 		ret = ae_dev->ops->init_client_instance(client, ae_dev);
 		if (ret) {
 			dev_err(&ae_dev->pdev->dev,
-				"fail to instantiate client\n");
+				"fail to instantiate client, ret = %d\n", ret);
 			return ret;
 		}
 
@@ -135,7 +128,8 @@ int hnae3_register_client(struct hnae3_client *client)
 		ret = hnae3_match_n_instantiate(client, ae_dev, true);
 		if (ret)
 			dev_err(&ae_dev->pdev->dev,
-				"match and instantiation failed for port\n");
+				"match and instantiation failed for port, ret = %d\n",
+				ret);
 	}
 
 exit:
@@ -185,11 +179,12 @@ void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo)
 		ae_dev->ops = ae_algo->ops;
 		ret = ae_algo->ops->init_ae_dev(ae_dev);
 		if (ret) {
-			dev_err(&ae_dev->pdev->dev, "init ae_dev error.\n");
+			dev_err(&ae_dev->pdev->dev,
+				"init ae_dev error, ret = %d\n", ret);
 			continue;
 		}
 
-		hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1);
+		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1);
 
 		/* check the client list for the match with this ae_dev type and
 		 * initialize the figure out client instance
@@ -198,7 +193,8 @@ void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo)
 			ret = hnae3_match_n_instantiate(client, ae_dev, true);
 			if (ret)
 				dev_err(&ae_dev->pdev->dev,
-					"match and instantiation failed\n");
+					"match and instantiation failed, ret = %d\n",
+					ret);
 		}
 	}
 
@@ -218,7 +214,7 @@ void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo)
 	mutex_lock(&hnae3_common_lock);
 	/* Check if there are matched ae_dev */
 	list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) {
-		if (!hnae_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))
+		if (!hnae3_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))
 			continue;
 
 		id = pci_match_id(ae_algo->pdev_id_table, ae_dev->pdev);
@@ -232,7 +228,7 @@ void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo)
 			hnae3_match_n_instantiate(client, ae_dev, false);
 
 		ae_algo->ops->uninit_ae_dev(ae_dev);
-		hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
+		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
 	}
 
 	list_del(&ae_algo->node);
@@ -271,11 +267,12 @@ void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev)
 		/* ae_dev init should set flag */
 		ret = ae_dev->ops->init_ae_dev(ae_dev);
 		if (ret) {
-			dev_err(&ae_dev->pdev->dev, "init ae_dev error\n");
+			dev_err(&ae_dev->pdev->dev,
+				"init ae_dev error, ret = %d\n", ret);
 			goto out_err;
 		}
 
-		hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1);
+		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1);
 		break;
 	}
 
@@ -286,7 +283,8 @@ void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev)
 		ret = hnae3_match_n_instantiate(client, ae_dev, true);
 		if (ret)
 			dev_err(&ae_dev->pdev->dev,
-				"match and instantiation failed\n");
+				"match and instantiation failed, ret = %d\n",
+				ret);
 	}
 
 out_err:
@@ -306,7 +304,7 @@ void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev)
 	mutex_lock(&hnae3_common_lock);
 	/* Check if there are matched ae_algo */
 	list_for_each_entry(ae_algo, &hnae3_ae_algo_list, node) {
-		if (!hnae_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))
+		if (!hnae3_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))
 			continue;
 
 		id = pci_match_id(ae_algo->pdev_id_table, ae_dev->pdev);
@@ -317,7 +315,7 @@ void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev)
 			hnae3_match_n_instantiate(client, ae_dev, false);
 
 		ae_algo->ops->uninit_ae_dev(ae_dev);
-		hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
+		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
 	}
 
 	list_del(&ae_dev->node);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 8acb1d116a02..67befff0bfc5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016-2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HNAE3_H
 #define __HNAE3_H
@@ -62,10 +56,10 @@
 		BIT(HNAE3_DEV_SUPPORT_ROCE_B))
 
 #define hnae3_dev_roce_supported(hdev) \
-	hnae_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)
+	hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)
 
 #define hnae3_dev_dcb_supported(hdev) \
-	hnae_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B)
+	hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B)
 
 #define ring_ptr_move_fw(ring, p) \
 	((ring)->p = ((ring)->p + 1) % (ring)->desc_num)
@@ -167,7 +161,6 @@ struct hnae3_client_ops {
 #define HNAE3_CLIENT_NAME_LENGTH 16
 struct hnae3_client {
 	char name[HNAE3_CLIENT_NAME_LENGTH];
-	u16 version;
 	unsigned long state;
 	enum hnae3_client_type type;
 	const struct hnae3_client_ops *ops;
@@ -436,7 +429,6 @@ struct hnae3_dcb_ops {
 struct hnae3_ae_algo {
 	const struct hnae3_ae_ops *ops;
 	struct list_head node;
-	char name[HNAE3_CLASS_NAME_SIZE];
 	const struct pci_device_id *pdev_id_table;
 };
 
@@ -509,17 +501,17 @@ struct hnae3_handle {
 	u32 numa_node_mask;	/* for multi-chip support */
 };
 
-#define hnae_set_field(origin, mask, shift, val) \
+#define hnae3_set_field(origin, mask, shift, val) \
 	do { \
 		(origin) &= (~(mask)); \
 		(origin) |= ((val) << (shift)) & (mask); \
 	} while (0)
-#define hnae_get_field(origin, mask, shift) (((origin) & (mask)) >> (shift))
+#define hnae3_get_field(origin, mask, shift) (((origin) & (mask)) >> (shift))
 
-#define hnae_set_bit(origin, shift, val) \
-	hnae_set_field((origin), (0x1 << (shift)), (shift), (val))
-#define hnae_get_bit(origin, shift) \
-	hnae_get_field((origin), (0x1 << (shift)), (shift))
+#define hnae3_set_bit(origin, shift, val) \
+	hnae3_set_field((origin), (0x1 << (shift)), (shift), (val))
+#define hnae3_get_bit(origin, shift) \
+	hnae3_get_field((origin), (0x1 << (shift)), (shift))
 
 void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev);
 void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c b/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c
index eb82700da7d0..ea5f8a84070d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016-2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include "hnae3.h"
 #include "hns3_enet.h"
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 25a73bb2e642..3554dca7a680 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016~2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include <linux/dma-mapping.h>
 #include <linux/etherdevice.h>
@@ -56,15 +50,16 @@ static const struct pci_device_id hns3_pci_tbl[] = {
 	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC),
 	 HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
 	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_VF), 0},
-	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_DCB_PFC_VF), 0},
+	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_DCB_PFC_VF),
+	 HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
 	/* required last entry */
 	{0, }
 };
 MODULE_DEVICE_TABLE(pci, hns3_pci_tbl);
 
-static irqreturn_t hns3_irq_handle(int irq, void *dev)
+static irqreturn_t hns3_irq_handle(int irq, void *vector)
 {
-	struct hns3_enet_tqp_vector *tqp_vector = dev;
+	struct hns3_enet_tqp_vector *tqp_vector = vector;
 
 	napi_schedule(&tqp_vector->napi);
 
@@ -239,7 +234,28 @@ static int hns3_nic_set_real_num_queue(struct net_device *netdev)
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 	struct hnae3_knic_private_info *kinfo = &h->kinfo;
 	unsigned int queue_size = kinfo->rss_size * kinfo->num_tc;
-	int ret;
+	int i, ret;
+
+	if (kinfo->num_tc <= 1) {
+		netdev_reset_tc(netdev);
+	} else {
+		ret = netdev_set_num_tc(netdev, kinfo->num_tc);
+		if (ret) {
+			netdev_err(netdev,
+				   "netdev_set_num_tc fail, ret=%d!\n", ret);
+			return ret;
+		}
+
+		for (i = 0; i < HNAE3_MAX_TC; i++) {
+			if (!kinfo->tc_info[i].enable)
+				continue;
+
+			netdev_set_tc_queue(netdev,
+					    kinfo->tc_info[i].tc,
+					    kinfo->tc_info[i].tqp_count,
+					    kinfo->tc_info[i].tqp_offset);
+		}
+	}
 
 	ret = netif_set_real_num_tx_queues(netdev, queue_size);
 	if (ret) {
@@ -312,7 +328,9 @@ out_start_err:
 static int hns3_nic_net_open(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	int ret;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+	struct hnae3_knic_private_info *kinfo;
+	int i, ret;
 
 	netif_carrier_off(netdev);
 
@@ -327,6 +345,12 @@ static int hns3_nic_net_open(struct net_device *netdev)
 		return ret;
 	}
 
+	kinfo = &h->kinfo;
+	for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
+		netdev_set_prio_tc_map(netdev, i,
+				       kinfo->prio_tc[i]);
+	}
+
 	priv->ae_handle->last_reset_time = jiffies;
 	return 0;
 }
@@ -493,8 +517,8 @@ static int hns3_set_tso(struct sk_buff *skb, u32 *paylen,
 
 	/* find the txbd field values */
 	*paylen = skb->len - hdr_len;
-	hnae_set_bit(*type_cs_vlan_tso,
-		     HNS3_TXD_TSO_B, 1);
+	hnae3_set_bit(*type_cs_vlan_tso,
+		      HNS3_TXD_TSO_B, 1);
 
 	/* get MSS for TSO */
 	*mss = skb_shinfo(skb)->gso_size;
@@ -586,21 +610,21 @@ static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto,
 
 	/* compute L2 header size for normal packet, defined in 2 Bytes */
 	l2_len = l3.hdr - skb->data;
-	hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M,
-		       HNS3_TXD_L2LEN_S, l2_len >> 1);
+	hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M,
+			HNS3_TXD_L2LEN_S, l2_len >> 1);
 
 	/* tunnel packet*/
 	if (skb->encapsulation) {
 		/* compute OL2 header size, defined in 2 Bytes */
 		ol2_len = l2_len;
-		hnae_set_field(*ol_type_vlan_len_msec,
-			       HNS3_TXD_L2LEN_M,
-			       HNS3_TXD_L2LEN_S, ol2_len >> 1);
+		hnae3_set_field(*ol_type_vlan_len_msec,
+				HNS3_TXD_L2LEN_M,
+				HNS3_TXD_L2LEN_S, ol2_len >> 1);
 
 		/* compute OL3 header size, defined in 4 Bytes */
 		ol3_len = l4.hdr - l3.hdr;
-		hnae_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L3LEN_M,
-			       HNS3_TXD_L3LEN_S, ol3_len >> 2);
+		hnae3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L3LEN_M,
+				HNS3_TXD_L3LEN_S, ol3_len >> 2);
 
 		/* MAC in UDP, MAC in GRE (0x6558)*/
 		if ((ol4_proto == IPPROTO_UDP) || (ol4_proto == IPPROTO_GRE)) {
@@ -609,16 +633,17 @@ static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto,
 
 			/* compute OL4 header size, defined in 4 Bytes. */
 			ol4_len = l2_hdr - l4.hdr;
-			hnae_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L4LEN_M,
-				       HNS3_TXD_L4LEN_S, ol4_len >> 2);
+			hnae3_set_field(*ol_type_vlan_len_msec,
+					HNS3_TXD_L4LEN_M, HNS3_TXD_L4LEN_S,
+					ol4_len >> 2);
 
 			/* switch IP header ptr from outer to inner header */
 			l3.hdr = skb_inner_network_header(skb);
 
 			/* compute inner l2 header size, defined in 2 Bytes. */
 			l2_len = l3.hdr - l2_hdr;
-			hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M,
-				       HNS3_TXD_L2LEN_S, l2_len >> 1);
+			hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M,
+					HNS3_TXD_L2LEN_S, l2_len >> 1);
 		} else {
 			/* skb packet types not supported by hardware,
 			 * txbd len fild doesn't be filled.
@@ -634,22 +659,24 @@ static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto,
 
 	/* compute inner(/normal) L3 header size, defined in 4 Bytes */
 	l3_len = l4.hdr - l3.hdr;
-	hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L3LEN_M,
-		       HNS3_TXD_L3LEN_S, l3_len >> 2);
+	hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3LEN_M,
+			HNS3_TXD_L3LEN_S, l3_len >> 2);
 
 	/* compute inner(/normal) L4 header size, defined in 4 Bytes */
 	switch (l4_proto) {
 	case IPPROTO_TCP:
-		hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
-			       HNS3_TXD_L4LEN_S, l4.tcp->doff);
+		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
+				HNS3_TXD_L4LEN_S, l4.tcp->doff);
 		break;
 	case IPPROTO_SCTP:
-		hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
-			       HNS3_TXD_L4LEN_S, (sizeof(struct sctphdr) >> 2));
+		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
+				HNS3_TXD_L4LEN_S,
+				(sizeof(struct sctphdr) >> 2));
 		break;
 	case IPPROTO_UDP:
-		hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
-			       HNS3_TXD_L4LEN_S, (sizeof(struct udphdr) >> 2));
+		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
+				HNS3_TXD_L4LEN_S,
+				(sizeof(struct udphdr) >> 2));
 		break;
 	default:
 		/* skb packet types not supported by hardware,
@@ -703,32 +730,34 @@ static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto,
 		/* define outer network header type.*/
 		if (skb->protocol == htons(ETH_P_IP)) {
 			if (skb_is_gso(skb))
-				hnae_set_field(*ol_type_vlan_len_msec,
-					       HNS3_TXD_OL3T_M, HNS3_TXD_OL3T_S,
-					       HNS3_OL3T_IPV4_CSUM);
+				hnae3_set_field(*ol_type_vlan_len_msec,
+						HNS3_TXD_OL3T_M,
+						HNS3_TXD_OL3T_S,
+						HNS3_OL3T_IPV4_CSUM);
 			else
-				hnae_set_field(*ol_type_vlan_len_msec,
-					       HNS3_TXD_OL3T_M, HNS3_TXD_OL3T_S,
-					       HNS3_OL3T_IPV4_NO_CSUM);
+				hnae3_set_field(*ol_type_vlan_len_msec,
+						HNS3_TXD_OL3T_M,
+						HNS3_TXD_OL3T_S,
+						HNS3_OL3T_IPV4_NO_CSUM);
 
 		} else if (skb->protocol == htons(ETH_P_IPV6)) {
-			hnae_set_field(*ol_type_vlan_len_msec, HNS3_TXD_OL3T_M,
-				       HNS3_TXD_OL3T_S, HNS3_OL3T_IPV6);
+			hnae3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_OL3T_M,
+					HNS3_TXD_OL3T_S, HNS3_OL3T_IPV6);
 		}
 
 		/* define tunnel type(OL4).*/
 		switch (l4_proto) {
 		case IPPROTO_UDP:
-			hnae_set_field(*ol_type_vlan_len_msec,
-				       HNS3_TXD_TUNTYPE_M,
-				       HNS3_TXD_TUNTYPE_S,
-				       HNS3_TUN_MAC_IN_UDP);
+			hnae3_set_field(*ol_type_vlan_len_msec,
+					HNS3_TXD_TUNTYPE_M,
+					HNS3_TXD_TUNTYPE_S,
+					HNS3_TUN_MAC_IN_UDP);
 			break;
 		case IPPROTO_GRE:
-			hnae_set_field(*ol_type_vlan_len_msec,
-				       HNS3_TXD_TUNTYPE_M,
-				       HNS3_TXD_TUNTYPE_S,
-				       HNS3_TUN_NVGRE);
+			hnae3_set_field(*ol_type_vlan_len_msec,
+					HNS3_TXD_TUNTYPE_M,
+					HNS3_TXD_TUNTYPE_S,
+					HNS3_TUN_NVGRE);
 			break;
 		default:
 			/* drop the skb tunnel packet if hardware don't support,
@@ -749,43 +778,43 @@ static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto,
 	}
 
 	if (l3.v4->version == 4) {
-		hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M,
-			       HNS3_TXD_L3T_S, HNS3_L3T_IPV4);
+		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M,
+				HNS3_TXD_L3T_S, HNS3_L3T_IPV4);
 
 		/* the stack computes the IP header already, the only time we
 		 * need the hardware to recompute it is in the case of TSO.
 		 */
 		if (skb_is_gso(skb))
-			hnae_set_bit(*type_cs_vlan_tso, HNS3_TXD_L3CS_B, 1);
-
-		hnae_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
+			hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L3CS_B, 1);
 	} else if (l3.v6->version == 6) {
-		hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M,
-			       HNS3_TXD_L3T_S, HNS3_L3T_IPV6);
-		hnae_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
+		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M,
+				HNS3_TXD_L3T_S, HNS3_L3T_IPV6);
 	}
 
 	switch (l4_proto) {
 	case IPPROTO_TCP:
-		hnae_set_field(*type_cs_vlan_tso,
-			       HNS3_TXD_L4T_M,
-			       HNS3_TXD_L4T_S,
-			       HNS3_L4T_TCP);
+		hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
+		hnae3_set_field(*type_cs_vlan_tso,
+				HNS3_TXD_L4T_M,
+				HNS3_TXD_L4T_S,
+				HNS3_L4T_TCP);
 		break;
 	case IPPROTO_UDP:
 		if (hns3_tunnel_csum_bug(skb))
 			break;
 
-		hnae_set_field(*type_cs_vlan_tso,
-			       HNS3_TXD_L4T_M,
-			       HNS3_TXD_L4T_S,
-			       HNS3_L4T_UDP);
+		hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
+		hnae3_set_field(*type_cs_vlan_tso,
+				HNS3_TXD_L4T_M,
+				HNS3_TXD_L4T_S,
+				HNS3_L4T_UDP);
 		break;
 	case IPPROTO_SCTP:
-		hnae_set_field(*type_cs_vlan_tso,
-			       HNS3_TXD_L4T_M,
-			       HNS3_TXD_L4T_S,
-			       HNS3_L4T_SCTP);
+		hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
+		hnae3_set_field(*type_cs_vlan_tso,
+				HNS3_TXD_L4T_M,
+				HNS3_TXD_L4T_S,
+				HNS3_L4T_SCTP);
 		break;
 	default:
 		/* drop the skb tunnel packet if hardware don't support,
@@ -807,11 +836,11 @@ static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto,
 static void hns3_set_txbd_baseinfo(u16 *bdtp_fe_sc_vld_ra_ri, int frag_end)
 {
 	/* Config bd buffer end */
-	hnae_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_BDTYPE_M,
-		       HNS3_TXD_BDTYPE_S, 0);
-	hnae_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_FE_B, !!frag_end);
-	hnae_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1);
-	hnae_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_SC_M, HNS3_TXD_SC_S, 0);
+	hnae3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_BDTYPE_M,
+			HNS3_TXD_BDTYPE_S, 0);
+	hnae3_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_FE_B, !!frag_end);
+	hnae3_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1);
+	hnae3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_SC_M, HNS3_TXD_SC_S, 0);
 }
 
 static int hns3_fill_desc_vtags(struct sk_buff *skb,
@@ -844,10 +873,10 @@ static int hns3_fill_desc_vtags(struct sk_buff *skb,
 		 * and use inner_vtag in one tag case.
 		 */
 		if (skb->protocol == htons(ETH_P_8021Q)) {
-			hnae_set_bit(*out_vlan_flag, HNS3_TXD_OVLAN_B, 1);
+			hnae3_set_bit(*out_vlan_flag, HNS3_TXD_OVLAN_B, 1);
 			*out_vtag = vlan_tag;
 		} else {
-			hnae_set_bit(*inner_vlan_flag, HNS3_TXD_VLAN_B, 1);
+			hnae3_set_bit(*inner_vlan_flag, HNS3_TXD_VLAN_B, 1);
 			*inner_vtag = vlan_tag;
 		}
 	} else if (skb->protocol == htons(ETH_P_8021Q)) {
@@ -880,7 +909,6 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 	u16 out_vtag = 0;
 	u32 paylen = 0;
 	u16 mss = 0;
-	__be16 protocol;
 	u8 ol4_proto;
 	u8 il4_proto;
 	int ret;
@@ -909,7 +937,6 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
 			skb_reset_mac_len(skb);
-			protocol = skb->protocol;
 
 			ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto);
 			if (ret)
@@ -1135,7 +1162,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	wmb(); /* Commit all data before submit */
 
-	hnae_queue_xmit(ring->tqp, buf_num);
+	hnae3_queue_xmit(ring->tqp, buf_num);
 
 	return NETDEV_TX_OK;
 
@@ -1304,7 +1331,6 @@ static int hns3_setup_tc(struct net_device *netdev, void *type_data)
 	u16 mode = mqprio_qopt->mode;
 	u8 hw = mqprio_qopt->qopt.hw;
 	bool if_running;
-	unsigned int i;
 	int ret;
 
 	if (!((hw == TC_MQPRIO_HW_OFFLOAD_TCS &&
@@ -1328,24 +1354,6 @@ static int hns3_setup_tc(struct net_device *netdev, void *type_data)
 	if (ret)
 		goto out;
 
-	if (tc <= 1) {
-		netdev_reset_tc(netdev);
-	} else {
-		ret = netdev_set_num_tc(netdev, tc);
-		if (ret)
-			goto out;
-
-		for (i = 0; i < HNAE3_MAX_TC; i++) {
-			if (!kinfo->tc_info[i].enable)
-				continue;
-
-			netdev_set_tc_queue(netdev,
-					    kinfo->tc_info[i].tc,
-					    kinfo->tc_info[i].tqp_count,
-					    kinfo->tc_info[i].tqp_offset);
-		}
-	}
-
 	ret = hns3_nic_set_real_num_queue(netdev);
 
 out:
@@ -1665,6 +1673,9 @@ static struct pci_driver hns3_driver = {
 /* set default feature to hns3 */
 static void hns3_set_default_feature(struct net_device *netdev)
 {
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+	struct pci_dev *pdev = h->pdev;
+
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 
 	netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
@@ -1698,12 +1709,15 @@ static void hns3_set_default_feature(struct net_device *netdev)
 		NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE |
 		NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL |
 		NETIF_F_GSO_UDP_TUNNEL_CSUM;
+
+	if (pdev->revision != 0x20)
+		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 }
 
 static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
 			     struct hns3_desc_cb *cb)
 {
-	unsigned int order = hnae_page_order(ring);
+	unsigned int order = hnae3_page_order(ring);
 	struct page *p;
 
 	p = dev_alloc_pages(order);
@@ -1714,7 +1728,7 @@ static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
 	cb->page_offset = 0;
 	cb->reuse_flag = 0;
 	cb->buf  = page_address(p);
-	cb->length = hnae_page_size(ring);
+	cb->length = hnae3_page_size(ring);
 	cb->type = DESC_TYPE_PAGE;
 
 	return 0;
@@ -1780,33 +1794,27 @@ static void hns3_free_buffers(struct hns3_enet_ring *ring)
 /* free desc along with its attached buffer */
 static void hns3_free_desc(struct hns3_enet_ring *ring)
 {
+	int size = ring->desc_num * sizeof(ring->desc[0]);
+
 	hns3_free_buffers(ring);
 
-	dma_unmap_single(ring_to_dev(ring), ring->desc_dma_addr,
-			 ring->desc_num * sizeof(ring->desc[0]),
-			 DMA_BIDIRECTIONAL);
-	ring->desc_dma_addr = 0;
-	kfree(ring->desc);
-	ring->desc = NULL;
+	if (ring->desc) {
+		dma_free_coherent(ring_to_dev(ring), size,
+				  ring->desc, ring->desc_dma_addr);
+		ring->desc = NULL;
+	}
 }
 
 static int hns3_alloc_desc(struct hns3_enet_ring *ring)
 {
 	int size = ring->desc_num * sizeof(ring->desc[0]);
 
-	ring->desc = kzalloc(size, GFP_KERNEL);
+	ring->desc = dma_zalloc_coherent(ring_to_dev(ring), size,
+					 &ring->desc_dma_addr,
+					 GFP_KERNEL);
 	if (!ring->desc)
 		return -ENOMEM;
 
-	ring->desc_dma_addr = dma_map_single(ring_to_dev(ring), ring->desc,
-					     size, DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(ring_to_dev(ring), ring->desc_dma_addr)) {
-		ring->desc_dma_addr = 0;
-		kfree(ring->desc);
-		ring->desc = NULL;
-		return -ENOMEM;
-	}
-
 	return 0;
 }
 
@@ -1887,7 +1895,7 @@ static void hns3_nic_reclaim_one_desc(struct hns3_enet_ring *ring, int *bytes,
 
 	(*pkts) += (desc_cb->type == DESC_TYPE_SKB);
 	(*bytes) += desc_cb->length;
-	/* desc_cb will be cleaned, after hnae_free_buffer_detach*/
+	/* desc_cb will be cleaned, after hnae3_free_buffer_detach*/
 	hns3_free_buffer_detach(ring, ring->next_to_clean);
 
 	ring_ptr_move_fw(ring, next_to_clean);
@@ -1917,7 +1925,7 @@ bool hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget)
 	if (is_ring_empty(ring) || head == ring->next_to_clean)
 		return true; /* no data to poll */
 
-	if (!is_valid_clean_head(ring, head)) {
+	if (unlikely(!is_valid_clean_head(ring, head))) {
 		netdev_err(netdev, "wrong head (%d, %d-%d)\n", head,
 			   ring->next_to_use, ring->next_to_clean);
 
@@ -2016,15 +2024,15 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
 	bool twobufs;
 
 	twobufs = ((PAGE_SIZE < 8192) &&
-		hnae_buf_size(ring) == HNS3_BUFFER_SIZE_2048);
+		hnae3_buf_size(ring) == HNS3_BUFFER_SIZE_2048);
 
 	desc = &ring->desc[ring->next_to_clean];
 	size = le16_to_cpu(desc->rx.size);
 
-	truesize = hnae_buf_size(ring);
+	truesize = hnae3_buf_size(ring);
 
 	if (!twobufs)
-		last_offset = hnae_page_size(ring) - hnae_buf_size(ring);
+		last_offset = hnae3_page_size(ring) - hnae3_buf_size(ring);
 
 	skb_add_rx_frag(skb, i, desc_cb->priv, desc_cb->page_offset + pull_len,
 			size - pull_len, truesize);
@@ -2076,13 +2084,13 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 		return;
 
 	/* check if hardware has done checksum */
-	if (!hnae_get_bit(bd_base_info, HNS3_RXD_L3L4P_B))
+	if (!hnae3_get_bit(bd_base_info, HNS3_RXD_L3L4P_B))
 		return;
 
-	if (unlikely(hnae_get_bit(l234info, HNS3_RXD_L3E_B) ||
-		     hnae_get_bit(l234info, HNS3_RXD_L4E_B) ||
-		     hnae_get_bit(l234info, HNS3_RXD_OL3E_B) ||
-		     hnae_get_bit(l234info, HNS3_RXD_OL4E_B))) {
+	if (unlikely(hnae3_get_bit(l234info, HNS3_RXD_L3E_B) ||
+		     hnae3_get_bit(l234info, HNS3_RXD_L4E_B) ||
+		     hnae3_get_bit(l234info, HNS3_RXD_OL3E_B) ||
+		     hnae3_get_bit(l234info, HNS3_RXD_OL4E_B))) {
 		netdev_err(netdev, "L3/L4 error pkt\n");
 		u64_stats_update_begin(&ring->syncp);
 		ring->stats.l3l4_csum_err++;
@@ -2091,23 +2099,25 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 		return;
 	}
 
-	l3_type = hnae_get_field(l234info, HNS3_RXD_L3ID_M,
-				 HNS3_RXD_L3ID_S);
-	l4_type = hnae_get_field(l234info, HNS3_RXD_L4ID_M,
-				 HNS3_RXD_L4ID_S);
+	l3_type = hnae3_get_field(l234info, HNS3_RXD_L3ID_M,
+				  HNS3_RXD_L3ID_S);
+	l4_type = hnae3_get_field(l234info, HNS3_RXD_L4ID_M,
+				  HNS3_RXD_L4ID_S);
 
-	ol4_type = hnae_get_field(l234info, HNS3_RXD_OL4ID_M, HNS3_RXD_OL4ID_S);
+	ol4_type = hnae3_get_field(l234info, HNS3_RXD_OL4ID_M,
+				   HNS3_RXD_OL4ID_S);
 	switch (ol4_type) {
 	case HNS3_OL4_TYPE_MAC_IN_UDP:
 	case HNS3_OL4_TYPE_NVGRE:
 		skb->csum_level = 1;
+		/* fall through */
 	case HNS3_OL4_TYPE_NO_TUN:
 		/* Can checksum ipv4 or ipv6 + UDP/TCP/SCTP packets */
-		if (l3_type == HNS3_L3_TYPE_IPV4 ||
-		    (l3_type == HNS3_L3_TYPE_IPV6 &&
-		     (l4_type == HNS3_L4_TYPE_UDP ||
-		      l4_type == HNS3_L4_TYPE_TCP ||
-		      l4_type == HNS3_L4_TYPE_SCTP)))
+		if ((l3_type == HNS3_L3_TYPE_IPV4 ||
+		     l3_type == HNS3_L3_TYPE_IPV6) &&
+		    (l4_type == HNS3_L4_TYPE_UDP ||
+		     l4_type == HNS3_L4_TYPE_TCP ||
+		     l4_type == HNS3_L4_TYPE_SCTP))
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 		break;
 	}
@@ -2135,8 +2145,8 @@ static u16 hns3_parse_vlan_tag(struct hns3_enet_ring *ring,
 #define HNS3_STRP_OUTER_VLAN	0x1
 #define HNS3_STRP_INNER_VLAN	0x2
 
-	switch (hnae_get_field(l234info, HNS3_RXD_STRP_TAGP_M,
-			       HNS3_RXD_STRP_TAGP_S)) {
+	switch (hnae3_get_field(l234info, HNS3_RXD_STRP_TAGP_M,
+				HNS3_RXD_STRP_TAGP_S)) {
 	case HNS3_STRP_OUTER_VLAN:
 		vlan_tag = le16_to_cpu(desc->rx.ot_vlan_tag);
 		break;
@@ -2174,7 +2184,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 	bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
 
 	/* Check valid BD */
-	if (!hnae_get_bit(bd_base_info, HNS3_RXD_VLD_B))
+	if (unlikely(!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B)))
 		return -EFAULT;
 
 	va = (unsigned char *)desc_cb->buf + desc_cb->page_offset;
@@ -2229,7 +2239,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 		hns3_nic_reuse_page(skb, 0, ring, pull_len, desc_cb);
 		ring_ptr_move_fw(ring, next_to_clean);
 
-		while (!hnae_get_bit(bd_base_info, HNS3_RXD_FE_B)) {
+		while (!hnae3_get_bit(bd_base_info, HNS3_RXD_FE_B)) {
 			desc = &ring->desc[ring->next_to_clean];
 			desc_cb = &ring->desc_cb[ring->next_to_clean];
 			bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
@@ -2257,7 +2267,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 					       vlan_tag);
 	}
 
-	if (unlikely(!hnae_get_bit(bd_base_info, HNS3_RXD_VLD_B))) {
+	if (unlikely(!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B))) {
 		netdev_err(netdev, "no valid bd,%016llx,%016llx\n",
 			   ((u64 *)desc)[0], ((u64 *)desc)[1]);
 		u64_stats_update_begin(&ring->syncp);
@@ -2269,7 +2279,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 	}
 
 	if (unlikely((!desc->rx.pkt_len) ||
-		     hnae_get_bit(l234info, HNS3_RXD_TRUNCAT_B))) {
+		     hnae3_get_bit(l234info, HNS3_RXD_TRUNCAT_B))) {
 		netdev_err(netdev, "truncated pkt\n");
 		u64_stats_update_begin(&ring->syncp);
 		ring->stats.err_pkt_len++;
@@ -2279,7 +2289,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 		return -EFAULT;
 	}
 
-	if (unlikely(hnae_get_bit(l234info, HNS3_RXD_L2E_B))) {
+	if (unlikely(hnae3_get_bit(l234info, HNS3_RXD_L2E_B))) {
 		netdev_err(netdev, "L2 error pkt\n");
 		u64_stats_update_begin(&ring->syncp);
 		ring->stats.l2_err++;
@@ -2532,10 +2542,10 @@ static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector,
 	tx_ring = tqp_vector->tx_group.ring;
 	if (tx_ring) {
 		cur_chain->tqp_index = tx_ring->tqp->tqp_index;
-		hnae_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B,
-			     HNAE3_RING_TYPE_TX);
-		hnae_set_field(cur_chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
-			       HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_TX);
+		hnae3_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B,
+			      HNAE3_RING_TYPE_TX);
+		hnae3_set_field(cur_chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
+				HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_TX);
 
 		cur_chain->next = NULL;
 
@@ -2549,12 +2559,12 @@ static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector,
 
 			cur_chain->next = chain;
 			chain->tqp_index = tx_ring->tqp->tqp_index;
-			hnae_set_bit(chain->flag, HNAE3_RING_TYPE_B,
-				     HNAE3_RING_TYPE_TX);
-			hnae_set_field(chain->int_gl_idx,
-				       HNAE3_RING_GL_IDX_M,
-				       HNAE3_RING_GL_IDX_S,
-				       HNAE3_RING_GL_TX);
+			hnae3_set_bit(chain->flag, HNAE3_RING_TYPE_B,
+				      HNAE3_RING_TYPE_TX);
+			hnae3_set_field(chain->int_gl_idx,
+					HNAE3_RING_GL_IDX_M,
+					HNAE3_RING_GL_IDX_S,
+					HNAE3_RING_GL_TX);
 
 			cur_chain = chain;
 		}
@@ -2564,10 +2574,10 @@ static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector,
 	if (!tx_ring && rx_ring) {
 		cur_chain->next = NULL;
 		cur_chain->tqp_index = rx_ring->tqp->tqp_index;
-		hnae_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B,
-			     HNAE3_RING_TYPE_RX);
-		hnae_set_field(cur_chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
-			       HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_RX);
+		hnae3_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B,
+			      HNAE3_RING_TYPE_RX);
+		hnae3_set_field(cur_chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
+				HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_RX);
 
 		rx_ring = rx_ring->next;
 	}
@@ -2579,10 +2589,10 @@ static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector,
 
 		cur_chain->next = chain;
 		chain->tqp_index = rx_ring->tqp->tqp_index;
-		hnae_set_bit(chain->flag, HNAE3_RING_TYPE_B,
-			     HNAE3_RING_TYPE_RX);
-		hnae_set_field(chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
-			       HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_RX);
+		hnae3_set_bit(chain->flag, HNAE3_RING_TYPE_B,
+			      HNAE3_RING_TYPE_RX);
+		hnae3_set_field(chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
+				HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_RX);
 
 		cur_chain = chain;
 
@@ -2745,10 +2755,6 @@ static int hns3_nic_uninit_vector_data(struct hns3_nic_priv *priv)
 		if (ret)
 			return ret;
 
-		ret = h->ae_algo->ops->put_vector(h, tqp_vector->vector_irq);
-		if (ret)
-			return ret;
-
 		hns3_free_vector_ring_chain(tqp_vector, &vector_ring_chain);
 
 		if (priv->tqp_vector[i].irq_init_flag == HNS3_VECTOR_INITED) {
@@ -2809,7 +2815,7 @@ static int hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv,
 		ring->io_base = q->io_base;
 	}
 
-	hnae_set_bit(ring->flag, HNAE3_RING_TYPE_B, ring_type);
+	hnae3_set_bit(ring->flag, HNAE3_RING_TYPE_B, ring_type);
 
 	ring->tqp = q;
 	ring->desc = NULL;
@@ -2969,13 +2975,33 @@ static void hns3_init_ring_hw(struct hns3_enet_ring *ring)
 		hns3_write_dev(q, HNS3_RING_TX_RING_BASEADDR_H_REG,
 			       (u32)((dma >> 31) >> 1));
 
-		hns3_write_dev(q, HNS3_RING_TX_RING_BD_LEN_REG,
-			       hns3_buf_size2type(ring->buf_size));
 		hns3_write_dev(q, HNS3_RING_TX_RING_BD_NUM_REG,
 			       ring->desc_num / 8 - 1);
 	}
 }
 
+static void hns3_init_tx_ring_tc(struct hns3_nic_priv *priv)
+{
+	struct hnae3_knic_private_info *kinfo = &priv->ae_handle->kinfo;
+	int i;
+
+	for (i = 0; i < HNAE3_MAX_TC; i++) {
+		struct hnae3_tc_info *tc_info = &kinfo->tc_info[i];
+		int j;
+
+		if (!tc_info->enable)
+			continue;
+
+		for (j = 0; j < tc_info->tqp_count; j++) {
+			struct hnae3_queue *q;
+
+			q = priv->ring_data[tc_info->tqp_offset + j].ring->tqp;
+			hns3_write_dev(q, HNS3_RING_TX_RING_TC_REG,
+				       tc_info->tc);
+		}
+	}
+}
+
 int hns3_init_all_ring(struct hns3_nic_priv *priv)
 {
 	struct hnae3_handle *h = priv->ae_handle;
@@ -3081,7 +3107,6 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	priv->dev = &pdev->dev;
 	priv->netdev = netdev;
 	priv->ae_handle = handle;
-	priv->ae_handle->reset_level = HNAE3_NONE_RESET;
 	priv->ae_handle->last_reset_time = jiffies;
 	priv->tx_timeout_count = 0;
 
@@ -3102,6 +3127,11 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	/* Carrier off reporting is important to ethtool even BEFORE open */
 	netif_carrier_off(netdev);
 
+	if (handle->flags & HNAE3_SUPPORT_VF)
+		handle->reset_level = HNAE3_VF_RESET;
+	else
+		handle->reset_level = HNAE3_FUNC_RESET;
+
 	ret = hns3_get_ring_config(priv);
 	if (ret) {
 		ret = -ENOMEM;
@@ -3208,7 +3238,6 @@ static int hns3_client_setup_tc(struct hnae3_handle *handle, u8 tc)
 	struct net_device *ndev = kinfo->netdev;
 	bool if_running;
 	int ret;
-	u8 i;
 
 	if (tc > HNAE3_MAX_TC)
 		return -EINVAL;
@@ -3218,10 +3247,6 @@ static int hns3_client_setup_tc(struct hnae3_handle *handle, u8 tc)
 
 	if_running = netif_running(ndev);
 
-	ret = netdev_set_num_tc(ndev, tc);
-	if (ret)
-		return ret;
-
 	if (if_running) {
 		(void)hns3_nic_net_stop(ndev);
 		msleep(100);
@@ -3232,27 +3257,6 @@ static int hns3_client_setup_tc(struct hnae3_handle *handle, u8 tc)
 	if (ret)
 		goto err_out;
 
-	if (tc <= 1) {
-		netdev_reset_tc(ndev);
-		goto out;
-	}
-
-	for (i = 0; i < HNAE3_MAX_TC; i++) {
-		struct hnae3_tc_info *tc_info = &kinfo->tc_info[i];
-
-		if (tc_info->enable)
-			netdev_set_tc_queue(ndev,
-					    tc_info->tc,
-					    tc_info->tqp_count,
-					    tc_info->tqp_offset);
-	}
-
-	for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
-		netdev_set_prio_tc_map(ndev, i,
-				       kinfo->prio_tc[i]);
-	}
-
-out:
 	ret = hns3_nic_set_real_num_queue(ndev);
 
 err_out:
@@ -3409,6 +3413,8 @@ int hns3_nic_reset_all_ring(struct hnae3_handle *h)
 		rx_ring->next_to_use = 0;
 	}
 
+	hns3_init_tx_ring_tc(priv);
+
 	return 0;
 }
 
@@ -3418,7 +3424,7 @@ static int hns3_reset_notify_down_enet(struct hnae3_handle *handle)
 	struct net_device *ndev = kinfo->netdev;
 
 	if (!netif_running(ndev))
-		return -EIO;
+		return 0;
 
 	return hns3_nic_net_stop(ndev);
 }
@@ -3458,10 +3464,6 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle)
 	/* Carrier off reporting is important to ethtool even BEFORE open */
 	netif_carrier_off(netdev);
 
-	ret = hns3_get_ring_config(priv);
-	if (ret)
-		return ret;
-
 	ret = hns3_nic_init_vector_data(priv);
 	if (ret)
 		return ret;
@@ -3493,10 +3495,6 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
 	if (ret)
 		netdev_err(netdev, "uninit ring error\n");
 
-	hns3_put_ring_config(priv);
-
-	priv->ring_data = NULL;
-
 	hns3_uninit_mac_addr(netdev);
 
 	return ret;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 3b083d5ae9ce..a02a96aee2a2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HNS3_ENET_H
 #define __HNS3_ENET_H
@@ -43,7 +37,7 @@ enum hns3_nic_state {
 #define HNS3_RING_TX_RING_BASEADDR_L_REG	0x00040
 #define HNS3_RING_TX_RING_BASEADDR_H_REG	0x00044
 #define HNS3_RING_TX_RING_BD_NUM_REG		0x00048
-#define HNS3_RING_TX_RING_BD_LEN_REG		0x0004C
+#define HNS3_RING_TX_RING_TC_REG		0x00050
 #define HNS3_RING_TX_RING_TAIL_REG		0x00058
 #define HNS3_RING_TX_RING_HEAD_REG		0x0005C
 #define HNS3_RING_TX_RING_FBDNUM_REG		0x00060
@@ -499,7 +493,6 @@ struct hns3_enet_tqp_vector {
 
 	u16 num_tqps;	/* total number of tqps in TQP vector */
 
-	cpumask_t affinity_mask;
 	char name[HNAE3_INT_NAME_LEN];
 
 	/* when 0 should adjust interrupt coalesce parameter */
@@ -591,7 +584,7 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value)
 #define hns3_write_dev(a, reg, value) \
 	hns3_write_reg((a)->io_base, (reg), (value))
 
-#define hnae_queue_xmit(tqp, buf_num) writel_relaxed(buf_num, \
+#define hnae3_queue_xmit(tqp, buf_num) writel_relaxed(buf_num, \
 		(tqp)->io_base + HNS3_RING_TX_RING_TAIL_REG)
 
 #define ring_to_dev(ring) (&(ring)->tqp->handle->pdev->dev)
@@ -601,9 +594,9 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value)
 
 #define tx_ring_data(priv, idx) ((priv)->ring_data[idx])
 
-#define hnae_buf_size(_ring) ((_ring)->buf_size)
-#define hnae_page_order(_ring) (get_order(hnae_buf_size(_ring)))
-#define hnae_page_size(_ring) (PAGE_SIZE << hnae_page_order(_ring))
+#define hnae3_buf_size(_ring) ((_ring)->buf_size)
+#define hnae3_page_order(_ring) (get_order(hnae3_buf_size(_ring)))
+#define hnae3_page_size(_ring) (PAGE_SIZE << hnae3_page_order(_ring))
 
 /* iterator for handling rings in ring group */
 #define hns3_for_each_ring(pos, head) \
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 40c0425b4023..f70ee6910ee2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016~2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include <linux/etherdevice.h>
 #include <linux/string.h>
@@ -59,7 +53,7 @@ static const struct hns3_stats hns3_rxq_stats[] = {
 
 #define HNS3_TQP_STATS_COUNT (HNS3_TXQ_STATS_COUNT + HNS3_RXQ_STATS_COUNT)
 
-#define HNS3_SELF_TEST_TPYE_NUM		1
+#define HNS3_SELF_TEST_TYPE_NUM		2
 #define HNS3_NIC_LB_TEST_PKT_NUM	1
 #define HNS3_NIC_LB_TEST_RING_ID	0
 #define HNS3_NIC_LB_TEST_PACKET_SIZE	128
@@ -84,6 +78,7 @@ static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en)
 		return -EOPNOTSUPP;
 
 	switch (loop) {
+	case HNAE3_MAC_INTER_LOOP_SERDES:
 	case HNAE3_MAC_INTER_LOOP_MAC:
 		ret = h->ae_algo->ops->set_loopback(h, loop, en);
 		break;
@@ -201,7 +196,9 @@ static u32 hns3_lb_check_rx_ring(struct hns3_nic_priv *priv, u32 budget)
 		rx_group = &ring->tqp_vector->rx_group;
 		pre_rx_pkt = rx_group->total_packets;
 
+		preempt_disable();
 		hns3_clean_rx_ring(ring, budget, hns3_lb_check_skb_data);
+		preempt_enable();
 
 		rcv_good_pkt_total += (rx_group->total_packets - pre_rx_pkt);
 		rx_group->total_packets = pre_rx_pkt;
@@ -291,7 +288,7 @@ static void hns3_self_test(struct net_device *ndev,
 {
 	struct hns3_nic_priv *priv = netdev_priv(ndev);
 	struct hnae3_handle *h = priv->ae_handle;
-	int st_param[HNS3_SELF_TEST_TPYE_NUM][2];
+	int st_param[HNS3_SELF_TEST_TYPE_NUM][2];
 	bool if_running = netif_running(ndev);
 #if IS_ENABLED(CONFIG_VLAN_8021Q)
 	bool dis_vlan_filter;
@@ -307,6 +304,10 @@ static void hns3_self_test(struct net_device *ndev,
 	st_param[HNAE3_MAC_INTER_LOOP_MAC][1] =
 			h->flags & HNAE3_SUPPORT_MAC_LOOPBACK;
 
+	st_param[HNAE3_MAC_INTER_LOOP_SERDES][0] = HNAE3_MAC_INTER_LOOP_SERDES;
+	st_param[HNAE3_MAC_INTER_LOOP_SERDES][1] =
+			h->flags & HNAE3_SUPPORT_SERDES_LOOPBACK;
+
 	if (if_running)
 		dev_close(ndev);
 
@@ -320,7 +321,7 @@ static void hns3_self_test(struct net_device *ndev,
 
 	set_bit(HNS3_NIC_STATE_TESTING, &priv->state);
 
-	for (i = 0; i < HNS3_SELF_TEST_TPYE_NUM; i++) {
+	for (i = 0; i < HNS3_SELF_TEST_TYPE_NUM; i++) {
 		enum hnae3_loop loop_type = (enum hnae3_loop)st_param[i][0];
 
 		if (!st_param[i][1])
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index c36d64710fa6..ac13cb2b168e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016~2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
@@ -18,8 +12,7 @@
 #include "hclge_main.h"
 
 #define hclge_is_csq(ring) ((ring)->flag & HCLGE_TYPE_CSQ)
-#define hclge_ring_to_dma_dir(ring) (hclge_is_csq(ring) ? \
-	DMA_TO_DEVICE : DMA_FROM_DEVICE)
+
 #define cmq_ring_to_dev(ring)   (&(ring)->dev->pdev->dev)
 
 static int hclge_ring_space(struct hclge_cmq_ring *ring)
@@ -46,31 +39,24 @@ static int hclge_alloc_cmd_desc(struct hclge_cmq_ring *ring)
 {
 	int size  = ring->desc_num * sizeof(struct hclge_desc);
 
-	ring->desc = kzalloc(size, GFP_KERNEL);
+	ring->desc = dma_zalloc_coherent(cmq_ring_to_dev(ring),
+					 size, &ring->desc_dma_addr,
+					 GFP_KERNEL);
 	if (!ring->desc)
 		return -ENOMEM;
 
-	ring->desc_dma_addr = dma_map_single(cmq_ring_to_dev(ring), ring->desc,
-					     size, DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(cmq_ring_to_dev(ring), ring->desc_dma_addr)) {
-		ring->desc_dma_addr = 0;
-		kfree(ring->desc);
-		ring->desc = NULL;
-		return -ENOMEM;
-	}
-
 	return 0;
 }
 
 static void hclge_free_cmd_desc(struct hclge_cmq_ring *ring)
 {
-	dma_unmap_single(cmq_ring_to_dev(ring), ring->desc_dma_addr,
-			 ring->desc_num * sizeof(ring->desc[0]),
-			 DMA_BIDIRECTIONAL);
+	int size  = ring->desc_num * sizeof(struct hclge_desc);
 
-	ring->desc_dma_addr = 0;
-	kfree(ring->desc);
-	ring->desc = NULL;
+	if (ring->desc) {
+		dma_free_coherent(cmq_ring_to_dev(ring), size,
+				  ring->desc, ring->desc_dma_addr);
+		ring->desc = NULL;
+	}
 }
 
 static int hclge_alloc_cmd_queue(struct hclge_dev *hdev, int ring_type)
@@ -80,7 +66,7 @@ static int hclge_alloc_cmd_queue(struct hclge_dev *hdev, int ring_type)
 		(ring_type == HCLGE_TYPE_CSQ) ? &hw->cmq.csq : &hw->cmq.crq;
 	int ret;
 
-	ring->flag = ring_type;
+	ring->ring_type = ring_type;
 	ring->dev = hdev;
 
 	ret = hclge_alloc_cmd_desc(ring);
@@ -111,8 +97,6 @@ void hclge_cmd_setup_basic_desc(struct hclge_desc *desc,
 
 	if (is_read)
 		desc->flag |= cpu_to_le16(HCLGE_CMD_FLAG_WR);
-	else
-		desc->flag &= cpu_to_le16(~HCLGE_CMD_FLAG_WR);
 }
 
 static void hclge_cmd_config_regs(struct hclge_cmq_ring *ring)
@@ -121,26 +105,26 @@ static void hclge_cmd_config_regs(struct hclge_cmq_ring *ring)
 	struct hclge_dev *hdev = ring->dev;
 	struct hclge_hw *hw = &hdev->hw;
 
-	if (ring->flag == HCLGE_TYPE_CSQ) {
+	if (ring->ring_type == HCLGE_TYPE_CSQ) {
 		hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_L_REG,
-				(u32)dma);
+				lower_32_bits(dma));
 		hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_H_REG,
-				(u32)((dma >> 31) >> 1));
+				upper_32_bits(dma));
 		hclge_write_dev(hw, HCLGE_NIC_CSQ_DEPTH_REG,
 				(ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S) |
 				HCLGE_NIC_CMQ_ENABLE);
-		hclge_write_dev(hw, HCLGE_NIC_CSQ_TAIL_REG, 0);
 		hclge_write_dev(hw, HCLGE_NIC_CSQ_HEAD_REG, 0);
+		hclge_write_dev(hw, HCLGE_NIC_CSQ_TAIL_REG, 0);
 	} else {
 		hclge_write_dev(hw, HCLGE_NIC_CRQ_BASEADDR_L_REG,
-				(u32)dma);
+				lower_32_bits(dma));
 		hclge_write_dev(hw, HCLGE_NIC_CRQ_BASEADDR_H_REG,
-				(u32)((dma >> 31) >> 1));
+				upper_32_bits(dma));
 		hclge_write_dev(hw, HCLGE_NIC_CRQ_DEPTH_REG,
 				(ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S) |
 				HCLGE_NIC_CMQ_ENABLE);
-		hclge_write_dev(hw, HCLGE_NIC_CRQ_TAIL_REG, 0);
 		hclge_write_dev(hw, HCLGE_NIC_CRQ_HEAD_REG, 0);
+		hclge_write_dev(hw, HCLGE_NIC_CRQ_TAIL_REG, 0);
 	}
 }
 
@@ -152,33 +136,27 @@ static void hclge_cmd_init_regs(struct hclge_hw *hw)
 
 static int hclge_cmd_csq_clean(struct hclge_hw *hw)
 {
-	struct hclge_dev *hdev = (struct hclge_dev *)hw->back;
+	struct hclge_dev *hdev = container_of(hw, struct hclge_dev, hw);
 	struct hclge_cmq_ring *csq = &hw->cmq.csq;
-	u16 ntc = csq->next_to_clean;
-	struct hclge_desc *desc;
-	int clean = 0;
 	u32 head;
+	int clean;
 
-	desc = &csq->desc[ntc];
 	head = hclge_read_dev(hw, HCLGE_NIC_CSQ_HEAD_REG);
 	rmb(); /* Make sure head is ready before touch any data */
 
 	if (!is_valid_csq_clean_head(csq, head)) {
-		dev_warn(&hdev->pdev->dev, "wrong head (%d, %d-%d)\n", head,
-			   csq->next_to_use, csq->next_to_clean);
-		return 0;
-	}
-
-	while (head != ntc) {
-		memset(desc, 0, sizeof(*desc));
-		ntc++;
-		if (ntc == csq->desc_num)
-			ntc = 0;
-		desc = &csq->desc[ntc];
-		clean++;
+		dev_warn(&hdev->pdev->dev, "wrong cmd head (%d, %d-%d)\n", head,
+			 csq->next_to_use, csq->next_to_clean);
+		dev_warn(&hdev->pdev->dev,
+			 "Disabling any further commands to IMP firmware\n");
+		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+		dev_warn(&hdev->pdev->dev,
+			 "IMP firmware watchdog reset soon expected!\n");
+		return -EIO;
 	}
-	csq->next_to_clean = ntc;
 
+	clean = (head - csq->next_to_clean + csq->desc_num) % csq->desc_num;
+	csq->next_to_clean = head;
 	return clean;
 }
 
@@ -216,7 +194,7 @@ static bool hclge_is_special_opcode(u16 opcode)
  **/
 int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 {
-	struct hclge_dev *hdev = (struct hclge_dev *)hw->back;
+	struct hclge_dev *hdev = container_of(hw, struct hclge_dev, hw);
 	struct hclge_desc *desc_to_use;
 	bool complete = false;
 	u32 timeout = 0;
@@ -227,7 +205,8 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 
 	spin_lock_bh(&hw->cmq.csq.lock);
 
-	if (num > hclge_ring_space(&hw->cmq.csq)) {
+	if (num > hclge_ring_space(&hw->cmq.csq) ||
+	    test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state)) {
 		spin_unlock_bh(&hw->cmq.csq.lock);
 		return -EBUSY;
 	}
@@ -256,33 +235,34 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 	 */
 	if (HCLGE_SEND_SYNC(le16_to_cpu(desc->flag))) {
 		do {
-			if (hclge_cmd_csq_done(hw))
+			if (hclge_cmd_csq_done(hw)) {
+				complete = true;
 				break;
+			}
 			udelay(1);
 			timeout++;
 		} while (timeout < hw->cmq.tx_timeout);
 	}
 
-	if (hclge_cmd_csq_done(hw)) {
-		complete = true;
+	if (!complete) {
+		retval = -EAGAIN;
+	} else {
 		handle = 0;
 		while (handle < num) {
 			/* Get the result of hardware write back */
 			desc_to_use = &hw->cmq.csq.desc[ntc];
 			desc[handle] = *desc_to_use;
-			pr_debug("Get cmd desc:\n");
 
 			if (likely(!hclge_is_special_opcode(opcode)))
 				desc_ret = le16_to_cpu(desc[handle].retval);
 			else
 				desc_ret = le16_to_cpu(desc[0].retval);
 
-			if ((enum hclge_cmd_return_status)desc_ret ==
-			    HCLGE_CMD_EXEC_SUCCESS)
+			if (desc_ret == HCLGE_CMD_EXEC_SUCCESS)
 				retval = 0;
 			else
 				retval = -EIO;
-			hw->cmq.last_status = (enum hclge_cmd_status)desc_ret;
+			hw->cmq.last_status = desc_ret;
 			ntc++;
 			handle++;
 			if (ntc == hw->cmq.csq.desc_num)
@@ -290,15 +270,13 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 		}
 	}
 
-	if (!complete)
-		retval = -EAGAIN;
-
 	/* Clean the command send queue */
 	handle = hclge_cmd_csq_clean(hw);
-	if (handle != num) {
+	if (handle < 0)
+		retval = handle;
+	else if (handle != num)
 		dev_warn(&hdev->pdev->dev,
 			 "cleaned %d, need to clean %d\n", handle, num);
-	}
 
 	spin_unlock_bh(&hw->cmq.csq.lock);
 
@@ -369,6 +347,7 @@ int hclge_cmd_init(struct hclge_dev *hdev)
 	spin_lock_init(&hdev->hw.cmq.crq.lock);
 
 	hclge_cmd_init_regs(&hdev->hw);
+	clear_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 
 	ret = hclge_cmd_query_firmware_version(&hdev->hw, &version);
 	if (ret) {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index d9aaa76c76eb..821d4c2f84bd 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016~2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_CMD_H
 #define __HCLGE_CMD_H
@@ -27,17 +21,10 @@ struct hclge_desc {
 	__le32 data[6];
 };
 
-struct hclge_desc_cb {
-	dma_addr_t dma;
-	void *va;
-	u32 length;
-};
-
 struct hclge_cmq_ring {
 	dma_addr_t desc_dma_addr;
 	struct hclge_desc *desc;
-	struct hclge_desc_cb *desc_cb;
-	struct hclge_dev  *dev;
+	struct hclge_dev *dev;
 	u32 head;
 	u32 tail;
 
@@ -45,7 +32,7 @@ struct hclge_cmq_ring {
 	u16 desc_num;
 	int next_to_use;
 	int next_to_clean;
-	u8 flag;
+	u8 ring_type; /* cmq ring type */
 	spinlock_t lock; /* Command queue lock */
 };
 
@@ -71,26 +58,19 @@ struct hclge_misc_vector {
 struct hclge_cmq {
 	struct hclge_cmq_ring csq;
 	struct hclge_cmq_ring crq;
-	u16 tx_timeout; /* Tx timeout */
+	u16 tx_timeout;
 	enum hclge_cmd_status last_status;
 };
 
-#define HCLGE_CMD_FLAG_IN_VALID_SHIFT	0
-#define HCLGE_CMD_FLAG_OUT_VALID_SHIFT	1
-#define HCLGE_CMD_FLAG_NEXT_SHIFT	2
-#define HCLGE_CMD_FLAG_WR_OR_RD_SHIFT	3
-#define HCLGE_CMD_FLAG_NO_INTR_SHIFT	4
-#define HCLGE_CMD_FLAG_ERR_INTR_SHIFT	5
-
-#define HCLGE_CMD_FLAG_IN	BIT(HCLGE_CMD_FLAG_IN_VALID_SHIFT)
-#define HCLGE_CMD_FLAG_OUT	BIT(HCLGE_CMD_FLAG_OUT_VALID_SHIFT)
-#define HCLGE_CMD_FLAG_NEXT	BIT(HCLGE_CMD_FLAG_NEXT_SHIFT)
-#define HCLGE_CMD_FLAG_WR	BIT(HCLGE_CMD_FLAG_WR_OR_RD_SHIFT)
-#define HCLGE_CMD_FLAG_NO_INTR	BIT(HCLGE_CMD_FLAG_NO_INTR_SHIFT)
-#define HCLGE_CMD_FLAG_ERR_INTR	BIT(HCLGE_CMD_FLAG_ERR_INTR_SHIFT)
+#define HCLGE_CMD_FLAG_IN	BIT(0)
+#define HCLGE_CMD_FLAG_OUT	BIT(1)
+#define HCLGE_CMD_FLAG_NEXT	BIT(2)
+#define HCLGE_CMD_FLAG_WR	BIT(3)
+#define HCLGE_CMD_FLAG_NO_INTR	BIT(4)
+#define HCLGE_CMD_FLAG_ERR_INTR	BIT(5)
 
 enum hclge_opcode_type {
-	/* Generic command */
+	/* Generic commands */
 	HCLGE_OPC_QUERY_FW_VER		= 0x0001,
 	HCLGE_OPC_CFG_RST_TRIGGER	= 0x0020,
 	HCLGE_OPC_GBL_RST_STATUS	= 0x0021,
@@ -106,18 +86,17 @@ enum hclge_opcode_type {
 	HCLGE_OPC_QUERY_REG_NUM		= 0x0040,
 	HCLGE_OPC_QUERY_32_BIT_REG	= 0x0041,
 	HCLGE_OPC_QUERY_64_BIT_REG	= 0x0042,
-	/* Device management command */
 
-	/* MAC commond */
+	/* MAC command */
 	HCLGE_OPC_CONFIG_MAC_MODE	= 0x0301,
 	HCLGE_OPC_CONFIG_AN_MODE	= 0x0304,
 	HCLGE_OPC_QUERY_AN_RESULT	= 0x0306,
 	HCLGE_OPC_QUERY_LINK_STATUS	= 0x0307,
 	HCLGE_OPC_CONFIG_MAX_FRM_SIZE	= 0x0308,
 	HCLGE_OPC_CONFIG_SPEED_DUP	= 0x0309,
-	/* MACSEC command */
+	HCLGE_OPC_SERDES_LOOPBACK       = 0x0315,
 
-	/* PFC/Pause CMD*/
+	/* PFC/Pause commands */
 	HCLGE_OPC_CFG_MAC_PAUSE_EN      = 0x0701,
 	HCLGE_OPC_CFG_PFC_PAUSE_EN      = 0x0702,
 	HCLGE_OPC_CFG_MAC_PARA          = 0x0703,
@@ -148,7 +127,7 @@ enum hclge_opcode_type {
 	HCLGE_OPC_TM_QS_SCH_MODE_CFG    = 0x0814,
 	HCLGE_OPC_TM_BP_TO_QSET_MAPPING = 0x0815,
 
-	/* Packet buffer allocate command */
+	/* Packet buffer allocate commands */
 	HCLGE_OPC_TX_BUFF_ALLOC		= 0x0901,
 	HCLGE_OPC_RX_PRIV_BUFF_ALLOC	= 0x0902,
 	HCLGE_OPC_RX_PRIV_WL_ALLOC	= 0x0903,
@@ -156,11 +135,10 @@ enum hclge_opcode_type {
 	HCLGE_OPC_RX_COM_WL_ALLOC	= 0x0905,
 	HCLGE_OPC_RX_GBL_PKT_CNT	= 0x0906,
 
-	/* PTP command */
 	/* TQP management command */
 	HCLGE_OPC_SET_TQP_MAP		= 0x0A01,
 
-	/* TQP command */
+	/* TQP commands */
 	HCLGE_OPC_CFG_TX_QUEUE		= 0x0B01,
 	HCLGE_OPC_QUERY_TX_POINTER	= 0x0B02,
 	HCLGE_OPC_QUERY_TX_STATUS	= 0x0B03,
@@ -172,10 +150,10 @@ enum hclge_opcode_type {
 	HCLGE_OPC_CFG_COM_TQP_QUEUE	= 0x0B20,
 	HCLGE_OPC_RESET_TQP_QUEUE	= 0x0B22,
 
-	/* TSO cmd */
+	/* TSO command */
 	HCLGE_OPC_TSO_GENERIC_CONFIG	= 0x0C01,
 
-	/* RSS cmd */
+	/* RSS commands */
 	HCLGE_OPC_RSS_GENERIC_CONFIG	= 0x0D01,
 	HCLGE_OPC_RSS_INDIR_TABLE	= 0x0D07,
 	HCLGE_OPC_RSS_TC_MODE		= 0x0D08,
@@ -184,15 +162,15 @@ enum hclge_opcode_type {
 	/* Promisuous mode command */
 	HCLGE_OPC_CFG_PROMISC_MODE	= 0x0E01,
 
-	/* Vlan offload command */
+	/* Vlan offload commands */
 	HCLGE_OPC_VLAN_PORT_TX_CFG	= 0x0F01,
 	HCLGE_OPC_VLAN_PORT_RX_CFG	= 0x0F02,
 
-	/* Interrupts cmd */
+	/* Interrupts commands */
 	HCLGE_OPC_ADD_RING_TO_VECTOR	= 0x1503,
 	HCLGE_OPC_DEL_RING_TO_VECTOR	= 0x1504,
 
-	/* MAC command */
+	/* MAC commands */
 	HCLGE_OPC_MAC_VLAN_ADD		    = 0x1000,
 	HCLGE_OPC_MAC_VLAN_REMOVE	    = 0x1001,
 	HCLGE_OPC_MAC_VLAN_TYPE_ID	    = 0x1002,
@@ -201,13 +179,13 @@ enum hclge_opcode_type {
 	HCLGE_OPC_MAC_ETHTYPE_REMOVE	= 0x1011,
 	HCLGE_OPC_MAC_VLAN_MASK_SET	= 0x1012,
 
-	/* Multicast linear table cmd */
+	/* Multicast linear table commands */
 	HCLGE_OPC_MTA_MAC_MODE_CFG	    = 0x1020,
 	HCLGE_OPC_MTA_MAC_FUNC_CFG	    = 0x1021,
 	HCLGE_OPC_MTA_TBL_ITEM_CFG	    = 0x1022,
 	HCLGE_OPC_MTA_TBL_ITEM_QUERY	= 0x1023,
 
-	/* VLAN command */
+	/* VLAN commands */
 	HCLGE_OPC_VLAN_FILTER_CTRL	    = 0x1100,
 	HCLGE_OPC_VLAN_FILTER_PF_CFG	= 0x1101,
 	HCLGE_OPC_VLAN_FILTER_VF_CFG	= 0x1102,
@@ -215,7 +193,7 @@ enum hclge_opcode_type {
 	/* MDIO command */
 	HCLGE_OPC_MDIO_CONFIG		= 0x1900,
 
-	/* QCN command */
+	/* QCN commands */
 	HCLGE_OPC_QCN_MOD_CFG		= 0x1A01,
 	HCLGE_OPC_QCN_GRP_TMPLT_CFG	= 0x1A02,
 	HCLGE_OPC_QCN_SHAPPING_IR_CFG	= 0x1A03,
@@ -225,7 +203,7 @@ enum hclge_opcode_type {
 	HCLGE_OPC_QCN_AJUST_INIT	= 0x1A07,
 	HCLGE_OPC_QCN_DFX_CNT_STATUS    = 0x1A08,
 
-	/* Mailbox cmd */
+	/* Mailbox command */
 	HCLGEVF_OPC_MBX_PF_TO_VF	= 0x2000,
 
 	/* Led command */
@@ -381,8 +359,10 @@ struct hclge_pf_res_cmd {
 	__le16 buf_size;
 	__le16 msixcap_localid_ba_nic;
 	__le16 msixcap_localid_ba_rocee;
+#define HCLGE_MSIX_OFT_ROCEE_S		0
+#define HCLGE_MSIX_OFT_ROCEE_M		GENMASK(15, 0)
 #define HCLGE_PF_VEC_NUM_S		0
-#define HCLGE_PF_VEC_NUM_M		(0xff << HCLGE_PF_VEC_NUM_S)
+#define HCLGE_PF_VEC_NUM_M		GENMASK(7, 0)
 	__le16 pf_intr_vector_number;
 	__le16 pf_own_fun_number;
 	__le32 rsv[3];
@@ -471,8 +451,8 @@ struct hclge_rss_tc_mode_cmd {
 	u8 rsv[8];
 };
 
-#define HCLGE_LINK_STS_B	0
-#define HCLGE_LINK_STATUS	BIT(HCLGE_LINK_STS_B)
+#define HCLGE_LINK_STATUS_UP_B	0
+#define HCLGE_LINK_STATUS_UP_M	BIT(HCLGE_LINK_STATUS_UP_B)
 struct hclge_link_status_cmd {
 	u8 status;
 	u8 rsv[23];
@@ -571,7 +551,8 @@ struct hclge_config_auto_neg_cmd {
 
 struct hclge_config_max_frm_size_cmd {
 	__le16  max_frm_size;
-	u8      rsv[22];
+	u8      min_frm_size;
+	u8      rsv[21];
 };
 
 enum hclge_mac_vlan_tbl_opcode {
@@ -581,13 +562,13 @@ enum hclge_mac_vlan_tbl_opcode {
 	HCLGE_MAC_VLAN_LKUP,    /* Lookup a entry through mac_vlan key */
 };
 
-#define HCLGE_MAC_VLAN_BIT0_EN_B	0x0
-#define HCLGE_MAC_VLAN_BIT1_EN_B	0x1
-#define HCLGE_MAC_EPORT_SW_EN_B		0xc
-#define HCLGE_MAC_EPORT_TYPE_B		0xb
-#define HCLGE_MAC_EPORT_VFID_S		0x3
+#define HCLGE_MAC_VLAN_BIT0_EN_B	0
+#define HCLGE_MAC_VLAN_BIT1_EN_B	1
+#define HCLGE_MAC_EPORT_SW_EN_B		12
+#define HCLGE_MAC_EPORT_TYPE_B		11
+#define HCLGE_MAC_EPORT_VFID_S		3
 #define HCLGE_MAC_EPORT_VFID_M		GENMASK(10, 3)
-#define HCLGE_MAC_EPORT_PFID_S		0x0
+#define HCLGE_MAC_EPORT_PFID_S		0
 #define HCLGE_MAC_EPORT_PFID_M		GENMASK(2, 0)
 struct hclge_mac_vlan_tbl_entry_cmd {
 	u8	flags;
@@ -603,7 +584,7 @@ struct hclge_mac_vlan_tbl_entry_cmd {
 	u8      rsv2[6];
 };
 
-#define HCLGE_VLAN_MASK_EN_B		0x0
+#define HCLGE_VLAN_MASK_EN_B		0
 struct hclge_mac_vlan_mask_entry_cmd {
 	u8 rsv0[2];
 	u8 vlan_mask;
@@ -634,23 +615,23 @@ struct hclge_mac_mgr_tbl_entry_cmd {
 	u8      rsv3[2];
 };
 
-#define HCLGE_CFG_MTA_MAC_SEL_S		0x0
+#define HCLGE_CFG_MTA_MAC_SEL_S		0
 #define HCLGE_CFG_MTA_MAC_SEL_M		GENMASK(1, 0)
-#define HCLGE_CFG_MTA_MAC_EN_B		0x7
+#define HCLGE_CFG_MTA_MAC_EN_B		7
 struct hclge_mta_filter_mode_cmd {
 	u8	dmac_sel_en; /* Use lowest 2 bit as sel_mode, bit 7 as enable */
 	u8      rsv[23];
 };
 
-#define HCLGE_CFG_FUNC_MTA_ACCEPT_B	0x0
+#define HCLGE_CFG_FUNC_MTA_ACCEPT_B	0
 struct hclge_cfg_func_mta_filter_cmd {
 	u8	accept; /* Only used lowest 1 bit */
 	u8      function_id;
 	u8      rsv[22];
 };
 
-#define HCLGE_CFG_MTA_ITEM_ACCEPT_B	0x0
-#define HCLGE_CFG_MTA_ITEM_IDX_S	0x0
+#define HCLGE_CFG_MTA_ITEM_ACCEPT_B	0
+#define HCLGE_CFG_MTA_ITEM_IDX_S	0
 #define HCLGE_CFG_MTA_ITEM_IDX_M	GENMASK(11, 0)
 struct hclge_cfg_func_mta_item_cmd {
 	__le16	item_idx; /* Only used lowest 12 bit */
@@ -795,6 +776,17 @@ struct hclge_reset_cmd {
 	u8 fun_reset_vfid;
 	u8 rsv[22];
 };
+
+#define HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B	BIT(0)
+#define HCLGE_CMD_SERDES_DONE_B			BIT(0)
+#define HCLGE_CMD_SERDES_SUCCESS_B		BIT(1)
+struct hclge_serdes_lb_cmd {
+	u8 mask;
+	u8 enable;
+	u8 result;
+	u8 rsv[21];
+};
+
 #define HCLGE_DEFAULT_TX_BUF		0x4000	 /* 16k  bytes */
 #define HCLGE_TOTAL_PKT_BUF		0x108000 /* 1.03125M bytes */
 #define HCLGE_DEFAULT_DV		0xA000	 /* 40k byte */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
index 955f0e3d5c95..f08ebb7caaaf 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016-2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include "hclge_main.h"
 #include "hclge_tm.h"
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h
index 7d808ee96694..278f21e02736 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016~2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_DCB_H__
 #define __HCLGE_DCB_H__
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index d318d35e598f..8577dfc799ad 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016-2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include <linux/acpi.h>
 #include <linux/device.h>
@@ -793,9 +787,10 @@ static int hclge_get_sset_count(struct hnae3_handle *handle, int stringset)
 		    hdev->hw.mac.speed == HCLGE_MAC_SPEED_1G) {
 			count += 1;
 			handle->flags |= HNAE3_SUPPORT_MAC_LOOPBACK;
-		} else {
-			count = -EOPNOTSUPP;
 		}
+
+		count++;
+		handle->flags |= HNAE3_SUPPORT_SERDES_LOOPBACK;
 	} else if (stringset == ETH_SS_STATS) {
 		count = ARRAY_SIZE(g_mac_stats_string) +
 			ARRAY_SIZE(g_all_32bit_stats_string) +
@@ -938,18 +933,22 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev)
 	hdev->pkt_buf_size = __le16_to_cpu(req->buf_size) << HCLGE_BUF_UNIT_S;
 
 	if (hnae3_dev_roce_supported(hdev)) {
+		hdev->roce_base_msix_offset =
+		hnae3_get_field(__le16_to_cpu(req->msixcap_localid_ba_rocee),
+				HCLGE_MSIX_OFT_ROCEE_M, HCLGE_MSIX_OFT_ROCEE_S);
 		hdev->num_roce_msi =
-		hnae_get_field(__le16_to_cpu(req->pf_intr_vector_number),
-			       HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
+		hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number),
+				HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
 
 		/* PF should have NIC vectors and Roce vectors,
 		 * NIC vectors are queued before Roce vectors.
 		 */
-		hdev->num_msi = hdev->num_roce_msi  + HCLGE_ROCE_VECTOR_OFFSET;
+		hdev->num_msi = hdev->num_roce_msi  +
+				hdev->roce_base_msix_offset;
 	} else {
 		hdev->num_msi =
-		hnae_get_field(__le16_to_cpu(req->pf_intr_vector_number),
-			       HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
+		hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number),
+				HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
 	}
 
 	return 0;
@@ -1038,38 +1037,38 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc)
 	req = (struct hclge_cfg_param_cmd *)desc[0].data;
 
 	/* get the configuration */
-	cfg->vmdq_vport_num = hnae_get_field(__le32_to_cpu(req->param[0]),
-					     HCLGE_CFG_VMDQ_M,
-					     HCLGE_CFG_VMDQ_S);
-	cfg->tc_num = hnae_get_field(__le32_to_cpu(req->param[0]),
-				     HCLGE_CFG_TC_NUM_M, HCLGE_CFG_TC_NUM_S);
-	cfg->tqp_desc_num = hnae_get_field(__le32_to_cpu(req->param[0]),
-					   HCLGE_CFG_TQP_DESC_N_M,
-					   HCLGE_CFG_TQP_DESC_N_S);
-
-	cfg->phy_addr = hnae_get_field(__le32_to_cpu(req->param[1]),
-				       HCLGE_CFG_PHY_ADDR_M,
-				       HCLGE_CFG_PHY_ADDR_S);
-	cfg->media_type = hnae_get_field(__le32_to_cpu(req->param[1]),
-					 HCLGE_CFG_MEDIA_TP_M,
-					 HCLGE_CFG_MEDIA_TP_S);
-	cfg->rx_buf_len = hnae_get_field(__le32_to_cpu(req->param[1]),
-					 HCLGE_CFG_RX_BUF_LEN_M,
-					 HCLGE_CFG_RX_BUF_LEN_S);
+	cfg->vmdq_vport_num = hnae3_get_field(__le32_to_cpu(req->param[0]),
+					      HCLGE_CFG_VMDQ_M,
+					      HCLGE_CFG_VMDQ_S);
+	cfg->tc_num = hnae3_get_field(__le32_to_cpu(req->param[0]),
+				      HCLGE_CFG_TC_NUM_M, HCLGE_CFG_TC_NUM_S);
+	cfg->tqp_desc_num = hnae3_get_field(__le32_to_cpu(req->param[0]),
+					    HCLGE_CFG_TQP_DESC_N_M,
+					    HCLGE_CFG_TQP_DESC_N_S);
+
+	cfg->phy_addr = hnae3_get_field(__le32_to_cpu(req->param[1]),
+					HCLGE_CFG_PHY_ADDR_M,
+					HCLGE_CFG_PHY_ADDR_S);
+	cfg->media_type = hnae3_get_field(__le32_to_cpu(req->param[1]),
+					  HCLGE_CFG_MEDIA_TP_M,
+					  HCLGE_CFG_MEDIA_TP_S);
+	cfg->rx_buf_len = hnae3_get_field(__le32_to_cpu(req->param[1]),
+					  HCLGE_CFG_RX_BUF_LEN_M,
+					  HCLGE_CFG_RX_BUF_LEN_S);
 	/* get mac_address */
 	mac_addr_tmp = __le32_to_cpu(req->param[2]);
-	mac_addr_tmp_high = hnae_get_field(__le32_to_cpu(req->param[3]),
-					   HCLGE_CFG_MAC_ADDR_H_M,
-					   HCLGE_CFG_MAC_ADDR_H_S);
+	mac_addr_tmp_high = hnae3_get_field(__le32_to_cpu(req->param[3]),
+					    HCLGE_CFG_MAC_ADDR_H_M,
+					    HCLGE_CFG_MAC_ADDR_H_S);
 
 	mac_addr_tmp |= (mac_addr_tmp_high << 31) << 1;
 
-	cfg->default_speed = hnae_get_field(__le32_to_cpu(req->param[3]),
-					    HCLGE_CFG_DEFAULT_SPEED_M,
-					    HCLGE_CFG_DEFAULT_SPEED_S);
-	cfg->rss_size_max = hnae_get_field(__le32_to_cpu(req->param[3]),
-					   HCLGE_CFG_RSS_SIZE_M,
-					   HCLGE_CFG_RSS_SIZE_S);
+	cfg->default_speed = hnae3_get_field(__le32_to_cpu(req->param[3]),
+					     HCLGE_CFG_DEFAULT_SPEED_M,
+					     HCLGE_CFG_DEFAULT_SPEED_S);
+	cfg->rss_size_max = hnae3_get_field(__le32_to_cpu(req->param[3]),
+					    HCLGE_CFG_RSS_SIZE_M,
+					    HCLGE_CFG_RSS_SIZE_S);
 
 	for (i = 0; i < ETH_ALEN; i++)
 		cfg->mac_addr[i] = (mac_addr_tmp >> (8 * i)) & 0xff;
@@ -1077,9 +1076,9 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc)
 	req = (struct hclge_cfg_param_cmd *)desc[1].data;
 	cfg->numa_node_map = __le32_to_cpu(req->param[0]);
 
-	cfg->speed_ability = hnae_get_field(__le32_to_cpu(req->param[1]),
-					    HCLGE_CFG_SPEED_ABILITY_M,
-					    HCLGE_CFG_SPEED_ABILITY_S);
+	cfg->speed_ability = hnae3_get_field(__le32_to_cpu(req->param[1]),
+					     HCLGE_CFG_SPEED_ABILITY_M,
+					     HCLGE_CFG_SPEED_ABILITY_S);
 }
 
 /* hclge_get_cfg: query the static parameter from flash
@@ -1098,22 +1097,22 @@ static int hclge_get_cfg(struct hclge_dev *hdev, struct hclge_cfg *hcfg)
 		req = (struct hclge_cfg_param_cmd *)desc[i].data;
 		hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_GET_CFG_PARAM,
 					   true);
-		hnae_set_field(offset, HCLGE_CFG_OFFSET_M,
-			       HCLGE_CFG_OFFSET_S, i * HCLGE_CFG_RD_LEN_BYTES);
+		hnae3_set_field(offset, HCLGE_CFG_OFFSET_M,
+				HCLGE_CFG_OFFSET_S, i * HCLGE_CFG_RD_LEN_BYTES);
 		/* Len should be united by 4 bytes when send to hardware */
-		hnae_set_field(offset, HCLGE_CFG_RD_LEN_M, HCLGE_CFG_RD_LEN_S,
-			       HCLGE_CFG_RD_LEN_BYTES / HCLGE_CFG_RD_LEN_UNIT);
+		hnae3_set_field(offset, HCLGE_CFG_RD_LEN_M, HCLGE_CFG_RD_LEN_S,
+				HCLGE_CFG_RD_LEN_BYTES / HCLGE_CFG_RD_LEN_UNIT);
 		req->offset = cpu_to_le32(offset);
 	}
 
 	ret = hclge_cmd_send(&hdev->hw, desc, HCLGE_PF_CFG_DESC_NUM);
 	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"get config failed %d.\n", ret);
+		dev_err(&hdev->pdev->dev, "get config failed %d.\n", ret);
 		return ret;
 	}
 
 	hclge_parse_cfg(hcfg, desc);
+
 	return 0;
 }
 
@@ -1130,13 +1129,10 @@ static int hclge_get_cap(struct hclge_dev *hdev)
 
 	/* get pf resource */
 	ret = hclge_query_pf_resource(hdev);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"query pf resource error %d.\n", ret);
-		return ret;
-	}
+	if (ret)
+		dev_err(&hdev->pdev->dev, "query pf resource error %d.\n", ret);
 
-	return 0;
+	return ret;
 }
 
 static int hclge_configure(struct hclge_dev *hdev)
@@ -1189,7 +1185,7 @@ static int hclge_configure(struct hclge_dev *hdev)
 
 	/* Currently not support uncontiuous tc */
 	for (i = 0; i < hdev->tm_info.num_tc; i++)
-		hnae_set_bit(hdev->hw_tc_map, i, 1);
+		hnae3_set_bit(hdev->hw_tc_map, i, 1);
 
 	hdev->tx_sch_mode = HCLGE_FLAG_TC_BASE_SCH_MODE;
 
@@ -1208,13 +1204,13 @@ static int hclge_config_tso(struct hclge_dev *hdev, int tso_mss_min,
 	req = (struct hclge_cfg_tso_status_cmd *)desc.data;
 
 	tso_mss = 0;
-	hnae_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M,
-		       HCLGE_TSO_MSS_MIN_S, tso_mss_min);
+	hnae3_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M,
+			HCLGE_TSO_MSS_MIN_S, tso_mss_min);
 	req->tso_mss_min = cpu_to_le16(tso_mss);
 
 	tso_mss = 0;
-	hnae_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M,
-		       HCLGE_TSO_MSS_MIN_S, tso_mss_max);
+	hnae3_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M,
+			HCLGE_TSO_MSS_MIN_S, tso_mss_max);
 	req->tso_mss_max = cpu_to_le16(tso_mss);
 
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -1265,44 +1261,43 @@ static int hclge_map_tqps_to_func(struct hclge_dev *hdev, u16 func_id,
 	req->tqp_vid = cpu_to_le16(tqp_vid);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
-		dev_err(&hdev->pdev->dev, "TQP map failed %d.\n",
-			ret);
-		return ret;
-	}
+	if (ret)
+		dev_err(&hdev->pdev->dev, "TQP map failed %d.\n", ret);
 
-	return 0;
+	return ret;
 }
 
-static int  hclge_assign_tqp(struct hclge_vport *vport,
-			     struct hnae3_queue **tqp, u16 num_tqps)
+static int  hclge_assign_tqp(struct hclge_vport *vport)
 {
+	struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo;
 	struct hclge_dev *hdev = vport->back;
 	int i, alloced;
 
 	for (i = 0, alloced = 0; i < hdev->num_tqps &&
-	     alloced < num_tqps; i++) {
+	     alloced < kinfo->num_tqps; i++) {
 		if (!hdev->htqp[i].alloced) {
 			hdev->htqp[i].q.handle = &vport->nic;
 			hdev->htqp[i].q.tqp_index = alloced;
-			tqp[alloced] = &hdev->htqp[i].q;
+			hdev->htqp[i].q.desc_num = kinfo->num_desc;
+			kinfo->tqp[alloced] = &hdev->htqp[i].q;
 			hdev->htqp[i].alloced = true;
 			alloced++;
 		}
 	}
-	vport->alloc_tqps = num_tqps;
+	vport->alloc_tqps = kinfo->num_tqps;
 
 	return 0;
 }
 
-static int hclge_knic_setup(struct hclge_vport *vport, u16 num_tqps)
+static int hclge_knic_setup(struct hclge_vport *vport,
+			    u16 num_tqps, u16 num_desc)
 {
 	struct hnae3_handle *nic = &vport->nic;
 	struct hnae3_knic_private_info *kinfo = &nic->kinfo;
 	struct hclge_dev *hdev = vport->back;
 	int i, ret;
 
-	kinfo->num_desc = hdev->num_desc;
+	kinfo->num_desc = num_desc;
 	kinfo->rx_buf_len = hdev->rx_buf_len;
 	kinfo->num_tc = min_t(u16, num_tqps, hdev->tm_info.num_tc);
 	kinfo->rss_size
@@ -1329,13 +1324,11 @@ static int hclge_knic_setup(struct hclge_vport *vport, u16 num_tqps)
 	if (!kinfo->tqp)
 		return -ENOMEM;
 
-	ret = hclge_assign_tqp(vport, kinfo->tqp, kinfo->num_tqps);
-	if (ret) {
+	ret = hclge_assign_tqp(vport);
+	if (ret)
 		dev_err(&hdev->pdev->dev, "fail to assign TQPs %d.\n", ret);
-		return -EINVAL;
-	}
 
-	return 0;
+	return ret;
 }
 
 static int hclge_map_tqp_to_vport(struct hclge_dev *hdev,
@@ -1397,7 +1390,7 @@ static int hclge_vport_setup(struct hclge_vport *vport, u16 num_tqps)
 	nic->numa_node_mask = hdev->numa_node_mask;
 
 	if (hdev->ae_dev->dev_type == HNAE3_DEV_KNIC) {
-		ret = hclge_knic_setup(vport, num_tqps);
+		ret = hclge_knic_setup(vport, num_tqps, hdev->num_desc);
 		if (ret) {
 			dev_err(&hdev->pdev->dev, "knic setup failed %d\n",
 				ret);
@@ -1487,13 +1480,11 @@ static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev,
 	}
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev, "tx buffer alloc cmd failed %d.\n",
 			ret);
-		return ret;
-	}
 
-	return 0;
+	return ret;
 }
 
 static int hclge_tx_buffer_alloc(struct hclge_dev *hdev,
@@ -1501,13 +1492,10 @@ static int hclge_tx_buffer_alloc(struct hclge_dev *hdev,
 {
 	int ret = hclge_cmd_alloc_tx_buff(hdev, buf_alloc);
 
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"tx buffer alloc failed %d\n", ret);
-		return ret;
-	}
+	if (ret)
+		dev_err(&hdev->pdev->dev, "tx buffer alloc failed %d\n", ret);
 
-	return 0;
+	return ret;
 }
 
 static int hclge_get_tc_num(struct hclge_dev *hdev)
@@ -1825,17 +1813,13 @@ static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev,
 			    (1 << HCLGE_TC0_PRI_BUF_EN_B));
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"rx private buffer alloc cmd failed %d\n", ret);
-		return ret;
-	}
 
-	return 0;
+	return ret;
 }
 
-#define HCLGE_PRIV_ENABLE(a) ((a) > 0 ? 1 : 0)
-
 static int hclge_rx_priv_wl_config(struct hclge_dev *hdev,
 				   struct hclge_pkt_buf_alloc *buf_alloc)
 {
@@ -1863,25 +1847,21 @@ static int hclge_rx_priv_wl_config(struct hclge_dev *hdev,
 			req->tc_wl[j].high =
 				cpu_to_le16(priv->wl.high >> HCLGE_BUF_UNIT_S);
 			req->tc_wl[j].high |=
-				cpu_to_le16(HCLGE_PRIV_ENABLE(priv->wl.high) <<
-					    HCLGE_RX_PRIV_EN_B);
+				cpu_to_le16(BIT(HCLGE_RX_PRIV_EN_B));
 			req->tc_wl[j].low =
 				cpu_to_le16(priv->wl.low >> HCLGE_BUF_UNIT_S);
 			req->tc_wl[j].low |=
-				cpu_to_le16(HCLGE_PRIV_ENABLE(priv->wl.low) <<
-					    HCLGE_RX_PRIV_EN_B);
+				 cpu_to_le16(BIT(HCLGE_RX_PRIV_EN_B));
 		}
 	}
 
 	/* Send 2 descriptor at one time */
 	ret = hclge_cmd_send(&hdev->hw, desc, 2);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"rx private waterline config cmd failed %d\n",
 			ret);
-		return ret;
-	}
-	return 0;
+	return ret;
 }
 
 static int hclge_common_thrd_config(struct hclge_dev *hdev,
@@ -1911,24 +1891,20 @@ static int hclge_common_thrd_config(struct hclge_dev *hdev,
 			req->com_thrd[j].high =
 				cpu_to_le16(tc->high >> HCLGE_BUF_UNIT_S);
 			req->com_thrd[j].high |=
-				cpu_to_le16(HCLGE_PRIV_ENABLE(tc->high) <<
-					    HCLGE_RX_PRIV_EN_B);
+				 cpu_to_le16(BIT(HCLGE_RX_PRIV_EN_B));
 			req->com_thrd[j].low =
 				cpu_to_le16(tc->low >> HCLGE_BUF_UNIT_S);
 			req->com_thrd[j].low |=
-				cpu_to_le16(HCLGE_PRIV_ENABLE(tc->low) <<
-					    HCLGE_RX_PRIV_EN_B);
+				 cpu_to_le16(BIT(HCLGE_RX_PRIV_EN_B));
 		}
 	}
 
 	/* Send 2 descriptors at one time */
 	ret = hclge_cmd_send(&hdev->hw, desc, 2);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"common threshold config cmd failed %d\n", ret);
-		return ret;
-	}
-	return 0;
+	return ret;
 }
 
 static int hclge_common_wl_config(struct hclge_dev *hdev,
@@ -1943,23 +1919,17 @@ static int hclge_common_wl_config(struct hclge_dev *hdev,
 
 	req = (struct hclge_rx_com_wl *)desc.data;
 	req->com_wl.high = cpu_to_le16(buf->self.high >> HCLGE_BUF_UNIT_S);
-	req->com_wl.high |=
-		cpu_to_le16(HCLGE_PRIV_ENABLE(buf->self.high) <<
-			    HCLGE_RX_PRIV_EN_B);
+	req->com_wl.high |=  cpu_to_le16(BIT(HCLGE_RX_PRIV_EN_B));
 
 	req->com_wl.low = cpu_to_le16(buf->self.low >> HCLGE_BUF_UNIT_S);
-	req->com_wl.low |=
-		cpu_to_le16(HCLGE_PRIV_ENABLE(buf->self.low) <<
-			    HCLGE_RX_PRIV_EN_B);
+	req->com_wl.low |=  cpu_to_le16(BIT(HCLGE_RX_PRIV_EN_B));
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"common waterline config cmd failed %d\n", ret);
-		return ret;
-	}
 
-	return 0;
+	return ret;
 }
 
 int hclge_buffer_alloc(struct hclge_dev *hdev)
@@ -2074,7 +2044,7 @@ static int hclge_init_msi(struct hclge_dev *hdev)
 	hdev->num_msi_left = vectors;
 	hdev->base_msi_vector = pdev->irq;
 	hdev->roce_base_vector = hdev->base_msi_vector +
-				HCLGE_ROCE_VECTOR_OFFSET;
+				hdev->roce_base_msix_offset;
 
 	hdev->vector_status = devm_kcalloc(&pdev->dev, hdev->num_msi,
 					   sizeof(u16), GFP_KERNEL);
@@ -2118,48 +2088,48 @@ int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex)
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_SPEED_DUP, false);
 
-	hnae_set_bit(req->speed_dup, HCLGE_CFG_DUPLEX_B, !!duplex);
+	hnae3_set_bit(req->speed_dup, HCLGE_CFG_DUPLEX_B, !!duplex);
 
 	switch (speed) {
 	case HCLGE_MAC_SPEED_10M:
-		hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-			       HCLGE_CFG_SPEED_S, 6);
+		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+				HCLGE_CFG_SPEED_S, 6);
 		break;
 	case HCLGE_MAC_SPEED_100M:
-		hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-			       HCLGE_CFG_SPEED_S, 7);
+		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+				HCLGE_CFG_SPEED_S, 7);
 		break;
 	case HCLGE_MAC_SPEED_1G:
-		hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-			       HCLGE_CFG_SPEED_S, 0);
+		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+				HCLGE_CFG_SPEED_S, 0);
 		break;
 	case HCLGE_MAC_SPEED_10G:
-		hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-			       HCLGE_CFG_SPEED_S, 1);
+		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+				HCLGE_CFG_SPEED_S, 1);
 		break;
 	case HCLGE_MAC_SPEED_25G:
-		hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-			       HCLGE_CFG_SPEED_S, 2);
+		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+				HCLGE_CFG_SPEED_S, 2);
 		break;
 	case HCLGE_MAC_SPEED_40G:
-		hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-			       HCLGE_CFG_SPEED_S, 3);
+		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+				HCLGE_CFG_SPEED_S, 3);
 		break;
 	case HCLGE_MAC_SPEED_50G:
-		hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-			       HCLGE_CFG_SPEED_S, 4);
+		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+				HCLGE_CFG_SPEED_S, 4);
 		break;
 	case HCLGE_MAC_SPEED_100G:
-		hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-			       HCLGE_CFG_SPEED_S, 5);
+		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+				HCLGE_CFG_SPEED_S, 5);
 		break;
 	default:
 		dev_err(&hdev->pdev->dev, "invalid speed (%d)\n", speed);
 		return -EINVAL;
 	}
 
-	hnae_set_bit(req->mac_change_fec_en, HCLGE_CFG_MAC_SPEED_CHANGE_EN_B,
-		     1);
+	hnae3_set_bit(req->mac_change_fec_en, HCLGE_CFG_MAC_SPEED_CHANGE_EN_B,
+		      1);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
@@ -2201,18 +2171,16 @@ static int hclge_query_mac_an_speed_dup(struct hclge_dev *hdev, int *speed,
 		return ret;
 	}
 
-	*duplex = hnae_get_bit(req->an_syn_dup_speed, HCLGE_QUERY_DUPLEX_B);
-	speed_tmp = hnae_get_field(req->an_syn_dup_speed, HCLGE_QUERY_SPEED_M,
-				   HCLGE_QUERY_SPEED_S);
+	*duplex = hnae3_get_bit(req->an_syn_dup_speed, HCLGE_QUERY_DUPLEX_B);
+	speed_tmp = hnae3_get_field(req->an_syn_dup_speed, HCLGE_QUERY_SPEED_M,
+				    HCLGE_QUERY_SPEED_S);
 
 	ret = hclge_parse_speed(speed_tmp, speed);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"could not parse speed(=%d), %d\n", speed_tmp, ret);
-		return -EIO;
-	}
 
-	return 0;
+	return ret;
 }
 
 static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable)
@@ -2225,17 +2193,15 @@ static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable)
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_AN_MODE, false);
 
 	req = (struct hclge_config_auto_neg_cmd *)desc.data;
-	hnae_set_bit(flag, HCLGE_MAC_CFG_AN_EN_B, !!enable);
+	hnae3_set_bit(flag, HCLGE_MAC_CFG_AN_EN_B, !!enable);
 	req->cfg_an_cmd_flag = cpu_to_le32(flag);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev, "auto neg set cmd failed %d.\n",
 			ret);
-		return ret;
-	}
 
-	return 0;
+	return ret;
 }
 
 static int hclge_set_autoneg(struct hnae3_handle *handle, bool enable)
@@ -2269,8 +2235,8 @@ static int hclge_set_default_mac_vlan_mask(struct hclge_dev *hdev,
 	req = (struct hclge_mac_vlan_mask_entry_cmd *)desc.data;
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_MASK_SET, false);
 
-	hnae_set_bit(req->vlan_mask, HCLGE_VLAN_MASK_EN_B,
-		     mask_vlan ? 1 : 0);
+	hnae3_set_bit(req->vlan_mask, HCLGE_VLAN_MASK_EN_B,
+		      mask_vlan ? 1 : 0);
 	ether_addr_copy(req->mac_mask, mac_mask);
 
 	status = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -2341,13 +2307,11 @@ static int hclge_mac_init(struct hclge_dev *hdev)
 		mtu = ETH_DATA_LEN;
 
 	ret = hclge_set_mtu(handle, mtu);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"set mtu failed ret=%d\n", ret);
-		return ret;
-	}
 
-	return 0;
+	return ret;
 }
 
 static void hclge_mbx_task_schedule(struct hclge_dev *hdev)
@@ -2386,7 +2350,7 @@ static int hclge_get_mac_link_status(struct hclge_dev *hdev)
 	}
 
 	req = (struct hclge_link_status_cmd *)desc.data;
-	link_status = req->status & HCLGE_LINK_STATUS;
+	link_status = req->status & HCLGE_LINK_STATUS_UP_M;
 
 	return !!link_status;
 }
@@ -2505,7 +2469,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 	u32 cmdq_src_reg;
 
 	/* fetch the events from their corresponding regs */
-	rst_src_reg = hclge_read_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG);
+	rst_src_reg = hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS);
 	cmdq_src_reg = hclge_read_dev(&hdev->hw, HCLGE_VECTOR0_CMDQ_SRC_REG);
 
 	/* Assumption: If by any chance reset and mailbox events are reported
@@ -2517,12 +2481,14 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 
 	/* check for vector0 reset event sources */
 	if (BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B) & rst_src_reg) {
+		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 		set_bit(HNAE3_GLOBAL_RESET, &hdev->reset_pending);
 		*clearval = BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B);
 		return HCLGE_VECTOR0_EVENT_RST;
 	}
 
 	if (BIT(HCLGE_VECTOR0_CORERESET_INT_B) & rst_src_reg) {
+		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 		set_bit(HNAE3_CORE_RESET, &hdev->reset_pending);
 		*clearval = BIT(HCLGE_VECTOR0_CORERESET_INT_B);
 		return HCLGE_VECTOR0_EVENT_RST;
@@ -2614,6 +2580,12 @@ static irqreturn_t hclge_misc_irq_handle(int irq, void *data)
 
 static void hclge_free_vector(struct hclge_dev *hdev, int vector_id)
 {
+	if (hdev->vector_status[vector_id] == HCLGE_INVALID_VPORT) {
+		dev_warn(&hdev->pdev->dev,
+			 "vector(vector_id %d) has been freed.\n", vector_id);
+		return;
+	}
+
 	hdev->vector_status[vector_id] = HCLGE_INVALID_VPORT;
 	hdev->num_msi_left += 1;
 	hdev->num_msi_used -= 1;
@@ -2705,7 +2677,7 @@ static int hclge_reset_wait(struct hclge_dev *hdev)
 	}
 
 	val = hclge_read_dev(&hdev->hw, reg);
-	while (hnae_get_bit(val, reg_bit) && cnt < HCLGE_RESET_WAIT_CNT) {
+	while (hnae3_get_bit(val, reg_bit) && cnt < HCLGE_RESET_WAIT_CNT) {
 		msleep(HCLGE_RESET_WATI_MS);
 		val = hclge_read_dev(&hdev->hw, reg);
 		cnt++;
@@ -2727,8 +2699,7 @@ int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id)
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_RST_TRIGGER, false);
-	hnae_set_bit(req->mac_func_reset, HCLGE_CFG_RESET_MAC_B, 0);
-	hnae_set_bit(req->mac_func_reset, HCLGE_CFG_RESET_FUNC_B, 1);
+	hnae3_set_bit(req->mac_func_reset, HCLGE_CFG_RESET_FUNC_B, 1);
 	req->fun_reset_vfid = func_id;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -2747,13 +2718,13 @@ static void hclge_do_reset(struct hclge_dev *hdev)
 	switch (hdev->reset_type) {
 	case HNAE3_GLOBAL_RESET:
 		val = hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG);
-		hnae_set_bit(val, HCLGE_GLOBAL_RESET_BIT, 1);
+		hnae3_set_bit(val, HCLGE_GLOBAL_RESET_BIT, 1);
 		hclge_write_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG, val);
 		dev_info(&pdev->dev, "Global Reset requested\n");
 		break;
 	case HNAE3_CORE_RESET:
 		val = hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG);
-		hnae_set_bit(val, HCLGE_CORE_RESET_BIT, 1);
+		hnae3_set_bit(val, HCLGE_CORE_RESET_BIT, 1);
 		hclge_write_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG, val);
 		dev_info(&pdev->dev, "Core Reset requested\n");
 		break;
@@ -2810,8 +2781,6 @@ static void hclge_clear_reset_cause(struct hclge_dev *hdev)
 		clearval = BIT(HCLGE_VECTOR0_CORERESET_INT_B);
 		break;
 	default:
-		dev_warn(&hdev->pdev->dev, "Unsupported reset event to clear:%d",
-			 hdev->reset_type);
 		break;
 	}
 
@@ -2824,16 +2793,17 @@ static void hclge_clear_reset_cause(struct hclge_dev *hdev)
 
 static void hclge_reset(struct hclge_dev *hdev)
 {
-	/* perform reset of the stack & ae device for a client */
+	struct hnae3_handle *handle;
 
+	/* perform reset of the stack & ae device for a client */
+	handle = &hdev->vport[0].nic;
+	rtnl_lock();
 	hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
 
 	if (!hclge_reset_wait(hdev)) {
-		rtnl_lock();
 		hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
 		hclge_reset_ae_dev(hdev->ae_dev);
 		hclge_notify_client(hdev, HNAE3_INIT_CLIENT);
-		rtnl_unlock();
 
 		hclge_clear_reset_cause(hdev);
 	} else {
@@ -2843,6 +2813,8 @@ static void hclge_reset(struct hclge_dev *hdev)
 	}
 
 	hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+	handle->last_reset_time = jiffies;
+	rtnl_unlock();
 }
 
 static void hclge_reset_event(struct hnae3_handle *handle)
@@ -2855,8 +2827,13 @@ static void hclge_reset_event(struct hnae3_handle *handle)
 	 * know this if last reset request did not occur very recently (watchdog
 	 * timer = 5*HZ, let us check after sufficiently large time, say 4*5*Hz)
 	 * In case of new request we reset the "reset level" to PF reset.
+	 * And if it is a repeat reset request of the most recent one then we
+	 * want to make sure we throttle the reset request. Therefore, we will
+	 * not allow it again before 3*HZ times.
 	 */
-	if (time_after(jiffies, (handle->last_reset_time + 4 * 5 * HZ)))
+	if (time_before(jiffies, (handle->last_reset_time + 3 * HZ)))
+		return;
+	else if (time_after(jiffies, (handle->last_reset_time + 4 * 5 * HZ)))
 		handle->reset_level = HNAE3_FUNC_RESET;
 
 	dev_info(&hdev->pdev->dev, "received reset event , reset type is %d",
@@ -2868,8 +2845,6 @@ static void hclge_reset_event(struct hnae3_handle *handle)
 
 	if (handle->reset_level < HNAE3_GLOBAL_RESET)
 		handle->reset_level++;
-
-	handle->last_reset_time = jiffies;
 }
 
 static void hclge_reset_subtask(struct hclge_dev *hdev)
@@ -3110,23 +3085,21 @@ static int hclge_set_rss_tc_mode(struct hclge_dev *hdev, u16 *tc_valid,
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
 		u16 mode = 0;
 
-		hnae_set_bit(mode, HCLGE_RSS_TC_VALID_B, (tc_valid[i] & 0x1));
-		hnae_set_field(mode, HCLGE_RSS_TC_SIZE_M,
-			       HCLGE_RSS_TC_SIZE_S, tc_size[i]);
-		hnae_set_field(mode, HCLGE_RSS_TC_OFFSET_M,
-			       HCLGE_RSS_TC_OFFSET_S, tc_offset[i]);
+		hnae3_set_bit(mode, HCLGE_RSS_TC_VALID_B, (tc_valid[i] & 0x1));
+		hnae3_set_field(mode, HCLGE_RSS_TC_SIZE_M,
+				HCLGE_RSS_TC_SIZE_S, tc_size[i]);
+		hnae3_set_field(mode, HCLGE_RSS_TC_OFFSET_M,
+				HCLGE_RSS_TC_OFFSET_S, tc_offset[i]);
 
 		req->rss_tc_mode[i] = cpu_to_le16(mode);
 	}
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"Configure rss tc mode fail, status = %d\n", ret);
-		return ret;
-	}
 
-	return 0;
+	return ret;
 }
 
 static int hclge_set_rss_input_tuple(struct hclge_dev *hdev)
@@ -3149,13 +3122,10 @@ static int hclge_set_rss_input_tuple(struct hclge_dev *hdev)
 	req->ipv6_sctp_en = hdev->vport[0].rss_tuple_sets.ipv6_sctp_en;
 	req->ipv6_fragment_en = hdev->vport[0].rss_tuple_sets.ipv6_fragment_en;
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"Configure rss input fail, status = %d\n", ret);
-		return ret;
-	}
-
-	return 0;
+	return ret;
 }
 
 static int hclge_get_rss(struct hnae3_handle *handle, u32 *indir,
@@ -3491,16 +3461,16 @@ int hclge_bind_ring_with_vector(struct hclge_vport *vport,
 	i = 0;
 	for (node = ring_chain; node; node = node->next) {
 		tqp_type_and_id = le16_to_cpu(req->tqp_type_and_id[i]);
-		hnae_set_field(tqp_type_and_id,  HCLGE_INT_TYPE_M,
-			       HCLGE_INT_TYPE_S,
-			       hnae_get_bit(node->flag, HNAE3_RING_TYPE_B));
-		hnae_set_field(tqp_type_and_id, HCLGE_TQP_ID_M,
-			       HCLGE_TQP_ID_S, node->tqp_index);
-		hnae_set_field(tqp_type_and_id, HCLGE_INT_GL_IDX_M,
-			       HCLGE_INT_GL_IDX_S,
-			       hnae_get_field(node->int_gl_idx,
-					      HNAE3_RING_GL_IDX_M,
-					      HNAE3_RING_GL_IDX_S));
+		hnae3_set_field(tqp_type_and_id,  HCLGE_INT_TYPE_M,
+				HCLGE_INT_TYPE_S,
+				hnae3_get_bit(node->flag, HNAE3_RING_TYPE_B));
+		hnae3_set_field(tqp_type_and_id, HCLGE_TQP_ID_M,
+				HCLGE_TQP_ID_S, node->tqp_index);
+		hnae3_set_field(tqp_type_and_id, HCLGE_INT_GL_IDX_M,
+				HCLGE_INT_GL_IDX_S,
+				hnae3_get_field(node->int_gl_idx,
+						HNAE3_RING_GL_IDX_M,
+						HNAE3_RING_GL_IDX_S));
 		req->tqp_type_and_id[i] = cpu_to_le16(tqp_type_and_id);
 		if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) {
 			req->int_cause_num = HCLGE_VECTOR_ELEMENTS_PER_CMD;
@@ -3603,12 +3573,11 @@ int hclge_cmd_set_promisc_mode(struct hclge_dev *hdev,
 		HCLGE_PROMISC_TX_EN_B | HCLGE_PROMISC_RX_EN_B;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"Set promisc mode fail, status is %d.\n", ret);
-		return ret;
-	}
-	return 0;
+
+	return ret;
 }
 
 void hclge_promisc_param_init(struct hclge_promisc_param *param, bool en_uc,
@@ -3648,20 +3617,20 @@ static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable)
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAC_MODE, false);
-	hnae_set_bit(loop_en, HCLGE_MAC_TX_EN_B, enable);
-	hnae_set_bit(loop_en, HCLGE_MAC_RX_EN_B, enable);
-	hnae_set_bit(loop_en, HCLGE_MAC_PAD_TX_B, enable);
-	hnae_set_bit(loop_en, HCLGE_MAC_PAD_RX_B, enable);
-	hnae_set_bit(loop_en, HCLGE_MAC_1588_TX_B, 0);
-	hnae_set_bit(loop_en, HCLGE_MAC_1588_RX_B, 0);
-	hnae_set_bit(loop_en, HCLGE_MAC_APP_LP_B, 0);
-	hnae_set_bit(loop_en, HCLGE_MAC_LINE_LP_B, 0);
-	hnae_set_bit(loop_en, HCLGE_MAC_FCS_TX_B, enable);
-	hnae_set_bit(loop_en, HCLGE_MAC_RX_FCS_B, enable);
-	hnae_set_bit(loop_en, HCLGE_MAC_RX_FCS_STRIP_B, enable);
-	hnae_set_bit(loop_en, HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B, enable);
-	hnae_set_bit(loop_en, HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B, enable);
-	hnae_set_bit(loop_en, HCLGE_MAC_TX_UNDER_MIN_ERR_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_TX_EN_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_RX_EN_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_PAD_TX_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_PAD_RX_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_1588_TX_B, 0);
+	hnae3_set_bit(loop_en, HCLGE_MAC_1588_RX_B, 0);
+	hnae3_set_bit(loop_en, HCLGE_MAC_APP_LP_B, 0);
+	hnae3_set_bit(loop_en, HCLGE_MAC_LINE_LP_B, 0);
+	hnae3_set_bit(loop_en, HCLGE_MAC_FCS_TX_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_RX_FCS_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_RX_FCS_STRIP_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_TX_UNDER_MIN_ERR_B, enable);
 	req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -3689,7 +3658,7 @@ static int hclge_set_mac_loopback(struct hclge_dev *hdev, bool en)
 
 	/* 2 Then setup the loopback flag */
 	loop_en = le32_to_cpu(req->txrx_pad_fcs_loop_en);
-	hnae_set_bit(loop_en, HCLGE_MAC_APP_LP_B, en ? 1 : 0);
+	hnae3_set_bit(loop_en, HCLGE_MAC_APP_LP_B, en ? 1 : 0);
 
 	req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en);
 
@@ -3704,6 +3673,55 @@ static int hclge_set_mac_loopback(struct hclge_dev *hdev, bool en)
 	return ret;
 }
 
+static int hclge_set_serdes_loopback(struct hclge_dev *hdev, bool en)
+{
+#define HCLGE_SERDES_RETRY_MS	10
+#define HCLGE_SERDES_RETRY_NUM	100
+	struct hclge_serdes_lb_cmd *req;
+	struct hclge_desc desc;
+	int ret, i = 0;
+
+	req = (struct hclge_serdes_lb_cmd *)&desc.data[0];
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_SERDES_LOOPBACK, false);
+
+	if (en) {
+		req->enable = HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B;
+		req->mask = HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B;
+	} else {
+		req->mask = HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B;
+	}
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"serdes loopback set fail, ret = %d\n", ret);
+		return ret;
+	}
+
+	do {
+		msleep(HCLGE_SERDES_RETRY_MS);
+		hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_SERDES_LOOPBACK,
+					   true);
+		ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"serdes loopback get, ret = %d\n", ret);
+			return ret;
+		}
+	} while (++i < HCLGE_SERDES_RETRY_NUM &&
+		 !(req->result & HCLGE_CMD_SERDES_DONE_B));
+
+	if (!(req->result & HCLGE_CMD_SERDES_DONE_B)) {
+		dev_err(&hdev->pdev->dev, "serdes loopback set timeout\n");
+		return -EBUSY;
+	} else if (!(req->result & HCLGE_CMD_SERDES_SUCCESS_B)) {
+		dev_err(&hdev->pdev->dev, "serdes loopback set failed in fw\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
 static int hclge_set_loopback(struct hnae3_handle *handle,
 			      enum hnae3_loop loop_mode, bool en)
 {
@@ -3715,6 +3733,9 @@ static int hclge_set_loopback(struct hnae3_handle *handle,
 	case HNAE3_MAC_INTER_LOOP_MAC:
 		ret = hclge_set_mac_loopback(hdev, en);
 		break;
+	case HNAE3_MAC_INTER_LOOP_SERDES:
+		ret = hclge_set_serdes_loopback(hdev, en);
+		break;
 	default:
 		ret = -ENOTSUPP;
 		dev_err(&hdev->pdev->dev,
@@ -3763,7 +3784,7 @@ static int hclge_ae_start(struct hnae3_handle *handle)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
-	int i, ret;
+	int i;
 
 	for (i = 0; i < vport->alloc_tqps; i++)
 		hclge_tqp_enable(hdev, i, 0, true);
@@ -3777,9 +3798,7 @@ static int hclge_ae_start(struct hnae3_handle *handle)
 	/* reset tqp stats */
 	hclge_reset_tqp_stats(handle);
 
-	ret = hclge_mac_start_phy(hdev);
-	if (ret)
-		return ret;
+	hclge_mac_start_phy(hdev);
 
 	return 0;
 }
@@ -3911,7 +3930,7 @@ static bool hclge_is_all_function_id_zero(struct hclge_desc *desc)
 #define HCLGE_FUNC_NUMBER_PER_DESC 6
 	int i, j;
 
-	for (i = 0; i < HCLGE_DESC_NUMBER; i++)
+	for (i = 1; i < HCLGE_DESC_NUMBER; i++)
 		for (j = 0; j < HCLGE_FUNC_NUMBER_PER_DESC; j++)
 			if (desc[i].data[j])
 				return false;
@@ -3953,20 +3972,18 @@ static int hclge_set_mta_filter_mode(struct hclge_dev *hdev,
 	req = (struct hclge_mta_filter_mode_cmd *)desc.data;
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_MODE_CFG, false);
 
-	hnae_set_bit(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_EN_B,
-		     enable);
-	hnae_set_field(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_SEL_M,
-		       HCLGE_CFG_MTA_MAC_SEL_S, mta_mac_sel);
+	hnae3_set_bit(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_EN_B,
+		      enable);
+	hnae3_set_field(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_SEL_M,
+			HCLGE_CFG_MTA_MAC_SEL_S, mta_mac_sel);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"Config mat filter mode failed for cmd_send, ret =%d.\n",
 			ret);
-		return ret;
-	}
 
-	return 0;
+	return ret;
 }
 
 int hclge_cfg_func_mta_filter(struct hclge_dev *hdev,
@@ -3980,19 +3997,17 @@ int hclge_cfg_func_mta_filter(struct hclge_dev *hdev,
 	req = (struct hclge_cfg_func_mta_filter_cmd *)desc.data;
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_FUNC_CFG, false);
 
-	hnae_set_bit(req->accept, HCLGE_CFG_FUNC_MTA_ACCEPT_B,
-		     enable);
+	hnae3_set_bit(req->accept, HCLGE_CFG_FUNC_MTA_ACCEPT_B,
+		      enable);
 	req->function_id = func_id;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"Config func_id enable failed for cmd_send, ret =%d.\n",
 			ret);
-		return ret;
-	}
 
-	return 0;
+	return ret;
 }
 
 static int hclge_set_mta_table_item(struct hclge_vport *vport,
@@ -4007,10 +4022,10 @@ static int hclge_set_mta_table_item(struct hclge_vport *vport,
 
 	req = (struct hclge_cfg_func_mta_item_cmd *)desc.data;
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_TBL_ITEM_CFG, false);
-	hnae_set_bit(req->accept, HCLGE_CFG_MTA_ITEM_ACCEPT_B, enable);
+	hnae3_set_bit(req->accept, HCLGE_CFG_MTA_ITEM_ACCEPT_B, enable);
 
-	hnae_set_field(item_idx, HCLGE_CFG_MTA_ITEM_IDX_M,
-		       HCLGE_CFG_MTA_ITEM_IDX_S, idx);
+	hnae3_set_field(item_idx, HCLGE_CFG_MTA_ITEM_IDX_M,
+			HCLGE_CFG_MTA_ITEM_IDX_S, idx);
 	req->item_idx = cpu_to_le16(item_idx);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -4257,17 +4272,10 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport,
 	}
 
 	memset(&req, 0, sizeof(req));
-	hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
-	hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
-	hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 0);
-	hnae_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
-
-	hnae_set_bit(egress_port, HCLGE_MAC_EPORT_SW_EN_B, 0);
-	hnae_set_bit(egress_port, HCLGE_MAC_EPORT_TYPE_B, 0);
-	hnae_set_field(egress_port, HCLGE_MAC_EPORT_VFID_M,
-		       HCLGE_MAC_EPORT_VFID_S, vport->vport_id);
-	hnae_set_field(egress_port, HCLGE_MAC_EPORT_PFID_M,
-		       HCLGE_MAC_EPORT_PFID_S, 0);
+	hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
+
+	hnae3_set_field(egress_port, HCLGE_MAC_EPORT_VFID_M,
+			HCLGE_MAC_EPORT_VFID_S, vport->vport_id);
 
 	req.egress_port = cpu_to_le16(egress_port);
 
@@ -4318,8 +4326,8 @@ int hclge_rm_uc_addr_common(struct hclge_vport *vport,
 	}
 
 	memset(&req, 0, sizeof(req));
-	hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
-	hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
+	hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
+	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
 	hclge_prepare_mac_addr(&req, addr);
 	ret = hclge_remove_mac_vlan_tbl(vport, &req);
 
@@ -4331,7 +4339,7 @@ static int hclge_add_mc_addr(struct hnae3_handle *handle,
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 
-	return	hclge_add_mc_addr_common(vport, addr);
+	return hclge_add_mc_addr_common(vport, addr);
 }
 
 int hclge_add_mc_addr_common(struct hclge_vport *vport,
@@ -4351,10 +4359,10 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport,
 		return -EINVAL;
 	}
 	memset(&req, 0, sizeof(req));
-	hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
-	hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
-	hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1);
-	hnae_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
+	hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
+	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
+	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1);
+	hnae3_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
 	hclge_prepare_mac_addr(&req, addr);
 	status = hclge_lookup_mac_vlan_tbl(vport, &req, desc, true);
 	if (!status) {
@@ -4418,10 +4426,10 @@ int hclge_rm_mc_addr_common(struct hclge_vport *vport,
 	}
 
 	memset(&req, 0, sizeof(req));
-	hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
-	hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
-	hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1);
-	hnae_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
+	hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
+	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
+	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1);
+	hnae3_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
 	hclge_prepare_mac_addr(&req, addr);
 	status = hclge_lookup_mac_vlan_tbl(vport, &req, desc, true);
 	if (!status) {
@@ -4604,13 +4612,11 @@ static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type,
 	req->vlan_fe = filter_en;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev, "set vlan filter fail, ret =%d.\n",
 			ret);
-		return ret;
-	}
 
-	return 0;
+	return ret;
 }
 
 #define HCLGE_FILTER_TYPE_VF		0
@@ -4802,19 +4808,19 @@ static int hclge_set_vlan_tx_offload_cfg(struct hclge_vport *vport)
 	req = (struct hclge_vport_vtag_tx_cfg_cmd *)desc.data;
 	req->def_vlan_tag1 = cpu_to_le16(vcfg->default_tag1);
 	req->def_vlan_tag2 = cpu_to_le16(vcfg->default_tag2);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_TAG1_B,
-			vcfg->accept_tag1 ? 1 : 0);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_UNTAG1_B,
-			vcfg->accept_untag1 ? 1 : 0);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_TAG2_B,
-			vcfg->accept_tag2 ? 1 : 0);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_UNTAG2_B,
-			vcfg->accept_untag2 ? 1 : 0);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_PORT_INS_TAG1_EN_B,
-		     vcfg->insert_tag1_en ? 1 : 0);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_PORT_INS_TAG2_EN_B,
-		     vcfg->insert_tag2_en ? 1 : 0);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_CFG_NIC_ROCE_SEL_B, 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_TAG1_B,
+		      vcfg->accept_tag1 ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_UNTAG1_B,
+		      vcfg->accept_untag1 ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_TAG2_B,
+		      vcfg->accept_tag2 ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_UNTAG2_B,
+		      vcfg->accept_untag2 ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_PORT_INS_TAG1_EN_B,
+		      vcfg->insert_tag1_en ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_PORT_INS_TAG2_EN_B,
+		      vcfg->insert_tag2_en ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_CFG_NIC_ROCE_SEL_B, 0);
 
 	req->vf_offset = vport->vport_id / HCLGE_VF_NUM_PER_CMD;
 	req->vf_bitmap[req->vf_offset] =
@@ -4840,14 +4846,14 @@ static int hclge_set_vlan_rx_offload_cfg(struct hclge_vport *vport)
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_PORT_RX_CFG, false);
 
 	req = (struct hclge_vport_vtag_rx_cfg_cmd *)desc.data;
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_REM_TAG1_EN_B,
-		     vcfg->strip_tag1_en ? 1 : 0);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_REM_TAG2_EN_B,
-		     vcfg->strip_tag2_en ? 1 : 0);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_SHOW_TAG1_EN_B,
-		     vcfg->vlan1_vlan_prionly ? 1 : 0);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_SHOW_TAG2_EN_B,
-		     vcfg->vlan2_vlan_prionly ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_REM_TAG1_EN_B,
+		      vcfg->strip_tag1_en ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_REM_TAG2_EN_B,
+		      vcfg->strip_tag2_en ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_SHOW_TAG1_EN_B,
+		      vcfg->vlan1_vlan_prionly ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_SHOW_TAG2_EN_B,
+		      vcfg->vlan2_vlan_prionly ? 1 : 0);
 
 	req->vf_offset = vport->vport_id / HCLGE_VF_NUM_PER_CMD;
 	req->vf_bitmap[req->vf_offset] =
@@ -4999,16 +5005,15 @@ static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mtu)
 
 	req = (struct hclge_config_max_frm_size_cmd *)desc.data;
 	req->max_frm_size = cpu_to_le16(max_frm_size);
+	req->min_frm_size = HCLGE_MAC_MIN_FRAME;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev, "set mtu fail, ret =%d.\n", ret);
-		return ret;
-	}
-
-	hdev->mps = max_frm_size;
+	else
+		hdev->mps = max_frm_size;
 
-	return 0;
+	return ret;
 }
 
 static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu)
@@ -5043,7 +5048,7 @@ static int hclge_send_reset_tqp_cmd(struct hclge_dev *hdev, u16 queue_id,
 
 	req = (struct hclge_reset_tqp_queue_cmd *)desc.data;
 	req->tqp_id = cpu_to_le16(queue_id & HCLGE_RING_ID_MASK);
-	hnae_set_bit(req->reset_req, HCLGE_TQP_RESET_B, enable);
+	hnae3_set_bit(req->reset_req, HCLGE_TQP_RESET_B, enable);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
@@ -5073,7 +5078,7 @@ static int hclge_get_reset_status(struct hclge_dev *hdev, u16 queue_id)
 		return ret;
 	}
 
-	return hnae_get_bit(req->ready_to_reset, HCLGE_TQP_RESET_B);
+	return hnae3_get_bit(req->ready_to_reset, HCLGE_TQP_RESET_B);
 }
 
 static u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle,
@@ -5380,12 +5385,12 @@ static void hclge_get_mdix_mode(struct hnae3_handle *handle,
 	phy_write(phydev, HCLGE_PHY_PAGE_REG, HCLGE_PHY_PAGE_MDIX);
 
 	retval = phy_read(phydev, HCLGE_PHY_CSC_REG);
-	mdix_ctrl = hnae_get_field(retval, HCLGE_PHY_MDIX_CTRL_M,
-				   HCLGE_PHY_MDIX_CTRL_S);
+	mdix_ctrl = hnae3_get_field(retval, HCLGE_PHY_MDIX_CTRL_M,
+				    HCLGE_PHY_MDIX_CTRL_S);
 
 	retval = phy_read(phydev, HCLGE_PHY_CSS_REG);
-	mdix = hnae_get_bit(retval, HCLGE_PHY_MDIX_STATUS_B);
-	is_resolved = hnae_get_bit(retval, HCLGE_PHY_SPEED_DUP_RESOLVE_B);
+	mdix = hnae3_get_bit(retval, HCLGE_PHY_MDIX_STATUS_B);
+	is_resolved = hnae3_get_bit(retval, HCLGE_PHY_SPEED_DUP_RESOLVE_B);
 
 	phy_write(phydev, HCLGE_PHY_PAGE_REG, HCLGE_PHY_PAGE_COPPER);
 
@@ -5412,6 +5417,16 @@ static void hclge_get_mdix_mode(struct hnae3_handle *handle,
 		*tp_mdix = ETH_TP_MDI;
 }
 
+static int hclge_init_instance_hw(struct hclge_dev *hdev)
+{
+	return hclge_mac_connect_phy(hdev);
+}
+
+static void hclge_uninit_instance_hw(struct hclge_dev *hdev)
+{
+	hclge_mac_disconnect_phy(hdev);
+}
+
 static int hclge_init_client_instance(struct hnae3_client *client,
 				      struct hnae3_ae_dev *ae_dev)
 {
@@ -5431,6 +5446,13 @@ static int hclge_init_client_instance(struct hnae3_client *client,
 			if (ret)
 				return ret;
 
+			ret = hclge_init_instance_hw(hdev);
+			if (ret) {
+			        client->ops->uninit_instance(&vport->nic,
+			                                     0);
+			        return ret;
+			}
+
 			if (hdev->roce_client &&
 			    hnae3_dev_roce_supported(hdev)) {
 				struct hnae3_client *rc = hdev->roce_client;
@@ -5493,6 +5515,7 @@ static void hclge_uninit_client_instance(struct hnae3_client *client,
 		if (client->type == HNAE3_CLIENT_ROCE)
 			return;
 		if (client->ops->uninit_instance) {
+			hclge_uninit_instance_hw(hdev);
 			client->ops->uninit_instance(&vport->nic, 0);
 			hdev->nic_client = NULL;
 			vport->nic.client = NULL;
@@ -5531,7 +5554,6 @@ static int hclge_pci_init(struct hclge_dev *hdev)
 
 	pci_set_master(pdev);
 	hw = &hdev->hw;
-	hw->back = hdev;
 	hw->io_base = pcim_iomap(pdev, 2, 0);
 	if (!hw->io_base) {
 		dev_err(&pdev->dev, "Can't map configuration register space\n");
@@ -5562,6 +5584,30 @@ static void hclge_pci_uninit(struct hclge_dev *hdev)
 	pci_disable_device(pdev);
 }
 
+static void hclge_state_init(struct hclge_dev *hdev)
+{
+	set_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state);
+	set_bit(HCLGE_STATE_DOWN, &hdev->state);
+	clear_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state);
+	clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state);
+	clear_bit(HCLGE_STATE_MBX_SERVICE_SCHED, &hdev->state);
+	clear_bit(HCLGE_STATE_MBX_HANDLING, &hdev->state);
+}
+
+static void hclge_state_uninit(struct hclge_dev *hdev)
+{
+	set_bit(HCLGE_STATE_DOWN, &hdev->state);
+
+	if (hdev->service_timer.function)
+		del_timer_sync(&hdev->service_timer);
+	if (hdev->service_task.func)
+		cancel_work_sync(&hdev->service_task);
+	if (hdev->rst_service_task.func)
+		cancel_work_sync(&hdev->rst_service_task);
+	if (hdev->mbx_service_task.func)
+		cancel_work_sync(&hdev->mbx_service_task);
+}
+
 static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 {
 	struct pci_dev *pdev = ae_dev->pdev;
@@ -5577,8 +5623,6 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hdev->pdev = pdev;
 	hdev->ae_dev = ae_dev;
 	hdev->reset_type = HNAE3_NONE_RESET;
-	hdev->reset_request = 0;
-	hdev->reset_pending = 0;
 	ae_dev->priv = hdev;
 
 	ret = hclge_pci_init(hdev);
@@ -5702,12 +5746,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	/* Enable MISC vector(vector0) */
 	hclge_enable_vector(&hdev->misc_vector, true);
 
-	set_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state);
-	set_bit(HCLGE_STATE_DOWN, &hdev->state);
-	clear_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state);
-	clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state);
-	clear_bit(HCLGE_STATE_MBX_SERVICE_SCHED, &hdev->state);
-	clear_bit(HCLGE_STATE_MBX_HANDLING, &hdev->state);
+	hclge_state_init(hdev);
 
 	pr_info("%s driver initialization finished.\n", HCLGE_DRIVER_NAME);
 	return 0;
@@ -5812,16 +5851,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 	struct hclge_dev *hdev = ae_dev->priv;
 	struct hclge_mac *mac = &hdev->hw.mac;
 
-	set_bit(HCLGE_STATE_DOWN, &hdev->state);
-
-	if (hdev->service_timer.function)
-		del_timer_sync(&hdev->service_timer);
-	if (hdev->service_task.func)
-		cancel_work_sync(&hdev->service_task);
-	if (hdev->rst_service_task.func)
-		cancel_work_sync(&hdev->rst_service_task);
-	if (hdev->mbx_service_task.func)
-		cancel_work_sync(&hdev->mbx_service_task);
+	hclge_state_uninit(hdev);
 
 	if (mac->phydev)
 		mdiobus_unregister(mac->mdio_bus);
@@ -5905,9 +5935,10 @@ static int hclge_set_channels(struct hnae3_handle *handle, u32 new_tqps_num)
 	u32 *rss_indir;
 	int ret, i;
 
+	/* Free old tqps, and reallocate with new tqp number when nic setup */
 	hclge_release_tqp(vport);
 
-	ret = hclge_knic_setup(vport, new_tqps_num);
+	ret = hclge_knic_setup(vport, new_tqps_num, kinfo->num_desc);
 	if (ret) {
 		dev_err(&hdev->pdev->dev, "setup nic fail, ret =%d\n", ret);
 		return ret;
@@ -6149,8 +6180,8 @@ static int hclge_set_led_status(struct hclge_dev *hdev, u8 locate_led_status)
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_LED_STATUS_CFG, false);
 
 	req = (struct hclge_set_led_state_cmd *)desc.data;
-	hnae_set_field(req->locate_led_config, HCLGE_LED_LOCATE_STATE_M,
-		       HCLGE_LED_LOCATE_STATE_S, locate_led_status);
+	hnae3_set_field(req->locate_led_config, HCLGE_LED_LOCATE_STATE_M,
+			HCLGE_LED_LOCATE_STATE_S, locate_led_status);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret)
@@ -6280,7 +6311,6 @@ static const struct hnae3_ae_ops hclge_ops = {
 
 static struct hnae3_ae_algo ae_algo = {
 	.ops = &hclge_ops,
-	.name = HCLGE_NAME,
 	.pdev_id_table = ae_algo_pci_tbl,
 };
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 7488534528cd..1528fb3fa6be 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016~2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_MAIN_H
 #define __HCLGE_MAIN_H
@@ -22,8 +16,6 @@
 
 #define HCLGE_INVALID_VPORT 0xffff
 
-#define HCLGE_ROCE_VECTOR_OFFSET	96
-
 #define HCLGE_PF_CFG_BLOCK_SIZE		32
 #define HCLGE_PF_CFG_DESC_NUM \
 	(HCLGE_PF_CFG_BLOCK_SIZE / HCLGE_CFG_RD_LEN_BYTES)
@@ -40,7 +32,7 @@
 #define HCLGE_RSS_HASH_ALGO_TOEPLITZ	0
 #define HCLGE_RSS_HASH_ALGO_SIMPLE	1
 #define HCLGE_RSS_HASH_ALGO_SYMMETRIC	2
-#define HCLGE_RSS_HASH_ALGO_MASK	0xf
+#define HCLGE_RSS_HASH_ALGO_MASK	GENMASK(3, 0)
 #define HCLGE_RSS_CFG_TBL_NUM \
 	(HCLGE_RSS_IND_TBL_SIZE / HCLGE_RSS_CFG_TBL_SIZE)
 
@@ -77,11 +69,11 @@
 /* Copper Specific Status Register */
 #define HCLGE_PHY_CSS_REG		17
 
-#define HCLGE_PHY_MDIX_CTRL_S		(5)
+#define HCLGE_PHY_MDIX_CTRL_S		5
 #define HCLGE_PHY_MDIX_CTRL_M		GENMASK(6, 5)
 
-#define HCLGE_PHY_MDIX_STATUS_B	(6)
-#define HCLGE_PHY_SPEED_DUP_RESOLVE_B	(11)
+#define HCLGE_PHY_MDIX_STATUS_B		6
+#define HCLGE_PHY_SPEED_DUP_RESOLVE_B	11
 
 /* Factor used to calculate offset and bitmap of VF num */
 #define HCLGE_VF_NUM_PER_CMD           64
@@ -89,9 +81,10 @@
 
 /* Reset related Registers */
 #define HCLGE_MISC_RESET_STS_REG	0x20700
+#define HCLGE_MISC_VECTOR_INT_STS	0x20800
 #define HCLGE_GLOBAL_RESET_REG		0x20A00
-#define HCLGE_GLOBAL_RESET_BIT		0x0
-#define HCLGE_CORE_RESET_BIT		0x1
+#define HCLGE_GLOBAL_RESET_BIT		0
+#define HCLGE_CORE_RESET_BIT		1
 #define HCLGE_FUN_RST_ING		0x20C00
 #define HCLGE_FUN_RST_ING_B		0
 
@@ -128,6 +121,7 @@ enum HCLGE_DEV_STATE {
 	HCLGE_STATE_MBX_SERVICE_SCHED,
 	HCLGE_STATE_MBX_HANDLING,
 	HCLGE_STATE_STATISTICS_UPDATING,
+	HCLGE_STATE_CMD_DISABLE,
 	HCLGE_STATE_MAX
 };
 
@@ -138,12 +132,6 @@ enum hclge_evt_cause {
 };
 
 #define HCLGE_MPF_ENBALE 1
-struct hclge_caps {
-	u16 num_tqp;
-	u16 num_buffer_cell;
-	u32 flag;
-	u16 vmdq;
-};
 
 enum HCLGE_MAC_SPEED {
 	HCLGE_MAC_SPEED_10M	= 10,		/* 10 Mbps */
@@ -189,8 +177,6 @@ struct hclge_hw {
 	struct hclge_mac mac;
 	int num_vec;
 	struct hclge_cmq cmq;
-	struct hclge_caps caps;
-	void *back;
 };
 
 /* TQP stats */
@@ -202,7 +188,10 @@ struct hlcge_tqp_stats {
 };
 
 struct hclge_tqp {
-	struct device *dev;	/* Device for DMA mapping */
+	/* copy of device pointer from pci_dev,
+	 * used when perform DMA mapping
+	 */
+	struct device *dev;
 	struct hnae3_queue q;
 	struct hlcge_tqp_stats tqp_stats;
 	u16 index;	/* Global index in a NIC controller */
@@ -492,13 +481,11 @@ struct hclge_dev {
 	u16 num_tqps;			/* Num task queue pairs of this PF */
 	u16 num_req_vfs;		/* Num VFs requested for this PF */
 
-	/* Base task tqp physical id of this PF */
-	u16 base_tqp_pid;
+	u16 base_tqp_pid;	/* Base task tqp physical id of this PF */
 	u16 alloc_rss_size;		/* Allocated RSS task queue */
 	u16 rss_size_max;		/* HW defined max RSS task queue */
 
-	/* Num of guaranteed filters for this PF */
-	u16 fdir_pf_filter_count;
+	u16 fdir_pf_filter_count; /* Num of guaranteed filters for this PF */
 	u16 num_alloc_vport;		/* Num vports this driver supports */
 	u32 numa_node_mask;
 	u16 rx_buf_len;
@@ -520,6 +507,7 @@ struct hclge_dev {
 	u16 num_msi;
 	u16 num_msi_left;
 	u16 num_msi_used;
+	u16 roce_base_msix_offset;
 	u32 base_msi_vector;
 	u16 *vector_status;
 	int *vector_irq;
@@ -560,7 +548,7 @@ struct hclge_dev {
 	u32 mps; /* Max packet size */
 
 	enum hclge_mta_dmac_sel_type mta_mac_sel_type;
-	bool enable_mta; /* Mutilcast filter enable */
+	bool enable_mta; /* Multicast filter enable */
 
 	struct hclge_vlan_type_cfg vlan_type_cfg;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index 7541cb9b71ce..f34851c91eb3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -104,13 +104,15 @@ static void hclge_free_vector_ring_chain(struct hnae3_ring_chain_node *head)
 	}
 }
 
-/* hclge_get_ring_chain_from_mbx: get ring type & tqpid from mailbox message
+/* hclge_get_ring_chain_from_mbx: get ring type & tqp id & int_gl idx
+ * from mailbox message
  * msg[0]: opcode
  * msg[1]: <not relevant to this function>
  * msg[2]: ring_num
  * msg[3]: first ring type (TX|RX)
  * msg[4]: first tqp id
- * msg[5] ~ msg[14]: other ring type and tqp id
+ * msg[5]: first int_gl idx
+ * msg[6] ~ msg[14]: other ring type, tqp id and int_gl idx
  */
 static int hclge_get_ring_chain_from_mbx(
 			struct hclge_mbx_vf_to_pf_cmd *req,
@@ -128,12 +130,12 @@ static int hclge_get_ring_chain_from_mbx(
 		HCLGE_MBX_RING_NODE_VARIABLE_NUM))
 		return -ENOMEM;
 
-	hnae_set_bit(ring_chain->flag, HNAE3_RING_TYPE_B, req->msg[3]);
+	hnae3_set_bit(ring_chain->flag, HNAE3_RING_TYPE_B, req->msg[3]);
 	ring_chain->tqp_index =
 			hclge_get_queue_id(vport->nic.kinfo.tqp[req->msg[4]]);
-	hnae_set_field(ring_chain->int_gl_idx, HCLGE_INT_GL_IDX_M,
-		       HCLGE_INT_GL_IDX_S,
-		       req->msg[5]);
+	hnae3_set_field(ring_chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
+			HNAE3_RING_GL_IDX_S,
+			req->msg[5]);
 
 	cur_chain = ring_chain;
 
@@ -142,19 +144,19 @@ static int hclge_get_ring_chain_from_mbx(
 		if (!new_chain)
 			goto err;
 
-		hnae_set_bit(new_chain->flag, HNAE3_RING_TYPE_B,
-			     req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i +
-			     HCLGE_MBX_RING_MAP_BASIC_MSG_NUM]);
+		hnae3_set_bit(new_chain->flag, HNAE3_RING_TYPE_B,
+			      req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i +
+			      HCLGE_MBX_RING_MAP_BASIC_MSG_NUM]);
 
 		new_chain->tqp_index =
 		hclge_get_queue_id(vport->nic.kinfo.tqp
 			[req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i +
 			HCLGE_MBX_RING_MAP_BASIC_MSG_NUM + 1]]);
 
-		hnae_set_field(new_chain->int_gl_idx, HCLGE_INT_GL_IDX_M,
-			       HCLGE_INT_GL_IDX_S,
-			       req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i +
-			       HCLGE_MBX_RING_MAP_BASIC_MSG_NUM + 2]);
+		hnae3_set_field(new_chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
+				HNAE3_RING_GL_IDX_S,
+				req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i +
+				HCLGE_MBX_RING_MAP_BASIC_MSG_NUM + 2]);
 
 		cur_chain->next = new_chain;
 		cur_chain = new_chain;
@@ -460,7 +462,7 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 		req = (struct hclge_mbx_vf_to_pf_cmd *)desc->data;
 
 		flag = le16_to_cpu(crq->desc[crq->next_to_use].flag);
-		if (unlikely(!hnae_get_bit(flag, HCLGE_CMDQ_RX_OUTVLD_B))) {
+		if (unlikely(!hnae3_get_bit(flag, HCLGE_CMDQ_RX_OUTVLD_B))) {
 			dev_warn(&hdev->pdev->dev,
 				 "dropped invalid mailbox message, code = %d\n",
 				 req->msg[0]);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
index 9f7932e423b5..398971a062f4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016~2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include <linux/etherdevice.h>
 #include <linux/kernel.h>
@@ -67,16 +61,16 @@ static int hclge_mdio_write(struct mii_bus *bus, int phyid, int regnum,
 
 	mdio_cmd = (struct hclge_mdio_cfg_cmd *)desc.data;
 
-	hnae_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M,
-		       HCLGE_MDIO_PHYID_S, phyid);
-	hnae_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M,
-		       HCLGE_MDIO_PHYREG_S, regnum);
+	hnae3_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M,
+			HCLGE_MDIO_PHYID_S, phyid);
+	hnae3_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M,
+			HCLGE_MDIO_PHYREG_S, regnum);
 
-	hnae_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1);
-	hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M,
-		       HCLGE_MDIO_CTRL_ST_S, 1);
-	hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_OP_M,
-		       HCLGE_MDIO_CTRL_OP_S, HCLGE_MDIO_C22_WRITE);
+	hnae3_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1);
+	hnae3_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M,
+			HCLGE_MDIO_CTRL_ST_S, 1);
+	hnae3_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_OP_M,
+			HCLGE_MDIO_CTRL_OP_S, HCLGE_MDIO_C22_WRITE);
 
 	mdio_cmd->data_wr = cpu_to_le16(data);
 
@@ -105,16 +99,16 @@ static int hclge_mdio_read(struct mii_bus *bus, int phyid, int regnum)
 
 	mdio_cmd = (struct hclge_mdio_cfg_cmd *)desc.data;
 
-	hnae_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M,
-		       HCLGE_MDIO_PHYID_S, phyid);
-	hnae_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M,
-		       HCLGE_MDIO_PHYREG_S, regnum);
+	hnae3_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M,
+			HCLGE_MDIO_PHYID_S, phyid);
+	hnae3_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M,
+			HCLGE_MDIO_PHYREG_S, regnum);
 
-	hnae_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1);
-	hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M,
-		       HCLGE_MDIO_CTRL_ST_S, 1);
-	hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_OP_M,
-		       HCLGE_MDIO_CTRL_OP_S, HCLGE_MDIO_C22_READ);
+	hnae3_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1);
+	hnae3_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M,
+			HCLGE_MDIO_CTRL_ST_S, 1);
+	hnae3_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_OP_M,
+			HCLGE_MDIO_CTRL_OP_S, HCLGE_MDIO_C22_READ);
 
 	/* Read out phy data */
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -125,7 +119,7 @@ static int hclge_mdio_read(struct mii_bus *bus, int phyid, int regnum)
 		return ret;
 	}
 
-	if (hnae_get_bit(le16_to_cpu(mdio_cmd->sta), HCLGE_MDIO_STA_B)) {
+	if (hnae3_get_bit(le16_to_cpu(mdio_cmd->sta), HCLGE_MDIO_STA_B)) {
 		dev_err(&hdev->pdev->dev, "mdio read data error\n");
 		return -EIO;
 	}
@@ -199,7 +193,7 @@ static void hclge_mac_adjust_link(struct net_device *netdev)
 		netdev_err(netdev, "failed to configure flow control.\n");
 }
 
-int hclge_mac_start_phy(struct hclge_dev *hdev)
+int hclge_mac_connect_phy(struct hclge_dev *hdev)
 {
 	struct net_device *netdev = hdev->vport[0].nic.netdev;
 	struct phy_device *phydev = hdev->hw.mac.phydev;
@@ -208,6 +202,8 @@ int hclge_mac_start_phy(struct hclge_dev *hdev)
 	if (!phydev)
 		return 0;
 
+	phydev->supported &= ~SUPPORTED_FIBRE;
+
 	ret = phy_connect_direct(netdev, phydev,
 				 hclge_mac_adjust_link,
 				 PHY_INTERFACE_MODE_SGMII);
@@ -219,11 +215,29 @@ int hclge_mac_start_phy(struct hclge_dev *hdev)
 	phydev->supported &= HCLGE_PHY_SUPPORTED_FEATURES;
 	phydev->advertising = phydev->supported;
 
-	phy_start(phydev);
-
 	return 0;
 }
 
+void hclge_mac_disconnect_phy(struct hclge_dev *hdev)
+{
+	struct phy_device *phydev = hdev->hw.mac.phydev;
+
+	if (!phydev)
+		return;
+
+	phy_disconnect(phydev);
+}
+
+void hclge_mac_start_phy(struct hclge_dev *hdev)
+{
+	struct phy_device *phydev = hdev->hw.mac.phydev;
+
+	if (!phydev)
+		return;
+
+	phy_start(phydev);
+}
+
 void hclge_mac_stop_phy(struct hclge_dev *hdev)
 {
 	struct net_device *netdev = hdev->vport[0].nic.netdev;
@@ -233,5 +247,4 @@ void hclge_mac_stop_phy(struct hclge_dev *hdev)
 		return;
 
 	phy_stop(phydev);
-	phy_disconnect(phydev);
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
index c5e91cfb8f2c..5fbf7dddb5d9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
@@ -1,17 +1,13 @@
-/*
- * Copyright (c) 2016-2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_MDIO_H
 #define __HCLGE_MDIO_H
 
 int hclge_mac_mdio_config(struct hclge_dev *hdev);
-int hclge_mac_start_phy(struct hclge_dev *hdev);
+int hclge_mac_connect_phy(struct hclge_dev *hdev);
+void hclge_mac_disconnect_phy(struct hclge_dev *hdev);
+void hclge_mac_start_phy(struct hclge_dev *hdev);
 void hclge_mac_stop_phy(struct hclge_dev *hdev);
 
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 262c125f8137..5db70a1451c5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016~2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include <linux/etherdevice.h>
 
@@ -1184,10 +1178,10 @@ static int hclge_bp_setup_hw(struct hclge_dev *hdev, u8 tc)
 			u16 qs_id = vport->qs_offset + tc;
 			u8 grp, sub_grp;
 
-			grp = hnae_get_field(qs_id, HCLGE_BP_GRP_ID_M,
-					     HCLGE_BP_GRP_ID_S);
-			sub_grp = hnae_get_field(qs_id, HCLGE_BP_SUB_GRP_ID_M,
-						 HCLGE_BP_SUB_GRP_ID_S);
+			grp = hnae3_get_field(qs_id, HCLGE_BP_GRP_ID_M,
+					      HCLGE_BP_GRP_ID_S);
+			sub_grp = hnae3_get_field(qs_id, HCLGE_BP_SUB_GRP_ID_M,
+						  HCLGE_BP_SUB_GRP_ID_S);
 			if (i == grp)
 				qs_bitmap |= (1 << sub_grp);
 
@@ -1223,6 +1217,10 @@ static int hclge_mac_pause_setup_hw(struct hclge_dev *hdev)
 		tx_en = true;
 		rx_en = true;
 		break;
+	case HCLGE_FC_PFC:
+		tx_en = false;
+		rx_en = false;
+		break;
 	default:
 		tx_en = true;
 		rx_en = true;
@@ -1240,8 +1238,9 @@ int hclge_pause_setup_hw(struct hclge_dev *hdev)
 	if (ret)
 		return ret;
 
-	if (hdev->tm_info.fc_mode != HCLGE_FC_PFC)
-		return hclge_mac_pause_setup_hw(hdev);
+	ret = hclge_mac_pause_setup_hw(hdev);
+	if (ret)
+		return ret;
 
 	/* Only DCB-supported dev supports qset back pressure and pfc cmd */
 	if (!hnae3_dev_dcb_supported(hdev))
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
index c2b6e8a6700f..dd4c194747c1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016~2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_TM_H
 #define __HCLGE_TM_H
@@ -123,10 +117,11 @@ struct hclge_port_shapping_cmd {
 };
 
 #define hclge_tm_set_field(dest, string, val) \
-			hnae_set_field((dest), (HCLGE_TM_SHAP_##string##_MSK), \
-				       (HCLGE_TM_SHAP_##string##_LSH), val)
+			   hnae3_set_field((dest), \
+			   (HCLGE_TM_SHAP_##string##_MSK), \
+			   (HCLGE_TM_SHAP_##string##_LSH), val)
 #define hclge_tm_get_field(src, string) \
-			hnae_get_field((src), (HCLGE_TM_SHAP_##string##_MSK), \
+			hnae3_get_field((src), (HCLGE_TM_SHAP_##string##_MSK), \
 				       (HCLGE_TM_SHAP_##string##_LSH))
 
 int hclge_tm_schd_init(struct hclge_dev *hdev);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
index 1bbfe131b596..fb471fe2c494 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
@@ -76,32 +76,24 @@ static int hclgevf_alloc_cmd_desc(struct hclgevf_cmq_ring *ring)
 {
 	int size = ring->desc_num * sizeof(struct hclgevf_desc);
 
-	ring->desc = kzalloc(size, GFP_KERNEL);
+	ring->desc = dma_zalloc_coherent(cmq_ring_to_dev(ring),
+					 size, &ring->desc_dma_addr,
+					 GFP_KERNEL);
 	if (!ring->desc)
 		return -ENOMEM;
 
-	ring->desc_dma_addr = dma_map_single(cmq_ring_to_dev(ring), ring->desc,
-					     size, DMA_BIDIRECTIONAL);
-
-	if (dma_mapping_error(cmq_ring_to_dev(ring), ring->desc_dma_addr)) {
-		ring->desc_dma_addr = 0;
-		kfree(ring->desc);
-		ring->desc = NULL;
-		return -ENOMEM;
-	}
-
 	return 0;
 }
 
 static void hclgevf_free_cmd_desc(struct hclgevf_cmq_ring *ring)
 {
-	dma_unmap_single(cmq_ring_to_dev(ring), ring->desc_dma_addr,
-			 ring->desc_num * sizeof(ring->desc[0]),
-			 hclgevf_ring_to_dma_dir(ring));
+	int size  = ring->desc_num * sizeof(struct hclgevf_desc);
 
-	ring->desc_dma_addr = 0;
-	kfree(ring->desc);
-	ring->desc = NULL;
+	if (ring->desc) {
+		dma_free_coherent(cmq_ring_to_dev(ring), size,
+				  ring->desc, ring->desc_dma_addr);
+		ring->desc = NULL;
+	}
 }
 
 static int hclgevf_init_cmd_queue(struct hclgevf_dev *hdev,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
index 621c6cbacf76..19b32860309c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
@@ -82,6 +82,7 @@ struct hclgevf_cmq {
 enum hclgevf_opcode_type {
 	/* Generic command */
 	HCLGEVF_OPC_QUERY_FW_VER	= 0x0001,
+	HCLGEVF_OPC_QUERY_VF_RSRC	= 0x0024,
 	/* TQP command */
 	HCLGEVF_OPC_QUERY_TX_STATUS	= 0x0B03,
 	HCLGEVF_OPC_QUERY_RX_STATUS	= 0x0B13,
@@ -134,6 +135,19 @@ struct hclgevf_query_version_cmd {
 	__le32 firmware_rsv[5];
 };
 
+#define HCLGEVF_MSIX_OFT_ROCEE_S       0
+#define HCLGEVF_MSIX_OFT_ROCEE_M       (0xffff << HCLGEVF_MSIX_OFT_ROCEE_S)
+#define HCLGEVF_VEC_NUM_S              0
+#define HCLGEVF_VEC_NUM_M              (0xff << HCLGEVF_VEC_NUM_S)
+struct hclgevf_query_res_cmd {
+	__le16 tqp_num;
+	__le16 reserved;
+	__le16 msixcap_localid_ba_nic;
+	__le16 msixcap_localid_ba_rocee;
+	__le16 vf_intr_vector_number;
+	__le16 rsv[7];
+};
+
 #define HCLGEVF_RSS_HASH_KEY_OFFSET	4
 #define HCLGEVF_RSS_HASH_KEY_NUM	16
 struct hclgevf_rss_config_cmd {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index a17872aab168..9c0091f2addf 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -330,6 +330,12 @@ static int hclgevf_set_handle_info(struct hclgevf_dev *hdev)
 
 static void hclgevf_free_vector(struct hclgevf_dev *hdev, int vector_id)
 {
+	if (hdev->vector_status[vector_id] == HCLGEVF_INVALID_VPORT) {
+		dev_warn(&hdev->pdev->dev,
+			 "vector(vector_id %d) has been freed.\n", vector_id);
+		return;
+	}
+
 	hdev->vector_status[vector_id] = HCLGEVF_INVALID_VPORT;
 	hdev->num_msi_left += 1;
 	hdev->num_msi_used -= 1;
@@ -444,12 +450,12 @@ static int hclgevf_set_rss_tc_mode(struct hclgevf_dev *hdev,  u16 rss_size)
 
 	hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_RSS_TC_MODE, false);
 	for (i = 0; i < HCLGEVF_MAX_TC_NUM; i++) {
-		hnae_set_bit(req->rss_tc_mode[i], HCLGEVF_RSS_TC_VALID_B,
-			     (tc_valid[i] & 0x1));
-		hnae_set_field(req->rss_tc_mode[i], HCLGEVF_RSS_TC_SIZE_M,
-			       HCLGEVF_RSS_TC_SIZE_S, tc_size[i]);
-		hnae_set_field(req->rss_tc_mode[i], HCLGEVF_RSS_TC_OFFSET_M,
-			       HCLGEVF_RSS_TC_OFFSET_S, tc_offset[i]);
+		hnae3_set_bit(req->rss_tc_mode[i], HCLGEVF_RSS_TC_VALID_B,
+			      (tc_valid[i] & 0x1));
+		hnae3_set_field(req->rss_tc_mode[i], HCLGEVF_RSS_TC_SIZE_M,
+				HCLGEVF_RSS_TC_SIZE_S, tc_size[i]);
+		hnae3_set_field(req->rss_tc_mode[i], HCLGEVF_RSS_TC_OFFSET_M,
+				HCLGEVF_RSS_TC_OFFSET_S, tc_offset[i]);
 	}
 	status = hclgevf_cmd_send(&hdev->hw, &desc, 1);
 	if (status)
@@ -547,24 +553,18 @@ static int hclgevf_get_tc_size(struct hnae3_handle *handle)
 }
 
 static int hclgevf_bind_ring_to_vector(struct hnae3_handle *handle, bool en,
-				       int vector,
+				       int vector_id,
 				       struct hnae3_ring_chain_node *ring_chain)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 	struct hnae3_ring_chain_node *node;
 	struct hclge_mbx_vf_to_pf_cmd *req;
 	struct hclgevf_desc desc;
-	int i = 0, vector_id;
+	int i = 0;
 	int status;
 	u8 type;
 
 	req = (struct hclge_mbx_vf_to_pf_cmd *)desc.data;
-	vector_id = hclgevf_get_vector_index(hdev, vector);
-	if (vector_id < 0) {
-		dev_err(&handle->pdev->dev,
-			"Get vector index fail. ret =%d\n", vector_id);
-		return vector_id;
-	}
 
 	for (node = ring_chain; node; node = node->next) {
 		int idx_offset = HCLGE_MBX_RING_MAP_BASIC_MSG_NUM +
@@ -582,11 +582,11 @@ static int hclgevf_bind_ring_to_vector(struct hnae3_handle *handle, bool en,
 		}
 
 		req->msg[idx_offset] =
-				hnae_get_bit(node->flag, HNAE3_RING_TYPE_B);
+				hnae3_get_bit(node->flag, HNAE3_RING_TYPE_B);
 		req->msg[idx_offset + 1] = node->tqp_index;
-		req->msg[idx_offset + 2] = hnae_get_field(node->int_gl_idx,
-							  HNAE3_RING_GL_IDX_M,
-							  HNAE3_RING_GL_IDX_S);
+		req->msg[idx_offset + 2] = hnae3_get_field(node->int_gl_idx,
+							   HNAE3_RING_GL_IDX_M,
+							   HNAE3_RING_GL_IDX_S);
 
 		i++;
 		if ((i == (HCLGE_MBX_VF_MSG_DATA_NUM -
@@ -617,7 +617,17 @@ static int hclgevf_bind_ring_to_vector(struct hnae3_handle *handle, bool en,
 static int hclgevf_map_ring_to_vector(struct hnae3_handle *handle, int vector,
 				      struct hnae3_ring_chain_node *ring_chain)
 {
-	return hclgevf_bind_ring_to_vector(handle, true, vector, ring_chain);
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	int vector_id;
+
+	vector_id = hclgevf_get_vector_index(hdev, vector);
+	if (vector_id < 0) {
+		dev_err(&handle->pdev->dev,
+			"Get vector index fail. ret =%d\n", vector_id);
+		return vector_id;
+	}
+
+	return hclgevf_bind_ring_to_vector(handle, true, vector_id, ring_chain);
 }
 
 static int hclgevf_unmap_ring_from_vector(
@@ -635,7 +645,7 @@ static int hclgevf_unmap_ring_from_vector(
 		return vector_id;
 	}
 
-	ret = hclgevf_bind_ring_to_vector(handle, false, vector, ring_chain);
+	ret = hclgevf_bind_ring_to_vector(handle, false, vector_id, ring_chain);
 	if (ret)
 		dev_err(&handle->pdev->dev,
 			"Unmap ring from vector fail. vector=%d, ret =%d\n",
@@ -648,8 +658,17 @@ static int hclgevf_unmap_ring_from_vector(
 static int hclgevf_put_vector(struct hnae3_handle *handle, int vector)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	int vector_id;
 
-	hclgevf_free_vector(hdev, vector);
+	vector_id = hclgevf_get_vector_index(hdev, vector);
+	if (vector_id < 0) {
+		dev_err(&handle->pdev->dev,
+			"hclgevf_put_vector get vector index fail. ret =%d\n",
+			vector_id);
+		return vector_id;
+	}
+
+	hclgevf_free_vector(hdev, vector_id);
 
 	return 0;
 }
@@ -990,8 +1009,8 @@ static int hclgevf_reset_wait(struct hclgevf_dev *hdev)
 
 	/* wait to check the hardware reset completion status */
 	val = hclgevf_read_dev(&hdev->hw, HCLGEVF_FUN_RST_ING);
-	while (hnae_get_bit(val, HCLGEVF_FUN_RST_ING_B) &&
-			    (cnt < HCLGEVF_RESET_WAIT_CNT)) {
+	while (hnae3_get_bit(val, HCLGEVF_FUN_RST_ING_B) &&
+	       (cnt < HCLGEVF_RESET_WAIT_CNT)) {
 		msleep(HCLGEVF_RESET_WAIT_MS);
 		val = hclgevf_read_dev(&hdev->hw, HCLGEVF_FUN_RST_ING);
 		cnt++;
@@ -1351,14 +1370,13 @@ static int hclgevf_init_roce_base_info(struct hclgevf_dev *hdev)
 	struct hnae3_handle *roce = &hdev->roce;
 	struct hnae3_handle *nic = &hdev->nic;
 
-	roce->rinfo.num_vectors = HCLGEVF_ROCEE_VECTOR_NUM;
+	roce->rinfo.num_vectors = hdev->num_roce_msix;
 
 	if (hdev->num_msi_left < roce->rinfo.num_vectors ||
 	    hdev->num_msi_left == 0)
 		return -EINVAL;
 
-	roce->rinfo.base_vector =
-		hdev->vector_status[hdev->num_msi_used];
+	roce->rinfo.base_vector = hdev->roce_base_vector;
 
 	roce->rinfo.netdev = nic->kinfo.netdev;
 	roce->rinfo.roce_io_base = hdev->hw.io_base;
@@ -1501,10 +1519,15 @@ static int hclgevf_init_msi(struct hclgevf_dev *hdev)
 	if (hclgevf_dev_ongoing_reset(hdev))
 		return 0;
 
-	hdev->num_msi = HCLGEVF_MAX_VF_VECTOR_NUM;
+	if (hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B))
+		vectors = pci_alloc_irq_vectors(pdev,
+						hdev->roce_base_msix_offset + 1,
+						hdev->num_msi,
+						PCI_IRQ_MSIX);
+	else
+		vectors = pci_alloc_irq_vectors(pdev, 1, hdev->num_msi,
+						PCI_IRQ_MSI | PCI_IRQ_MSIX);
 
-	vectors = pci_alloc_irq_vectors(pdev, 1, hdev->num_msi,
-					PCI_IRQ_MSI | PCI_IRQ_MSIX);
 	if (vectors < 0) {
 		dev_err(&pdev->dev,
 			"failed(%d) to allocate MSI/MSI-X vectors\n",
@@ -1519,6 +1542,7 @@ static int hclgevf_init_msi(struct hclgevf_dev *hdev)
 	hdev->num_msi = vectors;
 	hdev->num_msi_left = vectors;
 	hdev->base_msi_vector = pdev->irq;
+	hdev->roce_base_vector = pdev->irq + hdev->roce_base_msix_offset;
 
 	hdev->vector_status = devm_kcalloc(&pdev->dev, hdev->num_msi,
 					   sizeof(u16), GFP_KERNEL);
@@ -1582,9 +1606,10 @@ static void hclgevf_misc_irq_uninit(struct hclgevf_dev *hdev)
 	hclgevf_free_vector(hdev, 0);
 }
 
-static int hclgevf_init_instance(struct hclgevf_dev *hdev,
-				 struct hnae3_client *client)
+static int hclgevf_init_client_instance(struct hnae3_client *client,
+					struct hnae3_ae_dev *ae_dev)
 {
+	struct hclgevf_dev *hdev = ae_dev->priv;
 	int ret;
 
 	switch (client->type) {
@@ -1635,9 +1660,11 @@ static int hclgevf_init_instance(struct hclgevf_dev *hdev,
 	return 0;
 }
 
-static void hclgevf_uninit_instance(struct hclgevf_dev *hdev,
-				    struct hnae3_client *client)
+static void hclgevf_uninit_client_instance(struct hnae3_client *client,
+					   struct hnae3_ae_dev *ae_dev)
 {
+	struct hclgevf_dev *hdev = ae_dev->priv;
+
 	/* un-init roce, if it exists */
 	if (hdev->roce_client)
 		hdev->roce_client->ops->uninit_instance(&hdev->roce, 0);
@@ -1648,22 +1675,6 @@ static void hclgevf_uninit_instance(struct hclgevf_dev *hdev,
 		client->ops->uninit_instance(&hdev->nic, 0);
 }
 
-static int hclgevf_register_client(struct hnae3_client *client,
-				   struct hnae3_ae_dev *ae_dev)
-{
-	struct hclgevf_dev *hdev = ae_dev->priv;
-
-	return hclgevf_init_instance(hdev, client);
-}
-
-static void hclgevf_unregister_client(struct hnae3_client *client,
-				      struct hnae3_ae_dev *ae_dev)
-{
-	struct hclgevf_dev *hdev = ae_dev->priv;
-
-	hclgevf_uninit_instance(hdev, client);
-}
-
 static int hclgevf_pci_init(struct hclgevf_dev *hdev)
 {
 	struct pci_dev *pdev = hdev->pdev;
@@ -1727,6 +1738,45 @@ static void hclgevf_pci_uninit(struct hclgevf_dev *hdev)
 	pci_disable_device(pdev);
 }
 
+static int hclgevf_query_vf_resource(struct hclgevf_dev *hdev)
+{
+	struct hclgevf_query_res_cmd *req;
+	struct hclgevf_desc desc;
+	int ret;
+
+	hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_QUERY_VF_RSRC, true);
+	ret = hclgevf_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"query vf resource failed, ret = %d.\n", ret);
+		return ret;
+	}
+
+	req = (struct hclgevf_query_res_cmd *)desc.data;
+
+	if (hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)) {
+		hdev->roce_base_msix_offset =
+		hnae3_get_field(__le16_to_cpu(req->msixcap_localid_ba_rocee),
+				HCLGEVF_MSIX_OFT_ROCEE_M,
+				HCLGEVF_MSIX_OFT_ROCEE_S);
+		hdev->num_roce_msix =
+		hnae3_get_field(__le16_to_cpu(req->vf_intr_vector_number),
+				HCLGEVF_VEC_NUM_M, HCLGEVF_VEC_NUM_S);
+
+		/* VF should have NIC vectors and Roce vectors, NIC vectors
+		 * are queued before Roce vectors. The offset is fixed to 64.
+		 */
+		hdev->num_msi = hdev->num_roce_msix +
+				hdev->roce_base_msix_offset;
+	} else {
+		hdev->num_msi =
+		hnae3_get_field(__le16_to_cpu(req->vf_intr_vector_number),
+				HCLGEVF_VEC_NUM_M, HCLGEVF_VEC_NUM_S);
+	}
+
+	return 0;
+}
+
 static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 {
 	struct pci_dev *pdev = hdev->pdev;
@@ -1744,18 +1794,26 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		return ret;
 	}
 
+	ret = hclgevf_cmd_init(hdev);
+	if (ret)
+		goto err_cmd_init;
+
+	/* Get vf resource */
+	ret = hclgevf_query_vf_resource(hdev);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Query vf status error, ret = %d.\n", ret);
+		goto err_query_vf;
+	}
+
 	ret = hclgevf_init_msi(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed(%d) to init MSI/MSI-X\n", ret);
-		goto err_irq_init;
+		goto err_query_vf;
 	}
 
 	hclgevf_state_init(hdev);
 
-	ret = hclgevf_cmd_init(hdev);
-	if (ret)
-		goto err_cmd_init;
-
 	ret = hclgevf_misc_irq_init(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed(%d) to init Misc IRQ(vector0)\n",
@@ -1811,11 +1869,11 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 err_config:
 	hclgevf_misc_irq_uninit(hdev);
 err_misc_irq_init:
-	hclgevf_cmd_uninit(hdev);
-err_cmd_init:
 	hclgevf_state_uninit(hdev);
 	hclgevf_uninit_msi(hdev);
-err_irq_init:
+err_query_vf:
+	hclgevf_cmd_uninit(hdev);
+err_cmd_init:
 	hclgevf_pci_uninit(hdev);
 	return ret;
 }
@@ -1924,8 +1982,8 @@ void hclgevf_update_speed_duplex(struct hclgevf_dev *hdev, u32 speed,
 static const struct hnae3_ae_ops hclgevf_ops = {
 	.init_ae_dev = hclgevf_init_ae_dev,
 	.uninit_ae_dev = hclgevf_uninit_ae_dev,
-	.init_client_instance = hclgevf_register_client,
-	.uninit_client_instance = hclgevf_unregister_client,
+	.init_client_instance = hclgevf_init_client_instance,
+	.uninit_client_instance = hclgevf_uninit_client_instance,
 	.start = hclgevf_ae_start,
 	.stop = hclgevf_ae_stop,
 	.map_ring_to_vector = hclgevf_map_ring_to_vector,
@@ -1962,7 +2020,6 @@ static const struct hnae3_ae_ops hclgevf_ops = {
 
 static struct hnae3_ae_algo ae_algovf = {
 	.ops = &hclgevf_ops,
-	.name = HCLGEVF_NAME,
 	.pdev_id_table = ae_algovf_pci_tbl,
 };
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 0656e8e5c5f0..b23ba171473c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -12,7 +12,6 @@
 #define HCLGEVF_MOD_VERSION "1.0"
 #define HCLGEVF_DRIVER_NAME "hclgevf"
 
-#define HCLGEVF_ROCEE_VECTOR_NUM	0
 #define HCLGEVF_MISC_VECTOR_NUM		0
 
 #define HCLGEVF_INVALID_VPORT		0xffff
@@ -150,6 +149,9 @@ struct hclgevf_dev {
 	u16 num_msi;
 	u16 num_msi_left;
 	u16 num_msi_used;
+	u16 num_roce_msix;	/* Num of roce vectors for this VF */
+	u16 roce_base_msix_offset;
+	int roce_base_vector;
 	u32 base_msi_vector;
 	u16 *vector_status;
 	int *vector_irq;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
index b598c06af8e0..e9d5a4f96304 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@@ -152,7 +152,7 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
 		req = (struct hclge_mbx_pf_to_vf_cmd *)desc->data;
 
 		flag = le16_to_cpu(crq->desc[crq->next_to_use].flag);
-		if (unlikely(!hnae_get_bit(flag, HCLGEVF_CMDQ_RX_OUTVLD_B))) {
+		if (unlikely(!hnae3_get_bit(flag, HCLGEVF_CMDQ_RX_OUTVLD_B))) {
 			dev_warn(&hdev->pdev->dev,
 				 "dropped invalid mailbox message, code = %d\n",
 				 req->msg[0]);
@@ -208,7 +208,8 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
 
 			/* tail the async message in arq */
 			msg_q = hdev->arq.msg_q[hdev->arq.tail];
-			memcpy(&msg_q[0], req->msg, HCLGE_MBX_MAX_ARQ_MSG_SIZE);
+			memcpy(&msg_q[0], req->msg,
+			       HCLGE_MBX_MAX_ARQ_MSG_SIZE * sizeof(u16));
 			hclge_mbx_tail_ptr_move_arq(hdev->arq);
 			hdev->arq.count++;
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
index 79b567447084..6b19607a4caa 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
@@ -264,7 +264,6 @@ static int init_fw_ctxt(struct hinic_hwdev *hwdev)
 	struct hinic_hwif *hwif = hwdev->hwif;
 	struct pci_dev *pdev = hwif->pdev;
 	struct hinic_cmd_fw_ctxt fw_ctxt;
-	struct hinic_pfhwdev *pfhwdev;
 	u16 out_size;
 	int err;
 
@@ -276,8 +275,6 @@ static int init_fw_ctxt(struct hinic_hwdev *hwdev)
 	fw_ctxt.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
 	fw_ctxt.rx_buf_sz = HINIC_RX_BUF_SZ;
 
-	pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev);
-
 	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_FWCTXT_INIT,
 				 &fw_ctxt, sizeof(fw_ctxt),
 				 &fw_ctxt, &out_size);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
index b9db6d649743..cb239627770f 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
@@ -635,17 +635,18 @@ void hinic_sq_write_wqe(struct hinic_sq *sq, u16 prod_idx,
 }
 
 /**
- * hinic_sq_read_wqe - read wqe ptr in the current ci and update the ci
+ * hinic_sq_read_wqebb - read wqe ptr in the current ci and update the ci, the
+ * wqe only have one wqebb
  * @sq: send queue
  * @skb: return skb that was saved
- * @wqe_size: the size of the wqe
+ * @wqe_size: the wqe size ptr
  * @cons_idx: consumer index of the wqe
  *
  * Return wqe in ci position
  **/
-struct hinic_sq_wqe *hinic_sq_read_wqe(struct hinic_sq *sq,
-				       struct sk_buff **skb,
-				       unsigned int *wqe_size, u16 *cons_idx)
+struct hinic_sq_wqe *hinic_sq_read_wqebb(struct hinic_sq *sq,
+					 struct sk_buff **skb,
+					 unsigned int *wqe_size, u16 *cons_idx)
 {
 	struct hinic_hw_wqe *hw_wqe;
 	struct hinic_sq_wqe *sq_wqe;
@@ -658,6 +659,8 @@ struct hinic_sq_wqe *hinic_sq_read_wqe(struct hinic_sq *sq,
 	if (IS_ERR(hw_wqe))
 		return NULL;
 
+	*skb = sq->saved_skb[*cons_idx];
+
 	sq_wqe = &hw_wqe->sq_wqe;
 	ctrl = &sq_wqe->ctrl;
 	ctrl_info = be32_to_cpu(ctrl->ctrl_info);
@@ -665,11 +668,28 @@ struct hinic_sq_wqe *hinic_sq_read_wqe(struct hinic_sq *sq,
 
 	*wqe_size = sizeof(*ctrl) + sizeof(sq_wqe->task);
 	*wqe_size += SECT_SIZE_FROM_8BYTES(buf_sect_len);
+	*wqe_size = ALIGN(*wqe_size, sq->wq->wqebb_size);
 
-	*skb = sq->saved_skb[*cons_idx];
+	return &hw_wqe->sq_wqe;
+}
+
+/**
+ * hinic_sq_read_wqe - read wqe ptr in the current ci and update the ci
+ * @sq: send queue
+ * @skb: return skb that was saved
+ * @wqe_size: the size of the wqe
+ * @cons_idx: consumer index of the wqe
+ *
+ * Return wqe in ci position
+ **/
+struct hinic_sq_wqe *hinic_sq_read_wqe(struct hinic_sq *sq,
+				       struct sk_buff **skb,
+				       unsigned int wqe_size, u16 *cons_idx)
+{
+	struct hinic_hw_wqe *hw_wqe;
 
-	/* using the real wqe size to read wqe again */
-	hw_wqe = hinic_read_wqe(sq->wq, *wqe_size, cons_idx);
+	hw_wqe = hinic_read_wqe(sq->wq, wqe_size, cons_idx);
+	*skb = sq->saved_skb[*cons_idx];
 
 	return &hw_wqe->sq_wqe;
 }
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
index df729a1587e9..6c84f83ec283 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
@@ -165,7 +165,11 @@ void hinic_sq_write_wqe(struct hinic_sq *sq, u16 prod_idx,
 
 struct hinic_sq_wqe *hinic_sq_read_wqe(struct hinic_sq *sq,
 				       struct sk_buff **skb,
-				       unsigned int *wqe_size, u16 *cons_idx);
+				       unsigned int wqe_size, u16 *cons_idx);
+
+struct hinic_sq_wqe *hinic_sq_read_wqebb(struct hinic_sq *sq,
+					 struct sk_buff **skb,
+					 unsigned int *wqe_size, u16 *cons_idx);
 
 void hinic_sq_put_wqe(struct hinic_sq *sq, unsigned int wqe_size);
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index 2353ec829c04..c5fca0356c9c 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -283,7 +283,11 @@ static void free_all_tx_skbs(struct hinic_txq *txq)
 	int nr_sges;
 	u16 ci;
 
-	while ((sq_wqe = hinic_sq_read_wqe(sq, &skb, &wqe_size, &ci))) {
+	while ((sq_wqe = hinic_sq_read_wqebb(sq, &skb, &wqe_size, &ci))) {
+		sq_wqe = hinic_sq_read_wqe(sq, &skb, wqe_size, &ci);
+		if (!sq_wqe)
+			break;
+
 		nr_sges = skb_shinfo(skb)->nr_frags + 1;
 
 		hinic_sq_get_sges(sq_wqe, txq->free_sges, nr_sges);
@@ -319,11 +323,21 @@ static int free_tx_poll(struct napi_struct *napi, int budget)
 	do {
 		hw_ci = HW_CONS_IDX(sq) & wq->mask;
 
-		sq_wqe = hinic_sq_read_wqe(sq, &skb, &wqe_size, &sw_ci);
+		/* Reading a WQEBB to get real WQE size and consumer index. */
+		sq_wqe = hinic_sq_read_wqebb(sq, &skb, &wqe_size, &sw_ci);
 		if ((!sq_wqe) ||
 		    (((hw_ci - sw_ci) & wq->mask) * wq->wqebb_size < wqe_size))
 			break;
 
+		/* If this WQE have multiple WQEBBs, we will read again to get
+		 * full size WQE.
+		 */
+		if (wqe_size > wq->wqebb_size) {
+			sq_wqe = hinic_sq_read_wqe(sq, &skb, wqe_size, &sw_ci);
+			if (unlikely(!sq_wqe))
+				break;
+		}
+
 		tx_bytes += skb->len;
 		pkts++;
 
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index ffe7acbeaa22..dafdd4ade705 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -718,23 +718,6 @@ static int init_tx_pools(struct net_device *netdev)
 	return 0;
 }
 
-static void release_error_buffers(struct ibmvnic_adapter *adapter)
-{
-	struct device *dev = &adapter->vdev->dev;
-	struct ibmvnic_error_buff *error_buff, *tmp;
-	unsigned long flags;
-
-	spin_lock_irqsave(&adapter->error_list_lock, flags);
-	list_for_each_entry_safe(error_buff, tmp, &adapter->errors, list) {
-		list_del(&error_buff->list);
-		dma_unmap_single(dev, error_buff->dma, error_buff->len,
-				 DMA_FROM_DEVICE);
-		kfree(error_buff->buff);
-		kfree(error_buff);
-	}
-	spin_unlock_irqrestore(&adapter->error_list_lock, flags);
-}
-
 static void ibmvnic_napi_enable(struct ibmvnic_adapter *adapter)
 {
 	int i;
@@ -896,7 +879,6 @@ static void release_resources(struct ibmvnic_adapter *adapter)
 	release_tx_pools(adapter);
 	release_rx_pools(adapter);
 
-	release_error_buffers(adapter);
 	release_napi(adapter);
 	release_login_rsp_buffer(adapter);
 }
@@ -3843,132 +3825,41 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
 	ibmvnic_send_crq(adapter, &crq);
 }
 
-static void handle_error_info_rsp(union ibmvnic_crq *crq,
-				  struct ibmvnic_adapter *adapter)
-{
-	struct device *dev = &adapter->vdev->dev;
-	struct ibmvnic_error_buff *error_buff, *tmp;
-	unsigned long flags;
-	bool found = false;
-	int i;
-
-	if (!crq->request_error_rsp.rc.code) {
-		dev_info(dev, "Request Error Rsp returned with rc=%x\n",
-			 crq->request_error_rsp.rc.code);
-		return;
-	}
-
-	spin_lock_irqsave(&adapter->error_list_lock, flags);
-	list_for_each_entry_safe(error_buff, tmp, &adapter->errors, list)
-		if (error_buff->error_id == crq->request_error_rsp.error_id) {
-			found = true;
-			list_del(&error_buff->list);
-			break;
-		}
-	spin_unlock_irqrestore(&adapter->error_list_lock, flags);
-
-	if (!found) {
-		dev_err(dev, "Couldn't find error id %x\n",
-			be32_to_cpu(crq->request_error_rsp.error_id));
-		return;
-	}
-
-	dev_err(dev, "Detailed info for error id %x:",
-		be32_to_cpu(crq->request_error_rsp.error_id));
-
-	for (i = 0; i < error_buff->len; i++) {
-		pr_cont("%02x", (int)error_buff->buff[i]);
-		if (i % 8 == 7)
-			pr_cont(" ");
-	}
-	pr_cont("\n");
-
-	dma_unmap_single(dev, error_buff->dma, error_buff->len,
-			 DMA_FROM_DEVICE);
-	kfree(error_buff->buff);
-	kfree(error_buff);
-}
-
-static void request_error_information(struct ibmvnic_adapter *adapter,
-				      union ibmvnic_crq *err_crq)
-{
-	struct device *dev = &adapter->vdev->dev;
-	struct net_device *netdev = adapter->netdev;
-	struct ibmvnic_error_buff *error_buff;
-	unsigned long timeout = msecs_to_jiffies(30000);
-	union ibmvnic_crq crq;
-	unsigned long flags;
-	int rc, detail_len;
-
-	error_buff = kmalloc(sizeof(*error_buff), GFP_ATOMIC);
-	if (!error_buff)
-		return;
-
-	detail_len = be32_to_cpu(err_crq->error_indication.detail_error_sz);
-	error_buff->buff = kmalloc(detail_len, GFP_ATOMIC);
-	if (!error_buff->buff) {
-		kfree(error_buff);
-		return;
-	}
-
-	error_buff->dma = dma_map_single(dev, error_buff->buff, detail_len,
-					 DMA_FROM_DEVICE);
-	if (dma_mapping_error(dev, error_buff->dma)) {
-		netdev_err(netdev, "Couldn't map error buffer\n");
-		kfree(error_buff->buff);
-		kfree(error_buff);
-		return;
-	}
-
-	error_buff->len = detail_len;
-	error_buff->error_id = err_crq->error_indication.error_id;
-
-	spin_lock_irqsave(&adapter->error_list_lock, flags);
-	list_add_tail(&error_buff->list, &adapter->errors);
-	spin_unlock_irqrestore(&adapter->error_list_lock, flags);
-
-	memset(&crq, 0, sizeof(crq));
-	crq.request_error_info.first = IBMVNIC_CRQ_CMD;
-	crq.request_error_info.cmd = REQUEST_ERROR_INFO;
-	crq.request_error_info.ioba = cpu_to_be32(error_buff->dma);
-	crq.request_error_info.len = cpu_to_be32(detail_len);
-	crq.request_error_info.error_id = err_crq->error_indication.error_id;
-
-	rc = ibmvnic_send_crq(adapter, &crq);
-	if (rc) {
-		netdev_err(netdev, "failed to request error information\n");
-		goto err_info_fail;
-	}
-
-	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
-		netdev_err(netdev, "timeout waiting for error information\n");
-		goto err_info_fail;
+static const char *ibmvnic_fw_err_cause(u16 cause)
+{
+	switch (cause) {
+	case ADAPTER_PROBLEM:
+		return "adapter problem";
+	case BUS_PROBLEM:
+		return "bus problem";
+	case FW_PROBLEM:
+		return "firmware problem";
+	case DD_PROBLEM:
+		return "device driver problem";
+	case EEH_RECOVERY:
+		return "EEH recovery";
+	case FW_UPDATED:
+		return "firmware updated";
+	case LOW_MEMORY:
+		return "low Memory";
+	default:
+		return "unknown";
 	}
-
-	return;
-
-err_info_fail:
-	spin_lock_irqsave(&adapter->error_list_lock, flags);
-	list_del(&error_buff->list);
-	spin_unlock_irqrestore(&adapter->error_list_lock, flags);
-
-	kfree(error_buff->buff);
-	kfree(error_buff);
 }
 
 static void handle_error_indication(union ibmvnic_crq *crq,
 				    struct ibmvnic_adapter *adapter)
 {
 	struct device *dev = &adapter->vdev->dev;
+	u16 cause;
 
-	dev_err(dev, "Firmware reports %serror id %x, cause %d\n",
-		crq->error_indication.flags
-			& IBMVNIC_FATAL_ERROR ? "FATAL " : "",
-		be32_to_cpu(crq->error_indication.error_id),
-		be16_to_cpu(crq->error_indication.error_cause));
+	cause = be16_to_cpu(crq->error_indication.error_cause);
 
-	if (be32_to_cpu(crq->error_indication.error_id))
-		request_error_information(adapter, crq);
+	dev_warn_ratelimited(dev,
+			     "Firmware reports %serror, cause: %s. Starting recovery...\n",
+			     crq->error_indication.flags
+				& IBMVNIC_FATAL_ERROR ? "FATAL " : "",
+			     ibmvnic_fw_err_cause(cause));
 
 	if (crq->error_indication.flags & IBMVNIC_FATAL_ERROR)
 		ibmvnic_reset(adapter, VNIC_RESET_FATAL);
@@ -4468,10 +4359,6 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 		netdev_dbg(netdev, "Got Error Indication\n");
 		handle_error_indication(crq, adapter);
 		break;
-	case REQUEST_ERROR_RSP:
-		netdev_dbg(netdev, "Got Error Detail Response\n");
-		handle_error_info_rsp(crq, adapter);
-		break;
 	case REQUEST_STATISTICS_RSP:
 		netdev_dbg(netdev, "Got Statistics Response\n");
 		complete(&adapter->stats_done);
@@ -4830,9 +4717,6 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 
 	spin_lock_init(&adapter->stats_lock);
 
-	INIT_LIST_HEAD(&adapter->errors);
-	spin_lock_init(&adapter->error_list_lock);
-
 	INIT_WORK(&adapter->ibmvnic_reset, __ibmvnic_reset);
 	INIT_LIST_HEAD(&adapter->rwi_list);
 	mutex_init(&adapter->reset_lock);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index f9fb780102ac..f06eec145ca6 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -512,24 +512,6 @@ struct ibmvnic_error_indication {
 	u8 reserved2[2];
 } __packed __aligned(8);
 
-struct ibmvnic_request_error_info {
-	u8 first;
-	u8 cmd;
-	u8 reserved[2];
-	__be32 ioba;
-	__be32 len;
-	__be32 error_id;
-} __packed __aligned(8);
-
-struct ibmvnic_request_error_rsp {
-	u8 first;
-	u8 cmd;
-	u8 reserved[2];
-	__be32 error_id;
-	__be32 len;
-	struct ibmvnic_rc rc;
-} __packed __aligned(8);
-
 struct ibmvnic_link_state_indication {
 	u8 first;
 	u8 cmd;
@@ -709,8 +691,6 @@ union ibmvnic_crq {
 	struct ibmvnic_request_debug_stats request_debug_stats;
 	struct ibmvnic_request_debug_stats request_debug_stats_rsp;
 	struct ibmvnic_error_indication error_indication;
-	struct ibmvnic_request_error_info request_error_info;
-	struct ibmvnic_request_error_rsp request_error_rsp;
 	struct ibmvnic_link_state_indication link_state_indication;
 	struct ibmvnic_change_mac_addr change_mac_addr;
 	struct ibmvnic_change_mac_addr change_mac_addr_rsp;
@@ -809,8 +789,6 @@ enum ibmvnic_commands {
 	SET_PHYS_PARMS = 0x07,
 	SET_PHYS_PARMS_RSP = 0x87,
 	ERROR_INDICATION = 0x08,
-	REQUEST_ERROR_INFO = 0x09,
-	REQUEST_ERROR_RSP = 0x89,
 	LOGICAL_LINK_STATE = 0x0C,
 	LOGICAL_LINK_STATE_RSP = 0x8C,
 	REQUEST_STATISTICS = 0x0D,
@@ -945,14 +923,6 @@ struct ibmvnic_rx_pool {
 	struct ibmvnic_long_term_buff long_term_buff;
 };
 
-struct ibmvnic_error_buff {
-	char *buff;
-	dma_addr_t dma;
-	int len;
-	struct list_head list;
-	__be32 error_id;
-};
-
 struct ibmvnic_vpd {
 	unsigned char *buff;
 	dma_addr_t dma_addr;
@@ -1047,9 +1017,6 @@ struct ibmvnic_adapter {
 	struct completion init_done;
 	int init_done_rc;
 
-	struct list_head errors;
-	spinlock_t error_list_lock;
-
 	struct completion fw_done;
 	int fw_done_rc;
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index ddbea79d18e5..501ee718177f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -868,6 +868,8 @@ i40e_status i40e_asq_send_command(struct i40e_hw *hw,
 		cmd_completed = true;
 		if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_OK)
 			status = 0;
+		else if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_EBUSY)
+			status = I40E_ERR_NOT_READY;
 		else
 			status = I40E_ERR_ADMIN_QUEUE_ERROR;
 		hw->aq.asq_last_status = (enum i40e_admin_queue_err)retval;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 7d888e05f96f..80e3eec6134e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -2247,6 +2247,8 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_phy_register_access);
 struct i40e_aqc_nvm_update {
 	u8	command_flags;
 #define I40E_AQ_NVM_LAST_CMD			0x01
+#define I40E_AQ_NVM_REARRANGE_TO_FLAT		0x20
+#define I40E_AQ_NVM_REARRANGE_TO_STRUCT		0x40
 #define I40E_AQ_NVM_FLASH_ONLY			0x80
 #define I40E_AQ_NVM_PRESERVATION_FLAGS_SHIFT	1
 #define I40E_AQ_NVM_PRESERVATION_FLAGS_MASK	0x03
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index eb2d1530d331..85f75b5978fc 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -3541,6 +3541,41 @@ i40e_aq_update_nvm_exit:
 }
 
 /**
+ * i40e_aq_rearrange_nvm
+ * @hw: pointer to the hw struct
+ * @rearrange_nvm: defines direction of rearrangement
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Rearrange NVM structure, available only for transition FW
+ **/
+i40e_status i40e_aq_rearrange_nvm(struct i40e_hw *hw,
+				  u8 rearrange_nvm,
+				  struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aqc_nvm_update *cmd;
+	i40e_status status;
+	struct i40e_aq_desc desc;
+
+	cmd = (struct i40e_aqc_nvm_update *)&desc.params.raw;
+
+	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_nvm_update);
+
+	rearrange_nvm &= (I40E_AQ_NVM_REARRANGE_TO_FLAT |
+			 I40E_AQ_NVM_REARRANGE_TO_STRUCT);
+
+	if (!rearrange_nvm) {
+		status = I40E_ERR_PARAM;
+		goto i40e_aq_rearrange_nvm_exit;
+	}
+
+	cmd->command_flags |= rearrange_nvm;
+	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+i40e_aq_rearrange_nvm_exit:
+	return status;
+}
+
+/**
  * i40e_aq_get_lldp_mib
  * @hw: pointer to the hw struct
  * @bridge_type: type of bridge requested
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 6947a2a571cb..abcd096ede14 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -7,6 +7,11 @@
 #include "i40e_diag.h"
 
 struct i40e_stats {
+	/* The stat_string is expected to be a format string formatted using
+	 * vsnprintf by i40e_add_stat_strings. Every member of a stats array
+	 * should use the same format specifiers as they will be formatted
+	 * using the same variadic arguments.
+	 */
 	char stat_string[ETH_GSTRING_LEN];
 	int sizeof_stat;
 	int stat_offset;
@@ -26,6 +31,8 @@ struct i40e_stats {
 	I40E_STAT(struct i40e_vsi, _name, _stat)
 #define I40E_VEB_STAT(_name, _stat) \
 	I40E_STAT(struct i40e_veb, _name, _stat)
+#define I40E_PFC_STAT(_name, _stat) \
+	I40E_STAT(struct i40e_pfc_stats, _name, _stat)
 
 static const struct i40e_stats i40e_gstrings_net_stats[] = {
 	I40E_NETDEV_STAT(rx_packets),
@@ -56,6 +63,13 @@ static const struct i40e_stats i40e_gstrings_veb_stats[] = {
 	I40E_VEB_STAT("veb.rx_unknown_protocol", stats.rx_unknown_protocol),
 };
 
+static const struct i40e_stats i40e_gstrings_veb_tc_stats[] = {
+	I40E_VEB_STAT("veb.tc_%u_tx_packets", tc_stats.tc_tx_packets),
+	I40E_VEB_STAT("veb.tc_%u_tx_bytes", tc_stats.tc_tx_bytes),
+	I40E_VEB_STAT("veb.tc_%u_rx_packets", tc_stats.tc_rx_packets),
+	I40E_VEB_STAT("veb.tc_%u_rx_bytes", tc_stats.tc_rx_bytes),
+};
+
 static const struct i40e_stats i40e_gstrings_misc_stats[] = {
 	I40E_VSI_STAT("rx_unicast", eth_stats.rx_unicast),
 	I40E_VSI_STAT("tx_unicast", eth_stats.tx_unicast),
@@ -141,6 +155,22 @@ static const struct i40e_stats i40e_gstrings_stats[] = {
 	I40E_PF_STAT("port.rx_lpi_count", stats.rx_lpi_count),
 };
 
+struct i40e_pfc_stats {
+	u64 priority_xon_rx;
+	u64 priority_xoff_rx;
+	u64 priority_xon_tx;
+	u64 priority_xoff_tx;
+	u64 priority_xon_2_xoff;
+};
+
+static const struct i40e_stats i40e_gstrings_pfc_stats[] = {
+	I40E_PFC_STAT("port.tx_priority_%u_xon_tx", priority_xon_tx),
+	I40E_PFC_STAT("port.tx_priority_%u_xoff_tx", priority_xoff_tx),
+	I40E_PFC_STAT("port.rx_priority_%u_xon_rx", priority_xon_rx),
+	I40E_PFC_STAT("port.rx_priority_%u_xoff_rx", priority_xoff_rx),
+	I40E_PFC_STAT("port.rx_priority_%u_xon_2_xoff", priority_xon_2_xoff),
+};
+
 /* We use num_tx_queues here as a proxy for the maximum number of queues
  * available because we always allocate queues symmetrically.
  */
@@ -155,23 +185,17 @@ static const struct i40e_stats i40e_gstrings_stats[] = {
 #define I40E_VSI_STATS_LEN(n)	(I40E_NETDEV_STATS_LEN + \
 				 I40E_MISC_STATS_LEN + \
 				 I40E_QUEUE_STATS_LEN((n)))
-#define I40E_PFC_STATS_LEN ( \
-		(FIELD_SIZEOF(struct i40e_pf, stats.priority_xoff_rx) + \
-		 FIELD_SIZEOF(struct i40e_pf, stats.priority_xon_rx) + \
-		 FIELD_SIZEOF(struct i40e_pf, stats.priority_xoff_tx) + \
-		 FIELD_SIZEOF(struct i40e_pf, stats.priority_xon_tx) + \
-		 FIELD_SIZEOF(struct i40e_pf, stats.priority_xon_2_xoff)) \
-		 / sizeof(u64))
-#define I40E_VEB_TC_STATS_LEN ( \
-		(FIELD_SIZEOF(struct i40e_veb, tc_stats.tc_rx_packets) + \
-		 FIELD_SIZEOF(struct i40e_veb, tc_stats.tc_rx_bytes) + \
-		 FIELD_SIZEOF(struct i40e_veb, tc_stats.tc_tx_packets) + \
-		 FIELD_SIZEOF(struct i40e_veb, tc_stats.tc_tx_bytes)) \
-		 / sizeof(u64))
-#define I40E_VEB_STATS_LEN	ARRAY_SIZE(i40e_gstrings_veb_stats)
-#define I40E_VEB_STATS_TOTAL	(I40E_VEB_STATS_LEN + I40E_VEB_TC_STATS_LEN)
+
+#define I40E_PFC_STATS_LEN	(ARRAY_SIZE(i40e_gstrings_pfc_stats) * \
+				 I40E_MAX_USER_PRIORITY)
+
+#define I40E_VEB_STATS_LEN	(ARRAY_SIZE(i40e_gstrings_veb_stats) + \
+				 (ARRAY_SIZE(i40e_gstrings_veb_tc_stats) * \
+				  I40E_MAX_TRAFFIC_CLASS))
+
 #define I40E_PF_STATS_LEN(n)	(I40E_GLOBAL_STATS_LEN + \
 				 I40E_PFC_STATS_LEN + \
+				 I40E_VEB_STATS_LEN + \
 				 I40E_VSI_STATS_LEN((n)))
 
 enum i40e_ethtool_test_id {
@@ -1565,7 +1589,6 @@ static int i40e_set_ringparam(struct net_device *netdev,
 		}
 
 		for (i = 0; i < vsi->num_queue_pairs; i++) {
-			struct i40e_ring *ring;
 			u16 unused;
 
 			/* clone ring and setup updated count */
@@ -1589,9 +1612,8 @@ static int i40e_set_ringparam(struct net_device *netdev,
 			/* now allocate the Rx buffers to make sure the OS
 			 * has enough memory, any failure here means abort
 			 */
-			ring = &rx_rings[i];
-			unused = I40E_DESC_UNUSED(ring);
-			err = i40e_alloc_rx_buffers(ring, unused);
+			unused = I40E_DESC_UNUSED(&rx_rings[i]);
+			err = i40e_alloc_rx_buffers(&rx_rings[i], unused);
 rx_unwind:
 			if (err) {
 				do {
@@ -1681,7 +1703,7 @@ static int i40e_get_stats_count(struct net_device *netdev)
 	struct i40e_pf *pf = vsi->back;
 
 	if (vsi == pf->vsi[pf->lan_vsi] && pf->hw.partition_id == 1)
-		return I40E_PF_STATS_LEN(netdev) + I40E_VEB_STATS_TOTAL;
+		return I40E_PF_STATS_LEN(netdev);
 	else
 		return I40E_VSI_STATS_LEN(netdev);
 }
@@ -1706,6 +1728,114 @@ static int i40e_get_sset_count(struct net_device *netdev, int sset)
 }
 
 /**
+ * i40e_add_one_ethtool_stat - copy the stat into the supplied buffer
+ * @data: location to store the stat value
+ * @pointer: basis for where to copy from
+ * @stat: the stat definition
+ *
+ * Copies the stat data defined by the pointer and stat structure pair into
+ * the memory supplied as data. Used to implement i40e_add_ethtool_stats.
+ * If the pointer is null, data will be zero'd.
+ */
+static inline void
+i40e_add_one_ethtool_stat(u64 *data, void *pointer,
+			  const struct i40e_stats *stat)
+{
+	char *p;
+
+	if (!pointer) {
+		/* ensure that the ethtool data buffer is zero'd for any stats
+		 * which don't have a valid pointer.
+		 */
+		*data = 0;
+		return;
+	}
+
+	p = (char *)pointer + stat->stat_offset;
+	switch (stat->sizeof_stat) {
+	case sizeof(u64):
+		*data = *((u64 *)p);
+		break;
+	case sizeof(u32):
+		*data = *((u32 *)p);
+		break;
+	case sizeof(u16):
+		*data = *((u16 *)p);
+		break;
+	case sizeof(u8):
+		*data = *((u8 *)p);
+		break;
+	default:
+		WARN_ONCE(1, "unexpected stat size for %s",
+			  stat->stat_string);
+		*data = 0;
+	}
+}
+
+/**
+ * __i40e_add_ethtool_stats - copy stats into the ethtool supplied buffer
+ * @data: ethtool stats buffer
+ * @pointer: location to copy stats from
+ * @stats: array of stats to copy
+ * @size: the size of the stats definition
+ *
+ * Copy the stats defined by the stats array using the pointer as a base into
+ * the data buffer supplied by ethtool. Updates the data pointer to point to
+ * the next empty location for successive calls to __i40e_add_ethtool_stats.
+ * If pointer is null, set the data values to zero and update the pointer to
+ * skip these stats.
+ **/
+static inline void
+__i40e_add_ethtool_stats(u64 **data, void *pointer,
+			 const struct i40e_stats stats[],
+			 const unsigned int size)
+{
+	unsigned int i;
+
+	for (i = 0; i < size; i++)
+		i40e_add_one_ethtool_stat((*data)++, pointer, &stats[i]);
+}
+
+/**
+ * i40e_add_ethtool_stats - copy stats into ethtool supplied buffer
+ * @data: ethtool stats buffer
+ * @pointer: location where stats are stored
+ * @stats: static const array of stat definitions
+ *
+ * Macro to ease the use of __i40e_add_ethtool_stats by taking a static
+ * constant stats array and passing the ARRAY_SIZE(). This avoids typos by
+ * ensuring that we pass the size associated with the given stats array.
+ * Assumes that stats is an array.
+ **/
+#define i40e_add_ethtool_stats(data, pointer, stats) \
+	__i40e_add_ethtool_stats(data, pointer, stats, ARRAY_SIZE(stats))
+
+/**
+ * i40e_get_pfc_stats - copy HW PFC statistics to formatted structure
+ * @pf: the PF device structure
+ * @i: the priority value to copy
+ *
+ * The PFC stats are found as arrays in pf->stats, which is not easy to pass
+ * into i40e_add_ethtool_stats. Produce a formatted i40e_pfc_stats structure
+ * of the PFC stats for the given priority.
+ **/
+static inline struct i40e_pfc_stats
+i40e_get_pfc_stats(struct i40e_pf *pf, unsigned int i)
+{
+#define I40E_GET_PFC_STAT(stat, priority) \
+	.stat = pf->stats.stat[priority]
+
+	struct i40e_pfc_stats pfc = {
+		I40E_GET_PFC_STAT(priority_xon_rx, i),
+		I40E_GET_PFC_STAT(priority_xoff_rx, i),
+		I40E_GET_PFC_STAT(priority_xon_tx, i),
+		I40E_GET_PFC_STAT(priority_xoff_tx, i),
+		I40E_GET_PFC_STAT(priority_xon_2_xoff, i),
+	};
+	return pfc;
+}
+
+/**
  * i40e_get_ethtool_stats - copy stat values into supplied buffer
  * @netdev: the netdev to collect stats for
  * @stats: ethtool stats command structure
@@ -1726,23 +1856,19 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 	struct i40e_ring *tx_ring, *rx_ring;
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
+	struct i40e_veb *veb = pf->veb[pf->lan_veb];
 	unsigned int i;
-	char *p;
-	struct rtnl_link_stats64 *net_stats = i40e_get_vsi_stats_struct(vsi);
 	unsigned int start;
+	bool veb_stats;
+	u64 *p = data;
 
 	i40e_update_stats(vsi);
 
-	for (i = 0; i < I40E_NETDEV_STATS_LEN; i++) {
-		p = (char *)net_stats + i40e_gstrings_net_stats[i].stat_offset;
-		*(data++) = (i40e_gstrings_net_stats[i].sizeof_stat ==
-			sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
-	}
-	for (i = 0; i < I40E_MISC_STATS_LEN; i++) {
-		p = (char *)vsi + i40e_gstrings_misc_stats[i].stat_offset;
-		*(data++) = (i40e_gstrings_misc_stats[i].sizeof_stat ==
-			    sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
-	}
+	i40e_add_ethtool_stats(&data, i40e_get_vsi_stats_struct(vsi),
+			       i40e_gstrings_net_stats);
+
+	i40e_add_ethtool_stats(&data, vsi, i40e_gstrings_misc_stats);
+
 	rcu_read_lock();
 	for (i = 0; i < I40E_MAX_NUM_QUEUES(netdev) ; i++) {
 		tx_ring = READ_ONCE(vsi->tx_rings[i]);
@@ -1777,45 +1903,72 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 	}
 	rcu_read_unlock();
 	if (vsi != pf->vsi[pf->lan_vsi] || pf->hw.partition_id != 1)
-		return;
+		goto check_data_pointer;
 
-	if ((pf->lan_veb != I40E_NO_VEB) &&
-	    (pf->flags & I40E_FLAG_VEB_STATS_ENABLED)) {
-		struct i40e_veb *veb = pf->veb[pf->lan_veb];
+	veb_stats = ((pf->lan_veb != I40E_NO_VEB) &&
+		     (pf->flags & I40E_FLAG_VEB_STATS_ENABLED));
+
+	/* If veb stats aren't enabled, pass NULL instead of the veb so that
+	 * we initialize stats to zero and update the data pointer
+	 * intelligently
+	 */
+	i40e_add_ethtool_stats(&data, veb_stats ? veb : NULL,
+			       i40e_gstrings_veb_stats);
+
+	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++)
+		i40e_add_ethtool_stats(&data, veb_stats ? veb : NULL,
+				       i40e_gstrings_veb_tc_stats);
+
+	i40e_add_ethtool_stats(&data, pf, i40e_gstrings_stats);
 
-		for (i = 0; i < I40E_VEB_STATS_LEN; i++) {
-			p = (char *)veb;
-			p += i40e_gstrings_veb_stats[i].stat_offset;
-			*(data++) = (i40e_gstrings_veb_stats[i].sizeof_stat ==
-				     sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
-		}
-		for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
-			*(data++) = veb->tc_stats.tc_tx_packets[i];
-			*(data++) = veb->tc_stats.tc_tx_bytes[i];
-			*(data++) = veb->tc_stats.tc_rx_packets[i];
-			*(data++) = veb->tc_stats.tc_rx_bytes[i];
-		}
-	} else {
-		data += I40E_VEB_STATS_TOTAL;
-	}
-	for (i = 0; i < I40E_GLOBAL_STATS_LEN; i++) {
-		p = (char *)pf + i40e_gstrings_stats[i].stat_offset;
-		*(data++) = (i40e_gstrings_stats[i].sizeof_stat ==
-			     sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
-	}
 	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
-		*(data++) = pf->stats.priority_xon_tx[i];
-		*(data++) = pf->stats.priority_xoff_tx[i];
+		struct i40e_pfc_stats pfc = i40e_get_pfc_stats(pf, i);
+
+		i40e_add_ethtool_stats(&data, &pfc, i40e_gstrings_pfc_stats);
 	}
-	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
-		*(data++) = pf->stats.priority_xon_rx[i];
-		*(data++) = pf->stats.priority_xoff_rx[i];
+
+check_data_pointer:
+	WARN_ONCE(data - p != i40e_get_stats_count(netdev),
+		  "ethtool stats count mismatch!");
+}
+
+/**
+ * __i40e_add_stat_strings - copy stat strings into ethtool buffer
+ * @p: ethtool supplied buffer
+ * @stats: stat definitions array
+ * @size: size of the stats array
+ *
+ * Format and copy the strings described by stats into the buffer pointed at
+ * by p.
+ **/
+static void __i40e_add_stat_strings(u8 **p, const struct i40e_stats stats[],
+				    const unsigned int size, ...)
+{
+	unsigned int i;
+
+	for (i = 0; i < size; i++) {
+		va_list args;
+
+		va_start(args, size);
+		vsnprintf(*p, ETH_GSTRING_LEN, stats[i].stat_string, args);
+		*p += ETH_GSTRING_LEN;
+		va_end(args);
 	}
-	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++)
-		*(data++) = pf->stats.priority_xon_2_xoff[i];
 }
 
 /**
+ * 40e_add_stat_strings - copy stat strings into ethtool buffer
+ * @p: ethtool supplied buffer
+ * @stats: stat definitions array
+ *
+ * Format and copy the strings described by the const static stats value into
+ * the buffer pointed at by p. Assumes that stats can have ARRAY_SIZE called
+ * for it.
+ **/
+#define i40e_add_stat_strings(p, stats, ...) \
+	__i40e_add_stat_strings(p, stats, ARRAY_SIZE(stats), ## __VA_ARGS__)
+
+/**
  * i40e_get_stat_strings - copy stat strings into supplied buffer
  * @netdev: the netdev to collect strings for
  * @data: supplied buffer to copy strings into
@@ -1833,16 +1986,10 @@ static void i40e_get_stat_strings(struct net_device *netdev, u8 *data)
 	unsigned int i;
 	u8 *p = data;
 
-	for (i = 0; i < I40E_NETDEV_STATS_LEN; i++) {
-		snprintf(data, ETH_GSTRING_LEN, "%s",
-			 i40e_gstrings_net_stats[i].stat_string);
-		data += ETH_GSTRING_LEN;
-	}
-	for (i = 0; i < I40E_MISC_STATS_LEN; i++) {
-		snprintf(data, ETH_GSTRING_LEN, "%s",
-			 i40e_gstrings_misc_stats[i].stat_string);
-		data += ETH_GSTRING_LEN;
-	}
+	i40e_add_stat_strings(&data, i40e_gstrings_net_stats);
+
+	i40e_add_stat_strings(&data, i40e_gstrings_misc_stats);
+
 	for (i = 0; i < I40E_MAX_NUM_QUEUES(netdev); i++) {
 		snprintf(data, ETH_GSTRING_LEN, "tx-%u.tx_packets", i);
 		data += ETH_GSTRING_LEN;
@@ -1856,52 +2003,15 @@ static void i40e_get_stat_strings(struct net_device *netdev, u8 *data)
 	if (vsi != pf->vsi[pf->lan_vsi] || pf->hw.partition_id != 1)
 		return;
 
-	for (i = 0; i < I40E_VEB_STATS_LEN; i++) {
-		snprintf(data, ETH_GSTRING_LEN, "%s",
-			 i40e_gstrings_veb_stats[i].stat_string);
-		data += ETH_GSTRING_LEN;
-	}
-	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
-		snprintf(data, ETH_GSTRING_LEN,
-			 "veb.tc_%u_tx_packets", i);
-		data += ETH_GSTRING_LEN;
-		snprintf(data, ETH_GSTRING_LEN,
-			 "veb.tc_%u_tx_bytes", i);
-		data += ETH_GSTRING_LEN;
-		snprintf(data, ETH_GSTRING_LEN,
-			 "veb.tc_%u_rx_packets", i);
-		data += ETH_GSTRING_LEN;
-		snprintf(data, ETH_GSTRING_LEN,
-			 "veb.tc_%u_rx_bytes", i);
-		data += ETH_GSTRING_LEN;
-	}
+	i40e_add_stat_strings(&data, i40e_gstrings_veb_stats);
 
-	for (i = 0; i < I40E_GLOBAL_STATS_LEN; i++) {
-		snprintf(data, ETH_GSTRING_LEN, "%s",
-			 i40e_gstrings_stats[i].stat_string);
-		data += ETH_GSTRING_LEN;
-	}
-	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
-		snprintf(data, ETH_GSTRING_LEN,
-			 "port.tx_priority_%u_xon", i);
-		data += ETH_GSTRING_LEN;
-		snprintf(data, ETH_GSTRING_LEN,
-			 "port.tx_priority_%u_xoff", i);
-		data += ETH_GSTRING_LEN;
-	}
-	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
-		snprintf(data, ETH_GSTRING_LEN,
-			 "port.rx_priority_%u_xon", i);
-		data += ETH_GSTRING_LEN;
-		snprintf(data, ETH_GSTRING_LEN,
-			 "port.rx_priority_%u_xoff", i);
-		data += ETH_GSTRING_LEN;
-	}
-	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
-		snprintf(data, ETH_GSTRING_LEN,
-			 "port.rx_priority_%u_xon_2_xoff", i);
-		data += ETH_GSTRING_LEN;
-	}
+	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++)
+		i40e_add_stat_strings(&data, i40e_gstrings_veb_tc_stats, i);
+
+	i40e_add_stat_strings(&data, i40e_gstrings_stats);
+
+	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++)
+		i40e_add_stat_strings(&data, i40e_gstrings_pfc_stats, i);
 
 	WARN_ONCE(p - data != i40e_get_stats_count(netdev) * ETH_GSTRING_LEN,
 		  "stat strings count mismatch!");
@@ -4535,7 +4645,6 @@ flags_complete:
 	if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP) {
 		if (pf->flags & I40E_FLAG_DISABLE_FW_LLDP) {
 			struct i40e_dcbx_config *dcbcfg;
-			int i;
 
 			i40e_aq_stop_lldp(&pf->hw, true, NULL);
 			i40e_aq_set_dcb_parameters(&pf->hw, true, NULL);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index c944bd10b03d..f2c622e78802 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1800,6 +1800,7 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 						       num_tc_qps);
 					break;
 				}
+				/* fall through */
 			case I40E_VSI_FDIR:
 			case I40E_VSI_SRIOV:
 			case I40E_VSI_VMDQ2:
@@ -6597,6 +6598,8 @@ static i40e_status i40e_force_link_state(struct i40e_pf *pf, bool is_up)
 	config.eee_capability = abilities.eee_capability;
 	config.eeer = abilities.eeer_val;
 	config.low_power_ctrl = abilities.d3_lpan;
+	config.fec_config = abilities.fec_cfg_curr_mod_ext_info &
+			    I40E_AQ_PHY_FEC_CONFIG_MASK;
 	err = i40e_aq_set_phy_config(hw, &config, NULL);
 
 	if (err) {
@@ -7522,7 +7525,7 @@ static int i40e_setup_tc_cls_flower(struct i40e_netdev_priv *np,
 	case TC_CLSFLOWER_STATS:
 		return -EOPNOTSUPP;
 	default:
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 }
 
@@ -7554,7 +7557,7 @@ static int i40e_setup_tc_block(struct net_device *dev,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, i40e_setup_tc_block_cb,
-					     np, np);
+					     np, np, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, i40e_setup_tc_block_cb, np);
 		return 0;
@@ -11841,7 +11844,6 @@ static int i40e_xdp(struct net_device *dev,
 	case XDP_SETUP_PROG:
 		return i40e_xdp_setup(vsi, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = i40e_enabled_xdp_vsi(vsi);
 		xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0;
 		return 0;
 	default:
@@ -11978,7 +11980,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 		snprintf(netdev->name, IFNAMSIZ, "%.*sv%%d",
 			 IFNAMSIZ - 4,
 			 pf->vsi[pf->lan_vsi]->netdev->name);
-		random_ether_addr(mac_addr);
+		eth_random_addr(mac_addr);
 
 		spin_lock_bh(&vsi->mac_filter_hash_lock);
 		i40e_add_mac_filter(vsi, mac_addr);
@@ -14354,12 +14356,6 @@ static void i40e_shutdown(struct pci_dev *pdev)
 
 	set_bit(__I40E_SUSPENDED, pf->state);
 	set_bit(__I40E_DOWN, pf->state);
-	rtnl_lock();
-	i40e_prep_for_reset(pf, true);
-	rtnl_unlock();
-
-	wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0));
-	wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0));
 
 	del_timer_sync(&pf->service_timer);
 	cancel_work_sync(&pf->service_task);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index 3170655cdeb9..e08d754824b1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -193,6 +193,9 @@ i40e_status i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer,
 				u32 offset, u16 length, void *data,
 				bool last_command, u8 preservation_flags,
 				struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_rearrange_nvm(struct i40e_hw *hw,
+				  u8 rearrange_nvm,
+				  struct i40e_asq_cmd_details *cmd_details);
 i40e_status i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type,
 				u8 mib_type, void *buff, u16 buff_size,
 				u16 *local_len, u16 *remote_len,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index b151ae316546..b5042d1a63c0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2253,9 +2253,10 @@ static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring,
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
+		/* fall through */
 	case XDP_ABORTED:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
-		/* fallthrough -- handle aborts by dropping packet */
+		/* fall through -- handle aborts by dropping packet */
 	case XDP_DROP:
 		result = I40E_XDP_CONSUMED;
 		break;
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
index c355120dfdfd..21a0dbf6ccf6 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
@@ -797,6 +797,8 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw,
 		cmd_completed = true;
 		if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_OK)
 			status = 0;
+		else if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_EBUSY)
+			status = I40E_ERR_NOT_READY;
 		else
 			status = I40E_ERR_ADMIN_QUEUE_ERROR;
 		hw->aq.asq_last_status = (enum i40e_admin_queue_err)retval;
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
index aa81e87cd471..5fd8529465d4 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
@@ -2175,6 +2175,8 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_phy_register_access);
 struct i40e_aqc_nvm_update {
 	u8	command_flags;
 #define I40E_AQ_NVM_LAST_CMD			0x01
+#define I40E_AQ_NVM_REARRANGE_TO_FLAT		0x20
+#define I40E_AQ_NVM_REARRANGE_TO_STRUCT		0x40
 #define I40E_AQ_NVM_FLASH_ONLY			0x80
 #define I40E_AQ_NVM_PRESERVATION_FLAGS_SHIFT	1
 #define I40E_AQ_NVM_PRESERVATION_FLAGS_MASK	0x03
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c
index 9cef54971312..eea280ba411e 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c
@@ -1021,75 +1021,6 @@ do_retry:
 }
 
 /**
- * i40evf_aq_set_phy_register
- * @hw: pointer to the hw struct
- * @phy_select: select which phy should be accessed
- * @dev_addr: PHY device address
- * @reg_addr: PHY register address
- * @reg_val: new register value
- * @cmd_details: pointer to command details structure or NULL
- *
- * Reset the external PHY.
- **/
-i40e_status i40evf_aq_set_phy_register(struct i40e_hw *hw,
-				       u8 phy_select, u8 dev_addr,
-				       u32 reg_addr, u32 reg_val,
-				       struct i40e_asq_cmd_details *cmd_details)
-{
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_phy_register_access *cmd =
-		(struct i40e_aqc_phy_register_access *)&desc.params.raw;
-	i40e_status status;
-
-	i40evf_fill_default_direct_cmd_desc(&desc,
-					    i40e_aqc_opc_set_phy_register);
-
-	cmd->phy_interface = phy_select;
-	cmd->dev_address = dev_addr;
-	cmd->reg_address = cpu_to_le32(reg_addr);
-	cmd->reg_value = cpu_to_le32(reg_val);
-
-	status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details);
-
-	return status;
-}
-
-/**
- * i40evf_aq_get_phy_register
- * @hw: pointer to the hw struct
- * @phy_select: select which phy should be accessed
- * @dev_addr: PHY device address
- * @reg_addr: PHY register address
- * @reg_val: read register value
- * @cmd_details: pointer to command details structure or NULL
- *
- * Reset the external PHY.
- **/
-i40e_status i40evf_aq_get_phy_register(struct i40e_hw *hw,
-				       u8 phy_select, u8 dev_addr,
-				       u32 reg_addr, u32 *reg_val,
-				       struct i40e_asq_cmd_details *cmd_details)
-{
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_phy_register_access *cmd =
-		(struct i40e_aqc_phy_register_access *)&desc.params.raw;
-	i40e_status status;
-
-	i40evf_fill_default_direct_cmd_desc(&desc,
-					    i40e_aqc_opc_get_phy_register);
-
-	cmd->phy_interface = phy_select;
-	cmd->dev_address = dev_addr;
-	cmd->reg_address = cpu_to_le32(reg_addr);
-
-	status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details);
-	if (!status)
-		*reg_val = le32_to_cpu(cmd->reg_value);
-
-	return status;
-}
-
-/**
  * i40e_aq_send_msg_to_pf
  * @hw: pointer to the hardware structure
  * @v_opcode: opcodes for VF-PF communication
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index a7b87f935411..5906c1c1d19d 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -2884,7 +2884,7 @@ static int i40evf_setup_tc_cls_flower(struct i40evf_adapter *adapter,
 	case TC_CLSFLOWER_STATS:
 		return -EOPNOTSUPP;
 	default:
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 }
 
@@ -2926,7 +2926,7 @@ static int i40evf_setup_tc_block(struct net_device *dev,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, i40evf_setup_tc_block_cb,
-					     adapter, adapter);
+					     adapter, adapter, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, i40evf_setup_tc_block_cb,
 					adapter);
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index b13b42e5a1d9..bafdcf70a353 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -225,19 +225,7 @@ static s32 igb_init_phy_params_82575(struct e1000_hw *hw)
 	hw->bus.func = (rd32(E1000_STATUS) & E1000_STATUS_FUNC_MASK) >>
 			E1000_STATUS_FUNC_SHIFT;
 
-	/* Make sure the PHY is in a good state. Several people have reported
-	 * firmware leaving the PHY's page select register set to something
-	 * other than the default of zero, which causes the PHY ID read to
-	 * access something other than the intended register.
-	 */
-	ret_val = hw->phy.ops.reset(hw);
-	if (ret_val) {
-		hw_dbg("Error resetting the PHY.\n");
-		goto out;
-	}
-
 	/* Set phy->phy_addr and phy->id. */
-	igb_write_phy_reg_82580(hw, I347AT4_PAGE_SELECT, 0);
 	ret_val = igb_get_phy_id_82575(hw);
 	if (ret_val)
 		return ret_val;
@@ -1720,6 +1708,7 @@ static s32 igb_setup_serdes_link_82575(struct e1000_hw *hw)
 	case E1000_CTRL_EXT_LINK_MODE_1000BASE_KX:
 		/* disable PCS autoneg and support parallel detect only */
 		pcs_autoneg = false;
+		/* fall through */
 	default:
 		if (hw->mac.type == e1000_82575 ||
 		    hw->mac.type == e1000_82576) {
diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h
index 252440a418dc..8a28f3388f69 100644
--- a/drivers/net/ethernet/intel/igb/e1000_defines.h
+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h
@@ -1048,6 +1048,22 @@
 #define E1000_TQAVCTRL_XMIT_MODE	BIT(0)
 #define E1000_TQAVCTRL_DATAFETCHARB	BIT(4)
 #define E1000_TQAVCTRL_DATATRANARB	BIT(8)
+#define E1000_TQAVCTRL_DATATRANTIM	BIT(9)
+#define E1000_TQAVCTRL_SP_WAIT_SR	BIT(10)
+/* Fetch Time Delta - bits 31:16
+ *
+ * This field holds the value to be reduced from the launch time for
+ * fetch time decision. The FetchTimeDelta value is defined in 32 ns
+ * granularity.
+ *
+ * This field is 16 bits wide, and so the maximum value is:
+ *
+ * 65535 * 32 = 2097120 ~= 2.1 msec
+ *
+ * XXX: We are configuring the max value here since we couldn't come up
+ * with a reason for not doing so.
+ */
+#define E1000_TQAVCTRL_FETCHTIME_DELTA	(0xFFFF << 16)
 
 /* TX Qav Credit Control fields */
 #define E1000_TQAVCC_IDLESLOPE_MASK	0xFFFF
diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c
index 2be0e762ec69..ad2125e5a7f7 100644
--- a/drivers/net/ethernet/intel/igb/e1000_phy.c
+++ b/drivers/net/ethernet/intel/igb/e1000_phy.c
@@ -659,6 +659,7 @@ s32 igb_copper_link_setup_m88_gen2(struct e1000_hw *hw)
 			phy_data |= M88E1000_PSCR_AUTO_X_1000T;
 			break;
 		}
+		/* fall through */
 	case 0:
 	default:
 		phy_data |= M88E1000_PSCR_AUTO_X_MODE;
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 9643b5b3d444..ca54e268d157 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -262,6 +262,7 @@ struct igb_ring {
 	u16 count;			/* number of desc. in the ring */
 	u8 queue_index;			/* logical index of the ring*/
 	u8 reg_idx;			/* physical index of the ring */
+	bool launchtime_enable;		/* true if LaunchTime is enabled */
 	bool cbs_enable;		/* indicates if CBS is enabled */
 	s32 idleslope;			/* idleSlope in kbps */
 	s32 sendslope;			/* sendSlope in kbps */
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index f707709969ac..d03c2f0d7592 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -22,7 +22,6 @@
 #include <linux/if.h>
 #include <linux/if_vlan.h>
 #include <linux/pci.h>
-#include <linux/pci-aspm.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/ip.h>
@@ -1654,33 +1653,65 @@ static void set_queue_mode(struct e1000_hw *hw, int queue, enum queue_mode mode)
 	wr32(E1000_I210_TQAVCC(queue), val);
 }
 
+static bool is_any_cbs_enabled(struct igb_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		if (adapter->tx_ring[i]->cbs_enable)
+			return true;
+	}
+
+	return false;
+}
+
+static bool is_any_txtime_enabled(struct igb_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		if (adapter->tx_ring[i]->launchtime_enable)
+			return true;
+	}
+
+	return false;
+}
+
 /**
- *  igb_configure_cbs - Configure Credit-Based Shaper (CBS)
+ *  igb_config_tx_modes - Configure "Qav Tx mode" features on igb
  *  @adapter: pointer to adapter struct
  *  @queue: queue number
- *  @enable: true = enable CBS, false = disable CBS
- *  @idleslope: idleSlope in kbps
- *  @sendslope: sendSlope in kbps
- *  @hicredit: hiCredit in bytes
- *  @locredit: loCredit in bytes
  *
- *  Configure CBS for a given hardware queue. When disabling, idleslope,
- *  sendslope, hicredit, locredit arguments are ignored. Returns 0 if
- *  success. Negative otherwise.
+ *  Configure CBS and Launchtime for a given hardware queue.
+ *  Parameters are retrieved from the correct Tx ring, so
+ *  igb_save_cbs_params() and igb_save_txtime_params() should be used
+ *  for setting those correctly prior to this function being called.
  **/
-static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
-			      bool enable, int idleslope, int sendslope,
-			      int hicredit, int locredit)
+static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
 {
+	struct igb_ring *ring = adapter->tx_ring[queue];
 	struct net_device *netdev = adapter->netdev;
 	struct e1000_hw *hw = &adapter->hw;
-	u32 tqavcc;
+	u32 tqavcc, tqavctrl;
 	u16 value;
 
 	WARN_ON(hw->mac.type != e1000_i210);
 	WARN_ON(queue < 0 || queue > 1);
 
-	if (enable || queue == 0) {
+	/* If any of the Qav features is enabled, configure queues as SR and
+	 * with HIGH PRIO. If none is, then configure them with LOW PRIO and
+	 * as SP.
+	 */
+	if (ring->cbs_enable || ring->launchtime_enable) {
+		set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
+		set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION);
+	} else {
+		set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_LOW);
+		set_queue_mode(hw, queue, QUEUE_MODE_STRICT_PRIORITY);
+	}
+
+	/* If CBS is enabled, set DataTranARB and config its parameters. */
+	if (ring->cbs_enable || queue == 0) {
 		/* i210 does not allow the queue 0 to be in the Strict
 		 * Priority mode while the Qav mode is enabled, so,
 		 * instead of disabling strict priority mode, we give
@@ -1690,14 +1721,19 @@ static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
 		 * Queue0 QueueMode must be set to 1b when
 		 * TransmitMode is set to Qav."
 		 */
-		if (queue == 0 && !enable) {
+		if (queue == 0 && !ring->cbs_enable) {
 			/* max "linkspeed" idleslope in kbps */
-			idleslope = 1000000;
-			hicredit = ETH_FRAME_LEN;
+			ring->idleslope = 1000000;
+			ring->hicredit = ETH_FRAME_LEN;
 		}
 
-		set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
-		set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION);
+		/* Always set data transfer arbitration to credit-based
+		 * shaper algorithm on TQAVCTRL if CBS is enabled for any of
+		 * the queues.
+		 */
+		tqavctrl = rd32(E1000_I210_TQAVCTRL);
+		tqavctrl |= E1000_TQAVCTRL_DATATRANARB;
+		wr32(E1000_I210_TQAVCTRL, tqavctrl);
 
 		/* According to i210 datasheet section 7.2.7.7, we should set
 		 * the 'idleSlope' field from TQAVCC register following the
@@ -1756,17 +1792,16 @@ static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
 		 *       calculated value, so the resulting bandwidth might
 		 *       be slightly higher for some configurations.
 		 */
-		value = DIV_ROUND_UP_ULL(idleslope * 61034ULL, 1000000);
+		value = DIV_ROUND_UP_ULL(ring->idleslope * 61034ULL, 1000000);
 
 		tqavcc = rd32(E1000_I210_TQAVCC(queue));
 		tqavcc &= ~E1000_TQAVCC_IDLESLOPE_MASK;
 		tqavcc |= value;
 		wr32(E1000_I210_TQAVCC(queue), tqavcc);
 
-		wr32(E1000_I210_TQAVHC(queue), 0x80000000 + hicredit * 0x7735);
+		wr32(E1000_I210_TQAVHC(queue),
+		     0x80000000 + ring->hicredit * 0x7735);
 	} else {
-		set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_LOW);
-		set_queue_mode(hw, queue, QUEUE_MODE_STRICT_PRIORITY);
 
 		/* Set idleSlope to zero. */
 		tqavcc = rd32(E1000_I210_TQAVCC(queue));
@@ -1775,6 +1810,43 @@ static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
 
 		/* Set hiCredit to zero. */
 		wr32(E1000_I210_TQAVHC(queue), 0);
+
+		/* If CBS is not enabled for any queues anymore, then return to
+		 * the default state of Data Transmission Arbitration on
+		 * TQAVCTRL.
+		 */
+		if (!is_any_cbs_enabled(adapter)) {
+			tqavctrl = rd32(E1000_I210_TQAVCTRL);
+			tqavctrl &= ~E1000_TQAVCTRL_DATATRANARB;
+			wr32(E1000_I210_TQAVCTRL, tqavctrl);
+		}
+	}
+
+	/* If LaunchTime is enabled, set DataTranTIM. */
+	if (ring->launchtime_enable) {
+		/* Always set DataTranTIM on TQAVCTRL if LaunchTime is enabled
+		 * for any of the SR queues, and configure fetchtime delta.
+		 * XXX NOTE:
+		 *     - LaunchTime will be enabled for all SR queues.
+		 *     - A fixed offset can be added relative to the launch
+		 *       time of all packets if configured at reg LAUNCH_OS0.
+		 *       We are keeping it as 0 for now (default value).
+		 */
+		tqavctrl = rd32(E1000_I210_TQAVCTRL);
+		tqavctrl |= E1000_TQAVCTRL_DATATRANTIM |
+		       E1000_TQAVCTRL_FETCHTIME_DELTA;
+		wr32(E1000_I210_TQAVCTRL, tqavctrl);
+	} else {
+		/* If Launchtime is not enabled for any SR queues anymore,
+		 * then clear DataTranTIM on TQAVCTRL and clear fetchtime delta,
+		 * effectively disabling Launchtime.
+		 */
+		if (!is_any_txtime_enabled(adapter)) {
+			tqavctrl = rd32(E1000_I210_TQAVCTRL);
+			tqavctrl &= ~E1000_TQAVCTRL_DATATRANTIM;
+			tqavctrl &= ~E1000_TQAVCTRL_FETCHTIME_DELTA;
+			wr32(E1000_I210_TQAVCTRL, tqavctrl);
+		}
 	}
 
 	/* XXX: In i210 controller the sendSlope and loCredit parameters from
@@ -1782,9 +1854,27 @@ static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
 	 * configuration' in respect to these parameters.
 	 */
 
-	netdev_dbg(netdev, "CBS %s: queue %d idleslope %d sendslope %d hiCredit %d locredit %d\n",
-		   (enable) ? "enabled" : "disabled", queue,
-		   idleslope, sendslope, hicredit, locredit);
+	netdev_dbg(netdev, "Qav Tx mode: cbs %s, launchtime %s, queue %d \
+			    idleslope %d sendslope %d hiCredit %d \
+			    locredit %d\n",
+		   (ring->cbs_enable) ? "enabled" : "disabled",
+		   (ring->launchtime_enable) ? "enabled" : "disabled", queue,
+		   ring->idleslope, ring->sendslope, ring->hicredit,
+		   ring->locredit);
+}
+
+static int igb_save_txtime_params(struct igb_adapter *adapter, int queue,
+				  bool enable)
+{
+	struct igb_ring *ring;
+
+	if (queue < 0 || queue > adapter->num_tx_queues)
+		return -EINVAL;
+
+	ring = adapter->tx_ring[queue];
+	ring->launchtime_enable = enable;
+
+	return 0;
 }
 
 static int igb_save_cbs_params(struct igb_adapter *adapter, int queue,
@@ -1807,21 +1897,15 @@ static int igb_save_cbs_params(struct igb_adapter *adapter, int queue,
 	return 0;
 }
 
-static bool is_any_cbs_enabled(struct igb_adapter *adapter)
-{
-	struct igb_ring *ring;
-	int i;
-
-	for (i = 0; i < adapter->num_tx_queues; i++) {
-		ring = adapter->tx_ring[i];
-
-		if (ring->cbs_enable)
-			return true;
-	}
-
-	return false;
-}
-
+/**
+ *  igb_setup_tx_mode - Switch to/from Qav Tx mode when applicable
+ *  @adapter: pointer to adapter struct
+ *
+ *  Configure TQAVCTRL register switching the controller's Tx mode
+ *  if FQTSS mode is enabled or disabled. Additionally, will issue
+ *  a call to igb_config_tx_modes() per queue so any previously saved
+ *  Tx parameters are applied.
+ **/
 static void igb_setup_tx_mode(struct igb_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
@@ -1836,11 +1920,11 @@ static void igb_setup_tx_mode(struct igb_adapter *adapter)
 		int i, max_queue;
 
 		/* Configure TQAVCTRL register: set transmit mode to 'Qav',
-		 * set data fetch arbitration to 'round robin' and set data
-		 * transfer arbitration to 'credit shaper algorithm.
+		 * set data fetch arbitration to 'round robin', set SP_WAIT_SR
+		 * so SP queues wait for SR ones.
 		 */
 		val = rd32(E1000_I210_TQAVCTRL);
-		val |= E1000_TQAVCTRL_XMIT_MODE | E1000_TQAVCTRL_DATATRANARB;
+		val |= E1000_TQAVCTRL_XMIT_MODE | E1000_TQAVCTRL_SP_WAIT_SR;
 		val &= ~E1000_TQAVCTRL_DATAFETCHARB;
 		wr32(E1000_I210_TQAVCTRL, val);
 
@@ -1881,11 +1965,7 @@ static void igb_setup_tx_mode(struct igb_adapter *adapter)
 			    adapter->num_tx_queues : I210_SR_QUEUES_NUM;
 
 		for (i = 0; i < max_queue; i++) {
-			struct igb_ring *ring = adapter->tx_ring[i];
-
-			igb_configure_cbs(adapter, i, ring->cbs_enable,
-					  ring->idleslope, ring->sendslope,
-					  ring->hicredit, ring->locredit);
+			igb_config_tx_modes(adapter, i);
 		}
 	} else {
 		wr32(E1000_RXPBS, I210_RXPBSIZE_DEFAULT);
@@ -2459,6 +2539,19 @@ igb_features_check(struct sk_buff *skb, struct net_device *dev,
 	return features;
 }
 
+static void igb_offload_apply(struct igb_adapter *adapter, s32 queue)
+{
+	if (!is_fqtss_enabled(adapter)) {
+		enable_fqtss(adapter, true);
+		return;
+	}
+
+	igb_config_tx_modes(adapter, queue);
+
+	if (!is_any_cbs_enabled(adapter) && !is_any_txtime_enabled(adapter))
+		enable_fqtss(adapter, false);
+}
+
 static int igb_offload_cbs(struct igb_adapter *adapter,
 			   struct tc_cbs_qopt_offload *qopt)
 {
@@ -2479,17 +2572,7 @@ static int igb_offload_cbs(struct igb_adapter *adapter,
 	if (err)
 		return err;
 
-	if (is_fqtss_enabled(adapter)) {
-		igb_configure_cbs(adapter, qopt->queue, qopt->enable,
-				  qopt->idleslope, qopt->sendslope,
-				  qopt->hicredit, qopt->locredit);
-
-		if (!is_any_cbs_enabled(adapter))
-			enable_fqtss(adapter, false);
-
-	} else {
-		enable_fqtss(adapter, true);
-	}
+	igb_offload_apply(adapter, qopt->queue);
 
 	return 0;
 }
@@ -2698,7 +2781,7 @@ static int igb_setup_tc_cls_flower(struct igb_adapter *adapter,
 	case TC_CLSFLOWER_STATS:
 		return -EOPNOTSUPP;
 	default:
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 }
 
@@ -2728,7 +2811,7 @@ static int igb_setup_tc_block(struct igb_adapter *adapter,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, igb_setup_tc_block_cb,
-					     adapter, adapter);
+					     adapter, adapter, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, igb_setup_tc_block_cb,
 					adapter);
@@ -2738,6 +2821,29 @@ static int igb_setup_tc_block(struct igb_adapter *adapter,
 	}
 }
 
+static int igb_offload_txtime(struct igb_adapter *adapter,
+			      struct tc_etf_qopt_offload *qopt)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	int err;
+
+	/* Launchtime offloading is only supported by i210 controller. */
+	if (hw->mac.type != e1000_i210)
+		return -EOPNOTSUPP;
+
+	/* Launchtime offloading is only supported by queues 0 and 1. */
+	if (qopt->queue < 0 || qopt->queue > 1)
+		return -EINVAL;
+
+	err = igb_save_txtime_params(adapter, qopt->queue, qopt->enable);
+	if (err)
+		return err;
+
+	igb_offload_apply(adapter, qopt->queue);
+
+	return 0;
+}
+
 static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			void *type_data)
 {
@@ -2748,6 +2854,8 @@ static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
 		return igb_offload_cbs(adapter, type_data);
 	case TC_SETUP_BLOCK:
 		return igb_setup_tc_block(adapter, type_data);
+	case TC_SETUP_QDISC_ETF:
+		return igb_offload_txtime(adapter, type_data);
 
 	default:
 		return -EOPNOTSUPP;
@@ -5067,6 +5175,7 @@ bool igb_has_link(struct igb_adapter *adapter)
 	case e1000_media_type_copper:
 		if (!hw->mac.get_link_status)
 			return true;
+		/* fall through */
 	case e1000_media_type_internal_serdes:
 		hw->mac.ops.check_for_link(hw);
 		link_active = !hw->mac.get_link_status;
@@ -5568,11 +5677,14 @@ set_itr_now:
 	}
 }
 
-static void igb_tx_ctxtdesc(struct igb_ring *tx_ring, u32 vlan_macip_lens,
-			    u32 type_tucmd, u32 mss_l4len_idx)
+static void igb_tx_ctxtdesc(struct igb_ring *tx_ring,
+			    struct igb_tx_buffer *first,
+			    u32 vlan_macip_lens, u32 type_tucmd,
+			    u32 mss_l4len_idx)
 {
 	struct e1000_adv_tx_context_desc *context_desc;
 	u16 i = tx_ring->next_to_use;
+	struct timespec64 ts;
 
 	context_desc = IGB_TX_CTXTDESC(tx_ring, i);
 
@@ -5587,9 +5699,18 @@ static void igb_tx_ctxtdesc(struct igb_ring *tx_ring, u32 vlan_macip_lens,
 		mss_l4len_idx |= tx_ring->reg_idx << 4;
 
 	context_desc->vlan_macip_lens	= cpu_to_le32(vlan_macip_lens);
-	context_desc->seqnum_seed	= 0;
 	context_desc->type_tucmd_mlhl	= cpu_to_le32(type_tucmd);
 	context_desc->mss_l4len_idx	= cpu_to_le32(mss_l4len_idx);
+
+	/* We assume there is always a valid tx time available. Invalid times
+	 * should have been handled by the upper layers.
+	 */
+	if (tx_ring->launchtime_enable) {
+		ts = ns_to_timespec64(first->skb->tstamp);
+		context_desc->seqnum_seed = cpu_to_le32(ts.tv_nsec / 32);
+	} else {
+		context_desc->seqnum_seed = 0;
+	}
 }
 
 static int igb_tso(struct igb_ring *tx_ring,
@@ -5672,7 +5793,8 @@ static int igb_tso(struct igb_ring *tx_ring,
 	vlan_macip_lens |= (ip.hdr - skb->data) << E1000_ADVTXD_MACLEN_SHIFT;
 	vlan_macip_lens |= first->tx_flags & IGB_TX_FLAGS_VLAN_MASK;
 
-	igb_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, mss_l4len_idx);
+	igb_tx_ctxtdesc(tx_ring, first, vlan_macip_lens,
+			type_tucmd, mss_l4len_idx);
 
 	return 1;
 }
@@ -5714,6 +5836,7 @@ csum_failed:
 			type_tucmd = E1000_ADVTXD_TUCMD_L4T_SCTP;
 			break;
 		}
+		/* fall through */
 	default:
 		skb_checksum_help(skb);
 		goto csum_failed;
@@ -5727,7 +5850,7 @@ no_csum:
 	vlan_macip_lens |= skb_network_offset(skb) << E1000_ADVTXD_MACLEN_SHIFT;
 	vlan_macip_lens |= first->tx_flags & IGB_TX_FLAGS_VLAN_MASK;
 
-	igb_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, 0);
+	igb_tx_ctxtdesc(tx_ring, first, vlan_macip_lens, type_tucmd, 0);
 }
 
 #define IGB_SET_FLAG(_input, _flag, _result) \
@@ -5909,7 +6032,7 @@ static int igb_tx_map(struct igb_ring *tx_ring,
 	 * We also need this memory barrier to make certain all of the
 	 * status bits have been updated before next_to_watch is written.
 	 */
-	wmb();
+	dma_wmb();
 
 	/* set next_to_watch value indicating a packet is present */
 	first->next_to_watch = tx_desc;
@@ -6015,8 +6138,6 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 		}
 	}
 
-	skb_tx_timestamp(skb);
-
 	if (skb_vlan_tag_present(skb)) {
 		tx_flags |= IGB_TX_FLAGS_VLAN;
 		tx_flags |= (skb_vlan_tag_get(skb) << IGB_TX_FLAGS_VLAN_SHIFT);
@@ -6032,6 +6153,8 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 	else if (!tso)
 		igb_tx_csum(tx_ring, first);
 
+	skb_tx_timestamp(skb);
+
 	if (igb_tx_map(tx_ring, first, hdr_len))
 		goto cleanup_tx_tstamp;
 
@@ -8409,7 +8532,7 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
 		 * applicable for weak-ordered memory model archs,
 		 * such as IA-64).
 		 */
-		wmb();
+		dma_wmb();
 		writel(i, rx_ring->tail);
 	}
 }
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index f818f060e5a7..e0c989ffb2b3 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -2102,6 +2102,7 @@ csum_failed:
 			type_tucmd = E1000_ADVTXD_TUCMD_L4T_SCTP;
 			break;
 		}
+		/* fall through */
 	default:
 		skb_checksum_help(skb);
 		goto csum_failed;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 144d5fe6b944..4fc906c6166b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -855,7 +855,8 @@ void ixgbe_free_rx_resources(struct ixgbe_ring *);
 void ixgbe_free_tx_resources(struct ixgbe_ring *);
 void ixgbe_configure_rx_ring(struct ixgbe_adapter *, struct ixgbe_ring *);
 void ixgbe_configure_tx_ring(struct ixgbe_adapter *, struct ixgbe_ring *);
-void ixgbe_disable_rx_queue(struct ixgbe_adapter *adapter, struct ixgbe_ring *);
+void ixgbe_disable_rx(struct ixgbe_adapter *adapter);
+void ixgbe_disable_tx(struct ixgbe_adapter *adapter);
 void ixgbe_update_stats(struct ixgbe_adapter *adapter);
 int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter);
 bool ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index bd1ba88ec1d5..e5a8461fe6a9 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -511,7 +511,7 @@ static void ixgbe_set_msglevel(struct net_device *netdev, u32 data)
 
 static int ixgbe_get_regs_len(struct net_device *netdev)
 {
-#define IXGBE_REGS_LEN  1139
+#define IXGBE_REGS_LEN  1145
 	return IXGBE_REGS_LEN * sizeof(u32);
 }
 
@@ -874,6 +874,14 @@ static void ixgbe_get_regs(struct net_device *netdev,
 	/* X540 specific DCB registers  */
 	regs_buff[1137] = IXGBE_READ_REG(hw, IXGBE_RTTQCNCR);
 	regs_buff[1138] = IXGBE_READ_REG(hw, IXGBE_RTTQCNTG);
+
+	/* Security config registers */
+	regs_buff[1139] = IXGBE_READ_REG(hw, IXGBE_SECTXCTRL);
+	regs_buff[1140] = IXGBE_READ_REG(hw, IXGBE_SECTXSTAT);
+	regs_buff[1141] = IXGBE_READ_REG(hw, IXGBE_SECTXBUFFAF);
+	regs_buff[1142] = IXGBE_READ_REG(hw, IXGBE_SECTXMINIFG);
+	regs_buff[1143] = IXGBE_READ_REG(hw, IXGBE_SECRXCTRL);
+	regs_buff[1144] = IXGBE_READ_REG(hw, IXGBE_SECRXSTAT);
 }
 
 static int ixgbe_get_eeprom_len(struct net_device *netdev)
@@ -1690,35 +1698,17 @@ static int ixgbe_intr_test(struct ixgbe_adapter *adapter, u64 *data)
 
 static void ixgbe_free_desc_rings(struct ixgbe_adapter *adapter)
 {
-	struct ixgbe_ring *tx_ring = &adapter->test_tx_ring;
-	struct ixgbe_ring *rx_ring = &adapter->test_rx_ring;
-	struct ixgbe_hw *hw = &adapter->hw;
-	u32 reg_ctl;
-
-	/* shut down the DMA engines now so they can be reinitialized later */
+	/* Shut down the DMA engines now so they can be reinitialized later,
+	 * since the test rings and normally used rings should overlap on
+	 * queue 0 we can just use the standard disable Rx/Tx calls and they
+	 * will take care of disabling the test rings for us.
+	 */
 
 	/* first Rx */
-	hw->mac.ops.disable_rx(hw);
-	ixgbe_disable_rx_queue(adapter, rx_ring);
+	ixgbe_disable_rx(adapter);
 
 	/* now Tx */
-	reg_ctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(tx_ring->reg_idx));
-	reg_ctl &= ~IXGBE_TXDCTL_ENABLE;
-	IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(tx_ring->reg_idx), reg_ctl);
-
-	switch (hw->mac.type) {
-	case ixgbe_mac_82599EB:
-	case ixgbe_mac_X540:
-	case ixgbe_mac_X550:
-	case ixgbe_mac_X550EM_x:
-	case ixgbe_mac_x550em_a:
-		reg_ctl = IXGBE_READ_REG(hw, IXGBE_DMATXCTL);
-		reg_ctl &= ~IXGBE_DMATXCTL_TE;
-		IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL, reg_ctl);
-		break;
-	default:
-		break;
-	}
+	ixgbe_disable_tx(adapter);
 
 	ixgbe_reset(adapter);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 62e57b05a0ae..447098005490 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -4022,38 +4022,6 @@ static void ixgbe_rx_desc_queue_enable(struct ixgbe_adapter *adapter,
 	}
 }
 
-void ixgbe_disable_rx_queue(struct ixgbe_adapter *adapter,
-			    struct ixgbe_ring *ring)
-{
-	struct ixgbe_hw *hw = &adapter->hw;
-	int wait_loop = IXGBE_MAX_RX_DESC_POLL;
-	u32 rxdctl;
-	u8 reg_idx = ring->reg_idx;
-
-	if (ixgbe_removed(hw->hw_addr))
-		return;
-	rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
-	rxdctl &= ~IXGBE_RXDCTL_ENABLE;
-
-	/* write value back with RXDCTL.ENABLE bit cleared */
-	IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);
-
-	if (hw->mac.type == ixgbe_mac_82598EB &&
-	    !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP))
-		return;
-
-	/* the hardware may take up to 100us to really disable the rx queue */
-	do {
-		udelay(10);
-		rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
-	} while (--wait_loop && (rxdctl & IXGBE_RXDCTL_ENABLE));
-
-	if (!wait_loop) {
-		e_err(drv, "RXDCTL.ENABLE on Rx queue %d not cleared within "
-		      "the polling period\n", reg_idx);
-	}
-}
-
 void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 			     struct ixgbe_ring *ring)
 {
@@ -4063,9 +4031,13 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 	u32 rxdctl;
 	u8 reg_idx = ring->reg_idx;
 
-	/* disable queue to avoid issues while updating state */
+	/* disable queue to avoid use of these values while updating state */
 	rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
-	ixgbe_disable_rx_queue(adapter, ring);
+	rxdctl &= ~IXGBE_RXDCTL_ENABLE;
+
+	/* write value back with RXDCTL.ENABLE bit cleared */
+	IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);
+	IXGBE_WRITE_FLUSH(hw);
 
 	IXGBE_WRITE_REG(hw, IXGBE_RDBAL(reg_idx), (rdba & DMA_BIT_MASK(32)));
 	IXGBE_WRITE_REG(hw, IXGBE_RDBAH(reg_idx), (rdba >> 32));
@@ -5275,6 +5247,8 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
 static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter,
 			     struct ixgbe_fwd_adapter *accel)
 {
+	u16 rss_i = adapter->ring_feature[RING_F_RSS].indices;
+	int num_tc = netdev_get_num_tc(adapter->netdev);
 	struct net_device *vdev = accel->netdev;
 	int i, baseq, err;
 
@@ -5286,6 +5260,11 @@ static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter,
 	accel->rx_base_queue = baseq;
 	accel->tx_base_queue = baseq;
 
+	/* record configuration for macvlan interface in vdev */
+	for (i = 0; i < num_tc; i++)
+		netdev_bind_sb_channel_queue(adapter->netdev, vdev,
+					     i, rss_i, baseq + (rss_i * i));
+
 	for (i = 0; i < adapter->num_rx_queues_per_pool; i++)
 		adapter->rx_ring[baseq + i]->netdev = vdev;
 
@@ -5310,6 +5289,10 @@ static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter,
 
 	netdev_err(vdev, "L2FW offload disabled due to L2 filter error\n");
 
+	/* unbind the queues and drop the subordinate channel config */
+	netdev_unbind_sb_channel(adapter->netdev, vdev);
+	netdev_set_sb_channel(vdev, 0);
+
 	clear_bit(accel->pool, adapter->fwd_bitmask);
 	kfree(accel);
 
@@ -5622,6 +5605,212 @@ void ixgbe_up(struct ixgbe_adapter *adapter)
 	ixgbe_up_complete(adapter);
 }
 
+static unsigned long ixgbe_get_completion_timeout(struct ixgbe_adapter *adapter)
+{
+	u16 devctl2;
+
+	pcie_capability_read_word(adapter->pdev, PCI_EXP_DEVCTL2, &devctl2);
+
+	switch (devctl2 & IXGBE_PCIDEVCTRL2_TIMEO_MASK) {
+	case IXGBE_PCIDEVCTRL2_17_34s:
+	case IXGBE_PCIDEVCTRL2_4_8s:
+		/* For now we cap the upper limit on delay to 2 seconds
+		 * as we end up going up to 34 seconds of delay in worst
+		 * case timeout value.
+		 */
+	case IXGBE_PCIDEVCTRL2_1_2s:
+		return 2000000ul;	/* 2.0 s */
+	case IXGBE_PCIDEVCTRL2_260_520ms:
+		return 520000ul;	/* 520 ms */
+	case IXGBE_PCIDEVCTRL2_65_130ms:
+		return 130000ul;	/* 130 ms */
+	case IXGBE_PCIDEVCTRL2_16_32ms:
+		return 32000ul;		/* 32 ms */
+	case IXGBE_PCIDEVCTRL2_1_2ms:
+		return 2000ul;		/* 2 ms */
+	case IXGBE_PCIDEVCTRL2_50_100us:
+		return 100ul;		/* 100 us */
+	case IXGBE_PCIDEVCTRL2_16_32ms_def:
+		return 32000ul;		/* 32 ms */
+	default:
+		break;
+	}
+
+	/* We shouldn't need to hit this path, but just in case default as
+	 * though completion timeout is not supported and support 32ms.
+	 */
+	return 32000ul;
+}
+
+void ixgbe_disable_rx(struct ixgbe_adapter *adapter)
+{
+	unsigned long wait_delay, delay_interval;
+	struct ixgbe_hw *hw = &adapter->hw;
+	int i, wait_loop;
+	u32 rxdctl;
+
+	/* disable receives */
+	hw->mac.ops.disable_rx(hw);
+
+	if (ixgbe_removed(hw->hw_addr))
+		return;
+
+	/* disable all enabled Rx queues */
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		struct ixgbe_ring *ring = adapter->rx_ring[i];
+		u8 reg_idx = ring->reg_idx;
+
+		rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
+		rxdctl &= ~IXGBE_RXDCTL_ENABLE;
+		rxdctl |= IXGBE_RXDCTL_SWFLSH;
+
+		/* write value back with RXDCTL.ENABLE bit cleared */
+		IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);
+	}
+
+	/* RXDCTL.EN may not change on 82598 if link is down, so skip it */
+	if (hw->mac.type == ixgbe_mac_82598EB &&
+	    !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP))
+		return;
+
+	/* Determine our minimum delay interval. We will increase this value
+	 * with each subsequent test. This way if the device returns quickly
+	 * we should spend as little time as possible waiting, however as
+	 * the time increases we will wait for larger periods of time.
+	 *
+	 * The trick here is that we increase the interval using the
+	 * following pattern: 1x 3x 5x 7x 9x 11x 13x 15x 17x 19x. The result
+	 * of that wait is that it totals up to 100x whatever interval we
+	 * choose. Since our minimum wait is 100us we can just divide the
+	 * total timeout by 100 to get our minimum delay interval.
+	 */
+	delay_interval = ixgbe_get_completion_timeout(adapter) / 100;
+
+	wait_loop = IXGBE_MAX_RX_DESC_POLL;
+	wait_delay = delay_interval;
+
+	while (wait_loop--) {
+		usleep_range(wait_delay, wait_delay + 10);
+		wait_delay += delay_interval * 2;
+		rxdctl = 0;
+
+		/* OR together the reading of all the active RXDCTL registers,
+		 * and then test the result. We need the disable to complete
+		 * before we start freeing the memory and invalidating the
+		 * DMA mappings.
+		 */
+		for (i = 0; i < adapter->num_rx_queues; i++) {
+			struct ixgbe_ring *ring = adapter->rx_ring[i];
+			u8 reg_idx = ring->reg_idx;
+
+			rxdctl |= IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
+		}
+
+		if (!(rxdctl & IXGBE_RXDCTL_ENABLE))
+			return;
+	}
+
+	e_err(drv,
+	      "RXDCTL.ENABLE for one or more queues not cleared within the polling period\n");
+}
+
+void ixgbe_disable_tx(struct ixgbe_adapter *adapter)
+{
+	unsigned long wait_delay, delay_interval;
+	struct ixgbe_hw *hw = &adapter->hw;
+	int i, wait_loop;
+	u32 txdctl;
+
+	if (ixgbe_removed(hw->hw_addr))
+		return;
+
+	/* disable all enabled Tx queues */
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		struct ixgbe_ring *ring = adapter->tx_ring[i];
+		u8 reg_idx = ring->reg_idx;
+
+		IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH);
+	}
+
+	/* disable all enabled XDP Tx queues */
+	for (i = 0; i < adapter->num_xdp_queues; i++) {
+		struct ixgbe_ring *ring = adapter->xdp_ring[i];
+		u8 reg_idx = ring->reg_idx;
+
+		IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH);
+	}
+
+	/* If the link is not up there shouldn't be much in the way of
+	 * pending transactions. Those that are left will be flushed out
+	 * when the reset logic goes through the flush sequence to clean out
+	 * the pending Tx transactions.
+	 */
+	if (!(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP))
+		goto dma_engine_disable;
+
+	/* Determine our minimum delay interval. We will increase this value
+	 * with each subsequent test. This way if the device returns quickly
+	 * we should spend as little time as possible waiting, however as
+	 * the time increases we will wait for larger periods of time.
+	 *
+	 * The trick here is that we increase the interval using the
+	 * following pattern: 1x 3x 5x 7x 9x 11x 13x 15x 17x 19x. The result
+	 * of that wait is that it totals up to 100x whatever interval we
+	 * choose. Since our minimum wait is 100us we can just divide the
+	 * total timeout by 100 to get our minimum delay interval.
+	 */
+	delay_interval = ixgbe_get_completion_timeout(adapter) / 100;
+
+	wait_loop = IXGBE_MAX_RX_DESC_POLL;
+	wait_delay = delay_interval;
+
+	while (wait_loop--) {
+		usleep_range(wait_delay, wait_delay + 10);
+		wait_delay += delay_interval * 2;
+		txdctl = 0;
+
+		/* OR together the reading of all the active TXDCTL registers,
+		 * and then test the result. We need the disable to complete
+		 * before we start freeing the memory and invalidating the
+		 * DMA mappings.
+		 */
+		for (i = 0; i < adapter->num_tx_queues; i++) {
+			struct ixgbe_ring *ring = adapter->tx_ring[i];
+			u8 reg_idx = ring->reg_idx;
+
+			txdctl |= IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx));
+		}
+		for (i = 0; i < adapter->num_xdp_queues; i++) {
+			struct ixgbe_ring *ring = adapter->xdp_ring[i];
+			u8 reg_idx = ring->reg_idx;
+
+			txdctl |= IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx));
+		}
+
+		if (!(txdctl & IXGBE_TXDCTL_ENABLE))
+			goto dma_engine_disable;
+	}
+
+	e_err(drv,
+	      "TXDCTL.ENABLE for one or more queues not cleared within the polling period\n");
+
+dma_engine_disable:
+	/* Disable the Tx DMA engine on 82599 and later MAC */
+	switch (hw->mac.type) {
+	case ixgbe_mac_82599EB:
+	case ixgbe_mac_X540:
+	case ixgbe_mac_X550:
+	case ixgbe_mac_X550EM_x:
+	case ixgbe_mac_x550em_a:
+		IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL,
+				(IXGBE_READ_REG(hw, IXGBE_DMATXCTL) &
+				 ~IXGBE_DMATXCTL_TE));
+		/* fall through */
+	default:
+		break;
+	}
+}
+
 void ixgbe_reset(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -5803,24 +5992,19 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
 	if (test_and_set_bit(__IXGBE_DOWN, &adapter->state))
 		return; /* do nothing if already down */
 
-	/* disable receives */
-	hw->mac.ops.disable_rx(hw);
+	/* Shut off incoming Tx traffic */
+	netif_tx_stop_all_queues(netdev);
 
-	/* disable all enabled rx queues */
-	for (i = 0; i < adapter->num_rx_queues; i++)
-		/* this call also flushes the previous write */
-		ixgbe_disable_rx_queue(adapter, adapter->rx_ring[i]);
+	/* call carrier off first to avoid false dev_watchdog timeouts */
+	netif_carrier_off(netdev);
+	netif_tx_disable(netdev);
 
-	usleep_range(10000, 20000);
+	/* Disable Rx */
+	ixgbe_disable_rx(adapter);
 
 	/* synchronize_sched() needed for pending XDP buffers to drain */
 	if (adapter->xdp_ring[0])
 		synchronize_sched();
-	netif_tx_stop_all_queues(netdev);
-
-	/* call carrier off first to avoid false dev_watchdog timeouts */
-	netif_carrier_off(netdev);
-	netif_tx_disable(netdev);
 
 	ixgbe_irq_disable(adapter);
 
@@ -5848,30 +6032,7 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
 	}
 
 	/* disable transmits in the hardware now that interrupts are off */
-	for (i = 0; i < adapter->num_tx_queues; i++) {
-		u8 reg_idx = adapter->tx_ring[i]->reg_idx;
-		IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH);
-	}
-	for (i = 0; i < adapter->num_xdp_queues; i++) {
-		u8 reg_idx = adapter->xdp_ring[i]->reg_idx;
-
-		IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH);
-	}
-
-	/* Disable the Tx DMA engine on 82599 and later MAC */
-	switch (hw->mac.type) {
-	case ixgbe_mac_82599EB:
-	case ixgbe_mac_X540:
-	case ixgbe_mac_X550:
-	case ixgbe_mac_X550EM_x:
-	case ixgbe_mac_x550em_a:
-		IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL,
-				(IXGBE_READ_REG(hw, IXGBE_DMATXCTL) &
-				 ~IXGBE_DMATXCTL_TE));
-		break;
-	default:
-		break;
-	}
+	ixgbe_disable_tx(adapter);
 
 	if (!pci_channel_offline(adapter->pdev))
 		ixgbe_reset(adapter);
@@ -6458,6 +6619,11 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
+	if (adapter->xdp_prog) {
+		e_warn(probe, "MTU cannot be changed while XDP program is loaded\n");
+		return -EPERM;
+	}
+
 	/*
 	 * For 82599EB we cannot allow legacy VFs to enable their receive
 	 * paths when MTU greater than 1500 is configured.  So display a
@@ -8197,25 +8363,25 @@ static void ixgbe_atr(struct ixgbe_ring *ring,
 					      input, common, ring->queue_index);
 }
 
+#ifdef IXGBE_FCOE
 static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
-			      void *accel_priv, select_queue_fallback_t fallback)
+			      struct net_device *sb_dev,
+			      select_queue_fallback_t fallback)
 {
-	struct ixgbe_fwd_adapter *fwd_adapter = accel_priv;
 	struct ixgbe_adapter *adapter;
-	int txq;
-#ifdef IXGBE_FCOE
 	struct ixgbe_ring_feature *f;
-#endif
+	int txq;
 
-	if (fwd_adapter) {
-		adapter = netdev_priv(dev);
-		txq = reciprocal_scale(skb_get_hash(skb),
-				       adapter->num_rx_queues_per_pool);
+	if (sb_dev) {
+		u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
+		struct net_device *vdev = sb_dev;
 
-		return txq + fwd_adapter->tx_base_queue;
-	}
+		txq = vdev->tc_to_txq[tc].offset;
+		txq += reciprocal_scale(skb_get_hash(skb),
+					vdev->tc_to_txq[tc].count);
 
-#ifdef IXGBE_FCOE
+		return txq;
+	}
 
 	/*
 	 * only execute the code below if protocol is FCoE
@@ -8226,11 +8392,11 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 	case htons(ETH_P_FIP):
 		adapter = netdev_priv(dev);
 
-		if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)
+		if (!sb_dev && (adapter->flags & IXGBE_FLAG_FCOE_ENABLED))
 			break;
 		/* fall through */
 	default:
-		return fallback(dev, skb);
+		return fallback(dev, skb, sb_dev);
 	}
 
 	f = &adapter->ring_feature[RING_F_FCOE];
@@ -8242,11 +8408,9 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 		txq -= f->indices;
 
 	return txq + f->offset;
-#else
-	return fallback(dev, skb);
-#endif
 }
 
+#endif
 static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
 			       struct xdp_frame *xdpf)
 {
@@ -8766,6 +8930,11 @@ static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, void *data)
 	/* if we cannot find a free pool then disable the offload */
 	netdev_err(vdev, "L2FW offload disabled due to lack of queue resources\n");
 	macvlan_release_l2fw_offload(vdev);
+
+	/* unbind the queues and drop the subordinate channel config */
+	netdev_unbind_sb_channel(adapter->netdev, vdev);
+	netdev_set_sb_channel(vdev, 0);
+
 	kfree(accel);
 
 	return 0;
@@ -9329,7 +9498,7 @@ static int ixgbe_setup_tc_block(struct net_device *dev,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, ixgbe_setup_tc_block_cb,
-					     adapter, adapter);
+					     adapter, adapter, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, ixgbe_setup_tc_block_cb,
 					adapter);
@@ -9393,6 +9562,11 @@ static netdev_features_t ixgbe_fix_features(struct net_device *netdev,
 	if (!(adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE))
 		features &= ~NETIF_F_LRO;
 
+	if (adapter->xdp_prog && (features & NETIF_F_LRO)) {
+		e_dev_err("LRO is not supported with XDP\n");
+		features &= ~NETIF_F_LRO;
+	}
+
 	return features;
 }
 
@@ -9769,6 +9943,13 @@ static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
 	if (!macvlan_supports_dest_filter(vdev))
 		return ERR_PTR(-EMEDIUMTYPE);
 
+	/* We need to lock down the macvlan to be a single queue device so that
+	 * we can reuse the tc_to_txq field in the macvlan netdev to represent
+	 * the queue mapping to our netdev.
+	 */
+	if (netif_is_multiqueue(vdev))
+		return ERR_PTR(-ERANGE);
+
 	pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools);
 	if (pool == adapter->num_rx_pools) {
 		u16 used_pools = adapter->num_vfs + adapter->num_rx_pools;
@@ -9825,6 +10006,7 @@ static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
 		return ERR_PTR(-ENOMEM);
 
 	set_bit(pool, adapter->fwd_bitmask);
+	netdev_set_sb_channel(vdev, pool);
 	accel->pool = pool;
 	accel->netdev = vdev;
 
@@ -9866,6 +10048,10 @@ static void ixgbe_fwd_del(struct net_device *pdev, void *priv)
 		ring->netdev = NULL;
 	}
 
+	/* unbind the queues and drop the subordinate channel config */
+	netdev_unbind_sb_channel(pdev, accel->netdev);
+	netdev_set_sb_channel(accel->netdev, 0);
+
 	clear_bit(accel->pool, adapter->fwd_bitmask);
 	kfree(accel);
 }
@@ -9966,7 +10152,6 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	case XDP_SETUP_PROG:
 		return ixgbe_xdp_setup(dev, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!(adapter->xdp_prog);
 		xdp->prog_id = adapter->xdp_prog ?
 			adapter->xdp_prog->aux->id : 0;
 		return 0;
@@ -10026,7 +10211,6 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_open		= ixgbe_open,
 	.ndo_stop		= ixgbe_close,
 	.ndo_start_xmit		= ixgbe_xmit_frame,
-	.ndo_select_queue	= ixgbe_select_queue,
 	.ndo_set_rx_mode	= ixgbe_set_rx_mode,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= ixgbe_set_mac,
@@ -10049,6 +10233,7 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_poll_controller	= ixgbe_netpoll,
 #endif
 #ifdef IXGBE_FCOE
+	.ndo_select_queue	= ixgbe_select_queue,
 	.ndo_fcoe_ddp_setup = ixgbe_fcoe_ddp_get,
 	.ndo_fcoe_ddp_target = ixgbe_fcoe_ddp_target,
 	.ndo_fcoe_ddp_done = ixgbe_fcoe_ddp_put,
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 59416eddd840..d86446d202d5 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -4462,7 +4462,6 @@ static int ixgbevf_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	case XDP_SETUP_PROG:
 		return ixgbevf_xdp_setup(dev, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!(adapter->xdp_prog);
 		xdp->prog_id = adapter->xdp_prog ?
 			       adapter->xdp_prog->aux->id : 0;
 		return 0;
diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index 06ff185eb188..a5ab6f3403ae 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -1911,10 +1911,10 @@ jme_wait_link(struct jme_adapter *jme)
 {
 	u32 phylink, to = JME_WAIT_LINK_TIME;
 
-	mdelay(1000);
+	msleep(1000);
 	phylink = jme_linkstat_from_phy(jme);
 	while (!(phylink & PHY_LINK_UP) && (to -= 10) > 0) {
-		mdelay(10);
+		usleep_range(10000, 11000);
 		phylink = jme_linkstat_from_phy(jme);
 	}
 }
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index afc810069440..7a637b51c7d2 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -563,14 +563,6 @@ ltq_etop_set_multicast_list(struct net_device *dev)
 	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
-static u16
-ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb,
-		      void *accel_priv, select_queue_fallback_t fallback)
-{
-	/* we are currently only using the first queue */
-	return 0;
-}
-
 static int
 ltq_etop_init(struct net_device *dev)
 {
@@ -641,7 +633,7 @@ static const struct net_device_ops ltq_eth_netdev_ops = {
 	.ndo_set_mac_address = ltq_etop_set_mac_address,
 	.ndo_validate_addr = eth_validate_addr,
 	.ndo_set_rx_mode = ltq_etop_set_multicast_list,
-	.ndo_select_queue = ltq_etop_select_queue,
+	.ndo_select_queue = dev_pick_tx_zero,
 	.ndo_init = ltq_etop_init,
 	.ndo_tx_timeout = ltq_etop_tx_timeout,
 };
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 0ad2f3f7da85..bc80a678abc3 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -295,10 +295,10 @@
 #define MVNETA_RSS_LU_TABLE_SIZE	1
 
 /* Max number of Rx descriptors */
-#define MVNETA_MAX_RXD 128
+#define MVNETA_MAX_RXD 512
 
 /* Max number of Tx descriptors */
-#define MVNETA_MAX_TXD 532
+#define MVNETA_MAX_TXD 1024
 
 /* Max number of allowed TCP segments for software TSO */
 #define MVNETA_MAX_TSO_SEGS 100
@@ -328,6 +328,8 @@
 
 enum {
 	ETHTOOL_STAT_EEE_WAKEUP,
+	ETHTOOL_STAT_SKB_ALLOC_ERR,
+	ETHTOOL_STAT_REFILL_ERR,
 	ETHTOOL_MAX_STATS,
 };
 
@@ -375,6 +377,8 @@ static const struct mvneta_statistic mvneta_statistics[] = {
 	{ 0x3054, T_REG_32, "fc_sent", },
 	{ 0x300c, T_REG_32, "internal_mac_transmit_err", },
 	{ ETHTOOL_STAT_EEE_WAKEUP, T_SW, "eee_wakeup_errors", },
+	{ ETHTOOL_STAT_SKB_ALLOC_ERR, T_SW, "skb_alloc_errors", },
+	{ ETHTOOL_STAT_REFILL_ERR, T_SW, "refill_errors", },
 };
 
 struct mvneta_pcpu_stats {
@@ -479,7 +483,10 @@ struct mvneta_port {
 #define MVNETA_RXD_ERR_RESOURCE		(BIT(17) | BIT(18))
 #define MVNETA_RXD_ERR_CODE_MASK	(BIT(17) | BIT(18))
 #define MVNETA_RXD_L3_IP4		BIT(25)
-#define MVNETA_RXD_FIRST_LAST_DESC	(BIT(26) | BIT(27))
+#define MVNETA_RXD_LAST_DESC		BIT(26)
+#define MVNETA_RXD_FIRST_DESC		BIT(27)
+#define MVNETA_RXD_FIRST_LAST_DESC	(MVNETA_RXD_FIRST_DESC | \
+					 MVNETA_RXD_LAST_DESC)
 #define MVNETA_RXD_L4_CSUM_OK		BIT(30)
 
 #if defined(__LITTLE_ENDIAN)
@@ -589,9 +596,6 @@ struct mvneta_rx_queue {
 	/* num of rx descriptors in the rx descriptor ring */
 	int size;
 
-	/* counter of times when mvneta_refill() failed */
-	int missed;
-
 	u32 pkts_coal;
 	u32 time_coal;
 
@@ -609,6 +613,18 @@ struct mvneta_rx_queue {
 
 	/* Index of the next RX DMA descriptor to process */
 	int next_desc_to_proc;
+
+	/* Index of first RX DMA descriptor to refill */
+	int first_to_refill;
+	u32 refill_num;
+
+	/* pointer to uncomplete skb buffer */
+	struct sk_buff *skb;
+	int left_size;
+
+	/* error counters */
+	u32 skb_alloc_err;
+	u32 refill_err;
 };
 
 static enum cpuhp_state online_hpstate;
@@ -621,6 +637,7 @@ static int txq_number = 8;
 static int rxq_def;
 
 static int rx_copybreak __read_mostly = 256;
+static int rx_header_size __read_mostly = 128;
 
 /* HW BM need that each port be identify by a unique ID */
 static int global_port_id;
@@ -1684,13 +1701,6 @@ static void mvneta_rx_error(struct mvneta_port *pp,
 {
 	u32 status = rx_desc->status;
 
-	if (!mvneta_rxq_desc_is_first_last(status)) {
-		netdev_err(pp->dev,
-			   "bad rx status %08x (buffer oversize), size=%d\n",
-			   status, rx_desc->data_size);
-		return;
-	}
-
 	switch (status & MVNETA_RXD_ERR_CODE_MASK) {
 	case MVNETA_RXD_ERR_CRC:
 		netdev_err(pp->dev, "bad rx status %08x (crc error), size=%d\n",
@@ -1715,7 +1725,8 @@ static void mvneta_rx_error(struct mvneta_port *pp,
 static void mvneta_rx_csum(struct mvneta_port *pp, u32 status,
 			   struct sk_buff *skb)
 {
-	if ((status & MVNETA_RXD_L3_IP4) &&
+	if ((pp->dev->features & NETIF_F_RXCSUM) &&
+	    (status & MVNETA_RXD_L3_IP4) &&
 	    (status & MVNETA_RXD_L4_CSUM_OK)) {
 		skb->csum = 0;
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -1790,47 +1801,30 @@ static void mvneta_txq_done(struct mvneta_port *pp,
 	}
 }
 
-void *mvneta_frag_alloc(unsigned int frag_size)
-{
-	if (likely(frag_size <= PAGE_SIZE))
-		return netdev_alloc_frag(frag_size);
-	else
-		return kmalloc(frag_size, GFP_ATOMIC);
-}
-EXPORT_SYMBOL_GPL(mvneta_frag_alloc);
-
-void mvneta_frag_free(unsigned int frag_size, void *data)
-{
-	if (likely(frag_size <= PAGE_SIZE))
-		skb_free_frag(data);
-	else
-		kfree(data);
-}
-EXPORT_SYMBOL_GPL(mvneta_frag_free);
-
 /* Refill processing for SW buffer management */
+/* Allocate page per descriptor */
 static int mvneta_rx_refill(struct mvneta_port *pp,
 			    struct mvneta_rx_desc *rx_desc,
-			    struct mvneta_rx_queue *rxq)
-
+			    struct mvneta_rx_queue *rxq,
+			    gfp_t gfp_mask)
 {
 	dma_addr_t phys_addr;
-	void *data;
+	struct page *page;
 
-	data = mvneta_frag_alloc(pp->frag_size);
-	if (!data)
+	page = __dev_alloc_page(gfp_mask);
+	if (!page)
 		return -ENOMEM;
 
-	phys_addr = dma_map_single(pp->dev->dev.parent, data,
-				   MVNETA_RX_BUF_SIZE(pp->pkt_size),
-				   DMA_FROM_DEVICE);
+	/* map page for use */
+	phys_addr = dma_map_page(pp->dev->dev.parent, page, 0, PAGE_SIZE,
+				 DMA_FROM_DEVICE);
 	if (unlikely(dma_mapping_error(pp->dev->dev.parent, phys_addr))) {
-		mvneta_frag_free(pp->frag_size, data);
+		__free_page(page);
 		return -ENOMEM;
 	}
 
 	phys_addr += pp->rx_offset_correction;
-	mvneta_rx_desc_fill(rx_desc, phys_addr, data, rxq);
+	mvneta_rx_desc_fill(rx_desc, phys_addr, page, rxq);
 	return 0;
 }
 
@@ -1893,115 +1887,192 @@ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp,
 	for (i = 0; i < rxq->size; i++) {
 		struct mvneta_rx_desc *rx_desc = rxq->descs + i;
 		void *data = rxq->buf_virt_addr[i];
+		if (!data || !(rx_desc->buf_phys_addr))
+			continue;
 
 		dma_unmap_single(pp->dev->dev.parent, rx_desc->buf_phys_addr,
 				 MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE);
-		mvneta_frag_free(pp->frag_size, data);
+		__free_page(data);
 	}
 }
 
+static inline
+int mvneta_rx_refill_queue(struct mvneta_port *pp, struct mvneta_rx_queue *rxq)
+{
+	struct mvneta_rx_desc *rx_desc;
+	int curr_desc = rxq->first_to_refill;
+	int i;
+
+	for (i = 0; (i < rxq->refill_num) && (i < 64); i++) {
+		rx_desc = rxq->descs + curr_desc;
+		if (!(rx_desc->buf_phys_addr)) {
+			if (mvneta_rx_refill(pp, rx_desc, rxq, GFP_ATOMIC)) {
+				pr_err("Can't refill queue %d. Done %d from %d\n",
+				       rxq->id, i, rxq->refill_num);
+				rxq->refill_err++;
+				break;
+			}
+		}
+		curr_desc = MVNETA_QUEUE_NEXT_DESC(rxq, curr_desc);
+	}
+	rxq->refill_num -= i;
+	rxq->first_to_refill = curr_desc;
+
+	return i;
+}
+
 /* Main rx processing when using software buffer management */
-static int mvneta_rx_swbm(struct mvneta_port *pp, int rx_todo,
+static int mvneta_rx_swbm(struct napi_struct *napi,
+			  struct mvneta_port *pp, int budget,
 			  struct mvneta_rx_queue *rxq)
 {
-	struct mvneta_pcpu_port *port = this_cpu_ptr(pp->ports);
 	struct net_device *dev = pp->dev;
-	int rx_done;
+	int rx_todo, rx_proc;
+	int refill = 0;
 	u32 rcvd_pkts = 0;
 	u32 rcvd_bytes = 0;
 
 	/* Get number of received packets */
-	rx_done = mvneta_rxq_busy_desc_num_get(pp, rxq);
-
-	if (rx_todo > rx_done)
-		rx_todo = rx_done;
-
-	rx_done = 0;
+	rx_todo = mvneta_rxq_busy_desc_num_get(pp, rxq);
+	rx_proc = 0;
 
 	/* Fairness NAPI loop */
-	while (rx_done < rx_todo) {
+	while ((rcvd_pkts < budget) && (rx_proc < rx_todo)) {
 		struct mvneta_rx_desc *rx_desc = mvneta_rxq_next_desc_get(rxq);
-		struct sk_buff *skb;
 		unsigned char *data;
+		struct page *page;
 		dma_addr_t phys_addr;
-		u32 rx_status, frag_size;
-		int rx_bytes, err, index;
+		u32 rx_status, index;
+		int rx_bytes, skb_size, copy_size;
+		int frag_num, frag_size, frag_offset;
 
-		rx_done++;
-		rx_status = rx_desc->status;
-		rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
 		index = rx_desc - rxq->descs;
-		data = rxq->buf_virt_addr[index];
-		phys_addr = rx_desc->buf_phys_addr - pp->rx_offset_correction;
-
-		if (!mvneta_rxq_desc_is_first_last(rx_status) ||
-		    (rx_status & MVNETA_RXD_ERR_SUMMARY)) {
-			mvneta_rx_error(pp, rx_desc);
-err_drop_frame:
-			dev->stats.rx_errors++;
-			/* leave the descriptor untouched */
-			continue;
-		}
+		page = (struct page *)rxq->buf_virt_addr[index];
+		data = page_address(page);
+		/* Prefetch header */
+		prefetch(data);
 
-		if (rx_bytes <= rx_copybreak) {
-		/* better copy a small frame and not unmap the DMA region */
-			skb = netdev_alloc_skb_ip_align(dev, rx_bytes);
-			if (unlikely(!skb))
-				goto err_drop_frame;
-
-			dma_sync_single_range_for_cpu(dev->dev.parent,
-						      phys_addr,
-						      MVNETA_MH_SIZE + NET_SKB_PAD,
-						      rx_bytes,
-						      DMA_FROM_DEVICE);
-			skb_put_data(skb, data + MVNETA_MH_SIZE + NET_SKB_PAD,
-				     rx_bytes);
-
-			skb->protocol = eth_type_trans(skb, dev);
-			mvneta_rx_csum(pp, rx_status, skb);
-			napi_gro_receive(&port->napi, skb);
-
-			rcvd_pkts++;
-			rcvd_bytes += rx_bytes;
+		phys_addr = rx_desc->buf_phys_addr;
+		rx_status = rx_desc->status;
+		rx_proc++;
+		rxq->refill_num++;
+
+		if (rx_status & MVNETA_RXD_FIRST_DESC) {
+			/* Check errors only for FIRST descriptor */
+			if (rx_status & MVNETA_RXD_ERR_SUMMARY) {
+				mvneta_rx_error(pp, rx_desc);
+				dev->stats.rx_errors++;
+				/* leave the descriptor untouched */
+				continue;
+			}
+			rx_bytes = rx_desc->data_size -
+				   (ETH_FCS_LEN + MVNETA_MH_SIZE);
+
+			/* Allocate small skb for each new packet */
+			skb_size = max(rx_copybreak, rx_header_size);
+			rxq->skb = netdev_alloc_skb_ip_align(dev, skb_size);
+			if (unlikely(!rxq->skb)) {
+				netdev_err(dev,
+					   "Can't allocate skb on queue %d\n",
+					   rxq->id);
+				dev->stats.rx_dropped++;
+				rxq->skb_alloc_err++;
+				continue;
+			}
+			copy_size = min(skb_size, rx_bytes);
+
+			/* Copy data from buffer to SKB, skip Marvell header */
+			memcpy(rxq->skb->data, data + MVNETA_MH_SIZE,
+			       copy_size);
+			skb_put(rxq->skb, copy_size);
+			rxq->left_size = rx_bytes - copy_size;
+
+			mvneta_rx_csum(pp, rx_status, rxq->skb);
+			if (rxq->left_size == 0) {
+				int size = copy_size + MVNETA_MH_SIZE;
+
+				dma_sync_single_range_for_cpu(dev->dev.parent,
+							      phys_addr, 0,
+							      size,
+							      DMA_FROM_DEVICE);
+
+				/* leave the descriptor and buffer untouched */
+			} else {
+				/* refill descriptor with new buffer later */
+				rx_desc->buf_phys_addr = 0;
+
+				frag_num = 0;
+				frag_offset = copy_size + MVNETA_MH_SIZE;
+				frag_size = min(rxq->left_size,
+						(int)(PAGE_SIZE - frag_offset));
+				skb_add_rx_frag(rxq->skb, frag_num, page,
+						frag_offset, frag_size,
+						PAGE_SIZE);
+				dma_unmap_single(dev->dev.parent, phys_addr,
+						 PAGE_SIZE, DMA_FROM_DEVICE);
+				rxq->left_size -= frag_size;
+			}
+		} else {
+			/* Middle or Last descriptor */
+			if (unlikely(!rxq->skb)) {
+				pr_debug("no skb for rx_status 0x%x\n",
+					 rx_status);
+				continue;
+			}
+			if (!rxq->left_size) {
+				/* last descriptor has only FCS */
+				/* and can be discarded */
+				dma_sync_single_range_for_cpu(dev->dev.parent,
+							      phys_addr, 0,
+							      ETH_FCS_LEN,
+							      DMA_FROM_DEVICE);
+				/* leave the descriptor and buffer untouched */
+			} else {
+				/* refill descriptor with new buffer later */
+				rx_desc->buf_phys_addr = 0;
+
+				frag_num = skb_shinfo(rxq->skb)->nr_frags;
+				frag_offset = 0;
+				frag_size = min(rxq->left_size,
+						(int)(PAGE_SIZE - frag_offset));
+				skb_add_rx_frag(rxq->skb, frag_num, page,
+						frag_offset, frag_size,
+						PAGE_SIZE);
+
+				dma_unmap_single(dev->dev.parent, phys_addr,
+						 PAGE_SIZE,
+						 DMA_FROM_DEVICE);
+
+				rxq->left_size -= frag_size;
+			}
+		} /* Middle or Last descriptor */
 
-			/* leave the descriptor and buffer untouched */
+		if (!(rx_status & MVNETA_RXD_LAST_DESC))
+			/* no last descriptor this time */
 			continue;
-		}
 
-		/* Refill processing */
-		err = mvneta_rx_refill(pp, rx_desc, rxq);
-		if (err) {
-			netdev_err(dev, "Linux processing - Can't refill\n");
-			rxq->missed++;
-			goto err_drop_frame;
+		if (rxq->left_size) {
+			pr_err("get last desc, but left_size (%d) != 0\n",
+			       rxq->left_size);
+			dev_kfree_skb_any(rxq->skb);
+			rxq->left_size = 0;
+			rxq->skb = NULL;
+			continue;
 		}
-
-		frag_size = pp->frag_size;
-
-		skb = build_skb(data, frag_size > PAGE_SIZE ? 0 : frag_size);
-
-		/* After refill old buffer has to be unmapped regardless
-		 * the skb is successfully built or not.
-		 */
-		dma_unmap_single(dev->dev.parent, phys_addr,
-				 MVNETA_RX_BUF_SIZE(pp->pkt_size),
-				 DMA_FROM_DEVICE);
-
-		if (!skb)
-			goto err_drop_frame;
-
 		rcvd_pkts++;
-		rcvd_bytes += rx_bytes;
+		rcvd_bytes += rxq->skb->len;
 
 		/* Linux processing */
-		skb_reserve(skb, MVNETA_MH_SIZE + NET_SKB_PAD);
-		skb_put(skb, rx_bytes);
-
-		skb->protocol = eth_type_trans(skb, dev);
+		rxq->skb->protocol = eth_type_trans(rxq->skb, dev);
 
-		mvneta_rx_csum(pp, rx_status, skb);
+		if (dev->features & NETIF_F_GRO)
+			napi_gro_receive(napi, rxq->skb);
+		else
+			netif_receive_skb(rxq->skb);
 
-		napi_gro_receive(&port->napi, skb);
+		/* clean uncomplete skb pointer in queue */
+		rxq->skb = NULL;
+		rxq->left_size = 0;
 	}
 
 	if (rcvd_pkts) {
@@ -2013,17 +2084,20 @@ err_drop_frame:
 		u64_stats_update_end(&stats->syncp);
 	}
 
+	/* return some buffers to hardware queue, one at a time is too slow */
+	refill = mvneta_rx_refill_queue(pp, rxq);
+
 	/* Update rxq management counters */
-	mvneta_rxq_desc_num_update(pp, rxq, rx_done, rx_done);
+	mvneta_rxq_desc_num_update(pp, rxq, rx_proc, refill);
 
-	return rx_done;
+	return rcvd_pkts;
 }
 
 /* Main rx processing when using hardware buffer management */
-static int mvneta_rx_hwbm(struct mvneta_port *pp, int rx_todo,
+static int mvneta_rx_hwbm(struct napi_struct *napi,
+			  struct mvneta_port *pp, int rx_todo,
 			  struct mvneta_rx_queue *rxq)
 {
-	struct mvneta_pcpu_port *port = this_cpu_ptr(pp->ports);
 	struct net_device *dev = pp->dev;
 	int rx_done;
 	u32 rcvd_pkts = 0;
@@ -2085,7 +2159,7 @@ err_drop_frame:
 
 			skb->protocol = eth_type_trans(skb, dev);
 			mvneta_rx_csum(pp, rx_status, skb);
-			napi_gro_receive(&port->napi, skb);
+			napi_gro_receive(napi, skb);
 
 			rcvd_pkts++;
 			rcvd_bytes += rx_bytes;
@@ -2102,7 +2176,7 @@ err_drop_frame:
 		err = hwbm_pool_refill(&bm_pool->hwbm_pool, GFP_ATOMIC);
 		if (err) {
 			netdev_err(dev, "Linux processing - Can't refill\n");
-			rxq->missed++;
+			rxq->refill_err++;
 			goto err_drop_frame_ret_pool;
 		}
 
@@ -2129,7 +2203,7 @@ err_drop_frame:
 
 		mvneta_rx_csum(pp, rx_status, skb);
 
-		napi_gro_receive(&port->napi, skb);
+		napi_gro_receive(napi, skb);
 	}
 
 	if (rcvd_pkts) {
@@ -2722,9 +2796,11 @@ static int mvneta_poll(struct napi_struct *napi, int budget)
 	if (rx_queue) {
 		rx_queue = rx_queue - 1;
 		if (pp->bm_priv)
-			rx_done = mvneta_rx_hwbm(pp, budget, &pp->rxqs[rx_queue]);
+			rx_done = mvneta_rx_hwbm(napi, pp, budget,
+						 &pp->rxqs[rx_queue]);
 		else
-			rx_done = mvneta_rx_swbm(pp, budget, &pp->rxqs[rx_queue]);
+			rx_done = mvneta_rx_swbm(napi, pp, budget,
+						 &pp->rxqs[rx_queue]);
 	}
 
 	if (rx_done < budget) {
@@ -2761,9 +2837,11 @@ static int mvneta_rxq_fill(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 
 	for (i = 0; i < num; i++) {
 		memset(rxq->descs + i, 0, sizeof(struct mvneta_rx_desc));
-		if (mvneta_rx_refill(pp, rxq->descs + i, rxq) != 0) {
-			netdev_err(pp->dev, "%s:rxq %d, %d of %d buffs  filled\n",
-				__func__, rxq->id, i, num);
+		if (mvneta_rx_refill(pp, rxq->descs + i, rxq,
+				     GFP_KERNEL) != 0) {
+			netdev_err(pp->dev,
+				   "%s:rxq %d, %d of %d buffs  filled\n",
+				   __func__, rxq->id, i, num);
 			break;
 		}
 	}
@@ -2821,21 +2899,23 @@ static void mvneta_rxq_hw_init(struct mvneta_port *pp,
 	mvreg_write(pp, MVNETA_RXQ_BASE_ADDR_REG(rxq->id), rxq->descs_phys);
 	mvreg_write(pp, MVNETA_RXQ_SIZE_REG(rxq->id), rxq->size);
 
-	/* Set Offset */
-	mvneta_rxq_offset_set(pp, rxq, NET_SKB_PAD - pp->rx_offset_correction);
-
 	/* Set coalescing pkts and time */
 	mvneta_rx_pkts_coal_set(pp, rxq, rxq->pkts_coal);
 	mvneta_rx_time_coal_set(pp, rxq, rxq->time_coal);
 
 	if (!pp->bm_priv) {
-		/* Fill RXQ with buffers from RX pool */
-		mvneta_rxq_buf_size_set(pp, rxq,
-					MVNETA_RX_BUF_SIZE(pp->pkt_size));
+		/* Set Offset */
+		mvneta_rxq_offset_set(pp, rxq, 0);
+		mvneta_rxq_buf_size_set(pp, rxq, pp->frag_size);
 		mvneta_rxq_bm_disable(pp, rxq);
 		mvneta_rxq_fill(pp, rxq, rxq->size);
 	} else {
+		/* Set Offset */
+		mvneta_rxq_offset_set(pp, rxq,
+				      NET_SKB_PAD - pp->rx_offset_correction);
+
 		mvneta_rxq_bm_enable(pp, rxq);
+		/* Fill RXQ with buffers from RX pool */
 		mvneta_rxq_long_pool_set(pp, rxq);
 		mvneta_rxq_short_pool_set(pp, rxq);
 		mvneta_rxq_non_occup_desc_add(pp, rxq, rxq->size);
@@ -2864,6 +2944,9 @@ static void mvneta_rxq_deinit(struct mvneta_port *pp,
 {
 	mvneta_rxq_drop_pkts(pp, rxq);
 
+	if (rxq->skb)
+		dev_kfree_skb_any(rxq->skb);
+
 	if (rxq->descs)
 		dma_free_coherent(pp->dev->dev.parent,
 				  rxq->size * MVNETA_DESC_ALIGNED_SIZE,
@@ -2874,6 +2957,10 @@ static void mvneta_rxq_deinit(struct mvneta_port *pp,
 	rxq->last_desc         = 0;
 	rxq->next_desc_to_proc = 0;
 	rxq->descs_phys        = 0;
+	rxq->first_to_refill   = 0;
+	rxq->refill_num        = 0;
+	rxq->skb               = NULL;
+	rxq->left_size         = 0;
 }
 
 static int mvneta_txq_sw_init(struct mvneta_port *pp,
@@ -3177,8 +3264,6 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu)
 		mvneta_bm_update_mtu(pp, mtu);
 
 	pp->pkt_size = MVNETA_RX_PKT_SIZE(dev->mtu);
-	pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) +
-	                SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 	ret = mvneta_setup_rxqs(pp);
 	if (ret) {
@@ -3194,7 +3279,6 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu)
 
 	on_each_cpu(mvneta_percpu_enable, pp, true);
 	mvneta_start_dev(pp);
-	mvneta_port_up(pp);
 
 	netdev_update_features(dev);
 
@@ -3666,8 +3750,7 @@ static int mvneta_open(struct net_device *dev)
 	int ret;
 
 	pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu);
-	pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) +
-	                SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	pp->frag_size = PAGE_SIZE;
 
 	ret = mvneta_setup_rxqs(pp);
 	if (ret)
@@ -3962,6 +4045,12 @@ static void mvneta_ethtool_update_stats(struct mvneta_port *pp)
 			case ETHTOOL_STAT_EEE_WAKEUP:
 				val = phylink_get_eee_err(pp->phylink);
 				break;
+			case ETHTOOL_STAT_SKB_ALLOC_ERR:
+				val = pp->rxqs[0].skb_alloc_err;
+				break;
+			case ETHTOOL_STAT_REFILL_ERR:
+				val = pp->rxqs[0].refill_err;
+				break;
 			}
 			break;
 		}
@@ -4018,13 +4107,18 @@ static int  mvneta_config_rss(struct mvneta_port *pp)
 
 	on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
 
-	/* We have to synchronise on the napi of each CPU */
-	for_each_online_cpu(cpu) {
-		struct mvneta_pcpu_port *pcpu_port =
-			per_cpu_ptr(pp->ports, cpu);
+	if (!pp->neta_armada3700) {
+		/* We have to synchronise on the napi of each CPU */
+		for_each_online_cpu(cpu) {
+			struct mvneta_pcpu_port *pcpu_port =
+				per_cpu_ptr(pp->ports, cpu);
 
-		napi_synchronize(&pcpu_port->napi);
-		napi_disable(&pcpu_port->napi);
+			napi_synchronize(&pcpu_port->napi);
+			napi_disable(&pcpu_port->napi);
+		}
+	} else {
+		napi_synchronize(&pp->napi);
+		napi_disable(&pp->napi);
 	}
 
 	pp->rxq_def = pp->indir[0];
@@ -4041,12 +4135,16 @@ static int  mvneta_config_rss(struct mvneta_port *pp)
 	mvneta_percpu_elect(pp);
 	spin_unlock(&pp->lock);
 
-	/* We have to synchronise on the napi of each CPU */
-	for_each_online_cpu(cpu) {
-		struct mvneta_pcpu_port *pcpu_port =
-			per_cpu_ptr(pp->ports, cpu);
+	if (!pp->neta_armada3700) {
+		/* We have to synchronise on the napi of each CPU */
+		for_each_online_cpu(cpu) {
+			struct mvneta_pcpu_port *pcpu_port =
+				per_cpu_ptr(pp->ports, cpu);
 
-		napi_enable(&pcpu_port->napi);
+			napi_enable(&pcpu_port->napi);
+		}
+	} else {
+		napi_enable(&pp->napi);
 	}
 
 	netif_tx_start_all_queues(pp->dev);
@@ -4362,14 +4460,6 @@ static int mvneta_probe(struct platform_device *pdev)
 	pp->dn = dn;
 
 	pp->rxq_def = rxq_def;
-
-	/* Set RX packet offset correction for platforms, whose
-	 * NET_SKB_PAD, exceeds 64B. It should be 64B for 64-bit
-	 * platforms and 0B for 32-bit ones.
-	 */
-	pp->rx_offset_correction =
-		max(0, NET_SKB_PAD - MVNETA_RX_PKT_OFFSET_CORRECTION);
-
 	pp->indir[0] = rxq_def;
 
 	/* Get special SoC configurations */
@@ -4457,16 +4547,28 @@ static int mvneta_probe(struct platform_device *pdev)
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
 	pp->id = global_port_id++;
+	pp->rx_offset_correction = 0; /* not relevant for SW BM */
 
 	/* Obtain access to BM resources if enabled and already initialized */
 	bm_node = of_parse_phandle(dn, "buffer-manager", 0);
-	if (bm_node && bm_node->data) {
-		pp->bm_priv = bm_node->data;
-		err = mvneta_bm_port_init(pdev, pp);
-		if (err < 0) {
-			dev_info(&pdev->dev, "use SW buffer management\n");
-			pp->bm_priv = NULL;
+	if (bm_node) {
+		pp->bm_priv = mvneta_bm_get(bm_node);
+		if (pp->bm_priv) {
+			err = mvneta_bm_port_init(pdev, pp);
+			if (err < 0) {
+				dev_info(&pdev->dev,
+					 "use SW buffer management\n");
+				mvneta_bm_put(pp->bm_priv);
+				pp->bm_priv = NULL;
+			}
 		}
+		/* Set RX packet offset correction for platforms, whose
+		 * NET_SKB_PAD, exceeds 64B. It should be 64B for 64-bit
+		 * platforms and 0B for 32-bit ones.
+		 */
+		pp->rx_offset_correction = max(0,
+					       NET_SKB_PAD -
+					       MVNETA_RX_PKT_OFFSET_CORRECTION);
 	}
 	of_node_put(bm_node);
 
@@ -4526,6 +4628,7 @@ err_netdev:
 		mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_long, 1 << pp->id);
 		mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_short,
 				       1 << pp->id);
+		mvneta_bm_put(pp->bm_priv);
 	}
 err_free_stats:
 	free_percpu(pp->stats);
@@ -4563,6 +4666,7 @@ static int mvneta_remove(struct platform_device *pdev)
 		mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_long, 1 << pp->id);
 		mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_short,
 				       1 << pp->id);
+		mvneta_bm_put(pp->bm_priv);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/marvell/mvneta_bm.c b/drivers/net/ethernet/marvell/mvneta_bm.c
index 466939f8f0cf..de468e1bdba9 100644
--- a/drivers/net/ethernet/marvell/mvneta_bm.c
+++ b/drivers/net/ethernet/marvell/mvneta_bm.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/of.h>
+#include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/skbuff.h>
 #include <net/hwbm.h>
@@ -392,6 +393,20 @@ static void mvneta_bm_put_sram(struct mvneta_bm *priv)
 		      MVNETA_BM_BPPI_SIZE);
 }
 
+struct mvneta_bm *mvneta_bm_get(struct device_node *node)
+{
+	struct platform_device *pdev = of_find_device_by_node(node);
+
+	return pdev ? platform_get_drvdata(pdev) : NULL;
+}
+EXPORT_SYMBOL_GPL(mvneta_bm_get);
+
+void mvneta_bm_put(struct mvneta_bm *priv)
+{
+	platform_device_put(priv->pdev);
+}
+EXPORT_SYMBOL_GPL(mvneta_bm_put);
+
 static int mvneta_bm_probe(struct platform_device *pdev)
 {
 	struct device_node *dn = pdev->dev.of_node;
diff --git a/drivers/net/ethernet/marvell/mvneta_bm.h b/drivers/net/ethernet/marvell/mvneta_bm.h
index a32de432800c..c8425d35c049 100644
--- a/drivers/net/ethernet/marvell/mvneta_bm.h
+++ b/drivers/net/ethernet/marvell/mvneta_bm.h
@@ -130,10 +130,10 @@ struct mvneta_bm_pool {
 };
 
 /* Declarations and definitions */
-void *mvneta_frag_alloc(unsigned int frag_size);
-void mvneta_frag_free(unsigned int frag_size, void *data);
-
 #if IS_ENABLED(CONFIG_MVNETA_BM)
+struct mvneta_bm *mvneta_bm_get(struct device_node *node);
+void mvneta_bm_put(struct mvneta_bm *priv);
+
 void mvneta_bm_pool_destroy(struct mvneta_bm *priv,
 			    struct mvneta_bm_pool *bm_pool, u8 port_map);
 void mvneta_bm_bufs_free(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool,
@@ -178,5 +178,7 @@ static inline void mvneta_bm_pool_put_bp(struct mvneta_bm *priv,
 static inline u32 mvneta_bm_pool_get_bp(struct mvneta_bm *priv,
 					struct mvneta_bm_pool *bm_pool)
 { return 0; }
+struct mvneta_bm *mvneta_bm_get(struct device_node *node) { return NULL; }
+void mvneta_bm_put(struct mvneta_bm *priv) {}
 #endif /* CONFIG_MVNETA_BM */
 #endif
diff --git a/drivers/net/ethernet/marvell/mvpp2/Makefile b/drivers/net/ethernet/marvell/mvpp2/Makefile
index 4d11dd9e3246..51f65a202c6e 100644
--- a/drivers/net/ethernet/marvell/mvpp2/Makefile
+++ b/drivers/net/ethernet/marvell/mvpp2/Makefile
@@ -4,4 +4,4 @@
 #
 obj-$(CONFIG_MVPP2) := mvpp2.o
 
-mvpp2-objs := mvpp2_main.o mvpp2_prs.o mvpp2_cls.o
+mvpp2-objs := mvpp2_main.o mvpp2_prs.o mvpp2_cls.o mvpp2_debugfs.o
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index def00dc3eb4e..67b9e81b7c02 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -1,17 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Definitions for Marvell PPv2 network controller for Armada 375 SoC.
  *
  * Copyright (C) 2014 Marvell
  *
  * Marcin Wojtas <mw@semihalf.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 #ifndef _MVPP2_H_
 #define _MVPP2_H_
 
+#include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
 #include <linux/phy.h>
@@ -66,15 +64,18 @@
 #define MVPP2_PRS_SRAM_DATA_REG(idx)		(0x1204 + (idx) * 4)
 #define MVPP2_PRS_TCAM_CTRL_REG			0x1230
 #define     MVPP2_PRS_TCAM_EN_MASK		BIT(0)
+#define MVPP2_PRS_TCAM_HIT_IDX_REG		0x1240
+#define MVPP2_PRS_TCAM_HIT_CNT_REG		0x1244
+#define     MVPP2_PRS_TCAM_HIT_CNT_MASK		GENMASK(15, 0)
 
 /* RSS Registers */
 #define MVPP22_RSS_INDEX			0x1500
 #define     MVPP22_RSS_INDEX_TABLE_ENTRY(idx)	(idx)
 #define     MVPP22_RSS_INDEX_TABLE(idx)		((idx) << 8)
 #define     MVPP22_RSS_INDEX_QUEUE(idx)		((idx) << 16)
-#define MVPP22_RSS_TABLE_ENTRY			0x1508
-#define MVPP22_RSS_TABLE			0x1510
+#define MVPP22_RXQ2RSS_TABLE			0x1504
 #define     MVPP22_RSS_TABLE_POINTER(p)		(p)
+#define MVPP22_RSS_TABLE_ENTRY			0x1508
 #define MVPP22_RSS_WIDTH			0x150c
 
 /* Classifier Registers */
@@ -86,11 +87,28 @@
 #define     MVPP2_CLS_LKP_INDEX_WAY_OFFS	6
 #define MVPP2_CLS_LKP_TBL_REG			0x1818
 #define     MVPP2_CLS_LKP_TBL_RXQ_MASK		0xff
+#define     MVPP2_CLS_LKP_FLOW_PTR(flow)	((flow) << 16)
 #define     MVPP2_CLS_LKP_TBL_LOOKUP_EN_MASK	BIT(25)
 #define MVPP2_CLS_FLOW_INDEX_REG		0x1820
 #define MVPP2_CLS_FLOW_TBL0_REG			0x1824
+#define     MVPP2_CLS_FLOW_TBL0_LAST		BIT(0)
+#define     MVPP2_CLS_FLOW_TBL0_ENG_MASK	0x7
+#define     MVPP2_CLS_FLOW_TBL0_OFFS		1
+#define     MVPP2_CLS_FLOW_TBL0_ENG(x)		((x) << 1)
+#define     MVPP2_CLS_FLOW_TBL0_PORT_ID_MASK	0xff
+#define     MVPP2_CLS_FLOW_TBL0_PORT_ID(port)	((port) << 4)
+#define     MVPP2_CLS_FLOW_TBL0_PORT_ID_SEL	BIT(23)
 #define MVPP2_CLS_FLOW_TBL1_REG			0x1828
+#define     MVPP2_CLS_FLOW_TBL1_N_FIELDS_MASK	0x7
+#define     MVPP2_CLS_FLOW_TBL1_N_FIELDS(x)	(x)
+#define     MVPP2_CLS_FLOW_TBL1_PRIO_MASK	0x3f
+#define     MVPP2_CLS_FLOW_TBL1_PRIO(x)		((x) << 9)
+#define     MVPP2_CLS_FLOW_TBL1_SEQ_MASK	0x7
+#define     MVPP2_CLS_FLOW_TBL1_SEQ(x)		((x) << 15)
 #define MVPP2_CLS_FLOW_TBL2_REG			0x182c
+#define     MVPP2_CLS_FLOW_TBL2_FLD_MASK	0x3f
+#define     MVPP2_CLS_FLOW_TBL2_FLD_OFFS(n)	((n) * 6)
+#define     MVPP2_CLS_FLOW_TBL2_FLD(n, x)	((x) << ((n) * 6))
 #define MVPP2_CLS_OVERSIZE_RXQ_LOW_REG(port)	(0x1980 + ((port) * 4))
 #define     MVPP2_CLS_OVERSIZE_RXQ_LOW_BITS	3
 #define     MVPP2_CLS_OVERSIZE_RXQ_LOW_MASK	0x7
@@ -98,6 +116,32 @@
 #define MVPP2_CLS_SWFWD_PCTRL_REG		0x19d0
 #define     MVPP2_CLS_SWFWD_PCTRL_MASK(port)	(1 << (port))
 
+/* Classifier C2 engine Registers */
+#define MVPP22_CLS_C2_TCAM_IDX			0x1b00
+#define MVPP22_CLS_C2_TCAM_DATA0		0x1b10
+#define MVPP22_CLS_C2_TCAM_DATA1		0x1b14
+#define MVPP22_CLS_C2_TCAM_DATA2		0x1b18
+#define MVPP22_CLS_C2_TCAM_DATA3		0x1b1c
+#define MVPP22_CLS_C2_TCAM_DATA4		0x1b20
+#define     MVPP22_CLS_C2_PORT_ID(port)		((port) << 8)
+#define MVPP22_CLS_C2_HIT_CTR			0x1b50
+#define MVPP22_CLS_C2_ACT			0x1b60
+#define     MVPP22_CLS_C2_ACT_RSS_EN(act)	(((act) & 0x3) << 19)
+#define     MVPP22_CLS_C2_ACT_FWD(act)		(((act) & 0x7) << 13)
+#define     MVPP22_CLS_C2_ACT_QHIGH(act)	(((act) & 0x3) << 11)
+#define     MVPP22_CLS_C2_ACT_QLOW(act)		(((act) & 0x3) << 9)
+#define MVPP22_CLS_C2_ATTR0			0x1b64
+#define     MVPP22_CLS_C2_ATTR0_QHIGH(qh)	(((qh) & 0x1f) << 24)
+#define     MVPP22_CLS_C2_ATTR0_QHIGH_MASK	0x1f
+#define     MVPP22_CLS_C2_ATTR0_QHIGH_OFFS	24
+#define     MVPP22_CLS_C2_ATTR0_QLOW(ql)	(((ql) & 0x7) << 21)
+#define     MVPP22_CLS_C2_ATTR0_QLOW_MASK	0x7
+#define     MVPP22_CLS_C2_ATTR0_QLOW_OFFS	21
+#define MVPP22_CLS_C2_ATTR1			0x1b68
+#define MVPP22_CLS_C2_ATTR2			0x1b6c
+#define     MVPP22_CLS_C2_ATTR2_RSS_EN		BIT(30)
+#define MVPP22_CLS_C2_ATTR3			0x1b70
+
 /* Descriptor Manager Top Registers */
 #define MVPP2_RXQ_NUM_REG			0x2040
 #define MVPP2_RXQ_DESC_ADDR_REG			0x2044
@@ -275,6 +319,11 @@
 #define     MVPP22_BM_ADDR_HIGH_VIRT_RLS_MASK	0xff00
 #define     MVPP22_BM_ADDR_HIGH_VIRT_RLS_SHIFT	8
 
+/* Hit counters registers */
+#define MVPP2_CTRS_IDX				0x7040
+#define MVPP2_CLS_DEC_TBL_HIT_CTR		0x7700
+#define MVPP2_CLS_FLOW_TBL_HIT_CTR		0x7704
+
 /* TX Scheduler registers */
 #define MVPP2_TXP_SCHED_PORT_INDEX_REG		0x8000
 #define MVPP2_TXP_SCHED_Q_CMD_REG		0x8004
@@ -499,7 +548,7 @@
 #define MVPP2_MAX_SKB_DESCS		(MVPP2_MAX_TSO_SEGS * 2 + MAX_SKB_FRAGS)
 
 /* Dfault number of RXQs in use */
-#define MVPP2_DEFAULT_RXQ		4
+#define MVPP2_DEFAULT_RXQ		1
 
 /* Max number of Rx descriptors */
 #define MVPP2_MAX_RXD_MAX		1024
@@ -553,6 +602,11 @@
 	((total_size) - NET_SKB_PAD - MVPP2_SKB_SHINFO_SIZE)
 
 #define MVPP2_BIT_TO_BYTE(bit)		((bit) / 8)
+#define MVPP2_BIT_TO_WORD(bit)		((bit) / 32)
+#define MVPP2_BIT_IN_WORD(bit)		((bit) % 32)
+
+/* RSS constants */
+#define MVPP22_RSS_TABLE_ENTRIES	32
 
 /* IPv6 max L3 address size */
 #define MVPP2_MAX_L3_ADDR_SIZE		16
@@ -703,6 +757,9 @@ struct mvpp2 {
 	/* Workqueue to gather hardware statistics */
 	char queue_name[30];
 	struct workqueue_struct *stats_queue;
+
+	/* Debugfs root entry */
+	struct dentry *dbgfs_dir;
 };
 
 struct mvpp2_pcpu_stats {
@@ -795,6 +852,9 @@ struct mvpp2_port {
 	bool has_tx_irqs;
 
 	u32 tx_time_coal;
+
+	/* RSS indirection table */
+	u32 indir[MVPP22_RSS_TABLE_ENTRIES];
 };
 
 /* The mvpp2_tx_desc and mvpp2_rx_desc structures describe the
@@ -831,52 +891,52 @@ struct mvpp2_port {
 
 /* HW TX descriptor for PPv2.1 */
 struct mvpp21_tx_desc {
-	u32 command;		/* Options used by HW for packet transmitting.*/
+	__le32 command;		/* Options used by HW for packet transmitting.*/
 	u8  packet_offset;	/* the offset from the buffer beginning	*/
 	u8  phys_txq;		/* destination queue ID			*/
-	u16 data_size;		/* data size of transmitted packet in bytes */
-	u32 buf_dma_addr;	/* physical addr of transmitted buffer	*/
-	u32 buf_cookie;		/* cookie for access to TX buffer in tx path */
-	u32 reserved1[3];	/* hw_cmd (for future use, BM, PON, PNC) */
-	u32 reserved2;		/* reserved (for future use)		*/
+	__le16 data_size;	/* data size of transmitted packet in bytes */
+	__le32 buf_dma_addr;	/* physical addr of transmitted buffer	*/
+	__le32 buf_cookie;	/* cookie for access to TX buffer in tx path */
+	__le32 reserved1[3];	/* hw_cmd (for future use, BM, PON, PNC) */
+	__le32 reserved2;	/* reserved (for future use)		*/
 };
 
 /* HW RX descriptor for PPv2.1 */
 struct mvpp21_rx_desc {
-	u32 status;		/* info about received packet		*/
-	u16 reserved1;		/* parser_info (for future use, PnC)	*/
-	u16 data_size;		/* size of received packet in bytes	*/
-	u32 buf_dma_addr;	/* physical address of the buffer	*/
-	u32 buf_cookie;		/* cookie for access to RX buffer in rx path */
-	u16 reserved2;		/* gem_port_id (for future use, PON)	*/
-	u16 reserved3;		/* csum_l4 (for future use, PnC)	*/
+	__le32 status;		/* info about received packet		*/
+	__le16 reserved1;	/* parser_info (for future use, PnC)	*/
+	__le16 data_size;	/* size of received packet in bytes	*/
+	__le32 buf_dma_addr;	/* physical address of the buffer	*/
+	__le32 buf_cookie;	/* cookie for access to RX buffer in rx path */
+	__le16 reserved2;	/* gem_port_id (for future use, PON)	*/
+	__le16 reserved3;	/* csum_l4 (for future use, PnC)	*/
 	u8  reserved4;		/* bm_qset (for future use, BM)		*/
 	u8  reserved5;
-	u16 reserved6;		/* classify_info (for future use, PnC)	*/
-	u32 reserved7;		/* flow_id (for future use, PnC) */
-	u32 reserved8;
+	__le16 reserved6;	/* classify_info (for future use, PnC)	*/
+	__le32 reserved7;	/* flow_id (for future use, PnC) */
+	__le32 reserved8;
 };
 
 /* HW TX descriptor for PPv2.2 */
 struct mvpp22_tx_desc {
-	u32 command;
+	__le32 command;
 	u8  packet_offset;
 	u8  phys_txq;
-	u16 data_size;
-	u64 reserved1;
-	u64 buf_dma_addr_ptp;
-	u64 buf_cookie_misc;
+	__le16 data_size;
+	__le64 reserved1;
+	__le64 buf_dma_addr_ptp;
+	__le64 buf_cookie_misc;
 };
 
 /* HW RX descriptor for PPv2.2 */
 struct mvpp22_rx_desc {
-	u32 status;
-	u16 reserved1;
-	u16 data_size;
-	u32 reserved2;
-	u32 reserved3;
-	u64 buf_dma_addr_key_hash;
-	u64 buf_cookie_misc;
+	__le32 status;
+	__le16 reserved1;
+	__le16 data_size;
+	__le32 reserved2;
+	__le32 reserved3;
+	__le64 buf_dma_addr_key_hash;
+	__le64 buf_cookie_misc;
 };
 
 /* Opaque type used by the driver to manipulate the HW TX and RX
@@ -1043,4 +1103,8 @@ u32 mvpp2_percpu_read(struct mvpp2 *priv, int cpu, u32 offset);
 void mvpp2_percpu_write_relaxed(struct mvpp2 *priv, int cpu, u32 offset,
 				u32 data);
 
+void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name);
+
+void mvpp2_dbgfs_cleanup(struct mvpp2 *priv);
+
 #endif
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 8581d5b17dd5..efdb7a656835 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -1,17 +1,343 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * RSS and Classifier helpers for Marvell PPv2 Network Controller
  *
  * Copyright (C) 2014 Marvell
  *
  * Marcin Wojtas <mw@semihalf.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 
 #include "mvpp2.h"
 #include "mvpp2_cls.h"
+#include "mvpp2_prs.h"
+
+#define MVPP2_DEF_FLOW(_type, _id, _opts, _ri, _ri_mask)	\
+{								\
+	.flow_type = _type,					\
+	.flow_id = _id,						\
+	.supported_hash_opts = _opts,				\
+	.prs_ri = {						\
+		.ri = _ri,					\
+		.ri_mask = _ri_mask				\
+	}							\
+}
+
+static struct mvpp2_cls_flow cls_flows[MVPP2_N_FLOWS] = {
+	/* TCP over IPv4 flows, Not fragmented, no vlan tag */
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP4_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP4_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP4_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	/* TCP over IPv4 flows, Not fragmented, with vlan tag */
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_TAG,
+		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_TAG,
+		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_TAG,
+		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	/* TCP over IPv4 flows, fragmented, no vlan tag */
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP4_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP4_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP4_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	/* TCP over IPv4 flows, fragmented, with vlan tag */
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	/* UDP over IPv4 flows, Not fragmented, no vlan tag */
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP4_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP4_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP4_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	/* UDP over IPv4 flows, Not fragmented, with vlan tag */
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_TAG,
+		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_TAG,
+		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_TAG,
+		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	/* UDP over IPv4 flows, fragmented, no vlan tag */
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP4_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP4_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP4_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	/* UDP over IPv4 flows, fragmented, with vlan tag */
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	/* TCP over IPv6 flows, not fragmented, no vlan tag */
+	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP6_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP6_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	/* TCP over IPv6 flows, not fragmented, with vlan tag */
+	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_NF_TAG,
+		       MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_NF_TAG,
+		       MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	/* TCP over IPv6 flows, fragmented, no vlan tag */
+	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP6_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
+		       MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP6_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
+		       MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	/* TCP over IPv6 flows, fragmented, with vlan tag */
+	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_IP_FRAG_TRUE |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_IP_FRAG_TRUE |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	/* UDP over IPv6 flows, not fragmented, no vlan tag */
+	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP6_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP6_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	/* UDP over IPv6 flows, not fragmented, with vlan tag */
+	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_NF_TAG,
+		       MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_NF_TAG,
+		       MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	/* UDP over IPv6 flows, fragmented, no vlan tag */
+	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP6_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
+		       MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP6_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
+		       MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	/* UDP over IPv6 flows, fragmented, with vlan tag */
+	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_IP_FRAG_TRUE |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_IP_FRAG_TRUE |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	/* IPv4 flows, no vlan tag */
+	MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_UNTAG,
+		       MVPP22_CLS_HEK_IP4_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4,
+		       MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
+	MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_UNTAG,
+		       MVPP22_CLS_HEK_IP4_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT,
+		       MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
+	MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_UNTAG,
+		       MVPP22_CLS_HEK_IP4_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER,
+		       MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
+
+	/* IPv4 flows, with vlan tag */
+	MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4,
+		       MVPP2_PRS_RI_L3_PROTO_MASK),
+	MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OPT,
+		       MVPP2_PRS_RI_L3_PROTO_MASK),
+	MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OTHER,
+		       MVPP2_PRS_RI_L3_PROTO_MASK),
+
+	/* IPv6 flows, no vlan tag */
+	MVPP2_DEF_FLOW(IPV6_FLOW, MVPP2_FL_IP6_UNTAG,
+		       MVPP22_CLS_HEK_IP6_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6,
+		       MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
+	MVPP2_DEF_FLOW(IPV6_FLOW, MVPP2_FL_IP6_UNTAG,
+		       MVPP22_CLS_HEK_IP6_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6,
+		       MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
+
+	/* IPv6 flows, with vlan tag */
+	MVPP2_DEF_FLOW(IPV6_FLOW, MVPP2_FL_IP6_TAG,
+		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6,
+		       MVPP2_PRS_RI_L3_PROTO_MASK),
+	MVPP2_DEF_FLOW(IPV6_FLOW, MVPP2_FL_IP6_TAG,
+		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6,
+		       MVPP2_PRS_RI_L3_PROTO_MASK),
+
+	/* Non IP flow, no vlan tag */
+	MVPP2_DEF_FLOW(ETHER_FLOW, MVPP2_FL_NON_IP_UNTAG,
+		       0,
+		       MVPP2_PRS_RI_VLAN_NONE,
+		       MVPP2_PRS_RI_VLAN_MASK),
+	/* Non IP flow, with vlan tag */
+	MVPP2_DEF_FLOW(ETHER_FLOW, MVPP2_FL_NON_IP_TAG,
+		       MVPP22_CLS_HEK_OPT_VLAN,
+		       0, 0),
+};
+
+u32 mvpp2_cls_flow_hits(struct mvpp2 *priv, int index)
+{
+	mvpp2_write(priv, MVPP2_CTRS_IDX, index);
+
+	return mvpp2_read(priv, MVPP2_CLS_FLOW_TBL_HIT_CTR);
+}
+
+void mvpp2_cls_flow_read(struct mvpp2 *priv, int index,
+			 struct mvpp2_cls_flow_entry *fe)
+{
+	fe->index = index;
+	mvpp2_write(priv, MVPP2_CLS_FLOW_INDEX_REG, index);
+	fe->data[0] = mvpp2_read(priv, MVPP2_CLS_FLOW_TBL0_REG);
+	fe->data[1] = mvpp2_read(priv, MVPP2_CLS_FLOW_TBL1_REG);
+	fe->data[2] = mvpp2_read(priv, MVPP2_CLS_FLOW_TBL2_REG);
+}
 
 /* Update classification flow table registers */
 static void mvpp2_cls_flow_write(struct mvpp2 *priv,
@@ -23,6 +349,25 @@ static void mvpp2_cls_flow_write(struct mvpp2 *priv,
 	mvpp2_write(priv, MVPP2_CLS_FLOW_TBL2_REG,  fe->data[2]);
 }
 
+u32 mvpp2_cls_lookup_hits(struct mvpp2 *priv, int index)
+{
+	mvpp2_write(priv, MVPP2_CTRS_IDX, index);
+
+	return mvpp2_read(priv, MVPP2_CLS_DEC_TBL_HIT_CTR);
+}
+
+void mvpp2_cls_lookup_read(struct mvpp2 *priv, int lkpid, int way,
+			   struct mvpp2_cls_lookup_entry *le)
+{
+	u32 val;
+
+	val = (way << MVPP2_CLS_LKP_INDEX_WAY_OFFS) | lkpid;
+	mvpp2_write(priv, MVPP2_CLS_LKP_INDEX_REG, val);
+	le->way = way;
+	le->lkpid = lkpid;
+	le->data = mvpp2_read(priv, MVPP2_CLS_LKP_TBL_REG);
+}
+
 /* Update classification lookup table register */
 static void mvpp2_cls_lookup_write(struct mvpp2 *priv,
 				   struct mvpp2_cls_lookup_entry *le)
@@ -34,6 +379,439 @@ static void mvpp2_cls_lookup_write(struct mvpp2 *priv,
 	mvpp2_write(priv, MVPP2_CLS_LKP_TBL_REG, le->data);
 }
 
+/* Operations on flow entry */
+static int mvpp2_cls_flow_hek_num_get(struct mvpp2_cls_flow_entry *fe)
+{
+	return fe->data[1] & MVPP2_CLS_FLOW_TBL1_N_FIELDS_MASK;
+}
+
+static void mvpp2_cls_flow_hek_num_set(struct mvpp2_cls_flow_entry *fe,
+				       int num_of_fields)
+{
+	fe->data[1] &= ~MVPP2_CLS_FLOW_TBL1_N_FIELDS_MASK;
+	fe->data[1] |= MVPP2_CLS_FLOW_TBL1_N_FIELDS(num_of_fields);
+}
+
+static int mvpp2_cls_flow_hek_get(struct mvpp2_cls_flow_entry *fe,
+				  int field_index)
+{
+	return (fe->data[2] >> MVPP2_CLS_FLOW_TBL2_FLD_OFFS(field_index)) &
+		MVPP2_CLS_FLOW_TBL2_FLD_MASK;
+}
+
+static void mvpp2_cls_flow_hek_set(struct mvpp2_cls_flow_entry *fe,
+				   int field_index, int field_id)
+{
+	fe->data[2] &= ~MVPP2_CLS_FLOW_TBL2_FLD(field_index,
+						MVPP2_CLS_FLOW_TBL2_FLD_MASK);
+	fe->data[2] |= MVPP2_CLS_FLOW_TBL2_FLD(field_index, field_id);
+}
+
+static void mvpp2_cls_flow_eng_set(struct mvpp2_cls_flow_entry *fe,
+				   int engine)
+{
+	fe->data[0] &= ~MVPP2_CLS_FLOW_TBL0_ENG(MVPP2_CLS_FLOW_TBL0_ENG_MASK);
+	fe->data[0] |= MVPP2_CLS_FLOW_TBL0_ENG(engine);
+}
+
+int mvpp2_cls_flow_eng_get(struct mvpp2_cls_flow_entry *fe)
+{
+	return (fe->data[0] >> MVPP2_CLS_FLOW_TBL0_OFFS) &
+		MVPP2_CLS_FLOW_TBL0_ENG_MASK;
+}
+
+static void mvpp2_cls_flow_port_id_sel(struct mvpp2_cls_flow_entry *fe,
+				       bool from_packet)
+{
+	if (from_packet)
+		fe->data[0] |= MVPP2_CLS_FLOW_TBL0_PORT_ID_SEL;
+	else
+		fe->data[0] &= ~MVPP2_CLS_FLOW_TBL0_PORT_ID_SEL;
+}
+
+static void mvpp2_cls_flow_seq_set(struct mvpp2_cls_flow_entry *fe, u32 seq)
+{
+	fe->data[1] &= ~MVPP2_CLS_FLOW_TBL1_SEQ(MVPP2_CLS_FLOW_TBL1_SEQ_MASK);
+	fe->data[1] |= MVPP2_CLS_FLOW_TBL1_SEQ(seq);
+}
+
+static void mvpp2_cls_flow_last_set(struct mvpp2_cls_flow_entry *fe,
+				    bool is_last)
+{
+	fe->data[0] &= ~MVPP2_CLS_FLOW_TBL0_LAST;
+	fe->data[0] |= !!is_last;
+}
+
+static void mvpp2_cls_flow_pri_set(struct mvpp2_cls_flow_entry *fe, int prio)
+{
+	fe->data[1] &= ~MVPP2_CLS_FLOW_TBL1_PRIO(MVPP2_CLS_FLOW_TBL1_PRIO_MASK);
+	fe->data[1] |= MVPP2_CLS_FLOW_TBL1_PRIO(prio);
+}
+
+static void mvpp2_cls_flow_port_add(struct mvpp2_cls_flow_entry *fe,
+				    u32 port)
+{
+	fe->data[0] |= MVPP2_CLS_FLOW_TBL0_PORT_ID(port);
+}
+
+/* Initialize the parser entry for the given flow */
+static void mvpp2_cls_flow_prs_init(struct mvpp2 *priv,
+				    struct mvpp2_cls_flow *flow)
+{
+	mvpp2_prs_add_flow(priv, flow->flow_id, flow->prs_ri.ri,
+			   flow->prs_ri.ri_mask);
+}
+
+/* Initialize the Lookup Id table entry for the given flow */
+static void mvpp2_cls_flow_lkp_init(struct mvpp2 *priv,
+				    struct mvpp2_cls_flow *flow)
+{
+	struct mvpp2_cls_lookup_entry le;
+
+	le.way = 0;
+	le.lkpid = flow->flow_id;
+
+	/* The default RxQ for this port is set in the C2 lookup */
+	le.data = 0;
+
+	/* We point on the first lookup in the sequence for the flow, that is
+	 * the C2 lookup.
+	 */
+	le.data |= MVPP2_CLS_LKP_FLOW_PTR(MVPP2_FLOW_C2_ENTRY(flow->flow_id));
+
+	/* CLS is always enabled, RSS is enabled/disabled in C2 lookup */
+	le.data |= MVPP2_CLS_LKP_TBL_LOOKUP_EN_MASK;
+
+	mvpp2_cls_lookup_write(priv, &le);
+}
+
+/* Initialize the flow table entries for the given flow */
+static void mvpp2_cls_flow_init(struct mvpp2 *priv, struct mvpp2_cls_flow *flow)
+{
+	struct mvpp2_cls_flow_entry fe;
+	int i;
+
+	/* C2 lookup */
+	memset(&fe, 0, sizeof(fe));
+	fe.index = MVPP2_FLOW_C2_ENTRY(flow->flow_id);
+
+	mvpp2_cls_flow_eng_set(&fe, MVPP22_CLS_ENGINE_C2);
+	mvpp2_cls_flow_port_id_sel(&fe, true);
+	mvpp2_cls_flow_last_set(&fe, 0);
+	mvpp2_cls_flow_pri_set(&fe, 0);
+	mvpp2_cls_flow_seq_set(&fe, MVPP2_CLS_FLOW_SEQ_FIRST1);
+
+	/* Add all ports */
+	for (i = 0; i < MVPP2_MAX_PORTS; i++)
+		mvpp2_cls_flow_port_add(&fe, BIT(i));
+
+	mvpp2_cls_flow_write(priv, &fe);
+
+	/* C3Hx lookups */
+	for (i = 0; i < MVPP2_MAX_PORTS; i++) {
+		memset(&fe, 0, sizeof(fe));
+		fe.index = MVPP2_PORT_FLOW_HASH_ENTRY(i, flow->flow_id);
+
+		mvpp2_cls_flow_port_id_sel(&fe, true);
+		mvpp2_cls_flow_pri_set(&fe, i + 1);
+		mvpp2_cls_flow_seq_set(&fe, MVPP2_CLS_FLOW_SEQ_MIDDLE);
+		mvpp2_cls_flow_port_add(&fe, BIT(i));
+
+		mvpp2_cls_flow_write(priv, &fe);
+	}
+
+	/* Update the last entry */
+	mvpp2_cls_flow_last_set(&fe, 1);
+	mvpp2_cls_flow_seq_set(&fe, MVPP2_CLS_FLOW_SEQ_LAST);
+
+	mvpp2_cls_flow_write(priv, &fe);
+}
+
+/* Adds a field to the Header Extracted Key generation parameters*/
+static int mvpp2_flow_add_hek_field(struct mvpp2_cls_flow_entry *fe,
+				    u32 field_id)
+{
+	int nb_fields = mvpp2_cls_flow_hek_num_get(fe);
+
+	if (nb_fields == MVPP2_FLOW_N_FIELDS)
+		return -EINVAL;
+
+	mvpp2_cls_flow_hek_set(fe, nb_fields, field_id);
+
+	mvpp2_cls_flow_hek_num_set(fe, nb_fields + 1);
+
+	return 0;
+}
+
+static int mvpp2_flow_set_hek_fields(struct mvpp2_cls_flow_entry *fe,
+				     unsigned long hash_opts)
+{
+	u32 field_id;
+	int i;
+
+	/* Clear old fields */
+	mvpp2_cls_flow_hek_num_set(fe, 0);
+	fe->data[2] = 0;
+
+	for_each_set_bit(i, &hash_opts, MVPP22_CLS_HEK_N_FIELDS) {
+		switch (BIT(i)) {
+		case MVPP22_CLS_HEK_OPT_VLAN:
+			field_id = MVPP22_CLS_FIELD_VLAN;
+			break;
+		case MVPP22_CLS_HEK_OPT_IP4SA:
+			field_id = MVPP22_CLS_FIELD_IP4SA;
+			break;
+		case MVPP22_CLS_HEK_OPT_IP4DA:
+			field_id = MVPP22_CLS_FIELD_IP4DA;
+			break;
+		case MVPP22_CLS_HEK_OPT_IP6SA:
+			field_id = MVPP22_CLS_FIELD_IP6SA;
+			break;
+		case MVPP22_CLS_HEK_OPT_IP6DA:
+			field_id = MVPP22_CLS_FIELD_IP6DA;
+			break;
+		case MVPP22_CLS_HEK_OPT_L4SIP:
+			field_id = MVPP22_CLS_FIELD_L4SIP;
+			break;
+		case MVPP22_CLS_HEK_OPT_L4DIP:
+			field_id = MVPP22_CLS_FIELD_L4DIP;
+			break;
+		default:
+			return -EINVAL;
+		}
+		if (mvpp2_flow_add_hek_field(fe, field_id))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow)
+{
+	if (flow >= MVPP2_N_FLOWS)
+		return NULL;
+
+	return &cls_flows[flow];
+}
+
+/* Set the hash generation options for the given traffic flow.
+ * One traffic flow (in the ethtool sense) has multiple classification flows,
+ * to handle specific cases such as fragmentation, or the presence of a
+ * VLAN / DSA Tag.
+ *
+ * Each of these individual flows has different constraints, for example we
+ * can't hash fragmented packets on L4 data (else we would risk having packet
+ * re-ordering), so each classification flows masks the options with their
+ * supported ones.
+ *
+ */
+static int mvpp2_port_rss_hash_opts_set(struct mvpp2_port *port, int flow_type,
+					u16 requested_opts)
+{
+	struct mvpp2_cls_flow_entry fe;
+	struct mvpp2_cls_flow *flow;
+	int i, engine, flow_index;
+	u16 hash_opts;
+
+	for (i = 0; i < MVPP2_N_FLOWS; i++) {
+		flow = mvpp2_cls_flow_get(i);
+		if (!flow)
+			return -EINVAL;
+
+		if (flow->flow_type != flow_type)
+			continue;
+
+		flow_index = MVPP2_PORT_FLOW_HASH_ENTRY(port->id,
+							flow->flow_id);
+
+		mvpp2_cls_flow_read(port->priv, flow_index, &fe);
+
+		hash_opts = flow->supported_hash_opts & requested_opts;
+
+		/* Use C3HB engine to access L4 infos. This adds L4 infos to the
+		 * hash parameters
+		 */
+		if (hash_opts & MVPP22_CLS_HEK_L4_OPTS)
+			engine = MVPP22_CLS_ENGINE_C3HB;
+		else
+			engine = MVPP22_CLS_ENGINE_C3HA;
+
+		if (mvpp2_flow_set_hek_fields(&fe, hash_opts))
+			return -EINVAL;
+
+		mvpp2_cls_flow_eng_set(&fe, engine);
+
+		mvpp2_cls_flow_write(port->priv, &fe);
+	}
+
+	return 0;
+}
+
+u16 mvpp2_flow_get_hek_fields(struct mvpp2_cls_flow_entry *fe)
+{
+	u16 hash_opts = 0;
+	int n_fields, i, field;
+
+	n_fields = mvpp2_cls_flow_hek_num_get(fe);
+
+	for (i = 0; i < n_fields; i++) {
+		field = mvpp2_cls_flow_hek_get(fe, i);
+
+		switch (field) {
+		case MVPP22_CLS_FIELD_MAC_DA:
+			hash_opts |= MVPP22_CLS_HEK_OPT_MAC_DA;
+			break;
+		case MVPP22_CLS_FIELD_VLAN:
+			hash_opts |= MVPP22_CLS_HEK_OPT_VLAN;
+			break;
+		case MVPP22_CLS_FIELD_L3_PROTO:
+			hash_opts |= MVPP22_CLS_HEK_OPT_L3_PROTO;
+			break;
+		case MVPP22_CLS_FIELD_IP4SA:
+			hash_opts |= MVPP22_CLS_HEK_OPT_IP4SA;
+			break;
+		case MVPP22_CLS_FIELD_IP4DA:
+			hash_opts |= MVPP22_CLS_HEK_OPT_IP4DA;
+			break;
+		case MVPP22_CLS_FIELD_IP6SA:
+			hash_opts |= MVPP22_CLS_HEK_OPT_IP6SA;
+			break;
+		case MVPP22_CLS_FIELD_IP6DA:
+			hash_opts |= MVPP22_CLS_HEK_OPT_IP6DA;
+			break;
+		case MVPP22_CLS_FIELD_L4SIP:
+			hash_opts |= MVPP22_CLS_HEK_OPT_L4SIP;
+			break;
+		case MVPP22_CLS_FIELD_L4DIP:
+			hash_opts |= MVPP22_CLS_HEK_OPT_L4DIP;
+			break;
+		default:
+			break;
+		}
+	}
+	return hash_opts;
+}
+
+/* Returns the hash opts for this flow. There are several classifier flows
+ * for one traffic flow, this returns an aggregation of all configurations.
+ */
+static u16 mvpp2_port_rss_hash_opts_get(struct mvpp2_port *port, int flow_type)
+{
+	struct mvpp2_cls_flow_entry fe;
+	struct mvpp2_cls_flow *flow;
+	int i, flow_index;
+	u16 hash_opts = 0;
+
+	for (i = 0; i < MVPP2_N_FLOWS; i++) {
+		flow = mvpp2_cls_flow_get(i);
+		if (!flow)
+			return 0;
+
+		if (flow->flow_type != flow_type)
+			continue;
+
+		flow_index = MVPP2_PORT_FLOW_HASH_ENTRY(port->id,
+							flow->flow_id);
+
+		mvpp2_cls_flow_read(port->priv, flow_index, &fe);
+
+		hash_opts |= mvpp2_flow_get_hek_fields(&fe);
+	}
+
+	return hash_opts;
+}
+
+static void mvpp2_cls_port_init_flows(struct mvpp2 *priv)
+{
+	struct mvpp2_cls_flow *flow;
+	int i;
+
+	for (i = 0; i < MVPP2_N_FLOWS; i++) {
+		flow = mvpp2_cls_flow_get(i);
+		if (!flow)
+			break;
+
+		mvpp2_cls_flow_prs_init(priv, flow);
+		mvpp2_cls_flow_lkp_init(priv, flow);
+		mvpp2_cls_flow_init(priv, flow);
+	}
+}
+
+static void mvpp2_cls_c2_write(struct mvpp2 *priv,
+			       struct mvpp2_cls_c2_entry *c2)
+{
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_IDX, c2->index);
+
+	/* Write TCAM */
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA0, c2->tcam[0]);
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA1, c2->tcam[1]);
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA2, c2->tcam[2]);
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA3, c2->tcam[3]);
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA4, c2->tcam[4]);
+
+	mvpp2_write(priv, MVPP22_CLS_C2_ACT, c2->act);
+
+	mvpp2_write(priv, MVPP22_CLS_C2_ATTR0, c2->attr[0]);
+	mvpp2_write(priv, MVPP22_CLS_C2_ATTR1, c2->attr[1]);
+	mvpp2_write(priv, MVPP22_CLS_C2_ATTR2, c2->attr[2]);
+	mvpp2_write(priv, MVPP22_CLS_C2_ATTR3, c2->attr[3]);
+}
+
+void mvpp2_cls_c2_read(struct mvpp2 *priv, int index,
+		       struct mvpp2_cls_c2_entry *c2)
+{
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_IDX, index);
+
+	c2->index = index;
+
+	c2->tcam[0] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA0);
+	c2->tcam[1] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA1);
+	c2->tcam[2] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA2);
+	c2->tcam[3] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA3);
+	c2->tcam[4] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA4);
+
+	c2->act = mvpp2_read(priv, MVPP22_CLS_C2_ACT);
+
+	c2->attr[0] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR0);
+	c2->attr[1] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR1);
+	c2->attr[2] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR2);
+	c2->attr[3] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR3);
+}
+
+static void mvpp2_port_c2_cls_init(struct mvpp2_port *port)
+{
+	struct mvpp2_cls_c2_entry c2;
+	u8 qh, ql, pmap;
+
+	memset(&c2, 0, sizeof(c2));
+
+	c2.index = MVPP22_CLS_C2_RSS_ENTRY(port->id);
+
+	pmap = BIT(port->id);
+	c2.tcam[4] = MVPP22_CLS_C2_PORT_ID(pmap);
+	c2.tcam[4] |= MVPP22_CLS_C2_TCAM_EN(MVPP22_CLS_C2_PORT_ID(pmap));
+
+	/* Update RSS status after matching this entry */
+	c2.act = MVPP22_CLS_C2_ACT_RSS_EN(MVPP22_C2_UPD_LOCK);
+
+	/* Mark packet as "forwarded to software", needed for RSS */
+	c2.act |= MVPP22_CLS_C2_ACT_FWD(MVPP22_C2_FWD_SW_LOCK);
+
+	/* Configure the default rx queue : Update Queue Low and Queue High, but
+	 * don't lock, since the rx queue selection might be overridden by RSS
+	 */
+	c2.act |= MVPP22_CLS_C2_ACT_QHIGH(MVPP22_C2_UPD) |
+		   MVPP22_CLS_C2_ACT_QLOW(MVPP22_C2_UPD);
+
+	qh = (port->first_rxq >> 3) & MVPP22_CLS_C2_ATTR0_QHIGH_MASK;
+	ql = port->first_rxq & MVPP22_CLS_C2_ATTR0_QLOW_MASK;
+
+	c2.attr[0] = MVPP22_CLS_C2_ATTR0_QHIGH(qh) |
+		      MVPP22_CLS_C2_ATTR0_QLOW(ql);
+
+	mvpp2_cls_c2_write(port->priv, &c2);
+}
+
 /* Classifier default initialization */
 void mvpp2_cls_init(struct mvpp2 *priv)
 {
@@ -61,6 +839,8 @@ void mvpp2_cls_init(struct mvpp2 *priv)
 		le.way = 1;
 		mvpp2_cls_lookup_write(priv, &le);
 	}
+
+	mvpp2_cls_port_init_flows(priv);
 }
 
 void mvpp2_cls_port_config(struct mvpp2_port *port)
@@ -89,6 +869,47 @@ void mvpp2_cls_port_config(struct mvpp2_port *port)
 
 	/* Update lookup ID table entry */
 	mvpp2_cls_lookup_write(port->priv, &le);
+
+	mvpp2_port_c2_cls_init(port);
+}
+
+u32 mvpp2_cls_c2_hit_count(struct mvpp2 *priv, int c2_index)
+{
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_IDX, c2_index);
+
+	return mvpp2_read(priv, MVPP22_CLS_C2_HIT_CTR);
+}
+
+static void mvpp2_rss_port_c2_enable(struct mvpp2_port *port)
+{
+	struct mvpp2_cls_c2_entry c2;
+
+	mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
+
+	c2.attr[2] |= MVPP22_CLS_C2_ATTR2_RSS_EN;
+
+	mvpp2_cls_c2_write(port->priv, &c2);
+}
+
+static void mvpp2_rss_port_c2_disable(struct mvpp2_port *port)
+{
+	struct mvpp2_cls_c2_entry c2;
+
+	mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
+
+	c2.attr[2] &= ~MVPP22_CLS_C2_ATTR2_RSS_EN;
+
+	mvpp2_cls_c2_write(port->priv, &c2);
+}
+
+void mvpp22_rss_enable(struct mvpp2_port *port)
+{
+	mvpp2_rss_port_c2_enable(port);
+}
+
+void mvpp22_rss_disable(struct mvpp2_port *port)
+{
+	mvpp2_rss_port_c2_disable(port);
 }
 
 /* Set CPU queue number for oversize packets */
@@ -107,7 +928,116 @@ void mvpp2_cls_oversize_rxq_set(struct mvpp2_port *port)
 	mvpp2_write(port->priv, MVPP2_CLS_SWFWD_PCTRL_REG, val);
 }
 
-void mvpp22_init_rss(struct mvpp2_port *port)
+static inline u32 mvpp22_rxfh_indir(struct mvpp2_port *port, u32 rxq)
+{
+	int nrxqs, cpu, cpus = num_possible_cpus();
+
+	/* Number of RXQs per CPU */
+	nrxqs = port->nrxqs / cpus;
+
+	/* CPU that will handle this rx queue */
+	cpu = rxq / nrxqs;
+
+	if (!cpu_online(cpu))
+		return port->first_rxq;
+
+	/* Indirection to better distribute the paquets on the CPUs when
+	 * configuring the RSS queues.
+	 */
+	return port->first_rxq + ((rxq * nrxqs + rxq / cpus) % port->nrxqs);
+}
+
+void mvpp22_rss_fill_table(struct mvpp2_port *port, u32 table)
+{
+	struct mvpp2 *priv = port->priv;
+	int i;
+
+	for (i = 0; i < MVPP22_RSS_TABLE_ENTRIES; i++) {
+		u32 sel = MVPP22_RSS_INDEX_TABLE(table) |
+			  MVPP22_RSS_INDEX_TABLE_ENTRY(i);
+		mvpp2_write(priv, MVPP22_RSS_INDEX, sel);
+
+		mvpp2_write(priv, MVPP22_RSS_TABLE_ENTRY,
+			    mvpp22_rxfh_indir(port, port->indir[i]));
+	}
+}
+
+int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, struct ethtool_rxnfc *info)
+{
+	u16 hash_opts = 0;
+
+	switch (info->flow_type) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+		if (info->data & RXH_L4_B_0_1)
+			hash_opts |= MVPP22_CLS_HEK_OPT_L4SIP;
+		if (info->data & RXH_L4_B_2_3)
+			hash_opts |= MVPP22_CLS_HEK_OPT_L4DIP;
+		/* Fallthrough */
+	case IPV4_FLOW:
+	case IPV6_FLOW:
+		if (info->data & RXH_L2DA)
+			hash_opts |= MVPP22_CLS_HEK_OPT_MAC_DA;
+		if (info->data & RXH_VLAN)
+			hash_opts |= MVPP22_CLS_HEK_OPT_VLAN;
+		if (info->data & RXH_L3_PROTO)
+			hash_opts |= MVPP22_CLS_HEK_OPT_L3_PROTO;
+		if (info->data & RXH_IP_SRC)
+			hash_opts |= (MVPP22_CLS_HEK_OPT_IP4SA |
+				     MVPP22_CLS_HEK_OPT_IP6SA);
+		if (info->data & RXH_IP_DST)
+			hash_opts |= (MVPP22_CLS_HEK_OPT_IP4DA |
+				     MVPP22_CLS_HEK_OPT_IP6DA);
+		break;
+	default: return -EOPNOTSUPP;
+	}
+
+	return mvpp2_port_rss_hash_opts_set(port, info->flow_type, hash_opts);
+}
+
+int mvpp2_ethtool_rxfh_get(struct mvpp2_port *port, struct ethtool_rxnfc *info)
+{
+	unsigned long hash_opts;
+	int i;
+
+	hash_opts = mvpp2_port_rss_hash_opts_get(port, info->flow_type);
+	info->data = 0;
+
+	for_each_set_bit(i, &hash_opts, MVPP22_CLS_HEK_N_FIELDS) {
+		switch (BIT(i)) {
+		case MVPP22_CLS_HEK_OPT_MAC_DA:
+			info->data |= RXH_L2DA;
+			break;
+		case MVPP22_CLS_HEK_OPT_VLAN:
+			info->data |= RXH_VLAN;
+			break;
+		case MVPP22_CLS_HEK_OPT_L3_PROTO:
+			info->data |= RXH_L3_PROTO;
+			break;
+		case MVPP22_CLS_HEK_OPT_IP4SA:
+		case MVPP22_CLS_HEK_OPT_IP6SA:
+			info->data |= RXH_IP_SRC;
+			break;
+		case MVPP22_CLS_HEK_OPT_IP4DA:
+		case MVPP22_CLS_HEK_OPT_IP6DA:
+			info->data |= RXH_IP_DST;
+			break;
+		case MVPP22_CLS_HEK_OPT_L4SIP:
+			info->data |= RXH_L4_B_0_1;
+			break;
+		case MVPP22_CLS_HEK_OPT_L4DIP:
+			info->data |= RXH_L4_B_2_3;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+void mvpp22_rss_port_init(struct mvpp2_port *port)
 {
 	struct mvpp2 *priv = port->priv;
 	int i;
@@ -115,27 +1045,30 @@ void mvpp22_init_rss(struct mvpp2_port *port)
 	/* Set the table width: replace the whole classifier Rx queue number
 	 * with the ones configured in RSS table entries.
 	 */
-	mvpp2_write(priv, MVPP22_RSS_INDEX, MVPP22_RSS_INDEX_TABLE(0));
+	mvpp2_write(priv, MVPP22_RSS_INDEX, MVPP22_RSS_INDEX_TABLE(port->id));
 	mvpp2_write(priv, MVPP22_RSS_WIDTH, 8);
 
-	/* Loop through the classifier Rx Queues and map them to a RSS table.
-	 * Map them all to the first table (0) by default.
+	/* The default RxQ is used as a key to select the RSS table to use.
+	 * We use one RSS table per port.
 	 */
-	for (i = 0; i < MVPP2_CLS_RX_QUEUES; i++) {
-		mvpp2_write(priv, MVPP22_RSS_INDEX, MVPP22_RSS_INDEX_QUEUE(i));
-		mvpp2_write(priv, MVPP22_RSS_TABLE,
-			    MVPP22_RSS_TABLE_POINTER(0));
-	}
+	mvpp2_write(priv, MVPP22_RSS_INDEX,
+		    MVPP22_RSS_INDEX_QUEUE(port->first_rxq));
+	mvpp2_write(priv, MVPP22_RXQ2RSS_TABLE,
+		    MVPP22_RSS_TABLE_POINTER(port->id));
 
 	/* Configure the first table to evenly distribute the packets across
-	 * real Rx Queues. The table entries map a hash to an port Rx Queue.
+	 * real Rx Queues. The table entries map a hash to a port Rx Queue.
 	 */
-	for (i = 0; i < MVPP22_RSS_TABLE_ENTRIES; i++) {
-		u32 sel = MVPP22_RSS_INDEX_TABLE(0) |
-			  MVPP22_RSS_INDEX_TABLE_ENTRY(i);
-		mvpp2_write(priv, MVPP22_RSS_INDEX, sel);
+	for (i = 0; i < MVPP22_RSS_TABLE_ENTRIES; i++)
+		port->indir[i] = ethtool_rxfh_indir_default(i, port->nrxqs);
 
-		mvpp2_write(priv, MVPP22_RSS_TABLE_ENTRY, i % port->nrxqs);
-	}
+	mvpp22_rss_fill_table(port, port->id);
 
+	/* Configure default flows */
+	mvpp2_port_rss_hash_opts_set(port, IPV4_FLOW, MVPP22_CLS_HEK_IP4_2T);
+	mvpp2_port_rss_hash_opts_set(port, IPV6_FLOW, MVPP22_CLS_HEK_IP6_2T);
+	mvpp2_port_rss_hash_opts_set(port, TCP_V4_FLOW, MVPP22_CLS_HEK_IP4_5T);
+	mvpp2_port_rss_hash_opts_set(port, TCP_V6_FLOW, MVPP22_CLS_HEK_IP6_5T);
+	mvpp2_port_rss_hash_opts_set(port, UDP_V4_FLOW, MVPP22_CLS_HEK_IP4_5T);
+	mvpp2_port_rss_hash_opts_set(port, UDP_V6_FLOW, MVPP22_CLS_HEK_IP6_5T);
 }
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
index 8e1d7f9ffa0b..089f05f29891 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
@@ -1,27 +1,187 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * RSS and Classifier definitions for Marvell PPv2 Network Controller
  *
  * Copyright (C) 2014 Marvell
  *
  * Marcin Wojtas <mw@semihalf.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 
 #ifndef _MVPP2_CLS_H_
 #define _MVPP2_CLS_H_
 
+#include "mvpp2.h"
+#include "mvpp2_prs.h"
+
 /* Classifier constants */
 #define MVPP2_CLS_FLOWS_TBL_SIZE	512
 #define MVPP2_CLS_FLOWS_TBL_DATA_WORDS	3
 #define MVPP2_CLS_LKP_TBL_SIZE		64
 #define MVPP2_CLS_RX_QUEUES		256
 
-/* RSS constants */
-#define MVPP22_RSS_TABLE_ENTRIES	32
+/* Classifier flow constants */
+
+#define MVPP2_FLOW_N_FIELDS		4
+
+enum mvpp2_cls_engine {
+	MVPP22_CLS_ENGINE_C2 = 1,
+	MVPP22_CLS_ENGINE_C3A,
+	MVPP22_CLS_ENGINE_C3B,
+	MVPP22_CLS_ENGINE_C4,
+	MVPP22_CLS_ENGINE_C3HA = 6,
+	MVPP22_CLS_ENGINE_C3HB = 7,
+};
+
+#define MVPP22_CLS_HEK_OPT_MAC_DA	BIT(0)
+#define MVPP22_CLS_HEK_OPT_VLAN		BIT(1)
+#define MVPP22_CLS_HEK_OPT_L3_PROTO	BIT(2)
+#define MVPP22_CLS_HEK_OPT_IP4SA	BIT(3)
+#define MVPP22_CLS_HEK_OPT_IP4DA	BIT(4)
+#define MVPP22_CLS_HEK_OPT_IP6SA	BIT(5)
+#define MVPP22_CLS_HEK_OPT_IP6DA	BIT(6)
+#define MVPP22_CLS_HEK_OPT_L4SIP	BIT(7)
+#define MVPP22_CLS_HEK_OPT_L4DIP	BIT(8)
+#define MVPP22_CLS_HEK_N_FIELDS		9
+
+#define MVPP22_CLS_HEK_L4_OPTS	(MVPP22_CLS_HEK_OPT_L4SIP | \
+				 MVPP22_CLS_HEK_OPT_L4DIP)
+
+#define MVPP22_CLS_HEK_IP4_2T	(MVPP22_CLS_HEK_OPT_IP4SA | \
+				 MVPP22_CLS_HEK_OPT_IP4DA)
+
+#define MVPP22_CLS_HEK_IP6_2T	(MVPP22_CLS_HEK_OPT_IP6SA | \
+				 MVPP22_CLS_HEK_OPT_IP6DA)
+
+/* The fifth tuple in "5T" is the L4_Info field */
+#define MVPP22_CLS_HEK_IP4_5T	(MVPP22_CLS_HEK_IP4_2T | \
+				 MVPP22_CLS_HEK_L4_OPTS)
+
+#define MVPP22_CLS_HEK_IP6_5T	(MVPP22_CLS_HEK_IP6_2T | \
+				 MVPP22_CLS_HEK_L4_OPTS)
+
+enum mvpp2_cls_field_id {
+	MVPP22_CLS_FIELD_MAC_DA = 0x03,
+	MVPP22_CLS_FIELD_VLAN = 0x06,
+	MVPP22_CLS_FIELD_L3_PROTO = 0x0f,
+	MVPP22_CLS_FIELD_IP4SA = 0x10,
+	MVPP22_CLS_FIELD_IP4DA = 0x11,
+	MVPP22_CLS_FIELD_IP6SA = 0x17,
+	MVPP22_CLS_FIELD_IP6DA = 0x1a,
+	MVPP22_CLS_FIELD_L4SIP = 0x1d,
+	MVPP22_CLS_FIELD_L4DIP = 0x1e,
+};
+
+enum mvpp2_cls_flow_seq {
+	MVPP2_CLS_FLOW_SEQ_NORMAL = 0,
+	MVPP2_CLS_FLOW_SEQ_FIRST1,
+	MVPP2_CLS_FLOW_SEQ_FIRST2,
+	MVPP2_CLS_FLOW_SEQ_LAST,
+	MVPP2_CLS_FLOW_SEQ_MIDDLE
+};
+
+/* Classifier C2 engine constants */
+#define MVPP22_CLS_C2_TCAM_EN(data)		((data) << 16)
+
+enum mvpp22_cls_c2_action {
+	MVPP22_C2_NO_UPD = 0,
+	MVPP22_C2_NO_UPD_LOCK,
+	MVPP22_C2_UPD,
+	MVPP22_C2_UPD_LOCK,
+};
+
+enum mvpp22_cls_c2_fwd_action {
+	MVPP22_C2_FWD_NO_UPD = 0,
+	MVPP22_C2_FWD_NO_UPD_LOCK,
+	MVPP22_C2_FWD_SW,
+	MVPP22_C2_FWD_SW_LOCK,
+	MVPP22_C2_FWD_HW,
+	MVPP22_C2_FWD_HW_LOCK,
+	MVPP22_C2_FWD_HW_LOW_LAT,
+	MVPP22_C2_FWD_HW_LOW_LAT_LOCK,
+};
+
+#define MVPP2_CLS_C2_TCAM_WORDS			5
+#define MVPP2_CLS_C2_ATTR_WORDS			5
+
+struct mvpp2_cls_c2_entry {
+	u32 index;
+	u32 tcam[MVPP2_CLS_C2_TCAM_WORDS];
+	u32 act;
+	u32 attr[MVPP2_CLS_C2_ATTR_WORDS];
+};
+
+/* Classifier C2 engine entries */
+#define MVPP22_CLS_C2_RSS_ENTRY(port)	(port)
+#define MVPP22_CLS_C2_N_ENTRIES		MVPP2_MAX_PORTS
 
+/* RSS flow entries in the flow table. We have 2 entries per port for RSS.
+ *
+ * The first performs a lookup using the C2 TCAM engine, to tag the
+ * packet for software forwarding (needed for RSS), enable or disable RSS, and
+ * assign the default rx queue.
+ *
+ * The second configures the hash generation, by specifying which fields of the
+ * packet header are used to generate the hash, and specifies the relevant hash
+ * engine to use.
+ */
+#define MVPP22_RSS_FLOW_C2_OFFS		0
+#define MVPP22_RSS_FLOW_HASH_OFFS	1
+#define MVPP22_RSS_FLOW_SIZE		(MVPP22_RSS_FLOW_HASH_OFFS + 1)
+
+#define MVPP22_RSS_FLOW_C2(port)	((port) * MVPP22_RSS_FLOW_SIZE + \
+					 MVPP22_RSS_FLOW_C2_OFFS)
+#define MVPP22_RSS_FLOW_HASH(port)	((port) * MVPP22_RSS_FLOW_SIZE + \
+					 MVPP22_RSS_FLOW_HASH_OFFS)
+#define MVPP22_RSS_FLOW_FIRST(port)	MVPP22_RSS_FLOW_C2(port)
+
+/* Packet flow ID */
+enum mvpp2_prs_flow {
+	MVPP2_FL_START = 8,
+	MVPP2_FL_IP4_TCP_NF_UNTAG = MVPP2_FL_START,
+	MVPP2_FL_IP4_UDP_NF_UNTAG,
+	MVPP2_FL_IP4_TCP_NF_TAG,
+	MVPP2_FL_IP4_UDP_NF_TAG,
+	MVPP2_FL_IP6_TCP_NF_UNTAG,
+	MVPP2_FL_IP6_UDP_NF_UNTAG,
+	MVPP2_FL_IP6_TCP_NF_TAG,
+	MVPP2_FL_IP6_UDP_NF_TAG,
+	MVPP2_FL_IP4_TCP_FRAG_UNTAG,
+	MVPP2_FL_IP4_UDP_FRAG_UNTAG,
+	MVPP2_FL_IP4_TCP_FRAG_TAG,
+	MVPP2_FL_IP4_UDP_FRAG_TAG,
+	MVPP2_FL_IP6_TCP_FRAG_UNTAG,
+	MVPP2_FL_IP6_UDP_FRAG_UNTAG,
+	MVPP2_FL_IP6_TCP_FRAG_TAG,
+	MVPP2_FL_IP6_UDP_FRAG_TAG,
+	MVPP2_FL_IP4_UNTAG, /* non-TCP, non-UDP, same for below */
+	MVPP2_FL_IP4_TAG,
+	MVPP2_FL_IP6_UNTAG,
+	MVPP2_FL_IP6_TAG,
+	MVPP2_FL_NON_IP_UNTAG,
+	MVPP2_FL_NON_IP_TAG,
+	MVPP2_FL_LAST,
+};
+
+struct mvpp2_cls_flow {
+	/* The L2-L4 traffic flow type */
+	int flow_type;
+
+	/* The first id in the flow table for this flow */
+	u16 flow_id;
+
+	/* The supported HEK fields for this flow */
+	u16 supported_hash_opts;
+
+	/* The Header Parser result_info that matches this flow */
+	struct mvpp2_prs_result_info prs_ri;
+};
+
+#define MVPP2_N_FLOWS	52
+
+#define MVPP2_ENTRIES_PER_FLOW			(MVPP2_MAX_PORTS + 1)
+#define MVPP2_FLOW_C2_ENTRY(id)			((id) * MVPP2_ENTRIES_PER_FLOW)
+#define MVPP2_PORT_FLOW_HASH_ENTRY(port, id)	((id) * MVPP2_ENTRIES_PER_FLOW + \
+						(port) + 1)
 struct mvpp2_cls_flow_entry {
 	u32 index;
 	u32 data[MVPP2_CLS_FLOWS_TBL_DATA_WORDS];
@@ -33,7 +193,15 @@ struct mvpp2_cls_lookup_entry {
 	u32 data;
 };
 
-void mvpp22_init_rss(struct mvpp2_port *port);
+void mvpp22_rss_fill_table(struct mvpp2_port *port, u32 table);
+
+void mvpp22_rss_port_init(struct mvpp2_port *port);
+
+void mvpp22_rss_enable(struct mvpp2_port *port);
+void mvpp22_rss_disable(struct mvpp2_port *port);
+
+int mvpp2_ethtool_rxfh_get(struct mvpp2_port *port, struct ethtool_rxnfc *info);
+int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, struct ethtool_rxnfc *info);
 
 void mvpp2_cls_init(struct mvpp2 *priv);
 
@@ -41,4 +209,25 @@ void mvpp2_cls_port_config(struct mvpp2_port *port);
 
 void mvpp2_cls_oversize_rxq_set(struct mvpp2_port *port);
 
+int mvpp2_cls_flow_eng_get(struct mvpp2_cls_flow_entry *fe);
+
+u16 mvpp2_flow_get_hek_fields(struct mvpp2_cls_flow_entry *fe);
+
+struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow);
+
+u32 mvpp2_cls_flow_hits(struct mvpp2 *priv, int index);
+
+void mvpp2_cls_flow_read(struct mvpp2 *priv, int index,
+			 struct mvpp2_cls_flow_entry *fe);
+
+u32 mvpp2_cls_lookup_hits(struct mvpp2 *priv, int index);
+
+void mvpp2_cls_lookup_read(struct mvpp2 *priv, int lkpid, int way,
+			   struct mvpp2_cls_lookup_entry *le);
+
+u32 mvpp2_cls_c2_hit_count(struct mvpp2 *priv, int c2_index);
+
+void mvpp2_cls_c2_read(struct mvpp2 *priv, int index,
+		       struct mvpp2_cls_c2_entry *c2);
+
 #endif
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
new file mode 100644
index 000000000000..f9744a61e5dd
--- /dev/null
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
@@ -0,0 +1,703 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Driver for Marvell PPv2 network controller for Armada 375 SoC.
+ *
+ * Copyright (C) 2018 Marvell
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/debugfs.h>
+
+#include "mvpp2.h"
+#include "mvpp2_prs.h"
+#include "mvpp2_cls.h"
+
+struct mvpp2_dbgfs_prs_entry {
+	int tid;
+	struct mvpp2 *priv;
+};
+
+struct mvpp2_dbgfs_flow_entry {
+	int flow;
+	struct mvpp2 *priv;
+};
+
+struct mvpp2_dbgfs_port_flow_entry {
+	struct mvpp2_port *port;
+	struct mvpp2_dbgfs_flow_entry *dbg_fe;
+};
+
+static int mvpp2_dbgfs_flow_flt_hits_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_flow_entry *entry = s->private;
+	int id = MVPP2_FLOW_C2_ENTRY(entry->flow);
+
+	u32 hits = mvpp2_cls_flow_hits(entry->priv, id);
+
+	seq_printf(s, "%u\n", hits);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_flt_hits);
+
+static int mvpp2_dbgfs_flow_dec_hits_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_flow_entry *entry = s->private;
+
+	u32 hits = mvpp2_cls_lookup_hits(entry->priv, entry->flow);
+
+	seq_printf(s, "%u\n", hits);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_dec_hits);
+
+static int mvpp2_dbgfs_flow_type_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_flow_entry *entry = s->private;
+	struct mvpp2_cls_flow *f;
+	const char *flow_name;
+
+	f = mvpp2_cls_flow_get(entry->flow);
+	if (!f)
+		return -EINVAL;
+
+	switch (f->flow_type) {
+	case IPV4_FLOW:
+		flow_name = "ipv4";
+		break;
+	case IPV6_FLOW:
+		flow_name = "ipv6";
+		break;
+	case TCP_V4_FLOW:
+		flow_name = "tcp4";
+		break;
+	case TCP_V6_FLOW:
+		flow_name = "tcp6";
+		break;
+	case UDP_V4_FLOW:
+		flow_name = "udp4";
+		break;
+	case UDP_V6_FLOW:
+		flow_name = "udp6";
+		break;
+	default:
+		flow_name = "other";
+	}
+
+	seq_printf(s, "%s\n", flow_name);
+
+	return 0;
+}
+
+static int mvpp2_dbgfs_flow_type_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mvpp2_dbgfs_flow_type_show, inode->i_private);
+}
+
+static int mvpp2_dbgfs_flow_type_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct mvpp2_dbgfs_flow_entry *flow_entry = seq->private;
+
+	kfree(flow_entry);
+	return single_release(inode, file);
+}
+
+static const struct file_operations mvpp2_dbgfs_flow_type_fops = {
+	.open = mvpp2_dbgfs_flow_type_open,
+	.read = seq_read,
+	.release = mvpp2_dbgfs_flow_type_release,
+};
+
+static int mvpp2_dbgfs_flow_id_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_flow_entry *entry = s->private;
+	struct mvpp2_cls_flow *f;
+
+	f = mvpp2_cls_flow_get(entry->flow);
+	if (!f)
+		return -EINVAL;
+
+	seq_printf(s, "%d\n", f->flow_id);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_id);
+
+static int mvpp2_dbgfs_port_flow_hash_opt_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_port_flow_entry *entry = s->private;
+	struct mvpp2_port *port = entry->port;
+	struct mvpp2_cls_flow_entry fe;
+	struct mvpp2_cls_flow *f;
+	int flow_index;
+	u16 hash_opts;
+
+	f = mvpp2_cls_flow_get(entry->dbg_fe->flow);
+	if (!f)
+		return -EINVAL;
+
+	flow_index = MVPP2_PORT_FLOW_HASH_ENTRY(entry->port->id, f->flow_id);
+
+	mvpp2_cls_flow_read(port->priv, flow_index, &fe);
+
+	hash_opts = mvpp2_flow_get_hek_fields(&fe);
+
+	seq_printf(s, "0x%04x\n", hash_opts);
+
+	return 0;
+}
+
+static int mvpp2_dbgfs_port_flow_hash_opt_open(struct inode *inode,
+					       struct file *file)
+{
+	return single_open(file, mvpp2_dbgfs_port_flow_hash_opt_show,
+			   inode->i_private);
+}
+
+static int mvpp2_dbgfs_port_flow_hash_opt_release(struct inode *inode,
+						  struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct mvpp2_dbgfs_port_flow_entry *flow_entry = seq->private;
+
+	kfree(flow_entry);
+	return single_release(inode, file);
+}
+
+static const struct file_operations mvpp2_dbgfs_port_flow_hash_opt_fops = {
+	.open = mvpp2_dbgfs_port_flow_hash_opt_open,
+	.read = seq_read,
+	.release = mvpp2_dbgfs_port_flow_hash_opt_release,
+};
+
+static int mvpp2_dbgfs_port_flow_engine_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_port_flow_entry *entry = s->private;
+	struct mvpp2_port *port = entry->port;
+	struct mvpp2_cls_flow_entry fe;
+	struct mvpp2_cls_flow *f;
+	int flow_index, engine;
+
+	f = mvpp2_cls_flow_get(entry->dbg_fe->flow);
+	if (!f)
+		return -EINVAL;
+
+	flow_index = MVPP2_PORT_FLOW_HASH_ENTRY(entry->port->id, f->flow_id);
+
+	mvpp2_cls_flow_read(port->priv, flow_index, &fe);
+
+	engine = mvpp2_cls_flow_eng_get(&fe);
+
+	seq_printf(s, "%d\n", engine);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_port_flow_engine);
+
+static int mvpp2_dbgfs_flow_c2_hits_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_port *port = s->private;
+	u32 hits;
+
+	hits = mvpp2_cls_c2_hit_count(port->priv,
+				      MVPP22_CLS_C2_RSS_ENTRY(port->id));
+
+	seq_printf(s, "%u\n", hits);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_c2_hits);
+
+static int mvpp2_dbgfs_flow_c2_rxq_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_port *port = s->private;
+	struct mvpp2_cls_c2_entry c2;
+	u8 qh, ql;
+
+	mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
+
+	qh = (c2.attr[0] >> MVPP22_CLS_C2_ATTR0_QHIGH_OFFS) &
+	     MVPP22_CLS_C2_ATTR0_QHIGH_MASK;
+
+	ql = (c2.attr[0] >> MVPP22_CLS_C2_ATTR0_QLOW_OFFS) &
+	     MVPP22_CLS_C2_ATTR0_QLOW_MASK;
+
+	seq_printf(s, "%d\n", (qh << 3 | ql));
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_c2_rxq);
+
+static int mvpp2_dbgfs_flow_c2_enable_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_port *port = s->private;
+	struct mvpp2_cls_c2_entry c2;
+	int enabled;
+
+	mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
+
+	enabled = !!(c2.attr[2] & MVPP22_CLS_C2_ATTR2_RSS_EN);
+
+	seq_printf(s, "%d\n", enabled);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_c2_enable);
+
+static int mvpp2_dbgfs_port_vid_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_port *port = s->private;
+	unsigned char byte[2], enable[2];
+	struct mvpp2 *priv = port->priv;
+	struct mvpp2_prs_entry pe;
+	unsigned long pmap;
+	u16 rvid;
+	int tid;
+
+	for (tid = MVPP2_PRS_VID_PORT_FIRST(port->id);
+	     tid <= MVPP2_PRS_VID_PORT_LAST(port->id); tid++) {
+		mvpp2_prs_init_from_hw(priv, &pe, tid);
+
+		pmap = mvpp2_prs_tcam_port_map_get(&pe);
+
+		if (!priv->prs_shadow[tid].valid)
+			continue;
+
+		if (!test_bit(port->id, &pmap))
+			continue;
+
+		mvpp2_prs_tcam_data_byte_get(&pe, 2, &byte[0], &enable[0]);
+		mvpp2_prs_tcam_data_byte_get(&pe, 3, &byte[1], &enable[1]);
+
+		rvid = ((byte[0] & 0xf) << 8) + byte[1];
+
+		seq_printf(s, "%u\n", rvid);
+	}
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_port_vid);
+
+static int mvpp2_dbgfs_port_parser_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_port *port = s->private;
+	struct mvpp2 *priv = port->priv;
+	struct mvpp2_prs_entry pe;
+	unsigned long pmap;
+	int i;
+
+	for (i = 0; i < MVPP2_PRS_TCAM_SRAM_SIZE; i++) {
+		mvpp2_prs_init_from_hw(port->priv, &pe, i);
+
+		pmap = mvpp2_prs_tcam_port_map_get(&pe);
+		if (priv->prs_shadow[i].valid && test_bit(port->id, &pmap))
+			seq_printf(s, "%03d\n", i);
+	}
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_port_parser);
+
+static int mvpp2_dbgfs_filter_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_port *port = s->private;
+	struct mvpp2 *priv = port->priv;
+	struct mvpp2_prs_entry pe;
+	unsigned long pmap;
+	int index, tid;
+
+	for (tid = MVPP2_PE_MAC_RANGE_START;
+	     tid <= MVPP2_PE_MAC_RANGE_END; tid++) {
+		unsigned char da[ETH_ALEN], da_mask[ETH_ALEN];
+
+		if (!priv->prs_shadow[tid].valid ||
+		    priv->prs_shadow[tid].lu != MVPP2_PRS_LU_MAC ||
+		    priv->prs_shadow[tid].udf != MVPP2_PRS_UDF_MAC_DEF)
+			continue;
+
+		mvpp2_prs_init_from_hw(priv, &pe, tid);
+
+		pmap = mvpp2_prs_tcam_port_map_get(&pe);
+
+		/* We only want entries active on this port */
+		if (!test_bit(port->id, &pmap))
+			continue;
+
+		/* Read mac addr from entry */
+		for (index = 0; index < ETH_ALEN; index++)
+			mvpp2_prs_tcam_data_byte_get(&pe, index, &da[index],
+						     &da_mask[index]);
+
+		seq_printf(s, "%pM\n", da);
+	}
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_filter);
+
+static int mvpp2_dbgfs_prs_lu_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_prs_entry *entry = s->private;
+	struct mvpp2 *priv = entry->priv;
+
+	seq_printf(s, "%x\n", priv->prs_shadow[entry->tid].lu);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_lu);
+
+static int mvpp2_dbgfs_prs_pmap_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_prs_entry *entry = s->private;
+	struct mvpp2_prs_entry pe;
+	unsigned int pmap;
+
+	mvpp2_prs_init_from_hw(entry->priv, &pe, entry->tid);
+
+	pmap = mvpp2_prs_tcam_port_map_get(&pe);
+	pmap &= MVPP2_PRS_PORT_MASK;
+
+	seq_printf(s, "%02x\n", pmap);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_pmap);
+
+static int mvpp2_dbgfs_prs_ai_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_prs_entry *entry = s->private;
+	struct mvpp2_prs_entry pe;
+	unsigned char ai, ai_mask;
+
+	mvpp2_prs_init_from_hw(entry->priv, &pe, entry->tid);
+
+	ai = pe.tcam[MVPP2_PRS_TCAM_AI_WORD] & MVPP2_PRS_AI_MASK;
+	ai_mask = (pe.tcam[MVPP2_PRS_TCAM_AI_WORD] >> 16) & MVPP2_PRS_AI_MASK;
+
+	seq_printf(s, "%02x %02x\n", ai, ai_mask);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_ai);
+
+static int mvpp2_dbgfs_prs_hdata_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_prs_entry *entry = s->private;
+	struct mvpp2_prs_entry pe;
+	unsigned char data[8], mask[8];
+	int i;
+
+	mvpp2_prs_init_from_hw(entry->priv, &pe, entry->tid);
+
+	for (i = 0; i < 8; i++)
+		mvpp2_prs_tcam_data_byte_get(&pe, i, &data[i], &mask[i]);
+
+	seq_printf(s, "%*phN %*phN\n", 8, data, 8, mask);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_hdata);
+
+static int mvpp2_dbgfs_prs_sram_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_prs_entry *entry = s->private;
+	struct mvpp2_prs_entry pe;
+
+	mvpp2_prs_init_from_hw(entry->priv, &pe, entry->tid);
+
+	seq_printf(s, "%*phN\n", 14, pe.sram);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_sram);
+
+static int mvpp2_dbgfs_prs_hits_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_prs_entry *entry = s->private;
+	int val;
+
+	val = mvpp2_prs_hits(entry->priv, entry->tid);
+	if (val < 0)
+		return val;
+
+	seq_printf(s, "%d\n", val);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_hits);
+
+static int mvpp2_dbgfs_prs_valid_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_prs_entry *entry = s->private;
+	struct mvpp2 *priv = entry->priv;
+	int tid = entry->tid;
+
+	seq_printf(s, "%d\n", priv->prs_shadow[tid].valid ? 1 : 0);
+
+	return 0;
+}
+
+static int mvpp2_dbgfs_prs_valid_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mvpp2_dbgfs_prs_valid_show, inode->i_private);
+}
+
+static int mvpp2_dbgfs_prs_valid_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct mvpp2_dbgfs_prs_entry *entry = seq->private;
+
+	kfree(entry);
+	return single_release(inode, file);
+}
+
+static const struct file_operations mvpp2_dbgfs_prs_valid_fops = {
+	.open = mvpp2_dbgfs_prs_valid_open,
+	.read = seq_read,
+	.release = mvpp2_dbgfs_prs_valid_release,
+};
+
+static int mvpp2_dbgfs_flow_port_init(struct dentry *parent,
+				      struct mvpp2_port *port,
+				      struct mvpp2_dbgfs_flow_entry *entry)
+{
+	struct mvpp2_dbgfs_port_flow_entry *port_entry;
+	struct dentry *port_dir;
+
+	port_dir = debugfs_create_dir(port->dev->name, parent);
+	if (IS_ERR(port_dir))
+		return PTR_ERR(port_dir);
+
+	/* This will be freed by 'hash_opts' release op */
+	port_entry = kmalloc(sizeof(*port_entry), GFP_KERNEL);
+	if (!port_entry)
+		return -ENOMEM;
+
+	port_entry->port = port;
+	port_entry->dbg_fe = entry;
+
+	debugfs_create_file("hash_opts", 0444, port_dir, port_entry,
+			    &mvpp2_dbgfs_port_flow_hash_opt_fops);
+
+	debugfs_create_file("engine", 0444, port_dir, port_entry,
+			    &mvpp2_dbgfs_port_flow_engine_fops);
+
+	return 0;
+}
+
+static int mvpp2_dbgfs_flow_entry_init(struct dentry *parent,
+				       struct mvpp2 *priv, int flow)
+{
+	struct mvpp2_dbgfs_flow_entry *entry;
+	struct dentry *flow_entry_dir;
+	char flow_entry_name[10];
+	int i, ret;
+
+	sprintf(flow_entry_name, "%02d", flow);
+
+	flow_entry_dir = debugfs_create_dir(flow_entry_name, parent);
+	if (!flow_entry_dir)
+		return -ENOMEM;
+
+	/* This will be freed by 'type' release op */
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	entry->flow = flow;
+	entry->priv = priv;
+
+	debugfs_create_file("flow_hits", 0444, flow_entry_dir, entry,
+			    &mvpp2_dbgfs_flow_flt_hits_fops);
+
+	debugfs_create_file("dec_hits", 0444, flow_entry_dir, entry,
+			    &mvpp2_dbgfs_flow_dec_hits_fops);
+
+	debugfs_create_file("type", 0444, flow_entry_dir, entry,
+			    &mvpp2_dbgfs_flow_type_fops);
+
+	debugfs_create_file("id", 0444, flow_entry_dir, entry,
+			    &mvpp2_dbgfs_flow_id_fops);
+
+	/* Create entry for each port */
+	for (i = 0; i < priv->port_count; i++) {
+		ret = mvpp2_dbgfs_flow_port_init(flow_entry_dir,
+						 priv->port_list[i], entry);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static int mvpp2_dbgfs_flow_init(struct dentry *parent, struct mvpp2 *priv)
+{
+	struct dentry *flow_dir;
+	int i, ret;
+
+	flow_dir = debugfs_create_dir("flows", parent);
+	if (!flow_dir)
+		return -ENOMEM;
+
+	for (i = 0; i < MVPP2_N_FLOWS; i++) {
+		ret = mvpp2_dbgfs_flow_entry_init(flow_dir, priv, i);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int mvpp2_dbgfs_prs_entry_init(struct dentry *parent,
+				      struct mvpp2 *priv, int tid)
+{
+	struct mvpp2_dbgfs_prs_entry *entry;
+	struct dentry *prs_entry_dir;
+	char prs_entry_name[10];
+
+	if (tid >= MVPP2_PRS_TCAM_SRAM_SIZE)
+		return -EINVAL;
+
+	sprintf(prs_entry_name, "%03d", tid);
+
+	prs_entry_dir = debugfs_create_dir(prs_entry_name, parent);
+	if (!prs_entry_dir)
+		return -ENOMEM;
+
+	/* The 'valid' entry's ops will free that */
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	entry->tid = tid;
+	entry->priv = priv;
+
+	/* Create each attr */
+	debugfs_create_file("sram", 0444, prs_entry_dir, entry,
+			    &mvpp2_dbgfs_prs_sram_fops);
+
+	debugfs_create_file("valid", 0644, prs_entry_dir, entry,
+			    &mvpp2_dbgfs_prs_valid_fops);
+
+	debugfs_create_file("lookup_id", 0644, prs_entry_dir, entry,
+			    &mvpp2_dbgfs_prs_lu_fops);
+
+	debugfs_create_file("ai", 0644, prs_entry_dir, entry,
+			    &mvpp2_dbgfs_prs_ai_fops);
+
+	debugfs_create_file("header_data", 0644, prs_entry_dir, entry,
+			    &mvpp2_dbgfs_prs_hdata_fops);
+
+	debugfs_create_file("hits", 0444, prs_entry_dir, entry,
+			    &mvpp2_dbgfs_prs_hits_fops);
+
+	return 0;
+}
+
+static int mvpp2_dbgfs_prs_init(struct dentry *parent, struct mvpp2 *priv)
+{
+	struct dentry *prs_dir;
+	int i, ret;
+
+	prs_dir = debugfs_create_dir("parser", parent);
+	if (!prs_dir)
+		return -ENOMEM;
+
+	for (i = 0; i < MVPP2_PRS_TCAM_SRAM_SIZE; i++) {
+		ret = mvpp2_dbgfs_prs_entry_init(prs_dir, priv, i);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int mvpp2_dbgfs_port_init(struct dentry *parent,
+				 struct mvpp2_port *port)
+{
+	struct dentry *port_dir;
+
+	port_dir = debugfs_create_dir(port->dev->name, parent);
+	if (IS_ERR(port_dir))
+		return PTR_ERR(port_dir);
+
+	debugfs_create_file("parser_entries", 0444, port_dir, port,
+			    &mvpp2_dbgfs_port_parser_fops);
+
+	debugfs_create_file("mac_filter", 0444, port_dir, port,
+			    &mvpp2_dbgfs_filter_fops);
+
+	debugfs_create_file("vid_filter", 0444, port_dir, port,
+			    &mvpp2_dbgfs_port_vid_fops);
+
+	debugfs_create_file("c2_hits", 0444, port_dir, port,
+			    &mvpp2_dbgfs_flow_c2_hits_fops);
+
+	debugfs_create_file("default_rxq", 0444, port_dir, port,
+			    &mvpp2_dbgfs_flow_c2_rxq_fops);
+
+	debugfs_create_file("rss_enable", 0444, port_dir, port,
+			    &mvpp2_dbgfs_flow_c2_enable_fops);
+
+	return 0;
+}
+
+void mvpp2_dbgfs_cleanup(struct mvpp2 *priv)
+{
+	debugfs_remove_recursive(priv->dbgfs_dir);
+}
+
+void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name)
+{
+	struct dentry *mvpp2_dir, *mvpp2_root;
+	int ret, i;
+
+	mvpp2_root = debugfs_lookup(MVPP2_DRIVER_NAME, NULL);
+	if (!mvpp2_root) {
+		mvpp2_root = debugfs_create_dir(MVPP2_DRIVER_NAME, NULL);
+		if (IS_ERR(mvpp2_root))
+			return;
+	}
+
+	mvpp2_dir = debugfs_create_dir(name, mvpp2_root);
+	if (IS_ERR(mvpp2_dir))
+		return;
+
+	priv->dbgfs_dir = mvpp2_dir;
+
+	ret = mvpp2_dbgfs_prs_init(mvpp2_dir, priv);
+	if (ret)
+		goto err;
+
+	for (i = 0; i < priv->port_count; i++) {
+		ret = mvpp2_dbgfs_port_init(mvpp2_dir, priv->port_list[i]);
+		if (ret)
+			goto err;
+	}
+
+	ret = mvpp2_dbgfs_flow_init(mvpp2_dir, priv);
+	if (ret)
+		goto err;
+
+	return;
+err:
+	mvpp2_dbgfs_cleanup(priv);
+}
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 0319ed9ef8b8..32d785b616e1 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Driver for Marvell PPv2 network controller for Armada 375 SoC.
  *
  * Copyright (C) 2014 Marvell
  *
  * Marcin Wojtas <mw@semihalf.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 
 #include <linux/acpi.h>
@@ -66,7 +63,7 @@ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode,
 #define MVPP2_QDIST_SINGLE_MODE	0
 #define MVPP2_QDIST_MULTI_MODE	1
 
-static int queue_mode = MVPP2_QDIST_SINGLE_MODE;
+static int queue_mode = MVPP2_QDIST_MULTI_MODE;
 
 module_param(queue_mode, int, 0444);
 MODULE_PARM_DESC(queue_mode, "Set queue_mode (single=0, multi=1)");
@@ -151,9 +148,10 @@ static dma_addr_t mvpp2_txdesc_dma_addr_get(struct mvpp2_port *port,
 					    struct mvpp2_tx_desc *tx_desc)
 {
 	if (port->priv->hw_version == MVPP21)
-		return tx_desc->pp21.buf_dma_addr;
+		return le32_to_cpu(tx_desc->pp21.buf_dma_addr);
 	else
-		return tx_desc->pp22.buf_dma_addr_ptp & MVPP2_DESC_DMA_MASK;
+		return le64_to_cpu(tx_desc->pp22.buf_dma_addr_ptp) &
+		       MVPP2_DESC_DMA_MASK;
 }
 
 static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port,
@@ -166,12 +164,12 @@ static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port,
 	offset = dma_addr & MVPP2_TX_DESC_ALIGN;
 
 	if (port->priv->hw_version == MVPP21) {
-		tx_desc->pp21.buf_dma_addr = addr;
+		tx_desc->pp21.buf_dma_addr = cpu_to_le32(addr);
 		tx_desc->pp21.packet_offset = offset;
 	} else {
-		u64 val = (u64)addr;
+		__le64 val = cpu_to_le64(addr);
 
-		tx_desc->pp22.buf_dma_addr_ptp &= ~MVPP2_DESC_DMA_MASK;
+		tx_desc->pp22.buf_dma_addr_ptp &= ~cpu_to_le64(MVPP2_DESC_DMA_MASK);
 		tx_desc->pp22.buf_dma_addr_ptp |= val;
 		tx_desc->pp22.packet_offset = offset;
 	}
@@ -181,9 +179,9 @@ static size_t mvpp2_txdesc_size_get(struct mvpp2_port *port,
 				    struct mvpp2_tx_desc *tx_desc)
 {
 	if (port->priv->hw_version == MVPP21)
-		return tx_desc->pp21.data_size;
+		return le16_to_cpu(tx_desc->pp21.data_size);
 	else
-		return tx_desc->pp22.data_size;
+		return le16_to_cpu(tx_desc->pp22.data_size);
 }
 
 static void mvpp2_txdesc_size_set(struct mvpp2_port *port,
@@ -191,9 +189,9 @@ static void mvpp2_txdesc_size_set(struct mvpp2_port *port,
 				  size_t size)
 {
 	if (port->priv->hw_version == MVPP21)
-		tx_desc->pp21.data_size = size;
+		tx_desc->pp21.data_size = cpu_to_le16(size);
 	else
-		tx_desc->pp22.data_size = size;
+		tx_desc->pp22.data_size = cpu_to_le16(size);
 }
 
 static void mvpp2_txdesc_txq_set(struct mvpp2_port *port,
@@ -211,9 +209,9 @@ static void mvpp2_txdesc_cmd_set(struct mvpp2_port *port,
 				 unsigned int command)
 {
 	if (port->priv->hw_version == MVPP21)
-		tx_desc->pp21.command = command;
+		tx_desc->pp21.command = cpu_to_le32(command);
 	else
-		tx_desc->pp22.command = command;
+		tx_desc->pp22.command = cpu_to_le32(command);
 }
 
 static unsigned int mvpp2_txdesc_offset_get(struct mvpp2_port *port,
@@ -229,36 +227,38 @@ static dma_addr_t mvpp2_rxdesc_dma_addr_get(struct mvpp2_port *port,
 					    struct mvpp2_rx_desc *rx_desc)
 {
 	if (port->priv->hw_version == MVPP21)
-		return rx_desc->pp21.buf_dma_addr;
+		return le32_to_cpu(rx_desc->pp21.buf_dma_addr);
 	else
-		return rx_desc->pp22.buf_dma_addr_key_hash & MVPP2_DESC_DMA_MASK;
+		return le64_to_cpu(rx_desc->pp22.buf_dma_addr_key_hash) &
+		       MVPP2_DESC_DMA_MASK;
 }
 
 static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port,
 					     struct mvpp2_rx_desc *rx_desc)
 {
 	if (port->priv->hw_version == MVPP21)
-		return rx_desc->pp21.buf_cookie;
+		return le32_to_cpu(rx_desc->pp21.buf_cookie);
 	else
-		return rx_desc->pp22.buf_cookie_misc & MVPP2_DESC_DMA_MASK;
+		return le64_to_cpu(rx_desc->pp22.buf_cookie_misc) &
+		       MVPP2_DESC_DMA_MASK;
 }
 
 static size_t mvpp2_rxdesc_size_get(struct mvpp2_port *port,
 				    struct mvpp2_rx_desc *rx_desc)
 {
 	if (port->priv->hw_version == MVPP21)
-		return rx_desc->pp21.data_size;
+		return le16_to_cpu(rx_desc->pp21.data_size);
 	else
-		return rx_desc->pp22.data_size;
+		return le16_to_cpu(rx_desc->pp22.data_size);
 }
 
 static u32 mvpp2_rxdesc_status_get(struct mvpp2_port *port,
 				   struct mvpp2_rx_desc *rx_desc)
 {
 	if (port->priv->hw_version == MVPP21)
-		return rx_desc->pp21.status;
+		return le32_to_cpu(rx_desc->pp21.status);
 	else
-		return rx_desc->pp22.status;
+		return le32_to_cpu(rx_desc->pp22.status);
 }
 
 static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu)
@@ -1735,7 +1735,7 @@ static u32 mvpp2_txq_desc_csum(int l3_offs, int l3_proto,
 	command |= (ip_hdr_len << MVPP2_TXD_IP_HLEN_SHIFT);
 	command |= MVPP2_TXD_IP_CSUM_DISABLE;
 
-	if (l3_proto == swab16(ETH_P_IP)) {
+	if (l3_proto == htons(ETH_P_IP)) {
 		command &= ~MVPP2_TXD_IP_CSUM_DISABLE;	/* enable IPv4 csum */
 		command &= ~MVPP2_TXD_L3_IP6;		/* enable IPv4 */
 	} else {
@@ -3273,6 +3273,11 @@ static void mvpp2_irqs_deinit(struct mvpp2_port *port)
 	}
 }
 
+static bool mvpp22_rss_is_supported(void)
+{
+	return queue_mode == MVPP2_QDIST_MULTI_MODE;
+}
+
 static int mvpp2_open(struct net_device *dev)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
@@ -3365,9 +3370,6 @@ static int mvpp2_open(struct net_device *dev)
 
 	mvpp2_start_dev(port);
 
-	if (priv->hw_version == MVPP22)
-		mvpp22_init_rss(port);
-
 	/* Start hardware statistics gathering */
 	queue_delayed_work(priv->stats_queue, &port->stats_work,
 			   MVPP2_MIB_COUNTERS_STATS_DELAY);
@@ -3626,6 +3628,13 @@ static int mvpp2_set_features(struct net_device *dev,
 		}
 	}
 
+	if (changed & NETIF_F_RXHASH) {
+		if (features & NETIF_F_RXHASH)
+			mvpp22_rss_enable(port);
+		else
+			mvpp22_rss_disable(port);
+	}
+
 	return 0;
 }
 
@@ -3813,6 +3822,94 @@ static int mvpp2_ethtool_set_link_ksettings(struct net_device *dev,
 	return phylink_ethtool_ksettings_set(port->phylink, cmd);
 }
 
+static int mvpp2_ethtool_get_rxnfc(struct net_device *dev,
+				   struct ethtool_rxnfc *info, u32 *rules)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+	int ret = 0;
+
+	if (!mvpp22_rss_is_supported())
+		return -EOPNOTSUPP;
+
+	switch (info->cmd) {
+	case ETHTOOL_GRXFH:
+		ret = mvpp2_ethtool_rxfh_get(port, info);
+		break;
+	case ETHTOOL_GRXRINGS:
+		info->data = port->nrxqs;
+		break;
+	default:
+		return -ENOTSUPP;
+	}
+
+	return ret;
+}
+
+static int mvpp2_ethtool_set_rxnfc(struct net_device *dev,
+				   struct ethtool_rxnfc *info)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+	int ret = 0;
+
+	if (!mvpp22_rss_is_supported())
+		return -EOPNOTSUPP;
+
+	switch (info->cmd) {
+	case ETHTOOL_SRXFH:
+		ret = mvpp2_ethtool_rxfh_set(port, info);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+	return ret;
+}
+
+static u32 mvpp2_ethtool_get_rxfh_indir_size(struct net_device *dev)
+{
+	return mvpp22_rss_is_supported() ? MVPP22_RSS_TABLE_ENTRIES : 0;
+}
+
+static int mvpp2_ethtool_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
+				  u8 *hfunc)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+
+	if (!mvpp22_rss_is_supported())
+		return -EOPNOTSUPP;
+
+	if (indir)
+		memcpy(indir, port->indir,
+		       ARRAY_SIZE(port->indir) * sizeof(port->indir[0]));
+
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_CRC32;
+
+	return 0;
+}
+
+static int mvpp2_ethtool_set_rxfh(struct net_device *dev, const u32 *indir,
+				  const u8 *key, const u8 hfunc)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+
+	if (!mvpp22_rss_is_supported())
+		return -EOPNOTSUPP;
+
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_CRC32)
+		return -EOPNOTSUPP;
+
+	if (key)
+		return -EOPNOTSUPP;
+
+	if (indir) {
+		memcpy(port->indir, indir,
+		       ARRAY_SIZE(port->indir) * sizeof(port->indir[0]));
+		mvpp22_rss_fill_table(port, port->id);
+	}
+
+	return 0;
+}
+
 /* Device ops */
 
 static const struct net_device_ops mvpp2_netdev_ops = {
@@ -3844,6 +3941,12 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = {
 	.set_pauseparam		= mvpp2_ethtool_set_pause_param,
 	.get_link_ksettings	= mvpp2_ethtool_get_link_ksettings,
 	.set_link_ksettings	= mvpp2_ethtool_set_link_ksettings,
+	.get_rxnfc		= mvpp2_ethtool_get_rxnfc,
+	.set_rxnfc		= mvpp2_ethtool_set_rxnfc,
+	.get_rxfh_indir_size	= mvpp2_ethtool_get_rxfh_indir_size,
+	.get_rxfh		= mvpp2_ethtool_get_rxfh,
+	.set_rxfh		= mvpp2_ethtool_set_rxfh,
+
 };
 
 /* Used for PPv2.1, or PPv2.2 with the old Device Tree binding that
@@ -3985,8 +4088,8 @@ static int mvpp2_port_init(struct mvpp2_port *port)
 	    MVPP2_MAX_PORTS * priv->max_port_rxqs)
 		return -EINVAL;
 
-	if (port->nrxqs % 4 || (port->nrxqs > priv->max_port_rxqs) ||
-	    (port->ntxqs > MVPP2_MAX_TXQ))
+	if (port->nrxqs % MVPP2_DEFAULT_RXQ ||
+	    port->nrxqs > priv->max_port_rxqs || port->ntxqs > MVPP2_MAX_TXQ)
 		return -EINVAL;
 
 	/* Disable port */
@@ -4075,6 +4178,9 @@ static int mvpp2_port_init(struct mvpp2_port *port)
 	mvpp2_cls_oversize_rxq_set(port);
 	mvpp2_cls_port_config(port);
 
+	if (mvpp22_rss_is_supported())
+		mvpp22_rss_port_init(port);
+
 	/* Provide an initial Rx packet size */
 	port->pkt_size = MVPP2_RX_PKT_SIZE(port->dev->mtu);
 
@@ -4681,6 +4787,9 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	dev->hw_features |= features | NETIF_F_RXCSUM | NETIF_F_GRO |
 			    NETIF_F_HW_VLAN_CTAG_FILTER;
 
+	if (mvpp22_rss_is_supported())
+		dev->hw_features |= NETIF_F_RXHASH;
+
 	if (port->pool_long->id == MVPP2_BM_JUMBO && port->id != 0) {
 		dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
 		dev->hw_features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
@@ -5011,6 +5120,12 @@ static int mvpp2_probe(struct platform_device *pdev)
 			(unsigned long)of_device_get_match_data(&pdev->dev);
 	}
 
+	/* multi queue mode isn't supported on PPV2.1, fallback to single
+	 * mode
+	 */
+	if (priv->hw_version == MVPP21)
+		queue_mode = MVPP2_QDIST_SINGLE_MODE;
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(base))
@@ -5174,6 +5289,8 @@ static int mvpp2_probe(struct platform_device *pdev)
 		goto err_port_probe;
 	}
 
+	mvpp2_dbgfs_init(priv, pdev->name);
+
 	platform_set_drvdata(pdev, priv);
 	return 0;
 
@@ -5207,6 +5324,8 @@ static int mvpp2_remove(struct platform_device *pdev)
 	struct fwnode_handle *port_fwnode;
 	int i = 0;
 
+	mvpp2_dbgfs_cleanup(priv);
+
 	flush_workqueue(priv->stats_queue);
 	destroy_workqueue(priv->stats_queue);
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index 6bb69f086794..392fd895f278 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Header Parser helpers for Marvell PPv2 Network Controller
  *
  * Copyright (C) 2014 Marvell
  *
  * Marcin Wojtas <mw@semihalf.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 
 #include <linux/kernel.h>
@@ -30,24 +27,24 @@ static int mvpp2_prs_hw_write(struct mvpp2 *priv, struct mvpp2_prs_entry *pe)
 		return -EINVAL;
 
 	/* Clear entry invalidation bit */
-	pe->tcam.word[MVPP2_PRS_TCAM_INV_WORD] &= ~MVPP2_PRS_TCAM_INV_MASK;
+	pe->tcam[MVPP2_PRS_TCAM_INV_WORD] &= ~MVPP2_PRS_TCAM_INV_MASK;
 
 	/* Write tcam index - indirect access */
 	mvpp2_write(priv, MVPP2_PRS_TCAM_IDX_REG, pe->index);
 	for (i = 0; i < MVPP2_PRS_TCAM_WORDS; i++)
-		mvpp2_write(priv, MVPP2_PRS_TCAM_DATA_REG(i), pe->tcam.word[i]);
+		mvpp2_write(priv, MVPP2_PRS_TCAM_DATA_REG(i), pe->tcam[i]);
 
 	/* Write sram index - indirect access */
 	mvpp2_write(priv, MVPP2_PRS_SRAM_IDX_REG, pe->index);
 	for (i = 0; i < MVPP2_PRS_SRAM_WORDS; i++)
-		mvpp2_write(priv, MVPP2_PRS_SRAM_DATA_REG(i), pe->sram.word[i]);
+		mvpp2_write(priv, MVPP2_PRS_SRAM_DATA_REG(i), pe->sram[i]);
 
 	return 0;
 }
 
 /* Initialize tcam entry from hw */
-static int mvpp2_prs_init_from_hw(struct mvpp2 *priv,
-				  struct mvpp2_prs_entry *pe, int tid)
+int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe,
+			   int tid)
 {
 	int i;
 
@@ -60,18 +57,18 @@ static int mvpp2_prs_init_from_hw(struct mvpp2 *priv,
 	/* Write tcam index - indirect access */
 	mvpp2_write(priv, MVPP2_PRS_TCAM_IDX_REG, pe->index);
 
-	pe->tcam.word[MVPP2_PRS_TCAM_INV_WORD] = mvpp2_read(priv,
+	pe->tcam[MVPP2_PRS_TCAM_INV_WORD] = mvpp2_read(priv,
 			      MVPP2_PRS_TCAM_DATA_REG(MVPP2_PRS_TCAM_INV_WORD));
-	if (pe->tcam.word[MVPP2_PRS_TCAM_INV_WORD] & MVPP2_PRS_TCAM_INV_MASK)
+	if (pe->tcam[MVPP2_PRS_TCAM_INV_WORD] & MVPP2_PRS_TCAM_INV_MASK)
 		return MVPP2_PRS_TCAM_ENTRY_INVALID;
 
 	for (i = 0; i < MVPP2_PRS_TCAM_WORDS; i++)
-		pe->tcam.word[i] = mvpp2_read(priv, MVPP2_PRS_TCAM_DATA_REG(i));
+		pe->tcam[i] = mvpp2_read(priv, MVPP2_PRS_TCAM_DATA_REG(i));
 
 	/* Write sram index - indirect access */
 	mvpp2_write(priv, MVPP2_PRS_SRAM_IDX_REG, pe->index);
 	for (i = 0; i < MVPP2_PRS_SRAM_WORDS; i++)
-		pe->sram.word[i] = mvpp2_read(priv, MVPP2_PRS_SRAM_DATA_REG(i));
+		pe->sram[i] = mvpp2_read(priv, MVPP2_PRS_SRAM_DATA_REG(i));
 
 	return 0;
 }
@@ -103,42 +100,35 @@ static void mvpp2_prs_shadow_ri_set(struct mvpp2 *priv, int index,
 /* Update lookup field in tcam sw entry */
 static void mvpp2_prs_tcam_lu_set(struct mvpp2_prs_entry *pe, unsigned int lu)
 {
-	int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_LU_BYTE);
-
-	pe->tcam.byte[MVPP2_PRS_TCAM_LU_BYTE] = lu;
-	pe->tcam.byte[enable_off] = MVPP2_PRS_LU_MASK;
+	pe->tcam[MVPP2_PRS_TCAM_LU_WORD] &= ~MVPP2_PRS_TCAM_LU(MVPP2_PRS_LU_MASK);
+	pe->tcam[MVPP2_PRS_TCAM_LU_WORD] &= ~MVPP2_PRS_TCAM_LU_EN(MVPP2_PRS_LU_MASK);
+	pe->tcam[MVPP2_PRS_TCAM_LU_WORD] |= MVPP2_PRS_TCAM_LU(lu & MVPP2_PRS_LU_MASK);
+	pe->tcam[MVPP2_PRS_TCAM_LU_WORD] |= MVPP2_PRS_TCAM_LU_EN(MVPP2_PRS_LU_MASK);
 }
 
 /* Update mask for single port in tcam sw entry */
 static void mvpp2_prs_tcam_port_set(struct mvpp2_prs_entry *pe,
 				    unsigned int port, bool add)
 {
-	int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_PORT_BYTE);
-
 	if (add)
-		pe->tcam.byte[enable_off] &= ~(1 << port);
+		pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] &= ~MVPP2_PRS_TCAM_PORT_EN(BIT(port));
 	else
-		pe->tcam.byte[enable_off] |= 1 << port;
+		pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] |= MVPP2_PRS_TCAM_PORT_EN(BIT(port));
 }
 
 /* Update port map in tcam sw entry */
 static void mvpp2_prs_tcam_port_map_set(struct mvpp2_prs_entry *pe,
 					unsigned int ports)
 {
-	unsigned char port_mask = MVPP2_PRS_PORT_MASK;
-	int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_PORT_BYTE);
-
-	pe->tcam.byte[MVPP2_PRS_TCAM_PORT_BYTE] = 0;
-	pe->tcam.byte[enable_off] &= ~port_mask;
-	pe->tcam.byte[enable_off] |= ~ports & MVPP2_PRS_PORT_MASK;
+	pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] &= ~MVPP2_PRS_TCAM_PORT(MVPP2_PRS_PORT_MASK);
+	pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] &= ~MVPP2_PRS_TCAM_PORT_EN(MVPP2_PRS_PORT_MASK);
+	pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] |= MVPP2_PRS_TCAM_PORT_EN(~ports & MVPP2_PRS_PORT_MASK);
 }
 
 /* Obtain port map from tcam sw entry */
-static unsigned int mvpp2_prs_tcam_port_map_get(struct mvpp2_prs_entry *pe)
+unsigned int mvpp2_prs_tcam_port_map_get(struct mvpp2_prs_entry *pe)
 {
-	int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_PORT_BYTE);
-
-	return ~(pe->tcam.byte[enable_off]) & MVPP2_PRS_PORT_MASK;
+	return (~pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] >> 24) & MVPP2_PRS_PORT_MASK;
 }
 
 /* Set byte of data and its enable bits in tcam sw entry */
@@ -146,55 +136,58 @@ static void mvpp2_prs_tcam_data_byte_set(struct mvpp2_prs_entry *pe,
 					 unsigned int offs, unsigned char byte,
 					 unsigned char enable)
 {
-	pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE(offs)] = byte;
-	pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE_EN(offs)] = enable;
+	int pos = MVPP2_PRS_BYTE_IN_WORD(offs) * BITS_PER_BYTE;
+
+	pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] &= ~(0xff << pos);
+	pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] &= ~(MVPP2_PRS_TCAM_EN(0xff) << pos);
+	pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] |= byte << pos;
+	pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] |= MVPP2_PRS_TCAM_EN(enable << pos);
 }
 
 /* Get byte of data and its enable bits from tcam sw entry */
-static void mvpp2_prs_tcam_data_byte_get(struct mvpp2_prs_entry *pe,
-					 unsigned int offs, unsigned char *byte,
-					 unsigned char *enable)
+void mvpp2_prs_tcam_data_byte_get(struct mvpp2_prs_entry *pe,
+				  unsigned int offs, unsigned char *byte,
+				  unsigned char *enable)
 {
-	*byte = pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE(offs)];
-	*enable = pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE_EN(offs)];
+	int pos = MVPP2_PRS_BYTE_IN_WORD(offs) * BITS_PER_BYTE;
+
+	*byte = (pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] >> pos) & 0xff;
+	*enable = (pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] >> (pos + 16)) & 0xff;
 }
 
 /* Compare tcam data bytes with a pattern */
 static bool mvpp2_prs_tcam_data_cmp(struct mvpp2_prs_entry *pe, int offs,
 				    u16 data)
 {
-	int off = MVPP2_PRS_TCAM_DATA_BYTE(offs);
 	u16 tcam_data;
 
-	tcam_data = (pe->tcam.byte[off + 1] << 8) | pe->tcam.byte[off];
-	if (tcam_data != data)
-		return false;
-	return true;
+	tcam_data = pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] & 0xffff;
+	return tcam_data == data;
 }
 
 /* Update ai bits in tcam sw entry */
 static void mvpp2_prs_tcam_ai_update(struct mvpp2_prs_entry *pe,
 				     unsigned int bits, unsigned int enable)
 {
-	int i, ai_idx = MVPP2_PRS_TCAM_AI_BYTE;
+	int i;
 
 	for (i = 0; i < MVPP2_PRS_AI_BITS; i++) {
 		if (!(enable & BIT(i)))
 			continue;
 
 		if (bits & BIT(i))
-			pe->tcam.byte[ai_idx] |= 1 << i;
+			pe->tcam[MVPP2_PRS_TCAM_AI_WORD] |= BIT(i);
 		else
-			pe->tcam.byte[ai_idx] &= ~(1 << i);
+			pe->tcam[MVPP2_PRS_TCAM_AI_WORD] &= ~BIT(i);
 	}
 
-	pe->tcam.byte[MVPP2_PRS_TCAM_EN_OFFS(ai_idx)] |= enable;
+	pe->tcam[MVPP2_PRS_TCAM_AI_WORD] |= MVPP2_PRS_TCAM_AI_EN(enable);
 }
 
 /* Get ai bits from tcam sw entry */
 static int mvpp2_prs_tcam_ai_get(struct mvpp2_prs_entry *pe)
 {
-	return pe->tcam.byte[MVPP2_PRS_TCAM_AI_BYTE];
+	return pe->tcam[MVPP2_PRS_TCAM_AI_WORD] & MVPP2_PRS_AI_MASK;
 }
 
 /* Set ethertype in tcam sw entry */
@@ -215,16 +208,16 @@ static void mvpp2_prs_match_vid(struct mvpp2_prs_entry *pe, int offset,
 
 /* Set bits in sram sw entry */
 static void mvpp2_prs_sram_bits_set(struct mvpp2_prs_entry *pe, int bit_num,
-				    int val)
+				    u32 val)
 {
-	pe->sram.byte[MVPP2_BIT_TO_BYTE(bit_num)] |= (val << (bit_num % 8));
+	pe->sram[MVPP2_BIT_TO_WORD(bit_num)] |= (val << (MVPP2_BIT_IN_WORD(bit_num)));
 }
 
 /* Clear bits in sram sw entry */
 static void mvpp2_prs_sram_bits_clear(struct mvpp2_prs_entry *pe, int bit_num,
-				      int val)
+				      u32 val)
 {
-	pe->sram.byte[MVPP2_BIT_TO_BYTE(bit_num)] &= ~(val << (bit_num % 8));
+	pe->sram[MVPP2_BIT_TO_WORD(bit_num)] &= ~(val << (MVPP2_BIT_IN_WORD(bit_num)));
 }
 
 /* Update ri bits in sram sw entry */
@@ -234,15 +227,16 @@ static void mvpp2_prs_sram_ri_update(struct mvpp2_prs_entry *pe,
 	unsigned int i;
 
 	for (i = 0; i < MVPP2_PRS_SRAM_RI_CTRL_BITS; i++) {
-		int ri_off = MVPP2_PRS_SRAM_RI_OFFS;
-
 		if (!(mask & BIT(i)))
 			continue;
 
 		if (bits & BIT(i))
-			mvpp2_prs_sram_bits_set(pe, ri_off + i, 1);
+			mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_RI_OFFS + i,
+						1);
 		else
-			mvpp2_prs_sram_bits_clear(pe, ri_off + i, 1);
+			mvpp2_prs_sram_bits_clear(pe,
+						  MVPP2_PRS_SRAM_RI_OFFS + i,
+						  1);
 
 		mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_RI_CTRL_OFFS + i, 1);
 	}
@@ -251,7 +245,7 @@ static void mvpp2_prs_sram_ri_update(struct mvpp2_prs_entry *pe,
 /* Obtain ri bits from sram sw entry */
 static int mvpp2_prs_sram_ri_get(struct mvpp2_prs_entry *pe)
 {
-	return pe->sram.word[MVPP2_PRS_SRAM_RI_WORD];
+	return pe->sram[MVPP2_PRS_SRAM_RI_WORD];
 }
 
 /* Update ai bits in sram sw entry */
@@ -259,16 +253,18 @@ static void mvpp2_prs_sram_ai_update(struct mvpp2_prs_entry *pe,
 				     unsigned int bits, unsigned int mask)
 {
 	unsigned int i;
-	int ai_off = MVPP2_PRS_SRAM_AI_OFFS;
 
 	for (i = 0; i < MVPP2_PRS_SRAM_AI_CTRL_BITS; i++) {
 		if (!(mask & BIT(i)))
 			continue;
 
 		if (bits & BIT(i))
-			mvpp2_prs_sram_bits_set(pe, ai_off + i, 1);
+			mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_AI_OFFS + i,
+						1);
 		else
-			mvpp2_prs_sram_bits_clear(pe, ai_off + i, 1);
+			mvpp2_prs_sram_bits_clear(pe,
+						  MVPP2_PRS_SRAM_AI_OFFS + i,
+						  1);
 
 		mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_AI_CTRL_OFFS + i, 1);
 	}
@@ -278,12 +274,12 @@ static void mvpp2_prs_sram_ai_update(struct mvpp2_prs_entry *pe,
 static int mvpp2_prs_sram_ai_get(struct mvpp2_prs_entry *pe)
 {
 	u8 bits;
-	int ai_off = MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_AI_OFFS);
-	int ai_en_off = ai_off + 1;
-	int ai_shift = MVPP2_PRS_SRAM_AI_OFFS % 8;
+	/* ai is stored on bits 90->97; so it spreads across two u32 */
+	int ai_off = MVPP2_BIT_TO_WORD(MVPP2_PRS_SRAM_AI_OFFS);
+	int ai_shift = MVPP2_BIT_IN_WORD(MVPP2_PRS_SRAM_AI_OFFS);
 
-	bits = (pe->sram.byte[ai_off] >> ai_shift) |
-	       (pe->sram.byte[ai_en_off] << (8 - ai_shift));
+	bits = (pe->sram[ai_off] >> ai_shift) |
+	       (pe->sram[ai_off + 1] << (32 - ai_shift));
 
 	return bits;
 }
@@ -316,8 +312,7 @@ static void mvpp2_prs_sram_shift_set(struct mvpp2_prs_entry *pe, int shift,
 	}
 
 	/* Set value */
-	pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_SHIFT_OFFS)] =
-							   (unsigned char)shift;
+	pe->sram[MVPP2_BIT_TO_WORD(MVPP2_PRS_SRAM_SHIFT_OFFS)] = shift & MVPP2_PRS_SRAM_SHIFT_MASK;
 
 	/* Reset and set operation */
 	mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_OP_SEL_SHIFT_OFFS,
@@ -346,13 +341,8 @@ static void mvpp2_prs_sram_offset_set(struct mvpp2_prs_entry *pe,
 	/* Set value */
 	mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_UDF_OFFS,
 				  MVPP2_PRS_SRAM_UDF_MASK);
-	mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_UDF_OFFS, offset);
-	pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_UDF_OFFS +
-					MVPP2_PRS_SRAM_UDF_BITS)] &=
-	      ~(MVPP2_PRS_SRAM_UDF_MASK >> (8 - (MVPP2_PRS_SRAM_UDF_OFFS % 8)));
-	pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_UDF_OFFS +
-					MVPP2_PRS_SRAM_UDF_BITS)] |=
-				(offset >> (8 - (MVPP2_PRS_SRAM_UDF_OFFS % 8)));
+	mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_UDF_OFFS,
+				offset & MVPP2_PRS_SRAM_UDF_MASK);
 
 	/* Set offset type */
 	mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_UDF_TYPE_OFFS,
@@ -362,16 +352,8 @@ static void mvpp2_prs_sram_offset_set(struct mvpp2_prs_entry *pe,
 	/* Set offset operation */
 	mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS,
 				  MVPP2_PRS_SRAM_OP_SEL_UDF_MASK);
-	mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS, op);
-
-	pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS +
-					MVPP2_PRS_SRAM_OP_SEL_UDF_BITS)] &=
-					     ~(MVPP2_PRS_SRAM_OP_SEL_UDF_MASK >>
-				    (8 - (MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS % 8)));
-
-	pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS +
-					MVPP2_PRS_SRAM_OP_SEL_UDF_BITS)] |=
-			     (op >> (8 - (MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS % 8)));
+	mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS,
+				op & MVPP2_PRS_SRAM_OP_SEL_UDF_MASK);
 
 	/* Set base offset as current */
 	mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_OP_SEL_BASE_OFFS, 1);
@@ -662,7 +644,7 @@ static int mvpp2_prs_vlan_find(struct mvpp2 *priv, unsigned short tpid, int ai)
 			continue;
 
 		mvpp2_prs_init_from_hw(priv, &pe, tid);
-		match = mvpp2_prs_tcam_data_cmp(&pe, 0, swab16(tpid));
+		match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid);
 		if (!match)
 			continue;
 
@@ -790,8 +772,8 @@ static int mvpp2_prs_double_vlan_find(struct mvpp2 *priv, unsigned short tpid1,
 
 		mvpp2_prs_init_from_hw(priv, &pe, tid);
 
-		match = mvpp2_prs_tcam_data_cmp(&pe, 0, swab16(tpid1)) &&
-			mvpp2_prs_tcam_data_cmp(&pe, 4, swab16(tpid2));
+		match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid1) &&
+			mvpp2_prs_tcam_data_cmp(&pe, 4, tpid2);
 
 		if (!match)
 			continue;
@@ -932,8 +914,8 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto,
 
 	pe.index = tid;
 	/* Clear ri before updating */
-	pe.sram.word[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
-	pe.sram.word[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
+	pe.sram[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
+	pe.sram[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
 	mvpp2_prs_sram_ri_update(&pe, ri, ri_mask);
 
 	mvpp2_prs_sram_ri_update(&pe, ri | MVPP2_PRS_RI_IP_FRAG_TRUE,
@@ -1433,17 +1415,13 @@ static int mvpp2_prs_etype_init(struct mvpp2 *priv)
 
 	pe.index = tid;
 
-	/* Clear tcam data before updating */
-	pe.tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE(MVPP2_ETH_TYPE_LEN)] = 0x0;
-	pe.tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE_EN(MVPP2_ETH_TYPE_LEN)] = 0x0;
-
 	mvpp2_prs_tcam_data_byte_set(&pe, MVPP2_ETH_TYPE_LEN,
 				     MVPP2_PRS_IPV4_HEAD,
 				     MVPP2_PRS_IPV4_HEAD_MASK);
 
 	/* Clear ri before updating */
-	pe.sram.word[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
-	pe.sram.word[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
+	pe.sram[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
+	pe.sram[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
 	mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_L3_IP4_OPT,
 				 MVPP2_PRS_RI_L3_PROTO_MASK);
 
@@ -1644,8 +1622,8 @@ static int mvpp2_prs_pppoe_init(struct mvpp2 *priv)
 				     MVPP2_PRS_IPV4_IHL_MASK);
 
 	/* Clear ri before updating */
-	pe.sram.word[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
-	pe.sram.word[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
+	pe.sram[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
+	pe.sram[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
 	mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_L3_IP4,
 				 MVPP2_PRS_RI_L3_PROTO_MASK);
 
@@ -2428,6 +2406,41 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type)
 	return 0;
 }
 
+int mvpp2_prs_add_flow(struct mvpp2 *priv, int flow, u32 ri, u32 ri_mask)
+{
+	struct mvpp2_prs_entry pe;
+	u8 *ri_byte, *ri_byte_mask;
+	int tid, i;
+
+	memset(&pe, 0, sizeof(pe));
+
+	tid = mvpp2_prs_tcam_first_free(priv,
+					MVPP2_PE_LAST_FREE_TID,
+					MVPP2_PE_FIRST_FREE_TID);
+	if (tid < 0)
+		return tid;
+
+	pe.index = tid;
+
+	ri_byte = (u8 *)&ri;
+	ri_byte_mask = (u8 *)&ri_mask;
+
+	mvpp2_prs_sram_ai_update(&pe, flow, MVPP2_PRS_FLOW_ID_MASK);
+	mvpp2_prs_sram_bits_set(&pe, MVPP2_PRS_SRAM_LU_DONE_BIT, 1);
+
+	for (i = 0; i < 4; i++) {
+		mvpp2_prs_tcam_data_byte_set(&pe, i, ri_byte[i],
+					     ri_byte_mask[i]);
+	}
+
+	mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_FLOWS);
+	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_FLOWS);
+	mvpp2_prs_tcam_port_map_set(&pe, MVPP2_PRS_PORT_MASK);
+	mvpp2_prs_hw_write(priv, &pe);
+
+	return 0;
+}
+
 /* Set prs flow for the port */
 int mvpp2_prs_def_flow(struct mvpp2_port *port)
 {
@@ -2465,3 +2478,19 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port)
 
 	return 0;
 }
+
+int mvpp2_prs_hits(struct mvpp2 *priv, int index)
+{
+	u32 val;
+
+	if (index > MVPP2_PRS_TCAM_SRAM_SIZE)
+		return -EINVAL;
+
+	mvpp2_write(priv, MVPP2_PRS_TCAM_HIT_IDX_REG, index);
+
+	val = mvpp2_read(priv, MVPP2_PRS_TCAM_HIT_CNT_REG);
+
+	val &= MVPP2_PRS_TCAM_HIT_CNT_MASK;
+
+	return val;
+}
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
index 22fbbc4c8b28..e22f6c85d380 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
@@ -1,22 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Header Parser definitions for Marvell PPv2 Network Controller
  *
  * Copyright (C) 2014 Marvell
  *
  * Marcin Wojtas <mw@semihalf.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
+#ifndef _MVPP2_PRS_H_
+#define _MVPP2_PRS_H_
+
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
+#include <linux/platform_device.h>
 
 #include "mvpp2.h"
 
-#ifndef _MVPP2_PRS_H_
-#define _MVPP2_PRS_H_
-
 /* Parser constants */
 #define MVPP2_PRS_TCAM_SRAM_SIZE	256
 #define MVPP2_PRS_TCAM_WORDS		6
@@ -50,17 +48,25 @@
  * The fields are represented by MVPP2_PRS_TCAM_DATA_REG(5)->(0).
  */
 #define MVPP2_PRS_AI_BITS			8
+#define MVPP2_PRS_AI_MASK			0xff
 #define MVPP2_PRS_PORT_MASK			0xff
 #define MVPP2_PRS_LU_MASK			0xf
-#define MVPP2_PRS_TCAM_DATA_BYTE(offs)		\
-				    (((offs) - ((offs) % 2)) * 2 + ((offs) % 2))
-#define MVPP2_PRS_TCAM_DATA_BYTE_EN(offs)	\
-					      (((offs) * 2) - ((offs) % 2)  + 2)
-#define MVPP2_PRS_TCAM_AI_BYTE			16
-#define MVPP2_PRS_TCAM_PORT_BYTE		17
-#define MVPP2_PRS_TCAM_LU_BYTE			20
-#define MVPP2_PRS_TCAM_EN_OFFS(offs)		((offs) + 2)
-#define MVPP2_PRS_TCAM_INV_WORD			5
+
+/* TCAM entries in registers are accessed using 16 data bits + 16 enable bits */
+#define MVPP2_PRS_BYTE_TO_WORD(byte)	((byte) / 2)
+#define MVPP2_PRS_BYTE_IN_WORD(byte)	((byte) % 2)
+
+#define MVPP2_PRS_TCAM_EN(data)		((data) << 16)
+#define MVPP2_PRS_TCAM_AI_WORD		4
+#define MVPP2_PRS_TCAM_AI(ai)		(ai)
+#define MVPP2_PRS_TCAM_AI_EN(ai)	MVPP2_PRS_TCAM_EN(MVPP2_PRS_TCAM_AI(ai))
+#define MVPP2_PRS_TCAM_PORT_WORD	4
+#define MVPP2_PRS_TCAM_PORT(p)		((p) << 8)
+#define MVPP2_PRS_TCAM_PORT_EN(p)	MVPP2_PRS_TCAM_EN(MVPP2_PRS_TCAM_PORT(p))
+#define MVPP2_PRS_TCAM_LU_WORD		5
+#define MVPP2_PRS_TCAM_LU(lu)		(lu)
+#define MVPP2_PRS_TCAM_LU_EN(lu)	MVPP2_PRS_TCAM_EN(MVPP2_PRS_TCAM_LU(lu))
+#define MVPP2_PRS_TCAM_INV_WORD		5
 
 #define MVPP2_PRS_VID_TCAM_BYTE         2
 
@@ -146,6 +152,7 @@
 #define MVPP2_PRS_SRAM_RI_CTRL_BITS		32
 #define MVPP2_PRS_SRAM_SHIFT_OFFS		64
 #define MVPP2_PRS_SRAM_SHIFT_SIGN_BIT		72
+#define MVPP2_PRS_SRAM_SHIFT_MASK		0xff
 #define MVPP2_PRS_SRAM_UDF_OFFS			73
 #define MVPP2_PRS_SRAM_UDF_BITS			8
 #define MVPP2_PRS_SRAM_UDF_MASK			0xff
@@ -214,6 +221,10 @@
 #define MVPP2_PRS_RI_UDF7_IP6_LITE		BIT(29)
 #define MVPP2_PRS_RI_DROP_MASK			0x80000000
 
+#define MVPP2_PRS_IP_MASK			(MVPP2_PRS_RI_L3_PROTO_MASK | \
+						MVPP2_PRS_RI_IP_FRAG_MASK | \
+						MVPP2_PRS_RI_L4_PROTO_MASK)
+
 /* Sram additional info bits assignment */
 #define MVPP2_PRS_IPV4_DIP_AI_BIT		BIT(0)
 #define MVPP2_PRS_IPV6_NO_EXT_AI_BIT		BIT(0)
@@ -255,20 +266,15 @@ enum mvpp2_prs_lookup {
 	MVPP2_PRS_LU_LAST,
 };
 
-union mvpp2_prs_tcam_entry {
-	u32 word[MVPP2_PRS_TCAM_WORDS];
-	u8  byte[MVPP2_PRS_TCAM_WORDS * 4];
-};
-
-union mvpp2_prs_sram_entry {
-	u32 word[MVPP2_PRS_SRAM_WORDS];
-	u8  byte[MVPP2_PRS_SRAM_WORDS * 4];
-};
-
 struct mvpp2_prs_entry {
 	u32 index;
-	union mvpp2_prs_tcam_entry tcam;
-	union mvpp2_prs_sram_entry sram;
+	u32 tcam[MVPP2_PRS_TCAM_WORDS];
+	u32 sram[MVPP2_PRS_SRAM_WORDS];
+};
+
+struct mvpp2_prs_result_info {
+	u32 ri;
+	u32 ri_mask;
 };
 
 struct mvpp2_prs_shadow {
@@ -288,10 +294,21 @@ struct mvpp2_prs_shadow {
 
 int mvpp2_prs_default_init(struct platform_device *pdev, struct mvpp2 *priv);
 
+int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe,
+			   int tid);
+
+unsigned int mvpp2_prs_tcam_port_map_get(struct mvpp2_prs_entry *pe);
+
+void mvpp2_prs_tcam_data_byte_get(struct mvpp2_prs_entry *pe,
+				  unsigned int offs, unsigned char *byte,
+				  unsigned char *enable);
+
 int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add);
 
 int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type);
 
+int mvpp2_prs_add_flow(struct mvpp2 *priv, int flow, u32 ri, u32 ri_mask);
+
 int mvpp2_prs_def_flow(struct mvpp2_port *port);
 
 void mvpp2_prs_vid_enable_filtering(struct mvpp2_port *port);
@@ -311,4 +328,6 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port);
 
 int mvpp2_prs_update_mac_da(struct net_device *dev, const u8 *da);
 
+int mvpp2_prs_hits(struct mvpp2 *priv, int index);
+
 #endif
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index d8ebf0a05e0c..6e6abdc399de 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -605,10 +605,10 @@ static int mtk_init_fq_dma(struct mtk_eth *eth)
 	dma_addr_t dma_addr;
 	int i;
 
-	eth->scratch_ring = dma_alloc_coherent(eth->dev,
-					       cnt * sizeof(struct mtk_tx_dma),
-					       &eth->phy_scratch_ring,
-					       GFP_ATOMIC | __GFP_ZERO);
+	eth->scratch_ring = dma_zalloc_coherent(eth->dev,
+						cnt * sizeof(struct mtk_tx_dma),
+						&eth->phy_scratch_ring,
+						GFP_ATOMIC);
 	if (unlikely(!eth->scratch_ring))
 		return -ENOMEM;
 
@@ -623,7 +623,6 @@ static int mtk_init_fq_dma(struct mtk_eth *eth)
 	if (unlikely(dma_mapping_error(eth->dev, dma_addr)))
 		return -ENOMEM;
 
-	memset(eth->scratch_ring, 0x0, sizeof(struct mtk_tx_dma) * cnt);
 	phy_ring_tail = eth->phy_scratch_ring +
 			(sizeof(struct mtk_tx_dma) * (cnt - 1));
 
@@ -1221,14 +1220,11 @@ static int mtk_tx_alloc(struct mtk_eth *eth)
 	if (!ring->buf)
 		goto no_tx_mem;
 
-	ring->dma = dma_alloc_coherent(eth->dev,
-					  MTK_DMA_SIZE * sz,
-					  &ring->phys,
-					  GFP_ATOMIC | __GFP_ZERO);
+	ring->dma = dma_zalloc_coherent(eth->dev, MTK_DMA_SIZE * sz,
+					&ring->phys, GFP_ATOMIC);
 	if (!ring->dma)
 		goto no_tx_mem;
 
-	memset(ring->dma, 0, MTK_DMA_SIZE * sz);
 	for (i = 0; i < MTK_DMA_SIZE; i++) {
 		int next = (i + 1) % MTK_DMA_SIZE;
 		u32 next_ptr = ring->phys + next * sz;
@@ -1321,10 +1317,9 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 			return -ENOMEM;
 	}
 
-	ring->dma = dma_alloc_coherent(eth->dev,
-				       rx_dma_size * sizeof(*ring->dma),
-				       &ring->phys,
-				       GFP_ATOMIC | __GFP_ZERO);
+	ring->dma = dma_zalloc_coherent(eth->dev,
+					rx_dma_size * sizeof(*ring->dma),
+					&ring->phys, GFP_ATOMIC);
 	if (!ring->dma)
 		return -ENOMEM;
 
@@ -2463,42 +2458,6 @@ free_netdev:
 	return err;
 }
 
-static int mtk_get_chip_id(struct mtk_eth *eth, u32 *chip_id)
-{
-	u32 val[2], id[4];
-
-	regmap_read(eth->ethsys, ETHSYS_CHIPID0_3, &val[0]);
-	regmap_read(eth->ethsys, ETHSYS_CHIPID4_7, &val[1]);
-
-	id[3] = ((val[0] >> 16) & 0xff) - '0';
-	id[2] = ((val[0] >> 24) & 0xff) - '0';
-	id[1] = (val[1] & 0xff) - '0';
-	id[0] = ((val[1] >> 8) & 0xff) - '0';
-
-	*chip_id = (id[3] * 1000) + (id[2] * 100) +
-		   (id[1] * 10) + id[0];
-
-	if (!(*chip_id)) {
-		dev_err(eth->dev, "failed to get chip id\n");
-		return -ENODEV;
-	}
-
-	dev_info(eth->dev, "chip id = %d\n", *chip_id);
-
-	return 0;
-}
-
-static bool mtk_is_hwlro_supported(struct mtk_eth *eth)
-{
-	switch (eth->chip_id) {
-	case MT7622_ETH:
-	case MT7623_ETH:
-		return true;
-	}
-
-	return false;
-}
-
 static int mtk_probe(struct platform_device *pdev)
 {
 	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -2577,11 +2536,7 @@ static int mtk_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	err = mtk_get_chip_id(eth, &eth->chip_id);
-	if (err)
-		return err;
-
-	eth->hwlro = mtk_is_hwlro_supported(eth);
+	eth->hwlro = MTK_HAS_CAPS(eth->soc->caps, MTK_HWLRO);
 
 	for_each_child_of_node(pdev->dev.of_node, mac_np) {
 		if (!of_device_is_compatible(mac_np,
@@ -2670,19 +2625,19 @@ static int mtk_remove(struct platform_device *pdev)
 }
 
 static const struct mtk_soc_data mt2701_data = {
-	.caps = MTK_GMAC1_TRGMII,
+	.caps = MTK_GMAC1_TRGMII | MTK_HWLRO,
 	.required_clks = MT7623_CLKS_BITMAP,
 	.required_pctl = true,
 };
 
 static const struct mtk_soc_data mt7622_data = {
-	.caps = MTK_DUAL_GMAC_SHARED_SGMII | MTK_GMAC1_ESW,
+	.caps = MTK_DUAL_GMAC_SHARED_SGMII | MTK_GMAC1_ESW | MTK_HWLRO,
 	.required_clks = MT7622_CLKS_BITMAP,
 	.required_pctl = false,
 };
 
 static const struct mtk_soc_data mt7623_data = {
-	.caps = MTK_GMAC1_TRGMII,
+	.caps = MTK_GMAC1_TRGMII | MTK_HWLRO,
 	.required_clks = MT7623_CLKS_BITMAP,
 	.required_pctl = true,
 };
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 672b8c353c47..46819297fc3e 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -566,6 +566,7 @@ struct mtk_rx_ring {
 #define MTK_GMAC2_SGMII			(BIT(10) | MTK_SGMII)
 #define MTK_DUAL_GMAC_SHARED_SGMII	(BIT(11) | MTK_GMAC1_SGMII | \
 					 MTK_GMAC2_SGMII)
+#define MTK_HWLRO			BIT(12)
 #define MTK_HAS_CAPS(caps, _x)		(((caps) & (_x)) == (_x))
 
 /* struct mtk_eth_data -	This is the structure holding all differences
@@ -635,7 +636,6 @@ struct mtk_eth {
 	struct regmap			*ethsys;
 	struct regmap			*sgmiisys;
 	struct regmap			*pctl;
-	u32				chip_id;
 	bool				hwlro;
 	refcount_t			dma_refcnt;
 	struct mtk_tx_ring		tx_ring;
diff --git a/drivers/net/ethernet/mellanox/mlx4/Makefile b/drivers/net/ethernet/mellanox/mlx4/Makefile
index 16b10d01fcf4..3f400770fcd8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx4/Makefile
@@ -3,7 +3,7 @@ obj-$(CONFIG_MLX4_CORE)		+= mlx4_core.o
 
 mlx4_core-y :=	alloc.o catas.o cmd.o cq.o eq.o fw.o fw_qos.o icm.o intf.o \
 		main.o mcg.o mr.o pd.o port.o profile.o qp.o reset.o sense.o \
-		srq.o resource_tracker.o
+		srq.o resource_tracker.o crdump.o
 
 obj-$(CONFIG_MLX4_EN)               += mlx4_en.o
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index e2b6b0cac1ac..c81d15bf259c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -178,10 +178,12 @@ void mlx4_enter_error_state(struct mlx4_dev_persistent *persist)
 
 	dev = persist->dev;
 	mlx4_err(dev, "device is going to be reset\n");
-	if (mlx4_is_slave(dev))
+	if (mlx4_is_slave(dev)) {
 		err = mlx4_reset_slave(dev);
-	else
+	} else {
+		mlx4_crdump_collect(dev);
 		err = mlx4_reset_master(dev);
+	}
 
 	if (!err) {
 		mlx4_err(dev, "device was reset successfully\n");
@@ -212,7 +214,7 @@ static void mlx4_handle_error_state(struct mlx4_dev_persistent *persist)
 	mutex_lock(&persist->interface_state_mutex);
 	if (persist->interface_state & MLX4_INTERFACE_STATE_UP &&
 	    !(persist->interface_state & MLX4_INTERFACE_STATE_DELETION)) {
-		err = mlx4_restart_one(persist->pdev);
+		err = mlx4_restart_one(persist->pdev, false, NULL);
 		mlx4_info(persist->dev, "mlx4_restart_one was ended, ret=%d\n",
 			  err);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/crdump.c b/drivers/net/ethernet/mellanox/mlx4/crdump.c
new file mode 100644
index 000000000000..88316c743820
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx4/crdump.c
@@ -0,0 +1,239 @@
+/*
+ * Copyright (c) 2018, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "mlx4.h"
+
+#define BAD_ACCESS			0xBADACCE5
+#define HEALTH_BUFFER_SIZE		0x40
+#define CR_ENABLE_BIT			swab32(BIT(6))
+#define CR_ENABLE_BIT_OFFSET		0xF3F04
+#define MAX_NUM_OF_DUMPS_TO_STORE	(8)
+
+static const char *region_cr_space_str = "cr-space";
+static const char *region_fw_health_str = "fw-health";
+
+/* Set to true in case cr enable bit was set to true before crdump */
+static bool crdump_enbale_bit_set;
+
+static void crdump_enable_crspace_access(struct mlx4_dev *dev,
+					 u8 __iomem *cr_space)
+{
+	/* Get current enable bit value */
+	crdump_enbale_bit_set =
+		readl(cr_space + CR_ENABLE_BIT_OFFSET) & CR_ENABLE_BIT;
+
+	/* Enable FW CR filter (set bit6 to 0) */
+	if (crdump_enbale_bit_set)
+		writel(readl(cr_space + CR_ENABLE_BIT_OFFSET) & ~CR_ENABLE_BIT,
+		       cr_space + CR_ENABLE_BIT_OFFSET);
+
+	/* Enable block volatile crspace accesses */
+	writel(swab32(1), cr_space + dev->caps.health_buffer_addrs +
+	       HEALTH_BUFFER_SIZE);
+}
+
+static void crdump_disable_crspace_access(struct mlx4_dev *dev,
+					  u8 __iomem *cr_space)
+{
+	/* Disable block volatile crspace accesses */
+	writel(0, cr_space + dev->caps.health_buffer_addrs +
+	       HEALTH_BUFFER_SIZE);
+
+	/* Restore FW CR filter value (set bit6 to original value) */
+	if (crdump_enbale_bit_set)
+		writel(readl(cr_space + CR_ENABLE_BIT_OFFSET) | CR_ENABLE_BIT,
+		       cr_space + CR_ENABLE_BIT_OFFSET);
+}
+
+static void mlx4_crdump_collect_crspace(struct mlx4_dev *dev,
+					u8 __iomem *cr_space,
+					u32 id)
+{
+	struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+	struct pci_dev *pdev = dev->persist->pdev;
+	unsigned long cr_res_size;
+	u8 *crspace_data;
+	int offset;
+	int err;
+
+	if (!crdump->region_crspace) {
+		mlx4_err(dev, "crdump: cr-space region is NULL\n");
+		return;
+	}
+
+	/* Try to collect CR space */
+	cr_res_size = pci_resource_len(pdev, 0);
+	crspace_data = kvmalloc(cr_res_size, GFP_KERNEL);
+	if (crspace_data) {
+		for (offset = 0; offset < cr_res_size; offset += 4)
+			*(u32 *)(crspace_data + offset) =
+					readl(cr_space + offset);
+
+		err = devlink_region_snapshot_create(crdump->region_crspace,
+						     cr_res_size, crspace_data,
+						     id, &kvfree);
+		if (err) {
+			kvfree(crspace_data);
+			mlx4_warn(dev, "crdump: devlink create %s snapshot id %d err %d\n",
+				  region_cr_space_str, id, err);
+		} else {
+			mlx4_info(dev, "crdump: added snapshot %d to devlink region %s\n",
+				  id, region_cr_space_str);
+		}
+	} else {
+		mlx4_err(dev, "crdump: Failed to allocate crspace buffer\n");
+	}
+}
+
+static void mlx4_crdump_collect_fw_health(struct mlx4_dev *dev,
+					  u8 __iomem *cr_space,
+					  u32 id)
+{
+	struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+	u8 *health_data;
+	int offset;
+	int err;
+
+	if (!crdump->region_fw_health) {
+		mlx4_err(dev, "crdump: fw-health region is NULL\n");
+		return;
+	}
+
+	/* Try to collect health buffer */
+	health_data = kvmalloc(HEALTH_BUFFER_SIZE, GFP_KERNEL);
+	if (health_data) {
+		u8 __iomem *health_buf_start =
+				cr_space + dev->caps.health_buffer_addrs;
+
+		for (offset = 0; offset < HEALTH_BUFFER_SIZE; offset += 4)
+			*(u32 *)(health_data + offset) =
+					readl(health_buf_start + offset);
+
+		err = devlink_region_snapshot_create(crdump->region_fw_health,
+						     HEALTH_BUFFER_SIZE,
+						     health_data,
+						     id, &kvfree);
+		if (err) {
+			kvfree(health_data);
+			mlx4_warn(dev, "crdump: devlink create %s snapshot id %d err %d\n",
+				  region_fw_health_str, id, err);
+		} else {
+			mlx4_info(dev, "crdump: added snapshot %d to devlink region %s\n",
+				  id, region_fw_health_str);
+		}
+	} else {
+		mlx4_err(dev, "crdump: Failed to allocate health buffer\n");
+	}
+}
+
+int mlx4_crdump_collect(struct mlx4_dev *dev)
+{
+	struct devlink *devlink = priv_to_devlink(mlx4_priv(dev));
+	struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+	struct pci_dev *pdev = dev->persist->pdev;
+	unsigned long cr_res_size;
+	u8 __iomem *cr_space;
+	u32 id;
+
+	if (!dev->caps.health_buffer_addrs) {
+		mlx4_info(dev, "crdump: FW doesn't support health buffer access, skipping\n");
+		return 0;
+	}
+
+	if (!crdump->snapshot_enable) {
+		mlx4_info(dev, "crdump: devlink snapshot disabled, skipping\n");
+		return 0;
+	}
+
+	cr_res_size = pci_resource_len(pdev, 0);
+
+	cr_space = ioremap(pci_resource_start(pdev, 0), cr_res_size);
+	if (!cr_space) {
+		mlx4_err(dev, "crdump: Failed to map pci cr region\n");
+		return -ENODEV;
+	}
+
+	crdump_enable_crspace_access(dev, cr_space);
+
+	/* Get the available snapshot ID for the dumps */
+	id = devlink_region_shapshot_id_get(devlink);
+
+	/* Try to capture dumps */
+	mlx4_crdump_collect_crspace(dev, cr_space, id);
+	mlx4_crdump_collect_fw_health(dev, cr_space, id);
+
+	crdump_disable_crspace_access(dev, cr_space);
+
+	iounmap(cr_space);
+	return 0;
+}
+
+int mlx4_crdump_init(struct mlx4_dev *dev)
+{
+	struct devlink *devlink = priv_to_devlink(mlx4_priv(dev));
+	struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+	struct pci_dev *pdev = dev->persist->pdev;
+
+	crdump->snapshot_enable = false;
+
+	/* Create cr-space region */
+	crdump->region_crspace =
+		devlink_region_create(devlink,
+				      region_cr_space_str,
+				      MAX_NUM_OF_DUMPS_TO_STORE,
+				      pci_resource_len(pdev, 0));
+	if (IS_ERR(crdump->region_crspace))
+		mlx4_warn(dev, "crdump: create devlink region %s err %ld\n",
+			  region_cr_space_str,
+			  PTR_ERR(crdump->region_crspace));
+
+	/* Create fw-health region */
+	crdump->region_fw_health =
+		devlink_region_create(devlink,
+				      region_fw_health_str,
+				      MAX_NUM_OF_DUMPS_TO_STORE,
+				      HEALTH_BUFFER_SIZE);
+	if (IS_ERR(crdump->region_fw_health))
+		mlx4_warn(dev, "crdump: create devlink region %s err %ld\n",
+			  region_fw_health_str,
+			  PTR_ERR(crdump->region_fw_health));
+
+	return 0;
+}
+
+void mlx4_crdump_end(struct mlx4_dev *dev)
+{
+	struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+
+	devlink_region_destroy(crdump->region_fw_health);
+	devlink_region_destroy(crdump->region_crspace);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 65eb06e017e4..6785661d1a72 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2926,7 +2926,6 @@ static int mlx4_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		return mlx4_xdp_set(dev, xdp->prog);
 	case XDP_QUERY_PROG:
 		xdp->prog_id = mlx4_xdp_query(dev);
-		xdp->prog_attached = !!xdp->prog_id;
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 3360f7b9ee73..a1aeeb8094c3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -795,8 +795,10 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 				goto xdp_drop_no_cnt; /* Drop on xmit failure */
 			default:
 				bpf_warn_invalid_xdp_action(act);
+				/* fall through */
 			case XDP_ABORTED:
 				trace_xdp_exception(dev, xdp_prog, act);
+				/* fall through */
 			case XDP_DROP:
 				ring->xdp_drop++;
 xdp_drop_no_cnt:
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 0227786308af..1857ee0f0871 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -688,15 +688,16 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc,
 }
 
 u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
-			 void *accel_priv, select_queue_fallback_t fallback)
+			 struct net_device *sb_dev,
+			 select_queue_fallback_t fallback)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	u16 rings_p_up = priv->num_tx_rings_p_up;
 
 	if (netdev_get_num_tc(dev))
-		return fallback(dev, skb);
+		return fallback(dev, skb, NULL);
 
-	return fallback(dev, skb) % rings_p_up;
+	return fallback(dev, skb, NULL) % rings_p_up;
 }
 
 static void mlx4_bf_copy(void __iomem *dst, const void *src,
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 46dcbfbe4c5e..babcfd9c0571 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -825,7 +825,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_DEV_CAP_QP_RATE_LIMIT_NUM_OFFSET	0xcc
 #define QUERY_DEV_CAP_QP_RATE_LIMIT_MAX_OFFSET	0xd0
 #define QUERY_DEV_CAP_QP_RATE_LIMIT_MIN_OFFSET	0xd2
-
+#define QUERY_DEV_CAP_HEALTH_BUFFER_ADDRESS_OFFSET	0xe4
 
 	dev_cap->flags2 = 0;
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
@@ -1082,6 +1082,9 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		dev_cap->rl_caps.min_unit = size >> 14;
 	}
 
+	MLX4_GET(dev_cap->health_buffer_addrs, outbox,
+		 QUERY_DEV_CAP_HEALTH_BUFFER_ADDRESS_OFFSET);
+
 	MLX4_GET(field32, outbox, QUERY_DEV_CAP_EXT_2_FLAGS_OFFSET);
 	if (field32 & (1 << 16))
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_UPDATE_QP;
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index cd6399c76bfd..650ae08c71de 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -128,6 +128,7 @@ struct mlx4_dev_cap {
 	u32 dmfs_high_rate_qpn_base;
 	u32 dmfs_high_rate_qpn_range;
 	struct mlx4_rate_limit_caps rl_caps;
+	u32 health_buffer_addrs;
 	struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1];
 	bool wol_port[MLX4_MAX_PORTS + 1];
 };
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 872014702fc1..d2d59444f562 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -159,9 +159,10 @@ static bool use_prio;
 module_param_named(use_prio, use_prio, bool, 0444);
 MODULE_PARM_DESC(use_prio, "Enable steering by VLAN priority on ETH ports (deprecated)");
 
-int log_mtts_per_seg = ilog2(MLX4_MTT_ENTRY_PER_SEG);
+int log_mtts_per_seg = ilog2(1);
 module_param_named(log_mtts_per_seg, log_mtts_per_seg, int, 0444);
-MODULE_PARM_DESC(log_mtts_per_seg, "Log2 number of MTT entries per segment (1-7)");
+MODULE_PARM_DESC(log_mtts_per_seg, "Log2 number of MTT entries per segment "
+		 "(0-7) (default: 0)");
 
 static int port_type_array[2] = {MLX4_PORT_TYPE_NONE, MLX4_PORT_TYPE_NONE};
 static int arr_argc = 2;
@@ -177,6 +178,131 @@ struct mlx4_port_config {
 
 static atomic_t pf_loading = ATOMIC_INIT(0);
 
+static int mlx4_devlink_ierr_reset_get(struct devlink *devlink, u32 id,
+				       struct devlink_param_gset_ctx *ctx)
+{
+	ctx->val.vbool = !!mlx4_internal_err_reset;
+	return 0;
+}
+
+static int mlx4_devlink_ierr_reset_set(struct devlink *devlink, u32 id,
+				       struct devlink_param_gset_ctx *ctx)
+{
+	mlx4_internal_err_reset = ctx->val.vbool;
+	return 0;
+}
+
+static int mlx4_devlink_crdump_snapshot_get(struct devlink *devlink, u32 id,
+					    struct devlink_param_gset_ctx *ctx)
+{
+	struct mlx4_priv *priv = devlink_priv(devlink);
+	struct mlx4_dev *dev = &priv->dev;
+
+	ctx->val.vbool = dev->persist->crdump.snapshot_enable;
+	return 0;
+}
+
+static int mlx4_devlink_crdump_snapshot_set(struct devlink *devlink, u32 id,
+					    struct devlink_param_gset_ctx *ctx)
+{
+	struct mlx4_priv *priv = devlink_priv(devlink);
+	struct mlx4_dev *dev = &priv->dev;
+
+	dev->persist->crdump.snapshot_enable = ctx->val.vbool;
+	return 0;
+}
+
+static int
+mlx4_devlink_max_macs_validate(struct devlink *devlink, u32 id,
+			       union devlink_param_value val,
+			       struct netlink_ext_ack *extack)
+{
+	u32 value = val.vu32;
+
+	if (value < 1 || value > 128)
+		return -ERANGE;
+
+	if (!is_power_of_2(value)) {
+		NL_SET_ERR_MSG_MOD(extack, "max_macs supported must be power of 2");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+enum mlx4_devlink_param_id {
+	MLX4_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
+	MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE,
+	MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR,
+};
+
+static const struct devlink_param mlx4_devlink_params[] = {
+	DEVLINK_PARAM_GENERIC(INT_ERR_RESET,
+			      BIT(DEVLINK_PARAM_CMODE_RUNTIME) |
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      mlx4_devlink_ierr_reset_get,
+			      mlx4_devlink_ierr_reset_set, NULL),
+	DEVLINK_PARAM_GENERIC(MAX_MACS,
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, mlx4_devlink_max_macs_validate),
+	DEVLINK_PARAM_GENERIC(REGION_SNAPSHOT,
+			      BIT(DEVLINK_PARAM_CMODE_RUNTIME) |
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      mlx4_devlink_crdump_snapshot_get,
+			      mlx4_devlink_crdump_snapshot_set, NULL),
+	DEVLINK_PARAM_DRIVER(MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE,
+			     "enable_64b_cqe_eqe", DEVLINK_PARAM_TYPE_BOOL,
+			     BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			     NULL, NULL, NULL),
+	DEVLINK_PARAM_DRIVER(MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR,
+			     "enable_4k_uar", DEVLINK_PARAM_TYPE_BOOL,
+			     BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			     NULL, NULL, NULL),
+};
+
+static void mlx4_devlink_set_init_value(struct devlink *devlink, u32 param_id,
+					union devlink_param_value init_val)
+{
+	struct mlx4_priv *priv = devlink_priv(devlink);
+	struct mlx4_dev *dev = &priv->dev;
+	int err;
+
+	err = devlink_param_driverinit_value_set(devlink, param_id, init_val);
+	if (err)
+		mlx4_warn(dev,
+			  "devlink set parameter %u value failed (err = %d)",
+			  param_id, err);
+}
+
+static void mlx4_devlink_set_params_init_values(struct devlink *devlink)
+{
+	union devlink_param_value value;
+
+	value.vbool = !!mlx4_internal_err_reset;
+	mlx4_devlink_set_init_value(devlink,
+				    DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET,
+				    value);
+
+	value.vu32 = 1UL << log_num_mac;
+	mlx4_devlink_set_init_value(devlink,
+				    DEVLINK_PARAM_GENERIC_ID_MAX_MACS, value);
+
+	value.vbool = enable_64b_cqe_eqe;
+	mlx4_devlink_set_init_value(devlink,
+				    MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE,
+				    value);
+
+	value.vbool = enable_4k_uar;
+	mlx4_devlink_set_init_value(devlink,
+				    MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR,
+				    value);
+
+	value.vbool = false;
+	mlx4_devlink_set_init_value(devlink,
+				    DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT,
+				    value);
+}
+
 static inline void mlx4_set_num_reserved_uars(struct mlx4_dev *dev,
 					      struct mlx4_dev_cap *dev_cap)
 {
@@ -428,6 +554,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.max_rss_tbl_sz     = dev_cap->max_rss_tbl_sz;
 	dev->caps.wol_port[1]          = dev_cap->wol_port[1];
 	dev->caps.wol_port[2]          = dev_cap->wol_port[2];
+	dev->caps.health_buffer_addrs  = dev_cap->health_buffer_addrs;
 
 	/* Save uar page shift */
 	if (!mlx4_is_slave(dev)) {
@@ -3711,10 +3838,14 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data,
 		}
 	}
 
-	err = mlx4_catas_init(&priv->dev);
+	err = mlx4_crdump_init(&priv->dev);
 	if (err)
 		goto err_release_regions;
 
+	err = mlx4_catas_init(&priv->dev);
+	if (err)
+		goto err_crdump;
+
 	err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv, 0);
 	if (err)
 		goto err_catas;
@@ -3724,6 +3855,9 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data,
 err_catas:
 	mlx4_catas_end(&priv->dev);
 
+err_crdump:
+	mlx4_crdump_end(&priv->dev);
+
 err_release_regions:
 	pci_release_regions(pdev);
 
@@ -3757,8 +3891,68 @@ static int mlx4_devlink_port_type_set(struct devlink_port *devlink_port,
 	return __set_port_type(info, mlx4_port_type);
 }
 
+static void mlx4_devlink_param_load_driverinit_values(struct devlink *devlink)
+{
+	struct mlx4_priv *priv = devlink_priv(devlink);
+	struct mlx4_dev *dev = &priv->dev;
+	struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+	union devlink_param_value saved_value;
+	int err;
+
+	err = devlink_param_driverinit_value_get(devlink,
+						 DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET,
+						 &saved_value);
+	if (!err && mlx4_internal_err_reset != saved_value.vbool) {
+		mlx4_internal_err_reset = saved_value.vbool;
+		/* Notify on value changed on runtime configuration mode */
+		devlink_param_value_changed(devlink,
+					    DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET);
+	}
+	err = devlink_param_driverinit_value_get(devlink,
+						 DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
+						 &saved_value);
+	if (!err)
+		log_num_mac = order_base_2(saved_value.vu32);
+	err = devlink_param_driverinit_value_get(devlink,
+						 MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE,
+						 &saved_value);
+	if (!err)
+		enable_64b_cqe_eqe = saved_value.vbool;
+	err = devlink_param_driverinit_value_get(devlink,
+						 MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR,
+						 &saved_value);
+	if (!err)
+		enable_4k_uar = saved_value.vbool;
+	err = devlink_param_driverinit_value_get(devlink,
+						 DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT,
+						 &saved_value);
+	if (!err && crdump->snapshot_enable != saved_value.vbool) {
+		crdump->snapshot_enable = saved_value.vbool;
+		devlink_param_value_changed(devlink,
+					    DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT);
+	}
+}
+
+static int mlx4_devlink_reload(struct devlink *devlink,
+			       struct netlink_ext_ack *extack)
+{
+	struct mlx4_priv *priv = devlink_priv(devlink);
+	struct mlx4_dev *dev = &priv->dev;
+	struct mlx4_dev_persistent *persist = dev->persist;
+	int err;
+
+	if (persist->num_vfs)
+		mlx4_warn(persist->dev, "Reload performed on PF, will cause reset on operating Virtual Functions\n");
+	err = mlx4_restart_one(persist->pdev, true, devlink);
+	if (err)
+		mlx4_err(persist->dev, "mlx4_restart_one failed, ret=%d\n", err);
+
+	return err;
+}
+
 static const struct devlink_ops mlx4_devlink_ops = {
 	.port_type_set	= mlx4_devlink_port_type_set,
+	.reload		= mlx4_devlink_reload,
 };
 
 static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
@@ -3792,14 +3986,21 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	ret = devlink_register(devlink, &pdev->dev);
 	if (ret)
 		goto err_persist_free;
-
-	ret =  __mlx4_init_one(pdev, id->driver_data, priv);
+	ret = devlink_params_register(devlink, mlx4_devlink_params,
+				      ARRAY_SIZE(mlx4_devlink_params));
 	if (ret)
 		goto err_devlink_unregister;
+	mlx4_devlink_set_params_init_values(devlink);
+	ret =  __mlx4_init_one(pdev, id->driver_data, priv);
+	if (ret)
+		goto err_params_unregister;
 
 	pci_save_state(pdev);
 	return 0;
 
+err_params_unregister:
+	devlink_params_unregister(devlink, mlx4_devlink_params,
+				  ARRAY_SIZE(mlx4_devlink_params));
 err_devlink_unregister:
 	devlink_unregister(devlink);
 err_persist_free:
@@ -3929,6 +4130,7 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 	else
 		mlx4_info(dev, "%s: interface is down\n", __func__);
 	mlx4_catas_end(dev);
+	mlx4_crdump_end(dev);
 	if (dev->flags & MLX4_FLAG_SRIOV && !active_vfs) {
 		mlx4_warn(dev, "Disabling SR-IOV\n");
 		pci_disable_sriov(pdev);
@@ -3936,6 +4138,8 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 
 	pci_release_regions(pdev);
 	mlx4_pci_disable_device(dev);
+	devlink_params_unregister(devlink, mlx4_devlink_params,
+				  ARRAY_SIZE(mlx4_devlink_params));
 	devlink_unregister(devlink);
 	kfree(dev->persist);
 	devlink_free(devlink);
@@ -3960,7 +4164,7 @@ static int restore_current_port_types(struct mlx4_dev *dev,
 	return err;
 }
 
-int mlx4_restart_one(struct pci_dev *pdev)
+int mlx4_restart_one(struct pci_dev *pdev, bool reload, struct devlink *devlink)
 {
 	struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
 	struct mlx4_dev	 *dev  = persist->dev;
@@ -3973,6 +4177,8 @@ int mlx4_restart_one(struct pci_dev *pdev)
 	memcpy(nvfs, dev->persist->nvfs, sizeof(dev->persist->nvfs));
 
 	mlx4_unload_one(pdev);
+	if (reload)
+		mlx4_devlink_param_load_driverinit_values(devlink);
 	err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv, 1);
 	if (err) {
 		mlx4_err(dev, "%s: ERROR: mlx4_load_one failed, pci_name=%s, err=%d\n",
@@ -4205,7 +4411,7 @@ static int __init mlx4_verify_params(void)
 	if (use_prio != 0)
 		pr_warn("mlx4_core: use_prio - obsolete module param, ignored\n");
 
-	if ((log_mtts_per_seg < 1) || (log_mtts_per_seg > 7)) {
+	if ((log_mtts_per_seg < 0) || (log_mtts_per_seg > 7)) {
 		pr_warn("mlx4_core: bad log_mtts_per_seg: %d\n",
 			log_mtts_per_seg);
 		return -1;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index 4c5306dbcf11..ffed2d4c9403 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -1412,6 +1412,7 @@ int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	case MLX4_STEERING_MODE_A0:
 		if (prot == MLX4_PROT_ETH)
 			return 0;
+		/* fall through */
 
 	case MLX4_STEERING_MODE_B0:
 		if (prot == MLX4_PROT_ETH)
@@ -1441,6 +1442,7 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	case MLX4_STEERING_MODE_A0:
 		if (prot == MLX4_PROT_ETH)
 			return 0;
+		/* fall through */
 
 	case MLX4_STEERING_MODE_B0:
 		if (prot == MLX4_PROT_ETH)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index cb9e923e8399..ebcd2778eeb3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -84,7 +84,6 @@ enum {
 	MLX4_MIN_MGM_LOG_ENTRY_SIZE = 7,
 	MLX4_MAX_MGM_LOG_ENTRY_SIZE = 12,
 	MLX4_MAX_QP_PER_MGM = 4 * ((1 << MLX4_MAX_MGM_LOG_ENTRY_SIZE) / 16 - 2),
-	MLX4_MTT_ENTRY_PER_SEG	= 8,
 };
 
 enum {
@@ -1042,7 +1041,10 @@ void mlx4_start_catas_poll(struct mlx4_dev *dev);
 void mlx4_stop_catas_poll(struct mlx4_dev *dev);
 int mlx4_catas_init(struct mlx4_dev *dev);
 void mlx4_catas_end(struct mlx4_dev *dev);
-int mlx4_restart_one(struct pci_dev *pdev);
+int mlx4_crdump_init(struct mlx4_dev *dev);
+void mlx4_crdump_end(struct mlx4_dev *dev);
+int mlx4_restart_one(struct pci_dev *pdev, bool reload,
+		     struct devlink *devlink);
 int mlx4_register_device(struct mlx4_dev *dev);
 void mlx4_unregister_device(struct mlx4_dev *dev);
 void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type,
@@ -1227,6 +1229,8 @@ void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type);
 void mlx4_enter_error_state(struct mlx4_dev_persistent *persist);
 int mlx4_comm_internal_err(u32 slave_read);
 
+int mlx4_crdump_collect(struct mlx4_dev *dev);
+
 int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port,
 		    enum mlx4_port_type *type);
 void mlx4_do_sense_ports(struct mlx4_dev *dev,
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index ace6545f82e6..c3228b89df46 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -699,7 +699,8 @@ void mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq);
 
 void mlx4_en_tx_irq(struct mlx4_cq *mcq);
 u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
-			 void *accel_priv, select_queue_fallback_t fallback);
+			 struct net_device *sb_dev,
+			 select_queue_fallback_t fallback);
 netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
 netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 			       struct mlx4_en_rx_alloc *frame,
diff --git a/drivers/net/ethernet/mellanox/mlx4/profile.c b/drivers/net/ethernet/mellanox/mlx4/profile.c
index bae8b22edbb7..ba361c5fbda3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/profile.c
+++ b/drivers/net/ethernet/mellanox/mlx4/profile.c
@@ -105,7 +105,8 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 	request->num_mtt =
 		roundup_pow_of_two(max_t(unsigned, request->num_mtt,
 					 min(1UL << (31 - log_mtts_per_seg),
-					     si.totalram >> (log_mtts_per_seg - 1))));
+					     (si.totalram << 1) >> log_mtts_per_seg)));
+
 
 	profile[MLX4_RES_QP].size     = dev_cap->qpc_entry_sz;
 	profile[MLX4_RES_RDMARC].size = dev_cap->rdmarc_entry_sz;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 7a84dd07ced2..37a551436e4a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -7,6 +7,7 @@ config MLX5_CORE
 	depends on MAY_USE_DEVLINK
 	depends on PCI
 	imply PTP_1588_CLOCK
+	imply VXLAN
 	default n
 	---help---
 	  Core driver for low level functionality of the ConnectX-4 and
@@ -35,6 +36,24 @@ config MLX5_CORE_EN
 	---help---
 	  Ethernet support in Mellanox Technologies ConnectX-4 NIC.
 
+config MLX5_EN_ARFS
+	bool "Mellanox MLX5 ethernet accelerated receive flow steering (ARFS) support"
+	depends on MLX5_CORE_EN && RFS_ACCEL
+	default y
+	---help---
+	  Mellanox MLX5 ethernet hardware-accelerated receive flow steering support,
+	  Enables ethernet netdevice arfs support and ntuple filtering.
+
+config MLX5_EN_RXNFC
+	bool "Mellanox MLX5 ethernet rx nfc flow steering support"
+	depends on MLX5_CORE_EN
+	default y
+	---help---
+	  Mellanox MLX5 ethernet rx nfc flow steering support
+	  Enables ethtool receive network flow classification, which allows user defined
+	  flow rules to direct traffic into arbitrary rx queue via ethtool set/get_rxnfc
+	  API.
+
 config MLX5_MPFS
         bool "Mellanox Technologies MLX5 MPFS support"
         depends on MLX5_CORE_EN
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 9efbf193ad5a..d324a3884462 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -1,33 +1,61 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_MLX5_CORE)		+= mlx5_core.o
+#
+# Makefile for Mellanox 5th generation network adapters
+# (ConnectX series) core & netdev driver
+#
+
 subdir-ccflags-y += -I$(src)
 
+obj-$(CONFIG_MLX5_CORE) += mlx5_core.o
+
+#
+# mlx5 core basic
+#
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \
 		mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
-		fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o lib/clock.o \
-		diag/fs_tracepoint.o
-
-mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o accel/tls.o
-
-mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
-		fpga/ipsec.o fpga/tls.o
+		fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o  \
+		diag/fs_tracepoint.o diag/fw_tracer.o
 
+#
+# Netdev basic
+#
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
-		en_tx.o en_rx.o en_dim.o en_txrx.o en_stats.o vxlan.o \
-		en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o
-
-mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
-
-mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o en_rep.o en_tc.o
+		en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
+		en_selftest.o en/port.o
+
+#
+# Netdev extra
+#
+mlx5_core-$(CONFIG_MLX5_EN_ARFS)     += en_arfs.o
+mlx5_core-$(CONFIG_MLX5_EN_RXNFC)    += en_fs_ethtool.o
+mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o
+
+#
+# Core extra
+#
+mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o
+mlx5_core-$(CONFIG_MLX5_MPFS)      += lib/mpfs.o
+mlx5_core-$(CONFIG_VXLAN)          += lib/vxlan.o
+mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
+
+#
+# Ipoib netdev
+#
+mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib_vlan.o
 
-mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) +=  en_dcbnl.o en/port_buffer.o
+#
+# Accelerations & FPGA
+#
+mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o accel/tls.o
 
-mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib_vlan.o
+mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
+				 fpga/ipsec.o fpga/tls.o
 
 mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \
-		en_accel/ipsec_stats.o
+				     en_accel/ipsec_stats.o
 
-mlx5_core-$(CONFIG_MLX5_EN_TLS) +=  en_accel/tls.o en_accel/tls_rxtx.o en_accel/tls_stats.o
+mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/tls.o en_accel/tls_rxtx.o en_accel/tls_stats.o
 
 CFLAGS_tracepoint.o := -I$(src)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/accel.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/accel.h
new file mode 100644
index 000000000000..c13260467750
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/accel.h
@@ -0,0 +1,37 @@
+#ifndef __MLX5E_ACCEL_H__
+#define __MLX5E_ACCEL_H__
+
+#ifdef CONFIG_MLX5_ACCEL
+
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include "en.h"
+
+static inline bool is_metadata_hdr_valid(struct sk_buff *skb)
+{
+	__be16 *ethtype;
+
+	if (unlikely(skb->len < ETH_HLEN + MLX5E_METADATA_ETHER_LEN))
+		return false;
+	ethtype = (__be16 *)(skb->data + ETH_ALEN * 2);
+	if (*ethtype != cpu_to_be16(MLX5E_METADATA_ETHER_TYPE))
+		return false;
+	return true;
+}
+
+static inline void remove_metadata_hdr(struct sk_buff *skb)
+{
+	struct ethhdr *old_eth;
+	struct ethhdr *new_eth;
+
+	/* Remove the metadata from the buffer */
+	old_eth = (struct ethhdr *)skb->data;
+	new_eth = (struct ethhdr *)(skb->data + MLX5E_METADATA_ETHER_LEN);
+	memmove(new_eth, old_eth, 2 * ETH_ALEN);
+	/* Ethertype is already in its new place */
+	skb_pull_inline(skb, MLX5E_METADATA_ETHER_LEN);
+}
+
+#endif /* CONFIG_MLX5_ACCEL */
+
+#endif /* __MLX5E_EN_ACCEL_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c
index 77ac19f38cbe..da7bd26368f9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c
@@ -37,17 +37,26 @@
 #include "mlx5_core.h"
 #include "fpga/tls.h"
 
-int mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
-			       struct tls_crypto_info *crypto_info,
-			       u32 start_offload_tcp_sn, u32 *p_swid)
+int mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+			    struct tls_crypto_info *crypto_info,
+			    u32 start_offload_tcp_sn, u32 *p_swid,
+			    bool direction_sx)
 {
-	return mlx5_fpga_tls_add_tx_flow(mdev, flow, crypto_info,
-					 start_offload_tcp_sn, p_swid);
+	return mlx5_fpga_tls_add_flow(mdev, flow, crypto_info,
+				      start_offload_tcp_sn, p_swid,
+				      direction_sx);
 }
 
-void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid)
+void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+			     bool direction_sx)
 {
-	mlx5_fpga_tls_del_tx_flow(mdev, swid, GFP_KERNEL);
+	mlx5_fpga_tls_del_flow(mdev, swid, GFP_KERNEL, direction_sx);
+}
+
+int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
+			     u64 rcd_sn)
+{
+	return mlx5_fpga_tls_resync_rx(mdev, handle, seq, rcd_sn);
 }
 
 bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
index 6f9c9f446ecc..def4093ebfae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
@@ -60,10 +60,14 @@ struct mlx5_ifc_tls_flow_bits {
 	u8         reserved_at_2[0x1e];
 };
 
-int mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
-			       struct tls_crypto_info *crypto_info,
-			       u32 start_offload_tcp_sn, u32 *p_swid);
-void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid);
+int mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+			    struct tls_crypto_info *crypto_info,
+			    u32 start_offload_tcp_sn, u32 *p_swid,
+			    bool direction_sx);
+void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+			     bool direction_sx);
+int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
+			     u64 rcd_sn);
 bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev);
 u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev);
 int mlx5_accel_tls_init(struct mlx5_core_dev *mdev);
@@ -72,10 +76,14 @@ void mlx5_accel_tls_cleanup(struct mlx5_core_dev *mdev);
 #else
 
 static inline int
-mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
-			   struct tls_crypto_info *crypto_info,
-			   u32 start_offload_tcp_sn, u32 *p_swid) { return 0; }
-static inline void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid) { }
+mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+			struct tls_crypto_info *crypto_info,
+			u32 start_offload_tcp_sn, u32 *p_swid,
+			bool direction_sx) { return -ENOTSUPP; }
+static inline void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+					   bool direction_sx) { }
+static inline int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle,
+					   u32 seq, u64 rcd_sn) { return 0; }
 static inline bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev) { return false; }
 static inline u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev) { return 0; }
 static inline int mlx5_accel_tls_init(struct mlx5_core_dev *mdev) { return 0; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 9364015c818b..3ce14d42ddc8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -211,7 +211,7 @@ static void poll_timeout(struct mlx5_cmd_work_ent *ent)
 			ent->ret = 0;
 			return;
 		}
-		usleep_range(5000, 10000);
+		cond_resched();
 	} while (time_before(jiffies, poll_end));
 
 	ent->ret = -ETIMEDOUT;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
new file mode 100644
index 000000000000..d4ec93bde4de
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -0,0 +1,947 @@
+/*
+ * Copyright (c) 2018, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#define CREATE_TRACE_POINTS
+#include "fw_tracer.h"
+#include "fw_tracer_tracepoint.h"
+
+static int mlx5_query_mtrc_caps(struct mlx5_fw_tracer *tracer)
+{
+	u32 *string_db_base_address_out = tracer->str_db.base_address_out;
+	u32 *string_db_size_out = tracer->str_db.size_out;
+	struct mlx5_core_dev *dev = tracer->dev;
+	u32 out[MLX5_ST_SZ_DW(mtrc_cap)] = {0};
+	u32 in[MLX5_ST_SZ_DW(mtrc_cap)] = {0};
+	void *mtrc_cap_sp;
+	int err, i;
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out),
+				   MLX5_REG_MTRC_CAP, 0, 0);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Error reading tracer caps %d\n",
+			       err);
+		return err;
+	}
+
+	if (!MLX5_GET(mtrc_cap, out, trace_to_memory)) {
+		mlx5_core_dbg(dev, "FWTracer: Device does not support logging traces to memory\n");
+		return -ENOTSUPP;
+	}
+
+	tracer->trc_ver = MLX5_GET(mtrc_cap, out, trc_ver);
+	tracer->str_db.first_string_trace =
+			MLX5_GET(mtrc_cap, out, first_string_trace);
+	tracer->str_db.num_string_trace =
+			MLX5_GET(mtrc_cap, out, num_string_trace);
+	tracer->str_db.num_string_db = MLX5_GET(mtrc_cap, out, num_string_db);
+	tracer->owner = !!MLX5_GET(mtrc_cap, out, trace_owner);
+
+	for (i = 0; i < tracer->str_db.num_string_db; i++) {
+		mtrc_cap_sp = MLX5_ADDR_OF(mtrc_cap, out, string_db_param[i]);
+		string_db_base_address_out[i] = MLX5_GET(mtrc_string_db_param,
+							 mtrc_cap_sp,
+							 string_db_base_address);
+		string_db_size_out[i] = MLX5_GET(mtrc_string_db_param,
+						 mtrc_cap_sp, string_db_size);
+	}
+
+	return err;
+}
+
+static int mlx5_set_mtrc_caps_trace_owner(struct mlx5_fw_tracer *tracer,
+					  u32 *out, u32 out_size,
+					  u8 trace_owner)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	u32 in[MLX5_ST_SZ_DW(mtrc_cap)] = {0};
+
+	MLX5_SET(mtrc_cap, in, trace_owner, trace_owner);
+
+	return mlx5_core_access_reg(dev, in, sizeof(in), out, out_size,
+				    MLX5_REG_MTRC_CAP, 0, 1);
+}
+
+static int mlx5_fw_tracer_ownership_acquire(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	u32 out[MLX5_ST_SZ_DW(mtrc_cap)] = {0};
+	int err;
+
+	err = mlx5_set_mtrc_caps_trace_owner(tracer, out, sizeof(out),
+					     MLX5_FW_TRACER_ACQUIRE_OWNERSHIP);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Acquire tracer ownership failed %d\n",
+			       err);
+		return err;
+	}
+
+	tracer->owner = !!MLX5_GET(mtrc_cap, out, trace_owner);
+
+	if (!tracer->owner)
+		return -EBUSY;
+
+	return 0;
+}
+
+static void mlx5_fw_tracer_ownership_release(struct mlx5_fw_tracer *tracer)
+{
+	u32 out[MLX5_ST_SZ_DW(mtrc_cap)] = {0};
+
+	mlx5_set_mtrc_caps_trace_owner(tracer, out, sizeof(out),
+				       MLX5_FW_TRACER_RELEASE_OWNERSHIP);
+	tracer->owner = false;
+}
+
+static int mlx5_fw_tracer_create_log_buf(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	struct device *ddev = &dev->pdev->dev;
+	dma_addr_t dma;
+	void *buff;
+	gfp_t gfp;
+	int err;
+
+	tracer->buff.size = TRACE_BUFFER_SIZE_BYTE;
+
+	gfp = GFP_KERNEL | __GFP_ZERO;
+	buff = (void *)__get_free_pages(gfp,
+					get_order(tracer->buff.size));
+	if (!buff) {
+		err = -ENOMEM;
+		mlx5_core_warn(dev, "FWTracer: Failed to allocate pages, %d\n", err);
+		return err;
+	}
+	tracer->buff.log_buf = buff;
+
+	dma = dma_map_single(ddev, buff, tracer->buff.size, DMA_FROM_DEVICE);
+	if (dma_mapping_error(ddev, dma)) {
+		mlx5_core_warn(dev, "FWTracer: Unable to map DMA: %d\n",
+			       dma_mapping_error(ddev, dma));
+		err = -ENOMEM;
+		goto free_pages;
+	}
+	tracer->buff.dma = dma;
+
+	return 0;
+
+free_pages:
+	free_pages((unsigned long)tracer->buff.log_buf, get_order(tracer->buff.size));
+
+	return err;
+}
+
+static void mlx5_fw_tracer_destroy_log_buf(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	struct device *ddev = &dev->pdev->dev;
+
+	if (!tracer->buff.log_buf)
+		return;
+
+	dma_unmap_single(ddev, tracer->buff.dma, tracer->buff.size, DMA_FROM_DEVICE);
+	free_pages((unsigned long)tracer->buff.log_buf, get_order(tracer->buff.size));
+}
+
+static int mlx5_fw_tracer_create_mkey(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	int err, inlen, i;
+	__be64 *mtt;
+	void *mkc;
+	u32 *in;
+
+	inlen = MLX5_ST_SZ_BYTES(create_mkey_in) +
+			sizeof(*mtt) * round_up(TRACER_BUFFER_PAGE_NUM, 2);
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(create_mkey_in, in, translations_octword_actual_size,
+		 DIV_ROUND_UP(TRACER_BUFFER_PAGE_NUM, 2));
+	mtt = (u64 *)MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt);
+	for (i = 0 ; i < TRACER_BUFFER_PAGE_NUM ; i++)
+		mtt[i] = cpu_to_be64(tracer->buff.dma + i * PAGE_SIZE);
+
+	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
+	MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_MTT);
+	MLX5_SET(mkc, mkc, lr, 1);
+	MLX5_SET(mkc, mkc, lw, 1);
+	MLX5_SET(mkc, mkc, pd, tracer->buff.pdn);
+	MLX5_SET(mkc, mkc, bsf_octword_size, 0);
+	MLX5_SET(mkc, mkc, qpn, 0xffffff);
+	MLX5_SET(mkc, mkc, log_page_size, PAGE_SHIFT);
+	MLX5_SET(mkc, mkc, translations_octword_size,
+		 DIV_ROUND_UP(TRACER_BUFFER_PAGE_NUM, 2));
+	MLX5_SET64(mkc, mkc, start_addr, tracer->buff.dma);
+	MLX5_SET64(mkc, mkc, len, tracer->buff.size);
+	err = mlx5_core_create_mkey(dev, &tracer->buff.mkey, in, inlen);
+	if (err)
+		mlx5_core_warn(dev, "FWTracer: Failed to create mkey, %d\n", err);
+
+	kvfree(in);
+
+	return err;
+}
+
+static void mlx5_fw_tracer_free_strings_db(struct mlx5_fw_tracer *tracer)
+{
+	u32 num_string_db = tracer->str_db.num_string_db;
+	int i;
+
+	for (i = 0; i < num_string_db; i++) {
+		kfree(tracer->str_db.buffer[i]);
+		tracer->str_db.buffer[i] = NULL;
+	}
+}
+
+static int mlx5_fw_tracer_allocate_strings_db(struct mlx5_fw_tracer *tracer)
+{
+	u32 *string_db_size_out = tracer->str_db.size_out;
+	u32 num_string_db = tracer->str_db.num_string_db;
+	int i;
+
+	for (i = 0; i < num_string_db; i++) {
+		tracer->str_db.buffer[i] = kzalloc(string_db_size_out[i], GFP_KERNEL);
+		if (!tracer->str_db.buffer[i])
+			goto free_strings_db;
+	}
+
+	return 0;
+
+free_strings_db:
+	mlx5_fw_tracer_free_strings_db(tracer);
+	return -ENOMEM;
+}
+
+static void mlx5_tracer_read_strings_db(struct work_struct *work)
+{
+	struct mlx5_fw_tracer *tracer = container_of(work, struct mlx5_fw_tracer,
+						     read_fw_strings_work);
+	u32 num_of_reads, num_string_db = tracer->str_db.num_string_db;
+	struct mlx5_core_dev *dev = tracer->dev;
+	u32 in[MLX5_ST_SZ_DW(mtrc_cap)] = {0};
+	u32 leftovers, offset;
+	int err = 0, i, j;
+	u32 *out, outlen;
+	void *out_value;
+
+	outlen = MLX5_ST_SZ_BYTES(mtrc_stdb) + STRINGS_DB_READ_SIZE_BYTES;
+	out = kzalloc(outlen, GFP_KERNEL);
+	if (!out) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < num_string_db; i++) {
+		offset = 0;
+		MLX5_SET(mtrc_stdb, in, string_db_index, i);
+		num_of_reads = tracer->str_db.size_out[i] /
+				STRINGS_DB_READ_SIZE_BYTES;
+		leftovers = (tracer->str_db.size_out[i] %
+				STRINGS_DB_READ_SIZE_BYTES) /
+					STRINGS_DB_LEFTOVER_SIZE_BYTES;
+
+		MLX5_SET(mtrc_stdb, in, read_size, STRINGS_DB_READ_SIZE_BYTES);
+		for (j = 0; j < num_of_reads; j++) {
+			MLX5_SET(mtrc_stdb, in, start_offset, offset);
+
+			err = mlx5_core_access_reg(dev, in, sizeof(in), out,
+						   outlen, MLX5_REG_MTRC_STDB,
+						   0, 1);
+			if (err) {
+				mlx5_core_dbg(dev, "FWTracer: Failed to read strings DB %d\n",
+					      err);
+				goto out_free;
+			}
+
+			out_value = MLX5_ADDR_OF(mtrc_stdb, out, string_db_data);
+			memcpy(tracer->str_db.buffer[i] + offset, out_value,
+			       STRINGS_DB_READ_SIZE_BYTES);
+			offset += STRINGS_DB_READ_SIZE_BYTES;
+		}
+
+		/* Strings database is aligned to 64, need to read leftovers*/
+		MLX5_SET(mtrc_stdb, in, read_size,
+			 STRINGS_DB_LEFTOVER_SIZE_BYTES);
+		for (j = 0; j < leftovers; j++) {
+			MLX5_SET(mtrc_stdb, in, start_offset, offset);
+
+			err = mlx5_core_access_reg(dev, in, sizeof(in), out,
+						   outlen, MLX5_REG_MTRC_STDB,
+						   0, 1);
+			if (err) {
+				mlx5_core_dbg(dev, "FWTracer: Failed to read strings DB %d\n",
+					      err);
+				goto out_free;
+			}
+
+			out_value = MLX5_ADDR_OF(mtrc_stdb, out, string_db_data);
+			memcpy(tracer->str_db.buffer[i] + offset, out_value,
+			       STRINGS_DB_LEFTOVER_SIZE_BYTES);
+			offset += STRINGS_DB_LEFTOVER_SIZE_BYTES;
+		}
+	}
+
+	tracer->str_db.loaded = true;
+
+out_free:
+	kfree(out);
+out:
+	return;
+}
+
+static void mlx5_fw_tracer_arm(struct mlx5_core_dev *dev)
+{
+	u32 out[MLX5_ST_SZ_DW(mtrc_ctrl)] = {0};
+	u32 in[MLX5_ST_SZ_DW(mtrc_ctrl)] = {0};
+	int err;
+
+	MLX5_SET(mtrc_ctrl, in, arm_event, 1);
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out),
+				   MLX5_REG_MTRC_CTRL, 0, 1);
+	if (err)
+		mlx5_core_warn(dev, "FWTracer: Failed to arm tracer event %d\n", err);
+}
+
+static const char *VAL_PARM		= "%llx";
+static const char *REPLACE_64_VAL_PARM	= "%x%x";
+static const char *PARAM_CHAR		= "%";
+
+static int mlx5_tracer_message_hash(u32 message_id)
+{
+	return jhash_1word(message_id, 0) & (MESSAGE_HASH_SIZE - 1);
+}
+
+static struct tracer_string_format *mlx5_tracer_message_insert(struct mlx5_fw_tracer *tracer,
+							       struct tracer_event *tracer_event)
+{
+	struct hlist_head *head =
+		&tracer->hash[mlx5_tracer_message_hash(tracer_event->string_event.tmsn)];
+	struct tracer_string_format *cur_string;
+
+	cur_string = kzalloc(sizeof(*cur_string), GFP_KERNEL);
+	if (!cur_string)
+		return NULL;
+
+	hlist_add_head(&cur_string->hlist, head);
+
+	return cur_string;
+}
+
+static struct tracer_string_format *mlx5_tracer_get_string(struct mlx5_fw_tracer *tracer,
+							   struct tracer_event *tracer_event)
+{
+	struct tracer_string_format *cur_string;
+	u32 str_ptr, offset;
+	int i;
+
+	str_ptr = tracer_event->string_event.string_param;
+
+	for (i = 0; i < tracer->str_db.num_string_db; i++) {
+		if (str_ptr > tracer->str_db.base_address_out[i] &&
+		    str_ptr < tracer->str_db.base_address_out[i] +
+		    tracer->str_db.size_out[i]) {
+			offset = str_ptr - tracer->str_db.base_address_out[i];
+			/* add it to the hash */
+			cur_string = mlx5_tracer_message_insert(tracer, tracer_event);
+			if (!cur_string)
+				return NULL;
+			cur_string->string = (char *)(tracer->str_db.buffer[i] +
+							offset);
+			return cur_string;
+		}
+	}
+
+	return NULL;
+}
+
+static void mlx5_tracer_clean_message(struct tracer_string_format *str_frmt)
+{
+	hlist_del(&str_frmt->hlist);
+	kfree(str_frmt);
+}
+
+static int mlx5_tracer_get_num_of_params(char *str)
+{
+	char *substr, *pstr = str;
+	int num_of_params = 0;
+
+	/* replace %llx with %x%x */
+	substr = strstr(pstr, VAL_PARM);
+	while (substr) {
+		memcpy(substr, REPLACE_64_VAL_PARM, 4);
+		pstr = substr;
+		substr = strstr(pstr, VAL_PARM);
+	}
+
+	/* count all the % characters */
+	substr = strstr(str, PARAM_CHAR);
+	while (substr) {
+		num_of_params += 1;
+		str = substr + 1;
+		substr = strstr(str, PARAM_CHAR);
+	}
+
+	return num_of_params;
+}
+
+static struct tracer_string_format *mlx5_tracer_message_find(struct hlist_head *head,
+							     u8 event_id, u32 tmsn)
+{
+	struct tracer_string_format *message;
+
+	hlist_for_each_entry(message, head, hlist)
+		if (message->event_id == event_id && message->tmsn == tmsn)
+			return message;
+
+	return NULL;
+}
+
+static struct tracer_string_format *mlx5_tracer_message_get(struct mlx5_fw_tracer *tracer,
+							    struct tracer_event *tracer_event)
+{
+	struct hlist_head *head =
+		&tracer->hash[mlx5_tracer_message_hash(tracer_event->string_event.tmsn)];
+
+	return mlx5_tracer_message_find(head, tracer_event->event_id, tracer_event->string_event.tmsn);
+}
+
+static void poll_trace(struct mlx5_fw_tracer *tracer,
+		       struct tracer_event *tracer_event, u64 *trace)
+{
+	u32 timestamp_low, timestamp_mid, timestamp_high, urts;
+
+	tracer_event->event_id = MLX5_GET(tracer_event, trace, event_id);
+	tracer_event->lost_event = MLX5_GET(tracer_event, trace, lost);
+
+	switch (tracer_event->event_id) {
+	case TRACER_EVENT_TYPE_TIMESTAMP:
+		tracer_event->type = TRACER_EVENT_TYPE_TIMESTAMP;
+		urts = MLX5_GET(tracer_timestamp_event, trace, urts);
+		if (tracer->trc_ver == 0)
+			tracer_event->timestamp_event.unreliable = !!(urts >> 2);
+		else
+			tracer_event->timestamp_event.unreliable = !!(urts & 1);
+
+		timestamp_low = MLX5_GET(tracer_timestamp_event,
+					 trace, timestamp7_0);
+		timestamp_mid = MLX5_GET(tracer_timestamp_event,
+					 trace, timestamp39_8);
+		timestamp_high = MLX5_GET(tracer_timestamp_event,
+					  trace, timestamp52_40);
+
+		tracer_event->timestamp_event.timestamp =
+				((u64)timestamp_high << 40) |
+				((u64)timestamp_mid << 8) |
+				(u64)timestamp_low;
+		break;
+	default:
+		if (tracer_event->event_id >= tracer->str_db.first_string_trace ||
+		    tracer_event->event_id <= tracer->str_db.first_string_trace +
+					      tracer->str_db.num_string_trace) {
+			tracer_event->type = TRACER_EVENT_TYPE_STRING;
+			tracer_event->string_event.timestamp =
+				MLX5_GET(tracer_string_event, trace, timestamp);
+			tracer_event->string_event.string_param =
+				MLX5_GET(tracer_string_event, trace, string_param);
+			tracer_event->string_event.tmsn =
+				MLX5_GET(tracer_string_event, trace, tmsn);
+			tracer_event->string_event.tdsn =
+				MLX5_GET(tracer_string_event, trace, tdsn);
+		} else {
+			tracer_event->type = TRACER_EVENT_TYPE_UNRECOGNIZED;
+		}
+		break;
+	}
+}
+
+static u64 get_block_timestamp(struct mlx5_fw_tracer *tracer, u64 *ts_event)
+{
+	struct tracer_event tracer_event;
+	u8 event_id;
+
+	event_id = MLX5_GET(tracer_event, ts_event, event_id);
+
+	if (event_id == TRACER_EVENT_TYPE_TIMESTAMP)
+		poll_trace(tracer, &tracer_event, ts_event);
+	else
+		tracer_event.timestamp_event.timestamp = 0;
+
+	return tracer_event.timestamp_event.timestamp;
+}
+
+static void mlx5_fw_tracer_clean_print_hash(struct mlx5_fw_tracer *tracer)
+{
+	struct tracer_string_format *str_frmt;
+	struct hlist_node *n;
+	int i;
+
+	for (i = 0; i < MESSAGE_HASH_SIZE; i++) {
+		hlist_for_each_entry_safe(str_frmt, n, &tracer->hash[i], hlist)
+			mlx5_tracer_clean_message(str_frmt);
+	}
+}
+
+static void mlx5_fw_tracer_clean_ready_list(struct mlx5_fw_tracer *tracer)
+{
+	struct tracer_string_format *str_frmt, *tmp_str;
+
+	list_for_each_entry_safe(str_frmt, tmp_str, &tracer->ready_strings_list,
+				 list)
+		list_del(&str_frmt->list);
+}
+
+static void mlx5_tracer_print_trace(struct tracer_string_format *str_frmt,
+				    struct mlx5_core_dev *dev,
+				    u64 trace_timestamp)
+{
+	char	tmp[512];
+
+	snprintf(tmp, sizeof(tmp), str_frmt->string,
+		 str_frmt->params[0],
+		 str_frmt->params[1],
+		 str_frmt->params[2],
+		 str_frmt->params[3],
+		 str_frmt->params[4],
+		 str_frmt->params[5],
+		 str_frmt->params[6]);
+
+	trace_mlx5_fw(dev->tracer, trace_timestamp, str_frmt->lost,
+		      str_frmt->event_id, tmp);
+
+	/* remove it from hash */
+	mlx5_tracer_clean_message(str_frmt);
+}
+
+static int mlx5_tracer_handle_string_trace(struct mlx5_fw_tracer *tracer,
+					   struct tracer_event *tracer_event)
+{
+	struct tracer_string_format *cur_string;
+
+	if (tracer_event->string_event.tdsn == 0) {
+		cur_string = mlx5_tracer_get_string(tracer, tracer_event);
+		if (!cur_string)
+			return -1;
+
+		cur_string->num_of_params = mlx5_tracer_get_num_of_params(cur_string->string);
+		cur_string->last_param_num = 0;
+		cur_string->event_id = tracer_event->event_id;
+		cur_string->tmsn = tracer_event->string_event.tmsn;
+		cur_string->timestamp = tracer_event->string_event.timestamp;
+		cur_string->lost = tracer_event->lost_event;
+		if (cur_string->num_of_params == 0) /* trace with no params */
+			list_add_tail(&cur_string->list, &tracer->ready_strings_list);
+	} else {
+		cur_string = mlx5_tracer_message_get(tracer, tracer_event);
+		if (!cur_string) {
+			pr_debug("%s Got string event for unknown string tdsm: %d\n",
+				 __func__, tracer_event->string_event.tmsn);
+			return -1;
+		}
+		cur_string->last_param_num += 1;
+		if (cur_string->last_param_num > TRACER_MAX_PARAMS) {
+			pr_debug("%s Number of params exceeds the max (%d)\n",
+				 __func__, TRACER_MAX_PARAMS);
+			list_add_tail(&cur_string->list, &tracer->ready_strings_list);
+			return 0;
+		}
+		/* keep the new parameter */
+		cur_string->params[cur_string->last_param_num - 1] =
+			tracer_event->string_event.string_param;
+		if (cur_string->last_param_num == cur_string->num_of_params)
+			list_add_tail(&cur_string->list, &tracer->ready_strings_list);
+	}
+
+	return 0;
+}
+
+static void mlx5_tracer_handle_timestamp_trace(struct mlx5_fw_tracer *tracer,
+					       struct tracer_event *tracer_event)
+{
+	struct tracer_timestamp_event timestamp_event =
+						tracer_event->timestamp_event;
+	struct tracer_string_format *str_frmt, *tmp_str;
+	struct mlx5_core_dev *dev = tracer->dev;
+	u64 trace_timestamp;
+
+	list_for_each_entry_safe(str_frmt, tmp_str, &tracer->ready_strings_list, list) {
+		list_del(&str_frmt->list);
+		if (str_frmt->timestamp < (timestamp_event.timestamp & MASK_6_0))
+			trace_timestamp = (timestamp_event.timestamp & MASK_52_7) |
+					  (str_frmt->timestamp & MASK_6_0);
+		else
+			trace_timestamp = ((timestamp_event.timestamp & MASK_52_7) - 1) |
+					  (str_frmt->timestamp & MASK_6_0);
+
+		mlx5_tracer_print_trace(str_frmt, dev, trace_timestamp);
+	}
+}
+
+static int mlx5_tracer_handle_trace(struct mlx5_fw_tracer *tracer,
+				    struct tracer_event *tracer_event)
+{
+	if (tracer_event->type == TRACER_EVENT_TYPE_STRING) {
+		mlx5_tracer_handle_string_trace(tracer, tracer_event);
+	} else if (tracer_event->type == TRACER_EVENT_TYPE_TIMESTAMP) {
+		if (!tracer_event->timestamp_event.unreliable)
+			mlx5_tracer_handle_timestamp_trace(tracer, tracer_event);
+	} else {
+		pr_debug("%s Got unrecognised type %d for parsing, exiting..\n",
+			 __func__, tracer_event->type);
+	}
+	return 0;
+}
+
+static void mlx5_fw_tracer_handle_traces(struct work_struct *work)
+{
+	struct mlx5_fw_tracer *tracer =
+			container_of(work, struct mlx5_fw_tracer, handle_traces_work);
+	u64 block_timestamp, last_block_timestamp, tmp_trace_block[TRACES_PER_BLOCK];
+	u32 block_count, start_offset, prev_start_offset, prev_consumer_index;
+	u32 trace_event_size = MLX5_ST_SZ_BYTES(tracer_event);
+	struct mlx5_core_dev *dev = tracer->dev;
+	struct tracer_event tracer_event;
+	int i;
+
+	mlx5_core_dbg(dev, "FWTracer: Handle Trace event, owner=(%d)\n", tracer->owner);
+	if (!tracer->owner)
+		return;
+
+	block_count = tracer->buff.size / TRACER_BLOCK_SIZE_BYTE;
+	start_offset = tracer->buff.consumer_index * TRACER_BLOCK_SIZE_BYTE;
+
+	/* Copy the block to local buffer to avoid HW override while being processed*/
+	memcpy(tmp_trace_block, tracer->buff.log_buf + start_offset,
+	       TRACER_BLOCK_SIZE_BYTE);
+
+	block_timestamp =
+		get_block_timestamp(tracer, &tmp_trace_block[TRACES_PER_BLOCK - 1]);
+
+	while (block_timestamp > tracer->last_timestamp) {
+		/* Check block override if its not the first block */
+		if (!tracer->last_timestamp) {
+			u64 *ts_event;
+			/* To avoid block override be the HW in case of buffer
+			 * wraparound, the time stamp of the previous block
+			 * should be compared to the last timestamp handled
+			 * by the driver.
+			 */
+			prev_consumer_index =
+				(tracer->buff.consumer_index - 1) & (block_count - 1);
+			prev_start_offset = prev_consumer_index * TRACER_BLOCK_SIZE_BYTE;
+
+			ts_event = tracer->buff.log_buf + prev_start_offset +
+				   (TRACES_PER_BLOCK - 1) * trace_event_size;
+			last_block_timestamp = get_block_timestamp(tracer, ts_event);
+			/* If previous timestamp different from last stored
+			 * timestamp then there is a good chance that the
+			 * current buffer is overwritten and therefore should
+			 * not be parsed.
+			 */
+			if (tracer->last_timestamp != last_block_timestamp) {
+				mlx5_core_warn(dev, "FWTracer: Events were lost\n");
+				tracer->last_timestamp = block_timestamp;
+				tracer->buff.consumer_index =
+					(tracer->buff.consumer_index + 1) & (block_count - 1);
+				break;
+			}
+		}
+
+		/* Parse events */
+		for (i = 0; i < TRACES_PER_BLOCK ; i++) {
+			poll_trace(tracer, &tracer_event, &tmp_trace_block[i]);
+			mlx5_tracer_handle_trace(tracer, &tracer_event);
+		}
+
+		tracer->buff.consumer_index =
+			(tracer->buff.consumer_index + 1) & (block_count - 1);
+
+		tracer->last_timestamp = block_timestamp;
+		start_offset = tracer->buff.consumer_index * TRACER_BLOCK_SIZE_BYTE;
+		memcpy(tmp_trace_block, tracer->buff.log_buf + start_offset,
+		       TRACER_BLOCK_SIZE_BYTE);
+		block_timestamp = get_block_timestamp(tracer,
+						      &tmp_trace_block[TRACES_PER_BLOCK - 1]);
+	}
+
+	mlx5_fw_tracer_arm(dev);
+}
+
+static int mlx5_fw_tracer_set_mtrc_conf(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	u32 out[MLX5_ST_SZ_DW(mtrc_conf)] = {0};
+	u32 in[MLX5_ST_SZ_DW(mtrc_conf)] = {0};
+	int err;
+
+	MLX5_SET(mtrc_conf, in, trace_mode, TRACE_TO_MEMORY);
+	MLX5_SET(mtrc_conf, in, log_trace_buffer_size,
+		 ilog2(TRACER_BUFFER_PAGE_NUM));
+	MLX5_SET(mtrc_conf, in, trace_mkey, tracer->buff.mkey.key);
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out),
+				   MLX5_REG_MTRC_CONF, 0, 1);
+	if (err)
+		mlx5_core_warn(dev, "FWTracer: Failed to set tracer configurations %d\n", err);
+
+	return err;
+}
+
+static int mlx5_fw_tracer_set_mtrc_ctrl(struct mlx5_fw_tracer *tracer, u8 status, u8 arm)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	u32 out[MLX5_ST_SZ_DW(mtrc_ctrl)] = {0};
+	u32 in[MLX5_ST_SZ_DW(mtrc_ctrl)] = {0};
+	int err;
+
+	MLX5_SET(mtrc_ctrl, in, modify_field_select, TRACE_STATUS);
+	MLX5_SET(mtrc_ctrl, in, trace_status, status);
+	MLX5_SET(mtrc_ctrl, in, arm_event, arm);
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out),
+				   MLX5_REG_MTRC_CTRL, 0, 1);
+
+	if (!err && status)
+		tracer->last_timestamp = 0;
+
+	return err;
+}
+
+static int mlx5_fw_tracer_start(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	int err;
+
+	err = mlx5_fw_tracer_ownership_acquire(tracer);
+	if (err) {
+		mlx5_core_dbg(dev, "FWTracer: Ownership was not granted %d\n", err);
+		/* Don't fail since ownership can be acquired on a later FW event */
+		return 0;
+	}
+
+	err = mlx5_fw_tracer_set_mtrc_conf(tracer);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Failed to set tracer configuration %d\n", err);
+		goto release_ownership;
+	}
+
+	/* enable tracer & trace events */
+	err = mlx5_fw_tracer_set_mtrc_ctrl(tracer, 1, 1);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Failed to enable tracer %d\n", err);
+		goto release_ownership;
+	}
+
+	mlx5_core_dbg(dev, "FWTracer: Ownership granted and active\n");
+	return 0;
+
+release_ownership:
+	mlx5_fw_tracer_ownership_release(tracer);
+	return err;
+}
+
+static void mlx5_fw_tracer_ownership_change(struct work_struct *work)
+{
+	struct mlx5_fw_tracer *tracer =
+		container_of(work, struct mlx5_fw_tracer, ownership_change_work);
+
+	mlx5_core_dbg(tracer->dev, "FWTracer: ownership changed, current=(%d)\n", tracer->owner);
+	if (tracer->owner) {
+		tracer->owner = false;
+		tracer->buff.consumer_index = 0;
+		return;
+	}
+
+	mlx5_fw_tracer_start(tracer);
+}
+
+/* Create software resources (Buffers, etc ..) */
+struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_tracer *tracer = NULL;
+	int err;
+
+	if (!MLX5_CAP_MCAM_REG(dev, tracer_registers)) {
+		mlx5_core_dbg(dev, "FWTracer: Tracer capability not present\n");
+		return NULL;
+	}
+
+	tracer = kzalloc(sizeof(*tracer), GFP_KERNEL);
+	if (!tracer)
+		return ERR_PTR(-ENOMEM);
+
+	tracer->work_queue = create_singlethread_workqueue("mlx5_fw_tracer");
+	if (!tracer->work_queue) {
+		err = -ENOMEM;
+		goto free_tracer;
+	}
+
+	tracer->dev = dev;
+
+	INIT_LIST_HEAD(&tracer->ready_strings_list);
+	INIT_WORK(&tracer->ownership_change_work, mlx5_fw_tracer_ownership_change);
+	INIT_WORK(&tracer->read_fw_strings_work, mlx5_tracer_read_strings_db);
+	INIT_WORK(&tracer->handle_traces_work, mlx5_fw_tracer_handle_traces);
+
+
+	err = mlx5_query_mtrc_caps(tracer);
+	if (err) {
+		mlx5_core_dbg(dev, "FWTracer: Failed to query capabilities %d\n", err);
+		goto destroy_workqueue;
+	}
+
+	err = mlx5_fw_tracer_create_log_buf(tracer);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Create log buffer failed %d\n", err);
+		goto destroy_workqueue;
+	}
+
+	err = mlx5_fw_tracer_allocate_strings_db(tracer);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Allocate strings database failed %d\n", err);
+		goto free_log_buf;
+	}
+
+	mlx5_core_dbg(dev, "FWTracer: Tracer created\n");
+
+	return tracer;
+
+free_log_buf:
+	mlx5_fw_tracer_destroy_log_buf(tracer);
+destroy_workqueue:
+	tracer->dev = NULL;
+	destroy_workqueue(tracer->work_queue);
+free_tracer:
+	kfree(tracer);
+	return ERR_PTR(err);
+}
+
+/* Create HW resources + start tracer
+ * must be called before Async EQ is created
+ */
+int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev;
+	int err;
+
+	if (IS_ERR_OR_NULL(tracer))
+		return 0;
+
+	dev = tracer->dev;
+
+	if (!tracer->str_db.loaded)
+		queue_work(tracer->work_queue, &tracer->read_fw_strings_work);
+
+	err = mlx5_core_alloc_pd(dev, &tracer->buff.pdn);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Failed to allocate PD %d\n", err);
+		return err;
+	}
+
+	err = mlx5_fw_tracer_create_mkey(tracer);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Failed to create mkey %d\n", err);
+		goto err_dealloc_pd;
+	}
+
+	mlx5_fw_tracer_start(tracer);
+
+	return 0;
+
+err_dealloc_pd:
+	mlx5_core_dealloc_pd(dev, tracer->buff.pdn);
+	return err;
+}
+
+/* Stop tracer + Cleanup HW resources
+ * must be called after Async EQ is destroyed
+ */
+void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer)
+{
+	if (IS_ERR_OR_NULL(tracer))
+		return;
+
+	mlx5_core_dbg(tracer->dev, "FWTracer: Cleanup, is owner ? (%d)\n",
+		      tracer->owner);
+
+	cancel_work_sync(&tracer->ownership_change_work);
+	cancel_work_sync(&tracer->handle_traces_work);
+
+	if (tracer->owner)
+		mlx5_fw_tracer_ownership_release(tracer);
+
+	mlx5_core_destroy_mkey(tracer->dev, &tracer->buff.mkey);
+	mlx5_core_dealloc_pd(tracer->dev, tracer->buff.pdn);
+}
+
+/* Free software resources (Buffers, etc ..) */
+void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
+{
+	if (IS_ERR_OR_NULL(tracer))
+		return;
+
+	mlx5_core_dbg(tracer->dev, "FWTracer: Destroy\n");
+
+	cancel_work_sync(&tracer->read_fw_strings_work);
+	mlx5_fw_tracer_clean_ready_list(tracer);
+	mlx5_fw_tracer_clean_print_hash(tracer);
+	mlx5_fw_tracer_free_strings_db(tracer);
+	mlx5_fw_tracer_destroy_log_buf(tracer);
+	flush_workqueue(tracer->work_queue);
+	destroy_workqueue(tracer->work_queue);
+	kfree(tracer);
+}
+
+void mlx5_fw_tracer_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe)
+{
+	struct mlx5_fw_tracer *tracer = dev->tracer;
+
+	if (!tracer)
+		return;
+
+	switch (eqe->sub_type) {
+	case MLX5_TRACER_SUBTYPE_OWNERSHIP_CHANGE:
+		if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state))
+			queue_work(tracer->work_queue, &tracer->ownership_change_work);
+		break;
+	case MLX5_TRACER_SUBTYPE_TRACES_AVAILABLE:
+		if (likely(tracer->str_db.loaded))
+			queue_work(tracer->work_queue, &tracer->handle_traces_work);
+		break;
+	default:
+		mlx5_core_dbg(dev, "FWTracer: Event with unrecognized subtype: sub_type %d\n",
+			      eqe->sub_type);
+	}
+}
+
+EXPORT_TRACEPOINT_SYMBOL(mlx5_fw);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
new file mode 100644
index 000000000000..0347f2dd5cee
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
@@ -0,0 +1,175 @@
+/*
+ * Copyright (c) 2018, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef __LIB_TRACER_H__
+#define __LIB_TRACER_H__
+
+#include <linux/mlx5/driver.h>
+#include "mlx5_core.h"
+
+#define STRINGS_DB_SECTIONS_NUM 8
+#define STRINGS_DB_READ_SIZE_BYTES 256
+#define STRINGS_DB_LEFTOVER_SIZE_BYTES 64
+#define TRACER_BUFFER_PAGE_NUM 64
+#define TRACER_BUFFER_CHUNK 4096
+#define TRACE_BUFFER_SIZE_BYTE (TRACER_BUFFER_PAGE_NUM * TRACER_BUFFER_CHUNK)
+
+#define TRACER_BLOCK_SIZE_BYTE 256
+#define TRACES_PER_BLOCK 32
+
+#define TRACER_MAX_PARAMS 7
+#define MESSAGE_HASH_BITS 6
+#define MESSAGE_HASH_SIZE BIT(MESSAGE_HASH_BITS)
+
+#define MASK_52_7 (0x1FFFFFFFFFFF80)
+#define MASK_6_0  (0x7F)
+
+struct mlx5_fw_tracer {
+	struct mlx5_core_dev *dev;
+	bool owner;
+	u8   trc_ver;
+	struct workqueue_struct *work_queue;
+	struct work_struct ownership_change_work;
+	struct work_struct read_fw_strings_work;
+
+	/* Strings DB */
+	struct {
+		u8 first_string_trace;
+		u8 num_string_trace;
+		u32 num_string_db;
+		u32 base_address_out[STRINGS_DB_SECTIONS_NUM];
+		u32 size_out[STRINGS_DB_SECTIONS_NUM];
+		void *buffer[STRINGS_DB_SECTIONS_NUM];
+		bool loaded;
+	} str_db;
+
+	/* Log Buffer */
+	struct {
+		u32 pdn;
+		void *log_buf;
+		dma_addr_t dma;
+		u32 size;
+		struct mlx5_core_mkey mkey;
+		u32 consumer_index;
+	} buff;
+
+	u64 last_timestamp;
+	struct work_struct handle_traces_work;
+	struct hlist_head hash[MESSAGE_HASH_SIZE];
+	struct list_head ready_strings_list;
+};
+
+struct tracer_string_format {
+	char *string;
+	int params[TRACER_MAX_PARAMS];
+	int num_of_params;
+	int last_param_num;
+	u8 event_id;
+	u32 tmsn;
+	struct hlist_node hlist;
+	struct list_head list;
+	u32 timestamp;
+	bool lost;
+};
+
+enum mlx5_fw_tracer_ownership_state {
+	MLX5_FW_TRACER_RELEASE_OWNERSHIP,
+	MLX5_FW_TRACER_ACQUIRE_OWNERSHIP,
+};
+
+enum tracer_ctrl_fields_select {
+	TRACE_STATUS = 1 << 0,
+};
+
+enum tracer_event_type {
+	TRACER_EVENT_TYPE_STRING,
+	TRACER_EVENT_TYPE_TIMESTAMP = 0xFF,
+	TRACER_EVENT_TYPE_UNRECOGNIZED,
+};
+
+enum tracing_mode {
+	TRACE_TO_MEMORY = 1 << 0,
+};
+
+struct tracer_timestamp_event {
+	u64        timestamp;
+	u8         unreliable;
+};
+
+struct tracer_string_event {
+	u32        timestamp;
+	u32        tmsn;
+	u32        tdsn;
+	u32        string_param;
+};
+
+struct tracer_event {
+	bool      lost_event;
+	u32       type;
+	u8        event_id;
+	union {
+		struct tracer_string_event string_event;
+		struct tracer_timestamp_event timestamp_event;
+	};
+};
+
+struct mlx5_ifc_tracer_event_bits {
+	u8         lost[0x1];
+	u8         timestamp[0x7];
+	u8         event_id[0x8];
+	u8         event_data[0x30];
+};
+
+struct mlx5_ifc_tracer_string_event_bits {
+	u8         lost[0x1];
+	u8         timestamp[0x7];
+	u8         event_id[0x8];
+	u8         tmsn[0xd];
+	u8         tdsn[0x3];
+	u8         string_param[0x20];
+};
+
+struct mlx5_ifc_tracer_timestamp_event_bits {
+	u8         timestamp7_0[0x8];
+	u8         event_id[0x8];
+	u8         urts[0x3];
+	u8         timestamp52_40[0xd];
+	u8         timestamp39_8[0x20];
+};
+
+struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev);
+int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer);
+void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer);
+void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer);
+void mlx5_fw_tracer_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h
new file mode 100644
index 000000000000..83f90e9aff45
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h
@@ -0,0 +1,78 @@
+/*
+ * Copyright (c) 2018, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#if !defined(__LIB_TRACER_TRACEPOINT_H__) || defined(TRACE_HEADER_MULTI_READ)
+#define __LIB_TRACER_TRACEPOINT_H__
+
+#include <linux/tracepoint.h>
+#include "fw_tracer.h"
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mlx5
+
+/* Tracepoint for FWTracer messages: */
+TRACE_EVENT(mlx5_fw,
+	TP_PROTO(const struct mlx5_fw_tracer *tracer, u64 trace_timestamp,
+		 bool lost, u8 event_id, const char *msg),
+
+	TP_ARGS(tracer, trace_timestamp, lost, event_id, msg),
+
+	TP_STRUCT__entry(
+		__string(dev_name, dev_name(&tracer->dev->pdev->dev))
+		__field(u64, trace_timestamp)
+		__field(bool, lost)
+		__field(u8, event_id)
+		__string(msg, msg)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name, dev_name(&tracer->dev->pdev->dev));
+		__entry->trace_timestamp = trace_timestamp;
+		__entry->lost = lost;
+		__entry->event_id = event_id;
+		__assign_str(msg, msg);
+	),
+
+	TP_printk("%s [0x%llx] %d [0x%x] %s",
+		  __get_str(dev_name),
+		  __entry->trace_timestamp,
+		  __entry->lost, __entry->event_id,
+		  __get_str(msg))
+);
+
+#endif
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH ./diag
+#define TRACE_INCLUDE_FILE fw_tracer_tracepoint
+#include <trace/define_trace.h>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 405236cf0b04..db2cfcd21d43 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -52,6 +52,7 @@
 #include "wq.h"
 #include "mlx5_core.h"
 #include "en_stats.h"
+#include "en/fs.h"
 
 struct page_pool;
 
@@ -137,7 +138,6 @@ struct page_pool;
 #define MLX5E_MAX_NUM_CHANNELS         (MLX5E_INDIR_RQT_SIZE >> 1)
 #define MLX5E_MAX_NUM_SQS              (MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC)
 #define MLX5E_TX_CQ_POLL_BUDGET        128
-#define MLX5E_UPDATE_STATS_INTERVAL    200 /* msecs */
 #define MLX5E_SQ_RECOVER_MIN_INTERVAL  500 /* msecs */
 
 #define MLX5E_UMR_WQE_INLINE_SZ \
@@ -148,10 +148,6 @@ struct page_pool;
 	(DIV_ROUND_UP(MLX5E_UMR_WQE_INLINE_SZ, MLX5_SEND_WQE_BB))
 #define MLX5E_ICOSQ_MAX_WQEBBS MLX5E_UMR_WQEBBS
 
-#define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
-#define MLX5E_XDP_TX_DS_COUNT \
-	((sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) + 1 /* SG DS */)
-
 #define MLX5E_NUM_MAIN_GROUPS 9
 
 #define MLX5E_MSG_LEVEL			NETIF_MSG_LINK
@@ -349,6 +345,7 @@ enum {
 	MLX5E_SQ_STATE_IPSEC,
 	MLX5E_SQ_STATE_AM,
 	MLX5E_SQ_STATE_TLS,
+	MLX5E_SQ_STATE_REDIRECT,
 };
 
 struct mlx5e_sq_wqe_info {
@@ -369,16 +366,14 @@ struct mlx5e_txqsq {
 
 	struct mlx5e_cq            cq;
 
-	/* write@xmit, read@completion */
-	struct {
-		struct mlx5e_sq_dma       *dma_fifo;
-		struct mlx5e_tx_wqe_info  *wqe_info;
-	} db;
-
 	/* read only */
 	struct mlx5_wq_cyc         wq;
 	u32                        dma_fifo_mask;
 	struct mlx5e_sq_stats     *stats;
+	struct {
+		struct mlx5e_sq_dma       *dma_fifo;
+		struct mlx5e_tx_wqe_info  *wqe_info;
+	} db;
 	void __iomem              *uar_map;
 	struct netdev_queue       *txq;
 	u32                        sqn;
@@ -400,30 +395,43 @@ struct mlx5e_txqsq {
 	} recover;
 } ____cacheline_aligned_in_smp;
 
+struct mlx5e_dma_info {
+	struct page     *page;
+	dma_addr_t      addr;
+};
+
+struct mlx5e_xdp_info {
+	struct xdp_frame      *xdpf;
+	dma_addr_t            dma_addr;
+	struct mlx5e_dma_info di;
+};
+
 struct mlx5e_xdpsq {
 	/* data path */
 
-	/* dirtied @rx completion */
+	/* dirtied @completion */
 	u16                        cc;
-	u16                        pc;
+	bool                       redirect_flush;
 
-	struct mlx5e_cq            cq;
+	/* dirtied @xmit */
+	u16                        pc ____cacheline_aligned_in_smp;
+	bool                       doorbell;
 
-	/* write@xmit, read@completion */
-	struct {
-		struct mlx5e_dma_info     *di;
-		bool                       doorbell;
-		bool                       redirect_flush;
-	} db;
+	struct mlx5e_cq            cq;
 
 	/* read only */
 	struct mlx5_wq_cyc         wq;
+	struct mlx5e_xdpsq_stats  *stats;
+	struct {
+		struct mlx5e_xdp_info     *xdpi;
+	} db;
 	void __iomem              *uar_map;
 	u32                        sqn;
 	struct device             *pdev;
 	__be32                     mkey_be;
 	u8                         min_inline_mode;
 	unsigned long              state;
+	unsigned int               hw_mtu;
 
 	/* control path */
 	struct mlx5_wq_ctrl        wq_ctrl;
@@ -460,11 +468,6 @@ mlx5e_wqc_has_room_for(struct mlx5_wq_cyc *wq, u16 cc, u16 pc, u16 n)
 	return (mlx5_wq_cyc_ctr2ix(wq, cc - pc) >= n) || (cc == pc);
 }
 
-struct mlx5e_dma_info {
-	struct page	*page;
-	dma_addr_t	addr;
-};
-
 struct mlx5e_wqe_frag_info {
 	struct mlx5e_dma_info *di;
 	u32 offset;
@@ -567,7 +570,6 @@ struct mlx5e_rq {
 
 	/* XDP */
 	struct bpf_prog       *xdp_prog;
-	unsigned int           hw_mtu;
 	struct mlx5e_xdpsq     xdpsq;
 	DECLARE_BITMAP(flags, 8);
 	struct page_pool      *page_pool;
@@ -596,6 +598,9 @@ struct mlx5e_channel {
 	__be32                     mkey_be;
 	u8                         num_tc;
 
+	/* XDP_REDIRECT */
+	struct mlx5e_xdpsq         xdpsq;
+
 	/* data path - accessed per napi poll */
 	struct irq_desc *irq_desc;
 	struct mlx5e_ch_stats     *stats;
@@ -618,159 +623,16 @@ struct mlx5e_channel_stats {
 	struct mlx5e_ch_stats ch;
 	struct mlx5e_sq_stats sq[MLX5E_MAX_NUM_TC];
 	struct mlx5e_rq_stats rq;
+	struct mlx5e_xdpsq_stats rq_xdpsq;
+	struct mlx5e_xdpsq_stats xdpsq;
 } ____cacheline_aligned_in_smp;
 
-enum mlx5e_traffic_types {
-	MLX5E_TT_IPV4_TCP,
-	MLX5E_TT_IPV6_TCP,
-	MLX5E_TT_IPV4_UDP,
-	MLX5E_TT_IPV6_UDP,
-	MLX5E_TT_IPV4_IPSEC_AH,
-	MLX5E_TT_IPV6_IPSEC_AH,
-	MLX5E_TT_IPV4_IPSEC_ESP,
-	MLX5E_TT_IPV6_IPSEC_ESP,
-	MLX5E_TT_IPV4,
-	MLX5E_TT_IPV6,
-	MLX5E_TT_ANY,
-	MLX5E_NUM_TT,
-	MLX5E_NUM_INDIR_TIRS = MLX5E_TT_ANY,
-};
-
-enum mlx5e_tunnel_types {
-	MLX5E_TT_IPV4_GRE,
-	MLX5E_TT_IPV6_GRE,
-	MLX5E_NUM_TUNNEL_TT,
-};
-
 enum {
 	MLX5E_STATE_ASYNC_EVENTS_ENABLED,
 	MLX5E_STATE_OPENED,
 	MLX5E_STATE_DESTROYING,
 };
 
-struct mlx5e_vxlan_db {
-	spinlock_t			lock; /* protect vxlan table */
-	struct radix_tree_root		tree;
-};
-
-struct mlx5e_l2_rule {
-	u8  addr[ETH_ALEN + 2];
-	struct mlx5_flow_handle *rule;
-};
-
-struct mlx5e_flow_table {
-	int num_groups;
-	struct mlx5_flow_table *t;
-	struct mlx5_flow_group **g;
-};
-
-#define MLX5E_L2_ADDR_HASH_SIZE BIT(BITS_PER_BYTE)
-
-struct mlx5e_tc_table {
-	struct mlx5_flow_table		*t;
-
-	struct rhashtable               ht;
-
-	DECLARE_HASHTABLE(mod_hdr_tbl, 8);
-	DECLARE_HASHTABLE(hairpin_tbl, 8);
-};
-
-struct mlx5e_vlan_table {
-	struct mlx5e_flow_table		ft;
-	DECLARE_BITMAP(active_cvlans, VLAN_N_VID);
-	DECLARE_BITMAP(active_svlans, VLAN_N_VID);
-	struct mlx5_flow_handle	*active_cvlans_rule[VLAN_N_VID];
-	struct mlx5_flow_handle	*active_svlans_rule[VLAN_N_VID];
-	struct mlx5_flow_handle	*untagged_rule;
-	struct mlx5_flow_handle	*any_cvlan_rule;
-	struct mlx5_flow_handle	*any_svlan_rule;
-	bool			cvlan_filter_disabled;
-};
-
-struct mlx5e_l2_table {
-	struct mlx5e_flow_table    ft;
-	struct hlist_head          netdev_uc[MLX5E_L2_ADDR_HASH_SIZE];
-	struct hlist_head          netdev_mc[MLX5E_L2_ADDR_HASH_SIZE];
-	struct mlx5e_l2_rule	   broadcast;
-	struct mlx5e_l2_rule	   allmulti;
-	struct mlx5e_l2_rule	   promisc;
-	bool                       broadcast_enabled;
-	bool                       allmulti_enabled;
-	bool                       promisc_enabled;
-};
-
-/* L3/L4 traffic type classifier */
-struct mlx5e_ttc_table {
-	struct mlx5e_flow_table  ft;
-	struct mlx5_flow_handle	 *rules[MLX5E_NUM_TT];
-	struct mlx5_flow_handle  *tunnel_rules[MLX5E_NUM_TUNNEL_TT];
-};
-
-#define ARFS_HASH_SHIFT BITS_PER_BYTE
-#define ARFS_HASH_SIZE BIT(BITS_PER_BYTE)
-struct arfs_table {
-	struct mlx5e_flow_table  ft;
-	struct mlx5_flow_handle	 *default_rule;
-	struct hlist_head	 rules_hash[ARFS_HASH_SIZE];
-};
-
-enum  arfs_type {
-	ARFS_IPV4_TCP,
-	ARFS_IPV6_TCP,
-	ARFS_IPV4_UDP,
-	ARFS_IPV6_UDP,
-	ARFS_NUM_TYPES,
-};
-
-struct mlx5e_arfs_tables {
-	struct arfs_table arfs_tables[ARFS_NUM_TYPES];
-	/* Protect aRFS rules list */
-	spinlock_t                     arfs_lock;
-	struct list_head               rules;
-	int                            last_filter_id;
-	struct workqueue_struct        *wq;
-};
-
-/* NIC prio FTS */
-enum {
-	MLX5E_VLAN_FT_LEVEL = 0,
-	MLX5E_L2_FT_LEVEL,
-	MLX5E_TTC_FT_LEVEL,
-	MLX5E_INNER_TTC_FT_LEVEL,
-	MLX5E_ARFS_FT_LEVEL
-};
-
-enum {
-	MLX5E_TC_FT_LEVEL = 0,
-	MLX5E_TC_TTC_FT_LEVEL,
-};
-
-struct mlx5e_ethtool_table {
-	struct mlx5_flow_table *ft;
-	int                    num_rules;
-};
-
-#define ETHTOOL_NUM_L3_L4_FTS 7
-#define ETHTOOL_NUM_L2_FTS 4
-
-struct mlx5e_ethtool_steering {
-	struct mlx5e_ethtool_table      l3_l4_ft[ETHTOOL_NUM_L3_L4_FTS];
-	struct mlx5e_ethtool_table      l2_ft[ETHTOOL_NUM_L2_FTS];
-	struct list_head                rules;
-	int                             tot_num_rules;
-};
-
-struct mlx5e_flow_steering {
-	struct mlx5_flow_namespace      *ns;
-	struct mlx5e_ethtool_steering   ethtool;
-	struct mlx5e_tc_table           tc;
-	struct mlx5e_vlan_table         vlan;
-	struct mlx5e_l2_table           l2;
-	struct mlx5e_ttc_table          ttc;
-	struct mlx5e_ttc_table          inner_ttc;
-	struct mlx5e_arfs_tables        arfs;
-};
-
 struct mlx5e_rqt {
 	u32              rqtn;
 	bool		 enabled;
@@ -810,7 +672,6 @@ struct mlx5e_priv {
 	u32                        tx_rates[MLX5E_MAX_NUM_SQS];
 
 	struct mlx5e_flow_steering fs;
-	struct mlx5e_vxlan_db      vxlan;
 
 	struct workqueue_struct    *wq;
 	struct work_struct         update_carrier_work;
@@ -864,7 +725,8 @@ struct mlx5e_profile {
 void mlx5e_build_ptys2ethtool_map(void);
 
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv, select_queue_fallback_t fallback);
+		       struct net_device *sb_dev,
+		       select_queue_fallback_t fallback);
 netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
 netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 			  struct mlx5e_tx_wqe *wqe, u16 pi);
@@ -874,14 +736,13 @@ void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
 int mlx5e_napi_poll(struct napi_struct *napi, int budget);
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
-bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq);
 void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq);
-void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq);
 
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev);
 bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev,
 				struct mlx5e_params *params);
 
+void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info);
 void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info,
 			bool recycle);
 void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
@@ -890,7 +751,6 @@ bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq);
 bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq);
 void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
 void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
-void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi);
 struct sk_buff *
 mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 				u16 cqe_bcnt, u32 head_offset, u32 page_idx);
@@ -906,23 +766,10 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 
 void mlx5e_update_stats(struct mlx5e_priv *priv);
 
-int mlx5e_create_flow_steering(struct mlx5e_priv *priv);
-void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv);
 void mlx5e_init_l2_addr(struct mlx5e_priv *priv);
-void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft);
 int mlx5e_self_test_num(struct mlx5e_priv *priv);
 void mlx5e_self_test(struct net_device *ndev, struct ethtool_test *etest,
 		     u64 *buf);
-int mlx5e_ethtool_get_flow(struct mlx5e_priv *priv, struct ethtool_rxnfc *info,
-			   int location);
-int mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv,
-				struct ethtool_rxnfc *info, u32 *rule_locs);
-int mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
-			       struct ethtool_rx_flow_spec *fs);
-int mlx5e_ethtool_flow_remove(struct mlx5e_priv *priv,
-			      int location);
-void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv);
-void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv);
 void mlx5e_set_rx_mode_work(struct work_struct *work);
 
 int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr);
@@ -933,8 +780,6 @@ int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto,
 			  u16 vid);
 int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto,
 			   u16 vid);
-void mlx5e_enable_cvlan_filter(struct mlx5e_priv *priv);
-void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv);
 void mlx5e_timestamp_init(struct mlx5e_priv *priv);
 
 struct mlx5e_redirect_rqt_param {
@@ -1051,32 +896,6 @@ void mlx5e_dcbnl_init_app(struct mlx5e_priv *priv);
 void mlx5e_dcbnl_delete_app(struct mlx5e_priv *priv);
 #endif
 
-#ifndef CONFIG_RFS_ACCEL
-static inline int mlx5e_arfs_create_tables(struct mlx5e_priv *priv)
-{
-	return 0;
-}
-
-static inline void mlx5e_arfs_destroy_tables(struct mlx5e_priv *priv) {}
-
-static inline int mlx5e_arfs_enable(struct mlx5e_priv *priv)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int mlx5e_arfs_disable(struct mlx5e_priv *priv)
-{
-	return -EOPNOTSUPP;
-}
-#else
-int mlx5e_arfs_create_tables(struct mlx5e_priv *priv);
-void mlx5e_arfs_destroy_tables(struct mlx5e_priv *priv);
-int mlx5e_arfs_enable(struct mlx5e_priv *priv);
-int mlx5e_arfs_disable(struct mlx5e_priv *priv);
-int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
-			u16 rxq_index, u32 flow_id);
-#endif
-
 int mlx5e_create_tir(struct mlx5_core_dev *mdev,
 		     struct mlx5e_tir *tir, u32 *in, int inlen);
 void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
@@ -1097,27 +916,6 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv);
 void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv);
 void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt);
 
-struct ttc_params {
-	struct mlx5_flow_table_attr ft_attr;
-	u32 any_tt_tirn;
-	u32 indir_tirn[MLX5E_NUM_INDIR_TIRS];
-	struct mlx5e_ttc_table *inner_ttc;
-};
-
-void mlx5e_set_ttc_basic_params(struct mlx5e_priv *priv, struct ttc_params *ttc_params);
-void mlx5e_set_ttc_ft_params(struct ttc_params *ttc_params);
-void mlx5e_set_inner_ttc_ft_params(struct ttc_params *ttc_params);
-
-int mlx5e_create_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
-			   struct mlx5e_ttc_table *ttc);
-void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv,
-			     struct mlx5e_ttc_table *ttc);
-
-int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
-				 struct mlx5e_ttc_table *ttc);
-void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv,
-				   struct mlx5e_ttc_table *ttc);
-
 int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc,
 		     u32 underlay_qpn, u32 *tisn);
 void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
new file mode 100644
index 000000000000..bbf69e859b78
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -0,0 +1,210 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#ifndef __MLX5E_FLOW_STEER_H__
+#define __MLX5E_FLOW_STEER_H__
+
+enum {
+	MLX5E_TC_FT_LEVEL = 0,
+	MLX5E_TC_TTC_FT_LEVEL,
+};
+
+struct mlx5e_tc_table {
+	struct mlx5_flow_table		*t;
+
+	struct rhashtable               ht;
+
+	DECLARE_HASHTABLE(mod_hdr_tbl, 8);
+	DECLARE_HASHTABLE(hairpin_tbl, 8);
+};
+
+struct mlx5e_flow_table {
+	int num_groups;
+	struct mlx5_flow_table *t;
+	struct mlx5_flow_group **g;
+};
+
+struct mlx5e_l2_rule {
+	u8  addr[ETH_ALEN + 2];
+	struct mlx5_flow_handle *rule;
+};
+
+#define MLX5E_L2_ADDR_HASH_SIZE BIT(BITS_PER_BYTE)
+
+struct mlx5e_vlan_table {
+	struct mlx5e_flow_table		ft;
+	DECLARE_BITMAP(active_cvlans, VLAN_N_VID);
+	DECLARE_BITMAP(active_svlans, VLAN_N_VID);
+	struct mlx5_flow_handle	*active_cvlans_rule[VLAN_N_VID];
+	struct mlx5_flow_handle	*active_svlans_rule[VLAN_N_VID];
+	struct mlx5_flow_handle	*untagged_rule;
+	struct mlx5_flow_handle	*any_cvlan_rule;
+	struct mlx5_flow_handle	*any_svlan_rule;
+	bool			cvlan_filter_disabled;
+};
+
+struct mlx5e_l2_table {
+	struct mlx5e_flow_table    ft;
+	struct hlist_head          netdev_uc[MLX5E_L2_ADDR_HASH_SIZE];
+	struct hlist_head          netdev_mc[MLX5E_L2_ADDR_HASH_SIZE];
+	struct mlx5e_l2_rule	   broadcast;
+	struct mlx5e_l2_rule	   allmulti;
+	struct mlx5e_l2_rule	   promisc;
+	bool                       broadcast_enabled;
+	bool                       allmulti_enabled;
+	bool                       promisc_enabled;
+};
+
+enum mlx5e_traffic_types {
+	MLX5E_TT_IPV4_TCP,
+	MLX5E_TT_IPV6_TCP,
+	MLX5E_TT_IPV4_UDP,
+	MLX5E_TT_IPV6_UDP,
+	MLX5E_TT_IPV4_IPSEC_AH,
+	MLX5E_TT_IPV6_IPSEC_AH,
+	MLX5E_TT_IPV4_IPSEC_ESP,
+	MLX5E_TT_IPV6_IPSEC_ESP,
+	MLX5E_TT_IPV4,
+	MLX5E_TT_IPV6,
+	MLX5E_TT_ANY,
+	MLX5E_NUM_TT,
+	MLX5E_NUM_INDIR_TIRS = MLX5E_TT_ANY,
+};
+
+enum mlx5e_tunnel_types {
+	MLX5E_TT_IPV4_GRE,
+	MLX5E_TT_IPV6_GRE,
+	MLX5E_NUM_TUNNEL_TT,
+};
+
+/* L3/L4 traffic type classifier */
+struct mlx5e_ttc_table {
+	struct mlx5e_flow_table  ft;
+	struct mlx5_flow_handle	 *rules[MLX5E_NUM_TT];
+	struct mlx5_flow_handle  *tunnel_rules[MLX5E_NUM_TUNNEL_TT];
+};
+
+/* NIC prio FTS */
+enum {
+	MLX5E_VLAN_FT_LEVEL = 0,
+	MLX5E_L2_FT_LEVEL,
+	MLX5E_TTC_FT_LEVEL,
+	MLX5E_INNER_TTC_FT_LEVEL,
+#ifdef CONFIG_MLX5_EN_ARFS
+	MLX5E_ARFS_FT_LEVEL
+#endif
+};
+
+#ifdef CONFIG_MLX5_EN_RXNFC
+
+struct mlx5e_ethtool_table {
+	struct mlx5_flow_table *ft;
+	int                    num_rules;
+};
+
+#define ETHTOOL_NUM_L3_L4_FTS 7
+#define ETHTOOL_NUM_L2_FTS 4
+
+struct mlx5e_ethtool_steering {
+	struct mlx5e_ethtool_table      l3_l4_ft[ETHTOOL_NUM_L3_L4_FTS];
+	struct mlx5e_ethtool_table      l2_ft[ETHTOOL_NUM_L2_FTS];
+	struct list_head                rules;
+	int                             tot_num_rules;
+};
+
+void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv);
+void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv);
+int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd);
+int mlx5e_get_rxnfc(struct net_device *dev,
+		    struct ethtool_rxnfc *info, u32 *rule_locs);
+#else
+static inline void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv)    { }
+static inline void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv) { }
+#endif /* CONFIG_MLX5_EN_RXNFC */
+
+#ifdef CONFIG_MLX5_EN_ARFS
+#define ARFS_HASH_SHIFT BITS_PER_BYTE
+#define ARFS_HASH_SIZE BIT(BITS_PER_BYTE)
+
+struct arfs_table {
+	struct mlx5e_flow_table  ft;
+	struct mlx5_flow_handle	 *default_rule;
+	struct hlist_head	 rules_hash[ARFS_HASH_SIZE];
+};
+
+enum  arfs_type {
+	ARFS_IPV4_TCP,
+	ARFS_IPV6_TCP,
+	ARFS_IPV4_UDP,
+	ARFS_IPV6_UDP,
+	ARFS_NUM_TYPES,
+};
+
+struct mlx5e_arfs_tables {
+	struct arfs_table arfs_tables[ARFS_NUM_TYPES];
+	/* Protect aRFS rules list */
+	spinlock_t                     arfs_lock;
+	struct list_head               rules;
+	int                            last_filter_id;
+	struct workqueue_struct        *wq;
+};
+
+int mlx5e_arfs_create_tables(struct mlx5e_priv *priv);
+void mlx5e_arfs_destroy_tables(struct mlx5e_priv *priv);
+int mlx5e_arfs_enable(struct mlx5e_priv *priv);
+int mlx5e_arfs_disable(struct mlx5e_priv *priv);
+int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
+			u16 rxq_index, u32 flow_id);
+#else
+static inline int mlx5e_arfs_create_tables(struct mlx5e_priv *priv) { return 0; }
+static inline void mlx5e_arfs_destroy_tables(struct mlx5e_priv *priv) {}
+static inline int mlx5e_arfs_enable(struct mlx5e_priv *priv) { return -EOPNOTSUPP; }
+static inline int mlx5e_arfs_disable(struct mlx5e_priv *priv) {	return -EOPNOTSUPP; }
+#endif
+
+struct mlx5e_flow_steering {
+	struct mlx5_flow_namespace      *ns;
+#ifdef CONFIG_MLX5_EN_RXNFC
+	struct mlx5e_ethtool_steering   ethtool;
+#endif
+	struct mlx5e_tc_table           tc;
+	struct mlx5e_vlan_table         vlan;
+	struct mlx5e_l2_table           l2;
+	struct mlx5e_ttc_table          ttc;
+	struct mlx5e_ttc_table          inner_ttc;
+#ifdef CONFIG_MLX5_EN_ARFS
+	struct mlx5e_arfs_tables        arfs;
+#endif
+};
+
+struct ttc_params {
+	struct mlx5_flow_table_attr ft_attr;
+	u32 any_tt_tirn;
+	u32 indir_tirn[MLX5E_NUM_INDIR_TIRS];
+	struct mlx5e_ttc_table *inner_ttc;
+};
+
+void mlx5e_set_ttc_basic_params(struct mlx5e_priv *priv, struct ttc_params *ttc_params);
+void mlx5e_set_ttc_ft_params(struct ttc_params *ttc_params);
+void mlx5e_set_inner_ttc_ft_params(struct ttc_params *ttc_params);
+
+int mlx5e_create_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
+			   struct mlx5e_ttc_table *ttc);
+void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv,
+			     struct mlx5e_ttc_table *ttc);
+
+int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
+				 struct mlx5e_ttc_table *ttc);
+void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv,
+				   struct mlx5e_ttc_table *ttc);
+
+void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft);
+
+void mlx5e_enable_cvlan_filter(struct mlx5e_priv *priv);
+void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv);
+
+int mlx5e_create_flow_steering(struct mlx5e_priv *priv);
+void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv);
+
+#endif /* __MLX5E_FLOW_STEER_H__ */
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
new file mode 100644
index 000000000000..ad6d471d00dd
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -0,0 +1,307 @@
+/*
+ * Copyright (c) 2018, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/bpf_trace.h>
+#include "en/xdp.h"
+
+static inline bool
+mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_dma_info *di,
+		    struct xdp_buff *xdp)
+{
+	struct mlx5e_xdp_info xdpi;
+
+	xdpi.xdpf = convert_to_xdp_frame(xdp);
+	if (unlikely(!xdpi.xdpf))
+		return false;
+	xdpi.dma_addr = di->addr + (xdpi.xdpf->data - (void *)xdpi.xdpf);
+	dma_sync_single_for_device(sq->pdev, xdpi.dma_addr,
+				   xdpi.xdpf->len, PCI_DMA_TODEVICE);
+	xdpi.di = *di;
+
+	return mlx5e_xmit_xdp_frame(sq, &xdpi);
+}
+
+/* returns true if packet was consumed by xdp */
+bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
+		      void *va, u16 *rx_headroom, u32 *len)
+{
+	struct bpf_prog *prog = READ_ONCE(rq->xdp_prog);
+	struct xdp_buff xdp;
+	u32 act;
+	int err;
+
+	if (!prog)
+		return false;
+
+	xdp.data = va + *rx_headroom;
+	xdp_set_data_meta_invalid(&xdp);
+	xdp.data_end = xdp.data + *len;
+	xdp.data_hard_start = va;
+	xdp.rxq = &rq->xdp_rxq;
+
+	act = bpf_prog_run_xdp(prog, &xdp);
+	switch (act) {
+	case XDP_PASS:
+		*rx_headroom = xdp.data - xdp.data_hard_start;
+		*len = xdp.data_end - xdp.data;
+		return false;
+	case XDP_TX:
+		if (unlikely(!mlx5e_xmit_xdp_buff(&rq->xdpsq, di, &xdp)))
+			goto xdp_abort;
+		__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */
+		return true;
+	case XDP_REDIRECT:
+		/* When XDP enabled then page-refcnt==1 here */
+		err = xdp_do_redirect(rq->netdev, &xdp, prog);
+		if (unlikely(err))
+			goto xdp_abort;
+		__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags);
+		rq->xdpsq.redirect_flush = true;
+		mlx5e_page_dma_unmap(rq, di);
+		rq->stats->xdp_redirect++;
+		return true;
+	default:
+		bpf_warn_invalid_xdp_action(act);
+		/* fall through */
+	case XDP_ABORTED:
+xdp_abort:
+		trace_xdp_exception(rq->netdev, prog, act);
+		/* fall through */
+	case XDP_DROP:
+		rq->stats->xdp_drop++;
+		return true;
+	}
+}
+
+bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
+{
+	struct mlx5_wq_cyc       *wq   = &sq->wq;
+	u16                       pi   = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
+
+	struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
+	struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
+	struct mlx5_wqe_data_seg *dseg = wqe->data;
+
+	struct xdp_frame *xdpf = xdpi->xdpf;
+	dma_addr_t dma_addr  = xdpi->dma_addr;
+	unsigned int dma_len = xdpf->len;
+
+	struct mlx5e_xdpsq_stats *stats = sq->stats;
+
+	prefetchw(wqe);
+
+	if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE || sq->hw_mtu < dma_len)) {
+		stats->err++;
+		return false;
+	}
+
+	if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1))) {
+		if (sq->doorbell) {
+			/* SQ is full, ring doorbell */
+			mlx5e_xmit_xdp_doorbell(sq);
+			sq->doorbell = false;
+		}
+		stats->full++;
+		return false;
+	}
+
+	cseg->fm_ce_se = 0;
+
+	/* copy the inline part if required */
+	if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
+		memcpy(eseg->inline_hdr.start, xdpf->data, MLX5E_XDP_MIN_INLINE);
+		eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE);
+		dma_len  -= MLX5E_XDP_MIN_INLINE;
+		dma_addr += MLX5E_XDP_MIN_INLINE;
+		dseg++;
+	}
+
+	/* write the dma part */
+	dseg->addr       = cpu_to_be64(dma_addr);
+	dseg->byte_count = cpu_to_be32(dma_len);
+
+	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_SEND);
+
+	/* move page to reference to sq responsibility,
+	 * and mark so it's not put back in page-cache.
+	 */
+	sq->db.xdpi[pi] = *xdpi;
+	sq->pc++;
+
+	sq->doorbell = true;
+
+	stats->xmit++;
+	return true;
+}
+
+bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
+{
+	struct mlx5e_xdpsq *sq;
+	struct mlx5_cqe64 *cqe;
+	struct mlx5e_rq *rq;
+	bool is_redirect;
+	u16 sqcc;
+	int i;
+
+	sq = container_of(cq, struct mlx5e_xdpsq, cq);
+
+	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
+		return false;
+
+	cqe = mlx5_cqwq_get_cqe(&cq->wq);
+	if (!cqe)
+		return false;
+
+	is_redirect = test_bit(MLX5E_SQ_STATE_REDIRECT, &sq->state);
+	rq = container_of(sq, struct mlx5e_rq, xdpsq);
+
+	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
+	 * otherwise a cq overrun may occur
+	 */
+	sqcc = sq->cc;
+
+	i = 0;
+	do {
+		u16 wqe_counter;
+		bool last_wqe;
+
+		mlx5_cqwq_pop(&cq->wq);
+
+		wqe_counter = be16_to_cpu(cqe->wqe_counter);
+
+		do {
+			u16 ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
+			struct mlx5e_xdp_info *xdpi = &sq->db.xdpi[ci];
+
+			last_wqe = (sqcc == wqe_counter);
+			sqcc++;
+
+			if (is_redirect) {
+				xdp_return_frame(xdpi->xdpf);
+				dma_unmap_single(sq->pdev, xdpi->dma_addr,
+						 xdpi->xdpf->len, DMA_TO_DEVICE);
+			} else {
+				/* Recycle RX page */
+				mlx5e_page_release(rq, &xdpi->di, true);
+			}
+		} while (!last_wqe);
+	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
+
+	sq->stats->cqes += i;
+
+	mlx5_cqwq_update_db_record(&cq->wq);
+
+	/* ensure cq space is freed before enabling more cqes */
+	wmb();
+
+	sq->cc = sqcc;
+	return (i == MLX5E_TX_CQ_POLL_BUDGET);
+}
+
+void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
+{
+	struct mlx5e_rq *rq;
+	bool is_redirect;
+
+	is_redirect = test_bit(MLX5E_SQ_STATE_REDIRECT, &sq->state);
+	rq = is_redirect ? NULL : container_of(sq, struct mlx5e_rq, xdpsq);
+
+	while (sq->cc != sq->pc) {
+		u16 ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc);
+		struct mlx5e_xdp_info *xdpi = &sq->db.xdpi[ci];
+
+		sq->cc++;
+
+		if (is_redirect) {
+			xdp_return_frame(xdpi->xdpf);
+			dma_unmap_single(sq->pdev, xdpi->dma_addr,
+					 xdpi->xdpf->len, DMA_TO_DEVICE);
+		} else {
+			/* Recycle RX page */
+			mlx5e_page_release(rq, &xdpi->di, false);
+		}
+	}
+}
+
+int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
+		   u32 flags)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_xdpsq *sq;
+	int drops = 0;
+	int sq_num;
+	int i;
+
+	if (unlikely(!test_bit(MLX5E_STATE_OPENED, &priv->state)))
+		return -ENETDOWN;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	sq_num = smp_processor_id();
+
+	if (unlikely(sq_num >= priv->channels.num))
+		return -ENXIO;
+
+	sq = &priv->channels.c[sq_num]->xdpsq;
+
+	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
+		return -ENETDOWN;
+
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *xdpf = frames[i];
+		struct mlx5e_xdp_info xdpi;
+
+		xdpi.dma_addr = dma_map_single(sq->pdev, xdpf->data, xdpf->len,
+					       DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(sq->pdev, xdpi.dma_addr))) {
+			xdp_return_frame_rx_napi(xdpf);
+			drops++;
+			continue;
+		}
+
+		xdpi.xdpf = xdpf;
+
+		if (unlikely(!mlx5e_xmit_xdp_frame(sq, &xdpi))) {
+			dma_unmap_single(sq->pdev, xdpi.dma_addr,
+					 xdpf->len, DMA_TO_DEVICE);
+			xdp_return_frame_rx_napi(xdpf);
+			drops++;
+		}
+	}
+
+	if (flags & XDP_XMIT_FLUSH)
+		mlx5e_xmit_xdp_doorbell(sq);
+
+	return n - drops;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
new file mode 100644
index 000000000000..6dfab045925f
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -0,0 +1,63 @@
+/*
+ * Copyright (c) 2018, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef __MLX5_EN_XDP_H__
+#define __MLX5_EN_XDP_H__
+
+#include "en.h"
+
+#define MLX5E_XDP_MAX_MTU ((int)(PAGE_SIZE - \
+				 MLX5_SKB_FRAG_SZ(XDP_PACKET_HEADROOM)))
+#define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
+#define MLX5E_XDP_TX_DS_COUNT \
+	((sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) + 1 /* SG DS */)
+
+bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
+		      void *va, u16 *rx_headroom, u32 *len);
+bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq);
+void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq);
+
+bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi);
+int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
+		   u32 flags);
+
+static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
+{
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	struct mlx5e_tx_wqe *wqe;
+	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc - 1); /* last pi */
+
+	wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
+
+	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &wqe->ctrl);
+}
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index f20074dbef32..1dd225380a66 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -34,19 +34,26 @@
 #ifndef __MLX5E_EN_ACCEL_H__
 #define __MLX5E_EN_ACCEL_H__
 
-#ifdef CONFIG_MLX5_ACCEL
-
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include "en_accel/ipsec_rxtx.h"
 #include "en_accel/tls_rxtx.h"
 #include "en.h"
 
-static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb,
-						    struct mlx5e_txqsq *sq,
-						    struct net_device *dev,
-						    struct mlx5e_tx_wqe **wqe,
-						    u16 *pi)
+static inline void
+mlx5e_udp_gso_handle_tx_skb(struct sk_buff *skb)
+{
+	int payload_len = skb_shinfo(skb)->gso_size + sizeof(struct udphdr);
+
+	udp_hdr(skb)->len = htons(payload_len);
+}
+
+static inline struct sk_buff *
+mlx5e_accel_handle_tx(struct sk_buff *skb,
+		      struct mlx5e_txqsq *sq,
+		      struct net_device *dev,
+		      struct mlx5e_tx_wqe **wqe,
+		      u16 *pi)
 {
 #ifdef CONFIG_MLX5_EN_TLS
 	if (test_bit(MLX5E_SQ_STATE_TLS, &sq->state)) {
@@ -64,9 +71,10 @@ static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb,
 	}
 #endif
 
+	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
+		mlx5e_udp_gso_handle_tx_skb(skb);
+
 	return skb;
 }
 
-#endif /* CONFIG_MLX5_ACCEL */
-
 #endif /* __MLX5E_EN_ACCEL_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index c245d8e78509..128a82b1dbfc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -37,6 +37,7 @@
 
 #include "en_accel/ipsec_rxtx.h"
 #include "en_accel/ipsec.h"
+#include "accel/accel.h"
 #include "en.h"
 
 enum {
@@ -346,19 +347,12 @@ mlx5e_ipsec_build_sp(struct net_device *netdev, struct sk_buff *skb,
 }
 
 struct sk_buff *mlx5e_ipsec_handle_rx_skb(struct net_device *netdev,
-					  struct sk_buff *skb)
+					  struct sk_buff *skb, u32 *cqe_bcnt)
 {
 	struct mlx5e_ipsec_metadata *mdata;
-	struct ethhdr *old_eth;
-	struct ethhdr *new_eth;
 	struct xfrm_state *xs;
-	__be16 *ethtype;
 
-	/* Detect inline metadata */
-	if (skb->len < ETH_HLEN + MLX5E_METADATA_ETHER_LEN)
-		return skb;
-	ethtype = (__be16 *)(skb->data + ETH_ALEN * 2);
-	if (*ethtype != cpu_to_be16(MLX5E_METADATA_ETHER_TYPE))
+	if (!is_metadata_hdr_valid(skb))
 		return skb;
 
 	/* Use the metadata */
@@ -369,12 +363,8 @@ struct sk_buff *mlx5e_ipsec_handle_rx_skb(struct net_device *netdev,
 		return NULL;
 	}
 
-	/* Remove the metadata from the buffer */
-	old_eth = (struct ethhdr *)skb->data;
-	new_eth = (struct ethhdr *)(skb->data + MLX5E_METADATA_ETHER_LEN);
-	memmove(new_eth, old_eth, 2 * ETH_ALEN);
-	/* Ethertype is already in its new place */
-	skb_pull_inline(skb, MLX5E_METADATA_ETHER_LEN);
+	remove_metadata_hdr(skb);
+	*cqe_bcnt -= MLX5E_METADATA_ETHER_LEN;
 
 	return skb;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
index 2bfbbef1b054..ca47c0540904 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
@@ -41,7 +41,7 @@
 #include "en.h"
 
 struct sk_buff *mlx5e_ipsec_handle_rx_skb(struct net_device *netdev,
-					  struct sk_buff *skb);
+					  struct sk_buff *skb, u32 *cqe_bcnt);
 void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 
 void mlx5e_ipsec_inverse_table_init(void);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
index d167845271c3..eddd7702680b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
@@ -110,9 +110,7 @@ static int mlx5e_tls_add(struct net_device *netdev, struct sock *sk,
 	u32 caps = mlx5_accel_tls_device_caps(mdev);
 	int ret = -ENOMEM;
 	void *flow;
-
-	if (direction != TLS_OFFLOAD_CTX_DIR_TX)
-		return -EINVAL;
+	u32 swid;
 
 	flow = kzalloc(MLX5_ST_SZ_BYTES(tls_flow), GFP_KERNEL);
 	if (!flow)
@@ -122,18 +120,23 @@ static int mlx5e_tls_add(struct net_device *netdev, struct sock *sk,
 	if (ret)
 		goto free_flow;
 
+	ret = mlx5_accel_tls_add_flow(mdev, flow, crypto_info,
+				      start_offload_tcp_sn, &swid,
+				      direction == TLS_OFFLOAD_CTX_DIR_TX);
+	if (ret < 0)
+		goto free_flow;
+
 	if (direction == TLS_OFFLOAD_CTX_DIR_TX) {
-		struct mlx5e_tls_offload_context *tx_ctx =
+		struct mlx5e_tls_offload_context_tx *tx_ctx =
 		    mlx5e_get_tls_tx_context(tls_ctx);
-		u32 swid;
-
-		ret = mlx5_accel_tls_add_tx_flow(mdev, flow, crypto_info,
-						 start_offload_tcp_sn, &swid);
-		if (ret < 0)
-			goto free_flow;
 
 		tx_ctx->swid = htonl(swid);
 		tx_ctx->expected_seq = start_offload_tcp_sn;
+	} else {
+		struct mlx5e_tls_offload_context_rx *rx_ctx =
+		    mlx5e_get_tls_rx_context(tls_ctx);
+
+		rx_ctx->handle = htonl(swid);
 	}
 
 	return 0;
@@ -147,30 +150,60 @@ static void mlx5e_tls_del(struct net_device *netdev,
 			  enum tls_offload_ctx_dir direction)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	unsigned int handle;
 
-	if (direction == TLS_OFFLOAD_CTX_DIR_TX) {
-		u32 swid = ntohl(mlx5e_get_tls_tx_context(tls_ctx)->swid);
+	handle = ntohl((direction == TLS_OFFLOAD_CTX_DIR_TX) ?
+		       mlx5e_get_tls_tx_context(tls_ctx)->swid :
+		       mlx5e_get_tls_rx_context(tls_ctx)->handle);
 
-		mlx5_accel_tls_del_tx_flow(priv->mdev, swid);
-	} else {
-		netdev_err(netdev, "unsupported direction %d\n", direction);
-	}
+	mlx5_accel_tls_del_flow(priv->mdev, handle,
+				direction == TLS_OFFLOAD_CTX_DIR_TX);
+}
+
+static void mlx5e_tls_resync_rx(struct net_device *netdev, struct sock *sk,
+				u32 seq, u64 rcd_sn)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_tls_offload_context_rx *rx_ctx;
+
+	rx_ctx = mlx5e_get_tls_rx_context(tls_ctx);
+
+	netdev_info(netdev, "resyncing seq %d rcd %lld\n", seq,
+		    be64_to_cpu(rcd_sn));
+	mlx5_accel_tls_resync_rx(priv->mdev, rx_ctx->handle, seq, rcd_sn);
+	atomic64_inc(&priv->tls->sw_stats.rx_tls_resync_reply);
 }
 
 static const struct tlsdev_ops mlx5e_tls_ops = {
 	.tls_dev_add = mlx5e_tls_add,
 	.tls_dev_del = mlx5e_tls_del,
+	.tls_dev_resync_rx = mlx5e_tls_resync_rx,
 };
 
 void mlx5e_tls_build_netdev(struct mlx5e_priv *priv)
 {
+	u32 caps = mlx5_accel_tls_device_caps(priv->mdev);
 	struct net_device *netdev = priv->netdev;
 
 	if (!mlx5_accel_is_tls_device(priv->mdev))
 		return;
 
-	netdev->features |= NETIF_F_HW_TLS_TX;
-	netdev->hw_features |= NETIF_F_HW_TLS_TX;
+	if (caps & MLX5_ACCEL_TLS_TX) {
+		netdev->features          |= NETIF_F_HW_TLS_TX;
+		netdev->hw_features       |= NETIF_F_HW_TLS_TX;
+	}
+
+	if (caps & MLX5_ACCEL_TLS_RX) {
+		netdev->features          |= NETIF_F_HW_TLS_RX;
+		netdev->hw_features       |= NETIF_F_HW_TLS_RX;
+	}
+
+	if (!(caps & MLX5_ACCEL_TLS_LRO)) {
+		netdev->features          &= ~NETIF_F_LRO;
+		netdev->hw_features       &= ~NETIF_F_LRO;
+	}
+
 	netdev->tlsdev_ops = &mlx5e_tls_ops;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
index b6162178f621..3f5d72163b56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
@@ -43,25 +43,44 @@ struct mlx5e_tls_sw_stats {
 	atomic64_t tx_tls_drop_resync_alloc;
 	atomic64_t tx_tls_drop_no_sync_data;
 	atomic64_t tx_tls_drop_bypass_required;
+	atomic64_t rx_tls_drop_resync_request;
+	atomic64_t rx_tls_resync_request;
+	atomic64_t rx_tls_resync_reply;
+	atomic64_t rx_tls_auth_fail;
 };
 
 struct mlx5e_tls {
 	struct mlx5e_tls_sw_stats sw_stats;
 };
 
-struct mlx5e_tls_offload_context {
-	struct tls_offload_context base;
+struct mlx5e_tls_offload_context_tx {
+	struct tls_offload_context_tx base;
 	u32 expected_seq;
 	__be32 swid;
 };
 
-static inline struct mlx5e_tls_offload_context *
+static inline struct mlx5e_tls_offload_context_tx *
 mlx5e_get_tls_tx_context(struct tls_context *tls_ctx)
 {
-	BUILD_BUG_ON(sizeof(struct mlx5e_tls_offload_context) >
-		     TLS_OFFLOAD_CONTEXT_SIZE);
-	return container_of(tls_offload_ctx(tls_ctx),
-			    struct mlx5e_tls_offload_context,
+	BUILD_BUG_ON(sizeof(struct mlx5e_tls_offload_context_tx) >
+		     TLS_OFFLOAD_CONTEXT_SIZE_TX);
+	return container_of(tls_offload_ctx_tx(tls_ctx),
+			    struct mlx5e_tls_offload_context_tx,
+			    base);
+}
+
+struct mlx5e_tls_offload_context_rx {
+	struct tls_offload_context_rx base;
+	__be32 handle;
+};
+
+static inline struct mlx5e_tls_offload_context_rx *
+mlx5e_get_tls_rx_context(struct tls_context *tls_ctx)
+{
+	BUILD_BUG_ON(sizeof(struct mlx5e_tls_offload_context_rx) >
+		     TLS_OFFLOAD_CONTEXT_SIZE_RX);
+	return container_of(tls_offload_ctx_rx(tls_ctx),
+			    struct mlx5e_tls_offload_context_rx,
 			    base);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
index 15aef71d1957..be137d4a9169 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
@@ -33,6 +33,14 @@
 
 #include "en_accel/tls.h"
 #include "en_accel/tls_rxtx.h"
+#include "accel/accel.h"
+
+#include <net/inet6_hashtables.h>
+#include <linux/ipv6.h>
+
+#define SYNDROM_DECRYPTED  0x30
+#define SYNDROM_RESYNC_REQUEST 0x31
+#define SYNDROM_AUTH_FAILED 0x32
 
 #define SYNDROME_OFFLOAD_REQUIRED 32
 #define SYNDROME_SYNC 33
@@ -44,10 +52,26 @@ struct sync_info {
 	skb_frag_t frags[MAX_SKB_FRAGS];
 };
 
-struct mlx5e_tls_metadata {
+struct recv_metadata_content {
+	u8 syndrome;
+	u8 reserved;
+	__be32 sync_seq;
+} __packed;
+
+struct send_metadata_content {
 	/* One byte of syndrome followed by 3 bytes of swid */
 	__be32 syndrome_swid;
 	__be16 first_seq;
+} __packed;
+
+struct mlx5e_tls_metadata {
+	union {
+		/* from fpga to host */
+		struct recv_metadata_content recv;
+		/* from host to fpga */
+		struct send_metadata_content send;
+		unsigned char raw[6];
+	} __packed content;
 	/* packet type ID field	*/
 	__be16 ethertype;
 } __packed;
@@ -68,12 +92,13 @@ static int mlx5e_tls_add_metadata(struct sk_buff *skb, __be32 swid)
 		2 * ETH_ALEN);
 
 	eth->h_proto = cpu_to_be16(MLX5E_METADATA_ETHER_TYPE);
-	pet->syndrome_swid = htonl(SYNDROME_OFFLOAD_REQUIRED << 24) | swid;
+	pet->content.send.syndrome_swid =
+		htonl(SYNDROME_OFFLOAD_REQUIRED << 24) | swid;
 
 	return 0;
 }
 
-static int mlx5e_tls_get_sync_data(struct mlx5e_tls_offload_context *context,
+static int mlx5e_tls_get_sync_data(struct mlx5e_tls_offload_context_tx *context,
 				   u32 tcp_seq, struct sync_info *info)
 {
 	int remaining, i = 0, ret = -EINVAL;
@@ -149,7 +174,7 @@ static void mlx5e_tls_complete_sync_skb(struct sk_buff *skb,
 
 	pet = (struct mlx5e_tls_metadata *)(nskb->data + sizeof(struct ethhdr));
 	memcpy(pet, &syndrome, sizeof(syndrome));
-	pet->first_seq = htons(tcp_seq);
+	pet->content.send.first_seq = htons(tcp_seq);
 
 	/* MLX5 devices don't care about the checksum partial start, offset
 	 * and pseudo header
@@ -161,7 +186,7 @@ static void mlx5e_tls_complete_sync_skb(struct sk_buff *skb,
 }
 
 static struct sk_buff *
-mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context *context,
+mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context_tx *context,
 		     struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		     struct mlx5e_tx_wqe **wqe,
 		     u16 *pi,
@@ -239,7 +264,7 @@ struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev,
 					u16 *pi)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct mlx5e_tls_offload_context *context;
+	struct mlx5e_tls_offload_context_tx *context;
 	struct tls_context *tls_ctx;
 	u32 expected_seq;
 	int datalen;
@@ -276,3 +301,83 @@ struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev,
 out:
 	return skb;
 }
+
+static int tls_update_resync_sn(struct net_device *netdev,
+				struct sk_buff *skb,
+				struct mlx5e_tls_metadata *mdata)
+{
+	struct sock *sk = NULL;
+	struct iphdr *iph;
+	struct tcphdr *th;
+	__be32 seq;
+
+	if (mdata->ethertype != htons(ETH_P_IP))
+		return -EINVAL;
+
+	iph = (struct iphdr *)(mdata + 1);
+
+	th = ((void *)iph) + iph->ihl * 4;
+
+	if (iph->version == 4) {
+		sk = inet_lookup_established(dev_net(netdev), &tcp_hashinfo,
+					     iph->saddr, th->source, iph->daddr,
+					     th->dest, netdev->ifindex);
+#if IS_ENABLED(CONFIG_IPV6)
+	} else {
+		struct ipv6hdr *ipv6h = (struct ipv6hdr *)iph;
+
+		sk = __inet6_lookup_established(dev_net(netdev), &tcp_hashinfo,
+						&ipv6h->saddr, th->source,
+						&ipv6h->daddr, ntohs(th->dest),
+						netdev->ifindex, 0);
+#endif
+	}
+	if (!sk || sk->sk_state == TCP_TIME_WAIT) {
+		struct mlx5e_priv *priv = netdev_priv(netdev);
+
+		atomic64_inc(&priv->tls->sw_stats.rx_tls_drop_resync_request);
+		goto out;
+	}
+
+	skb->sk = sk;
+	skb->destructor = sock_edemux;
+
+	memcpy(&seq, &mdata->content.recv.sync_seq, sizeof(seq));
+	tls_offload_rx_resync_request(sk, seq);
+out:
+	return 0;
+}
+
+void mlx5e_tls_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
+			     u32 *cqe_bcnt)
+{
+	struct mlx5e_tls_metadata *mdata;
+	struct mlx5e_priv *priv;
+
+	if (!is_metadata_hdr_valid(skb))
+		return;
+
+	/* Use the metadata */
+	mdata = (struct mlx5e_tls_metadata *)(skb->data + ETH_HLEN);
+	switch (mdata->content.recv.syndrome) {
+	case SYNDROM_DECRYPTED:
+		skb->decrypted = 1;
+		break;
+	case SYNDROM_RESYNC_REQUEST:
+		tls_update_resync_sn(netdev, skb, mdata);
+		priv = netdev_priv(netdev);
+		atomic64_inc(&priv->tls->sw_stats.rx_tls_resync_request);
+		break;
+	case SYNDROM_AUTH_FAILED:
+		/* Authentication failure will be observed and verified by kTLS */
+		priv = netdev_priv(netdev);
+		atomic64_inc(&priv->tls->sw_stats.rx_tls_auth_fail);
+		break;
+	default:
+		/* Bypass the metadata header to others */
+		return;
+	}
+
+	remove_metadata_hdr(skb);
+	*cqe_bcnt -= MLX5E_METADATA_ETHER_LEN;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
index 405dfd302225..311667ec71b8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
@@ -45,6 +45,9 @@ struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev,
 					struct mlx5e_tx_wqe **wqe,
 					u16 *pi);
 
+void mlx5e_tls_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
+			     u32 *cqe_bcnt);
+
 #endif /* CONFIG_MLX5_EN_TLS */
 
 #endif /* __MLX5E_TLS_RXTX_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index d258bb679271..45cdde694d20 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -30,8 +30,6 @@
  * SOFTWARE.
  */
 
-#ifdef CONFIG_RFS_ACCEL
-
 #include <linux/hash.h>
 #include <linux/mlx5/fs.h>
 #include <linux/ip.h>
@@ -738,4 +736,4 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	spin_unlock_bh(&arfs->arfs_lock);
 	return arfs_rule->filter_id;
 }
-#endif
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index fffe514ba855..98dd3e0ada72 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -32,6 +32,7 @@
 
 #include "en.h"
 #include "en/port.h"
+#include "lib/clock.h"
 
 void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
 			       struct ethtool_drvinfo *drvinfo)
@@ -969,33 +970,6 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 	return 0;
 }
 
-static int mlx5e_get_rxnfc(struct net_device *netdev,
-			   struct ethtool_rxnfc *info, u32 *rule_locs)
-{
-	struct mlx5e_priv *priv = netdev_priv(netdev);
-	int err = 0;
-
-	switch (info->cmd) {
-	case ETHTOOL_GRXRINGS:
-		info->data = priv->channels.params.num_channels;
-		break;
-	case ETHTOOL_GRXCLSRLCNT:
-		info->rule_cnt = priv->fs.ethtool.tot_num_rules;
-		break;
-	case ETHTOOL_GRXCLSRULE:
-		err = mlx5e_ethtool_get_flow(priv, info, info->fs.location);
-		break;
-	case ETHTOOL_GRXCLSRLALL:
-		err = mlx5e_ethtool_get_all_flows(priv, info, rule_locs);
-		break;
-	default:
-		err = -EOPNOTSUPP;
-		break;
-	}
-
-	return err;
-}
-
 #define MLX5E_PFC_PREVEN_AUTO_TOUT_MSEC		100
 #define MLX5E_PFC_PREVEN_TOUT_MAX_MSEC		8000
 #define MLX5E_PFC_PREVEN_MINOR_PRECENT		85
@@ -1133,10 +1107,10 @@ int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
 	if (ret)
 		return ret;
 
-	info->phc_index = mdev->clock.ptp ?
-			  ptp_clock_index(mdev->clock.ptp) : -1;
+	info->phc_index = mlx5_clock_get_ptp_index(mdev);
 
-	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz))
+	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz) ||
+	    info->phc_index == -1)
 		return 0;
 
 	info->so_timestamping |= SOF_TIMESTAMPING_TX_HARDWARE |
@@ -1606,26 +1580,6 @@ static u32 mlx5e_get_priv_flags(struct net_device *netdev)
 	return priv->channels.params.pflags;
 }
 
-static int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
-{
-	int err = 0;
-	struct mlx5e_priv *priv = netdev_priv(dev);
-
-	switch (cmd->cmd) {
-	case ETHTOOL_SRXCLSRLINS:
-		err = mlx5e_ethtool_flow_replace(priv, &cmd->fs);
-		break;
-	case ETHTOOL_SRXCLSRLDEL:
-		err = mlx5e_ethtool_flow_remove(priv, cmd->fs.location);
-		break;
-	default:
-		err = -EOPNOTSUPP;
-		break;
-	}
-
-	return err;
-}
-
 int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv,
 			       struct ethtool_flash *flash)
 {
@@ -1678,8 +1632,10 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
 	.get_rxfh_indir_size = mlx5e_get_rxfh_indir_size,
 	.get_rxfh          = mlx5e_get_rxfh,
 	.set_rxfh          = mlx5e_set_rxfh,
+#ifdef CONFIG_MLX5_EN_RXNFC
 	.get_rxnfc         = mlx5e_get_rxnfc,
 	.set_rxnfc         = mlx5e_set_rxnfc,
+#endif
 	.flash_device      = mlx5e_flash_device,
 	.get_tunable       = mlx5e_get_tunable,
 	.set_tunable       = mlx5e_set_tunable,
@@ -1696,5 +1652,4 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
 	.self_test         = mlx5e_self_test,
 	.get_msglevel      = mlx5e_get_msglevel,
 	.set_msglevel      = mlx5e_set_msglevel,
-
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index eafc59280ada..75bb981e00b7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -66,11 +66,14 @@ static struct mlx5e_ethtool_table *get_flow_table(struct mlx5e_priv *priv,
 	switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
 		max_tuples = ETHTOOL_NUM_L3_L4_FTS;
 		prio = MLX5E_ETHTOOL_L3_L4_PRIO + (max_tuples - num_tuples);
 		eth_ft = &priv->fs.ethtool.l3_l4_ft[prio];
 		break;
 	case IP_USER_FLOW:
+	case IPV6_USER_FLOW:
 		max_tuples = ETHTOOL_NUM_L3_L4_FTS;
 		prio = MLX5E_ETHTOOL_L3_L4_PRIO + (max_tuples - num_tuples);
 		eth_ft = &priv->fs.ethtool.l3_l4_ft[prio];
@@ -115,29 +118,203 @@ static void mask_spec(u8 *mask, u8 *val, size_t size)
 		*((u8 *)val) = *((u8 *)mask) & *((u8 *)val);
 }
 
-static void set_ips(void *outer_headers_v, void *outer_headers_c, __be32 ip4src_m,
-		    __be32 ip4src_v, __be32 ip4dst_m, __be32 ip4dst_v)
+#define MLX5E_FTE_SET(header_p, fld, v)  \
+	MLX5_SET(fte_match_set_lyr_2_4, header_p, fld, v)
+
+#define MLX5E_FTE_ADDR_OF(header_p, fld) \
+	MLX5_ADDR_OF(fte_match_set_lyr_2_4, header_p, fld)
+
+static void
+set_ip4(void *headers_c, void *headers_v, __be32 ip4src_m,
+	__be32 ip4src_v, __be32 ip4dst_m, __be32 ip4dst_v)
 {
 	if (ip4src_m) {
-		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_v,
-				    src_ipv4_src_ipv6.ipv4_layout.ipv4),
+		memcpy(MLX5E_FTE_ADDR_OF(headers_v, src_ipv4_src_ipv6.ipv4_layout.ipv4),
 		       &ip4src_v, sizeof(ip4src_v));
-		memset(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_c,
-				    src_ipv4_src_ipv6.ipv4_layout.ipv4),
+		memset(MLX5E_FTE_ADDR_OF(headers_c, src_ipv4_src_ipv6.ipv4_layout.ipv4),
 		       0xff, sizeof(ip4src_m));
 	}
 	if (ip4dst_m) {
-		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_v,
-				    dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
+		memcpy(MLX5E_FTE_ADDR_OF(headers_v, dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
 		       &ip4dst_v, sizeof(ip4dst_v));
-		memset(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_c,
-				    dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
+		memset(MLX5E_FTE_ADDR_OF(headers_c, dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
 		       0xff, sizeof(ip4dst_m));
 	}
-	MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
-		 ethertype, ETH_P_IP);
-	MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
-		 ethertype, 0xffff);
+
+	MLX5E_FTE_SET(headers_c, ethertype, 0xffff);
+	MLX5E_FTE_SET(headers_v, ethertype, ETH_P_IP);
+}
+
+static void
+set_ip6(void *headers_c, void *headers_v, __be32 ip6src_m[4],
+	__be32 ip6src_v[4], __be32 ip6dst_m[4], __be32 ip6dst_v[4])
+{
+	u8 ip6_sz = MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6);
+
+	if (!ipv6_addr_any((struct in6_addr *)ip6src_m)) {
+		memcpy(MLX5E_FTE_ADDR_OF(headers_v, src_ipv4_src_ipv6.ipv6_layout.ipv6),
+		       ip6src_v, ip6_sz);
+		memcpy(MLX5E_FTE_ADDR_OF(headers_c, src_ipv4_src_ipv6.ipv6_layout.ipv6),
+		       ip6src_m, ip6_sz);
+	}
+	if (!ipv6_addr_any((struct in6_addr *)ip6dst_m)) {
+		memcpy(MLX5E_FTE_ADDR_OF(headers_v, dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
+		       ip6dst_v, ip6_sz);
+		memcpy(MLX5E_FTE_ADDR_OF(headers_c, dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
+		       ip6dst_m, ip6_sz);
+	}
+
+	MLX5E_FTE_SET(headers_c, ethertype, 0xffff);
+	MLX5E_FTE_SET(headers_v, ethertype, ETH_P_IPV6);
+}
+
+static void
+set_tcp(void *headers_c, void *headers_v, __be16 psrc_m, __be16 psrc_v,
+	__be16 pdst_m, __be16 pdst_v)
+{
+	if (psrc_m) {
+		MLX5E_FTE_SET(headers_c, tcp_sport, 0xffff);
+		MLX5E_FTE_SET(headers_v, tcp_sport, ntohs(psrc_v));
+	}
+	if (pdst_m) {
+		MLX5E_FTE_SET(headers_c, tcp_dport, 0xffff);
+		MLX5E_FTE_SET(headers_v, tcp_dport, ntohs(pdst_v));
+	}
+
+	MLX5E_FTE_SET(headers_c, ip_protocol, 0xffff);
+	MLX5E_FTE_SET(headers_v, ip_protocol, IPPROTO_TCP);
+}
+
+static void
+set_udp(void *headers_c, void *headers_v, __be16 psrc_m, __be16 psrc_v,
+	__be16 pdst_m, __be16 pdst_v)
+{
+	if (psrc_m) {
+		MLX5E_FTE_SET(headers_c, udp_sport, 0xffff);
+		MLX5E_FTE_SET(headers_c, udp_sport, ntohs(psrc_v));
+	}
+
+	if (pdst_m) {
+		MLX5E_FTE_SET(headers_c, udp_dport, 0xffff);
+		MLX5E_FTE_SET(headers_v, udp_dport, ntohs(pdst_v));
+	}
+
+	MLX5E_FTE_SET(headers_c, ip_protocol, 0xffff);
+	MLX5E_FTE_SET(headers_v, ip_protocol, IPPROTO_UDP);
+}
+
+static void
+parse_tcp4(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip4_spec *l4_mask = &fs->m_u.tcp_ip4_spec;
+	struct ethtool_tcpip4_spec *l4_val  = &fs->h_u.tcp_ip4_spec;
+
+	set_ip4(headers_c, headers_v, l4_mask->ip4src, l4_val->ip4src,
+		l4_mask->ip4dst, l4_val->ip4dst);
+
+	set_tcp(headers_c, headers_v, l4_mask->psrc, l4_val->psrc,
+		l4_mask->pdst, l4_val->pdst);
+}
+
+static void
+parse_udp4(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip4_spec *l4_mask = &fs->m_u.udp_ip4_spec;
+	struct ethtool_tcpip4_spec *l4_val  = &fs->h_u.udp_ip4_spec;
+
+	set_ip4(headers_c, headers_v, l4_mask->ip4src, l4_val->ip4src,
+		l4_mask->ip4dst, l4_val->ip4dst);
+
+	set_udp(headers_c, headers_v, l4_mask->psrc, l4_val->psrc,
+		l4_mask->pdst, l4_val->pdst);
+}
+
+static void
+parse_ip4(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_usrip4_spec *l3_mask = &fs->m_u.usr_ip4_spec;
+	struct ethtool_usrip4_spec *l3_val  = &fs->h_u.usr_ip4_spec;
+
+	set_ip4(headers_c, headers_v, l3_mask->ip4src, l3_val->ip4src,
+		l3_mask->ip4dst, l3_val->ip4dst);
+
+	if (l3_mask->proto) {
+		MLX5E_FTE_SET(headers_c, ip_protocol, l3_mask->proto);
+		MLX5E_FTE_SET(headers_v, ip_protocol, l3_val->proto);
+	}
+}
+
+static void
+parse_ip6(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_usrip6_spec *l3_mask = &fs->m_u.usr_ip6_spec;
+	struct ethtool_usrip6_spec *l3_val  = &fs->h_u.usr_ip6_spec;
+
+	set_ip6(headers_c, headers_v, l3_mask->ip6src,
+		l3_val->ip6src, l3_mask->ip6dst, l3_val->ip6dst);
+
+	if (l3_mask->l4_proto) {
+		MLX5E_FTE_SET(headers_c, ip_protocol, l3_mask->l4_proto);
+		MLX5E_FTE_SET(headers_v, ip_protocol, l3_val->l4_proto);
+	}
+}
+
+static void
+parse_tcp6(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip6_spec *l4_mask = &fs->m_u.tcp_ip6_spec;
+	struct ethtool_tcpip6_spec *l4_val  = &fs->h_u.tcp_ip6_spec;
+
+	set_ip6(headers_c, headers_v, l4_mask->ip6src,
+		l4_val->ip6src, l4_mask->ip6dst, l4_val->ip6dst);
+
+	set_tcp(headers_c, headers_v, l4_mask->psrc, l4_val->psrc,
+		l4_mask->pdst, l4_val->pdst);
+}
+
+static void
+parse_udp6(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip6_spec *l4_mask = &fs->m_u.udp_ip6_spec;
+	struct ethtool_tcpip6_spec *l4_val  = &fs->h_u.udp_ip6_spec;
+
+	set_ip6(headers_c, headers_v, l4_mask->ip6src,
+		l4_val->ip6src, l4_mask->ip6dst, l4_val->ip6dst);
+
+	set_udp(headers_c, headers_v, l4_mask->psrc, l4_val->psrc,
+		l4_mask->pdst, l4_val->pdst);
+}
+
+static void
+parse_ether(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethhdr *eth_mask = &fs->m_u.ether_spec;
+	struct ethhdr *eth_val = &fs->h_u.ether_spec;
+
+	mask_spec((u8 *)eth_mask, (u8 *)eth_val, sizeof(*eth_mask));
+	ether_addr_copy(MLX5E_FTE_ADDR_OF(headers_c, smac_47_16), eth_mask->h_source);
+	ether_addr_copy(MLX5E_FTE_ADDR_OF(headers_v, smac_47_16), eth_val->h_source);
+	ether_addr_copy(MLX5E_FTE_ADDR_OF(headers_c, dmac_47_16), eth_mask->h_dest);
+	ether_addr_copy(MLX5E_FTE_ADDR_OF(headers_v, dmac_47_16), eth_val->h_dest);
+	MLX5E_FTE_SET(headers_c, ethertype, ntohs(eth_mask->h_proto));
+	MLX5E_FTE_SET(headers_v, ethertype, ntohs(eth_val->h_proto));
+}
+
+static void
+set_cvlan(void *headers_c, void *headers_v, __be16 vlan_tci)
+{
+	MLX5E_FTE_SET(headers_c, cvlan_tag, 1);
+	MLX5E_FTE_SET(headers_v, cvlan_tag, 1);
+	MLX5E_FTE_SET(headers_c, first_vid, 0xfff);
+	MLX5E_FTE_SET(headers_v, first_vid, ntohs(vlan_tci));
+}
+
+static void
+set_dmac(void *headers_c, void *headers_v,
+	 unsigned char m_dest[ETH_ALEN], unsigned char v_dest[ETH_ALEN])
+{
+	ether_addr_copy(MLX5E_FTE_ADDR_OF(headers_c, dmac_47_16), m_dest);
+	ether_addr_copy(MLX5E_FTE_ADDR_OF(headers_v, dmac_47_16), v_dest);
 }
 
 static int set_flow_attrs(u32 *match_c, u32 *match_v,
@@ -148,112 +325,42 @@ static int set_flow_attrs(u32 *match_c, u32 *match_v,
 	void *outer_headers_v = MLX5_ADDR_OF(fte_match_param, match_v,
 					     outer_headers);
 	u32 flow_type = fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT);
-	struct ethtool_tcpip4_spec *l4_mask;
-	struct ethtool_tcpip4_spec *l4_val;
-	struct ethtool_usrip4_spec *l3_mask;
-	struct ethtool_usrip4_spec *l3_val;
-	struct ethhdr *eth_val;
-	struct ethhdr *eth_mask;
 
 	switch (flow_type) {
 	case TCP_V4_FLOW:
-		l4_mask = &fs->m_u.tcp_ip4_spec;
-		l4_val = &fs->h_u.tcp_ip4_spec;
-		set_ips(outer_headers_v, outer_headers_c, l4_mask->ip4src,
-			l4_val->ip4src, l4_mask->ip4dst, l4_val->ip4dst);
-
-		if (l4_mask->psrc) {
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, tcp_sport,
-				 0xffff);
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, tcp_sport,
-				 ntohs(l4_val->psrc));
-		}
-		if (l4_mask->pdst) {
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, tcp_dport,
-				 0xffff);
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, tcp_dport,
-				 ntohs(l4_val->pdst));
-		}
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, ip_protocol,
-			 0xffff);
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, ip_protocol,
-			 IPPROTO_TCP);
+		parse_tcp4(outer_headers_c, outer_headers_v, fs);
 		break;
 	case UDP_V4_FLOW:
-		l4_mask = &fs->m_u.tcp_ip4_spec;
-		l4_val = &fs->h_u.tcp_ip4_spec;
-		set_ips(outer_headers_v, outer_headers_c, l4_mask->ip4src,
-			l4_val->ip4src, l4_mask->ip4dst, l4_val->ip4dst);
-
-		if (l4_mask->psrc) {
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, udp_sport,
-				 0xffff);
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, udp_sport,
-				 ntohs(l4_val->psrc));
-		}
-		if (l4_mask->pdst) {
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, udp_dport,
-				 0xffff);
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, udp_dport,
-				 ntohs(l4_val->pdst));
-		}
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, ip_protocol,
-			 0xffff);
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, ip_protocol,
-			 IPPROTO_UDP);
+		parse_udp4(outer_headers_c, outer_headers_v, fs);
 		break;
 	case IP_USER_FLOW:
-		l3_mask = &fs->m_u.usr_ip4_spec;
-		l3_val = &fs->h_u.usr_ip4_spec;
-		set_ips(outer_headers_v, outer_headers_c, l3_mask->ip4src,
-			l3_val->ip4src, l3_mask->ip4dst, l3_val->ip4dst);
+		parse_ip4(outer_headers_c, outer_headers_v, fs);
+		break;
+	case TCP_V6_FLOW:
+		parse_tcp6(outer_headers_c, outer_headers_v, fs);
+		break;
+	case UDP_V6_FLOW:
+		parse_udp6(outer_headers_c, outer_headers_v, fs);
+		break;
+	case IPV6_USER_FLOW:
+		parse_ip6(outer_headers_c, outer_headers_v, fs);
 		break;
 	case ETHER_FLOW:
-		eth_mask = &fs->m_u.ether_spec;
-		eth_val = &fs->h_u.ether_spec;
-
-		mask_spec((u8 *)eth_mask, (u8 *)eth_val, sizeof(*eth_mask));
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-					     outer_headers_c, smac_47_16),
-				eth_mask->h_source);
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-					     outer_headers_v, smac_47_16),
-				eth_val->h_source);
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-					     outer_headers_c, dmac_47_16),
-				eth_mask->h_dest);
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-					     outer_headers_v, dmac_47_16),
-				eth_val->h_dest);
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, ethertype,
-			 ntohs(eth_mask->h_proto));
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, ethertype,
-			 ntohs(eth_val->h_proto));
+		parse_ether(outer_headers_c, outer_headers_v, fs);
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	if ((fs->flow_type & FLOW_EXT) &&
-	    (fs->m_ext.vlan_tci & cpu_to_be16(VLAN_VID_MASK))) {
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
-			 cvlan_tag, 1);
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
-			 cvlan_tag, 1);
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
-			 first_vid, 0xfff);
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
-			 first_vid, ntohs(fs->h_ext.vlan_tci));
-	}
+	    (fs->m_ext.vlan_tci & cpu_to_be16(VLAN_VID_MASK)))
+		set_cvlan(outer_headers_c, outer_headers_v, fs->h_ext.vlan_tci);
+
 	if (fs->flow_type & FLOW_MAC_EXT &&
 	    !is_zero_ether_addr(fs->m_ext.h_dest)) {
 		mask_spec(fs->m_ext.h_dest, fs->h_ext.h_dest, ETH_ALEN);
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-					     outer_headers_c, dmac_47_16),
-				fs->m_ext.h_dest);
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-					     outer_headers_v, dmac_47_16),
-				fs->h_ext.h_dest);
+		set_dmac(outer_headers_c, outer_headers_v, fs->m_ext.h_dest,
+			 fs->h_ext.h_dest);
 	}
 
 	return 0;
@@ -379,16 +486,143 @@ static struct mlx5e_ethtool_rule *get_ethtool_rule(struct mlx5e_priv *priv,
 #define all_zeros_or_all_ones(field)		\
 	((field) == 0 || (field) == (__force typeof(field))-1)
 
+static int validate_ethter(struct ethtool_rx_flow_spec *fs)
+{
+	struct ethhdr *eth_mask = &fs->m_u.ether_spec;
+	int ntuples = 0;
+
+	if (!is_zero_ether_addr(eth_mask->h_dest))
+		ntuples++;
+	if (!is_zero_ether_addr(eth_mask->h_source))
+		ntuples++;
+	if (eth_mask->h_proto)
+		ntuples++;
+	return ntuples;
+}
+
+static int validate_tcpudp4(struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip4_spec *l4_mask = &fs->m_u.tcp_ip4_spec;
+	int ntuples = 0;
+
+	if (l4_mask->tos)
+		return -EINVAL;
+
+	if (l4_mask->ip4src) {
+		if (!all_ones(l4_mask->ip4src))
+			return -EINVAL;
+		ntuples++;
+	}
+	if (l4_mask->ip4dst) {
+		if (!all_ones(l4_mask->ip4dst))
+			return -EINVAL;
+		ntuples++;
+	}
+	if (l4_mask->psrc) {
+		if (!all_ones(l4_mask->psrc))
+			return -EINVAL;
+		ntuples++;
+	}
+	if (l4_mask->pdst) {
+		if (!all_ones(l4_mask->pdst))
+			return -EINVAL;
+		ntuples++;
+	}
+	/* Flow is TCP/UDP */
+	return ++ntuples;
+}
+
+static int validate_ip4(struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_usrip4_spec *l3_mask = &fs->m_u.usr_ip4_spec;
+	int ntuples = 0;
+
+	if (l3_mask->l4_4_bytes || l3_mask->tos ||
+	    fs->h_u.usr_ip4_spec.ip_ver != ETH_RX_NFC_IP4)
+		return -EINVAL;
+	if (l3_mask->ip4src) {
+		if (!all_ones(l3_mask->ip4src))
+			return -EINVAL;
+		ntuples++;
+	}
+	if (l3_mask->ip4dst) {
+		if (!all_ones(l3_mask->ip4dst))
+			return -EINVAL;
+		ntuples++;
+	}
+	if (l3_mask->proto)
+		ntuples++;
+	/* Flow is IPv4 */
+	return ++ntuples;
+}
+
+static int validate_ip6(struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_usrip6_spec *l3_mask = &fs->m_u.usr_ip6_spec;
+	int ntuples = 0;
+
+	if (l3_mask->l4_4_bytes || l3_mask->tclass)
+		return -EINVAL;
+	if (!ipv6_addr_any((struct in6_addr *)l3_mask->ip6src))
+		ntuples++;
+
+	if (!ipv6_addr_any((struct in6_addr *)l3_mask->ip6dst))
+		ntuples++;
+	if (l3_mask->l4_proto)
+		ntuples++;
+	/* Flow is IPv6 */
+	return ++ntuples;
+}
+
+static int validate_tcpudp6(struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip6_spec *l4_mask = &fs->m_u.tcp_ip6_spec;
+	int ntuples = 0;
+
+	if (l4_mask->tclass)
+		return -EINVAL;
+
+	if (!ipv6_addr_any((struct in6_addr *)l4_mask->ip6src))
+		ntuples++;
+
+	if (!ipv6_addr_any((struct in6_addr *)l4_mask->ip6dst))
+		ntuples++;
+
+	if (l4_mask->psrc) {
+		if (!all_ones(l4_mask->psrc))
+			return -EINVAL;
+		ntuples++;
+	}
+	if (l4_mask->pdst) {
+		if (!all_ones(l4_mask->pdst))
+			return -EINVAL;
+		ntuples++;
+	}
+	/* Flow is TCP/UDP */
+	return ++ntuples;
+}
+
+static int validate_vlan(struct ethtool_rx_flow_spec *fs)
+{
+	if (fs->m_ext.vlan_etype ||
+	    fs->m_ext.vlan_tci != cpu_to_be16(VLAN_VID_MASK))
+		return -EINVAL;
+
+	if (fs->m_ext.vlan_tci &&
+	    (be16_to_cpu(fs->h_ext.vlan_tci) >= VLAN_N_VID))
+		return -EINVAL;
+
+	return 1;
+}
+
 static int validate_flow(struct mlx5e_priv *priv,
 			 struct ethtool_rx_flow_spec *fs)
 {
-	struct ethtool_tcpip4_spec *l4_mask;
-	struct ethtool_usrip4_spec *l3_mask;
-	struct ethhdr *eth_mask;
 	int num_tuples = 0;
+	int ret = 0;
 
 	if (fs->location >= MAX_NUM_OF_ETHTOOL_RULES)
-		return -EINVAL;
+		return -ENOSPC;
 
 	if (fs->ring_cookie >= priv->channels.params.num_channels &&
 	    fs->ring_cookie != RX_CLS_FLOW_DISC)
@@ -396,73 +630,42 @@ static int validate_flow(struct mlx5e_priv *priv,
 
 	switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
 	case ETHER_FLOW:
-		eth_mask = &fs->m_u.ether_spec;
-		if (!is_zero_ether_addr(eth_mask->h_dest))
-			num_tuples++;
-		if (!is_zero_ether_addr(eth_mask->h_source))
-			num_tuples++;
-		if (eth_mask->h_proto)
-			num_tuples++;
+		num_tuples += validate_ethter(fs);
 		break;
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
-		if (fs->m_u.tcp_ip4_spec.tos)
-			return -EINVAL;
-		l4_mask = &fs->m_u.tcp_ip4_spec;
-		if (l4_mask->ip4src) {
-			if (!all_ones(l4_mask->ip4src))
-				return -EINVAL;
-			num_tuples++;
-		}
-		if (l4_mask->ip4dst) {
-			if (!all_ones(l4_mask->ip4dst))
-				return -EINVAL;
-			num_tuples++;
-		}
-		if (l4_mask->psrc) {
-			if (!all_ones(l4_mask->psrc))
-				return -EINVAL;
-			num_tuples++;
-		}
-		if (l4_mask->pdst) {
-			if (!all_ones(l4_mask->pdst))
-				return -EINVAL;
-			num_tuples++;
-		}
-		/* Flow is TCP/UDP */
-		num_tuples++;
+		ret = validate_tcpudp4(fs);
+		if (ret < 0)
+			return ret;
+		num_tuples += ret;
 		break;
 	case IP_USER_FLOW:
-		l3_mask = &fs->m_u.usr_ip4_spec;
-		if (l3_mask->l4_4_bytes || l3_mask->tos || l3_mask->proto ||
-		    fs->h_u.usr_ip4_spec.ip_ver != ETH_RX_NFC_IP4)
-			return -EINVAL;
-		if (l3_mask->ip4src) {
-			if (!all_ones(l3_mask->ip4src))
-				return -EINVAL;
-			num_tuples++;
-		}
-		if (l3_mask->ip4dst) {
-			if (!all_ones(l3_mask->ip4dst))
-				return -EINVAL;
-			num_tuples++;
-		}
-		/* Flow is IPv4 */
-		num_tuples++;
+		ret = validate_ip4(fs);
+		if (ret < 0)
+			return ret;
+		num_tuples += ret;
+		break;
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+		ret = validate_tcpudp6(fs);
+		if (ret < 0)
+			return ret;
+		num_tuples += ret;
+		break;
+	case IPV6_USER_FLOW:
+		ret = validate_ip6(fs);
+		if (ret < 0)
+			return ret;
+		num_tuples += ret;
 		break;
 	default:
-		return -EINVAL;
+		return -ENOTSUPP;
 	}
 	if ((fs->flow_type & FLOW_EXT)) {
-		if (fs->m_ext.vlan_etype ||
-		    (fs->m_ext.vlan_tci != cpu_to_be16(VLAN_VID_MASK)))
-			return -EINVAL;
-
-		if (fs->m_ext.vlan_tci) {
-			if (be16_to_cpu(fs->h_ext.vlan_tci) >= VLAN_N_VID)
-				return -EINVAL;
-		}
-		num_tuples++;
+		ret = validate_vlan(fs);
+		if (ret < 0)
+			return ret;
+		num_tuples += ret;
 	}
 
 	if (fs->flow_type & FLOW_MAC_EXT &&
@@ -472,8 +675,9 @@ static int validate_flow(struct mlx5e_priv *priv,
 	return num_tuples;
 }
 
-int mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
-			       struct ethtool_rx_flow_spec *fs)
+static int
+mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
+			   struct ethtool_rx_flow_spec *fs)
 {
 	struct mlx5e_ethtool_table *eth_ft;
 	struct mlx5e_ethtool_rule *eth_rule;
@@ -483,8 +687,9 @@ int mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
 
 	num_tuples = validate_flow(priv, fs);
 	if (num_tuples <= 0) {
-		netdev_warn(priv->netdev, "%s: flow is not valid\n",  __func__);
-		return -EINVAL;
+		netdev_warn(priv->netdev, "%s: flow is not valid %d\n",
+			    __func__, num_tuples);
+		return num_tuples;
 	}
 
 	eth_ft = get_flow_table(priv, fs, num_tuples);
@@ -519,8 +724,8 @@ del_ethtool_rule:
 	return err;
 }
 
-int mlx5e_ethtool_flow_remove(struct mlx5e_priv *priv,
-			      int location)
+static int
+mlx5e_ethtool_flow_remove(struct mlx5e_priv *priv, int location)
 {
 	struct mlx5e_ethtool_rule *eth_rule;
 	int err = 0;
@@ -539,8 +744,9 @@ out:
 	return err;
 }
 
-int mlx5e_ethtool_get_flow(struct mlx5e_priv *priv, struct ethtool_rxnfc *info,
-			   int location)
+static int
+mlx5e_ethtool_get_flow(struct mlx5e_priv *priv,
+		       struct ethtool_rxnfc *info, int location)
 {
 	struct mlx5e_ethtool_rule *eth_rule;
 
@@ -557,8 +763,9 @@ int mlx5e_ethtool_get_flow(struct mlx5e_priv *priv, struct ethtool_rxnfc *info,
 	return -ENOENT;
 }
 
-int mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv, struct ethtool_rxnfc *info,
-				u32 *rule_locs)
+static int
+mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv,
+			    struct ethtool_rxnfc *info, u32 *rule_locs)
 {
 	int location = 0;
 	int idx = 0;
@@ -587,3 +794,51 @@ void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv)
 {
 	INIT_LIST_HEAD(&priv->fs.ethtool.rules);
 }
+
+int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
+{
+	int err = 0;
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	switch (cmd->cmd) {
+	case ETHTOOL_SRXCLSRLINS:
+		err = mlx5e_ethtool_flow_replace(priv, &cmd->fs);
+		break;
+	case ETHTOOL_SRXCLSRLDEL:
+		err = mlx5e_ethtool_flow_remove(priv, cmd->fs.location);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+int mlx5e_get_rxnfc(struct net_device *dev,
+		    struct ethtool_rxnfc *info, u32 *rule_locs)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	int err = 0;
+
+	switch (info->cmd) {
+	case ETHTOOL_GRXRINGS:
+		info->data = priv->channels.params.num_channels;
+		break;
+	case ETHTOOL_GRXCLSRLCNT:
+		info->rule_cnt = priv->fs.ethtool.tot_num_rules;
+		break;
+	case ETHTOOL_GRXCLSRULE:
+		err = mlx5e_ethtool_get_flow(priv, info, info->fs.location);
+		break;
+	case ETHTOOL_GRXCLSRLALL:
+		err = mlx5e_ethtool_get_all_flows(priv, info, rule_locs);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index c592678ab5f1..5a7939e70190 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -45,8 +45,10 @@
 #include "en_accel/tls.h"
 #include "accel/ipsec.h"
 #include "accel/tls.h"
-#include "vxlan.h"
+#include "lib/vxlan.h"
+#include "lib/clock.h"
 #include "en/port.h"
+#include "en/xdp.h"
 
 struct mlx5e_rq_param {
 	u32			rqc[MLX5_ST_SZ_DW(rqc)];
@@ -96,14 +98,19 @@ bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 
 static u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params)
 {
-	if (!params->xdp_prog) {
-		u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
-		u16 rq_headroom = MLX5_RX_HEADROOM + NET_IP_ALIGN;
+	u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+	u16 linear_rq_headroom = params->xdp_prog ?
+		XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM;
+	u32 frag_sz;
 
-		return MLX5_SKB_FRAG_SZ(rq_headroom + hw_mtu);
-	}
+	linear_rq_headroom += NET_IP_ALIGN;
+
+	frag_sz = MLX5_SKB_FRAG_SZ(linear_rq_headroom + hw_mtu);
+
+	if (params->xdp_prog && frag_sz < PAGE_SIZE)
+		frag_sz = PAGE_SIZE;
 
-	return PAGE_SIZE;
+	return frag_sz;
 }
 
 static u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params)
@@ -222,7 +229,7 @@ static void mlx5e_update_carrier(struct mlx5e_priv *priv)
 	u8 port_state;
 
 	port_state = mlx5_query_vport_state(mdev,
-					    MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT,
+					    MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT,
 					    0);
 
 	if (port_state == VPORT_STATE_UP) {
@@ -270,12 +277,9 @@ void mlx5e_update_stats_work(struct work_struct *work)
 	struct delayed_work *dwork = to_delayed_work(work);
 	struct mlx5e_priv *priv = container_of(dwork, struct mlx5e_priv,
 					       update_stats_work);
+
 	mutex_lock(&priv->state_lock);
-	if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
-		priv->profile->update_stats(priv);
-		queue_delayed_work(priv->wq, dwork,
-				   msecs_to_jiffies(MLX5E_UPDATE_STATS_INTERVAL));
-	}
+	priv->profile->update_stats(priv);
 	mutex_unlock(&priv->state_lock);
 }
 
@@ -352,8 +356,9 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,
 {
 	int wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq);
 
-	rq->mpwqe.info = kcalloc_node(wq_sz, sizeof(*rq->mpwqe.info),
-				      GFP_KERNEL, cpu_to_node(c->cpu));
+	rq->mpwqe.info = kvzalloc_node(array_size(wq_sz,
+						  sizeof(*rq->mpwqe.info)),
+				       GFP_KERNEL, cpu_to_node(c->cpu));
 	if (!rq->mpwqe.info)
 		return -ENOMEM;
 
@@ -487,7 +492,6 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	rq->channel = c;
 	rq->ix      = c->ix;
 	rq->mdev    = mdev;
-	rq->hw_mtu  = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	rq->stats   = &c->priv->channel_stats[c->ix].rq;
 
 	rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL;
@@ -670,7 +674,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 err_free:
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		kfree(rq->mpwqe.info);
+		kvfree(rq->mpwqe.info);
 		mlx5_core_destroy_mkey(mdev, &rq->umr_mkey);
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
@@ -702,7 +706,7 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
 
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		kfree(rq->mpwqe.info);
+		kvfree(rq->mpwqe.info);
 		mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey);
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
@@ -879,7 +883,7 @@ static void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 
 		/* UMR WQE (if in progress) is always at wq->head */
 		if (rq->mpwqe.umr_in_progress)
-			mlx5e_free_rx_mpwqe(rq, &rq->mpwqe.info[wq->head]);
+			rq->dealloc_wqe(rq, wq->head);
 
 		while (!mlx5_wq_ll_is_empty(wq)) {
 			struct mlx5e_rx_wqe_ll *wqe;
@@ -965,16 +969,16 @@ static void mlx5e_close_rq(struct mlx5e_rq *rq)
 
 static void mlx5e_free_xdpsq_db(struct mlx5e_xdpsq *sq)
 {
-	kfree(sq->db.di);
+	kvfree(sq->db.xdpi);
 }
 
 static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa)
 {
 	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 
-	sq->db.di = kcalloc_node(wq_sz, sizeof(*sq->db.di),
-				     GFP_KERNEL, numa);
-	if (!sq->db.di) {
+	sq->db.xdpi = kvzalloc_node(array_size(wq_sz, sizeof(*sq->db.xdpi)),
+				    GFP_KERNEL, numa);
+	if (!sq->db.xdpi) {
 		mlx5e_free_xdpsq_db(sq);
 		return -ENOMEM;
 	}
@@ -985,7 +989,8 @@ static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa)
 static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 			     struct mlx5e_params *params,
 			     struct mlx5e_sq_param *param,
-			     struct mlx5e_xdpsq *sq)
+			     struct mlx5e_xdpsq *sq,
+			     bool is_redirect)
 {
 	void *sqc_wq               = MLX5_ADDR_OF(sqc, param->sqc, wq);
 	struct mlx5_core_dev *mdev = c->mdev;
@@ -997,6 +1002,10 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 	sq->channel   = c;
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
+	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+	sq->stats     = is_redirect ?
+		&c->priv->channel_stats[c->ix].xdpsq :
+		&c->priv->channel_stats[c->ix].rq_xdpsq;
 
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, wq, &sq->wq_ctrl);
@@ -1024,15 +1033,16 @@ static void mlx5e_free_xdpsq(struct mlx5e_xdpsq *sq)
 
 static void mlx5e_free_icosq_db(struct mlx5e_icosq *sq)
 {
-	kfree(sq->db.ico_wqe);
+	kvfree(sq->db.ico_wqe);
 }
 
 static int mlx5e_alloc_icosq_db(struct mlx5e_icosq *sq, int numa)
 {
 	u8 wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 
-	sq->db.ico_wqe = kcalloc_node(wq_sz, sizeof(*sq->db.ico_wqe),
-				      GFP_KERNEL, numa);
+	sq->db.ico_wqe = kvzalloc_node(array_size(wq_sz,
+						  sizeof(*sq->db.ico_wqe)),
+				       GFP_KERNEL, numa);
 	if (!sq->db.ico_wqe)
 		return -ENOMEM;
 
@@ -1077,8 +1087,8 @@ static void mlx5e_free_icosq(struct mlx5e_icosq *sq)
 
 static void mlx5e_free_txqsq_db(struct mlx5e_txqsq *sq)
 {
-	kfree(sq->db.wqe_info);
-	kfree(sq->db.dma_fifo);
+	kvfree(sq->db.wqe_info);
+	kvfree(sq->db.dma_fifo);
 }
 
 static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa)
@@ -1086,10 +1096,12 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa)
 	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 	int df_sz = wq_sz * MLX5_SEND_WQEBB_NUM_DS;
 
-	sq->db.dma_fifo = kcalloc_node(df_sz, sizeof(*sq->db.dma_fifo),
-					   GFP_KERNEL, numa);
-	sq->db.wqe_info = kcalloc_node(wq_sz, sizeof(*sq->db.wqe_info),
-					   GFP_KERNEL, numa);
+	sq->db.dma_fifo = kvzalloc_node(array_size(df_sz,
+						   sizeof(*sq->db.dma_fifo)),
+					GFP_KERNEL, numa);
+	sq->db.wqe_info = kvzalloc_node(array_size(wq_sz,
+						   sizeof(*sq->db.wqe_info)),
+					GFP_KERNEL, numa);
 	if (!sq->db.dma_fifo || !sq->db.wqe_info) {
 		mlx5e_free_txqsq_db(sq);
 		return -ENOMEM;
@@ -1523,7 +1535,8 @@ static void mlx5e_close_icosq(struct mlx5e_icosq *sq)
 static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
 			    struct mlx5e_params *params,
 			    struct mlx5e_sq_param *param,
-			    struct mlx5e_xdpsq *sq)
+			    struct mlx5e_xdpsq *sq,
+			    bool is_redirect)
 {
 	unsigned int ds_cnt = MLX5E_XDP_TX_DS_COUNT;
 	struct mlx5e_create_sq_param csp = {};
@@ -1531,7 +1544,7 @@ static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
 	int err;
 	int i;
 
-	err = mlx5e_alloc_xdpsq(c, params, param, sq);
+	err = mlx5e_alloc_xdpsq(c, params, param, sq, is_redirect);
 	if (err)
 		return err;
 
@@ -1540,6 +1553,8 @@ static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
 	csp.cqn             = sq->cq.mcq.cqn;
 	csp.wq_ctrl         = &sq->wq_ctrl;
 	csp.min_inline_mode = sq->min_inline_mode;
+	if (is_redirect)
+		set_bit(MLX5E_SQ_STATE_REDIRECT, &sq->state);
 	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
 	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, &sq->sqn);
 	if (err)
@@ -1893,7 +1908,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	int err;
 	int eqn;
 
-	c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
+	c = kvzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
 	if (!c)
 		return -ENOMEM;
 
@@ -1922,10 +1937,14 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	if (err)
 		goto err_close_icosq_cq;
 
-	err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam->rx_cq, &c->rq.cq);
+	err = mlx5e_open_cq(c, params->tx_cq_moderation, &cparam->tx_cq, &c->xdpsq.cq);
 	if (err)
 		goto err_close_tx_cqs;
 
+	err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam->rx_cq, &c->rq.cq);
+	if (err)
+		goto err_close_xdp_tx_cqs;
+
 	/* XDP SQ CQ params are same as normal TXQ sq CQ params */
 	err = c->xdp ? mlx5e_open_cq(c, params->tx_cq_moderation,
 				     &cparam->tx_cq, &c->rq.xdpsq.cq) : 0;
@@ -1942,7 +1961,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	if (err)
 		goto err_close_icosq;
 
-	err = c->xdp ? mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->rq.xdpsq) : 0;
+	err = c->xdp ? mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->rq.xdpsq, false) : 0;
 	if (err)
 		goto err_close_sqs;
 
@@ -1950,9 +1969,17 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	if (err)
 		goto err_close_xdp_sq;
 
+	err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->xdpsq, true);
+	if (err)
+		goto err_close_rq;
+
 	*cp = c;
 
 	return 0;
+
+err_close_rq:
+	mlx5e_close_rq(&c->rq);
+
 err_close_xdp_sq:
 	if (c->xdp)
 		mlx5e_close_xdpsq(&c->rq.xdpsq);
@@ -1971,6 +1998,9 @@ err_disable_napi:
 err_close_rx_cq:
 	mlx5e_close_cq(&c->rq.cq);
 
+err_close_xdp_tx_cqs:
+	mlx5e_close_cq(&c->xdpsq.cq);
+
 err_close_tx_cqs:
 	mlx5e_close_tx_cqs(c);
 
@@ -1979,7 +2009,7 @@ err_close_icosq_cq:
 
 err_napi_del:
 	netif_napi_del(&c->napi);
-	kfree(c);
+	kvfree(c);
 
 	return err;
 }
@@ -2005,6 +2035,7 @@ static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
 
 static void mlx5e_close_channel(struct mlx5e_channel *c)
 {
+	mlx5e_close_xdpsq(&c->xdpsq);
 	mlx5e_close_rq(&c->rq);
 	if (c->xdp)
 		mlx5e_close_xdpsq(&c->rq.xdpsq);
@@ -2014,11 +2045,12 @@ static void mlx5e_close_channel(struct mlx5e_channel *c)
 	if (c->xdp)
 		mlx5e_close_cq(&c->rq.xdpsq.cq);
 	mlx5e_close_cq(&c->rq.cq);
+	mlx5e_close_cq(&c->xdpsq.cq);
 	mlx5e_close_tx_cqs(c);
 	mlx5e_close_cq(&c->icosq.cq);
 	netif_napi_del(&c->napi);
 
-	kfree(c);
+	kvfree(c);
 }
 
 #define DEFAULT_FRAG_SIZE (2048)
@@ -2276,7 +2308,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
 	chs->num = chs->params.num_channels;
 
 	chs->c = kcalloc(chs->num, sizeof(struct mlx5e_channel *), GFP_KERNEL);
-	cparam = kzalloc(sizeof(struct mlx5e_channel_param), GFP_KERNEL);
+	cparam = kvzalloc(sizeof(struct mlx5e_channel_param), GFP_KERNEL);
 	if (!chs->c || !cparam)
 		goto err_free;
 
@@ -2287,7 +2319,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
 			goto err_close_channels;
 	}
 
-	kfree(cparam);
+	kvfree(cparam);
 	return 0;
 
 err_close_channels:
@@ -2296,7 +2328,7 @@ err_close_channels:
 
 err_free:
 	kfree(chs->c);
-	kfree(cparam);
+	kvfree(cparam);
 	chs->num = 0;
 	return err;
 }
@@ -2943,7 +2975,7 @@ int mlx5e_open(struct net_device *netdev)
 		mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_UP);
 	mutex_unlock(&priv->state_lock);
 
-	if (mlx5e_vxlan_allowed(priv->mdev))
+	if (mlx5_vxlan_allowed(priv->mdev->vxlan))
 		udp_tunnel_get_rx_info(netdev);
 
 	return err;
@@ -3371,7 +3403,7 @@ static int mlx5e_setup_tc_block(struct net_device *dev,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, mlx5e_setup_tc_block_cb,
-					     priv, priv);
+					     priv, priv, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, mlx5e_setup_tc_block_cb,
 					priv);
@@ -3405,6 +3437,9 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	struct mlx5e_vport_stats *vstats = &priv->stats.vport;
 	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
 
+	/* update HW stats in background for next time */
+	queue_delayed_work(priv->wq, &priv->update_stats_work, 0);
+
 	if (mlx5e_is_uplink_rep(priv)) {
 		stats->rx_packets = PPORT_802_3_GET(pstats, a_frames_received_ok);
 		stats->rx_bytes   = PPORT_802_3_GET(pstats, a_octets_received_ok);
@@ -3590,7 +3625,7 @@ unlock:
 	return err;
 }
 
-#ifdef CONFIG_RFS_ACCEL
+#ifdef CONFIG_MLX5_EN_ARFS
 static int set_feature_arfs(struct net_device *netdev, bool enable)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -3645,7 +3680,7 @@ static int mlx5e_set_features(struct net_device *netdev,
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_RXALL, set_feature_rx_all);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_RXFCS, set_feature_rx_fcs);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_VLAN_CTAG_RX, set_feature_rx_vlan);
-#ifdef CONFIG_RFS_ACCEL
+#ifdef CONFIG_MLX5_EN_ARFS
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_NTUPLE, set_feature_arfs);
 #endif
 
@@ -3703,6 +3738,14 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 	new_channels.params = *params;
 	new_channels.params.sw_mtu = new_mtu;
 
+	if (params->xdp_prog &&
+	    !mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
+		netdev_err(netdev, "MTU(%d) > %d is not allowed while XDP enabled\n",
+			   new_mtu, MLX5E_XDP_MAX_MTU);
+		err = -EINVAL;
+		goto out;
+	}
+
 	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
 		u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params);
 		u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params);
@@ -3740,7 +3783,8 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
 	struct hwtstamp_config config;
 	int err;
 
-	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz))
+	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz) ||
+	    (mlx5_clock_get_ptp_index(priv->mdev) == -1))
 		return -EOPNOTSUPP;
 
 	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
@@ -3874,9 +3918,9 @@ static int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate,
 static int mlx5_vport_link2ifla(u8 esw_link)
 {
 	switch (esw_link) {
-	case MLX5_ESW_VPORT_ADMIN_STATE_DOWN:
+	case MLX5_VPORT_ADMIN_STATE_DOWN:
 		return IFLA_VF_LINK_STATE_DISABLE;
-	case MLX5_ESW_VPORT_ADMIN_STATE_UP:
+	case MLX5_VPORT_ADMIN_STATE_UP:
 		return IFLA_VF_LINK_STATE_ENABLE;
 	}
 	return IFLA_VF_LINK_STATE_AUTO;
@@ -3886,11 +3930,11 @@ static int mlx5_ifla_link2vport(u8 ifla_link)
 {
 	switch (ifla_link) {
 	case IFLA_VF_LINK_STATE_DISABLE:
-		return MLX5_ESW_VPORT_ADMIN_STATE_DOWN;
+		return MLX5_VPORT_ADMIN_STATE_DOWN;
 	case IFLA_VF_LINK_STATE_ENABLE:
-		return MLX5_ESW_VPORT_ADMIN_STATE_UP;
+		return MLX5_VPORT_ADMIN_STATE_UP;
 	}
-	return MLX5_ESW_VPORT_ADMIN_STATE_AUTO;
+	return MLX5_VPORT_ADMIN_STATE_AUTO;
 }
 
 static int mlx5e_set_vf_link_state(struct net_device *dev, int vf,
@@ -3928,6 +3972,57 @@ static int mlx5e_get_vf_stats(struct net_device *dev,
 }
 #endif
 
+struct mlx5e_vxlan_work {
+	struct work_struct	work;
+	struct mlx5e_priv	*priv;
+	u16			port;
+};
+
+static void mlx5e_vxlan_add_work(struct work_struct *work)
+{
+	struct mlx5e_vxlan_work *vxlan_work =
+		container_of(work, struct mlx5e_vxlan_work, work);
+	struct mlx5e_priv *priv = vxlan_work->priv;
+	u16 port = vxlan_work->port;
+
+	mutex_lock(&priv->state_lock);
+	mlx5_vxlan_add_port(priv->mdev->vxlan, port);
+	mutex_unlock(&priv->state_lock);
+
+	kfree(vxlan_work);
+}
+
+static void mlx5e_vxlan_del_work(struct work_struct *work)
+{
+	struct mlx5e_vxlan_work *vxlan_work =
+		container_of(work, struct mlx5e_vxlan_work, work);
+	struct mlx5e_priv *priv         = vxlan_work->priv;
+	u16 port = vxlan_work->port;
+
+	mutex_lock(&priv->state_lock);
+	mlx5_vxlan_del_port(priv->mdev->vxlan, port);
+	mutex_unlock(&priv->state_lock);
+	kfree(vxlan_work);
+}
+
+static void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, u16 port, int add)
+{
+	struct mlx5e_vxlan_work *vxlan_work;
+
+	vxlan_work = kmalloc(sizeof(*vxlan_work), GFP_ATOMIC);
+	if (!vxlan_work)
+		return;
+
+	if (add)
+		INIT_WORK(&vxlan_work->work, mlx5e_vxlan_add_work);
+	else
+		INIT_WORK(&vxlan_work->work, mlx5e_vxlan_del_work);
+
+	vxlan_work->priv = priv;
+	vxlan_work->port = port;
+	queue_work(priv->wq, &vxlan_work->work);
+}
+
 static void mlx5e_add_vxlan_port(struct net_device *netdev,
 				 struct udp_tunnel_info *ti)
 {
@@ -3936,10 +4031,10 @@ static void mlx5e_add_vxlan_port(struct net_device *netdev,
 	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
 		return;
 
-	if (!mlx5e_vxlan_allowed(priv->mdev))
+	if (!mlx5_vxlan_allowed(priv->mdev->vxlan))
 		return;
 
-	mlx5e_vxlan_queue_work(priv, ti->sa_family, be16_to_cpu(ti->port), 1);
+	mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 1);
 }
 
 static void mlx5e_del_vxlan_port(struct net_device *netdev,
@@ -3950,10 +4045,10 @@ static void mlx5e_del_vxlan_port(struct net_device *netdev,
 	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
 		return;
 
-	if (!mlx5e_vxlan_allowed(priv->mdev))
+	if (!mlx5_vxlan_allowed(priv->mdev->vxlan))
 		return;
 
-	mlx5e_vxlan_queue_work(priv, ti->sa_family, be16_to_cpu(ti->port), 0);
+	mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 0);
 }
 
 static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
@@ -3984,7 +4079,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
 		port = be16_to_cpu(udph->dest);
 
 		/* Verify if UDP port is being offloaded by HW */
-		if (mlx5e_vxlan_lookup_port(priv, port))
+		if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, port))
 			return features;
 	}
 
@@ -4091,26 +4186,47 @@ static void mlx5e_tx_timeout(struct net_device *dev)
 	queue_work(priv->wq, &priv->tx_timeout_work);
 }
 
+static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog)
+{
+	struct net_device *netdev = priv->netdev;
+	struct mlx5e_channels new_channels = {};
+
+	if (priv->channels.params.lro_en) {
+		netdev_warn(netdev, "can't set XDP while LRO is on, disable LRO first\n");
+		return -EINVAL;
+	}
+
+	if (MLX5_IPSEC_DEV(priv->mdev)) {
+		netdev_warn(netdev, "can't set XDP with IPSec offload\n");
+		return -EINVAL;
+	}
+
+	new_channels.params = priv->channels.params;
+	new_channels.params.xdp_prog = prog;
+
+	if (!mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
+		netdev_warn(netdev, "XDP is not allowed with MTU(%d) > %d\n",
+			    new_channels.params.sw_mtu, MLX5E_XDP_MAX_MTU);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct bpf_prog *old_prog;
-	int err = 0;
 	bool reset, was_opened;
+	int err = 0;
 	int i;
 
 	mutex_lock(&priv->state_lock);
 
-	if ((netdev->features & NETIF_F_LRO) && prog) {
-		netdev_warn(netdev, "can't set XDP while LRO is on, disable LRO first\n");
-		err = -EINVAL;
-		goto unlock;
-	}
-
-	if ((netdev->features & NETIF_F_HW_ESP) && prog) {
-		netdev_warn(netdev, "can't set XDP with IPSec offload\n");
-		err = -EINVAL;
-		goto unlock;
+	if (prog) {
+		err = mlx5e_xdp_allowed(priv, prog);
+		if (err)
+			goto unlock;
 	}
 
 	was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
@@ -4193,7 +4309,6 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		return mlx5e_xdp_set(dev, xdp->prog);
 	case XDP_QUERY_PROG:
 		xdp->prog_id = mlx5e_xdp_query(dev);
-		xdp->prog_attached = !!xdp->prog_id;
 		return 0;
 	default:
 		return -EINVAL;
@@ -4235,11 +4350,12 @@ static const struct net_device_ops mlx5e_netdev_ops = {
 	.ndo_udp_tunnel_add      = mlx5e_add_vxlan_port,
 	.ndo_udp_tunnel_del      = mlx5e_del_vxlan_port,
 	.ndo_features_check      = mlx5e_features_check,
-#ifdef CONFIG_RFS_ACCEL
-	.ndo_rx_flow_steer	 = mlx5e_rx_flow_steer,
-#endif
 	.ndo_tx_timeout          = mlx5e_tx_timeout,
 	.ndo_bpf		 = mlx5e_xdp,
+	.ndo_xdp_xmit            = mlx5e_xdp_xmit,
+#ifdef CONFIG_MLX5_EN_ARFS
+	.ndo_rx_flow_steer	 = mlx5e_rx_flow_steer,
+#endif
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller     = mlx5e_netpoll,
 #endif
@@ -4535,8 +4651,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->hw_features      |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	netdev->hw_features      |= NETIF_F_HW_VLAN_STAG_TX;
 
-	if (mlx5e_vxlan_allowed(mdev) || MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) {
-		netdev->hw_features     |= NETIF_F_GSO_PARTIAL;
+	if (mlx5_vxlan_allowed(mdev->vxlan) || MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) {
 		netdev->hw_enc_features |= NETIF_F_IP_CSUM;
 		netdev->hw_enc_features |= NETIF_F_IPV6_CSUM;
 		netdev->hw_enc_features |= NETIF_F_TSO;
@@ -4544,7 +4659,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 		netdev->hw_enc_features |= NETIF_F_GSO_PARTIAL;
 	}
 
-	if (mlx5e_vxlan_allowed(mdev)) {
+	if (mlx5_vxlan_allowed(mdev->vxlan)) {
 		netdev->hw_features     |= NETIF_F_GSO_UDP_TUNNEL |
 					   NETIF_F_GSO_UDP_TUNNEL_CSUM;
 		netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL |
@@ -4561,6 +4676,11 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 						NETIF_F_GSO_GRE_CSUM;
 	}
 
+	netdev->hw_features	                 |= NETIF_F_GSO_PARTIAL;
+	netdev->gso_partial_features             |= NETIF_F_GSO_UDP_L4;
+	netdev->hw_features                      |= NETIF_F_GSO_UDP_L4;
+	netdev->features                         |= NETIF_F_GSO_UDP_L4;
+
 	mlx5_query_port_fcs(mdev, &fcs_supported, &fcs_enabled);
 
 	if (fcs_supported)
@@ -4585,7 +4705,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	    FT_CAP(identified_miss_table_mode) &&
 	    FT_CAP(flow_table_modify)) {
 		netdev->hw_features      |= NETIF_F_HW_TC;
-#ifdef CONFIG_RFS_ACCEL
+#ifdef CONFIG_MLX5_EN_ARFS
 		netdev->hw_features	 |= NETIF_F_NTUPLE;
 #endif
 	}
@@ -4650,14 +4770,12 @@ static void mlx5e_nic_init(struct mlx5_core_dev *mdev,
 		mlx5_core_err(mdev, "TLS initialization failed, %d\n", err);
 	mlx5e_build_nic_netdev(netdev);
 	mlx5e_build_tc2txq_maps(priv);
-	mlx5e_vxlan_init(priv);
 }
 
 static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
 {
 	mlx5e_tls_cleanup(priv);
 	mlx5e_ipsec_cleanup(priv);
-	mlx5e_vxlan_cleanup(priv);
 }
 
 static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
@@ -4831,7 +4949,7 @@ struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev,
 		return NULL;
 	}
 
-#ifdef CONFIG_RFS_ACCEL
+#ifdef CONFIG_MLX5_EN_ARFS
 	netdev->rx_cpu_rmap = mdev->rmap;
 #endif
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 2b8040a3cdbd..c9cc9747d21d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -698,8 +698,8 @@ static int mlx5e_rep_open(struct net_device *dev)
 		goto unlock;
 
 	if (!mlx5_modify_vport_admin_state(priv->mdev,
-					   MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
-					   rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_UP))
+					   MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
+					   rep->vport, MLX5_VPORT_ADMIN_STATE_UP))
 		netif_carrier_on(dev);
 
 unlock:
@@ -716,8 +716,8 @@ static int mlx5e_rep_close(struct net_device *dev)
 
 	mutex_lock(&priv->state_lock);
 	mlx5_modify_vport_admin_state(priv->mdev,
-				      MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
-				      rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN);
+				      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
+				      rep->vport, MLX5_VPORT_ADMIN_STATE_DOWN);
 	ret = mlx5e_close_locked(dev);
 	mutex_unlock(&priv->state_lock);
 	return ret;
@@ -797,7 +797,7 @@ static int mlx5e_rep_setup_tc_block(struct net_device *dev,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, mlx5e_rep_setup_tc_cb,
-					     priv, priv);
+					     priv, priv, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, mlx5e_rep_setup_tc_cb, priv);
 		return 0;
@@ -897,6 +897,9 @@ mlx5e_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
+	/* update HW stats in background for next time */
+	queue_delayed_work(priv->wq, &priv->update_stats_work, 0);
+
 	memcpy(stats, &priv->stats.vf_vport, sizeof(*stats));
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index d3a1dd20e41d..15d8ae28c040 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -34,7 +34,6 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/tcp.h>
-#include <linux/bpf_trace.h>
 #include <net/busy_poll.h>
 #include <net/ip6_checksum.h>
 #include <net/page_pool.h>
@@ -44,7 +43,9 @@
 #include "en_rep.h"
 #include "ipoib/ipoib.h"
 #include "en_accel/ipsec_rxtx.h"
+#include "en_accel/tls_rxtx.h"
 #include "lib/clock.h"
+#include "en/xdp.h"
 
 static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
 {
@@ -238,8 +239,7 @@ static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq,
 	return 0;
 }
 
-static void mlx5e_page_dma_unmap(struct mlx5e_rq *rq,
-					struct mlx5e_dma_info *dma_info)
+void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info)
 {
 	dma_unmap_page(rq->pdev, dma_info->addr, PAGE_SIZE, rq->buff.map_dir);
 }
@@ -276,10 +276,11 @@ static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq,
 }
 
 static inline void mlx5e_put_rx_frag(struct mlx5e_rq *rq,
-				     struct mlx5e_wqe_frag_info *frag)
+				     struct mlx5e_wqe_frag_info *frag,
+				     bool recycle)
 {
 	if (frag->last_in_page)
-		mlx5e_page_release(rq, frag->di, true);
+		mlx5e_page_release(rq, frag->di, recycle);
 }
 
 static inline struct mlx5e_wqe_frag_info *get_frag(struct mlx5e_rq *rq, u16 ix)
@@ -307,25 +308,26 @@ static int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe_cyc *wqe,
 
 free_frags:
 	while (--i >= 0)
-		mlx5e_put_rx_frag(rq, --frag);
+		mlx5e_put_rx_frag(rq, --frag, true);
 
 	return err;
 }
 
 static inline void mlx5e_free_rx_wqe(struct mlx5e_rq *rq,
-				     struct mlx5e_wqe_frag_info *wi)
+				     struct mlx5e_wqe_frag_info *wi,
+				     bool recycle)
 {
 	int i;
 
 	for (i = 0; i < rq->wqe.info.num_frags; i++, wi++)
-		mlx5e_put_rx_frag(rq, wi);
+		mlx5e_put_rx_frag(rq, wi, recycle);
 }
 
 void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix)
 {
 	struct mlx5e_wqe_frag_info *wi = get_frag(rq, ix);
 
-	mlx5e_free_rx_wqe(rq, wi);
+	mlx5e_free_rx_wqe(rq, wi, false);
 }
 
 static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, u8 wqe_bulk)
@@ -395,7 +397,8 @@ mlx5e_copy_skb_header_mpwqe(struct device *pdev,
 	}
 }
 
-void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
+static void
+mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, bool recycle)
 {
 	const bool no_xdp_xmit =
 		bitmap_empty(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE);
@@ -404,7 +407,7 @@ void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
 
 	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++)
 		if (no_xdp_xmit || !test_bit(i, wi->xdp_xmit_bitmap))
-			mlx5e_page_release(rq, &dma_info[i], true);
+			mlx5e_page_release(rq, &dma_info[i], recycle);
 }
 
 static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq)
@@ -487,7 +490,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 
 	sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
 	sq->pc += MLX5E_UMR_WQEBBS;
-	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &umr_wqe->ctrl);
+	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &umr_wqe->ctrl);
 
 	return 0;
 
@@ -504,8 +507,8 @@ err_unmap:
 void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 {
 	struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
-
-	mlx5e_free_rx_mpwqe(rq, wi);
+	/* Don't recycle, this function is called on rq/netdev close */
+	mlx5e_free_rx_mpwqe(rq, wi, false);
 }
 
 bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
@@ -601,6 +604,8 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
 
 	if (!rq->mpwqe.umr_in_progress)
 		mlx5e_alloc_rx_mpwqe(rq, wq->head);
+	else
+		rq->stats->congst_umr += mlx5_wq_ll_missing(wq) > 2;
 
 	return false;
 }
@@ -795,6 +800,11 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 	struct net_device *netdev = rq->netdev;
 
 	skb->mac_len = ETH_HLEN;
+
+#ifdef CONFIG_MLX5_EN_TLS
+	mlx5e_tls_handle_rx_skb(netdev, skb, &cqe_bcnt);
+#endif
+
 	if (lro_num_seg > 1) {
 		mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt);
 		skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt, lro_num_seg);
@@ -839,135 +849,6 @@ static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq,
 	mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb);
 }
 
-static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
-{
-	struct mlx5_wq_cyc *wq = &sq->wq;
-	struct mlx5e_tx_wqe *wqe;
-	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc - 1); /* last pi */
-
-	wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
-
-	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &wqe->ctrl);
-}
-
-static inline bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq,
-					struct mlx5e_dma_info *di,
-					const struct xdp_buff *xdp)
-{
-	struct mlx5e_xdpsq       *sq   = &rq->xdpsq;
-	struct mlx5_wq_cyc       *wq   = &sq->wq;
-	u16                       pi   = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-	struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
-
-	struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
-	struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
-	struct mlx5_wqe_data_seg *dseg;
-
-	ptrdiff_t data_offset = xdp->data - xdp->data_hard_start;
-	dma_addr_t dma_addr  = di->addr + data_offset;
-	unsigned int dma_len = xdp->data_end - xdp->data;
-
-	struct mlx5e_rq_stats *stats = rq->stats;
-
-	prefetchw(wqe);
-
-	if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE || rq->hw_mtu < dma_len)) {
-		stats->xdp_drop++;
-		return false;
-	}
-
-	if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1))) {
-		if (sq->db.doorbell) {
-			/* SQ is full, ring doorbell */
-			mlx5e_xmit_xdp_doorbell(sq);
-			sq->db.doorbell = false;
-		}
-		stats->xdp_tx_full++;
-		return false;
-	}
-
-	dma_sync_single_for_device(sq->pdev, dma_addr, dma_len, PCI_DMA_TODEVICE);
-
-	cseg->fm_ce_se = 0;
-
-	dseg = (struct mlx5_wqe_data_seg *)eseg + 1;
-
-	/* copy the inline part if required */
-	if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
-		memcpy(eseg->inline_hdr.start, xdp->data, MLX5E_XDP_MIN_INLINE);
-		eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE);
-		dma_len  -= MLX5E_XDP_MIN_INLINE;
-		dma_addr += MLX5E_XDP_MIN_INLINE;
-		dseg++;
-	}
-
-	/* write the dma part */
-	dseg->addr       = cpu_to_be64(dma_addr);
-	dseg->byte_count = cpu_to_be32(dma_len);
-
-	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_SEND);
-
-	/* move page to reference to sq responsibility,
-	 * and mark so it's not put back in page-cache.
-	 */
-	__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */
-	sq->db.di[pi] = *di;
-	sq->pc++;
-
-	sq->db.doorbell = true;
-
-	stats->xdp_tx++;
-	return true;
-}
-
-/* returns true if packet was consumed by xdp */
-static inline bool mlx5e_xdp_handle(struct mlx5e_rq *rq,
-				    struct mlx5e_dma_info *di,
-				    void *va, u16 *rx_headroom, u32 *len)
-{
-	struct bpf_prog *prog = READ_ONCE(rq->xdp_prog);
-	struct xdp_buff xdp;
-	u32 act;
-	int err;
-
-	if (!prog)
-		return false;
-
-	xdp.data = va + *rx_headroom;
-	xdp_set_data_meta_invalid(&xdp);
-	xdp.data_end = xdp.data + *len;
-	xdp.data_hard_start = va;
-	xdp.rxq = &rq->xdp_rxq;
-
-	act = bpf_prog_run_xdp(prog, &xdp);
-	switch (act) {
-	case XDP_PASS:
-		*rx_headroom = xdp.data - xdp.data_hard_start;
-		*len = xdp.data_end - xdp.data;
-		return false;
-	case XDP_TX:
-		if (unlikely(!mlx5e_xmit_xdp_frame(rq, di, &xdp)))
-			trace_xdp_exception(rq->netdev, prog, act);
-		return true;
-	case XDP_REDIRECT:
-		/* When XDP enabled then page-refcnt==1 here */
-		err = xdp_do_redirect(rq->netdev, &xdp, prog);
-		if (!err) {
-			__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags);
-			rq->xdpsq.db.redirect_flush = true;
-			mlx5e_page_dma_unmap(rq, di);
-		}
-		return true;
-	default:
-		bpf_warn_invalid_xdp_action(act);
-	case XDP_ABORTED:
-		trace_xdp_exception(rq->netdev, prog, act);
-	case XDP_DROP:
-		rq->stats->xdp_drop++;
-		return true;
-	}
-}
-
 static inline
 struct sk_buff *mlx5e_build_linear_skb(struct mlx5e_rq *rq, void *va,
 				       u32 frag_size, u16 headroom,
@@ -1105,7 +986,7 @@ void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	napi_gro_receive(rq->cq.napi, skb);
 
 free_wqe:
-	mlx5e_free_rx_wqe(rq, wi);
+	mlx5e_free_rx_wqe(rq, wi, true);
 wq_cyc_pop:
 	mlx5_wq_cyc_pop(wq);
 }
@@ -1147,7 +1028,7 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	napi_gro_receive(rq->cq.napi, skb);
 
 free_wqe:
-	mlx5e_free_rx_wqe(rq, wi);
+	mlx5e_free_rx_wqe(rq, wi, true);
 wq_cyc_pop:
 	mlx5_wq_cyc_pop(wq);
 }
@@ -1218,6 +1099,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 
 	dma_sync_single_range_for_cpu(rq->pdev, di->addr, head_offset,
 				      frag_size, DMA_FROM_DEVICE);
+	prefetchw(va); /* xdp_frame data area */
 	prefetch(data);
 
 	rcu_read_lock();
@@ -1261,7 +1143,10 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	}
 
 	if (unlikely(mpwrq_is_filler_cqe(cqe))) {
-		rq->stats->mpwqe_filler++;
+		struct mlx5e_rq_stats *stats = rq->stats;
+
+		stats->mpwqe_filler_cqes++;
+		stats->mpwqe_filler_strides += cstrides;
 		goto mpwrq_cqe_out;
 	}
 
@@ -1281,7 +1166,7 @@ mpwrq_cqe_out:
 
 	wq  = &rq->mpwqe.wq;
 	wqe = mlx5_wq_ll_get_wqe(wq, wqe_id);
-	mlx5e_free_rx_mpwqe(rq, wi);
+	mlx5e_free_rx_mpwqe(rq, wi, true);
 	mlx5_wq_ll_pop(wq, cqe->wqe_id, &wqe->next.next_wqe_index);
 }
 
@@ -1317,14 +1202,14 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 		rq->handle_rx_cqe(rq, cqe);
 	} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
-	if (xdpsq->db.doorbell) {
+	if (xdpsq->doorbell) {
 		mlx5e_xmit_xdp_doorbell(xdpsq);
-		xdpsq->db.doorbell = false;
+		xdpsq->doorbell = false;
 	}
 
-	if (xdpsq->db.redirect_flush) {
+	if (xdpsq->redirect_flush) {
 		xdp_do_flush_map();
-		xdpsq->db.redirect_flush = false;
+		xdpsq->redirect_flush = false;
 	}
 
 	mlx5_cqwq_update_db_record(&cq->wq);
@@ -1335,78 +1220,6 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	return work_done;
 }
 
-bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
-{
-	struct mlx5e_xdpsq *sq;
-	struct mlx5_cqe64 *cqe;
-	struct mlx5e_rq *rq;
-	u16 sqcc;
-	int i;
-
-	sq = container_of(cq, struct mlx5e_xdpsq, cq);
-
-	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
-		return false;
-
-	cqe = mlx5_cqwq_get_cqe(&cq->wq);
-	if (!cqe)
-		return false;
-
-	rq = container_of(sq, struct mlx5e_rq, xdpsq);
-
-	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
-	 * otherwise a cq overrun may occur
-	 */
-	sqcc = sq->cc;
-
-	i = 0;
-	do {
-		u16 wqe_counter;
-		bool last_wqe;
-
-		mlx5_cqwq_pop(&cq->wq);
-
-		wqe_counter = be16_to_cpu(cqe->wqe_counter);
-
-		do {
-			struct mlx5e_dma_info *di;
-			u16 ci;
-
-			last_wqe = (sqcc == wqe_counter);
-
-			ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
-			di = &sq->db.di[ci];
-
-			sqcc++;
-			/* Recycle RX page */
-			mlx5e_page_release(rq, di, true);
-		} while (!last_wqe);
-	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
-
-	mlx5_cqwq_update_db_record(&cq->wq);
-
-	/* ensure cq space is freed before enabling more cqes */
-	wmb();
-
-	sq->cc = sqcc;
-	return (i == MLX5E_TX_CQ_POLL_BUDGET);
-}
-
-void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
-{
-	struct mlx5e_rq *rq = container_of(sq, struct mlx5e_rq, xdpsq);
-	struct mlx5e_dma_info *di;
-	u16 ci;
-
-	while (sq->cc != sq->pc) {
-		ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc);
-		di = &sq->db.di[ci];
-		sq->cc++;
-
-		mlx5e_page_release(rq, di, false);
-	}
-}
-
 #ifdef CONFIG_MLX5_CORE_IPOIB
 
 #define MLX5_IB_GRH_DGID_OFFSET 24
@@ -1508,7 +1321,7 @@ void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	napi_gro_receive(rq->cq.napi, skb);
 
 wq_free_wqe:
-	mlx5e_free_rx_wqe(rq, wi);
+	mlx5e_free_rx_wqe(rq, wi, true);
 	mlx5_wq_cyc_pop(wq);
 }
 
@@ -1531,19 +1344,19 @@ void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt);
 	if (unlikely(!skb)) {
 		/* a DROP, save the page-reuse checks */
-		mlx5e_free_rx_wqe(rq, wi);
+		mlx5e_free_rx_wqe(rq, wi, true);
 		goto wq_cyc_pop;
 	}
-	skb = mlx5e_ipsec_handle_rx_skb(rq->netdev, skb);
+	skb = mlx5e_ipsec_handle_rx_skb(rq->netdev, skb, &cqe_bcnt);
 	if (unlikely(!skb)) {
-		mlx5e_free_rx_wqe(rq, wi);
+		mlx5e_free_rx_wqe(rq, wi, true);
 		goto wq_cyc_pop;
 	}
 
 	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
 	napi_gro_receive(rq->cq.napi, skb);
 
-	mlx5e_free_rx_wqe(rq, wi);
+	mlx5e_free_rx_wqe(rq, wi, true);
 wq_cyc_pop:
 	mlx5_wq_cyc_pop(wq);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 4d316cc9b008..35ded91203f5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -74,7 +74,7 @@ static int mlx5e_test_link_state(struct mlx5e_priv *priv)
 	if (!netif_carrier_ok(priv->netdev))
 		return 1;
 
-	port_state = mlx5_query_vport_state(priv->mdev, MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT, 0);
+	port_state = mlx5_query_vport_state(priv->mdev, MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT, 0);
 	return port_state == VPORT_STATE_UP ? 0 : 1;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 1646859974ce..12fdf5c92b67 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -44,6 +44,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_packets) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_bytes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_added_vlan_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_nop) },
 
 #ifdef CONFIG_MLX5_EN_TLS
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ooo) },
@@ -58,8 +59,11 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_redirect) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_xmit) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_err) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_none) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial_inner) },
@@ -67,10 +71,17 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_dropped) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xmit_more) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_recover) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_udp_seg_rem) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_xmit) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_full) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_err) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_cqes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_cqes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_strides) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts) },
@@ -80,6 +91,11 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_empty) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_busy) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_congst_umr) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_events) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_poll) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_arm) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_aff_change) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_eq_rearm) },
 };
 
@@ -118,6 +134,8 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 	for (i = 0; i < priv->profile->max_nch(priv->mdev); i++) {
 		struct mlx5e_channel_stats *channel_stats =
 			&priv->channel_stats[i];
+		struct mlx5e_xdpsq_stats *xdpsq_red_stats = &channel_stats->xdpsq;
+		struct mlx5e_xdpsq_stats *xdpsq_stats = &channel_stats->rq_xdpsq;
 		struct mlx5e_rq_stats *rq_stats = &channel_stats->rq;
 		struct mlx5e_ch_stats *ch_stats = &channel_stats->ch;
 		int j;
@@ -131,11 +149,15 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_csum_complete += rq_stats->csum_complete;
 		s->rx_csum_unnecessary += rq_stats->csum_unnecessary;
 		s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
-		s->rx_xdp_drop += rq_stats->xdp_drop;
-		s->rx_xdp_tx += rq_stats->xdp_tx;
-		s->rx_xdp_tx_full += rq_stats->xdp_tx_full;
+		s->rx_xdp_drop     += rq_stats->xdp_drop;
+		s->rx_xdp_redirect += rq_stats->xdp_redirect;
+		s->rx_xdp_tx_xmit  += xdpsq_stats->xmit;
+		s->rx_xdp_tx_full  += xdpsq_stats->full;
+		s->rx_xdp_tx_err   += xdpsq_stats->err;
+		s->rx_xdp_tx_cqe   += xdpsq_stats->cqes;
 		s->rx_wqe_err   += rq_stats->wqe_err;
-		s->rx_mpwqe_filler += rq_stats->mpwqe_filler;
+		s->rx_mpwqe_filler_cqes    += rq_stats->mpwqe_filler_cqes;
+		s->rx_mpwqe_filler_strides += rq_stats->mpwqe_filler_strides;
 		s->rx_buff_alloc_err += rq_stats->buff_alloc_err;
 		s->rx_cqe_compress_blks += rq_stats->cqe_compress_blks;
 		s->rx_cqe_compress_pkts += rq_stats->cqe_compress_pkts;
@@ -145,7 +167,17 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_cache_empty += rq_stats->cache_empty;
 		s->rx_cache_busy  += rq_stats->cache_busy;
 		s->rx_cache_waive += rq_stats->cache_waive;
-		s->ch_eq_rearm += ch_stats->eq_rearm;
+		s->rx_congst_umr  += rq_stats->congst_umr;
+		s->ch_events      += ch_stats->events;
+		s->ch_poll        += ch_stats->poll;
+		s->ch_arm         += ch_stats->arm;
+		s->ch_aff_change  += ch_stats->aff_change;
+		s->ch_eq_rearm    += ch_stats->eq_rearm;
+		/* xdp redirect */
+		s->tx_xdp_xmit    += xdpsq_red_stats->xmit;
+		s->tx_xdp_full    += xdpsq_red_stats->full;
+		s->tx_xdp_err     += xdpsq_red_stats->err;
+		s->tx_xdp_cqes    += xdpsq_red_stats->cqes;
 
 		for (j = 0; j < priv->max_opened_tc; j++) {
 			struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j];
@@ -157,8 +189,10 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 			s->tx_tso_inner_packets	+= sq_stats->tso_inner_packets;
 			s->tx_tso_inner_bytes	+= sq_stats->tso_inner_bytes;
 			s->tx_added_vlan_packets += sq_stats->added_vlan_packets;
+			s->tx_nop               += sq_stats->nop;
 			s->tx_queue_stopped	+= sq_stats->stopped;
 			s->tx_queue_wake	+= sq_stats->wake;
+			s->tx_udp_seg_rem	+= sq_stats->udp_seg_rem;
 			s->tx_queue_dropped	+= sq_stats->dropped;
 			s->tx_cqe_err		+= sq_stats->cqe_err;
 			s->tx_recover		+= sq_stats->recover;
@@ -170,6 +204,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 			s->tx_tls_ooo		+= sq_stats->tls_ooo;
 			s->tx_tls_resync_bytes	+= sq_stats->tls_resync_bytes;
 #endif
+			s->tx_cqes		+= sq_stats->cqes;
 		}
 	}
 
@@ -1106,13 +1141,13 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_drop) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx_full) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_redirect) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, removed_vlan_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_cqes) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_strides) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
@@ -1122,6 +1157,7 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_empty) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_busy) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_waive) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, congst_umr) },
 };
 
 static const struct counter_desc sq_stats_desc[] = {
@@ -1140,16 +1176,37 @@ static const struct counter_desc sq_stats_desc[] = {
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, xmit_more) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, recover) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqes) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqe_err) },
 };
 
+static const struct counter_desc rq_xdpsq_stats_desc[] = {
+	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) },
+	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) },
+	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) },
+	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },
+};
+
+static const struct counter_desc xdpsq_stats_desc[] = {
+	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) },
+	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) },
+	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) },
+	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },
+};
+
 static const struct counter_desc ch_stats_desc[] = {
+	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, events) },
+	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, poll) },
+	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, arm) },
+	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, aff_change) },
 	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, eq_rearm) },
 };
 
 #define NUM_RQ_STATS			ARRAY_SIZE(rq_stats_desc)
 #define NUM_SQ_STATS			ARRAY_SIZE(sq_stats_desc)
+#define NUM_XDPSQ_STATS			ARRAY_SIZE(xdpsq_stats_desc)
+#define NUM_RQ_XDPSQ_STATS		ARRAY_SIZE(rq_xdpsq_stats_desc)
 #define NUM_CH_STATS			ARRAY_SIZE(ch_stats_desc)
 
 static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv)
@@ -1158,7 +1215,9 @@ static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv)
 
 	return (NUM_RQ_STATS * max_nch) +
 	       (NUM_CH_STATS * max_nch) +
-	       (NUM_SQ_STATS * max_nch * priv->max_opened_tc);
+	       (NUM_SQ_STATS * max_nch * priv->max_opened_tc) +
+	       (NUM_RQ_XDPSQ_STATS * max_nch) +
+	       (NUM_XDPSQ_STATS * max_nch);
 }
 
 static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
@@ -1172,9 +1231,14 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
 			sprintf(data + (idx++) * ETH_GSTRING_LEN,
 				ch_stats_desc[j].format, i);
 
-	for (i = 0; i < max_nch; i++)
+	for (i = 0; i < max_nch; i++) {
 		for (j = 0; j < NUM_RQ_STATS; j++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN, rq_stats_desc[j].format, i);
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				rq_stats_desc[j].format, i);
+		for (j = 0; j < NUM_RQ_XDPSQ_STATS; j++)
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				rq_xdpsq_stats_desc[j].format, i);
+	}
 
 	for (tc = 0; tc < priv->max_opened_tc; tc++)
 		for (i = 0; i < max_nch; i++)
@@ -1183,6 +1247,11 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
 					sq_stats_desc[j].format,
 					priv->channel_tc2txq[i][tc]);
 
+	for (i = 0; i < max_nch; i++)
+		for (j = 0; j < NUM_XDPSQ_STATS; j++)
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				xdpsq_stats_desc[j].format, i);
+
 	return idx;
 }
 
@@ -1198,11 +1267,16 @@ static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data,
 				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].ch,
 						     ch_stats_desc, j);
 
-	for (i = 0; i < max_nch; i++)
+	for (i = 0; i < max_nch; i++) {
 		for (j = 0; j < NUM_RQ_STATS; j++)
 			data[idx++] =
 				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].rq,
 						     rq_stats_desc, j);
+		for (j = 0; j < NUM_RQ_XDPSQ_STATS; j++)
+			data[idx++] =
+				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].rq_xdpsq,
+						     rq_xdpsq_stats_desc, j);
+	}
 
 	for (tc = 0; tc < priv->max_opened_tc; tc++)
 		for (i = 0; i < max_nch; i++)
@@ -1211,6 +1285,12 @@ static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data,
 					MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].sq[tc],
 							     sq_stats_desc, j);
 
+	for (i = 0; i < max_nch; i++)
+		for (j = 0; j < NUM_XDPSQ_STATS; j++)
+			data[idx++] =
+				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].xdpsq,
+						     xdpsq_stats_desc, j);
+
 	return idx;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 643153bb3607..a4c035aedd46 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -44,6 +44,8 @@
 #define MLX5E_DECLARE_STAT(type, fld) #fld, offsetof(type, fld)
 #define MLX5E_DECLARE_RX_STAT(type, fld) "rx%d_"#fld, offsetof(type, fld)
 #define MLX5E_DECLARE_TX_STAT(type, fld) "tx%d_"#fld, offsetof(type, fld)
+#define MLX5E_DECLARE_XDPSQ_STAT(type, fld) "tx%d_xdp_"#fld, offsetof(type, fld)
+#define MLX5E_DECLARE_RQ_XDPSQ_STAT(type, fld) "rx%d_xdp_tx_"#fld, offsetof(type, fld)
 #define MLX5E_DECLARE_CH_STAT(type, fld) "ch%d_"#fld, offsetof(type, fld)
 
 struct counter_desc {
@@ -61,6 +63,7 @@ struct mlx5e_sw_stats {
 	u64 tx_tso_inner_packets;
 	u64 tx_tso_inner_bytes;
 	u64 tx_added_vlan_packets;
+	u64 tx_nop;
 	u64 rx_lro_packets;
 	u64 rx_lro_bytes;
 	u64 rx_removed_vlan_packets;
@@ -69,8 +72,11 @@ struct mlx5e_sw_stats {
 	u64 rx_csum_complete;
 	u64 rx_csum_unnecessary_inner;
 	u64 rx_xdp_drop;
-	u64 rx_xdp_tx;
+	u64 rx_xdp_redirect;
+	u64 rx_xdp_tx_xmit;
 	u64 rx_xdp_tx_full;
+	u64 rx_xdp_tx_err;
+	u64 rx_xdp_tx_cqe;
 	u64 tx_csum_none;
 	u64 tx_csum_partial;
 	u64 tx_csum_partial_inner;
@@ -78,10 +84,17 @@ struct mlx5e_sw_stats {
 	u64 tx_queue_dropped;
 	u64 tx_xmit_more;
 	u64 tx_recover;
+	u64 tx_cqes;
 	u64 tx_queue_wake;
+	u64 tx_udp_seg_rem;
 	u64 tx_cqe_err;
+	u64 tx_xdp_xmit;
+	u64 tx_xdp_full;
+	u64 tx_xdp_err;
+	u64 tx_xdp_cqes;
 	u64 rx_wqe_err;
-	u64 rx_mpwqe_filler;
+	u64 rx_mpwqe_filler_cqes;
+	u64 rx_mpwqe_filler_strides;
 	u64 rx_buff_alloc_err;
 	u64 rx_cqe_compress_blks;
 	u64 rx_cqe_compress_pkts;
@@ -91,6 +104,11 @@ struct mlx5e_sw_stats {
 	u64 rx_cache_empty;
 	u64 rx_cache_busy;
 	u64 rx_cache_waive;
+	u64 rx_congst_umr;
+	u64 ch_events;
+	u64 ch_poll;
+	u64 ch_arm;
+	u64 ch_aff_change;
 	u64 ch_eq_rearm;
 
 #ifdef CONFIG_MLX5_EN_TLS
@@ -168,10 +186,10 @@ struct mlx5e_rq_stats {
 	u64 lro_bytes;
 	u64 removed_vlan_packets;
 	u64 xdp_drop;
-	u64 xdp_tx;
-	u64 xdp_tx_full;
+	u64 xdp_redirect;
 	u64 wqe_err;
-	u64 mpwqe_filler;
+	u64 mpwqe_filler_cqes;
+	u64 mpwqe_filler_strides;
 	u64 buff_alloc_err;
 	u64 cqe_compress_blks;
 	u64 cqe_compress_pkts;
@@ -181,6 +199,7 @@ struct mlx5e_rq_stats {
 	u64 cache_empty;
 	u64 cache_busy;
 	u64 cache_waive;
+	u64 congst_umr;
 };
 
 struct mlx5e_sq_stats {
@@ -196,6 +215,7 @@ struct mlx5e_sq_stats {
 	u64 csum_partial_inner;
 	u64 added_vlan_packets;
 	u64 nop;
+	u64 udp_seg_rem;
 #ifdef CONFIG_MLX5_EN_TLS
 	u64 tls_ooo;
 	u64 tls_resync_bytes;
@@ -206,11 +226,24 @@ struct mlx5e_sq_stats {
 	u64 dropped;
 	u64 recover;
 	/* dirtied @completion */
-	u64 wake ____cacheline_aligned_in_smp;
+	u64 cqes ____cacheline_aligned_in_smp;
+	u64 wake;
 	u64 cqe_err;
 };
 
+struct mlx5e_xdpsq_stats {
+	u64 xmit;
+	u64 full;
+	u64 err;
+	/* dirtied @completion */
+	u64 cqes ____cacheline_aligned_in_smp;
+};
+
 struct mlx5e_ch_stats {
+	u64 events;
+	u64 poll;
+	u64 arm;
+	u64 aff_change;
 	u64 eq_rearm;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index dfbcda0d0e08..9131a1376e7d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -50,7 +50,7 @@
 #include "en_rep.h"
 #include "en_tc.h"
 #include "eswitch.h"
-#include "vxlan.h"
+#include "lib/vxlan.h"
 #include "fs_core.h"
 #include "en/port.h"
 
@@ -1032,10 +1032,8 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
 		 * dst ip pair
 		 */
 		n = neigh_lookup(tbl, &m_neigh->dst_ip, m_neigh->dev);
-		if (!n) {
-			WARN(1, "The neighbour already freed\n");
+		if (!n)
 			return;
-		}
 
 		neigh_event_send(n, NULL);
 		neigh_release(n);
@@ -1126,16 +1124,12 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 			skb_flow_dissector_target(f->dissector,
 						  FLOW_DISSECTOR_KEY_ENC_PORTS,
 						  f->mask);
-		struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-		struct mlx5e_rep_priv *uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
-		struct net_device *up_dev = uplink_rpriv->netdev;
-		struct mlx5e_priv *up_priv = netdev_priv(up_dev);
 
 		/* Full udp dst port must be given */
 		if (memchr_inv(&mask->dst, 0xff, sizeof(mask->dst)))
 			goto vxlan_match_offload_err;
 
-		if (mlx5e_vxlan_lookup_port(up_priv, be16_to_cpu(key->dst)) &&
+		if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->dst)) &&
 		    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
 			parse_vxlan_attr(spec, f);
 		else {
@@ -1213,6 +1207,26 @@ vxlan_match_offload_err:
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IPV6);
 	}
 
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_IP)) {
+		struct flow_dissector_key_ip *key =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_ENC_IP,
+						  f->key);
+		struct flow_dissector_key_ip *mask =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_ENC_IP,
+						  f->mask);
+
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn, mask->tos & 0x3);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn, key->tos & 0x3);
+
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp, mask->tos >> 2);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp, key->tos  >> 2);
+
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit, mask->ttl);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit, key->ttl);
+	}
+
 	/* Enforce DMAC when offloading incoming tunneled flows.
 	 * Flow counters require a match on the DMAC.
 	 */
@@ -1237,6 +1251,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 				       outer_headers);
 	void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				       outer_headers);
+	void *misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    misc_parameters);
+	void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				    misc_parameters);
 	u16 addr_type = 0;
 	u8 ip_proto = 0;
 
@@ -1247,6 +1265,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
 	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
+	      BIT(FLOW_DISSECTOR_KEY_CVLAN) |
 	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
@@ -1256,7 +1275,8 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 	      BIT(FLOW_DISSECTOR_KEY_ENC_PORTS)	|
 	      BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_TCP) |
-	      BIT(FLOW_DISSECTOR_KEY_IP))) {
+	      BIT(FLOW_DISSECTOR_KEY_IP)  |
+	      BIT(FLOW_DISSECTOR_KEY_ENC_IP))) {
 		netdev_warn(priv->netdev, "Unsupported key used: 0x%x\n",
 			    f->dissector->used_keys);
 		return -EOPNOTSUPP;
@@ -1327,9 +1347,18 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 			skb_flow_dissector_target(f->dissector,
 						  FLOW_DISSECTOR_KEY_VLAN,
 						  f->mask);
-		if (mask->vlan_id || mask->vlan_priority) {
-			MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1);
-			MLX5_SET(fte_match_set_lyr_2_4, headers_v, cvlan_tag, 1);
+		if (mask->vlan_id || mask->vlan_priority || mask->vlan_tpid) {
+			if (key->vlan_tpid == htons(ETH_P_8021AD)) {
+				MLX5_SET(fte_match_set_lyr_2_4, headers_c,
+					 svlan_tag, 1);
+				MLX5_SET(fte_match_set_lyr_2_4, headers_v,
+					 svlan_tag, 1);
+			} else {
+				MLX5_SET(fte_match_set_lyr_2_4, headers_c,
+					 cvlan_tag, 1);
+				MLX5_SET(fte_match_set_lyr_2_4, headers_v,
+					 cvlan_tag, 1);
+			}
 
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid, mask->vlan_id);
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, key->vlan_id);
@@ -1341,6 +1370,41 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 		}
 	}
 
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CVLAN)) {
+		struct flow_dissector_key_vlan *key =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_CVLAN,
+						  f->key);
+		struct flow_dissector_key_vlan *mask =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_CVLAN,
+						  f->mask);
+		if (mask->vlan_id || mask->vlan_priority || mask->vlan_tpid) {
+			if (key->vlan_tpid == htons(ETH_P_8021AD)) {
+				MLX5_SET(fte_match_set_misc, misc_c,
+					 outer_second_svlan_tag, 1);
+				MLX5_SET(fte_match_set_misc, misc_v,
+					 outer_second_svlan_tag, 1);
+			} else {
+				MLX5_SET(fte_match_set_misc, misc_c,
+					 outer_second_cvlan_tag, 1);
+				MLX5_SET(fte_match_set_misc, misc_v,
+					 outer_second_cvlan_tag, 1);
+			}
+
+			MLX5_SET(fte_match_set_misc, misc_c, outer_second_vid,
+				 mask->vlan_id);
+			MLX5_SET(fte_match_set_misc, misc_v, outer_second_vid,
+				 key->vlan_id);
+			MLX5_SET(fte_match_set_misc, misc_c, outer_second_prio,
+				 mask->vlan_priority);
+			MLX5_SET(fte_match_set_misc, misc_v, outer_second_prio,
+				 key->vlan_priority);
+
+			*match_level = MLX5_MATCH_L2;
+		}
+	}
+
 	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
 		struct flow_dissector_key_basic *key =
 			skb_flow_dissector_target(f->dissector,
@@ -2082,7 +2146,7 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 				   struct net_device **out_dev,
 				   struct flowi4 *fl4,
 				   struct neighbour **out_n,
-				   int *out_ttl)
+				   u8 *out_ttl)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5e_rep_priv *uplink_rpriv;
@@ -2106,7 +2170,8 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 	else
 		*out_dev = rt->dst.dev;
 
-	*out_ttl = ip4_dst_hoplimit(&rt->dst);
+	if (!(*out_ttl))
+		*out_ttl = ip4_dst_hoplimit(&rt->dst);
 	n = dst_neigh_lookup(&rt->dst, &fl4->daddr);
 	ip_rt_put(rt);
 	if (!n)
@@ -2135,7 +2200,7 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 				   struct net_device **out_dev,
 				   struct flowi6 *fl6,
 				   struct neighbour **out_n,
-				   int *out_ttl)
+				   u8 *out_ttl)
 {
 	struct neighbour *n = NULL;
 	struct dst_entry *dst;
@@ -2150,7 +2215,8 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 	if (ret < 0)
 		return ret;
 
-	*out_ttl = ip6_dst_hoplimit(dst);
+	if (!(*out_ttl))
+		*out_ttl = ip6_dst_hoplimit(dst);
 
 	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
 	/* if the egress device isn't on the same HW e-switch, we use the uplink */
@@ -2174,7 +2240,7 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 static void gen_vxlan_header_ipv4(struct net_device *out_dev,
 				  char buf[], int encap_size,
 				  unsigned char h_dest[ETH_ALEN],
-				  int ttl,
+				  u8 tos, u8 ttl,
 				  __be32 daddr,
 				  __be32 saddr,
 				  __be16 udp_dst_port,
@@ -2194,6 +2260,7 @@ static void gen_vxlan_header_ipv4(struct net_device *out_dev,
 	ip->daddr = daddr;
 	ip->saddr = saddr;
 
+	ip->tos = tos;
 	ip->ttl = ttl;
 	ip->protocol = IPPROTO_UDP;
 	ip->version = 0x4;
@@ -2207,7 +2274,7 @@ static void gen_vxlan_header_ipv4(struct net_device *out_dev,
 static void gen_vxlan_header_ipv6(struct net_device *out_dev,
 				  char buf[], int encap_size,
 				  unsigned char h_dest[ETH_ALEN],
-				  int ttl,
+				  u8 tos, u8 ttl,
 				  struct in6_addr *daddr,
 				  struct in6_addr *saddr,
 				  __be16 udp_dst_port,
@@ -2224,7 +2291,7 @@ static void gen_vxlan_header_ipv6(struct net_device *out_dev,
 	ether_addr_copy(eth->h_source, out_dev->dev_addr);
 	eth->h_proto = htons(ETH_P_IPV6);
 
-	ip6_flow_hdr(ip6h, 0, 0);
+	ip6_flow_hdr(ip6h, tos, 0);
 	/* the HW fills up ipv6 payload len */
 	ip6h->nexthdr     = IPPROTO_UDP;
 	ip6h->hop_limit   = ttl;
@@ -2246,9 +2313,9 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 	struct net_device *out_dev;
 	struct neighbour *n = NULL;
 	struct flowi4 fl4 = {};
+	u8 nud_state, tos, ttl;
 	char *encap_header;
-	int ttl, err;
-	u8 nud_state;
+	int err;
 
 	if (max_encap_size < ipv4_encap_size) {
 		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
@@ -2269,6 +2336,10 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 		err = -EOPNOTSUPP;
 		goto free_encap;
 	}
+
+	tos = tun_key->tos;
+	ttl = tun_key->ttl;
+
 	fl4.flowi4_tos = tun_key->tos;
 	fl4.daddr = tun_key->u.ipv4.dst;
 	fl4.saddr = tun_key->u.ipv4.src;
@@ -2303,7 +2374,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 	switch (e->tunnel_type) {
 	case MLX5_HEADER_TYPE_VXLAN:
 		gen_vxlan_header_ipv4(out_dev, encap_header,
-				      ipv4_encap_size, e->h_dest, ttl,
+				      ipv4_encap_size, e->h_dest, tos, ttl,
 				      fl4.daddr,
 				      fl4.saddr, tun_key->tp_dst,
 				      tunnel_id_to_key32(tun_key->tun_id));
@@ -2351,9 +2422,9 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 	struct net_device *out_dev;
 	struct neighbour *n = NULL;
 	struct flowi6 fl6 = {};
+	u8 nud_state, tos, ttl;
 	char *encap_header;
-	int err, ttl = 0;
-	u8 nud_state;
+	int err;
 
 	if (max_encap_size < ipv6_encap_size) {
 		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
@@ -2375,6 +2446,9 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 		goto free_encap;
 	}
 
+	tos = tun_key->tos;
+	ttl = tun_key->ttl;
+
 	fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label);
 	fl6.daddr = tun_key->u.ipv6.dst;
 	fl6.saddr = tun_key->u.ipv6.src;
@@ -2409,7 +2483,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 	switch (e->tunnel_type) {
 	case MLX5_HEADER_TYPE_VXLAN:
 		gen_vxlan_header_ipv6(out_dev, encap_header,
-				      ipv6_encap_size, e->h_dest, ttl,
+				      ipv6_encap_size, e->h_dest, tos, ttl,
 				      &fl6.daddr,
 				      &fl6.saddr, tun_key->tp_dst,
 				      tunnel_id_to_key32(tun_key->tun_id));
@@ -2455,11 +2529,7 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 			      struct mlx5e_tc_flow *flow)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5e_rep_priv *uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw,
-									   REP_ETH);
-	struct net_device *up_dev = uplink_rpriv->netdev;
 	unsigned short family = ip_tunnel_info_af(tun_info);
-	struct mlx5e_priv *up_priv = netdev_priv(up_dev);
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
 	struct ip_tunnel_key *key = &tun_info->key;
 	struct mlx5e_encap_entry *e;
@@ -2479,7 +2549,7 @@ vxlan_encap_offload_err:
 		return -EOPNOTSUPP;
 	}
 
-	if (mlx5e_vxlan_lookup_port(up_priv, be16_to_cpu(key->tp_dst)) &&
+	if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->tp_dst)) &&
 	    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) {
 		tunnel_type = MLX5_HEADER_TYPE_VXLAN;
 	} else {
@@ -2535,6 +2605,56 @@ out_err:
 	return err;
 }
 
+static int parse_tc_vlan_action(struct mlx5e_priv *priv,
+				const struct tc_action *a,
+				struct mlx5_esw_flow_attr *attr,
+				u32 *action)
+{
+	u8 vlan_idx = attr->total_vlan;
+
+	if (vlan_idx >= MLX5_FS_VLAN_DEPTH)
+		return -EOPNOTSUPP;
+
+	if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) {
+		if (vlan_idx) {
+			if (!mlx5_eswitch_vlan_actions_supported(priv->mdev,
+								 MLX5_FS_VLAN_DEPTH))
+				return -EOPNOTSUPP;
+
+			*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2;
+		} else {
+			*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
+		}
+	} else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) {
+		attr->vlan_vid[vlan_idx] = tcf_vlan_push_vid(a);
+		attr->vlan_prio[vlan_idx] = tcf_vlan_push_prio(a);
+		attr->vlan_proto[vlan_idx] = tcf_vlan_push_proto(a);
+		if (!attr->vlan_proto[vlan_idx])
+			attr->vlan_proto[vlan_idx] = htons(ETH_P_8021Q);
+
+		if (vlan_idx) {
+			if (!mlx5_eswitch_vlan_actions_supported(priv->mdev,
+								 MLX5_FS_VLAN_DEPTH))
+				return -EOPNOTSUPP;
+
+			*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2;
+		} else {
+			if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, 1) &&
+			    (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q) ||
+			     tcf_vlan_push_prio(a)))
+				return -EOPNOTSUPP;
+
+			*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
+		}
+	} else { /* action is TCA_VLAN_ACT_MODIFY */
+		return -EOPNOTSUPP;
+	}
+
+	attr->total_vlan = vlan_idx + 1;
+
+	return 0;
+}
+
 static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				struct mlx5e_tc_flow_parse_attr *parse_attr,
 				struct mlx5e_tc_flow *flow)
@@ -2546,6 +2666,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 	LIST_HEAD(actions);
 	bool encap = false;
 	u32 action = 0;
+	int err;
 
 	if (!tcf_exts_has_actions(exts))
 		return -EINVAL;
@@ -2562,8 +2683,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 		}
 
 		if (is_tcf_pedit(a)) {
-			int err;
-
 			err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_FDB,
 						    parse_attr);
 			if (err)
@@ -2630,23 +2749,11 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 		}
 
 		if (is_tcf_vlan(a)) {
-			if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) {
-				action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
-			} else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) {
-				action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
-				attr->vlan_vid = tcf_vlan_push_vid(a);
-				if (mlx5_eswitch_vlan_actions_supported(priv->mdev)) {
-					attr->vlan_prio = tcf_vlan_push_prio(a);
-					attr->vlan_proto = tcf_vlan_push_proto(a);
-					if (!attr->vlan_proto)
-						attr->vlan_proto = htons(ETH_P_8021Q);
-				} else if (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q) ||
-					   tcf_vlan_push_prio(a)) {
-					return -EOPNOTSUPP;
-				}
-			} else { /* action is TCA_VLAN_ACT_MODIFY */
-				return -EOPNOTSUPP;
-			}
+			err = parse_tc_vlan_action(priv, a, attr, &action);
+
+			if (err)
+				return err;
+
 			attr->mirror_count = attr->out_count;
 			continue;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index f29deb44bf3b..ae73ea992845 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -66,22 +66,21 @@ static inline void mlx5e_tx_dma_unmap(struct device *pdev,
 	}
 }
 
+static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_txqsq *sq, u32 i)
+{
+	return &sq->db.dma_fifo[i & sq->dma_fifo_mask];
+}
+
 static inline void mlx5e_dma_push(struct mlx5e_txqsq *sq,
 				  dma_addr_t addr,
 				  u32 size,
 				  enum mlx5e_dma_map_type map_type)
 {
-	u32 i = sq->dma_fifo_pc & sq->dma_fifo_mask;
-
-	sq->db.dma_fifo[i].addr = addr;
-	sq->db.dma_fifo[i].size = size;
-	sq->db.dma_fifo[i].type = map_type;
-	sq->dma_fifo_pc++;
-}
+	struct mlx5e_sq_dma *dma = mlx5e_dma_get(sq, sq->dma_fifo_pc++);
 
-static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_txqsq *sq, u32 i)
-{
-	return &sq->db.dma_fifo[i & sq->dma_fifo_mask];
+	dma->addr = addr;
+	dma->size = size;
+	dma->type = map_type;
 }
 
 static void mlx5e_dma_unmap_wqe_err(struct mlx5e_txqsq *sq, u8 num_dma)
@@ -111,10 +110,11 @@ static inline int mlx5e_get_dscp_up(struct mlx5e_priv *priv, struct sk_buff *skb
 #endif
 
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv, select_queue_fallback_t fallback)
+		       struct net_device *sb_dev,
+		       select_queue_fallback_t fallback)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	int channel_ix = fallback(dev, skb);
+	int channel_ix = fallback(dev, skb, NULL);
 	u16 num_channels;
 	int up = 0;
 
@@ -228,7 +228,10 @@ mlx5e_tx_get_gso_ihs(struct mlx5e_txqsq *sq, struct sk_buff *skb)
 		stats->tso_inner_packets++;
 		stats->tso_inner_bytes += skb->len - ihs;
 	} else {
-		ihs = skb_transport_offset(skb) + tcp_hdrlen(skb);
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
+			ihs = skb_transport_offset(skb) + sizeof(struct udphdr);
+		else
+			ihs = skb_transport_offset(skb) + tcp_hdrlen(skb);
 		stats->tso_packets++;
 		stats->tso_bytes += skb->len - ihs;
 	}
@@ -443,12 +446,11 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 	sq = priv->txq2sq[skb_get_queue_mapping(skb)];
 	mlx5e_sq_fetch_wqe(sq, &wqe, &pi);
 
-#ifdef CONFIG_MLX5_ACCEL
 	/* might send skbs and update wqe and pi */
 	skb = mlx5e_accel_handle_tx(skb, sq, dev, &wqe, &pi);
 	if (unlikely(!skb))
 		return NETDEV_TX_OK;
-#endif
+
 	return mlx5e_sq_xmit(sq, skb, wqe, pi);
 }
 
@@ -466,6 +468,7 @@ static void mlx5e_dump_error_cqe(struct mlx5e_txqsq *sq,
 
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 {
+	struct mlx5e_sq_stats *stats;
 	struct mlx5e_txqsq *sq;
 	struct mlx5_cqe64 *cqe;
 	u32 dma_fifo_cc;
@@ -483,6 +486,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 	if (!cqe)
 		return false;
 
+	stats = sq->stats;
+
 	npkts = 0;
 	nbytes = 0;
 
@@ -511,7 +516,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 				queue_work(cq->channel->priv->wq,
 					   &sq->recover.recover_work);
 			}
-			sq->stats->cqe_err++;
+			stats->cqe_err++;
 		}
 
 		do {
@@ -556,6 +561,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
+	stats->cqes += i;
+
 	mlx5_cqwq_update_db_record(&cq->wq);
 
 	/* ensure cq space is freed before enabling more cqes */
@@ -571,7 +578,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 				   MLX5E_SQ_STOP_ROOM) &&
 	    !test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) {
 		netif_tx_wake_queue(sq->txq);
-		sq->stats->wake++;
+		stats->wake++;
 	}
 
 	return (i == MLX5E_TX_CQ_POLL_BUDGET);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index 1b17f682693b..85d517360157 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -32,6 +32,7 @@
 
 #include <linux/irq.h>
 #include "en.h"
+#include "en/xdp.h"
 
 static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c)
 {
@@ -74,13 +75,18 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel,
 					       napi);
+	struct mlx5e_ch_stats *ch_stats = c->stats;
 	bool busy = false;
 	int work_done = 0;
 	int i;
 
+	ch_stats->poll++;
+
 	for (i = 0; i < c->num_tc; i++)
 		busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget);
 
+	busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq.cq);
+
 	if (c->xdp)
 		busy |= mlx5e_poll_xdpsq_cq(&c->rq.xdpsq.cq);
 
@@ -94,6 +100,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	if (busy) {
 		if (likely(mlx5e_channel_no_affinity_change(c)))
 			return budget;
+		ch_stats->aff_change++;
 		if (budget && work_done == budget)
 			work_done--;
 	}
@@ -101,6 +108,8 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	if (unlikely(!napi_complete_done(napi, work_done)))
 		return work_done;
 
+	ch_stats->arm++;
+
 	for (i = 0; i < c->num_tc; i++) {
 		mlx5e_handle_tx_dim(&c->sq[i]);
 		mlx5e_cq_arm(&c->sq[i].cq);
@@ -110,6 +119,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 
 	mlx5e_cq_arm(&c->rq.cq);
 	mlx5e_cq_arm(&c->icosq.cq);
+	mlx5e_cq_arm(&c->xdpsq.cq);
 
 	return work_done;
 }
@@ -118,8 +128,9 @@ void mlx5e_completion_event(struct mlx5_core_cq *mcq)
 {
 	struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq);
 
-	cq->event_ctr++;
 	napi_schedule(cq->napi);
+	cq->event_ctr++;
+	cq->channel->stats->events++;
 }
 
 void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 406c23862f5f..48864f4988a4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -40,6 +40,8 @@
 #include "mlx5_core.h"
 #include "fpga/core.h"
 #include "eswitch.h"
+#include "lib/clock.h"
+#include "diag/fw_tracer.h"
 
 enum {
 	MLX5_EQE_SIZE		= sizeof(struct mlx5_eqe),
@@ -168,6 +170,8 @@ static const char *eqe_type_str(u8 type)
 		return "MLX5_EVENT_TYPE_FPGA_QP_ERROR";
 	case MLX5_EVENT_TYPE_GENERAL_EVENT:
 		return "MLX5_EVENT_TYPE_GENERAL_EVENT";
+	case MLX5_EVENT_TYPE_DEVICE_TRACER:
+		return "MLX5_EVENT_TYPE_DEVICE_TRACER";
 	default:
 		return "Unrecognized event";
 	}
@@ -576,6 +580,11 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
 		case MLX5_EVENT_TYPE_GENERAL_EVENT:
 			general_event_handler(dev, eqe);
 			break;
+
+		case MLX5_EVENT_TYPE_DEVICE_TRACER:
+			mlx5_fw_tracer_event(dev, eqe);
+			break;
+
 		default:
 			mlx5_core_warn(dev, "Unhandled event 0x%x on EQ 0x%x\n",
 				       eqe->type, eq->eqn);
@@ -853,6 +862,9 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev)
 	if (MLX5_CAP_GEN(dev, temp_warn_event))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_TEMP_WARN_EVENT);
 
+	if (MLX5_CAP_MCAM_REG(dev, tracer_registers))
+		async_event_mask |= (1ull << MLX5_EVENT_TYPE_DEVICE_TRACER);
+
 	err = mlx5_create_map_eq(dev, &table->cmd_eq, MLX5_EQ_VEC_CMD,
 				 MLX5_NUM_CMD_EQE, 1ull << MLX5_EVENT_TYPE_CMD,
 				 "mlx5_cmd_eq", MLX5_EQ_TYPE_ASYNC);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 40dba9e8af92..2b252cde5cc2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -246,7 +246,7 @@ esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport)
 	return __esw_fdb_set_vport_rule(esw, vport, true, mac_c, mac_v);
 }
 
-static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw, int nvports)
+static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_flow_table_attr ft_attr = {};
@@ -1469,7 +1469,7 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw,
 		return;
 
 	mlx5_modify_vport_admin_state(esw->dev,
-				      MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
+				      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
 				      vport_num,
 				      vport->info.link_state);
 	mlx5_modify_nic_vport_mac_address(esw->dev, vport_num, vport->info.mac);
@@ -1582,9 +1582,9 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 	esw_vport_disable_qos(esw, vport_num);
 	if (vport_num && esw->mode == SRIOV_LEGACY) {
 		mlx5_modify_vport_admin_state(esw->dev,
-					      MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
+					      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
 					      vport_num,
-					      MLX5_ESW_VPORT_ADMIN_STATE_DOWN);
+					      MLX5_VPORT_ADMIN_STATE_DOWN);
 		esw_vport_disable_egress_acl(esw, vport);
 		esw_vport_disable_ingress_acl(esw, vport);
 		esw_vport_destroy_drop_counters(vport);
@@ -1618,7 +1618,7 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 	esw->mode = mode;
 
 	if (mode == SRIOV_LEGACY) {
-		err = esw_create_legacy_fdb_table(esw, nvfs + 1);
+		err = esw_create_legacy_fdb_table(esw);
 	} else {
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
 
@@ -1736,7 +1736,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 		struct mlx5_vport *vport = &esw->vports[vport_num];
 
 		vport->vport = vport_num;
-		vport->info.link_state = MLX5_ESW_VPORT_ADMIN_STATE_AUTO;
+		vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
 		vport->dev = dev;
 		INIT_WORK(&vport->vport_change_handler,
 			  esw_vport_change_handler);
@@ -1860,7 +1860,7 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
 	evport = &esw->vports[vport];
 
 	err = mlx5_modify_vport_admin_state(esw->dev,
-					    MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
+					    MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
 					    vport, link_state);
 	if (err) {
 		mlx5_core_warn(esw->dev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index b174da2884c5..c17bfcab517c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -38,6 +38,7 @@
 #include <net/devlink.h>
 #include <linux/mlx5/device.h>
 #include <linux/mlx5/eswitch.h>
+#include <linux/mlx5/fs.h>
 #include "lib/mpfs.h"
 
 #ifdef CONFIG_MLX5_ESWITCH
@@ -256,9 +257,10 @@ struct mlx5_esw_flow_attr {
 	int out_count;
 
 	int	action;
-	__be16	vlan_proto;
-	u16	vlan_vid;
-	u8	vlan_prio;
+	__be16	vlan_proto[MLX5_FS_VLAN_DEPTH];
+	u16	vlan_vid[MLX5_FS_VLAN_DEPTH];
+	u8	vlan_prio[MLX5_FS_VLAN_DEPTH];
+	u8	total_vlan;
 	bool	vlan_handled;
 	u32	encap_id;
 	u32	mod_hdr_id;
@@ -282,10 +284,17 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
 int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 				  int vport, u16 vlan, u8 qos, u8 set_flags);
 
-static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev)
+static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev,
+						       u8 vlan_depth)
 {
-	return MLX5_CAP_ESW_FLOWTABLE_FDB(dev, pop_vlan) &&
-	       MLX5_CAP_ESW_FLOWTABLE_FDB(dev, push_vlan);
+	bool ret = MLX5_CAP_ESW_FLOWTABLE_FDB(dev, pop_vlan) &&
+		   MLX5_CAP_ESW_FLOWTABLE_FDB(dev, push_vlan);
+
+	if (vlan_depth == 1)
+		return ret;
+
+	return  ret && MLX5_CAP_ESW_FLOWTABLE_FDB(dev, pop_vlan_2) &&
+		MLX5_CAP_ESW_FLOWTABLE_FDB(dev, push_vlan_2);
 }
 
 #define MLX5_DEBUG_ESWITCH_MASK BIT(3)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index f32e69170b30..f72b5c9dcfe9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -66,13 +66,18 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 
 	flow_act.action = attr->action;
 	/* if per flow vlan pop/push is emulated, don't set that into the firmware */
-	if (!mlx5_eswitch_vlan_actions_supported(esw->dev))
+	if (!mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
 		flow_act.action &= ~(MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH |
 				     MLX5_FLOW_CONTEXT_ACTION_VLAN_POP);
 	else if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) {
-		flow_act.vlan[0].ethtype = ntohs(attr->vlan_proto);
-		flow_act.vlan[0].vid = attr->vlan_vid;
-		flow_act.vlan[0].prio = attr->vlan_prio;
+		flow_act.vlan[0].ethtype = ntohs(attr->vlan_proto[0]);
+		flow_act.vlan[0].vid = attr->vlan_vid[0];
+		flow_act.vlan[0].prio = attr->vlan_prio[0];
+		if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2) {
+			flow_act.vlan[1].ethtype = ntohs(attr->vlan_proto[1]);
+			flow_act.vlan[1].vid = attr->vlan_vid[1];
+			flow_act.vlan[1].prio = attr->vlan_prio[1];
+		}
 	}
 
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
@@ -266,7 +271,7 @@ static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr,
 	/* protects against (1) setting rules with different vlans to push and
 	 * (2) setting rules w.o vlans (attr->vlan = 0) && w. vlans to push (!= 0)
 	 */
-	if (push && in_rep->vlan_refcount && (in_rep->vlan != attr->vlan_vid))
+	if (push && in_rep->vlan_refcount && (in_rep->vlan != attr->vlan_vid[0]))
 		goto out_notsupp;
 
 	return 0;
@@ -284,7 +289,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
 	int err = 0;
 
 	/* nop if we're on the vlan push/pop non emulation mode */
-	if (mlx5_eswitch_vlan_actions_supported(esw->dev))
+	if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
 		return 0;
 
 	push = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH);
@@ -324,11 +329,11 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
 		if (vport->vlan_refcount)
 			goto skip_set_push;
 
-		err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport, attr->vlan_vid, 0,
+		err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport, attr->vlan_vid[0], 0,
 						    SET_VLAN_INSERT | SET_VLAN_STRIP);
 		if (err)
 			goto out;
-		vport->vlan = attr->vlan_vid;
+		vport->vlan = attr->vlan_vid[0];
 skip_set_push:
 		vport->vlan_refcount++;
 	}
@@ -347,7 +352,7 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
 	int err = 0;
 
 	/* nop if we're on the vlan push/pop non emulation mode */
-	if (mlx5_eswitch_vlan_actions_supported(esw->dev))
+	if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
 		return 0;
 
 	if (!attr->vlan_handled)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
index c9736238604a..5cf5f2a9d51f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
@@ -129,6 +129,7 @@ static void mlx5_fpga_tls_cmd_send(struct mlx5_fpga_device *fdev,
 static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock,
 				    void *ptr)
 {
+	unsigned long flags;
 	int ret;
 
 	/* TLS metadata format is 1 byte for syndrome followed
@@ -139,9 +140,9 @@ static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock,
 	BUILD_BUG_ON((SWID_END - 1) & 0xFF000000);
 
 	idr_preload(GFP_KERNEL);
-	spin_lock_irq(idr_spinlock);
+	spin_lock_irqsave(idr_spinlock, flags);
 	ret = idr_alloc(idr, ptr, SWID_START, SWID_END, GFP_ATOMIC);
-	spin_unlock_irq(idr_spinlock);
+	spin_unlock_irqrestore(idr_spinlock, flags);
 	idr_preload_end();
 
 	return ret;
@@ -157,6 +158,13 @@ static void mlx5_fpga_tls_release_swid(struct idr *idr,
 	spin_unlock_irqrestore(idr_spinlock, flags);
 }
 
+static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn,
+				   struct mlx5_fpga_device *fdev,
+				   struct mlx5_fpga_dma_buf *buf, u8 status)
+{
+	kfree(buf);
+}
+
 struct mlx5_teardown_stream_context {
 	struct mlx5_fpga_tls_command_context cmd;
 	u32 swid;
@@ -178,9 +186,13 @@ mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn,
 			mlx5_fpga_err(fdev,
 				      "Teardown stream failed with syndrome = %d",
 				      syndrome);
-		else
+		else if (MLX5_GET(tls_cmd, cmd->buf.sg[0].data, direction_sx))
 			mlx5_fpga_tls_release_swid(&fdev->tls->tx_idr,
-						   &fdev->tls->idr_spinlock,
+						   &fdev->tls->tx_idr_spinlock,
+						   ctx->swid);
+		else
+			mlx5_fpga_tls_release_swid(&fdev->tls->rx_idr,
+						   &fdev->tls->rx_idr_spinlock,
 						   ctx->swid);
 	}
 	mlx5_fpga_tls_put_command_ctx(cmd);
@@ -196,6 +208,40 @@ static void mlx5_fpga_tls_flow_to_cmd(void *flow, void *cmd)
 		 MLX5_GET(tls_flow, flow, direction_sx));
 }
 
+int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
+			    u64 rcd_sn)
+{
+	struct mlx5_fpga_dma_buf *buf;
+	int size = sizeof(*buf) + MLX5_TLS_COMMAND_SIZE;
+	void *flow;
+	void *cmd;
+	int ret;
+
+	buf = kzalloc(size, GFP_ATOMIC);
+	if (!buf)
+		return -ENOMEM;
+
+	cmd = (buf + 1);
+
+	rcu_read_lock();
+	flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
+	rcu_read_unlock();
+	mlx5_fpga_tls_flow_to_cmd(flow, cmd);
+
+	MLX5_SET(tls_cmd, cmd, swid, ntohl(handle));
+	MLX5_SET64(tls_cmd, cmd, tls_rcd_sn, be64_to_cpu(rcd_sn));
+	MLX5_SET(tls_cmd, cmd, tcp_sn, seq);
+	MLX5_SET(tls_cmd, cmd, command_type, CMD_RESYNC_RX);
+
+	buf->sg[0].data = cmd;
+	buf->sg[0].size = MLX5_TLS_COMMAND_SIZE;
+	buf->complete = mlx_tls_kfree_complete;
+
+	ret = mlx5_fpga_sbu_conn_sendmsg(mdev->fpga->tls->conn, buf);
+
+	return ret;
+}
+
 static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 					    void *flow, u32 swid, gfp_t flags)
 {
@@ -223,14 +269,18 @@ static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 			       mlx5_fpga_tls_teardown_completion);
 }
 
-void mlx5_fpga_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid,
-			       gfp_t flags)
+void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+			    gfp_t flags, bool direction_sx)
 {
 	struct mlx5_fpga_tls *tls = mdev->fpga->tls;
 	void *flow;
 
 	rcu_read_lock();
-	flow = idr_find(&tls->tx_idr, swid);
+	if (direction_sx)
+		flow = idr_find(&tls->tx_idr, swid);
+	else
+		flow = idr_find(&tls->rx_idr, swid);
+
 	rcu_read_unlock();
 
 	if (!flow) {
@@ -289,9 +339,11 @@ mlx5_fpga_tls_setup_completion(struct mlx5_fpga_conn *conn,
 		 * the command context because we might not have received
 		 * the tx completion yet.
 		 */
-		mlx5_fpga_tls_del_tx_flow(fdev->mdev,
-					  MLX5_GET(tls_cmd, tls_cmd, swid),
-					  GFP_ATOMIC);
+		mlx5_fpga_tls_del_flow(fdev->mdev,
+				       MLX5_GET(tls_cmd, tls_cmd, swid),
+				       GFP_ATOMIC,
+				       MLX5_GET(tls_cmd, tls_cmd,
+						direction_sx));
 	}
 
 	mlx5_fpga_tls_put_command_ctx(cmd);
@@ -415,8 +467,7 @@ int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev)
 	if (err)
 		goto error;
 
-	if (!(tls->caps & (MLX5_ACCEL_TLS_TX | MLX5_ACCEL_TLS_V12 |
-				 MLX5_ACCEL_TLS_AES_GCM128))) {
+	if (!(tls->caps & (MLX5_ACCEL_TLS_V12 | MLX5_ACCEL_TLS_AES_GCM128))) {
 		err = -ENOTSUPP;
 		goto error;
 	}
@@ -438,7 +489,9 @@ int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev)
 	INIT_LIST_HEAD(&tls->pending_cmds);
 
 	idr_init(&tls->tx_idr);
-	spin_lock_init(&tls->idr_spinlock);
+	idr_init(&tls->rx_idr);
+	spin_lock_init(&tls->tx_idr_spinlock);
+	spin_lock_init(&tls->rx_idr_spinlock);
 	fdev->tls = tls;
 	return 0;
 
@@ -500,9 +553,9 @@ static int mlx5_fpga_tls_set_key_material(void *cmd, u32 caps,
 	return 0;
 }
 
-static int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
-				  struct tls_crypto_info *crypto_info, u32 swid,
-				  u32 tcp_sn)
+static int _mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+				   struct tls_crypto_info *crypto_info,
+				   u32 swid, u32 tcp_sn)
 {
 	u32 caps = mlx5_fpga_tls_device_caps(mdev);
 	struct mlx5_setup_stream_context *ctx;
@@ -533,30 +586,42 @@ out:
 	return ret;
 }
 
-int mlx5_fpga_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
-			      struct tls_crypto_info *crypto_info,
-			      u32 start_offload_tcp_sn, u32 *p_swid)
+int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+			   struct tls_crypto_info *crypto_info,
+			   u32 start_offload_tcp_sn, u32 *p_swid,
+			   bool direction_sx)
 {
 	struct mlx5_fpga_tls *tls = mdev->fpga->tls;
 	int ret = -ENOMEM;
 	u32 swid;
 
-	ret = mlx5_fpga_tls_alloc_swid(&tls->tx_idr, &tls->idr_spinlock, flow);
+	if (direction_sx)
+		ret = mlx5_fpga_tls_alloc_swid(&tls->tx_idr,
+					       &tls->tx_idr_spinlock, flow);
+	else
+		ret = mlx5_fpga_tls_alloc_swid(&tls->rx_idr,
+					       &tls->rx_idr_spinlock, flow);
+
 	if (ret < 0)
 		return ret;
 
 	swid = ret;
-	MLX5_SET(tls_flow, flow, direction_sx, 1);
+	MLX5_SET(tls_flow, flow, direction_sx, direction_sx ? 1 : 0);
 
-	ret = mlx5_fpga_tls_add_flow(mdev, flow, crypto_info, swid,
-				     start_offload_tcp_sn);
+	ret = _mlx5_fpga_tls_add_flow(mdev, flow, crypto_info, swid,
+				      start_offload_tcp_sn);
 	if (ret && ret != -EINTR)
 		goto free_swid;
 
 	*p_swid = swid;
 	return 0;
 free_swid:
-	mlx5_fpga_tls_release_swid(&tls->tx_idr, &tls->idr_spinlock, swid);
+	if (direction_sx)
+		mlx5_fpga_tls_release_swid(&tls->tx_idr,
+					   &tls->tx_idr_spinlock, swid);
+	else
+		mlx5_fpga_tls_release_swid(&tls->rx_idr,
+					   &tls->rx_idr_spinlock, swid);
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h
index 800a214e4e49..3b2e37bf76fe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h
@@ -46,15 +46,18 @@ struct mlx5_fpga_tls {
 	struct mlx5_fpga_conn *conn;
 
 	struct idr tx_idr;
-	spinlock_t idr_spinlock; /* protects the IDR */
+	struct idr rx_idr;
+	spinlock_t tx_idr_spinlock; /* protects the IDR */
+	spinlock_t rx_idr_spinlock; /* protects the IDR */
 };
 
-int mlx5_fpga_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
-			      struct tls_crypto_info *crypto_info,
-			      u32 start_offload_tcp_sn, u32 *p_swid);
+int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+			   struct tls_crypto_info *crypto_info,
+			   u32 start_offload_tcp_sn, u32 *p_swid,
+			   bool direction_sx);
 
-void mlx5_fpga_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid,
-			       gfp_t flags);
+void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+			    gfp_t flags, bool direction_sx);
 
 bool mlx5_fpga_is_tls_device(struct mlx5_core_dev *mdev);
 int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev);
@@ -65,4 +68,7 @@ static inline u32 mlx5_fpga_tls_device_caps(struct mlx5_core_dev *mdev)
 	return mdev->fpga->tls->caps;
 }
 
+int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
+			    u64 rcd_sn);
+
 #endif /* __MLX5_FPGA_TLS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 56cee33cfb83..f418541af7cf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1803,7 +1803,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 		    struct mlx5_flow_spec *spec,
 		    struct mlx5_flow_act *flow_act,
 		    struct mlx5_flow_destination *dest,
-		    int dest_num)
+		    int num_dest)
 {
 	struct mlx5_flow_root_namespace *root = find_root(&ft->node);
 	struct mlx5_flow_destination gen_dest = {};
@@ -1816,7 +1816,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 	if (flow_act->action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
 		if (!fwd_next_prio_supported(ft))
 			return ERR_PTR(-EOPNOTSUPP);
-		if (dest_num)
+		if (num_dest)
 			return ERR_PTR(-EINVAL);
 		mutex_lock(&root->chain_lock);
 		next_ft = find_next_chained_ft(prio);
@@ -1824,7 +1824,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 			gen_dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 			gen_dest.ft = next_ft;
 			dest = &gen_dest;
-			dest_num = 1;
+			num_dest = 1;
 			flow_act->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 		} else {
 			mutex_unlock(&root->chain_lock);
@@ -1832,7 +1832,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 		}
 	}
 
-	handle = _mlx5_add_flow_rules(ft, spec, flow_act, dest, dest_num);
+	handle = _mlx5_add_flow_rules(ft, spec, flow_act, dest, num_dest);
 
 	if (sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
 		if (!IS_ERR_OR_NULL(handle) &&
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
index a8eecedd46c2..02e2e4575e4f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
@@ -33,8 +33,15 @@
 #ifndef __LIB_CLOCK_H__
 #define __LIB_CLOCK_H__
 
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
 void mlx5_init_clock(struct mlx5_core_dev *mdev);
 void mlx5_cleanup_clock(struct mlx5_core_dev *mdev);
+void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
+
+static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
+{
+	return mdev->clock.ptp ? ptp_clock_index(mdev->clock.ptp) : -1;
+}
 
 static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
 						u64 timestamp)
@@ -48,4 +55,21 @@ static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
 	return ns_to_ktime(nsec);
 }
 
+#else
+static inline void mlx5_init_clock(struct mlx5_core_dev *mdev) {}
+static inline void mlx5_cleanup_clock(struct mlx5_core_dev *mdev) {}
+static inline void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe) {}
+
+static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
+{
+	return -1;
+}
+
+static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
+						u64 timestamp)
+{
+	return 0;
+}
+#endif
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
new file mode 100644
index 000000000000..9a8fd762167b
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
@@ -0,0 +1,230 @@
+/*
+ * Copyright (c) 2016, Mellanox Technologies, Ltd.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mlx5/driver.h>
+#include "mlx5_core.h"
+#include "vxlan.h"
+
+struct mlx5_vxlan {
+	struct mlx5_core_dev		*mdev;
+	spinlock_t			lock; /* protect vxlan table */
+	/* max_num_ports is usuallly 4, 16 buckets is more than enough */
+	DECLARE_HASHTABLE(htable, 4);
+	int				num_ports;
+	struct mutex                    sync_lock; /* sync add/del port HW operations */
+};
+
+struct mlx5_vxlan_port {
+	struct hlist_node hlist;
+	atomic_t refcount;
+	u16 udp_port;
+};
+
+static inline u8 mlx5_vxlan_max_udp_ports(struct mlx5_core_dev *mdev)
+{
+	return MLX5_CAP_ETH(mdev, max_vxlan_udp_ports) ?: 4;
+}
+
+static int mlx5_vxlan_core_add_port_cmd(struct mlx5_core_dev *mdev, u16 port)
+{
+	u32 in[MLX5_ST_SZ_DW(add_vxlan_udp_dport_in)]   = {0};
+	u32 out[MLX5_ST_SZ_DW(add_vxlan_udp_dport_out)] = {0};
+
+	MLX5_SET(add_vxlan_udp_dport_in, in, opcode,
+		 MLX5_CMD_OP_ADD_VXLAN_UDP_DPORT);
+	MLX5_SET(add_vxlan_udp_dport_in, in, vxlan_udp_port, port);
+	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+static int mlx5_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port)
+{
+	u32 in[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_in)]   = {0};
+	u32 out[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_out)] = {0};
+
+	MLX5_SET(delete_vxlan_udp_dport_in, in, opcode,
+		 MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT);
+	MLX5_SET(delete_vxlan_udp_dport_in, in, vxlan_udp_port, port);
+	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+static struct mlx5_vxlan_port*
+mlx5_vxlan_lookup_port_locked(struct mlx5_vxlan *vxlan, u16 port)
+{
+	struct mlx5_vxlan_port *vxlanp;
+
+	hash_for_each_possible(vxlan->htable, vxlanp, hlist, port) {
+		if (vxlanp->udp_port == port)
+			return vxlanp;
+	}
+
+	return NULL;
+}
+
+struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port)
+{
+	struct mlx5_vxlan_port *vxlanp;
+
+	if (!mlx5_vxlan_allowed(vxlan))
+		return NULL;
+
+	spin_lock_bh(&vxlan->lock);
+	vxlanp = mlx5_vxlan_lookup_port_locked(vxlan, port);
+	spin_unlock_bh(&vxlan->lock);
+
+	return vxlanp;
+}
+
+int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port)
+{
+	struct mlx5_vxlan_port *vxlanp;
+	int ret = -ENOSPC;
+
+	vxlanp = mlx5_vxlan_lookup_port(vxlan, port);
+	if (vxlanp) {
+		atomic_inc(&vxlanp->refcount);
+		return 0;
+	}
+
+	mutex_lock(&vxlan->sync_lock);
+	if (vxlan->num_ports >= mlx5_vxlan_max_udp_ports(vxlan->mdev)) {
+		mlx5_core_info(vxlan->mdev,
+			       "UDP port (%d) not offloaded, max number of UDP ports (%d) are already offloaded\n",
+			       port, mlx5_vxlan_max_udp_ports(vxlan->mdev));
+		ret = -ENOSPC;
+		goto unlock;
+	}
+
+	ret = mlx5_vxlan_core_add_port_cmd(vxlan->mdev, port);
+	if (ret)
+		goto unlock;
+
+	vxlanp = kzalloc(sizeof(*vxlanp), GFP_KERNEL);
+	if (!vxlanp) {
+		ret = -ENOMEM;
+		goto err_delete_port;
+	}
+
+	vxlanp->udp_port = port;
+	atomic_set(&vxlanp->refcount, 1);
+
+	spin_lock_bh(&vxlan->lock);
+	hash_add(vxlan->htable, &vxlanp->hlist, port);
+	spin_unlock_bh(&vxlan->lock);
+
+	vxlan->num_ports++;
+	mutex_unlock(&vxlan->sync_lock);
+	return 0;
+
+err_delete_port:
+	mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port);
+
+unlock:
+	mutex_unlock(&vxlan->sync_lock);
+	return ret;
+}
+
+int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port)
+{
+	struct mlx5_vxlan_port *vxlanp;
+	bool remove = false;
+	int ret = 0;
+
+	mutex_lock(&vxlan->sync_lock);
+
+	spin_lock_bh(&vxlan->lock);
+	vxlanp = mlx5_vxlan_lookup_port_locked(vxlan, port);
+	if (!vxlanp) {
+		ret = -ENOENT;
+		goto out_unlock;
+	}
+
+	if (atomic_dec_and_test(&vxlanp->refcount)) {
+		hash_del(&vxlanp->hlist);
+		remove = true;
+	}
+
+out_unlock:
+	spin_unlock_bh(&vxlan->lock);
+
+	if (remove) {
+		mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port);
+		kfree(vxlanp);
+		vxlan->num_ports--;
+	}
+
+	mutex_unlock(&vxlan->sync_lock);
+
+	return ret;
+}
+
+struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_vxlan *vxlan;
+
+	if (!MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) || !mlx5_core_is_pf(mdev))
+		return ERR_PTR(-ENOTSUPP);
+
+	vxlan = kzalloc(sizeof(*vxlan), GFP_KERNEL);
+	if (!vxlan)
+		return ERR_PTR(-ENOMEM);
+
+	vxlan->mdev = mdev;
+	mutex_init(&vxlan->sync_lock);
+	spin_lock_init(&vxlan->lock);
+	hash_init(vxlan->htable);
+
+	/* Hardware adds 4789 by default */
+	mlx5_vxlan_add_port(vxlan, 4789);
+
+	return vxlan;
+}
+
+void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan)
+{
+	struct mlx5_vxlan_port *vxlanp;
+	struct hlist_node *tmp;
+	int bkt;
+
+	if (!mlx5_vxlan_allowed(vxlan))
+		return;
+
+	/* Lockless since we are the only hash table consumers*/
+	hash_for_each_safe(vxlan->htable, bkt, tmp, vxlanp, hlist) {
+		hash_del(&vxlanp->hlist);
+		mlx5_vxlan_core_del_port_cmd(vxlan->mdev, vxlanp->udp_port);
+		kfree(vxlanp);
+	}
+
+	kfree(vxlan);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h
index 5ef6ae7d568a..8fb0eb08fa6d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h
@@ -33,31 +33,32 @@
 #define __MLX5_VXLAN_H__
 
 #include <linux/mlx5/driver.h>
-#include "en.h"
 
-struct mlx5e_vxlan {
-	atomic_t refcount;
-	u16 udp_port;
-};
+struct mlx5_vxlan;
+struct mlx5_vxlan_port;
 
-struct mlx5e_vxlan_work {
-	struct work_struct	work;
-	struct mlx5e_priv	*priv;
-	sa_family_t		sa_family;
-	u16			port;
-};
-
-static inline bool mlx5e_vxlan_allowed(struct mlx5_core_dev *mdev)
+static inline bool mlx5_vxlan_allowed(struct mlx5_vxlan *vxlan)
 {
-	return (MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) &&
-		mlx5_core_is_pf(mdev));
+	/* not allowed reason is encoded in vxlan pointer as error,
+	 * on mlx5_vxlan_create
+	 */
+	return !IS_ERR_OR_NULL(vxlan);
 }
 
-void mlx5e_vxlan_init(struct mlx5e_priv *priv);
-void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv);
-
-void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, sa_family_t sa_family,
-			    u16 port, int add);
-struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port);
+#if IS_ENABLED(CONFIG_VXLAN)
+struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev);
+void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan);
+int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port);
+int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port);
+struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port);
+#else
+static inline struct mlx5_vxlan*
+mlx5_vxlan_create(struct mlx5_core_dev *mdev) { return ERR_PTR(-EOPNOTSUPP); }
+static inline void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) { return; }
+static inline int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; }
+static inline int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; }
+static inline struct mx5_vxlan_port*
+mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port) { return NULL; }
+#endif
 
 #endif /* __MLX5_VXLAN_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index f9b950e1bd85..cf3e4a659052 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -62,6 +62,8 @@
 #include "accel/ipsec.h"
 #include "accel/tls.h"
 #include "lib/clock.h"
+#include "lib/vxlan.h"
+#include "diag/fw_tracer.h"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver");
@@ -321,7 +323,9 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
 	struct mlx5_eq_table *table = &priv->eq_table;
-	int num_eqs = 1 << MLX5_CAP_GEN(dev, log_max_eq);
+	int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
+		      MLX5_CAP_GEN(dev, max_num_eqs) :
+		      1 << MLX5_CAP_GEN(dev, log_max_eq);
 	int nvec;
 	int err;
 
@@ -960,6 +964,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 
 	mlx5_init_clock(dev);
 
+	dev->vxlan = mlx5_vxlan_create(dev);
+
 	err = mlx5_init_rl_table(dev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to init rate limiting\n");
@@ -990,6 +996,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 		goto err_sriov_cleanup;
 	}
 
+	dev->tracer = mlx5_fw_tracer_create(dev);
+
 	return 0;
 
 err_sriov_cleanup:
@@ -1001,6 +1009,7 @@ err_mpfs_cleanup:
 err_rl_cleanup:
 	mlx5_cleanup_rl_table(dev);
 err_tables_cleanup:
+	mlx5_vxlan_destroy(dev->vxlan);
 	mlx5_cleanup_mkey_table(dev);
 	mlx5_cleanup_srq_table(dev);
 	mlx5_cleanup_qp_table(dev);
@@ -1015,11 +1024,13 @@ out:
 
 static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 {
+	mlx5_fw_tracer_destroy(dev->tracer);
 	mlx5_fpga_cleanup(dev);
 	mlx5_sriov_cleanup(dev);
 	mlx5_eswitch_cleanup(dev->priv.eswitch);
 	mlx5_mpfs_cleanup(dev);
 	mlx5_cleanup_rl_table(dev);
+	mlx5_vxlan_destroy(dev->vxlan);
 	mlx5_cleanup_clock(dev);
 	mlx5_cleanup_reserved_gids(dev);
 	mlx5_cleanup_mkey_table(dev);
@@ -1167,10 +1178,16 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto err_put_uars;
 	}
 
+	err = mlx5_fw_tracer_init(dev->tracer);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to init FW tracer\n");
+		goto err_fw_tracer;
+	}
+
 	err = alloc_comp_eqs(dev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to alloc completion EQs\n");
-		goto err_stop_eqs;
+		goto err_comp_eqs;
 	}
 
 	err = mlx5_irq_set_affinity_hints(dev);
@@ -1252,7 +1269,10 @@ err_fpga_start:
 err_affinity_hints:
 	free_comp_eqs(dev);
 
-err_stop_eqs:
+err_comp_eqs:
+	mlx5_fw_tracer_cleanup(dev->tracer);
+
+err_fw_tracer:
 	mlx5_stop_eqs(dev);
 
 err_put_uars:
@@ -1320,6 +1340,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	mlx5_fpga_device_stop(dev);
 	mlx5_irq_clear_affinity_hints(dev);
 	free_comp_eqs(dev);
+	mlx5_fw_tracer_cleanup(dev->tracer);
 	mlx5_stop_eqs(dev);
 	mlx5_put_uars_page(dev, priv->uar);
 	mlx5_free_irq_vectors(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 49955117ae36..b4134fa0bba3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -99,7 +99,6 @@ void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
 		     unsigned long param);
 void mlx5_core_page_fault(struct mlx5_core_dev *dev,
 			  struct mlx5_pagefault *pfault);
-void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
 void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
 void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force);
 void mlx5_disable_device(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 7eecd5b07bb1..b02af317c125 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -62,17 +62,6 @@ u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport)
 
 	return MLX5_GET(query_vport_state_out, out, state);
 }
-EXPORT_SYMBOL_GPL(mlx5_query_vport_state);
-
-u8 mlx5_query_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport)
-{
-	u32 out[MLX5_ST_SZ_DW(query_vport_state_out)] = {0};
-
-	_mlx5_query_vport_state(mdev, opmod, vport, out, sizeof(out));
-
-	return MLX5_GET(query_vport_state_out, out, admin_state);
-}
-EXPORT_SYMBOL_GPL(mlx5_query_vport_admin_state);
 
 int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
 				  u16 vport, u8 state)
@@ -90,7 +79,6 @@ int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
 
 	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
 }
-EXPORT_SYMBOL_GPL(mlx5_modify_vport_admin_state);
 
 static int mlx5_query_nic_vport_context(struct mlx5_core_dev *mdev, u16 vport,
 					u32 *out, int outlen)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
deleted file mode 100644
index 2f74953e4561..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ /dev/null
@@ -1,190 +0,0 @@
-/*
- * Copyright (c) 2016, Mellanox Technologies, Ltd.  All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mlx5/driver.h>
-#include "mlx5_core.h"
-#include "vxlan.h"
-
-void mlx5e_vxlan_init(struct mlx5e_priv *priv)
-{
-	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
-
-	spin_lock_init(&vxlan_db->lock);
-	INIT_RADIX_TREE(&vxlan_db->tree, GFP_ATOMIC);
-}
-
-static int mlx5e_vxlan_core_add_port_cmd(struct mlx5_core_dev *mdev, u16 port)
-{
-	u32 in[MLX5_ST_SZ_DW(add_vxlan_udp_dport_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(add_vxlan_udp_dport_out)] = {0};
-
-	MLX5_SET(add_vxlan_udp_dport_in, in, opcode,
-		 MLX5_CMD_OP_ADD_VXLAN_UDP_DPORT);
-	MLX5_SET(add_vxlan_udp_dport_in, in, vxlan_udp_port, port);
-	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
-}
-
-static int mlx5e_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port)
-{
-	u32 in[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_out)] = {0};
-
-	MLX5_SET(delete_vxlan_udp_dport_in, in, opcode,
-		 MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT);
-	MLX5_SET(delete_vxlan_udp_dport_in, in, vxlan_udp_port, port);
-	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
-}
-
-struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port)
-{
-	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
-	struct mlx5e_vxlan *vxlan;
-
-	spin_lock_bh(&vxlan_db->lock);
-	vxlan = radix_tree_lookup(&vxlan_db->tree, port);
-	spin_unlock_bh(&vxlan_db->lock);
-
-	return vxlan;
-}
-
-static void mlx5e_vxlan_add_port(struct work_struct *work)
-{
-	struct mlx5e_vxlan_work *vxlan_work =
-		container_of(work, struct mlx5e_vxlan_work, work);
-	struct mlx5e_priv *priv = vxlan_work->priv;
-	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
-	u16 port = vxlan_work->port;
-	struct mlx5e_vxlan *vxlan;
-	int err;
-
-	mutex_lock(&priv->state_lock);
-	vxlan = mlx5e_vxlan_lookup_port(priv, port);
-	if (vxlan) {
-		atomic_inc(&vxlan->refcount);
-		goto free_work;
-	}
-
-	if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port))
-		goto free_work;
-
-	vxlan = kzalloc(sizeof(*vxlan), GFP_KERNEL);
-	if (!vxlan)
-		goto err_delete_port;
-
-	vxlan->udp_port = port;
-	atomic_set(&vxlan->refcount, 1);
-
-	spin_lock_bh(&vxlan_db->lock);
-	err = radix_tree_insert(&vxlan_db->tree, vxlan->udp_port, vxlan);
-	spin_unlock_bh(&vxlan_db->lock);
-	if (err)
-		goto err_free;
-
-	goto free_work;
-
-err_free:
-	kfree(vxlan);
-err_delete_port:
-	mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
-free_work:
-	mutex_unlock(&priv->state_lock);
-	kfree(vxlan_work);
-}
-
-static void mlx5e_vxlan_del_port(struct work_struct *work)
-{
-	struct mlx5e_vxlan_work *vxlan_work =
-		container_of(work, struct mlx5e_vxlan_work, work);
-	struct mlx5e_priv *priv         = vxlan_work->priv;
-	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
-	u16 port = vxlan_work->port;
-	struct mlx5e_vxlan *vxlan;
-	bool remove = false;
-
-	mutex_lock(&priv->state_lock);
-	spin_lock_bh(&vxlan_db->lock);
-	vxlan = radix_tree_lookup(&vxlan_db->tree, port);
-	if (!vxlan)
-		goto out_unlock;
-
-	if (atomic_dec_and_test(&vxlan->refcount)) {
-		radix_tree_delete(&vxlan_db->tree, port);
-		remove = true;
-	}
-
-out_unlock:
-	spin_unlock_bh(&vxlan_db->lock);
-
-	if (remove) {
-		mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
-		kfree(vxlan);
-	}
-	mutex_unlock(&priv->state_lock);
-	kfree(vxlan_work);
-}
-
-void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, sa_family_t sa_family,
-			    u16 port, int add)
-{
-	struct mlx5e_vxlan_work *vxlan_work;
-
-	vxlan_work = kmalloc(sizeof(*vxlan_work), GFP_ATOMIC);
-	if (!vxlan_work)
-		return;
-
-	if (add)
-		INIT_WORK(&vxlan_work->work, mlx5e_vxlan_add_port);
-	else
-		INIT_WORK(&vxlan_work->work, mlx5e_vxlan_del_port);
-
-	vxlan_work->priv = priv;
-	vxlan_work->port = port;
-	vxlan_work->sa_family = sa_family;
-	queue_work(priv->wq, &vxlan_work->work);
-}
-
-void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv)
-{
-	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
-	struct mlx5e_vxlan *vxlan;
-	unsigned int port = 0;
-
-	/* Lockless since we are the only radix-tree consumers, wq is disabled */
-	while (radix_tree_gang_lookup(&vxlan_db->tree, (void **)&vxlan, port, 1)) {
-		port = vxlan->udp_port;
-		radix_tree_delete(&vxlan_db->tree, port);
-		mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
-		kfree(vxlan);
-	}
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
index 0b47126815b6..2bd4c3184eba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
@@ -229,6 +229,11 @@ static inline int mlx5_wq_ll_is_empty(struct mlx5_wq_ll *wq)
 	return !wq->cur_sz;
 }
 
+static inline int mlx5_wq_ll_missing(struct mlx5_wq_ll *wq)
+{
+	return wq->fbc.sz_m1 - wq->cur_sz;
+}
+
 static inline void *mlx5_wq_ll_get_wqe(struct mlx5_wq_ll *wq, u16 ix)
 {
 	return mlx5_frag_buf_get_wqe(&wq->fbc, ix);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
index 82827a8d3d67..8a291eb36c64 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
@@ -78,6 +78,7 @@ config MLXSW_SPECTRUM
 	depends on IPV6 || IPV6=n
 	depends on NET_IPGRE || NET_IPGRE=n
 	depends on IPV6_GRE || IPV6_GRE=n
+	select GENERIC_ALLOCATOR
 	select PARMAN
 	select MLXFW
 	default m
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 0cadcabfe86f..68fa44a41485 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -15,11 +15,18 @@ mlxsw_switchx2-objs		:= switchx2.o
 obj-$(CONFIG_MLXSW_SPECTRUM)	+= mlxsw_spectrum.o
 mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum_switchdev.o spectrum_router.o \
-				   spectrum_kvdl.o spectrum_acl_tcam.o \
-				   spectrum_acl.o spectrum_flower.o \
-				   spectrum_cnt.o spectrum_fid.o \
-				   spectrum_ipip.o spectrum_acl_flex_actions.o \
-				   spectrum_mr.o spectrum_mr_tcam.o \
+				   spectrum1_kvdl.o spectrum2_kvdl.o \
+				   spectrum_kvdl.o \
+				   spectrum_acl_tcam.o spectrum_acl_ctcam.o \
+				   spectrum_acl_atcam.o spectrum_acl_erp.o \
+				   spectrum1_acl_tcam.o spectrum2_acl_tcam.o \
+				   spectrum_acl.o \
+				   spectrum_flower.o spectrum_cnt.o \
+				   spectrum_fid.o spectrum_ipip.o \
+				   spectrum_acl_flex_actions.o \
+				   spectrum_acl_flex_keys.o \
+				   spectrum1_mr_tcam.o spectrum2_mr_tcam.o \
+				   spectrum_mr_tcam.o spectrum_mr.o \
 				   spectrum_qdisc.o spectrum_span.o
 mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB)	+= spectrum_dcb.o
 mlxsw_spectrum-$(CONFIG_NET_DEVLINK) += spectrum_dpipe.o
diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
index 2bc48054b685..0772e4339b33 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
@@ -1,37 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/cmd.h
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_CMD_H
 #define _MLXSW_CMD_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index f9c724752a32..81533d7f395c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1,38 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/core.c
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2015 Elad Raz <eladr@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -759,15 +726,6 @@ static struct mlxsw_driver *mlxsw_core_driver_get(const char *kind)
 	return mlxsw_driver;
 }
 
-static void mlxsw_core_driver_put(const char *kind)
-{
-	struct mlxsw_driver *mlxsw_driver;
-
-	spin_lock(&mlxsw_core_driver_list_lock);
-	mlxsw_driver = __driver_find(kind);
-	spin_unlock(&mlxsw_core_driver_list_lock);
-}
-
 static int mlxsw_devlink_port_split(struct devlink *devlink,
 				    unsigned int port_index,
 				    unsigned int count,
@@ -1115,7 +1073,6 @@ err_bus_init:
 	if (!reload)
 		devlink_free(devlink);
 err_devlink_alloc:
-	mlxsw_core_driver_put(device_kind);
 	return err;
 }
 EXPORT_SYMBOL(mlxsw_core_bus_device_register);
@@ -1123,7 +1080,6 @@ EXPORT_SYMBOL(mlxsw_core_bus_device_register);
 void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 				      bool reload)
 {
-	const char *device_kind = mlxsw_core->bus_info->device_kind;
 	struct devlink *devlink = priv_to_devlink(mlxsw_core);
 
 	if (mlxsw_core->reload_fail)
@@ -1144,7 +1100,6 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 		return;
 reload_fail:
 	devlink_free(devlink);
-	mlxsw_core_driver_put(device_kind);
 }
 EXPORT_SYMBOL(mlxsw_core_bus_device_unregister);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index 552cfa29c2f7..655ddd204ab2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -1,38 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/core.h
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2015 Elad Raz <eladr@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_CORE_H
 #define _MLXSW_CORE_H
@@ -362,6 +329,7 @@ struct mlxsw_fw_rev {
 	u16 major;
 	u16 minor;
 	u16 subminor;
+	u16 can_reset_minor;
 };
 
 struct mlxsw_bus_info {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index f6f6a568d66a..c51b2adfc1e1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
- * Copyright (c) 2017, 2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -355,9 +324,24 @@ struct mlxsw_afa_block *mlxsw_afa_block_create(struct mlxsw_afa *mlxsw_afa)
 	block->first_set = mlxsw_afa_set_create(true);
 	if (!block->first_set)
 		goto err_first_set_create;
-	block->cur_set = block->first_set;
+
+	/* In case user instructs to have dummy first set, we leave it
+	 * empty here and create another, real, set right away.
+	 */
+	if (mlxsw_afa->ops->dummy_first_set) {
+		block->cur_set = mlxsw_afa_set_create(false);
+		if (!block->cur_set)
+			goto err_second_set_create;
+		block->cur_set->prev = block->first_set;
+		block->first_set->next = block->cur_set;
+	} else {
+		block->cur_set = block->first_set;
+	}
+
 	return block;
 
+err_second_set_create:
+	mlxsw_afa_set_destroy(block->first_set);
 err_first_set_create:
 	kfree(block);
 	return NULL;
@@ -419,11 +403,31 @@ char *mlxsw_afa_block_first_set(struct mlxsw_afa_block *block)
 }
 EXPORT_SYMBOL(mlxsw_afa_block_first_set);
 
-u32 mlxsw_afa_block_first_set_kvdl_index(struct mlxsw_afa_block *block)
+char *mlxsw_afa_block_cur_set(struct mlxsw_afa_block *block)
 {
-	return block->first_set->kvdl_index;
+	return block->cur_set->ht_key.enc_actions;
 }
-EXPORT_SYMBOL(mlxsw_afa_block_first_set_kvdl_index);
+EXPORT_SYMBOL(mlxsw_afa_block_cur_set);
+
+u32 mlxsw_afa_block_first_kvdl_index(struct mlxsw_afa_block *block)
+{
+	/* First set is never in KVD linear. So the first set
+	 * with valid KVD linear index is always the second one.
+	 */
+	if (WARN_ON(!block->first_set->next))
+		return 0;
+	return block->first_set->next->kvdl_index;
+}
+EXPORT_SYMBOL(mlxsw_afa_block_first_kvdl_index);
+
+int mlxsw_afa_block_activity_get(struct mlxsw_afa_block *block, bool *activity)
+{
+	u32 kvdl_index = mlxsw_afa_block_first_kvdl_index(block);
+
+	return block->afa->ops->kvdl_set_activity_get(block->afa->ops_priv,
+						      kvdl_index, activity);
+}
+EXPORT_SYMBOL(mlxsw_afa_block_activity_get);
 
 int mlxsw_afa_block_continue(struct mlxsw_afa_block *block)
 {
@@ -724,14 +728,17 @@ mlxsw_afa_vlan_pack(char *payload,
 }
 
 int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block,
-				       u16 vid, u8 pcp, u8 et)
+				       u16 vid, u8 pcp, u8 et,
+				       struct netlink_ext_ack *extack)
 {
 	char *act = mlxsw_afa_block_append_action(block,
 						  MLXSW_AFA_VLAN_CODE,
 						  MLXSW_AFA_VLAN_SIZE);
 
-	if (IS_ERR(act))
+	if (IS_ERR(act)) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot append vlan_modify action");
 		return PTR_ERR(act);
+	}
 	mlxsw_afa_vlan_pack(act, MLXSW_AFA_VLAN_VLAN_TAG_CMD_NOP,
 			    MLXSW_AFA_VLAN_CMD_SET_OUTER, vid,
 			    MLXSW_AFA_VLAN_CMD_SET_OUTER, pcp,
@@ -925,19 +932,23 @@ mlxsw_afa_block_append_allocated_mirror(struct mlxsw_afa_block *block,
 
 int
 mlxsw_afa_block_append_mirror(struct mlxsw_afa_block *block, u8 local_in_port,
-			      const struct net_device *out_dev, bool ingress)
+			      const struct net_device *out_dev, bool ingress,
+			      struct netlink_ext_ack *extack)
 {
 	struct mlxsw_afa_mirror *mirror;
 	int err;
 
 	mirror = mlxsw_afa_mirror_create(block, local_in_port, out_dev,
 					 ingress);
-	if (IS_ERR(mirror))
+	if (IS_ERR(mirror)) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot create mirror action");
 		return PTR_ERR(mirror);
-
+	}
 	err = mlxsw_afa_block_append_allocated_mirror(block, mirror->span_id);
-	if (err)
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot append mirror action");
 		goto err_append_allocated_mirror;
+	}
 
 	return 0;
 
@@ -987,23 +998,29 @@ mlxsw_afa_forward_pack(char *payload, enum mlxsw_afa_forward_type type,
 }
 
 int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block,
-			       u8 local_port, bool in_port)
+			       u8 local_port, bool in_port,
+			       struct netlink_ext_ack *extack)
 {
 	struct mlxsw_afa_fwd_entry_ref *fwd_entry_ref;
 	u32 kvdl_index;
 	char *act;
 	int err;
 
-	if (in_port)
+	if (in_port) {
+		NL_SET_ERR_MSG_MOD(extack, "Forwarding to ingress port is not supported");
 		return -EOPNOTSUPP;
+	}
 	fwd_entry_ref = mlxsw_afa_fwd_entry_ref_create(block, local_port);
-	if (IS_ERR(fwd_entry_ref))
+	if (IS_ERR(fwd_entry_ref)) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot create forward action");
 		return PTR_ERR(fwd_entry_ref);
+	}
 	kvdl_index = fwd_entry_ref->fwd_entry->kvdl_index;
 
 	act = mlxsw_afa_block_append_action(block, MLXSW_AFA_FORWARD_CODE,
 					    MLXSW_AFA_FORWARD_SIZE);
 	if (IS_ERR(act)) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot append forward action");
 		err = PTR_ERR(act);
 		goto err_append_action;
 	}
@@ -1068,21 +1085,25 @@ int mlxsw_afa_block_append_allocated_counter(struct mlxsw_afa_block *block,
 EXPORT_SYMBOL(mlxsw_afa_block_append_allocated_counter);
 
 int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block,
-				   u32 *p_counter_index)
+				   u32 *p_counter_index,
+				   struct netlink_ext_ack *extack)
 {
 	struct mlxsw_afa_counter *counter;
 	u32 counter_index;
 	int err;
 
 	counter = mlxsw_afa_counter_create(block);
-	if (IS_ERR(counter))
+	if (IS_ERR(counter)) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot create count action");
 		return PTR_ERR(counter);
+	}
 	counter_index = counter->counter_index;
 
 	err = mlxsw_afa_block_append_allocated_counter(block, counter_index);
-	if (err)
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot append count action");
 		goto err_append_allocated_counter;
-
+	}
 	if (p_counter_index)
 		*p_counter_index = counter_index;
 	return 0;
@@ -1125,13 +1146,16 @@ static inline void mlxsw_afa_virfwd_pack(char *payload,
 	mlxsw_afa_virfwd_fid_set(payload, fid);
 }
 
-int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid)
+int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid,
+				   struct netlink_ext_ack *extack)
 {
 	char *act = mlxsw_afa_block_append_action(block,
 						  MLXSW_AFA_VIRFWD_CODE,
 						  MLXSW_AFA_VIRFWD_SIZE);
-	if (IS_ERR(act))
+	if (IS_ERR(act)) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot append fid_set action");
 		return PTR_ERR(act);
+	}
 	mlxsw_afa_virfwd_pack(act, MLXSW_AFA_VIRFWD_FID_CMD_SET, fid);
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
index 3a155d104384..0e3a59dda12e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_CORE_ACL_FLEX_ACTIONS_H
 #define _MLXSW_CORE_ACL_FLEX_ACTIONS_H
@@ -45,6 +14,8 @@ struct mlxsw_afa_ops {
 	int (*kvdl_set_add)(void *priv, u32 *p_kvdl_index,
 			    char *enc_actions, bool is_first);
 	void (*kvdl_set_del)(void *priv, u32 kvdl_index, bool is_first);
+	int (*kvdl_set_activity_get)(void *priv, u32 kvdl_index,
+				     bool *activity);
 	int (*kvdl_fwd_entry_add)(void *priv, u32 *p_kvdl_index, u8 local_port);
 	void (*kvdl_fwd_entry_del)(void *priv, u32 kvdl_index);
 	int (*counter_index_get)(void *priv, unsigned int *p_counter_index);
@@ -54,6 +25,7 @@ struct mlxsw_afa_ops {
 			  bool ingress, int *p_span_id);
 	void (*mirror_del)(void *priv, u8 local_in_port, int span_id,
 			   bool ingress);
+	bool dummy_first_set;
 };
 
 struct mlxsw_afa *mlxsw_afa_create(unsigned int max_acts_per_set,
@@ -64,7 +36,9 @@ struct mlxsw_afa_block *mlxsw_afa_block_create(struct mlxsw_afa *mlxsw_afa);
 void mlxsw_afa_block_destroy(struct mlxsw_afa_block *block);
 int mlxsw_afa_block_commit(struct mlxsw_afa_block *block);
 char *mlxsw_afa_block_first_set(struct mlxsw_afa_block *block);
-u32 mlxsw_afa_block_first_set_kvdl_index(struct mlxsw_afa_block *block);
+char *mlxsw_afa_block_cur_set(struct mlxsw_afa_block *block);
+u32 mlxsw_afa_block_first_kvdl_index(struct mlxsw_afa_block *block);
+int mlxsw_afa_block_activity_get(struct mlxsw_afa_block *block, bool *activity);
 int mlxsw_afa_block_continue(struct mlxsw_afa_block *block);
 int mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id);
 int mlxsw_afa_block_terminate(struct mlxsw_afa_block *block);
@@ -75,16 +49,21 @@ int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block,
 int mlxsw_afa_block_append_mirror(struct mlxsw_afa_block *block,
 				  u8 local_in_port,
 				  const struct net_device *out_dev,
-				  bool ingress);
+				  bool ingress,
+				  struct netlink_ext_ack *extack);
 int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block,
-			       u8 local_port, bool in_port);
+			       u8 local_port, bool in_port,
+			       struct netlink_ext_ack *extack);
 int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block,
-				       u16 vid, u8 pcp, u8 et);
+				       u16 vid, u8 pcp, u8 et,
+				       struct netlink_ext_ack *extack);
 int mlxsw_afa_block_append_allocated_counter(struct mlxsw_afa_block *block,
 					     u32 counter_index);
 int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block,
-				   u32 *p_counter_index);
-int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid);
+				   u32 *p_counter_index,
+				   struct netlink_ext_ack *extack);
+int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid,
+				   struct netlink_ext_ack *extack);
 int mlxsw_afa_block_append_mcrouter(struct mlxsw_afa_block *block,
 				    u16 expected_irif, u16 min_mtu,
 				    bool rmid_valid, u32 kvdl_index);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
index b32a00972e83..785bf01fe2be 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -43,6 +12,7 @@
 struct mlxsw_afk {
 	struct list_head key_info_list;
 	unsigned int max_blocks;
+	const struct mlxsw_afk_ops *ops;
 	const struct mlxsw_afk_block *blocks;
 	unsigned int blocks_count;
 };
@@ -69,8 +39,7 @@ static bool mlxsw_afk_blocks_check(struct mlxsw_afk *mlxsw_afk)
 }
 
 struct mlxsw_afk *mlxsw_afk_create(unsigned int max_blocks,
-				   const struct mlxsw_afk_block *blocks,
-				   unsigned int blocks_count)
+				   const struct mlxsw_afk_ops *ops)
 {
 	struct mlxsw_afk *mlxsw_afk;
 
@@ -79,8 +48,9 @@ struct mlxsw_afk *mlxsw_afk_create(unsigned int max_blocks,
 		return NULL;
 	INIT_LIST_HEAD(&mlxsw_afk->key_info_list);
 	mlxsw_afk->max_blocks = max_blocks;
-	mlxsw_afk->blocks = blocks;
-	mlxsw_afk->blocks_count = blocks_count;
+	mlxsw_afk->ops = ops;
+	mlxsw_afk->blocks = ops->blocks;
+	mlxsw_afk->blocks_count = ops->blocks_count;
 	WARN_ON(!mlxsw_afk_blocks_check(mlxsw_afk));
 	return mlxsw_afk;
 }
@@ -415,61 +385,76 @@ void mlxsw_afk_values_add_buf(struct mlxsw_afk_element_values *values,
 }
 EXPORT_SYMBOL(mlxsw_afk_values_add_buf);
 
-static void mlxsw_afk_encode_u32(const struct mlxsw_item *storage_item,
-				 const struct mlxsw_item *output_item,
-				 char *storage, char *output_indexed)
+static void mlxsw_sp_afk_encode_u32(const struct mlxsw_item *storage_item,
+				    const struct mlxsw_item *output_item,
+				    char *storage, char *output)
 {
 	u32 value;
 
 	value = __mlxsw_item_get32(storage, storage_item, 0);
-	__mlxsw_item_set32(output_indexed, output_item, 0, value);
+	__mlxsw_item_set32(output, output_item, 0, value);
 }
 
-static void mlxsw_afk_encode_buf(const struct mlxsw_item *storage_item,
-				 const struct mlxsw_item *output_item,
-				 char *storage, char *output_indexed)
+static void mlxsw_sp_afk_encode_buf(const struct mlxsw_item *storage_item,
+				    const struct mlxsw_item *output_item,
+				    char *storage, char *output)
 {
 	char *storage_data = __mlxsw_item_data(storage, storage_item, 0);
-	char *output_data = __mlxsw_item_data(output_indexed, output_item, 0);
+	char *output_data = __mlxsw_item_data(output, output_item, 0);
 	size_t len = output_item->size.bytes;
 
 	memcpy(output_data, storage_data, len);
 }
 
-#define MLXSW_AFK_KEY_BLOCK_SIZE 16
-
-static void mlxsw_afk_encode_one(const struct mlxsw_afk_element_inst *elinst,
-				 int block_index, char *storage, char *output)
+static void
+mlxsw_sp_afk_encode_one(const struct mlxsw_afk_element_inst *elinst,
+			char *output, char *storage)
 {
-	char *output_indexed = output + block_index * MLXSW_AFK_KEY_BLOCK_SIZE;
 	const struct mlxsw_item *storage_item = &elinst->info->item;
 	const struct mlxsw_item *output_item = &elinst->item;
 
 	if (elinst->type == MLXSW_AFK_ELEMENT_TYPE_U32)
-		mlxsw_afk_encode_u32(storage_item, output_item,
-				     storage, output_indexed);
+		mlxsw_sp_afk_encode_u32(storage_item, output_item,
+					storage, output);
 	else if (elinst->type == MLXSW_AFK_ELEMENT_TYPE_BUF)
-		mlxsw_afk_encode_buf(storage_item, output_item,
-				     storage, output_indexed);
+		mlxsw_sp_afk_encode_buf(storage_item, output_item,
+					storage, output);
 }
 
-void mlxsw_afk_encode(struct mlxsw_afk_key_info *key_info,
+#define MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE 16
+
+void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
+		      struct mlxsw_afk_key_info *key_info,
 		      struct mlxsw_afk_element_values *values,
-		      char *key, char *mask)
+		      char *key, char *mask, int block_start, int block_end)
 {
+	char block_mask[MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE];
+	char block_key[MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE];
 	const struct mlxsw_afk_element_inst *elinst;
 	enum mlxsw_afk_element element;
-	int block_index;
+	int block_index, i;
+
+	for (i = block_start; i <= block_end; i++) {
+		memset(block_key, 0, MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE);
+		memset(block_mask, 0, MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE);
+
+		mlxsw_afk_element_usage_for_each(element, &values->elusage) {
+			elinst = mlxsw_afk_key_info_elinst_get(key_info,
+							       element,
+							       &block_index);
+			if (!elinst || block_index != i)
+				continue;
+
+			mlxsw_sp_afk_encode_one(elinst, block_key,
+						values->storage.key);
+			mlxsw_sp_afk_encode_one(elinst, block_mask,
+						values->storage.mask);
+		}
 
-	mlxsw_afk_element_usage_for_each(element, &values->elusage) {
-		elinst = mlxsw_afk_key_info_elinst_get(key_info, element,
-						       &block_index);
-		if (!elinst)
-			continue;
-		mlxsw_afk_encode_one(elinst, block_index,
-				     values->storage.key, key);
-		mlxsw_afk_encode_one(elinst, block_index,
-				     values->storage.mask, mask);
+		if (key)
+			mlxsw_afk->ops->encode_block(block_key, i, key);
+		if (mask)
+			mlxsw_afk->ops->encode_block(block_mask, i, mask);
 	}
 }
 EXPORT_SYMBOL(mlxsw_afk_encode);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
index 122506daa586..c29c045d826d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_CORE_ACL_FLEX_KEYS_H
 #define _MLXSW_CORE_ACL_FLEX_KEYS_H
@@ -42,16 +11,20 @@
 
 enum mlxsw_afk_element {
 	MLXSW_AFK_ELEMENT_SRC_SYS_PORT,
-	MLXSW_AFK_ELEMENT_DMAC,
-	MLXSW_AFK_ELEMENT_SMAC,
+	MLXSW_AFK_ELEMENT_DMAC_32_47,
+	MLXSW_AFK_ELEMENT_DMAC_0_31,
+	MLXSW_AFK_ELEMENT_SMAC_32_47,
+	MLXSW_AFK_ELEMENT_SMAC_0_31,
 	MLXSW_AFK_ELEMENT_ETHERTYPE,
 	MLXSW_AFK_ELEMENT_IP_PROTO,
-	MLXSW_AFK_ELEMENT_SRC_IP4,
-	MLXSW_AFK_ELEMENT_DST_IP4,
-	MLXSW_AFK_ELEMENT_SRC_IP6_HI,
-	MLXSW_AFK_ELEMENT_SRC_IP6_LO,
-	MLXSW_AFK_ELEMENT_DST_IP6_HI,
-	MLXSW_AFK_ELEMENT_DST_IP6_LO,
+	MLXSW_AFK_ELEMENT_SRC_IP_96_127,
+	MLXSW_AFK_ELEMENT_SRC_IP_64_95,
+	MLXSW_AFK_ELEMENT_SRC_IP_32_63,
+	MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+	MLXSW_AFK_ELEMENT_DST_IP_96_127,
+	MLXSW_AFK_ELEMENT_DST_IP_64_95,
+	MLXSW_AFK_ELEMENT_DST_IP_32_63,
+	MLXSW_AFK_ELEMENT_DST_IP_0_31,
 	MLXSW_AFK_ELEMENT_DST_L4_PORT,
 	MLXSW_AFK_ELEMENT_SRC_L4_PORT,
 	MLXSW_AFK_ELEMENT_VID,
@@ -99,9 +72,11 @@ struct mlxsw_afk_element_info {
  * define an internal storage geometry.
  */
 static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = {
-	MLXSW_AFK_ELEMENT_INFO_U32(SRC_SYS_PORT, 0x00, 16, 16),
-	MLXSW_AFK_ELEMENT_INFO_BUF(DMAC, 0x04, 6),
-	MLXSW_AFK_ELEMENT_INFO_BUF(SMAC, 0x0A, 6),
+	MLXSW_AFK_ELEMENT_INFO_U32(SRC_SYS_PORT, 0x00, 16, 8),
+	MLXSW_AFK_ELEMENT_INFO_BUF(DMAC_32_47, 0x04, 2),
+	MLXSW_AFK_ELEMENT_INFO_BUF(DMAC_0_31, 0x06, 4),
+	MLXSW_AFK_ELEMENT_INFO_BUF(SMAC_32_47, 0x0A, 2),
+	MLXSW_AFK_ELEMENT_INFO_BUF(SMAC_0_31, 0x0C, 4),
 	MLXSW_AFK_ELEMENT_INFO_U32(ETHERTYPE, 0x00, 0, 16),
 	MLXSW_AFK_ELEMENT_INFO_U32(IP_PROTO, 0x10, 0, 8),
 	MLXSW_AFK_ELEMENT_INFO_U32(VID, 0x10, 8, 12),
@@ -112,12 +87,14 @@ static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = {
 	MLXSW_AFK_ELEMENT_INFO_U32(IP_TTL_, 0x18, 0, 8),
 	MLXSW_AFK_ELEMENT_INFO_U32(IP_ECN, 0x18, 9, 2),
 	MLXSW_AFK_ELEMENT_INFO_U32(IP_DSCP, 0x18, 11, 6),
-	MLXSW_AFK_ELEMENT_INFO_U32(SRC_IP4, 0x20, 0, 32),
-	MLXSW_AFK_ELEMENT_INFO_U32(DST_IP4, 0x24, 0, 32),
-	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_HI, 0x20, 8),
-	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_LO, 0x28, 8),
-	MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP6_HI, 0x30, 8),
-	MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP6_LO, 0x38, 8),
+	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_96_127, 0x20, 4),
+	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_64_95, 0x24, 4),
+	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_32_63, 0x28, 4),
+	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_0_31, 0x2C, 4),
+	MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_96_127, 0x30, 4),
+	MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_64_95, 0x34, 4),
+	MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_32_63, 0x38, 4),
+	MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_0_31, 0x3C, 4),
 };
 
 #define MLXSW_AFK_ELEMENT_STORAGE_SIZE 0x40
@@ -208,9 +185,14 @@ mlxsw_afk_element_usage_subset(struct mlxsw_afk_element_usage *elusage_small,
 
 struct mlxsw_afk;
 
+struct mlxsw_afk_ops {
+	const struct mlxsw_afk_block *blocks;
+	unsigned int blocks_count;
+	void (*encode_block)(char *block, int block_index, char *output);
+};
+
 struct mlxsw_afk *mlxsw_afk_create(unsigned int max_blocks,
-				   const struct mlxsw_afk_block *blocks,
-				   unsigned int blocks_count);
+				   const struct mlxsw_afk_ops *ops);
 void mlxsw_afk_destroy(struct mlxsw_afk *mlxsw_afk);
 
 struct mlxsw_afk_key_info;
@@ -243,8 +225,9 @@ void mlxsw_afk_values_add_buf(struct mlxsw_afk_element_values *values,
 			      enum mlxsw_afk_element element,
 			      const char *key_value, const char *mask_value,
 			      unsigned int len);
-void mlxsw_afk_encode(struct mlxsw_afk_key_info *key_info,
+void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
+		      struct mlxsw_afk_key_info *key_info,
 		      struct mlxsw_afk_element_values *values,
-		      char *key, char *mask);
+		      char *key, char *mask, int block_start, int block_end);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
index 84185f8dfbae..f6cf2896d337 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index d866c98c1a97..6d29dc428608 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -1,34 +1,6 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved
  * Copyright (c) 2016 Ivan Vecera <cera@cera.cz>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/emad.h b/drivers/net/ethernet/mellanox/mlxsw/emad.h
index 97b6bb5d9185..a33b896f4bb8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/emad.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/emad.h
@@ -1,37 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/emad.h
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_EMAD_H
 #define _MLXSW_EMAD_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
index 25f9915ebd82..798bd5aca384 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/i2c.c
- * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Vadim Pasternak <vadimp@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/err.h>
 #include <linux/i2c.h>
@@ -46,8 +15,6 @@
 #include "core.h"
 #include "i2c.h"
 
-static const char mlxsw_i2c_driver_name[] = "mlxsw_i2c";
-
 #define MLXSW_I2C_CIR2_BASE		0x72000
 #define MLXSW_I2C_CIR_STATUS_OFF	0x18
 #define MLXSW_I2C_CIR2_OFF_STATUS	(MLXSW_I2C_CIR2_BASE + \
diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.h b/drivers/net/ethernet/mellanox/mlxsw/i2c.h
index daa24b213ea4..17e059d47fae 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/i2c.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/i2c.h
- * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Vadim Pasternak <vadimp@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_I2C_H
 #define _MLXSW_I2C_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/ib.h b/drivers/net/ethernet/mellanox/mlxsw/ib.h
index ce313aaa6336..2d0cb0f5eb85 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/ib.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/ib.h
@@ -1,36 +1,6 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/ib.h
- * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Elad Raz <eladr@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
+
 #ifndef _MLXSW_IB_H
 #define _MLXSW_IB_H
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/item.h b/drivers/net/ethernet/mellanox/mlxsw/item.h
index 31c886edc791..e92cadc98128 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/item.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/item.h
@@ -1,37 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/item.h
- * Copyright (c) 2015-2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015-2017 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_ITEM_H
 #define _MLXSW_ITEM_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
index 3dd16267b76c..5a6c4457fb55 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/minimal.c
- * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Vadim Pasternak <vadimp@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/i2c.h>
 #include <linux/kernel.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index fc4557245ff4..4d271fb3de3d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/pci.c
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -53,8 +22,6 @@
 #include "port.h"
 #include "resources.h"
 
-static const char mlxsw_pci_driver_name[] = "mlxsw_pci";
-
 #define mlxsw_pci_write32(mlxsw_pci, reg, val) \
 	iowrite32be(val, (mlxsw_pci)->hw_addr + (MLXSW_PCI_ ## reg))
 #define mlxsw_pci_read32(mlxsw_pci, reg) \
@@ -1750,6 +1717,7 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	const char *driver_name = pdev->driver->name;
 	struct mlxsw_pci *mlxsw_pci;
+	bool called_again = false;
 	int err;
 
 	mlxsw_pci = kzalloc(sizeof(*mlxsw_pci), GFP_KERNEL);
@@ -1806,10 +1774,18 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	mlxsw_pci->bus_info.dev = &pdev->dev;
 	mlxsw_pci->id = id;
 
+again:
 	err = mlxsw_core_bus_device_register(&mlxsw_pci->bus_info,
 					     &mlxsw_pci_bus, mlxsw_pci, false,
 					     NULL);
-	if (err) {
+	/* -EAGAIN is returned in case the FW was updated. FW needs
+	 * a reset, so lets try to call mlxsw_core_bus_device_register()
+	 * again.
+	 */
+	if (err == -EAGAIN && !called_again) {
+		called_again = true;
+		goto again;
+	} else if (err) {
 		dev_err(&pdev->dev, "cannot register bus device\n");
 		goto err_bus_device_register;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.h b/drivers/net/ethernet/mellanox/mlxsw/pci.h
index d65582325cd5..946339e13eb9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/pci.h
- * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_PCI_H
 #define _MLXSW_PCI_H
@@ -39,6 +8,7 @@
 
 #define PCI_DEVICE_ID_MELLANOX_SWITCHX2		0xc738
 #define PCI_DEVICE_ID_MELLANOX_SPECTRUM		0xcb84
+#define PCI_DEVICE_ID_MELLANOX_SPECTRUM2	0xcf6c
 #define PCI_DEVICE_ID_MELLANOX_SWITCHIB		0xcb20
 #define PCI_DEVICE_ID_MELLANOX_SWITCHIB2	0xcf08
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
index 963155f6a17a..83f452b7ccbb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
- * Copyright (c) 2015-2016 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015-2016 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_PCI_HW_H
 #define _MLXSW_PCI_HW_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/port.h b/drivers/net/ethernet/mellanox/mlxsw/port.h
index c580abba8d34..a33eeef0b00c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/port.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/port.h
@@ -1,38 +1,6 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/port.h
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Elad Raz <eladr@mellanox.com>
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
+
 #ifndef _MLXSW_PORT_H
 #define _MLXSW_PORT_H
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 1877d9f8a11a..6e8b619b769b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -1,44 +1,10 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/reg.h
- * Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015-2016 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2015 Elad Raz <eladr@mellanox.com>
- * Copyright (c) 2015-2017 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2016 Yotam Gigi <yotamg@mellanox.com>
- * Copyright (c) 2017-2018 Petr Machata <petrm@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_REG_H
 #define _MLXSW_REG_H
 
+#include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/bitops.h>
 #include <linux/if_vlan.h>
@@ -1943,6 +1909,28 @@ static inline void mlxsw_reg_cwtpm_pack(char *payload, u8 local_port,
 	mlxsw_reg_cwtpm_ntcp_r_set(payload, profile);
 }
 
+/* PGCR - Policy-Engine General Configuration Register
+ * ---------------------------------------------------
+ * This register configures general Policy-Engine settings.
+ */
+#define MLXSW_REG_PGCR_ID 0x3001
+#define MLXSW_REG_PGCR_LEN 0x20
+
+MLXSW_REG_DEFINE(pgcr, MLXSW_REG_PGCR_ID, MLXSW_REG_PGCR_LEN);
+
+/* reg_pgcr_default_action_pointer_base
+ * Default action pointer base. Each region has a default action pointer
+ * which is equal to default_action_pointer_base + region_id.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pgcr, default_action_pointer_base, 0x1C, 0, 24);
+
+static inline void mlxsw_reg_pgcr_pack(char *payload, u32 pointer_base)
+{
+	MLXSW_REG_ZERO(pgcr, payload);
+	mlxsw_reg_pgcr_default_action_pointer_base_set(payload, pointer_base);
+}
+
 /* PPBT - Policy-Engine Port Binding Table
  * ---------------------------------------
  * This register is used for configuration of the Port Binding Table.
@@ -2132,14 +2120,18 @@ MLXSW_ITEM32(reg, ptar, op, 0x00, 28, 4);
 
 /* reg_ptar_action_set_type
  * Type of action set to be used on this region.
- * For Spectrum, this is always type 2 - "flexible"
+ * For Spectrum and Spectrum-2, this is always type 2 - "flexible"
  * Access: WO
  */
 MLXSW_ITEM32(reg, ptar, action_set_type, 0x00, 16, 8);
 
+enum mlxsw_reg_ptar_key_type {
+	MLXSW_REG_PTAR_KEY_TYPE_FLEX = 0x50, /* Spetrum */
+	MLXSW_REG_PTAR_KEY_TYPE_FLEX2 = 0x51, /* Spectrum-2 */
+};
+
 /* reg_ptar_key_type
  * TCAM key type for the region.
- * For Spectrum, this is always type 0x50 - "FLEX_KEY"
  * Access: WO
  */
 MLXSW_ITEM32(reg, ptar, key_type, 0x00, 0, 8);
@@ -2182,13 +2174,14 @@ MLXSW_ITEM8_INDEXED(reg, ptar, flexible_key_id, 0x20, 0, 8,
 		    MLXSW_REG_PTAR_KEY_ID_LEN, 0x00, false);
 
 static inline void mlxsw_reg_ptar_pack(char *payload, enum mlxsw_reg_ptar_op op,
+				       enum mlxsw_reg_ptar_key_type key_type,
 				       u16 region_size, u16 region_id,
 				       const char *tcam_region_info)
 {
 	MLXSW_REG_ZERO(ptar, payload);
 	mlxsw_reg_ptar_op_set(payload, op);
 	mlxsw_reg_ptar_action_set_type_set(payload, 2); /* "flexible" */
-	mlxsw_reg_ptar_key_type_set(payload, 0x50); /* "FLEX_KEY" */
+	mlxsw_reg_ptar_key_type_set(payload, key_type);
 	mlxsw_reg_ptar_region_size_set(payload, region_size);
 	mlxsw_reg_ptar_region_id_set(payload, region_id);
 	mlxsw_reg_ptar_tcam_region_info_memcpy_to(payload, tcam_region_info);
@@ -2327,6 +2320,23 @@ MLXSW_REG_DEFINE(pefa, MLXSW_REG_PEFA_ID, MLXSW_REG_PEFA_LEN);
  */
 MLXSW_ITEM32(reg, pefa, index, 0x00, 0, 24);
 
+/* reg_pefa_a
+ * Index in the KVD Linear Centralized Database.
+ * Activity
+ * For a new entry: set if ca=0, clear if ca=1
+ * Set if a packet lookup has hit on the specific entry
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, pefa, a, 0x04, 29, 1);
+
+/* reg_pefa_ca
+ * Clear activity
+ * When write: activity is according to this field
+ * When read: after reading the activity is cleared according to ca
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, pefa, ca, 0x04, 24, 1);
+
 #define MLXSW_REG_FLEX_ACTION_SET_LEN 0xA8
 
 /* reg_pefa_flex_action_set
@@ -2336,12 +2346,20 @@ MLXSW_ITEM32(reg, pefa, index, 0x00, 0, 24);
  */
 MLXSW_ITEM_BUF(reg, pefa, flex_action_set, 0x08, MLXSW_REG_FLEX_ACTION_SET_LEN);
 
-static inline void mlxsw_reg_pefa_pack(char *payload, u32 index,
+static inline void mlxsw_reg_pefa_pack(char *payload, u32 index, bool ca,
 				       const char *flex_action_set)
 {
 	MLXSW_REG_ZERO(pefa, payload);
 	mlxsw_reg_pefa_index_set(payload, index);
-	mlxsw_reg_pefa_flex_action_set_memcpy_to(payload, flex_action_set);
+	mlxsw_reg_pefa_ca_set(payload, ca);
+	if (flex_action_set)
+		mlxsw_reg_pefa_flex_action_set_memcpy_to(payload,
+							 flex_action_set);
+}
+
+static inline void mlxsw_reg_pefa_unpack(char *payload, bool *p_a)
+{
+	*p_a = mlxsw_reg_pefa_a_get(payload);
 }
 
 /* PTCE-V2 - Policy-Engine TCAM Entry Register Version 2
@@ -2397,6 +2415,15 @@ MLXSW_ITEM32(reg, ptce2, op, 0x00, 20, 3);
  */
 MLXSW_ITEM32(reg, ptce2, offset, 0x00, 0, 16);
 
+/* reg_ptce2_priority
+ * Priority of the rule, higher values win. The range is 1..cap_kvd_size-1.
+ * Note: priority does not have to be unique per rule.
+ * Within a region, higher priority should have lower offset (no limitation
+ * between regions in a multi-region).
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ptce2, priority, 0x04, 0, 24);
+
 /* reg_ptce2_tcam_region_info
  * Opaque object that represents the TCAM region.
  * Access: Index
@@ -2404,14 +2431,14 @@ MLXSW_ITEM32(reg, ptce2, offset, 0x00, 0, 16);
 MLXSW_ITEM_BUF(reg, ptce2, tcam_region_info, 0x10,
 	       MLXSW_REG_PXXX_TCAM_REGION_INFO_LEN);
 
-#define MLXSW_REG_PTCE2_FLEX_KEY_BLOCKS_LEN 96
+#define MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN 96
 
 /* reg_ptce2_flex_key_blocks
  * ACL Key.
  * Access: RW
  */
 MLXSW_ITEM_BUF(reg, ptce2, flex_key_blocks, 0x20,
-	       MLXSW_REG_PTCE2_FLEX_KEY_BLOCKS_LEN);
+	       MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN);
 
 /* reg_ptce2_mask
  * mask- in the same size as key. A bit that is set directs the TCAM
@@ -2420,7 +2447,7 @@ MLXSW_ITEM_BUF(reg, ptce2, flex_key_blocks, 0x20,
  * Access: RW
  */
 MLXSW_ITEM_BUF(reg, ptce2, mask, 0x80,
-	       MLXSW_REG_PTCE2_FLEX_KEY_BLOCKS_LEN);
+	       MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN);
 
 /* reg_ptce2_flex_action_set
  * ACL action set.
@@ -2432,15 +2459,567 @@ MLXSW_ITEM_BUF(reg, ptce2, flex_action_set, 0xE0,
 static inline void mlxsw_reg_ptce2_pack(char *payload, bool valid,
 					enum mlxsw_reg_ptce2_op op,
 					const char *tcam_region_info,
-					u16 offset)
+					u16 offset, u32 priority)
 {
 	MLXSW_REG_ZERO(ptce2, payload);
 	mlxsw_reg_ptce2_v_set(payload, valid);
 	mlxsw_reg_ptce2_op_set(payload, op);
 	mlxsw_reg_ptce2_offset_set(payload, offset);
+	mlxsw_reg_ptce2_priority_set(payload, priority);
 	mlxsw_reg_ptce2_tcam_region_info_memcpy_to(payload, tcam_region_info);
 }
 
+/* PERPT - Policy-Engine ERP Table Register
+ * ----------------------------------------
+ * This register adds and removes eRPs from the eRP table.
+ */
+#define MLXSW_REG_PERPT_ID 0x3021
+#define MLXSW_REG_PERPT_LEN 0x80
+
+MLXSW_REG_DEFINE(perpt, MLXSW_REG_PERPT_ID, MLXSW_REG_PERPT_LEN);
+
+/* reg_perpt_erpt_bank
+ * eRP table bank.
+ * Range 0 .. cap_max_erp_table_banks - 1
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, perpt, erpt_bank, 0x00, 16, 4);
+
+/* reg_perpt_erpt_index
+ * Index to eRP table within the eRP bank.
+ * Range is 0 .. cap_max_erp_table_bank_size - 1
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, perpt, erpt_index, 0x00, 0, 8);
+
+enum mlxsw_reg_perpt_key_size {
+	MLXSW_REG_PERPT_KEY_SIZE_2KB,
+	MLXSW_REG_PERPT_KEY_SIZE_4KB,
+	MLXSW_REG_PERPT_KEY_SIZE_8KB,
+	MLXSW_REG_PERPT_KEY_SIZE_12KB,
+};
+
+/* reg_perpt_key_size
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, perpt, key_size, 0x04, 0, 4);
+
+/* reg_perpt_bf_bypass
+ * 0 - The eRP is used only if bloom filter state is set for the given
+ * rule.
+ * 1 - The eRP is used regardless of bloom filter state.
+ * The bypass is an OR condition of region_id or eRP. See PERCR.bf_bypass
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, perpt, bf_bypass, 0x08, 8, 1);
+
+/* reg_perpt_erp_id
+ * eRP ID for use by the rules.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, perpt, erp_id, 0x08, 0, 4);
+
+/* reg_perpt_erpt_base_bank
+ * Base eRP table bank, points to head of erp_vector
+ * Range is 0 .. cap_max_erp_table_banks - 1
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, perpt, erpt_base_bank, 0x0C, 16, 4);
+
+/* reg_perpt_erpt_base_index
+ * Base index to eRP table within the eRP bank
+ * Range is 0 .. cap_max_erp_table_bank_size - 1
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, perpt, erpt_base_index, 0x0C, 0, 8);
+
+/* reg_perpt_erp_index_in_vector
+ * eRP index in the vector.
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, perpt, erp_index_in_vector, 0x10, 0, 4);
+
+/* reg_perpt_erp_vector
+ * eRP vector.
+ * Access: OP
+ */
+MLXSW_ITEM_BIT_ARRAY(reg, perpt, erp_vector, 0x14, 4, 1);
+
+/* reg_perpt_mask
+ * Mask
+ * 0 - A-TCAM will ignore the bit in key
+ * 1 - A-TCAM will compare the bit in key
+ * Access: RW
+ */
+MLXSW_ITEM_BUF(reg, perpt, mask, 0x20, MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN);
+
+static inline void mlxsw_reg_perpt_erp_vector_pack(char *payload,
+						   unsigned long *erp_vector,
+						   unsigned long size)
+{
+	unsigned long bit;
+
+	for_each_set_bit(bit, erp_vector, size)
+		mlxsw_reg_perpt_erp_vector_set(payload, bit, true);
+}
+
+static inline void
+mlxsw_reg_perpt_pack(char *payload, u8 erpt_bank, u8 erpt_index,
+		     enum mlxsw_reg_perpt_key_size key_size, u8 erp_id,
+		     u8 erpt_base_bank, u8 erpt_base_index, u8 erp_index,
+		     char *mask)
+{
+	MLXSW_REG_ZERO(perpt, payload);
+	mlxsw_reg_perpt_erpt_bank_set(payload, erpt_bank);
+	mlxsw_reg_perpt_erpt_index_set(payload, erpt_index);
+	mlxsw_reg_perpt_key_size_set(payload, key_size);
+	mlxsw_reg_perpt_bf_bypass_set(payload, true);
+	mlxsw_reg_perpt_erp_id_set(payload, erp_id);
+	mlxsw_reg_perpt_erpt_base_bank_set(payload, erpt_base_bank);
+	mlxsw_reg_perpt_erpt_base_index_set(payload, erpt_base_index);
+	mlxsw_reg_perpt_erp_index_in_vector_set(payload, erp_index);
+	mlxsw_reg_perpt_mask_memcpy_to(payload, mask);
+}
+
+/* PERAR - Policy-Engine Region Association Register
+ * -------------------------------------------------
+ * This register associates a hw region for region_id's. Changing on the fly
+ * is supported by the device.
+ */
+#define MLXSW_REG_PERAR_ID 0x3026
+#define MLXSW_REG_PERAR_LEN 0x08
+
+MLXSW_REG_DEFINE(perar, MLXSW_REG_PERAR_ID, MLXSW_REG_PERAR_LEN);
+
+/* reg_perar_region_id
+ * Region identifier
+ * Range 0 .. cap_max_regions-1
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, perar, region_id, 0x00, 0, 16);
+
+static inline unsigned int
+mlxsw_reg_perar_hw_regions_needed(unsigned int block_num)
+{
+	return DIV_ROUND_UP(block_num, 4);
+}
+
+/* reg_perar_hw_region
+ * HW Region
+ * Range 0 .. cap_max_regions-1
+ * Default: hw_region = region_id
+ * For a 8 key block region, 2 consecutive regions are used
+ * For a 12 key block region, 3 consecutive regions are used
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, perar, hw_region, 0x04, 0, 16);
+
+static inline void mlxsw_reg_perar_pack(char *payload, u16 region_id,
+					u16 hw_region)
+{
+	MLXSW_REG_ZERO(perar, payload);
+	mlxsw_reg_perar_region_id_set(payload, region_id);
+	mlxsw_reg_perar_hw_region_set(payload, hw_region);
+}
+
+/* PTCE-V3 - Policy-Engine TCAM Entry Register Version 3
+ * -----------------------------------------------------
+ * This register is a new version of PTCE-V2 in order to support the
+ * A-TCAM. This register is not supported by SwitchX/-2 and Spectrum.
+ */
+#define MLXSW_REG_PTCE3_ID 0x3027
+#define MLXSW_REG_PTCE3_LEN 0xF0
+
+MLXSW_REG_DEFINE(ptce3, MLXSW_REG_PTCE3_ID, MLXSW_REG_PTCE3_LEN);
+
+/* reg_ptce3_v
+ * Valid.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ptce3, v, 0x00, 31, 1);
+
+enum mlxsw_reg_ptce3_op {
+	/* Write operation. Used to write a new entry to the table.
+	 * All R/W fields are relevant for new entry. Activity bit is set
+	 * for new entries. Write with v = 0 will delete the entry. Must
+	 * not be used if an entry exists.
+	 */
+	 MLXSW_REG_PTCE3_OP_WRITE_WRITE = 0,
+	 /* Update operation */
+	 MLXSW_REG_PTCE3_OP_WRITE_UPDATE = 1,
+	 /* Read operation */
+	 MLXSW_REG_PTCE3_OP_QUERY_READ = 0,
+};
+
+/* reg_ptce3_op
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, ptce3, op, 0x00, 20, 3);
+
+/* reg_ptce3_priority
+ * Priority of the rule. Higher values win.
+ * For Spectrum-2 range is 1..cap_kvd_size - 1
+ * Note: Priority does not have to be unique per rule.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ptce3, priority, 0x04, 0, 24);
+
+/* reg_ptce3_tcam_region_info
+ * Opaque object that represents the TCAM region.
+ * Access: Index
+ */
+MLXSW_ITEM_BUF(reg, ptce3, tcam_region_info, 0x10,
+	       MLXSW_REG_PXXX_TCAM_REGION_INFO_LEN);
+
+/* reg_ptce3_flex2_key_blocks
+ * ACL key. The key must be masked according to eRP (if exists) or
+ * according to master mask.
+ * Access: Index
+ */
+MLXSW_ITEM_BUF(reg, ptce3, flex2_key_blocks, 0x20,
+	       MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN);
+
+/* reg_ptce3_erp_id
+ * eRP ID.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, ptce3, erp_id, 0x80, 0, 4);
+
+/* reg_ptce3_delta_start
+ * Start point of delta_value and delta_mask, in bits. Must not exceed
+ * num_key_blocks * 36 - 8. Reserved when delta_mask = 0.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, ptce3, delta_start, 0x84, 0, 10);
+
+/* reg_ptce3_delta_mask
+ * Delta mask.
+ * 0 - Ignore relevant bit in delta_value
+ * 1 - Compare relevant bit in delta_value
+ * Delta mask must not be set for reserved fields in the key blocks.
+ * Note: No delta when no eRPs. Thus, for regions with
+ * PERERP.erpt_pointer_valid = 0 the delta mask must be 0.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, ptce3, delta_mask, 0x88, 16, 8);
+
+/* reg_ptce3_delta_value
+ * Delta value.
+ * Bits which are masked by delta_mask must be 0.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, ptce3, delta_value, 0x88, 0, 8);
+
+/* reg_ptce3_prune_vector
+ * Pruning vector relative to the PERPT.erp_id.
+ * Used for reducing lookups.
+ * 0 - NEED: Do a lookup using the eRP.
+ * 1 - PRUNE: Do not perform a lookup using the eRP.
+ * Maybe be modified by PEAPBL and PEAPBM.
+ * Note: In Spectrum-2, a region of 8 key blocks must be set to either
+ * all 1's or all 0's.
+ * Access: RW
+ */
+MLXSW_ITEM_BIT_ARRAY(reg, ptce3, prune_vector, 0x90, 4, 1);
+
+/* reg_ptce3_prune_ctcam
+ * Pruning on C-TCAM. Used for reducing lookups.
+ * 0 - NEED: Do a lookup in the C-TCAM.
+ * 1 - PRUNE: Do not perform a lookup in the C-TCAM.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ptce3, prune_ctcam, 0x94, 31, 1);
+
+/* reg_ptce3_large_exists
+ * Large entry key ID exists.
+ * Within the region:
+ * 0 - SINGLE: The large_entry_key_id is not currently in use.
+ * For rule insert: The MSB of the key (blocks 6..11) will be added.
+ * For rule delete: The MSB of the key will be removed.
+ * 1 - NON_SINGLE: The large_entry_key_id is currently in use.
+ * For rule insert: The MSB of the key (blocks 6..11) will not be added.
+ * For rule delete: The MSB of the key will not be removed.
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, ptce3, large_exists, 0x98, 31, 1);
+
+/* reg_ptce3_large_entry_key_id
+ * Large entry key ID.
+ * A key for 12 key blocks rules. Reserved when region has less than 12 key
+ * blocks. Must be different for different keys which have the same common
+ * 6 key blocks (MSB, blocks 6..11) key within a region.
+ * Range is 0..cap_max_pe_large_key_id - 1
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ptce3, large_entry_key_id, 0x98, 0, 24);
+
+/* reg_ptce3_action_pointer
+ * Pointer to action.
+ * Range is 0..cap_max_kvd_action_sets - 1
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ptce3, action_pointer, 0xA0, 0, 24);
+
+static inline void mlxsw_reg_ptce3_pack(char *payload, bool valid,
+					enum mlxsw_reg_ptce3_op op,
+					u32 priority,
+					const char *tcam_region_info,
+					const char *key, u8 erp_id,
+					bool large_exists, u32 lkey_id,
+					u32 action_pointer)
+{
+	MLXSW_REG_ZERO(ptce3, payload);
+	mlxsw_reg_ptce3_v_set(payload, valid);
+	mlxsw_reg_ptce3_op_set(payload, op);
+	mlxsw_reg_ptce3_priority_set(payload, priority);
+	mlxsw_reg_ptce3_tcam_region_info_memcpy_to(payload, tcam_region_info);
+	mlxsw_reg_ptce3_flex2_key_blocks_memcpy_to(payload, key);
+	mlxsw_reg_ptce3_erp_id_set(payload, erp_id);
+	mlxsw_reg_ptce3_large_exists_set(payload, large_exists);
+	mlxsw_reg_ptce3_large_entry_key_id_set(payload, lkey_id);
+	mlxsw_reg_ptce3_action_pointer_set(payload, action_pointer);
+}
+
+/* PERCR - Policy-Engine Region Configuration Register
+ * ---------------------------------------------------
+ * This register configures the region parameters. The region_id must be
+ * allocated.
+ */
+#define MLXSW_REG_PERCR_ID 0x302A
+#define MLXSW_REG_PERCR_LEN 0x80
+
+MLXSW_REG_DEFINE(percr, MLXSW_REG_PERCR_ID, MLXSW_REG_PERCR_LEN);
+
+/* reg_percr_region_id
+ * Region identifier.
+ * Range 0..cap_max_regions-1
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, percr, region_id, 0x00, 0, 16);
+
+/* reg_percr_atcam_ignore_prune
+ * Ignore prune_vector by other A-TCAM rules. Used e.g., for a new rule.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, percr, atcam_ignore_prune, 0x04, 25, 1);
+
+/* reg_percr_ctcam_ignore_prune
+ * Ignore prune_ctcam by other A-TCAM rules. Used e.g., for a new rule.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, percr, ctcam_ignore_prune, 0x04, 24, 1);
+
+/* reg_percr_bf_bypass
+ * Bloom filter bypass.
+ * 0 - Bloom filter is used (default)
+ * 1 - Bloom filter is bypassed. The bypass is an OR condition of
+ * region_id or eRP. See PERPT.bf_bypass
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, percr, bf_bypass, 0x04, 16, 1);
+
+/* reg_percr_master_mask
+ * Master mask. Logical OR mask of all masks of all rules of a region
+ * (both A-TCAM and C-TCAM). When there are no eRPs
+ * (erpt_pointer_valid = 0), then this provides the mask.
+ * Access: RW
+ */
+MLXSW_ITEM_BUF(reg, percr, master_mask, 0x20, 96);
+
+static inline void mlxsw_reg_percr_pack(char *payload, u16 region_id)
+{
+	MLXSW_REG_ZERO(percr, payload);
+	mlxsw_reg_percr_region_id_set(payload, region_id);
+	mlxsw_reg_percr_atcam_ignore_prune_set(payload, false);
+	mlxsw_reg_percr_ctcam_ignore_prune_set(payload, false);
+	mlxsw_reg_percr_bf_bypass_set(payload, true);
+}
+
+/* PERERP - Policy-Engine Region eRP Register
+ * ------------------------------------------
+ * This register configures the region eRP. The region_id must be
+ * allocated.
+ */
+#define MLXSW_REG_PERERP_ID 0x302B
+#define MLXSW_REG_PERERP_LEN 0x1C
+
+MLXSW_REG_DEFINE(pererp, MLXSW_REG_PERERP_ID, MLXSW_REG_PERERP_LEN);
+
+/* reg_pererp_region_id
+ * Region identifier.
+ * Range 0..cap_max_regions-1
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, pererp, region_id, 0x00, 0, 16);
+
+/* reg_pererp_ctcam_le
+ * C-TCAM lookup enable. Reserved when erpt_pointer_valid = 0.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pererp, ctcam_le, 0x04, 28, 1);
+
+/* reg_pererp_erpt_pointer_valid
+ * erpt_pointer is valid.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pererp, erpt_pointer_valid, 0x10, 31, 1);
+
+/* reg_pererp_erpt_bank_pointer
+ * Pointer to eRP table bank. May be modified at any time.
+ * Range 0..cap_max_erp_table_banks-1
+ * Reserved when erpt_pointer_valid = 0
+ */
+MLXSW_ITEM32(reg, pererp, erpt_bank_pointer, 0x10, 16, 4);
+
+/* reg_pererp_erpt_pointer
+ * Pointer to eRP table within the eRP bank. Can be changed for an
+ * existing region.
+ * Range 0..cap_max_erp_table_size-1
+ * Reserved when erpt_pointer_valid = 0
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pererp, erpt_pointer, 0x10, 0, 8);
+
+/* reg_pererp_erpt_vector
+ * Vector of allowed eRP indexes starting from erpt_pointer within the
+ * erpt_bank_pointer. Next entries will be in next bank.
+ * Note that eRP index is used and not eRP ID.
+ * Reserved when erpt_pointer_valid = 0
+ * Access: RW
+ */
+MLXSW_ITEM_BIT_ARRAY(reg, pererp, erpt_vector, 0x14, 4, 1);
+
+/* reg_pererp_master_rp_id
+ * Master RP ID. When there are no eRPs, then this provides the eRP ID
+ * for the lookup. Can be changed for an existing region.
+ * Reserved when erpt_pointer_valid = 1
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pererp, master_rp_id, 0x18, 0, 4);
+
+static inline void mlxsw_reg_pererp_erp_vector_pack(char *payload,
+						    unsigned long *erp_vector,
+						    unsigned long size)
+{
+	unsigned long bit;
+
+	for_each_set_bit(bit, erp_vector, size)
+		mlxsw_reg_pererp_erpt_vector_set(payload, bit, true);
+}
+
+static inline void mlxsw_reg_pererp_pack(char *payload, u16 region_id,
+					 bool ctcam_le, bool erpt_pointer_valid,
+					 u8 erpt_bank_pointer, u8 erpt_pointer,
+					 u8 master_rp_id)
+{
+	MLXSW_REG_ZERO(pererp, payload);
+	mlxsw_reg_pererp_region_id_set(payload, region_id);
+	mlxsw_reg_pererp_ctcam_le_set(payload, ctcam_le);
+	mlxsw_reg_pererp_erpt_pointer_valid_set(payload, erpt_pointer_valid);
+	mlxsw_reg_pererp_erpt_bank_pointer_set(payload, erpt_bank_pointer);
+	mlxsw_reg_pererp_erpt_pointer_set(payload, erpt_pointer);
+	mlxsw_reg_pererp_master_rp_id_set(payload, master_rp_id);
+}
+
+/* IEDR - Infrastructure Entry Delete Register
+ * ----------------------------------------------------
+ * This register is used for deleting entries from the entry tables.
+ * It is legitimate to attempt to delete a nonexisting entry (the device will
+ * respond as a good flow).
+ */
+#define MLXSW_REG_IEDR_ID 0x3804
+#define MLXSW_REG_IEDR_BASE_LEN 0x10 /* base length, without records */
+#define MLXSW_REG_IEDR_REC_LEN 0x8 /* record length */
+#define MLXSW_REG_IEDR_REC_MAX_COUNT 64
+#define MLXSW_REG_IEDR_LEN (MLXSW_REG_IEDR_BASE_LEN +	\
+			    MLXSW_REG_IEDR_REC_LEN *	\
+			    MLXSW_REG_IEDR_REC_MAX_COUNT)
+
+MLXSW_REG_DEFINE(iedr, MLXSW_REG_IEDR_ID, MLXSW_REG_IEDR_LEN);
+
+/* reg_iedr_num_rec
+ * Number of records.
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, iedr, num_rec, 0x00, 0, 8);
+
+/* reg_iedr_rec_type
+ * Resource type.
+ * Access: OP
+ */
+MLXSW_ITEM32_INDEXED(reg, iedr, rec_type, MLXSW_REG_IEDR_BASE_LEN, 24, 8,
+		     MLXSW_REG_IEDR_REC_LEN, 0x00, false);
+
+/* reg_iedr_rec_size
+ * Size of entries do be deleted. The unit is 1 entry, regardless of entry type.
+ * Access: OP
+ */
+MLXSW_ITEM32_INDEXED(reg, iedr, rec_size, MLXSW_REG_IEDR_BASE_LEN, 0, 11,
+		     MLXSW_REG_IEDR_REC_LEN, 0x00, false);
+
+/* reg_iedr_rec_index_start
+ * Resource index start.
+ * Access: OP
+ */
+MLXSW_ITEM32_INDEXED(reg, iedr, rec_index_start, MLXSW_REG_IEDR_BASE_LEN, 0, 24,
+		     MLXSW_REG_IEDR_REC_LEN, 0x04, false);
+
+static inline void mlxsw_reg_iedr_pack(char *payload)
+{
+	MLXSW_REG_ZERO(iedr, payload);
+}
+
+static inline void mlxsw_reg_iedr_rec_pack(char *payload, int rec_index,
+					   u8 rec_type, u16 rec_size,
+					   u32 rec_index_start)
+{
+	u8 num_rec = mlxsw_reg_iedr_num_rec_get(payload);
+
+	if (rec_index >= num_rec)
+		mlxsw_reg_iedr_num_rec_set(payload, rec_index + 1);
+	mlxsw_reg_iedr_rec_type_set(payload, rec_index, rec_type);
+	mlxsw_reg_iedr_rec_size_set(payload, rec_index, rec_size);
+	mlxsw_reg_iedr_rec_index_start_set(payload, rec_index, rec_index_start);
+}
+
+/* QPTS - QoS Priority Trust State Register
+ * ----------------------------------------
+ * This register controls the port policy to calculate the switch priority and
+ * packet color based on incoming packet fields.
+ */
+#define MLXSW_REG_QPTS_ID 0x4002
+#define MLXSW_REG_QPTS_LEN 0x8
+
+MLXSW_REG_DEFINE(qpts, MLXSW_REG_QPTS_ID, MLXSW_REG_QPTS_LEN);
+
+/* reg_qpts_local_port
+ * Local port number.
+ * Access: Index
+ *
+ * Note: CPU port is supported.
+ */
+MLXSW_ITEM32(reg, qpts, local_port, 0x00, 16, 8);
+
+enum mlxsw_reg_qpts_trust_state {
+	MLXSW_REG_QPTS_TRUST_STATE_PCP = 1,
+	MLXSW_REG_QPTS_TRUST_STATE_DSCP = 2, /* For MPLS, trust EXP. */
+};
+
+/* reg_qpts_trust_state
+ * Trust state for a given port.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qpts, trust_state, 0x04, 0, 3);
+
+static inline void mlxsw_reg_qpts_pack(char *payload, u8 local_port,
+				       enum mlxsw_reg_qpts_trust_state ts)
+{
+	MLXSW_REG_ZERO(qpts, payload);
+
+	mlxsw_reg_qpts_local_port_set(payload, local_port);
+	mlxsw_reg_qpts_trust_state_set(payload, ts);
+}
+
 /* QPCR - QoS Policer Configuration Register
  * -----------------------------------------
  * The QPCR register is used to create policers - that limit
@@ -2753,6 +3332,219 @@ static inline void mlxsw_reg_qeec_pack(char *payload, u8 local_port,
 	mlxsw_reg_qeec_next_element_index_set(payload, next_index);
 }
 
+/* QRWE - QoS ReWrite Enable
+ * -------------------------
+ * This register configures the rewrite enable per receive port.
+ */
+#define MLXSW_REG_QRWE_ID 0x400F
+#define MLXSW_REG_QRWE_LEN 0x08
+
+MLXSW_REG_DEFINE(qrwe, MLXSW_REG_QRWE_ID, MLXSW_REG_QRWE_LEN);
+
+/* reg_qrwe_local_port
+ * Local port number.
+ * Access: Index
+ *
+ * Note: CPU port is supported. No support for router port.
+ */
+MLXSW_ITEM32(reg, qrwe, local_port, 0x00, 16, 8);
+
+/* reg_qrwe_dscp
+ * Whether to enable DSCP rewrite (default is 0, don't rewrite).
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qrwe, dscp, 0x04, 1, 1);
+
+/* reg_qrwe_pcp
+ * Whether to enable PCP and DEI rewrite (default is 0, don't rewrite).
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qrwe, pcp, 0x04, 0, 1);
+
+static inline void mlxsw_reg_qrwe_pack(char *payload, u8 local_port,
+				       bool rewrite_pcp, bool rewrite_dscp)
+{
+	MLXSW_REG_ZERO(qrwe, payload);
+	mlxsw_reg_qrwe_local_port_set(payload, local_port);
+	mlxsw_reg_qrwe_pcp_set(payload, rewrite_pcp);
+	mlxsw_reg_qrwe_dscp_set(payload, rewrite_dscp);
+}
+
+/* QPDSM - QoS Priority to DSCP Mapping
+ * ------------------------------------
+ * QoS Priority to DSCP Mapping Register
+ */
+#define MLXSW_REG_QPDSM_ID 0x4011
+#define MLXSW_REG_QPDSM_BASE_LEN 0x04 /* base length, without records */
+#define MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN 0x4 /* record length */
+#define MLXSW_REG_QPDSM_PRIO_ENTRY_REC_MAX_COUNT 16
+#define MLXSW_REG_QPDSM_LEN (MLXSW_REG_QPDSM_BASE_LEN +			\
+			     MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN *	\
+			     MLXSW_REG_QPDSM_PRIO_ENTRY_REC_MAX_COUNT)
+
+MLXSW_REG_DEFINE(qpdsm, MLXSW_REG_QPDSM_ID, MLXSW_REG_QPDSM_LEN);
+
+/* reg_qpdsm_local_port
+ * Local Port. Supported for data packets from CPU port.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, qpdsm, local_port, 0x00, 16, 8);
+
+/* reg_qpdsm_prio_entry_color0_e
+ * Enable update of the entry for color 0 and a given port.
+ * Access: WO
+ */
+MLXSW_ITEM32_INDEXED(reg, qpdsm, prio_entry_color0_e,
+		     MLXSW_REG_QPDSM_BASE_LEN, 31, 1,
+		     MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN, 0x00, false);
+
+/* reg_qpdsm_prio_entry_color0_dscp
+ * DSCP field in the outer label of the packet for color 0 and a given port.
+ * Reserved when e=0.
+ * Access: RW
+ */
+MLXSW_ITEM32_INDEXED(reg, qpdsm, prio_entry_color0_dscp,
+		     MLXSW_REG_QPDSM_BASE_LEN, 24, 6,
+		     MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN, 0x00, false);
+
+/* reg_qpdsm_prio_entry_color1_e
+ * Enable update of the entry for color 1 and a given port.
+ * Access: WO
+ */
+MLXSW_ITEM32_INDEXED(reg, qpdsm, prio_entry_color1_e,
+		     MLXSW_REG_QPDSM_BASE_LEN, 23, 1,
+		     MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN, 0x00, false);
+
+/* reg_qpdsm_prio_entry_color1_dscp
+ * DSCP field in the outer label of the packet for color 1 and a given port.
+ * Reserved when e=0.
+ * Access: RW
+ */
+MLXSW_ITEM32_INDEXED(reg, qpdsm, prio_entry_color1_dscp,
+		     MLXSW_REG_QPDSM_BASE_LEN, 16, 6,
+		     MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN, 0x00, false);
+
+/* reg_qpdsm_prio_entry_color2_e
+ * Enable update of the entry for color 2 and a given port.
+ * Access: WO
+ */
+MLXSW_ITEM32_INDEXED(reg, qpdsm, prio_entry_color2_e,
+		     MLXSW_REG_QPDSM_BASE_LEN, 15, 1,
+		     MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN, 0x00, false);
+
+/* reg_qpdsm_prio_entry_color2_dscp
+ * DSCP field in the outer label of the packet for color 2 and a given port.
+ * Reserved when e=0.
+ * Access: RW
+ */
+MLXSW_ITEM32_INDEXED(reg, qpdsm, prio_entry_color2_dscp,
+		     MLXSW_REG_QPDSM_BASE_LEN, 8, 6,
+		     MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN, 0x00, false);
+
+static inline void mlxsw_reg_qpdsm_pack(char *payload, u8 local_port)
+{
+	MLXSW_REG_ZERO(qpdsm, payload);
+	mlxsw_reg_qpdsm_local_port_set(payload, local_port);
+}
+
+static inline void
+mlxsw_reg_qpdsm_prio_pack(char *payload, unsigned short prio, u8 dscp)
+{
+	mlxsw_reg_qpdsm_prio_entry_color0_e_set(payload, prio, 1);
+	mlxsw_reg_qpdsm_prio_entry_color0_dscp_set(payload, prio, dscp);
+	mlxsw_reg_qpdsm_prio_entry_color1_e_set(payload, prio, 1);
+	mlxsw_reg_qpdsm_prio_entry_color1_dscp_set(payload, prio, dscp);
+	mlxsw_reg_qpdsm_prio_entry_color2_e_set(payload, prio, 1);
+	mlxsw_reg_qpdsm_prio_entry_color2_dscp_set(payload, prio, dscp);
+}
+
+/* QPDPM - QoS Port DSCP to Priority Mapping Register
+ * --------------------------------------------------
+ * This register controls the mapping from DSCP field to
+ * Switch Priority for IP packets.
+ */
+#define MLXSW_REG_QPDPM_ID 0x4013
+#define MLXSW_REG_QPDPM_BASE_LEN 0x4 /* base length, without records */
+#define MLXSW_REG_QPDPM_DSCP_ENTRY_REC_LEN 0x2 /* record length */
+#define MLXSW_REG_QPDPM_DSCP_ENTRY_REC_MAX_COUNT 64
+#define MLXSW_REG_QPDPM_LEN (MLXSW_REG_QPDPM_BASE_LEN +			\
+			     MLXSW_REG_QPDPM_DSCP_ENTRY_REC_LEN *	\
+			     MLXSW_REG_QPDPM_DSCP_ENTRY_REC_MAX_COUNT)
+
+MLXSW_REG_DEFINE(qpdpm, MLXSW_REG_QPDPM_ID, MLXSW_REG_QPDPM_LEN);
+
+/* reg_qpdpm_local_port
+ * Local Port. Supported for data packets from CPU port.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, qpdpm, local_port, 0x00, 16, 8);
+
+/* reg_qpdpm_dscp_e
+ * Enable update of the specific entry. When cleared, the switch_prio and color
+ * fields are ignored and the previous switch_prio and color values are
+ * preserved.
+ * Access: WO
+ */
+MLXSW_ITEM16_INDEXED(reg, qpdpm, dscp_entry_e, MLXSW_REG_QPDPM_BASE_LEN, 15, 1,
+		     MLXSW_REG_QPDPM_DSCP_ENTRY_REC_LEN, 0x00, false);
+
+/* reg_qpdpm_dscp_prio
+ * The new Switch Priority value for the relevant DSCP value.
+ * Access: RW
+ */
+MLXSW_ITEM16_INDEXED(reg, qpdpm, dscp_entry_prio,
+		     MLXSW_REG_QPDPM_BASE_LEN, 0, 4,
+		     MLXSW_REG_QPDPM_DSCP_ENTRY_REC_LEN, 0x00, false);
+
+static inline void mlxsw_reg_qpdpm_pack(char *payload, u8 local_port)
+{
+	MLXSW_REG_ZERO(qpdpm, payload);
+	mlxsw_reg_qpdpm_local_port_set(payload, local_port);
+}
+
+static inline void
+mlxsw_reg_qpdpm_dscp_pack(char *payload, unsigned short dscp, u8 prio)
+{
+	mlxsw_reg_qpdpm_dscp_entry_e_set(payload, dscp, 1);
+	mlxsw_reg_qpdpm_dscp_entry_prio_set(payload, dscp, prio);
+}
+
+/* QTCTM - QoS Switch Traffic Class Table is Multicast-Aware Register
+ * ------------------------------------------------------------------
+ * This register configures if the Switch Priority to Traffic Class mapping is
+ * based on Multicast packet indication. If so, then multicast packets will get
+ * a Traffic Class that is plus (cap_max_tclass_data/2) the value configured by
+ * QTCT.
+ * By default, Switch Priority to Traffic Class mapping is not based on
+ * Multicast packet indication.
+ */
+#define MLXSW_REG_QTCTM_ID 0x401A
+#define MLXSW_REG_QTCTM_LEN 0x08
+
+MLXSW_REG_DEFINE(qtctm, MLXSW_REG_QTCTM_ID, MLXSW_REG_QTCTM_LEN);
+
+/* reg_qtctm_local_port
+ * Local port number.
+ * No support for CPU port.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, qtctm, local_port, 0x00, 16, 8);
+
+/* reg_qtctm_mc
+ * Multicast Mode
+ * Whether Switch Priority to Traffic Class mapping is based on Multicast packet
+ * indication (default is 0, not based on Multicast packet indication).
+ */
+MLXSW_ITEM32(reg, qtctm, mc, 0x04, 0, 1);
+
+static inline void
+mlxsw_reg_qtctm_pack(char *payload, u8 local_port, bool mc)
+{
+	MLXSW_REG_ZERO(qtctm, payload);
+	mlxsw_reg_qtctm_local_port_set(payload, local_port);
+	mlxsw_reg_qtctm_mc_set(payload, mc);
+}
+
 /* PMLP - Ports Module to Local Port Register
  * ------------------------------------------
  * Configures the assignment of modules to local ports.
@@ -3350,6 +4142,7 @@ MLXSW_ITEM32(reg, ppcnt, pnat, 0x00, 14, 2);
 
 enum mlxsw_reg_ppcnt_grp {
 	MLXSW_REG_PPCNT_IEEE_8023_CNT = 0x0,
+	MLXSW_REG_PPCNT_RFC_2819_CNT = 0x2,
 	MLXSW_REG_PPCNT_EXT_CNT = 0x5,
 	MLXSW_REG_PPCNT_PRIO_CNT = 0x10,
 	MLXSW_REG_PPCNT_TC_CNT = 0x11,
@@ -3508,6 +4301,68 @@ MLXSW_ITEM64(reg, ppcnt, a_pause_mac_ctrl_frames_received,
 MLXSW_ITEM64(reg, ppcnt, a_pause_mac_ctrl_frames_transmitted,
 	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x90, 0, 64);
 
+/* Ethernet RFC 2819 Counter Group */
+
+/* reg_ppcnt_ether_stats_pkts64octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts64octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x58, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts65to127octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts65to127octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x60, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts128to255octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts128to255octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x68, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts256to511octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts256to511octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x70, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts512to1023octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts512to1023octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x78, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts1024to1518octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts1024to1518octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x80, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts1519to2047octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts1519to2047octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x88, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts2048to4095octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts2048to4095octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x90, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts4096to8191octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts4096to8191octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x98, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts8192to10239octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts8192to10239octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0xA0, 0, 64);
+
 /* Ethernet Extended Counter Group Counters */
 
 /* reg_ppcnt_ecn_marked
@@ -4338,6 +5193,20 @@ MLXSW_ITEM32(reg, ritr, if_swid, 0x08, 24, 8);
  */
 MLXSW_ITEM_BUF(reg, ritr, if_mac, 0x12, 6);
 
+/* reg_ritr_if_vrrp_id_ipv6
+ * VRRP ID for IPv6
+ * Note: Reserved for RIF types other than VLAN, FID and Sub-port.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, if_vrrp_id_ipv6, 0x1C, 8, 8);
+
+/* reg_ritr_if_vrrp_id_ipv4
+ * VRRP ID for IPv4
+ * Note: Reserved for RIF types other than VLAN, FID and Sub-port.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, if_vrrp_id_ipv4, 0x1C, 0, 8);
+
 /* VLAN Interface */
 
 /* reg_ritr_vlan_if_vid
@@ -7871,6 +8740,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(spvmlr),
 	MLXSW_REG(cwtp),
 	MLXSW_REG(cwtpm),
+	MLXSW_REG(pgcr),
 	MLXSW_REG(ppbt),
 	MLXSW_REG(pacl),
 	MLXSW_REG(pagt),
@@ -7879,9 +8749,20 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(prcr),
 	MLXSW_REG(pefa),
 	MLXSW_REG(ptce2),
+	MLXSW_REG(perpt),
+	MLXSW_REG(perar),
+	MLXSW_REG(ptce3),
+	MLXSW_REG(percr),
+	MLXSW_REG(pererp),
+	MLXSW_REG(iedr),
+	MLXSW_REG(qpts),
 	MLXSW_REG(qpcr),
 	MLXSW_REG(qtct),
 	MLXSW_REG(qeec),
+	MLXSW_REG(qrwe),
+	MLXSW_REG(qpdsm),
+	MLXSW_REG(qpdpm),
+	MLXSW_REG(qtctm),
 	MLXSW_REG(pmlp),
 	MLXSW_REG(pmtu),
 	MLXSW_REG(ptys),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h
index fd9299ccec72..79a31de7c825 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/resources.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/resources.h
- * Copyright (c) 2016-2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016-2017 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_RESOURCES_H
 #define _MLXSW_RESOURCES_H
@@ -42,6 +11,8 @@ enum mlxsw_res_id {
 	MLXSW_RES_ID_KVD_SIZE,
 	MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE,
 	MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE,
+	MLXSW_RES_ID_MAX_KVD_LINEAR_RANGE,
+	MLXSW_RES_ID_MAX_KVD_ACTION_SETS,
 	MLXSW_RES_ID_MAX_TRAP_GROUPS,
 	MLXSW_RES_ID_CQE_V0,
 	MLXSW_RES_ID_CQE_V1,
@@ -63,6 +34,13 @@ enum mlxsw_res_id {
 	MLXSW_RES_ID_ACL_FLEX_KEYS,
 	MLXSW_RES_ID_ACL_MAX_ACTION_PER_RULE,
 	MLXSW_RES_ID_ACL_ACTIONS_PER_SET,
+	MLXSW_RES_ID_ACL_MAX_ERPT_BANKS,
+	MLXSW_RES_ID_ACL_MAX_ERPT_BANK_SIZE,
+	MLXSW_RES_ID_ACL_MAX_LARGE_KEY_ID,
+	MLXSW_RES_ID_ACL_ERPT_ENTRIES_2KB,
+	MLXSW_RES_ID_ACL_ERPT_ENTRIES_4KB,
+	MLXSW_RES_ID_ACL_ERPT_ENTRIES_8KB,
+	MLXSW_RES_ID_ACL_ERPT_ENTRIES_12KB,
 	MLXSW_RES_ID_MAX_CPU_POLICERS,
 	MLXSW_RES_ID_MAX_VRS,
 	MLXSW_RES_ID_MAX_RIFS,
@@ -83,6 +61,8 @@ static u16 mlxsw_res_ids[] = {
 	[MLXSW_RES_ID_KVD_SIZE] = 0x1001,
 	[MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE] = 0x1002,
 	[MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE] = 0x1003,
+	[MLXSW_RES_ID_MAX_KVD_LINEAR_RANGE] = 0x1005,
+	[MLXSW_RES_ID_MAX_KVD_ACTION_SETS] = 0x1007,
 	[MLXSW_RES_ID_MAX_TRAP_GROUPS] = 0x2201,
 	[MLXSW_RES_ID_CQE_V0] = 0x2210,
 	[MLXSW_RES_ID_CQE_V1] = 0x2211,
@@ -104,6 +84,13 @@ static u16 mlxsw_res_ids[] = {
 	[MLXSW_RES_ID_ACL_FLEX_KEYS] = 0x2910,
 	[MLXSW_RES_ID_ACL_MAX_ACTION_PER_RULE] = 0x2911,
 	[MLXSW_RES_ID_ACL_ACTIONS_PER_SET] = 0x2912,
+	[MLXSW_RES_ID_ACL_MAX_ERPT_BANKS] = 0x2940,
+	[MLXSW_RES_ID_ACL_MAX_ERPT_BANK_SIZE] = 0x2941,
+	[MLXSW_RES_ID_ACL_MAX_LARGE_KEY_ID] = 0x2942,
+	[MLXSW_RES_ID_ACL_ERPT_ENTRIES_2KB] = 0x2950,
+	[MLXSW_RES_ID_ACL_ERPT_ENTRIES_4KB] = 0x2951,
+	[MLXSW_RES_ID_ACL_ERPT_ENTRIES_8KB] = 0x2952,
+	[MLXSW_RES_ID_ACL_ERPT_ENTRIES_12KB] = 0x2953,
 	[MLXSW_RES_ID_MAX_CPU_POLICERS] = 0x2A13,
 	[MLXSW_RES_ID_MAX_VRS] = 0x2C01,
 	[MLXSW_RES_ID_MAX_RIFS] = 0x2C02,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 968b88af2ef5..6070d1591d1e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1,38 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum.c
- * Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015-2017 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2015 Elad Raz <eladr@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -74,17 +41,27 @@
 #include "spectrum_span.h"
 #include "../mlxfw/mlxfw.h"
 
-#define MLXSW_FWREV_MAJOR 13
-#define MLXSW_FWREV_MINOR 1620
-#define MLXSW_FWREV_SUBMINOR 192
-#define MLXSW_FWREV_MINOR_TO_BRANCH(minor) ((minor) / 100)
+#define MLXSW_SP_FWREV_MINOR_TO_BRANCH(minor) ((minor) / 100)
+
+#define MLXSW_SP1_FWREV_MAJOR 13
+#define MLXSW_SP1_FWREV_MINOR 1702
+#define MLXSW_SP1_FWREV_SUBMINOR 6
+#define MLXSW_SP1_FWREV_CAN_RESET_MINOR 1702
 
-#define MLXSW_SP_FW_FILENAME \
-	"mellanox/mlxsw_spectrum-" __stringify(MLXSW_FWREV_MAJOR) \
-	"." __stringify(MLXSW_FWREV_MINOR) \
-	"." __stringify(MLXSW_FWREV_SUBMINOR) ".mfa2"
+static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = {
+	.major = MLXSW_SP1_FWREV_MAJOR,
+	.minor = MLXSW_SP1_FWREV_MINOR,
+	.subminor = MLXSW_SP1_FWREV_SUBMINOR,
+	.can_reset_minor = MLXSW_SP1_FWREV_CAN_RESET_MINOR,
+};
+
+#define MLXSW_SP1_FW_FILENAME \
+	"mellanox/mlxsw_spectrum-" __stringify(MLXSW_SP1_FWREV_MAJOR) \
+	"." __stringify(MLXSW_SP1_FWREV_MINOR) \
+	"." __stringify(MLXSW_SP1_FWREV_SUBMINOR) ".mfa2"
 
-static const char mlxsw_sp_driver_name[] = "mlxsw_spectrum";
+static const char mlxsw_sp1_driver_name[] = "mlxsw_spectrum";
+static const char mlxsw_sp2_driver_name[] = "mlxsw_spectrum2";
 static const char mlxsw_sp_driver_version[] = "1.0";
 
 /* tx_hdr_version
@@ -338,35 +315,50 @@ static int mlxsw_sp_firmware_flash(struct mlxsw_sp *mlxsw_sp,
 static int mlxsw_sp_fw_rev_validate(struct mlxsw_sp *mlxsw_sp)
 {
 	const struct mlxsw_fw_rev *rev = &mlxsw_sp->bus_info->fw_rev;
+	const struct mlxsw_fw_rev *req_rev = mlxsw_sp->req_rev;
+	const char *fw_filename = mlxsw_sp->fw_filename;
 	const struct firmware *firmware;
 	int err;
 
+	/* Don't check if driver does not require it */
+	if (!req_rev || !fw_filename)
+		return 0;
+
 	/* Validate driver & FW are compatible */
-	if (rev->major != MLXSW_FWREV_MAJOR) {
+	if (rev->major != req_rev->major) {
 		WARN(1, "Mismatch in major FW version [%d:%d] is never expected; Please contact support\n",
-		     rev->major, MLXSW_FWREV_MAJOR);
+		     rev->major, req_rev->major);
 		return -EINVAL;
 	}
-	if (MLXSW_FWREV_MINOR_TO_BRANCH(rev->minor) ==
-	    MLXSW_FWREV_MINOR_TO_BRANCH(MLXSW_FWREV_MINOR))
+	if (MLXSW_SP_FWREV_MINOR_TO_BRANCH(rev->minor) ==
+	    MLXSW_SP_FWREV_MINOR_TO_BRANCH(req_rev->minor))
 		return 0;
 
 	dev_info(mlxsw_sp->bus_info->dev, "The firmware version %d.%d.%d is incompatible with the driver\n",
 		 rev->major, rev->minor, rev->subminor);
 	dev_info(mlxsw_sp->bus_info->dev, "Flashing firmware using file %s\n",
-		 MLXSW_SP_FW_FILENAME);
+		 fw_filename);
 
-	err = request_firmware_direct(&firmware, MLXSW_SP_FW_FILENAME,
+	err = request_firmware_direct(&firmware, fw_filename,
 				      mlxsw_sp->bus_info->dev);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Could not request firmware file %s\n",
-			MLXSW_SP_FW_FILENAME);
+			fw_filename);
 		return err;
 	}
 
 	err = mlxsw_sp_firmware_flash(mlxsw_sp, firmware);
 	release_firmware(firmware);
-	return err;
+	if (err)
+		dev_err(mlxsw_sp->bus_info->dev, "Could not upgrade firmware\n");
+
+	/* On FW flash success, tell the caller FW reset is needed
+	 * if current FW supports it.
+	 */
+	if (rev->minor >= req_rev->can_reset_minor)
+		return err ? err : -EAGAIN;
+	else
+		return 0;
 }
 
 int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp,
@@ -1441,6 +1433,11 @@ mlxsw_sp_setup_tc_cls_flower(struct mlxsw_sp_acl_block *acl_block,
 		return 0;
 	case TC_CLSFLOWER_STATS:
 		return mlxsw_sp_flower_stats(mlxsw_sp, acl_block, f);
+	case TC_CLSFLOWER_TMPLT_CREATE:
+		return mlxsw_sp_flower_tmplt_create(mlxsw_sp, acl_block, f);
+	case TC_CLSFLOWER_TMPLT_DESTROY:
+		mlxsw_sp_flower_tmplt_destroy(mlxsw_sp, acl_block, f);
+		return 0;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -1503,7 +1500,8 @@ static int mlxsw_sp_setup_tc_block_cb_flower(enum tc_setup_type type,
 
 static int
 mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port,
-				    struct tcf_block *block, bool ingress)
+				    struct tcf_block *block, bool ingress,
+				    struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct mlxsw_sp_acl_block *acl_block;
@@ -1518,7 +1516,7 @@ mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port,
 			return -ENOMEM;
 		block_cb = __tcf_block_cb_register(block,
 						   mlxsw_sp_setup_tc_block_cb_flower,
-						   mlxsw_sp, acl_block);
+						   mlxsw_sp, acl_block, extack);
 		if (IS_ERR(block_cb)) {
 			err = PTR_ERR(block_cb);
 			goto err_cb_register;
@@ -1541,7 +1539,7 @@ mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port,
 
 err_block_bind:
 	if (!tcf_block_cb_decref(block_cb)) {
-		__tcf_block_cb_unregister(block_cb);
+		__tcf_block_cb_unregister(block, block_cb);
 err_cb_register:
 		mlxsw_sp_acl_block_destroy(acl_block);
 	}
@@ -1571,7 +1569,7 @@ mlxsw_sp_setup_tc_block_flower_unbind(struct mlxsw_sp_port *mlxsw_sp_port,
 	err = mlxsw_sp_acl_block_unbind(mlxsw_sp, acl_block,
 					mlxsw_sp_port, ingress);
 	if (!err && !tcf_block_cb_decref(block_cb)) {
-		__tcf_block_cb_unregister(block_cb);
+		__tcf_block_cb_unregister(block, block_cb);
 		mlxsw_sp_acl_block_destroy(acl_block);
 	}
 }
@@ -1596,11 +1594,12 @@ static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		err = tcf_block_cb_register(f->block, cb, mlxsw_sp_port,
-					    mlxsw_sp_port);
+					    mlxsw_sp_port, f->extack);
 		if (err)
 			return err;
 		err = mlxsw_sp_setup_tc_block_flower_bind(mlxsw_sp_port,
-							  f->block, ingress);
+							  f->block, ingress,
+							  f->extack);
 		if (err) {
 			tcf_block_cb_unregister(f->block, cb, mlxsw_sp_port);
 			return err;
@@ -1712,7 +1711,8 @@ static void mlxsw_sp_port_get_drvinfo(struct net_device *dev,
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 
-	strlcpy(drvinfo->driver, mlxsw_sp_driver_name, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->driver, mlxsw_sp->bus_info->device_kind,
+		sizeof(drvinfo->driver));
 	strlcpy(drvinfo->version, mlxsw_sp_driver_version,
 		sizeof(drvinfo->version));
 	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
@@ -1873,6 +1873,52 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_stats[] = {
 
 #define MLXSW_SP_PORT_HW_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_stats)
 
+static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_rfc_2819_stats[] = {
+	{
+		.str = "ether_pkts64octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts64octets_get,
+	},
+	{
+		.str = "ether_pkts65to127octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts65to127octets_get,
+	},
+	{
+		.str = "ether_pkts128to255octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts128to255octets_get,
+	},
+	{
+		.str = "ether_pkts256to511octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts256to511octets_get,
+	},
+	{
+		.str = "ether_pkts512to1023octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts512to1023octets_get,
+	},
+	{
+		.str = "ether_pkts1024to1518octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts1024to1518octets_get,
+	},
+	{
+		.str = "ether_pkts1519to2047octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts1519to2047octets_get,
+	},
+	{
+		.str = "ether_pkts2048to4095octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts2048to4095octets_get,
+	},
+	{
+		.str = "ether_pkts4096to8191octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts4096to8191octets_get,
+	},
+	{
+		.str = "ether_pkts8192to10239octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts8192to10239octets_get,
+	},
+};
+
+#define MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN \
+	ARRAY_SIZE(mlxsw_sp_port_hw_rfc_2819_stats)
+
 static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_prio_stats[] = {
 	{
 		.str = "rx_octets_prio",
@@ -1925,9 +1971,11 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_tc_stats[] = {
 #define MLXSW_SP_PORT_HW_TC_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_tc_stats)
 
 #define MLXSW_SP_PORT_ETHTOOL_STATS_LEN (MLXSW_SP_PORT_HW_STATS_LEN + \
-					 (MLXSW_SP_PORT_HW_PRIO_STATS_LEN + \
-					  MLXSW_SP_PORT_HW_TC_STATS_LEN) * \
-					 IEEE_8021QAZ_MAX_TCS)
+					 MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN + \
+					 (MLXSW_SP_PORT_HW_PRIO_STATS_LEN * \
+					  IEEE_8021QAZ_MAX_TCS) + \
+					 (MLXSW_SP_PORT_HW_TC_STATS_LEN * \
+					  TC_MAX_QUEUE))
 
 static void mlxsw_sp_port_get_prio_strings(u8 **p, int prio)
 {
@@ -1964,11 +2012,16 @@ static void mlxsw_sp_port_get_strings(struct net_device *dev,
 			       ETH_GSTRING_LEN);
 			p += ETH_GSTRING_LEN;
 		}
+		for (i = 0; i < MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN; i++) {
+			memcpy(p, mlxsw_sp_port_hw_rfc_2819_stats[i].str,
+			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
 
 		for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
 			mlxsw_sp_port_get_prio_strings(&p, i);
 
-		for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+		for (i = 0; i < TC_MAX_QUEUE; i++)
 			mlxsw_sp_port_get_tc_strings(&p, i);
 
 		break;
@@ -2003,10 +2056,14 @@ mlxsw_sp_get_hw_stats_by_group(struct mlxsw_sp_port_hw_stats **p_hw_stats,
 			       int *p_len, enum mlxsw_reg_ppcnt_grp grp)
 {
 	switch (grp) {
-	case  MLXSW_REG_PPCNT_IEEE_8023_CNT:
+	case MLXSW_REG_PPCNT_IEEE_8023_CNT:
 		*p_hw_stats = mlxsw_sp_port_hw_stats;
 		*p_len = MLXSW_SP_PORT_HW_STATS_LEN;
 		break;
+	case MLXSW_REG_PPCNT_RFC_2819_CNT:
+		*p_hw_stats = mlxsw_sp_port_hw_rfc_2819_stats;
+		*p_len = MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN;
+		break;
 	case MLXSW_REG_PPCNT_PRIO_CNT:
 		*p_hw_stats = mlxsw_sp_port_hw_prio_stats;
 		*p_len = MLXSW_SP_PORT_HW_PRIO_STATS_LEN;
@@ -2056,6 +2113,11 @@ static void mlxsw_sp_port_get_stats(struct net_device *dev,
 				  data, data_index);
 	data_index = MLXSW_SP_PORT_HW_STATS_LEN;
 
+	/* RFC 2819 Counters */
+	__mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_RFC_2819_CNT, 0,
+				  data, data_index);
+	data_index += MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN;
+
 	/* Per-Priority Counters */
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
 		__mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_PRIO_CNT, i,
@@ -2064,7 +2126,7 @@ static void mlxsw_sp_port_get_stats(struct net_device *dev,
 	}
 
 	/* Per-TC Counters */
-	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+	for (i = 0; i < TC_MAX_QUEUE; i++) {
 		__mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_TC_CNT, i,
 					  data, data_index);
 		data_index += MLXSW_SP_PORT_HW_TC_STATS_LEN;
@@ -2711,9 +2773,16 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port)
 					    false, 0);
 		if (err)
 			return err;
+
+		err = mlxsw_sp_port_ets_set(mlxsw_sp_port,
+					    MLXSW_REG_QEEC_HIERARCY_TC,
+					    i + 8, i,
+					    false, 0);
+		if (err)
+			return err;
 	}
 
-	/* Make sure the max shaper is disabled in all hierarcies that
+	/* Make sure the max shaper is disabled in all hierarchies that
 	 * support it.
 	 */
 	err = mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port,
@@ -2748,6 +2817,16 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port)
 	return 0;
 }
 
+static int mlxsw_sp_port_tc_mc_mode_set(struct mlxsw_sp_port *mlxsw_sp_port,
+					bool enable)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char qtctm_pl[MLXSW_REG_QTCTM_LEN];
+
+	mlxsw_reg_qtctm_pack(qtctm_pl, mlxsw_sp_port->local_port, enable);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qtctm), qtctm_pl);
+}
+
 static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				bool split, u8 module, u8 width, u8 lane)
 {
@@ -2876,6 +2955,13 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 		goto err_port_ets_init;
 	}
 
+	err = mlxsw_sp_port_tc_mc_mode_set(mlxsw_sp_port, true);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to initialize TC MC mode\n",
+			mlxsw_sp_port->local_port);
+		goto err_port_tc_mc_mode;
+	}
+
 	/* ETS and buffers must be initialized before DCB. */
 	err = mlxsw_sp_port_dcb_init(mlxsw_sp_port);
 	if (err) {
@@ -2932,6 +3018,8 @@ err_port_qdiscs_init:
 err_port_fids_init:
 	mlxsw_sp_port_dcb_fini(mlxsw_sp_port);
 err_port_dcb_init:
+	mlxsw_sp_port_tc_mc_mode_set(mlxsw_sp_port, false);
+err_port_tc_mc_mode:
 err_port_ets_init:
 err_port_buffers_init:
 err_port_admin_status_set:
@@ -2966,6 +3054,7 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 	mlxsw_sp_tc_qdisc_fini(mlxsw_sp_port);
 	mlxsw_sp_port_fids_fini(mlxsw_sp_port);
 	mlxsw_sp_port_dcb_fini(mlxsw_sp_port);
+	mlxsw_sp_port_tc_mc_mode_set(mlxsw_sp_port, false);
 	mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT);
 	mlxsw_sp_port_module_unmap(mlxsw_sp_port);
 	kfree(mlxsw_sp_port->sample);
@@ -3371,6 +3460,8 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV4, TRAP_TO_CPU, ROUTER_EXP, false),
 	MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV6, TRAP_TO_CPU, ROUTER_EXP, false),
 	MLXSW_SP_RXL_MARK(IPIP_DECAP_ERROR, TRAP_TO_CPU, ROUTER_EXP, false),
+	MLXSW_SP_RXL_MARK(IPV4_VRRP, TRAP_TO_CPU, ROUTER_EXP, false),
+	MLXSW_SP_RXL_MARK(IPV6_VRRP, TRAP_TO_CPU, ROUTER_EXP, false),
 	/* PKT Sample trap */
 	MLXSW_RXL(mlxsw_sp_rx_listener_sample_func, PKT_SAMPLE, MIRROR_TO_CPU,
 		  false, SP_IP2ME, DISCARD),
@@ -3623,10 +3714,8 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 	mlxsw_sp->bus_info = mlxsw_bus_info;
 
 	err = mlxsw_sp_fw_rev_validate(mlxsw_sp);
-	if (err) {
-		dev_err(mlxsw_sp->bus_info->dev, "Could not upgrade firmware\n");
+	if (err)
 		return err;
-	}
 
 	err = mlxsw_sp_base_mac_get(mlxsw_sp);
 	if (err) {
@@ -3757,6 +3846,36 @@ err_fids_init:
 	return err;
 }
 
+static int mlxsw_sp1_init(struct mlxsw_core *mlxsw_core,
+			  const struct mlxsw_bus_info *mlxsw_bus_info)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+
+	mlxsw_sp->req_rev = &mlxsw_sp1_fw_rev;
+	mlxsw_sp->fw_filename = MLXSW_SP1_FW_FILENAME;
+	mlxsw_sp->kvdl_ops = &mlxsw_sp1_kvdl_ops;
+	mlxsw_sp->afa_ops = &mlxsw_sp1_act_afa_ops;
+	mlxsw_sp->afk_ops = &mlxsw_sp1_afk_ops;
+	mlxsw_sp->mr_tcam_ops = &mlxsw_sp1_mr_tcam_ops;
+	mlxsw_sp->acl_tcam_ops = &mlxsw_sp1_acl_tcam_ops;
+
+	return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info);
+}
+
+static int mlxsw_sp2_init(struct mlxsw_core *mlxsw_core,
+			  const struct mlxsw_bus_info *mlxsw_bus_info)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+
+	mlxsw_sp->kvdl_ops = &mlxsw_sp2_kvdl_ops;
+	mlxsw_sp->afa_ops = &mlxsw_sp2_act_afa_ops;
+	mlxsw_sp->afk_ops = &mlxsw_sp2_afk_ops;
+	mlxsw_sp->mr_tcam_ops = &mlxsw_sp2_mr_tcam_ops;
+	mlxsw_sp->acl_tcam_ops = &mlxsw_sp2_acl_tcam_ops;
+
+	return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info);
+}
+
 static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
@@ -3777,7 +3896,7 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 	mlxsw_sp_kvdl_fini(mlxsw_sp);
 }
 
-static const struct mlxsw_config_profile mlxsw_sp_config_profile = {
+static const struct mlxsw_config_profile mlxsw_sp1_config_profile = {
 	.used_max_mid			= 1,
 	.max_mid			= MLXSW_SP_MID_MAX,
 	.used_flood_tables		= 1,
@@ -3803,6 +3922,28 @@ static const struct mlxsw_config_profile mlxsw_sp_config_profile = {
 	},
 };
 
+static const struct mlxsw_config_profile mlxsw_sp2_config_profile = {
+	.used_max_mid			= 1,
+	.max_mid			= MLXSW_SP_MID_MAX,
+	.used_flood_tables		= 1,
+	.used_flood_mode		= 1,
+	.flood_mode			= 3,
+	.max_fid_offset_flood_tables	= 3,
+	.fid_offset_flood_table_size	= VLAN_N_VID - 1,
+	.max_fid_flood_tables		= 3,
+	.fid_flood_table_size		= MLXSW_SP_FID_8021D_MAX,
+	.used_max_ib_mc			= 1,
+	.max_ib_mc			= 0,
+	.used_max_pkey			= 1,
+	.max_pkey			= 0,
+	.swid_config			= {
+		{
+			.used_type	= 1,
+			.type		= MLXSW_PORT_SWID_TYPE_ETH,
+		}
+	},
+};
+
 static void
 mlxsw_sp_resource_size_params_prepare(struct mlxsw_core *mlxsw_core,
 				      struct devlink_resource_size_params *kvd_size_params,
@@ -3839,7 +3980,7 @@ mlxsw_sp_resource_size_params_prepare(struct mlxsw_core *mlxsw_core,
 					  DEVLINK_RESOURCE_UNIT_ENTRY);
 }
 
-static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core)
+static int mlxsw_sp1_resources_kvd_register(struct mlxsw_core *mlxsw_core)
 {
 	struct devlink *devlink = priv_to_devlink(mlxsw_core);
 	struct devlink_resource_size_params hash_single_size_params;
@@ -3850,7 +3991,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core)
 	const struct mlxsw_config_profile *profile;
 	int err;
 
-	profile = &mlxsw_sp_config_profile;
+	profile = &mlxsw_sp1_config_profile;
 	if (!MLXSW_CORE_RES_VALID(mlxsw_core, KVD_SIZE))
 		return -EIO;
 
@@ -3876,7 +4017,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core)
 	if (err)
 		return err;
 
-	err = mlxsw_sp_kvdl_resources_register(mlxsw_core);
+	err = mlxsw_sp1_kvdl_resources_register(mlxsw_core);
 	if  (err)
 		return err;
 
@@ -3905,6 +4046,16 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core)
 	return 0;
 }
 
+static int mlxsw_sp1_resources_register(struct mlxsw_core *mlxsw_core)
+{
+	return mlxsw_sp1_resources_kvd_register(mlxsw_core);
+}
+
+static int mlxsw_sp2_resources_register(struct mlxsw_core *mlxsw_core)
+{
+	return 0;
+}
+
 static int mlxsw_sp_kvd_sizes_get(struct mlxsw_core *mlxsw_core,
 				  const struct mlxsw_config_profile *profile,
 				  u64 *p_single_size, u64 *p_double_size,
@@ -3960,10 +4111,10 @@ static int mlxsw_sp_kvd_sizes_get(struct mlxsw_core *mlxsw_core,
 	return 0;
 }
 
-static struct mlxsw_driver mlxsw_sp_driver = {
-	.kind				= mlxsw_sp_driver_name,
+static struct mlxsw_driver mlxsw_sp1_driver = {
+	.kind				= mlxsw_sp1_driver_name,
 	.priv_size			= sizeof(struct mlxsw_sp),
-	.init				= mlxsw_sp_init,
+	.init				= mlxsw_sp1_init,
 	.fini				= mlxsw_sp_fini,
 	.basic_trap_groups_set		= mlxsw_sp_basic_trap_groups_set,
 	.port_split			= mlxsw_sp_port_split,
@@ -3979,10 +4130,35 @@ static struct mlxsw_driver mlxsw_sp_driver = {
 	.sb_occ_port_pool_get		= mlxsw_sp_sb_occ_port_pool_get,
 	.sb_occ_tc_port_bind_get	= mlxsw_sp_sb_occ_tc_port_bind_get,
 	.txhdr_construct		= mlxsw_sp_txhdr_construct,
-	.resources_register		= mlxsw_sp_resources_register,
+	.resources_register		= mlxsw_sp1_resources_register,
 	.kvd_sizes_get			= mlxsw_sp_kvd_sizes_get,
 	.txhdr_len			= MLXSW_TXHDR_LEN,
-	.profile			= &mlxsw_sp_config_profile,
+	.profile			= &mlxsw_sp1_config_profile,
+	.res_query_enabled		= true,
+};
+
+static struct mlxsw_driver mlxsw_sp2_driver = {
+	.kind				= mlxsw_sp2_driver_name,
+	.priv_size			= sizeof(struct mlxsw_sp),
+	.init				= mlxsw_sp2_init,
+	.fini				= mlxsw_sp_fini,
+	.basic_trap_groups_set		= mlxsw_sp_basic_trap_groups_set,
+	.port_split			= mlxsw_sp_port_split,
+	.port_unsplit			= mlxsw_sp_port_unsplit,
+	.sb_pool_get			= mlxsw_sp_sb_pool_get,
+	.sb_pool_set			= mlxsw_sp_sb_pool_set,
+	.sb_port_pool_get		= mlxsw_sp_sb_port_pool_get,
+	.sb_port_pool_set		= mlxsw_sp_sb_port_pool_set,
+	.sb_tc_pool_bind_get		= mlxsw_sp_sb_tc_pool_bind_get,
+	.sb_tc_pool_bind_set		= mlxsw_sp_sb_tc_pool_bind_set,
+	.sb_occ_snapshot		= mlxsw_sp_sb_occ_snapshot,
+	.sb_occ_max_clear		= mlxsw_sp_sb_occ_max_clear,
+	.sb_occ_port_pool_get		= mlxsw_sp_sb_occ_port_pool_get,
+	.sb_occ_tc_port_bind_get	= mlxsw_sp_sb_occ_tc_port_bind_get,
+	.txhdr_construct		= mlxsw_sp_txhdr_construct,
+	.resources_register		= mlxsw_sp2_resources_register,
+	.txhdr_len			= MLXSW_TXHDR_LEN,
+	.profile			= &mlxsw_sp2_config_profile,
 	.res_query_enabled		= true,
 };
 
@@ -4397,7 +4573,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 		if (!is_vlan_dev(upper_dev) &&
 		    !netif_is_lag_master(upper_dev) &&
 		    !netif_is_bridge_master(upper_dev) &&
-		    !netif_is_ovs_master(upper_dev)) {
+		    !netif_is_ovs_master(upper_dev) &&
+		    !netif_is_macvlan(upper_dev)) {
 			NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
 			return -EINVAL;
 		}
@@ -4423,6 +4600,11 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 			NL_SET_ERR_MSG_MOD(extack, "Can not put a VLAN on a LAG port");
 			return -EINVAL;
 		}
+		if (netif_is_macvlan(upper_dev) &&
+		    !mlxsw_sp_rif_find_by_dev(mlxsw_sp, lower_dev)) {
+			NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
+			return -EOPNOTSUPP;
+		}
 		if (netif_is_ovs_master(upper_dev) && vlan_uses_dev(dev)) {
 			NL_SET_ERR_MSG_MOD(extack, "Master device is an OVS master and this device has a VLAN");
 			return -EINVAL;
@@ -4461,6 +4643,9 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 				err = mlxsw_sp_port_ovs_join(mlxsw_sp_port);
 			else
 				mlxsw_sp_port_ovs_leave(mlxsw_sp_port);
+		} else if (netif_is_macvlan(upper_dev)) {
+			if (!info->linking)
+				mlxsw_sp_rif_macvlan_del(mlxsw_sp, upper_dev);
 		}
 		break;
 	}
@@ -4545,8 +4730,9 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev,
 	switch (event) {
 	case NETDEV_PRECHANGEUPPER:
 		upper_dev = info->upper_dev;
-		if (!netif_is_bridge_master(upper_dev)) {
-			NL_SET_ERR_MSG_MOD(extack, "VLAN devices only support bridge and VRF uppers");
+		if (!netif_is_bridge_master(upper_dev) &&
+		    !netif_is_macvlan(upper_dev)) {
+			NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
 			return -EINVAL;
 		}
 		if (!info->linking)
@@ -4558,6 +4744,11 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev,
 			NL_SET_ERR_MSG_MOD(extack, "Enslaving a port to a device that already has an upper device is not supported");
 			return -EINVAL;
 		}
+		if (netif_is_macvlan(upper_dev) &&
+		    !mlxsw_sp_rif_find_by_dev(mlxsw_sp, vlan_dev)) {
+			NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
+			return -EOPNOTSUPP;
+		}
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
@@ -4571,6 +4762,9 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev,
 				mlxsw_sp_port_bridge_leave(mlxsw_sp_port,
 							   vlan_dev,
 							   upper_dev);
+		} else if (netif_is_macvlan(upper_dev)) {
+			if (!info->linking)
+				mlxsw_sp_rif_macvlan_del(mlxsw_sp, upper_dev);
 		} else {
 			err = -EINVAL;
 			WARN_ON(1);
@@ -4620,6 +4814,64 @@ static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev,
 	return 0;
 }
 
+static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev,
+					   unsigned long event, void *ptr)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(br_dev);
+	struct netdev_notifier_changeupper_info *info = ptr;
+	struct netlink_ext_ack *extack;
+	struct net_device *upper_dev;
+
+	if (!mlxsw_sp)
+		return 0;
+
+	extack = netdev_notifier_info_to_extack(&info->info);
+
+	switch (event) {
+	case NETDEV_PRECHANGEUPPER:
+		upper_dev = info->upper_dev;
+		if (!is_vlan_dev(upper_dev) && !netif_is_macvlan(upper_dev)) {
+			NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
+			return -EOPNOTSUPP;
+		}
+		if (!info->linking)
+			break;
+		if (netif_is_macvlan(upper_dev) &&
+		    !mlxsw_sp_rif_find_by_dev(mlxsw_sp, br_dev)) {
+			NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
+			return -EOPNOTSUPP;
+		}
+		break;
+	case NETDEV_CHANGEUPPER:
+		upper_dev = info->upper_dev;
+		if (info->linking)
+			break;
+		if (netif_is_macvlan(upper_dev))
+			mlxsw_sp_rif_macvlan_del(mlxsw_sp, upper_dev);
+		break;
+	}
+
+	return 0;
+}
+
+static int mlxsw_sp_netdevice_macvlan_event(struct net_device *macvlan_dev,
+					    unsigned long event, void *ptr)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(macvlan_dev);
+	struct netdev_notifier_changeupper_info *info = ptr;
+	struct netlink_ext_ack *extack;
+
+	if (!mlxsw_sp || event != NETDEV_PRECHANGEUPPER)
+		return 0;
+
+	extack = netdev_notifier_info_to_extack(&info->info);
+
+	/* VRF enslavement is handled in mlxsw_sp_netdevice_vrf_event() */
+	NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
+
+	return -EOPNOTSUPP;
+}
+
 static bool mlxsw_sp_is_vrf_event(unsigned long event, void *ptr)
 {
 	struct netdev_notifier_changeupper_info *info = ptr;
@@ -4661,6 +4913,10 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *nb,
 		err = mlxsw_sp_netdevice_lag_event(dev, event, ptr);
 	else if (is_vlan_dev(dev))
 		err = mlxsw_sp_netdevice_vlan_event(dev, event, ptr);
+	else if (netif_is_bridge_master(dev))
+		err = mlxsw_sp_netdevice_bridge_event(dev, event, ptr);
+	else if (netif_is_macvlan(dev))
+		err = mlxsw_sp_netdevice_macvlan_event(dev, event, ptr);
 
 	return notifier_from_errno(err);
 }
@@ -4681,14 +4937,24 @@ static struct notifier_block mlxsw_sp_inet6addr_nb __read_mostly = {
 	.notifier_call = mlxsw_sp_inet6addr_event,
 };
 
-static const struct pci_device_id mlxsw_sp_pci_id_table[] = {
+static const struct pci_device_id mlxsw_sp1_pci_id_table[] = {
 	{PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SPECTRUM), 0},
 	{0, },
 };
 
-static struct pci_driver mlxsw_sp_pci_driver = {
-	.name = mlxsw_sp_driver_name,
-	.id_table = mlxsw_sp_pci_id_table,
+static struct pci_driver mlxsw_sp1_pci_driver = {
+	.name = mlxsw_sp1_driver_name,
+	.id_table = mlxsw_sp1_pci_id_table,
+};
+
+static const struct pci_device_id mlxsw_sp2_pci_id_table[] = {
+	{PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SPECTRUM2), 0},
+	{0, },
+};
+
+static struct pci_driver mlxsw_sp2_pci_driver = {
+	.name = mlxsw_sp2_driver_name,
+	.id_table = mlxsw_sp2_pci_id_table,
 };
 
 static int __init mlxsw_sp_module_init(void)
@@ -4700,19 +4966,31 @@ static int __init mlxsw_sp_module_init(void)
 	register_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb);
 	register_inet6addr_notifier(&mlxsw_sp_inet6addr_nb);
 
-	err = mlxsw_core_driver_register(&mlxsw_sp_driver);
+	err = mlxsw_core_driver_register(&mlxsw_sp1_driver);
+	if (err)
+		goto err_sp1_core_driver_register;
+
+	err = mlxsw_core_driver_register(&mlxsw_sp2_driver);
+	if (err)
+		goto err_sp2_core_driver_register;
+
+	err = mlxsw_pci_driver_register(&mlxsw_sp1_pci_driver);
 	if (err)
-		goto err_core_driver_register;
+		goto err_sp1_pci_driver_register;
 
-	err = mlxsw_pci_driver_register(&mlxsw_sp_pci_driver);
+	err = mlxsw_pci_driver_register(&mlxsw_sp2_pci_driver);
 	if (err)
-		goto err_pci_driver_register;
+		goto err_sp2_pci_driver_register;
 
 	return 0;
 
-err_pci_driver_register:
-	mlxsw_core_driver_unregister(&mlxsw_sp_driver);
-err_core_driver_register:
+err_sp2_pci_driver_register:
+	mlxsw_pci_driver_unregister(&mlxsw_sp2_pci_driver);
+err_sp1_pci_driver_register:
+	mlxsw_core_driver_unregister(&mlxsw_sp2_driver);
+err_sp2_core_driver_register:
+	mlxsw_core_driver_unregister(&mlxsw_sp1_driver);
+err_sp1_core_driver_register:
 	unregister_inet6addr_notifier(&mlxsw_sp_inet6addr_nb);
 	unregister_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb);
 	unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
@@ -4722,8 +5000,10 @@ err_core_driver_register:
 
 static void __exit mlxsw_sp_module_exit(void)
 {
-	mlxsw_pci_driver_unregister(&mlxsw_sp_pci_driver);
-	mlxsw_core_driver_unregister(&mlxsw_sp_driver);
+	mlxsw_pci_driver_unregister(&mlxsw_sp2_pci_driver);
+	mlxsw_pci_driver_unregister(&mlxsw_sp1_pci_driver);
+	mlxsw_core_driver_unregister(&mlxsw_sp2_driver);
+	mlxsw_core_driver_unregister(&mlxsw_sp1_driver);
 	unregister_inet6addr_notifier(&mlxsw_sp_inet6addr_nb);
 	unregister_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb);
 	unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
@@ -4736,5 +5016,6 @@ module_exit(mlxsw_sp_module_exit);
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Jiri Pirko <jiri@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox Spectrum driver");
-MODULE_DEVICE_TABLE(pci, mlxsw_sp_pci_id_table);
-MODULE_FIRMWARE(MLXSW_SP_FW_FILENAME);
+MODULE_DEVICE_TABLE(pci, mlxsw_sp1_pci_id_table);
+MODULE_DEVICE_TABLE(pci, mlxsw_sp2_pci_id_table);
+MODULE_FIRMWARE(MLXSW_SP1_FW_FILENAME);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 4a519d8edec8..3ae930196741 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -1,38 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum.h
- * Copyright (c) 2015-2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015-2017 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2015 Elad Raz <eladr@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_SPECTRUM_H
 #define _MLXSW_SPECTRUM_H
@@ -54,6 +21,7 @@
 #include "core.h"
 #include "core_acl_flex_keys.h"
 #include "core_acl_flex_actions.h"
+#include "reg.h"
 
 #define MLXSW_SP_FID_8021D_MAX 1024
 
@@ -145,6 +113,9 @@ struct mlxsw_sp_acl;
 struct mlxsw_sp_counter_pool;
 struct mlxsw_sp_fid_core;
 struct mlxsw_sp_kvdl;
+struct mlxsw_sp_kvdl_ops;
+struct mlxsw_sp_mr_tcam_ops;
+struct mlxsw_sp_acl_tcam_ops;
 
 struct mlxsw_sp {
 	struct mlxsw_sp_port **ports;
@@ -168,6 +139,13 @@ struct mlxsw_sp {
 		struct mlxsw_sp_span_entry *entries;
 		int entries_count;
 	} span;
+	const struct mlxsw_fw_rev *req_rev;
+	const char *fw_filename;
+	const struct mlxsw_sp_kvdl_ops *kvdl_ops;
+	const struct mlxsw_afa_ops *afa_ops;
+	const struct mlxsw_afk_ops *afk_ops;
+	const struct mlxsw_sp_mr_tcam_ops *mr_tcam_ops;
+	const struct mlxsw_sp_acl_tcam_ops *acl_tcam_ops;
 };
 
 static inline struct mlxsw_sp_upper *
@@ -233,6 +211,7 @@ struct mlxsw_sp_port {
 		struct ieee_ets *ets;
 		struct ieee_maxrate *maxrate;
 		struct ieee_pfc *pfc;
+		enum mlxsw_reg_qpts_trust_state trust_state;
 	} dcb;
 	struct {
 		u8 module;
@@ -407,6 +386,8 @@ static inline void mlxsw_sp_port_dcb_fini(struct mlxsw_sp_port *mlxsw_sp_port)
 int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp);
 int mlxsw_sp_netdevice_router_port_event(struct net_device *dev);
+void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp,
+			      const struct net_device *macvlan_dev);
 int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
 			    unsigned long event, void *ptr);
 int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused,
@@ -435,15 +416,62 @@ mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
 void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif);
 
 /* spectrum_kvdl.c */
+enum mlxsw_sp_kvdl_entry_type {
+	MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+	MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
+	MLXSW_SP_KVDL_ENTRY_TYPE_PBS,
+	MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR,
+};
+
+static inline unsigned int
+mlxsw_sp_kvdl_entry_size(enum mlxsw_sp_kvdl_entry_type type)
+{
+	switch (type) {
+	case MLXSW_SP_KVDL_ENTRY_TYPE_ADJ: /* fall through */
+	case MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET: /* fall through */
+	case MLXSW_SP_KVDL_ENTRY_TYPE_PBS: /* fall through */
+	case MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR: /* fall through */
+	default:
+		return 1;
+	}
+}
+
+struct mlxsw_sp_kvdl_ops {
+	size_t priv_size;
+	int (*init)(struct mlxsw_sp *mlxsw_sp, void *priv);
+	void (*fini)(struct mlxsw_sp *mlxsw_sp, void *priv);
+	int (*alloc)(struct mlxsw_sp *mlxsw_sp, void *priv,
+		     enum mlxsw_sp_kvdl_entry_type type,
+		     unsigned int entry_count, u32 *p_entry_index);
+	void (*free)(struct mlxsw_sp *mlxsw_sp, void *priv,
+		     enum mlxsw_sp_kvdl_entry_type type,
+		     unsigned int entry_count, int entry_index);
+	int (*alloc_size_query)(struct mlxsw_sp *mlxsw_sp, void *priv,
+				enum mlxsw_sp_kvdl_entry_type type,
+				unsigned int entry_count,
+				unsigned int *p_alloc_count);
+	int (*resources_register)(struct mlxsw_sp *mlxsw_sp, void *priv);
+};
+
 int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_kvdl_fini(struct mlxsw_sp *mlxsw_sp);
-int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count,
-			u32 *p_entry_index);
-void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index);
-int mlxsw_sp_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp,
-				   unsigned int entry_count,
-				   unsigned int *p_alloc_size);
-int mlxsw_sp_kvdl_resources_register(struct mlxsw_core *mlxsw_core);
+int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp,
+			enum mlxsw_sp_kvdl_entry_type type,
+			unsigned int entry_count, u32 *p_entry_index);
+void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp,
+			enum mlxsw_sp_kvdl_entry_type type,
+			unsigned int entry_count, int entry_index);
+int mlxsw_sp_kvdl_alloc_count_query(struct mlxsw_sp *mlxsw_sp,
+				    enum mlxsw_sp_kvdl_entry_type type,
+				    unsigned int entry_count,
+				    unsigned int *p_alloc_count);
+
+/* spectrum1_kvdl.c */
+extern const struct mlxsw_sp_kvdl_ops mlxsw_sp1_kvdl_ops;
+int mlxsw_sp1_kvdl_resources_register(struct mlxsw_core *mlxsw_core);
+
+/* spectrum2_kvdl.c */
+extern const struct mlxsw_sp_kvdl_ops mlxsw_sp2_kvdl_ops;
 
 struct mlxsw_sp_acl_rule_info {
 	unsigned int priority;
@@ -452,44 +480,14 @@ struct mlxsw_sp_acl_rule_info {
 	unsigned int counter_index;
 };
 
-enum mlxsw_sp_acl_profile {
-	MLXSW_SP_ACL_PROFILE_FLOWER,
-};
-
-struct mlxsw_sp_acl_profile_ops {
-	size_t ruleset_priv_size;
-	int (*ruleset_add)(struct mlxsw_sp *mlxsw_sp,
-			   void *priv, void *ruleset_priv);
-	void (*ruleset_del)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv);
-	int (*ruleset_bind)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
-			    struct mlxsw_sp_port *mlxsw_sp_port,
-			    bool ingress);
-	void (*ruleset_unbind)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
-			       struct mlxsw_sp_port *mlxsw_sp_port,
-			       bool ingress);
-	u16 (*ruleset_group_id)(void *ruleset_priv);
-	size_t rule_priv_size;
-	int (*rule_add)(struct mlxsw_sp *mlxsw_sp,
-			void *ruleset_priv, void *rule_priv,
-			struct mlxsw_sp_acl_rule_info *rulei);
-	void (*rule_del)(struct mlxsw_sp *mlxsw_sp, void *rule_priv);
-	int (*rule_activity_get)(struct mlxsw_sp *mlxsw_sp, void *rule_priv,
-				 bool *activity);
-};
-
-struct mlxsw_sp_acl_ops {
-	size_t priv_size;
-	int (*init)(struct mlxsw_sp *mlxsw_sp, void *priv);
-	void (*fini)(struct mlxsw_sp *mlxsw_sp, void *priv);
-	const struct mlxsw_sp_acl_profile_ops *
-			(*profile_ops)(struct mlxsw_sp *mlxsw_sp,
-				       enum mlxsw_sp_acl_profile profile);
-};
-
 struct mlxsw_sp_acl_block;
 struct mlxsw_sp_acl_ruleset;
 
 /* spectrum_acl.c */
+enum mlxsw_sp_acl_profile {
+	MLXSW_SP_ACL_PROFILE_FLOWER,
+};
+
 struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl);
 struct mlxsw_sp *mlxsw_sp_acl_block_mlxsw_sp(struct mlxsw_sp_acl_block *block);
 unsigned int mlxsw_sp_acl_block_rule_count(struct mlxsw_sp_acl_block *block);
@@ -507,6 +505,7 @@ int mlxsw_sp_acl_block_unbind(struct mlxsw_sp *mlxsw_sp,
 			      struct mlxsw_sp_acl_block *block,
 			      struct mlxsw_sp_port *mlxsw_sp_port,
 			      bool ingress);
+bool mlxsw_sp_acl_block_is_egress_bound(struct mlxsw_sp_acl_block *block);
 struct mlxsw_sp_acl_ruleset *
 mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_block *block, u32 chain_index,
@@ -514,7 +513,8 @@ mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp *mlxsw_sp,
 struct mlxsw_sp_acl_ruleset *
 mlxsw_sp_acl_ruleset_get(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_acl_block *block, u32 chain_index,
-			 enum mlxsw_sp_acl_profile profile);
+			 enum mlxsw_sp_acl_profile profile,
+			 struct mlxsw_afk_element_usage *tmplt_elusage);
 void mlxsw_sp_acl_ruleset_put(struct mlxsw_sp *mlxsw_sp,
 			      struct mlxsw_sp_acl_ruleset *ruleset);
 u16 mlxsw_sp_acl_ruleset_group_id(struct mlxsw_sp_acl_ruleset *ruleset);
@@ -541,25 +541,30 @@ int mlxsw_sp_acl_rulei_act_trap(struct mlxsw_sp_acl_rule_info *rulei);
 int mlxsw_sp_acl_rulei_act_mirror(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_acl_rule_info *rulei,
 				  struct mlxsw_sp_acl_block *block,
-				  struct net_device *out_dev);
+				  struct net_device *out_dev,
+				  struct netlink_ext_ack *extack);
 int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_rule_info *rulei,
-			       struct net_device *out_dev);
+			       struct net_device *out_dev,
+			       struct netlink_ext_ack *extack);
 int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_acl_rule_info *rulei,
-				u32 action, u16 vid, u16 proto, u8 prio);
+				u32 action, u16 vid, u16 proto, u8 prio,
+				struct netlink_ext_ack *extack);
 int mlxsw_sp_acl_rulei_act_count(struct mlxsw_sp *mlxsw_sp,
-				 struct mlxsw_sp_acl_rule_info *rulei);
+				 struct mlxsw_sp_acl_rule_info *rulei,
+				 struct netlink_ext_ack *extack);
 int mlxsw_sp_acl_rulei_act_fid_set(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_acl_rule_info *rulei,
-				   u16 fid);
+				   u16 fid, struct netlink_ext_ack *extack);
 
 struct mlxsw_sp_acl_rule;
 
 struct mlxsw_sp_acl_rule *
 mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_acl_ruleset *ruleset,
-			 unsigned long cookie);
+			 unsigned long cookie,
+			 struct netlink_ext_ack *extack);
 void mlxsw_sp_acl_rule_destroy(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_rule *rule);
 int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp,
@@ -582,7 +587,52 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp);
 
 /* spectrum_acl_tcam.c */
-extern const struct mlxsw_sp_acl_ops mlxsw_sp_acl_tcam_ops;
+struct mlxsw_sp_acl_tcam;
+struct mlxsw_sp_acl_tcam_region;
+
+struct mlxsw_sp_acl_tcam_ops {
+	enum mlxsw_reg_ptar_key_type key_type;
+	size_t priv_size;
+	int (*init)(struct mlxsw_sp *mlxsw_sp, void *priv,
+		    struct mlxsw_sp_acl_tcam *tcam);
+	void (*fini)(struct mlxsw_sp *mlxsw_sp, void *priv);
+	size_t region_priv_size;
+	int (*region_init)(struct mlxsw_sp *mlxsw_sp, void *region_priv,
+			   void *tcam_priv,
+			   struct mlxsw_sp_acl_tcam_region *region);
+	void (*region_fini)(struct mlxsw_sp *mlxsw_sp, void *region_priv);
+	int (*region_associate)(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_tcam_region *region);
+	size_t chunk_priv_size;
+	void (*chunk_init)(void *region_priv, void *chunk_priv,
+			   unsigned int priority);
+	void (*chunk_fini)(void *chunk_priv);
+	size_t entry_priv_size;
+	int (*entry_add)(struct mlxsw_sp *mlxsw_sp,
+			 void *region_priv, void *chunk_priv,
+			 void *entry_priv,
+			 struct mlxsw_sp_acl_rule_info *rulei);
+	void (*entry_del)(struct mlxsw_sp *mlxsw_sp,
+			  void *region_priv, void *chunk_priv,
+			  void *entry_priv);
+	int (*entry_activity_get)(struct mlxsw_sp *mlxsw_sp,
+				  void *region_priv, void *entry_priv,
+				  bool *activity);
+};
+
+/* spectrum1_acl_tcam.c */
+extern const struct mlxsw_sp_acl_tcam_ops mlxsw_sp1_acl_tcam_ops;
+
+/* spectrum2_acl_tcam.c */
+extern const struct mlxsw_sp_acl_tcam_ops mlxsw_sp2_acl_tcam_ops;
+
+/* spectrum_acl_flex_actions.c */
+extern const struct mlxsw_afa_ops mlxsw_sp1_act_afa_ops;
+extern const struct mlxsw_afa_ops mlxsw_sp2_act_afa_ops;
+
+/* spectrum_acl_flex_keys.c */
+extern const struct mlxsw_afk_ops mlxsw_sp1_afk_ops;
+extern const struct mlxsw_afk_ops mlxsw_sp2_afk_ops;
 
 /* spectrum_flower.c */
 int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
@@ -594,6 +644,12 @@ void mlxsw_sp_flower_destroy(struct mlxsw_sp *mlxsw_sp,
 int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp,
 			  struct mlxsw_sp_acl_block *block,
 			  struct tc_cls_flower_offload *f);
+int mlxsw_sp_flower_tmplt_create(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_block *block,
+				 struct tc_cls_flower_offload *f);
+void mlxsw_sp_flower_tmplt_destroy(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_acl_block *block,
+				   struct tc_cls_flower_offload *f);
 
 /* spectrum_qdisc.c */
 int mlxsw_sp_tc_qdisc_init(struct mlxsw_sp_port *mlxsw_sp_port);
@@ -631,4 +687,40 @@ void mlxsw_sp_port_fids_fini(struct mlxsw_sp_port *mlxsw_sp_port);
 int mlxsw_sp_fids_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_fids_fini(struct mlxsw_sp *mlxsw_sp);
 
+/* spectrum_mr.c */
+enum mlxsw_sp_mr_route_prio {
+	MLXSW_SP_MR_ROUTE_PRIO_SG,
+	MLXSW_SP_MR_ROUTE_PRIO_STARG,
+	MLXSW_SP_MR_ROUTE_PRIO_CATCHALL,
+	__MLXSW_SP_MR_ROUTE_PRIO_MAX
+};
+
+#define MLXSW_SP_MR_ROUTE_PRIO_MAX (__MLXSW_SP_MR_ROUTE_PRIO_MAX - 1)
+
+struct mlxsw_sp_mr_route_key;
+
+struct mlxsw_sp_mr_tcam_ops {
+	size_t priv_size;
+	int (*init)(struct mlxsw_sp *mlxsw_sp, void *priv);
+	void (*fini)(void *priv);
+	size_t route_priv_size;
+	int (*route_create)(struct mlxsw_sp *mlxsw_sp, void *priv,
+			    void *route_priv,
+			    struct mlxsw_sp_mr_route_key *key,
+			    struct mlxsw_afa_block *afa_block,
+			    enum mlxsw_sp_mr_route_prio prio);
+	void (*route_destroy)(struct mlxsw_sp *mlxsw_sp, void *priv,
+			      void *route_priv,
+			      struct mlxsw_sp_mr_route_key *key);
+	int (*route_update)(struct mlxsw_sp *mlxsw_sp, void *route_priv,
+			    struct mlxsw_sp_mr_route_key *key,
+			    struct mlxsw_afa_block *afa_block);
+};
+
+/* spectrum1_mr_tcam.c */
+extern const struct mlxsw_sp_mr_tcam_ops mlxsw_sp1_mr_tcam_ops;
+
+/* spectrum2_mr_tcam.c */
+extern const struct mlxsw_sp_mr_tcam_ops mlxsw_sp2_mr_tcam_ops;
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
new file mode 100644
index 000000000000..2a9eac90002e
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+#include "reg.h"
+#include "core.h"
+#include "spectrum.h"
+#include "spectrum_acl_tcam.h"
+
+struct mlxsw_sp1_acl_tcam_region {
+	struct mlxsw_sp_acl_ctcam_region cregion;
+	struct mlxsw_sp_acl_tcam_region *region;
+	struct {
+		struct mlxsw_sp_acl_ctcam_chunk cchunk;
+		struct mlxsw_sp_acl_ctcam_entry centry;
+		struct mlxsw_sp_acl_rule_info *rulei;
+	} catchall;
+};
+
+struct mlxsw_sp1_acl_tcam_chunk {
+	struct mlxsw_sp_acl_ctcam_chunk cchunk;
+};
+
+struct mlxsw_sp1_acl_tcam_entry {
+	struct mlxsw_sp_acl_ctcam_entry centry;
+};
+
+static int
+mlxsw_sp1_acl_ctcam_region_entry_insert(struct mlxsw_sp_acl_ctcam_region *cregion,
+					struct mlxsw_sp_acl_ctcam_entry *centry,
+					const char *mask)
+{
+	return 0;
+}
+
+static void
+mlxsw_sp1_acl_ctcam_region_entry_remove(struct mlxsw_sp_acl_ctcam_region *cregion,
+					struct mlxsw_sp_acl_ctcam_entry *centry)
+{
+}
+
+static const struct mlxsw_sp_acl_ctcam_region_ops
+mlxsw_sp1_acl_ctcam_region_ops = {
+	.entry_insert = mlxsw_sp1_acl_ctcam_region_entry_insert,
+	.entry_remove = mlxsw_sp1_acl_ctcam_region_entry_remove,
+};
+
+static int mlxsw_sp1_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv,
+				   struct mlxsw_sp_acl_tcam *tcam)
+{
+	return 0;
+}
+
+static void mlxsw_sp1_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+}
+
+static int
+mlxsw_sp1_acl_ctcam_region_catchall_add(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp1_acl_tcam_region *region)
+{
+	struct mlxsw_sp_acl_rule_info *rulei;
+	int err;
+
+	mlxsw_sp_acl_ctcam_chunk_init(&region->cregion,
+				      &region->catchall.cchunk,
+				      MLXSW_SP_ACL_TCAM_CATCHALL_PRIO);
+	rulei = mlxsw_sp_acl_rulei_create(mlxsw_sp->acl);
+	if (IS_ERR(rulei)) {
+		err = PTR_ERR(rulei);
+		goto err_rulei_create;
+	}
+	err = mlxsw_sp_acl_rulei_act_continue(rulei);
+	if (WARN_ON(err))
+		goto err_rulei_act_continue;
+	err = mlxsw_sp_acl_rulei_commit(rulei);
+	if (err)
+		goto err_rulei_commit;
+	err = mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, &region->cregion,
+					   &region->catchall.cchunk,
+					   &region->catchall.centry,
+					   rulei, false);
+	if (err)
+		goto err_entry_add;
+	region->catchall.rulei = rulei;
+	return 0;
+
+err_entry_add:
+err_rulei_commit:
+err_rulei_act_continue:
+	mlxsw_sp_acl_rulei_destroy(rulei);
+err_rulei_create:
+	mlxsw_sp_acl_ctcam_chunk_fini(&region->catchall.cchunk);
+	return err;
+}
+
+static void
+mlxsw_sp1_acl_ctcam_region_catchall_del(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp1_acl_tcam_region *region)
+{
+	struct mlxsw_sp_acl_rule_info *rulei = region->catchall.rulei;
+
+	mlxsw_sp_acl_ctcam_entry_del(mlxsw_sp, &region->cregion,
+				     &region->catchall.cchunk,
+				     &region->catchall.centry);
+	mlxsw_sp_acl_rulei_destroy(rulei);
+	mlxsw_sp_acl_ctcam_chunk_fini(&region->catchall.cchunk);
+}
+
+static int
+mlxsw_sp1_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv,
+			       void *tcam_priv,
+			       struct mlxsw_sp_acl_tcam_region *_region)
+{
+	struct mlxsw_sp1_acl_tcam_region *region = region_priv;
+	int err;
+
+	err = mlxsw_sp_acl_ctcam_region_init(mlxsw_sp, &region->cregion,
+					     _region,
+					     &mlxsw_sp1_acl_ctcam_region_ops);
+	if (err)
+		return err;
+	err = mlxsw_sp1_acl_ctcam_region_catchall_add(mlxsw_sp, region);
+	if (err)
+		goto err_catchall_add;
+	region->region = _region;
+	return 0;
+
+err_catchall_add:
+	mlxsw_sp_acl_ctcam_region_fini(&region->cregion);
+	return err;
+}
+
+static void
+mlxsw_sp1_acl_tcam_region_fini(struct mlxsw_sp *mlxsw_sp, void *region_priv)
+{
+	struct mlxsw_sp1_acl_tcam_region *region = region_priv;
+
+	mlxsw_sp1_acl_ctcam_region_catchall_del(mlxsw_sp, region);
+	mlxsw_sp_acl_ctcam_region_fini(&region->cregion);
+}
+
+static int
+mlxsw_sp1_acl_tcam_region_associate(struct mlxsw_sp *mlxsw_sp,
+				    struct mlxsw_sp_acl_tcam_region *region)
+{
+	return 0;
+}
+
+static void mlxsw_sp1_acl_tcam_chunk_init(void *region_priv, void *chunk_priv,
+					  unsigned int priority)
+{
+	struct mlxsw_sp1_acl_tcam_region *region = region_priv;
+	struct mlxsw_sp1_acl_tcam_chunk *chunk = chunk_priv;
+
+	mlxsw_sp_acl_ctcam_chunk_init(&region->cregion, &chunk->cchunk,
+				      priority);
+}
+
+static void mlxsw_sp1_acl_tcam_chunk_fini(void *chunk_priv)
+{
+	struct mlxsw_sp1_acl_tcam_chunk *chunk = chunk_priv;
+
+	mlxsw_sp_acl_ctcam_chunk_fini(&chunk->cchunk);
+}
+
+static int mlxsw_sp1_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp,
+					void *region_priv, void *chunk_priv,
+					void *entry_priv,
+					struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp1_acl_tcam_region *region = region_priv;
+	struct mlxsw_sp1_acl_tcam_chunk *chunk = chunk_priv;
+	struct mlxsw_sp1_acl_tcam_entry *entry = entry_priv;
+
+	return mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, &region->cregion,
+					    &chunk->cchunk, &entry->centry,
+					    rulei, false);
+}
+
+static void mlxsw_sp1_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
+					 void *region_priv, void *chunk_priv,
+					 void *entry_priv)
+{
+	struct mlxsw_sp1_acl_tcam_region *region = region_priv;
+	struct mlxsw_sp1_acl_tcam_chunk *chunk = chunk_priv;
+	struct mlxsw_sp1_acl_tcam_entry *entry = entry_priv;
+
+	mlxsw_sp_acl_ctcam_entry_del(mlxsw_sp, &region->cregion,
+				     &chunk->cchunk, &entry->centry);
+}
+
+static int
+mlxsw_sp1_acl_tcam_region_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
+					     struct mlxsw_sp_acl_tcam_region *_region,
+					     unsigned int offset,
+					     bool *activity)
+{
+	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
+	int err;
+
+	mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_QUERY_CLEAR_ON_READ,
+			     _region->tcam_region_info, offset, 0);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
+	if (err)
+		return err;
+	*activity = mlxsw_reg_ptce2_a_get(ptce2_pl);
+	return 0;
+}
+
+static int
+mlxsw_sp1_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
+				      void *region_priv, void *entry_priv,
+				      bool *activity)
+{
+	struct mlxsw_sp1_acl_tcam_region *region = region_priv;
+	struct mlxsw_sp1_acl_tcam_entry *entry = entry_priv;
+	unsigned int offset;
+
+	offset = mlxsw_sp_acl_ctcam_entry_offset(&entry->centry);
+	return mlxsw_sp1_acl_tcam_region_entry_activity_get(mlxsw_sp,
+							    region->region,
+							    offset, activity);
+}
+
+const struct mlxsw_sp_acl_tcam_ops mlxsw_sp1_acl_tcam_ops = {
+	.key_type		= MLXSW_REG_PTAR_KEY_TYPE_FLEX,
+	.priv_size		= 0,
+	.init			= mlxsw_sp1_acl_tcam_init,
+	.fini			= mlxsw_sp1_acl_tcam_fini,
+	.region_priv_size	= sizeof(struct mlxsw_sp1_acl_tcam_region),
+	.region_init		= mlxsw_sp1_acl_tcam_region_init,
+	.region_fini		= mlxsw_sp1_acl_tcam_region_fini,
+	.region_associate	= mlxsw_sp1_acl_tcam_region_associate,
+	.chunk_priv_size	= sizeof(struct mlxsw_sp1_acl_tcam_chunk),
+	.chunk_init		= mlxsw_sp1_acl_tcam_chunk_init,
+	.chunk_fini		= mlxsw_sp1_acl_tcam_chunk_fini,
+	.entry_priv_size	= sizeof(struct mlxsw_sp1_acl_tcam_entry),
+	.entry_add		= mlxsw_sp1_acl_tcam_entry_add,
+	.entry_del		= mlxsw_sp1_acl_tcam_entry_del,
+	.entry_activity_get	= mlxsw_sp1_acl_tcam_entry_activity_get,
+};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c
new file mode 100644
index 000000000000..09ee0a807747
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c
@@ -0,0 +1,428 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
+
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+
+#include "spectrum.h"
+
+#define MLXSW_SP1_KVDL_SINGLE_BASE 0
+#define MLXSW_SP1_KVDL_SINGLE_SIZE 16384
+#define MLXSW_SP1_KVDL_SINGLE_END \
+	(MLXSW_SP1_KVDL_SINGLE_SIZE + MLXSW_SP1_KVDL_SINGLE_BASE - 1)
+
+#define MLXSW_SP1_KVDL_CHUNKS_BASE \
+	(MLXSW_SP1_KVDL_SINGLE_BASE + MLXSW_SP1_KVDL_SINGLE_SIZE)
+#define MLXSW_SP1_KVDL_CHUNKS_SIZE 49152
+#define MLXSW_SP1_KVDL_CHUNKS_END \
+	(MLXSW_SP1_KVDL_CHUNKS_SIZE + MLXSW_SP1_KVDL_CHUNKS_BASE - 1)
+
+#define MLXSW_SP1_KVDL_LARGE_CHUNKS_BASE \
+	(MLXSW_SP1_KVDL_CHUNKS_BASE + MLXSW_SP1_KVDL_CHUNKS_SIZE)
+#define MLXSW_SP1_KVDL_LARGE_CHUNKS_SIZE \
+	(MLXSW_SP_KVD_LINEAR_SIZE - MLXSW_SP1_KVDL_LARGE_CHUNKS_BASE)
+#define MLXSW_SP1_KVDL_LARGE_CHUNKS_END \
+	(MLXSW_SP1_KVDL_LARGE_CHUNKS_SIZE + MLXSW_SP1_KVDL_LARGE_CHUNKS_BASE - 1)
+
+#define MLXSW_SP1_KVDL_SINGLE_ALLOC_SIZE 1
+#define MLXSW_SP1_KVDL_CHUNKS_ALLOC_SIZE 32
+#define MLXSW_SP1_KVDL_LARGE_CHUNKS_ALLOC_SIZE 512
+
+struct mlxsw_sp1_kvdl_part_info {
+	unsigned int part_index;
+	unsigned int start_index;
+	unsigned int end_index;
+	unsigned int alloc_size;
+	enum mlxsw_sp_resource_id resource_id;
+};
+
+enum mlxsw_sp1_kvdl_part_id {
+	MLXSW_SP1_KVDL_PART_ID_SINGLE,
+	MLXSW_SP1_KVDL_PART_ID_CHUNKS,
+	MLXSW_SP1_KVDL_PART_ID_LARGE_CHUNKS,
+};
+
+#define MLXSW_SP1_KVDL_PART_INFO(id)				\
+[MLXSW_SP1_KVDL_PART_ID_##id] = {				\
+	.start_index = MLXSW_SP1_KVDL_##id##_BASE,		\
+	.end_index = MLXSW_SP1_KVDL_##id##_END,			\
+	.alloc_size = MLXSW_SP1_KVDL_##id##_ALLOC_SIZE,		\
+	.resource_id = MLXSW_SP_RESOURCE_KVD_LINEAR_##id,	\
+}
+
+static const struct mlxsw_sp1_kvdl_part_info mlxsw_sp1_kvdl_parts_info[] = {
+	MLXSW_SP1_KVDL_PART_INFO(SINGLE),
+	MLXSW_SP1_KVDL_PART_INFO(CHUNKS),
+	MLXSW_SP1_KVDL_PART_INFO(LARGE_CHUNKS),
+};
+
+#define MLXSW_SP1_KVDL_PARTS_INFO_LEN ARRAY_SIZE(mlxsw_sp1_kvdl_parts_info)
+
+struct mlxsw_sp1_kvdl_part {
+	struct mlxsw_sp1_kvdl_part_info info;
+	unsigned long usage[0];	/* Entries */
+};
+
+struct mlxsw_sp1_kvdl {
+	struct mlxsw_sp1_kvdl_part *parts[MLXSW_SP1_KVDL_PARTS_INFO_LEN];
+};
+
+static struct mlxsw_sp1_kvdl_part *
+mlxsw_sp1_kvdl_alloc_size_part(struct mlxsw_sp1_kvdl *kvdl,
+			       unsigned int alloc_size)
+{
+	struct mlxsw_sp1_kvdl_part *part, *min_part = NULL;
+	int i;
+
+	for (i = 0; i < MLXSW_SP1_KVDL_PARTS_INFO_LEN; i++) {
+		part = kvdl->parts[i];
+		if (alloc_size <= part->info.alloc_size &&
+		    (!min_part ||
+		     part->info.alloc_size <= min_part->info.alloc_size))
+			min_part = part;
+	}
+
+	return min_part ?: ERR_PTR(-ENOBUFS);
+}
+
+static struct mlxsw_sp1_kvdl_part *
+mlxsw_sp1_kvdl_index_part(struct mlxsw_sp1_kvdl *kvdl, u32 kvdl_index)
+{
+	struct mlxsw_sp1_kvdl_part *part;
+	int i;
+
+	for (i = 0; i < MLXSW_SP1_KVDL_PARTS_INFO_LEN; i++) {
+		part = kvdl->parts[i];
+		if (kvdl_index >= part->info.start_index &&
+		    kvdl_index <= part->info.end_index)
+			return part;
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static u32
+mlxsw_sp1_kvdl_to_kvdl_index(const struct mlxsw_sp1_kvdl_part_info *info,
+			     unsigned int entry_index)
+{
+	return info->start_index + entry_index * info->alloc_size;
+}
+
+static unsigned int
+mlxsw_sp1_kvdl_to_entry_index(const struct mlxsw_sp1_kvdl_part_info *info,
+			      u32 kvdl_index)
+{
+	return (kvdl_index - info->start_index) / info->alloc_size;
+}
+
+static int mlxsw_sp1_kvdl_part_alloc(struct mlxsw_sp1_kvdl_part *part,
+				     u32 *p_kvdl_index)
+{
+	const struct mlxsw_sp1_kvdl_part_info *info = &part->info;
+	unsigned int entry_index, nr_entries;
+
+	nr_entries = (info->end_index - info->start_index + 1) /
+		     info->alloc_size;
+	entry_index = find_first_zero_bit(part->usage, nr_entries);
+	if (entry_index == nr_entries)
+		return -ENOBUFS;
+	__set_bit(entry_index, part->usage);
+
+	*p_kvdl_index = mlxsw_sp1_kvdl_to_kvdl_index(info, entry_index);
+
+	return 0;
+}
+
+static void mlxsw_sp1_kvdl_part_free(struct mlxsw_sp1_kvdl_part *part,
+				     u32 kvdl_index)
+{
+	const struct mlxsw_sp1_kvdl_part_info *info = &part->info;
+	unsigned int entry_index;
+
+	entry_index = mlxsw_sp1_kvdl_to_entry_index(info, kvdl_index);
+	__clear_bit(entry_index, part->usage);
+}
+
+static int mlxsw_sp1_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, void *priv,
+				enum mlxsw_sp_kvdl_entry_type type,
+				unsigned int entry_count,
+				u32 *p_entry_index)
+{
+	struct mlxsw_sp1_kvdl *kvdl = priv;
+	struct mlxsw_sp1_kvdl_part *part;
+
+	/* Find partition with smallest allocation size satisfying the
+	 * requested size.
+	 */
+	part = mlxsw_sp1_kvdl_alloc_size_part(kvdl, entry_count);
+	if (IS_ERR(part))
+		return PTR_ERR(part);
+
+	return mlxsw_sp1_kvdl_part_alloc(part, p_entry_index);
+}
+
+static void mlxsw_sp1_kvdl_free(struct mlxsw_sp *mlxsw_sp, void *priv,
+				enum mlxsw_sp_kvdl_entry_type type,
+				unsigned int entry_count, int entry_index)
+{
+	struct mlxsw_sp1_kvdl *kvdl = priv;
+	struct mlxsw_sp1_kvdl_part *part;
+
+	part = mlxsw_sp1_kvdl_index_part(kvdl, entry_index);
+	if (IS_ERR(part))
+		return;
+	mlxsw_sp1_kvdl_part_free(part, entry_index);
+}
+
+static int mlxsw_sp1_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp,
+					   void *priv,
+					   enum mlxsw_sp_kvdl_entry_type type,
+					   unsigned int entry_count,
+					   unsigned int *p_alloc_size)
+{
+	struct mlxsw_sp1_kvdl *kvdl = priv;
+	struct mlxsw_sp1_kvdl_part *part;
+
+	part = mlxsw_sp1_kvdl_alloc_size_part(kvdl, entry_count);
+	if (IS_ERR(part))
+		return PTR_ERR(part);
+
+	*p_alloc_size = part->info.alloc_size;
+
+	return 0;
+}
+
+static void mlxsw_sp1_kvdl_part_update(struct mlxsw_sp1_kvdl_part *part,
+				       struct mlxsw_sp1_kvdl_part *part_prev,
+				       unsigned int size)
+{
+	if (!part_prev) {
+		part->info.end_index = size - 1;
+	} else {
+		part->info.start_index = part_prev->info.end_index + 1;
+		part->info.end_index = part->info.start_index + size - 1;
+	}
+}
+
+static struct mlxsw_sp1_kvdl_part *
+mlxsw_sp1_kvdl_part_init(struct mlxsw_sp *mlxsw_sp,
+			 const struct mlxsw_sp1_kvdl_part_info *info,
+			 struct mlxsw_sp1_kvdl_part *part_prev)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+	struct mlxsw_sp1_kvdl_part *part;
+	bool need_update = true;
+	unsigned int nr_entries;
+	size_t usage_size;
+	u64 resource_size;
+	int err;
+
+	err = devlink_resource_size_get(devlink, info->resource_id,
+					&resource_size);
+	if (err) {
+		need_update = false;
+		resource_size = info->end_index - info->start_index + 1;
+	}
+
+	nr_entries = div_u64(resource_size, info->alloc_size);
+	usage_size = BITS_TO_LONGS(nr_entries) * sizeof(unsigned long);
+	part = kzalloc(sizeof(*part) + usage_size, GFP_KERNEL);
+	if (!part)
+		return ERR_PTR(-ENOMEM);
+
+	memcpy(&part->info, info, sizeof(part->info));
+
+	if (need_update)
+		mlxsw_sp1_kvdl_part_update(part, part_prev, resource_size);
+	return part;
+}
+
+static void mlxsw_sp1_kvdl_part_fini(struct mlxsw_sp1_kvdl_part *part)
+{
+	kfree(part);
+}
+
+static int mlxsw_sp1_kvdl_parts_init(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp1_kvdl *kvdl)
+{
+	const struct mlxsw_sp1_kvdl_part_info *info;
+	struct mlxsw_sp1_kvdl_part *part_prev = NULL;
+	int err, i;
+
+	for (i = 0; i < MLXSW_SP1_KVDL_PARTS_INFO_LEN; i++) {
+		info = &mlxsw_sp1_kvdl_parts_info[i];
+		kvdl->parts[i] = mlxsw_sp1_kvdl_part_init(mlxsw_sp, info,
+							  part_prev);
+		if (IS_ERR(kvdl->parts[i])) {
+			err = PTR_ERR(kvdl->parts[i]);
+			goto err_kvdl_part_init;
+		}
+		part_prev = kvdl->parts[i];
+	}
+	return 0;
+
+err_kvdl_part_init:
+	for (i--; i >= 0; i--)
+		mlxsw_sp1_kvdl_part_fini(kvdl->parts[i]);
+	return err;
+}
+
+static void mlxsw_sp1_kvdl_parts_fini(struct mlxsw_sp1_kvdl *kvdl)
+{
+	int i;
+
+	for (i = 0; i < MLXSW_SP1_KVDL_PARTS_INFO_LEN; i++)
+		mlxsw_sp1_kvdl_part_fini(kvdl->parts[i]);
+}
+
+static u64 mlxsw_sp1_kvdl_part_occ(struct mlxsw_sp1_kvdl_part *part)
+{
+	const struct mlxsw_sp1_kvdl_part_info *info = &part->info;
+	unsigned int nr_entries;
+	int bit = -1;
+	u64 occ = 0;
+
+	nr_entries = (info->end_index -
+		      info->start_index + 1) /
+		      info->alloc_size;
+	while ((bit = find_next_bit(part->usage, nr_entries, bit + 1))
+		< nr_entries)
+		occ += info->alloc_size;
+	return occ;
+}
+
+static u64 mlxsw_sp1_kvdl_occ_get(void *priv)
+{
+	const struct mlxsw_sp1_kvdl *kvdl = priv;
+	u64 occ = 0;
+	int i;
+
+	for (i = 0; i < MLXSW_SP1_KVDL_PARTS_INFO_LEN; i++)
+		occ += mlxsw_sp1_kvdl_part_occ(kvdl->parts[i]);
+
+	return occ;
+}
+
+static u64 mlxsw_sp1_kvdl_single_occ_get(void *priv)
+{
+	const struct mlxsw_sp1_kvdl *kvdl = priv;
+	struct mlxsw_sp1_kvdl_part *part;
+
+	part = kvdl->parts[MLXSW_SP1_KVDL_PART_ID_SINGLE];
+	return mlxsw_sp1_kvdl_part_occ(part);
+}
+
+static u64 mlxsw_sp1_kvdl_chunks_occ_get(void *priv)
+{
+	const struct mlxsw_sp1_kvdl *kvdl = priv;
+	struct mlxsw_sp1_kvdl_part *part;
+
+	part = kvdl->parts[MLXSW_SP1_KVDL_PART_ID_CHUNKS];
+	return mlxsw_sp1_kvdl_part_occ(part);
+}
+
+static u64 mlxsw_sp1_kvdl_large_chunks_occ_get(void *priv)
+{
+	const struct mlxsw_sp1_kvdl *kvdl = priv;
+	struct mlxsw_sp1_kvdl_part *part;
+
+	part = kvdl->parts[MLXSW_SP1_KVDL_PART_ID_LARGE_CHUNKS];
+	return mlxsw_sp1_kvdl_part_occ(part);
+}
+
+static int mlxsw_sp1_kvdl_init(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+	struct mlxsw_sp1_kvdl *kvdl = priv;
+	int err;
+
+	err = mlxsw_sp1_kvdl_parts_init(mlxsw_sp, kvdl);
+	if (err)
+		return err;
+	devlink_resource_occ_get_register(devlink,
+					  MLXSW_SP_RESOURCE_KVD_LINEAR,
+					  mlxsw_sp1_kvdl_occ_get,
+					  kvdl);
+	devlink_resource_occ_get_register(devlink,
+					  MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE,
+					  mlxsw_sp1_kvdl_single_occ_get,
+					  kvdl);
+	devlink_resource_occ_get_register(devlink,
+					  MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS,
+					  mlxsw_sp1_kvdl_chunks_occ_get,
+					  kvdl);
+	devlink_resource_occ_get_register(devlink,
+					  MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS,
+					  mlxsw_sp1_kvdl_large_chunks_occ_get,
+					  kvdl);
+	return 0;
+}
+
+static void mlxsw_sp1_kvdl_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+	struct mlxsw_sp1_kvdl *kvdl = priv;
+
+	devlink_resource_occ_get_unregister(devlink,
+					    MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS);
+	devlink_resource_occ_get_unregister(devlink,
+					    MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS);
+	devlink_resource_occ_get_unregister(devlink,
+					    MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE);
+	devlink_resource_occ_get_unregister(devlink,
+					    MLXSW_SP_RESOURCE_KVD_LINEAR);
+	mlxsw_sp1_kvdl_parts_fini(kvdl);
+}
+
+const struct mlxsw_sp_kvdl_ops mlxsw_sp1_kvdl_ops = {
+	.priv_size = sizeof(struct mlxsw_sp1_kvdl),
+	.init = mlxsw_sp1_kvdl_init,
+	.fini = mlxsw_sp1_kvdl_fini,
+	.alloc = mlxsw_sp1_kvdl_alloc,
+	.free = mlxsw_sp1_kvdl_free,
+	.alloc_size_query = mlxsw_sp1_kvdl_alloc_size_query,
+};
+
+int mlxsw_sp1_kvdl_resources_register(struct mlxsw_core *mlxsw_core)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_core);
+	static struct devlink_resource_size_params size_params;
+	u32 kvdl_max_size;
+	int err;
+
+	kvdl_max_size = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SIZE) -
+			MLXSW_CORE_RES_GET(mlxsw_core, KVD_SINGLE_MIN_SIZE) -
+			MLXSW_CORE_RES_GET(mlxsw_core, KVD_DOUBLE_MIN_SIZE);
+
+	devlink_resource_size_params_init(&size_params, 0, kvdl_max_size,
+					  MLXSW_SP1_KVDL_SINGLE_ALLOC_SIZE,
+					  DEVLINK_RESOURCE_UNIT_ENTRY);
+	err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_SINGLES,
+					MLXSW_SP1_KVDL_SINGLE_SIZE,
+					MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE,
+					MLXSW_SP_RESOURCE_KVD_LINEAR,
+					&size_params);
+	if (err)
+		return err;
+
+	devlink_resource_size_params_init(&size_params, 0, kvdl_max_size,
+					  MLXSW_SP1_KVDL_CHUNKS_ALLOC_SIZE,
+					  DEVLINK_RESOURCE_UNIT_ENTRY);
+	err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_CHUNKS,
+					MLXSW_SP1_KVDL_CHUNKS_SIZE,
+					MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS,
+					MLXSW_SP_RESOURCE_KVD_LINEAR,
+					&size_params);
+	if (err)
+		return err;
+
+	devlink_resource_size_params_init(&size_params, 0, kvdl_max_size,
+					  MLXSW_SP1_KVDL_LARGE_CHUNKS_ALLOC_SIZE,
+					  DEVLINK_RESOURCE_UNIT_ENTRY);
+	err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_LARGE_CHUNKS,
+					MLXSW_SP1_KVDL_LARGE_CHUNKS_SIZE,
+					MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS,
+					MLXSW_SP_RESOURCE_KVD_LINEAR,
+					&size_params);
+	return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_mr_tcam.c
new file mode 100644
index 000000000000..c8c67536917b
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_mr_tcam.c
@@ -0,0 +1,342 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
+
+#include <linux/kernel.h>
+#include <linux/parman.h>
+
+#include "reg.h"
+#include "spectrum.h"
+#include "core_acl_flex_actions.h"
+#include "spectrum_mr.h"
+
+struct mlxsw_sp1_mr_tcam_region {
+	struct mlxsw_sp *mlxsw_sp;
+	enum mlxsw_reg_rtar_key_type rtar_key_type;
+	struct parman *parman;
+	struct parman_prio *parman_prios;
+};
+
+struct mlxsw_sp1_mr_tcam {
+	struct mlxsw_sp1_mr_tcam_region tcam_regions[MLXSW_SP_L3_PROTO_MAX];
+};
+
+struct mlxsw_sp1_mr_tcam_route {
+	struct parman_item parman_item;
+	struct parman_prio *parman_prio;
+};
+
+static int mlxsw_sp1_mr_tcam_route_replace(struct mlxsw_sp *mlxsw_sp,
+					   struct parman_item *parman_item,
+					   struct mlxsw_sp_mr_route_key *key,
+					   struct mlxsw_afa_block *afa_block)
+{
+	char rmft2_pl[MLXSW_REG_RMFT2_LEN];
+
+	switch (key->proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, true, parman_item->index,
+					  key->vrid,
+					  MLXSW_REG_RMFT2_IRIF_MASK_IGNORE, 0,
+					  ntohl(key->group.addr4),
+					  ntohl(key->group_mask.addr4),
+					  ntohl(key->source.addr4),
+					  ntohl(key->source_mask.addr4),
+					  mlxsw_afa_block_first_set(afa_block));
+		break;
+	case MLXSW_SP_L3_PROTO_IPV6:
+		mlxsw_reg_rmft2_ipv6_pack(rmft2_pl, true, parman_item->index,
+					  key->vrid,
+					  MLXSW_REG_RMFT2_IRIF_MASK_IGNORE, 0,
+					  key->group.addr6,
+					  key->group_mask.addr6,
+					  key->source.addr6,
+					  key->source_mask.addr6,
+					  mlxsw_afa_block_first_set(afa_block));
+	}
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl);
+}
+
+static int mlxsw_sp1_mr_tcam_route_remove(struct mlxsw_sp *mlxsw_sp,
+					  struct parman_item *parman_item,
+					  struct mlxsw_sp_mr_route_key *key)
+{
+	struct in6_addr zero_addr = IN6ADDR_ANY_INIT;
+	char rmft2_pl[MLXSW_REG_RMFT2_LEN];
+
+	switch (key->proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, false, parman_item->index,
+					  key->vrid, 0, 0, 0, 0, 0, 0, NULL);
+		break;
+	case MLXSW_SP_L3_PROTO_IPV6:
+		mlxsw_reg_rmft2_ipv6_pack(rmft2_pl, false, parman_item->index,
+					  key->vrid, 0, 0, zero_addr, zero_addr,
+					  zero_addr, zero_addr, NULL);
+		break;
+	}
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl);
+}
+
+static struct mlxsw_sp1_mr_tcam_region *
+mlxsw_sp1_mr_tcam_protocol_region(struct mlxsw_sp1_mr_tcam *mr_tcam,
+				  enum mlxsw_sp_l3proto proto)
+{
+	return &mr_tcam->tcam_regions[proto];
+}
+
+static int
+mlxsw_sp1_mr_tcam_route_parman_item_add(struct mlxsw_sp1_mr_tcam *mr_tcam,
+					struct mlxsw_sp1_mr_tcam_route *route,
+					struct mlxsw_sp_mr_route_key *key,
+					enum mlxsw_sp_mr_route_prio prio)
+{
+	struct mlxsw_sp1_mr_tcam_region *tcam_region;
+	int err;
+
+	tcam_region = mlxsw_sp1_mr_tcam_protocol_region(mr_tcam, key->proto);
+	err = parman_item_add(tcam_region->parman,
+			      &tcam_region->parman_prios[prio],
+			      &route->parman_item);
+	if (err)
+		return err;
+
+	route->parman_prio = &tcam_region->parman_prios[prio];
+	return 0;
+}
+
+static void
+mlxsw_sp1_mr_tcam_route_parman_item_remove(struct mlxsw_sp1_mr_tcam *mr_tcam,
+					   struct mlxsw_sp1_mr_tcam_route *route,
+					   struct mlxsw_sp_mr_route_key *key)
+{
+	struct mlxsw_sp1_mr_tcam_region *tcam_region;
+
+	tcam_region = mlxsw_sp1_mr_tcam_protocol_region(mr_tcam, key->proto);
+	parman_item_remove(tcam_region->parman,
+			   route->parman_prio, &route->parman_item);
+}
+
+static int
+mlxsw_sp1_mr_tcam_route_create(struct mlxsw_sp *mlxsw_sp, void *priv,
+			       void *route_priv,
+			       struct mlxsw_sp_mr_route_key *key,
+			       struct mlxsw_afa_block *afa_block,
+			       enum mlxsw_sp_mr_route_prio prio)
+{
+	struct mlxsw_sp1_mr_tcam_route *route = route_priv;
+	struct mlxsw_sp1_mr_tcam *mr_tcam = priv;
+	int err;
+
+	err = mlxsw_sp1_mr_tcam_route_parman_item_add(mr_tcam, route,
+						      key, prio);
+	if (err)
+		return err;
+
+	err = mlxsw_sp1_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
+					      key, afa_block);
+	if (err)
+		goto err_route_replace;
+	return 0;
+
+err_route_replace:
+	mlxsw_sp1_mr_tcam_route_parman_item_remove(mr_tcam, route, key);
+	return err;
+}
+
+static void
+mlxsw_sp1_mr_tcam_route_destroy(struct mlxsw_sp *mlxsw_sp, void *priv,
+				void *route_priv,
+				struct mlxsw_sp_mr_route_key *key)
+{
+	struct mlxsw_sp1_mr_tcam_route *route = route_priv;
+	struct mlxsw_sp1_mr_tcam *mr_tcam = priv;
+
+	mlxsw_sp1_mr_tcam_route_remove(mlxsw_sp, &route->parman_item, key);
+	mlxsw_sp1_mr_tcam_route_parman_item_remove(mr_tcam, route, key);
+}
+
+static int
+mlxsw_sp1_mr_tcam_route_update(struct mlxsw_sp *mlxsw_sp,
+			       void *route_priv,
+			       struct mlxsw_sp_mr_route_key *key,
+			       struct mlxsw_afa_block *afa_block)
+{
+	struct mlxsw_sp1_mr_tcam_route *route = route_priv;
+
+	return mlxsw_sp1_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
+					       key, afa_block);
+}
+
+#define MLXSW_SP1_MR_TCAM_REGION_BASE_COUNT 16
+#define MLXSW_SP1_MR_TCAM_REGION_RESIZE_STEP 16
+
+static int
+mlxsw_sp1_mr_tcam_region_alloc(struct mlxsw_sp1_mr_tcam_region *mr_tcam_region)
+{
+	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+	char rtar_pl[MLXSW_REG_RTAR_LEN];
+
+	mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_ALLOCATE,
+			    mr_tcam_region->rtar_key_type,
+			    MLXSW_SP1_MR_TCAM_REGION_BASE_COUNT);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
+}
+
+static void
+mlxsw_sp1_mr_tcam_region_free(struct mlxsw_sp1_mr_tcam_region *mr_tcam_region)
+{
+	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+	char rtar_pl[MLXSW_REG_RTAR_LEN];
+
+	mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_DEALLOCATE,
+			    mr_tcam_region->rtar_key_type, 0);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
+}
+
+static int mlxsw_sp1_mr_tcam_region_parman_resize(void *priv,
+						  unsigned long new_count)
+{
+	struct mlxsw_sp1_mr_tcam_region *mr_tcam_region = priv;
+	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+	char rtar_pl[MLXSW_REG_RTAR_LEN];
+	u64 max_tcam_rules;
+
+	max_tcam_rules = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_TCAM_RULES);
+	if (new_count > max_tcam_rules)
+		return -EINVAL;
+	mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_RESIZE,
+			    mr_tcam_region->rtar_key_type, new_count);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
+}
+
+static void mlxsw_sp1_mr_tcam_region_parman_move(void *priv,
+						 unsigned long from_index,
+						 unsigned long to_index,
+						 unsigned long count)
+{
+	struct mlxsw_sp1_mr_tcam_region *mr_tcam_region = priv;
+	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+	char rrcr_pl[MLXSW_REG_RRCR_LEN];
+
+	mlxsw_reg_rrcr_pack(rrcr_pl, MLXSW_REG_RRCR_OP_MOVE,
+			    from_index, count,
+			    mr_tcam_region->rtar_key_type, to_index);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rrcr), rrcr_pl);
+}
+
+static const struct parman_ops mlxsw_sp1_mr_tcam_region_parman_ops = {
+	.base_count	= MLXSW_SP1_MR_TCAM_REGION_BASE_COUNT,
+	.resize_step	= MLXSW_SP1_MR_TCAM_REGION_RESIZE_STEP,
+	.resize		= mlxsw_sp1_mr_tcam_region_parman_resize,
+	.move		= mlxsw_sp1_mr_tcam_region_parman_move,
+	.algo		= PARMAN_ALGO_TYPE_LSORT,
+};
+
+static int
+mlxsw_sp1_mr_tcam_region_init(struct mlxsw_sp *mlxsw_sp,
+			      struct mlxsw_sp1_mr_tcam_region *mr_tcam_region,
+			      enum mlxsw_reg_rtar_key_type rtar_key_type)
+{
+	struct parman_prio *parman_prios;
+	struct parman *parman;
+	int err;
+	int i;
+
+	mr_tcam_region->rtar_key_type = rtar_key_type;
+	mr_tcam_region->mlxsw_sp = mlxsw_sp;
+
+	err = mlxsw_sp1_mr_tcam_region_alloc(mr_tcam_region);
+	if (err)
+		return err;
+
+	parman = parman_create(&mlxsw_sp1_mr_tcam_region_parman_ops,
+			       mr_tcam_region);
+	if (!parman) {
+		err = -ENOMEM;
+		goto err_parman_create;
+	}
+	mr_tcam_region->parman = parman;
+
+	parman_prios = kmalloc_array(MLXSW_SP_MR_ROUTE_PRIO_MAX + 1,
+				     sizeof(*parman_prios), GFP_KERNEL);
+	if (!parman_prios) {
+		err = -ENOMEM;
+		goto err_parman_prios_alloc;
+	}
+	mr_tcam_region->parman_prios = parman_prios;
+
+	for (i = 0; i < MLXSW_SP_MR_ROUTE_PRIO_MAX + 1; i++)
+		parman_prio_init(mr_tcam_region->parman,
+				 &mr_tcam_region->parman_prios[i], i);
+	return 0;
+
+err_parman_prios_alloc:
+	parman_destroy(parman);
+err_parman_create:
+	mlxsw_sp1_mr_tcam_region_free(mr_tcam_region);
+	return err;
+}
+
+static void
+mlxsw_sp1_mr_tcam_region_fini(struct mlxsw_sp1_mr_tcam_region *mr_tcam_region)
+{
+	int i;
+
+	for (i = 0; i < MLXSW_SP_MR_ROUTE_PRIO_MAX + 1; i++)
+		parman_prio_fini(&mr_tcam_region->parman_prios[i]);
+	kfree(mr_tcam_region->parman_prios);
+	parman_destroy(mr_tcam_region->parman);
+	mlxsw_sp1_mr_tcam_region_free(mr_tcam_region);
+}
+
+static int mlxsw_sp1_mr_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+	struct mlxsw_sp1_mr_tcam *mr_tcam = priv;
+	struct mlxsw_sp1_mr_tcam_region *region = &mr_tcam->tcam_regions[0];
+	u32 rtar_key;
+	int err;
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_TCAM_RULES))
+		return -EIO;
+
+	rtar_key = MLXSW_REG_RTAR_KEY_TYPE_IPV4_MULTICAST;
+	err = mlxsw_sp1_mr_tcam_region_init(mlxsw_sp,
+					    &region[MLXSW_SP_L3_PROTO_IPV4],
+					    rtar_key);
+	if (err)
+		return err;
+
+	rtar_key = MLXSW_REG_RTAR_KEY_TYPE_IPV6_MULTICAST;
+	err = mlxsw_sp1_mr_tcam_region_init(mlxsw_sp,
+					    &region[MLXSW_SP_L3_PROTO_IPV6],
+					    rtar_key);
+	if (err)
+		goto err_ipv6_region_init;
+
+	return 0;
+
+err_ipv6_region_init:
+	mlxsw_sp1_mr_tcam_region_fini(&region[MLXSW_SP_L3_PROTO_IPV4]);
+	return err;
+}
+
+static void mlxsw_sp1_mr_tcam_fini(void *priv)
+{
+	struct mlxsw_sp1_mr_tcam *mr_tcam = priv;
+	struct mlxsw_sp1_mr_tcam_region *region = &mr_tcam->tcam_regions[0];
+
+	mlxsw_sp1_mr_tcam_region_fini(&region[MLXSW_SP_L3_PROTO_IPV6]);
+	mlxsw_sp1_mr_tcam_region_fini(&region[MLXSW_SP_L3_PROTO_IPV4]);
+}
+
+const struct mlxsw_sp_mr_tcam_ops mlxsw_sp1_mr_tcam_ops = {
+	.priv_size = sizeof(struct mlxsw_sp1_mr_tcam),
+	.init = mlxsw_sp1_mr_tcam_init,
+	.fini = mlxsw_sp1_mr_tcam_fini,
+	.route_priv_size = sizeof(struct mlxsw_sp1_mr_tcam_route),
+	.route_create = mlxsw_sp1_mr_tcam_route_create,
+	.route_destroy = mlxsw_sp1_mr_tcam_route_destroy,
+	.route_update = mlxsw_sp1_mr_tcam_route_update,
+};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
new file mode 100644
index 000000000000..8ca77f3e8f27
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
@@ -0,0 +1,239 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
+
+#include <linux/kernel.h>
+
+#include "spectrum.h"
+#include "spectrum_acl_tcam.h"
+#include "core_acl_flex_actions.h"
+
+struct mlxsw_sp2_acl_tcam {
+	struct mlxsw_sp_acl_atcam atcam;
+	u32 kvdl_index;
+	unsigned int kvdl_count;
+};
+
+struct mlxsw_sp2_acl_tcam_region {
+	struct mlxsw_sp_acl_atcam_region aregion;
+	struct mlxsw_sp_acl_tcam_region *region;
+};
+
+struct mlxsw_sp2_acl_tcam_chunk {
+	struct mlxsw_sp_acl_atcam_chunk achunk;
+};
+
+struct mlxsw_sp2_acl_tcam_entry {
+	struct mlxsw_sp_acl_atcam_entry aentry;
+	struct mlxsw_afa_block *act_block;
+};
+
+static int
+mlxsw_sp2_acl_ctcam_region_entry_insert(struct mlxsw_sp_acl_ctcam_region *cregion,
+					struct mlxsw_sp_acl_ctcam_entry *centry,
+					const char *mask)
+{
+	struct mlxsw_sp_acl_atcam_region *aregion;
+	struct mlxsw_sp_acl_atcam_entry *aentry;
+	struct mlxsw_sp_acl_erp *erp;
+
+	aregion = mlxsw_sp_acl_tcam_cregion_aregion(cregion);
+	aentry = mlxsw_sp_acl_tcam_centry_aentry(centry);
+
+	erp = mlxsw_sp_acl_erp_get(aregion, mask, true);
+	if (IS_ERR(erp))
+		return PTR_ERR(erp);
+	aentry->erp = erp;
+
+	return 0;
+}
+
+static void
+mlxsw_sp2_acl_ctcam_region_entry_remove(struct mlxsw_sp_acl_ctcam_region *cregion,
+					struct mlxsw_sp_acl_ctcam_entry *centry)
+{
+	struct mlxsw_sp_acl_atcam_region *aregion;
+	struct mlxsw_sp_acl_atcam_entry *aentry;
+
+	aregion = mlxsw_sp_acl_tcam_cregion_aregion(cregion);
+	aentry = mlxsw_sp_acl_tcam_centry_aentry(centry);
+
+	mlxsw_sp_acl_erp_put(aregion, aentry->erp);
+}
+
+static const struct mlxsw_sp_acl_ctcam_region_ops
+mlxsw_sp2_acl_ctcam_region_ops = {
+	.entry_insert = mlxsw_sp2_acl_ctcam_region_entry_insert,
+	.entry_remove = mlxsw_sp2_acl_ctcam_region_entry_remove,
+};
+
+static int mlxsw_sp2_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv,
+				   struct mlxsw_sp_acl_tcam *_tcam)
+{
+	struct mlxsw_sp2_acl_tcam *tcam = priv;
+	struct mlxsw_afa_block *afa_block;
+	char pefa_pl[MLXSW_REG_PEFA_LEN];
+	char pgcr_pl[MLXSW_REG_PGCR_LEN];
+	char *enc_actions;
+	int i;
+	int err;
+
+	tcam->kvdl_count = _tcam->max_regions;
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
+				  tcam->kvdl_count, &tcam->kvdl_index);
+	if (err)
+		return err;
+
+	/* Create flex action block, set default action (continue)
+	 * but don't commit. We need just the current set encoding
+	 * to be written using PEFA register to all indexes for all regions.
+	 */
+	afa_block = mlxsw_afa_block_create(mlxsw_sp->afa);
+	if (!afa_block) {
+		err = -ENOMEM;
+		goto err_afa_block;
+	}
+	err = mlxsw_afa_block_continue(afa_block);
+	if (WARN_ON(err))
+		goto err_afa_block_continue;
+	enc_actions = mlxsw_afa_block_cur_set(afa_block);
+
+	for (i = 0; i < tcam->kvdl_count; i++) {
+		mlxsw_reg_pefa_pack(pefa_pl, tcam->kvdl_index + i,
+				    true, enc_actions);
+		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pefa), pefa_pl);
+		if (err)
+			goto err_pefa_write;
+	}
+	mlxsw_reg_pgcr_pack(pgcr_pl, tcam->kvdl_index);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pgcr), pgcr_pl);
+	if (err)
+		goto err_pgcr_write;
+
+	err = mlxsw_sp_acl_atcam_init(mlxsw_sp, &tcam->atcam);
+	if (err)
+		goto err_atcam_init;
+
+	mlxsw_afa_block_destroy(afa_block);
+	return 0;
+
+err_atcam_init:
+err_pgcr_write:
+err_pefa_write:
+err_afa_block_continue:
+	mlxsw_afa_block_destroy(afa_block);
+err_afa_block:
+	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
+			   tcam->kvdl_count, tcam->kvdl_index);
+	return err;
+}
+
+static void mlxsw_sp2_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+	struct mlxsw_sp2_acl_tcam *tcam = priv;
+
+	mlxsw_sp_acl_atcam_fini(mlxsw_sp, &tcam->atcam);
+	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
+			   tcam->kvdl_count, tcam->kvdl_index);
+}
+
+static int
+mlxsw_sp2_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv,
+			       void *tcam_priv,
+			       struct mlxsw_sp_acl_tcam_region *_region)
+{
+	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
+	struct mlxsw_sp2_acl_tcam *tcam = tcam_priv;
+
+	region->region = _region;
+
+	return mlxsw_sp_acl_atcam_region_init(mlxsw_sp, &tcam->atcam,
+					      &region->aregion, _region,
+					      &mlxsw_sp2_acl_ctcam_region_ops);
+}
+
+static void
+mlxsw_sp2_acl_tcam_region_fini(struct mlxsw_sp *mlxsw_sp, void *region_priv)
+{
+	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
+
+	mlxsw_sp_acl_atcam_region_fini(&region->aregion);
+}
+
+static int
+mlxsw_sp2_acl_tcam_region_associate(struct mlxsw_sp *mlxsw_sp,
+				    struct mlxsw_sp_acl_tcam_region *region)
+{
+	return mlxsw_sp_acl_atcam_region_associate(mlxsw_sp, region->id);
+}
+
+static void mlxsw_sp2_acl_tcam_chunk_init(void *region_priv, void *chunk_priv,
+					  unsigned int priority)
+{
+	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
+	struct mlxsw_sp2_acl_tcam_chunk *chunk = chunk_priv;
+
+	mlxsw_sp_acl_atcam_chunk_init(&region->aregion, &chunk->achunk,
+				      priority);
+}
+
+static void mlxsw_sp2_acl_tcam_chunk_fini(void *chunk_priv)
+{
+	struct mlxsw_sp2_acl_tcam_chunk *chunk = chunk_priv;
+
+	mlxsw_sp_acl_atcam_chunk_fini(&chunk->achunk);
+}
+
+static int mlxsw_sp2_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp,
+					void *region_priv, void *chunk_priv,
+					void *entry_priv,
+					struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
+	struct mlxsw_sp2_acl_tcam_chunk *chunk = chunk_priv;
+	struct mlxsw_sp2_acl_tcam_entry *entry = entry_priv;
+
+	entry->act_block = rulei->act_block;
+	return mlxsw_sp_acl_atcam_entry_add(mlxsw_sp, &region->aregion,
+					    &chunk->achunk, &entry->aentry,
+					    rulei);
+}
+
+static void mlxsw_sp2_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
+					 void *region_priv, void *chunk_priv,
+					 void *entry_priv)
+{
+	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
+	struct mlxsw_sp2_acl_tcam_chunk *chunk = chunk_priv;
+	struct mlxsw_sp2_acl_tcam_entry *entry = entry_priv;
+
+	mlxsw_sp_acl_atcam_entry_del(mlxsw_sp, &region->aregion, &chunk->achunk,
+				     &entry->aentry);
+}
+
+static int
+mlxsw_sp2_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
+				      void *region_priv, void *entry_priv,
+				      bool *activity)
+{
+	struct mlxsw_sp2_acl_tcam_entry *entry = entry_priv;
+
+	return mlxsw_afa_block_activity_get(entry->act_block, activity);
+}
+
+const struct mlxsw_sp_acl_tcam_ops mlxsw_sp2_acl_tcam_ops = {
+	.key_type		= MLXSW_REG_PTAR_KEY_TYPE_FLEX2,
+	.priv_size		= sizeof(struct mlxsw_sp2_acl_tcam),
+	.init			= mlxsw_sp2_acl_tcam_init,
+	.fini			= mlxsw_sp2_acl_tcam_fini,
+	.region_priv_size	= sizeof(struct mlxsw_sp2_acl_tcam_region),
+	.region_init		= mlxsw_sp2_acl_tcam_region_init,
+	.region_fini		= mlxsw_sp2_acl_tcam_region_fini,
+	.region_associate	= mlxsw_sp2_acl_tcam_region_associate,
+	.chunk_priv_size	= sizeof(struct mlxsw_sp2_acl_tcam_chunk),
+	.chunk_init		= mlxsw_sp2_acl_tcam_chunk_init,
+	.chunk_fini		= mlxsw_sp2_acl_tcam_chunk_fini,
+	.entry_priv_size	= sizeof(struct mlxsw_sp2_acl_tcam_entry),
+	.entry_add		= mlxsw_sp2_acl_tcam_entry_add,
+	.entry_del		= mlxsw_sp2_acl_tcam_entry_del,
+	.entry_activity_get	= mlxsw_sp2_acl_tcam_entry_activity_get,
+};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c
new file mode 100644
index 000000000000..68c8b148bef2
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c
@@ -0,0 +1,271 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
+
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+
+#include "spectrum.h"
+#include "core.h"
+#include "reg.h"
+#include "resources.h"
+
+struct mlxsw_sp2_kvdl_part_info {
+	u8 res_type;
+	/* For each defined partititon we need to know how many
+	 * usage bits we need and how many indexes there are
+	 * represented by a single bit. This could be got from FW
+	 * querying appropriate resources. So have the resource
+	 * ids for for this purpose in partition definition.
+	 */
+	enum mlxsw_res_id usage_bit_count_res_id;
+	enum mlxsw_res_id index_range_res_id;
+};
+
+#define MLXSW_SP2_KVDL_PART_INFO(_entry_type, _res_type,			\
+				 _usage_bit_count_res_id, _index_range_res_id)	\
+[MLXSW_SP_KVDL_ENTRY_TYPE_##_entry_type] = {					\
+	.res_type = _res_type,							\
+	.usage_bit_count_res_id = MLXSW_RES_ID_##_usage_bit_count_res_id,	\
+	.index_range_res_id = MLXSW_RES_ID_##_index_range_res_id,		\
+}
+
+static const struct mlxsw_sp2_kvdl_part_info mlxsw_sp2_kvdl_parts_info[] = {
+	MLXSW_SP2_KVDL_PART_INFO(ADJ, 0x21, KVD_SIZE, MAX_KVD_LINEAR_RANGE),
+	MLXSW_SP2_KVDL_PART_INFO(ACTSET, 0x23, MAX_KVD_ACTION_SETS,
+				 MAX_KVD_ACTION_SETS),
+	MLXSW_SP2_KVDL_PART_INFO(PBS, 0x24, KVD_SIZE, KVD_SIZE),
+	MLXSW_SP2_KVDL_PART_INFO(MCRIGR, 0x26, KVD_SIZE, KVD_SIZE),
+};
+
+#define MLXSW_SP2_KVDL_PARTS_INFO_LEN ARRAY_SIZE(mlxsw_sp2_kvdl_parts_info)
+
+struct mlxsw_sp2_kvdl_part {
+	const struct mlxsw_sp2_kvdl_part_info *info;
+	unsigned int usage_bit_count;
+	unsigned int indexes_per_usage_bit;
+	unsigned int last_allocated_bit;
+	unsigned long usage[0];	/* Usage bits */
+};
+
+struct mlxsw_sp2_kvdl {
+	struct mlxsw_sp2_kvdl_part *parts[MLXSW_SP2_KVDL_PARTS_INFO_LEN];
+};
+
+static int mlxsw_sp2_kvdl_part_find_zero_bits(struct mlxsw_sp2_kvdl_part *part,
+					      unsigned int bit_count,
+					      unsigned int *p_bit)
+{
+	unsigned int start_bit;
+	unsigned int bit;
+	unsigned int i;
+	bool wrap = false;
+
+	start_bit = part->last_allocated_bit + 1;
+	if (start_bit == part->usage_bit_count)
+		start_bit = 0;
+	bit = start_bit;
+again:
+	bit = find_next_zero_bit(part->usage, part->usage_bit_count, bit);
+	if (!wrap && bit + bit_count >= part->usage_bit_count) {
+		wrap = true;
+		bit = 0;
+		goto again;
+	}
+	if (wrap && bit + bit_count >= start_bit)
+		return -ENOBUFS;
+	for (i = 0; i < bit_count; i++) {
+		if (test_bit(bit + i, part->usage)) {
+			bit += bit_count;
+			goto again;
+		}
+	}
+	*p_bit = bit;
+	return 0;
+}
+
+static int mlxsw_sp2_kvdl_part_alloc(struct mlxsw_sp2_kvdl_part *part,
+				     unsigned int size,
+				     u32 *p_kvdl_index)
+{
+	unsigned int bit_count;
+	unsigned int bit;
+	unsigned int i;
+	int err;
+
+	bit_count = DIV_ROUND_UP(size, part->indexes_per_usage_bit);
+	err = mlxsw_sp2_kvdl_part_find_zero_bits(part, bit_count, &bit);
+	if (err)
+		return err;
+	for (i = 0; i < bit_count; i++)
+		__set_bit(bit + i, part->usage);
+	*p_kvdl_index = bit * part->indexes_per_usage_bit;
+	return 0;
+}
+
+static int mlxsw_sp2_kvdl_rec_del(struct mlxsw_sp *mlxsw_sp, u8 res_type,
+				  u16 size, u32 kvdl_index)
+{
+	char *iedr_pl;
+	int err;
+
+	iedr_pl = kmalloc(MLXSW_REG_IEDR_LEN, GFP_KERNEL);
+	if (!iedr_pl)
+		return -ENOMEM;
+
+	mlxsw_reg_iedr_pack(iedr_pl);
+	mlxsw_reg_iedr_rec_pack(iedr_pl, 0, res_type, size, kvdl_index);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(iedr), iedr_pl);
+	kfree(iedr_pl);
+	return err;
+}
+
+static void mlxsw_sp2_kvdl_part_free(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp2_kvdl_part *part,
+				     unsigned int size, u32 kvdl_index)
+{
+	unsigned int bit_count;
+	unsigned int bit;
+	unsigned int i;
+	int err;
+
+	/* We need to ask FW to delete previously used KVD linear index */
+	err = mlxsw_sp2_kvdl_rec_del(mlxsw_sp, part->info->res_type,
+				     size, kvdl_index);
+	if (err)
+		return;
+
+	bit_count = DIV_ROUND_UP(size, part->indexes_per_usage_bit);
+	bit = kvdl_index / part->indexes_per_usage_bit;
+	for (i = 0; i < bit_count; i++)
+		__clear_bit(bit + i, part->usage);
+}
+
+static int mlxsw_sp2_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, void *priv,
+				enum mlxsw_sp_kvdl_entry_type type,
+				unsigned int entry_count,
+				u32 *p_entry_index)
+{
+	unsigned int size = entry_count * mlxsw_sp_kvdl_entry_size(type);
+	struct mlxsw_sp2_kvdl *kvdl = priv;
+	struct mlxsw_sp2_kvdl_part *part = kvdl->parts[type];
+
+	return mlxsw_sp2_kvdl_part_alloc(part, size, p_entry_index);
+}
+
+static void mlxsw_sp2_kvdl_free(struct mlxsw_sp *mlxsw_sp, void *priv,
+				enum mlxsw_sp_kvdl_entry_type type,
+				unsigned int entry_count,
+				int entry_index)
+{
+	unsigned int size = entry_count * mlxsw_sp_kvdl_entry_size(type);
+	struct mlxsw_sp2_kvdl *kvdl = priv;
+	struct mlxsw_sp2_kvdl_part *part = kvdl->parts[type];
+
+	return mlxsw_sp2_kvdl_part_free(mlxsw_sp, part, size, entry_index);
+}
+
+static int mlxsw_sp2_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp,
+					   void *priv,
+					   enum mlxsw_sp_kvdl_entry_type type,
+					   unsigned int entry_count,
+					   unsigned int *p_alloc_count)
+{
+	*p_alloc_count = entry_count;
+	return 0;
+}
+
+static struct mlxsw_sp2_kvdl_part *
+mlxsw_sp2_kvdl_part_init(struct mlxsw_sp *mlxsw_sp,
+			 const struct mlxsw_sp2_kvdl_part_info *info)
+{
+	unsigned int indexes_per_usage_bit;
+	struct mlxsw_sp2_kvdl_part *part;
+	unsigned int index_range;
+	unsigned int usage_bit_count;
+	size_t usage_size;
+
+	if (!mlxsw_core_res_valid(mlxsw_sp->core,
+				  info->usage_bit_count_res_id) ||
+	    !mlxsw_core_res_valid(mlxsw_sp->core,
+				  info->index_range_res_id))
+		return ERR_PTR(-EIO);
+	usage_bit_count = mlxsw_core_res_get(mlxsw_sp->core,
+					     info->usage_bit_count_res_id);
+	index_range = mlxsw_core_res_get(mlxsw_sp->core,
+					 info->index_range_res_id);
+
+	/* For some partitions, one usage bit represents a group of indexes.
+	 * That's why we compute the number of indexes per usage bit here,
+	 * according to queried resources.
+	 */
+	indexes_per_usage_bit = index_range / usage_bit_count;
+
+	usage_size = BITS_TO_LONGS(usage_bit_count) * sizeof(unsigned long);
+	part = kzalloc(sizeof(*part) + usage_size, GFP_KERNEL);
+	if (!part)
+		return ERR_PTR(-ENOMEM);
+	part->info = info;
+	part->usage_bit_count = usage_bit_count;
+	part->indexes_per_usage_bit = indexes_per_usage_bit;
+	part->last_allocated_bit = usage_bit_count - 1;
+	return part;
+}
+
+static void mlxsw_sp2_kvdl_part_fini(struct mlxsw_sp2_kvdl_part *part)
+{
+	kfree(part);
+}
+
+static int mlxsw_sp2_kvdl_parts_init(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp2_kvdl *kvdl)
+{
+	const struct mlxsw_sp2_kvdl_part_info *info;
+	int i;
+	int err;
+
+	for (i = 0; i < MLXSW_SP2_KVDL_PARTS_INFO_LEN; i++) {
+		info = &mlxsw_sp2_kvdl_parts_info[i];
+		kvdl->parts[i] = mlxsw_sp2_kvdl_part_init(mlxsw_sp, info);
+		if (IS_ERR(kvdl->parts[i])) {
+			err = PTR_ERR(kvdl->parts[i]);
+			goto err_kvdl_part_init;
+		}
+	}
+	return 0;
+
+err_kvdl_part_init:
+	for (i--; i >= 0; i--)
+		mlxsw_sp2_kvdl_part_fini(kvdl->parts[i]);
+	return err;
+}
+
+static void mlxsw_sp2_kvdl_parts_fini(struct mlxsw_sp2_kvdl *kvdl)
+{
+	int i;
+
+	for (i = 0; i < MLXSW_SP2_KVDL_PARTS_INFO_LEN; i++)
+		mlxsw_sp2_kvdl_part_fini(kvdl->parts[i]);
+}
+
+static int mlxsw_sp2_kvdl_init(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+	struct mlxsw_sp2_kvdl *kvdl = priv;
+
+	return mlxsw_sp2_kvdl_parts_init(mlxsw_sp, kvdl);
+}
+
+static void mlxsw_sp2_kvdl_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+	struct mlxsw_sp2_kvdl *kvdl = priv;
+
+	mlxsw_sp2_kvdl_parts_fini(kvdl);
+}
+
+const struct mlxsw_sp_kvdl_ops mlxsw_sp2_kvdl_ops = {
+	.priv_size = sizeof(struct mlxsw_sp2_kvdl),
+	.init = mlxsw_sp2_kvdl_init,
+	.fini = mlxsw_sp2_kvdl_fini,
+	.alloc = mlxsw_sp2_kvdl_alloc,
+	.free = mlxsw_sp2_kvdl_free,
+	.alloc_size_query = mlxsw_sp2_kvdl_alloc_size_query,
+};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c
new file mode 100644
index 000000000000..4dd62478162e
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
+
+#include <linux/kernel.h>
+
+#include "core_acl_flex_actions.h"
+#include "spectrum.h"
+#include "spectrum_mr.h"
+
+static int
+mlxsw_sp2_mr_tcam_route_create(struct mlxsw_sp *mlxsw_sp, void *priv,
+			       void *route_priv,
+			       struct mlxsw_sp_mr_route_key *key,
+			       struct mlxsw_afa_block *afa_block,
+			       enum mlxsw_sp_mr_route_prio prio)
+{
+	return 0;
+}
+
+static void
+mlxsw_sp2_mr_tcam_route_destroy(struct mlxsw_sp *mlxsw_sp, void *priv,
+				void *route_priv,
+				struct mlxsw_sp_mr_route_key *key)
+{
+}
+
+static int
+mlxsw_sp2_mr_tcam_route_update(struct mlxsw_sp *mlxsw_sp,
+			       void *route_priv,
+			       struct mlxsw_sp_mr_route_key *key,
+			       struct mlxsw_afa_block *afa_block)
+{
+	return 0;
+}
+
+static int mlxsw_sp2_mr_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+	return 0;
+}
+
+static void mlxsw_sp2_mr_tcam_fini(void *priv)
+{
+}
+
+const struct mlxsw_sp_mr_tcam_ops mlxsw_sp2_mr_tcam_ops = {
+	.init = mlxsw_sp2_mr_tcam_init,
+	.fini = mlxsw_sp2_mr_tcam_fini,
+	.route_create = mlxsw_sp2_mr_tcam_route_create,
+	.route_destroy = mlxsw_sp2_mr_tcam_route_destroy,
+	.route_update = mlxsw_sp2_mr_tcam_route_update,
+};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 79b1fa27a9a4..c4f9238591e6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -48,13 +17,12 @@
 #include "spectrum.h"
 #include "core_acl_flex_keys.h"
 #include "core_acl_flex_actions.h"
-#include "spectrum_acl_flex_keys.h"
+#include "spectrum_acl_tcam.h"
 
 struct mlxsw_sp_acl {
 	struct mlxsw_sp *mlxsw_sp;
 	struct mlxsw_afk *afk;
 	struct mlxsw_sp_fid *dummy_fid;
-	const struct mlxsw_sp_acl_ops *ops;
 	struct rhashtable ruleset_ht;
 	struct list_head rules;
 	struct {
@@ -62,8 +30,7 @@ struct mlxsw_sp_acl {
 		unsigned long interval;	/* ms */
 #define MLXSW_SP_ACL_RULE_ACTIVITY_UPDATE_PERIOD_MS 1000
 	} rule_activity_update;
-	unsigned long priv[0];
-	/* priv has to be always the last item */
+	struct mlxsw_sp_acl_tcam tcam;
 };
 
 struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl)
@@ -160,6 +127,17 @@ bool mlxsw_sp_acl_block_disabled(struct mlxsw_sp_acl_block *block)
 	return block->disable_count;
 }
 
+bool mlxsw_sp_acl_block_is_egress_bound(struct mlxsw_sp_acl_block *block)
+{
+	struct mlxsw_sp_acl_block_binding *binding;
+
+	list_for_each_entry(binding, &block->binding_list, list) {
+		if (!binding->ingress)
+			return true;
+	}
+	return false;
+}
+
 static bool
 mlxsw_sp_acl_ruleset_is_singular(const struct mlxsw_sp_acl_ruleset *ruleset)
 {
@@ -319,7 +297,8 @@ int mlxsw_sp_acl_block_unbind(struct mlxsw_sp *mlxsw_sp,
 static struct mlxsw_sp_acl_ruleset *
 mlxsw_sp_acl_ruleset_create(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_block *block, u32 chain_index,
-			    const struct mlxsw_sp_acl_profile_ops *ops)
+			    const struct mlxsw_sp_acl_profile_ops *ops,
+			    struct mlxsw_afk_element_usage *tmplt_elusage)
 {
 	struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
 	struct mlxsw_sp_acl_ruleset *ruleset;
@@ -339,7 +318,8 @@ mlxsw_sp_acl_ruleset_create(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_rhashtable_init;
 
-	err = ops->ruleset_add(mlxsw_sp, acl->priv, ruleset->priv);
+	err = ops->ruleset_add(mlxsw_sp, &acl->tcam, ruleset->priv,
+			       tmplt_elusage);
 	if (err)
 		goto err_ops_ruleset_add;
 
@@ -409,7 +389,7 @@ mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
 	struct mlxsw_sp_acl_ruleset *ruleset;
 
-	ops = acl->ops->profile_ops(mlxsw_sp, profile);
+	ops = mlxsw_sp_acl_tcam_profile_ops(mlxsw_sp, profile);
 	if (!ops)
 		return ERR_PTR(-EINVAL);
 	ruleset = __mlxsw_sp_acl_ruleset_lookup(acl, block, chain_index, ops);
@@ -421,13 +401,14 @@ mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp *mlxsw_sp,
 struct mlxsw_sp_acl_ruleset *
 mlxsw_sp_acl_ruleset_get(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_acl_block *block, u32 chain_index,
-			 enum mlxsw_sp_acl_profile profile)
+			 enum mlxsw_sp_acl_profile profile,
+			 struct mlxsw_afk_element_usage *tmplt_elusage)
 {
 	const struct mlxsw_sp_acl_profile_ops *ops;
 	struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
 	struct mlxsw_sp_acl_ruleset *ruleset;
 
-	ops = acl->ops->profile_ops(mlxsw_sp, profile);
+	ops = mlxsw_sp_acl_tcam_profile_ops(mlxsw_sp, profile);
 	if (!ops)
 		return ERR_PTR(-EINVAL);
 
@@ -436,7 +417,8 @@ mlxsw_sp_acl_ruleset_get(struct mlxsw_sp *mlxsw_sp,
 		mlxsw_sp_acl_ruleset_ref_inc(ruleset);
 		return ruleset;
 	}
-	return mlxsw_sp_acl_ruleset_create(mlxsw_sp, block, chain_index, ops);
+	return mlxsw_sp_acl_ruleset_create(mlxsw_sp, block, chain_index, ops,
+					   tmplt_elusage);
 }
 
 void mlxsw_sp_acl_ruleset_put(struct mlxsw_sp *mlxsw_sp,
@@ -487,7 +469,7 @@ int mlxsw_sp_acl_rulei_commit(struct mlxsw_sp_acl_rule_info *rulei)
 void mlxsw_sp_acl_rulei_priority(struct mlxsw_sp_acl_rule_info *rulei,
 				 unsigned int priority)
 {
-	rulei->priority = priority;
+	rulei->priority = priority >> 16;
 }
 
 void mlxsw_sp_acl_rulei_keymask_u32(struct mlxsw_sp_acl_rule_info *rulei,
@@ -536,18 +518,23 @@ int mlxsw_sp_acl_rulei_act_trap(struct mlxsw_sp_acl_rule_info *rulei)
 
 int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_rule_info *rulei,
-			       struct net_device *out_dev)
+			       struct net_device *out_dev,
+			       struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	u8 local_port;
 	bool in_port;
 
 	if (out_dev) {
-		if (!mlxsw_sp_port_dev_check(out_dev))
+		if (!mlxsw_sp_port_dev_check(out_dev)) {
+			NL_SET_ERR_MSG_MOD(extack, "Invalid output device");
 			return -EINVAL;
+		}
 		mlxsw_sp_port = netdev_priv(out_dev);
-		if (mlxsw_sp_port->mlxsw_sp != mlxsw_sp)
+		if (mlxsw_sp_port->mlxsw_sp != mlxsw_sp) {
+			NL_SET_ERR_MSG_MOD(extack, "Invalid output device");
 			return -EINVAL;
+		}
 		local_port = mlxsw_sp_port->local_port;
 		in_port = false;
 	} else {
@@ -558,20 +545,22 @@ int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp,
 		in_port = true;
 	}
 	return mlxsw_afa_block_append_fwd(rulei->act_block,
-					  local_port, in_port);
+					  local_port, in_port, extack);
 }
 
 int mlxsw_sp_acl_rulei_act_mirror(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_acl_rule_info *rulei,
 				  struct mlxsw_sp_acl_block *block,
-				  struct net_device *out_dev)
+				  struct net_device *out_dev,
+				  struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_acl_block_binding *binding;
 	struct mlxsw_sp_port *in_port;
 
-	if (!list_is_singular(&block->binding_list))
+	if (!list_is_singular(&block->binding_list)) {
+		NL_SET_ERR_MSG_MOD(extack, "Only a single mirror source is allowed");
 		return -EOPNOTSUPP;
-
+	}
 	binding = list_first_entry(&block->binding_list,
 				   struct mlxsw_sp_acl_block_binding, list);
 	in_port = binding->mlxsw_sp_port;
@@ -579,12 +568,14 @@ int mlxsw_sp_acl_rulei_act_mirror(struct mlxsw_sp *mlxsw_sp,
 	return mlxsw_afa_block_append_mirror(rulei->act_block,
 					     in_port->local_port,
 					     out_dev,
-					     binding->ingress);
+					     binding->ingress,
+					     extack);
 }
 
 int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_acl_rule_info *rulei,
-				u32 action, u16 vid, u16 proto, u8 prio)
+				u32 action, u16 vid, u16 proto, u8 prio,
+				struct netlink_ext_ack *extack)
 {
 	u8 ethertype;
 
@@ -597,44 +588,50 @@ int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp,
 			ethertype = 1;
 			break;
 		default:
+			NL_SET_ERR_MSG_MOD(extack, "Unsupported VLAN protocol");
 			dev_err(mlxsw_sp->bus_info->dev, "Unsupported VLAN protocol %#04x\n",
 				proto);
 			return -EINVAL;
 		}
 
 		return mlxsw_afa_block_append_vlan_modify(rulei->act_block,
-							  vid, prio, ethertype);
+							  vid, prio, ethertype,
+							  extack);
 	} else {
+		NL_SET_ERR_MSG_MOD(extack, "Unsupported VLAN action");
 		dev_err(mlxsw_sp->bus_info->dev, "Unsupported VLAN action\n");
 		return -EINVAL;
 	}
 }
 
 int mlxsw_sp_acl_rulei_act_count(struct mlxsw_sp *mlxsw_sp,
-				 struct mlxsw_sp_acl_rule_info *rulei)
+				 struct mlxsw_sp_acl_rule_info *rulei,
+				 struct netlink_ext_ack *extack)
 {
 	return mlxsw_afa_block_append_counter(rulei->act_block,
-					      &rulei->counter_index);
+					      &rulei->counter_index, extack);
 }
 
 int mlxsw_sp_acl_rulei_act_fid_set(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_acl_rule_info *rulei,
-				   u16 fid)
+				   u16 fid, struct netlink_ext_ack *extack)
 {
-	return mlxsw_afa_block_append_fid_set(rulei->act_block, fid);
+	return mlxsw_afa_block_append_fid_set(rulei->act_block, fid, extack);
 }
 
 struct mlxsw_sp_acl_rule *
 mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_acl_ruleset *ruleset,
-			 unsigned long cookie)
+			 unsigned long cookie,
+			 struct netlink_ext_ack *extack)
 {
 	const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops;
 	struct mlxsw_sp_acl_rule *rule;
 	int err;
 
 	mlxsw_sp_acl_ruleset_ref_inc(ruleset);
-	rule = kzalloc(sizeof(*rule) + ops->rule_priv_size, GFP_KERNEL);
+	rule = kzalloc(sizeof(*rule) + ops->rule_priv_size(mlxsw_sp),
+		       GFP_KERNEL);
 	if (!rule) {
 		err = -ENOMEM;
 		goto err_alloc;
@@ -825,20 +822,20 @@ int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp,
 
 int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 {
-	const struct mlxsw_sp_acl_ops *acl_ops = &mlxsw_sp_acl_tcam_ops;
 	struct mlxsw_sp_fid *fid;
 	struct mlxsw_sp_acl *acl;
+	size_t alloc_size;
 	int err;
 
-	acl = kzalloc(sizeof(*acl) + acl_ops->priv_size, GFP_KERNEL);
+	alloc_size = sizeof(*acl) + mlxsw_sp_acl_tcam_priv_size(mlxsw_sp);
+	acl = kzalloc(alloc_size, GFP_KERNEL);
 	if (!acl)
 		return -ENOMEM;
 	mlxsw_sp->acl = acl;
 	acl->mlxsw_sp = mlxsw_sp;
 	acl->afk = mlxsw_afk_create(MLXSW_CORE_RES_GET(mlxsw_sp->core,
 						       ACL_FLEX_KEYS),
-				    mlxsw_sp_afk_blocks,
-				    MLXSW_SP_AFK_BLOCKS_COUNT);
+				    mlxsw_sp->afk_ops);
 	if (!acl->afk) {
 		err = -ENOMEM;
 		goto err_afk_create;
@@ -857,12 +854,10 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 	acl->dummy_fid = fid;
 
 	INIT_LIST_HEAD(&acl->rules);
-	err = acl_ops->init(mlxsw_sp, acl->priv);
+	err = mlxsw_sp_acl_tcam_init(mlxsw_sp, &acl->tcam);
 	if (err)
 		goto err_acl_ops_init;
 
-	acl->ops = acl_ops;
-
 	/* Create the delayed work for the rule activity_update */
 	INIT_DELAYED_WORK(&acl->rule_activity_update.dw,
 			  mlxsw_sp_acl_rul_activity_update_work);
@@ -884,10 +879,9 @@ err_afk_create:
 void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp)
 {
 	struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
-	const struct mlxsw_sp_acl_ops *acl_ops = acl->ops;
 
 	cancel_delayed_work_sync(&mlxsw_sp->acl->rule_activity_update.dw);
-	acl_ops->fini(mlxsw_sp, acl->priv);
+	mlxsw_sp_acl_tcam_fini(mlxsw_sp, &acl->tcam);
 	WARN_ON(!list_empty(&acl->rules));
 	mlxsw_sp_fid_put(acl->dummy_fid);
 	rhashtable_destroy(&acl->ruleset_ht);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
new file mode 100644
index 000000000000..2dda028f94db
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -0,0 +1,536 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/gfp.h>
+#include <linux/refcount.h>
+#include <linux/rhashtable.h>
+
+#include "reg.h"
+#include "core.h"
+#include "spectrum.h"
+#include "spectrum_acl_tcam.h"
+#include "core_acl_flex_keys.h"
+
+#define MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_START	6
+#define MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_END	11
+
+struct mlxsw_sp_acl_atcam_lkey_id_ht_key {
+	char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* MSB blocks */
+	u8 erp_id;
+};
+
+struct mlxsw_sp_acl_atcam_lkey_id {
+	struct rhash_head ht_node;
+	struct mlxsw_sp_acl_atcam_lkey_id_ht_key ht_key;
+	refcount_t refcnt;
+	u32 id;
+};
+
+struct mlxsw_sp_acl_atcam_region_ops {
+	int (*init)(struct mlxsw_sp_acl_atcam_region *aregion);
+	void (*fini)(struct mlxsw_sp_acl_atcam_region *aregion);
+	struct mlxsw_sp_acl_atcam_lkey_id *
+		(*lkey_id_get)(struct mlxsw_sp_acl_atcam_region *aregion,
+			       struct mlxsw_sp_acl_rule_info *rulei, u8 erp_id);
+	void (*lkey_id_put)(struct mlxsw_sp_acl_atcam_region *aregion,
+			    struct mlxsw_sp_acl_atcam_lkey_id *lkey_id);
+};
+
+struct mlxsw_sp_acl_atcam_region_generic {
+	struct mlxsw_sp_acl_atcam_lkey_id dummy_lkey_id;
+};
+
+struct mlxsw_sp_acl_atcam_region_12kb {
+	struct rhashtable lkey_ht;
+	unsigned int max_lkey_id;
+	unsigned long *used_lkey_id;
+};
+
+static const struct rhashtable_params mlxsw_sp_acl_atcam_lkey_id_ht_params = {
+	.key_len = sizeof(struct mlxsw_sp_acl_atcam_lkey_id_ht_key),
+	.key_offset = offsetof(struct mlxsw_sp_acl_atcam_lkey_id, ht_key),
+	.head_offset = offsetof(struct mlxsw_sp_acl_atcam_lkey_id, ht_node),
+};
+
+static const struct rhashtable_params mlxsw_sp_acl_atcam_entries_ht_params = {
+	.key_len = sizeof(struct mlxsw_sp_acl_atcam_entry_ht_key),
+	.key_offset = offsetof(struct mlxsw_sp_acl_atcam_entry, ht_key),
+	.head_offset = offsetof(struct mlxsw_sp_acl_atcam_entry, ht_node),
+};
+
+static bool
+mlxsw_sp_acl_atcam_is_centry(const struct mlxsw_sp_acl_atcam_entry *aentry)
+{
+	return mlxsw_sp_acl_erp_is_ctcam_erp(aentry->erp);
+}
+
+static int
+mlxsw_sp_acl_atcam_region_generic_init(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	struct mlxsw_sp_acl_atcam_region_generic *region_generic;
+
+	region_generic = kzalloc(sizeof(*region_generic), GFP_KERNEL);
+	if (!region_generic)
+		return -ENOMEM;
+
+	refcount_set(&region_generic->dummy_lkey_id.refcnt, 1);
+	aregion->priv = region_generic;
+
+	return 0;
+}
+
+static void
+mlxsw_sp_acl_atcam_region_generic_fini(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	kfree(aregion->priv);
+}
+
+static struct mlxsw_sp_acl_atcam_lkey_id *
+mlxsw_sp_acl_atcam_generic_lkey_id_get(struct mlxsw_sp_acl_atcam_region *aregion,
+				       struct mlxsw_sp_acl_rule_info *rulei,
+				       u8 erp_id)
+{
+	struct mlxsw_sp_acl_atcam_region_generic *region_generic;
+
+	region_generic = aregion->priv;
+	return &region_generic->dummy_lkey_id;
+}
+
+static void
+mlxsw_sp_acl_atcam_generic_lkey_id_put(struct mlxsw_sp_acl_atcam_region *aregion,
+				       struct mlxsw_sp_acl_atcam_lkey_id *lkey_id)
+{
+}
+
+static const struct mlxsw_sp_acl_atcam_region_ops
+mlxsw_sp_acl_atcam_region_generic_ops = {
+	.init		= mlxsw_sp_acl_atcam_region_generic_init,
+	.fini		= mlxsw_sp_acl_atcam_region_generic_fini,
+	.lkey_id_get	= mlxsw_sp_acl_atcam_generic_lkey_id_get,
+	.lkey_id_put	= mlxsw_sp_acl_atcam_generic_lkey_id_put,
+};
+
+static int
+mlxsw_sp_acl_atcam_region_12kb_init(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	struct mlxsw_sp *mlxsw_sp = aregion->region->mlxsw_sp;
+	struct mlxsw_sp_acl_atcam_region_12kb *region_12kb;
+	size_t alloc_size;
+	u64 max_lkey_id;
+	int err;
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_LARGE_KEY_ID))
+		return -EIO;
+
+	max_lkey_id = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_LARGE_KEY_ID);
+	region_12kb = kzalloc(sizeof(*region_12kb), GFP_KERNEL);
+	if (!region_12kb)
+		return -ENOMEM;
+
+	alloc_size = BITS_TO_LONGS(max_lkey_id) * sizeof(unsigned long);
+	region_12kb->used_lkey_id = kzalloc(alloc_size, GFP_KERNEL);
+	if (!region_12kb->used_lkey_id) {
+		err = -ENOMEM;
+		goto err_used_lkey_id_alloc;
+	}
+
+	err = rhashtable_init(&region_12kb->lkey_ht,
+			      &mlxsw_sp_acl_atcam_lkey_id_ht_params);
+	if (err)
+		goto err_rhashtable_init;
+
+	region_12kb->max_lkey_id = max_lkey_id;
+	aregion->priv = region_12kb;
+
+	return 0;
+
+err_rhashtable_init:
+	kfree(region_12kb->used_lkey_id);
+err_used_lkey_id_alloc:
+	kfree(region_12kb);
+	return err;
+}
+
+static void
+mlxsw_sp_acl_atcam_region_12kb_fini(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	struct mlxsw_sp_acl_atcam_region_12kb *region_12kb = aregion->priv;
+
+	rhashtable_destroy(&region_12kb->lkey_ht);
+	kfree(region_12kb->used_lkey_id);
+	kfree(region_12kb);
+}
+
+static struct mlxsw_sp_acl_atcam_lkey_id *
+mlxsw_sp_acl_atcam_lkey_id_create(struct mlxsw_sp_acl_atcam_region *aregion,
+				  struct mlxsw_sp_acl_atcam_lkey_id_ht_key *ht_key)
+{
+	struct mlxsw_sp_acl_atcam_region_12kb *region_12kb = aregion->priv;
+	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id;
+	u32 id;
+	int err;
+
+	id = find_first_zero_bit(region_12kb->used_lkey_id,
+				 region_12kb->max_lkey_id);
+	if (id < region_12kb->max_lkey_id)
+		__set_bit(id, region_12kb->used_lkey_id);
+	else
+		return ERR_PTR(-ENOBUFS);
+
+	lkey_id = kzalloc(sizeof(*lkey_id), GFP_KERNEL);
+	if (!lkey_id) {
+		err = -ENOMEM;
+		goto err_lkey_id_alloc;
+	}
+
+	lkey_id->id = id;
+	memcpy(&lkey_id->ht_key, ht_key, sizeof(*ht_key));
+	refcount_set(&lkey_id->refcnt, 1);
+
+	err = rhashtable_insert_fast(&region_12kb->lkey_ht,
+				     &lkey_id->ht_node,
+				     mlxsw_sp_acl_atcam_lkey_id_ht_params);
+	if (err)
+		goto err_rhashtable_insert;
+
+	return lkey_id;
+
+err_rhashtable_insert:
+	kfree(lkey_id);
+err_lkey_id_alloc:
+	__clear_bit(id, region_12kb->used_lkey_id);
+	return ERR_PTR(err);
+}
+
+static void
+mlxsw_sp_acl_atcam_lkey_id_destroy(struct mlxsw_sp_acl_atcam_region *aregion,
+				   struct mlxsw_sp_acl_atcam_lkey_id *lkey_id)
+{
+	struct mlxsw_sp_acl_atcam_region_12kb *region_12kb = aregion->priv;
+	u32 id = lkey_id->id;
+
+	rhashtable_remove_fast(&region_12kb->lkey_ht, &lkey_id->ht_node,
+			       mlxsw_sp_acl_atcam_lkey_id_ht_params);
+	kfree(lkey_id);
+	__clear_bit(id, region_12kb->used_lkey_id);
+}
+
+static struct mlxsw_sp_acl_atcam_lkey_id *
+mlxsw_sp_acl_atcam_12kb_lkey_id_get(struct mlxsw_sp_acl_atcam_region *aregion,
+				    struct mlxsw_sp_acl_rule_info *rulei,
+				    u8 erp_id)
+{
+	struct mlxsw_sp_acl_atcam_region_12kb *region_12kb = aregion->priv;
+	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
+	struct mlxsw_sp_acl_atcam_lkey_id_ht_key ht_key = {{ 0 } };
+	struct mlxsw_sp *mlxsw_sp = region->mlxsw_sp;
+	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
+	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id;
+
+	mlxsw_afk_encode(afk, region->key_info, &rulei->values, ht_key.enc_key,
+			 NULL, MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_START,
+			 MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_END);
+	ht_key.erp_id = erp_id;
+	lkey_id = rhashtable_lookup_fast(&region_12kb->lkey_ht, &ht_key,
+					 mlxsw_sp_acl_atcam_lkey_id_ht_params);
+	if (lkey_id) {
+		refcount_inc(&lkey_id->refcnt);
+		return lkey_id;
+	}
+
+	return mlxsw_sp_acl_atcam_lkey_id_create(aregion, &ht_key);
+}
+
+static void
+mlxsw_sp_acl_atcam_12kb_lkey_id_put(struct mlxsw_sp_acl_atcam_region *aregion,
+				    struct mlxsw_sp_acl_atcam_lkey_id *lkey_id)
+{
+	if (refcount_dec_and_test(&lkey_id->refcnt))
+		mlxsw_sp_acl_atcam_lkey_id_destroy(aregion, lkey_id);
+}
+
+static const struct mlxsw_sp_acl_atcam_region_ops
+mlxsw_sp_acl_atcam_region_12kb_ops = {
+	.init		= mlxsw_sp_acl_atcam_region_12kb_init,
+	.fini		= mlxsw_sp_acl_atcam_region_12kb_fini,
+	.lkey_id_get	= mlxsw_sp_acl_atcam_12kb_lkey_id_get,
+	.lkey_id_put	= mlxsw_sp_acl_atcam_12kb_lkey_id_put,
+};
+
+static const struct mlxsw_sp_acl_atcam_region_ops *
+mlxsw_sp_acl_atcam_region_ops_arr[] = {
+	[MLXSW_SP_ACL_ATCAM_REGION_TYPE_2KB]	=
+		&mlxsw_sp_acl_atcam_region_generic_ops,
+	[MLXSW_SP_ACL_ATCAM_REGION_TYPE_4KB]	=
+		&mlxsw_sp_acl_atcam_region_generic_ops,
+	[MLXSW_SP_ACL_ATCAM_REGION_TYPE_8KB]	=
+		&mlxsw_sp_acl_atcam_region_generic_ops,
+	[MLXSW_SP_ACL_ATCAM_REGION_TYPE_12KB]	=
+		&mlxsw_sp_acl_atcam_region_12kb_ops,
+};
+
+int mlxsw_sp_acl_atcam_region_associate(struct mlxsw_sp *mlxsw_sp,
+					u16 region_id)
+{
+	char perar_pl[MLXSW_REG_PERAR_LEN];
+	/* For now, just assume that every region has 12 key blocks */
+	u16 hw_region = region_id * 3;
+	u64 max_regions;
+
+	max_regions = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_REGIONS);
+	if (hw_region >= max_regions)
+		return -ENOBUFS;
+
+	mlxsw_reg_perar_pack(perar_pl, region_id, hw_region);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(perar), perar_pl);
+}
+
+static void
+mlxsw_sp_acl_atcam_region_type_init(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
+	enum mlxsw_sp_acl_atcam_region_type region_type;
+	unsigned int blocks_count;
+
+	/* We already know the blocks count can not exceed the maximum
+	 * blocks count.
+	 */
+	blocks_count = mlxsw_afk_key_info_blocks_count_get(region->key_info);
+	if (blocks_count <= 2)
+		region_type = MLXSW_SP_ACL_ATCAM_REGION_TYPE_2KB;
+	else if (blocks_count <= 4)
+		region_type = MLXSW_SP_ACL_ATCAM_REGION_TYPE_4KB;
+	else if (blocks_count <= 8)
+		region_type = MLXSW_SP_ACL_ATCAM_REGION_TYPE_8KB;
+	else
+		region_type = MLXSW_SP_ACL_ATCAM_REGION_TYPE_12KB;
+
+	aregion->type = region_type;
+	aregion->ops = mlxsw_sp_acl_atcam_region_ops_arr[region_type];
+}
+
+int
+mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_atcam *atcam,
+			       struct mlxsw_sp_acl_atcam_region *aregion,
+			       struct mlxsw_sp_acl_tcam_region *region,
+			       const struct mlxsw_sp_acl_ctcam_region_ops *ops)
+{
+	int err;
+
+	aregion->region = region;
+	aregion->atcam = atcam;
+	mlxsw_sp_acl_atcam_region_type_init(aregion);
+
+	err = rhashtable_init(&aregion->entries_ht,
+			      &mlxsw_sp_acl_atcam_entries_ht_params);
+	if (err)
+		return err;
+	err = aregion->ops->init(aregion);
+	if (err)
+		goto err_ops_init;
+	err = mlxsw_sp_acl_erp_region_init(aregion);
+	if (err)
+		goto err_erp_region_init;
+	err = mlxsw_sp_acl_ctcam_region_init(mlxsw_sp, &aregion->cregion,
+					     region, ops);
+	if (err)
+		goto err_ctcam_region_init;
+
+	return 0;
+
+err_ctcam_region_init:
+	mlxsw_sp_acl_erp_region_fini(aregion);
+err_erp_region_init:
+	aregion->ops->fini(aregion);
+err_ops_init:
+	rhashtable_destroy(&aregion->entries_ht);
+	return err;
+}
+
+void mlxsw_sp_acl_atcam_region_fini(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	mlxsw_sp_acl_ctcam_region_fini(&aregion->cregion);
+	mlxsw_sp_acl_erp_region_fini(aregion);
+	aregion->ops->fini(aregion);
+	rhashtable_destroy(&aregion->entries_ht);
+}
+
+void mlxsw_sp_acl_atcam_chunk_init(struct mlxsw_sp_acl_atcam_region *aregion,
+				   struct mlxsw_sp_acl_atcam_chunk *achunk,
+				   unsigned int priority)
+{
+	mlxsw_sp_acl_ctcam_chunk_init(&aregion->cregion, &achunk->cchunk,
+				      priority);
+}
+
+void mlxsw_sp_acl_atcam_chunk_fini(struct mlxsw_sp_acl_atcam_chunk *achunk)
+{
+	mlxsw_sp_acl_ctcam_chunk_fini(&achunk->cchunk);
+}
+
+static int
+mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp_acl_atcam_region *aregion,
+				       struct mlxsw_sp_acl_atcam_entry *aentry,
+				       struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
+	u8 erp_id = mlxsw_sp_acl_erp_id(aentry->erp);
+	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id;
+	char ptce3_pl[MLXSW_REG_PTCE3_LEN];
+	u32 kvdl_index, priority;
+	int err;
+
+	err = mlxsw_sp_acl_tcam_priority_get(mlxsw_sp, rulei, &priority, true);
+	if (err)
+		return err;
+
+	lkey_id = aregion->ops->lkey_id_get(aregion, rulei, erp_id);
+	if (IS_ERR(lkey_id))
+		return PTR_ERR(lkey_id);
+	aentry->lkey_id = lkey_id;
+
+	kvdl_index = mlxsw_afa_block_first_kvdl_index(rulei->act_block);
+	mlxsw_reg_ptce3_pack(ptce3_pl, true, MLXSW_REG_PTCE3_OP_WRITE_WRITE,
+			     priority, region->tcam_region_info,
+			     aentry->ht_key.enc_key, erp_id,
+			     refcount_read(&lkey_id->refcnt) != 1, lkey_id->id,
+			     kvdl_index);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce3), ptce3_pl);
+	if (err)
+		goto err_ptce3_write;
+
+	return 0;
+
+err_ptce3_write:
+	aregion->ops->lkey_id_put(aregion, lkey_id);
+	return err;
+}
+
+static void
+mlxsw_sp_acl_atcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp_acl_atcam_region *aregion,
+				       struct mlxsw_sp_acl_atcam_entry *aentry)
+{
+	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id = aentry->lkey_id;
+	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
+	u8 erp_id = mlxsw_sp_acl_erp_id(aentry->erp);
+	char ptce3_pl[MLXSW_REG_PTCE3_LEN];
+
+	mlxsw_reg_ptce3_pack(ptce3_pl, false, MLXSW_REG_PTCE3_OP_WRITE_WRITE, 0,
+			     region->tcam_region_info, aentry->ht_key.enc_key,
+			     erp_id, refcount_read(&lkey_id->refcnt) != 1,
+			     lkey_id->id, 0);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce3), ptce3_pl);
+	aregion->ops->lkey_id_put(aregion, lkey_id);
+}
+
+static int
+__mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_atcam_region *aregion,
+			       struct mlxsw_sp_acl_atcam_entry *aentry,
+			       struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
+	char mask[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN] = { 0 };
+	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
+	struct mlxsw_sp_acl_erp *erp;
+	unsigned int blocks_count;
+	int err;
+
+	blocks_count = mlxsw_afk_key_info_blocks_count_get(region->key_info);
+	mlxsw_afk_encode(afk, region->key_info, &rulei->values,
+			 aentry->ht_key.enc_key, mask, 0, blocks_count - 1);
+
+	erp = mlxsw_sp_acl_erp_get(aregion, mask, false);
+	if (IS_ERR(erp))
+		return PTR_ERR(erp);
+	aentry->erp = erp;
+	aentry->ht_key.erp_id = mlxsw_sp_acl_erp_id(erp);
+
+	/* We can't insert identical rules into the A-TCAM, so fail and
+	 * let the rule spill into C-TCAM
+	 */
+	err = rhashtable_lookup_insert_fast(&aregion->entries_ht,
+					    &aentry->ht_node,
+					    mlxsw_sp_acl_atcam_entries_ht_params);
+	if (err)
+		goto err_rhashtable_insert;
+
+	err = mlxsw_sp_acl_atcam_region_entry_insert(mlxsw_sp, aregion, aentry,
+						     rulei);
+	if (err)
+		goto err_rule_insert;
+
+	return 0;
+
+err_rule_insert:
+	rhashtable_remove_fast(&aregion->entries_ht, &aentry->ht_node,
+			       mlxsw_sp_acl_atcam_entries_ht_params);
+err_rhashtable_insert:
+	mlxsw_sp_acl_erp_put(aregion, erp);
+	return err;
+}
+
+static void
+__mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_atcam_region *aregion,
+			       struct mlxsw_sp_acl_atcam_entry *aentry)
+{
+	mlxsw_sp_acl_atcam_region_entry_remove(mlxsw_sp, aregion, aentry);
+	rhashtable_remove_fast(&aregion->entries_ht, &aentry->ht_node,
+			       mlxsw_sp_acl_atcam_entries_ht_params);
+	mlxsw_sp_acl_erp_put(aregion, aentry->erp);
+}
+
+int mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_atcam_region *aregion,
+				 struct mlxsw_sp_acl_atcam_chunk *achunk,
+				 struct mlxsw_sp_acl_atcam_entry *aentry,
+				 struct mlxsw_sp_acl_rule_info *rulei)
+{
+	int err;
+
+	err = __mlxsw_sp_acl_atcam_entry_add(mlxsw_sp, aregion, aentry, rulei);
+	if (!err)
+		return 0;
+
+	/* It is possible we failed to add the rule to the A-TCAM due to
+	 * exceeded number of masks. Try to spill into C-TCAM.
+	 */
+	err = mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, &aregion->cregion,
+					   &achunk->cchunk, &aentry->centry,
+					   rulei, true);
+	if (!err)
+		return 0;
+
+	return err;
+}
+
+void mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_acl_atcam_region *aregion,
+				  struct mlxsw_sp_acl_atcam_chunk *achunk,
+				  struct mlxsw_sp_acl_atcam_entry *aentry)
+{
+	if (mlxsw_sp_acl_atcam_is_centry(aentry))
+		mlxsw_sp_acl_ctcam_entry_del(mlxsw_sp, &aregion->cregion,
+					     &achunk->cchunk, &aentry->centry);
+	else
+		__mlxsw_sp_acl_atcam_entry_del(mlxsw_sp, aregion, aentry);
+}
+
+int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp,
+			    struct mlxsw_sp_acl_atcam *atcam)
+{
+	return mlxsw_sp_acl_erps_init(mlxsw_sp, atcam);
+}
+
+void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_acl_atcam *atcam)
+{
+	mlxsw_sp_acl_erps_fini(mlxsw_sp, atcam);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
new file mode 100644
index 000000000000..e3c6fe8b1d40
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/parman.h>
+
+#include "reg.h"
+#include "core.h"
+#include "spectrum.h"
+#include "spectrum_acl_tcam.h"
+
+static int
+mlxsw_sp_acl_ctcam_region_resize(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_tcam_region *region,
+				 u16 new_size)
+{
+	char ptar_pl[MLXSW_REG_PTAR_LEN];
+
+	mlxsw_reg_ptar_pack(ptar_pl, MLXSW_REG_PTAR_OP_RESIZE,
+			    region->key_type, new_size, region->id,
+			    region->tcam_region_info);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptar), ptar_pl);
+}
+
+static void
+mlxsw_sp_acl_ctcam_region_move(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_tcam_region *region,
+			       u16 src_offset, u16 dst_offset, u16 size)
+{
+	char prcr_pl[MLXSW_REG_PRCR_LEN];
+
+	mlxsw_reg_prcr_pack(prcr_pl, MLXSW_REG_PRCR_OP_MOVE,
+			    region->tcam_region_info, src_offset,
+			    region->tcam_region_info, dst_offset, size);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(prcr), prcr_pl);
+}
+
+static int
+mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp_acl_ctcam_region *cregion,
+				       struct mlxsw_sp_acl_ctcam_entry *centry,
+				       struct mlxsw_sp_acl_rule_info *rulei,
+				       bool fillup_priority)
+{
+	struct mlxsw_sp_acl_tcam_region *region = cregion->region;
+	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
+	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
+	unsigned int blocks_count;
+	char *act_set;
+	u32 priority;
+	char *mask;
+	char *key;
+	int err;
+
+	err = mlxsw_sp_acl_tcam_priority_get(mlxsw_sp, rulei, &priority,
+					     fillup_priority);
+	if (err)
+		return err;
+
+	mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_WRITE_WRITE,
+			     region->tcam_region_info,
+			     centry->parman_item.index, priority);
+	key = mlxsw_reg_ptce2_flex_key_blocks_data(ptce2_pl);
+	mask = mlxsw_reg_ptce2_mask_data(ptce2_pl);
+	blocks_count = mlxsw_afk_key_info_blocks_count_get(region->key_info);
+	mlxsw_afk_encode(afk, region->key_info, &rulei->values, key, mask, 0,
+			 blocks_count - 1);
+
+	err = cregion->ops->entry_insert(cregion, centry, mask);
+	if (err)
+		return err;
+
+	/* Only the first action set belongs here, the rest is in KVD */
+	act_set = mlxsw_afa_block_first_set(rulei->act_block);
+	mlxsw_reg_ptce2_flex_action_set_memcpy_to(ptce2_pl, act_set);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
+}
+
+static void
+mlxsw_sp_acl_ctcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp_acl_ctcam_region *cregion,
+				       struct mlxsw_sp_acl_ctcam_entry *centry)
+{
+	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
+
+	mlxsw_reg_ptce2_pack(ptce2_pl, false, MLXSW_REG_PTCE2_OP_WRITE_WRITE,
+			     cregion->region->tcam_region_info,
+			     centry->parman_item.index, 0);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
+	cregion->ops->entry_remove(cregion, centry);
+}
+
+static int mlxsw_sp_acl_ctcam_region_parman_resize(void *priv,
+						   unsigned long new_count)
+{
+	struct mlxsw_sp_acl_ctcam_region *cregion = priv;
+	struct mlxsw_sp_acl_tcam_region *region = cregion->region;
+	struct mlxsw_sp *mlxsw_sp = region->mlxsw_sp;
+	u64 max_tcam_rules;
+
+	max_tcam_rules = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_TCAM_RULES);
+	if (new_count > max_tcam_rules)
+		return -EINVAL;
+	return mlxsw_sp_acl_ctcam_region_resize(mlxsw_sp, region, new_count);
+}
+
+static void mlxsw_sp_acl_ctcam_region_parman_move(void *priv,
+						  unsigned long from_index,
+						  unsigned long to_index,
+						  unsigned long count)
+{
+	struct mlxsw_sp_acl_ctcam_region *cregion = priv;
+	struct mlxsw_sp_acl_tcam_region *region = cregion->region;
+	struct mlxsw_sp *mlxsw_sp = region->mlxsw_sp;
+
+	mlxsw_sp_acl_ctcam_region_move(mlxsw_sp, region,
+				       from_index, to_index, count);
+}
+
+static const struct parman_ops mlxsw_sp_acl_ctcam_region_parman_ops = {
+	.base_count	= MLXSW_SP_ACL_TCAM_REGION_BASE_COUNT,
+	.resize_step	= MLXSW_SP_ACL_TCAM_REGION_RESIZE_STEP,
+	.resize		= mlxsw_sp_acl_ctcam_region_parman_resize,
+	.move		= mlxsw_sp_acl_ctcam_region_parman_move,
+	.algo		= PARMAN_ALGO_TYPE_LSORT,
+};
+
+int
+mlxsw_sp_acl_ctcam_region_init(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_ctcam_region *cregion,
+			       struct mlxsw_sp_acl_tcam_region *region,
+			       const struct mlxsw_sp_acl_ctcam_region_ops *ops)
+{
+	cregion->region = region;
+	cregion->ops = ops;
+	cregion->parman = parman_create(&mlxsw_sp_acl_ctcam_region_parman_ops,
+					cregion);
+	if (!cregion->parman)
+		return -ENOMEM;
+	return 0;
+}
+
+void mlxsw_sp_acl_ctcam_region_fini(struct mlxsw_sp_acl_ctcam_region *cregion)
+{
+	parman_destroy(cregion->parman);
+}
+
+void mlxsw_sp_acl_ctcam_chunk_init(struct mlxsw_sp_acl_ctcam_region *cregion,
+				   struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+				   unsigned int priority)
+{
+	parman_prio_init(cregion->parman, &cchunk->parman_prio, priority);
+}
+
+void mlxsw_sp_acl_ctcam_chunk_fini(struct mlxsw_sp_acl_ctcam_chunk *cchunk)
+{
+	parman_prio_fini(&cchunk->parman_prio);
+}
+
+int mlxsw_sp_acl_ctcam_entry_add(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_ctcam_region *cregion,
+				 struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+				 struct mlxsw_sp_acl_ctcam_entry *centry,
+				 struct mlxsw_sp_acl_rule_info *rulei,
+				 bool fillup_priority)
+{
+	int err;
+
+	err = parman_item_add(cregion->parman, &cchunk->parman_prio,
+			      &centry->parman_item);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_acl_ctcam_region_entry_insert(mlxsw_sp, cregion, centry,
+						     rulei, fillup_priority);
+	if (err)
+		goto err_rule_insert;
+	return 0;
+
+err_rule_insert:
+	parman_item_remove(cregion->parman, &cchunk->parman_prio,
+			   &centry->parman_item);
+	return err;
+}
+
+void mlxsw_sp_acl_ctcam_entry_del(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_acl_ctcam_region *cregion,
+				  struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+				  struct mlxsw_sp_acl_ctcam_entry *centry)
+{
+	mlxsw_sp_acl_ctcam_region_entry_remove(mlxsw_sp, cregion, centry);
+	parman_item_remove(cregion->parman, &cchunk->parman_prio,
+			   &centry->parman_item);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
new file mode 100644
index 000000000000..0a4fd3c8662a
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -0,0 +1,1168 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
+
+#include <linux/bitmap.h>
+#include <linux/errno.h>
+#include <linux/genalloc.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/rhashtable.h>
+#include <linux/rtnetlink.h>
+#include <linux/slab.h>
+
+#include "core.h"
+#include "reg.h"
+#include "spectrum.h"
+#include "spectrum_acl_tcam.h"
+
+/* gen_pool_alloc() returns 0 when allocation fails, so use an offset */
+#define MLXSW_SP_ACL_ERP_GENALLOC_OFFSET 0x100
+#define MLXSW_SP_ACL_ERP_MAX_PER_REGION 16
+
+struct mlxsw_sp_acl_erp_core {
+	unsigned int erpt_entries_size[MLXSW_SP_ACL_ATCAM_REGION_TYPE_MAX + 1];
+	struct gen_pool *erp_tables;
+	struct mlxsw_sp *mlxsw_sp;
+	unsigned int num_erp_banks;
+};
+
+struct mlxsw_sp_acl_erp_key {
+	char mask[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN];
+	bool ctcam;
+};
+
+struct mlxsw_sp_acl_erp {
+	struct mlxsw_sp_acl_erp_key key;
+	u8 id;
+	u8 index;
+	refcount_t refcnt;
+	DECLARE_BITMAP(mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN);
+	struct list_head list;
+	struct rhash_head ht_node;
+	struct mlxsw_sp_acl_erp_table *erp_table;
+};
+
+struct mlxsw_sp_acl_erp_master_mask {
+	DECLARE_BITMAP(bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN);
+	unsigned int count[MLXSW_SP_ACL_TCAM_MASK_LEN];
+};
+
+struct mlxsw_sp_acl_erp_table {
+	struct mlxsw_sp_acl_erp_master_mask master_mask;
+	DECLARE_BITMAP(erp_id_bitmap, MLXSW_SP_ACL_ERP_MAX_PER_REGION);
+	DECLARE_BITMAP(erp_index_bitmap, MLXSW_SP_ACL_ERP_MAX_PER_REGION);
+	struct list_head atcam_erps_list;
+	struct rhashtable erp_ht;
+	struct mlxsw_sp_acl_erp_core *erp_core;
+	struct mlxsw_sp_acl_atcam_region *aregion;
+	const struct mlxsw_sp_acl_erp_table_ops *ops;
+	unsigned long base_index;
+	unsigned int num_atcam_erps;
+	unsigned int num_max_atcam_erps;
+	unsigned int num_ctcam_erps;
+};
+
+static const struct rhashtable_params mlxsw_sp_acl_erp_ht_params = {
+	.key_len = sizeof(struct mlxsw_sp_acl_erp_key),
+	.key_offset = offsetof(struct mlxsw_sp_acl_erp, key),
+	.head_offset = offsetof(struct mlxsw_sp_acl_erp, ht_node),
+};
+
+struct mlxsw_sp_acl_erp_table_ops {
+	struct mlxsw_sp_acl_erp *
+		(*erp_create)(struct mlxsw_sp_acl_erp_table *erp_table,
+			      struct mlxsw_sp_acl_erp_key *key);
+	void (*erp_destroy)(struct mlxsw_sp_acl_erp_table *erp_table,
+			    struct mlxsw_sp_acl_erp *erp);
+};
+
+static struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
+			     struct mlxsw_sp_acl_erp_key *key);
+static void
+mlxsw_sp_acl_erp_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
+			      struct mlxsw_sp_acl_erp *erp);
+static struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_second_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
+				    struct mlxsw_sp_acl_erp_key *key);
+static void
+mlxsw_sp_acl_erp_second_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
+				     struct mlxsw_sp_acl_erp *erp);
+static struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_first_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
+				   struct mlxsw_sp_acl_erp_key *key);
+static void
+mlxsw_sp_acl_erp_first_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
+				    struct mlxsw_sp_acl_erp *erp);
+static void
+mlxsw_sp_acl_erp_no_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
+				 struct mlxsw_sp_acl_erp *erp);
+
+static const struct mlxsw_sp_acl_erp_table_ops erp_multiple_masks_ops = {
+	.erp_create = mlxsw_sp_acl_erp_mask_create,
+	.erp_destroy = mlxsw_sp_acl_erp_mask_destroy,
+};
+
+static const struct mlxsw_sp_acl_erp_table_ops erp_two_masks_ops = {
+	.erp_create = mlxsw_sp_acl_erp_mask_create,
+	.erp_destroy = mlxsw_sp_acl_erp_second_mask_destroy,
+};
+
+static const struct mlxsw_sp_acl_erp_table_ops erp_single_mask_ops = {
+	.erp_create = mlxsw_sp_acl_erp_second_mask_create,
+	.erp_destroy = mlxsw_sp_acl_erp_first_mask_destroy,
+};
+
+static const struct mlxsw_sp_acl_erp_table_ops erp_no_mask_ops = {
+	.erp_create = mlxsw_sp_acl_erp_first_mask_create,
+	.erp_destroy = mlxsw_sp_acl_erp_no_mask_destroy,
+};
+
+bool mlxsw_sp_acl_erp_is_ctcam_erp(const struct mlxsw_sp_acl_erp *erp)
+{
+	return erp->key.ctcam;
+}
+
+u8 mlxsw_sp_acl_erp_id(const struct mlxsw_sp_acl_erp *erp)
+{
+	return erp->id;
+}
+
+static unsigned int
+mlxsw_sp_acl_erp_table_entry_size(const struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	struct mlxsw_sp_acl_atcam_region *aregion = erp_table->aregion;
+	struct mlxsw_sp_acl_erp_core *erp_core = erp_table->erp_core;
+
+	return erp_core->erpt_entries_size[aregion->type];
+}
+
+static int mlxsw_sp_acl_erp_id_get(struct mlxsw_sp_acl_erp_table *erp_table,
+				   u8 *p_id)
+{
+	u8 id;
+
+	id = find_first_zero_bit(erp_table->erp_id_bitmap,
+				 MLXSW_SP_ACL_ERP_MAX_PER_REGION);
+	if (id < MLXSW_SP_ACL_ERP_MAX_PER_REGION) {
+		__set_bit(id, erp_table->erp_id_bitmap);
+		*p_id = id;
+		return 0;
+	}
+
+	return -ENOBUFS;
+}
+
+static void mlxsw_sp_acl_erp_id_put(struct mlxsw_sp_acl_erp_table *erp_table,
+				    u8 id)
+{
+	__clear_bit(id, erp_table->erp_id_bitmap);
+}
+
+static void
+mlxsw_sp_acl_erp_master_mask_bit_set(unsigned long bit,
+				     struct mlxsw_sp_acl_erp_master_mask *mask)
+{
+	if (mask->count[bit]++ == 0)
+		__set_bit(bit, mask->bitmap);
+}
+
+static void
+mlxsw_sp_acl_erp_master_mask_bit_clear(unsigned long bit,
+				       struct mlxsw_sp_acl_erp_master_mask *mask)
+{
+	if (--mask->count[bit] == 0)
+		__clear_bit(bit, mask->bitmap);
+}
+
+static int
+mlxsw_sp_acl_erp_master_mask_update(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	struct mlxsw_sp_acl_tcam_region *region = erp_table->aregion->region;
+	struct mlxsw_sp *mlxsw_sp = region->mlxsw_sp;
+	char percr_pl[MLXSW_REG_PERCR_LEN];
+	char *master_mask;
+
+	mlxsw_reg_percr_pack(percr_pl, region->id);
+	master_mask = mlxsw_reg_percr_master_mask_data(percr_pl);
+	bitmap_to_arr32((u32 *) master_mask, erp_table->master_mask.bitmap,
+			MLXSW_SP_ACL_TCAM_MASK_LEN);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(percr), percr_pl);
+}
+
+static int
+mlxsw_sp_acl_erp_master_mask_set(struct mlxsw_sp_acl_erp_table *erp_table,
+				 const struct mlxsw_sp_acl_erp *erp)
+{
+	unsigned long bit;
+	int err;
+
+	for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
+		mlxsw_sp_acl_erp_master_mask_bit_set(bit,
+						     &erp_table->master_mask);
+
+	err = mlxsw_sp_acl_erp_master_mask_update(erp_table);
+	if (err)
+		goto err_master_mask_update;
+
+	return 0;
+
+err_master_mask_update:
+	for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
+		mlxsw_sp_acl_erp_master_mask_bit_clear(bit,
+						       &erp_table->master_mask);
+	return err;
+}
+
+static int
+mlxsw_sp_acl_erp_master_mask_clear(struct mlxsw_sp_acl_erp_table *erp_table,
+				   const struct mlxsw_sp_acl_erp *erp)
+{
+	unsigned long bit;
+	int err;
+
+	for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
+		mlxsw_sp_acl_erp_master_mask_bit_clear(bit,
+						       &erp_table->master_mask);
+
+	err = mlxsw_sp_acl_erp_master_mask_update(erp_table);
+	if (err)
+		goto err_master_mask_update;
+
+	return 0;
+
+err_master_mask_update:
+	for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
+		mlxsw_sp_acl_erp_master_mask_bit_set(bit,
+						     &erp_table->master_mask);
+	return err;
+}
+
+static struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_generic_create(struct mlxsw_sp_acl_erp_table *erp_table,
+				struct mlxsw_sp_acl_erp_key *key)
+{
+	struct mlxsw_sp_acl_erp *erp;
+	int err;
+
+	erp = kzalloc(sizeof(*erp), GFP_KERNEL);
+	if (!erp)
+		return ERR_PTR(-ENOMEM);
+
+	err = mlxsw_sp_acl_erp_id_get(erp_table, &erp->id);
+	if (err)
+		goto err_erp_id_get;
+
+	memcpy(&erp->key, key, sizeof(*key));
+	bitmap_from_arr32(erp->mask_bitmap, (u32 *) key->mask,
+			  MLXSW_SP_ACL_TCAM_MASK_LEN);
+	list_add(&erp->list, &erp_table->atcam_erps_list);
+	refcount_set(&erp->refcnt, 1);
+	erp_table->num_atcam_erps++;
+	erp->erp_table = erp_table;
+
+	err = mlxsw_sp_acl_erp_master_mask_set(erp_table, erp);
+	if (err)
+		goto err_master_mask_set;
+
+	err = rhashtable_insert_fast(&erp_table->erp_ht, &erp->ht_node,
+				     mlxsw_sp_acl_erp_ht_params);
+	if (err)
+		goto err_rhashtable_insert;
+
+	return erp;
+
+err_rhashtable_insert:
+	mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp);
+err_master_mask_set:
+	erp_table->num_atcam_erps--;
+	list_del(&erp->list);
+	mlxsw_sp_acl_erp_id_put(erp_table, erp->id);
+err_erp_id_get:
+	kfree(erp);
+	return ERR_PTR(err);
+}
+
+static void
+mlxsw_sp_acl_erp_generic_destroy(struct mlxsw_sp_acl_erp *erp)
+{
+	struct mlxsw_sp_acl_erp_table *erp_table = erp->erp_table;
+
+	rhashtable_remove_fast(&erp_table->erp_ht, &erp->ht_node,
+			       mlxsw_sp_acl_erp_ht_params);
+	mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp);
+	erp_table->num_atcam_erps--;
+	list_del(&erp->list);
+	mlxsw_sp_acl_erp_id_put(erp_table, erp->id);
+	kfree(erp);
+}
+
+static int
+mlxsw_sp_acl_erp_table_alloc(struct mlxsw_sp_acl_erp_core *erp_core,
+			     unsigned int num_erps,
+			     enum mlxsw_sp_acl_atcam_region_type region_type,
+			     unsigned long *p_index)
+{
+	unsigned int num_rows, entry_size;
+
+	/* We only allow allocations of entire rows */
+	if (num_erps % erp_core->num_erp_banks != 0)
+		return -EINVAL;
+
+	entry_size = erp_core->erpt_entries_size[region_type];
+	num_rows = num_erps / erp_core->num_erp_banks;
+
+	*p_index = gen_pool_alloc(erp_core->erp_tables, num_rows * entry_size);
+	if (*p_index == 0)
+		return -ENOBUFS;
+	*p_index -= MLXSW_SP_ACL_ERP_GENALLOC_OFFSET;
+
+	return 0;
+}
+
+static void
+mlxsw_sp_acl_erp_table_free(struct mlxsw_sp_acl_erp_core *erp_core,
+			    unsigned int num_erps,
+			    enum mlxsw_sp_acl_atcam_region_type region_type,
+			    unsigned long index)
+{
+	unsigned long base_index;
+	unsigned int entry_size;
+	size_t size;
+
+	entry_size = erp_core->erpt_entries_size[region_type];
+	base_index = index + MLXSW_SP_ACL_ERP_GENALLOC_OFFSET;
+	size = num_erps / erp_core->num_erp_banks * entry_size;
+	gen_pool_free(erp_core->erp_tables, base_index, size);
+}
+
+static struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_table_master_rp(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	if (!list_is_singular(&erp_table->atcam_erps_list))
+		return NULL;
+
+	return list_first_entry(&erp_table->atcam_erps_list,
+				struct mlxsw_sp_acl_erp, list);
+}
+
+static int mlxsw_sp_acl_erp_index_get(struct mlxsw_sp_acl_erp_table *erp_table,
+				      u8 *p_index)
+{
+	u8 index;
+
+	index = find_first_zero_bit(erp_table->erp_index_bitmap,
+				    erp_table->num_max_atcam_erps);
+	if (index < erp_table->num_max_atcam_erps) {
+		__set_bit(index, erp_table->erp_index_bitmap);
+		*p_index = index;
+		return 0;
+	}
+
+	return -ENOBUFS;
+}
+
+static void mlxsw_sp_acl_erp_index_put(struct mlxsw_sp_acl_erp_table *erp_table,
+				       u8 index)
+{
+	__clear_bit(index, erp_table->erp_index_bitmap);
+}
+
+static void
+mlxsw_sp_acl_erp_table_locate(const struct mlxsw_sp_acl_erp_table *erp_table,
+			      const struct mlxsw_sp_acl_erp *erp,
+			      u8 *p_erpt_bank, u8 *p_erpt_index)
+{
+	unsigned int entry_size = mlxsw_sp_acl_erp_table_entry_size(erp_table);
+	struct mlxsw_sp_acl_erp_core *erp_core = erp_table->erp_core;
+	unsigned int row;
+
+	*p_erpt_bank = erp->index % erp_core->num_erp_banks;
+	row = erp->index / erp_core->num_erp_banks;
+	*p_erpt_index = erp_table->base_index + row * entry_size;
+}
+
+static int
+mlxsw_sp_acl_erp_table_erp_add(struct mlxsw_sp_acl_erp_table *erp_table,
+			       struct mlxsw_sp_acl_erp *erp)
+{
+	struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp;
+	enum mlxsw_reg_perpt_key_size key_size;
+	char perpt_pl[MLXSW_REG_PERPT_LEN];
+	u8 erpt_bank, erpt_index;
+
+	mlxsw_sp_acl_erp_table_locate(erp_table, erp, &erpt_bank, &erpt_index);
+	key_size = (enum mlxsw_reg_perpt_key_size) erp_table->aregion->type;
+	mlxsw_reg_perpt_pack(perpt_pl, erpt_bank, erpt_index, key_size, erp->id,
+			     0, erp_table->base_index, erp->index,
+			     erp->key.mask);
+	mlxsw_reg_perpt_erp_vector_pack(perpt_pl, erp_table->erp_index_bitmap,
+					MLXSW_SP_ACL_ERP_MAX_PER_REGION);
+	mlxsw_reg_perpt_erp_vector_set(perpt_pl, erp->index, true);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(perpt), perpt_pl);
+}
+
+static void mlxsw_sp_acl_erp_table_erp_del(struct mlxsw_sp_acl_erp *erp)
+{
+	char empty_mask[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN] = { 0 };
+	struct mlxsw_sp_acl_erp_table *erp_table = erp->erp_table;
+	struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp;
+	enum mlxsw_reg_perpt_key_size key_size;
+	char perpt_pl[MLXSW_REG_PERPT_LEN];
+	u8 erpt_bank, erpt_index;
+
+	mlxsw_sp_acl_erp_table_locate(erp_table, erp, &erpt_bank, &erpt_index);
+	key_size = (enum mlxsw_reg_perpt_key_size) erp_table->aregion->type;
+	mlxsw_reg_perpt_pack(perpt_pl, erpt_bank, erpt_index, key_size, erp->id,
+			     0, erp_table->base_index, erp->index, empty_mask);
+	mlxsw_reg_perpt_erp_vector_pack(perpt_pl, erp_table->erp_index_bitmap,
+					MLXSW_SP_ACL_ERP_MAX_PER_REGION);
+	mlxsw_reg_perpt_erp_vector_set(perpt_pl, erp->index, false);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(perpt), perpt_pl);
+}
+
+static int
+mlxsw_sp_acl_erp_table_enable(struct mlxsw_sp_acl_erp_table *erp_table,
+			      bool ctcam_le)
+{
+	struct mlxsw_sp_acl_tcam_region *region = erp_table->aregion->region;
+	struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp;
+	char pererp_pl[MLXSW_REG_PERERP_LEN];
+
+	mlxsw_reg_pererp_pack(pererp_pl, region->id, ctcam_le, true, 0,
+			      erp_table->base_index, 0);
+	mlxsw_reg_pererp_erp_vector_pack(pererp_pl, erp_table->erp_index_bitmap,
+					 MLXSW_SP_ACL_ERP_MAX_PER_REGION);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl);
+}
+
+static void
+mlxsw_sp_acl_erp_table_disable(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	struct mlxsw_sp_acl_tcam_region *region = erp_table->aregion->region;
+	struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp;
+	char pererp_pl[MLXSW_REG_PERERP_LEN];
+	struct mlxsw_sp_acl_erp *master_rp;
+
+	master_rp = mlxsw_sp_acl_erp_table_master_rp(erp_table);
+	/* It is possible we do not have a master RP when we disable the
+	 * table when there are no rules in the A-TCAM and the last C-TCAM
+	 * rule is deleted
+	 */
+	mlxsw_reg_pererp_pack(pererp_pl, region->id, false, false, 0, 0,
+			      master_rp ? master_rp->id : 0);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl);
+}
+
+static int
+mlxsw_sp_acl_erp_table_relocate(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	struct mlxsw_sp_acl_erp *erp;
+	int err;
+
+	list_for_each_entry(erp, &erp_table->atcam_erps_list, list) {
+		err = mlxsw_sp_acl_erp_table_erp_add(erp_table, erp);
+		if (err)
+			goto err_table_erp_add;
+	}
+
+	return 0;
+
+err_table_erp_add:
+	list_for_each_entry_continue_reverse(erp, &erp_table->atcam_erps_list,
+					     list)
+		mlxsw_sp_acl_erp_table_erp_del(erp);
+	return err;
+}
+
+static int
+mlxsw_sp_acl_erp_table_expand(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	unsigned int num_erps, old_num_erps = erp_table->num_max_atcam_erps;
+	struct mlxsw_sp_acl_erp_core *erp_core = erp_table->erp_core;
+	unsigned long old_base_index = erp_table->base_index;
+	bool ctcam_le = erp_table->num_ctcam_erps > 0;
+	int err;
+
+	if (erp_table->num_atcam_erps < erp_table->num_max_atcam_erps)
+		return 0;
+
+	if (erp_table->num_max_atcam_erps == MLXSW_SP_ACL_ERP_MAX_PER_REGION)
+		return -ENOBUFS;
+
+	num_erps = old_num_erps + erp_core->num_erp_banks;
+	err = mlxsw_sp_acl_erp_table_alloc(erp_core, num_erps,
+					   erp_table->aregion->type,
+					   &erp_table->base_index);
+	if (err)
+		return err;
+	erp_table->num_max_atcam_erps = num_erps;
+
+	err = mlxsw_sp_acl_erp_table_relocate(erp_table);
+	if (err)
+		goto err_table_relocate;
+
+	err = mlxsw_sp_acl_erp_table_enable(erp_table, ctcam_le);
+	if (err)
+		goto err_table_enable;
+
+	mlxsw_sp_acl_erp_table_free(erp_core, old_num_erps,
+				    erp_table->aregion->type, old_base_index);
+
+	return 0;
+
+err_table_enable:
+err_table_relocate:
+	erp_table->num_max_atcam_erps = old_num_erps;
+	mlxsw_sp_acl_erp_table_free(erp_core, num_erps,
+				    erp_table->aregion->type,
+				    erp_table->base_index);
+	erp_table->base_index = old_base_index;
+	return err;
+}
+
+static int
+mlxsw_sp_acl_erp_region_table_trans(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	struct mlxsw_sp_acl_erp_core *erp_core = erp_table->erp_core;
+	struct mlxsw_sp_acl_erp *master_rp;
+	int err;
+
+	/* Initially, allocate a single eRP row. Expand later as needed */
+	err = mlxsw_sp_acl_erp_table_alloc(erp_core, erp_core->num_erp_banks,
+					   erp_table->aregion->type,
+					   &erp_table->base_index);
+	if (err)
+		return err;
+	erp_table->num_max_atcam_erps = erp_core->num_erp_banks;
+
+	/* Transition the sole RP currently configured (the master RP)
+	 * to the eRP table
+	 */
+	master_rp = mlxsw_sp_acl_erp_table_master_rp(erp_table);
+	if (!master_rp) {
+		err = -EINVAL;
+		goto err_table_master_rp;
+	}
+
+	/* Maintain the same eRP bank for the master RP, so that we
+	 * wouldn't need to update the bloom filter
+	 */
+	master_rp->index = master_rp->index % erp_core->num_erp_banks;
+	__set_bit(master_rp->index, erp_table->erp_index_bitmap);
+
+	err = mlxsw_sp_acl_erp_table_erp_add(erp_table, master_rp);
+	if (err)
+		goto err_table_master_rp_add;
+
+	err = mlxsw_sp_acl_erp_table_enable(erp_table, false);
+	if (err)
+		goto err_table_enable;
+
+	return 0;
+
+err_table_enable:
+	mlxsw_sp_acl_erp_table_erp_del(master_rp);
+err_table_master_rp_add:
+	__clear_bit(master_rp->index, erp_table->erp_index_bitmap);
+err_table_master_rp:
+	mlxsw_sp_acl_erp_table_free(erp_core, erp_table->num_max_atcam_erps,
+				    erp_table->aregion->type,
+				    erp_table->base_index);
+	return err;
+}
+
+static void
+mlxsw_sp_acl_erp_region_master_mask_trans(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	struct mlxsw_sp_acl_erp_core *erp_core = erp_table->erp_core;
+	struct mlxsw_sp_acl_erp *master_rp;
+
+	mlxsw_sp_acl_erp_table_disable(erp_table);
+	master_rp = mlxsw_sp_acl_erp_table_master_rp(erp_table);
+	if (!master_rp)
+		return;
+	mlxsw_sp_acl_erp_table_erp_del(master_rp);
+	__clear_bit(master_rp->index, erp_table->erp_index_bitmap);
+	mlxsw_sp_acl_erp_table_free(erp_core, erp_table->num_max_atcam_erps,
+				    erp_table->aregion->type,
+				    erp_table->base_index);
+}
+
+static int
+mlxsw_sp_acl_erp_region_erp_add(struct mlxsw_sp_acl_erp_table *erp_table,
+				struct mlxsw_sp_acl_erp *erp)
+{
+	struct mlxsw_sp_acl_tcam_region *region = erp_table->aregion->region;
+	struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp;
+	bool ctcam_le = erp_table->num_ctcam_erps > 0;
+	char pererp_pl[MLXSW_REG_PERERP_LEN];
+
+	mlxsw_reg_pererp_pack(pererp_pl, region->id, ctcam_le, true, 0,
+			      erp_table->base_index, 0);
+	mlxsw_reg_pererp_erp_vector_pack(pererp_pl, erp_table->erp_index_bitmap,
+					 MLXSW_SP_ACL_ERP_MAX_PER_REGION);
+	mlxsw_reg_pererp_erpt_vector_set(pererp_pl, erp->index, true);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl);
+}
+
+static void mlxsw_sp_acl_erp_region_erp_del(struct mlxsw_sp_acl_erp *erp)
+{
+	struct mlxsw_sp_acl_erp_table *erp_table = erp->erp_table;
+	struct mlxsw_sp_acl_tcam_region *region = erp_table->aregion->region;
+	struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp;
+	bool ctcam_le = erp_table->num_ctcam_erps > 0;
+	char pererp_pl[MLXSW_REG_PERERP_LEN];
+
+	mlxsw_reg_pererp_pack(pererp_pl, region->id, ctcam_le, true, 0,
+			      erp_table->base_index, 0);
+	mlxsw_reg_pererp_erp_vector_pack(pererp_pl, erp_table->erp_index_bitmap,
+					 MLXSW_SP_ACL_ERP_MAX_PER_REGION);
+	mlxsw_reg_pererp_erpt_vector_set(pererp_pl, erp->index, false);
+
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl);
+}
+
+static int
+mlxsw_sp_acl_erp_region_ctcam_enable(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	/* No need to re-enable lookup in the C-TCAM */
+	if (erp_table->num_ctcam_erps > 1)
+		return 0;
+
+	return mlxsw_sp_acl_erp_table_enable(erp_table, true);
+}
+
+static void
+mlxsw_sp_acl_erp_region_ctcam_disable(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	/* Only disable C-TCAM lookup when last C-TCAM eRP is deleted */
+	if (erp_table->num_ctcam_erps > 1)
+		return;
+
+	mlxsw_sp_acl_erp_table_enable(erp_table, false);
+}
+
+static void
+mlxsw_sp_acl_erp_ctcam_table_ops_set(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	switch (erp_table->num_atcam_erps) {
+	case 2:
+		/* Keep using the eRP table, but correctly set the
+		 * operations pointer so that when an A-TCAM eRP is
+		 * deleted we will transition to use the master mask
+		 */
+		erp_table->ops = &erp_two_masks_ops;
+		break;
+	case 1:
+		/* We only kept the eRP table because we had C-TCAM
+		 * eRPs in use. Now that the last C-TCAM eRP is gone we
+		 * can stop using the table and transition to use the
+		 * master mask
+		 */
+		mlxsw_sp_acl_erp_region_master_mask_trans(erp_table);
+		erp_table->ops = &erp_single_mask_ops;
+		break;
+	case 0:
+		/* There are no more eRPs of any kind used by the region
+		 * so free its eRP table and transition to initial state
+		 */
+		mlxsw_sp_acl_erp_table_disable(erp_table);
+		mlxsw_sp_acl_erp_table_free(erp_table->erp_core,
+					    erp_table->num_max_atcam_erps,
+					    erp_table->aregion->type,
+					    erp_table->base_index);
+		erp_table->ops = &erp_no_mask_ops;
+		break;
+	default:
+		break;
+	}
+}
+
+static struct mlxsw_sp_acl_erp *
+__mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
+				     struct mlxsw_sp_acl_erp_key *key)
+{
+	struct mlxsw_sp_acl_erp *erp;
+	int err;
+
+	erp = kzalloc(sizeof(*erp), GFP_KERNEL);
+	if (!erp)
+		return ERR_PTR(-ENOMEM);
+
+	memcpy(&erp->key, key, sizeof(*key));
+	bitmap_from_arr32(erp->mask_bitmap, (u32 *) key->mask,
+			  MLXSW_SP_ACL_TCAM_MASK_LEN);
+	refcount_set(&erp->refcnt, 1);
+	erp_table->num_ctcam_erps++;
+	erp->erp_table = erp_table;
+
+	err = mlxsw_sp_acl_erp_master_mask_set(erp_table, erp);
+	if (err)
+		goto err_master_mask_set;
+
+	err = rhashtable_insert_fast(&erp_table->erp_ht, &erp->ht_node,
+				     mlxsw_sp_acl_erp_ht_params);
+	if (err)
+		goto err_rhashtable_insert;
+
+	err = mlxsw_sp_acl_erp_region_ctcam_enable(erp_table);
+	if (err)
+		goto err_erp_region_ctcam_enable;
+
+	/* When C-TCAM is used, the eRP table must be used */
+	erp_table->ops = &erp_multiple_masks_ops;
+
+	return erp;
+
+err_erp_region_ctcam_enable:
+	rhashtable_remove_fast(&erp_table->erp_ht, &erp->ht_node,
+			       mlxsw_sp_acl_erp_ht_params);
+err_rhashtable_insert:
+	mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp);
+err_master_mask_set:
+	erp_table->num_ctcam_erps--;
+	kfree(erp);
+	return ERR_PTR(err);
+}
+
+static struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
+				   struct mlxsw_sp_acl_erp_key *key)
+{
+	struct mlxsw_sp_acl_erp *erp;
+	int err;
+
+	/* There is a special situation where we need to spill rules
+	 * into the C-TCAM, yet the region is still using a master
+	 * mask and thus not performing a lookup in the C-TCAM. This
+	 * can happen when two rules that only differ in priority - and
+	 * thus sharing the same key - are programmed. In this case
+	 * we transition the region to use an eRP table
+	 */
+	err = mlxsw_sp_acl_erp_region_table_trans(erp_table);
+	if (err)
+		return ERR_PTR(err);
+
+	erp = __mlxsw_sp_acl_erp_ctcam_mask_create(erp_table, key);
+	if (IS_ERR(erp)) {
+		err = PTR_ERR(erp);
+		goto err_erp_create;
+	}
+
+	return erp;
+
+err_erp_create:
+	mlxsw_sp_acl_erp_region_master_mask_trans(erp_table);
+	return ERR_PTR(err);
+}
+
+static void
+mlxsw_sp_acl_erp_ctcam_mask_destroy(struct mlxsw_sp_acl_erp *erp)
+{
+	struct mlxsw_sp_acl_erp_table *erp_table = erp->erp_table;
+
+	mlxsw_sp_acl_erp_region_ctcam_disable(erp_table);
+	rhashtable_remove_fast(&erp_table->erp_ht, &erp->ht_node,
+			       mlxsw_sp_acl_erp_ht_params);
+	mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp);
+	erp_table->num_ctcam_erps--;
+	kfree(erp);
+
+	/* Once the last C-TCAM eRP was destroyed, the state we
+	 * transition to depends on the number of A-TCAM eRPs currently
+	 * in use
+	 */
+	if (erp_table->num_ctcam_erps > 0)
+		return;
+	mlxsw_sp_acl_erp_ctcam_table_ops_set(erp_table);
+}
+
+static struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
+			     struct mlxsw_sp_acl_erp_key *key)
+{
+	struct mlxsw_sp_acl_erp *erp;
+	int err;
+
+	if (key->ctcam)
+		return __mlxsw_sp_acl_erp_ctcam_mask_create(erp_table, key);
+
+	/* Expand the eRP table for the new eRP, if needed */
+	err = mlxsw_sp_acl_erp_table_expand(erp_table);
+	if (err)
+		return ERR_PTR(err);
+
+	erp = mlxsw_sp_acl_erp_generic_create(erp_table, key);
+	if (IS_ERR(erp))
+		return erp;
+
+	err = mlxsw_sp_acl_erp_index_get(erp_table, &erp->index);
+	if (err)
+		goto err_erp_index_get;
+
+	err = mlxsw_sp_acl_erp_table_erp_add(erp_table, erp);
+	if (err)
+		goto err_table_erp_add;
+
+	err = mlxsw_sp_acl_erp_region_erp_add(erp_table, erp);
+	if (err)
+		goto err_region_erp_add;
+
+	erp_table->ops = &erp_multiple_masks_ops;
+
+	return erp;
+
+err_region_erp_add:
+	mlxsw_sp_acl_erp_table_erp_del(erp);
+err_table_erp_add:
+	mlxsw_sp_acl_erp_index_put(erp_table, erp->index);
+err_erp_index_get:
+	mlxsw_sp_acl_erp_generic_destroy(erp);
+	return ERR_PTR(err);
+}
+
+static void
+mlxsw_sp_acl_erp_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
+			      struct mlxsw_sp_acl_erp *erp)
+{
+	if (erp->key.ctcam)
+		return mlxsw_sp_acl_erp_ctcam_mask_destroy(erp);
+
+	mlxsw_sp_acl_erp_region_erp_del(erp);
+	mlxsw_sp_acl_erp_table_erp_del(erp);
+	mlxsw_sp_acl_erp_index_put(erp_table, erp->index);
+	mlxsw_sp_acl_erp_generic_destroy(erp);
+
+	if (erp_table->num_atcam_erps == 2 && erp_table->num_ctcam_erps == 0)
+		erp_table->ops = &erp_two_masks_ops;
+}
+
+static struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_second_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
+				    struct mlxsw_sp_acl_erp_key *key)
+{
+	struct mlxsw_sp_acl_erp *erp;
+	int err;
+
+	if (key->ctcam)
+		return mlxsw_sp_acl_erp_ctcam_mask_create(erp_table, key);
+
+	/* Transition to use eRP table instead of master mask */
+	err = mlxsw_sp_acl_erp_region_table_trans(erp_table);
+	if (err)
+		return ERR_PTR(err);
+
+	erp = mlxsw_sp_acl_erp_generic_create(erp_table, key);
+	if (IS_ERR(erp)) {
+		err = PTR_ERR(erp);
+		goto err_erp_create;
+	}
+
+	err = mlxsw_sp_acl_erp_index_get(erp_table, &erp->index);
+	if (err)
+		goto err_erp_index_get;
+
+	err = mlxsw_sp_acl_erp_table_erp_add(erp_table, erp);
+	if (err)
+		goto err_table_erp_add;
+
+	err = mlxsw_sp_acl_erp_region_erp_add(erp_table, erp);
+	if (err)
+		goto err_region_erp_add;
+
+	erp_table->ops = &erp_two_masks_ops;
+
+	return erp;
+
+err_region_erp_add:
+	mlxsw_sp_acl_erp_table_erp_del(erp);
+err_table_erp_add:
+	mlxsw_sp_acl_erp_index_put(erp_table, erp->index);
+err_erp_index_get:
+	mlxsw_sp_acl_erp_generic_destroy(erp);
+err_erp_create:
+	mlxsw_sp_acl_erp_region_master_mask_trans(erp_table);
+	return ERR_PTR(err);
+}
+
+static void
+mlxsw_sp_acl_erp_second_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
+				     struct mlxsw_sp_acl_erp *erp)
+{
+	if (erp->key.ctcam)
+		return mlxsw_sp_acl_erp_ctcam_mask_destroy(erp);
+
+	mlxsw_sp_acl_erp_region_erp_del(erp);
+	mlxsw_sp_acl_erp_table_erp_del(erp);
+	mlxsw_sp_acl_erp_index_put(erp_table, erp->index);
+	mlxsw_sp_acl_erp_generic_destroy(erp);
+	/* Transition to use master mask instead of eRP table */
+	mlxsw_sp_acl_erp_region_master_mask_trans(erp_table);
+
+	erp_table->ops = &erp_single_mask_ops;
+}
+
+static struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_first_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
+				   struct mlxsw_sp_acl_erp_key *key)
+{
+	struct mlxsw_sp_acl_erp *erp;
+
+	if (key->ctcam)
+		return ERR_PTR(-EINVAL);
+
+	erp = mlxsw_sp_acl_erp_generic_create(erp_table, key);
+	if (IS_ERR(erp))
+		return erp;
+
+	erp_table->ops = &erp_single_mask_ops;
+
+	return erp;
+}
+
+static void
+mlxsw_sp_acl_erp_first_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
+				    struct mlxsw_sp_acl_erp *erp)
+{
+	mlxsw_sp_acl_erp_generic_destroy(erp);
+	erp_table->ops = &erp_no_mask_ops;
+}
+
+static void
+mlxsw_sp_acl_erp_no_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
+				 struct mlxsw_sp_acl_erp *erp)
+{
+	WARN_ON(1);
+}
+
+struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_get(struct mlxsw_sp_acl_atcam_region *aregion,
+		     const char *mask, bool ctcam)
+{
+	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
+	struct mlxsw_sp_acl_erp_key key;
+	struct mlxsw_sp_acl_erp *erp;
+
+	/* eRPs are allocated from a shared resource, but currently all
+	 * allocations are done under RTNL.
+	 */
+	ASSERT_RTNL();
+
+	memcpy(key.mask, mask, MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN);
+	key.ctcam = ctcam;
+	erp = rhashtable_lookup_fast(&erp_table->erp_ht, &key,
+				     mlxsw_sp_acl_erp_ht_params);
+	if (erp) {
+		refcount_inc(&erp->refcnt);
+		return erp;
+	}
+
+	return erp_table->ops->erp_create(erp_table, &key);
+}
+
+void mlxsw_sp_acl_erp_put(struct mlxsw_sp_acl_atcam_region *aregion,
+			  struct mlxsw_sp_acl_erp *erp)
+{
+	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
+
+	ASSERT_RTNL();
+
+	if (!refcount_dec_and_test(&erp->refcnt))
+		return;
+
+	erp_table->ops->erp_destroy(erp_table, erp);
+}
+
+static struct mlxsw_sp_acl_erp_table *
+mlxsw_sp_acl_erp_table_create(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	struct mlxsw_sp_acl_erp_table *erp_table;
+	int err;
+
+	erp_table = kzalloc(sizeof(*erp_table), GFP_KERNEL);
+	if (!erp_table)
+		return ERR_PTR(-ENOMEM);
+
+	err = rhashtable_init(&erp_table->erp_ht, &mlxsw_sp_acl_erp_ht_params);
+	if (err)
+		goto err_rhashtable_init;
+
+	erp_table->erp_core = aregion->atcam->erp_core;
+	erp_table->ops = &erp_no_mask_ops;
+	INIT_LIST_HEAD(&erp_table->atcam_erps_list);
+	erp_table->aregion = aregion;
+
+	return erp_table;
+
+err_rhashtable_init:
+	kfree(erp_table);
+	return ERR_PTR(err);
+}
+
+static void
+mlxsw_sp_acl_erp_table_destroy(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	WARN_ON(!list_empty(&erp_table->atcam_erps_list));
+	rhashtable_destroy(&erp_table->erp_ht);
+	kfree(erp_table);
+}
+
+static int
+mlxsw_sp_acl_erp_master_mask_init(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	struct mlxsw_sp *mlxsw_sp = aregion->region->mlxsw_sp;
+	char percr_pl[MLXSW_REG_PERCR_LEN];
+
+	mlxsw_reg_percr_pack(percr_pl, aregion->region->id);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(percr), percr_pl);
+}
+
+static int
+mlxsw_sp_acl_erp_region_param_init(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	struct mlxsw_sp *mlxsw_sp = aregion->region->mlxsw_sp;
+	char pererp_pl[MLXSW_REG_PERERP_LEN];
+
+	mlxsw_reg_pererp_pack(pererp_pl, aregion->region->id, false, false, 0,
+			      0, 0);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl);
+}
+
+int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	struct mlxsw_sp_acl_erp_table *erp_table;
+	int err;
+
+	erp_table = mlxsw_sp_acl_erp_table_create(aregion);
+	if (IS_ERR(erp_table))
+		return PTR_ERR(erp_table);
+	aregion->erp_table = erp_table;
+
+	/* Initialize the region's master mask to all zeroes */
+	err = mlxsw_sp_acl_erp_master_mask_init(aregion);
+	if (err)
+		goto err_erp_master_mask_init;
+
+	/* Initialize the region to not use the eRP table */
+	err = mlxsw_sp_acl_erp_region_param_init(aregion);
+	if (err)
+		goto err_erp_region_param_init;
+
+	return 0;
+
+err_erp_region_param_init:
+err_erp_master_mask_init:
+	mlxsw_sp_acl_erp_table_destroy(erp_table);
+	return err;
+}
+
+void mlxsw_sp_acl_erp_region_fini(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	mlxsw_sp_acl_erp_table_destroy(aregion->erp_table);
+}
+
+static int
+mlxsw_sp_acl_erp_tables_sizes_query(struct mlxsw_sp *mlxsw_sp,
+				    struct mlxsw_sp_acl_erp_core *erp_core)
+{
+	unsigned int size;
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_ERPT_ENTRIES_2KB) ||
+	    !MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_ERPT_ENTRIES_4KB) ||
+	    !MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_ERPT_ENTRIES_8KB) ||
+	    !MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_ERPT_ENTRIES_12KB))
+		return -EIO;
+
+	size = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_ERPT_ENTRIES_2KB);
+	erp_core->erpt_entries_size[MLXSW_SP_ACL_ATCAM_REGION_TYPE_2KB] = size;
+
+	size = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_ERPT_ENTRIES_4KB);
+	erp_core->erpt_entries_size[MLXSW_SP_ACL_ATCAM_REGION_TYPE_4KB] = size;
+
+	size = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_ERPT_ENTRIES_8KB);
+	erp_core->erpt_entries_size[MLXSW_SP_ACL_ATCAM_REGION_TYPE_8KB] = size;
+
+	size = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_ERPT_ENTRIES_12KB);
+	erp_core->erpt_entries_size[MLXSW_SP_ACL_ATCAM_REGION_TYPE_12KB] = size;
+
+	return 0;
+}
+
+static int mlxsw_sp_acl_erp_tables_init(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp_acl_erp_core *erp_core)
+{
+	unsigned int erpt_bank_size;
+	int err;
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_ERPT_BANK_SIZE) ||
+	    !MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_ERPT_BANKS))
+		return -EIO;
+	erpt_bank_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
+					    ACL_MAX_ERPT_BANK_SIZE);
+	erp_core->num_erp_banks = MLXSW_CORE_RES_GET(mlxsw_sp->core,
+						     ACL_MAX_ERPT_BANKS);
+
+	erp_core->erp_tables = gen_pool_create(0, -1);
+	if (!erp_core->erp_tables)
+		return -ENOMEM;
+	gen_pool_set_algo(erp_core->erp_tables, gen_pool_best_fit, NULL);
+
+	err = gen_pool_add(erp_core->erp_tables,
+			   MLXSW_SP_ACL_ERP_GENALLOC_OFFSET, erpt_bank_size,
+			   -1);
+	if (err)
+		goto err_gen_pool_add;
+
+	/* Different regions require masks of different sizes */
+	err = mlxsw_sp_acl_erp_tables_sizes_query(mlxsw_sp, erp_core);
+	if (err)
+		goto err_erp_tables_sizes_query;
+
+	return 0;
+
+err_erp_tables_sizes_query:
+err_gen_pool_add:
+	gen_pool_destroy(erp_core->erp_tables);
+	return err;
+}
+
+static void mlxsw_sp_acl_erp_tables_fini(struct mlxsw_sp *mlxsw_sp,
+					 struct mlxsw_sp_acl_erp_core *erp_core)
+{
+	gen_pool_destroy(erp_core->erp_tables);
+}
+
+int mlxsw_sp_acl_erps_init(struct mlxsw_sp *mlxsw_sp,
+			   struct mlxsw_sp_acl_atcam *atcam)
+{
+	struct mlxsw_sp_acl_erp_core *erp_core;
+	int err;
+
+	erp_core = kzalloc(sizeof(*erp_core), GFP_KERNEL);
+	if (!erp_core)
+		return -ENOMEM;
+	erp_core->mlxsw_sp = mlxsw_sp;
+	atcam->erp_core = erp_core;
+
+	err = mlxsw_sp_acl_erp_tables_init(mlxsw_sp, erp_core);
+	if (err)
+		goto err_erp_tables_init;
+
+	return 0;
+
+err_erp_tables_init:
+	kfree(erp_core);
+	return err;
+}
+
+void mlxsw_sp_acl_erps_fini(struct mlxsw_sp *mlxsw_sp,
+			    struct mlxsw_sp_acl_atcam *atcam)
+{
+	mlxsw_sp_acl_erp_tables_fini(mlxsw_sp, atcam->erp_core);
+	kfree(atcam->erp_core);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
index 510ce48d87f7..e47d1d286e93 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
@@ -1,46 +1,12 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
- * Copyright (c) 2017, 2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include "spectrum_acl_flex_actions.h"
 #include "core_acl_flex_actions.h"
 #include "spectrum_span.h"
 
-#define MLXSW_SP_KVDL_ACT_EXT_SIZE 1
-
 static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
-				     char *enc_actions, bool is_first)
+				     char *enc_actions, bool is_first, bool ca)
 {
 	struct mlxsw_sp *mlxsw_sp = priv;
 	char pefa_pl[MLXSW_REG_PEFA_LEN];
@@ -53,11 +19,11 @@ static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
 	if (is_first)
 		return 0;
 
-	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ACT_EXT_SIZE,
-				  &kvdl_index);
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
+				  1, &kvdl_index);
 	if (err)
 		return err;
-	mlxsw_reg_pefa_pack(pefa_pl, kvdl_index, enc_actions);
+	mlxsw_reg_pefa_pack(pefa_pl, kvdl_index, ca, enc_actions);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pefa), pefa_pl);
 	if (err)
 		goto err_pefa_write;
@@ -65,10 +31,25 @@ static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
 	return 0;
 
 err_pefa_write:
-	mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
+			   1, kvdl_index);
 	return err;
 }
 
+static int mlxsw_sp1_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
+				      char *enc_actions, bool is_first)
+{
+	return mlxsw_sp_act_kvdl_set_add(priv, p_kvdl_index, enc_actions,
+					 is_first, false);
+}
+
+static int mlxsw_sp2_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
+				      char *enc_actions, bool is_first)
+{
+	return mlxsw_sp_act_kvdl_set_add(priv, p_kvdl_index, enc_actions,
+					 is_first, true);
+}
+
 static void mlxsw_sp_act_kvdl_set_del(void *priv, u32 kvdl_index,
 				      bool is_first)
 {
@@ -76,7 +57,29 @@ static void mlxsw_sp_act_kvdl_set_del(void *priv, u32 kvdl_index,
 
 	if (is_first)
 		return;
-	mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
+			   1, kvdl_index);
+}
+
+static int mlxsw_sp1_act_kvdl_set_activity_get(void *priv, u32 kvdl_index,
+					       bool *activity)
+{
+	return -EOPNOTSUPP;
+}
+
+static int mlxsw_sp2_act_kvdl_set_activity_get(void *priv, u32 kvdl_index,
+					       bool *activity)
+{
+	struct mlxsw_sp *mlxsw_sp = priv;
+	char pefa_pl[MLXSW_REG_PEFA_LEN];
+	int err;
+
+	mlxsw_reg_pefa_pack(pefa_pl, kvdl_index, true, NULL);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(pefa), pefa_pl);
+	if (err)
+		return err;
+	mlxsw_reg_pefa_unpack(pefa_pl, activity);
+	return 0;
 }
 
 static int mlxsw_sp_act_kvdl_fwd_entry_add(void *priv, u32 *p_kvdl_index,
@@ -87,7 +90,8 @@ static int mlxsw_sp_act_kvdl_fwd_entry_add(void *priv, u32 *p_kvdl_index,
 	u32 kvdl_index;
 	int err;
 
-	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, 1, &kvdl_index);
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_PBS,
+				  1, &kvdl_index);
 	if (err)
 		return err;
 	mlxsw_reg_ppbs_pack(ppbs_pl, kvdl_index, local_port);
@@ -98,7 +102,8 @@ static int mlxsw_sp_act_kvdl_fwd_entry_add(void *priv, u32 *p_kvdl_index,
 	return 0;
 
 err_ppbs_write:
-	mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_PBS,
+			   1, kvdl_index);
 	return err;
 }
 
@@ -106,7 +111,8 @@ static void mlxsw_sp_act_kvdl_fwd_entry_del(void *priv, u32 kvdl_index)
 {
 	struct mlxsw_sp *mlxsw_sp = priv;
 
-	mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_PBS,
+			   1, kvdl_index);
 }
 
 static int
@@ -154,22 +160,36 @@ mlxsw_sp_act_mirror_del(void *priv, u8 local_in_port, int span_id, bool ingress)
 	mlxsw_sp_span_mirror_del(in_port, span_id, type, false);
 }
 
-static const struct mlxsw_afa_ops mlxsw_sp_act_afa_ops = {
-	.kvdl_set_add		= mlxsw_sp_act_kvdl_set_add,
+const struct mlxsw_afa_ops mlxsw_sp1_act_afa_ops = {
+	.kvdl_set_add		= mlxsw_sp1_act_kvdl_set_add,
+	.kvdl_set_del		= mlxsw_sp_act_kvdl_set_del,
+	.kvdl_set_activity_get	= mlxsw_sp1_act_kvdl_set_activity_get,
+	.kvdl_fwd_entry_add	= mlxsw_sp_act_kvdl_fwd_entry_add,
+	.kvdl_fwd_entry_del	= mlxsw_sp_act_kvdl_fwd_entry_del,
+	.counter_index_get	= mlxsw_sp_act_counter_index_get,
+	.counter_index_put	= mlxsw_sp_act_counter_index_put,
+	.mirror_add		= mlxsw_sp_act_mirror_add,
+	.mirror_del		= mlxsw_sp_act_mirror_del,
+};
+
+const struct mlxsw_afa_ops mlxsw_sp2_act_afa_ops = {
+	.kvdl_set_add		= mlxsw_sp2_act_kvdl_set_add,
 	.kvdl_set_del		= mlxsw_sp_act_kvdl_set_del,
+	.kvdl_set_activity_get	= mlxsw_sp2_act_kvdl_set_activity_get,
 	.kvdl_fwd_entry_add	= mlxsw_sp_act_kvdl_fwd_entry_add,
 	.kvdl_fwd_entry_del	= mlxsw_sp_act_kvdl_fwd_entry_del,
 	.counter_index_get	= mlxsw_sp_act_counter_index_get,
 	.counter_index_put	= mlxsw_sp_act_counter_index_put,
 	.mirror_add		= mlxsw_sp_act_mirror_add,
 	.mirror_del		= mlxsw_sp_act_mirror_del,
+	.dummy_first_set	= true,
 };
 
 int mlxsw_sp_afa_init(struct mlxsw_sp *mlxsw_sp)
 {
 	mlxsw_sp->afa = mlxsw_afa_create(MLXSW_CORE_RES_GET(mlxsw_sp->core,
 							    ACL_ACTIONS_PER_SET),
-					 &mlxsw_sp_act_afa_ops, mlxsw_sp);
+					 mlxsw_sp->afa_ops, mlxsw_sp);
 	return PTR_ERR_OR_ZERO(mlxsw_sp->afa);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.h
index bd6d552d95b9..fe436d816d0c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.h
@@ -1,37 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_SPECTRUM_ACL_FLEX_ACTIONS_H
 #define _MLXSW_SPECTRUM_ACL_FLEX_ACTIONS_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
new file mode 100644
index 000000000000..d409b09ba8df
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
@@ -0,0 +1,285 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include "spectrum.h"
+#include "item.h"
+#include "core_acl_flex_keys.h"
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_dmac[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(DMAC_32_47, 0x00, 2),
+	MLXSW_AFK_ELEMENT_INST_BUF(DMAC_0_31, 0x02, 4),
+	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
+	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_32_47, 0x00, 2),
+	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_0_31, 0x02, 4),
+	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
+	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac_ex[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_32_47, 0x02, 2),
+	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_0_31, 0x04, 4),
+	MLXSW_AFK_ELEMENT_INST_U32(ETHERTYPE, 0x0C, 0, 16),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_sip[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_dip[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_0_31, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_U32(IP_ECN, 0x04, 4, 2),
+	MLXSW_AFK_ELEMENT_INST_U32(IP_TTL_, 0x04, 24, 8),
+	MLXSW_AFK_ELEMENT_INST_U32(IP_DSCP, 0x08, 0, 6),
+	MLXSW_AFK_ELEMENT_INST_U32(TCP_FLAGS, 0x08, 8, 9), /* TCP_CONTROL+TCP_ECN */
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_ex[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x00, 0, 12),
+	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 29, 3),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_L4_PORT, 0x08, 0, 16),
+	MLXSW_AFK_ELEMENT_INST_U32(DST_L4_PORT, 0x0C, 0, 16),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_dip[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_32_63, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_0_31, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_ex1[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_96_127, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_64_95, 0x04, 4),
+	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_sip[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_32_63, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_sip_ex[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_96_127, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_64_95, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_packet_type[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(ETHERTYPE, 0x00, 0, 16),
+};
+
+static const struct mlxsw_afk_block mlxsw_sp1_afk_blocks[] = {
+	MLXSW_AFK_BLOCK(0x10, mlxsw_sp_afk_element_info_l2_dmac),
+	MLXSW_AFK_BLOCK(0x11, mlxsw_sp_afk_element_info_l2_smac),
+	MLXSW_AFK_BLOCK(0x12, mlxsw_sp_afk_element_info_l2_smac_ex),
+	MLXSW_AFK_BLOCK(0x30, mlxsw_sp_afk_element_info_ipv4_sip),
+	MLXSW_AFK_BLOCK(0x31, mlxsw_sp_afk_element_info_ipv4_dip),
+	MLXSW_AFK_BLOCK(0x32, mlxsw_sp_afk_element_info_ipv4),
+	MLXSW_AFK_BLOCK(0x33, mlxsw_sp_afk_element_info_ipv4_ex),
+	MLXSW_AFK_BLOCK(0x60, mlxsw_sp_afk_element_info_ipv6_dip),
+	MLXSW_AFK_BLOCK(0x65, mlxsw_sp_afk_element_info_ipv6_ex1),
+	MLXSW_AFK_BLOCK(0x62, mlxsw_sp_afk_element_info_ipv6_sip),
+	MLXSW_AFK_BLOCK(0x63, mlxsw_sp_afk_element_info_ipv6_sip_ex),
+	MLXSW_AFK_BLOCK(0xB0, mlxsw_sp_afk_element_info_packet_type),
+};
+
+#define MLXSW_SP1_AFK_KEY_BLOCK_SIZE 16
+
+static void mlxsw_sp1_afk_encode_block(char *block, int block_index,
+				       char *output)
+{
+	unsigned int offset = block_index * MLXSW_SP1_AFK_KEY_BLOCK_SIZE;
+	char *output_indexed = output + offset;
+
+	memcpy(output_indexed, block, MLXSW_SP1_AFK_KEY_BLOCK_SIZE);
+}
+
+const struct mlxsw_afk_ops mlxsw_sp1_afk_ops = {
+	.blocks		= mlxsw_sp1_afk_blocks,
+	.blocks_count	= ARRAY_SIZE(mlxsw_sp1_afk_blocks),
+	.encode_block	= mlxsw_sp1_afk_encode_block,
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_0[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(DMAC_0_31, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_1[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_0_31, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_2[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_32_47, 0x04, 2),
+	MLXSW_AFK_ELEMENT_INST_BUF(DMAC_32_47, 0x06, 2),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_3[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x00, 0, 3),
+	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x04, 16, 12),
+	MLXSW_AFK_ELEMENT_INST_BUF(DMAC_32_47, 0x06, 2),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_4[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x00, 0, 3),
+	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x04, 16, 12),
+	MLXSW_AFK_ELEMENT_INST_U32(ETHERTYPE, 0x04, 0, 16),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_5[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x04, 16, 12),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x04, 0, 8), /* RX_ACL_SYSTEM_PORT */
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_0[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_0_31, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_1[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_2[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(IP_DSCP, 0x04, 0, 6),
+	MLXSW_AFK_ELEMENT_INST_U32(IP_ECN, 0x04, 6, 2),
+	MLXSW_AFK_ELEMENT_INST_U32(IP_TTL_, 0x04, 8, 8),
+	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x04, 16, 8),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_0[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_32_63, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_1[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_64_95, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_2[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_96_127, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_3[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_32_63, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_4[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_64_95, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_5[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_96_127, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l4_0[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_L4_PORT, 0x04, 16, 16),
+	MLXSW_AFK_ELEMENT_INST_U32(DST_L4_PORT, 0x04, 0, 16),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l4_2[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(TCP_FLAGS, 0x04, 16, 9), /* TCP_CONTROL + TCP_ECN */
+};
+
+static const struct mlxsw_afk_block mlxsw_sp2_afk_blocks[] = {
+	MLXSW_AFK_BLOCK(0x10, mlxsw_sp_afk_element_info_mac_0),
+	MLXSW_AFK_BLOCK(0x11, mlxsw_sp_afk_element_info_mac_1),
+	MLXSW_AFK_BLOCK(0x12, mlxsw_sp_afk_element_info_mac_2),
+	MLXSW_AFK_BLOCK(0x13, mlxsw_sp_afk_element_info_mac_3),
+	MLXSW_AFK_BLOCK(0x14, mlxsw_sp_afk_element_info_mac_4),
+	MLXSW_AFK_BLOCK(0x15, mlxsw_sp_afk_element_info_mac_5),
+	MLXSW_AFK_BLOCK(0x38, mlxsw_sp_afk_element_info_ipv4_0),
+	MLXSW_AFK_BLOCK(0x39, mlxsw_sp_afk_element_info_ipv4_1),
+	MLXSW_AFK_BLOCK(0x3A, mlxsw_sp_afk_element_info_ipv4_2),
+	MLXSW_AFK_BLOCK(0x40, mlxsw_sp_afk_element_info_ipv6_0),
+	MLXSW_AFK_BLOCK(0x41, mlxsw_sp_afk_element_info_ipv6_1),
+	MLXSW_AFK_BLOCK(0x42, mlxsw_sp_afk_element_info_ipv6_2),
+	MLXSW_AFK_BLOCK(0x43, mlxsw_sp_afk_element_info_ipv6_3),
+	MLXSW_AFK_BLOCK(0x44, mlxsw_sp_afk_element_info_ipv6_4),
+	MLXSW_AFK_BLOCK(0x45, mlxsw_sp_afk_element_info_ipv6_5),
+	MLXSW_AFK_BLOCK(0x90, mlxsw_sp_afk_element_info_l4_0),
+	MLXSW_AFK_BLOCK(0x92, mlxsw_sp_afk_element_info_l4_2),
+};
+
+#define MLXSW_SP2_AFK_BITS_PER_BLOCK 36
+
+/* A block in Spectrum-2 is of the following form:
+ *
+ * +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+ * |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |35|34|33|32|
+ * +-----------------------------------------------------------------------------------------------+
+ * |31|30|29|28|27|26|25|24|23|22|21|20|19|18|17|16|15|14|13|12|11|10| 9| 8| 7| 6| 5| 4| 3| 2| 1| 0|
+ * +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+ */
+MLXSW_ITEM64(sp2_afk, block, value, 0x00, 0, MLXSW_SP2_AFK_BITS_PER_BLOCK);
+
+/* The key / mask block layout in Spectrum-2 is of the following form:
+ *
+ * +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+ * |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |                block11_high                   |
+ * +-----------------------------------------------------------------------------------------------+
+ * |                    block11_low                               |         block10_high           |
+ * +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+ * ...
+ */
+
+struct mlxsw_sp2_afk_block_layout {
+	unsigned short offset;
+	struct mlxsw_item item;
+};
+
+#define MLXSW_SP2_AFK_BLOCK_LAYOUT(_block, _offset, _shift)			\
+	{									\
+		.offset = _offset,						\
+		{								\
+			.shift = _shift,					\
+			.size = {.bits = MLXSW_SP2_AFK_BITS_PER_BLOCK},		\
+			.name = #_block,					\
+		}								\
+	}									\
+
+static const struct mlxsw_sp2_afk_block_layout mlxsw_sp2_afk_blocks_layout[] = {
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block0, 0x30, 0),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block1, 0x2C, 4),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block2, 0x28, 8),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block3, 0x24, 12),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block4, 0x20, 16),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block5, 0x1C, 20),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block6, 0x18, 24),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block7, 0x14, 28),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block8, 0x0C, 0),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block9, 0x08, 4),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block10, 0x04, 8),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block11, 0x00, 12),
+};
+
+static void mlxsw_sp2_afk_encode_block(char *block, int block_index,
+				       char *output)
+{
+	u64 block_value = mlxsw_sp2_afk_block_value_get(block);
+	const struct mlxsw_sp2_afk_block_layout *block_layout;
+
+	if (WARN_ON(block_index < 0 ||
+		    block_index >= ARRAY_SIZE(mlxsw_sp2_afk_blocks_layout)))
+		return;
+
+	block_layout = &mlxsw_sp2_afk_blocks_layout[block_index];
+	__mlxsw_item_set64(output + block_layout->offset,
+			   &block_layout->item, 0, block_value);
+}
+
+const struct mlxsw_afk_ops mlxsw_sp2_afk_ops = {
+	.blocks		= mlxsw_sp2_afk_blocks,
+	.blocks_count	= ARRAY_SIZE(mlxsw_sp2_afk_blocks),
+	.encode_block	= mlxsw_sp2_afk_encode_block,
+};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
deleted file mode 100644
index fb8031828454..000000000000
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
+++ /dev/null
@@ -1,124 +0,0 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
-
-#ifndef _MLXSW_SPECTRUM_ACL_FLEX_KEYS_H
-#define _MLXSW_SPECTRUM_ACL_FLEX_KEYS_H
-
-#include "core_acl_flex_keys.h"
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_dmac[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(DMAC, 0x00, 6),
-	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
-	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(SMAC, 0x00, 6),
-	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
-	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac_ex[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(SMAC, 0x02, 6),
-	MLXSW_AFK_ELEMENT_INST_U32(ETHERTYPE, 0x0C, 0, 16),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_sip[] = {
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_IP4, 0x00, 0, 32),
-	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_dip[] = {
-	MLXSW_AFK_ELEMENT_INST_U32(DST_IP4, 0x00, 0, 32),
-	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4[] = {
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_IP4, 0x00, 0, 32),
-	MLXSW_AFK_ELEMENT_INST_U32(IP_ECN, 0x04, 4, 2),
-	MLXSW_AFK_ELEMENT_INST_U32(IP_TTL_, 0x04, 24, 8),
-	MLXSW_AFK_ELEMENT_INST_U32(IP_DSCP, 0x08, 0, 6),
-	MLXSW_AFK_ELEMENT_INST_U32(TCP_FLAGS, 0x08, 8, 9), /* TCP_CONTROL+TCP_ECN */
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_ex[] = {
-	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x00, 0, 12),
-	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 29, 3),
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_L4_PORT, 0x08, 0, 16),
-	MLXSW_AFK_ELEMENT_INST_U32(DST_L4_PORT, 0x0C, 0, 16),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_dip[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP6_LO, 0x00, 8),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_ex1[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP6_HI, 0x00, 8),
-	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_sip[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP6_LO, 0x00, 8),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_sip_ex[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP6_HI, 0x00, 8),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_packet_type[] = {
-	MLXSW_AFK_ELEMENT_INST_U32(ETHERTYPE, 0x00, 0, 16),
-};
-
-static const struct mlxsw_afk_block mlxsw_sp_afk_blocks[] = {
-	MLXSW_AFK_BLOCK(0x10, mlxsw_sp_afk_element_info_l2_dmac),
-	MLXSW_AFK_BLOCK(0x11, mlxsw_sp_afk_element_info_l2_smac),
-	MLXSW_AFK_BLOCK(0x12, mlxsw_sp_afk_element_info_l2_smac_ex),
-	MLXSW_AFK_BLOCK(0x30, mlxsw_sp_afk_element_info_ipv4_sip),
-	MLXSW_AFK_BLOCK(0x31, mlxsw_sp_afk_element_info_ipv4_dip),
-	MLXSW_AFK_BLOCK(0x32, mlxsw_sp_afk_element_info_ipv4),
-	MLXSW_AFK_BLOCK(0x33, mlxsw_sp_afk_element_info_ipv4_ex),
-	MLXSW_AFK_BLOCK(0x60, mlxsw_sp_afk_element_info_ipv6_dip),
-	MLXSW_AFK_BLOCK(0x65, mlxsw_sp_afk_element_info_ipv6_ex1),
-	MLXSW_AFK_BLOCK(0x62, mlxsw_sp_afk_element_info_ipv6_sip),
-	MLXSW_AFK_BLOCK(0x63, mlxsw_sp_afk_element_info_ipv6_sip_ex),
-	MLXSW_AFK_BLOCK(0xB0, mlxsw_sp_afk_element_info_packet_type),
-};
-
-#define MLXSW_SP_AFK_BLOCKS_COUNT ARRAY_SIZE(mlxsw_sp_afk_blocks)
-
-#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index ad1b548e3cac..e171513bb32a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -39,25 +8,25 @@
 #include <linux/list.h>
 #include <linux/rhashtable.h>
 #include <linux/netdevice.h>
-#include <linux/parman.h>
 
 #include "reg.h"
 #include "core.h"
 #include "resources.h"
 #include "spectrum.h"
+#include "spectrum_acl_tcam.h"
 #include "core_acl_flex_keys.h"
 
-struct mlxsw_sp_acl_tcam {
-	unsigned long *used_regions; /* bit array */
-	unsigned int max_regions;
-	unsigned long *used_groups;  /* bit array */
-	unsigned int max_groups;
-	unsigned int max_group_size;
-};
+size_t mlxsw_sp_acl_tcam_priv_size(struct mlxsw_sp *mlxsw_sp)
+{
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+
+	return ops->priv_size;
+}
 
-static int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
+int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp,
+			   struct mlxsw_sp_acl_tcam *tcam)
 {
-	struct mlxsw_sp_acl_tcam *tcam = priv;
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 	u64 max_tcam_regions;
 	u64 max_regions;
 	u64 max_groups;
@@ -88,21 +57,53 @@ static int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
 	tcam->max_groups = max_groups;
 	tcam->max_group_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
 						 ACL_MAX_GROUP_SIZE);
+
+	err = ops->init(mlxsw_sp, tcam->priv, tcam);
+	if (err)
+		goto err_tcam_init;
+
 	return 0;
 
+err_tcam_init:
+	kfree(tcam->used_groups);
 err_alloc_used_groups:
 	kfree(tcam->used_regions);
 	return err;
 }
 
-static void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
+void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp,
+			    struct mlxsw_sp_acl_tcam *tcam)
 {
-	struct mlxsw_sp_acl_tcam *tcam = priv;
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 
+	ops->fini(mlxsw_sp, tcam->priv);
 	kfree(tcam->used_groups);
 	kfree(tcam->used_regions);
 }
 
+int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_acl_rule_info *rulei,
+				   u32 *priority, bool fillup_priority)
+{
+	u64 max_priority;
+
+	if (!fillup_priority) {
+		*priority = 0;
+		return 0;
+	}
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, KVD_SIZE))
+		return -EIO;
+
+	max_priority = MLXSW_CORE_RES_GET(mlxsw_sp->core, KVD_SIZE);
+	if (rulei->priority > max_priority)
+		return -EINVAL;
+
+	/* Unlike in TC, in HW, higher number means higher priority. */
+	*priority = max_priority - rulei->priority;
+	return 0;
+}
+
 static int mlxsw_sp_acl_tcam_region_id_get(struct mlxsw_sp_acl_tcam *tcam,
 					   u16 *p_id)
 {
@@ -157,37 +158,25 @@ struct mlxsw_sp_acl_tcam_group {
 	struct mlxsw_sp_acl_tcam_group_ops *ops;
 	const struct mlxsw_sp_acl_tcam_pattern *patterns;
 	unsigned int patterns_count;
-};
-
-struct mlxsw_sp_acl_tcam_region {
-	struct list_head list; /* Member of a TCAM group */
-	struct list_head chunk_list; /* List of chunks under this region */
-	struct parman *parman;
-	struct mlxsw_sp *mlxsw_sp;
-	struct mlxsw_sp_acl_tcam_group *group;
-	u16 id; /* ACL ID and region ID - they are same */
-	char tcam_region_info[MLXSW_REG_PXXX_TCAM_REGION_INFO_LEN];
-	struct mlxsw_afk_key_info *key_info;
-	struct {
-		struct parman_prio parman_prio;
-		struct parman_item parman_item;
-		struct mlxsw_sp_acl_rule_info *rulei;
-	} catchall;
+	bool tmplt_elusage_set;
+	struct mlxsw_afk_element_usage tmplt_elusage;
 };
 
 struct mlxsw_sp_acl_tcam_chunk {
 	struct list_head list; /* Member of a TCAM region */
 	struct rhash_head ht_node; /* Member of a chunk HT */
 	unsigned int priority; /* Priority within the region and group */
-	struct parman_prio parman_prio;
 	struct mlxsw_sp_acl_tcam_group *group;
 	struct mlxsw_sp_acl_tcam_region *region;
 	unsigned int ref_count;
+	unsigned long priv[0];
+	/* priv has to be always the last item */
 };
 
 struct mlxsw_sp_acl_tcam_entry {
-	struct parman_item parman_item;
 	struct mlxsw_sp_acl_tcam_chunk *chunk;
+	unsigned long priv[0];
+	/* priv has to be always the last item */
 };
 
 static const struct rhashtable_params mlxsw_sp_acl_tcam_chunk_ht_params = {
@@ -216,13 +205,19 @@ mlxsw_sp_acl_tcam_group_add(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_tcam *tcam,
 			    struct mlxsw_sp_acl_tcam_group *group,
 			    const struct mlxsw_sp_acl_tcam_pattern *patterns,
-			    unsigned int patterns_count)
+			    unsigned int patterns_count,
+			    struct mlxsw_afk_element_usage *tmplt_elusage)
 {
 	int err;
 
 	group->tcam = tcam;
 	group->patterns = patterns;
 	group->patterns_count = patterns_count;
+	if (tmplt_elusage) {
+		group->tmplt_elusage_set = true;
+		memcpy(&group->tmplt_elusage, tmplt_elusage,
+		       sizeof(group->tmplt_elusage));
+	}
 	INIT_LIST_HEAD(&group->region_list);
 	err = mlxsw_sp_acl_tcam_group_id_get(tcam, &group->id);
 	if (err)
@@ -431,6 +426,15 @@ mlxsw_sp_acl_tcam_group_use_patterns(struct mlxsw_sp_acl_tcam_group *group,
 	const struct mlxsw_sp_acl_tcam_pattern *pattern;
 	int i;
 
+	/* In case the template is set, we don't have to look up the pattern
+	 * and just use the template.
+	 */
+	if (group->tmplt_elusage_set) {
+		memcpy(out, &group->tmplt_elusage, sizeof(*out));
+		WARN_ON(!mlxsw_afk_element_usage_subset(elusage, out));
+		return;
+	}
+
 	for (i = 0; i < group->patterns_count; i++) {
 		pattern = &group->patterns[i];
 		mlxsw_afk_element_usage_fill(out, pattern->elements,
@@ -441,9 +445,6 @@ mlxsw_sp_acl_tcam_group_use_patterns(struct mlxsw_sp_acl_tcam_group *group,
 	memcpy(out, elusage, sizeof(*out));
 }
 
-#define MLXSW_SP_ACL_TCAM_REGION_BASE_COUNT 16
-#define MLXSW_SP_ACL_TCAM_REGION_RESIZE_STEP 16
-
 static int
 mlxsw_sp_acl_tcam_region_alloc(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_tcam_region *region)
@@ -455,6 +456,7 @@ mlxsw_sp_acl_tcam_region_alloc(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	mlxsw_reg_ptar_pack(ptar_pl, MLXSW_REG_PTAR_OP_ALLOC,
+			    region->key_type,
 			    MLXSW_SP_ACL_TCAM_REGION_BASE_COUNT,
 			    region->id, region->tcam_region_info);
 	encodings_count = mlxsw_afk_key_info_blocks_count_get(key_info);
@@ -477,24 +479,13 @@ mlxsw_sp_acl_tcam_region_free(struct mlxsw_sp *mlxsw_sp,
 {
 	char ptar_pl[MLXSW_REG_PTAR_LEN];
 
-	mlxsw_reg_ptar_pack(ptar_pl, MLXSW_REG_PTAR_OP_FREE, 0, region->id,
+	mlxsw_reg_ptar_pack(ptar_pl, MLXSW_REG_PTAR_OP_FREE,
+			    region->key_type, 0, region->id,
 			    region->tcam_region_info);
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptar), ptar_pl);
 }
 
 static int
-mlxsw_sp_acl_tcam_region_resize(struct mlxsw_sp *mlxsw_sp,
-				struct mlxsw_sp_acl_tcam_region *region,
-				u16 new_size)
-{
-	char ptar_pl[MLXSW_REG_PTAR_LEN];
-
-	mlxsw_reg_ptar_pack(ptar_pl, MLXSW_REG_PTAR_OP_RESIZE,
-			    new_size, region->id, region->tcam_region_info);
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptar), ptar_pl);
-}
-
-static int
 mlxsw_sp_acl_tcam_region_enable(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_acl_tcam_region *region)
 {
@@ -516,193 +507,22 @@ mlxsw_sp_acl_tcam_region_disable(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pacl), pacl_pl);
 }
 
-static int
-mlxsw_sp_acl_tcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
-				      struct mlxsw_sp_acl_tcam_region *region,
-				      unsigned int offset,
-				      struct mlxsw_sp_acl_rule_info *rulei)
-{
-	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
-	char *act_set;
-	char *mask;
-	char *key;
-
-	mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_WRITE_WRITE,
-			     region->tcam_region_info, offset);
-	key = mlxsw_reg_ptce2_flex_key_blocks_data(ptce2_pl);
-	mask = mlxsw_reg_ptce2_mask_data(ptce2_pl);
-	mlxsw_afk_encode(region->key_info, &rulei->values, key, mask);
-
-	/* Only the first action set belongs here, the rest is in KVD */
-	act_set = mlxsw_afa_block_first_set(rulei->act_block);
-	mlxsw_reg_ptce2_flex_action_set_memcpy_to(ptce2_pl, act_set);
-
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
-}
-
-static void
-mlxsw_sp_acl_tcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
-				      struct mlxsw_sp_acl_tcam_region *region,
-				      unsigned int offset)
-{
-	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
-
-	mlxsw_reg_ptce2_pack(ptce2_pl, false, MLXSW_REG_PTCE2_OP_WRITE_WRITE,
-			     region->tcam_region_info, offset);
-	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
-}
-
-static int
-mlxsw_sp_acl_tcam_region_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
-					    struct mlxsw_sp_acl_tcam_region *region,
-					    unsigned int offset,
-					    bool *activity)
-{
-	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
-	int err;
-
-	mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_QUERY_CLEAR_ON_READ,
-			     region->tcam_region_info, offset);
-	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
-	if (err)
-		return err;
-	*activity = mlxsw_reg_ptce2_a_get(ptce2_pl);
-	return 0;
-}
-
-#define MLXSW_SP_ACL_TCAM_CATCHALL_PRIO (~0U)
-
-static int
-mlxsw_sp_acl_tcam_region_catchall_add(struct mlxsw_sp *mlxsw_sp,
-				      struct mlxsw_sp_acl_tcam_region *region)
-{
-	struct parman_prio *parman_prio = &region->catchall.parman_prio;
-	struct parman_item *parman_item = &region->catchall.parman_item;
-	struct mlxsw_sp_acl_rule_info *rulei;
-	int err;
-
-	parman_prio_init(region->parman, parman_prio,
-			 MLXSW_SP_ACL_TCAM_CATCHALL_PRIO);
-	err = parman_item_add(region->parman, parman_prio, parman_item);
-	if (err)
-		goto err_parman_item_add;
-
-	rulei = mlxsw_sp_acl_rulei_create(mlxsw_sp->acl);
-	if (IS_ERR(rulei)) {
-		err = PTR_ERR(rulei);
-		goto err_rulei_create;
-	}
-
-	err = mlxsw_sp_acl_rulei_act_continue(rulei);
-	if (WARN_ON(err))
-		goto err_rulei_act_continue;
-
-	err = mlxsw_sp_acl_rulei_commit(rulei);
-	if (err)
-		goto err_rulei_commit;
-
-	err = mlxsw_sp_acl_tcam_region_entry_insert(mlxsw_sp, region,
-						    parman_item->index, rulei);
-	region->catchall.rulei = rulei;
-	if (err)
-		goto err_rule_insert;
-
-	return 0;
-
-err_rule_insert:
-err_rulei_commit:
-err_rulei_act_continue:
-	mlxsw_sp_acl_rulei_destroy(rulei);
-err_rulei_create:
-	parman_item_remove(region->parman, parman_prio, parman_item);
-err_parman_item_add:
-	parman_prio_fini(parman_prio);
-	return err;
-}
-
-static void
-mlxsw_sp_acl_tcam_region_catchall_del(struct mlxsw_sp *mlxsw_sp,
-				      struct mlxsw_sp_acl_tcam_region *region)
-{
-	struct parman_prio *parman_prio = &region->catchall.parman_prio;
-	struct parman_item *parman_item = &region->catchall.parman_item;
-	struct mlxsw_sp_acl_rule_info *rulei = region->catchall.rulei;
-
-	mlxsw_sp_acl_tcam_region_entry_remove(mlxsw_sp, region,
-					      parman_item->index);
-	mlxsw_sp_acl_rulei_destroy(rulei);
-	parman_item_remove(region->parman, parman_prio, parman_item);
-	parman_prio_fini(parman_prio);
-}
-
-static void
-mlxsw_sp_acl_tcam_region_move(struct mlxsw_sp *mlxsw_sp,
-			      struct mlxsw_sp_acl_tcam_region *region,
-			      u16 src_offset, u16 dst_offset, u16 size)
-{
-	char prcr_pl[MLXSW_REG_PRCR_LEN];
-
-	mlxsw_reg_prcr_pack(prcr_pl, MLXSW_REG_PRCR_OP_MOVE,
-			    region->tcam_region_info, src_offset,
-			    region->tcam_region_info, dst_offset, size);
-	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(prcr), prcr_pl);
-}
-
-static int mlxsw_sp_acl_tcam_region_parman_resize(void *priv,
-						  unsigned long new_count)
-{
-	struct mlxsw_sp_acl_tcam_region *region = priv;
-	struct mlxsw_sp *mlxsw_sp = region->mlxsw_sp;
-	u64 max_tcam_rules;
-
-	max_tcam_rules = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_TCAM_RULES);
-	if (new_count > max_tcam_rules)
-		return -EINVAL;
-	return mlxsw_sp_acl_tcam_region_resize(mlxsw_sp, region, new_count);
-}
-
-static void mlxsw_sp_acl_tcam_region_parman_move(void *priv,
-						 unsigned long from_index,
-						 unsigned long to_index,
-						 unsigned long count)
-{
-	struct mlxsw_sp_acl_tcam_region *region = priv;
-	struct mlxsw_sp *mlxsw_sp = region->mlxsw_sp;
-
-	mlxsw_sp_acl_tcam_region_move(mlxsw_sp, region,
-				      from_index, to_index, count);
-}
-
-static const struct parman_ops mlxsw_sp_acl_tcam_region_parman_ops = {
-	.base_count	= MLXSW_SP_ACL_TCAM_REGION_BASE_COUNT,
-	.resize_step	= MLXSW_SP_ACL_TCAM_REGION_RESIZE_STEP,
-	.resize		= mlxsw_sp_acl_tcam_region_parman_resize,
-	.move		= mlxsw_sp_acl_tcam_region_parman_move,
-	.algo		= PARMAN_ALGO_TYPE_LSORT,
-};
-
 static struct mlxsw_sp_acl_tcam_region *
 mlxsw_sp_acl_tcam_region_create(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_acl_tcam *tcam,
 				struct mlxsw_afk_element_usage *elusage)
 {
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
 	struct mlxsw_sp_acl_tcam_region *region;
 	int err;
 
-	region = kzalloc(sizeof(*region), GFP_KERNEL);
+	region = kzalloc(sizeof(*region) + ops->region_priv_size, GFP_KERNEL);
 	if (!region)
 		return ERR_PTR(-ENOMEM);
 	INIT_LIST_HEAD(&region->chunk_list);
 	region->mlxsw_sp = mlxsw_sp;
 
-	region->parman = parman_create(&mlxsw_sp_acl_tcam_region_parman_ops,
-				       region);
-	if (!region->parman) {
-		err = -ENOMEM;
-		goto err_parman_create;
-	}
-
 	region->key_info = mlxsw_afk_key_info_get(afk, elusage);
 	if (IS_ERR(region->key_info)) {
 		err = PTR_ERR(region->key_info);
@@ -713,6 +533,11 @@ mlxsw_sp_acl_tcam_region_create(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_region_id_get;
 
+	err = ops->region_associate(mlxsw_sp, region);
+	if (err)
+		goto err_tcam_region_associate;
+
+	region->key_type = ops->key_type;
 	err = mlxsw_sp_acl_tcam_region_alloc(mlxsw_sp, region);
 	if (err)
 		goto err_tcam_region_alloc;
@@ -721,23 +546,22 @@ mlxsw_sp_acl_tcam_region_create(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_tcam_region_enable;
 
-	err = mlxsw_sp_acl_tcam_region_catchall_add(mlxsw_sp, region);
+	err = ops->region_init(mlxsw_sp, region->priv, tcam->priv, region);
 	if (err)
-		goto err_tcam_region_catchall_add;
+		goto err_tcam_region_init;
 
 	return region;
 
-err_tcam_region_catchall_add:
+err_tcam_region_init:
 	mlxsw_sp_acl_tcam_region_disable(mlxsw_sp, region);
 err_tcam_region_enable:
 	mlxsw_sp_acl_tcam_region_free(mlxsw_sp, region);
 err_tcam_region_alloc:
+err_tcam_region_associate:
 	mlxsw_sp_acl_tcam_region_id_put(tcam, region->id);
 err_region_id_get:
 	mlxsw_afk_key_info_put(region->key_info);
 err_key_info_get:
-	parman_destroy(region->parman);
-err_parman_create:
 	kfree(region);
 	return ERR_PTR(err);
 }
@@ -746,12 +570,13 @@ static void
 mlxsw_sp_acl_tcam_region_destroy(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_acl_tcam_region *region)
 {
-	mlxsw_sp_acl_tcam_region_catchall_del(mlxsw_sp, region);
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+
+	ops->region_fini(mlxsw_sp, region->priv);
 	mlxsw_sp_acl_tcam_region_disable(mlxsw_sp, region);
 	mlxsw_sp_acl_tcam_region_free(mlxsw_sp, region);
 	mlxsw_sp_acl_tcam_region_id_put(region->group->tcam, region->id);
 	mlxsw_afk_key_info_put(region->key_info);
-	parman_destroy(region->parman);
 	kfree(region);
 }
 
@@ -826,13 +651,14 @@ mlxsw_sp_acl_tcam_chunk_create(struct mlxsw_sp *mlxsw_sp,
 			       unsigned int priority,
 			       struct mlxsw_afk_element_usage *elusage)
 {
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 	struct mlxsw_sp_acl_tcam_chunk *chunk;
 	int err;
 
 	if (priority == MLXSW_SP_ACL_TCAM_CATCHALL_PRIO)
 		return ERR_PTR(-EINVAL);
 
-	chunk = kzalloc(sizeof(*chunk), GFP_KERNEL);
+	chunk = kzalloc(sizeof(*chunk) + ops->chunk_priv_size, GFP_KERNEL);
 	if (!chunk)
 		return ERR_PTR(-ENOMEM);
 	chunk->priority = priority;
@@ -844,7 +670,7 @@ mlxsw_sp_acl_tcam_chunk_create(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_chunk_assoc;
 
-	parman_prio_init(chunk->region->parman, &chunk->parman_prio, priority);
+	ops->chunk_init(chunk->region->priv, chunk->priv, priority);
 
 	err = rhashtable_insert_fast(&group->chunk_ht, &chunk->ht_node,
 				     mlxsw_sp_acl_tcam_chunk_ht_params);
@@ -854,7 +680,7 @@ mlxsw_sp_acl_tcam_chunk_create(struct mlxsw_sp *mlxsw_sp,
 	return chunk;
 
 err_rhashtable_insert:
-	parman_prio_fini(&chunk->parman_prio);
+	ops->chunk_fini(chunk->priv);
 	mlxsw_sp_acl_tcam_chunk_deassoc(mlxsw_sp, chunk);
 err_chunk_assoc:
 	kfree(chunk);
@@ -865,11 +691,12 @@ static void
 mlxsw_sp_acl_tcam_chunk_destroy(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_acl_tcam_chunk *chunk)
 {
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 	struct mlxsw_sp_acl_tcam_group *group = chunk->group;
 
 	rhashtable_remove_fast(&group->chunk_ht, &chunk->ht_node,
 			       mlxsw_sp_acl_tcam_chunk_ht_params);
-	parman_prio_fini(&chunk->parman_prio);
+	ops->chunk_fini(chunk->priv);
 	mlxsw_sp_acl_tcam_chunk_deassoc(mlxsw_sp, chunk);
 	kfree(chunk);
 }
@@ -903,11 +730,19 @@ static void mlxsw_sp_acl_tcam_chunk_put(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, chunk);
 }
 
+static size_t mlxsw_sp_acl_tcam_entry_priv_size(struct mlxsw_sp *mlxsw_sp)
+{
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+
+	return ops->entry_priv_size;
+}
+
 static int mlxsw_sp_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 				       struct mlxsw_sp_acl_tcam_group *group,
 				       struct mlxsw_sp_acl_tcam_entry *entry,
 				       struct mlxsw_sp_acl_rule_info *rulei)
 {
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 	struct mlxsw_sp_acl_tcam_chunk *chunk;
 	struct mlxsw_sp_acl_tcam_region *region;
 	int err;
@@ -918,24 +753,16 @@ static int mlxsw_sp_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 		return PTR_ERR(chunk);
 
 	region = chunk->region;
-	err = parman_item_add(region->parman, &chunk->parman_prio,
-			      &entry->parman_item);
-	if (err)
-		goto err_parman_item_add;
 
-	err = mlxsw_sp_acl_tcam_region_entry_insert(mlxsw_sp, region,
-						    entry->parman_item.index,
-						    rulei);
+	err = ops->entry_add(mlxsw_sp, region->priv, chunk->priv,
+			     entry->priv, rulei);
 	if (err)
-		goto err_rule_insert;
+		goto err_entry_add;
 	entry->chunk = chunk;
 
 	return 0;
 
-err_rule_insert:
-	parman_item_remove(region->parman, &chunk->parman_prio,
-			   &entry->parman_item);
-err_parman_item_add:
+err_entry_add:
 	mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk);
 	return err;
 }
@@ -943,13 +770,11 @@ err_parman_item_add:
 static void mlxsw_sp_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 					struct mlxsw_sp_acl_tcam_entry *entry)
 {
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 	struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk;
 	struct mlxsw_sp_acl_tcam_region *region = chunk->region;
 
-	mlxsw_sp_acl_tcam_region_entry_remove(mlxsw_sp, region,
-					      entry->parman_item.index);
-	parman_item_remove(region->parman, &chunk->parman_prio,
-			   &entry->parman_item);
+	ops->entry_del(mlxsw_sp, region->priv, chunk->priv, entry->priv);
 	mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk);
 }
 
@@ -958,22 +783,24 @@ mlxsw_sp_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
 				     struct mlxsw_sp_acl_tcam_entry *entry,
 				     bool *activity)
 {
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 	struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk;
 	struct mlxsw_sp_acl_tcam_region *region = chunk->region;
 
-	return mlxsw_sp_acl_tcam_region_entry_activity_get(mlxsw_sp, region,
-							   entry->parman_item.index,
-							   activity);
+	return ops->entry_activity_get(mlxsw_sp, region->priv,
+				       entry->priv, activity);
 }
 
 static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = {
 	MLXSW_AFK_ELEMENT_SRC_SYS_PORT,
-	MLXSW_AFK_ELEMENT_DMAC,
-	MLXSW_AFK_ELEMENT_SMAC,
+	MLXSW_AFK_ELEMENT_DMAC_32_47,
+	MLXSW_AFK_ELEMENT_DMAC_0_31,
+	MLXSW_AFK_ELEMENT_SMAC_32_47,
+	MLXSW_AFK_ELEMENT_SMAC_0_31,
 	MLXSW_AFK_ELEMENT_ETHERTYPE,
 	MLXSW_AFK_ELEMENT_IP_PROTO,
-	MLXSW_AFK_ELEMENT_SRC_IP4,
-	MLXSW_AFK_ELEMENT_DST_IP4,
+	MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+	MLXSW_AFK_ELEMENT_DST_IP_0_31,
 	MLXSW_AFK_ELEMENT_DST_L4_PORT,
 	MLXSW_AFK_ELEMENT_SRC_L4_PORT,
 	MLXSW_AFK_ELEMENT_VID,
@@ -987,10 +814,14 @@ static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = {
 static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv6[] = {
 	MLXSW_AFK_ELEMENT_ETHERTYPE,
 	MLXSW_AFK_ELEMENT_IP_PROTO,
-	MLXSW_AFK_ELEMENT_SRC_IP6_HI,
-	MLXSW_AFK_ELEMENT_SRC_IP6_LO,
-	MLXSW_AFK_ELEMENT_DST_IP6_HI,
-	MLXSW_AFK_ELEMENT_DST_IP6_LO,
+	MLXSW_AFK_ELEMENT_SRC_IP_96_127,
+	MLXSW_AFK_ELEMENT_SRC_IP_64_95,
+	MLXSW_AFK_ELEMENT_SRC_IP_32_63,
+	MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+	MLXSW_AFK_ELEMENT_DST_IP_96_127,
+	MLXSW_AFK_ELEMENT_DST_IP_64_95,
+	MLXSW_AFK_ELEMENT_DST_IP_32_63,
+	MLXSW_AFK_ELEMENT_DST_IP_0_31,
 	MLXSW_AFK_ELEMENT_DST_L4_PORT,
 	MLXSW_AFK_ELEMENT_SRC_L4_PORT,
 };
@@ -1019,14 +850,16 @@ struct mlxsw_sp_acl_tcam_flower_rule {
 
 static int
 mlxsw_sp_acl_tcam_flower_ruleset_add(struct mlxsw_sp *mlxsw_sp,
-				     void *priv, void *ruleset_priv)
+				     struct mlxsw_sp_acl_tcam *tcam,
+				     void *ruleset_priv,
+				     struct mlxsw_afk_element_usage *tmplt_elusage)
 {
 	struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv;
-	struct mlxsw_sp_acl_tcam *tcam = priv;
 
 	return mlxsw_sp_acl_tcam_group_add(mlxsw_sp, tcam, &ruleset->group,
 					   mlxsw_sp_acl_tcam_patterns,
-					   MLXSW_SP_ACL_TCAM_PATTERNS_COUNT);
+					   MLXSW_SP_ACL_TCAM_PATTERNS_COUNT,
+					   tmplt_elusage);
 }
 
 static void
@@ -1070,6 +903,12 @@ mlxsw_sp_acl_tcam_flower_ruleset_group_id(void *ruleset_priv)
 	return mlxsw_sp_acl_tcam_group_id(&ruleset->group);
 }
 
+static size_t mlxsw_sp_acl_tcam_flower_rule_priv_size(struct mlxsw_sp *mlxsw_sp)
+{
+	return sizeof(struct mlxsw_sp_acl_tcam_flower_rule) +
+	       mlxsw_sp_acl_tcam_entry_priv_size(mlxsw_sp);
+}
+
 static int
 mlxsw_sp_acl_tcam_flower_rule_add(struct mlxsw_sp *mlxsw_sp,
 				  void *ruleset_priv, void *rule_priv,
@@ -1107,7 +946,7 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = {
 	.ruleset_bind		= mlxsw_sp_acl_tcam_flower_ruleset_bind,
 	.ruleset_unbind		= mlxsw_sp_acl_tcam_flower_ruleset_unbind,
 	.ruleset_group_id	= mlxsw_sp_acl_tcam_flower_ruleset_group_id,
-	.rule_priv_size		= sizeof(struct mlxsw_sp_acl_tcam_flower_rule),
+	.rule_priv_size		= mlxsw_sp_acl_tcam_flower_rule_priv_size,
 	.rule_add		= mlxsw_sp_acl_tcam_flower_rule_add,
 	.rule_del		= mlxsw_sp_acl_tcam_flower_rule_del,
 	.rule_activity_get	= mlxsw_sp_acl_tcam_flower_rule_activity_get,
@@ -1118,7 +957,7 @@ mlxsw_sp_acl_tcam_profile_ops_arr[] = {
 	[MLXSW_SP_ACL_PROFILE_FLOWER] = &mlxsw_sp_acl_tcam_flower_ops,
 };
 
-static const struct mlxsw_sp_acl_profile_ops *
+const struct mlxsw_sp_acl_profile_ops *
 mlxsw_sp_acl_tcam_profile_ops(struct mlxsw_sp *mlxsw_sp,
 			      enum mlxsw_sp_acl_profile profile)
 {
@@ -1131,10 +970,3 @@ mlxsw_sp_acl_tcam_profile_ops(struct mlxsw_sp *mlxsw_sp,
 		return NULL;
 	return ops;
 }
-
-const struct mlxsw_sp_acl_ops mlxsw_sp_acl_tcam_ops = {
-	.priv_size		= sizeof(struct mlxsw_sp_acl_tcam),
-	.init			= mlxsw_sp_acl_tcam_init,
-	.fini			= mlxsw_sp_acl_tcam_fini,
-	.profile_ops		= mlxsw_sp_acl_tcam_profile_ops,
-};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
new file mode 100644
index 000000000000..219a4e26c332
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -0,0 +1,228 @@
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
+
+#ifndef _MLXSW_SPECTRUM_ACL_TCAM_H
+#define _MLXSW_SPECTRUM_ACL_TCAM_H
+
+#include <linux/list.h>
+#include <linux/parman.h>
+
+#include "reg.h"
+#include "spectrum.h"
+#include "core_acl_flex_keys.h"
+
+struct mlxsw_sp_acl_tcam {
+	unsigned long *used_regions; /* bit array */
+	unsigned int max_regions;
+	unsigned long *used_groups;  /* bit array */
+	unsigned int max_groups;
+	unsigned int max_group_size;
+	unsigned long priv[0];
+	/* priv has to be always the last item */
+};
+
+size_t mlxsw_sp_acl_tcam_priv_size(struct mlxsw_sp *mlxsw_sp);
+int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp,
+			   struct mlxsw_sp_acl_tcam *tcam);
+void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp,
+			    struct mlxsw_sp_acl_tcam *tcam);
+int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_acl_rule_info *rulei,
+				   u32 *priority, bool fillup_priority);
+
+struct mlxsw_sp_acl_profile_ops {
+	size_t ruleset_priv_size;
+	int (*ruleset_add)(struct mlxsw_sp *mlxsw_sp,
+			   struct mlxsw_sp_acl_tcam *tcam, void *ruleset_priv,
+			   struct mlxsw_afk_element_usage *tmplt_elusage);
+	void (*ruleset_del)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv);
+	int (*ruleset_bind)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
+			    struct mlxsw_sp_port *mlxsw_sp_port,
+			    bool ingress);
+	void (*ruleset_unbind)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
+			       struct mlxsw_sp_port *mlxsw_sp_port,
+			       bool ingress);
+	u16 (*ruleset_group_id)(void *ruleset_priv);
+	size_t (*rule_priv_size)(struct mlxsw_sp *mlxsw_sp);
+	int (*rule_add)(struct mlxsw_sp *mlxsw_sp,
+			void *ruleset_priv, void *rule_priv,
+			struct mlxsw_sp_acl_rule_info *rulei);
+	void (*rule_del)(struct mlxsw_sp *mlxsw_sp, void *rule_priv);
+	int (*rule_activity_get)(struct mlxsw_sp *mlxsw_sp, void *rule_priv,
+				 bool *activity);
+};
+
+const struct mlxsw_sp_acl_profile_ops *
+mlxsw_sp_acl_tcam_profile_ops(struct mlxsw_sp *mlxsw_sp,
+			      enum mlxsw_sp_acl_profile profile);
+
+#define MLXSW_SP_ACL_TCAM_REGION_BASE_COUNT 16
+#define MLXSW_SP_ACL_TCAM_REGION_RESIZE_STEP 16
+
+#define MLXSW_SP_ACL_TCAM_CATCHALL_PRIO (~0U)
+
+#define MLXSW_SP_ACL_TCAM_MASK_LEN \
+	(MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN * BITS_PER_BYTE)
+
+struct mlxsw_sp_acl_tcam_group;
+
+struct mlxsw_sp_acl_tcam_region {
+	struct list_head list; /* Member of a TCAM group */
+	struct list_head chunk_list; /* List of chunks under this region */
+	struct mlxsw_sp_acl_tcam_group *group;
+	enum mlxsw_reg_ptar_key_type key_type;
+	u16 id; /* ACL ID and region ID - they are same */
+	char tcam_region_info[MLXSW_REG_PXXX_TCAM_REGION_INFO_LEN];
+	struct mlxsw_afk_key_info *key_info;
+	struct mlxsw_sp *mlxsw_sp;
+	unsigned long priv[0];
+	/* priv has to be always the last item */
+};
+
+struct mlxsw_sp_acl_ctcam_region {
+	struct parman *parman;
+	const struct mlxsw_sp_acl_ctcam_region_ops *ops;
+	struct mlxsw_sp_acl_tcam_region *region;
+};
+
+struct mlxsw_sp_acl_ctcam_chunk {
+	struct parman_prio parman_prio;
+};
+
+struct mlxsw_sp_acl_ctcam_entry {
+	struct parman_item parman_item;
+};
+
+struct mlxsw_sp_acl_ctcam_region_ops {
+	int (*entry_insert)(struct mlxsw_sp_acl_ctcam_region *cregion,
+			    struct mlxsw_sp_acl_ctcam_entry *centry,
+			    const char *mask);
+	void (*entry_remove)(struct mlxsw_sp_acl_ctcam_region *cregion,
+			     struct mlxsw_sp_acl_ctcam_entry *centry);
+};
+
+int
+mlxsw_sp_acl_ctcam_region_init(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_ctcam_region *cregion,
+			       struct mlxsw_sp_acl_tcam_region *region,
+			       const struct mlxsw_sp_acl_ctcam_region_ops *ops);
+void mlxsw_sp_acl_ctcam_region_fini(struct mlxsw_sp_acl_ctcam_region *cregion);
+void mlxsw_sp_acl_ctcam_chunk_init(struct mlxsw_sp_acl_ctcam_region *cregion,
+				   struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+				   unsigned int priority);
+void mlxsw_sp_acl_ctcam_chunk_fini(struct mlxsw_sp_acl_ctcam_chunk *cchunk);
+int mlxsw_sp_acl_ctcam_entry_add(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_ctcam_region *cregion,
+				 struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+				 struct mlxsw_sp_acl_ctcam_entry *centry,
+				 struct mlxsw_sp_acl_rule_info *rulei,
+				 bool fillup_priority);
+void mlxsw_sp_acl_ctcam_entry_del(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_acl_ctcam_region *cregion,
+				  struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+				  struct mlxsw_sp_acl_ctcam_entry *centry);
+static inline unsigned int
+mlxsw_sp_acl_ctcam_entry_offset(struct mlxsw_sp_acl_ctcam_entry *centry)
+{
+	return centry->parman_item.index;
+}
+
+enum mlxsw_sp_acl_atcam_region_type {
+	MLXSW_SP_ACL_ATCAM_REGION_TYPE_2KB,
+	MLXSW_SP_ACL_ATCAM_REGION_TYPE_4KB,
+	MLXSW_SP_ACL_ATCAM_REGION_TYPE_8KB,
+	MLXSW_SP_ACL_ATCAM_REGION_TYPE_12KB,
+	__MLXSW_SP_ACL_ATCAM_REGION_TYPE_MAX,
+};
+
+#define MLXSW_SP_ACL_ATCAM_REGION_TYPE_MAX \
+	(__MLXSW_SP_ACL_ATCAM_REGION_TYPE_MAX - 1)
+
+struct mlxsw_sp_acl_atcam {
+	struct mlxsw_sp_acl_erp_core *erp_core;
+};
+
+struct mlxsw_sp_acl_atcam_region {
+	struct rhashtable entries_ht; /* A-TCAM only */
+	struct mlxsw_sp_acl_ctcam_region cregion;
+	const struct mlxsw_sp_acl_atcam_region_ops *ops;
+	struct mlxsw_sp_acl_tcam_region *region;
+	struct mlxsw_sp_acl_atcam *atcam;
+	enum mlxsw_sp_acl_atcam_region_type type;
+	struct mlxsw_sp_acl_erp_table *erp_table;
+	void *priv;
+};
+
+struct mlxsw_sp_acl_atcam_entry_ht_key {
+	char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key */
+	u8 erp_id;
+};
+
+struct mlxsw_sp_acl_atcam_chunk {
+	struct mlxsw_sp_acl_ctcam_chunk cchunk;
+};
+
+struct mlxsw_sp_acl_atcam_entry {
+	struct rhash_head ht_node;
+	struct mlxsw_sp_acl_atcam_entry_ht_key ht_key;
+	struct mlxsw_sp_acl_ctcam_entry centry;
+	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id;
+	struct mlxsw_sp_acl_erp *erp;
+};
+
+static inline struct mlxsw_sp_acl_atcam_region *
+mlxsw_sp_acl_tcam_cregion_aregion(struct mlxsw_sp_acl_ctcam_region *cregion)
+{
+	return container_of(cregion, struct mlxsw_sp_acl_atcam_region, cregion);
+}
+
+static inline struct mlxsw_sp_acl_atcam_entry *
+mlxsw_sp_acl_tcam_centry_aentry(struct mlxsw_sp_acl_ctcam_entry *centry)
+{
+	return container_of(centry, struct mlxsw_sp_acl_atcam_entry, centry);
+}
+
+int mlxsw_sp_acl_atcam_region_associate(struct mlxsw_sp *mlxsw_sp,
+					u16 region_id);
+int
+mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_atcam *atcam,
+			       struct mlxsw_sp_acl_atcam_region *aregion,
+			       struct mlxsw_sp_acl_tcam_region *region,
+			       const struct mlxsw_sp_acl_ctcam_region_ops *ops);
+void mlxsw_sp_acl_atcam_region_fini(struct mlxsw_sp_acl_atcam_region *aregion);
+void mlxsw_sp_acl_atcam_chunk_init(struct mlxsw_sp_acl_atcam_region *aregion,
+				   struct mlxsw_sp_acl_atcam_chunk *achunk,
+				   unsigned int priority);
+void mlxsw_sp_acl_atcam_chunk_fini(struct mlxsw_sp_acl_atcam_chunk *achunk);
+int mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_atcam_region *aregion,
+				 struct mlxsw_sp_acl_atcam_chunk *achunk,
+				 struct mlxsw_sp_acl_atcam_entry *aentry,
+				 struct mlxsw_sp_acl_rule_info *rulei);
+void mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_acl_atcam_region *aregion,
+				  struct mlxsw_sp_acl_atcam_chunk *achunk,
+				  struct mlxsw_sp_acl_atcam_entry *aentry);
+int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp,
+			    struct mlxsw_sp_acl_atcam *atcam);
+void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_acl_atcam *atcam);
+
+struct mlxsw_sp_acl_erp;
+
+bool mlxsw_sp_acl_erp_is_ctcam_erp(const struct mlxsw_sp_acl_erp *erp);
+u8 mlxsw_sp_acl_erp_id(const struct mlxsw_sp_acl_erp *erp);
+struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_get(struct mlxsw_sp_acl_atcam_region *aregion,
+		     const char *mask, bool ctcam);
+void mlxsw_sp_acl_erp_put(struct mlxsw_sp_acl_atcam_region *aregion,
+			  struct mlxsw_sp_acl_erp *erp);
+int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion);
+void mlxsw_sp_acl_erp_region_fini(struct mlxsw_sp_acl_atcam_region *aregion);
+int mlxsw_sp_acl_erps_init(struct mlxsw_sp *mlxsw_sp,
+			   struct mlxsw_sp_acl_atcam *atcam);
+void mlxsw_sp_acl_erps_fini(struct mlxsw_sp *mlxsw_sp,
+			    struct mlxsw_sp_acl_atcam *atcam);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index 0a9adc5962fb..4327487553c5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
index 0f46775e0307..83c2e1e5f216 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Arkadi Sharshevsky <arkadis@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/bitops.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h
index fd34d0a01073..81465e267b10 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Arkadi Sharshevsky <arkdis@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_SPECTRUM_CNT_H
 #define _MLXSW_SPECTRUM_CNT_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
index b6ed7f7c531e..b25048c6c761 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
- * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Ido Schimmel <idosch@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/netdevice.h>
 #include <linux/string.h>
@@ -255,6 +224,270 @@ static int mlxsw_sp_dcbnl_ieee_setets(struct net_device *dev,
 	return 0;
 }
 
+static int mlxsw_sp_dcbnl_app_validate(struct net_device *dev,
+				       struct dcb_app *app)
+{
+	int prio;
+
+	if (app->priority >= IEEE_8021QAZ_MAX_TCS) {
+		netdev_err(dev, "APP entry with priority value %u is invalid\n",
+			   app->priority);
+		return -EINVAL;
+	}
+
+	switch (app->selector) {
+	case IEEE_8021QAZ_APP_SEL_DSCP:
+		if (app->protocol >= 64) {
+			netdev_err(dev, "DSCP APP entry with protocol value %u is invalid\n",
+				   app->protocol);
+			return -EINVAL;
+		}
+
+		/* Warn about any DSCP APP entries with the same PID. */
+		prio = fls(dcb_ieee_getapp_mask(dev, app));
+		if (prio--) {
+			if (prio < app->priority)
+				netdev_warn(dev, "Choosing priority %d for DSCP %d in favor of previously-active value of %d\n",
+					    app->priority, app->protocol, prio);
+			else if (prio > app->priority)
+				netdev_warn(dev, "Ignoring new priority %d for DSCP %d in favor of current value of %d\n",
+					    app->priority, app->protocol, prio);
+		}
+		break;
+
+	case IEEE_8021QAZ_APP_SEL_ETHERTYPE:
+		if (app->protocol) {
+			netdev_err(dev, "EtherType APP entries with protocol value != 0 not supported\n");
+			return -EINVAL;
+		}
+		break;
+
+	default:
+		netdev_err(dev, "APP entries with selector %u not supported\n",
+			   app->selector);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static u8
+mlxsw_sp_port_dcb_app_default_prio(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	u8 prio_mask;
+
+	prio_mask = dcb_ieee_getapp_default_prio_mask(mlxsw_sp_port->dev);
+	if (prio_mask)
+		/* Take the highest configured priority. */
+		return fls(prio_mask) - 1;
+
+	return 0;
+}
+
+static void
+mlxsw_sp_port_dcb_app_dscp_prio_map(struct mlxsw_sp_port *mlxsw_sp_port,
+				    u8 default_prio,
+				    struct dcb_ieee_app_dscp_map *map)
+{
+	int i;
+
+	dcb_ieee_getapp_dscp_prio_mask_map(mlxsw_sp_port->dev, map);
+	for (i = 0; i < ARRAY_SIZE(map->map); ++i) {
+		if (map->map[i])
+			map->map[i] = fls(map->map[i]) - 1;
+		else
+			map->map[i] = default_prio;
+	}
+}
+
+static bool
+mlxsw_sp_port_dcb_app_prio_dscp_map(struct mlxsw_sp_port *mlxsw_sp_port,
+				    struct dcb_ieee_app_prio_map *map)
+{
+	bool have_dscp = false;
+	int i;
+
+	dcb_ieee_getapp_prio_dscp_mask_map(mlxsw_sp_port->dev, map);
+	for (i = 0; i < ARRAY_SIZE(map->map); ++i) {
+		if (map->map[i]) {
+			map->map[i] = fls64(map->map[i]) - 1;
+			have_dscp = true;
+		}
+	}
+
+	return have_dscp;
+}
+
+static int
+mlxsw_sp_port_dcb_app_update_qpts(struct mlxsw_sp_port *mlxsw_sp_port,
+				  enum mlxsw_reg_qpts_trust_state ts)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char qpts_pl[MLXSW_REG_QPTS_LEN];
+
+	mlxsw_reg_qpts_pack(qpts_pl, mlxsw_sp_port->local_port, ts);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qpts), qpts_pl);
+}
+
+static int
+mlxsw_sp_port_dcb_app_update_qrwe(struct mlxsw_sp_port *mlxsw_sp_port,
+				  bool rewrite_dscp)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char qrwe_pl[MLXSW_REG_QRWE_LEN];
+
+	mlxsw_reg_qrwe_pack(qrwe_pl, mlxsw_sp_port->local_port,
+			    false, rewrite_dscp);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qrwe), qrwe_pl);
+}
+
+static int
+mlxsw_sp_port_dcb_toggle_trust(struct mlxsw_sp_port *mlxsw_sp_port,
+			       enum mlxsw_reg_qpts_trust_state ts)
+{
+	bool rewrite_dscp = ts == MLXSW_REG_QPTS_TRUST_STATE_DSCP;
+	int err;
+
+	if (mlxsw_sp_port->dcb.trust_state == ts)
+		return 0;
+
+	err = mlxsw_sp_port_dcb_app_update_qpts(mlxsw_sp_port, ts);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_port_dcb_app_update_qrwe(mlxsw_sp_port, rewrite_dscp);
+	if (err)
+		goto err_update_qrwe;
+
+	mlxsw_sp_port->dcb.trust_state = ts;
+	return 0;
+
+err_update_qrwe:
+	mlxsw_sp_port_dcb_app_update_qpts(mlxsw_sp_port,
+					  mlxsw_sp_port->dcb.trust_state);
+	return err;
+}
+
+static int
+mlxsw_sp_port_dcb_app_update_qpdpm(struct mlxsw_sp_port *mlxsw_sp_port,
+				   struct dcb_ieee_app_dscp_map *map)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char qpdpm_pl[MLXSW_REG_QPDPM_LEN];
+	short int i;
+
+	mlxsw_reg_qpdpm_pack(qpdpm_pl, mlxsw_sp_port->local_port);
+	for (i = 0; i < ARRAY_SIZE(map->map); ++i)
+		mlxsw_reg_qpdpm_dscp_pack(qpdpm_pl, i, map->map[i]);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qpdpm), qpdpm_pl);
+}
+
+static int
+mlxsw_sp_port_dcb_app_update_qpdsm(struct mlxsw_sp_port *mlxsw_sp_port,
+				   struct dcb_ieee_app_prio_map *map)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char qpdsm_pl[MLXSW_REG_QPDSM_LEN];
+	short int i;
+
+	mlxsw_reg_qpdsm_pack(qpdsm_pl, mlxsw_sp_port->local_port);
+	for (i = 0; i < ARRAY_SIZE(map->map); ++i)
+		mlxsw_reg_qpdsm_prio_pack(qpdsm_pl, i, map->map[i]);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qpdsm), qpdsm_pl);
+}
+
+static int mlxsw_sp_port_dcb_app_update(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	struct dcb_ieee_app_prio_map prio_map;
+	struct dcb_ieee_app_dscp_map dscp_map;
+	u8 default_prio;
+	bool have_dscp;
+	int err;
+
+	default_prio = mlxsw_sp_port_dcb_app_default_prio(mlxsw_sp_port);
+	have_dscp = mlxsw_sp_port_dcb_app_prio_dscp_map(mlxsw_sp_port,
+							&prio_map);
+
+	if (!have_dscp) {
+		err = mlxsw_sp_port_dcb_toggle_trust(mlxsw_sp_port,
+					MLXSW_REG_QPTS_TRUST_STATE_PCP);
+		if (err)
+			netdev_err(mlxsw_sp_port->dev, "Couldn't switch to trust L2\n");
+		return err;
+	}
+
+	mlxsw_sp_port_dcb_app_dscp_prio_map(mlxsw_sp_port, default_prio,
+					    &dscp_map);
+	err = mlxsw_sp_port_dcb_app_update_qpdpm(mlxsw_sp_port,
+						 &dscp_map);
+	if (err) {
+		netdev_err(mlxsw_sp_port->dev, "Couldn't configure priority map\n");
+		return err;
+	}
+
+	err = mlxsw_sp_port_dcb_app_update_qpdsm(mlxsw_sp_port,
+						 &prio_map);
+	if (err) {
+		netdev_err(mlxsw_sp_port->dev, "Couldn't configure DSCP rewrite map\n");
+		return err;
+	}
+
+	err = mlxsw_sp_port_dcb_toggle_trust(mlxsw_sp_port,
+					     MLXSW_REG_QPTS_TRUST_STATE_DSCP);
+	if (err) {
+		/* A failure to set trust DSCP means that the QPDPM and QPDSM
+		 * maps installed above are not in effect. And since we are here
+		 * attempting to set trust DSCP, we couldn't have attempted to
+		 * switch trust to PCP. Thus no cleanup is necessary.
+		 */
+		netdev_err(mlxsw_sp_port->dev, "Couldn't switch to trust L3\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static int mlxsw_sp_dcbnl_ieee_setapp(struct net_device *dev,
+				      struct dcb_app *app)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	int err;
+
+	err = mlxsw_sp_dcbnl_app_validate(dev, app);
+	if (err)
+		return err;
+
+	err = dcb_ieee_setapp(dev, app);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_port_dcb_app_update(mlxsw_sp_port);
+	if (err)
+		goto err_update;
+
+	return 0;
+
+err_update:
+	dcb_ieee_delapp(dev, app);
+	return err;
+}
+
+static int mlxsw_sp_dcbnl_ieee_delapp(struct net_device *dev,
+				      struct dcb_app *app)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	int err;
+
+	err = dcb_ieee_delapp(dev, app);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_port_dcb_app_update(mlxsw_sp_port);
+	if (err)
+		netdev_err(dev, "Failed to update DCB APP configuration\n");
+	return 0;
+}
+
 static int mlxsw_sp_dcbnl_ieee_getmaxrate(struct net_device *dev,
 					  struct ieee_maxrate *maxrate)
 {
@@ -394,6 +627,8 @@ static const struct dcbnl_rtnl_ops mlxsw_sp_dcbnl_ops = {
 	.ieee_setmaxrate	= mlxsw_sp_dcbnl_ieee_setmaxrate,
 	.ieee_getpfc		= mlxsw_sp_dcbnl_ieee_getpfc,
 	.ieee_setpfc		= mlxsw_sp_dcbnl_ieee_setpfc,
+	.ieee_setapp		= mlxsw_sp_dcbnl_ieee_setapp,
+	.ieee_delapp		= mlxsw_sp_dcbnl_ieee_delapp,
 
 	.getdcbx		= mlxsw_sp_dcbnl_getdcbx,
 	.setdcbx		= mlxsw_sp_dcbnl_setdcbx,
@@ -467,6 +702,7 @@ int mlxsw_sp_port_dcb_init(struct mlxsw_sp_port *mlxsw_sp_port)
 	if (err)
 		goto err_port_pfc_init;
 
+	mlxsw_sp_port->dcb.trust_state = MLXSW_REG_QPTS_TRUST_STATE_PCP;
 	mlxsw_sp_port->dev->dcbnl_ops = &mlxsw_sp_dcbnl_ops;
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
index f56fa18d6b26..41e607a14846 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Arkadi Sharshevsky <arakdis@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <net/devlink.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
index 815d543cf114..e689576231ab 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Arkadi Sharshevsky <arkadis@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_PIPELINE_H_
 #define _MLXSW_PIPELINE_H_
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index 54262af4e98f..715d24ff937e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Ido Schimmel <idosch@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/bitops.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 89dbf569dff5..ebd1b24ebaa5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/errno.h>
@@ -48,7 +17,8 @@
 static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 					 struct mlxsw_sp_acl_block *block,
 					 struct mlxsw_sp_acl_rule_info *rulei,
-					 struct tcf_exts *exts)
+					 struct tcf_exts *exts,
+					 struct netlink_ext_ack *extack)
 {
 	const struct tc_action *a;
 	LIST_HEAD(actions);
@@ -58,7 +28,7 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 		return 0;
 
 	/* Count action is inserted first */
-	err = mlxsw_sp_acl_rulei_act_count(mlxsw_sp, rulei);
+	err = mlxsw_sp_acl_rulei_act_count(mlxsw_sp, rulei, extack);
 	if (err)
 		return err;
 
@@ -66,16 +36,22 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 	list_for_each_entry(a, &actions, list) {
 		if (is_tcf_gact_ok(a)) {
 			err = mlxsw_sp_acl_rulei_act_terminate(rulei);
-			if (err)
+			if (err) {
+				NL_SET_ERR_MSG_MOD(extack, "Cannot append terminate action");
 				return err;
+			}
 		} else if (is_tcf_gact_shot(a)) {
 			err = mlxsw_sp_acl_rulei_act_drop(rulei);
-			if (err)
+			if (err) {
+				NL_SET_ERR_MSG_MOD(extack, "Cannot append drop action");
 				return err;
+			}
 		} else if (is_tcf_gact_trap(a)) {
 			err = mlxsw_sp_acl_rulei_act_trap(rulei);
-			if (err)
+			if (err) {
+				NL_SET_ERR_MSG_MOD(extack, "Cannot append trap action");
 				return err;
+			}
 		} else if (is_tcf_gact_goto_chain(a)) {
 			u32 chain_index = tcf_gact_goto_chain_index(a);
 			struct mlxsw_sp_acl_ruleset *ruleset;
@@ -89,8 +65,10 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 
 			group_id = mlxsw_sp_acl_ruleset_group_id(ruleset);
 			err = mlxsw_sp_acl_rulei_act_jump(rulei, group_id);
-			if (err)
+			if (err) {
+				NL_SET_ERR_MSG_MOD(extack, "Cannot append jump action");
 				return err;
+			}
 		} else if (is_tcf_mirred_egress_redirect(a)) {
 			struct net_device *out_dev;
 			struct mlxsw_sp_fid *fid;
@@ -99,20 +77,21 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 			fid = mlxsw_sp_acl_dummy_fid(mlxsw_sp);
 			fid_index = mlxsw_sp_fid_index(fid);
 			err = mlxsw_sp_acl_rulei_act_fid_set(mlxsw_sp, rulei,
-							     fid_index);
+							     fid_index, extack);
 			if (err)
 				return err;
 
 			out_dev = tcf_mirred_dev(a);
 			err = mlxsw_sp_acl_rulei_act_fwd(mlxsw_sp, rulei,
-							 out_dev);
+							 out_dev, extack);
 			if (err)
 				return err;
 		} else if (is_tcf_mirred_egress_mirror(a)) {
 			struct net_device *out_dev = tcf_mirred_dev(a);
 
 			err = mlxsw_sp_acl_rulei_act_mirror(mlxsw_sp, rulei,
-							    block, out_dev);
+							    block, out_dev,
+							    extack);
 			if (err)
 				return err;
 		} else if (is_tcf_vlan(a)) {
@@ -123,8 +102,9 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 
 			return mlxsw_sp_acl_rulei_act_vlan(mlxsw_sp, rulei,
 							   action, vid,
-							   proto, prio);
+							   proto, prio, extack);
 		} else {
+			NL_SET_ERR_MSG_MOD(extack, "Unsupported action");
 			dev_err(mlxsw_sp->bus_info->dev, "Unsupported action\n");
 			return -EOPNOTSUPP;
 		}
@@ -144,10 +124,12 @@ static void mlxsw_sp_flower_parse_ipv4(struct mlxsw_sp_acl_rule_info *rulei,
 					  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
 					  f->mask);
 
-	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_SRC_IP4,
-				       ntohl(key->src), ntohl(mask->src));
-	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_DST_IP4,
-				       ntohl(key->dst), ntohl(mask->dst));
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+				       (char *) &key->src,
+				       (char *) &mask->src, 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_0_31,
+				       (char *) &key->dst,
+				       (char *) &mask->dst, 4);
 }
 
 static void mlxsw_sp_flower_parse_ipv6(struct mlxsw_sp_acl_rule_info *rulei,
@@ -161,24 +143,31 @@ static void mlxsw_sp_flower_parse_ipv6(struct mlxsw_sp_acl_rule_info *rulei,
 		skb_flow_dissector_target(f->dissector,
 					  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
 					  f->mask);
-	size_t addr_half_size = sizeof(key->src) / 2;
-
-	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP6_HI,
-				       &key->src.s6_addr[0],
-				       &mask->src.s6_addr[0],
-				       addr_half_size);
-	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP6_LO,
-				       &key->src.s6_addr[addr_half_size],
-				       &mask->src.s6_addr[addr_half_size],
-				       addr_half_size);
-	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP6_HI,
-				       &key->dst.s6_addr[0],
-				       &mask->dst.s6_addr[0],
-				       addr_half_size);
-	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP6_LO,
-				       &key->dst.s6_addr[addr_half_size],
-				       &mask->dst.s6_addr[addr_half_size],
-				       addr_half_size);
+
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_96_127,
+				       &key->src.s6_addr[0x0],
+				       &mask->src.s6_addr[0x0], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_64_95,
+				       &key->src.s6_addr[0x4],
+				       &mask->src.s6_addr[0x4], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_32_63,
+				       &key->src.s6_addr[0x8],
+				       &mask->src.s6_addr[0x8], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+				       &key->src.s6_addr[0xC],
+				       &mask->src.s6_addr[0xC], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_96_127,
+				       &key->dst.s6_addr[0x0],
+				       &mask->dst.s6_addr[0x0], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_64_95,
+				       &key->dst.s6_addr[0x4],
+				       &mask->dst.s6_addr[0x4], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_32_63,
+				       &key->dst.s6_addr[0x8],
+				       &mask->dst.s6_addr[0x8], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_0_31,
+				       &key->dst.s6_addr[0xC],
+				       &mask->dst.s6_addr[0xC], 4);
 }
 
 static int mlxsw_sp_flower_parse_ports(struct mlxsw_sp *mlxsw_sp,
@@ -192,6 +181,7 @@ static int mlxsw_sp_flower_parse_ports(struct mlxsw_sp *mlxsw_sp,
 		return 0;
 
 	if (ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) {
+		NL_SET_ERR_MSG_MOD(f->common.extack, "Only UDP and TCP keys are supported");
 		dev_err(mlxsw_sp->bus_info->dev, "Only UDP and TCP keys are supported\n");
 		return -EINVAL;
 	}
@@ -220,6 +210,7 @@ static int mlxsw_sp_flower_parse_tcp(struct mlxsw_sp *mlxsw_sp,
 		return 0;
 
 	if (ip_proto != IPPROTO_TCP) {
+		NL_SET_ERR_MSG_MOD(f->common.extack, "TCP keys supported only for TCP");
 		dev_err(mlxsw_sp->bus_info->dev, "TCP keys supported only for TCP\n");
 		return -EINVAL;
 	}
@@ -246,6 +237,7 @@ static int mlxsw_sp_flower_parse_ip(struct mlxsw_sp *mlxsw_sp,
 		return 0;
 
 	if (n_proto != ETH_P_IP && n_proto != ETH_P_IPV6) {
+		NL_SET_ERR_MSG_MOD(f->common.extack, "IP keys supported only for IPv4/6");
 		dev_err(mlxsw_sp->bus_info->dev, "IP keys supported only for IPv4/6\n");
 		return -EINVAL;
 	}
@@ -290,6 +282,7 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 	      BIT(FLOW_DISSECTOR_KEY_IP) |
 	      BIT(FLOW_DISSECTOR_KEY_VLAN))) {
 		dev_err(mlxsw_sp->bus_info->dev, "Unsupported key\n");
+		NL_SET_ERR_MSG_MOD(f->common.extack, "Unsupported key");
 		return -EOPNOTSUPP;
 	}
 
@@ -340,13 +333,17 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 						  f->mask);
 
 		mlxsw_sp_acl_rulei_keymask_buf(rulei,
-					       MLXSW_AFK_ELEMENT_DMAC,
-					       key->dst, mask->dst,
-					       sizeof(key->dst));
+					       MLXSW_AFK_ELEMENT_DMAC_32_47,
+					       key->dst, mask->dst, 2);
 		mlxsw_sp_acl_rulei_keymask_buf(rulei,
-					       MLXSW_AFK_ELEMENT_SMAC,
-					       key->src, mask->src,
-					       sizeof(key->src));
+					       MLXSW_AFK_ELEMENT_DMAC_0_31,
+					       key->dst + 2, mask->dst + 2, 4);
+		mlxsw_sp_acl_rulei_keymask_buf(rulei,
+					       MLXSW_AFK_ELEMENT_SMAC_32_47,
+					       key->src, mask->src, 2);
+		mlxsw_sp_acl_rulei_keymask_buf(rulei,
+					       MLXSW_AFK_ELEMENT_SMAC_0_31,
+					       key->src + 2, mask->src + 2, 4);
 	}
 
 	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
@@ -358,6 +355,11 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 			skb_flow_dissector_target(f->dissector,
 						  FLOW_DISSECTOR_KEY_VLAN,
 						  f->mask);
+
+		if (mlxsw_sp_acl_block_is_egress_bound(block)) {
+			NL_SET_ERR_MSG_MOD(f->common.extack, "vlan_id key is not supported on egress");
+			return -EOPNOTSUPP;
+		}
 		if (mask->vlan_id != 0)
 			mlxsw_sp_acl_rulei_keymask_u32(rulei,
 						       MLXSW_AFK_ELEMENT_VID,
@@ -387,7 +389,8 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		return err;
 
-	return mlxsw_sp_flower_parse_actions(mlxsw_sp, block, rulei, f->exts);
+	return mlxsw_sp_flower_parse_actions(mlxsw_sp, block, rulei, f->exts,
+					     f->common.extack);
 }
 
 int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
@@ -401,11 +404,12 @@ int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
 
 	ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, block,
 					   f->common.chain_index,
-					   MLXSW_SP_ACL_PROFILE_FLOWER);
+					   MLXSW_SP_ACL_PROFILE_FLOWER, NULL);
 	if (IS_ERR(ruleset))
 		return PTR_ERR(ruleset);
 
-	rule = mlxsw_sp_acl_rule_create(mlxsw_sp, ruleset, f->cookie);
+	rule = mlxsw_sp_acl_rule_create(mlxsw_sp, ruleset, f->cookie,
+					f->common.extack);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
 		goto err_rule_create;
@@ -445,7 +449,7 @@ void mlxsw_sp_flower_destroy(struct mlxsw_sp *mlxsw_sp,
 
 	ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, block,
 					   f->common.chain_index,
-					   MLXSW_SP_ACL_PROFILE_FLOWER);
+					   MLXSW_SP_ACL_PROFILE_FLOWER, NULL);
 	if (IS_ERR(ruleset))
 		return;
 
@@ -471,7 +475,7 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp,
 
 	ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, block,
 					   f->common.chain_index,
-					   MLXSW_SP_ACL_PROFILE_FLOWER);
+					   MLXSW_SP_ACL_PROFILE_FLOWER, NULL);
 	if (WARN_ON(IS_ERR(ruleset)))
 		return -EINVAL;
 
@@ -493,3 +497,40 @@ err_rule_get_stats:
 	mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
 	return err;
 }
+
+int mlxsw_sp_flower_tmplt_create(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_block *block,
+				 struct tc_cls_flower_offload *f)
+{
+	struct mlxsw_sp_acl_ruleset *ruleset;
+	struct mlxsw_sp_acl_rule_info rulei;
+	int err;
+
+	memset(&rulei, 0, sizeof(rulei));
+	err = mlxsw_sp_flower_parse(mlxsw_sp, block, &rulei, f);
+	if (err)
+		return err;
+	ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, block,
+					   f->common.chain_index,
+					   MLXSW_SP_ACL_PROFILE_FLOWER,
+					   &rulei.values.elusage);
+
+	/* keep the reference to the ruleset */
+	return PTR_ERR_OR_ZERO(ruleset);
+}
+
+void mlxsw_sp_flower_tmplt_destroy(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_acl_block *block,
+				   struct tc_cls_flower_offload *f)
+{
+	struct mlxsw_sp_acl_ruleset *ruleset;
+
+	ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, block,
+					   f->common.chain_index,
+					   MLXSW_SP_ACL_PROFILE_FLOWER, NULL);
+	if (IS_ERR(ruleset))
+		return;
+	/* put the reference to the ruleset kept in create */
+	mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
+	mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
index 98d896c14b87..00db26c96bf5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
- * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017-2018 Petr Machata <petrm@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <net/ip_tunnels.h>
 #include <net/ip6_tunnel.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h
index 6909d867bb59..bb5c4d4a5872 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h
- * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017-2018 Petr Machata <petrm@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_IPIP_H_
 #define _MLXSW_IPIP_H_
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
index fe4327f547d2..1e4cdee7bcd7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
@@ -1,454 +1,75 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
- * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
-#include <linux/bitops.h>
+#include <linux/slab.h>
 
 #include "spectrum.h"
 
-#define MLXSW_SP_KVDL_SINGLE_BASE 0
-#define MLXSW_SP_KVDL_SINGLE_SIZE 16384
-#define MLXSW_SP_KVDL_SINGLE_END \
-	(MLXSW_SP_KVDL_SINGLE_SIZE + MLXSW_SP_KVDL_SINGLE_BASE - 1)
-
-#define MLXSW_SP_KVDL_CHUNKS_BASE \
-	(MLXSW_SP_KVDL_SINGLE_BASE + MLXSW_SP_KVDL_SINGLE_SIZE)
-#define MLXSW_SP_KVDL_CHUNKS_SIZE 49152
-#define MLXSW_SP_KVDL_CHUNKS_END \
-	(MLXSW_SP_KVDL_CHUNKS_SIZE + MLXSW_SP_KVDL_CHUNKS_BASE - 1)
-
-#define MLXSW_SP_KVDL_LARGE_CHUNKS_BASE \
-	(MLXSW_SP_KVDL_CHUNKS_BASE + MLXSW_SP_KVDL_CHUNKS_SIZE)
-#define MLXSW_SP_KVDL_LARGE_CHUNKS_SIZE \
-	(MLXSW_SP_KVD_LINEAR_SIZE - MLXSW_SP_KVDL_LARGE_CHUNKS_BASE)
-#define MLXSW_SP_KVDL_LARGE_CHUNKS_END \
-	(MLXSW_SP_KVDL_LARGE_CHUNKS_SIZE + MLXSW_SP_KVDL_LARGE_CHUNKS_BASE - 1)
-
-#define MLXSW_SP_KVDL_SINGLE_ALLOC_SIZE 1
-#define MLXSW_SP_KVDL_CHUNKS_ALLOC_SIZE 32
-#define MLXSW_SP_KVDL_LARGE_CHUNKS_ALLOC_SIZE 512
-
-struct mlxsw_sp_kvdl_part_info {
-	unsigned int part_index;
-	unsigned int start_index;
-	unsigned int end_index;
-	unsigned int alloc_size;
-	enum mlxsw_sp_resource_id resource_id;
-};
-
-enum mlxsw_sp_kvdl_part_id {
-	MLXSW_SP_KVDL_PART_ID_SINGLE,
-	MLXSW_SP_KVDL_PART_ID_CHUNKS,
-	MLXSW_SP_KVDL_PART_ID_LARGE_CHUNKS,
-};
-
-#define MLXSW_SP_KVDL_PART_INFO(id)				\
-[MLXSW_SP_KVDL_PART_ID_##id] = {				\
-	.start_index = MLXSW_SP_KVDL_##id##_BASE,		\
-	.end_index = MLXSW_SP_KVDL_##id##_END,			\
-	.alloc_size = MLXSW_SP_KVDL_##id##_ALLOC_SIZE,		\
-	.resource_id = MLXSW_SP_RESOURCE_KVD_LINEAR_##id,	\
-}
-
-static const struct mlxsw_sp_kvdl_part_info mlxsw_sp_kvdl_parts_info[] = {
-	MLXSW_SP_KVDL_PART_INFO(SINGLE),
-	MLXSW_SP_KVDL_PART_INFO(CHUNKS),
-	MLXSW_SP_KVDL_PART_INFO(LARGE_CHUNKS),
-};
-
-#define MLXSW_SP_KVDL_PARTS_INFO_LEN ARRAY_SIZE(mlxsw_sp_kvdl_parts_info)
-
-struct mlxsw_sp_kvdl_part {
-	struct mlxsw_sp_kvdl_part_info info;
-	unsigned long usage[0];	/* Entries */
-};
-
 struct mlxsw_sp_kvdl {
-	struct mlxsw_sp_kvdl_part *parts[MLXSW_SP_KVDL_PARTS_INFO_LEN];
+	const struct mlxsw_sp_kvdl_ops *kvdl_ops;
+	unsigned long priv[0];
+	/* priv has to be always the last item */
 };
 
-static struct mlxsw_sp_kvdl_part *
-mlxsw_sp_kvdl_alloc_size_part(struct mlxsw_sp_kvdl *kvdl,
-			      unsigned int alloc_size)
-{
-	struct mlxsw_sp_kvdl_part *part, *min_part = NULL;
-	int i;
-
-	for (i = 0; i < MLXSW_SP_KVDL_PARTS_INFO_LEN; i++) {
-		part = kvdl->parts[i];
-		if (alloc_size <= part->info.alloc_size &&
-		    (!min_part ||
-		     part->info.alloc_size <= min_part->info.alloc_size))
-			min_part = part;
-	}
-
-	return min_part ?: ERR_PTR(-ENOBUFS);
-}
-
-static struct mlxsw_sp_kvdl_part *
-mlxsw_sp_kvdl_index_part(struct mlxsw_sp_kvdl *kvdl, u32 kvdl_index)
-{
-	struct mlxsw_sp_kvdl_part *part;
-	int i;
-
-	for (i = 0; i < MLXSW_SP_KVDL_PARTS_INFO_LEN; i++) {
-		part = kvdl->parts[i];
-		if (kvdl_index >= part->info.start_index &&
-		    kvdl_index <= part->info.end_index)
-			return part;
-	}
-
-	return ERR_PTR(-EINVAL);
-}
-
-static u32
-mlxsw_sp_entry_index_kvdl_index(const struct mlxsw_sp_kvdl_part_info *info,
-				unsigned int entry_index)
-{
-	return info->start_index + entry_index * info->alloc_size;
-}
-
-static unsigned int
-mlxsw_sp_kvdl_index_entry_index(const struct mlxsw_sp_kvdl_part_info *info,
-				u32 kvdl_index)
-{
-	return (kvdl_index - info->start_index) / info->alloc_size;
-}
-
-static int mlxsw_sp_kvdl_part_alloc(struct mlxsw_sp_kvdl_part *part,
-				    u32 *p_kvdl_index)
-{
-	const struct mlxsw_sp_kvdl_part_info *info = &part->info;
-	unsigned int entry_index, nr_entries;
-
-	nr_entries = (info->end_index - info->start_index + 1) /
-		     info->alloc_size;
-	entry_index = find_first_zero_bit(part->usage, nr_entries);
-	if (entry_index == nr_entries)
-		return -ENOBUFS;
-	__set_bit(entry_index, part->usage);
-
-	*p_kvdl_index = mlxsw_sp_entry_index_kvdl_index(info, entry_index);
-
-	return 0;
-}
-
-static void mlxsw_sp_kvdl_part_free(struct mlxsw_sp_kvdl_part *part,
-				    u32 kvdl_index)
-{
-	const struct mlxsw_sp_kvdl_part_info *info = &part->info;
-	unsigned int entry_index;
-
-	entry_index = mlxsw_sp_kvdl_index_entry_index(info, kvdl_index);
-	__clear_bit(entry_index, part->usage);
-}
-
-int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count,
-			u32 *p_entry_index)
-{
-	struct mlxsw_sp_kvdl_part *part;
-
-	/* Find partition with smallest allocation size satisfying the
-	 * requested size.
-	 */
-	part = mlxsw_sp_kvdl_alloc_size_part(mlxsw_sp->kvdl, entry_count);
-	if (IS_ERR(part))
-		return PTR_ERR(part);
-
-	return mlxsw_sp_kvdl_part_alloc(part, p_entry_index);
-}
-
-void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index)
-{
-	struct mlxsw_sp_kvdl_part *part;
-
-	part = mlxsw_sp_kvdl_index_part(mlxsw_sp->kvdl, entry_index);
-	if (IS_ERR(part))
-		return;
-	mlxsw_sp_kvdl_part_free(part, entry_index);
-}
-
-int mlxsw_sp_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp,
-				   unsigned int entry_count,
-				   unsigned int *p_alloc_size)
-{
-	struct mlxsw_sp_kvdl_part *part;
-
-	part = mlxsw_sp_kvdl_alloc_size_part(mlxsw_sp->kvdl, entry_count);
-	if (IS_ERR(part))
-		return PTR_ERR(part);
-
-	*p_alloc_size = part->info.alloc_size;
-
-	return 0;
-}
-
-static void mlxsw_sp_kvdl_part_update(struct mlxsw_sp_kvdl_part *part,
-				      struct mlxsw_sp_kvdl_part *part_prev,
-				      unsigned int size)
-{
-
-	if (!part_prev) {
-		part->info.end_index = size - 1;
-	} else {
-		part->info.start_index = part_prev->info.end_index + 1;
-		part->info.end_index = part->info.start_index + size - 1;
-	}
-}
-
-static struct mlxsw_sp_kvdl_part *
-mlxsw_sp_kvdl_part_init(struct mlxsw_sp *mlxsw_sp,
-			const struct mlxsw_sp_kvdl_part_info *info,
-			struct mlxsw_sp_kvdl_part *part_prev)
+int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp)
 {
-	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
-	struct mlxsw_sp_kvdl_part *part;
-	bool need_update = true;
-	unsigned int nr_entries;
-	size_t usage_size;
-	u64 resource_size;
+	const struct mlxsw_sp_kvdl_ops *kvdl_ops = mlxsw_sp->kvdl_ops;
+	struct mlxsw_sp_kvdl *kvdl;
 	int err;
 
-	err = devlink_resource_size_get(devlink, info->resource_id,
-					&resource_size);
-	if (err) {
-		need_update = false;
-		resource_size = info->end_index - info->start_index + 1;
-	}
-
-	nr_entries = div_u64(resource_size, info->alloc_size);
-	usage_size = BITS_TO_LONGS(nr_entries) * sizeof(unsigned long);
-	part = kzalloc(sizeof(*part) + usage_size, GFP_KERNEL);
-	if (!part)
-		return ERR_PTR(-ENOMEM);
-
-	memcpy(&part->info, info, sizeof(part->info));
-
-	if (need_update)
-		mlxsw_sp_kvdl_part_update(part, part_prev, resource_size);
-	return part;
-}
-
-static void mlxsw_sp_kvdl_part_fini(struct mlxsw_sp_kvdl_part *part)
-{
-	kfree(part);
-}
-
-static int mlxsw_sp_kvdl_parts_init(struct mlxsw_sp *mlxsw_sp)
-{
-	struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl;
-	const struct mlxsw_sp_kvdl_part_info *info;
-	struct mlxsw_sp_kvdl_part *part_prev = NULL;
-	int err, i;
+	kvdl = kzalloc(sizeof(*mlxsw_sp->kvdl) + kvdl_ops->priv_size,
+		       GFP_KERNEL);
+	if (!kvdl)
+		return -ENOMEM;
+	kvdl->kvdl_ops = kvdl_ops;
+	mlxsw_sp->kvdl = kvdl;
 
-	for (i = 0; i < MLXSW_SP_KVDL_PARTS_INFO_LEN; i++) {
-		info = &mlxsw_sp_kvdl_parts_info[i];
-		kvdl->parts[i] = mlxsw_sp_kvdl_part_init(mlxsw_sp, info,
-							 part_prev);
-		if (IS_ERR(kvdl->parts[i])) {
-			err = PTR_ERR(kvdl->parts[i]);
-			goto err_kvdl_part_init;
-		}
-		part_prev = kvdl->parts[i];
-	}
+	err = kvdl_ops->init(mlxsw_sp, kvdl->priv);
+	if (err)
+		goto err_init;
 	return 0;
 
-err_kvdl_part_init:
-	for (i--; i >= 0; i--)
-		mlxsw_sp_kvdl_part_fini(kvdl->parts[i]);
+err_init:
+	kfree(kvdl);
 	return err;
 }
 
-static void mlxsw_sp_kvdl_parts_fini(struct mlxsw_sp *mlxsw_sp)
+void mlxsw_sp_kvdl_fini(struct mlxsw_sp *mlxsw_sp)
 {
 	struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl;
-	int i;
-
-	for (i = 0; i < MLXSW_SP_KVDL_PARTS_INFO_LEN; i++)
-		mlxsw_sp_kvdl_part_fini(kvdl->parts[i]);
-}
-
-static u64 mlxsw_sp_kvdl_part_occ(struct mlxsw_sp_kvdl_part *part)
-{
-	const struct mlxsw_sp_kvdl_part_info *info = &part->info;
-	unsigned int nr_entries;
-	int bit = -1;
-	u64 occ = 0;
-
-	nr_entries = (info->end_index -
-		      info->start_index + 1) /
-		      info->alloc_size;
-	while ((bit = find_next_bit(part->usage, nr_entries, bit + 1))
-		< nr_entries)
-		occ += info->alloc_size;
-	return occ;
-}
-
-static u64 mlxsw_sp_kvdl_occ_get(void *priv)
-{
-	const struct mlxsw_sp *mlxsw_sp = priv;
-	u64 occ = 0;
-	int i;
-
-	for (i = 0; i < MLXSW_SP_KVDL_PARTS_INFO_LEN; i++)
-		occ += mlxsw_sp_kvdl_part_occ(mlxsw_sp->kvdl->parts[i]);
-
-	return occ;
-}
-
-static u64 mlxsw_sp_kvdl_single_occ_get(void *priv)
-{
-	const struct mlxsw_sp *mlxsw_sp = priv;
-	struct mlxsw_sp_kvdl_part *part;
-
-	part = mlxsw_sp->kvdl->parts[MLXSW_SP_KVDL_PART_ID_SINGLE];
-	return mlxsw_sp_kvdl_part_occ(part);
-}
-
-static u64 mlxsw_sp_kvdl_chunks_occ_get(void *priv)
-{
-	const struct mlxsw_sp *mlxsw_sp = priv;
-	struct mlxsw_sp_kvdl_part *part;
-
-	part = mlxsw_sp->kvdl->parts[MLXSW_SP_KVDL_PART_ID_CHUNKS];
-	return mlxsw_sp_kvdl_part_occ(part);
-}
-
-static u64 mlxsw_sp_kvdl_large_chunks_occ_get(void *priv)
-{
-	const struct mlxsw_sp *mlxsw_sp = priv;
-	struct mlxsw_sp_kvdl_part *part;
 
-	part = mlxsw_sp->kvdl->parts[MLXSW_SP_KVDL_PART_ID_LARGE_CHUNKS];
-	return mlxsw_sp_kvdl_part_occ(part);
+	kvdl->kvdl_ops->fini(mlxsw_sp, kvdl->priv);
+	kfree(kvdl);
 }
 
-int mlxsw_sp_kvdl_resources_register(struct mlxsw_core *mlxsw_core)
+int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp,
+			enum mlxsw_sp_kvdl_entry_type type,
+			unsigned int entry_count, u32 *p_entry_index)
 {
-	struct devlink *devlink = priv_to_devlink(mlxsw_core);
-	static struct devlink_resource_size_params size_params;
-	u32 kvdl_max_size;
-	int err;
-
-	kvdl_max_size = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SIZE) -
-			MLXSW_CORE_RES_GET(mlxsw_core, KVD_SINGLE_MIN_SIZE) -
-			MLXSW_CORE_RES_GET(mlxsw_core, KVD_DOUBLE_MIN_SIZE);
-
-	devlink_resource_size_params_init(&size_params, 0, kvdl_max_size,
-					  MLXSW_SP_KVDL_SINGLE_ALLOC_SIZE,
-					  DEVLINK_RESOURCE_UNIT_ENTRY);
-	err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_SINGLES,
-					MLXSW_SP_KVDL_SINGLE_SIZE,
-					MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE,
-					MLXSW_SP_RESOURCE_KVD_LINEAR,
-					&size_params);
-	if (err)
-		return err;
-
-	devlink_resource_size_params_init(&size_params, 0, kvdl_max_size,
-					  MLXSW_SP_KVDL_CHUNKS_ALLOC_SIZE,
-					  DEVLINK_RESOURCE_UNIT_ENTRY);
-	err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_CHUNKS,
-					MLXSW_SP_KVDL_CHUNKS_SIZE,
-					MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS,
-					MLXSW_SP_RESOURCE_KVD_LINEAR,
-					&size_params);
-	if (err)
-		return err;
+	struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl;
 
-	devlink_resource_size_params_init(&size_params, 0, kvdl_max_size,
-					  MLXSW_SP_KVDL_LARGE_CHUNKS_ALLOC_SIZE,
-					  DEVLINK_RESOURCE_UNIT_ENTRY);
-	err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_LARGE_CHUNKS,
-					MLXSW_SP_KVDL_LARGE_CHUNKS_SIZE,
-					MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS,
-					MLXSW_SP_RESOURCE_KVD_LINEAR,
-					&size_params);
-	return err;
+	return kvdl->kvdl_ops->alloc(mlxsw_sp, kvdl->priv, type,
+				     entry_count, p_entry_index);
 }
 
-int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp)
+void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp,
+			enum mlxsw_sp_kvdl_entry_type type,
+			unsigned int entry_count, int entry_index)
 {
-	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
-	struct mlxsw_sp_kvdl *kvdl;
-	int err;
-
-	kvdl = kzalloc(sizeof(*mlxsw_sp->kvdl), GFP_KERNEL);
-	if (!kvdl)
-		return -ENOMEM;
-	mlxsw_sp->kvdl = kvdl;
-
-	err = mlxsw_sp_kvdl_parts_init(mlxsw_sp);
-	if (err)
-		goto err_kvdl_parts_init;
-
-	devlink_resource_occ_get_register(devlink,
-					  MLXSW_SP_RESOURCE_KVD_LINEAR,
-					  mlxsw_sp_kvdl_occ_get,
-					  mlxsw_sp);
-	devlink_resource_occ_get_register(devlink,
-					  MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE,
-					  mlxsw_sp_kvdl_single_occ_get,
-					  mlxsw_sp);
-	devlink_resource_occ_get_register(devlink,
-					  MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS,
-					  mlxsw_sp_kvdl_chunks_occ_get,
-					  mlxsw_sp);
-	devlink_resource_occ_get_register(devlink,
-					  MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS,
-					  mlxsw_sp_kvdl_large_chunks_occ_get,
-					  mlxsw_sp);
-
-	return 0;
+	struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl;
 
-err_kvdl_parts_init:
-	kfree(mlxsw_sp->kvdl);
-	return err;
+	kvdl->kvdl_ops->free(mlxsw_sp, kvdl->priv, type,
+			     entry_count, entry_index);
 }
 
-void mlxsw_sp_kvdl_fini(struct mlxsw_sp *mlxsw_sp)
+int mlxsw_sp_kvdl_alloc_count_query(struct mlxsw_sp *mlxsw_sp,
+				    enum mlxsw_sp_kvdl_entry_type type,
+				    unsigned int entry_count,
+				    unsigned int *p_alloc_count)
 {
-	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+	struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl;
 
-	devlink_resource_occ_get_unregister(devlink,
-					    MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS);
-	devlink_resource_occ_get_unregister(devlink,
-					    MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS);
-	devlink_resource_occ_get_unregister(devlink,
-					    MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE);
-	devlink_resource_occ_get_unregister(devlink,
-					    MLXSW_SP_RESOURCE_KVD_LINEAR);
-	mlxsw_sp_kvdl_parts_fini(mlxsw_sp);
-	kfree(mlxsw_sp->kvdl);
+	return kvdl->kvdl_ops->alloc_size_query(mlxsw_sp, kvdl->priv, type,
+						entry_count, p_alloc_count);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
index a82539609d49..54275624718b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/rhashtable.h>
 #include <net/ipv6.h>
@@ -1075,6 +1044,6 @@ void mlxsw_sp_mr_fini(struct mlxsw_sp *mlxsw_sp)
 	struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
 
 	cancel_delayed_work_sync(&mr->stats_update_dw);
-	mr->mr_ops->fini(mr->priv);
+	mr->mr_ops->fini(mlxsw_sp, mr->priv);
 	kfree(mr);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h
index 7c864a86811d..3cde3671fe35 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_SPECTRUM_MCROUTER_H
 #define _MLXSW_SPECTRUM_MCROUTER_H
@@ -46,15 +15,6 @@ enum mlxsw_sp_mr_route_action {
 	MLXSW_SP_MR_ROUTE_ACTION_TRAP_AND_FORWARD,
 };
 
-enum mlxsw_sp_mr_route_prio {
-	MLXSW_SP_MR_ROUTE_PRIO_SG,
-	MLXSW_SP_MR_ROUTE_PRIO_STARG,
-	MLXSW_SP_MR_ROUTE_PRIO_CATCHALL,
-	__MLXSW_SP_MR_ROUTE_PRIO_MAX
-};
-
-#define MLXSW_SP_MR_ROUTE_PRIO_MAX (__MLXSW_SP_MR_ROUTE_PRIO_MAX - 1)
-
 struct mlxsw_sp_mr_route_key {
 	int vrid;
 	enum mlxsw_sp_l3proto proto;
@@ -101,7 +61,7 @@ struct mlxsw_sp_mr_ops {
 			      u16 erif_index);
 	void (*route_destroy)(struct mlxsw_sp *mlxsw_sp, void *priv,
 			      void *route_priv);
-	void (*fini)(void *priv);
+	void (*fini)(struct mlxsw_sp *mlxsw_sp, void *priv);
 };
 
 struct mlxsw_sp_mr;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
index 4f4c0d311883..346f4a5fe053 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
@@ -1,41 +1,9 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/netdevice.h>
-#include <linux/parman.h>
 
 #include "spectrum_mr_tcam.h"
 #include "reg.h"
@@ -43,15 +11,8 @@
 #include "core_acl_flex_actions.h"
 #include "spectrum_mr.h"
 
-struct mlxsw_sp_mr_tcam_region {
-	struct mlxsw_sp *mlxsw_sp;
-	enum mlxsw_reg_rtar_key_type rtar_key_type;
-	struct parman *parman;
-	struct parman_prio *parman_prios;
-};
-
 struct mlxsw_sp_mr_tcam {
-	struct mlxsw_sp_mr_tcam_region tcam_regions[MLXSW_SP_L3_PROTO_MAX];
+	void *priv;
 };
 
 /* This struct maps to one RIGR2 register entry */
@@ -84,8 +45,6 @@ mlxsw_sp_mr_erif_list_init(struct mlxsw_sp_mr_tcam_erif_list *erif_list)
 	INIT_LIST_HEAD(&erif_list->erif_sublists);
 }
 
-#define MLXSW_SP_KVDL_RIGR2_SIZE 1
-
 static struct mlxsw_sp_mr_erif_sublist *
 mlxsw_sp_mr_erif_sublist_create(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_mr_tcam_erif_list *erif_list)
@@ -96,8 +55,8 @@ mlxsw_sp_mr_erif_sublist_create(struct mlxsw_sp *mlxsw_sp,
 	erif_sublist = kzalloc(sizeof(*erif_sublist), GFP_KERNEL);
 	if (!erif_sublist)
 		return ERR_PTR(-ENOMEM);
-	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_RIGR2_SIZE,
-				  &erif_sublist->rigr2_kvdl_index);
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR,
+				  1, &erif_sublist->rigr2_kvdl_index);
 	if (err) {
 		kfree(erif_sublist);
 		return ERR_PTR(err);
@@ -112,7 +71,8 @@ mlxsw_sp_mr_erif_sublist_destroy(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_mr_erif_sublist *erif_sublist)
 {
 	list_del(&erif_sublist->list);
-	mlxsw_sp_kvdl_free(mlxsw_sp, erif_sublist->rigr2_kvdl_index);
+	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR,
+			   1, erif_sublist->rigr2_kvdl_index);
 	kfree(erif_sublist);
 }
 
@@ -221,12 +181,11 @@ struct mlxsw_sp_mr_tcam_route {
 	struct mlxsw_sp_mr_tcam_erif_list erif_list;
 	struct mlxsw_afa_block *afa_block;
 	u32 counter_index;
-	struct parman_item parman_item;
-	struct parman_prio *parman_prio;
 	enum mlxsw_sp_mr_route_action action;
 	struct mlxsw_sp_mr_route_key key;
 	u16 irif_index;
 	u16 min_mtu;
+	void *priv;
 };
 
 static struct mlxsw_afa_block *
@@ -297,60 +256,6 @@ mlxsw_sp_mr_tcam_afa_block_destroy(struct mlxsw_afa_block *afa_block)
 	mlxsw_afa_block_destroy(afa_block);
 }
 
-static int mlxsw_sp_mr_tcam_route_replace(struct mlxsw_sp *mlxsw_sp,
-					  struct parman_item *parman_item,
-					  struct mlxsw_sp_mr_route_key *key,
-					  struct mlxsw_afa_block *afa_block)
-{
-	char rmft2_pl[MLXSW_REG_RMFT2_LEN];
-
-	switch (key->proto) {
-	case MLXSW_SP_L3_PROTO_IPV4:
-		mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, true, parman_item->index,
-					  key->vrid,
-					  MLXSW_REG_RMFT2_IRIF_MASK_IGNORE, 0,
-					  ntohl(key->group.addr4),
-					  ntohl(key->group_mask.addr4),
-					  ntohl(key->source.addr4),
-					  ntohl(key->source_mask.addr4),
-					  mlxsw_afa_block_first_set(afa_block));
-		break;
-	case MLXSW_SP_L3_PROTO_IPV6:
-		mlxsw_reg_rmft2_ipv6_pack(rmft2_pl, true, parman_item->index,
-					  key->vrid,
-					  MLXSW_REG_RMFT2_IRIF_MASK_IGNORE, 0,
-					  key->group.addr6,
-					  key->group_mask.addr6,
-					  key->source.addr6,
-					  key->source_mask.addr6,
-					  mlxsw_afa_block_first_set(afa_block));
-	}
-
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl);
-}
-
-static int mlxsw_sp_mr_tcam_route_remove(struct mlxsw_sp *mlxsw_sp, int vrid,
-					 struct mlxsw_sp_mr_route_key *key,
-					 struct parman_item *parman_item)
-{
-	struct in6_addr zero_addr = IN6ADDR_ANY_INIT;
-	char rmft2_pl[MLXSW_REG_RMFT2_LEN];
-
-	switch (key->proto) {
-	case MLXSW_SP_L3_PROTO_IPV4:
-		mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, false, parman_item->index,
-					  vrid, 0, 0, 0, 0, 0, 0, NULL);
-		break;
-	case MLXSW_SP_L3_PROTO_IPV6:
-		mlxsw_reg_rmft2_ipv6_pack(rmft2_pl, false, parman_item->index,
-					  vrid, 0, 0, zero_addr, zero_addr,
-					  zero_addr, zero_addr, NULL);
-		break;
-	}
-
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl);
-}
-
 static int
 mlxsw_sp_mr_tcam_erif_populate(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_mr_tcam_erif_list *erif_list,
@@ -370,51 +275,12 @@ mlxsw_sp_mr_tcam_erif_populate(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 }
 
-static struct mlxsw_sp_mr_tcam_region *
-mlxsw_sp_mr_tcam_protocol_region(struct mlxsw_sp_mr_tcam *mr_tcam,
-				 enum mlxsw_sp_l3proto proto)
-{
-	return &mr_tcam->tcam_regions[proto];
-}
-
-static int
-mlxsw_sp_mr_tcam_route_parman_item_add(struct mlxsw_sp_mr_tcam *mr_tcam,
-				       struct mlxsw_sp_mr_tcam_route *route,
-				       enum mlxsw_sp_mr_route_prio prio)
-{
-	struct mlxsw_sp_mr_tcam_region *tcam_region;
-	int err;
-
-	tcam_region = mlxsw_sp_mr_tcam_protocol_region(mr_tcam,
-						       route->key.proto);
-	err = parman_item_add(tcam_region->parman,
-			      &tcam_region->parman_prios[prio],
-			      &route->parman_item);
-	if (err)
-		return err;
-
-	route->parman_prio = &tcam_region->parman_prios[prio];
-	return 0;
-}
-
-static void
-mlxsw_sp_mr_tcam_route_parman_item_remove(struct mlxsw_sp_mr_tcam *mr_tcam,
-					  struct mlxsw_sp_mr_tcam_route *route)
-{
-	struct mlxsw_sp_mr_tcam_region *tcam_region;
-
-	tcam_region = mlxsw_sp_mr_tcam_protocol_region(mr_tcam,
-						       route->key.proto);
-
-	parman_item_remove(tcam_region->parman,
-			   route->parman_prio, &route->parman_item);
-}
-
 static int
 mlxsw_sp_mr_tcam_route_create(struct mlxsw_sp *mlxsw_sp, void *priv,
 			      void *route_priv,
 			      struct mlxsw_sp_mr_route_params *route_params)
 {
+	const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
 	struct mlxsw_sp_mr_tcam_route *route = route_priv;
 	struct mlxsw_sp_mr_tcam *mr_tcam = priv;
 	int err;
@@ -448,22 +314,23 @@ mlxsw_sp_mr_tcam_route_create(struct mlxsw_sp *mlxsw_sp, void *priv,
 		goto err_afa_block_create;
 	}
 
-	/* Allocate place in the TCAM */
-	err = mlxsw_sp_mr_tcam_route_parman_item_add(mr_tcam, route,
-						     route_params->prio);
-	if (err)
-		goto err_parman_item_add;
+	route->priv = kzalloc(ops->route_priv_size, GFP_KERNEL);
+	if (!route->priv) {
+		err = -ENOMEM;
+		goto err_route_priv_alloc;
+	}
 
 	/* Write the route to the TCAM */
-	err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
-					     &route->key, route->afa_block);
+	err = ops->route_create(mlxsw_sp, mr_tcam->priv, route->priv,
+				&route->key, route->afa_block,
+				route_params->prio);
 	if (err)
-		goto err_route_replace;
+		goto err_route_create;
 	return 0;
 
-err_route_replace:
-	mlxsw_sp_mr_tcam_route_parman_item_remove(mr_tcam, route);
-err_parman_item_add:
+err_route_create:
+	kfree(route->priv);
+err_route_priv_alloc:
 	mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block);
 err_afa_block_create:
 	mlxsw_sp_flow_counter_free(mlxsw_sp, route->counter_index);
@@ -476,12 +343,12 @@ err_counter_alloc:
 static void mlxsw_sp_mr_tcam_route_destroy(struct mlxsw_sp *mlxsw_sp,
 					   void *priv, void *route_priv)
 {
+	const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
 	struct mlxsw_sp_mr_tcam_route *route = route_priv;
 	struct mlxsw_sp_mr_tcam *mr_tcam = priv;
 
-	mlxsw_sp_mr_tcam_route_remove(mlxsw_sp, route->key.vrid,
-				      &route->key, &route->parman_item);
-	mlxsw_sp_mr_tcam_route_parman_item_remove(mr_tcam, route);
+	ops->route_destroy(mlxsw_sp, mr_tcam->priv, route->priv, &route->key);
+	kfree(route->priv);
 	mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block);
 	mlxsw_sp_flow_counter_free(mlxsw_sp, route->counter_index);
 	mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &route->erif_list);
@@ -502,6 +369,7 @@ mlxsw_sp_mr_tcam_route_action_update(struct mlxsw_sp *mlxsw_sp,
 				     void *route_priv,
 				     enum mlxsw_sp_mr_route_action route_action)
 {
+	const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
 	struct mlxsw_sp_mr_tcam_route *route = route_priv;
 	struct mlxsw_afa_block *afa_block;
 	int err;
@@ -516,8 +384,7 @@ mlxsw_sp_mr_tcam_route_action_update(struct mlxsw_sp *mlxsw_sp,
 		return PTR_ERR(afa_block);
 
 	/* Update the TCAM route entry */
-	err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
-					     &route->key, afa_block);
+	err = ops->route_update(mlxsw_sp, route->priv, &route->key, afa_block);
 	if (err)
 		goto err;
 
@@ -534,6 +401,7 @@ err:
 static int mlxsw_sp_mr_tcam_route_min_mtu_update(struct mlxsw_sp *mlxsw_sp,
 						 void *route_priv, u16 min_mtu)
 {
+	const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
 	struct mlxsw_sp_mr_tcam_route *route = route_priv;
 	struct mlxsw_afa_block *afa_block;
 	int err;
@@ -549,8 +417,7 @@ static int mlxsw_sp_mr_tcam_route_min_mtu_update(struct mlxsw_sp *mlxsw_sp,
 		return PTR_ERR(afa_block);
 
 	/* Update the TCAM route entry */
-	err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
-					     &route->key, afa_block);
+	err = ops->route_update(mlxsw_sp, route->priv, &route->key, afa_block);
 	if (err)
 		goto err;
 
@@ -596,6 +463,7 @@ static int mlxsw_sp_mr_tcam_route_erif_add(struct mlxsw_sp *mlxsw_sp,
 static int mlxsw_sp_mr_tcam_route_erif_del(struct mlxsw_sp *mlxsw_sp,
 					   void *route_priv, u16 erif_index)
 {
+	const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
 	struct mlxsw_sp_mr_tcam_route *route = route_priv;
 	struct mlxsw_sp_mr_erif_sublist *erif_sublist;
 	struct mlxsw_sp_mr_tcam_erif_list erif_list;
@@ -630,8 +498,7 @@ static int mlxsw_sp_mr_tcam_route_erif_del(struct mlxsw_sp *mlxsw_sp,
 	}
 
 	/* Update the TCAM route entry */
-	err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
-					     &route->key, afa_block);
+	err = ops->route_update(mlxsw_sp, route->priv, &route->key, afa_block);
 	if (err)
 		goto err_route_write;
 
@@ -653,6 +520,7 @@ static int
 mlxsw_sp_mr_tcam_route_update(struct mlxsw_sp *mlxsw_sp, void *route_priv,
 			      struct mlxsw_sp_mr_route_info *route_info)
 {
+	const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
 	struct mlxsw_sp_mr_tcam_route *route = route_priv;
 	struct mlxsw_sp_mr_tcam_erif_list erif_list;
 	struct mlxsw_afa_block *afa_block;
@@ -677,8 +545,7 @@ mlxsw_sp_mr_tcam_route_update(struct mlxsw_sp *mlxsw_sp, void *route_priv,
 	}
 
 	/* Update the TCAM route entry */
-	err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
-					     &route->key, afa_block);
+	err = ops->route_update(mlxsw_sp, route->priv, &route->key, afa_block);
 	if (err)
 		goto err_route_write;
 
@@ -699,167 +566,36 @@ err_erif_populate:
 	return err;
 }
 
-#define MLXSW_SP_MR_TCAM_REGION_BASE_COUNT 16
-#define MLXSW_SP_MR_TCAM_REGION_RESIZE_STEP 16
-
-static int
-mlxsw_sp_mr_tcam_region_alloc(struct mlxsw_sp_mr_tcam_region *mr_tcam_region)
-{
-	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
-	char rtar_pl[MLXSW_REG_RTAR_LEN];
-
-	mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_ALLOCATE,
-			    mr_tcam_region->rtar_key_type,
-			    MLXSW_SP_MR_TCAM_REGION_BASE_COUNT);
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
-}
-
-static void
-mlxsw_sp_mr_tcam_region_free(struct mlxsw_sp_mr_tcam_region *mr_tcam_region)
-{
-	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
-	char rtar_pl[MLXSW_REG_RTAR_LEN];
-
-	mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_DEALLOCATE,
-			    mr_tcam_region->rtar_key_type, 0);
-	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
-}
-
-static int mlxsw_sp_mr_tcam_region_parman_resize(void *priv,
-						 unsigned long new_count)
-{
-	struct mlxsw_sp_mr_tcam_region *mr_tcam_region = priv;
-	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
-	char rtar_pl[MLXSW_REG_RTAR_LEN];
-	u64 max_tcam_rules;
-
-	max_tcam_rules = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_TCAM_RULES);
-	if (new_count > max_tcam_rules)
-		return -EINVAL;
-	mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_RESIZE,
-			    mr_tcam_region->rtar_key_type, new_count);
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
-}
-
-static void mlxsw_sp_mr_tcam_region_parman_move(void *priv,
-						unsigned long from_index,
-						unsigned long to_index,
-						unsigned long count)
-{
-	struct mlxsw_sp_mr_tcam_region *mr_tcam_region = priv;
-	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
-	char rrcr_pl[MLXSW_REG_RRCR_LEN];
-
-	mlxsw_reg_rrcr_pack(rrcr_pl, MLXSW_REG_RRCR_OP_MOVE,
-			    from_index, count,
-			    mr_tcam_region->rtar_key_type, to_index);
-	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rrcr), rrcr_pl);
-}
-
-static const struct parman_ops mlxsw_sp_mr_tcam_region_parman_ops = {
-	.base_count	= MLXSW_SP_MR_TCAM_REGION_BASE_COUNT,
-	.resize_step	= MLXSW_SP_MR_TCAM_REGION_RESIZE_STEP,
-	.resize		= mlxsw_sp_mr_tcam_region_parman_resize,
-	.move		= mlxsw_sp_mr_tcam_region_parman_move,
-	.algo		= PARMAN_ALGO_TYPE_LSORT,
-};
-
-static int
-mlxsw_sp_mr_tcam_region_init(struct mlxsw_sp *mlxsw_sp,
-			     struct mlxsw_sp_mr_tcam_region *mr_tcam_region,
-			     enum mlxsw_reg_rtar_key_type rtar_key_type)
-{
-	struct parman_prio *parman_prios;
-	struct parman *parman;
-	int err;
-	int i;
-
-	mr_tcam_region->rtar_key_type = rtar_key_type;
-	mr_tcam_region->mlxsw_sp = mlxsw_sp;
-
-	err = mlxsw_sp_mr_tcam_region_alloc(mr_tcam_region);
-	if (err)
-		return err;
-
-	parman = parman_create(&mlxsw_sp_mr_tcam_region_parman_ops,
-			       mr_tcam_region);
-	if (!parman) {
-		err = -ENOMEM;
-		goto err_parman_create;
-	}
-	mr_tcam_region->parman = parman;
-
-	parman_prios = kmalloc_array(MLXSW_SP_MR_ROUTE_PRIO_MAX + 1,
-				     sizeof(*parman_prios), GFP_KERNEL);
-	if (!parman_prios) {
-		err = -ENOMEM;
-		goto err_parman_prios_alloc;
-	}
-	mr_tcam_region->parman_prios = parman_prios;
-
-	for (i = 0; i < MLXSW_SP_MR_ROUTE_PRIO_MAX + 1; i++)
-		parman_prio_init(mr_tcam_region->parman,
-				 &mr_tcam_region->parman_prios[i], i);
-	return 0;
-
-err_parman_prios_alloc:
-	parman_destroy(parman);
-err_parman_create:
-	mlxsw_sp_mr_tcam_region_free(mr_tcam_region);
-	return err;
-}
-
-static void
-mlxsw_sp_mr_tcam_region_fini(struct mlxsw_sp_mr_tcam_region *mr_tcam_region)
-{
-	int i;
-
-	for (i = 0; i < MLXSW_SP_MR_ROUTE_PRIO_MAX + 1; i++)
-		parman_prio_fini(&mr_tcam_region->parman_prios[i]);
-	kfree(mr_tcam_region->parman_prios);
-	parman_destroy(mr_tcam_region->parman);
-	mlxsw_sp_mr_tcam_region_free(mr_tcam_region);
-}
-
 static int mlxsw_sp_mr_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
 {
+	const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
 	struct mlxsw_sp_mr_tcam *mr_tcam = priv;
-	struct mlxsw_sp_mr_tcam_region *region = &mr_tcam->tcam_regions[0];
-	u32 rtar_key;
 	int err;
 
-	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MC_ERIF_LIST_ENTRIES) ||
-	    !MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_TCAM_RULES))
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MC_ERIF_LIST_ENTRIES))
 		return -EIO;
 
-	rtar_key = MLXSW_REG_RTAR_KEY_TYPE_IPV4_MULTICAST;
-	err = mlxsw_sp_mr_tcam_region_init(mlxsw_sp,
-					   &region[MLXSW_SP_L3_PROTO_IPV4],
-					   rtar_key);
-	if (err)
-		return err;
+	mr_tcam->priv = kzalloc(ops->priv_size, GFP_KERNEL);
+	if (!mr_tcam->priv)
+		return -ENOMEM;
 
-	rtar_key = MLXSW_REG_RTAR_KEY_TYPE_IPV6_MULTICAST;
-	err = mlxsw_sp_mr_tcam_region_init(mlxsw_sp,
-					   &region[MLXSW_SP_L3_PROTO_IPV6],
-					   rtar_key);
+	err = ops->init(mlxsw_sp, mr_tcam->priv);
 	if (err)
-		goto err_ipv6_region_init;
-
+		goto err_init;
 	return 0;
 
-err_ipv6_region_init:
-	mlxsw_sp_mr_tcam_region_fini(&region[MLXSW_SP_L3_PROTO_IPV4]);
+err_init:
+	kfree(mr_tcam->priv);
 	return err;
 }
 
-static void mlxsw_sp_mr_tcam_fini(void *priv)
+static void mlxsw_sp_mr_tcam_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
 {
+	const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
 	struct mlxsw_sp_mr_tcam *mr_tcam = priv;
-	struct mlxsw_sp_mr_tcam_region *region = &mr_tcam->tcam_regions[0];
 
-	mlxsw_sp_mr_tcam_region_fini(&region[MLXSW_SP_L3_PROTO_IPV6]);
-	mlxsw_sp_mr_tcam_region_fini(&region[MLXSW_SP_L3_PROTO_IPV4]);
+	ops->fini(mr_tcam->priv);
+	kfree(mr_tcam->priv);
 }
 
 const struct mlxsw_sp_mr_ops mlxsw_sp_mr_tcam_ops = {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h
index f9b59ee25406..3c84151b4c33 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_SPECTRUM_MCROUTER_TCAM_H
 #define _MLXSW_SPECTRUM_MCROUTER_TCAM_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
index cad603c35271..bdf53cf350f6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Nogah Frankel <nogahf@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/errno.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 77b2adb29341..3a96307f51b0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -1,39 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
- * Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2016 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2016 Yotam Gigi <yotamg@mellanox.com>
- * Copyright (c) 2017-2018 Petr Machata <petrm@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -48,6 +14,7 @@
 #include <linux/route.h>
 #include <linux/gcd.h>
 #include <linux/random.h>
+#include <linux/if_macvlan.h>
 #include <net/netevent.h>
 #include <net/neighbour.h>
 #include <net/arp.h>
@@ -60,6 +27,7 @@
 #include <net/ndisc.h>
 #include <net/ipv6.h>
 #include <net/fib_notifier.h>
+#include <net/switchdev.h>
 
 #include "spectrum.h"
 #include "core.h"
@@ -163,7 +131,9 @@ struct mlxsw_sp_rif_ops {
 		      const struct mlxsw_sp_rif_params *params);
 	int (*configure)(struct mlxsw_sp_rif *rif);
 	void (*deconfigure)(struct mlxsw_sp_rif *rif);
-	struct mlxsw_sp_fid * (*fid_get)(struct mlxsw_sp_rif *rif);
+	struct mlxsw_sp_fid * (*fid_get)(struct mlxsw_sp_rif *rif,
+					 struct netlink_ext_ack *extack);
+	void (*fdb_del)(struct mlxsw_sp_rif *rif, const char *mac);
 };
 
 static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree);
@@ -342,10 +312,6 @@ static void mlxsw_sp_rif_counters_free(struct mlxsw_sp_rif *rif)
 	mlxsw_sp_rif_counter_free(mlxsw_sp, rif, MLXSW_SP_RIF_COUNTER_EGRESS);
 }
 
-static struct mlxsw_sp_rif *
-mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
-			 const struct net_device *dev);
-
 #define MLXSW_SP_PREFIX_COUNT (sizeof(struct in6_addr) * BITS_PER_BYTE + 1)
 
 struct mlxsw_sp_prefix_usage {
@@ -1109,7 +1075,8 @@ mlxsw_sp_fib_entry_decap_init(struct mlxsw_sp *mlxsw_sp,
 	u32 tunnel_index;
 	int err;
 
-	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, 1, &tunnel_index);
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+				  1, &tunnel_index);
 	if (err)
 		return err;
 
@@ -1125,7 +1092,8 @@ static void mlxsw_sp_fib_entry_decap_fini(struct mlxsw_sp *mlxsw_sp,
 	/* Unlink this node from the IPIP entry that it's the decap entry of. */
 	fib_entry->decap.ipip_entry->decap_fib_entry = NULL;
 	fib_entry->decap.ipip_entry = NULL;
-	mlxsw_sp_kvdl_free(mlxsw_sp, fib_entry->decap.tunnel_index);
+	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+			   1, fib_entry->decap.tunnel_index);
 }
 
 static struct mlxsw_sp_fib_node *
@@ -2434,17 +2402,48 @@ static void mlxsw_sp_router_mp_hash_event_work(struct work_struct *work)
 	kfree(net_work);
 }
 
+static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp);
+
+static void mlxsw_sp_router_update_priority_work(struct work_struct *work)
+{
+	struct mlxsw_sp_netevent_work *net_work =
+		container_of(work, struct mlxsw_sp_netevent_work, work);
+	struct mlxsw_sp *mlxsw_sp = net_work->mlxsw_sp;
+
+	__mlxsw_sp_router_init(mlxsw_sp);
+	kfree(net_work);
+}
+
+static int mlxsw_sp_router_schedule_work(struct net *net,
+					 struct notifier_block *nb,
+					 void (*cb)(struct work_struct *))
+{
+	struct mlxsw_sp_netevent_work *net_work;
+	struct mlxsw_sp_router *router;
+
+	if (!net_eq(net, &init_net))
+		return NOTIFY_DONE;
+
+	net_work = kzalloc(sizeof(*net_work), GFP_ATOMIC);
+	if (!net_work)
+		return NOTIFY_BAD;
+
+	router = container_of(nb, struct mlxsw_sp_router, netevent_nb);
+	INIT_WORK(&net_work->work, cb);
+	net_work->mlxsw_sp = router->mlxsw_sp;
+	mlxsw_core_schedule_work(&net_work->work);
+	return NOTIFY_DONE;
+}
+
 static int mlxsw_sp_router_netevent_event(struct notifier_block *nb,
 					  unsigned long event, void *ptr)
 {
 	struct mlxsw_sp_netevent_work *net_work;
 	struct mlxsw_sp_port *mlxsw_sp_port;
-	struct mlxsw_sp_router *router;
 	struct mlxsw_sp *mlxsw_sp;
 	unsigned long interval;
 	struct neigh_parms *p;
 	struct neighbour *n;
-	struct net *net;
 
 	switch (event) {
 	case NETEVENT_DELAY_PROBE_TIME_UPDATE:
@@ -2498,20 +2497,12 @@ static int mlxsw_sp_router_netevent_event(struct notifier_block *nb,
 		break;
 	case NETEVENT_IPV4_MPATH_HASH_UPDATE:
 	case NETEVENT_IPV6_MPATH_HASH_UPDATE:
-		net = ptr;
-
-		if (!net_eq(net, &init_net))
-			return NOTIFY_DONE;
+		return mlxsw_sp_router_schedule_work(ptr, nb,
+				mlxsw_sp_router_mp_hash_event_work);
 
-		net_work = kzalloc(sizeof(*net_work), GFP_ATOMIC);
-		if (!net_work)
-			return NOTIFY_BAD;
-
-		router = container_of(nb, struct mlxsw_sp_router, netevent_nb);
-		INIT_WORK(&net_work->work, mlxsw_sp_router_mp_hash_event_work);
-		net_work->mlxsw_sp = router->mlxsw_sp;
-		mlxsw_core_schedule_work(&net_work->work);
-		break;
+	case NETEVENT_IPV4_FWD_UPDATE_PRIORITY_UPDATE:
+		return mlxsw_sp_router_schedule_work(ptr, nb,
+				mlxsw_sp_router_update_priority_work);
 	}
 
 	return NOTIFY_DONE;
@@ -3165,8 +3156,9 @@ static int mlxsw_sp_fix_adj_grp_size(struct mlxsw_sp *mlxsw_sp,
 	 * by the device and make sure the request can be satisfied.
 	 */
 	mlxsw_sp_adj_grp_size_round_up(p_adj_grp_size);
-	err = mlxsw_sp_kvdl_alloc_size_query(mlxsw_sp, *p_adj_grp_size,
-					     &alloc_size);
+	err = mlxsw_sp_kvdl_alloc_count_query(mlxsw_sp,
+					      MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+					      *p_adj_grp_size, &alloc_size);
 	if (err)
 		return err;
 	/* It is possible the allocation results in more allocated
@@ -3278,7 +3270,8 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 		/* No valid allocation size available. */
 		goto set_trap;
 
-	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, ecmp_size, &adj_index);
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+				  ecmp_size, &adj_index);
 	if (err) {
 		/* We ran out of KVD linear space, just set the
 		 * trap and let everything flow through kernel.
@@ -3313,7 +3306,8 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 
 	err = mlxsw_sp_adj_index_mass_update(mlxsw_sp, nh_grp,
 					     old_adj_index, old_ecmp_size);
-	mlxsw_sp_kvdl_free(mlxsw_sp, old_adj_index);
+	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+			   old_ecmp_size, old_adj_index);
 	if (err) {
 		dev_warn(mlxsw_sp->bus_info->dev, "Failed to mass-update adjacency index for nexthop group.\n");
 		goto set_trap;
@@ -3335,7 +3329,8 @@ set_trap:
 	if (err)
 		dev_warn(mlxsw_sp->bus_info->dev, "Failed to set traps for fib entries.\n");
 	if (old_adj_index_valid)
-		mlxsw_sp_kvdl_free(mlxsw_sp, nh_grp->adj_index);
+		mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+				   nh_grp->ecmp_size, nh_grp->adj_index);
 }
 
 static void __mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp_nexthop *nh,
@@ -5967,7 +5962,7 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 	return NOTIFY_DONE;
 }
 
-static struct mlxsw_sp_rif *
+struct mlxsw_sp_rif *
 mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
 			 const struct net_device *dev)
 {
@@ -6024,6 +6019,12 @@ mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *rif, struct net_device *dev,
 		    !list_empty(&inet6_dev->addr_list))
 			addr_list_empty = false;
 
+		/* macvlans do not have a RIF, but rather piggy back on the
+		 * RIF of their lower device.
+		 */
+		if (netif_is_macvlan(dev) && addr_list_empty)
+			return true;
+
 		if (rif && addr_list_empty &&
 		    !netif_is_l3_slave(rif->dev))
 			return true;
@@ -6125,6 +6126,11 @@ const struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif)
 	return rif->dev;
 }
 
+struct mlxsw_sp_fid *mlxsw_sp_rif_fid(const struct mlxsw_sp_rif *rif)
+{
+	return rif->fid;
+}
+
 static struct mlxsw_sp_rif *
 mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 		    const struct mlxsw_sp_rif_params *params,
@@ -6162,7 +6168,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 	rif->ops = ops;
 
 	if (ops->fid_get) {
-		fid = ops->fid_get(rif);
+		fid = ops->fid_get(rif, extack);
 		if (IS_ERR(fid)) {
 			err = PTR_ERR(fid);
 			goto err_fid_get;
@@ -6267,7 +6273,7 @@ mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 	}
 
 	/* FID was already created, just take a reference */
-	fid = rif->ops->fid_get(rif);
+	fid = rif->ops->fid_get(rif, extack);
 	err = mlxsw_sp_fid_port_vid_map(fid, mlxsw_sp_port, vid);
 	if (err)
 		goto err_fid_port_vid_map;
@@ -6432,6 +6438,123 @@ static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev,
 	return 0;
 }
 
+static bool mlxsw_sp_rif_macvlan_is_vrrp4(const u8 *mac)
+{
+	u8 vrrp4[ETH_ALEN] = { 0x00, 0x00, 0x5e, 0x00, 0x01, 0x00 };
+	u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0x00 };
+
+	return ether_addr_equal_masked(mac, vrrp4, mask);
+}
+
+static bool mlxsw_sp_rif_macvlan_is_vrrp6(const u8 *mac)
+{
+	u8 vrrp6[ETH_ALEN] = { 0x00, 0x00, 0x5e, 0x00, 0x02, 0x00 };
+	u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0x00 };
+
+	return ether_addr_equal_masked(mac, vrrp6, mask);
+}
+
+static int mlxsw_sp_rif_vrrp_op(struct mlxsw_sp *mlxsw_sp, u16 rif_index,
+				const u8 *mac, bool adding)
+{
+	char ritr_pl[MLXSW_REG_RITR_LEN];
+	u8 vrrp_id = adding ? mac[5] : 0;
+	int err;
+
+	if (!mlxsw_sp_rif_macvlan_is_vrrp4(mac) &&
+	    !mlxsw_sp_rif_macvlan_is_vrrp6(mac))
+		return 0;
+
+	mlxsw_reg_ritr_rif_pack(ritr_pl, rif_index);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+	if (err)
+		return err;
+
+	if (mlxsw_sp_rif_macvlan_is_vrrp4(mac))
+		mlxsw_reg_ritr_if_vrrp_id_ipv4_set(ritr_pl, vrrp_id);
+	else
+		mlxsw_reg_ritr_if_vrrp_id_ipv6_set(ritr_pl, vrrp_id);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+static int mlxsw_sp_rif_macvlan_add(struct mlxsw_sp *mlxsw_sp,
+				    const struct net_device *macvlan_dev,
+				    struct netlink_ext_ack *extack)
+{
+	struct macvlan_dev *vlan = netdev_priv(macvlan_dev);
+	struct mlxsw_sp_rif *rif;
+	int err;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, vlan->lowerdev);
+	if (!rif) {
+		NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
+		return -EOPNOTSUPP;
+	}
+
+	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, macvlan_dev->dev_addr,
+				  mlxsw_sp_fid_index(rif->fid), true);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_rif_vrrp_op(mlxsw_sp, rif->rif_index,
+				   macvlan_dev->dev_addr, true);
+	if (err)
+		goto err_rif_vrrp_add;
+
+	/* Make sure the bridge driver does not have this MAC pointing at
+	 * some other port.
+	 */
+	if (rif->ops->fdb_del)
+		rif->ops->fdb_del(rif, macvlan_dev->dev_addr);
+
+	return 0;
+
+err_rif_vrrp_add:
+	mlxsw_sp_rif_fdb_op(mlxsw_sp, macvlan_dev->dev_addr,
+			    mlxsw_sp_fid_index(rif->fid), false);
+	return err;
+}
+
+void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp,
+			      const struct net_device *macvlan_dev)
+{
+	struct macvlan_dev *vlan = netdev_priv(macvlan_dev);
+	struct mlxsw_sp_rif *rif;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, vlan->lowerdev);
+	/* If we do not have a RIF, then we already took care of
+	 * removing the macvlan's MAC during RIF deletion.
+	 */
+	if (!rif)
+		return;
+	mlxsw_sp_rif_vrrp_op(mlxsw_sp, rif->rif_index, macvlan_dev->dev_addr,
+			     false);
+	mlxsw_sp_rif_fdb_op(mlxsw_sp, macvlan_dev->dev_addr,
+			    mlxsw_sp_fid_index(rif->fid), false);
+}
+
+static int mlxsw_sp_inetaddr_macvlan_event(struct net_device *macvlan_dev,
+					   unsigned long event,
+					   struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp *mlxsw_sp;
+
+	mlxsw_sp = mlxsw_sp_lower_get(macvlan_dev);
+	if (!mlxsw_sp)
+		return 0;
+
+	switch (event) {
+	case NETDEV_UP:
+		return mlxsw_sp_rif_macvlan_add(mlxsw_sp, macvlan_dev, extack);
+	case NETDEV_DOWN:
+		mlxsw_sp_rif_macvlan_del(mlxsw_sp, macvlan_dev);
+		break;
+	}
+
+	return 0;
+}
+
 static int __mlxsw_sp_inetaddr_event(struct net_device *dev,
 				     unsigned long event,
 				     struct netlink_ext_ack *extack)
@@ -6444,6 +6567,8 @@ static int __mlxsw_sp_inetaddr_event(struct net_device *dev,
 		return mlxsw_sp_inetaddr_bridge_event(dev, event, extack);
 	else if (is_vlan_dev(dev))
 		return mlxsw_sp_inetaddr_vlan_event(dev, event, extack);
+	else if (netif_is_macvlan(dev))
+		return mlxsw_sp_inetaddr_macvlan_event(dev, event, extack);
 	else
 		return 0;
 }
@@ -6684,7 +6809,10 @@ int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event,
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev);
 	int err = 0;
 
-	if (!mlxsw_sp)
+	/* We do not create a RIF for a macvlan, but only use it to
+	 * direct more MAC addresses to the router.
+	 */
+	if (!mlxsw_sp || netif_is_macvlan(l3_dev))
 		return 0;
 
 	switch (event) {
@@ -6705,6 +6833,27 @@ int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event,
 	return err;
 }
 
+static int __mlxsw_sp_rif_macvlan_flush(struct net_device *dev, void *data)
+{
+	struct mlxsw_sp_rif *rif = data;
+
+	if (!netif_is_macvlan(dev))
+		return 0;
+
+	return mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, dev->dev_addr,
+				   mlxsw_sp_fid_index(rif->fid), false);
+}
+
+static int mlxsw_sp_rif_macvlan_flush(struct mlxsw_sp_rif *rif)
+{
+	if (!netif_is_macvlan_port(rif->dev))
+		return 0;
+
+	netdev_warn(rif->dev, "Router interface is deleted. Upper macvlans will not work\n");
+	return netdev_walk_all_upper_dev_rcu(rif->dev,
+					     __mlxsw_sp_rif_macvlan_flush, rif);
+}
+
 static struct mlxsw_sp_rif_subport *
 mlxsw_sp_rif_subport_rif(const struct mlxsw_sp_rif *rif)
 {
@@ -6771,11 +6920,13 @@ static void mlxsw_sp_rif_subport_deconfigure(struct mlxsw_sp_rif *rif)
 	mlxsw_sp_fid_rif_set(fid, NULL);
 	mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr,
 			    mlxsw_sp_fid_index(fid), false);
+	mlxsw_sp_rif_macvlan_flush(rif);
 	mlxsw_sp_rif_subport_op(rif, false);
 }
 
 static struct mlxsw_sp_fid *
-mlxsw_sp_rif_subport_fid_get(struct mlxsw_sp_rif *rif)
+mlxsw_sp_rif_subport_fid_get(struct mlxsw_sp_rif *rif,
+			     struct netlink_ext_ack *extack)
 {
 	return mlxsw_sp_fid_rfid_get(rif->mlxsw_sp, rif->rif_index);
 }
@@ -6857,6 +7008,7 @@ static void mlxsw_sp_rif_vlan_deconfigure(struct mlxsw_sp_rif *rif)
 	mlxsw_sp_fid_rif_set(fid, NULL);
 	mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr,
 			    mlxsw_sp_fid_index(fid), false);
+	mlxsw_sp_rif_macvlan_flush(rif);
 	mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC,
 			       mlxsw_sp_router_port(mlxsw_sp), false);
 	mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_MC,
@@ -6865,19 +7017,49 @@ static void mlxsw_sp_rif_vlan_deconfigure(struct mlxsw_sp_rif *rif)
 }
 
 static struct mlxsw_sp_fid *
-mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif)
+mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif,
+			  struct netlink_ext_ack *extack)
 {
-	u16 vid = is_vlan_dev(rif->dev) ? vlan_dev_vlan_id(rif->dev) : 1;
+	u16 vid;
+	int err;
+
+	if (is_vlan_dev(rif->dev)) {
+		vid = vlan_dev_vlan_id(rif->dev);
+	} else {
+		err = br_vlan_get_pvid(rif->dev, &vid);
+		if (err < 0 || !vid) {
+			NL_SET_ERR_MSG_MOD(extack, "Couldn't determine bridge PVID");
+			return ERR_PTR(-EINVAL);
+		}
+	}
 
 	return mlxsw_sp_fid_8021q_get(rif->mlxsw_sp, vid);
 }
 
+static void mlxsw_sp_rif_vlan_fdb_del(struct mlxsw_sp_rif *rif, const char *mac)
+{
+	u16 vid = mlxsw_sp_fid_8021q_vid(rif->fid);
+	struct switchdev_notifier_fdb_info info;
+	struct net_device *br_dev;
+	struct net_device *dev;
+
+	br_dev = is_vlan_dev(rif->dev) ? vlan_dev_real_dev(rif->dev) : rif->dev;
+	dev = br_fdb_find_port(br_dev, mac, vid);
+	if (!dev)
+		return;
+
+	info.addr = mac;
+	info.vid = vid;
+	call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, dev, &info.info);
+}
+
 static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_vlan_ops = {
 	.type			= MLXSW_SP_RIF_TYPE_VLAN,
 	.rif_size		= sizeof(struct mlxsw_sp_rif),
 	.configure		= mlxsw_sp_rif_vlan_configure,
 	.deconfigure		= mlxsw_sp_rif_vlan_deconfigure,
 	.fid_get		= mlxsw_sp_rif_vlan_fid_get,
+	.fdb_del		= mlxsw_sp_rif_vlan_fdb_del,
 };
 
 static int mlxsw_sp_rif_fid_configure(struct mlxsw_sp_rif *rif)
@@ -6929,6 +7111,7 @@ static void mlxsw_sp_rif_fid_deconfigure(struct mlxsw_sp_rif *rif)
 	mlxsw_sp_fid_rif_set(fid, NULL);
 	mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr,
 			    mlxsw_sp_fid_index(fid), false);
+	mlxsw_sp_rif_macvlan_flush(rif);
 	mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC,
 			       mlxsw_sp_router_port(mlxsw_sp), false);
 	mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_MC,
@@ -6937,17 +7120,33 @@ static void mlxsw_sp_rif_fid_deconfigure(struct mlxsw_sp_rif *rif)
 }
 
 static struct mlxsw_sp_fid *
-mlxsw_sp_rif_fid_fid_get(struct mlxsw_sp_rif *rif)
+mlxsw_sp_rif_fid_fid_get(struct mlxsw_sp_rif *rif,
+			 struct netlink_ext_ack *extack)
 {
 	return mlxsw_sp_fid_8021d_get(rif->mlxsw_sp, rif->dev->ifindex);
 }
 
+static void mlxsw_sp_rif_fid_fdb_del(struct mlxsw_sp_rif *rif, const char *mac)
+{
+	struct switchdev_notifier_fdb_info info;
+	struct net_device *dev;
+
+	dev = br_fdb_find_port(rif->dev, mac, 0);
+	if (!dev)
+		return;
+
+	info.addr = mac;
+	info.vid = 0;
+	call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, dev, &info.info);
+}
+
 static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_fid_ops = {
 	.type			= MLXSW_SP_RIF_TYPE_FID,
 	.rif_size		= sizeof(struct mlxsw_sp_rif),
 	.configure		= mlxsw_sp_rif_fid_configure,
 	.deconfigure		= mlxsw_sp_rif_fid_deconfigure,
 	.fid_get		= mlxsw_sp_rif_fid_fid_get,
+	.fdb_del		= mlxsw_sp_rif_fid_fdb_del,
 };
 
 static struct mlxsw_sp_rif_ipip_lb *
@@ -7172,6 +7371,7 @@ static int mlxsw_sp_dscp_init(struct mlxsw_sp *mlxsw_sp)
 
 static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 {
+	bool usp = init_net.ipv4.sysctl_ip_fwd_update_priority;
 	char rgcr_pl[MLXSW_REG_RGCR_LEN];
 	u64 max_rifs;
 	int err;
@@ -7182,7 +7382,7 @@ static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 
 	mlxsw_reg_rgcr_pack(rgcr_pl, true, true);
 	mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, max_rifs);
-	mlxsw_reg_rgcr_usp_set(rgcr_pl, true);
+	mlxsw_reg_rgcr_usp_set(rgcr_pl, usp);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index a01edcf56797..1a60391daafa 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Arkadi Sharshevsky <arkadis@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_ROUTER_H_
 #define _MLXSW_ROUTER_H_
@@ -66,6 +35,8 @@ struct mlxsw_sp_neigh_entry;
 struct mlxsw_sp_nexthop;
 struct mlxsw_sp_ipip_entry;
 
+struct mlxsw_sp_rif *mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
+					      const struct net_device *dev);
 struct mlxsw_sp_rif *mlxsw_sp_rif_by_index(const struct mlxsw_sp *mlxsw_sp,
 					   u16 rif_index);
 u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif);
@@ -75,6 +46,7 @@ u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev);
 int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif);
 u8 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp);
 const struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif);
+struct mlxsw_sp_fid *mlxsw_sp_rif_fid(const struct mlxsw_sp_rif *rif);
 int mlxsw_sp_rif_counter_value_get(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_rif *rif,
 				   enum mlxsw_sp_rif_counter_dir dir,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index 3d187d88cc7c..d965fd275c90 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -1,41 +1,11 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/mlxsw_span.c
- * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2018 Petr Machata <petrm@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/if_bridge.h>
 #include <linux/list.h>
 #include <net/arp.h>
 #include <net/gre.h>
+#include <net/lag.h>
 #include <net/ndisc.h>
 #include <net/ip6_tunnel.h>
 
@@ -254,7 +224,9 @@ mlxsw_sp_span_entry_lag(struct net_device *lag_dev)
 	struct list_head *iter;
 
 	netdev_for_each_lower_dev(lag_dev, dev, iter)
-		if ((dev->flags & IFF_UP) && mlxsw_sp_port_dev_check(dev))
+		if (netif_carrier_ok(dev) &&
+		    net_lag_port_dev_txable(dev) &&
+		    mlxsw_sp_port_dev_check(dev))
 			return dev;
 
 	return NULL;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
index 14a6de904db1..5e04252f2a11 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
@@ -1,35 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/mlxsw_span.h
- * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_SPECTRUM_SPAN_H
 #define _MLXSW_SPECTRUM_SPAN_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index eea5666a86b2..0d8444aaba01 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1,38 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2015 Elad Raz <eladr@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -1135,6 +1102,39 @@ err_port_vlan_set:
 	return err;
 }
 
+static int
+mlxsw_sp_br_ban_rif_pvid_change(struct mlxsw_sp *mlxsw_sp,
+				const struct net_device *br_dev,
+				const struct switchdev_obj_port_vlan *vlan)
+{
+	struct mlxsw_sp_rif *rif;
+	struct mlxsw_sp_fid *fid;
+	u16 pvid;
+	u16 vid;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, br_dev);
+	if (!rif)
+		return 0;
+	fid = mlxsw_sp_rif_fid(rif);
+	pvid = mlxsw_sp_fid_8021q_vid(fid);
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+		if (vlan->flags & BRIDGE_VLAN_INFO_PVID) {
+			if (vid != pvid) {
+				netdev_err(br_dev, "Can't change PVID, it's used by router interface\n");
+				return -EBUSY;
+			}
+		} else {
+			if (vid == pvid) {
+				netdev_err(br_dev, "Can't remove PVID, it's used by router interface\n");
+				return -EBUSY;
+			}
+		}
+	}
+
+	return 0;
+}
+
 static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 				   const struct switchdev_obj_port_vlan *vlan,
 				   struct switchdev_trans *trans)
@@ -1146,8 +1146,18 @@ static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 	struct mlxsw_sp_bridge_port *bridge_port;
 	u16 vid;
 
-	if (netif_is_bridge_master(orig_dev))
-		return -EOPNOTSUPP;
+	if (netif_is_bridge_master(orig_dev)) {
+		int err = 0;
+
+		if ((vlan->flags & BRIDGE_VLAN_INFO_BRENTRY) &&
+		    br_vlan_enabled(orig_dev) &&
+		    switchdev_trans_ph_prepare(trans))
+			err = mlxsw_sp_br_ban_rif_pvid_change(mlxsw_sp,
+							      orig_dev, vlan);
+		if (!err)
+			err = -EOPNOTSUPP;
+		return err;
+	}
 
 	if (switchdev_trans_ph_prepare(trans))
 		return 0;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.h
index bc44d5effc28..c218e10bd835 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.h
@@ -1,35 +1,5 @@
-/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.h
- * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/netdevice.h>
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchib.c b/drivers/net/ethernet/mellanox/mlxsw/switchib.c
index c698ec4fd9d4..bcf2e79a21c8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchib.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchib.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/switchib.c
- * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Elad Raz <eladr@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index 3922c1cfe5f5..2d4f213e154d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -1,38 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/switchx2.c
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2015-2016 Elad Raz <eladr@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h
index 399e9d6993f7..53020724c2f6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h
@@ -1,38 +1,6 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/trap.h
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Elad Raz <eladr@mellanox.com>
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
+
 #ifndef _MLXSW_TRAP_H
 #define _MLXSW_TRAP_H
 
@@ -63,6 +31,7 @@ enum {
 	MLXSW_TRAP_ID_LBERROR = 0x54,
 	MLXSW_TRAP_ID_IPV4_OSPF = 0x55,
 	MLXSW_TRAP_ID_IPV4_PIM = 0x58,
+	MLXSW_TRAP_ID_IPV4_VRRP = 0x59,
 	MLXSW_TRAP_ID_RPF = 0x5C,
 	MLXSW_TRAP_ID_IP2ME = 0x5F,
 	MLXSW_TRAP_ID_IPV6_UNSPECIFIED_ADDRESS = 0x60,
@@ -78,6 +47,7 @@ enum {
 	MLXSW_TRAP_ID_IPV6_ALL_ROUTERS_LINK = 0x6F,
 	MLXSW_TRAP_ID_RTR_INGRESS0 = 0x70,
 	MLXSW_TRAP_ID_IPV6_PIM = 0x79,
+	MLXSW_TRAP_ID_IPV6_VRRP = 0x7A,
 	MLXSW_TRAP_ID_IPV4_BGP = 0x88,
 	MLXSW_TRAP_ID_IPV6_BGP = 0x89,
 	MLXSW_TRAP_ID_L3_IPV6_ROUTER_SOLICITATION = 0x8A,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/txheader.h b/drivers/net/ethernet/mellanox/mlxsw/txheader.h
index fdf94720ca62..da51dd9d5e44 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/txheader.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/txheader.h
@@ -1,37 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/txheader.h
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_TXHEADER_H
 #define _MLXSW_TXHEADER_H
diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c
index f3e9dd47b56f..0e9719fbc624 100644
--- a/drivers/net/ethernet/micrel/ks8851_mll.c
+++ b/drivers/net/ethernet/micrel/ks8851_mll.c
@@ -30,6 +30,7 @@
 #include <linux/ethtool.h>
 #include <linux/cache.h>
 #include <linux/crc32.h>
+#include <linux/crc32poly.h>
 #include <linux/mii.h>
 #include <linux/platform_device.h>
 #include <linux/delay.h>
@@ -1078,7 +1079,7 @@ static void ks_stop_rx(struct ks_net *ks)
 
 }  /* ks_stop_rx */
 
-static unsigned long const ethernet_polynomial = 0x04c11db7U;
+static unsigned long const ethernet_polynomial = CRC32_POLY_BE;
 
 static unsigned long ether_gen_crc(int length, u8 *data)
 {
diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c
index b72d1bd11296..ebbdfb908745 100644
--- a/drivers/net/ethernet/micrel/ksz884x.c
+++ b/drivers/net/ethernet/micrel/ksz884x.c
@@ -3373,7 +3373,6 @@ static void port_get_link_speed(struct ksz_port *port)
  */
 static void port_set_link_speed(struct ksz_port *port)
 {
-	struct ksz_port_info *info;
 	struct ksz_hw *hw = port->hw;
 	u16 data;
 	u16 cfg;
@@ -3382,8 +3381,6 @@ static void port_set_link_speed(struct ksz_port *port)
 	int p;
 
 	for (i = 0, p = port->first_port; i < port->port_cnt; i++, p++) {
-		info = &hw->port_info[p];
-
 		port_r16(hw, p, KS884X_PORT_CTRL_4_OFFSET, &data);
 		port_r8(hw, p, KS884X_PORT_STATUS_OFFSET, &status);
 
diff --git a/drivers/net/ethernet/microchip/Kconfig b/drivers/net/ethernet/microchip/Kconfig
index 71dca8bd51ac..16bd3f44dbe8 100644
--- a/drivers/net/ethernet/microchip/Kconfig
+++ b/drivers/net/ethernet/microchip/Kconfig
@@ -46,6 +46,7 @@ config LAN743X
 	tristate "LAN743x support"
 	depends on PCI
 	select PHYLIB
+	select CRC16
 	---help---
 	  Support for the Microchip LAN743x PCI Express Gigabit Ethernet chip
 
diff --git a/drivers/net/ethernet/microchip/Makefile b/drivers/net/ethernet/microchip/Makefile
index 2e982cc249fb..538926d2b43f 100644
--- a/drivers/net/ethernet/microchip/Makefile
+++ b/drivers/net/ethernet/microchip/Makefile
@@ -6,4 +6,4 @@ obj-$(CONFIG_ENC28J60) += enc28j60.o
 obj-$(CONFIG_ENCX24J600) += encx24j600.o encx24j600-regmap.o
 obj-$(CONFIG_LAN743X) += lan743x.o
 
-lan743x-objs := lan743x_main.o
+lan743x-objs := lan743x_main.o lan743x_ethtool.o lan743x_ptp.o
diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
new file mode 100644
index 000000000000..07c1eb63415a
--- /dev/null
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -0,0 +1,723 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (C) 2018 Microchip Technology Inc. */
+
+#include <linux/netdevice.h>
+#include "lan743x_main.h"
+#include "lan743x_ethtool.h"
+#include <linux/net_tstamp.h>
+#include <linux/pci.h>
+#include <linux/phy.h>
+
+/* eeprom */
+#define LAN743X_EEPROM_MAGIC		    (0x74A5)
+#define LAN743X_OTP_MAGIC		    (0x74F3)
+#define EEPROM_INDICATOR_1		    (0xA5)
+#define EEPROM_INDICATOR_2		    (0xAA)
+#define EEPROM_MAC_OFFSET		    (0x01)
+#define MAX_EEPROM_SIZE			    512
+#define OTP_INDICATOR_1			    (0xF3)
+#define OTP_INDICATOR_2			    (0xF7)
+
+static int lan743x_otp_write(struct lan743x_adapter *adapter, u32 offset,
+			     u32 length, u8 *data)
+{
+	unsigned long timeout;
+	u32 buf;
+	int i;
+
+	buf = lan743x_csr_read(adapter, OTP_PWR_DN);
+
+	if (buf & OTP_PWR_DN_PWRDN_N_) {
+		/* clear it and wait to be cleared */
+		lan743x_csr_write(adapter, OTP_PWR_DN, 0);
+
+		timeout = jiffies + HZ;
+		do {
+			udelay(1);
+			buf = lan743x_csr_read(adapter, OTP_PWR_DN);
+			if (time_after(jiffies, timeout)) {
+				netif_warn(adapter, drv, adapter->netdev,
+					   "timeout on OTP_PWR_DN completion\n");
+				return -EIO;
+			}
+		} while (buf & OTP_PWR_DN_PWRDN_N_);
+	}
+
+	/* set to BYTE program mode */
+	lan743x_csr_write(adapter, OTP_PRGM_MODE, OTP_PRGM_MODE_BYTE_);
+
+	for (i = 0; i < length; i++) {
+		lan743x_csr_write(adapter, OTP_ADDR1,
+				  ((offset + i) >> 8) &
+				  OTP_ADDR1_15_11_MASK_);
+		lan743x_csr_write(adapter, OTP_ADDR2,
+				  ((offset + i) &
+				  OTP_ADDR2_10_3_MASK_));
+		lan743x_csr_write(adapter, OTP_PRGM_DATA, data[i]);
+		lan743x_csr_write(adapter, OTP_TST_CMD, OTP_TST_CMD_PRGVRFY_);
+		lan743x_csr_write(adapter, OTP_CMD_GO, OTP_CMD_GO_GO_);
+
+		timeout = jiffies + HZ;
+		do {
+			udelay(1);
+			buf = lan743x_csr_read(adapter, OTP_STATUS);
+			if (time_after(jiffies, timeout)) {
+				netif_warn(adapter, drv, adapter->netdev,
+					   "Timeout on OTP_STATUS completion\n");
+				return -EIO;
+			}
+		} while (buf & OTP_STATUS_BUSY_);
+	}
+
+	return 0;
+}
+
+static int lan743x_eeprom_wait(struct lan743x_adapter *adapter)
+{
+	unsigned long start_time = jiffies;
+	u32 val;
+
+	do {
+		val = lan743x_csr_read(adapter, E2P_CMD);
+
+		if (!(val & E2P_CMD_EPC_BUSY_) ||
+		    (val & E2P_CMD_EPC_TIMEOUT_))
+			break;
+		usleep_range(40, 100);
+	} while (!time_after(jiffies, start_time + HZ));
+
+	if (val & (E2P_CMD_EPC_TIMEOUT_ | E2P_CMD_EPC_BUSY_)) {
+		netif_warn(adapter, drv, adapter->netdev,
+			   "EEPROM read operation timeout\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int lan743x_eeprom_confirm_not_busy(struct lan743x_adapter *adapter)
+{
+	unsigned long start_time = jiffies;
+	u32 val;
+
+	do {
+		val = lan743x_csr_read(adapter, E2P_CMD);
+
+		if (!(val & E2P_CMD_EPC_BUSY_))
+			return 0;
+
+		usleep_range(40, 100);
+	} while (!time_after(jiffies, start_time + HZ));
+
+	netif_warn(adapter, drv, adapter->netdev, "EEPROM is busy\n");
+	return -EIO;
+}
+
+static int lan743x_eeprom_read(struct lan743x_adapter *adapter,
+			       u32 offset, u32 length, u8 *data)
+{
+	int retval;
+	u32 val;
+	int i;
+
+	retval = lan743x_eeprom_confirm_not_busy(adapter);
+	if (retval)
+		return retval;
+
+	for (i = 0; i < length; i++) {
+		val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_READ_;
+		val |= (offset & E2P_CMD_EPC_ADDR_MASK_);
+		lan743x_csr_write(adapter, E2P_CMD, val);
+
+		retval = lan743x_eeprom_wait(adapter);
+		if (retval < 0)
+			return retval;
+
+		val = lan743x_csr_read(adapter, E2P_DATA);
+		data[i] = val & 0xFF;
+		offset++;
+	}
+
+	return 0;
+}
+
+static int lan743x_eeprom_write(struct lan743x_adapter *adapter,
+				u32 offset, u32 length, u8 *data)
+{
+	int retval;
+	u32 val;
+	int i;
+
+	retval = lan743x_eeprom_confirm_not_busy(adapter);
+	if (retval)
+		return retval;
+
+	/* Issue write/erase enable command */
+	val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_EWEN_;
+	lan743x_csr_write(adapter, E2P_CMD, val);
+
+	retval = lan743x_eeprom_wait(adapter);
+	if (retval < 0)
+		return retval;
+
+	for (i = 0; i < length; i++) {
+		/* Fill data register */
+		val = data[i];
+		lan743x_csr_write(adapter, E2P_DATA, val);
+
+		/* Send "write" command */
+		val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_WRITE_;
+		val |= (offset & E2P_CMD_EPC_ADDR_MASK_);
+		lan743x_csr_write(adapter, E2P_CMD, val);
+
+		retval = lan743x_eeprom_wait(adapter);
+		if (retval < 0)
+			return retval;
+
+		offset++;
+	}
+
+	return 0;
+}
+
+static void lan743x_ethtool_get_drvinfo(struct net_device *netdev,
+					struct ethtool_drvinfo *info)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	strlcpy(info->driver, DRIVER_NAME, sizeof(info->driver));
+	strlcpy(info->bus_info,
+		pci_name(adapter->pdev), sizeof(info->bus_info));
+}
+
+static u32 lan743x_ethtool_get_msglevel(struct net_device *netdev)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	return adapter->msg_enable;
+}
+
+static void lan743x_ethtool_set_msglevel(struct net_device *netdev,
+					 u32 msglevel)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	adapter->msg_enable = msglevel;
+}
+
+static int lan743x_ethtool_get_eeprom_len(struct net_device *netdev)
+{
+	return MAX_EEPROM_SIZE;
+}
+
+static int lan743x_ethtool_get_eeprom(struct net_device *netdev,
+				      struct ethtool_eeprom *ee, u8 *data)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	return lan743x_eeprom_read(adapter, ee->offset, ee->len, data);
+}
+
+static int lan743x_ethtool_set_eeprom(struct net_device *netdev,
+				      struct ethtool_eeprom *ee, u8 *data)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	int ret = -EINVAL;
+
+	if (ee->magic == LAN743X_EEPROM_MAGIC)
+		ret = lan743x_eeprom_write(adapter, ee->offset, ee->len,
+					   data);
+	/* Beware!  OTP is One Time Programming ONLY!
+	 * So do some strict condition check before messing up
+	 */
+	else if ((ee->magic == LAN743X_OTP_MAGIC) &&
+		 (ee->offset == 0) &&
+		 (ee->len == MAX_EEPROM_SIZE) &&
+		 (data[0] == OTP_INDICATOR_1))
+		ret = lan743x_otp_write(adapter, ee->offset, ee->len, data);
+
+	return ret;
+}
+
+static const char lan743x_set0_hw_cnt_strings[][ETH_GSTRING_LEN] = {
+	"RX FCS Errors",
+	"RX Alignment Errors",
+	"Rx Fragment Errors",
+	"RX Jabber Errors",
+	"RX Undersize Frame Errors",
+	"RX Oversize Frame Errors",
+	"RX Dropped Frames",
+	"RX Unicast Byte Count",
+	"RX Broadcast Byte Count",
+	"RX Multicast Byte Count",
+	"RX Unicast Frames",
+	"RX Broadcast Frames",
+	"RX Multicast Frames",
+	"RX Pause Frames",
+	"RX 64 Byte Frames",
+	"RX 65 - 127 Byte Frames",
+	"RX 128 - 255 Byte Frames",
+	"RX 256 - 511 Bytes Frames",
+	"RX 512 - 1023 Byte Frames",
+	"RX 1024 - 1518 Byte Frames",
+	"RX Greater 1518 Byte Frames",
+};
+
+static const char lan743x_set1_sw_cnt_strings[][ETH_GSTRING_LEN] = {
+	"RX Queue 0 Frames",
+	"RX Queue 1 Frames",
+	"RX Queue 2 Frames",
+	"RX Queue 3 Frames",
+};
+
+static const char lan743x_set2_hw_cnt_strings[][ETH_GSTRING_LEN] = {
+	"RX Total Frames",
+	"EEE RX LPI Transitions",
+	"EEE RX LPI Time",
+	"RX Counter Rollover Status",
+	"TX FCS Errors",
+	"TX Excess Deferral Errors",
+	"TX Carrier Errors",
+	"TX Bad Byte Count",
+	"TX Single Collisions",
+	"TX Multiple Collisions",
+	"TX Excessive Collision",
+	"TX Late Collisions",
+	"TX Unicast Byte Count",
+	"TX Broadcast Byte Count",
+	"TX Multicast Byte Count",
+	"TX Unicast Frames",
+	"TX Broadcast Frames",
+	"TX Multicast Frames",
+	"TX Pause Frames",
+	"TX 64 Byte Frames",
+	"TX 65 - 127 Byte Frames",
+	"TX 128 - 255 Byte Frames",
+	"TX 256 - 511 Bytes Frames",
+	"TX 512 - 1023 Byte Frames",
+	"TX 1024 - 1518 Byte Frames",
+	"TX Greater 1518 Byte Frames",
+	"TX Total Frames",
+	"EEE TX LPI Transitions",
+	"EEE TX LPI Time",
+	"TX Counter Rollover Status",
+};
+
+static const u32 lan743x_set0_hw_cnt_addr[] = {
+	STAT_RX_FCS_ERRORS,
+	STAT_RX_ALIGNMENT_ERRORS,
+	STAT_RX_FRAGMENT_ERRORS,
+	STAT_RX_JABBER_ERRORS,
+	STAT_RX_UNDERSIZE_FRAME_ERRORS,
+	STAT_RX_OVERSIZE_FRAME_ERRORS,
+	STAT_RX_DROPPED_FRAMES,
+	STAT_RX_UNICAST_BYTE_COUNT,
+	STAT_RX_BROADCAST_BYTE_COUNT,
+	STAT_RX_MULTICAST_BYTE_COUNT,
+	STAT_RX_UNICAST_FRAMES,
+	STAT_RX_BROADCAST_FRAMES,
+	STAT_RX_MULTICAST_FRAMES,
+	STAT_RX_PAUSE_FRAMES,
+	STAT_RX_64_BYTE_FRAMES,
+	STAT_RX_65_127_BYTE_FRAMES,
+	STAT_RX_128_255_BYTE_FRAMES,
+	STAT_RX_256_511_BYTES_FRAMES,
+	STAT_RX_512_1023_BYTE_FRAMES,
+	STAT_RX_1024_1518_BYTE_FRAMES,
+	STAT_RX_GREATER_1518_BYTE_FRAMES,
+};
+
+static const u32 lan743x_set2_hw_cnt_addr[] = {
+	STAT_RX_TOTAL_FRAMES,
+	STAT_EEE_RX_LPI_TRANSITIONS,
+	STAT_EEE_RX_LPI_TIME,
+	STAT_RX_COUNTER_ROLLOVER_STATUS,
+	STAT_TX_FCS_ERRORS,
+	STAT_TX_EXCESS_DEFERRAL_ERRORS,
+	STAT_TX_CARRIER_ERRORS,
+	STAT_TX_BAD_BYTE_COUNT,
+	STAT_TX_SINGLE_COLLISIONS,
+	STAT_TX_MULTIPLE_COLLISIONS,
+	STAT_TX_EXCESSIVE_COLLISION,
+	STAT_TX_LATE_COLLISIONS,
+	STAT_TX_UNICAST_BYTE_COUNT,
+	STAT_TX_BROADCAST_BYTE_COUNT,
+	STAT_TX_MULTICAST_BYTE_COUNT,
+	STAT_TX_UNICAST_FRAMES,
+	STAT_TX_BROADCAST_FRAMES,
+	STAT_TX_MULTICAST_FRAMES,
+	STAT_TX_PAUSE_FRAMES,
+	STAT_TX_64_BYTE_FRAMES,
+	STAT_TX_65_127_BYTE_FRAMES,
+	STAT_TX_128_255_BYTE_FRAMES,
+	STAT_TX_256_511_BYTES_FRAMES,
+	STAT_TX_512_1023_BYTE_FRAMES,
+	STAT_TX_1024_1518_BYTE_FRAMES,
+	STAT_TX_GREATER_1518_BYTE_FRAMES,
+	STAT_TX_TOTAL_FRAMES,
+	STAT_EEE_TX_LPI_TRANSITIONS,
+	STAT_EEE_TX_LPI_TIME,
+	STAT_TX_COUNTER_ROLLOVER_STATUS
+};
+
+static void lan743x_ethtool_get_strings(struct net_device *netdev,
+					u32 stringset, u8 *data)
+{
+	switch (stringset) {
+	case ETH_SS_STATS:
+		memcpy(data, lan743x_set0_hw_cnt_strings,
+		       sizeof(lan743x_set0_hw_cnt_strings));
+		memcpy(&data[sizeof(lan743x_set0_hw_cnt_strings)],
+		       lan743x_set1_sw_cnt_strings,
+		       sizeof(lan743x_set1_sw_cnt_strings));
+		memcpy(&data[sizeof(lan743x_set0_hw_cnt_strings) +
+		       sizeof(lan743x_set1_sw_cnt_strings)],
+		       lan743x_set2_hw_cnt_strings,
+		       sizeof(lan743x_set2_hw_cnt_strings));
+		break;
+	}
+}
+
+static void lan743x_ethtool_get_ethtool_stats(struct net_device *netdev,
+					      struct ethtool_stats *stats,
+					      u64 *data)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	int data_index = 0;
+	u32 buf;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(lan743x_set0_hw_cnt_addr); i++) {
+		buf = lan743x_csr_read(adapter, lan743x_set0_hw_cnt_addr[i]);
+		data[data_index++] = (u64)buf;
+	}
+	for (i = 0; i < ARRAY_SIZE(adapter->rx); i++)
+		data[data_index++] = (u64)(adapter->rx[i].frame_count);
+	for (i = 0; i < ARRAY_SIZE(lan743x_set2_hw_cnt_addr); i++) {
+		buf = lan743x_csr_read(adapter, lan743x_set2_hw_cnt_addr[i]);
+		data[data_index++] = (u64)buf;
+	}
+}
+
+static int lan743x_ethtool_get_sset_count(struct net_device *netdev, int sset)
+{
+	switch (sset) {
+	case ETH_SS_STATS:
+	{
+		int ret;
+
+		ret = ARRAY_SIZE(lan743x_set0_hw_cnt_strings);
+		ret += ARRAY_SIZE(lan743x_set1_sw_cnt_strings);
+		ret += ARRAY_SIZE(lan743x_set2_hw_cnt_strings);
+		return ret;
+	}
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int lan743x_ethtool_get_rxnfc(struct net_device *netdev,
+				     struct ethtool_rxnfc *rxnfc,
+				     u32 *rule_locs)
+{
+	switch (rxnfc->cmd) {
+	case ETHTOOL_GRXFH:
+		rxnfc->data = 0;
+		switch (rxnfc->flow_type) {
+		case TCP_V4_FLOW:case UDP_V4_FLOW:
+		case TCP_V6_FLOW:case UDP_V6_FLOW:
+			rxnfc->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+			/* fall through */
+		case IPV4_FLOW: case IPV6_FLOW:
+			rxnfc->data |= RXH_IP_SRC | RXH_IP_DST;
+			return 0;
+		}
+		break;
+	case ETHTOOL_GRXRINGS:
+		rxnfc->data = LAN743X_USED_RX_CHANNELS;
+		return 0;
+	}
+	return -EOPNOTSUPP;
+}
+
+static u32 lan743x_ethtool_get_rxfh_key_size(struct net_device *netdev)
+{
+	return 40;
+}
+
+static u32 lan743x_ethtool_get_rxfh_indir_size(struct net_device *netdev)
+{
+	return 128;
+}
+
+static int lan743x_ethtool_get_rxfh(struct net_device *netdev,
+				    u32 *indir, u8 *key, u8 *hfunc)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	if (indir) {
+		int dw_index;
+		int byte_index = 0;
+
+		for (dw_index = 0; dw_index < 32; dw_index++) {
+			u32 four_entries =
+				lan743x_csr_read(adapter, RFE_INDX(dw_index));
+
+			byte_index = dw_index << 2;
+			indir[byte_index + 0] =
+				((four_entries >> 0) & 0x000000FF);
+			indir[byte_index + 1] =
+				((four_entries >> 8) & 0x000000FF);
+			indir[byte_index + 2] =
+				((four_entries >> 16) & 0x000000FF);
+			indir[byte_index + 3] =
+				((four_entries >> 24) & 0x000000FF);
+		}
+	}
+	if (key) {
+		int dword_index;
+		int byte_index = 0;
+
+		for (dword_index = 0; dword_index < 10; dword_index++) {
+			u32 four_entries =
+				lan743x_csr_read(adapter,
+						 RFE_HASH_KEY(dword_index));
+
+			byte_index = dword_index << 2;
+			key[byte_index + 0] =
+				((four_entries >> 0) & 0x000000FF);
+			key[byte_index + 1] =
+				((four_entries >> 8) & 0x000000FF);
+			key[byte_index + 2] =
+				((four_entries >> 16) & 0x000000FF);
+			key[byte_index + 3] =
+				((four_entries >> 24) & 0x000000FF);
+		}
+	}
+	if (hfunc)
+		(*hfunc) = ETH_RSS_HASH_TOP;
+	return 0;
+}
+
+static int lan743x_ethtool_set_rxfh(struct net_device *netdev,
+				    const u32 *indir, const u8 *key,
+				    const u8 hfunc)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+
+	if (indir) {
+		u32 indir_value = 0;
+		int dword_index = 0;
+		int byte_index = 0;
+
+		for (dword_index = 0; dword_index < 32; dword_index++) {
+			byte_index = dword_index << 2;
+			indir_value =
+				(((indir[byte_index + 0] & 0x000000FF) << 0) |
+				((indir[byte_index + 1] & 0x000000FF) << 8) |
+				((indir[byte_index + 2] & 0x000000FF) << 16) |
+				((indir[byte_index + 3] & 0x000000FF) << 24));
+			lan743x_csr_write(adapter, RFE_INDX(dword_index),
+					  indir_value);
+		}
+	}
+	if (key) {
+		int dword_index = 0;
+		int byte_index = 0;
+		u32 key_value = 0;
+
+		for (dword_index = 0; dword_index < 10; dword_index++) {
+			byte_index = dword_index << 2;
+			key_value =
+				((((u32)(key[byte_index + 0])) << 0) |
+				(((u32)(key[byte_index + 1])) << 8) |
+				(((u32)(key[byte_index + 2])) << 16) |
+				(((u32)(key[byte_index + 3])) << 24));
+			lan743x_csr_write(adapter, RFE_HASH_KEY(dword_index),
+					  key_value);
+		}
+	}
+	return 0;
+}
+
+static int lan743x_ethtool_get_ts_info(struct net_device *netdev,
+				       struct ethtool_ts_info *ts_info)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	ts_info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+				   SOF_TIMESTAMPING_RX_SOFTWARE |
+				   SOF_TIMESTAMPING_SOFTWARE |
+				   SOF_TIMESTAMPING_TX_HARDWARE |
+				   SOF_TIMESTAMPING_RX_HARDWARE |
+				   SOF_TIMESTAMPING_RAW_HARDWARE;
+
+	if (adapter->ptp.ptp_clock)
+		ts_info->phc_index = ptp_clock_index(adapter->ptp.ptp_clock);
+	else
+		ts_info->phc_index = -1;
+
+	ts_info->tx_types = BIT(HWTSTAMP_TX_OFF) |
+			    BIT(HWTSTAMP_TX_ON) |
+			    BIT(HWTSTAMP_TX_ONESTEP_SYNC);
+	ts_info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) |
+			      BIT(HWTSTAMP_FILTER_ALL);
+	return 0;
+}
+
+static int lan743x_ethtool_get_eee(struct net_device *netdev,
+				   struct ethtool_eee *eee)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	struct phy_device *phydev = netdev->phydev;
+	u32 buf;
+	int ret;
+
+	if (!phydev)
+		return -EIO;
+	if (!phydev->drv) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "Missing PHY Driver\n");
+		return -EIO;
+	}
+
+	ret = phy_ethtool_get_eee(phydev, eee);
+	if (ret < 0)
+		return ret;
+
+	buf = lan743x_csr_read(adapter, MAC_CR);
+	if (buf & MAC_CR_EEE_EN_) {
+		eee->eee_enabled = true;
+		eee->eee_active = !!(eee->advertised & eee->lp_advertised);
+		eee->tx_lpi_enabled = true;
+		/* EEE_TX_LPI_REQ_DLY & tx_lpi_timer are same uSec unit */
+		buf = lan743x_csr_read(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT);
+		eee->tx_lpi_timer = buf;
+	} else {
+		eee->eee_enabled = false;
+		eee->eee_active = false;
+		eee->tx_lpi_enabled = false;
+		eee->tx_lpi_timer = 0;
+	}
+
+	return 0;
+}
+
+static int lan743x_ethtool_set_eee(struct net_device *netdev,
+				   struct ethtool_eee *eee)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	struct phy_device *phydev = NULL;
+	u32 buf = 0;
+	int ret = 0;
+
+	if (!netdev)
+		return -EINVAL;
+	adapter = netdev_priv(netdev);
+	if (!adapter)
+		return -EINVAL;
+	phydev = netdev->phydev;
+	if (!phydev)
+		return -EIO;
+	if (!phydev->drv) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "Missing PHY Driver\n");
+		return -EIO;
+	}
+
+	if (eee->eee_enabled) {
+		ret = phy_init_eee(phydev, 0);
+		if (ret) {
+			netif_err(adapter, drv, adapter->netdev,
+				  "EEE initialization failed\n");
+			return ret;
+		}
+
+		buf = (u32)eee->tx_lpi_timer;
+		lan743x_csr_write(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT, buf);
+
+		buf = lan743x_csr_read(adapter, MAC_CR);
+		buf |= MAC_CR_EEE_EN_;
+		lan743x_csr_write(adapter, MAC_CR, buf);
+	} else {
+		buf = lan743x_csr_read(adapter, MAC_CR);
+		buf &= ~MAC_CR_EEE_EN_;
+		lan743x_csr_write(adapter, MAC_CR, buf);
+	}
+
+	return phy_ethtool_set_eee(phydev, eee);
+}
+
+#ifdef CONFIG_PM
+static void lan743x_ethtool_get_wol(struct net_device *netdev,
+				    struct ethtool_wolinfo *wol)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	wol->supported = 0;
+	wol->wolopts = 0;
+	phy_ethtool_get_wol(netdev->phydev, wol);
+
+	wol->supported |= WAKE_BCAST | WAKE_UCAST | WAKE_MCAST |
+		WAKE_MAGIC | WAKE_PHY | WAKE_ARP;
+
+	wol->wolopts |= adapter->wolopts;
+}
+
+static int lan743x_ethtool_set_wol(struct net_device *netdev,
+				   struct ethtool_wolinfo *wol)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	adapter->wolopts = 0;
+	if (wol->wolopts & WAKE_UCAST)
+		adapter->wolopts |= WAKE_UCAST;
+	if (wol->wolopts & WAKE_MCAST)
+		adapter->wolopts |= WAKE_MCAST;
+	if (wol->wolopts & WAKE_BCAST)
+		adapter->wolopts |= WAKE_BCAST;
+	if (wol->wolopts & WAKE_MAGIC)
+		adapter->wolopts |= WAKE_MAGIC;
+	if (wol->wolopts & WAKE_PHY)
+		adapter->wolopts |= WAKE_PHY;
+	if (wol->wolopts & WAKE_ARP)
+		adapter->wolopts |= WAKE_ARP;
+
+	device_set_wakeup_enable(&adapter->pdev->dev, (bool)wol->wolopts);
+
+	phy_ethtool_set_wol(netdev->phydev, wol);
+
+	return 0;
+}
+#endif /* CONFIG_PM */
+
+const struct ethtool_ops lan743x_ethtool_ops = {
+	.get_drvinfo = lan743x_ethtool_get_drvinfo,
+	.get_msglevel = lan743x_ethtool_get_msglevel,
+	.set_msglevel = lan743x_ethtool_set_msglevel,
+	.get_link = ethtool_op_get_link,
+
+	.get_eeprom_len = lan743x_ethtool_get_eeprom_len,
+	.get_eeprom = lan743x_ethtool_get_eeprom,
+	.set_eeprom = lan743x_ethtool_set_eeprom,
+	.get_strings = lan743x_ethtool_get_strings,
+	.get_ethtool_stats = lan743x_ethtool_get_ethtool_stats,
+	.get_sset_count = lan743x_ethtool_get_sset_count,
+	.get_rxnfc = lan743x_ethtool_get_rxnfc,
+	.get_rxfh_key_size = lan743x_ethtool_get_rxfh_key_size,
+	.get_rxfh_indir_size = lan743x_ethtool_get_rxfh_indir_size,
+	.get_rxfh = lan743x_ethtool_get_rxfh,
+	.set_rxfh = lan743x_ethtool_set_rxfh,
+	.get_ts_info = lan743x_ethtool_get_ts_info,
+	.get_eee = lan743x_ethtool_get_eee,
+	.set_eee = lan743x_ethtool_set_eee,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
+#ifdef CONFIG_PM
+	.get_wol = lan743x_ethtool_get_wol,
+	.set_wol = lan743x_ethtool_set_wol,
+#endif
+};
diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.h b/drivers/net/ethernet/microchip/lan743x_ethtool.h
new file mode 100644
index 000000000000..d0d11a777a58
--- /dev/null
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (C) 2018 Microchip Technology Inc. */
+
+#ifndef _LAN743X_ETHTOOL_H
+#define _LAN743X_ETHTOOL_H
+
+#include "linux/ethtool.h"
+
+extern const struct ethtool_ops lan743x_ethtool_ops;
+
+#endif /* _LAN743X_ETHTOOL_H */
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index dd947e4dd3ce..e7dce79ff2c9 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -11,7 +11,9 @@
 #include <linux/phy.h>
 #include <linux/rtnetlink.h>
 #include <linux/iopoll.h>
+#include <linux/crc16.h>
 #include "lan743x_main.h"
+#include "lan743x_ethtool.h"
 
 static void lan743x_pci_cleanup(struct lan743x_adapter *adapter)
 {
@@ -53,13 +55,13 @@ return_error:
 	return ret;
 }
 
-static u32 lan743x_csr_read(struct lan743x_adapter *adapter, int offset)
+u32 lan743x_csr_read(struct lan743x_adapter *adapter, int offset)
 {
 	return ioread32(&adapter->csr.csr_address[offset]);
 }
 
-static void lan743x_csr_write(struct lan743x_adapter *adapter, int offset,
-			      u32 data)
+void lan743x_csr_write(struct lan743x_adapter *adapter, int offset,
+		       u32 data)
 {
 	iowrite32(data, &adapter->csr.csr_address[offset]);
 }
@@ -265,6 +267,10 @@ static void lan743x_intr_shared_isr(void *context, u32 int_sts, u32 flags)
 			lan743x_intr_software_isr(adapter);
 			int_sts &= ~INT_BIT_SW_GP_;
 		}
+		if (int_sts & INT_BIT_1588_) {
+			lan743x_ptp_isr(adapter);
+			int_sts &= ~INT_BIT_1588_;
+		}
 	}
 	if (int_sts)
 		lan743x_csr_write(adapter, INT_EN_CLR, int_sts);
@@ -828,7 +834,7 @@ static int lan743x_mac_init(struct lan743x_adapter *adapter)
 	}
 
 	if (!mac_address_valid)
-		random_ether_addr(adapter->mac_address);
+		eth_random_addr(adapter->mac_address);
 	lan743x_mac_set_address(adapter, adapter->mac_address);
 	ether_addr_copy(netdev->dev_addr, adapter->mac_address);
 	return 0;
@@ -974,6 +980,7 @@ static void lan743x_phy_link_status_change(struct net_device *netdev)
 					       ksettings.base.duplex,
 					       local_advertisement,
 					       remote_advertisement);
+		lan743x_ptp_update_latency(adapter, ksettings.base.speed);
 	}
 }
 
@@ -1023,6 +1030,24 @@ return_error:
 	return ret;
 }
 
+static void lan743x_rfe_open(struct lan743x_adapter *adapter)
+{
+	lan743x_csr_write(adapter, RFE_RSS_CFG,
+		RFE_RSS_CFG_UDP_IPV6_EX_ |
+		RFE_RSS_CFG_TCP_IPV6_EX_ |
+		RFE_RSS_CFG_IPV6_EX_ |
+		RFE_RSS_CFG_UDP_IPV6_ |
+		RFE_RSS_CFG_TCP_IPV6_ |
+		RFE_RSS_CFG_IPV6_ |
+		RFE_RSS_CFG_UDP_IPV4_ |
+		RFE_RSS_CFG_TCP_IPV4_ |
+		RFE_RSS_CFG_IPV4_ |
+		RFE_RSS_CFG_VALID_HASH_BITS_ |
+		RFE_RSS_CFG_RSS_QUEUE_ENABLE_ |
+		RFE_RSS_CFG_RSS_HASH_STORE_ |
+		RFE_RSS_CFG_RSS_ENABLE_);
+}
+
 static void lan743x_rfe_update_mac_address(struct lan743x_adapter *adapter)
 {
 	u8 *mac_addr;
@@ -1206,6 +1231,7 @@ static void lan743x_tx_release_desc(struct lan743x_tx *tx,
 	struct lan743x_tx_buffer_info *buffer_info = NULL;
 	struct lan743x_tx_descriptor *descriptor = NULL;
 	u32 descriptor_type = 0;
+	bool ignore_sync;
 
 	descriptor = &tx->ring_cpu_ptr[descriptor_index];
 	buffer_info = &tx->buffer_info[descriptor_index];
@@ -1236,11 +1262,27 @@ clean_up_data_descriptor:
 		buffer_info->dma_ptr = 0;
 		buffer_info->buffer_length = 0;
 	}
-	if (buffer_info->skb) {
+	if (!buffer_info->skb)
+		goto clear_active;
+
+	if (!(buffer_info->flags & TX_BUFFER_INFO_FLAG_TIMESTAMP_REQUESTED)) {
 		dev_kfree_skb(buffer_info->skb);
-		buffer_info->skb = NULL;
+		goto clear_skb;
 	}
 
+	if (cleanup) {
+		lan743x_ptp_unrequest_tx_timestamp(tx->adapter);
+		dev_kfree_skb(buffer_info->skb);
+	} else {
+		ignore_sync = (buffer_info->flags &
+			       TX_BUFFER_INFO_FLAG_IGNORE_SYNC) != 0;
+		lan743x_ptp_tx_timestamp_skb(tx->adapter,
+					     buffer_info->skb, ignore_sync);
+	}
+
+clear_skb:
+	buffer_info->skb = NULL;
+
 clear_active:
 	buffer_info->flags &= ~TX_BUFFER_INFO_FLAG_ACTIVE;
 
@@ -1301,10 +1343,25 @@ static int lan743x_tx_get_avail_desc(struct lan743x_tx *tx)
 		return last_head - last_tail - 1;
 }
 
+void lan743x_tx_set_timestamping_mode(struct lan743x_tx *tx,
+				      bool enable_timestamping,
+				      bool enable_onestep_sync)
+{
+	if (enable_timestamping)
+		tx->ts_flags |= TX_TS_FLAG_TIMESTAMPING_ENABLED;
+	else
+		tx->ts_flags &= ~TX_TS_FLAG_TIMESTAMPING_ENABLED;
+	if (enable_onestep_sync)
+		tx->ts_flags |= TX_TS_FLAG_ONE_STEP_SYNC;
+	else
+		tx->ts_flags &= ~TX_TS_FLAG_ONE_STEP_SYNC;
+}
+
 static int lan743x_tx_frame_start(struct lan743x_tx *tx,
 				  unsigned char *first_buffer,
 				  unsigned int first_buffer_length,
 				  unsigned int frame_length,
+				  bool time_stamp,
 				  bool check_sum)
 {
 	/* called only from within lan743x_tx_xmit_frame.
@@ -1342,6 +1399,8 @@ static int lan743x_tx_frame_start(struct lan743x_tx *tx,
 		TX_DESC_DATA0_DTYPE_DATA_ |
 		TX_DESC_DATA0_FS_ |
 		TX_DESC_DATA0_FCS_;
+	if (time_stamp)
+		tx->frame_data0 |= TX_DESC_DATA0_TSE_;
 
 	if (check_sum)
 		tx->frame_data0 |= TX_DESC_DATA0_ICE_ |
@@ -1455,6 +1514,7 @@ static int lan743x_tx_frame_add_fragment(struct lan743x_tx *tx,
 
 static void lan743x_tx_frame_end(struct lan743x_tx *tx,
 				 struct sk_buff *skb,
+				 bool time_stamp,
 				 bool ignore_sync)
 {
 	/* called only from within lan743x_tx_xmit_frame
@@ -1472,6 +1532,8 @@ static void lan743x_tx_frame_end(struct lan743x_tx *tx,
 	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
 	buffer_info = &tx->buffer_info[tx->frame_tail];
 	buffer_info->skb = skb;
+	if (time_stamp)
+		buffer_info->flags |= TX_BUFFER_INFO_FLAG_TIMESTAMP_REQUESTED;
 	if (ignore_sync)
 		buffer_info->flags |= TX_BUFFER_INFO_FLAG_IGNORE_SYNC;
 
@@ -1500,6 +1562,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx,
 	unsigned int frame_length = 0;
 	unsigned int head_length = 0;
 	unsigned long irq_flags = 0;
+	bool do_timestamp = false;
 	bool ignore_sync = false;
 	int nr_frags = 0;
 	bool gso = false;
@@ -1521,6 +1584,14 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx,
 	}
 
 	/* space available, transmit skb  */
+	if ((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+	    (tx->ts_flags & TX_TS_FLAG_TIMESTAMPING_ENABLED) &&
+	    (lan743x_ptp_request_tx_timestamp(tx->adapter))) {
+		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+		do_timestamp = true;
+		if (tx->ts_flags & TX_TS_FLAG_ONE_STEP_SYNC)
+			ignore_sync = true;
+	}
 	head_length = skb_headlen(skb);
 	frame_length = skb_pagelen(skb);
 	nr_frags = skb_shinfo(skb)->nr_frags;
@@ -1534,6 +1605,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx,
 	if (lan743x_tx_frame_start(tx,
 				   skb->data, head_length,
 				   start_frame_length,
+				   do_timestamp,
 				   skb->ip_summed == CHECKSUM_PARTIAL)) {
 		dev_kfree_skb(skb);
 		goto unlock;
@@ -1561,7 +1633,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx,
 	}
 
 finish:
-	lan743x_tx_frame_end(tx, skb, ignore_sync);
+	lan743x_tx_frame_end(tx, skb, do_timestamp, ignore_sync);
 
 unlock:
 	spin_unlock_irqrestore(&tx->ring_lock, irq_flags);
@@ -2390,6 +2462,8 @@ static int lan743x_netdev_close(struct net_device *netdev)
 	for (index = 0; index < LAN743X_USED_RX_CHANNELS; index++)
 		lan743x_rx_close(&adapter->rx[index]);
 
+	lan743x_ptp_close(adapter);
+
 	lan743x_phy_close(adapter);
 
 	lan743x_mac_close(adapter);
@@ -2417,6 +2491,12 @@ static int lan743x_netdev_open(struct net_device *netdev)
 	if (ret)
 		goto close_mac;
 
+	ret = lan743x_ptp_open(adapter);
+	if (ret)
+		goto close_phy;
+
+	lan743x_rfe_open(adapter);
+
 	for (index = 0; index < LAN743X_USED_RX_CHANNELS; index++) {
 		ret = lan743x_rx_open(&adapter->rx[index]);
 		if (ret)
@@ -2434,6 +2514,9 @@ close_rx:
 		if (adapter->rx[index].ring_cpu_ptr)
 			lan743x_rx_close(&adapter->rx[index]);
 	}
+	lan743x_ptp_close(adapter);
+
+close_phy:
 	lan743x_phy_close(adapter);
 
 close_mac:
@@ -2461,6 +2544,8 @@ static int lan743x_netdev_ioctl(struct net_device *netdev,
 {
 	if (!netif_running(netdev))
 		return -EINVAL;
+	if (cmd == SIOCSHWTSTAMP)
+		return lan743x_ptp_ioctl(netdev, ifr, cmd);
 	return phy_mii_ioctl(netdev->phydev, ifr, cmd);
 }
 
@@ -2585,6 +2670,11 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter,
 	adapter->intr.irq = adapter->pdev->irq;
 	lan743x_csr_write(adapter, INT_EN_CLR, 0xFFFFFFFF);
 	mutex_init(&adapter->dp_lock);
+
+	ret = lan743x_gpio_init(adapter);
+	if (ret)
+		return ret;
+
 	ret = lan743x_mac_init(adapter);
 	if (ret)
 		return ret;
@@ -2593,6 +2683,10 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter,
 	if (ret)
 		return ret;
 
+	ret = lan743x_ptp_init(adapter);
+	if (ret)
+		return ret;
+
 	lan743x_rfe_update_mac_address(adapter);
 
 	ret = lan743x_dmac_init(adapter);
@@ -2689,6 +2783,7 @@ static int lan743x_pcidev_probe(struct pci_dev *pdev,
 		goto cleanup_hardware;
 
 	adapter->netdev->netdev_ops = &lan743x_netdev_ops;
+	adapter->netdev->ethtool_ops = &lan743x_ethtool_ops;
 	adapter->netdev->features = NETIF_F_SG | NETIF_F_TSO | NETIF_F_HW_CSUM;
 	adapter->netdev->hw_features = adapter->netdev->features;
 
@@ -2747,10 +2842,182 @@ static void lan743x_pcidev_shutdown(struct pci_dev *pdev)
 		lan743x_netdev_close(netdev);
 	rtnl_unlock();
 
+#ifdef CONFIG_PM
+	pci_save_state(pdev);
+#endif
+
 	/* clean up lan743x portion */
 	lan743x_hardware_cleanup(adapter);
 }
 
+#ifdef CONFIG_PM
+static u16 lan743x_pm_wakeframe_crc16(const u8 *buf, int len)
+{
+	return bitrev16(crc16(0xFFFF, buf, len));
+}
+
+static void lan743x_pm_set_wol(struct lan743x_adapter *adapter)
+{
+	const u8 ipv4_multicast[3] = { 0x01, 0x00, 0x5E };
+	const u8 ipv6_multicast[3] = { 0x33, 0x33 };
+	const u8 arp_type[2] = { 0x08, 0x06 };
+	int mask_index;
+	u32 pmtctl;
+	u32 wucsr;
+	u32 macrx;
+	u16 crc;
+
+	for (mask_index = 0; mask_index < MAC_NUM_OF_WUF_CFG; mask_index++)
+		lan743x_csr_write(adapter, MAC_WUF_CFG(mask_index), 0);
+
+	/* clear wake settings */
+	pmtctl = lan743x_csr_read(adapter, PMT_CTL);
+	pmtctl |= PMT_CTL_WUPS_MASK_;
+	pmtctl &= ~(PMT_CTL_GPIO_WAKEUP_EN_ | PMT_CTL_EEE_WAKEUP_EN_ |
+		PMT_CTL_WOL_EN_ | PMT_CTL_MAC_D3_RX_CLK_OVR_ |
+		PMT_CTL_RX_FCT_RFE_D3_CLK_OVR_ | PMT_CTL_ETH_PHY_WAKE_EN_);
+
+	macrx = lan743x_csr_read(adapter, MAC_RX);
+
+	wucsr = 0;
+	mask_index = 0;
+
+	pmtctl |= PMT_CTL_ETH_PHY_D3_COLD_OVR_ | PMT_CTL_ETH_PHY_D3_OVR_;
+
+	if (adapter->wolopts & WAKE_PHY) {
+		pmtctl |= PMT_CTL_ETH_PHY_EDPD_PLL_CTL_;
+		pmtctl |= PMT_CTL_ETH_PHY_WAKE_EN_;
+	}
+	if (adapter->wolopts & WAKE_MAGIC) {
+		wucsr |= MAC_WUCSR_MPEN_;
+		macrx |= MAC_RX_RXEN_;
+		pmtctl |= PMT_CTL_WOL_EN_ | PMT_CTL_MAC_D3_RX_CLK_OVR_;
+	}
+	if (adapter->wolopts & WAKE_UCAST) {
+		wucsr |= MAC_WUCSR_RFE_WAKE_EN_ | MAC_WUCSR_PFDA_EN_;
+		macrx |= MAC_RX_RXEN_;
+		pmtctl |= PMT_CTL_WOL_EN_ | PMT_CTL_MAC_D3_RX_CLK_OVR_;
+		pmtctl |= PMT_CTL_RX_FCT_RFE_D3_CLK_OVR_;
+	}
+	if (adapter->wolopts & WAKE_BCAST) {
+		wucsr |= MAC_WUCSR_RFE_WAKE_EN_ | MAC_WUCSR_BCST_EN_;
+		macrx |= MAC_RX_RXEN_;
+		pmtctl |= PMT_CTL_WOL_EN_ | PMT_CTL_MAC_D3_RX_CLK_OVR_;
+		pmtctl |= PMT_CTL_RX_FCT_RFE_D3_CLK_OVR_;
+	}
+	if (adapter->wolopts & WAKE_MCAST) {
+		/* IPv4 multicast */
+		crc = lan743x_pm_wakeframe_crc16(ipv4_multicast, 3);
+		lan743x_csr_write(adapter, MAC_WUF_CFG(mask_index),
+				  MAC_WUF_CFG_EN_ | MAC_WUF_CFG_TYPE_MCAST_ |
+				  (0 << MAC_WUF_CFG_OFFSET_SHIFT_) |
+				  (crc & MAC_WUF_CFG_CRC16_MASK_));
+		lan743x_csr_write(adapter, MAC_WUF_MASK0(mask_index), 7);
+		lan743x_csr_write(adapter, MAC_WUF_MASK1(mask_index), 0);
+		lan743x_csr_write(adapter, MAC_WUF_MASK2(mask_index), 0);
+		lan743x_csr_write(adapter, MAC_WUF_MASK3(mask_index), 0);
+		mask_index++;
+
+		/* IPv6 multicast */
+		crc = lan743x_pm_wakeframe_crc16(ipv6_multicast, 2);
+		lan743x_csr_write(adapter, MAC_WUF_CFG(mask_index),
+				  MAC_WUF_CFG_EN_ | MAC_WUF_CFG_TYPE_MCAST_ |
+				  (0 << MAC_WUF_CFG_OFFSET_SHIFT_) |
+				  (crc & MAC_WUF_CFG_CRC16_MASK_));
+		lan743x_csr_write(adapter, MAC_WUF_MASK0(mask_index), 3);
+		lan743x_csr_write(adapter, MAC_WUF_MASK1(mask_index), 0);
+		lan743x_csr_write(adapter, MAC_WUF_MASK2(mask_index), 0);
+		lan743x_csr_write(adapter, MAC_WUF_MASK3(mask_index), 0);
+		mask_index++;
+
+		wucsr |= MAC_WUCSR_RFE_WAKE_EN_ | MAC_WUCSR_WAKE_EN_;
+		macrx |= MAC_RX_RXEN_;
+		pmtctl |= PMT_CTL_WOL_EN_ | PMT_CTL_MAC_D3_RX_CLK_OVR_;
+		pmtctl |= PMT_CTL_RX_FCT_RFE_D3_CLK_OVR_;
+	}
+	if (adapter->wolopts & WAKE_ARP) {
+		/* set MAC_WUF_CFG & WUF_MASK
+		 * for packettype (offset 12,13) = ARP (0x0806)
+		 */
+		crc = lan743x_pm_wakeframe_crc16(arp_type, 2);
+		lan743x_csr_write(adapter, MAC_WUF_CFG(mask_index),
+				  MAC_WUF_CFG_EN_ | MAC_WUF_CFG_TYPE_ALL_ |
+				  (0 << MAC_WUF_CFG_OFFSET_SHIFT_) |
+				  (crc & MAC_WUF_CFG_CRC16_MASK_));
+		lan743x_csr_write(adapter, MAC_WUF_MASK0(mask_index), 0x3000);
+		lan743x_csr_write(adapter, MAC_WUF_MASK1(mask_index), 0);
+		lan743x_csr_write(adapter, MAC_WUF_MASK2(mask_index), 0);
+		lan743x_csr_write(adapter, MAC_WUF_MASK3(mask_index), 0);
+		mask_index++;
+
+		wucsr |= MAC_WUCSR_RFE_WAKE_EN_ | MAC_WUCSR_WAKE_EN_;
+		macrx |= MAC_RX_RXEN_;
+		pmtctl |= PMT_CTL_WOL_EN_ | PMT_CTL_MAC_D3_RX_CLK_OVR_;
+		pmtctl |= PMT_CTL_RX_FCT_RFE_D3_CLK_OVR_;
+	}
+
+	lan743x_csr_write(adapter, MAC_WUCSR, wucsr);
+	lan743x_csr_write(adapter, PMT_CTL, pmtctl);
+	lan743x_csr_write(adapter, MAC_RX, macrx);
+}
+
+static int lan743x_pm_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	int ret;
+
+	lan743x_pcidev_shutdown(pdev);
+
+	/* clear all wakes */
+	lan743x_csr_write(adapter, MAC_WUCSR, 0);
+	lan743x_csr_write(adapter, MAC_WUCSR2, 0);
+	lan743x_csr_write(adapter, MAC_WK_SRC, 0xFFFFFFFF);
+
+	if (adapter->wolopts)
+		lan743x_pm_set_wol(adapter);
+
+	/* Host sets PME_En, put D3hot */
+	ret = pci_prepare_to_sleep(pdev);
+
+	return 0;
+}
+
+static int lan743x_pm_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	int ret;
+
+	pci_set_power_state(pdev, PCI_D0);
+	pci_restore_state(pdev);
+	pci_save_state(pdev);
+
+	ret = lan743x_hardware_init(adapter, pdev);
+	if (ret) {
+		netif_err(adapter, probe, adapter->netdev,
+			  "lan743x_hardware_init returned %d\n", ret);
+	}
+
+	/* open netdev when netdev is at running state while resume.
+	 * For instance, it is true when system wakesup after pm-suspend
+	 * However, it is false when system wakes up after suspend GUI menu
+	 */
+	if (netif_running(netdev))
+		lan743x_netdev_open(netdev);
+
+	netif_device_attach(netdev);
+
+	return 0;
+}
+
+static const struct dev_pm_ops lan743x_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(lan743x_pm_suspend, lan743x_pm_resume)
+};
+#endif /*CONFIG_PM */
+
 static const struct pci_device_id lan743x_pcidev_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_LAN7430) },
 	{ 0, }
@@ -2761,6 +3028,9 @@ static struct pci_driver lan743x_pcidev_driver = {
 	.id_table = lan743x_pcidev_tbl,
 	.probe    = lan743x_pcidev_probe,
 	.remove   = lan743x_pcidev_remove,
+#ifdef CONFIG_PM
+	.driver.pm = &lan743x_pm_ops,
+#endif
 	.shutdown = lan743x_pcidev_shutdown,
 };
 
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index 73b463a9df61..0e82b6368798 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -4,12 +4,17 @@
 #ifndef _LAN743X_H
 #define _LAN743X_H
 
+#include "lan743x_ptp.h"
+
 #define DRIVER_AUTHOR   "Bryan Whitehead <Bryan.Whitehead@microchip.com>"
 #define DRIVER_DESC "LAN743x PCIe Gigabit Ethernet Driver"
 #define DRIVER_NAME "lan743x"
 
 /* Register Definitions */
 #define ID_REV				(0x00)
+#define ID_REV_ID_MASK_			(0xFFFF0000)
+#define ID_REV_ID_LAN7430_		(0x74300000)
+#define ID_REV_ID_LAN7431_		(0x74310000)
 #define ID_REV_IS_VALID_CHIP_ID_(id_rev)	\
 	(((id_rev) & 0xFFF00000) == 0x74300000)
 #define ID_REV_CHIP_REV_MASK_		(0x0000FFFF)
@@ -24,8 +29,18 @@
 #define HW_CFG_LRST_				BIT(1)
 
 #define PMT_CTL					(0x014)
+#define PMT_CTL_ETH_PHY_D3_COLD_OVR_		BIT(27)
+#define PMT_CTL_MAC_D3_RX_CLK_OVR_		BIT(25)
+#define PMT_CTL_ETH_PHY_EDPD_PLL_CTL_		BIT(24)
+#define PMT_CTL_ETH_PHY_D3_OVR_			BIT(23)
+#define PMT_CTL_RX_FCT_RFE_D3_CLK_OVR_		BIT(18)
+#define PMT_CTL_GPIO_WAKEUP_EN_			BIT(15)
+#define PMT_CTL_EEE_WAKEUP_EN_			BIT(13)
 #define PMT_CTL_READY_				BIT(7)
 #define PMT_CTL_ETH_PHY_RST_			BIT(4)
+#define PMT_CTL_WOL_EN_				BIT(3)
+#define PMT_CTL_ETH_PHY_WAKE_EN_		BIT(2)
+#define PMT_CTL_WUPS_MASK_			(0x00000003)
 
 #define DP_SEL				(0x024)
 #define DP_SEL_DPRDY_			BIT(31)
@@ -42,6 +57,31 @@
 
 #define DP_DATA_0			(0x030)
 
+#define E2P_CMD				(0x040)
+#define E2P_CMD_EPC_BUSY_		BIT(31)
+#define E2P_CMD_EPC_CMD_WRITE_		(0x30000000)
+#define E2P_CMD_EPC_CMD_EWEN_		(0x20000000)
+#define E2P_CMD_EPC_CMD_READ_		(0x00000000)
+#define E2P_CMD_EPC_TIMEOUT_		BIT(10)
+#define E2P_CMD_EPC_ADDR_MASK_		(0x000001FF)
+
+#define E2P_DATA			(0x044)
+
+#define GPIO_CFG0			(0x050)
+#define GPIO_CFG0_GPIO_DIR_BIT_(bit)	BIT(16 + (bit))
+#define GPIO_CFG0_GPIO_DATA_BIT_(bit)	BIT(0 + (bit))
+
+#define GPIO_CFG1			(0x054)
+#define GPIO_CFG1_GPIOEN_BIT_(bit)	BIT(16 + (bit))
+#define GPIO_CFG1_GPIOBUF_BIT_(bit)	BIT(0 + (bit))
+
+#define GPIO_CFG2			(0x058)
+#define GPIO_CFG2_1588_POL_BIT_(bit)	BIT(0 + (bit))
+
+#define GPIO_CFG3			(0x05C)
+#define GPIO_CFG3_1588_CH_SEL_BIT_(bit)	BIT(16 + (bit))
+#define GPIO_CFG3_1588_OE_BIT_(bit)	BIT(0 + (bit))
+
 #define FCT_RX_CTL			(0xAC)
 #define FCT_RX_CTL_EN_(channel)		BIT(28 + (channel))
 #define FCT_RX_CTL_DIS_(channel)	BIT(24 + (channel))
@@ -62,6 +102,7 @@
 	((value << 0) & FCT_FLOW_CTL_ON_THRESHOLD_)
 
 #define MAC_CR				(0x100)
+#define MAC_CR_EEE_EN_			BIT(17)
 #define MAC_CR_ADD_			BIT(12)
 #define MAC_CR_ASD_			BIT(11)
 #define MAC_CR_CNTR_RST_		BIT(5)
@@ -97,6 +138,40 @@
 
 #define MAC_MII_DATA			(0x124)
 
+#define MAC_EEE_TX_LPI_REQ_DLY_CNT		(0x130)
+
+#define MAC_WUCSR				(0x140)
+#define MAC_WUCSR_RFE_WAKE_EN_			BIT(14)
+#define MAC_WUCSR_PFDA_EN_			BIT(3)
+#define MAC_WUCSR_WAKE_EN_			BIT(2)
+#define MAC_WUCSR_MPEN_				BIT(1)
+#define MAC_WUCSR_BCST_EN_			BIT(0)
+
+#define MAC_WK_SRC				(0x144)
+
+#define MAC_WUF_CFG0			(0x150)
+#define MAC_NUM_OF_WUF_CFG		(32)
+#define MAC_WUF_CFG_BEGIN		(MAC_WUF_CFG0)
+#define MAC_WUF_CFG(index)		(MAC_WUF_CFG_BEGIN + (4 * (index)))
+#define MAC_WUF_CFG_EN_			BIT(31)
+#define MAC_WUF_CFG_TYPE_MCAST_		(0x02000000)
+#define MAC_WUF_CFG_TYPE_ALL_		(0x01000000)
+#define MAC_WUF_CFG_OFFSET_SHIFT_	(16)
+#define MAC_WUF_CFG_CRC16_MASK_		(0x0000FFFF)
+
+#define MAC_WUF_MASK0_0			(0x200)
+#define MAC_WUF_MASK0_1			(0x204)
+#define MAC_WUF_MASK0_2			(0x208)
+#define MAC_WUF_MASK0_3			(0x20C)
+#define MAC_WUF_MASK0_BEGIN		(MAC_WUF_MASK0_0)
+#define MAC_WUF_MASK1_BEGIN		(MAC_WUF_MASK0_1)
+#define MAC_WUF_MASK2_BEGIN		(MAC_WUF_MASK0_2)
+#define MAC_WUF_MASK3_BEGIN		(MAC_WUF_MASK0_3)
+#define MAC_WUF_MASK0(index)		(MAC_WUF_MASK0_BEGIN + (0x10 * (index)))
+#define MAC_WUF_MASK1(index)		(MAC_WUF_MASK1_BEGIN + (0x10 * (index)))
+#define MAC_WUF_MASK2(index)		(MAC_WUF_MASK2_BEGIN + (0x10 * (index)))
+#define MAC_WUF_MASK3(index)		(MAC_WUF_MASK3_BEGIN + (0x10 * (index)))
+
 /* offset 0x400 - 0x500, x may range from 0 to 32, for a total of 33 entries */
 #define RFE_ADDR_FILT_HI(x)		(0x400 + (8 * (x)))
 #define RFE_ADDR_FILT_HI_VALID_		BIT(31)
@@ -111,13 +186,35 @@
 #define RFE_CTL_MCAST_HASH_		BIT(3)
 #define RFE_CTL_DA_PERFECT_		BIT(1)
 
+#define RFE_RSS_CFG			(0x554)
+#define RFE_RSS_CFG_UDP_IPV6_EX_	BIT(16)
+#define RFE_RSS_CFG_TCP_IPV6_EX_	BIT(15)
+#define RFE_RSS_CFG_IPV6_EX_		BIT(14)
+#define RFE_RSS_CFG_UDP_IPV6_		BIT(13)
+#define RFE_RSS_CFG_TCP_IPV6_		BIT(12)
+#define RFE_RSS_CFG_IPV6_		BIT(11)
+#define RFE_RSS_CFG_UDP_IPV4_		BIT(10)
+#define RFE_RSS_CFG_TCP_IPV4_		BIT(9)
+#define RFE_RSS_CFG_IPV4_		BIT(8)
+#define RFE_RSS_CFG_VALID_HASH_BITS_	(0x000000E0)
+#define RFE_RSS_CFG_RSS_QUEUE_ENABLE_	BIT(2)
+#define RFE_RSS_CFG_RSS_HASH_STORE_	BIT(1)
+#define RFE_RSS_CFG_RSS_ENABLE_		BIT(0)
+
+#define RFE_HASH_KEY(index)		(0x558 + (index << 2))
+
+#define RFE_INDX(index)			(0x580 + (index << 2))
+
+#define MAC_WUCSR2			(0x600)
+
 #define INT_STS				(0x780)
 #define INT_BIT_DMA_RX_(channel)	BIT(24 + (channel))
 #define INT_BIT_ALL_RX_			(0x0F000000)
 #define INT_BIT_DMA_TX_(channel)	BIT(16 + (channel))
 #define INT_BIT_ALL_TX_			(0x000F0000)
 #define INT_BIT_SW_GP_			BIT(9)
-#define INT_BIT_ALL_OTHER_		(0x00000280)
+#define INT_BIT_1588_			BIT(7)
+#define INT_BIT_ALL_OTHER_		(INT_BIT_SW_GP_ | INT_BIT_1588_)
 #define INT_BIT_MAS_			BIT(0)
 
 #define INT_SET				(0x784)
@@ -158,6 +255,71 @@
 #define INT_MOD_CFG6			(0x7D8)
 #define INT_MOD_CFG7			(0x7DC)
 
+#define PTP_CMD_CTL					(0x0A00)
+#define PTP_CMD_CTL_PTP_CLK_STP_NSEC_			BIT(6)
+#define PTP_CMD_CTL_PTP_CLOCK_STEP_SEC_			BIT(5)
+#define PTP_CMD_CTL_PTP_CLOCK_LOAD_			BIT(4)
+#define PTP_CMD_CTL_PTP_CLOCK_READ_			BIT(3)
+#define PTP_CMD_CTL_PTP_ENABLE_				BIT(2)
+#define PTP_CMD_CTL_PTP_DISABLE_			BIT(1)
+#define PTP_CMD_CTL_PTP_RESET_				BIT(0)
+#define PTP_GENERAL_CONFIG				(0x0A04)
+#define PTP_GENERAL_CONFIG_CLOCK_EVENT_X_MASK_(channel) \
+	(0x7 << (1 + ((channel) << 2)))
+#define PTP_GENERAL_CONFIG_CLOCK_EVENT_100NS_	(0)
+#define PTP_GENERAL_CONFIG_CLOCK_EVENT_10US_	(1)
+#define PTP_GENERAL_CONFIG_CLOCK_EVENT_100US_	(2)
+#define PTP_GENERAL_CONFIG_CLOCK_EVENT_1MS_	(3)
+#define PTP_GENERAL_CONFIG_CLOCK_EVENT_10MS_	(4)
+#define PTP_GENERAL_CONFIG_CLOCK_EVENT_200MS_	(5)
+#define PTP_GENERAL_CONFIG_CLOCK_EVENT_X_SET_(channel, value) \
+	(((value) & 0x7) << (1 + ((channel) << 2)))
+#define PTP_GENERAL_CONFIG_RELOAD_ADD_X_(channel)	(BIT((channel) << 2))
+
+#define PTP_INT_STS				(0x0A08)
+#define PTP_INT_EN_SET				(0x0A0C)
+#define PTP_INT_EN_CLR				(0x0A10)
+#define PTP_INT_BIT_TX_SWTS_ERR_		BIT(13)
+#define PTP_INT_BIT_TX_TS_			BIT(12)
+#define PTP_INT_BIT_TIMER_B_			BIT(1)
+#define PTP_INT_BIT_TIMER_A_			BIT(0)
+
+#define PTP_CLOCK_SEC				(0x0A14)
+#define PTP_CLOCK_NS				(0x0A18)
+#define PTP_CLOCK_SUBNS				(0x0A1C)
+#define PTP_CLOCK_RATE_ADJ			(0x0A20)
+#define PTP_CLOCK_RATE_ADJ_DIR_			BIT(31)
+#define PTP_CLOCK_STEP_ADJ			(0x0A2C)
+#define PTP_CLOCK_STEP_ADJ_DIR_			BIT(31)
+#define PTP_CLOCK_STEP_ADJ_VALUE_MASK_		(0x3FFFFFFF)
+#define PTP_CLOCK_TARGET_SEC_X(channel)		(0x0A30 + ((channel) << 4))
+#define PTP_CLOCK_TARGET_NS_X(channel)		(0x0A34 + ((channel) << 4))
+#define PTP_CLOCK_TARGET_RELOAD_SEC_X(channel)	(0x0A38 + ((channel) << 4))
+#define PTP_CLOCK_TARGET_RELOAD_NS_X(channel)	(0x0A3C + ((channel) << 4))
+#define PTP_LATENCY				(0x0A5C)
+#define PTP_LATENCY_TX_SET_(tx_latency)		(((u32)(tx_latency)) << 16)
+#define PTP_LATENCY_RX_SET_(rx_latency)		\
+	(((u32)(rx_latency)) & 0x0000FFFF)
+#define PTP_CAP_INFO				(0x0A60)
+#define PTP_CAP_INFO_TX_TS_CNT_GET_(reg_val)	(((reg_val) & 0x00000070) >> 4)
+
+#define PTP_TX_MOD				(0x0AA4)
+#define PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_	(0x10000000)
+
+#define PTP_TX_MOD2				(0x0AA8)
+#define PTP_TX_MOD2_TX_PTP_CLR_UDPV4_CHKSUM_	(0x00000001)
+
+#define PTP_TX_EGRESS_SEC			(0x0AAC)
+#define PTP_TX_EGRESS_NS			(0x0AB0)
+#define PTP_TX_EGRESS_NS_CAPTURE_CAUSE_MASK_	(0xC0000000)
+#define PTP_TX_EGRESS_NS_CAPTURE_CAUSE_AUTO_	(0x00000000)
+#define PTP_TX_EGRESS_NS_CAPTURE_CAUSE_SW_	(0x40000000)
+#define PTP_TX_EGRESS_NS_TS_NS_MASK_		(0x3FFFFFFF)
+
+#define PTP_TX_MSG_HEADER			(0x0AB4)
+#define PTP_TX_MSG_HEADER_MSG_TYPE_		(0x000F0000)
+#define PTP_TX_MSG_HEADER_MSG_TYPE_SYNC_	(0x00000000)
+
 #define DMAC_CFG				(0xC00)
 #define DMAC_CFG_COAL_EN_			BIT(16)
 #define DMAC_CFG_CH_ARB_SEL_RX_HIGH_		(0x00000000)
@@ -288,9 +450,33 @@
 #define TX_CFG_C_TX_DMA_INT_STS_AUTO_CLR_	BIT(3)
 #define TX_CFG_C_TX_INT_STS_R2C_MODE_MASK_	(0x00000007)
 
+#define OTP_PWR_DN				(0x1000)
+#define OTP_PWR_DN_PWRDN_N_			BIT(0)
+
+#define OTP_ADDR1				(0x1004)
+#define OTP_ADDR1_15_11_MASK_			(0x1F)
+
+#define OTP_ADDR2				(0x1008)
+#define OTP_ADDR2_10_3_MASK_			(0xFF)
+
+#define OTP_PRGM_DATA				(0x1010)
+
+#define OTP_PRGM_MODE				(0x1014)
+#define OTP_PRGM_MODE_BYTE_			BIT(0)
+
+#define OTP_TST_CMD				(0x1024)
+#define OTP_TST_CMD_PRGVRFY_			BIT(3)
+
+#define OTP_CMD_GO				(0x1028)
+#define OTP_CMD_GO_GO_				BIT(0)
+
+#define OTP_STATUS				(0x1030)
+#define OTP_STATUS_BUSY_			BIT(0)
+
 /* MAC statistics registers */
 #define STAT_RX_FCS_ERRORS			(0x1200)
 #define STAT_RX_ALIGNMENT_ERRORS		(0x1204)
+#define STAT_RX_FRAGMENT_ERRORS			(0x1208)
 #define STAT_RX_JABBER_ERRORS			(0x120C)
 #define STAT_RX_UNDERSIZE_FRAME_ERRORS		(0x1210)
 #define STAT_RX_OVERSIZE_FRAME_ERRORS		(0x1214)
@@ -298,12 +484,26 @@
 #define STAT_RX_UNICAST_BYTE_COUNT		(0x121C)
 #define STAT_RX_BROADCAST_BYTE_COUNT		(0x1220)
 #define STAT_RX_MULTICAST_BYTE_COUNT		(0x1224)
+#define STAT_RX_UNICAST_FRAMES			(0x1228)
+#define STAT_RX_BROADCAST_FRAMES		(0x122C)
 #define STAT_RX_MULTICAST_FRAMES		(0x1230)
+#define STAT_RX_PAUSE_FRAMES			(0x1234)
+#define STAT_RX_64_BYTE_FRAMES			(0x1238)
+#define STAT_RX_65_127_BYTE_FRAMES		(0x123C)
+#define STAT_RX_128_255_BYTE_FRAMES		(0x1240)
+#define STAT_RX_256_511_BYTES_FRAMES		(0x1244)
+#define STAT_RX_512_1023_BYTE_FRAMES		(0x1248)
+#define STAT_RX_1024_1518_BYTE_FRAMES		(0x124C)
+#define STAT_RX_GREATER_1518_BYTE_FRAMES	(0x1250)
 #define STAT_RX_TOTAL_FRAMES			(0x1254)
+#define STAT_EEE_RX_LPI_TRANSITIONS		(0x1258)
+#define STAT_EEE_RX_LPI_TIME			(0x125C)
+#define STAT_RX_COUNTER_ROLLOVER_STATUS		(0x127C)
 
 #define STAT_TX_FCS_ERRORS			(0x1280)
 #define STAT_TX_EXCESS_DEFERRAL_ERRORS		(0x1284)
 #define STAT_TX_CARRIER_ERRORS			(0x1288)
+#define STAT_TX_BAD_BYTE_COUNT			(0x128C)
 #define STAT_TX_SINGLE_COLLISIONS		(0x1290)
 #define STAT_TX_MULTIPLE_COLLISIONS		(0x1294)
 #define STAT_TX_EXCESSIVE_COLLISION		(0x1298)
@@ -311,8 +511,21 @@
 #define STAT_TX_UNICAST_BYTE_COUNT		(0x12A0)
 #define STAT_TX_BROADCAST_BYTE_COUNT		(0x12A4)
 #define STAT_TX_MULTICAST_BYTE_COUNT		(0x12A8)
+#define STAT_TX_UNICAST_FRAMES			(0x12AC)
+#define STAT_TX_BROADCAST_FRAMES		(0x12B0)
 #define STAT_TX_MULTICAST_FRAMES		(0x12B4)
+#define STAT_TX_PAUSE_FRAMES			(0x12B8)
+#define STAT_TX_64_BYTE_FRAMES			(0x12BC)
+#define STAT_TX_65_127_BYTE_FRAMES		(0x12C0)
+#define STAT_TX_128_255_BYTE_FRAMES		(0x12C4)
+#define STAT_TX_256_511_BYTES_FRAMES		(0x12C8)
+#define STAT_TX_512_1023_BYTE_FRAMES		(0x12CC)
+#define STAT_TX_1024_1518_BYTE_FRAMES		(0x12D0)
+#define STAT_TX_GREATER_1518_BYTE_FRAMES	(0x12D4)
 #define STAT_TX_TOTAL_FRAMES			(0x12D8)
+#define STAT_EEE_TX_LPI_TRANSITIONS		(0x12DC)
+#define STAT_EEE_TX_LPI_TIME			(0x12E0)
+#define STAT_TX_COUNTER_ROLLOVER_STATUS		(0x12FC)
 
 /* End of Register definitions */
 
@@ -415,8 +628,12 @@ struct lan743x_tx_buffer_info;
 
 #define TX_FRAME_FLAG_IN_PROGRESS	BIT(0)
 
+#define TX_TS_FLAG_TIMESTAMPING_ENABLED	BIT(0)
+#define TX_TS_FLAG_ONE_STEP_SYNC	BIT(1)
+
 struct lan743x_tx {
 	struct lan743x_adapter *adapter;
+	u32	ts_flags;
 	u32	vector_flags;
 	int	channel_number;
 
@@ -443,6 +660,10 @@ struct lan743x_tx {
 	struct sk_buff *overflow_skb;
 };
 
+void lan743x_tx_set_timestamping_mode(struct lan743x_tx *tx,
+				      bool enable_timestamping,
+				      bool enable_onestep_sync);
+
 /* RX */
 struct lan743x_rx_descriptor;
 struct lan743x_rx_buffer_info;
@@ -473,6 +694,9 @@ struct lan743x_adapter {
 	struct net_device       *netdev;
 	struct mii_bus		*mdiobus;
 	int                     msg_enable;
+#ifdef CONFIG_PM
+	u32			wolopts;
+#endif
 	struct pci_dev		*pdev;
 	struct lan743x_csr      csr;
 	struct lan743x_intr     intr;
@@ -480,6 +704,9 @@ struct lan743x_adapter {
 	/* lock, used to prevent concurrent access to data port */
 	struct mutex		dp_lock;
 
+	struct lan743x_gpio	gpio;
+	struct lan743x_ptp	ptp;
+
 	u8			mac_address[ETH_ALEN];
 
 	struct lan743x_phy      phy;
@@ -530,6 +757,7 @@ struct lan743x_adapter {
 #define TX_DESC_DATA0_IPE_			(0x00200000)
 #define TX_DESC_DATA0_TPE_			(0x00100000)
 #define TX_DESC_DATA0_FCS_			(0x00020000)
+#define TX_DESC_DATA0_TSE_			(0x00010000)
 #define TX_DESC_DATA0_BUF_LENGTH_MASK_		(0x0000FFFF)
 #define TX_DESC_DATA0_EXT_LSO_			(0x00200000)
 #define TX_DESC_DATA0_EXT_PAY_LENGTH_MASK_	(0x000FFFFF)
@@ -543,6 +771,7 @@ struct lan743x_tx_descriptor {
 } __aligned(DEFAULT_DMA_DESCRIPTOR_SPACING);
 
 #define TX_BUFFER_INFO_FLAG_ACTIVE		BIT(0)
+#define TX_BUFFER_INFO_FLAG_TIMESTAMP_REQUESTED	BIT(1)
 #define TX_BUFFER_INFO_FLAG_IGNORE_SYNC		BIT(2)
 #define TX_BUFFER_INFO_FLAG_SKB_FRAGMENT	BIT(3)
 struct lan743x_tx_buffer_info {
@@ -594,4 +823,7 @@ struct lan743x_rx_buffer_info {
 #define RX_PROCESS_RESULT_PACKET_RECEIVED   (1)
 #define RX_PROCESS_RESULT_PACKET_DROPPED    (2)
 
+u32 lan743x_csr_read(struct lan743x_adapter *adapter, int offset);
+void lan743x_csr_write(struct lan743x_adapter *adapter, int offset, u32 data);
+
 #endif /* _LAN743X_H */
diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c
new file mode 100644
index 000000000000..64dba96edc79
--- /dev/null
+++ b/drivers/net/ethernet/microchip/lan743x_ptp.c
@@ -0,0 +1,1160 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (C) 2018 Microchip Technology Inc. */
+
+#include <linux/netdevice.h>
+#include "lan743x_main.h"
+
+#include <linux/ptp_clock_kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/net_tstamp.h>
+
+#include "lan743x_ptp.h"
+
+#define LAN743X_NUMBER_OF_GPIO			(12)
+#define LAN743X_PTP_MAX_FREQ_ADJ_IN_PPB		(31249999)
+#define LAN743X_PTP_MAX_FINE_ADJ_IN_SCALED_PPM	(2047999934)
+
+static bool lan743x_ptp_is_enabled(struct lan743x_adapter *adapter);
+static void lan743x_ptp_enable(struct lan743x_adapter *adapter);
+static void lan743x_ptp_disable(struct lan743x_adapter *adapter);
+static void lan743x_ptp_reset(struct lan743x_adapter *adapter);
+static void lan743x_ptp_clock_set(struct lan743x_adapter *adapter,
+				  u32 seconds, u32 nano_seconds,
+				  u32 sub_nano_seconds);
+
+int lan743x_gpio_init(struct lan743x_adapter *adapter)
+{
+	struct lan743x_gpio *gpio = &adapter->gpio;
+
+	spin_lock_init(&gpio->gpio_lock);
+
+	gpio->gpio_cfg0 = 0; /* set all direction to input, data = 0 */
+	gpio->gpio_cfg1 = 0x0FFF0000;/* disable all gpio, set to open drain */
+	gpio->gpio_cfg2 = 0;/* set all to 1588 low polarity level */
+	gpio->gpio_cfg3 = 0;/* disable all 1588 output */
+	lan743x_csr_write(adapter, GPIO_CFG0, gpio->gpio_cfg0);
+	lan743x_csr_write(adapter, GPIO_CFG1, gpio->gpio_cfg1);
+	lan743x_csr_write(adapter, GPIO_CFG2, gpio->gpio_cfg2);
+	lan743x_csr_write(adapter, GPIO_CFG3, gpio->gpio_cfg3);
+
+	return 0;
+}
+
+static void lan743x_ptp_wait_till_cmd_done(struct lan743x_adapter *adapter,
+					   u32 bit_mask)
+{
+	int timeout = 1000;
+	u32 data = 0;
+
+	while (timeout &&
+	       (data = (lan743x_csr_read(adapter, PTP_CMD_CTL) &
+	       bit_mask))) {
+		usleep_range(1000, 20000);
+		timeout--;
+	}
+	if (data) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "timeout waiting for cmd to be done, cmd = 0x%08X\n",
+			  bit_mask);
+	}
+}
+
+static void lan743x_ptp_tx_ts_enqueue_ts(struct lan743x_adapter *adapter,
+					 u32 seconds, u32 nano_seconds,
+					 u32 header)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	spin_lock_bh(&ptp->tx_ts_lock);
+	if (ptp->tx_ts_queue_size < LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS) {
+		ptp->tx_ts_seconds_queue[ptp->tx_ts_queue_size] = seconds;
+		ptp->tx_ts_nseconds_queue[ptp->tx_ts_queue_size] = nano_seconds;
+		ptp->tx_ts_header_queue[ptp->tx_ts_queue_size] = header;
+		ptp->tx_ts_queue_size++;
+	} else {
+		netif_err(adapter, drv, adapter->netdev,
+			  "tx ts queue overflow\n");
+	}
+	spin_unlock_bh(&ptp->tx_ts_lock);
+}
+
+static void lan743x_ptp_tx_ts_complete(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+	struct skb_shared_hwtstamps tstamps;
+	u32 header, nseconds, seconds;
+	bool ignore_sync = false;
+	struct sk_buff *skb;
+	int c, i;
+
+	spin_lock_bh(&ptp->tx_ts_lock);
+	c = ptp->tx_ts_skb_queue_size;
+
+	if (c > ptp->tx_ts_queue_size)
+		c = ptp->tx_ts_queue_size;
+	if (c <= 0)
+		goto done;
+
+	for (i = 0; i < c; i++) {
+		ignore_sync = ((ptp->tx_ts_ignore_sync_queue &
+				BIT(i)) != 0);
+		skb = ptp->tx_ts_skb_queue[i];
+		nseconds = ptp->tx_ts_nseconds_queue[i];
+		seconds = ptp->tx_ts_seconds_queue[i];
+		header = ptp->tx_ts_header_queue[i];
+
+		memset(&tstamps, 0, sizeof(tstamps));
+		tstamps.hwtstamp = ktime_set(seconds, nseconds);
+		if (!ignore_sync ||
+		    ((header & PTP_TX_MSG_HEADER_MSG_TYPE_) !=
+		    PTP_TX_MSG_HEADER_MSG_TYPE_SYNC_))
+			skb_tstamp_tx(skb, &tstamps);
+
+		dev_kfree_skb(skb);
+
+		ptp->tx_ts_skb_queue[i] = NULL;
+		ptp->tx_ts_seconds_queue[i] = 0;
+		ptp->tx_ts_nseconds_queue[i] = 0;
+		ptp->tx_ts_header_queue[i] = 0;
+	}
+
+	/* shift queue */
+	ptp->tx_ts_ignore_sync_queue >>= c;
+	for (i = c; i < LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS; i++) {
+		ptp->tx_ts_skb_queue[i - c] = ptp->tx_ts_skb_queue[i];
+		ptp->tx_ts_seconds_queue[i - c] = ptp->tx_ts_seconds_queue[i];
+		ptp->tx_ts_nseconds_queue[i - c] = ptp->tx_ts_nseconds_queue[i];
+		ptp->tx_ts_header_queue[i - c] = ptp->tx_ts_header_queue[i];
+
+		ptp->tx_ts_skb_queue[i] = NULL;
+		ptp->tx_ts_seconds_queue[i] = 0;
+		ptp->tx_ts_nseconds_queue[i] = 0;
+		ptp->tx_ts_header_queue[i] = 0;
+	}
+	ptp->tx_ts_skb_queue_size -= c;
+	ptp->tx_ts_queue_size -= c;
+done:
+	ptp->pending_tx_timestamps -= c;
+	spin_unlock_bh(&ptp->tx_ts_lock);
+}
+
+static int lan743x_ptp_reserve_event_ch(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+	int result = -ENODEV;
+	int index = 0;
+
+	mutex_lock(&ptp->command_lock);
+	for (index = 0; index < LAN743X_PTP_NUMBER_OF_EVENT_CHANNELS; index++) {
+		if (!(test_bit(index, &ptp->used_event_ch))) {
+			ptp->used_event_ch |= BIT(index);
+			result = index;
+			break;
+		}
+	}
+	mutex_unlock(&ptp->command_lock);
+	return result;
+}
+
+static void lan743x_ptp_release_event_ch(struct lan743x_adapter *adapter,
+					 int event_channel)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	mutex_lock(&ptp->command_lock);
+	if (test_bit(event_channel, &ptp->used_event_ch)) {
+		ptp->used_event_ch &= ~BIT(event_channel);
+	} else {
+		netif_warn(adapter, drv, adapter->netdev,
+			   "attempted release on a not used event_channel = %d\n",
+			   event_channel);
+	}
+	mutex_unlock(&ptp->command_lock);
+}
+
+static void lan743x_ptp_clock_get(struct lan743x_adapter *adapter,
+				  u32 *seconds, u32 *nano_seconds,
+				  u32 *sub_nano_seconds);
+static void lan743x_ptp_clock_step(struct lan743x_adapter *adapter,
+				   s64 time_step_ns);
+
+static int lan743x_gpio_rsrv_ptp_out(struct lan743x_adapter *adapter,
+				     int bit, int ptp_channel)
+{
+	struct lan743x_gpio *gpio = &adapter->gpio;
+	unsigned long irq_flags = 0;
+	int bit_mask = BIT(bit);
+	int ret = -EBUSY;
+
+	spin_lock_irqsave(&gpio->gpio_lock, irq_flags);
+
+	if (!(gpio->used_bits & bit_mask)) {
+		gpio->used_bits |= bit_mask;
+		gpio->output_bits |= bit_mask;
+		gpio->ptp_bits |= bit_mask;
+
+		/* set as output, and zero initial value */
+		gpio->gpio_cfg0 |= GPIO_CFG0_GPIO_DIR_BIT_(bit);
+		gpio->gpio_cfg0 &= ~GPIO_CFG0_GPIO_DATA_BIT_(bit);
+		lan743x_csr_write(adapter, GPIO_CFG0, gpio->gpio_cfg0);
+
+		/* enable gpio, and set buffer type to push pull */
+		gpio->gpio_cfg1 &= ~GPIO_CFG1_GPIOEN_BIT_(bit);
+		gpio->gpio_cfg1 |= GPIO_CFG1_GPIOBUF_BIT_(bit);
+		lan743x_csr_write(adapter, GPIO_CFG1, gpio->gpio_cfg1);
+
+		/* set 1588 polarity to high */
+		gpio->gpio_cfg2 |= GPIO_CFG2_1588_POL_BIT_(bit);
+		lan743x_csr_write(adapter, GPIO_CFG2, gpio->gpio_cfg2);
+
+		if (!ptp_channel) {
+			/* use channel A */
+			gpio->gpio_cfg3 &= ~GPIO_CFG3_1588_CH_SEL_BIT_(bit);
+		} else {
+			/* use channel B */
+			gpio->gpio_cfg3 |= GPIO_CFG3_1588_CH_SEL_BIT_(bit);
+		}
+		gpio->gpio_cfg3 |= GPIO_CFG3_1588_OE_BIT_(bit);
+		lan743x_csr_write(adapter, GPIO_CFG3, gpio->gpio_cfg3);
+
+		ret = bit;
+	}
+	spin_unlock_irqrestore(&gpio->gpio_lock, irq_flags);
+	return ret;
+}
+
+static void lan743x_gpio_release(struct lan743x_adapter *adapter, int bit)
+{
+	struct lan743x_gpio *gpio = &adapter->gpio;
+	unsigned long irq_flags = 0;
+	int bit_mask = BIT(bit);
+
+	spin_lock_irqsave(&gpio->gpio_lock, irq_flags);
+	if (gpio->used_bits & bit_mask) {
+		gpio->used_bits &= ~bit_mask;
+		if (gpio->output_bits & bit_mask) {
+			gpio->output_bits &= ~bit_mask;
+
+			if (gpio->ptp_bits & bit_mask) {
+				gpio->ptp_bits &= ~bit_mask;
+				/* disable ptp output */
+				gpio->gpio_cfg3 &= ~GPIO_CFG3_1588_OE_BIT_(bit);
+				lan743x_csr_write(adapter, GPIO_CFG3,
+						  gpio->gpio_cfg3);
+			}
+			/* release gpio output */
+
+			/* disable gpio */
+			gpio->gpio_cfg1 |= GPIO_CFG1_GPIOEN_BIT_(bit);
+			gpio->gpio_cfg1 &= ~GPIO_CFG1_GPIOBUF_BIT_(bit);
+			lan743x_csr_write(adapter, GPIO_CFG1, gpio->gpio_cfg1);
+
+			/* reset back to input */
+			gpio->gpio_cfg0 &= ~GPIO_CFG0_GPIO_DIR_BIT_(bit);
+			gpio->gpio_cfg0 &= ~GPIO_CFG0_GPIO_DATA_BIT_(bit);
+			lan743x_csr_write(adapter, GPIO_CFG0, gpio->gpio_cfg0);
+		}
+	}
+	spin_unlock_irqrestore(&gpio->gpio_lock, irq_flags);
+}
+
+static int lan743x_ptpci_adjfine(struct ptp_clock_info *ptpci, long scaled_ppm)
+{
+	struct lan743x_ptp *ptp =
+		container_of(ptpci, struct lan743x_ptp, ptp_clock_info);
+	struct lan743x_adapter *adapter =
+		container_of(ptp, struct lan743x_adapter, ptp);
+	u32 lan743x_rate_adj = 0;
+	bool positive = true;
+	u64 u64_delta = 0;
+
+	if ((scaled_ppm < (-LAN743X_PTP_MAX_FINE_ADJ_IN_SCALED_PPM)) ||
+	    scaled_ppm > LAN743X_PTP_MAX_FINE_ADJ_IN_SCALED_PPM) {
+		return -EINVAL;
+	}
+	if (scaled_ppm > 0) {
+		u64_delta = (u64)scaled_ppm;
+		positive = true;
+	} else {
+		u64_delta = (u64)(-scaled_ppm);
+		positive = false;
+	}
+	u64_delta = (u64_delta << 19);
+	lan743x_rate_adj = div_u64(u64_delta, 1000000);
+
+	if (positive)
+		lan743x_rate_adj |= PTP_CLOCK_RATE_ADJ_DIR_;
+
+	lan743x_csr_write(adapter, PTP_CLOCK_RATE_ADJ,
+			  lan743x_rate_adj);
+
+	return 0;
+}
+
+static int lan743x_ptpci_adjfreq(struct ptp_clock_info *ptpci, s32 delta_ppb)
+{
+	struct lan743x_ptp *ptp =
+		container_of(ptpci, struct lan743x_ptp, ptp_clock_info);
+	struct lan743x_adapter *adapter =
+		container_of(ptp, struct lan743x_adapter, ptp);
+	u32 lan743x_rate_adj = 0;
+	bool positive = true;
+	u32 u32_delta = 0;
+	u64 u64_delta = 0;
+
+	if ((delta_ppb < (-LAN743X_PTP_MAX_FREQ_ADJ_IN_PPB)) ||
+	    delta_ppb > LAN743X_PTP_MAX_FREQ_ADJ_IN_PPB) {
+		return -EINVAL;
+	}
+	if (delta_ppb > 0) {
+		u32_delta = (u32)delta_ppb;
+		positive = true;
+	} else {
+		u32_delta = (u32)(-delta_ppb);
+		positive = false;
+	}
+	u64_delta = (((u64)u32_delta) << 35);
+	lan743x_rate_adj = div_u64(u64_delta, 1000000000);
+
+	if (positive)
+		lan743x_rate_adj |= PTP_CLOCK_RATE_ADJ_DIR_;
+
+	lan743x_csr_write(adapter, PTP_CLOCK_RATE_ADJ,
+			  lan743x_rate_adj);
+
+	return 0;
+}
+
+static int lan743x_ptpci_adjtime(struct ptp_clock_info *ptpci, s64 delta)
+{
+	struct lan743x_ptp *ptp =
+		container_of(ptpci, struct lan743x_ptp, ptp_clock_info);
+	struct lan743x_adapter *adapter =
+		container_of(ptp, struct lan743x_adapter, ptp);
+
+	lan743x_ptp_clock_step(adapter, delta);
+
+	return 0;
+}
+
+static int lan743x_ptpci_gettime64(struct ptp_clock_info *ptpci,
+				   struct timespec64 *ts)
+{
+	struct lan743x_ptp *ptp =
+		container_of(ptpci, struct lan743x_ptp, ptp_clock_info);
+	struct lan743x_adapter *adapter =
+		container_of(ptp, struct lan743x_adapter, ptp);
+	u32 nano_seconds = 0;
+	u32 seconds = 0;
+
+	lan743x_ptp_clock_get(adapter, &seconds, &nano_seconds, NULL);
+	ts->tv_sec = seconds;
+	ts->tv_nsec = nano_seconds;
+
+	return 0;
+}
+
+static int lan743x_ptpci_settime64(struct ptp_clock_info *ptpci,
+				   const struct timespec64 *ts)
+{
+	struct lan743x_ptp *ptp =
+		container_of(ptpci, struct lan743x_ptp, ptp_clock_info);
+	struct lan743x_adapter *adapter =
+		container_of(ptp, struct lan743x_adapter, ptp);
+	u32 nano_seconds = 0;
+	u32 seconds = 0;
+
+	if (ts) {
+		if (ts->tv_sec > 0xFFFFFFFFLL ||
+		    ts->tv_sec < 0) {
+			netif_warn(adapter, drv, adapter->netdev,
+				   "ts->tv_sec out of range, %lld\n",
+				   ts->tv_sec);
+			return -ERANGE;
+		}
+		if (ts->tv_nsec >= 1000000000L ||
+		    ts->tv_nsec < 0) {
+			netif_warn(adapter, drv, adapter->netdev,
+				   "ts->tv_nsec out of range, %ld\n",
+				   ts->tv_nsec);
+			return -ERANGE;
+		}
+		seconds = ts->tv_sec;
+		nano_seconds = ts->tv_nsec;
+		lan743x_ptp_clock_set(adapter, seconds, nano_seconds, 0);
+	} else {
+		netif_warn(adapter, drv, adapter->netdev, "ts == NULL\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void lan743x_ptp_perout_off(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+	u32 general_config = 0;
+
+	if (ptp->perout_gpio_bit >= 0) {
+		lan743x_gpio_release(adapter, ptp->perout_gpio_bit);
+		ptp->perout_gpio_bit = -1;
+	}
+
+	if (ptp->perout_event_ch >= 0) {
+		/* set target to far in the future, effectively disabling it */
+		lan743x_csr_write(adapter,
+				  PTP_CLOCK_TARGET_SEC_X(ptp->perout_event_ch),
+				  0xFFFF0000);
+		lan743x_csr_write(adapter,
+				  PTP_CLOCK_TARGET_NS_X(ptp->perout_event_ch),
+				  0);
+
+		general_config = lan743x_csr_read(adapter, PTP_GENERAL_CONFIG);
+		general_config |= PTP_GENERAL_CONFIG_RELOAD_ADD_X_
+				  (ptp->perout_event_ch);
+		lan743x_csr_write(adapter, PTP_GENERAL_CONFIG, general_config);
+		lan743x_ptp_release_event_ch(adapter, ptp->perout_event_ch);
+		ptp->perout_event_ch = -1;
+	}
+}
+
+static int lan743x_ptp_perout(struct lan743x_adapter *adapter, int on,
+			      struct ptp_perout_request *perout)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+	u32 period_sec = 0, period_nsec = 0;
+	u32 start_sec = 0, start_nsec = 0;
+	u32 general_config = 0;
+	int pulse_width = 0;
+	int perout_bit = 0;
+
+	if (!on) {
+		lan743x_ptp_perout_off(adapter);
+		return 0;
+	}
+
+	if (ptp->perout_event_ch >= 0 ||
+	    ptp->perout_gpio_bit >= 0) {
+		/* already on, turn off first */
+		lan743x_ptp_perout_off(adapter);
+	}
+
+	ptp->perout_event_ch = lan743x_ptp_reserve_event_ch(adapter);
+	if (ptp->perout_event_ch < 0) {
+		netif_warn(adapter, drv, adapter->netdev,
+			   "Failed to reserve event channel for PEROUT\n");
+		goto failed;
+	}
+
+	switch (adapter->csr.id_rev & ID_REV_ID_MASK_) {
+	case ID_REV_ID_LAN7430_:
+		perout_bit = 2;/* GPIO 2 is preferred on EVB LAN7430 */
+		break;
+	case ID_REV_ID_LAN7431_:
+		perout_bit = 4;/* GPIO 4 is preferred on EVB LAN7431 */
+		break;
+	}
+
+	ptp->perout_gpio_bit = lan743x_gpio_rsrv_ptp_out(adapter,
+							 perout_bit,
+							 ptp->perout_event_ch);
+
+	if (ptp->perout_gpio_bit < 0) {
+		netif_warn(adapter, drv, adapter->netdev,
+			   "Failed to reserve gpio %d for PEROUT\n",
+			   perout_bit);
+		goto failed;
+	}
+
+	start_sec = perout->start.sec;
+	start_sec += perout->start.nsec / 1000000000;
+	start_nsec = perout->start.nsec % 1000000000;
+
+	period_sec = perout->period.sec;
+	period_sec += perout->period.nsec / 1000000000;
+	period_nsec = perout->period.nsec % 1000000000;
+
+	if (period_sec == 0) {
+		if (period_nsec >= 400000000) {
+			pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_200MS_;
+		} else if (period_nsec >= 20000000) {
+			pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_10MS_;
+		} else if (period_nsec >= 2000000) {
+			pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_1MS_;
+		} else if (period_nsec >= 200000) {
+			pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_100US_;
+		} else if (period_nsec >= 20000) {
+			pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_10US_;
+		} else if (period_nsec >= 200) {
+			pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_100NS_;
+		} else {
+			netif_warn(adapter, drv, adapter->netdev,
+				   "perout period too small, minimum is 200nS\n");
+			goto failed;
+		}
+	} else {
+		pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_200MS_;
+	}
+
+	/* turn off by setting target far in future */
+	lan743x_csr_write(adapter,
+			  PTP_CLOCK_TARGET_SEC_X(ptp->perout_event_ch),
+			  0xFFFF0000);
+	lan743x_csr_write(adapter,
+			  PTP_CLOCK_TARGET_NS_X(ptp->perout_event_ch), 0);
+
+	/* Configure to pulse every period */
+	general_config = lan743x_csr_read(adapter, PTP_GENERAL_CONFIG);
+	general_config &= ~(PTP_GENERAL_CONFIG_CLOCK_EVENT_X_MASK_
+			  (ptp->perout_event_ch));
+	general_config |= PTP_GENERAL_CONFIG_CLOCK_EVENT_X_SET_
+			  (ptp->perout_event_ch, pulse_width);
+	general_config &= ~PTP_GENERAL_CONFIG_RELOAD_ADD_X_
+			  (ptp->perout_event_ch);
+	lan743x_csr_write(adapter, PTP_GENERAL_CONFIG, general_config);
+
+	/* set the reload to one toggle cycle */
+	lan743x_csr_write(adapter,
+			  PTP_CLOCK_TARGET_RELOAD_SEC_X(ptp->perout_event_ch),
+			  period_sec);
+	lan743x_csr_write(adapter,
+			  PTP_CLOCK_TARGET_RELOAD_NS_X(ptp->perout_event_ch),
+			  period_nsec);
+
+	/* set the start time */
+	lan743x_csr_write(adapter,
+			  PTP_CLOCK_TARGET_SEC_X(ptp->perout_event_ch),
+			  start_sec);
+	lan743x_csr_write(adapter,
+			  PTP_CLOCK_TARGET_NS_X(ptp->perout_event_ch),
+			  start_nsec);
+
+	return 0;
+
+failed:
+	lan743x_ptp_perout_off(adapter);
+	return -ENODEV;
+}
+
+static int lan743x_ptpci_enable(struct ptp_clock_info *ptpci,
+				struct ptp_clock_request *request, int on)
+{
+	struct lan743x_ptp *ptp =
+		container_of(ptpci, struct lan743x_ptp, ptp_clock_info);
+	struct lan743x_adapter *adapter =
+		container_of(ptp, struct lan743x_adapter, ptp);
+
+	if (request) {
+		switch (request->type) {
+		case PTP_CLK_REQ_EXTTS:
+			return -EINVAL;
+		case PTP_CLK_REQ_PEROUT:
+			if (request->perout.index == 0)
+				return lan743x_ptp_perout(adapter, on,
+							  &request->perout);
+			return -EINVAL;
+		case PTP_CLK_REQ_PPS:
+			return -EINVAL;
+		default:
+			netif_err(adapter, drv, adapter->netdev,
+				  "request->type == %d, Unknown\n",
+				  request->type);
+			break;
+		}
+	} else {
+		netif_err(adapter, drv, adapter->netdev, "request == NULL\n");
+	}
+	return 0;
+}
+
+static long lan743x_ptpci_do_aux_work(struct ptp_clock_info *ptpci)
+{
+	struct lan743x_ptp *ptp =
+		container_of(ptpci, struct lan743x_ptp, ptp_clock_info);
+	struct lan743x_adapter *adapter =
+		container_of(ptp, struct lan743x_adapter, ptp);
+	u32 cap_info, cause, header, nsec, seconds;
+	bool new_timestamp_available = false;
+	int count = 0;
+
+	while ((count < 100) &&
+	       (lan743x_csr_read(adapter, PTP_INT_STS) & PTP_INT_BIT_TX_TS_)) {
+		count++;
+		cap_info = lan743x_csr_read(adapter, PTP_CAP_INFO);
+
+		if (PTP_CAP_INFO_TX_TS_CNT_GET_(cap_info) > 0) {
+			seconds = lan743x_csr_read(adapter,
+						   PTP_TX_EGRESS_SEC);
+			nsec = lan743x_csr_read(adapter, PTP_TX_EGRESS_NS);
+			cause = (nsec &
+				 PTP_TX_EGRESS_NS_CAPTURE_CAUSE_MASK_);
+			header = lan743x_csr_read(adapter,
+						  PTP_TX_MSG_HEADER);
+
+			if (cause == PTP_TX_EGRESS_NS_CAPTURE_CAUSE_SW_) {
+				nsec &= PTP_TX_EGRESS_NS_TS_NS_MASK_;
+				lan743x_ptp_tx_ts_enqueue_ts(adapter,
+							     seconds, nsec,
+							     header);
+				new_timestamp_available = true;
+			} else if (cause ==
+				PTP_TX_EGRESS_NS_CAPTURE_CAUSE_AUTO_) {
+				netif_err(adapter, drv, adapter->netdev,
+					  "Auto capture cause not supported\n");
+			} else {
+				netif_warn(adapter, drv, adapter->netdev,
+					   "unknown tx timestamp capture cause\n");
+			}
+		} else {
+			netif_warn(adapter, drv, adapter->netdev,
+				   "TX TS INT but no TX TS CNT\n");
+		}
+		lan743x_csr_write(adapter, PTP_INT_STS, PTP_INT_BIT_TX_TS_);
+	}
+
+	if (new_timestamp_available)
+		lan743x_ptp_tx_ts_complete(adapter);
+
+	lan743x_csr_write(adapter, INT_EN_SET, INT_BIT_1588_);
+
+	return -1;
+}
+
+static void lan743x_ptp_clock_get(struct lan743x_adapter *adapter,
+				  u32 *seconds, u32 *nano_seconds,
+				  u32 *sub_nano_seconds)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	mutex_lock(&ptp->command_lock);
+
+	lan743x_csr_write(adapter, PTP_CMD_CTL, PTP_CMD_CTL_PTP_CLOCK_READ_);
+	lan743x_ptp_wait_till_cmd_done(adapter, PTP_CMD_CTL_PTP_CLOCK_READ_);
+
+	if (seconds)
+		(*seconds) = lan743x_csr_read(adapter, PTP_CLOCK_SEC);
+
+	if (nano_seconds)
+		(*nano_seconds) = lan743x_csr_read(adapter, PTP_CLOCK_NS);
+
+	if (sub_nano_seconds)
+		(*sub_nano_seconds) =
+		lan743x_csr_read(adapter, PTP_CLOCK_SUBNS);
+
+	mutex_unlock(&ptp->command_lock);
+}
+
+static void lan743x_ptp_clock_step(struct lan743x_adapter *adapter,
+				   s64 time_step_ns)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+	u32 nano_seconds_step = 0;
+	u64 abs_time_step_ns = 0;
+	u32 unsigned_seconds = 0;
+	u32 nano_seconds = 0;
+	u32 remainder = 0;
+	s32 seconds = 0;
+
+	if (time_step_ns >  15000000000LL) {
+		/* convert to clock set */
+		lan743x_ptp_clock_get(adapter, &unsigned_seconds,
+				      &nano_seconds, NULL);
+		unsigned_seconds += div_u64_rem(time_step_ns, 1000000000LL,
+						&remainder);
+		nano_seconds += remainder;
+		if (nano_seconds >= 1000000000) {
+			unsigned_seconds++;
+			nano_seconds -= 1000000000;
+		}
+		lan743x_ptp_clock_set(adapter, unsigned_seconds,
+				      nano_seconds, 0);
+		return;
+	} else if (time_step_ns < -15000000000LL) {
+		/* convert to clock set */
+		time_step_ns = -time_step_ns;
+
+		lan743x_ptp_clock_get(adapter, &unsigned_seconds,
+				      &nano_seconds, NULL);
+		unsigned_seconds -= div_u64_rem(time_step_ns, 1000000000LL,
+						&remainder);
+		nano_seconds_step = remainder;
+		if (nano_seconds < nano_seconds_step) {
+			unsigned_seconds--;
+			nano_seconds += 1000000000;
+		}
+		nano_seconds -= nano_seconds_step;
+		lan743x_ptp_clock_set(adapter, unsigned_seconds,
+				      nano_seconds, 0);
+		return;
+	}
+
+	/* do clock step */
+	if (time_step_ns >= 0) {
+		abs_time_step_ns = (u64)(time_step_ns);
+		seconds = (s32)div_u64_rem(abs_time_step_ns, 1000000000,
+					   &remainder);
+		nano_seconds = (u32)remainder;
+	} else {
+		abs_time_step_ns = (u64)(-time_step_ns);
+		seconds = -((s32)div_u64_rem(abs_time_step_ns, 1000000000,
+					     &remainder));
+		nano_seconds = (u32)remainder;
+		if (nano_seconds > 0) {
+			/* subtracting nano seconds is not allowed
+			 * convert to subtracting from seconds,
+			 * and adding to nanoseconds
+			 */
+			seconds--;
+			nano_seconds = (1000000000 - nano_seconds);
+		}
+	}
+
+	if (nano_seconds > 0) {
+		/* add 8 ns to cover the likely normal increment */
+		nano_seconds += 8;
+	}
+
+	if (nano_seconds >= 1000000000) {
+		/* carry into seconds */
+		seconds++;
+		nano_seconds -= 1000000000;
+	}
+
+	while (seconds) {
+		mutex_lock(&ptp->command_lock);
+		if (seconds > 0) {
+			u32 adjustment_value = (u32)seconds;
+
+			if (adjustment_value > 0xF)
+				adjustment_value = 0xF;
+			lan743x_csr_write(adapter, PTP_CLOCK_STEP_ADJ,
+					  PTP_CLOCK_STEP_ADJ_DIR_ |
+					  adjustment_value);
+			seconds -= ((s32)adjustment_value);
+		} else {
+			u32 adjustment_value = (u32)(-seconds);
+
+			if (adjustment_value > 0xF)
+				adjustment_value = 0xF;
+			lan743x_csr_write(adapter, PTP_CLOCK_STEP_ADJ,
+					  adjustment_value);
+			seconds += ((s32)adjustment_value);
+		}
+		lan743x_csr_write(adapter, PTP_CMD_CTL,
+				  PTP_CMD_CTL_PTP_CLOCK_STEP_SEC_);
+		lan743x_ptp_wait_till_cmd_done(adapter,
+					       PTP_CMD_CTL_PTP_CLOCK_STEP_SEC_);
+		mutex_unlock(&ptp->command_lock);
+	}
+	if (nano_seconds) {
+		mutex_lock(&ptp->command_lock);
+		lan743x_csr_write(adapter, PTP_CLOCK_STEP_ADJ,
+				  PTP_CLOCK_STEP_ADJ_DIR_ |
+				  (nano_seconds &
+				  PTP_CLOCK_STEP_ADJ_VALUE_MASK_));
+		lan743x_csr_write(adapter, PTP_CMD_CTL,
+				  PTP_CMD_CTL_PTP_CLK_STP_NSEC_);
+		lan743x_ptp_wait_till_cmd_done(adapter,
+					       PTP_CMD_CTL_PTP_CLK_STP_NSEC_);
+		mutex_unlock(&ptp->command_lock);
+	}
+}
+
+void lan743x_ptp_isr(void *context)
+{
+	struct lan743x_adapter *adapter = (struct lan743x_adapter *)context;
+	struct lan743x_ptp *ptp = NULL;
+	int enable_flag = 1;
+	u32 ptp_int_sts = 0;
+
+	ptp = &adapter->ptp;
+
+	lan743x_csr_write(adapter, INT_EN_CLR, INT_BIT_1588_);
+
+	ptp_int_sts = lan743x_csr_read(adapter, PTP_INT_STS);
+	ptp_int_sts &= lan743x_csr_read(adapter, PTP_INT_EN_SET);
+
+	if (ptp_int_sts & PTP_INT_BIT_TX_TS_) {
+		ptp_schedule_worker(ptp->ptp_clock, 0);
+		enable_flag = 0;/* tasklet will re-enable later */
+	}
+	if (ptp_int_sts & PTP_INT_BIT_TX_SWTS_ERR_) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "PTP TX Software Timestamp Error\n");
+		/* clear int status bit */
+		lan743x_csr_write(adapter, PTP_INT_STS,
+				  PTP_INT_BIT_TX_SWTS_ERR_);
+	}
+	if (ptp_int_sts & PTP_INT_BIT_TIMER_B_) {
+		/* clear int status bit */
+		lan743x_csr_write(adapter, PTP_INT_STS,
+				  PTP_INT_BIT_TIMER_B_);
+	}
+	if (ptp_int_sts & PTP_INT_BIT_TIMER_A_) {
+		/* clear int status bit */
+		lan743x_csr_write(adapter, PTP_INT_STS,
+				  PTP_INT_BIT_TIMER_A_);
+	}
+
+	if (enable_flag) {
+		/* re-enable isr */
+		lan743x_csr_write(adapter, INT_EN_SET, INT_BIT_1588_);
+	}
+}
+
+static void lan743x_ptp_tx_ts_enqueue_skb(struct lan743x_adapter *adapter,
+					  struct sk_buff *skb, bool ignore_sync)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	spin_lock_bh(&ptp->tx_ts_lock);
+	if (ptp->tx_ts_skb_queue_size < LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS) {
+		ptp->tx_ts_skb_queue[ptp->tx_ts_skb_queue_size] = skb;
+		if (ignore_sync)
+			ptp->tx_ts_ignore_sync_queue |=
+				BIT(ptp->tx_ts_skb_queue_size);
+		ptp->tx_ts_skb_queue_size++;
+	} else {
+		/* this should never happen, so long as the tx channel
+		 * calls and honors the result from
+		 * lan743x_ptp_request_tx_timestamp
+		 */
+		netif_err(adapter, drv, adapter->netdev,
+			  "tx ts skb queue overflow\n");
+		dev_kfree_skb(skb);
+	}
+	spin_unlock_bh(&ptp->tx_ts_lock);
+}
+
+static void lan743x_ptp_sync_to_system_clock(struct lan743x_adapter *adapter)
+{
+	struct timespec64 ts;
+
+	memset(&ts, 0, sizeof(ts));
+	timekeeping_clocktai64(&ts);
+
+	lan743x_ptp_clock_set(adapter, ts.tv_sec, ts.tv_nsec, 0);
+}
+
+void lan743x_ptp_update_latency(struct lan743x_adapter *adapter,
+				u32 link_speed)
+{
+	switch (link_speed) {
+	case 10:
+		lan743x_csr_write(adapter, PTP_LATENCY,
+				  PTP_LATENCY_TX_SET_(0) |
+				  PTP_LATENCY_RX_SET_(0));
+		break;
+	case 100:
+		lan743x_csr_write(adapter, PTP_LATENCY,
+				  PTP_LATENCY_TX_SET_(181) |
+				  PTP_LATENCY_RX_SET_(594));
+		break;
+	case 1000:
+		lan743x_csr_write(adapter, PTP_LATENCY,
+				  PTP_LATENCY_TX_SET_(30) |
+				  PTP_LATENCY_RX_SET_(525));
+		break;
+	}
+}
+
+int lan743x_ptp_init(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	mutex_init(&ptp->command_lock);
+	spin_lock_init(&ptp->tx_ts_lock);
+	ptp->used_event_ch = 0;
+	ptp->perout_event_ch = -1;
+	ptp->perout_gpio_bit = -1;
+	return 0;
+}
+
+int lan743x_ptp_open(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+	int ret = -ENODEV;
+	u32 temp;
+
+	lan743x_ptp_reset(adapter);
+	lan743x_ptp_sync_to_system_clock(adapter);
+	temp = lan743x_csr_read(adapter, PTP_TX_MOD2);
+	temp |= PTP_TX_MOD2_TX_PTP_CLR_UDPV4_CHKSUM_;
+	lan743x_csr_write(adapter, PTP_TX_MOD2, temp);
+	lan743x_ptp_enable(adapter);
+	lan743x_csr_write(adapter, INT_EN_SET, INT_BIT_1588_);
+	lan743x_csr_write(adapter, PTP_INT_EN_SET,
+			  PTP_INT_BIT_TX_SWTS_ERR_ | PTP_INT_BIT_TX_TS_);
+	ptp->flags |= PTP_FLAG_ISR_ENABLED;
+
+	if (!IS_ENABLED(CONFIG_PTP_1588_CLOCK))
+		return 0;
+
+	snprintf(ptp->pin_config[0].name, 32, "lan743x_ptp_pin_0");
+	ptp->pin_config[0].index = 0;
+	ptp->pin_config[0].func = PTP_PF_PEROUT;
+	ptp->pin_config[0].chan = 0;
+
+	ptp->ptp_clock_info.owner = THIS_MODULE;
+	snprintf(ptp->ptp_clock_info.name, 16, "%pm",
+		 adapter->netdev->dev_addr);
+	ptp->ptp_clock_info.max_adj = LAN743X_PTP_MAX_FREQ_ADJ_IN_PPB;
+	ptp->ptp_clock_info.n_alarm = 0;
+	ptp->ptp_clock_info.n_ext_ts = 0;
+	ptp->ptp_clock_info.n_per_out = 1;
+	ptp->ptp_clock_info.n_pins = 0;
+	ptp->ptp_clock_info.pps = 0;
+	ptp->ptp_clock_info.pin_config = NULL;
+	ptp->ptp_clock_info.adjfine = lan743x_ptpci_adjfine;
+	ptp->ptp_clock_info.adjfreq = lan743x_ptpci_adjfreq;
+	ptp->ptp_clock_info.adjtime = lan743x_ptpci_adjtime;
+	ptp->ptp_clock_info.gettime64 = lan743x_ptpci_gettime64;
+	ptp->ptp_clock_info.getcrosststamp = NULL;
+	ptp->ptp_clock_info.settime64 = lan743x_ptpci_settime64;
+	ptp->ptp_clock_info.enable = lan743x_ptpci_enable;
+	ptp->ptp_clock_info.do_aux_work = lan743x_ptpci_do_aux_work;
+	ptp->ptp_clock_info.verify = NULL;
+
+	ptp->ptp_clock = ptp_clock_register(&ptp->ptp_clock_info,
+					    &adapter->pdev->dev);
+
+	if (IS_ERR(ptp->ptp_clock)) {
+		netif_err(adapter, ifup, adapter->netdev,
+			  "ptp_clock_register failed\n");
+		goto done;
+	}
+	ptp->flags |= PTP_FLAG_PTP_CLOCK_REGISTERED;
+	netif_info(adapter, ifup, adapter->netdev,
+		   "successfully registered ptp clock\n");
+
+	return 0;
+done:
+	lan743x_ptp_close(adapter);
+	return ret;
+}
+
+void lan743x_ptp_close(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+	int index;
+
+	if (IS_ENABLED(CONFIG_PTP_1588_CLOCK) &&
+	    ptp->flags & PTP_FLAG_PTP_CLOCK_REGISTERED) {
+		ptp_clock_unregister(ptp->ptp_clock);
+		ptp->ptp_clock = NULL;
+		ptp->flags &= ~PTP_FLAG_PTP_CLOCK_REGISTERED;
+		netif_info(adapter, drv, adapter->netdev,
+			   "ptp clock unregister\n");
+	}
+
+	if (ptp->flags & PTP_FLAG_ISR_ENABLED) {
+		lan743x_csr_write(adapter, PTP_INT_EN_CLR,
+				  PTP_INT_BIT_TX_SWTS_ERR_ |
+				  PTP_INT_BIT_TX_TS_);
+		lan743x_csr_write(adapter, INT_EN_CLR, INT_BIT_1588_);
+		ptp->flags &= ~PTP_FLAG_ISR_ENABLED;
+	}
+
+	/* clean up pending timestamp requests */
+	lan743x_ptp_tx_ts_complete(adapter);
+	spin_lock_bh(&ptp->tx_ts_lock);
+	for (index = 0;
+		index < LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS;
+		index++) {
+		struct sk_buff *skb = ptp->tx_ts_skb_queue[index];
+
+		if (skb)
+			dev_kfree_skb(skb);
+		ptp->tx_ts_skb_queue[index] = NULL;
+		ptp->tx_ts_seconds_queue[index] = 0;
+		ptp->tx_ts_nseconds_queue[index] = 0;
+	}
+	ptp->tx_ts_skb_queue_size = 0;
+	ptp->tx_ts_queue_size = 0;
+	ptp->pending_tx_timestamps = 0;
+	spin_unlock_bh(&ptp->tx_ts_lock);
+
+	lan743x_ptp_disable(adapter);
+}
+
+void lan743x_ptp_set_sync_ts_insert(struct lan743x_adapter *adapter,
+				    bool ts_insert_enable)
+{
+	u32 ptp_tx_mod = lan743x_csr_read(adapter, PTP_TX_MOD);
+
+	if (ts_insert_enable)
+		ptp_tx_mod |= PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_;
+	else
+		ptp_tx_mod &= ~PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_;
+
+	lan743x_csr_write(adapter, PTP_TX_MOD, ptp_tx_mod);
+}
+
+static bool lan743x_ptp_is_enabled(struct lan743x_adapter *adapter)
+{
+	if (lan743x_csr_read(adapter, PTP_CMD_CTL) & PTP_CMD_CTL_PTP_ENABLE_)
+		return true;
+	return false;
+}
+
+static void lan743x_ptp_enable(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	mutex_lock(&ptp->command_lock);
+
+	if (lan743x_ptp_is_enabled(adapter)) {
+		netif_warn(adapter, drv, adapter->netdev,
+			   "PTP already enabled\n");
+		goto done;
+	}
+	lan743x_csr_write(adapter, PTP_CMD_CTL, PTP_CMD_CTL_PTP_ENABLE_);
+done:
+	mutex_unlock(&ptp->command_lock);
+}
+
+static void lan743x_ptp_disable(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	mutex_lock(&ptp->command_lock);
+	if (!lan743x_ptp_is_enabled(adapter)) {
+		netif_warn(adapter, drv, adapter->netdev,
+			   "PTP already disabled\n");
+		goto done;
+	}
+	lan743x_csr_write(adapter, PTP_CMD_CTL, PTP_CMD_CTL_PTP_DISABLE_);
+	lan743x_ptp_wait_till_cmd_done(adapter, PTP_CMD_CTL_PTP_ENABLE_);
+done:
+	mutex_unlock(&ptp->command_lock);
+}
+
+static void lan743x_ptp_reset(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	mutex_lock(&ptp->command_lock);
+
+	if (lan743x_ptp_is_enabled(adapter)) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "Attempting reset while enabled\n");
+		goto done;
+	}
+
+	lan743x_csr_write(adapter, PTP_CMD_CTL, PTP_CMD_CTL_PTP_RESET_);
+	lan743x_ptp_wait_till_cmd_done(adapter, PTP_CMD_CTL_PTP_RESET_);
+done:
+	mutex_unlock(&ptp->command_lock);
+}
+
+static void lan743x_ptp_clock_set(struct lan743x_adapter *adapter,
+				  u32 seconds, u32 nano_seconds,
+				  u32 sub_nano_seconds)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	mutex_lock(&ptp->command_lock);
+
+	lan743x_csr_write(adapter, PTP_CLOCK_SEC, seconds);
+	lan743x_csr_write(adapter, PTP_CLOCK_NS, nano_seconds);
+	lan743x_csr_write(adapter, PTP_CLOCK_SUBNS, sub_nano_seconds);
+
+	lan743x_csr_write(adapter, PTP_CMD_CTL, PTP_CMD_CTL_PTP_CLOCK_LOAD_);
+	lan743x_ptp_wait_till_cmd_done(adapter, PTP_CMD_CTL_PTP_CLOCK_LOAD_);
+	mutex_unlock(&ptp->command_lock);
+}
+
+bool lan743x_ptp_request_tx_timestamp(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+	bool result = false;
+
+	spin_lock_bh(&ptp->tx_ts_lock);
+	if (ptp->pending_tx_timestamps < LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS) {
+		/* request granted */
+		ptp->pending_tx_timestamps++;
+		result = true;
+	}
+	spin_unlock_bh(&ptp->tx_ts_lock);
+	return result;
+}
+
+void lan743x_ptp_unrequest_tx_timestamp(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	spin_lock_bh(&ptp->tx_ts_lock);
+	if (ptp->pending_tx_timestamps > 0)
+		ptp->pending_tx_timestamps--;
+	else
+		netif_err(adapter, drv, adapter->netdev,
+			  "unrequest failed, pending_tx_timestamps==0\n");
+	spin_unlock_bh(&ptp->tx_ts_lock);
+}
+
+void lan743x_ptp_tx_timestamp_skb(struct lan743x_adapter *adapter,
+				  struct sk_buff *skb, bool ignore_sync)
+{
+	lan743x_ptp_tx_ts_enqueue_skb(adapter, skb, ignore_sync);
+
+	lan743x_ptp_tx_ts_complete(adapter);
+}
+
+int lan743x_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	struct hwtstamp_config config;
+	int ret = 0;
+	int index;
+
+	if (!ifr) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "SIOCSHWTSTAMP, ifr == NULL\n");
+		return -EINVAL;
+	}
+
+	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
+		return -EFAULT;
+
+	if (config.flags) {
+		netif_warn(adapter, drv, adapter->netdev,
+			   "ignoring hwtstamp_config.flags == 0x%08X, expected 0\n",
+			   config.flags);
+	}
+
+	switch (config.tx_type) {
+	case HWTSTAMP_TX_OFF:
+		for (index = 0; index < LAN743X_MAX_TX_CHANNELS;
+			index++)
+			lan743x_tx_set_timestamping_mode(&adapter->tx[index],
+							 false, false);
+		lan743x_ptp_set_sync_ts_insert(adapter, false);
+		break;
+	case HWTSTAMP_TX_ON:
+		for (index = 0; index < LAN743X_MAX_TX_CHANNELS;
+			index++)
+			lan743x_tx_set_timestamping_mode(&adapter->tx[index],
+							 true, false);
+		lan743x_ptp_set_sync_ts_insert(adapter, false);
+		break;
+	case HWTSTAMP_TX_ONESTEP_SYNC:
+		for (index = 0; index < LAN743X_MAX_TX_CHANNELS;
+			index++)
+			lan743x_tx_set_timestamping_mode(&adapter->tx[index],
+							 true, true);
+
+		lan743x_ptp_set_sync_ts_insert(adapter, true);
+		break;
+	default:
+		netif_warn(adapter, drv, adapter->netdev,
+			   "  tx_type = %d, UNKNOWN\n", config.tx_type);
+		ret = -EINVAL;
+		break;
+	}
+
+	if (!ret)
+		return copy_to_user(ifr->ifr_data, &config,
+			sizeof(config)) ? -EFAULT : 0;
+	return ret;
+}
diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.h b/drivers/net/ethernet/microchip/lan743x_ptp.h
new file mode 100644
index 000000000000..5fc1b3cd5e33
--- /dev/null
+++ b/drivers/net/ethernet/microchip/lan743x_ptp.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (C) 2018 Microchip Technology Inc. */
+
+#ifndef _LAN743X_PTP_H
+#define _LAN743X_PTP_H
+
+#include "linux/ptp_clock_kernel.h"
+#include "linux/netdevice.h"
+
+struct lan743x_adapter;
+
+/* GPIO */
+struct lan743x_gpio {
+	/* gpio_lock: used to prevent concurrent access to gpio settings */
+	spinlock_t gpio_lock;
+
+	int used_bits;
+	int output_bits;
+	int ptp_bits;
+	u32 gpio_cfg0;
+	u32 gpio_cfg1;
+	u32 gpio_cfg2;
+	u32 gpio_cfg3;
+};
+
+int lan743x_gpio_init(struct lan743x_adapter *adapter);
+
+void lan743x_ptp_isr(void *context);
+bool lan743x_ptp_request_tx_timestamp(struct lan743x_adapter *adapter);
+void lan743x_ptp_unrequest_tx_timestamp(struct lan743x_adapter *adapter);
+void lan743x_ptp_tx_timestamp_skb(struct lan743x_adapter *adapter,
+				  struct sk_buff *skb, bool ignore_sync);
+int lan743x_ptp_init(struct lan743x_adapter *adapter);
+int lan743x_ptp_open(struct lan743x_adapter *adapter);
+void lan743x_ptp_close(struct lan743x_adapter *adapter);
+void lan743x_ptp_update_latency(struct lan743x_adapter *adapter,
+				u32 link_speed);
+
+int lan743x_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd);
+
+#define LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS (4)
+
+#define PTP_FLAG_PTP_CLOCK_REGISTERED	BIT(1)
+#define PTP_FLAG_ISR_ENABLED			BIT(2)
+
+struct lan743x_ptp {
+	int flags;
+
+	/* command_lock: used to prevent concurrent ptp commands */
+	struct mutex	command_lock;
+
+	struct ptp_clock *ptp_clock;
+	struct ptp_clock_info ptp_clock_info;
+	struct ptp_pin_desc pin_config[1];
+
+#define LAN743X_PTP_NUMBER_OF_EVENT_CHANNELS (2)
+	unsigned long used_event_ch;
+
+	int perout_event_ch;
+	int perout_gpio_bit;
+
+	/* tx_ts_lock: used to prevent concurrent access to timestamp arrays */
+	spinlock_t	tx_ts_lock;
+	int pending_tx_timestamps;
+	struct sk_buff *tx_ts_skb_queue[LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS];
+	unsigned int	tx_ts_ignore_sync_queue;
+	int tx_ts_skb_queue_size;
+	u32 tx_ts_seconds_queue[LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS];
+	u32 tx_ts_nseconds_queue[LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS];
+	u32 tx_ts_header_queue[LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS];
+	int tx_ts_queue_size;
+};
+
+#endif /* _LAN743X_PTP_H */
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 776a8a9be8e3..1a4f2bb48ead 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -148,12 +148,191 @@ static inline int ocelot_vlant_wait_for_completion(struct ocelot *ocelot)
 	return 0;
 }
 
+static int ocelot_vlant_set_mask(struct ocelot *ocelot, u16 vid, u32 mask)
+{
+	/* Select the VID to configure */
+	ocelot_write(ocelot, ANA_TABLES_VLANTIDX_V_INDEX(vid),
+		     ANA_TABLES_VLANTIDX);
+	/* Set the vlan port members mask and issue a write command */
+	ocelot_write(ocelot, ANA_TABLES_VLANACCESS_VLAN_PORT_MASK(mask) |
+			     ANA_TABLES_VLANACCESS_CMD_WRITE,
+		     ANA_TABLES_VLANACCESS);
+
+	return ocelot_vlant_wait_for_completion(ocelot);
+}
+
+static void ocelot_vlan_mode(struct ocelot_port *port,
+			     netdev_features_t features)
+{
+	struct ocelot *ocelot = port->ocelot;
+	u8 p = port->chip_port;
+	u32 val;
+
+	/* Filtering */
+	val = ocelot_read(ocelot, ANA_VLANMASK);
+	if (features & NETIF_F_HW_VLAN_CTAG_FILTER)
+		val |= BIT(p);
+	else
+		val &= ~BIT(p);
+	ocelot_write(ocelot, val, ANA_VLANMASK);
+}
+
+static void ocelot_vlan_port_apply(struct ocelot *ocelot,
+				   struct ocelot_port *port)
+{
+	u32 val;
+
+	/* Ingress clasification (ANA_PORT_VLAN_CFG) */
+	/* Default vlan to clasify for untagged frames (may be zero) */
+	val = ANA_PORT_VLAN_CFG_VLAN_VID(port->pvid);
+	if (port->vlan_aware)
+		val |= ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
+		       ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1);
+
+	ocelot_rmw_gix(ocelot, val,
+		       ANA_PORT_VLAN_CFG_VLAN_VID_M |
+		       ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
+		       ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M,
+		       ANA_PORT_VLAN_CFG, port->chip_port);
+
+	/* Drop frames with multicast source address */
+	val = ANA_PORT_DROP_CFG_DROP_MC_SMAC_ENA;
+	if (port->vlan_aware && !port->vid)
+		/* If port is vlan-aware and tagged, drop untagged and priority
+		 * tagged frames.
+		 */
+		val |= ANA_PORT_DROP_CFG_DROP_UNTAGGED_ENA |
+		       ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA |
+		       ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA;
+	ocelot_write_gix(ocelot, val, ANA_PORT_DROP_CFG, port->chip_port);
+
+	/* Egress configuration (REW_TAG_CFG): VLAN tag type to 8021Q. */
+	val = REW_TAG_CFG_TAG_TPID_CFG(0);
+
+	if (port->vlan_aware) {
+		if (port->vid)
+			/* Tag all frames except when VID == DEFAULT_VLAN */
+			val |= REW_TAG_CFG_TAG_CFG(1);
+		else
+			/* Tag all frames */
+			val |= REW_TAG_CFG_TAG_CFG(3);
+	}
+	ocelot_rmw_gix(ocelot, val,
+		       REW_TAG_CFG_TAG_TPID_CFG_M |
+		       REW_TAG_CFG_TAG_CFG_M,
+		       REW_TAG_CFG, port->chip_port);
+
+	/* Set default VLAN and tag type to 8021Q. */
+	val = REW_PORT_VLAN_CFG_PORT_TPID(ETH_P_8021Q) |
+	      REW_PORT_VLAN_CFG_PORT_VID(port->vid);
+	ocelot_rmw_gix(ocelot, val,
+		       REW_PORT_VLAN_CFG_PORT_TPID_M |
+		       REW_PORT_VLAN_CFG_PORT_VID_M,
+		       REW_PORT_VLAN_CFG, port->chip_port);
+}
+
+static int ocelot_vlan_vid_add(struct net_device *dev, u16 vid, bool pvid,
+			       bool untagged)
+{
+	struct ocelot_port *port = netdev_priv(dev);
+	struct ocelot *ocelot = port->ocelot;
+	int ret;
+
+	/* Add the port MAC address to with the right VLAN information */
+	ocelot_mact_learn(ocelot, PGID_CPU, dev->dev_addr, vid,
+			  ENTRYTYPE_LOCKED);
+
+	/* Make the port a member of the VLAN */
+	ocelot->vlan_mask[vid] |= BIT(port->chip_port);
+	ret = ocelot_vlant_set_mask(ocelot, vid, ocelot->vlan_mask[vid]);
+	if (ret)
+		return ret;
+
+	/* Default ingress vlan classification */
+	if (pvid)
+		port->pvid = vid;
+
+	/* Untagged egress vlan clasification */
+	if (untagged)
+		port->vid = vid;
+
+	ocelot_vlan_port_apply(ocelot, port);
+
+	return 0;
+}
+
+static int ocelot_vlan_vid_del(struct net_device *dev, u16 vid)
+{
+	struct ocelot_port *port = netdev_priv(dev);
+	struct ocelot *ocelot = port->ocelot;
+	int ret;
+
+	/* 8021q removes VID 0 on module unload for all interfaces
+	 * with VLAN filtering feature. We need to keep it to receive
+	 * untagged traffic.
+	 */
+	if (vid == 0)
+		return 0;
+
+	/* Del the port MAC address to with the right VLAN information */
+	ocelot_mact_forget(ocelot, dev->dev_addr, vid);
+
+	/* Stop the port from being a member of the vlan */
+	ocelot->vlan_mask[vid] &= ~BIT(port->chip_port);
+	ret = ocelot_vlant_set_mask(ocelot, vid, ocelot->vlan_mask[vid]);
+	if (ret)
+		return ret;
+
+	/* Ingress */
+	if (port->pvid == vid)
+		port->pvid = 0;
+
+	/* Egress */
+	if (port->vid == vid)
+		port->vid = 0;
+
+	ocelot_vlan_port_apply(ocelot, port);
+
+	return 0;
+}
+
 static void ocelot_vlan_init(struct ocelot *ocelot)
 {
+	u16 port, vid;
+
 	/* Clear VLAN table, by default all ports are members of all VLANs */
 	ocelot_write(ocelot, ANA_TABLES_VLANACCESS_CMD_INIT,
 		     ANA_TABLES_VLANACCESS);
 	ocelot_vlant_wait_for_completion(ocelot);
+
+	/* Configure the port VLAN memberships */
+	for (vid = 1; vid < VLAN_N_VID; vid++) {
+		ocelot->vlan_mask[vid] = 0;
+		ocelot_vlant_set_mask(ocelot, vid, ocelot->vlan_mask[vid]);
+	}
+
+	/* Because VLAN filtering is enabled, we need VID 0 to get untagged
+	 * traffic.  It is added automatically if 8021q module is loaded, but
+	 * we can't rely on it since module may be not loaded.
+	 */
+	ocelot->vlan_mask[0] = GENMASK(ocelot->num_phys_ports - 1, 0);
+	ocelot_vlant_set_mask(ocelot, 0, ocelot->vlan_mask[0]);
+
+	/* Configure the CPU port to be VLAN aware */
+	ocelot_write_gix(ocelot, ANA_PORT_VLAN_CFG_VLAN_VID(0) |
+				 ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
+				 ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1),
+			 ANA_PORT_VLAN_CFG, ocelot->num_phys_ports);
+
+	/* Set vlan ingress filter mask to all ports but the CPU port by
+	 * default.
+	 */
+	ocelot_write(ocelot, GENMASK(9, 0), ANA_VLANMASK);
+
+	for (port = 0; port < ocelot->num_phys_ports; port++) {
+		ocelot_write_gix(ocelot, 0, REW_PORT_VLAN_CFG, port);
+		ocelot_write_gix(ocelot, 0, REW_TAG_CFG, port);
+	}
 }
 
 /* Watermark encode
@@ -539,6 +718,20 @@ static int ocelot_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	struct ocelot_port *port = netdev_priv(dev);
 	struct ocelot *ocelot = port->ocelot;
 
+	if (!vid) {
+		if (!port->vlan_aware)
+			/* If the bridge is not VLAN aware and no VID was
+			 * provided, set it to pvid to ensure the MAC entry
+			 * matches incoming untagged packets
+			 */
+			vid = port->pvid;
+		else
+			/* If the bridge is VLAN aware a VID must be provided as
+			 * otherwise the learnt entry wouldn't match any frame.
+			 */
+			return -EINVAL;
+	}
+
 	return ocelot_mact_learn(ocelot, port->chip_port, addr, vid,
 				 ENTRYTYPE_NORMAL);
 }
@@ -690,6 +883,30 @@ end:
 	return ret;
 }
 
+static int ocelot_vlan_rx_add_vid(struct net_device *dev, __be16 proto,
+				  u16 vid)
+{
+	return ocelot_vlan_vid_add(dev, vid, false, true);
+}
+
+static int ocelot_vlan_rx_kill_vid(struct net_device *dev, __be16 proto,
+				   u16 vid)
+{
+	return ocelot_vlan_vid_del(dev, vid);
+}
+
+static int ocelot_set_features(struct net_device *dev,
+			       netdev_features_t features)
+{
+	struct ocelot_port *port = netdev_priv(dev);
+	netdev_features_t changed = dev->features ^ features;
+
+	if (changed & NETIF_F_HW_VLAN_CTAG_FILTER)
+		ocelot_vlan_mode(port, features);
+
+	return 0;
+}
+
 static const struct net_device_ops ocelot_port_netdev_ops = {
 	.ndo_open			= ocelot_port_open,
 	.ndo_stop			= ocelot_port_stop,
@@ -701,6 +918,9 @@ static const struct net_device_ops ocelot_port_netdev_ops = {
 	.ndo_fdb_add			= ocelot_fdb_add,
 	.ndo_fdb_del			= ocelot_fdb_del,
 	.ndo_fdb_dump			= ocelot_fdb_dump,
+	.ndo_vlan_rx_add_vid		= ocelot_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid		= ocelot_vlan_rx_kill_vid,
+	.ndo_set_features		= ocelot_set_features,
 };
 
 static void ocelot_get_strings(struct net_device *netdev, u32 sset, u8 *data)
@@ -780,6 +1000,8 @@ static const struct ethtool_ops ocelot_ethtool_ops = {
 	.get_strings		= ocelot_get_strings,
 	.get_ethtool_stats	= ocelot_get_ethtool_stats,
 	.get_sset_count		= ocelot_get_sset_count,
+	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
+	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 };
 
 static int ocelot_port_attr_get(struct net_device *dev,
@@ -914,6 +1136,10 @@ static int ocelot_port_attr_set(struct net_device *dev,
 	case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME:
 		ocelot_port_attr_ageing_set(ocelot_port, attr->u.ageing_time);
 		break;
+	case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING:
+		ocelot_port->vlan_aware = attr->u.vlan_filtering;
+		ocelot_vlan_port_apply(ocelot_port->ocelot, ocelot_port);
+		break;
 	case SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED:
 		ocelot_port_attr_mc_set(ocelot_port, !attr->u.mc_disabled);
 		break;
@@ -925,6 +1151,40 @@ static int ocelot_port_attr_set(struct net_device *dev,
 	return err;
 }
 
+static int ocelot_port_obj_add_vlan(struct net_device *dev,
+				    const struct switchdev_obj_port_vlan *vlan,
+				    struct switchdev_trans *trans)
+{
+	int ret;
+	u16 vid;
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
+		ret = ocelot_vlan_vid_add(dev, vid,
+					  vlan->flags & BRIDGE_VLAN_INFO_PVID,
+					  vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int ocelot_port_vlan_del_vlan(struct net_device *dev,
+				     const struct switchdev_obj_port_vlan *vlan)
+{
+	int ret;
+	u16 vid;
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
+		ret = ocelot_vlan_vid_del(dev, vid);
+
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static struct ocelot_multicast *ocelot_multicast_get(struct ocelot *ocelot,
 						     const unsigned char *addr,
 						     u16 vid)
@@ -951,7 +1211,7 @@ static int ocelot_port_obj_add_mdb(struct net_device *dev,
 	bool new = false;
 
 	if (!vid)
-		vid = 1;
+		vid = port->pvid;
 
 	mc = ocelot_multicast_get(ocelot, mdb->addr, vid);
 	if (!mc) {
@@ -992,7 +1252,7 @@ static int ocelot_port_obj_del_mdb(struct net_device *dev,
 	u16 vid = mdb->vid;
 
 	if (!vid)
-		vid = 1;
+		vid = port->pvid;
 
 	mc = ocelot_multicast_get(ocelot, mdb->addr, vid);
 	if (!mc)
@@ -1024,6 +1284,11 @@ static int ocelot_port_obj_add(struct net_device *dev,
 	int ret = 0;
 
 	switch (obj->id) {
+	case SWITCHDEV_OBJ_ID_PORT_VLAN:
+		ret = ocelot_port_obj_add_vlan(dev,
+					       SWITCHDEV_OBJ_PORT_VLAN(obj),
+					       trans);
+		break;
 	case SWITCHDEV_OBJ_ID_PORT_MDB:
 		ret = ocelot_port_obj_add_mdb(dev, SWITCHDEV_OBJ_PORT_MDB(obj),
 					      trans);
@@ -1041,6 +1306,10 @@ static int ocelot_port_obj_del(struct net_device *dev,
 	int ret = 0;
 
 	switch (obj->id) {
+	case SWITCHDEV_OBJ_ID_PORT_VLAN:
+		ret = ocelot_port_vlan_del_vlan(dev,
+						SWITCHDEV_OBJ_PORT_VLAN(obj));
+		break;
 	case SWITCHDEV_OBJ_ID_PORT_MDB:
 		ret = ocelot_port_obj_del_mdb(dev, SWITCHDEV_OBJ_PORT_MDB(obj));
 		break;
@@ -1086,6 +1355,142 @@ static void ocelot_port_bridge_leave(struct ocelot_port *ocelot_port,
 
 	if (!ocelot->bridge_mask)
 		ocelot->hw_bridge_dev = NULL;
+
+	/* Clear bridge vlan settings before calling ocelot_vlan_port_apply */
+	ocelot_port->vlan_aware = 0;
+	ocelot_port->pvid = 0;
+	ocelot_port->vid = 0;
+}
+
+static void ocelot_set_aggr_pgids(struct ocelot *ocelot)
+{
+	int i, port, lag;
+
+	/* Reset destination and aggregation PGIDS */
+	for (port = 0; port < ocelot->num_phys_ports; port++)
+		ocelot_write_rix(ocelot, BIT(port), ANA_PGID_PGID, port);
+
+	for (i = PGID_AGGR; i < PGID_SRC; i++)
+		ocelot_write_rix(ocelot, GENMASK(ocelot->num_phys_ports - 1, 0),
+				 ANA_PGID_PGID, i);
+
+	/* Now, set PGIDs for each LAG */
+	for (lag = 0; lag < ocelot->num_phys_ports; lag++) {
+		unsigned long bond_mask;
+		int aggr_count = 0;
+		u8 aggr_idx[16];
+
+		bond_mask = ocelot->lags[lag];
+		if (!bond_mask)
+			continue;
+
+		for_each_set_bit(port, &bond_mask, ocelot->num_phys_ports) {
+			// Destination mask
+			ocelot_write_rix(ocelot, bond_mask,
+					 ANA_PGID_PGID, port);
+			aggr_idx[aggr_count] = port;
+			aggr_count++;
+		}
+
+		for (i = PGID_AGGR; i < PGID_SRC; i++) {
+			u32 ac;
+
+			ac = ocelot_read_rix(ocelot, ANA_PGID_PGID, i);
+			ac &= ~bond_mask;
+			ac |= BIT(aggr_idx[i % aggr_count]);
+			ocelot_write_rix(ocelot, ac, ANA_PGID_PGID, i);
+		}
+	}
+}
+
+static void ocelot_setup_lag(struct ocelot *ocelot, int lag)
+{
+	unsigned long bond_mask = ocelot->lags[lag];
+	unsigned int p;
+
+	for_each_set_bit(p, &bond_mask, ocelot->num_phys_ports) {
+		u32 port_cfg = ocelot_read_gix(ocelot, ANA_PORT_PORT_CFG, p);
+
+		port_cfg &= ~ANA_PORT_PORT_CFG_PORTID_VAL_M;
+
+		/* Use lag port as logical port for port i */
+		ocelot_write_gix(ocelot, port_cfg |
+				 ANA_PORT_PORT_CFG_PORTID_VAL(lag),
+				 ANA_PORT_PORT_CFG, p);
+	}
+}
+
+static int ocelot_port_lag_join(struct ocelot_port *ocelot_port,
+				struct net_device *bond)
+{
+	struct ocelot *ocelot = ocelot_port->ocelot;
+	int p = ocelot_port->chip_port;
+	int lag, lp;
+	struct net_device *ndev;
+	u32 bond_mask = 0;
+
+	rcu_read_lock();
+	for_each_netdev_in_bond_rcu(bond, ndev) {
+		struct ocelot_port *port = netdev_priv(ndev);
+
+		bond_mask |= BIT(port->chip_port);
+	}
+	rcu_read_unlock();
+
+	lp = __ffs(bond_mask);
+
+	/* If the new port is the lowest one, use it as the logical port from
+	 * now on
+	 */
+	if (p == lp) {
+		lag = p;
+		ocelot->lags[p] = bond_mask;
+		bond_mask &= ~BIT(p);
+		if (bond_mask) {
+			lp = __ffs(bond_mask);
+			ocelot->lags[lp] = 0;
+		}
+	} else {
+		lag = lp;
+		ocelot->lags[lp] |= BIT(p);
+	}
+
+	ocelot_setup_lag(ocelot, lag);
+	ocelot_set_aggr_pgids(ocelot);
+
+	return 0;
+}
+
+static void ocelot_port_lag_leave(struct ocelot_port *ocelot_port,
+				  struct net_device *bond)
+{
+	struct ocelot *ocelot = ocelot_port->ocelot;
+	int p = ocelot_port->chip_port;
+	u32 port_cfg;
+	int i;
+
+	/* Remove port from any lag */
+	for (i = 0; i < ocelot->num_phys_ports; i++)
+		ocelot->lags[i] &= ~BIT(ocelot_port->chip_port);
+
+	/* if it was the logical port of the lag, move the lag config to the
+	 * next port
+	 */
+	if (ocelot->lags[p]) {
+		int n = __ffs(ocelot->lags[p]);
+
+		ocelot->lags[n] = ocelot->lags[p];
+		ocelot->lags[p] = 0;
+
+		ocelot_setup_lag(ocelot, n);
+	}
+
+	port_cfg = ocelot_read_gix(ocelot, ANA_PORT_PORT_CFG, p);
+	port_cfg &= ~ANA_PORT_PORT_CFG_PORTID_VAL_M;
+	ocelot_write_gix(ocelot, port_cfg | ANA_PORT_PORT_CFG_PORTID_VAL(p),
+			 ANA_PORT_PORT_CFG, p);
+
+	ocelot_set_aggr_pgids(ocelot);
 }
 
 /* Checks if the net_device instance given to us originate from our driver. */
@@ -1113,6 +1518,17 @@ static int ocelot_netdevice_port_event(struct net_device *dev,
 			else
 				ocelot_port_bridge_leave(ocelot_port,
 							 info->upper_dev);
+
+			ocelot_vlan_port_apply(ocelot_port->ocelot,
+					       ocelot_port);
+		}
+		if (netif_is_lag_master(info->upper_dev)) {
+			if (info->linking)
+				err = ocelot_port_lag_join(ocelot_port,
+							   info->upper_dev);
+			else
+				ocelot_port_lag_leave(ocelot_port,
+						      info->upper_dev);
 		}
 		break;
 	default:
@@ -1129,6 +1545,20 @@ static int ocelot_netdevice_event(struct notifier_block *unused,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	int ret = 0;
 
+	if (event == NETDEV_PRECHANGEUPPER &&
+	    netif_is_lag_master(info->upper_dev)) {
+		struct netdev_lag_upper_info *lag_upper_info = info->upper_info;
+		struct netlink_ext_ack *extack;
+
+		if (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) {
+			extack = netdev_notifier_info_to_extack(&info->info);
+			NL_SET_ERR_MSG_MOD(extack, "LAG device using unsupported Tx type");
+
+			ret = -EINVAL;
+			goto notify;
+		}
+	}
+
 	if (netif_is_lag_master(dev)) {
 		struct net_device *slave;
 		struct list_head *iter;
@@ -1176,6 +1606,9 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port,
 	dev->ethtool_ops = &ocelot_ethtool_ops;
 	dev->switchdev_ops = &ocelot_port_switchdev_ops;
 
+	dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+	dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+
 	memcpy(dev->dev_addr, ocelot->base_mac, ETH_ALEN);
 	dev->dev_addr[ETH_ALEN - 1] += port;
 	ocelot_mact_learn(ocelot, PGID_CPU, dev->dev_addr, ocelot_port->pvid,
@@ -1187,6 +1620,9 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port,
 		goto err_register_netdev;
 	}
 
+	/* Basic L2 initialization */
+	ocelot_vlan_port_apply(ocelot, ocelot_port);
+
 	return 0;
 
 err_register_netdev:
@@ -1201,6 +1637,11 @@ int ocelot_init(struct ocelot *ocelot)
 	int i, cpu = ocelot->num_phys_ports;
 	char queue_name[32];
 
+	ocelot->lags = devm_kcalloc(ocelot->dev, ocelot->num_phys_ports,
+				    sizeof(u32), GFP_KERNEL);
+	if (!ocelot->lags)
+		return -ENOMEM;
+
 	ocelot->stats = devm_kcalloc(ocelot->dev,
 				     ocelot->num_phys_ports * ocelot->num_stats,
 				     sizeof(u64), GFP_KERNEL);
diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index 097bd12a10d4..616bec30dfa3 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -493,7 +493,7 @@ struct ocelot {
 	u8 num_cpu_ports;
 	struct ocelot_port **ports;
 
-	u16 lags[16];
+	u32 *lags;
 
 	/* Keep track of the vlan port masks */
 	u32 vlan_mask[VLAN_N_VID];
diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index 18df7d934e81..26bb3b18f3be 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -29,7 +29,7 @@ static int ocelot_parse_ifh(u32 *ifh, struct frame_info *info)
 	info->port = (ifh[2] & GENMASK(14, 11)) >> 11;
 
 	info->cpuq = (ifh[3] & GENMASK(27, 20)) >> 20;
-	info->tag_type = (ifh[3] & GENMASK(16, 16)) >> 16;
+	info->tag_type = (ifh[3] & BIT(16)) >> 16;
 	info->vid = ifh[3] & GENMASK(11, 0);
 
 	return 0;
diff --git a/drivers/net/ethernet/neterion/Kconfig b/drivers/net/ethernet/neterion/Kconfig
index 71899009c468..c26e0f70c494 100644
--- a/drivers/net/ethernet/neterion/Kconfig
+++ b/drivers/net/ethernet/neterion/Kconfig
@@ -2,8 +2,8 @@
 # Exar device configuration
 #
 
-config NET_VENDOR_EXAR
-	bool "Exar devices"
+config NET_VENDOR_NETERION
+	bool "Neterion (Exar) devices"
 	default y
 	depends on PCI
 	---help---
@@ -11,16 +11,19 @@ config NET_VENDOR_EXAR
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
-	  the questions about Exar cards. If you say Y, you will be asked for
-	  your specific card in the following questions.
+	  the questions about Neterion/Exar cards. If you say Y, you will be
+	  asked for your specific card in the following questions.
 
-if NET_VENDOR_EXAR
+if NET_VENDOR_NETERION
 
 config S2IO
-	tristate "Exar Xframe 10Gb Ethernet Adapter"
+	tristate "Neterion (Exar) Xframe 10Gb Ethernet Adapter"
 	depends on PCI
 	---help---
 	  This driver supports Exar Corp's Xframe Series 10Gb Ethernet Adapters.
+	  These were originally released from S2IO, which renamed itself
+	  Neterion.  So, the adapters might be labeled as either one, depending
+	  on its age.
 
 	  More specific information on configuring the driver is in
 	  <file:Documentation/networking/s2io.txt>.
@@ -29,11 +32,13 @@ config S2IO
 	  will be called s2io.
 
 config VXGE
-	tristate "Exar X3100 Series 10GbE PCIe Server Adapter"
+	tristate "Neterion (Exar) X3100 Series 10GbE PCIe Server Adapter"
 	depends on PCI
 	---help---
 	  This driver supports Exar Corp's X3100 Series 10 GbE PCIe
-	  I/O Virtualized Server Adapter.
+	  I/O Virtualized Server Adapter.  These were originally released from
+	  Neterion, which was later acquired by Exar.  So, the adapters might be
+	  labeled as either one, depending on its age.
 
 	  More specific information on configuring the driver is in
 	  <file:Documentation/networking/vxge.txt>.
@@ -50,4 +55,4 @@ config VXGE_DEBUG_TRACE_ALL
 	  the vxge driver. By default only few debug trace statements are
 	  enabled.
 
-endif # NET_VENDOR_EXAR
+endif # NET_VENDOR_NETERION
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c
index 358ed6118881..398011c87643 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-config.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c
@@ -14,7 +14,6 @@
 #include <linux/vmalloc.h>
 #include <linux/etherdevice.h>
 #include <linux/pci.h>
-#include <linux/pci_hotplug.h>
 #include <linux/slab.h>
 
 #include "vxge-traffic.h"
@@ -1095,12 +1094,9 @@ static void __vxge_hw_blockpool_destroy(struct __vxge_hw_blockpool *blockpool)
 {
 	struct __vxge_hw_device *hldev;
 	struct list_head *p, *n;
-	u16 ret;
 
-	if (blockpool == NULL) {
-		ret = 1;
-		goto exit;
-	}
+	if (!blockpool)
+		return;
 
 	hldev = blockpool->hldev;
 
@@ -1123,8 +1119,7 @@ static void __vxge_hw_blockpool_destroy(struct __vxge_hw_blockpool *blockpool)
 		list_del(&((struct __vxge_hw_blockpool_entry *)p)->item);
 		kfree((void *)p);
 	}
-	ret = 0;
-exit:
+
 	return;
 }
 
@@ -2260,14 +2255,11 @@ static void vxge_hw_blockpool_block_add(struct __vxge_hw_device *devh,
 	struct __vxge_hw_blockpool *blockpool;
 	struct __vxge_hw_blockpool_entry *entry = NULL;
 	dma_addr_t dma_addr;
-	enum vxge_hw_status status = VXGE_HW_OK;
-	u32 req_out;
 
 	blockpool = &devh->block_pool;
 
 	if (block_addr == NULL) {
 		blockpool->req_out--;
-		status = VXGE_HW_FAIL;
 		goto exit;
 	}
 
@@ -2277,7 +2269,6 @@ static void vxge_hw_blockpool_block_add(struct __vxge_hw_device *devh,
 	if (unlikely(pci_dma_mapping_error(devh->pdev, dma_addr))) {
 		vxge_os_dma_free(devh->pdev, block_addr, &acc_handle);
 		blockpool->req_out--;
-		status = VXGE_HW_FAIL;
 		goto exit;
 	}
 
@@ -2292,7 +2283,7 @@ static void vxge_hw_blockpool_block_add(struct __vxge_hw_device *devh,
 	else
 		list_del(&entry->item);
 
-	if (entry != NULL) {
+	if (entry) {
 		entry->length = length;
 		entry->memblock = block_addr;
 		entry->dma_addr = dma_addr;
@@ -2300,13 +2291,10 @@ static void vxge_hw_blockpool_block_add(struct __vxge_hw_device *devh,
 		entry->dma_handle = dma_h;
 		list_add(&entry->item, &blockpool->free_block_list);
 		blockpool->pool_size++;
-		status = VXGE_HW_OK;
-	} else
-		status = VXGE_HW_ERR_OUT_OF_MEMORY;
+	}
 
 	blockpool->req_out--;
 
-	req_out = blockpool->req_out;
 exit:
 	return;
 }
@@ -2358,7 +2346,6 @@ static void *__vxge_hw_blockpool_malloc(struct __vxge_hw_device *devh, u32 size,
 	struct __vxge_hw_blockpool_entry *entry = NULL;
 	struct __vxge_hw_blockpool  *blockpool;
 	void *memblock = NULL;
-	enum vxge_hw_status status = VXGE_HW_OK;
 
 	blockpool = &devh->block_pool;
 
@@ -2368,10 +2355,8 @@ static void *__vxge_hw_blockpool_malloc(struct __vxge_hw_device *devh, u32 size,
 						&dma_object->handle,
 						&dma_object->acc_handle);
 
-		if (memblock == NULL) {
-			status = VXGE_HW_ERR_OUT_OF_MEMORY;
+		if (!memblock)
 			goto exit;
-		}
 
 		dma_object->addr = pci_map_single(devh->pdev, memblock, size,
 					PCI_DMA_BIDIRECTIONAL);
@@ -2380,7 +2365,6 @@ static void *__vxge_hw_blockpool_malloc(struct __vxge_hw_device *devh, u32 size,
 				dma_object->addr))) {
 			vxge_os_dma_free(devh->pdev, memblock,
 				&dma_object->acc_handle);
-			status = VXGE_HW_ERR_OUT_OF_MEMORY;
 			goto exit;
 		}
 
@@ -3784,17 +3768,20 @@ vxge_hw_rts_rth_data0_data1_get(u32 j, u64 *data0, u64 *data1,
 			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM0_ENTRY_EN |
 			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM0_BUCKET_DATA(
 			itable[j]);
+		/* fall through */
 	case 2:
 		*data0 |=
 			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM1_BUCKET_NUM(j)|
 			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM1_ENTRY_EN |
 			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM1_BUCKET_DATA(
 			itable[j]);
+		/* fall through */
 	case 3:
 		*data1 = VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM0_BUCKET_NUM(j)|
 			VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM0_ENTRY_EN |
 			VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM0_BUCKET_DATA(
 			itable[j]);
+		/* fall through */
 	case 4:
 		*data1 |=
 			VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM1_BUCKET_NUM(j)|
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
index cb87fccb9f6a..2572a4b91c7c 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
@@ -43,8 +43,6 @@
 #include "fw.h"
 #include "main.h"
 
-#define cmsg_warn(bpf, msg...)	nn_dp_warn(&(bpf)->app->ctrl->dp, msg)
-
 #define NFP_BPF_TAG_ALLOC_SPAN	(U16_MAX / 4)
 
 static bool nfp_bpf_all_tags_busy(struct nfp_app_bpf *bpf)
@@ -441,7 +439,10 @@ void nfp_bpf_ctrl_msg_rx(struct nfp_app *app, struct sk_buff *skb)
 	}
 
 	if (nfp_bpf_cmsg_get_type(skb) == CMSG_TYPE_BPF_EVENT) {
-		nfp_bpf_event_output(bpf, skb);
+		if (!nfp_bpf_event_output(bpf, skb->data, skb->len))
+			dev_consume_skb_any(skb);
+		else
+			dev_kfree_skb_any(skb);
 		return;
 	}
 
@@ -465,3 +466,21 @@ err_unlock:
 err_free:
 	dev_kfree_skb_any(skb);
 }
+
+void
+nfp_bpf_ctrl_msg_rx_raw(struct nfp_app *app, const void *data, unsigned int len)
+{
+	struct nfp_app_bpf *bpf = app->priv;
+	const struct cmsg_hdr *hdr = data;
+
+	if (unlikely(len < sizeof(struct cmsg_reply_map_simple))) {
+		cmsg_warn(bpf, "cmsg drop - too short %d!\n", len);
+		return;
+	}
+
+	if (hdr->type == CMSG_TYPE_BPF_EVENT)
+		nfp_bpf_event_output(bpf, data, len);
+	else
+		cmsg_warn(bpf, "cmsg drop - msg type %d with raw buffer!\n",
+			  hdr->type);
+}
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/fw.h b/drivers/net/ethernet/netronome/nfp/bpf/fw.h
index 4c7972e3db63..e4f9b7ec8528 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/fw.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/fw.h
@@ -51,6 +51,7 @@ enum bpf_cap_tlv_type {
 	NFP_BPF_CAP_TYPE_MAPS		= 3,
 	NFP_BPF_CAP_TYPE_RANDOM		= 4,
 	NFP_BPF_CAP_TYPE_QUEUE_SELECT	= 5,
+	NFP_BPF_CAP_TYPE_ADJUST_TAIL	= 6,
 };
 
 struct nfp_bpf_cap_tlv_func {
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index 8a92088df0d7..eff57f7d056a 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -34,10 +34,11 @@
 #define pr_fmt(fmt)	"NFP net bpf: " fmt
 
 #include <linux/bug.h>
-#include <linux/kernel.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
+#include <linux/kernel.h>
 #include <linux/pkt_cls.h>
+#include <linux/reciprocal_div.h>
 #include <linux/unistd.h>
 
 #include "main.h"
@@ -416,6 +417,60 @@ emit_alu(struct nfp_prog *nfp_prog, swreg dst,
 }
 
 static void
+__emit_mul(struct nfp_prog *nfp_prog, enum alu_dst_ab dst_ab, u16 areg,
+	   enum mul_type type, enum mul_step step, u16 breg, bool swap,
+	   bool wr_both, bool dst_lmextn, bool src_lmextn)
+{
+	u64 insn;
+
+	insn = OP_MUL_BASE |
+		FIELD_PREP(OP_MUL_A_SRC, areg) |
+		FIELD_PREP(OP_MUL_B_SRC, breg) |
+		FIELD_PREP(OP_MUL_STEP, step) |
+		FIELD_PREP(OP_MUL_DST_AB, dst_ab) |
+		FIELD_PREP(OP_MUL_SW, swap) |
+		FIELD_PREP(OP_MUL_TYPE, type) |
+		FIELD_PREP(OP_MUL_WR_AB, wr_both) |
+		FIELD_PREP(OP_MUL_SRC_LMEXTN, src_lmextn) |
+		FIELD_PREP(OP_MUL_DST_LMEXTN, dst_lmextn);
+
+	nfp_prog_push(nfp_prog, insn);
+}
+
+static void
+emit_mul(struct nfp_prog *nfp_prog, swreg lreg, enum mul_type type,
+	 enum mul_step step, swreg rreg)
+{
+	struct nfp_insn_ur_regs reg;
+	u16 areg;
+	int err;
+
+	if (type == MUL_TYPE_START && step != MUL_STEP_NONE) {
+		nfp_prog->error = -EINVAL;
+		return;
+	}
+
+	if (step == MUL_LAST || step == MUL_LAST_2) {
+		/* When type is step and step Number is LAST or LAST2, left
+		 * source is used as destination.
+		 */
+		err = swreg_to_unrestricted(lreg, reg_none(), rreg, &reg);
+		areg = reg.dst;
+	} else {
+		err = swreg_to_unrestricted(reg_none(), lreg, rreg, &reg);
+		areg = reg.areg;
+	}
+
+	if (err) {
+		nfp_prog->error = err;
+		return;
+	}
+
+	__emit_mul(nfp_prog, reg.dst_ab, areg, type, step, reg.breg, reg.swap,
+		   reg.wr_both, reg.dst_lmextn, reg.src_lmextn);
+}
+
+static void
 __emit_ld_field(struct nfp_prog *nfp_prog, enum shf_sc sc,
 		u8 areg, u8 bmask, u8 breg, u8 shift, bool imm8,
 		bool zero, bool swap, bool wr_both,
@@ -670,7 +725,7 @@ static int nfp_cpp_memcpy(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	xfer_num = round_up(len, 4) / 4;
 
 	if (src_40bit_addr)
-		addr40_offset(nfp_prog, meta->insn.src_reg, off, &src_base,
+		addr40_offset(nfp_prog, meta->insn.src_reg * 2, off, &src_base,
 			      &off);
 
 	/* Setup PREV_ALU fields to override memory read length. */
@@ -1380,6 +1435,133 @@ static void wrp_end32(struct nfp_prog *nfp_prog, swreg reg_in, u8 gpr_out)
 		      SHF_SC_R_ROT, 16);
 }
 
+static void
+wrp_mul_u32(struct nfp_prog *nfp_prog, swreg dst_hi, swreg dst_lo, swreg lreg,
+	    swreg rreg, bool gen_high_half)
+{
+	emit_mul(nfp_prog, lreg, MUL_TYPE_START, MUL_STEP_NONE, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_1, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_2, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_3, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_4, rreg);
+	emit_mul(nfp_prog, dst_lo, MUL_TYPE_STEP_32x32, MUL_LAST, reg_none());
+	if (gen_high_half)
+		emit_mul(nfp_prog, dst_hi, MUL_TYPE_STEP_32x32, MUL_LAST_2,
+			 reg_none());
+	else
+		wrp_immed(nfp_prog, dst_hi, 0);
+}
+
+static void
+wrp_mul_u16(struct nfp_prog *nfp_prog, swreg dst_hi, swreg dst_lo, swreg lreg,
+	    swreg rreg)
+{
+	emit_mul(nfp_prog, lreg, MUL_TYPE_START, MUL_STEP_NONE, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_16x16, MUL_STEP_1, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_16x16, MUL_STEP_2, rreg);
+	emit_mul(nfp_prog, dst_lo, MUL_TYPE_STEP_16x16, MUL_LAST, reg_none());
+}
+
+static int
+wrp_mul(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+	bool gen_high_half, bool ropnd_from_reg)
+{
+	swreg multiplier, multiplicand, dst_hi, dst_lo;
+	const struct bpf_insn *insn = &meta->insn;
+	u32 lopnd_max, ropnd_max;
+	u8 dst_reg;
+
+	dst_reg = insn->dst_reg;
+	multiplicand = reg_a(dst_reg * 2);
+	dst_hi = reg_both(dst_reg * 2 + 1);
+	dst_lo = reg_both(dst_reg * 2);
+	lopnd_max = meta->umax_dst;
+	if (ropnd_from_reg) {
+		multiplier = reg_b(insn->src_reg * 2);
+		ropnd_max = meta->umax_src;
+	} else {
+		u32 imm = insn->imm;
+
+		multiplier = ur_load_imm_any(nfp_prog, imm, imm_b(nfp_prog));
+		ropnd_max = imm;
+	}
+	if (lopnd_max > U16_MAX || ropnd_max > U16_MAX)
+		wrp_mul_u32(nfp_prog, dst_hi, dst_lo, multiplicand, multiplier,
+			    gen_high_half);
+	else
+		wrp_mul_u16(nfp_prog, dst_hi, dst_lo, multiplicand, multiplier);
+
+	return 0;
+}
+
+static int wrp_div_imm(struct nfp_prog *nfp_prog, u8 dst, u64 imm)
+{
+	swreg dst_both = reg_both(dst), dst_a = reg_a(dst), dst_b = reg_a(dst);
+	struct reciprocal_value_adv rvalue;
+	u8 pre_shift, exp;
+	swreg magic;
+
+	if (imm > U32_MAX) {
+		wrp_immed(nfp_prog, dst_both, 0);
+		return 0;
+	}
+
+	/* NOTE: because we are using "reciprocal_value_adv" which doesn't
+	 * support "divisor > (1u << 31)", we need to JIT separate NFP sequence
+	 * to handle such case which actually equals to the result of unsigned
+	 * comparison "dst >= imm" which could be calculated using the following
+	 * NFP sequence:
+	 *
+	 *  alu[--, dst, -, imm]
+	 *  immed[imm, 0]
+	 *  alu[dst, imm, +carry, 0]
+	 *
+	 */
+	if (imm > 1U << 31) {
+		swreg tmp_b = ur_load_imm_any(nfp_prog, imm, imm_b(nfp_prog));
+
+		emit_alu(nfp_prog, reg_none(), dst_a, ALU_OP_SUB, tmp_b);
+		wrp_immed(nfp_prog, imm_a(nfp_prog), 0);
+		emit_alu(nfp_prog, dst_both, imm_a(nfp_prog), ALU_OP_ADD_C,
+			 reg_imm(0));
+		return 0;
+	}
+
+	rvalue = reciprocal_value_adv(imm, 32);
+	exp = rvalue.exp;
+	if (rvalue.is_wide_m && !(imm & 1)) {
+		pre_shift = fls(imm & -imm) - 1;
+		rvalue = reciprocal_value_adv(imm >> pre_shift, 32 - pre_shift);
+	} else {
+		pre_shift = 0;
+	}
+	magic = ur_load_imm_any(nfp_prog, rvalue.m, imm_b(nfp_prog));
+	if (imm == 1U << exp) {
+		emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE, dst_b,
+			 SHF_SC_R_SHF, exp);
+	} else if (rvalue.is_wide_m) {
+		wrp_mul_u32(nfp_prog, imm_both(nfp_prog), reg_none(), dst_a,
+			    magic, true);
+		emit_alu(nfp_prog, dst_both, dst_a, ALU_OP_SUB,
+			 imm_b(nfp_prog));
+		emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE, dst_b,
+			 SHF_SC_R_SHF, 1);
+		emit_alu(nfp_prog, dst_both, dst_a, ALU_OP_ADD,
+			 imm_b(nfp_prog));
+		emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE, dst_b,
+			 SHF_SC_R_SHF, rvalue.sh - 1);
+	} else {
+		if (pre_shift)
+			emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE,
+				 dst_b, SHF_SC_R_SHF, pre_shift);
+		wrp_mul_u32(nfp_prog, dst_both, reg_none(), dst_a, magic, true);
+		emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE,
+			 dst_b, SHF_SC_R_SHF, rvalue.sh);
+	}
+
+	return 0;
+}
+
 static int adjust_head(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	swreg tmp = imm_a(nfp_prog), tmp_len = imm_b(nfp_prog);
@@ -1460,6 +1642,51 @@ static int adjust_head(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return 0;
 }
 
+static int adjust_tail(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	u32 ret_einval, end;
+	swreg plen, delta;
+
+	BUILD_BUG_ON(plen_reg(nfp_prog) != reg_b(STATIC_REG_PKT_LEN));
+
+	plen = imm_a(nfp_prog);
+	delta = reg_a(2 * 2);
+
+	ret_einval = nfp_prog_current_offset(nfp_prog) + 9;
+	end = nfp_prog_current_offset(nfp_prog) + 11;
+
+	/* Calculate resulting length */
+	emit_alu(nfp_prog, plen, plen_reg(nfp_prog), ALU_OP_ADD, delta);
+	/* delta == 0 is not allowed by the kernel, add must overflow to make
+	 * length smaller.
+	 */
+	emit_br(nfp_prog, BR_BCC, ret_einval, 0);
+
+	/* if (new_len < 14) then -EINVAL */
+	emit_alu(nfp_prog, reg_none(), plen, ALU_OP_SUB, reg_imm(ETH_HLEN));
+	emit_br(nfp_prog, BR_BMI, ret_einval, 0);
+
+	emit_alu(nfp_prog, plen_reg(nfp_prog),
+		 plen_reg(nfp_prog), ALU_OP_ADD, delta);
+	emit_alu(nfp_prog, pv_len(nfp_prog),
+		 pv_len(nfp_prog), ALU_OP_ADD, delta);
+
+	emit_br(nfp_prog, BR_UNC, end, 2);
+	wrp_immed(nfp_prog, reg_both(0), 0);
+	wrp_immed(nfp_prog, reg_both(1), 0);
+
+	if (!nfp_prog_confirm_current_offset(nfp_prog, ret_einval))
+		return -EINVAL;
+
+	wrp_immed(nfp_prog, reg_both(0), -22);
+	wrp_immed(nfp_prog, reg_both(1), ~0);
+
+	if (!nfp_prog_confirm_current_offset(nfp_prog, end))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int
 map_call_stack_common(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
@@ -1684,6 +1911,31 @@ static int sub_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return 0;
 }
 
+static int mul_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return wrp_mul(nfp_prog, meta, true, true);
+}
+
+static int mul_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return wrp_mul(nfp_prog, meta, true, false);
+}
+
+static int div_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+
+	return wrp_div_imm(nfp_prog, insn->dst_reg * 2, insn->imm);
+}
+
+static int div_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	/* NOTE: verifier hook has rejected cases for which verifier doesn't
+	 * know whether the source operand is constant or not.
+	 */
+	return wrp_div_imm(nfp_prog, meta->insn.dst_reg * 2, meta->umin_src);
+}
+
 static int neg_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
@@ -1772,8 +2024,8 @@ static int shl_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	u8 dst, src;
 
 	dst = insn->dst_reg * 2;
-	umin = meta->umin;
-	umax = meta->umax;
+	umin = meta->umin_src;
+	umax = meta->umax_src;
 	if (umin == umax)
 		return __shl_imm64(nfp_prog, dst, umin);
 
@@ -1881,8 +2133,8 @@ static int shr_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	u8 dst, src;
 
 	dst = insn->dst_reg * 2;
-	umin = meta->umin;
-	umax = meta->umax;
+	umin = meta->umin_src;
+	umax = meta->umax_src;
 	if (umin == umax)
 		return __shr_imm64(nfp_prog, dst, umin);
 
@@ -1995,8 +2247,8 @@ static int ashr_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	u8 dst, src;
 
 	dst = insn->dst_reg * 2;
-	umin = meta->umin;
-	umax = meta->umax;
+	umin = meta->umin_src;
+	umax = meta->umax_src;
 	if (umin == umax)
 		return __ashr_imm64(nfp_prog, dst, umin);
 
@@ -2097,6 +2349,26 @@ static int sub_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_SUB, !meta->insn.imm);
 }
 
+static int mul_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return wrp_mul(nfp_prog, meta, false, true);
+}
+
+static int mul_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return wrp_mul(nfp_prog, meta, false, false);
+}
+
+static int div_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return div_reg64(nfp_prog, meta);
+}
+
+static int div_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return div_imm64(nfp_prog, meta);
+}
+
 static int neg_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	u8 dst = meta->insn.dst_reg * 2;
@@ -2814,6 +3086,8 @@ static int call(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	switch (meta->insn.imm) {
 	case BPF_FUNC_xdp_adjust_head:
 		return adjust_head(nfp_prog, meta);
+	case BPF_FUNC_xdp_adjust_tail:
+		return adjust_tail(nfp_prog, meta);
 	case BPF_FUNC_map_lookup_elem:
 	case BPF_FUNC_map_update_elem:
 	case BPF_FUNC_map_delete_elem:
@@ -2848,6 +3122,10 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_ALU64 | BPF_ADD | BPF_K] =	add_imm64,
 	[BPF_ALU64 | BPF_SUB | BPF_X] =	sub_reg64,
 	[BPF_ALU64 | BPF_SUB | BPF_K] =	sub_imm64,
+	[BPF_ALU64 | BPF_MUL | BPF_X] =	mul_reg64,
+	[BPF_ALU64 | BPF_MUL | BPF_K] =	mul_imm64,
+	[BPF_ALU64 | BPF_DIV | BPF_X] =	div_reg64,
+	[BPF_ALU64 | BPF_DIV | BPF_K] =	div_imm64,
 	[BPF_ALU64 | BPF_NEG] =		neg_reg64,
 	[BPF_ALU64 | BPF_LSH | BPF_X] =	shl_reg64,
 	[BPF_ALU64 | BPF_LSH | BPF_K] =	shl_imm64,
@@ -2867,6 +3145,10 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_ALU | BPF_ADD | BPF_K] =	add_imm,
 	[BPF_ALU | BPF_SUB | BPF_X] =	sub_reg,
 	[BPF_ALU | BPF_SUB | BPF_K] =	sub_imm,
+	[BPF_ALU | BPF_MUL | BPF_X] =	mul_reg,
+	[BPF_ALU | BPF_MUL | BPF_K] =	mul_imm,
+	[BPF_ALU | BPF_DIV | BPF_X] =	div_reg,
+	[BPF_ALU | BPF_DIV | BPF_K] =	div_imm,
 	[BPF_ALU | BPF_NEG] =		neg_reg,
 	[BPF_ALU | BPF_LSH | BPF_K] =	shl_imm,
 	[BPF_ALU | BPF_END | BPF_X] =	end_reg32,
@@ -3299,7 +3581,8 @@ curr_pair_is_memcpy(struct nfp_insn_meta *ld_meta,
 	if (!is_mbpf_load(ld_meta) || !is_mbpf_store(st_meta))
 		return false;
 
-	if (ld_meta->ptr.type != PTR_TO_PACKET)
+	if (ld_meta->ptr.type != PTR_TO_PACKET &&
+	    ld_meta->ptr.type != PTR_TO_MAP_VALUE)
 		return false;
 
 	if (st_meta->ptr.type != PTR_TO_PACKET)
@@ -3647,6 +3930,7 @@ static int nfp_bpf_replace_map_ptrs(struct nfp_prog *nfp_prog)
 	struct nfp_insn_meta *meta1, *meta2;
 	struct nfp_bpf_map *nfp_map;
 	struct bpf_map *map;
+	u32 id;
 
 	nfp_for_each_insn_walk2(nfp_prog, meta1, meta2) {
 		if (meta1->skip || meta2->skip)
@@ -3658,11 +3942,14 @@ static int nfp_bpf_replace_map_ptrs(struct nfp_prog *nfp_prog)
 
 		map = (void *)(unsigned long)((u32)meta1->insn.imm |
 					      (u64)meta2->insn.imm << 32);
-		if (bpf_map_offload_neutral(map))
-			continue;
-		nfp_map = map_to_offmap(map)->dev_priv;
+		if (bpf_map_offload_neutral(map)) {
+			id = map->id;
+		} else {
+			nfp_map = map_to_offmap(map)->dev_priv;
+			id = nfp_map->tid;
+		}
 
-		meta1->insn.imm = nfp_map->tid;
+		meta1->insn.imm = id;
 		meta2->insn.imm = 0;
 	}
 
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index 40216d56dddc..970af07f4656 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -45,8 +45,8 @@
 
 const struct rhashtable_params nfp_bpf_maps_neutral_params = {
 	.nelem_hint		= 4,
-	.key_len		= FIELD_SIZEOF(struct nfp_bpf_neutral_map, ptr),
-	.key_offset		= offsetof(struct nfp_bpf_neutral_map, ptr),
+	.key_len		= FIELD_SIZEOF(struct bpf_map, id),
+	.key_offset		= offsetof(struct nfp_bpf_neutral_map, map_id),
 	.head_offset		= offsetof(struct nfp_bpf_neutral_map, l),
 	.automatic_shrinking	= true,
 };
@@ -66,26 +66,19 @@ nfp_bpf_xdp_offload(struct nfp_app *app, struct nfp_net *nn,
 		    struct bpf_prog *prog, struct netlink_ext_ack *extack)
 {
 	bool running, xdp_running;
-	int ret;
 
 	if (!nfp_net_ebpf_capable(nn))
 		return -EINVAL;
 
 	running = nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF;
-	xdp_running = running && nn->dp.bpf_offload_xdp;
+	xdp_running = running && nn->xdp_hw.prog;
 
 	if (!prog && !xdp_running)
 		return 0;
 	if (prog && running && !xdp_running)
 		return -EBUSY;
 
-	ret = nfp_net_bpf_offload(nn, prog, running, extack);
-	/* Stop offload if replace not possible */
-	if (ret)
-		return ret;
-
-	nn->dp.bpf_offload_xdp = !!prog;
-	return ret;
+	return nfp_net_bpf_offload(nn, prog, running, extack);
 }
 
 static const char *nfp_bpf_extra_cap(struct nfp_app *app, struct nfp_net *nn)
@@ -202,14 +195,11 @@ static int nfp_bpf_setup_tc_block(struct net_device *netdev,
 	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		return -EOPNOTSUPP;
 
-	if (tcf_block_shared(f->block))
-		return -EOPNOTSUPP;
-
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block,
 					     nfp_bpf_setup_tc_block_cb,
-					     nn, nn);
+					     nn, nn, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block,
 					nfp_bpf_setup_tc_block_cb,
@@ -344,6 +334,14 @@ nfp_bpf_parse_cap_qsel(struct nfp_app_bpf *bpf, void __iomem *value, u32 length)
 	return 0;
 }
 
+static int
+nfp_bpf_parse_cap_adjust_tail(struct nfp_app_bpf *bpf, void __iomem *value,
+			      u32 length)
+{
+	bpf->adjust_tail = true;
+	return 0;
+}
+
 static int nfp_bpf_parse_capabilities(struct nfp_app *app)
 {
 	struct nfp_cpp *cpp = app->pf->cpp;
@@ -390,6 +388,11 @@ static int nfp_bpf_parse_capabilities(struct nfp_app *app)
 			if (nfp_bpf_parse_cap_qsel(app->priv, value, length))
 				goto err_release_free;
 			break;
+		case NFP_BPF_CAP_TYPE_ADJUST_TAIL:
+			if (nfp_bpf_parse_cap_adjust_tail(app->priv, value,
+							  length))
+				goto err_release_free;
+			break;
 		default:
 			nfp_dbg(cpp, "unknown BPF capability: %d\n", type);
 			break;
@@ -411,6 +414,20 @@ err_release_free:
 	return -EINVAL;
 }
 
+static int nfp_bpf_ndo_init(struct nfp_app *app, struct net_device *netdev)
+{
+	struct nfp_app_bpf *bpf = app->priv;
+
+	return bpf_offload_dev_netdev_register(bpf->bpf_dev, netdev);
+}
+
+static void nfp_bpf_ndo_uninit(struct nfp_app *app, struct net_device *netdev)
+{
+	struct nfp_app_bpf *bpf = app->priv;
+
+	bpf_offload_dev_netdev_unregister(bpf->bpf_dev, netdev);
+}
+
 static int nfp_bpf_init(struct nfp_app *app)
 {
 	struct nfp_app_bpf *bpf;
@@ -434,6 +451,11 @@ static int nfp_bpf_init(struct nfp_app *app)
 	if (err)
 		goto err_free_neutral_maps;
 
+	bpf->bpf_dev = bpf_offload_dev_create();
+	err = PTR_ERR_OR_ZERO(bpf->bpf_dev);
+	if (err)
+		goto err_free_neutral_maps;
+
 	return 0;
 
 err_free_neutral_maps:
@@ -452,6 +474,7 @@ static void nfp_bpf_clean(struct nfp_app *app)
 {
 	struct nfp_app_bpf *bpf = app->priv;
 
+	bpf_offload_dev_destroy(bpf->bpf_dev);
 	WARN_ON(!skb_queue_empty(&bpf->cmsg_replies));
 	WARN_ON(!list_empty(&bpf->map_list));
 	WARN_ON(bpf->maps_in_use || bpf->map_elems_in_use);
@@ -473,10 +496,14 @@ const struct nfp_app_type app_bpf = {
 
 	.extra_cap	= nfp_bpf_extra_cap,
 
+	.ndo_init	= nfp_bpf_ndo_init,
+	.ndo_uninit	= nfp_bpf_ndo_uninit,
+
 	.vnic_alloc	= nfp_bpf_vnic_alloc,
 	.vnic_free	= nfp_bpf_vnic_free,
 
 	.ctrl_msg_rx	= nfp_bpf_ctrl_msg_rx,
+	.ctrl_msg_rx_raw	= nfp_bpf_ctrl_msg_rx_raw,
 
 	.setup_tc	= nfp_bpf_setup_tc,
 	.bpf		= nfp_ndo_bpf,
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index 654fe7823e5e..dbd00982fd2b 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -47,6 +47,8 @@
 #include "../nfp_asm.h"
 #include "fw.h"
 
+#define cmsg_warn(bpf, msg...)	nn_dp_warn(&(bpf)->app->ctrl->dp, msg)
+
 /* For relocation logic use up-most byte of branch instruction as scratch
  * area.  Remember to clear this before sending instructions to HW!
  */
@@ -110,6 +112,8 @@ enum pkt_vec {
  * struct nfp_app_bpf - bpf app priv structure
  * @app:		backpointer to the app
  *
+ * @bpf_dev:		BPF offload device handle
+ *
  * @tag_allocator:	bitmap of control message tags in use
  * @tag_alloc_next:	next tag bit to allocate
  * @tag_alloc_last:	next tag bit to be freed
@@ -146,10 +150,13 @@ enum pkt_vec {
  *
  * @pseudo_random:	FW initialized the pseudo-random machinery (CSRs)
  * @queue_select:	BPF can set the RX queue ID in packet vector
+ * @adjust_tail:	BPF can simply trunc packet size for adjust tail
  */
 struct nfp_app_bpf {
 	struct nfp_app *app;
 
+	struct bpf_offload_dev *bpf_dev;
+
 	DECLARE_BITMAP(tag_allocator, U16_MAX + 1);
 	u16 tag_alloc_next;
 	u16 tag_alloc_last;
@@ -189,6 +196,7 @@ struct nfp_app_bpf {
 
 	bool pseudo_random;
 	bool queue_select;
+	bool adjust_tail;
 };
 
 enum nfp_bpf_map_use {
@@ -217,6 +225,7 @@ struct nfp_bpf_map {
 struct nfp_bpf_neutral_map {
 	struct rhash_head l;
 	struct bpf_map *ptr;
+	u32 map_id;
 	u32 count;
 };
 
@@ -263,8 +272,10 @@ struct nfp_bpf_reg_state {
  * @func_id: function id for call instructions
  * @arg1: arg1 for call instructions
  * @arg2: arg2 for call instructions
- * @umin: copy of core verifier umin_value.
- * @umax: copy of core verifier umax_value.
+ * @umin_src: copy of core verifier umin_value for src opearnd.
+ * @umax_src: copy of core verifier umax_value for src operand.
+ * @umin_dst: copy of core verifier umin_value for dst opearnd.
+ * @umax_dst: copy of core verifier umax_value for dst operand.
  * @off: index of first generated machine instruction (in nfp_prog.prog)
  * @n: eBPF instruction number
  * @flags: eBPF instruction extra optimization flags
@@ -300,12 +311,15 @@ struct nfp_insn_meta {
 			struct bpf_reg_state arg1;
 			struct nfp_bpf_reg_state arg2;
 		};
-		/* We are interested in range info for some operands,
-		 * for example, the shift amount.
+		/* We are interested in range info for operands of ALU
+		 * operations. For example, shift amount, multiplicand and
+		 * multiplier etc.
 		 */
 		struct {
-			u64 umin;
-			u64 umax;
+			u64 umin_src;
+			u64 umax_src;
+			u64 umin_dst;
+			u64 umax_dst;
 		};
 	};
 	unsigned int off;
@@ -339,6 +353,11 @@ static inline u8 mbpf_mode(const struct nfp_insn_meta *meta)
 	return BPF_MODE(meta->insn.code);
 }
 
+static inline bool is_mbpf_alu(const struct nfp_insn_meta *meta)
+{
+	return mbpf_class(meta) == BPF_ALU64 || mbpf_class(meta) == BPF_ALU;
+}
+
 static inline bool is_mbpf_load(const struct nfp_insn_meta *meta)
 {
 	return (meta->insn.code & ~BPF_SIZE_MASK) == (BPF_LDX | BPF_MEM);
@@ -384,23 +403,14 @@ static inline bool is_mbpf_xadd(const struct nfp_insn_meta *meta)
 	return (meta->insn.code & ~BPF_SIZE_MASK) == (BPF_STX | BPF_XADD);
 }
 
-static inline bool is_mbpf_indir_shift(const struct nfp_insn_meta *meta)
+static inline bool is_mbpf_mul(const struct nfp_insn_meta *meta)
 {
-	u8 code = meta->insn.code;
-	bool is_alu, is_shift;
-	u8 opclass, opcode;
-
-	opclass = BPF_CLASS(code);
-	is_alu = opclass == BPF_ALU64 || opclass == BPF_ALU;
-	if (!is_alu)
-		return false;
-
-	opcode = BPF_OP(code);
-	is_shift = opcode == BPF_LSH || opcode == BPF_RSH || opcode == BPF_ARSH;
-	if (!is_shift)
-		return false;
+	return is_mbpf_alu(meta) && mbpf_op(meta) == BPF_MUL;
+}
 
-	return BPF_SRC(code) == BPF_X;
+static inline bool is_mbpf_div(const struct nfp_insn_meta *meta)
+{
+	return is_mbpf_alu(meta) && mbpf_op(meta) == BPF_DIV;
 }
 
 /**
@@ -496,7 +506,11 @@ int nfp_bpf_ctrl_lookup_entry(struct bpf_offloaded_map *offmap,
 int nfp_bpf_ctrl_getnext_entry(struct bpf_offloaded_map *offmap,
 			       void *key, void *next_key);
 
-int nfp_bpf_event_output(struct nfp_app_bpf *bpf, struct sk_buff *skb);
+int nfp_bpf_event_output(struct nfp_app_bpf *bpf, const void *data,
+			 unsigned int len);
 
 void nfp_bpf_ctrl_msg_rx(struct nfp_app *app, struct sk_buff *skb);
+void
+nfp_bpf_ctrl_msg_rx_raw(struct nfp_app *app, const void *data,
+			unsigned int len);
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 7eae4c0266f8..1ccd6371a15b 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -67,7 +67,7 @@ nfp_map_ptr_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
 	ASSERT_RTNL();
 
 	/* Reuse path - other offloaded program is already tracking this map. */
-	record = rhashtable_lookup_fast(&bpf->maps_neutral, &map,
+	record = rhashtable_lookup_fast(&bpf->maps_neutral, &map->id,
 					nfp_bpf_maps_neutral_params);
 	if (record) {
 		nfp_prog->map_records[nfp_prog->map_records_cnt++] = record;
@@ -89,6 +89,7 @@ nfp_map_ptr_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
 	}
 
 	record->ptr = map;
+	record->map_id = map->id;
 	record->count = 1;
 
 	err = rhashtable_insert_fast(&bpf->maps_neutral, &record->l,
@@ -190,8 +191,10 @@ nfp_prog_prepare(struct nfp_prog *nfp_prog, const struct bpf_insn *prog,
 
 		meta->insn = prog[i];
 		meta->n = i;
-		if (is_mbpf_indir_shift(meta))
-			meta->umin = U64_MAX;
+		if (is_mbpf_alu(meta)) {
+			meta->umin_src = U64_MAX;
+			meta->umin_dst = U64_MAX;
+		}
 
 		list_add_tail(&meta->l, &nfp_prog->insns);
 	}
@@ -377,11 +380,23 @@ nfp_bpf_map_alloc(struct nfp_app_bpf *bpf, struct bpf_offloaded_map *offmap)
 			bpf->maps.max_elems - bpf->map_elems_in_use);
 		return -ENOMEM;
 	}
-	if (offmap->map.key_size > bpf->maps.max_key_sz ||
-	    offmap->map.value_size > bpf->maps.max_val_sz ||
-	    round_up(offmap->map.key_size, 8) +
+
+	if (round_up(offmap->map.key_size, 8) +
 	    round_up(offmap->map.value_size, 8) > bpf->maps.max_elem_sz) {
-		pr_info("elements don't fit in device constraints\n");
+		pr_info("map elements too large: %u, FW max element size (key+value): %u\n",
+			round_up(offmap->map.key_size, 8) +
+			round_up(offmap->map.value_size, 8),
+			bpf->maps.max_elem_sz);
+		return -ENOMEM;
+	}
+	if (offmap->map.key_size > bpf->maps.max_key_sz) {
+		pr_info("map key size %u, FW max is %u\n",
+			offmap->map.key_size, bpf->maps.max_key_sz);
+		return -ENOMEM;
+	}
+	if (offmap->map.value_size > bpf->maps.max_val_sz) {
+		pr_info("map value size %u, FW max is %u\n",
+			offmap->map.value_size, bpf->maps.max_val_sz);
 		return -ENOMEM;
 	}
 
@@ -451,43 +466,43 @@ nfp_bpf_perf_event_copy(void *dst, const void *src,
 	return 0;
 }
 
-int nfp_bpf_event_output(struct nfp_app_bpf *bpf, struct sk_buff *skb)
+int nfp_bpf_event_output(struct nfp_app_bpf *bpf, const void *data,
+			 unsigned int len)
 {
-	struct cmsg_bpf_event *cbe = (void *)skb->data;
-	u32 pkt_size, data_size;
-	struct bpf_map *map;
+	struct cmsg_bpf_event *cbe = (void *)data;
+	struct nfp_bpf_neutral_map *record;
+	u32 pkt_size, data_size, map_id;
+	u64 map_id_full;
 
-	if (skb->len < sizeof(struct cmsg_bpf_event))
-		goto err_drop;
+	if (len < sizeof(struct cmsg_bpf_event))
+		return -EINVAL;
 
 	pkt_size = be32_to_cpu(cbe->pkt_size);
 	data_size = be32_to_cpu(cbe->data_size);
-	map = (void *)(unsigned long)be64_to_cpu(cbe->map_ptr);
+	map_id_full = be64_to_cpu(cbe->map_ptr);
+	map_id = map_id_full;
 
-	if (skb->len < sizeof(struct cmsg_bpf_event) + pkt_size + data_size)
-		goto err_drop;
+	if (len < sizeof(struct cmsg_bpf_event) + pkt_size + data_size)
+		return -EINVAL;
 	if (cbe->hdr.ver != CMSG_MAP_ABI_VERSION)
-		goto err_drop;
+		return -EINVAL;
 
 	rcu_read_lock();
-	if (!rhashtable_lookup_fast(&bpf->maps_neutral, &map,
-				    nfp_bpf_maps_neutral_params)) {
+	record = rhashtable_lookup_fast(&bpf->maps_neutral, &map_id,
+					nfp_bpf_maps_neutral_params);
+	if (!record || map_id_full > U32_MAX) {
 		rcu_read_unlock();
-		pr_warn("perf event: dest map pointer %px not recognized, dropping event\n",
-			map);
-		goto err_drop;
+		cmsg_warn(bpf, "perf event: map id %lld (0x%llx) not recognized, dropping event\n",
+			  map_id_full, map_id_full);
+		return -EINVAL;
 	}
 
-	bpf_event_output(map, be32_to_cpu(cbe->cpu_id),
+	bpf_event_output(record->ptr, be32_to_cpu(cbe->cpu_id),
 			 &cbe->data[round_up(pkt_size, 4)], data_size,
 			 cbe->data, pkt_size, nfp_bpf_perf_event_copy);
 	rcu_read_unlock();
 
-	dev_consume_skb_any(skb);
 	return 0;
-err_drop:
-	dev_kfree_skb_any(skb);
-	return -EINVAL;
 }
 
 static int
@@ -564,14 +579,8 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog,
 {
 	int err;
 
-	if (prog) {
-		struct bpf_prog_offload *offload = prog->aux->offload;
-
-		if (!offload)
-			return -EINVAL;
-		if (offload->netdev != nn->dp.netdev)
-			return -EINVAL;
-	}
+	if (prog && !bpf_offload_dev_match(prog, nn->dp.netdev))
+		return -EINVAL;
 
 	if (prog && old_prog) {
 		u8 cap;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
index 4bfeba7b21b2..a6e9248669e1 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
@@ -178,6 +178,13 @@ nfp_bpf_check_call(struct nfp_prog *nfp_prog, struct bpf_verifier_env *env,
 		nfp_record_adjust_head(bpf, nfp_prog, meta, reg2);
 		break;
 
+	case BPF_FUNC_xdp_adjust_tail:
+		if (!bpf->adjust_tail) {
+			pr_vlog(env, "adjust_tail not supported by FW\n");
+			return -EOPNOTSUPP;
+		}
+		break;
+
 	case BPF_FUNC_map_lookup_elem:
 		if (!nfp_bpf_map_call_ok("map_lookup", env, meta,
 					 bpf->helpers.map_lookup, reg1) ||
@@ -517,6 +524,82 @@ nfp_bpf_check_xadd(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 }
 
 static int
+nfp_bpf_check_alu(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+		  struct bpf_verifier_env *env)
+{
+	const struct bpf_reg_state *sreg =
+		cur_regs(env) + meta->insn.src_reg;
+	const struct bpf_reg_state *dreg =
+		cur_regs(env) + meta->insn.dst_reg;
+
+	meta->umin_src = min(meta->umin_src, sreg->umin_value);
+	meta->umax_src = max(meta->umax_src, sreg->umax_value);
+	meta->umin_dst = min(meta->umin_dst, dreg->umin_value);
+	meta->umax_dst = max(meta->umax_dst, dreg->umax_value);
+
+	/* NFP supports u16 and u32 multiplication.
+	 *
+	 * For ALU64, if either operand is beyond u32's value range, we reject
+	 * it. One thing to note, if the source operand is BPF_K, then we need
+	 * to check "imm" field directly, and we'd reject it if it is negative.
+	 * Because for ALU64, "imm" (with s32 type) is expected to be sign
+	 * extended to s64 which NFP mul doesn't support.
+	 *
+	 * For ALU32, it is fine for "imm" be negative though, because the
+	 * result is 32-bits and there is no difference on the low halve of
+	 * the result for signed/unsigned mul, so we will get correct result.
+	 */
+	if (is_mbpf_mul(meta)) {
+		if (meta->umax_dst > U32_MAX) {
+			pr_vlog(env, "multiplier is not within u32 value range\n");
+			return -EINVAL;
+		}
+		if (mbpf_src(meta) == BPF_X && meta->umax_src > U32_MAX) {
+			pr_vlog(env, "multiplicand is not within u32 value range\n");
+			return -EINVAL;
+		}
+		if (mbpf_class(meta) == BPF_ALU64 &&
+		    mbpf_src(meta) == BPF_K && meta->insn.imm < 0) {
+			pr_vlog(env, "sign extended multiplicand won't be within u32 value range\n");
+			return -EINVAL;
+		}
+	}
+
+	/* NFP doesn't have divide instructions, we support divide by constant
+	 * through reciprocal multiplication. Given NFP support multiplication
+	 * no bigger than u32, we'd require divisor and dividend no bigger than
+	 * that as well.
+	 *
+	 * Also eBPF doesn't support signed divide and has enforced this on C
+	 * language level by failing compilation. However LLVM assembler hasn't
+	 * enforced this, so it is possible for negative constant to leak in as
+	 * a BPF_K operand through assembly code, we reject such cases as well.
+	 */
+	if (is_mbpf_div(meta)) {
+		if (meta->umax_dst > U32_MAX) {
+			pr_vlog(env, "dividend is not within u32 value range\n");
+			return -EINVAL;
+		}
+		if (mbpf_src(meta) == BPF_X) {
+			if (meta->umin_src != meta->umax_src) {
+				pr_vlog(env, "divisor is not constant\n");
+				return -EINVAL;
+			}
+			if (meta->umax_src > U32_MAX) {
+				pr_vlog(env, "divisor is not within u32 value range\n");
+				return -EINVAL;
+			}
+		}
+		if (mbpf_src(meta) == BPF_K && meta->insn.imm < 0) {
+			pr_vlog(env, "divide by negative constant is not supported\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int
 nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx)
 {
 	struct nfp_prog *nfp_prog = env->prog->aux->offload->dev_priv;
@@ -551,13 +634,8 @@ nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx)
 	if (is_mbpf_xadd(meta))
 		return nfp_bpf_check_xadd(nfp_prog, meta, env);
 
-	if (is_mbpf_indir_shift(meta)) {
-		const struct bpf_reg_state *sreg =
-			cur_regs(env) + meta->insn.src_reg;
-
-		meta->umin = min(meta->umin, sreg->umin_value);
-		meta->umax = max(meta->umax, sreg->umax_value);
-	}
+	if (is_mbpf_alu(meta))
+		return nfp_bpf_check_alu(nfp_prog, meta, env);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index 4a6d2db75071..0ba0356ec4e6 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -32,8 +32,10 @@
  */
 
 #include <linux/bitfield.h>
+#include <net/geneve.h>
 #include <net/pkt_cls.h>
 #include <net/switchdev.h>
+#include <net/tc_act/tc_csum.h>
 #include <net/tc_act/tc_gact.h>
 #include <net/tc_act/tc_mirred.h>
 #include <net/tc_act/tc_pedit.h>
@@ -44,6 +46,16 @@
 #include "main.h"
 #include "../nfp_net_repr.h"
 
+/* The kernel versions of TUNNEL_* are not ABI and therefore vulnerable
+ * to change. Such changes will break our FW ABI.
+ */
+#define NFP_FL_TUNNEL_CSUM			cpu_to_be16(0x01)
+#define NFP_FL_TUNNEL_KEY			cpu_to_be16(0x04)
+#define NFP_FL_TUNNEL_GENEVE_OPT		cpu_to_be16(0x0800)
+#define NFP_FL_SUPPORTED_IPV4_UDP_TUN_FLAGS	(NFP_FL_TUNNEL_CSUM | \
+						 NFP_FL_TUNNEL_KEY | \
+						 NFP_FL_TUNNEL_GENEVE_OPT)
+
 static void nfp_fl_pop_vlan(struct nfp_fl_pop_vlan *pop_vlan)
 {
 	size_t act_size = sizeof(struct nfp_fl_pop_vlan);
@@ -226,7 +238,71 @@ static struct nfp_fl_pre_tunnel *nfp_fl_pre_tunnel(char *act_data, int act_len)
 }
 
 static int
-nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun,
+nfp_fl_push_geneve_options(struct nfp_fl_payload *nfp_fl, int *list_len,
+			   const struct tc_action *action)
+{
+	struct ip_tunnel_info *ip_tun = tcf_tunnel_info(action);
+	int opt_len, opt_cnt, act_start, tot_push_len;
+	u8 *src = ip_tunnel_info_opts(ip_tun);
+
+	/* We need to populate the options in reverse order for HW.
+	 * Therefore we go through the options, calculating the
+	 * number of options and the total size, then we populate
+	 * them in reverse order in the action list.
+	 */
+	opt_cnt = 0;
+	tot_push_len = 0;
+	opt_len = ip_tun->options_len;
+	while (opt_len > 0) {
+		struct geneve_opt *opt = (struct geneve_opt *)src;
+
+		opt_cnt++;
+		if (opt_cnt > NFP_FL_MAX_GENEVE_OPT_CNT)
+			return -EOPNOTSUPP;
+
+		tot_push_len += sizeof(struct nfp_fl_push_geneve) +
+			       opt->length * 4;
+		if (tot_push_len > NFP_FL_MAX_GENEVE_OPT_ACT)
+			return -EOPNOTSUPP;
+
+		opt_len -= sizeof(struct geneve_opt) + opt->length * 4;
+		src += sizeof(struct geneve_opt) + opt->length * 4;
+	}
+
+	if (*list_len + tot_push_len > NFP_FL_MAX_A_SIZ)
+		return -EOPNOTSUPP;
+
+	act_start = *list_len;
+	*list_len += tot_push_len;
+	src = ip_tunnel_info_opts(ip_tun);
+	while (opt_cnt) {
+		struct geneve_opt *opt = (struct geneve_opt *)src;
+		struct nfp_fl_push_geneve *push;
+		size_t act_size, len;
+
+		opt_cnt--;
+		act_size = sizeof(struct nfp_fl_push_geneve) + opt->length * 4;
+		tot_push_len -= act_size;
+		len = act_start + tot_push_len;
+
+		push = (struct nfp_fl_push_geneve *)&nfp_fl->action_data[len];
+		push->head.jump_id = NFP_FL_ACTION_OPCODE_PUSH_GENEVE;
+		push->head.len_lw = act_size >> NFP_FL_LW_SIZ;
+		push->reserved = 0;
+		push->class = opt->opt_class;
+		push->type = opt->type;
+		push->length = opt->length;
+		memcpy(&push->opt_data, opt->opt_data, opt->length * 4);
+
+		src += sizeof(struct geneve_opt) + opt->length * 4;
+	}
+
+	return 0;
+}
+
+static int
+nfp_fl_set_ipv4_udp_tun(struct nfp_app *app,
+			struct nfp_fl_set_ipv4_udp_tun *set_tun,
 			const struct tc_action *action,
 			struct nfp_fl_pre_tunnel *pre_tun,
 			enum nfp_flower_tun_type tun_type,
@@ -234,16 +310,19 @@ nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun,
 {
 	size_t act_size = sizeof(struct nfp_fl_set_ipv4_udp_tun);
 	struct ip_tunnel_info *ip_tun = tcf_tunnel_info(action);
+	struct nfp_flower_priv *priv = app->priv;
 	u32 tmp_set_ip_tun_type_index = 0;
 	/* Currently support one pre-tunnel so index is always 0. */
 	int pretun_idx = 0;
-	struct net *net;
 
-	if (ip_tun->options_len)
+	BUILD_BUG_ON(NFP_FL_TUNNEL_CSUM != TUNNEL_CSUM ||
+		     NFP_FL_TUNNEL_KEY	!= TUNNEL_KEY ||
+		     NFP_FL_TUNNEL_GENEVE_OPT != TUNNEL_GENEVE_OPT);
+	if (ip_tun->options_len &&
+	    (tun_type != NFP_FL_TUNNEL_GENEVE ||
+	    !(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE_OPT)))
 		return -EOPNOTSUPP;
 
-	net = dev_net(netdev);
-
 	set_tun->head.jump_id = NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL;
 	set_tun->head.len_lw = act_size >> NFP_FL_LW_SIZ;
 
@@ -254,7 +333,42 @@ nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun,
 
 	set_tun->tun_type_index = cpu_to_be32(tmp_set_ip_tun_type_index);
 	set_tun->tun_id = ip_tun->key.tun_id;
-	set_tun->ttl = net->ipv4.sysctl_ip_default_ttl;
+
+	if (ip_tun->key.ttl) {
+		set_tun->ttl = ip_tun->key.ttl;
+	} else {
+		struct net *net = dev_net(netdev);
+		struct flowi4 flow = {};
+		struct rtable *rt;
+		int err;
+
+		/* Do a route lookup to determine ttl - if fails then use
+		 * default. Note that CONFIG_INET is a requirement of
+		 * CONFIG_NET_SWITCHDEV so must be defined here.
+		 */
+		flow.daddr = ip_tun->key.u.ipv4.dst;
+		flow.flowi4_proto = IPPROTO_UDP;
+		rt = ip_route_output_key(net, &flow);
+		err = PTR_ERR_OR_ZERO(rt);
+		if (!err) {
+			set_tun->ttl = ip4_dst_hoplimit(&rt->dst);
+			ip_rt_put(rt);
+		} else {
+			set_tun->ttl = net->ipv4.sysctl_ip_default_ttl;
+		}
+	}
+
+	set_tun->tos = ip_tun->key.tos;
+
+	if (!(ip_tun->key.tun_flags & NFP_FL_TUNNEL_KEY) ||
+	    ip_tun->key.tun_flags & ~NFP_FL_SUPPORTED_IPV4_UDP_TUN_FLAGS)
+		return -EOPNOTSUPP;
+	set_tun->tun_flags = ip_tun->key.tun_flags;
+
+	if (tun_type == NFP_FL_TUNNEL_GENEVE) {
+		set_tun->tun_proto = htons(ETH_P_TEB);
+		set_tun->tun_len = ip_tun->options_len / 4;
+	}
 
 	/* Complete pre_tunnel action. */
 	pre_tun->ipv4_dst = ip_tun->key.u.ipv4.dst;
@@ -398,8 +512,27 @@ nfp_fl_set_tport(const struct tc_action *action, int idx, u32 off,
 	return 0;
 }
 
+static u32 nfp_fl_csum_l4_to_flag(u8 ip_proto)
+{
+	switch (ip_proto) {
+	case 0:
+		/* Filter doesn't force proto match,
+		 * both TCP and UDP will be updated if encountered
+		 */
+		return TCA_CSUM_UPDATE_FLAG_TCP | TCA_CSUM_UPDATE_FLAG_UDP;
+	case IPPROTO_TCP:
+		return TCA_CSUM_UPDATE_FLAG_TCP;
+	case IPPROTO_UDP:
+		return TCA_CSUM_UPDATE_FLAG_UDP;
+	default:
+		/* All other protocols will be ignored by FW */
+		return 0;
+	}
+}
+
 static int
-nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len)
+nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow,
+	     char *nfp_action, int *a_len, u32 *csum_updated)
 {
 	struct nfp_fl_set_ipv6_addr set_ip6_dst, set_ip6_src;
 	struct nfp_fl_set_ip4_addrs set_ip_addr;
@@ -409,6 +542,7 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len)
 	int idx, nkeys, err;
 	size_t act_size;
 	u32 offset, cmd;
+	u8 ip_proto = 0;
 
 	memset(&set_ip6_dst, 0, sizeof(set_ip6_dst));
 	memset(&set_ip6_src, 0, sizeof(set_ip6_src));
@@ -451,6 +585,15 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len)
 			return err;
 	}
 
+	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_dissector_key_basic *basic;
+
+		basic = skb_flow_dissector_target(flow->dissector,
+						  FLOW_DISSECTOR_KEY_BASIC,
+						  flow->key);
+		ip_proto = basic->ip_proto;
+	}
+
 	if (set_eth.head.len_lw) {
 		act_size = sizeof(set_eth);
 		memcpy(nfp_action, &set_eth, act_size);
@@ -459,6 +602,10 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len)
 		act_size = sizeof(set_ip_addr);
 		memcpy(nfp_action, &set_ip_addr, act_size);
 		*a_len += act_size;
+
+		/* Hardware will automatically fix IPv4 and TCP/UDP checksum. */
+		*csum_updated |= TCA_CSUM_UPDATE_FLAG_IPV4HDR |
+				nfp_fl_csum_l4_to_flag(ip_proto);
 	} else if (set_ip6_dst.head.len_lw && set_ip6_src.head.len_lw) {
 		/* TC compiles set src and dst IPv6 address as a single action,
 		 * the hardware requires this to be 2 separate actions.
@@ -471,18 +618,30 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len)
 		memcpy(&nfp_action[sizeof(set_ip6_src)], &set_ip6_dst,
 		       act_size);
 		*a_len += act_size;
+
+		/* Hardware will automatically fix TCP/UDP checksum. */
+		*csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
 	} else if (set_ip6_dst.head.len_lw) {
 		act_size = sizeof(set_ip6_dst);
 		memcpy(nfp_action, &set_ip6_dst, act_size);
 		*a_len += act_size;
+
+		/* Hardware will automatically fix TCP/UDP checksum. */
+		*csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
 	} else if (set_ip6_src.head.len_lw) {
 		act_size = sizeof(set_ip6_src);
 		memcpy(nfp_action, &set_ip6_src, act_size);
 		*a_len += act_size;
+
+		/* Hardware will automatically fix TCP/UDP checksum. */
+		*csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
 	} else if (set_tport.head.len_lw) {
 		act_size = sizeof(set_tport);
 		memcpy(nfp_action, &set_tport, act_size);
 		*a_len += act_size;
+
+		/* Hardware will automatically fix TCP/UDP checksum. */
+		*csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
 	}
 
 	return 0;
@@ -493,12 +652,18 @@ nfp_flower_output_action(struct nfp_app *app, const struct tc_action *a,
 			 struct nfp_fl_payload *nfp_fl, int *a_len,
 			 struct net_device *netdev, bool last,
 			 enum nfp_flower_tun_type *tun_type, int *tun_out_cnt,
-			 int *out_cnt)
+			 int *out_cnt, u32 *csum_updated)
 {
 	struct nfp_flower_priv *priv = app->priv;
 	struct nfp_fl_output *output;
 	int err, prelag_size;
 
+	/* If csum_updated has not been reset by now, it means HW will
+	 * incorrectly update csums when they are not requested.
+	 */
+	if (*csum_updated)
+		return -EOPNOTSUPP;
+
 	if (*a_len + sizeof(struct nfp_fl_output) > NFP_FL_MAX_A_SIZ)
 		return -EOPNOTSUPP;
 
@@ -529,10 +694,11 @@ nfp_flower_output_action(struct nfp_app *app, const struct tc_action *a,
 
 static int
 nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a,
+		       struct tc_cls_flower_offload *flow,
 		       struct nfp_fl_payload *nfp_fl, int *a_len,
 		       struct net_device *netdev,
 		       enum nfp_flower_tun_type *tun_type, int *tun_out_cnt,
-		       int *out_cnt)
+		       int *out_cnt, u32 *csum_updated)
 {
 	struct nfp_fl_set_ipv4_udp_tun *set_tun;
 	struct nfp_fl_pre_tunnel *pre_tun;
@@ -545,14 +711,14 @@ nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a,
 	} else if (is_tcf_mirred_egress_redirect(a)) {
 		err = nfp_flower_output_action(app, a, nfp_fl, a_len, netdev,
 					       true, tun_type, tun_out_cnt,
-					       out_cnt);
+					       out_cnt, csum_updated);
 		if (err)
 			return err;
 
 	} else if (is_tcf_mirred_egress_mirror(a)) {
 		err = nfp_flower_output_action(app, a, nfp_fl, a_len, netdev,
 					       false, tun_type, tun_out_cnt,
-					       out_cnt);
+					       out_cnt, csum_updated);
 		if (err)
 			return err;
 
@@ -592,9 +758,13 @@ nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a,
 		nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_NULL);
 		*a_len += sizeof(struct nfp_fl_pre_tunnel);
 
+		err = nfp_fl_push_geneve_options(nfp_fl, a_len, a);
+		if (err)
+			return err;
+
 		set_tun = (void *)&nfp_fl->action_data[*a_len];
-		err = nfp_fl_set_ipv4_udp_tun(set_tun, a, pre_tun, *tun_type,
-					      netdev);
+		err = nfp_fl_set_ipv4_udp_tun(app, set_tun, a, pre_tun,
+					      *tun_type, netdev);
 		if (err)
 			return err;
 		*a_len += sizeof(struct nfp_fl_set_ipv4_udp_tun);
@@ -602,8 +772,17 @@ nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a,
 		/* Tunnel decap is handled by default so accept action. */
 		return 0;
 	} else if (is_tcf_pedit(a)) {
-		if (nfp_fl_pedit(a, &nfp_fl->action_data[*a_len], a_len))
+		if (nfp_fl_pedit(a, flow, &nfp_fl->action_data[*a_len],
+				 a_len, csum_updated))
+			return -EOPNOTSUPP;
+	} else if (is_tcf_csum(a)) {
+		/* csum action requests recalc of something we have not fixed */
+		if (tcf_csum_update_flags(a) & ~*csum_updated)
 			return -EOPNOTSUPP;
+		/* If we will correctly fix the csum we can remove it from the
+		 * csum update list. Which will later be used to check support.
+		 */
+		*csum_updated &= ~tcf_csum_update_flags(a);
 	} else {
 		/* Currently we do not handle any other actions. */
 		return -EOPNOTSUPP;
@@ -620,6 +799,7 @@ int nfp_flower_compile_action(struct nfp_app *app,
 	int act_len, act_cnt, err, tun_out_cnt, out_cnt;
 	enum nfp_flower_tun_type tun_type;
 	const struct tc_action *a;
+	u32 csum_updated = 0;
 	LIST_HEAD(actions);
 
 	memset(nfp_flow->action_data, 0, NFP_FL_MAX_A_SIZ);
@@ -632,8 +812,9 @@ int nfp_flower_compile_action(struct nfp_app *app,
 
 	tcf_exts_to_list(flow->exts, &actions);
 	list_for_each_entry(a, &actions, list) {
-		err = nfp_flower_loop_action(app, a, nfp_flow, &act_len, netdev,
-					     &tun_type, &tun_out_cnt, &out_cnt);
+		err = nfp_flower_loop_action(app, a, flow, nfp_flow, &act_len,
+					     netdev, &tun_type, &tun_out_cnt,
+					     &out_cnt, &csum_updated);
 		if (err)
 			return err;
 		act_cnt++;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index 4a7f3510a296..325954b829c8 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -37,6 +37,7 @@
 #include <linux/bitfield.h>
 #include <linux/skbuff.h>
 #include <linux/types.h>
+#include <net/geneve.h>
 
 #include "../nfp_app.h"
 #include "../nfpcore/nfp_cpp.h"
@@ -51,6 +52,7 @@
 #define NFP_FLOWER_LAYER_VXLAN		BIT(7)
 
 #define NFP_FLOWER_LAYER2_GENEVE	BIT(5)
+#define NFP_FLOWER_LAYER2_GENEVE_OP	BIT(6)
 
 #define NFP_FLOWER_MASK_VLAN_PRIO	GENMASK(15, 13)
 #define NFP_FLOWER_MASK_VLAN_CFI	BIT(12)
@@ -81,6 +83,11 @@
 #define NFP_FL_MAX_A_SIZ		1216
 #define NFP_FL_LW_SIZ			2
 
+/* Maximum allowed geneve options */
+#define NFP_FL_MAX_GENEVE_OPT_ACT	32
+#define NFP_FL_MAX_GENEVE_OPT_CNT	64
+#define NFP_FL_MAX_GENEVE_OPT_KEY	32
+
 /* Action opcodes */
 #define NFP_FL_ACTION_OPCODE_OUTPUT		0
 #define NFP_FL_ACTION_OPCODE_PUSH_VLAN		1
@@ -94,6 +101,7 @@
 #define NFP_FL_ACTION_OPCODE_SET_TCP		15
 #define NFP_FL_ACTION_OPCODE_PRE_LAG		16
 #define NFP_FL_ACTION_OPCODE_PRE_TUNNEL		17
+#define NFP_FL_ACTION_OPCODE_PUSH_GENEVE	26
 #define NFP_FL_ACTION_OPCODE_NUM		32
 
 #define NFP_FL_OUT_FLAGS_LAST		BIT(15)
@@ -203,10 +211,22 @@ struct nfp_fl_set_ipv4_udp_tun {
 	__be16 reserved;
 	__be64 tun_id __packed;
 	__be32 tun_type_index;
-	__be16 reserved2;
+	__be16 tun_flags;
 	u8 ttl;
-	u8 reserved3;
-	__be32 extra[2];
+	u8 tos;
+	__be32 extra;
+	u8 tun_len;
+	u8 res2;
+	__be16 tun_proto;
+};
+
+struct nfp_fl_push_geneve {
+	struct nfp_fl_act_head head;
+	__be16 reserved;
+	__be16 class;
+	u8 type;
+	u8 length;
+	u8 opt_data[];
 };
 
 /* Metadata with L2 (1W/4B)
@@ -346,7 +366,7 @@ struct nfp_flower_ipv6 {
  * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
  * |                         ipv4_addr_dst                         |
  * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
- * |                            Reserved                           |
+ * |           Reserved            |      tos      |      ttl      |
  * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
  * |                            Reserved                           |
  * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
@@ -356,10 +376,17 @@ struct nfp_flower_ipv6 {
 struct nfp_flower_ipv4_udp_tun {
 	__be32 ip_src;
 	__be32 ip_dst;
-	__be32 reserved[2];
+	__be16 reserved1;
+	u8 tos;
+	u8 ttl;
+	__be32 reserved2;
 	__be32 tun_id;
 };
 
+struct nfp_flower_geneve_options {
+	u8 data[NFP_FL_MAX_GENEVE_OPT_KEY];
+};
+
 #define NFP_FL_TUN_VNI_OFFSET 8
 
 /* The base header for a control message packet.
diff --git a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
index 0c4c957717ea..bf10598f66ae 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
@@ -564,8 +564,9 @@ nfp_fl_lag_changeupper_event(struct nfp_fl_lag *lag,
 	if (lag_upper_info &&
 	    lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_ACTIVEBACKUP &&
 	    (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH ||
-	    (lag_upper_info->hash_type != NETDEV_LAG_HASH_L34 &&
-	    lag_upper_info->hash_type != NETDEV_LAG_HASH_E34))) {
+	     (lag_upper_info->hash_type != NETDEV_LAG_HASH_L34 &&
+	      lag_upper_info->hash_type != NETDEV_LAG_HASH_E34 &&
+	      lag_upper_info->hash_type != NETDEV_LAG_HASH_UNKNOWN))) {
 		can_offload = false;
 		nfp_flower_cmsg_warn(priv->app,
 				     "Unable to offload tx_type %u hash %u\n",
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index bbe5764d26cb..85f8209bf007 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -69,11 +69,12 @@ struct nfp_app;
 /* Extra features bitmap. */
 #define NFP_FL_FEATS_GENEVE		BIT(0)
 #define NFP_FL_NBI_MTU_SETTING		BIT(1)
+#define NFP_FL_FEATS_GENEVE_OPT		BIT(2)
 #define NFP_FL_FEATS_LAG		BIT(31)
 
 struct nfp_fl_mask_id {
 	struct circ_buf mask_id_free_list;
-	struct timespec64 *last_used;
+	ktime_t *last_used;
 	u8 init_unallocated;
 };
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c
index 84f7a5dbea9d..a0c72f277faa 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/match.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/match.c
@@ -262,6 +262,21 @@ nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *frame,
 	nfp_flower_compile_ip_ext(&frame->ip_ext, flow, mask_version);
 }
 
+static int
+nfp_flower_compile_geneve_opt(void *key_buf, struct tc_cls_flower_offload *flow,
+			      bool mask_version)
+{
+	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
+	struct flow_dissector_key_enc_opts *opts;
+
+	opts = skb_flow_dissector_target(flow->dissector,
+					 FLOW_DISSECTOR_KEY_ENC_OPTS,
+					 target);
+	memcpy(key_buf, opts->data, opts->len);
+
+	return 0;
+}
+
 static void
 nfp_flower_compile_ipv4_udp_tun(struct nfp_flower_ipv4_udp_tun *frame,
 				struct tc_cls_flower_offload *flow,
@@ -270,6 +285,7 @@ nfp_flower_compile_ipv4_udp_tun(struct nfp_flower_ipv4_udp_tun *frame,
 	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
 	struct flow_dissector_key_ipv4_addrs *tun_ips;
 	struct flow_dissector_key_keyid *vni;
+	struct flow_dissector_key_ip *ip;
 
 	memset(frame, 0, sizeof(struct nfp_flower_ipv4_udp_tun));
 
@@ -293,6 +309,14 @@ nfp_flower_compile_ipv4_udp_tun(struct nfp_flower_ipv4_udp_tun *frame,
 		frame->ip_src = tun_ips->src;
 		frame->ip_dst = tun_ips->dst;
 	}
+
+	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_ENC_IP)) {
+		ip = skb_flow_dissector_target(flow->dissector,
+					       FLOW_DISSECTOR_KEY_ENC_IP,
+					       target);
+		frame->tos = ip->tos;
+		frame->ttl = ip->ttl;
+	}
 }
 
 int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
@@ -415,6 +439,16 @@ int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
 			nfp_flow->nfp_tun_ipv4_addr = tun_dst;
 			nfp_tunnel_add_ipv4_off(netdev_repr->app, tun_dst);
 		}
+
+		if (key_ls->key_layer_two & NFP_FLOWER_LAYER2_GENEVE_OP) {
+			err = nfp_flower_compile_geneve_opt(ext, flow, false);
+			if (err)
+				return err;
+
+			err = nfp_flower_compile_geneve_opt(msk, flow, true);
+			if (err)
+				return err;
+		}
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
index 93fb809f50d1..c098730544b7 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
@@ -158,7 +158,6 @@ static int nfp_release_mask_id(struct nfp_app *app, u8 mask_id)
 {
 	struct nfp_flower_priv *priv = app->priv;
 	struct circ_buf *ring;
-	struct timespec64 now;
 
 	ring = &priv->mask_ids.mask_id_free_list;
 	/* Checking if buffer is full. */
@@ -169,8 +168,7 @@ static int nfp_release_mask_id(struct nfp_app *app, u8 mask_id)
 	ring->head = (ring->head + NFP_FLOWER_MASK_ELEMENT_RS) %
 		     (NFP_FLOWER_MASK_ENTRY_RS * NFP_FLOWER_MASK_ELEMENT_RS);
 
-	getnstimeofday64(&now);
-	priv->mask_ids.last_used[mask_id] = now;
+	priv->mask_ids.last_used[mask_id] = ktime_get();
 
 	return 0;
 }
@@ -178,7 +176,7 @@ static int nfp_release_mask_id(struct nfp_app *app, u8 mask_id)
 static int nfp_mask_alloc(struct nfp_app *app, u8 *mask_id)
 {
 	struct nfp_flower_priv *priv = app->priv;
-	struct timespec64 delta, now;
+	ktime_t reuse_timeout;
 	struct circ_buf *ring;
 	u8 temp_id, freed_id;
 
@@ -198,10 +196,10 @@ static int nfp_mask_alloc(struct nfp_app *app, u8 *mask_id)
 	memcpy(&temp_id, &ring->buf[ring->tail], NFP_FLOWER_MASK_ELEMENT_RS);
 	*mask_id = temp_id;
 
-	getnstimeofday64(&now);
-	delta = timespec64_sub(now, priv->mask_ids.last_used[*mask_id]);
+	reuse_timeout = ktime_add_ns(priv->mask_ids.last_used[*mask_id],
+				     NFP_FL_MASK_REUSE_TIME_NS);
 
-	if (timespec64_to_ns(&delta) < NFP_FL_MASK_REUSE_TIME_NS)
+	if (ktime_before(ktime_get(), reuse_timeout))
 		goto err_not_found;
 
 	memcpy(&ring->buf[ring->tail], &freed_id, NFP_FLOWER_MASK_ELEMENT_RS);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 525057bee0ed..2edab01c3beb 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -66,6 +66,8 @@
 	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \
 	 BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
 	 BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | \
+	 BIT(FLOW_DISSECTOR_KEY_ENC_OPTS) | \
+	 BIT(FLOW_DISSECTOR_KEY_ENC_IP) | \
 	 BIT(FLOW_DISSECTOR_KEY_MPLS) | \
 	 BIT(FLOW_DISSECTOR_KEY_IP))
 
@@ -74,7 +76,9 @@
 	 BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | \
 	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \
 	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \
-	 BIT(FLOW_DISSECTOR_KEY_ENC_PORTS))
+	 BIT(FLOW_DISSECTOR_KEY_ENC_OPTS) | \
+	 BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | \
+	 BIT(FLOW_DISSECTOR_KEY_ENC_IP))
 
 #define NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R \
 	(BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
@@ -139,6 +143,21 @@ static bool nfp_flower_check_higher_than_mac(struct tc_cls_flower_offload *f)
 }
 
 static int
+nfp_flower_calc_opt_layer(struct flow_dissector_key_enc_opts *enc_opts,
+			  u32 *key_layer_two, int *key_size)
+{
+	if (enc_opts->len > NFP_FL_MAX_GENEVE_OPT_KEY)
+		return -EOPNOTSUPP;
+
+	if (enc_opts->len > 0) {
+		*key_layer_two |= NFP_FLOWER_LAYER2_GENEVE_OP;
+		*key_size += sizeof(struct nfp_flower_geneve_options);
+	}
+
+	return 0;
+}
+
+static int
 nfp_flower_calculate_key_layers(struct nfp_app *app,
 				struct nfp_fl_key_ls *ret_key_ls,
 				struct tc_cls_flower_offload *flow,
@@ -151,6 +170,7 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 	u32 key_layer_two;
 	u8 key_layer;
 	int key_size;
+	int err;
 
 	if (flow->dissector->used_keys & ~NFP_FLOWER_WHITELIST_DISSECTOR)
 		return -EOPNOTSUPP;
@@ -176,6 +196,7 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 			       FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
 		struct flow_dissector_key_ipv4_addrs *mask_ipv4 = NULL;
 		struct flow_dissector_key_ports *mask_enc_ports = NULL;
+		struct flow_dissector_key_enc_opts *enc_op = NULL;
 		struct flow_dissector_key_ports *enc_ports = NULL;
 		struct flow_dissector_key_control *mask_enc_ctl =
 			skb_flow_dissector_target(flow->dissector,
@@ -212,11 +233,21 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 		if (mask_enc_ports->dst != cpu_to_be16(~0))
 			return -EOPNOTSUPP;
 
+		if (dissector_uses_key(flow->dissector,
+				       FLOW_DISSECTOR_KEY_ENC_OPTS)) {
+			enc_op = skb_flow_dissector_target(flow->dissector,
+							   FLOW_DISSECTOR_KEY_ENC_OPTS,
+							   flow->key);
+		}
+
 		switch (enc_ports->dst) {
 		case htons(NFP_FL_VXLAN_PORT):
 			*tun_type = NFP_FL_TUNNEL_VXLAN;
 			key_layer |= NFP_FLOWER_LAYER_VXLAN;
 			key_size += sizeof(struct nfp_flower_ipv4_udp_tun);
+
+			if (enc_op)
+				return -EOPNOTSUPP;
 			break;
 		case htons(NFP_FL_GENEVE_PORT):
 			if (!(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE))
@@ -226,6 +257,15 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 			key_size += sizeof(struct nfp_flower_ext_meta);
 			key_layer_two |= NFP_FLOWER_LAYER2_GENEVE;
 			key_size += sizeof(struct nfp_flower_ipv4_udp_tun);
+
+			if (!enc_op)
+				break;
+			if (!(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE_OPT))
+				return -EOPNOTSUPP;
+			err = nfp_flower_calc_opt_layer(enc_op, &key_layer_two,
+							&key_size);
+			if (err)
+				return err;
 			break;
 		default:
 			return -EOPNOTSUPP;
@@ -584,9 +624,9 @@ nfp_flower_repr_offload(struct nfp_app *app, struct net_device *netdev,
 		return nfp_flower_del_offload(app, netdev, flower, egress);
 	case TC_CLSFLOWER_STATS:
 		return nfp_flower_get_stats(app, netdev, flower, egress);
+	default:
+		return -EOPNOTSUPP;
 	}
-
-	return -EOPNOTSUPP;
 }
 
 int nfp_flower_setup_tc_egress_cb(enum tc_setup_type type, void *type_data,
@@ -631,14 +671,11 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev,
 	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		return -EOPNOTSUPP;
 
-	if (tcf_block_shared(f->block))
-		return -EOPNOTSUPP;
-
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block,
 					     nfp_flower_setup_tc_block_cb,
-					     repr, repr);
+					     repr, repr, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block,
 					nfp_flower_setup_tc_block_cb,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.c b/drivers/net/ethernet/netronome/nfp/nfp_app.c
index f28b244f4ee7..8607d09ab732 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app.c
@@ -86,6 +86,23 @@ const char *nfp_app_mip_name(struct nfp_app *app)
 	return nfp_mip_name(app->pf->mip);
 }
 
+int nfp_app_ndo_init(struct net_device *netdev)
+{
+	struct nfp_app *app = nfp_app_from_netdev(netdev);
+
+	if (!app || !app->type->ndo_init)
+		return 0;
+	return app->type->ndo_init(app, netdev);
+}
+
+void nfp_app_ndo_uninit(struct net_device *netdev)
+{
+	struct nfp_app *app = nfp_app_from_netdev(netdev);
+
+	if (app && app->type->ndo_uninit)
+		app->type->ndo_uninit(app, netdev);
+}
+
 u64 *nfp_app_port_get_stats(struct nfp_port *port, u64 *data)
 {
 	if (!port || !port->app || !port->app->type->port_get_stats)
@@ -155,6 +172,8 @@ struct nfp_app *nfp_app_alloc(struct nfp_pf *pf, enum nfp_app_id id)
 
 	if (WARN_ON(!apps[id]->name || !apps[id]->vnic_alloc))
 		return ERR_PTR(-EINVAL);
+	if (WARN_ON(!apps[id]->ctrl_msg_rx && apps[id]->ctrl_msg_rx_raw))
+		return ERR_PTR(-EINVAL);
 
 	app = kzalloc(sizeof(*app), GFP_KERNEL);
 	if (!app)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h
index ee74caacb015..4e1eb3395648 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h
@@ -78,6 +78,8 @@ extern const struct nfp_app_type app_abm;
  * @init:	perform basic app checks and init
  * @clean:	clean app state
  * @extra_cap:	extra capabilities string
+ * @ndo_init:	vNIC and repr netdev .ndo_init
+ * @ndo_uninit:	vNIC and repr netdev .ndo_unint
  * @vnic_alloc:	allocate vNICs (assign port types, etc.)
  * @vnic_free:	free up app's vNIC state
  * @vnic_init:	vNIC netdev was registered
@@ -96,6 +98,7 @@ extern const struct nfp_app_type app_abm;
  * @start:	start application logic
  * @stop:	stop application logic
  * @ctrl_msg_rx:    control message handler
+ * @ctrl_msg_rx_raw:	handler for control messages from data queues
  * @setup_tc:	setup TC ndo
  * @bpf:	BPF ndo offload-related calls
  * @xdp_offload:    offload an XDP program
@@ -117,6 +120,9 @@ struct nfp_app_type {
 
 	const char *(*extra_cap)(struct nfp_app *app, struct nfp_net *nn);
 
+	int (*ndo_init)(struct nfp_app *app, struct net_device *netdev);
+	void (*ndo_uninit)(struct nfp_app *app, struct net_device *netdev);
+
 	int (*vnic_alloc)(struct nfp_app *app, struct nfp_net *nn,
 			  unsigned int id);
 	void (*vnic_free)(struct nfp_app *app, struct nfp_net *nn);
@@ -145,6 +151,8 @@ struct nfp_app_type {
 	void (*stop)(struct nfp_app *app);
 
 	void (*ctrl_msg_rx)(struct nfp_app *app, struct sk_buff *skb);
+	void (*ctrl_msg_rx_raw)(struct nfp_app *app, const void *data,
+				unsigned int len);
 
 	int (*setup_tc)(struct nfp_app *app, struct net_device *netdev,
 			enum tc_setup_type type, void *type_data);
@@ -200,6 +208,9 @@ static inline void nfp_app_clean(struct nfp_app *app)
 		app->type->clean(app);
 }
 
+int nfp_app_ndo_init(struct net_device *netdev);
+void nfp_app_ndo_uninit(struct net_device *netdev);
+
 static inline int nfp_app_vnic_alloc(struct nfp_app *app, struct nfp_net *nn,
 				     unsigned int id)
 {
@@ -310,6 +321,11 @@ static inline bool nfp_app_ctrl_has_meta(struct nfp_app *app)
 	return app->type->ctrl_has_meta;
 }
 
+static inline bool nfp_app_ctrl_uses_data_vnics(struct nfp_app *app)
+{
+	return app && app->type->ctrl_msg_rx_raw;
+}
+
 static inline const char *nfp_app_extra_cap(struct nfp_app *app,
 					    struct nfp_net *nn)
 {
@@ -373,6 +389,16 @@ static inline void nfp_app_ctrl_rx(struct nfp_app *app, struct sk_buff *skb)
 	app->type->ctrl_msg_rx(app, skb);
 }
 
+static inline void
+nfp_app_ctrl_rx_raw(struct nfp_app *app, const void *data, unsigned int len)
+{
+	if (!app || !app->type->ctrl_msg_rx_raw)
+		return;
+
+	trace_devlink_hwmsg(priv_to_devlink(app->pf), true, 0, data, len);
+	app->type->ctrl_msg_rx_raw(app, data, len);
+}
+
 static inline int nfp_app_eswitch_mode_get(struct nfp_app *app, u16 *mode)
 {
 	if (!app->type->eswitch_mode_get)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.h b/drivers/net/ethernet/netronome/nfp/nfp_asm.h
index f6677bc9875a..fad0e62a910c 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_asm.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.h
@@ -93,6 +93,7 @@ enum br_mask {
 	BR_BNE = 0x01,
 	BR_BMI = 0x02,
 	BR_BHS = 0x04,
+	BR_BCC = 0x05,
 	BR_BLO = 0x05,
 	BR_BGE = 0x08,
 	BR_BLT = 0x09,
@@ -426,4 +427,32 @@ static inline u32 nfp_get_ind_csr_ctx_ptr_offs(u32 read_offset)
 	return (read_offset & ~NFP_IND_ME_CTX_PTR_BASE_MASK) | NFP_CSR_CTX_PTR;
 }
 
+enum mul_type {
+	MUL_TYPE_START		= 0x00,
+	MUL_TYPE_STEP_24x8	= 0x01,
+	MUL_TYPE_STEP_16x16	= 0x02,
+	MUL_TYPE_STEP_32x32	= 0x03,
+};
+
+enum mul_step {
+	MUL_STEP_1		= 0x00,
+	MUL_STEP_NONE		= MUL_STEP_1,
+	MUL_STEP_2		= 0x01,
+	MUL_STEP_3		= 0x02,
+	MUL_STEP_4		= 0x03,
+	MUL_LAST		= 0x04,
+	MUL_LAST_2		= 0x05,
+};
+
+#define OP_MUL_BASE		0x0f800000000ULL
+#define OP_MUL_A_SRC		0x000000003ffULL
+#define OP_MUL_B_SRC		0x000000ffc00ULL
+#define OP_MUL_STEP		0x00000700000ULL
+#define OP_MUL_DST_AB		0x00000800000ULL
+#define OP_MUL_SW		0x00040000000ULL
+#define OP_MUL_TYPE		0x00180000000ULL
+#define OP_MUL_WR_AB		0x20000000000ULL
+#define OP_MUL_SRC_LMEXTN	0x40000000000ULL
+#define OP_MUL_DST_LMEXTN	0x80000000000ULL
+
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c
index 152283d7e59c..4a540c5e27fe 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c
@@ -236,16 +236,20 @@ static int nfp_pcie_sriov_read_nfd_limit(struct nfp_pf *pf)
 	int err;
 
 	pf->limit_vfs = nfp_rtsym_read_le(pf->rtbl, "nfd_vf_cfg_max_vfs", &err);
-	if (!err)
-		return pci_sriov_set_totalvfs(pf->pdev, pf->limit_vfs);
+	if (err) {
+		/* For backwards compatibility if symbol not found allow all */
+		pf->limit_vfs = ~0;
+		if (err == -ENOENT)
+			return 0;
 
-	pf->limit_vfs = ~0;
-	/* Allow any setting for backwards compatibility if symbol not found */
-	if (err == -ENOENT)
-		return 0;
+		nfp_warn(pf->cpp, "Warning: VF limit read failed: %d\n", err);
+		return err;
+	}
 
-	nfp_warn(pf->cpp, "Warning: VF limit read failed: %d\n", err);
-	return err;
+	err = pci_sriov_set_totalvfs(pf->pdev, pf->limit_vfs);
+	if (err)
+		nfp_warn(pf->cpp, "Failed to set VF count in sysfs: %d\n", err);
+	return 0;
 }
 
 static int nfp_pcie_sriov_enable(struct pci_dev *pdev, int num_vfs)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index 2a71a9ffd095..439e6ffe2f05 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -250,7 +250,7 @@ struct nfp_net_tx_ring {
 	struct nfp_net_tx_desc *txds;
 
 	dma_addr_t dma;
-	unsigned int size;
+	size_t size;
 	bool is_xdp;
 } ____cacheline_aligned;
 
@@ -350,9 +350,9 @@ struct nfp_net_rx_buf {
  * @qcp_fl:     Pointer to base of the QCP freelist queue
  * @rxbufs:     Array of transmitted FL/RX buffers
  * @rxds:       Virtual address of FL/RX ring in host memory
+ * @xdp_rxq:    RX-ring info avail for XDP
  * @dma:        DMA address of the FL/RX ring
  * @size:       Size, in bytes, of the FL/RX ring (needed to free)
- * @xdp_rxq:    RX-ring info avail for XDP
  */
 struct nfp_net_rx_ring {
 	struct nfp_net_r_vector *r_vec;
@@ -364,14 +364,15 @@ struct nfp_net_rx_ring {
 	u32 idx;
 
 	int fl_qcidx;
-	unsigned int size;
 	u8 __iomem *qcp_fl;
 
 	struct nfp_net_rx_buf *rxbufs;
 	struct nfp_net_rx_desc *rxds;
 
-	dma_addr_t dma;
 	struct xdp_rxq_info xdp_rxq;
+
+	dma_addr_t dma;
+	size_t size;
 } ____cacheline_aligned;
 
 /**
@@ -485,7 +486,6 @@ struct nfp_stat_pair {
  * @dev:		Backpointer to struct device
  * @netdev:		Backpointer to net_device structure
  * @is_vf:		Is the driver attached to a VF?
- * @bpf_offload_xdp:	Offloaded BPF program is XDP
  * @chained_metadata_format:  Firemware will use new metadata format
  * @rx_dma_dir:		Mapping direction for RX buffers
  * @rx_dma_off:		Offset at which DMA packets (for XDP headroom)
@@ -510,7 +510,6 @@ struct nfp_net_dp {
 	struct net_device *netdev;
 
 	u8 is_vf:1;
-	u8 bpf_offload_xdp:1;
 	u8 chained_metadata_format:1;
 
 	u8 rx_dma_dir;
@@ -553,8 +552,8 @@ struct nfp_net_dp {
  * @rss_cfg:            RSS configuration
  * @rss_key:            RSS secret key
  * @rss_itbl:           RSS indirection table
- * @xdp_flags:		Flags with which XDP prog was loaded
- * @xdp_prog:		XDP prog (for ctrl path, both DRV and HW modes)
+ * @xdp:		Information about the driver XDP program
+ * @xdp_hw:		Information about the HW XDP program
  * @max_r_vecs:		Number of allocated interrupt vectors for RX/TX
  * @max_tx_rings:       Maximum number of TX rings supported by the Firmware
  * @max_rx_rings:       Maximum number of RX rings supported by the Firmware
@@ -610,8 +609,8 @@ struct nfp_net {
 	u8 rss_key[NFP_NET_CFG_RSS_KEY_SZ];
 	u8 rss_itbl[NFP_NET_CFG_RSS_ITBL_SZ];
 
-	u32 xdp_flags;
-	struct bpf_prog *xdp_prog;
+	struct xdp_attachment_info xdp;
+	struct xdp_attachment_info xdp_hw;
 
 	unsigned int max_tx_rings;
 	unsigned int max_rx_rings;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index d4c27f849f9b..a8b9fbab5f73 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -53,6 +53,8 @@
 #include <linux/interrupt.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/mm.h>
+#include <linux/overflow.h>
 #include <linux/page_ref.h>
 #include <linux/pci.h>
 #include <linux/pci_regs.h>
@@ -945,11 +947,10 @@ err_free:
 
 /**
  * nfp_net_tx_complete() - Handled completed TX packets
- * @tx_ring:   TX ring structure
- *
- * Return: Number of completed TX descriptors
+ * @tx_ring:	TX ring structure
+ * @budget:	NAPI budget (only used as bool to determine if in NAPI context)
  */
-static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
+static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring, int budget)
 {
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
 	struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
@@ -999,7 +1000,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 
 		/* check for last gather fragment */
 		if (fidx == nr_frags - 1)
-			dev_consume_skb_any(skb);
+			napi_consume_skb(skb, budget);
 
 		tx_ring->txbufs[idx].dma_addr = 0;
 		tx_ring->txbufs[idx].skb = NULL;
@@ -1077,7 +1078,7 @@ static bool nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring)
  * @dp:		NFP Net data path struct
  * @tx_ring:	TX ring structure
  *
- * Assumes that the device is stopped
+ * Assumes that the device is stopped, must be idempotent.
  */
 static void
 nfp_net_tx_ring_reset(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring)
@@ -1119,7 +1120,7 @@ nfp_net_tx_ring_reset(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring)
 		tx_ring->rd_p++;
 	}
 
-	memset(tx_ring->txds, 0, sizeof(*tx_ring->txds) * tx_ring->cnt);
+	memset(tx_ring->txds, 0, tx_ring->size);
 	tx_ring->wr_p = 0;
 	tx_ring->rd_p = 0;
 	tx_ring->qcp_rd_p = 0;
@@ -1279,13 +1280,18 @@ static void nfp_net_rx_give_one(const struct nfp_net_dp *dp,
  * nfp_net_rx_ring_reset() - Reflect in SW state of freelist after disable
  * @rx_ring:	RX ring structure
  *
- * Warning: Do *not* call if ring buffers were never put on the FW freelist
- *	    (i.e. device was not enabled)!
+ * Assumes that the device is stopped, must be idempotent.
  */
 static void nfp_net_rx_ring_reset(struct nfp_net_rx_ring *rx_ring)
 {
 	unsigned int wr_idx, last_idx;
 
+	/* wr_p == rd_p means ring was never fed FL bufs.  RX rings are always
+	 * kept at cnt - 1 FL bufs.
+	 */
+	if (rx_ring->wr_p == 0 && rx_ring->rd_p == 0)
+		return;
+
 	/* Move the empty entry to the end of the list */
 	wr_idx = D_IDX(rx_ring, rx_ring->wr_p);
 	last_idx = rx_ring->cnt - 1;
@@ -1294,7 +1300,7 @@ static void nfp_net_rx_ring_reset(struct nfp_net_rx_ring *rx_ring)
 	rx_ring->rxbufs[last_idx].dma_addr = 0;
 	rx_ring->rxbufs[last_idx].frag = NULL;
 
-	memset(rx_ring->rxds, 0, sizeof(*rx_ring->rxds) * rx_ring->cnt);
+	memset(rx_ring->rxds, 0, rx_ring->size);
 	rx_ring->wr_p = 0;
 	rx_ring->rd_p = 0;
 }
@@ -1709,8 +1715,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 			}
 		}
 
-		if (xdp_prog && !(rxd->rxd.flags & PCIE_DESC_RX_BPF &&
-				  dp->bpf_offload_xdp) && !meta.portid) {
+		if (xdp_prog && !meta.portid) {
 			void *orig_data = rxbuf->frag + pkt_off;
 			unsigned int dma_off;
 			int act;
@@ -1752,6 +1757,29 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 			}
 		}
 
+		if (likely(!meta.portid)) {
+			netdev = dp->netdev;
+		} else if (meta.portid == NFP_META_PORT_ID_CTRL) {
+			struct nfp_net *nn = netdev_priv(dp->netdev);
+
+			nfp_app_ctrl_rx_raw(nn->app, rxbuf->frag + pkt_off,
+					    pkt_len);
+			nfp_net_rx_give_one(dp, rx_ring, rxbuf->frag,
+					    rxbuf->dma_addr);
+			continue;
+		} else {
+			struct nfp_net *nn;
+
+			nn = netdev_priv(dp->netdev);
+			netdev = nfp_app_repr_get(nn->app, meta.portid);
+			if (unlikely(!netdev)) {
+				nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf,
+						NULL);
+				continue;
+			}
+			nfp_repr_inc_rx_stats(netdev, pkt_len);
+		}
+
 		skb = build_skb(rxbuf->frag, true_bufsz);
 		if (unlikely(!skb)) {
 			nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, NULL);
@@ -1767,20 +1795,6 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 
 		nfp_net_rx_give_one(dp, rx_ring, new_frag, new_dma_addr);
 
-		if (likely(!meta.portid)) {
-			netdev = dp->netdev;
-		} else {
-			struct nfp_net *nn;
-
-			nn = netdev_priv(dp->netdev);
-			netdev = nfp_app_repr_get(nn->app, meta.portid);
-			if (unlikely(!netdev)) {
-				nfp_net_rx_drop(dp, r_vec, rx_ring, NULL, skb);
-				continue;
-			}
-			nfp_repr_inc_rx_stats(netdev, pkt_len);
-		}
-
 		skb_reserve(skb, pkt_off);
 		skb_put(skb, pkt_len);
 
@@ -1828,7 +1842,7 @@ static int nfp_net_poll(struct napi_struct *napi, int budget)
 	unsigned int pkts_polled = 0;
 
 	if (r_vec->tx_ring)
-		nfp_net_tx_complete(r_vec->tx_ring);
+		nfp_net_tx_complete(r_vec->tx_ring, budget);
 	if (r_vec->rx_ring)
 		pkts_polled = nfp_net_rx(r_vec->rx_ring, budget);
 
@@ -2062,7 +2076,7 @@ static void nfp_ctrl_poll(unsigned long arg)
 	struct nfp_net_r_vector *r_vec = (void *)arg;
 
 	spin_lock_bh(&r_vec->lock);
-	nfp_net_tx_complete(r_vec->tx_ring);
+	nfp_net_tx_complete(r_vec->tx_ring, 0);
 	__nfp_ctrl_tx_queued(r_vec);
 	spin_unlock_bh(&r_vec->lock);
 
@@ -2121,7 +2135,7 @@ static void nfp_net_tx_ring_free(struct nfp_net_tx_ring *tx_ring)
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
 	struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
 
-	kfree(tx_ring->txbufs);
+	kvfree(tx_ring->txbufs);
 
 	if (tx_ring->txds)
 		dma_free_coherent(dp->dev, tx_ring->size,
@@ -2145,18 +2159,17 @@ static int
 nfp_net_tx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring)
 {
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
-	int sz;
 
 	tx_ring->cnt = dp->txd_cnt;
 
-	tx_ring->size = sizeof(*tx_ring->txds) * tx_ring->cnt;
+	tx_ring->size = array_size(tx_ring->cnt, sizeof(*tx_ring->txds));
 	tx_ring->txds = dma_zalloc_coherent(dp->dev, tx_ring->size,
 					    &tx_ring->dma, GFP_KERNEL);
 	if (!tx_ring->txds)
 		goto err_alloc;
 
-	sz = sizeof(*tx_ring->txbufs) * tx_ring->cnt;
-	tx_ring->txbufs = kzalloc(sz, GFP_KERNEL);
+	tx_ring->txbufs = kvcalloc(tx_ring->cnt, sizeof(*tx_ring->txbufs),
+				   GFP_KERNEL);
 	if (!tx_ring->txbufs)
 		goto err_alloc;
 
@@ -2270,7 +2283,7 @@ static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring)
 
 	if (dp->netdev)
 		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
-	kfree(rx_ring->rxbufs);
+	kvfree(rx_ring->rxbufs);
 
 	if (rx_ring->rxds)
 		dma_free_coherent(dp->dev, rx_ring->size,
@@ -2293,7 +2306,7 @@ static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring)
 static int
 nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring)
 {
-	int sz, err;
+	int err;
 
 	if (dp->netdev) {
 		err = xdp_rxq_info_reg(&rx_ring->xdp_rxq, dp->netdev,
@@ -2303,14 +2316,14 @@ nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring)
 	}
 
 	rx_ring->cnt = dp->rxd_cnt;
-	rx_ring->size = sizeof(*rx_ring->rxds) * rx_ring->cnt;
+	rx_ring->size = array_size(rx_ring->cnt, sizeof(*rx_ring->rxds));
 	rx_ring->rxds = dma_zalloc_coherent(dp->dev, rx_ring->size,
 					    &rx_ring->dma, GFP_KERNEL);
 	if (!rx_ring->rxds)
 		goto err_alloc;
 
-	sz = sizeof(*rx_ring->rxbufs) * rx_ring->cnt;
-	rx_ring->rxbufs = kzalloc(sz, GFP_KERNEL);
+	rx_ring->rxbufs = kvcalloc(rx_ring->cnt, sizeof(*rx_ring->rxbufs),
+				   GFP_KERNEL);
 	if (!rx_ring->rxbufs)
 		goto err_alloc;
 
@@ -2508,6 +2521,8 @@ static void nfp_net_vec_clear_ring_data(struct nfp_net *nn, unsigned int idx)
 /**
  * nfp_net_clear_config_and_disable() - Clear control BAR and disable NFP
  * @nn:      NFP Net device to reconfigure
+ *
+ * Warning: must be fully idempotent.
  */
 static void nfp_net_clear_config_and_disable(struct nfp_net *nn)
 {
@@ -3115,6 +3130,21 @@ nfp_net_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid)
 	return nfp_net_reconfig_mbox(nn, NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_KILL);
 }
 
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void nfp_net_netpoll(struct net_device *netdev)
+{
+	struct nfp_net *nn = netdev_priv(netdev);
+	int i;
+
+	/* nfp_net's NAPIs are statically allocated so even if there is a race
+	 * with reconfig path this will simply try to schedule some disabled
+	 * NAPI instances.
+	 */
+	for (i = 0; i < nn->dp.num_stack_tx_rings; i++)
+		napi_schedule_irqoff(&nn->r_vecs[i].napi);
+}
+#endif
+
 static void nfp_net_stat64(struct net_device *netdev,
 			   struct rtnl_link_stats64 *stats)
 {
@@ -3377,14 +3407,18 @@ static void nfp_net_del_vxlan_port(struct net_device *netdev,
 		nfp_net_set_vxlan_port(nn, idx, 0);
 }
 
-static int
-nfp_net_xdp_setup_drv(struct nfp_net *nn, struct bpf_prog *prog,
-		      struct netlink_ext_ack *extack)
+static int nfp_net_xdp_setup_drv(struct nfp_net *nn, struct netdev_bpf *bpf)
 {
+	struct bpf_prog *prog = bpf->prog;
 	struct nfp_net_dp *dp;
+	int err;
+
+	if (!xdp_attachment_flags_ok(&nn->xdp, bpf))
+		return -EBUSY;
 
 	if (!prog == !nn->dp.xdp_prog) {
 		WRITE_ONCE(nn->dp.xdp_prog, prog);
+		xdp_attachment_setup(&nn->xdp, bpf);
 		return 0;
 	}
 
@@ -3398,38 +3432,26 @@ nfp_net_xdp_setup_drv(struct nfp_net *nn, struct bpf_prog *prog,
 	dp->rx_dma_off = prog ? XDP_PACKET_HEADROOM - nn->dp.rx_offset : 0;
 
 	/* We need RX reconfig to remap the buffers (BIDIR vs FROM_DEV) */
-	return nfp_net_ring_reconfig(nn, dp, extack);
+	err = nfp_net_ring_reconfig(nn, dp, bpf->extack);
+	if (err)
+		return err;
+
+	xdp_attachment_setup(&nn->xdp, bpf);
+	return 0;
 }
 
-static int
-nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog, u32 flags,
-		  struct netlink_ext_ack *extack)
+static int nfp_net_xdp_setup_hw(struct nfp_net *nn, struct netdev_bpf *bpf)
 {
-	struct bpf_prog *drv_prog, *offload_prog;
 	int err;
 
-	if (nn->xdp_prog && (flags ^ nn->xdp_flags) & XDP_FLAGS_MODES)
+	if (!xdp_attachment_flags_ok(&nn->xdp_hw, bpf))
 		return -EBUSY;
 
-	/* Load both when no flags set to allow easy activation of driver path
-	 * when program is replaced by one which can't be offloaded.
-	 */
-	drv_prog     = flags & XDP_FLAGS_HW_MODE  ? NULL : prog;
-	offload_prog = flags & XDP_FLAGS_DRV_MODE ? NULL : prog;
-
-	err = nfp_net_xdp_setup_drv(nn, drv_prog, extack);
+	err = nfp_app_xdp_offload(nn->app, nn, bpf->prog, bpf->extack);
 	if (err)
 		return err;
 
-	err = nfp_app_xdp_offload(nn->app, nn, offload_prog, extack);
-	if (err && flags & XDP_FLAGS_HW_MODE)
-		return err;
-
-	if (nn->xdp_prog)
-		bpf_prog_put(nn->xdp_prog);
-	nn->xdp_prog = prog;
-	nn->xdp_flags = flags;
-
+	xdp_attachment_setup(&nn->xdp_hw, bpf);
 	return 0;
 }
 
@@ -3439,16 +3461,13 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
+		return nfp_net_xdp_setup_drv(nn, xdp);
 	case XDP_SETUP_PROG_HW:
-		return nfp_net_xdp_setup(nn, xdp->prog, xdp->flags,
-					 xdp->extack);
+		return nfp_net_xdp_setup_hw(nn, xdp);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!nn->xdp_prog;
-		if (nn->dp.bpf_offload_xdp)
-			xdp->prog_attached = XDP_ATTACHED_HW;
-		xdp->prog_id = nn->xdp_prog ? nn->xdp_prog->aux->id : 0;
-		xdp->prog_flags = nn->xdp_prog ? nn->xdp_flags : 0;
-		return 0;
+		return xdp_attachment_query(&nn->xdp, xdp);
+	case XDP_QUERY_PROG_HW:
+		return xdp_attachment_query(&nn->xdp_hw, xdp);
 	default:
 		return nfp_app_bpf(nn->app, nn, xdp);
 	}
@@ -3476,12 +3495,17 @@ static int nfp_net_set_mac_address(struct net_device *netdev, void *addr)
 }
 
 const struct net_device_ops nfp_net_netdev_ops = {
+	.ndo_init		= nfp_app_ndo_init,
+	.ndo_uninit		= nfp_app_ndo_uninit,
 	.ndo_open		= nfp_net_netdev_open,
 	.ndo_stop		= nfp_net_netdev_close,
 	.ndo_start_xmit		= nfp_net_tx,
 	.ndo_get_stats64	= nfp_net_stat64,
 	.ndo_vlan_rx_add_vid	= nfp_net_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= nfp_net_vlan_rx_kill_vid,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= nfp_net_netpoll,
+#endif
 	.ndo_set_vf_mac         = nfp_app_set_vf_mac,
 	.ndo_set_vf_vlan        = nfp_app_set_vf_vlan,
 	.ndo_set_vf_spoofchk    = nfp_app_set_vf_spoofchk,
@@ -3840,6 +3864,9 @@ int nfp_net_init(struct nfp_net *nn)
 		nn->dp.mtu = NFP_NET_DEFAULT_MTU;
 	nn->dp.fl_bufsz = nfp_net_calc_fl_bufsz(&nn->dp);
 
+	if (nfp_app_ctrl_uses_data_vnics(nn->app))
+		nn->dp.ctrl |= nn->cap & NFP_NET_CFG_CTRL_CMSG_DATA;
+
 	if (nn->cap & NFP_NET_CFG_CTRL_RSS_ANY) {
 		nfp_net_rss_init(nn);
 		nn->dp.ctrl |= nn->cap & NFP_NET_CFG_CTRL_RSS2 ?:
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
index bb63c115537d..44d3ea75d043 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
@@ -127,6 +127,7 @@
 #define   NFP_NET_CFG_CTRL_GATHER	  (0x1 <<  9) /* Gather DMA */
 #define   NFP_NET_CFG_CTRL_LSO		  (0x1 << 10) /* LSO/TSO (version 1) */
 #define   NFP_NET_CFG_CTRL_CTAG_FILTER	  (0x1 << 11) /* VLAN CTAG filtering */
+#define   NFP_NET_CFG_CTRL_CMSG_DATA	  (0x1 << 12) /* RX cmsgs on data Qs */
 #define   NFP_NET_CFG_CTRL_RINGCFG	  (0x1 << 16) /* Ring runtime changes */
 #define   NFP_NET_CFG_CTRL_RSS		  (0x1 << 17) /* RSS (version 1) */
 #define   NFP_NET_CFG_CTRL_IRQMOD	  (0x1 << 18) /* Interrupt moderation */
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index 26d1cc4e2906..6a79c8e4a7a4 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -233,12 +233,10 @@ nfp_net_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
 static void
 nfp_app_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
 {
-	struct nfp_app *app;
-
-	app = nfp_app_from_netdev(netdev);
-	if (!app)
-		return;
+	struct nfp_app *app = nfp_app_from_netdev(netdev);
 
+	strlcpy(drvinfo->bus_info, pci_name(app->pdev),
+		sizeof(drvinfo->bus_info));
 	nfp_get_drvinfo(app, app->pdev, "*", drvinfo);
 }
 
@@ -452,7 +450,7 @@ static unsigned int nfp_vnic_get_sw_stats_count(struct net_device *netdev)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 
-	return NN_RVEC_GATHER_STATS + nn->dp.num_r_vecs * NN_RVEC_PER_Q_STATS;
+	return NN_RVEC_GATHER_STATS + nn->max_r_vecs * NN_RVEC_PER_Q_STATS;
 }
 
 static u8 *nfp_vnic_get_sw_stats_strings(struct net_device *netdev, u8 *data)
@@ -460,7 +458,7 @@ static u8 *nfp_vnic_get_sw_stats_strings(struct net_device *netdev, u8 *data)
 	struct nfp_net *nn = netdev_priv(netdev);
 	int i;
 
-	for (i = 0; i < nn->dp.num_r_vecs; i++) {
+	for (i = 0; i < nn->max_r_vecs; i++) {
 		data = nfp_pr_et(data, "rvec_%u_rx_pkts", i);
 		data = nfp_pr_et(data, "rvec_%u_tx_pkts", i);
 		data = nfp_pr_et(data, "rvec_%u_tx_busy", i);
@@ -486,7 +484,7 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data)
 	u64 tmp[NN_RVEC_GATHER_STATS];
 	unsigned int i, j;
 
-	for (i = 0; i < nn->dp.num_r_vecs; i++) {
+	for (i = 0; i < nn->max_r_vecs; i++) {
 		unsigned int start;
 
 		do {
@@ -521,15 +519,13 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data)
 	return data;
 }
 
-static unsigned int
-nfp_vnic_get_hw_stats_count(unsigned int rx_rings, unsigned int tx_rings)
+static unsigned int nfp_vnic_get_hw_stats_count(unsigned int num_vecs)
 {
-	return NN_ET_GLOBAL_STATS_LEN + (rx_rings + tx_rings) * 2;
+	return NN_ET_GLOBAL_STATS_LEN + num_vecs * 4;
 }
 
 static u8 *
-nfp_vnic_get_hw_stats_strings(u8 *data, unsigned int rx_rings,
-			      unsigned int tx_rings, bool repr)
+nfp_vnic_get_hw_stats_strings(u8 *data, unsigned int num_vecs, bool repr)
 {
 	int swap_off, i;
 
@@ -549,36 +545,29 @@ nfp_vnic_get_hw_stats_strings(u8 *data, unsigned int rx_rings,
 	for (i = NN_ET_SWITCH_STATS_LEN * 2; i < NN_ET_GLOBAL_STATS_LEN; i++)
 		data = nfp_pr_et(data, nfp_net_et_stats[i].name);
 
-	for (i = 0; i < tx_rings; i++) {
-		data = nfp_pr_et(data, "txq_%u_pkts", i);
-		data = nfp_pr_et(data, "txq_%u_bytes", i);
-	}
-
-	for (i = 0; i < rx_rings; i++) {
+	for (i = 0; i < num_vecs; i++) {
 		data = nfp_pr_et(data, "rxq_%u_pkts", i);
 		data = nfp_pr_et(data, "rxq_%u_bytes", i);
+		data = nfp_pr_et(data, "txq_%u_pkts", i);
+		data = nfp_pr_et(data, "txq_%u_bytes", i);
 	}
 
 	return data;
 }
 
 static u64 *
-nfp_vnic_get_hw_stats(u64 *data, u8 __iomem *mem,
-		      unsigned int rx_rings, unsigned int tx_rings)
+nfp_vnic_get_hw_stats(u64 *data, u8 __iomem *mem, unsigned int num_vecs)
 {
 	unsigned int i;
 
 	for (i = 0; i < NN_ET_GLOBAL_STATS_LEN; i++)
 		*data++ = readq(mem + nfp_net_et_stats[i].off);
 
-	for (i = 0; i < tx_rings; i++) {
-		*data++ = readq(mem + NFP_NET_CFG_TXR_STATS(i));
-		*data++ = readq(mem + NFP_NET_CFG_TXR_STATS(i) + 8);
-	}
-
-	for (i = 0; i < rx_rings; i++) {
+	for (i = 0; i < num_vecs; i++) {
 		*data++ = readq(mem + NFP_NET_CFG_RXR_STATS(i));
 		*data++ = readq(mem + NFP_NET_CFG_RXR_STATS(i) + 8);
+		*data++ = readq(mem + NFP_NET_CFG_TXR_STATS(i));
+		*data++ = readq(mem + NFP_NET_CFG_TXR_STATS(i) + 8);
 	}
 
 	return data;
@@ -633,8 +622,7 @@ static void nfp_net_get_strings(struct net_device *netdev,
 	switch (stringset) {
 	case ETH_SS_STATS:
 		data = nfp_vnic_get_sw_stats_strings(netdev, data);
-		data = nfp_vnic_get_hw_stats_strings(data, nn->dp.num_rx_rings,
-						     nn->dp.num_tx_rings,
+		data = nfp_vnic_get_hw_stats_strings(data, nn->max_r_vecs,
 						     false);
 		data = nfp_mac_get_stats_strings(netdev, data);
 		data = nfp_app_port_get_stats_strings(nn->port, data);
@@ -649,8 +637,7 @@ nfp_net_get_stats(struct net_device *netdev, struct ethtool_stats *stats,
 	struct nfp_net *nn = netdev_priv(netdev);
 
 	data = nfp_vnic_get_sw_stats(netdev, data);
-	data = nfp_vnic_get_hw_stats(data, nn->dp.ctrl_bar,
-				     nn->dp.num_rx_rings, nn->dp.num_tx_rings);
+	data = nfp_vnic_get_hw_stats(data, nn->dp.ctrl_bar, nn->max_r_vecs);
 	data = nfp_mac_get_stats(netdev, data);
 	data = nfp_app_port_get_stats(nn->port, data);
 }
@@ -662,8 +649,7 @@ static int nfp_net_get_sset_count(struct net_device *netdev, int sset)
 	switch (sset) {
 	case ETH_SS_STATS:
 		return nfp_vnic_get_sw_stats_count(netdev) +
-		       nfp_vnic_get_hw_stats_count(nn->dp.num_rx_rings,
-						   nn->dp.num_tx_rings) +
+		       nfp_vnic_get_hw_stats_count(nn->max_r_vecs) +
 		       nfp_mac_get_stats_count(netdev) +
 		       nfp_app_port_get_stats_count(nn->port);
 	default:
@@ -679,7 +665,7 @@ static void nfp_port_get_strings(struct net_device *netdev,
 	switch (stringset) {
 	case ETH_SS_STATS:
 		if (nfp_port_is_vnic(port))
-			data = nfp_vnic_get_hw_stats_strings(data, 0, 0, true);
+			data = nfp_vnic_get_hw_stats_strings(data, 0, true);
 		else
 			data = nfp_mac_get_stats_strings(netdev, data);
 		data = nfp_app_port_get_stats_strings(port, data);
@@ -694,7 +680,7 @@ nfp_port_get_stats(struct net_device *netdev, struct ethtool_stats *stats,
 	struct nfp_port *port = nfp_port_from_netdev(netdev);
 
 	if (nfp_port_is_vnic(port))
-		data = nfp_vnic_get_hw_stats(data, port->vnic, 0, 0);
+		data = nfp_vnic_get_hw_stats(data, port->vnic, 0);
 	else
 		data = nfp_mac_get_stats(netdev, data);
 	data = nfp_app_port_get_stats(port, data);
@@ -708,7 +694,7 @@ static int nfp_port_get_sset_count(struct net_device *netdev, int sset)
 	switch (sset) {
 	case ETH_SS_STATS:
 		if (nfp_port_is_vnic(port))
-			count = nfp_vnic_get_hw_stats_count(0, 0);
+			count = nfp_vnic_get_hw_stats_count(0);
 		else
 			count = nfp_mac_get_stats_count(netdev);
 		count += nfp_app_port_get_stats_count(port);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index d7b712f6362f..18a09cdcd9c6 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -262,6 +262,8 @@ err_port_disable:
 }
 
 const struct net_device_ops nfp_repr_netdev_ops = {
+	.ndo_init		= nfp_app_ndo_init,
+	.ndo_uninit		= nfp_app_ndo_uninit,
 	.ndo_open		= nfp_repr_open,
 	.ndo_stop		= nfp_repr_stop,
 	.ndo_start_xmit		= nfp_repr_xmit,
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
index 749655c329b2..c8d0b1016a64 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
@@ -1248,7 +1248,7 @@ static void nfp6000_free(struct nfp_cpp *cpp)
 	kfree(nfp);
 }
 
-static void nfp6000_read_serial(struct device *dev, u8 *serial)
+static int nfp6000_read_serial(struct device *dev, u8 *serial)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	int pos;
@@ -1256,25 +1256,29 @@ static void nfp6000_read_serial(struct device *dev, u8 *serial)
 
 	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DSN);
 	if (!pos) {
-		memset(serial, 0, NFP_SERIAL_LEN);
-		return;
+		dev_err(dev, "can't find PCIe Serial Number Capability\n");
+		return -EINVAL;
 	}
 
 	pci_read_config_dword(pdev, pos + 4, &reg);
 	put_unaligned_be16(reg >> 16, serial + 4);
 	pci_read_config_dword(pdev, pos + 8, &reg);
 	put_unaligned_be32(reg, serial);
+
+	return 0;
 }
 
-static u16 nfp6000_get_interface(struct device *dev)
+static int nfp6000_get_interface(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	int pos;
 	u32 reg;
 
 	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DSN);
-	if (!pos)
-		return NFP_CPP_INTERFACE(NFP_CPP_INTERFACE_TYPE_PCI, 0, 0xff);
+	if (!pos) {
+		dev_err(dev, "can't find PCIe Serial Number Capability\n");
+		return -EINVAL;
+	}
 
 	pci_read_config_dword(pdev, pos + 4, &reg);
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h
index b0da3d436850..c338d539fa96 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h
@@ -364,8 +364,8 @@ struct nfp_cpp_operations {
 	int (*init)(struct nfp_cpp *cpp);
 	void (*free)(struct nfp_cpp *cpp);
 
-	void (*read_serial)(struct device *dev, u8 *serial);
-	u16 (*get_interface)(struct device *dev);
+	int (*read_serial)(struct device *dev, u8 *serial);
+	int (*get_interface)(struct device *dev);
 
 	int (*area_init)(struct nfp_cpp_area *area,
 			 u32 dest, unsigned long long address,
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
index ef30597aa319..73de57a09800 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
@@ -1163,10 +1163,10 @@ nfp_cpp_from_operations(const struct nfp_cpp_operations *ops,
 {
 	const u32 arm = NFP_CPP_ID(NFP_CPP_TARGET_ARM, NFP_CPP_ACTION_RW, 0);
 	struct nfp_cpp *cpp;
+	int ifc, err;
 	u32 mask[2];
 	u32 xpbaddr;
 	size_t tgt;
-	int err;
 
 	cpp = kzalloc(sizeof(*cpp), GFP_KERNEL);
 	if (!cpp) {
@@ -1176,9 +1176,19 @@ nfp_cpp_from_operations(const struct nfp_cpp_operations *ops,
 
 	cpp->op = ops;
 	cpp->priv = priv;
-	cpp->interface = ops->get_interface(parent);
-	if (ops->read_serial)
-		ops->read_serial(parent, cpp->serial);
+
+	ifc = ops->get_interface(parent);
+	if (ifc < 0) {
+		err = ifc;
+		goto err_free_cpp;
+	}
+	cpp->interface = ifc;
+	if (ops->read_serial) {
+		err = ops->read_serial(parent, cpp->serial);
+		if (err)
+			goto err_free_cpp;
+	}
+
 	rwlock_init(&cpp->resource_lock);
 	init_waitqueue_head(&cpp->waitq);
 	lockdep_set_class(&cpp->resource_lock, &nfp_cpp_resource_lock_key);
@@ -1191,7 +1201,7 @@ nfp_cpp_from_operations(const struct nfp_cpp_operations *ops,
 	err = device_register(&cpp->dev);
 	if (err < 0) {
 		put_device(&cpp->dev);
-		goto err_dev;
+		goto err_free_cpp;
 	}
 
 	dev_set_drvdata(&cpp->dev, cpp);
@@ -1238,7 +1248,7 @@ nfp_cpp_from_operations(const struct nfp_cpp_operations *ops,
 
 err_out:
 	device_unregister(&cpp->dev);
-err_dev:
+err_free_cpp:
 	kfree(cpp);
 err_malloc:
 	return ERR_PTR(err);
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c
index 37a6d7822a38..40510860341b 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c
@@ -207,7 +207,7 @@ nffw_res_fwinfos(struct nfp_nffw_info_data *fwinf, struct nffw_fwinfo **arr)
  * nfp_nffw_info_open() - Acquire the lock on the NFFW table
  * @cpp:	NFP CPP handle
  *
- * Return: 0, or -ERRNO
+ * Return: pointer to nfp_nffw_info object or ERR_PTR()
  */
 struct nfp_nffw_info *nfp_nffw_info_open(struct nfp_cpp *cpp)
 {
@@ -253,10 +253,8 @@ err_free:
 }
 
 /**
- * nfp_nffw_info_release() - Release the lock on the NFFW table
+ * nfp_nffw_info_close() - Release the lock on the NFFW table and free state
  * @state:	NFP FW info state
- *
- * Return: 0, or -ERRNO
  */
 void nfp_nffw_info_close(struct nfp_nffw_info *state)
 {
diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c
index 09f674ec0f9e..76efed058f33 100644
--- a/drivers/net/ethernet/ni/nixge.c
+++ b/drivers/net/ethernet/ni/nixge.c
@@ -155,7 +155,6 @@ struct nixge_priv {
 
 	int tx_irq;
 	int rx_irq;
-	u32 last_link;
 
 	/* Buffer descriptors */
 	struct nixge_hw_dma_bd *tx_bd_v;
@@ -504,7 +503,6 @@ static int nixge_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	tx_skb->skb = skb;
 
 	cur_p->cntrl |= XAXIDMA_BD_CTRL_TXEOF_MASK;
-	cur_p->app4 = (unsigned long)skb;
 
 	tail_p = priv->tx_bd_p + sizeof(*priv->tx_bd_v) * priv->tx_bd_tail;
 	/* Start the transfer */
@@ -740,22 +738,12 @@ static void nixge_dma_err_handler(unsigned long data)
 		cur_p->phys = 0;
 		cur_p->cntrl = 0;
 		cur_p->status = 0;
-		cur_p->app0 = 0;
-		cur_p->app1 = 0;
-		cur_p->app2 = 0;
-		cur_p->app3 = 0;
-		cur_p->app4 = 0;
 		cur_p->sw_id_offset = 0;
 	}
 
 	for (i = 0; i < RX_BD_NUM; i++) {
 		cur_p = &lp->rx_bd_v[i];
 		cur_p->status = 0;
-		cur_p->app0 = 0;
-		cur_p->app1 = 0;
-		cur_p->app2 = 0;
-		cur_p->app3 = 0;
-		cur_p->app4 = 0;
 	}
 
 	lp->tx_bd_ci = 0;
diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index 7cbd0174459c..1d9b0d44ddb6 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -5777,7 +5777,7 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id)
 						      (np->rx_ring_size +
 						      np->tx_ring_size),
 						      &np->ring_addr,
-						      GFP_ATOMIC);
+						      GFP_KERNEL);
 		if (!np->rx_ring.orig)
 			goto out_unmap;
 		np->tx_ring.orig = &np->rx_ring.orig[np->rx_ring_size];
@@ -5786,7 +5786,7 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id)
 						    sizeof(struct ring_desc_ex) *
 						    (np->rx_ring_size +
 						    np->tx_ring_size),
-						    &np->ring_addr, GFP_ATOMIC);
+						    &np->ring_addr, GFP_KERNEL);
 		if (!np->rx_ring.ex)
 			goto out_unmap;
 		np->tx_ring.ex = &np->rx_ring.ex[np->rx_ring_size];
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/Makefile b/drivers/net/ethernet/oki-semi/pch_gbe/Makefile
index 31288d4ad248..862de0f3bc41 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/Makefile
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/Makefile
@@ -1,4 +1,4 @@
 obj-$(CONFIG_PCH_GBE) += pch_gbe.o
 
 pch_gbe-y := pch_gbe_phy.o pch_gbe_ethtool.o pch_gbe_param.o
-pch_gbe-y += pch_gbe_api.o pch_gbe_main.o
+pch_gbe-y += pch_gbe_main.o
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
index 697e29dd4bd3..44c2f291e766 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
@@ -326,32 +326,6 @@ struct pch_gbe_regs {
 #define PCH_GBE_FC_FULL			3
 #define PCH_GBE_FC_DEFAULT		PCH_GBE_FC_FULL
 
-
-struct pch_gbe_hw;
-/**
- * struct  pch_gbe_functions - HAL APi function pointer
- * @get_bus_info:	for pch_gbe_hal_get_bus_info
- * @init_hw:		for pch_gbe_hal_init_hw
- * @read_phy_reg:	for pch_gbe_hal_read_phy_reg
- * @write_phy_reg:	for pch_gbe_hal_write_phy_reg
- * @reset_phy:		for pch_gbe_hal_phy_hw_reset
- * @sw_reset_phy:	for pch_gbe_hal_phy_sw_reset
- * @power_up_phy:	for pch_gbe_hal_power_up_phy
- * @power_down_phy:	for pch_gbe_hal_power_down_phy
- * @read_mac_addr:	for pch_gbe_hal_read_mac_addr
- */
-struct pch_gbe_functions {
-	void (*get_bus_info) (struct pch_gbe_hw *);
-	s32 (*init_hw) (struct pch_gbe_hw *);
-	s32 (*read_phy_reg) (struct pch_gbe_hw *, u32, u16 *);
-	s32 (*write_phy_reg) (struct pch_gbe_hw *, u32, u16);
-	void (*reset_phy) (struct pch_gbe_hw *);
-	void (*sw_reset_phy) (struct pch_gbe_hw *);
-	void (*power_up_phy) (struct pch_gbe_hw *hw);
-	void (*power_down_phy) (struct pch_gbe_hw *hw);
-	s32 (*read_mac_addr) (struct pch_gbe_hw *);
-};
-
 /**
  * struct pch_gbe_mac_info - MAC information
  * @addr[6]:		Store the MAC address
@@ -394,17 +368,6 @@ struct pch_gbe_phy_info {
 
 /*!
  * @ingroup Gigabit Ether driver Layer
- * @struct  pch_gbe_bus_info
- * @brief   Bus information
- */
-struct pch_gbe_bus_info {
-	u8 type;
-	u8 speed;
-	u8 width;
-};
-
-/*!
- * @ingroup Gigabit Ether driver Layer
  * @struct  pch_gbe_hw
  * @brief   Hardware information
  */
@@ -414,10 +377,8 @@ struct pch_gbe_hw {
 	struct pch_gbe_regs  __iomem *reg;
 	spinlock_t miim_lock;
 
-	const struct pch_gbe_functions *func;
 	struct pch_gbe_mac_info mac;
 	struct pch_gbe_phy_info phy;
-	struct pch_gbe_bus_info bus;
 };
 
 /**
@@ -680,7 +641,6 @@ void pch_gbe_set_ethtool_ops(struct net_device *netdev);
 
 /* pch_gbe_mac.c */
 s32 pch_gbe_mac_force_mac_fc(struct pch_gbe_hw *hw);
-s32 pch_gbe_mac_read_mac_addr(struct pch_gbe_hw *hw);
 u16 pch_gbe_mac_ctrl_miim(struct pch_gbe_hw *hw, u32 addr, u32 dir, u32 reg,
 			  u16 data);
 #endif /* _PCH_GBE_H_ */
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
deleted file mode 100644
index 51250363566b..000000000000
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
+++ /dev/null
@@ -1,262 +0,0 @@
-/*
- * Copyright (C) 1999 - 2010 Intel Corporation.
- * Copyright (C) 2010 OKI SEMICONDUCTOR Co., LTD.
- *
- * This code was derived from the Intel e1000e Linux driver.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- */
-#include "pch_gbe.h"
-#include "pch_gbe_phy.h"
-#include "pch_gbe_api.h"
-
-/* bus type values */
-#define pch_gbe_bus_type_unknown	0
-#define pch_gbe_bus_type_pci		1
-#define pch_gbe_bus_type_pcix		2
-#define pch_gbe_bus_type_pci_express	3
-#define pch_gbe_bus_type_reserved	4
-
-/* bus speed values */
-#define pch_gbe_bus_speed_unknown	0
-#define pch_gbe_bus_speed_33		1
-#define pch_gbe_bus_speed_66		2
-#define pch_gbe_bus_speed_100		3
-#define pch_gbe_bus_speed_120		4
-#define pch_gbe_bus_speed_133		5
-#define pch_gbe_bus_speed_2500		6
-#define pch_gbe_bus_speed_reserved	7
-
-/* bus width values */
-#define pch_gbe_bus_width_unknown	0
-#define pch_gbe_bus_width_pcie_x1	1
-#define pch_gbe_bus_width_pcie_x2	2
-#define pch_gbe_bus_width_pcie_x4	4
-#define pch_gbe_bus_width_32		5
-#define pch_gbe_bus_width_64		6
-#define pch_gbe_bus_width_reserved	7
-
-/**
- * pch_gbe_plat_get_bus_info - Obtain bus information for adapter
- * @hw:	Pointer to the HW structure
- */
-static void pch_gbe_plat_get_bus_info(struct pch_gbe_hw *hw)
-{
-	hw->bus.type  = pch_gbe_bus_type_pci_express;
-	hw->bus.speed = pch_gbe_bus_speed_2500;
-	hw->bus.width = pch_gbe_bus_width_pcie_x1;
-}
-
-/**
- * pch_gbe_plat_init_hw - Initialize hardware
- * @hw:	Pointer to the HW structure
- * Returns:
- *	0:		Successfully
- *	Negative value:	Failed-EBUSY
- */
-static s32 pch_gbe_plat_init_hw(struct pch_gbe_hw *hw)
-{
-	s32 ret_val;
-
-	ret_val = pch_gbe_phy_get_id(hw);
-	if (ret_val) {
-		struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
-		netdev_err(adapter->netdev, "pch_gbe_phy_get_id error\n");
-		return ret_val;
-	}
-	pch_gbe_phy_init_setting(hw);
-	/* Setup Mac interface option RGMII */
-#ifdef PCH_GBE_MAC_IFOP_RGMII
-	pch_gbe_phy_set_rgmii(hw);
-#endif
-	return ret_val;
-}
-
-static const struct pch_gbe_functions pch_gbe_ops = {
-	.get_bus_info      = pch_gbe_plat_get_bus_info,
-	.init_hw           = pch_gbe_plat_init_hw,
-	.read_phy_reg      = pch_gbe_phy_read_reg_miic,
-	.write_phy_reg     = pch_gbe_phy_write_reg_miic,
-	.reset_phy         = pch_gbe_phy_hw_reset,
-	.sw_reset_phy      = pch_gbe_phy_sw_reset,
-	.power_up_phy      = pch_gbe_phy_power_up,
-	.power_down_phy    = pch_gbe_phy_power_down,
-	.read_mac_addr     = pch_gbe_mac_read_mac_addr
-};
-
-/**
- * pch_gbe_plat_init_function_pointers - Init func ptrs
- * @hw:	Pointer to the HW structure
- */
-static void pch_gbe_plat_init_function_pointers(struct pch_gbe_hw *hw)
-{
-	/* Set PHY parameter */
-	hw->phy.reset_delay_us     = PCH_GBE_PHY_RESET_DELAY_US;
-	/* Set function pointers */
-	hw->func = &pch_gbe_ops;
-}
-
-/**
- * pch_gbe_hal_setup_init_funcs - Initializes function pointers
- * @hw:	Pointer to the HW structure
- * Returns:
- *	0:	Successfully
- *	ENOSYS:	Function is not registered
- */
-s32 pch_gbe_hal_setup_init_funcs(struct pch_gbe_hw *hw)
-{
-	if (!hw->reg) {
-		struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
-		netdev_err(adapter->netdev, "ERROR: Registers not mapped\n");
-		return -ENOSYS;
-	}
-	pch_gbe_plat_init_function_pointers(hw);
-	return 0;
-}
-
-/**
- * pch_gbe_hal_get_bus_info - Obtain bus information for adapter
- * @hw:	Pointer to the HW structure
- */
-void pch_gbe_hal_get_bus_info(struct pch_gbe_hw *hw)
-{
-	if (!hw->func->get_bus_info) {
-		struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
-		netdev_err(adapter->netdev, "ERROR: configuration\n");
-		return;
-	}
-	hw->func->get_bus_info(hw);
-}
-
-/**
- * pch_gbe_hal_init_hw - Initialize hardware
- * @hw:	Pointer to the HW structure
- * Returns:
- *	0:	Successfully
- *	ENOSYS:	Function is not registered
- */
-s32 pch_gbe_hal_init_hw(struct pch_gbe_hw *hw)
-{
-	if (!hw->func->init_hw) {
-		struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
-		netdev_err(adapter->netdev, "ERROR: configuration\n");
-		return -ENOSYS;
-	}
-	return hw->func->init_hw(hw);
-}
-
-/**
- * pch_gbe_hal_read_phy_reg - Reads PHY register
- * @hw:	    Pointer to the HW structure
- * @offset: The register to read
- * @data:   The buffer to store the 16-bit read.
- * Returns:
- *	0:	Successfully
- *	Negative value:	Failed
- */
-s32 pch_gbe_hal_read_phy_reg(struct pch_gbe_hw *hw, u32 offset,
-					u16 *data)
-{
-	if (!hw->func->read_phy_reg)
-		return 0;
-	return hw->func->read_phy_reg(hw, offset, data);
-}
-
-/**
- * pch_gbe_hal_write_phy_reg - Writes PHY register
- * @hw:	    Pointer to the HW structure
- * @offset: The register to read
- * @data:   The value to write.
- * Returns:
- *	0:	Successfully
- *	Negative value:	Failed
- */
-s32 pch_gbe_hal_write_phy_reg(struct pch_gbe_hw *hw, u32 offset,
-					u16 data)
-{
-	if (!hw->func->write_phy_reg)
-		return 0;
-	return hw->func->write_phy_reg(hw, offset, data);
-}
-
-/**
- * pch_gbe_hal_phy_hw_reset - Hard PHY reset
- * @hw:	    Pointer to the HW structure
- */
-void pch_gbe_hal_phy_hw_reset(struct pch_gbe_hw *hw)
-{
-	if (!hw->func->reset_phy) {
-		struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
-		netdev_err(adapter->netdev, "ERROR: configuration\n");
-		return;
-	}
-	hw->func->reset_phy(hw);
-}
-
-/**
- * pch_gbe_hal_phy_sw_reset - Soft PHY reset
- * @hw:	    Pointer to the HW structure
- */
-void pch_gbe_hal_phy_sw_reset(struct pch_gbe_hw *hw)
-{
-	if (!hw->func->sw_reset_phy) {
-		struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
-		netdev_err(adapter->netdev, "ERROR: configuration\n");
-		return;
-	}
-	hw->func->sw_reset_phy(hw);
-}
-
-/**
- * pch_gbe_hal_read_mac_addr - Reads MAC address
- * @hw:	Pointer to the HW structure
- * Returns:
- *	0:	Successfully
- *	ENOSYS:	Function is not registered
- */
-s32 pch_gbe_hal_read_mac_addr(struct pch_gbe_hw *hw)
-{
-	if (!hw->func->read_mac_addr) {
-		struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
-		netdev_err(adapter->netdev, "ERROR: configuration\n");
-		return -ENOSYS;
-	}
-	return hw->func->read_mac_addr(hw);
-}
-
-/**
- * pch_gbe_hal_power_up_phy - Power up PHY
- * @hw:	Pointer to the HW structure
- */
-void pch_gbe_hal_power_up_phy(struct pch_gbe_hw *hw)
-{
-	if (hw->func->power_up_phy)
-		hw->func->power_up_phy(hw);
-}
-
-/**
- * pch_gbe_hal_power_down_phy - Power down PHY
- * @hw:	Pointer to the HW structure
- */
-void pch_gbe_hal_power_down_phy(struct pch_gbe_hw *hw)
-{
-	if (hw->func->power_down_phy)
-		hw->func->power_down_phy(hw);
-}
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
deleted file mode 100644
index 91ce07c8306c..000000000000
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/*
- * Copyright (C) 1999 - 2010 Intel Corporation.
- * Copyright (C) 2010 OKI SEMICONDUCTOR Co., LTD.
- *
- * This code was derived from the Intel e1000e Linux driver.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- */
-#ifndef _PCH_GBE_API_H_
-#define _PCH_GBE_API_H_
-
-#include "pch_gbe_phy.h"
-
-s32 pch_gbe_hal_setup_init_funcs(struct pch_gbe_hw *hw);
-void pch_gbe_hal_get_bus_info(struct pch_gbe_hw *hw);
-s32 pch_gbe_hal_init_hw(struct pch_gbe_hw *hw);
-s32 pch_gbe_hal_read_phy_reg(struct pch_gbe_hw *hw, u32 offset, u16 *data);
-s32 pch_gbe_hal_write_phy_reg(struct pch_gbe_hw *hw, u32 offset, u16 data);
-void pch_gbe_hal_phy_hw_reset(struct pch_gbe_hw *hw);
-void pch_gbe_hal_phy_sw_reset(struct pch_gbe_hw *hw);
-s32 pch_gbe_hal_read_mac_addr(struct pch_gbe_hw *hw);
-void pch_gbe_hal_power_up_phy(struct pch_gbe_hw *hw);
-void pch_gbe_hal_power_down_phy(struct pch_gbe_hw *hw);
-
-#endif
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
index 731ce1e419e4..adaa0024adfe 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
@@ -17,7 +17,7 @@
  * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 #include "pch_gbe.h"
-#include "pch_gbe_api.h"
+#include "pch_gbe_phy.h"
 
 /**
  * pch_gbe_stats - Stats item information
@@ -125,7 +125,7 @@ static int pch_gbe_set_link_ksettings(struct net_device *netdev,
 	u32 advertising;
 	int ret;
 
-	pch_gbe_hal_write_phy_reg(hw, MII_BMCR, BMCR_RESET);
+	pch_gbe_phy_write_reg_miic(hw, MII_BMCR, BMCR_RESET);
 
 	memcpy(&copy_ecmd, ecmd, sizeof(*ecmd));
 
@@ -204,7 +204,7 @@ static void pch_gbe_get_regs(struct net_device *netdev,
 		*regs_buff++ = ioread32(&hw->reg->INT_ST + i);
 	/* PHY register */
 	for (i = 0; i < PCH_GBE_PHY_REGS_LEN; i++) {
-		pch_gbe_hal_read_phy_reg(&adapter->hw, i, &tmp);
+		pch_gbe_phy_read_reg_miic(&adapter->hw, i, &tmp);
 		*regs_buff++ = tmp;
 	}
 }
@@ -349,25 +349,12 @@ static int pch_gbe_set_ringparam(struct net_device *netdev,
 		err = pch_gbe_setup_tx_resources(adapter, adapter->tx_ring);
 		if (err)
 			goto err_setup_tx;
-		/* save the new, restore the old in order to free it,
-		 * then restore the new back again */
-#ifdef RINGFREE
-		adapter->rx_ring = rx_old;
-		adapter->tx_ring = tx_old;
-		pch_gbe_free_rx_resources(adapter, adapter->rx_ring);
-		pch_gbe_free_tx_resources(adapter, adapter->tx_ring);
-		kfree(tx_old);
-		kfree(rx_old);
-		adapter->rx_ring = rxdr;
-		adapter->tx_ring = txdr;
-#else
 		pch_gbe_free_rx_resources(adapter, rx_old);
 		pch_gbe_free_tx_resources(adapter, tx_old);
 		kfree(tx_old);
 		kfree(rx_old);
 		adapter->rx_ring = rxdr;
 		adapter->tx_ring = txdr;
-#endif
 		err = pch_gbe_up(adapter);
 	}
 	return err;
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 34a1581eda95..43c0c10dfeb7 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -18,7 +18,7 @@
  */
 
 #include "pch_gbe.h"
-#include "pch_gbe_api.h"
+#include "pch_gbe_phy.h"
 #include <linux/module.h>
 #include <linux/net_tstamp.h>
 #include <linux/ptp_classify.h>
@@ -34,7 +34,6 @@ const char pch_driver_version[] = DRV_VERSION;
 #define PCH_GBE_DMA_ALIGN		0
 #define PCH_GBE_DMA_PADDING		2
 #define PCH_GBE_WATCHDOG_PERIOD		(5 * HZ)	/* watchdog time */
-#define PCH_GBE_COPYBREAK_DEFAULT	256
 #define PCH_GBE_PCI_BAR			1
 #define PCH_GBE_RESERVE_MEMORY		0x200000	/* 2MB */
 
@@ -113,8 +112,6 @@ const char pch_driver_version[] = DRV_VERSION;
 
 #define MINNOW_PHY_RESET_GPIO		13
 
-static unsigned int copybreak __read_mostly = PCH_GBE_COPYBREAK_DEFAULT;
-
 static int pch_gbe_mdio_read(struct net_device *netdev, int addr, int reg);
 static void pch_gbe_mdio_write(struct net_device *netdev, int addr, int reg,
 			       int data);
@@ -290,7 +287,7 @@ static inline void pch_gbe_mac_load_mac_addr(struct pch_gbe_hw *hw)
  * Returns:
  *	0:			Successful.
  */
-s32 pch_gbe_mac_read_mac_addr(struct pch_gbe_hw *hw)
+static s32 pch_gbe_mac_read_mac_addr(struct pch_gbe_hw *hw)
 {
 	struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
 	u32  adr1a, adr1b;
@@ -369,9 +366,7 @@ static void pch_gbe_mac_reset_hw(struct pch_gbe_hw *hw)
 	/* Read the MAC address. and store to the private data */
 	pch_gbe_mac_read_mac_addr(hw);
 	iowrite32(PCH_GBE_ALL_RST, &hw->reg->RESET);
-#ifdef PCH_GBE_MAC_IFOP_RGMII
 	iowrite32(PCH_GBE_MODE_GMII_ETHER, &hw->reg->MODE);
-#endif
 	pch_gbe_wait_clr_bit(&hw->reg->RESET, PCH_GBE_ALL_RST);
 	/* Setup the receive addresses */
 	pch_gbe_mac_mar_set(hw, hw->mac.addr, 0);
@@ -416,44 +411,6 @@ static void pch_gbe_mac_init_rx_addrs(struct pch_gbe_hw *hw, u16 mar_count)
 	pch_gbe_wait_clr_bit(&hw->reg->ADDR_MASK, PCH_GBE_BUSY);
 }
 
-
-/**
- * pch_gbe_mac_mc_addr_list_update - Update Multicast addresses
- * @hw:	            Pointer to the HW structure
- * @mc_addr_list:   Array of multicast addresses to program
- * @mc_addr_count:  Number of multicast addresses to program
- * @mar_used_count: The first MAC Address register free to program
- * @mar_total_num:  Total number of supported MAC Address Registers
- */
-static void pch_gbe_mac_mc_addr_list_update(struct pch_gbe_hw *hw,
-					    u8 *mc_addr_list, u32 mc_addr_count,
-					    u32 mar_used_count, u32 mar_total_num)
-{
-	u32 i, adrmask;
-
-	/* Load the first set of multicast addresses into the exact
-	 * filters (RAR).  If there are not enough to fill the RAR
-	 * array, clear the filters.
-	 */
-	for (i = mar_used_count; i < mar_total_num; i++) {
-		if (mc_addr_count) {
-			pch_gbe_mac_mar_set(hw, mc_addr_list, i);
-			mc_addr_count--;
-			mc_addr_list += ETH_ALEN;
-		} else {
-			/* Clear MAC address mask */
-			adrmask = ioread32(&hw->reg->ADDR_MASK);
-			iowrite32((adrmask | (0x0001 << i)),
-					&hw->reg->ADDR_MASK);
-			/* wait busy */
-			pch_gbe_wait_clr_bit(&hw->reg->ADDR_MASK, PCH_GBE_BUSY);
-			/* Clear MAC address */
-			iowrite32(0, &hw->reg->mac_adr[i].high);
-			iowrite32(0, &hw->reg->mac_adr[i].low);
-		}
-	}
-}
-
 /**
  * pch_gbe_mac_force_mac_fc - Force the MAC's flow control settings
  * @hw:	            Pointer to the HW structure
@@ -763,14 +720,23 @@ void pch_gbe_reinit_locked(struct pch_gbe_adapter *adapter)
 void pch_gbe_reset(struct pch_gbe_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
+	struct pch_gbe_hw *hw = &adapter->hw;
+	s32 ret_val;
 
-	pch_gbe_mac_reset_hw(&adapter->hw);
+	pch_gbe_mac_reset_hw(hw);
 	/* reprogram multicast address register after reset */
 	pch_gbe_set_multi(netdev);
 	/* Setup the receive address. */
-	pch_gbe_mac_init_rx_addrs(&adapter->hw, PCH_GBE_MAR_ENTRIES);
-	if (pch_gbe_hal_init_hw(&adapter->hw))
-		netdev_err(netdev, "Hardware Error\n");
+	pch_gbe_mac_init_rx_addrs(hw, PCH_GBE_MAR_ENTRIES);
+
+	ret_val = pch_gbe_phy_get_id(hw);
+	if (ret_val) {
+		netdev_err(adapter->netdev, "pch_gbe_phy_get_id error\n");
+		return;
+	}
+	pch_gbe_phy_init_setting(hw);
+	/* Setup Mac interface option RGMII */
+	pch_gbe_phy_set_rgmii(hw);
 }
 
 /**
@@ -1036,7 +1002,6 @@ static void pch_gbe_set_rgmii_ctrl(struct pch_gbe_adapter *adapter, u16 speed,
 	unsigned long rgmii = 0;
 
 	/* Set the RGMII control. */
-#ifdef PCH_GBE_MAC_IFOP_RGMII
 	switch (speed) {
 	case SPEED_10:
 		rgmii = (PCH_GBE_RGMII_RATE_2_5M |
@@ -1052,10 +1017,6 @@ static void pch_gbe_set_rgmii_ctrl(struct pch_gbe_adapter *adapter, u16 speed,
 		break;
 	}
 	iowrite32(rgmii, &hw->reg->RGMII_CTRL);
-#else	/* GMII */
-	rgmii = 0;
-	iowrite32(rgmii, &hw->reg->RGMII_CTRL);
-#endif
 }
 static void pch_gbe_set_mode(struct pch_gbe_adapter *adapter, u16 speed,
 			      u16 duplex)
@@ -2029,12 +1990,8 @@ static int pch_gbe_sw_init(struct pch_gbe_adapter *adapter)
 	adapter->rx_buffer_len = PCH_GBE_FRAME_SIZE_2048;
 	hw->mac.max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
 	hw->mac.min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
+	hw->phy.reset_delay_us = PCH_GBE_PHY_RESET_DELAY_US;
 
-	/* Initialize the hardware-specific values */
-	if (pch_gbe_hal_setup_init_funcs(hw)) {
-		netdev_err(netdev, "Hardware Initialization Failure\n");
-		return -EIO;
-	}
 	if (pch_gbe_alloc_queues(adapter)) {
 		netdev_err(netdev, "Unable to allocate memory for queues\n");
 		return -ENOMEM;
@@ -2075,7 +2032,7 @@ static int pch_gbe_open(struct net_device *netdev)
 	err = pch_gbe_setup_rx_resources(adapter, adapter->rx_ring);
 	if (err)
 		goto err_setup_rx;
-	pch_gbe_hal_power_up_phy(hw);
+	pch_gbe_phy_power_up(hw);
 	err = pch_gbe_up(adapter);
 	if (err)
 		goto err_up;
@@ -2084,7 +2041,7 @@ static int pch_gbe_open(struct net_device *netdev)
 
 err_up:
 	if (!adapter->wake_up_evt)
-		pch_gbe_hal_power_down_phy(hw);
+		pch_gbe_phy_power_down(hw);
 	pch_gbe_free_rx_resources(adapter, adapter->rx_ring);
 err_setup_rx:
 	pch_gbe_free_tx_resources(adapter, adapter->tx_ring);
@@ -2107,7 +2064,7 @@ static int pch_gbe_stop(struct net_device *netdev)
 
 	pch_gbe_down(adapter);
 	if (!adapter->wake_up_evt)
-		pch_gbe_hal_power_down_phy(hw);
+		pch_gbe_phy_power_down(hw);
 	pch_gbe_free_tx_resources(adapter, adapter->tx_ring);
 	pch_gbe_free_rx_resources(adapter, adapter->rx_ring);
 	return 0;
@@ -2148,50 +2105,52 @@ static void pch_gbe_set_multi(struct net_device *netdev)
 	struct pch_gbe_adapter *adapter = netdev_priv(netdev);
 	struct pch_gbe_hw *hw = &adapter->hw;
 	struct netdev_hw_addr *ha;
-	u8 *mta_list;
-	u32 rctl;
-	int i;
-	int mc_count;
+	u32 rctl, adrmask;
+	int mc_count, i;
 
 	netdev_dbg(netdev, "netdev->flags : 0x%08x\n", netdev->flags);
 
-	/* Check for Promiscuous and All Multicast modes */
+	/* By default enable address & multicast filtering */
 	rctl = ioread32(&hw->reg->RX_MODE);
+	rctl |= PCH_GBE_ADD_FIL_EN | PCH_GBE_MLT_FIL_EN;
+
+	/* Promiscuous mode disables all hardware address filtering */
+	if (netdev->flags & IFF_PROMISC)
+		rctl &= ~(PCH_GBE_ADD_FIL_EN | PCH_GBE_MLT_FIL_EN);
+
+	/* If we want to monitor more multicast addresses than the hardware can
+	 * support then disable hardware multicast filtering.
+	 */
 	mc_count = netdev_mc_count(netdev);
-	if ((netdev->flags & IFF_PROMISC)) {
-		rctl &= ~PCH_GBE_ADD_FIL_EN;
-		rctl &= ~PCH_GBE_MLT_FIL_EN;
-	} else if ((netdev->flags & IFF_ALLMULTI)) {
-		/* all the multicasting receive permissions */
-		rctl |= PCH_GBE_ADD_FIL_EN;
+	if ((netdev->flags & IFF_ALLMULTI) || mc_count >= PCH_GBE_MAR_ENTRIES)
 		rctl &= ~PCH_GBE_MLT_FIL_EN;
-	} else {
-		if (mc_count >= PCH_GBE_MAR_ENTRIES) {
-			/* all the multicasting receive permissions */
-			rctl |= PCH_GBE_ADD_FIL_EN;
-			rctl &= ~PCH_GBE_MLT_FIL_EN;
-		} else {
-			rctl |= (PCH_GBE_ADD_FIL_EN | PCH_GBE_MLT_FIL_EN);
-		}
-	}
+
 	iowrite32(rctl, &hw->reg->RX_MODE);
 
-	if (mc_count >= PCH_GBE_MAR_ENTRIES)
-		return;
-	mta_list = kmalloc_array(ETH_ALEN, mc_count, GFP_ATOMIC);
-	if (!mta_list)
+	/* If we're not using multicast filtering then there's no point
+	 * configuring the unused MAC address registers.
+	 */
+	if (!(rctl & PCH_GBE_MLT_FIL_EN))
 		return;
 
-	/* The shared function expects a packed array of only addresses. */
-	i = 0;
-	netdev_for_each_mc_addr(ha, netdev) {
-		if (i == mc_count)
-			break;
-		memcpy(mta_list + (i++ * ETH_ALEN), &ha->addr, ETH_ALEN);
+	/* Load the first set of multicast addresses into MAC address registers
+	 * for use by hardware filtering.
+	 */
+	i = 1;
+	netdev_for_each_mc_addr(ha, netdev)
+		pch_gbe_mac_mar_set(hw, ha->addr, i++);
+
+	/* If there are spare MAC registers, mask & clear them */
+	for (; i < PCH_GBE_MAR_ENTRIES; i++) {
+		/* Clear MAC address mask */
+		adrmask = ioread32(&hw->reg->ADDR_MASK);
+		iowrite32(adrmask | BIT(i), &hw->reg->ADDR_MASK);
+		/* wait busy */
+		pch_gbe_wait_clr_bit(&hw->reg->ADDR_MASK, PCH_GBE_BUSY);
+		/* Clear MAC address */
+		iowrite32(0, &hw->reg->mac_adr[i].high);
+		iowrite32(0, &hw->reg->mac_adr[i].low);
 	}
-	pch_gbe_mac_mc_addr_list_update(hw, mta_list, i, 1,
-					PCH_GBE_MAR_ENTRIES);
-	kfree(mta_list);
 
 	netdev_dbg(netdev,
 		 "RX_MODE reg(check bit31,30 ADD,MLT) : 0x%08x  netdev->mc_count : 0x%08x\n",
@@ -2437,7 +2396,7 @@ static pci_ers_result_t pch_gbe_io_slot_reset(struct pci_dev *pdev)
 	}
 	pci_set_master(pdev);
 	pci_enable_wake(pdev, PCI_D0, 0);
-	pch_gbe_hal_power_up_phy(hw);
+	pch_gbe_phy_power_up(hw);
 	pch_gbe_reset(adapter);
 	/* Clear wake up status */
 	pch_gbe_mac_set_wol_event(hw, 0);
@@ -2482,7 +2441,7 @@ static int __pch_gbe_suspend(struct pci_dev *pdev)
 		pch_gbe_mac_set_wol_event(hw, wufc);
 		pci_disable_device(pdev);
 	} else {
-		pch_gbe_hal_power_down_phy(hw);
+		pch_gbe_phy_power_down(hw);
 		pch_gbe_mac_set_wol_event(hw, wufc);
 		pci_disable_device(pdev);
 	}
@@ -2511,7 +2470,7 @@ static int pch_gbe_resume(struct device *device)
 		return err;
 	}
 	pci_set_master(pdev);
-	pch_gbe_hal_power_up_phy(hw);
+	pch_gbe_phy_power_up(hw);
 	pch_gbe_reset(adapter);
 	/* Clear wake on lan control and status */
 	pch_gbe_mac_set_wol_event(hw, 0);
@@ -2541,7 +2500,7 @@ static void pch_gbe_remove(struct pci_dev *pdev)
 	cancel_work_sync(&adapter->reset_task);
 	unregister_netdev(netdev);
 
-	pch_gbe_hal_phy_hw_reset(&adapter->hw);
+	pch_gbe_phy_hw_reset(&adapter->hw);
 
 	free_netdev(netdev);
 }
@@ -2627,10 +2586,9 @@ static int pch_gbe_probe(struct pci_dev *pdev,
 		dev_err(&pdev->dev, "PHY initialize error\n");
 		goto err_free_adapter;
 	}
-	pch_gbe_hal_get_bus_info(&adapter->hw);
 
 	/* Read the MAC address. and store to the private data */
-	ret = pch_gbe_hal_read_mac_addr(&adapter->hw);
+	ret = pch_gbe_mac_read_mac_addr(&adapter->hw);
 	if (ret) {
 		dev_err(&pdev->dev, "MAC address Read Error\n");
 		goto err_free_adapter;
@@ -2677,7 +2635,7 @@ static int pch_gbe_probe(struct pci_dev *pdev,
 	return 0;
 
 err_free_adapter:
-	pch_gbe_hal_phy_hw_reset(&adapter->hw);
+	pch_gbe_phy_hw_reset(&adapter->hw);
 err_free_netdev:
 	free_netdev(netdev);
 	return ret;
@@ -2776,32 +2734,7 @@ static struct pci_driver pch_gbe_driver = {
 	.shutdown = pch_gbe_shutdown,
 	.err_handler = &pch_gbe_err_handler
 };
-
-
-static int __init pch_gbe_init_module(void)
-{
-	int ret;
-
-	pr_info("EG20T PCH Gigabit Ethernet Driver - version %s\n",DRV_VERSION);
-	ret = pci_register_driver(&pch_gbe_driver);
-	if (copybreak != PCH_GBE_COPYBREAK_DEFAULT) {
-		if (copybreak == 0) {
-			pr_info("copybreak disabled\n");
-		} else {
-			pr_info("copybreak enabled for packets <= %u bytes\n",
-				copybreak);
-		}
-	}
-	return ret;
-}
-
-static void __exit pch_gbe_exit_module(void)
-{
-	pci_unregister_driver(&pch_gbe_driver);
-}
-
-module_init(pch_gbe_init_module);
-module_exit(pch_gbe_exit_module);
+module_pci_driver(pch_gbe_driver);
 
 MODULE_DESCRIPTION("EG20T PCH Gigabit ethernet Driver");
 MODULE_AUTHOR("LAPIS SEMICONDUCTOR, <tshimizu818@gmail.com>");
@@ -2809,8 +2742,4 @@ MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_VERSION);
 MODULE_DEVICE_TABLE(pci, pch_gbe_pcidev_id);
 
-module_param(copybreak, uint, 0644);
-MODULE_PARM_DESC(copybreak,
-	"Maximum size of packet that is copied to a new buffer on receive");
-
 /* pch_gbe_main.c */
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c
index a5cad5ea9436..6b35b573beef 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c
@@ -184,7 +184,7 @@ s32 pch_gbe_phy_write_reg_miic(struct pch_gbe_hw *hw, u32 offset, u16 data)
  * pch_gbe_phy_sw_reset - PHY software reset
  * @hw:	            Pointer to the HW structure
  */
-void pch_gbe_phy_sw_reset(struct pch_gbe_hw *hw)
+static void pch_gbe_phy_sw_reset(struct pch_gbe_hw *hw)
 {
 	u16 phy_ctrl;
 
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h
index 95ad0151ad02..23ac38711619 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h
@@ -21,12 +21,10 @@
 
 #define PCH_GBE_PHY_REGS_LEN		32
 #define	PCH_GBE_PHY_RESET_DELAY_US	10
-#define PCH_GBE_MAC_IFOP_RGMII
 
 s32 pch_gbe_phy_get_id(struct pch_gbe_hw *hw);
 s32 pch_gbe_phy_read_reg_miic(struct pch_gbe_hw *hw, u32 offset, u16 *data);
 s32 pch_gbe_phy_write_reg_miic(struct pch_gbe_hw *hw, u32 offset, u16 data);
-void pch_gbe_phy_sw_reset(struct pch_gbe_hw *hw);
 void pch_gbe_phy_hw_reset(struct pch_gbe_hw *hw);
 void pch_gbe_phy_power_up(struct pch_gbe_hw *hw);
 void pch_gbe_phy_power_down(struct pch_gbe_hw *hw);
diff --git a/drivers/net/ethernet/packetengines/Kconfig b/drivers/net/ethernet/packetengines/Kconfig
index b5ea2a56106e..1df28f2edd1f 100644
--- a/drivers/net/ethernet/packetengines/Kconfig
+++ b/drivers/net/ethernet/packetengines/Kconfig
@@ -2,7 +2,7 @@
 # Packet engine device configuration
 #
 
-config NET_PACKET_ENGINE
+config NET_VENDOR_PACKET_ENGINES
 	bool "Packet Engine devices"
 	default y
 	depends on PCI
@@ -14,7 +14,7 @@ config NET_PACKET_ENGINE
 	  the questions about packet engine devices. If you say Y, you will
 	  be asked for your specific card in the following questions.
 
-if NET_PACKET_ENGINE
+if NET_VENDOR_PACKET_ENGINES
 
 config HAMACHI
 	tristate "Packet Engines Hamachi GNIC-II support"
@@ -40,4 +40,4 @@ config YELLOWFIN
 	  To compile this driver as a module, choose M here: the module
 	  will be called yellowfin.  This is recommended.
 
-endif # NET_PACKET_ENGINE
+endif # NET_VENDOR_PACKET_ENGINES
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
index 3157f97dd782..3c1be87cdfa5 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
@@ -167,9 +167,9 @@ skip:
 	case NETXEN_BRDTYPE_P3_REF_QG:
 	case NETXEN_BRDTYPE_P3_4_GB:
 	case NETXEN_BRDTYPE_P3_4_GB_MM:
-
 		supported |= SUPPORTED_Autoneg;
 		advertising |= ADVERTISED_Autoneg;
+		/* fall through */
 	case NETXEN_BRDTYPE_P2_SB31_10G_CX4:
 	case NETXEN_BRDTYPE_P3_10G_CX4:
 	case NETXEN_BRDTYPE_P3_10G_CX4_LP:
@@ -198,6 +198,7 @@ skip:
 		supported |= SUPPORTED_TP;
 		check_sfp_module = netif_running(dev) &&
 			adapter->has_link_events;
+		/* fall through */
 	case NETXEN_BRDTYPE_P2_SB31_10G:
 	case NETXEN_BRDTYPE_P3_10G_XFP:
 		supported |= SUPPORTED_FIBRE;
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c
index 1cd39c9a0345..52ad80621335 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c
@@ -566,9 +566,8 @@ static int
 netxen_send_cmd_descs(struct netxen_adapter *adapter,
 		struct cmd_desc_type0 *cmd_desc_arr, int nr_desc)
 {
-	u32 i, producer, consumer;
+	u32 i, producer;
 	struct netxen_cmd_buffer *pbuf;
-	struct cmd_desc_type0 *cmd_desc;
 	struct nx_host_tx_ring *tx_ring;
 
 	i = 0;
@@ -580,7 +579,6 @@ netxen_send_cmd_descs(struct netxen_adapter *adapter,
 	__netif_tx_lock_bh(tx_ring->txq);
 
 	producer = tx_ring->producer;
-	consumer = tx_ring->sw_consumer;
 
 	if (nr_desc >= netxen_tx_avail(tx_ring)) {
 		netif_tx_stop_queue(tx_ring->txq);
@@ -595,8 +593,6 @@ netxen_send_cmd_descs(struct netxen_adapter *adapter,
 	}
 
 	do {
-		cmd_desc = &cmd_desc_arr[i];
-
 		pbuf = &tx_ring->cmd_buf_arr[producer];
 		pbuf->skb = NULL;
 		pbuf->frag_count = 0;
@@ -2350,7 +2346,7 @@ static int netxen_md_entry_err_chk(struct netxen_adapter *adapter,
 static int netxen_parse_md_template(struct netxen_adapter *adapter)
 {
 	int num_of_entries, buff_level, e_cnt, esize;
-	int end_cnt = 0, rv = 0, sane_start = 0, sane_end = 0;
+	int rv = 0, sane_start = 0, sane_end = 0;
 	char *dbuff;
 	void *template_buff = adapter->mdump.md_template;
 	char *dump_buff = adapter->mdump.md_capture_buff;
@@ -2386,8 +2382,6 @@ static int netxen_parse_md_template(struct netxen_adapter *adapter)
 			break;
 		case RDEND:
 			entry->hdr.driver_flags |= NX_DUMP_SKIP;
-			if (!sane_end)
-				end_cnt = e_cnt;
 			sane_end += 1;
 			break;
 		case CNTRL:
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index 8259e8309320..69aa7fc392c5 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -2073,7 +2073,7 @@ netxen_nic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 	struct skb_frag_struct *frag;
 
 	u32 producer;
-	int frag_count, no_of_desc;
+	int frag_count;
 	u32 num_txd = tx_ring->num_desc;
 
 	frag_count = skb_shinfo(skb)->nr_frags + 1;
@@ -2093,8 +2093,6 @@ netxen_nic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 
 		frag_count = 1 + skb_shinfo(skb)->nr_frags;
 	}
-	/* 4 fragments per cmd des */
-	no_of_desc = (frag_count + 3) >> 2;
 
 	if (unlikely(netxen_tx_avail(tx_ring) <= TX_STOP_THRESH)) {
 		netif_stop_queue(netdev);
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 1dfaccd151f0..a60e1c8d470a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -336,6 +336,10 @@ struct qed_hw_info {
 	 */
 	u8 num_active_tc;
 	u8				offload_tc;
+	bool				offload_tc_set;
+
+	bool				multi_tc_roce_en;
+#define IS_QED_MULTI_TC_ROCE(p_hwfn) (((p_hwfn)->hw_info.multi_tc_roce_en))
 
 	u32				concrete_fid;
 	u16				opaque_fid;
@@ -399,8 +403,8 @@ struct qed_qm_info {
 	u16				start_pq;
 	u8				start_vport;
 	u16				 pure_lb_pq;
-	u16				offload_pq;
-	u16				low_latency_pq;
+	u16				first_ofld_pq;
+	u16				first_llt_pq;
 	u16				pure_ack_pq;
 	u16				ooo_pq;
 	u16				first_vf_pq;
@@ -881,11 +885,14 @@ void qed_set_fw_mac_addr(__le16 *fw_msb,
 #define PQ_FLAGS_OFLD   (BIT(5))
 #define PQ_FLAGS_VFS    (BIT(6))
 #define PQ_FLAGS_LLT    (BIT(7))
+#define PQ_FLAGS_MTC    (BIT(8))
 
 /* physical queue index for cm context intialization */
 u16 qed_get_cm_pq_idx(struct qed_hwfn *p_hwfn, u32 pq_flags);
 u16 qed_get_cm_pq_idx_mcos(struct qed_hwfn *p_hwfn, u8 tc);
 u16 qed_get_cm_pq_idx_vf(struct qed_hwfn *p_hwfn, u16 vf);
+u16 qed_get_cm_pq_idx_ofld_mtc(struct qed_hwfn *p_hwfn, u8 tc);
+u16 qed_get_cm_pq_idx_llt_mtc(struct qed_hwfn *p_hwfn, u8 tc);
 
 #define QED_LEADING_HWFN(dev)   (&dev->hwfns[0])
 
@@ -921,4 +928,6 @@ int qed_mfw_tlv_req(struct qed_hwfn *hwfn);
 int qed_mfw_fill_tlv_data(struct qed_hwfn *hwfn,
 			  enum qed_mfw_tlv_type type,
 			  union qed_mfw_tlv_data *tlv_data);
+
+void qed_hw_info_set_offload_tc(struct qed_hw_info *p_info, u8 tc);
 #endif /* _QED_H */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index b5b5ff725426..f1977aa440e5 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -1531,7 +1531,7 @@ void qed_qm_init_pf(struct qed_hwfn *p_hwfn,
 }
 
 /* CM PF */
-void qed_cm_init_pf(struct qed_hwfn *p_hwfn)
+static void qed_cm_init_pf(struct qed_hwfn *p_hwfn)
 {
 	/* XCM pure-LB queue */
 	STORE_RT_REG(p_hwfn, XCM_REG_CON_PHY_Q3_RT_OFFSET,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index e0680ce91328..6bb76e6d3c14 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -208,7 +208,7 @@ qed_dcbx_set_params(struct qed_dcbx_results *p_data,
 
 	/* QM reconf data */
 	if (p_info->personality == personality)
-		p_info->offload_tc = tc;
+		qed_hw_info_set_offload_tc(p_info, tc);
 }
 
 /* Update app protocol data and hw_info fields with the TLV info */
@@ -221,7 +221,6 @@ qed_dcbx_update_app_info(struct qed_dcbx_results *p_data,
 	struct qed_hw_info *p_info = &p_hwfn->hw_info;
 	enum qed_pci_personality personality;
 	enum dcbx_protocol_type id;
-	char *name;
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(qed_dcbx_app_update); i++) {
@@ -231,7 +230,6 @@ qed_dcbx_update_app_info(struct qed_dcbx_results *p_data,
 			continue;
 
 		personality = qed_dcbx_app_update[i].personality;
-		name = qed_dcbx_app_update[i].name;
 
 		qed_dcbx_set_params(p_data, p_info, enable,
 				    prio, tc, type, personality);
@@ -869,7 +867,7 @@ static int qed_dcbx_read_mib(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
-void qed_dcbx_aen(struct qed_hwfn *hwfn, u32 mib_type)
+static void qed_dcbx_aen(struct qed_hwfn *hwfn, u32 mib_type)
 {
 	struct qed_common_cb_ops *op = hwfn->cdev->protocol_ops.common;
 	void *cookie = hwfn->cdev->ops_cookie;
@@ -991,6 +989,24 @@ void qed_dcbx_set_pf_update_params(struct qed_dcbx_results *p_src,
 	qed_dcbx_update_protocol_data(p_dcb_data, p_src, DCBX_PROTOCOL_ETH);
 }
 
+u8 qed_dcbx_get_priority_tc(struct qed_hwfn *p_hwfn, u8 pri)
+{
+	struct qed_dcbx_get *dcbx_info = &p_hwfn->p_dcbx_info->get;
+
+	if (pri >= QED_MAX_PFC_PRIORITIES) {
+		DP_ERR(p_hwfn, "Invalid priority %d\n", pri);
+		return QED_DCBX_DEFAULT_TC;
+	}
+
+	if (!dcbx_info->operational.valid) {
+		DP_VERBOSE(p_hwfn, QED_MSG_DCB,
+			   "Dcbx parameters not available\n");
+		return QED_DCBX_DEFAULT_TC;
+	}
+
+	return dcbx_info->operational.params.ets_pri_tc_tbl[pri];
+}
+
 #ifdef CONFIG_DCB
 static int qed_dcbx_query_params(struct qed_hwfn *p_hwfn,
 				 struct qed_dcbx_get *p_get,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
index 5feb90e049e0..a4d688c04e18 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
@@ -123,4 +123,7 @@ void qed_dcbx_info_free(struct qed_hwfn *p_hwfn);
 void qed_dcbx_set_pf_update_params(struct qed_dcbx_results *p_src,
 				   struct pf_update_ramrod_data *p_dest);
 
+#define QED_DCBX_DEFAULT_TC	0
+
+u8 qed_dcbx_get_priority_tc(struct qed_hwfn *p_hwfn, u8 pri);
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index 4340c4c90bcb..1aa9fc1c5890 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -7838,8 +7838,8 @@ int qed_dbg_igu_fifo_size(struct qed_dev *cdev)
 	return qed_dbg_feature_size(cdev, DBG_FEATURE_IGU_FIFO);
 }
 
-int qed_dbg_nvm_image_length(struct qed_hwfn *p_hwfn,
-			     enum qed_nvm_images image_id, u32 *length)
+static int qed_dbg_nvm_image_length(struct qed_hwfn *p_hwfn,
+				    enum qed_nvm_images image_id, u32 *length)
 {
 	struct qed_nvm_image_att image_att;
 	int rc;
@@ -7854,8 +7854,9 @@ int qed_dbg_nvm_image_length(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
-int qed_dbg_nvm_image(struct qed_dev *cdev, void *buffer,
-		      u32 *num_dumped_bytes, enum qed_nvm_images image_id)
+static int qed_dbg_nvm_image(struct qed_dev *cdev, void *buffer,
+			     u32 *num_dumped_bytes,
+			     enum qed_nvm_images image_id)
 {
 	struct qed_hwfn *p_hwfn =
 		&cdev->hwfns[cdev->dbg_params.engine_for_debug];
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index e5249b4741d0..016ca8a7ec8a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -215,6 +215,8 @@ static u32 qed_get_pq_flags(struct qed_hwfn *p_hwfn)
 		break;
 	case QED_PCI_ETH_ROCE:
 		flags |= PQ_FLAGS_MCOS | PQ_FLAGS_OFLD | PQ_FLAGS_LLT;
+		if (IS_QED_MULTI_TC_ROCE(p_hwfn))
+			flags |= PQ_FLAGS_MTC;
 		break;
 	case QED_PCI_ETH_IWARP:
 		flags |= PQ_FLAGS_MCOS | PQ_FLAGS_ACK | PQ_FLAGS_OOO |
@@ -230,20 +232,30 @@ static u32 qed_get_pq_flags(struct qed_hwfn *p_hwfn)
 }
 
 /* Getters for resource amounts necessary for qm initialization */
-u8 qed_init_qm_get_num_tcs(struct qed_hwfn *p_hwfn)
+static u8 qed_init_qm_get_num_tcs(struct qed_hwfn *p_hwfn)
 {
 	return p_hwfn->hw_info.num_hw_tc;
 }
 
-u16 qed_init_qm_get_num_vfs(struct qed_hwfn *p_hwfn)
+static u16 qed_init_qm_get_num_vfs(struct qed_hwfn *p_hwfn)
 {
 	return IS_QED_SRIOV(p_hwfn->cdev) ?
 	       p_hwfn->cdev->p_iov_info->total_vfs : 0;
 }
 
+static u8 qed_init_qm_get_num_mtc_tcs(struct qed_hwfn *p_hwfn)
+{
+	u32 pq_flags = qed_get_pq_flags(p_hwfn);
+
+	if (!(PQ_FLAGS_MTC & pq_flags))
+		return 1;
+
+	return qed_init_qm_get_num_tcs(p_hwfn);
+}
+
 #define NUM_DEFAULT_RLS 1
 
-u16 qed_init_qm_get_num_pf_rls(struct qed_hwfn *p_hwfn)
+static u16 qed_init_qm_get_num_pf_rls(struct qed_hwfn *p_hwfn)
 {
 	u16 num_pf_rls, num_vfs = qed_init_qm_get_num_vfs(p_hwfn);
 
@@ -261,7 +273,7 @@ u16 qed_init_qm_get_num_pf_rls(struct qed_hwfn *p_hwfn)
 	return num_pf_rls;
 }
 
-u16 qed_init_qm_get_num_vports(struct qed_hwfn *p_hwfn)
+static u16 qed_init_qm_get_num_vports(struct qed_hwfn *p_hwfn)
 {
 	u32 pq_flags = qed_get_pq_flags(p_hwfn);
 
@@ -273,7 +285,7 @@ u16 qed_init_qm_get_num_vports(struct qed_hwfn *p_hwfn)
 }
 
 /* calc amount of PQs according to the requested flags */
-u16 qed_init_qm_get_num_pqs(struct qed_hwfn *p_hwfn)
+static u16 qed_init_qm_get_num_pqs(struct qed_hwfn *p_hwfn)
 {
 	u32 pq_flags = qed_get_pq_flags(p_hwfn);
 
@@ -282,8 +294,11 @@ u16 qed_init_qm_get_num_pqs(struct qed_hwfn *p_hwfn)
 	       (!!(PQ_FLAGS_MCOS & pq_flags)) *
 	       qed_init_qm_get_num_tcs(p_hwfn) +
 	       (!!(PQ_FLAGS_LB & pq_flags)) + (!!(PQ_FLAGS_OOO & pq_flags)) +
-	       (!!(PQ_FLAGS_ACK & pq_flags)) + (!!(PQ_FLAGS_OFLD & pq_flags)) +
-	       (!!(PQ_FLAGS_LLT & pq_flags)) +
+	       (!!(PQ_FLAGS_ACK & pq_flags)) +
+	       (!!(PQ_FLAGS_OFLD & pq_flags)) *
+	       qed_init_qm_get_num_mtc_tcs(p_hwfn) +
+	       (!!(PQ_FLAGS_LLT & pq_flags)) *
+	       qed_init_qm_get_num_mtc_tcs(p_hwfn) +
 	       (!!(PQ_FLAGS_VFS & pq_flags)) * qed_init_qm_get_num_vfs(p_hwfn);
 }
 
@@ -394,7 +409,25 @@ static void qed_init_qm_advance_vport(struct qed_hwfn *p_hwfn)
 /* defines for pq init */
 #define PQ_INIT_DEFAULT_WRR_GROUP       1
 #define PQ_INIT_DEFAULT_TC              0
-#define PQ_INIT_OFLD_TC                 (p_hwfn->hw_info.offload_tc)
+
+void qed_hw_info_set_offload_tc(struct qed_hw_info *p_info, u8 tc)
+{
+	p_info->offload_tc = tc;
+	p_info->offload_tc_set = true;
+}
+
+static bool qed_is_offload_tc_set(struct qed_hwfn *p_hwfn)
+{
+	return p_hwfn->hw_info.offload_tc_set;
+}
+
+static u32 qed_get_offload_tc(struct qed_hwfn *p_hwfn)
+{
+	if (qed_is_offload_tc_set(p_hwfn))
+		return p_hwfn->hw_info.offload_tc;
+
+	return PQ_INIT_DEFAULT_TC;
+}
 
 static void qed_init_qm_pq(struct qed_hwfn *p_hwfn,
 			   struct qed_qm_info *qm_info,
@@ -456,9 +489,9 @@ static u16 *qed_init_qm_get_idx_from_flags(struct qed_hwfn *p_hwfn,
 	case PQ_FLAGS_ACK:
 		return &qm_info->pure_ack_pq;
 	case PQ_FLAGS_OFLD:
-		return &qm_info->offload_pq;
+		return &qm_info->first_ofld_pq;
 	case PQ_FLAGS_LLT:
-		return &qm_info->low_latency_pq;
+		return &qm_info->first_llt_pq;
 	case PQ_FLAGS_VFS:
 		return &qm_info->first_vf_pq;
 	default:
@@ -507,14 +540,26 @@ u16 qed_get_cm_pq_idx_vf(struct qed_hwfn *p_hwfn, u16 vf)
 	return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_VFS) + vf;
 }
 
-u16 qed_get_cm_pq_idx_rl(struct qed_hwfn *p_hwfn, u8 rl)
+u16 qed_get_cm_pq_idx_ofld_mtc(struct qed_hwfn *p_hwfn, u8 tc)
+{
+	u16 first_ofld_pq, pq_offset;
+
+	first_ofld_pq = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
+	pq_offset = (tc < qed_init_qm_get_num_mtc_tcs(p_hwfn)) ?
+		    tc : PQ_INIT_DEFAULT_TC;
+
+	return first_ofld_pq + pq_offset;
+}
+
+u16 qed_get_cm_pq_idx_llt_mtc(struct qed_hwfn *p_hwfn, u8 tc)
 {
-	u16 max_rl = qed_init_qm_get_num_pf_rls(p_hwfn);
+	u16 first_llt_pq, pq_offset;
 
-	if (rl > max_rl)
-		DP_ERR(p_hwfn, "rl %d must be smaller than %d\n", rl, max_rl);
+	first_llt_pq = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_LLT);
+	pq_offset = (tc < qed_init_qm_get_num_mtc_tcs(p_hwfn)) ?
+		    tc : PQ_INIT_DEFAULT_TC;
 
-	return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_RLS) + rl;
+	return first_llt_pq + pq_offset;
 }
 
 /* Functions for creating specific types of pqs */
@@ -548,7 +593,22 @@ static void qed_init_qm_pure_ack_pq(struct qed_hwfn *p_hwfn)
 		return;
 
 	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_ACK, qm_info->num_pqs);
-	qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT);
+	qed_init_qm_pq(p_hwfn, qm_info, qed_get_offload_tc(p_hwfn),
+		       PQ_INIT_SHARE_VPORT);
+}
+
+static void qed_init_qm_mtc_pqs(struct qed_hwfn *p_hwfn)
+{
+	u8 num_tcs = qed_init_qm_get_num_mtc_tcs(p_hwfn);
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+	u8 tc;
+
+	/* override pq's TC if offload TC is set */
+	for (tc = 0; tc < num_tcs; tc++)
+		qed_init_qm_pq(p_hwfn, qm_info,
+			       qed_is_offload_tc_set(p_hwfn) ?
+			       p_hwfn->hw_info.offload_tc : tc,
+			       PQ_INIT_SHARE_VPORT);
 }
 
 static void qed_init_qm_offload_pq(struct qed_hwfn *p_hwfn)
@@ -559,7 +619,7 @@ static void qed_init_qm_offload_pq(struct qed_hwfn *p_hwfn)
 		return;
 
 	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_OFLD, qm_info->num_pqs);
-	qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT);
+	qed_init_qm_mtc_pqs(p_hwfn);
 }
 
 static void qed_init_qm_low_latency_pq(struct qed_hwfn *p_hwfn)
@@ -570,7 +630,7 @@ static void qed_init_qm_low_latency_pq(struct qed_hwfn *p_hwfn)
 		return;
 
 	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_LLT, qm_info->num_pqs);
-	qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT);
+	qed_init_qm_mtc_pqs(p_hwfn);
 }
 
 static void qed_init_qm_mcos_pqs(struct qed_hwfn *p_hwfn)
@@ -611,7 +671,8 @@ static void qed_init_qm_rl_pqs(struct qed_hwfn *p_hwfn)
 
 	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_RLS, qm_info->num_pqs);
 	for (pf_rls_idx = 0; pf_rls_idx < num_pf_rls; pf_rls_idx++)
-		qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_PF_RL);
+		qed_init_qm_pq(p_hwfn, qm_info, qed_get_offload_tc(p_hwfn),
+			       PQ_INIT_PF_RL);
 }
 
 static void qed_init_qm_pq_params(struct qed_hwfn *p_hwfn)
@@ -652,12 +713,19 @@ static int qed_init_qm_sanity(struct qed_hwfn *p_hwfn)
 		return -EINVAL;
 	}
 
-	if (qed_init_qm_get_num_pqs(p_hwfn) > RESC_NUM(p_hwfn, QED_PQ)) {
-		DP_ERR(p_hwfn, "requested amount of pqs exceeds resource\n");
-		return -EINVAL;
+	if (qed_init_qm_get_num_pqs(p_hwfn) <= RESC_NUM(p_hwfn, QED_PQ))
+		return 0;
+
+	if (QED_IS_ROCE_PERSONALITY(p_hwfn)) {
+		p_hwfn->hw_info.multi_tc_roce_en = 0;
+		DP_NOTICE(p_hwfn,
+			  "multi-tc roce was disabled to reduce requested amount of pqs\n");
+		if (qed_init_qm_get_num_pqs(p_hwfn) <= RESC_NUM(p_hwfn, QED_PQ))
+			return 0;
 	}
 
-	return 0;
+	DP_ERR(p_hwfn, "requested amount of pqs exceeds resource\n");
+	return -EINVAL;
 }
 
 static void qed_dp_init_qm_params(struct qed_hwfn *p_hwfn)
@@ -671,11 +739,13 @@ static void qed_dp_init_qm_params(struct qed_hwfn *p_hwfn)
 	/* top level params */
 	DP_VERBOSE(p_hwfn,
 		   NETIF_MSG_HW,
-		   "qm init top level params: start_pq %d, start_vport %d, pure_lb_pq %d, offload_pq %d, pure_ack_pq %d\n",
+		   "qm init top level params: start_pq %d, start_vport %d, pure_lb_pq %d, offload_pq %d, llt_pq %d, pure_ack_pq %d\n",
 		   qm_info->start_pq,
 		   qm_info->start_vport,
 		   qm_info->pure_lb_pq,
-		   qm_info->offload_pq, qm_info->pure_ack_pq);
+		   qm_info->first_ofld_pq,
+		   qm_info->first_llt_pq,
+		   qm_info->pure_ack_pq);
 	DP_VERBOSE(p_hwfn,
 		   NETIF_MSG_HW,
 		   "ooo_pq %d, first_vf_pq %d, num_pqs %d, num_vf_pqs %d, num_vports %d, max_phys_tcs_per_port %d\n",
@@ -1719,14 +1789,14 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 						p_hwfn->hw_info.hw_mode);
 			if (rc)
 				break;
-		/* Fall into */
+		/* Fall through */
 		case FW_MSG_CODE_DRV_LOAD_PORT:
 			rc = qed_hw_init_port(p_hwfn, p_hwfn->p_main_ptt,
 					      p_hwfn->hw_info.hw_mode);
 			if (rc)
 				break;
 
-		/* Fall into */
+		/* Fall through */
 		case FW_MSG_CODE_DRV_LOAD_FUNCTION:
 			rc = qed_hw_init_pf(p_hwfn, p_hwfn->p_main_ptt,
 					    p_params->p_tunn,
@@ -2908,6 +2978,9 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn,
 		p_hwfn->hw_info.personality = protocol;
 	}
 
+	if (QED_IS_ROCE_PERSONALITY(p_hwfn))
+		p_hwfn->hw_info.multi_tc_roce_en = 1;
+
 	p_hwfn->hw_info.num_hw_tc = NUM_PHYS_TCS_4PORT_K2;
 	p_hwfn->hw_info.num_active_tc = 1;
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index bee10c1781fb..8faceb691657 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -12444,6 +12444,8 @@ struct public_drv_mb {
 #define DRV_MSG_CODE_STATS_TYPE_ISCSI           3
 #define DRV_MSG_CODE_STATS_TYPE_RDMA            4
 
+#define DRV_MSG_CODE_TRANSCEIVER_READ           0x00160000
+
 #define DRV_MSG_CODE_MASK_PARITIES              0x001a0000
 
 #define DRV_MSG_CODE_BIST_TEST			0x001e0000
@@ -12543,6 +12545,15 @@ struct public_drv_mb {
 #define DRV_MB_PARAM_SET_LED_MODE_ON		0x1
 #define DRV_MB_PARAM_SET_LED_MODE_OFF		0x2
 
+#define DRV_MB_PARAM_TRANSCEIVER_PORT_OFFSET		0
+#define DRV_MB_PARAM_TRANSCEIVER_PORT_MASK		0x00000003
+#define DRV_MB_PARAM_TRANSCEIVER_SIZE_OFFSET		2
+#define DRV_MB_PARAM_TRANSCEIVER_SIZE_MASK		0x000000FC
+#define DRV_MB_PARAM_TRANSCEIVER_I2C_ADDRESS_OFFSET	8
+#define DRV_MB_PARAM_TRANSCEIVER_I2C_ADDRESS_MASK	0x0000FF00
+#define DRV_MB_PARAM_TRANSCEIVER_OFFSET_OFFSET		16
+#define DRV_MB_PARAM_TRANSCEIVER_OFFSET_MASK		0xFFFF0000
+
 	/* Resource Allocation params - Driver version support */
 #define DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_MASK	0xFFFF0000
 #define DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_SHIFT	16
@@ -12596,6 +12607,9 @@ struct public_drv_mb {
 #define FW_MSG_CODE_PHY_OK			0x00110000
 #define FW_MSG_CODE_OK				0x00160000
 #define FW_MSG_CODE_ERROR			0x00170000
+#define FW_MSG_CODE_TRANSCEIVER_DIAG_OK		0x00160000
+#define FW_MSG_CODE_TRANSCEIVER_DIAG_ERROR	0x00170000
+#define FW_MSG_CODE_TRANSCEIVER_NOT_PRESENT	0x00020000
 
 #define FW_MSG_CODE_OS_WOL_SUPPORTED            0x00800000
 #define FW_MSG_CODE_OS_WOL_NOT_SUPPORTED        0x00810000
@@ -12687,6 +12701,8 @@ struct mcp_public_data {
 	struct public_func func[MCP_GLOB_FUNC_MAX];
 };
 
+#define MAX_I2C_TRANSACTION_SIZE	16
+
 /* OCBB definitions */
 enum tlvs {
 	/* Category 1: Device Properties */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
index d845badf9b90..d6430dfebd83 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
@@ -1225,19 +1225,6 @@ void qed_gft_disable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u16 pf_id)
 	       0);
 }
 
-void qed_set_gft_event_id_cm_hdr(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
-{
-	u32 rfs_cm_hdr_event_id;
-
-	/* Set RFS event ID to be awakened i Tstorm By Prs */
-	rfs_cm_hdr_event_id = qed_rd(p_hwfn, p_ptt, PRS_REG_CM_HDR_GFT);
-	rfs_cm_hdr_event_id |= T_ETH_PACKET_ACTION_GFT_EVENTID <<
-			       PRS_REG_CM_HDR_GFT_EVENT_ID_SHIFT;
-	rfs_cm_hdr_event_id |= PARSER_ETH_CONN_GFT_ACTION_CM_HDR <<
-			       PRS_REG_CM_HDR_GFT_CM_HDR_SHIFT;
-	qed_wr(p_hwfn, p_ptt, PRS_REG_CM_HDR_GFT, rfs_cm_hdr_event_id);
-}
-
 void qed_gft_config(struct qed_hwfn *p_hwfn,
 		    struct qed_ptt *p_ptt,
 		    u16 pf_id,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
index c0d4a54a5edb..1135387bd99d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
@@ -873,8 +873,8 @@ static void qed_iscsi_release_connection(struct qed_hwfn *p_hwfn,
 	spin_unlock_bh(&p_hwfn->p_iscsi_info->lock);
 }
 
-void qed_iscsi_free_connection(struct qed_hwfn *p_hwfn,
-			       struct qed_iscsi_conn *p_conn)
+static void qed_iscsi_free_connection(struct qed_hwfn *p_hwfn,
+				      struct qed_iscsi_conn *p_conn)
 {
 	qed_chain_free(p_hwfn->cdev, &p_conn->xhq);
 	qed_chain_free(p_hwfn->cdev, &p_conn->uhq);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index 90a2b53096e2..17f3dfa2cc94 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -377,7 +377,7 @@ qed_iwarp2roce_state(enum qed_iwarp_qp_state state)
 	}
 }
 
-const char *iwarp_state_names[] = {
+const static char *iwarp_state_names[] = {
 	"IDLE",
 	"RTS",
 	"TERMINATE",
@@ -942,7 +942,7 @@ qed_iwarp_return_ep(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep)
 	spin_unlock_bh(&p_hwfn->p_rdma_info->iwarp.iw_lock);
 }
 
-void
+static void
 qed_iwarp_parse_private_data(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep)
 {
 	struct mpa_v2_hdr *mpa_v2_params;
@@ -967,7 +967,7 @@ qed_iwarp_parse_private_data(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep)
 				       mpa_data_size;
 }
 
-void
+static void
 qed_iwarp_mpa_reply_arrived(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep)
 {
 	struct qed_iwarp_cm_event_params params;
@@ -2500,7 +2500,7 @@ static void qed_iwarp_ll2_rel_tx_pkt(void *cxt, u8 connection_handle,
 /* The only slowpath for iwarp ll2 is unalign flush. When this completion
  * is received, need to reset the FPDU.
  */
-void
+static void
 qed_iwarp_ll2_slowpath(void *cxt,
 		       u8 connection_handle,
 		       u32 opaque_data_0, u32 opaque_data_1)
@@ -2803,8 +2803,9 @@ int qed_iwarp_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	return qed_iwarp_ll2_stop(p_hwfn, p_ptt);
 }
 
-void qed_iwarp_qp_in_error(struct qed_hwfn *p_hwfn,
-			   struct qed_iwarp_ep *ep, u8 fw_return_code)
+static void qed_iwarp_qp_in_error(struct qed_hwfn *p_hwfn,
+				  struct qed_iwarp_ep *ep,
+				  u8 fw_return_code)
 {
 	struct qed_iwarp_cm_event_params params;
 
@@ -2824,8 +2825,9 @@ void qed_iwarp_qp_in_error(struct qed_hwfn *p_hwfn,
 	ep->event_cb(ep->cb_context, &params);
 }
 
-void qed_iwarp_exception_received(struct qed_hwfn *p_hwfn,
-				  struct qed_iwarp_ep *ep, int fw_ret_code)
+static void qed_iwarp_exception_received(struct qed_hwfn *p_hwfn,
+					 struct qed_iwarp_ep *ep,
+					 int fw_ret_code)
 {
 	struct qed_iwarp_cm_event_params params;
 	bool event_cb = false;
@@ -2954,7 +2956,7 @@ qed_iwarp_tcp_connect_unsuccessful(struct qed_hwfn *p_hwfn,
 	}
 }
 
-void
+static void
 qed_iwarp_connect_complete(struct qed_hwfn *p_hwfn,
 			   struct qed_iwarp_ep *ep, u8 fw_return_code)
 {
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index 5ede6408649d..82a1bd1f8a8c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -2188,16 +2188,17 @@ out:
 static int qed_fill_eth_dev_info(struct qed_dev *cdev,
 				 struct qed_dev_eth_info *info)
 {
+	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
 	int i;
 
 	memset(info, 0, sizeof(*info));
 
-	info->num_tc = 1;
-
 	if (IS_PF(cdev)) {
 		int max_vf_vlan_filters = 0;
 		int max_vf_mac_filters = 0;
 
+		info->num_tc = p_hwfn->hw_info.num_hw_tc;
+
 		if (cdev->int_params.out.int_mode == QED_INT_MODE_MSIX) {
 			u16 num_queues = 0;
 
@@ -2248,6 +2249,8 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev,
 	} else {
 		u16 total_cids = 0;
 
+		info->num_tc = 1;
+
 		/* Determine queues &  XDP support */
 		for_each_hwfn(cdev, i) {
 			struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
@@ -2554,7 +2557,7 @@ static int qed_start_txq(struct qed_dev *cdev,
 
 	rc = qed_eth_tx_queue_start(p_hwfn,
 				    p_hwfn->hw_info.opaque_fid,
-				    p_params, 0,
+				    p_params, p_params->tc,
 				    pbl_addr, pbl_size, ret_params);
 
 	if (rc) {
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index 012973d75ad0..14ac9cab2653 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -158,7 +158,8 @@ static void qed_ll2_kill_buffers(struct qed_dev *cdev)
 		qed_ll2_dealloc_buffer(cdev, buffer);
 }
 
-void qed_ll2b_complete_rx_packet(void *cxt, struct qed_ll2_comp_rx_data *data)
+static void qed_ll2b_complete_rx_packet(void *cxt,
+					struct qed_ll2_comp_rx_data *data)
 {
 	struct qed_hwfn *p_hwfn = cxt;
 	struct qed_ll2_buffer *buffer = data->cookie;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 758a9a5127fa..2094d86a7a08 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -948,13 +948,14 @@ static void qed_update_pf_params(struct qed_dev *cdev,
 		params->eth_pf_params.num_arfs_filters = 0;
 
 	/* In case we might support RDMA, don't allow qede to be greedy
-	 * with the L2 contexts. Allow for 64 queues [rx, tx, xdp] per hwfn.
+	 * with the L2 contexts. Allow for 64 queues [rx, tx cos, xdp]
+	 * per hwfn.
 	 */
 	if (QED_IS_RDMA_PERSONALITY(QED_LEADING_HWFN(cdev))) {
 		u16 *num_cons;
 
 		num_cons = &params->eth_pf_params.num_cons;
-		*num_cons = min_t(u16, *num_cons, 192);
+		*num_cons = min_t(u16, *num_cons, QED_MAX_L2_CONS);
 	}
 
 	for (i = 0; i < cdev->num_hwfns; i++) {
@@ -2102,6 +2103,28 @@ out:
 	return status;
 }
 
+static int qed_read_module_eeprom(struct qed_dev *cdev, char *buf,
+				  u8 dev_addr, u32 offset, u32 len)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_ptt *ptt;
+	int rc = 0;
+
+	if (IS_VF(cdev))
+		return 0;
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return -EAGAIN;
+
+	rc = qed_mcp_phy_sfp_read(hwfn, ptt, MFW_PORT(hwfn), dev_addr,
+				  offset, len, buf);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return rc;
+}
+
 static struct qed_selftest_ops qed_selftest_ops_pass = {
 	.selftest_memory = &qed_selftest_memory,
 	.selftest_interrupt = &qed_selftest_interrupt,
@@ -2144,6 +2167,7 @@ const struct qed_common_ops qed_common_ops_pass = {
 	.update_mac = &qed_update_mac,
 	.update_mtu = &qed_update_mtu,
 	.update_wol = &qed_update_wol,
+	.read_module_eeprom = &qed_read_module_eeprom,
 };
 
 void qed_get_protocol_stats(struct qed_dev *cdev,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index cdd645024a32..d89a0e22f6e4 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -570,12 +570,13 @@ int qed_mcp_cmd(struct qed_hwfn *p_hwfn,
 	return 0;
 }
 
-int qed_mcp_nvm_wr_cmd(struct qed_hwfn *p_hwfn,
-		       struct qed_ptt *p_ptt,
-		       u32 cmd,
-		       u32 param,
-		       u32 *o_mcp_resp,
-		       u32 *o_mcp_param, u32 i_txn_size, u32 *i_buf)
+static int
+qed_mcp_nvm_wr_cmd(struct qed_hwfn *p_hwfn,
+		   struct qed_ptt *p_ptt,
+		   u32 cmd,
+		   u32 param,
+		   u32 *o_mcp_resp,
+		   u32 *o_mcp_param, u32 i_txn_size, u32 *i_buf)
 {
 	struct qed_mcp_mb_params mb_params;
 	int rc;
@@ -1551,7 +1552,8 @@ qed_mcp_handle_ufp_event(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 
 	if (p_hwfn->ufp_info.mode == QED_UFP_MODE_VNIC_BW) {
 		p_hwfn->qm_info.ooo_tc = p_hwfn->ufp_info.tc;
-		p_hwfn->hw_info.offload_tc = p_hwfn->ufp_info.tc;
+		qed_hw_info_set_offload_tc(&p_hwfn->hw_info,
+					   p_hwfn->ufp_info.tc);
 
 		qed_qm_reconf(p_hwfn, p_ptt);
 	} else if (p_hwfn->ufp_info.mode == QED_UFP_MODE_ETS) {
@@ -2473,6 +2475,55 @@ out:
 	return rc;
 }
 
+int qed_mcp_phy_sfp_read(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+			 u32 port, u32 addr, u32 offset, u32 len, u8 *p_buf)
+{
+	u32 bytes_left, bytes_to_copy, buf_size, nvm_offset = 0;
+	u32 resp, param;
+	int rc;
+
+	nvm_offset |= (port << DRV_MB_PARAM_TRANSCEIVER_PORT_OFFSET) &
+		       DRV_MB_PARAM_TRANSCEIVER_PORT_MASK;
+	nvm_offset |= (addr << DRV_MB_PARAM_TRANSCEIVER_I2C_ADDRESS_OFFSET) &
+		       DRV_MB_PARAM_TRANSCEIVER_I2C_ADDRESS_MASK;
+
+	addr = offset;
+	offset = 0;
+	bytes_left = len;
+	while (bytes_left > 0) {
+		bytes_to_copy = min_t(u32, bytes_left,
+				      MAX_I2C_TRANSACTION_SIZE);
+		nvm_offset &= (DRV_MB_PARAM_TRANSCEIVER_I2C_ADDRESS_MASK |
+			       DRV_MB_PARAM_TRANSCEIVER_PORT_MASK);
+		nvm_offset |= ((addr + offset) <<
+			       DRV_MB_PARAM_TRANSCEIVER_OFFSET_OFFSET) &
+			       DRV_MB_PARAM_TRANSCEIVER_OFFSET_MASK;
+		nvm_offset |= (bytes_to_copy <<
+			       DRV_MB_PARAM_TRANSCEIVER_SIZE_OFFSET) &
+			       DRV_MB_PARAM_TRANSCEIVER_SIZE_MASK;
+		rc = qed_mcp_nvm_rd_cmd(p_hwfn, p_ptt,
+					DRV_MSG_CODE_TRANSCEIVER_READ,
+					nvm_offset, &resp, &param, &buf_size,
+					(u32 *)(p_buf + offset));
+		if (rc) {
+			DP_NOTICE(p_hwfn,
+				  "Failed to send a transceiver read command to the MFW. rc = %d.\n",
+				  rc);
+			return rc;
+		}
+
+		if (resp == FW_MSG_CODE_TRANSCEIVER_NOT_PRESENT)
+			return -ENODEV;
+		else if (resp != FW_MSG_CODE_TRANSCEIVER_DIAG_OK)
+			return -EINVAL;
+
+		offset += buf_size;
+		bytes_left -= buf_size;
+	}
+
+	return 0;
+}
+
 int qed_mcp_bist_register_test(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	u32 drv_mb_param = 0, rsp, param;
@@ -2959,7 +3010,7 @@ static int qed_mcp_resource_cmd(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
-int
+static int
 __qed_mcp_resc_lock(struct qed_hwfn *p_hwfn,
 		    struct qed_ptt *p_ptt,
 		    struct qed_resc_lock_params *p_params)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
index 632a838f1fe3..047976d5c6e9 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
@@ -840,6 +840,22 @@ int qed_mcp_nvm_rd_cmd(struct qed_hwfn *p_hwfn,
 		       u32 *o_mcp_param, u32 *o_txn_size, u32 *o_buf);
 
 /**
+ * @brief Read from sfp
+ *
+ *  @param p_hwfn - hw function
+ *  @param p_ptt  - PTT required for register access
+ *  @param port   - transceiver port
+ *  @param addr   - I2C address
+ *  @param offset - offset in sfp
+ *  @param len    - buffer length
+ *  @param p_buf  - buffer to read into
+ *
+ * @return int - 0 - operation was successful.
+ */
+int qed_mcp_phy_sfp_read(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+			 u32 port, u32 addr, u32 offset, u32 len, u8 *p_buf);
+
+/**
  * @brief indicates whether the MFW objects [under mcp_info] are accessible
  *
  * @param p_hwfn
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
index 101d677114f2..be941cfaa2d4 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
@@ -134,7 +134,7 @@ static bool qed_bmap_is_empty(struct qed_bmap *bmap)
 	return bmap->max_count == find_first_bit(bmap->bitmap, bmap->max_count);
 }
 
-u32 qed_rdma_get_sb_id(void *p_hwfn, u32 rel_sb_id)
+static u32 qed_rdma_get_sb_id(void *p_hwfn, u32 rel_sb_id)
 {
 	/* First sb id for RoCE is after all the l2 sb */
 	return FEAT_NUM((struct qed_hwfn *)p_hwfn, QED_PF_L2_QUE) + rel_sb_id;
@@ -706,7 +706,7 @@ static int qed_rdma_setup(struct qed_hwfn *p_hwfn,
 	return qed_rdma_start_fw(p_hwfn, params, p_ptt);
 }
 
-int qed_rdma_stop(void *rdma_cxt)
+static int qed_rdma_stop(void *rdma_cxt)
 {
 	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
 	struct rdma_close_func_ramrod_data *p_ramrod;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index b5ce1581645f..7d7a64c55ff1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -44,8 +44,10 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
+#include <linux/if_vlan.h>
 #include "qed.h"
 #include "qed_cxt.h"
+#include "qed_dcbx.h"
 #include "qed_hsi.h"
 #include "qed_hw.h"
 #include "qed_init_ops.h"
@@ -157,7 +159,7 @@ static enum roce_flavor qed_roce_mode_to_flavor(enum roce_mode roce_mode)
 	return flavor;
 }
 
-void qed_roce_free_cid_pair(struct qed_hwfn *p_hwfn, u16 cid)
+static void qed_roce_free_cid_pair(struct qed_hwfn *p_hwfn, u16 cid)
 {
 	spin_lock_bh(&p_hwfn->p_rdma_info->lock);
 	qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->cid_map, cid);
@@ -231,16 +233,33 @@ static void qed_roce_set_real_cid(struct qed_hwfn *p_hwfn, u32 cid)
 	spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
 }
 
+static u8 qed_roce_get_qp_tc(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
+{
+	u8 pri, tc = 0;
+
+	if (qp->vlan_id) {
+		pri = (qp->vlan_id & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+		tc = qed_dcbx_get_priority_tc(p_hwfn, pri);
+	}
+
+	DP_VERBOSE(p_hwfn, QED_MSG_SP,
+		   "qp icid %u tc: %u (vlan priority %s)\n",
+		   qp->icid, tc, qp->vlan_id ? "enabled" : "disabled");
+
+	return tc;
+}
+
 static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 					struct qed_rdma_qp *qp)
 {
 	struct roce_create_qp_resp_ramrod_data *p_ramrod;
+	u16 regular_latency_queue, low_latency_queue;
 	struct qed_sp_init_data init_data;
 	enum roce_flavor roce_flavor;
 	struct qed_spq_entry *p_ent;
-	u16 regular_latency_queue;
 	enum protocol_type proto;
 	int rc;
+	u8 tc;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
 
@@ -324,12 +343,17 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 	p_ramrod->cq_cid = cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) |
 				       qp->rq_cq_id);
 
-	regular_latency_queue = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
-
+	tc = qed_roce_get_qp_tc(p_hwfn, qp);
+	regular_latency_queue = qed_get_cm_pq_idx_ofld_mtc(p_hwfn, tc);
+	low_latency_queue = qed_get_cm_pq_idx_llt_mtc(p_hwfn, tc);
+	DP_VERBOSE(p_hwfn, QED_MSG_SP,
+		   "qp icid %u pqs: regular_latency %u low_latency %u\n",
+		   qp->icid, regular_latency_queue - CM_TX_PQ_BASE,
+		   low_latency_queue - CM_TX_PQ_BASE);
 	p_ramrod->regular_latency_phy_queue =
 	    cpu_to_le16(regular_latency_queue);
 	p_ramrod->low_latency_phy_queue =
-	    cpu_to_le16(regular_latency_queue);
+	    cpu_to_le16(low_latency_queue);
 
 	p_ramrod->dpi = cpu_to_le16(qp->dpi);
 
@@ -345,11 +369,6 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 				     qp->stats_queue;
 
 	rc = qed_spq_post(p_hwfn, p_ent, NULL);
-
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
-		   "rc = %d regular physical queue = 0x%x\n", rc,
-		   regular_latency_queue);
-
 	if (rc)
 		goto err;
 
@@ -375,12 +394,13 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 					struct qed_rdma_qp *qp)
 {
 	struct roce_create_qp_req_ramrod_data *p_ramrod;
+	u16 regular_latency_queue, low_latency_queue;
 	struct qed_sp_init_data init_data;
 	enum roce_flavor roce_flavor;
 	struct qed_spq_entry *p_ent;
-	u16 regular_latency_queue;
 	enum protocol_type proto;
 	int rc;
+	u8 tc;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
 
@@ -453,12 +473,17 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 	p_ramrod->cq_cid =
 	    cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) | qp->sq_cq_id);
 
-	regular_latency_queue = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
-
+	tc = qed_roce_get_qp_tc(p_hwfn, qp);
+	regular_latency_queue = qed_get_cm_pq_idx_ofld_mtc(p_hwfn, tc);
+	low_latency_queue = qed_get_cm_pq_idx_llt_mtc(p_hwfn, tc);
+	DP_VERBOSE(p_hwfn, QED_MSG_SP,
+		   "qp icid %u pqs: regular_latency %u low_latency %u\n",
+		   qp->icid, regular_latency_queue - CM_TX_PQ_BASE,
+		   low_latency_queue - CM_TX_PQ_BASE);
 	p_ramrod->regular_latency_phy_queue =
 	    cpu_to_le16(regular_latency_queue);
 	p_ramrod->low_latency_phy_queue =
-	    cpu_to_le16(regular_latency_queue);
+	    cpu_to_le16(low_latency_queue);
 
 	p_ramrod->dpi = cpu_to_le16(qp->dpi);
 
@@ -471,9 +496,6 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 				     qp->stats_queue;
 
 	rc = qed_spq_post(p_hwfn, p_ent, NULL);
-
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "rc = %d\n", rc);
-
 	if (rc)
 		goto err;
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index 26e918d7f2f9..9b08a9d9e151 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -672,8 +672,8 @@ int qed_iov_hw_info(struct qed_hwfn *p_hwfn)
 	return 0;
 }
 
-bool _qed_iov_pf_sanity_check(struct qed_hwfn *p_hwfn,
-			      int vfid, bool b_fail_malicious)
+static bool _qed_iov_pf_sanity_check(struct qed_hwfn *p_hwfn,
+				     int vfid, bool b_fail_malicious)
 {
 	/* Check PF supports sriov */
 	if (IS_VF(p_hwfn->cdev) || !IS_QED_SRIOV(p_hwfn->cdev) ||
@@ -687,7 +687,7 @@ bool _qed_iov_pf_sanity_check(struct qed_hwfn *p_hwfn,
 	return true;
 }
 
-bool qed_iov_pf_sanity_check(struct qed_hwfn *p_hwfn, int vfid)
+static bool qed_iov_pf_sanity_check(struct qed_hwfn *p_hwfn, int vfid)
 {
 	return _qed_iov_pf_sanity_check(p_hwfn, vfid, true);
 }
@@ -3979,7 +3979,7 @@ static void qed_iov_process_mbx_req(struct qed_hwfn *p_hwfn,
 	}
 }
 
-void qed_iov_pf_get_pending_events(struct qed_hwfn *p_hwfn, u64 *events)
+static void qed_iov_pf_get_pending_events(struct qed_hwfn *p_hwfn, u64 *events)
 {
 	int i;
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index be6ddde1a104..3d4269659820 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -169,7 +169,7 @@ static void qed_vf_pf_add_qid(struct qed_hwfn *p_hwfn,
 	p_qid_tlv->qid = p_cid->qid_usage_idx;
 }
 
-int _qed_vf_pf_release(struct qed_hwfn *p_hwfn, bool b_final)
+static int _qed_vf_pf_release(struct qed_hwfn *p_hwfn, bool b_final)
 {
 	struct qed_vf_iov *p_iov = p_hwfn->vf_iov_info;
 	struct pfvf_def_resp_tlv *resp;
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index d7ed0d3dbf71..6a4d266fb8e2 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -52,6 +52,9 @@
 #include <linux/qed/qed_chain.h>
 #include <linux/qed/qed_eth_if.h>
 
+#include <net/pkt_cls.h>
+#include <net/tc_act/tc_gact.h>
+
 #define QEDE_MAJOR_VERSION		8
 #define QEDE_MINOR_VERSION		33
 #define QEDE_REVISION_VERSION		0
@@ -386,6 +389,15 @@ struct qede_tx_queue {
 #define QEDE_TXQ_XDP_TO_IDX(edev, txq)	((txq)->index - \
 					 QEDE_MAX_TSS_CNT(edev))
 #define QEDE_TXQ_IDX_TO_XDP(edev, idx)	((idx) + QEDE_MAX_TSS_CNT(edev))
+#define QEDE_NDEV_TXQ_ID_TO_FP_ID(edev, idx)	((edev)->fp_num_rx + \
+						 ((idx) % QEDE_TSS_COUNT(edev)))
+#define QEDE_NDEV_TXQ_ID_TO_TXQ_COS(edev, idx)	((idx) / QEDE_TSS_COUNT(edev))
+#define QEDE_TXQ_TO_NDEV_TXQ_ID(edev, txq)	((QEDE_TSS_COUNT(edev) * \
+						 (txq)->cos) + (txq)->index)
+#define QEDE_NDEV_TXQ_ID_TO_TXQ(edev, idx)	\
+	(&((edev)->fp_array[QEDE_NDEV_TXQ_ID_TO_FP_ID(edev, idx)].txq \
+	[QEDE_NDEV_TXQ_ID_TO_TXQ_COS(edev, idx)]))
+#define QEDE_FP_TC0_TXQ(fp)	(&((fp)->txq[0]))
 
 	/* Regular Tx requires skb + metadata for release purpose,
 	 * while XDP requires the pages and the mapped address.
@@ -399,6 +411,8 @@ struct qede_tx_queue {
 
 	/* Slowpath; Should be kept in end [unless missing padding] */
 	void *handle;
+	u16 cos;
+	u16 ndev_txq_id;
 };
 
 #define BD_UNMAP_ADDR(bd)		HILO_U64(le32_to_cpu((bd)->addr.hi), \
@@ -458,7 +472,7 @@ void qede_arfs_filter_op(void *dev, void *filter, u8 fw_rc);
 void qede_free_arfs(struct qede_dev *edev);
 int qede_alloc_arfs(struct qede_dev *edev);
 int qede_add_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info);
-int qede_del_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info);
+int qede_delete_flow_filter(struct qede_dev *edev, u64 cookie);
 int qede_get_cls_rule_entry(struct qede_dev *edev, struct ethtool_rxnfc *cmd);
 int qede_get_cls_rule_all(struct qede_dev *edev, struct ethtool_rxnfc *info,
 			  u32 *rule_locs);
@@ -524,6 +538,8 @@ bool qede_has_rx_work(struct qede_rx_queue *rxq);
 int qede_txq_has_work(struct qede_tx_queue *txq);
 void qede_recycle_rx_bd_ring(struct qede_rx_queue *rxq, u8 count);
 void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq);
+int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto,
+			    struct tc_cls_flower_offload *f);
 
 #define RX_RING_SIZE_POW	13
 #define RX_RING_SIZE		((u16)BIT(RX_RING_SIZE_POW))
@@ -541,5 +557,7 @@ void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq);
 #define QEDE_RX_HDR_SIZE		256
 #define QEDE_MAX_JUMBO_PACKET_SIZE	9600
 #define	for_each_queue(i) for (i = 0; i < edev->num_queues; i++)
+#define for_each_cos_in_txq(edev, var) \
+	for ((var) = 0; (var) < (edev)->dev_info.num_tc; (var)++)
 
 #endif /* _QEDE_H_ */
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index f4a0f8ff8261..19652cd27ca7 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -222,7 +222,7 @@ static void qede_get_strings_stats_txq(struct qede_dev *edev,
 				QEDE_TXQ_XDP_TO_IDX(edev, txq),
 				qede_tqstats_arr[i].string);
 		else
-			sprintf(*buf, "%d: %s", txq->index,
+			sprintf(*buf, "%d_%d: %s", txq->index, txq->cos,
 				qede_tqstats_arr[i].string);
 		*buf += ETH_GSTRING_LEN;
 	}
@@ -262,8 +262,13 @@ static void qede_get_strings_stats(struct qede_dev *edev, u8 *buf)
 		if (fp->type & QEDE_FASTPATH_XDP)
 			qede_get_strings_stats_txq(edev, fp->xdp_tx, &buf);
 
-		if (fp->type & QEDE_FASTPATH_TX)
-			qede_get_strings_stats_txq(edev, fp->txq, &buf);
+		if (fp->type & QEDE_FASTPATH_TX) {
+			int cos;
+
+			for_each_cos_in_txq(edev, cos)
+				qede_get_strings_stats_txq(edev,
+							   &fp->txq[cos], &buf);
+		}
 	}
 
 	/* Account for non-queue statistics */
@@ -338,8 +343,12 @@ static void qede_get_ethtool_stats(struct net_device *dev,
 		if (fp->type & QEDE_FASTPATH_XDP)
 			qede_get_ethtool_stats_txq(fp->xdp_tx, &buf);
 
-		if (fp->type & QEDE_FASTPATH_TX)
-			qede_get_ethtool_stats_txq(fp->txq, &buf);
+		if (fp->type & QEDE_FASTPATH_TX) {
+			int cos;
+
+			for_each_cos_in_txq(edev, cos)
+				qede_get_ethtool_stats_txq(&fp->txq[cos], &buf);
+		}
 	}
 
 	for (i = 0; i < QEDE_NUM_STATS; i++) {
@@ -366,7 +375,8 @@ static int qede_get_sset_count(struct net_device *dev, int stringset)
 				num_stats--;
 
 		/* Account for the Regular Tx statistics */
-		num_stats += QEDE_TSS_COUNT(edev) * QEDE_NUM_TQSTATS;
+		num_stats += QEDE_TSS_COUNT(edev) * QEDE_NUM_TQSTATS *
+				edev->dev_info.num_tc;
 
 		/* Account for the Regular Rx statistics */
 		num_stats += QEDE_RSS_COUNT(edev) * QEDE_NUM_RQSTATS;
@@ -741,9 +751,17 @@ static int qede_get_coalesce(struct net_device *dev,
 		}
 
 		for_each_queue(i) {
+			struct qede_tx_queue *txq;
+
 			fp = &edev->fp_array[i];
+
+			/* All TX queues of given fastpath uses same
+			 * coalescing value, so no need to iterate over
+			 * all TCs, TC0 txq should suffice.
+			 */
 			if (fp->type & QEDE_FASTPATH_TX) {
-				tx_handle = fp->txq->handle;
+				txq = QEDE_FP_TC0_TXQ(fp);
+				tx_handle = txq->handle;
 				break;
 			}
 		}
@@ -801,9 +819,17 @@ static int qede_set_coalesce(struct net_device *dev,
 		}
 
 		if (edev->fp_array[i].type & QEDE_FASTPATH_TX) {
+			struct qede_tx_queue *txq;
+
+			/* All TX queues of given fastpath uses same
+			 * coalescing value, so no need to iterate over
+			 * all TCs, TC0 txq should suffice.
+			 */
+			txq = QEDE_FP_TC0_TXQ(fp);
+
 			rc = edev->ops->common->set_coalesce(edev->cdev,
 							     0, txc,
-							     fp->txq->handle);
+							     txq->handle);
 			if (rc) {
 				DP_INFO(edev,
 					"Set TX coalesce error, rc = %d\n", rc);
@@ -1259,7 +1285,7 @@ static int qede_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info)
 		rc = qede_add_cls_rule(edev, info);
 		break;
 	case ETHTOOL_SRXCLSRLDEL:
-		rc = qede_del_cls_rule(edev, info);
+		rc = qede_delete_flow_filter(edev, info->fs.location);
 		break;
 	default:
 		DP_INFO(edev, "Command parameters not supported\n");
@@ -1385,8 +1411,10 @@ static int qede_selftest_transmit_traffic(struct qede_dev *edev,
 	u16 val;
 
 	for_each_queue(i) {
-		if (edev->fp_array[i].type & QEDE_FASTPATH_TX) {
-			txq = edev->fp_array[i].txq;
+		struct qede_fastpath *fp = &edev->fp_array[i];
+
+		if (fp->type & QEDE_FASTPATH_TX) {
+			txq = QEDE_FP_TC0_TXQ(fp);
 			break;
 		}
 	}
@@ -1780,6 +1808,92 @@ static int qede_set_eee(struct net_device *dev, struct ethtool_eee *edata)
 	return 0;
 }
 
+static int qede_get_module_info(struct net_device *dev,
+				struct ethtool_modinfo *modinfo)
+{
+	struct qede_dev *edev = netdev_priv(dev);
+	u8 buf[4];
+	int rc;
+
+	/* Read first 4 bytes to find the sfp type */
+	rc = edev->ops->common->read_module_eeprom(edev->cdev, buf,
+						   QED_I2C_DEV_ADDR_A0, 0, 4);
+	if (rc) {
+		DP_ERR(edev, "Failed reading EEPROM data %d\n", rc);
+		return rc;
+	}
+
+	switch (buf[0]) {
+	case 0x3: /* SFP, SFP+, SFP-28 */
+		modinfo->type = ETH_MODULE_SFF_8472;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+		break;
+	case 0xc: /* QSFP */
+	case 0xd: /* QSFP+ */
+		modinfo->type = ETH_MODULE_SFF_8436;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
+		break;
+	case 0x11: /* QSFP-28 */
+		modinfo->type = ETH_MODULE_SFF_8636;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN;
+		break;
+	default:
+		DP_ERR(edev, "Unknown transceiver type 0x%x\n", buf[0]);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int qede_get_module_eeprom(struct net_device *dev,
+				  struct ethtool_eeprom *ee, u8 *data)
+{
+	struct qede_dev *edev = netdev_priv(dev);
+	u32 start_addr = ee->offset, size = 0;
+	u8 *buf = data;
+	int rc = 0;
+
+	/* Read A0 section */
+	if (ee->offset < ETH_MODULE_SFF_8079_LEN) {
+		/* Limit transfer size to the A0 section boundary */
+		if (ee->offset + ee->len > ETH_MODULE_SFF_8079_LEN)
+			size = ETH_MODULE_SFF_8079_LEN - ee->offset;
+		else
+			size = ee->len;
+
+		rc = edev->ops->common->read_module_eeprom(edev->cdev, buf,
+							   QED_I2C_DEV_ADDR_A0,
+							   start_addr, size);
+		if (rc) {
+			DP_ERR(edev, "Failed reading A0 section  %d\n", rc);
+			return rc;
+		}
+
+		buf += size;
+		start_addr += size;
+	}
+
+	/* Read A2 section */
+	if (start_addr >= ETH_MODULE_SFF_8079_LEN &&
+	    start_addr < ETH_MODULE_SFF_8472_LEN) {
+		size = ee->len - size;
+		/* Limit transfer size to the A2 section boundary */
+		if (start_addr + size > ETH_MODULE_SFF_8472_LEN)
+			size = ETH_MODULE_SFF_8472_LEN - start_addr;
+		start_addr -= ETH_MODULE_SFF_8079_LEN;
+		rc = edev->ops->common->read_module_eeprom(edev->cdev, buf,
+							   QED_I2C_DEV_ADDR_A2,
+							   start_addr, size);
+		if (rc) {
+			DP_VERBOSE(edev, QED_MSG_DEBUG,
+				   "Failed reading A2 section %d\n", rc);
+			return 0;
+		}
+	}
+
+	return rc;
+}
+
 static const struct ethtool_ops qede_ethtool_ops = {
 	.get_link_ksettings = qede_get_link_ksettings,
 	.set_link_ksettings = qede_set_link_ksettings,
@@ -1813,6 +1927,8 @@ static const struct ethtool_ops qede_ethtool_ops = {
 	.get_channels = qede_get_channels,
 	.set_channels = qede_set_channels,
 	.self_test = qede_self_test,
+	.get_module_info = qede_get_module_info,
+	.get_module_eeprom = qede_get_module_eeprom,
 	.get_eee = qede_get_eee,
 	.set_eee = qede_set_eee,
 
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index b823bfe2ea4d..9673d19308e6 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -83,7 +83,7 @@ struct qede_arfs_fltr_node {
 	struct qede_arfs_tuple tuple;
 
 	u32 flow_id;
-	u16 sw_id;
+	u64 sw_id;
 	u16 rxq_id;
 	u16 next_rxq_id;
 	u8 vfid;
@@ -138,7 +138,7 @@ static void qede_configure_arfs_fltr(struct qede_dev *edev,
 
 		n->tuple.stringify(&n->tuple, tuple_buffer);
 		DP_VERBOSE(edev, NETIF_MSG_RX_STATUS,
-			   "%s sw_id[0x%x]: %s [vf %u queue %d]\n",
+			   "%s sw_id[0x%llx]: %s [vf %u queue %d]\n",
 			   add_fltr ? "Adding" : "Deleting",
 			   n->sw_id, tuple_buffer, n->vfid, rxq_id);
 	}
@@ -152,7 +152,10 @@ static void
 qede_free_arfs_filter(struct qede_dev *edev,  struct qede_arfs_fltr_node *fltr)
 {
 	kfree(fltr->data);
-	clear_bit(fltr->sw_id, edev->arfs->arfs_fltr_bmap);
+
+	if (fltr->sw_id < QEDE_RFS_MAX_FLTR)
+		clear_bit(fltr->sw_id, edev->arfs->arfs_fltr_bmap);
+
 	kfree(fltr);
 }
 
@@ -214,7 +217,7 @@ void qede_arfs_filter_op(void *dev, void *filter, u8 fw_rc)
 
 	if (fw_rc) {
 		DP_NOTICE(edev,
-			  "Failed arfs filter configuration fw_rc=%d, flow_id=%d, sw_id=%d, src_port=%d, dst_port=%d, rxq=%d\n",
+			  "Failed arfs filter configuration fw_rc=%d, flow_id=%d, sw_id=0x%llx, src_port=%d, dst_port=%d, rxq=%d\n",
 			  fw_rc, fltr->flow_id, fltr->sw_id,
 			  ntohs(fltr->tuple.src_port),
 			  ntohs(fltr->tuple.dst_port), fltr->rxq_id);
@@ -1116,7 +1119,6 @@ int qede_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	case XDP_SETUP_PROG:
 		return qede_xdp_set(edev, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!edev->xdp_prog;
 		xdp->prog_id = edev->xdp_prog ? edev->xdp_prog->aux->id : 0;
 		return 0;
 	default:
@@ -1349,7 +1351,7 @@ out:
 }
 
 static struct qede_arfs_fltr_node *
-qede_get_arfs_fltr_by_loc(struct hlist_head *head, u32 location)
+qede_get_arfs_fltr_by_loc(struct hlist_head *head, u64 location)
 {
 	struct qede_arfs_fltr_node *fltr;
 
@@ -1600,6 +1602,69 @@ static int qede_flow_spec_validate_unused(struct qede_dev *edev,
 	return 0;
 }
 
+static int qede_set_v4_tuple_to_profile(struct qede_dev *edev,
+					struct qede_arfs_tuple *t)
+{
+	/* We must have Only 4-tuples/l4 port/src ip/dst ip
+	 * as an input.
+	 */
+	if (t->src_port && t->dst_port && t->src_ipv4 && t->dst_ipv4) {
+		t->mode = QED_FILTER_CONFIG_MODE_5_TUPLE;
+	} else if (!t->src_port && t->dst_port &&
+		   !t->src_ipv4 && !t->dst_ipv4) {
+		t->mode = QED_FILTER_CONFIG_MODE_L4_PORT;
+	} else if (!t->src_port && !t->dst_port &&
+		   !t->dst_ipv4 && t->src_ipv4) {
+		t->mode = QED_FILTER_CONFIG_MODE_IP_SRC;
+	} else if (!t->src_port && !t->dst_port &&
+		   t->dst_ipv4 && !t->src_ipv4) {
+		t->mode = QED_FILTER_CONFIG_MODE_IP_DEST;
+	} else {
+		DP_INFO(edev, "Invalid N-tuple\n");
+		return -EOPNOTSUPP;
+	}
+
+	t->ip_comp = qede_flow_spec_ipv4_cmp;
+	t->build_hdr = qede_flow_build_ipv4_hdr;
+	t->stringify = qede_flow_stringify_ipv4_hdr;
+
+	return 0;
+}
+
+static int qede_set_v6_tuple_to_profile(struct qede_dev *edev,
+					struct qede_arfs_tuple *t,
+					struct in6_addr *zaddr)
+{
+	/* We must have Only 4-tuples/l4 port/src ip/dst ip
+	 * as an input.
+	 */
+	if (t->src_port && t->dst_port &&
+	    memcmp(&t->src_ipv6, zaddr, sizeof(struct in6_addr)) &&
+	    memcmp(&t->dst_ipv6, zaddr, sizeof(struct in6_addr))) {
+		t->mode = QED_FILTER_CONFIG_MODE_5_TUPLE;
+	} else if (!t->src_port && t->dst_port &&
+		   !memcmp(&t->src_ipv6, zaddr, sizeof(struct in6_addr)) &&
+		   !memcmp(&t->dst_ipv6, zaddr, sizeof(struct in6_addr))) {
+		t->mode = QED_FILTER_CONFIG_MODE_L4_PORT;
+	} else if (!t->src_port && !t->dst_port &&
+		   !memcmp(&t->dst_ipv6, zaddr, sizeof(struct in6_addr)) &&
+		   memcmp(&t->src_ipv6, zaddr, sizeof(struct in6_addr))) {
+		t->mode = QED_FILTER_CONFIG_MODE_IP_SRC;
+	} else if (!t->src_port && !t->dst_port &&
+		   memcmp(&t->dst_ipv6, zaddr, sizeof(struct in6_addr)) &&
+		   !memcmp(&t->src_ipv6, zaddr, sizeof(struct in6_addr))) {
+		t->mode = QED_FILTER_CONFIG_MODE_IP_DEST;
+	} else {
+		DP_INFO(edev, "Invalid N-tuple\n");
+		return -EOPNOTSUPP;
+	}
+
+	t->ip_comp = qede_flow_spec_ipv6_cmp;
+	t->build_hdr = qede_flow_build_ipv6_hdr;
+
+	return 0;
+}
+
 static int qede_flow_spec_to_tuple_ipv4_common(struct qede_dev *edev,
 					       struct qede_arfs_tuple *t,
 					       struct ethtool_rx_flow_spec *fs)
@@ -1639,27 +1704,7 @@ static int qede_flow_spec_to_tuple_ipv4_common(struct qede_dev *edev,
 	t->src_port = fs->h_u.tcp_ip4_spec.psrc;
 	t->dst_port = fs->h_u.tcp_ip4_spec.pdst;
 
-	/* We must either have a valid 4-tuple or only dst port
-	 * or only src ip as an input
-	 */
-	if (t->src_port && t->dst_port && t->src_ipv4 && t->dst_ipv4) {
-		t->mode = QED_FILTER_CONFIG_MODE_5_TUPLE;
-	} else if (!t->src_port && t->dst_port &&
-		   !t->src_ipv4 && !t->dst_ipv4) {
-		t->mode = QED_FILTER_CONFIG_MODE_L4_PORT;
-	}  else if (!t->src_port && !t->dst_port &&
-		    !t->dst_ipv4 && t->src_ipv4) {
-		t->mode = QED_FILTER_CONFIG_MODE_IP_SRC;
-	} else {
-		DP_INFO(edev, "Invalid N-tuple\n");
-		return -EOPNOTSUPP;
-	}
-
-	t->ip_comp = qede_flow_spec_ipv4_cmp;
-	t->build_hdr = qede_flow_build_ipv4_hdr;
-	t->stringify = qede_flow_stringify_ipv4_hdr;
-
-	return 0;
+	return qede_set_v4_tuple_to_profile(edev, t);
 }
 
 static int qede_flow_spec_to_tuple_tcpv4(struct qede_dev *edev,
@@ -1691,10 +1736,8 @@ static int qede_flow_spec_to_tuple_ipv6_common(struct qede_dev *edev,
 					       struct ethtool_rx_flow_spec *fs)
 {
 	struct in6_addr zero_addr;
-	void *p;
 
-	p = &zero_addr;
-	memset(p, 0, sizeof(zero_addr));
+	memset(&zero_addr, 0, sizeof(zero_addr));
 
 	if ((fs->h_u.tcp_ip6_spec.psrc &
 	     fs->m_u.tcp_ip6_spec.psrc) != fs->h_u.tcp_ip6_spec.psrc) {
@@ -1721,30 +1764,7 @@ static int qede_flow_spec_to_tuple_ipv6_common(struct qede_dev *edev,
 	t->src_port = fs->h_u.tcp_ip6_spec.psrc;
 	t->dst_port = fs->h_u.tcp_ip6_spec.pdst;
 
-	/* We must make sure we have a valid 4-tuple or only dest port
-	 * or only src ip as an input
-	 */
-	if (t->src_port && t->dst_port &&
-	    memcmp(&t->src_ipv6, p, sizeof(struct in6_addr)) &&
-	    memcmp(&t->dst_ipv6, p, sizeof(struct in6_addr))) {
-		t->mode = QED_FILTER_CONFIG_MODE_5_TUPLE;
-	} else if (!t->src_port && t->dst_port &&
-		   !memcmp(&t->src_ipv6, p, sizeof(struct in6_addr)) &&
-		   !memcmp(&t->dst_ipv6, p, sizeof(struct in6_addr))) {
-		t->mode = QED_FILTER_CONFIG_MODE_L4_PORT;
-	} else if (!t->src_port && !t->dst_port &&
-		   !memcmp(&t->dst_ipv6, p, sizeof(struct in6_addr)) &&
-		   memcmp(&t->src_ipv6, p, sizeof(struct in6_addr))) {
-		t->mode = QED_FILTER_CONFIG_MODE_IP_SRC;
-	} else {
-		DP_INFO(edev, "Invalid N-tuple\n");
-		return -EOPNOTSUPP;
-	}
-
-	t->ip_comp = qede_flow_spec_ipv6_cmp;
-	t->build_hdr = qede_flow_build_ipv6_hdr;
-
-	return 0;
+	return qede_set_v6_tuple_to_profile(edev, t, &zero_addr);
 }
 
 static int qede_flow_spec_to_tuple_tcpv6(struct qede_dev *edev,
@@ -1942,9 +1962,8 @@ unlock:
 	return rc;
 }
 
-int qede_del_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info)
+int qede_delete_flow_filter(struct qede_dev *edev, u64 cookie)
 {
-	struct ethtool_rx_flow_spec *fsp = &info->fs;
 	struct qede_arfs_fltr_node *fltr = NULL;
 	int rc = -EPERM;
 
@@ -1953,7 +1972,7 @@ int qede_del_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info)
 		goto unlock;
 
 	fltr = qede_get_arfs_fltr_by_loc(QEDE_ARFS_BUCKET_HEAD(edev, 0),
-					 fsp->location);
+					 cookie);
 	if (!fltr)
 		goto unlock;
 
@@ -1983,3 +2002,293 @@ unlock:
 	__qede_unlock(edev);
 	return count;
 }
+
+static int qede_parse_actions(struct qede_dev *edev,
+			      struct tcf_exts *exts)
+{
+	int rc = -EINVAL, num_act = 0;
+	const struct tc_action *a;
+	bool is_drop = false;
+	LIST_HEAD(actions);
+
+	if (!tcf_exts_has_actions(exts)) {
+		DP_NOTICE(edev, "No tc actions received\n");
+		return rc;
+	}
+
+	tcf_exts_to_list(exts, &actions);
+	list_for_each_entry(a, &actions, list) {
+		num_act++;
+
+		if (is_tcf_gact_shot(a))
+			is_drop = true;
+	}
+
+	if (num_act == 1 && is_drop)
+		return 0;
+
+	return rc;
+}
+
+static int
+qede_tc_parse_ports(struct qede_dev *edev,
+		    struct tc_cls_flower_offload *f,
+		    struct qede_arfs_tuple *t)
+{
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_dissector_key_ports *key, *mask;
+
+		key = skb_flow_dissector_target(f->dissector,
+						FLOW_DISSECTOR_KEY_PORTS,
+						f->key);
+		mask = skb_flow_dissector_target(f->dissector,
+						 FLOW_DISSECTOR_KEY_PORTS,
+						 f->mask);
+
+		if ((key->src && mask->src != U16_MAX) ||
+		    (key->dst && mask->dst != U16_MAX)) {
+			DP_NOTICE(edev, "Do not support ports masks\n");
+			return -EINVAL;
+		}
+
+		t->src_port = key->src;
+		t->dst_port = key->dst;
+	}
+
+	return 0;
+}
+
+static int
+qede_tc_parse_v6_common(struct qede_dev *edev,
+			struct tc_cls_flower_offload *f,
+			struct qede_arfs_tuple *t)
+{
+	struct in6_addr zero_addr, addr;
+
+	memset(&zero_addr, 0, sizeof(addr));
+	memset(&addr, 0xff, sizeof(addr));
+
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
+		struct flow_dissector_key_ipv6_addrs *key, *mask;
+
+		key = skb_flow_dissector_target(f->dissector,
+						FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+						f->key);
+		mask = skb_flow_dissector_target(f->dissector,
+						 FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+						 f->mask);
+
+		if ((memcmp(&key->src, &zero_addr, sizeof(addr)) &&
+		     memcmp(&mask->src, &addr, sizeof(addr))) ||
+		    (memcmp(&key->dst, &zero_addr, sizeof(addr)) &&
+		     memcmp(&mask->dst, &addr, sizeof(addr)))) {
+			DP_NOTICE(edev,
+				  "Do not support IPv6 address prefix/mask\n");
+			return -EINVAL;
+		}
+
+		memcpy(&t->src_ipv6, &key->src, sizeof(addr));
+		memcpy(&t->dst_ipv6, &key->dst, sizeof(addr));
+	}
+
+	if (qede_tc_parse_ports(edev, f, t))
+		return -EINVAL;
+
+	return qede_set_v6_tuple_to_profile(edev, t, &zero_addr);
+}
+
+static int
+qede_tc_parse_v4_common(struct qede_dev *edev,
+			struct tc_cls_flower_offload *f,
+			struct qede_arfs_tuple *t)
+{
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
+		struct flow_dissector_key_ipv4_addrs *key, *mask;
+
+		key = skb_flow_dissector_target(f->dissector,
+						FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+						f->key);
+		mask = skb_flow_dissector_target(f->dissector,
+						 FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+						 f->mask);
+
+		if ((key->src && mask->src != U32_MAX) ||
+		    (key->dst && mask->dst != U32_MAX)) {
+			DP_NOTICE(edev, "Do not support ipv4 prefix/masks\n");
+			return -EINVAL;
+		}
+
+		t->src_ipv4 = key->src;
+		t->dst_ipv4 = key->dst;
+	}
+
+	if (qede_tc_parse_ports(edev, f, t))
+		return -EINVAL;
+
+	return qede_set_v4_tuple_to_profile(edev, t);
+}
+
+static int
+qede_tc_parse_tcp_v6(struct qede_dev *edev,
+		     struct tc_cls_flower_offload *f,
+		     struct qede_arfs_tuple *tuple)
+{
+	tuple->ip_proto = IPPROTO_TCP;
+	tuple->eth_proto = htons(ETH_P_IPV6);
+
+	return qede_tc_parse_v6_common(edev, f, tuple);
+}
+
+static int
+qede_tc_parse_tcp_v4(struct qede_dev *edev,
+		     struct tc_cls_flower_offload *f,
+		     struct qede_arfs_tuple *tuple)
+{
+	tuple->ip_proto = IPPROTO_TCP;
+	tuple->eth_proto = htons(ETH_P_IP);
+
+	return qede_tc_parse_v4_common(edev, f, tuple);
+}
+
+static int
+qede_tc_parse_udp_v6(struct qede_dev *edev,
+		     struct tc_cls_flower_offload *f,
+		     struct qede_arfs_tuple *tuple)
+{
+	tuple->ip_proto = IPPROTO_UDP;
+	tuple->eth_proto = htons(ETH_P_IPV6);
+
+	return qede_tc_parse_v6_common(edev, f, tuple);
+}
+
+static int
+qede_tc_parse_udp_v4(struct qede_dev *edev,
+		     struct tc_cls_flower_offload *f,
+		     struct qede_arfs_tuple *tuple)
+{
+	tuple->ip_proto = IPPROTO_UDP;
+	tuple->eth_proto = htons(ETH_P_IP);
+
+	return qede_tc_parse_v4_common(edev, f, tuple);
+}
+
+static int
+qede_parse_flower_attr(struct qede_dev *edev, __be16 proto,
+		       struct tc_cls_flower_offload *f,
+		       struct qede_arfs_tuple *tuple)
+{
+	int rc = -EINVAL;
+	u8 ip_proto = 0;
+
+	memset(tuple, 0, sizeof(*tuple));
+
+	if (f->dissector->used_keys &
+	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT(FLOW_DISSECTOR_KEY_PORTS))) {
+		DP_NOTICE(edev, "Unsupported key set:0x%x\n",
+			  f->dissector->used_keys);
+		return -EOPNOTSUPP;
+	}
+
+	if (proto != htons(ETH_P_IP) &&
+	    proto != htons(ETH_P_IPV6)) {
+		DP_NOTICE(edev, "Unsupported proto=0x%x\n", proto);
+		return -EPROTONOSUPPORT;
+	}
+
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_dissector_key_basic *key;
+
+		key = skb_flow_dissector_target(f->dissector,
+						FLOW_DISSECTOR_KEY_BASIC,
+						f->key);
+		ip_proto = key->ip_proto;
+	}
+
+	if (ip_proto == IPPROTO_TCP && proto == htons(ETH_P_IP))
+		rc = qede_tc_parse_tcp_v4(edev, f, tuple);
+	else if (ip_proto == IPPROTO_TCP && proto == htons(ETH_P_IPV6))
+		rc = qede_tc_parse_tcp_v6(edev, f, tuple);
+	else if (ip_proto == IPPROTO_UDP && proto == htons(ETH_P_IP))
+		rc = qede_tc_parse_udp_v4(edev, f, tuple);
+	else if (ip_proto == IPPROTO_UDP && proto == htons(ETH_P_IPV6))
+		rc = qede_tc_parse_udp_v6(edev, f, tuple);
+	else
+		DP_NOTICE(edev, "Invalid tc protocol request\n");
+
+	return rc;
+}
+
+int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto,
+			    struct tc_cls_flower_offload *f)
+{
+	struct qede_arfs_fltr_node *n;
+	int min_hlen, rc = -EINVAL;
+	struct qede_arfs_tuple t;
+
+	__qede_lock(edev);
+
+	if (!edev->arfs) {
+		rc = -EPERM;
+		goto unlock;
+	}
+
+	/* parse flower attribute and prepare filter */
+	if (qede_parse_flower_attr(edev, proto, f, &t))
+		goto unlock;
+
+	/* Validate profile mode and number of filters */
+	if ((edev->arfs->filter_count && edev->arfs->mode != t.mode) ||
+	    edev->arfs->filter_count == QEDE_RFS_MAX_FLTR) {
+		DP_NOTICE(edev,
+			  "Filter configuration invalidated, filter mode=0x%x, configured mode=0x%x, filter count=0x%x\n",
+			  t.mode, edev->arfs->mode, edev->arfs->filter_count);
+		goto unlock;
+	}
+
+	/* parse tc actions and get the vf_id */
+	if (qede_parse_actions(edev, f->exts))
+		goto unlock;
+
+	if (qede_flow_find_fltr(edev, &t)) {
+		rc = -EEXIST;
+		goto unlock;
+	}
+
+	n = kzalloc(sizeof(*n), GFP_KERNEL);
+	if (!n) {
+		rc = -ENOMEM;
+		goto unlock;
+	}
+
+	min_hlen = qede_flow_get_min_header_size(&t);
+
+	n->data = kzalloc(min_hlen, GFP_KERNEL);
+	if (!n->data) {
+		kfree(n);
+		rc = -ENOMEM;
+		goto unlock;
+	}
+
+	memcpy(&n->tuple, &t, sizeof(n->tuple));
+
+	n->buf_len = min_hlen;
+	n->b_is_drop = true;
+	n->sw_id = f->cookie;
+
+	n->tuple.build_hdr(&n->tuple, n->data);
+
+	rc = qede_enqueue_fltr_and_config_searcher(edev, n, 0);
+	if (rc)
+		goto unlock;
+
+	qede_configure_arfs_fltr(edev, n, n->rxq_id, true);
+	rc = qede_poll_arfs_filter_config(edev, n);
+
+unlock:
+	__qede_unlock(edev);
+	return rc;
+}
diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index 6c702399b801..1a78027de071 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -408,12 +408,12 @@ static void qede_xdp_tx_int(struct qede_dev *edev, struct qede_tx_queue *txq)
 
 static int qede_tx_int(struct qede_dev *edev, struct qede_tx_queue *txq)
 {
+	unsigned int pkts_compl = 0, bytes_compl = 0;
 	struct netdev_queue *netdev_txq;
 	u16 hw_bd_cons;
-	unsigned int pkts_compl = 0, bytes_compl = 0;
 	int rc;
 
-	netdev_txq = netdev_get_tx_queue(edev->ndev, txq->index);
+	netdev_txq = netdev_get_tx_queue(edev->ndev, txq->ndev_txq_id);
 
 	hw_bd_cons = le16_to_cpu(*txq->hw_cons_ptr);
 	barrier();
@@ -1119,8 +1119,10 @@ static bool qede_rx_xdp(struct qede_dev *edev,
 
 	default:
 		bpf_warn_invalid_xdp_action(act);
+		/* Fall through */
 	case XDP_ABORTED:
 		trace_xdp_exception(edev->ndev, prog, act);
+		/* Fall through */
 	case XDP_DROP:
 		qede_recycle_rx_bd_ring(rxq, cqe->bd_num);
 	}
@@ -1363,9 +1365,14 @@ static bool qede_poll_is_more_work(struct qede_fastpath *fp)
 		if (qede_txq_has_work(fp->xdp_tx))
 			return true;
 
-	if (likely(fp->type & QEDE_FASTPATH_TX))
-		if (qede_txq_has_work(fp->txq))
-			return true;
+	if (likely(fp->type & QEDE_FASTPATH_TX)) {
+		int cos;
+
+		for_each_cos_in_txq(fp->edev, cos) {
+			if (qede_txq_has_work(&fp->txq[cos]))
+				return true;
+		}
+	}
 
 	return false;
 }
@@ -1380,8 +1387,14 @@ int qede_poll(struct napi_struct *napi, int budget)
 	struct qede_dev *edev = fp->edev;
 	int rx_work_done = 0;
 
-	if (likely(fp->type & QEDE_FASTPATH_TX) && qede_txq_has_work(fp->txq))
-		qede_tx_int(edev, fp->txq);
+	if (likely(fp->type & QEDE_FASTPATH_TX)) {
+		int cos;
+
+		for_each_cos_in_txq(fp->edev, cos) {
+			if (qede_txq_has_work(&fp->txq[cos]))
+				qede_tx_int(edev, &fp->txq[cos]);
+		}
+	}
 
 	if ((fp->type & QEDE_FASTPATH_XDP) && qede_txq_has_work(fp->xdp_tx))
 		qede_xdp_tx_int(edev, fp->xdp_tx);
@@ -1442,8 +1455,8 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 
 	/* Get tx-queue context and netdev index */
 	txq_index = skb_get_queue_mapping(skb);
-	WARN_ON(txq_index >= QEDE_TSS_COUNT(edev));
-	txq = edev->fp_array[edev->fp_num_rx + txq_index].txq;
+	WARN_ON(txq_index >= QEDE_TSS_COUNT(edev) * edev->dev_info.num_tc);
+	txq = QEDE_NDEV_TXQ_ID_TO_TXQ(edev, txq_index);
 	netdev_txq = netdev_get_tx_queue(ndev, txq_index);
 
 	WARN_ON(qed_chain_get_elem_left(&txq->tx_pbl) < (MAX_SKB_FRAGS + 1));
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 6a796040a32c..46d0f2eaa0c0 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -536,6 +536,97 @@ static int qede_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	return 0;
 }
 
+static int qede_setup_tc(struct net_device *ndev, u8 num_tc)
+{
+	struct qede_dev *edev = netdev_priv(ndev);
+	int cos, count, offset;
+
+	if (num_tc > edev->dev_info.num_tc)
+		return -EINVAL;
+
+	netdev_reset_tc(ndev);
+	netdev_set_num_tc(ndev, num_tc);
+
+	for_each_cos_in_txq(edev, cos) {
+		count = QEDE_TSS_COUNT(edev);
+		offset = cos * QEDE_TSS_COUNT(edev);
+		netdev_set_tc_queue(ndev, cos, count, offset);
+	}
+
+	return 0;
+}
+
+static int
+qede_set_flower(struct qede_dev *edev, struct tc_cls_flower_offload *f,
+		__be16 proto)
+{
+	switch (f->command) {
+	case TC_CLSFLOWER_REPLACE:
+		return qede_add_tc_flower_fltr(edev, proto, f);
+	case TC_CLSFLOWER_DESTROY:
+		return qede_delete_flow_filter(edev, f->cookie);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int qede_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+				  void *cb_priv)
+{
+	struct tc_cls_flower_offload *f;
+	struct qede_dev *edev = cb_priv;
+
+	if (!tc_cls_can_offload_and_chain0(edev->ndev, type_data))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		f = type_data;
+		return qede_set_flower(edev, f, f->common.protocol);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int qede_setup_tc_block(struct qede_dev *edev,
+			       struct tc_block_offload *f)
+{
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block,
+					     qede_setup_tc_block_cb,
+					     edev, edev, f->extack);
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block, qede_setup_tc_block_cb, edev);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int
+qede_setup_tc_offload(struct net_device *dev, enum tc_setup_type type,
+		      void *type_data)
+{
+	struct qede_dev *edev = netdev_priv(dev);
+	struct tc_mqprio_qopt *mqprio;
+
+	switch (type) {
+	case TC_SETUP_BLOCK:
+		return qede_setup_tc_block(edev, type_data);
+	case TC_SETUP_QDISC_MQPRIO:
+		mqprio = type_data;
+
+		mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+		return qede_setup_tc(dev, mqprio->num_tc);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static const struct net_device_ops qede_netdev_ops = {
 	.ndo_open = qede_open,
 	.ndo_stop = qede_close,
@@ -568,6 +659,7 @@ static const struct net_device_ops qede_netdev_ops = {
 #ifdef CONFIG_RFS_ACCEL
 	.ndo_rx_flow_steer = qede_rx_flow_steer,
 #endif
+	.ndo_setup_tc = qede_setup_tc_offload,
 };
 
 static const struct net_device_ops qede_netdev_vf_ops = {
@@ -621,7 +713,8 @@ static struct qede_dev *qede_alloc_etherdev(struct qed_dev *cdev,
 	struct qede_dev *edev;
 
 	ndev = alloc_etherdev_mqs(sizeof(*edev),
-				  info->num_queues, info->num_queues);
+				  info->num_queues * info->num_tc,
+				  info->num_queues);
 	if (!ndev) {
 		pr_err("etherdev allocation failed\n");
 		return NULL;
@@ -688,7 +781,7 @@ static void qede_init_ndev(struct qede_dev *edev)
 	/* user-changeble features */
 	hw_features = NETIF_F_GRO | NETIF_F_GRO_HW | NETIF_F_SG |
 		      NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-		      NETIF_F_TSO | NETIF_F_TSO6;
+		      NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_HW_TC;
 
 	if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1)
 		hw_features |= NETIF_F_NTUPLE;
@@ -830,7 +923,8 @@ static int qede_alloc_fp_array(struct qede_dev *edev)
 		}
 
 		if (fp->type & QEDE_FASTPATH_TX) {
-			fp->txq = kzalloc(sizeof(*fp->txq), GFP_KERNEL);
+			fp->txq = kcalloc(edev->dev_info.num_tc,
+					  sizeof(*fp->txq), GFP_KERNEL);
 			if (!fp->txq)
 				goto err;
 		}
@@ -879,10 +973,15 @@ static void qede_sp_task(struct work_struct *work)
 static void qede_update_pf_params(struct qed_dev *cdev)
 {
 	struct qed_pf_params pf_params;
+	u16 num_cons;
 
 	/* 64 rx + 64 tx + 64 XDP */
 	memset(&pf_params, 0, sizeof(struct qed_pf_params));
-	pf_params.eth_pf_params.num_cons = (MAX_SB_PER_PF_MIMD - 1) * 3;
+
+	/* 1 rx + 1 xdp + max tx cos */
+	num_cons = QED_MIN_L2_CONS;
+
+	pf_params.eth_pf_params.num_cons = (MAX_SB_PER_PF_MIMD - 1) * num_cons;
 
 	/* Same for VFs - make sure they'll have sufficient connections
 	 * to support XDP Tx queues.
@@ -1363,8 +1462,12 @@ static void qede_free_mem_fp(struct qede_dev *edev, struct qede_fastpath *fp)
 	if (fp->type & QEDE_FASTPATH_XDP)
 		qede_free_mem_txq(edev, fp->xdp_tx);
 
-	if (fp->type & QEDE_FASTPATH_TX)
-		qede_free_mem_txq(edev, fp->txq);
+	if (fp->type & QEDE_FASTPATH_TX) {
+		int cos;
+
+		for_each_cos_in_txq(edev, cos)
+			qede_free_mem_txq(edev, &fp->txq[cos]);
+	}
 }
 
 /* This function allocates all memory needed for a single fp (i.e. an entity
@@ -1391,9 +1494,13 @@ static int qede_alloc_mem_fp(struct qede_dev *edev, struct qede_fastpath *fp)
 	}
 
 	if (fp->type & QEDE_FASTPATH_TX) {
-		rc = qede_alloc_mem_txq(edev, fp->txq);
-		if (rc)
-			goto out;
+		int cos;
+
+		for_each_cos_in_txq(edev, cos) {
+			rc = qede_alloc_mem_txq(edev, &fp->txq[cos]);
+			if (rc)
+				goto out;
+		}
 	}
 
 out:
@@ -1466,10 +1573,23 @@ static void qede_init_fp(struct qede_dev *edev)
 		}
 
 		if (fp->type & QEDE_FASTPATH_TX) {
-			fp->txq->index = txq_index++;
-			if (edev->dev_info.is_legacy)
-				fp->txq->is_legacy = 1;
-			fp->txq->dev = &edev->pdev->dev;
+			int cos;
+
+			for_each_cos_in_txq(edev, cos) {
+				struct qede_tx_queue *txq = &fp->txq[cos];
+				u16 ndev_tx_id;
+
+				txq->cos = cos;
+				txq->index = txq_index;
+				ndev_tx_id = QEDE_TXQ_TO_NDEV_TXQ_ID(edev, txq);
+				txq->ndev_txq_id = ndev_tx_id;
+
+				if (edev->dev_info.is_legacy)
+					txq->is_legacy = 1;
+				txq->dev = &edev->pdev->dev;
+			}
+
+			txq_index++;
 		}
 
 		snprintf(fp->name, sizeof(fp->name), "%s-fp-%d",
@@ -1483,7 +1603,9 @@ static int qede_set_real_num_queues(struct qede_dev *edev)
 {
 	int rc = 0;
 
-	rc = netif_set_real_num_tx_queues(edev->ndev, QEDE_TSS_COUNT(edev));
+	rc = netif_set_real_num_tx_queues(edev->ndev,
+					  QEDE_TSS_COUNT(edev) *
+					  edev->dev_info.num_tc);
 	if (rc) {
 		DP_NOTICE(edev, "Failed to set real number of Tx queues\n");
 		return rc;
@@ -1685,9 +1807,13 @@ static int qede_stop_queues(struct qede_dev *edev)
 		fp = &edev->fp_array[i];
 
 		if (fp->type & QEDE_FASTPATH_TX) {
-			rc = qede_drain_txq(edev, fp->txq, true);
-			if (rc)
-				return rc;
+			int cos;
+
+			for_each_cos_in_txq(edev, cos) {
+				rc = qede_drain_txq(edev, &fp->txq[cos], true);
+				if (rc)
+					return rc;
+			}
 		}
 
 		if (fp->type & QEDE_FASTPATH_XDP) {
@@ -1703,9 +1829,13 @@ static int qede_stop_queues(struct qede_dev *edev)
 
 		/* Stop the Tx Queue(s) */
 		if (fp->type & QEDE_FASTPATH_TX) {
-			rc = qede_stop_txq(edev, fp->txq, i);
-			if (rc)
-				return rc;
+			int cos;
+
+			for_each_cos_in_txq(edev, cos) {
+				rc = qede_stop_txq(edev, &fp->txq[cos], i);
+				if (rc)
+					return rc;
+			}
 		}
 
 		/* Stop the Rx Queue */
@@ -1758,6 +1888,7 @@ static int qede_start_txq(struct qede_dev *edev,
 
 	params.p_sb = fp->sb_info;
 	params.sb_idx = sb_idx;
+	params.tc = txq->cos;
 
 	rc = edev->ops->q_tx_start(edev->cdev, rss_id, &params, phys_table,
 				   page_cnt, &ret_params);
@@ -1877,9 +2008,14 @@ static int qede_start_queues(struct qede_dev *edev, bool clear_stats)
 		}
 
 		if (fp->type & QEDE_FASTPATH_TX) {
-			rc = qede_start_txq(edev, fp, fp->txq, i, TX_PI(0));
-			if (rc)
-				goto out;
+			int cos;
+
+			for_each_cos_in_txq(edev, cos) {
+				rc = qede_start_txq(edev, fp, &fp->txq[cos], i,
+						    TX_PI(cos));
+				if (rc)
+					goto out;
+			}
 		}
 	}
 
@@ -1973,6 +2109,7 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode,
 		     bool is_locked)
 {
 	struct qed_link_params link_params;
+	u8 num_tc;
 	int rc;
 
 	DP_INFO(edev, "Starting qede load\n");
@@ -2019,6 +2156,10 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode,
 		goto err4;
 	DP_INFO(edev, "Start VPORT, RXQ and TXQ succeeded\n");
 
+	num_tc = netdev_get_num_tc(edev->ndev);
+	num_tc = num_tc ? num_tc : edev->dev_info.num_tc;
+	qede_setup_tc(edev->ndev, num_tc);
+
 	/* Program un-configured VLANs */
 	qede_configure_vlan_filters(edev);
 
@@ -2143,7 +2284,7 @@ static bool qede_is_txq_full(struct qede_dev *edev, struct qede_tx_queue *txq)
 {
 	struct netdev_queue *netdev_txq;
 
-	netdev_txq = netdev_get_tx_queue(edev->ndev, txq->index);
+	netdev_txq = netdev_get_tx_queue(edev->ndev, txq->ndev_txq_id);
 	if (netif_xmit_stopped(netdev_txq))
 		return true;
 
@@ -2208,9 +2349,11 @@ static void qede_get_eth_tlv_data(void *dev, void *data)
 	for_each_queue(i) {
 		fp = &edev->fp_array[i];
 		if (fp->type & QEDE_FASTPATH_TX) {
-			if (fp->txq->sw_tx_cons != fp->txq->sw_tx_prod)
+			struct qede_tx_queue *txq = QEDE_FP_TC0_TXQ(fp);
+
+			if (txq->sw_tx_cons != txq->sw_tx_prod)
 				etlv->txqs_empty = false;
-			if (qede_is_txq_full(edev, fp->txq))
+			if (qede_is_txq_full(edev, txq))
 				etlv->num_txqs_full++;
 		}
 		if (fp->type & QEDE_FASTPATH_RX) {
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index 7f7deeaf1cf0..3b0adda7cc9c 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -351,9 +351,9 @@ skip:
 	case QLCNIC_BRDTYPE_P3P_REF_QG:
 	case QLCNIC_BRDTYPE_P3P_4_GB:
 	case QLCNIC_BRDTYPE_P3P_4_GB_MM:
-
 		supported |= SUPPORTED_Autoneg;
 		advertising |= ADVERTISED_Autoneg;
+		/* fall through */
 	case QLCNIC_BRDTYPE_P3P_10G_CX4:
 	case QLCNIC_BRDTYPE_P3P_10G_CX4_LP:
 	case QLCNIC_BRDTYPE_P3P_10000_BASE_T:
@@ -377,6 +377,7 @@ skip:
 		supported |= SUPPORTED_TP;
 		check_sfp_module = netif_running(adapter->netdev) &&
 				   ahw->has_link_events;
+		/* fall through */
 	case QLCNIC_BRDTYPE_P3P_10G_XFP:
 		supported |= SUPPORTED_FIBRE;
 		advertising |= ADVERTISED_FIBRE;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
index 7848cf04b29a..822aa393c370 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
@@ -276,13 +276,6 @@ static const unsigned crb_hub_agt[64] = {
 	0,
 };
 
-static const u32 msi_tgt_status[8] = {
-	ISR_INT_TARGET_STATUS, ISR_INT_TARGET_STATUS_F1,
-	ISR_INT_TARGET_STATUS_F2, ISR_INT_TARGET_STATUS_F3,
-	ISR_INT_TARGET_STATUS_F4, ISR_INT_TARGET_STATUS_F5,
-	ISR_INT_TARGET_STATUS_F6, ISR_INT_TARGET_STATUS_F7
-};
-
 /*  PCI Windowing for DDR regions.  */
 
 #define QLCNIC_PCIE_SEM_TIMEOUT	10000
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
index 0c744b9c6e0a..77e386ebff09 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
@@ -212,7 +212,7 @@ int qlcnic_sriov_init(struct qlcnic_adapter *adapter, int num_vfs)
 			vp->max_tx_bw = MAX_BW;
 			vp->min_tx_bw = MIN_BW;
 			vp->spoofchk = false;
-			random_ether_addr(vp->mac);
+			eth_random_addr(vp->mac);
 			dev_info(&adapter->pdev->dev,
 				 "MAC Address %pM is configured for VF %d\n",
 				 vp->mac, i);
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_mpi.c b/drivers/net/ethernet/qlogic/qlge/qlge_mpi.c
index 4be65d6761b3..957c72985a06 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_mpi.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_mpi.c
@@ -1176,6 +1176,7 @@ void ql_mpi_idc_work(struct work_struct *work)
 	case MB_CMD_PORT_RESET:
 	case MB_CMD_STOP_FW:
 		ql_link_off(qdev);
+		/* Fall through */
 	case MB_CMD_SET_PORT_CFG:
 		/* Signal the resulting link up AEN
 		 * that the frame routing and mac addr
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
index b9a7548ec6a0..0afc3d335d56 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
@@ -210,7 +210,7 @@ void rmnet_vnd_setup(struct net_device *rmnet_dev)
 	rmnet_dev->netdev_ops = &rmnet_vnd_ops;
 	rmnet_dev->mtu = RMNET_DFLT_PACKET_SIZE;
 	rmnet_dev->needed_headroom = RMNET_NEEDED_HEADROOM;
-	random_ether_addr(rmnet_dev->dev_addr);
+	eth_random_addr(rmnet_dev->dev_addr);
 	rmnet_dev->tx_queue_len = RMNET_TX_QUEUE_LEN;
 
 	/* Raw IP mode */
diff --git a/drivers/net/ethernet/realtek/Kconfig b/drivers/net/ethernet/realtek/Kconfig
index 7c69f4c8134d..e1cd934c2e4f 100644
--- a/drivers/net/ethernet/realtek/Kconfig
+++ b/drivers/net/ethernet/realtek/Kconfig
@@ -99,7 +99,7 @@ config R8169
 	depends on PCI
 	select FW_LOADER
 	select CRC32
-	select MII
+	select PHYLIB
 	---help---
 	  Say Y here if you have a Realtek 8169 PCI Gigabit Ethernet adapter.
 
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index eaedc11ed686..0d9c3831838f 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -15,27 +15,22 @@
 #include <linux/etherdevice.h>
 #include <linux/delay.h>
 #include <linux/ethtool.h>
-#include <linux/mii.h>
+#include <linux/phy.h>
 #include <linux/if_vlan.h>
 #include <linux/crc32.h>
 #include <linux/in.h>
+#include <linux/io.h>
 #include <linux/ip.h>
 #include <linux/tcp.h>
 #include <linux/interrupt.h>
 #include <linux/dma-mapping.h>
 #include <linux/pm_runtime.h>
 #include <linux/firmware.h>
-#include <linux/pci-aspm.h>
 #include <linux/prefetch.h>
 #include <linux/ipv6.h>
 #include <net/ip6_checksum.h>
 
-#include <asm/io.h>
-#include <asm/irq.h>
-
-#define RTL8169_VERSION "2.3LK-NAPI"
 #define MODULENAME "r8169"
-#define PFX MODULENAME ": "
 
 #define FIRMWARE_8168D_1	"rtl_nic/rtl8168d-1.fw"
 #define FIRMWARE_8168D_2	"rtl_nic/rtl8168d-2.fw"
@@ -57,19 +52,6 @@
 #define FIRMWARE_8107E_1	"rtl_nic/rtl8107e-1.fw"
 #define FIRMWARE_8107E_2	"rtl_nic/rtl8107e-2.fw"
 
-#ifdef RTL8169_DEBUG
-#define assert(expr) \
-	if (!(expr)) {					\
-		printk( "Assertion failed! %s,%s,%s,line=%d\n",	\
-		#expr,__FILE__,__func__,__LINE__);		\
-	}
-#define dprintk(fmt, args...) \
-	do { printk(KERN_DEBUG PFX fmt, ## args); } while (0)
-#else
-#define assert(expr) do {} while (0)
-#define dprintk(fmt, args...)	do {} while (0)
-#endif /* RTL8169_DEBUG */
-
 #define R8169_MSG_DEFAULT \
 	(NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_IFUP | NETIF_MSG_IFDOWN)
 
@@ -95,7 +77,6 @@ static const int multicast_filter_limit = 32;
 #define R8169_RX_RING_BYTES	(NUM_RX_DESC * sizeof(struct RxDesc))
 
 #define RTL8169_TX_TIMEOUT	(6*HZ)
-#define RTL8169_PHY_TIMEOUT	(10*HZ)
 
 /* write/read MMIO register */
 #define RTL_W8(tp, reg, val8)	writeb((val8), tp->mmio_addr + (reg))
@@ -160,136 +141,70 @@ enum mac_version {
 	RTL_GIGA_MAC_NONE   = 0xff,
 };
 
-enum rtl_tx_desc_version {
-	RTL_TD_0	= 0,
-	RTL_TD_1	= 1,
-};
-
 #define JUMBO_1K	ETH_DATA_LEN
 #define JUMBO_4K	(4*1024 - ETH_HLEN - 2)
 #define JUMBO_6K	(6*1024 - ETH_HLEN - 2)
 #define JUMBO_7K	(7*1024 - ETH_HLEN - 2)
 #define JUMBO_9K	(9*1024 - ETH_HLEN - 2)
 
-#define _R(NAME,TD,FW,SZ) {	\
-	.name = NAME,		\
-	.txd_version = TD,	\
-	.fw_name = FW,		\
-	.jumbo_max = SZ,	\
-}
-
 static const struct {
 	const char *name;
-	enum rtl_tx_desc_version txd_version;
 	const char *fw_name;
-	u16 jumbo_max;
 } rtl_chip_infos[] = {
 	/* PCI devices. */
-	[RTL_GIGA_MAC_VER_01] =
-		_R("RTL8169",		RTL_TD_0, NULL, JUMBO_7K),
-	[RTL_GIGA_MAC_VER_02] =
-		_R("RTL8169s",		RTL_TD_0, NULL, JUMBO_7K),
-	[RTL_GIGA_MAC_VER_03] =
-		_R("RTL8110s",		RTL_TD_0, NULL, JUMBO_7K),
-	[RTL_GIGA_MAC_VER_04] =
-		_R("RTL8169sb/8110sb",	RTL_TD_0, NULL, JUMBO_7K),
-	[RTL_GIGA_MAC_VER_05] =
-		_R("RTL8169sc/8110sc",	RTL_TD_0, NULL, JUMBO_7K),
-	[RTL_GIGA_MAC_VER_06] =
-		_R("RTL8169sc/8110sc",	RTL_TD_0, NULL, JUMBO_7K),
+	[RTL_GIGA_MAC_VER_01] = {"RTL8169"				},
+	[RTL_GIGA_MAC_VER_02] = {"RTL8169s"				},
+	[RTL_GIGA_MAC_VER_03] = {"RTL8110s"				},
+	[RTL_GIGA_MAC_VER_04] = {"RTL8169sb/8110sb"			},
+	[RTL_GIGA_MAC_VER_05] = {"RTL8169sc/8110sc"			},
+	[RTL_GIGA_MAC_VER_06] = {"RTL8169sc/8110sc"			},
 	/* PCI-E devices. */
-	[RTL_GIGA_MAC_VER_07] =
-		_R("RTL8102e",		RTL_TD_1, NULL, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_08] =
-		_R("RTL8102e",		RTL_TD_1, NULL, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_09] =
-		_R("RTL8102e",		RTL_TD_1, NULL, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_10] =
-		_R("RTL8101e",		RTL_TD_0, NULL, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_11] =
-		_R("RTL8168b/8111b",	RTL_TD_0, NULL, JUMBO_4K),
-	[RTL_GIGA_MAC_VER_12] =
-		_R("RTL8168b/8111b",	RTL_TD_0, NULL, JUMBO_4K),
-	[RTL_GIGA_MAC_VER_13] =
-		_R("RTL8101e",		RTL_TD_0, NULL, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_14] =
-		_R("RTL8100e",		RTL_TD_0, NULL, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_15] =
-		_R("RTL8100e",		RTL_TD_0, NULL, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_16] =
-		_R("RTL8101e",		RTL_TD_0, NULL, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_17] =
-		_R("RTL8168b/8111b",	RTL_TD_0, NULL, JUMBO_4K),
-	[RTL_GIGA_MAC_VER_18] =
-		_R("RTL8168cp/8111cp",	RTL_TD_1, NULL, JUMBO_6K),
-	[RTL_GIGA_MAC_VER_19] =
-		_R("RTL8168c/8111c",	RTL_TD_1, NULL, JUMBO_6K),
-	[RTL_GIGA_MAC_VER_20] =
-		_R("RTL8168c/8111c",	RTL_TD_1, NULL, JUMBO_6K),
-	[RTL_GIGA_MAC_VER_21] =
-		_R("RTL8168c/8111c",	RTL_TD_1, NULL, JUMBO_6K),
-	[RTL_GIGA_MAC_VER_22] =
-		_R("RTL8168c/8111c",	RTL_TD_1, NULL, JUMBO_6K),
-	[RTL_GIGA_MAC_VER_23] =
-		_R("RTL8168cp/8111cp",	RTL_TD_1, NULL, JUMBO_6K),
-	[RTL_GIGA_MAC_VER_24] =
-		_R("RTL8168cp/8111cp",	RTL_TD_1, NULL, JUMBO_6K),
-	[RTL_GIGA_MAC_VER_25] =
-		_R("RTL8168d/8111d",	RTL_TD_1, FIRMWARE_8168D_1, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_26] =
-		_R("RTL8168d/8111d",	RTL_TD_1, FIRMWARE_8168D_2, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_27] =
-		_R("RTL8168dp/8111dp",	RTL_TD_1, NULL, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_28] =
-		_R("RTL8168dp/8111dp",	RTL_TD_1, NULL, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_29] =
-		_R("RTL8105e",		RTL_TD_1, FIRMWARE_8105E_1, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_30] =
-		_R("RTL8105e",		RTL_TD_1, FIRMWARE_8105E_1, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_31] =
-		_R("RTL8168dp/8111dp",	RTL_TD_1, NULL, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_32] =
-		_R("RTL8168e/8111e",	RTL_TD_1, FIRMWARE_8168E_1, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_33] =
-		_R("RTL8168e/8111e",	RTL_TD_1, FIRMWARE_8168E_2, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_34] =
-		_R("RTL8168evl/8111evl",RTL_TD_1, FIRMWARE_8168E_3, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_35] =
-		_R("RTL8168f/8111f",	RTL_TD_1, FIRMWARE_8168F_1, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_36] =
-		_R("RTL8168f/8111f",	RTL_TD_1, FIRMWARE_8168F_2, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_37] =
-		_R("RTL8402",		RTL_TD_1, FIRMWARE_8402_1,  JUMBO_1K),
-	[RTL_GIGA_MAC_VER_38] =
-		_R("RTL8411",		RTL_TD_1, FIRMWARE_8411_1,  JUMBO_9K),
-	[RTL_GIGA_MAC_VER_39] =
-		_R("RTL8106e",		RTL_TD_1, FIRMWARE_8106E_1, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_40] =
-		_R("RTL8168g/8111g",	RTL_TD_1, FIRMWARE_8168G_2, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_41] =
-		_R("RTL8168g/8111g",	RTL_TD_1, NULL, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_42] =
-		_R("RTL8168g/8111g",	RTL_TD_1, FIRMWARE_8168G_3, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_43] =
-		_R("RTL8106e",		RTL_TD_1, FIRMWARE_8106E_2, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_44] =
-		_R("RTL8411",		RTL_TD_1, FIRMWARE_8411_2,  JUMBO_9K),
-	[RTL_GIGA_MAC_VER_45] =
-		_R("RTL8168h/8111h",	RTL_TD_1, FIRMWARE_8168H_1, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_46] =
-		_R("RTL8168h/8111h",	RTL_TD_1, FIRMWARE_8168H_2, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_47] =
-		_R("RTL8107e",		RTL_TD_1, FIRMWARE_8107E_1, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_48] =
-		_R("RTL8107e",		RTL_TD_1, FIRMWARE_8107E_2, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_49] =
-		_R("RTL8168ep/8111ep",	RTL_TD_1, NULL, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_50] =
-		_R("RTL8168ep/8111ep",	RTL_TD_1, NULL, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_51] =
-		_R("RTL8168ep/8111ep",	RTL_TD_1, NULL, JUMBO_9K),
+	[RTL_GIGA_MAC_VER_07] = {"RTL8102e"				},
+	[RTL_GIGA_MAC_VER_08] = {"RTL8102e"				},
+	[RTL_GIGA_MAC_VER_09] = {"RTL8102e"				},
+	[RTL_GIGA_MAC_VER_10] = {"RTL8101e"				},
+	[RTL_GIGA_MAC_VER_11] = {"RTL8168b/8111b"			},
+	[RTL_GIGA_MAC_VER_12] = {"RTL8168b/8111b"			},
+	[RTL_GIGA_MAC_VER_13] = {"RTL8101e"				},
+	[RTL_GIGA_MAC_VER_14] = {"RTL8100e"				},
+	[RTL_GIGA_MAC_VER_15] = {"RTL8100e"				},
+	[RTL_GIGA_MAC_VER_16] = {"RTL8101e"				},
+	[RTL_GIGA_MAC_VER_17] = {"RTL8168b/8111b"			},
+	[RTL_GIGA_MAC_VER_18] = {"RTL8168cp/8111cp"			},
+	[RTL_GIGA_MAC_VER_19] = {"RTL8168c/8111c"			},
+	[RTL_GIGA_MAC_VER_20] = {"RTL8168c/8111c"			},
+	[RTL_GIGA_MAC_VER_21] = {"RTL8168c/8111c"			},
+	[RTL_GIGA_MAC_VER_22] = {"RTL8168c/8111c"			},
+	[RTL_GIGA_MAC_VER_23] = {"RTL8168cp/8111cp"			},
+	[RTL_GIGA_MAC_VER_24] = {"RTL8168cp/8111cp"			},
+	[RTL_GIGA_MAC_VER_25] = {"RTL8168d/8111d",	FIRMWARE_8168D_1},
+	[RTL_GIGA_MAC_VER_26] = {"RTL8168d/8111d",	FIRMWARE_8168D_2},
+	[RTL_GIGA_MAC_VER_27] = {"RTL8168dp/8111dp"			},
+	[RTL_GIGA_MAC_VER_28] = {"RTL8168dp/8111dp"			},
+	[RTL_GIGA_MAC_VER_29] = {"RTL8105e",		FIRMWARE_8105E_1},
+	[RTL_GIGA_MAC_VER_30] = {"RTL8105e",		FIRMWARE_8105E_1},
+	[RTL_GIGA_MAC_VER_31] = {"RTL8168dp/8111dp"			},
+	[RTL_GIGA_MAC_VER_32] = {"RTL8168e/8111e",	FIRMWARE_8168E_1},
+	[RTL_GIGA_MAC_VER_33] = {"RTL8168e/8111e",	FIRMWARE_8168E_2},
+	[RTL_GIGA_MAC_VER_34] = {"RTL8168evl/8111evl",	FIRMWARE_8168E_3},
+	[RTL_GIGA_MAC_VER_35] = {"RTL8168f/8111f",	FIRMWARE_8168F_1},
+	[RTL_GIGA_MAC_VER_36] = {"RTL8168f/8111f",	FIRMWARE_8168F_2},
+	[RTL_GIGA_MAC_VER_37] = {"RTL8402",		FIRMWARE_8402_1 },
+	[RTL_GIGA_MAC_VER_38] = {"RTL8411",		FIRMWARE_8411_1 },
+	[RTL_GIGA_MAC_VER_39] = {"RTL8106e",		FIRMWARE_8106E_1},
+	[RTL_GIGA_MAC_VER_40] = {"RTL8168g/8111g",	FIRMWARE_8168G_2},
+	[RTL_GIGA_MAC_VER_41] = {"RTL8168g/8111g"			},
+	[RTL_GIGA_MAC_VER_42] = {"RTL8168g/8111g",	FIRMWARE_8168G_3},
+	[RTL_GIGA_MAC_VER_43] = {"RTL8106e",		FIRMWARE_8106E_2},
+	[RTL_GIGA_MAC_VER_44] = {"RTL8411",		FIRMWARE_8411_2 },
+	[RTL_GIGA_MAC_VER_45] = {"RTL8168h/8111h",	FIRMWARE_8168H_1},
+	[RTL_GIGA_MAC_VER_46] = {"RTL8168h/8111h",	FIRMWARE_8168H_2},
+	[RTL_GIGA_MAC_VER_47] = {"RTL8107e",		FIRMWARE_8107E_1},
+	[RTL_GIGA_MAC_VER_48] = {"RTL8107e",		FIRMWARE_8107E_2},
+	[RTL_GIGA_MAC_VER_49] = {"RTL8168ep/8111ep"			},
+	[RTL_GIGA_MAC_VER_50] = {"RTL8168ep/8111ep"			},
+	[RTL_GIGA_MAC_VER_51] = {"RTL8168ep/8111ep"			},
 };
-#undef _R
 
 enum cfg_version {
 	RTL_CFG_0 = 0x00,
@@ -399,12 +314,6 @@ enum rtl_registers {
 	FuncForceEvent	= 0xfc,
 };
 
-enum rtl8110_registers {
-	TBICSR			= 0x64,
-	TBI_ANAR		= 0x68,
-	TBI_LPAR		= 0x6a,
-};
-
 enum rtl8168_8101_registers {
 	CSIDR			= 0x64,
 	CSIAR			= 0x68,
@@ -571,14 +480,6 @@ enum rtl_register_content {
 	PMEStatus	= (1 << 0),	/* PME status can be reset by PCI RST# */
 	ASPM_en		= (1 << 0),	/* ASPM enable */
 
-	/* TBICSR p.28 */
-	TBIReset	= 0x80000000,
-	TBILoopback	= 0x40000000,
-	TBINwEnable	= 0x20000000,
-	TBINwRestart	= 0x10000000,
-	TBILinkOk	= 0x02000000,
-	TBINwComplete	= 0x01000000,
-
 	/* CPlusCmd p.31 */
 	EnableBist	= (1 << 15),	// 8168 8101
 	Mac_dbgo_oe	= (1 << 14),	// 8168 8101
@@ -732,7 +633,6 @@ enum rtl_flag {
 	RTL_FLAG_TASK_ENABLED,
 	RTL_FLAG_TASK_SLOW_PENDING,
 	RTL_FLAG_TASK_RESET_PENDING,
-	RTL_FLAG_TASK_PHY_PENDING,
 	RTL_FLAG_MAX
 };
 
@@ -760,7 +660,6 @@ struct rtl8169_private {
 	dma_addr_t RxPhyAddr;
 	void *Rx_databuff[NUM_RX_DESC];	/* Rx data buffers */
 	struct ring_info tx_skb[NUM_TX_DESC];	/* Tx data buffers */
-	struct timer_list timer;
 	u16 cp_cmd;
 
 	u16 event_slow;
@@ -776,14 +675,7 @@ struct rtl8169_private {
 		void (*disable)(struct rtl8169_private *);
 	} jumbo_ops;
 
-	int (*set_speed)(struct net_device *, u8 aneg, u16 sp, u8 dpx, u32 adv);
-	int (*get_link_ksettings)(struct net_device *,
-				  struct ethtool_link_ksettings *);
-	void (*phy_reset_enable)(struct rtl8169_private *tp);
 	void (*hw_start)(struct rtl8169_private *tp);
-	unsigned int (*phy_reset_pending)(struct rtl8169_private *tp);
-	unsigned int (*link_ok)(struct rtl8169_private *tp);
-	int (*do_ioctl)(struct rtl8169_private *tp, struct mii_ioctl_data *data, int cmd);
 	bool (*tso_csum)(struct rtl8169_private *, struct sk_buff *, u32 *);
 
 	struct {
@@ -792,7 +684,8 @@ struct rtl8169_private {
 		struct work_struct work;
 	} wk;
 
-	struct mii_if_info mii;
+	unsigned supports_gmii:1;
+	struct mii_bus *mii_bus;
 	dma_addr_t counters_phys_addr;
 	struct rtl8169_counters *counters;
 	struct rtl8169_tc_offsets tc_offset;
@@ -822,7 +715,6 @@ MODULE_PARM_DESC(use_dac, "Enable PCI DAC. Unsafe on 32 bit PCI slot.");
 module_param_named(debug, debug.msg_enable, int, 0);
 MODULE_PARM_DESC(debug, "Debug verbosity level (0=none, ..., 16=all)");
 MODULE_LICENSE("GPL");
-MODULE_VERSION(RTL8169_VERSION);
 MODULE_FIRMWARE(FIRMWARE_8168D_1);
 MODULE_FIRMWARE(FIRMWARE_8168D_2);
 MODULE_FIRMWARE(FIRMWARE_8168E_1);
@@ -1143,21 +1035,6 @@ static void rtl_w0w1_phy(struct rtl8169_private *tp, int reg_addr, int p, int m)
 	rtl_writephy(tp, reg_addr, (val & ~m) | p);
 }
 
-static void rtl_mdio_write(struct net_device *dev, int phy_id, int location,
-			   int val)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-
-	rtl_writephy(tp, location, val);
-}
-
-static int rtl_mdio_read(struct net_device *dev, int phy_id, int location)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-
-	return rtl_readphy(tp, location);
-}
-
 DECLARE_RTL_COND(rtl_ephyar_cond)
 {
 	return RTL_R32(tp, EPHYAR) & EPHYAR_FLAG;
@@ -1478,54 +1355,22 @@ static void rtl8169_irq_mask_and_ack(struct rtl8169_private *tp)
 	RTL_R8(tp, ChipCmd);
 }
 
-static unsigned int rtl8169_tbi_reset_pending(struct rtl8169_private *tp)
-{
-	return RTL_R32(tp, TBICSR) & TBIReset;
-}
-
-static unsigned int rtl8169_xmii_reset_pending(struct rtl8169_private *tp)
-{
-	return rtl_readphy(tp, MII_BMCR) & BMCR_RESET;
-}
-
-static unsigned int rtl8169_tbi_link_ok(struct rtl8169_private *tp)
-{
-	return RTL_R32(tp, TBICSR) & TBILinkOk;
-}
-
-static unsigned int rtl8169_xmii_link_ok(struct rtl8169_private *tp)
-{
-	return RTL_R8(tp, PHYstatus) & LinkStatus;
-}
-
-static void rtl8169_tbi_reset_enable(struct rtl8169_private *tp)
-{
-	RTL_W32(tp, TBICSR, RTL_R32(tp, TBICSR) | TBIReset);
-}
-
-static void rtl8169_xmii_reset_enable(struct rtl8169_private *tp)
-{
-	unsigned int val;
-
-	val = rtl_readphy(tp, MII_BMCR) | BMCR_RESET;
-	rtl_writephy(tp, MII_BMCR, val & 0xffff);
-}
-
 static void rtl_link_chg_patch(struct rtl8169_private *tp)
 {
 	struct net_device *dev = tp->dev;
+	struct phy_device *phydev = dev->phydev;
 
 	if (!netif_running(dev))
 		return;
 
 	if (tp->mac_version == RTL_GIGA_MAC_VER_34 ||
 	    tp->mac_version == RTL_GIGA_MAC_VER_38) {
-		if (RTL_R8(tp, PHYstatus) & _1000bpsF) {
+		if (phydev->speed == SPEED_1000) {
 			rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x00000011,
 				      ERIAR_EXGMAC);
 			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005,
 				      ERIAR_EXGMAC);
-		} else if (RTL_R8(tp, PHYstatus) & _100bps) {
+		} else if (phydev->speed == SPEED_100) {
 			rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x0000001f,
 				      ERIAR_EXGMAC);
 			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005,
@@ -1543,7 +1388,7 @@ static void rtl_link_chg_patch(struct rtl8169_private *tp)
 			     ERIAR_EXGMAC);
 	} else if (tp->mac_version == RTL_GIGA_MAC_VER_35 ||
 		   tp->mac_version == RTL_GIGA_MAC_VER_36) {
-		if (RTL_R8(tp, PHYstatus) & _1000bpsF) {
+		if (phydev->speed == SPEED_1000) {
 			rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x00000011,
 				      ERIAR_EXGMAC);
 			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005,
@@ -1555,7 +1400,7 @@ static void rtl_link_chg_patch(struct rtl8169_private *tp)
 				      ERIAR_EXGMAC);
 		}
 	} else if (tp->mac_version == RTL_GIGA_MAC_VER_37) {
-		if (RTL_R8(tp, PHYstatus) & _10bps) {
+		if (phydev->speed == SPEED_10) {
 			rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x4d02,
 				      ERIAR_EXGMAC);
 			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_0011, 0x0060,
@@ -1567,25 +1412,6 @@ static void rtl_link_chg_patch(struct rtl8169_private *tp)
 	}
 }
 
-static void rtl8169_check_link_status(struct net_device *dev,
-				      struct rtl8169_private *tp)
-{
-	struct device *d = tp_to_dev(tp);
-
-	if (tp->link_ok(tp)) {
-		rtl_link_chg_patch(tp);
-		/* This is to cancel a scheduled suspend if there's one. */
-		pm_request_resume(d);
-		netif_carrier_on(dev);
-		if (net_ratelimit())
-			netif_info(tp, ifup, dev, "link up\n");
-	} else {
-		netif_carrier_off(dev);
-		netif_info(tp, ifdown, dev, "link down\n");
-		pm_runtime_idle(d);
-	}
-}
-
 #define WAKE_ANY (WAKE_PHY | WAKE_MAGIC | WAKE_UCAST | WAKE_BCAST | WAKE_MCAST)
 
 static u32 __rtl8169_get_wol(struct rtl8169_private *tp)
@@ -1626,21 +1452,11 @@ static u32 __rtl8169_get_wol(struct rtl8169_private *tp)
 static void rtl8169_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
-	struct device *d = tp_to_dev(tp);
-
-	pm_runtime_get_noresume(d);
 
 	rtl_lock_work(tp);
-
 	wol->supported = WAKE_ANY;
-	if (pm_runtime_active(d))
-		wol->wolopts = __rtl8169_get_wol(tp);
-	else
-		wol->wolopts = tp->saved_wolopts;
-
+	wol->wolopts = tp->saved_wolopts;
 	rtl_unlock_work(tp);
-
-	pm_runtime_put_noidle(d);
 }
 
 static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
@@ -1716,18 +1532,21 @@ static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	struct rtl8169_private *tp = netdev_priv(dev);
 	struct device *d = tp_to_dev(tp);
 
+	if (wol->wolopts & ~WAKE_ANY)
+		return -EINVAL;
+
 	pm_runtime_get_noresume(d);
 
 	rtl_lock_work(tp);
 
+	tp->saved_wolopts = wol->wolopts;
+
 	if (pm_runtime_active(d))
-		__rtl8169_set_wol(tp, wol->wolopts);
-	else
-		tp->saved_wolopts = wol->wolopts;
+		__rtl8169_set_wol(tp, tp->saved_wolopts);
 
 	rtl_unlock_work(tp);
 
-	device_set_wakeup_enable(d, wol->wolopts);
+	device_set_wakeup_enable(d, tp->saved_wolopts);
 
 	pm_runtime_put_noidle(d);
 
@@ -1746,7 +1565,6 @@ static void rtl8169_get_drvinfo(struct net_device *dev,
 	struct rtl_fw *rtl_fw = tp->rtl_fw;
 
 	strlcpy(info->driver, MODULENAME, sizeof(info->driver));
-	strlcpy(info->version, RTL8169_VERSION, sizeof(info->version));
 	strlcpy(info->bus_info, pci_name(tp->pci_dev), sizeof(info->bus_info));
 	BUILD_BUG_ON(sizeof(info->fw_version) < sizeof(rtl_fw->version));
 	if (!IS_ERR_OR_NULL(rtl_fw))
@@ -1759,124 +1577,6 @@ static int rtl8169_get_regs_len(struct net_device *dev)
 	return R8169_REGS_SIZE;
 }
 
-static int rtl8169_set_speed_tbi(struct net_device *dev,
-				 u8 autoneg, u16 speed, u8 duplex, u32 ignored)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-	int ret = 0;
-	u32 reg;
-
-	reg = RTL_R32(tp, TBICSR);
-	if ((autoneg == AUTONEG_DISABLE) && (speed == SPEED_1000) &&
-	    (duplex == DUPLEX_FULL)) {
-		RTL_W32(tp, TBICSR, reg & ~(TBINwEnable | TBINwRestart));
-	} else if (autoneg == AUTONEG_ENABLE)
-		RTL_W32(tp, TBICSR, reg | TBINwEnable | TBINwRestart);
-	else {
-		netif_warn(tp, link, dev,
-			   "incorrect speed setting refused in TBI mode\n");
-		ret = -EOPNOTSUPP;
-	}
-
-	return ret;
-}
-
-static int rtl8169_set_speed_xmii(struct net_device *dev,
-				  u8 autoneg, u16 speed, u8 duplex, u32 adv)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-	int giga_ctrl, bmcr;
-	int rc = -EINVAL;
-
-	rtl_writephy(tp, 0x1f, 0x0000);
-
-	if (autoneg == AUTONEG_ENABLE) {
-		int auto_nego;
-
-		auto_nego = rtl_readphy(tp, MII_ADVERTISE);
-		auto_nego &= ~(ADVERTISE_10HALF | ADVERTISE_10FULL |
-				ADVERTISE_100HALF | ADVERTISE_100FULL);
-
-		if (adv & ADVERTISED_10baseT_Half)
-			auto_nego |= ADVERTISE_10HALF;
-		if (adv & ADVERTISED_10baseT_Full)
-			auto_nego |= ADVERTISE_10FULL;
-		if (adv & ADVERTISED_100baseT_Half)
-			auto_nego |= ADVERTISE_100HALF;
-		if (adv & ADVERTISED_100baseT_Full)
-			auto_nego |= ADVERTISE_100FULL;
-
-		auto_nego |= ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM;
-
-		giga_ctrl = rtl_readphy(tp, MII_CTRL1000);
-		giga_ctrl &= ~(ADVERTISE_1000FULL | ADVERTISE_1000HALF);
-
-		/* The 8100e/8101e/8102e do Fast Ethernet only. */
-		if (tp->mii.supports_gmii) {
-			if (adv & ADVERTISED_1000baseT_Half)
-				giga_ctrl |= ADVERTISE_1000HALF;
-			if (adv & ADVERTISED_1000baseT_Full)
-				giga_ctrl |= ADVERTISE_1000FULL;
-		} else if (adv & (ADVERTISED_1000baseT_Half |
-				  ADVERTISED_1000baseT_Full)) {
-			netif_info(tp, link, dev,
-				   "PHY does not support 1000Mbps\n");
-			goto out;
-		}
-
-		bmcr = BMCR_ANENABLE | BMCR_ANRESTART;
-
-		rtl_writephy(tp, MII_ADVERTISE, auto_nego);
-		rtl_writephy(tp, MII_CTRL1000, giga_ctrl);
-	} else {
-		if (speed == SPEED_10)
-			bmcr = 0;
-		else if (speed == SPEED_100)
-			bmcr = BMCR_SPEED100;
-		else
-			goto out;
-
-		if (duplex == DUPLEX_FULL)
-			bmcr |= BMCR_FULLDPLX;
-	}
-
-	rtl_writephy(tp, MII_BMCR, bmcr);
-
-	if (tp->mac_version == RTL_GIGA_MAC_VER_02 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_03) {
-		if ((speed == SPEED_100) && (autoneg != AUTONEG_ENABLE)) {
-			rtl_writephy(tp, 0x17, 0x2138);
-			rtl_writephy(tp, 0x0e, 0x0260);
-		} else {
-			rtl_writephy(tp, 0x17, 0x2108);
-			rtl_writephy(tp, 0x0e, 0x0000);
-		}
-	}
-
-	rc = 0;
-out:
-	return rc;
-}
-
-static int rtl8169_set_speed(struct net_device *dev,
-			     u8 autoneg, u16 speed, u8 duplex, u32 advertising)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-	int ret;
-
-	ret = tp->set_speed(dev, autoneg, speed, duplex, advertising);
-	if (ret < 0)
-		goto out;
-
-	if (netif_running(dev) && (autoneg == AUTONEG_ENABLE) &&
-	    (advertising & ADVERTISED_1000baseT_Full) &&
-	    !pci_is_pcie(tp->pci_dev)) {
-		mod_timer(&tp->timer, jiffies + RTL8169_PHY_TIMEOUT);
-	}
-out:
-	return ret;
-}
-
 static netdev_features_t rtl8169_fix_features(struct net_device *dev,
 	netdev_features_t features)
 {
@@ -1940,76 +1640,6 @@ static void rtl8169_rx_vlan_tag(struct RxDesc *desc, struct sk_buff *skb)
 		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), swab16(opts2 & 0xffff));
 }
 
-static int rtl8169_get_link_ksettings_tbi(struct net_device *dev,
-					  struct ethtool_link_ksettings *cmd)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-	u32 status;
-	u32 supported, advertising;
-
-	supported =
-		SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg | SUPPORTED_FIBRE;
-	cmd->base.port = PORT_FIBRE;
-
-	status = RTL_R32(tp, TBICSR);
-	advertising = (status & TBINwEnable) ?  ADVERTISED_Autoneg : 0;
-	cmd->base.autoneg = !!(status & TBINwEnable);
-
-	cmd->base.speed = SPEED_1000;
-	cmd->base.duplex = DUPLEX_FULL; /* Always set */
-
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
-						supported);
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
-						advertising);
-
-	return 0;
-}
-
-static int rtl8169_get_link_ksettings_xmii(struct net_device *dev,
-					   struct ethtool_link_ksettings *cmd)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-
-	mii_ethtool_get_link_ksettings(&tp->mii, cmd);
-
-	return 0;
-}
-
-static int rtl8169_get_link_ksettings(struct net_device *dev,
-				      struct ethtool_link_ksettings *cmd)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-	int rc;
-
-	rtl_lock_work(tp);
-	rc = tp->get_link_ksettings(dev, cmd);
-	rtl_unlock_work(tp);
-
-	return rc;
-}
-
-static int rtl8169_set_link_ksettings(struct net_device *dev,
-				      const struct ethtool_link_ksettings *cmd)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-	int rc;
-	u32 advertising;
-
-	if (!ethtool_convert_link_mode_to_legacy_u32(&advertising,
-	    cmd->link_modes.advertising))
-		return -EINVAL;
-
-	del_timer_sync(&tp->timer);
-
-	rtl_lock_work(tp);
-	rc = rtl8169_set_speed(dev, cmd->base.autoneg, cmd->base.speed,
-			       cmd->base.duplex, advertising);
-	rtl_unlock_work(tp);
-
-	return rc;
-}
-
 static void rtl8169_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 			     void *p)
 {
@@ -2185,13 +1815,6 @@ static void rtl8169_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 	}
 }
 
-static int rtl8169_nway_reset(struct net_device *dev)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-
-	return mii_nway_restart(&tp->mii);
-}
-
 /*
  * Interrupt coalescing
  *
@@ -2264,7 +1887,7 @@ static const struct rtl_coalesce_info *rtl_coalesce_info(struct net_device *dev)
 	const struct rtl_coalesce_info *ci;
 	int rc;
 
-	rc = rtl8169_get_link_ksettings(dev, &ecmd);
+	rc = phy_ethtool_get_link_ksettings(dev, &ecmd);
 	if (rc < 0)
 		return ERR_PTR(rc);
 
@@ -2422,9 +2045,9 @@ static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.get_sset_count		= rtl8169_get_sset_count,
 	.get_ethtool_stats	= rtl8169_get_ethtool_stats,
 	.get_ts_info		= ethtool_op_get_ts_info,
-	.nway_reset		= rtl8169_nway_reset,
-	.get_link_ksettings	= rtl8169_get_link_ksettings,
-	.set_link_ksettings	= rtl8169_set_link_ksettings,
+	.nway_reset		= phy_ethtool_nway_reset,
+	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
+	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 };
 
 static void rtl8169_get_mac_version(struct rtl8169_private *tp,
@@ -2537,15 +2160,15 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp,
 			   "unknown MAC, using family default\n");
 		tp->mac_version = default_version;
 	} else if (tp->mac_version == RTL_GIGA_MAC_VER_42) {
-		tp->mac_version = tp->mii.supports_gmii ?
+		tp->mac_version = tp->supports_gmii ?
 				  RTL_GIGA_MAC_VER_42 :
 				  RTL_GIGA_MAC_VER_43;
 	} else if (tp->mac_version == RTL_GIGA_MAC_VER_45) {
-		tp->mac_version = tp->mii.supports_gmii ?
+		tp->mac_version = tp->supports_gmii ?
 				  RTL_GIGA_MAC_VER_45 :
 				  RTL_GIGA_MAC_VER_47;
 	} else if (tp->mac_version == RTL_GIGA_MAC_VER_46) {
-		tp->mac_version = tp->mii.supports_gmii ?
+		tp->mac_version = tp->supports_gmii ?
 				  RTL_GIGA_MAC_VER_46 :
 				  RTL_GIGA_MAC_VER_48;
 	}
@@ -2553,7 +2176,7 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp,
 
 static void rtl8169_print_mac_version(struct rtl8169_private *tp)
 {
-	dprintk("mac_version = 0x%02x\n", tp->mac_version);
+	netif_dbg(tp, drv, tp->dev, "mac_version = 0x%02x\n", tp->mac_version);
 }
 
 struct phy_reg {
@@ -4405,62 +4028,16 @@ static void rtl_hw_phy_config(struct net_device *dev)
 	}
 }
 
-static void rtl_phy_work(struct rtl8169_private *tp)
-{
-	struct timer_list *timer = &tp->timer;
-	unsigned long timeout = RTL8169_PHY_TIMEOUT;
-
-	assert(tp->mac_version > RTL_GIGA_MAC_VER_01);
-
-	if (tp->phy_reset_pending(tp)) {
-		/*
-		 * A busy loop could burn quite a few cycles on nowadays CPU.
-		 * Let's delay the execution of the timer for a few ticks.
-		 */
-		timeout = HZ/10;
-		goto out_mod_timer;
-	}
-
-	if (tp->link_ok(tp))
-		return;
-
-	netif_dbg(tp, link, tp->dev, "PHY reset until link up\n");
-
-	tp->phy_reset_enable(tp);
-
-out_mod_timer:
-	mod_timer(timer, jiffies + timeout);
-}
-
 static void rtl_schedule_task(struct rtl8169_private *tp, enum rtl_flag flag)
 {
 	if (!test_and_set_bit(flag, tp->wk.flags))
 		schedule_work(&tp->wk.work);
 }
 
-static void rtl8169_phy_timer(struct timer_list *t)
-{
-	struct rtl8169_private *tp = from_timer(tp, t, timer);
-
-	rtl_schedule_task(tp, RTL_FLAG_TASK_PHY_PENDING);
-}
-
-DECLARE_RTL_COND(rtl_phy_reset_cond)
-{
-	return tp->phy_reset_pending(tp);
-}
-
-static void rtl8169_phy_reset(struct net_device *dev,
-			      struct rtl8169_private *tp)
-{
-	tp->phy_reset_enable(tp);
-	rtl_msleep_loop_wait_low(tp, &rtl_phy_reset_cond, 1, 100);
-}
-
 static bool rtl_tbi_enabled(struct rtl8169_private *tp)
 {
 	return (tp->mac_version == RTL_GIGA_MAC_VER_01) &&
-	    (RTL_R8(tp, PHYstatus) & TBI_Enable);
+	       (RTL_R8(tp, PHYstatus) & TBI_Enable);
 }
 
 static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp)
@@ -4468,7 +4045,8 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp)
 	rtl_hw_phy_config(dev);
 
 	if (tp->mac_version <= RTL_GIGA_MAC_VER_06) {
-		dprintk("Set MAC Reg C+CR Offset 0x82h = 0x01h\n");
+		netif_dbg(tp, drv, dev,
+			  "Set MAC Reg C+CR Offset 0x82h = 0x01h\n");
 		RTL_W8(tp, 0x82, 0x01);
 	}
 
@@ -4478,23 +4056,18 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp)
 		pci_write_config_byte(tp->pci_dev, PCI_CACHE_LINE_SIZE, 0x08);
 
 	if (tp->mac_version == RTL_GIGA_MAC_VER_02) {
-		dprintk("Set MAC Reg C+CR Offset 0x82h = 0x01h\n");
+		netif_dbg(tp, drv, dev,
+			  "Set MAC Reg C+CR Offset 0x82h = 0x01h\n");
 		RTL_W8(tp, 0x82, 0x01);
-		dprintk("Set PHY Reg 0x0bh = 0x00h\n");
+		netif_dbg(tp, drv, dev,
+			  "Set PHY Reg 0x0bh = 0x00h\n");
 		rtl_writephy(tp, 0x0b, 0x0000); //w 0x0b 15 0 0
 	}
 
-	rtl8169_phy_reset(dev, tp);
+	/* We may have called phy_speed_down before */
+	phy_speed_up(dev->phydev);
 
-	rtl8169_set_speed(dev, AUTONEG_ENABLE, SPEED_1000, DUPLEX_FULL,
-			  ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full |
-			  ADVERTISED_100baseT_Half | ADVERTISED_100baseT_Full |
-			  (tp->mii.supports_gmii ?
-			   ADVERTISED_1000baseT_Half |
-			   ADVERTISED_1000baseT_Full : 0));
-
-	if (rtl_tbi_enabled(tp))
-		netif_info(tp, link, dev, "TBI auto-negotiating\n");
+	genphy_soft_reset(dev->phydev);
 }
 
 static void rtl_rar_set(struct rtl8169_private *tp, u8 *addr)
@@ -4539,34 +4112,10 @@ static int rtl_set_mac_address(struct net_device *dev, void *p)
 
 static int rtl8169_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
-	struct rtl8169_private *tp = netdev_priv(dev);
-	struct mii_ioctl_data *data = if_mii(ifr);
-
-	return netif_running(dev) ? tp->do_ioctl(tp, data, cmd) : -ENODEV;
-}
-
-static int rtl_xmii_ioctl(struct rtl8169_private *tp,
-			  struct mii_ioctl_data *data, int cmd)
-{
-	switch (cmd) {
-	case SIOCGMIIPHY:
-		data->phy_id = 32; /* Internal PHY */
-		return 0;
-
-	case SIOCGMIIREG:
-		data->val_out = rtl_readphy(tp, data->reg_num & 0x1f);
-		return 0;
-
-	case SIOCSMIIREG:
-		rtl_writephy(tp, data->reg_num & 0x1f, data->val_in);
-		return 0;
-	}
-	return -EOPNOTSUPP;
-}
+	if (!netif_running(dev))
+		return -ENODEV;
 
-static int rtl_tbi_ioctl(struct rtl8169_private *tp, struct mii_ioctl_data *data, int cmd)
-{
-	return -EOPNOTSUPP;
+	return phy_mii_ioctl(dev->phydev, ifr, cmd);
 }
 
 static void rtl_init_mdio_ops(struct rtl8169_private *tp)
@@ -4594,30 +4143,6 @@ static void rtl_init_mdio_ops(struct rtl8169_private *tp)
 	}
 }
 
-static void rtl_speed_down(struct rtl8169_private *tp)
-{
-	u32 adv;
-	int lpa;
-
-	rtl_writephy(tp, 0x1f, 0x0000);
-	lpa = rtl_readphy(tp, MII_LPA);
-
-	if (lpa & (LPA_10HALF | LPA_10FULL))
-		adv = ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full;
-	else if (lpa & (LPA_100HALF | LPA_100FULL))
-		adv = ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full |
-		      ADVERTISED_100baseT_Half | ADVERTISED_100baseT_Full;
-	else
-		adv = ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full |
-		      ADVERTISED_100baseT_Half | ADVERTISED_100baseT_Full |
-		      (tp->mii.supports_gmii ?
-		       ADVERTISED_1000baseT_Half |
-		       ADVERTISED_1000baseT_Full : 0);
-
-	rtl8169_set_speed(tp->dev, AUTONEG_ENABLE, SPEED_1000, DUPLEX_FULL,
-			  adv);
-}
-
 static void rtl_wol_suspend_quirk(struct rtl8169_private *tp)
 {
 	switch (tp->mac_version) {
@@ -4639,56 +4164,15 @@ static void rtl_wol_suspend_quirk(struct rtl8169_private *tp)
 
 static bool rtl_wol_pll_power_down(struct rtl8169_private *tp)
 {
-	if (!(__rtl8169_get_wol(tp) & WAKE_ANY))
+	if (!netif_running(tp->dev) || !__rtl8169_get_wol(tp))
 		return false;
 
-	rtl_speed_down(tp);
+	phy_speed_down(tp->dev->phydev, false);
 	rtl_wol_suspend_quirk(tp);
 
 	return true;
 }
 
-static void r8168_phy_power_up(struct rtl8169_private *tp)
-{
-	rtl_writephy(tp, 0x1f, 0x0000);
-	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_11:
-	case RTL_GIGA_MAC_VER_12:
-	case RTL_GIGA_MAC_VER_17 ... RTL_GIGA_MAC_VER_28:
-	case RTL_GIGA_MAC_VER_31:
-		rtl_writephy(tp, 0x0e, 0x0000);
-		break;
-	default:
-		break;
-	}
-	rtl_writephy(tp, MII_BMCR, BMCR_ANENABLE);
-
-	/* give MAC/PHY some time to resume */
-	msleep(20);
-}
-
-static void r8168_phy_power_down(struct rtl8169_private *tp)
-{
-	rtl_writephy(tp, 0x1f, 0x0000);
-	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_32:
-	case RTL_GIGA_MAC_VER_33:
-	case RTL_GIGA_MAC_VER_40:
-	case RTL_GIGA_MAC_VER_41:
-		rtl_writephy(tp, MII_BMCR, BMCR_ANENABLE | BMCR_PDOWN);
-		break;
-
-	case RTL_GIGA_MAC_VER_11:
-	case RTL_GIGA_MAC_VER_12:
-	case RTL_GIGA_MAC_VER_17 ... RTL_GIGA_MAC_VER_28:
-	case RTL_GIGA_MAC_VER_31:
-		rtl_writephy(tp, 0x0e, 0x0200);
-	default:
-		rtl_writephy(tp, MII_BMCR, BMCR_PDOWN);
-		break;
-	}
-}
-
 static void r8168_pll_power_down(struct rtl8169_private *tp)
 {
 	if (r8168_check_dash(tp))
@@ -4701,8 +4185,6 @@ static void r8168_pll_power_down(struct rtl8169_private *tp)
 	if (rtl_wol_pll_power_down(tp))
 		return;
 
-	r8168_phy_power_down(tp);
-
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33:
 	case RTL_GIGA_MAC_VER_37:
@@ -4754,7 +4236,9 @@ static void r8168_pll_power_up(struct rtl8169_private *tp)
 		break;
 	}
 
-	r8168_phy_power_up(tp);
+	phy_resume(tp->dev->phydev);
+	/* give MAC/PHY some time to resume */
+	msleep(20);
 }
 
 static void rtl_pll_power_down(struct rtl8169_private *tp)
@@ -5172,8 +4656,8 @@ static void rtl_hw_start_8169(struct rtl8169_private *tp)
 
 	if (tp->mac_version == RTL_GIGA_MAC_VER_02 ||
 	    tp->mac_version == RTL_GIGA_MAC_VER_03) {
-		dprintk("Set MAC Reg C+CR Offset 0xe0. "
-			"Bit-3 and bit-14 MUST be 1\n");
+		netif_dbg(tp, drv, tp->dev,
+			  "Set MAC Reg C+CR Offset 0xe0. Bit 3 and Bit 14 MUST be 1\n");
 		tp->cp_cmd |= (1 << 14);
 	}
 
@@ -5236,12 +4720,7 @@ static void rtl_csi_access_enable(struct rtl8169_private *tp, u8 val)
 	rtl_csi_write(tp, 0x070c, csi | val << 24);
 }
 
-static void rtl_csi_access_enable_1(struct rtl8169_private *tp)
-{
-	rtl_csi_access_enable(tp, 0x17);
-}
-
-static void rtl_csi_access_enable_2(struct rtl8169_private *tp)
+static void rtl_set_def_aspm_entry_latency(struct rtl8169_private *tp)
 {
 	rtl_csi_access_enable(tp, 0x27);
 }
@@ -5290,6 +4769,17 @@ static void rtl_pcie_state_l2l3_enable(struct rtl8169_private *tp, bool enable)
 	RTL_W8(tp, Config3, data);
 }
 
+static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
+{
+	if (enable) {
+		RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn);
+		RTL_W8(tp, Config5, RTL_R8(tp, Config5) | ASPM_en);
+	} else {
+		RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
+		RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+	}
+}
+
 static void rtl_hw_start_8168bb(struct rtl8169_private *tp)
 {
 	RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en);
@@ -5337,7 +4827,7 @@ static void rtl_hw_start_8168cp_1(struct rtl8169_private *tp)
 		{ 0x07, 0,	0x2000 }
 	};
 
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_ephy_init(tp, e_info_8168cp, ARRAY_SIZE(e_info_8168cp));
 
@@ -5346,7 +4836,7 @@ static void rtl_hw_start_8168cp_1(struct rtl8169_private *tp)
 
 static void rtl_hw_start_8168cp_2(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en);
 
@@ -5359,7 +4849,7 @@ static void rtl_hw_start_8168cp_2(struct rtl8169_private *tp)
 
 static void rtl_hw_start_8168cp_3(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en);
 
@@ -5383,7 +4873,7 @@ static void rtl_hw_start_8168c_1(struct rtl8169_private *tp)
 		{ 0x06, 0x0080,	0x0000 }
 	};
 
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	RTL_W8(tp, DBG_REG, 0x06 | FIX_NAK_1 | FIX_NAK_2);
 
@@ -5399,7 +4889,7 @@ static void rtl_hw_start_8168c_2(struct rtl8169_private *tp)
 		{ 0x03, 0x0400,	0x0220 }
 	};
 
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_ephy_init(tp, e_info_8168c_2, ARRAY_SIZE(e_info_8168c_2));
 
@@ -5413,14 +4903,14 @@ static void rtl_hw_start_8168c_3(struct rtl8169_private *tp)
 
 static void rtl_hw_start_8168c_4(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	__rtl_hw_start_8168cp(tp);
 }
 
 static void rtl_hw_start_8168d(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_disable_clock_request(tp);
 
@@ -5435,7 +4925,7 @@ static void rtl_hw_start_8168d(struct rtl8169_private *tp)
 
 static void rtl_hw_start_8168dp(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_1(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	if (tp->dev->mtu <= ETH_DATA_LEN)
 		rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
@@ -5453,7 +4943,7 @@ static void rtl_hw_start_8168d_4(struct rtl8169_private *tp)
 		{ 0x0c, 0x0100,	0x0020 }
 	};
 
-	rtl_csi_access_enable_1(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
@@ -5482,7 +4972,7 @@ static void rtl_hw_start_8168e_1(struct rtl8169_private *tp)
 		{ 0x0a, 0x0000,	0x0040 }
 	};
 
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_ephy_init(tp, e_info_8168e_1, ARRAY_SIZE(e_info_8168e_1));
 
@@ -5507,7 +4997,7 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp)
 		{ 0x19, 0x0000,	0x0224 }
 	};
 
-	rtl_csi_access_enable_1(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_ephy_init(tp, e_info_8168e_2, ARRAY_SIZE(e_info_8168e_2));
 
@@ -5536,11 +5026,13 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp)
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN);
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) | PWM_EN);
 	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~Spi_en);
+
+	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8168f(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
@@ -5611,7 +5103,7 @@ static void rtl_hw_start_8168g(struct rtl8169_private *tp)
 	rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x48, ERIAR_EXGMAC);
 	rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, 0x00100006, ERIAR_EXGMAC);
 
-	rtl_csi_access_enable_1(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
@@ -5646,9 +5138,9 @@ static void rtl_hw_start_8168g_1(struct rtl8169_private *tp)
 	rtl_hw_start_8168g(tp);
 
 	/* disable aspm and clock request before access ephy */
-	RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
-	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8168g_1, ARRAY_SIZE(e_info_8168g_1));
+	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8168g_2(struct rtl8169_private *tp)
@@ -5681,9 +5173,9 @@ static void rtl_hw_start_8411_2(struct rtl8169_private *tp)
 	rtl_hw_start_8168g(tp);
 
 	/* disable aspm and clock request before access ephy */
-	RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
-	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8411_2, ARRAY_SIZE(e_info_8411_2));
+	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
@@ -5700,8 +5192,7 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
 	};
 
 	/* disable aspm and clock request before access ephy */
-	RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
-	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8168h_1, ARRAY_SIZE(e_info_8168h_1));
 
 	RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO);
@@ -5711,7 +5202,7 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
 	rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x48, ERIAR_EXGMAC);
 	rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, 0x00100006, ERIAR_EXGMAC);
 
-	rtl_csi_access_enable_1(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
@@ -5780,6 +5271,8 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
 	r8168_mac_ocp_write(tp, 0xe63e, 0x0000);
 	r8168_mac_ocp_write(tp, 0xc094, 0x0000);
 	r8168_mac_ocp_write(tp, 0xc09e, 0x0000);
+
+	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8168ep(struct rtl8169_private *tp)
@@ -5793,7 +5286,7 @@ static void rtl_hw_start_8168ep(struct rtl8169_private *tp)
 	rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x5f, ERIAR_EXGMAC);
 	rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, 0x00100006, ERIAR_EXGMAC);
 
-	rtl_csi_access_enable_1(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
@@ -5831,11 +5324,12 @@ static void rtl_hw_start_8168ep_1(struct rtl8169_private *tp)
 	};
 
 	/* disable aspm and clock request before access ephy */
-	RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
-	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8168ep_1, ARRAY_SIZE(e_info_8168ep_1));
 
 	rtl_hw_start_8168ep(tp);
+
+	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8168ep_2(struct rtl8169_private *tp)
@@ -5847,14 +5341,15 @@ static void rtl_hw_start_8168ep_2(struct rtl8169_private *tp)
 	};
 
 	/* disable aspm and clock request before access ephy */
-	RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
-	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8168ep_2, ARRAY_SIZE(e_info_8168ep_2));
 
 	rtl_hw_start_8168ep(tp);
 
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN);
 	RTL_W8(tp, MISC_1, RTL_R8(tp, MISC_1) & ~PFM_D3COLD_EN);
+
+	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp)
@@ -5868,8 +5363,7 @@ static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp)
 	};
 
 	/* disable aspm and clock request before access ephy */
-	RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
-	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8168ep_3, ARRAY_SIZE(e_info_8168ep_3));
 
 	rtl_hw_start_8168ep(tp);
@@ -5889,6 +5383,8 @@ static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp)
 	data = r8168_mac_ocp_read(tp, 0xe860);
 	data |= 0x0080;
 	r8168_mac_ocp_write(tp, 0xe860, data);
+
+	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8168(struct rtl8169_private *tp)
@@ -6006,8 +5502,9 @@ static void rtl_hw_start_8168(struct rtl8169_private *tp)
 		break;
 
 	default:
-		printk(KERN_ERR PFX "%s: unknown chipset (mac_version = %d).\n",
-		       tp->dev->name, tp->mac_version);
+		netif_err(tp, drv, tp->dev,
+			  "unknown chipset (mac_version = %d)\n",
+			  tp->mac_version);
 		break;
 	}
 }
@@ -6026,7 +5523,7 @@ static void rtl_hw_start_8102e_1(struct rtl8169_private *tp)
 	};
 	u8 cfg1;
 
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	RTL_W8(tp, DBG_REG, FIX_NAK_1);
 
@@ -6045,7 +5542,7 @@ static void rtl_hw_start_8102e_1(struct rtl8169_private *tp)
 
 static void rtl_hw_start_8102e_2(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
@@ -6100,7 +5597,7 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp)
 		{ 0x1e,	0, 0x4000 }
 	};
 
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	/* Force LAN exit from ASPM if Rx/Tx are not idle */
 	RTL_W32(tp, FuncEvent, RTL_R32(tp, FuncEvent) | 0x002800);
@@ -6384,7 +5881,6 @@ static void rtl_reset_work(struct rtl8169_private *tp)
 	napi_enable(&tp->napi);
 	rtl_hw_start(tp);
 	netif_wake_queue(dev);
-	rtl8169_check_link_status(dev, tp);
 }
 
 static void rtl8169_tx_timeout(struct net_device *dev)
@@ -6958,20 +6454,15 @@ release_descriptor:
 static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
 {
 	struct rtl8169_private *tp = dev_instance;
-	int handled = 0;
-	u16 status;
+	u16 status = rtl_get_events(tp);
 
-	status = rtl_get_events(tp);
-	if (status && status != 0xffff) {
-		status &= RTL_EVENT_NAPI | tp->event_slow;
-		if (status) {
-			handled = 1;
+	if (status == 0xffff || !(status & (RTL_EVENT_NAPI | tp->event_slow)))
+		return IRQ_NONE;
 
-			rtl_irq_disable(tp);
-			napi_schedule_irqoff(&tp->napi);
-		}
-	}
-	return IRQ_RETVAL(handled);
+	rtl_irq_disable(tp);
+	napi_schedule_irqoff(&tp->napi);
+
+	return IRQ_HANDLED;
 }
 
 /*
@@ -7001,7 +6492,7 @@ static void rtl_slow_event_work(struct rtl8169_private *tp)
 		rtl8169_pcierr_interrupt(dev);
 
 	if (status & LinkChg)
-		rtl8169_check_link_status(dev, tp);
+		phy_mac_interrupt(dev->phydev);
 
 	rtl_irq_enable_all(tp);
 }
@@ -7015,7 +6506,6 @@ static void rtl_task(struct work_struct *work)
 		/* XXX - keep rtl_slow_event_work() as first element. */
 		{ RTL_FLAG_TASK_SLOW_PENDING,	rtl_slow_event_work },
 		{ RTL_FLAG_TASK_RESET_PENDING,	rtl_reset_work },
-		{ RTL_FLAG_TASK_PHY_PENDING,	rtl_phy_work }
 	};
 	struct rtl8169_private *tp =
 		container_of(work, struct rtl8169_private, wk.work);
@@ -7084,11 +6574,51 @@ static void rtl8169_rx_missed(struct net_device *dev)
 	RTL_W32(tp, RxMissed, 0);
 }
 
+static void r8169_phylink_handler(struct net_device *ndev)
+{
+	struct rtl8169_private *tp = netdev_priv(ndev);
+
+	if (netif_carrier_ok(ndev)) {
+		rtl_link_chg_patch(tp);
+		pm_request_resume(&tp->pci_dev->dev);
+	} else {
+		pm_runtime_idle(&tp->pci_dev->dev);
+	}
+
+	if (net_ratelimit())
+		phy_print_status(ndev->phydev);
+}
+
+static int r8169_phy_connect(struct rtl8169_private *tp)
+{
+	struct phy_device *phydev = mdiobus_get_phy(tp->mii_bus, 0);
+	phy_interface_t phy_mode;
+	int ret;
+
+	phy_mode = tp->supports_gmii ? PHY_INTERFACE_MODE_GMII :
+		   PHY_INTERFACE_MODE_MII;
+
+	ret = phy_connect_direct(tp->dev, phydev, r8169_phylink_handler,
+				 phy_mode);
+	if (ret)
+		return ret;
+
+	if (!tp->supports_gmii)
+		phy_set_max_speed(phydev, SPEED_100);
+
+	/* Ensure to advertise everything, incl. pause */
+	phydev->advertising = phydev->supported;
+
+	phy_attached_info(phydev);
+
+	return 0;
+}
+
 static void rtl8169_down(struct net_device *dev)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 
-	del_timer_sync(&tp->timer);
+	phy_stop(dev->phydev);
 
 	napi_disable(&tp->napi);
 	netif_stop_queue(dev);
@@ -7129,6 +6659,8 @@ static int rtl8169_close(struct net_device *dev)
 
 	cancel_work_sync(&tp->wk.work);
 
+	phy_disconnect(dev->phydev);
+
 	pci_free_irq(pdev, 0, tp);
 
 	dma_free_coherent(&pdev->dev, R8169_RX_RING_BYTES, tp->RxDescArray,
@@ -7189,6 +6721,10 @@ static int rtl_open(struct net_device *dev)
 	if (retval < 0)
 		goto err_release_fw_2;
 
+	retval = r8169_phy_connect(tp);
+	if (retval)
+		goto err_free_irq;
+
 	rtl_lock_work(tp);
 
 	set_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags);
@@ -7204,17 +6740,17 @@ static int rtl_open(struct net_device *dev)
 	if (!rtl8169_init_counter_offsets(tp))
 		netif_warn(tp, hw, dev, "counter reset/update failed\n");
 
+	phy_start(dev->phydev);
 	netif_start_queue(dev);
 
 	rtl_unlock_work(tp);
 
-	tp->saved_wolopts = 0;
 	pm_runtime_put_sync(&pdev->dev);
-
-	rtl8169_check_link_status(dev, tp);
 out:
 	return retval;
 
+err_free_irq:
+	pci_free_irq(pdev, 0, tp);
 err_release_fw_2:
 	rtl_release_firmware(tp);
 	rtl8169_rx_clear(tp);
@@ -7293,6 +6829,7 @@ static void rtl8169_net_suspend(struct net_device *dev)
 	if (!netif_running(dev))
 		return;
 
+	phy_stop(dev->phydev);
 	netif_device_detach(dev);
 	netif_stop_queue(dev);
 
@@ -7323,6 +6860,9 @@ static void __rtl8169_resume(struct net_device *dev)
 	netif_device_attach(dev);
 
 	rtl_pll_power_up(tp);
+	rtl8169_init_phy(dev, tp);
+
+	phy_start(tp->dev->phydev);
 
 	rtl_lock_work(tp);
 	napi_enable(&tp->napi);
@@ -7336,9 +6876,6 @@ static int rtl8169_resume(struct device *device)
 {
 	struct pci_dev *pdev = to_pci_dev(device);
 	struct net_device *dev = pci_get_drvdata(pdev);
-	struct rtl8169_private *tp = netdev_priv(dev);
-
-	rtl8169_init_phy(dev, tp);
 
 	if (netif_running(dev))
 		__rtl8169_resume(dev);
@@ -7352,13 +6889,10 @@ static int rtl8169_runtime_suspend(struct device *device)
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct rtl8169_private *tp = netdev_priv(dev);
 
-	if (!tp->TxDescArray) {
-		rtl_pll_power_down(tp);
+	if (!tp->TxDescArray)
 		return 0;
-	}
 
 	rtl_lock_work(tp);
-	tp->saved_wolopts = __rtl8169_get_wol(tp);
 	__rtl8169_set_wol(tp, WAKE_ANY);
 	rtl_unlock_work(tp);
 
@@ -7383,11 +6917,8 @@ static int rtl8169_runtime_resume(struct device *device)
 
 	rtl_lock_work(tp);
 	__rtl8169_set_wol(tp, tp->saved_wolopts);
-	tp->saved_wolopts = 0;
 	rtl_unlock_work(tp);
 
-	rtl8169_init_phy(dev, tp);
-
 	__rtl8169_resume(dev);
 
 	return 0;
@@ -7455,7 +6986,7 @@ static void rtl_shutdown(struct pci_dev *pdev)
 	rtl8169_hw_reset(tp);
 
 	if (system_state == SYSTEM_POWER_OFF) {
-		if (__rtl8169_get_wol(tp) & WAKE_ANY) {
+		if (tp->saved_wolopts) {
 			rtl_wol_suspend_quirk(tp);
 			rtl_wol_shutdown_quirk(tp);
 		}
@@ -7476,6 +7007,7 @@ static void rtl_remove_one(struct pci_dev *pdev)
 	netif_napi_del(&tp->napi);
 
 	unregister_netdev(dev);
+	mdiobus_unregister(tp->mii_bus);
 
 	rtl_release_firmware(tp);
 
@@ -7544,6 +7076,11 @@ static int rtl_alloc_irq(struct rtl8169_private *tp)
 		RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~MSIEnable);
 		RTL_W8(tp, Cfg9346, Cfg9346_Lock);
 		flags = PCI_IRQ_LEGACY;
+	} else if (tp->mac_version == RTL_GIGA_MAC_VER_40) {
+		/* This version was reported to have issues with resume
+		 * from suspend when using MSI-X
+		 */
+		flags = PCI_IRQ_LEGACY | PCI_IRQ_MSI;
 	} else {
 		flags = PCI_IRQ_ALL_TYPES;
 	}
@@ -7561,6 +7098,68 @@ DECLARE_RTL_COND(rtl_rxtx_empty_cond)
 	return (RTL_R8(tp, MCU) & RXTX_EMPTY) == RXTX_EMPTY;
 }
 
+static int r8169_mdio_read_reg(struct mii_bus *mii_bus, int phyaddr, int phyreg)
+{
+	struct rtl8169_private *tp = mii_bus->priv;
+
+	if (phyaddr > 0)
+		return -ENODEV;
+
+	return rtl_readphy(tp, phyreg);
+}
+
+static int r8169_mdio_write_reg(struct mii_bus *mii_bus, int phyaddr,
+				int phyreg, u16 val)
+{
+	struct rtl8169_private *tp = mii_bus->priv;
+
+	if (phyaddr > 0)
+		return -ENODEV;
+
+	rtl_writephy(tp, phyreg, val);
+
+	return 0;
+}
+
+static int r8169_mdio_register(struct rtl8169_private *tp)
+{
+	struct pci_dev *pdev = tp->pci_dev;
+	struct phy_device *phydev;
+	struct mii_bus *new_bus;
+	int ret;
+
+	new_bus = devm_mdiobus_alloc(&pdev->dev);
+	if (!new_bus)
+		return -ENOMEM;
+
+	new_bus->name = "r8169";
+	new_bus->priv = tp;
+	new_bus->parent = &pdev->dev;
+	new_bus->irq[0] = PHY_IGNORE_INTERRUPT;
+	snprintf(new_bus->id, MII_BUS_ID_SIZE, "r8169-%x",
+		 PCI_DEVID(pdev->bus->number, pdev->devfn));
+
+	new_bus->read = r8169_mdio_read_reg;
+	new_bus->write = r8169_mdio_write_reg;
+
+	ret = mdiobus_register(new_bus);
+	if (ret)
+		return ret;
+
+	phydev = mdiobus_get_phy(new_bus, 0);
+	if (!phydev) {
+		mdiobus_unregister(new_bus);
+		return -ENODEV;
+	}
+
+	/* PHY will be woken up in rtl_open() */
+	phy_suspend(phydev);
+
+	tp->mii_bus = new_bus;
+
+	return 0;
+}
+
 static void rtl_hw_init_8168g(struct rtl8169_private *tp)
 {
 	u32 data;
@@ -7614,19 +7213,48 @@ static void rtl_hw_initialize(struct rtl8169_private *tp)
 	}
 }
 
+/* Versions RTL8102e and from RTL8168c onwards support csum_v2 */
+static bool rtl_chip_supports_csum_v2(struct rtl8169_private *tp)
+{
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_01 ... RTL_GIGA_MAC_VER_06:
+	case RTL_GIGA_MAC_VER_10 ... RTL_GIGA_MAC_VER_17:
+		return false;
+	default:
+		return true;
+	}
+}
+
+static int rtl_jumbo_max(struct rtl8169_private *tp)
+{
+	/* Non-GBit versions don't support jumbo frames */
+	if (!tp->supports_gmii)
+		return JUMBO_1K;
+
+	switch (tp->mac_version) {
+	/* RTL8169 */
+	case RTL_GIGA_MAC_VER_01 ... RTL_GIGA_MAC_VER_06:
+		return JUMBO_7K;
+	/* RTL8168b */
+	case RTL_GIGA_MAC_VER_11:
+	case RTL_GIGA_MAC_VER_12:
+	case RTL_GIGA_MAC_VER_17:
+		return JUMBO_4K;
+	/* RTL8168c */
+	case RTL_GIGA_MAC_VER_18 ... RTL_GIGA_MAC_VER_24:
+		return JUMBO_6K;
+	default:
+		return JUMBO_9K;
+	}
+}
+
 static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	const struct rtl_cfg_info *cfg = rtl_cfg_infos + ent->driver_data;
 	struct rtl8169_private *tp;
-	struct mii_if_info *mii;
 	struct net_device *dev;
 	int chipset, region, i;
-	int rc;
-
-	if (netif_msg_drv(&debug)) {
-		printk(KERN_INFO "%s Gigabit Ethernet driver %s loaded\n",
-		       MODULENAME, RTL8169_VERSION);
-	}
+	int jumbo_max, rc;
 
 	dev = devm_alloc_etherdev(&pdev->dev, sizeof (*tp));
 	if (!dev)
@@ -7638,19 +7266,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	tp->dev = dev;
 	tp->pci_dev = pdev;
 	tp->msg_enable = netif_msg_init(debug.msg_enable, R8169_MSG_DEFAULT);
-
-	mii = &tp->mii;
-	mii->dev = dev;
-	mii->mdio_read = rtl_mdio_read;
-	mii->mdio_write = rtl_mdio_write;
-	mii->phy_id_mask = 0x1f;
-	mii->reg_num_mask = 0x1f;
-	mii->supports_gmii = cfg->has_gmii;
-
-	/* disable ASPM completely as that cause random device stop working
-	 * problems as well as full system hangs for some PCIe devices users */
-	pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1 |
-				     PCIE_LINK_STATE_CLKPM);
+	tp->supports_gmii = cfg->has_gmii;
 
 	/* enable device (incl. PCI PM wakeup and hotplug setup) */
 	rc = pcim_enable_device(pdev);
@@ -7689,6 +7305,11 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Identify chip attached to board */
 	rtl8169_get_mac_version(tp, cfg->default_ver);
 
+	if (rtl_tbi_enabled(tp)) {
+		dev_err(&pdev->dev, "TBI fiber mode not supported\n");
+		return -ENODEV;
+	}
+
 	tp->cp_cmd = RTL_R16(tp, CPlusCmd);
 
 	if ((sizeof(dma_addr_t) > 4) &&
@@ -7736,22 +7357,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	tp->saved_wolopts = __rtl8169_get_wol(tp);
 
-	if (rtl_tbi_enabled(tp)) {
-		tp->set_speed = rtl8169_set_speed_tbi;
-		tp->get_link_ksettings = rtl8169_get_link_ksettings_tbi;
-		tp->phy_reset_enable = rtl8169_tbi_reset_enable;
-		tp->phy_reset_pending = rtl8169_tbi_reset_pending;
-		tp->link_ok = rtl8169_tbi_link_ok;
-		tp->do_ioctl = rtl_tbi_ioctl;
-	} else {
-		tp->set_speed = rtl8169_set_speed_xmii;
-		tp->get_link_ksettings = rtl8169_get_link_ksettings_xmii;
-		tp->phy_reset_enable = rtl8169_xmii_reset_enable;
-		tp->phy_reset_pending = rtl8169_xmii_reset_pending;
-		tp->link_ok = rtl8169_xmii_link_ok;
-		tp->do_ioctl = rtl_xmii_ioctl;
-	}
-
 	mutex_init(&tp->wk.mutex);
 	u64_stats_init(&tp->rx_stats.syncp);
 	u64_stats_init(&tp->tx_stats.syncp);
@@ -7800,16 +7405,11 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		/* Disallow toggling */
 		dev->hw_features &= ~NETIF_F_HW_VLAN_CTAG_RX;
 
-	switch (rtl_chip_infos[chipset].txd_version) {
-	case RTL_TD_0:
-		tp->tso_csum = rtl8169_tso_csum_v1;
-		break;
-	case RTL_TD_1:
+	if (rtl_chip_supports_csum_v2(tp)) {
 		tp->tso_csum = rtl8169_tso_csum_v2;
 		dev->hw_features |= NETIF_F_IPV6_CSUM | NETIF_F_TSO6;
-		break;
-	default:
-		WARN_ON_ONCE(1);
+	} else {
+		tp->tso_csum = rtl8169_tso_csum_v1;
 	}
 
 	dev->hw_features |= NETIF_F_RXALL;
@@ -7817,14 +7417,13 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* MTU range: 60 - hw-specific max */
 	dev->min_mtu = ETH_ZLEN;
-	dev->max_mtu = rtl_chip_infos[chipset].jumbo_max;
+	jumbo_max = rtl_jumbo_max(tp);
+	dev->max_mtu = jumbo_max;
 
 	tp->hw_start = cfg->hw_start;
 	tp->event_slow = cfg->event_slow;
 	tp->coalesce_info = cfg->coalesce_info;
 
-	timer_setup(&tp->timer, rtl8169_phy_timer, 0);
-
 	tp->rtl_fw = RTL_FIRMWARE_UNKNOWN;
 
 	tp->counters = dmam_alloc_coherent (&pdev->dev, sizeof(*tp->counters),
@@ -7835,30 +7434,39 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_drvdata(pdev, dev);
 
-	rc = register_netdev(dev);
-	if (rc < 0)
+	rc = r8169_mdio_register(tp);
+	if (rc)
 		return rc;
 
+	/* chip gets powered up in rtl_open() */
+	rtl_pll_power_down(tp);
+
+	rc = register_netdev(dev);
+	if (rc)
+		goto err_mdio_unregister;
+
 	netif_info(tp, probe, dev, "%s, %pM, XID %08x, IRQ %d\n",
 		   rtl_chip_infos[chipset].name, dev->dev_addr,
 		   (u32)(RTL_R32(tp, TxConfig) & 0xfcf0f8ff),
 		   pci_irq_vector(pdev, 0));
-	if (rtl_chip_infos[chipset].jumbo_max != JUMBO_1K) {
-		netif_info(tp, probe, dev, "jumbo features [frames: %d bytes, "
-			   "tx checksumming: %s]\n",
-			   rtl_chip_infos[chipset].jumbo_max,
-			  tp->mac_version <= RTL_GIGA_MAC_VER_06 ? "ok" : "ko");
-	}
+
+	if (jumbo_max > JUMBO_1K)
+		netif_info(tp, probe, dev,
+			   "jumbo features [frames: %d bytes, tx checksumming: %s]\n",
+			   jumbo_max, tp->mac_version <= RTL_GIGA_MAC_VER_06 ?
+			   "ok" : "ko");
 
 	if (r8168_check_dash(tp))
 		rtl8168_driver_start(tp);
 
-	netif_carrier_off(dev);
-
 	if (pci_dev_run_wake(pdev))
 		pm_runtime_put_sync(&pdev->dev);
 
 	return 0;
+
+err_mdio_unregister:
+	mdiobus_unregister(tp->mii_bus);
+	return rc;
 }
 
 static struct pci_driver rtl8169_pci_driver = {
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 0d811c02ff34..c06f2df895c2 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1167,7 +1167,7 @@ static int ravb_get_sset_count(struct net_device *netdev, int sset)
 }
 
 static void ravb_get_ethtool_stats(struct net_device *ndev,
-				   struct ethtool_stats *stats, u64 *data)
+				   struct ethtool_stats *estats, u64 *data)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
 	int i = 0;
@@ -1199,7 +1199,7 @@ static void ravb_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
 {
 	switch (stringset) {
 	case ETH_SS_STATS:
-		memcpy(data, *ravb_gstrings_stats, sizeof(ravb_gstrings_stats));
+		memcpy(data, ravb_gstrings_stats, sizeof(ravb_gstrings_stats));
 		break;
 	}
 }
@@ -1564,7 +1564,7 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		/* TAG and timestamp required flag */
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 		desc->tagh_tsr = (ts_skb->tag >> 4) | TX_TSR;
-		desc->ds_tagl |= le16_to_cpu(ts_skb->tag << 12);
+		desc->ds_tagl |= cpu_to_le16(ts_skb->tag << 12);
 	}
 
 	skb_tx_timestamp(skb);
@@ -1597,7 +1597,8 @@ drop:
 }
 
 static u16 ravb_select_queue(struct net_device *ndev, struct sk_buff *skb,
-			     void *accel_priv, select_queue_fallback_t fallback)
+			     struct net_device *sb_dev,
+			     select_queue_fallback_t fallback)
 {
 	/* If skb needs TX timestamp, it is handled in network control queue */
 	return (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) ? RAVB_NC :
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 5614fd231bbe..5573199c4536 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -439,10 +439,15 @@ static void sh_eth_modify(struct net_device *ndev, int enum_index, u32 clear,
 		     enum_index);
 }
 
+static u16 sh_eth_tsu_get_offset(struct sh_eth_private *mdp, int enum_index)
+{
+	return mdp->reg_offset[enum_index];
+}
+
 static void sh_eth_tsu_write(struct sh_eth_private *mdp, u32 data,
 			     int enum_index)
 {
-	u16 offset = mdp->reg_offset[enum_index];
+	u16 offset = sh_eth_tsu_get_offset(mdp, enum_index);
 
 	if (WARN_ON(offset == SH_ETH_OFFSET_INVALID))
 		return;
@@ -452,7 +457,7 @@ static void sh_eth_tsu_write(struct sh_eth_private *mdp, u32 data,
 
 static u32 sh_eth_tsu_read(struct sh_eth_private *mdp, int enum_index)
 {
-	u16 offset = mdp->reg_offset[enum_index];
+	u16 offset = sh_eth_tsu_get_offset(mdp, enum_index);
 
 	if (WARN_ON(offset == SH_ETH_OFFSET_INVALID))
 		return ~0U;
@@ -622,7 +627,6 @@ static struct sh_eth_cpu_data r7s72100_data = {
 	.tpauser	= 1,
 	.hw_swap	= 1,
 	.rpadir		= 1,
-	.rpadir_value   = 2 << 16,
 	.no_trimd	= 1,
 	.no_ade		= 1,
 	.xdfar_rw	= 1,
@@ -672,7 +676,6 @@ static struct sh_eth_cpu_data r8a7740_data = {
 	.bculr		= 1,
 	.hw_swap	= 1,
 	.rpadir		= 1,
-	.rpadir_value   = 2 << 16,
 	.no_trimd	= 1,
 	.no_ade		= 1,
 	.xdfar_rw	= 1,
@@ -798,7 +801,6 @@ static struct sh_eth_cpu_data r8a77980_data = {
 	.hw_swap	= 1,
 	.nbst		= 1,
 	.rpadir		= 1,
-	.rpadir_value   = 2 << 16,
 	.no_trimd	= 1,
 	.no_ade		= 1,
 	.xdfar_rw	= 1,
@@ -851,7 +853,6 @@ static struct sh_eth_cpu_data sh7724_data = {
 	.tpauser	= 1,
 	.hw_swap	= 1,
 	.rpadir		= 1,
-	.rpadir_value	= 0x00020000, /* NET_IP_ALIGN assumed to be 2 */
 };
 
 static void sh_eth_set_rate_sh7757(struct net_device *ndev)
@@ -898,7 +899,6 @@ static struct sh_eth_cpu_data sh7757_data = {
 	.hw_swap	= 1,
 	.no_ade		= 1,
 	.rpadir		= 1,
-	.rpadir_value   = 2 << 16,
 	.rtrate		= 1,
 	.dual_port	= 1,
 };
@@ -978,7 +978,6 @@ static struct sh_eth_cpu_data sh7757_data_giga = {
 	.bculr		= 1,
 	.hw_swap	= 1,
 	.rpadir		= 1,
-	.rpadir_value   = 2 << 16,
 	.no_trimd	= 1,
 	.no_ade		= 1,
 	.xdfar_rw	= 1,
@@ -1467,7 +1466,7 @@ static int sh_eth_dev_init(struct net_device *ndev)
 	/* Descriptor format */
 	sh_eth_ring_format(ndev);
 	if (mdp->cd->rpadir)
-		sh_eth_write(ndev, mdp->cd->rpadir_value, RPADIR);
+		sh_eth_write(ndev, NET_IP_ALIGN << 16, RPADIR);
 
 	/* all sh_eth int mask */
 	sh_eth_write(ndev, 0, EESIPR);
@@ -1527,9 +1526,9 @@ static int sh_eth_dev_init(struct net_device *ndev)
 
 	/* mask reset */
 	if (mdp->cd->apr)
-		sh_eth_write(ndev, APR_AP, APR);
+		sh_eth_write(ndev, 1, APR);
 	if (mdp->cd->mpr)
-		sh_eth_write(ndev, MPR_MP, MPR);
+		sh_eth_write(ndev, 1, MPR);
 	if (mdp->cd->tpauser)
 		sh_eth_write(ndev, TPAUSER_UNLIMITED, TPAUSER);
 
@@ -2677,34 +2676,36 @@ static int sh_eth_tsu_busy(struct net_device *ndev)
 	return 0;
 }
 
-static int sh_eth_tsu_write_entry(struct net_device *ndev, void *reg,
+static int sh_eth_tsu_write_entry(struct net_device *ndev, u16 offset,
 				  const u8 *addr)
 {
+	struct sh_eth_private *mdp = netdev_priv(ndev);
 	u32 val;
 
 	val = addr[0] << 24 | addr[1] << 16 | addr[2] << 8 | addr[3];
-	iowrite32(val, reg);
+	iowrite32(val, mdp->tsu_addr + offset);
 	if (sh_eth_tsu_busy(ndev) < 0)
 		return -EBUSY;
 
 	val = addr[4] << 8 | addr[5];
-	iowrite32(val, reg + 4);
+	iowrite32(val, mdp->tsu_addr + offset + 4);
 	if (sh_eth_tsu_busy(ndev) < 0)
 		return -EBUSY;
 
 	return 0;
 }
 
-static void sh_eth_tsu_read_entry(void *reg, u8 *addr)
+static void sh_eth_tsu_read_entry(struct net_device *ndev, u16 offset, u8 *addr)
 {
+	struct sh_eth_private *mdp = netdev_priv(ndev);
 	u32 val;
 
-	val = ioread32(reg);
+	val = ioread32(mdp->tsu_addr + offset);
 	addr[0] = (val >> 24) & 0xff;
 	addr[1] = (val >> 16) & 0xff;
 	addr[2] = (val >> 8) & 0xff;
 	addr[3] = val & 0xff;
-	val = ioread32(reg + 4);
+	val = ioread32(mdp->tsu_addr + offset + 4);
 	addr[4] = (val >> 8) & 0xff;
 	addr[5] = val & 0xff;
 }
@@ -2713,12 +2714,12 @@ static void sh_eth_tsu_read_entry(void *reg, u8 *addr)
 static int sh_eth_tsu_find_entry(struct net_device *ndev, const u8 *addr)
 {
 	struct sh_eth_private *mdp = netdev_priv(ndev);
-	void *reg_offset = sh_eth_tsu_get_offset(mdp, TSU_ADRH0);
+	u16 reg_offset = sh_eth_tsu_get_offset(mdp, TSU_ADRH0);
 	int i;
 	u8 c_addr[ETH_ALEN];
 
 	for (i = 0; i < SH_ETH_TSU_CAM_ENTRIES; i++, reg_offset += 8) {
-		sh_eth_tsu_read_entry(reg_offset, c_addr);
+		sh_eth_tsu_read_entry(ndev, reg_offset, c_addr);
 		if (ether_addr_equal(addr, c_addr))
 			return i;
 	}
@@ -2740,7 +2741,7 @@ static int sh_eth_tsu_disable_cam_entry_table(struct net_device *ndev,
 					      int entry)
 {
 	struct sh_eth_private *mdp = netdev_priv(ndev);
-	void *reg_offset = sh_eth_tsu_get_offset(mdp, TSU_ADRH0);
+	u16 reg_offset = sh_eth_tsu_get_offset(mdp, TSU_ADRH0);
 	int ret;
 	u8 blank[ETH_ALEN];
 
@@ -2757,7 +2758,7 @@ static int sh_eth_tsu_disable_cam_entry_table(struct net_device *ndev,
 static int sh_eth_tsu_add_entry(struct net_device *ndev, const u8 *addr)
 {
 	struct sh_eth_private *mdp = netdev_priv(ndev);
-	void *reg_offset = sh_eth_tsu_get_offset(mdp, TSU_ADRH0);
+	u16 reg_offset = sh_eth_tsu_get_offset(mdp, TSU_ADRH0);
 	int i, ret;
 
 	if (!mdp->cd->tsu)
@@ -2831,15 +2832,15 @@ static int sh_eth_tsu_purge_all(struct net_device *ndev)
 static void sh_eth_tsu_purge_mcast(struct net_device *ndev)
 {
 	struct sh_eth_private *mdp = netdev_priv(ndev);
+	u16 reg_offset = sh_eth_tsu_get_offset(mdp, TSU_ADRH0);
 	u8 addr[ETH_ALEN];
-	void *reg_offset = sh_eth_tsu_get_offset(mdp, TSU_ADRH0);
 	int i;
 
 	if (!mdp->cd->tsu)
 		return;
 
 	for (i = 0; i < SH_ETH_TSU_CAM_ENTRIES; i++, reg_offset += 8) {
-		sh_eth_tsu_read_entry(reg_offset, addr);
+		sh_eth_tsu_read_entry(ndev, reg_offset, addr);
 		if (is_multicast_ether_addr(addr))
 			sh_eth_tsu_del_entry(ndev, addr);
 	}
diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h
index 726c55a82dd7..f94be99cf400 100644
--- a/drivers/net/ethernet/renesas/sh_eth.h
+++ b/drivers/net/ethernet/renesas/sh_eth.h
@@ -383,12 +383,12 @@ enum ECSIPR_STATUS_MASK_BIT {
 
 /* APR */
 enum APR_BIT {
-	APR_AP = 0x00000001,
+	APR_AP = 0x0000ffff,
 };
 
 /* MPR */
 enum MPR_BIT {
-	MPR_MP = 0x00000001,
+	MPR_MP = 0x0000ffff,
 };
 
 /* TRSCER */
@@ -403,8 +403,7 @@ enum DESC_I_BIT {
 
 /* RPADIR */
 enum RPADIR_BIT {
-	RPADIR_PADS1 = 0x20000, RPADIR_PADS0 = 0x10000,
-	RPADIR_PADR = 0x0003f,
+	RPADIR_PADS = 0x1f0000, RPADIR_PADR = 0xffff,
 };
 
 /* FDR */
@@ -488,7 +487,6 @@ struct sh_eth_cpu_data {
 	u32 ecsipr_value;
 	u32 fdr_value;
 	u32 fcftr_value;
-	u32 rpadir_value;
 
 	/* interrupt checking mask */
 	u32 tx_check;
@@ -560,10 +558,4 @@ struct sh_eth_private {
 	unsigned wol_enabled:1;
 };
 
-static inline void *sh_eth_tsu_get_offset(struct sh_eth_private *mdp,
-					  int enum_index)
-{
-	return mdp->tsu_addr + mdp->reg_offset[enum_index];
-}
-
 #endif	/* #ifndef __SH_ETH_H__ */
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
index 542b67d436df..c9aad0eda57f 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
@@ -319,6 +319,7 @@ static int sxgbe_get_rss_hash_opts(struct sxgbe_priv_data *priv,
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
 		cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		/* Fall through */
 	case SCTP_V4_FLOW:
 	case AH_ESP_V4_FLOW:
 	case AH_V4_FLOW:
@@ -329,6 +330,7 @@ static int sxgbe_get_rss_hash_opts(struct sxgbe_priv_data *priv,
 	case TCP_V6_FLOW:
 	case UDP_V6_FLOW:
 		cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		/* Fall through */
 	case SCTP_V6_FLOW:
 	case AH_ESP_V6_FLOW:
 	case AH_V6_FLOW:
diff --git a/drivers/net/ethernet/sfc/Makefile b/drivers/net/ethernet/sfc/Makefile
index 3bac58d0f88b..c5c297e78d06 100644
--- a/drivers/net/ethernet/sfc/Makefile
+++ b/drivers/net/ethernet/sfc/Makefile
@@ -6,3 +6,5 @@ sfc-$(CONFIG_SFC_MTD)	+= mtd.o
 sfc-$(CONFIG_SFC_SRIOV)	+= sriov.o siena_sriov.o ef10_sriov.o
 
 obj-$(CONFIG_SFC)	+= sfc.o
+
+obj-$(CONFIG_SFC_FALCON) += falcon/
diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c
index 019cef1d3cf7..3d76fd1504c2 100644
--- a/drivers/net/ethernet/sfc/ef10_sriov.c
+++ b/drivers/net/ethernet/sfc/ef10_sriov.c
@@ -199,7 +199,7 @@ static int efx_ef10_sriov_alloc_vf_vswitching(struct efx_nic *efx)
 		return -ENOMEM;
 
 	for (i = 0; i < efx->vf_count; i++) {
-		random_ether_addr(nic_data->vf[i].mac);
+		eth_random_addr(nic_data->vf[i].mac);
 		nic_data->vf[i].efx = NULL;
 		nic_data->vf[i].vlan = EFX_EF10_NO_VLAN;
 
@@ -564,7 +564,7 @@ int efx_ef10_sriov_set_vf_vlan(struct efx_nic *efx, int vf_i, u16 vlan,
 {
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	struct ef10_vf *vf;
-	u16 old_vlan, new_vlan;
+	u16 new_vlan;
 	int rc = 0, rc2 = 0;
 
 	if (vf_i >= efx->vf_count)
@@ -619,7 +619,6 @@ int efx_ef10_sriov_set_vf_vlan(struct efx_nic *efx, int vf_i, u16 vlan,
 	}
 
 	/* Do the actual vlan change */
-	old_vlan = vf->vlan;
 	vf->vlan = new_vlan;
 
 	/* Restore everything in reverse order */
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index ce3a177081a8..330233286e78 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -264,11 +264,17 @@ static int efx_check_disabled(struct efx_nic *efx)
 static int efx_process_channel(struct efx_channel *channel, int budget)
 {
 	struct efx_tx_queue *tx_queue;
+	struct list_head rx_list;
 	int spent;
 
 	if (unlikely(!channel->enabled))
 		return 0;
 
+	/* Prepare the batch receive list */
+	EFX_WARN_ON_PARANOID(channel->rx_list != NULL);
+	INIT_LIST_HEAD(&rx_list);
+	channel->rx_list = &rx_list;
+
 	efx_for_each_channel_tx_queue(tx_queue, channel) {
 		tx_queue->pkts_compl = 0;
 		tx_queue->bytes_compl = 0;
@@ -291,6 +297,10 @@ static int efx_process_channel(struct efx_channel *channel, int budget)
 		}
 	}
 
+	/* Receive any packets we queued up */
+	netif_receive_skb_list(channel->rx_list);
+	channel->rx_list = NULL;
+
 	return spent;
 }
 
@@ -555,6 +565,8 @@ static int efx_probe_channel(struct efx_channel *channel)
 			goto fail;
 	}
 
+	channel->rx_list = NULL;
+
 	return 0;
 
 fail:
diff --git a/drivers/net/ethernet/sfc/falcon/ethtool.c b/drivers/net/ethernet/sfc/falcon/ethtool.c
index 56049157a5af..1ccdb7a82e2a 100644
--- a/drivers/net/ethernet/sfc/falcon/ethtool.c
+++ b/drivers/net/ethernet/sfc/falcon/ethtool.c
@@ -963,6 +963,7 @@ ef4_ethtool_get_rxnfc(struct net_device *net_dev,
 		switch (info->flow_type) {
 		case TCP_V4_FLOW:
 			info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+			/* Fall through */
 		case UDP_V4_FLOW:
 		case SCTP_V4_FLOW:
 		case AH_ESP_V4_FLOW:
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 65568925c3ef..961b92979640 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -448,6 +448,7 @@ enum efx_sync_events_state {
  *	__efx_rx_packet(), or zero if there is none
  * @rx_pkt_index: Ring index of first buffer for next packet to be delivered
  *	by __efx_rx_packet(), if @rx_pkt_n_frags != 0
+ * @rx_list: list of SKBs from current RX, awaiting processing
  * @rx_queue: RX queue for this channel
  * @tx_queue: TX queues for this channel
  * @sync_events_state: Current state of sync events on this channel
@@ -500,6 +501,8 @@ struct efx_channel {
 	unsigned int rx_pkt_n_frags;
 	unsigned int rx_pkt_index;
 
+	struct list_head *rx_list;
+
 	struct efx_rx_queue rx_queue;
 	struct efx_tx_queue tx_queue[EFX_TXQ_TYPES];
 
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index d2e254f2f72b..396ff01298cd 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -634,7 +634,12 @@ static void efx_rx_deliver(struct efx_channel *channel, u8 *eh,
 			return;
 
 	/* Pass the packet up */
-	netif_receive_skb(skb);
+	if (channel->rx_list != NULL)
+		/* Add to list, will pass up later */
+		list_add_tail(&skb->list, channel->rx_list);
+	else
+		/* No list, so pass it up now */
+		netif_receive_skb(skb);
 }
 
 /* Handle a received packet.  Second half: Touches packet payload. */
diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c
index 949aaef390b6..15c62c160953 100644
--- a/drivers/net/ethernet/smsc/epic100.c
+++ b/drivers/net/ethernet/smsc/epic100.c
@@ -321,7 +321,6 @@ static int epic_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	static int card_idx = -1;
 	void __iomem *ioaddr;
 	int chip_idx = (int) ent->driver_data;
-	int irq;
 	struct net_device *dev;
 	struct epic_private *ep;
 	int i, ret, option = 0, duplex = 0;
@@ -338,7 +337,6 @@ static int epic_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	ret = pci_enable_device(pdev);
 	if (ret)
 		goto out;
-	irq = pdev->irq;
 
 	if (pci_resource_len(pdev, 0) < EPIC_TOTAL_SIZE) {
 		dev_err(&pdev->dev, "no PCI region space\n");
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index e080d3e7c582..7aa5ebb6766c 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -232,8 +232,7 @@
 #define NETSEC_EEPROM_PKT_ME_ADDRESS		0x20
 #define NETSEC_EEPROM_PKT_ME_SIZE		0x24
 
-#define DESC_NUM	128
-#define NAPI_BUDGET	(DESC_NUM / 2)
+#define DESC_NUM	256
 
 #define DESC_SZ	sizeof(struct netsec_de)
 
@@ -642,8 +641,6 @@ static struct sk_buff *netsec_get_rx_pkt_data(struct netsec_priv *priv,
 
 	tmp_skb = netsec_alloc_skb(priv, &td);
 
-	dma_rmb();
-
 	tail = dring->tail;
 
 	if (!tmp_skb) {
@@ -657,8 +654,6 @@ static struct sk_buff *netsec_get_rx_pkt_data(struct netsec_priv *priv,
 	/* move tail ahead */
 	dring->tail = (dring->tail + 1) % DESC_NUM;
 
-	dring->pkt_cnt--;
-
 	return skb;
 }
 
@@ -731,25 +726,24 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
 	struct net_device *ndev = priv->ndev;
 	struct netsec_rx_pkt_info rx_info;
-	int done = 0, rx_num = 0;
+	int done = 0;
 	struct netsec_desc desc;
 	struct sk_buff *skb;
 	u16 len;
 
 	while (done < budget) {
-		if (!rx_num) {
-			rx_num = netsec_read(priv, NETSEC_REG_NRM_RX_PKTCNT);
-			dring->pkt_cnt += rx_num;
+		u16 idx = dring->tail;
+		struct netsec_de *de = dring->vaddr + (DESC_SZ * idx);
 
-			/* move head 'rx_num' */
-			dring->head = (dring->head + rx_num) % DESC_NUM;
+		if (de->attr & (1U << NETSEC_RX_PKT_OWN_FIELD))
+			break;
 
-			rx_num = dring->pkt_cnt;
-			if (!rx_num)
-				break;
-		}
+		/* This  barrier is needed to keep us from reading
+		 * any other fields out of the netsec_de until we have
+		 * verified the descriptor has been written back
+		 */
+		dma_rmb();
 		done++;
-		rx_num--;
 		skb = netsec_get_rx_pkt_data(priv, &rx_info, &desc, &len);
 		if (unlikely(!skb) || rx_info.err_flag) {
 			netif_err(priv, drv, priv->ndev,
@@ -780,11 +774,9 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 static int netsec_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct netsec_priv *priv;
-	struct net_device *ndev;
 	int tx, rx, done, todo;
 
 	priv = container_of(napi, struct netsec_priv, napi);
-	ndev = priv->ndev;
 
 	todo = budget;
 	do {
@@ -1666,7 +1658,7 @@ static int netsec_probe(struct platform_device *pdev)
 	dev_info(&pdev->dev, "hardware revision %d.%d\n",
 		 hw_ver >> 16, hw_ver & 0xffff);
 
-	netif_napi_add(ndev, &priv->napi, netsec_napi_poll, NAPI_BUDGET);
+	netif_napi_add(ndev, &priv->napi, netsec_napi_poll, NAPI_POLL_WEIGHT);
 
 	ndev->netdev_ops = &netsec_netdev_ops;
 	ndev->ethtool_ops = &netsec_ethtool_ops;
diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index 68e9e2640c62..99967a80a8c8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -5,7 +5,8 @@ stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o	\
 	      dwmac100_core.o dwmac100_dma.o enh_desc.o norm_desc.o	\
 	      mmc_core.o stmmac_hwtstamp.o stmmac_ptp.o dwmac4_descs.o	\
 	      dwmac4_dma.o dwmac4_lib.o dwmac4_core.o dwmac5.o hwif.o \
-	      stmmac_tc.o $(stmmac-y)
+	      stmmac_tc.o dwxgmac2_core.o dwxgmac2_dma.o dwxgmac2_descs.o \
+	      $(stmmac-y)
 
 # Ordering matters. Generic driver must be last.
 obj-$(CONFIG_STMMAC_PLATFORM)	+= stmmac-platform.o
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 78fd0f8b8e81..1854f270ad66 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -36,12 +36,14 @@
 #include "mmc.h"
 
 /* Synopsys Core versions */
-#define	DWMAC_CORE_3_40	0x34
-#define	DWMAC_CORE_3_50	0x35
-#define	DWMAC_CORE_4_00	0x40
-#define DWMAC_CORE_4_10	0x41
-#define DWMAC_CORE_5_00 0x50
-#define DWMAC_CORE_5_10 0x51
+#define	DWMAC_CORE_3_40		0x34
+#define	DWMAC_CORE_3_50		0x35
+#define	DWMAC_CORE_4_00		0x40
+#define DWMAC_CORE_4_10		0x41
+#define DWMAC_CORE_5_00		0x50
+#define DWMAC_CORE_5_10		0x51
+#define DWXGMAC_CORE_2_10	0x21
+
 #define STMMAC_CHAN0	0	/* Always supported and default for all chips */
 
 /* These need to be power of two, and >= 4 */
@@ -398,6 +400,8 @@ struct mac_link {
 	u32 speed10;
 	u32 speed100;
 	u32 speed1000;
+	u32 speed2500;
+	u32 speed10000;
 	u32 duplex;
 };
 
@@ -439,6 +443,7 @@ struct stmmac_rx_routing {
 int dwmac100_setup(struct stmmac_priv *priv);
 int dwmac1000_setup(struct stmmac_priv *priv);
 int dwmac4_setup(struct stmmac_priv *priv);
+int dwxgmac2_setup(struct stmmac_priv *priv);
 
 void stmmac_set_mac_addr(void __iomem *ioaddr, u8 addr[6],
 			 unsigned int high, unsigned int low);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c
index 3304095c934c..fad503820e04 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c
@@ -78,6 +78,8 @@ static const struct of_device_id dwmac_generic_match[] = {
 	{ .compatible = "snps,dwmac-4.00"},
 	{ .compatible = "snps,dwmac-4.10a"},
 	{ .compatible = "snps,dwmac"},
+	{ .compatible = "snps,dwxgmac-2.10"},
+	{ .compatible = "snps,dwxgmac"},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, dwmac_generic_match);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index f08625a02cea..7b923362ee55 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -61,6 +61,7 @@ struct rk_priv_data {
 	struct clk *mac_clk_tx;
 	struct clk *clk_mac_ref;
 	struct clk *clk_mac_refout;
+	struct clk *clk_mac_speed;
 	struct clk *aclk_mac;
 	struct clk *pclk_mac;
 	struct clk *clk_phy;
@@ -83,6 +84,64 @@ struct rk_priv_data {
 	(((tx) ? soc##_GMAC_TXCLK_DLY_ENABLE : soc##_GMAC_TXCLK_DLY_DISABLE) | \
 	 ((rx) ? soc##_GMAC_RXCLK_DLY_ENABLE : soc##_GMAC_RXCLK_DLY_DISABLE))
 
+#define PX30_GRF_GMAC_CON1		0x0904
+
+/* PX30_GRF_GMAC_CON1 */
+#define PX30_GMAC_PHY_INTF_SEL_RMII	(GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | \
+					 GRF_BIT(6))
+#define PX30_GMAC_SPEED_10M		GRF_CLR_BIT(2)
+#define PX30_GMAC_SPEED_100M		GRF_BIT(2)
+
+static void px30_set_to_rmii(struct rk_priv_data *bsp_priv)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
+		return;
+	}
+
+	regmap_write(bsp_priv->grf, PX30_GRF_GMAC_CON1,
+		     PX30_GMAC_PHY_INTF_SEL_RMII);
+}
+
+static void px30_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+	int ret;
+
+	if (IS_ERR(bsp_priv->clk_mac_speed)) {
+		dev_err(dev, "%s: Missing clk_mac_speed clock\n", __func__);
+		return;
+	}
+
+	if (speed == 10) {
+		regmap_write(bsp_priv->grf, PX30_GRF_GMAC_CON1,
+			     PX30_GMAC_SPEED_10M);
+
+		ret = clk_set_rate(bsp_priv->clk_mac_speed, 2500000);
+		if (ret)
+			dev_err(dev, "%s: set clk_mac_speed rate 2500000 failed: %d\n",
+				__func__, ret);
+	} else if (speed == 100) {
+		regmap_write(bsp_priv->grf, PX30_GRF_GMAC_CON1,
+			     PX30_GMAC_SPEED_100M);
+
+		ret = clk_set_rate(bsp_priv->clk_mac_speed, 25000000);
+		if (ret)
+			dev_err(dev, "%s: set clk_mac_speed rate 25000000 failed: %d\n",
+				__func__, ret);
+
+	} else {
+		dev_err(dev, "unknown speed value for RMII! speed=%d", speed);
+	}
+}
+
+static const struct rk_gmac_ops px30_ops = {
+	.set_to_rmii = px30_set_to_rmii,
+	.set_rmii_speed = px30_set_rmii_speed,
+};
+
 #define RK3128_GRF_MAC_CON0	0x0168
 #define RK3128_GRF_MAC_CON1	0x016c
 
@@ -1042,6 +1101,10 @@ static int rk_gmac_clk_init(struct plat_stmmacenet_data *plat)
 		}
 	}
 
+	bsp_priv->clk_mac_speed = devm_clk_get(dev, "clk_mac_speed");
+	if (IS_ERR(bsp_priv->clk_mac_speed))
+		dev_err(dev, "cannot get clock %s\n", "clk_mac_speed");
+
 	if (bsp_priv->clock_input) {
 		dev_info(dev, "clock input from PHY\n");
 	} else {
@@ -1094,6 +1157,9 @@ static int gmac_clk_enable(struct rk_priv_data *bsp_priv, bool enable)
 			if (!IS_ERR(bsp_priv->mac_clk_tx))
 				clk_prepare_enable(bsp_priv->mac_clk_tx);
 
+			if (!IS_ERR(bsp_priv->clk_mac_speed))
+				clk_prepare_enable(bsp_priv->clk_mac_speed);
+
 			/**
 			 * if (!IS_ERR(bsp_priv->clk_mac))
 			 *	clk_prepare_enable(bsp_priv->clk_mac);
@@ -1118,6 +1184,8 @@ static int gmac_clk_enable(struct rk_priv_data *bsp_priv, bool enable)
 			clk_disable_unprepare(bsp_priv->pclk_mac);
 
 			clk_disable_unprepare(bsp_priv->mac_clk_tx);
+
+			clk_disable_unprepare(bsp_priv->clk_mac_speed);
 			/**
 			 * if (!IS_ERR(bsp_priv->clk_mac))
 			 *	clk_disable_unprepare(bsp_priv->clk_mac);
@@ -1414,6 +1482,7 @@ static int rk_gmac_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(rk_gmac_pm_ops, rk_gmac_suspend, rk_gmac_resume);
 
 static const struct of_device_id rk_gmac_dwmac_match[] = {
+	{ .compatible = "rockchip,px30-gmac",	.data = &px30_ops   },
 	{ .compatible = "rockchip,rk3128-gmac", .data = &rk3128_ops },
 	{ .compatible = "rockchip,rk3228-gmac", .data = &rk3228_ops },
 	{ .compatible = "rockchip,rk3288-gmac", .data = &rk3288_ops },
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index 65bc3556bd8f..edb6053bd980 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -407,6 +407,19 @@ static void dwmac4_enable_tso(void __iomem *ioaddr, bool en, u32 chan)
 	}
 }
 
+static void dwmac4_qmode(void __iomem *ioaddr, u32 channel, u8 qmode)
+{
+	u32 mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel));
+
+	mtl_tx_op &= ~MTL_OP_MODE_TXQEN_MASK;
+	if (qmode != MTL_QUEUE_AVB)
+		mtl_tx_op |= MTL_OP_MODE_TXQEN;
+	else
+		mtl_tx_op |= MTL_OP_MODE_TXQEN_AV;
+
+	writel(mtl_tx_op, ioaddr +  MTL_CHAN_TX_OP_MODE(channel));
+}
+
 static void dwmac4_set_bfsize(void __iomem *ioaddr, int bfsize, u32 chan)
 {
 	u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan));
@@ -441,6 +454,7 @@ const struct stmmac_dma_ops dwmac4_dma_ops = {
 	.set_rx_tail_ptr = dwmac4_set_rx_tail_ptr,
 	.set_tx_tail_ptr = dwmac4_set_tx_tail_ptr,
 	.enable_tso = dwmac4_enable_tso,
+	.qmode = dwmac4_qmode,
 	.set_bfsize = dwmac4_set_bfsize,
 };
 
@@ -468,5 +482,6 @@ const struct stmmac_dma_ops dwmac410_dma_ops = {
 	.set_rx_tail_ptr = dwmac4_set_rx_tail_ptr,
 	.set_tx_tail_ptr = dwmac4_set_tx_tail_ptr,
 	.enable_tso = dwmac4_enable_tso,
+	.qmode = dwmac4_qmode,
 	.set_bfsize = dwmac4_set_bfsize,
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
new file mode 100644
index 000000000000..0a80fa25afe3
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -0,0 +1,228 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2018 Synopsys, Inc. and/or its affiliates.
+ * stmmac XGMAC definitions.
+ */
+
+#ifndef __STMMAC_DWXGMAC2_H__
+#define __STMMAC_DWXGMAC2_H__
+
+#include "common.h"
+
+/* Misc */
+#define XGMAC_JUMBO_LEN			16368
+
+/* MAC Registers */
+#define XGMAC_TX_CONFIG			0x00000000
+#define XGMAC_CONFIG_SS_OFF		29
+#define XGMAC_CONFIG_SS_MASK		GENMASK(30, 29)
+#define XGMAC_CONFIG_SS_10000		(0x0 << XGMAC_CONFIG_SS_OFF)
+#define XGMAC_CONFIG_SS_2500		(0x2 << XGMAC_CONFIG_SS_OFF)
+#define XGMAC_CONFIG_SS_1000		(0x3 << XGMAC_CONFIG_SS_OFF)
+#define XGMAC_CONFIG_SARC		GENMASK(22, 20)
+#define XGMAC_CONFIG_SARC_SHIFT		20
+#define XGMAC_CONFIG_JD			BIT(16)
+#define XGMAC_CONFIG_TE			BIT(0)
+#define XGMAC_CORE_INIT_TX		(XGMAC_CONFIG_JD)
+#define XGMAC_RX_CONFIG			0x00000004
+#define XGMAC_CONFIG_ARPEN		BIT(31)
+#define XGMAC_CONFIG_GPSL		GENMASK(29, 16)
+#define XGMAC_CONFIG_GPSL_SHIFT		16
+#define XGMAC_CONFIG_S2KP		BIT(11)
+#define XGMAC_CONFIG_IPC		BIT(9)
+#define XGMAC_CONFIG_JE			BIT(8)
+#define XGMAC_CONFIG_WD			BIT(7)
+#define XGMAC_CONFIG_GPSLCE		BIT(6)
+#define XGMAC_CONFIG_CST		BIT(2)
+#define XGMAC_CONFIG_ACS		BIT(1)
+#define XGMAC_CONFIG_RE			BIT(0)
+#define XGMAC_CORE_INIT_RX		0
+#define XGMAC_PACKET_FILTER		0x00000008
+#define XGMAC_FILTER_RA			BIT(31)
+#define XGMAC_FILTER_PM			BIT(4)
+#define XGMAC_FILTER_HMC		BIT(2)
+#define XGMAC_FILTER_PR			BIT(0)
+#define XGMAC_HASH_TABLE(x)		(0x00000010 + (x) * 4)
+#define XGMAC_RXQ_CTRL0			0x000000a0
+#define XGMAC_RXQEN(x)			GENMASK((x) * 2 + 1, (x) * 2)
+#define XGMAC_RXQEN_SHIFT(x)		((x) * 2)
+#define XGMAC_RXQ_CTRL2			0x000000a8
+#define XGMAC_RXQ_CTRL3			0x000000ac
+#define XGMAC_PSRQ(x)			GENMASK((x) * 8 + 7, (x) * 8)
+#define XGMAC_PSRQ_SHIFT(x)		((x) * 8)
+#define XGMAC_INT_STATUS		0x000000b0
+#define XGMAC_PMTIS			BIT(4)
+#define XGMAC_INT_EN			0x000000b4
+#define XGMAC_TSIE			BIT(12)
+#define XGMAC_LPIIE			BIT(5)
+#define XGMAC_PMTIE			BIT(4)
+#define XGMAC_INT_DEFAULT_EN		(XGMAC_LPIIE | XGMAC_PMTIE | XGMAC_TSIE)
+#define XGMAC_Qx_TX_FLOW_CTRL(x)	(0x00000070 + (x) * 4)
+#define XGMAC_PT			GENMASK(31, 16)
+#define XGMAC_PT_SHIFT			16
+#define XGMAC_TFE			BIT(1)
+#define XGMAC_RX_FLOW_CTRL		0x00000090
+#define XGMAC_RFE			BIT(0)
+#define XGMAC_PMT			0x000000c0
+#define XGMAC_GLBLUCAST			BIT(9)
+#define XGMAC_RWKPKTEN			BIT(2)
+#define XGMAC_MGKPKTEN			BIT(1)
+#define XGMAC_PWRDWN			BIT(0)
+#define XGMAC_HW_FEATURE0		0x0000011c
+#define XGMAC_HWFEAT_SAVLANINS		BIT(27)
+#define XGMAC_HWFEAT_RXCOESEL		BIT(16)
+#define XGMAC_HWFEAT_TXCOESEL		BIT(14)
+#define XGMAC_HWFEAT_TSSEL		BIT(12)
+#define XGMAC_HWFEAT_AVSEL		BIT(11)
+#define XGMAC_HWFEAT_RAVSEL		BIT(10)
+#define XGMAC_HWFEAT_ARPOFFSEL		BIT(9)
+#define XGMAC_HWFEAT_MGKSEL		BIT(7)
+#define XGMAC_HWFEAT_RWKSEL		BIT(6)
+#define XGMAC_HWFEAT_GMIISEL		BIT(1)
+#define XGMAC_HW_FEATURE1		0x00000120
+#define XGMAC_HWFEAT_TSOEN		BIT(18)
+#define XGMAC_HWFEAT_TXFIFOSIZE		GENMASK(10, 6)
+#define XGMAC_HWFEAT_RXFIFOSIZE		GENMASK(4, 0)
+#define XGMAC_HW_FEATURE2		0x00000124
+#define XGMAC_HWFEAT_PPSOUTNUM		GENMASK(26, 24)
+#define XGMAC_HWFEAT_TXCHCNT		GENMASK(21, 18)
+#define XGMAC_HWFEAT_RXCHCNT		GENMASK(15, 12)
+#define XGMAC_HWFEAT_TXQCNT		GENMASK(9, 6)
+#define XGMAC_HWFEAT_RXQCNT		GENMASK(3, 0)
+#define XGMAC_MDIO_ADDR			0x00000200
+#define XGMAC_MDIO_DATA			0x00000204
+#define XGMAC_MDIO_C22P			0x00000220
+#define XGMAC_ADDR0_HIGH		0x00000300
+#define XGMAC_AE			BIT(31)
+#define XGMAC_DCS			GENMASK(19, 16)
+#define XGMAC_DCS_SHIFT			16
+#define XGMAC_ADDR0_LOW			0x00000304
+#define XGMAC_ARP_ADDR			0x00000c10
+#define XGMAC_TIMESTAMP_STATUS		0x00000d20
+#define XGMAC_TXTSC			BIT(15)
+#define XGMAC_TXTIMESTAMP_NSEC		0x00000d30
+#define XGMAC_TXTSSTSLO			GENMASK(30, 0)
+#define XGMAC_TXTIMESTAMP_SEC		0x00000d34
+
+/* MTL Registers */
+#define XGMAC_MTL_OPMODE		0x00001000
+#define XGMAC_ETSALG			GENMASK(6, 5)
+#define XGMAC_WRR			(0x0 << 5)
+#define XGMAC_WFQ			(0x1 << 5)
+#define XGMAC_DWRR			(0x2 << 5)
+#define XGMAC_RAA			BIT(2)
+#define XGMAC_MTL_INT_STATUS		0x00001020
+#define XGMAC_MTL_RXQ_DMA_MAP0		0x00001030
+#define XGMAC_MTL_RXQ_DMA_MAP1		0x00001034
+#define XGMAC_QxMDMACH(x)		GENMASK((x) * 8 + 3, (x) * 8)
+#define XGMAC_QxMDMACH_SHIFT(x)		((x) * 8)
+#define XGMAC_MTL_TXQ_OPMODE(x)		(0x00001100 + (0x80 * (x)))
+#define XGMAC_TQS			GENMASK(25, 16)
+#define XGMAC_TQS_SHIFT			16
+#define XGMAC_TTC			GENMASK(6, 4)
+#define XGMAC_TTC_SHIFT			4
+#define XGMAC_TXQEN			GENMASK(3, 2)
+#define XGMAC_TXQEN_SHIFT		2
+#define XGMAC_TSF			BIT(1)
+#define XGMAC_MTL_RXQ_OPMODE(x)		(0x00001140 + (0x80 * (x)))
+#define XGMAC_RQS			GENMASK(25, 16)
+#define XGMAC_RQS_SHIFT			16
+#define XGMAC_EHFC			BIT(7)
+#define XGMAC_RSF			BIT(5)
+#define XGMAC_RTC			GENMASK(1, 0)
+#define XGMAC_RTC_SHIFT			0
+#define XGMAC_MTL_QINTEN(x)		(0x00001170 + (0x80 * (x)))
+#define XGMAC_RXOIE			BIT(16)
+#define XGMAC_MTL_QINT_STATUS(x)	(0x00001174 + (0x80 * (x)))
+#define XGMAC_RXOVFIS			BIT(16)
+#define XGMAC_ABPSIS			BIT(1)
+#define XGMAC_TXUNFIS			BIT(0)
+
+/* DMA Registers */
+#define XGMAC_DMA_MODE			0x00003000
+#define XGMAC_SWR			BIT(0)
+#define XGMAC_DMA_SYSBUS_MODE		0x00003004
+#define XGMAC_WR_OSR_LMT		GENMASK(29, 24)
+#define XGMAC_WR_OSR_LMT_SHIFT		24
+#define XGMAC_RD_OSR_LMT		GENMASK(21, 16)
+#define XGMAC_RD_OSR_LMT_SHIFT		16
+#define XGMAC_EN_LPI			BIT(15)
+#define XGMAC_LPI_XIT_PKT		BIT(14)
+#define XGMAC_AAL			BIT(12)
+#define XGMAC_BLEN			GENMASK(7, 1)
+#define XGMAC_BLEN256			BIT(7)
+#define XGMAC_BLEN128			BIT(6)
+#define XGMAC_BLEN64			BIT(5)
+#define XGMAC_BLEN32			BIT(4)
+#define XGMAC_BLEN16			BIT(3)
+#define XGMAC_BLEN8			BIT(2)
+#define XGMAC_BLEN4			BIT(1)
+#define XGMAC_UNDEF			BIT(0)
+#define XGMAC_DMA_CH_CONTROL(x)		(0x00003100 + (0x80 * (x)))
+#define XGMAC_PBLx8			BIT(16)
+#define XGMAC_DMA_CH_TX_CONTROL(x)	(0x00003104 + (0x80 * (x)))
+#define XGMAC_TxPBL			GENMASK(21, 16)
+#define XGMAC_TxPBL_SHIFT		16
+#define XGMAC_TSE			BIT(12)
+#define XGMAC_OSP			BIT(4)
+#define XGMAC_TXST			BIT(0)
+#define XGMAC_DMA_CH_RX_CONTROL(x)	(0x00003108 + (0x80 * (x)))
+#define XGMAC_RxPBL			GENMASK(21, 16)
+#define XGMAC_RxPBL_SHIFT		16
+#define XGMAC_RXST			BIT(0)
+#define XGMAC_DMA_CH_TxDESC_LADDR(x)	(0x00003114 + (0x80 * (x)))
+#define XGMAC_DMA_CH_RxDESC_LADDR(x)	(0x0000311c + (0x80 * (x)))
+#define XGMAC_DMA_CH_TxDESC_TAIL_LPTR(x)	(0x00003124 + (0x80 * (x)))
+#define XGMAC_DMA_CH_RxDESC_TAIL_LPTR(x)	(0x0000312c + (0x80 * (x)))
+#define XGMAC_DMA_CH_TxDESC_RING_LEN(x)		(0x00003130 + (0x80 * (x)))
+#define XGMAC_DMA_CH_RxDESC_RING_LEN(x)		(0x00003134 + (0x80 * (x)))
+#define XGMAC_DMA_CH_INT_EN(x)		(0x00003138 + (0x80 * (x)))
+#define XGMAC_NIE			BIT(15)
+#define XGMAC_AIE			BIT(14)
+#define XGMAC_RBUE			BIT(7)
+#define XGMAC_RIE			BIT(6)
+#define XGMAC_TIE			BIT(0)
+#define XGMAC_DMA_INT_DEFAULT_EN	(XGMAC_NIE | XGMAC_AIE | XGMAC_RBUE | \
+					XGMAC_RIE | XGMAC_TIE)
+#define XGMAC_DMA_CH_Rx_WATCHDOG(x)	(0x0000313c + (0x80 * (x)))
+#define XGMAC_RWT			GENMASK(7, 0)
+#define XGMAC_DMA_CH_STATUS(x)		(0x00003160 + (0x80 * (x)))
+#define XGMAC_NIS			BIT(15)
+#define XGMAC_AIS			BIT(14)
+#define XGMAC_FBE			BIT(12)
+#define XGMAC_RBU			BIT(7)
+#define XGMAC_RI			BIT(6)
+#define XGMAC_TPS			BIT(1)
+#define XGMAC_TI			BIT(0)
+
+/* Descriptors */
+#define XGMAC_TDES2_IOC			BIT(31)
+#define XGMAC_TDES2_TTSE		BIT(30)
+#define XGMAC_TDES2_B2L			GENMASK(29, 16)
+#define XGMAC_TDES2_B2L_SHIFT		16
+#define XGMAC_TDES2_B1L			GENMASK(13, 0)
+#define XGMAC_TDES3_OWN			BIT(31)
+#define XGMAC_TDES3_CTXT		BIT(30)
+#define XGMAC_TDES3_FD			BIT(29)
+#define XGMAC_TDES3_LD			BIT(28)
+#define XGMAC_TDES3_CPC			GENMASK(27, 26)
+#define XGMAC_TDES3_CPC_SHIFT		26
+#define XGMAC_TDES3_TCMSSV		BIT(26)
+#define XGMAC_TDES3_THL			GENMASK(22, 19)
+#define XGMAC_TDES3_THL_SHIFT		19
+#define XGMAC_TDES3_TSE			BIT(18)
+#define XGMAC_TDES3_CIC			GENMASK(17, 16)
+#define XGMAC_TDES3_CIC_SHIFT		16
+#define XGMAC_TDES3_TPL			GENMASK(17, 0)
+#define XGMAC_TDES3_FL			GENMASK(14, 0)
+#define XGMAC_RDES3_OWN			BIT(31)
+#define XGMAC_RDES3_CTXT		BIT(30)
+#define XGMAC_RDES3_IOC			BIT(30)
+#define XGMAC_RDES3_LD			BIT(28)
+#define XGMAC_RDES3_CDA			BIT(27)
+#define XGMAC_RDES3_ES			BIT(15)
+#define XGMAC_RDES3_PL			GENMASK(13, 0)
+#define XGMAC_RDES3_TSD			BIT(6)
+#define XGMAC_RDES3_TSA			BIT(4)
+
+#endif /* __STMMAC_DWXGMAC2_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
new file mode 100644
index 000000000000..d182f82f7b58
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -0,0 +1,371 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2018 Synopsys, Inc. and/or its affiliates.
+ * stmmac XGMAC support.
+ */
+
+#include "stmmac.h"
+#include "dwxgmac2.h"
+
+static void dwxgmac2_core_init(struct mac_device_info *hw,
+			       struct net_device *dev)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	int mtu = dev->mtu;
+	u32 tx, rx;
+
+	tx = readl(ioaddr + XGMAC_TX_CONFIG);
+	rx = readl(ioaddr + XGMAC_RX_CONFIG);
+
+	tx |= XGMAC_CORE_INIT_TX;
+	rx |= XGMAC_CORE_INIT_RX;
+
+	if (mtu >= 9000) {
+		rx |= XGMAC_CONFIG_GPSLCE;
+		rx |= XGMAC_JUMBO_LEN << XGMAC_CONFIG_GPSL_SHIFT;
+		rx |= XGMAC_CONFIG_WD;
+	} else if (mtu > 2000) {
+		rx |= XGMAC_CONFIG_JE;
+	} else if (mtu > 1500) {
+		rx |= XGMAC_CONFIG_S2KP;
+	}
+
+	if (hw->ps) {
+		tx |= XGMAC_CONFIG_TE;
+		tx &= ~hw->link.speed_mask;
+
+		switch (hw->ps) {
+		case SPEED_10000:
+			tx |= hw->link.speed10000;
+			break;
+		case SPEED_2500:
+			tx |= hw->link.speed2500;
+			break;
+		case SPEED_1000:
+		default:
+			tx |= hw->link.speed1000;
+			break;
+		}
+	}
+
+	writel(tx, ioaddr + XGMAC_TX_CONFIG);
+	writel(rx, ioaddr + XGMAC_RX_CONFIG);
+	writel(XGMAC_INT_DEFAULT_EN, ioaddr + XGMAC_INT_EN);
+}
+
+static void dwxgmac2_set_mac(void __iomem *ioaddr, bool enable)
+{
+	u32 tx = readl(ioaddr + XGMAC_TX_CONFIG);
+	u32 rx = readl(ioaddr + XGMAC_RX_CONFIG);
+
+	if (enable) {
+		tx |= XGMAC_CONFIG_TE;
+		rx |= XGMAC_CONFIG_RE;
+	} else {
+		tx &= ~XGMAC_CONFIG_TE;
+		rx &= ~XGMAC_CONFIG_RE;
+	}
+
+	writel(tx, ioaddr + XGMAC_TX_CONFIG);
+	writel(rx, ioaddr + XGMAC_RX_CONFIG);
+}
+
+static int dwxgmac2_rx_ipc(struct mac_device_info *hw)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_RX_CONFIG);
+	if (hw->rx_csum)
+		value |= XGMAC_CONFIG_IPC;
+	else
+		value &= ~XGMAC_CONFIG_IPC;
+	writel(value, ioaddr + XGMAC_RX_CONFIG);
+
+	return !!(readl(ioaddr + XGMAC_RX_CONFIG) & XGMAC_CONFIG_IPC);
+}
+
+static void dwxgmac2_rx_queue_enable(struct mac_device_info *hw, u8 mode,
+				     u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_RXQ_CTRL0) & ~XGMAC_RXQEN(queue);
+	if (mode == MTL_QUEUE_AVB)
+		value |= 0x1 << XGMAC_RXQEN_SHIFT(queue);
+	else if (mode == MTL_QUEUE_DCB)
+		value |= 0x2 << XGMAC_RXQEN_SHIFT(queue);
+	writel(value, ioaddr + XGMAC_RXQ_CTRL0);
+}
+
+static void dwxgmac2_rx_queue_prio(struct mac_device_info *hw, u32 prio,
+				   u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value, reg;
+
+	reg = (queue < 4) ? XGMAC_RXQ_CTRL2 : XGMAC_RXQ_CTRL3;
+
+	value = readl(ioaddr + reg);
+	value &= ~XGMAC_PSRQ(queue);
+	value |= (prio << XGMAC_PSRQ_SHIFT(queue)) & XGMAC_PSRQ(queue);
+
+	writel(value, ioaddr + reg);
+}
+
+static void dwxgmac2_prog_mtl_rx_algorithms(struct mac_device_info *hw,
+					    u32 rx_alg)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_MTL_OPMODE);
+	value &= ~XGMAC_RAA;
+
+	switch (rx_alg) {
+	case MTL_RX_ALGORITHM_SP:
+		break;
+	case MTL_RX_ALGORITHM_WSP:
+		value |= XGMAC_RAA;
+		break;
+	default:
+		break;
+	}
+
+	writel(value, ioaddr + XGMAC_MTL_OPMODE);
+}
+
+static void dwxgmac2_prog_mtl_tx_algorithms(struct mac_device_info *hw,
+					    u32 tx_alg)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_MTL_OPMODE);
+	value &= ~XGMAC_ETSALG;
+
+	switch (tx_alg) {
+	case MTL_TX_ALGORITHM_WRR:
+		value |= XGMAC_WRR;
+		break;
+	case MTL_TX_ALGORITHM_WFQ:
+		value |= XGMAC_WFQ;
+		break;
+	case MTL_TX_ALGORITHM_DWRR:
+		value |= XGMAC_DWRR;
+		break;
+	default:
+		break;
+	}
+
+	writel(value, ioaddr + XGMAC_MTL_OPMODE);
+}
+
+static void dwxgmac2_map_mtl_to_dma(struct mac_device_info *hw, u32 queue,
+				    u32 chan)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value, reg;
+
+	reg = (queue < 4) ? XGMAC_MTL_RXQ_DMA_MAP0 : XGMAC_MTL_RXQ_DMA_MAP1;
+
+	value = readl(ioaddr + reg);
+	value &= ~XGMAC_QxMDMACH(queue);
+	value |= (chan << XGMAC_QxMDMACH_SHIFT(queue)) & XGMAC_QxMDMACH(queue);
+
+	writel(value, ioaddr + reg);
+}
+
+static int dwxgmac2_host_irq_status(struct mac_device_info *hw,
+				    struct stmmac_extra_stats *x)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 stat, en;
+
+	en = readl(ioaddr + XGMAC_INT_EN);
+	stat = readl(ioaddr + XGMAC_INT_STATUS);
+
+	stat &= en;
+
+	if (stat & XGMAC_PMTIS) {
+		x->irq_receive_pmt_irq_n++;
+		readl(ioaddr + XGMAC_PMT);
+	}
+
+	return 0;
+}
+
+static int dwxgmac2_host_mtl_irq_status(struct mac_device_info *hw, u32 chan)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	int ret = 0;
+	u32 status;
+
+	status = readl(ioaddr + XGMAC_MTL_INT_STATUS);
+	if (status & BIT(chan)) {
+		u32 chan_status = readl(ioaddr + XGMAC_MTL_QINT_STATUS(chan));
+
+		if (chan_status & XGMAC_RXOVFIS)
+			ret |= CORE_IRQ_MTL_RX_OVERFLOW;
+
+		writel(~0x0, ioaddr + XGMAC_MTL_QINT_STATUS(chan));
+	}
+
+	return ret;
+}
+
+static void dwxgmac2_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
+			       unsigned int fc, unsigned int pause_time,
+			       u32 tx_cnt)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 i;
+
+	if (fc & FLOW_RX)
+		writel(XGMAC_RFE, ioaddr + XGMAC_RX_FLOW_CTRL);
+	if (fc & FLOW_TX) {
+		for (i = 0; i < tx_cnt; i++) {
+			u32 value = XGMAC_TFE;
+
+			if (duplex)
+				value |= pause_time << XGMAC_PT_SHIFT;
+
+			writel(value, ioaddr + XGMAC_Qx_TX_FLOW_CTRL(i));
+		}
+	}
+}
+
+static void dwxgmac2_pmt(struct mac_device_info *hw, unsigned long mode)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 val = 0x0;
+
+	if (mode & WAKE_MAGIC)
+		val |= XGMAC_PWRDWN | XGMAC_MGKPKTEN;
+	if (mode & WAKE_UCAST)
+		val |= XGMAC_PWRDWN | XGMAC_GLBLUCAST | XGMAC_RWKPKTEN;
+	if (val) {
+		u32 cfg = readl(ioaddr + XGMAC_RX_CONFIG);
+		cfg |= XGMAC_CONFIG_RE;
+		writel(cfg, ioaddr + XGMAC_RX_CONFIG);
+	}
+
+	writel(val, ioaddr + XGMAC_PMT);
+}
+
+static void dwxgmac2_set_umac_addr(struct mac_device_info *hw,
+				   unsigned char *addr, unsigned int reg_n)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	value = (addr[5] << 8) | addr[4];
+	writel(value | XGMAC_AE, ioaddr + XGMAC_ADDR0_HIGH);
+
+	value = (addr[3] << 24) | (addr[2] << 16) | (addr[1] << 8) | addr[0];
+	writel(value, ioaddr + XGMAC_ADDR0_LOW);
+}
+
+static void dwxgmac2_get_umac_addr(struct mac_device_info *hw,
+				   unsigned char *addr, unsigned int reg_n)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 hi_addr, lo_addr;
+
+	/* Read the MAC address from the hardware */
+	hi_addr = readl(ioaddr + XGMAC_ADDR0_HIGH);
+	lo_addr = readl(ioaddr + XGMAC_ADDR0_LOW);
+
+	/* Extract the MAC address from the high and low words */
+	addr[0] = lo_addr & 0xff;
+	addr[1] = (lo_addr >> 8) & 0xff;
+	addr[2] = (lo_addr >> 16) & 0xff;
+	addr[3] = (lo_addr >> 24) & 0xff;
+	addr[4] = hi_addr & 0xff;
+	addr[5] = (hi_addr >> 8) & 0xff;
+}
+
+static void dwxgmac2_set_filter(struct mac_device_info *hw,
+				struct net_device *dev)
+{
+	void __iomem *ioaddr = (void __iomem *)dev->base_addr;
+	u32 value = XGMAC_FILTER_RA;
+
+	if (dev->flags & IFF_PROMISC) {
+		value |= XGMAC_FILTER_PR;
+	} else if ((dev->flags & IFF_ALLMULTI) ||
+		   (netdev_mc_count(dev) > HASH_TABLE_SIZE)) {
+		value |= XGMAC_FILTER_PM;
+		writel(~0x0, ioaddr + XGMAC_HASH_TABLE(0));
+		writel(~0x0, ioaddr + XGMAC_HASH_TABLE(1));
+	}
+
+	writel(value, ioaddr + XGMAC_PACKET_FILTER);
+}
+
+const struct stmmac_ops dwxgmac210_ops = {
+	.core_init = dwxgmac2_core_init,
+	.set_mac = dwxgmac2_set_mac,
+	.rx_ipc = dwxgmac2_rx_ipc,
+	.rx_queue_enable = dwxgmac2_rx_queue_enable,
+	.rx_queue_prio = dwxgmac2_rx_queue_prio,
+	.tx_queue_prio = NULL,
+	.rx_queue_routing = NULL,
+	.prog_mtl_rx_algorithms = dwxgmac2_prog_mtl_rx_algorithms,
+	.prog_mtl_tx_algorithms = dwxgmac2_prog_mtl_tx_algorithms,
+	.set_mtl_tx_queue_weight = NULL,
+	.map_mtl_to_dma = dwxgmac2_map_mtl_to_dma,
+	.config_cbs = NULL,
+	.dump_regs = NULL,
+	.host_irq_status = dwxgmac2_host_irq_status,
+	.host_mtl_irq_status = dwxgmac2_host_mtl_irq_status,
+	.flow_ctrl = dwxgmac2_flow_ctrl,
+	.pmt = dwxgmac2_pmt,
+	.set_umac_addr = dwxgmac2_set_umac_addr,
+	.get_umac_addr = dwxgmac2_get_umac_addr,
+	.set_eee_mode = NULL,
+	.reset_eee_mode = NULL,
+	.set_eee_timer = NULL,
+	.set_eee_pls = NULL,
+	.pcs_ctrl_ane = NULL,
+	.pcs_rane = NULL,
+	.pcs_get_adv_lp = NULL,
+	.debug = NULL,
+	.set_filter = dwxgmac2_set_filter,
+};
+
+int dwxgmac2_setup(struct stmmac_priv *priv)
+{
+	struct mac_device_info *mac = priv->hw;
+
+	dev_info(priv->device, "\tXGMAC2\n");
+
+	priv->dev->priv_flags |= IFF_UNICAST_FLT;
+	mac->pcsr = priv->ioaddr;
+	mac->multicast_filter_bins = priv->plat->multicast_filter_bins;
+	mac->unicast_filter_entries = priv->plat->unicast_filter_entries;
+	mac->mcast_bits_log2 = 0;
+
+	if (mac->multicast_filter_bins)
+		mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins);
+
+	mac->link.duplex = 0;
+	mac->link.speed10 = 0;
+	mac->link.speed100 = 0;
+	mac->link.speed1000 = XGMAC_CONFIG_SS_1000;
+	mac->link.speed2500 = XGMAC_CONFIG_SS_2500;
+	mac->link.speed10000 = XGMAC_CONFIG_SS_10000;
+	mac->link.speed_mask = XGMAC_CONFIG_SS_MASK;
+
+	mac->mii.addr = XGMAC_MDIO_ADDR;
+	mac->mii.data = XGMAC_MDIO_DATA;
+	mac->mii.addr_shift = 16;
+	mac->mii.addr_mask = GENMASK(20, 16);
+	mac->mii.reg_shift = 0;
+	mac->mii.reg_mask = GENMASK(15, 0);
+	mac->mii.clk_csr_shift = 19;
+	mac->mii.clk_csr_mask = GENMASK(21, 19);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
new file mode 100644
index 000000000000..1d858fdec997
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
@@ -0,0 +1,280 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2018 Synopsys, Inc. and/or its affiliates.
+ * stmmac XGMAC support.
+ */
+
+#include <linux/stmmac.h>
+#include "common.h"
+#include "dwxgmac2.h"
+
+static int dwxgmac2_get_tx_status(void *data, struct stmmac_extra_stats *x,
+				  struct dma_desc *p, void __iomem *ioaddr)
+{
+	unsigned int tdes3 = le32_to_cpu(p->des3);
+	int ret = tx_done;
+
+	if (unlikely(tdes3 & XGMAC_TDES3_OWN))
+		return tx_dma_own;
+	if (likely(!(tdes3 & XGMAC_TDES3_LD)))
+		return tx_not_ls;
+
+	return ret;
+}
+
+static int dwxgmac2_get_rx_status(void *data, struct stmmac_extra_stats *x,
+				  struct dma_desc *p)
+{
+	unsigned int rdes3 = le32_to_cpu(p->des3);
+	int ret = good_frame;
+
+	if (unlikely(rdes3 & XGMAC_RDES3_OWN))
+		return dma_own;
+	if (likely(!(rdes3 & XGMAC_RDES3_LD)))
+		return discard_frame;
+	if (unlikely(rdes3 & XGMAC_RDES3_ES))
+		ret = discard_frame;
+
+	return ret;
+}
+
+static int dwxgmac2_get_tx_len(struct dma_desc *p)
+{
+	return (le32_to_cpu(p->des2) & XGMAC_TDES2_B1L);
+}
+
+static int dwxgmac2_get_tx_owner(struct dma_desc *p)
+{
+	return (le32_to_cpu(p->des3) & XGMAC_TDES3_OWN) > 0;
+}
+
+static void dwxgmac2_set_tx_owner(struct dma_desc *p)
+{
+	p->des3 |= cpu_to_le32(XGMAC_TDES3_OWN);
+}
+
+static void dwxgmac2_set_rx_owner(struct dma_desc *p, int disable_rx_ic)
+{
+	p->des3 = cpu_to_le32(XGMAC_RDES3_OWN);
+
+	if (!disable_rx_ic)
+		p->des3 |= cpu_to_le32(XGMAC_RDES3_IOC);
+}
+
+static int dwxgmac2_get_tx_ls(struct dma_desc *p)
+{
+	return (le32_to_cpu(p->des3) & XGMAC_RDES3_LD) > 0;
+}
+
+static int dwxgmac2_get_rx_frame_len(struct dma_desc *p, int rx_coe)
+{
+	return (le32_to_cpu(p->des3) & XGMAC_RDES3_PL);
+}
+
+static void dwxgmac2_enable_tx_timestamp(struct dma_desc *p)
+{
+	p->des2 |= cpu_to_le32(XGMAC_TDES2_TTSE);
+}
+
+static int dwxgmac2_get_tx_timestamp_status(struct dma_desc *p)
+{
+	return 0; /* Not supported */
+}
+
+static inline void dwxgmac2_get_timestamp(void *desc, u32 ats, u64 *ts)
+{
+	struct dma_desc *p = (struct dma_desc *)desc;
+	u64 ns = 0;
+
+	ns += le32_to_cpu(p->des1) * 1000000000ULL;
+	ns += le32_to_cpu(p->des0);
+
+	*ts = ns;
+}
+
+static int dwxgmac2_rx_check_timestamp(void *desc)
+{
+	struct dma_desc *p = (struct dma_desc *)desc;
+	unsigned int rdes3 = le32_to_cpu(p->des3);
+	bool desc_valid, ts_valid;
+
+	desc_valid = !(rdes3 & XGMAC_RDES3_OWN) && (rdes3 & XGMAC_RDES3_CTXT);
+	ts_valid = !(rdes3 & XGMAC_RDES3_TSD) && (rdes3 & XGMAC_RDES3_TSA);
+
+	if (likely(desc_valid && ts_valid))
+		return 0;
+	return -EINVAL;
+}
+
+static int dwxgmac2_get_rx_timestamp_status(void *desc, void *next_desc,
+					    u32 ats)
+{
+	struct dma_desc *p = (struct dma_desc *)desc;
+	unsigned int rdes3 = le32_to_cpu(p->des3);
+	int ret = -EBUSY;
+
+	if (likely(rdes3 & XGMAC_RDES3_CDA)) {
+		ret = dwxgmac2_rx_check_timestamp(next_desc);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+static void dwxgmac2_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
+				  int mode, int end)
+{
+	dwxgmac2_set_rx_owner(p, disable_rx_ic);
+}
+
+static void dwxgmac2_init_tx_desc(struct dma_desc *p, int mode, int end)
+{
+	p->des0 = 0;
+	p->des1 = 0;
+	p->des2 = 0;
+	p->des3 = 0;
+}
+
+static void dwxgmac2_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
+				     bool csum_flag, int mode, bool tx_own,
+				     bool ls, unsigned int tot_pkt_len)
+{
+	unsigned int tdes3 = le32_to_cpu(p->des3);
+
+	p->des2 |= cpu_to_le32(len & XGMAC_TDES2_B1L);
+
+	tdes3 = tot_pkt_len & XGMAC_TDES3_FL;
+	if (is_fs)
+		tdes3 |= XGMAC_TDES3_FD;
+	else
+		tdes3 &= ~XGMAC_TDES3_FD;
+
+	if (csum_flag)
+		tdes3 |= 0x3 << XGMAC_TDES3_CIC_SHIFT;
+	else
+		tdes3 &= ~XGMAC_TDES3_CIC;
+
+	if (ls)
+		tdes3 |= XGMAC_TDES3_LD;
+	else
+		tdes3 &= ~XGMAC_TDES3_LD;
+
+	/* Finally set the OWN bit. Later the DMA will start! */
+	if (tx_own)
+		tdes3 |= XGMAC_TDES3_OWN;
+
+	if (is_fs && tx_own)
+		/* When the own bit, for the first frame, has to be set, all
+		 * descriptors for the same frame has to be set before, to
+		 * avoid race condition.
+		 */
+		dma_wmb();
+
+	p->des3 = cpu_to_le32(tdes3);
+}
+
+static void dwxgmac2_prepare_tso_tx_desc(struct dma_desc *p, int is_fs,
+					 int len1, int len2, bool tx_own,
+					 bool ls, unsigned int tcphdrlen,
+					 unsigned int tcppayloadlen)
+{
+	unsigned int tdes3 = le32_to_cpu(p->des3);
+
+	if (len1)
+		p->des2 |= cpu_to_le32(len1 & XGMAC_TDES2_B1L);
+	if (len2)
+		p->des2 |= cpu_to_le32((len2 << XGMAC_TDES2_B2L_SHIFT) &
+				XGMAC_TDES2_B2L);
+	if (is_fs) {
+		tdes3 |= XGMAC_TDES3_FD | XGMAC_TDES3_TSE;
+		tdes3 |= (tcphdrlen << XGMAC_TDES3_THL_SHIFT) &
+			XGMAC_TDES3_THL;
+		tdes3 |= tcppayloadlen & XGMAC_TDES3_TPL;
+	} else {
+		tdes3 &= ~XGMAC_TDES3_FD;
+	}
+
+	if (ls)
+		tdes3 |= XGMAC_TDES3_LD;
+	else
+		tdes3 &= ~XGMAC_TDES3_LD;
+
+	/* Finally set the OWN bit. Later the DMA will start! */
+	if (tx_own)
+		tdes3 |= XGMAC_TDES3_OWN;
+
+	if (is_fs && tx_own)
+		/* When the own bit, for the first frame, has to be set, all
+		 * descriptors for the same frame has to be set before, to
+		 * avoid race condition.
+		 */
+		dma_wmb();
+
+	p->des3 = cpu_to_le32(tdes3);
+}
+
+static void dwxgmac2_release_tx_desc(struct dma_desc *p, int mode)
+{
+	p->des0 = 0;
+	p->des1 = 0;
+	p->des2 = 0;
+	p->des3 = 0;
+}
+
+static void dwxgmac2_set_tx_ic(struct dma_desc *p)
+{
+	p->des2 |= cpu_to_le32(XGMAC_TDES2_IOC);
+}
+
+static void dwxgmac2_set_mss(struct dma_desc *p, unsigned int mss)
+{
+	p->des0 = 0;
+	p->des1 = 0;
+	p->des2 = cpu_to_le32(mss);
+	p->des3 = cpu_to_le32(XGMAC_TDES3_CTXT | XGMAC_TDES3_TCMSSV);
+}
+
+static void dwxgmac2_get_addr(struct dma_desc *p, unsigned int *addr)
+{
+	*addr = le32_to_cpu(p->des0);
+}
+
+static void dwxgmac2_set_addr(struct dma_desc *p, dma_addr_t addr)
+{
+	p->des0 = cpu_to_le32(addr);
+	p->des1 = 0;
+}
+
+static void dwxgmac2_clear(struct dma_desc *p)
+{
+	p->des0 = 0;
+	p->des1 = 0;
+	p->des2 = 0;
+	p->des3 = 0;
+}
+
+const struct stmmac_desc_ops dwxgmac210_desc_ops = {
+	.tx_status = dwxgmac2_get_tx_status,
+	.rx_status = dwxgmac2_get_rx_status,
+	.get_tx_len = dwxgmac2_get_tx_len,
+	.get_tx_owner = dwxgmac2_get_tx_owner,
+	.set_tx_owner = dwxgmac2_set_tx_owner,
+	.set_rx_owner = dwxgmac2_set_rx_owner,
+	.get_tx_ls = dwxgmac2_get_tx_ls,
+	.get_rx_frame_len = dwxgmac2_get_rx_frame_len,
+	.enable_tx_timestamp = dwxgmac2_enable_tx_timestamp,
+	.get_tx_timestamp_status = dwxgmac2_get_tx_timestamp_status,
+	.get_rx_timestamp_status = dwxgmac2_get_rx_timestamp_status,
+	.get_timestamp = dwxgmac2_get_timestamp,
+	.set_tx_ic = dwxgmac2_set_tx_ic,
+	.prepare_tx_desc = dwxgmac2_prepare_tx_desc,
+	.prepare_tso_tx_desc = dwxgmac2_prepare_tso_tx_desc,
+	.release_tx_desc = dwxgmac2_release_tx_desc,
+	.init_rx_desc = dwxgmac2_init_rx_desc,
+	.init_tx_desc = dwxgmac2_init_tx_desc,
+	.set_mss = dwxgmac2_set_mss,
+	.get_addr = dwxgmac2_get_addr,
+	.set_addr = dwxgmac2_set_addr,
+	.clear = dwxgmac2_clear,
+};
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
new file mode 100644
index 000000000000..20909036e002
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -0,0 +1,411 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2018 Synopsys, Inc. and/or its affiliates.
+ * stmmac XGMAC support.
+ */
+
+#include <linux/iopoll.h>
+#include "stmmac.h"
+#include "dwxgmac2.h"
+
+static int dwxgmac2_dma_reset(void __iomem *ioaddr)
+{
+	u32 value = readl(ioaddr + XGMAC_DMA_MODE);
+
+	/* DMA SW reset */
+	writel(value | XGMAC_SWR, ioaddr + XGMAC_DMA_MODE);
+
+	return readl_poll_timeout(ioaddr + XGMAC_DMA_MODE, value,
+				  !(value & XGMAC_SWR), 0, 100000);
+}
+
+static void dwxgmac2_dma_init(void __iomem *ioaddr,
+			      struct stmmac_dma_cfg *dma_cfg, int atds)
+{
+	u32 value = readl(ioaddr + XGMAC_DMA_SYSBUS_MODE);
+
+	if (dma_cfg->aal)
+		value |= XGMAC_AAL;
+
+	writel(value, ioaddr + XGMAC_DMA_SYSBUS_MODE);
+}
+
+static void dwxgmac2_dma_init_chan(void __iomem *ioaddr,
+				   struct stmmac_dma_cfg *dma_cfg, u32 chan)
+{
+	u32 value = readl(ioaddr + XGMAC_DMA_CH_CONTROL(chan));
+
+	if (dma_cfg->pblx8)
+		value |= XGMAC_PBLx8;
+
+	writel(value, ioaddr + XGMAC_DMA_CH_CONTROL(chan));
+	writel(XGMAC_DMA_INT_DEFAULT_EN, ioaddr + XGMAC_DMA_CH_INT_EN(chan));
+}
+
+static void dwxgmac2_dma_init_rx_chan(void __iomem *ioaddr,
+				      struct stmmac_dma_cfg *dma_cfg,
+				      u32 dma_rx_phy, u32 chan)
+{
+	u32 rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl;
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
+	value &= ~XGMAC_RxPBL;
+	value |= (rxpbl << XGMAC_RxPBL_SHIFT) & XGMAC_RxPBL;
+	writel(value, ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
+
+	writel(dma_rx_phy, ioaddr + XGMAC_DMA_CH_RxDESC_LADDR(chan));
+}
+
+static void dwxgmac2_dma_init_tx_chan(void __iomem *ioaddr,
+				      struct stmmac_dma_cfg *dma_cfg,
+				      u32 dma_tx_phy, u32 chan)
+{
+	u32 txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
+	value &= ~XGMAC_TxPBL;
+	value |= (txpbl << XGMAC_TxPBL_SHIFT) & XGMAC_TxPBL;
+	value |= XGMAC_OSP;
+	writel(value, ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
+
+	writel(dma_tx_phy, ioaddr + XGMAC_DMA_CH_TxDESC_LADDR(chan));
+}
+
+static void dwxgmac2_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi)
+{
+	u32 value = readl(ioaddr + XGMAC_DMA_SYSBUS_MODE);
+	int i;
+
+	if (axi->axi_lpi_en)
+		value |= XGMAC_EN_LPI;
+	if (axi->axi_xit_frm)
+		value |= XGMAC_LPI_XIT_PKT;
+
+	value &= ~XGMAC_WR_OSR_LMT;
+	value |= (axi->axi_wr_osr_lmt << XGMAC_WR_OSR_LMT_SHIFT) &
+		XGMAC_WR_OSR_LMT;
+
+	value &= ~XGMAC_RD_OSR_LMT;
+	value |= (axi->axi_rd_osr_lmt << XGMAC_RD_OSR_LMT_SHIFT) &
+		XGMAC_RD_OSR_LMT;
+
+	value &= ~XGMAC_BLEN;
+	for (i = 0; i < AXI_BLEN; i++) {
+		if (axi->axi_blen[i])
+			value &= ~XGMAC_UNDEF;
+
+		switch (axi->axi_blen[i]) {
+		case 256:
+			value |= XGMAC_BLEN256;
+			break;
+		case 128:
+			value |= XGMAC_BLEN128;
+			break;
+		case 64:
+			value |= XGMAC_BLEN64;
+			break;
+		case 32:
+			value |= XGMAC_BLEN32;
+			break;
+		case 16:
+			value |= XGMAC_BLEN16;
+			break;
+		case 8:
+			value |= XGMAC_BLEN8;
+			break;
+		case 4:
+			value |= XGMAC_BLEN4;
+			break;
+		}
+	}
+
+	writel(value, ioaddr + XGMAC_DMA_SYSBUS_MODE);
+}
+
+static void dwxgmac2_dma_rx_mode(void __iomem *ioaddr, int mode,
+				 u32 channel, int fifosz, u8 qmode)
+{
+	u32 value = readl(ioaddr + XGMAC_MTL_RXQ_OPMODE(channel));
+	unsigned int rqs = fifosz / 256 - 1;
+
+	if (mode == SF_DMA_MODE) {
+		value |= XGMAC_RSF;
+	} else {
+		value &= ~XGMAC_RSF;
+		value &= ~XGMAC_RTC;
+
+		if (mode <= 64)
+			value |= 0x0 << XGMAC_RTC_SHIFT;
+		else if (mode <= 96)
+			value |= 0x2 << XGMAC_RTC_SHIFT;
+		else
+			value |= 0x3 << XGMAC_RTC_SHIFT;
+	}
+
+	value &= ~XGMAC_RQS;
+	value |= (rqs << XGMAC_RQS_SHIFT) & XGMAC_RQS;
+
+	writel(value, ioaddr + XGMAC_MTL_RXQ_OPMODE(channel));
+
+	/* Enable MTL RX overflow */
+	value = readl(ioaddr + XGMAC_MTL_QINTEN(channel));
+	writel(value | XGMAC_RXOIE, ioaddr + XGMAC_MTL_QINTEN(channel));
+}
+
+static void dwxgmac2_dma_tx_mode(void __iomem *ioaddr, int mode,
+				 u32 channel, int fifosz, u8 qmode)
+{
+	u32 value = readl(ioaddr + XGMAC_MTL_TXQ_OPMODE(channel));
+	unsigned int tqs = fifosz / 256 - 1;
+
+	if (mode == SF_DMA_MODE) {
+		value |= XGMAC_TSF;
+	} else {
+		value &= ~XGMAC_TSF;
+		value &= ~XGMAC_TTC;
+
+		if (mode <= 64)
+			value |= 0x0 << XGMAC_TTC_SHIFT;
+		else if (mode <= 96)
+			value |= 0x2 << XGMAC_TTC_SHIFT;
+		else if (mode <= 128)
+			value |= 0x3 << XGMAC_TTC_SHIFT;
+		else if (mode <= 192)
+			value |= 0x4 << XGMAC_TTC_SHIFT;
+		else if (mode <= 256)
+			value |= 0x5 << XGMAC_TTC_SHIFT;
+		else if (mode <= 384)
+			value |= 0x6 << XGMAC_TTC_SHIFT;
+		else
+			value |= 0x7 << XGMAC_TTC_SHIFT;
+	}
+
+	value &= ~XGMAC_TXQEN;
+	if (qmode != MTL_QUEUE_AVB)
+		value |= 0x2 << XGMAC_TXQEN_SHIFT;
+	else
+		value |= 0x1 << XGMAC_TXQEN_SHIFT;
+
+	value &= ~XGMAC_TQS;
+	value |= (tqs << XGMAC_TQS_SHIFT) & XGMAC_TQS;
+
+	writel(value, ioaddr +  XGMAC_MTL_TXQ_OPMODE(channel));
+}
+
+static void dwxgmac2_enable_dma_irq(void __iomem *ioaddr, u32 chan)
+{
+	writel(XGMAC_DMA_INT_DEFAULT_EN, ioaddr + XGMAC_DMA_CH_INT_EN(chan));
+}
+
+static void dwxgmac2_disable_dma_irq(void __iomem *ioaddr, u32 chan)
+{
+	writel(0, ioaddr + XGMAC_DMA_CH_INT_EN(chan));
+}
+
+static void dwxgmac2_dma_start_tx(void __iomem *ioaddr, u32 chan)
+{
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
+	value |= XGMAC_TXST;
+	writel(value, ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
+
+	value = readl(ioaddr + XGMAC_TX_CONFIG);
+	value |= XGMAC_CONFIG_TE;
+	writel(value, ioaddr + XGMAC_TX_CONFIG);
+}
+
+static void dwxgmac2_dma_stop_tx(void __iomem *ioaddr, u32 chan)
+{
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
+	value &= ~XGMAC_TXST;
+	writel(value, ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
+
+	value = readl(ioaddr + XGMAC_TX_CONFIG);
+	value &= ~XGMAC_CONFIG_TE;
+	writel(value, ioaddr + XGMAC_TX_CONFIG);
+}
+
+static void dwxgmac2_dma_start_rx(void __iomem *ioaddr, u32 chan)
+{
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
+	value |= XGMAC_RXST;
+	writel(value, ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
+
+	value = readl(ioaddr + XGMAC_RX_CONFIG);
+	value |= XGMAC_CONFIG_RE;
+	writel(value, ioaddr + XGMAC_RX_CONFIG);
+}
+
+static void dwxgmac2_dma_stop_rx(void __iomem *ioaddr, u32 chan)
+{
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
+	value &= ~XGMAC_RXST;
+	writel(value, ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
+
+	value = readl(ioaddr + XGMAC_RX_CONFIG);
+	value &= ~XGMAC_CONFIG_RE;
+	writel(value, ioaddr + XGMAC_RX_CONFIG);
+}
+
+static int dwxgmac2_dma_interrupt(void __iomem *ioaddr,
+				  struct stmmac_extra_stats *x, u32 chan)
+{
+	u32 intr_status = readl(ioaddr + XGMAC_DMA_CH_STATUS(chan));
+	int ret = 0;
+
+	/* ABNORMAL interrupts */
+	if (unlikely(intr_status & XGMAC_AIS)) {
+		if (unlikely(intr_status & XGMAC_TPS)) {
+			x->tx_process_stopped_irq++;
+			ret |= tx_hard_error;
+		}
+		if (unlikely(intr_status & XGMAC_FBE)) {
+			x->fatal_bus_error_irq++;
+			ret |= tx_hard_error;
+		}
+	}
+
+	/* TX/RX NORMAL interrupts */
+	if (likely(intr_status & XGMAC_NIS)) {
+		x->normal_irq_n++;
+
+		if (likely(intr_status & XGMAC_RI)) {
+			u32 value = readl(ioaddr + XGMAC_DMA_CH_INT_EN(chan));
+			if (likely(value & XGMAC_RIE)) {
+				x->rx_normal_irq_n++;
+				ret |= handle_rx;
+			}
+		}
+		if (likely(intr_status & XGMAC_TI)) {
+			x->tx_normal_irq_n++;
+			ret |= handle_tx;
+		}
+	}
+
+	/* Clear interrupts */
+	writel(~0x0, ioaddr + XGMAC_DMA_CH_STATUS(chan));
+
+	return ret;
+}
+
+static void dwxgmac2_get_hw_feature(void __iomem *ioaddr,
+				    struct dma_features *dma_cap)
+{
+	u32 hw_cap;
+
+	/*  MAC HW feature 0 */
+	hw_cap = readl(ioaddr + XGMAC_HW_FEATURE0);
+	dma_cap->rx_coe = (hw_cap & XGMAC_HWFEAT_RXCOESEL) >> 16;
+	dma_cap->tx_coe = (hw_cap & XGMAC_HWFEAT_TXCOESEL) >> 14;
+	dma_cap->atime_stamp = (hw_cap & XGMAC_HWFEAT_TSSEL) >> 12;
+	dma_cap->av = (hw_cap & XGMAC_HWFEAT_AVSEL) >> 11;
+	dma_cap->av &= (hw_cap & XGMAC_HWFEAT_RAVSEL) >> 10;
+	dma_cap->pmt_magic_frame = (hw_cap & XGMAC_HWFEAT_MGKSEL) >> 7;
+	dma_cap->pmt_remote_wake_up = (hw_cap & XGMAC_HWFEAT_RWKSEL) >> 6;
+	dma_cap->mbps_1000 = (hw_cap & XGMAC_HWFEAT_GMIISEL) >> 1;
+
+	/* MAC HW feature 1 */
+	hw_cap = readl(ioaddr + XGMAC_HW_FEATURE1);
+	dma_cap->tsoen = (hw_cap & XGMAC_HWFEAT_TSOEN) >> 18;
+	dma_cap->tx_fifo_size =
+		128 << ((hw_cap & XGMAC_HWFEAT_TXFIFOSIZE) >> 6);
+	dma_cap->rx_fifo_size =
+		128 << ((hw_cap & XGMAC_HWFEAT_RXFIFOSIZE) >> 0);
+
+	/* MAC HW feature 2 */
+	hw_cap = readl(ioaddr + XGMAC_HW_FEATURE2);
+	dma_cap->pps_out_num = (hw_cap & XGMAC_HWFEAT_PPSOUTNUM) >> 24;
+	dma_cap->number_tx_channel =
+		((hw_cap & XGMAC_HWFEAT_TXCHCNT) >> 18) + 1;
+	dma_cap->number_rx_channel =
+		((hw_cap & XGMAC_HWFEAT_RXCHCNT) >> 12) + 1;
+	dma_cap->number_tx_queues =
+		((hw_cap & XGMAC_HWFEAT_TXQCNT) >> 6) + 1;
+	dma_cap->number_rx_queues =
+		((hw_cap & XGMAC_HWFEAT_RXQCNT) >> 0) + 1;
+}
+
+static void dwxgmac2_rx_watchdog(void __iomem *ioaddr, u32 riwt, u32 nchan)
+{
+	u32 i;
+
+	for (i = 0; i < nchan; i++)
+		writel(riwt & XGMAC_RWT, ioaddr + XGMAC_DMA_CH_Rx_WATCHDOG(i));
+}
+
+static void dwxgmac2_set_rx_ring_len(void __iomem *ioaddr, u32 len, u32 chan)
+{
+	writel(len, ioaddr + XGMAC_DMA_CH_RxDESC_RING_LEN(chan));
+}
+
+static void dwxgmac2_set_tx_ring_len(void __iomem *ioaddr, u32 len, u32 chan)
+{
+	writel(len, ioaddr + XGMAC_DMA_CH_TxDESC_RING_LEN(chan));
+}
+
+static void dwxgmac2_set_rx_tail_ptr(void __iomem *ioaddr, u32 ptr, u32 chan)
+{
+	writel(ptr, ioaddr + XGMAC_DMA_CH_RxDESC_TAIL_LPTR(chan));
+}
+
+static void dwxgmac2_set_tx_tail_ptr(void __iomem *ioaddr, u32 ptr, u32 chan)
+{
+	writel(ptr, ioaddr + XGMAC_DMA_CH_TxDESC_TAIL_LPTR(chan));
+}
+
+static void dwxgmac2_enable_tso(void __iomem *ioaddr, bool en, u32 chan)
+{
+	u32 value = readl(ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
+
+	if (en)
+		value |= XGMAC_TSE;
+	else
+		value &= ~XGMAC_TSE;
+
+	writel(value, ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
+}
+
+static void dwxgmac2_set_bfsize(void __iomem *ioaddr, int bfsize, u32 chan)
+{
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
+	value |= bfsize << 1;
+	writel(value, ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
+}
+
+const struct stmmac_dma_ops dwxgmac210_dma_ops = {
+	.reset = dwxgmac2_dma_reset,
+	.init = dwxgmac2_dma_init,
+	.init_chan = dwxgmac2_dma_init_chan,
+	.init_rx_chan = dwxgmac2_dma_init_rx_chan,
+	.init_tx_chan = dwxgmac2_dma_init_tx_chan,
+	.axi = dwxgmac2_dma_axi,
+	.dump_regs = NULL,
+	.dma_rx_mode = dwxgmac2_dma_rx_mode,
+	.dma_tx_mode = dwxgmac2_dma_tx_mode,
+	.enable_dma_irq = dwxgmac2_enable_dma_irq,
+	.disable_dma_irq = dwxgmac2_disable_dma_irq,
+	.start_tx = dwxgmac2_dma_start_tx,
+	.stop_tx = dwxgmac2_dma_stop_tx,
+	.start_rx = dwxgmac2_dma_start_rx,
+	.stop_rx = dwxgmac2_dma_stop_rx,
+	.dma_interrupt = dwxgmac2_dma_interrupt,
+	.get_hw_feature = dwxgmac2_get_hw_feature,
+	.rx_watchdog = dwxgmac2_rx_watchdog,
+	.set_rx_ring_len = dwxgmac2_set_rx_ring_len,
+	.set_tx_ring_len = dwxgmac2_set_tx_ring_len,
+	.set_rx_tail_ptr = dwxgmac2_set_rx_tail_ptr,
+	.set_tx_tail_ptr = dwxgmac2_set_tx_tail_ptr,
+	.enable_tso = dwxgmac2_enable_tso,
+	.set_bfsize = dwxgmac2_set_bfsize,
+};
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c
index 1f50e83cafb2..357309a6d6a5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.c
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c
@@ -72,6 +72,7 @@ static int stmmac_dwmac4_quirks(struct stmmac_priv *priv)
 static const struct stmmac_hwif_entry {
 	bool gmac;
 	bool gmac4;
+	bool xgmac;
 	u32 min_id;
 	const struct stmmac_regs_off regs;
 	const void *desc;
@@ -87,6 +88,7 @@ static const struct stmmac_hwif_entry {
 	{
 		.gmac = false,
 		.gmac4 = false,
+		.xgmac = false,
 		.min_id = 0,
 		.regs = {
 			.ptp_off = PTP_GMAC3_X_OFFSET,
@@ -103,6 +105,7 @@ static const struct stmmac_hwif_entry {
 	}, {
 		.gmac = true,
 		.gmac4 = false,
+		.xgmac = false,
 		.min_id = 0,
 		.regs = {
 			.ptp_off = PTP_GMAC3_X_OFFSET,
@@ -119,6 +122,7 @@ static const struct stmmac_hwif_entry {
 	}, {
 		.gmac = false,
 		.gmac4 = true,
+		.xgmac = false,
 		.min_id = 0,
 		.regs = {
 			.ptp_off = PTP_GMAC4_OFFSET,
@@ -135,6 +139,7 @@ static const struct stmmac_hwif_entry {
 	}, {
 		.gmac = false,
 		.gmac4 = true,
+		.xgmac = false,
 		.min_id = DWMAC_CORE_4_00,
 		.regs = {
 			.ptp_off = PTP_GMAC4_OFFSET,
@@ -151,6 +156,7 @@ static const struct stmmac_hwif_entry {
 	}, {
 		.gmac = false,
 		.gmac4 = true,
+		.xgmac = false,
 		.min_id = DWMAC_CORE_4_10,
 		.regs = {
 			.ptp_off = PTP_GMAC4_OFFSET,
@@ -167,6 +173,7 @@ static const struct stmmac_hwif_entry {
 	}, {
 		.gmac = false,
 		.gmac4 = true,
+		.xgmac = false,
 		.min_id = DWMAC_CORE_5_10,
 		.regs = {
 			.ptp_off = PTP_GMAC4_OFFSET,
@@ -180,11 +187,29 @@ static const struct stmmac_hwif_entry {
 		.tc = &dwmac510_tc_ops,
 		.setup = dwmac4_setup,
 		.quirks = NULL,
-	}
+	}, {
+		.gmac = false,
+		.gmac4 = false,
+		.xgmac = true,
+		.min_id = DWXGMAC_CORE_2_10,
+		.regs = {
+			.ptp_off = PTP_XGMAC_OFFSET,
+			.mmc_off = 0,
+		},
+		.desc = &dwxgmac210_desc_ops,
+		.dma = &dwxgmac210_dma_ops,
+		.mac = &dwxgmac210_ops,
+		.hwtimestamp = &stmmac_ptp,
+		.mode = NULL,
+		.tc = NULL,
+		.setup = dwxgmac2_setup,
+		.quirks = NULL,
+	},
 };
 
 int stmmac_hwif_init(struct stmmac_priv *priv)
 {
+	bool needs_xgmac = priv->plat->has_xgmac;
 	bool needs_gmac4 = priv->plat->has_gmac4;
 	bool needs_gmac = priv->plat->has_gmac;
 	const struct stmmac_hwif_entry *entry;
@@ -195,7 +220,7 @@ int stmmac_hwif_init(struct stmmac_priv *priv)
 
 	if (needs_gmac) {
 		id = stmmac_get_id(priv, GMAC_VERSION);
-	} else if (needs_gmac4) {
+	} else if (needs_gmac4 || needs_xgmac) {
 		id = stmmac_get_id(priv, GMAC4_VERSION);
 	} else {
 		id = 0;
@@ -229,6 +254,8 @@ int stmmac_hwif_init(struct stmmac_priv *priv)
 			continue;
 		if (needs_gmac4 ^ entry->gmac4)
 			continue;
+		if (needs_xgmac ^ entry->xgmac)
+			continue;
 		/* Use synopsys_id var because some setups can override this */
 		if (priv->synopsys_id < entry->min_id)
 			continue;
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index fe8b536b13f8..92b8944f26e3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -183,6 +183,7 @@ struct stmmac_dma_ops {
 	void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 	void (*set_tx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 	void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan);
+	void (*qmode)(void __iomem *ioaddr, u32 channel, u8 qmode);
 	void (*set_bfsize)(void __iomem *ioaddr, int bfsize, u32 chan);
 };
 
@@ -236,6 +237,8 @@ struct stmmac_dma_ops {
 	stmmac_do_void_callback(__priv, dma, set_tx_tail_ptr, __args)
 #define stmmac_enable_tso(__priv, __args...) \
 	stmmac_do_void_callback(__priv, dma, enable_tso, __args)
+#define stmmac_dma_qmode(__priv, __args...) \
+	stmmac_do_void_callback(__priv, dma, qmode, __args)
 #define stmmac_set_dma_bfsize(__priv, __args...) \
 	stmmac_do_void_callback(__priv, dma, set_bfsize, __args)
 
@@ -444,17 +447,22 @@ struct stmmac_mode_ops {
 
 struct stmmac_priv;
 struct tc_cls_u32_offload;
+struct tc_cbs_qopt_offload;
 
 struct stmmac_tc_ops {
 	int (*init)(struct stmmac_priv *priv);
 	int (*setup_cls_u32)(struct stmmac_priv *priv,
 			     struct tc_cls_u32_offload *cls);
+	int (*setup_cbs)(struct stmmac_priv *priv,
+			 struct tc_cbs_qopt_offload *qopt);
 };
 
 #define stmmac_tc_init(__priv, __args...) \
 	stmmac_do_callback(__priv, tc, init, __args)
 #define stmmac_tc_setup_cls_u32(__priv, __args...) \
 	stmmac_do_callback(__priv, tc, setup_cls_u32, __args)
+#define stmmac_tc_setup_cbs(__priv, __args...) \
+	stmmac_do_callback(__priv, tc, setup_cbs, __args)
 
 struct stmmac_regs_off {
 	u32 ptp_off;
@@ -471,6 +479,9 @@ extern const struct stmmac_ops dwmac410_ops;
 extern const struct stmmac_dma_ops dwmac410_dma_ops;
 extern const struct stmmac_ops dwmac510_ops;
 extern const struct stmmac_tc_ops dwmac510_tc_ops;
+extern const struct stmmac_ops dwxgmac210_ops;
+extern const struct stmmac_dma_ops dwxgmac210_dma_ops;
+extern const struct stmmac_desc_ops dwxgmac210_desc_ops;
 
 #define GMAC_VERSION		0x00000020	/* GMAC CORE Version */
 #define GMAC4_VERSION		0x00000110	/* GMAC4+ CORE Version */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index ef6a8d39db2f..ff1ffb46198a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -51,6 +51,7 @@
 #include <linux/reset.h>
 #include <linux/of_mdio.h>
 #include "dwmac1000.h"
+#include "dwxgmac2.h"
 #include "hwif.h"
 
 #define	STMMAC_ALIGN(x)		__ALIGN_KERNEL(x, SMP_CACHE_BYTES)
@@ -262,6 +263,21 @@ static void stmmac_clk_csr_set(struct stmmac_priv *priv)
 		else
 			priv->clk_csr = 0;
 	}
+
+	if (priv->plat->has_xgmac) {
+		if (clk_rate > 400000000)
+			priv->clk_csr = 0x5;
+		else if (clk_rate > 350000000)
+			priv->clk_csr = 0x4;
+		else if (clk_rate > 300000000)
+			priv->clk_csr = 0x3;
+		else if (clk_rate > 250000000)
+			priv->clk_csr = 0x2;
+		else if (clk_rate > 150000000)
+			priv->clk_csr = 0x1;
+		else
+			priv->clk_csr = 0x0;
+	}
 }
 
 static void print_pkt(unsigned char *buf, int len)
@@ -498,7 +514,7 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p,
 	if (!priv->hwts_rx_en)
 		return;
 	/* For GMAC4, the valid timestamp is from CTX next desc. */
-	if (priv->plat->has_gmac4)
+	if (priv->plat->has_gmac4 || priv->plat->has_xgmac)
 		desc = np;
 
 	/* Check if timestamp is available */
@@ -540,6 +556,9 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 	u32 ts_event_en = 0;
 	u32 value = 0;
 	u32 sec_inc;
+	bool xmac;
+
+	xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
 
 	if (!(priv->dma_cap.time_stamp || priv->adv_ts)) {
 		netdev_alert(priv->dev, "No support for HW time stamping\n");
@@ -575,7 +594,7 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 			/* PTP v1, UDP, any kind of event packet */
 			config.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 			/* take time stamp for all event messages */
-			if (priv->plat->has_gmac4)
+			if (xmac)
 				snap_type_sel = PTP_GMAC4_TCR_SNAPTYPSEL_1;
 			else
 				snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
@@ -610,7 +629,7 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			/* take time stamp for all event messages */
-			if (priv->plat->has_gmac4)
+			if (xmac)
 				snap_type_sel = PTP_GMAC4_TCR_SNAPTYPSEL_1;
 			else
 				snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
@@ -647,7 +666,7 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			/* take time stamp for all event messages */
-			if (priv->plat->has_gmac4)
+			if (xmac)
 				snap_type_sel = PTP_GMAC4_TCR_SNAPTYPSEL_1;
 			else
 				snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
@@ -718,7 +737,7 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 		/* program Sub Second Increment reg */
 		stmmac_config_sub_second_increment(priv,
 				priv->ptpaddr, priv->plat->clk_ptp_rate,
-				priv->plat->has_gmac4, &sec_inc);
+				xmac, &sec_inc);
 		temp = div_u64(1000000000ULL, sec_inc);
 
 		/* Store sub second increment and flags for later use */
@@ -755,12 +774,14 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
  */
 static int stmmac_init_ptp(struct stmmac_priv *priv)
 {
+	bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
+
 	if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp))
 		return -EOPNOTSUPP;
 
 	priv->adv_ts = 0;
-	/* Check if adv_ts can be enabled for dwmac 4.x core */
-	if (priv->plat->has_gmac4 && priv->dma_cap.atime_stamp)
+	/* Check if adv_ts can be enabled for dwmac 4.x / xgmac core */
+	if (xmac && priv->dma_cap.atime_stamp)
 		priv->adv_ts = 1;
 	/* Dwmac 3.x core with extend_desc can support adv_ts */
 	else if (priv->extend_desc && priv->dma_cap.atime_stamp)
@@ -2173,6 +2194,12 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 		return ret;
 	}
 
+	/* DMA Configuration */
+	stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg, atds);
+
+	if (priv->plat->axi)
+		stmmac_axi(priv, priv->ioaddr, priv->plat->axi);
+
 	/* DMA RX Channel Configuration */
 	for (chan = 0; chan < rx_channels_count; chan++) {
 		rx_q = &priv->rx_queue[chan];
@@ -2203,12 +2230,6 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 	for (chan = 0; chan < dma_csr_ch; chan++)
 		stmmac_init_chan(priv, priv->ioaddr, priv->plat->dma_cfg, chan);
 
-	/* DMA Configuration */
-	stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg, atds);
-
-	if (priv->plat->axi)
-		stmmac_axi(priv, priv->ioaddr, priv->plat->axi);
-
 	return ret;
 }
 
@@ -2526,9 +2547,6 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 		netdev_warn(priv->dev, "%s: failed debugFS registration\n",
 			    __func__);
 #endif
-	/* Start the ball rolling... */
-	stmmac_start_all_dma(priv);
-
 	priv->tx_lpi_timer = STMMAC_DEFAULT_TWT_LS;
 
 	if (priv->use_riwt) {
@@ -2549,6 +2567,9 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 			stmmac_enable_tso(priv, priv->ioaddr, 1, chan);
 	}
 
+	/* Start the ball rolling... */
+	stmmac_start_all_dma(priv);
+
 	return 0;
 }
 
@@ -3305,6 +3326,9 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 	int coe = priv->hw->rx_csum;
 	unsigned int next_entry;
 	unsigned int count = 0;
+	bool xmac;
+
+	xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
 
 	if (netif_msg_rx_status(priv)) {
 		void *rx_head;
@@ -3406,7 +3430,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			 * in case of GMAC4 because it needs
 			 * to refill the used descriptors, always.
 			 */
-			if (unlikely(!priv->plat->has_gmac4 &&
+			if (unlikely(!xmac &&
 				     ((frame_len < priv->rx_copybreak) ||
 				     stmmac_rx_threshold_count(rx_q)))) {
 				skb = netdev_alloc_skb_ip_align(priv->dev,
@@ -3642,7 +3666,9 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 	u32 tx_cnt = priv->plat->tx_queues_to_use;
 	u32 queues_count;
 	u32 queue;
+	bool xmac;
 
+	xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
 	queues_count = (rx_cnt > tx_cnt) ? rx_cnt : tx_cnt;
 
 	if (priv->irq_wake)
@@ -3661,7 +3687,7 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 		return IRQ_HANDLED;
 
 	/* To handle GMAC own interrupts */
-	if ((priv->plat->has_gmac) || (priv->plat->has_gmac4)) {
+	if ((priv->plat->has_gmac) || xmac) {
 		int status = stmmac_host_irq_status(priv, priv->hw, &priv->xstats);
 		int mtl_status;
 
@@ -3778,7 +3804,7 @@ static int stmmac_setup_tc_block(struct stmmac_priv *priv,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, stmmac_setup_tc_block_cb,
-				priv, priv);
+				priv, priv, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, stmmac_setup_tc_block_cb, priv);
 		return 0;
@@ -3795,6 +3821,8 @@ static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 	switch (type) {
 	case TC_SETUP_BLOCK:
 		return stmmac_setup_tc_block(priv, type_data);
+	case TC_SETUP_QDISC_CBS:
+		return stmmac_tc_setup_cbs(priv, priv, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -4267,6 +4295,8 @@ int stmmac_dvr_probe(struct device *device,
 	ndev->min_mtu = ETH_ZLEN - ETH_HLEN;
 	if ((priv->plat->enh_desc) || (priv->synopsys_id >= DWMAC_CORE_4_00))
 		ndev->max_mtu = JUMBO_LEN;
+	else if (priv->plat->has_xgmac)
+		ndev->max_mtu = XGMAC_JUMBO_LEN;
 	else
 		ndev->max_mtu = SKB_MAX_HEAD(NET_SKB_PAD + NET_IP_ALIGN);
 	/* Will not overwrite ndev->max_mtu if plat->maxmtu > ndev->max_mtu
@@ -4288,7 +4318,8 @@ int stmmac_dvr_probe(struct device *device,
 	 * has to be disable and this can be done by passing the
 	 * riwt_off field from the platform.
 	 */
-	if ((priv->synopsys_id >= DWMAC_CORE_3_50) && (!priv->plat->riwt_off)) {
+	if (((priv->synopsys_id >= DWMAC_CORE_3_50) ||
+	    (priv->plat->has_xgmac)) && (!priv->plat->riwt_off)) {
 		priv->use_riwt = 1;
 		dev_info(priv->device,
 			 "Enable RX Mitigation via HW Watchdog Timer\n");
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index 5df1a608e566..b72ef171477e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -29,6 +29,7 @@
 #include <linux/phy.h>
 #include <linux/slab.h>
 
+#include "dwxgmac2.h"
 #include "stmmac.h"
 
 #define MII_BUSY 0x00000001
@@ -39,6 +40,115 @@
 #define MII_GMAC4_WRITE			(1 << MII_GMAC4_GOC_SHIFT)
 #define MII_GMAC4_READ			(3 << MII_GMAC4_GOC_SHIFT)
 
+/* XGMAC defines */
+#define MII_XGMAC_SADDR			BIT(18)
+#define MII_XGMAC_CMD_SHIFT		16
+#define MII_XGMAC_WRITE			(1 << MII_XGMAC_CMD_SHIFT)
+#define MII_XGMAC_READ			(3 << MII_XGMAC_CMD_SHIFT)
+#define MII_XGMAC_BUSY			BIT(22)
+#define MII_XGMAC_MAX_C22ADDR		3
+#define MII_XGMAC_C22P_MASK		GENMASK(MII_XGMAC_MAX_C22ADDR, 0)
+
+static int stmmac_xgmac2_c22_format(struct stmmac_priv *priv, int phyaddr,
+				    int phyreg, u32 *hw_addr)
+{
+	unsigned int mii_data = priv->hw->mii.data;
+	u32 tmp;
+
+	/* HW does not support C22 addr >= 4 */
+	if (phyaddr > MII_XGMAC_MAX_C22ADDR)
+		return -ENODEV;
+	/* Wait until any existing MII operation is complete */
+	if (readl_poll_timeout(priv->ioaddr + mii_data, tmp,
+			       !(tmp & MII_XGMAC_BUSY), 100, 10000))
+		return -EBUSY;
+
+	/* Set port as Clause 22 */
+	tmp = readl(priv->ioaddr + XGMAC_MDIO_C22P);
+	tmp &= ~MII_XGMAC_C22P_MASK;
+	tmp |= BIT(phyaddr);
+	writel(tmp, priv->ioaddr + XGMAC_MDIO_C22P);
+
+	*hw_addr = (phyaddr << 16) | (phyreg & 0x1f);
+	return 0;
+}
+
+static int stmmac_xgmac2_mdio_read(struct mii_bus *bus, int phyaddr, int phyreg)
+{
+	struct net_device *ndev = bus->priv;
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	unsigned int mii_address = priv->hw->mii.addr;
+	unsigned int mii_data = priv->hw->mii.data;
+	u32 tmp, addr, value = MII_XGMAC_BUSY;
+	int ret;
+
+	if (phyreg & MII_ADDR_C45) {
+		return -EOPNOTSUPP;
+	} else {
+		ret = stmmac_xgmac2_c22_format(priv, phyaddr, phyreg, &addr);
+		if (ret)
+			return ret;
+	}
+
+	value |= (priv->clk_csr << priv->hw->mii.clk_csr_shift)
+		& priv->hw->mii.clk_csr_mask;
+	value |= MII_XGMAC_SADDR | MII_XGMAC_READ;
+
+	/* Wait until any existing MII operation is complete */
+	if (readl_poll_timeout(priv->ioaddr + mii_data, tmp,
+			       !(tmp & MII_XGMAC_BUSY), 100, 10000))
+		return -EBUSY;
+
+	/* Set the MII address register to read */
+	writel(addr, priv->ioaddr + mii_address);
+	writel(value, priv->ioaddr + mii_data);
+
+	/* Wait until any existing MII operation is complete */
+	if (readl_poll_timeout(priv->ioaddr + mii_data, tmp,
+			       !(tmp & MII_XGMAC_BUSY), 100, 10000))
+		return -EBUSY;
+
+	/* Read the data from the MII data register */
+	return readl(priv->ioaddr + mii_data) & GENMASK(15, 0);
+}
+
+static int stmmac_xgmac2_mdio_write(struct mii_bus *bus, int phyaddr,
+				    int phyreg, u16 phydata)
+{
+	struct net_device *ndev = bus->priv;
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	unsigned int mii_address = priv->hw->mii.addr;
+	unsigned int mii_data = priv->hw->mii.data;
+	u32 addr, tmp, value = MII_XGMAC_BUSY;
+	int ret;
+
+	if (phyreg & MII_ADDR_C45) {
+		return -EOPNOTSUPP;
+	} else {
+		ret = stmmac_xgmac2_c22_format(priv, phyaddr, phyreg, &addr);
+		if (ret)
+			return ret;
+	}
+
+	value |= (priv->clk_csr << priv->hw->mii.clk_csr_shift)
+		& priv->hw->mii.clk_csr_mask;
+	value |= phydata | MII_XGMAC_SADDR;
+	value |= MII_XGMAC_WRITE;
+
+	/* Wait until any existing MII operation is complete */
+	if (readl_poll_timeout(priv->ioaddr + mii_data, tmp,
+			       !(tmp & MII_XGMAC_BUSY), 100, 10000))
+		return -EBUSY;
+
+	/* Set the MII address register to write */
+	writel(addr, priv->ioaddr + mii_address);
+	writel(value, priv->ioaddr + mii_data);
+
+	/* Wait until any existing MII operation is complete */
+	return readl_poll_timeout(priv->ioaddr + mii_data, tmp,
+				  !(tmp & MII_XGMAC_BUSY), 100, 10000);
+}
+
 /**
  * stmmac_mdio_read
  * @bus: points to the mii_bus structure
@@ -205,7 +315,7 @@ int stmmac_mdio_register(struct net_device *ndev)
 	struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data;
 	struct device_node *mdio_node = priv->plat->mdio_node;
 	struct device *dev = ndev->dev.parent;
-	int addr, found;
+	int addr, found, max_addr;
 
 	if (!mdio_bus_data)
 		return 0;
@@ -223,8 +333,23 @@ int stmmac_mdio_register(struct net_device *ndev)
 #endif
 
 	new_bus->name = "stmmac";
-	new_bus->read = &stmmac_mdio_read;
-	new_bus->write = &stmmac_mdio_write;
+
+	if (priv->plat->has_xgmac) {
+		new_bus->read = &stmmac_xgmac2_mdio_read;
+		new_bus->write = &stmmac_xgmac2_mdio_write;
+
+		/* Right now only C22 phys are supported */
+		max_addr = MII_XGMAC_MAX_C22ADDR + 1;
+
+		/* Check if DT specified an unsupported phy addr */
+		if (priv->plat->phy_addr > MII_XGMAC_MAX_C22ADDR)
+			dev_err(dev, "Unsupported phy_addr (max=%d)\n",
+					MII_XGMAC_MAX_C22ADDR);
+	} else {
+		new_bus->read = &stmmac_mdio_read;
+		new_bus->write = &stmmac_mdio_write;
+		max_addr = PHY_MAX_ADDR;
+	}
 
 	new_bus->reset = &stmmac_mdio_reset;
 	snprintf(new_bus->id, MII_BUS_ID_SIZE, "%s-%x",
@@ -243,7 +368,7 @@ int stmmac_mdio_register(struct net_device *ndev)
 		goto bus_register_done;
 
 	found = 0;
-	for (addr = 0; addr < PHY_MAX_ADDR; addr++) {
+	for (addr = 0; addr < max_addr; addr++) {
 		struct phy_device *phydev = mdiobus_get_phy(new_bus, addr);
 
 		if (!phydev)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index 6a393b16a1fc..c54a50dbd5ac 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -303,7 +303,7 @@ static void stmmac_pci_remove(struct pci_dev *pdev)
 	pci_disable_device(pdev);
 }
 
-static int stmmac_pci_suspend(struct device *dev)
+static int __maybe_unused stmmac_pci_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	int ret;
@@ -321,7 +321,7 @@ static int stmmac_pci_suspend(struct device *dev)
 	return 0;
 }
 
-static int stmmac_pci_resume(struct device *dev)
+static int __maybe_unused stmmac_pci_resume(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	int ret;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 72da77b94ecd..3609c7b696c7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -486,6 +486,12 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 		plat->force_sf_dma_mode = 1;
 	}
 
+	if (of_device_is_compatible(np, "snps,dwxgmac")) {
+		plat->has_xgmac = 1;
+		plat->pmt = 1;
+		plat->tso_en = of_property_read_bool(np, "snps,tso");
+	}
+
 	dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg),
 			       GFP_KERNEL);
 	if (!dma_cfg) {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index 0cb0e39a2be9..2293e21f789f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -71,6 +71,9 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta)
 	u32 sec, nsec;
 	u32 quotient, reminder;
 	int neg_adj = 0;
+	bool xmac;
+
+	xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
 
 	if (delta < 0) {
 		neg_adj = 1;
@@ -82,8 +85,7 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta)
 	nsec = reminder;
 
 	spin_lock_irqsave(&priv->ptp_lock, flags);
-	stmmac_adjust_systime(priv, priv->ptpaddr, sec, nsec, neg_adj,
-			priv->plat->has_gmac4);
+	stmmac_adjust_systime(priv, priv->ptpaddr, sec, nsec, neg_adj, xmac);
 	spin_unlock_irqrestore(&priv->ptp_lock, flags);
 
 	return 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
index f4b31d69f60e..ecccf895fd7e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
@@ -21,6 +21,7 @@
 #ifndef	__STMMAC_PTP_H__
 #define	__STMMAC_PTP_H__
 
+#define PTP_XGMAC_OFFSET	0xd00
 #define	PTP_GMAC4_OFFSET	0xb00
 #define	PTP_GMAC3_X_OFFSET	0x700
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index 2258cd8cc844..1a96dd9c1091 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -289,7 +289,67 @@ static int tc_init(struct stmmac_priv *priv)
 	return 0;
 }
 
+static int tc_setup_cbs(struct stmmac_priv *priv,
+			struct tc_cbs_qopt_offload *qopt)
+{
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
+	u32 queue = qopt->queue;
+	u32 ptr, speed_div;
+	u32 mode_to_use;
+	u64 value;
+	int ret;
+
+	/* Queue 0 is not AVB capable */
+	if (queue <= 0 || queue >= tx_queues_count)
+		return -EINVAL;
+	if (priv->speed != SPEED_100 && priv->speed != SPEED_1000)
+		return -EOPNOTSUPP;
+
+	mode_to_use = priv->plat->tx_queues_cfg[queue].mode_to_use;
+	if (mode_to_use == MTL_QUEUE_DCB && qopt->enable) {
+		ret = stmmac_dma_qmode(priv, priv->ioaddr, queue, MTL_QUEUE_AVB);
+		if (ret)
+			return ret;
+
+		priv->plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_AVB;
+	} else if (!qopt->enable) {
+		return stmmac_dma_qmode(priv, priv->ioaddr, queue, MTL_QUEUE_DCB);
+	}
+
+	/* Port Transmit Rate and Speed Divider */
+	ptr = (priv->speed == SPEED_100) ? 4 : 8;
+	speed_div = (priv->speed == SPEED_100) ? 100000 : 1000000;
+
+	/* Final adjustments for HW */
+	value = div_s64(qopt->idleslope * 1024ll * ptr, speed_div);
+	priv->plat->tx_queues_cfg[queue].idle_slope = value & GENMASK(31, 0);
+
+	value = div_s64(-qopt->sendslope * 1024ll * ptr, speed_div);
+	priv->plat->tx_queues_cfg[queue].send_slope = value & GENMASK(31, 0);
+
+	value = qopt->hicredit * 1024ll * 8;
+	priv->plat->tx_queues_cfg[queue].high_credit = value & GENMASK(31, 0);
+
+	value = qopt->locredit * 1024ll * 8;
+	priv->plat->tx_queues_cfg[queue].low_credit = value & GENMASK(31, 0);
+
+	ret = stmmac_config_cbs(priv, priv->hw,
+				priv->plat->tx_queues_cfg[queue].send_slope,
+				priv->plat->tx_queues_cfg[queue].idle_slope,
+				priv->plat->tx_queues_cfg[queue].high_credit,
+				priv->plat->tx_queues_cfg[queue].low_credit,
+				queue);
+	if (ret)
+		return ret;
+
+	dev_info(priv->device, "CBS queue %d: send %d, idle %d, hi %d, lo %d\n",
+			queue, qopt->sendslope, qopt->idleslope,
+			qopt->hicredit, qopt->locredit);
+	return 0;
+}
+
 const struct stmmac_tc_ops dwmac510_tc_ops = {
 	.init = tc_init,
 	.setup_cls_u32 = tc_setup_cls_u32,
+	.setup_cbs = tc_setup_cbs,
 };
diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c
index a5dd627fe2f9..d42f47f6c632 100644
--- a/drivers/net/ethernet/sun/ldmvsw.c
+++ b/drivers/net/ethernet/sun/ldmvsw.c
@@ -101,7 +101,8 @@ static struct vnet_port *vsw_tx_port_find(struct sk_buff *skb,
 }
 
 static u16 vsw_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    void *accel_priv, select_queue_fallback_t fallback)
+			    struct net_device *sb_dev,
+			    select_queue_fallback_t fallback)
 {
 	struct vnet_port *port = netdev_priv(dev);
 
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 88c12474a0c3..9319d84bf49f 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -1225,25 +1225,9 @@ static int link_status_1g_rgmii(struct niu *np, int *link_up_p)
 
 	bmsr = err;
 	if (bmsr & BMSR_LSTATUS) {
-		u16 adv, lpa;
-
-		err = mii_read(np, np->phy_addr, MII_ADVERTISE);
-		if (err < 0)
-			goto out;
-		adv = err;
-
-		err = mii_read(np, np->phy_addr, MII_LPA);
-		if (err < 0)
-			goto out;
-		lpa = err;
-
-		err = mii_read(np, np->phy_addr, MII_ESTATUS);
-		if (err < 0)
-			goto out;
 		link_up = 1;
 		current_speed = SPEED_1000;
 		current_duplex = DUPLEX_FULL;
-
 	}
 	lp->active_speed = current_speed;
 	lp->active_duplex = current_duplex;
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index a94f50442613..12539b357a78 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -234,7 +234,8 @@ static struct vnet_port *vnet_tx_port_find(struct sk_buff *skb,
 }
 
 static u16 vnet_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     void *accel_priv, select_queue_fallback_t fallback)
+			     struct net_device *sb_dev,
+			     select_queue_fallback_t fallback)
 {
 	struct vnet *vp = netdev_priv(dev);
 	struct vnet_port *port = __tx_port_find(vp, skb);
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c
index 458a7844260a..99d86e39ff54 100644
--- a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c
@@ -20,6 +20,7 @@
 #include <linux/clk.h>
 #include <linux/bitrev.h>
 #include <linux/crc32.h>
+#include <linux/crc32poly.h>
 #include <linux/dcbnl.h>
 
 #include "dwc-xlgmac.h"
@@ -193,7 +194,6 @@ static u32 xlgmac_vid_crc32_le(__le16 vid_le)
 {
 	unsigned char *data = (unsigned char *)&vid_le;
 	unsigned char data_byte = 0;
-	u32 poly = 0xedb88320;
 	u32 crc = ~0;
 	u32 temp = 0;
 	int i, bits;
@@ -208,7 +208,7 @@ static u32 xlgmac_vid_crc32_le(__le16 vid_le)
 		data_byte >>= 1;
 
 		if (temp)
-			crc ^= poly;
+			crc ^= CRC32_POLY_LE;
 	}
 
 	return crc;
diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index 163d8d16bc24..dc966ddb6d81 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -1151,7 +1151,6 @@ static void bdx_recycle_skb(struct bdx_priv *priv, struct rxd_desc *rxdd)
 	struct rx_map *dm;
 	struct rxf_fifo *f;
 	struct rxdb *db;
-	struct sk_buff *skb;
 	int delta;
 
 	ENTER;
@@ -1161,7 +1160,6 @@ static void bdx_recycle_skb(struct bdx_priv *priv, struct rxd_desc *rxdd)
 	DBG("db=%p f=%p\n", db, f);
 	dm = bdx_rxdb_addr_elem(db, rxdd->va_lo);
 	DBG("dm=%p\n", dm);
-	skb = dm->skb;
 	rxfd = (struct rxf_desc *)(f->m.va + f->m.wptr);
 	rxfd->info = CPU_CHIP_SWAP32(0x10003);	/* INFO=1 BC=3 */
 	rxfd->va_lo = rxdd->va_lo;
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 3e34cb8ac1d3..832bce07c385 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -39,12 +39,15 @@
 #include <linux/sys_soc.h>
 
 #include <linux/pinctrl/consumer.h>
+#include <net/pkt_cls.h>
 
 #include "cpsw.h"
 #include "cpsw_ale.h"
 #include "cpts.h"
 #include "davinci_cpdma.h"
 
+#include <net/pkt_sched.h>
+
 #define CPSW_DEBUG	(NETIF_MSG_HW		| NETIF_MSG_WOL		| \
 			 NETIF_MSG_DRV		| NETIF_MSG_LINK	| \
 			 NETIF_MSG_IFUP		| NETIF_MSG_INTR	| \
@@ -153,6 +156,12 @@ do {								\
 #define IRQ_NUM			2
 #define CPSW_MAX_QUEUES		8
 #define CPSW_CPDMA_DESCS_POOL_SIZE_DEFAULT 256
+#define CPSW_FIFO_QUEUE_TYPE_SHIFT	16
+#define CPSW_FIFO_SHAPE_EN_SHIFT	16
+#define CPSW_FIFO_RATE_EN_SHIFT		20
+#define CPSW_TC_NUM			4
+#define CPSW_FIFO_SHAPERS_NUM		(CPSW_TC_NUM - 1)
+#define CPSW_PCT_MASK			0x7f
 
 #define CPSW_RX_VLAN_ENCAP_HDR_PRIO_SHIFT	29
 #define CPSW_RX_VLAN_ENCAP_HDR_PRIO_MSK		GENMASK(2, 0)
@@ -253,23 +262,24 @@ struct cpsw_ss_regs {
 #define RX_DSCP_PRI_MAP7    0x4c /* Rx DSCP Priority to Rx Packet Mapping */
 
 /* Bit definitions for the CPSW2_CONTROL register */
-#define PASS_PRI_TAGGED     (1<<24) /* Pass Priority Tagged */
-#define VLAN_LTYPE2_EN      (1<<21) /* VLAN LTYPE 2 enable */
-#define VLAN_LTYPE1_EN      (1<<20) /* VLAN LTYPE 1 enable */
-#define DSCP_PRI_EN         (1<<16) /* DSCP Priority Enable */
-#define TS_320              (1<<14) /* Time Sync Dest Port 320 enable */
-#define TS_319              (1<<13) /* Time Sync Dest Port 319 enable */
-#define TS_132              (1<<12) /* Time Sync Dest IP Addr 132 enable */
-#define TS_131              (1<<11) /* Time Sync Dest IP Addr 131 enable */
-#define TS_130              (1<<10) /* Time Sync Dest IP Addr 130 enable */
-#define TS_129              (1<<9)  /* Time Sync Dest IP Addr 129 enable */
-#define TS_TTL_NONZERO      (1<<8)  /* Time Sync Time To Live Non-zero enable */
-#define TS_ANNEX_F_EN       (1<<6)  /* Time Sync Annex F enable */
-#define TS_ANNEX_D_EN       (1<<4)  /* Time Sync Annex D enable */
-#define TS_LTYPE2_EN        (1<<3)  /* Time Sync LTYPE 2 enable */
-#define TS_LTYPE1_EN        (1<<2)  /* Time Sync LTYPE 1 enable */
-#define TS_TX_EN            (1<<1)  /* Time Sync Transmit Enable */
-#define TS_RX_EN            (1<<0)  /* Time Sync Receive Enable */
+#define PASS_PRI_TAGGED     BIT(24) /* Pass Priority Tagged */
+#define VLAN_LTYPE2_EN      BIT(21) /* VLAN LTYPE 2 enable */
+#define VLAN_LTYPE1_EN      BIT(20) /* VLAN LTYPE 1 enable */
+#define DSCP_PRI_EN         BIT(16) /* DSCP Priority Enable */
+#define TS_107              BIT(15) /* Tyme Sync Dest IP Address 107 */
+#define TS_320              BIT(14) /* Time Sync Dest Port 320 enable */
+#define TS_319              BIT(13) /* Time Sync Dest Port 319 enable */
+#define TS_132              BIT(12) /* Time Sync Dest IP Addr 132 enable */
+#define TS_131              BIT(11) /* Time Sync Dest IP Addr 131 enable */
+#define TS_130              BIT(10) /* Time Sync Dest IP Addr 130 enable */
+#define TS_129              BIT(9)  /* Time Sync Dest IP Addr 129 enable */
+#define TS_TTL_NONZERO      BIT(8)  /* Time Sync Time To Live Non-zero enable */
+#define TS_ANNEX_F_EN       BIT(6)  /* Time Sync Annex F enable */
+#define TS_ANNEX_D_EN       BIT(4)  /* Time Sync Annex D enable */
+#define TS_LTYPE2_EN        BIT(3)  /* Time Sync LTYPE 2 enable */
+#define TS_LTYPE1_EN        BIT(2)  /* Time Sync LTYPE 1 enable */
+#define TS_TX_EN            BIT(1)  /* Time Sync Transmit Enable */
+#define TS_RX_EN            BIT(0)  /* Time Sync Receive Enable */
 
 #define CTRL_V2_TS_BITS \
 	(TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 |\
@@ -281,7 +291,7 @@ struct cpsw_ss_regs {
 
 
 #define CTRL_V3_TS_BITS \
-	(TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 |\
+	(TS_107 | TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 |\
 	 TS_TTL_NONZERO | TS_ANNEX_F_EN | TS_ANNEX_D_EN |\
 	 TS_LTYPE1_EN)
 
@@ -453,6 +463,9 @@ struct cpsw_priv {
 	u8				mac_addr[ETH_ALEN];
 	bool				rx_pause;
 	bool				tx_pause;
+	bool				mqprio_hw;
+	int				fifo_bw[CPSW_TC_NUM];
+	int				shp_cfg_speed;
 	u32 emac_port;
 	struct cpsw_common *cpsw;
 };
@@ -552,40 +565,28 @@ static const struct cpsw_stats cpsw_gstrings_ch_stats[] = {
 				(func)(slave++, ##arg);			\
 	} while (0)
 
-#define cpsw_dual_emac_src_port_detect(cpsw, status, ndev, skb)		\
-	do {								\
-		if (!cpsw->data.dual_emac)				\
-			break;						\
-		if (CPDMA_RX_SOURCE_PORT(status) == 1) {		\
-			ndev = cpsw->slaves[0].ndev;			\
-			skb->dev = ndev;				\
-		} else if (CPDMA_RX_SOURCE_PORT(status) == 2) {		\
-			ndev = cpsw->slaves[1].ndev;			\
-			skb->dev = ndev;				\
-		}							\
-	} while (0)
-#define cpsw_add_mcast(cpsw, priv, addr)				\
-	do {								\
-		if (cpsw->data.dual_emac) {				\
-			struct cpsw_slave *slave = cpsw->slaves +	\
-						priv->emac_port;	\
-			int slave_port = cpsw_get_slave_port(		\
-						slave->slave_num);	\
-			cpsw_ale_add_mcast(cpsw->ale, addr,		\
-				1 << slave_port | ALE_PORT_HOST,	\
-				ALE_VLAN, slave->port_vlan, 0);		\
-		} else {						\
-			cpsw_ale_add_mcast(cpsw->ale, addr,		\
-				ALE_ALL_PORTS,				\
-				0, 0, 0);				\
-		}							\
-	} while (0)
-
 static inline int cpsw_get_slave_port(u32 slave_num)
 {
 	return slave_num + 1;
 }
 
+static void cpsw_add_mcast(struct cpsw_priv *priv, u8 *addr)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+
+	if (cpsw->data.dual_emac) {
+		struct cpsw_slave *slave = cpsw->slaves + priv->emac_port;
+		int slave_port = cpsw_get_slave_port(slave->slave_num);
+
+		cpsw_ale_add_mcast(cpsw->ale, addr,
+				   1 << slave_port | ALE_PORT_HOST,
+				   ALE_VLAN, slave->port_vlan, 0);
+		return;
+	}
+
+	cpsw_ale_add_mcast(cpsw->ale, addr, ALE_ALL_PORTS, 0, 0, 0);
+}
+
 static void cpsw_set_promiscious(struct net_device *ndev, bool enable)
 {
 	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
@@ -693,7 +694,7 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
 
 		/* program multicast address list into ALE register */
 		netdev_for_each_mc_addr(ha, ndev) {
-			cpsw_add_mcast(cpsw, priv, (u8 *)ha->addr);
+			cpsw_add_mcast(priv, ha->addr);
 		}
 	}
 }
@@ -785,10 +786,16 @@ static void cpsw_rx_handler(void *token, int len, int status)
 	struct sk_buff		*skb = token;
 	struct sk_buff		*new_skb;
 	struct net_device	*ndev = skb->dev;
-	int			ret = 0;
+	int			ret = 0, port;
 	struct cpsw_common	*cpsw = ndev_to_cpsw(ndev);
 
-	cpsw_dual_emac_src_port_detect(cpsw, status, ndev, skb);
+	if (cpsw->data.dual_emac) {
+		port = CPDMA_RX_SOURCE_PORT(status);
+		if (port) {
+			ndev = cpsw->slaves[--port].ndev;
+			skb->dev = ndev;
+		}
+	}
 
 	if (unlikely(status < 0) || unlikely(!netif_running(ndev))) {
 		/* In dual emac mode check for all interfaces */
@@ -967,8 +974,8 @@ static int cpsw_tx_mq_poll(struct napi_struct *napi_tx, int budget)
 
 	/* process every unprocessed channel */
 	ch_map = cpdma_ctrl_txchs_state(cpsw->dma);
-	for (ch = 0, num_tx = 0; ch_map; ch_map >>= 1, ch++) {
-		if (!(ch_map & 0x01))
+	for (ch = 0, num_tx = 0; ch_map & 0xff; ch_map <<= 1, ch++) {
+		if (!(ch_map & 0x80))
 			continue;
 
 		txv = &cpsw->txv[ch];
@@ -1077,6 +1084,38 @@ static void cpsw_set_slave_mac(struct cpsw_slave *slave,
 	slave_write(slave, mac_lo(priv->mac_addr), SA_LO);
 }
 
+static bool cpsw_shp_is_off(struct cpsw_priv *priv)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct cpsw_slave *slave;
+	u32 shift, mask, val;
+
+	val = readl_relaxed(&cpsw->regs->ptype);
+
+	slave = &cpsw->slaves[cpsw_slave_index(cpsw, priv)];
+	shift = CPSW_FIFO_SHAPE_EN_SHIFT + 3 * slave->slave_num;
+	mask = 7 << shift;
+	val = val & mask;
+
+	return !val;
+}
+
+static void cpsw_fifo_shp_on(struct cpsw_priv *priv, int fifo, int on)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct cpsw_slave *slave;
+	u32 shift, mask, val;
+
+	val = readl_relaxed(&cpsw->regs->ptype);
+
+	slave = &cpsw->slaves[cpsw_slave_index(cpsw, priv)];
+	shift = CPSW_FIFO_SHAPE_EN_SHIFT + 3 * slave->slave_num;
+	mask = (1 << --fifo) << shift;
+	val = on ? val | mask : val & ~mask;
+
+	writel_relaxed(val, &cpsw->regs->ptype);
+}
+
 static void _cpsw_adjust_link(struct cpsw_slave *slave,
 			      struct cpsw_priv *priv, bool *link)
 {
@@ -1116,6 +1155,12 @@ static void _cpsw_adjust_link(struct cpsw_slave *slave,
 			mac_control |= BIT(4);
 
 		*link = true;
+
+		if (priv->shp_cfg_speed &&
+		    priv->shp_cfg_speed != slave->phy->speed &&
+		    !cpsw_shp_is_off(priv))
+			dev_warn(priv->dev,
+				 "Speed was changed, CBS shaper speeds are changed!");
 	} else {
 		mac_control = 0;
 		/* disable forwarding */
@@ -1577,6 +1622,231 @@ static void cpsw_slave_stop(struct cpsw_slave *slave, struct cpsw_common *cpsw)
 	soft_reset_slave(slave);
 }
 
+static int cpsw_tc_to_fifo(int tc, int num_tc)
+{
+	if (tc == num_tc - 1)
+		return 0;
+
+	return CPSW_FIFO_SHAPERS_NUM - tc;
+}
+
+static int cpsw_set_fifo_bw(struct cpsw_priv *priv, int fifo, int bw)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	u32 val = 0, send_pct, shift;
+	struct cpsw_slave *slave;
+	int pct = 0, i;
+
+	if (bw > priv->shp_cfg_speed * 1000)
+		goto err;
+
+	/* shaping has to stay enabled for highest fifos linearly
+	 * and fifo bw no more then interface can allow
+	 */
+	slave = &cpsw->slaves[cpsw_slave_index(cpsw, priv)];
+	send_pct = slave_read(slave, SEND_PERCENT);
+	for (i = CPSW_FIFO_SHAPERS_NUM; i > 0; i--) {
+		if (!bw) {
+			if (i >= fifo || !priv->fifo_bw[i])
+				continue;
+
+			dev_warn(priv->dev, "Prev FIFO%d is shaped", i);
+			continue;
+		}
+
+		if (!priv->fifo_bw[i] && i > fifo) {
+			dev_err(priv->dev, "Upper FIFO%d is not shaped", i);
+			return -EINVAL;
+		}
+
+		shift = (i - 1) * 8;
+		if (i == fifo) {
+			send_pct &= ~(CPSW_PCT_MASK << shift);
+			val = DIV_ROUND_UP(bw, priv->shp_cfg_speed * 10);
+			if (!val)
+				val = 1;
+
+			send_pct |= val << shift;
+			pct += val;
+			continue;
+		}
+
+		if (priv->fifo_bw[i])
+			pct += (send_pct >> shift) & CPSW_PCT_MASK;
+	}
+
+	if (pct >= 100)
+		goto err;
+
+	slave_write(slave, send_pct, SEND_PERCENT);
+	priv->fifo_bw[fifo] = bw;
+
+	dev_warn(priv->dev, "set FIFO%d bw = %d\n", fifo,
+		 DIV_ROUND_CLOSEST(val * priv->shp_cfg_speed, 100));
+
+	return 0;
+err:
+	dev_err(priv->dev, "Bandwidth doesn't fit in tc configuration");
+	return -EINVAL;
+}
+
+static int cpsw_set_fifo_rlimit(struct cpsw_priv *priv, int fifo, int bw)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct cpsw_slave *slave;
+	u32 tx_in_ctl_rg, val;
+	int ret;
+
+	ret = cpsw_set_fifo_bw(priv, fifo, bw);
+	if (ret)
+		return ret;
+
+	slave = &cpsw->slaves[cpsw_slave_index(cpsw, priv)];
+	tx_in_ctl_rg = cpsw->version == CPSW_VERSION_1 ?
+		       CPSW1_TX_IN_CTL : CPSW2_TX_IN_CTL;
+
+	if (!bw)
+		cpsw_fifo_shp_on(priv, fifo, bw);
+
+	val = slave_read(slave, tx_in_ctl_rg);
+	if (cpsw_shp_is_off(priv)) {
+		/* disable FIFOs rate limited queues */
+		val &= ~(0xf << CPSW_FIFO_RATE_EN_SHIFT);
+
+		/* set type of FIFO queues to normal priority mode */
+		val &= ~(3 << CPSW_FIFO_QUEUE_TYPE_SHIFT);
+
+		/* set type of FIFO queues to be rate limited */
+		if (bw)
+			val |= 2 << CPSW_FIFO_QUEUE_TYPE_SHIFT;
+		else
+			priv->shp_cfg_speed = 0;
+	}
+
+	/* toggle a FIFO rate limited queue */
+	if (bw)
+		val |= BIT(fifo + CPSW_FIFO_RATE_EN_SHIFT);
+	else
+		val &= ~BIT(fifo + CPSW_FIFO_RATE_EN_SHIFT);
+	slave_write(slave, val, tx_in_ctl_rg);
+
+	/* FIFO transmit shape enable */
+	cpsw_fifo_shp_on(priv, fifo, bw);
+	return 0;
+}
+
+/* Defaults:
+ * class A - prio 3
+ * class B - prio 2
+ * shaping for class A should be set first
+ */
+static int cpsw_set_cbs(struct net_device *ndev,
+			struct tc_cbs_qopt_offload *qopt)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct cpsw_slave *slave;
+	int prev_speed = 0;
+	int tc, ret, fifo;
+	u32 bw = 0;
+
+	tc = netdev_txq_to_tc(priv->ndev, qopt->queue);
+
+	/* enable channels in backward order, as highest FIFOs must be rate
+	 * limited first and for compliance with CPDMA rate limited channels
+	 * that also used in bacward order. FIFO0 cannot be rate limited.
+	 */
+	fifo = cpsw_tc_to_fifo(tc, ndev->num_tc);
+	if (!fifo) {
+		dev_err(priv->dev, "Last tc%d can't be rate limited", tc);
+		return -EINVAL;
+	}
+
+	/* do nothing, it's disabled anyway */
+	if (!qopt->enable && !priv->fifo_bw[fifo])
+		return 0;
+
+	/* shapers can be set if link speed is known */
+	slave = &cpsw->slaves[cpsw_slave_index(cpsw, priv)];
+	if (slave->phy && slave->phy->link) {
+		if (priv->shp_cfg_speed &&
+		    priv->shp_cfg_speed != slave->phy->speed)
+			prev_speed = priv->shp_cfg_speed;
+
+		priv->shp_cfg_speed = slave->phy->speed;
+	}
+
+	if (!priv->shp_cfg_speed) {
+		dev_err(priv->dev, "Link speed is not known");
+		return -1;
+	}
+
+	ret = pm_runtime_get_sync(cpsw->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(cpsw->dev);
+		return ret;
+	}
+
+	bw = qopt->enable ? qopt->idleslope : 0;
+	ret = cpsw_set_fifo_rlimit(priv, fifo, bw);
+	if (ret) {
+		priv->shp_cfg_speed = prev_speed;
+		prev_speed = 0;
+	}
+
+	if (bw && prev_speed)
+		dev_warn(priv->dev,
+			 "Speed was changed, CBS shaper speeds are changed!");
+
+	pm_runtime_put_sync(cpsw->dev);
+	return ret;
+}
+
+static void cpsw_cbs_resume(struct cpsw_slave *slave, struct cpsw_priv *priv)
+{
+	int fifo, bw;
+
+	for (fifo = CPSW_FIFO_SHAPERS_NUM; fifo > 0; fifo--) {
+		bw = priv->fifo_bw[fifo];
+		if (!bw)
+			continue;
+
+		cpsw_set_fifo_rlimit(priv, fifo, bw);
+	}
+}
+
+static void cpsw_mqprio_resume(struct cpsw_slave *slave, struct cpsw_priv *priv)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	u32 tx_prio_map = 0;
+	int i, tc, fifo;
+	u32 tx_prio_rg;
+
+	if (!priv->mqprio_hw)
+		return;
+
+	for (i = 0; i < 8; i++) {
+		tc = netdev_get_prio_tc_map(priv->ndev, i);
+		fifo = CPSW_FIFO_SHAPERS_NUM - tc;
+		tx_prio_map |= fifo << (4 * i);
+	}
+
+	tx_prio_rg = cpsw->version == CPSW_VERSION_1 ?
+		     CPSW1_TX_PRI_MAP : CPSW2_TX_PRI_MAP;
+
+	slave_write(slave, tx_prio_map, tx_prio_rg);
+}
+
+/* restore resources after port reset */
+static void cpsw_restore(struct cpsw_priv *priv)
+{
+	/* restore MQPRIO offload */
+	for_each_slave(priv, cpsw_mqprio_resume, priv);
+
+	/* restore CBS offload */
+	for_each_slave(priv, cpsw_cbs_resume, priv);
+}
+
 static int cpsw_ndo_open(struct net_device *ndev)
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
@@ -1656,6 +1926,8 @@ static int cpsw_ndo_open(struct net_device *ndev)
 
 	}
 
+	cpsw_restore(priv);
+
 	/* Enable Interrupt pacing if configured */
 	if (cpsw->coal_intvl != 0) {
 		struct ethtool_coalesce coal;
@@ -2187,6 +2459,78 @@ static int cpsw_ndo_set_tx_maxrate(struct net_device *ndev, int queue, u32 rate)
 	return ret;
 }
 
+static int cpsw_set_mqprio(struct net_device *ndev, void *type_data)
+{
+	struct tc_mqprio_qopt_offload *mqprio = type_data;
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int fifo, num_tc, count, offset;
+	struct cpsw_slave *slave;
+	u32 tx_prio_map = 0;
+	int i, tc, ret;
+
+	num_tc = mqprio->qopt.num_tc;
+	if (num_tc > CPSW_TC_NUM)
+		return -EINVAL;
+
+	if (mqprio->mode != TC_MQPRIO_MODE_DCB)
+		return -EINVAL;
+
+	ret = pm_runtime_get_sync(cpsw->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(cpsw->dev);
+		return ret;
+	}
+
+	if (num_tc) {
+		for (i = 0; i < 8; i++) {
+			tc = mqprio->qopt.prio_tc_map[i];
+			fifo = cpsw_tc_to_fifo(tc, num_tc);
+			tx_prio_map |= fifo << (4 * i);
+		}
+
+		netdev_set_num_tc(ndev, num_tc);
+		for (i = 0; i < num_tc; i++) {
+			count = mqprio->qopt.count[i];
+			offset = mqprio->qopt.offset[i];
+			netdev_set_tc_queue(ndev, i, count, offset);
+		}
+	}
+
+	if (!mqprio->qopt.hw) {
+		/* restore default configuration */
+		netdev_reset_tc(ndev);
+		tx_prio_map = TX_PRIORITY_MAPPING;
+	}
+
+	priv->mqprio_hw = mqprio->qopt.hw;
+
+	offset = cpsw->version == CPSW_VERSION_1 ?
+		 CPSW1_TX_PRI_MAP : CPSW2_TX_PRI_MAP;
+
+	slave = &cpsw->slaves[cpsw_slave_index(cpsw, priv)];
+	slave_write(slave, tx_prio_map, offset);
+
+	pm_runtime_put_sync(cpsw->dev);
+
+	return 0;
+}
+
+static int cpsw_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
+			     void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_QDISC_CBS:
+		return cpsw_set_cbs(ndev, type_data);
+
+	case TC_SETUP_QDISC_MQPRIO:
+		return cpsw_set_mqprio(ndev, type_data);
+
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static const struct net_device_ops cpsw_netdev_ops = {
 	.ndo_open		= cpsw_ndo_open,
 	.ndo_stop		= cpsw_ndo_stop,
@@ -2202,6 +2546,7 @@ static const struct net_device_ops cpsw_netdev_ops = {
 #endif
 	.ndo_vlan_rx_add_vid	= cpsw_ndo_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= cpsw_ndo_vlan_rx_kill_vid,
+	.ndo_setup_tc           = cpsw_ndo_setup_tc,
 };
 
 static int cpsw_get_regs_len(struct net_device *ndev)
@@ -2428,7 +2773,7 @@ static int cpsw_update_channels_res(struct cpsw_priv *priv, int ch_num, int rx)
 	void (*handler)(void *, int, int);
 	struct netdev_queue *queue;
 	struct cpsw_vector *vec;
-	int ret, *ch;
+	int ret, *ch, vch;
 
 	if (rx) {
 		ch = &cpsw->rx_ch_num;
@@ -2441,7 +2786,8 @@ static int cpsw_update_channels_res(struct cpsw_priv *priv, int ch_num, int rx)
 	}
 
 	while (*ch < ch_num) {
-		vec[*ch].ch = cpdma_chan_create(cpsw->dma, *ch, handler, rx);
+		vch = rx ? *ch : 7 - *ch;
+		vec[*ch].ch = cpdma_chan_create(cpsw->dma, vch, handler, rx);
 		queue = netdev_get_tx_queue(priv->ndev, *ch);
 		queue->tx_maxrate = 0;
 
@@ -2924,7 +3270,7 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv)
 		dev_info(cpsw->dev, "cpsw: Detected MACID = %pM\n",
 			 priv_sl2->mac_addr);
 	} else {
-		random_ether_addr(priv_sl2->mac_addr);
+		eth_random_addr(priv_sl2->mac_addr);
 		dev_info(cpsw->dev, "cpsw: Random MACID = %pM\n",
 			 priv_sl2->mac_addr);
 	}
@@ -2932,7 +3278,7 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv)
 
 	priv_sl2->emac_port = 1;
 	cpsw->slaves[1].ndev = ndev;
-	ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+	ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
 
 	ndev->netdev_ops = &cpsw_netdev_ops;
 	ndev->ethtool_ops = &cpsw_ethtool_ops;
@@ -2978,7 +3324,7 @@ static int cpsw_probe(struct platform_device *pdev)
 	u32 slave_offset, sliver_offset, slave_size;
 	const struct soc_device_attribute *soc;
 	struct cpsw_common		*cpsw;
-	int ret = 0, i;
+	int ret = 0, i, ch;
 	int irq;
 
 	cpsw = devm_kzalloc(&pdev->dev, sizeof(struct cpsw_common), GFP_KERNEL);
@@ -3153,7 +3499,8 @@ static int cpsw_probe(struct platform_device *pdev)
 	if (soc)
 		cpsw->quirk_irq = 1;
 
-	cpsw->txv[0].ch = cpdma_chan_create(cpsw->dma, 0, cpsw_tx_handler, 0);
+	ch = cpsw->quirk_irq ? 0 : 7;
+	cpsw->txv[0].ch = cpdma_chan_create(cpsw->dma, ch, cpsw_tx_handler, 0);
 	if (IS_ERR(cpsw->txv[0].ch)) {
 		dev_err(priv->dev, "error initializing tx dma channel\n");
 		ret = PTR_ERR(cpsw->txv[0].ch);
diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index 6f63c8729afc..b96b93c686bf 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -114,7 +114,10 @@ static bool cpts_match_tx_ts(struct cpts *cpts, struct cpts_event *event)
 			dev_consume_skb_any(skb);
 			dev_dbg(cpts->dev, "match tx timestamp mtype %u seqid %04x\n",
 				mtype, seqid);
-		} else if (time_after(jiffies, skb_cb->tmo)) {
+			break;
+		}
+
+		if (time_after(jiffies, skb_cb->tmo)) {
 			/* timeout any expired skbs over 1s */
 			dev_dbg(cpts->dev,
 				"expiring tx timestamp mtype %u seqid %04x\n",
@@ -158,6 +161,7 @@ static int cpts_fifo_read(struct cpts *cpts, int match)
 				 */
 				break;
 			}
+			/* fall through */
 		case CPTS_EV_PUSH:
 		case CPTS_EV_RX:
 			list_del_init(&event->list);
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index 4f1267477aa4..4236dcdd5634 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -406,37 +406,36 @@ static int cpdma_chan_fit_rate(struct cpdma_chan *ch, u32 rate,
 	struct cpdma_chan *chan;
 	u32 old_rate = ch->rate;
 	u32 new_rmask = 0;
-	int rlim = 1;
+	int rlim = 0;
 	int i;
 
-	*prio_mode = 0;
 	for (i = tx_chan_num(0); i < tx_chan_num(CPDMA_MAX_CHANNELS); i++) {
 		chan = ctlr->channels[i];
-		if (!chan) {
-			rlim = 0;
+		if (!chan)
 			continue;
-		}
 
 		if (chan == ch)
 			chan->rate = rate;
 
 		if (chan->rate) {
-			if (rlim) {
-				new_rmask |= chan->mask;
-			} else {
-				ch->rate = old_rate;
-				dev_err(ctlr->dev, "Prev channel of %dch is not rate limited\n",
-					chan->chan_num);
-				return -EINVAL;
-			}
-		} else {
-			*prio_mode = 1;
-			rlim = 0;
+			rlim = 1;
+			new_rmask |= chan->mask;
+			continue;
 		}
+
+		if (rlim)
+			goto err;
 	}
 
 	*rmask = new_rmask;
+	*prio_mode = rlim;
 	return 0;
+
+err:
+	ch->rate = old_rate;
+	dev_err(ctlr->dev, "Upper cpdma ch%d is not rate limited\n",
+		chan->chan_num);
+	return -EINVAL;
 }
 
 static u32 cpdma_chan_set_factors(struct cpdma_ctlr *ctlr,
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index e40aa3e31af2..a1d335a3c5e4 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -1889,13 +1889,6 @@ static int netcp_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid)
 	return err;
 }
 
-static u16 netcp_select_queue(struct net_device *dev, struct sk_buff *skb,
-			      void *accel_priv,
-			      select_queue_fallback_t fallback)
-{
-	return 0;
-}
-
 static int netcp_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			  void *type_data)
 {
@@ -1972,7 +1965,7 @@ static const struct net_device_ops netcp_netdev_ops = {
 	.ndo_vlan_rx_add_vid	= netcp_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= netcp_rx_kill_vid,
 	.ndo_tx_timeout		= netcp_ndo_tx_timeout,
-	.ndo_select_queue	= netcp_select_queue,
+	.ndo_select_queue	= dev_pick_tx_zero,
 	.ndo_setup_tc		= netcp_setup_tc,
 };
 
@@ -2052,7 +2045,7 @@ static int netcp_create_interface(struct netcp_device *netcp_device,
 		if (is_valid_ether_addr(efuse_mac_addr))
 			ether_addr_copy(ndev->dev_addr, efuse_mac_addr);
 		else
-			random_ether_addr(ndev->dev_addr);
+			eth_random_addr(ndev->dev_addr);
 
 		devm_iounmap(dev, efuse);
 		devm_release_mem_region(dev, res.start, size);
@@ -2061,7 +2054,7 @@ static int netcp_create_interface(struct netcp_device *netcp_device,
 		if (mac_addr)
 			ether_addr_copy(ndev->dev_addr, mac_addr);
 		else
-			random_ether_addr(ndev->dev_addr);
+			eth_random_addr(ndev->dev_addr);
 	}
 
 	ret = of_property_read_string(node_interface, "rx-channel",
diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c
index c769cd9d11e7..93d142867c2a 100644
--- a/drivers/net/ethernet/ti/tlan.c
+++ b/drivers/net/ethernet/ti/tlan.c
@@ -966,6 +966,7 @@ static int tlan_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	switch (cmd) {
 	case SIOCGMIIPHY:		/* get address of MII PHY in use. */
 		data->phy_id = phy;
+		/* fall through */
 
 
 	case SIOCGMIIREG:		/* read MII PHY register. */
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index 2a0c06e0f730..42f1f518dad6 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -70,7 +70,8 @@
 #define XEL_TSR_XMIT_IE_MASK	 0x00000008	/* Tx interrupt enable bit */
 #define XEL_TSR_XMIT_ACTIVE_MASK 0x80000000	/* Buffer is active, SW bit
 						 * only. This is not documented
-						 * in the HW spec */
+						 * in the HW spec
+						 */
 
 /* Define for programming the MAC address into the EmacLite */
 #define XEL_TSR_PROG_MAC_ADDR	(XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_PROGRAM_MASK)
@@ -94,11 +95,11 @@
 
 
 
-#define TX_TIMEOUT		(60*HZ)		/* Tx timeout is 60 seconds. */
+#define TX_TIMEOUT		(60 * HZ)	/* Tx timeout is 60 seconds. */
 #define ALIGNMENT		4
 
 /* BUFFER_ALIGN(adr) calculates the number of bytes to the next alignment. */
-#define BUFFER_ALIGN(adr) ((ALIGNMENT - ((u32) adr)) % ALIGNMENT)
+#define BUFFER_ALIGN(adr) ((ALIGNMENT - ((u32)adr)) % ALIGNMENT)
 
 #ifdef __BIG_ENDIAN
 #define xemaclite_readl		ioread32be
@@ -238,8 +239,8 @@ static void xemaclite_aligned_write(void *src_ptr, u32 *dest_ptr,
 
 		/* Set up to output the remaining data */
 		align_buffer = 0;
-		to_u8_ptr = (u8 *) &align_buffer;
-		from_u8_ptr = (u8 *) from_u16_ptr;
+		to_u8_ptr = (u8 *)&align_buffer;
+		from_u8_ptr = (u8 *)from_u16_ptr;
 
 		/* Output the remaining data */
 		for (; length > 0; length--)
@@ -272,7 +273,7 @@ static void xemaclite_aligned_read(u32 *src_ptr, u8 *dest_ptr,
 	u32 align_buffer;
 
 	from_u32_ptr = src_ptr;
-	to_u16_ptr = (u16 *) dest_ptr;
+	to_u16_ptr = (u16 *)dest_ptr;
 
 	for (; length > 3; length -= 4) {
 		/* Copy each word into the temporary buffer */
@@ -288,9 +289,9 @@ static void xemaclite_aligned_read(u32 *src_ptr, u8 *dest_ptr,
 		u8 *to_u8_ptr, *from_u8_ptr;
 
 		/* Set up to read the remaining data */
-		to_u8_ptr = (u8 *) to_u16_ptr;
+		to_u8_ptr = (u8 *)to_u16_ptr;
 		align_buffer = *from_u32_ptr++;
-		from_u8_ptr = (u8 *) &align_buffer;
+		from_u8_ptr = (u8 *)&align_buffer;
 
 		/* Read the remaining data */
 		for (; length > 0; length--)
@@ -336,7 +337,8 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
 			drvdata->next_tx_buf_to_use ^= XEL_BUFFER_OFFSET;
 	} else if (drvdata->tx_ping_pong != 0) {
 		/* If the expected buffer is full, try the other buffer,
-		 * if it is configured in HW */
+		 * if it is configured in HW
+		 */
 
 		addr = (void __iomem __force *)((u32 __force)addr ^
 						 XEL_BUFFER_OFFSET);
@@ -349,7 +351,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
 		return -1; /* Buffer was full, return failure */
 
 	/* Write the frame to the buffer */
-	xemaclite_aligned_write(data, (u32 __force *) addr, byte_count);
+	xemaclite_aligned_write(data, (u32 __force *)addr, byte_count);
 
 	xemaclite_writel((byte_count & XEL_TPLR_LENGTH_MASK),
 			 addr + XEL_TPLR_OFFSET);
@@ -357,7 +359,8 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
 	/* Update the Tx Status Register to indicate that there is a
 	 * frame to send. Set the XEL_TSR_XMIT_ACTIVE_MASK flag which
 	 * is used by the interrupt handler to check whether a frame
-	 * has been transmitted */
+	 * has been transmitted
+	 */
 	reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
 	reg_data |= (XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_XMIT_ACTIVE_MASK);
 	xemaclite_writel(reg_data, addr + XEL_TSR_OFFSET);
@@ -369,6 +372,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
  * xemaclite_recv_data - Receive a frame
  * @drvdata:	Pointer to the Emaclite device private data
  * @data:	Address where the data is to be received
+ * @maxlen:    Maximum supported ethernet packet length
  *
  * This function is intended to be called from the interrupt context or
  * with a wrapper which waits for the receive frame to be available.
@@ -394,7 +398,8 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen)
 		/* The instance is out of sync, try other buffer if other
 		 * buffer is configured, return 0 otherwise. If the instance is
 		 * out of sync, do not update the 'next_rx_buf_to_use' since it
-		 * will correct on subsequent calls */
+		 * will correct on subsequent calls
+		 */
 		if (drvdata->rx_ping_pong != 0)
 			addr = (void __iomem __force *)((u32 __force)addr ^
 							 XEL_BUFFER_OFFSET);
@@ -408,13 +413,15 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen)
 			return 0;	/* No data was available */
 	}
 
-	/* Get the protocol type of the ethernet frame that arrived */
+	/* Get the protocol type of the ethernet frame that arrived
+	 */
 	proto_type = ((ntohl(xemaclite_readl(addr + XEL_HEADER_OFFSET +
 			XEL_RXBUFF_OFFSET)) >> XEL_HEADER_SHIFT) &
 			XEL_RPLR_LENGTH_MASK);
 
 	/* Check if received ethernet frame is a raw ethernet frame
-	 * or an IP packet or an ARP packet */
+	 * or an IP packet or an ARP packet
+	 */
 	if (proto_type > ETH_DATA_LEN) {
 
 		if (proto_type == ETH_P_IP) {
@@ -430,7 +437,8 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen)
 			length = XEL_ARP_PACKET_SIZE + ETH_HLEN + ETH_FCS_LEN;
 		else
 			/* Field contains type other than IP or ARP, use max
-			 * frame size and let user parse it */
+			 * frame size and let user parse it
+			 */
 			length = ETH_FRAME_LEN + ETH_FCS_LEN;
 	} else
 		/* Use the length in the frame, plus the header and trailer */
@@ -440,7 +448,7 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen)
 		length = maxlen;
 
 	/* Read from the EmacLite device */
-	xemaclite_aligned_read((u32 __force *) (addr + XEL_RXBUFF_OFFSET),
+	xemaclite_aligned_read((u32 __force *)(addr + XEL_RXBUFF_OFFSET),
 				data, length);
 
 	/* Acknowledge the frame */
@@ -471,7 +479,7 @@ static void xemaclite_update_address(struct net_local *drvdata,
 	/* Determine the expected Tx buffer address */
 	addr = drvdata->base_addr + drvdata->next_tx_buf_to_use;
 
-	xemaclite_aligned_write(address_ptr, (u32 __force *) addr, ETH_ALEN);
+	xemaclite_aligned_write(address_ptr, (u32 __force *)addr, ETH_ALEN);
 
 	xemaclite_writel(ETH_ALEN, addr + XEL_TPLR_OFFSET);
 
@@ -488,7 +496,7 @@ static void xemaclite_update_address(struct net_local *drvdata,
 /**
  * xemaclite_set_mac_address - Set the MAC address for this device
  * @dev:	Pointer to the network device instance
- * @addr:	Void pointer to the sockaddr structure
+ * @address:	Void pointer to the sockaddr structure
  *
  * This function copies the HW address from the sockaddr strucutre to the
  * net_device structure and updates the address in HW.
@@ -564,19 +572,19 @@ static void xemaclite_tx_handler(struct net_device *dev)
 	struct net_local *lp = netdev_priv(dev);
 
 	dev->stats.tx_packets++;
-	if (lp->deferred_skb) {
-		if (xemaclite_send_data(lp,
-					(u8 *) lp->deferred_skb->data,
-					lp->deferred_skb->len) != 0)
-			return;
-		else {
-			dev->stats.tx_bytes += lp->deferred_skb->len;
-			dev_kfree_skb_irq(lp->deferred_skb);
-			lp->deferred_skb = NULL;
-			netif_trans_update(dev); /* prevent tx timeout */
-			netif_wake_queue(dev);
-		}
-	}
+
+	if (!lp->deferred_skb)
+		return;
+
+	if (xemaclite_send_data(lp, (u8 *)lp->deferred_skb->data,
+				lp->deferred_skb->len))
+		return;
+
+	dev->stats.tx_bytes += lp->deferred_skb->len;
+	dev_kfree_skb_irq(lp->deferred_skb);
+	lp->deferred_skb = NULL;
+	netif_trans_update(dev); /* prevent tx timeout */
+	netif_wake_queue(dev);
 }
 
 /**
@@ -602,18 +610,18 @@ static void xemaclite_rx_handler(struct net_device *dev)
 		return;
 	}
 
-	/*
-	 * A new skb should have the data halfword aligned, but this code is
+	/* A new skb should have the data halfword aligned, but this code is
 	 * here just in case that isn't true. Calculate how many
 	 * bytes we should reserve to get the data to start on a word
-	 * boundary */
+	 * boundary
+	 */
 	align = BUFFER_ALIGN(skb->data);
 	if (align)
 		skb_reserve(skb, align);
 
 	skb_reserve(skb, 2);
 
-	len = xemaclite_recv_data(lp, (u8 *) skb->data, len);
+	len = xemaclite_recv_data(lp, (u8 *)skb->data, len);
 
 	if (!len) {
 		dev->stats.rx_errors++;
@@ -639,6 +647,8 @@ static void xemaclite_rx_handler(struct net_device *dev)
  * @dev_id:	Void pointer to the network device instance used as callback
  *		reference
  *
+ * Return:	IRQ_HANDLED
+ *
  * This function handles the Tx and Rx interrupts of the EmacLite device.
  */
 static irqreturn_t xemaclite_interrupt(int irq, void *dev_id)
@@ -706,8 +716,8 @@ static int xemaclite_mdio_wait(struct net_local *lp)
 	unsigned long end = jiffies + 2;
 
 	/* wait for the MDIO interface to not be busy or timeout
-	   after some time.
-	*/
+	 * after some time.
+	 */
 	while (xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) &
 			XEL_MDIOCTRL_MDIOSTS_MASK) {
 		if (time_before_eq(end, jiffies)) {
@@ -757,7 +767,7 @@ static int xemaclite_mdio_read(struct mii_bus *bus, int phy_id, int reg)
 	rc = xemaclite_readl(lp->base_addr + XEL_MDIORD_OFFSET);
 
 	dev_dbg(&lp->ndev->dev,
-		"xemaclite_mdio_read(phy_id=%i, reg=%x) == %x\n",
+		"%s(phy_id=%i, reg=%x) == %x\n", __func__,
 		phy_id, reg, rc);
 
 	return rc;
@@ -772,6 +782,8 @@ static int xemaclite_mdio_read(struct mii_bus *bus, int phy_id, int reg)
  *
  * This function waits till the device is ready to accept a new MDIO
  * request and then writes the val to the MDIO Write Data register.
+ *
+ * Return:      0 upon success or a negative error upon failure
  */
 static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg,
 				u16 val)
@@ -780,7 +792,7 @@ static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg,
 	u32 ctrl_reg;
 
 	dev_dbg(&lp->ndev->dev,
-		"xemaclite_mdio_write(phy_id=%i, reg=%x, val=%x)\n",
+		"%s(phy_id=%i, reg=%x, val=%x)\n", __func__,
 		phy_id, reg, val);
 
 	if (xemaclite_mdio_wait(lp))
@@ -805,7 +817,7 @@ static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg,
 /**
  * xemaclite_mdio_setup - Register mii_bus for the Emaclite device
  * @lp:		Pointer to the Emaclite device private data
- * @ofdev:	Pointer to OF device structure
+ * @dev:	Pointer to OF device structure
  *
  * This function enables MDIO bus in the Emaclite device and registers a
  * mii_bus.
@@ -905,6 +917,9 @@ static void xemaclite_adjust_link(struct net_device *ndev)
  * This function sets the MAC address, requests an IRQ and enables interrupts
  * for the Emaclite device and starts the Tx queue.
  * It also connects to the phy device, if MDIO is included in Emaclite device.
+ *
+ * Return:	0 on success. -ENODEV, if PHY cannot be connected.
+ *		Non-zero error value on failure.
  */
 static int xemaclite_open(struct net_device *dev)
 {
@@ -975,6 +990,8 @@ static int xemaclite_open(struct net_device *dev)
  * This function stops the Tx queue, disables interrupts and frees the IRQ for
  * the Emaclite device.
  * It also disconnects the phy device associated with the Emaclite device.
+ *
+ * Return:	0, always.
  */
 static int xemaclite_close(struct net_device *dev)
 {
@@ -1017,10 +1034,11 @@ static int xemaclite_send(struct sk_buff *orig_skb, struct net_device *dev)
 	new_skb = orig_skb;
 
 	spin_lock_irqsave(&lp->reset_lock, flags);
-	if (xemaclite_send_data(lp, (u8 *) new_skb->data, len) != 0) {
+	if (xemaclite_send_data(lp, (u8 *)new_skb->data, len) != 0) {
 		/* If the Emaclite Tx buffer is busy, stop the Tx queue and
 		 * defer the skb for transmission during the ISR, after the
-		 * current transmission is complete */
+		 * current transmission is complete
+		 */
 		netif_stop_queue(dev);
 		lp->deferred_skb = new_skb;
 		/* Take the time stamp now, since we can't do this in an ISR. */
@@ -1052,13 +1070,12 @@ static bool get_bool(struct platform_device *ofdev, const char *s)
 {
 	u32 *p = (u32 *)of_get_property(ofdev->dev.of_node, s, NULL);
 
-	if (p) {
-		return (bool)*p;
-	} else {
-		dev_warn(&ofdev->dev, "Parameter %s not found,"
-			"defaulting to false\n", s);
+	if (!p) {
+		dev_warn(&ofdev->dev, "Parameter %s not found, defaulting to false\n", s);
 		return false;
 	}
+
+	return (bool)*p;
 }
 
 static const struct net_device_ops xemaclite_netdev_ops;
@@ -1066,7 +1083,6 @@ static const struct net_device_ops xemaclite_netdev_ops;
 /**
  * xemaclite_of_probe - Probe method for the Emaclite device.
  * @ofdev:	Pointer to OF device structure
- * @match:	Pointer to the structure used for matching a device
  *
  * This function probes for the Emaclite device in the device tree.
  * It initializes the driver data structure and the hardware, sets the MAC
diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c
index 750954be5a74..d3eae1239045 100644
--- a/drivers/net/fjes/fjes_main.c
+++ b/drivers/net/fjes/fjes_main.c
@@ -1395,8 +1395,8 @@ static void fjes_watch_unshare_task(struct work_struct *work)
 
 	while ((unshare_watch_bitmask || hw->txrx_stop_req_bit) &&
 	       (wait_time < 3000)) {
-		for (epidx = 0; epidx < hw->max_epid; epidx++) {
-			if (epidx == hw->my_epid)
+		for (epidx = 0; epidx < max_epid; epidx++) {
+			if (epidx == my_epid)
 				continue;
 
 			is_shared = fjes_hw_epid_is_shared(hw->hw_info.share,
@@ -1453,8 +1453,8 @@ static void fjes_watch_unshare_task(struct work_struct *work)
 	}
 
 	if (hw->hw_info.buffer_unshare_reserve_bit) {
-		for (epidx = 0; epidx < hw->max_epid; epidx++) {
-			if (epidx == hw->my_epid)
+		for (epidx = 0; epidx < max_epid; epidx++) {
+			if (epidx == my_epid)
 				continue;
 
 			if (test_bit(epidx,
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index ada33c2d9ac2..6acb6b5718b9 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -236,7 +236,8 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs,
 		}
 		/* Update tunnel dst according to Geneve options. */
 		ip_tunnel_info_opts_set(&tun_dst->u.tun_info,
-					gnvh->options, gnvh->opt_len * 4);
+					gnvh->options, gnvh->opt_len * 4,
+					TUNNEL_GENEVE_OPT);
 	} else {
 		/* Drop packets w/ critical options,
 		 * since we don't support any...
@@ -418,11 +419,12 @@ static int geneve_hlen(struct genevehdr *gh)
 	return sizeof(*gh) + gh->opt_len * 4;
 }
 
-static struct sk_buff **geneve_gro_receive(struct sock *sk,
-					   struct sk_buff **head,
-					   struct sk_buff *skb)
+static struct sk_buff *geneve_gro_receive(struct sock *sk,
+					  struct list_head *head,
+					  struct sk_buff *skb)
 {
-	struct sk_buff *p, **pp = NULL;
+	struct sk_buff *pp = NULL;
+	struct sk_buff *p;
 	struct genevehdr *gh, *gh2;
 	unsigned int hlen, gh_len, off_gnv;
 	const struct packet_offload *ptype;
@@ -449,7 +451,7 @@ static struct sk_buff **geneve_gro_receive(struct sock *sk,
 			goto out;
 	}
 
-	for (p = *head; p; p = p->next) {
+	list_for_each_entry(p, head, list) {
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
 
@@ -674,7 +676,8 @@ static void geneve_build_header(struct genevehdr *geneveh,
 	geneveh->proto_type = htons(ETH_P_TEB);
 	geneveh->rsvd2 = 0;
 
-	ip_tunnel_info_opts_get(geneveh->options, info);
+	if (info->key.tun_flags & TUNNEL_GENEVE_OPT)
+		ip_tunnel_info_opts_get(geneveh->options, info);
 }
 
 static int geneve_build_skb(struct dst_entry *dst, struct sk_buff *skb,
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index ec629a730005..7a145172d503 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1255,7 +1255,7 @@ out:
 	return skb->len;
 }
 
-static struct nla_policy gtp_genl_policy[GTPA_MAX + 1] = {
+static const struct nla_policy gtp_genl_policy[GTPA_MAX + 1] = {
 	[GTPA_LINK]		= { .type = NLA_U32, },
 	[GTPA_VERSION]		= { .type = NLA_U32, },
 	[GTPA_TID]		= { .type = NLA_U64, },
diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index 32f49c4ce457..d79a69dd2146 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -878,10 +878,8 @@ static void decode_data(struct sixpack *sp, unsigned char inbyte)
 
 static void decode_prio_command(struct sixpack *sp, unsigned char cmd)
 {
-	unsigned char channel;
 	int actual;
 
-	channel = cmd & SIXP_CHN_MASK;
 	if ((cmd & SIXP_PRIO_DATA_MASK) != 0) {     /* idle ? */
 
 	/* RX and DCD flags can only be set in the same prio command,
@@ -933,10 +931,9 @@ static void decode_prio_command(struct sixpack *sp, unsigned char cmd)
 
 static void decode_std_command(struct sixpack *sp, unsigned char cmd)
 {
-	unsigned char checksum = 0, rest = 0, channel;
+	unsigned char checksum = 0, rest = 0;
 	short i;
 
-	channel = cmd & SIXP_CHN_MASK;
 	switch (cmd & SIXP_CMD_MASK) {     /* normal command */
 	case SIXP_SEOF:
 		if ((sp->rx_count == 0) && (sp->rx_count_cooked == 0)) {
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 4b6e308199d2..a32ded5b4f41 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -873,6 +873,17 @@ struct netvsc_ethtool_stats {
 	unsigned long wake_queue;
 };
 
+struct netvsc_ethtool_pcpu_stats {
+	u64     rx_packets;
+	u64     rx_bytes;
+	u64     tx_packets;
+	u64     tx_bytes;
+	u64     vf_rx_packets;
+	u64     vf_rx_bytes;
+	u64     vf_tx_packets;
+	u64     vf_tx_bytes;
+};
+
 struct netvsc_vf_pcpu_stats {
 	u64     rx_packets;
 	u64     rx_bytes;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index dd1d6e115145..20275d1e6f9a 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -329,7 +329,7 @@ static u16 netvsc_pick_tx(struct net_device *ndev, struct sk_buff *skb)
 }
 
 static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
-			       void *accel_priv,
+			       struct net_device *sb_dev,
 			       select_queue_fallback_t fallback)
 {
 	struct net_device_context *ndc = netdev_priv(ndev);
@@ -343,9 +343,9 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 
 		if (vf_ops->ndo_select_queue)
 			txq = vf_ops->ndo_select_queue(vf_netdev, skb,
-						       accel_priv, fallback);
+						       sb_dev, fallback);
 		else
-			txq = fallback(vf_netdev, skb);
+			txq = fallback(vf_netdev, skb, NULL);
 
 		/* Record the queue selected by VF so that it can be
 		 * used for common case where VF has more queues than
@@ -1118,6 +1118,64 @@ static void netvsc_get_vf_stats(struct net_device *net,
 	}
 }
 
+static void netvsc_get_pcpu_stats(struct net_device *net,
+				  struct netvsc_ethtool_pcpu_stats *pcpu_tot)
+{
+	struct net_device_context *ndev_ctx = netdev_priv(net);
+	struct netvsc_device *nvdev = rcu_dereference_rtnl(ndev_ctx->nvdev);
+	int i;
+
+	/* fetch percpu stats of vf */
+	for_each_possible_cpu(i) {
+		const struct netvsc_vf_pcpu_stats *stats =
+			per_cpu_ptr(ndev_ctx->vf_stats, i);
+		struct netvsc_ethtool_pcpu_stats *this_tot = &pcpu_tot[i];
+		unsigned int start;
+
+		do {
+			start = u64_stats_fetch_begin_irq(&stats->syncp);
+			this_tot->vf_rx_packets = stats->rx_packets;
+			this_tot->vf_tx_packets = stats->tx_packets;
+			this_tot->vf_rx_bytes = stats->rx_bytes;
+			this_tot->vf_tx_bytes = stats->tx_bytes;
+		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+		this_tot->rx_packets = this_tot->vf_rx_packets;
+		this_tot->tx_packets = this_tot->vf_tx_packets;
+		this_tot->rx_bytes   = this_tot->vf_rx_bytes;
+		this_tot->tx_bytes   = this_tot->vf_tx_bytes;
+	}
+
+	/* fetch percpu stats of netvsc */
+	for (i = 0; i < nvdev->num_chn; i++) {
+		const struct netvsc_channel *nvchan = &nvdev->chan_table[i];
+		const struct netvsc_stats *stats;
+		struct netvsc_ethtool_pcpu_stats *this_tot =
+			&pcpu_tot[nvchan->channel->target_cpu];
+		u64 packets, bytes;
+		unsigned int start;
+
+		stats = &nvchan->tx_stats;
+		do {
+			start = u64_stats_fetch_begin_irq(&stats->syncp);
+			packets = stats->packets;
+			bytes = stats->bytes;
+		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+
+		this_tot->tx_bytes	+= bytes;
+		this_tot->tx_packets	+= packets;
+
+		stats = &nvchan->rx_stats;
+		do {
+			start = u64_stats_fetch_begin_irq(&stats->syncp);
+			packets = stats->packets;
+			bytes = stats->bytes;
+		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+
+		this_tot->rx_bytes	+= bytes;
+		this_tot->rx_packets	+= packets;
+	}
+}
+
 static void netvsc_get_stats64(struct net_device *net,
 			       struct rtnl_link_stats64 *t)
 {
@@ -1215,6 +1273,23 @@ static const struct {
 	{ "rx_no_memory", offsetof(struct netvsc_ethtool_stats, rx_no_memory) },
 	{ "stop_queue", offsetof(struct netvsc_ethtool_stats, stop_queue) },
 	{ "wake_queue", offsetof(struct netvsc_ethtool_stats, wake_queue) },
+}, pcpu_stats[] = {
+	{ "cpu%u_rx_packets",
+		offsetof(struct netvsc_ethtool_pcpu_stats, rx_packets) },
+	{ "cpu%u_rx_bytes",
+		offsetof(struct netvsc_ethtool_pcpu_stats, rx_bytes) },
+	{ "cpu%u_tx_packets",
+		offsetof(struct netvsc_ethtool_pcpu_stats, tx_packets) },
+	{ "cpu%u_tx_bytes",
+		offsetof(struct netvsc_ethtool_pcpu_stats, tx_bytes) },
+	{ "cpu%u_vf_rx_packets",
+		offsetof(struct netvsc_ethtool_pcpu_stats, vf_rx_packets) },
+	{ "cpu%u_vf_rx_bytes",
+		offsetof(struct netvsc_ethtool_pcpu_stats, vf_rx_bytes) },
+	{ "cpu%u_vf_tx_packets",
+		offsetof(struct netvsc_ethtool_pcpu_stats, vf_tx_packets) },
+	{ "cpu%u_vf_tx_bytes",
+		offsetof(struct netvsc_ethtool_pcpu_stats, vf_tx_bytes) },
 }, vf_stats[] = {
 	{ "vf_rx_packets", offsetof(struct netvsc_vf_pcpu_stats, rx_packets) },
 	{ "vf_rx_bytes",   offsetof(struct netvsc_vf_pcpu_stats, rx_bytes) },
@@ -1226,6 +1301,9 @@ static const struct {
 #define NETVSC_GLOBAL_STATS_LEN	ARRAY_SIZE(netvsc_stats)
 #define NETVSC_VF_STATS_LEN	ARRAY_SIZE(vf_stats)
 
+/* statistics per queue (rx/tx packets/bytes) */
+#define NETVSC_PCPU_STATS_LEN (num_present_cpus() * ARRAY_SIZE(pcpu_stats))
+
 /* 4 statistics per queue (rx/tx packets/bytes) */
 #define NETVSC_QUEUE_STATS_LEN(dev) ((dev)->num_chn * 4)
 
@@ -1241,7 +1319,8 @@ static int netvsc_get_sset_count(struct net_device *dev, int string_set)
 	case ETH_SS_STATS:
 		return NETVSC_GLOBAL_STATS_LEN
 			+ NETVSC_VF_STATS_LEN
-			+ NETVSC_QUEUE_STATS_LEN(nvdev);
+			+ NETVSC_QUEUE_STATS_LEN(nvdev)
+			+ NETVSC_PCPU_STATS_LEN;
 	default:
 		return -EINVAL;
 	}
@@ -1255,9 +1334,10 @@ static void netvsc_get_ethtool_stats(struct net_device *dev,
 	const void *nds = &ndc->eth_stats;
 	const struct netvsc_stats *qstats;
 	struct netvsc_vf_pcpu_stats sum;
+	struct netvsc_ethtool_pcpu_stats *pcpu_sum;
 	unsigned int start;
 	u64 packets, bytes;
-	int i, j;
+	int i, j, cpu;
 
 	if (!nvdev)
 		return;
@@ -1289,6 +1369,19 @@ static void netvsc_get_ethtool_stats(struct net_device *dev,
 		data[i++] = packets;
 		data[i++] = bytes;
 	}
+
+	pcpu_sum = kvmalloc_array(num_possible_cpus(),
+				  sizeof(struct netvsc_ethtool_pcpu_stats),
+				  GFP_KERNEL);
+	netvsc_get_pcpu_stats(dev, pcpu_sum);
+	for_each_present_cpu(cpu) {
+		struct netvsc_ethtool_pcpu_stats *this_sum = &pcpu_sum[cpu];
+
+		for (j = 0; j < ARRAY_SIZE(pcpu_stats); j++)
+			data[i++] = *(u64 *)((void *)this_sum
+					     + pcpu_stats[j].offset);
+	}
+	kvfree(pcpu_sum);
 }
 
 static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
@@ -1296,7 +1389,7 @@ static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 	struct net_device_context *ndc = netdev_priv(dev);
 	struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev);
 	u8 *p = data;
-	int i;
+	int i, cpu;
 
 	if (!nvdev)
 		return;
@@ -1324,6 +1417,13 @@ static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 			p += ETH_GSTRING_LEN;
 		}
 
+		for_each_present_cpu(cpu) {
+			for (i = 0; i < ARRAY_SIZE(pcpu_stats); i++) {
+				sprintf(p, pcpu_stats[i].name, cpu);
+				p += ETH_GSTRING_LEN;
+			}
+		}
+
 		break;
 	}
 }
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 408ece27131c..2a5209f23f29 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1338,7 +1338,7 @@ out:
 	/* setting up multiple channels failed */
 	net_device->max_chn = 1;
 	net_device->num_chn = 1;
-	return 0;
+	return net_device;
 
 err_dev_remv:
 	rndis_filter_device_remove(dev, net_device);
diff --git a/drivers/net/ieee802154/Kconfig b/drivers/net/ieee802154/Kconfig
index 8782f5655e3f..0e372f392cb1 100644
--- a/drivers/net/ieee802154/Kconfig
+++ b/drivers/net/ieee802154/Kconfig
@@ -115,3 +115,14 @@ config IEEE802154_MCR20A
 
 	  This driver can also be built as a module. To do so, say M here.
 	  the module will be called 'mcr20a'.
+
+config IEEE802154_HWSIM
+	depends on IEEE802154_DRIVERS && MAC802154
+	tristate "Simulated radio testing tool for mac802154"
+	---help---
+	  This driver is a developer testing tool that can be used to test
+	  IEEE 802.15.4 networking stack (mac802154) functionality. This is not
+	  needed for normal wpan usage and is only for testing.
+
+	  This driver can also be built as a module. To do so say M here.
+	  The module will be called 'mac802154_hwsim'.
diff --git a/drivers/net/ieee802154/Makefile b/drivers/net/ieee802154/Makefile
index 104744d5a668..0c78b6298060 100644
--- a/drivers/net/ieee802154/Makefile
+++ b/drivers/net/ieee802154/Makefile
@@ -7,3 +7,4 @@ obj-$(CONFIG_IEEE802154_ATUSB) += atusb.o
 obj-$(CONFIG_IEEE802154_ADF7242) += adf7242.o
 obj-$(CONFIG_IEEE802154_CA8210) += ca8210.o
 obj-$(CONFIG_IEEE802154_MCR20A) += mcr20a.o
+obj-$(CONFIG_IEEE802154_HWSIM) += mac802154_hwsim.o
diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c
index 176395e4b7bb..3b0588d7e702 100644
--- a/drivers/net/ieee802154/fakelb.c
+++ b/drivers/net/ieee802154/fakelb.c
@@ -254,6 +254,9 @@ static __init int fakelb_init_module(void)
 {
 	ieee802154fake_dev = platform_device_register_simple(
 			     "ieee802154fakelb", -1, NULL, 0);
+
+	pr_warn("fakelb driver is marked as deprecated, please use mac802154_hwsim!\n");
+
 	return platform_driver_register(&ieee802154fake_driver);
 }
 
diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c
new file mode 100644
index 000000000000..bf70ab892e69
--- /dev/null
+++ b/drivers/net/ieee802154/mac802154_hwsim.c
@@ -0,0 +1,937 @@
+/*
+ * HWSIM IEEE 802.15.4 interface
+ *
+ * (C) 2018 Mojatau, Alexander Aring <aring@mojatau.com>
+ * Copyright 2007-2012 Siemens AG
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Based on fakelb, original Written by:
+ * Sergey Lapin <slapin@ossfans.org>
+ * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
+ * Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
+ */
+
+#include <linux/module.h>
+#include <linux/timer.h>
+#include <linux/platform_device.h>
+#include <linux/rtnetlink.h>
+#include <linux/netdevice.h>
+#include <linux/device.h>
+#include <linux/spinlock.h>
+#include <net/mac802154.h>
+#include <net/cfg802154.h>
+#include <net/genetlink.h>
+#include "mac802154_hwsim.h"
+
+MODULE_DESCRIPTION("Software simulator of IEEE 802.15.4 radio(s) for mac802154");
+MODULE_LICENSE("GPL");
+
+static LIST_HEAD(hwsim_phys);
+static DEFINE_MUTEX(hwsim_phys_lock);
+
+static LIST_HEAD(hwsim_ifup_phys);
+
+static struct platform_device *mac802154hwsim_dev;
+
+/* MAC802154_HWSIM netlink family */
+static struct genl_family hwsim_genl_family;
+
+static int hwsim_radio_idx;
+
+enum hwsim_multicast_groups {
+	HWSIM_MCGRP_CONFIG,
+};
+
+static const struct genl_multicast_group hwsim_mcgrps[] = {
+	[HWSIM_MCGRP_CONFIG] = { .name = "config", },
+};
+
+struct hwsim_pib {
+	u8 page;
+	u8 channel;
+
+	struct rcu_head rcu;
+};
+
+struct hwsim_edge_info {
+	u8 lqi;
+
+	struct rcu_head rcu;
+};
+
+struct hwsim_edge {
+	struct hwsim_phy *endpoint;
+	struct hwsim_edge_info __rcu *info;
+
+	struct list_head list;
+	struct rcu_head rcu;
+};
+
+struct hwsim_phy {
+	struct ieee802154_hw *hw;
+	u32 idx;
+
+	struct hwsim_pib __rcu *pib;
+
+	bool suspended;
+	struct list_head edges;
+
+	struct list_head list;
+	struct list_head list_ifup;
+};
+
+static int hwsim_add_one(struct genl_info *info, struct device *dev,
+			 bool init);
+static void hwsim_del(struct hwsim_phy *phy);
+
+static int hwsim_hw_ed(struct ieee802154_hw *hw, u8 *level)
+{
+	*level = 0xbe;
+
+	return 0;
+}
+
+static int hwsim_hw_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
+{
+	struct hwsim_phy *phy = hw->priv;
+	struct hwsim_pib *pib, *pib_old;
+
+	pib = kzalloc(sizeof(*pib), GFP_KERNEL);
+	if (!pib)
+		return -ENOMEM;
+
+	pib->page = page;
+	pib->channel = channel;
+
+	pib_old = rtnl_dereference(phy->pib);
+	rcu_assign_pointer(phy->pib, pib);
+	kfree_rcu(pib_old, rcu);
+	return 0;
+}
+
+static int hwsim_hw_xmit(struct ieee802154_hw *hw, struct sk_buff *skb)
+{
+	struct hwsim_phy *current_phy = hw->priv;
+	struct hwsim_pib *current_pib, *endpoint_pib;
+	struct hwsim_edge_info *einfo;
+	struct hwsim_edge *e;
+
+	WARN_ON(current_phy->suspended);
+
+	rcu_read_lock();
+	current_pib = rcu_dereference(current_phy->pib);
+	list_for_each_entry_rcu(e, &current_phy->edges, list) {
+		/* Can be changed later in rx_irqsafe, but this is only a
+		 * performance tweak. Received radio should drop the frame
+		 * in mac802154 stack anyway... so we don't need to be
+		 * 100% of locking here to check on suspended
+		 */
+		if (e->endpoint->suspended)
+			continue;
+
+		endpoint_pib = rcu_dereference(e->endpoint->pib);
+		if (current_pib->page == endpoint_pib->page &&
+		    current_pib->channel == endpoint_pib->channel) {
+			struct sk_buff *newskb = pskb_copy(skb, GFP_ATOMIC);
+
+			einfo = rcu_dereference(e->info);
+			if (newskb)
+				ieee802154_rx_irqsafe(e->endpoint->hw, newskb,
+						      einfo->lqi);
+		}
+	}
+	rcu_read_unlock();
+
+	ieee802154_xmit_complete(hw, skb, false);
+	return 0;
+}
+
+static int hwsim_hw_start(struct ieee802154_hw *hw)
+{
+	struct hwsim_phy *phy = hw->priv;
+
+	phy->suspended = false;
+	list_add_rcu(&phy->list_ifup, &hwsim_ifup_phys);
+	synchronize_rcu();
+
+	return 0;
+}
+
+static void hwsim_hw_stop(struct ieee802154_hw *hw)
+{
+	struct hwsim_phy *phy = hw->priv;
+
+	phy->suspended = true;
+	list_del_rcu(&phy->list_ifup);
+	synchronize_rcu();
+}
+
+static int
+hwsim_set_promiscuous_mode(struct ieee802154_hw *hw, const bool on)
+{
+	return 0;
+}
+
+static const struct ieee802154_ops hwsim_ops = {
+	.owner = THIS_MODULE,
+	.xmit_async = hwsim_hw_xmit,
+	.ed = hwsim_hw_ed,
+	.set_channel = hwsim_hw_channel,
+	.start = hwsim_hw_start,
+	.stop = hwsim_hw_stop,
+	.set_promiscuous_mode = hwsim_set_promiscuous_mode,
+};
+
+static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info)
+{
+	return hwsim_add_one(info, &mac802154hwsim_dev->dev, false);
+}
+
+static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info)
+{
+	struct hwsim_phy *phy, *tmp;
+	s64 idx = -1;
+
+	if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID])
+		return -EINVAL;
+
+	idx = nla_get_u32(info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID]);
+
+	mutex_lock(&hwsim_phys_lock);
+	list_for_each_entry_safe(phy, tmp, &hwsim_phys, list) {
+		if (idx == phy->idx) {
+			hwsim_del(phy);
+			mutex_unlock(&hwsim_phys_lock);
+			return 0;
+		}
+	}
+	mutex_unlock(&hwsim_phys_lock);
+
+	return -ENODEV;
+}
+
+static int append_radio_msg(struct sk_buff *skb, struct hwsim_phy *phy)
+{
+	struct nlattr *nl_edges, *nl_edge;
+	struct hwsim_edge_info *einfo;
+	struct hwsim_edge *e;
+	int ret;
+
+	ret = nla_put_u32(skb, MAC802154_HWSIM_ATTR_RADIO_ID, phy->idx);
+	if (ret < 0)
+		return ret;
+
+	rcu_read_lock();
+	if (list_empty(&phy->edges)) {
+		rcu_read_unlock();
+		return 0;
+	}
+
+	nl_edges = nla_nest_start(skb, MAC802154_HWSIM_ATTR_RADIO_EDGES);
+	if (!nl_edges) {
+		rcu_read_unlock();
+		return -ENOBUFS;
+	}
+
+	list_for_each_entry_rcu(e, &phy->edges, list) {
+		nl_edge = nla_nest_start(skb, MAC802154_HWSIM_ATTR_RADIO_EDGE);
+		if (!nl_edge) {
+			rcu_read_unlock();
+			nla_nest_cancel(skb, nl_edges);
+			return -ENOBUFS;
+		}
+
+		ret = nla_put_u32(skb, MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID,
+				  e->endpoint->idx);
+		if (ret < 0) {
+			rcu_read_unlock();
+			nla_nest_cancel(skb, nl_edge);
+			nla_nest_cancel(skb, nl_edges);
+			return ret;
+		}
+
+		einfo = rcu_dereference(e->info);
+		ret = nla_put_u8(skb, MAC802154_HWSIM_EDGE_ATTR_LQI,
+				 einfo->lqi);
+		if (ret < 0) {
+			rcu_read_unlock();
+			nla_nest_cancel(skb, nl_edge);
+			nla_nest_cancel(skb, nl_edges);
+			return ret;
+		}
+
+		nla_nest_end(skb, nl_edge);
+	}
+	rcu_read_unlock();
+
+	nla_nest_end(skb, nl_edges);
+
+	return 0;
+}
+
+static int hwsim_get_radio(struct sk_buff *skb, struct hwsim_phy *phy,
+			   u32 portid, u32 seq,
+			   struct netlink_callback *cb, int flags)
+{
+	void *hdr;
+	int res = -EMSGSIZE;
+
+	hdr = genlmsg_put(skb, portid, seq, &hwsim_genl_family, flags,
+			  MAC802154_HWSIM_CMD_GET_RADIO);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (cb)
+		genl_dump_check_consistent(cb, hdr);
+
+	res = append_radio_msg(skb, phy);
+	if (res < 0)
+		goto out_err;
+
+	genlmsg_end(skb, hdr);
+	return 0;
+
+out_err:
+	genlmsg_cancel(skb, hdr);
+	return res;
+}
+
+static int hwsim_get_radio_nl(struct sk_buff *msg, struct genl_info *info)
+{
+	struct hwsim_phy *phy;
+	struct sk_buff *skb;
+	int idx, res = -ENODEV;
+
+	if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID])
+		return -EINVAL;
+	idx = nla_get_u32(info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID]);
+
+	mutex_lock(&hwsim_phys_lock);
+	list_for_each_entry(phy, &hwsim_phys, list) {
+		if (phy->idx != idx)
+			continue;
+
+		skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+		if (!skb) {
+			res = -ENOMEM;
+			goto out_err;
+		}
+
+		res = hwsim_get_radio(skb, phy, info->snd_portid,
+				      info->snd_seq, NULL, 0);
+		if (res < 0) {
+			nlmsg_free(skb);
+			goto out_err;
+		}
+
+		genlmsg_reply(skb, info);
+		break;
+	}
+
+out_err:
+	mutex_unlock(&hwsim_phys_lock);
+
+	return res;
+}
+
+static int hwsim_dump_radio_nl(struct sk_buff *skb,
+			       struct netlink_callback *cb)
+{
+	int idx = cb->args[0];
+	struct hwsim_phy *phy;
+	int res;
+
+	mutex_lock(&hwsim_phys_lock);
+
+	if (idx == hwsim_radio_idx)
+		goto done;
+
+	list_for_each_entry(phy, &hwsim_phys, list) {
+		if (phy->idx < idx)
+			continue;
+
+		res = hwsim_get_radio(skb, phy, NETLINK_CB(cb->skb).portid,
+				      cb->nlh->nlmsg_seq, cb, NLM_F_MULTI);
+		if (res < 0)
+			break;
+
+		idx = phy->idx + 1;
+	}
+
+	cb->args[0] = idx;
+
+done:
+	mutex_unlock(&hwsim_phys_lock);
+	return skb->len;
+}
+
+/* caller need to held hwsim_phys_lock */
+static struct hwsim_phy *hwsim_get_radio_by_id(uint32_t idx)
+{
+	struct hwsim_phy *phy;
+
+	list_for_each_entry(phy, &hwsim_phys, list) {
+		if (phy->idx == idx)
+			return phy;
+	}
+
+	return NULL;
+}
+
+static const struct nla_policy hwsim_edge_policy[MAC802154_HWSIM_EDGE_ATTR_MAX + 1] = {
+	[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID] = { .type = NLA_U32 },
+	[MAC802154_HWSIM_EDGE_ATTR_LQI] = { .type = NLA_U8 },
+};
+
+static struct hwsim_edge *hwsim_alloc_edge(struct hwsim_phy *endpoint, u8 lqi)
+{
+	struct hwsim_edge_info *einfo;
+	struct hwsim_edge *e;
+
+	e = kzalloc(sizeof(*e), GFP_KERNEL);
+	if (!e)
+		return NULL;
+
+	einfo = kzalloc(sizeof(*einfo), GFP_KERNEL);
+	if (!einfo) {
+		kfree(e);
+		return NULL;
+	}
+
+	einfo->lqi = 0xff;
+	rcu_assign_pointer(e->info, einfo);
+	e->endpoint = endpoint;
+
+	return e;
+}
+
+static void hwsim_free_edge(struct hwsim_edge *e)
+{
+	struct hwsim_edge_info *einfo;
+
+	rcu_read_lock();
+	einfo = rcu_dereference(e->info);
+	rcu_read_unlock();
+
+	kfree_rcu(einfo, rcu);
+	kfree_rcu(e, rcu);
+}
+
+static int hwsim_new_edge_nl(struct sk_buff *msg, struct genl_info *info)
+{
+	struct nlattr *edge_attrs[MAC802154_HWSIM_EDGE_ATTR_MAX + 1];
+	struct hwsim_phy *phy_v0, *phy_v1;
+	struct hwsim_edge *e;
+	u32 v0, v1;
+
+	if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID] &&
+	    !info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE])
+		return -EINVAL;
+
+	if (nla_parse_nested(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX,
+			     info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE],
+			     hwsim_edge_policy, NULL))
+		return -EINVAL;
+
+	if (!edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID])
+		return -EINVAL;
+
+	v0 = nla_get_u32(info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID]);
+	v1 = nla_get_u32(edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID]);
+
+	if (v0 == v1)
+		return -EINVAL;
+
+	mutex_lock(&hwsim_phys_lock);
+	phy_v0 = hwsim_get_radio_by_id(v0);
+	if (!phy_v0) {
+		mutex_unlock(&hwsim_phys_lock);
+		return -ENOENT;
+	}
+
+	phy_v1 = hwsim_get_radio_by_id(v1);
+	if (!phy_v1) {
+		mutex_unlock(&hwsim_phys_lock);
+		return -ENOENT;
+	}
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(e, &phy_v0->edges, list) {
+		if (e->endpoint->idx == v1) {
+			mutex_unlock(&hwsim_phys_lock);
+			rcu_read_unlock();
+			return -EEXIST;
+		}
+	}
+	rcu_read_unlock();
+
+	e = hwsim_alloc_edge(phy_v1, 0xff);
+	if (!e) {
+		mutex_unlock(&hwsim_phys_lock);
+		return -ENOMEM;
+	}
+	list_add_rcu(&e->list, &phy_v0->edges);
+	/* wait until changes are done under hwsim_phys_lock lock
+	 * should prevent of calling this function twice while
+	 * edges list has not the changes yet.
+	 */
+	synchronize_rcu();
+	mutex_unlock(&hwsim_phys_lock);
+
+	return 0;
+}
+
+static int hwsim_del_edge_nl(struct sk_buff *msg, struct genl_info *info)
+{
+	struct nlattr *edge_attrs[MAC802154_HWSIM_EDGE_ATTR_MAX + 1];
+	struct hwsim_phy *phy_v0;
+	struct hwsim_edge *e;
+	u32 v0, v1;
+
+	if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID] &&
+	    !info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE])
+		return -EINVAL;
+
+	if (nla_parse_nested(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX + 1,
+			     info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE],
+			     hwsim_edge_policy, NULL))
+		return -EINVAL;
+
+	if (!edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID])
+		return -EINVAL;
+
+	v0 = nla_get_u32(info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID]);
+	v1 = nla_get_u32(edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID]);
+
+	mutex_lock(&hwsim_phys_lock);
+	phy_v0 = hwsim_get_radio_by_id(v0);
+	if (!phy_v0) {
+		mutex_unlock(&hwsim_phys_lock);
+		return -ENOENT;
+	}
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(e, &phy_v0->edges, list) {
+		if (e->endpoint->idx == v1) {
+			rcu_read_unlock();
+			list_del_rcu(&e->list);
+			hwsim_free_edge(e);
+			/* same again - wait until list changes are done */
+			synchronize_rcu();
+			mutex_unlock(&hwsim_phys_lock);
+			return 0;
+		}
+	}
+	rcu_read_unlock();
+
+	mutex_unlock(&hwsim_phys_lock);
+
+	return -ENOENT;
+}
+
+static int hwsim_set_edge_lqi(struct sk_buff *msg, struct genl_info *info)
+{
+	struct nlattr *edge_attrs[MAC802154_HWSIM_EDGE_ATTR_MAX + 1];
+	struct hwsim_edge_info *einfo;
+	struct hwsim_phy *phy_v0;
+	struct hwsim_edge *e;
+	u32 v0, v1;
+	u8 lqi;
+
+	if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID] &&
+	    !info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE])
+		return -EINVAL;
+
+	if (nla_parse_nested(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX + 1,
+			     info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE],
+			     hwsim_edge_policy, NULL))
+		return -EINVAL;
+
+	if (!edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID] &&
+	    !edge_attrs[MAC802154_HWSIM_EDGE_ATTR_LQI])
+		return -EINVAL;
+
+	v0 = nla_get_u32(info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID]);
+	v1 = nla_get_u32(edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID]);
+	lqi = nla_get_u8(edge_attrs[MAC802154_HWSIM_EDGE_ATTR_LQI]);
+
+	mutex_lock(&hwsim_phys_lock);
+	phy_v0 = hwsim_get_radio_by_id(v0);
+	if (!phy_v0) {
+		mutex_unlock(&hwsim_phys_lock);
+		return -ENOENT;
+	}
+
+	einfo = kzalloc(sizeof(*einfo), GFP_KERNEL);
+	if (!einfo) {
+		mutex_unlock(&hwsim_phys_lock);
+		return -ENOMEM;
+	}
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(e, &phy_v0->edges, list) {
+		if (e->endpoint->idx == v1) {
+			einfo->lqi = lqi;
+			rcu_assign_pointer(e->info, einfo);
+			rcu_read_unlock();
+			mutex_unlock(&hwsim_phys_lock);
+			return 0;
+		}
+	}
+	rcu_read_unlock();
+
+	kfree(einfo);
+	mutex_unlock(&hwsim_phys_lock);
+
+	return -ENOENT;
+}
+
+/* MAC802154_HWSIM netlink policy */
+
+static const struct nla_policy hwsim_genl_policy[MAC802154_HWSIM_ATTR_MAX + 1] = {
+	[MAC802154_HWSIM_ATTR_RADIO_ID] = { .type = NLA_U32 },
+	[MAC802154_HWSIM_ATTR_RADIO_EDGE] = { .type = NLA_NESTED },
+	[MAC802154_HWSIM_ATTR_RADIO_EDGES] = { .type = NLA_NESTED },
+};
+
+/* Generic Netlink operations array */
+static const struct genl_ops hwsim_nl_ops[] = {
+	{
+		.cmd = MAC802154_HWSIM_CMD_NEW_RADIO,
+		.policy = hwsim_genl_policy,
+		.doit = hwsim_new_radio_nl,
+		.flags = GENL_UNS_ADMIN_PERM,
+	},
+	{
+		.cmd = MAC802154_HWSIM_CMD_DEL_RADIO,
+		.policy = hwsim_genl_policy,
+		.doit = hwsim_del_radio_nl,
+		.flags = GENL_UNS_ADMIN_PERM,
+	},
+	{
+		.cmd = MAC802154_HWSIM_CMD_GET_RADIO,
+		.policy = hwsim_genl_policy,
+		.doit = hwsim_get_radio_nl,
+		.dumpit = hwsim_dump_radio_nl,
+	},
+	{
+		.cmd = MAC802154_HWSIM_CMD_NEW_EDGE,
+		.policy = hwsim_genl_policy,
+		.doit = hwsim_new_edge_nl,
+		.flags = GENL_UNS_ADMIN_PERM,
+	},
+	{
+		.cmd = MAC802154_HWSIM_CMD_DEL_EDGE,
+		.policy = hwsim_genl_policy,
+		.doit = hwsim_del_edge_nl,
+		.flags = GENL_UNS_ADMIN_PERM,
+	},
+	{
+		.cmd = MAC802154_HWSIM_CMD_SET_EDGE,
+		.policy = hwsim_genl_policy,
+		.doit = hwsim_set_edge_lqi,
+		.flags = GENL_UNS_ADMIN_PERM,
+	},
+};
+
+static struct genl_family hwsim_genl_family __ro_after_init = {
+	.name = "MAC802154_HWSIM",
+	.version = 1,
+	.maxattr = MAC802154_HWSIM_ATTR_MAX,
+	.module = THIS_MODULE,
+	.ops = hwsim_nl_ops,
+	.n_ops = ARRAY_SIZE(hwsim_nl_ops),
+	.mcgrps = hwsim_mcgrps,
+	.n_mcgrps = ARRAY_SIZE(hwsim_mcgrps),
+};
+
+static void hwsim_mcast_config_msg(struct sk_buff *mcast_skb,
+				   struct genl_info *info)
+{
+	if (info)
+		genl_notify(&hwsim_genl_family, mcast_skb, info,
+			    HWSIM_MCGRP_CONFIG, GFP_KERNEL);
+	else
+		genlmsg_multicast(&hwsim_genl_family, mcast_skb, 0,
+				  HWSIM_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+static void hwsim_mcast_new_radio(struct genl_info *info, struct hwsim_phy *phy)
+{
+	struct sk_buff *mcast_skb;
+	void *data;
+
+	mcast_skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!mcast_skb)
+		return;
+
+	data = genlmsg_put(mcast_skb, 0, 0, &hwsim_genl_family, 0,
+			   MAC802154_HWSIM_CMD_NEW_RADIO);
+	if (!data)
+		goto out_err;
+
+	if (append_radio_msg(mcast_skb, phy) < 0)
+		goto out_err;
+
+	genlmsg_end(mcast_skb, data);
+
+	hwsim_mcast_config_msg(mcast_skb, info);
+	return;
+
+out_err:
+	genlmsg_cancel(mcast_skb, data);
+	nlmsg_free(mcast_skb);
+}
+
+static void hwsim_edge_unsubscribe_me(struct hwsim_phy *phy)
+{
+	struct hwsim_phy *tmp;
+	struct hwsim_edge *e;
+
+	rcu_read_lock();
+	/* going to all phy edges and remove phy from it */
+	list_for_each_entry(tmp, &hwsim_phys, list) {
+		list_for_each_entry_rcu(e, &tmp->edges, list) {
+			if (e->endpoint->idx == phy->idx) {
+				list_del_rcu(&e->list);
+				hwsim_free_edge(e);
+			}
+		}
+	}
+	rcu_read_unlock();
+
+	synchronize_rcu();
+}
+
+static int hwsim_subscribe_all_others(struct hwsim_phy *phy)
+{
+	struct hwsim_phy *sub;
+	struct hwsim_edge *e;
+
+	list_for_each_entry(sub, &hwsim_phys, list) {
+		e = hwsim_alloc_edge(sub, 0xff);
+		if (!e)
+			goto me_fail;
+
+		list_add_rcu(&e->list, &phy->edges);
+	}
+
+	list_for_each_entry(sub, &hwsim_phys, list) {
+		e = hwsim_alloc_edge(phy, 0xff);
+		if (!e)
+			goto sub_fail;
+
+		list_add_rcu(&e->list, &sub->edges);
+	}
+
+	return 0;
+
+me_fail:
+	rcu_read_lock();
+	list_for_each_entry_rcu(e, &phy->edges, list) {
+		list_del_rcu(&e->list);
+		hwsim_free_edge(e);
+	}
+	rcu_read_unlock();
+sub_fail:
+	hwsim_edge_unsubscribe_me(phy);
+	return -ENOMEM;
+}
+
+static int hwsim_add_one(struct genl_info *info, struct device *dev,
+			 bool init)
+{
+	struct ieee802154_hw *hw;
+	struct hwsim_phy *phy;
+	struct hwsim_pib *pib;
+	int idx;
+	int err;
+
+	idx = hwsim_radio_idx++;
+
+	hw = ieee802154_alloc_hw(sizeof(*phy), &hwsim_ops);
+	if (!hw)
+		return -ENOMEM;
+
+	phy = hw->priv;
+	phy->hw = hw;
+
+	/* 868 MHz BPSK	802.15.4-2003 */
+	hw->phy->supported.channels[0] |= 1;
+	/* 915 MHz BPSK	802.15.4-2003 */
+	hw->phy->supported.channels[0] |= 0x7fe;
+	/* 2.4 GHz O-QPSK 802.15.4-2003 */
+	hw->phy->supported.channels[0] |= 0x7FFF800;
+	/* 868 MHz ASK 802.15.4-2006 */
+	hw->phy->supported.channels[1] |= 1;
+	/* 915 MHz ASK 802.15.4-2006 */
+	hw->phy->supported.channels[1] |= 0x7fe;
+	/* 868 MHz O-QPSK 802.15.4-2006 */
+	hw->phy->supported.channels[2] |= 1;
+	/* 915 MHz O-QPSK 802.15.4-2006 */
+	hw->phy->supported.channels[2] |= 0x7fe;
+	/* 2.4 GHz CSS 802.15.4a-2007 */
+	hw->phy->supported.channels[3] |= 0x3fff;
+	/* UWB Sub-gigahertz 802.15.4a-2007 */
+	hw->phy->supported.channels[4] |= 1;
+	/* UWB Low band 802.15.4a-2007 */
+	hw->phy->supported.channels[4] |= 0x1e;
+	/* UWB High band 802.15.4a-2007 */
+	hw->phy->supported.channels[4] |= 0xffe0;
+	/* 750 MHz O-QPSK 802.15.4c-2009 */
+	hw->phy->supported.channels[5] |= 0xf;
+	/* 750 MHz MPSK 802.15.4c-2009 */
+	hw->phy->supported.channels[5] |= 0xf0;
+	/* 950 MHz BPSK 802.15.4d-2009 */
+	hw->phy->supported.channels[6] |= 0x3ff;
+	/* 950 MHz GFSK 802.15.4d-2009 */
+	hw->phy->supported.channels[6] |= 0x3ffc00;
+
+	ieee802154_random_extended_addr(&hw->phy->perm_extended_addr);
+
+	/* hwsim phy channel 13 as default */
+	hw->phy->current_channel = 13;
+	pib = kzalloc(sizeof(*pib), GFP_KERNEL);
+	if (!pib) {
+		err = -ENOMEM;
+		goto err_pib;
+	}
+
+	rcu_assign_pointer(phy->pib, pib);
+	phy->idx = idx;
+	INIT_LIST_HEAD(&phy->edges);
+
+	hw->flags = IEEE802154_HW_PROMISCUOUS;
+	hw->parent = dev;
+
+	err = ieee802154_register_hw(hw);
+	if (err)
+		goto err_reg;
+
+	mutex_lock(&hwsim_phys_lock);
+	if (init) {
+		err = hwsim_subscribe_all_others(phy);
+		if (err < 0) {
+			mutex_unlock(&hwsim_phys_lock);
+			goto err_reg;
+		}
+	}
+	list_add_tail(&phy->list, &hwsim_phys);
+	mutex_unlock(&hwsim_phys_lock);
+
+	hwsim_mcast_new_radio(info, phy);
+
+	return idx;
+
+err_reg:
+	kfree(pib);
+err_pib:
+	ieee802154_free_hw(phy->hw);
+	return err;
+}
+
+static void hwsim_del(struct hwsim_phy *phy)
+{
+	struct hwsim_pib *pib;
+
+	hwsim_edge_unsubscribe_me(phy);
+
+	list_del(&phy->list);
+
+	rcu_read_lock();
+	pib = rcu_dereference(phy->pib);
+	rcu_read_unlock();
+
+	kfree_rcu(pib, rcu);
+
+	ieee802154_unregister_hw(phy->hw);
+	ieee802154_free_hw(phy->hw);
+}
+
+static int hwsim_probe(struct platform_device *pdev)
+{
+	struct hwsim_phy *phy, *tmp;
+	int err, i;
+
+	for (i = 0; i < 2; i++) {
+		err = hwsim_add_one(NULL, &pdev->dev, true);
+		if (err < 0)
+			goto err_slave;
+	}
+
+	dev_info(&pdev->dev, "Added 2 mac802154 hwsim hardware radios\n");
+	return 0;
+
+err_slave:
+	mutex_lock(&hwsim_phys_lock);
+	list_for_each_entry_safe(phy, tmp, &hwsim_phys, list)
+		hwsim_del(phy);
+	mutex_unlock(&hwsim_phys_lock);
+	return err;
+}
+
+static int hwsim_remove(struct platform_device *pdev)
+{
+	struct hwsim_phy *phy, *tmp;
+
+	mutex_lock(&hwsim_phys_lock);
+	list_for_each_entry_safe(phy, tmp, &hwsim_phys, list)
+		hwsim_del(phy);
+	mutex_unlock(&hwsim_phys_lock);
+
+	return 0;
+}
+
+static struct platform_driver mac802154hwsim_driver = {
+	.probe = hwsim_probe,
+	.remove = hwsim_remove,
+	.driver = {
+			.name = "mac802154_hwsim",
+	},
+};
+
+static __init int hwsim_init_module(void)
+{
+	int rc;
+
+	rc = genl_register_family(&hwsim_genl_family);
+	if (rc)
+		return rc;
+
+	mac802154hwsim_dev = platform_device_register_simple("mac802154_hwsim",
+							     -1, NULL, 0);
+	if (IS_ERR(mac802154hwsim_dev)) {
+		rc = PTR_ERR(mac802154hwsim_dev);
+		goto platform_dev;
+	}
+
+	rc = platform_driver_register(&mac802154hwsim_driver);
+	if (rc < 0)
+		goto platform_drv;
+
+	return 0;
+
+platform_drv:
+	genl_unregister_family(&hwsim_genl_family);
+platform_dev:
+	platform_device_unregister(mac802154hwsim_dev);
+	return rc;
+}
+
+static __exit void hwsim_remove_module(void)
+{
+	genl_unregister_family(&hwsim_genl_family);
+	platform_driver_unregister(&mac802154hwsim_driver);
+	platform_device_unregister(mac802154hwsim_dev);
+}
+
+module_init(hwsim_init_module);
+module_exit(hwsim_remove_module);
diff --git a/drivers/net/ieee802154/mac802154_hwsim.h b/drivers/net/ieee802154/mac802154_hwsim.h
new file mode 100644
index 000000000000..6c6e30e3871d
--- /dev/null
+++ b/drivers/net/ieee802154/mac802154_hwsim.h
@@ -0,0 +1,73 @@
+#ifndef __MAC802154_HWSIM_H
+#define __MAC802154_HWSIM_H
+
+/* mac802154 hwsim netlink commands
+ *
+ * @MAC802154_HWSIM_CMD_UNSPEC: unspecified command to catch error
+ * @MAC802154_HWSIM_CMD_GET_RADIO: fetch information about existing radios
+ * @MAC802154_HWSIM_CMD_SET_RADIO: change radio parameters during runtime
+ * @MAC802154_HWSIM_CMD_NEW_RADIO: create a new radio with the given parameters
+ *	returns the radio ID (>= 0) or negative on errors, if successful
+ *	then multicast the result
+ * @MAC802154_HWSIM_CMD_DEL_RADIO: destroy a radio, reply is multicasted
+ * @MAC802154_HWSIM_CMD_GET_EDGE: fetch information about existing edges
+ * @MAC802154_HWSIM_CMD_SET_EDGE: change edge parameters during runtime
+ * @MAC802154_HWSIM_CMD_DEL_EDGE: delete edges between radios
+ * @MAC802154_HWSIM_CMD_NEW_EDGE: create a new edge between two radios
+ * @__MAC802154_HWSIM_CMD_MAX: enum limit
+ */
+enum {
+	MAC802154_HWSIM_CMD_UNSPEC,
+
+	MAC802154_HWSIM_CMD_GET_RADIO,
+	MAC802154_HWSIM_CMD_SET_RADIO,
+	MAC802154_HWSIM_CMD_NEW_RADIO,
+	MAC802154_HWSIM_CMD_DEL_RADIO,
+
+	MAC802154_HWSIM_CMD_GET_EDGE,
+	MAC802154_HWSIM_CMD_SET_EDGE,
+	MAC802154_HWSIM_CMD_DEL_EDGE,
+	MAC802154_HWSIM_CMD_NEW_EDGE,
+
+	__MAC802154_HWSIM_CMD_MAX,
+};
+
+#define MAC802154_HWSIM_CMD_MAX (__MAC802154_HWSIM_MAX - 1)
+
+/* mac802154 hwsim netlink attributes
+ *
+ * @MAC802154_HWSIM_ATTR_UNSPEC: unspecified attribute to catch error
+ * @MAC802154_HWSIM_ATTR_RADIO_ID: u32 attribute to identify the radio
+ * @MAC802154_HWSIM_ATTR_EDGE: nested attribute of edges
+ * @MAC802154_HWSIM_ATTR_EDGES: list if nested attributes which contains the
+ *	edge information according the radio id
+ * @__MAC802154_HWSIM_ATTR_MAX: enum limit
+ */
+enum {
+	MAC802154_HWSIM_ATTR_UNSPEC,
+	MAC802154_HWSIM_ATTR_RADIO_ID,
+	MAC802154_HWSIM_ATTR_RADIO_EDGE,
+	MAC802154_HWSIM_ATTR_RADIO_EDGES,
+	__MAC802154_HWSIM_ATTR_MAX,
+};
+
+#define MAC802154_HWSIM_ATTR_MAX (__MAC802154_HWSIM_ATTR_MAX - 1)
+
+/* mac802154 hwsim edge netlink attributes
+ *
+ * @MAC802154_HWSIM_EDGE_ATTR_UNSPEC: unspecified attribute to catch error
+ * @MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID: radio id where the edge points to
+ * @MAC802154_HWSIM_EDGE_ATTR_LQI: LQI value which the endpoint radio will
+ *	receive for this edge
+ * @__MAC802154_HWSIM_ATTR_MAX: enum limit
+ */
+enum {
+	MAC802154_HWSIM_EDGE_ATTR_UNSPEC,
+	MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID,
+	MAC802154_HWSIM_EDGE_ATTR_LQI,
+	__MAC802154_HWSIM_EDGE_ATTR_MAX,
+};
+
+#define MAC802154_HWSIM_EDGE_ATTR_MAX (__MAC802154_HWSIM_EDGE_ATTR_MAX - 1)
+
+#endif /* __MAC802154_HWSIM_H */
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index adde8fc45588..cfda146f3b3b 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -514,7 +514,6 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
 	const struct macvlan_dev *vlan = netdev_priv(dev);
 	const struct macvlan_port *port = vlan->port;
 	const struct macvlan_dev *dest;
-	void *accel_priv = NULL;
 
 	if (vlan->mode == MACVLAN_MODE_BRIDGE) {
 		const struct ethhdr *eth = (void *)skb->data;
@@ -533,15 +532,10 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
 			return NET_XMIT_SUCCESS;
 		}
 	}
-
-	/* For packets that are non-multicast and not bridged we will pass
-	 * the necessary information so that the lowerdev can distinguish
-	 * the source of the packets via the accel_priv value.
-	 */
-	accel_priv = vlan->accel_priv;
 xmit_world:
 	skb->dev = vlan->lowerdev;
-	return dev_queue_xmit_accel(skb, accel_priv);
+	return dev_queue_xmit_accel(skb,
+				    netdev_get_sb_channel(dev) ? dev : NULL);
 }
 
 static inline netdev_tx_t macvlan_netpoll_send_skb(struct macvlan_dev *vlan, struct sk_buff *skb)
@@ -1647,6 +1641,7 @@ static int macvlan_device_event(struct notifier_block *unused,
 
 	switch (event) {
 	case NETDEV_UP:
+	case NETDEV_DOWN:
 	case NETDEV_CHANGE:
 		list_for_each_entry(vlan, &port->vlans, list)
 			netif_stacked_transfer_operstate(vlan->lowerdev,
diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c
index 4f390fa557e4..7ae1856d1f18 100644
--- a/drivers/net/net_failover.c
+++ b/drivers/net/net_failover.c
@@ -115,7 +115,8 @@ static netdev_tx_t net_failover_start_xmit(struct sk_buff *skb,
 }
 
 static u16 net_failover_select_queue(struct net_device *dev,
-				     struct sk_buff *skb, void *accel_priv,
+				     struct sk_buff *skb,
+				     struct net_device *sb_dev,
 				     select_queue_fallback_t fallback)
 {
 	struct net_failover_info *nfo_info = netdev_priv(dev);
@@ -128,9 +129,9 @@ static u16 net_failover_select_queue(struct net_device *dev,
 
 		if (ops->ndo_select_queue)
 			txq = ops->ndo_select_queue(primary_dev, skb,
-						    accel_priv, fallback);
+						    sb_dev, fallback);
 		else
-			txq = fallback(primary_dev, skb);
+			txq = fallback(primary_dev, skb, NULL);
 
 		qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping;
 
@@ -219,14 +220,14 @@ static int net_failover_change_mtu(struct net_device *dev, int new_mtu)
 	struct net_device *primary_dev, *standby_dev;
 	int ret = 0;
 
-	primary_dev = rcu_dereference(nfo_info->primary_dev);
+	primary_dev = rtnl_dereference(nfo_info->primary_dev);
 	if (primary_dev) {
 		ret = dev_set_mtu(primary_dev, new_mtu);
 		if (ret)
 			return ret;
 	}
 
-	standby_dev = rcu_dereference(nfo_info->standby_dev);
+	standby_dev = rtnl_dereference(nfo_info->standby_dev);
 	if (standby_dev) {
 		ret = dev_set_mtu(standby_dev, new_mtu);
 		if (ret) {
diff --git a/drivers/net/netdevsim/Makefile b/drivers/net/netdevsim/Makefile
index 449b2a1a1800..0fee1d06c084 100644
--- a/drivers/net/netdevsim/Makefile
+++ b/drivers/net/netdevsim/Makefile
@@ -13,3 +13,7 @@ endif
 ifneq ($(CONFIG_NET_DEVLINK),)
 netdevsim-objs += devlink.o fib.o
 endif
+
+ifneq ($(CONFIG_XFRM_OFFLOAD),)
+netdevsim-objs += ipsec.o
+endif
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index 75c25306d234..81444208b216 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -92,7 +92,7 @@ static const struct bpf_prog_offload_ops nsim_bpf_analyzer_ops = {
 
 static bool nsim_xdp_offload_active(struct netdevsim *ns)
 {
-	return ns->xdp_prog_mode == XDP_ATTACHED_HW;
+	return ns->xdp_hw.prog;
 }
 
 static void nsim_prog_set_loaded(struct bpf_prog *prog, bool loaded)
@@ -195,14 +195,14 @@ static int nsim_xdp_offload_prog(struct netdevsim *ns, struct netdev_bpf *bpf)
 	return nsim_bpf_offload(ns, bpf->prog, nsim_xdp_offload_active(ns));
 }
 
-static int nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf)
+static int
+nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf,
+		  struct xdp_attachment_info *xdp)
 {
 	int err;
 
-	if (ns->xdp_prog && (bpf->flags ^ ns->xdp_flags) & XDP_FLAGS_MODES) {
-		NSIM_EA(bpf->extack, "program loaded with different flags");
+	if (!xdp_attachment_flags_ok(xdp, bpf))
 		return -EBUSY;
-	}
 
 	if (bpf->command == XDP_SETUP_PROG && !ns->bpf_xdpdrv_accept) {
 		NSIM_EA(bpf->extack, "driver XDP disabled in DebugFS");
@@ -219,18 +219,7 @@ static int nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf)
 			return err;
 	}
 
-	if (ns->xdp_prog)
-		bpf_prog_put(ns->xdp_prog);
-
-	ns->xdp_prog = bpf->prog;
-	ns->xdp_flags = bpf->flags;
-
-	if (!bpf->prog)
-		ns->xdp_prog_mode = XDP_ATTACHED_NONE;
-	else if (bpf->command == XDP_SETUP_PROG)
-		ns->xdp_prog_mode = XDP_ATTACHED_DRV;
-	else
-		ns->xdp_prog_mode = XDP_ATTACHED_HW;
+	xdp_attachment_setup(xdp, bpf);
 
 	return 0;
 }
@@ -249,8 +238,8 @@ static int nsim_bpf_create_prog(struct netdevsim *ns, struct bpf_prog *prog)
 	state->state = "verify";
 
 	/* Program id is not populated yet when we create the state. */
-	sprintf(name, "%u", ns->prog_id_gen++);
-	state->ddir = debugfs_create_dir(name, ns->ddir_bpf_bound_progs);
+	sprintf(name, "%u", ns->sdev->prog_id_gen++);
+	state->ddir = debugfs_create_dir(name, ns->sdev->ddir_bpf_bound_progs);
 	if (IS_ERR_OR_NULL(state->ddir)) {
 		kfree(state);
 		return -ENOMEM;
@@ -261,7 +250,7 @@ static int nsim_bpf_create_prog(struct netdevsim *ns, struct bpf_prog *prog)
 			    &state->state, &nsim_bpf_string_fops);
 	debugfs_create_bool("loaded", 0400, state->ddir, &state->is_loaded);
 
-	list_add_tail(&state->l, &ns->bpf_bound_progs);
+	list_add_tail(&state->l, &ns->sdev->bpf_bound_progs);
 
 	prog->aux->offload->dev_priv = state;
 
@@ -290,10 +279,6 @@ static int nsim_setup_prog_checks(struct netdevsim *ns, struct netdev_bpf *bpf)
 		NSIM_EA(bpf->extack, "MTU too large w/ XDP enabled");
 		return -EINVAL;
 	}
-	if (nsim_xdp_offload_active(ns)) {
-		NSIM_EA(bpf->extack, "xdp offload active, can't load drv prog");
-		return -EBUSY;
-	}
 	return 0;
 }
 
@@ -309,7 +294,7 @@ nsim_setup_prog_hw_checks(struct netdevsim *ns, struct netdev_bpf *bpf)
 		NSIM_EA(bpf->extack, "xdpoffload of non-bound program");
 		return -EINVAL;
 	}
-	if (bpf->prog->aux->offload->netdev != ns->netdev) {
+	if (!bpf_offload_dev_match(bpf->prog, ns->netdev)) {
 		NSIM_EA(bpf->extack, "program bound to different dev");
 		return -EINVAL;
 	}
@@ -512,7 +497,7 @@ nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap)
 	}
 
 	offmap->dev_ops = &nsim_bpf_map_ops;
-	list_add_tail(&nmap->l, &ns->bpf_bound_maps);
+	list_add_tail(&nmap->l, &ns->sdev->bpf_bound_maps);
 
 	return 0;
 
@@ -567,22 +552,21 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 		nsim_bpf_destroy_prog(bpf->offload.prog);
 		return 0;
 	case XDP_QUERY_PROG:
-		bpf->prog_attached = ns->xdp_prog_mode;
-		bpf->prog_id = ns->xdp_prog ? ns->xdp_prog->aux->id : 0;
-		bpf->prog_flags = ns->xdp_prog ? ns->xdp_flags : 0;
-		return 0;
+		return xdp_attachment_query(&ns->xdp, bpf);
+	case XDP_QUERY_PROG_HW:
+		return xdp_attachment_query(&ns->xdp_hw, bpf);
 	case XDP_SETUP_PROG:
 		err = nsim_setup_prog_checks(ns, bpf);
 		if (err)
 			return err;
 
-		return nsim_xdp_set_prog(ns, bpf);
+		return nsim_xdp_set_prog(ns, bpf, &ns->xdp);
 	case XDP_SETUP_PROG_HW:
 		err = nsim_setup_prog_hw_checks(ns, bpf);
 		if (err)
 			return err;
 
-		return nsim_xdp_set_prog(ns, bpf);
+		return nsim_xdp_set_prog(ns, bpf, &ns->xdp_hw);
 	case BPF_OFFLOAD_MAP_ALLOC:
 		if (!ns->bpf_map_accept)
 			return -EOPNOTSUPP;
@@ -598,8 +582,26 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 
 int nsim_bpf_init(struct netdevsim *ns)
 {
-	INIT_LIST_HEAD(&ns->bpf_bound_progs);
-	INIT_LIST_HEAD(&ns->bpf_bound_maps);
+	int err;
+
+	if (ns->sdev->refcnt == 1) {
+		INIT_LIST_HEAD(&ns->sdev->bpf_bound_progs);
+		INIT_LIST_HEAD(&ns->sdev->bpf_bound_maps);
+
+		ns->sdev->ddir_bpf_bound_progs =
+			debugfs_create_dir("bpf_bound_progs", ns->sdev->ddir);
+		if (IS_ERR_OR_NULL(ns->sdev->ddir_bpf_bound_progs))
+			return -ENOMEM;
+
+		ns->sdev->bpf_dev = bpf_offload_dev_create();
+		err = PTR_ERR_OR_ZERO(ns->sdev->bpf_dev);
+		if (err)
+			return err;
+	}
+
+	err = bpf_offload_dev_netdev_register(ns->sdev->bpf_dev, ns->netdev);
+	if (err)
+		goto err_destroy_bdev;
 
 	debugfs_create_u32("bpf_offloaded_id", 0400, ns->ddir,
 			   &ns->bpf_offloaded_id);
@@ -609,10 +611,6 @@ int nsim_bpf_init(struct netdevsim *ns)
 			    &ns->bpf_bind_accept);
 	debugfs_create_u32("bpf_bind_verifier_delay", 0600, ns->ddir,
 			   &ns->bpf_bind_verifier_delay);
-	ns->ddir_bpf_bound_progs =
-		debugfs_create_dir("bpf_bound_progs", ns->ddir);
-	if (IS_ERR_OR_NULL(ns->ddir_bpf_bound_progs))
-		return -ENOMEM;
 
 	ns->bpf_tc_accept = true;
 	debugfs_create_bool("bpf_tc_accept", 0600, ns->ddir,
@@ -631,12 +629,23 @@ int nsim_bpf_init(struct netdevsim *ns)
 			    &ns->bpf_map_accept);
 
 	return 0;
+
+err_destroy_bdev:
+	if (ns->sdev->refcnt == 1)
+		bpf_offload_dev_destroy(ns->sdev->bpf_dev);
+	return err;
 }
 
 void nsim_bpf_uninit(struct netdevsim *ns)
 {
-	WARN_ON(!list_empty(&ns->bpf_bound_progs));
-	WARN_ON(!list_empty(&ns->bpf_bound_maps));
-	WARN_ON(ns->xdp_prog);
+	WARN_ON(ns->xdp.prog);
+	WARN_ON(ns->xdp_hw.prog);
 	WARN_ON(ns->bpf_offloaded);
+	bpf_offload_dev_netdev_unregister(ns->sdev->bpf_dev, ns->netdev);
+
+	if (ns->sdev->refcnt == 1) {
+		WARN_ON(!list_empty(&ns->sdev->bpf_bound_progs));
+		WARN_ON(!list_empty(&ns->sdev->bpf_bound_maps));
+		bpf_offload_dev_destroy(ns->sdev->bpf_dev);
+	}
 }
diff --git a/drivers/net/netdevsim/ipsec.c b/drivers/net/netdevsim/ipsec.c
new file mode 100644
index 000000000000..2dcf6cc269d0
--- /dev/null
+++ b/drivers/net/netdevsim/ipsec.c
@@ -0,0 +1,297 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2018 Oracle and/or its affiliates. All rights reserved. */
+
+#include <crypto/aead.h>
+#include <linux/debugfs.h>
+#include <net/xfrm.h>
+
+#include "netdevsim.h"
+
+#define NSIM_IPSEC_AUTH_BITS	128
+
+static ssize_t nsim_dbg_netdev_ops_read(struct file *filp,
+					char __user *buffer,
+					size_t count, loff_t *ppos)
+{
+	struct netdevsim *ns = filp->private_data;
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+	size_t bufsize;
+	char *buf, *p;
+	int len;
+	int i;
+
+	/* the buffer needed is
+	 * (num SAs * 3 lines each * ~60 bytes per line) + one more line
+	 */
+	bufsize = (ipsec->count * 4 * 60) + 60;
+	buf = kzalloc(bufsize, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	p = buf;
+	p += snprintf(p, bufsize - (p - buf),
+		      "SA count=%u tx=%u\n",
+		      ipsec->count, ipsec->tx);
+
+	for (i = 0; i < NSIM_IPSEC_MAX_SA_COUNT; i++) {
+		struct nsim_sa *sap = &ipsec->sa[i];
+
+		if (!sap->used)
+			continue;
+
+		p += snprintf(p, bufsize - (p - buf),
+			      "sa[%i] %cx ipaddr=0x%08x %08x %08x %08x\n",
+			      i, (sap->rx ? 'r' : 't'), sap->ipaddr[0],
+			      sap->ipaddr[1], sap->ipaddr[2], sap->ipaddr[3]);
+		p += snprintf(p, bufsize - (p - buf),
+			      "sa[%i]    spi=0x%08x proto=0x%x salt=0x%08x crypt=%d\n",
+			      i, be32_to_cpu(sap->xs->id.spi),
+			      sap->xs->id.proto, sap->salt, sap->crypt);
+		p += snprintf(p, bufsize - (p - buf),
+			      "sa[%i]    key=0x%08x %08x %08x %08x\n",
+			      i, sap->key[0], sap->key[1],
+			      sap->key[2], sap->key[3]);
+	}
+
+	len = simple_read_from_buffer(buffer, count, ppos, buf, p - buf);
+
+	kfree(buf);
+	return len;
+}
+
+static const struct file_operations ipsec_dbg_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.read = nsim_dbg_netdev_ops_read,
+};
+
+static int nsim_ipsec_find_empty_idx(struct nsim_ipsec *ipsec)
+{
+	u32 i;
+
+	if (ipsec->count == NSIM_IPSEC_MAX_SA_COUNT)
+		return -ENOSPC;
+
+	/* search sa table */
+	for (i = 0; i < NSIM_IPSEC_MAX_SA_COUNT; i++) {
+		if (!ipsec->sa[i].used)
+			return i;
+	}
+
+	return -ENOSPC;
+}
+
+static int nsim_ipsec_parse_proto_keys(struct xfrm_state *xs,
+				       u32 *mykey, u32 *mysalt)
+{
+	const char aes_gcm_name[] = "rfc4106(gcm(aes))";
+	struct net_device *dev = xs->xso.dev;
+	unsigned char *key_data;
+	char *alg_name = NULL;
+	int key_len;
+
+	if (!xs->aead) {
+		netdev_err(dev, "Unsupported IPsec algorithm\n");
+		return -EINVAL;
+	}
+
+	if (xs->aead->alg_icv_len != NSIM_IPSEC_AUTH_BITS) {
+		netdev_err(dev, "IPsec offload requires %d bit authentication\n",
+			   NSIM_IPSEC_AUTH_BITS);
+		return -EINVAL;
+	}
+
+	key_data = &xs->aead->alg_key[0];
+	key_len = xs->aead->alg_key_len;
+	alg_name = xs->aead->alg_name;
+
+	if (strcmp(alg_name, aes_gcm_name)) {
+		netdev_err(dev, "Unsupported IPsec algorithm - please use %s\n",
+			   aes_gcm_name);
+		return -EINVAL;
+	}
+
+	/* 160 accounts for 16 byte key and 4 byte salt */
+	if (key_len > NSIM_IPSEC_AUTH_BITS) {
+		*mysalt = ((u32 *)key_data)[4];
+	} else if (key_len == NSIM_IPSEC_AUTH_BITS) {
+		*mysalt = 0;
+	} else {
+		netdev_err(dev, "IPsec hw offload only supports 128 bit keys with optional 32 bit salt\n");
+		return -EINVAL;
+	}
+	memcpy(mykey, key_data, 16);
+
+	return 0;
+}
+
+static int nsim_ipsec_add_sa(struct xfrm_state *xs)
+{
+	struct nsim_ipsec *ipsec;
+	struct net_device *dev;
+	struct netdevsim *ns;
+	struct nsim_sa sa;
+	u16 sa_idx;
+	int ret;
+
+	dev = xs->xso.dev;
+	ns = netdev_priv(dev);
+	ipsec = &ns->ipsec;
+
+	if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) {
+		netdev_err(dev, "Unsupported protocol 0x%04x for ipsec offload\n",
+			   xs->id.proto);
+		return -EINVAL;
+	}
+
+	if (xs->calg) {
+		netdev_err(dev, "Compression offload not supported\n");
+		return -EINVAL;
+	}
+
+	/* find the first unused index */
+	ret = nsim_ipsec_find_empty_idx(ipsec);
+	if (ret < 0) {
+		netdev_err(dev, "No space for SA in Rx table!\n");
+		return ret;
+	}
+	sa_idx = (u16)ret;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.used = true;
+	sa.xs = xs;
+
+	if (sa.xs->id.proto & IPPROTO_ESP)
+		sa.crypt = xs->ealg || xs->aead;
+
+	/* get the key and salt */
+	ret = nsim_ipsec_parse_proto_keys(xs, sa.key, &sa.salt);
+	if (ret) {
+		netdev_err(dev, "Failed to get key data for SA table\n");
+		return ret;
+	}
+
+	if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) {
+		sa.rx = true;
+
+		if (xs->props.family == AF_INET6)
+			memcpy(sa.ipaddr, &xs->id.daddr.a6, 16);
+		else
+			memcpy(&sa.ipaddr[3], &xs->id.daddr.a4, 4);
+	}
+
+	/* the preparations worked, so save the info */
+	memcpy(&ipsec->sa[sa_idx], &sa, sizeof(sa));
+
+	/* the XFRM stack doesn't like offload_handle == 0,
+	 * so add a bitflag in case our array index is 0
+	 */
+	xs->xso.offload_handle = sa_idx | NSIM_IPSEC_VALID;
+	ipsec->count++;
+
+	return 0;
+}
+
+static void nsim_ipsec_del_sa(struct xfrm_state *xs)
+{
+	struct netdevsim *ns = netdev_priv(xs->xso.dev);
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+	u16 sa_idx;
+
+	sa_idx = xs->xso.offload_handle & ~NSIM_IPSEC_VALID;
+	if (!ipsec->sa[sa_idx].used) {
+		netdev_err(ns->netdev, "Invalid SA for delete sa_idx=%d\n",
+			   sa_idx);
+		return;
+	}
+
+	memset(&ipsec->sa[sa_idx], 0, sizeof(struct nsim_sa));
+	ipsec->count--;
+}
+
+static bool nsim_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
+{
+	struct netdevsim *ns = netdev_priv(xs->xso.dev);
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+
+	ipsec->ok++;
+
+	return true;
+}
+
+static const struct xfrmdev_ops nsim_xfrmdev_ops = {
+	.xdo_dev_state_add	= nsim_ipsec_add_sa,
+	.xdo_dev_state_delete	= nsim_ipsec_del_sa,
+	.xdo_dev_offload_ok	= nsim_ipsec_offload_ok,
+};
+
+bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb)
+{
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+	struct xfrm_state *xs;
+	struct nsim_sa *tsa;
+	u32 sa_idx;
+
+	/* do we even need to check this packet? */
+	if (!skb->sp)
+		return true;
+
+	if (unlikely(!skb->sp->len)) {
+		netdev_err(ns->netdev, "no xfrm state len = %d\n",
+			   skb->sp->len);
+		return false;
+	}
+
+	xs = xfrm_input_state(skb);
+	if (unlikely(!xs)) {
+		netdev_err(ns->netdev, "no xfrm_input_state() xs = %p\n", xs);
+		return false;
+	}
+
+	sa_idx = xs->xso.offload_handle & ~NSIM_IPSEC_VALID;
+	if (unlikely(sa_idx >= NSIM_IPSEC_MAX_SA_COUNT)) {
+		netdev_err(ns->netdev, "bad sa_idx=%d max=%d\n",
+			   sa_idx, NSIM_IPSEC_MAX_SA_COUNT);
+		return false;
+	}
+
+	tsa = &ipsec->sa[sa_idx];
+	if (unlikely(!tsa->used)) {
+		netdev_err(ns->netdev, "unused sa_idx=%d\n", sa_idx);
+		return false;
+	}
+
+	if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) {
+		netdev_err(ns->netdev, "unexpected proto=%d\n", xs->id.proto);
+		return false;
+	}
+
+	ipsec->tx++;
+
+	return true;
+}
+
+void nsim_ipsec_init(struct netdevsim *ns)
+{
+	ns->netdev->xfrmdev_ops = &nsim_xfrmdev_ops;
+
+#define NSIM_ESP_FEATURES	(NETIF_F_HW_ESP | \
+				 NETIF_F_HW_ESP_TX_CSUM | \
+				 NETIF_F_GSO_ESP)
+
+	ns->netdev->features |= NSIM_ESP_FEATURES;
+	ns->netdev->hw_enc_features |= NSIM_ESP_FEATURES;
+
+	ns->ipsec.pfile = debugfs_create_file("ipsec", 0400, ns->ddir, ns,
+					      &ipsec_dbg_fops);
+}
+
+void nsim_ipsec_teardown(struct netdevsim *ns)
+{
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+
+	if (ipsec->count)
+		netdev_err(ns->netdev, "tearing down IPsec offload with %d SAs left\n",
+			   ipsec->count);
+	debugfs_remove_recursive(ipsec->pfile);
+}
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index ec68f38213d9..8d8e2b3f263e 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -22,6 +22,7 @@
 #include <net/netlink.h>
 #include <net/pkt_cls.h>
 #include <net/rtnetlink.h>
+#include <net/switchdev.h>
 
 #include "netdevsim.h"
 
@@ -40,6 +41,9 @@ struct nsim_vf_config {
 
 static u32 nsim_dev_id;
 
+static struct dentry *nsim_ddir;
+static struct dentry *nsim_sdev_ddir;
+
 static int nsim_num_vf(struct device *dev)
 {
 	struct netdevsim *ns = to_nsim(dev);
@@ -144,8 +148,29 @@ static struct device_type nsim_dev_type = {
 	.release = nsim_dev_release,
 };
 
+static int
+nsim_port_attr_get(struct net_device *dev, struct switchdev_attr *attr)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	switch (attr->id) {
+	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
+		attr->u.ppid.id_len = sizeof(ns->sdev->switch_id);
+		memcpy(&attr->u.ppid.id, &ns->sdev->switch_id,
+		       attr->u.ppid.id_len);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static const struct switchdev_ops nsim_switchdev_ops = {
+	.switchdev_port_attr_get	= nsim_port_attr_get,
+};
+
 static int nsim_init(struct net_device *dev)
 {
+	char sdev_ddir_name[10], sdev_link_name[32];
 	struct netdevsim *ns = netdev_priv(dev);
 	int err;
 
@@ -154,9 +179,32 @@ static int nsim_init(struct net_device *dev)
 	if (IS_ERR_OR_NULL(ns->ddir))
 		return -ENOMEM;
 
+	if (!ns->sdev) {
+		ns->sdev = kzalloc(sizeof(*ns->sdev), GFP_KERNEL);
+		if (!ns->sdev) {
+			err = -ENOMEM;
+			goto err_debugfs_destroy;
+		}
+		ns->sdev->refcnt = 1;
+		ns->sdev->switch_id = nsim_dev_id;
+		sprintf(sdev_ddir_name, "%u", ns->sdev->switch_id);
+		ns->sdev->ddir = debugfs_create_dir(sdev_ddir_name,
+						    nsim_sdev_ddir);
+		if (IS_ERR_OR_NULL(ns->sdev->ddir)) {
+			err = PTR_ERR_OR_ZERO(ns->sdev->ddir) ?: -EINVAL;
+			goto err_sdev_free;
+		}
+	} else {
+		sprintf(sdev_ddir_name, "%u", ns->sdev->switch_id);
+		ns->sdev->refcnt++;
+	}
+
+	sprintf(sdev_link_name, "../../" DRV_NAME "_sdev/%s", sdev_ddir_name);
+	debugfs_create_symlink("sdev", ns->ddir, sdev_link_name);
+
 	err = nsim_bpf_init(ns);
 	if (err)
-		goto err_debugfs_destroy;
+		goto err_sdev_destroy;
 
 	ns->dev.id = nsim_dev_id++;
 	ns->dev.bus = &nsim_bus;
@@ -166,17 +214,26 @@ static int nsim_init(struct net_device *dev)
 		goto err_bpf_uninit;
 
 	SET_NETDEV_DEV(dev, &ns->dev);
+	SWITCHDEV_SET_OPS(dev, &nsim_switchdev_ops);
 
 	err = nsim_devlink_setup(ns);
 	if (err)
 		goto err_unreg_dev;
 
+	nsim_ipsec_init(ns);
+
 	return 0;
 
 err_unreg_dev:
 	device_unregister(&ns->dev);
 err_bpf_uninit:
 	nsim_bpf_uninit(ns);
+err_sdev_destroy:
+	if (!--ns->sdev->refcnt) {
+		debugfs_remove_recursive(ns->sdev->ddir);
+err_sdev_free:
+		kfree(ns->sdev);
+	}
 err_debugfs_destroy:
 	debugfs_remove_recursive(ns->ddir);
 	return err;
@@ -186,9 +243,14 @@ static void nsim_uninit(struct net_device *dev)
 {
 	struct netdevsim *ns = netdev_priv(dev);
 
+	nsim_ipsec_teardown(ns);
 	nsim_devlink_teardown(ns);
 	debugfs_remove_recursive(ns->ddir);
 	nsim_bpf_uninit(ns);
+	if (!--ns->sdev->refcnt) {
+		debugfs_remove_recursive(ns->sdev->ddir);
+		kfree(ns->sdev);
+	}
 }
 
 static void nsim_free(struct net_device *dev)
@@ -203,11 +265,15 @@ static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct netdevsim *ns = netdev_priv(dev);
 
+	if (!nsim_ipsec_tx(ns, skb))
+		goto out;
+
 	u64_stats_update_begin(&ns->syncp);
 	ns->tx_packets++;
 	ns->tx_bytes += skb->len;
 	u64_stats_update_end(&ns->syncp);
 
+out:
 	dev_kfree_skb(skb);
 
 	return NETDEV_TX_OK;
@@ -221,8 +287,7 @@ static int nsim_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct netdevsim *ns = netdev_priv(dev);
 
-	if (ns->xdp_prog_mode == XDP_ATTACHED_DRV &&
-	    new_mtu > NSIM_XDP_MAX_MTU)
+	if (ns->xdp.prog && new_mtu > NSIM_XDP_MAX_MTU)
 		return -EBUSY;
 
 	dev->mtu = new_mtu;
@@ -260,7 +325,7 @@ nsim_setup_tc_block(struct net_device *dev, struct tc_block_offload *f)
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, nsim_setup_tc_block_cb,
-					     ns, ns);
+					     ns, ns, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, nsim_setup_tc_block_cb, ns);
 		return 0;
@@ -464,15 +529,46 @@ static int nsim_validate(struct nlattr *tb[], struct nlattr *data[],
 	return 0;
 }
 
+static int nsim_newlink(struct net *src_net, struct net_device *dev,
+			struct nlattr *tb[], struct nlattr *data[],
+			struct netlink_ext_ack *extack)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (tb[IFLA_LINK]) {
+		struct net_device *joindev;
+		struct netdevsim *joinns;
+
+		joindev = __dev_get_by_index(src_net,
+					     nla_get_u32(tb[IFLA_LINK]));
+		if (!joindev)
+			return -ENODEV;
+		if (joindev->netdev_ops != &nsim_netdev_ops)
+			return -EINVAL;
+
+		joinns = netdev_priv(joindev);
+		if (!joinns->sdev || !joinns->sdev->refcnt)
+			return -EINVAL;
+		ns->sdev = joinns->sdev;
+	}
+
+	return register_netdevice(dev);
+}
+
+static void nsim_dellink(struct net_device *dev, struct list_head *head)
+{
+	unregister_netdevice_queue(dev, head);
+}
+
 static struct rtnl_link_ops nsim_link_ops __read_mostly = {
 	.kind		= DRV_NAME,
 	.priv_size	= sizeof(struct netdevsim),
 	.setup		= nsim_setup,
 	.validate	= nsim_validate,
+	.newlink	= nsim_newlink,
+	.dellink	= nsim_dellink,
 };
 
-struct dentry *nsim_ddir;
-
 static int __init nsim_module_init(void)
 {
 	int err;
@@ -481,9 +577,15 @@ static int __init nsim_module_init(void)
 	if (IS_ERR_OR_NULL(nsim_ddir))
 		return -ENOMEM;
 
+	nsim_sdev_ddir = debugfs_create_dir(DRV_NAME "_sdev", NULL);
+	if (IS_ERR_OR_NULL(nsim_sdev_ddir)) {
+		err = -ENOMEM;
+		goto err_debugfs_destroy;
+	}
+
 	err = bus_register(&nsim_bus);
 	if (err)
-		goto err_debugfs_destroy;
+		goto err_sdir_destroy;
 
 	err = nsim_devlink_init();
 	if (err)
@@ -499,6 +601,8 @@ err_dl_fini:
 	nsim_devlink_exit();
 err_unreg_bus:
 	bus_unregister(&nsim_bus);
+err_sdir_destroy:
+	debugfs_remove_recursive(nsim_sdev_ddir);
 err_debugfs_destroy:
 	debugfs_remove_recursive(nsim_ddir);
 	return err;
@@ -509,6 +613,7 @@ static void __exit nsim_module_exit(void)
 	rtnl_link_unregister(&nsim_link_ops);
 	nsim_devlink_exit();
 	bus_unregister(&nsim_bus);
+	debugfs_remove_recursive(nsim_sdev_ddir);
 	debugfs_remove_recursive(nsim_ddir);
 }
 
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 8ca50b72c328..384c254fafc5 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -18,6 +18,7 @@
 #include <linux/list.h>
 #include <linux/netdevice.h>
 #include <linux/u64_stats_sync.h>
+#include <net/xdp.h>
 
 #define DRV_NAME	"netdevsim"
 
@@ -26,9 +27,46 @@
 #define NSIM_EA(extack, msg)	NL_SET_ERR_MSG_MOD((extack), msg)
 
 struct bpf_prog;
+struct bpf_offload_dev;
 struct dentry;
 struct nsim_vf_config;
 
+struct netdevsim_shared_dev {
+	unsigned int refcnt;
+	u32 switch_id;
+
+	struct dentry *ddir;
+
+	struct bpf_offload_dev *bpf_dev;
+
+	struct dentry *ddir_bpf_bound_progs;
+	u32 prog_id_gen;
+
+	struct list_head bpf_bound_progs;
+	struct list_head bpf_bound_maps;
+};
+
+#define NSIM_IPSEC_MAX_SA_COUNT		33
+#define NSIM_IPSEC_VALID		BIT(31)
+
+struct nsim_sa {
+	struct xfrm_state *xs;
+	__be32 ipaddr[4];
+	u32 key[4];
+	u32 salt;
+	bool used;
+	bool crypt;
+	bool rx;
+};
+
+struct nsim_ipsec {
+	struct nsim_sa sa[NSIM_IPSEC_MAX_SA_COUNT];
+	struct dentry *pfile;
+	u32 count;
+	u32 tx;
+	u32 ok;
+};
+
 struct netdevsim {
 	struct net_device *netdev;
 
@@ -37,6 +75,7 @@ struct netdevsim {
 	struct u64_stats_sync syncp;
 
 	struct device dev;
+	struct netdevsim_shared_dev *sdev;
 
 	struct dentry *ddir;
 
@@ -46,16 +85,11 @@ struct netdevsim {
 	struct bpf_prog	*bpf_offloaded;
 	u32 bpf_offloaded_id;
 
-	u32 xdp_flags;
-	int xdp_prog_mode;
-	struct bpf_prog	*xdp_prog;
-
-	u32 prog_id_gen;
+	struct xdp_attachment_info xdp;
+	struct xdp_attachment_info xdp_hw;
 
 	bool bpf_bind_accept;
 	u32 bpf_bind_verifier_delay;
-	struct dentry *ddir_bpf_bound_progs;
-	struct list_head bpf_bound_progs;
 
 	bool bpf_tc_accept;
 	bool bpf_tc_non_bound_accept;
@@ -63,14 +97,12 @@ struct netdevsim {
 	bool bpf_xdpoffload_accept;
 
 	bool bpf_map_accept;
-	struct list_head bpf_bound_maps;
 #if IS_ENABLED(CONFIG_NET_DEVLINK)
 	struct devlink *devlink;
 #endif
+	struct nsim_ipsec ipsec;
 };
 
-extern struct dentry *nsim_ddir;
-
 #ifdef CONFIG_BPF_SYSCALL
 int nsim_bpf_init(struct netdevsim *ns);
 void nsim_bpf_uninit(struct netdevsim *ns);
@@ -148,6 +180,25 @@ static inline void nsim_devlink_exit(void)
 }
 #endif
 
+#if IS_ENABLED(CONFIG_XFRM_OFFLOAD)
+void nsim_ipsec_init(struct netdevsim *ns);
+void nsim_ipsec_teardown(struct netdevsim *ns);
+bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb);
+#else
+static inline void nsim_ipsec_init(struct netdevsim *ns)
+{
+}
+
+static inline void nsim_ipsec_teardown(struct netdevsim *ns)
+{
+}
+
+static inline bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb)
+{
+	return true;
+}
+#endif
+
 static inline struct netdevsim *to_nsim(struct device *ptr)
 {
 	return container_of(ptr, struct netdevsim, dev);
diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c
index 9f6f7ccd44f7..b12023bc2cab 100644
--- a/drivers/net/ntb_netdev.c
+++ b/drivers/net/ntb_netdev.c
@@ -430,7 +430,7 @@ static int ntb_netdev_probe(struct device *client_dev)
 	ndev->hw_features = ndev->features;
 	ndev->watchdog_timeo = msecs_to_jiffies(NTB_TX_TIMEOUT_MS);
 
-	random_ether_addr(ndev->perm_addr);
+	eth_random_addr(ndev->perm_addr);
 	memcpy(ndev->dev_addr, ndev->perm_addr, ndev->addr_len);
 
 	ndev->netdev_ops = &ntb_netdev_ops;
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 343989f9f9d9..82070792edbb 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -28,7 +28,7 @@ config MDIO_BCM_IPROC
 
 config MDIO_BCM_UNIMAC
 	tristate "Broadcom UniMAC MDIO bus controller"
-	depends on HAS_IOMEM && OF_MDIO
+	depends on HAS_IOMEM
 	help
 	  This module provides a driver for the Broadcom UniMAC MDIO busses.
 	  This hardware can be found in the Broadcom GENET Ethernet MAC
@@ -92,7 +92,8 @@ config MDIO_CAVIUM
 
 config MDIO_GPIO
 	tristate "GPIO lib-based bitbanged MDIO buses"
-	depends on MDIO_BITBANG && GPIOLIB
+	depends on MDIO_BITBANG
+	depends on GPIOLIB || COMPILE_TEST
 	---help---
 	  Supports GPIO lib-based MDIO busses.
 
@@ -213,6 +214,7 @@ comment "MII PHY device drivers"
 config SFP
 	tristate "SFP cage support"
 	depends on I2C && PHYLINK
+	depends on HWMON || HWMON=n
 	select MDIO_I2C
 
 config AMD_PHY
diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index 01d2ff2f6241..b2b6307d64a4 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -229,6 +229,7 @@ static int bcm7xxx_28nm_config_init(struct phy_device *phydev)
 	phy_read(phydev, MII_BMSR);
 
 	switch (rev) {
+	case 0xa0:
 	case 0xb0:
 		ret = bcm7xxx_28nm_b0_afe_config_init(phydev);
 		break;
@@ -659,6 +660,7 @@ static struct phy_driver bcm7xxx_driver[] = {
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7439, "Broadcom BCM7439"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7439_2, "Broadcom BCM7439 (2)"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7445, "Broadcom BCM7445"),
+	BCM7XXX_28NM_GPHY(PHY_ID_BCM_OMEGA, "Broadcom Omega Combo GPHY"),
 	BCM7XXX_40NM_EPHY(PHY_ID_BCM7346, "Broadcom BCM7346"),
 	BCM7XXX_40NM_EPHY(PHY_ID_BCM7362, "Broadcom BCM7362"),
 	BCM7XXX_40NM_EPHY(PHY_ID_BCM7425, "Broadcom BCM7425"),
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 79e9b103188b..29aa8d772b0c 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -757,13 +757,16 @@ static int decode_evnt(struct dp83640_private *dp83640,
 
 	phy_txts = data;
 
-	switch (words) { /* fall through in every case */
+	switch (words) {
 	case 3:
 		dp83640->edata.sec_hi = phy_txts->sec_hi;
+		/* fall through */
 	case 2:
 		dp83640->edata.sec_lo = phy_txts->sec_lo;
+		/* fall through */
 	case 1:
 		dp83640->edata.ns_hi = phy_txts->ns_hi;
+		/* fall through */
 	case 0:
 		dp83640->edata.ns_lo = phy_txts->ns_lo;
 	}
diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c
index 49ac678eb2dc..78cad134a79e 100644
--- a/drivers/net/phy/dp83tc811.c
+++ b/drivers/net/phy/dp83tc811.c
@@ -21,6 +21,7 @@
 #define MII_DP83811_SGMII_CTRL	0x09
 #define MII_DP83811_INT_STAT1	0x12
 #define MII_DP83811_INT_STAT2	0x13
+#define MII_DP83811_INT_STAT3	0x18
 #define MII_DP83811_RESET_CTRL	0x1f
 
 #define DP83811_HW_RESET	BIT(15)
@@ -44,6 +45,11 @@
 #define DP83811_OVERVOLTAGE_INT_EN	BIT(6)
 #define DP83811_UNDERVOLTAGE_INT_EN	BIT(7)
 
+/* INT_STAT3 bits */
+#define DP83811_LPS_INT_EN	BIT(0)
+#define DP83811_NO_FRAME_INT_EN	BIT(3)
+#define DP83811_POR_DONE_INT_EN	BIT(4)
+
 #define MII_DP83811_RXSOP1	0x04a5
 #define MII_DP83811_RXSOP2	0x04a6
 #define MII_DP83811_RXSOP3	0x04a7
@@ -81,6 +87,10 @@ static int dp83811_ack_interrupt(struct phy_device *phydev)
 	if (err < 0)
 		return err;
 
+	err = phy_read(phydev, MII_DP83811_INT_STAT3);
+	if (err < 0)
+		return err;
+
 	return 0;
 }
 
@@ -216,6 +226,18 @@ static int dp83811_config_intr(struct phy_device *phydev)
 				DP83811_UNDERVOLTAGE_INT_EN);
 
 		err = phy_write(phydev, MII_DP83811_INT_STAT2, misr_status);
+		if (err < 0)
+			return err;
+
+		misr_status = phy_read(phydev, MII_DP83811_INT_STAT3);
+		if (misr_status < 0)
+			return misr_status;
+
+		misr_status |= (DP83811_LPS_INT_EN |
+				DP83811_NO_FRAME_INT_EN |
+				DP83811_POR_DONE_INT_EN);
+
+		err = phy_write(phydev, MII_DP83811_INT_STAT3, misr_status);
 
 	} else {
 		err = phy_write(phydev, MII_DP83811_INT_STAT1, 0);
@@ -223,6 +245,10 @@ static int dp83811_config_intr(struct phy_device *phydev)
 			return err;
 
 		err = phy_write(phydev, MII_DP83811_INT_STAT2, 0);
+		if (err < 0)
+			return err;
+
+		err = phy_write(phydev, MII_DP83811_INT_STAT3, 0);
 	}
 
 	return err;
@@ -258,21 +284,19 @@ static int dp83811_config_init(struct phy_device *phydev)
 	if (err < 0)
 		return err;
 
+	value = phy_read(phydev, MII_DP83811_SGMII_CTRL);
 	if (phydev->interface == PHY_INTERFACE_MODE_SGMII) {
-		value = phy_read(phydev, MII_DP83811_SGMII_CTRL);
-		if (!(value & DP83811_SGMII_EN)) {
-			err = phy_write(phydev, MII_DP83811_SGMII_CTRL,
+		err = phy_write(phydev, MII_DP83811_SGMII_CTRL,
 					(DP83811_SGMII_EN | value));
-			if (err < 0)
-				return err;
-		} else {
-			err = phy_write(phydev, MII_DP83811_SGMII_CTRL,
-					(~DP83811_SGMII_EN & value));
-			if (err < 0)
-				return err;
-		}
+	} else {
+		err = phy_write(phydev, MII_DP83811_SGMII_CTRL,
+				(~DP83811_SGMII_EN & value));
 	}
 
+	if (err < 0)
+
+		return err;
+
 	value = DP83811_WOL_MAGIC_EN | DP83811_WOL_SECURE_ON | DP83811_WOL_EN;
 
 	return phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG,
diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index 001fe1df7557..67b260877f30 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -259,10 +259,8 @@ static int __init fixed_mdio_bus_init(void)
 	int ret;
 
 	pdev = platform_device_register_simple("Fixed MDIO bus", 0, NULL, 0);
-	if (IS_ERR(pdev)) {
-		ret = PTR_ERR(pdev);
-		goto err_pdev;
-	}
+	if (IS_ERR(pdev))
+		return PTR_ERR(pdev);
 
 	fmb->mii_bus = mdiobus_alloc();
 	if (fmb->mii_bus == NULL) {
@@ -287,7 +285,6 @@ err_mdiobus_alloc:
 	mdiobus_free(fmb->mii_bus);
 err_mdiobus_reg:
 	platform_device_unregister(pdev);
-err_pdev:
 	return ret;
 }
 module_init(fixed_mdio_bus_init);
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 1cd439bdf608..f7c69ca34056 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -679,7 +679,7 @@ static int m88e1116r_config_init(struct phy_device *phydev)
 	if (err < 0)
 		return err;
 
-	mdelay(500);
+	msleep(500);
 
 	err = marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE);
 	if (err < 0)
diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c
index 0c5b68e7da51..c017486e9b86 100644
--- a/drivers/net/phy/mdio-mux-bcm-iproc.c
+++ b/drivers/net/phy/mdio-mux-bcm-iproc.c
@@ -13,7 +13,7 @@
  * You should have received a copy of the GNU General Public License
  * version 2 (GPLv2) along with this source code.
  */
-
+#include <linux/clk.h>
 #include <linux/platform_device.h>
 #include <linux/device.h>
 #include <linux/of_mdio.h>
@@ -22,7 +22,14 @@
 #include <linux/mdio-mux.h>
 #include <linux/delay.h>
 
-#define MDIO_PARAM_OFFSET		0x00
+#define MDIO_RATE_ADJ_EXT_OFFSET	0x000
+#define MDIO_RATE_ADJ_INT_OFFSET	0x004
+#define MDIO_RATE_ADJ_DIVIDENT_SHIFT	16
+
+#define MDIO_SCAN_CTRL_OFFSET		0x008
+#define MDIO_SCAN_CTRL_OVRIDE_EXT_MSTR	28
+
+#define MDIO_PARAM_OFFSET		0x23c
 #define MDIO_PARAM_MIIM_CYCLE		29
 #define MDIO_PARAM_INTERNAL_SEL		25
 #define MDIO_PARAM_BUS_ID		22
@@ -30,27 +37,56 @@
 #define MDIO_PARAM_PHY_ID		16
 #define MDIO_PARAM_PHY_DATA		0
 
-#define MDIO_READ_OFFSET		0x04
+#define MDIO_READ_OFFSET		0x240
 #define MDIO_READ_DATA_MASK		0xffff
-#define MDIO_ADDR_OFFSET		0x08
+#define MDIO_ADDR_OFFSET		0x244
 
-#define MDIO_CTRL_OFFSET		0x0C
+#define MDIO_CTRL_OFFSET		0x248
 #define MDIO_CTRL_WRITE_OP		0x1
 #define MDIO_CTRL_READ_OP		0x2
 
-#define MDIO_STAT_OFFSET		0x10
+#define MDIO_STAT_OFFSET		0x24c
 #define MDIO_STAT_DONE			1
 
 #define BUS_MAX_ADDR			32
 #define EXT_BUS_START_ADDR		16
 
+#define MDIO_REG_ADDR_SPACE_SIZE	0x250
+
+#define MDIO_OPERATING_FREQUENCY	11000000
+#define MDIO_RATE_ADJ_DIVIDENT		1
+
 struct iproc_mdiomux_desc {
 	void *mux_handle;
 	void __iomem *base;
 	struct device *dev;
 	struct mii_bus *mii_bus;
+	struct clk *core_clk;
 };
 
+static void mdio_mux_iproc_config(struct iproc_mdiomux_desc *md)
+{
+	u32 divisor;
+	u32 val;
+
+	/* Disable external mdio master access */
+	val = readl(md->base + MDIO_SCAN_CTRL_OFFSET);
+	val |= BIT(MDIO_SCAN_CTRL_OVRIDE_EXT_MSTR);
+	writel(val, md->base + MDIO_SCAN_CTRL_OFFSET);
+
+	if (md->core_clk) {
+		/* use rate adjust regs to derrive the mdio's operating
+		 * frequency from the specified core clock
+		 */
+		divisor = clk_get_rate(md->core_clk) / MDIO_OPERATING_FREQUENCY;
+		divisor = divisor / (MDIO_RATE_ADJ_DIVIDENT + 1);
+		val = divisor;
+		val |= MDIO_RATE_ADJ_DIVIDENT << MDIO_RATE_ADJ_DIVIDENT_SHIFT;
+		writel(val, md->base + MDIO_RATE_ADJ_EXT_OFFSET);
+		writel(val, md->base + MDIO_RATE_ADJ_INT_OFFSET);
+	}
+}
+
 static int iproc_mdio_wait_for_idle(void __iomem *base, bool result)
 {
 	unsigned int timeout = 1000; /* loop for 1s */
@@ -169,18 +205,39 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev)
 	md->dev = &pdev->dev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (res->start & 0xfff) {
+		/* For backward compatibility in case the
+		 * base address is specified with an offset.
+		 */
+		dev_info(&pdev->dev, "fix base address in dt-blob\n");
+		res->start &= ~0xfff;
+		res->end = res->start + MDIO_REG_ADDR_SPACE_SIZE - 1;
+	}
 	md->base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(md->base)) {
 		dev_err(&pdev->dev, "failed to ioremap register\n");
 		return PTR_ERR(md->base);
 	}
 
-	md->mii_bus = mdiobus_alloc();
+	md->mii_bus = devm_mdiobus_alloc(&pdev->dev);
 	if (!md->mii_bus) {
 		dev_err(&pdev->dev, "mdiomux bus alloc failed\n");
 		return -ENOMEM;
 	}
 
+	md->core_clk = devm_clk_get(&pdev->dev, NULL);
+	if (md->core_clk == ERR_PTR(-ENOENT) ||
+	    md->core_clk == ERR_PTR(-EINVAL))
+		md->core_clk = NULL;
+	else if (IS_ERR(md->core_clk))
+		return PTR_ERR(md->core_clk);
+
+	rc = clk_prepare_enable(md->core_clk);
+	if (rc) {
+		dev_err(&pdev->dev, "failed to enable core clk\n");
+		return rc;
+	}
+
 	bus = md->mii_bus;
 	bus->priv = md;
 	bus->name = "iProc MDIO mux bus";
@@ -194,7 +251,7 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev)
 	rc = mdiobus_register(bus);
 	if (rc) {
 		dev_err(&pdev->dev, "mdiomux registration failed\n");
-		goto out;
+		goto out_clk;
 	}
 
 	platform_set_drvdata(pdev, md);
@@ -206,13 +263,15 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev)
 		goto out_register;
 	}
 
+	mdio_mux_iproc_config(md);
+
 	dev_info(md->dev, "iProc mdiomux registered\n");
 	return 0;
 
 out_register:
 	mdiobus_unregister(bus);
-out:
-	mdiobus_free(bus);
+out_clk:
+	clk_disable_unprepare(md->core_clk);
 	return rc;
 }
 
@@ -222,11 +281,37 @@ static int mdio_mux_iproc_remove(struct platform_device *pdev)
 
 	mdio_mux_uninit(md->mux_handle);
 	mdiobus_unregister(md->mii_bus);
-	mdiobus_free(md->mii_bus);
+	clk_disable_unprepare(md->core_clk);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int mdio_mux_iproc_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct iproc_mdiomux_desc *md = platform_get_drvdata(pdev);
+
+	clk_disable_unprepare(md->core_clk);
 
 	return 0;
 }
 
+static int mdio_mux_iproc_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct iproc_mdiomux_desc *md = platform_get_drvdata(pdev);
+
+	clk_prepare_enable(md->core_clk);
+	mdio_mux_iproc_config(md);
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(mdio_mux_iproc_pm_ops,
+			 mdio_mux_iproc_suspend, mdio_mux_iproc_resume);
+
 static const struct of_device_id mdio_mux_iproc_match[] = {
 	{
 		.compatible = "brcm,mdio-mux-iproc",
@@ -239,6 +324,7 @@ static struct platform_driver mdiomux_iproc_driver = {
 	.driver = {
 		.name		= "mdio-mux-iproc",
 		.of_match_table = mdio_mux_iproc_match,
+		.pm		= &mdio_mux_iproc_pm_ops,
 	},
 	.probe		= mdio_mux_iproc_probe,
 	.remove		= mdio_mux_iproc_remove,
diff --git a/drivers/net/phy/mdio-mux-gpio.c b/drivers/net/phy/mdio-mux-gpio.c
index 082ffef0dec4..bc90764a8b8d 100644
--- a/drivers/net/phy/mdio-mux-gpio.c
+++ b/drivers/net/phy/mdio-mux-gpio.c
@@ -20,23 +20,23 @@
 struct mdio_mux_gpio_state {
 	struct gpio_descs *gpios;
 	void *mux_handle;
+	int values[];
 };
 
 static int mdio_mux_gpio_switch_fn(int current_child, int desired_child,
 				   void *data)
 {
 	struct mdio_mux_gpio_state *s = data;
-	int values[s->gpios->ndescs];
 	unsigned int n;
 
 	if (current_child == desired_child)
 		return 0;
 
 	for (n = 0; n < s->gpios->ndescs; n++)
-		values[n] = (desired_child >> n) & 1;
+		s->values[n] = (desired_child >> n) & 1;
 
 	gpiod_set_array_value_cansleep(s->gpios->ndescs, s->gpios->desc,
-				       values);
+				       s->values);
 
 	return 0;
 }
@@ -44,15 +44,21 @@ static int mdio_mux_gpio_switch_fn(int current_child, int desired_child,
 static int mdio_mux_gpio_probe(struct platform_device *pdev)
 {
 	struct mdio_mux_gpio_state *s;
+	struct gpio_descs *gpios;
 	int r;
 
-	s = devm_kzalloc(&pdev->dev, sizeof(*s), GFP_KERNEL);
-	if (!s)
+	gpios = gpiod_get_array(&pdev->dev, NULL, GPIOD_OUT_LOW);
+	if (IS_ERR(gpios))
+		return PTR_ERR(gpios);
+
+	s = devm_kzalloc(&pdev->dev, struct_size(s, values, gpios->ndescs),
+			 GFP_KERNEL);
+	if (!s) {
+		gpiod_put_array(gpios);
 		return -ENOMEM;
+	}
 
-	s->gpios = gpiod_get_array(&pdev->dev, NULL, GPIOD_OUT_LOW);
-	if (IS_ERR(s->gpios))
-		return PTR_ERR(s->gpios);
+	s->gpios = gpios;
 
 	r = mdio_mux_init(&pdev->dev, pdev->dev.of_node,
 			  mdio_mux_gpio_switch_fn, &s->mux_handle, s, NULL);
diff --git a/drivers/net/phy/mscc.c b/drivers/net/phy/mscc.c
index 650c2667d523..84ca9ff40ae0 100644
--- a/drivers/net/phy/mscc.c
+++ b/drivers/net/phy/mscc.c
@@ -123,7 +123,7 @@ static const struct vsc8531_edge_rate_table edge_table[] = {
 };
 #endif /* CONFIG_OF_MDIO */
 
-static int vsc85xx_phy_page_set(struct phy_device *phydev, u8 page)
+static int vsc85xx_phy_page_set(struct phy_device *phydev, u16 page)
 {
 	int rc;
 
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 6c9b24fe3148..1ee25877c4d1 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -467,6 +467,20 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
 }
 EXPORT_SYMBOL(phy_mii_ioctl);
 
+static int phy_config_aneg(struct phy_device *phydev)
+{
+	if (phydev->drv->config_aneg)
+		return phydev->drv->config_aneg(phydev);
+
+	/* Clause 45 PHYs that don't implement Clause 22 registers are not
+	 * allowed to call genphy_config_aneg()
+	 */
+	if (phydev->is_c45 && !(phydev->c45_ids.devices_in_package & BIT(0)))
+		return -EOPNOTSUPP;
+
+	return genphy_config_aneg(phydev);
+}
+
 /**
  * phy_start_aneg_priv - start auto-negotiation for this PHY device
  * @phydev: the phy_device struct
@@ -493,10 +507,7 @@ static int phy_start_aneg_priv(struct phy_device *phydev, bool sync)
 	/* Invalidate LP advertising flags */
 	phydev->lp_advertising = 0;
 
-	if (phydev->drv->config_aneg)
-		err = phydev->drv->config_aneg(phydev);
-	else
-		err = genphy_config_aneg(phydev);
+	err = phy_config_aneg(phydev);
 	if (err < 0)
 		goto out_unlock;
 
@@ -514,7 +525,7 @@ static int phy_start_aneg_priv(struct phy_device *phydev, bool sync)
 	 * negotiation may already be done and aneg interrupt may not be
 	 * generated.
 	 */
-	if (phydev->irq != PHY_POLL && phydev->state == PHY_AN) {
+	if (!phy_polling_mode(phydev) && phydev->state == PHY_AN) {
 		err = phy_aneg_done(phydev);
 		if (err > 0) {
 			trigger = true;
@@ -546,6 +557,84 @@ int phy_start_aneg(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(phy_start_aneg);
 
+static int phy_poll_aneg_done(struct phy_device *phydev)
+{
+	unsigned int retries = 100;
+	int ret;
+
+	do {
+		msleep(100);
+		ret = phy_aneg_done(phydev);
+	} while (!ret && --retries);
+
+	if (!ret)
+		return -ETIMEDOUT;
+
+	return ret < 0 ? ret : 0;
+}
+
+/**
+ * phy_speed_down - set speed to lowest speed supported by both link partners
+ * @phydev: the phy_device struct
+ * @sync: perform action synchronously
+ *
+ * Description: Typically used to save energy when waiting for a WoL packet
+ *
+ * WARNING: Setting sync to false may cause the system being unable to suspend
+ * in case the PHY generates an interrupt when finishing the autonegotiation.
+ * This interrupt may wake up the system immediately after suspend.
+ * Therefore use sync = false only if you're sure it's safe with the respective
+ * network chip.
+ */
+int phy_speed_down(struct phy_device *phydev, bool sync)
+{
+	u32 adv = phydev->lp_advertising & phydev->supported;
+	u32 adv_old = phydev->advertising;
+	int ret;
+
+	if (phydev->autoneg != AUTONEG_ENABLE)
+		return 0;
+
+	if (adv & PHY_10BT_FEATURES)
+		phydev->advertising &= ~(PHY_100BT_FEATURES |
+					 PHY_1000BT_FEATURES);
+	else if (adv & PHY_100BT_FEATURES)
+		phydev->advertising &= ~PHY_1000BT_FEATURES;
+
+	if (phydev->advertising == adv_old)
+		return 0;
+
+	ret = phy_config_aneg(phydev);
+	if (ret)
+		return ret;
+
+	return sync ? phy_poll_aneg_done(phydev) : 0;
+}
+EXPORT_SYMBOL_GPL(phy_speed_down);
+
+/**
+ * phy_speed_up - (re)set advertised speeds to all supported speeds
+ * @phydev: the phy_device struct
+ *
+ * Description: Used to revert the effect of phy_speed_down
+ */
+int phy_speed_up(struct phy_device *phydev)
+{
+	u32 mask = PHY_10BT_FEATURES | PHY_100BT_FEATURES | PHY_1000BT_FEATURES;
+	u32 adv_old = phydev->advertising;
+
+	if (phydev->autoneg != AUTONEG_ENABLE)
+		return 0;
+
+	phydev->advertising = (adv_old & ~mask) | (phydev->supported & mask);
+
+	if (phydev->advertising == adv_old)
+		return 0;
+
+	return phy_config_aneg(phydev);
+}
+EXPORT_SYMBOL_GPL(phy_speed_up);
+
 /**
  * phy_start_machine - start PHY state machine tracking
  * @phydev: the phy_device struct
@@ -894,7 +983,7 @@ void phy_state_machine(struct work_struct *work)
 			needs_aneg = true;
 		break;
 	case PHY_NOLINK:
-		if (phydev->irq != PHY_POLL)
+		if (!phy_polling_mode(phydev))
 			break;
 
 		err = phy_read_status(phydev);
@@ -935,7 +1024,7 @@ void phy_state_machine(struct work_struct *work)
 		/* Only register a CHANGE if we are polling and link changed
 		 * since latest checking.
 		 */
-		if (phydev->irq == PHY_POLL) {
+		if (phy_polling_mode(phydev)) {
 			old_link = phydev->link;
 			err = phy_read_status(phydev);
 			if (err)
@@ -1034,7 +1123,7 @@ void phy_state_machine(struct work_struct *work)
 	 * PHY, if PHY_IGNORE_INTERRUPT is set, then we will be moving
 	 * between states from phy_mac_interrupt()
 	 */
-	if (phydev->irq == PHY_POLL)
+	if (phy_polling_mode(phydev))
 		queue_delayed_work(system_power_efficient_wq, &phydev->state_queue,
 				   PHY_STATE_TIME * HZ);
 }
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index b9f5f40a7ac1..db1172db1e7c 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1555,6 +1555,14 @@ int genphy_read_status(struct phy_device *phydev)
 			if (adv < 0)
 				return adv;
 
+			if (lpagb & LPA_1000MSFAIL) {
+				if (adv & CTL1000_ENABLE_MASTER)
+					phydev_err(phydev, "Master/Slave resolution failed, maybe conflicting manual settings?\n");
+				else
+					phydev_err(phydev, "Master/Slave resolution failed\n");
+				return -ENOLINK;
+			}
+
 			phydev->lp_advertising =
 				mii_stat1000_to_ethtool_lpa_t(lpagb);
 			common_adv_gb = lpagb & adv << 2;
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index af4dc4425be2..3ba5cf2a8a5f 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1688,4 +1688,34 @@ static const struct sfp_upstream_ops sfp_phylink_ops = {
 	.disconnect_phy = phylink_sfp_disconnect_phy,
 };
 
+/* Helpers for MAC drivers */
+
+/**
+ * phylink_helper_basex_speed() - 1000BaseX/2500BaseX helper
+ * @state: a pointer to a &struct phylink_link_state
+ *
+ * Inspect the interface mode, advertising mask or forced speed and
+ * decide whether to run at 2.5Gbit or 1Gbit appropriately, switching
+ * the interface mode to suit.  @state->interface is appropriately
+ * updated, and the advertising mask has the "other" baseX_Full flag
+ * cleared.
+ */
+void phylink_helper_basex_speed(struct phylink_link_state *state)
+{
+	if (phy_interface_mode_is_8023z(state->interface)) {
+		bool want_2500 = state->an_enabled ?
+			phylink_test(state->advertising, 2500baseX_Full) :
+			state->speed == SPEED_2500;
+
+		if (want_2500) {
+			phylink_clear(state->advertising, 1000baseX_Full);
+			state->interface = PHY_INTERFACE_MODE_2500BASEX;
+		} else {
+			phylink_clear(state->advertising, 2500baseX_Full);
+			state->interface = PHY_INTERFACE_MODE_1000BASEX;
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(phylink_helper_basex_speed);
+
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 082fb40c656d..7fc8508b5231 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -37,6 +37,9 @@
 #define RTL8201F_ISR				0x1e
 #define RTL8201F_IER				0x13
 
+#define RTL8366RB_POWER_SAVE			0x15
+#define RTL8366RB_POWER_SAVE_ON			BIT(12)
+
 MODULE_DESCRIPTION("Realtek PHY driver");
 MODULE_AUTHOR("Johnson Leung");
 MODULE_LICENSE("GPL");
@@ -128,6 +131,37 @@ static int rtl8211f_config_intr(struct phy_device *phydev)
 	return phy_write_paged(phydev, 0xa42, RTL821x_INER, val);
 }
 
+static int rtl8211_config_aneg(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = genphy_config_aneg(phydev);
+	if (ret < 0)
+		return ret;
+
+	/* Quirk was copied from vendor driver. Unfortunately it includes no
+	 * description of the magic numbers.
+	 */
+	if (phydev->speed == SPEED_100 && phydev->autoneg == AUTONEG_DISABLE) {
+		phy_write(phydev, 0x17, 0x2138);
+		phy_write(phydev, 0x0e, 0x0260);
+	} else {
+		phy_write(phydev, 0x17, 0x2108);
+		phy_write(phydev, 0x0e, 0x0000);
+	}
+
+	return 0;
+}
+
+static int rtl8211c_config_init(struct phy_device *phydev)
+{
+	/* RTL8211C has an issue when operating in Gigabit slave mode */
+	phy_set_bits(phydev, MII_CTRL1000,
+		     CTL1000_ENABLE_MASTER | CTL1000_AS_MASTER);
+
+	return genphy_config_init(phydev);
+}
+
 static int rtl8211f_config_init(struct phy_device *phydev)
 {
 	int ret;
@@ -159,6 +193,24 @@ static int rtl8211b_resume(struct phy_device *phydev)
 	return genphy_resume(phydev);
 }
 
+static int rtl8366rb_config_init(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = genphy_config_init(phydev);
+	if (ret < 0)
+		return ret;
+
+	ret = phy_set_bits(phydev, RTL8366RB_POWER_SAVE,
+			   RTL8366RB_POWER_SAVE_ON);
+	if (ret) {
+		dev_err(&phydev->mdio.dev,
+			"error enabling power management\n");
+	}
+
+	return ret;
+}
+
 static struct phy_driver realtek_drvs[] = {
 	{
 		.phy_id         = 0x00008201,
@@ -179,6 +231,14 @@ static struct phy_driver realtek_drvs[] = {
 		.read_page	= rtl821x_read_page,
 		.write_page	= rtl821x_write_page,
 	}, {
+		.phy_id		= 0x001cc910,
+		.name		= "RTL8211 Gigabit Ethernet",
+		.phy_id_mask	= 0x001fffff,
+		.features	= PHY_GBIT_FEATURES,
+		.config_aneg	= rtl8211_config_aneg,
+		.read_mmd	= &genphy_read_mmd_unsupported,
+		.write_mmd	= &genphy_write_mmd_unsupported,
+	}, {
 		.phy_id		= 0x001cc912,
 		.name		= "RTL8211B Gigabit Ethernet",
 		.phy_id_mask	= 0x001fffff,
@@ -191,6 +251,14 @@ static struct phy_driver realtek_drvs[] = {
 		.suspend	= rtl8211b_suspend,
 		.resume		= rtl8211b_resume,
 	}, {
+		.phy_id		= 0x001cc913,
+		.name		= "RTL8211C Gigabit Ethernet",
+		.phy_id_mask	= 0x001fffff,
+		.features	= PHY_GBIT_FEATURES,
+		.config_init	= rtl8211c_config_init,
+		.read_mmd	= &genphy_read_mmd_unsupported,
+		.write_mmd	= &genphy_write_mmd_unsupported,
+	}, {
 		.phy_id		= 0x001cc914,
 		.name		= "RTL8211DN Gigabit Ethernet",
 		.phy_id_mask	= 0x001fffff,
@@ -223,6 +291,15 @@ static struct phy_driver realtek_drvs[] = {
 		.resume		= genphy_resume,
 		.read_page	= rtl821x_read_page,
 		.write_page	= rtl821x_write_page,
+	}, {
+		.phy_id		= 0x001cc961,
+		.name		= "RTL8366RB Gigabit Ethernet",
+		.phy_id_mask	= 0x001fffff,
+		.features	= PHY_GBIT_FEATURES,
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_init	= &rtl8366rb_config_init,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
 	},
 };
 
@@ -230,10 +307,13 @@ module_phy_driver(realtek_drvs);
 
 static struct mdio_device_id __maybe_unused realtek_tbl[] = {
 	{ 0x001cc816, 0x001fffff },
+	{ 0x001cc910, 0x001fffff },
 	{ 0x001cc912, 0x001fffff },
+	{ 0x001cc913, 0x001fffff },
 	{ 0x001cc914, 0x001fffff },
 	{ 0x001cc915, 0x001fffff },
 	{ 0x001cc916, 0x001fffff },
+	{ 0x001cc961, 0x001fffff },
 	{ }
 };
 
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index c4c92db86dfa..4637d980310e 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -1,5 +1,7 @@
+#include <linux/ctype.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
+#include <linux/hwmon.h>
 #include <linux/i2c.h>
 #include <linux/interrupt.h>
 #include <linux/jiffies.h>
@@ -58,6 +60,69 @@ enum {
 	SFP_S_TX_DISABLE,
 };
 
+static const char  * const mod_state_strings[] = {
+	[SFP_MOD_EMPTY] = "empty",
+	[SFP_MOD_PROBE] = "probe",
+	[SFP_MOD_HPOWER] = "hpower",
+	[SFP_MOD_PRESENT] = "present",
+	[SFP_MOD_ERROR] = "error",
+};
+
+static const char *mod_state_to_str(unsigned short mod_state)
+{
+	if (mod_state >= ARRAY_SIZE(mod_state_strings))
+		return "Unknown module state";
+	return mod_state_strings[mod_state];
+}
+
+static const char * const dev_state_strings[] = {
+	[SFP_DEV_DOWN] = "down",
+	[SFP_DEV_UP] = "up",
+};
+
+static const char *dev_state_to_str(unsigned short dev_state)
+{
+	if (dev_state >= ARRAY_SIZE(dev_state_strings))
+		return "Unknown device state";
+	return dev_state_strings[dev_state];
+}
+
+static const char * const event_strings[] = {
+	[SFP_E_INSERT] = "insert",
+	[SFP_E_REMOVE] = "remove",
+	[SFP_E_DEV_DOWN] = "dev_down",
+	[SFP_E_DEV_UP] = "dev_up",
+	[SFP_E_TX_FAULT] = "tx_fault",
+	[SFP_E_TX_CLEAR] = "tx_clear",
+	[SFP_E_LOS_HIGH] = "los_high",
+	[SFP_E_LOS_LOW] = "los_low",
+	[SFP_E_TIMEOUT] = "timeout",
+};
+
+static const char *event_to_str(unsigned short event)
+{
+	if (event >= ARRAY_SIZE(event_strings))
+		return "Unknown event";
+	return event_strings[event];
+}
+
+static const char * const sm_state_strings[] = {
+	[SFP_S_DOWN] = "down",
+	[SFP_S_INIT] = "init",
+	[SFP_S_WAIT_LOS] = "wait_los",
+	[SFP_S_LINK_UP] = "link_up",
+	[SFP_S_TX_FAULT] = "tx_fault",
+	[SFP_S_REINIT] = "reinit",
+	[SFP_S_TX_DISABLE] = "rx_disable",
+};
+
+static const char *sm_state_to_str(unsigned short sm_state)
+{
+	if (sm_state >= ARRAY_SIZE(sm_state_strings))
+		return "Unknown state";
+	return sm_state_strings[sm_state];
+}
+
 static const char *gpio_of_names[] = {
 	"mod-def0",
 	"los",
@@ -131,6 +196,12 @@ struct sfp {
 	unsigned int sm_retries;
 
 	struct sfp_eeprom_id id;
+#if IS_ENABLED(CONFIG_HWMON)
+	struct sfp_diag diag;
+	struct device *hwmon_dev;
+	char *hwmon_name;
+#endif
+
 };
 
 static bool sff_module_supported(const struct sfp_eeprom_id *id)
@@ -316,6 +387,719 @@ static unsigned int sfp_check(void *buf, size_t len)
 	return check;
 }
 
+/* hwmon */
+#if IS_ENABLED(CONFIG_HWMON)
+static umode_t sfp_hwmon_is_visible(const void *data,
+				    enum hwmon_sensor_types type,
+				    u32 attr, int channel)
+{
+	const struct sfp *sfp = data;
+
+	switch (type) {
+	case hwmon_temp:
+		switch (attr) {
+		case hwmon_temp_input:
+		case hwmon_temp_min_alarm:
+		case hwmon_temp_max_alarm:
+		case hwmon_temp_lcrit_alarm:
+		case hwmon_temp_crit_alarm:
+		case hwmon_temp_min:
+		case hwmon_temp_max:
+		case hwmon_temp_lcrit:
+		case hwmon_temp_crit:
+			return 0444;
+		default:
+			return 0;
+		}
+	case hwmon_in:
+		switch (attr) {
+		case hwmon_in_input:
+		case hwmon_in_min_alarm:
+		case hwmon_in_max_alarm:
+		case hwmon_in_lcrit_alarm:
+		case hwmon_in_crit_alarm:
+		case hwmon_in_min:
+		case hwmon_in_max:
+		case hwmon_in_lcrit:
+		case hwmon_in_crit:
+			return 0444;
+		default:
+			return 0;
+		}
+	case hwmon_curr:
+		switch (attr) {
+		case hwmon_curr_input:
+		case hwmon_curr_min_alarm:
+		case hwmon_curr_max_alarm:
+		case hwmon_curr_lcrit_alarm:
+		case hwmon_curr_crit_alarm:
+		case hwmon_curr_min:
+		case hwmon_curr_max:
+		case hwmon_curr_lcrit:
+		case hwmon_curr_crit:
+			return 0444;
+		default:
+			return 0;
+		}
+	case hwmon_power:
+		/* External calibration of receive power requires
+		 * floating point arithmetic. Doing that in the kernel
+		 * is not easy, so just skip it. If the module does
+		 * not require external calibration, we can however
+		 * show receiver power, since FP is then not needed.
+		 */
+		if (sfp->id.ext.diagmon & SFP_DIAGMON_EXT_CAL &&
+		    channel == 1)
+			return 0;
+		switch (attr) {
+		case hwmon_power_input:
+		case hwmon_power_min_alarm:
+		case hwmon_power_max_alarm:
+		case hwmon_power_lcrit_alarm:
+		case hwmon_power_crit_alarm:
+		case hwmon_power_min:
+		case hwmon_power_max:
+		case hwmon_power_lcrit:
+		case hwmon_power_crit:
+			return 0444;
+		default:
+			return 0;
+		}
+	default:
+		return 0;
+	}
+}
+
+static int sfp_hwmon_read_sensor(struct sfp *sfp, int reg, long *value)
+{
+	__be16 val;
+	int err;
+
+	err = sfp_read(sfp, true, reg, &val, sizeof(val));
+	if (err < 0)
+		return err;
+
+	*value = be16_to_cpu(val);
+
+	return 0;
+}
+
+static void sfp_hwmon_to_rx_power(long *value)
+{
+	*value = DIV_ROUND_CLOSEST(*value, 100);
+}
+
+static void sfp_hwmon_calibrate(struct sfp *sfp, unsigned int slope, int offset,
+				long *value)
+{
+	if (sfp->id.ext.diagmon & SFP_DIAGMON_EXT_CAL)
+		*value = DIV_ROUND_CLOSEST(*value * slope, 256) + offset;
+}
+
+static void sfp_hwmon_calibrate_temp(struct sfp *sfp, long *value)
+{
+	sfp_hwmon_calibrate(sfp, be16_to_cpu(sfp->diag.cal_t_slope),
+			    be16_to_cpu(sfp->diag.cal_t_offset), value);
+
+	if (*value >= 0x8000)
+		*value -= 0x10000;
+
+	*value = DIV_ROUND_CLOSEST(*value * 1000, 256);
+}
+
+static void sfp_hwmon_calibrate_vcc(struct sfp *sfp, long *value)
+{
+	sfp_hwmon_calibrate(sfp, be16_to_cpu(sfp->diag.cal_v_slope),
+			    be16_to_cpu(sfp->diag.cal_v_offset), value);
+
+	*value = DIV_ROUND_CLOSEST(*value, 10);
+}
+
+static void sfp_hwmon_calibrate_bias(struct sfp *sfp, long *value)
+{
+	sfp_hwmon_calibrate(sfp, be16_to_cpu(sfp->diag.cal_txi_slope),
+			    be16_to_cpu(sfp->diag.cal_txi_offset), value);
+
+	*value = DIV_ROUND_CLOSEST(*value, 500);
+}
+
+static void sfp_hwmon_calibrate_tx_power(struct sfp *sfp, long *value)
+{
+	sfp_hwmon_calibrate(sfp, be16_to_cpu(sfp->diag.cal_txpwr_slope),
+			    be16_to_cpu(sfp->diag.cal_txpwr_offset), value);
+
+	*value = DIV_ROUND_CLOSEST(*value, 10);
+}
+
+static int sfp_hwmon_read_temp(struct sfp *sfp, int reg, long *value)
+{
+	int err;
+
+	err = sfp_hwmon_read_sensor(sfp, reg, value);
+	if (err < 0)
+		return err;
+
+	sfp_hwmon_calibrate_temp(sfp, value);
+
+	return 0;
+}
+
+static int sfp_hwmon_read_vcc(struct sfp *sfp, int reg, long *value)
+{
+	int err;
+
+	err = sfp_hwmon_read_sensor(sfp, reg, value);
+	if (err < 0)
+		return err;
+
+	sfp_hwmon_calibrate_vcc(sfp, value);
+
+	return 0;
+}
+
+static int sfp_hwmon_read_bias(struct sfp *sfp, int reg, long *value)
+{
+	int err;
+
+	err = sfp_hwmon_read_sensor(sfp, reg, value);
+	if (err < 0)
+		return err;
+
+	sfp_hwmon_calibrate_bias(sfp, value);
+
+	return 0;
+}
+
+static int sfp_hwmon_read_tx_power(struct sfp *sfp, int reg, long *value)
+{
+	int err;
+
+	err = sfp_hwmon_read_sensor(sfp, reg, value);
+	if (err < 0)
+		return err;
+
+	sfp_hwmon_calibrate_tx_power(sfp, value);
+
+	return 0;
+}
+
+static int sfp_hwmon_read_rx_power(struct sfp *sfp, int reg, long *value)
+{
+	int err;
+
+	err = sfp_hwmon_read_sensor(sfp, reg, value);
+	if (err < 0)
+		return err;
+
+	sfp_hwmon_to_rx_power(value);
+
+	return 0;
+}
+
+static int sfp_hwmon_temp(struct sfp *sfp, u32 attr, long *value)
+{
+	u8 status;
+	int err;
+
+	switch (attr) {
+	case hwmon_temp_input:
+		return sfp_hwmon_read_temp(sfp, SFP_TEMP, value);
+
+	case hwmon_temp_lcrit:
+		*value = be16_to_cpu(sfp->diag.temp_low_alarm);
+		sfp_hwmon_calibrate_temp(sfp, value);
+		return 0;
+
+	case hwmon_temp_min:
+		*value = be16_to_cpu(sfp->diag.temp_low_warn);
+		sfp_hwmon_calibrate_temp(sfp, value);
+		return 0;
+	case hwmon_temp_max:
+		*value = be16_to_cpu(sfp->diag.temp_high_warn);
+		sfp_hwmon_calibrate_temp(sfp, value);
+		return 0;
+
+	case hwmon_temp_crit:
+		*value = be16_to_cpu(sfp->diag.temp_high_alarm);
+		sfp_hwmon_calibrate_temp(sfp, value);
+		return 0;
+
+	case hwmon_temp_lcrit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM0_TEMP_LOW);
+		return 0;
+
+	case hwmon_temp_min_alarm:
+		err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN0_TEMP_LOW);
+		return 0;
+
+	case hwmon_temp_max_alarm:
+		err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN0_TEMP_HIGH);
+		return 0;
+
+	case hwmon_temp_crit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM0_TEMP_HIGH);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int sfp_hwmon_vcc(struct sfp *sfp, u32 attr, long *value)
+{
+	u8 status;
+	int err;
+
+	switch (attr) {
+	case hwmon_in_input:
+		return sfp_hwmon_read_vcc(sfp, SFP_VCC, value);
+
+	case hwmon_in_lcrit:
+		*value = be16_to_cpu(sfp->diag.volt_low_alarm);
+		sfp_hwmon_calibrate_vcc(sfp, value);
+		return 0;
+
+	case hwmon_in_min:
+		*value = be16_to_cpu(sfp->diag.volt_low_warn);
+		sfp_hwmon_calibrate_vcc(sfp, value);
+		return 0;
+
+	case hwmon_in_max:
+		*value = be16_to_cpu(sfp->diag.volt_high_warn);
+		sfp_hwmon_calibrate_vcc(sfp, value);
+		return 0;
+
+	case hwmon_in_crit:
+		*value = be16_to_cpu(sfp->diag.volt_high_alarm);
+		sfp_hwmon_calibrate_vcc(sfp, value);
+		return 0;
+
+	case hwmon_in_lcrit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM0_VCC_LOW);
+		return 0;
+
+	case hwmon_in_min_alarm:
+		err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN0_VCC_LOW);
+		return 0;
+
+	case hwmon_in_max_alarm:
+		err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN0_VCC_HIGH);
+		return 0;
+
+	case hwmon_in_crit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM0_VCC_HIGH);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int sfp_hwmon_bias(struct sfp *sfp, u32 attr, long *value)
+{
+	u8 status;
+	int err;
+
+	switch (attr) {
+	case hwmon_curr_input:
+		return sfp_hwmon_read_bias(sfp, SFP_TX_BIAS, value);
+
+	case hwmon_curr_lcrit:
+		*value = be16_to_cpu(sfp->diag.bias_low_alarm);
+		sfp_hwmon_calibrate_bias(sfp, value);
+		return 0;
+
+	case hwmon_curr_min:
+		*value = be16_to_cpu(sfp->diag.bias_low_warn);
+		sfp_hwmon_calibrate_bias(sfp, value);
+		return 0;
+
+	case hwmon_curr_max:
+		*value = be16_to_cpu(sfp->diag.bias_high_warn);
+		sfp_hwmon_calibrate_bias(sfp, value);
+		return 0;
+
+	case hwmon_curr_crit:
+		*value = be16_to_cpu(sfp->diag.bias_high_alarm);
+		sfp_hwmon_calibrate_bias(sfp, value);
+		return 0;
+
+	case hwmon_curr_lcrit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM0_TX_BIAS_LOW);
+		return 0;
+
+	case hwmon_curr_min_alarm:
+		err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN0_TX_BIAS_LOW);
+		return 0;
+
+	case hwmon_curr_max_alarm:
+		err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN0_TX_BIAS_HIGH);
+		return 0;
+
+	case hwmon_curr_crit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM0_TX_BIAS_HIGH);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int sfp_hwmon_tx_power(struct sfp *sfp, u32 attr, long *value)
+{
+	u8 status;
+	int err;
+
+	switch (attr) {
+	case hwmon_power_input:
+		return sfp_hwmon_read_tx_power(sfp, SFP_TX_POWER, value);
+
+	case hwmon_power_lcrit:
+		*value = be16_to_cpu(sfp->diag.txpwr_low_alarm);
+		sfp_hwmon_calibrate_tx_power(sfp, value);
+		return 0;
+
+	case hwmon_power_min:
+		*value = be16_to_cpu(sfp->diag.txpwr_low_warn);
+		sfp_hwmon_calibrate_tx_power(sfp, value);
+		return 0;
+
+	case hwmon_power_max:
+		*value = be16_to_cpu(sfp->diag.txpwr_high_warn);
+		sfp_hwmon_calibrate_tx_power(sfp, value);
+		return 0;
+
+	case hwmon_power_crit:
+		*value = be16_to_cpu(sfp->diag.txpwr_high_alarm);
+		sfp_hwmon_calibrate_tx_power(sfp, value);
+		return 0;
+
+	case hwmon_power_lcrit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM0_TXPWR_LOW);
+		return 0;
+
+	case hwmon_power_min_alarm:
+		err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN0_TXPWR_LOW);
+		return 0;
+
+	case hwmon_power_max_alarm:
+		err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN0_TXPWR_HIGH);
+		return 0;
+
+	case hwmon_power_crit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM0_TXPWR_HIGH);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int sfp_hwmon_rx_power(struct sfp *sfp, u32 attr, long *value)
+{
+	u8 status;
+	int err;
+
+	switch (attr) {
+	case hwmon_power_input:
+		return sfp_hwmon_read_rx_power(sfp, SFP_RX_POWER, value);
+
+	case hwmon_power_lcrit:
+		*value = be16_to_cpu(sfp->diag.rxpwr_low_alarm);
+		sfp_hwmon_to_rx_power(value);
+		return 0;
+
+	case hwmon_power_min:
+		*value = be16_to_cpu(sfp->diag.rxpwr_low_warn);
+		sfp_hwmon_to_rx_power(value);
+		return 0;
+
+	case hwmon_power_max:
+		*value = be16_to_cpu(sfp->diag.rxpwr_high_warn);
+		sfp_hwmon_to_rx_power(value);
+		return 0;
+
+	case hwmon_power_crit:
+		*value = be16_to_cpu(sfp->diag.rxpwr_high_alarm);
+		sfp_hwmon_to_rx_power(value);
+		return 0;
+
+	case hwmon_power_lcrit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM1, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM1_RXPWR_LOW);
+		return 0;
+
+	case hwmon_power_min_alarm:
+		err = sfp_read(sfp, true, SFP_WARN1, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN1_RXPWR_LOW);
+		return 0;
+
+	case hwmon_power_max_alarm:
+		err = sfp_read(sfp, true, SFP_WARN1, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN1_RXPWR_HIGH);
+		return 0;
+
+	case hwmon_power_crit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM1, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM1_RXPWR_HIGH);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int sfp_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
+			  u32 attr, int channel, long *value)
+{
+	struct sfp *sfp = dev_get_drvdata(dev);
+
+	switch (type) {
+	case hwmon_temp:
+		return sfp_hwmon_temp(sfp, attr, value);
+	case hwmon_in:
+		return sfp_hwmon_vcc(sfp, attr, value);
+	case hwmon_curr:
+		return sfp_hwmon_bias(sfp, attr, value);
+	case hwmon_power:
+		switch (channel) {
+		case 0:
+			return sfp_hwmon_tx_power(sfp, attr, value);
+		case 1:
+			return sfp_hwmon_rx_power(sfp, attr, value);
+		default:
+			return -EOPNOTSUPP;
+		}
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static const struct hwmon_ops sfp_hwmon_ops = {
+	.is_visible = sfp_hwmon_is_visible,
+	.read = sfp_hwmon_read,
+};
+
+static u32 sfp_hwmon_chip_config[] = {
+	HWMON_C_REGISTER_TZ,
+	0,
+};
+
+static const struct hwmon_channel_info sfp_hwmon_chip = {
+	.type = hwmon_chip,
+	.config = sfp_hwmon_chip_config,
+};
+
+static u32 sfp_hwmon_temp_config[] = {
+	HWMON_T_INPUT |
+	HWMON_T_MAX | HWMON_T_MIN |
+	HWMON_T_MAX_ALARM | HWMON_T_MIN_ALARM |
+	HWMON_T_CRIT | HWMON_T_LCRIT |
+	HWMON_T_CRIT_ALARM | HWMON_T_LCRIT_ALARM,
+	0,
+};
+
+static const struct hwmon_channel_info sfp_hwmon_temp_channel_info = {
+	.type = hwmon_temp,
+	.config = sfp_hwmon_temp_config,
+};
+
+static u32 sfp_hwmon_vcc_config[] = {
+	HWMON_I_INPUT |
+	HWMON_I_MAX | HWMON_I_MIN |
+	HWMON_I_MAX_ALARM | HWMON_I_MIN_ALARM |
+	HWMON_I_CRIT | HWMON_I_LCRIT |
+	HWMON_I_CRIT_ALARM | HWMON_I_LCRIT_ALARM,
+	0,
+};
+
+static const struct hwmon_channel_info sfp_hwmon_vcc_channel_info = {
+	.type = hwmon_in,
+	.config = sfp_hwmon_vcc_config,
+};
+
+static u32 sfp_hwmon_bias_config[] = {
+	HWMON_C_INPUT |
+	HWMON_C_MAX | HWMON_C_MIN |
+	HWMON_C_MAX_ALARM | HWMON_C_MIN_ALARM |
+	HWMON_C_CRIT | HWMON_C_LCRIT |
+	HWMON_C_CRIT_ALARM | HWMON_C_LCRIT_ALARM,
+	0,
+};
+
+static const struct hwmon_channel_info sfp_hwmon_bias_channel_info = {
+	.type = hwmon_curr,
+	.config = sfp_hwmon_bias_config,
+};
+
+static u32 sfp_hwmon_power_config[] = {
+	/* Transmit power */
+	HWMON_P_INPUT |
+	HWMON_P_MAX | HWMON_P_MIN |
+	HWMON_P_MAX_ALARM | HWMON_P_MIN_ALARM |
+	HWMON_P_CRIT | HWMON_P_LCRIT |
+	HWMON_P_CRIT_ALARM | HWMON_P_LCRIT_ALARM,
+	/* Receive power */
+	HWMON_P_INPUT |
+	HWMON_P_MAX | HWMON_P_MIN |
+	HWMON_P_MAX_ALARM | HWMON_P_MIN_ALARM |
+	HWMON_P_CRIT | HWMON_P_LCRIT |
+	HWMON_P_CRIT_ALARM | HWMON_P_LCRIT_ALARM,
+	0,
+};
+
+static const struct hwmon_channel_info sfp_hwmon_power_channel_info = {
+	.type = hwmon_power,
+	.config = sfp_hwmon_power_config,
+};
+
+static const struct hwmon_channel_info *sfp_hwmon_info[] = {
+	&sfp_hwmon_chip,
+	&sfp_hwmon_vcc_channel_info,
+	&sfp_hwmon_temp_channel_info,
+	&sfp_hwmon_bias_channel_info,
+	&sfp_hwmon_power_channel_info,
+	NULL,
+};
+
+static const struct hwmon_chip_info sfp_hwmon_chip_info = {
+	.ops = &sfp_hwmon_ops,
+	.info = sfp_hwmon_info,
+};
+
+static int sfp_hwmon_insert(struct sfp *sfp)
+{
+	int err, i;
+
+	if (sfp->id.ext.sff8472_compliance == SFP_SFF8472_COMPLIANCE_NONE)
+		return 0;
+
+	if (!(sfp->id.ext.diagmon & SFP_DIAGMON_DDM))
+		return 0;
+
+	if (sfp->id.ext.diagmon & SFP_DIAGMON_ADDRMODE)
+		/* This driver in general does not support address
+		 * change.
+		 */
+		return 0;
+
+	err = sfp_read(sfp, true, 0, &sfp->diag, sizeof(sfp->diag));
+	if (err < 0)
+		return err;
+
+	sfp->hwmon_name = kstrdup(dev_name(sfp->dev), GFP_KERNEL);
+	if (!sfp->hwmon_name)
+		return -ENODEV;
+
+	for (i = 0; sfp->hwmon_name[i]; i++)
+		if (hwmon_is_bad_char(sfp->hwmon_name[i]))
+			sfp->hwmon_name[i] = '_';
+
+	sfp->hwmon_dev = hwmon_device_register_with_info(sfp->dev,
+							 sfp->hwmon_name, sfp,
+							 &sfp_hwmon_chip_info,
+							 NULL);
+
+	return PTR_ERR_OR_ZERO(sfp->hwmon_dev);
+}
+
+static void sfp_hwmon_remove(struct sfp *sfp)
+{
+	hwmon_device_unregister(sfp->hwmon_dev);
+	kfree(sfp->hwmon_name);
+}
+#else
+static int sfp_hwmon_insert(struct sfp *sfp)
+{
+	return 0;
+}
+
+static void sfp_hwmon_remove(struct sfp *sfp)
+{
+}
+#endif
+
 /* Helpers */
 static void sfp_module_tx_disable(struct sfp *sfp)
 {
@@ -636,6 +1420,10 @@ static int sfp_sm_mod_probe(struct sfp *sfp)
 		dev_warn(sfp->dev,
 			 "module address swap to access page 0xA2 is not supported.\n");
 
+	ret = sfp_hwmon_insert(sfp);
+	if (ret < 0)
+		return ret;
+
 	ret = sfp_module_insert(sfp->sfp_bus, &sfp->id);
 	if (ret < 0)
 		return ret;
@@ -647,6 +1435,8 @@ static void sfp_sm_mod_remove(struct sfp *sfp)
 {
 	sfp_module_remove(sfp->sfp_bus);
 
+	sfp_hwmon_remove(sfp);
+
 	if (sfp->mod_phy)
 		sfp_sm_phy_detach(sfp);
 
@@ -661,8 +1451,11 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event)
 {
 	mutex_lock(&sfp->sm_mutex);
 
-	dev_dbg(sfp->dev, "SM: enter %u:%u:%u event %u\n",
-		sfp->sm_mod_state, sfp->sm_dev_state, sfp->sm_state, event);
+	dev_dbg(sfp->dev, "SM: enter %s:%s:%s event %s\n",
+		mod_state_to_str(sfp->sm_mod_state),
+		dev_state_to_str(sfp->sm_dev_state),
+		sm_state_to_str(sfp->sm_state),
+		event_to_str(event));
 
 	/* This state machine tracks the insert/remove state of
 	 * the module, and handles probing the on-board EEPROM.
@@ -793,8 +1586,10 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event)
 		break;
 	}
 
-	dev_dbg(sfp->dev, "SM: exit %u:%u:%u\n",
-		sfp->sm_mod_state, sfp->sm_dev_state, sfp->sm_state);
+	dev_dbg(sfp->dev, "SM: exit %s:%s:%s\n",
+		mod_state_to_str(sfp->sm_mod_state),
+		dev_state_to_str(sfp->sm_dev_state),
+		sm_state_to_str(sfp->sm_state));
 
 	mutex_unlock(&sfp->sm_mutex);
 }
diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c
index d9dd8fbfffc7..fbf9ad429593 100644
--- a/drivers/net/phy/vitesse.c
+++ b/drivers/net/phy/vitesse.c
@@ -72,6 +72,10 @@
 #define PHY_ID_VSC8572			0x000704d0
 #define PHY_ID_VSC8574			0x000704a0
 #define PHY_ID_VSC8601			0x00070420
+#define PHY_ID_VSC7385			0x00070450
+#define PHY_ID_VSC7388			0x00070480
+#define PHY_ID_VSC7395			0x00070550
+#define PHY_ID_VSC7398			0x00070580
 #define PHY_ID_VSC8662			0x00070660
 #define PHY_ID_VSC8221			0x000fc550
 #define PHY_ID_VSC8211			0x000fc4b0
@@ -116,6 +120,137 @@ static int vsc824x_config_init(struct phy_device *phydev)
 	return err;
 }
 
+#define VSC73XX_EXT_PAGE_ACCESS 0x1f
+
+static int vsc73xx_read_page(struct phy_device *phydev)
+{
+	return __phy_read(phydev, VSC73XX_EXT_PAGE_ACCESS);
+}
+
+static int vsc73xx_write_page(struct phy_device *phydev, int page)
+{
+	return __phy_write(phydev, VSC73XX_EXT_PAGE_ACCESS, page);
+}
+
+static void vsc73xx_config_init(struct phy_device *phydev)
+{
+	/* Receiver init */
+	phy_write(phydev, 0x1f, 0x2a30);
+	phy_modify(phydev, 0x0c, 0x0300, 0x0200);
+	phy_write(phydev, 0x1f, 0x0000);
+
+	/* Config LEDs 0x61 */
+	phy_modify(phydev, MII_TPISTATUS, 0xff00, 0x0061);
+}
+
+static int vsc738x_config_init(struct phy_device *phydev)
+{
+	u16 rev;
+	/* This magic sequence appear in the application note
+	 * "VSC7385/7388 PHY Configuration".
+	 *
+	 * Maybe one day we will get to know what it all means.
+	 */
+	phy_write(phydev, 0x1f, 0x2a30);
+	phy_modify(phydev, 0x08, 0x0200, 0x0200);
+	phy_write(phydev, 0x1f, 0x52b5);
+	phy_write(phydev, 0x10, 0xb68a);
+	phy_modify(phydev, 0x12, 0xff07, 0x0003);
+	phy_modify(phydev, 0x11, 0x00ff, 0x00a2);
+	phy_write(phydev, 0x10, 0x968a);
+	phy_write(phydev, 0x1f, 0x2a30);
+	phy_modify(phydev, 0x08, 0x0200, 0x0000);
+	phy_write(phydev, 0x1f, 0x0000);
+
+	/* Read revision */
+	rev = phy_read(phydev, MII_PHYSID2);
+	rev &= 0x0f;
+
+	/* Special quirk for revision 0 */
+	if (rev == 0) {
+		phy_write(phydev, 0x1f, 0x2a30);
+		phy_modify(phydev, 0x08, 0x0200, 0x0200);
+		phy_write(phydev, 0x1f, 0x52b5);
+		phy_write(phydev, 0x12, 0x0000);
+		phy_write(phydev, 0x11, 0x0689);
+		phy_write(phydev, 0x10, 0x8f92);
+		phy_write(phydev, 0x1f, 0x52b5);
+		phy_write(phydev, 0x12, 0x0000);
+		phy_write(phydev, 0x11, 0x0e35);
+		phy_write(phydev, 0x10, 0x9786);
+		phy_write(phydev, 0x1f, 0x2a30);
+		phy_modify(phydev, 0x08, 0x0200, 0x0000);
+		phy_write(phydev, 0x17, 0xff80);
+		phy_write(phydev, 0x17, 0x0000);
+	}
+
+	phy_write(phydev, 0x1f, 0x0000);
+	phy_write(phydev, 0x12, 0x0048);
+
+	if (rev == 0) {
+		phy_write(phydev, 0x1f, 0x2a30);
+		phy_write(phydev, 0x14, 0x6600);
+		phy_write(phydev, 0x1f, 0x0000);
+		phy_write(phydev, 0x18, 0xa24e);
+	} else {
+		phy_write(phydev, 0x1f, 0x2a30);
+		phy_modify(phydev, 0x16, 0x0fc0, 0x0240);
+		phy_modify(phydev, 0x14, 0x6000, 0x4000);
+		/* bits 14-15 in extended register 0x14 controls DACG amplitude
+		 * 6 = -8%, 2 is hardware default
+		 */
+		phy_write(phydev, 0x1f, 0x0001);
+		phy_modify(phydev, 0x14, 0xe000, 0x6000);
+		phy_write(phydev, 0x1f, 0x0000);
+	}
+
+	vsc73xx_config_init(phydev);
+
+	return genphy_config_init(phydev);
+}
+
+static int vsc739x_config_init(struct phy_device *phydev)
+{
+	/* This magic sequence appears in the VSC7395 SparX-G5e application
+	 * note "VSC7395/VSC7398 PHY Configuration"
+	 *
+	 * Maybe one day we will get to know what it all means.
+	 */
+	phy_write(phydev, 0x1f, 0x2a30);
+	phy_modify(phydev, 0x08, 0x0200, 0x0200);
+	phy_write(phydev, 0x1f, 0x52b5);
+	phy_write(phydev, 0x10, 0xb68a);
+	phy_modify(phydev, 0x12, 0xff07, 0x0003);
+	phy_modify(phydev, 0x11, 0x00ff, 0x00a2);
+	phy_write(phydev, 0x10, 0x968a);
+	phy_write(phydev, 0x1f, 0x2a30);
+	phy_modify(phydev, 0x08, 0x0200, 0x0000);
+	phy_write(phydev, 0x1f, 0x0000);
+
+	phy_write(phydev, 0x1f, 0x0000);
+	phy_write(phydev, 0x12, 0x0048);
+	phy_write(phydev, 0x1f, 0x2a30);
+	phy_modify(phydev, 0x16, 0x0fc0, 0x0240);
+	phy_modify(phydev, 0x14, 0x6000, 0x4000);
+	phy_write(phydev, 0x1f, 0x0001);
+	phy_modify(phydev, 0x14, 0xe000, 0x6000);
+	phy_write(phydev, 0x1f, 0x0000);
+
+	vsc73xx_config_init(phydev);
+
+	return genphy_config_init(phydev);
+}
+
+static int vsc73xx_config_aneg(struct phy_device *phydev)
+{
+	/* The VSC73xx switches does not like to be instructed to
+	 * do autonegotiation in any way, it prefers that you just go
+	 * with the power-on/reset defaults. Writing some registers will
+	 * just make autonegotiation permanently fail.
+	 */
+	return 0;
+}
+
 /* This adds a skew for both TX and RX clocks, so the skew should only be
  * applied to "rgmii-id" interfaces. It may not work as expected
  * on "rgmii-txid", "rgmii-rxid" or "rgmii" interfaces. */
@@ -319,6 +454,42 @@ static struct phy_driver vsc82xx_driver[] = {
 	.ack_interrupt  = &vsc824x_ack_interrupt,
 	.config_intr    = &vsc82xx_config_intr,
 }, {
+	.phy_id         = PHY_ID_VSC7385,
+	.name           = "Vitesse VSC7385",
+	.phy_id_mask    = 0x000ffff0,
+	.features       = PHY_GBIT_FEATURES,
+	.config_init    = vsc738x_config_init,
+	.config_aneg    = vsc73xx_config_aneg,
+	.read_page      = vsc73xx_read_page,
+	.write_page     = vsc73xx_write_page,
+}, {
+	.phy_id         = PHY_ID_VSC7388,
+	.name           = "Vitesse VSC7388",
+	.phy_id_mask    = 0x000ffff0,
+	.features       = PHY_GBIT_FEATURES,
+	.config_init    = vsc738x_config_init,
+	.config_aneg    = vsc73xx_config_aneg,
+	.read_page      = vsc73xx_read_page,
+	.write_page     = vsc73xx_write_page,
+}, {
+	.phy_id         = PHY_ID_VSC7395,
+	.name           = "Vitesse VSC7395",
+	.phy_id_mask    = 0x000ffff0,
+	.features       = PHY_GBIT_FEATURES,
+	.config_init    = vsc739x_config_init,
+	.config_aneg    = vsc73xx_config_aneg,
+	.read_page      = vsc73xx_read_page,
+	.write_page     = vsc73xx_write_page,
+}, {
+	.phy_id         = PHY_ID_VSC7398,
+	.name           = "Vitesse VSC7398",
+	.phy_id_mask    = 0x000ffff0,
+	.features       = PHY_GBIT_FEATURES,
+	.config_init    = vsc739x_config_init,
+	.config_aneg    = vsc73xx_config_aneg,
+	.read_page      = vsc73xx_read_page,
+	.write_page     = vsc73xx_write_page,
+}, {
 	.phy_id         = PHY_ID_VSC8662,
 	.name           = "Vitesse VSC8662",
 	.phy_id_mask    = 0x000ffff0,
@@ -358,6 +529,10 @@ static struct mdio_device_id __maybe_unused vitesse_tbl[] = {
 	{ PHY_ID_VSC8514, 0x000ffff0 },
 	{ PHY_ID_VSC8572, 0x000ffff0 },
 	{ PHY_ID_VSC8574, 0x000ffff0 },
+	{ PHY_ID_VSC7385, 0x000ffff0 },
+	{ PHY_ID_VSC7388, 0x000ffff0 },
+	{ PHY_ID_VSC7395, 0x000ffff0 },
+	{ PHY_ID_VSC7398, 0x000ffff0 },
 	{ PHY_ID_VSC8662, 0x000ffff0 },
 	{ PHY_ID_VSC8221, 0x000ffff0 },
 	{ PHY_ID_VSC8211, 0x000ffff0 },
diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c
index 2e5150b0b8d5..74a8782313cf 100644
--- a/drivers/net/phy/xilinx_gmii2rgmii.c
+++ b/drivers/net/phy/xilinx_gmii2rgmii.c
@@ -33,17 +33,22 @@ struct gmii2rgmii {
 	struct phy_device *phy_dev;
 	struct phy_driver *phy_drv;
 	struct phy_driver conv_phy_drv;
-	int addr;
+	struct mdio_device *mdio;
 };
 
 static int xgmiitorgmii_read_status(struct phy_device *phydev)
 {
 	struct gmii2rgmii *priv = phydev->priv;
+	struct mii_bus *bus = priv->mdio->bus;
+	int addr = priv->mdio->addr;
 	u16 val = 0;
+	int err;
 
-	priv->phy_drv->read_status(phydev);
+	err = priv->phy_drv->read_status(phydev);
+	if (err < 0)
+		return err;
 
-	val = mdiobus_read(phydev->mdio.bus, priv->addr, XILINX_GMII2RGMII_REG);
+	val = mdiobus_read(bus, addr, XILINX_GMII2RGMII_REG);
 	val &= ~XILINX_GMII2RGMII_SPEED_MASK;
 
 	if (phydev->speed == SPEED_1000)
@@ -53,7 +58,7 @@ static int xgmiitorgmii_read_status(struct phy_device *phydev)
 	else
 		val |= BMCR_SPEED10;
 
-	mdiobus_write(phydev->mdio.bus, priv->addr, XILINX_GMII2RGMII_REG, val);
+	mdiobus_write(bus, addr, XILINX_GMII2RGMII_REG, val);
 
 	return 0;
 }
@@ -81,7 +86,12 @@ static int xgmiitorgmii_probe(struct mdio_device *mdiodev)
 		return -EPROBE_DEFER;
 	}
 
-	priv->addr = mdiodev->addr;
+	if (!priv->phy_dev->drv) {
+		dev_info(dev, "Attached phy not ready\n");
+		return -EPROBE_DEFER;
+	}
+
+	priv->mdio = mdiodev;
 	priv->phy_drv = priv->phy_dev->drv;
 	memcpy(&priv->conv_phy_drv, priv->phy_dev->drv,
 	       sizeof(struct phy_driver));
diff --git a/drivers/net/ppp/ppp_mppe.c b/drivers/net/ppp/ppp_mppe.c
index 6c7fd98cb00a..a205750b431b 100644
--- a/drivers/net/ppp/ppp_mppe.c
+++ b/drivers/net/ppp/ppp_mppe.c
@@ -96,7 +96,7 @@ static inline void sha_pad_init(struct sha_pad *shapad)
  */
 struct ppp_mppe_state {
 	struct crypto_skcipher *arc4;
-	struct crypto_ahash *sha1;
+	struct shash_desc *sha1;
 	unsigned char *sha1_digest;
 	unsigned char master_key[MPPE_MAX_KEY_LEN];
 	unsigned char session_key[MPPE_MAX_KEY_LEN];
@@ -136,25 +136,16 @@ struct ppp_mppe_state {
  */
 static void get_new_key_from_sha(struct ppp_mppe_state * state)
 {
-	AHASH_REQUEST_ON_STACK(req, state->sha1);
-	struct scatterlist sg[4];
-	unsigned int nbytes;
-
-	sg_init_table(sg, 4);
-
-	nbytes = setup_sg(&sg[0], state->master_key, state->keylen);
-	nbytes += setup_sg(&sg[1], sha_pad->sha_pad1,
-			   sizeof(sha_pad->sha_pad1));
-	nbytes += setup_sg(&sg[2], state->session_key, state->keylen);
-	nbytes += setup_sg(&sg[3], sha_pad->sha_pad2,
-			   sizeof(sha_pad->sha_pad2));
-
-	ahash_request_set_tfm(req, state->sha1);
-	ahash_request_set_callback(req, 0, NULL, NULL);
-	ahash_request_set_crypt(req, sg, state->sha1_digest, nbytes);
-
-	crypto_ahash_digest(req);
-	ahash_request_zero(req);
+	crypto_shash_init(state->sha1);
+	crypto_shash_update(state->sha1, state->master_key,
+			    state->keylen);
+	crypto_shash_update(state->sha1, sha_pad->sha_pad1,
+			    sizeof(sha_pad->sha_pad1));
+	crypto_shash_update(state->sha1, state->session_key,
+			    state->keylen);
+	crypto_shash_update(state->sha1, sha_pad->sha_pad2,
+			    sizeof(sha_pad->sha_pad2));
+	crypto_shash_final(state->sha1, state->sha1_digest);
 }
 
 /*
@@ -200,6 +191,7 @@ static void mppe_rekey(struct ppp_mppe_state * state, int initial_key)
 static void *mppe_alloc(unsigned char *options, int optlen)
 {
 	struct ppp_mppe_state *state;
+	struct crypto_shash *shash;
 	unsigned int digestsize;
 
 	if (optlen != CILEN_MPPE + sizeof(state->master_key) ||
@@ -217,13 +209,21 @@ static void *mppe_alloc(unsigned char *options, int optlen)
 		goto out_free;
 	}
 
-	state->sha1 = crypto_alloc_ahash("sha1", 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(state->sha1)) {
-		state->sha1 = NULL;
+	shash = crypto_alloc_shash("sha1", 0, 0);
+	if (IS_ERR(shash))
+		goto out_free;
+
+	state->sha1 = kmalloc(sizeof(*state->sha1) +
+				     crypto_shash_descsize(shash),
+			      GFP_KERNEL);
+	if (!state->sha1) {
+		crypto_free_shash(shash);
 		goto out_free;
 	}
+	state->sha1->tfm = shash;
+	state->sha1->flags = 0;
 
-	digestsize = crypto_ahash_digestsize(state->sha1);
+	digestsize = crypto_shash_digestsize(shash);
 	if (digestsize < MPPE_MAX_KEY_LEN)
 		goto out_free;
 
@@ -246,7 +246,10 @@ static void *mppe_alloc(unsigned char *options, int optlen)
 
 out_free:
 	kfree(state->sha1_digest);
-	crypto_free_ahash(state->sha1);
+	if (state->sha1) {
+		crypto_free_shash(state->sha1->tfm);
+		kzfree(state->sha1);
+	}
 	crypto_free_skcipher(state->arc4);
 	kfree(state);
 out:
@@ -261,7 +264,8 @@ static void mppe_free(void *arg)
 	struct ppp_mppe_state *state = (struct ppp_mppe_state *) arg;
 	if (state) {
 		kfree(state->sha1_digest);
-		crypto_free_ahash(state->sha1);
+		crypto_free_shash(state->sha1->tfm);
+		kzfree(state->sha1);
 		crypto_free_skcipher(state->arc4);
 		kfree(state);
 	}
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index b070959737ff..6a047d30e8c6 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -41,11 +41,6 @@
 
 #define team_port_exists(dev) (dev->priv_flags & IFF_TEAM_PORT)
 
-static struct team_port *team_port_get_rcu(const struct net_device *dev)
-{
-	return rcu_dereference(dev->rx_handler_data);
-}
-
 static struct team_port *team_port_get_rtnl(const struct net_device *dev)
 {
 	struct team_port *port = rtnl_dereference(dev->rx_handler_data);
@@ -1707,7 +1702,8 @@ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev)
 }
 
 static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     void *accel_priv, select_queue_fallback_t fallback)
+			     struct net_device *sb_dev,
+			     select_queue_fallback_t fallback)
 {
 	/*
 	 * This helper function exists to help dev_pick_tx get the correct
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index f5727baac84a..2bbefe828670 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -200,6 +200,7 @@ struct tun_flow_entry {
 };
 
 #define TUN_NUM_FLOW_ENTRIES 1024
+#define TUN_MASK_FLOW_ENTRIES (TUN_NUM_FLOW_ENTRIES - 1)
 
 struct tun_prog {
 	struct rcu_head rcu;
@@ -406,7 +407,7 @@ static inline __virtio16 cpu_to_tun16(struct tun_struct *tun, u16 val)
 
 static inline u32 tun_hashfn(u32 rxhash)
 {
-	return rxhash & 0x3ff;
+	return rxhash & TUN_MASK_FLOW_ENTRIES;
 }
 
 static struct tun_flow_entry *tun_flow_find(struct hlist_head *head, u32 rxhash)
@@ -607,7 +608,8 @@ static u16 tun_ebpf_select_queue(struct tun_struct *tun, struct sk_buff *skb)
 }
 
 static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    void *accel_priv, select_queue_fallback_t fallback)
+			    struct net_device *sb_dev,
+			    select_queue_fallback_t fallback)
 {
 	struct tun_struct *tun = netdev_priv(dev);
 	u16 ret;
@@ -1268,7 +1270,6 @@ static int tun_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		return tun_xdp_set(dev, xdp->prog, xdp->extack);
 	case XDP_QUERY_PROG:
 		xdp->prog_id = tun_xdp_query(dev);
-		xdp->prog_attached = !!xdp->prog_id;
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index b1b3d8f7e67d..b654f05b2ccd 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -693,24 +693,32 @@ static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf)
 	u32 phyid;
 	struct asix_common_private *priv;
 
-	usbnet_get_endpoints(dev,intf);
+	usbnet_get_endpoints(dev, intf);
 
-	/* Get the MAC address */
-	if (dev->driver_info->data & FLAG_EEPROM_MAC) {
-		for (i = 0; i < (ETH_ALEN >> 1); i++) {
-			ret = asix_read_cmd(dev, AX_CMD_READ_EEPROM, 0x04 + i,
-					    0, 2, buf + i * 2, 0);
-			if (ret < 0)
-				break;
-		}
+	/* Maybe the boot loader passed the MAC address via device tree */
+	if (!eth_platform_get_mac_address(&dev->udev->dev, buf)) {
+		netif_dbg(dev, ifup, dev->net,
+			  "MAC address read from device tree");
 	} else {
-		ret = asix_read_cmd(dev, AX_CMD_READ_NODE_ID,
-				0, 0, ETH_ALEN, buf, 0);
-	}
+		/* Try getting the MAC address from EEPROM */
+		if (dev->driver_info->data & FLAG_EEPROM_MAC) {
+			for (i = 0; i < (ETH_ALEN >> 1); i++) {
+				ret = asix_read_cmd(dev, AX_CMD_READ_EEPROM,
+						    0x04 + i, 0, 2, buf + i * 2,
+						    0);
+				if (ret < 0)
+					break;
+			}
+		} else {
+			ret = asix_read_cmd(dev, AX_CMD_READ_NODE_ID,
+					    0, 0, ETH_ALEN, buf, 0);
+		}
 
-	if (ret < 0) {
-		netdev_dbg(dev->net, "Failed to read MAC address: %d\n", ret);
-		return ret;
+		if (ret < 0) {
+			netdev_dbg(dev->net, "Failed to read MAC address: %d\n",
+				   ret);
+			return ret;
+		}
 	}
 
 	asix_set_netdev_dev_addr(dev, buf);
diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c
index 18d36dff97ea..424053bd8b21 100644
--- a/drivers/net/usb/catc.c
+++ b/drivers/net/usb/catc.c
@@ -869,6 +869,7 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
 		default:
 			dev_warn(&intf->dev,
 				 "Couldn't detect memory size, assuming 32k\n");
+			/* fall through */
 		case 0x87654321:
 			catc_set_reg(catc, TxBufCount, 4);
 			catc_set_reg(catc, RxBufCount, 16);
diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c
index 288ecd999171..78b16eb9e58c 100644
--- a/drivers/net/usb/cdc-phonet.c
+++ b/drivers/net/usb/cdc-phonet.c
@@ -99,6 +99,7 @@ static void tx_complete(struct urb *req)
 	struct net_device *dev = skb->dev;
 	struct usbpn_dev *pnd = netdev_priv(dev);
 	int status = req->status;
+	unsigned long flags;
 
 	switch (status) {
 	case 0:
@@ -109,16 +110,17 @@ static void tx_complete(struct urb *req)
 	case -ECONNRESET:
 	case -ESHUTDOWN:
 		dev->stats.tx_aborted_errors++;
+		/* fall through */
 	default:
 		dev->stats.tx_errors++;
 		dev_dbg(&dev->dev, "TX error (%d)\n", status);
 	}
 	dev->stats.tx_packets++;
 
-	spin_lock(&pnd->tx_lock);
+	spin_lock_irqsave(&pnd->tx_lock, flags);
 	pnd->tx_queue--;
 	netif_wake_queue(dev);
-	spin_unlock(&pnd->tx_lock);
+	spin_unlock_irqrestore(&pnd->tx_lock, flags);
 
 	dev_kfree_skb_any(skb);
 	usb_free_urb(req);
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index e53883ad6107..184c24baca15 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -999,6 +999,7 @@ static void read_bulk_callback(struct urb *urb)
 	struct hso_net *odev = urb->context;
 	struct net_device *net;
 	int result;
+	unsigned long flags;
 	int status = urb->status;
 
 	/* is al ok?  (Filip: Who's Al ?) */
@@ -1028,11 +1029,11 @@ static void read_bulk_callback(struct urb *urb)
 	if (urb->actual_length) {
 		/* Handle the IP stream, add header and push it onto network
 		 * stack if the packet is complete. */
-		spin_lock(&odev->net_lock);
+		spin_lock_irqsave(&odev->net_lock, flags);
 		packetizeRx(odev, urb->transfer_buffer, urb->actual_length,
 			    (urb->transfer_buffer_length >
 			     urb->actual_length) ? 1 : 0);
-		spin_unlock(&odev->net_lock);
+		spin_unlock_irqrestore(&odev->net_lock, flags);
 	}
 
 	/* We are done with this URB, resubmit it. Prep the USB to wait for
@@ -1193,6 +1194,7 @@ static void hso_std_serial_read_bulk_callback(struct urb *urb)
 {
 	struct hso_serial *serial = urb->context;
 	int status = urb->status;
+	unsigned long flags;
 
 	hso_dbg(0x8, "--- Got serial_read_bulk callback %02x ---\n", status);
 
@@ -1216,10 +1218,10 @@ static void hso_std_serial_read_bulk_callback(struct urb *urb)
 	if (serial->parent->port_spec & HSO_INFO_CRC_BUG)
 		fix_crc_bug(urb, serial->in_endp->wMaxPacketSize);
 	/* Valid data, handle RX data */
-	spin_lock(&serial->serial_lock);
+	spin_lock_irqsave(&serial->serial_lock, flags);
 	serial->rx_urb_filled[hso_urb_to_index(serial, urb)] = 1;
 	put_rxbuf_data_and_resubmit_bulk_urb(serial);
-	spin_unlock(&serial->serial_lock);
+	spin_unlock_irqrestore(&serial->serial_lock, flags);
 }
 
 /*
@@ -1502,12 +1504,13 @@ static void tiocmget_intr_callback(struct urb *urb)
 		DUMP(serial_state_notification,
 		     sizeof(struct hso_serial_state_notification));
 	} else {
+		unsigned long flags;
 
 		UART_state_bitmap = le16_to_cpu(serial_state_notification->
 						UART_state_bitmap);
 		prev_UART_state_bitmap = tiocmget->prev_UART_state_bitmap;
 		icount = &tiocmget->icount;
-		spin_lock(&serial->serial_lock);
+		spin_lock_irqsave(&serial->serial_lock, flags);
 		if ((UART_state_bitmap & B_OVERRUN) !=
 		   (prev_UART_state_bitmap & B_OVERRUN))
 			icount->parity++;
@@ -1530,7 +1533,7 @@ static void tiocmget_intr_callback(struct urb *urb)
 		   (prev_UART_state_bitmap & B_RX_CARRIER))
 			icount->dcd++;
 		tiocmget->prev_UART_state_bitmap = UART_state_bitmap;
-		spin_unlock(&serial->serial_lock);
+		spin_unlock_irqrestore(&serial->serial_lock, flags);
 		tiocmget->intr_completed = 1;
 		wake_up_interruptible(&tiocmget->waitq);
 	}
@@ -1729,7 +1732,6 @@ static int hso_serial_ioctl(struct tty_struct *tty,
 /* starts a transmit */
 static void hso_kick_transmit(struct hso_serial *serial)
 {
-	u8 *temp;
 	unsigned long flags;
 	int res;
 
@@ -1745,14 +1747,12 @@ static void hso_kick_transmit(struct hso_serial *serial)
 		goto out;
 
 	/* Switch pointers around to avoid memcpy */
-	temp = serial->tx_buffer;
-	serial->tx_buffer = serial->tx_data;
-	serial->tx_data = temp;
+	swap(serial->tx_buffer, serial->tx_data);
 	serial->tx_data_count = serial->tx_buffer_count;
 	serial->tx_buffer_count = 0;
 
-	/* If temp is set, it means we switched buffers */
-	if (temp && serial->write_data) {
+	/* If serial->tx_data is set, it means we switched buffers */
+	if (serial->tx_data && serial->write_data) {
 		res = serial->write_data(serial);
 		if (res >= 0)
 			serial->tx_urb_used = 1;
@@ -1852,6 +1852,7 @@ static void intr_callback(struct urb *urb)
 	struct hso_serial *serial;
 	unsigned char *port_req;
 	int status = urb->status;
+	unsigned long flags;
 	int i;
 
 	usb_mark_last_busy(urb->dev);
@@ -1879,7 +1880,7 @@ static void intr_callback(struct urb *urb)
 			if (serial != NULL) {
 				hso_dbg(0x1, "Pending read interrupt on port %d\n",
 					i);
-				spin_lock(&serial->serial_lock);
+				spin_lock_irqsave(&serial->serial_lock, flags);
 				if (serial->rx_state == RX_IDLE &&
 					serial->port.count > 0) {
 					/* Setup and send a ctrl req read on
@@ -1893,7 +1894,8 @@ static void intr_callback(struct urb *urb)
 					hso_dbg(0x1, "Already a read pending on port %d or port not open\n",
 						i);
 				}
-				spin_unlock(&serial->serial_lock);
+				spin_unlock_irqrestore(&serial->serial_lock,
+						       flags);
 			}
 		}
 	}
@@ -1920,6 +1922,7 @@ static void hso_std_serial_write_bulk_callback(struct urb *urb)
 {
 	struct hso_serial *serial = urb->context;
 	int status = urb->status;
+	unsigned long flags;
 
 	/* sanity check */
 	if (!serial) {
@@ -1927,9 +1930,9 @@ static void hso_std_serial_write_bulk_callback(struct urb *urb)
 		return;
 	}
 
-	spin_lock(&serial->serial_lock);
+	spin_lock_irqsave(&serial->serial_lock, flags);
 	serial->tx_urb_used = 0;
-	spin_unlock(&serial->serial_lock);
+	spin_unlock_irqrestore(&serial->serial_lock, flags);
 	if (status) {
 		handle_usb_error(status, __func__, serial->parent);
 		return;
@@ -1971,14 +1974,15 @@ static void ctrl_callback(struct urb *urb)
 	struct hso_serial *serial = urb->context;
 	struct usb_ctrlrequest *req;
 	int status = urb->status;
+	unsigned long flags;
 
 	/* sanity check */
 	if (!serial)
 		return;
 
-	spin_lock(&serial->serial_lock);
+	spin_lock_irqsave(&serial->serial_lock, flags);
 	serial->tx_urb_used = 0;
-	spin_unlock(&serial->serial_lock);
+	spin_unlock_irqrestore(&serial->serial_lock, flags);
 	if (status) {
 		handle_usb_error(status, __func__, serial->parent);
 		return;
@@ -1994,9 +1998,9 @@ static void ctrl_callback(struct urb *urb)
 	    (USB_DIR_IN | USB_TYPE_OPTION_VENDOR | USB_RECIP_INTERFACE)) {
 		/* response to a read command */
 		serial->rx_urb_filled[0] = 1;
-		spin_lock(&serial->serial_lock);
+		spin_lock_irqsave(&serial->serial_lock, flags);
 		put_rxbuf_data_and_resubmit_ctrl_urb(serial);
-		spin_unlock(&serial->serial_lock);
+		spin_unlock_irqrestore(&serial->serial_lock, flags);
 	} else {
 		hso_put_activity(serial->parent);
 		tty_port_tty_wakeup(&serial->port);
diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c
index f1605833c5cf..913e50bab0a2 100644
--- a/drivers/net/usb/kaweth.c
+++ b/drivers/net/usb/kaweth.c
@@ -587,7 +587,7 @@ static void kaweth_usb_receive(struct urb *urb)
 	struct kaweth_device *kaweth = urb->context;
 	struct net_device *net = kaweth->net;
 	int status = urb->status;
-
+	unsigned long flags;
 	int count = urb->actual_length;
 	int count2 = urb->transfer_buffer_length;
 
@@ -619,12 +619,12 @@ static void kaweth_usb_receive(struct urb *urb)
 		net->stats.rx_errors++;
 		dev_dbg(dev, "Status was -EOVERFLOW.\n");
 	}
-	spin_lock(&kaweth->device_lock);
+	spin_lock_irqsave(&kaweth->device_lock, flags);
 	if (IS_BLOCKED(kaweth->status)) {
-		spin_unlock(&kaweth->device_lock);
+		spin_unlock_irqrestore(&kaweth->device_lock, flags);
 		return;
 	}
-	spin_unlock(&kaweth->device_lock);
+	spin_unlock_irqrestore(&kaweth->device_lock, flags);
 
 	if(status && status != -EREMOTEIO && count != 1) {
 		dev_err(&kaweth->intf->dev,
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index aeca484a75b8..a9991c5f4736 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1649,7 +1649,7 @@ lan78xx_get_regs(struct net_device *netdev, struct ethtool_regs *regs,
 	struct lan78xx_net *dev = netdev_priv(netdev);
 
 	/* Read Device/MAC registers */
-	for (i = 0; i < (sizeof(lan78xx_regs) / sizeof(u32)); i++)
+	for (i = 0; i < ARRAY_SIZE(lan78xx_regs); i++)
 		lan78xx_read_reg(dev, lan78xx_regs[i], &data[i]);
 
 	if (!netdev->phydev)
@@ -1723,7 +1723,7 @@ static void lan78xx_init_mac_address(struct lan78xx_net *dev)
 				  "MAC address read from EEPROM");
 		} else {
 			/* generate random MAC */
-			random_ether_addr(addr);
+			eth_random_addr(addr);
 			netif_dbg(dev, ifup, dev->net,
 				  "MAC address set to random addr");
 		}
diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index 6514c86f043e..f4247b275e09 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -1067,7 +1067,7 @@ static inline void setup_pegasus_II(pegasus_t *pegasus)
 
 	set_register(pegasus, Reg1d, 0);
 	set_register(pegasus, Reg7b, 1);
-	mdelay(100);
+	msleep(100);
 	if ((pegasus->features & HAS_HOME_PNA) && mii_mode)
 		set_register(pegasus, Reg7b, 0);
 	else
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 2a58607a6aea..97742708460b 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -1252,6 +1252,7 @@ static void read_bulk_callback(struct urb *urb)
 	int status = urb->status;
 	struct rx_agg *agg;
 	struct r8152 *tp;
+	unsigned long flags;
 
 	agg = urb->context;
 	if (!agg)
@@ -1281,9 +1282,9 @@ static void read_bulk_callback(struct urb *urb)
 		if (urb->actual_length < ETH_ZLEN)
 			break;
 
-		spin_lock(&tp->rx_lock);
+		spin_lock_irqsave(&tp->rx_lock, flags);
 		list_add_tail(&agg->list, &tp->rx_done);
-		spin_unlock(&tp->rx_lock);
+		spin_unlock_irqrestore(&tp->rx_lock, flags);
 		napi_schedule(&tp->napi);
 		return;
 	case -ESHUTDOWN:
@@ -1311,6 +1312,7 @@ static void write_bulk_callback(struct urb *urb)
 	struct net_device *netdev;
 	struct tx_agg *agg;
 	struct r8152 *tp;
+	unsigned long flags;
 	int status = urb->status;
 
 	agg = urb->context;
@@ -1332,9 +1334,9 @@ static void write_bulk_callback(struct urb *urb)
 		stats->tx_bytes += agg->skb_len;
 	}
 
-	spin_lock(&tp->tx_lock);
+	spin_lock_irqsave(&tp->tx_lock, flags);
 	list_add_tail(&agg->list, &tp->tx_free);
-	spin_unlock(&tp->tx_lock);
+	spin_unlock_irqrestore(&tp->tx_lock, flags);
 
 	usb_autopm_put_interface_async(tp->intf);
 
@@ -1374,6 +1376,7 @@ static void intr_callback(struct urb *urb)
 	case -ECONNRESET:	/* unlink */
 	case -ESHUTDOWN:
 		netif_device_detach(tp->netdev);
+		/* fall through */
 	case -ENOENT:
 	case -EPROTO:
 		netif_info(tp, intr, tp->netdev,
@@ -2739,6 +2742,7 @@ static void r8153b_ups_en(struct r8152 *tp, bool enable)
 			r8152_mdio_write(tp, MII_BMCR, data);
 
 			data = r8153_phy_status(tp, PHY_STAT_LAN_ON);
+			/* fall through */
 
 		default:
 			if (data != PHY_STAT_LAN_ON)
@@ -4411,7 +4415,6 @@ out1:
 static int rtl8152_system_suspend(struct r8152 *tp)
 {
 	struct net_device *netdev = tp->netdev;
-	int ret = 0;
 
 	netif_device_detach(netdev);
 
@@ -4426,7 +4429,7 @@ static int rtl8152_system_suspend(struct r8152 *tp)
 		napi_enable(napi);
 	}
 
-	return ret;
+	return 0;
 }
 
 static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index 48ba80a8ca5c..80373a9171dd 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -391,6 +391,7 @@ static void read_bulk_callback(struct urb *urb)
 	u16 rx_stat;
 	int status = urb->status;
 	int result;
+	unsigned long flags;
 
 	dev = urb->context;
 	if (!dev)
@@ -432,9 +433,9 @@ static void read_bulk_callback(struct urb *urb)
 	netdev->stats.rx_packets++;
 	netdev->stats.rx_bytes += pkt_len;
 
-	spin_lock(&dev->rx_pool_lock);
+	spin_lock_irqsave(&dev->rx_pool_lock, flags);
 	skb = pull_skb(dev);
-	spin_unlock(&dev->rx_pool_lock);
+	spin_unlock_irqrestore(&dev->rx_pool_lock, flags);
 	if (!skb)
 		goto resched;
 
diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c
index 2d316c1b851b..6ac232e52bf7 100644
--- a/drivers/net/usb/sr9700.c
+++ b/drivers/net/usb/sr9700.c
@@ -358,7 +358,7 @@ static int sr9700_bind(struct usbnet *dev, struct usb_interface *intf)
 	/* power up and reset phy */
 	sr_write_reg(dev, SR_PRR, PRR_PHY_RST);
 	/* at least 10ms, here 20ms for safe */
-	mdelay(20);
+	msleep(20);
 	sr_write_reg(dev, SR_PRR, 0);
 	/* at least 1ms, here 2ms for reading right register */
 	udelay(2 * 1000);
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index a69ad39ee57e..e3202af72df5 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -17,22 +17,47 @@
 #include <net/rtnetlink.h>
 #include <net/dst.h>
 #include <net/xfrm.h>
+#include <net/xdp.h>
 #include <linux/veth.h>
 #include <linux/module.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/ptr_ring.h>
+#include <linux/bpf_trace.h>
 
 #define DRV_NAME	"veth"
 #define DRV_VERSION	"1.0"
 
+#define VETH_XDP_FLAG		BIT(0)
+#define VETH_RING_SIZE		256
+#define VETH_XDP_HEADROOM	(XDP_PACKET_HEADROOM + NET_IP_ALIGN)
+
+/* Separating two types of XDP xmit */
+#define VETH_XDP_TX		BIT(0)
+#define VETH_XDP_REDIR		BIT(1)
+
 struct pcpu_vstats {
 	u64			packets;
 	u64			bytes;
 	struct u64_stats_sync	syncp;
 };
 
+struct veth_rq {
+	struct napi_struct	xdp_napi;
+	struct net_device	*dev;
+	struct bpf_prog __rcu	*xdp_prog;
+	struct xdp_mem_info	xdp_mem;
+	bool			rx_notify_masked;
+	struct ptr_ring		xdp_ring;
+	struct xdp_rxq_info	xdp_rxq;
+};
+
 struct veth_priv {
 	struct net_device __rcu	*peer;
 	atomic64_t		dropped;
-	unsigned		requested_headroom;
+	struct bpf_prog		*_xdp_prog;
+	struct veth_rq		*rq;
+	unsigned int		requested_headroom;
 };
 
 /*
@@ -98,11 +123,67 @@ static const struct ethtool_ops veth_ethtool_ops = {
 	.get_link_ksettings	= veth_get_link_ksettings,
 };
 
+/* general routines */
+
+static bool veth_is_xdp_frame(void *ptr)
+{
+	return (unsigned long)ptr & VETH_XDP_FLAG;
+}
+
+static void *veth_ptr_to_xdp(void *ptr)
+{
+	return (void *)((unsigned long)ptr & ~VETH_XDP_FLAG);
+}
+
+static void *veth_xdp_to_ptr(void *ptr)
+{
+	return (void *)((unsigned long)ptr | VETH_XDP_FLAG);
+}
+
+static void veth_ptr_free(void *ptr)
+{
+	if (veth_is_xdp_frame(ptr))
+		xdp_return_frame(veth_ptr_to_xdp(ptr));
+	else
+		kfree_skb(ptr);
+}
+
+static void __veth_xdp_flush(struct veth_rq *rq)
+{
+	/* Write ptr_ring before reading rx_notify_masked */
+	smp_mb();
+	if (!rq->rx_notify_masked) {
+		rq->rx_notify_masked = true;
+		napi_schedule(&rq->xdp_napi);
+	}
+}
+
+static int veth_xdp_rx(struct veth_rq *rq, struct sk_buff *skb)
+{
+	if (unlikely(ptr_ring_produce(&rq->xdp_ring, skb))) {
+		dev_kfree_skb_any(skb);
+		return NET_RX_DROP;
+	}
+
+	return NET_RX_SUCCESS;
+}
+
+static int veth_forward_skb(struct net_device *dev, struct sk_buff *skb,
+			    struct veth_rq *rq, bool xdp)
+{
+	return __dev_forward_skb(dev, skb) ?: xdp ?
+		veth_xdp_rx(rq, skb) :
+		netif_rx(skb);
+}
+
 static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-	struct veth_priv *priv = netdev_priv(dev);
+	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
+	struct veth_rq *rq = NULL;
 	struct net_device *rcv;
 	int length = skb->len;
+	bool rcv_xdp = false;
+	int rxq;
 
 	rcu_read_lock();
 	rcv = rcu_dereference(priv->peer);
@@ -111,7 +192,16 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto drop;
 	}
 
-	if (likely(dev_forward_skb(rcv, skb) == NET_RX_SUCCESS)) {
+	rcv_priv = netdev_priv(rcv);
+	rxq = skb_get_queue_mapping(skb);
+	if (rxq < rcv->real_num_rx_queues) {
+		rq = &rcv_priv->rq[rxq];
+		rcv_xdp = rcu_access_pointer(rq->xdp_prog);
+		if (rcv_xdp)
+			skb_record_rx_queue(skb, rxq);
+	}
+
+	if (likely(veth_forward_skb(rcv, skb, rq, rcv_xdp) == NET_RX_SUCCESS)) {
 		struct pcpu_vstats *stats = this_cpu_ptr(dev->vstats);
 
 		u64_stats_update_begin(&stats->syncp);
@@ -122,14 +212,15 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 drop:
 		atomic64_inc(&priv->dropped);
 	}
+
+	if (rcv_xdp)
+		__veth_xdp_flush(rq);
+
 	rcu_read_unlock();
+
 	return NETDEV_TX_OK;
 }
 
-/*
- * general routines
- */
-
 static u64 veth_stats_one(struct pcpu_vstats *result, struct net_device *dev)
 {
 	struct veth_priv *priv = netdev_priv(dev);
@@ -179,18 +270,502 @@ static void veth_set_multicast_list(struct net_device *dev)
 {
 }
 
+static struct sk_buff *veth_build_skb(void *head, int headroom, int len,
+				      int buflen)
+{
+	struct sk_buff *skb;
+
+	if (!buflen) {
+		buflen = SKB_DATA_ALIGN(headroom + len) +
+			 SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	}
+	skb = build_skb(head, buflen);
+	if (!skb)
+		return NULL;
+
+	skb_reserve(skb, headroom);
+	skb_put(skb, len);
+
+	return skb;
+}
+
+static int veth_select_rxq(struct net_device *dev)
+{
+	return smp_processor_id() % dev->real_num_rx_queues;
+}
+
+static int veth_xdp_xmit(struct net_device *dev, int n,
+			 struct xdp_frame **frames, u32 flags)
+{
+	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
+	struct net_device *rcv;
+	unsigned int max_len;
+	struct veth_rq *rq;
+	int i, drops = 0;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	rcv = rcu_dereference(priv->peer);
+	if (unlikely(!rcv))
+		return -ENXIO;
+
+	rcv_priv = netdev_priv(rcv);
+	rq = &rcv_priv->rq[veth_select_rxq(rcv)];
+	/* Non-NULL xdp_prog ensures that xdp_ring is initialized on receive
+	 * side. This means an XDP program is loaded on the peer and the peer
+	 * device is up.
+	 */
+	if (!rcu_access_pointer(rq->xdp_prog))
+		return -ENXIO;
+
+	max_len = rcv->mtu + rcv->hard_header_len + VLAN_HLEN;
+
+	spin_lock(&rq->xdp_ring.producer_lock);
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *frame = frames[i];
+		void *ptr = veth_xdp_to_ptr(frame);
+
+		if (unlikely(frame->len > max_len ||
+			     __ptr_ring_produce(&rq->xdp_ring, ptr))) {
+			xdp_return_frame_rx_napi(frame);
+			drops++;
+		}
+	}
+	spin_unlock(&rq->xdp_ring.producer_lock);
+
+	if (flags & XDP_XMIT_FLUSH)
+		__veth_xdp_flush(rq);
+
+	return n - drops;
+}
+
+static void veth_xdp_flush(struct net_device *dev)
+{
+	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
+	struct net_device *rcv;
+	struct veth_rq *rq;
+
+	rcu_read_lock();
+	rcv = rcu_dereference(priv->peer);
+	if (unlikely(!rcv))
+		goto out;
+
+	rcv_priv = netdev_priv(rcv);
+	rq = &rcv_priv->rq[veth_select_rxq(rcv)];
+	/* xdp_ring is initialized on receive side? */
+	if (unlikely(!rcu_access_pointer(rq->xdp_prog)))
+		goto out;
+
+	__veth_xdp_flush(rq);
+out:
+	rcu_read_unlock();
+}
+
+static int veth_xdp_tx(struct net_device *dev, struct xdp_buff *xdp)
+{
+	struct xdp_frame *frame = convert_to_xdp_frame(xdp);
+
+	if (unlikely(!frame))
+		return -EOVERFLOW;
+
+	return veth_xdp_xmit(dev, 1, &frame, 0);
+}
+
+static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
+					struct xdp_frame *frame,
+					unsigned int *xdp_xmit)
+{
+	void *hard_start = frame->data - frame->headroom;
+	void *head = hard_start - sizeof(struct xdp_frame);
+	int len = frame->len, delta = 0;
+	struct xdp_frame orig_frame;
+	struct bpf_prog *xdp_prog;
+	unsigned int headroom;
+	struct sk_buff *skb;
+
+	rcu_read_lock();
+	xdp_prog = rcu_dereference(rq->xdp_prog);
+	if (likely(xdp_prog)) {
+		struct xdp_buff xdp;
+		u32 act;
+
+		xdp.data_hard_start = hard_start;
+		xdp.data = frame->data;
+		xdp.data_end = frame->data + frame->len;
+		xdp.data_meta = frame->data - frame->metasize;
+		xdp.rxq = &rq->xdp_rxq;
+
+		act = bpf_prog_run_xdp(xdp_prog, &xdp);
+
+		switch (act) {
+		case XDP_PASS:
+			delta = frame->data - xdp.data;
+			len = xdp.data_end - xdp.data;
+			break;
+		case XDP_TX:
+			orig_frame = *frame;
+			xdp.data_hard_start = head;
+			xdp.rxq->mem = frame->mem;
+			if (unlikely(veth_xdp_tx(rq->dev, &xdp) < 0)) {
+				trace_xdp_exception(rq->dev, xdp_prog, act);
+				frame = &orig_frame;
+				goto err_xdp;
+			}
+			*xdp_xmit |= VETH_XDP_TX;
+			rcu_read_unlock();
+			goto xdp_xmit;
+		case XDP_REDIRECT:
+			orig_frame = *frame;
+			xdp.data_hard_start = head;
+			xdp.rxq->mem = frame->mem;
+			if (xdp_do_redirect(rq->dev, &xdp, xdp_prog)) {
+				frame = &orig_frame;
+				goto err_xdp;
+			}
+			*xdp_xmit |= VETH_XDP_REDIR;
+			rcu_read_unlock();
+			goto xdp_xmit;
+		default:
+			bpf_warn_invalid_xdp_action(act);
+		case XDP_ABORTED:
+			trace_xdp_exception(rq->dev, xdp_prog, act);
+		case XDP_DROP:
+			goto err_xdp;
+		}
+	}
+	rcu_read_unlock();
+
+	headroom = sizeof(struct xdp_frame) + frame->headroom - delta;
+	skb = veth_build_skb(head, headroom, len, 0);
+	if (!skb) {
+		xdp_return_frame(frame);
+		goto err;
+	}
+
+	xdp_scrub_frame(frame);
+	skb->protocol = eth_type_trans(skb, rq->dev);
+err:
+	return skb;
+err_xdp:
+	rcu_read_unlock();
+	xdp_return_frame(frame);
+xdp_xmit:
+	return NULL;
+}
+
+static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, struct sk_buff *skb,
+					unsigned int *xdp_xmit)
+{
+	u32 pktlen, headroom, act, metalen;
+	void *orig_data, *orig_data_end;
+	struct bpf_prog *xdp_prog;
+	int mac_len, delta, off;
+	struct xdp_buff xdp;
+
+	rcu_read_lock();
+	xdp_prog = rcu_dereference(rq->xdp_prog);
+	if (unlikely(!xdp_prog)) {
+		rcu_read_unlock();
+		goto out;
+	}
+
+	mac_len = skb->data - skb_mac_header(skb);
+	pktlen = skb->len + mac_len;
+	headroom = skb_headroom(skb) - mac_len;
+
+	if (skb_shared(skb) || skb_head_is_locked(skb) ||
+	    skb_is_nonlinear(skb) || headroom < XDP_PACKET_HEADROOM) {
+		struct sk_buff *nskb;
+		int size, head_off;
+		void *head, *start;
+		struct page *page;
+
+		size = SKB_DATA_ALIGN(VETH_XDP_HEADROOM + pktlen) +
+		       SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+		if (size > PAGE_SIZE)
+			goto drop;
+
+		page = alloc_page(GFP_ATOMIC | __GFP_NOWARN);
+		if (!page)
+			goto drop;
+
+		head = page_address(page);
+		start = head + VETH_XDP_HEADROOM;
+		if (skb_copy_bits(skb, -mac_len, start, pktlen)) {
+			page_frag_free(head);
+			goto drop;
+		}
+
+		nskb = veth_build_skb(head,
+				      VETH_XDP_HEADROOM + mac_len, skb->len,
+				      PAGE_SIZE);
+		if (!nskb) {
+			page_frag_free(head);
+			goto drop;
+		}
+
+		skb_copy_header(nskb, skb);
+		head_off = skb_headroom(nskb) - skb_headroom(skb);
+		skb_headers_offset_update(nskb, head_off);
+		if (skb->sk)
+			skb_set_owner_w(nskb, skb->sk);
+		consume_skb(skb);
+		skb = nskb;
+	}
+
+	xdp.data_hard_start = skb->head;
+	xdp.data = skb_mac_header(skb);
+	xdp.data_end = xdp.data + pktlen;
+	xdp.data_meta = xdp.data;
+	xdp.rxq = &rq->xdp_rxq;
+	orig_data = xdp.data;
+	orig_data_end = xdp.data_end;
+
+	act = bpf_prog_run_xdp(xdp_prog, &xdp);
+
+	switch (act) {
+	case XDP_PASS:
+		break;
+	case XDP_TX:
+		get_page(virt_to_page(xdp.data));
+		consume_skb(skb);
+		xdp.rxq->mem = rq->xdp_mem;
+		if (unlikely(veth_xdp_tx(rq->dev, &xdp) < 0)) {
+			trace_xdp_exception(rq->dev, xdp_prog, act);
+			goto err_xdp;
+		}
+		*xdp_xmit |= VETH_XDP_TX;
+		rcu_read_unlock();
+		goto xdp_xmit;
+	case XDP_REDIRECT:
+		get_page(virt_to_page(xdp.data));
+		consume_skb(skb);
+		xdp.rxq->mem = rq->xdp_mem;
+		if (xdp_do_redirect(rq->dev, &xdp, xdp_prog))
+			goto err_xdp;
+		*xdp_xmit |= VETH_XDP_REDIR;
+		rcu_read_unlock();
+		goto xdp_xmit;
+	default:
+		bpf_warn_invalid_xdp_action(act);
+	case XDP_ABORTED:
+		trace_xdp_exception(rq->dev, xdp_prog, act);
+	case XDP_DROP:
+		goto drop;
+	}
+	rcu_read_unlock();
+
+	delta = orig_data - xdp.data;
+	off = mac_len + delta;
+	if (off > 0)
+		__skb_push(skb, off);
+	else if (off < 0)
+		__skb_pull(skb, -off);
+	skb->mac_header -= delta;
+	off = xdp.data_end - orig_data_end;
+	if (off != 0)
+		__skb_put(skb, off);
+	skb->protocol = eth_type_trans(skb, rq->dev);
+
+	metalen = xdp.data - xdp.data_meta;
+	if (metalen)
+		skb_metadata_set(skb, metalen);
+out:
+	return skb;
+drop:
+	rcu_read_unlock();
+	kfree_skb(skb);
+	return NULL;
+err_xdp:
+	rcu_read_unlock();
+	page_frag_free(xdp.data);
+xdp_xmit:
+	return NULL;
+}
+
+static int veth_xdp_rcv(struct veth_rq *rq, int budget, unsigned int *xdp_xmit)
+{
+	int i, done = 0;
+
+	for (i = 0; i < budget; i++) {
+		void *ptr = __ptr_ring_consume(&rq->xdp_ring);
+		struct sk_buff *skb;
+
+		if (!ptr)
+			break;
+
+		if (veth_is_xdp_frame(ptr)) {
+			skb = veth_xdp_rcv_one(rq, veth_ptr_to_xdp(ptr),
+					       xdp_xmit);
+		} else {
+			skb = veth_xdp_rcv_skb(rq, ptr, xdp_xmit);
+		}
+
+		if (skb)
+			napi_gro_receive(&rq->xdp_napi, skb);
+
+		done++;
+	}
+
+	return done;
+}
+
+static int veth_poll(struct napi_struct *napi, int budget)
+{
+	struct veth_rq *rq =
+		container_of(napi, struct veth_rq, xdp_napi);
+	unsigned int xdp_xmit = 0;
+	int done;
+
+	xdp_set_return_frame_no_direct();
+	done = veth_xdp_rcv(rq, budget, &xdp_xmit);
+
+	if (done < budget && napi_complete_done(napi, done)) {
+		/* Write rx_notify_masked before reading ptr_ring */
+		smp_store_mb(rq->rx_notify_masked, false);
+		if (unlikely(!__ptr_ring_empty(&rq->xdp_ring))) {
+			rq->rx_notify_masked = true;
+			napi_schedule(&rq->xdp_napi);
+		}
+	}
+
+	if (xdp_xmit & VETH_XDP_TX)
+		veth_xdp_flush(rq->dev);
+	if (xdp_xmit & VETH_XDP_REDIR)
+		xdp_do_flush_map();
+	xdp_clear_return_frame_no_direct();
+
+	return done;
+}
+
+static int veth_napi_add(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	int err, i;
+
+	for (i = 0; i < dev->real_num_rx_queues; i++) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		err = ptr_ring_init(&rq->xdp_ring, VETH_RING_SIZE, GFP_KERNEL);
+		if (err)
+			goto err_xdp_ring;
+	}
+
+	for (i = 0; i < dev->real_num_rx_queues; i++) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		netif_napi_add(dev, &rq->xdp_napi, veth_poll, NAPI_POLL_WEIGHT);
+		napi_enable(&rq->xdp_napi);
+	}
+
+	return 0;
+err_xdp_ring:
+	for (i--; i >= 0; i--)
+		ptr_ring_cleanup(&priv->rq[i].xdp_ring, veth_ptr_free);
+
+	return err;
+}
+
+static void veth_napi_del(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	int i;
+
+	for (i = 0; i < dev->real_num_rx_queues; i++) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		napi_disable(&rq->xdp_napi);
+		napi_hash_del(&rq->xdp_napi);
+	}
+	synchronize_net();
+
+	for (i = 0; i < dev->real_num_rx_queues; i++) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		netif_napi_del(&rq->xdp_napi);
+		rq->rx_notify_masked = false;
+		ptr_ring_cleanup(&rq->xdp_ring, veth_ptr_free);
+	}
+}
+
+static int veth_enable_xdp(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	int err, i;
+
+	if (!xdp_rxq_info_is_reg(&priv->rq[0].xdp_rxq)) {
+		for (i = 0; i < dev->real_num_rx_queues; i++) {
+			struct veth_rq *rq = &priv->rq[i];
+
+			err = xdp_rxq_info_reg(&rq->xdp_rxq, dev, i);
+			if (err < 0)
+				goto err_rxq_reg;
+
+			err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
+							 MEM_TYPE_PAGE_SHARED,
+							 NULL);
+			if (err < 0)
+				goto err_reg_mem;
+
+			/* Save original mem info as it can be overwritten */
+			rq->xdp_mem = rq->xdp_rxq.mem;
+		}
+
+		err = veth_napi_add(dev);
+		if (err)
+			goto err_rxq_reg;
+	}
+
+	for (i = 0; i < dev->real_num_rx_queues; i++)
+		rcu_assign_pointer(priv->rq[i].xdp_prog, priv->_xdp_prog);
+
+	return 0;
+err_reg_mem:
+	xdp_rxq_info_unreg(&priv->rq[i].xdp_rxq);
+err_rxq_reg:
+	for (i--; i >= 0; i--)
+		xdp_rxq_info_unreg(&priv->rq[i].xdp_rxq);
+
+	return err;
+}
+
+static void veth_disable_xdp(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	int i;
+
+	for (i = 0; i < dev->real_num_rx_queues; i++)
+		rcu_assign_pointer(priv->rq[i].xdp_prog, NULL);
+	veth_napi_del(dev);
+	for (i = 0; i < dev->real_num_rx_queues; i++) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		rq->xdp_rxq.mem = rq->xdp_mem;
+		xdp_rxq_info_unreg(&rq->xdp_rxq);
+	}
+}
+
 static int veth_open(struct net_device *dev)
 {
 	struct veth_priv *priv = netdev_priv(dev);
 	struct net_device *peer = rtnl_dereference(priv->peer);
+	int err;
 
 	if (!peer)
 		return -ENOTCONN;
 
+	if (priv->_xdp_prog) {
+		err = veth_enable_xdp(dev);
+		if (err)
+			return err;
+	}
+
 	if (peer->flags & IFF_UP) {
 		netif_carrier_on(dev);
 		netif_carrier_on(peer);
 	}
+
 	return 0;
 }
 
@@ -203,6 +778,9 @@ static int veth_close(struct net_device *dev)
 	if (peer)
 		netif_carrier_off(peer);
 
+	if (priv->_xdp_prog)
+		veth_disable_xdp(dev);
+
 	return 0;
 }
 
@@ -228,7 +806,7 @@ static void veth_dev_free(struct net_device *dev)
 static void veth_poll_controller(struct net_device *dev)
 {
 	/* veth only receives frames when its peer sends one
-	 * Since it's a synchronous operation, we are guaranteed
+	 * Since it has nothing to do with disabling irqs, we are guaranteed
 	 * never to have pending data when we poll for it so
 	 * there is nothing to do here.
 	 *
@@ -253,6 +831,23 @@ static int veth_get_iflink(const struct net_device *dev)
 	return iflink;
 }
 
+static netdev_features_t veth_fix_features(struct net_device *dev,
+					   netdev_features_t features)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	struct net_device *peer;
+
+	peer = rtnl_dereference(priv->peer);
+	if (peer) {
+		struct veth_priv *peer_priv = netdev_priv(peer);
+
+		if (peer_priv->_xdp_prog)
+			features &= ~NETIF_F_GSO_SOFTWARE;
+	}
+
+	return features;
+}
+
 static void veth_set_rx_headroom(struct net_device *dev, int new_hr)
 {
 	struct veth_priv *peer_priv, *priv = netdev_priv(dev);
@@ -276,6 +871,103 @@ out:
 	rcu_read_unlock();
 }
 
+static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
+			struct netlink_ext_ack *extack)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	struct bpf_prog *old_prog;
+	struct net_device *peer;
+	unsigned int max_mtu;
+	int err;
+
+	old_prog = priv->_xdp_prog;
+	priv->_xdp_prog = prog;
+	peer = rtnl_dereference(priv->peer);
+
+	if (prog) {
+		if (!peer) {
+			NL_SET_ERR_MSG_MOD(extack, "Cannot set XDP when peer is detached");
+			err = -ENOTCONN;
+			goto err;
+		}
+
+		max_mtu = PAGE_SIZE - VETH_XDP_HEADROOM -
+			  peer->hard_header_len -
+			  SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+		if (peer->mtu > max_mtu) {
+			NL_SET_ERR_MSG_MOD(extack, "Peer MTU is too large to set XDP");
+			err = -ERANGE;
+			goto err;
+		}
+
+		if (dev->real_num_rx_queues < peer->real_num_tx_queues) {
+			NL_SET_ERR_MSG_MOD(extack, "XDP expects number of rx queues not less than peer tx queues");
+			err = -ENOSPC;
+			goto err;
+		}
+
+		if (dev->flags & IFF_UP) {
+			err = veth_enable_xdp(dev);
+			if (err) {
+				NL_SET_ERR_MSG_MOD(extack, "Setup for XDP failed");
+				goto err;
+			}
+		}
+
+		if (!old_prog) {
+			peer->hw_features &= ~NETIF_F_GSO_SOFTWARE;
+			peer->max_mtu = max_mtu;
+		}
+	}
+
+	if (old_prog) {
+		if (!prog) {
+			if (dev->flags & IFF_UP)
+				veth_disable_xdp(dev);
+
+			if (peer) {
+				peer->hw_features |= NETIF_F_GSO_SOFTWARE;
+				peer->max_mtu = ETH_MAX_MTU;
+			}
+		}
+		bpf_prog_put(old_prog);
+	}
+
+	if ((!!old_prog ^ !!prog) && peer)
+		netdev_update_features(peer);
+
+	return 0;
+err:
+	priv->_xdp_prog = old_prog;
+
+	return err;
+}
+
+static u32 veth_xdp_query(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	const struct bpf_prog *xdp_prog;
+
+	xdp_prog = priv->_xdp_prog;
+	if (xdp_prog)
+		return xdp_prog->aux->id;
+
+	return 0;
+}
+
+static int veth_xdp(struct net_device *dev, struct netdev_bpf *xdp)
+{
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return veth_xdp_set(dev, xdp->prog, xdp->extack);
+	case XDP_QUERY_PROG:
+		xdp->prog_id = veth_xdp_query(dev);
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
 static const struct net_device_ops veth_netdev_ops = {
 	.ndo_init            = veth_dev_init,
 	.ndo_open            = veth_open,
@@ -288,8 +980,11 @@ static const struct net_device_ops veth_netdev_ops = {
 	.ndo_poll_controller	= veth_poll_controller,
 #endif
 	.ndo_get_iflink		= veth_get_iflink,
+	.ndo_fix_features	= veth_fix_features,
 	.ndo_features_check	= passthru_features_check,
 	.ndo_set_rx_headroom	= veth_set_rx_headroom,
+	.ndo_bpf		= veth_xdp,
+	.ndo_xdp_xmit		= veth_xdp_xmit,
 };
 
 #define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \
@@ -345,13 +1040,31 @@ static int veth_validate(struct nlattr *tb[], struct nlattr *data[],
 	return 0;
 }
 
+static int veth_alloc_queues(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+
+	priv->rq = kcalloc(dev->num_rx_queues, sizeof(*priv->rq), GFP_KERNEL);
+	if (!priv->rq)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void veth_free_queues(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+
+	kfree(priv->rq);
+}
+
 static struct rtnl_link_ops veth_link_ops;
 
 static int veth_newlink(struct net *src_net, struct net_device *dev,
 			struct nlattr *tb[], struct nlattr *data[],
 			struct netlink_ext_ack *extack)
 {
-	int err;
+	int err, i;
 	struct net_device *peer;
 	struct veth_priv *priv;
 	char ifname[IFNAMSIZ];
@@ -404,6 +1117,12 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
 		return PTR_ERR(peer);
 	}
 
+	err = veth_alloc_queues(peer);
+	if (err) {
+		put_net(net);
+		goto err_peer_alloc_queues;
+	}
+
 	if (!ifmp || !tbp[IFLA_ADDRESS])
 		eth_hw_addr_random(peer);
 
@@ -432,6 +1151,10 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
 	 * should be re-allocated
 	 */
 
+	err = veth_alloc_queues(dev);
+	if (err)
+		goto err_alloc_queues;
+
 	if (tb[IFLA_ADDRESS] == NULL)
 		eth_hw_addr_random(dev);
 
@@ -451,19 +1174,28 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
 	 */
 
 	priv = netdev_priv(dev);
+	for (i = 0; i < dev->real_num_rx_queues; i++)
+		priv->rq[i].dev = dev;
 	rcu_assign_pointer(priv->peer, peer);
 
 	priv = netdev_priv(peer);
+	for (i = 0; i < peer->real_num_rx_queues; i++)
+		priv->rq[i].dev = peer;
 	rcu_assign_pointer(priv->peer, dev);
+
 	return 0;
 
 err_register_dev:
+	veth_free_queues(dev);
+err_alloc_queues:
 	/* nothing to do */
 err_configure_peer:
 	unregister_netdevice(peer);
 	return err;
 
 err_register_peer:
+	veth_free_queues(peer);
+err_peer_alloc_queues:
 	free_netdev(peer);
 	return err;
 }
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 2b6ec927809e..765920905226 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -30,7 +30,7 @@
 #include <linux/cpu.h>
 #include <linux/average.h>
 #include <linux/filter.h>
-#include <linux/netdevice.h>
+#include <linux/kernel.h>
 #include <linux/pci.h>
 #include <net/route.h>
 #include <net/xdp.h>
@@ -82,25 +82,43 @@ struct virtnet_sq_stats {
 	struct u64_stats_sync syncp;
 	u64 packets;
 	u64 bytes;
+	u64 xdp_tx;
+	u64 xdp_tx_drops;
+	u64 kicks;
 };
 
 struct virtnet_rq_stats {
 	struct u64_stats_sync syncp;
 	u64 packets;
 	u64 bytes;
+	u64 drops;
+	u64 xdp_packets;
+	u64 xdp_tx;
+	u64 xdp_redirects;
+	u64 xdp_drops;
+	u64 kicks;
 };
 
 #define VIRTNET_SQ_STAT(m)	offsetof(struct virtnet_sq_stats, m)
 #define VIRTNET_RQ_STAT(m)	offsetof(struct virtnet_rq_stats, m)
 
 static const struct virtnet_stat_desc virtnet_sq_stats_desc[] = {
-	{ "packets",	VIRTNET_SQ_STAT(packets) },
-	{ "bytes",	VIRTNET_SQ_STAT(bytes) },
+	{ "packets",		VIRTNET_SQ_STAT(packets) },
+	{ "bytes",		VIRTNET_SQ_STAT(bytes) },
+	{ "xdp_tx",		VIRTNET_SQ_STAT(xdp_tx) },
+	{ "xdp_tx_drops",	VIRTNET_SQ_STAT(xdp_tx_drops) },
+	{ "kicks",		VIRTNET_SQ_STAT(kicks) },
 };
 
 static const struct virtnet_stat_desc virtnet_rq_stats_desc[] = {
-	{ "packets",	VIRTNET_RQ_STAT(packets) },
-	{ "bytes",	VIRTNET_RQ_STAT(bytes) },
+	{ "packets",		VIRTNET_RQ_STAT(packets) },
+	{ "bytes",		VIRTNET_RQ_STAT(bytes) },
+	{ "drops",		VIRTNET_RQ_STAT(drops) },
+	{ "xdp_packets",	VIRTNET_RQ_STAT(xdp_packets) },
+	{ "xdp_tx",		VIRTNET_RQ_STAT(xdp_tx) },
+	{ "xdp_redirects",	VIRTNET_RQ_STAT(xdp_redirects) },
+	{ "xdp_drops",		VIRTNET_RQ_STAT(xdp_drops) },
+	{ "kicks",		VIRTNET_RQ_STAT(kicks) },
 };
 
 #define VIRTNET_SQ_STATS_LEN	ARRAY_SIZE(virtnet_sq_stats_desc)
@@ -447,22 +465,12 @@ static int __virtnet_xdp_xmit_one(struct virtnet_info *vi,
 	return 0;
 }
 
-static int __virtnet_xdp_tx_xmit(struct virtnet_info *vi,
-				   struct xdp_frame *xdpf)
+static struct send_queue *virtnet_xdp_sq(struct virtnet_info *vi)
 {
-	struct xdp_frame *xdpf_sent;
-	struct send_queue *sq;
-	unsigned int len;
 	unsigned int qp;
 
 	qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id();
-	sq = &vi->sq[qp];
-
-	/* Free up any pending old buffers before queueing new ones. */
-	while ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL)
-		xdp_return_frame(xdpf_sent);
-
-	return __virtnet_xdp_xmit_one(vi, sq, xdpf);
+	return &vi->sq[qp];
 }
 
 static int virtnet_xdp_xmit(struct net_device *dev,
@@ -474,23 +482,28 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	struct bpf_prog *xdp_prog;
 	struct send_queue *sq;
 	unsigned int len;
-	unsigned int qp;
 	int drops = 0;
-	int err;
+	int kicks = 0;
+	int ret, err;
 	int i;
 
-	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
-		return -EINVAL;
+	sq = virtnet_xdp_sq(vi);
 
-	qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id();
-	sq = &vi->sq[qp];
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) {
+		ret = -EINVAL;
+		drops = n;
+		goto out;
+	}
 
 	/* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this
 	 * indicate XDP resources have been successfully allocated.
 	 */
 	xdp_prog = rcu_dereference(rq->xdp_prog);
-	if (!xdp_prog)
-		return -ENXIO;
+	if (!xdp_prog) {
+		ret = -ENXIO;
+		drops = n;
+		goto out;
+	}
 
 	/* Free up any pending old buffers before queueing new ones. */
 	while ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL)
@@ -505,11 +518,20 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 			drops++;
 		}
 	}
+	ret = n - drops;
 
-	if (flags & XDP_XMIT_FLUSH)
-		virtqueue_kick(sq->vq);
+	if (flags & XDP_XMIT_FLUSH) {
+		if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq))
+			kicks = 1;
+	}
+out:
+	u64_stats_update_begin(&sq->stats.syncp);
+	sq->stats.xdp_tx += n;
+	sq->stats.xdp_tx_drops += drops;
+	sq->stats.kicks += kicks;
+	u64_stats_update_end(&sq->stats.syncp);
 
-	return n - drops;
+	return ret;
 }
 
 static unsigned int virtnet_get_headroom(struct virtnet_info *vi)
@@ -587,7 +609,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 				     void *buf, void *ctx,
 				     unsigned int len,
 				     unsigned int *xdp_xmit,
-				     unsigned int *rbytes)
+				     struct virtnet_rq_stats *stats)
 {
 	struct sk_buff *skb;
 	struct bpf_prog *xdp_prog;
@@ -602,7 +624,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 	int err;
 
 	len -= vi->hdr_len;
-	*rbytes += len;
+	stats->bytes += len;
 
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
@@ -644,6 +666,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 		xdp.rxq = &rq->xdp_rxq;
 		orig_data = xdp.data;
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
+		stats->xdp_packets++;
 
 		switch (act) {
 		case XDP_PASS:
@@ -652,11 +675,12 @@ static struct sk_buff *receive_small(struct net_device *dev,
 			len = xdp.data_end - xdp.data;
 			break;
 		case XDP_TX:
+			stats->xdp_tx++;
 			xdpf = convert_to_xdp_frame(&xdp);
 			if (unlikely(!xdpf))
 				goto err_xdp;
-			err = __virtnet_xdp_tx_xmit(vi, xdpf);
-			if (unlikely(err)) {
+			err = virtnet_xdp_xmit(dev, 1, &xdpf, 0);
+			if (unlikely(err < 0)) {
 				trace_xdp_exception(vi->dev, xdp_prog, act);
 				goto err_xdp;
 			}
@@ -664,6 +688,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 			rcu_read_unlock();
 			goto xdp_xmit;
 		case XDP_REDIRECT:
+			stats->xdp_redirects++;
 			err = xdp_do_redirect(dev, &xdp, xdp_prog);
 			if (err)
 				goto err_xdp;
@@ -672,6 +697,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 			goto xdp_xmit;
 		default:
 			bpf_warn_invalid_xdp_action(act);
+			/* fall through */
 		case XDP_ABORTED:
 			trace_xdp_exception(vi->dev, xdp_prog, act);
 		case XDP_DROP:
@@ -697,7 +723,8 @@ err:
 
 err_xdp:
 	rcu_read_unlock();
-	dev->stats.rx_dropped++;
+	stats->xdp_drops++;
+	stats->drops++;
 	put_page(page);
 xdp_xmit:
 	return NULL;
@@ -708,19 +735,19 @@ static struct sk_buff *receive_big(struct net_device *dev,
 				   struct receive_queue *rq,
 				   void *buf,
 				   unsigned int len,
-				   unsigned int *rbytes)
+				   struct virtnet_rq_stats *stats)
 {
 	struct page *page = buf;
 	struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE);
 
-	*rbytes += len - vi->hdr_len;
+	stats->bytes += len - vi->hdr_len;
 	if (unlikely(!skb))
 		goto err;
 
 	return skb;
 
 err:
-	dev->stats.rx_dropped++;
+	stats->drops++;
 	give_pages(rq, page);
 	return NULL;
 }
@@ -732,7 +759,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 					 void *ctx,
 					 unsigned int len,
 					 unsigned int *xdp_xmit,
-					 unsigned int *rbytes)
+					 struct virtnet_rq_stats *stats)
 {
 	struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
 	u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
@@ -745,7 +772,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	int err;
 
 	head_skb = NULL;
-	*rbytes += len - vi->hdr_len;
+	stats->bytes += len - vi->hdr_len;
 
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
@@ -794,6 +821,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		xdp.rxq = &rq->xdp_rxq;
 
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
+		stats->xdp_packets++;
 
 		switch (act) {
 		case XDP_PASS:
@@ -818,11 +846,12 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			}
 			break;
 		case XDP_TX:
+			stats->xdp_tx++;
 			xdpf = convert_to_xdp_frame(&xdp);
 			if (unlikely(!xdpf))
 				goto err_xdp;
-			err = __virtnet_xdp_tx_xmit(vi, xdpf);
-			if (unlikely(err)) {
+			err = virtnet_xdp_xmit(dev, 1, &xdpf, 0);
+			if (unlikely(err < 0)) {
 				trace_xdp_exception(vi->dev, xdp_prog, act);
 				if (unlikely(xdp_page != page))
 					put_page(xdp_page);
@@ -834,6 +863,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			rcu_read_unlock();
 			goto xdp_xmit;
 		case XDP_REDIRECT:
+			stats->xdp_redirects++;
 			err = xdp_do_redirect(dev, &xdp, xdp_prog);
 			if (err) {
 				if (unlikely(xdp_page != page))
@@ -847,8 +877,10 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			goto xdp_xmit;
 		default:
 			bpf_warn_invalid_xdp_action(act);
+			/* fall through */
 		case XDP_ABORTED:
 			trace_xdp_exception(vi->dev, xdp_prog, act);
+			/* fall through */
 		case XDP_DROP:
 			if (unlikely(xdp_page != page))
 				__free_pages(xdp_page, 0);
@@ -883,7 +915,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			goto err_buf;
 		}
 
-		*rbytes += len;
+		stats->bytes += len;
 		page = virt_to_head_page(buf);
 
 		truesize = mergeable_ctx_to_truesize(ctx);
@@ -929,6 +961,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 
 err_xdp:
 	rcu_read_unlock();
+	stats->xdp_drops++;
 err_skb:
 	put_page(page);
 	while (num_buf-- > 1) {
@@ -939,12 +972,12 @@ err_skb:
 			dev->stats.rx_length_errors++;
 			break;
 		}
-		*rbytes += len;
+		stats->bytes += len;
 		page = virt_to_head_page(buf);
 		put_page(page);
 	}
 err_buf:
-	dev->stats.rx_dropped++;
+	stats->drops++;
 	dev_kfree_skb(head_skb);
 xdp_xmit:
 	return NULL;
@@ -952,7 +985,8 @@ xdp_xmit:
 
 static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 			void *buf, unsigned int len, void **ctx,
-			unsigned int *xdp_xmit, unsigned int *rbytes)
+			unsigned int *xdp_xmit,
+			struct virtnet_rq_stats *stats)
 {
 	struct net_device *dev = vi->dev;
 	struct sk_buff *skb;
@@ -973,11 +1007,11 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 
 	if (vi->mergeable_rx_bufs)
 		skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit,
-					rbytes);
+					stats);
 	else if (vi->big_packets)
-		skb = receive_big(dev, vi, rq, buf, len, rbytes);
+		skb = receive_big(dev, vi, rq, buf, len, stats);
 	else
-		skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit, rbytes);
+		skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit, stats);
 
 	if (unlikely(!skb))
 		return;
@@ -1171,7 +1205,12 @@ static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq,
 		if (err)
 			break;
 	} while (rq->vq->num_free);
-	virtqueue_kick(rq->vq);
+	if (virtqueue_kick_prepare(rq->vq) && virtqueue_notify(rq->vq)) {
+		u64_stats_update_begin(&rq->stats.syncp);
+		rq->stats.kicks++;
+		u64_stats_update_end(&rq->stats.syncp);
+	}
+
 	return !oom;
 }
 
@@ -1246,22 +1285,24 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 			   unsigned int *xdp_xmit)
 {
 	struct virtnet_info *vi = rq->vq->vdev->priv;
-	unsigned int len, received = 0, bytes = 0;
+	struct virtnet_rq_stats stats = {};
+	unsigned int len;
 	void *buf;
+	int i;
 
 	if (!vi->big_packets || vi->mergeable_rx_bufs) {
 		void *ctx;
 
-		while (received < budget &&
+		while (stats.packets < budget &&
 		       (buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) {
-			receive_buf(vi, rq, buf, len, ctx, xdp_xmit, &bytes);
-			received++;
+			receive_buf(vi, rq, buf, len, ctx, xdp_xmit, &stats);
+			stats.packets++;
 		}
 	} else {
-		while (received < budget &&
+		while (stats.packets < budget &&
 		       (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
-			receive_buf(vi, rq, buf, len, NULL, xdp_xmit, &bytes);
-			received++;
+			receive_buf(vi, rq, buf, len, NULL, xdp_xmit, &stats);
+			stats.packets++;
 		}
 	}
 
@@ -1271,11 +1312,16 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 	}
 
 	u64_stats_update_begin(&rq->stats.syncp);
-	rq->stats.bytes += bytes;
-	rq->stats.packets += received;
+	for (i = 0; i < VIRTNET_RQ_STATS_LEN; i++) {
+		size_t offset = virtnet_rq_stats_desc[i].offset;
+		u64 *item;
+
+		item = (u64 *)((u8 *)&rq->stats + offset);
+		*item += *(u64 *)((u8 *)&stats + offset);
+	}
 	u64_stats_update_end(&rq->stats.syncp);
 
-	return received;
+	return stats.packets;
 }
 
 static void free_old_xmit_skbs(struct send_queue *sq)
@@ -1331,7 +1377,7 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 		container_of(napi, struct receive_queue, napi);
 	struct virtnet_info *vi = rq->vq->vdev->priv;
 	struct send_queue *sq;
-	unsigned int received, qp;
+	unsigned int received;
 	unsigned int xdp_xmit = 0;
 
 	virtnet_poll_cleantx(rq);
@@ -1346,10 +1392,12 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 		xdp_do_flush_map();
 
 	if (xdp_xmit & VIRTIO_XDP_TX) {
-		qp = vi->curr_queue_pairs - vi->xdp_queue_pairs +
-		     smp_processor_id();
-		sq = &vi->sq[qp];
-		virtqueue_kick(sq->vq);
+		sq = virtnet_xdp_sq(vi);
+		if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) {
+			u64_stats_update_begin(&sq->stats.syncp);
+			sq->stats.kicks++;
+			u64_stats_update_end(&sq->stats.syncp);
+		}
 	}
 
 	return received;
@@ -1511,8 +1559,13 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 
-	if (kick || netif_xmit_stopped(txq))
-		virtqueue_kick(sq->vq);
+	if (kick || netif_xmit_stopped(txq)) {
+		if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) {
+			u64_stats_update_begin(&sq->stats.syncp);
+			sq->stats.kicks++;
+			u64_stats_update_end(&sq->stats.syncp);
+		}
+	}
 
 	return NETDEV_TX_OK;
 }
@@ -1616,7 +1669,7 @@ static void virtnet_stats(struct net_device *dev,
 	int i;
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
-		u64 tpackets, tbytes, rpackets, rbytes;
+		u64 tpackets, tbytes, rpackets, rbytes, rdrops;
 		struct receive_queue *rq = &vi->rq[i];
 		struct send_queue *sq = &vi->sq[i];
 
@@ -1630,17 +1683,18 @@ static void virtnet_stats(struct net_device *dev,
 			start = u64_stats_fetch_begin_irq(&rq->stats.syncp);
 			rpackets = rq->stats.packets;
 			rbytes   = rq->stats.bytes;
+			rdrops   = rq->stats.drops;
 		} while (u64_stats_fetch_retry_irq(&rq->stats.syncp, start));
 
 		tot->rx_packets += rpackets;
 		tot->tx_packets += tpackets;
 		tot->rx_bytes   += rbytes;
 		tot->tx_bytes   += tbytes;
+		tot->rx_dropped += rdrops;
 	}
 
 	tot->tx_dropped = dev->stats.tx_dropped;
 	tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
-	tot->rx_dropped = dev->stats.rx_dropped;
 	tot->rx_length_errors = dev->stats.rx_length_errors;
 	tot->rx_frame_errors = dev->stats.rx_frame_errors;
 }
@@ -1824,8 +1878,8 @@ static void virtnet_clean_affinity(struct virtnet_info *vi, long hcpu)
 
 	if (vi->affinity_hint_set) {
 		for (i = 0; i < vi->max_queue_pairs; i++) {
-			virtqueue_set_affinity(vi->rq[i].vq, -1);
-			virtqueue_set_affinity(vi->sq[i].vq, -1);
+			virtqueue_set_affinity(vi->rq[i].vq, NULL);
+			virtqueue_set_affinity(vi->sq[i].vq, NULL);
 		}
 
 		vi->affinity_hint_set = false;
@@ -1834,28 +1888,41 @@ static void virtnet_clean_affinity(struct virtnet_info *vi, long hcpu)
 
 static void virtnet_set_affinity(struct virtnet_info *vi)
 {
-	int i;
-	int cpu;
+	cpumask_var_t mask;
+	int stragglers;
+	int group_size;
+	int i, j, cpu;
+	int num_cpu;
+	int stride;
 
-	/* In multiqueue mode, when the number of cpu is equal to the number of
-	 * queue pairs, we let the queue pairs to be private to one cpu by
-	 * setting the affinity hint to eliminate the contention.
-	 */
-	if (vi->curr_queue_pairs == 1 ||
-	    vi->max_queue_pairs != num_online_cpus()) {
+	if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) {
 		virtnet_clean_affinity(vi, -1);
 		return;
 	}
 
-	i = 0;
-	for_each_online_cpu(cpu) {
-		virtqueue_set_affinity(vi->rq[i].vq, cpu);
-		virtqueue_set_affinity(vi->sq[i].vq, cpu);
-		netif_set_xps_queue(vi->dev, cpumask_of(cpu), i);
-		i++;
+	num_cpu = num_online_cpus();
+	stride = max_t(int, num_cpu / vi->curr_queue_pairs, 1);
+	stragglers = num_cpu >= vi->curr_queue_pairs ?
+			num_cpu % vi->curr_queue_pairs :
+			0;
+	cpu = cpumask_next(-1, cpu_online_mask);
+
+	for (i = 0; i < vi->curr_queue_pairs; i++) {
+		group_size = stride + (i < stragglers ? 1 : 0);
+
+		for (j = 0; j < group_size; j++) {
+			cpumask_set_cpu(cpu, mask);
+			cpu = cpumask_next_wrap(cpu, cpu_online_mask,
+						nr_cpu_ids, false);
+		}
+		virtqueue_set_affinity(vi->rq[i].vq, mask);
+		virtqueue_set_affinity(vi->sq[i].vq, mask);
+		__netif_set_xps_queue(vi->dev, cpumask_bits(mask), i, false);
+		cpumask_clear(mask);
 	}
 
 	vi->affinity_hint_set = true;
+	free_cpumask_var(mask);
 }
 
 static int virtnet_cpu_online(unsigned int cpu, struct hlist_node *node)
@@ -2348,7 +2415,6 @@ static int virtnet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		return virtnet_xdp_set(dev, xdp->prog, xdp->extack);
 	case XDP_QUERY_PROG:
 		xdp->prog_id = virtnet_xdp_query(dev);
-		xdp->prog_attached = !!xdp->prog_id;
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index e857cb3335f6..ababba37d735 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -568,11 +568,12 @@ static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb,
 	return vh;
 }
 
-static struct sk_buff **vxlan_gro_receive(struct sock *sk,
-					  struct sk_buff **head,
-					  struct sk_buff *skb)
+static struct sk_buff *vxlan_gro_receive(struct sock *sk,
+					 struct list_head *head,
+					 struct sk_buff *skb)
 {
-	struct sk_buff *p, **pp = NULL;
+	struct sk_buff *pp = NULL;
+	struct sk_buff *p;
 	struct vxlanhdr *vh, *vh2;
 	unsigned int hlen, off_vx;
 	int flush = 1;
@@ -607,7 +608,7 @@ static struct sk_buff **vxlan_gro_receive(struct sock *sk,
 
 	skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */
 
-	for (p = *head; p; p = p->next) {
+	list_for_each_entry(p, head, list) {
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
 
@@ -2154,7 +2155,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		vni = tunnel_id_to_key32(info->key.tun_id);
 		ifindex = 0;
 		dst_cache = &info->dst_cache;
-		if (info->options_len)
+		if (info->options_len &&
+		    info->key.tun_flags & TUNNEL_VXLAN_OPT)
 			md = ip_tunnel_info_opts(info);
 		ttl = info->key.ttl;
 		tos = info->key.tos;
diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c
index bd46b2552980..2a3f0f1a2b0a 100644
--- a/drivers/net/wan/farsync.c
+++ b/drivers/net/wan/farsync.c
@@ -2134,7 +2134,6 @@ static void
 fst_openport(struct fst_port_info *port)
 {
 	int signals;
-	int txq_length;
 
 	/* Only init things if card is actually running. This allows open to
 	 * succeed for downloads etc.
@@ -2161,7 +2160,6 @@ fst_openport(struct fst_port_info *port)
 		else
 			netif_carrier_off(port_to_dev(port));
 
-		txq_length = port->txqe - port->txqs;
 		port->txqe = 0;
 		port->txqs = 0;
 	}
diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index 9b09c9d0d0fb..5f0366a125e2 100644
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -192,7 +192,7 @@ static int uhdlc_init(struct ucc_hdlc_private *priv)
 	priv->ucc_pram_offset = qe_muram_alloc(sizeof(struct ucc_hdlc_param),
 				ALIGNMENT_OF_UCC_HDLC_PRAM);
 
-	if (priv->ucc_pram_offset < 0) {
+	if (IS_ERR_VALUE(priv->ucc_pram_offset)) {
 		dev_err(priv->dev, "Can not allocate MURAM for hdlc parameter.\n");
 		ret = -ENOMEM;
 		goto free_tx_bd;
@@ -230,14 +230,14 @@ static int uhdlc_init(struct ucc_hdlc_private *priv)
 
 	/* Alloc riptr, tiptr */
 	riptr = qe_muram_alloc(32, 32);
-	if (riptr < 0) {
+	if (IS_ERR_VALUE(riptr)) {
 		dev_err(priv->dev, "Cannot allocate MURAM mem for Receive internal temp data pointer\n");
 		ret = -ENOMEM;
 		goto free_tx_skbuff;
 	}
 
 	tiptr = qe_muram_alloc(32, 32);
-	if (tiptr < 0) {
+	if (IS_ERR_VALUE(tiptr)) {
 		dev_err(priv->dev, "Cannot allocate MURAM mem for Transmit internal temp data pointer\n");
 		ret = -ENOMEM;
 		goto free_riptr;
diff --git a/drivers/net/wan/lmc/lmc_main.c b/drivers/net/wan/lmc/lmc_main.c
index b3a1b6f5c406..4907453f17f5 100644
--- a/drivers/net/wan/lmc/lmc_main.c
+++ b/drivers/net/wan/lmc/lmc_main.c
@@ -1491,7 +1491,6 @@ static int lmc_rx(struct net_device *dev)
     lmc_softc_t *sc = dev_to_sc(dev);
     int i;
     int rx_work_limit = LMC_RXDESCS;
-    unsigned int next_rx;
     int rxIntLoopCnt;		/* debug -baz */
     int localLengthErrCnt = 0;
     long stat;
@@ -1505,7 +1504,6 @@ static int lmc_rx(struct net_device *dev)
     rxIntLoopCnt = 0;		/* debug -baz */
 
     i = sc->lmc_next_rx % LMC_RXDESCS;
-    next_rx = sc->lmc_next_rx;
 
     while (((stat = sc->lmc_rxring[i].status) & LMC_RDES_OWN_BIT) != DESC_OWNED_BY_DC21X4)
     {
diff --git a/drivers/net/wimax/i2400m/control.c b/drivers/net/wimax/i2400m/control.c
index 4c417903e9be..094cea775d0c 100644
--- a/drivers/net/wimax/i2400m/control.c
+++ b/drivers/net/wimax/i2400m/control.c
@@ -566,13 +566,12 @@ static void i2400m_msg_ack_hook(struct i2400m *i2400m,
 {
 	int result;
 	struct device *dev = i2400m_dev(i2400m);
-	unsigned ack_type, ack_status;
+	unsigned int ack_type;
 	char strerr[32];
 
 	/* Chew on the message, we might need some information from
 	 * here */
 	ack_type = le16_to_cpu(l3l4_hdr->type);
-	ack_status = le16_to_cpu(l3l4_hdr->status);
 	switch (ack_type) {
 	case I2400M_MT_CMD_ENTER_POWERSAVE:
 		/* This is just left here for the sake of example, as
diff --git a/drivers/net/wimax/i2400m/fw.c b/drivers/net/wimax/i2400m/fw.c
index a89b5685e68b..e9fc168bb734 100644
--- a/drivers/net/wimax/i2400m/fw.c
+++ b/drivers/net/wimax/i2400m/fw.c
@@ -1552,7 +1552,6 @@ int i2400m_dev_bootstrap(struct i2400m *i2400m, enum i2400m_bri flags)
 	int ret, itr;
 	struct device *dev = i2400m_dev(i2400m);
 	struct i2400m_fw *i2400m_fw;
-	const struct i2400m_bcf_hdr *bcf;	/* Firmware data */
 	const struct firmware *fw;
 	const char *fw_name;
 
@@ -1574,7 +1573,7 @@ int i2400m_dev_bootstrap(struct i2400m *i2400m, enum i2400m_bri flags)
 	}
 
 	/* Load firmware files to memory. */
-	for (itr = 0, bcf = NULL, ret = -ENOENT; ; itr++) {
+	for (itr = 0, ret = -ENOENT; ; itr++) {
 		fw_name = i2400m->bus_fw_names[itr];
 		if (fw_name == NULL) {
 			dev_err(dev, "Could not find a usable firmware image\n");
diff --git a/drivers/net/wimax/i2400m/netdev.c b/drivers/net/wimax/i2400m/netdev.c
index a654687b5fa2..9ab3f0fdfea4 100644
--- a/drivers/net/wimax/i2400m/netdev.c
+++ b/drivers/net/wimax/i2400m/netdev.c
@@ -535,14 +535,12 @@ void i2400m_net_erx(struct i2400m *i2400m, struct sk_buff *skb,
 {
 	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
 	struct device *dev = i2400m_dev(i2400m);
-	int protocol;
 
 	d_fnstart(2, dev, "(i2400m %p skb %p [%u] cs %d)\n",
 		  i2400m, skb, skb->len, cs);
 	switch(cs) {
 	case I2400M_CS_IPV4_0:
 	case I2400M_CS_IPV4:
-		protocol = ETH_P_IP;
 		i2400m_rx_fake_eth_header(i2400m->wimax_dev.net_dev,
 					  skb->data - ETH_HLEN,
 					  cpu_to_be16(ETH_P_IP));
diff --git a/drivers/net/wimax/i2400m/usb-fw.c b/drivers/net/wimax/i2400m/usb-fw.c
index 502c346aa790..529ebca1e9e1 100644
--- a/drivers/net/wimax/i2400m/usb-fw.c
+++ b/drivers/net/wimax/i2400m/usb-fw.c
@@ -130,12 +130,12 @@ retry:
 			dev_err(dev, "BM-CMD: too many stalls in "
 				"URB; resetting device\n");
 			usb_queue_reset_device(i2400mu->usb_iface);
-			/* fallthrough */
 		} else {
 			usb_clear_halt(i2400mu->usb_dev, pipe);
 			msleep(10);	/* give the device some time */
 			goto retry;
 		}
+		/* fall through */
 	case -EINVAL:			/* while removing driver */
 	case -ENODEV:			/* dev disconnect ... */
 	case -ENOENT:			/* just ignore it */
diff --git a/drivers/net/wimax/i2400m/usb-tx.c b/drivers/net/wimax/i2400m/usb-tx.c
index 99ef81b3d5a5..3a0e7226768a 100644
--- a/drivers/net/wimax/i2400m/usb-tx.c
+++ b/drivers/net/wimax/i2400m/usb-tx.c
@@ -131,12 +131,12 @@ retry:
 			dev_err(dev, "BM-CMD: too many stalls in "
 				"URB; resetting device\n");
 			usb_queue_reset_device(i2400mu->usb_iface);
-			/* fallthrough */
 		} else {
 			usb_clear_halt(i2400mu->usb_dev, usb_pipe);
 			msleep(10);	/* give the device some time */
 			goto retry;
 		}
+		/* fall through */
 	case -EINVAL:			/* while removing driver */
 	case -ENODEV:			/* dev disconnect ... */
 	case -ENOENT:			/* just ignore it */
diff --git a/drivers/net/wireless/ath/ath10k/Kconfig b/drivers/net/wireless/ath/ath10k/Kconfig
index 84f071ac0d84..54ff5930126c 100644
--- a/drivers/net/wireless/ath/ath10k/Kconfig
+++ b/drivers/net/wireless/ath/ath10k/Kconfig
@@ -1,15 +1,15 @@
 config ATH10K
-        tristate "Atheros 802.11ac wireless cards support"
-        depends on MAC80211 && HAS_DMA
+	tristate "Atheros 802.11ac wireless cards support"
+	depends on MAC80211 && HAS_DMA
 	select ATH_COMMON
 	select CRC32
 	select WANT_DEV_COREDUMP
 	select ATH10K_CE
-        ---help---
-          This module adds support for wireless adapters based on
-          Atheros IEEE 802.11ac family of chipsets.
+	---help---
+	  This module adds support for wireless adapters based on
+	  Atheros IEEE 802.11ac family of chipsets.
 
-          If you choose to build a module, it'll be called ath10k.
+	  If you choose to build a module, it'll be called ath10k.
 
 config ATH10K_CE
 	bool
@@ -41,12 +41,12 @@ config ATH10K_USB
 	  work in progress and will not fully work.
 
 config ATH10K_SNOC
-        tristate "Qualcomm ath10k SNOC support (EXPERIMENTAL)"
-        depends on ATH10K && ARCH_QCOM
-        ---help---
-          This module adds support for integrated WCN3990 chip connected
-          to system NOC(SNOC). Currently work in progress and will not
-          fully work.
+	tristate "Qualcomm ath10k SNOC support (EXPERIMENTAL)"
+	depends on ATH10K && ARCH_QCOM
+	---help---
+	  This module adds support for integrated WCN3990 chip connected
+	  to system NOC(SNOC). Currently work in progress and will not
+	  fully work.
 
 config ATH10K_DEBUG
 	bool "Atheros ath10k debugging"
diff --git a/drivers/net/wireless/ath/ath10k/ahb.c b/drivers/net/wireless/ath/ath10k/ahb.c
index fa39ffffd34d..c9bd0e2b5db7 100644
--- a/drivers/net/wireless/ath/ath10k/ahb.c
+++ b/drivers/net/wireless/ath/ath10k/ahb.c
@@ -133,11 +133,8 @@ static void ath10k_ahb_clock_deinit(struct ath10k *ar)
 static int ath10k_ahb_clock_enable(struct ath10k *ar)
 {
 	struct ath10k_ahb *ar_ahb = ath10k_ahb_priv(ar);
-	struct device *dev;
 	int ret;
 
-	dev = &ar_ahb->pdev->dev;
-
 	if (IS_ERR_OR_NULL(ar_ahb->cmd_clk) ||
 	    IS_ERR_OR_NULL(ar_ahb->ref_clk) ||
 	    IS_ERR_OR_NULL(ar_ahb->rtc_clk)) {
@@ -451,12 +448,10 @@ static int ath10k_ahb_resource_init(struct ath10k *ar)
 {
 	struct ath10k_ahb *ar_ahb = ath10k_ahb_priv(ar);
 	struct platform_device *pdev;
-	struct device *dev;
 	struct resource *res;
 	int ret;
 
 	pdev = ar_ahb->pdev;
-	dev = &pdev->dev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
diff --git a/drivers/net/wireless/ath/ath10k/ce.c b/drivers/net/wireless/ath/ath10k/ce.c
index 3b96a43fbda4..18c709c484e7 100644
--- a/drivers/net/wireless/ath/ath10k/ce.c
+++ b/drivers/net/wireless/ath/ath10k/ce.c
@@ -1512,7 +1512,7 @@ ath10k_ce_alloc_src_ring_64(struct ath10k *ar, unsigned int ce_id,
 		ret = ath10k_ce_alloc_shadow_base(ar, src_ring, nentries);
 		if (ret) {
 			dma_free_coherent(ar->dev,
-					  (nentries * sizeof(struct ce_desc) +
+					  (nentries * sizeof(struct ce_desc_64) +
 					   CE_DESC_RING_ALIGN),
 					  src_ring->base_addr_owner_space_unaligned,
 					  base_addr);
diff --git a/drivers/net/wireless/ath/ath10k/ce.h b/drivers/net/wireless/ath/ath10k/ce.h
index dbeffaef6024..b8fb5382dede 100644
--- a/drivers/net/wireless/ath/ath10k/ce.h
+++ b/drivers/net/wireless/ath/ath10k/ce.h
@@ -383,4 +383,46 @@ static inline u32 ath10k_ce_interrupt_summary(struct ath10k *ar)
 		return CE_INTERRUPT_SUMMARY;
 }
 
+/* Host software's Copy Engine configuration. */
+#define CE_ATTR_FLAGS 0
+
+/*
+ * Configuration information for a Copy Engine pipe.
+ * Passed from Host to Target during startup (one per CE).
+ *
+ * NOTE: Structure is shared between Host software and Target firmware!
+ */
+struct ce_pipe_config {
+	__le32 pipenum;
+	__le32 pipedir;
+	__le32 nentries;
+	__le32 nbytes_max;
+	__le32 flags;
+	__le32 reserved;
+};
+
+/*
+ * Directions for interconnect pipe configuration.
+ * These definitions may be used during configuration and are shared
+ * between Host and Target.
+ *
+ * Pipe Directions are relative to the Host, so PIPEDIR_IN means
+ * "coming IN over air through Target to Host" as with a WiFi Rx operation.
+ * Conversely, PIPEDIR_OUT means "going OUT from Host through Target over air"
+ * as with a WiFi Tx operation. This is somewhat awkward for the "middle-man"
+ * Target since things that are "PIPEDIR_OUT" are coming IN to the Target
+ * over the interconnect.
+ */
+#define PIPEDIR_NONE    0
+#define PIPEDIR_IN      1  /* Target-->Host, WiFi Rx direction */
+#define PIPEDIR_OUT     2  /* Host->Target, WiFi Tx direction */
+#define PIPEDIR_INOUT   3  /* bidirectional */
+
+/* Establish a mapping between a service/direction and a pipe. */
+struct service_to_pipe {
+	__le32 service_id;
+	__le32 pipedir;
+	__le32 pipenum;
+};
+
 #endif /* _CE_H_ */
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index ad4f6e3c0737..c40cd129afe7 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -41,10 +41,8 @@ static bool uart_print;
 static bool skip_otp;
 static bool rawmode;
 
-/* Enable ATH10K_FW_CRASH_DUMP_REGISTERS and ATH10K_FW_CRASH_DUMP_CE_DATA
- * by default.
- */
-unsigned long ath10k_coredump_mask = 0x3;
+unsigned long ath10k_coredump_mask = BIT(ATH10K_FW_CRASH_DUMP_REGISTERS) |
+				     BIT(ATH10K_FW_CRASH_DUMP_CE_DATA);
 
 /* FIXME: most of these should be readonly */
 module_param_named(debug_mask, ath10k_debug_mask, uint, 0644);
@@ -82,6 +80,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
 		.spectral_bin_discard = 0,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 8,
@@ -113,6 +112,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
 		.spectral_bin_discard = 0,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 8,
@@ -145,6 +145,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
 		.spectral_bin_discard = 0,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 8,
@@ -176,6 +177,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
 		.spectral_bin_discard = 0,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 8,
@@ -207,6 +209,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
 		.spectral_bin_discard = 0,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 8,
@@ -238,6 +241,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
 		.spectral_bin_discard = 0,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 8,
@@ -272,6 +276,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.target_cpu_freq = 176000000,
 		.decap_align_bytes = 4,
 		.spectral_bin_discard = 0,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 8,
@@ -309,6 +314,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca99x0_ops,
 		.decap_align_bytes = 1,
 		.spectral_bin_discard = 4,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 11,
@@ -347,6 +353,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca99x0_ops,
 		.decap_align_bytes = 1,
 		.spectral_bin_discard = 12,
+		.spectral_bin_offset = 8,
 
 		/* Can do only 2x2 VHT160 or 80+80. 1560Mbps is 4x4 80Mhz
 		 * or 2x2 160Mhz, long-guard-interval.
@@ -388,6 +395,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca99x0_ops,
 		.decap_align_bytes = 1,
 		.spectral_bin_discard = 12,
+		.spectral_bin_offset = 8,
 
 		/* Can do only 1x1 VHT160 or 80+80. 780Mbps is 2x2 80Mhz or
 		 * 1x1 160Mhz, long-guard-interval.
@@ -423,6 +431,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
 		.spectral_bin_discard = 0,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 8,
@@ -456,6 +465,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.target_cpu_freq = 176000000,
 		.decap_align_bytes = 4,
 		.spectral_bin_discard = 0,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 8,
@@ -494,6 +504,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca99x0_ops,
 		.decap_align_bytes = 1,
 		.spectral_bin_discard = 4,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 11,
@@ -2084,6 +2095,7 @@ static int ath10k_core_init_firmware_features(struct ath10k *ar)
 		ar->fw_stats_req_mask = WMI_STAT_PDEV | WMI_STAT_VDEV |
 			WMI_STAT_PEER;
 		ar->max_spatial_stream = WMI_MAX_SPATIAL_STREAM;
+		ar->wmi.mgmt_max_num_pending_tx = TARGET_TLV_MGMT_NUM_MSDU_DESC;
 		break;
 	case ATH10K_FW_WMI_OP_VERSION_10_4:
 		ar->max_num_peers = TARGET_10_4_NUM_PEERS;
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 951dbdd1c9eb..9feea02e7d37 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -48,7 +48,8 @@
 #define WMI_READY_TIMEOUT (5 * HZ)
 #define ATH10K_FLUSH_TIMEOUT_HZ (5 * HZ)
 #define ATH10K_CONNECTION_LOSS_HZ (3 * HZ)
-#define ATH10K_NUM_CHANS 40
+#define ATH10K_NUM_CHANS 41
+#define ATH10K_MAX_5G_CHAN 173
 
 /* Antenna noise floor */
 #define ATH10K_DEFAULT_NOISE_FLOOR -95
@@ -185,6 +186,11 @@ struct ath10k_wmi {
 	const struct wmi_ops *ops;
 	const struct wmi_peer_flags_map *peer_flags;
 
+	u32 mgmt_max_num_pending_tx;
+
+	/* Protected by data_lock */
+	struct idr mgmt_pending_tx;
+
 	u32 num_mem_chunks;
 	u32 rx_decap_mode;
 	struct ath10k_mem_chunk mem_chunks[WMI_MAX_MEM_REQS];
diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c
index 0d98c93a3aba..0baaad90b8d1 100644
--- a/drivers/net/wireless/ath/ath10k/debug.c
+++ b/drivers/net/wireless/ath/ath10k/debug.c
@@ -1727,7 +1727,9 @@ int ath10k_debug_start(struct ath10k *ar)
 			ath10k_warn(ar, "failed to disable pktlog: %d\n", ret);
 	}
 
-	if (ar->debug.nf_cal_period) {
+	if (ar->debug.nf_cal_period &&
+	    !test_bit(ATH10K_FW_FEATURE_NON_BMI,
+		      ar->normal_mode_fw.fw_file.fw_features)) {
 		ret = ath10k_wmi_pdev_set_param(ar,
 						ar->wmi.pdev_param->cal_period,
 						ar->debug.nf_cal_period);
@@ -1744,7 +1746,9 @@ void ath10k_debug_stop(struct ath10k *ar)
 {
 	lockdep_assert_held(&ar->conf_mutex);
 
-	ath10k_debug_cal_data_fetch(ar);
+	if (!test_bit(ATH10K_FW_FEATURE_NON_BMI,
+		      ar->normal_mode_fw.fw_file.fw_features))
+		ath10k_debug_cal_data_fetch(ar);
 
 	/* Must not use _sync to avoid deadlock, we do that in
 	 * ath10k_debug_destroy(). The check for htt_stats_mask is to avoid
@@ -2293,6 +2297,52 @@ static const struct file_operations fops_tpc_stats_final = {
 	.llseek = default_llseek,
 };
 
+static ssize_t ath10k_write_warm_hw_reset(struct file *file,
+					  const char __user *user_buf,
+					  size_t count, loff_t *ppos)
+{
+	struct ath10k *ar = file->private_data;
+	int ret;
+	bool val;
+
+	if (kstrtobool_from_user(user_buf, count, &val))
+		return -EFAULT;
+
+	if (!val)
+		return -EINVAL;
+
+	mutex_lock(&ar->conf_mutex);
+
+	if (ar->state != ATH10K_STATE_ON) {
+		ret = -ENETDOWN;
+		goto exit;
+	}
+
+	if (!(test_bit(WMI_SERVICE_RESET_CHIP, ar->wmi.svc_map)))
+		ath10k_warn(ar, "wmi service for reset chip is not available\n");
+
+	ret = ath10k_wmi_pdev_set_param(ar, ar->wmi.pdev_param->pdev_reset,
+					WMI_RST_MODE_WARM_RESET);
+
+	if (ret) {
+		ath10k_warn(ar, "failed to enable warm hw reset: %d\n", ret);
+		goto exit;
+	}
+
+	ret = count;
+
+exit:
+	mutex_unlock(&ar->conf_mutex);
+	return ret;
+}
+
+static const struct file_operations fops_warm_hw_reset = {
+	.write = ath10k_write_warm_hw_reset,
+	.open = simple_open,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
 int ath10k_debug_create(struct ath10k *ar)
 {
 	ar->debug.cal_data = vzalloc(ATH10K_DEBUG_CAL_DATA_LEN);
@@ -2367,15 +2417,18 @@ int ath10k_debug_register(struct ath10k *ar)
 	debugfs_create_file("fw_dbglog", 0600, ar->debug.debugfs_phy, ar,
 			    &fops_fw_dbglog);
 
-	debugfs_create_file("cal_data", 0400, ar->debug.debugfs_phy, ar,
-			    &fops_cal_data);
+	if (!test_bit(ATH10K_FW_FEATURE_NON_BMI,
+		      ar->normal_mode_fw.fw_file.fw_features)) {
+		debugfs_create_file("cal_data", 0400, ar->debug.debugfs_phy, ar,
+				    &fops_cal_data);
+
+		debugfs_create_file("nf_cal_period", 0600, ar->debug.debugfs_phy, ar,
+				    &fops_nf_cal_period);
+	}
 
 	debugfs_create_file("ani_enable", 0600, ar->debug.debugfs_phy, ar,
 			    &fops_ani_enable);
 
-	debugfs_create_file("nf_cal_period", 0600, ar->debug.debugfs_phy, ar,
-			    &fops_nf_cal_period);
-
 	if (IS_ENABLED(CONFIG_ATH10K_DFS_CERTIFIED)) {
 		debugfs_create_file("dfs_simulate_radar", 0200, ar->debug.debugfs_phy,
 				    ar, &fops_simulate_radar);
@@ -2418,6 +2471,9 @@ int ath10k_debug_register(struct ath10k *ar)
 				    ar->debug.debugfs_phy, ar,
 				    &fops_tpc_stats_final);
 
+	debugfs_create_file("warm_hw_reset", 0600, ar->debug.debugfs_phy, ar,
+			    &fops_warm_hw_reset);
+
 	return 0;
 }
 
diff --git a/drivers/net/wireless/ath/ath10k/htc.c b/drivers/net/wireless/ath/ath10k/htc.c
index 8902720b4e49..331b8d558791 100644
--- a/drivers/net/wireless/ath/ath10k/htc.c
+++ b/drivers/net/wireless/ath/ath10k/htc.c
@@ -274,7 +274,7 @@ ath10k_htc_process_lookahead_bundle(struct ath10k_htc *htc,
 	struct ath10k *ar = htc->ar;
 	int bundle_cnt = len / sizeof(*report);
 
-	if (!bundle_cnt || (bundle_cnt > HTC_HOST_MAX_MSG_PER_BUNDLE)) {
+	if (!bundle_cnt || (bundle_cnt > HTC_HOST_MAX_MSG_PER_RX_BUNDLE)) {
 		ath10k_warn(ar, "Invalid lookahead bundle count: %d\n",
 			    bundle_cnt);
 		return -EINVAL;
@@ -655,7 +655,7 @@ int ath10k_htc_wait_target(struct ath10k_htc *htc)
 	    sizeof(msg->hdr) + sizeof(msg->ready_ext)) {
 		htc->max_msgs_per_htc_bundle =
 			min_t(u8, msg->ready_ext.max_msgs_per_htc_bundle,
-			      HTC_HOST_MAX_MSG_PER_BUNDLE);
+			      HTC_HOST_MAX_MSG_PER_RX_BUNDLE);
 		ath10k_dbg(ar, ATH10K_DBG_HTC,
 			   "Extended ready message. RX bundle size: %d\n",
 			   htc->max_msgs_per_htc_bundle);
diff --git a/drivers/net/wireless/ath/ath10k/htc.h b/drivers/net/wireless/ath/ath10k/htc.h
index 34877597dd6a..51fda6c23f69 100644
--- a/drivers/net/wireless/ath/ath10k/htc.h
+++ b/drivers/net/wireless/ath/ath10k/htc.h
@@ -50,7 +50,8 @@ struct ath10k;
  * 4-byte aligned.
  */
 
-#define HTC_HOST_MAX_MSG_PER_BUNDLE        8
+#define HTC_HOST_MAX_MSG_PER_RX_BUNDLE        8
+#define HTC_HOST_MAX_MSG_PER_TX_BUNDLE        16
 
 enum ath10k_htc_tx_flags {
 	ATH10K_HTC_FLAG_NEED_CREDIT_UPDATE = 0x01,
@@ -58,6 +59,7 @@ enum ath10k_htc_tx_flags {
 };
 
 enum ath10k_htc_rx_flags {
+	ATH10K_HTC_FLAGS_RECV_1MORE_BLOCK = 0x01,
 	ATH10K_HTC_FLAG_TRAILER_PRESENT = 0x02,
 	ATH10K_HTC_FLAG_BUNDLE_MASK     = 0xF0
 };
diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index c72d8af122a2..4d1cd90d6d27 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -268,11 +268,12 @@ int ath10k_htt_rx_ring_refill(struct ath10k *ar)
 	spin_lock_bh(&htt->rx_ring.lock);
 	ret = ath10k_htt_rx_ring_fill_n(htt, (htt->rx_ring.fill_level -
 					      htt->rx_ring.fill_cnt));
-	spin_unlock_bh(&htt->rx_ring.lock);
 
 	if (ret)
 		ath10k_htt_rx_ring_free(htt);
 
+	spin_unlock_bh(&htt->rx_ring.lock);
+
 	return ret;
 }
 
@@ -284,7 +285,9 @@ void ath10k_htt_rx_free(struct ath10k_htt *htt)
 	skb_queue_purge(&htt->rx_in_ord_compl_q);
 	skb_queue_purge(&htt->tx_fetch_ind_q);
 
+	spin_lock_bh(&htt->rx_ring.lock);
 	ath10k_htt_rx_ring_free(htt);
+	spin_unlock_bh(&htt->rx_ring.lock);
 
 	dma_free_coherent(htt->ar->dev,
 			  ath10k_htt_get_rx_ring_size(htt),
@@ -1089,7 +1092,7 @@ static void ath10k_htt_rx_h_queue_msdu(struct ath10k *ar,
 	status = IEEE80211_SKB_RXCB(skb);
 	*status = *rx_status;
 
-	__skb_queue_tail(&ar->htt.rx_msdus_q, skb);
+	skb_queue_tail(&ar->htt.rx_msdus_q, skb);
 }
 
 static void ath10k_process_rx(struct ath10k *ar, struct sk_buff *skb)
@@ -2810,7 +2813,7 @@ bool ath10k_htt_t2h_msg_handler(struct ath10k *ar, struct sk_buff *skb)
 		break;
 	}
 	case HTT_T2H_MSG_TYPE_RX_IN_ORD_PADDR_IND: {
-		__skb_queue_tail(&htt->rx_in_ord_compl_q, skb);
+		skb_queue_tail(&htt->rx_in_ord_compl_q, skb);
 		return false;
 	}
 	case HTT_T2H_MSG_TYPE_TX_CREDIT_UPDATE_IND:
@@ -2874,7 +2877,7 @@ static int ath10k_htt_rx_deliver_msdu(struct ath10k *ar, int quota, int budget)
 		if (skb_queue_empty(&ar->htt.rx_msdus_q))
 			break;
 
-		skb = __skb_dequeue(&ar->htt.rx_msdus_q);
+		skb = skb_dequeue(&ar->htt.rx_msdus_q);
 		if (!skb)
 			break;
 		ath10k_process_rx(ar, skb);
@@ -2905,7 +2908,7 @@ int ath10k_htt_txrx_compl_task(struct ath10k *ar, int budget)
 		goto exit;
 	}
 
-	while ((skb = __skb_dequeue(&htt->rx_in_ord_compl_q))) {
+	while ((skb = skb_dequeue(&htt->rx_in_ord_compl_q))) {
 		spin_lock_bh(&htt->rx_ring.lock);
 		ret = ath10k_htt_rx_in_ord_ind(ar, skb);
 		spin_unlock_bh(&htt->rx_ring.lock);
diff --git a/drivers/net/wireless/ath/ath10k/htt_tx.c b/drivers/net/wireless/ath/ath10k/htt_tx.c
index 5d8b97a0ccaa..7cff0d52338f 100644
--- a/drivers/net/wireless/ath/ath10k/htt_tx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_tx.c
@@ -208,10 +208,10 @@ int ath10k_htt_tx_alloc_msdu_id(struct ath10k_htt *htt, struct sk_buff *skb)
 	struct ath10k *ar = htt->ar;
 	int ret;
 
-	lockdep_assert_held(&htt->tx_lock);
-
+	spin_lock_bh(&htt->tx_lock);
 	ret = idr_alloc(&htt->pending_tx, skb, 0,
 			htt->max_num_pending_tx, GFP_ATOMIC);
+	spin_unlock_bh(&htt->tx_lock);
 
 	ath10k_dbg(ar, ATH10K_DBG_HTT, "htt tx alloc msdu_id %d\n", ret);
 
@@ -1056,7 +1056,7 @@ static u8 ath10k_htt_tx_get_tid(struct sk_buff *skb, bool is_eth)
 	if (!is_eth && ieee80211_is_mgmt(hdr->frame_control))
 		return HTT_DATA_TX_EXT_TID_MGMT;
 	else if (cb->flags & ATH10K_SKB_F_QOS)
-		return skb->priority % IEEE80211_QOS_CTL_TID_MASK;
+		return skb->priority & IEEE80211_QOS_CTL_TID_MASK;
 	else
 		return HTT_DATA_TX_EXT_TID_NON_QOS_MCAST_BCAST;
 }
@@ -1077,9 +1077,7 @@ int ath10k_htt_mgmt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
 	len += sizeof(cmd->hdr);
 	len += sizeof(cmd->mgmt_tx);
 
-	spin_lock_bh(&htt->tx_lock);
 	res = ath10k_htt_tx_alloc_msdu_id(htt, msdu);
-	spin_unlock_bh(&htt->tx_lock);
 	if (res < 0)
 		goto err;
 
@@ -1161,9 +1159,7 @@ static int ath10k_htt_tx_32(struct ath10k_htt *htt,
 	struct htt_msdu_ext_desc *ext_desc = NULL;
 	struct htt_msdu_ext_desc *ext_desc_t = NULL;
 
-	spin_lock_bh(&htt->tx_lock);
 	res = ath10k_htt_tx_alloc_msdu_id(htt, msdu);
-	spin_unlock_bh(&htt->tx_lock);
 	if (res < 0)
 		goto err;
 
@@ -1202,7 +1198,7 @@ static int ath10k_htt_tx_32(struct ath10k_htt *htt,
 	case ATH10K_HW_TXRX_RAW:
 	case ATH10K_HW_TXRX_NATIVE_WIFI:
 		flags0 |= HTT_DATA_TX_DESC_FLAGS0_MAC_HDR_PRESENT;
-		/* pass through */
+		/* fall through */
 	case ATH10K_HW_TXRX_ETHERNET:
 		if (ar->hw_params.continuous_frag_desc) {
 			ext_desc_t = htt->frag_desc.vaddr_desc_32;
@@ -1363,9 +1359,7 @@ static int ath10k_htt_tx_64(struct ath10k_htt *htt,
 	struct htt_msdu_ext_desc_64 *ext_desc = NULL;
 	struct htt_msdu_ext_desc_64 *ext_desc_t = NULL;
 
-	spin_lock_bh(&htt->tx_lock);
 	res = ath10k_htt_tx_alloc_msdu_id(htt, msdu);
-	spin_unlock_bh(&htt->tx_lock);
 	if (res < 0)
 		goto err;
 
@@ -1404,7 +1398,7 @@ static int ath10k_htt_tx_64(struct ath10k_htt *htt,
 	case ATH10K_HW_TXRX_RAW:
 	case ATH10K_HW_TXRX_NATIVE_WIFI:
 		flags0 |= HTT_DATA_TX_DESC_FLAGS0_MAC_HDR_PRESENT;
-		/* pass through */
+		/* fall through */
 	case ATH10K_HW_TXRX_ETHERNET:
 		if (ar->hw_params.continuous_frag_desc) {
 			ext_desc_t = htt->frag_desc.vaddr_desc_64;
diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h
index 23467e9fefeb..977f79ebb4fd 100644
--- a/drivers/net/wireless/ath/ath10k/hw.h
+++ b/drivers/net/wireless/ath/ath10k/hw.h
@@ -586,6 +586,9 @@ struct ath10k_hw_params {
 
 	/* target supporting retention restore on ddr */
 	bool rri_on_ddr;
+
+	/* Number of bytes to be the offset for each FFT sample */
+	int spectral_bin_offset;
 };
 
 struct htt_rx_desc;
@@ -696,6 +699,7 @@ ath10k_rx_desc_get_l3_pad_bytes(struct ath10k_hw_params *hw,
 #define TARGET_TLV_NUM_TIDS			((TARGET_TLV_NUM_PEERS) * 2)
 #define TARGET_TLV_NUM_MSDU_DESC		(1024 + 32)
 #define TARGET_TLV_NUM_WOW_PATTERNS		22
+#define TARGET_TLV_MGMT_NUM_MSDU_DESC		(50)
 
 /* Target specific defines for WMI-HL-1.0 firmware */
 #define TARGET_HL_10_TLV_NUM_PEERS		14
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 836e0a47b94a..90f9372dec25 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -101,6 +101,8 @@ static struct ieee80211_rate ath10k_rates_rev2[] = {
 #define ath10k_g_rates_rev2 (ath10k_rates_rev2 + 0)
 #define ath10k_g_rates_rev2_size (ARRAY_SIZE(ath10k_rates_rev2))
 
+#define ath10k_wmi_legacy_rates ath10k_rates
+
 static bool ath10k_mac_bitrate_is_cck(int bitrate)
 {
 	switch (bitrate) {
@@ -3085,6 +3087,13 @@ static int ath10k_update_channel_list(struct ath10k *ar)
 			passive = channel->flags & IEEE80211_CHAN_NO_IR;
 			ch->passive = passive;
 
+			/* the firmware is ignoring the "radar" flag of the
+			 * channel and is scanning actively using Probe Requests
+			 * on "Radar detection"/DFS channels which are not
+			 * marked as "available"
+			 */
+			ch->passive |= ch->chan_radar;
+
 			ch->freq = channel->center_freq;
 			ch->band_center_freq1 = channel->center_freq;
 			ch->min_power = 0;
@@ -4026,7 +4035,7 @@ void ath10k_mac_tx_push_pending(struct ath10k *ar)
 				   drv_priv);
 
 		/* Prevent aggressive sta/tid taking over tx queue */
-		max = 16;
+		max = HTC_HOST_MAX_MSG_PER_TX_BUNDLE;
 		ret = 0;
 		while (ath10k_mac_tx_can_push(hw, txq) && max--) {
 			ret = ath10k_mac_tx_push_txq(hw, txq);
@@ -4047,6 +4056,7 @@ void ath10k_mac_tx_push_pending(struct ath10k *ar)
 	rcu_read_unlock();
 	spin_unlock_bh(&ar->txqs_lock);
 }
+EXPORT_SYMBOL(ath10k_mac_tx_push_pending);
 
 /************/
 /* Scanning */
@@ -4287,7 +4297,7 @@ static void ath10k_mac_op_wake_tx_queue(struct ieee80211_hw *hw,
 	struct ieee80211_txq *f_txq;
 	struct ath10k_txq *f_artxq;
 	int ret = 0;
-	int max = 16;
+	int max = HTC_HOST_MAX_MSG_PER_TX_BUNDLE;
 
 	spin_lock_bh(&ar->txqs_lock);
 	if (list_empty(&artxq->list))
@@ -5438,8 +5448,12 @@ static void ath10k_bss_info_changed(struct ieee80211_hw *hw,
 {
 	struct ath10k *ar = hw->priv;
 	struct ath10k_vif *arvif = (void *)vif->drv_priv;
-	int ret = 0;
+	struct cfg80211_chan_def def;
 	u32 vdev_param, pdev_param, slottime, preamble;
+	u16 bitrate, hw_value;
+	u8 rate;
+	int rateidx, ret = 0;
+	enum nl80211_band band;
 
 	mutex_lock(&ar->conf_mutex);
 
@@ -5607,6 +5621,44 @@ static void ath10k_bss_info_changed(struct ieee80211_hw *hw,
 				    arvif->vdev_id, ret);
 	}
 
+	if (changed & BSS_CHANGED_MCAST_RATE &&
+	    !WARN_ON(ath10k_mac_vif_chan(arvif->vif, &def))) {
+		band = def.chan->band;
+		rateidx = vif->bss_conf.mcast_rate[band] - 1;
+
+		if (ar->phy_capability & WHAL_WLAN_11A_CAPABILITY)
+			rateidx += ATH10K_MAC_FIRST_OFDM_RATE_IDX;
+
+		bitrate = ath10k_wmi_legacy_rates[rateidx].bitrate;
+		hw_value = ath10k_wmi_legacy_rates[rateidx].hw_value;
+		if (ath10k_mac_bitrate_is_cck(bitrate))
+			preamble = WMI_RATE_PREAMBLE_CCK;
+		else
+			preamble = WMI_RATE_PREAMBLE_OFDM;
+
+		rate = ATH10K_HW_RATECODE(hw_value, 0, preamble);
+
+		ath10k_dbg(ar, ATH10K_DBG_MAC,
+			   "mac vdev %d mcast_rate %x\n",
+			   arvif->vdev_id, rate);
+
+		vdev_param = ar->wmi.vdev_param->mcast_data_rate;
+		ret = ath10k_wmi_vdev_set_param(ar, arvif->vdev_id,
+						vdev_param, rate);
+		if (ret)
+			ath10k_warn(ar,
+				    "failed to set mcast rate on vdev %i: %d\n",
+				    arvif->vdev_id,  ret);
+
+		vdev_param = ar->wmi.vdev_param->bcast_data_rate;
+		ret = ath10k_wmi_vdev_set_param(ar, arvif->vdev_id,
+						vdev_param, rate);
+		if (ret)
+			ath10k_warn(ar,
+				    "failed to set bcast rate on vdev %i: %d\n",
+				    arvif->vdev_id,  ret);
+	}
+
 	mutex_unlock(&ar->conf_mutex);
 }
 
@@ -6062,13 +6114,13 @@ static void ath10k_sta_rc_update_wk(struct work_struct *wk)
 
 		mode = chan_to_phymode(&def);
 		ath10k_dbg(ar, ATH10K_DBG_MAC, "mac update sta %pM peer bw %d phymode %d\n",
-				sta->addr, bw, mode);
+			   sta->addr, bw, mode);
 
 		err = ath10k_wmi_peer_set_param(ar, arvif->vdev_id, sta->addr,
-				WMI_PEER_PHYMODE, mode);
+						WMI_PEER_PHYMODE, mode);
 		if (err) {
 			ath10k_warn(ar, "failed to update STA %pM peer phymode %d: %d\n",
-					sta->addr, mode, err);
+				    sta->addr, mode, err);
 			goto exit;
 		}
 
@@ -6934,7 +6986,6 @@ ath10k_mac_bitrate_mask_get_single_rate(struct ath10k *ar,
 					const struct cfg80211_bitrate_mask *mask,
 					u8 *rate, u8 *nss)
 {
-	struct ieee80211_supported_band *sband = &ar->mac.sbands[band];
 	int rate_idx;
 	int i;
 	u16 bitrate;
@@ -6944,8 +6995,11 @@ ath10k_mac_bitrate_mask_get_single_rate(struct ath10k *ar,
 	if (hweight32(mask->control[band].legacy) == 1) {
 		rate_idx = ffs(mask->control[band].legacy) - 1;
 
-		hw_rate = sband->bitrates[rate_idx].hw_value;
-		bitrate = sband->bitrates[rate_idx].bitrate;
+		if (ar->phy_capability & WHAL_WLAN_11A_CAPABILITY)
+			rate_idx += ATH10K_MAC_FIRST_OFDM_RATE_IDX;
+
+		hw_rate = ath10k_wmi_legacy_rates[rate_idx].hw_value;
+		bitrate = ath10k_wmi_legacy_rates[rate_idx].bitrate;
 
 		if (ath10k_mac_bitrate_is_cck(bitrate))
 			preamble = WMI_RATE_PREAMBLE_CCK;
@@ -7737,7 +7791,7 @@ static void ath10k_sta_statistics(struct ieee80211_hw *hw,
 		return;
 
 	sinfo->rx_duration = arsta->rx_duration;
-	sinfo->filled |= 1ULL << NL80211_STA_INFO_RX_DURATION;
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_DURATION);
 
 	if (!arsta->txrate.legacy && !arsta->txrate.nss)
 		return;
@@ -7750,7 +7804,7 @@ static void ath10k_sta_statistics(struct ieee80211_hw *hw,
 		sinfo->txrate.bw = arsta->txrate.bw;
 	}
 	sinfo->txrate.flags = arsta->txrate.flags;
-	sinfo->filled |= 1ULL << NL80211_STA_INFO_TX_BITRATE;
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 }
 
 static const struct ieee80211_ops ath10k_ops = {
@@ -7870,6 +7924,9 @@ static const struct ieee80211_channel ath10k_5ghz_channels[] = {
 	CHAN5G(161, 5805, 0),
 	CHAN5G(165, 5825, 0),
 	CHAN5G(169, 5845, 0),
+	CHAN5G(173, 5865, 0),
+	/* If you add more, you may need to change ATH10K_MAX_5G_CHAN */
+	/* And you will definitely need to change ATH10K_NUM_CHANS in core.h */
 };
 
 struct ath10k *ath10k_mac_create(size_t priv_size)
diff --git a/drivers/net/wireless/ath/ath10k/pci.h b/drivers/net/wireless/ath/ath10k/pci.h
index e52fd83156b6..0ed436657108 100644
--- a/drivers/net/wireless/ath/ath10k/pci.h
+++ b/drivers/net/wireless/ath/ath10k/pci.h
@@ -86,48 +86,6 @@ struct pcie_state {
 /* PCIE_CONFIG_FLAG definitions */
 #define PCIE_CONFIG_FLAG_ENABLE_L1  0x0000001
 
-/* Host software's Copy Engine configuration. */
-#define CE_ATTR_FLAGS 0
-
-/*
- * Configuration information for a Copy Engine pipe.
- * Passed from Host to Target during startup (one per CE).
- *
- * NOTE: Structure is shared between Host software and Target firmware!
- */
-struct ce_pipe_config {
-	__le32 pipenum;
-	__le32 pipedir;
-	__le32 nentries;
-	__le32 nbytes_max;
-	__le32 flags;
-	__le32 reserved;
-};
-
-/*
- * Directions for interconnect pipe configuration.
- * These definitions may be used during configuration and are shared
- * between Host and Target.
- *
- * Pipe Directions are relative to the Host, so PIPEDIR_IN means
- * "coming IN over air through Target to Host" as with a WiFi Rx operation.
- * Conversely, PIPEDIR_OUT means "going OUT from Host through Target over air"
- * as with a WiFi Tx operation. This is somewhat awkward for the "middle-man"
- * Target since things that are "PIPEDIR_OUT" are coming IN to the Target
- * over the interconnect.
- */
-#define PIPEDIR_NONE    0
-#define PIPEDIR_IN      1  /* Target-->Host, WiFi Rx direction */
-#define PIPEDIR_OUT     2  /* Host->Target, WiFi Tx direction */
-#define PIPEDIR_INOUT   3  /* bidirectional */
-
-/* Establish a mapping between a service/direction and a pipe. */
-struct service_to_pipe {
-	__le32 service_id;
-	__le32 pipedir;
-	__le32 pipenum;
-};
-
 /* Per-pipe state. */
 struct ath10k_pci_pipe {
 	/* Handle of underlying Copy Engine */
diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c
index d612ce8c9cff..7f61591ce0de 100644
--- a/drivers/net/wireless/ath/ath10k/sdio.c
+++ b/drivers/net/wireless/ath/ath10k/sdio.c
@@ -30,6 +30,7 @@
 #include "debug.h"
 #include "hif.h"
 #include "htc.h"
+#include "mac.h"
 #include "targaddrs.h"
 #include "trace.h"
 #include "sdio.h"
@@ -396,6 +397,7 @@ static int ath10k_sdio_mbox_rx_process_packet(struct ath10k *ar,
 	int ret;
 
 	payload_len = le16_to_cpu(htc_hdr->len);
+	skb->len = payload_len + sizeof(struct ath10k_htc_hdr);
 
 	if (trailer_present) {
 		trailer = skb->data + sizeof(*htc_hdr) +
@@ -434,12 +436,14 @@ static int ath10k_sdio_mbox_rx_process_packets(struct ath10k *ar,
 	enum ath10k_htc_ep_id id;
 	int ret, i, *n_lookahead_local;
 	u32 *lookaheads_local;
+	int lookahead_idx = 0;
 
 	for (i = 0; i < ar_sdio->n_rx_pkts; i++) {
 		lookaheads_local = lookaheads;
 		n_lookahead_local = n_lookahead;
 
-		id = ((struct ath10k_htc_hdr *)&lookaheads[i])->eid;
+		id = ((struct ath10k_htc_hdr *)
+		      &lookaheads[lookahead_idx++])->eid;
 
 		if (id >= ATH10K_HTC_EP_COUNT) {
 			ath10k_warn(ar, "invalid endpoint in look-ahead: %d\n",
@@ -462,6 +466,7 @@ static int ath10k_sdio_mbox_rx_process_packets(struct ath10k *ar,
 			/* Only read lookahead's from RX trailers
 			 * for the last packet in a bundle.
 			 */
+			lookahead_idx--;
 			lookaheads_local = NULL;
 			n_lookahead_local = NULL;
 		}
@@ -505,11 +510,11 @@ static int ath10k_sdio_mbox_alloc_pkt_bundle(struct ath10k *ar,
 
 	*bndl_cnt = FIELD_GET(ATH10K_HTC_FLAG_BUNDLE_MASK, htc_hdr->flags);
 
-	if (*bndl_cnt > HTC_HOST_MAX_MSG_PER_BUNDLE) {
+	if (*bndl_cnt > HTC_HOST_MAX_MSG_PER_RX_BUNDLE) {
 		ath10k_warn(ar,
 			    "HTC bundle length %u exceeds maximum %u\n",
 			    le16_to_cpu(htc_hdr->len),
-			    HTC_HOST_MAX_MSG_PER_BUNDLE);
+			    HTC_HOST_MAX_MSG_PER_RX_BUNDLE);
 		return -ENOMEM;
 	}
 
@@ -600,6 +605,9 @@ static int ath10k_sdio_mbox_rx_alloc(struct ath10k *ar,
 		 * ATH10K_HTC_FLAG_BUNDLE_MASK flag set, all bundled
 		 * packet skb's have been allocated in the previous step.
 		 */
+		if (htc_hdr->flags & ATH10K_HTC_FLAGS_RECV_1MORE_BLOCK)
+			full_len += ATH10K_HIF_MBOX_BLOCK_SIZE;
+
 		ret = ath10k_sdio_mbox_alloc_rx_pkt(&ar_sdio->rx_pkts[i],
 						    act_len,
 						    full_len,
@@ -1342,6 +1350,8 @@ static void ath10k_sdio_irq_handler(struct sdio_func *func)
 			break;
 	} while (time_before(jiffies, timeout) && !done);
 
+	ath10k_mac_tx_push_pending(ar);
+
 	sdio_claim_host(ar_sdio->func);
 
 	if (ret && ret != -ECANCELED)
diff --git a/drivers/net/wireless/ath/ath10k/sdio.h b/drivers/net/wireless/ath/ath10k/sdio.h
index 4ff7b545293b..453eb6263143 100644
--- a/drivers/net/wireless/ath/ath10k/sdio.h
+++ b/drivers/net/wireless/ath/ath10k/sdio.h
@@ -96,14 +96,14 @@
  * way:
  *
  * Let's assume that each packet in a bundle of the maximum bundle size
- * (HTC_HOST_MAX_MSG_PER_BUNDLE) has the HTC header bundle count set
- * to the maximum value (HTC_HOST_MAX_MSG_PER_BUNDLE).
+ * (HTC_HOST_MAX_MSG_PER_RX_BUNDLE) has the HTC header bundle count set
+ * to the maximum value (HTC_HOST_MAX_MSG_PER_RX_BUNDLE).
  *
  * in this case the driver must allocate
- * (HTC_HOST_MAX_MSG_PER_BUNDLE * HTC_HOST_MAX_MSG_PER_BUNDLE) skb's.
+ * (HTC_HOST_MAX_MSG_PER_RX_BUNDLE * HTC_HOST_MAX_MSG_PER_RX_BUNDLE) skb's.
  */
 #define ATH10K_SDIO_MAX_RX_MSGS \
-	(HTC_HOST_MAX_MSG_PER_BUNDLE * HTC_HOST_MAX_MSG_PER_BUNDLE)
+	(HTC_HOST_MAX_MSG_PER_RX_BUNDLE * HTC_HOST_MAX_MSG_PER_RX_BUNDLE)
 
 #define ATH10K_FIFO_TIMEOUT_AND_CHIP_CONTROL   0x00000868u
 #define ATH10K_FIFO_TIMEOUT_AND_CHIP_CONTROL_DISABLE_SLEEP_OFF 0xFFFEFFFF
diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index a3a7042fe13a..fa1843a7e0fd 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -14,19 +14,20 @@
  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
  */
 
-#include <linux/module.h>
+#include <linux/clk.h>
 #include <linux/kernel.h>
-#include "debug.h"
-#include "hif.h"
-#include "htc.h"
-#include "ce.h"
-#include "snoc.h"
+#include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
-#include <linux/clk.h>
-#define  WCN3990_CE_ATTR_FLAGS 0
+
+#include "ce.h"
+#include "debug.h"
+#include "hif.h"
+#include "htc.h"
+#include "snoc.h"
+
 #define ATH10K_SNOC_RX_POST_RETRY_MS 50
 #define CE_POLL_PIPE 4
 
@@ -449,7 +450,7 @@ static void ath10k_snoc_htt_rx_cb(struct ath10k_ce_pipe *ce_state)
 
 static void ath10k_snoc_rx_replenish_retry(struct timer_list *t)
 {
-	struct ath10k_pci *ar_snoc = from_timer(ar_snoc, t, rx_post_retry);
+	struct ath10k_snoc *ar_snoc = from_timer(ar_snoc, t, rx_post_retry);
 	struct ath10k *ar = ar_snoc->ar;
 
 	ath10k_snoc_rx_post(ar);
@@ -820,7 +821,7 @@ static const struct ath10k_bus_ops ath10k_snoc_bus_ops = {
 	.write32	= ath10k_snoc_write32,
 };
 
-int ath10k_snoc_get_ce_id_from_irq(struct ath10k *ar, int irq)
+static int ath10k_snoc_get_ce_id_from_irq(struct ath10k *ar, int irq)
 {
 	struct ath10k_snoc *ar_snoc = ath10k_snoc_priv(ar);
 	int i;
@@ -868,7 +869,7 @@ static int ath10k_snoc_napi_poll(struct napi_struct *ctx, int budget)
 	return done;
 }
 
-void ath10k_snoc_init_napi(struct ath10k *ar)
+static void ath10k_snoc_init_napi(struct ath10k *ar)
 {
 	netif_napi_add(&ar->napi_dev, &ar->napi, ath10k_snoc_napi_poll,
 		       ATH10K_NAPI_BUDGET);
@@ -1303,13 +1304,13 @@ static int ath10k_snoc_probe(struct platform_device *pdev)
 	ar_snoc->ce.bus_ops = &ath10k_snoc_bus_ops;
 	ar->ce_priv = &ar_snoc->ce;
 
-	ath10k_snoc_resource_init(ar);
+	ret = ath10k_snoc_resource_init(ar);
 	if (ret) {
 		ath10k_warn(ar, "failed to initialize resource: %d\n", ret);
 		goto err_core_destroy;
 	}
 
-	ath10k_snoc_setup_resource(ar);
+	ret = ath10k_snoc_setup_resource(ar);
 	if (ret) {
 		ath10k_warn(ar, "failed to setup resource: %d\n", ret);
 		goto err_core_destroy;
@@ -1388,25 +1389,7 @@ static struct platform_driver ath10k_snoc_driver = {
 			.of_match_table = ath10k_snoc_dt_match,
 		},
 };
-
-static int __init ath10k_snoc_init(void)
-{
-	int ret;
-
-	ret = platform_driver_register(&ath10k_snoc_driver);
-	if (ret)
-		pr_err("failed to register ath10k snoc driver: %d\n",
-		       ret);
-
-	return ret;
-}
-module_init(ath10k_snoc_init);
-
-static void __exit ath10k_snoc_exit(void)
-{
-	platform_driver_unregister(&ath10k_snoc_driver);
-}
-module_exit(ath10k_snoc_exit);
+module_platform_driver(ath10k_snoc_driver);
 
 MODULE_AUTHOR("Qualcomm");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/ath/ath10k/snoc.h b/drivers/net/wireless/ath/ath10k/snoc.h
index 05dc98f46ccd..f9e530189d48 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.h
+++ b/drivers/net/wireless/ath/ath10k/snoc.h
@@ -19,7 +19,6 @@
 
 #include "hw.h"
 #include "ce.h"
-#include "pci.h"
 
 struct ath10k_snoc_drv_priv {
 	enum ath10k_hw_rev hw_rev;
diff --git a/drivers/net/wireless/ath/ath10k/spectral.c b/drivers/net/wireless/ath/ath10k/spectral.c
index af6995de7e00..653b6d013207 100644
--- a/drivers/net/wireless/ath/ath10k/spectral.c
+++ b/drivers/net/wireless/ath/ath10k/spectral.c
@@ -145,7 +145,7 @@ int ath10k_spectral_process_fft(struct ath10k *ar,
 	fft_sample->noise = __cpu_to_be16(phyerr->nf_chains[chain_idx]);
 
 	bins = (u8 *)fftr;
-	bins += sizeof(*fftr);
+	bins += sizeof(*fftr) + ar->hw_params.spectral_bin_offset;
 
 	fft_sample->tsf = __cpu_to_be64(tsf);
 
diff --git a/drivers/net/wireless/ath/ath10k/wmi-ops.h b/drivers/net/wireless/ath/ath10k/wmi-ops.h
index 5ecce04005d2..7fd63bbf8e24 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-ops.h
+++ b/drivers/net/wireless/ath/ath10k/wmi-ops.h
@@ -31,6 +31,8 @@ struct wmi_ops {
 			 struct wmi_scan_ev_arg *arg);
 	int (*pull_mgmt_rx)(struct ath10k *ar, struct sk_buff *skb,
 			    struct wmi_mgmt_rx_ev_arg *arg);
+	int (*pull_mgmt_tx_compl)(struct ath10k *ar, struct sk_buff *skb,
+				  struct wmi_tlv_mgmt_tx_compl_ev_arg *arg);
 	int (*pull_ch_info)(struct ath10k *ar, struct sk_buff *skb,
 			    struct wmi_ch_info_ev_arg *arg);
 	int (*pull_vdev_start)(struct ath10k *ar, struct sk_buff *skb,
@@ -262,6 +264,16 @@ ath10k_wmi_pull_scan(struct ath10k *ar, struct sk_buff *skb,
 }
 
 static inline int
+ath10k_wmi_pull_mgmt_tx_compl(struct ath10k *ar, struct sk_buff *skb,
+			      struct wmi_tlv_mgmt_tx_compl_ev_arg *arg)
+{
+	if (!ar->wmi.ops->pull_mgmt_tx_compl)
+		return -EOPNOTSUPP;
+
+	return ar->wmi.ops->pull_mgmt_tx_compl(ar, skb, arg);
+}
+
+static inline int
 ath10k_wmi_pull_mgmt_rx(struct ath10k *ar, struct sk_buff *skb,
 			struct wmi_mgmt_rx_ev_arg *arg)
 {
diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
index 8c49a26fc571..cdc1e64d52ad 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c
+++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
@@ -618,6 +618,9 @@ static void ath10k_wmi_tlv_op_rx(struct ath10k *ar, struct sk_buff *skb)
 	case WMI_TLV_TDLS_PEER_EVENTID:
 		ath10k_wmi_event_tdls_peer(ar, skb);
 		break;
+	case WMI_TLV_MGMT_TX_COMPLETION_EVENTID:
+		ath10k_wmi_event_mgmt_tx_compl(ar, skb);
+		break;
 	default:
 		ath10k_warn(ar, "Unknown eventid: %d\n", id);
 		break;
@@ -659,6 +662,31 @@ static int ath10k_wmi_tlv_op_pull_scan_ev(struct ath10k *ar,
 	return 0;
 }
 
+static int
+ath10k_wmi_tlv_op_pull_mgmt_tx_compl_ev(struct ath10k *ar, struct sk_buff *skb,
+					struct wmi_tlv_mgmt_tx_compl_ev_arg *arg)
+{
+	const void **tb;
+	const struct wmi_tlv_mgmt_tx_compl_ev *ev;
+	int ret;
+
+	tb = ath10k_wmi_tlv_parse_alloc(ar, skb->data, skb->len, GFP_ATOMIC);
+	if (IS_ERR(tb)) {
+		ret = PTR_ERR(tb);
+		ath10k_warn(ar, "failed to parse tlv: %d\n", ret);
+		return ret;
+	}
+
+	ev = tb[WMI_TLV_TAG_STRUCT_MGMT_TX_COMPL_EVENT];
+
+	arg->desc_id = ev->desc_id;
+	arg->status = ev->status;
+	arg->pdev_id = ev->pdev_id;
+
+	kfree(tb);
+	return 0;
+}
+
 static int ath10k_wmi_tlv_op_pull_mgmt_rx_ev(struct ath10k *ar,
 					     struct sk_buff *skb,
 					     struct wmi_mgmt_rx_ev_arg *arg)
@@ -1076,6 +1104,8 @@ static int ath10k_wmi_tlv_op_pull_svc_rdy_ev(struct ath10k *ar,
 	arg->phy_capab = ev->phy_capability;
 	arg->num_rf_chains = ev->num_rf_chains;
 	arg->eeprom_rd = reg->eeprom_rd;
+	arg->low_5ghz_chan = reg->low_5ghz_chan;
+	arg->high_5ghz_chan = reg->high_5ghz_chan;
 	arg->num_mem_reqs = ev->num_mem_reqs;
 	arg->service_map = svc_bmap;
 	arg->service_map_len = ath10k_wmi_tlv_len(svc_bmap);
@@ -1584,6 +1614,11 @@ static struct sk_buff *ath10k_wmi_tlv_op_gen_init(struct ath10k *ar)
 	cfg->keep_alive_pattern_size = __cpu_to_le32(0);
 	cfg->max_tdls_concurrent_sleep_sta = __cpu_to_le32(1);
 	cfg->max_tdls_concurrent_buffer_sta = __cpu_to_le32(1);
+	cfg->wmi_send_separate = __cpu_to_le32(0);
+	cfg->num_ocb_vdevs = __cpu_to_le32(0);
+	cfg->num_ocb_channels = __cpu_to_le32(0);
+	cfg->num_ocb_schedules = __cpu_to_le32(0);
+	cfg->host_capab = __cpu_to_le32(0);
 
 	ath10k_wmi_put_host_mem_chunks(ar, chunks);
 
@@ -1614,10 +1649,10 @@ ath10k_wmi_tlv_op_gen_start_scan(struct ath10k *ar,
 	bssid_len = arg->n_bssids * sizeof(struct wmi_mac_addr);
 	ie_len = roundup(arg->ie_len, 4);
 	len = (sizeof(*tlv) + sizeof(*cmd)) +
-	      (arg->n_channels ? sizeof(*tlv) + chan_len : 0) +
-	      (arg->n_ssids ? sizeof(*tlv) + ssid_len : 0) +
-	      (arg->n_bssids ? sizeof(*tlv) + bssid_len : 0) +
-	      (arg->ie_len ? sizeof(*tlv) + ie_len : 0);
+	      sizeof(*tlv) + chan_len +
+	      sizeof(*tlv) + ssid_len +
+	      sizeof(*tlv) + bssid_len +
+	      sizeof(*tlv) + ie_len;
 
 	skb = ath10k_wmi_alloc_skb(ar, len);
 	if (!skb)
@@ -1785,7 +1820,6 @@ ath10k_wmi_tlv_op_gen_vdev_start(struct ath10k *ar,
 {
 	struct wmi_tlv_vdev_start_cmd *cmd;
 	struct wmi_channel *ch;
-	struct wmi_p2p_noa_descriptor *noa;
 	struct wmi_tlv *tlv;
 	struct sk_buff *skb;
 	size_t len;
@@ -1843,7 +1877,6 @@ ath10k_wmi_tlv_op_gen_vdev_start(struct ath10k *ar,
 	tlv = ptr;
 	tlv->tag = __cpu_to_le16(WMI_TLV_TAG_ARRAY_STRUCT);
 	tlv->len = 0;
-	noa = (void *)tlv->value;
 
 	/* Note: This is a nested TLV containing:
 	 * [wmi_tlv][wmi_p2p_noa_descriptor][wmi_tlv]..
@@ -2605,6 +2638,30 @@ ath10k_wmi_tlv_op_gen_request_stats(struct ath10k *ar, u32 stats_mask)
 	return skb;
 }
 
+static int
+ath10k_wmi_mgmt_tx_alloc_msdu_id(struct ath10k *ar, struct sk_buff *skb,
+				 dma_addr_t paddr)
+{
+	struct ath10k_wmi *wmi = &ar->wmi;
+	struct ath10k_mgmt_tx_pkt_addr *pkt_addr;
+	int ret;
+
+	pkt_addr = kmalloc(sizeof(*pkt_addr), GFP_ATOMIC);
+	if (!pkt_addr)
+		return -ENOMEM;
+
+	pkt_addr->vaddr = skb;
+	pkt_addr->paddr = paddr;
+
+	spin_lock_bh(&ar->data_lock);
+	ret = idr_alloc(&wmi->mgmt_pending_tx, pkt_addr, 0,
+			wmi->mgmt_max_num_pending_tx, GFP_ATOMIC);
+	spin_unlock_bh(&ar->data_lock);
+
+	ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi mgmt tx alloc msdu_id ret %d\n", ret);
+	return ret;
+}
+
 static struct sk_buff *
 ath10k_wmi_tlv_op_gen_mgmt_tx_send(struct ath10k *ar, struct sk_buff *msdu,
 				   dma_addr_t paddr)
@@ -2616,9 +2673,9 @@ ath10k_wmi_tlv_op_gen_mgmt_tx_send(struct ath10k *ar, struct sk_buff *msdu,
 	u32 buf_len = msdu->len;
 	struct wmi_tlv *tlv;
 	struct sk_buff *skb;
+	int len, desc_id;
 	u32 vdev_id;
 	void *ptr;
-	int len;
 
 	if (!cb->vif)
 		return ERR_PTR(-EINVAL);
@@ -2649,13 +2706,17 @@ ath10k_wmi_tlv_op_gen_mgmt_tx_send(struct ath10k *ar, struct sk_buff *msdu,
 	if (!skb)
 		return ERR_PTR(-ENOMEM);
 
+	desc_id = ath10k_wmi_mgmt_tx_alloc_msdu_id(ar, msdu, paddr);
+	if (desc_id < 0)
+		goto err_free_skb;
+
 	ptr = (void *)skb->data;
 	tlv = ptr;
 	tlv->tag = __cpu_to_le16(WMI_TLV_TAG_STRUCT_MGMT_TX_CMD);
 	tlv->len = __cpu_to_le16(sizeof(*cmd));
 	cmd = (void *)tlv->value;
 	cmd->vdev_id = __cpu_to_le32(vdev_id);
-	cmd->desc_id = 0;
+	cmd->desc_id = __cpu_to_le32(desc_id);
 	cmd->chanfreq = 0;
 	cmd->buf_len = __cpu_to_le32(buf_len);
 	cmd->frame_len = __cpu_to_le32(msdu->len);
@@ -2672,6 +2733,10 @@ ath10k_wmi_tlv_op_gen_mgmt_tx_send(struct ath10k *ar, struct sk_buff *msdu,
 	memcpy(ptr, msdu->data, buf_len);
 
 	return skb;
+
+err_free_skb:
+	dev_kfree_skb(skb);
+	return ERR_PTR(desc_id);
 }
 
 static struct sk_buff *
@@ -2700,7 +2765,8 @@ ath10k_wmi_tlv_op_gen_force_fw_hang(struct ath10k *ar,
 
 static struct sk_buff *
 ath10k_wmi_tlv_op_gen_dbglog_cfg(struct ath10k *ar, u64 module_enable,
-				 u32 log_level) {
+				 u32 log_level)
+{
 	struct wmi_tlv_dbglog_cmd *cmd;
 	struct wmi_tlv *tlv;
 	struct sk_buff *skb;
@@ -3835,6 +3901,7 @@ static const struct wmi_ops wmi_tlv_ops = {
 
 	.pull_scan = ath10k_wmi_tlv_op_pull_scan_ev,
 	.pull_mgmt_rx = ath10k_wmi_tlv_op_pull_mgmt_rx_ev,
+	.pull_mgmt_tx_compl = ath10k_wmi_tlv_op_pull_mgmt_tx_compl_ev,
 	.pull_ch_info = ath10k_wmi_tlv_op_pull_ch_info_ev,
 	.pull_vdev_start = ath10k_wmi_tlv_op_pull_vdev_start_ev,
 	.pull_peer_kick = ath10k_wmi_tlv_op_pull_peer_kick_ev,
diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.h b/drivers/net/wireless/ath/ath10k/wmi-tlv.h
index 3e1e340cd834..4f0c20c90642 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-tlv.h
+++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.h
@@ -320,6 +320,7 @@ enum wmi_tlv_event_id {
 	WMI_TLV_TBTTOFFSET_UPDATE_EVENTID,
 	WMI_TLV_OFFLOAD_BCN_TX_STATUS_EVENTID,
 	WMI_TLV_OFFLOAD_PROB_RESP_TX_STATUS_EVENTID,
+	WMI_TLV_MGMT_TX_COMPLETION_EVENTID,
 	WMI_TLV_TX_DELBA_COMPLETE_EVENTID = WMI_TLV_EV(WMI_TLV_GRP_BA_NEG),
 	WMI_TLV_TX_ADDBA_COMPLETE_EVENTID,
 	WMI_TLV_BA_RSP_SSN_EVENTID,
@@ -1573,6 +1574,17 @@ struct wmi_tlv {
 	u8 value[0];
 } __packed;
 
+struct ath10k_mgmt_tx_pkt_addr {
+	void *vaddr;
+	dma_addr_t paddr;
+};
+
+struct wmi_tlv_mgmt_tx_compl_ev {
+	__le32 desc_id;
+	__le32 status;
+	__le32 pdev_id;
+};
+
 #define WMI_TLV_MGMT_RX_NUM_RSSI 4
 
 struct wmi_tlv_mgmt_rx_ev {
@@ -1670,6 +1682,11 @@ struct wmi_tlv_resource_config {
 	__le32 keep_alive_pattern_size;
 	__le32 max_tdls_concurrent_sleep_sta;
 	__le32 max_tdls_concurrent_buffer_sta;
+	__le32 wmi_send_separate;
+	__le32 num_ocb_vdevs;
+	__le32 num_ocb_channels;
+	__le32 num_ocb_schedules;
+	__le32 host_capab;
 } __packed;
 
 struct wmi_tlv_init_cmd {
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index f97ab795cf2e..fd612d2905b0 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -1333,7 +1333,7 @@ static struct wmi_pdev_param_map wmi_10_2_4_pdev_param_map = {
 	.enable_per_tid_ampdu = WMI_PDEV_PARAM_UNSUPPORTED,
 	.cca_threshold = WMI_PDEV_PARAM_UNSUPPORTED,
 	.rts_fixed_rate = WMI_PDEV_PARAM_UNSUPPORTED,
-	.pdev_reset = WMI_PDEV_PARAM_UNSUPPORTED,
+	.pdev_reset = WMI_10X_PDEV_PARAM_PDEV_RESET,
 	.wapi_mbssid_offset = WMI_PDEV_PARAM_UNSUPPORTED,
 	.arp_srcaddr = WMI_PDEV_PARAM_UNSUPPORTED,
 	.arp_dstaddr = WMI_PDEV_PARAM_UNSUPPORTED,
@@ -2313,6 +2313,59 @@ static bool ath10k_wmi_rx_is_decrypted(struct ath10k *ar,
 	return true;
 }
 
+static int wmi_process_mgmt_tx_comp(struct ath10k *ar, u32 desc_id,
+				    u32 status)
+{
+	struct ath10k_mgmt_tx_pkt_addr *pkt_addr;
+	struct ath10k_wmi *wmi = &ar->wmi;
+	struct ieee80211_tx_info *info;
+	struct sk_buff *msdu;
+	int ret;
+
+	spin_lock_bh(&ar->data_lock);
+
+	pkt_addr = idr_find(&wmi->mgmt_pending_tx, desc_id);
+	if (!pkt_addr) {
+		ath10k_warn(ar, "received mgmt tx completion for invalid msdu_id: %d\n",
+			    desc_id);
+		ret = -ENOENT;
+		goto out;
+	}
+
+	msdu = pkt_addr->vaddr;
+	dma_unmap_single(ar->dev, pkt_addr->paddr,
+			 msdu->len, DMA_FROM_DEVICE);
+	info = IEEE80211_SKB_CB(msdu);
+	info->flags |= status;
+	ieee80211_tx_status_irqsafe(ar->hw, msdu);
+
+	ret = 0;
+
+out:
+	idr_remove(&wmi->mgmt_pending_tx, desc_id);
+	spin_unlock_bh(&ar->data_lock);
+	return ret;
+}
+
+int ath10k_wmi_event_mgmt_tx_compl(struct ath10k *ar, struct sk_buff *skb)
+{
+	struct wmi_tlv_mgmt_tx_compl_ev_arg arg;
+	int ret;
+
+	ret = ath10k_wmi_pull_mgmt_tx_compl(ar, skb, &arg);
+	if (ret) {
+		ath10k_warn(ar, "failed to parse mgmt comp event: %d\n", ret);
+		return ret;
+	}
+
+	wmi_process_mgmt_tx_comp(ar, __le32_to_cpu(arg.desc_id),
+				 __le32_to_cpu(arg.status));
+
+	ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi tlv evnt mgmt tx completion\n");
+
+	return 0;
+}
+
 int ath10k_wmi_event_mgmt_rx(struct ath10k *ar, struct sk_buff *skb)
 {
 	struct wmi_mgmt_rx_ev_arg arg = {};
@@ -2366,7 +2419,7 @@ int ath10k_wmi_event_mgmt_rx(struct ath10k *ar, struct sk_buff *skb)
 	 */
 	if (channel >= 1 && channel <= 14) {
 		status->band = NL80211_BAND_2GHZ;
-	} else if (channel >= 36 && channel <= 169) {
+	} else if (channel >= 36 && channel <= ATH10K_MAX_5G_CHAN) {
 		status->band = NL80211_BAND_5GHZ;
 	} else {
 		/* Shouldn't happen unless list of advertised channels to
@@ -4602,10 +4655,6 @@ void ath10k_wmi_event_pdev_tpc_config(struct ath10k *ar, struct sk_buff *skb)
 
 	ev = (struct wmi_pdev_tpc_config_event *)skb->data;
 
-	tpc_stats = kzalloc(sizeof(*tpc_stats), GFP_ATOMIC);
-	if (!tpc_stats)
-		return;
-
 	num_tx_chain = __le32_to_cpu(ev->num_tx_chain);
 
 	if (num_tx_chain > WMI_TPC_TX_N_CHAIN) {
@@ -4614,6 +4663,10 @@ void ath10k_wmi_event_pdev_tpc_config(struct ath10k *ar, struct sk_buff *skb)
 		return;
 	}
 
+	tpc_stats = kzalloc(sizeof(*tpc_stats), GFP_ATOMIC);
+	if (!tpc_stats)
+		return;
+
 	ath10k_wmi_tpc_config_get_rate_code(rate_code, pream_table,
 					    num_tx_chain);
 
@@ -5018,13 +5071,11 @@ static int ath10k_wmi_alloc_chunk(struct ath10k *ar, u32 req_id,
 	void *vaddr;
 
 	pool_size = num_units * round_up(unit_len, 4);
-	vaddr = dma_alloc_coherent(ar->dev, pool_size, &paddr, GFP_KERNEL);
+	vaddr = dma_zalloc_coherent(ar->dev, pool_size, &paddr, GFP_KERNEL);
 
 	if (!vaddr)
 		return -ENOMEM;
 
-	memset(vaddr, 0, pool_size);
-
 	ar->wmi.mem_chunks[idx].vaddr = vaddr;
 	ar->wmi.mem_chunks[idx].paddr = paddr;
 	ar->wmi.mem_chunks[idx].len = pool_size;
@@ -9075,6 +9126,11 @@ int ath10k_wmi_attach(struct ath10k *ar)
 	INIT_WORK(&ar->radar_confirmation_work,
 		  ath10k_radar_confirmation_work);
 
+	if (test_bit(ATH10K_FW_FEATURE_MGMT_TX_BY_REF,
+		     ar->running_fw->fw_file.fw_features)) {
+		idr_init(&ar->wmi.mgmt_pending_tx);
+	}
+
 	return 0;
 }
 
@@ -9093,8 +9149,35 @@ void ath10k_wmi_free_host_mem(struct ath10k *ar)
 	ar->wmi.num_mem_chunks = 0;
 }
 
+static int ath10k_wmi_mgmt_tx_clean_up_pending(int msdu_id, void *ptr,
+					       void *ctx)
+{
+	struct ath10k_mgmt_tx_pkt_addr *pkt_addr = ptr;
+	struct ath10k *ar = ctx;
+	struct sk_buff *msdu;
+
+	ath10k_dbg(ar, ATH10K_DBG_WMI,
+		   "force cleanup mgmt msdu_id %hu\n", msdu_id);
+
+	msdu = pkt_addr->vaddr;
+	dma_unmap_single(ar->dev, pkt_addr->paddr,
+			 msdu->len, DMA_FROM_DEVICE);
+	ieee80211_free_txskb(ar->hw, msdu);
+
+	return 0;
+}
+
 void ath10k_wmi_detach(struct ath10k *ar)
 {
+	if (test_bit(ATH10K_FW_FEATURE_MGMT_TX_BY_REF,
+		     ar->running_fw->fw_file.fw_features)) {
+		spin_lock_bh(&ar->data_lock);
+		idr_for_each(&ar->wmi.mgmt_pending_tx,
+			     ath10k_wmi_mgmt_tx_clean_up_pending, ar);
+		idr_destroy(&ar->wmi.mgmt_pending_tx);
+		spin_unlock_bh(&ar->data_lock);
+	}
+
 	cancel_work_sync(&ar->svc_rdy_work);
 
 	if (ar->svc_rdy_skb)
diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h
index d68afb65402a..36220258e3c7 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.h
+++ b/drivers/net/wireless/ath/ath10k/wmi.h
@@ -462,6 +462,7 @@ static inline char *wmi_service_name(int service_id)
 	SVCSTR(WMI_SERVICE_HTT_MGMT_TX_COMP_VALID_FLAGS);
 	SVCSTR(WMI_SERVICE_HOST_DFS_CHECK_SUPPORT);
 	SVCSTR(WMI_SERVICE_TPC_STATS_FINAL);
+	SVCSTR(WMI_SERVICE_RESET_CHIP);
 	default:
 		return NULL;
 	}
@@ -3934,7 +3935,11 @@ enum wmi_10x_pdev_param {
 	WMI_10X_PDEV_PARAM_REMOVE_MCAST2UCAST_BUFFER,
 	WMI_10X_PDEV_PARAM_PEER_STA_PS_STATECHG_ENABLE,
 	WMI_10X_PDEV_PARAM_RTS_FIXED_RATE,
-	WMI_10X_PDEV_PARAM_CAL_PERIOD
+	WMI_10X_PDEV_PARAM_CAL_PERIOD,
+	WMI_10X_PDEV_PARAM_ATF_STRICT_SCH,
+	WMI_10X_PDEV_PARAM_ATF_SCHED_DURATION,
+	WMI_10X_PDEV_PARAM_SET_PROMISC_MODE_CMDID,
+	WMI_10X_PDEV_PARAM_PDEV_RESET
 };
 
 enum wmi_10_4_pdev_param {
@@ -6501,6 +6506,15 @@ struct wmi_force_fw_hang_cmd {
 	__le32 delay_ms;
 } __packed;
 
+enum wmi_pdev_reset_mode_type {
+	WMI_RST_MODE_TX_FLUSH = 1,
+	WMI_RST_MODE_WARM_RESET,
+	WMI_RST_MODE_COLD_RESET,
+	WMI_RST_MODE_WARM_RESET_RESTORE_CAL,
+	WMI_RST_MODE_COLD_RESET_RESTORE_CAL,
+	WMI_RST_MODE_MAX,
+};
+
 enum ath10k_dbglog_level {
 	ATH10K_DBGLOG_LEVEL_VERBOSE = 0,
 	ATH10K_DBGLOG_LEVEL_INFO = 1,
@@ -6600,6 +6614,12 @@ struct wmi_scan_ev_arg {
 	__le32 vdev_id;
 };
 
+struct wmi_tlv_mgmt_tx_compl_ev_arg {
+	__le32 desc_id;
+	__le32 status;
+	__le32 pdev_id;
+};
+
 struct wmi_mgmt_rx_ev_arg {
 	__le32 channel;
 	__le32 snr;
@@ -7071,6 +7091,7 @@ int ath10k_wmi_start_scan_verify(const struct wmi_start_scan_arg *arg);
 
 int ath10k_wmi_event_scan(struct ath10k *ar, struct sk_buff *skb);
 int ath10k_wmi_event_mgmt_rx(struct ath10k *ar, struct sk_buff *skb);
+int ath10k_wmi_event_mgmt_tx_compl(struct ath10k *ar, struct sk_buff *skb);
 void ath10k_wmi_event_chan_info(struct ath10k *ar, struct sk_buff *skb);
 void ath10k_wmi_event_echo(struct ath10k *ar, struct sk_buff *skb);
 int ath10k_wmi_event_debug_mesg(struct ath10k *ar, struct sk_buff *skb);
diff --git a/drivers/net/wireless/ath/ath5k/pcu.c b/drivers/net/wireless/ath/ath5k/pcu.c
index f23c851765df..05140d8baa36 100644
--- a/drivers/net/wireless/ath/ath5k/pcu.c
+++ b/drivers/net/wireless/ath/ath5k/pcu.c
@@ -670,6 +670,7 @@ ath5k_hw_init_beacon_timers(struct ath5k_hw *ah, u32 next_beacon, u32 interval)
 		break;
 	case NL80211_IFTYPE_ADHOC:
 		AR5K_REG_ENABLE_BITS(ah, AR5K_TXCFG, AR5K_TXCFG_ADHOC_BCN_ATIM);
+		/* fall through */
 	default:
 		/* On non-STA modes timer1 is used as next DMA
 		 * beacon alert (DBA) timer and timer2 as next
diff --git a/drivers/net/wireless/ath/ath5k/phy.c b/drivers/net/wireless/ath/ath5k/phy.c
index b1b8bc326830..ae08572c4b58 100644
--- a/drivers/net/wireless/ath/ath5k/phy.c
+++ b/drivers/net/wireless/ath/ath5k/phy.c
@@ -483,7 +483,6 @@ static u32
 ath5k_hw_rf_gainf_corr(struct ath5k_hw *ah)
 {
 	u32 mix, step;
-	u32 *rf;
 	const struct ath5k_gain_opt *go;
 	const struct ath5k_gain_opt_step *g_step;
 	const struct ath5k_rf_reg *rf_regs;
@@ -502,7 +501,6 @@ ath5k_hw_rf_gainf_corr(struct ath5k_hw *ah)
 	if (ah->ah_rf_banks == NULL)
 		return 0;
 
-	rf = ah->ah_rf_banks;
 	ah->ah_gain.g_f_corr = 0;
 
 	/* No VGA (Variable Gain Amplifier) override, skip */
@@ -549,13 +547,10 @@ ath5k_hw_rf_check_gainf_readback(struct ath5k_hw *ah)
 {
 	const struct ath5k_rf_reg *rf_regs;
 	u32 step, mix_ovr, level[4];
-	u32 *rf;
 
 	if (ah->ah_rf_banks == NULL)
 		return false;
 
-	rf = ah->ah_rf_banks;
-
 	if (ah->ah_radio == AR5K_RF5111) {
 
 		rf_regs = rf_regs_5111;
diff --git a/drivers/net/wireless/ath/ath6kl/bmi.c b/drivers/net/wireless/ath/ath6kl/bmi.c
index 334dbd834b3a..bde5a10d470c 100644
--- a/drivers/net/wireless/ath/ath6kl/bmi.c
+++ b/drivers/net/wireless/ath/ath6kl/bmi.c
@@ -534,7 +534,7 @@ int ath6kl_bmi_init(struct ath6kl *ar)
 	/* cmd + addr + len + data_size */
 	ar->bmi.max_cmd_size = ar->bmi.max_data_size + (sizeof(u32) * 3);
 
-	ar->bmi.cmd_buf = kzalloc(ar->bmi.max_cmd_size, GFP_ATOMIC);
+	ar->bmi.cmd_buf = kzalloc(ar->bmi.max_cmd_size, GFP_KERNEL);
 	if (!ar->bmi.cmd_buf)
 		return -ENOMEM;
 
diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index 0687697d5e2d..e121187f371f 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -1811,20 +1811,20 @@ static int ath6kl_get_station(struct wiphy *wiphy, struct net_device *dev,
 
 	if (vif->target_stats.rx_byte) {
 		sinfo->rx_bytes = vif->target_stats.rx_byte;
-		sinfo->filled |= BIT(NL80211_STA_INFO_RX_BYTES64);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BYTES64);
 		sinfo->rx_packets = vif->target_stats.rx_pkt;
-		sinfo->filled |= BIT(NL80211_STA_INFO_RX_PACKETS);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_PACKETS);
 	}
 
 	if (vif->target_stats.tx_byte) {
 		sinfo->tx_bytes = vif->target_stats.tx_byte;
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BYTES64);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BYTES64);
 		sinfo->tx_packets = vif->target_stats.tx_pkt;
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_PACKETS);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_PACKETS);
 	}
 
 	sinfo->signal = vif->target_stats.cs_rssi;
-	sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 
 	rate = vif->target_stats.tx_ucast_rate;
 
@@ -1857,12 +1857,12 @@ static int ath6kl_get_station(struct wiphy *wiphy, struct net_device *dev,
 		return 0;
 	}
 
-	sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 
 	if (test_bit(CONNECTED, &vif->flags) &&
 	    test_bit(DTIM_PERIOD_AVAIL, &vif->flags) &&
 	    vif->nw_type == INFRA_NETWORK) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_BSS_PARAM);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BSS_PARAM);
 		sinfo->bss_param.flags = 0;
 		sinfo->bss_param.dtim_period = vif->assoc_bss_dtim_period;
 		sinfo->bss_param.beacon_interval = vif->assoc_bss_beacon_int;
@@ -3899,16 +3899,19 @@ int ath6kl_cfg80211_init(struct ath6kl *ar)
 	switch (ar->hw.cap) {
 	case WMI_11AN_CAP:
 		ht = true;
+		/* fall through */
 	case WMI_11A_CAP:
 		band_5gig = true;
 		break;
 	case WMI_11GN_CAP:
 		ht = true;
+		/* fall through */
 	case WMI_11G_CAP:
 		band_2gig = true;
 		break;
 	case WMI_11AGN_CAP:
 		ht = true;
+		/* fall through */
 	case WMI_11AG_CAP:
 		band_2gig = true;
 		band_5gig = true;
diff --git a/drivers/net/wireless/ath/ath6kl/htc_pipe.c b/drivers/net/wireless/ath/ath6kl/htc_pipe.c
index 546243e11737..434b66829646 100644
--- a/drivers/net/wireless/ath/ath6kl/htc_pipe.c
+++ b/drivers/net/wireless/ath/ath6kl/htc_pipe.c
@@ -746,10 +746,8 @@ static int ath6kl_htc_pipe_tx_complete(struct ath6kl *ar, struct sk_buff *skb)
 	struct htc_endpoint *ep;
 	struct htc_packet *packet;
 	u8 ep_id, *netdata;
-	u32 netlen;
 
 	netdata = skb->data;
-	netlen = skb->len;
 
 	htc_hdr = (struct htc_frame_hdr *) netdata;
 
@@ -855,12 +853,8 @@ static int htc_process_trailer(struct htc_target *target, u8 *buffer,
 {
 	struct htc_credit_report *report;
 	struct htc_record_hdr *record;
-	u8 *record_buf, *orig_buf;
-	int orig_len, status;
-
-	orig_buf = buffer;
-	orig_len = len;
-	status = 0;
+	u8 *record_buf;
+	int status = 0;
 
 	while (len > 0) {
 		if (len < sizeof(struct htc_record_hdr)) {
diff --git a/drivers/net/wireless/ath/ath6kl/main.c b/drivers/net/wireless/ath/ath6kl/main.c
index 808fb30be9ad..0c61dbaa62a4 100644
--- a/drivers/net/wireless/ath/ath6kl/main.c
+++ b/drivers/net/wireless/ath/ath6kl/main.c
@@ -272,7 +272,7 @@ int ath6kl_read_fwlogs(struct ath6kl *ar)
 {
 	struct ath6kl_dbglog_hdr debug_hdr;
 	struct ath6kl_dbglog_buf debug_buf;
-	u32 address, length, dropped, firstbuf, debug_hdr_addr;
+	u32 address, length, firstbuf, debug_hdr_addr;
 	int ret, loop;
 	u8 *buf;
 
@@ -303,7 +303,6 @@ int ath6kl_read_fwlogs(struct ath6kl *ar)
 	address = TARG_VTOP(ar->target_type,
 			    le32_to_cpu(debug_hdr.dbuf_addr));
 	firstbuf = address;
-	dropped = le32_to_cpu(debug_hdr.dropped);
 	ret = ath6kl_diag_read(ar, address, &debug_buf, sizeof(debug_buf));
 	if (ret)
 		goto out;
diff --git a/drivers/net/wireless/ath/ath6kl/sdio.c b/drivers/net/wireless/ath/ath6kl/sdio.c
index 2195b1b7a8a6..bb50680580f3 100644
--- a/drivers/net/wireless/ath/ath6kl/sdio.c
+++ b/drivers/net/wireless/ath/ath6kl/sdio.c
@@ -1415,6 +1415,7 @@ static const struct sdio_device_id ath6kl_sdio_devices[] = {
 	{SDIO_DEVICE(MANUFACTURER_CODE, (MANUFACTURER_ID_AR6004_BASE | 0x1))},
 	{SDIO_DEVICE(MANUFACTURER_CODE, (MANUFACTURER_ID_AR6004_BASE | 0x2))},
 	{SDIO_DEVICE(MANUFACTURER_CODE, (MANUFACTURER_ID_AR6004_BASE | 0x18))},
+	{SDIO_DEVICE(MANUFACTURER_CODE, (MANUFACTURER_ID_AR6004_BASE | 0x19))},
 	{},
 };
 
diff --git a/drivers/net/wireless/ath/ath6kl/txrx.c b/drivers/net/wireless/ath/ath6kl/txrx.c
index 618d12ed4b40..b22ed499f7ba 100644
--- a/drivers/net/wireless/ath/ath6kl/txrx.c
+++ b/drivers/net/wireless/ath/ath6kl/txrx.c
@@ -1701,7 +1701,6 @@ void aggr_recv_addba_req_evt(struct ath6kl_vif *vif, u8 tid_mux, u16 seq_no,
 	struct ath6kl_sta *sta;
 	struct aggr_info_conn *aggr_conn = NULL;
 	struct rxtid *rxtid;
-	struct rxtid_stats *stats;
 	u16 hold_q_size;
 	u8 tid, aid;
 
@@ -1722,7 +1721,6 @@ void aggr_recv_addba_req_evt(struct ath6kl_vif *vif, u8 tid_mux, u16 seq_no,
 		return;
 
 	rxtid = &aggr_conn->rx_tid[tid];
-	stats = &aggr_conn->stat[tid];
 
 	if (win_sz < AGGR_WIN_SZ_MIN || win_sz > AGGR_WIN_SZ_MAX)
 		ath6kl_dbg(ATH6KL_DBG_WLAN_RX, "%s: win_sz %d, tid %d\n",
diff --git a/drivers/net/wireless/ath/ath9k/ar5008_phy.c b/drivers/net/wireless/ath/ath9k/ar5008_phy.c
index 7922550c2159..ef2dd68d3f77 100644
--- a/drivers/net/wireless/ath/ath9k/ar5008_phy.c
+++ b/drivers/net/wireless/ath/ath9k/ar5008_phy.c
@@ -583,12 +583,14 @@ static void ar5008_hw_init_chain_masks(struct ath_hw *ah)
 	case 0x5:
 		REG_SET_BIT(ah, AR_PHY_ANALOG_SWAP,
 			    AR_PHY_SWAP_ALT_CHAIN);
+		/* fall through */
 	case 0x3:
 		if (ah->hw_version.macVersion == AR_SREV_REVISION_5416_10) {
 			REG_WRITE(ah, AR_PHY_RX_CHAINMASK, 0x7);
 			REG_WRITE(ah, AR_PHY_CAL_CHAINMASK, 0x7);
 			break;
 		}
+		/* else: fall through */
 	case 0x1:
 	case 0x2:
 	case 0x7:
diff --git a/drivers/net/wireless/ath/ath9k/ar9002_calib.c b/drivers/net/wireless/ath/ath9k/ar9002_calib.c
index 50fcd343c41a..fd9db8ca99d7 100644
--- a/drivers/net/wireless/ath/ath9k/ar9002_calib.c
+++ b/drivers/net/wireless/ath/ath9k/ar9002_calib.c
@@ -676,10 +676,10 @@ static int ar9002_hw_calibrate(struct ath_hw *ah, struct ath9k_channel *chan,
 			return 0;
 
 		ah->cal_list_curr = currCal = currCal->calNext;
-		if (currCal->calState == CAL_WAITING) {
+		if (currCal->calState == CAL_WAITING)
 			ath9k_hw_reset_calibration(ah, currCal);
-			return 0;
-		}
+
+		return 0;
 	}
 
 	/* Do NF cal only at longer intervals */
diff --git a/drivers/net/wireless/ath/ath9k/ar9002_phy.c b/drivers/net/wireless/ath/ath9k/ar9002_phy.c
index 61a9b85045d2..713291881208 100644
--- a/drivers/net/wireless/ath/ath9k/ar9002_phy.c
+++ b/drivers/net/wireless/ath/ath9k/ar9002_phy.c
@@ -119,6 +119,7 @@ static int ar9002_hw_set_channel(struct ath_hw *ah, struct ath9k_channel *chan)
 				aModeRefSel = 2;
 			if (aModeRefSel)
 				break;
+			/* else: fall through */
 		case 1:
 		default:
 			aModeRefSel = 0;
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.c b/drivers/net/wireless/ath/ath9k/ar9003_phy.c
index fe5102ca5010..98c5f524a360 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_phy.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.c
@@ -1800,6 +1800,8 @@ static void ar9003_hw_spectral_scan_config(struct ath_hw *ah,
 
 static void ar9003_hw_spectral_scan_trigger(struct ath_hw *ah)
 {
+	REG_SET_BIT(ah, AR_PHY_SPECTRAL_SCAN,
+		    AR_PHY_SPECTRAL_SCAN_ENABLE);
 	/* Activate spectral scan */
 	REG_SET_BIT(ah, AR_PHY_SPECTRAL_SCAN,
 		    AR_PHY_SPECTRAL_SCAN_ACTIVE);
diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h
index ef0de4f1312c..21ba20981a80 100644
--- a/drivers/net/wireless/ath/ath9k/ath9k.h
+++ b/drivers/net/wireless/ath/ath9k/ath9k.h
@@ -342,7 +342,7 @@ struct ath_chanctx {
 
 	struct ath_beacon_config beacon;
 	struct ath9k_hw_cal_data caldata;
-	struct timespec tsf_ts;
+	struct timespec64 tsf_ts;
 	u64 tsf_val;
 	u32 last_beacon;
 
@@ -1021,7 +1021,7 @@ struct ath_softc {
 	struct ath_offchannel offchannel;
 	struct ath_chanctx *next_chan;
 	struct completion go_beacon;
-	struct timespec last_event_time;
+	struct timespec64 last_event_time;
 #endif
 
 	unsigned long driver_data;
diff --git a/drivers/net/wireless/ath/ath9k/channel.c b/drivers/net/wireless/ath/ath9k/channel.c
index 1b05b5d7a038..fd61ae4782b6 100644
--- a/drivers/net/wireless/ath/ath9k/channel.c
+++ b/drivers/net/wireless/ath/ath9k/channel.c
@@ -233,9 +233,9 @@ static const char *chanctx_state_string(enum ath_chanctx_state state)
 static u32 chanctx_event_delta(struct ath_softc *sc)
 {
 	u64 ms;
-	struct timespec ts, *old;
+	struct timespec64 ts, *old;
 
-	getrawmonotonic(&ts);
+	ktime_get_raw_ts64(&ts);
 	old = &sc->last_event_time;
 	ms = ts.tv_sec * 1000 + ts.tv_nsec / 1000000;
 	ms -= old->tv_sec * 1000 + old->tv_nsec / 1000000;
@@ -334,7 +334,7 @@ ath_chanctx_get_next(struct ath_softc *sc, struct ath_chanctx *ctx)
 static void ath_chanctx_adjust_tbtt_delta(struct ath_softc *sc)
 {
 	struct ath_chanctx *prev, *cur;
-	struct timespec ts;
+	struct timespec64 ts;
 	u32 cur_tsf, prev_tsf, beacon_int;
 	s32 offset;
 
@@ -346,7 +346,7 @@ static void ath_chanctx_adjust_tbtt_delta(struct ath_softc *sc)
 	if (!prev->switch_after_beacon)
 		return;
 
-	getrawmonotonic(&ts);
+	ktime_get_raw_ts64(&ts);
 	cur_tsf = (u32) cur->tsf_val +
 		  ath9k_hw_get_tsf_offset(&cur->tsf_ts, &ts);
 
@@ -1230,7 +1230,7 @@ void ath_chanctx_set_next(struct ath_softc *sc, bool force)
 {
 	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
 	struct ath_chanctx *old_ctx;
-	struct timespec ts;
+	struct timespec64 ts;
 	bool measure_time = false;
 	bool send_ps = false;
 	bool queues_stopped = false;
@@ -1260,7 +1260,7 @@ void ath_chanctx_set_next(struct ath_softc *sc, bool force)
 		spin_unlock_bh(&sc->chan_lock);
 
 		if (sc->next_chan == &sc->offchannel.chan) {
-			getrawmonotonic(&ts);
+			ktime_get_raw_ts64(&ts);
 			measure_time = true;
 		}
 
@@ -1277,7 +1277,7 @@ void ath_chanctx_set_next(struct ath_softc *sc, bool force)
 		spin_lock_bh(&sc->chan_lock);
 
 		if (sc->cur_chan != &sc->offchannel.chan) {
-			getrawmonotonic(&sc->cur_chan->tsf_ts);
+			ktime_get_raw_ts64(&sc->cur_chan->tsf_ts);
 			sc->cur_chan->tsf_val = ath9k_hw_gettsf64(sc->sc_ah);
 		}
 	}
diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c
index f685843a2ff3..0a6eb8a8c1ed 100644
--- a/drivers/net/wireless/ath/ath9k/debug.c
+++ b/drivers/net/wireless/ath/ath9k/debug.c
@@ -538,7 +538,7 @@ static int read_file_interrupt(struct seq_file *file, void *data)
 	if (sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_EDMA) {
 		PR_IS("RXLP", rxlp);
 		PR_IS("RXHP", rxhp);
-		PR_IS("WATHDOG", bb_watchdog);
+		PR_IS("WATCHDOG", bb_watchdog);
 	} else {
 		PR_IS("RX", rxok);
 	}
diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c
index cb0eef13af1c..fb649d85b8fc 100644
--- a/drivers/net/wireless/ath/ath9k/hif_usb.c
+++ b/drivers/net/wireless/ath/ath9k/hif_usb.c
@@ -138,6 +138,7 @@ static void hif_usb_mgmt_cb(struct urb *urb)
 {
 	struct cmd_buf *cmd = (struct cmd_buf *)urb->context;
 	struct hif_device_usb *hif_dev;
+	unsigned long flags;
 	bool txok = true;
 
 	if (!cmd || !cmd->skb || !cmd->hif_dev)
@@ -158,14 +159,14 @@ static void hif_usb_mgmt_cb(struct urb *urb)
 		 * If the URBs are being flushed, no need to complete
 		 * this packet.
 		 */
-		spin_lock(&hif_dev->tx.tx_lock);
+		spin_lock_irqsave(&hif_dev->tx.tx_lock, flags);
 		if (hif_dev->tx.flags & HIF_USB_TX_FLUSH) {
-			spin_unlock(&hif_dev->tx.tx_lock);
+			spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags);
 			dev_kfree_skb_any(cmd->skb);
 			kfree(cmd);
 			return;
 		}
-		spin_unlock(&hif_dev->tx.tx_lock);
+		spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags);
 
 		break;
 	default:
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
index 585736a837ed..799010ed04e0 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
@@ -1107,25 +1107,26 @@ void ath9k_htc_rxep(void *drv_priv, struct sk_buff *skb,
 	struct ath_hw *ah = priv->ah;
 	struct ath_common *common = ath9k_hw_common(ah);
 	struct ath9k_htc_rxbuf *rxbuf = NULL, *tmp_buf = NULL;
+	unsigned long flags;
 
-	spin_lock(&priv->rx.rxbuflock);
+	spin_lock_irqsave(&priv->rx.rxbuflock, flags);
 	list_for_each_entry(tmp_buf, &priv->rx.rxbuf, list) {
 		if (!tmp_buf->in_process) {
 			rxbuf = tmp_buf;
 			break;
 		}
 	}
-	spin_unlock(&priv->rx.rxbuflock);
+	spin_unlock_irqrestore(&priv->rx.rxbuflock, flags);
 
 	if (rxbuf == NULL) {
 		ath_dbg(common, ANY, "No free RX buffer\n");
 		goto err;
 	}
 
-	spin_lock(&priv->rx.rxbuflock);
+	spin_lock_irqsave(&priv->rx.rxbuflock, flags);
 	rxbuf->skb = skb;
 	rxbuf->in_process = true;
-	spin_unlock(&priv->rx.rxbuflock);
+	spin_unlock_irqrestore(&priv->rx.rxbuflock, flags);
 
 	tasklet_schedule(&priv->rx_tasklet);
 	return;
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index e60bea4604e4..bb319f22761f 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -496,7 +496,7 @@ static void ath9k_hw_init_macaddr(struct ath_hw *ah)
 	ath_err(common, "eeprom contains invalid mac address: %pM\n",
 		common->macaddr);
 
-	random_ether_addr(common->macaddr);
+	eth_random_addr(common->macaddr);
 	ath_err(common, "random mac address will be used: %pM\n",
 		common->macaddr);
 
@@ -1835,13 +1835,13 @@ fail:
 	return -EINVAL;
 }
 
-u32 ath9k_hw_get_tsf_offset(struct timespec *last, struct timespec *cur)
+u32 ath9k_hw_get_tsf_offset(struct timespec64 *last, struct timespec64 *cur)
 {
-	struct timespec ts;
+	struct timespec64 ts;
 	s64 usec;
 
 	if (!cur) {
-		getrawmonotonic(&ts);
+		ktime_get_raw_ts64(&ts);
 		cur = &ts;
 	}
 
@@ -1859,7 +1859,7 @@ int ath9k_hw_reset(struct ath_hw *ah, struct ath9k_channel *chan,
 	u32 saveLedState;
 	u32 saveDefAntenna;
 	u32 macStaId1;
-	struct timespec tsf_ts;
+	struct timespec64 tsf_ts;
 	u32 tsf_offset;
 	u64 tsf = 0;
 	int r;
@@ -1905,7 +1905,7 @@ int ath9k_hw_reset(struct ath_hw *ah, struct ath9k_channel *chan,
 	macStaId1 = REG_READ(ah, AR_STA_ID1) & AR_STA_ID1_BASE_RATE_11B;
 
 	/* Save TSF before chip reset, a cold reset clears it */
-	getrawmonotonic(&tsf_ts);
+	ktime_get_raw_ts64(&tsf_ts);
 	tsf = ath9k_hw_gettsf64(ah);
 
 	saveLedState = REG_READ(ah, AR_CFG_LED) &
@@ -2942,16 +2942,19 @@ void ath9k_hw_apply_txpower(struct ath_hw *ah, struct ath9k_channel *chan,
 	struct ath_regulatory *reg = ath9k_hw_regulatory(ah);
 	struct ieee80211_channel *channel;
 	int chan_pwr, new_pwr;
+	u16 ctl = NO_CTL;
 
 	if (!chan)
 		return;
 
+	if (!test)
+		ctl = ath9k_regd_get_ctl(reg, chan);
+
 	channel = chan->chan;
 	chan_pwr = min_t(int, channel->max_power * 2, MAX_RATE_POWER);
 	new_pwr = min_t(int, chan_pwr, reg->power_limit);
 
-	ah->eep_ops->set_txpower(ah, chan,
-				 ath9k_regd_get_ctl(reg, chan),
+	ah->eep_ops->set_txpower(ah, chan, ctl,
 				 get_antenna_gain(ah, chan), new_pwr, test);
 }
 
diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h
index 9804a24a2dc0..68956cdc8c9a 100644
--- a/drivers/net/wireless/ath/ath9k/hw.h
+++ b/drivers/net/wireless/ath/ath9k/hw.h
@@ -1060,7 +1060,7 @@ u32 ath9k_hw_gettsf32(struct ath_hw *ah);
 u64 ath9k_hw_gettsf64(struct ath_hw *ah);
 void ath9k_hw_settsf64(struct ath_hw *ah, u64 tsf64);
 void ath9k_hw_reset_tsf(struct ath_hw *ah);
-u32 ath9k_hw_get_tsf_offset(struct timespec *last, struct timespec *cur);
+u32 ath9k_hw_get_tsf_offset(struct timespec64 *last, struct timespec64 *cur);
 void ath9k_hw_set_tsfadjust(struct ath_hw *ah, bool set);
 void ath9k_hw_init_global_settings(struct ath_hw *ah);
 u32 ar9003_get_pll_sqsum_dvc(struct ath_hw *ah);
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index b6663c80e7dd..1049773378f2 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -1865,7 +1865,7 @@ static void ath9k_set_tsf(struct ieee80211_hw *hw,
 	mutex_lock(&sc->mutex);
 	ath9k_ps_wakeup(sc);
 	tsf -= le64_to_cpu(avp->tsf_adjust);
-	getrawmonotonic(&avp->chanctx->tsf_ts);
+	ktime_get_raw_ts64(&avp->chanctx->tsf_ts);
 	if (sc->cur_chan == avp->chanctx)
 		ath9k_hw_settsf64(sc->sc_ah, tsf);
 	avp->chanctx->tsf_val = tsf;
@@ -1881,7 +1881,7 @@ static void ath9k_reset_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	mutex_lock(&sc->mutex);
 
 	ath9k_ps_wakeup(sc);
-	getrawmonotonic(&avp->chanctx->tsf_ts);
+	ktime_get_raw_ts64(&avp->chanctx->tsf_ts);
 	if (sc->cur_chan == avp->chanctx)
 		ath9k_hw_reset_tsf(sc->sc_ah);
 	avp->chanctx->tsf_val = 0;
@@ -1928,6 +1928,7 @@ static int ath9k_ampdu_action(struct ieee80211_hw *hw,
 	case IEEE80211_AMPDU_TX_STOP_FLUSH:
 	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
 		flush = true;
+		/* fall through */
 	case IEEE80211_AMPDU_TX_STOP_CONT:
 		ath9k_ps_wakeup(sc);
 		ath_tx_aggr_stop(sc, sta, tid);
diff --git a/drivers/net/wireless/ath/ath9k/pci.c b/drivers/net/wireless/ath/ath9k/pci.c
index 645f0fbd9179..92b2dd396436 100644
--- a/drivers/net/wireless/ath/ath9k/pci.c
+++ b/drivers/net/wireless/ath/ath9k/pci.c
@@ -18,7 +18,6 @@
 
 #include <linux/nl80211.h>
 #include <linux/pci.h>
-#include <linux/pci-aspm.h>
 #include <linux/module.h>
 #include "ath9k.h"
 
diff --git a/drivers/net/wireless/ath/ath9k/wmi.c b/drivers/net/wireless/ath/ath9k/wmi.c
index b0b5579b7560..d1f6710ca63b 100644
--- a/drivers/net/wireless/ath/ath9k/wmi.c
+++ b/drivers/net/wireless/ath/ath9k/wmi.c
@@ -209,6 +209,7 @@ static void ath9k_wmi_ctrl_rx(void *priv, struct sk_buff *skb,
 {
 	struct wmi *wmi = priv;
 	struct wmi_cmd_hdr *hdr;
+	unsigned long flags;
 	u16 cmd_id;
 
 	if (unlikely(wmi->stopped))
@@ -218,20 +219,20 @@ static void ath9k_wmi_ctrl_rx(void *priv, struct sk_buff *skb,
 	cmd_id = be16_to_cpu(hdr->command_id);
 
 	if (cmd_id & 0x1000) {
-		spin_lock(&wmi->wmi_lock);
+		spin_lock_irqsave(&wmi->wmi_lock, flags);
 		__skb_queue_tail(&wmi->wmi_event_queue, skb);
-		spin_unlock(&wmi->wmi_lock);
+		spin_unlock_irqrestore(&wmi->wmi_lock, flags);
 		tasklet_schedule(&wmi->wmi_event_tasklet);
 		return;
 	}
 
 	/* Check if there has been a timeout. */
-	spin_lock(&wmi->wmi_lock);
+	spin_lock_irqsave(&wmi->wmi_lock, flags);
 	if (be16_to_cpu(hdr->seq_no) != wmi->last_seq_id) {
-		spin_unlock(&wmi->wmi_lock);
+		spin_unlock_irqrestore(&wmi->wmi_lock, flags);
 		goto free_skb;
 	}
-	spin_unlock(&wmi->wmi_lock);
+	spin_unlock_irqrestore(&wmi->wmi_lock, flags);
 
 	/* WMI command response */
 	ath9k_wmi_rsp_callback(wmi, skb);
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index 7fdb152be0bb..43b6c8508e49 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -62,7 +62,7 @@ static void ath_tx_rc_status(struct ath_softc *sc, struct ath_buf *bf,
 			     struct ath_tx_status *ts, int nframes, int nbad,
 			     int txok);
 static void ath_tx_update_baw(struct ath_softc *sc, struct ath_atx_tid *tid,
-			      int seqno);
+			      struct ath_buf *bf);
 static struct ath_buf *ath_tx_setup_buffer(struct ath_softc *sc,
 					   struct ath_txq *txq,
 					   struct ath_atx_tid *tid,
@@ -86,7 +86,8 @@ static void ath_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_sta *sta = info->status.status_driver_data[0];
 
-	if (info->flags & IEEE80211_TX_CTL_REQ_TX_STATUS) {
+	if (info->flags & (IEEE80211_TX_CTL_REQ_TX_STATUS |
+			   IEEE80211_TX_STATUS_EOSP)) {
 		ieee80211_tx_status(hw, skb);
 		return;
 	}
@@ -295,7 +296,7 @@ static void ath_tx_flush_tid(struct ath_softc *sc, struct ath_atx_tid *tid)
 		}
 
 		if (fi->baw_tracked) {
-			ath_tx_update_baw(sc, tid, bf->bf_state.seqno);
+			ath_tx_update_baw(sc, tid, bf);
 			sendbar = true;
 		}
 
@@ -311,10 +312,15 @@ static void ath_tx_flush_tid(struct ath_softc *sc, struct ath_atx_tid *tid)
 }
 
 static void ath_tx_update_baw(struct ath_softc *sc, struct ath_atx_tid *tid,
-			      int seqno)
+			      struct ath_buf *bf)
 {
+	struct ath_frame_info *fi = get_frame_info(bf->bf_mpdu);
+	u16 seqno = bf->bf_state.seqno;
 	int index, cindex;
 
+	if (!fi->baw_tracked)
+		return;
+
 	index  = ATH_BA_INDEX(tid->seq_start, seqno);
 	cindex = (tid->baw_head + index) & (ATH_TID_MAX_BUFS - 1);
 
@@ -335,6 +341,9 @@ static void ath_tx_addto_baw(struct ath_softc *sc, struct ath_atx_tid *tid,
 	u16 seqno = bf->bf_state.seqno;
 	int index, cindex;
 
+	if (fi->baw_tracked)
+		return;
+
 	index  = ATH_BA_INDEX(tid->seq_start, seqno);
 	cindex = (tid->baw_head + index) & (ATH_TID_MAX_BUFS - 1);
 	__set_bit(cindex, tid->tx_buf);
@@ -611,7 +620,7 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq,
 			 * complete the acked-ones/xretried ones; update
 			 * block-ack window
 			 */
-			ath_tx_update_baw(sc, tid, seqno);
+			ath_tx_update_baw(sc, tid, bf);
 
 			if (rc_update && (acked_cnt == 1 || txfail_cnt == 1)) {
 				memcpy(tx_info->control.rates, rates, sizeof(rates));
@@ -641,7 +650,7 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq,
 				 * run out of tx buf.
 				 */
 				if (!tbf) {
-					ath_tx_update_baw(sc, tid, seqno);
+					ath_tx_update_baw(sc, tid, bf);
 
 					ath_tx_complete_buf(sc, bf, txq,
 							    &bf_head, NULL, ts,
@@ -969,7 +978,8 @@ ath_tx_get_tid_subframe(struct ath_softc *sc, struct ath_txq *txq,
 		bf->bf_lastbf = bf;
 
 		tx_info = IEEE80211_SKB_CB(skb);
-		tx_info->flags &= ~IEEE80211_TX_CTL_CLEAR_PS_FILT;
+		tx_info->flags &= ~(IEEE80211_TX_CTL_CLEAR_PS_FILT |
+				    IEEE80211_TX_STATUS_EOSP);
 
 		/*
 		 * No aggregation session is running, but there may be frames
@@ -1009,11 +1019,14 @@ ath_tx_get_tid_subframe(struct ath_softc *sc, struct ath_txq *txq,
 
 			INIT_LIST_HEAD(&bf_head);
 			list_add(&bf->list, &bf_head);
-			ath_tx_update_baw(sc, tid, seqno);
+			ath_tx_update_baw(sc, tid, bf);
 			ath_tx_complete_buf(sc, bf, txq, &bf_head, NULL, &ts, 0);
 			continue;
 		}
 
+		if (bf_isampdu(bf))
+			ath_tx_addto_baw(sc, tid, bf);
+
 		return bf;
 	}
 
@@ -1071,8 +1084,6 @@ ath_tx_form_aggr(struct ath_softc *sc, struct ath_txq *txq,
 		bf->bf_next = NULL;
 
 		/* link buffers of this frame to the aggregate */
-		if (!fi->baw_tracked)
-			ath_tx_addto_baw(sc, tid, bf);
 		bf->bf_state.ndelim = ndelim;
 
 		list_add_tail(&bf->list, bf_q);
@@ -1659,6 +1670,22 @@ void ath_tx_aggr_wakeup(struct ath_softc *sc, struct ath_node *an)
 	}
 }
 
+
+static void
+ath9k_set_moredata(struct ath_softc *sc, struct ath_buf *bf, bool val)
+{
+	struct ieee80211_hdr *hdr;
+	u16 mask = cpu_to_le16(IEEE80211_FCTL_MOREDATA);
+	u16 mask_val = mask * val;
+
+	hdr = (struct ieee80211_hdr *) bf->bf_mpdu->data;
+	if ((hdr->frame_control & mask) != mask_val) {
+		hdr->frame_control = (hdr->frame_control & ~mask) | mask_val;
+		dma_sync_single_for_device(sc->dev, bf->bf_buf_addr,
+			sizeof(*hdr), DMA_TO_DEVICE);
+	}
+}
+
 void ath9k_release_buffered_frames(struct ieee80211_hw *hw,
 				   struct ieee80211_sta *sta,
 				   u16 tids, int nframes,
@@ -1689,12 +1716,11 @@ void ath9k_release_buffered_frames(struct ieee80211_hw *hw,
 			if (!bf)
 				break;
 
+			ath9k_set_moredata(sc, bf, true);
 			list_add_tail(&bf->list, &bf_q);
 			ath_set_rates(tid->an->vif, tid->an->sta, bf);
-			if (bf_isampdu(bf)) {
-				ath_tx_addto_baw(sc, tid, bf);
+			if (bf_isampdu(bf))
 				bf->bf_state.bf_type &= ~BUF_AGGR;
-			}
 			if (bf_tail)
 				bf_tail->bf_next = bf;
 
@@ -1712,6 +1738,9 @@ void ath9k_release_buffered_frames(struct ieee80211_hw *hw,
 	if (list_empty(&bf_q))
 		return;
 
+	if (!more_data)
+		ath9k_set_moredata(sc, bf_tail, false);
+
 	info = IEEE80211_SKB_CB(bf_tail->bf_mpdu);
 	info->flags |= IEEE80211_TX_STATUS_EOSP;
 
@@ -2407,7 +2436,6 @@ void ath_tx_cabq(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		.txq = sc->beacon.cabq
 	};
 	struct ath_tx_info info = {};
-	struct ieee80211_hdr *hdr;
 	struct ath_buf *bf_tail = NULL;
 	struct ath_buf *bf;
 	LIST_HEAD(bf_q);
@@ -2451,15 +2479,10 @@ void ath_tx_cabq(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	if (list_empty(&bf_q))
 		return;
 
-	bf = list_first_entry(&bf_q, struct ath_buf, list);
-	hdr = (struct ieee80211_hdr *) bf->bf_mpdu->data;
-
-	if (hdr->frame_control & cpu_to_le16(IEEE80211_FCTL_MOREDATA)) {
-		hdr->frame_control &= ~cpu_to_le16(IEEE80211_FCTL_MOREDATA);
-		dma_sync_single_for_device(sc->dev, bf->bf_buf_addr,
-			sizeof(*hdr), DMA_TO_DEVICE);
-	}
+	bf = list_last_entry(&bf_q, struct ath_buf, list);
+	ath9k_set_moredata(sc, bf, false);
 
+	bf = list_first_entry(&bf_q, struct ath_buf, list);
 	ath_txq_lock(sc, txctl.txq);
 	ath_tx_fill_desc(sc, bf, txctl.txq, 0);
 	ath_tx_txqaddbuf(sc, txctl.txq, &bf_q, false);
diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index aeb5e6e806be..79998a3ddb7a 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -493,7 +493,7 @@ static int wcn36xx_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 {
 	struct wcn36xx *wcn = hw->priv;
 	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
-	struct wcn36xx_sta *sta_priv = wcn36xx_sta_to_priv(sta);
+	struct wcn36xx_sta *sta_priv = sta ? wcn36xx_sta_to_priv(sta) : NULL;
 	int ret = 0;
 	u8 key[WLAN_MAX_KEY_LEN];
 
@@ -512,7 +512,7 @@ static int wcn36xx_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 		vif_priv->encrypt_type = WCN36XX_HAL_ED_WEP40;
 		break;
 	case WLAN_CIPHER_SUITE_WEP104:
-		vif_priv->encrypt_type = WCN36XX_HAL_ED_WEP40;
+		vif_priv->encrypt_type = WCN36XX_HAL_ED_WEP104;
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
 		vif_priv->encrypt_type = WCN36XX_HAL_ED_CCMP;
@@ -567,15 +567,19 @@ static int wcn36xx_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 				key_conf->keyidx,
 				key_conf->keylen,
 				key);
+
 			if ((WLAN_CIPHER_SUITE_WEP40 == key_conf->cipher) ||
 			    (WLAN_CIPHER_SUITE_WEP104 == key_conf->cipher)) {
-				sta_priv->is_data_encrypted = true;
-				wcn36xx_smd_set_stakey(wcn,
-					vif_priv->encrypt_type,
-					key_conf->keyidx,
-					key_conf->keylen,
-					key,
-					get_sta_index(vif, sta_priv));
+				list_for_each_entry(sta_priv,
+						    &vif_priv->sta_list, list) {
+					sta_priv->is_data_encrypted = true;
+					wcn36xx_smd_set_stakey(wcn,
+						vif_priv->encrypt_type,
+						key_conf->keyidx,
+						key_conf->keylen,
+						key,
+						get_sta_index(vif, sta_priv));
+				}
 			}
 		}
 		break;
@@ -984,6 +988,7 @@ static int wcn36xx_add_interface(struct ieee80211_hw *hw,
 	mutex_lock(&wcn->conf_mutex);
 
 	vif_priv->bss_index = WCN36XX_HAL_BSS_INVALID_IDX;
+	INIT_LIST_HEAD(&vif_priv->sta_list);
 	list_add(&vif_priv->list, &wcn->vif_list);
 	wcn36xx_smd_add_sta_self(wcn, vif);
 
@@ -1005,6 +1010,8 @@ static int wcn36xx_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 
 	spin_lock_init(&sta_priv->ampdu_lock);
 	sta_priv->vif = vif_priv;
+	list_add(&sta_priv->list, &vif_priv->sta_list);
+
 	/*
 	 * For STA mode HW will be configured on BSS_CHANGED_ASSOC because
 	 * at this stage AID is not available yet.
@@ -1032,6 +1039,7 @@ static int wcn36xx_sta_remove(struct ieee80211_hw *hw,
 
 	mutex_lock(&wcn->conf_mutex);
 
+	list_del(&sta_priv->list);
 	wcn36xx_smd_delete_sta(wcn, sta_priv->sta_index);
 	sta_priv->vif = NULL;
 
@@ -1153,8 +1161,6 @@ static const struct ieee80211_ops wcn36xx_ops = {
 
 static int wcn36xx_init_ieee80211(struct wcn36xx *wcn)
 {
-	int ret = 0;
-
 	static const u32 cipher_suites[] = {
 		WLAN_CIPHER_SUITE_WEP40,
 		WLAN_CIPHER_SUITE_WEP104,
@@ -1201,7 +1207,7 @@ static int wcn36xx_init_ieee80211(struct wcn36xx *wcn)
 	wiphy_ext_feature_set(wcn->hw->wiphy,
 			      NL80211_EXT_FEATURE_CQM_RSSI_LIST);
 
-	return ret;
+	return 0;
 }
 
 static int wcn36xx_platform_get_resources(struct wcn36xx *wcn,
diff --git a/drivers/net/wireless/ath/wcn36xx/smd.c b/drivers/net/wireless/ath/wcn36xx/smd.c
index b4dadf75d565..00098f24116d 100644
--- a/drivers/net/wireless/ath/wcn36xx/smd.c
+++ b/drivers/net/wireless/ath/wcn36xx/smd.c
@@ -250,7 +250,7 @@ static void wcn36xx_smd_set_sta_params(struct wcn36xx *wcn,
 
 static int wcn36xx_smd_send_and_wait(struct wcn36xx *wcn, size_t len)
 {
-	int ret = 0;
+	int ret;
 	unsigned long start;
 	struct wcn36xx_hal_msg_header *hdr =
 		(struct wcn36xx_hal_msg_header *)wcn->hal_buf;
@@ -446,7 +446,7 @@ static int wcn36xx_smd_start_rsp(struct wcn36xx *wcn, void *buf, size_t len)
 int wcn36xx_smd_start(struct wcn36xx *wcn)
 {
 	struct wcn36xx_hal_mac_start_req_msg msg_body, *body;
-	int ret = 0;
+	int ret;
 	int i;
 	size_t len;
 
@@ -493,7 +493,7 @@ out:
 int wcn36xx_smd_stop(struct wcn36xx *wcn)
 {
 	struct wcn36xx_hal_mac_stop_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_STOP_REQ);
@@ -520,7 +520,7 @@ out:
 int wcn36xx_smd_init_scan(struct wcn36xx *wcn, enum wcn36xx_hal_sys_mode mode)
 {
 	struct wcn36xx_hal_init_scan_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_INIT_SCAN_REQ);
@@ -549,7 +549,7 @@ out:
 int wcn36xx_smd_start_scan(struct wcn36xx *wcn, u8 scan_channel)
 {
 	struct wcn36xx_hal_start_scan_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_START_SCAN_REQ);
@@ -579,7 +579,7 @@ out:
 int wcn36xx_smd_end_scan(struct wcn36xx *wcn, u8 scan_channel)
 {
 	struct wcn36xx_hal_end_scan_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_END_SCAN_REQ);
@@ -610,7 +610,7 @@ int wcn36xx_smd_finish_scan(struct wcn36xx *wcn,
 			    enum wcn36xx_hal_sys_mode mode)
 {
 	struct wcn36xx_hal_finish_scan_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_FINISH_SCAN_REQ);
@@ -732,7 +732,7 @@ out:
 static int wcn36xx_smd_switch_channel_rsp(void *buf, size_t len)
 {
 	struct wcn36xx_hal_switch_channel_rsp_msg *rsp;
-	int ret = 0;
+	int ret;
 
 	ret = wcn36xx_smd_rsp_status_check(buf, len);
 	if (ret)
@@ -747,7 +747,7 @@ int wcn36xx_smd_switch_channel(struct wcn36xx *wcn,
 			       struct ieee80211_vif *vif, int ch)
 {
 	struct wcn36xx_hal_switch_channel_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_CH_SWITCH_REQ);
@@ -860,7 +860,7 @@ int wcn36xx_smd_update_scan_params(struct wcn36xx *wcn,
 				   u8 *channels, size_t channel_count)
 {
 	struct wcn36xx_hal_update_scan_params_req_ex msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_UPDATE_SCAN_PARAM_REQ);
@@ -931,7 +931,7 @@ static int wcn36xx_smd_add_sta_self_rsp(struct wcn36xx *wcn,
 int wcn36xx_smd_add_sta_self(struct wcn36xx *wcn, struct ieee80211_vif *vif)
 {
 	struct wcn36xx_hal_add_sta_self_req msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_ADD_STA_SELF_REQ);
@@ -965,7 +965,7 @@ out:
 int wcn36xx_smd_delete_sta_self(struct wcn36xx *wcn, u8 *addr)
 {
 	struct wcn36xx_hal_del_sta_self_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_DEL_STA_SELF_REQ);
@@ -993,7 +993,7 @@ out:
 int wcn36xx_smd_delete_sta(struct wcn36xx *wcn, u8 sta_index)
 {
 	struct wcn36xx_hal_delete_sta_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_DELETE_STA_REQ);
@@ -1040,7 +1040,7 @@ static int wcn36xx_smd_join_rsp(void *buf, size_t len)
 int wcn36xx_smd_join(struct wcn36xx *wcn, const u8 *bssid, u8 *vif, u8 ch)
 {
 	struct wcn36xx_hal_join_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_JOIN_REQ);
@@ -1089,7 +1089,7 @@ int wcn36xx_smd_set_link_st(struct wcn36xx *wcn, const u8 *bssid,
 			    enum wcn36xx_hal_link_state state)
 {
 	struct wcn36xx_hal_set_link_state_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_SET_LINK_ST_REQ);
@@ -1215,7 +1215,7 @@ int wcn36xx_smd_config_sta(struct wcn36xx *wcn, struct ieee80211_vif *vif,
 {
 	struct wcn36xx_hal_config_sta_req_msg msg;
 	struct wcn36xx_hal_config_sta_params *sta_params;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg, WCN36XX_HAL_CONFIG_STA_REQ);
@@ -1414,7 +1414,7 @@ int wcn36xx_smd_config_bss(struct wcn36xx *wcn, struct ieee80211_vif *vif,
 	struct wcn36xx_hal_config_bss_params *bss;
 	struct wcn36xx_hal_config_sta_params *sta_params;
 	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg, WCN36XX_HAL_CONFIG_BSS_REQ);
@@ -1579,7 +1579,7 @@ int wcn36xx_smd_send_beacon(struct wcn36xx *wcn, struct ieee80211_vif *vif,
 			    u16 p2p_off)
 {
 	struct wcn36xx_hal_send_beacon_req_msg msg_body;
-	int ret = 0, pad, pvm_len;
+	int ret, pad, pvm_len;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_SEND_BEACON_REQ);
@@ -1653,7 +1653,7 @@ int wcn36xx_smd_update_proberesp_tmpl(struct wcn36xx *wcn,
 				      struct sk_buff *skb)
 {
 	struct wcn36xx_hal_send_probe_resp_req_msg msg;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg, WCN36XX_HAL_UPDATE_PROBE_RSP_TEMPLATE_REQ);
@@ -1700,7 +1700,7 @@ int wcn36xx_smd_set_stakey(struct wcn36xx *wcn,
 			   u8 sta_index)
 {
 	struct wcn36xx_hal_set_sta_key_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_SET_STAKEY_REQ);
@@ -1708,12 +1708,20 @@ int wcn36xx_smd_set_stakey(struct wcn36xx *wcn,
 	msg_body.set_sta_key_params.sta_index = sta_index;
 	msg_body.set_sta_key_params.enc_type = enc_type;
 
-	msg_body.set_sta_key_params.key[0].id = keyidx;
-	msg_body.set_sta_key_params.key[0].unicast = 1;
-	msg_body.set_sta_key_params.key[0].direction = WCN36XX_HAL_TX_RX;
-	msg_body.set_sta_key_params.key[0].pae_role = 0;
-	msg_body.set_sta_key_params.key[0].length = keylen;
-	memcpy(msg_body.set_sta_key_params.key[0].key, key, keylen);
+	if (enc_type == WCN36XX_HAL_ED_WEP104 ||
+	    enc_type == WCN36XX_HAL_ED_WEP40) {
+		/* Use bss key for wep (static) */
+		msg_body.set_sta_key_params.def_wep_idx = keyidx;
+		msg_body.set_sta_key_params.wep_type = 0;
+	} else {
+		msg_body.set_sta_key_params.key[0].id = keyidx;
+		msg_body.set_sta_key_params.key[0].unicast = 1;
+		msg_body.set_sta_key_params.key[0].direction = WCN36XX_HAL_TX_RX;
+		msg_body.set_sta_key_params.key[0].pae_role = 0;
+		msg_body.set_sta_key_params.key[0].length = keylen;
+		memcpy(msg_body.set_sta_key_params.key[0].key, key, keylen);
+	}
+
 	msg_body.set_sta_key_params.single_tid_rc = 1;
 
 	PREPARE_HAL_BUF(wcn->hal_buf, msg_body);
@@ -1741,7 +1749,7 @@ int wcn36xx_smd_set_bsskey(struct wcn36xx *wcn,
 			   u8 *key)
 {
 	struct wcn36xx_hal_set_bss_key_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_SET_BSSKEY_REQ);
@@ -1778,7 +1786,7 @@ int wcn36xx_smd_remove_stakey(struct wcn36xx *wcn,
 			      u8 sta_index)
 {
 	struct wcn36xx_hal_remove_sta_key_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_RMV_STAKEY_REQ);
@@ -1810,7 +1818,7 @@ int wcn36xx_smd_remove_bsskey(struct wcn36xx *wcn,
 			      u8 keyidx)
 {
 	struct wcn36xx_hal_remove_bss_key_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_RMV_BSSKEY_REQ);
@@ -1839,7 +1847,7 @@ int wcn36xx_smd_enter_bmps(struct wcn36xx *wcn, struct ieee80211_vif *vif)
 {
 	struct wcn36xx_hal_enter_bmps_req_msg msg_body;
 	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_ENTER_BMPS_REQ);
@@ -1869,7 +1877,7 @@ int wcn36xx_smd_exit_bmps(struct wcn36xx *wcn, struct ieee80211_vif *vif)
 {
 	struct wcn36xx_hal_exit_bmps_req_msg msg_body;
 	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_EXIT_BMPS_REQ);
@@ -1895,7 +1903,7 @@ out:
 int wcn36xx_smd_set_power_params(struct wcn36xx *wcn, bool ignore_dtim)
 {
 	struct wcn36xx_hal_set_power_params_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_SET_POWER_PARAMS_REQ);
@@ -1930,7 +1938,7 @@ int wcn36xx_smd_keep_alive_req(struct wcn36xx *wcn,
 {
 	struct wcn36xx_hal_keep_alive_req_msg msg_body;
 	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_KEEP_ALIVE_REQ);
@@ -1968,7 +1976,7 @@ int wcn36xx_smd_dump_cmd_req(struct wcn36xx *wcn, u32 arg1, u32 arg2,
 			     u32 arg3, u32 arg4, u32 arg5)
 {
 	struct wcn36xx_hal_dump_cmd_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_DUMP_COMMAND_REQ);
@@ -2013,7 +2021,6 @@ void set_feat_caps(u32 *bitmap, enum place_holder_in_cap_bitmap cap)
 int get_feat_caps(u32 *bitmap, enum place_holder_in_cap_bitmap cap)
 {
 	int arr_idx, bit_idx;
-	int ret = 0;
 
 	if (cap < 0 || cap > 127) {
 		wcn36xx_warn("error cap idx %d\n", cap);
@@ -2022,8 +2029,8 @@ int get_feat_caps(u32 *bitmap, enum place_holder_in_cap_bitmap cap)
 
 	arr_idx = cap / 32;
 	bit_idx = cap % 32;
-	ret = (bitmap[arr_idx] & (1 << bit_idx)) ? 1 : 0;
-	return ret;
+
+	return (bitmap[arr_idx] & (1 << bit_idx)) ? 1 : 0;
 }
 
 void clear_feat_caps(u32 *bitmap, enum place_holder_in_cap_bitmap cap)
@@ -2043,7 +2050,7 @@ void clear_feat_caps(u32 *bitmap, enum place_holder_in_cap_bitmap cap)
 int wcn36xx_smd_feature_caps_exchange(struct wcn36xx *wcn)
 {
 	struct wcn36xx_hal_feat_caps_msg msg_body, *rsp;
-	int ret = 0, i;
+	int ret, i;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_FEATURE_CAPS_EXCHANGE_REQ);
@@ -2079,7 +2086,7 @@ int wcn36xx_smd_add_ba_session(struct wcn36xx *wcn,
 		u8 sta_index)
 {
 	struct wcn36xx_hal_add_ba_session_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_ADD_BA_SESSION_REQ);
@@ -2117,7 +2124,7 @@ out:
 int wcn36xx_smd_add_ba(struct wcn36xx *wcn)
 {
 	struct wcn36xx_hal_add_ba_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_ADD_BA_REQ);
@@ -2145,7 +2152,7 @@ out:
 int wcn36xx_smd_del_ba(struct wcn36xx *wcn, u16 tid, u8 sta_index)
 {
 	struct wcn36xx_hal_del_ba_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_DEL_BA_REQ);
@@ -2185,7 +2192,7 @@ int wcn36xx_smd_trigger_ba(struct wcn36xx *wcn, u8 sta_index)
 {
 	struct wcn36xx_hal_trigger_ba_req_msg msg_body;
 	struct wcn36xx_hal_trigger_ba_req_candidate *candidate;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_TRIGGER_BA_REQ);
@@ -2364,7 +2371,7 @@ int wcn36xx_smd_update_cfg(struct wcn36xx *wcn, u32 cfg_id, u32 value)
 {
 	struct wcn36xx_hal_update_cfg_req_msg msg_body, *body;
 	size_t len;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_UPDATE_CFG_REQ);
@@ -2399,7 +2406,7 @@ int wcn36xx_smd_set_mc_list(struct wcn36xx *wcn,
 {
 	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
 	struct wcn36xx_hal_rcv_flt_pkt_set_mc_list_req_msg *msg_body = NULL;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 
diff --git a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
index 11e74015c79a..a58f313983b9 100644
--- a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
+++ b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
@@ -129,6 +129,8 @@ struct wcn36xx_vif {
 	u8 self_sta_index;
 	u8 self_dpu_desc_index;
 	u8 self_ucast_dpu_sign;
+
+	struct list_head sta_list;
 };
 
 /**
@@ -154,6 +156,7 @@ struct wcn36xx_vif {
  * |______________|_____________|_______________|
  */
 struct wcn36xx_sta {
+	struct list_head list;
 	struct wcn36xx_vif *vif;
 	u16 aid;
 	u16 tid;
diff --git a/drivers/net/wireless/ath/wil6210/Makefile b/drivers/net/wireless/ath/wil6210/Makefile
index 398edd2a7f2b..d3d61ae459e2 100644
--- a/drivers/net/wireless/ath/wil6210/Makefile
+++ b/drivers/net/wireless/ath/wil6210/Makefile
@@ -9,6 +9,7 @@ wil6210-$(CONFIG_WIL6210_DEBUGFS) += debugfs.o
 wil6210-y += wmi.o
 wil6210-y += interrupt.o
 wil6210-y += txrx.o
+wil6210-y += txrx_edma.o
 wil6210-y += debug.o
 wil6210-y += rx_reorder.o
 wil6210-y += fw.o
diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c
index 78946f28d0c7..f79c337105cb 100644
--- a/drivers/net/wireless/ath/wil6210/cfg80211.c
+++ b/drivers/net/wireless/ath/wil6210/cfg80211.c
@@ -302,14 +302,14 @@ int wil_cid_fill_sinfo(struct wil6210_vif *vif, int cid,
 
 	sinfo->generation = wil->sinfo_gen;
 
-	sinfo->filled = BIT(NL80211_STA_INFO_RX_BYTES) |
-			BIT(NL80211_STA_INFO_TX_BYTES) |
-			BIT(NL80211_STA_INFO_RX_PACKETS) |
-			BIT(NL80211_STA_INFO_TX_PACKETS) |
-			BIT(NL80211_STA_INFO_RX_BITRATE) |
-			BIT(NL80211_STA_INFO_TX_BITRATE) |
-			BIT(NL80211_STA_INFO_RX_DROP_MISC) |
-			BIT(NL80211_STA_INFO_TX_FAILED);
+	sinfo->filled = BIT_ULL(NL80211_STA_INFO_RX_BYTES) |
+			BIT_ULL(NL80211_STA_INFO_TX_BYTES) |
+			BIT_ULL(NL80211_STA_INFO_RX_PACKETS) |
+			BIT_ULL(NL80211_STA_INFO_TX_PACKETS) |
+			BIT_ULL(NL80211_STA_INFO_RX_BITRATE) |
+			BIT_ULL(NL80211_STA_INFO_TX_BITRATE) |
+			BIT_ULL(NL80211_STA_INFO_RX_DROP_MISC) |
+			BIT_ULL(NL80211_STA_INFO_TX_FAILED);
 
 	sinfo->txrate.flags = RATE_INFO_FLAGS_60G;
 	sinfo->txrate.mcs = le16_to_cpu(reply.evt.bf_mcs);
@@ -322,7 +322,7 @@ int wil_cid_fill_sinfo(struct wil6210_vif *vif, int cid,
 	sinfo->tx_failed = stats->tx_errors;
 
 	if (test_bit(wil_vif_fwconnected, vif->status)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 		if (test_bit(WMI_FW_CAPABILITY_RSSI_REPORTING,
 			     wil->fw_capabilities))
 			sinfo->signal = reply.evt.rssi;
@@ -689,11 +689,12 @@ static int wil_cfg80211_scan(struct wiphy *wiphy,
 
 	wil_dbg_misc(wil, "scan: wdev=0x%p iftype=%d\n", wdev, wdev->iftype);
 
-	/* check we are client side */
+	/* scan is supported on client interfaces and on AP interface */
 	switch (wdev->iftype) {
 	case NL80211_IFTYPE_STATION:
 	case NL80211_IFTYPE_P2P_CLIENT:
 	case NL80211_IFTYPE_P2P_DEVICE:
+	case NL80211_IFTYPE_AP:
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -1089,18 +1090,51 @@ int wil_cfg80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 	int rc;
 	bool tx_status;
 
-	/* Note, currently we do not support the "wait" parameter, user-space
-	 * must call remain_on_channel before mgmt_tx or listen on a channel
-	 * another way (AP/PCP or connected station)
-	 * in addition we need to check if specified "chan" argument is
-	 * different from currently "listened" channel and fail if it is.
+	wil_dbg_misc(wil, "mgmt_tx: channel %d offchan %d, wait %d\n",
+		     params->chan ? params->chan->hw_value : -1,
+		     params->offchan,
+		     params->wait);
+
+	/* Note, currently we support the "wait" parameter only on AP mode.
+	 * In other modes, user-space must call remain_on_channel before
+	 * mgmt_tx or listen on a channel other than active one.
 	 */
 
-	rc = wmi_mgmt_tx(vif, buf, len);
-	tx_status = (rc == 0);
+	if (params->chan && params->chan->hw_value == 0) {
+		wil_err(wil, "invalid channel\n");
+		return -EINVAL;
+	}
 
+	if (wdev->iftype != NL80211_IFTYPE_AP) {
+		wil_dbg_misc(wil,
+			     "send WMI_SW_TX_REQ_CMDID on non-AP interfaces\n");
+		rc = wmi_mgmt_tx(vif, buf, len);
+		goto out;
+	}
+
+	if (!params->chan || params->chan->hw_value == vif->channel) {
+		wil_dbg_misc(wil,
+			     "send WMI_SW_TX_REQ_CMDID for on-channel\n");
+		rc = wmi_mgmt_tx(vif, buf, len);
+		goto out;
+	}
+
+	if (params->offchan == 0) {
+		wil_err(wil,
+			"invalid channel params: current %d requested %d, off-channel not allowed\n",
+			vif->channel, params->chan->hw_value);
+		return -EBUSY;
+	}
+
+	/* use the wmi_mgmt_tx_ext only on AP mode and off-channel */
+	rc = wmi_mgmt_tx_ext(vif, buf, len, params->chan->hw_value,
+			     params->wait);
+
+out:
+	tx_status = (rc == 0);
 	cfg80211_mgmt_tx_status(wdev, cookie ? *cookie : 0, buf, len,
 				tx_status, GFP_KERNEL);
+
 	return rc;
 }
 
@@ -1726,7 +1760,7 @@ static int wil_cfg80211_change_station(struct wiphy *wiphy,
 	struct wil6210_priv *wil = wiphy_to_wil(wiphy);
 	int authorize;
 	int cid, i;
-	struct vring_tx_data *txdata = NULL;
+	struct wil_ring_tx_data *txdata = NULL;
 
 	wil_dbg_misc(wil, "change station %pM mask 0x%x set 0x%x mid %d\n",
 		     mac, params->sta_flags_mask, params->sta_flags_set,
@@ -1746,20 +1780,20 @@ static int wil_cfg80211_change_station(struct wiphy *wiphy,
 		return -ENOLINK;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(wil->vring2cid_tid); i++)
-		if (wil->vring2cid_tid[i][0] == cid) {
-			txdata = &wil->vring_tx_data[i];
+	for (i = 0; i < ARRAY_SIZE(wil->ring2cid_tid); i++)
+		if (wil->ring2cid_tid[i][0] == cid) {
+			txdata = &wil->ring_tx_data[i];
 			break;
 		}
 
 	if (!txdata) {
-		wil_err(wil, "vring data not found\n");
+		wil_err(wil, "ring data not found\n");
 		return -ENOLINK;
 	}
 
 	authorize = params->sta_flags_set & BIT(NL80211_STA_FLAG_AUTHORIZED);
 	txdata->dot1x_open = authorize ? 1 : 0;
-	wil_dbg_misc(wil, "cid %d vring %d authorize %d\n", cid, i,
+	wil_dbg_misc(wil, "cid %d ring %d authorize %d\n", cid, i,
 		     txdata->dot1x_open);
 
 	return 0;
diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index ebfdff4d328c..51c3330bc316 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -29,7 +29,10 @@
 /* Nasty hack. Better have per device instances */
 static u32 mem_addr;
 static u32 dbg_txdesc_index;
-static u32 dbg_vring_index; /* 24+ for Rx, 0..23 for Tx */
+static u32 dbg_ring_index; /* 24+ for Rx, 0..23 for Tx */
+static u32 dbg_status_msg_index;
+/* 0..wil->num_rx_status_rings-1 for Rx, wil->tx_sring_idx for Tx */
+static u32 dbg_sring_index;
 
 enum dbg_off_type {
 	doff_u32 = 0,
@@ -47,20 +50,53 @@ struct dbg_off {
 	enum dbg_off_type type;
 };
 
-static void wil_print_vring(struct seq_file *s, struct wil6210_priv *wil,
-			    const char *name, struct vring *vring,
-			    char _s, char _h)
+static void wil_print_desc_edma(struct seq_file *s, struct wil6210_priv *wil,
+				struct wil_ring *ring,
+				char _s, char _h, int idx)
 {
-	void __iomem *x = wmi_addr(wil, vring->hwtail);
+	u8 num_of_descs;
+	bool has_skb = false;
+
+	if (ring->is_rx) {
+		struct wil_rx_enhanced_desc *rx_d =
+			(struct wil_rx_enhanced_desc *)
+			&ring->va[idx].rx.enhanced;
+		u16 buff_id = le16_to_cpu(rx_d->mac.buff_id);
+
+		has_skb = wil->rx_buff_mgmt.buff_arr[buff_id].skb;
+		seq_printf(s, "%c", (has_skb) ? _h : _s);
+	} else {
+		struct wil_tx_enhanced_desc *d =
+			(struct wil_tx_enhanced_desc *)
+			&ring->va[idx].tx.enhanced;
+
+		num_of_descs = (u8)d->mac.d[2];
+		has_skb = ring->ctx[idx].skb;
+		if (num_of_descs >= 1)
+			seq_printf(s, "%c", ring->ctx[idx].skb ? _h : _s);
+		else
+			/* num_of_descs == 0, it's a frag in a list of descs */
+			seq_printf(s, "%c", has_skb ? 'h' : _s);
+	}
+}
+
+static void wil_print_ring(struct seq_file *s, struct wil6210_priv *wil,
+			   const char *name, struct wil_ring *ring,
+			   char _s, char _h)
+{
+	void __iomem *x = wmi_addr(wil, ring->hwtail);
 	u32 v;
 
-	seq_printf(s, "VRING %s = {\n", name);
-	seq_printf(s, "  pa     = %pad\n", &vring->pa);
-	seq_printf(s, "  va     = 0x%p\n", vring->va);
-	seq_printf(s, "  size   = %d\n", vring->size);
-	seq_printf(s, "  swtail = %d\n", vring->swtail);
-	seq_printf(s, "  swhead = %d\n", vring->swhead);
-	seq_printf(s, "  hwtail = [0x%08x] -> ", vring->hwtail);
+	seq_printf(s, "RING %s = {\n", name);
+	seq_printf(s, "  pa     = %pad\n", &ring->pa);
+	seq_printf(s, "  va     = 0x%p\n", ring->va);
+	seq_printf(s, "  size   = %d\n", ring->size);
+	if (wil->use_enhanced_dma_hw && ring->is_rx)
+		seq_printf(s, "  swtail = %u\n", *ring->edma_rx_swtail.va);
+	else
+		seq_printf(s, "  swtail = %d\n", ring->swtail);
+	seq_printf(s, "  swhead = %d\n", ring->swhead);
+	seq_printf(s, "  hwtail = [0x%08x] -> ", ring->hwtail);
 	if (x) {
 		v = readl(x);
 		seq_printf(s, "0x%08x = %d\n", v, v);
@@ -68,41 +104,45 @@ static void wil_print_vring(struct seq_file *s, struct wil6210_priv *wil,
 		seq_puts(s, "???\n");
 	}
 
-	if (vring->va && (vring->size <= (1 << WIL_RING_SIZE_ORDER_MAX))) {
+	if (ring->va && (ring->size <= (1 << WIL_RING_SIZE_ORDER_MAX))) {
 		uint i;
 
-		for (i = 0; i < vring->size; i++) {
-			volatile struct vring_tx_desc *d = &vring->va[i].tx;
-
-			if ((i % 128) == 0 && (i != 0))
+		for (i = 0; i < ring->size; i++) {
+			if ((i % 128) == 0 && i != 0)
 				seq_puts(s, "\n");
-			seq_printf(s, "%c", (d->dma.status & BIT(0)) ?
-					_s : (vring->ctx[i].skb ? _h : 'h'));
+			if (wil->use_enhanced_dma_hw) {
+				wil_print_desc_edma(s, wil, ring, _s, _h, i);
+			} else {
+				volatile struct vring_tx_desc *d =
+					&ring->va[i].tx.legacy;
+				seq_printf(s, "%c", (d->dma.status & BIT(0)) ?
+					   _s : (ring->ctx[i].skb ? _h : 'h'));
+			}
 		}
 		seq_puts(s, "\n");
 	}
 	seq_puts(s, "}\n");
 }
 
-static int wil_vring_debugfs_show(struct seq_file *s, void *data)
+static int wil_ring_debugfs_show(struct seq_file *s, void *data)
 {
 	uint i;
 	struct wil6210_priv *wil = s->private;
 
-	wil_print_vring(s, wil, "rx", &wil->vring_rx, 'S', '_');
+	wil_print_ring(s, wil, "rx", &wil->ring_rx, 'S', '_');
 
-	for (i = 0; i < ARRAY_SIZE(wil->vring_tx); i++) {
-		struct vring *vring = &wil->vring_tx[i];
-		struct vring_tx_data *txdata = &wil->vring_tx_data[i];
+	for (i = 0; i < ARRAY_SIZE(wil->ring_tx); i++) {
+		struct wil_ring *ring = &wil->ring_tx[i];
+		struct wil_ring_tx_data *txdata = &wil->ring_tx_data[i];
 
-		if (vring->va) {
-			int cid = wil->vring2cid_tid[i][0];
-			int tid = wil->vring2cid_tid[i][1];
-			u32 swhead = vring->swhead;
-			u32 swtail = vring->swtail;
-			int used = (vring->size + swhead - swtail)
-				   % vring->size;
-			int avail = vring->size - used - 1;
+		if (ring->va) {
+			int cid = wil->ring2cid_tid[i][0];
+			int tid = wil->ring2cid_tid[i][1];
+			u32 swhead = ring->swhead;
+			u32 swtail = ring->swtail;
+			int used = (ring->size + swhead - swtail)
+				   % ring->size;
+			int avail = ring->size - used - 1;
 			char name[10];
 			char sidle[10];
 			/* performance monitoring */
@@ -137,20 +177,88 @@ static int wil_vring_debugfs_show(struct seq_file *s, void *data)
 					   txdata->dot1x_open ? "+" : "-",
 					   used, avail, sidle);
 
-			wil_print_vring(s, wil, name, vring, '_', 'H');
+			wil_print_ring(s, wil, name, ring, '_', 'H');
+		}
+	}
+
+	return 0;
+}
+
+static int wil_ring_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wil_ring_debugfs_show, inode->i_private);
+}
+
+static const struct file_operations fops_ring = {
+	.open		= wil_ring_seq_open,
+	.release	= single_release,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+};
+
+static void wil_print_sring(struct seq_file *s, struct wil6210_priv *wil,
+			    struct wil_status_ring *sring)
+{
+	void __iomem *x = wmi_addr(wil, sring->hwtail);
+	int sring_idx = sring - wil->srings;
+	u32 v;
+
+	seq_printf(s, "Status Ring %s [ %d ] = {\n",
+		   sring->is_rx ? "RX" : "TX", sring_idx);
+	seq_printf(s, "  pa     = %pad\n", &sring->pa);
+	seq_printf(s, "  va     = 0x%pK\n", sring->va);
+	seq_printf(s, "  size   = %d\n", sring->size);
+	seq_printf(s, "  elem_size   = %zu\n", sring->elem_size);
+	seq_printf(s, "  swhead = %d\n", sring->swhead);
+	seq_printf(s, "  hwtail = [0x%08x] -> ", sring->hwtail);
+	if (x) {
+		v = readl_relaxed(x);
+		seq_printf(s, "0x%08x = %d\n", v, v);
+	} else {
+		seq_puts(s, "???\n");
+	}
+	seq_printf(s, "  desc_rdy_pol   = %d\n", sring->desc_rdy_pol);
+
+	if (sring->va && (sring->size <= (1 << WIL_RING_SIZE_ORDER_MAX))) {
+		uint i;
+
+		for (i = 0; i < sring->size; i++) {
+			u32 *sdword_0 =
+				(u32 *)(sring->va + (sring->elem_size * i));
+
+			if ((i % 128) == 0 && i != 0)
+				seq_puts(s, "\n");
+			if (i == sring->swhead)
+				seq_printf(s, "%c", (*sdword_0 & BIT(31)) ?
+					   'X' : 'x');
+			else
+				seq_printf(s, "%c", (*sdword_0 & BIT(31)) ?
+					   '1' : '0');
 		}
+		seq_puts(s, "\n");
 	}
+	seq_puts(s, "}\n");
+}
+
+static int wil_srings_debugfs_show(struct seq_file *s, void *data)
+{
+	struct wil6210_priv *wil = s->private;
+	int i = 0;
+
+	for (i = 0; i < WIL6210_MAX_STATUS_RINGS; i++)
+		if (wil->srings[i].va)
+			wil_print_sring(s, wil, &wil->srings[i]);
 
 	return 0;
 }
 
-static int wil_vring_seq_open(struct inode *inode, struct file *file)
+static int wil_srings_seq_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, wil_vring_debugfs_show, inode->i_private);
+	return single_open(file, wil_srings_debugfs_show, inode->i_private);
 }
 
-static const struct file_operations fops_vring = {
-	.open		= wil_vring_seq_open,
+static const struct file_operations fops_srings = {
+	.open		= wil_srings_seq_open,
 	.release	= single_release,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
@@ -162,8 +270,8 @@ static void wil_seq_hexdump(struct seq_file *s, void *p, int len,
 	seq_hex_dump(s, prefix, DUMP_PREFIX_NONE, 16, 1, p, len, false);
 }
 
-static void wil_print_ring(struct seq_file *s, const char *prefix,
-			   void __iomem *off)
+static void wil_print_mbox_ring(struct seq_file *s, const char *prefix,
+				void __iomem *off)
 {
 	struct wil6210_priv *wil = s->private;
 	struct wil6210_mbox_ring r;
@@ -249,9 +357,9 @@ static int wil_mbox_debugfs_show(struct seq_file *s, void *data)
 	if (ret < 0)
 		return ret;
 
-	wil_print_ring(s, "tx", wil->csr + HOST_MBOX +
+	wil_print_mbox_ring(s, "tx", wil->csr + HOST_MBOX +
 		       offsetof(struct wil6210_mbox_ctl, tx));
-	wil_print_ring(s, "rx", wil->csr + HOST_MBOX +
+	wil_print_mbox_ring(s, "rx", wil->csr + HOST_MBOX +
 		       offsetof(struct wil6210_mbox_ctl, rx));
 
 	wil_pm_runtime_put(wil);
@@ -719,13 +827,13 @@ static ssize_t wil_write_back(struct file *file, const char __user *buf,
 
 	if ((strcmp(cmd, "add") == 0) ||
 	    (strcmp(cmd, "del_tx") == 0)) {
-		struct vring_tx_data *txdata;
+		struct wil_ring_tx_data *txdata;
 
 		if (p1 < 0 || p1 >= WIL6210_MAX_TX_RINGS) {
 			wil_err(wil, "BACK: invalid ring id %d\n", p1);
 			return -EINVAL;
 		}
-		txdata = &wil->vring_tx_data[p1];
+		txdata = &wil->ring_tx_data[p1];
 		if (strcmp(cmd, "add") == 0) {
 			if (rc < 3) {
 				wil_err(wil, "BACK: add require at least 2 params\n");
@@ -972,54 +1080,93 @@ static void wil_seq_print_skb(struct seq_file *s, struct sk_buff *skb)
 static int wil_txdesc_debugfs_show(struct seq_file *s, void *data)
 {
 	struct wil6210_priv *wil = s->private;
-	struct vring *vring;
-	bool tx = (dbg_vring_index < WIL6210_MAX_TX_RINGS);
+	struct wil_ring *ring;
+	bool tx;
+	int ring_idx = dbg_ring_index;
+	int txdesc_idx = dbg_txdesc_index;
+	volatile struct vring_tx_desc *d;
+	volatile u32 *u;
+	struct sk_buff *skb;
+
+	if (wil->use_enhanced_dma_hw) {
+		/* RX ring index == 0 */
+		if (ring_idx >= WIL6210_MAX_TX_RINGS) {
+			seq_printf(s, "invalid ring index %d\n", ring_idx);
+			return 0;
+		}
+		tx = ring_idx > 0; /* desc ring 0 is reserved for RX */
+	} else {
+		/* RX ring index == WIL6210_MAX_TX_RINGS */
+		if (ring_idx > WIL6210_MAX_TX_RINGS) {
+			seq_printf(s, "invalid ring index %d\n", ring_idx);
+			return 0;
+		}
+		tx = (ring_idx < WIL6210_MAX_TX_RINGS);
+	}
 
-	vring = tx ? &wil->vring_tx[dbg_vring_index] : &wil->vring_rx;
+	ring = tx ? &wil->ring_tx[ring_idx] : &wil->ring_rx;
 
-	if (!vring->va) {
+	if (!ring->va) {
 		if (tx)
-			seq_printf(s, "No Tx[%2d] VRING\n", dbg_vring_index);
+			seq_printf(s, "No Tx[%2d] RING\n", ring_idx);
 		else
-			seq_puts(s, "No Rx VRING\n");
+			seq_puts(s, "No Rx RING\n");
 		return 0;
 	}
 
-	if (dbg_txdesc_index < vring->size) {
-		/* use struct vring_tx_desc for Rx as well,
-		 * only field used, .dma.length, is the same
-		 */
-		volatile struct vring_tx_desc *d =
-				&vring->va[dbg_txdesc_index].tx;
-		volatile u32 *u = (volatile u32 *)d;
-		struct sk_buff *skb = vring->ctx[dbg_txdesc_index].skb;
-
+	if (txdesc_idx >= ring->size) {
 		if (tx)
-			seq_printf(s, "Tx[%2d][%3d] = {\n", dbg_vring_index,
-				   dbg_txdesc_index);
+			seq_printf(s, "[%2d] TxDesc index (%d) >= size (%d)\n",
+				   ring_idx, txdesc_idx, ring->size);
 		else
-			seq_printf(s, "Rx[%3d] = {\n", dbg_txdesc_index);
-		seq_printf(s, "  MAC = 0x%08x 0x%08x 0x%08x 0x%08x\n",
-			   u[0], u[1], u[2], u[3]);
-		seq_printf(s, "  DMA = 0x%08x 0x%08x 0x%08x 0x%08x\n",
-			   u[4], u[5], u[6], u[7]);
-		seq_printf(s, "  SKB = 0x%p\n", skb);
+			seq_printf(s, "RxDesc index (%d) >= size (%d)\n",
+				   txdesc_idx, ring->size);
+		return 0;
+	}
 
-		if (skb) {
-			skb_get(skb);
-			wil_seq_print_skb(s, skb);
-			kfree_skb(skb);
+	/* use struct vring_tx_desc for Rx as well,
+	 * only field used, .dma.length, is the same
+	 */
+	d = &ring->va[txdesc_idx].tx.legacy;
+	u = (volatile u32 *)d;
+	skb = NULL;
+
+	if (wil->use_enhanced_dma_hw) {
+		if (tx) {
+			skb = ring->ctx[txdesc_idx].skb;
+		} else {
+			struct wil_rx_enhanced_desc *rx_d =
+				(struct wil_rx_enhanced_desc *)
+				&ring->va[txdesc_idx].rx.enhanced;
+			u16 buff_id = le16_to_cpu(rx_d->mac.buff_id);
+
+			if (!wil_val_in_range(buff_id, 0,
+					      wil->rx_buff_mgmt.size)) {
+				seq_printf(s, "invalid buff_id %d\n", buff_id);
+				return 0;
+			}
+			skb = wil->rx_buff_mgmt.buff_arr[buff_id].skb;
 		}
-		seq_puts(s, "}\n");
 	} else {
-		if (tx)
-			seq_printf(s, "[%2d] TxDesc index (%d) >= size (%d)\n",
-				   dbg_vring_index, dbg_txdesc_index,
-				   vring->size);
-		else
-			seq_printf(s, "RxDesc index (%d) >= size (%d)\n",
-				   dbg_txdesc_index, vring->size);
+		skb = ring->ctx[txdesc_idx].skb;
 	}
+	if (tx)
+		seq_printf(s, "Tx[%2d][%3d] = {\n", ring_idx,
+			   txdesc_idx);
+	else
+		seq_printf(s, "Rx[%3d] = {\n", txdesc_idx);
+	seq_printf(s, "  MAC = 0x%08x 0x%08x 0x%08x 0x%08x\n",
+		   u[0], u[1], u[2], u[3]);
+	seq_printf(s, "  DMA = 0x%08x 0x%08x 0x%08x 0x%08x\n",
+		   u[4], u[5], u[6], u[7]);
+	seq_printf(s, "  SKB = 0x%p\n", skb);
+
+	if (skb) {
+		skb_get(skb);
+		wil_seq_print_skb(s, skb);
+		kfree_skb(skb);
+	}
+	seq_puts(s, "}\n");
 
 	return 0;
 }
@@ -1036,6 +1183,115 @@ static const struct file_operations fops_txdesc = {
 	.llseek		= seq_lseek,
 };
 
+/*---------Tx/Rx status message------------*/
+static int wil_status_msg_debugfs_show(struct seq_file *s, void *data)
+{
+	struct wil6210_priv *wil = s->private;
+	int sring_idx = dbg_sring_index;
+	struct wil_status_ring *sring;
+	bool tx = sring_idx == wil->tx_sring_idx ? 1 : 0;
+	u32 status_msg_idx = dbg_status_msg_index;
+	u32 *u;
+
+	if (sring_idx >= WIL6210_MAX_STATUS_RINGS) {
+		seq_printf(s, "invalid status ring index %d\n", sring_idx);
+		return 0;
+	}
+
+	sring = &wil->srings[sring_idx];
+
+	if (!sring->va) {
+		seq_printf(s, "No %cX status ring\n", tx ? 'T' : 'R');
+		return 0;
+	}
+
+	if (status_msg_idx >= sring->size) {
+		seq_printf(s, "%cxDesc index (%d) >= size (%d)\n",
+			   tx ? 'T' : 'R', status_msg_idx, sring->size);
+		return 0;
+	}
+
+	u = sring->va + (sring->elem_size * status_msg_idx);
+
+	seq_printf(s, "%cx[%d][%3d] = {\n",
+		   tx ? 'T' : 'R', sring_idx, status_msg_idx);
+
+	seq_printf(s, "  0x%08x 0x%08x 0x%08x 0x%08x\n",
+		   u[0], u[1], u[2], u[3]);
+	if (!tx && !wil->use_compressed_rx_status)
+		seq_printf(s, "  0x%08x 0x%08x 0x%08x 0x%08x\n",
+			   u[4], u[5], u[6], u[7]);
+
+	seq_puts(s, "}\n");
+
+	return 0;
+}
+
+static int wil_status_msg_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wil_status_msg_debugfs_show,
+			   inode->i_private);
+}
+
+static const struct file_operations fops_status_msg = {
+	.open		= wil_status_msg_seq_open,
+	.release	= single_release,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+};
+
+static int wil_print_rx_buff(struct seq_file *s, struct list_head *lh)
+{
+	struct wil_rx_buff *it;
+	int i = 0;
+
+	list_for_each_entry(it, lh, list) {
+		if ((i % 16) == 0 && i != 0)
+			seq_puts(s, "\n    ");
+		seq_printf(s, "[%4d] ", it->id);
+		i++;
+	}
+	seq_printf(s, "\nNumber of buffers: %u\n", i);
+
+	return i;
+}
+
+static int wil_rx_buff_mgmt_debugfs_show(struct seq_file *s, void *data)
+{
+	struct wil6210_priv *wil = s->private;
+	struct wil_rx_buff_mgmt *rbm = &wil->rx_buff_mgmt;
+	int num_active;
+	int num_free;
+
+	seq_printf(s, "  size = %zu\n", rbm->size);
+	seq_printf(s, "  free_list_empty_cnt = %lu\n",
+		   rbm->free_list_empty_cnt);
+
+	/* Print active list */
+	seq_puts(s, "  Active list:\n");
+	num_active = wil_print_rx_buff(s, &rbm->active);
+	seq_puts(s, "\n  Free list:\n");
+	num_free = wil_print_rx_buff(s, &rbm->free);
+
+	seq_printf(s, "  Total number of buffers: %u\n",
+		   num_active + num_free);
+
+	return 0;
+}
+
+static int wil_rx_buff_mgmt_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wil_rx_buff_mgmt_debugfs_show,
+			   inode->i_private);
+}
+
+static const struct file_operations fops_rx_buff_mgmt = {
+	.open		= wil_rx_buff_mgmt_seq_open,
+	.release	= single_release,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+};
+
 /*---------beamforming------------*/
 static char *wil_bfstatus_str(u32 status)
 {
@@ -1132,7 +1388,7 @@ static const struct file_operations fops_bf = {
 };
 
 /*---------temp------------*/
-static void print_temp(struct seq_file *s, const char *prefix, u32 t)
+static void print_temp(struct seq_file *s, const char *prefix, s32 t)
 {
 	switch (t) {
 	case 0:
@@ -1140,7 +1396,8 @@ static void print_temp(struct seq_file *s, const char *prefix, u32 t)
 		seq_printf(s, "%s N/A\n", prefix);
 	break;
 	default:
-		seq_printf(s, "%s %d.%03d\n", prefix, t / 1000, t % 1000);
+		seq_printf(s, "%s %s%d.%03d\n", prefix, (t < 0 ? "-" : ""),
+			   abs(t / 1000), abs(t % 1000));
 		break;
 	}
 }
@@ -1148,7 +1405,7 @@ static void print_temp(struct seq_file *s, const char *prefix, u32 t)
 static int wil_temp_debugfs_show(struct seq_file *s, void *data)
 {
 	struct wil6210_priv *wil = s->private;
-	u32 t_m, t_r;
+	s32 t_m, t_r;
 	int rc = wmi_get_temperature(wil, &t_m, &t_r);
 
 	if (rc) {
@@ -1384,6 +1641,7 @@ static void wil_print_rxtid(struct seq_file *s, struct wil_tid_ampdu_rx *r)
 	int i;
 	u16 index = ((r->head_seq_num - r->ssn) & 0xfff) % r->buf_size;
 	unsigned long long drop_dup = r->drop_dup, drop_old = r->drop_old;
+	unsigned long long drop_dup_mcast = r->drop_dup_mcast;
 
 	seq_printf(s, "([%2d]) 0x%03x [", r->buf_size, r->head_seq_num);
 	for (i = 0; i < r->buf_size; i++) {
@@ -1393,9 +1651,9 @@ static void wil_print_rxtid(struct seq_file *s, struct wil_tid_ampdu_rx *r)
 			seq_printf(s, "%c", r->reorder_buf[i] ? '*' : '_');
 	}
 	seq_printf(s,
-		   "] total %llu drop %llu (dup %llu + old %llu) last 0x%03x\n",
-		   r->total, drop_dup + drop_old, drop_dup, drop_old,
-		   r->ssn_last_drop);
+		   "] total %llu drop %llu (dup %llu + old %llu + dup mcast %llu) last 0x%03x\n",
+		   r->total, drop_dup + drop_old + drop_dup_mcast, drop_dup,
+		   drop_old, drop_dup_mcast, r->ssn_last_drop);
 }
 
 static void wil_print_rxtid_crypto(struct seq_file *s, int tid,
@@ -1477,6 +1735,12 @@ __acquires(&p->tid_rx_lock) __releases(&p->tid_rx_lock)
 				   p->stats.rx_short_frame,
 				   p->stats.rx_large_frame,
 				   p->stats.rx_replay);
+			seq_printf(s,
+				   "mic error %lu, key error %lu, amsdu error %lu, csum error %lu\n",
+				   p->stats.rx_mic_error,
+				   p->stats.rx_key_error,
+				   p->stats.rx_amsdu_error,
+				   p->stats.rx_csum_err);
 
 			seq_puts(s, "Rx/MCS:");
 			for (mcs = 0; mcs < ARRAY_SIZE(p->stats.rx_per_mcs);
@@ -1538,6 +1802,343 @@ static const struct file_operations fops_mids = {
 	.llseek		= seq_lseek,
 };
 
+static int wil_tx_latency_debugfs_show(struct seq_file *s, void *data)
+__acquires(&p->tid_rx_lock) __releases(&p->tid_rx_lock)
+{
+	struct wil6210_priv *wil = s->private;
+	int i, bin;
+
+	for (i = 0; i < ARRAY_SIZE(wil->sta); i++) {
+		struct wil_sta_info *p = &wil->sta[i];
+		char *status = "unknown";
+		u8 aid = 0;
+		u8 mid;
+
+		if (!p->tx_latency_bins)
+			continue;
+
+		switch (p->status) {
+		case wil_sta_unused:
+			status = "unused   ";
+			break;
+		case wil_sta_conn_pending:
+			status = "pending  ";
+			break;
+		case wil_sta_connected:
+			status = "connected";
+			aid = p->aid;
+			break;
+		}
+		mid = (p->status != wil_sta_unused) ? p->mid : U8_MAX;
+		seq_printf(s, "[%d] %pM %s MID %d AID %d\n", i, p->addr, status,
+			   mid, aid);
+
+		if (p->status == wil_sta_connected) {
+			u64 num_packets = 0;
+			u64 tx_latency_avg = p->stats.tx_latency_total_us;
+
+			seq_puts(s, "Tx/Latency bin:");
+			for (bin = 0; bin < WIL_NUM_LATENCY_BINS; bin++) {
+				seq_printf(s, " %lld",
+					   p->tx_latency_bins[bin]);
+				num_packets += p->tx_latency_bins[bin];
+			}
+			seq_puts(s, "\n");
+			if (!num_packets)
+				continue;
+			do_div(tx_latency_avg, num_packets);
+			seq_printf(s, "Tx/Latency min/avg/max (us): %d/%lld/%d",
+				   p->stats.tx_latency_min_us,
+				   tx_latency_avg,
+				   p->stats.tx_latency_max_us);
+
+			seq_puts(s, "\n");
+		}
+	}
+
+	return 0;
+}
+
+static int wil_tx_latency_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wil_tx_latency_debugfs_show,
+			   inode->i_private);
+}
+
+static ssize_t wil_tx_latency_write(struct file *file, const char __user *buf,
+				    size_t len, loff_t *ppos)
+{
+	struct seq_file *s = file->private_data;
+	struct wil6210_priv *wil = s->private;
+	int val, rc, i;
+	bool enable;
+
+	rc = kstrtoint_from_user(buf, len, 0, &val);
+	if (rc) {
+		wil_err(wil, "Invalid argument\n");
+		return rc;
+	}
+	if (val == 1)
+		/* default resolution */
+		val = 500;
+	if (val && (val < 50 || val > 1000)) {
+		wil_err(wil, "Invalid resolution %d\n", val);
+		return -EINVAL;
+	}
+
+	enable = !!val;
+	if (wil->tx_latency == enable)
+		return len;
+
+	wil_info(wil, "%s TX latency measurements (resolution %dusec)\n",
+		 enable ? "Enabling" : "Disabling", val);
+
+	if (enable) {
+		size_t sz = sizeof(u64) * WIL_NUM_LATENCY_BINS;
+
+		wil->tx_latency_res = val;
+		for (i = 0; i < ARRAY_SIZE(wil->sta); i++) {
+			struct wil_sta_info *sta = &wil->sta[i];
+
+			kfree(sta->tx_latency_bins);
+			sta->tx_latency_bins = kzalloc(sz, GFP_KERNEL);
+			if (!sta->tx_latency_bins)
+				return -ENOMEM;
+			sta->stats.tx_latency_min_us = U32_MAX;
+			sta->stats.tx_latency_max_us = 0;
+			sta->stats.tx_latency_total_us = 0;
+		}
+	}
+	wil->tx_latency = enable;
+
+	return len;
+}
+
+static const struct file_operations fops_tx_latency = {
+	.open		= wil_tx_latency_seq_open,
+	.release	= single_release,
+	.read		= seq_read,
+	.write		= wil_tx_latency_write,
+	.llseek		= seq_lseek,
+};
+
+static void wil_link_stats_print_basic(struct wil6210_vif *vif,
+				       struct seq_file *s,
+				       struct wmi_link_stats_basic *basic)
+{
+	char per[5] = "?";
+
+	if (basic->per_average != 0xff)
+		snprintf(per, sizeof(per), "%d%%", basic->per_average);
+
+	seq_printf(s, "CID %d {\n"
+		   "\tTxMCS %d TxTpt %d\n"
+		   "\tGoodput(rx:tx) %d:%d\n"
+		   "\tRxBcastFrames %d\n"
+		   "\tRSSI %d SQI %d SNR %d PER %s\n"
+		   "\tRx RFC %d Ant num %d\n"
+		   "\tSectors(rx:tx) my %d:%d peer %d:%d\n"
+		   "}\n",
+		   basic->cid,
+		   basic->bf_mcs, le32_to_cpu(basic->tx_tpt),
+		   le32_to_cpu(basic->rx_goodput),
+		   le32_to_cpu(basic->tx_goodput),
+		   le32_to_cpu(basic->rx_bcast_frames),
+		   basic->rssi, basic->sqi, basic->snr, per,
+		   basic->selected_rfc, basic->rx_effective_ant_num,
+		   basic->my_rx_sector, basic->my_tx_sector,
+		   basic->other_rx_sector, basic->other_tx_sector);
+}
+
+static void wil_link_stats_print_global(struct wil6210_priv *wil,
+					struct seq_file *s,
+					struct wmi_link_stats_global *global)
+{
+	seq_printf(s, "Frames(rx:tx) %d:%d\n"
+		   "BA Frames(rx:tx) %d:%d\n"
+		   "Beacons %d\n"
+		   "Rx Errors (MIC:CRC) %d:%d\n"
+		   "Tx Errors (no ack) %d\n",
+		   le32_to_cpu(global->rx_frames),
+		   le32_to_cpu(global->tx_frames),
+		   le32_to_cpu(global->rx_ba_frames),
+		   le32_to_cpu(global->tx_ba_frames),
+		   le32_to_cpu(global->tx_beacons),
+		   le32_to_cpu(global->rx_mic_errors),
+		   le32_to_cpu(global->rx_crc_errors),
+		   le32_to_cpu(global->tx_fail_no_ack));
+}
+
+static void wil_link_stats_debugfs_show_vif(struct wil6210_vif *vif,
+					    struct seq_file *s)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	struct wmi_link_stats_basic *stats;
+	int i;
+
+	if (!vif->fw_stats_ready) {
+		seq_puts(s, "no statistics\n");
+		return;
+	}
+
+	seq_printf(s, "TSF %lld\n", vif->fw_stats_tsf);
+	for (i = 0; i < ARRAY_SIZE(wil->sta); i++) {
+		if (wil->sta[i].status == wil_sta_unused)
+			continue;
+		if (wil->sta[i].mid != vif->mid)
+			continue;
+
+		stats = &wil->sta[i].fw_stats_basic;
+		wil_link_stats_print_basic(vif, s, stats);
+	}
+}
+
+static int wil_link_stats_debugfs_show(struct seq_file *s, void *data)
+{
+	struct wil6210_priv *wil = s->private;
+	struct wil6210_vif *vif;
+	int i, rc;
+
+	rc = mutex_lock_interruptible(&wil->vif_mutex);
+	if (rc)
+		return rc;
+
+	/* iterate over all MIDs and show per-cid statistics. Then show the
+	 * global statistics
+	 */
+	for (i = 0; i < wil->max_vifs; i++) {
+		vif = wil->vifs[i];
+
+		seq_printf(s, "MID %d ", i);
+		if (!vif) {
+			seq_puts(s, "unused\n");
+			continue;
+		}
+
+		wil_link_stats_debugfs_show_vif(vif, s);
+	}
+
+	mutex_unlock(&wil->vif_mutex);
+
+	return 0;
+}
+
+static int wil_link_stats_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wil_link_stats_debugfs_show, inode->i_private);
+}
+
+static ssize_t wil_link_stats_write(struct file *file, const char __user *buf,
+				    size_t len, loff_t *ppos)
+{
+	struct seq_file *s = file->private_data;
+	struct wil6210_priv *wil = s->private;
+	int cid, interval, rc, i;
+	struct wil6210_vif *vif;
+	char *kbuf = kmalloc(len + 1, GFP_KERNEL);
+
+	if (!kbuf)
+		return -ENOMEM;
+
+	rc = simple_write_to_buffer(kbuf, len, ppos, buf, len);
+	if (rc != len) {
+		kfree(kbuf);
+		return rc >= 0 ? -EIO : rc;
+	}
+
+	kbuf[len] = '\0';
+	/* specify cid (use -1 for all cids) and snapshot interval in ms */
+	rc = sscanf(kbuf, "%d %d", &cid, &interval);
+	kfree(kbuf);
+	if (rc < 0)
+		return rc;
+	if (rc < 2 || interval < 0)
+		return -EINVAL;
+
+	wil_info(wil, "request link statistics, cid %d interval %d\n",
+		 cid, interval);
+
+	rc = mutex_lock_interruptible(&wil->vif_mutex);
+	if (rc)
+		return rc;
+
+	for (i = 0; i < wil->max_vifs; i++) {
+		vif = wil->vifs[i];
+		if (!vif)
+			continue;
+
+		rc = wmi_link_stats_cfg(vif, WMI_LINK_STATS_TYPE_BASIC,
+					(cid == -1 ? 0xff : cid), interval);
+		if (rc)
+			wil_err(wil, "link statistics failed for mid %d\n", i);
+	}
+	mutex_unlock(&wil->vif_mutex);
+
+	return len;
+}
+
+static const struct file_operations fops_link_stats = {
+	.open		= wil_link_stats_seq_open,
+	.release	= single_release,
+	.read		= seq_read,
+	.write		= wil_link_stats_write,
+	.llseek		= seq_lseek,
+};
+
+static int
+wil_link_stats_global_debugfs_show(struct seq_file *s, void *data)
+{
+	struct wil6210_priv *wil = s->private;
+
+	if (!wil->fw_stats_global.ready)
+		return 0;
+
+	seq_printf(s, "TSF %lld\n", wil->fw_stats_global.tsf);
+	wil_link_stats_print_global(wil, s, &wil->fw_stats_global.stats);
+
+	return 0;
+}
+
+static int
+wil_link_stats_global_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wil_link_stats_global_debugfs_show,
+			   inode->i_private);
+}
+
+static ssize_t
+wil_link_stats_global_write(struct file *file, const char __user *buf,
+			    size_t len, loff_t *ppos)
+{
+	struct seq_file *s = file->private_data;
+	struct wil6210_priv *wil = s->private;
+	int interval, rc;
+	struct wil6210_vif *vif = ndev_to_vif(wil->main_ndev);
+
+	/* specify snapshot interval in ms */
+	rc = kstrtoint_from_user(buf, len, 0, &interval);
+	if (rc || interval < 0) {
+		wil_err(wil, "Invalid argument\n");
+		return -EINVAL;
+	}
+
+	wil_info(wil, "request global link stats, interval %d\n", interval);
+
+	rc = wmi_link_stats_cfg(vif, WMI_LINK_STATS_TYPE_GLOBAL, 0, interval);
+	if (rc)
+		wil_err(wil, "global link stats failed %d\n", rc);
+
+	return rc ? rc : len;
+}
+
+static const struct file_operations fops_link_stats_global = {
+	.open		= wil_link_stats_global_seq_open,
+	.release	= single_release,
+	.read		= seq_read,
+	.write		= wil_link_stats_global_write,
+	.llseek		= seq_lseek,
+};
+
 static ssize_t wil_read_file_led_cfg(struct file *file, char __user *user_buf,
 				     size_t count, loff_t *ppos)
 {
@@ -1760,6 +2361,60 @@ static const struct file_operations fops_suspend_stats = {
 	.open  = simple_open,
 };
 
+/*---------compressed_rx_status---------*/
+static ssize_t wil_compressed_rx_status_write(struct file *file,
+					      const char __user *buf,
+					      size_t len, loff_t *ppos)
+{
+	struct seq_file *s = file->private_data;
+	struct wil6210_priv *wil = s->private;
+	int compressed_rx_status;
+	int rc;
+
+	rc = kstrtoint_from_user(buf, len, 0, &compressed_rx_status);
+	if (rc) {
+		wil_err(wil, "Invalid argument\n");
+		return rc;
+	}
+
+	if (wil_has_active_ifaces(wil, true, false)) {
+		wil_err(wil, "cannot change edma config after iface is up\n");
+		return -EPERM;
+	}
+
+	wil_info(wil, "%sable compressed_rx_status\n",
+		 compressed_rx_status ? "En" : "Dis");
+
+	wil->use_compressed_rx_status = compressed_rx_status;
+
+	return len;
+}
+
+static int
+wil_compressed_rx_status_show(struct seq_file *s, void *data)
+{
+	struct wil6210_priv *wil = s->private;
+
+	seq_printf(s, "%d\n", wil->use_compressed_rx_status);
+
+	return 0;
+}
+
+static int
+wil_compressed_rx_status_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wil_compressed_rx_status_show,
+			   inode->i_private);
+}
+
+static const struct file_operations fops_compressed_rx_status = {
+	.open  = wil_compressed_rx_status_seq_open,
+	.release = single_release,
+	.read = seq_read,
+	.write = wil_compressed_rx_status_write,
+	.llseek	= seq_lseek,
+};
+
 /*----------------*/
 static void wil6210_debugfs_init_blobs(struct wil6210_priv *wil,
 				       struct dentry *dbg)
@@ -1790,7 +2445,7 @@ static const struct {
 	const struct file_operations *fops;
 } dbg_files[] = {
 	{"mbox",	0444,		&fops_mbox},
-	{"vrings",	0444,		&fops_vring},
+	{"rings",	0444,		&fops_ring},
 	{"stations", 0444,		&fops_sta},
 	{"mids",	0444,		&fops_mids},
 	{"desc",	0444,		&fops_txdesc},
@@ -1813,6 +2468,13 @@ static const struct {
 	{"fw_capabilities",	0444,	&fops_fw_capabilities},
 	{"fw_version",	0444,		&fops_fw_version},
 	{"suspend_stats",	0644,	&fops_suspend_stats},
+	{"compressed_rx_status", 0644,	&fops_compressed_rx_status},
+	{"srings",	0444,		&fops_srings},
+	{"status_msg",	0444,		&fops_status_msg},
+	{"rx_buff_mgmt",	0444,	&fops_rx_buff_mgmt},
+	{"tx_latency",	0644,		&fops_tx_latency},
+	{"link_stats",	0644,		&fops_link_stats},
+	{"link_stats_global",	0644,	&fops_link_stats_global},
 };
 
 static void wil6210_debugfs_init_files(struct wil6210_priv *wil,
@@ -1858,7 +2520,12 @@ static const struct dbg_off dbg_wil_off[] = {
 	WIL_FIELD(chip_revision, 0444,	doff_u8),
 	WIL_FIELD(abft_len, 0644,		doff_u8),
 	WIL_FIELD(wakeup_trigger, 0644,		doff_u8),
-	WIL_FIELD(vring_idle_trsh, 0644,	doff_u32),
+	WIL_FIELD(ring_idle_trsh, 0644,	doff_u32),
+	WIL_FIELD(num_rx_status_rings, 0644,	doff_u8),
+	WIL_FIELD(rx_status_ring_order, 0644,	doff_u32),
+	WIL_FIELD(tx_status_ring_order, 0644,	doff_u32),
+	WIL_FIELD(rx_buff_id_count, 0644,	doff_u32),
+	WIL_FIELD(amsdu_en, 0644,	doff_u8),
 	{},
 };
 
@@ -1872,9 +2539,11 @@ static const struct dbg_off dbg_wil_regs[] = {
 /* static parameters */
 static const struct dbg_off dbg_statics[] = {
 	{"desc_index",	0644, (ulong)&dbg_txdesc_index, doff_u32},
-	{"vring_index",	0644, (ulong)&dbg_vring_index, doff_u32},
+	{"ring_index",	0644, (ulong)&dbg_ring_index, doff_u32},
 	{"mem_addr",	0644, (ulong)&mem_addr, doff_u32},
 	{"led_polarity", 0644, (ulong)&led_polarity, doff_u8},
+	{"status_index", 0644, (ulong)&dbg_status_msg_index, doff_u32},
+	{"sring_index",	0644, (ulong)&dbg_sring_index, doff_u32},
 	{},
 };
 
@@ -1922,10 +2591,14 @@ int wil6210_debugfs_init(struct wil6210_priv *wil)
 
 void wil6210_debugfs_remove(struct wil6210_priv *wil)
 {
+	int i;
+
 	debugfs_remove_recursive(wil->debug);
 	wil->debug = NULL;
 
 	kfree(wil->dbg_data.data_arr);
+	for (i = 0; i < ARRAY_SIZE(wil->sta); i++)
+		kfree(wil->sta[i].tx_latency_bins);
 
 	/* free pmc memory without sending command to fw, as it will
 	 * be reset on the way down anyway
diff --git a/drivers/net/wireless/ath/wil6210/ethtool.c b/drivers/net/wireless/ath/wil6210/ethtool.c
index e7ff41e623d2..a04c87ffd37b 100644
--- a/drivers/net/wireless/ath/wil6210/ethtool.c
+++ b/drivers/net/wireless/ath/wil6210/ethtool.c
@@ -101,7 +101,7 @@ static int wil_ethtoolops_set_coalesce(struct net_device *ndev,
 	if (ret < 0)
 		return ret;
 
-	wil_configure_interrupt_moderation(wil);
+	wil->txrx_ops.configure_interrupt_moderation(wil);
 
 	wil_pm_runtime_put(wil);
 
diff --git a/drivers/net/wireless/ath/wil6210/fw.c b/drivers/net/wireless/ath/wil6210/fw.c
index 540fc20984d8..3e2bbbceca06 100644
--- a/drivers/net/wireless/ath/wil6210/fw.c
+++ b/drivers/net/wireless/ath/wil6210/fw.c
@@ -1,5 +1,6 @@
 /*
  * Copyright (c) 2014-2015,2017 Qualcomm Atheros, Inc.
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
  *
  * Permission to use, copy, modify, and/or distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above
@@ -22,6 +23,8 @@
 MODULE_FIRMWARE(WIL_FW_NAME_DEFAULT);
 MODULE_FIRMWARE(WIL_FW_NAME_SPARROW_PLUS);
 MODULE_FIRMWARE(WIL_BOARD_FILE_NAME);
+MODULE_FIRMWARE(WIL_FW_NAME_TALYN);
+MODULE_FIRMWARE(WIL_BRD_NAME_TALYN);
 
 static
 void wil_memset_toio_32(volatile void __iomem *dst, u32 val,
diff --git a/drivers/net/wireless/ath/wil6210/fw_inc.c b/drivers/net/wireless/ath/wil6210/fw_inc.c
index 718161b829c2..388b3d4717ca 100644
--- a/drivers/net/wireless/ath/wil6210/fw_inc.c
+++ b/drivers/net/wireless/ath/wil6210/fw_inc.c
@@ -145,7 +145,7 @@ fw_handle_capabilities(struct wil6210_priv *wil, const void *data,
 				    capabilities);
 	bitmap_zero(wil->fw_capabilities, WMI_FW_CAPABILITY_MAX);
 	memcpy(wil->fw_capabilities, rec->capabilities,
-	       min(sizeof(wil->fw_capabilities), capa_size));
+	       min_t(size_t, sizeof(wil->fw_capabilities), capa_size));
 	wil_hex_dump_fw("CAPA", DUMP_PREFIX_OFFSET, 16, 1,
 			rec->capabilities, capa_size, false);
 	return 0;
diff --git a/drivers/net/wireless/ath/wil6210/interrupt.c b/drivers/net/wireless/ath/wil6210/interrupt.c
index 84e9840c1752..5d287a8e1b45 100644
--- a/drivers/net/wireless/ath/wil6210/interrupt.c
+++ b/drivers/net/wireless/ath/wil6210/interrupt.c
@@ -44,6 +44,8 @@
 				    (~(BIT_DMA_EP_RX_ICR_RX_HTRSH)))
 #define WIL6210_IMC_TX		(BIT_DMA_EP_TX_ICR_TX_DONE | \
 				BIT_DMA_EP_TX_ICR_TX_DONE_N(0))
+#define WIL6210_IMC_TX_EDMA		BIT_TX_STATUS_IRQ
+#define WIL6210_IMC_RX_EDMA		BIT_RX_STATUS_IRQ
 #define WIL6210_IMC_MISC_NO_HALP	(ISR_MISC_FW_READY | \
 					 ISR_MISC_MBOX_EVT | \
 					 ISR_MISC_FW_ERROR)
@@ -87,12 +89,24 @@ static void wil6210_mask_irq_tx(struct wil6210_priv *wil)
 	      WIL6210_IRQ_DISABLE);
 }
 
+static void wil6210_mask_irq_tx_edma(struct wil6210_priv *wil)
+{
+	wil_w(wil, RGF_INT_GEN_TX_ICR + offsetof(struct RGF_ICR, IMS),
+	      WIL6210_IRQ_DISABLE);
+}
+
 static void wil6210_mask_irq_rx(struct wil6210_priv *wil)
 {
 	wil_w(wil, RGF_DMA_EP_RX_ICR + offsetof(struct RGF_ICR, IMS),
 	      WIL6210_IRQ_DISABLE);
 }
 
+static void wil6210_mask_irq_rx_edma(struct wil6210_priv *wil)
+{
+	wil_w(wil, RGF_INT_GEN_RX_ICR + offsetof(struct RGF_ICR, IMS),
+	      WIL6210_IRQ_DISABLE);
+}
+
 static void wil6210_mask_irq_misc(struct wil6210_priv *wil, bool mask_halp)
 {
 	wil_dbg_irq(wil, "mask_irq_misc: mask_halp(%s)\n",
@@ -125,6 +139,12 @@ void wil6210_unmask_irq_tx(struct wil6210_priv *wil)
 	      WIL6210_IMC_TX);
 }
 
+void wil6210_unmask_irq_tx_edma(struct wil6210_priv *wil)
+{
+	wil_w(wil, RGF_INT_GEN_TX_ICR + offsetof(struct RGF_ICR, IMC),
+	      WIL6210_IMC_TX_EDMA);
+}
+
 void wil6210_unmask_irq_rx(struct wil6210_priv *wil)
 {
 	bool unmask_rx_htrsh = atomic_read(&wil->connected_vifs) > 0;
@@ -133,6 +153,12 @@ void wil6210_unmask_irq_rx(struct wil6210_priv *wil)
 	      unmask_rx_htrsh ? WIL6210_IMC_RX : WIL6210_IMC_RX_NO_RX_HTRSH);
 }
 
+void wil6210_unmask_irq_rx_edma(struct wil6210_priv *wil)
+{
+	wil_w(wil, RGF_INT_GEN_RX_ICR + offsetof(struct RGF_ICR, IMC),
+	      WIL6210_IMC_RX_EDMA);
+}
+
 static void wil6210_unmask_irq_misc(struct wil6210_priv *wil, bool unmask_halp)
 {
 	wil_dbg_irq(wil, "unmask_irq_misc: unmask_halp(%s)\n",
@@ -164,7 +190,9 @@ void wil_mask_irq(struct wil6210_priv *wil)
 	wil_dbg_irq(wil, "mask_irq\n");
 
 	wil6210_mask_irq_tx(wil);
+	wil6210_mask_irq_tx_edma(wil);
 	wil6210_mask_irq_rx(wil);
+	wil6210_mask_irq_rx_edma(wil);
 	wil6210_mask_irq_misc(wil, true);
 	wil6210_mask_irq_pseudo(wil);
 }
@@ -179,13 +207,43 @@ void wil_unmask_irq(struct wil6210_priv *wil)
 	      WIL_ICR_ICC_VALUE);
 	wil_w(wil, RGF_DMA_EP_MISC_ICR + offsetof(struct RGF_ICR, ICC),
 	      WIL_ICR_ICC_MISC_VALUE);
+	wil_w(wil, RGF_INT_GEN_TX_ICR + offsetof(struct RGF_ICR, ICC),
+	      WIL_ICR_ICC_VALUE);
+	wil_w(wil, RGF_INT_GEN_RX_ICR + offsetof(struct RGF_ICR, ICC),
+	      WIL_ICR_ICC_VALUE);
 
 	wil6210_unmask_irq_pseudo(wil);
-	wil6210_unmask_irq_tx(wil);
-	wil6210_unmask_irq_rx(wil);
+	if (wil->use_enhanced_dma_hw) {
+		wil6210_unmask_irq_tx_edma(wil);
+		wil6210_unmask_irq_rx_edma(wil);
+	} else {
+		wil6210_unmask_irq_tx(wil);
+		wil6210_unmask_irq_rx(wil);
+	}
 	wil6210_unmask_irq_misc(wil, true);
 }
 
+void wil_configure_interrupt_moderation_edma(struct wil6210_priv *wil)
+{
+	u32 moderation;
+
+	wil_s(wil, RGF_INT_GEN_IDLE_TIME_LIMIT, WIL_EDMA_IDLE_TIME_LIMIT_USEC);
+
+	wil_s(wil, RGF_INT_GEN_TIME_UNIT_LIMIT, WIL_EDMA_TIME_UNIT_CLK_CYCLES);
+
+	/* Update RX and TX moderation */
+	moderation = wil->rx_max_burst_duration |
+		(WIL_EDMA_AGG_WATERMARK << WIL_EDMA_AGG_WATERMARK_POS);
+	wil_w(wil, RGF_INT_CTRL_INT_GEN_CFG_0, moderation);
+	wil_w(wil, RGF_INT_CTRL_INT_GEN_CFG_1, moderation);
+
+	/* Treat special events as regular
+	 * (set bit 0 to 0x1 and clear bits 1-8)
+	 */
+	wil_c(wil, RGF_INT_COUNT_ON_SPECIAL_EVT, 0x1FE);
+	wil_s(wil, RGF_INT_COUNT_ON_SPECIAL_EVT, 0x1);
+}
+
 void wil_configure_interrupt_moderation(struct wil6210_priv *wil)
 {
 	struct wireless_dev *wdev = wil->main_ndev->ieee80211_ptr;
@@ -294,6 +352,97 @@ static irqreturn_t wil6210_irq_rx(int irq, void *cookie)
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t wil6210_irq_rx_edma(int irq, void *cookie)
+{
+	struct wil6210_priv *wil = cookie;
+	u32 isr = wil_ioread32_and_clear(wil->csr +
+					 HOSTADDR(RGF_INT_GEN_RX_ICR) +
+					 offsetof(struct RGF_ICR, ICR));
+	bool need_unmask = true;
+
+	trace_wil6210_irq_rx(isr);
+	wil_dbg_irq(wil, "ISR RX 0x%08x\n", isr);
+
+	if (unlikely(!isr)) {
+		wil_err(wil, "spurious IRQ: RX\n");
+		return IRQ_NONE;
+	}
+
+	wil6210_mask_irq_rx_edma(wil);
+
+	if (likely(isr & BIT_RX_STATUS_IRQ)) {
+		wil_dbg_irq(wil, "RX status ring\n");
+		isr &= ~BIT_RX_STATUS_IRQ;
+		if (likely(test_bit(wil_status_fwready, wil->status))) {
+			if (likely(test_bit(wil_status_napi_en, wil->status))) {
+				wil_dbg_txrx(wil, "NAPI(Rx) schedule\n");
+				need_unmask = false;
+				napi_schedule(&wil->napi_rx);
+			} else {
+				wil_err(wil,
+					"Got Rx interrupt while stopping interface\n");
+			}
+		} else {
+			wil_err(wil, "Got Rx interrupt while in reset\n");
+		}
+	}
+
+	if (unlikely(isr))
+		wil_err(wil, "un-handled RX ISR bits 0x%08x\n", isr);
+
+	/* Rx IRQ will be enabled when NAPI processing finished */
+
+	atomic_inc(&wil->isr_count_rx);
+
+	if (unlikely(need_unmask))
+		wil6210_unmask_irq_rx_edma(wil);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t wil6210_irq_tx_edma(int irq, void *cookie)
+{
+	struct wil6210_priv *wil = cookie;
+	u32 isr = wil_ioread32_and_clear(wil->csr +
+					 HOSTADDR(RGF_INT_GEN_TX_ICR) +
+					 offsetof(struct RGF_ICR, ICR));
+	bool need_unmask = true;
+
+	trace_wil6210_irq_tx(isr);
+	wil_dbg_irq(wil, "ISR TX 0x%08x\n", isr);
+
+	if (unlikely(!isr)) {
+		wil_err(wil, "spurious IRQ: TX\n");
+		return IRQ_NONE;
+	}
+
+	wil6210_mask_irq_tx_edma(wil);
+
+	if (likely(isr & BIT_TX_STATUS_IRQ)) {
+		wil_dbg_irq(wil, "TX status ring\n");
+		isr &= ~BIT_TX_STATUS_IRQ;
+		if (likely(test_bit(wil_status_fwready, wil->status))) {
+			wil_dbg_txrx(wil, "NAPI(Tx) schedule\n");
+			need_unmask = false;
+			napi_schedule(&wil->napi_tx);
+		} else {
+			wil_err(wil, "Got Tx status ring IRQ while in reset\n");
+		}
+	}
+
+	if (unlikely(isr))
+		wil_err(wil, "un-handled TX ISR bits 0x%08x\n", isr);
+
+	/* Tx IRQ will be enabled when NAPI processing finished */
+
+	atomic_inc(&wil->isr_count_tx);
+
+	if (unlikely(need_unmask))
+		wil6210_unmask_irq_tx_edma(wil);
+
+	return IRQ_HANDLED;
+}
+
 static irqreturn_t wil6210_irq_tx(int irq, void *cookie)
 {
 	struct wil6210_priv *wil = cookie;
@@ -476,6 +625,15 @@ static irqreturn_t wil6210_irq_misc_thread(int irq, void *cookie)
 
 	wil6210_unmask_irq_misc(wil, false);
 
+	/* in non-triple MSI case, this is done inside wil6210_thread_irq
+	 * because it has to be done after unmasking the pseudo.
+	 */
+	if (wil->n_msi == 3 && wil->suspend_resp_rcvd) {
+		wil_dbg_irq(wil, "set suspend_resp_comp to true\n");
+		wil->suspend_resp_comp = true;
+		wake_up_interruptible(&wil->wq);
+	}
+
 	return IRQ_HANDLED;
 }
 
@@ -510,30 +668,53 @@ static irqreturn_t wil6210_thread_irq(int irq, void *cookie)
  */
 static int wil6210_debug_irq_mask(struct wil6210_priv *wil, u32 pseudo_cause)
 {
+	u32 icm_rx, icr_rx, imv_rx;
+	u32 icm_tx, icr_tx, imv_tx;
+	u32 icm_misc, icr_misc, imv_misc;
+
 	if (!test_bit(wil_status_irqen, wil->status)) {
-		u32 icm_rx = wil_ioread32_and_clear(wil->csr +
-				HOSTADDR(RGF_DMA_EP_RX_ICR) +
-				offsetof(struct RGF_ICR, ICM));
-		u32 icr_rx = wil_ioread32_and_clear(wil->csr +
-				HOSTADDR(RGF_DMA_EP_RX_ICR) +
-				offsetof(struct RGF_ICR, ICR));
-		u32 imv_rx = wil_r(wil, RGF_DMA_EP_RX_ICR +
+		if (wil->use_enhanced_dma_hw) {
+			icm_rx = wil_ioread32_and_clear(wil->csr +
+					HOSTADDR(RGF_INT_GEN_RX_ICR) +
+					offsetof(struct RGF_ICR, ICM));
+			icr_rx = wil_ioread32_and_clear(wil->csr +
+					HOSTADDR(RGF_INT_GEN_RX_ICR) +
+					offsetof(struct RGF_ICR, ICR));
+			imv_rx = wil_r(wil, RGF_INT_GEN_RX_ICR +
 				   offsetof(struct RGF_ICR, IMV));
-		u32 icm_tx = wil_ioread32_and_clear(wil->csr +
-				HOSTADDR(RGF_DMA_EP_TX_ICR) +
-				offsetof(struct RGF_ICR, ICM));
-		u32 icr_tx = wil_ioread32_and_clear(wil->csr +
-				HOSTADDR(RGF_DMA_EP_TX_ICR) +
-				offsetof(struct RGF_ICR, ICR));
-		u32 imv_tx = wil_r(wil, RGF_DMA_EP_TX_ICR +
+			icm_tx = wil_ioread32_and_clear(wil->csr +
+					HOSTADDR(RGF_INT_GEN_TX_ICR) +
+					offsetof(struct RGF_ICR, ICM));
+			icr_tx = wil_ioread32_and_clear(wil->csr +
+					HOSTADDR(RGF_INT_GEN_TX_ICR) +
+					offsetof(struct RGF_ICR, ICR));
+			imv_tx = wil_r(wil, RGF_INT_GEN_TX_ICR +
+					   offsetof(struct RGF_ICR, IMV));
+		} else {
+			icm_rx = wil_ioread32_and_clear(wil->csr +
+					HOSTADDR(RGF_DMA_EP_RX_ICR) +
+					offsetof(struct RGF_ICR, ICM));
+			icr_rx = wil_ioread32_and_clear(wil->csr +
+					HOSTADDR(RGF_DMA_EP_RX_ICR) +
+					offsetof(struct RGF_ICR, ICR));
+			imv_rx = wil_r(wil, RGF_DMA_EP_RX_ICR +
 				   offsetof(struct RGF_ICR, IMV));
-		u32 icm_misc = wil_ioread32_and_clear(wil->csr +
+			icm_tx = wil_ioread32_and_clear(wil->csr +
+					HOSTADDR(RGF_DMA_EP_TX_ICR) +
+					offsetof(struct RGF_ICR, ICM));
+			icr_tx = wil_ioread32_and_clear(wil->csr +
+					HOSTADDR(RGF_DMA_EP_TX_ICR) +
+					offsetof(struct RGF_ICR, ICR));
+			imv_tx = wil_r(wil, RGF_DMA_EP_TX_ICR +
+					   offsetof(struct RGF_ICR, IMV));
+		}
+		icm_misc = wil_ioread32_and_clear(wil->csr +
 				HOSTADDR(RGF_DMA_EP_MISC_ICR) +
 				offsetof(struct RGF_ICR, ICM));
-		u32 icr_misc = wil_ioread32_and_clear(wil->csr +
+		icr_misc = wil_ioread32_and_clear(wil->csr +
 				HOSTADDR(RGF_DMA_EP_MISC_ICR) +
 				offsetof(struct RGF_ICR, ICR));
-		u32 imv_misc = wil_r(wil, RGF_DMA_EP_MISC_ICR +
+		imv_misc = wil_r(wil, RGF_DMA_EP_MISC_ICR +
 				     offsetof(struct RGF_ICR, IMV));
 
 		/* HALP interrupt can be unmasked when misc interrupts are
@@ -592,11 +773,11 @@ static irqreturn_t wil6210_hardirq(int irq, void *cookie)
 	 * voting for wake thread - need at least 1 vote
 	 */
 	if ((pseudo_cause & BIT_DMA_PSEUDO_CAUSE_RX) &&
-	    (wil6210_irq_rx(irq, cookie) == IRQ_WAKE_THREAD))
+	    (wil->txrx_ops.irq_rx(irq, cookie) == IRQ_WAKE_THREAD))
 		rc = IRQ_WAKE_THREAD;
 
 	if ((pseudo_cause & BIT_DMA_PSEUDO_CAUSE_TX) &&
-	    (wil6210_irq_tx(irq, cookie) == IRQ_WAKE_THREAD))
+	    (wil->txrx_ops.irq_tx(irq, cookie) == IRQ_WAKE_THREAD))
 		rc = IRQ_WAKE_THREAD;
 
 	if ((pseudo_cause & BIT_DMA_PSEUDO_CAUSE_MISC) &&
@@ -610,6 +791,40 @@ static irqreturn_t wil6210_hardirq(int irq, void *cookie)
 	return rc;
 }
 
+static int wil6210_request_3msi(struct wil6210_priv *wil, int irq)
+{
+	int rc;
+
+	/* IRQ's are in the following order:
+	 * - Tx
+	 * - Rx
+	 * - Misc
+	 */
+	rc = request_irq(irq, wil->txrx_ops.irq_tx, IRQF_SHARED,
+			 WIL_NAME "_tx", wil);
+	if (rc)
+		return rc;
+
+	rc = request_irq(irq + 1, wil->txrx_ops.irq_rx, IRQF_SHARED,
+			 WIL_NAME "_rx", wil);
+	if (rc)
+		goto free0;
+
+	rc = request_threaded_irq(irq + 2, wil6210_irq_misc,
+				  wil6210_irq_misc_thread,
+				  IRQF_SHARED, WIL_NAME "_misc", wil);
+	if (rc)
+		goto free1;
+
+	return 0;
+free1:
+	free_irq(irq + 1, wil);
+free0:
+	free_irq(irq, wil);
+
+	return rc;
+}
+
 /* can't use wil_ioread32_and_clear because ICC value is not set yet */
 static inline void wil_clear32(void __iomem *addr)
 {
@@ -624,6 +839,10 @@ void wil6210_clear_irq(struct wil6210_priv *wil)
 		    offsetof(struct RGF_ICR, ICR));
 	wil_clear32(wil->csr + HOSTADDR(RGF_DMA_EP_TX_ICR) +
 		    offsetof(struct RGF_ICR, ICR));
+	wil_clear32(wil->csr + HOSTADDR(RGF_INT_GEN_RX_ICR) +
+		    offsetof(struct RGF_ICR, ICR));
+	wil_clear32(wil->csr + HOSTADDR(RGF_INT_GEN_TX_ICR) +
+		    offsetof(struct RGF_ICR, ICR));
 	wil_clear32(wil->csr + HOSTADDR(RGF_DMA_EP_MISC_ICR) +
 		    offsetof(struct RGF_ICR, ICR));
 	wmb(); /* make sure write completed */
@@ -646,16 +865,28 @@ void wil6210_clear_halp(struct wil6210_priv *wil)
 	wil6210_unmask_halp(wil);
 }
 
-int wil6210_init_irq(struct wil6210_priv *wil, int irq, bool use_msi)
+int wil6210_init_irq(struct wil6210_priv *wil, int irq)
 {
 	int rc;
 
-	wil_dbg_misc(wil, "init_irq: %s\n", use_msi ? "MSI" : "INTx");
+	wil_dbg_misc(wil, "init_irq: %s, n_msi=%d\n",
+		     wil->n_msi ? "MSI" : "INTx", wil->n_msi);
 
-	rc = request_threaded_irq(irq, wil6210_hardirq,
-				  wil6210_thread_irq,
-				  use_msi ? 0 : IRQF_SHARED,
-				  WIL_NAME, wil);
+	if (wil->use_enhanced_dma_hw) {
+		wil->txrx_ops.irq_tx = wil6210_irq_tx_edma;
+		wil->txrx_ops.irq_rx = wil6210_irq_rx_edma;
+	} else {
+		wil->txrx_ops.irq_tx = wil6210_irq_tx;
+		wil->txrx_ops.irq_rx = wil6210_irq_rx;
+	}
+
+	if (wil->n_msi == 3)
+		rc = wil6210_request_3msi(wil, irq);
+	else
+		rc = request_threaded_irq(irq, wil6210_hardirq,
+					  wil6210_thread_irq,
+					  wil->n_msi ? 0 : IRQF_SHARED,
+					  WIL_NAME, wil);
 	return rc;
 }
 
@@ -665,4 +896,8 @@ void wil6210_fini_irq(struct wil6210_priv *wil, int irq)
 
 	wil_mask_irq(wil);
 	free_irq(irq, wil);
+	if (wil->n_msi == 3) {
+		free_irq(irq + 1, wil);
+		free_irq(irq + 2, wil);
+	}
 }
diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index e7006c2428a0..7debed6bec06 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -21,11 +21,14 @@
 
 #include "wil6210.h"
 #include "txrx.h"
+#include "txrx_edma.h"
 #include "wmi.h"
 #include "boot_loader.h"
 
 #define WAIT_FOR_HALP_VOTE_MS 100
 #define WAIT_FOR_SCAN_ABORT_MS 1000
+#define WIL_DEFAULT_NUM_RX_STATUS_RINGS 1
+#define WIL_BOARD_FILE_MAX_NAMELEN 128
 
 bool debug_fw; /* = false; */
 module_param(debug_fw, bool, 0444);
@@ -110,9 +113,29 @@ MODULE_PARM_DESC(tx_ring_order, " Tx ring order; size = 1 << order");
 module_param_cb(bcast_ring_order, &ring_order_ops, &bcast_ring_order, 0444);
 MODULE_PARM_DESC(bcast_ring_order, " Bcast ring order; size = 1 << order");
 
-#define RST_DELAY (20) /* msec, for loop in @wil_target_reset */
+enum {
+	WIL_BOOT_ERR,
+	WIL_BOOT_VANILLA,
+	WIL_BOOT_PRODUCTION,
+	WIL_BOOT_DEVELOPMENT,
+};
+
+enum {
+	WIL_SIG_STATUS_VANILLA = 0x0,
+	WIL_SIG_STATUS_DEVELOPMENT = 0x1,
+	WIL_SIG_STATUS_PRODUCTION = 0x2,
+	WIL_SIG_STATUS_CORRUPTED_PRODUCTION = 0x3,
+};
+
+#define RST_DELAY (20) /* msec, for loop in @wil_wait_device_ready */
 #define RST_COUNT (1 + 1000/RST_DELAY) /* round up to be above 1 sec total */
 
+#define PMU_READY_DELAY_MS (4) /* ms, for sleep in @wil_wait_device_ready */
+
+#define OTP_HW_DELAY (200) /* usec, loop in @wil_wait_device_ready_talyn_mb */
+/* round up to be above 2 ms total */
+#define OTP_HW_COUNT (1 + 2000 / OTP_HW_DELAY)
+
 /*
  * Due to a hardware issue,
  * one has to read/write to/from NIC in 32-bit chunks;
@@ -160,6 +183,37 @@ void wil_memcpy_toio_32(volatile void __iomem *dst, const void *src,
 	}
 }
 
+static void wil_ring_fini_tx(struct wil6210_priv *wil, int id)
+{
+	struct wil_ring *ring = &wil->ring_tx[id];
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[id];
+
+	lockdep_assert_held(&wil->mutex);
+
+	if (!ring->va)
+		return;
+
+	wil_dbg_misc(wil, "vring_fini_tx: id=%d\n", id);
+
+	spin_lock_bh(&txdata->lock);
+	txdata->dot1x_open = false;
+	txdata->mid = U8_MAX;
+	txdata->enabled = 0; /* no Tx can be in progress or start anew */
+	spin_unlock_bh(&txdata->lock);
+	/* napi_synchronize waits for completion of the current NAPI but will
+	 * not prevent the next NAPI run.
+	 * Add a memory barrier to guarantee that txdata->enabled is zeroed
+	 * before napi_synchronize so that the next scheduled NAPI will not
+	 * handle this vring
+	 */
+	wmb();
+	/* make sure NAPI won't touch this vring */
+	if (test_bit(wil_status_napi_en, wil->status))
+		napi_synchronize(&wil->napi_tx);
+
+	wil->txrx_ops.ring_fini_tx(wil, ring);
+}
+
 static void wil_disconnect_cid(struct wil6210_vif *vif, int cid,
 			       u16 reason_code, bool from_event)
 __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
@@ -219,12 +273,13 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 	memset(sta->tid_crypto_rx, 0, sizeof(sta->tid_crypto_rx));
 	memset(&sta->group_crypto_rx, 0, sizeof(sta->group_crypto_rx));
 	/* release vrings */
-	for (i = 0; i < ARRAY_SIZE(wil->vring_tx); i++) {
-		if (wil->vring2cid_tid[i][0] == cid)
-			wil_vring_fini_tx(wil, i);
+	for (i = 0; i < ARRAY_SIZE(wil->ring_tx); i++) {
+		if (wil->ring2cid_tid[i][0] == cid)
+			wil_ring_fini_tx(wil, i);
 	}
 	/* statistics */
 	memset(&sta->stats, 0, sizeof(sta->stats));
+	sta->stats.tx_latency_min_us = U32_MAX;
 }
 
 static bool wil_vif_is_connected(struct wil6210_priv *wil, u8 mid)
@@ -453,18 +508,19 @@ static void wil_fw_error_worker(struct work_struct *work)
 	mutex_unlock(&wil->mutex);
 }
 
-static int wil_find_free_vring(struct wil6210_priv *wil)
+static int wil_find_free_ring(struct wil6210_priv *wil)
 {
 	int i;
+	int min_ring_id = wil_get_min_tx_ring_id(wil);
 
-	for (i = 0; i < WIL6210_MAX_TX_RINGS; i++) {
-		if (!wil->vring_tx[i].va)
+	for (i = min_ring_id; i < WIL6210_MAX_TX_RINGS; i++) {
+		if (!wil->ring_tx[i].va)
 			return i;
 	}
 	return -EINVAL;
 }
 
-int wil_tx_init(struct wil6210_vif *vif, int cid)
+int wil_ring_init_tx(struct wil6210_vif *vif, int cid)
 {
 	struct wil6210_priv *wil = vif_to_wil(vif);
 	int rc = -EINVAL, ringid;
@@ -473,16 +529,17 @@ int wil_tx_init(struct wil6210_vif *vif, int cid)
 		wil_err(wil, "No connection pending\n");
 		goto out;
 	}
-	ringid = wil_find_free_vring(wil);
+	ringid = wil_find_free_ring(wil);
 	if (ringid < 0) {
 		wil_err(wil, "No free vring found\n");
 		goto out;
 	}
 
-	wil_dbg_wmi(wil, "Configure for connection CID %d MID %d vring %d\n",
+	wil_dbg_wmi(wil, "Configure for connection CID %d MID %d ring %d\n",
 		    cid, vif->mid, ringid);
 
-	rc = wil_vring_init_tx(vif, ringid, 1 << tx_ring_order, cid, 0);
+	rc = wil->txrx_ops.ring_init_tx(vif, ringid, 1 << tx_ring_order,
+					cid, 0);
 	if (rc)
 		wil_err(wil, "init TX for CID %d MID %d vring %d failed\n",
 			cid, vif->mid, ringid);
@@ -494,19 +551,19 @@ out:
 int wil_bcast_init(struct wil6210_vif *vif)
 {
 	struct wil6210_priv *wil = vif_to_wil(vif);
-	int ri = vif->bcast_vring, rc;
+	int ri = vif->bcast_ring, rc;
 
-	if ((ri >= 0) && wil->vring_tx[ri].va)
+	if (ri >= 0 && wil->ring_tx[ri].va)
 		return 0;
 
-	ri = wil_find_free_vring(wil);
+	ri = wil_find_free_ring(wil);
 	if (ri < 0)
 		return ri;
 
-	vif->bcast_vring = ri;
-	rc = wil_vring_init_bcast(vif, ri, 1 << bcast_ring_order);
+	vif->bcast_ring = ri;
+	rc = wil->txrx_ops.ring_init_bcast(vif, ri, 1 << bcast_ring_order);
 	if (rc)
-		vif->bcast_vring = -1;
+		vif->bcast_ring = -1;
 
 	return rc;
 }
@@ -514,13 +571,13 @@ int wil_bcast_init(struct wil6210_vif *vif)
 void wil_bcast_fini(struct wil6210_vif *vif)
 {
 	struct wil6210_priv *wil = vif_to_wil(vif);
-	int ri = vif->bcast_vring;
+	int ri = vif->bcast_ring;
 
 	if (ri < 0)
 		return;
 
-	vif->bcast_vring = -1;
-	wil_vring_fini_tx(wil, ri);
+	vif->bcast_ring = -1;
+	wil_ring_fini_tx(wil, ri);
 }
 
 void wil_bcast_fini_all(struct wil6210_priv *wil)
@@ -548,7 +605,7 @@ int wil_priv_init(struct wil6210_priv *wil)
 	}
 
 	for (i = 0; i < WIL6210_MAX_TX_RINGS; i++)
-		spin_lock_init(&wil->vring_tx_data[i].lock);
+		spin_lock_init(&wil->ring_tx_data[i].lock);
 
 	mutex_init(&wil->mutex);
 	mutex_init(&wil->vif_mutex);
@@ -589,11 +646,30 @@ int wil_priv_init(struct wil6210_priv *wil)
 	wil->wakeup_trigger = WMI_WAKEUP_TRIGGER_UCAST |
 			      WMI_WAKEUP_TRIGGER_BCAST;
 	memset(&wil->suspend_stats, 0, sizeof(wil->suspend_stats));
-	wil->vring_idle_trsh = 16;
+	wil->ring_idle_trsh = 16;
 
 	wil->reply_mid = U8_MAX;
 	wil->max_vifs = 1;
 
+	/* edma configuration can be updated via debugfs before allocation */
+	wil->num_rx_status_rings = WIL_DEFAULT_NUM_RX_STATUS_RINGS;
+	wil->use_compressed_rx_status = true;
+	wil->use_rx_hw_reordering = true;
+	wil->tx_status_ring_order = WIL_TX_SRING_SIZE_ORDER_DEFAULT;
+
+	/* Rx status ring size should be bigger than the number of RX buffers
+	 * in order to prevent backpressure on the status ring, which may
+	 * cause HW freeze.
+	 */
+	wil->rx_status_ring_order = WIL_RX_SRING_SIZE_ORDER_DEFAULT;
+	/* Number of RX buffer IDs should be bigger than the RX descriptor
+	 * ring size as in HW reorder flow, the HW can consume additional
+	 * buffers before releasing the previous ones.
+	 */
+	wil->rx_buff_id_count = WIL_RX_BUFF_ARR_SIZE_DEFAULT;
+
+	wil->amsdu_en = 1;
+
 	return 0;
 
 out_wmi_wq:
@@ -736,14 +812,24 @@ static void wil_bl_prepare_halt(struct wil6210_priv *wil)
 
 static inline void wil_halt_cpu(struct wil6210_priv *wil)
 {
-	wil_w(wil, RGF_USER_USER_CPU_0, BIT_USER_USER_CPU_MAN_RST);
-	wil_w(wil, RGF_USER_MAC_CPU_0,  BIT_USER_MAC_CPU_MAN_RST);
+	if (wil->hw_version >= HW_VER_TALYN_MB) {
+		wil_w(wil, RGF_USER_USER_CPU_0_TALYN_MB,
+		      BIT_USER_USER_CPU_MAN_RST);
+		wil_w(wil, RGF_USER_MAC_CPU_0_TALYN_MB,
+		      BIT_USER_MAC_CPU_MAN_RST);
+	} else {
+		wil_w(wil, RGF_USER_USER_CPU_0, BIT_USER_USER_CPU_MAN_RST);
+		wil_w(wil, RGF_USER_MAC_CPU_0,  BIT_USER_MAC_CPU_MAN_RST);
+	}
 }
 
 static inline void wil_release_cpu(struct wil6210_priv *wil)
 {
 	/* Start CPU */
-	wil_w(wil, RGF_USER_USER_CPU_0, 1);
+	if (wil->hw_version >= HW_VER_TALYN_MB)
+		wil_w(wil, RGF_USER_USER_CPU_0_TALYN_MB, 1);
+	else
+		wil_w(wil, RGF_USER_USER_CPU_0, 1);
 }
 
 static void wil_set_oob_mode(struct wil6210_priv *wil, u8 mode)
@@ -767,11 +853,146 @@ static void wil_set_oob_mode(struct wil6210_priv *wil, u8 mode)
 	}
 }
 
-static int wil_target_reset(struct wil6210_priv *wil, int no_flash)
+static int wil_wait_device_ready(struct wil6210_priv *wil, int no_flash)
 {
 	int delay = 0;
 	u32 x, x1 = 0;
 
+	/* wait until device ready. */
+	if (no_flash) {
+		msleep(PMU_READY_DELAY_MS);
+
+		wil_dbg_misc(wil, "Reset completed\n");
+	} else {
+		do {
+			msleep(RST_DELAY);
+			x = wil_r(wil, RGF_USER_BL +
+				  offsetof(struct bl_dedicated_registers_v0,
+					   boot_loader_ready));
+			if (x1 != x) {
+				wil_dbg_misc(wil, "BL.ready 0x%08x => 0x%08x\n",
+					     x1, x);
+				x1 = x;
+			}
+			if (delay++ > RST_COUNT) {
+				wil_err(wil, "Reset not completed, bl.ready 0x%08x\n",
+					x);
+				return -ETIME;
+			}
+		} while (x != BL_READY);
+
+		wil_dbg_misc(wil, "Reset completed in %d ms\n",
+			     delay * RST_DELAY);
+	}
+
+	return 0;
+}
+
+static int wil_wait_device_ready_talyn_mb(struct wil6210_priv *wil)
+{
+	u32 otp_hw;
+	u8 signature_status;
+	bool otp_signature_err;
+	bool hw_section_done;
+	u32 otp_qc_secured;
+	int delay = 0;
+
+	/* Wait for OTP signature test to complete */
+	usleep_range(2000, 2200);
+
+	wil->boot_config = WIL_BOOT_ERR;
+
+	/* Poll until OTP signature status is valid.
+	 * In vanilla and development modes, when signature test is complete
+	 * HW sets BIT_OTP_SIGNATURE_ERR_TALYN_MB.
+	 * In production mode BIT_OTP_SIGNATURE_ERR_TALYN_MB remains 0, poll
+	 * for signature status change to 2 or 3.
+	 */
+	do {
+		otp_hw = wil_r(wil, RGF_USER_OTP_HW_RD_MACHINE_1);
+		signature_status = WIL_GET_BITS(otp_hw, 8, 9);
+		otp_signature_err = otp_hw & BIT_OTP_SIGNATURE_ERR_TALYN_MB;
+
+		if (otp_signature_err &&
+		    signature_status == WIL_SIG_STATUS_VANILLA) {
+			wil->boot_config = WIL_BOOT_VANILLA;
+			break;
+		}
+		if (otp_signature_err &&
+		    signature_status == WIL_SIG_STATUS_DEVELOPMENT) {
+			wil->boot_config = WIL_BOOT_DEVELOPMENT;
+			break;
+		}
+		if (!otp_signature_err &&
+		    signature_status == WIL_SIG_STATUS_PRODUCTION) {
+			wil->boot_config = WIL_BOOT_PRODUCTION;
+			break;
+		}
+		if  (!otp_signature_err &&
+		     signature_status ==
+		     WIL_SIG_STATUS_CORRUPTED_PRODUCTION) {
+			/* Unrecognized OTP signature found. Possibly a
+			 * corrupted production signature, access control
+			 * is applied as in production mode, therefore
+			 * do not fail
+			 */
+			wil->boot_config = WIL_BOOT_PRODUCTION;
+			break;
+		}
+		if (delay++ > OTP_HW_COUNT)
+			break;
+
+		usleep_range(OTP_HW_DELAY, OTP_HW_DELAY + 10);
+	} while (!otp_signature_err && signature_status == 0);
+
+	if (wil->boot_config == WIL_BOOT_ERR) {
+		wil_err(wil,
+			"invalid boot config, signature_status %d otp_signature_err %d\n",
+			signature_status, otp_signature_err);
+		return -ETIME;
+	}
+
+	wil_dbg_misc(wil,
+		     "signature test done in %d usec, otp_hw 0x%x, boot_config %d\n",
+		     delay * OTP_HW_DELAY, otp_hw, wil->boot_config);
+
+	if (wil->boot_config == WIL_BOOT_VANILLA)
+		/* Assuming not SPI boot (currently not supported) */
+		goto out;
+
+	hw_section_done = otp_hw & BIT_OTP_HW_SECTION_DONE_TALYN_MB;
+	delay = 0;
+
+	while (!hw_section_done) {
+		msleep(RST_DELAY);
+
+		otp_hw = wil_r(wil, RGF_USER_OTP_HW_RD_MACHINE_1);
+		hw_section_done = otp_hw & BIT_OTP_HW_SECTION_DONE_TALYN_MB;
+
+		if (delay++ > RST_COUNT) {
+			wil_err(wil, "TO waiting for hw_section_done\n");
+			return -ETIME;
+		}
+	}
+
+	wil_dbg_misc(wil, "HW section done in %d ms\n", delay * RST_DELAY);
+
+	otp_qc_secured = wil_r(wil, RGF_OTP_QC_SECURED);
+	wil->secured_boot = otp_qc_secured & BIT_BOOT_FROM_ROM ? 1 : 0;
+	wil_dbg_misc(wil, "secured boot is %sabled\n",
+		     wil->secured_boot ? "en" : "dis");
+
+out:
+	wil_dbg_misc(wil, "Reset completed\n");
+
+	return 0;
+}
+
+static int wil_target_reset(struct wil6210_priv *wil, int no_flash)
+{
+	u32 x;
+	int rc;
+
 	wil_dbg_misc(wil, "Resetting \"%s\"...\n", wil->hw_name);
 
 	/* Clear MAC link up */
@@ -811,10 +1032,17 @@ static int wil_target_reset(struct wil6210_priv *wil, int no_flash)
 	wil_w(wil, RGF_USER_CLKS_CTL_EXT_SW_RST_VEC_0, 0x3ff81f);
 	wil_w(wil, RGF_USER_CLKS_CTL_EXT_SW_RST_VEC_1, 0xf);
 
-	wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_2, 0xFE000000);
-	wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_1, 0x0000003F);
-	wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_3, 0x000000f0);
-	wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_0, 0xFFE7FE00);
+	if (wil->hw_version >= HW_VER_TALYN_MB) {
+		wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_2, 0x7e000000);
+		wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_1, 0x0000003f);
+		wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_3, 0xc00000f0);
+		wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_0, 0xffe7fe00);
+	} else {
+		wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_2, 0xfe000000);
+		wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_1, 0x0000003f);
+		wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_3, 0x000000f0);
+		wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_0, 0xffe7fe00);
+	}
 
 	wil_w(wil, RGF_USER_CLKS_CTL_EXT_SW_RST_VEC_0, 0x0);
 	wil_w(wil, RGF_USER_CLKS_CTL_EXT_SW_RST_VEC_1, 0x0);
@@ -830,34 +1058,12 @@ static int wil_target_reset(struct wil6210_priv *wil, int no_flash)
 
 	wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_0, 0);
 
-	/* wait until device ready. typical time is 20..80 msec */
-	if (no_flash)
-		do {
-			msleep(RST_DELAY);
-			x = wil_r(wil, USER_EXT_USER_PMU_3);
-			if (delay++ > RST_COUNT) {
-				wil_err(wil, "Reset not completed, PMU_3 0x%08x\n",
-					x);
-				return -ETIME;
-			}
-		} while ((x & BIT_PMU_DEVICE_RDY) == 0);
+	if (wil->hw_version == HW_VER_TALYN_MB)
+		rc = wil_wait_device_ready_talyn_mb(wil);
 	else
-		do {
-			msleep(RST_DELAY);
-			x = wil_r(wil, RGF_USER_BL +
-				  offsetof(struct bl_dedicated_registers_v0,
-					   boot_loader_ready));
-			if (x1 != x) {
-				wil_dbg_misc(wil, "BL.ready 0x%08x => 0x%08x\n",
-					     x1, x);
-				x1 = x;
-			}
-			if (delay++ > RST_COUNT) {
-				wil_err(wil, "Reset not completed, bl.ready 0x%08x\n",
-					x);
-				return -ETIME;
-			}
-		} while (x != BL_READY);
+		rc = wil_wait_device_ready(wil, no_flash);
+	if (rc)
+		return rc;
 
 	wil_c(wil, RGF_USER_CLKS_CTL_0, BIT_USER_CLKS_RST_PWGD);
 
@@ -865,7 +1071,7 @@ static int wil_target_reset(struct wil6210_priv *wil, int no_flash)
 	wil_s(wil, RGF_DMA_OFUL_NID_0, BIT_DMA_OFUL_NID_0_RX_EXT_TR_EN |
 	      BIT_DMA_OFUL_NID_0_RX_EXT_A3_SRC);
 
-	if (no_flash) {
+	if (wil->hw_version < HW_VER_TALYN_MB && no_flash) {
 		/* Reset OTP HW vectors to fit 40MHz */
 		wil_w(wil, RGF_USER_XPM_IFC_RD_TIME1, 0x60001);
 		wil_w(wil, RGF_USER_XPM_IFC_RD_TIME2, 0x20027);
@@ -880,7 +1086,6 @@ static int wil_target_reset(struct wil6210_priv *wil, int no_flash)
 		wil_w(wil, RGF_USER_XPM_RD_DOUT_SAMPLE_TIME, 0x57);
 	}
 
-	wil_dbg_misc(wil, "Reset completed in %d ms\n", delay * RST_DELAY);
 	return 0;
 }
 
@@ -925,6 +1130,9 @@ void wil_refresh_fw_capabilities(struct wil6210_priv *wil)
 		wiphy->max_sched_scan_plans = WMI_MAX_PLANS_NUM;
 	}
 
+	if (test_bit(WMI_FW_CAPABILITY_TX_REQ_EXT, wil->fw_capabilities))
+		wiphy->flags |= WIPHY_FLAG_OFFCHAN_TX;
+
 	if (wil->platform_ops.set_features) {
 		features = (test_bit(WMI_FW_CAPABILITY_REF_CLOCK_CONTROL,
 				     wil->fw_capabilities) &&
@@ -932,8 +1140,20 @@ void wil_refresh_fw_capabilities(struct wil6210_priv *wil)
 				     wil->platform_capa)) ?
 			BIT(WIL_PLATFORM_FEATURE_FW_EXT_CLK_CONTROL) : 0;
 
+		if (wil->n_msi == 3)
+			features |= BIT(WIL_PLATFORM_FEATURE_TRIPLE_MSI);
+
 		wil->platform_ops.set_features(wil->platform_handle, features);
 	}
+
+	if (test_bit(WMI_FW_CAPABILITY_BACK_WIN_SIZE_64,
+		     wil->fw_capabilities)) {
+		wil->max_agg_wsize = WIL_MAX_AGG_WSIZE_64;
+		wil->max_ampdu_size = WIL_MAX_AMPDU_SIZE_128;
+	} else {
+		wil->max_agg_wsize = WIL_MAX_AGG_WSIZE;
+		wil->max_ampdu_size = WIL_MAX_AMPDU_SIZE;
+	}
 }
 
 void wil_mbox_ring_le2cpus(struct wil6210_mbox_ring *r)
@@ -945,6 +1165,28 @@ void wil_mbox_ring_le2cpus(struct wil6210_mbox_ring *r)
 	le32_to_cpus(&r->head);
 }
 
+/* construct actual board file name to use */
+void wil_get_board_file(struct wil6210_priv *wil, char *buf, size_t len)
+{
+	const char *board_file;
+	const char *wil_talyn_fw_name = ftm_mode ? WIL_FW_NAME_FTM_TALYN :
+			      WIL_FW_NAME_TALYN;
+
+	if (wil->board_file) {
+		board_file = wil->board_file;
+	} else {
+		/* If specific FW file is used for Talyn,
+		 * use specific board file
+		 */
+		if (strcmp(wil->wil_fw_name, wil_talyn_fw_name) == 0)
+			board_file = WIL_BRD_NAME_TALYN;
+		else
+			board_file = WIL_BOARD_FILE_NAME;
+	}
+
+	strlcpy(buf, board_file, len);
+}
+
 static int wil_get_bl_info(struct wil6210_priv *wil)
 {
 	struct net_device *ndev = wil->main_ndev;
@@ -1042,8 +1284,14 @@ static int wil_get_otp_info(struct wil6210_priv *wil)
 	struct net_device *ndev = wil->main_ndev;
 	struct wiphy *wiphy = wil_to_wiphy(wil);
 	u8 mac[8];
+	int mac_addr;
 
-	wil_memcpy_fromio_32(mac, wil->csr + HOSTADDR(RGF_OTP_MAC),
+	if (wil->hw_version >= HW_VER_TALYN_MB)
+		mac_addr = RGF_OTP_MAC_TALYN_MB;
+	else
+		mac_addr = RGF_OTP_MAC;
+
+	wil_memcpy_fromio_32(mac, wil->csr + HOSTADDR(mac_addr),
 			     sizeof(mac));
 	if (!is_valid_ether_addr(mac)) {
 		wil_err(wil, "Invalid MAC %pM\n", mac);
@@ -1060,7 +1308,7 @@ static int wil_get_otp_info(struct wil6210_priv *wil)
 
 static int wil_wait_for_fw_ready(struct wil6210_priv *wil)
 {
-	ulong to = msecs_to_jiffies(1000);
+	ulong to = msecs_to_jiffies(2000);
 	ulong left = wait_for_completion_timeout(&wil->wmi_ready, to);
 
 	if (0 == left) {
@@ -1147,8 +1395,13 @@ static void wil_pre_fw_config(struct wil6210_priv *wil)
 	/* it is W1C, clear by writing back same value */
 	wil_s(wil, RGF_CAF_ICR + offsetof(struct RGF_ICR, ICR), 0);
 	wil_w(wil, RGF_CAF_ICR + offsetof(struct RGF_ICR, IMV), ~0);
-	/* clear PAL_UNIT_ICR (potential D0->D3 leftover) */
-	wil_s(wil, RGF_PAL_UNIT_ICR + offsetof(struct RGF_ICR, ICR), 0);
+	/* clear PAL_UNIT_ICR (potential D0->D3 leftover)
+	 * In Talyn-MB host cannot access this register due to
+	 * access control, hence PAL_UNIT_ICR is cleared by the FW
+	 */
+	if (wil->hw_version < HW_VER_TALYN_MB)
+		wil_s(wil, RGF_PAL_UNIT_ICR + offsetof(struct RGF_ICR, ICR),
+		      0);
 
 	if (wil->fw_calib_result > 0) {
 		__le32 val = cpu_to_le32(wil->fw_calib_result |
@@ -1284,7 +1537,8 @@ int wil_reset(struct wil6210_priv *wil, bool load_fw)
 	rc = wil_target_reset(wil, no_flash);
 	wil6210_clear_irq(wil);
 	wil_enable_irq(wil);
-	wil_rx_fini(wil);
+	wil->txrx_ops.rx_fini(wil);
+	wil->txrx_ops.tx_fini(wil);
 	if (rc) {
 		if (!no_flash)
 			wil_bl_crash_info(wil, true);
@@ -1304,8 +1558,17 @@ int wil_reset(struct wil6210_priv *wil, bool load_fw)
 
 	wil_set_oob_mode(wil, oob_mode);
 	if (load_fw) {
+		char board_file[WIL_BOARD_FILE_MAX_NAMELEN];
+
+		if  (wil->secured_boot) {
+			wil_err(wil, "secured boot is not supported\n");
+			return -ENOTSUPP;
+		}
+
+		board_file[0] = '\0';
+		wil_get_board_file(wil, board_file, sizeof(board_file));
 		wil_info(wil, "Use firmware <%s> + board <%s>\n",
-			 wil->wil_fw_name, WIL_BOARD_FILE_NAME);
+			 wil->wil_fw_name, board_file);
 
 		if (!no_flash)
 			wil_bl_prepare_halt(wil);
@@ -1317,11 +1580,9 @@ int wil_reset(struct wil6210_priv *wil, bool load_fw)
 		if (rc)
 			goto out;
 		if (wil->brd_file_addr)
-			rc = wil_request_board(wil, WIL_BOARD_FILE_NAME);
+			rc = wil_request_board(wil, board_file);
 		else
-			rc = wil_request_firmware(wil,
-						  WIL_BOARD_FILE_NAME,
-						  true);
+			rc = wil_request_firmware(wil, board_file, true);
 		if (rc)
 			goto out;
 
@@ -1337,7 +1598,6 @@ int wil_reset(struct wil6210_priv *wil, bool load_fw)
 	clear_bit(wil_status_resetting, wil->status);
 
 	if (load_fw) {
-		wil_configure_interrupt_moderation(wil);
 		wil_unmask_irq(wil);
 
 		/* we just started MAC, wait for FW ready */
@@ -1352,6 +1612,15 @@ int wil_reset(struct wil6210_priv *wil, bool load_fw)
 			return rc;
 		}
 
+		wil->txrx_ops.configure_interrupt_moderation(wil);
+
+		/* Enable OFU rdy valid bug fix, to prevent hang in oful34_rx
+		 * while there is back-pressure from Host during RX
+		 */
+		if (wil->hw_version >= HW_VER_TALYN_MB)
+			wil_s(wil, RGF_DMA_MISC_CTL,
+			      BIT_OFUL34_RDY_VALID_BUG_FIX_EN);
+
 		rc = wil_restore_vifs(wil);
 		if (rc) {
 			wil_err(wil, "failed to restore vifs, rc %d\n", rc);
@@ -1406,8 +1675,12 @@ int __wil_up(struct wil6210_priv *wil)
 	if (rc)
 		return rc;
 
-	/* Rx VRING. After MAC and beacon */
-	rc = wil_rx_init(wil, 1 << rx_ring_order);
+	/* Rx RING. After MAC and beacon */
+	rc = wil->txrx_ops.rx_init(wil, 1 << rx_ring_order);
+	if (rc)
+		return rc;
+
+	rc = wil->txrx_ops.tx_init(wil);
 	if (rc)
 		return rc;
 
@@ -1568,3 +1841,11 @@ void wil_halp_unvote(struct wil6210_priv *wil)
 
 	mutex_unlock(&wil->halp.lock);
 }
+
+void wil_init_txrx_ops(struct wil6210_priv *wil)
+{
+	if (wil->use_enhanced_dma_hw)
+		wil_init_txrx_ops_edma(wil);
+	else
+		wil_init_txrx_ops_legacy_dma(wil);
+}
diff --git a/drivers/net/wireless/ath/wil6210/netdev.c b/drivers/net/wireless/ath/wil6210/netdev.c
index eb6c14ed65a4..7a78a06bd356 100644
--- a/drivers/net/wireless/ath/wil6210/netdev.c
+++ b/drivers/net/wireless/ath/wil6210/netdev.c
@@ -120,6 +120,27 @@ static int wil6210_netdev_poll_rx(struct napi_struct *napi, int budget)
 	return done;
 }
 
+static int wil6210_netdev_poll_rx_edma(struct napi_struct *napi, int budget)
+{
+	struct wil6210_priv *wil = container_of(napi, struct wil6210_priv,
+						napi_rx);
+	int quota = budget;
+	int done;
+
+	wil_rx_handle_edma(wil, &quota);
+	done = budget - quota;
+
+	if (done < budget) {
+		napi_complete_done(napi, done);
+		wil6210_unmask_irq_rx_edma(wil);
+		wil_dbg_txrx(wil, "NAPI RX complete\n");
+	}
+
+	wil_dbg_txrx(wil, "NAPI RX poll(%d) done %d\n", budget, done);
+
+	return done;
+}
+
 static int wil6210_netdev_poll_tx(struct napi_struct *napi, int budget)
 {
 	struct wil6210_priv *wil = container_of(napi, struct wil6210_priv,
@@ -129,11 +150,11 @@ static int wil6210_netdev_poll_tx(struct napi_struct *napi, int budget)
 
 	/* always process ALL Tx complete, regardless budget - it is fast */
 	for (i = 0; i < WIL6210_MAX_TX_RINGS; i++) {
-		struct vring *vring = &wil->vring_tx[i];
-		struct vring_tx_data *txdata = &wil->vring_tx_data[i];
+		struct wil_ring *ring = &wil->ring_tx[i];
+		struct wil_ring_tx_data *txdata = &wil->ring_tx_data[i];
 		struct wil6210_vif *vif;
 
-		if (!vring->va || !txdata->enabled ||
+		if (!ring->va || !txdata->enabled ||
 		    txdata->mid >= wil->max_vifs)
 			continue;
 
@@ -157,6 +178,30 @@ static int wil6210_netdev_poll_tx(struct napi_struct *napi, int budget)
 	return min(tx_done, budget);
 }
 
+static int wil6210_netdev_poll_tx_edma(struct napi_struct *napi, int budget)
+{
+	struct wil6210_priv *wil = container_of(napi, struct wil6210_priv,
+						napi_tx);
+	int tx_done;
+	/* There is only one status TX ring */
+	struct wil_status_ring *sring = &wil->srings[wil->tx_sring_idx];
+
+	if (!sring->va)
+		return 0;
+
+	tx_done = wil_tx_sring_handler(wil, sring);
+
+	if (tx_done < budget) {
+		napi_complete(napi);
+		wil6210_unmask_irq_tx_edma(wil);
+		wil_dbg_txrx(wil, "NAPI TX complete\n");
+	}
+
+	wil_dbg_txrx(wil, "NAPI TX poll(%d) done %d\n", budget, tx_done);
+
+	return min(tx_done, budget);
+}
+
 static void wil_dev_setup(struct net_device *dev)
 {
 	ether_setup(dev);
@@ -228,7 +273,7 @@ static void wil_p2p_discovery_timer_fn(struct timer_list *t)
 
 static void wil_vif_init(struct wil6210_vif *vif)
 {
-	vif->bcast_vring = -1;
+	vif->bcast_ring = -1;
 
 	mutex_init(&vif->probe_client_mutex);
 
@@ -418,11 +463,21 @@ int wil_if_add(struct wil6210_priv *wil)
 	}
 
 	init_dummy_netdev(&wil->napi_ndev);
-	netif_napi_add(&wil->napi_ndev, &wil->napi_rx, wil6210_netdev_poll_rx,
-		       WIL6210_NAPI_BUDGET);
-	netif_tx_napi_add(&wil->napi_ndev,
-			  &wil->napi_tx, wil6210_netdev_poll_tx,
-			  WIL6210_NAPI_BUDGET);
+	if (wil->use_enhanced_dma_hw) {
+		netif_napi_add(&wil->napi_ndev, &wil->napi_rx,
+			       wil6210_netdev_poll_rx_edma,
+			       WIL6210_NAPI_BUDGET);
+		netif_tx_napi_add(&wil->napi_ndev,
+				  &wil->napi_tx, wil6210_netdev_poll_tx_edma,
+				  WIL6210_NAPI_BUDGET);
+	} else {
+		netif_napi_add(&wil->napi_ndev, &wil->napi_rx,
+			       wil6210_netdev_poll_rx,
+			       WIL6210_NAPI_BUDGET);
+		netif_tx_napi_add(&wil->napi_ndev,
+				  &wil->napi_tx, wil6210_netdev_poll_tx,
+				  WIL6210_NAPI_BUDGET);
+	}
 
 	wil_update_net_queues_bh(wil, vif, NULL, true);
 
diff --git a/drivers/net/wireless/ath/wil6210/pcie_bus.c b/drivers/net/wireless/ath/wil6210/pcie_bus.c
index 19cbc6add637..89119e7facd0 100644
--- a/drivers/net/wireless/ath/wil6210/pcie_bus.c
+++ b/drivers/net/wireless/ath/wil6210/pcie_bus.c
@@ -24,11 +24,11 @@
 #include <linux/rtnetlink.h>
 #include <linux/pm_runtime.h>
 
-static bool use_msi = true;
-module_param(use_msi, bool, 0444);
-MODULE_PARM_DESC(use_msi, " Use MSI interrupt, default - true");
+static int n_msi = 3;
+module_param(n_msi, int, 0444);
+MODULE_PARM_DESC(n_msi, " Use MSI interrupt: 0 - use INTx, 1 - single, or 3 - (default) ");
 
-static bool ftm_mode;
+bool ftm_mode;
 module_param(ftm_mode, bool, 0444);
 MODULE_PARM_DESC(ftm_mode, " Set factory test mode, default - false");
 
@@ -85,7 +85,7 @@ int wil_set_capabilities(struct wil6210_priv *wil)
 		wil->rgf_ucode_assert_code_addr = SPARROW_RGF_UCODE_ASSERT_CODE;
 		break;
 	case JTAG_DEV_ID_TALYN:
-		wil->hw_name = "Talyn";
+		wil->hw_name = "Talyn-MA";
 		wil->hw_version = HW_VER_TALYN;
 		memcpy(fw_mapping, talyn_fw_mapping, sizeof(talyn_fw_mapping));
 		wil->rgf_fw_assert_code_addr = TALYN_RGF_FW_ASSERT_CODE;
@@ -93,6 +93,25 @@ int wil_set_capabilities(struct wil6210_priv *wil)
 		if (wil_r(wil, RGF_USER_OTP_HW_RD_MACHINE_1) &
 		    BIT_NO_FLASH_INDICATION)
 			set_bit(hw_capa_no_flash, wil->hw_capa);
+		wil_fw_name = ftm_mode ? WIL_FW_NAME_FTM_TALYN :
+			      WIL_FW_NAME_TALYN;
+		if (wil_fw_verify_file_exists(wil, wil_fw_name))
+			wil->wil_fw_name = wil_fw_name;
+		break;
+	case JTAG_DEV_ID_TALYN_MB:
+		wil->hw_name = "Talyn-MB";
+		wil->hw_version = HW_VER_TALYN_MB;
+		memcpy(fw_mapping, talyn_mb_fw_mapping,
+		       sizeof(talyn_mb_fw_mapping));
+		wil->rgf_fw_assert_code_addr = TALYN_RGF_FW_ASSERT_CODE;
+		wil->rgf_ucode_assert_code_addr = TALYN_RGF_UCODE_ASSERT_CODE;
+		set_bit(hw_capa_no_flash, wil->hw_capa);
+		wil->use_enhanced_dma_hw = true;
+		wil->use_rx_hw_reordering = true;
+		wil_fw_name = ftm_mode ? WIL_FW_NAME_FTM_TALYN :
+			      WIL_FW_NAME_TALYN;
+		if (wil_fw_verify_file_exists(wil, wil_fw_name))
+			wil->wil_fw_name = wil_fw_name;
 		break;
 	default:
 		wil_err(wil, "Unknown board hardware, chip_id 0x%08x, chip_revision 0x%08x\n",
@@ -102,6 +121,8 @@ int wil_set_capabilities(struct wil6210_priv *wil)
 		return -EINVAL;
 	}
 
+	wil_init_txrx_ops(wil);
+
 	iccm_section = wil_find_fw_mapping("fw_code");
 	if (!iccm_section) {
 		wil_err(wil, "fw_code section not found in fw_mapping\n");
@@ -129,12 +150,24 @@ int wil_set_capabilities(struct wil6210_priv *wil)
 
 void wil_disable_irq(struct wil6210_priv *wil)
 {
-	disable_irq(wil->pdev->irq);
+	int irq = wil->pdev->irq;
+
+	disable_irq(irq);
+	if (wil->n_msi == 3) {
+		disable_irq(irq + 1);
+		disable_irq(irq + 2);
+	}
 }
 
 void wil_enable_irq(struct wil6210_priv *wil)
 {
-	enable_irq(wil->pdev->irq);
+	int irq = wil->pdev->irq;
+
+	enable_irq(irq);
+	if (wil->n_msi == 3) {
+		enable_irq(irq + 1);
+		enable_irq(irq + 2);
+	}
 }
 
 static void wil_remove_all_additional_vifs(struct wil6210_priv *wil)
@@ -161,28 +194,47 @@ static int wil_if_pcie_enable(struct wil6210_priv *wil)
 	 * and only MSI should be used
 	 */
 	int msi_only = pdev->msi_enabled;
-	bool _use_msi = use_msi;
 
 	wil_dbg_misc(wil, "if_pcie_enable\n");
 
 	pci_set_master(pdev);
 
-	wil_dbg_misc(wil, "Setup %s interrupt\n", use_msi ? "MSI" : "INTx");
+	/* how many MSI interrupts to request? */
+	switch (n_msi) {
+	case 3:
+	case 1:
+		wil_dbg_misc(wil, "Setup %d MSI interrupts\n", n_msi);
+		break;
+	case 0:
+		wil_dbg_misc(wil, "MSI interrupts disabled, use INTx\n");
+		break;
+	default:
+		wil_err(wil, "Invalid n_msi=%d, default to 1\n", n_msi);
+		n_msi = 1;
+	}
+
+	if (n_msi == 3 &&
+	    pci_alloc_irq_vectors(pdev, n_msi, n_msi, PCI_IRQ_MSI) < n_msi) {
+		wil_err(wil, "3 MSI mode failed, try 1 MSI\n");
+		n_msi = 1;
+	}
 
-	if (use_msi && pci_enable_msi(pdev)) {
+	if (n_msi == 1 && pci_enable_msi(pdev)) {
 		wil_err(wil, "pci_enable_msi failed, use INTx\n");
-		_use_msi = false;
+		n_msi = 0;
 	}
 
-	if (!_use_msi && msi_only) {
+	wil->n_msi = n_msi;
+
+	if (wil->n_msi == 0 && msi_only) {
 		wil_err(wil, "Interrupt pin not routed, unable to use INTx\n");
 		rc = -ENODEV;
 		goto stop_master;
 	}
 
-	rc = wil6210_init_irq(wil, pdev->irq, _use_msi);
+	rc = wil6210_init_irq(wil, pdev->irq);
 	if (rc)
-		goto stop_master;
+		goto release_vectors;
 
 	/* need reset here to obtain MAC */
 	mutex_lock(&wil->mutex);
@@ -195,8 +247,9 @@ static int wil_if_pcie_enable(struct wil6210_priv *wil)
 
  release_irq:
 	wil6210_fini_irq(wil, pdev->irq);
-	/* safe to call if no MSI */
-	pci_disable_msi(pdev);
+ release_vectors:
+	/* safe to call if no allocation */
+	pci_free_irq_vectors(pdev);
  stop_master:
 	pci_clear_master(pdev);
 	return rc;
@@ -257,8 +310,8 @@ static int wil_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		.fw_recovery = wil_platform_rop_fw_recovery,
 	};
 	u32 bar_size = pci_resource_len(pdev, 0);
-	int dma_addr_size[] = {48, 40, 32}; /* keep descending order */
-	int i;
+	int dma_addr_size[] = {64, 48, 40, 32}; /* keep descending order */
+	int i, start_idx;
 
 	/* check HW */
 	dev_info(&pdev->dev, WIL_NAME
@@ -293,24 +346,6 @@ static int wil_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto if_free;
 	}
 	/* rollback to err_plat */
-
-	/* device supports >32bit addresses */
-	for (i = 0; i < ARRAY_SIZE(dma_addr_size); i++) {
-		rc = dma_set_mask_and_coherent(dev,
-					       DMA_BIT_MASK(dma_addr_size[i]));
-		if (rc) {
-			dev_err(dev, "dma_set_mask_and_coherent(%d) failed: %d\n",
-				dma_addr_size[i], rc);
-			continue;
-		}
-		dev_info(dev, "using dma mask %d", dma_addr_size[i]);
-		wil->dma_addr_size = dma_addr_size[i];
-		break;
-	}
-
-	if (wil->dma_addr_size == 0)
-		goto err_plat;
-
 	rc = pci_enable_device(pdev);
 	if (rc && pdev->msi_enabled == 0) {
 		wil_err(wil,
@@ -350,6 +385,28 @@ static int wil_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		wil_err(wil, "wil_set_capabilities failed, rc %d\n", rc);
 		goto err_iounmap;
 	}
+
+	/* device supports >32bit addresses.
+	 * for legacy DMA start from 48 bit.
+	 */
+	start_idx = wil->use_enhanced_dma_hw ? 0 : 1;
+
+	for (i = start_idx; i < ARRAY_SIZE(dma_addr_size); i++) {
+		rc = dma_set_mask_and_coherent(dev,
+					       DMA_BIT_MASK(dma_addr_size[i]));
+		if (rc) {
+			dev_err(dev, "dma_set_mask_and_coherent(%d) failed: %d\n",
+				dma_addr_size[i], rc);
+			continue;
+		}
+		dev_info(dev, "using dma mask %d", dma_addr_size[i]);
+		wil->dma_addr_size = dma_addr_size[i];
+		break;
+	}
+
+	if (wil->dma_addr_size == 0)
+		goto err_iounmap;
+
 	wil6210_clear_irq(wil);
 
 	/* FW should raise IRQ when ready */
diff --git a/drivers/net/wireless/ath/wil6210/pm.c b/drivers/net/wireless/ath/wil6210/pm.c
index ba81fb3ac96f..3a4194779ddf 100644
--- a/drivers/net/wireless/ath/wil6210/pm.c
+++ b/drivers/net/wireless/ath/wil6210/pm.c
@@ -211,7 +211,7 @@ static int wil_suspend_keep_radio_on(struct wil6210_priv *wil)
 		goto reject_suspend;
 	}
 
-	if (!wil_is_rx_idle(wil)) {
+	if (!wil->txrx_ops.is_rx_idle(wil)) {
 		wil_dbg_pm(wil, "Pending RX data, reject suspend\n");
 		wil->suspend_stats.rejected_by_host++;
 		goto reject_suspend;
@@ -235,9 +235,9 @@ static int wil_suspend_keep_radio_on(struct wil6210_priv *wil)
 	start = jiffies;
 	data_comp_to = jiffies + msecs_to_jiffies(WIL_DATA_COMPLETION_TO_MS);
 	if (test_bit(wil_status_napi_en, wil->status)) {
-		while (!wil_is_rx_idle(wil)) {
+		while (!wil->txrx_ops.is_rx_idle(wil)) {
 			if (time_after(jiffies, data_comp_to)) {
-				if (wil_is_rx_idle(wil))
+				if (wil->txrx_ops.is_rx_idle(wil))
 					break;
 				wil_err(wil,
 					"TO waiting for idle RX, suspend failed\n");
diff --git a/drivers/net/wireless/ath/wil6210/rx_reorder.c b/drivers/net/wireless/ath/wil6210/rx_reorder.c
index 76f8084c1fd8..b608aa16b4f1 100644
--- a/drivers/net/wireless/ath/wil6210/rx_reorder.c
+++ b/drivers/net/wireless/ath/wil6210/rx_reorder.c
@@ -95,17 +95,17 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 {
 	struct wil6210_vif *vif;
 	struct net_device *ndev;
-	struct vring_rx_desc *d = wil_skb_rxdesc(skb);
-	int tid = wil_rxdesc_tid(d);
-	int cid = wil_rxdesc_cid(d);
-	int mid = wil_rxdesc_mid(d);
-	u16 seq = wil_rxdesc_seq(d);
-	int mcast = wil_rxdesc_mcast(d);
-	struct wil_sta_info *sta = &wil->sta[cid];
+	int tid, cid, mid, mcast, retry;
+	u16 seq;
+	struct wil_sta_info *sta;
 	struct wil_tid_ampdu_rx *r;
 	u16 hseq;
 	int index;
 
+	wil->txrx_ops.get_reorder_params(wil, skb, &tid, &cid, &mid, &seq,
+					 &mcast, &retry);
+	sta = &wil->sta[cid];
+
 	wil_dbg_txrx(wil, "MID %d CID %d TID %d Seq 0x%03x mcast %01x\n",
 		     mid, cid, tid, seq, mcast);
 
@@ -117,11 +117,6 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 	}
 	ndev = vif_to_ndev(vif);
 
-	if (unlikely(mcast)) {
-		wil_netif_rx_any(skb, ndev);
-		return;
-	}
-
 	spin_lock(&sta->tid_rx_lock);
 
 	r = sta->tid_rx[tid];
@@ -130,6 +125,19 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 		goto out;
 	}
 
+	if (unlikely(mcast)) {
+		if (retry && seq == r->mcast_last_seq) {
+			r->drop_dup_mcast++;
+			wil_dbg_txrx(wil, "Rx drop: dup mcast seq 0x%03x\n",
+				     seq);
+			dev_kfree_skb(skb);
+			goto out;
+		}
+		r->mcast_last_seq = seq;
+		wil_netif_rx_any(skb, ndev);
+		goto out;
+	}
+
 	r->total++;
 	hseq = r->head_seq_num;
 
@@ -262,6 +270,7 @@ struct wil_tid_ampdu_rx *wil_tid_ampdu_rx_alloc(struct wil6210_priv *wil,
 	r->buf_size = size;
 	r->stored_mpdu_num = 0;
 	r->first_time = true;
+	r->mcast_last_seq = U16_MAX;
 	return r;
 }
 
@@ -288,7 +297,7 @@ void wil_tid_ampdu_rx_free(struct wil6210_priv *wil,
 /* ADDBA processing */
 static u16 wil_agg_size(struct wil6210_priv *wil, u16 req_agg_wsize)
 {
-	u16 max_agg_size = min_t(u16, WIL_MAX_AGG_WSIZE, WIL_MAX_AMPDU_SIZE /
+	u16 max_agg_size = min_t(u16, wil->max_agg_wsize, wil->max_ampdu_size /
 				 (mtu_max + WIL_MAX_MPDU_OVERHEAD));
 
 	if (!req_agg_wsize)
@@ -315,7 +324,10 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 	 * bits 6..15: buffer size
 	 */
 	u16 req_agg_wsize = WIL_GET_BITS(param_set, 6, 15);
-	bool agg_amsdu = !!(param_set & BIT(0));
+	bool agg_amsdu = wil->use_enhanced_dma_hw &&
+		wil->use_rx_hw_reordering &&
+		test_bit(WMI_FW_CAPABILITY_AMSDU, wil->fw_capabilities) &&
+		wil->amsdu_en && (param_set & BIT(0));
 	int ba_policy = param_set & BIT(1);
 	u16 status = WLAN_STATUS_SUCCESS;
 	u16 ssn = seq_ctrl >> 4;
@@ -352,16 +364,17 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 	if (status == WLAN_STATUS_SUCCESS) {
 		if (req_agg_wsize == 0) {
 			wil_dbg_misc(wil, "Suggest BACK wsize %d\n",
-				     WIL_MAX_AGG_WSIZE);
-			agg_wsize = WIL_MAX_AGG_WSIZE;
+				     wil->max_agg_wsize);
+			agg_wsize = wil->max_agg_wsize;
 		} else {
 			agg_wsize = min_t(u16,
-					  WIL_MAX_AGG_WSIZE, req_agg_wsize);
+					  wil->max_agg_wsize, req_agg_wsize);
 		}
 	}
 
-	rc = wmi_addba_rx_resp(wil, mid, cid, tid, dialog_token, status,
-			       agg_amsdu, agg_wsize, agg_timeout);
+	rc = wil->txrx_ops.wmi_addba_rx_resp(wil, mid, cid, tid, dialog_token,
+					     status, agg_amsdu, agg_wsize,
+					     agg_timeout);
 	if (rc || (status != WLAN_STATUS_SUCCESS)) {
 		wil_err(wil, "do not apply ba, rc(%d), status(%d)\n", rc,
 			status);
@@ -384,7 +397,7 @@ int wil_addba_tx_request(struct wil6210_priv *wil, u8 ringid, u16 wsize)
 {
 	u8 agg_wsize = wil_agg_size(wil, wsize);
 	u16 agg_timeout = 0;
-	struct vring_tx_data *txdata = &wil->vring_tx_data[ringid];
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[ringid];
 	int rc = 0;
 
 	if (txdata->addba_in_progress) {
diff --git a/drivers/net/wireless/ath/wil6210/trace.h b/drivers/net/wireless/ath/wil6210/trace.h
index c4db2a9d9f7f..853abc3a73e4 100644
--- a/drivers/net/wireless/ath/wil6210/trace.h
+++ b/drivers/net/wireless/ath/wil6210/trace.h
@@ -187,6 +187,40 @@ TRACE_EVENT(wil6210_rx,
 		  __entry->seq, __entry->type, __entry->subtype)
 );
 
+TRACE_EVENT(wil6210_rx_status,
+	    TP_PROTO(struct wil6210_priv *wil, u8 use_compressed, u16 buff_id,
+		     void *msg),
+	    TP_ARGS(wil, use_compressed, buff_id, msg),
+	    TP_STRUCT__entry(__field(u8, use_compressed)
+			     __field(u16, buff_id)
+			     __field(unsigned int, len)
+			     __field(u8, mid)
+			     __field(u8, cid)
+			     __field(u8, tid)
+			     __field(u8, type)
+			     __field(u8, subtype)
+			     __field(u16, seq)
+			     __field(u8, mcs)
+	    ),
+	    TP_fast_assign(__entry->use_compressed = use_compressed;
+			   __entry->buff_id = buff_id;
+			   __entry->len = wil_rx_status_get_length(msg);
+			   __entry->mid = wil_rx_status_get_mid(msg);
+			   __entry->cid = wil_rx_status_get_cid(msg);
+			   __entry->tid = wil_rx_status_get_tid(msg);
+			   __entry->type = wil_rx_status_get_frame_type(wil,
+									msg);
+			   __entry->subtype = wil_rx_status_get_fc1(wil, msg);
+			   __entry->seq = wil_rx_status_get_seq(wil, msg);
+			   __entry->mcs = wil_rx_status_get_mcs(msg);
+	    ),
+	    TP_printk(
+		      "compressed %d buff_id %d len %d mid %d cid %d tid %d mcs %d seq 0x%03x type 0x%1x subtype 0x%1x",
+		      __entry->use_compressed, __entry->buff_id, __entry->len,
+		      __entry->mid, __entry->cid, __entry->tid, __entry->mcs,
+		      __entry->seq, __entry->type, __entry->subtype)
+);
+
 TRACE_EVENT(wil6210_tx,
 	TP_PROTO(u8 vring, u16 index, unsigned int len, u8 frags),
 	TP_ARGS(vring, index, len, frags),
@@ -226,6 +260,31 @@ TRACE_EVENT(wil6210_tx_done,
 		  __entry->err)
 );
 
+TRACE_EVENT(wil6210_tx_status,
+	    TP_PROTO(struct wil_ring_tx_status *msg, u16 index,
+		     unsigned int len),
+	    TP_ARGS(msg, index, len),
+	    TP_STRUCT__entry(__field(u16, index)
+			     __field(unsigned int, len)
+			     __field(u8, num_descs)
+			     __field(u8, ring_id)
+			     __field(u8, status)
+			     __field(u8, mcs)
+
+	    ),
+	    TP_fast_assign(__entry->index = index;
+			   __entry->len = len;
+			   __entry->num_descs = msg->num_descriptors;
+			   __entry->ring_id = msg->ring_id;
+			   __entry->status = msg->status;
+			   __entry->mcs = wil_tx_status_get_mcs(msg);
+	    ),
+	    TP_printk(
+		      "ring_id %d swtail 0x%x len %d num_descs %d status 0x%x mcs %d",
+		      __entry->ring_id, __entry->index, __entry->len,
+		      __entry->num_descs, __entry->status, __entry->mcs)
+);
+
 #endif /* WIL6210_TRACE_H || TRACE_HEADER_MULTI_READ*/
 
 #if defined(CONFIG_WIL6210_TRACING) && !defined(__CHECKER__)
diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index b9a9fa828961..6a7943e487fb 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -28,6 +28,7 @@
 #include "wmi.h"
 #include "txrx.h"
 #include "trace.h"
+#include "txrx_edma.h"
 
 static bool rtap_include_phy_info;
 module_param(rtap_include_phy_info, bool, 0444);
@@ -47,62 +48,28 @@ static inline uint wil_rx_snaplen(void)
 	return rx_align_2 ? 6 : 0;
 }
 
-static inline int wil_vring_is_empty(struct vring *vring)
+/* wil_ring_wmark_low - low watermark for available descriptor space */
+static inline int wil_ring_wmark_low(struct wil_ring *ring)
 {
-	return vring->swhead == vring->swtail;
+	return ring->size / 8;
 }
 
-static inline u32 wil_vring_next_tail(struct vring *vring)
+/* wil_ring_wmark_high - high watermark for available descriptor space */
+static inline int wil_ring_wmark_high(struct wil_ring *ring)
 {
-	return (vring->swtail + 1) % vring->size;
-}
-
-static inline void wil_vring_advance_head(struct vring *vring, int n)
-{
-	vring->swhead = (vring->swhead + n) % vring->size;
-}
-
-static inline int wil_vring_is_full(struct vring *vring)
-{
-	return wil_vring_next_tail(vring) == vring->swhead;
-}
-
-/* Used space in Tx Vring */
-static inline int wil_vring_used_tx(struct vring *vring)
-{
-	u32 swhead = vring->swhead;
-	u32 swtail = vring->swtail;
-	return (vring->size + swhead - swtail) % vring->size;
-}
-
-/* Available space in Tx Vring */
-static inline int wil_vring_avail_tx(struct vring *vring)
-{
-	return vring->size - wil_vring_used_tx(vring) - 1;
-}
-
-/* wil_vring_wmark_low - low watermark for available descriptor space */
-static inline int wil_vring_wmark_low(struct vring *vring)
-{
-	return vring->size/8;
-}
-
-/* wil_vring_wmark_high - high watermark for available descriptor space */
-static inline int wil_vring_wmark_high(struct vring *vring)
-{
-	return vring->size/4;
+	return ring->size / 4;
 }
 
 /* returns true if num avail descriptors is lower than wmark_low */
-static inline int wil_vring_avail_low(struct vring *vring)
+static inline int wil_ring_avail_low(struct wil_ring *ring)
 {
-	return wil_vring_avail_tx(vring) < wil_vring_wmark_low(vring);
+	return wil_ring_avail_tx(ring) < wil_ring_wmark_low(ring);
 }
 
 /* returns true if num avail descriptors is higher than wmark_high */
-static inline int wil_vring_avail_high(struct vring *vring)
+static inline int wil_ring_avail_high(struct wil_ring *ring)
 {
-	return wil_vring_avail_tx(vring) > wil_vring_wmark_high(vring);
+	return wil_ring_avail_tx(ring) > wil_ring_wmark_high(ring);
 }
 
 /* returns true when all tx vrings are empty */
@@ -112,9 +79,10 @@ bool wil_is_tx_idle(struct wil6210_priv *wil)
 	unsigned long data_comp_to;
 
 	for (i = 0; i < WIL6210_MAX_TX_RINGS; i++) {
-		struct vring *vring = &wil->vring_tx[i];
-		int vring_index = vring - wil->vring_tx;
-		struct vring_tx_data *txdata = &wil->vring_tx_data[vring_index];
+		struct wil_ring *vring = &wil->ring_tx[i];
+		int vring_index = vring - wil->ring_tx;
+		struct wil_ring_tx_data *txdata =
+			&wil->ring_tx_data[vring_index];
 
 		spin_lock(&txdata->lock);
 
@@ -126,7 +94,7 @@ bool wil_is_tx_idle(struct wil6210_priv *wil)
 		data_comp_to = jiffies + msecs_to_jiffies(
 					WIL_DATA_COMPLETION_TO_MS);
 		if (test_bit(wil_status_napi_en, wil->status)) {
-			while (!wil_vring_is_empty(vring)) {
+			while (!wil_ring_is_empty(vring)) {
 				if (time_after(jiffies, data_comp_to)) {
 					wil_dbg_pm(wil,
 						   "TO waiting for idle tx\n");
@@ -150,13 +118,7 @@ bool wil_is_tx_idle(struct wil6210_priv *wil)
 	return true;
 }
 
-/* wil_val_in_range - check if value in [min,max) */
-static inline bool wil_val_in_range(int val, int min, int max)
-{
-	return val >= min && val < max;
-}
-
-static int wil_vring_alloc(struct wil6210_priv *wil, struct vring *vring)
+static int wil_vring_alloc(struct wil6210_priv *wil, struct wil_ring *vring)
 {
 	struct device *dev = wil_to_dev(wil);
 	size_t sz = vring->size * sizeof(vring->va[0]);
@@ -205,7 +167,8 @@ static int wil_vring_alloc(struct wil6210_priv *wil, struct vring *vring)
 	 * we can use any
 	 */
 	for (i = 0; i < vring->size; i++) {
-		volatile struct vring_tx_desc *_d = &vring->va[i].tx;
+		volatile struct vring_tx_desc *_d =
+			&vring->va[i].tx.legacy;
 
 		_d->dma.status = TX_DMA_STATUS_DU;
 	}
@@ -216,9 +179,10 @@ static int wil_vring_alloc(struct wil6210_priv *wil, struct vring *vring)
 	return 0;
 }
 
-static void wil_txdesc_unmap(struct device *dev, struct vring_tx_desc *d,
+static void wil_txdesc_unmap(struct device *dev, union wil_tx_desc *desc,
 			     struct wil_ctx *ctx)
 {
+	struct vring_tx_desc *d = &desc->legacy;
 	dma_addr_t pa = wil_desc_addr(&d->dma.addr);
 	u16 dmalen = le16_to_cpu(d->dma.length);
 
@@ -234,15 +198,14 @@ static void wil_txdesc_unmap(struct device *dev, struct vring_tx_desc *d,
 	}
 }
 
-static void wil_vring_free(struct wil6210_priv *wil, struct vring *vring,
-			   int tx)
+static void wil_vring_free(struct wil6210_priv *wil, struct wil_ring *vring)
 {
 	struct device *dev = wil_to_dev(wil);
 	size_t sz = vring->size * sizeof(vring->va[0]);
 
 	lockdep_assert_held(&wil->mutex);
-	if (tx) {
-		int vring_index = vring - wil->vring_tx;
+	if (!vring->is_rx) {
+		int vring_index = vring - wil->ring_tx;
 
 		wil_dbg_misc(wil, "free Tx vring %d [%d] 0x%p:%pad 0x%p\n",
 			     vring_index, vring->size, vring->va,
@@ -253,33 +216,33 @@ static void wil_vring_free(struct wil6210_priv *wil, struct vring *vring,
 			     &vring->pa, vring->ctx);
 	}
 
-	while (!wil_vring_is_empty(vring)) {
+	while (!wil_ring_is_empty(vring)) {
 		dma_addr_t pa;
 		u16 dmalen;
 		struct wil_ctx *ctx;
 
-		if (tx) {
+		if (!vring->is_rx) {
 			struct vring_tx_desc dd, *d = &dd;
 			volatile struct vring_tx_desc *_d =
-					&vring->va[vring->swtail].tx;
+					&vring->va[vring->swtail].tx.legacy;
 
 			ctx = &vring->ctx[vring->swtail];
 			if (!ctx) {
 				wil_dbg_txrx(wil,
 					     "ctx(%d) was already completed\n",
 					     vring->swtail);
-				vring->swtail = wil_vring_next_tail(vring);
+				vring->swtail = wil_ring_next_tail(vring);
 				continue;
 			}
 			*d = *_d;
-			wil_txdesc_unmap(dev, d, ctx);
+			wil_txdesc_unmap(dev, (union wil_tx_desc *)d, ctx);
 			if (ctx->skb)
 				dev_kfree_skb_any(ctx->skb);
-			vring->swtail = wil_vring_next_tail(vring);
+			vring->swtail = wil_ring_next_tail(vring);
 		} else { /* rx */
 			struct vring_rx_desc dd, *d = &dd;
 			volatile struct vring_rx_desc *_d =
-					&vring->va[vring->swhead].rx;
+				&vring->va[vring->swhead].rx.legacy;
 
 			ctx = &vring->ctx[vring->swhead];
 			*d = *_d;
@@ -287,7 +250,7 @@ static void wil_vring_free(struct wil6210_priv *wil, struct vring *vring,
 			dmalen = le16_to_cpu(d->dma.length);
 			dma_unmap_single(dev, pa, dmalen, DMA_FROM_DEVICE);
 			kfree_skb(ctx->skb);
-			wil_vring_advance_head(vring, 1);
+			wil_ring_advance_head(vring, 1);
 		}
 	}
 	dma_free_coherent(dev, sz, (void *)vring->va, vring->pa);
@@ -302,13 +265,13 @@ static void wil_vring_free(struct wil6210_priv *wil, struct vring *vring,
  *
  * Safe to call from IRQ
  */
-static int wil_vring_alloc_skb(struct wil6210_priv *wil, struct vring *vring,
+static int wil_vring_alloc_skb(struct wil6210_priv *wil, struct wil_ring *vring,
 			       u32 i, int headroom)
 {
 	struct device *dev = wil_to_dev(wil);
 	unsigned int sz = wil->rx_buf_len + ETH_HLEN + wil_rx_snaplen();
 	struct vring_rx_desc dd, *d = &dd;
-	volatile struct vring_rx_desc *_d = &vring->va[i].rx;
+	volatile struct vring_rx_desc *_d = &vring->va[i].rx.legacy;
 	dma_addr_t pa;
 	struct sk_buff *skb = dev_alloc_skb(sz + headroom);
 
@@ -318,6 +281,12 @@ static int wil_vring_alloc_skb(struct wil6210_priv *wil, struct vring *vring,
 	skb_reserve(skb, headroom);
 	skb_put(skb, sz);
 
+	/**
+	 * Make sure that the network stack calculates checksum for packets
+	 * which failed the HW checksum calculation
+	 */
+	skb->ip_summed = CHECKSUM_NONE;
+
 	pa = dma_map_single(dev, skb->data, skb->len, DMA_FROM_DEVICE);
 	if (unlikely(dma_mapping_error(dev, pa))) {
 		kfree_skb(skb);
@@ -445,19 +414,12 @@ static void wil_rx_add_radiotap_header(struct wil6210_priv *wil,
 	}
 }
 
-/* similar to ieee80211_ version, but FC contain only 1-st byte */
-static inline int wil_is_back_req(u8 fc)
-{
-	return (fc & (IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) ==
-	       (IEEE80211_FTYPE_CTL | IEEE80211_STYPE_BACK_REQ);
-}
-
-bool wil_is_rx_idle(struct wil6210_priv *wil)
+static bool wil_is_rx_idle(struct wil6210_priv *wil)
 {
 	struct vring_rx_desc *_d;
-	struct vring *vring = &wil->vring_rx;
+	struct wil_ring *ring = &wil->ring_rx;
 
-	_d = (struct vring_rx_desc *)&vring->va[vring->swhead].rx;
+	_d = (struct vring_rx_desc *)&ring->va[ring->swhead].rx.legacy;
 	if (_d->dma.status & RX_DMA_STATUS_DU)
 		return false;
 
@@ -472,7 +434,7 @@ bool wil_is_rx_idle(struct wil6210_priv *wil)
  * Safe to call from IRQ
  */
 static struct sk_buff *wil_vring_reap_rx(struct wil6210_priv *wil,
-					 struct vring *vring)
+					 struct wil_ring *vring)
 {
 	struct device *dev = wil_to_dev(wil);
 	struct wil6210_vif *vif;
@@ -492,11 +454,11 @@ static struct sk_buff *wil_vring_reap_rx(struct wil6210_priv *wil,
 	BUILD_BUG_ON(sizeof(struct vring_rx_desc) > sizeof(skb->cb));
 
 again:
-	if (unlikely(wil_vring_is_empty(vring)))
+	if (unlikely(wil_ring_is_empty(vring)))
 		return NULL;
 
 	i = (int)vring->swhead;
-	_d = &vring->va[i].rx;
+	_d = &vring->va[i].rx.legacy;
 	if (unlikely(!(_d->dma.status & RX_DMA_STATUS_DU))) {
 		/* it is not error, we just reached end of Rx done area */
 		return NULL;
@@ -504,7 +466,7 @@ again:
 
 	skb = vring->ctx[i].skb;
 	vring->ctx[i].skb = NULL;
-	wil_vring_advance_head(vring, 1);
+	wil_ring_advance_head(vring, 1);
 	if (!skb) {
 		wil_err(wil, "No Rx skb at [%d]\n", i);
 		goto again;
@@ -613,6 +575,8 @@ again:
 		 * mis-calculates TCP checksum - if it should be 0x0,
 		 * it writes 0xffff in violation of RFC 1624
 		 */
+		else
+			stats->rx_csum_err++;
 	}
 
 	if (snaplen) {
@@ -641,15 +605,15 @@ again:
 static int wil_rx_refill(struct wil6210_priv *wil, int count)
 {
 	struct net_device *ndev = wil->main_ndev;
-	struct vring *v = &wil->vring_rx;
+	struct wil_ring *v = &wil->ring_rx;
 	u32 next_tail;
 	int rc = 0;
 	int headroom = ndev->type == ARPHRD_IEEE80211_RADIOTAP ?
 			WIL6210_RTAP_SIZE : 0;
 
-	for (; next_tail = wil_vring_next_tail(v),
-			(next_tail != v->swhead) && (count-- > 0);
-			v->swtail = next_tail) {
+	for (; next_tail = wil_ring_next_tail(v),
+	     (next_tail != v->swhead) && (count-- > 0);
+	     v->swtail = next_tail) {
 		rc = wil_vring_alloc_skb(wil, v, v->swtail, headroom);
 		if (unlikely(rc)) {
 			wil_err_ratelimited(wil, "Error %d in rx refill[%d]\n",
@@ -677,7 +641,7 @@ static int wil_rx_refill(struct wil6210_priv *wil, int count)
  * Cut'n'paste from original memcmp (see lib/string.c)
  * with minimal modifications
  */
-static int reverse_memcmp(const void *cs, const void *ct, size_t count)
+int reverse_memcmp(const void *cs, const void *ct, size_t count)
 {
 	const unsigned char *su1, *su2;
 	int res = 0;
@@ -722,6 +686,30 @@ static int wil_rx_crypto_check(struct wil6210_priv *wil, struct sk_buff *skb)
 	return 0;
 }
 
+static int wil_rx_error_check(struct wil6210_priv *wil, struct sk_buff *skb,
+			      struct wil_net_stats *stats)
+{
+	struct vring_rx_desc *d = wil_skb_rxdesc(skb);
+
+	if ((d->dma.status & RX_DMA_STATUS_ERROR) &&
+	    (d->dma.error & RX_DMA_ERROR_MIC)) {
+		stats->rx_mic_error++;
+		wil_dbg_txrx(wil, "MIC error, dropping packet\n");
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+static void wil_get_netif_rx_params(struct sk_buff *skb, int *cid,
+				    int *security)
+{
+	struct vring_rx_desc *d = wil_skb_rxdesc(skb);
+
+	*cid = wil_rxdesc_cid(d); /* always 0..7, no need to check */
+	*security = wil_rxdesc_security(d);
+}
+
 /*
  * Pass Rx packet to the netif. Update statistics.
  * Called in softirq context (NAPI poll).
@@ -733,15 +721,14 @@ void wil_netif_rx_any(struct sk_buff *skb, struct net_device *ndev)
 	struct wil6210_priv *wil = ndev_to_wil(ndev);
 	struct wireless_dev *wdev = vif_to_wdev(vif);
 	unsigned int len = skb->len;
-	struct vring_rx_desc *d = wil_skb_rxdesc(skb);
-	int cid = wil_rxdesc_cid(d); /* always 0..7, no need to check */
-	int security = wil_rxdesc_security(d);
+	int cid;
+	int security;
 	struct ethhdr *eth = (void *)skb->data;
 	/* here looking for DA, not A1, thus Rxdesc's 'mcast' indication
 	 * is not suitable, need to look at data
 	 */
 	int mcast = is_multicast_ether_addr(eth->h_dest);
-	struct wil_net_stats *stats = &wil->sta[cid].stats;
+	struct wil_net_stats *stats;
 	struct sk_buff *xmit_skb = NULL;
 	static const char * const gro_res_str[] = {
 		[GRO_MERGED]		= "GRO_MERGED",
@@ -751,6 +738,10 @@ void wil_netif_rx_any(struct sk_buff *skb, struct net_device *ndev)
 		[GRO_DROP]		= "GRO_DROP",
 	};
 
+	wil->txrx_ops.get_netif_rx_params(skb, &cid, &security);
+
+	stats = &wil->sta[cid].stats;
+
 	if (ndev->features & NETIF_F_RXHASH)
 		/* fake L4 to ensure it won't be re-calculated later
 		 * set hash to any non-zero value to activate rps
@@ -761,13 +752,19 @@ void wil_netif_rx_any(struct sk_buff *skb, struct net_device *ndev)
 
 	skb_orphan(skb);
 
-	if (security && (wil_rx_crypto_check(wil, skb) != 0)) {
+	if (security && (wil->txrx_ops.rx_crypto_check(wil, skb) != 0)) {
 		rc = GRO_DROP;
 		dev_kfree_skb(skb);
 		stats->rx_replay++;
 		goto stats;
 	}
 
+	/* check errors reported by HW and update statistics */
+	if (unlikely(wil->txrx_ops.rx_error_check(wil, skb, stats))) {
+		dev_kfree_skb(skb);
+		return;
+	}
+
 	if (wdev->iftype == NL80211_IFTYPE_AP && !vif->ap_isolate) {
 		if (mcast) {
 			/* send multicast frames both to higher layers in
@@ -835,7 +832,7 @@ void wil_rx_handle(struct wil6210_priv *wil, int *quota)
 {
 	struct net_device *ndev = wil->main_ndev;
 	struct wireless_dev *wdev = ndev->ieee80211_ptr;
-	struct vring *v = &wil->vring_rx;
+	struct wil_ring *v = &wil->ring_rx;
 	struct sk_buff *skb;
 
 	if (unlikely(!v->va)) {
@@ -875,9 +872,9 @@ static void wil_rx_buf_len_init(struct wil6210_priv *wil)
 	}
 }
 
-int wil_rx_init(struct wil6210_priv *wil, u16 size)
+static int wil_rx_init(struct wil6210_priv *wil, u16 size)
 {
-	struct vring *vring = &wil->vring_rx;
+	struct wil_ring *vring = &wil->ring_rx;
 	int rc;
 
 	wil_dbg_misc(wil, "rx_init\n");
@@ -890,6 +887,7 @@ int wil_rx_init(struct wil6210_priv *wil, u16 size)
 	wil_rx_buf_len_init(wil);
 
 	vring->size = size;
+	vring->is_rx = true;
 	rc = wil_vring_alloc(wil, vring);
 	if (rc)
 		return rc;
@@ -904,22 +902,46 @@ int wil_rx_init(struct wil6210_priv *wil, u16 size)
 
 	return 0;
  err_free:
-	wil_vring_free(wil, vring, 0);
+	wil_vring_free(wil, vring);
 
 	return rc;
 }
 
-void wil_rx_fini(struct wil6210_priv *wil)
+static void wil_rx_fini(struct wil6210_priv *wil)
 {
-	struct vring *vring = &wil->vring_rx;
+	struct wil_ring *vring = &wil->ring_rx;
 
 	wil_dbg_misc(wil, "rx_fini\n");
 
 	if (vring->va)
-		wil_vring_free(wil, vring, 0);
+		wil_vring_free(wil, vring);
+}
+
+static int wil_tx_desc_map(union wil_tx_desc *desc, dma_addr_t pa,
+			   u32 len, int vring_index)
+{
+	struct vring_tx_desc *d = &desc->legacy;
+
+	wil_desc_addr_set(&d->dma.addr, pa);
+	d->dma.ip_length = 0;
+	/* 0..6: mac_length; 7:ip_version 0-IP6 1-IP4*/
+	d->dma.b11 = 0/*14 | BIT(7)*/;
+	d->dma.error = 0;
+	d->dma.status = 0; /* BIT(0) should be 0 for HW_OWNED */
+	d->dma.length = cpu_to_le16((u16)len);
+	d->dma.d0 = (vring_index << DMA_CFG_DESC_TX_0_QID_POS);
+	d->mac.d[0] = 0;
+	d->mac.d[1] = 0;
+	d->mac.d[2] = 0;
+	d->mac.ucode_cmd = 0;
+	/* translation type:  0 - bypass; 1 - 802.3; 2 - native wifi */
+	d->mac.d[2] = BIT(MAC_CFG_DESC_TX_2_SNAP_HDR_INSERTION_EN_POS) |
+		      (1 << MAC_CFG_DESC_TX_2_L2_TRANSLATION_TYPE_POS);
+
+	return 0;
 }
 
-static inline void wil_tx_data_init(struct vring_tx_data *txdata)
+void wil_tx_data_init(struct wil_ring_tx_data *txdata)
 {
 	spin_lock_bh(&txdata->lock);
 	txdata->dot1x_open = 0;
@@ -935,8 +957,8 @@ static inline void wil_tx_data_init(struct vring_tx_data *txdata)
 	spin_unlock_bh(&txdata->lock);
 }
 
-int wil_vring_init_tx(struct wil6210_vif *vif, int id, int size,
-		      int cid, int tid)
+static int wil_vring_init_tx(struct wil6210_vif *vif, int id, int size,
+			     int cid, int tid)
 {
 	struct wil6210_priv *wil = vif_to_wil(vif);
 	int rc;
@@ -966,8 +988,8 @@ int wil_vring_init_tx(struct wil6210_vif *vif, int id, int size,
 	} __packed reply = {
 		.cmd = {.status = WMI_FW_STATUS_FAILURE},
 	};
-	struct vring *vring = &wil->vring_tx[id];
-	struct vring_tx_data *txdata = &wil->vring_tx_data[id];
+	struct wil_ring *vring = &wil->ring_tx[id];
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[id];
 
 	wil_dbg_misc(wil, "vring_init_tx: max_mpdu_size %d\n",
 		     cmd.vring_cfg.tx_sw_ring.max_mpdu_size);
@@ -980,13 +1002,14 @@ int wil_vring_init_tx(struct wil6210_vif *vif, int id, int size,
 	}
 
 	wil_tx_data_init(txdata);
+	vring->is_rx = false;
 	vring->size = size;
 	rc = wil_vring_alloc(wil, vring);
 	if (rc)
 		goto out;
 
-	wil->vring2cid_tid[id][0] = cid;
-	wil->vring2cid_tid[id][1] = tid;
+	wil->ring2cid_tid[id][0] = cid;
+	wil->ring2cid_tid[id][1] = tid;
 
 	cmd.vring_cfg.tx_sw_ring.ring_mem_base = cpu_to_le64(vring->pa);
 
@@ -1019,9 +1042,9 @@ int wil_vring_init_tx(struct wil6210_vif *vif, int id, int size,
 	txdata->dot1x_open = false;
 	txdata->enabled = 0;
 	spin_unlock_bh(&txdata->lock);
-	wil_vring_free(wil, vring, 1);
-	wil->vring2cid_tid[id][0] = WIL6210_MAX_CID;
-	wil->vring2cid_tid[id][1] = 0;
+	wil_vring_free(wil, vring);
+	wil->ring2cid_tid[id][0] = WIL6210_MAX_CID;
+	wil->ring2cid_tid[id][1] = 0;
 
  out:
 
@@ -1050,8 +1073,8 @@ int wil_vring_init_bcast(struct wil6210_vif *vif, int id, int size)
 	} __packed reply = {
 		.cmd = {.status = WMI_FW_STATUS_FAILURE},
 	};
-	struct vring *vring = &wil->vring_tx[id];
-	struct vring_tx_data *txdata = &wil->vring_tx_data[id];
+	struct wil_ring *vring = &wil->ring_tx[id];
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[id];
 
 	wil_dbg_misc(wil, "vring_init_bcast: max_mpdu_size %d\n",
 		     cmd.vring_cfg.tx_sw_ring.max_mpdu_size);
@@ -1064,13 +1087,14 @@ int wil_vring_init_bcast(struct wil6210_vif *vif, int id, int size)
 	}
 
 	wil_tx_data_init(txdata);
+	vring->is_rx = false;
 	vring->size = size;
 	rc = wil_vring_alloc(wil, vring);
 	if (rc)
 		goto out;
 
-	wil->vring2cid_tid[id][0] = WIL6210_MAX_CID; /* CID */
-	wil->vring2cid_tid[id][1] = 0; /* TID */
+	wil->ring2cid_tid[id][0] = WIL6210_MAX_CID; /* CID */
+	wil->ring2cid_tid[id][1] = 0; /* TID */
 
 	cmd.vring_cfg.tx_sw_ring.ring_mem_base = cpu_to_le64(vring->pa);
 
@@ -1101,62 +1125,32 @@ int wil_vring_init_bcast(struct wil6210_vif *vif, int id, int size)
 	txdata->enabled = 0;
 	txdata->dot1x_open = false;
 	spin_unlock_bh(&txdata->lock);
-	wil_vring_free(wil, vring, 1);
+	wil_vring_free(wil, vring);
  out:
 
 	return rc;
 }
 
-void wil_vring_fini_tx(struct wil6210_priv *wil, int id)
-{
-	struct vring *vring = &wil->vring_tx[id];
-	struct vring_tx_data *txdata = &wil->vring_tx_data[id];
-
-	lockdep_assert_held(&wil->mutex);
-
-	if (!vring->va)
-		return;
-
-	wil_dbg_misc(wil, "vring_fini_tx: id=%d\n", id);
-
-	spin_lock_bh(&txdata->lock);
-	txdata->dot1x_open = false;
-	txdata->mid = U8_MAX;
-	txdata->enabled = 0; /* no Tx can be in progress or start anew */
-	spin_unlock_bh(&txdata->lock);
-	/* napi_synchronize waits for completion of the current NAPI but will
-	 * not prevent the next NAPI run.
-	 * Add a memory barrier to guarantee that txdata->enabled is zeroed
-	 * before napi_synchronize so that the next scheduled NAPI will not
-	 * handle this vring
-	 */
-	wmb();
-	/* make sure NAPI won't touch this vring */
-	if (test_bit(wil_status_napi_en, wil->status))
-		napi_synchronize(&wil->napi_tx);
-
-	wil_vring_free(wil, vring, 1);
-}
-
-static struct vring *wil_find_tx_ucast(struct wil6210_priv *wil,
-				       struct wil6210_vif *vif,
-				       struct sk_buff *skb)
+static struct wil_ring *wil_find_tx_ucast(struct wil6210_priv *wil,
+					  struct wil6210_vif *vif,
+					  struct sk_buff *skb)
 {
 	int i;
 	struct ethhdr *eth = (void *)skb->data;
 	int cid = wil_find_cid(wil, vif->mid, eth->h_dest);
+	int min_ring_id = wil_get_min_tx_ring_id(wil);
 
 	if (cid < 0)
 		return NULL;
 
 	/* TODO: fix for multiple TID */
-	for (i = 0; i < ARRAY_SIZE(wil->vring2cid_tid); i++) {
-		if (!wil->vring_tx_data[i].dot1x_open &&
-		    (skb->protocol != cpu_to_be16(ETH_P_PAE)))
+	for (i = min_ring_id; i < ARRAY_SIZE(wil->ring2cid_tid); i++) {
+		if (!wil->ring_tx_data[i].dot1x_open &&
+		    skb->protocol != cpu_to_be16(ETH_P_PAE))
 			continue;
-		if (wil->vring2cid_tid[i][0] == cid) {
-			struct vring *v = &wil->vring_tx[i];
-			struct vring_tx_data *txdata = &wil->vring_tx_data[i];
+		if (wil->ring2cid_tid[i][0] == cid) {
+			struct wil_ring *v = &wil->ring_tx[i];
+			struct wil_ring_tx_data *txdata = &wil->ring_tx_data[i];
 
 			wil_dbg_txrx(wil, "find_tx_ucast: (%pM) -> [%d]\n",
 				     eth->h_dest, i);
@@ -1174,42 +1168,43 @@ static struct vring *wil_find_tx_ucast(struct wil6210_priv *wil,
 	return NULL;
 }
 
-static int wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
-			struct vring *vring, struct sk_buff *skb);
+static int wil_tx_ring(struct wil6210_priv *wil, struct wil6210_vif *vif,
+		       struct wil_ring *ring, struct sk_buff *skb);
 
-static struct vring *wil_find_tx_vring_sta(struct wil6210_priv *wil,
-					   struct wil6210_vif *vif,
-					   struct sk_buff *skb)
+static struct wil_ring *wil_find_tx_ring_sta(struct wil6210_priv *wil,
+					     struct wil6210_vif *vif,
+					     struct sk_buff *skb)
 {
-	struct vring *v;
+	struct wil_ring *ring;
 	int i;
 	u8 cid;
-	struct vring_tx_data *txdata;
+	struct wil_ring_tx_data  *txdata;
+	int min_ring_id = wil_get_min_tx_ring_id(wil);
 
 	/* In the STA mode, it is expected to have only 1 VRING
 	 * for the AP we connected to.
 	 * find 1-st vring eligible for this skb and use it.
 	 */
-	for (i = 0; i < WIL6210_MAX_TX_RINGS; i++) {
-		v = &wil->vring_tx[i];
-		txdata = &wil->vring_tx_data[i];
-		if (!v->va || !txdata->enabled || txdata->mid != vif->mid)
+	for (i = min_ring_id; i < WIL6210_MAX_TX_RINGS; i++) {
+		ring = &wil->ring_tx[i];
+		txdata = &wil->ring_tx_data[i];
+		if (!ring->va || !txdata->enabled || txdata->mid != vif->mid)
 			continue;
 
-		cid = wil->vring2cid_tid[i][0];
+		cid = wil->ring2cid_tid[i][0];
 		if (cid >= WIL6210_MAX_CID) /* skip BCAST */
 			continue;
 
-		if (!wil->vring_tx_data[i].dot1x_open &&
-		    (skb->protocol != cpu_to_be16(ETH_P_PAE)))
+		if (!wil->ring_tx_data[i].dot1x_open &&
+		    skb->protocol != cpu_to_be16(ETH_P_PAE))
 			continue;
 
 		wil_dbg_txrx(wil, "Tx -> ring %d\n", i);
 
-		return v;
+		return ring;
 	}
 
-	wil_dbg_txrx(wil, "Tx while no vrings active?\n");
+	wil_dbg_txrx(wil, "Tx while no rings active?\n");
 
 	return NULL;
 }
@@ -1225,22 +1220,22 @@ static struct vring *wil_find_tx_vring_sta(struct wil6210_priv *wil,
  * Use old strategy when new is not supported yet:
  *  - for PBSS
  */
-static struct vring *wil_find_tx_bcast_1(struct wil6210_priv *wil,
-					 struct wil6210_vif *vif,
-					 struct sk_buff *skb)
+static struct wil_ring *wil_find_tx_bcast_1(struct wil6210_priv *wil,
+					    struct wil6210_vif *vif,
+					    struct sk_buff *skb)
 {
-	struct vring *v;
-	struct vring_tx_data *txdata;
-	int i = vif->bcast_vring;
+	struct wil_ring *v;
+	struct wil_ring_tx_data *txdata;
+	int i = vif->bcast_ring;
 
 	if (i < 0)
 		return NULL;
-	v = &wil->vring_tx[i];
-	txdata = &wil->vring_tx_data[i];
+	v = &wil->ring_tx[i];
+	txdata = &wil->ring_tx_data[i];
 	if (!v->va || !txdata->enabled)
 		return NULL;
-	if (!wil->vring_tx_data[i].dot1x_open &&
-	    (skb->protocol != cpu_to_be16(ETH_P_PAE)))
+	if (!wil->ring_tx_data[i].dot1x_open &&
+	    skb->protocol != cpu_to_be16(ETH_P_PAE))
 		return NULL;
 
 	return v;
@@ -1250,35 +1245,36 @@ static void wil_set_da_for_vring(struct wil6210_priv *wil,
 				 struct sk_buff *skb, int vring_index)
 {
 	struct ethhdr *eth = (void *)skb->data;
-	int cid = wil->vring2cid_tid[vring_index][0];
+	int cid = wil->ring2cid_tid[vring_index][0];
 
 	ether_addr_copy(eth->h_dest, wil->sta[cid].addr);
 }
 
-static struct vring *wil_find_tx_bcast_2(struct wil6210_priv *wil,
-					 struct wil6210_vif *vif,
-					 struct sk_buff *skb)
+static struct wil_ring *wil_find_tx_bcast_2(struct wil6210_priv *wil,
+					    struct wil6210_vif *vif,
+					    struct sk_buff *skb)
 {
-	struct vring *v, *v2;
+	struct wil_ring *v, *v2;
 	struct sk_buff *skb2;
 	int i;
 	u8 cid;
 	struct ethhdr *eth = (void *)skb->data;
 	char *src = eth->h_source;
-	struct vring_tx_data *txdata, *txdata2;
+	struct wil_ring_tx_data *txdata, *txdata2;
+	int min_ring_id = wil_get_min_tx_ring_id(wil);
 
 	/* find 1-st vring eligible for data */
-	for (i = 0; i < WIL6210_MAX_TX_RINGS; i++) {
-		v = &wil->vring_tx[i];
-		txdata = &wil->vring_tx_data[i];
+	for (i = min_ring_id; i < WIL6210_MAX_TX_RINGS; i++) {
+		v = &wil->ring_tx[i];
+		txdata = &wil->ring_tx_data[i];
 		if (!v->va || !txdata->enabled || txdata->mid != vif->mid)
 			continue;
 
-		cid = wil->vring2cid_tid[i][0];
+		cid = wil->ring2cid_tid[i][0];
 		if (cid >= WIL6210_MAX_CID) /* skip BCAST */
 			continue;
-		if (!wil->vring_tx_data[i].dot1x_open &&
-		    (skb->protocol != cpu_to_be16(ETH_P_PAE)))
+		if (!wil->ring_tx_data[i].dot1x_open &&
+		    skb->protocol != cpu_to_be16(ETH_P_PAE))
 			continue;
 
 		/* don't Tx back to source when re-routing Rx->Tx at the AP */
@@ -1298,15 +1294,15 @@ found:
 
 	/* find other active vrings and duplicate skb for each */
 	for (i++; i < WIL6210_MAX_TX_RINGS; i++) {
-		v2 = &wil->vring_tx[i];
-		txdata2 = &wil->vring_tx_data[i];
+		v2 = &wil->ring_tx[i];
+		txdata2 = &wil->ring_tx_data[i];
 		if (!v2->va || txdata2->mid != vif->mid)
 			continue;
-		cid = wil->vring2cid_tid[i][0];
+		cid = wil->ring2cid_tid[i][0];
 		if (cid >= WIL6210_MAX_CID) /* skip BCAST */
 			continue;
-		if (!wil->vring_tx_data[i].dot1x_open &&
-		    (skb->protocol != cpu_to_be16(ETH_P_PAE)))
+		if (!wil->ring_tx_data[i].dot1x_open &&
+		    skb->protocol != cpu_to_be16(ETH_P_PAE))
 			continue;
 
 		if (0 == memcmp(wil->sta[cid].addr, src, ETH_ALEN))
@@ -1316,7 +1312,7 @@ found:
 		if (skb2) {
 			wil_dbg_txrx(wil, "BCAST DUP -> ring %d\n", i);
 			wil_set_da_for_vring(wil, skb2, i);
-			wil_tx_vring(wil, vif, v2, skb2);
+			wil_tx_ring(wil, vif, v2, skb2);
 		} else {
 			wil_err(wil, "skb_copy failed\n");
 		}
@@ -1325,28 +1321,6 @@ found:
 	return v;
 }
 
-static int wil_tx_desc_map(struct vring_tx_desc *d, dma_addr_t pa, u32 len,
-			   int vring_index)
-{
-	wil_desc_addr_set(&d->dma.addr, pa);
-	d->dma.ip_length = 0;
-	/* 0..6: mac_length; 7:ip_version 0-IP6 1-IP4*/
-	d->dma.b11 = 0/*14 | BIT(7)*/;
-	d->dma.error = 0;
-	d->dma.status = 0; /* BIT(0) should be 0 for HW_OWNED */
-	d->dma.length = cpu_to_le16((u16)len);
-	d->dma.d0 = (vring_index << DMA_CFG_DESC_TX_0_QID_POS);
-	d->mac.d[0] = 0;
-	d->mac.d[1] = 0;
-	d->mac.d[2] = 0;
-	d->mac.ucode_cmd = 0;
-	/* translation type:  0 - bypass; 1 - 802.3; 2 - native wifi */
-	d->mac.d[2] = BIT(MAC_CFG_DESC_TX_2_SNAP_HDR_INSERTION_EN_POS) |
-		      (1 << MAC_CFG_DESC_TX_2_L2_TRANSLATION_TYPE_POS);
-
-	return 0;
-}
-
 static inline
 void wil_tx_desc_set_nr_frags(struct vring_tx_desc *d, int nr_frags)
 {
@@ -1454,7 +1428,7 @@ static inline void wil_set_tx_desc_last_tso(volatile struct vring_tx_desc *d)
 }
 
 static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif,
-			      struct vring *vring, struct sk_buff *skb)
+			      struct wil_ring *vring, struct sk_buff *skb)
 {
 	struct device *dev = wil_to_dev(wil);
 
@@ -1474,13 +1448,13 @@ static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	int sg_desc_cnt = 0; /* number of descriptors for current mss*/
 
 	u32 swhead = vring->swhead;
-	int used, avail = wil_vring_avail_tx(vring);
+	int used, avail = wil_ring_avail_tx(vring);
 	int nr_frags = skb_shinfo(skb)->nr_frags;
 	int min_desc_required = nr_frags + 1;
 	int mss = skb_shinfo(skb)->gso_size;	/* payload size w/o headers */
 	int f, len, hdrlen, headlen;
-	int vring_index = vring - wil->vring_tx;
-	struct vring_tx_data *txdata = &wil->vring_tx_data[vring_index];
+	int vring_index = vring - wil->ring_tx;
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[vring_index];
 	uint i = swhead;
 	dma_addr_t pa;
 	const skb_frag_t *frag = NULL;
@@ -1548,7 +1522,7 @@ static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	tcp_hdr_len = tcp_hdrlen(skb);
 	skb_net_hdr_len = skb_network_header_len(skb);
 
-	_hdr_desc = &vring->va[i].tx;
+	_hdr_desc = &vring->va[i].tx.legacy;
 
 	pa = dma_map_single(dev, skb->data, hdrlen, DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(dev, pa))) {
@@ -1556,7 +1530,8 @@ static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif,
 		goto err_exit;
 	}
 
-	wil_tx_desc_map(hdr_desc, pa, hdrlen, vring_index);
+	wil->txrx_ops.tx_desc_map((union wil_tx_desc *)hdr_desc, pa,
+				  hdrlen, vring_index);
 	wil_tx_desc_offload_setup_tso(hdr_desc, skb, wil_tso_type_hdr, is_ipv4,
 				      tcp_hdr_len, skb_net_hdr_len);
 	wil_tx_last_desc(hdr_desc);
@@ -1613,7 +1588,7 @@ static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif,
 				goto mem_error;
 			}
 
-			_desc = &vring->va[i].tx;
+			_desc = &vring->va[i].tx.legacy;
 
 			if (!_first_desc) {
 				_first_desc = _desc;
@@ -1623,7 +1598,8 @@ static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif,
 				d = &desc_mem;
 			}
 
-			wil_tx_desc_map(d, pa, lenmss, vring_index);
+			wil->txrx_ops.tx_desc_map((union wil_tx_desc *)d,
+						  pa, lenmss, vring_index);
 			wil_tx_desc_offload_setup_tso(d, skb, desc_tso_type,
 						      is_ipv4, tcp_hdr_len,
 						      skb_net_hdr_len);
@@ -1701,8 +1677,8 @@ static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	vring->ctx[i].skb = skb_get(skb);
 
 	/* performance monitoring */
-	used = wil_vring_used_tx(vring);
-	if (wil_val_in_range(wil->vring_idle_trsh,
+	used = wil_ring_used_tx(vring);
+	if (wil_val_in_range(wil->ring_idle_trsh,
 			     used, used + descs_used)) {
 		txdata->idle += get_cycles() - txdata->last_idle;
 		wil_dbg_txrx(wil,  "Ring[%2d] not idle %d -> %d\n",
@@ -1717,7 +1693,7 @@ static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	wmb();
 
 	/* advance swhead */
-	wil_vring_advance_head(vring, descs_used);
+	wil_ring_advance_head(vring, descs_used);
 	wil_dbg_txrx(wil, "TSO: Tx swhead %d -> %d\n", swhead, vring->swhead);
 
 	/* make sure all writes to descriptors (shared memory) are done before
@@ -1725,6 +1701,11 @@ static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	 */
 	wmb();
 
+	if (wil->tx_latency)
+		*(ktime_t *)&skb->cb = ktime_get();
+	else
+		memset(skb->cb, 0, sizeof(ktime_t));
+
 	wil_w(wil, vring->hwtail, vring->swhead);
 	return 0;
 
@@ -1733,12 +1714,12 @@ mem_error:
 		struct wil_ctx *ctx;
 
 		i = (swhead + descs_used - 1) % vring->size;
-		d = (struct vring_tx_desc *)&vring->va[i].tx;
-		_desc = &vring->va[i].tx;
+		d = (struct vring_tx_desc *)&vring->va[i].tx.legacy;
+		_desc = &vring->va[i].tx.legacy;
 		*d = *_desc;
 		_desc->dma.status = TX_DMA_STATUS_DU;
 		ctx = &vring->ctx[i];
-		wil_txdesc_unmap(dev, d, ctx);
+		wil_txdesc_unmap(dev, (union wil_tx_desc *)d, ctx);
 		memset(ctx, 0, sizeof(*ctx));
 		descs_used--;
 	}
@@ -1746,26 +1727,26 @@ err_exit:
 	return rc;
 }
 
-static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
-			  struct vring *vring, struct sk_buff *skb)
+static int __wil_tx_ring(struct wil6210_priv *wil, struct wil6210_vif *vif,
+			 struct wil_ring *ring, struct sk_buff *skb)
 {
 	struct device *dev = wil_to_dev(wil);
 	struct vring_tx_desc dd, *d = &dd;
 	volatile struct vring_tx_desc *_d;
-	u32 swhead = vring->swhead;
-	int avail = wil_vring_avail_tx(vring);
+	u32 swhead = ring->swhead;
+	int avail = wil_ring_avail_tx(ring);
 	int nr_frags = skb_shinfo(skb)->nr_frags;
 	uint f = 0;
-	int vring_index = vring - wil->vring_tx;
-	struct vring_tx_data *txdata = &wil->vring_tx_data[vring_index];
+	int ring_index = ring - wil->ring_tx;
+	struct wil_ring_tx_data  *txdata = &wil->ring_tx_data[ring_index];
 	uint i = swhead;
 	dma_addr_t pa;
 	int used;
-	bool mcast = (vring_index == vif->bcast_vring);
+	bool mcast = (ring_index == vif->bcast_ring);
 	uint len = skb_headlen(skb);
 
-	wil_dbg_txrx(wil, "tx_vring: %d bytes to vring %d\n", skb->len,
-		     vring_index);
+	wil_dbg_txrx(wil, "tx_ring: %d bytes to ring %d, nr_frags %d\n",
+		     skb->len, ring_index, nr_frags);
 
 	if (unlikely(!txdata->enabled))
 		return -EINVAL;
@@ -1773,23 +1754,24 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	if (unlikely(avail < 1 + nr_frags)) {
 		wil_err_ratelimited(wil,
 				    "Tx ring[%2d] full. No space for %d fragments\n",
-				    vring_index, 1 + nr_frags);
+				    ring_index, 1 + nr_frags);
 		return -ENOMEM;
 	}
-	_d = &vring->va[i].tx;
+	_d = &ring->va[i].tx.legacy;
 
 	pa = dma_map_single(dev, skb->data, skb_headlen(skb), DMA_TO_DEVICE);
 
-	wil_dbg_txrx(wil, "Tx[%2d] skb %d bytes 0x%p -> %pad\n", vring_index,
+	wil_dbg_txrx(wil, "Tx[%2d] skb %d bytes 0x%p -> %pad\n", ring_index,
 		     skb_headlen(skb), skb->data, &pa);
 	wil_hex_dump_txrx("Tx ", DUMP_PREFIX_OFFSET, 16, 1,
 			  skb->data, skb_headlen(skb), false);
 
 	if (unlikely(dma_mapping_error(dev, pa)))
 		return -EINVAL;
-	vring->ctx[i].mapped_as = wil_mapped_as_single;
+	ring->ctx[i].mapped_as = wil_mapped_as_single;
 	/* 1-st segment */
-	wil_tx_desc_map(d, pa, len, vring_index);
+	wil->txrx_ops.tx_desc_map((union wil_tx_desc *)d, pa, len,
+				   ring_index);
 	if (unlikely(mcast)) {
 		d->mac.d[0] |= BIT(MAC_CFG_DESC_TX_0_MCS_EN_POS); /* MCS 0 */
 		if (unlikely(len > WIL_BCAST_MCS0_LIMIT)) /* set MCS 1 */
@@ -1798,11 +1780,11 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	/* Process TCP/UDP checksum offloading */
 	if (unlikely(wil_tx_desc_offload_setup(d, skb))) {
 		wil_err(wil, "Tx[%2d] Failed to set cksum, drop packet\n",
-			vring_index);
+			ring_index);
 		goto dma_error;
 	}
 
-	vring->ctx[i].nr_frags = nr_frags;
+	ring->ctx[i].nr_frags = nr_frags;
 	wil_tx_desc_set_nr_frags(d, nr_frags + 1);
 
 	/* middle segments */
@@ -1812,20 +1794,21 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 		int len = skb_frag_size(frag);
 
 		*_d = *d;
-		wil_dbg_txrx(wil, "Tx[%2d] desc[%4d]\n", vring_index, i);
+		wil_dbg_txrx(wil, "Tx[%2d] desc[%4d]\n", ring_index, i);
 		wil_hex_dump_txrx("TxD ", DUMP_PREFIX_NONE, 32, 4,
 				  (const void *)d, sizeof(*d), false);
-		i = (swhead + f + 1) % vring->size;
-		_d = &vring->va[i].tx;
+		i = (swhead + f + 1) % ring->size;
+		_d = &ring->va[i].tx.legacy;
 		pa = skb_frag_dma_map(dev, frag, 0, skb_frag_size(frag),
 				      DMA_TO_DEVICE);
 		if (unlikely(dma_mapping_error(dev, pa))) {
 			wil_err(wil, "Tx[%2d] failed to map fragment\n",
-				vring_index);
+				ring_index);
 			goto dma_error;
 		}
-		vring->ctx[i].mapped_as = wil_mapped_as_page;
-		wil_tx_desc_map(d, pa, len, vring_index);
+		ring->ctx[i].mapped_as = wil_mapped_as_page;
+		wil->txrx_ops.tx_desc_map((union wil_tx_desc *)d,
+					   pa, len, ring_index);
 		/* no need to check return code -
 		 * if it succeeded for 1-st descriptor,
 		 * it will succeed here too
@@ -1837,7 +1820,7 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	d->dma.d0 |= BIT(DMA_CFG_DESC_TX_0_CMD_MARK_WB_POS);
 	d->dma.d0 |= BIT(DMA_CFG_DESC_TX_0_CMD_DMA_IT_POS);
 	*_d = *d;
-	wil_dbg_txrx(wil, "Tx[%2d] desc[%4d]\n", vring_index, i);
+	wil_dbg_txrx(wil, "Tx[%2d] desc[%4d]\n", ring_index, i);
 	wil_hex_dump_txrx("TxD ", DUMP_PREFIX_NONE, 32, 4,
 			  (const void *)d, sizeof(*d), false);
 
@@ -1845,15 +1828,15 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	 * to prevent skb release before accounting
 	 * in case of immediate "tx done"
 	 */
-	vring->ctx[i].skb = skb_get(skb);
+	ring->ctx[i].skb = skb_get(skb);
 
 	/* performance monitoring */
-	used = wil_vring_used_tx(vring);
-	if (wil_val_in_range(wil->vring_idle_trsh,
+	used = wil_ring_used_tx(ring);
+	if (wil_val_in_range(wil->ring_idle_trsh,
 			     used, used + nr_frags + 1)) {
 		txdata->idle += get_cycles() - txdata->last_idle;
 		wil_dbg_txrx(wil,  "Ring[%2d] not idle %d -> %d\n",
-			     vring_index, used, used + nr_frags + 1);
+			     ring_index, used, used + nr_frags + 1);
 	}
 
 	/* Make sure to advance the head only after descriptor update is done.
@@ -1864,17 +1847,22 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	wmb();
 
 	/* advance swhead */
-	wil_vring_advance_head(vring, nr_frags + 1);
-	wil_dbg_txrx(wil, "Tx[%2d] swhead %d -> %d\n", vring_index, swhead,
-		     vring->swhead);
-	trace_wil6210_tx(vring_index, swhead, skb->len, nr_frags);
+	wil_ring_advance_head(ring, nr_frags + 1);
+	wil_dbg_txrx(wil, "Tx[%2d] swhead %d -> %d\n", ring_index, swhead,
+		     ring->swhead);
+	trace_wil6210_tx(ring_index, swhead, skb->len, nr_frags);
 
 	/* make sure all writes to descriptors (shared memory) are done before
 	 * committing them to HW
 	 */
 	wmb();
 
-	wil_w(wil, vring->hwtail, vring->swhead);
+	if (wil->tx_latency)
+		*(ktime_t *)&skb->cb = ktime_get();
+	else
+		memset(skb->cb, 0, sizeof(ktime_t));
+
+	wil_w(wil, ring->hwtail, ring->swhead);
 
 	return 0;
  dma_error:
@@ -1883,12 +1871,14 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	for (f = 0; f < nr_frags; f++) {
 		struct wil_ctx *ctx;
 
-		i = (swhead + f) % vring->size;
-		ctx = &vring->ctx[i];
-		_d = &vring->va[i].tx;
+		i = (swhead + f) % ring->size;
+		ctx = &ring->ctx[i];
+		_d = &ring->va[i].tx.legacy;
 		*d = *_d;
 		_d->dma.status = TX_DMA_STATUS_DU;
-		wil_txdesc_unmap(dev, d, ctx);
+		wil->txrx_ops.tx_desc_unmap(dev,
+					    (union wil_tx_desc *)d,
+					    ctx);
 
 		memset(ctx, 0, sizeof(*ctx));
 	}
@@ -1896,11 +1886,11 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	return -EINVAL;
 }
 
-static int wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
-			struct vring *vring, struct sk_buff *skb)
+static int wil_tx_ring(struct wil6210_priv *wil, struct wil6210_vif *vif,
+		       struct wil_ring *ring, struct sk_buff *skb)
 {
-	int vring_index = vring - wil->vring_tx;
-	struct vring_tx_data *txdata = &wil->vring_tx_data[vring_index];
+	int ring_index = ring - wil->ring_tx;
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[ring_index];
 	int rc;
 
 	spin_lock(&txdata->lock);
@@ -1914,8 +1904,8 @@ static int wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 		return -EINVAL;
 	}
 
-	rc = (skb_is_gso(skb) ? __wil_tx_vring_tso : __wil_tx_vring)
-	     (wil, vif, vring, skb);
+	rc = (skb_is_gso(skb) ? wil->txrx_ops.tx_ring_tso : __wil_tx_ring)
+	     (wil, vif, ring, skb);
 
 	spin_unlock(&txdata->lock);
 
@@ -1941,7 +1931,7 @@ static int wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
  */
 static inline void __wil_update_net_queues(struct wil6210_priv *wil,
 					   struct wil6210_vif *vif,
-					   struct vring *vring,
+					   struct wil_ring *ring,
 					   bool check_stop)
 {
 	int i;
@@ -1949,9 +1939,9 @@ static inline void __wil_update_net_queues(struct wil6210_priv *wil,
 	if (unlikely(!vif))
 		return;
 
-	if (vring)
+	if (ring)
 		wil_dbg_txrx(wil, "vring %d, mid %d, check_stop=%d, stopped=%d",
-			     (int)(vring - wil->vring_tx), vif->mid, check_stop,
+			     (int)(ring - wil->ring_tx), vif->mid, check_stop,
 			     vif->net_queue_stopped);
 	else
 		wil_dbg_txrx(wil, "check_stop=%d, mid=%d, stopped=%d",
@@ -1962,7 +1952,7 @@ static inline void __wil_update_net_queues(struct wil6210_priv *wil,
 		return;
 
 	if (check_stop) {
-		if (!vring || unlikely(wil_vring_avail_low(vring))) {
+		if (!ring || unlikely(wil_ring_avail_low(ring))) {
 			/* not enough room in the vring */
 			netif_tx_stop_all_queues(vif_to_ndev(vif));
 			vif->net_queue_stopped = true;
@@ -1978,22 +1968,22 @@ static inline void __wil_update_net_queues(struct wil6210_priv *wil,
 
 	/* check wake */
 	for (i = 0; i < WIL6210_MAX_TX_RINGS; i++) {
-		struct vring *cur_vring = &wil->vring_tx[i];
-		struct vring_tx_data *txdata = &wil->vring_tx_data[i];
+		struct wil_ring *cur_ring = &wil->ring_tx[i];
+		struct wil_ring_tx_data  *txdata = &wil->ring_tx_data[i];
 
-		if (txdata->mid != vif->mid || !cur_vring->va ||
-		    !txdata->enabled || cur_vring == vring)
+		if (txdata->mid != vif->mid || !cur_ring->va ||
+		    !txdata->enabled || cur_ring == ring)
 			continue;
 
-		if (wil_vring_avail_low(cur_vring)) {
-			wil_dbg_txrx(wil, "vring %d full, can't wake\n",
-				     (int)(cur_vring - wil->vring_tx));
+		if (wil_ring_avail_low(cur_ring)) {
+			wil_dbg_txrx(wil, "ring %d full, can't wake\n",
+				     (int)(cur_ring - wil->ring_tx));
 			return;
 		}
 	}
 
-	if (!vring || wil_vring_avail_high(vring)) {
-		/* enough room in the vring */
+	if (!ring || wil_ring_avail_high(ring)) {
+		/* enough room in the ring */
 		wil_dbg_txrx(wil, "calling netif_tx_wake\n");
 		netif_tx_wake_all_queues(vif_to_ndev(vif));
 		vif->net_queue_stopped = false;
@@ -2001,18 +1991,18 @@ static inline void __wil_update_net_queues(struct wil6210_priv *wil,
 }
 
 void wil_update_net_queues(struct wil6210_priv *wil, struct wil6210_vif *vif,
-			   struct vring *vring, bool check_stop)
+			   struct wil_ring *ring, bool check_stop)
 {
 	spin_lock(&wil->net_queue_lock);
-	__wil_update_net_queues(wil, vif, vring, check_stop);
+	__wil_update_net_queues(wil, vif, ring, check_stop);
 	spin_unlock(&wil->net_queue_lock);
 }
 
 void wil_update_net_queues_bh(struct wil6210_priv *wil, struct wil6210_vif *vif,
-			      struct vring *vring, bool check_stop)
+			      struct wil_ring *ring, bool check_stop)
 {
 	spin_lock_bh(&wil->net_queue_lock);
-	__wil_update_net_queues(wil, vif, vring, check_stop);
+	__wil_update_net_queues(wil, vif, ring, check_stop);
 	spin_unlock_bh(&wil->net_queue_lock);
 }
 
@@ -2022,7 +2012,7 @@ netdev_tx_t wil_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	struct wil6210_priv *wil = vif_to_wil(vif);
 	struct ethhdr *eth = (void *)skb->data;
 	bool bcast = is_multicast_ether_addr(eth->h_dest);
-	struct vring *vring;
+	struct wil_ring *ring;
 	static bool pr_once_fw;
 	int rc;
 
@@ -2048,36 +2038,36 @@ netdev_tx_t wil_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	/* find vring */
 	if (vif->wdev.iftype == NL80211_IFTYPE_STATION && !vif->pbss) {
 		/* in STA mode (ESS), all to same VRING (to AP) */
-		vring = wil_find_tx_vring_sta(wil, vif, skb);
+		ring = wil_find_tx_ring_sta(wil, vif, skb);
 	} else if (bcast) {
 		if (vif->pbss)
 			/* in pbss, no bcast VRING - duplicate skb in
 			 * all stations VRINGs
 			 */
-			vring = wil_find_tx_bcast_2(wil, vif, skb);
+			ring = wil_find_tx_bcast_2(wil, vif, skb);
 		else if (vif->wdev.iftype == NL80211_IFTYPE_AP)
 			/* AP has a dedicated bcast VRING */
-			vring = wil_find_tx_bcast_1(wil, vif, skb);
+			ring = wil_find_tx_bcast_1(wil, vif, skb);
 		else
 			/* unexpected combination, fallback to duplicating
 			 * the skb in all stations VRINGs
 			 */
-			vring = wil_find_tx_bcast_2(wil, vif, skb);
+			ring = wil_find_tx_bcast_2(wil, vif, skb);
 	} else {
 		/* unicast, find specific VRING by dest. address */
-		vring = wil_find_tx_ucast(wil, vif, skb);
+		ring = wil_find_tx_ucast(wil, vif, skb);
 	}
-	if (unlikely(!vring)) {
-		wil_dbg_txrx(wil, "No Tx VRING found for %pM\n", eth->h_dest);
+	if (unlikely(!ring)) {
+		wil_dbg_txrx(wil, "No Tx RING found for %pM\n", eth->h_dest);
 		goto drop;
 	}
 	/* set up vring entry */
-	rc = wil_tx_vring(wil, vif, vring, skb);
+	rc = wil_tx_ring(wil, vif, ring, skb);
 
 	switch (rc) {
 	case 0:
 		/* shall we stop net queues? */
-		wil_update_net_queues_bh(wil, vif, vring, true);
+		wil_update_net_queues_bh(wil, vif, ring, true);
 		/* statistics will be updated on the tx_complete */
 		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
@@ -2093,20 +2083,29 @@ netdev_tx_t wil_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	return NET_XMIT_DROP;
 }
 
-static inline bool wil_need_txstat(struct sk_buff *skb)
+void wil_tx_latency_calc(struct wil6210_priv *wil, struct sk_buff *skb,
+			 struct wil_sta_info *sta)
 {
-	struct ethhdr *eth = (void *)skb->data;
+	int skb_time_us;
+	int bin;
 
-	return is_unicast_ether_addr(eth->h_dest) && skb->sk &&
-	       (skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS);
-}
+	if (!wil->tx_latency)
+		return;
 
-static inline void wil_consume_skb(struct sk_buff *skb, bool acked)
-{
-	if (unlikely(wil_need_txstat(skb)))
-		skb_complete_wifi_ack(skb, acked);
-	else
-		acked ? dev_consume_skb_any(skb) : dev_kfree_skb_any(skb);
+	if (ktime_to_ms(*(ktime_t *)&skb->cb) == 0)
+		return;
+
+	skb_time_us = ktime_us_delta(ktime_get(), *(ktime_t *)&skb->cb);
+	bin = skb_time_us / wil->tx_latency_res;
+	bin = min_t(int, bin, WIL_NUM_LATENCY_BINS - 1);
+
+	wil_dbg_txrx(wil, "skb time %dus => bin %d\n", skb_time_us, bin);
+	sta->tx_latency_bins[bin]++;
+	sta->stats.tx_latency_total_us += skb_time_us;
+	if (skb_time_us < sta->stats.tx_latency_min_us)
+		sta->stats.tx_latency_min_us = skb_time_us;
+	if (skb_time_us > sta->stats.tx_latency_max_us)
+		sta->stats.tx_latency_max_us = skb_time_us;
 }
 
 /**
@@ -2121,10 +2120,10 @@ int wil_tx_complete(struct wil6210_vif *vif, int ringid)
 	struct wil6210_priv *wil = vif_to_wil(vif);
 	struct net_device *ndev = vif_to_ndev(vif);
 	struct device *dev = wil_to_dev(wil);
-	struct vring *vring = &wil->vring_tx[ringid];
-	struct vring_tx_data *txdata = &wil->vring_tx_data[ringid];
+	struct wil_ring *vring = &wil->ring_tx[ringid];
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[ringid];
 	int done = 0;
-	int cid = wil->vring2cid_tid[ringid][0];
+	int cid = wil->ring2cid_tid[ringid][0];
 	struct wil_net_stats *stats = NULL;
 	volatile struct vring_tx_desc *_d;
 	int used_before_complete;
@@ -2142,12 +2141,12 @@ int wil_tx_complete(struct wil6210_vif *vif, int ringid)
 
 	wil_dbg_txrx(wil, "tx_complete: (%d)\n", ringid);
 
-	used_before_complete = wil_vring_used_tx(vring);
+	used_before_complete = wil_ring_used_tx(vring);
 
 	if (cid < WIL6210_MAX_CID)
 		stats = &wil->sta[cid].stats;
 
-	while (!wil_vring_is_empty(vring)) {
+	while (!wil_ring_is_empty(vring)) {
 		int new_swtail;
 		struct wil_ctx *ctx = &vring->ctx[vring->swtail];
 		/**
@@ -2158,7 +2157,7 @@ int wil_tx_complete(struct wil6210_vif *vif, int ringid)
 		int lf = (vring->swtail + ctx->nr_frags) % vring->size;
 		/* TODO: check we are not past head */
 
-		_d = &vring->va[lf].tx;
+		_d = &vring->va[lf].tx.legacy;
 		if (unlikely(!(_d->dma.status & TX_DMA_STATUS_DU)))
 			break;
 
@@ -2170,7 +2169,7 @@ int wil_tx_complete(struct wil6210_vif *vif, int ringid)
 
 			ctx = &vring->ctx[vring->swtail];
 			skb = ctx->skb;
-			_d = &vring->va[vring->swtail].tx;
+			_d = &vring->va[vring->swtail].tx.legacy;
 
 			*d = *_d;
 
@@ -2184,7 +2183,9 @@ int wil_tx_complete(struct wil6210_vif *vif, int ringid)
 			wil_hex_dump_txrx("TxCD ", DUMP_PREFIX_NONE, 32, 4,
 					  (const void *)d, sizeof(*d), false);
 
-			wil_txdesc_unmap(dev, d, ctx);
+			wil->txrx_ops.tx_desc_unmap(dev,
+						    (union wil_tx_desc *)d,
+						    ctx);
 
 			if (skb) {
 				if (likely(d->dma.error == 0)) {
@@ -2193,6 +2194,9 @@ int wil_tx_complete(struct wil6210_vif *vif, int ringid)
 					if (stats) {
 						stats->tx_packets++;
 						stats->tx_bytes += skb->len;
+
+						wil_tx_latency_calc(wil, skb,
+							&wil->sta[cid]);
 					}
 				} else {
 					ndev->stats.tx_errors++;
@@ -2203,7 +2207,7 @@ int wil_tx_complete(struct wil6210_vif *vif, int ringid)
 			}
 			memset(ctx, 0, sizeof(*ctx));
 			/* Make sure the ctx is zeroed before updating the tail
-			 * to prevent a case where wil_tx_vring will see
+			 * to prevent a case where wil_tx_ring will see
 			 * this descriptor as used and handle it before ctx zero
 			 * is completed.
 			 */
@@ -2213,14 +2217,14 @@ int wil_tx_complete(struct wil6210_vif *vif, int ringid)
 			 *   so hardware will not try to process this desc.,
 			 * - rest of descriptor will be initialized on Tx.
 			 */
-			vring->swtail = wil_vring_next_tail(vring);
+			vring->swtail = wil_ring_next_tail(vring);
 			done++;
 		}
 	}
 
 	/* performance monitoring */
-	used_new = wil_vring_used_tx(vring);
-	if (wil_val_in_range(wil->vring_idle_trsh,
+	used_new = wil_ring_used_tx(vring);
+	if (wil_val_in_range(wil->ring_idle_trsh,
 			     used_new, used_before_complete)) {
 		wil_dbg_txrx(wil, "Ring[%2d] idle %d -> %d\n",
 			     ringid, used_before_complete, used_new);
@@ -2233,3 +2237,49 @@ int wil_tx_complete(struct wil6210_vif *vif, int ringid)
 
 	return done;
 }
+
+static inline int wil_tx_init(struct wil6210_priv *wil)
+{
+	return 0;
+}
+
+static inline void wil_tx_fini(struct wil6210_priv *wil) {}
+
+static void wil_get_reorder_params(struct wil6210_priv *wil,
+				   struct sk_buff *skb, int *tid, int *cid,
+				   int *mid, u16 *seq, int *mcast, int *retry)
+{
+	struct vring_rx_desc *d = wil_skb_rxdesc(skb);
+
+	*tid = wil_rxdesc_tid(d);
+	*cid = wil_rxdesc_cid(d);
+	*mid = wil_rxdesc_mid(d);
+	*seq = wil_rxdesc_seq(d);
+	*mcast = wil_rxdesc_mcast(d);
+	*retry = wil_rxdesc_retry(d);
+}
+
+void wil_init_txrx_ops_legacy_dma(struct wil6210_priv *wil)
+{
+	wil->txrx_ops.configure_interrupt_moderation =
+		wil_configure_interrupt_moderation;
+	/* TX ops */
+	wil->txrx_ops.tx_desc_map = wil_tx_desc_map;
+	wil->txrx_ops.tx_desc_unmap = wil_txdesc_unmap;
+	wil->txrx_ops.tx_ring_tso =  __wil_tx_vring_tso;
+	wil->txrx_ops.ring_init_tx = wil_vring_init_tx;
+	wil->txrx_ops.ring_fini_tx = wil_vring_free;
+	wil->txrx_ops.ring_init_bcast = wil_vring_init_bcast;
+	wil->txrx_ops.tx_init = wil_tx_init;
+	wil->txrx_ops.tx_fini = wil_tx_fini;
+	/* RX ops */
+	wil->txrx_ops.rx_init = wil_rx_init;
+	wil->txrx_ops.wmi_addba_rx_resp = wmi_addba_rx_resp;
+	wil->txrx_ops.get_reorder_params = wil_get_reorder_params;
+	wil->txrx_ops.get_netif_rx_params =
+		wil_get_netif_rx_params;
+	wil->txrx_ops.rx_crypto_check = wil_rx_crypto_check;
+	wil->txrx_ops.rx_error_check = wil_rx_error_check;
+	wil->txrx_ops.is_rx_idle = wil_is_rx_idle;
+	wil->txrx_ops.rx_fini = wil_rx_fini;
+}
diff --git a/drivers/net/wireless/ath/wil6210/txrx.h b/drivers/net/wireless/ath/wil6210/txrx.h
index 5f07717acc2c..9d83be481839 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.h
+++ b/drivers/net/wireless/ath/wil6210/txrx.h
@@ -18,6 +18,9 @@
 #ifndef WIL6210_TXRX_H
 #define WIL6210_TXRX_H
 
+#include "wil6210.h"
+#include "txrx_edma.h"
+
 #define BUF_SW_OWNED    (1)
 #define BUF_HW_OWNED    (0)
 
@@ -29,19 +32,13 @@
 
 /* Tx/Rx path */
 
-/* Common representation of physical address in Vring */
-struct vring_dma_addr {
-	__le32 addr_low;
-	__le16 addr_high;
-} __packed;
-
-static inline dma_addr_t wil_desc_addr(struct vring_dma_addr *addr)
+static inline dma_addr_t wil_desc_addr(struct wil_ring_dma_addr *addr)
 {
 	return le32_to_cpu(addr->addr_low) |
 			   ((u64)le16_to_cpu(addr->addr_high) << 32);
 }
 
-static inline void wil_desc_addr_set(struct vring_dma_addr *addr,
+static inline void wil_desc_addr_set(struct wil_ring_dma_addr *addr,
 				     dma_addr_t pa)
 {
 	addr->addr_low = cpu_to_le32(lower_32_bits(pa));
@@ -294,7 +291,7 @@ struct vring_tx_mac {
  */
 struct vring_tx_dma {
 	u32 d0;
-	struct vring_dma_addr addr;
+	struct wil_ring_dma_addr addr;
 	u8  ip_length;
 	u8  b11;       /* 0..6: mac_length; 7:ip_version */
 	u8  error;     /* 0..2: err; 3..7: reserved; */
@@ -428,7 +425,7 @@ struct vring_rx_mac {
 
 struct vring_rx_dma {
 	u32 d0;
-	struct vring_dma_addr addr;
+	struct wil_ring_dma_addr addr;
 	u8  ip_length;
 	u8  b11;
 	u8  error;
@@ -441,14 +438,24 @@ struct vring_tx_desc {
 	struct vring_tx_dma dma;
 } __packed;
 
+union wil_tx_desc {
+	struct vring_tx_desc legacy;
+	struct wil_tx_enhanced_desc enhanced;
+} __packed;
+
 struct vring_rx_desc {
 	struct vring_rx_mac mac;
 	struct vring_rx_dma dma;
 } __packed;
 
-union vring_desc {
-	struct vring_tx_desc tx;
-	struct vring_rx_desc rx;
+union wil_rx_desc {
+	struct vring_rx_desc legacy;
+	struct wil_rx_enhanced_desc enhanced;
+} __packed;
+
+union wil_ring_desc {
+	union wil_tx_desc tx;
+	union wil_rx_desc rx;
 } __packed;
 
 static inline int wil_rxdesc_tid(struct vring_rx_desc *d)
@@ -493,6 +500,11 @@ static inline int wil_rxdesc_ext_subtype(struct vring_rx_desc *d)
 	return WIL_GET_BITS(d->mac.d0, 28, 31);
 }
 
+static inline int wil_rxdesc_retry(struct vring_rx_desc *d)
+{
+	return WIL_GET_BITS(d->mac.d0, 31, 31);
+}
+
 static inline int wil_rxdesc_key_id(struct vring_rx_desc *d)
 {
 	return WIL_GET_BITS(d->mac.d1, 4, 5);
@@ -528,6 +540,76 @@ static inline struct vring_rx_desc *wil_skb_rxdesc(struct sk_buff *skb)
 	return (void *)skb->cb;
 }
 
+static inline int wil_ring_is_empty(struct wil_ring *ring)
+{
+	return ring->swhead == ring->swtail;
+}
+
+static inline u32 wil_ring_next_tail(struct wil_ring *ring)
+{
+	return (ring->swtail + 1) % ring->size;
+}
+
+static inline void wil_ring_advance_head(struct wil_ring *ring, int n)
+{
+	ring->swhead = (ring->swhead + n) % ring->size;
+}
+
+static inline int wil_ring_is_full(struct wil_ring *ring)
+{
+	return wil_ring_next_tail(ring) == ring->swhead;
+}
+
+static inline bool wil_need_txstat(struct sk_buff *skb)
+{
+	struct ethhdr *eth = (void *)skb->data;
+
+	return is_unicast_ether_addr(eth->h_dest) && skb->sk &&
+	       (skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS);
+}
+
+static inline void wil_consume_skb(struct sk_buff *skb, bool acked)
+{
+	if (unlikely(wil_need_txstat(skb)))
+		skb_complete_wifi_ack(skb, acked);
+	else
+		acked ? dev_consume_skb_any(skb) : dev_kfree_skb_any(skb);
+}
+
+/* Used space in Tx ring */
+static inline int wil_ring_used_tx(struct wil_ring *ring)
+{
+	u32 swhead = ring->swhead;
+	u32 swtail = ring->swtail;
+
+	return (ring->size + swhead - swtail) % ring->size;
+}
+
+/* Available space in Tx ring */
+static inline int wil_ring_avail_tx(struct wil_ring *ring)
+{
+	return ring->size - wil_ring_used_tx(ring) - 1;
+}
+
+static inline int wil_get_min_tx_ring_id(struct wil6210_priv *wil)
+{
+	/* In Enhanced DMA ring 0 is reserved for RX */
+	return wil->use_enhanced_dma_hw ? 1 : 0;
+}
+
+/* similar to ieee80211_ version, but FC contain only 1-st byte */
+static inline int wil_is_back_req(u8 fc)
+{
+	return (fc & (IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) ==
+	       (IEEE80211_FTYPE_CTL | IEEE80211_STYPE_BACK_REQ);
+}
+
+/* wil_val_in_range - check if value in [min,max) */
+static inline bool wil_val_in_range(int val, int min, int max)
+{
+	return val >= min && val < max;
+}
+
 void wil_netif_rx_any(struct sk_buff *skb, struct net_device *ndev);
 void wil_rx_reorder(struct wil6210_priv *wil, struct sk_buff *skb);
 void wil_rx_bar(struct wil6210_priv *wil, struct wil6210_vif *vif,
@@ -536,5 +618,9 @@ struct wil_tid_ampdu_rx *wil_tid_ampdu_rx_alloc(struct wil6210_priv *wil,
 						int size, u16 ssn);
 void wil_tid_ampdu_rx_free(struct wil6210_priv *wil,
 			   struct wil_tid_ampdu_rx *r);
+void wil_tx_data_init(struct wil_ring_tx_data *txdata);
+void wil_init_txrx_ops_legacy_dma(struct wil6210_priv *wil);
+void wil_tx_latency_calc(struct wil6210_priv *wil, struct sk_buff *skb,
+			 struct wil_sta_info *sta);
 
 #endif /* WIL6210_TXRX_H */
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.c b/drivers/net/wireless/ath/wil6210/txrx_edma.c
new file mode 100644
index 000000000000..bca61cb44c37
--- /dev/null
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.c
@@ -0,0 +1,1608 @@
+/*
+ * Copyright (c) 2012-2018 The Linux Foundation. All rights reserved.
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/moduleparam.h>
+#include <linux/prefetch.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include "wil6210.h"
+#include "txrx_edma.h"
+#include "txrx.h"
+#include "trace.h"
+
+#define WIL_EDMA_MAX_DATA_OFFSET (2)
+/* RX buffer size must be aligned to 4 bytes */
+#define WIL_EDMA_RX_BUF_LEN_DEFAULT (2048)
+
+static void wil_tx_desc_unmap_edma(struct device *dev,
+				   union wil_tx_desc *desc,
+				   struct wil_ctx *ctx)
+{
+	struct wil_tx_enhanced_desc *d = (struct wil_tx_enhanced_desc *)desc;
+	dma_addr_t pa = wil_tx_desc_get_addr_edma(&d->dma);
+	u16 dmalen = le16_to_cpu(d->dma.length);
+
+	switch (ctx->mapped_as) {
+	case wil_mapped_as_single:
+		dma_unmap_single(dev, pa, dmalen, DMA_TO_DEVICE);
+		break;
+	case wil_mapped_as_page:
+		dma_unmap_page(dev, pa, dmalen, DMA_TO_DEVICE);
+		break;
+	default:
+		break;
+	}
+}
+
+static int wil_find_free_sring(struct wil6210_priv *wil)
+{
+	int i;
+
+	for (i = 0; i < WIL6210_MAX_STATUS_RINGS; i++) {
+		if (!wil->srings[i].va)
+			return i;
+	}
+
+	return -EINVAL;
+}
+
+static void wil_sring_free(struct wil6210_priv *wil,
+			   struct wil_status_ring *sring)
+{
+	struct device *dev = wil_to_dev(wil);
+	size_t sz;
+
+	if (!sring || !sring->va)
+		return;
+
+	sz = sring->elem_size * sring->size;
+
+	wil_dbg_misc(wil, "status_ring_free, size(bytes)=%zu, 0x%p:%pad\n",
+		     sz, sring->va, &sring->pa);
+
+	dma_free_coherent(dev, sz, (void *)sring->va, sring->pa);
+	sring->pa = 0;
+	sring->va = NULL;
+}
+
+static int wil_sring_alloc(struct wil6210_priv *wil,
+			   struct wil_status_ring *sring)
+{
+	struct device *dev = wil_to_dev(wil);
+	size_t sz = sring->elem_size * sring->size;
+
+	wil_dbg_misc(wil, "status_ring_alloc: size=%zu\n", sz);
+
+	if (sz == 0) {
+		wil_err(wil, "Cannot allocate a zero size status ring\n");
+		return -EINVAL;
+	}
+
+	sring->swhead = 0;
+
+	/* Status messages are allocated and initialized to 0. This is necessary
+	 * since DR bit should be initialized to 0.
+	 */
+	sring->va = dma_zalloc_coherent(dev, sz, &sring->pa, GFP_KERNEL);
+	if (!sring->va)
+		return -ENOMEM;
+
+	wil_dbg_misc(wil, "status_ring[%d] 0x%p:%pad\n", sring->size, sring->va,
+		     &sring->pa);
+
+	return 0;
+}
+
+static int wil_tx_init_edma(struct wil6210_priv *wil)
+{
+	int ring_id = wil_find_free_sring(wil);
+	struct wil_status_ring *sring;
+	int rc;
+	u16 status_ring_size;
+
+	if (wil->tx_status_ring_order < WIL_SRING_SIZE_ORDER_MIN ||
+	    wil->tx_status_ring_order > WIL_SRING_SIZE_ORDER_MAX)
+		wil->tx_status_ring_order = WIL_TX_SRING_SIZE_ORDER_DEFAULT;
+
+	status_ring_size = 1 << wil->tx_status_ring_order;
+
+	wil_dbg_misc(wil, "init TX sring: size=%u, ring_id=%u\n",
+		     status_ring_size, ring_id);
+
+	if (ring_id < 0)
+		return ring_id;
+
+	/* Allocate Tx status ring. Tx descriptor rings will be
+	 * allocated on WMI connect event
+	 */
+	sring = &wil->srings[ring_id];
+
+	sring->is_rx = false;
+	sring->size = status_ring_size;
+	sring->elem_size = sizeof(struct wil_ring_tx_status);
+	rc = wil_sring_alloc(wil, sring);
+	if (rc)
+		return rc;
+
+	rc = wil_wmi_tx_sring_cfg(wil, ring_id);
+	if (rc)
+		goto out_free;
+
+	sring->desc_rdy_pol = 1;
+	wil->tx_sring_idx = ring_id;
+
+	return 0;
+out_free:
+	wil_sring_free(wil, sring);
+	return rc;
+}
+
+/**
+ * Allocate one skb for Rx descriptor RING
+ */
+static int wil_ring_alloc_skb_edma(struct wil6210_priv *wil,
+				   struct wil_ring *ring, u32 i)
+{
+	struct device *dev = wil_to_dev(wil);
+	unsigned int sz = ALIGN(wil->rx_buf_len, 4);
+	dma_addr_t pa;
+	u16 buff_id;
+	struct list_head *active = &wil->rx_buff_mgmt.active;
+	struct list_head *free = &wil->rx_buff_mgmt.free;
+	struct wil_rx_buff *rx_buff;
+	struct wil_rx_buff *buff_arr = wil->rx_buff_mgmt.buff_arr;
+	struct sk_buff *skb;
+	struct wil_rx_enhanced_desc dd, *d = &dd;
+	struct wil_rx_enhanced_desc *_d = (struct wil_rx_enhanced_desc *)
+		&ring->va[i].rx.enhanced;
+
+	if (unlikely(list_empty(free))) {
+		wil->rx_buff_mgmt.free_list_empty_cnt++;
+		return -EAGAIN;
+	}
+
+	skb = dev_alloc_skb(sz);
+	if (unlikely(!skb))
+		return -ENOMEM;
+
+	skb_put(skb, sz);
+
+	/**
+	 * Make sure that the network stack calculates checksum for packets
+	 * which failed the HW checksum calculation
+	 */
+	skb->ip_summed = CHECKSUM_NONE;
+
+	pa = dma_map_single(dev, skb->data, skb->len, DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(dev, pa))) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	/* Get the buffer ID - the index of the rx buffer in the buff_arr */
+	rx_buff = list_first_entry(free, struct wil_rx_buff, list);
+	buff_id = rx_buff->id;
+
+	/* Move a buffer from the free list to the active list */
+	list_move(&rx_buff->list, active);
+
+	buff_arr[buff_id].skb = skb;
+
+	wil_desc_set_addr_edma(&d->dma.addr, &d->dma.addr_high_high, pa);
+	d->dma.length = cpu_to_le16(sz);
+	d->mac.buff_id = cpu_to_le16(buff_id);
+	*_d = *d;
+
+	/* Save the physical address in skb->cb for later use in dma_unmap */
+	memcpy(skb->cb, &pa, sizeof(pa));
+
+	return 0;
+}
+
+static inline
+void wil_get_next_rx_status_msg(struct wil_status_ring *sring, void *msg)
+{
+	memcpy(msg, (void *)(sring->va + (sring->elem_size * sring->swhead)),
+	       sring->elem_size);
+}
+
+static inline void wil_sring_advance_swhead(struct wil_status_ring *sring)
+{
+	sring->swhead = (sring->swhead + 1) % sring->size;
+	if (sring->swhead == 0)
+		sring->desc_rdy_pol = 1 - sring->desc_rdy_pol;
+}
+
+static int wil_rx_refill_edma(struct wil6210_priv *wil)
+{
+	struct wil_ring *ring = &wil->ring_rx;
+	u32 next_head;
+	int rc = 0;
+	u32 swtail = *ring->edma_rx_swtail.va;
+
+	for (; next_head = wil_ring_next_head(ring), (next_head != swtail);
+	     ring->swhead = next_head) {
+		rc = wil_ring_alloc_skb_edma(wil, ring, ring->swhead);
+		if (unlikely(rc)) {
+			if (rc == -EAGAIN)
+				wil_dbg_txrx(wil, "No free buffer ID found\n");
+			else
+				wil_err_ratelimited(wil,
+						    "Error %d in refill desc[%d]\n",
+						    rc, ring->swhead);
+			break;
+		}
+	}
+
+	/* make sure all writes to descriptors (shared memory) are done before
+	 * committing them to HW
+	 */
+	wmb();
+
+	wil_w(wil, ring->hwtail, ring->swhead);
+
+	return rc;
+}
+
+static void wil_move_all_rx_buff_to_free_list(struct wil6210_priv *wil,
+					      struct wil_ring *ring)
+{
+	struct device *dev = wil_to_dev(wil);
+	u32 next_tail;
+	u32 swhead = (ring->swhead + 1) % ring->size;
+	dma_addr_t pa;
+	u16 dmalen;
+
+	for (; next_tail = wil_ring_next_tail(ring), (next_tail != swhead);
+	     ring->swtail = next_tail) {
+		struct wil_rx_enhanced_desc dd, *d = &dd;
+		struct wil_rx_enhanced_desc *_d =
+			(struct wil_rx_enhanced_desc *)
+			&ring->va[ring->swtail].rx.enhanced;
+		struct sk_buff *skb;
+		u16 buff_id;
+
+		*d = *_d;
+		pa = wil_rx_desc_get_addr_edma(&d->dma);
+		dmalen = le16_to_cpu(d->dma.length);
+		dma_unmap_single(dev, pa, dmalen, DMA_FROM_DEVICE);
+
+		/* Extract the SKB from the rx_buff management array */
+		buff_id = __le16_to_cpu(d->mac.buff_id);
+		if (buff_id >= wil->rx_buff_mgmt.size) {
+			wil_err(wil, "invalid buff_id %d\n", buff_id);
+			continue;
+		}
+		skb = wil->rx_buff_mgmt.buff_arr[buff_id].skb;
+		wil->rx_buff_mgmt.buff_arr[buff_id].skb = NULL;
+		if (unlikely(!skb))
+			wil_err(wil, "No Rx skb at buff_id %d\n", buff_id);
+		else
+			kfree_skb(skb);
+
+		/* Move the buffer from the active to the free list */
+		list_move(&wil->rx_buff_mgmt.buff_arr[buff_id].list,
+			  &wil->rx_buff_mgmt.free);
+	}
+}
+
+static void wil_free_rx_buff_arr(struct wil6210_priv *wil)
+{
+	struct wil_ring *ring = &wil->ring_rx;
+
+	if (!wil->rx_buff_mgmt.buff_arr)
+		return;
+
+	/* Move all the buffers to the free list in case active list is
+	 * not empty in order to release all SKBs before deleting the array
+	 */
+	wil_move_all_rx_buff_to_free_list(wil, ring);
+
+	kfree(wil->rx_buff_mgmt.buff_arr);
+	wil->rx_buff_mgmt.buff_arr = NULL;
+}
+
+static int wil_init_rx_buff_arr(struct wil6210_priv *wil,
+				size_t size)
+{
+	struct wil_rx_buff *buff_arr;
+	struct list_head *active = &wil->rx_buff_mgmt.active;
+	struct list_head *free = &wil->rx_buff_mgmt.free;
+	int i;
+
+	wil->rx_buff_mgmt.buff_arr = kcalloc(size, sizeof(struct wil_rx_buff),
+					     GFP_KERNEL);
+	if (!wil->rx_buff_mgmt.buff_arr)
+		return -ENOMEM;
+
+	/* Set list heads */
+	INIT_LIST_HEAD(active);
+	INIT_LIST_HEAD(free);
+
+	/* Linkify the list */
+	buff_arr = wil->rx_buff_mgmt.buff_arr;
+	for (i = 0; i < size; i++) {
+		list_add(&buff_arr[i].list, free);
+		buff_arr[i].id = i;
+	}
+
+	wil->rx_buff_mgmt.size = size;
+
+	return 0;
+}
+
+static int wil_init_rx_sring(struct wil6210_priv *wil,
+			     u16 status_ring_size,
+			     size_t elem_size,
+			     u16 ring_id)
+{
+	struct wil_status_ring *sring = &wil->srings[ring_id];
+	int rc;
+
+	wil_dbg_misc(wil, "init RX sring: size=%u, ring_id=%u\n", sring->size,
+		     ring_id);
+
+	memset(&sring->rx_data, 0, sizeof(sring->rx_data));
+
+	sring->is_rx = true;
+	sring->size = status_ring_size;
+	sring->elem_size = elem_size;
+	rc = wil_sring_alloc(wil, sring);
+	if (rc)
+		return rc;
+
+	rc = wil_wmi_rx_sring_add(wil, ring_id);
+	if (rc)
+		goto out_free;
+
+	sring->desc_rdy_pol = 1;
+
+	return 0;
+out_free:
+	wil_sring_free(wil, sring);
+	return rc;
+}
+
+static int wil_ring_alloc_desc_ring(struct wil6210_priv *wil,
+				    struct wil_ring *ring)
+{
+	struct device *dev = wil_to_dev(wil);
+	size_t sz = ring->size * sizeof(ring->va[0]);
+
+	wil_dbg_misc(wil, "alloc_desc_ring:\n");
+
+	BUILD_BUG_ON(sizeof(ring->va[0]) != 32);
+
+	ring->swhead = 0;
+	ring->swtail = 0;
+	ring->ctx = kcalloc(ring->size, sizeof(ring->ctx[0]), GFP_KERNEL);
+	if (!ring->ctx)
+		goto err;
+
+	ring->va = dma_zalloc_coherent(dev, sz, &ring->pa, GFP_KERNEL);
+	if (!ring->va)
+		goto err_free_ctx;
+
+	if (ring->is_rx) {
+		sz = sizeof(*ring->edma_rx_swtail.va);
+		ring->edma_rx_swtail.va =
+			dma_zalloc_coherent(dev, sz, &ring->edma_rx_swtail.pa,
+					    GFP_KERNEL);
+		if (!ring->edma_rx_swtail.va)
+			goto err_free_va;
+	}
+
+	wil_dbg_misc(wil, "%s ring[%d] 0x%p:%pad 0x%p\n",
+		     ring->is_rx ? "RX" : "TX",
+		     ring->size, ring->va, &ring->pa, ring->ctx);
+
+	return 0;
+err_free_va:
+	dma_free_coherent(dev, ring->size * sizeof(ring->va[0]),
+			  (void *)ring->va, ring->pa);
+	ring->va = NULL;
+err_free_ctx:
+	kfree(ring->ctx);
+	ring->ctx = NULL;
+err:
+	return -ENOMEM;
+}
+
+static void wil_ring_free_edma(struct wil6210_priv *wil, struct wil_ring *ring)
+{
+	struct device *dev = wil_to_dev(wil);
+	size_t sz;
+	int ring_index = 0;
+
+	if (!ring->va)
+		return;
+
+	sz = ring->size * sizeof(ring->va[0]);
+
+	lockdep_assert_held(&wil->mutex);
+	if (ring->is_rx) {
+		wil_dbg_misc(wil, "free Rx ring [%d] 0x%p:%pad 0x%p\n",
+			     ring->size, ring->va,
+			     &ring->pa, ring->ctx);
+
+		wil_move_all_rx_buff_to_free_list(wil, ring);
+		goto out;
+	}
+
+	/* TX ring */
+	ring_index = ring - wil->ring_tx;
+
+	wil_dbg_misc(wil, "free Tx ring %d [%d] 0x%p:%pad 0x%p\n",
+		     ring_index, ring->size, ring->va,
+		     &ring->pa, ring->ctx);
+
+	while (!wil_ring_is_empty(ring)) {
+		struct wil_ctx *ctx;
+
+		struct wil_tx_enhanced_desc dd, *d = &dd;
+		struct wil_tx_enhanced_desc *_d =
+			(struct wil_tx_enhanced_desc *)
+			&ring->va[ring->swtail].tx.enhanced;
+
+		ctx = &ring->ctx[ring->swtail];
+		if (!ctx) {
+			wil_dbg_txrx(wil,
+				     "ctx(%d) was already completed\n",
+				     ring->swtail);
+			ring->swtail = wil_ring_next_tail(ring);
+			continue;
+		}
+		*d = *_d;
+		wil_tx_desc_unmap_edma(dev, (union wil_tx_desc *)d, ctx);
+		if (ctx->skb)
+			dev_kfree_skb_any(ctx->skb);
+		ring->swtail = wil_ring_next_tail(ring);
+	}
+
+out:
+	dma_free_coherent(dev, sz, (void *)ring->va, ring->pa);
+	kfree(ring->ctx);
+	ring->pa = 0;
+	ring->va = NULL;
+	ring->ctx = NULL;
+}
+
+static int wil_init_rx_desc_ring(struct wil6210_priv *wil, u16 desc_ring_size,
+				 int status_ring_id)
+{
+	struct wil_ring *ring = &wil->ring_rx;
+	int rc;
+
+	wil_dbg_misc(wil, "init RX desc ring\n");
+
+	ring->size = desc_ring_size;
+	ring->is_rx = true;
+	rc = wil_ring_alloc_desc_ring(wil, ring);
+	if (rc)
+		return rc;
+
+	rc = wil_wmi_rx_desc_ring_add(wil, status_ring_id);
+	if (rc)
+		goto out_free;
+
+	return 0;
+out_free:
+	wil_ring_free_edma(wil, ring);
+	return rc;
+}
+
+static void wil_get_reorder_params_edma(struct wil6210_priv *wil,
+					struct sk_buff *skb, int *tid,
+					int *cid, int *mid, u16 *seq,
+					int *mcast, int *retry)
+{
+	struct wil_rx_status_extended *s = wil_skb_rxstatus(skb);
+
+	*tid = wil_rx_status_get_tid(s);
+	*cid = wil_rx_status_get_cid(s);
+	*mid = wil_rx_status_get_mid(s);
+	*seq = le16_to_cpu(wil_rx_status_get_seq(wil, s));
+	*mcast = wil_rx_status_get_mcast(s);
+	*retry = wil_rx_status_get_retry(s);
+}
+
+static void wil_get_netif_rx_params_edma(struct sk_buff *skb, int *cid,
+					 int *security)
+{
+	struct wil_rx_status_extended *s = wil_skb_rxstatus(skb);
+
+	*cid = wil_rx_status_get_cid(s);
+	*security = wil_rx_status_get_security(s);
+}
+
+static int wil_rx_crypto_check_edma(struct wil6210_priv *wil,
+				    struct sk_buff *skb)
+{
+	struct wil_rx_status_extended *st;
+	int cid, tid, key_id, mc;
+	struct wil_sta_info *s;
+	struct wil_tid_crypto_rx *c;
+	struct wil_tid_crypto_rx_single *cc;
+	const u8 *pn;
+
+	/* In HW reorder, HW is responsible for crypto check */
+	if (wil->use_rx_hw_reordering)
+		return 0;
+
+	st = wil_skb_rxstatus(skb);
+
+	cid = wil_rx_status_get_cid(st);
+	tid = wil_rx_status_get_tid(st);
+	key_id = wil_rx_status_get_key_id(st);
+	mc = wil_rx_status_get_mcast(st);
+	s = &wil->sta[cid];
+	c = mc ? &s->group_crypto_rx : &s->tid_crypto_rx[tid];
+	cc = &c->key_id[key_id];
+	pn = (u8 *)&st->ext.pn_15_0;
+
+	if (!cc->key_set) {
+		wil_err_ratelimited(wil,
+				    "Key missing. CID %d TID %d MCast %d KEY_ID %d\n",
+				    cid, tid, mc, key_id);
+		return -EINVAL;
+	}
+
+	if (reverse_memcmp(pn, cc->pn, IEEE80211_GCMP_PN_LEN) <= 0) {
+		wil_err_ratelimited(wil,
+				    "Replay attack. CID %d TID %d MCast %d KEY_ID %d PN %6phN last %6phN\n",
+				    cid, tid, mc, key_id, pn, cc->pn);
+		return -EINVAL;
+	}
+	memcpy(cc->pn, pn, IEEE80211_GCMP_PN_LEN);
+
+	return 0;
+}
+
+static bool wil_is_rx_idle_edma(struct wil6210_priv *wil)
+{
+	struct wil_status_ring *sring;
+	struct wil_rx_status_extended msg1;
+	void *msg = &msg1;
+	u8 dr_bit;
+	int i;
+
+	for (i = 0; i < wil->num_rx_status_rings; i++) {
+		sring = &wil->srings[i];
+		if (!sring->va)
+			continue;
+
+		wil_get_next_rx_status_msg(sring, msg);
+		dr_bit = wil_rx_status_get_desc_rdy_bit(msg);
+
+		/* Check if there are unhandled RX status messages */
+		if (dr_bit == sring->desc_rdy_pol)
+			return false;
+	}
+
+	return true;
+}
+
+static void wil_rx_buf_len_init_edma(struct wil6210_priv *wil)
+{
+	wil->rx_buf_len = rx_large_buf ?
+		WIL_MAX_ETH_MTU : WIL_EDMA_RX_BUF_LEN_DEFAULT;
+}
+
+static int wil_rx_init_edma(struct wil6210_priv *wil, u16 desc_ring_size)
+{
+	u16 status_ring_size;
+	struct wil_ring *ring = &wil->ring_rx;
+	int rc;
+	size_t elem_size = wil->use_compressed_rx_status ?
+		sizeof(struct wil_rx_status_compressed) :
+		sizeof(struct wil_rx_status_extended);
+	int i;
+	u16 max_rx_pl_per_desc;
+
+	/* In SW reorder one must use extended status messages */
+	if (wil->use_compressed_rx_status && !wil->use_rx_hw_reordering) {
+		wil_err(wil,
+			"compressed RX status cannot be used with SW reorder\n");
+		return -EINVAL;
+	}
+
+	if (wil->rx_status_ring_order < WIL_SRING_SIZE_ORDER_MIN ||
+	    wil->rx_status_ring_order > WIL_SRING_SIZE_ORDER_MAX)
+		wil->rx_status_ring_order = WIL_RX_SRING_SIZE_ORDER_DEFAULT;
+
+	status_ring_size = 1 << wil->rx_status_ring_order;
+
+	wil_dbg_misc(wil,
+		     "rx_init, desc_ring_size=%u, status_ring_size=%u, elem_size=%zu\n",
+		     desc_ring_size, status_ring_size, elem_size);
+
+	wil_rx_buf_len_init_edma(wil);
+
+	max_rx_pl_per_desc = ALIGN(wil->rx_buf_len, 4);
+
+	/* Use debugfs dbg_num_rx_srings if set, reserve one sring for TX */
+	if (wil->num_rx_status_rings > WIL6210_MAX_STATUS_RINGS - 1)
+		wil->num_rx_status_rings = WIL6210_MAX_STATUS_RINGS - 1;
+
+	wil_dbg_misc(wil, "rx_init: allocate %d status rings\n",
+		     wil->num_rx_status_rings);
+
+	rc = wil_wmi_cfg_def_rx_offload(wil, max_rx_pl_per_desc);
+	if (rc)
+		return rc;
+
+	/* Allocate status ring */
+	for (i = 0; i < wil->num_rx_status_rings; i++) {
+		int sring_id = wil_find_free_sring(wil);
+
+		if (sring_id < 0) {
+			rc = -EFAULT;
+			goto err_free_status;
+		}
+		rc = wil_init_rx_sring(wil, status_ring_size, elem_size,
+				       sring_id);
+		if (rc)
+			goto err_free_status;
+	}
+
+	/* Allocate descriptor ring */
+	rc = wil_init_rx_desc_ring(wil, desc_ring_size,
+				   WIL_DEFAULT_RX_STATUS_RING_ID);
+	if (rc)
+		goto err_free_status;
+
+	if (wil->rx_buff_id_count >= status_ring_size) {
+		wil_info(wil,
+			 "rx_buff_id_count %d exceeds sring_size %d. set it to %d\n",
+			 wil->rx_buff_id_count, status_ring_size,
+			 status_ring_size - 1);
+		wil->rx_buff_id_count = status_ring_size - 1;
+	}
+
+	/* Allocate Rx buffer array */
+	rc = wil_init_rx_buff_arr(wil, wil->rx_buff_id_count);
+	if (rc)
+		goto err_free_desc;
+
+	/* Fill descriptor ring with credits */
+	rc = wil_rx_refill_edma(wil);
+	if (rc)
+		goto err_free_rx_buff_arr;
+
+	return 0;
+err_free_rx_buff_arr:
+	wil_free_rx_buff_arr(wil);
+err_free_desc:
+	wil_ring_free_edma(wil, ring);
+err_free_status:
+	for (i = 0; i < wil->num_rx_status_rings; i++)
+		wil_sring_free(wil, &wil->srings[i]);
+
+	return rc;
+}
+
+static int wil_ring_init_tx_edma(struct wil6210_vif *vif, int ring_id,
+				 int size, int cid, int tid)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	int rc;
+	struct wil_ring *ring = &wil->ring_tx[ring_id];
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[ring_id];
+
+	lockdep_assert_held(&wil->mutex);
+
+	wil_dbg_misc(wil,
+		     "init TX ring: ring_id=%u, cid=%u, tid=%u, sring_id=%u\n",
+		     ring_id, cid, tid, wil->tx_sring_idx);
+
+	wil_tx_data_init(txdata);
+	ring->size = size;
+	rc = wil_ring_alloc_desc_ring(wil, ring);
+	if (rc)
+		goto out;
+
+	wil->ring2cid_tid[ring_id][0] = cid;
+	wil->ring2cid_tid[ring_id][1] = tid;
+	if (!vif->privacy)
+		txdata->dot1x_open = true;
+
+	rc = wil_wmi_tx_desc_ring_add(vif, ring_id, cid, tid);
+	if (rc) {
+		wil_err(wil, "WMI_TX_DESC_RING_ADD_CMD failed\n");
+		goto out_free;
+	}
+
+	if (txdata->dot1x_open && agg_wsize >= 0)
+		wil_addba_tx_request(wil, ring_id, agg_wsize);
+
+	return 0;
+ out_free:
+	spin_lock_bh(&txdata->lock);
+	txdata->dot1x_open = false;
+	txdata->enabled = 0;
+	spin_unlock_bh(&txdata->lock);
+	wil_ring_free_edma(wil, ring);
+	wil->ring2cid_tid[ring_id][0] = WIL6210_MAX_CID;
+	wil->ring2cid_tid[ring_id][1] = 0;
+
+ out:
+	return rc;
+}
+
+/* This function is used only for RX SW reorder */
+static int wil_check_bar(struct wil6210_priv *wil, void *msg, int cid,
+			 struct sk_buff *skb, struct wil_net_stats *stats)
+{
+	u8 ftype;
+	u8 fc1;
+	int mid;
+	int tid;
+	u16 seq;
+	struct wil6210_vif *vif;
+
+	ftype = wil_rx_status_get_frame_type(wil, msg);
+	if (ftype == IEEE80211_FTYPE_DATA)
+		return 0;
+
+	fc1 = wil_rx_status_get_fc1(wil, msg);
+	mid = wil_rx_status_get_mid(msg);
+	tid = wil_rx_status_get_tid(msg);
+	seq = le16_to_cpu(wil_rx_status_get_seq(wil, msg));
+	vif = wil->vifs[mid];
+
+	if (unlikely(!vif)) {
+		wil_dbg_txrx(wil, "RX descriptor with invalid mid %d", mid);
+		return -EAGAIN;
+	}
+
+	wil_dbg_txrx(wil,
+		     "Non-data frame FC[7:0] 0x%02x MID %d CID %d TID %d Seq 0x%03x\n",
+		     fc1, mid, cid, tid, seq);
+	if (stats)
+		stats->rx_non_data_frame++;
+	if (wil_is_back_req(fc1)) {
+		wil_dbg_txrx(wil,
+			     "BAR: MID %d CID %d TID %d Seq 0x%03x\n",
+			     mid, cid, tid, seq);
+		wil_rx_bar(wil, vif, cid, tid, seq);
+	} else {
+		u32 sz = wil->use_compressed_rx_status ?
+			sizeof(struct wil_rx_status_compressed) :
+			sizeof(struct wil_rx_status_extended);
+
+		/* print again all info. One can enable only this
+		 * without overhead for printing every Rx frame
+		 */
+		wil_dbg_txrx(wil,
+			     "Unhandled non-data frame FC[7:0] 0x%02x MID %d CID %d TID %d Seq 0x%03x\n",
+			     fc1, mid, cid, tid, seq);
+		wil_hex_dump_txrx("RxS ", DUMP_PREFIX_NONE, 32, 4,
+				  (const void *)msg, sz, false);
+		wil_hex_dump_txrx("Rx ", DUMP_PREFIX_OFFSET, 16, 1,
+				  skb->data, skb_headlen(skb), false);
+	}
+
+	return -EAGAIN;
+}
+
+static int wil_rx_error_check_edma(struct wil6210_priv *wil,
+				   struct sk_buff *skb,
+				   struct wil_net_stats *stats)
+{
+	int error;
+	int l2_rx_status;
+	int l3_rx_status;
+	int l4_rx_status;
+	void *msg = wil_skb_rxstatus(skb);
+
+	error = wil_rx_status_get_error(msg);
+	if (!error) {
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		return 0;
+	}
+
+	l2_rx_status = wil_rx_status_get_l2_rx_status(msg);
+	if (l2_rx_status != 0) {
+		wil_dbg_txrx(wil, "L2 RX error, l2_rx_status=0x%x\n",
+			     l2_rx_status);
+		/* Due to HW issue, KEY error will trigger a MIC error */
+		if (l2_rx_status & WIL_RX_EDMA_ERROR_MIC) {
+			wil_dbg_txrx(wil,
+				     "L2 MIC/KEY error, dropping packet\n");
+			stats->rx_mic_error++;
+		}
+		if (l2_rx_status & WIL_RX_EDMA_ERROR_KEY) {
+			wil_dbg_txrx(wil, "L2 KEY error, dropping packet\n");
+			stats->rx_key_error++;
+		}
+		if (l2_rx_status & WIL_RX_EDMA_ERROR_REPLAY) {
+			wil_dbg_txrx(wil,
+				     "L2 REPLAY error, dropping packet\n");
+			stats->rx_replay++;
+		}
+		if (l2_rx_status & WIL_RX_EDMA_ERROR_AMSDU) {
+			wil_dbg_txrx(wil,
+				     "L2 AMSDU error, dropping packet\n");
+			stats->rx_amsdu_error++;
+		}
+		return -EFAULT;
+	}
+
+	l3_rx_status = wil_rx_status_get_l3_rx_status(msg);
+	l4_rx_status = wil_rx_status_get_l4_rx_status(msg);
+	if (!l3_rx_status && !l4_rx_status)
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	/* If HW reports bad checksum, let IP stack re-check it
+	 * For example, HW don't understand Microsoft IP stack that
+	 * mis-calculates TCP checksum - if it should be 0x0,
+	 * it writes 0xffff in violation of RFC 1624
+	 */
+	else
+		stats->rx_csum_err++;
+
+	return 0;
+}
+
+static struct sk_buff *wil_sring_reap_rx_edma(struct wil6210_priv *wil,
+					      struct wil_status_ring *sring)
+{
+	struct device *dev = wil_to_dev(wil);
+	struct wil_rx_status_extended msg1;
+	void *msg = &msg1;
+	u16 buff_id;
+	struct sk_buff *skb;
+	dma_addr_t pa;
+	struct wil_ring_rx_data *rxdata = &sring->rx_data;
+	unsigned int sz = ALIGN(wil->rx_buf_len, 4);
+	struct wil_net_stats *stats = NULL;
+	u16 dmalen;
+	int cid;
+	bool eop, headstolen;
+	int delta;
+	u8 dr_bit;
+	u8 data_offset;
+	struct wil_rx_status_extended *s;
+	u16 sring_idx = sring - wil->srings;
+
+	BUILD_BUG_ON(sizeof(struct wil_rx_status_extended) > sizeof(skb->cb));
+
+again:
+	wil_get_next_rx_status_msg(sring, msg);
+	dr_bit = wil_rx_status_get_desc_rdy_bit(msg);
+
+	/* Completed handling all the ready status messages */
+	if (dr_bit != sring->desc_rdy_pol)
+		return NULL;
+
+	/* Extract the buffer ID from the status message */
+	buff_id = le16_to_cpu(wil_rx_status_get_buff_id(msg));
+	if (unlikely(!wil_val_in_range(buff_id, 0, wil->rx_buff_mgmt.size))) {
+		wil_err(wil, "Corrupt buff_id=%d, sring->swhead=%d\n",
+			buff_id, sring->swhead);
+		wil_sring_advance_swhead(sring);
+		goto again;
+	}
+
+	wil_sring_advance_swhead(sring);
+
+	/* Extract the SKB from the rx_buff management array */
+	skb = wil->rx_buff_mgmt.buff_arr[buff_id].skb;
+	wil->rx_buff_mgmt.buff_arr[buff_id].skb = NULL;
+	if (!skb) {
+		wil_err(wil, "No Rx skb at buff_id %d\n", buff_id);
+		goto again;
+	}
+
+	memcpy(&pa, skb->cb, sizeof(pa));
+	dma_unmap_single(dev, pa, sz, DMA_FROM_DEVICE);
+	dmalen = le16_to_cpu(wil_rx_status_get_length(msg));
+
+	trace_wil6210_rx_status(wil, wil->use_compressed_rx_status, buff_id,
+				msg);
+	wil_dbg_txrx(wil, "Rx, buff_id=%u, sring_idx=%u, dmalen=%u bytes\n",
+		     buff_id, sring_idx, dmalen);
+	wil_hex_dump_txrx("RxS ", DUMP_PREFIX_NONE, 32, 4,
+			  (const void *)msg, wil->use_compressed_rx_status ?
+			  sizeof(struct wil_rx_status_compressed) :
+			  sizeof(struct wil_rx_status_extended), false);
+
+	/* Move the buffer from the active list to the free list */
+	list_move(&wil->rx_buff_mgmt.buff_arr[buff_id].list,
+		  &wil->rx_buff_mgmt.free);
+
+	eop = wil_rx_status_get_eop(msg);
+
+	cid = wil_rx_status_get_cid(msg);
+	if (unlikely(!wil_val_in_range(cid, 0, WIL6210_MAX_CID))) {
+		wil_err(wil, "Corrupt cid=%d, sring->swhead=%d\n",
+			cid, sring->swhead);
+		rxdata->skipping = true;
+		goto skipping;
+	}
+	stats = &wil->sta[cid].stats;
+
+	if (unlikely(skb->len < ETH_HLEN)) {
+		wil_dbg_txrx(wil, "Short frame, len = %d\n", skb->len);
+		stats->rx_short_frame++;
+		rxdata->skipping = true;
+		goto skipping;
+	}
+
+	if (unlikely(dmalen > sz)) {
+		wil_err(wil, "Rx size too large: %d bytes!\n", dmalen);
+		stats->rx_large_frame++;
+		rxdata->skipping = true;
+	}
+
+skipping:
+	/* skipping indicates if a certain SKB should be dropped.
+	 * It is set in case there is an error on the current SKB or in case
+	 * of RX chaining: as long as we manage to merge the SKBs it will
+	 * be false. once we have a bad SKB or we don't manage to merge SKBs
+	 * it will be set to the !EOP value of the current SKB.
+	 * This guarantees that all the following SKBs until EOP will also
+	 * get dropped.
+	 */
+	if (unlikely(rxdata->skipping)) {
+		kfree_skb(skb);
+		if (rxdata->skb) {
+			kfree_skb(rxdata->skb);
+			rxdata->skb = NULL;
+		}
+		rxdata->skipping = !eop;
+		goto again;
+	}
+
+	skb_trim(skb, dmalen);
+
+	prefetch(skb->data);
+
+	if (!rxdata->skb) {
+		rxdata->skb = skb;
+	} else {
+		if (likely(skb_try_coalesce(rxdata->skb, skb, &headstolen,
+					    &delta))) {
+			kfree_skb_partial(skb, headstolen);
+		} else {
+			wil_err(wil, "failed to merge skbs!\n");
+			kfree_skb(skb);
+			kfree_skb(rxdata->skb);
+			rxdata->skb = NULL;
+			rxdata->skipping = !eop;
+			goto again;
+		}
+	}
+
+	if (!eop)
+		goto again;
+
+	/* reaching here rxdata->skb always contains a full packet */
+	skb = rxdata->skb;
+	rxdata->skb = NULL;
+	rxdata->skipping = false;
+
+	if (stats) {
+		stats->last_mcs_rx = wil_rx_status_get_mcs(msg);
+		if (stats->last_mcs_rx < ARRAY_SIZE(stats->rx_per_mcs))
+			stats->rx_per_mcs[stats->last_mcs_rx]++;
+	}
+
+	if (!wil->use_rx_hw_reordering && !wil->use_compressed_rx_status &&
+	    wil_check_bar(wil, msg, cid, skb, stats) == -EAGAIN) {
+		kfree_skb(skb);
+		goto again;
+	}
+
+	/* Compensate for the HW data alignment according to the status
+	 * message
+	 */
+	data_offset = wil_rx_status_get_data_offset(msg);
+	if (data_offset == 0xFF ||
+	    data_offset > WIL_EDMA_MAX_DATA_OFFSET) {
+		wil_err(wil, "Unexpected data offset %d\n", data_offset);
+		kfree_skb(skb);
+		goto again;
+	}
+
+	skb_pull(skb, data_offset);
+
+	wil_hex_dump_txrx("Rx ", DUMP_PREFIX_OFFSET, 16, 1,
+			  skb->data, skb_headlen(skb), false);
+
+	/* Has to be done after dma_unmap_single as skb->cb is also
+	 * used for holding the pa
+	 */
+	s = wil_skb_rxstatus(skb);
+	memcpy(s, msg, sring->elem_size);
+
+	return skb;
+}
+
+void wil_rx_handle_edma(struct wil6210_priv *wil, int *quota)
+{
+	struct net_device *ndev;
+	struct wil_ring *ring = &wil->ring_rx;
+	struct wil_status_ring *sring;
+	struct sk_buff *skb;
+	int i;
+
+	if (unlikely(!ring->va)) {
+		wil_err(wil, "Rx IRQ while Rx not yet initialized\n");
+		return;
+	}
+	wil_dbg_txrx(wil, "rx_handle\n");
+
+	for (i = 0; i < wil->num_rx_status_rings; i++) {
+		sring = &wil->srings[i];
+		if (unlikely(!sring->va)) {
+			wil_err(wil,
+				"Rx IRQ while Rx status ring %d not yet initialized\n",
+				i);
+			continue;
+		}
+
+		while ((*quota > 0) &&
+		       (NULL != (skb =
+			wil_sring_reap_rx_edma(wil, sring)))) {
+			(*quota)--;
+			if (wil->use_rx_hw_reordering) {
+				void *msg = wil_skb_rxstatus(skb);
+				int mid = wil_rx_status_get_mid(msg);
+				struct wil6210_vif *vif = wil->vifs[mid];
+
+				if (unlikely(!vif)) {
+					wil_dbg_txrx(wil,
+						     "RX desc invalid mid %d",
+						     mid);
+					kfree_skb(skb);
+					continue;
+				}
+				ndev = vif_to_ndev(vif);
+				wil_netif_rx_any(skb, ndev);
+			} else {
+				wil_rx_reorder(wil, skb);
+			}
+		}
+
+		wil_w(wil, sring->hwtail, (sring->swhead - 1) % sring->size);
+	}
+
+	wil_rx_refill_edma(wil);
+}
+
+static int wil_tx_desc_map_edma(union wil_tx_desc *desc,
+				dma_addr_t pa,
+				u32 len,
+				int ring_index)
+{
+	struct wil_tx_enhanced_desc *d =
+		(struct wil_tx_enhanced_desc *)&desc->enhanced;
+
+	memset(d, 0, sizeof(struct wil_tx_enhanced_desc));
+
+	wil_desc_set_addr_edma(&d->dma.addr, &d->dma.addr_high_high, pa);
+
+	/* 0..6: mac_length; 7:ip_version 0-IP6 1-IP4*/
+	d->dma.length = cpu_to_le16((u16)len);
+	d->mac.d[0] = (ring_index << WIL_EDMA_DESC_TX_MAC_CFG_0_QID_POS);
+	/* translation type:  0 - bypass; 1 - 802.3; 2 - native wifi;
+	 * 3 - eth mode
+	 */
+	d->mac.d[2] = BIT(MAC_CFG_DESC_TX_2_SNAP_HDR_INSERTION_EN_POS) |
+		      (0x3 << MAC_CFG_DESC_TX_2_L2_TRANSLATION_TYPE_POS);
+
+	return 0;
+}
+
+static inline void
+wil_get_next_tx_status_msg(struct wil_status_ring *sring,
+			   struct wil_ring_tx_status *msg)
+{
+	struct wil_ring_tx_status *_msg = (struct wil_ring_tx_status *)
+		(sring->va + (sring->elem_size * sring->swhead));
+
+	*msg = *_msg;
+}
+
+/**
+ * Clean up transmitted skb's from the Tx descriptor RING.
+ * Return number of descriptors cleared.
+ */
+int wil_tx_sring_handler(struct wil6210_priv *wil,
+			 struct wil_status_ring *sring)
+{
+	struct net_device *ndev;
+	struct device *dev = wil_to_dev(wil);
+	struct wil_ring *ring = NULL;
+	struct wil_ring_tx_data *txdata;
+	/* Total number of completed descriptors in all descriptor rings */
+	int desc_cnt = 0;
+	int cid;
+	struct wil_net_stats *stats = NULL;
+	struct wil_tx_enhanced_desc *_d;
+	unsigned int ring_id;
+	unsigned int num_descs;
+	int i;
+	u8 dr_bit; /* Descriptor Ready bit */
+	struct wil_ring_tx_status msg;
+	struct wil6210_vif *vif;
+	int used_before_complete;
+	int used_new;
+
+	wil_get_next_tx_status_msg(sring, &msg);
+	dr_bit = msg.desc_ready >> TX_STATUS_DESC_READY_POS;
+
+	/* Process completion messages while DR bit has the expected polarity */
+	while (dr_bit == sring->desc_rdy_pol) {
+		num_descs = msg.num_descriptors;
+		if (!num_descs) {
+			wil_err(wil, "invalid num_descs 0\n");
+			goto again;
+		}
+
+		/* Find the corresponding descriptor ring */
+		ring_id = msg.ring_id;
+
+		if (unlikely(ring_id >= WIL6210_MAX_TX_RINGS)) {
+			wil_err(wil, "invalid ring id %d\n", ring_id);
+			goto again;
+		}
+		ring = &wil->ring_tx[ring_id];
+		if (unlikely(!ring->va)) {
+			wil_err(wil, "Tx irq[%d]: ring not initialized\n",
+				ring_id);
+			goto again;
+		}
+		txdata = &wil->ring_tx_data[ring_id];
+		if (unlikely(!txdata->enabled)) {
+			wil_info(wil, "Tx irq[%d]: ring disabled\n", ring_id);
+			goto again;
+		}
+		vif = wil->vifs[txdata->mid];
+		if (unlikely(!vif)) {
+			wil_dbg_txrx(wil, "invalid MID %d for ring %d\n",
+				     txdata->mid, ring_id);
+			goto again;
+		}
+
+		ndev = vif_to_ndev(vif);
+
+		cid = wil->ring2cid_tid[ring_id][0];
+		if (cid < WIL6210_MAX_CID)
+			stats = &wil->sta[cid].stats;
+
+		wil_dbg_txrx(wil,
+			     "tx_status: completed desc_ring (%d), num_descs (%d)\n",
+			     ring_id, num_descs);
+
+		used_before_complete = wil_ring_used_tx(ring);
+
+		for (i = 0 ; i < num_descs; ++i) {
+			struct wil_ctx *ctx = &ring->ctx[ring->swtail];
+			struct wil_tx_enhanced_desc dd, *d = &dd;
+			u16 dmalen;
+			struct sk_buff *skb = ctx->skb;
+
+			_d = (struct wil_tx_enhanced_desc *)
+				&ring->va[ring->swtail].tx.enhanced;
+			*d = *_d;
+
+			dmalen = le16_to_cpu(d->dma.length);
+			trace_wil6210_tx_status(&msg, ring->swtail, dmalen);
+			wil_dbg_txrx(wil,
+				     "TxC[%2d][%3d] : %d bytes, status 0x%02x\n",
+				     ring_id, ring->swtail, dmalen,
+				     msg.status);
+			wil_hex_dump_txrx("TxS ", DUMP_PREFIX_NONE, 32, 4,
+					  (const void *)&msg, sizeof(msg),
+					  false);
+
+			wil_tx_desc_unmap_edma(dev,
+					       (union wil_tx_desc *)d,
+					       ctx);
+
+			if (skb) {
+				if (likely(msg.status == 0)) {
+					ndev->stats.tx_packets++;
+					ndev->stats.tx_bytes += skb->len;
+					if (stats) {
+						stats->tx_packets++;
+						stats->tx_bytes += skb->len;
+
+						wil_tx_latency_calc(wil, skb,
+							&wil->sta[cid]);
+					}
+				} else {
+					ndev->stats.tx_errors++;
+					if (stats)
+						stats->tx_errors++;
+				}
+				wil_consume_skb(skb, msg.status == 0);
+			}
+			memset(ctx, 0, sizeof(*ctx));
+			/* Make sure the ctx is zeroed before updating the tail
+			 * to prevent a case where wil_tx_ring will see
+			 * this descriptor as used and handle it before ctx zero
+			 * is completed.
+			 */
+			wmb();
+
+			ring->swtail = wil_ring_next_tail(ring);
+
+			desc_cnt++;
+		}
+
+		/* performance monitoring */
+		used_new = wil_ring_used_tx(ring);
+		if (wil_val_in_range(wil->ring_idle_trsh,
+				     used_new, used_before_complete)) {
+			wil_dbg_txrx(wil, "Ring[%2d] idle %d -> %d\n",
+				     ring_id, used_before_complete, used_new);
+			txdata->last_idle = get_cycles();
+		}
+
+again:
+		wil_sring_advance_swhead(sring);
+
+		wil_get_next_tx_status_msg(sring, &msg);
+		dr_bit = msg.desc_ready >> TX_STATUS_DESC_READY_POS;
+	}
+
+	/* shall we wake net queues? */
+	if (desc_cnt)
+		wil_update_net_queues(wil, vif, NULL, false);
+
+	/* Update the HW tail ptr (RD ptr) */
+	wil_w(wil, sring->hwtail, (sring->swhead - 1) % sring->size);
+
+	return desc_cnt;
+}
+
+/**
+ * Sets the descriptor @d up for csum and/or TSO offloading. The corresponding
+ * @skb is used to obtain the protocol and headers length.
+ * @tso_desc_type is a descriptor type for TSO: 0 - a header, 1 - first data,
+ * 2 - middle, 3 - last descriptor.
+ */
+static void wil_tx_desc_offload_setup_tso_edma(struct wil_tx_enhanced_desc *d,
+					       int tso_desc_type, bool is_ipv4,
+					       int tcp_hdr_len,
+					       int skb_net_hdr_len,
+					       int mss)
+{
+	/* Number of descriptors */
+	d->mac.d[2] |= 1;
+	/* Maximum Segment Size */
+	d->mac.tso_mss |= cpu_to_le16(mss >> 2);
+	/* L4 header len: TCP header length */
+	d->dma.l4_hdr_len |= tcp_hdr_len & DMA_CFG_DESC_TX_0_L4_LENGTH_MSK;
+	/* EOP, TSO desc type, Segmentation enable,
+	 * Insert IPv4 and TCP / UDP Checksum
+	 */
+	d->dma.cmd |= BIT(WIL_EDMA_DESC_TX_CFG_EOP_POS) |
+		      tso_desc_type << WIL_EDMA_DESC_TX_CFG_TSO_DESC_TYPE_POS |
+		      BIT(WIL_EDMA_DESC_TX_CFG_SEG_EN_POS) |
+		      BIT(WIL_EDMA_DESC_TX_CFG_INSERT_IP_CHKSUM_POS) |
+		      BIT(WIL_EDMA_DESC_TX_CFG_INSERT_TCP_CHKSUM_POS);
+	/* Calculate pseudo-header */
+	d->dma.w1 |= BIT(WIL_EDMA_DESC_TX_CFG_PSEUDO_HEADER_CALC_EN_POS) |
+		     BIT(WIL_EDMA_DESC_TX_CFG_L4_TYPE_POS);
+	/* IP Header Length */
+	d->dma.ip_length |= skb_net_hdr_len;
+	/* MAC header length and IP address family*/
+	d->dma.b11 |= ETH_HLEN |
+		      is_ipv4 << DMA_CFG_DESC_TX_OFFLOAD_CFG_L3T_IPV4_POS;
+}
+
+static int wil_tx_tso_gen_desc(struct wil6210_priv *wil, void *buff_addr,
+			       int len, uint i, int tso_desc_type,
+			       skb_frag_t *frag, struct wil_ring *ring,
+			       struct sk_buff *skb, bool is_ipv4,
+			       int tcp_hdr_len, int skb_net_hdr_len,
+			       int mss, int *descs_used)
+{
+	struct device *dev = wil_to_dev(wil);
+	struct wil_tx_enhanced_desc *_desc = (struct wil_tx_enhanced_desc *)
+		&ring->va[i].tx.enhanced;
+	struct wil_tx_enhanced_desc desc_mem, *d = &desc_mem;
+	int ring_index = ring - wil->ring_tx;
+	dma_addr_t pa;
+
+	if (len == 0)
+		return 0;
+
+	if (!frag) {
+		pa = dma_map_single(dev, buff_addr, len, DMA_TO_DEVICE);
+		ring->ctx[i].mapped_as = wil_mapped_as_single;
+	} else {
+		pa = skb_frag_dma_map(dev, frag, 0, len, DMA_TO_DEVICE);
+		ring->ctx[i].mapped_as = wil_mapped_as_page;
+	}
+	if (unlikely(dma_mapping_error(dev, pa))) {
+		wil_err(wil, "TSO: Skb DMA map error\n");
+		return -EINVAL;
+	}
+
+	wil->txrx_ops.tx_desc_map((union wil_tx_desc *)d, pa,
+				   len, ring_index);
+	wil_tx_desc_offload_setup_tso_edma(d, tso_desc_type, is_ipv4,
+					   tcp_hdr_len,
+					   skb_net_hdr_len, mss);
+
+	/* hold reference to skb
+	 * to prevent skb release before accounting
+	 * in case of immediate "tx done"
+	 */
+	if (tso_desc_type == wil_tso_type_lst)
+		ring->ctx[i].skb = skb_get(skb);
+
+	wil_hex_dump_txrx("TxD ", DUMP_PREFIX_NONE, 32, 4,
+			  (const void *)d, sizeof(*d), false);
+
+	*_desc = *d;
+	(*descs_used)++;
+
+	return 0;
+}
+
+static int __wil_tx_ring_tso_edma(struct wil6210_priv *wil,
+				  struct wil6210_vif *vif,
+				  struct wil_ring *ring,
+				  struct sk_buff *skb)
+{
+	int ring_index = ring - wil->ring_tx;
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[ring_index];
+	int nr_frags = skb_shinfo(skb)->nr_frags;
+	int min_desc_required = nr_frags + 2; /* Headers, Head, Fragments */
+	int used, avail = wil_ring_avail_tx(ring);
+	int f, hdrlen, headlen;
+	int gso_type;
+	bool is_ipv4;
+	u32 swhead = ring->swhead;
+	int descs_used = 0; /* total number of used descriptors */
+	int rc = -EINVAL;
+	int tcp_hdr_len;
+	int skb_net_hdr_len;
+	int mss = skb_shinfo(skb)->gso_size;
+
+	wil_dbg_txrx(wil, "tx_ring_tso: %d bytes to ring %d\n", skb->len,
+		     ring_index);
+
+	if (unlikely(!txdata->enabled))
+		return -EINVAL;
+
+	if (unlikely(avail < min_desc_required)) {
+		wil_err_ratelimited(wil,
+				    "TSO: Tx ring[%2d] full. No space for %d fragments\n",
+				    ring_index, min_desc_required);
+		return -ENOMEM;
+	}
+
+	gso_type = skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV6 | SKB_GSO_TCPV4);
+	switch (gso_type) {
+	case SKB_GSO_TCPV4:
+		is_ipv4 = true;
+		break;
+	case SKB_GSO_TCPV6:
+		is_ipv4 = false;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return -EINVAL;
+
+	/* tcp header length and skb network header length are fixed for all
+	 * packet's descriptors - read them once here
+	 */
+	tcp_hdr_len = tcp_hdrlen(skb);
+	skb_net_hdr_len = skb_network_header_len(skb);
+
+	/* First descriptor must contain the header only
+	 * Header Length = MAC header len + IP header len + TCP header len
+	 */
+	hdrlen = ETH_HLEN + tcp_hdr_len + skb_net_hdr_len;
+	wil_dbg_txrx(wil, "TSO: process header descriptor, hdrlen %u\n",
+		     hdrlen);
+	rc = wil_tx_tso_gen_desc(wil, skb->data, hdrlen, swhead,
+				 wil_tso_type_hdr, NULL, ring, skb,
+				 is_ipv4, tcp_hdr_len, skb_net_hdr_len,
+				 mss, &descs_used);
+	if (rc)
+		return -EINVAL;
+
+	/* Second descriptor contains the head */
+	headlen = skb_headlen(skb) - hdrlen;
+	wil_dbg_txrx(wil, "TSO: process skb head, headlen %u\n", headlen);
+	rc = wil_tx_tso_gen_desc(wil, skb->data + hdrlen, headlen,
+				 (swhead + descs_used) % ring->size,
+				 (nr_frags != 0) ? wil_tso_type_first :
+				 wil_tso_type_lst, NULL, ring, skb,
+				 is_ipv4, tcp_hdr_len, skb_net_hdr_len,
+				 mss, &descs_used);
+	if (rc)
+		goto mem_error;
+
+	/* Rest of the descriptors are from the SKB fragments */
+	for (f = 0; f < nr_frags; f++) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[f];
+		int len = frag->size;
+
+		wil_dbg_txrx(wil, "TSO: frag[%d]: len %u, descs_used %d\n", f,
+			     len, descs_used);
+
+		rc = wil_tx_tso_gen_desc(wil, NULL, len,
+					 (swhead + descs_used) % ring->size,
+					 (f != nr_frags - 1) ?
+					 wil_tso_type_mid : wil_tso_type_lst,
+					 frag, ring, skb, is_ipv4,
+					 tcp_hdr_len, skb_net_hdr_len,
+					 mss, &descs_used);
+		if (rc)
+			goto mem_error;
+	}
+
+	/* performance monitoring */
+	used = wil_ring_used_tx(ring);
+	if (wil_val_in_range(wil->ring_idle_trsh,
+			     used, used + descs_used)) {
+		txdata->idle += get_cycles() - txdata->last_idle;
+		wil_dbg_txrx(wil,  "Ring[%2d] not idle %d -> %d\n",
+			     ring_index, used, used + descs_used);
+	}
+
+	/* advance swhead */
+	wil_ring_advance_head(ring, descs_used);
+	wil_dbg_txrx(wil, "TSO: Tx swhead %d -> %d\n", swhead, ring->swhead);
+
+	/* make sure all writes to descriptors (shared memory) are done before
+	 * committing them to HW
+	 */
+	wmb();
+
+	if (wil->tx_latency)
+		*(ktime_t *)&skb->cb = ktime_get();
+	else
+		memset(skb->cb, 0, sizeof(ktime_t));
+
+	wil_w(wil, ring->hwtail, ring->swhead);
+
+	return 0;
+
+mem_error:
+	while (descs_used > 0) {
+		struct device *dev = wil_to_dev(wil);
+		struct wil_ctx *ctx;
+		int i = (swhead + descs_used - 1) % ring->size;
+		struct wil_tx_enhanced_desc dd, *d = &dd;
+		struct wil_tx_enhanced_desc *_desc =
+			(struct wil_tx_enhanced_desc *)
+			&ring->va[i].tx.enhanced;
+
+		*d = *_desc;
+		ctx = &ring->ctx[i];
+		wil_tx_desc_unmap_edma(dev, (union wil_tx_desc *)d, ctx);
+		memset(ctx, 0, sizeof(*ctx));
+		descs_used--;
+	}
+	return rc;
+}
+
+static int wil_ring_init_bcast_edma(struct wil6210_vif *vif, int ring_id,
+				    int size)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	struct wil_ring *ring = &wil->ring_tx[ring_id];
+	int rc;
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[ring_id];
+
+	wil_dbg_misc(wil, "init bcast: ring_id=%d, sring_id=%d\n",
+		     ring_id, wil->tx_sring_idx);
+
+	lockdep_assert_held(&wil->mutex);
+
+	wil_tx_data_init(txdata);
+	ring->size = size;
+	ring->is_rx = false;
+	rc = wil_ring_alloc_desc_ring(wil, ring);
+	if (rc)
+		goto out;
+
+	wil->ring2cid_tid[ring_id][0] = WIL6210_MAX_CID; /* CID */
+	wil->ring2cid_tid[ring_id][1] = 0; /* TID */
+	if (!vif->privacy)
+		txdata->dot1x_open = true;
+
+	rc = wil_wmi_bcast_desc_ring_add(vif, ring_id);
+	if (rc)
+		goto out_free;
+
+	return 0;
+
+ out_free:
+	spin_lock_bh(&txdata->lock);
+	txdata->enabled = 0;
+	txdata->dot1x_open = false;
+	spin_unlock_bh(&txdata->lock);
+	wil_ring_free_edma(wil, ring);
+
+out:
+	return rc;
+}
+
+static void wil_tx_fini_edma(struct wil6210_priv *wil)
+{
+	struct wil_status_ring *sring = &wil->srings[wil->tx_sring_idx];
+
+	wil_dbg_misc(wil, "free TX sring\n");
+
+	wil_sring_free(wil, sring);
+}
+
+static void wil_rx_data_free(struct wil_status_ring *sring)
+{
+	if (!sring)
+		return;
+
+	kfree_skb(sring->rx_data.skb);
+	sring->rx_data.skb = NULL;
+}
+
+static void wil_rx_fini_edma(struct wil6210_priv *wil)
+{
+	struct wil_ring *ring = &wil->ring_rx;
+	int i;
+
+	wil_dbg_misc(wil, "rx_fini_edma\n");
+
+	wil_ring_free_edma(wil, ring);
+
+	for (i = 0; i < wil->num_rx_status_rings; i++) {
+		wil_rx_data_free(&wil->srings[i]);
+		wil_sring_free(wil, &wil->srings[i]);
+	}
+
+	wil_free_rx_buff_arr(wil);
+}
+
+void wil_init_txrx_ops_edma(struct wil6210_priv *wil)
+{
+	wil->txrx_ops.configure_interrupt_moderation =
+		wil_configure_interrupt_moderation_edma;
+	/* TX ops */
+	wil->txrx_ops.ring_init_tx = wil_ring_init_tx_edma;
+	wil->txrx_ops.ring_fini_tx = wil_ring_free_edma;
+	wil->txrx_ops.ring_init_bcast = wil_ring_init_bcast_edma;
+	wil->txrx_ops.tx_init = wil_tx_init_edma;
+	wil->txrx_ops.tx_fini = wil_tx_fini_edma;
+	wil->txrx_ops.tx_desc_map = wil_tx_desc_map_edma;
+	wil->txrx_ops.tx_desc_unmap = wil_tx_desc_unmap_edma;
+	wil->txrx_ops.tx_ring_tso = __wil_tx_ring_tso_edma;
+	/* RX ops */
+	wil->txrx_ops.rx_init = wil_rx_init_edma;
+	wil->txrx_ops.wmi_addba_rx_resp = wmi_addba_rx_resp_edma;
+	wil->txrx_ops.get_reorder_params = wil_get_reorder_params_edma;
+	wil->txrx_ops.get_netif_rx_params = wil_get_netif_rx_params_edma;
+	wil->txrx_ops.rx_crypto_check = wil_rx_crypto_check_edma;
+	wil->txrx_ops.rx_error_check = wil_rx_error_check_edma;
+	wil->txrx_ops.is_rx_idle = wil_is_rx_idle_edma;
+	wil->txrx_ops.rx_fini = wil_rx_fini_edma;
+}
+
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.h b/drivers/net/wireless/ath/wil6210/txrx_edma.h
new file mode 100644
index 000000000000..a7fe9292fda3
--- /dev/null
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.h
@@ -0,0 +1,568 @@
+/*
+ * Copyright (c) 2012-2016,2018, The Linux Foundation. All rights reserved.
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#ifndef WIL6210_TXRX_EDMA_H
+#define WIL6210_TXRX_EDMA_H
+
+#include "wil6210.h"
+
+/* limit status ring size in range [ring size..max ring size] */
+#define WIL_SRING_SIZE_ORDER_MIN	(WIL_RING_SIZE_ORDER_MIN)
+#define WIL_SRING_SIZE_ORDER_MAX	(WIL_RING_SIZE_ORDER_MAX)
+/* RX sring order should be bigger than RX ring order */
+#define WIL_RX_SRING_SIZE_ORDER_DEFAULT	(11)
+#define WIL_TX_SRING_SIZE_ORDER_DEFAULT	(12)
+#define WIL_RX_BUFF_ARR_SIZE_DEFAULT (1536)
+
+#define WIL_DEFAULT_RX_STATUS_RING_ID 0
+#define WIL_RX_DESC_RING_ID 0
+#define WIL_RX_STATUS_IRQ_IDX 0
+#define WIL_TX_STATUS_IRQ_IDX 1
+
+#define WIL_EDMA_AGG_WATERMARK (0xffff)
+#define WIL_EDMA_AGG_WATERMARK_POS (16)
+
+#define WIL_EDMA_IDLE_TIME_LIMIT_USEC (50)
+#define WIL_EDMA_TIME_UNIT_CLK_CYCLES (330) /* fits 1 usec */
+
+/* Error field */
+#define WIL_RX_EDMA_ERROR_MIC	(1)
+#define WIL_RX_EDMA_ERROR_KEY	(2) /* Key missing */
+#define WIL_RX_EDMA_ERROR_REPLAY	(3)
+#define WIL_RX_EDMA_ERROR_AMSDU	(4)
+#define WIL_RX_EDMA_ERROR_FCS	(7)
+
+#define WIL_RX_EDMA_ERROR_L3_ERR	(BIT(0) | BIT(1))
+#define WIL_RX_EDMA_ERROR_L4_ERR	(BIT(0) | BIT(1))
+
+#define WIL_RX_EDMA_DLPF_LU_MISS_BIT		BIT(11)
+#define WIL_RX_EDMA_DLPF_LU_MISS_CID_TID_MASK	0x7
+#define WIL_RX_EDMA_DLPF_LU_HIT_CID_TID_MASK	0xf
+
+#define WIL_RX_EDMA_DLPF_LU_MISS_CID_POS	2
+#define WIL_RX_EDMA_DLPF_LU_HIT_CID_POS		4
+
+#define WIL_RX_EDMA_DLPF_LU_MISS_TID_POS	5
+
+#define WIL_RX_EDMA_MID_VALID_BIT		BIT(22)
+
+#define WIL_EDMA_DESC_TX_MAC_CFG_0_QID_POS 16
+#define WIL_EDMA_DESC_TX_MAC_CFG_0_QID_LEN 6
+
+#define WIL_EDMA_DESC_TX_CFG_EOP_POS 0
+#define WIL_EDMA_DESC_TX_CFG_EOP_LEN 1
+
+#define WIL_EDMA_DESC_TX_CFG_TSO_DESC_TYPE_POS 3
+#define WIL_EDMA_DESC_TX_CFG_TSO_DESC_TYPE_LEN 2
+
+#define WIL_EDMA_DESC_TX_CFG_SEG_EN_POS 5
+#define WIL_EDMA_DESC_TX_CFG_SEG_EN_LEN 1
+
+#define WIL_EDMA_DESC_TX_CFG_INSERT_IP_CHKSUM_POS 6
+#define WIL_EDMA_DESC_TX_CFG_INSERT_IP_CHKSUM_LEN 1
+
+#define WIL_EDMA_DESC_TX_CFG_INSERT_TCP_CHKSUM_POS 7
+#define WIL_EDMA_DESC_TX_CFG_INSERT_TCP_CHKSUM_LEN 1
+
+#define WIL_EDMA_DESC_TX_CFG_L4_TYPE_POS 15
+#define WIL_EDMA_DESC_TX_CFG_L4_TYPE_LEN 1
+
+#define WIL_EDMA_DESC_TX_CFG_PSEUDO_HEADER_CALC_EN_POS 5
+#define WIL_EDMA_DESC_TX_CFG_PSEUDO_HEADER_CALC_EN_LEN 1
+
+/* Enhanced Rx descriptor - MAC part
+ * [dword 0] : Reserved
+ * [dword 1] : Reserved
+ * [dword 2] : Reserved
+ * [dword 3]
+ *	bit  0..15 : Buffer ID
+ *	bit 16..31 : Reserved
+ */
+struct wil_ring_rx_enhanced_mac {
+	u32 d[3];
+	__le16 buff_id;
+	u16 reserved;
+} __packed;
+
+/* Enhanced Rx descriptor - DMA part
+ * [dword 0] - Reserved
+ * [dword 1]
+ *	bit  0..31 : addr_low:32 The payload buffer address, bits 0-31
+ * [dword 2]
+ *	bit  0..15 : addr_high_low:16 The payload buffer address, bits 32-47
+ *	bit 16..31 : Reserved
+ * [dword 3]
+ *	bit  0..15 : addr_high_high:16 The payload buffer address, bits 48-63
+ *	bit 16..31 : length
+ */
+struct wil_ring_rx_enhanced_dma {
+	u32 d0;
+	struct wil_ring_dma_addr addr;
+	u16 w5;
+	__le16 addr_high_high;
+	__le16 length;
+} __packed;
+
+struct wil_rx_enhanced_desc {
+	struct wil_ring_rx_enhanced_mac mac;
+	struct wil_ring_rx_enhanced_dma dma;
+} __packed;
+
+/* Enhanced Tx descriptor - DMA part
+ * [dword 0]
+ *	Same as legacy
+ * [dword 1]
+ * bit  0..31 : addr_low:32 The payload buffer address, bits 0-31
+ * [dword 2]
+ * bit  0..15 : addr_high_low:16 The payload buffer address, bits 32-47
+ * bit 16..23 : ip_length:8 The IP header length for the TX IP checksum
+ *		offload feature
+ * bit 24..30 : mac_length:7
+ * bit     31 : ip_version:1 1 - IPv4, 0 - IPv6
+ * [dword 3]
+ * bit  0..15 : addr_high_high:16 The payload buffer address, bits 48-63
+ * bit 16..31 : length
+ */
+struct wil_ring_tx_enhanced_dma {
+	u8 l4_hdr_len;
+	u8 cmd;
+	u16 w1;
+	struct wil_ring_dma_addr addr;
+	u8  ip_length;
+	u8  b11;       /* 0..6: mac_length; 7:ip_version */
+	__le16 addr_high_high;
+	__le16 length;
+} __packed;
+
+/* Enhanced Tx descriptor - MAC part
+ * [dword 0]
+ * bit  0.. 9 : lifetime_expiry_value:10
+ * bit     10 : interrupt_en:1
+ * bit     11 : status_en:1
+ * bit 12..13 : txss_override:2
+ * bit     14 : timestamp_insertion:1
+ * bit     15 : duration_preserve:1
+ * bit 16..21 : reserved0:6
+ * bit 22..26 : mcs_index:5
+ * bit     27 : mcs_en:1
+ * bit 28..30 : reserved1:3
+ * bit     31 : sn_preserved:1
+ * [dword 1]
+ * bit  0.. 3 : pkt_mode:4
+ * bit      4 : pkt_mode_en:1
+ * bit  5..14 : reserved0:10
+ * bit     15 : ack_policy_en:1
+ * bit 16..19 : dst_index:4
+ * bit     20 : dst_index_en:1
+ * bit 21..22 : ack_policy:2
+ * bit     23 : lifetime_en:1
+ * bit 24..30 : max_retry:7
+ * bit     31 : max_retry_en:1
+ * [dword 2]
+ * bit  0.. 7 : num_of_descriptors:8
+ * bit  8..17 : reserved:10
+ * bit 18..19 : l2_translation_type:2 00 - bypass, 01 - 802.3, 10 - 802.11
+ * bit     20 : snap_hdr_insertion_en:1
+ * bit     21 : vlan_removal_en:1
+ * bit 22..23 : reserved0:2
+ * bit	   24 : Dest ID extension:1
+ * bit 25..31 : reserved0:7
+ * [dword 3]
+ * bit  0..15 : tso_mss:16
+ * bit 16..31 : descriptor_scratchpad:16 - mailbox between driver and ucode
+ */
+struct wil_ring_tx_enhanced_mac {
+	u32 d[3];
+	__le16 tso_mss;
+	u16 scratchpad;
+} __packed;
+
+struct wil_tx_enhanced_desc {
+	struct wil_ring_tx_enhanced_mac mac;
+	struct wil_ring_tx_enhanced_dma dma;
+} __packed;
+
+#define TX_STATUS_DESC_READY_POS 7
+
+/* Enhanced TX status message
+ * [dword 0]
+ *	bit  0.. 7 : Number of Descriptor:8 - The number of descriptors that
+ *		     are used to form the packets. It  is needed for WB when
+ *		     releasing the packet
+ *	bit  8..15 : tx_ring_id:8 The transmission ring ID that is related to
+ *		     the message
+ *	bit 16..23 : Status:8 - The TX status Code
+ *		0x0 - A successful transmission
+ *		0x1 - Retry expired
+ *		0x2 - Lifetime Expired
+ *		0x3 - Released
+ *		0x4-0xFF - Reserved
+ *	bit 24..30 : Reserved:7
+ *	bit     31 : Descriptor Ready bit:1 - It is initiated to
+ *		zero by the driver when the ring is created. It is set by the HW
+ *		to one for each completed status message. Each wrap around,
+ *		the DR bit value is flipped.
+ * [dword 1]
+ *	bit 0..31  : timestamp:32 - Set when MPDU is transmitted.
+ * [dword 2]
+ *	bit  0.. 4 : MCS:5 - The transmitted MCS value
+ *	bit      5 : Reserved:1
+ *	bit  6.. 7 : CB mode:2 - 0-DMG 1-EDMG 2-Wide
+ *	bit  8..12 : QID:5 - The QID that was used for the transmission
+ *	bit 13..15 : Reserved:3
+ *	bit 16..20 : Num of MSDUs:5 - Number of MSDUs in the aggregation
+ *	bit 21..22 : Reserved:2
+ *	bit     23 : Retry:1 - An indication that the transmission was retried
+ *	bit 24..31 : TX-Sector:8 - the antenna sector that was used for
+ *		     transmission
+ * [dword 3]
+ *	bit  0..11 : Sequence number:12 - The Sequence Number that was used
+ *		     for the MPDU transmission
+ *	bit 12..31 : Reserved:20
+ */
+struct wil_ring_tx_status {
+	u8 num_descriptors;
+	u8 ring_id;
+	u8 status;
+	u8 desc_ready; /* Only the last bit should be set */
+	u32 timestamp;
+	u32 d2;
+	u16 seq_number; /* Only the first 12 bits */
+	u16 w7;
+} __packed;
+
+/* Enhanced Rx status message - compressed part
+ * [dword 0]
+ *	bit  0.. 2 : L2 Rx Status:3 - The L2 packet reception Status
+ *		     0-Success, 1-MIC Error, 2-Key Error, 3-Replay Error,
+ *		     4-A-MSDU Error, 5-Reserved, 6-Reserved, 7-FCS Error
+ *	bit  3.. 4 : L3 Rx Status:2 - Bit0 - L3I - L3 identified and checksum
+ *		     calculated, Bit1- L3Err - IPv4 Checksum Error
+ *	bit  5.. 6 : L4 Rx Status:2 - Bit0 - L4I - L4 identified and checksum
+ *		     calculated, Bit1- L4Err - TCP/UDP Checksum Error
+ *	bit      7 : Reserved:1
+ *	bit  8..19 : Flow ID:12 - MSDU flow ID
+ *	bit 20..21 : MID:2 - The MAC ID
+ *	bit     22 : MID_V:1 - The MAC ID field is valid
+ *	bit     23 : L3T:1 - IP types: 0-IPv6, 1-IPv4
+ *	bit     24 : L4T:1 - Layer 4 Type: 0-UDP, 1-TCP
+ *	bit     25 : BC:1 - The received MPDU is broadcast
+ *	bit     26 : MC:1 - The received MPDU is multicast
+ *	bit     27 : Raw:1 - The MPDU received with no translation
+ *	bit     28 : Sec:1 - The FC control (b14) - Frame Protected
+ *	bit     29 : Error:1 - An error is set when (L2 status != 0) ||
+ *		(L3 status == 3) || (L4 status == 3)
+ *	bit     30 : EOP:1 - End of MSDU signaling. It is set to mark the end
+ *		     of the transfer, otherwise the status indicates buffer
+ *		     only completion.
+ *	bit     31 : Descriptor Ready bit:1 - It is initiated to
+ *		     zero by the driver when the ring is created. It is set
+ *		     by the HW to one for each completed status message.
+ *		     Each wrap around, the DR bit value is flipped.
+ * [dword 1]
+ *	bit  0.. 5 : MAC Len:6 - The number of bytes that are used for L2 header
+ *	bit  6..11 : IPLEN:6 - The number of DW that are used for L3 header
+ *	bit 12..15 : I4Len:4 - The number of DW that are used for L4 header
+ *	bit 16..21 : MCS:6 - The received MCS field from the PLCP Header
+ *	bit 22..23 : CB mode:2 - The CB Mode: 0-DMG, 1-EDMG, 2-Wide
+ *	bit 24..27 : Data Offset:4 - The data offset, a code that describe the
+ *		     payload shift from the beginning of the buffer:
+ *		     0 - 0 Bytes, 3 - 2 Bytes
+ *	bit     28 : A-MSDU Present:1 - The QoS (b7) A-MSDU present field
+ *	bit     29 : A-MSDU Type:1 The QoS (b8) A-MSDU Type field
+ *	bit     30 : A-MPDU:1 - Packet is part of aggregated MPDU
+ *	bit     31 : Key ID:1 - The extracted Key ID from the encryption header
+ * [dword 2]
+ *	bit  0..15 : Buffer ID:16 - The Buffer Identifier
+ *	bit 16..31 : Length:16 - It indicates the valid bytes that are stored
+ *		     in the current descriptor buffer. For multiple buffer
+ *		     descriptor, SW need to sum the total descriptor length
+ *		     in all buffers to produce the packet length
+ * [dword 3]
+ *	bit  0..31  : timestamp:32 - The MPDU Timestamp.
+ */
+struct wil_rx_status_compressed {
+	u32 d0;
+	u32 d1;
+	__le16 buff_id;
+	__le16 length;
+	u32 timestamp;
+} __packed;
+
+/* Enhanced Rx status message - extension part
+ * [dword 0]
+ *	bit  0.. 4 : QID:5 - The Queue Identifier that the packet is received
+ *		     from
+ *	bit  5.. 7 : Reserved:3
+ *	bit  8..11 : TID:4 - The QoS (b3-0) TID Field
+ *	bit 12..15   Source index:4 - The Source index that was found
+		     during Parsing the TA. This field is used to define the
+		     source of the packet
+ *	bit 16..18 : Destination index:3 - The Destination index that
+		     was found during Parsing the RA.
+ *	bit 19..20 : DS Type:2 - The FC Control (b9-8) - From / To DS
+ *	bit 21..22 : MIC ICR:2 - this signal tells the DMA to assert an
+		     interrupt after it writes the packet
+ *	bit     23 : ESOP:1 - The QoS (b4) ESOP field
+ *	bit     24 : RDG:1
+ *	bit 25..31 : Reserved:7
+ * [dword 1]
+ *	bit  0.. 1 : Frame Type:2 - The FC Control (b3-2) - MPDU Type
+		     (management, data, control and extension)
+ *	bit  2.. 5 : Syb type:4 - The FC Control (b7-4) - Frame Subtype
+ *	bit  6..11 : Ext sub type:6 - The FC Control (b11-8) - Frame Extended
+ *                   Subtype
+ *	bit 12..13 : ACK Policy:2 - The QoS (b6-5) ACK Policy fields
+ *	bit 14     : DECRYPT_BYP:1 - The MPDU is bypass by the decryption unit
+ *	bit 15..23 : Reserved:9
+ *	bit 24..31 : RSSI/SNR:8 - The RSSI / SNR measurement for the received
+ *                   MPDU
+ * [dword 2]
+ *	bit  0..11 : SN:12 - The received Sequence number field
+ *	bit 12..15 : Reserved:4
+ *	bit 16..31 : PN bits [15:0]:16
+ * [dword 3]
+ *	bit  0..31 : PN bits [47:16]:32
+ */
+struct wil_rx_status_extension {
+	u32 d0;
+	u32 d1;
+	__le16 seq_num; /* only lower 12 bits */
+	u16 pn_15_0;
+	u32 pn_47_16;
+} __packed;
+
+struct wil_rx_status_extended {
+	struct wil_rx_status_compressed comp;
+	struct wil_rx_status_extension ext;
+} __packed;
+
+static inline void *wil_skb_rxstatus(struct sk_buff *skb)
+{
+	return (void *)skb->cb;
+}
+
+static inline __le16 wil_rx_status_get_length(void *msg)
+{
+	return ((struct wil_rx_status_compressed *)msg)->length;
+}
+
+static inline u8 wil_rx_status_get_mcs(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d1,
+			    16, 21);
+}
+
+static inline u16 wil_rx_status_get_flow_id(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    8, 19);
+}
+
+static inline u8 wil_rx_status_get_mcast(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    26, 26);
+}
+
+/**
+ * In case of DLPF miss the parsing of flow Id should be as follows:
+ * dest_id:2
+ * src_id :3 - cid
+ * tid:3
+ * Otherwise:
+ * tid:4
+ * cid:4
+ */
+
+static inline u8 wil_rx_status_get_cid(void *msg)
+{
+	u16 val = wil_rx_status_get_flow_id(msg);
+
+	if (val & WIL_RX_EDMA_DLPF_LU_MISS_BIT)
+		/* CID is in bits 2..4 */
+		return (val >> WIL_RX_EDMA_DLPF_LU_MISS_CID_POS) &
+			WIL_RX_EDMA_DLPF_LU_MISS_CID_TID_MASK;
+	else
+		/* CID is in bits 4..7 */
+		return (val >> WIL_RX_EDMA_DLPF_LU_HIT_CID_POS) &
+			WIL_RX_EDMA_DLPF_LU_HIT_CID_TID_MASK;
+}
+
+static inline u8 wil_rx_status_get_tid(void *msg)
+{
+	u16 val = wil_rx_status_get_flow_id(msg);
+
+	if (val & WIL_RX_EDMA_DLPF_LU_MISS_BIT)
+		/* TID is in bits 5..7 */
+		return (val >> WIL_RX_EDMA_DLPF_LU_MISS_TID_POS) &
+			WIL_RX_EDMA_DLPF_LU_MISS_CID_TID_MASK;
+	else
+		/* TID is in bits 0..3 */
+		return val & WIL_RX_EDMA_DLPF_LU_MISS_CID_TID_MASK;
+}
+
+static inline int wil_rx_status_get_desc_rdy_bit(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    31, 31);
+}
+
+static inline int wil_rx_status_get_eop(void *msg) /* EoP = End of Packet */
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    30, 30);
+}
+
+static inline __le16 wil_rx_status_get_buff_id(void *msg)
+{
+	return ((struct wil_rx_status_compressed *)msg)->buff_id;
+}
+
+static inline u8 wil_rx_status_get_data_offset(void *msg)
+{
+	u8 val = WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d1,
+			      24, 27);
+
+	switch (val) {
+	case 0: return 0;
+	case 3: return 2;
+	default: return 0xFF;
+	}
+}
+
+static inline int wil_rx_status_get_frame_type(struct wil6210_priv *wil,
+					       void *msg)
+{
+	if (wil->use_compressed_rx_status)
+		return IEEE80211_FTYPE_DATA;
+
+	return WIL_GET_BITS(((struct wil_rx_status_extended *)msg)->ext.d1,
+			    0, 1) << 2;
+}
+
+static inline int wil_rx_status_get_fc1(struct wil6210_priv *wil, void *msg)
+{
+	if (wil->use_compressed_rx_status)
+		return 0;
+
+	return WIL_GET_BITS(((struct wil_rx_status_extended *)msg)->ext.d1,
+			    0, 5) << 2;
+}
+
+static inline __le16 wil_rx_status_get_seq(struct wil6210_priv *wil, void *msg)
+{
+	if (wil->use_compressed_rx_status)
+		return 0;
+
+	return ((struct wil_rx_status_extended *)msg)->ext.seq_num;
+}
+
+static inline u8 wil_rx_status_get_retry(void *msg)
+{
+	/* retry bit is missing in EDMA HW. return 1 to be on the safe side */
+	return 1;
+}
+
+static inline int wil_rx_status_get_mid(void *msg)
+{
+	if (!(((struct wil_rx_status_compressed *)msg)->d0 &
+	    WIL_RX_EDMA_MID_VALID_BIT))
+		return 0; /* use the default MID */
+
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    20, 21);
+}
+
+static inline int wil_rx_status_get_error(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    29, 29);
+}
+
+static inline int wil_rx_status_get_l2_rx_status(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    0, 2);
+}
+
+static inline int wil_rx_status_get_l3_rx_status(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    3, 4);
+}
+
+static inline int wil_rx_status_get_l4_rx_status(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    5, 6);
+}
+
+static inline int wil_rx_status_get_security(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    28, 28);
+}
+
+static inline u8 wil_rx_status_get_key_id(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d1,
+			    31, 31);
+}
+
+static inline u8 wil_tx_status_get_mcs(struct wil_ring_tx_status *msg)
+{
+	return WIL_GET_BITS(msg->d2, 0, 4);
+}
+
+static inline u32 wil_ring_next_head(struct wil_ring *ring)
+{
+	return (ring->swhead + 1) % ring->size;
+}
+
+static inline void wil_desc_set_addr_edma(struct wil_ring_dma_addr *addr,
+					  __le16 *addr_high_high,
+					  dma_addr_t pa)
+{
+	addr->addr_low = cpu_to_le32(lower_32_bits(pa));
+	addr->addr_high = cpu_to_le16((u16)upper_32_bits(pa));
+	*addr_high_high = cpu_to_le16((u16)(upper_32_bits(pa) >> 16));
+}
+
+static inline
+dma_addr_t wil_tx_desc_get_addr_edma(struct wil_ring_tx_enhanced_dma *dma)
+{
+	return le32_to_cpu(dma->addr.addr_low) |
+			   ((u64)le16_to_cpu(dma->addr.addr_high) << 32) |
+			   ((u64)le16_to_cpu(dma->addr_high_high) << 48);
+}
+
+static inline
+dma_addr_t wil_rx_desc_get_addr_edma(struct wil_ring_rx_enhanced_dma *dma)
+{
+	return le32_to_cpu(dma->addr.addr_low) |
+			   ((u64)le16_to_cpu(dma->addr.addr_high) << 32) |
+			   ((u64)le16_to_cpu(dma->addr_high_high) << 48);
+}
+
+void wil_configure_interrupt_moderation_edma(struct wil6210_priv *wil);
+int wil_tx_sring_handler(struct wil6210_priv *wil,
+			 struct wil_status_ring *sring);
+void wil_rx_handle_edma(struct wil6210_priv *wil, int *quota);
+void wil_init_txrx_ops_edma(struct wil6210_priv *wil);
+
+#endif /* WIL6210_TXRX_EDMA_H */
+
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index b623510c6f6c..17c294b1ead1 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -24,6 +24,7 @@
 #include <net/cfg80211.h>
 #include <linux/timex.h>
 #include <linux/types.h>
+#include <linux/irqreturn.h>
 #include "wmi.h"
 #include "wil_platform.h"
 #include "fw.h"
@@ -36,6 +37,11 @@ extern bool rx_align_2;
 extern bool rx_large_buf;
 extern bool debug_fw;
 extern bool disable_ap_sme;
+extern bool ftm_mode;
+
+struct wil6210_priv;
+struct wil6210_vif;
+union wil_tx_desc;
 
 #define WIL_NAME "wil6210"
 
@@ -45,11 +51,17 @@ extern bool disable_ap_sme;
 #define WIL_FW_NAME_SPARROW_PLUS "wil6210_sparrow_plus.fw"
 #define WIL_FW_NAME_FTM_SPARROW_PLUS "wil6210_sparrow_plus_ftm.fw"
 
+#define WIL_FW_NAME_TALYN "wil6436.fw"
+#define WIL_FW_NAME_FTM_TALYN "wil6436_ftm.fw"
+#define WIL_BRD_NAME_TALYN "wil6436.brd"
+
 #define WIL_BOARD_FILE_NAME "wil6210.brd" /* board & radio parameters */
 
 #define WIL_DEFAULT_BUS_REQUEST_KBPS 128000 /* ~1Gbps */
 #define WIL_MAX_BUS_REQUEST_KBPS 800000 /* ~6.1Gbps */
 
+#define WIL_NUM_LATENCY_BINS 200
+
 /* maximum number of virtual interfaces the driver supports
  * (including the main interface)
  */
@@ -80,6 +92,10 @@ static inline u32 WIL_GET_BITS(u32 x, int b0, int b1)
 #define WIL6210_NAPI_BUDGET	(16) /* arbitrary */
 #define WIL_MAX_AMPDU_SIZE	(64 * 1024) /* FW/HW limit */
 #define WIL_MAX_AGG_WSIZE	(32) /* FW/HW limit */
+#define WIL_MAX_AMPDU_SIZE_128	(128 * 1024) /* FW/HW limit */
+#define WIL_MAX_AGG_WSIZE_64	(64) /* FW/HW limit */
+#define WIL6210_MAX_STATUS_RINGS	(8)
+
 /* Hardware offload block adds the following:
  * 26 bytes - 3-address QoS data header
  *  8 bytes - IV + EIV (for GCMP)
@@ -203,7 +219,9 @@ struct RGF_ICR {
 #define RGF_USER_SPARROW_M_4			(0x880c50) /* Sparrow */
 	#define BIT_SPARROW_M_4_SEL_SLEEP_OR_REF	BIT(2)
 #define RGF_USER_OTP_HW_RD_MACHINE_1	(0x880ce0)
-	#define BIT_NO_FLASH_INDICATION		BIT(8)
+	#define BIT_OTP_SIGNATURE_ERR_TALYN_MB		BIT(0)
+	#define BIT_OTP_HW_SECTION_DONE_TALYN_MB	BIT(2)
+	#define BIT_NO_FLASH_INDICATION			BIT(8)
 #define RGF_USER_XPM_IFC_RD_TIME1	(0x880cec)
 #define RGF_USER_XPM_IFC_RD_TIME2	(0x880cf0)
 #define RGF_USER_XPM_IFC_RD_TIME3	(0x880cf4)
@@ -284,6 +302,8 @@ struct RGF_ICR {
 	#define BIT_DMA_ITR_RX_IDL_CNT_CTL_FOREVER		BIT(2)
 	#define BIT_DMA_ITR_RX_IDL_CNT_CTL_CLR			BIT(3)
 	#define BIT_DMA_ITR_RX_IDL_CNT_CTL_REACHED_TRESH	BIT(4)
+#define RGF_DMA_MISC_CTL				(0x881d6c)
+	#define BIT_OFUL34_RDY_VALID_BUG_FIX_EN			BIT(7)
 
 #define RGF_DMA_PSEUDO_CAUSE		(0x881c68)
 #define RGF_DMA_PSEUDO_CAUSE_MASK_SW	(0x881c6c)
@@ -305,20 +325,49 @@ struct RGF_ICR {
 #define RGF_CAF_PLL_LOCK_STATUS		(0x88afec)
 	#define BIT_CAF_OSC_DIG_XTAL_STABLE	BIT(0)
 
+#define RGF_OTP_QC_SECURED		(0x8a0038)
+	#define BIT_BOOT_FROM_ROM		BIT(31)
+
+/* eDMA */
+#define RGF_INT_COUNT_ON_SPECIAL_EVT	(0x8b62d8)
+
+#define RGF_INT_CTRL_INT_GEN_CFG_0	(0x8bc000)
+#define RGF_INT_CTRL_INT_GEN_CFG_1	(0x8bc004)
+#define RGF_INT_GEN_TIME_UNIT_LIMIT	(0x8bc0c8)
+
+#define RGF_INT_GEN_CTRL		(0x8bc0ec)
+	#define BIT_CONTROL_0			BIT(0)
+
+/* eDMA status interrupts */
+#define RGF_INT_GEN_RX_ICR		(0x8bc0f4)
+	#define BIT_RX_STATUS_IRQ BIT(WIL_RX_STATUS_IRQ_IDX)
+#define RGF_INT_GEN_TX_ICR		(0x8bc110)
+	#define BIT_TX_STATUS_IRQ BIT(WIL_TX_STATUS_IRQ_IDX)
+#define RGF_INT_CTRL_RX_INT_MASK	(0x8bc12c)
+#define RGF_INT_CTRL_TX_INT_MASK	(0x8bc130)
+
+#define RGF_INT_GEN_IDLE_TIME_LIMIT	(0x8bc134)
+
 #define USER_EXT_USER_PMU_3		(0x88d00c)
 	#define BIT_PMU_DEVICE_RDY		BIT(0)
 
 #define RGF_USER_JTAG_DEV_ID	(0x880b34) /* device ID */
 	#define JTAG_DEV_ID_SPARROW	(0x2632072f)
 	#define JTAG_DEV_ID_TALYN	(0x7e0e1)
+	#define JTAG_DEV_ID_TALYN_MB	(0x1007e0e1)
 
 #define RGF_USER_REVISION_ID		(0x88afe4)
 #define RGF_USER_REVISION_ID_MASK	(3)
 	#define REVISION_ID_SPARROW_B0	(0x0)
 	#define REVISION_ID_SPARROW_D0	(0x3)
 
+#define RGF_OTP_MAC_TALYN_MB		(0x8a0304)
 #define RGF_OTP_MAC			(0x8a0620)
 
+/* Talyn-MB */
+#define RGF_USER_USER_CPU_0_TALYN_MB	(0x8c0138)
+#define RGF_USER_MAC_CPU_0_TALYN_MB	(0x8c0154)
+
 /* crash codes for FW/Ucode stored here */
 
 /* ASSERT RGFs */
@@ -332,6 +381,7 @@ enum {
 	HW_VER_SPARROW_B0, /* REVISION_ID_SPARROW_B0 */
 	HW_VER_SPARROW_D0, /* REVISION_ID_SPARROW_D0 */
 	HW_VER_TALYN,	/* JTAG_DEV_ID_TALYN */
+	HW_VER_TALYN_MB	/* JTAG_DEV_ID_TALYN_MB */
 };
 
 /* popular locations */
@@ -349,7 +399,14 @@ enum {
 /* Hardware definitions end */
 #define SPARROW_FW_MAPPING_TABLE_SIZE 10
 #define TALYN_FW_MAPPING_TABLE_SIZE 13
-#define MAX_FW_MAPPING_TABLE_SIZE 13
+#define TALYN_MB_FW_MAPPING_TABLE_SIZE 19
+#define MAX_FW_MAPPING_TABLE_SIZE 19
+
+/* Common representation of physical address in wil ring */
+struct wil_ring_dma_addr {
+	__le32 addr_low;
+	__le16 addr_high;
+} __packed;
 
 struct fw_map {
 	u32 from; /* linker address - from, inclusive */
@@ -357,12 +414,14 @@ struct fw_map {
 	u32 host; /* PCI/Host address - BAR0 + 0x880000 */
 	const char *name; /* for debugfs */
 	bool fw; /* true if FW mapping, false if UCODE mapping */
+	bool crash_dump; /* true if should be dumped during crash dump */
 };
 
 /* array size should be in sync with actual definition in the wmi.c */
 extern const struct fw_map sparrow_fw_mapping[SPARROW_FW_MAPPING_TABLE_SIZE];
 extern const struct fw_map sparrow_d0_mac_rgf_ext;
 extern const struct fw_map talyn_fw_mapping[TALYN_FW_MAPPING_TABLE_SIZE];
+extern const struct fw_map talyn_mb_fw_mapping[TALYN_MB_FW_MAPPING_TABLE_SIZE];
 extern struct fw_map fw_mapping[MAX_FW_MAPPING_TABLE_SIZE];
 
 /**
@@ -438,7 +497,7 @@ enum { /* for wil_ctx.mapped_as */
 };
 
 /**
- * struct wil_ctx - software context for Vring descriptor
+ * struct wil_ctx - software context for ring descriptor
  */
 struct wil_ctx {
 	struct sk_buff *skb;
@@ -446,22 +505,123 @@ struct wil_ctx {
 	u8 mapped_as;
 };
 
-union vring_desc;
+struct wil_desc_ring_rx_swtail { /* relevant for enhanced DMA only */
+	u32 *va;
+	dma_addr_t pa;
+};
 
-struct vring {
+/**
+ * A general ring structure, used for RX and TX.
+ * In legacy DMA it represents the vring,
+ * In enahnced DMA it represents the descriptor ring (vrings are handled by FW)
+ */
+struct wil_ring {
 	dma_addr_t pa;
-	volatile union vring_desc *va; /* vring_desc[size], WriteBack by DMA */
-	u16 size; /* number of vring_desc elements */
+	volatile union wil_ring_desc *va;
+	u16 size; /* number of wil_ring_desc elements */
 	u32 swtail;
 	u32 swhead;
 	u32 hwtail; /* write here to inform hw */
 	struct wil_ctx *ctx; /* ctx[size] - software context */
+	struct wil_desc_ring_rx_swtail edma_rx_swtail;
+	bool is_rx;
+};
+
+/**
+ * Additional data for Rx ring.
+ * Used for enhanced DMA RX chaining.
+ */
+struct wil_ring_rx_data {
+	/* the skb being assembled */
+	struct sk_buff *skb;
+	/* true if we are skipping a bad fragmented packet */
+	bool skipping;
+	u16 buff_size;
+};
+
+/**
+ * Status ring structure, used for enhanced DMA completions for RX and TX.
+ */
+struct wil_status_ring {
+	dma_addr_t pa;
+	void *va; /* pointer to ring_[tr]x_status elements */
+	u16 size; /* number of status elements */
+	size_t elem_size; /* status element size in bytes */
+	u32 swhead;
+	u32 hwtail; /* write here to inform hw */
+	bool is_rx;
+	u8 desc_rdy_pol; /* Expected descriptor ready bit polarity */
+	struct wil_ring_rx_data rx_data;
+};
+
+#define WIL_STA_TID_NUM (16)
+#define WIL_MCS_MAX (12) /* Maximum MCS supported */
+
+struct wil_net_stats {
+	unsigned long	rx_packets;
+	unsigned long	tx_packets;
+	unsigned long	rx_bytes;
+	unsigned long	tx_bytes;
+	unsigned long	tx_errors;
+	u32 tx_latency_min_us;
+	u32 tx_latency_max_us;
+	u64 tx_latency_total_us;
+	unsigned long	rx_dropped;
+	unsigned long	rx_non_data_frame;
+	unsigned long	rx_short_frame;
+	unsigned long	rx_large_frame;
+	unsigned long	rx_replay;
+	unsigned long	rx_mic_error;
+	unsigned long	rx_key_error; /* eDMA specific */
+	unsigned long	rx_amsdu_error; /* eDMA specific */
+	unsigned long	rx_csum_err;
+	u16 last_mcs_rx;
+	u64 rx_per_mcs[WIL_MCS_MAX + 1];
 };
 
 /**
- * Additional data for Tx Vring
+ * struct tx_rx_ops - different TX/RX ops for legacy and enhanced
+ * DMA flow
  */
-struct vring_tx_data {
+struct wil_txrx_ops {
+	void (*configure_interrupt_moderation)(struct wil6210_priv *wil);
+	/* TX ops */
+	int (*ring_init_tx)(struct wil6210_vif *vif, int ring_id,
+			    int size, int cid, int tid);
+	void (*ring_fini_tx)(struct wil6210_priv *wil, struct wil_ring *ring);
+	int (*ring_init_bcast)(struct wil6210_vif *vif, int id, int size);
+	int (*tx_init)(struct wil6210_priv *wil);
+	void (*tx_fini)(struct wil6210_priv *wil);
+	int (*tx_desc_map)(union wil_tx_desc *desc, dma_addr_t pa,
+			   u32 len, int ring_index);
+	void (*tx_desc_unmap)(struct device *dev,
+			      union wil_tx_desc *desc,
+			      struct wil_ctx *ctx);
+	int (*tx_ring_tso)(struct wil6210_priv *wil, struct wil6210_vif *vif,
+			   struct wil_ring *ring, struct sk_buff *skb);
+	irqreturn_t (*irq_tx)(int irq, void *cookie);
+	/* RX ops */
+	int (*rx_init)(struct wil6210_priv *wil, u16 ring_size);
+	void (*rx_fini)(struct wil6210_priv *wil);
+	int (*wmi_addba_rx_resp)(struct wil6210_priv *wil, u8 mid, u8 cid,
+				 u8 tid, u8 token, u16 status, bool amsdu,
+				 u16 agg_wsize, u16 timeout);
+	void (*get_reorder_params)(struct wil6210_priv *wil,
+				   struct sk_buff *skb, int *tid, int *cid,
+				   int *mid, u16 *seq, int *mcast, int *retry);
+	void (*get_netif_rx_params)(struct sk_buff *skb,
+				    int *cid, int *security);
+	int (*rx_crypto_check)(struct wil6210_priv *wil, struct sk_buff *skb);
+	int (*rx_error_check)(struct wil6210_priv *wil, struct sk_buff *skb,
+			      struct wil_net_stats *stats);
+	bool (*is_rx_idle)(struct wil6210_priv *wil);
+	irqreturn_t (*irq_rx)(int irq, void *cookie);
+};
+
+/**
+ * Additional data for Tx ring
+ */
+struct wil_ring_tx_data {
 	bool dot1x_open;
 	int enabled;
 	cycles_t idle, last_idle, begin;
@@ -503,6 +663,8 @@ struct pci_dev;
  * @drop_dup: duplicate frames dropped for this reorder buffer
  * @drop_old: old frames dropped for this reorder buffer
  * @first_time: true when this buffer used 1-st time
+ * @mcast_last_seq: sequence number (SN) of last received multicast packet
+ * @drop_dup_mcast: duplicate multicast frames dropped for this reorder buffer
  */
 struct wil_tid_ampdu_rx {
 	struct sk_buff **reorder_buf;
@@ -516,6 +678,8 @@ struct wil_tid_ampdu_rx {
 	unsigned long long drop_dup;
 	unsigned long long drop_old;
 	bool first_time; /* is it 1-st time this buffer used? */
+	u16 mcast_last_seq; /* multicast dup detection */
+	unsigned long long drop_dup_mcast;
 };
 
 /**
@@ -550,24 +714,6 @@ enum wil_sta_status {
 	wil_sta_connected = 2,
 };
 
-#define WIL_STA_TID_NUM (16)
-#define WIL_MCS_MAX (12) /* Maximum MCS supported */
-
-struct wil_net_stats {
-	unsigned long	rx_packets;
-	unsigned long	tx_packets;
-	unsigned long	rx_bytes;
-	unsigned long	tx_bytes;
-	unsigned long	tx_errors;
-	unsigned long	rx_dropped;
-	unsigned long	rx_non_data_frame;
-	unsigned long	rx_short_frame;
-	unsigned long	rx_large_frame;
-	unsigned long	rx_replay;
-	u16 last_mcs_rx;
-	u64 rx_per_mcs[WIL_MCS_MAX + 1];
-};
-
 /**
  * struct wil_sta_info - data for peer
  *
@@ -581,6 +727,14 @@ struct wil_sta_info {
 	u8 mid;
 	enum wil_sta_status status;
 	struct wil_net_stats stats;
+	/**
+	 * 20 latency bins. 1st bin counts packets with latency
+	 * of 0..tx_latency_res, last bin counts packets with latency
+	 * of 19*tx_latency_res and above.
+	 * tx_latency_res is configured from "tx_latency" debug-fs.
+	 */
+	u64 *tx_latency_bins;
+	struct wmi_link_stats_basic fw_stats_basic;
 	/* Rx BACK */
 	struct wil_tid_ampdu_rx *tid_rx[WIL_STA_TID_NUM];
 	spinlock_t tid_rx_lock; /* guarding tid_rx array */
@@ -681,7 +835,7 @@ struct wil6210_vif {
 	u8 hidden_ssid; /* relevant in AP mode */
 	u32 ap_isolate; /* no intra-BSS communication */
 	bool pbss;
-	int bcast_vring;
+	int bcast_ring;
 	struct cfg80211_bss *bss; /* connected bss, relevant in STA mode */
 	int locally_generated_disc; /* relevant in STA mode */
 	struct timer_list connect_timer;
@@ -695,6 +849,39 @@ struct wil6210_vif {
 	struct mutex probe_client_mutex; /* protect @probe_client_pending */
 	struct work_struct probe_client_worker;
 	int net_queue_stopped; /* netif_tx_stop_all_queues invoked */
+	bool fw_stats_ready; /* per-cid statistics are ready inside sta_info */
+	u64 fw_stats_tsf; /* measurement timestamp */
+};
+
+/**
+ * RX buffer allocated for enhanced DMA RX descriptors
+ */
+struct wil_rx_buff {
+	struct sk_buff *skb;
+	struct list_head list;
+	int id;
+};
+
+/**
+ * During Rx completion processing, the driver extracts a buffer ID which
+ * is used as an index to the rx_buff_mgmt.buff_arr array and then the SKB
+ * is given to the network stack and the buffer is moved from the 'active'
+ * list to the 'free' list.
+ * During Rx refill, SKBs are attached to free buffers and moved to the
+ * 'active' list.
+ */
+struct wil_rx_buff_mgmt {
+	struct wil_rx_buff *buff_arr;
+	size_t size; /* number of items in buff_arr */
+	struct list_head active;
+	struct list_head free;
+	unsigned long free_list_empty_cnt; /* statistics */
+};
+
+struct wil_fw_stats_global {
+	bool ready;
+	u64 tsf; /* measurement timestamp */
+	struct wmi_link_stats_global stats;
 };
 
 struct wil6210_priv {
@@ -702,6 +889,7 @@ struct wil6210_priv {
 	u32 bar_size;
 	struct wiphy *wiphy;
 	struct net_device *main_ndev;
+	int n_msi;
 	void __iomem *csr;
 	DECLARE_BITMAP(status, wil_status_last);
 	u8 fw_version[ETHTOOL_FWVERS_LEN];
@@ -761,14 +949,20 @@ struct wil6210_priv {
 	struct net_device napi_ndev; /* dummy net_device serving all VIFs */
 
 	/* DMA related */
-	struct vring vring_rx;
+	struct wil_ring ring_rx;
 	unsigned int rx_buf_len;
-	struct vring vring_tx[WIL6210_MAX_TX_RINGS];
-	struct vring_tx_data vring_tx_data[WIL6210_MAX_TX_RINGS];
-	u8 vring2cid_tid[WIL6210_MAX_TX_RINGS][2]; /* [0] - CID, [1] - TID */
+	struct wil_ring ring_tx[WIL6210_MAX_TX_RINGS];
+	struct wil_ring_tx_data ring_tx_data[WIL6210_MAX_TX_RINGS];
+	struct wil_status_ring srings[WIL6210_MAX_STATUS_RINGS];
+	u8 num_rx_status_rings;
+	int tx_sring_idx;
+	u8 ring2cid_tid[WIL6210_MAX_TX_RINGS][2]; /* [0] - CID, [1] - TID */
 	struct wil_sta_info sta[WIL6210_MAX_CID];
-	u32 vring_idle_trsh; /* HW fetches up to 16 descriptors at once  */
+	u32 ring_idle_trsh; /* HW fetches up to 16 descriptors at once  */
 	u32 dma_addr_size; /* indicates dma addr size */
+	struct wil_rx_buff_mgmt rx_buff_mgmt;
+	bool use_enhanced_dma_hw;
+	struct wil_txrx_ops txrx_ops;
 
 	struct mutex mutex; /* for wil6210_priv access in wil_{up|down} */
 	/* statistics */
@@ -781,6 +975,8 @@ struct wil6210_priv {
 	u8 wakeup_trigger;
 	struct wil_suspend_stats suspend_stats;
 	struct wil_debugfs_data dbg_data;
+	bool tx_latency; /* collect TX latency measurements */
+	size_t tx_latency_res; /* bin resolution in usec */
 
 	void *platform_handle;
 	struct wil_platform_ops platform_ops;
@@ -811,6 +1007,21 @@ struct wil6210_priv {
 	u32 rgf_fw_assert_code_addr;
 	u32 rgf_ucode_assert_code_addr;
 	u32 iccm_base;
+
+	/* relevant only for eDMA */
+	bool use_compressed_rx_status;
+	u32 rx_status_ring_order;
+	u32 tx_status_ring_order;
+	u32 rx_buff_id_count;
+	bool amsdu_en;
+	bool use_rx_hw_reordering;
+	bool secured_boot;
+	u8 boot_config;
+
+	struct wil_fw_stats_global fw_stats_global;
+
+	u32 max_agg_wsize;
+	u32 max_ampdu_size;
 };
 
 #define wil_to_wiphy(i) (i->wiphy)
@@ -894,6 +1105,8 @@ static inline void wil_c(struct wil6210_priv *wil, u32 reg, u32 val)
 	wil_w(wil, reg, wil_r(wil, reg) & ~val);
 }
 
+void wil_get_board_file(struct wil6210_priv *wil, char *buf, size_t len);
+
 #if defined(CONFIG_DYNAMIC_DEBUG)
 #define wil_hex_dump_txrx(prefix_str, prefix_type, rowsize,	\
 			  groupsize, buf, len, ascii)		\
@@ -990,7 +1203,7 @@ int wmi_add_cipher_key(struct wil6210_vif *vif, u8 key_index,
 		       int key_usage);
 int wmi_echo(struct wil6210_priv *wil);
 int wmi_set_ie(struct wil6210_vif *vif, u8 type, u16 ie_len, const void *ie);
-int wmi_rx_chain_add(struct wil6210_priv *wil, struct vring *vring);
+int wmi_rx_chain_add(struct wil6210_priv *wil, struct wil_ring *vring);
 int wmi_rxon(struct wil6210_priv *wil, bool on);
 int wmi_get_temperature(struct wil6210_priv *wil, u32 *t_m, u32 *t_r);
 int wmi_disconnect_sta(struct wil6210_vif *vif, const u8 *mac,
@@ -1010,13 +1223,14 @@ int wmi_new_sta(struct wil6210_vif *vif, const u8 *mac, u8 aid);
 int wmi_port_allocate(struct wil6210_priv *wil, u8 mid,
 		      const u8 *mac, enum nl80211_iftype iftype);
 int wmi_port_delete(struct wil6210_priv *wil, u8 mid);
+int wmi_link_stats_cfg(struct wil6210_vif *vif, u32 type, u8 cid, u32 interval);
 int wil_addba_rx_request(struct wil6210_priv *wil, u8 mid,
 			 u8 cidxtid, u8 dialog_token, __le16 ba_param_set,
 			 __le16 ba_timeout, __le16 ba_seq_ctrl);
 int wil_addba_tx_request(struct wil6210_priv *wil, u8 ringid, u16 wsize);
 
 void wil6210_clear_irq(struct wil6210_priv *wil);
-int wil6210_init_irq(struct wil6210_priv *wil, int irq, bool use_msi);
+int wil6210_init_irq(struct wil6210_priv *wil, int irq);
 void wil6210_fini_irq(struct wil6210_priv *wil, int irq);
 void wil_mask_irq(struct wil6210_priv *wil);
 void wil_unmask_irq(struct wil6210_priv *wil);
@@ -1083,30 +1297,28 @@ void wil_probe_client_flush(struct wil6210_vif *vif);
 void wil_probe_client_worker(struct work_struct *work);
 void wil_disconnect_worker(struct work_struct *work);
 
-int wil_rx_init(struct wil6210_priv *wil, u16 size);
-void wil_rx_fini(struct wil6210_priv *wil);
+void wil_init_txrx_ops(struct wil6210_priv *wil);
 
 /* TX API */
-int wil_vring_init_tx(struct wil6210_vif *vif, int id, int size,
-		      int cid, int tid);
-void wil_vring_fini_tx(struct wil6210_priv *wil, int id);
-int wil_tx_init(struct wil6210_vif *vif, int cid);
+int wil_ring_init_tx(struct wil6210_vif *vif, int cid);
 int wil_vring_init_bcast(struct wil6210_vif *vif, int id, int size);
 int wil_bcast_init(struct wil6210_vif *vif);
 void wil_bcast_fini(struct wil6210_vif *vif);
 void wil_bcast_fini_all(struct wil6210_priv *wil);
 
 void wil_update_net_queues(struct wil6210_priv *wil, struct wil6210_vif *vif,
-			   struct vring *vring, bool should_stop);
+			   struct wil_ring *ring, bool should_stop);
 void wil_update_net_queues_bh(struct wil6210_priv *wil, struct wil6210_vif *vif,
-			      struct vring *vring, bool check_stop);
+			      struct wil_ring *ring, bool check_stop);
 netdev_tx_t wil_start_xmit(struct sk_buff *skb, struct net_device *ndev);
 int wil_tx_complete(struct wil6210_vif *vif, int ringid);
 void wil6210_unmask_irq_tx(struct wil6210_priv *wil);
+void wil6210_unmask_irq_tx_edma(struct wil6210_priv *wil);
 
 /* RX API */
 void wil_rx_handle(struct wil6210_priv *wil, int *quota);
 void wil6210_unmask_irq_rx(struct wil6210_priv *wil);
+void wil6210_unmask_irq_rx_edma(struct wil6210_priv *wil);
 
 int wil_iftype_nl2wmi(enum nl80211_iftype type);
 
@@ -1127,7 +1339,6 @@ bool wil_is_wmi_idle(struct wil6210_priv *wil);
 int wmi_resume(struct wil6210_priv *wil);
 int wmi_suspend(struct wil6210_priv *wil);
 bool wil_is_tx_idle(struct wil6210_priv *wil);
-bool wil_is_rx_idle(struct wil6210_priv *wil);
 
 int wil_fw_copy_crash_dump(struct wil6210_priv *wil, void *dest, u32 size);
 void wil_fw_core_dump(struct wil6210_priv *wil);
@@ -1141,5 +1352,22 @@ int wmi_start_sched_scan(struct wil6210_priv *wil,
 			 struct cfg80211_sched_scan_request *request);
 int wmi_stop_sched_scan(struct wil6210_priv *wil);
 int wmi_mgmt_tx(struct wil6210_vif *vif, const u8 *buf, size_t len);
+int wmi_mgmt_tx_ext(struct wil6210_vif *vif, const u8 *buf, size_t len,
+		    u8 channel, u16 duration_ms);
+
+int reverse_memcmp(const void *cs, const void *ct, size_t count);
+
+/* WMI for enhanced DMA */
+int wil_wmi_tx_sring_cfg(struct wil6210_priv *wil, int ring_id);
+int wil_wmi_cfg_def_rx_offload(struct wil6210_priv *wil,
+			       u16 max_rx_pl_per_desc);
+int wil_wmi_rx_sring_add(struct wil6210_priv *wil, u16 ring_id);
+int wil_wmi_rx_desc_ring_add(struct wil6210_priv *wil, int status_ring_id);
+int wil_wmi_tx_desc_ring_add(struct wil6210_vif *vif, int ring_id, int cid,
+			     int tid);
+int wil_wmi_bcast_desc_ring_add(struct wil6210_vif *vif, int ring_id);
+int wmi_addba_rx_resp_edma(struct wil6210_priv *wil, u8 mid, u8 cid,
+			   u8 tid, u8 token, u16 status, bool amsdu,
+			   u16 agg_wsize, u16 timeout);
 
 #endif /* __WIL6210_H__ */
diff --git a/drivers/net/wireless/ath/wil6210/wil_crash_dump.c b/drivers/net/wireless/ath/wil6210/wil_crash_dump.c
index 1ed330674d9b..dc33a0b4c3fa 100644
--- a/drivers/net/wireless/ath/wil6210/wil_crash_dump.c
+++ b/drivers/net/wireless/ath/wil6210/wil_crash_dump.c
@@ -1,5 +1,6 @@
 /*
  * Copyright (c) 2015,2017 Qualcomm Atheros, Inc.
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
  *
  * Permission to use, copy, modify, and/or distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above
@@ -36,7 +37,7 @@ static int wil_fw_get_crash_dump_bounds(struct wil6210_priv *wil,
 	for (i = 1; i < ARRAY_SIZE(fw_mapping); i++) {
 		map = &fw_mapping[i];
 
-		if (!map->fw)
+		if (!map->crash_dump)
 			continue;
 
 		if (map->host < host_min)
@@ -85,7 +86,7 @@ int wil_fw_copy_crash_dump(struct wil6210_priv *wil, void *dest, u32 size)
 	for (i = 0; i < ARRAY_SIZE(fw_mapping); i++) {
 		map = &fw_mapping[i];
 
-		if (!map->fw)
+		if (!map->crash_dump)
 			continue;
 
 		data = (void * __force)wil->csr + HOSTADDR(map->host);
diff --git a/drivers/net/wireless/ath/wil6210/wil_platform.h b/drivers/net/wireless/ath/wil6210/wil_platform.h
index 177026e5323b..bca090611477 100644
--- a/drivers/net/wireless/ath/wil6210/wil_platform.h
+++ b/drivers/net/wireless/ath/wil6210/wil_platform.h
@@ -29,6 +29,7 @@ enum wil_platform_event {
 
 enum wil_platform_features {
 	WIL_PLATFORM_FEATURE_FW_EXT_CLK_CONTROL = 0,
+	WIL_PLATFORM_FEATURE_TRIPLE_MSI = 1,
 	WIL_PLATFORM_FEATURE_MAX,
 };
 
diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c
index 5d991243cdb5..42c02a20ec97 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.c
+++ b/drivers/net/wireless/ath/wil6210/wmi.c
@@ -89,28 +89,28 @@ MODULE_PARM_DESC(led_id,
  */
 const struct fw_map sparrow_fw_mapping[] = {
 	/* FW code RAM 256k */
-	{0x000000, 0x040000, 0x8c0000, "fw_code", true},
+	{0x000000, 0x040000, 0x8c0000, "fw_code", true, true},
 	/* FW data RAM 32k */
-	{0x800000, 0x808000, 0x900000, "fw_data", true},
+	{0x800000, 0x808000, 0x900000, "fw_data", true, true},
 	/* periph data 128k */
-	{0x840000, 0x860000, 0x908000, "fw_peri", true},
+	{0x840000, 0x860000, 0x908000, "fw_peri", true, true},
 	/* various RGF 40k */
-	{0x880000, 0x88a000, 0x880000, "rgf", true},
+	{0x880000, 0x88a000, 0x880000, "rgf", true, true},
 	/* AGC table   4k */
-	{0x88a000, 0x88b000, 0x88a000, "AGC_tbl", true},
+	{0x88a000, 0x88b000, 0x88a000, "AGC_tbl", true, true},
 	/* Pcie_ext_rgf 4k */
-	{0x88b000, 0x88c000, 0x88b000, "rgf_ext", true},
+	{0x88b000, 0x88c000, 0x88b000, "rgf_ext", true, true},
 	/* mac_ext_rgf 512b */
-	{0x88c000, 0x88c200, 0x88c000, "mac_rgf_ext", true},
+	{0x88c000, 0x88c200, 0x88c000, "mac_rgf_ext", true, true},
 	/* upper area 548k */
-	{0x8c0000, 0x949000, 0x8c0000, "upper", true},
+	{0x8c0000, 0x949000, 0x8c0000, "upper", true, true},
 	/* UCODE areas - accessible by debugfs blobs but not by
 	 * wmi_addr_remap. UCODE areas MUST be added AFTER FW areas!
 	 */
 	/* ucode code RAM 128k */
-	{0x000000, 0x020000, 0x920000, "uc_code", false},
+	{0x000000, 0x020000, 0x920000, "uc_code", false, false},
 	/* ucode data RAM 16k */
-	{0x800000, 0x804000, 0x940000, "uc_data", false},
+	{0x800000, 0x804000, 0x940000, "uc_data", false, false},
 };
 
 /**
@@ -118,7 +118,7 @@ const struct fw_map sparrow_fw_mapping[] = {
  * it is a bit larger to support extra features
  */
 const struct fw_map sparrow_d0_mac_rgf_ext = {
-	0x88c000, 0x88c500, 0x88c000, "mac_rgf_ext", true
+	0x88c000, 0x88c500, 0x88c000, "mac_rgf_ext", true, true
 };
 
 /**
@@ -134,34 +134,89 @@ const struct fw_map sparrow_d0_mac_rgf_ext = {
  */
 const struct fw_map talyn_fw_mapping[] = {
 	/* FW code RAM 1M */
-	{0x000000, 0x100000, 0x900000, "fw_code", true},
+	{0x000000, 0x100000, 0x900000, "fw_code", true, true},
 	/* FW data RAM 128k */
-	{0x800000, 0x820000, 0xa00000, "fw_data", true},
+	{0x800000, 0x820000, 0xa00000, "fw_data", true, true},
 	/* periph. data RAM 96k */
-	{0x840000, 0x858000, 0xa20000, "fw_peri", true},
+	{0x840000, 0x858000, 0xa20000, "fw_peri", true, true},
 	/* various RGF 40k */
-	{0x880000, 0x88a000, 0x880000, "rgf", true},
+	{0x880000, 0x88a000, 0x880000, "rgf", true, true},
 	/* AGC table 4k */
-	{0x88a000, 0x88b000, 0x88a000, "AGC_tbl", true},
+	{0x88a000, 0x88b000, 0x88a000, "AGC_tbl", true, true},
 	/* Pcie_ext_rgf 4k */
-	{0x88b000, 0x88c000, 0x88b000, "rgf_ext", true},
+	{0x88b000, 0x88c000, 0x88b000, "rgf_ext", true, true},
 	/* mac_ext_rgf 1344b */
-	{0x88c000, 0x88c540, 0x88c000, "mac_rgf_ext", true},
+	{0x88c000, 0x88c540, 0x88c000, "mac_rgf_ext", true, true},
 	/* ext USER RGF 4k */
-	{0x88d000, 0x88e000, 0x88d000, "ext_user_rgf", true},
+	{0x88d000, 0x88e000, 0x88d000, "ext_user_rgf", true, true},
 	/* OTP 4k */
-	{0x8a0000, 0x8a1000, 0x8a0000, "otp", true},
+	{0x8a0000, 0x8a1000, 0x8a0000, "otp", true, false},
 	/* DMA EXT RGF 64k */
-	{0x8b0000, 0x8c0000, 0x8b0000, "dma_ext_rgf", true},
+	{0x8b0000, 0x8c0000, 0x8b0000, "dma_ext_rgf", true, true},
 	/* upper area 1536k */
-	{0x900000, 0xa80000, 0x900000, "upper", true},
+	{0x900000, 0xa80000, 0x900000, "upper", true, true},
 	/* UCODE areas - accessible by debugfs blobs but not by
 	 * wmi_addr_remap. UCODE areas MUST be added AFTER FW areas!
 	 */
 	/* ucode code RAM 256k */
-	{0x000000, 0x040000, 0xa38000, "uc_code", false},
+	{0x000000, 0x040000, 0xa38000, "uc_code", false, false},
 	/* ucode data RAM 32k */
-	{0x800000, 0x808000, 0xa78000, "uc_data", false},
+	{0x800000, 0x808000, 0xa78000, "uc_data", false, false},
+};
+
+/**
+ * @talyn_mb_fw_mapping provides memory remapping table for Talyn-MB
+ *
+ * array size should be in sync with the declaration in the wil6210.h
+ *
+ * Talyn MB memory mapping:
+ * Linker address         PCI/Host address
+ *                        0x880000 .. 0xc80000  4Mb BAR0
+ * 0x800000 .. 0x820000   0xa00000 .. 0xa20000  128k DCCM
+ * 0x840000 .. 0x858000   0xa20000 .. 0xa38000  96k PERIPH
+ */
+const struct fw_map talyn_mb_fw_mapping[] = {
+	/* FW code RAM 768k */
+	{0x000000, 0x0c0000, 0x900000, "fw_code", true, true},
+	/* FW data RAM 128k */
+	{0x800000, 0x820000, 0xa00000, "fw_data", true, true},
+	/* periph. data RAM 96k */
+	{0x840000, 0x858000, 0xa20000, "fw_peri", true, true},
+	/* various RGF 40k */
+	{0x880000, 0x88a000, 0x880000, "rgf", true, true},
+	/* AGC table 4k */
+	{0x88a000, 0x88b000, 0x88a000, "AGC_tbl", true, true},
+	/* Pcie_ext_rgf 4k */
+	{0x88b000, 0x88c000, 0x88b000, "rgf_ext", true, true},
+	/* mac_ext_rgf 2256b */
+	{0x88c000, 0x88c8d0, 0x88c000, "mac_rgf_ext", true, true},
+	/* ext USER RGF 4k */
+	{0x88d000, 0x88e000, 0x88d000, "ext_user_rgf", true, true},
+	/* SEC PKA 16k */
+	{0x890000, 0x894000, 0x890000, "sec_pka", true, true},
+	/* SEC KDF RGF 3096b */
+	{0x898000, 0x898c18, 0x898000, "sec_kdf_rgf", true, true},
+	/* SEC MAIN 2124b */
+	{0x89a000, 0x89a84c, 0x89a000, "sec_main", true, true},
+	/* OTP 4k */
+	{0x8a0000, 0x8a1000, 0x8a0000, "otp", true, false},
+	/* DMA EXT RGF 64k */
+	{0x8b0000, 0x8c0000, 0x8b0000, "dma_ext_rgf", true, true},
+	/* DUM USER RGF 528b */
+	{0x8c0000, 0x8c0210, 0x8c0000, "dum_user_rgf", true, true},
+	/* DMA OFU 296b */
+	{0x8c2000, 0x8c2128, 0x8c2000, "dma_ofu", true, true},
+	/* ucode debug 4k */
+	{0x8c3000, 0x8c4000, 0x8c3000, "ucode_debug", true, true},
+	/* upper area 1536k */
+	{0x900000, 0xa80000, 0x900000, "upper", true, true},
+	/* UCODE areas - accessible by debugfs blobs but not by
+	 * wmi_addr_remap. UCODE areas MUST be added AFTER FW areas!
+	 */
+	/* ucode code RAM 256k */
+	{0x000000, 0x040000, 0xa38000, "uc_code", false, false},
+	/* ucode data RAM 32k */
+	{0x800000, 0x808000, 0xa78000, "uc_data", false, false},
 };
 
 struct fw_map fw_mapping[MAX_FW_MAPPING_TABLE_SIZE];
@@ -365,14 +420,16 @@ static const char *cmdid2name(u16 cmdid)
 		return "WMI_DEL_STA_CMD";
 	case WMI_DISCONNECT_STA_CMDID:
 		return "WMI_DISCONNECT_STA_CMD";
-	case WMI_VRING_BA_EN_CMDID:
-		return "WMI_VRING_BA_EN_CMD";
-	case WMI_VRING_BA_DIS_CMDID:
-		return "WMI_VRING_BA_DIS_CMD";
+	case WMI_RING_BA_EN_CMDID:
+		return "WMI_RING_BA_EN_CMD";
+	case WMI_RING_BA_DIS_CMDID:
+		return "WMI_RING_BA_DIS_CMD";
 	case WMI_RCP_DELBA_CMDID:
 		return "WMI_RCP_DELBA_CMD";
 	case WMI_RCP_ADDBA_RESP_CMDID:
 		return "WMI_RCP_ADDBA_RESP_CMD";
+	case WMI_RCP_ADDBA_RESP_EDMA_CMDID:
+		return "WMI_RCP_ADDBA_RESP_EDMA_CMD";
 	case WMI_PS_DEV_PROFILE_CFG_CMDID:
 		return "WMI_PS_DEV_PROFILE_CFG_CMD";
 	case WMI_SET_MGMT_RETRY_LIMIT_CMDID:
@@ -395,6 +452,22 @@ static const char *cmdid2name(u16 cmdid)
 		return "WMI_START_SCHED_SCAN_CMD";
 	case WMI_STOP_SCHED_SCAN_CMDID:
 		return "WMI_STOP_SCHED_SCAN_CMD";
+	case WMI_TX_STATUS_RING_ADD_CMDID:
+		return "WMI_TX_STATUS_RING_ADD_CMD";
+	case WMI_RX_STATUS_RING_ADD_CMDID:
+		return "WMI_RX_STATUS_RING_ADD_CMD";
+	case WMI_TX_DESC_RING_ADD_CMDID:
+		return "WMI_TX_DESC_RING_ADD_CMD";
+	case WMI_RX_DESC_RING_ADD_CMDID:
+		return "WMI_RX_DESC_RING_ADD_CMD";
+	case WMI_BCAST_DESC_RING_ADD_CMDID:
+		return "WMI_BCAST_DESC_RING_ADD_CMD";
+	case WMI_CFG_DEF_RX_OFFLOAD_CMDID:
+		return "WMI_CFG_DEF_RX_OFFLOAD_CMD";
+	case WMI_LINK_STATS_CMDID:
+		return "WMI_LINK_STATS_CMD";
+	case WMI_SW_TX_REQ_EXT_CMDID:
+		return "WMI_SW_TX_REQ_EXT_CMDID";
 	default:
 		return "Untracked CMD";
 	}
@@ -449,8 +522,8 @@ static const char *eventid2name(u16 eventid)
 		return "WMI_RCP_ADDBA_REQ_EVENT";
 	case WMI_DELBA_EVENTID:
 		return "WMI_DELBA_EVENT";
-	case WMI_VRING_EN_EVENTID:
-		return "WMI_VRING_EN_EVENT";
+	case WMI_RING_EN_EVENTID:
+		return "WMI_RING_EN_EVENT";
 	case WMI_DATA_PORT_OPEN_EVENTID:
 		return "WMI_DATA_PORT_OPEN_EVENT";
 	case WMI_AOA_MEAS_EVENTID:
@@ -519,6 +592,20 @@ static const char *eventid2name(u16 eventid)
 		return "WMI_STOP_SCHED_SCAN_EVENT";
 	case WMI_SCHED_SCAN_RESULT_EVENTID:
 		return "WMI_SCHED_SCAN_RESULT_EVENT";
+	case WMI_TX_STATUS_RING_CFG_DONE_EVENTID:
+		return "WMI_TX_STATUS_RING_CFG_DONE_EVENT";
+	case WMI_RX_STATUS_RING_CFG_DONE_EVENTID:
+		return "WMI_RX_STATUS_RING_CFG_DONE_EVENT";
+	case WMI_TX_DESC_RING_CFG_DONE_EVENTID:
+		return "WMI_TX_DESC_RING_CFG_DONE_EVENT";
+	case WMI_RX_DESC_RING_CFG_DONE_EVENTID:
+		return "WMI_RX_DESC_RING_CFG_DONE_EVENT";
+	case WMI_CFG_DEF_RX_OFFLOAD_DONE_EVENTID:
+		return "WMI_CFG_DEF_RX_OFFLOAD_DONE_EVENT";
+	case WMI_LINK_STATS_CONFIG_DONE_EVENTID:
+		return "WMI_LINK_STATS_CONFIG_DONE_EVENT";
+	case WMI_LINK_STATS_EVENTID:
+		return "WMI_LINK_STATS_EVENT";
 	default:
 		return "Untracked EVENT";
 	}
@@ -906,7 +993,7 @@ static void wmi_evt_connect(struct wil6210_vif *vif, int id, void *d, int len)
 	wil->sta[evt->cid].mid = vif->mid;
 	wil->sta[evt->cid].status = wil_sta_conn_pending;
 
-	rc = wil_tx_init(vif, evt->cid);
+	rc = wil_ring_init_tx(vif, evt->cid);
 	if (rc) {
 		wil_err(wil, "config tx vring failed for CID %d, rc (%d)\n",
 			evt->cid, rc);
@@ -1063,16 +1150,16 @@ static void wmi_evt_eapol_rx(struct wil6210_vif *vif, int id, void *d, int len)
 	}
 }
 
-static void wmi_evt_vring_en(struct wil6210_vif *vif, int id, void *d, int len)
+static void wmi_evt_ring_en(struct wil6210_vif *vif, int id, void *d, int len)
 {
 	struct wil6210_priv *wil = vif_to_wil(vif);
-	struct wmi_vring_en_event *evt = d;
-	u8 vri = evt->vring_index;
+	struct wmi_ring_en_event *evt = d;
+	u8 vri = evt->ring_index;
 	struct wireless_dev *wdev = vif_to_wdev(vif);
 
 	wil_dbg_wmi(wil, "Enable vring %d MID %d\n", vri, vif->mid);
 
-	if (vri >= ARRAY_SIZE(wil->vring_tx)) {
+	if (vri >= ARRAY_SIZE(wil->ring_tx)) {
 		wil_err(wil, "Enable for invalid vring %d\n", vri);
 		return;
 	}
@@ -1081,8 +1168,8 @@ static void wmi_evt_vring_en(struct wil6210_vif *vif, int id, void *d, int len)
 		/* in AP mode with disable_ap_sme, this is done by
 		 * wil_cfg80211_change_station()
 		 */
-		wil->vring_tx_data[vri].dot1x_open = true;
-	if (vri == vif->bcast_vring) /* no BA for bcast */
+		wil->ring_tx_data[vri].dot1x_open = true;
+	if (vri == vif->bcast_ring) /* no BA for bcast */
 		return;
 	if (agg_wsize >= 0)
 		wil_addba_tx_request(wil, vri, agg_wsize);
@@ -1093,7 +1180,7 @@ static void wmi_evt_ba_status(struct wil6210_vif *vif, int id,
 {
 	struct wil6210_priv *wil = vif_to_wil(vif);
 	struct wmi_ba_status_event *evt = d;
-	struct vring_tx_data *txdata;
+	struct wil_ring_tx_data *txdata;
 
 	wil_dbg_wmi(wil, "BACK[%d] %s {%d} timeout %d AMSDU%s\n",
 		    evt->ringid,
@@ -1112,7 +1199,7 @@ static void wmi_evt_ba_status(struct wil6210_vif *vif, int id,
 		evt->amsdu = 0;
 	}
 
-	txdata = &wil->vring_tx_data[evt->ringid];
+	txdata = &wil->ring_tx_data[evt->ringid];
 
 	txdata->agg_timeout = le16_to_cpu(evt->ba_timeout);
 	txdata->agg_wsize = evt->agg_wsize;
@@ -1150,11 +1237,11 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 	if (!evt->from_initiator) {
 		int i;
 		/* find Tx vring it belongs to */
-		for (i = 0; i < ARRAY_SIZE(wil->vring2cid_tid); i++) {
-			if ((wil->vring2cid_tid[i][0] == cid) &&
-			    (wil->vring2cid_tid[i][1] == tid)) {
-				struct vring_tx_data *txdata =
-					&wil->vring_tx_data[i];
+		for (i = 0; i < ARRAY_SIZE(wil->ring2cid_tid); i++) {
+			if (wil->ring2cid_tid[i][0] == cid &&
+			    wil->ring2cid_tid[i][1] == tid) {
+				struct wil_ring_tx_data *txdata =
+					&wil->ring_tx_data[i];
 
 				wil_dbg_wmi(wil, "DELBA Tx vring %d\n", i);
 				txdata->agg_timeout = 0;
@@ -1164,7 +1251,7 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 				break; /* max. 1 matching ring */
 			}
 		}
-		if (i >= ARRAY_SIZE(wil->vring2cid_tid))
+		if (i >= ARRAY_SIZE(wil->ring2cid_tid))
 			wil_err(wil, "DELBA: unable to find Tx vring\n");
 		return;
 	}
@@ -1250,6 +1337,130 @@ wmi_evt_sched_scan_result(struct wil6210_vif *vif, int id, void *d, int len)
 	cfg80211_sched_scan_results(wiphy, 0);
 }
 
+static void wil_link_stats_store_basic(struct wil6210_vif *vif,
+				       struct wmi_link_stats_basic *basic)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	u8 cid = basic->cid;
+	struct wil_sta_info *sta;
+
+	if (cid < 0 || cid >= WIL6210_MAX_CID) {
+		wil_err(wil, "invalid cid %d\n", cid);
+		return;
+	}
+
+	sta = &wil->sta[cid];
+	sta->fw_stats_basic = *basic;
+}
+
+static void wil_link_stats_store_global(struct wil6210_vif *vif,
+					struct wmi_link_stats_global *global)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+
+	wil->fw_stats_global.stats = *global;
+}
+
+static void wmi_link_stats_parse(struct wil6210_vif *vif, u64 tsf,
+				 bool has_next, void *payload,
+				 size_t payload_size)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	size_t hdr_size = sizeof(struct wmi_link_stats_record);
+	size_t stats_size, record_size, expected_size;
+	struct wmi_link_stats_record *hdr;
+
+	if (payload_size < hdr_size) {
+		wil_err(wil, "link stats wrong event size %zu\n", payload_size);
+		return;
+	}
+
+	while (payload_size >= hdr_size) {
+		hdr = payload;
+		stats_size = le16_to_cpu(hdr->record_size);
+		record_size = hdr_size + stats_size;
+
+		if (payload_size < record_size) {
+			wil_err(wil, "link stats payload ended unexpectedly, size %zu < %zu\n",
+				payload_size, record_size);
+			return;
+		}
+
+		switch (hdr->record_type_id) {
+		case WMI_LINK_STATS_TYPE_BASIC:
+			expected_size = sizeof(struct wmi_link_stats_basic);
+			if (stats_size < expected_size) {
+				wil_err(wil, "link stats invalid basic record size %zu < %zu\n",
+					stats_size, expected_size);
+				return;
+			}
+			if (vif->fw_stats_ready) {
+				/* clean old statistics */
+				vif->fw_stats_tsf = 0;
+				vif->fw_stats_ready = 0;
+			}
+
+			wil_link_stats_store_basic(vif, payload + hdr_size);
+
+			if (!has_next) {
+				vif->fw_stats_tsf = tsf;
+				vif->fw_stats_ready = 1;
+			}
+
+			break;
+		case WMI_LINK_STATS_TYPE_GLOBAL:
+			expected_size = sizeof(struct wmi_link_stats_global);
+			if (stats_size < sizeof(struct wmi_link_stats_global)) {
+				wil_err(wil, "link stats invalid global record size %zu < %zu\n",
+					stats_size, expected_size);
+				return;
+			}
+
+			if (wil->fw_stats_global.ready) {
+				/* clean old statistics */
+				wil->fw_stats_global.tsf = 0;
+				wil->fw_stats_global.ready = 0;
+			}
+
+			wil_link_stats_store_global(vif, payload + hdr_size);
+
+			if (!has_next) {
+				wil->fw_stats_global.tsf = tsf;
+				wil->fw_stats_global.ready = 1;
+			}
+
+			break;
+		default:
+			break;
+		}
+
+		/* skip to next record */
+		payload += record_size;
+		payload_size -= record_size;
+	}
+}
+
+static void
+wmi_evt_link_stats(struct wil6210_vif *vif, int id, void *d, int len)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	struct wmi_link_stats_event *evt = d;
+	size_t payload_size;
+
+	if (len < offsetof(struct wmi_link_stats_event, payload)) {
+		wil_err(wil, "stats event way too short %d\n", len);
+		return;
+	}
+	payload_size = le16_to_cpu(evt->payload_size);
+	if (len < sizeof(struct wmi_link_stats_event) + payload_size) {
+		wil_err(wil, "stats event too short %d\n", len);
+		return;
+	}
+
+	wmi_link_stats_parse(vif, le64_to_cpu(evt->tsf), evt->has_next,
+			     evt->payload, payload_size);
+}
+
 /**
  * Some events are ignored for purpose; and need not be interpreted as
  * "unhandled events"
@@ -1277,9 +1488,10 @@ static const struct {
 	{WMI_BA_STATUS_EVENTID,		wmi_evt_ba_status},
 	{WMI_RCP_ADDBA_REQ_EVENTID,	wmi_evt_addba_rx_req},
 	{WMI_DELBA_EVENTID,		wmi_evt_delba},
-	{WMI_VRING_EN_EVENTID,		wmi_evt_vring_en},
+	{WMI_RING_EN_EVENTID,		wmi_evt_ring_en},
 	{WMI_DATA_PORT_OPEN_EVENTID,		wmi_evt_ignore},
 	{WMI_SCHED_SCAN_RESULT_EVENTID,		wmi_evt_sched_scan_result},
+	{WMI_LINK_STATS_EVENTID,		wmi_evt_link_stats},
 };
 
 /*
@@ -1909,7 +2121,7 @@ int wmi_rxon(struct wil6210_priv *wil, bool on)
 	return rc;
 }
 
-int wmi_rx_chain_add(struct wil6210_priv *wil, struct vring *vring)
+int wmi_rx_chain_add(struct wil6210_priv *wil, struct wil_ring *vring)
 {
 	struct net_device *ndev = wil->main_ndev;
 	struct wireless_dev *wdev = ndev->ieee80211_ptr;
@@ -2063,29 +2275,32 @@ int wmi_disconnect_sta(struct wil6210_vif *vif, const u8 *mac,
 int wmi_addba(struct wil6210_priv *wil, u8 mid,
 	      u8 ringid, u8 size, u16 timeout)
 {
-	struct wmi_vring_ba_en_cmd cmd = {
-		.ringid = ringid,
+	u8 amsdu = wil->use_enhanced_dma_hw && wil->use_rx_hw_reordering &&
+		test_bit(WMI_FW_CAPABILITY_AMSDU, wil->fw_capabilities) &&
+		wil->amsdu_en;
+	struct wmi_ring_ba_en_cmd cmd = {
+		.ring_id = ringid,
 		.agg_max_wsize = size,
 		.ba_timeout = cpu_to_le16(timeout),
-		.amsdu = 0,
+		.amsdu = amsdu,
 	};
 
-	wil_dbg_wmi(wil, "addba: (ring %d size %d timeout %d)\n", ringid, size,
-		    timeout);
+	wil_dbg_wmi(wil, "addba: (ring %d size %d timeout %d amsdu %d)\n",
+		    ringid, size, timeout, amsdu);
 
-	return wmi_send(wil, WMI_VRING_BA_EN_CMDID, mid, &cmd, sizeof(cmd));
+	return wmi_send(wil, WMI_RING_BA_EN_CMDID, mid, &cmd, sizeof(cmd));
 }
 
 int wmi_delba_tx(struct wil6210_priv *wil, u8 mid, u8 ringid, u16 reason)
 {
-	struct wmi_vring_ba_dis_cmd cmd = {
-		.ringid = ringid,
+	struct wmi_ring_ba_dis_cmd cmd = {
+		.ring_id = ringid,
 		.reason = cpu_to_le16(reason),
 	};
 
 	wil_dbg_wmi(wil, "delba_tx: (ring %d reason %d)\n", ringid, reason);
 
-	return wmi_send(wil, WMI_VRING_BA_DIS_CMDID, mid, &cmd, sizeof(cmd));
+	return wmi_send(wil, WMI_RING_BA_DIS_CMDID, mid, &cmd, sizeof(cmd));
 }
 
 int wmi_delba_rx(struct wil6210_priv *wil, u8 mid, u8 cidxtid, u16 reason)
@@ -2146,6 +2361,54 @@ int wmi_addba_rx_resp(struct wil6210_priv *wil,
 	return rc;
 }
 
+int wmi_addba_rx_resp_edma(struct wil6210_priv *wil, u8 mid, u8 cid, u8 tid,
+			   u8 token, u16 status, bool amsdu, u16 agg_wsize,
+			   u16 timeout)
+{
+	int rc;
+	struct wmi_rcp_addba_resp_edma_cmd cmd = {
+		.cid = cid,
+		.tid = tid,
+		.dialog_token = token,
+		.status_code = cpu_to_le16(status),
+		/* bit 0: A-MSDU supported
+		 * bit 1: policy (should be 0 for us)
+		 * bits 2..5: TID
+		 * bits 6..15: buffer size
+		 */
+		.ba_param_set = cpu_to_le16((amsdu ? 1 : 0) | (tid << 2) |
+					    (agg_wsize << 6)),
+		.ba_timeout = cpu_to_le16(timeout),
+		/* route all the connections to status ring 0 */
+		.status_ring_id = WIL_DEFAULT_RX_STATUS_RING_ID,
+	};
+	struct {
+		struct wmi_cmd_hdr wmi;
+		struct wmi_rcp_addba_resp_sent_event evt;
+	} __packed reply = {
+		.evt = {.status = cpu_to_le16(WMI_FW_STATUS_FAILURE)},
+	};
+
+	wil_dbg_wmi(wil,
+		    "ADDBA response for CID %d TID %d size %d timeout %d status %d AMSDU%s, sring_id %d\n",
+		    cid, tid, agg_wsize, timeout, status, amsdu ? "+" : "-",
+		    WIL_DEFAULT_RX_STATUS_RING_ID);
+
+	rc = wmi_call(wil, WMI_RCP_ADDBA_RESP_EDMA_CMDID, mid, &cmd,
+		      sizeof(cmd), WMI_RCP_ADDBA_RESP_SENT_EVENTID, &reply,
+		      sizeof(reply), WIL_WMI_CALL_GENERAL_TO_MS);
+	if (rc)
+		return rc;
+
+	if (reply.evt.status) {
+		wil_err(wil, "ADDBA response failed with status %d\n",
+			le16_to_cpu(reply.evt.status));
+		rc = -EINVAL;
+	}
+
+	return rc;
+}
+
 int wmi_ps_dev_profile_cfg(struct wil6210_priv *wil,
 			   enum wmi_ps_profile_type ps_profile)
 {
@@ -2852,3 +3115,351 @@ int wmi_mgmt_tx(struct wil6210_vif *vif, const u8 *buf, size_t len)
 
 	return rc;
 }
+
+int wmi_mgmt_tx_ext(struct wil6210_vif *vif, const u8 *buf, size_t len,
+		    u8 channel, u16 duration_ms)
+{
+	size_t total;
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	struct ieee80211_mgmt *mgmt_frame = (void *)buf;
+	struct wmi_sw_tx_req_ext_cmd *cmd;
+	struct {
+		struct wmi_cmd_hdr wmi;
+		struct wmi_sw_tx_complete_event evt;
+	} __packed evt = {
+		.evt = {.status = WMI_FW_STATUS_FAILURE},
+	};
+	int rc;
+
+	wil_dbg_wmi(wil, "mgmt_tx_ext mid %d channel %d duration %d\n",
+		    vif->mid, channel, duration_ms);
+	wil_hex_dump_wmi("mgmt_tx_ext frame ", DUMP_PREFIX_OFFSET, 16, 1, buf,
+			 len, true);
+
+	if (len < sizeof(struct ieee80211_hdr_3addr)) {
+		wil_err(wil, "short frame. len %zu\n", len);
+		return -EINVAL;
+	}
+
+	total = sizeof(*cmd) + len;
+	if (total < len) {
+		wil_err(wil, "mgmt_tx_ext invalid len %zu\n", len);
+		return -EINVAL;
+	}
+
+	cmd = kzalloc(total, GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	memcpy(cmd->dst_mac, mgmt_frame->da, WMI_MAC_LEN);
+	cmd->len = cpu_to_le16(len);
+	memcpy(cmd->payload, buf, len);
+	cmd->channel = channel - 1;
+	cmd->duration_ms = cpu_to_le16(duration_ms);
+
+	rc = wmi_call(wil, WMI_SW_TX_REQ_EXT_CMDID, vif->mid, cmd, total,
+		      WMI_SW_TX_COMPLETE_EVENTID, &evt, sizeof(evt), 2000);
+	if (!rc && evt.evt.status != WMI_FW_STATUS_SUCCESS) {
+		wil_err(wil, "mgmt_tx_ext failed with status %d\n",
+			evt.evt.status);
+		rc = -EINVAL;
+	}
+
+	kfree(cmd);
+
+	return rc;
+}
+
+int wil_wmi_tx_sring_cfg(struct wil6210_priv *wil, int ring_id)
+{
+	int rc;
+	struct wil6210_vif *vif = ndev_to_vif(wil->main_ndev);
+	struct wil_status_ring *sring = &wil->srings[ring_id];
+	struct wmi_tx_status_ring_add_cmd cmd = {
+		.ring_cfg = {
+			.ring_size = cpu_to_le16(sring->size),
+		},
+		.irq_index = WIL_TX_STATUS_IRQ_IDX
+	};
+	struct {
+		struct wmi_cmd_hdr hdr;
+		struct wmi_tx_status_ring_cfg_done_event evt;
+	} __packed reply = {
+		.evt = {.status = WMI_FW_STATUS_FAILURE},
+	};
+
+	cmd.ring_cfg.ring_id = ring_id;
+
+	cmd.ring_cfg.ring_mem_base = cpu_to_le64(sring->pa);
+	rc = wmi_call(wil, WMI_TX_STATUS_RING_ADD_CMDID, vif->mid, &cmd,
+		      sizeof(cmd), WMI_TX_STATUS_RING_CFG_DONE_EVENTID,
+		      &reply, sizeof(reply), WIL_WMI_CALL_GENERAL_TO_MS);
+	if (rc) {
+		wil_err(wil, "TX_STATUS_RING_ADD_CMD failed, rc %d\n", rc);
+		return rc;
+	}
+
+	if (reply.evt.status != WMI_FW_STATUS_SUCCESS) {
+		wil_err(wil, "TX_STATUS_RING_ADD_CMD failed, status %d\n",
+			reply.evt.status);
+		return -EINVAL;
+	}
+
+	sring->hwtail = le32_to_cpu(reply.evt.ring_tail_ptr);
+
+	return 0;
+}
+
+int wil_wmi_cfg_def_rx_offload(struct wil6210_priv *wil, u16 max_rx_pl_per_desc)
+{
+	struct net_device *ndev = wil->main_ndev;
+	struct wil6210_vif *vif = ndev_to_vif(ndev);
+	int rc;
+	struct wmi_cfg_def_rx_offload_cmd cmd = {
+		.max_msdu_size = cpu_to_le16(wil_mtu2macbuf(WIL_MAX_ETH_MTU)),
+		.max_rx_pl_per_desc = cpu_to_le16(max_rx_pl_per_desc),
+		.decap_trans_type = WMI_DECAP_TYPE_802_3,
+		.l2_802_3_offload_ctrl = 0,
+		.l3_l4_ctrl = 1 << L3_L4_CTRL_TCPIP_CHECKSUM_EN_POS,
+	};
+	struct {
+		struct wmi_cmd_hdr hdr;
+		struct wmi_cfg_def_rx_offload_done_event evt;
+	} __packed reply = {
+		.evt = {.status = WMI_FW_STATUS_FAILURE},
+	};
+
+	rc = wmi_call(wil, WMI_CFG_DEF_RX_OFFLOAD_CMDID, vif->mid, &cmd,
+		      sizeof(cmd), WMI_CFG_DEF_RX_OFFLOAD_DONE_EVENTID, &reply,
+		      sizeof(reply), WIL_WMI_CALL_GENERAL_TO_MS);
+	if (rc) {
+		wil_err(wil, "WMI_CFG_DEF_RX_OFFLOAD_CMD failed, rc %d\n", rc);
+		return rc;
+	}
+
+	if (reply.evt.status != WMI_FW_STATUS_SUCCESS) {
+		wil_err(wil, "WMI_CFG_DEF_RX_OFFLOAD_CMD failed, status %d\n",
+			reply.evt.status);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int wil_wmi_rx_sring_add(struct wil6210_priv *wil, u16 ring_id)
+{
+	struct net_device *ndev = wil->main_ndev;
+	struct wil6210_vif *vif = ndev_to_vif(ndev);
+	struct wil_status_ring *sring = &wil->srings[ring_id];
+	int rc;
+	struct wmi_rx_status_ring_add_cmd cmd = {
+		.ring_cfg = {
+			.ring_size = cpu_to_le16(sring->size),
+			.ring_id = ring_id,
+		},
+		.rx_msg_type = wil->use_compressed_rx_status ?
+			WMI_RX_MSG_TYPE_COMPRESSED :
+			WMI_RX_MSG_TYPE_EXTENDED,
+		.irq_index = WIL_RX_STATUS_IRQ_IDX,
+	};
+	struct {
+		struct wmi_cmd_hdr hdr;
+		struct wmi_rx_status_ring_cfg_done_event evt;
+	} __packed reply = {
+		.evt = {.status = WMI_FW_STATUS_FAILURE},
+	};
+
+	cmd.ring_cfg.ring_mem_base = cpu_to_le64(sring->pa);
+	rc = wmi_call(wil, WMI_RX_STATUS_RING_ADD_CMDID, vif->mid, &cmd,
+		      sizeof(cmd), WMI_RX_STATUS_RING_CFG_DONE_EVENTID, &reply,
+		      sizeof(reply), WIL_WMI_CALL_GENERAL_TO_MS);
+	if (rc) {
+		wil_err(wil, "RX_STATUS_RING_ADD_CMD failed, rc %d\n", rc);
+		return rc;
+	}
+
+	if (reply.evt.status != WMI_FW_STATUS_SUCCESS) {
+		wil_err(wil, "RX_STATUS_RING_ADD_CMD failed, status %d\n",
+			reply.evt.status);
+		return -EINVAL;
+	}
+
+	sring->hwtail = le32_to_cpu(reply.evt.ring_tail_ptr);
+
+	return 0;
+}
+
+int wil_wmi_rx_desc_ring_add(struct wil6210_priv *wil, int status_ring_id)
+{
+	struct net_device *ndev = wil->main_ndev;
+	struct wil6210_vif *vif = ndev_to_vif(ndev);
+	struct wil_ring *ring = &wil->ring_rx;
+	int rc;
+	struct wmi_rx_desc_ring_add_cmd cmd = {
+		.ring_cfg = {
+			.ring_size = cpu_to_le16(ring->size),
+			.ring_id = WIL_RX_DESC_RING_ID,
+		},
+		.status_ring_id = status_ring_id,
+		.irq_index = WIL_RX_STATUS_IRQ_IDX,
+	};
+	struct {
+		struct wmi_cmd_hdr hdr;
+		struct wmi_rx_desc_ring_cfg_done_event evt;
+	} __packed reply = {
+		.evt = {.status = WMI_FW_STATUS_FAILURE},
+	};
+
+	cmd.ring_cfg.ring_mem_base = cpu_to_le64(ring->pa);
+	cmd.sw_tail_host_addr = cpu_to_le64(ring->edma_rx_swtail.pa);
+	rc = wmi_call(wil, WMI_RX_DESC_RING_ADD_CMDID, vif->mid, &cmd,
+		      sizeof(cmd), WMI_RX_DESC_RING_CFG_DONE_EVENTID, &reply,
+		      sizeof(reply), WIL_WMI_CALL_GENERAL_TO_MS);
+	if (rc) {
+		wil_err(wil, "WMI_RX_DESC_RING_ADD_CMD failed, rc %d\n", rc);
+		return rc;
+	}
+
+	if (reply.evt.status != WMI_FW_STATUS_SUCCESS) {
+		wil_err(wil, "WMI_RX_DESC_RING_ADD_CMD failed, status %d\n",
+			reply.evt.status);
+		return -EINVAL;
+	}
+
+	ring->hwtail = le32_to_cpu(reply.evt.ring_tail_ptr);
+
+	return 0;
+}
+
+int wil_wmi_tx_desc_ring_add(struct wil6210_vif *vif, int ring_id, int cid,
+			     int tid)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	int sring_id = wil->tx_sring_idx; /* there is only one TX sring */
+	int rc;
+	struct wil_ring *ring = &wil->ring_tx[ring_id];
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[ring_id];
+	struct wmi_tx_desc_ring_add_cmd cmd = {
+		.ring_cfg = {
+			.ring_size = cpu_to_le16(ring->size),
+			.ring_id = ring_id,
+		},
+		.status_ring_id = sring_id,
+		.cid = cid,
+		.tid = tid,
+		.encap_trans_type = WMI_VRING_ENC_TYPE_802_3,
+		.max_msdu_size = cpu_to_le16(wil_mtu2macbuf(mtu_max)),
+		.schd_params = {
+			.priority = cpu_to_le16(0),
+			.timeslot_us = cpu_to_le16(0xfff),
+		}
+	};
+	struct {
+		struct wmi_cmd_hdr hdr;
+		struct wmi_tx_desc_ring_cfg_done_event evt;
+	} __packed reply = {
+		.evt = {.status = WMI_FW_STATUS_FAILURE},
+	};
+
+	cmd.ring_cfg.ring_mem_base = cpu_to_le64(ring->pa);
+	rc = wmi_call(wil, WMI_TX_DESC_RING_ADD_CMDID, vif->mid, &cmd,
+		      sizeof(cmd), WMI_TX_DESC_RING_CFG_DONE_EVENTID, &reply,
+		      sizeof(reply), WIL_WMI_CALL_GENERAL_TO_MS);
+	if (rc) {
+		wil_err(wil, "WMI_TX_DESC_RING_ADD_CMD failed, rc %d\n", rc);
+		return rc;
+	}
+
+	if (reply.evt.status != WMI_FW_STATUS_SUCCESS) {
+		wil_err(wil, "WMI_TX_DESC_RING_ADD_CMD failed, status %d\n",
+			reply.evt.status);
+		return -EINVAL;
+	}
+
+	spin_lock_bh(&txdata->lock);
+	ring->hwtail = le32_to_cpu(reply.evt.ring_tail_ptr);
+	txdata->mid = vif->mid;
+	txdata->enabled = 1;
+	spin_unlock_bh(&txdata->lock);
+
+	return 0;
+}
+
+int wil_wmi_bcast_desc_ring_add(struct wil6210_vif *vif, int ring_id)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	struct wil_ring *ring = &wil->ring_tx[ring_id];
+	int rc;
+	struct wmi_bcast_desc_ring_add_cmd cmd = {
+		.ring_cfg = {
+			.ring_size = cpu_to_le16(ring->size),
+			.ring_id = ring_id,
+		},
+		.status_ring_id = wil->tx_sring_idx,
+		.encap_trans_type = WMI_VRING_ENC_TYPE_802_3,
+	};
+	struct {
+		struct wmi_cmd_hdr hdr;
+		struct wmi_rx_desc_ring_cfg_done_event evt;
+	} __packed reply = {
+		.evt = {.status = WMI_FW_STATUS_FAILURE},
+	};
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[ring_id];
+
+	cmd.ring_cfg.ring_mem_base = cpu_to_le64(ring->pa);
+	rc = wmi_call(wil, WMI_BCAST_DESC_RING_ADD_CMDID, vif->mid, &cmd,
+		      sizeof(cmd), WMI_TX_DESC_RING_CFG_DONE_EVENTID, &reply,
+		      sizeof(reply), WIL_WMI_CALL_GENERAL_TO_MS);
+	if (rc) {
+		wil_err(wil, "WMI_BCAST_DESC_RING_ADD_CMD failed, rc %d\n", rc);
+		return rc;
+	}
+
+	if (reply.evt.status != WMI_FW_STATUS_SUCCESS) {
+		wil_err(wil, "Broadcast Tx config failed, status %d\n",
+			reply.evt.status);
+		return -EINVAL;
+	}
+
+	spin_lock_bh(&txdata->lock);
+	ring->hwtail = le32_to_cpu(reply.evt.ring_tail_ptr);
+	txdata->mid = vif->mid;
+	txdata->enabled = 1;
+	spin_unlock_bh(&txdata->lock);
+
+	return 0;
+}
+
+int wmi_link_stats_cfg(struct wil6210_vif *vif, u32 type, u8 cid, u32 interval)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	struct wmi_link_stats_cmd cmd = {
+		.record_type_mask = cpu_to_le32(type),
+		.cid = cid,
+		.action = WMI_LINK_STATS_SNAPSHOT,
+		.interval_msec = cpu_to_le32(interval),
+	};
+	struct {
+		struct wmi_cmd_hdr wmi;
+		struct wmi_link_stats_config_done_event evt;
+	} __packed reply = {
+		.evt = {.status = WMI_FW_STATUS_FAILURE},
+	};
+	int rc;
+
+	rc = wmi_call(wil, WMI_LINK_STATS_CMDID, vif->mid, &cmd, sizeof(cmd),
+		      WMI_LINK_STATS_CONFIG_DONE_EVENTID, &reply,
+		      sizeof(reply), WIL_WMI_CALL_GENERAL_TO_MS);
+	if (rc) {
+		wil_err(wil, "WMI_LINK_STATS_CMDID failed, rc %d\n", rc);
+		return rc;
+	}
+
+	if (reply.evt.status != WMI_FW_STATUS_SUCCESS) {
+		wil_err(wil, "Link statistics config failed, status %d\n",
+			reply.evt.status);
+		return -EINVAL;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/wireless/ath/wil6210/wmi.h b/drivers/net/wireless/ath/wil6210/wmi.h
index dc503d903786..139acb2caf92 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.h
+++ b/drivers/net/wireless/ath/wil6210/wmi.h
@@ -53,6 +53,17 @@
  * must always be kept equal to (WMI_RF_RX2TX_LENGTH+1)
  */
 #define WMI_RF_RX2TX_CONF_LENGTH	(4)
+/* Qos configuration */
+#define WMI_QOS_NUM_OF_PRIORITY		(4)
+#define WMI_QOS_MIN_DEFAULT_WEIGHT	(10)
+#define WMI_QOS_VRING_SLOT_MIN_MS	(2)
+#define WMI_QOS_VRING_SLOT_MAX_MS	(10)
+/* (WMI_QOS_MIN_DEFAULT_WEIGHT * WMI_QOS_VRING_SLOT_MAX_MS /
+ * WMI_QOS_VRING_SLOT_MIN_MS)
+ */
+#define WMI_QOS_MAX_WEIGHT		50
+#define WMI_QOS_SET_VIF_PRIORITY	(0xFF)
+#define WMI_QOS_DEFAULT_PRIORITY	(WMI_QOS_NUM_OF_PRIORITY)
 
 /* Mailbox interface
  * used for commands and events
@@ -86,6 +97,12 @@ enum wmi_fw_capability {
 	WMI_FW_CAPABILITY_PNO				= 15,
 	WMI_FW_CAPABILITY_REF_CLOCK_CONTROL		= 18,
 	WMI_FW_CAPABILITY_AP_SME_OFFLOAD_NONE		= 19,
+	WMI_FW_CAPABILITY_MULTI_VIFS			= 20,
+	WMI_FW_CAPABILITY_FT_ROAMING			= 21,
+	WMI_FW_CAPABILITY_BACK_WIN_SIZE_64		= 22,
+	WMI_FW_CAPABILITY_AMSDU				= 23,
+	WMI_FW_CAPABILITY_RAW_MODE			= 24,
+	WMI_FW_CAPABILITY_TX_REQ_EXT			= 25,
 	WMI_FW_CAPABILITY_MAX,
 };
 
@@ -109,6 +126,9 @@ enum wmi_command_id {
 	WMI_SET_PROBED_SSID_CMDID			= 0x0A,
 	/* deprecated */
 	WMI_SET_LISTEN_INT_CMDID			= 0x0B,
+	WMI_FT_AUTH_CMDID				= 0x0C,
+	WMI_FT_REASSOC_CMDID				= 0x0D,
+	WMI_UPDATE_FT_IES_CMDID				= 0x0E,
 	WMI_BCON_CTRL_CMDID				= 0x0F,
 	WMI_ADD_CIPHER_KEY_CMDID			= 0x16,
 	WMI_DELETE_CIPHER_KEY_CMDID			= 0x17,
@@ -117,6 +137,12 @@ enum wmi_command_id {
 	WMI_SET_WSC_STATUS_CMDID			= 0x41,
 	WMI_PXMT_RANGE_CFG_CMDID			= 0x42,
 	WMI_PXMT_SNR2_RANGE_CFG_CMDID			= 0x43,
+	WMI_RADAR_GENERAL_CONFIG_CMDID			= 0x100,
+	WMI_RADAR_CONFIG_SELECT_CMDID			= 0x101,
+	WMI_RADAR_PARAMS_CONFIG_CMDID			= 0x102,
+	WMI_RADAR_SET_MODE_CMDID			= 0x103,
+	WMI_RADAR_CONTROL_CMDID				= 0x104,
+	WMI_RADAR_PCI_CONTROL_CMDID			= 0x105,
 	WMI_MEM_READ_CMDID				= 0x800,
 	WMI_MEM_WR_CMDID				= 0x801,
 	WMI_ECHO_CMDID					= 0x803,
@@ -148,8 +174,8 @@ enum wmi_command_id {
 	WMI_CFG_RX_CHAIN_CMDID				= 0x820,
 	WMI_VRING_CFG_CMDID				= 0x821,
 	WMI_BCAST_VRING_CFG_CMDID			= 0x822,
-	WMI_VRING_BA_EN_CMDID				= 0x823,
-	WMI_VRING_BA_DIS_CMDID				= 0x824,
+	WMI_RING_BA_EN_CMDID				= 0x823,
+	WMI_RING_BA_DIS_CMDID				= 0x824,
 	WMI_RCP_ADDBA_RESP_CMDID			= 0x825,
 	WMI_RCP_DELBA_CMDID				= 0x826,
 	WMI_SET_SSID_CMDID				= 0x827,
@@ -157,12 +183,17 @@ enum wmi_command_id {
 	WMI_SET_PCP_CHANNEL_CMDID			= 0x829,
 	WMI_GET_PCP_CHANNEL_CMDID			= 0x82A,
 	WMI_SW_TX_REQ_CMDID				= 0x82B,
+	/* Event is shared between WMI_SW_TX_REQ_CMDID and
+	 * WMI_SW_TX_REQ_EXT_CMDID
+	 */
+	WMI_SW_TX_REQ_EXT_CMDID				= 0x82C,
 	WMI_MLME_PUSH_CMDID				= 0x835,
 	WMI_BEAMFORMING_MGMT_CMDID			= 0x836,
 	WMI_BF_TXSS_MGMT_CMDID				= 0x837,
 	WMI_BF_SM_MGMT_CMDID				= 0x838,
 	WMI_BF_RXSS_MGMT_CMDID				= 0x839,
 	WMI_BF_TRIG_CMDID				= 0x83A,
+	WMI_RCP_ADDBA_RESP_EDMA_CMDID			= 0x83B,
 	WMI_LINK_MAINTAIN_CFG_WRITE_CMDID		= 0x842,
 	WMI_LINK_MAINTAIN_CFG_READ_CMDID		= 0x843,
 	WMI_SET_SECTORS_CMDID				= 0x849,
@@ -205,7 +236,12 @@ enum wmi_command_id {
 	WMI_GET_PCP_FACTOR_CMDID			= 0x91B,
 	/* Power Save Configuration Commands */
 	WMI_PS_DEV_PROFILE_CFG_CMDID			= 0x91C,
+	WMI_RS_ENABLE_CMDID				= 0x91E,
+	WMI_RS_CFG_EX_CMDID				= 0x91F,
+	WMI_GET_DETAILED_RS_RES_EX_CMDID		= 0x920,
+	/* deprecated */
 	WMI_RS_CFG_CMDID				= 0x921,
+	/* deprecated */
 	WMI_GET_DETAILED_RS_RES_CMDID			= 0x922,
 	WMI_AOA_MEAS_CMDID				= 0x923,
 	WMI_BRP_SET_ANT_LIMIT_CMDID			= 0x924,
@@ -234,7 +270,15 @@ enum wmi_command_id {
 	WMI_PRIO_TX_SECTORS_ORDER_CMDID			= 0x9A5,
 	WMI_PRIO_TX_SECTORS_NUMBER_CMDID		= 0x9A6,
 	WMI_PRIO_TX_SECTORS_SET_DEFAULT_CFG_CMDID	= 0x9A7,
+	/* deprecated */
 	WMI_BF_CONTROL_CMDID				= 0x9AA,
+	WMI_BF_CONTROL_EX_CMDID				= 0x9AB,
+	WMI_TX_STATUS_RING_ADD_CMDID			= 0x9C0,
+	WMI_RX_STATUS_RING_ADD_CMDID			= 0x9C1,
+	WMI_TX_DESC_RING_ADD_CMDID			= 0x9C2,
+	WMI_RX_DESC_RING_ADD_CMDID			= 0x9C3,
+	WMI_BCAST_DESC_RING_ADD_CMDID			= 0x9C4,
+	WMI_CFG_DEF_RX_OFFLOAD_CMDID			= 0x9C5,
 	WMI_SCHEDULING_SCHEME_CMDID			= 0xA01,
 	WMI_FIXED_SCHEDULING_CONFIG_CMDID		= 0xA02,
 	WMI_ENABLE_FIXED_SCHEDULING_CMDID		= 0xA03,
@@ -244,6 +288,11 @@ enum wmi_command_id {
 	WMI_GET_CCA_INDICATIONS_CMDID			= 0xA07,
 	WMI_SET_CCA_INDICATIONS_BI_AVG_NUM_CMDID	= 0xA08,
 	WMI_INTERNAL_FW_IOCTL_CMDID			= 0xA0B,
+	WMI_LINK_STATS_CMDID				= 0xA0C,
+	WMI_SET_GRANT_MCS_CMDID				= 0xA0E,
+	WMI_SET_AP_SLOT_SIZE_CMDID			= 0xA0F,
+	WMI_SET_VRING_PRIORITY_WEIGHT_CMDID		= 0xA10,
+	WMI_SET_VRING_PRIORITY_CMDID			= 0xA11,
 	WMI_SET_MAC_ADDRESS_CMDID			= 0xF003,
 	WMI_ABORT_SCAN_CMDID				= 0xF007,
 	WMI_SET_PROMISCUOUS_MODE_CMDID			= 0xF041,
@@ -442,6 +491,30 @@ struct wmi_start_sched_scan_cmd {
 	struct wmi_sched_scan_plan scan_plans[WMI_MAX_PLANS_NUM];
 } __packed;
 
+/* WMI_FT_AUTH_CMDID */
+struct wmi_ft_auth_cmd {
+	u8 bssid[WMI_MAC_LEN];
+	/* enum wmi_channel */
+	u8 channel;
+	/* enum wmi_channel */
+	u8 edmg_channel;
+	u8 reserved[4];
+} __packed;
+
+/* WMI_FT_REASSOC_CMDID */
+struct wmi_ft_reassoc_cmd {
+	u8 bssid[WMI_MAC_LEN];
+	u8 reserved[2];
+} __packed;
+
+/* WMI_UPDATE_FT_IES_CMDID */
+struct wmi_update_ft_ies_cmd {
+	/* Length of the FT IEs */
+	__le16 ie_len;
+	u8 reserved[2];
+	u8 ie_info[0];
+} __packed;
+
 /* WMI_SET_PROBED_SSID_CMDID */
 #define MAX_PROBED_SSID_INDEX	(3)
 
@@ -498,6 +571,109 @@ struct wmi_pxmt_snr2_range_cfg_cmd {
 	s8 snr2range_arr[2];
 } __packed;
 
+/* WMI_RADAR_GENERAL_CONFIG_CMDID */
+struct wmi_radar_general_config_cmd {
+	/* Number of pulses (CIRs) in FW FIFO to initiate pulses transfer
+	 * from FW to Host
+	 */
+	__le32 fifo_watermark;
+	/* In unit of us, in the range [100, 1000000] */
+	__le32 t_burst;
+	/* Valid in the range [1, 32768], 0xFFFF means infinite */
+	__le32 n_bursts;
+	/* In unit of 330Mhz clk, in the range [4, 2000]*330 */
+	__le32 t_pulse;
+	/* In the range of [1,4096] */
+	__le16 n_pulses;
+	/* Number of taps after cTap per CIR */
+	__le16 n_samples;
+	/* Offset from the main tap (0 = zero-distance). In the range of [0,
+	 * 255]
+	 */
+	u8 first_sample_offset;
+	/* Number of Pulses to average, 1, 2, 4, 8 */
+	u8 pulses_to_avg;
+	/* Number of adjacent taps to average, 1, 2, 4, 8 */
+	u8 samples_to_avg;
+	/* The index to config general params */
+	u8 general_index;
+	u8 reserved[4];
+} __packed;
+
+/* WMI_RADAR_CONFIG_SELECT_CMDID */
+struct wmi_radar_config_select_cmd {
+	/* Select the general params index to use */
+	u8 general_index;
+	u8 reserved[3];
+	/* 0 means don't update burst_active_vector */
+	__le32 burst_active_vector;
+	/* 0 means don't update pulse_active_vector */
+	__le32 pulse_active_vector;
+} __packed;
+
+/* WMI_RADAR_PARAMS_CONFIG_CMDID */
+struct wmi_radar_params_config_cmd {
+	/* The burst index selected to config */
+	u8 burst_index;
+	/* 0-not active, 1-active */
+	u8 burst_en;
+	/* The pulse index selected to config */
+	u8 pulse_index;
+	/* 0-not active, 1-active */
+	u8 pulse_en;
+	/* TX RF to use on current pulse */
+	u8 tx_rfc_idx;
+	u8 tx_sector;
+	/* Offset from calibrated value.(expected to be 0)(value is row in
+	 * Gain-LUT, not dB)
+	 */
+	s8 tx_rf_gain_comp;
+	/* expected to be 0 */
+	s8 tx_bb_gain_comp;
+	/* RX RF to use on current pulse */
+	u8 rx_rfc_idx;
+	u8 rx_sector;
+	/* Offset from calibrated value.(expected to be 0)(value is row in
+	 * Gain-LUT, not dB)
+	 */
+	s8 rx_rf_gain_comp;
+	/* Value in dB.(expected to be 0) */
+	s8 rx_bb_gain_comp;
+	/* Offset from calibrated value.(expected to be 0) */
+	s8 rx_timing_offset;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_RADAR_SET_MODE_CMDID */
+struct wmi_radar_set_mode_cmd {
+	/* 0-disable/1-enable */
+	u8 enable;
+	/* enum wmi_channel */
+	u8 channel;
+	/* In the range of [0,7], 0xff means use default */
+	u8 tx_rfc_idx;
+	/* In the range of [0,7], 0xff means use default */
+	u8 rx_rfc_idx;
+} __packed;
+
+/* WMI_RADAR_CONTROL_CMDID */
+struct wmi_radar_control_cmd {
+	/* 0-stop/1-start */
+	u8 start;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_RADAR_PCI_CONTROL_CMDID */
+struct wmi_radar_pci_control_cmd {
+	/* pcie host buffer start address */
+	__le64 base_addr;
+	/* pcie host control block address */
+	__le64 control_block_addr;
+	/* pcie host buffer size */
+	__le32 buffer_size;
+	__le32 reserved;
+} __packed;
+
 /* WMI_RF_MGMT_CMDID */
 enum wmi_rf_mgmt_type {
 	WMI_RF_MGMT_W_DISABLE	= 0x00,
@@ -635,12 +811,18 @@ struct wmi_pcp_start_cmd {
 	u8 pcp_max_assoc_sta;
 	u8 hidden_ssid;
 	u8 is_go;
-	u8 reserved0[5];
+	/* enum wmi_channel WMI_CHANNEL_9..WMI_CHANNEL_12 */
+	u8 edmg_channel;
+	u8 raw_mode;
+	u8 reserved[3];
 	/* A-BFT length override if non-0 */
 	u8 abft_len;
 	/* enum wmi_ap_sme_offload_mode_e */
 	u8 ap_sme_offload_mode;
 	u8 network_type;
+	/* enum wmi_channel WMI_CHANNEL_1..WMI_CHANNEL_6; for EDMG this is
+	 * the primary channel number
+	 */
 	u8 channel;
 	u8 disable_sec_offload;
 	u8 disable_sec;
@@ -653,6 +835,17 @@ struct wmi_sw_tx_req_cmd {
 	u8 payload[0];
 } __packed;
 
+/* WMI_SW_TX_REQ_EXT_CMDID */
+struct wmi_sw_tx_req_ext_cmd {
+	u8 dst_mac[WMI_MAC_LEN];
+	__le16 len;
+	__le16 duration_ms;
+	/* Channel to use, 0xFF for currently active channel */
+	u8 channel;
+	u8 reserved[5];
+	u8 payload[0];
+} __packed;
+
 /* WMI_VRING_SWITCH_TIMING_CONFIG_CMDID */
 struct wmi_vring_switch_timing_config_cmd {
 	/* Set vring timing configuration:
@@ -679,6 +872,7 @@ struct wmi_vring_cfg_schd {
 enum wmi_vring_cfg_encap_trans_type {
 	WMI_VRING_ENC_TYPE_802_3	= 0x00,
 	WMI_VRING_ENC_TYPE_NATIVE_WIFI	= 0x01,
+	WMI_VRING_ENC_TYPE_NONE		= 0x02,
 };
 
 enum wmi_vring_cfg_ds_cfg {
@@ -736,7 +930,11 @@ struct wmi_vring_cfg {
 	u8 cid;
 	/* Used when cidxtid = CIDXTID_EXTENDED_CID_TID */
 	u8 tid;
-	u8 reserved[2];
+	/* Update the vring's priority for Qos purpose. Set to
+	 * WMI_QOS_DEFAULT_PRIORITY to use MID's QoS priority
+	 */
+	u8 qos_priority;
+	u8 reserved;
 } __packed;
 
 enum wmi_vring_cfg_cmd_action {
@@ -767,6 +965,78 @@ struct wmi_bcast_vring_cfg_cmd {
 	struct wmi_bcast_vring_cfg vring_cfg;
 } __packed;
 
+struct wmi_edma_ring_cfg {
+	__le64 ring_mem_base;
+	/* size in number of items */
+	__le16 ring_size;
+	u8 ring_id;
+	u8 reserved;
+} __packed;
+
+enum wmi_rx_msg_type {
+	WMI_RX_MSG_TYPE_COMPRESSED	= 0x00,
+	WMI_RX_MSG_TYPE_EXTENDED	= 0x01,
+};
+
+struct wmi_tx_status_ring_add_cmd {
+	struct wmi_edma_ring_cfg ring_cfg;
+	u8 irq_index;
+	u8 reserved[3];
+} __packed;
+
+struct wmi_rx_status_ring_add_cmd {
+	struct wmi_edma_ring_cfg ring_cfg;
+	u8 irq_index;
+	/* wmi_rx_msg_type */
+	u8 rx_msg_type;
+	u8 reserved[2];
+} __packed;
+
+struct wmi_cfg_def_rx_offload_cmd {
+	__le16 max_msdu_size;
+	__le16 max_rx_pl_per_desc;
+	u8 decap_trans_type;
+	u8 l2_802_3_offload_ctrl;
+	u8 l2_nwifi_offload_ctrl;
+	u8 vlan_id;
+	u8 nwifi_ds_trans_type;
+	u8 l3_l4_ctrl;
+	u8 reserved[6];
+} __packed;
+
+struct wmi_tx_desc_ring_add_cmd {
+	struct wmi_edma_ring_cfg ring_cfg;
+	__le16 max_msdu_size;
+	/* Correlated status ring (0-63) */
+	u8 status_ring_id;
+	u8 cid;
+	u8 tid;
+	u8 encap_trans_type;
+	u8 mac_ctrl;
+	u8 to_resolution;
+	u8 agg_max_wsize;
+	u8 reserved[3];
+	struct wmi_vring_cfg_schd schd_params;
+} __packed;
+
+struct wmi_rx_desc_ring_add_cmd {
+	struct wmi_edma_ring_cfg ring_cfg;
+	u8 irq_index;
+	/* 0-63 status rings */
+	u8 status_ring_id;
+	u8 reserved[2];
+	__le64 sw_tail_host_addr;
+} __packed;
+
+struct wmi_bcast_desc_ring_add_cmd {
+	struct wmi_edma_ring_cfg ring_cfg;
+	__le16 max_msdu_size;
+	/* Correlated status ring (0-63) */
+	u8 status_ring_id;
+	u8 encap_trans_type;
+	u8 reserved[4];
+} __packed;
+
 /* WMI_LO_POWER_CALIB_FROM_OTP_CMDID */
 struct wmi_lo_power_calib_from_otp_cmd {
 	/* index to read from OTP. zero based */
@@ -781,18 +1051,18 @@ struct wmi_lo_power_calib_from_otp_event {
 	u8 reserved[3];
 } __packed;
 
-/* WMI_VRING_BA_EN_CMDID */
-struct wmi_vring_ba_en_cmd {
-	u8 ringid;
+/* WMI_RING_BA_EN_CMDID */
+struct wmi_ring_ba_en_cmd {
+	u8 ring_id;
 	u8 agg_max_wsize;
 	__le16 ba_timeout;
 	u8 amsdu;
 	u8 reserved[3];
 } __packed;
 
-/* WMI_VRING_BA_DIS_CMDID */
-struct wmi_vring_ba_dis_cmd {
-	u8 ringid;
+/* WMI_RING_BA_DIS_CMDID */
+struct wmi_ring_ba_dis_cmd {
+	u8 ring_id;
 	u8 reserved;
 	__le16 reason;
 } __packed;
@@ -950,6 +1220,21 @@ struct wmi_rcp_addba_resp_cmd {
 	u8 reserved[2];
 } __packed;
 
+/* WMI_RCP_ADDBA_RESP_EDMA_CMDID */
+struct wmi_rcp_addba_resp_edma_cmd {
+	u8 cid;
+	u8 tid;
+	u8 dialog_token;
+	u8 reserved;
+	__le16 status_code;
+	/* ieee80211_ba_parameterset field to send */
+	__le16 ba_param_set;
+	__le16 ba_timeout;
+	u8 status_ring_id;
+	/* wmi_cfg_rx_chain_cmd_reorder_type */
+	u8 reorder_type;
+} __packed;
+
 /* WMI_RCP_DELBA_CMDID */
 struct wmi_rcp_delba_cmd {
 	/* Used for cid less than 8. For higher cid set
@@ -999,8 +1284,8 @@ struct wmi_echo_cmd {
 } __packed;
 
 /* WMI_DEEP_ECHO_CMDID
- * Check FW and ucode are alive
- * Returned event: WMI_ECHO_RSP_EVENTID
+ * Check FW and uCode is alive
+ * Returned event: WMI_DEEP_ECHO_RSP_EVENTID
  */
 struct wmi_deep_echo_cmd {
 	__le32 value;
@@ -1324,6 +1609,10 @@ struct wmi_fixed_scheduling_config_complete_event {
 	u8 reserved[3];
 } __packed;
 
+/* This value exists for backwards compatibility only.
+ * Do not use it in new commands.
+ * Use dynamic arrays where possible.
+ */
 #define WMI_NUM_MCS	(13)
 
 /* WMI_FIXED_SCHEDULING_CONFIG_CMDID */
@@ -1371,6 +1660,52 @@ struct wmi_set_multi_directed_omnis_config_event {
 	u8 reserved[3];
 } __packed;
 
+/* WMI_RADAR_GENERAL_CONFIG_EVENTID */
+struct wmi_radar_general_config_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_RADAR_CONFIG_SELECT_EVENTID */
+struct wmi_radar_config_select_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+	/* In unit of bytes */
+	__le32 fifo_size;
+	/* In unit of bytes */
+	__le32 pulse_size;
+} __packed;
+
+/* WMI_RADAR_PARAMS_CONFIG_EVENTID */
+struct wmi_radar_params_config_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_RADAR_SET_MODE_EVENTID */
+struct wmi_radar_set_mode_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_RADAR_CONTROL_EVENTID */
+struct wmi_radar_control_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_RADAR_PCI_CONTROL_EVENTID */
+struct wmi_radar_pci_control_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
 /* WMI_SET_LONG_RANGE_CONFIG_CMDID */
 struct wmi_set_long_range_config_cmd {
 	__le32 reserved;
@@ -1383,12 +1718,12 @@ struct wmi_set_long_range_config_complete_event {
 	u8 reserved[3];
 } __packed;
 
-/* payload max size is 236 bytes: max event buffer size (256) - WMI headers
+/* payload max size is 1024 bytes: max event buffer size (1044) - WMI headers
  * (16) - prev struct field size (4)
  */
-#define WMI_MAX_IOCTL_PAYLOAD_SIZE		(236)
-#define WMI_MAX_IOCTL_REPLY_PAYLOAD_SIZE	(236)
-#define WMI_MAX_INTERNAL_EVENT_PAYLOAD_SIZE	(236)
+#define WMI_MAX_IOCTL_PAYLOAD_SIZE		(1024)
+#define WMI_MAX_IOCTL_REPLY_PAYLOAD_SIZE	(1024)
+#define WMI_MAX_INTERNAL_EVENT_PAYLOAD_SIZE	(1024)
 
 enum wmi_internal_fw_ioctl_code {
 	WMI_INTERNAL_FW_CODE_NONE	= 0x0,
@@ -1428,7 +1763,37 @@ struct wmi_internal_fw_event_event {
 	__le32 payload[0];
 } __packed;
 
-/* WMI_BF_CONTROL_CMDID */
+/* WMI_SET_VRING_PRIORITY_WEIGHT_CMDID */
+struct wmi_set_vring_priority_weight_cmd {
+	/* Array of weights. Valid values are
+	 * WMI_QOS_MIN_DEFAULT_WEIGHT...WMI_QOS_MAX_WEIGHT. Weight #0 is
+	 * hard-coded WMI_QOS_MIN_WEIGHT. This array provide the weights
+	 * #1..#3
+	 */
+	u8 weight[3];
+	u8 reserved;
+} __packed;
+
+/* WMI_SET_VRING_PRIORITY_CMDID */
+struct wmi_vring_priority {
+	u8 vring_idx;
+	/* Weight index. Valid value is 0-3 */
+	u8 priority;
+	u8 reserved[2];
+} __packed;
+
+/* WMI_SET_VRING_PRIORITY_CMDID */
+struct wmi_set_vring_priority_cmd {
+	/* number of entries in vring_priority. Set to
+	 * WMI_QOS_SET_VIF_PRIORITY to update the VIF's priority, and there
+	 * will be only one entry in vring_priority
+	 */
+	u8 num_of_vrings;
+	u8 reserved[3];
+	struct wmi_vring_priority vring_priority[0];
+} __packed;
+
+/* WMI_BF_CONTROL_CMDID - deprecated */
 struct wmi_bf_control_cmd {
 	/* wmi_bf_triggers */
 	__le32 triggers;
@@ -1470,6 +1835,95 @@ struct wmi_bf_control_cmd {
 	u8 reserved2[2];
 } __packed;
 
+/* BF configuration for each MCS */
+struct wmi_bf_control_ex_mcs {
+	/* Long term throughput threshold [Mbps] */
+	u8 long_term_mbps_th_tbl;
+	u8 reserved;
+	/* Long term timeout threshold table [msec] */
+	__le16 long_term_trig_timeout_per_mcs;
+} __packed;
+
+/* WMI_BF_CONTROL_EX_CMDID */
+struct wmi_bf_control_ex_cmd {
+	/* wmi_bf_triggers */
+	__le32 triggers;
+	/* enum wmi_edmg_tx_mode */
+	u8 tx_mode;
+	/* DISABLED = 0, ENABLED = 1 , DRY_RUN = 2 */
+	u8 txss_mode;
+	/* DISABLED = 0, ENABLED = 1, DRY_RUN = 2 */
+	u8 brp_mode;
+	/* Max cts threshold (correspond to
+	 * WMI_BF_TRIGGER_MAX_CTS_FAILURE_IN_TXOP)
+	 */
+	u8 bf_trigger_max_cts_failure_thr;
+	/* Max cts threshold in dense (correspond to
+	 * WMI_BF_TRIGGER_MAX_CTS_FAILURE_IN_TXOP)
+	 */
+	u8 bf_trigger_max_cts_failure_dense_thr;
+	/* Max b-ack threshold (correspond to
+	 * WMI_BF_TRIGGER_MAX_BACK_FAILURE)
+	 */
+	u8 bf_trigger_max_back_failure_thr;
+	/* Max b-ack threshold in dense (correspond to
+	 * WMI_BF_TRIGGER_MAX_BACK_FAILURE)
+	 */
+	u8 bf_trigger_max_back_failure_dense_thr;
+	u8 reserved0;
+	/* Wrong sectors threshold */
+	__le32 wrong_sector_bis_thr;
+	/* BOOL to enable/disable long term trigger */
+	u8 long_term_enable;
+	/* 1 = Update long term thresholds from the long_term_mbps_th_tbl and
+	 * long_term_trig_timeout_per_mcs arrays, 0 = Ignore
+	 */
+	u8 long_term_update_thr;
+	u8 each_mcs_cfg_size;
+	u8 reserved1;
+	/* Configuration for each MCS */
+	struct wmi_bf_control_ex_mcs each_mcs_cfg[0];
+} __packed;
+
+/* WMI_LINK_STATS_CMD */
+enum wmi_link_stats_action {
+	WMI_LINK_STATS_SNAPSHOT		= 0x00,
+	WMI_LINK_STATS_PERIODIC		= 0x01,
+	WMI_LINK_STATS_STOP_PERIODIC	= 0x02,
+};
+
+/* WMI_LINK_STATS_EVENT record identifiers */
+enum wmi_link_stats_record_type {
+	WMI_LINK_STATS_TYPE_BASIC	= 0x01,
+	WMI_LINK_STATS_TYPE_GLOBAL	= 0x02,
+};
+
+/* WMI_LINK_STATS_CMDID */
+struct wmi_link_stats_cmd {
+	/* bitmask of required record types
+	 * (wmi_link_stats_record_type_e)
+	 */
+	__le32 record_type_mask;
+	/* 0xff for all cids */
+	u8 cid;
+	/* wmi_link_stats_action_e */
+	u8 action;
+	u8 reserved[6];
+	/* range = 100 - 10000 */
+	__le32 interval_msec;
+} __packed;
+
+/* WMI_SET_GRANT_MCS_CMDID */
+struct wmi_set_grant_mcs_cmd {
+	u8 mcs;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_SET_AP_SLOT_SIZE_CMDID */
+struct wmi_set_ap_slot_size_cmd {
+	__le32 slot_size;
+} __packed;
+
 /* WMI Events
  * List of Events (target to host)
  */
@@ -1482,10 +1936,19 @@ enum wmi_event_id {
 	WMI_SCHED_SCAN_RESULT_EVENTID			= 0x1007,
 	WMI_SCAN_COMPLETE_EVENTID			= 0x100A,
 	WMI_REPORT_STATISTICS_EVENTID			= 0x100B,
+	WMI_FT_AUTH_STATUS_EVENTID			= 0x100C,
+	WMI_FT_REASSOC_STATUS_EVENTID			= 0x100D,
+	WMI_RADAR_GENERAL_CONFIG_EVENTID		= 0x1100,
+	WMI_RADAR_CONFIG_SELECT_EVENTID			= 0x1101,
+	WMI_RADAR_PARAMS_CONFIG_EVENTID			= 0x1102,
+	WMI_RADAR_SET_MODE_EVENTID			= 0x1103,
+	WMI_RADAR_CONTROL_EVENTID			= 0x1104,
+	WMI_RADAR_PCI_CONTROL_EVENTID			= 0x1105,
 	WMI_RD_MEM_RSP_EVENTID				= 0x1800,
 	WMI_FW_READY_EVENTID				= 0x1801,
 	WMI_EXIT_FAST_MEM_ACC_MODE_EVENTID		= 0x200,
 	WMI_ECHO_RSP_EVENTID				= 0x1803,
+	WMI_DEEP_ECHO_RSP_EVENTID			= 0x1804,
 	/* deprecated */
 	WMI_FS_TUNE_DONE_EVENTID			= 0x180A,
 	/* deprecated */
@@ -1511,6 +1974,9 @@ enum wmi_event_id {
 	WMI_DELBA_EVENTID				= 0x1826,
 	WMI_GET_SSID_EVENTID				= 0x1828,
 	WMI_GET_PCP_CHANNEL_EVENTID			= 0x182A,
+	/* Event is shared between WMI_SW_TX_REQ_CMDID and
+	 * WMI_SW_TX_REQ_EXT_CMDID
+	 */
 	WMI_SW_TX_COMPLETE_EVENTID			= 0x182B,
 	WMI_BEAMFORMING_MGMT_DONE_EVENTID		= 0x1836,
 	WMI_BF_TXSS_MGMT_DONE_EVENTID			= 0x1837,
@@ -1535,7 +2001,7 @@ enum wmi_event_id {
 	WMI_BF_CTRL_DONE_EVENTID			= 0x1862,
 	WMI_NOTIFY_REQ_DONE_EVENTID			= 0x1863,
 	WMI_GET_STATUS_DONE_EVENTID			= 0x1864,
-	WMI_VRING_EN_EVENTID				= 0x1865,
+	WMI_RING_EN_EVENTID				= 0x1865,
 	WMI_GET_RF_STATUS_EVENTID			= 0x1866,
 	WMI_GET_BASEBAND_TYPE_EVENTID			= 0x1867,
 	WMI_VRING_SWITCH_TIMING_CONFIG_EVENTID		= 0x1868,
@@ -1558,7 +2024,12 @@ enum wmi_event_id {
 	WMI_PCP_FACTOR_EVENTID				= 0x191A,
 	/* Power Save Configuration Events */
 	WMI_PS_DEV_PROFILE_CFG_EVENTID			= 0x191C,
+	WMI_RS_ENABLE_EVENTID				= 0x191E,
+	WMI_RS_CFG_EX_EVENTID				= 0x191F,
+	WMI_GET_DETAILED_RS_RES_EX_EVENTID		= 0x1920,
+	/* deprecated */
 	WMI_RS_CFG_DONE_EVENTID				= 0x1921,
+	/* deprecated */
 	WMI_GET_DETAILED_RS_RES_EVENTID			= 0x1922,
 	WMI_AOA_MEAS_EVENTID				= 0x1923,
 	WMI_BRP_SET_ANT_LIMIT_EVENTID			= 0x1924,
@@ -1586,7 +2057,14 @@ enum wmi_event_id {
 	WMI_PRIO_TX_SECTORS_ORDER_EVENTID		= 0x19A5,
 	WMI_PRIO_TX_SECTORS_NUMBER_EVENTID		= 0x19A6,
 	WMI_PRIO_TX_SECTORS_SET_DEFAULT_CFG_EVENTID	= 0x19A7,
+	/* deprecated */
 	WMI_BF_CONTROL_EVENTID				= 0x19AA,
+	WMI_BF_CONTROL_EX_EVENTID			= 0x19AB,
+	WMI_TX_STATUS_RING_CFG_DONE_EVENTID		= 0x19C0,
+	WMI_RX_STATUS_RING_CFG_DONE_EVENTID		= 0x19C1,
+	WMI_TX_DESC_RING_CFG_DONE_EVENTID		= 0x19C2,
+	WMI_RX_DESC_RING_CFG_DONE_EVENTID		= 0x19C3,
+	WMI_CFG_DEF_RX_OFFLOAD_DONE_EVENTID		= 0x19C5,
 	WMI_SCHEDULING_SCHEME_EVENTID			= 0x1A01,
 	WMI_FIXED_SCHEDULING_CONFIG_COMPLETE_EVENTID	= 0x1A02,
 	WMI_ENABLE_FIXED_SCHEDULING_COMPLETE_EVENTID	= 0x1A03,
@@ -1597,6 +2075,12 @@ enum wmi_event_id {
 	WMI_SET_CCA_INDICATIONS_BI_AVG_NUM_EVENTID	= 0x1A08,
 	WMI_INTERNAL_FW_EVENT_EVENTID			= 0x1A0A,
 	WMI_INTERNAL_FW_IOCTL_EVENTID			= 0x1A0B,
+	WMI_LINK_STATS_CONFIG_DONE_EVENTID		= 0x1A0C,
+	WMI_LINK_STATS_EVENTID				= 0x1A0D,
+	WMI_SET_GRANT_MCS_EVENTID			= 0x1A0E,
+	WMI_SET_AP_SLOT_SIZE_EVENTID			= 0x1A0F,
+	WMI_SET_VRING_PRIORITY_WEIGHT_EVENTID		= 0x1A10,
+	WMI_SET_VRING_PRIORITY_EVENTID			= 0x1A11,
 	WMI_SET_CHANNEL_EVENTID				= 0x9000,
 	WMI_ASSOC_REQ_EVENTID				= 0x9001,
 	WMI_EAPOL_RX_EVENTID				= 0x9002,
@@ -1861,6 +2345,33 @@ struct wmi_scan_complete_event {
 	__le32 status;
 } __packed;
 
+/* WMI_FT_AUTH_STATUS_EVENTID */
+struct wmi_ft_auth_status_event {
+	/* enum wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+	u8 mac_addr[WMI_MAC_LEN];
+	__le16 ie_len;
+	u8 ie_info[0];
+} __packed;
+
+/* WMI_FT_REASSOC_STATUS_EVENTID */
+struct wmi_ft_reassoc_status_event {
+	/* enum wmi_fw_status */
+	u8 status;
+	/* association id received from new AP */
+	u8 aid;
+	/* enum wmi_channel */
+	u8 channel;
+	/* enum wmi_channel */
+	u8 edmg_channel;
+	u8 mac_addr[WMI_MAC_LEN];
+	__le16 beacon_ie_len;
+	__le16 reassoc_req_ie_len;
+	__le16 reassoc_resp_ie_len;
+	u8 ie_info[0];
+} __packed;
+
 /* wmi_rx_mgmt_info */
 struct wmi_rx_mgmt_info {
 	u8 mcs;
@@ -1997,6 +2508,49 @@ struct wmi_rcp_addba_resp_sent_event {
 	u8 reserved2[2];
 } __packed;
 
+/* WMI_TX_STATUS_RING_CFG_DONE_EVENTID */
+struct wmi_tx_status_ring_cfg_done_event {
+	u8 ring_id;
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[2];
+	__le32 ring_tail_ptr;
+} __packed;
+
+/* WMI_RX_STATUS_RING_CFG_DONE_EVENTID */
+struct wmi_rx_status_ring_cfg_done_event {
+	u8 ring_id;
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[2];
+	__le32 ring_tail_ptr;
+} __packed;
+
+/* WMI_CFG_DEF_RX_OFFLOAD_DONE_EVENTID */
+struct wmi_cfg_def_rx_offload_done_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_TX_DESC_RING_CFG_DONE_EVENTID */
+struct wmi_tx_desc_ring_cfg_done_event {
+	u8 ring_id;
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[2];
+	__le32 ring_tail_ptr;
+} __packed;
+
+/* WMI_RX_DESC_RING_CFG_DONE_EVENTID */
+struct wmi_rx_desc_ring_cfg_done_event {
+	u8 ring_id;
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[2];
+	__le32 ring_tail_ptr;
+} __packed;
+
 /* WMI_RCP_ADDBA_REQ_EVENTID */
 struct wmi_rcp_addba_req_event {
 	/* Used for cid less than 8. For higher cid set
@@ -2047,9 +2601,9 @@ struct wmi_data_port_open_event {
 	u8 reserved[3];
 } __packed;
 
-/* WMI_VRING_EN_EVENTID */
-struct wmi_vring_en_event {
-	u8 vring_index;
+/* WMI_RING_EN_EVENTID */
+struct wmi_ring_en_event {
+	u8 ring_index;
 	u8 reserved[3];
 } __packed;
 
@@ -2174,6 +2728,11 @@ struct wmi_echo_rsp_event {
 	__le32 echoed_value;
 } __packed;
 
+/* WMI_DEEP_ECHO_RSP_EVENTID */
+struct wmi_deep_echo_rsp_event {
+	__le32 echoed_value;
+} __packed;
+
 /* WMI_RF_PWR_ON_DELAY_RSP_EVENTID */
 struct wmi_rf_pwr_on_delay_rsp_event {
 	/* wmi_fw_status */
@@ -2312,6 +2871,81 @@ struct wmi_rs_cfg {
 	__le32 mcs_en_vec;
 } __packed;
 
+enum wmi_edmg_tx_mode {
+	WMI_TX_MODE_DMG			= 0x0,
+	WMI_TX_MODE_EDMG_CB1		= 0x1,
+	WMI_TX_MODE_EDMG_CB2		= 0x2,
+	WMI_TX_MODE_EDMG_CB1_LONG_LDPC	= 0x3,
+	WMI_TX_MODE_EDMG_CB2_LONG_LDPC	= 0x4,
+	WMI_TX_MODE_MAX,
+};
+
+/* Rate search parameters common configuration */
+struct wmi_rs_cfg_ex_common {
+	/* enum wmi_edmg_tx_mode */
+	u8 mode;
+	/* stop threshold [0-100] */
+	u8 stop_th;
+	/* MCS1 stop threshold [0-100] */
+	u8 mcs1_fail_th;
+	u8 max_back_failure_th;
+	/* Debug feature for disabling internal RS trigger (which is
+	 * currently triggered by BF Done)
+	 */
+	u8 dbg_disable_internal_trigger;
+	u8 reserved[3];
+	__le32 back_failure_mask;
+} __packed;
+
+/* Rate search parameters configuration per MCS */
+struct wmi_rs_cfg_ex_mcs {
+	/* The maximal allowed PER for each MCS
+	 * MCS will be considered as failed if PER during RS is higher
+	 */
+	u8 per_threshold;
+	/* Number of MPDUs for each MCS
+	 * this is the minimal statistic required to make an educated
+	 * decision
+	 */
+	u8 min_frame_cnt;
+	u8 reserved[2];
+} __packed;
+
+/* WMI_RS_CFG_EX_CMDID */
+struct wmi_rs_cfg_ex_cmd {
+	/* Configuration for all MCSs */
+	struct wmi_rs_cfg_ex_common common_cfg;
+	u8 each_mcs_cfg_size;
+	u8 reserved[3];
+	/* Configuration for each MCS */
+	struct wmi_rs_cfg_ex_mcs each_mcs_cfg[0];
+} __packed;
+
+/* WMI_RS_CFG_EX_EVENTID */
+struct wmi_rs_cfg_ex_event {
+	/* enum wmi_edmg_tx_mode */
+	u8 mode;
+	/* enum wmi_fw_status */
+	u8 status;
+	u8 reserved[2];
+} __packed;
+
+/* WMI_RS_ENABLE_CMDID */
+struct wmi_rs_enable_cmd {
+	u8 cid;
+	/* enable or disable rate search */
+	u8 rs_enable;
+	u8 reserved[2];
+	__le32 mcs_en_vec;
+} __packed;
+
+/* WMI_RS_ENABLE_EVENTID */
+struct wmi_rs_enable_event {
+	/* enum wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
 /* Slot types */
 enum wmi_sched_scheme_slot_type {
 	WMI_SCHED_SLOT_SP		= 0x0,
@@ -2404,7 +3038,7 @@ struct wmi_scheduling_scheme_event {
 	u8 reserved[1];
 } __packed;
 
-/* WMI_RS_CFG_CMDID */
+/* WMI_RS_CFG_CMDID - deprecated */
 struct wmi_rs_cfg_cmd {
 	/* connection id */
 	u8 cid;
@@ -2414,7 +3048,7 @@ struct wmi_rs_cfg_cmd {
 	struct wmi_rs_cfg rs_cfg;
 } __packed;
 
-/* WMI_RS_CFG_DONE_EVENTID */
+/* WMI_RS_CFG_DONE_EVENTID - deprecated */
 struct wmi_rs_cfg_done_event {
 	u8 cid;
 	/* enum wmi_fw_status */
@@ -2422,7 +3056,7 @@ struct wmi_rs_cfg_done_event {
 	u8 reserved[2];
 } __packed;
 
-/* WMI_GET_DETAILED_RS_RES_CMDID */
+/* WMI_GET_DETAILED_RS_RES_CMDID - deprecated */
 struct wmi_get_detailed_rs_res_cmd {
 	/* connection id */
 	u8 cid;
@@ -2447,7 +3081,7 @@ struct wmi_rs_results {
 	u8 mcs;
 } __packed;
 
-/* WMI_GET_DETAILED_RS_RES_EVENTID */
+/* WMI_GET_DETAILED_RS_RES_EVENTID - deprecated */
 struct wmi_get_detailed_rs_res_event {
 	u8 cid;
 	/* enum wmi_rs_results_status */
@@ -2457,6 +3091,45 @@ struct wmi_get_detailed_rs_res_event {
 	u8 reserved[3];
 } __packed;
 
+/* WMI_GET_DETAILED_RS_RES_EX_CMDID */
+struct wmi_get_detailed_rs_res_ex_cmd {
+	u8 cid;
+	u8 reserved[3];
+} __packed;
+
+/* Rate search results */
+struct wmi_rs_results_ex_common {
+	/* RS timestamp */
+	__le32 tsf;
+	/* RS selected MCS */
+	u8 mcs;
+	/* enum wmi_edmg_tx_mode */
+	u8 mode;
+	u8 reserved[2];
+} __packed;
+
+/* Rate search results */
+struct wmi_rs_results_ex_mcs {
+	/* number of sent MPDUs */
+	u8 num_of_tx_pkt;
+	/* number of non-acked MPDUs */
+	u8 num_of_non_acked_pkt;
+	u8 reserved[2];
+} __packed;
+
+/* WMI_GET_DETAILED_RS_RES_EX_EVENTID */
+struct wmi_get_detailed_rs_res_ex_event {
+	u8 cid;
+	/* enum wmi_rs_results_status */
+	u8 status;
+	u8 reserved0[2];
+	struct wmi_rs_results_ex_common common_rs_results;
+	u8 each_mcs_results_size;
+	u8 reserved1[3];
+	/* Results for each MCS */
+	struct wmi_rs_results_ex_mcs each_mcs_results[0];
+} __packed;
+
 /* BRP antenna limit mode */
 enum wmi_brp_ant_limit_mode {
 	/* Disable BRP force antenna limit */
@@ -3207,13 +3880,20 @@ struct wmi_get_assoc_list_res_event {
 	u8 reserved[3];
 } __packed;
 
-/* WMI_BF_CONTROL_EVENTID */
+/* WMI_BF_CONTROL_EVENTID - deprecated */
 struct wmi_bf_control_event {
 	/* wmi_fw_status */
 	u8 status;
 	u8 reserved[3];
 } __packed;
 
+/* WMI_BF_CONTROL_EX_EVENTID */
+struct wmi_bf_control_ex_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
 /* WMI_COMMAND_NOT_SUPPORTED_EVENTID */
 struct wmi_command_not_supported_event {
 	/* device id */
@@ -3283,4 +3963,96 @@ struct wmi_internal_fw_set_channel_event {
 	u8 reserved[3];
 } __packed;
 
+/* WMI_LINK_STATS_CONFIG_DONE_EVENTID */
+struct wmi_link_stats_config_done_event {
+	/* wmi_fw_status_e */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_LINK_STATS_EVENTID */
+struct wmi_link_stats_event {
+	__le64 tsf;
+	__le16 payload_size;
+	u8 has_next;
+	u8 reserved[5];
+	/* a stream of wmi_link_stats_record_s */
+	u8 payload[0];
+} __packed;
+
+/* WMI_LINK_STATS_EVENT */
+struct wmi_link_stats_record {
+	/* wmi_link_stats_record_type_e */
+	u8 record_type_id;
+	u8 reserved;
+	__le16 record_size;
+	u8 record[0];
+} __packed;
+
+/* WMI_LINK_STATS_TYPE_BASIC */
+struct wmi_link_stats_basic {
+	u8 cid;
+	s8 rssi;
+	u8 sqi;
+	u8 bf_mcs;
+	u8 per_average;
+	u8 selected_rfc;
+	u8 rx_effective_ant_num;
+	u8 my_rx_sector;
+	u8 my_tx_sector;
+	u8 other_rx_sector;
+	u8 other_tx_sector;
+	u8 reserved[7];
+	/* 1/4 Db units */
+	__le16 snr;
+	__le32 tx_tpt;
+	__le32 tx_goodput;
+	__le32 rx_goodput;
+	__le32 bf_count;
+	__le32 rx_bcast_frames;
+} __packed;
+
+/* WMI_LINK_STATS_TYPE_GLOBAL */
+struct wmi_link_stats_global {
+	/* all ack-able frames */
+	__le32 rx_frames;
+	/* all ack-able frames */
+	__le32 tx_frames;
+	__le32 rx_ba_frames;
+	__le32 tx_ba_frames;
+	__le32 tx_beacons;
+	__le32 rx_mic_errors;
+	__le32 rx_crc_errors;
+	__le32 tx_fail_no_ack;
+	u8 reserved[8];
+} __packed;
+
+/* WMI_SET_GRANT_MCS_EVENTID */
+struct wmi_set_grant_mcs_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_SET_AP_SLOT_SIZE_EVENTID */
+struct wmi_set_ap_slot_size_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_SET_VRING_PRIORITY_WEIGHT_EVENTID */
+struct wmi_set_vring_priority_weight_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_SET_VRING_PRIORITY_EVENTID */
+struct wmi_set_vring_priority_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
 #endif /* __WILOCITY_WMI_H__ */
diff --git a/drivers/net/wireless/atmel/atmel.c b/drivers/net/wireless/atmel/atmel.c
index b01dc34d55af..74538085cfb7 100644
--- a/drivers/net/wireless/atmel/atmel.c
+++ b/drivers/net/wireless/atmel/atmel.c
@@ -1399,6 +1399,7 @@ static int atmel_validate_channel(struct atmel_private *priv, int channel)
 	return 0;
 }
 
+#ifdef CONFIG_PROC_FS
 static int atmel_proc_show(struct seq_file *m, void *v)
 {
 	struct atmel_private *priv = m->private;
@@ -1481,6 +1482,7 @@ static int atmel_proc_show(struct seq_file *m, void *v)
 	seq_printf(m, "Current state:\t\t%s\n", s);
 	return 0;
 }
+#endif
 
 static const struct net_device_ops atmel_netdev_ops = {
 	.ndo_open 		= atmel_open,
@@ -1516,10 +1518,9 @@ struct net_device *init_atmel_card(unsigned short irq, unsigned long port,
 	priv->present_callback = card_present;
 	priv->card = card;
 	priv->firmware = NULL;
-	priv->firmware_id[0] = '\0';
 	priv->firmware_type = fw_type;
 	if (firmware) /* module parameter */
-		strcpy(priv->firmware_id, firmware);
+		strlcpy(priv->firmware_id, firmware, sizeof(priv->firmware_id));
 	priv->bus_type = card_present ? BUS_TYPE_PCCARD : BUS_TYPE_PCI;
 	priv->station_state = STATION_STATE_DOWN;
 	priv->do_rx_crc = 0;
@@ -2646,14 +2647,9 @@ static int atmel_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 			break;
 		}
 
-		if (!(new_firmware = kmalloc(com.len, GFP_KERNEL))) {
-			rc = -ENOMEM;
-			break;
-		}
-
-		if (copy_from_user(new_firmware, com.data, com.len)) {
-			kfree(new_firmware);
-			rc = -EFAULT;
+		new_firmware = memdup_user(com.data, com.len);
+		if (IS_ERR(new_firmware)) {
+			rc = PTR_ERR(new_firmware);
 			break;
 		}
 
@@ -3681,7 +3677,7 @@ static int probe_atmel_card(struct net_device *dev)
 		atmel_write16(dev, GCR, 0x0060);
 
 	atmel_write16(dev, GCR, 0x0040);
-	mdelay(500);
+	msleep(500);
 
 	if (atmel_read16(dev, MR2) == 0) {
 		/* No stored firmware so load a small stub which just
diff --git a/drivers/net/wireless/broadcom/b43/leds.c b/drivers/net/wireless/broadcom/b43/leds.c
index cb987c2ecc6b..87131f663292 100644
--- a/drivers/net/wireless/broadcom/b43/leds.c
+++ b/drivers/net/wireless/broadcom/b43/leds.c
@@ -131,7 +131,7 @@ static int b43_register_led(struct b43_wldev *dev, struct b43_led *led,
 	led->wl = dev->wl;
 	led->index = led_index;
 	led->activelow = activelow;
-	strncpy(led->name, name, sizeof(led->name));
+	strlcpy(led->name, name, sizeof(led->name));
 	atomic_set(&led->state, 0);
 
 	led->led_dev.name = led->name;
diff --git a/drivers/net/wireless/broadcom/b43legacy/leds.c b/drivers/net/wireless/broadcom/b43legacy/leds.c
index fd4565389c77..bc922118b6ac 100644
--- a/drivers/net/wireless/broadcom/b43legacy/leds.c
+++ b/drivers/net/wireless/broadcom/b43legacy/leds.c
@@ -101,7 +101,7 @@ static int b43legacy_register_led(struct b43legacy_wldev *dev,
 	led->dev = dev;
 	led->index = led_index;
 	led->activelow = activelow;
-	strncpy(led->name, name, sizeof(led->name));
+	strlcpy(led->name, name, sizeof(led->name));
 
 	led->led_dev.name = led->name;
 	led->led_dev.default_trigger = default_trigger;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index b6122aad639e..5444e6213d45 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -2434,7 +2434,7 @@ static void brcmf_convert_sta_flags(u32 fw_sta_flags, struct station_info *si)
 	struct nl80211_sta_flag_update *sfu;
 
 	brcmf_dbg(TRACE, "flags %08x\n", fw_sta_flags);
-	si->filled |= BIT(NL80211_STA_INFO_STA_FLAGS);
+	si->filled |= BIT_ULL(NL80211_STA_INFO_STA_FLAGS);
 	sfu = &si->sta_flags;
 	sfu->mask = BIT(NL80211_STA_FLAG_WME) |
 		    BIT(NL80211_STA_FLAG_AUTHENTICATED) |
@@ -2470,7 +2470,7 @@ static void brcmf_fill_bss_param(struct brcmf_if *ifp, struct station_info *si)
 		brcmf_err("Failed to get bss info (%d)\n", err);
 		goto out_kfree;
 	}
-	si->filled |= BIT(NL80211_STA_INFO_BSS_PARAM);
+	si->filled |= BIT_ULL(NL80211_STA_INFO_BSS_PARAM);
 	si->bss_param.beacon_interval = le16_to_cpu(buf->bss_le.beacon_period);
 	si->bss_param.dtim_period = buf->bss_le.dtim_period;
 	capability = le16_to_cpu(buf->bss_le.capability);
@@ -2501,7 +2501,7 @@ brcmf_cfg80211_get_station_ibss(struct brcmf_if *ifp,
 		brcmf_err("BRCMF_C_GET_RATE error (%d)\n", err);
 		return err;
 	}
-	sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 	sinfo->txrate.legacy = rate * 5;
 
 	memset(&scbval, 0, sizeof(scbval));
@@ -2512,7 +2512,7 @@ brcmf_cfg80211_get_station_ibss(struct brcmf_if *ifp,
 		return err;
 	}
 	rssi = le32_to_cpu(scbval.val);
-	sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 	sinfo->signal = rssi;
 
 	err = brcmf_fil_cmd_data_get(ifp, BRCMF_C_GET_GET_PKTCNTS, &pktcnt,
@@ -2521,10 +2521,10 @@ brcmf_cfg80211_get_station_ibss(struct brcmf_if *ifp,
 		brcmf_err("BRCMF_C_GET_GET_PKTCNTS error (%d)\n", err);
 		return err;
 	}
-	sinfo->filled |= BIT(NL80211_STA_INFO_RX_PACKETS) |
-			 BIT(NL80211_STA_INFO_RX_DROP_MISC) |
-			 BIT(NL80211_STA_INFO_TX_PACKETS) |
-			 BIT(NL80211_STA_INFO_TX_FAILED);
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_PACKETS) |
+			 BIT_ULL(NL80211_STA_INFO_RX_DROP_MISC) |
+			 BIT_ULL(NL80211_STA_INFO_TX_PACKETS) |
+			 BIT_ULL(NL80211_STA_INFO_TX_FAILED);
 	sinfo->rx_packets = le32_to_cpu(pktcnt.rx_good_pkt);
 	sinfo->rx_dropped_misc = le32_to_cpu(pktcnt.rx_bad_pkt);
 	sinfo->tx_packets = le32_to_cpu(pktcnt.tx_good_pkt);
@@ -2571,7 +2571,7 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev,
 		}
 	}
 	brcmf_dbg(TRACE, "version %d\n", le16_to_cpu(sta_info_le.ver));
-	sinfo->filled = BIT(NL80211_STA_INFO_INACTIVE_TIME);
+	sinfo->filled = BIT_ULL(NL80211_STA_INFO_INACTIVE_TIME);
 	sinfo->inactive_time = le32_to_cpu(sta_info_le.idle) * 1000;
 	sta_flags = le32_to_cpu(sta_info_le.flags);
 	brcmf_convert_sta_flags(sta_flags, sinfo);
@@ -2581,33 +2581,33 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev,
 	else
 		sinfo->sta_flags.set &= ~BIT(NL80211_STA_FLAG_TDLS_PEER);
 	if (sta_flags & BRCMF_STA_ASSOC) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_CONNECTED_TIME);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CONNECTED_TIME);
 		sinfo->connected_time = le32_to_cpu(sta_info_le.in);
 		brcmf_fill_bss_param(ifp, sinfo);
 	}
 	if (sta_flags & BRCMF_STA_SCBSTATS) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_FAILED);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_FAILED);
 		sinfo->tx_failed = le32_to_cpu(sta_info_le.tx_failures);
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_PACKETS);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_PACKETS);
 		sinfo->tx_packets = le32_to_cpu(sta_info_le.tx_pkts);
 		sinfo->tx_packets += le32_to_cpu(sta_info_le.tx_mcast_pkts);
-		sinfo->filled |= BIT(NL80211_STA_INFO_RX_PACKETS);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_PACKETS);
 		sinfo->rx_packets = le32_to_cpu(sta_info_le.rx_ucast_pkts);
 		sinfo->rx_packets += le32_to_cpu(sta_info_le.rx_mcast_pkts);
 		if (sinfo->tx_packets) {
-			sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 			sinfo->txrate.legacy =
 				le32_to_cpu(sta_info_le.tx_rate) / 100;
 		}
 		if (sinfo->rx_packets) {
-			sinfo->filled |= BIT(NL80211_STA_INFO_RX_BITRATE);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BITRATE);
 			sinfo->rxrate.legacy =
 				le32_to_cpu(sta_info_le.rx_rate) / 100;
 		}
 		if (le16_to_cpu(sta_info_le.ver) >= 4) {
-			sinfo->filled |= BIT(NL80211_STA_INFO_TX_BYTES);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BYTES);
 			sinfo->tx_bytes = le64_to_cpu(sta_info_le.tx_tot_bytes);
-			sinfo->filled |= BIT(NL80211_STA_INFO_RX_BYTES);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BYTES);
 			sinfo->rx_bytes = le64_to_cpu(sta_info_le.rx_tot_bytes);
 		}
 		total_rssi = 0;
@@ -2623,10 +2623,10 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev,
 			}
 		}
 		if (count_rssi) {
-			sinfo->filled |= BIT(NL80211_STA_INFO_CHAIN_SIGNAL);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL);
 			sinfo->chains = count_rssi;
 
-			sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 			total_rssi /= count_rssi;
 			sinfo->signal = total_rssi;
 		} else if (test_bit(BRCMF_VIF_STATUS_CONNECTED,
@@ -2639,7 +2639,7 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev,
 				goto done;
 			} else {
 				rssi = le32_to_cpu(scb_val.val);
-				sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+				sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 				sinfo->signal = rssi;
 				brcmf_dbg(CONN, "RSSI %d dBm\n", rssi);
 			}
@@ -6926,15 +6926,15 @@ struct brcmf_cfg80211_info *brcmf_cfg80211_attach(struct brcmf_pub *drvr,
 	cfg->d11inf.io_type = (u8)io_type;
 	brcmu_d11_attach(&cfg->d11inf);
 
-	err = brcmf_setup_wiphy(wiphy, ifp);
-	if (err < 0)
-		goto priv_out;
-
 	/* regulatory notifer below needs access to cfg so
 	 * assign it now.
 	 */
 	drvr->config = cfg;
 
+	err = brcmf_setup_wiphy(wiphy, ifp);
+	if (err < 0)
+		goto priv_out;
+
 	brcmf_dbg(INFO, "Registering custom regulatory\n");
 	wiphy->reg_notifier = brcmf_cfg80211_reg_notifier;
 	wiphy->regulatory_flags |= REGULATORY_CUSTOM_REG;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
index 72954fd6df3b..b1f702faff4f 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
@@ -21,6 +21,7 @@
 #include <net/cfg80211.h>
 #include <net/rtnetlink.h>
 #include <net/addrconf.h>
+#include <net/ieee80211_radiotap.h>
 #include <net/ipv6.h>
 #include <brcmu_utils.h>
 #include <brcmu_wifi.h>
@@ -404,6 +405,30 @@ void brcmf_netif_rx(struct brcmf_if *ifp, struct sk_buff *skb)
 		netif_rx_ni(skb);
 }
 
+void brcmf_netif_mon_rx(struct brcmf_if *ifp, struct sk_buff *skb)
+{
+	if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_MONITOR_FMT_RADIOTAP)) {
+		/* Do nothing */
+	} else {
+		struct ieee80211_radiotap_header *radiotap;
+
+		/* TODO: use RX status to fill some radiotap data */
+		radiotap = skb_push(skb, sizeof(*radiotap));
+		memset(radiotap, 0, sizeof(*radiotap));
+		radiotap->it_len = cpu_to_le16(sizeof(*radiotap));
+
+		/* TODO: 4 bytes with receive status? */
+		skb->len -= 4;
+	}
+
+	skb->dev = ifp->ndev;
+	skb_reset_mac_header(skb);
+	skb->pkt_type = PACKET_OTHERHOST;
+	skb->protocol = htons(ETH_P_802_2);
+
+	brcmf_netif_rx(ifp, skb);
+}
+
 static int brcmf_rx_hdrpull(struct brcmf_pub *drvr, struct sk_buff *skb,
 			    struct brcmf_if **ifp)
 {
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h
index 401f50458686..dcf6e27cc16f 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h
@@ -121,6 +121,7 @@ struct brcmf_pub {
 
 	struct brcmf_if *iflist[BRCMF_MAX_IFS];
 	s32 if2bss[BRCMF_MAX_IFS];
+	struct brcmf_if *mon_if;
 
 	struct mutex proto_block;
 	unsigned char proto_buf[BRCMF_DCMD_MAXLEN];
@@ -216,6 +217,7 @@ void brcmf_txflowblock_if(struct brcmf_if *ifp,
 			  enum brcmf_netif_stop_reason reason, bool state);
 void brcmf_txfinalize(struct brcmf_if *ifp, struct sk_buff *txp, bool success);
 void brcmf_netif_rx(struct brcmf_if *ifp, struct sk_buff *skb);
+void brcmf_netif_mon_rx(struct brcmf_if *ifp, struct sk_buff *skb);
 void brcmf_net_setcarrier(struct brcmf_if *ifp, bool on);
 int __init brcmf_core_init(void);
 void __exit brcmf_core_exit(void);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
index 800a423c7bc2..8347da632a5b 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
@@ -48,6 +48,8 @@ static const struct brcmf_feat_fwcap brcmf_fwcap_map[] = {
 	{ BRCMF_FEAT_MBSS, "mbss" },
 	{ BRCMF_FEAT_MCHAN, "mchan" },
 	{ BRCMF_FEAT_P2P, "p2p" },
+	{ BRCMF_FEAT_MONITOR, "monitor" },
+	{ BRCMF_FEAT_MONITOR_FMT_RADIOTAP, "rtap" },
 };
 
 #ifdef DEBUG
@@ -91,6 +93,42 @@ static int brcmf_feat_debugfs_read(struct seq_file *seq, void *data)
 }
 #endif /* DEBUG */
 
+struct brcmf_feat_fwfeat {
+	const char * const fwid;
+	u32 feat_flags;
+};
+
+static const struct brcmf_feat_fwfeat brcmf_feat_fwfeat_map[] = {
+	/* brcmfmac43602-pcie.ap.bin from linux-firmware.git commit ea1178515b88 */
+	{ "01-6cb8e269", BIT(BRCMF_FEAT_MONITOR) },
+	/* brcmfmac4366b-pcie.bin from linux-firmware.git commit 52442afee990 */
+	{ "01-c47a91a4", BIT(BRCMF_FEAT_MONITOR) },
+};
+
+static void brcmf_feat_firmware_overrides(struct brcmf_pub *drv)
+{
+	const struct brcmf_feat_fwfeat *e;
+	u32 feat_flags = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(brcmf_feat_fwfeat_map); i++) {
+		e = &brcmf_feat_fwfeat_map[i];
+		if (!strcmp(e->fwid, drv->fwver)) {
+			feat_flags = e->feat_flags;
+			break;
+		}
+	}
+
+	if (!feat_flags)
+		return;
+
+	for (i = 0; i < BRCMF_FEAT_LAST; i++)
+		if (feat_flags & BIT(i))
+			brcmf_dbg(INFO, "enabling firmware feature: %s\n",
+				  brcmf_feat_names[i]);
+	drv->feat_flags |= feat_flags;
+}
+
 /**
  * brcmf_feat_iovar_int_get() - determine feature through iovar query.
  *
@@ -251,6 +289,8 @@ void brcmf_feat_attach(struct brcmf_pub *drvr)
 	}
 	brcmf_feat_iovar_int_get(ifp, BRCMF_FEAT_FWSUP, "sup_wpa");
 
+	brcmf_feat_firmware_overrides(drvr);
+
 	/* set chip related quirks */
 	switch (drvr->bus_if->chip) {
 	case BRCM_CC_43236_CHIP_ID:
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h
index d1193825e559..0b4974df353a 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h
@@ -33,6 +33,8 @@
  * MFP: 802.11w Management Frame Protection.
  * GSCAN: enhanced scan offload feature.
  * FWSUP: Firmware supplicant.
+ * MONITOR: firmware can pass monitor packets to host.
+ * MONITOR_FMT_RADIOTAP: firmware provides monitor packets with radiotap header
  */
 #define BRCMF_FEAT_LIST \
 	BRCMF_FEAT_DEF(MBSS) \
@@ -48,7 +50,9 @@
 	BRCMF_FEAT_DEF(WOWL_ARP_ND) \
 	BRCMF_FEAT_DEF(MFP) \
 	BRCMF_FEAT_DEF(GSCAN) \
-	BRCMF_FEAT_DEF(FWSUP)
+	BRCMF_FEAT_DEF(FWSUP) \
+	BRCMF_FEAT_DEF(MONITOR) \
+	BRCMF_FEAT_DEF(MONITOR_FMT_RADIOTAP)
 
 /*
  * Quirks:
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
index 4b290705e3e6..d5bb81e88762 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
@@ -32,11 +32,30 @@
 #define	BRCMF_BSS_INFO_VERSION	109 /* curr ver of brcmf_bss_info_le struct */
 #define BRCMF_BSS_RSSI_ON_CHANNEL	0x0002
 
-#define BRCMF_STA_WME              0x00000002      /* WMM association */
-#define BRCMF_STA_AUTHE            0x00000008      /* Authenticated */
-#define BRCMF_STA_ASSOC            0x00000010      /* Associated */
-#define BRCMF_STA_AUTHO            0x00000020      /* Authorized */
-#define BRCMF_STA_SCBSTATS         0x00004000      /* Per STA debug stats */
+#define BRCMF_STA_BRCM			0x00000001	/* Running a Broadcom driver */
+#define BRCMF_STA_WME			0x00000002	/* WMM association */
+#define BRCMF_STA_NONERP		0x00000004	/* No ERP */
+#define BRCMF_STA_AUTHE			0x00000008	/* Authenticated */
+#define BRCMF_STA_ASSOC			0x00000010	/* Associated */
+#define BRCMF_STA_AUTHO			0x00000020	/* Authorized */
+#define BRCMF_STA_WDS			0x00000040	/* Wireless Distribution System */
+#define BRCMF_STA_WDS_LINKUP		0x00000080	/* WDS traffic/probes flowing properly */
+#define BRCMF_STA_PS			0x00000100	/* STA is in power save mode from AP's viewpoint */
+#define BRCMF_STA_APSD_BE		0x00000200	/* APSD delv/trigger for AC_BE is default enabled */
+#define BRCMF_STA_APSD_BK		0x00000400	/* APSD delv/trigger for AC_BK is default enabled */
+#define BRCMF_STA_APSD_VI		0x00000800	/* APSD delv/trigger for AC_VI is default enabled */
+#define BRCMF_STA_APSD_VO		0x00001000	/* APSD delv/trigger for AC_VO is default enabled */
+#define BRCMF_STA_N_CAP			0x00002000	/* STA 802.11n capable */
+#define BRCMF_STA_SCBSTATS		0x00004000	/* Per STA debug stats */
+#define BRCMF_STA_AMPDU_CAP		0x00008000	/* STA AMPDU capable */
+#define BRCMF_STA_AMSDU_CAP		0x00010000	/* STA AMSDU capable */
+#define BRCMF_STA_MIMO_PS		0x00020000	/* mimo ps mode is enabled */
+#define BRCMF_STA_MIMO_RTS		0x00040000	/* send rts in mimo ps mode */
+#define BRCMF_STA_RIFS_CAP		0x00080000	/* rifs enabled */
+#define BRCMF_STA_VHT_CAP		0x00100000	/* STA VHT(11ac) capable */
+#define BRCMF_STA_WPS			0x00200000	/* WPS state */
+#define BRCMF_STA_DWDS_CAP		0x01000000	/* DWDS CAP */
+#define BRCMF_STA_DWDS			0x02000000	/* DWDS active */
 
 /* size of brcmf_scan_params not including variable length array */
 #define BRCMF_SCAN_PARAMS_FIXED_SIZE	64
@@ -155,6 +174,8 @@
 #define BRCMF_MFP_CAPABLE		1
 #define BRCMF_MFP_REQUIRED		2
 
+#define BRCMF_VHT_CAP_MCS_MAP_NSS_MAX	8
+
 /* MAX_CHUNK_LEN is the maximum length for data passing to firmware in each
  * ioctl. It is relatively small because firmware has small maximum size input
  * playload restriction for ioctls.
@@ -531,6 +552,8 @@ struct brcmf_sta_info_le {
 						/* w/hi bit set if basic */
 	__le32 in;		/* seconds elapsed since associated */
 	__le32 listen_interval_inms; /* Min Listen interval in ms for STA */
+
+	/* Fields valid for ver >= 3 */
 	__le32 tx_pkts;	/* # of packets transmitted */
 	__le32 tx_failures;	/* # of packets failed */
 	__le32 rx_ucast_pkts;	/* # of unicast packets received */
@@ -539,6 +562,8 @@ struct brcmf_sta_info_le {
 	__le32 rx_rate;	/* Rate of last successful rx frame */
 	__le32 rx_decrypt_succeeds;	/* # of packet decrypted successfully */
 	__le32 rx_decrypt_failures;	/* # of packet decrypted failed */
+
+	/* Fields valid for ver >= 4 */
 	__le32 tx_tot_pkts;    /* # of tx pkts (ucast + mcast) */
 	__le32 rx_tot_pkts;    /* # of data packets recvd (uni + mcast) */
 	__le32 tx_mcast_pkts;  /* # of mcast pkts txed */
@@ -575,6 +600,14 @@ struct brcmf_sta_info_le {
 						*/
 	__le32 rx_pkts_retried;        /* # rx with retry bit set */
 	__le32 tx_rate_fallback;       /* lowest fallback TX rate */
+
+	/* Fields valid for ver >= 5 */
+	struct {
+		__le32 count;					/* # rates in this set */
+		u8 rates[BRCMF_MAXRATES_IN_SET];		/* rates in 500kbps units w/hi bit set if basic */
+		u8 mcs[BRCMF_MCSSET_LEN];			/* supported mcs index bit map */
+		__le16 vht_mcs[BRCMF_VHT_CAP_MCS_MAP_NSS_MAX];	/* supported mcs index bit map per nss */
+	} rateset_adv;
 };
 
 struct brcmf_chanspec_list {
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c
index c40ba8855cd5..4e8397a0cbc8 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c
@@ -69,6 +69,8 @@
 #define BRCMF_MSGBUF_MAX_EVENTBUF_POST		8
 
 #define BRCMF_MSGBUF_PKT_FLAGS_FRAME_802_3	0x01
+#define BRCMF_MSGBUF_PKT_FLAGS_FRAME_802_11	0x02
+#define BRCMF_MSGBUF_PKT_FLAGS_FRAME_MASK	0x07
 #define BRCMF_MSGBUF_PKT_FLAGS_PRIO_SHIFT	5
 
 #define BRCMF_MSGBUF_TX_FLUSH_CNT1		32
@@ -1128,6 +1130,7 @@ brcmf_msgbuf_process_rx_complete(struct brcmf_msgbuf *msgbuf, void *buf)
 	struct sk_buff *skb;
 	u16 data_offset;
 	u16 buflen;
+	u16 flags;
 	u32 idx;
 	struct brcmf_if *ifp;
 
@@ -1137,6 +1140,7 @@ brcmf_msgbuf_process_rx_complete(struct brcmf_msgbuf *msgbuf, void *buf)
 	data_offset = le16_to_cpu(rx_complete->data_offset);
 	buflen = le16_to_cpu(rx_complete->data_len);
 	idx = le32_to_cpu(rx_complete->msg.request_id);
+	flags = le16_to_cpu(rx_complete->flags);
 
 	skb = brcmf_msgbuf_get_pktid(msgbuf->drvr->bus_if->dev,
 				     msgbuf->rx_pktids, idx);
@@ -1150,6 +1154,20 @@ brcmf_msgbuf_process_rx_complete(struct brcmf_msgbuf *msgbuf, void *buf)
 
 	skb_trim(skb, buflen);
 
+	if ((flags & BRCMF_MSGBUF_PKT_FLAGS_FRAME_MASK) ==
+	    BRCMF_MSGBUF_PKT_FLAGS_FRAME_802_11) {
+		ifp = msgbuf->drvr->mon_if;
+
+		if (!ifp) {
+			brcmf_err("Received unexpected monitor pkt\n");
+			brcmu_pkt_buf_free_skb(skb);
+			return;
+		}
+
+		brcmf_netif_mon_rx(ifp, skb);
+		return;
+	}
+
 	ifp = brcmf_get_ifp(msgbuf->drvr, rx_complete->msg.ifidx);
 	if (!ifp || !ifp->ndev) {
 		brcmf_err("Received pkt for invalid ifidx %d\n",
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c
index 3a13d176b221..35e3b101e5cf 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c
@@ -159,7 +159,7 @@ u16 read_radio_reg(struct brcms_phy *pi, u16 addr)
 {
 	u16 data;
 
-	if ((addr == RADIO_IDCODE))
+	if (addr == RADIO_IDCODE)
 		return 0xffff;
 
 	switch (pi->pubpi.phy_type) {
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c
index 1a187557982e..bedec1606caa 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c
@@ -16904,7 +16904,7 @@ static void wlc_phy_workarounds_nphy_rev3(struct brcms_phy *pi)
 	}
 }
 
-void wlc_phy_workarounds_nphy_rev1(struct brcms_phy *pi)
+static void wlc_phy_workarounds_nphy_rev1(struct brcms_phy *pi)
 {
 	static const u8 rfseq_rx2tx_events[] = {
 		NPHY_RFSEQ_CMD_NOP,
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_qmath.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_qmath.c
index b9672da24a9d..b24bc57ca91b 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_qmath.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_qmath.c
@@ -213,7 +213,7 @@ static const s16 log_table[] = {
 	30498,
 	31267,
 	32024,
-	32768
+	32767
 };
 
 #define LOG_TABLE_SIZE 32       /* log_table size */
diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c
index 72046e182745..04dd7a936593 100644
--- a/drivers/net/wireless/cisco/airo.c
+++ b/drivers/net/wireless/cisco/airo.c
@@ -3419,7 +3419,7 @@ done:
 
 static void airo_handle_tx(struct airo_info *ai, u16 status)
 {
-	int i, len = 0, index = -1;
+	int i, index = -1;
 	u16 fid;
 
 	if (test_bit(FLAG_MPI, &ai->flags)) {
@@ -3443,11 +3443,9 @@ static void airo_handle_tx(struct airo_info *ai, u16 status)
 
 	fid = IN4500(ai, TXCOMPLFID);
 
-	for(i = 0; i < MAX_FIDS; i++) {
-		if ((ai->fids[i] & 0xffff) == fid) {
-			len = ai->fids[i] >> 16;
+	for (i = 0; i < MAX_FIDS; i++) {
+		if ((ai->fids[i] & 0xffff) == fid)
 			index = i;
-		}
 	}
 
 	if (index != -1) {
diff --git a/drivers/net/wireless/cisco/airo_cs.c b/drivers/net/wireless/cisco/airo_cs.c
index d9ed22b4cc6b..3718f958c0fc 100644
--- a/drivers/net/wireless/cisco/airo_cs.c
+++ b/drivers/net/wireless/cisco/airo_cs.c
@@ -102,11 +102,8 @@ static int airo_cs_config_check(struct pcmcia_device *p_dev, void *priv_data)
 
 static int airo_config(struct pcmcia_device *link)
 {
-	struct local_info *dev;
 	int ret;
 
-	dev = link->priv;
-
 	dev_dbg(&link->dev, "airo_config\n");
 
 	link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_VPP |
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2100.c b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
index b8fd3cc90634..910db46db6a1 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2100.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
@@ -692,7 +692,7 @@ static void printk_buf(int level, const u8 * data, u32 len)
 
 static void schedule_reset(struct ipw2100_priv *priv)
 {
-	unsigned long now = get_seconds();
+	time64_t now = ktime_get_boottime_seconds();
 
 	/* If we haven't received a reset request within the backoff period,
 	 * then we can reset the backoff interval so this reset occurs
@@ -701,10 +701,10 @@ static void schedule_reset(struct ipw2100_priv *priv)
 	    (now - priv->last_reset > priv->reset_backoff))
 		priv->reset_backoff = 0;
 
-	priv->last_reset = get_seconds();
+	priv->last_reset = now;
 
 	if (!(priv->status & STATUS_RESET_PENDING)) {
-		IPW_DEBUG_INFO("%s: Scheduling firmware restart (%ds).\n",
+		IPW_DEBUG_INFO("%s: Scheduling firmware restart (%llds).\n",
 			       priv->net_dev->name, priv->reset_backoff);
 		netif_carrier_off(priv->net_dev);
 		netif_stop_queue(priv->net_dev);
@@ -2079,7 +2079,7 @@ static void isr_indicate_associated(struct ipw2100_priv *priv, u32 status)
 	memcpy(priv->bssid, bssid, ETH_ALEN);
 
 	priv->status |= STATUS_ASSOCIATING;
-	priv->connect_start = get_seconds();
+	priv->connect_start = ktime_get_boottime_seconds();
 
 	schedule_delayed_work(&priv->wx_event_work, HZ / 10);
 }
@@ -4070,8 +4070,8 @@ static ssize_t show_internals(struct device *d, struct device_attribute *attr,
 #define DUMP_VAR(x,y) len += sprintf(buf + len, # x ": %" y "\n", priv-> x)
 
 	if (priv->status & STATUS_ASSOCIATED)
-		len += sprintf(buf + len, "connected: %lu\n",
-			       get_seconds() - priv->connect_start);
+		len += sprintf(buf + len, "connected: %llu\n",
+			       ktime_get_boottime_seconds() - priv->connect_start);
 	else
 		len += sprintf(buf + len, "not connected\n");
 
@@ -4108,7 +4108,7 @@ static ssize_t show_internals(struct device *d, struct device_attribute *attr,
 	DUMP_VAR(txq_stat.lo, "d");
 
 	DUMP_VAR(ieee->scans, "d");
-	DUMP_VAR(reset_backoff, "d");
+	DUMP_VAR(reset_backoff, "lld");
 
 	return len;
 }
@@ -5112,11 +5112,9 @@ static int ipw2100_disassociate_bssid(struct ipw2100_priv *priv)
 		.host_command_length = ETH_ALEN
 	};
 	int err;
-	int len;
 
 	IPW_DEBUG_HC("DISASSOCIATION_BSSID\n");
 
-	len = ETH_ALEN;
 	/* The Firmware currently ignores the BSSID and just disassociates from
 	 * the currently associated AP -- but in the off chance that a future
 	 * firmware does use the BSSID provided here, we go ahead and try and
@@ -6437,7 +6435,7 @@ static int ipw2100_suspend(struct pci_dev *pci_dev, pm_message_t state)
 	pci_disable_device(pci_dev);
 	pci_set_power_state(pci_dev, PCI_D3hot);
 
-	priv->suspend_at = get_seconds();
+	priv->suspend_at = ktime_get_boottime_seconds();
 
 	mutex_unlock(&priv->action_mutex);
 
@@ -6482,7 +6480,7 @@ static int ipw2100_resume(struct pci_dev *pci_dev)
 	 * the queue of needed */
 	netif_device_attach(dev);
 
-	priv->suspend_time = get_seconds() - priv->suspend_at;
+	priv->suspend_time = ktime_get_boottime_seconds() - priv->suspend_at;
 
 	/* Bring the device back up */
 	if (!(priv->status & STATUS_RF_KILL_SW))
@@ -7723,7 +7721,6 @@ static int ipw2100_wx_get_auth(struct net_device *dev,
 	struct libipw_device *ieee = priv->ieee;
 	struct lib80211_crypt_data *crypt;
 	struct iw_param *param = &wrqu->param;
-	int ret = 0;
 
 	switch (param->flags & IW_AUTH_INDEX) {
 	case IW_AUTH_WPA_VERSION:
@@ -7733,7 +7730,6 @@ static int ipw2100_wx_get_auth(struct net_device *dev,
 		/*
 		 * wpa_supplicant will control these internally
 		 */
-		ret = -EOPNOTSUPP;
 		break;
 
 	case IW_AUTH_TKIP_COUNTERMEASURES:
@@ -7801,9 +7797,6 @@ static int ipw2100_wx_set_mlme(struct net_device *dev,
 {
 	struct ipw2100_priv *priv = libipw_priv(dev);
 	struct iw_mlme *mlme = (struct iw_mlme *)extra;
-	__le16 reason;
-
-	reason = cpu_to_le16(mlme->reason_code);
 
 	switch (mlme->cmd) {
 	case IW_MLME_DEAUTH:
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2100.h b/drivers/net/wireless/intel/ipw2x00/ipw2100.h
index ce3e35f6b60f..8c11c7fa2eef 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2100.h
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2100.h
@@ -491,7 +491,7 @@ struct ipw2100_priv {
 
 	/* Statistics */
 	int resets;
-	int reset_backoff;
+	time64_t reset_backoff;
 
 	/* Context */
 	u8 essid[IW_ESSID_MAX_SIZE];
@@ -500,8 +500,8 @@ struct ipw2100_priv {
 	u8 channel;
 	int last_mode;
 
-	unsigned long connect_start;
-	unsigned long last_reset;
+	time64_t connect_start;
+	time64_t last_reset;
 
 	u32 channel_mask;
 	u32 fatal_error;
@@ -581,9 +581,9 @@ struct ipw2100_priv {
 
 	int user_requested_scan;
 
-	/* Track time in suspend */
-	unsigned long suspend_at;
-	unsigned long suspend_time;
+	/* Track time in suspend, using CLOCK_BOOTTIME */
+	time64_t suspend_at;
+	time64_t suspend_time;
 
 	u32 interrupts;
 	int tx_interrupts;
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.c b/drivers/net/wireless/intel/ipw2x00/ipw2200.c
index 8a858f7e36f4..9644e7b93645 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2200.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.c
@@ -7112,7 +7112,7 @@ static u32 ipw_qos_get_burst_duration(struct ipw_priv *priv)
 {
 	u32 ret = 0;
 
-	if ((priv == NULL))
+	if (!priv)
 		return 0;
 
 	if (!(priv->ieee->modulation & LIBIPW_OFDM_MODULATION))
@@ -11888,7 +11888,7 @@ static int ipw_pci_suspend(struct pci_dev *pdev, pm_message_t state)
 	pci_disable_device(pdev);
 	pci_set_power_state(pdev, pci_choose_state(pdev, state));
 
-	priv->suspend_at = get_seconds();
+	priv->suspend_at = ktime_get_boottime_seconds();
 
 	return 0;
 }
@@ -11925,7 +11925,7 @@ static int ipw_pci_resume(struct pci_dev *pdev)
 	 * the queue of needed */
 	netif_device_attach(dev);
 
-	priv->suspend_time = get_seconds() - priv->suspend_at;
+	priv->suspend_time = ktime_get_boottime_seconds() - priv->suspend_at;
 
 	/* Bring the device back up */
 	schedule_work(&priv->up);
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.h b/drivers/net/wireless/intel/ipw2x00/ipw2200.h
index aa301d1eee3c..f98ab1f71edd 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2200.h
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.h
@@ -1343,9 +1343,9 @@ struct ipw_priv {
 
 	s8 tx_power;
 
-	/* Track time in suspend */
-	unsigned long suspend_at;
-	unsigned long suspend_time;
+	/* Track time in suspend using CLOCK_BOOTIME */
+	time64_t suspend_at;
+	time64_t suspend_time;
 
 #ifdef CONFIG_PM
 	u32 pm_state[16];
diff --git a/drivers/net/wireless/intel/ipw2x00/libipw_wx.c b/drivers/net/wireless/intel/ipw2x00/libipw_wx.c
index dd29f46d086b..d32d39fa2686 100644
--- a/drivers/net/wireless/intel/ipw2x00/libipw_wx.c
+++ b/drivers/net/wireless/intel/ipw2x00/libipw_wx.c
@@ -479,7 +479,6 @@ int libipw_wx_get_encode(struct libipw_device *ieee,
 {
 	struct iw_point *erq = &(wrqu->encoding);
 	int len, key;
-	struct lib80211_crypt_data *crypt;
 	struct libipw_security *sec = &ieee->sec;
 
 	LIBIPW_DEBUG_WX("GET_ENCODE\n");
@@ -492,7 +491,6 @@ int libipw_wx_get_encode(struct libipw_device *ieee,
 	} else
 		key = ieee->crypt_info.tx_keyidx;
 
-	crypt = ieee->crypt_info.crypt[key];
 	erq->flags = key + 1;
 
 	if (!sec->enabled) {
diff --git a/drivers/net/wireless/intel/iwlegacy/3945-debug.c b/drivers/net/wireless/intel/iwlegacy/3945-debug.c
index c1b4441fb8b2..a2960032be81 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945-debug.c
+++ b/drivers/net/wireless/intel/iwlegacy/3945-debug.c
@@ -95,7 +95,7 @@ il3945_ucode_rx_stats_read(struct file *file, char __user *user_buf,
 	pos +=
 	    scnprintf(buf + pos, bufsz - pos,
 		      "%-32s     current"
-		      "acumulative       delta         max\n",
+		      "accumulative      delta         max\n",
 		      "Statistics_Rx - OFDM:");
 	pos +=
 	    scnprintf(buf + pos, bufsz - pos,
diff --git a/drivers/net/wireless/intel/iwlegacy/3945-mac.c b/drivers/net/wireless/intel/iwlegacy/3945-mac.c
index 62a9794f952b..57e3b6cca234 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/3945-mac.c
@@ -476,8 +476,6 @@ il3945_tx_skb(struct il_priv *il,
 	int txq_id = skb_get_queue_mapping(skb);
 	u16 len, idx, hdr_len;
 	u16 firstlen, secondlen;
-	u8 id;
-	u8 unicast;
 	u8 sta_id;
 	u8 tid = 0;
 	__le16 fc;
@@ -496,9 +494,6 @@ il3945_tx_skb(struct il_priv *il,
 		goto drop_unlock;
 	}
 
-	unicast = !is_multicast_ether_addr(hdr->addr1);
-	id = 0;
-
 	fc = hdr->frame_control;
 
 #ifdef CONFIG_IWLEGACY_DEBUG
@@ -957,10 +952,8 @@ il3945_rx_queue_restock(struct il_priv *il)
 	struct list_head *element;
 	struct il_rx_buf *rxb;
 	unsigned long flags;
-	int write;
 
 	spin_lock_irqsave(&rxq->lock, flags);
-	write = rxq->write & ~0x7;
 	while (il_rx_queue_space(rxq) > 0 && rxq->free_count) {
 		/* Get next free Rx buffer, remove from free list */
 		element = rxq->rx_free.next;
@@ -2725,7 +2718,6 @@ void
 il3945_post_associate(struct il_priv *il)
 {
 	int rc = 0;
-	struct ieee80211_conf *conf = NULL;
 
 	if (!il->vif || !il->is_open)
 		return;
@@ -2738,8 +2730,6 @@ il3945_post_associate(struct il_priv *il)
 
 	il_scan_cancel_timeout(il, 200);
 
-	conf = &il->hw->conf;
-
 	il->staging.filter_flags &= ~RXON_FILTER_ASSOC_MSK;
 	il3945_commit_rxon(il);
 
diff --git a/drivers/net/wireless/intel/iwlegacy/3945.c b/drivers/net/wireless/intel/iwlegacy/3945.c
index dbf164d48ed3..3e568ce2fb20 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945.c
+++ b/drivers/net/wireless/intel/iwlegacy/3945.c
@@ -1634,7 +1634,6 @@ il3945_hw_reg_set_txpower(struct il_priv *il, s8 power)
 {
 	struct il_channel_info *ch_info;
 	s8 max_power;
-	u8 a_band;
 	u8 i;
 
 	if (il->tx_power_user_lmt == power) {
@@ -1650,7 +1649,6 @@ il3945_hw_reg_set_txpower(struct il_priv *il, s8 power)
 
 	for (i = 0; i < il->channel_count; i++) {
 		ch_info = &il->channel_info[i];
-		a_band = il_is_channel_a_band(ch_info);
 
 		/* find minimum power of all user and regulatory constraints
 		 *    (does not consider h/w clipping limitations) */
diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
index 562e94870a9c..280cd8ae1696 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
@@ -1338,15 +1338,12 @@ il4965_accumulative_stats(struct il_priv *il, __le32 * stats)
 	u32 *accum_stats;
 	u32 *delta, *max_delta;
 	struct stats_general_common *general, *accum_general;
-	struct stats_tx *tx, *accum_tx;
 
 	prev_stats = (__le32 *) &il->_4965.stats;
 	accum_stats = (u32 *) &il->_4965.accum_stats;
 	size = sizeof(struct il_notif_stats);
 	general = &il->_4965.stats.general.common;
 	accum_general = &il->_4965.accum_stats.general.common;
-	tx = &il->_4965.stats.tx;
-	accum_tx = &il->_4965.accum_stats.tx;
 	delta = (u32 *) &il->_4965.delta_stats;
 	max_delta = (u32 *) &il->_4965.max_delta;
 
@@ -4784,7 +4781,6 @@ static void
 il4965_ucode_callback(const struct firmware *ucode_raw, void *context)
 {
 	struct il_priv *il = context;
-	struct il_ucode_header *ucode;
 	int err;
 	struct il4965_firmware_pieces pieces;
 	const unsigned int api_max = il->cfg->ucode_api_max;
@@ -4814,8 +4810,6 @@ il4965_ucode_callback(const struct firmware *ucode_raw, void *context)
 	}
 
 	/* Data from ucode file:  header followed by uCode images */
-	ucode = (struct il_ucode_header *)ucode_raw->data;
-
 	err = il4965_load_firmware(il, ucode_raw, &pieces);
 
 	if (err)
diff --git a/drivers/net/wireless/intel/iwlwifi/Makefile b/drivers/net/wireless/intel/iwlwifi/Makefile
index 4d08d78c6b71..04e376cc898c 100644
--- a/drivers/net/wireless/intel/iwlwifi/Makefile
+++ b/drivers/net/wireless/intel/iwlwifi/Makefile
@@ -7,13 +7,13 @@ iwlwifi-objs		+= iwl-debug.o
 iwlwifi-objs		+= iwl-eeprom-read.o iwl-eeprom-parse.o
 iwlwifi-objs		+= iwl-phy-db.o iwl-nvm-parse.o
 iwlwifi-objs		+= pcie/drv.o pcie/rx.o pcie/tx.o pcie/trans.o
-iwlwifi-objs		+= pcie/ctxt-info.o pcie/trans-gen2.o pcie/tx-gen2.o
+iwlwifi-objs		+= pcie/ctxt-info.o pcie/ctxt-info-gen3.o
+iwlwifi-objs		+= pcie/trans-gen2.o pcie/tx-gen2.o
 iwlwifi-$(CONFIG_IWLDVM) += cfg/1000.o cfg/2000.o cfg/5000.o cfg/6000.o
 iwlwifi-$(CONFIG_IWLMVM) += cfg/7000.o cfg/8000.o cfg/9000.o cfg/22000.o
 iwlwifi-objs		+= iwl-trans.o
 iwlwifi-objs		+= fw/notif-wait.o
 iwlwifi-$(CONFIG_IWLMVM) += fw/paging.o fw/smem.o fw/init.o fw/dbg.o
-iwlwifi-$(CONFIG_IWLMVM) += fw/common_rx.o
 iwlwifi-$(CONFIG_ACPI) += fw/acpi.o
 iwlwifi-$(CONFIG_IWLWIFI_DEBUGFS) += fw/debugfs.o
 
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/2000.c b/drivers/net/wireless/intel/iwlwifi/cfg/2000.c
index a63ca8820568..fedb108db68f 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/2000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/2000.c
@@ -63,6 +63,7 @@
 static const struct iwl_base_params iwl2000_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
+	.max_tfd_queue_size = 256,
 	.max_ll_items = OTP_MAX_LL_ITEMS_2x00,
 	.shadow_ram_support = true,
 	.led_compensation = 51,
@@ -76,6 +77,7 @@ static const struct iwl_base_params iwl2000_base_params = {
 static const struct iwl_base_params iwl2030_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
+	.max_tfd_queue_size = 256,
 	.max_ll_items = OTP_MAX_LL_ITEMS_2x00,
 	.shadow_ram_support = true,
 	.led_compensation = 57,
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index d4ba66aecdc9..91ca77c7571c 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -59,7 +59,7 @@
 #define IWL_22000_UCODE_API_MAX	38
 
 /* Lowest firmware API version supported */
-#define IWL_22000_UCODE_API_MIN	24
+#define IWL_22000_UCODE_API_MIN	39
 
 /* NVM versions */
 #define IWL_22000_NVM_VERSION		0x0a1d
@@ -73,29 +73,48 @@
 #define IWL_22000_SMEM_OFFSET		0x400000
 #define IWL_22000_SMEM_LEN		0xD0000
 
-#define IWL_22000_JF_FW_PRE	"iwlwifi-Qu-a0-jf-b0-"
-#define IWL_22000_HR_FW_PRE	"iwlwifi-Qu-a0-hr-a0-"
-#define IWL_22000_HR_CDB_FW_PRE	"iwlwifi-QuIcp-z0-hrcdb-a0-"
-#define IWL_22000_HR_F0_FW_PRE	"iwlwifi-QuQnj-f0-hr-a0-"
-#define IWL_22000_JF_B0_FW_PRE	"iwlwifi-QuQnj-a0-jf-b0-"
-#define IWL_22000_HR_A0_FW_PRE	"iwlwifi-QuQnj-a0-hr-a0-"
+#define IWL_22000_JF_FW_PRE		"iwlwifi-Qu-a0-jf-b0-"
+#define IWL_22000_HR_FW_PRE		"iwlwifi-Qu-a0-hr-a0-"
+#define IWL_22000_HR_CDB_FW_PRE		"iwlwifi-QuIcp-z0-hrcdb-a0-"
+#define IWL_22000_HR_A_F0_FW_PRE	"iwlwifi-QuQnj-f0-hr-a0-"
+#define IWL_22000_HR_B_FW_PRE		"iwlwifi-Qu-b0-hr-b0-"
+#define IWL_22000_JF_B0_FW_PRE		"iwlwifi-QuQnj-a0-jf-b0-"
+#define IWL_22000_HR_A0_FW_PRE		"iwlwifi-QuQnj-a0-hr-a0-"
+#define IWL_22000_SU_Z0_FW_PRE		"iwlwifi-su-z0-"
 
 #define IWL_22000_HR_MODULE_FIRMWARE(api) \
 	IWL_22000_HR_FW_PRE __stringify(api) ".ucode"
 #define IWL_22000_JF_MODULE_FIRMWARE(api) \
 	IWL_22000_JF_FW_PRE __stringify(api) ".ucode"
-#define IWL_22000_HR_F0_QNJ_MODULE_FIRMWARE(api) \
-	IWL_22000_HR_F0_FW_PRE __stringify(api) ".ucode"
+#define IWL_22000_HR_A_F0_QNJ_MODULE_FIRMWARE(api) \
+	IWL_22000_HR_A_F0_FW_PRE __stringify(api) ".ucode"
+#define IWL_22000_HR_B_QNJ_MODULE_FIRMWARE(api) \
+	IWL_22000_HR_B_FW_PRE __stringify(api) ".ucode"
 #define IWL_22000_JF_B0_QNJ_MODULE_FIRMWARE(api) \
 	IWL_22000_JF_B0_FW_PRE __stringify(api) ".ucode"
 #define IWL_22000_HR_A0_QNJ_MODULE_FIRMWARE(api) \
 	IWL_22000_HR_A0_FW_PRE __stringify(api) ".ucode"
+#define IWL_22000_SU_Z0_MODULE_FIRMWARE(api) \
+	IWL_22000_SU_Z0_FW_PRE __stringify(api) ".ucode"
 
 #define NVM_HW_SECTION_NUM_FAMILY_22000		10
 
 static const struct iwl_base_params iwl_22000_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_FAMILY_22000,
 	.num_of_queues = 512,
+	.max_tfd_queue_size = 256,
+	.shadow_ram_support = true,
+	.led_compensation = 57,
+	.wd_timeout = IWL_LONG_WD_TIMEOUT,
+	.max_event_log_size = 512,
+	.shadow_reg_enable = true,
+	.pcie_l1_allowed = true,
+};
+
+static const struct iwl_base_params iwl_22560_base_params = {
+	.eeprom_size = OTP_LOW_IMAGE_SIZE_FAMILY_22000,
+	.num_of_queues = 512,
+	.max_tfd_queue_size = 65536,
 	.shadow_ram_support = true,
 	.led_compensation = 57,
 	.wd_timeout = IWL_LONG_WD_TIMEOUT,
@@ -110,11 +129,9 @@ static const struct iwl_ht_params iwl_22000_ht_params = {
 	.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
 };
 
-#define IWL_DEVICE_22000						\
+#define IWL_DEVICE_22000_COMMON						\
 	.ucode_api_max = IWL_22000_UCODE_API_MAX,			\
 	.ucode_api_min = IWL_22000_UCODE_API_MIN,			\
-	.device_family = IWL_DEVICE_FAMILY_22000,			\
-	.base_params = &iwl_22000_base_params,				\
 	.led_mode = IWL_LED_RF_STATE,					\
 	.nvm_hw_section_num = NVM_HW_SECTION_NUM_FAMILY_22000,		\
 	.non_shared_ant = ANT_A,					\
@@ -129,6 +146,10 @@ static const struct iwl_ht_params iwl_22000_ht_params = {
 	.mq_rx_supported = true,					\
 	.vht_mu_mimo_supported = true,					\
 	.mac_addr_from_csr = true,					\
+	.ht_params = &iwl_22000_ht_params,				\
+	.nvm_ver = IWL_22000_NVM_VERSION,				\
+	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,			\
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,		\
 	.use_tfh = true,						\
 	.rf_id = true,							\
 	.gen2 = true,							\
@@ -136,86 +157,114 @@ static const struct iwl_ht_params iwl_22000_ht_params = {
 	.dbgc_supported = true,						\
 	.min_umac_error_event_table = 0x400000
 
+#define IWL_DEVICE_22500						\
+	IWL_DEVICE_22000_COMMON,					\
+	.device_family = IWL_DEVICE_FAMILY_22000,			\
+	.base_params = &iwl_22000_base_params,				\
+	.csr = &iwl_csr_v1
+
+#define IWL_DEVICE_22560						\
+	IWL_DEVICE_22000_COMMON,					\
+	.device_family = IWL_DEVICE_FAMILY_22560,			\
+	.base_params = &iwl_22560_base_params,				\
+	.csr = &iwl_csr_v2
+
 const struct iwl_cfg iwl22000_2ac_cfg_hr = {
 	.name = "Intel(R) Dual Band Wireless AC 22000",
 	.fw_name_pre = IWL_22000_HR_FW_PRE,
-	IWL_DEVICE_22000,
-	.csr = &iwl_csr_v1,
-	.ht_params = &iwl_22000_ht_params,
-	.nvm_ver = IWL_22000_NVM_VERSION,
-	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	IWL_DEVICE_22500,
 };
 
 const struct iwl_cfg iwl22000_2ac_cfg_hr_cdb = {
 	.name = "Intel(R) Dual Band Wireless AC 22000",
 	.fw_name_pre = IWL_22000_HR_CDB_FW_PRE,
-	IWL_DEVICE_22000,
-	.csr = &iwl_csr_v1,
-	.ht_params = &iwl_22000_ht_params,
-	.nvm_ver = IWL_22000_NVM_VERSION,
-	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	IWL_DEVICE_22500,
 	.cdb = true,
 };
 
 const struct iwl_cfg iwl22000_2ac_cfg_jf = {
 	.name = "Intel(R) Dual Band Wireless AC 22000",
 	.fw_name_pre = IWL_22000_JF_FW_PRE,
-	IWL_DEVICE_22000,
-	.csr = &iwl_csr_v1,
-	.ht_params = &iwl_22000_ht_params,
-	.nvm_ver = IWL_22000_NVM_VERSION,
-	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	IWL_DEVICE_22500,
 };
 
 const struct iwl_cfg iwl22000_2ax_cfg_hr = {
 	.name = "Intel(R) Dual Band Wireless AX 22000",
 	.fw_name_pre = IWL_22000_HR_FW_PRE,
-	IWL_DEVICE_22000,
-	.csr = &iwl_csr_v1,
-	.ht_params = &iwl_22000_ht_params,
-	.nvm_ver = IWL_22000_NVM_VERSION,
-	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	IWL_DEVICE_22500,
+	/*
+	 * This device doesn't support receiving BlockAck with a large bitmap
+	 * so we need to restrict the size of transmitted aggregation to the
+	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
+	 */
+	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
 };
 
-const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_f0 = {
+const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_a0_f0 = {
 	.name = "Intel(R) Dual Band Wireless AX 22000",
-	.fw_name_pre = IWL_22000_HR_F0_FW_PRE,
-	IWL_DEVICE_22000,
-	.csr = &iwl_csr_v1,
-	.ht_params = &iwl_22000_ht_params,
-	.nvm_ver = IWL_22000_NVM_VERSION,
-	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	.fw_name_pre = IWL_22000_HR_A_F0_FW_PRE,
+	IWL_DEVICE_22500,
+	/*
+	 * This device doesn't support receiving BlockAck with a large bitmap
+	 * so we need to restrict the size of transmitted aggregation to the
+	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
+	 */
+	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
+};
+
+const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_b0 = {
+	.name = "Intel(R) Dual Band Wireless AX 22000",
+	.fw_name_pre = IWL_22000_HR_B_FW_PRE,
+	IWL_DEVICE_22500,
+	/*
+	 * This device doesn't support receiving BlockAck with a large bitmap
+	 * so we need to restrict the size of transmitted aggregation to the
+	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
+	 */
+	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
 };
 
 const struct iwl_cfg iwl22000_2ax_cfg_qnj_jf_b0 = {
 	.name = "Intel(R) Dual Band Wireless AX 22000",
 	.fw_name_pre = IWL_22000_JF_B0_FW_PRE,
-	IWL_DEVICE_22000,
-	.csr = &iwl_csr_v1,
-	.ht_params = &iwl_22000_ht_params,
-	.nvm_ver = IWL_22000_NVM_VERSION,
-	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	IWL_DEVICE_22500,
+	/*
+	 * This device doesn't support receiving BlockAck with a large bitmap
+	 * so we need to restrict the size of transmitted aggregation to the
+	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
+	 */
+	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
 };
 
 const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_a0 = {
 	.name = "Intel(R) Dual Band Wireless AX 22000",
 	.fw_name_pre = IWL_22000_HR_A0_FW_PRE,
-	IWL_DEVICE_22000,
-	.csr = &iwl_csr_v1,
-	.ht_params = &iwl_22000_ht_params,
-	.nvm_ver = IWL_22000_NVM_VERSION,
-	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	IWL_DEVICE_22500,
+	/*
+	 * This device doesn't support receiving BlockAck with a large bitmap
+	 * so we need to restrict the size of transmitted aggregation to the
+	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
+	 */
+	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
+};
+
+const struct iwl_cfg iwl22560_2ax_cfg_su_cdb = {
+	.name = "Intel(R) Dual Band Wireless AX 22560",
+	.fw_name_pre = IWL_22000_SU_Z0_FW_PRE,
+	IWL_DEVICE_22560,
+	.cdb = true,
+	/*
+	 * This device doesn't support receiving BlockAck with a large bitmap
+	 * so we need to restrict the size of transmitted aggregation to the
+	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
+	 */
+	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
 };
 
 MODULE_FIRMWARE(IWL_22000_HR_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_22000_JF_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
-MODULE_FIRMWARE(IWL_22000_HR_F0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
+MODULE_FIRMWARE(IWL_22000_HR_A_F0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
+MODULE_FIRMWARE(IWL_22000_HR_B_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_22000_JF_B0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_22000_HR_A0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
+MODULE_FIRMWARE(IWL_22000_SU_Z0_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/5000.c b/drivers/net/wireless/intel/iwlwifi/cfg/5000.c
index a224f1be1ec2..36151e61a26f 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/5000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/5000.c
@@ -53,6 +53,7 @@
 static const struct iwl_base_params iwl5000_base_params = {
 	.eeprom_size = IWLAGN_EEPROM_IMG_SIZE,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
+	.max_tfd_queue_size = 256,
 	.pll_cfg = true,
 	.led_compensation = 51,
 	.wd_timeout = IWL_WATCHDOG_DISABLED,
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/6000.c b/drivers/net/wireless/intel/iwlwifi/cfg/6000.c
index dbcec7ce7863..b5d8274761d8 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/6000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/6000.c
@@ -72,6 +72,7 @@
 static const struct iwl_base_params iwl6000_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
+	.max_tfd_queue_size = 256,
 	.max_ll_items = OTP_MAX_LL_ITEMS_6x00,
 	.shadow_ram_support = true,
 	.led_compensation = 51,
@@ -84,6 +85,7 @@ static const struct iwl_base_params iwl6000_base_params = {
 static const struct iwl_base_params iwl6050_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
+	.max_tfd_queue_size = 256,
 	.max_ll_items = OTP_MAX_LL_ITEMS_6x50,
 	.shadow_ram_support = true,
 	.led_compensation = 51,
@@ -96,6 +98,7 @@ static const struct iwl_base_params iwl6050_base_params = {
 static const struct iwl_base_params iwl6000_g2_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
+	.max_tfd_queue_size = 256,
 	.max_ll_items = OTP_MAX_LL_ITEMS_6x00,
 	.shadow_ram_support = true,
 	.led_compensation = 57,
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/7000.c b/drivers/net/wireless/intel/iwlwifi/cfg/7000.c
index 69bfa827e82a..a62c8346f13a 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/7000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/7000.c
@@ -123,6 +123,7 @@
 static const struct iwl_base_params iwl7000_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_FAMILY_7000,
 	.num_of_queues = 31,
+	.max_tfd_queue_size = 256,
 	.shadow_ram_support = true,
 	.led_compensation = 57,
 	.wd_timeout = IWL_LONG_WD_TIMEOUT,
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/8000.c b/drivers/net/wireless/intel/iwlwifi/cfg/8000.c
index 7262e973e0d6..c46fa712985b 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/8000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/8000.c
@@ -104,6 +104,7 @@
 static const struct iwl_base_params iwl8000_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_FAMILY_8000,
 	.num_of_queues = 31,
+	.max_tfd_queue_size = 256,
 	.shadow_ram_support = true,
 	.led_compensation = 57,
 	.wd_timeout = IWL_LONG_WD_TIMEOUT,
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
index c8ea63d02619..24b2f7cbb308 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
@@ -95,6 +95,7 @@
 static const struct iwl_base_params iwl9000_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_FAMILY_9000,
 	.num_of_queues = 31,
+	.max_tfd_queue_size = 256,
 	.shadow_ram_support = true,
 	.led_compensation = 57,
 	.wd_timeout = IWL_LONG_WD_TIMEOUT,
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h b/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h
index 007bfe7656a4..08d3d8a190f6 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h
@@ -8,6 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright (C) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -30,6 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright (C) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -187,20 +189,4 @@ struct iwl_card_state_notif {
 	__le32 flags;
 } __packed; /* CARD_STATE_NTFY_API_S_VER_1 */
 
-/**
- * struct iwl_fseq_ver_mismatch_nty - Notification about version
- *
- * This notification does not have a direct impact on the init flow.
- * It means that another core (not WiFi) has initiated the FSEQ flow
- * and updated the FSEQ version.  The driver only prints an error when
- * this occurs.
- *
- * @aux_read_fseq_ver: auxiliary read FSEQ version
- * @wifi_fseq_ver: FSEQ version (embedded in WiFi)
- */
-struct iwl_fseq_ver_mismatch_ntf {
-	__le32 aux_read_fseq_ver;
-	__le32 wifi_fseq_ver;
-} __packed; /* FSEQ_VER_MISMATCH_NTFY_API_S_VER_1 */
-
 #endif /* __iwl_fw_api_alive_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
index f285bacc8726..6dad748e5cdc 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
@@ -193,7 +193,8 @@ enum iwl_legacy_cmds {
 	FW_GET_ITEM_CMD = 0x1a,
 
 	/**
-	 * @TX_CMD: uses &struct iwl_tx_cmd or &struct iwl_tx_cmd_gen2,
+	 * @TX_CMD: uses &struct iwl_tx_cmd or &struct iwl_tx_cmd_gen2 or
+	 *	&struct iwl_tx_cmd_gen3,
 	 *	response in &struct iwl_mvm_tx_resp or
 	 *	&struct iwl_mvm_tx_resp_v3
 	 */
@@ -646,13 +647,6 @@ enum iwl_system_subcmd_ids {
 	 * @INIT_EXTENDED_CFG_CMD: &struct iwl_init_extended_cfg_cmd
 	 */
 	INIT_EXTENDED_CFG_CMD = 0x03,
-
-	/**
-	 * @FSEQ_VER_MISMATCH_NTF: Notification about fseq version
-	 *	mismatch during init.  The format is specified in
-	 *	&struct iwl_fseq_ver_mismatch_ntf.
-	 */
-	FSEQ_VER_MISMATCH_NTF = 0xFF,
 };
 
 #endif /* __iwl_fw_api_commands_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
index 5f6e855006dd..59b3c6e8f37b 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
@@ -8,6 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright (C) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -30,6 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright (C) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -83,6 +85,16 @@ enum iwl_data_path_subcmd_ids {
 	TRIGGER_RX_QUEUES_NOTIF_CMD = 0x2,
 
 	/**
+	 * @STA_HE_CTXT_CMD: &struct iwl_he_sta_context_cmd
+	 */
+	STA_HE_CTXT_CMD = 0x7,
+
+	/**
+	 * @RFH_QUEUE_CONFIG_CMD: &struct iwl_rfh_queue_config
+	 */
+	RFH_QUEUE_CONFIG_CMD = 0xD,
+
+	/**
 	 * @TLC_MNG_CONFIG_CMD: &struct iwl_tlc_config_cmd
 	 */
 	TLC_MNG_CONFIG_CMD = 0xF,
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
index f2e31e040a7b..55594c93b014 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
@@ -7,6 +7,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2017        Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -28,6 +29,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2017        Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -279,6 +281,10 @@ enum iwl_mac_filter_flags {
 	MAC_FILTER_OUT_BCAST		= BIT(8),
 	MAC_FILTER_IN_CRC32		= BIT(11),
 	MAC_FILTER_IN_PROBE_REQUEST	= BIT(12),
+	/**
+	 * @MAC_FILTER_IN_11AX: mark BSS as supporting 802.11ax
+	 */
+	MAC_FILTER_IN_11AX		= BIT(14),
 };
 
 /**
@@ -406,4 +412,170 @@ struct iwl_missed_beacons_notif {
 	__le32 num_recvd_beacons;
 } __packed; /* MISSED_BEACON_NTFY_API_S_VER_3 */
 
+/**
+ * struct iwl_he_backoff_conf - used for backoff configuration
+ * Per each trigger-based AC, (set by MU EDCA Parameter set info-element)
+ * used for backoff configuration of TXF5..TXF8 trigger based.
+ * The MU-TIMER is reloaded w/ MU_TIME each time a frame from the AC is sent via
+ * trigger-based TX.
+ * @cwmin: CW min
+ * @cwmax: CW max
+ * @aifsn: AIFSN
+ *	AIFSN=0, means that no backoff from the specified TRIG-BASED AC is
+ *	allowed till the MU-TIMER is 0
+ * @mu_time: MU time in 8TU units
+ */
+struct iwl_he_backoff_conf {
+	__le16 cwmin;
+	__le16 cwmax;
+	__le16 aifsn;
+	__le16 mu_time;
+} __packed; /* AC_QOS_DOT11AX_API_S */
+
+#define MAX_HE_SUPP_NSS	2
+#define MAX_HE_CHANNEL_BW_INDX	4
+
+/**
+ * struct iwl_he_pkt_ext - QAM thresholds
+ * The required PPE is set via HE Capabilities IE, per Nss x BW x MCS
+ * The IE is organized in the following way:
+ * Support for Nss x BW (or RU) matrix:
+ *	(0=SISO, 1=MIMO2) x (0-20MHz, 1-40MHz, 2-80MHz, 3-160MHz)
+ * Each entry contains 2 QAM thresholds for 8us and 16us:
+ *	0=BPSK, 1=QPSK, 2=16QAM, 3=64QAM, 4=256QAM, 5=1024QAM, 6/7=RES
+ * i.e. QAM_th1 < QAM_th2 such if TX uses QAM_tx:
+ *	QAM_tx < QAM_th1            --> PPE=0us
+ *	QAM_th1 <= QAM_tx < QAM_th2 --> PPE=8us
+ *	QAM_th2 <= QAM_tx           --> PPE=16us
+ * @pkt_ext_qam_th: QAM thresholds
+ *	For each Nss/Bw define 2 QAM thrsholds (0..5)
+ *	For rates below the low_th, no need for PPE
+ *	For rates between low_th and high_th, need 8us PPE
+ *	For rates equal or higher then the high_th, need 16us PPE
+ *	Nss (0-siso, 1-mimo2) x BW (0-20MHz, 1-40MHz, 2-80MHz, 3-160MHz) x
+ *		(0-low_th, 1-high_th)
+ */
+struct iwl_he_pkt_ext {
+	u8 pkt_ext_qam_th[MAX_HE_SUPP_NSS][MAX_HE_CHANNEL_BW_INDX][2];
+} __packed; /* PKT_EXT_DOT11AX_API_S */
+
+/**
+ * enum iwl_he_sta_ctxt_flags - HE STA context flags
+ * @STA_CTXT_HE_REF_BSSID_VALID: ref bssid addr valid (for receiving specific
+ *	control frames such as TRIG, NDPA, BACK)
+ * @STA_CTXT_HE_BSS_COLOR_DIS: BSS color disable, don't use the BSS
+ *	color for RX filter but use MAC header
+ * @STA_CTXT_HE_PARTIAL_BSS_COLOR: partial BSS color allocation
+ * @STA_CTXT_HE_32BIT_BA_BITMAP: indicates the receiver supports BA bitmap
+ *	of 32-bits
+ * @STA_CTXT_HE_PACKET_EXT: indicates that the packet-extension info is valid
+ *	and should be used
+ * @STA_CTXT_HE_TRIG_RND_ALLOC: indicates that trigger based random allocation
+ *	is enabled according to UORA element existence
+ * @STA_CTXT_HE_CONST_TRIG_RND_ALLOC: used for AV testing
+ * @STA_CTXT_HE_ACK_ENABLED: indicates that the AP supports receiving ACK-
+ *	enabled AGG, i.e. both BACK and non-BACK frames in a single AGG
+ * @STA_CTXT_HE_MU_EDCA_CW: indicates that there is an element of MU EDCA
+ *	parameter set, i.e. the backoff counters for trig-based ACs
+ */
+enum iwl_he_sta_ctxt_flags {
+	STA_CTXT_HE_REF_BSSID_VALID		= BIT(4),
+	STA_CTXT_HE_BSS_COLOR_DIS		= BIT(5),
+	STA_CTXT_HE_PARTIAL_BSS_COLOR		= BIT(6),
+	STA_CTXT_HE_32BIT_BA_BITMAP		= BIT(7),
+	STA_CTXT_HE_PACKET_EXT			= BIT(8),
+	STA_CTXT_HE_TRIG_RND_ALLOC		= BIT(9),
+	STA_CTXT_HE_CONST_TRIG_RND_ALLOC	= BIT(10),
+	STA_CTXT_HE_ACK_ENABLED			= BIT(11),
+	STA_CTXT_HE_MU_EDCA_CW			= BIT(12),
+};
+
+/**
+ * enum iwl_he_htc_flags - HE HTC support flags
+ * @IWL_HE_HTC_SUPPORT: HE-HTC support
+ * @IWL_HE_HTC_UL_MU_RESP_SCHED: HE UL MU response schedule
+ *	support via A-control field
+ * @IWL_HE_HTC_BSR_SUPP: BSR support in A-control field
+ * @IWL_HE_HTC_OMI_SUPP: A-OMI support in A-control field
+ * @IWL_HE_HTC_BQR_SUPP: A-BQR support in A-control field
+ */
+enum iwl_he_htc_flags {
+	IWL_HE_HTC_SUPPORT			= BIT(0),
+	IWL_HE_HTC_UL_MU_RESP_SCHED		= BIT(3),
+	IWL_HE_HTC_BSR_SUPP			= BIT(4),
+	IWL_HE_HTC_OMI_SUPP			= BIT(5),
+	IWL_HE_HTC_BQR_SUPP			= BIT(6),
+};
+
+/*
+ * @IWL_HE_HTC_LINK_ADAP_NO_FEEDBACK: the STA does not provide HE MFB
+ * @IWL_HE_HTC_LINK_ADAP_UNSOLICITED: the STA provides only unsolicited HE MFB
+ * @IWL_HE_HTC_LINK_ADAP_BOTH: the STA is capable of providing HE MFB in
+ *      response to HE MRQ and if the STA provides unsolicited HE MFB
+ */
+#define IWL_HE_HTC_LINK_ADAP_POS		(1)
+#define IWL_HE_HTC_LINK_ADAP_NO_FEEDBACK	(0)
+#define IWL_HE_HTC_LINK_ADAP_UNSOLICITED	(2 << IWL_HE_HTC_LINK_ADAP_POS)
+#define IWL_HE_HTC_LINK_ADAP_BOTH		(3 << IWL_HE_HTC_LINK_ADAP_POS)
+
+/**
+ * struct iwl_he_sta_context_cmd - configure FW to work with HE AP
+ * @sta_id: STA id
+ * @tid_limit: max num of TIDs in TX HE-SU multi-TID agg
+ *	0 - bad value, 1 - multi-tid not supported, 2..8 - tid limit
+ * @reserved1: reserved byte for future use
+ * @reserved2: reserved byte for future use
+ * @flags: see %iwl_11ax_sta_ctxt_flags
+ * @ref_bssid_addr: reference BSSID used by the AP
+ * @reserved0: reserved 2 bytes for aligning the ref_bssid_addr field to 8 bytes
+ * @htc_flags: which features are supported in HTC
+ * @frag_flags: frag support in A-MSDU
+ * @frag_level: frag support level
+ * @frag_max_num: max num of "open" MSDUs in the receiver (in power of 2)
+ * @frag_min_size: min frag size (except last frag)
+ * @pkt_ext: optional, exists according to PPE-present bit in the HE-PHY capa
+ * @bss_color: 11ax AP ID that is used in the HE SIG-A to mark inter BSS frame
+ * @htc_trig_based_pkt_ext: default PE in 4us units
+ * @frame_time_rts_th: HE duration RTS threshold, in units of 32us
+ * @rand_alloc_ecwmin: random CWmin = 2**ECWmin-1
+ * @rand_alloc_ecwmax: random CWmax = 2**ECWmax-1
+ * @reserved3: reserved byte for future use
+ * @trig_based_txf: MU EDCA Parameter set for the trigger based traffic queues
+ */
+struct iwl_he_sta_context_cmd {
+	u8 sta_id;
+	u8 tid_limit;
+	u8 reserved1;
+	u8 reserved2;
+	__le32 flags;
+
+	/* The below fields are set via Multiple BSSID IE */
+	u8 ref_bssid_addr[6];
+	__le16 reserved0;
+
+	/* The below fields are set via HE-capabilities IE */
+	__le32 htc_flags;
+
+	u8 frag_flags;
+	u8 frag_level;
+	u8 frag_max_num;
+	u8 frag_min_size;
+
+	/* The below fields are set via PPE thresholds element */
+	struct iwl_he_pkt_ext pkt_ext;
+
+	/* The below fields are set via HE-Operation IE */
+	u8 bss_color;
+	u8 htc_trig_based_pkt_ext;
+	__le16 frame_time_rts_th;
+
+	/* Random access parameter set (i.e. RAPS) */
+	u8 rand_alloc_ecwmin;
+	u8 rand_alloc_ecwmax;
+	__le16 reserved3;
+
+	/* The below fields are set via MU EDCA parameter set element */
+	struct iwl_he_backoff_conf trig_based_txf[AC_NUM];
+} __packed; /* STA_CONTEXT_DOT11AX_API_S */
+
 #endif /* __iwl_fw_api_mac_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h
index 8d6dc9189985..6c5338364794 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h
@@ -195,7 +195,6 @@ struct iwl_nvm_get_info_general {
  * @NVM_MAC_SKU_FLAGS_BAND_5_2_ENABLED: true if 5.2 band enabled
  * @NVM_MAC_SKU_FLAGS_802_11N_ENABLED: true if 11n enabled
  * @NVM_MAC_SKU_FLAGS_802_11AC_ENABLED: true if 11ac enabled
- * @NVM_MAC_SKU_FLAGS_802_11AX_ENABLED: true if 11ax enabled
  * @NVM_MAC_SKU_FLAGS_MIMO_DISABLED: true if MIMO disabled
  * @NVM_MAC_SKU_FLAGS_WAPI_ENABLED: true if WAPI enabled
  * @NVM_MAC_SKU_FLAGS_REG_CHECK_ENABLED: true if regulatory checker enabled
@@ -206,6 +205,9 @@ enum iwl_nvm_mac_sku_flags {
 	NVM_MAC_SKU_FLAGS_BAND_5_2_ENABLED	= BIT(1),
 	NVM_MAC_SKU_FLAGS_802_11N_ENABLED	= BIT(2),
 	NVM_MAC_SKU_FLAGS_802_11AC_ENABLED	= BIT(3),
+	/**
+	 * @NVM_MAC_SKU_FLAGS_802_11AX_ENABLED: true if 11ax enabled
+	 */
 	NVM_MAC_SKU_FLAGS_802_11AX_ENABLED	= BIT(4),
 	NVM_MAC_SKU_FLAGS_MIMO_DISABLED		= BIT(5),
 	NVM_MAC_SKU_FLAGS_WAPI_ENABLED		= BIT(8),
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h b/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h
index 21e13a315421..087fae91baef 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h
@@ -314,8 +314,11 @@ enum {
 	IWL_RATE_MCS_8_INDEX,
 	IWL_RATE_MCS_9_INDEX,
 	IWL_LAST_VHT_RATE = IWL_RATE_MCS_9_INDEX,
+	IWL_RATE_MCS_10_INDEX,
+	IWL_RATE_MCS_11_INDEX,
+	IWL_LAST_HE_RATE = IWL_RATE_MCS_11_INDEX,
 	IWL_RATE_COUNT_LEGACY = IWL_LAST_NON_HT_RATE + 1,
-	IWL_RATE_COUNT = IWL_LAST_VHT_RATE + 1,
+	IWL_RATE_COUNT = IWL_LAST_HE_RATE + 1,
 };
 
 #define IWL_RATE_BIT_MSK(r) BIT(IWL_RATE_##r##M_INDEX)
@@ -440,8 +443,8 @@ enum {
 #define RATE_LEGACY_RATE_MSK 0xff
 
 /* Bit 10 - OFDM HE */
-#define RATE_MCS_OFDM_HE_POS		10
-#define RATE_MCS_OFDM_HE_MSK		BIT(RATE_MCS_OFDM_HE_POS)
+#define RATE_MCS_HE_POS		10
+#define RATE_MCS_HE_MSK		BIT(RATE_MCS_HE_POS)
 
 /*
  * Bit 11-12: (0) 20MHz, (1) 40MHz, (2) 80MHz, (3) 160MHz
@@ -482,15 +485,33 @@ enum {
 #define RATE_MCS_BF_MSK			(1 << RATE_MCS_BF_POS)
 
 /*
- * Bit 20-21: HE guard interval and LTF type.
- * (0) 1xLTF+1.6us, (1) 2xLTF+0.8us,
- * (2) 2xLTF+1.6us, (3) 4xLTF+3.2us
+ * Bit 20-21: HE LTF type and guard interval
+ * HE (ext) SU:
+ *	0			1xLTF+0.8us
+ *	1			2xLTF+0.8us
+ *	2			2xLTF+1.6us
+ *	3 & SGI (bit 13) clear	4xLTF+3.2us
+ *	3 & SGI (bit 13) set	4xLTF+0.8us
+ * HE MU:
+ *	0			4xLTF+0.8us
+ *	1			2xLTF+0.8us
+ *	2			2xLTF+1.6us
+ *	3			4xLTF+3.2us
+ * HE TRIG:
+ *	0			1xLTF+1.6us
+ *	1			2xLTF+1.6us
+ *	2			4xLTF+3.2us
+ *	3			(does not occur)
  */
 #define RATE_MCS_HE_GI_LTF_POS		20
 #define RATE_MCS_HE_GI_LTF_MSK		(3 << RATE_MCS_HE_GI_LTF_POS)
 
 /* Bit 22-23: HE type. (0) SU, (1) SU_EXT, (2) MU, (3) trigger based */
 #define RATE_MCS_HE_TYPE_POS		22
+#define RATE_MCS_HE_TYPE_SU		(0 << RATE_MCS_HE_TYPE_POS)
+#define RATE_MCS_HE_TYPE_EXT_SU		(1 << RATE_MCS_HE_TYPE_POS)
+#define RATE_MCS_HE_TYPE_MU		(2 << RATE_MCS_HE_TYPE_POS)
+#define RATE_MCS_HE_TYPE_TRIG		(3 << RATE_MCS_HE_TYPE_POS)
 #define RATE_MCS_HE_TYPE_MSK		(3 << RATE_MCS_HE_TYPE_POS)
 
 /* Bit 24-25: (0) 20MHz (no dup), (1) 2x20MHz, (2) 4x20MHz, 3 8x20MHz */
@@ -501,6 +522,9 @@ enum {
 #define RATE_MCS_LDPC_POS		27
 #define RATE_MCS_LDPC_MSK		(1 << RATE_MCS_LDPC_POS)
 
+/* Bit 28: (1) 106-tone RX (8 MHz RU), (0) normal bandwidth */
+#define RATE_MCS_HE_106T_POS		28
+#define RATE_MCS_HE_106T_MSK		(1 << RATE_MCS_HE_106T_POS)
 
 /* Link Quality definitions */
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
index 7e570c4a9df0..2f599353c885 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
@@ -8,6 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -30,6 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -343,6 +345,169 @@ enum iwl_rx_mpdu_mac_info {
 	IWL_RX_MPDU_PHY_PHY_INDEX_MASK		= 0xf0,
 };
 
+/*
+ * enum iwl_rx_he_phy - HE PHY data
+ */
+enum iwl_rx_he_phy {
+	IWL_RX_HE_PHY_BEAM_CHNG			= BIT(0),
+	IWL_RX_HE_PHY_UPLINK			= BIT(1),
+	IWL_RX_HE_PHY_BSS_COLOR_MASK		= 0xfc,
+	IWL_RX_HE_PHY_SPATIAL_REUSE_MASK	= 0xf00,
+	IWL_RX_HE_PHY_SU_EXT_BW10		= BIT(12),
+	IWL_RX_HE_PHY_TXOP_DUR_MASK		= 0xfe000,
+	IWL_RX_HE_PHY_LDPC_EXT_SYM		= BIT(20),
+	IWL_RX_HE_PHY_PRE_FEC_PAD_MASK		= 0x600000,
+	IWL_RX_HE_PHY_PE_DISAMBIG		= BIT(23),
+	IWL_RX_HE_PHY_DOPPLER			= BIT(24),
+	/* 6 bits reserved */
+	IWL_RX_HE_PHY_DELIM_EOF			= BIT(31),
+
+	/* second dword - MU data */
+	IWL_RX_HE_PHY_SIGB_COMPRESSION		= BIT_ULL(32 + 0),
+	IWL_RX_HE_PHY_SIBG_SYM_OR_USER_NUM_MASK	= 0x1e00000000ULL,
+	IWL_RX_HE_PHY_HE_LTF_NUM_MASK		= 0xe000000000ULL,
+	IWL_RX_HE_PHY_RU_ALLOC_SEC80		= BIT_ULL(32 + 8),
+	/* trigger encoded */
+	IWL_RX_HE_PHY_RU_ALLOC_MASK		= 0xfe0000000000ULL,
+	IWL_RX_HE_PHY_SIGB_MCS_MASK		= 0xf000000000000ULL,
+	/* 1 bit reserved */
+	IWL_RX_HE_PHY_SIGB_DCM			= BIT_ULL(32 + 21),
+	IWL_RX_HE_PHY_PREAMBLE_PUNC_TYPE_MASK	= 0xc0000000000000ULL,
+	/* 8 bits reserved */
+};
+
+/**
+ * struct iwl_rx_mpdu_desc_v1 - RX MPDU descriptor
+ */
+struct iwl_rx_mpdu_desc_v1 {
+	/* DW7 - carries rss_hash only when rpa_en == 1 */
+	/**
+	 * @rss_hash: RSS hash value
+	 */
+	__le32 rss_hash;
+	/* DW8 - carries filter_match only when rpa_en == 1 */
+	/**
+	 * @filter_match: filter match value
+	 */
+	__le32 filter_match;
+	/* DW9 */
+	/**
+	 * @rate_n_flags: RX rate/flags encoding
+	 */
+	__le32 rate_n_flags;
+	/* DW10 */
+	/**
+	 * @energy_a: energy chain A
+	 */
+	u8 energy_a;
+	/**
+	 * @energy_b: energy chain B
+	 */
+	u8 energy_b;
+	/**
+	 * @channel: channel number
+	 */
+	u8 channel;
+	/**
+	 * @mac_context: MAC context mask
+	 */
+	u8 mac_context;
+	/* DW11 */
+	/**
+	 * @gp2_on_air_rise: GP2 timer value on air rise (INA)
+	 */
+	__le32 gp2_on_air_rise;
+	/* DW12 & DW13 */
+	union {
+		/**
+		 * @tsf_on_air_rise:
+		 * TSF value on air rise (INA), only valid if
+		 * %IWL_RX_MPDU_PHY_TSF_OVERLOAD isn't set
+		 */
+		__le64 tsf_on_air_rise;
+		/**
+		 * @he_phy_data:
+		 * HE PHY data, see &enum iwl_rx_he_phy, valid
+		 * only if %IWL_RX_MPDU_PHY_TSF_OVERLOAD is set
+		 */
+		__le64 he_phy_data;
+	};
+} __packed;
+
+/**
+ * struct iwl_rx_mpdu_desc_v3 - RX MPDU descriptor
+ */
+struct iwl_rx_mpdu_desc_v3 {
+	/* DW7 - carries filter_match only when rpa_en == 1 */
+	/**
+	 * @filter_match: filter match value
+	 */
+	__le32 filter_match;
+	/* DW8 - carries rss_hash only when rpa_en == 1 */
+	/**
+	 * @rss_hash: RSS hash value
+	 */
+	__le32 rss_hash;
+	/* DW9 */
+	/**
+	 * @partial_hash: 31:0 ip/tcp header hash
+	 *	w/o some fields (such as IP SRC addr)
+	 */
+	__le32 partial_hash;
+	/* DW10 */
+	/**
+	 * @raw_xsum: raw xsum value
+	 */
+	__le32 raw_xsum;
+	/* DW11 */
+	/**
+	 * @rate_n_flags: RX rate/flags encoding
+	 */
+	__le32 rate_n_flags;
+	/* DW12 */
+	/**
+	 * @energy_a: energy chain A
+	 */
+	u8 energy_a;
+	/**
+	 * @energy_b: energy chain B
+	 */
+	u8 energy_b;
+	/**
+	 * @channel: channel number
+	 */
+	u8 channel;
+	/**
+	 * @mac_context: MAC context mask
+	 */
+	u8 mac_context;
+	/* DW13 */
+	/**
+	 * @gp2_on_air_rise: GP2 timer value on air rise (INA)
+	 */
+	__le32 gp2_on_air_rise;
+	/* DW14 & DW15 */
+	union {
+		/**
+		 * @tsf_on_air_rise:
+		 * TSF value on air rise (INA), only valid if
+		 * %IWL_RX_MPDU_PHY_TSF_OVERLOAD isn't set
+		 */
+		__le64 tsf_on_air_rise;
+		/**
+		 * @he_phy_data:
+		 * HE PHY data, see &enum iwl_rx_he_phy, valid
+		 * only if %IWL_RX_MPDU_PHY_TSF_OVERLOAD is set
+		 */
+		__le64 he_phy_data;
+	};
+	/* DW16 & DW17 */
+	/**
+	 * @reserved: reserved
+	 */
+	__le32 reserved[2];
+} __packed; /* RX_MPDU_RES_START_API_S_VER_3 */
+
 /**
  * struct iwl_rx_mpdu_desc - RX MPDU descriptor
  */
@@ -400,51 +565,14 @@ struct iwl_rx_mpdu_desc {
 	 * @reorder_data: &enum iwl_rx_mpdu_reorder_data
 	 */
 	__le32 reorder_data;
-	/* DW7 - carries rss_hash only when rpa_en == 1 */
-	/**
-	 * @rss_hash: RSS hash value
-	 */
-	__le32 rss_hash;
-	/* DW8 - carries filter_match only when rpa_en == 1 */
-	/**
-	 * @filter_match: filter match value
-	 */
-	__le32 filter_match;
-	/* DW9 */
-	/**
-	 * @rate_n_flags: RX rate/flags encoding
-	 */
-	__le32 rate_n_flags;
-	/* DW10 */
-	/**
-	 * @energy_a: energy chain A
-	 */
-	u8 energy_a;
-	/**
-	 * @energy_b: energy chain B
-	 */
-	u8 energy_b;
-	/**
-	 * @channel: channel number
-	 */
-	u8 channel;
-	/**
-	 * @mac_context: MAC context mask
-	 */
-	u8 mac_context;
-	/* DW11 */
-	/**
-	 * @gp2_on_air_rise: GP2 timer value on air rise (INA)
-	 */
-	__le32 gp2_on_air_rise;
-	/* DW12 & DW13 */
-	/**
-	 * @tsf_on_air_rise:
-	 * TSF value on air rise (INA), only valid if
-	 * %IWL_RX_MPDU_PHY_TSF_OVERLOAD isn't set
-	 */
-	__le64 tsf_on_air_rise;
-} __packed;
+
+	union {
+		struct iwl_rx_mpdu_desc_v1 v1;
+		struct iwl_rx_mpdu_desc_v3 v3;
+	};
+} __packed; /* RX_MPDU_RES_START_API_S_VER_3 */
+
+#define IWL_RX_DESC_SIZE_V1 offsetofend(struct iwl_rx_mpdu_desc, v1)
 
 struct iwl_frame_release {
 	u8 baid;
@@ -587,4 +715,36 @@ struct iwl_ba_window_status_notif {
 	__le16 mpdu_rx_count[BA_WINDOW_STREAMS_MAX];
 } __packed; /* BA_WINDOW_STATUS_NTFY_API_S_VER_1 */
 
+/**
+ * struct iwl_rfh_queue_config - RX queue configuration
+ * @q_num: Q num
+ * @enable: enable queue
+ * @reserved: alignment
+ * @urbd_stts_wrptr: DMA address of urbd_stts_wrptr
+ * @fr_bd_cb: DMA address of freeRB table
+ * @ur_bd_cb: DMA address of used RB table
+ * @fr_bd_wid: Initial index of the free table
+ */
+struct iwl_rfh_queue_data {
+	u8 q_num;
+	u8 enable;
+	__le16 reserved;
+	__le64 urbd_stts_wrptr;
+	__le64 fr_bd_cb;
+	__le64 ur_bd_cb;
+	__le32 fr_bd_wid;
+} __packed; /* RFH_QUEUE_CONFIG_S_VER_1 */
+
+/**
+ * struct iwl_rfh_queue_config - RX queue configuration
+ * @num_queues: number of queues configured
+ * @reserved: alignment
+ * @data: DMA addresses per-queue
+ */
+struct iwl_rfh_queue_config {
+	u8 num_queues;
+	u8 reserved[3];
+	struct iwl_rfh_queue_data data[];
+} __packed; /* RFH_QUEUE_CONFIG_API_S_VER_1 */
+
 #endif /* __iwl_fw_api_rx_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h
index a2a40b515a3c..514b86123d3d 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h
@@ -7,6 +7,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -28,6 +29,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -320,6 +322,29 @@ struct iwl_tx_cmd_gen2 {
 	struct ieee80211_hdr hdr[0];
 } __packed; /* TX_CMD_API_S_VER_7 */
 
+/**
+ * struct iwl_tx_cmd_gen3 - TX command struct to FW for 22560 devices
+ * ( TX_CMD = 0x1c )
+ * @len: in bytes of the payload, see below for details
+ * @flags: combination of &enum iwl_tx_cmd_flags
+ * @offload_assist: TX offload configuration
+ * @dram_info: FW internal DRAM storage
+ * @rate_n_flags: rate for *all* Tx attempts, if TX_CMD_FLG_STA_RATE_MSK is
+ *	cleared. Combination of RATE_MCS_*
+ * @ttl: time to live - packet lifetime limit. The FW should drop if
+ *	passed.
+ * @hdr: 802.11 header
+ */
+struct iwl_tx_cmd_gen3 {
+	__le16 len;
+	__le16 flags;
+	__le32 offload_assist;
+	struct iwl_dram_sec_info dram_info;
+	__le32 rate_n_flags;
+	__le64 ttl;
+	struct ieee80211_hdr hdr[0];
+} __packed; /* TX_CMD_API_S_VER_8 */
+
 /*
  * TX response related data
  */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/common_rx.c b/drivers/net/wireless/intel/iwlwifi/fw/common_rx.c
deleted file mode 100644
index 6f75985eea66..000000000000
--- a/drivers/net/wireless/intel/iwlwifi/fw/common_rx.c
+++ /dev/null
@@ -1,88 +0,0 @@
-/******************************************************************************
- *
- * This file is provided under a dual BSD/GPLv2 license.  When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2017 Intel Deutschland GmbH
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * The full GNU General Public License is included in this distribution
- * in the file called COPYING.
- *
- * Contact Information:
- *  Intel Linux Wireless <linuxwifi@intel.com>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- * BSD LICENSE
- *
- * Copyright(c) 2017 Intel Deutschland GmbH
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- *  * Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- *  * Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in
- *    the documentation and/or other materials provided with the
- *    distribution.
- *  * Neither the name Intel Corporation nor the names of its
- *    contributors may be used to endorse or promote products derived
- *    from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- *****************************************************************************/
-#include "iwl-drv.h"
-#include "runtime.h"
-#include "fw/api/commands.h"
-#include "fw/api/alive.h"
-
-static void iwl_fwrt_fseq_ver_mismatch(struct iwl_fw_runtime *fwrt,
-				       struct iwl_rx_cmd_buffer *rxb)
-{
-	struct iwl_rx_packet *pkt = rxb_addr(rxb);
-	struct iwl_fseq_ver_mismatch_ntf *fseq = (void *)pkt->data;
-
-	IWL_ERR(fwrt, "FSEQ version mismatch (aux: %d, wifi: %d)\n",
-		__le32_to_cpu(fseq->aux_read_fseq_ver),
-		__le32_to_cpu(fseq->wifi_fseq_ver));
-}
-
-void iwl_fwrt_handle_notification(struct iwl_fw_runtime *fwrt,
-				  struct iwl_rx_cmd_buffer *rxb)
-{
-	struct iwl_rx_packet *pkt = rxb_addr(rxb);
-	u32 cmd = WIDE_ID(pkt->hdr.group_id, pkt->hdr.cmd);
-
-	switch (cmd) {
-	case WIDE_ID(SYSTEM_GROUP, FSEQ_VER_MISMATCH_NTF):
-		iwl_fwrt_fseq_ver_mismatch(fwrt, rxb);
-		break;
-	default:
-		break;
-	}
-}
-IWL_EXPORT_SYMBOL(iwl_fwrt_handle_notification);
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index fa283285fcbe..a31a42e673c4 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -243,39 +243,47 @@ static void iwl_fw_dump_fifos(struct iwl_fw_runtime *fwrt,
 	if (!iwl_trans_grab_nic_access(fwrt->trans, &flags))
 		return;
 
-	/* Pull RXF1 */
-	iwl_fwrt_dump_rxf(fwrt, dump_data, cfg->lmac[0].rxfifo1_size, 0, 0);
-	/* Pull RXF2 */
-	iwl_fwrt_dump_rxf(fwrt, dump_data, cfg->rxfifo2_size,
-			  RXF_DIFF_FROM_PREV, 1);
-	/* Pull LMAC2 RXF1 */
-	if (fwrt->smem_cfg.num_lmacs > 1)
-		iwl_fwrt_dump_rxf(fwrt, dump_data, cfg->lmac[1].rxfifo1_size,
-				  LMAC2_PRPH_OFFSET, 2);
-
-	/* Pull TXF data from LMAC1 */
-	for (i = 0; i < fwrt->smem_cfg.num_txfifo_entries; i++) {
-		/* Mark the number of TXF we're pulling now */
-		iwl_trans_write_prph(fwrt->trans, TXF_LARC_NUM, i);
-		iwl_fwrt_dump_txf(fwrt, dump_data, cfg->lmac[0].txfifo_size[i],
-				  0, i);
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_RXF)) {
+		/* Pull RXF1 */
+		iwl_fwrt_dump_rxf(fwrt, dump_data,
+				  cfg->lmac[0].rxfifo1_size, 0, 0);
+		/* Pull RXF2 */
+		iwl_fwrt_dump_rxf(fwrt, dump_data, cfg->rxfifo2_size,
+				  RXF_DIFF_FROM_PREV, 1);
+		/* Pull LMAC2 RXF1 */
+		if (fwrt->smem_cfg.num_lmacs > 1)
+			iwl_fwrt_dump_rxf(fwrt, dump_data,
+					  cfg->lmac[1].rxfifo1_size,
+					  LMAC2_PRPH_OFFSET, 2);
 	}
 
-	/* Pull TXF data from LMAC2 */
-	if (fwrt->smem_cfg.num_lmacs > 1) {
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_TXF)) {
+		/* Pull TXF data from LMAC1 */
 		for (i = 0; i < fwrt->smem_cfg.num_txfifo_entries; i++) {
 			/* Mark the number of TXF we're pulling now */
-			iwl_trans_write_prph(fwrt->trans,
-					     TXF_LARC_NUM + LMAC2_PRPH_OFFSET,
-					     i);
+			iwl_trans_write_prph(fwrt->trans, TXF_LARC_NUM, i);
 			iwl_fwrt_dump_txf(fwrt, dump_data,
-					  cfg->lmac[1].txfifo_size[i],
-					  LMAC2_PRPH_OFFSET,
-					  i + cfg->num_txfifo_entries);
+					  cfg->lmac[0].txfifo_size[i], 0, i);
+		}
+
+		/* Pull TXF data from LMAC2 */
+		if (fwrt->smem_cfg.num_lmacs > 1) {
+			for (i = 0; i < fwrt->smem_cfg.num_txfifo_entries;
+			     i++) {
+				/* Mark the number of TXF we're pulling now */
+				iwl_trans_write_prph(fwrt->trans,
+						     TXF_LARC_NUM +
+						     LMAC2_PRPH_OFFSET, i);
+				iwl_fwrt_dump_txf(fwrt, dump_data,
+						  cfg->lmac[1].txfifo_size[i],
+						  LMAC2_PRPH_OFFSET,
+						  i + cfg->num_txfifo_entries);
+			}
 		}
 	}
 
-	if (fw_has_capa(&fwrt->fw->ucode_capa,
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_INTERNAL_TXF) &&
+	    fw_has_capa(&fwrt->fw->ucode_capa,
 			IWL_UCODE_TLV_CAPA_EXTEND_SHARED_MEM_CFG)) {
 		/* Pull UMAC internal TXF data from all TXFs */
 		for (i = 0;
@@ -600,42 +608,54 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 	if (test_bit(STATUS_FW_ERROR, &fwrt->trans->status)) {
 		fifo_data_len = 0;
 
-		/* Count RXF2 size */
-		if (mem_cfg->rxfifo2_size) {
-			/* Add header info */
-			fifo_data_len += mem_cfg->rxfifo2_size +
-					 sizeof(*dump_data) +
-					 sizeof(struct iwl_fw_error_dump_fifo);
-		}
-
-		/* Count RXF1 sizes */
-		for (i = 0; i < mem_cfg->num_lmacs; i++) {
-			if (!mem_cfg->lmac[i].rxfifo1_size)
-				continue;
-
-			/* Add header info */
-			fifo_data_len += mem_cfg->lmac[i].rxfifo1_size +
-					 sizeof(*dump_data) +
-					 sizeof(struct iwl_fw_error_dump_fifo);
-		}
+		if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_RXF)) {
 
-		/* Count TXF sizes */
-		for (i = 0; i < mem_cfg->num_lmacs; i++) {
-			int j;
+			/* Count RXF2 size */
+			if (mem_cfg->rxfifo2_size) {
+				/* Add header info */
+				fifo_data_len +=
+					mem_cfg->rxfifo2_size +
+					sizeof(*dump_data) +
+					sizeof(struct iwl_fw_error_dump_fifo);
+			}
 
-			for (j = 0; j < mem_cfg->num_txfifo_entries; j++) {
-				if (!mem_cfg->lmac[i].txfifo_size[j])
+			/* Count RXF1 sizes */
+			for (i = 0; i < mem_cfg->num_lmacs; i++) {
+				if (!mem_cfg->lmac[i].rxfifo1_size)
 					continue;
 
 				/* Add header info */
 				fifo_data_len +=
-					mem_cfg->lmac[i].txfifo_size[j] +
+					mem_cfg->lmac[i].rxfifo1_size +
 					sizeof(*dump_data) +
 					sizeof(struct iwl_fw_error_dump_fifo);
 			}
 		}
 
-		if (fw_has_capa(&fwrt->fw->ucode_capa,
+		if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_TXF)) {
+			size_t fifo_const_len = sizeof(*dump_data) +
+				sizeof(struct iwl_fw_error_dump_fifo);
+
+			/* Count TXF sizes */
+			for (i = 0; i < mem_cfg->num_lmacs; i++) {
+				int j;
+
+				for (j = 0; j < mem_cfg->num_txfifo_entries;
+				     j++) {
+					if (!mem_cfg->lmac[i].txfifo_size[j])
+						continue;
+
+					/* Add header info */
+					fifo_data_len +=
+						fifo_const_len +
+						mem_cfg->lmac[i].txfifo_size[j];
+				}
+			}
+		}
+
+		if ((fwrt->fw->dbg_dump_mask &
+		    BIT(IWL_FW_ERROR_DUMP_INTERNAL_TXF)) &&
+		    fw_has_capa(&fwrt->fw->ucode_capa,
 				IWL_UCODE_TLV_CAPA_EXTEND_SHARED_MEM_CFG)) {
 			for (i = 0;
 			     i < ARRAY_SIZE(mem_cfg->internal_txfifo_size);
@@ -652,7 +672,8 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 		}
 
 		/* Make room for PRPH registers */
-		if (!fwrt->trans->cfg->gen2) {
+		if (!fwrt->trans->cfg->gen2 &&
+		    fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_PRPH)) {
 			for (i = 0; i < ARRAY_SIZE(iwl_prph_dump_addr_comm);
 			     i++) {
 				/* The range includes both boundaries */
@@ -667,7 +688,8 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 		}
 
 		if (!fwrt->trans->cfg->gen2 &&
-		    fwrt->trans->cfg->mq_rx_supported) {
+		    fwrt->trans->cfg->mq_rx_supported &&
+		    fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_PRPH)) {
 			for (i = 0; i <
 				ARRAY_SIZE(iwl_prph_dump_addr_9000); i++) {
 				/* The range includes both boundaries */
@@ -681,34 +703,42 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 			}
 		}
 
-		if (fwrt->trans->cfg->device_family == IWL_DEVICE_FAMILY_7000)
+		if (fwrt->trans->cfg->device_family == IWL_DEVICE_FAMILY_7000 &&
+		    fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_RADIO_REG))
 			radio_len = sizeof(*dump_data) + RADIO_REG_MAX_READ;
 	}
 
 	file_len = sizeof(*dump_file) +
-		   sizeof(*dump_data) * 3 +
-		   sizeof(*dump_smem_cfg) +
 		   fifo_data_len +
 		   prph_len +
-		   radio_len +
-		   sizeof(*dump_info);
-
-	/* Make room for the SMEM, if it exists */
-	if (smem_len)
-		file_len += sizeof(*dump_data) + sizeof(*dump_mem) + smem_len;
-
-	/* Make room for the secondary SRAM, if it exists */
-	if (sram2_len)
-		file_len += sizeof(*dump_data) + sizeof(*dump_mem) + sram2_len;
-
-	/* Make room for MEM segments */
-	for (i = 0; i < fwrt->fw->n_dbg_mem_tlv; i++) {
-		file_len += sizeof(*dump_data) + sizeof(*dump_mem) +
-			    le32_to_cpu(fw_dbg_mem[i].len);
+		   radio_len;
+
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_DEV_FW_INFO))
+		file_len += sizeof(*dump_data) + sizeof(*dump_info);
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM_CFG))
+		file_len += sizeof(*dump_data) + sizeof(*dump_smem_cfg);
+
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM)) {
+		/* Make room for the SMEM, if it exists */
+		if (smem_len)
+			file_len += sizeof(*dump_data) + sizeof(*dump_mem) +
+				smem_len;
+
+		/* Make room for the secondary SRAM, if it exists */
+		if (sram2_len)
+			file_len += sizeof(*dump_data) + sizeof(*dump_mem) +
+				sram2_len;
+
+		/* Make room for MEM segments */
+		for (i = 0; i < fwrt->fw->n_dbg_mem_tlv; i++) {
+			file_len += sizeof(*dump_data) + sizeof(*dump_mem) +
+				    le32_to_cpu(fw_dbg_mem[i].len);
+		}
 	}
 
 	/* Make room for fw's virtual image pages, if it exists */
-	if (!fwrt->trans->cfg->gen2 &&
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_PAGING) &&
+	    !fwrt->trans->cfg->gen2 &&
 	    fwrt->fw->img[fwrt->cur_fw_img].paging_mem_size &&
 	    fwrt->fw_paging_db[0].fw_paging_block)
 		file_len += fwrt->num_of_paging_blk *
@@ -722,12 +752,14 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 			   sizeof(*dump_info) + sizeof(*dump_smem_cfg);
 	}
 
-	if (fwrt->dump.desc)
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_ERROR_INFO) &&
+	    fwrt->dump.desc)
 		file_len += sizeof(*dump_data) + sizeof(*dump_trig) +
 			    fwrt->dump.desc->len;
 
-	if (!fwrt->fw->n_dbg_mem_tlv)
-		file_len += sram_len + sizeof(*dump_mem);
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM) &&
+	    !fwrt->fw->n_dbg_mem_tlv)
+		file_len += sizeof(*dump_data) + sram_len + sizeof(*dump_mem);
 
 	dump_file = vzalloc(file_len);
 	if (!dump_file) {
@@ -740,48 +772,56 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 	dump_file->barker = cpu_to_le32(IWL_FW_ERROR_DUMP_BARKER);
 	dump_data = (void *)dump_file->data;
 
-	dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_DEV_FW_INFO);
-	dump_data->len = cpu_to_le32(sizeof(*dump_info));
-	dump_info = (void *)dump_data->data;
-	dump_info->device_family =
-		fwrt->trans->cfg->device_family == IWL_DEVICE_FAMILY_7000 ?
-			cpu_to_le32(IWL_FW_ERROR_DUMP_FAMILY_7) :
-			cpu_to_le32(IWL_FW_ERROR_DUMP_FAMILY_8);
-	dump_info->hw_step = cpu_to_le32(CSR_HW_REV_STEP(fwrt->trans->hw_rev));
-	memcpy(dump_info->fw_human_readable, fwrt->fw->human_readable,
-	       sizeof(dump_info->fw_human_readable));
-	strncpy(dump_info->dev_human_readable, fwrt->trans->cfg->name,
-		sizeof(dump_info->dev_human_readable));
-	strncpy(dump_info->bus_human_readable, fwrt->dev->bus->name,
-		sizeof(dump_info->bus_human_readable));
-
-	dump_data = iwl_fw_error_next_data(dump_data);
-
-	/* Dump shared memory configuration */
-	dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_MEM_CFG);
-	dump_data->len = cpu_to_le32(sizeof(*dump_smem_cfg));
-	dump_smem_cfg = (void *)dump_data->data;
-	dump_smem_cfg->num_lmacs = cpu_to_le32(mem_cfg->num_lmacs);
-	dump_smem_cfg->num_txfifo_entries =
-		cpu_to_le32(mem_cfg->num_txfifo_entries);
-	for (i = 0; i < MAX_NUM_LMAC; i++) {
-		int j;
-
-		for (j = 0; j < TX_FIFO_MAX_NUM; j++)
-			dump_smem_cfg->lmac[i].txfifo_size[j] =
-				cpu_to_le32(mem_cfg->lmac[i].txfifo_size[j]);
-		dump_smem_cfg->lmac[i].rxfifo1_size =
-			cpu_to_le32(mem_cfg->lmac[i].rxfifo1_size);
-	}
-	dump_smem_cfg->rxfifo2_size = cpu_to_le32(mem_cfg->rxfifo2_size);
-	dump_smem_cfg->internal_txfifo_addr =
-		cpu_to_le32(mem_cfg->internal_txfifo_addr);
-	for (i = 0; i < TX_FIFO_INTERNAL_MAX_NUM; i++) {
-		dump_smem_cfg->internal_txfifo_size[i] =
-			cpu_to_le32(mem_cfg->internal_txfifo_size[i]);
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_DEV_FW_INFO)) {
+		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_DEV_FW_INFO);
+		dump_data->len = cpu_to_le32(sizeof(*dump_info));
+		dump_info = (void *)dump_data->data;
+		dump_info->device_family =
+			fwrt->trans->cfg->device_family ==
+			IWL_DEVICE_FAMILY_7000 ?
+				cpu_to_le32(IWL_FW_ERROR_DUMP_FAMILY_7) :
+				cpu_to_le32(IWL_FW_ERROR_DUMP_FAMILY_8);
+		dump_info->hw_step =
+			cpu_to_le32(CSR_HW_REV_STEP(fwrt->trans->hw_rev));
+		memcpy(dump_info->fw_human_readable, fwrt->fw->human_readable,
+		       sizeof(dump_info->fw_human_readable));
+		strncpy(dump_info->dev_human_readable, fwrt->trans->cfg->name,
+			sizeof(dump_info->dev_human_readable) - 1);
+		strncpy(dump_info->bus_human_readable, fwrt->dev->bus->name,
+			sizeof(dump_info->bus_human_readable) - 1);
+
+		dump_data = iwl_fw_error_next_data(dump_data);
 	}
 
-	dump_data = iwl_fw_error_next_data(dump_data);
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM_CFG)) {
+		/* Dump shared memory configuration */
+		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_MEM_CFG);
+		dump_data->len = cpu_to_le32(sizeof(*dump_smem_cfg));
+		dump_smem_cfg = (void *)dump_data->data;
+		dump_smem_cfg->num_lmacs = cpu_to_le32(mem_cfg->num_lmacs);
+		dump_smem_cfg->num_txfifo_entries =
+			cpu_to_le32(mem_cfg->num_txfifo_entries);
+		for (i = 0; i < MAX_NUM_LMAC; i++) {
+			int j;
+			u32 *txf_size = mem_cfg->lmac[i].txfifo_size;
+
+			for (j = 0; j < TX_FIFO_MAX_NUM; j++)
+				dump_smem_cfg->lmac[i].txfifo_size[j] =
+					cpu_to_le32(txf_size[j]);
+			dump_smem_cfg->lmac[i].rxfifo1_size =
+				cpu_to_le32(mem_cfg->lmac[i].rxfifo1_size);
+		}
+		dump_smem_cfg->rxfifo2_size =
+			cpu_to_le32(mem_cfg->rxfifo2_size);
+		dump_smem_cfg->internal_txfifo_addr =
+			cpu_to_le32(mem_cfg->internal_txfifo_addr);
+		for (i = 0; i < TX_FIFO_INTERNAL_MAX_NUM; i++) {
+			dump_smem_cfg->internal_txfifo_size[i] =
+				cpu_to_le32(mem_cfg->internal_txfifo_size[i]);
+		}
+
+		dump_data = iwl_fw_error_next_data(dump_data);
+	}
 
 	/* We only dump the FIFOs if the FW is in error state */
 	if (test_bit(STATUS_FW_ERROR, &fwrt->trans->status)) {
@@ -790,7 +830,8 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 			iwl_read_radio_regs(fwrt, &dump_data);
 	}
 
-	if (fwrt->dump.desc) {
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_ERROR_INFO) &&
+	    fwrt->dump.desc) {
 		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_ERROR_INFO);
 		dump_data->len = cpu_to_le32(sizeof(*dump_trig) +
 					     fwrt->dump.desc->len);
@@ -805,7 +846,8 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 	if (monitor_dump_only)
 		goto dump_trans_data;
 
-	if (!fwrt->fw->n_dbg_mem_tlv) {
+	if (!fwrt->fw->n_dbg_mem_tlv &&
+	    fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM)) {
 		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_MEM);
 		dump_data->len = cpu_to_le32(sram_len + sizeof(*dump_mem));
 		dump_mem = (void *)dump_data->data;
@@ -821,6 +863,9 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 		u32 ofs = le32_to_cpu(fw_dbg_mem[i].ofs);
 		bool success;
 
+		if (!(fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM)))
+			break;
+
 		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_MEM);
 		dump_data->len = cpu_to_le32(len + sizeof(*dump_mem));
 		dump_mem = (void *)dump_data->data;
@@ -854,7 +899,7 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 			dump_data = iwl_fw_error_next_data(dump_data);
 	}
 
-	if (smem_len) {
+	if (smem_len && fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM)) {
 		IWL_DEBUG_INFO(fwrt, "WRT SMEM dump\n");
 		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_MEM);
 		dump_data->len = cpu_to_le32(smem_len + sizeof(*dump_mem));
@@ -867,7 +912,7 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 		dump_data = iwl_fw_error_next_data(dump_data);
 	}
 
-	if (sram2_len) {
+	if (sram2_len && fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM)) {
 		IWL_DEBUG_INFO(fwrt, "WRT SRAM dump\n");
 		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_MEM);
 		dump_data->len = cpu_to_le32(sram2_len + sizeof(*dump_mem));
@@ -881,7 +926,8 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 	}
 
 	/* Dump fw's virtual image */
-	if (!fwrt->trans->cfg->gen2 &&
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_PAGING) &&
+	    !fwrt->trans->cfg->gen2 &&
 	    fwrt->fw->img[fwrt->cur_fw_img].paging_mem_size &&
 	    fwrt->fw_paging_db[0].fw_paging_block) {
 		IWL_DEBUG_INFO(fwrt, "WRT paging dump\n");
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h
index 9d939cbaf6c6..bbf2b265a06a 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/file.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h
@@ -146,6 +146,9 @@ enum iwl_ucode_tlv_type {
 	IWL_UCODE_TLV_FW_GSCAN_CAPA	= 50,
 	IWL_UCODE_TLV_FW_MEM_SEG	= 51,
 	IWL_UCODE_TLV_IML		= 52,
+
+	/* TLVs 0x1000-0x2000 are for internal driver usage */
+	IWL_UCODE_TLV_FW_DBG_DUMP_LST	= 0x1000,
 };
 
 struct iwl_ucode_tlv {
@@ -318,7 +321,7 @@ typedef unsigned int __bitwise iwl_ucode_tlv_capa_t;
  *	IWL_UCODE_TLV_API_WIFI_MCC_UPDATE. When either is set, multi-source LAR
  *	is supported.
  * @IWL_UCODE_TLV_CAPA_BT_COEX_RRC: supports BT Coex RRC
- * @IWL_UCODE_TLV_CAPA_GSCAN_SUPPORT: supports gscan
+ * @IWL_UCODE_TLV_CAPA_GSCAN_SUPPORT: supports gscan (no longer used)
  * @IWL_UCODE_TLV_CAPA_STA_PM_NOTIF: firmware will send STA PM notification
  * @IWL_UCODE_TLV_CAPA_TLC_OFFLOAD: firmware implements rate scaling algorithm
  * @IWL_UCODE_TLV_CAPA_DYNAMIC_QUOTA: firmware implements quota related
@@ -889,39 +892,4 @@ struct iwl_fw_dbg_conf_tlv {
 	struct iwl_fw_dbg_conf_hcmd hcmd;
 } __packed;
 
-/**
- * struct iwl_fw_gscan_capabilities - gscan capabilities supported by FW
- * @max_scan_cache_size: total space allocated for scan results (in bytes).
- * @max_scan_buckets: maximum number of channel buckets.
- * @max_ap_cache_per_scan: maximum number of APs that can be stored per scan.
- * @max_rssi_sample_size: number of RSSI samples used for averaging RSSI.
- * @max_scan_reporting_threshold: max possible report threshold. in percentage.
- * @max_hotlist_aps: maximum number of entries for hotlist APs.
- * @max_significant_change_aps: maximum number of entries for significant
- *	change APs.
- * @max_bssid_history_entries: number of BSSID/RSSI entries that the device can
- *	hold.
- * @max_hotlist_ssids: maximum number of entries for hotlist SSIDs.
- * @max_number_epno_networks: max number of epno entries.
- * @max_number_epno_networks_by_ssid: max number of epno entries if ssid is
- *	specified.
- * @max_number_of_white_listed_ssid: max number of white listed SSIDs.
- * @max_number_of_black_listed_ssid: max number of black listed SSIDs.
- */
-struct iwl_fw_gscan_capabilities {
-	__le32 max_scan_cache_size;
-	__le32 max_scan_buckets;
-	__le32 max_ap_cache_per_scan;
-	__le32 max_rssi_sample_size;
-	__le32 max_scan_reporting_threshold;
-	__le32 max_hotlist_aps;
-	__le32 max_significant_change_aps;
-	__le32 max_bssid_history_entries;
-	__le32 max_hotlist_ssids;
-	__le32 max_number_epno_networks;
-	__le32 max_number_epno_networks_by_ssid;
-	__le32 max_number_of_white_listed_ssid;
-	__le32 max_number_of_black_listed_ssid;
-} __packed;
-
 #endif  /* __iwl_fw_file_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/img.h b/drivers/net/wireless/intel/iwlwifi/fw/img.h
index f4912382b6af..0861b97c4233 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/img.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/img.h
@@ -193,41 +193,6 @@ struct iwl_fw_cscheme_list {
 } __packed;
 
 /**
- * struct iwl_gscan_capabilities - gscan capabilities supported by FW
- * @max_scan_cache_size: total space allocated for scan results (in bytes).
- * @max_scan_buckets: maximum number of channel buckets.
- * @max_ap_cache_per_scan: maximum number of APs that can be stored per scan.
- * @max_rssi_sample_size: number of RSSI samples used for averaging RSSI.
- * @max_scan_reporting_threshold: max possible report threshold. in percentage.
- * @max_hotlist_aps: maximum number of entries for hotlist APs.
- * @max_significant_change_aps: maximum number of entries for significant
- *	change APs.
- * @max_bssid_history_entries: number of BSSID/RSSI entries that the device can
- *	hold.
- * @max_hotlist_ssids: maximum number of entries for hotlist SSIDs.
- * @max_number_epno_networks: max number of epno entries.
- * @max_number_epno_networks_by_ssid: max number of epno entries if ssid is
- *	specified.
- * @max_number_of_white_listed_ssid: max number of white listed SSIDs.
- * @max_number_of_black_listed_ssid: max number of black listed SSIDs.
- */
-struct iwl_gscan_capabilities {
-	u32 max_scan_cache_size;
-	u32 max_scan_buckets;
-	u32 max_ap_cache_per_scan;
-	u32 max_rssi_sample_size;
-	u32 max_scan_reporting_threshold;
-	u32 max_hotlist_aps;
-	u32 max_significant_change_aps;
-	u32 max_bssid_history_entries;
-	u32 max_hotlist_ssids;
-	u32 max_number_epno_networks;
-	u32 max_number_epno_networks_by_ssid;
-	u32 max_number_of_white_listed_ssid;
-	u32 max_number_of_black_listed_ssid;
-};
-
-/**
  * enum iwl_fw_type - iwlwifi firmware type
  * @IWL_FW_DVM: DVM firmware
  * @IWL_FW_MVM: MVM firmware
@@ -298,7 +263,7 @@ struct iwl_fw {
 	size_t n_dbg_mem_tlv;
 	size_t dbg_trigger_tlv_len[FW_DBG_TRIGGER_MAX];
 	u8 dbg_dest_reg_num;
-	struct iwl_gscan_capabilities gscan_capa;
+	u32 dbg_dump_mask;
 };
 
 static inline const char *get_fw_dbg_mode_string(int mode)
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
index d8db1dd100b0..ed23367f7088 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
@@ -168,7 +168,4 @@ void iwl_free_fw_paging(struct iwl_fw_runtime *fwrt);
 
 void iwl_get_shared_mem_conf(struct iwl_fw_runtime *fwrt);
 
-void iwl_fwrt_handle_notification(struct iwl_fw_runtime *fwrt,
-				  struct iwl_rx_cmd_buffer *rxb);
-
 #endif /* __iwl_fw_runtime_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/smem.c b/drivers/net/wireless/intel/iwlwifi/fw/smem.c
index fb4b6442b4d7..ff85d69c2a8c 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/smem.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/smem.c
@@ -8,6 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -30,6 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -143,7 +145,7 @@ void iwl_get_shared_mem_conf(struct iwl_fw_runtime *fwrt)
 		return;
 
 	pkt = cmd.resp_pkt;
-	if (fwrt->trans->cfg->device_family == IWL_DEVICE_FAMILY_22000)
+	if (fwrt->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22000)
 		iwl_parse_shared_mem_22000(fwrt, pkt);
 	else
 		iwl_parse_shared_mem(fwrt, pkt);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index 84a816809723..12fddcf15bab 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -93,6 +93,7 @@ enum iwl_device_family {
 	IWL_DEVICE_FAMILY_8000,
 	IWL_DEVICE_FAMILY_9000,
 	IWL_DEVICE_FAMILY_22000,
+	IWL_DEVICE_FAMILY_22560,
 };
 
 /*
@@ -176,6 +177,7 @@ static inline u8 num_of_ant(u8 mask)
  * @apmg_wake_up_wa: should the MAC access REQ be asserted when a command
  *	is in flight. This is due to a HW bug in 7260, 3160 and 7265.
  * @scd_chain_ext_wa: should the chain extension feature in SCD be disabled.
+ * @max_tfd_queue_size: max number of entries in tfd queue.
  */
 struct iwl_base_params {
 	unsigned int wd_timeout;
@@ -191,6 +193,7 @@ struct iwl_base_params {
 	   scd_chain_ext_wa:1;
 
 	u16 num_of_queues;	/* def: HW dependent */
+	u32 max_tfd_queue_size;	/* def: HW dependent */
 
 	u8 max_ll_items;
 	u8 led_compensation;
@@ -571,9 +574,11 @@ extern const struct iwl_cfg iwl22000_2ac_cfg_hr;
 extern const struct iwl_cfg iwl22000_2ac_cfg_hr_cdb;
 extern const struct iwl_cfg iwl22000_2ac_cfg_jf;
 extern const struct iwl_cfg iwl22000_2ax_cfg_hr;
-extern const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_f0;
+extern const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_a0_f0;
+extern const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_b0;
 extern const struct iwl_cfg iwl22000_2ax_cfg_qnj_jf_b0;
 extern const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_a0;
+extern const struct iwl_cfg iwl22560_2ax_cfg_su_cdb;
 #endif /* CONFIG_IWLMVM */
 
 #endif /* __IWL_CONFIG_H__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h b/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h
new file mode 100644
index 000000000000..ebea99189ca9
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h
@@ -0,0 +1,286 @@
+/******************************************************************************
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2018 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2018 Intel Corporation
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *  * Neither the name Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *****************************************************************************/
+#ifndef __iwl_context_info_file_gen3_h__
+#define __iwl_context_info_file_gen3_h__
+
+#include "iwl-context-info.h"
+
+#define CSR_CTXT_INFO_BOOT_CTRL         0x0
+#define CSR_CTXT_INFO_ADDR              0x118
+#define CSR_IML_DATA_ADDR               0x120
+#define CSR_IML_SIZE_ADDR               0x128
+#define CSR_IML_RESP_ADDR               0x12c
+
+/* Set bit for enabling automatic function boot */
+#define CSR_AUTO_FUNC_BOOT_ENA          BIT(1)
+/* Set bit for initiating function boot */
+#define CSR_AUTO_FUNC_INIT              BIT(7)
+
+/**
+ * enum iwl_prph_scratch_mtr_format - tfd size configuration
+ * @IWL_PRPH_MTR_FORMAT_16B: 16 bit tfd
+ * @IWL_PRPH_MTR_FORMAT_32B: 32 bit tfd
+ * @IWL_PRPH_MTR_FORMAT_64B: 64 bit tfd
+ * @IWL_PRPH_MTR_FORMAT_256B: 256 bit tfd
+ */
+enum iwl_prph_scratch_mtr_format {
+	IWL_PRPH_MTR_FORMAT_16B = 0x0,
+	IWL_PRPH_MTR_FORMAT_32B = 0x40000,
+	IWL_PRPH_MTR_FORMAT_64B = 0x80000,
+	IWL_PRPH_MTR_FORMAT_256B = 0xC0000,
+};
+
+/**
+ * enum iwl_prph_scratch_flags - PRPH scratch control flags
+ * @IWL_PRPH_SCRATCH_EARLY_DEBUG_EN: enable early debug conf
+ * @IWL_PRPH_SCRATCH_EDBG_DEST_DRAM: use DRAM, with size allocated
+ *	in hwm config.
+ * @IWL_PRPH_SCRATCH_EDBG_DEST_INTERNAL: use buffer on SRAM
+ * @IWL_PRPH_SCRATCH_EDBG_DEST_ST_ARBITER: use st arbiter, mainly for
+ *	multicomm.
+ * @IWL_PRPH_SCRATCH_EDBG_DEST_TB22DTF: route debug data to SoC HW
+ * @IWL_PRPH_SCTATCH_RB_SIZE_4K: Use 4K RB size (the default is 2K)
+ * @IWL_PRPH_SCRATCH_MTR_MODE: format used for completion - 0: for
+ *	completion descriptor, 1 for responses (legacy)
+ * @IWL_PRPH_SCRATCH_MTR_FORMAT: a mask for the size of the tfd.
+ *	There are 4 optional values: 0: 16 bit, 1: 32 bit, 2: 64 bit,
+ *	3: 256 bit.
+ */
+enum iwl_prph_scratch_flags {
+	IWL_PRPH_SCRATCH_EARLY_DEBUG_EN		= BIT(4),
+	IWL_PRPH_SCRATCH_EDBG_DEST_DRAM		= BIT(8),
+	IWL_PRPH_SCRATCH_EDBG_DEST_INTERNAL	= BIT(9),
+	IWL_PRPH_SCRATCH_EDBG_DEST_ST_ARBITER	= BIT(10),
+	IWL_PRPH_SCRATCH_EDBG_DEST_TB22DTF	= BIT(11),
+	IWL_PRPH_SCRATCH_RB_SIZE_4K		= BIT(16),
+	IWL_PRPH_SCRATCH_MTR_MODE		= BIT(17),
+	IWL_PRPH_SCRATCH_MTR_FORMAT		= BIT(18) | BIT(19),
+};
+
+/*
+ * struct iwl_prph_scratch_version - version structure
+ * @mac_id: SKU and revision id
+ * @version: prph scratch information version id
+ * @size: the size of the context information in DWs
+ * @reserved: reserved
+ */
+struct iwl_prph_scratch_version {
+	__le16 mac_id;
+	__le16 version;
+	__le16 size;
+	__le16 reserved;
+} __packed; /* PERIPH_SCRATCH_VERSION_S */
+
+/*
+ * struct iwl_prph_scratch_control - control structure
+ * @control_flags: context information flags see &enum iwl_prph_scratch_flags
+ * @reserved: reserved
+ */
+struct iwl_prph_scratch_control {
+	__le32 control_flags;
+	__le32 reserved;
+} __packed; /* PERIPH_SCRATCH_CONTROL_S */
+
+/*
+ * struct iwl_prph_scratch_ror_cfg - ror config
+ * @ror_base_addr: ror start address
+ * @ror_size: ror size in DWs
+ * @reserved: reserved
+ */
+struct iwl_prph_scratch_ror_cfg {
+	__le64 ror_base_addr;
+	__le32 ror_size;
+	__le32 reserved;
+} __packed; /* PERIPH_SCRATCH_ROR_CFG_S */
+
+/*
+ * struct iwl_prph_scratch_hwm_cfg - hwm config
+ * @hwm_base_addr: hwm start address
+ * @hwm_size: hwm size in DWs
+ * @reserved: reserved
+ */
+struct iwl_prph_scratch_hwm_cfg {
+	__le64 hwm_base_addr;
+	__le32 hwm_size;
+	__le32 reserved;
+} __packed; /* PERIPH_SCRATCH_HWM_CFG_S */
+
+/*
+ * struct iwl_prph_scratch_rbd_cfg - RBDs configuration
+ * @free_rbd_addr: default queue free RB CB base address
+ * @reserved: reserved
+ */
+struct iwl_prph_scratch_rbd_cfg {
+	__le64 free_rbd_addr;
+	__le32 reserved;
+} __packed; /* PERIPH_SCRATCH_RBD_CFG_S */
+
+/*
+ * struct iwl_prph_scratch_ctrl_cfg - prph scratch ctrl and config
+ * @version: version information of context info and HW
+ * @control: control flags of FH configurations
+ * @ror_cfg: ror configuration
+ * @hwm_cfg: hwm configuration
+ * @rbd_cfg: default RX queue configuration
+ */
+struct iwl_prph_scratch_ctrl_cfg {
+	struct iwl_prph_scratch_version version;
+	struct iwl_prph_scratch_control control;
+	struct iwl_prph_scratch_ror_cfg ror_cfg;
+	struct iwl_prph_scratch_hwm_cfg hwm_cfg;
+	struct iwl_prph_scratch_rbd_cfg rbd_cfg;
+} __packed; /* PERIPH_SCRATCH_CTRL_CFG_S */
+
+/*
+ * struct iwl_prph_scratch - peripheral scratch mapping
+ * @ctrl_cfg: control and configuration of prph scratch
+ * @dram: firmware images addresses in DRAM
+ * @reserved: reserved
+ */
+struct iwl_prph_scratch {
+	struct iwl_prph_scratch_ctrl_cfg ctrl_cfg;
+	__le32 reserved[16];
+	struct iwl_context_info_dram dram;
+} __packed; /* PERIPH_SCRATCH_S */
+
+/*
+ * struct iwl_prph_info - peripheral information
+ * @boot_stage_mirror: reflects the value in the Boot Stage CSR register
+ * @ipc_status_mirror: reflects the value in the IPC Status CSR register
+ * @sleep_notif: indicates the peripheral sleep status
+ * @reserved: reserved
+ */
+struct iwl_prph_info {
+	__le32 boot_stage_mirror;
+	__le32 ipc_status_mirror;
+	__le32 sleep_notif;
+	__le32 reserved;
+} __packed; /* PERIPH_INFO_S */
+
+/*
+ * struct iwl_context_info_gen3 - device INIT configuration
+ * @version: version of the context information
+ * @size: size of context information in DWs
+ * @config: context in which the peripheral would execute - a subset of
+ *	capability csr register published by the peripheral
+ * @prph_info_base_addr: the peripheral information structure start address
+ * @cr_head_idx_arr_base_addr: the completion ring head index array
+ *	start address
+ * @tr_tail_idx_arr_base_addr: the transfer ring tail index array
+ *	start address
+ * @cr_tail_idx_arr_base_addr: the completion ring tail index array
+ *	start address
+ * @tr_head_idx_arr_base_addr: the transfer ring head index array
+ *	start address
+ * @cr_idx_arr_size: number of entries in the completion ring index array
+ * @tr_idx_arr_size: number of entries in the transfer ring index array
+ * @mtr_base_addr: the message transfer ring start address
+ * @mcr_base_addr: the message completion ring start address
+ * @mtr_size: number of entries which the message transfer ring can hold
+ * @mcr_size: number of entries which the message completion ring can hold
+ * @mtr_doorbell_vec: the doorbell vector associated with the message
+ *	transfer ring
+ * @mcr_doorbell_vec: the doorbell vector associated with the message
+ *	completion ring
+ * @mtr_msi_vec: the MSI which shall be generated by the peripheral after
+ *	completing a transfer descriptor in the message transfer ring
+ * @mcr_msi_vec: the MSI which shall be generated by the peripheral after
+ *	completing a completion descriptor in the message completion ring
+ * @mtr_opt_header_size: the size of the optional header in the transfer
+ *	descriptor associated with the message transfer ring in DWs
+ * @mtr_opt_footer_size: the size of the optional footer in the transfer
+ *	descriptor associated with the message transfer ring in DWs
+ * @mcr_opt_header_size: the size of the optional header in the completion
+ *	descriptor associated with the message completion ring in DWs
+ * @mcr_opt_footer_size: the size of the optional footer in the completion
+ *	descriptor associated with the message completion ring in DWs
+ * @msg_rings_ctrl_flags: message rings control flags
+ * @prph_info_msi_vec: the MSI which shall be generated by the peripheral
+ *	after updating the Peripheral Information structure
+ * @prph_scratch_base_addr: the peripheral scratch structure start address
+ * @prph_scratch_size: the size of the peripheral scratch structure in DWs
+ * @reserved: reserved
+ */
+struct iwl_context_info_gen3 {
+	__le16 version;
+	__le16 size;
+	__le32 config;
+	__le64 prph_info_base_addr;
+	__le64 cr_head_idx_arr_base_addr;
+	__le64 tr_tail_idx_arr_base_addr;
+	__le64 cr_tail_idx_arr_base_addr;
+	__le64 tr_head_idx_arr_base_addr;
+	__le16 cr_idx_arr_size;
+	__le16 tr_idx_arr_size;
+	__le64 mtr_base_addr;
+	__le64 mcr_base_addr;
+	__le16 mtr_size;
+	__le16 mcr_size;
+	__le16 mtr_doorbell_vec;
+	__le16 mcr_doorbell_vec;
+	__le16 mtr_msi_vec;
+	__le16 mcr_msi_vec;
+	u8 mtr_opt_header_size;
+	u8 mtr_opt_footer_size;
+	u8 mcr_opt_header_size;
+	u8 mcr_opt_footer_size;
+	__le16 msg_rings_ctrl_flags;
+	__le16 prph_info_msi_vec;
+	__le64 prph_scratch_base_addr;
+	__le32 prph_scratch_size;
+	__le32 reserved;
+} __packed; /* IPC_CONTEXT_INFO_S */
+
+int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
+				 const struct fw_img *fw);
+void iwl_pcie_ctxt_info_gen3_free(struct iwl_trans *trans);
+
+#endif /* __iwl_context_info_file_gen3_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-context-info.h b/drivers/net/wireless/intel/iwlwifi/iwl-context-info.h
index b870c0986744..4b6fdf3b15fb 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-context-info.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-context-info.h
@@ -6,6 +6,7 @@
  * GPL LICENSE SUMMARY
  *
  * Copyright(c) 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -19,6 +20,7 @@
  * BSD LICENSE
  *
  * Copyright(c) 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -199,5 +201,8 @@ struct iwl_context_info {
 int iwl_pcie_ctxt_info_init(struct iwl_trans *trans, const struct fw_img *fw);
 void iwl_pcie_ctxt_info_free(struct iwl_trans *trans);
 void iwl_pcie_ctxt_info_free_paging(struct iwl_trans *trans);
+int iwl_pcie_init_fw_sec(struct iwl_trans *trans,
+			 const struct fw_img *fw,
+			 struct iwl_context_info_dram *ctxt_dram);
 
 #endif /* __iwl_context_info_file_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
index ba971d3946e2..9019de99f077 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
@@ -339,6 +339,9 @@ enum {
 /* HW_RF CHIP ID  */
 #define CSR_HW_RF_ID_TYPE_CHIP_ID(_val) (((_val) >> 12) & 0xFFF)
 
+/* HW_RF CHIP STEP  */
+#define CSR_HW_RF_STEP(_val) (((_val) >> 8) & 0xF)
+
 /* EEPROM REG */
 #define CSR_EEPROM_REG_READ_VALID_MSK	(0x00000001)
 #define CSR_EEPROM_REG_BIT_CMD		(0x00000002)
@@ -592,6 +595,8 @@ enum msix_fh_int_causes {
 enum msix_hw_int_causes {
 	MSIX_HW_INT_CAUSES_REG_ALIVE		= BIT(0),
 	MSIX_HW_INT_CAUSES_REG_WAKEUP		= BIT(1),
+	MSIX_HW_INT_CAUSES_REG_IPC		= BIT(1),
+	MSIX_HW_INT_CAUSES_REG_SW_ERR_V2	= BIT(5),
 	MSIX_HW_INT_CAUSES_REG_CT_KILL		= BIT(6),
 	MSIX_HW_INT_CAUSES_REG_RF_KILL		= BIT(7),
 	MSIX_HW_INT_CAUSES_REG_PERIODIC		= BIT(8),
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index c59ce4f8a5ed..c0631255aee7 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -402,35 +402,6 @@ static int iwl_store_cscheme(struct iwl_fw *fw, const u8 *data, const u32 len)
 	return 0;
 }
 
-static void iwl_store_gscan_capa(struct iwl_fw *fw, const u8 *data,
-				 const u32 len)
-{
-	struct iwl_fw_gscan_capabilities *fw_capa = (void *)data;
-	struct iwl_gscan_capabilities *capa = &fw->gscan_capa;
-
-	capa->max_scan_cache_size = le32_to_cpu(fw_capa->max_scan_cache_size);
-	capa->max_scan_buckets = le32_to_cpu(fw_capa->max_scan_buckets);
-	capa->max_ap_cache_per_scan =
-		le32_to_cpu(fw_capa->max_ap_cache_per_scan);
-	capa->max_rssi_sample_size = le32_to_cpu(fw_capa->max_rssi_sample_size);
-	capa->max_scan_reporting_threshold =
-		le32_to_cpu(fw_capa->max_scan_reporting_threshold);
-	capa->max_hotlist_aps = le32_to_cpu(fw_capa->max_hotlist_aps);
-	capa->max_significant_change_aps =
-		le32_to_cpu(fw_capa->max_significant_change_aps);
-	capa->max_bssid_history_entries =
-		le32_to_cpu(fw_capa->max_bssid_history_entries);
-	capa->max_hotlist_ssids = le32_to_cpu(fw_capa->max_hotlist_ssids);
-	capa->max_number_epno_networks =
-		le32_to_cpu(fw_capa->max_number_epno_networks);
-	capa->max_number_epno_networks_by_ssid =
-		le32_to_cpu(fw_capa->max_number_epno_networks_by_ssid);
-	capa->max_number_of_white_listed_ssid =
-		le32_to_cpu(fw_capa->max_number_of_white_listed_ssid);
-	capa->max_number_of_black_listed_ssid =
-		le32_to_cpu(fw_capa->max_number_of_black_listed_ssid);
-}
-
 /*
  * Gets uCode section from tlv.
  */
@@ -644,7 +615,6 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 	u32 build, paging_mem_size;
 	int num_of_cpus;
 	bool usniffer_req = false;
-	bool gscan_capa = false;
 
 	if (len < sizeof(*ucode)) {
 		IWL_ERR(drv, "uCode has invalid length: %zd\n", len);
@@ -1043,6 +1013,17 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 			pieces->dbg_trigger_tlv_len[trigger_id] = tlv_len;
 			break;
 			}
+		case IWL_UCODE_TLV_FW_DBG_DUMP_LST: {
+			if (tlv_len != sizeof(u32)) {
+				IWL_ERR(drv,
+					"dbg lst mask size incorrect, skip\n");
+				break;
+			}
+
+			drv->fw.dbg_dump_mask =
+				le32_to_cpup((__le32 *)tlv_data);
+			break;
+			}
 		case IWL_UCODE_TLV_SEC_RT_USNIFFER:
 			*usniffer_images = true;
 			iwl_store_ucode_sec(pieces, tlv_data,
@@ -1079,16 +1060,7 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 				paging_mem_size;
 			break;
 		case IWL_UCODE_TLV_FW_GSCAN_CAPA:
-			/*
-			 * Don't return an error in case of a shorter tlv_len
-			 * to enable loading of FW that has an old format
-			 * of GSCAN capabilities TLV.
-			 */
-			if (tlv_len < sizeof(struct iwl_fw_gscan_capabilities))
-				break;
-
-			iwl_store_gscan_capa(&drv->fw, tlv_data, tlv_len);
-			gscan_capa = true;
+			/* ignored */
 			break;
 		case IWL_UCODE_TLV_FW_MEM_SEG: {
 			struct iwl_fw_dbg_mem_seg_tlv *dbg_mem =
@@ -1153,19 +1125,6 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 		return -EINVAL;
 	}
 
-	/*
-	 * If ucode advertises that it supports GSCAN but GSCAN
-	 * capabilities TLV is not present, or if it has an old format,
-	 * warn and continue without GSCAN.
-	 */
-	if (fw_has_capa(capa, IWL_UCODE_TLV_CAPA_GSCAN_SUPPORT) &&
-	    !gscan_capa) {
-		IWL_DEBUG_INFO(drv,
-			       "GSCAN is supported but capabilities TLV is unavailable\n");
-		__clear_bit((__force long)IWL_UCODE_TLV_CAPA_GSCAN_SUPPORT,
-			    capa->_capa);
-	}
-
 	return 0;
 
  invalid_tlv_len:
@@ -1316,6 +1275,8 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context)
 	fw->ucode_capa.standard_phy_calibration_size =
 			IWL_DEFAULT_STANDARD_PHY_CALIBRATE_TBL_SIZE;
 	fw->ucode_capa.n_scan_channels = IWL_DEFAULT_SCAN_CHANNELS;
+	/* dump all fw memory areas by default */
+	fw->dbg_dump_mask = 0xffffffff;
 
 	pieces = kzalloc(sizeof(*pieces), GFP_KERNEL);
 	if (!pieces)
@@ -1787,7 +1748,8 @@ MODULE_PARM_DESC(11n_disable,
 	"disable 11n functionality, bitmap: 1: full, 2: disable agg TX, 4: disable agg RX, 8 enable agg TX");
 module_param_named(amsdu_size, iwlwifi_mod_params.amsdu_size, int, 0444);
 MODULE_PARM_DESC(amsdu_size,
-		 "amsdu size 0: 12K for multi Rx queue devices, 4K for other devices 1:4K 2:8K 3:12K (default 0)");
+		 "amsdu size 0: 12K for multi Rx queue devices, 2K for 22560 devices, "
+		 "4K for other devices 1:4K 2:8K 3:12K 4: 2K (default 0)");
 module_param_named(fw_restart, iwlwifi_mod_params.fw_restart, bool, 0444);
 MODULE_PARM_DESC(fw_restart, "restart firmware in case of error (default true)");
 
@@ -1856,3 +1818,7 @@ module_param_named(remove_when_gone,
 		   0444);
 MODULE_PARM_DESC(remove_when_gone,
 		 "Remove dev from PCIe bus if it is deemed inaccessible (default: false)");
+
+module_param_named(disable_11ax, iwlwifi_mod_params.disable_11ax, bool,
+		   S_IRUGO);
+MODULE_PARM_DESC(disable_11ax, "Disable HE capabilities (default: false)");
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c
index 777f5df8a0c6..a4c96215933b 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c
@@ -7,6 +7,7 @@
  *
  * Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -18,9 +19,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110,
- * USA
+ * along with this program;
  *
  * The full GNU General Public License is included in this distribution
  * in the file called COPYING.
@@ -33,6 +32,7 @@
  *
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -767,7 +767,7 @@ void iwl_init_ht_hw_capab(const struct iwl_cfg *cfg,
 		ht_info->cap |= IEEE80211_HT_CAP_LDPC_CODING;
 
 	if ((cfg->mq_rx_supported &&
-	     iwlwifi_mod_params.amsdu_size != IWL_AMSDU_4K) ||
+	     iwlwifi_mod_params.amsdu_size == IWL_AMSDU_DEF) ||
 	     iwlwifi_mod_params.amsdu_size >= IWL_AMSDU_8K)
 		ht_info->cap |= IEEE80211_HT_CAP_MAX_AMSDU;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-fh.h b/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
index 11789ffb6512..df0e9ffff706 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
@@ -7,6 +7,7 @@
  *
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -18,9 +19,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110,
- * USA
+ * along with this program.
  *
  * The full GNU General Public License is included in this distribution
  * in the file called COPYING.
@@ -33,6 +32,7 @@
  *
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -434,13 +434,15 @@ static inline unsigned int FH_MEM_CBBC_QUEUE(struct iwl_trans *trans,
  * RXF to DRAM.
  * Once the RXF-to-DRAM DMA is active, this flag is immediately turned off.
  */
-#define RFH_GEN_STATUS 0xA09808
+#define RFH_GEN_STATUS		0xA09808
+#define RFH_GEN_STATUS_GEN3	0xA07824
 #define RBD_FETCH_IDLE	BIT(29)
 #define SRAM_DMA_IDLE	BIT(30)
 #define RXF_DMA_IDLE	BIT(31)
 
 /* DMA configuration */
-#define RFH_RXF_DMA_CFG 0xA09820
+#define RFH_RXF_DMA_CFG		0xA09820
+#define RFH_RXF_DMA_CFG_GEN3	0xA07880
 /* RB size */
 #define RFH_RXF_DMA_RB_SIZE_MASK (0x000F0000) /* bits 16-19 */
 #define RFH_RXF_DMA_RB_SIZE_POS 16
@@ -643,10 +645,13 @@ struct iwl_rb_status {
 
 
 #define TFD_QUEUE_SIZE_MAX      (256)
+#define TFD_QUEUE_SIZE_MAX_GEN3 (65536)
 /* cb size is the exponent - 3 */
 #define TFD_QUEUE_CB_SIZE(x)	(ilog2(x) - 3)
 #define TFD_QUEUE_SIZE_BC_DUP	(64)
 #define TFD_QUEUE_BC_SIZE	(TFD_QUEUE_SIZE_MAX + TFD_QUEUE_SIZE_BC_DUP)
+#define TFD_QUEUE_BC_SIZE_GEN3	(TFD_QUEUE_SIZE_MAX_GEN3 + \
+				 TFD_QUEUE_SIZE_BC_DUP)
 #define IWL_TX_DMA_MASK        DMA_BIT_MASK(36)
 #define IWL_NUM_OF_TBS		20
 #define IWL_TFH_NUM_TBS		25
@@ -753,7 +758,7 @@ struct iwl_tfh_tfd {
  * For devices up to 22000:
  * @tfd_offset  0-12 - tx command byte count
  *		12-16 - station index
- * For 22000 and on:
+ * For 22000:
  * @tfd_offset  0-12 - tx command byte count
  *		12-13 - number of 64 byte chunks
  *		14-16 - reserved
@@ -762,4 +767,15 @@ struct iwlagn_scd_bc_tbl {
 	__le16 tfd_offset[TFD_QUEUE_BC_SIZE];
 } __packed;
 
+/**
+ * struct iwl_gen3_bc_tbl scheduler byte count table gen3
+ * For 22560 and on:
+ * @tfd_offset: 0-12 - tx command byte count
+ *		12-13 - number of 64 byte chunks
+ *		14-16 - reserved
+ */
+struct iwl_gen3_bc_tbl {
+	__le16 tfd_offset[TFD_QUEUE_BC_SIZE_GEN3];
+} __packed;
+
 #endif /* !__iwl_fh_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
index a7dd8a8cddf9..97072cf75bca 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
@@ -6,6 +6,7 @@
  * GPL LICENSE SUMMARY
  *
  * Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -17,9 +18,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110,
- * USA
+ * along with this program;
  *
  * The full GNU General Public License is included in this distribution
  * in the file called COPYING.
@@ -31,6 +30,7 @@
  * BSD LICENSE
  *
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -90,6 +90,8 @@ enum iwl_amsdu_size {
 	IWL_AMSDU_4K = 1,
 	IWL_AMSDU_8K = 2,
 	IWL_AMSDU_12K = 3,
+	/* Add 2K at the end to avoid breaking current API */
+	IWL_AMSDU_2K = 4,
 };
 
 enum iwl_uapsd_disable {
@@ -144,6 +146,10 @@ struct iwl_mod_params {
 	bool lar_disable;
 	bool fw_monitor;
 	bool disable_11ac;
+	/**
+	 * @disable_11ax: disable HE capabilities, default = false
+	 */
+	bool disable_11ax;
 	bool remove_when_gone;
 };
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index b815ba38dbdb..b4c3a957c102 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -430,6 +430,13 @@ static void iwl_init_vht_hw_capab(const struct iwl_cfg *cfg,
 		else
 			vht_cap->cap |= IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895;
 		break;
+	case IWL_AMSDU_2K:
+		if (cfg->mq_rx_supported)
+			vht_cap->cap |=
+				IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454;
+		else
+			WARN(1, "RB size of 2K is not supported by this device\n");
+		break;
 	case IWL_AMSDU_4K:
 		vht_cap->cap |= IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895;
 		break;
@@ -463,6 +470,101 @@ static void iwl_init_vht_hw_capab(const struct iwl_cfg *cfg,
 	vht_cap->vht_mcs.tx_mcs_map = vht_cap->vht_mcs.rx_mcs_map;
 }
 
+static struct ieee80211_sband_iftype_data iwl_he_capa = {
+	.types_mask = BIT(NL80211_IFTYPE_STATION) | BIT(NL80211_IFTYPE_AP),
+	.he_cap = {
+		.has_he = true,
+		.he_cap_elem = {
+			.mac_cap_info[0] =
+				IEEE80211_HE_MAC_CAP0_HTC_HE,
+			.mac_cap_info[1] =
+				IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US |
+				IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8,
+			.mac_cap_info[2] =
+				IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP |
+				IEEE80211_HE_MAC_CAP2_ACK_EN,
+			.mac_cap_info[3] =
+				IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU |
+				IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2,
+			.mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU,
+			.phy_cap_info[0] =
+				IEEE80211_HE_PHY_CAP0_DUAL_BAND |
+				IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G |
+				IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G |
+				IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G,
+			.phy_cap_info[1] =
+				IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A |
+				IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD |
+				IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS,
+			.phy_cap_info[2] =
+				IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US |
+				IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ |
+				IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ,
+			.phy_cap_info[3] =
+				IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK |
+				IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 |
+				IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK |
+				IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1,
+			.phy_cap_info[4] =
+				IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE |
+				IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_8 |
+				IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8,
+			.phy_cap_info[5] =
+				IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 |
+				IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2,
+			.phy_cap_info[6] =
+				IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT,
+			.phy_cap_info[7] =
+				IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_AR |
+				IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI |
+				IEEE80211_HE_PHY_CAP7_MAX_NC_7,
+			.phy_cap_info[8] =
+				IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI |
+				IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G |
+				IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU |
+				IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU,
+		},
+		/*
+		 * Set default Tx/Rx HE MCS NSS Support field. Indicate support
+		 * for up to 2 spatial streams and all MCS, without any special
+		 * cases
+		 */
+		.he_mcs_nss_supp = {
+			.rx_mcs_80 = cpu_to_le16(0xfffa),
+			.tx_mcs_80 = cpu_to_le16(0xfffa),
+			.rx_mcs_160 = cpu_to_le16(0xfffa),
+			.tx_mcs_160 = cpu_to_le16(0xfffa),
+			.rx_mcs_80p80 = cpu_to_le16(0xffff),
+			.tx_mcs_80p80 = cpu_to_le16(0xffff),
+		},
+		/*
+		 * Set default PPE thresholds, with PPET16 set to 0, PPET8 set
+		 * to 7
+		 */
+		.ppe_thres = {0x61, 0x1c, 0xc7, 0x71},
+	},
+};
+
+static void iwl_init_he_hw_capab(struct ieee80211_supported_band *sband,
+				 u8 tx_chains, u8 rx_chains)
+{
+	if (sband->band == NL80211_BAND_2GHZ ||
+	    sband->band == NL80211_BAND_5GHZ)
+		sband->iftype_data = &iwl_he_capa;
+	else
+		return;
+
+	sband->n_iftype_data = 1;
+
+	/* If not 2x2, we need to indicate 1x1 in the Midamble RX Max NSTS */
+	if ((tx_chains & rx_chains) != ANT_AB) {
+		iwl_he_capa.he_cap.he_cap_elem.phy_cap_info[1] &=
+			~IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS;
+		iwl_he_capa.he_cap.he_cap_elem.phy_cap_info[2] &=
+			~IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_MAX_NSTS;
+	}
+}
+
 static void iwl_init_sbands(struct device *dev, const struct iwl_cfg *cfg,
 			    struct iwl_nvm_data *data,
 			    const __le16 *nvm_ch_flags, u8 tx_chains,
@@ -483,6 +585,9 @@ static void iwl_init_sbands(struct device *dev, const struct iwl_cfg *cfg,
 	iwl_init_ht_hw_capab(cfg, data, &sband->ht_cap, NL80211_BAND_2GHZ,
 			     tx_chains, rx_chains);
 
+	if (data->sku_cap_11ax_enable && !iwlwifi_mod_params.disable_11ax)
+		iwl_init_he_hw_capab(sband, tx_chains, rx_chains);
+
 	sband = &data->bands[NL80211_BAND_5GHZ];
 	sband->band = NL80211_BAND_5GHZ;
 	sband->bitrates = &iwl_cfg80211_rates[RATES_52_OFFS];
@@ -495,6 +600,9 @@ static void iwl_init_sbands(struct device *dev, const struct iwl_cfg *cfg,
 		iwl_init_vht_hw_capab(cfg, data, &sband->vht_cap,
 				      tx_chains, rx_chains);
 
+	if (data->sku_cap_11ax_enable && !iwlwifi_mod_params.disable_11ax)
+		iwl_init_he_hw_capab(sband, tx_chains, rx_chains);
+
 	if (n_channels != n_used)
 		IWL_ERR_DEV(dev, "NVM: used only %d of %d channels\n",
 			    n_used, n_channels);
@@ -1293,6 +1401,8 @@ struct iwl_nvm_data *iwl_get_nvm(struct iwl_trans *trans,
 		!!(mac_flags & NVM_MAC_SKU_FLAGS_802_11AC_ENABLED);
 	nvm->sku_cap_11n_enable =
 		!!(mac_flags & NVM_MAC_SKU_FLAGS_802_11N_ENABLED);
+	nvm->sku_cap_11ax_enable =
+		!!(mac_flags & NVM_MAC_SKU_FLAGS_802_11AX_ENABLED);
 	nvm->sku_cap_band_24ghz_enable =
 		!!(mac_flags & NVM_MAC_SKU_FLAGS_BAND_2_4_ENABLED);
 	nvm->sku_cap_band_52ghz_enable =
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 1b9c627ee34d..279dd7b7a3fb 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -350,6 +350,8 @@ static inline int
 iwl_trans_get_rb_size_order(enum iwl_amsdu_size rb_size)
 {
 	switch (rb_size) {
+	case IWL_AMSDU_2K:
+		return get_order(2 * 1024);
 	case IWL_AMSDU_4K:
 		return get_order(4 * 1024);
 	case IWL_AMSDU_8K:
@@ -438,6 +440,20 @@ struct iwl_trans_txq_scd_cfg {
 };
 
 /**
+ * struct iwl_trans_rxq_dma_data - RX queue DMA data
+ * @fr_bd_cb: DMA address of free BD cyclic buffer
+ * @fr_bd_wid: Initial write index of the free BD cyclic buffer
+ * @urbd_stts_wrptr: DMA address of urbd_stts_wrptr
+ * @ur_bd_cb: DMA address of used BD cyclic buffer
+ */
+struct iwl_trans_rxq_dma_data {
+	u64 fr_bd_cb;
+	u32 fr_bd_wid;
+	u64 urbd_stts_wrptr;
+	u64 ur_bd_cb;
+};
+
+/**
  * struct iwl_trans_ops - transport specific operations
  *
  * All the handlers MUST be implemented
@@ -557,6 +573,8 @@ struct iwl_trans_ops {
 			 int cmd_id, int size,
 			 unsigned int queue_wdg_timeout);
 	void (*txq_free)(struct iwl_trans *trans, int queue);
+	int (*rxq_dma_data)(struct iwl_trans *trans, int queue,
+			    struct iwl_trans_rxq_dma_data *data);
 
 	void (*txq_set_shared_mode)(struct iwl_trans *trans, u32 txq_id,
 				    bool shared);
@@ -753,6 +771,7 @@ struct iwl_trans {
 	const struct iwl_fw_dbg_dest_tlv_v1 *dbg_dest_tlv;
 	const struct iwl_fw_dbg_conf_tlv *dbg_conf_tlv[FW_DBG_CONF_MAX];
 	struct iwl_fw_dbg_trigger_tlv * const *dbg_trigger_tlv;
+	u32 dbg_dump_mask;
 	u8 dbg_dest_reg_num;
 
 	enum iwl_plat_pm_mode system_pm_mode;
@@ -945,6 +964,16 @@ iwl_trans_txq_enable_cfg(struct iwl_trans *trans, int queue, u16 ssn,
 				      cfg, queue_wdg_timeout);
 }
 
+static inline int
+iwl_trans_get_rxq_dma_data(struct iwl_trans *trans, int queue,
+			   struct iwl_trans_rxq_dma_data *data)
+{
+	if (WARN_ON_ONCE(!trans->ops->rxq_dma_data))
+		return -ENOTSUPP;
+
+	return trans->ops->rxq_dma_data(trans, queue, data);
+}
+
 static inline void
 iwl_trans_txq_free(struct iwl_trans *trans, int queue)
 {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index 3fcf489f3120..79bdae994822 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -1037,6 +1037,13 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw,
 			cpu_to_le32(IWL_WAKEUP_D3_CONFIG_FW_ERROR);
 #endif
 
+	/*
+	 * TODO: this is needed because the firmware is not stopping
+	 * the recording automatically before entering D3.  This can
+	 * be removed once the FW starts doing that.
+	 */
+	iwl_fw_dbg_stop_recording(&mvm->fwrt);
+
 	/* must be last -- this switches firmware state */
 	ret = iwl_mvm_send_cmd(mvm, &d3_cfg_cmd);
 	if (ret)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index 1c4178f20441..05b77419953c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -1150,6 +1150,10 @@ static ssize_t iwl_dbgfs_inject_packet_write(struct iwl_mvm *mvm,
 	struct iwl_rx_mpdu_desc *desc;
 	int bin_len = count / 2;
 	int ret = -EINVAL;
+	size_t mpdu_cmd_hdr_size =
+		(mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) ?
+		sizeof(struct iwl_rx_mpdu_desc) :
+		IWL_RX_DESC_SIZE_V1;
 
 	if (!iwl_mvm_firmware_running(mvm))
 		return -EIO;
@@ -1168,7 +1172,7 @@ static ssize_t iwl_dbgfs_inject_packet_write(struct iwl_mvm *mvm,
 		goto out;
 
 	/* avoid invalid memory access */
-	if (bin_len < sizeof(*pkt) + sizeof(*desc))
+	if (bin_len < sizeof(*pkt) + mpdu_cmd_hdr_size)
 		goto out;
 
 	/* check this is RX packet */
@@ -1179,7 +1183,7 @@ static ssize_t iwl_dbgfs_inject_packet_write(struct iwl_mvm *mvm,
 	/* check the length in metadata matches actual received length */
 	desc = (void *)pkt->data;
 	if (le16_to_cpu(desc->mpdu_len) !=
-	    (bin_len - sizeof(*desc) - sizeof(*pkt)))
+	    (bin_len - mpdu_cmd_hdr_size - sizeof(*pkt)))
 		goto out;
 
 	local_bh_disable();
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 866c91c923be..6bb1a99a197a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -130,6 +130,41 @@ static int iwl_send_rss_cfg_cmd(struct iwl_mvm *mvm)
 	return iwl_mvm_send_cmd_pdu(mvm, RSS_CONFIG_CMD, 0, sizeof(cmd), &cmd);
 }
 
+static int iwl_configure_rxq(struct iwl_mvm *mvm)
+{
+	int i, num_queues, size;
+	struct iwl_rfh_queue_config *cmd;
+
+	/* Do not configure default queue, it is configured via context info */
+	num_queues = mvm->trans->num_rx_queues - 1;
+
+	size = sizeof(*cmd) + num_queues * sizeof(struct iwl_rfh_queue_data);
+
+	cmd = kzalloc(size, GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->num_queues = num_queues;
+
+	for (i = 0; i < num_queues; i++) {
+		struct iwl_trans_rxq_dma_data data;
+
+		cmd->data[i].q_num = i + 1;
+		iwl_trans_get_rxq_dma_data(mvm->trans, i + 1, &data);
+
+		cmd->data[i].fr_bd_cb = cpu_to_le64(data.fr_bd_cb);
+		cmd->data[i].urbd_stts_wrptr =
+			cpu_to_le64(data.urbd_stts_wrptr);
+		cmd->data[i].ur_bd_cb = cpu_to_le64(data.ur_bd_cb);
+		cmd->data[i].fr_bd_wid = cpu_to_le32(data.fr_bd_wid);
+	}
+
+	return iwl_mvm_send_cmd_pdu(mvm,
+				    WIDE_ID(DATA_PATH_GROUP,
+					    RFH_QUEUE_CONFIG_CMD),
+				    0, size, cmd);
+}
+
 static int iwl_mvm_send_dqa_cmd(struct iwl_mvm *mvm)
 {
 	struct iwl_dqa_enable_cmd dqa_cmd = {
@@ -301,7 +336,7 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 	if (ret) {
 		struct iwl_trans *trans = mvm->trans;
 
-		if (trans->cfg->device_family == IWL_DEVICE_FAMILY_22000)
+		if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22000)
 			IWL_ERR(mvm,
 				"SecBoot CPU1 Status: 0x%x, CPU2 Status: 0x%x\n",
 				iwl_read_prph(trans, UMAG_SB_CPU_1_STATUS),
@@ -1007,9 +1042,16 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 		goto error;
 
 	/* Init RSS configuration */
-	/* TODO - remove 22000 disablement when we have RXQ config API */
-	if (iwl_mvm_has_new_rx_api(mvm) &&
-	    mvm->trans->cfg->device_family != IWL_DEVICE_FAMILY_22000) {
+	if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22000) {
+		ret = iwl_configure_rxq(mvm);
+		if (ret) {
+			IWL_ERR(mvm, "Failed to configure RX queues: %d\n",
+				ret);
+			goto error;
+		}
+	}
+
+	if (iwl_mvm_has_new_rx_api(mvm)) {
 		ret = iwl_send_rss_cfg_cmd(mvm);
 		if (ret) {
 			IWL_ERR(mvm, "Failed to configure RSS queues: %d\n",
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index 8ba16fc24e3a..b3fd20502abb 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -780,6 +780,10 @@ static int iwl_mvm_mac_ctxt_cmd_sta(struct iwl_mvm *mvm,
 	if (vif->probe_req_reg && vif->bss_conf.assoc && vif->p2p)
 		cmd.filter_flags |= cpu_to_le32(MAC_FILTER_IN_PROBE_REQUEST);
 
+	if (vif->bss_conf.assoc && vif->bss_conf.he_support &&
+	    !iwlwifi_mod_params.disable_11ax)
+		cmd.filter_flags |= cpu_to_le32(MAC_FILTER_IN_11AX);
+
 	return iwl_mvm_mac_ctxt_send_cmd(mvm, &cmd);
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index a6e072234398..b15b0d84bb7e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -36,6 +36,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018        Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -914,7 +915,7 @@ static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw,
 	enum ieee80211_ampdu_mlme_action action = params->action;
 	u16 tid = params->tid;
 	u16 *ssn = &params->ssn;
-	u8 buf_size = params->buf_size;
+	u16 buf_size = params->buf_size;
 	bool amsdu = params->amsdu;
 	u16 timeout = params->timeout;
 
@@ -1897,6 +1898,194 @@ void iwl_mvm_mu_mimo_grp_notif(struct iwl_mvm *mvm,
 			iwl_mvm_mu_mimo_iface_iterator, notif);
 }
 
+static u8 iwl_mvm_he_get_ppe_val(u8 *ppe, u8 ppe_pos_bit)
+{
+	u8 byte_num = ppe_pos_bit / 8;
+	u8 bit_num = ppe_pos_bit % 8;
+	u8 residue_bits;
+	u8 res;
+
+	if (bit_num <= 5)
+		return (ppe[byte_num] >> bit_num) &
+		       (BIT(IEEE80211_PPE_THRES_INFO_PPET_SIZE) - 1);
+
+	/*
+	 * If bit_num > 5, we have to combine bits with next byte.
+	 * Calculate how many bits we need to take from current byte (called
+	 * here "residue_bits"), and add them to bits from next byte.
+	 */
+
+	residue_bits = 8 - bit_num;
+
+	res = (ppe[byte_num + 1] &
+	       (BIT(IEEE80211_PPE_THRES_INFO_PPET_SIZE - residue_bits) - 1)) <<
+	      residue_bits;
+	res += (ppe[byte_num] >> bit_num) & (BIT(residue_bits) - 1);
+
+	return res;
+}
+
+static void iwl_mvm_cfg_he_sta(struct iwl_mvm *mvm,
+			       struct ieee80211_vif *vif, u8 sta_id)
+{
+	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+	struct iwl_he_sta_context_cmd sta_ctxt_cmd = {
+		.sta_id = sta_id,
+		.tid_limit = IWL_MAX_TID_COUNT,
+		.bss_color = vif->bss_conf.bss_color,
+		.htc_trig_based_pkt_ext = vif->bss_conf.htc_trig_based_pkt_ext,
+		.frame_time_rts_th =
+			cpu_to_le16(vif->bss_conf.frame_time_rts_th),
+	};
+	struct ieee80211_sta *sta;
+	u32 flags;
+	int i;
+
+	rcu_read_lock();
+
+	sta = rcu_dereference(mvm->fw_id_to_mac_id[sta_ctxt_cmd.sta_id]);
+	if (IS_ERR(sta)) {
+		rcu_read_unlock();
+		WARN(1, "Can't find STA to configure HE\n");
+		return;
+	}
+
+	if (!sta->he_cap.has_he) {
+		rcu_read_unlock();
+		return;
+	}
+
+	flags = 0;
+
+	/* HTC flags */
+	if (sta->he_cap.he_cap_elem.mac_cap_info[0] &
+	    IEEE80211_HE_MAC_CAP0_HTC_HE)
+		sta_ctxt_cmd.htc_flags |= cpu_to_le32(IWL_HE_HTC_SUPPORT);
+	if ((sta->he_cap.he_cap_elem.mac_cap_info[1] &
+	      IEEE80211_HE_MAC_CAP1_LINK_ADAPTATION) ||
+	    (sta->he_cap.he_cap_elem.mac_cap_info[2] &
+	      IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION)) {
+		u8 link_adap =
+			((sta->he_cap.he_cap_elem.mac_cap_info[2] &
+			  IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION) << 1) +
+			 (sta->he_cap.he_cap_elem.mac_cap_info[1] &
+			  IEEE80211_HE_MAC_CAP1_LINK_ADAPTATION);
+
+		if (link_adap == 2)
+			sta_ctxt_cmd.htc_flags |=
+				cpu_to_le32(IWL_HE_HTC_LINK_ADAP_UNSOLICITED);
+		else if (link_adap == 3)
+			sta_ctxt_cmd.htc_flags |=
+				cpu_to_le32(IWL_HE_HTC_LINK_ADAP_BOTH);
+	}
+	if (sta->he_cap.he_cap_elem.mac_cap_info[2] &
+	    IEEE80211_HE_MAC_CAP2_UL_MU_RESP_SCHED)
+		sta_ctxt_cmd.htc_flags |=
+			cpu_to_le32(IWL_HE_HTC_UL_MU_RESP_SCHED);
+	if (sta->he_cap.he_cap_elem.mac_cap_info[2] & IEEE80211_HE_MAC_CAP2_BSR)
+		sta_ctxt_cmd.htc_flags |= cpu_to_le32(IWL_HE_HTC_BSR_SUPP);
+	if (sta->he_cap.he_cap_elem.mac_cap_info[3] &
+	    IEEE80211_HE_MAC_CAP3_OMI_CONTROL)
+		sta_ctxt_cmd.htc_flags |= cpu_to_le32(IWL_HE_HTC_OMI_SUPP);
+	if (sta->he_cap.he_cap_elem.mac_cap_info[4] & IEEE80211_HE_MAC_CAP4_BQR)
+		sta_ctxt_cmd.htc_flags |= cpu_to_le32(IWL_HE_HTC_BQR_SUPP);
+
+	/* If PPE Thresholds exist, parse them into a FW-familiar format */
+	if (sta->he_cap.he_cap_elem.phy_cap_info[6] &
+	    IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) {
+		u8 nss = (sta->he_cap.ppe_thres[0] &
+			  IEEE80211_PPE_THRES_NSS_MASK) + 1;
+		u8 ru_index_bitmap =
+			(sta->he_cap.ppe_thres[0] &
+			 IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK) >>
+			IEEE80211_PPE_THRES_RU_INDEX_BITMASK_POS;
+		u8 *ppe = &sta->he_cap.ppe_thres[0];
+		u8 ppe_pos_bit = 7; /* Starting after PPE header */
+
+		/*
+		 * FW currently supports only nss == MAX_HE_SUPP_NSS
+		 *
+		 * If nss > MAX: we can ignore values we don't support
+		 * If nss < MAX: we can set zeros in other streams
+		 */
+		if (nss > MAX_HE_SUPP_NSS) {
+			IWL_INFO(mvm, "Got NSS = %d - trimming to %d\n", nss,
+				 MAX_HE_SUPP_NSS);
+			nss = MAX_HE_SUPP_NSS;
+		}
+
+		for (i = 0; i < nss; i++) {
+			u8 ru_index_tmp = ru_index_bitmap << 1;
+			u8 bw;
+
+			for (bw = 0; bw < MAX_HE_CHANNEL_BW_INDX; bw++) {
+				ru_index_tmp >>= 1;
+				if (!(ru_index_tmp & 1))
+					continue;
+
+				sta_ctxt_cmd.pkt_ext.pkt_ext_qam_th[i][bw][1] =
+					iwl_mvm_he_get_ppe_val(ppe,
+							       ppe_pos_bit);
+				ppe_pos_bit +=
+					IEEE80211_PPE_THRES_INFO_PPET_SIZE;
+				sta_ctxt_cmd.pkt_ext.pkt_ext_qam_th[i][bw][0] =
+					iwl_mvm_he_get_ppe_val(ppe,
+							       ppe_pos_bit);
+				ppe_pos_bit +=
+					IEEE80211_PPE_THRES_INFO_PPET_SIZE;
+			}
+		}
+
+		flags |= STA_CTXT_HE_PACKET_EXT;
+	}
+	rcu_read_unlock();
+
+	/* Mark MU EDCA as enabled, unless none detected on some AC */
+	flags |= STA_CTXT_HE_MU_EDCA_CW;
+	for (i = 0; i < AC_NUM; i++) {
+		struct ieee80211_he_mu_edca_param_ac_rec *mu_edca =
+			&mvmvif->queue_params[i].mu_edca_param_rec;
+
+		if (!mvmvif->queue_params[i].mu_edca) {
+			flags &= ~STA_CTXT_HE_MU_EDCA_CW;
+			break;
+		}
+
+		sta_ctxt_cmd.trig_based_txf[i].cwmin =
+			cpu_to_le16(mu_edca->ecw_min_max & 0xf);
+		sta_ctxt_cmd.trig_based_txf[i].cwmax =
+			cpu_to_le16((mu_edca->ecw_min_max & 0xf0) >> 4);
+		sta_ctxt_cmd.trig_based_txf[i].aifsn =
+			cpu_to_le16(mu_edca->aifsn);
+		sta_ctxt_cmd.trig_based_txf[i].mu_time =
+			cpu_to_le16(mu_edca->mu_edca_timer);
+	}
+
+	if (vif->bss_conf.multi_sta_back_32bit)
+		flags |= STA_CTXT_HE_32BIT_BA_BITMAP;
+
+	if (vif->bss_conf.ack_enabled)
+		flags |= STA_CTXT_HE_ACK_ENABLED;
+
+	if (vif->bss_conf.uora_exists) {
+		flags |= STA_CTXT_HE_TRIG_RND_ALLOC;
+
+		sta_ctxt_cmd.rand_alloc_ecwmin =
+			vif->bss_conf.uora_ocw_range & 0x7;
+		sta_ctxt_cmd.rand_alloc_ecwmax =
+			(vif->bss_conf.uora_ocw_range >> 3) & 0x7;
+	}
+
+	/* TODO: support Multi BSSID IE */
+
+	sta_ctxt_cmd.flags = cpu_to_le32(flags);
+
+	if (iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(STA_HE_CTXT_CMD,
+						 DATA_PATH_GROUP, 0),
+				 0, sizeof(sta_ctxt_cmd), &sta_ctxt_cmd))
+		IWL_ERR(mvm, "Failed to config FW to work HE!\n");
+}
+
 static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm,
 					     struct ieee80211_vif *vif,
 					     struct ieee80211_bss_conf *bss_conf,
@@ -1910,8 +2099,13 @@ static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm,
 	 * beacon interval, which was not known when the station interface was
 	 * added.
 	 */
-	if (changes & BSS_CHANGED_ASSOC && bss_conf->assoc)
+	if (changes & BSS_CHANGED_ASSOC && bss_conf->assoc) {
+		if (vif->bss_conf.he_support &&
+		    !iwlwifi_mod_params.disable_11ax)
+			iwl_mvm_cfg_he_sta(mvm, vif, mvmvif->ap_sta_id);
+
 		iwl_mvm_mac_ctxt_recalc_tsf_id(mvm, vif);
+	}
 
 	/*
 	 * If we're not associated yet, take the (new) BSSID before associating
@@ -4216,7 +4410,7 @@ static void iwl_mvm_mac_sta_statistics(struct ieee80211_hw *hw,
 
 	if (mvmsta->avg_energy) {
 		sinfo->signal_avg = mvmsta->avg_energy;
-		sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL_AVG);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG);
 	}
 
 	if (!fw_has_capa(&mvm->fw->ucode_capa,
@@ -4240,11 +4434,11 @@ static void iwl_mvm_mac_sta_statistics(struct ieee80211_hw *hw,
 
 	sinfo->rx_beacon = mvmvif->beacon_stats.num_beacons +
 			   mvmvif->beacon_stats.accu_num_beacons;
-	sinfo->filled |= BIT(NL80211_STA_INFO_BEACON_RX);
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BEACON_RX);
 	if (mvmvif->beacon_stats.avg_signal) {
 		/* firmware only reports a value after RXing a few beacons */
 		sinfo->rx_beacon_signal_avg = mvmvif->beacon_stats.avg_signal;
-		sinfo->filled |= BIT(NL80211_STA_INFO_BEACON_SIGNAL_AVG);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BEACON_SIGNAL_AVG);
 	}
  unlock:
 	mutex_unlock(&mvm->mutex);
@@ -4364,13 +4558,6 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm,
 		atomic_set(&mvm->queue_sync_counter,
 			   mvm->trans->num_rx_queues);
 
-	/* TODO - remove this when we have RXQ config API */
-	if (mvm->trans->cfg->device_family == IWL_DEVICE_FAMILY_22000) {
-		qmask = BIT(0);
-		if (notif->sync)
-			atomic_set(&mvm->queue_sync_counter, 1);
-	}
-
 	ret = iwl_mvm_notify_rx_queue(mvm, qmask, (u8 *)notif, size);
 	if (ret) {
 		IWL_ERR(mvm, "Failed to trigger RX queues sync (%d)\n", ret);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 6a4ba160c59e..b3987a0a7018 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -654,7 +654,7 @@ struct iwl_mvm_tcm {
 struct iwl_mvm_reorder_buffer {
 	u16 head_sn;
 	u16 num_stored;
-	u8 buf_size;
+	u16 buf_size;
 	int queue;
 	u16 last_amsdu;
 	u8 last_sub_index;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index ff1e518096c5..0e26619fb330 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -448,6 +448,8 @@ static const struct iwl_hcmd_names iwl_mvm_data_path_names[] = {
 	HCMD_NAME(DQA_ENABLE_CMD),
 	HCMD_NAME(UPDATE_MU_GROUPS_CMD),
 	HCMD_NAME(TRIGGER_RX_QUEUES_NOTIF_CMD),
+	HCMD_NAME(STA_HE_CTXT_CMD),
+	HCMD_NAME(RFH_QUEUE_CONFIG_CMD),
 	HCMD_NAME(STA_PM_NOTIF),
 	HCMD_NAME(MU_GROUP_MGMT_NOTIF),
 	HCMD_NAME(RX_QUEUES_NOTIFICATION),
@@ -620,7 +622,11 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 
 	if (iwl_mvm_has_new_rx_api(mvm)) {
 		op_mode->ops = &iwl_mvm_ops_mq;
-		trans->rx_mpdu_cmd_hdr_size = sizeof(struct iwl_rx_mpdu_desc);
+		trans->rx_mpdu_cmd_hdr_size =
+			(trans->cfg->device_family >=
+			 IWL_DEVICE_FAMILY_22560) ?
+			sizeof(struct iwl_rx_mpdu_desc) :
+			IWL_RX_DESC_SIZE_V1;
 	} else {
 		op_mode->ops = &iwl_mvm_ops;
 		trans->rx_mpdu_cmd_hdr_size =
@@ -703,11 +709,17 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	}
 
 	/* the hardware splits the A-MSDU */
-	if (mvm->cfg->mq_rx_supported)
+	if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
+		trans_cfg.rx_buf_size = IWL_AMSDU_2K;
+		/* TODO: remove when balanced power mode is fw supported */
+		iwlmvm_mod_params.power_scheme = IWL_POWER_SCHEME_CAM;
+	} else if (mvm->cfg->mq_rx_supported) {
 		trans_cfg.rx_buf_size = IWL_AMSDU_4K;
+	}
 
 	trans->wide_cmd_header = true;
-	trans_cfg.bc_table_dword = true;
+	trans_cfg.bc_table_dword =
+		mvm->trans->cfg->device_family < IWL_DEVICE_FAMILY_22560;
 
 	trans_cfg.command_groups = iwl_mvm_groups;
 	trans_cfg.command_groups_size = ARRAY_SIZE(iwl_mvm_groups);
@@ -738,6 +750,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	memcpy(trans->dbg_conf_tlv, mvm->fw->dbg_conf_tlv,
 	       sizeof(trans->dbg_conf_tlv));
 	trans->dbg_trigger_tlv = mvm->fw->dbg_trigger_tlv;
+	trans->dbg_dump_mask = mvm->fw->dbg_dump_mask;
 
 	trans->iml = mvm->fw->iml;
 	trans->iml_len = mvm->fw->iml_len;
@@ -1003,10 +1016,8 @@ static void iwl_mvm_rx_common(struct iwl_mvm *mvm,
 		list_add_tail(&entry->list, &mvm->async_handlers_list);
 		spin_unlock(&mvm->async_handlers_lock);
 		schedule_work(&mvm->async_handlers_wk);
-		return;
+		break;
 	}
-
-	iwl_fwrt_handle_notification(&mvm->fwrt, rxb);
 }
 
 static void iwl_mvm_rx(struct iwl_op_mode *op_mode,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
index b8b2b819e8e7..8169d1450b3b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
@@ -183,6 +183,43 @@ rs_fw_vht_set_enabled_rates(const struct ieee80211_sta *sta,
 	}
 }
 
+static u16 rs_fw_he_ieee80211_mcs_to_rs_mcs(u16 mcs)
+{
+	switch (mcs) {
+	case IEEE80211_HE_MCS_SUPPORT_0_7:
+		return BIT(IWL_TLC_MNG_HT_RATE_MCS7 + 1) - 1;
+	case IEEE80211_HE_MCS_SUPPORT_0_9:
+		return BIT(IWL_TLC_MNG_HT_RATE_MCS9 + 1) - 1;
+	case IEEE80211_HE_MCS_SUPPORT_0_11:
+		return BIT(IWL_TLC_MNG_HT_RATE_MCS11 + 1) - 1;
+	case IEEE80211_HE_MCS_NOT_SUPPORTED:
+		return 0;
+	}
+
+	WARN(1, "invalid HE MCS %d\n", mcs);
+	return 0;
+}
+
+static void
+rs_fw_he_set_enabled_rates(const struct ieee80211_sta *sta,
+			   const struct ieee80211_sta_he_cap *he_cap,
+			   struct iwl_tlc_config_cmd *cmd)
+{
+	u16 mcs_160 = le16_to_cpu(sta->he_cap.he_mcs_nss_supp.rx_mcs_160);
+	u16 mcs_80 = le16_to_cpu(sta->he_cap.he_mcs_nss_supp.rx_mcs_80);
+	int i;
+
+	for (i = 0; i < sta->rx_nss && i < MAX_NSS; i++) {
+		u16 _mcs_160 = (mcs_160 >> (2 * i)) & 0x3;
+		u16 _mcs_80 = (mcs_80 >> (2 * i)) & 0x3;
+
+		cmd->ht_rates[i][0] =
+			cpu_to_le16(rs_fw_he_ieee80211_mcs_to_rs_mcs(_mcs_80));
+		cmd->ht_rates[i][1] =
+			cpu_to_le16(rs_fw_he_ieee80211_mcs_to_rs_mcs(_mcs_160));
+	}
+}
+
 static void rs_fw_set_supp_rates(struct ieee80211_sta *sta,
 				 struct ieee80211_supported_band *sband,
 				 struct iwl_tlc_config_cmd *cmd)
@@ -192,6 +229,7 @@ static void rs_fw_set_supp_rates(struct ieee80211_sta *sta,
 	unsigned long supp; /* must be unsigned long for for_each_set_bit */
 	const struct ieee80211_sta_ht_cap *ht_cap = &sta->ht_cap;
 	const struct ieee80211_sta_vht_cap *vht_cap = &sta->vht_cap;
+	const struct ieee80211_sta_he_cap *he_cap = &sta->he_cap;
 
 	/* non HT rates */
 	supp = 0;
@@ -202,7 +240,11 @@ static void rs_fw_set_supp_rates(struct ieee80211_sta *sta,
 	cmd->non_ht_rates = cpu_to_le16(supp);
 	cmd->mode = IWL_TLC_MNG_MODE_NON_HT;
 
-	if (vht_cap && vht_cap->vht_supported) {
+	/* HT/VHT rates */
+	if (he_cap && he_cap->has_he) {
+		cmd->mode = IWL_TLC_MNG_MODE_HE;
+		rs_fw_he_set_enabled_rates(sta, he_cap, cmd);
+	} else if (vht_cap && vht_cap->vht_supported) {
 		cmd->mode = IWL_TLC_MNG_MODE_VHT;
 		rs_fw_vht_set_enabled_rates(sta, vht_cap, cmd);
 	} else if (ht_cap && ht_cap->ht_supported) {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
index 642da10b0b7f..30cfd7d50bc9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
@@ -363,7 +363,8 @@ static int iwl_hwrate_to_plcp_idx(u32 rate_n_flags)
 			idx += 1;
 		if ((idx >= IWL_FIRST_HT_RATE) && (idx <= IWL_LAST_HT_RATE))
 			return idx;
-	} else if (rate_n_flags & RATE_MCS_VHT_MSK) {
+	} else if (rate_n_flags & RATE_MCS_VHT_MSK ||
+		   rate_n_flags & RATE_MCS_HE_MSK) {
 		idx = rate_n_flags & RATE_VHT_MCS_RATE_CODE_MSK;
 		idx += IWL_RATE_MCS_0_INDEX;
 
@@ -372,6 +373,9 @@ static int iwl_hwrate_to_plcp_idx(u32 rate_n_flags)
 			idx++;
 		if ((idx >= IWL_FIRST_VHT_RATE) && (idx <= IWL_LAST_VHT_RATE))
 			return idx;
+		if ((rate_n_flags & RATE_MCS_HE_MSK) &&
+		    (idx <= IWL_LAST_HE_RATE))
+			return idx;
 	} else {
 		/* legacy rate format, search for match in table */
 
@@ -516,6 +520,8 @@ static const char *rs_pretty_lq_type(enum iwl_table_type type)
 		[LQ_HT_MIMO2] = "HT MIMO",
 		[LQ_VHT_SISO] = "VHT SISO",
 		[LQ_VHT_MIMO2] = "VHT MIMO",
+		[LQ_HE_SISO] = "HE SISO",
+		[LQ_HE_MIMO2] = "HE MIMO",
 	};
 
 	if (type < LQ_NONE || type >= LQ_MAX)
@@ -900,7 +906,8 @@ static int rs_rate_from_ucode_rate(const u32 ucode_rate,
 
 	/* Legacy */
 	if (!(ucode_rate & RATE_MCS_HT_MSK) &&
-	    !(ucode_rate & RATE_MCS_VHT_MSK)) {
+	    !(ucode_rate & RATE_MCS_VHT_MSK) &&
+	    !(ucode_rate & RATE_MCS_HE_MSK)) {
 		if (num_of_ant == 1) {
 			if (band == NL80211_BAND_5GHZ)
 				rate->type = LQ_LEGACY_A;
@@ -911,7 +918,7 @@ static int rs_rate_from_ucode_rate(const u32 ucode_rate,
 		return 0;
 	}
 
-	/* HT or VHT */
+	/* HT, VHT or HE */
 	if (ucode_rate & RATE_MCS_SGI_MSK)
 		rate->sgi = true;
 	if (ucode_rate & RATE_MCS_LDPC_MSK)
@@ -953,10 +960,24 @@ static int rs_rate_from_ucode_rate(const u32 ucode_rate,
 		} else {
 			WARN_ON_ONCE(1);
 		}
+	} else if (ucode_rate & RATE_MCS_HE_MSK) {
+		nss = ((ucode_rate & RATE_VHT_MCS_NSS_MSK) >>
+		      RATE_VHT_MCS_NSS_POS) + 1;
+
+		if (nss == 1) {
+			rate->type = LQ_HE_SISO;
+			WARN_ONCE(!rate->stbc && !rate->bfer && num_of_ant != 1,
+				  "stbc %d bfer %d", rate->stbc, rate->bfer);
+		} else if (nss == 2) {
+			rate->type = LQ_HE_MIMO2;
+			WARN_ON_ONCE(num_of_ant != 2);
+		} else {
+			WARN_ON_ONCE(1);
+		}
 	}
 
 	WARN_ON_ONCE(rate->bw == RATE_MCS_CHAN_WIDTH_80 &&
-		     !is_vht(rate));
+		     !is_he(rate) && !is_vht(rate));
 
 	return 0;
 }
@@ -3606,7 +3627,8 @@ int rs_pretty_print_rate(char *buf, int bufsz, const u32 rate)
 	u8 ant = (rate & RATE_MCS_ANT_ABC_MSK) >> RATE_MCS_ANT_POS;
 
 	if (!(rate & RATE_MCS_HT_MSK) &&
-	    !(rate & RATE_MCS_VHT_MSK)) {
+	    !(rate & RATE_MCS_VHT_MSK) &&
+	    !(rate & RATE_MCS_HE_MSK)) {
 		int index = iwl_hwrate_to_plcp_idx(rate);
 
 		return scnprintf(buf, bufsz, "Legacy | ANT: %s Rate: %s Mbps\n",
@@ -3625,6 +3647,11 @@ int rs_pretty_print_rate(char *buf, int bufsz, const u32 rate)
 		mcs = rate & RATE_HT_MCS_INDEX_MSK;
 		nss = ((rate & RATE_HT_MCS_NSS_MSK)
 		       >> RATE_HT_MCS_NSS_POS) + 1;
+	} else if (rate & RATE_MCS_HE_MSK) {
+		type = "HE";
+		mcs = rate & RATE_VHT_MCS_RATE_CODE_MSK;
+		nss = ((rate & RATE_VHT_MCS_NSS_MSK)
+		       >> RATE_VHT_MCS_NSS_POS) + 1;
 	} else {
 		type = "Unknown"; /* shouldn't happen */
 	}
@@ -3886,6 +3913,8 @@ static ssize_t rs_sta_dbgfs_drv_tx_stats_read(struct file *file,
 		[IWL_RATE_MCS_7_INDEX] = "MCS7",
 		[IWL_RATE_MCS_8_INDEX] = "MCS8",
 		[IWL_RATE_MCS_9_INDEX] = "MCS9",
+		[IWL_RATE_MCS_10_INDEX] = "MCS10",
+		[IWL_RATE_MCS_11_INDEX] = "MCS11",
 	};
 
 	char *buff, *pos, *endpos;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h
index cffb8c852934..d2cf484e2b73 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h
@@ -144,8 +144,13 @@ enum {
 
 #define LINK_QUAL_AGG_FRAME_LIMIT_DEF	(63)
 #define LINK_QUAL_AGG_FRAME_LIMIT_MAX	(63)
-#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_DEF	(64)
-#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_MAX	(64)
+/*
+ * FIXME - various places in firmware API still use u8,
+ * e.g. LQ command and SCD config command.
+ * This should be 256 instead.
+ */
+#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_DEF	(255)
+#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_MAX	(255)
 #define LINK_QUAL_AGG_FRAME_LIMIT_MIN	(0)
 
 #define LQ_SIZE		2	/* 2 mode tables:  "Active" and "Search" */
@@ -162,6 +167,8 @@ enum iwl_table_type {
 	LQ_HT_MIMO2,
 	LQ_VHT_SISO,    /* VHT types */
 	LQ_VHT_MIMO2,
+	LQ_HE_SISO,     /* HE types */
+	LQ_HE_MIMO2,
 	LQ_MAX,
 };
 
@@ -183,11 +190,16 @@ struct rs_rate {
 #define is_type_ht_mimo2(type) ((type) == LQ_HT_MIMO2)
 #define is_type_vht_siso(type) ((type) == LQ_VHT_SISO)
 #define is_type_vht_mimo2(type) ((type) == LQ_VHT_MIMO2)
-#define is_type_siso(type) (is_type_ht_siso(type) || is_type_vht_siso(type))
-#define is_type_mimo2(type) (is_type_ht_mimo2(type) || is_type_vht_mimo2(type))
+#define is_type_he_siso(type) ((type) == LQ_HE_SISO)
+#define is_type_he_mimo2(type) ((type) == LQ_HE_MIMO2)
+#define is_type_siso(type) (is_type_ht_siso(type) || is_type_vht_siso(type) || \
+			    is_type_he_siso(type))
+#define is_type_mimo2(type) (is_type_ht_mimo2(type) || \
+			     is_type_vht_mimo2(type) || is_type_he_mimo2(type))
 #define is_type_mimo(type) (is_type_mimo2(type))
 #define is_type_ht(type) (is_type_ht_siso(type) || is_type_ht_mimo2(type))
 #define is_type_vht(type) (is_type_vht_siso(type) || is_type_vht_mimo2(type))
+#define is_type_he(type) (is_type_he_siso(type) || is_type_he_mimo2(type))
 #define is_type_a_band(type) ((type) == LQ_LEGACY_A)
 #define is_type_g_band(type) ((type) == LQ_LEGACY_G)
 
@@ -201,6 +213,7 @@ struct rs_rate {
 #define is_mimo(rate)         is_type_mimo((rate)->type)
 #define is_ht(rate)           is_type_ht((rate)->type)
 #define is_vht(rate)          is_type_vht((rate)->type)
+#define is_he(rate)           is_type_he((rate)->type)
 #define is_a_band(rate)       is_type_a_band((rate)->type)
 #define is_g_band(rate)       is_type_g_band((rate)->type)
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 129c4c09648d..b53148f972a4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -8,6 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -30,6 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -196,22 +198,31 @@ static void iwl_mvm_pass_packet_to_mac80211(struct iwl_mvm *mvm,
 					    struct sk_buff *skb, int queue,
 					    struct ieee80211_sta *sta)
 {
-	if (iwl_mvm_check_pn(mvm, skb, queue, sta))
+	struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb);
+
+	if (iwl_mvm_check_pn(mvm, skb, queue, sta)) {
 		kfree_skb(skb);
-	else
+	} else {
+		unsigned int radiotap_len = 0;
+
+		if (rx_status->flag & RX_FLAG_RADIOTAP_HE)
+			radiotap_len += sizeof(struct ieee80211_radiotap_he);
+		if (rx_status->flag & RX_FLAG_RADIOTAP_HE_MU)
+			radiotap_len += sizeof(struct ieee80211_radiotap_he_mu);
+		__skb_push(skb, radiotap_len);
 		ieee80211_rx_napi(mvm->hw, sta, skb, napi);
+	}
 }
 
 static void iwl_mvm_get_signal_strength(struct iwl_mvm *mvm,
-					struct iwl_rx_mpdu_desc *desc,
-					struct ieee80211_rx_status *rx_status)
+					struct ieee80211_rx_status *rx_status,
+					u32 rate_n_flags, int energy_a,
+					int energy_b)
 {
-	int energy_a, energy_b, max_energy;
-	u32 rate_flags = le32_to_cpu(desc->rate_n_flags);
+	int max_energy;
+	u32 rate_flags = rate_n_flags;
 
-	energy_a = desc->energy_a;
 	energy_a = energy_a ? -energy_a : S8_MIN;
-	energy_b = desc->energy_b;
 	energy_b = energy_b ? -energy_b : S8_MIN;
 	max_energy = max(energy_a, energy_b);
 
@@ -356,7 +367,8 @@ static bool iwl_mvm_is_dup(struct ieee80211_sta *sta, int queue,
 		tid = IWL_MAX_TID_COUNT;
 
 	/* If this wasn't a part of an A-MSDU the sub-frame index will be 0 */
-	sub_frame_idx = desc->amsdu_info & IWL_RX_MPDU_AMSDU_SUBFRAME_IDX_MASK;
+	sub_frame_idx = desc->amsdu_info &
+		IWL_RX_MPDU_AMSDU_SUBFRAME_IDX_MASK;
 
 	if (unlikely(ieee80211_has_retry(hdr->frame_control) &&
 		     dup_data->last_seq[tid] == hdr->seq_ctrl &&
@@ -850,17 +862,41 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 	struct ieee80211_rx_status *rx_status;
 	struct iwl_rx_packet *pkt = rxb_addr(rxb);
 	struct iwl_rx_mpdu_desc *desc = (void *)pkt->data;
-	struct ieee80211_hdr *hdr = (void *)(pkt->data + sizeof(*desc));
+	struct ieee80211_hdr *hdr;
 	u32 len = le16_to_cpu(desc->mpdu_len);
-	u32 rate_n_flags = le32_to_cpu(desc->rate_n_flags);
+	u32 rate_n_flags, gp2_on_air_rise;
 	u16 phy_info = le16_to_cpu(desc->phy_info);
 	struct ieee80211_sta *sta = NULL;
 	struct sk_buff *skb;
-	u8 crypt_len = 0;
+	u8 crypt_len = 0, channel, energy_a, energy_b;
+	struct ieee80211_radiotap_he *he = NULL;
+	struct ieee80211_radiotap_he_mu *he_mu = NULL;
+	u32 he_type = 0xffffffff;
+	/* this is invalid e.g. because puncture type doesn't allow 0b11 */
+#define HE_PHY_DATA_INVAL ((u64)-1)
+	u64 he_phy_data = HE_PHY_DATA_INVAL;
+	size_t desc_size;
 
 	if (unlikely(test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)))
 		return;
 
+	if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
+		rate_n_flags = le32_to_cpu(desc->v3.rate_n_flags);
+		channel = desc->v3.channel;
+		gp2_on_air_rise = le32_to_cpu(desc->v3.gp2_on_air_rise);
+		energy_a = desc->v3.energy_a;
+		energy_b = desc->v3.energy_b;
+		desc_size = sizeof(*desc);
+	} else {
+		rate_n_flags = le32_to_cpu(desc->v1.rate_n_flags);
+		channel = desc->v1.channel;
+		gp2_on_air_rise = le32_to_cpu(desc->v1.gp2_on_air_rise);
+		energy_a = desc->v1.energy_a;
+		energy_b = desc->v1.energy_b;
+		desc_size = IWL_RX_DESC_SIZE_V1;
+	}
+
+	hdr = (void *)(pkt->data + desc_size);
 	/* Dont use dev_alloc_skb(), we'll have enough headroom once
 	 * ieee80211_hdr pulled.
 	 */
@@ -882,6 +918,51 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 
 	rx_status = IEEE80211_SKB_RXCB(skb);
 
+	if (rate_n_flags & RATE_MCS_HE_MSK) {
+		static const struct ieee80211_radiotap_he known = {
+			.data1 = cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_DATA_MCS_KNOWN |
+					     IEEE80211_RADIOTAP_HE_DATA1_DATA_DCM_KNOWN |
+					     IEEE80211_RADIOTAP_HE_DATA1_STBC_KNOWN |
+					     IEEE80211_RADIOTAP_HE_DATA1_CODING_KNOWN),
+			.data2 = cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_GI_KNOWN |
+					     IEEE80211_RADIOTAP_HE_DATA2_TXBF_KNOWN),
+		};
+		static const struct ieee80211_radiotap_he_mu mu_known = {
+			.flags1 = cpu_to_le16(IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_MCS_KNOWN |
+					      IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_DCM_KNOWN |
+					      IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_SYMS_USERS_KNOWN |
+					      IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_COMP_KNOWN),
+			.flags2 = cpu_to_le16(IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW_KNOWN),
+		};
+		unsigned int radiotap_len = 0;
+
+		he = skb_put_data(skb, &known, sizeof(known));
+		radiotap_len += sizeof(known);
+		rx_status->flag |= RX_FLAG_RADIOTAP_HE;
+
+		he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK;
+
+		if (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD) {
+			if (mvm->trans->cfg->device_family >=
+			    IWL_DEVICE_FAMILY_22560)
+				he_phy_data = le64_to_cpu(desc->v3.he_phy_data);
+			else
+				he_phy_data = le64_to_cpu(desc->v1.he_phy_data);
+
+			if (he_type == RATE_MCS_HE_TYPE_MU) {
+				he_mu = skb_put_data(skb, &mu_known,
+						     sizeof(mu_known));
+				radiotap_len += sizeof(mu_known);
+				rx_status->flag |= RX_FLAG_RADIOTAP_HE_MU;
+			}
+		}
+
+		/* temporarily hide the radiotap data */
+		__skb_pull(skb, radiotap_len);
+	}
+
+	rx_status = IEEE80211_SKB_RXCB(skb);
+
 	if (iwl_mvm_rx_crypto(mvm, hdr, rx_status, phy_info, desc,
 			      le32_to_cpu(pkt->len_n_flags), queue,
 			      &crypt_len)) {
@@ -904,20 +985,80 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		rx_status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
 
 	if (likely(!(phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD))) {
-		rx_status->mactime = le64_to_cpu(desc->tsf_on_air_rise);
+		u64 tsf_on_air_rise;
+
+		if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+			tsf_on_air_rise = le64_to_cpu(desc->v3.tsf_on_air_rise);
+		else
+			tsf_on_air_rise = le64_to_cpu(desc->v1.tsf_on_air_rise);
+
+		rx_status->mactime = tsf_on_air_rise;
 		/* TSF as indicated by the firmware is at INA time */
 		rx_status->flag |= RX_FLAG_MACTIME_PLCP_START;
+	} else if (he_type == RATE_MCS_HE_TYPE_SU) {
+		u64 he_phy_data;
+
+		if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+			he_phy_data = le64_to_cpu(desc->v3.he_phy_data);
+		else
+			he_phy_data = le64_to_cpu(desc->v1.he_phy_data);
+
+		he->data1 |=
+			cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_UL_DL_KNOWN);
+		if (FIELD_GET(IWL_RX_HE_PHY_UPLINK,
+			      he_phy_data))
+			he->data3 |=
+				cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA3_UL_DL);
+
+		if (!queue && !(phy_info & IWL_RX_MPDU_PHY_AMPDU)) {
+			rx_status->ampdu_reference = mvm->ampdu_ref;
+			mvm->ampdu_ref++;
+
+			rx_status->flag |= RX_FLAG_AMPDU_DETAILS;
+			rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN;
+			if (FIELD_GET(IWL_RX_HE_PHY_DELIM_EOF,
+				      he_phy_data))
+				rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT;
+		}
+	} else if (he_mu && he_phy_data != HE_PHY_DATA_INVAL) {
+		he_mu->flags1 |=
+			le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_SIBG_SYM_OR_USER_NUM_MASK,
+						   he_phy_data),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_SYMS_USERS);
+		he_mu->flags1 |=
+			le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_SIGB_DCM,
+						   he_phy_data),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_DCM);
+		he_mu->flags1 |=
+			le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_SIGB_MCS_MASK,
+						   he_phy_data),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_MCS);
+		he_mu->flags2 |=
+			le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_SIGB_COMPRESSION,
+						   he_phy_data),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_COMP);
+		he_mu->flags2 |=
+			le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_PREAMBLE_PUNC_TYPE_MASK,
+						   he_phy_data),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW);
 	}
-	rx_status->device_timestamp = le32_to_cpu(desc->gp2_on_air_rise);
-	rx_status->band = desc->channel > 14 ? NL80211_BAND_5GHZ :
-					       NL80211_BAND_2GHZ;
-	rx_status->freq = ieee80211_channel_to_frequency(desc->channel,
+	rx_status->device_timestamp = gp2_on_air_rise;
+	rx_status->band = channel > 14 ? NL80211_BAND_5GHZ :
+		NL80211_BAND_2GHZ;
+	rx_status->freq = ieee80211_channel_to_frequency(channel,
 							 rx_status->band);
-	iwl_mvm_get_signal_strength(mvm, desc, rx_status);
+	iwl_mvm_get_signal_strength(mvm, rx_status, rate_n_flags, energy_a,
+				    energy_b);
 
 	/* update aggregation data for monitor sake on default queue */
 	if (!queue && (phy_info & IWL_RX_MPDU_PHY_AMPDU)) {
 		bool toggle_bit = phy_info & IWL_RX_MPDU_PHY_AMPDU_TOGGLE;
+		u64 he_phy_data;
+
+		if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+			he_phy_data = le64_to_cpu(desc->v3.he_phy_data);
+		else
+			he_phy_data = le64_to_cpu(desc->v1.he_phy_data);
 
 		rx_status->flag |= RX_FLAG_AMPDU_DETAILS;
 		rx_status->ampdu_reference = mvm->ampdu_ref;
@@ -925,6 +1066,15 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		if (toggle_bit != mvm->ampdu_toggle) {
 			mvm->ampdu_ref++;
 			mvm->ampdu_toggle = toggle_bit;
+
+			if (he_phy_data != HE_PHY_DATA_INVAL &&
+			    he_type == RATE_MCS_HE_TYPE_MU) {
+				rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN;
+				if (FIELD_GET(IWL_RX_HE_PHY_DELIM_EOF,
+					      he_phy_data))
+					rx_status->flag |=
+						RX_FLAG_AMPDU_EOF_BIT;
+			}
 		}
 	}
 
@@ -1033,7 +1183,6 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		}
 	}
 
-	/* Set up the HT phy flags */
 	switch (rate_n_flags & RATE_MCS_CHAN_WIDTH_MSK) {
 	case RATE_MCS_CHAN_WIDTH_20:
 		break;
@@ -1048,6 +1197,70 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		break;
 	}
 
+	if (he_type == RATE_MCS_HE_TYPE_EXT_SU &&
+	    rate_n_flags & RATE_MCS_HE_106T_MSK) {
+		rx_status->bw = RATE_INFO_BW_HE_RU;
+		rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_106;
+	}
+
+	if (rate_n_flags & RATE_MCS_HE_MSK &&
+	    phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD &&
+	    he_type == RATE_MCS_HE_TYPE_MU) {
+		/*
+		 * Unfortunately, we have to leave the mac80211 data
+		 * incorrect for the case that we receive an HE-MU
+		 * transmission and *don't* have the he_mu pointer,
+		 * i.e. we don't have the phy data (due to the bits
+		 * being used for TSF). This shouldn't happen though
+		 * as management frames where we need the TSF/timers
+		 * are not be transmitted in HE-MU, I think.
+		 */
+		u8 ru = FIELD_GET(IWL_RX_HE_PHY_RU_ALLOC_MASK, he_phy_data);
+		u8 offs = 0;
+
+		rx_status->bw = RATE_INFO_BW_HE_RU;
+
+		switch (ru) {
+		case 0 ... 36:
+			rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_26;
+			offs = ru;
+			break;
+		case 37 ... 52:
+			rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_52;
+			offs = ru - 37;
+			break;
+		case 53 ... 60:
+			rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_106;
+			offs = ru - 53;
+			break;
+		case 61 ... 64:
+			rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_242;
+			offs = ru - 61;
+			break;
+		case 65 ... 66:
+			rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_484;
+			offs = ru - 65;
+			break;
+		case 67:
+			rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_996;
+			break;
+		case 68:
+			rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_2x996;
+			break;
+		}
+		he->data2 |=
+			le16_encode_bits(offs,
+					 IEEE80211_RADIOTAP_HE_DATA2_RU_OFFSET);
+		he->data2 |=
+			cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_KNOWN);
+		if (he_phy_data & IWL_RX_HE_PHY_RU_ALLOC_SEC80)
+			he->data2 |=
+				cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_SEC);
+	} else if (he) {
+		he->data1 |=
+			cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_BW_RU_ALLOC_KNOWN);
+	}
+
 	if (!(rate_n_flags & RATE_MCS_CCK_MSK) &&
 	    rate_n_flags & RATE_MCS_SGI_MSK)
 		rx_status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
@@ -1072,6 +1285,119 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT;
 		if (rate_n_flags & RATE_MCS_BF_MSK)
 			rx_status->enc_flags |= RX_ENC_FLAG_BF;
+	} else if (he) {
+		u8 stbc = (rate_n_flags & RATE_MCS_STBC_MSK) >>
+				RATE_MCS_STBC_POS;
+		rx_status->nss =
+			((rate_n_flags & RATE_VHT_MCS_NSS_MSK) >>
+						RATE_VHT_MCS_NSS_POS) + 1;
+		rx_status->rate_idx = rate_n_flags & RATE_VHT_MCS_RATE_CODE_MSK;
+		rx_status->encoding = RX_ENC_HE;
+		rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT;
+		if (rate_n_flags & RATE_MCS_BF_MSK)
+			rx_status->enc_flags |= RX_ENC_FLAG_BF;
+
+		rx_status->he_dcm =
+			!!(rate_n_flags & RATE_HE_DUAL_CARRIER_MODE_MSK);
+
+#define CHECK_TYPE(F)							\
+	BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA1_FORMAT_ ## F !=	\
+		     (RATE_MCS_HE_TYPE_ ## F >> RATE_MCS_HE_TYPE_POS))
+
+		CHECK_TYPE(SU);
+		CHECK_TYPE(EXT_SU);
+		CHECK_TYPE(MU);
+		CHECK_TYPE(TRIG);
+
+		he->data1 |= cpu_to_le16(he_type >> RATE_MCS_HE_TYPE_POS);
+
+		if (rate_n_flags & RATE_MCS_BF_POS)
+			he->data5 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA5_TXBF);
+
+		switch ((rate_n_flags & RATE_MCS_HE_GI_LTF_MSK) >>
+			RATE_MCS_HE_GI_LTF_POS) {
+		case 0:
+			rx_status->he_gi = NL80211_RATE_INFO_HE_GI_0_8;
+			break;
+		case 1:
+			rx_status->he_gi = NL80211_RATE_INFO_HE_GI_0_8;
+			break;
+		case 2:
+			rx_status->he_gi = NL80211_RATE_INFO_HE_GI_1_6;
+			break;
+		case 3:
+			if (rate_n_flags & RATE_MCS_SGI_MSK)
+				rx_status->he_gi = NL80211_RATE_INFO_HE_GI_0_8;
+			else
+				rx_status->he_gi = NL80211_RATE_INFO_HE_GI_3_2;
+			break;
+		}
+
+		switch (he_type) {
+		case RATE_MCS_HE_TYPE_SU: {
+			u16 val;
+
+			/* LTF syms correspond to streams */
+			he->data2 |=
+				cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_NUM_LTF_SYMS_KNOWN);
+			switch (rx_status->nss) {
+			case 1:
+				val = 0;
+				break;
+			case 2:
+				val = 1;
+				break;
+			case 3:
+			case 4:
+				val = 2;
+				break;
+			case 5:
+			case 6:
+				val = 3;
+				break;
+			case 7:
+			case 8:
+				val = 4;
+				break;
+			default:
+				WARN_ONCE(1, "invalid nss: %d\n",
+					  rx_status->nss);
+				val = 0;
+			}
+			he->data5 |=
+				le16_encode_bits(val,
+						 IEEE80211_RADIOTAP_HE_DATA5_NUM_LTF_SYMS);
+			}
+			break;
+		case RATE_MCS_HE_TYPE_MU: {
+			u16 val;
+			u64 he_phy_data;
+
+			if (mvm->trans->cfg->device_family >=
+			    IWL_DEVICE_FAMILY_22560)
+				he_phy_data = le64_to_cpu(desc->v3.he_phy_data);
+			else
+				he_phy_data = le64_to_cpu(desc->v1.he_phy_data);
+
+			if (he_phy_data == HE_PHY_DATA_INVAL)
+				break;
+
+			val = FIELD_GET(IWL_RX_HE_PHY_HE_LTF_NUM_MASK,
+					he_phy_data);
+
+			he->data2 |=
+				cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_NUM_LTF_SYMS_KNOWN);
+			he->data5 |=
+				cpu_to_le16(FIELD_PREP(
+					IEEE80211_RADIOTAP_HE_DATA5_NUM_LTF_SYMS,
+					val));
+			}
+			break;
+		case RATE_MCS_HE_TYPE_EXT_SU:
+		case RATE_MCS_HE_TYPE_TRIG:
+			/* not supported yet */
+			break;
+		}
 	} else {
 		int rate = iwl_mvm_legacy_rate_to_mac80211_idx(rate_n_flags,
 							       rx_status->band);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 9263b9aa8b72..18db1ed92d9b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -2184,7 +2184,7 @@ static void iwl_mvm_free_reorder(struct iwl_mvm *mvm,
 
 static void iwl_mvm_init_reorder_buffer(struct iwl_mvm *mvm,
 					struct iwl_mvm_baid_data *data,
-					u16 ssn, u8 buf_size)
+					u16 ssn, u16 buf_size)
 {
 	int i;
 
@@ -2211,7 +2211,7 @@ static void iwl_mvm_init_reorder_buffer(struct iwl_mvm *mvm,
 }
 
 int iwl_mvm_sta_rx_agg(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
-		       int tid, u16 ssn, bool start, u8 buf_size, u16 timeout)
+		       int tid, u16 ssn, bool start, u16 buf_size, u16 timeout)
 {
 	struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta);
 	struct iwl_mvm_add_sta_cmd cmd = {};
@@ -2273,7 +2273,7 @@ int iwl_mvm_sta_rx_agg(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 	if (start) {
 		cmd.add_immediate_ba_tid = (u8) tid;
 		cmd.add_immediate_ba_ssn = cpu_to_le16(ssn);
-		cmd.rx_ba_window = cpu_to_le16((u16)buf_size);
+		cmd.rx_ba_window = cpu_to_le16(buf_size);
 	} else {
 		cmd.remove_immediate_ba_tid = (u8) tid;
 	}
@@ -2559,7 +2559,7 @@ out:
 }
 
 int iwl_mvm_sta_tx_agg_oper(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
-			    struct ieee80211_sta *sta, u16 tid, u8 buf_size,
+			    struct ieee80211_sta *sta, u16 tid, u16 buf_size,
 			    bool amsdu)
 {
 	struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
index 1c43ea8dd8cc..0fc211108149 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
@@ -412,7 +412,7 @@ struct iwl_mvm_sta {
 	u32 tfd_queue_msk;
 	u32 mac_id_n_color;
 	u16 tid_disable_agg;
-	u8 max_agg_bufsize;
+	u16 max_agg_bufsize;
 	enum iwl_sta_type sta_type;
 	enum ieee80211_sta_state sta_state;
 	bool bt_reduced_txpower;
@@ -518,11 +518,11 @@ void iwl_mvm_rx_eosp_notif(struct iwl_mvm *mvm,
 
 /* AMPDU */
 int iwl_mvm_sta_rx_agg(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
-		       int tid, u16 ssn, bool start, u8 buf_size, u16 timeout);
+		       int tid, u16 ssn, bool start, u16 buf_size, u16 timeout);
 int iwl_mvm_sta_tx_agg_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			struct ieee80211_sta *sta, u16 tid, u16 *ssn);
 int iwl_mvm_sta_tx_agg_oper(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
-			    struct ieee80211_sta *sta, u16 tid, u8 buf_size,
+			    struct ieee80211_sta *sta, u16 tid, u16 buf_size,
 			    bool amsdu);
 int iwl_mvm_sta_tx_agg_stop(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			    struct ieee80211_sta *sta, u16 tid);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index cf2591f2ac23..ff193dca2020 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -484,13 +484,15 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 
 	/* Make sure we zero enough of dev_cmd */
 	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen2) > sizeof(*tx_cmd));
+	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen3) > sizeof(*tx_cmd));
 
 	memset(dev_cmd, 0, sizeof(dev_cmd->hdr) + sizeof(*tx_cmd));
 	dev_cmd->hdr.cmd = TX_CMD;
 
 	if (iwl_mvm_has_new_tx_api(mvm)) {
-		struct iwl_tx_cmd_gen2 *cmd = (void *)dev_cmd->payload;
 		u16 offload_assist = 0;
+		u32 rate_n_flags = 0;
+		u16 flags = 0;
 
 		if (ieee80211_is_data_qos(hdr->frame_control)) {
 			u8 *qc = ieee80211_get_qos_ctl(hdr);
@@ -507,25 +509,43 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 		    !(offload_assist & BIT(TX_CMD_OFFLD_AMSDU)))
 			offload_assist |= BIT(TX_CMD_OFFLD_PAD);
 
-		cmd->offload_assist |= cpu_to_le16(offload_assist);
+		if (!info->control.hw_key)
+			flags |= IWL_TX_FLAGS_ENCRYPT_DIS;
 
-		/* Total # bytes to be transmitted */
-		cmd->len = cpu_to_le16((u16)skb->len);
+		/* For data packets rate info comes from the fw */
+		if (!(ieee80211_is_data(hdr->frame_control) && sta)) {
+			flags |= IWL_TX_FLAGS_CMD_RATE;
+			rate_n_flags = iwl_mvm_get_tx_rate(mvm, info, sta);
+		}
 
-		/* Copy MAC header from skb into command buffer */
-		memcpy(cmd->hdr, hdr, hdrlen);
+		if (mvm->trans->cfg->device_family >=
+		    IWL_DEVICE_FAMILY_22560) {
+			struct iwl_tx_cmd_gen3 *cmd = (void *)dev_cmd->payload;
 
-		if (!info->control.hw_key)
-			cmd->flags |= cpu_to_le32(IWL_TX_FLAGS_ENCRYPT_DIS);
+			cmd->offload_assist |= cpu_to_le32(offload_assist);
 
-		/* For data packets rate info comes from the fw */
-		if (ieee80211_is_data(hdr->frame_control) && sta)
-			goto out;
+			/* Total # bytes to be transmitted */
+			cmd->len = cpu_to_le16((u16)skb->len);
 
-		cmd->flags |= cpu_to_le32(IWL_TX_FLAGS_CMD_RATE);
-		cmd->rate_n_flags =
-			cpu_to_le32(iwl_mvm_get_tx_rate(mvm, info, sta));
+			/* Copy MAC header from skb into command buffer */
+			memcpy(cmd->hdr, hdr, hdrlen);
 
+			cmd->flags = cpu_to_le16(flags);
+			cmd->rate_n_flags = cpu_to_le32(rate_n_flags);
+		} else {
+			struct iwl_tx_cmd_gen2 *cmd = (void *)dev_cmd->payload;
+
+			cmd->offload_assist |= cpu_to_le16(offload_assist);
+
+			/* Total # bytes to be transmitted */
+			cmd->len = cpu_to_le16((u16)skb->len);
+
+			/* Copy MAC header from skb into command buffer */
+			memcpy(cmd->hdr, hdr, hdrlen);
+
+			cmd->flags = cpu_to_le32(flags);
+			cmd->rate_n_flags = cpu_to_le32(rate_n_flags);
+		}
 		goto out;
 	}
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
new file mode 100644
index 000000000000..2146fda8da2f
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
@@ -0,0 +1,207 @@
+/******************************************************************************
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2018 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2018 Intel Corporation
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *  * Neither the name Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *****************************************************************************/
+
+#include "iwl-trans.h"
+#include "iwl-fh.h"
+#include "iwl-context-info-gen3.h"
+#include "internal.h"
+#include "iwl-prph.h"
+
+int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
+				 const struct fw_img *fw)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_context_info_gen3 *ctxt_info_gen3;
+	struct iwl_prph_scratch *prph_scratch;
+	struct iwl_prph_scratch_ctrl_cfg *prph_sc_ctrl;
+	struct iwl_prph_info *prph_info;
+	void *iml_img;
+	u32 control_flags = 0;
+	int ret;
+
+	/* Allocate prph scratch */
+	prph_scratch = dma_alloc_coherent(trans->dev, sizeof(*prph_scratch),
+					  &trans_pcie->prph_scratch_dma_addr,
+					  GFP_KERNEL);
+	if (!prph_scratch)
+		return -ENOMEM;
+
+	prph_sc_ctrl = &prph_scratch->ctrl_cfg;
+
+	prph_sc_ctrl->version.version = 0;
+	prph_sc_ctrl->version.mac_id =
+		cpu_to_le16((u16)iwl_read32(trans, CSR_HW_REV));
+	prph_sc_ctrl->version.size = cpu_to_le16(sizeof(*prph_scratch) / 4);
+
+	control_flags = IWL_PRPH_SCRATCH_RB_SIZE_4K |
+			IWL_PRPH_SCRATCH_MTR_MODE |
+			(IWL_PRPH_MTR_FORMAT_256B &
+			 IWL_PRPH_SCRATCH_MTR_FORMAT) |
+			IWL_PRPH_SCRATCH_EARLY_DEBUG_EN |
+			IWL_PRPH_SCRATCH_EDBG_DEST_DRAM;
+	prph_sc_ctrl->control.control_flags = cpu_to_le32(control_flags);
+
+	/* initialize RX default queue */
+	prph_sc_ctrl->rbd_cfg.free_rbd_addr =
+		cpu_to_le64(trans_pcie->rxq->bd_dma);
+
+	/* Configure debug, for integration */
+	iwl_pcie_alloc_fw_monitor(trans, 0);
+	prph_sc_ctrl->hwm_cfg.hwm_base_addr =
+		cpu_to_le64(trans_pcie->fw_mon_phys);
+	prph_sc_ctrl->hwm_cfg.hwm_size =
+		cpu_to_le32(trans_pcie->fw_mon_size);
+
+	/* allocate ucode sections in dram and set addresses */
+	ret = iwl_pcie_init_fw_sec(trans, fw, &prph_scratch->dram);
+	if (ret) {
+		dma_free_coherent(trans->dev,
+				  sizeof(*prph_scratch),
+				  prph_scratch,
+				  trans_pcie->prph_scratch_dma_addr);
+		return ret;
+	}
+
+	/* Allocate prph information
+	 * currently we don't assign to the prph info anything, but it would get
+	 * assigned later */
+	prph_info = dma_alloc_coherent(trans->dev, sizeof(*prph_info),
+				       &trans_pcie->prph_info_dma_addr,
+				       GFP_KERNEL);
+	if (!prph_info)
+		return -ENOMEM;
+
+	/* Allocate context info */
+	ctxt_info_gen3 = dma_alloc_coherent(trans->dev,
+					    sizeof(*ctxt_info_gen3),
+					    &trans_pcie->ctxt_info_dma_addr,
+					    GFP_KERNEL);
+	if (!ctxt_info_gen3)
+		return -ENOMEM;
+
+	ctxt_info_gen3->prph_info_base_addr =
+		cpu_to_le64(trans_pcie->prph_info_dma_addr);
+	ctxt_info_gen3->prph_scratch_base_addr =
+		cpu_to_le64(trans_pcie->prph_scratch_dma_addr);
+	ctxt_info_gen3->prph_scratch_size =
+		cpu_to_le32(sizeof(*prph_scratch));
+	ctxt_info_gen3->cr_head_idx_arr_base_addr =
+		cpu_to_le64(trans_pcie->rxq->rb_stts_dma);
+	ctxt_info_gen3->tr_tail_idx_arr_base_addr =
+		cpu_to_le64(trans_pcie->rxq->tr_tail_dma);
+	ctxt_info_gen3->cr_tail_idx_arr_base_addr =
+		cpu_to_le64(trans_pcie->rxq->cr_tail_dma);
+	ctxt_info_gen3->cr_idx_arr_size =
+		cpu_to_le16(IWL_NUM_OF_COMPLETION_RINGS);
+	ctxt_info_gen3->tr_idx_arr_size =
+		cpu_to_le16(IWL_NUM_OF_TRANSFER_RINGS);
+	ctxt_info_gen3->mtr_base_addr =
+		cpu_to_le64(trans_pcie->txq[trans_pcie->cmd_queue]->dma_addr);
+	ctxt_info_gen3->mcr_base_addr =
+		cpu_to_le64(trans_pcie->rxq->used_bd_dma);
+	ctxt_info_gen3->mtr_size =
+		cpu_to_le16(TFD_QUEUE_CB_SIZE(TFD_CMD_SLOTS));
+	ctxt_info_gen3->mcr_size =
+		cpu_to_le16(RX_QUEUE_CB_SIZE(MQ_RX_TABLE_SIZE));
+
+	trans_pcie->ctxt_info_gen3 = ctxt_info_gen3;
+	trans_pcie->prph_info = prph_info;
+	trans_pcie->prph_scratch = prph_scratch;
+
+	/* Allocate IML */
+	iml_img = dma_alloc_coherent(trans->dev, trans->iml_len,
+				     &trans_pcie->iml_dma_addr, GFP_KERNEL);
+	if (!iml_img)
+		return -ENOMEM;
+
+	memcpy(iml_img, trans->iml, trans->iml_len);
+
+	iwl_enable_interrupts(trans);
+
+	/* kick FW self load */
+	iwl_write64(trans, CSR_CTXT_INFO_ADDR,
+		    trans_pcie->ctxt_info_dma_addr);
+	iwl_write64(trans, CSR_IML_DATA_ADDR,
+		    trans_pcie->iml_dma_addr);
+	iwl_write32(trans, CSR_IML_SIZE_ADDR, trans->iml_len);
+	iwl_set_bit(trans, CSR_CTXT_INFO_BOOT_CTRL, CSR_AUTO_FUNC_BOOT_ENA);
+	iwl_set_bit(trans, CSR_GP_CNTRL, CSR_AUTO_FUNC_INIT);
+
+	return 0;
+}
+
+void iwl_pcie_ctxt_info_gen3_free(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+
+	if (!trans_pcie->ctxt_info_gen3)
+		return;
+
+	dma_free_coherent(trans->dev, sizeof(*trans_pcie->ctxt_info_gen3),
+			  trans_pcie->ctxt_info_gen3,
+			  trans_pcie->ctxt_info_dma_addr);
+	trans_pcie->ctxt_info_dma_addr = 0;
+	trans_pcie->ctxt_info_gen3 = NULL;
+
+	iwl_pcie_ctxt_info_free_fw_img(trans);
+
+	dma_free_coherent(trans->dev, sizeof(*trans_pcie->prph_scratch),
+			  trans_pcie->prph_scratch,
+			  trans_pcie->prph_scratch_dma_addr);
+	trans_pcie->prph_scratch_dma_addr = 0;
+	trans_pcie->prph_scratch = NULL;
+
+	dma_free_coherent(trans->dev, sizeof(*trans_pcie->prph_info),
+			  trans_pcie->prph_info,
+			  trans_pcie->prph_info_dma_addr);
+	trans_pcie->prph_info_dma_addr = 0;
+	trans_pcie->prph_info = NULL;
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
index 3fc4343581ee..b2cd7ef5fc3a 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
@@ -6,6 +6,7 @@
  * GPL LICENSE SUMMARY
  *
  * Copyright(c) 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -19,6 +20,7 @@
  * BSD LICENSE
  *
  * Copyright(c) 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -55,57 +57,6 @@
 #include "internal.h"
 #include "iwl-prph.h"
 
-static int iwl_pcie_get_num_sections(const struct fw_img *fw,
-				     int start)
-{
-	int i = 0;
-
-	while (start < fw->num_sec &&
-	       fw->sec[start].offset != CPU1_CPU2_SEPARATOR_SECTION &&
-	       fw->sec[start].offset != PAGING_SEPARATOR_SECTION) {
-		start++;
-		i++;
-	}
-
-	return i;
-}
-
-static int iwl_pcie_ctxt_info_alloc_dma(struct iwl_trans *trans,
-					const struct fw_desc *sec,
-					struct iwl_dram_data *dram)
-{
-	dram->block = dma_alloc_coherent(trans->dev, sec->len,
-					 &dram->physical,
-					 GFP_KERNEL);
-	if (!dram->block)
-		return -ENOMEM;
-
-	dram->size = sec->len;
-	memcpy(dram->block, sec->data, sec->len);
-
-	return 0;
-}
-
-static void iwl_pcie_ctxt_info_free_fw_img(struct iwl_trans *trans)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_self_init_dram *dram = &trans_pcie->init_dram;
-	int i;
-
-	if (!dram->fw) {
-		WARN_ON(dram->fw_cnt);
-		return;
-	}
-
-	for (i = 0; i < dram->fw_cnt; i++)
-		dma_free_coherent(trans->dev, dram->fw[i].size,
-				  dram->fw[i].block, dram->fw[i].physical);
-
-	kfree(dram->fw);
-	dram->fw_cnt = 0;
-	dram->fw = NULL;
-}
-
 void iwl_pcie_ctxt_info_free_paging(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -128,13 +79,12 @@ void iwl_pcie_ctxt_info_free_paging(struct iwl_trans *trans)
 	dram->paging = NULL;
 }
 
-static int iwl_pcie_ctxt_info_init_fw_sec(struct iwl_trans *trans,
-					  const struct fw_img *fw,
-					  struct iwl_context_info *ctxt_info)
+int iwl_pcie_init_fw_sec(struct iwl_trans *trans,
+			 const struct fw_img *fw,
+			 struct iwl_context_info_dram *ctxt_dram)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_self_init_dram *dram = &trans_pcie->init_dram;
-	struct iwl_context_info_dram *ctxt_dram = &ctxt_info->dram;
 	int i, ret, lmac_cnt, umac_cnt, paging_cnt;
 
 	if (WARN(dram->paging,
@@ -247,7 +197,7 @@ int iwl_pcie_ctxt_info_init(struct iwl_trans *trans,
 		TFD_QUEUE_CB_SIZE(TFD_CMD_SLOTS);
 
 	/* allocate ucode sections in dram and set addresses */
-	ret = iwl_pcie_ctxt_info_init_fw_sec(trans, fw, ctxt_info);
+	ret = iwl_pcie_init_fw_sec(trans, fw, &ctxt_info->dram);
 	if (ret) {
 		dma_free_coherent(trans->dev, sizeof(*trans_pcie->ctxt_info),
 				  ctxt_info, trans_pcie->ctxt_info_dma_addr);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 8520523b91b4..b150da4c6721 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -72,7 +72,6 @@
 #include <linux/module.h>
 #include <linux/pm_runtime.h>
 #include <linux/pci.h>
-#include <linux/pci-aspm.h>
 #include <linux/acpi.h>
 
 #include "fw/acpi.h"
@@ -828,19 +827,32 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0xA370, 0x42A4, iwl9462_2ac_cfg_soc)},
 
 /* 22000 Series */
-	{IWL_PCI_DEVICE(0x2720, 0x0A10, iwl22000_2ac_cfg_hr_cdb)},
-	{IWL_PCI_DEVICE(0x34F0, 0x0310, iwl22000_2ac_cfg_jf)},
 	{IWL_PCI_DEVICE(0x2720, 0x0000, iwl22000_2ax_cfg_hr)},
-	{IWL_PCI_DEVICE(0x34F0, 0x0070, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0x2720, 0x0040, iwl22000_2ax_cfg_hr)},
 	{IWL_PCI_DEVICE(0x2720, 0x0078, iwl22000_2ax_cfg_hr)},
 	{IWL_PCI_DEVICE(0x2720, 0x0070, iwl22000_2ac_cfg_hr_cdb)},
 	{IWL_PCI_DEVICE(0x2720, 0x0030, iwl22000_2ac_cfg_hr_cdb)},
 	{IWL_PCI_DEVICE(0x2720, 0x1080, iwl22000_2ax_cfg_hr)},
 	{IWL_PCI_DEVICE(0x2720, 0x0090, iwl22000_2ac_cfg_hr_cdb)},
 	{IWL_PCI_DEVICE(0x2720, 0x0310, iwl22000_2ac_cfg_hr_cdb)},
-	{IWL_PCI_DEVICE(0x40C0, 0x0000, iwl22000_2ax_cfg_hr)},
-	{IWL_PCI_DEVICE(0x40C0, 0x0A10, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0x34F0, 0x0040, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0x34F0, 0x0070, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0x34F0, 0x0078, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0x34F0, 0x0310, iwl22000_2ac_cfg_jf)},
+	{IWL_PCI_DEVICE(0x40C0, 0x0000, iwl22560_2ax_cfg_su_cdb)},
+	{IWL_PCI_DEVICE(0x40C0, 0x0010, iwl22560_2ax_cfg_su_cdb)},
+	{IWL_PCI_DEVICE(0x40c0, 0x0090, iwl22560_2ax_cfg_su_cdb)},
+	{IWL_PCI_DEVICE(0x40C0, 0x0310, iwl22560_2ax_cfg_su_cdb)},
+	{IWL_PCI_DEVICE(0x40C0, 0x0A10, iwl22560_2ax_cfg_su_cdb)},
+	{IWL_PCI_DEVICE(0x43F0, 0x0040, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0x43F0, 0x0070, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0x43F0, 0x0078, iwl22000_2ax_cfg_hr)},
 	{IWL_PCI_DEVICE(0xA0F0, 0x0000, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x0040, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x0070, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x0078, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x00B0, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x0A10, iwl22000_2ax_cfg_hr)},
 
 #endif /* CONFIG_IWLMVM */
 
@@ -1003,6 +1015,10 @@ static int iwl_pci_resume(struct device *device)
 	if (!trans->op_mode)
 		return 0;
 
+	/* In WOWLAN, let iwl_trans_pcie_d3_resume do the rest of the work */
+	if (test_bit(STATUS_DEVICE_ENABLED, &trans->status))
+		return 0;
+
 	/* reconfigure the MSI-X mapping to get the correct IRQ for rfkill */
 	iwl_pcie_conf_msix_hw(trans_pcie);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 45ea32796cda..b63d44b7cd7c 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -3,6 +3,7 @@
  * Copyright(c) 2003 - 2015 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * Portions of this file are derived from the ipw3945 project, as well
  * as portions of the ieee80211 subsystem header files.
@@ -17,8 +18,7 @@
  * more details.
  *
  * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110, USA
+ * this program.
  *
  * The full GNU General Public License is included in this distribution in the
  * file called LICENSE.
@@ -45,6 +45,7 @@
 #include "iwl-debug.h"
 #include "iwl-io.h"
 #include "iwl-op-mode.h"
+#include "iwl-drv.h"
 
 /* We need 2 entries for the TX command and header, and another one might
  * be needed for potential data in the SKB's head. The remaining ones can
@@ -59,6 +60,7 @@
 #define RX_POST_REQ_ALLOC 2
 #define RX_CLAIM_REQ_ALLOC 8
 #define RX_PENDING_WATERMARK 16
+#define FIRST_RX_QUEUE 512
 
 struct iwl_host_cmd;
 
@@ -71,6 +73,7 @@ struct iwl_host_cmd;
  * @page: driver's pointer to the rxb page
  * @invalid: rxb is in driver ownership - not owned by HW
  * @vid: index of this rxb in the global table
+ * @size: size used from the buffer
  */
 struct iwl_rx_mem_buffer {
 	dma_addr_t page_dma;
@@ -78,6 +81,7 @@ struct iwl_rx_mem_buffer {
 	u16 vid;
 	bool invalid;
 	struct list_head list;
+	u32 size;
 };
 
 /**
@@ -98,14 +102,121 @@ struct isr_statistics {
 	u32 unhandled;
 };
 
+#define IWL_CD_STTS_OPTIMIZED_POS	0
+#define IWL_CD_STTS_OPTIMIZED_MSK	0x01
+#define IWL_CD_STTS_TRANSFER_STATUS_POS	1
+#define IWL_CD_STTS_TRANSFER_STATUS_MSK	0x0E
+#define IWL_CD_STTS_WIFI_STATUS_POS	4
+#define IWL_CD_STTS_WIFI_STATUS_MSK	0xF0
+
+/**
+ * enum iwl_completion_desc_transfer_status -  transfer status (bits 1-3)
+ * @IWL_CD_STTS_END_TRANSFER: successful transfer complete.
+ *	In sniffer mode, when split is used, set in last CD completion. (RX)
+ * @IWL_CD_STTS_OVERFLOW: In sniffer mode, when using split - used for
+ *	all CD completion. (RX)
+ * @IWL_CD_STTS_ABORTED: CR abort / close flow. (RX)
+ */
+enum iwl_completion_desc_transfer_status {
+	IWL_CD_STTS_UNUSED,
+	IWL_CD_STTS_UNUSED_2,
+	IWL_CD_STTS_END_TRANSFER,
+	IWL_CD_STTS_OVERFLOW,
+	IWL_CD_STTS_ABORTED,
+	IWL_CD_STTS_ERROR,
+};
+
+/**
+ * enum iwl_completion_desc_wifi_status - wifi status (bits 4-7)
+ * @IWL_CD_STTS_VALID: the packet is valid (RX)
+ * @IWL_CD_STTS_FCS_ERR: frame check sequence error (RX)
+ * @IWL_CD_STTS_SEC_KEY_ERR: error handling the security key of rx (RX)
+ * @IWL_CD_STTS_DECRYPTION_ERR: error decrypting the frame (RX)
+ * @IWL_CD_STTS_DUP: duplicate packet (RX)
+ * @IWL_CD_STTS_ICV_MIC_ERR: MIC error (RX)
+ * @IWL_CD_STTS_INTERNAL_SNAP_ERR: problems removing the snap (RX)
+ * @IWL_CD_STTS_SEC_PORT_FAIL: security port fail (RX)
+ * @IWL_CD_STTS_BA_OLD_SN: block ack received old SN (RX)
+ * @IWL_CD_STTS_QOS_NULL: QoS null packet (RX)
+ * @IWL_CD_STTS_MAC_HDR_ERR: MAC header conversion error (RX)
+ * @IWL_CD_STTS_MAX_RETRANS: reached max number of retransmissions (TX)
+ * @IWL_CD_STTS_EX_LIFETIME: exceeded lifetime (TX)
+ * @IWL_CD_STTS_NOT_USED: completed but not used (RX)
+ * @IWL_CD_STTS_REPLAY_ERR: pn check failed, replay error (RX)
+ */
+enum iwl_completion_desc_wifi_status {
+	IWL_CD_STTS_VALID,
+	IWL_CD_STTS_FCS_ERR,
+	IWL_CD_STTS_SEC_KEY_ERR,
+	IWL_CD_STTS_DECRYPTION_ERR,
+	IWL_CD_STTS_DUP,
+	IWL_CD_STTS_ICV_MIC_ERR,
+	IWL_CD_STTS_INTERNAL_SNAP_ERR,
+	IWL_CD_STTS_SEC_PORT_FAIL,
+	IWL_CD_STTS_BA_OLD_SN,
+	IWL_CD_STTS_QOS_NULL,
+	IWL_CD_STTS_MAC_HDR_ERR,
+	IWL_CD_STTS_MAX_RETRANS,
+	IWL_CD_STTS_EX_LIFETIME,
+	IWL_CD_STTS_NOT_USED,
+	IWL_CD_STTS_REPLAY_ERR,
+};
+
+#define IWL_RX_TD_TYPE_MSK	0xff000000
+#define IWL_RX_TD_SIZE_MSK	0x00ffffff
+#define IWL_RX_TD_SIZE_2K	BIT(11)
+#define IWL_RX_TD_TYPE		0
+
+/**
+ * struct iwl_rx_transfer_desc - transfer descriptor
+ * @type_n_size: buffer type (bit 0: external buff valid,
+ *	bit 1: optional footer valid, bit 2-7: reserved)
+ *	and buffer size
+ * @addr: ptr to free buffer start address
+ * @rbid: unique tag of the buffer
+ * @reserved: reserved
+ */
+struct iwl_rx_transfer_desc {
+	__le32 type_n_size;
+	__le64 addr;
+	__le16 rbid;
+	__le16 reserved;
+} __packed;
+
+#define IWL_RX_CD_SIZE		0xffffff00
+
+/**
+ * struct iwl_rx_completion_desc - completion descriptor
+ * @type: buffer type (bit 0: external buff valid,
+ *	bit 1: optional footer valid, bit 2-7: reserved)
+ * @status: status of the completion
+ * @reserved1: reserved
+ * @rbid: unique tag of the received buffer
+ * @size: buffer size, masked by IWL_RX_CD_SIZE
+ * @reserved2: reserved
+ */
+struct iwl_rx_completion_desc {
+	u8 type;
+	u8 status;
+	__le16 reserved1;
+	__le16 rbid;
+	__le32 size;
+	u8 reserved2[22];
+} __packed;
+
 /**
  * struct iwl_rxq - Rx queue
  * @id: queue index
  * @bd: driver's pointer to buffer of receive buffer descriptors (rbd).
  *	Address size is 32 bit in pre-9000 devices and 64 bit in 9000 devices.
+ *	In 22560 devices it is a pointer to a list of iwl_rx_transfer_desc's
  * @bd_dma: bus address of buffer of receive buffer descriptors (rbd)
  * @ubd: driver's pointer to buffer of used receive buffer descriptors (rbd)
  * @ubd_dma: physical address of buffer of used receive buffer descriptors (rbd)
+ * @tr_tail: driver's pointer to the transmission ring tail buffer
+ * @tr_tail_dma: physical address of the buffer for the transmission ring tail
+ * @cr_tail: driver's pointer to the completion ring tail buffer
+ * @cr_tail_dma: physical address of the buffer for the completion ring tail
  * @read: Shared index to newest available Rx buffer
  * @write: Shared index to oldest written Rx packet
  * @free_count: Number of pre-allocated buffers in rx_free
@@ -125,8 +236,16 @@ struct iwl_rxq {
 	int id;
 	void *bd;
 	dma_addr_t bd_dma;
-	__le32 *used_bd;
+	union {
+		void *used_bd;
+		__le32 *bd_32;
+		struct iwl_rx_completion_desc *cd;
+	};
 	dma_addr_t used_bd_dma;
+	__le16 *tr_tail;
+	dma_addr_t tr_tail_dma;
+	__le16 *cr_tail;
+	dma_addr_t cr_tail_dma;
 	u32 read;
 	u32 write;
 	u32 free_count;
@@ -136,7 +255,7 @@ struct iwl_rxq {
 	struct list_head rx_free;
 	struct list_head rx_used;
 	bool need_update;
-	struct iwl_rb_status *rb_stts;
+	void *rb_stts;
 	dma_addr_t rb_stts_dma;
 	spinlock_t lock;
 	struct napi_struct napi;
@@ -175,18 +294,36 @@ struct iwl_dma_ptr {
  * iwl_queue_inc_wrap - increment queue index, wrap back to beginning
  * @index -- current index
  */
-static inline int iwl_queue_inc_wrap(int index)
+static inline int iwl_queue_inc_wrap(struct iwl_trans *trans, int index)
 {
-	return ++index & (TFD_QUEUE_SIZE_MAX - 1);
+	return ++index & (trans->cfg->base_params->max_tfd_queue_size - 1);
+}
+
+/**
+ * iwl_get_closed_rb_stts - get closed rb stts from different structs
+ * @rxq - the rxq to get the rb stts from
+ */
+static inline __le16 iwl_get_closed_rb_stts(struct iwl_trans *trans,
+					    struct iwl_rxq *rxq)
+{
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
+		__le16 *rb_stts = rxq->rb_stts;
+
+		return READ_ONCE(*rb_stts);
+	} else {
+		struct iwl_rb_status *rb_stts = rxq->rb_stts;
+
+		return READ_ONCE(rb_stts->closed_rb_num);
+	}
 }
 
 /**
  * iwl_queue_dec_wrap - decrement queue index, wrap back to end
  * @index -- current index
  */
-static inline int iwl_queue_dec_wrap(int index)
+static inline int iwl_queue_dec_wrap(struct iwl_trans *trans, int index)
 {
-	return --index & (TFD_QUEUE_SIZE_MAX - 1);
+	return --index & (trans->cfg->base_params->max_tfd_queue_size - 1);
 }
 
 struct iwl_cmd_meta {
@@ -315,6 +452,18 @@ enum iwl_shared_irq_flags {
 };
 
 /**
+ * enum iwl_image_response_code - image response values
+ * @IWL_IMAGE_RESP_DEF: the default value of the register
+ * @IWL_IMAGE_RESP_SUCCESS: iml was read successfully
+ * @IWL_IMAGE_RESP_FAIL: iml reading failed
+ */
+enum iwl_image_response_code {
+	IWL_IMAGE_RESP_DEF		= 0,
+	IWL_IMAGE_RESP_SUCCESS		= 1,
+	IWL_IMAGE_RESP_FAIL		= 2,
+};
+
+/**
  * struct iwl_dram_data
  * @physical: page phy pointer
  * @block: pointer to the allocated block/page
@@ -347,6 +496,12 @@ struct iwl_self_init_dram {
  * @global_table: table mapping received VID from hw to rxb
  * @rba: allocator for RX replenishing
  * @ctxt_info: context information for FW self init
+ * @ctxt_info_gen3: context information for gen3 devices
+ * @prph_info: prph info for self init
+ * @prph_scratch: prph scratch for self init
+ * @ctxt_info_dma_addr: dma addr of context information
+ * @prph_info_dma_addr: dma addr of prph info
+ * @prph_scratch_dma_addr: dma addr of prph scratch
  * @ctxt_info_dma_addr: dma addr of context information
  * @init_dram: DRAM data of firmware image (including paging).
  *	Context information addresses will be taken from here.
@@ -391,8 +546,16 @@ struct iwl_trans_pcie {
 	struct iwl_rx_mem_buffer rx_pool[RX_POOL_SIZE];
 	struct iwl_rx_mem_buffer *global_table[RX_POOL_SIZE];
 	struct iwl_rb_allocator rba;
-	struct iwl_context_info *ctxt_info;
+	union {
+		struct iwl_context_info *ctxt_info;
+		struct iwl_context_info_gen3 *ctxt_info_gen3;
+	};
+	struct iwl_prph_info *prph_info;
+	struct iwl_prph_scratch *prph_scratch;
 	dma_addr_t ctxt_info_dma_addr;
+	dma_addr_t prph_info_dma_addr;
+	dma_addr_t prph_scratch_dma_addr;
+	dma_addr_t iml_dma_addr;
 	struct iwl_self_init_dram init_dram;
 	struct iwl_trans *trans;
 
@@ -477,6 +640,20 @@ IWL_TRANS_GET_PCIE_TRANS(struct iwl_trans *trans)
 	return (void *)trans->trans_specific;
 }
 
+static inline void iwl_pcie_clear_irq(struct iwl_trans *trans,
+				      struct msix_entry *entry)
+{
+	/*
+	 * Before sending the interrupt the HW disables it to prevent
+	 * a nested interrupt. This is done by writing 1 to the corresponding
+	 * bit in the mask register. After handling the interrupt, it should be
+	 * re-enabled by clearing this bit. This register is defined as
+	 * write 1 clear (W1C) register, meaning that it's being clear
+	 * by writing 1 to the bit.
+	 */
+	iwl_write32(trans, CSR_MSIX_AUTOMASK_ST_AD, BIT(entry->entry));
+}
+
 static inline struct iwl_trans *
 iwl_trans_pcie_get_trans(struct iwl_trans_pcie *trans_pcie)
 {
@@ -504,6 +681,11 @@ irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id);
 irqreturn_t iwl_pcie_irq_rx_msix_handler(int irq, void *dev_id);
 int iwl_pcie_rx_stop(struct iwl_trans *trans);
 void iwl_pcie_rx_free(struct iwl_trans *trans);
+void iwl_pcie_free_rbs_pool(struct iwl_trans *trans);
+void iwl_pcie_rx_init_rxb_lists(struct iwl_rxq *rxq);
+int iwl_pcie_dummy_napi_poll(struct napi_struct *napi, int budget);
+void iwl_pcie_rxq_alloc_rbs(struct iwl_trans *trans, gfp_t priority,
+			    struct iwl_rxq *rxq);
 
 /*****************************************************
 * ICT - interrupt handling
@@ -588,6 +770,60 @@ static inline void _iwl_disable_interrupts(struct iwl_trans *trans)
 	IWL_DEBUG_ISR(trans, "Disabled interrupts\n");
 }
 
+#define IWL_NUM_OF_COMPLETION_RINGS	31
+#define IWL_NUM_OF_TRANSFER_RINGS	527
+
+static inline int iwl_pcie_get_num_sections(const struct fw_img *fw,
+					    int start)
+{
+	int i = 0;
+
+	while (start < fw->num_sec &&
+	       fw->sec[start].offset != CPU1_CPU2_SEPARATOR_SECTION &&
+	       fw->sec[start].offset != PAGING_SEPARATOR_SECTION) {
+		start++;
+		i++;
+	}
+
+	return i;
+}
+
+static inline int iwl_pcie_ctxt_info_alloc_dma(struct iwl_trans *trans,
+					       const struct fw_desc *sec,
+					       struct iwl_dram_data *dram)
+{
+	dram->block = dma_alloc_coherent(trans->dev, sec->len,
+					 &dram->physical,
+					 GFP_KERNEL);
+	if (!dram->block)
+		return -ENOMEM;
+
+	dram->size = sec->len;
+	memcpy(dram->block, sec->data, sec->len);
+
+	return 0;
+}
+
+static inline void iwl_pcie_ctxt_info_free_fw_img(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_self_init_dram *dram = &trans_pcie->init_dram;
+	int i;
+
+	if (!dram->fw) {
+		WARN_ON(dram->fw_cnt);
+		return;
+	}
+
+	for (i = 0; i < dram->fw_cnt; i++)
+		dma_free_coherent(trans->dev, dram->fw[i].size,
+				  dram->fw[i].block, dram->fw[i].physical);
+
+	kfree(dram->fw);
+	dram->fw_cnt = 0;
+	dram->fw = NULL;
+}
+
 static inline void iwl_disable_interrupts(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -660,7 +896,7 @@ static inline void iwl_enable_fw_load_int(struct iwl_trans *trans)
 	}
 }
 
-static inline u8 iwl_pcie_get_cmd_index(struct iwl_txq *q, u32 index)
+static inline u16 iwl_pcie_get_cmd_index(const struct iwl_txq *q, u32 index)
 {
 	return index & (q->n_window - 1);
 }
@@ -676,6 +912,29 @@ static inline void *iwl_pcie_get_tfd(struct iwl_trans *trans,
 	return txq->tfds + trans_pcie->tfd_size * idx;
 }
 
+static inline const char *queue_name(struct device *dev,
+				     struct iwl_trans_pcie *trans_p, int i)
+{
+	if (trans_p->shared_vec_mask) {
+		int vec = trans_p->shared_vec_mask &
+			  IWL_SHARED_IRQ_FIRST_RSS ? 1 : 0;
+
+		if (i == 0)
+			return DRV_NAME ": shared IRQ";
+
+		return devm_kasprintf(dev, GFP_KERNEL,
+				      DRV_NAME ": queue %d", i + vec);
+	}
+	if (i == 0)
+		return DRV_NAME ": default queue";
+
+	if (i == trans_p->alloc_vecs - 1)
+		return DRV_NAME ": exception";
+
+	return devm_kasprintf(dev, GFP_KERNEL,
+			      DRV_NAME  ": queue %d", i);
+}
+
 static inline void iwl_enable_rfkill_int(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -730,9 +989,13 @@ static inline void iwl_stop_queue(struct iwl_trans *trans,
 
 static inline bool iwl_queue_used(const struct iwl_txq *q, int i)
 {
-	return q->write_ptr >= q->read_ptr ?
-		(i >= q->read_ptr && i < q->write_ptr) :
-		!(i < q->read_ptr && i >= q->write_ptr);
+	int index = iwl_pcie_get_cmd_index(q, i);
+	int r = iwl_pcie_get_cmd_index(q, q->read_ptr);
+	int w = iwl_pcie_get_cmd_index(q, q->write_ptr);
+
+	return w >= r ?
+		(index >= r && index < w) :
+		!(index < r && index >= w);
 }
 
 static inline bool iwl_is_rfkill_set(struct iwl_trans *trans)
@@ -801,7 +1064,7 @@ bool iwl_pcie_check_hw_rf_kill(struct iwl_trans *trans);
 void iwl_trans_pcie_handle_stop_rfkill(struct iwl_trans *trans,
 				       bool was_in_rfkill);
 void iwl_pcie_txq_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq);
-int iwl_queue_space(const struct iwl_txq *q);
+int iwl_queue_space(struct iwl_trans *trans, const struct iwl_txq *q);
 void iwl_pcie_apm_stop_master(struct iwl_trans *trans);
 void iwl_pcie_conf_msix_hw(struct iwl_trans_pcie *trans_pcie);
 int iwl_pcie_txq_init(struct iwl_trans *trans, struct iwl_txq *txq,
@@ -818,6 +1081,9 @@ void iwl_pcie_free_tso_page(struct iwl_trans_pcie *trans_pcie,
 struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len);
 #endif
 
+/* common functions that are used by gen3 transport */
+void iwl_pcie_alloc_fw_monitor(struct iwl_trans *trans, u8 max_power);
+
 /* transport gen 2 exported functions */
 int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans,
 				 const struct fw_img *fw, bool run_in_rfkill);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index d15f5ba2dc77..d017aa2a0a8b 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -18,8 +18,7 @@
  * more details.
  *
  * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110, USA
+ * this program.
  *
  * The full GNU General Public License is included in this distribution in the
  * file called LICENSE.
@@ -37,6 +36,7 @@
 #include "iwl-io.h"
 #include "internal.h"
 #include "iwl-op-mode.h"
+#include "iwl-context-info-gen3.h"
 
 /******************************************************************************
  *
@@ -167,7 +167,12 @@ static inline __le32 iwl_pcie_dma_addr2rbd_ptr(dma_addr_t dma_addr)
  */
 int iwl_pcie_rx_stop(struct iwl_trans *trans)
 {
-	if (trans->cfg->mq_rx_supported) {
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
+		/* TODO: remove this for 22560 once fw does it */
+		iwl_write_prph(trans, RFH_RXF_DMA_CFG_GEN3, 0);
+		return iwl_poll_prph_bit(trans, RFH_GEN_STATUS_GEN3,
+					 RXF_DMA_IDLE, RXF_DMA_IDLE, 1000);
+	} else if (trans->cfg->mq_rx_supported) {
 		iwl_write_prph(trans, RFH_RXF_DMA_CFG, 0);
 		return iwl_poll_prph_bit(trans, RFH_GEN_STATUS,
 					   RXF_DMA_IDLE, RXF_DMA_IDLE, 1000);
@@ -209,7 +214,11 @@ static void iwl_pcie_rxq_inc_wr_ptr(struct iwl_trans *trans,
 	}
 
 	rxq->write_actual = round_down(rxq->write, 8);
-	if (trans->cfg->mq_rx_supported)
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+		iwl_write32(trans, HBUS_TARG_WRPTR,
+			    (rxq->write_actual |
+			     ((FIRST_RX_QUEUE + rxq->id) << 16)));
+	else if (trans->cfg->mq_rx_supported)
 		iwl_write32(trans, RFH_Q_FRBDCB_WIDX_TRG(rxq->id),
 			    rxq->write_actual);
 	else
@@ -233,6 +242,25 @@ static void iwl_pcie_rxq_check_wrptr(struct iwl_trans *trans)
 	}
 }
 
+static void iwl_pcie_restock_bd(struct iwl_trans *trans,
+				struct iwl_rxq *rxq,
+				struct iwl_rx_mem_buffer *rxb)
+{
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
+		struct iwl_rx_transfer_desc *bd = rxq->bd;
+
+		bd[rxq->write].type_n_size =
+			cpu_to_le32((IWL_RX_TD_TYPE & IWL_RX_TD_TYPE_MSK) |
+			((IWL_RX_TD_SIZE_2K >> 8) & IWL_RX_TD_SIZE_MSK));
+		bd[rxq->write].addr = cpu_to_le64(rxb->page_dma);
+		bd[rxq->write].rbid = cpu_to_le16(rxb->vid);
+	} else {
+		__le64 *bd = rxq->bd;
+
+		bd[rxq->write] = cpu_to_le64(rxb->page_dma | rxb->vid);
+	}
+}
+
 /*
  * iwl_pcie_rxmq_restock - restock implementation for multi-queue rx
  */
@@ -254,8 +282,6 @@ static void iwl_pcie_rxmq_restock(struct iwl_trans *trans,
 
 	spin_lock(&rxq->lock);
 	while (rxq->free_count) {
-		__le64 *bd = (__le64 *)rxq->bd;
-
 		/* Get next free Rx buffer, remove from free list */
 		rxb = list_first_entry(&rxq->rx_free, struct iwl_rx_mem_buffer,
 				       list);
@@ -264,7 +290,7 @@ static void iwl_pcie_rxmq_restock(struct iwl_trans *trans,
 		/* 12 first bits are expected to be empty */
 		WARN_ON(rxb->page_dma & DMA_BIT_MASK(12));
 		/* Point to Rx buffer via next RBD in circular buffer */
-		bd[rxq->write] = cpu_to_le64(rxb->page_dma | rxb->vid);
+		iwl_pcie_restock_bd(trans, rxq, rxb);
 		rxq->write = (rxq->write + 1) & MQ_RX_TABLE_MASK;
 		rxq->free_count--;
 	}
@@ -391,8 +417,8 @@ static struct page *iwl_pcie_rx_alloc_page(struct iwl_trans *trans,
  * iwl_pcie_rxq_restock. The latter function will update the HW to use the newly
  * allocated buffers.
  */
-static void iwl_pcie_rxq_alloc_rbs(struct iwl_trans *trans, gfp_t priority,
-				   struct iwl_rxq *rxq)
+void iwl_pcie_rxq_alloc_rbs(struct iwl_trans *trans, gfp_t priority,
+			    struct iwl_rxq *rxq)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_rx_mem_buffer *rxb;
@@ -448,7 +474,7 @@ static void iwl_pcie_rxq_alloc_rbs(struct iwl_trans *trans, gfp_t priority,
 	}
 }
 
-static void iwl_pcie_free_rbs_pool(struct iwl_trans *trans)
+void iwl_pcie_free_rbs_pool(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	int i;
@@ -608,89 +634,174 @@ void iwl_pcie_rx_allocator_work(struct work_struct *data)
 	iwl_pcie_rx_allocator(trans_pcie->trans);
 }
 
-static int iwl_pcie_rx_alloc(struct iwl_trans *trans)
+static int iwl_pcie_free_bd_size(struct iwl_trans *trans, bool use_rx_td)
 {
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_rb_allocator *rba = &trans_pcie->rba;
-	struct device *dev = trans->dev;
-	int i;
-	int free_size = trans->cfg->mq_rx_supported ? sizeof(__le64) :
-						      sizeof(__le32);
+	struct iwl_rx_transfer_desc *rx_td;
 
-	if (WARN_ON(trans_pcie->rxq))
-		return -EINVAL;
+	if (use_rx_td)
+		return sizeof(*rx_td);
+	else
+		return trans->cfg->mq_rx_supported ? sizeof(__le64) :
+			sizeof(__le32);
+}
 
-	trans_pcie->rxq = kcalloc(trans->num_rx_queues, sizeof(struct iwl_rxq),
-				  GFP_KERNEL);
-	if (!trans_pcie->rxq)
-		return -EINVAL;
+static void iwl_pcie_free_rxq_dma(struct iwl_trans *trans,
+				  struct iwl_rxq *rxq)
+{
+	struct device *dev = trans->dev;
+	bool use_rx_td = (trans->cfg->device_family >=
+			  IWL_DEVICE_FAMILY_22560);
+	int free_size = iwl_pcie_free_bd_size(trans, use_rx_td);
+
+	if (rxq->bd)
+		dma_free_coherent(trans->dev,
+				  free_size * rxq->queue_size,
+				  rxq->bd, rxq->bd_dma);
+	rxq->bd_dma = 0;
+	rxq->bd = NULL;
+
+	if (rxq->rb_stts)
+		dma_free_coherent(trans->dev,
+				  use_rx_td ? sizeof(__le16) :
+				  sizeof(struct iwl_rb_status),
+				  rxq->rb_stts, rxq->rb_stts_dma);
+	rxq->rb_stts_dma = 0;
+	rxq->rb_stts = NULL;
+
+	if (rxq->used_bd)
+		dma_free_coherent(trans->dev,
+				  (use_rx_td ? sizeof(*rxq->cd) :
+				   sizeof(__le32)) * rxq->queue_size,
+				  rxq->used_bd, rxq->used_bd_dma);
+	rxq->used_bd_dma = 0;
+	rxq->used_bd = NULL;
+
+	if (trans->cfg->device_family < IWL_DEVICE_FAMILY_22560)
+		return;
 
-	spin_lock_init(&rba->lock);
+	if (rxq->tr_tail)
+		dma_free_coherent(dev, sizeof(__le16),
+				  rxq->tr_tail, rxq->tr_tail_dma);
+	rxq->tr_tail_dma = 0;
+	rxq->tr_tail = NULL;
+
+	if (rxq->cr_tail)
+		dma_free_coherent(dev, sizeof(__le16),
+				  rxq->cr_tail, rxq->cr_tail_dma);
+	rxq->cr_tail_dma = 0;
+	rxq->cr_tail = NULL;
+}
 
-	for (i = 0; i < trans->num_rx_queues; i++) {
-		struct iwl_rxq *rxq = &trans_pcie->rxq[i];
+static int iwl_pcie_alloc_rxq_dma(struct iwl_trans *trans,
+				  struct iwl_rxq *rxq)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct device *dev = trans->dev;
+	int i;
+	int free_size;
+	bool use_rx_td = (trans->cfg->device_family >=
+			  IWL_DEVICE_FAMILY_22560);
 
-		spin_lock_init(&rxq->lock);
-		if (trans->cfg->mq_rx_supported)
-			rxq->queue_size = MQ_RX_TABLE_SIZE;
-		else
-			rxq->queue_size = RX_QUEUE_SIZE;
+	spin_lock_init(&rxq->lock);
+	if (trans->cfg->mq_rx_supported)
+		rxq->queue_size = MQ_RX_TABLE_SIZE;
+	else
+		rxq->queue_size = RX_QUEUE_SIZE;
 
-		/*
-		 * Allocate the circular buffer of Read Buffer Descriptors
-		 * (RBDs)
-		 */
-		rxq->bd = dma_zalloc_coherent(dev,
-					     free_size * rxq->queue_size,
-					     &rxq->bd_dma, GFP_KERNEL);
-		if (!rxq->bd)
-			goto err;
+	free_size = iwl_pcie_free_bd_size(trans, use_rx_td);
 
-		if (trans->cfg->mq_rx_supported) {
-			rxq->used_bd = dma_zalloc_coherent(dev,
-							   sizeof(__le32) *
-							   rxq->queue_size,
-							   &rxq->used_bd_dma,
-							   GFP_KERNEL);
-			if (!rxq->used_bd)
-				goto err;
-		}
+	/*
+	 * Allocate the circular buffer of Read Buffer Descriptors
+	 * (RBDs)
+	 */
+	rxq->bd = dma_zalloc_coherent(dev,
+				      free_size * rxq->queue_size,
+				      &rxq->bd_dma, GFP_KERNEL);
+	if (!rxq->bd)
+		goto err;
 
-		/*Allocate the driver's pointer to receive buffer status */
-		rxq->rb_stts = dma_zalloc_coherent(dev, sizeof(*rxq->rb_stts),
-						   &rxq->rb_stts_dma,
+	if (trans->cfg->mq_rx_supported) {
+		rxq->used_bd = dma_zalloc_coherent(dev,
+						   (use_rx_td ?
+						   sizeof(*rxq->cd) :
+						   sizeof(__le32)) *
+						   rxq->queue_size,
+						   &rxq->used_bd_dma,
 						   GFP_KERNEL);
-		if (!rxq->rb_stts)
+		if (!rxq->used_bd)
 			goto err;
 	}
+
+	/* Allocate the driver's pointer to receive buffer status */
+	rxq->rb_stts = dma_zalloc_coherent(dev, use_rx_td ?
+					   sizeof(__le16) :
+					   sizeof(struct iwl_rb_status),
+					   &rxq->rb_stts_dma,
+					   GFP_KERNEL);
+	if (!rxq->rb_stts)
+		goto err;
+
+	if (!use_rx_td)
+		return 0;
+
+	/* Allocate the driver's pointer to TR tail */
+	rxq->tr_tail = dma_zalloc_coherent(dev, sizeof(__le16),
+					   &rxq->tr_tail_dma,
+					   GFP_KERNEL);
+	if (!rxq->tr_tail)
+		goto err;
+
+	/* Allocate the driver's pointer to CR tail */
+	rxq->cr_tail = dma_zalloc_coherent(dev, sizeof(__le16),
+					   &rxq->cr_tail_dma,
+					   GFP_KERNEL);
+	if (!rxq->cr_tail)
+		goto err;
+	/*
+	 * W/A 22560 device step Z0 must be non zero bug
+	 * TODO: remove this when stop supporting Z0
+	 */
+	*rxq->cr_tail = cpu_to_le16(500);
+
 	return 0;
 
 err:
 	for (i = 0; i < trans->num_rx_queues; i++) {
 		struct iwl_rxq *rxq = &trans_pcie->rxq[i];
 
-		if (rxq->bd)
-			dma_free_coherent(dev, free_size * rxq->queue_size,
-					  rxq->bd, rxq->bd_dma);
-		rxq->bd_dma = 0;
-		rxq->bd = NULL;
-
-		if (rxq->rb_stts)
-			dma_free_coherent(trans->dev,
-					  sizeof(struct iwl_rb_status),
-					  rxq->rb_stts, rxq->rb_stts_dma);
-
-		if (rxq->used_bd)
-			dma_free_coherent(dev, sizeof(__le32) * rxq->queue_size,
-					  rxq->used_bd, rxq->used_bd_dma);
-		rxq->used_bd_dma = 0;
-		rxq->used_bd = NULL;
+		iwl_pcie_free_rxq_dma(trans, rxq);
 	}
 	kfree(trans_pcie->rxq);
 
 	return -ENOMEM;
 }
 
+static int iwl_pcie_rx_alloc(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_rb_allocator *rba = &trans_pcie->rba;
+	int i, ret;
+
+	if (WARN_ON(trans_pcie->rxq))
+		return -EINVAL;
+
+	trans_pcie->rxq = kcalloc(trans->num_rx_queues, sizeof(struct iwl_rxq),
+				  GFP_KERNEL);
+	if (!trans_pcie->rxq)
+		return -EINVAL;
+
+	spin_lock_init(&rba->lock);
+
+	for (i = 0; i < trans->num_rx_queues; i++) {
+		struct iwl_rxq *rxq = &trans_pcie->rxq[i];
+
+		ret = iwl_pcie_alloc_rxq_dma(trans, rxq);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
 static void iwl_pcie_rx_hw_init(struct iwl_trans *trans, struct iwl_rxq *rxq)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -792,6 +903,9 @@ static void iwl_pcie_rx_mq_hw_init(struct iwl_trans *trans)
 	int i;
 
 	switch (trans_pcie->rx_buf_size) {
+	case IWL_AMSDU_2K:
+		rb_size = RFH_RXF_DMA_RB_SIZE_2K;
+		break;
 	case IWL_AMSDU_4K:
 		rb_size = RFH_RXF_DMA_RB_SIZE_4K;
 		break;
@@ -872,7 +986,7 @@ static void iwl_pcie_rx_mq_hw_init(struct iwl_trans *trans)
 	iwl_pcie_enable_rx_wake(trans, true);
 }
 
-static void iwl_pcie_rx_init_rxb_lists(struct iwl_rxq *rxq)
+void iwl_pcie_rx_init_rxb_lists(struct iwl_rxq *rxq)
 {
 	lockdep_assert_held(&rxq->lock);
 
@@ -882,7 +996,7 @@ static void iwl_pcie_rx_init_rxb_lists(struct iwl_rxq *rxq)
 	rxq->used_count = 0;
 }
 
-static int iwl_pcie_dummy_napi_poll(struct napi_struct *napi, int budget)
+int iwl_pcie_dummy_napi_poll(struct napi_struct *napi, int budget)
 {
 	WARN_ON(1);
 	return 0;
@@ -931,7 +1045,9 @@ static int _iwl_pcie_rx_init(struct iwl_trans *trans)
 		rxq->read = 0;
 		rxq->write = 0;
 		rxq->write_actual = 0;
-		memset(rxq->rb_stts, 0, sizeof(*rxq->rb_stts));
+		memset(rxq->rb_stts, 0,
+		       (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) ?
+		       sizeof(__le16) : sizeof(struct iwl_rb_status));
 
 		iwl_pcie_rx_init_rxb_lists(rxq);
 
@@ -1002,8 +1118,6 @@ void iwl_pcie_rx_free(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_rb_allocator *rba = &trans_pcie->rba;
-	int free_size = trans->cfg->mq_rx_supported ? sizeof(__le64) :
-					      sizeof(__le32);
 	int i;
 
 	/*
@@ -1022,27 +1136,7 @@ void iwl_pcie_rx_free(struct iwl_trans *trans)
 	for (i = 0; i < trans->num_rx_queues; i++) {
 		struct iwl_rxq *rxq = &trans_pcie->rxq[i];
 
-		if (rxq->bd)
-			dma_free_coherent(trans->dev,
-					  free_size * rxq->queue_size,
-					  rxq->bd, rxq->bd_dma);
-		rxq->bd_dma = 0;
-		rxq->bd = NULL;
-
-		if (rxq->rb_stts)
-			dma_free_coherent(trans->dev,
-					  sizeof(struct iwl_rb_status),
-					  rxq->rb_stts, rxq->rb_stts_dma);
-		else
-			IWL_DEBUG_INFO(trans,
-				       "Free rxq->rb_stts which is NULL\n");
-
-		if (rxq->used_bd)
-			dma_free_coherent(trans->dev,
-					  sizeof(__le32) * rxq->queue_size,
-					  rxq->used_bd, rxq->used_bd_dma);
-		rxq->used_bd_dma = 0;
-		rxq->used_bd = NULL;
+		iwl_pcie_free_rxq_dma(trans, rxq);
 
 		if (rxq->napi.poll)
 			netif_napi_del(&rxq->napi);
@@ -1202,6 +1296,8 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
 		}
 
 		page_stolen |= rxcb._page_stolen;
+		if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+			break;
 		offset += ALIGN(len, FH_RSCSR_FRAME_ALIGN);
 	}
 
@@ -1236,6 +1332,45 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
 		iwl_pcie_rx_reuse_rbd(trans, rxb, rxq, emergency);
 }
 
+static struct iwl_rx_mem_buffer *iwl_pcie_get_rxb(struct iwl_trans *trans,
+						  struct iwl_rxq *rxq, int i)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_rx_mem_buffer *rxb;
+	u16 vid;
+
+	if (!trans->cfg->mq_rx_supported) {
+		rxb = rxq->queue[i];
+		rxq->queue[i] = NULL;
+		return rxb;
+	}
+
+	/* used_bd is a 32/16 bit but only 12 are used to retrieve the vid */
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+		vid = le16_to_cpu(rxq->cd[i].rbid) & 0x0FFF;
+	else
+		vid = le32_to_cpu(rxq->bd_32[i]) & 0x0FFF;
+
+	if (!vid || vid > ARRAY_SIZE(trans_pcie->global_table))
+		goto out_err;
+
+	rxb = trans_pcie->global_table[vid - 1];
+	if (rxb->invalid)
+		goto out_err;
+
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+		rxb->size = le32_to_cpu(rxq->cd[i].size) & IWL_RX_CD_SIZE;
+
+	rxb->invalid = true;
+
+	return rxb;
+
+out_err:
+	WARN(1, "Invalid rxb from HW %u\n", (u32)vid);
+	iwl_force_nmi(trans);
+	return NULL;
+}
+
 /*
  * iwl_pcie_rx_handle - Main entry function for receiving responses from fw
  */
@@ -1250,7 +1385,7 @@ restart:
 	spin_lock(&rxq->lock);
 	/* uCode's read index (stored in shared DRAM) indicates the last Rx
 	 * buffer that the driver may process (last buffer filled by ucode). */
-	r = le16_to_cpu(READ_ONCE(rxq->rb_stts->closed_rb_num)) & 0x0FFF;
+	r = le16_to_cpu(iwl_get_closed_rb_stts(trans, rxq)) & 0x0FFF;
 	i = rxq->read;
 
 	/* W/A 9000 device step A0 wrap-around bug */
@@ -1266,30 +1401,9 @@ restart:
 		if (unlikely(rxq->used_count == rxq->queue_size / 2))
 			emergency = true;
 
-		if (trans->cfg->mq_rx_supported) {
-			/*
-			 * used_bd is a 32 bit but only 12 are used to retrieve
-			 * the vid
-			 */
-			u16 vid = le32_to_cpu(rxq->used_bd[i]) & 0x0FFF;
-
-			if (WARN(!vid ||
-				 vid > ARRAY_SIZE(trans_pcie->global_table),
-				 "Invalid rxb index from HW %u\n", (u32)vid)) {
-				iwl_force_nmi(trans);
-				goto out;
-			}
-			rxb = trans_pcie->global_table[vid - 1];
-			if (WARN(rxb->invalid,
-				 "Invalid rxb from HW %u\n", (u32)vid)) {
-				iwl_force_nmi(trans);
-				goto out;
-			}
-			rxb->invalid = true;
-		} else {
-			rxb = rxq->queue[i];
-			rxq->queue[i] = NULL;
-		}
+		rxb = iwl_pcie_get_rxb(trans, rxq, i);
+		if (!rxb)
+			goto out;
 
 		IWL_DEBUG_RX(trans, "Q %d: HW = %d, SW = %d\n", rxq->id, r, i);
 		iwl_pcie_rx_handle_rb(trans, rxq, rxb, emergency);
@@ -1331,6 +1445,9 @@ restart:
 out:
 	/* Backtrack one entry */
 	rxq->read = i;
+	/* update cr tail with the rxq read pointer */
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+		*rxq->cr_tail = cpu_to_le16(r);
 	spin_unlock(&rxq->lock);
 
 	/*
@@ -1362,20 +1479,6 @@ static struct iwl_trans_pcie *iwl_pcie_get_trans_pcie(struct msix_entry *entry)
 	return container_of(entries, struct iwl_trans_pcie, msix_entries[0]);
 }
 
-static inline void iwl_pcie_clear_irq(struct iwl_trans *trans,
-				      struct msix_entry *entry)
-{
-	/*
-	 * Before sending the interrupt the HW disables it to prevent
-	 * a nested interrupt. This is done by writing 1 to the corresponding
-	 * bit in the mask register. After handling the interrupt, it should be
-	 * re-enabled by clearing this bit. This register is defined as
-	 * write 1 clear (W1C) register, meaning that it's being clear
-	 * by writing 1 to the bit.
-	 */
-	iwl_write32(trans, CSR_MSIX_AUTOMASK_ST_AD, BIT(entry->entry));
-}
-
 /*
  * iwl_pcie_rx_msix_handle - Main entry function for receiving responses from fw
  * This interrupt handler should be used with RSS queue only.
@@ -1970,7 +2073,8 @@ irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id)
 
 	/* Error detected by uCode */
 	if ((inta_fh & MSIX_FH_INT_CAUSES_FH_ERR) ||
-	    (inta_hw & MSIX_HW_INT_CAUSES_REG_SW_ERR)) {
+	    (inta_hw & MSIX_HW_INT_CAUSES_REG_SW_ERR) ||
+	    (inta_hw & MSIX_HW_INT_CAUSES_REG_SW_ERR_V2)) {
 		IWL_ERR(trans,
 			"Microcode SW error detected. Restarting 0x%X.\n",
 			inta_fh);
@@ -1995,8 +2099,18 @@ irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id)
 		}
 	}
 
-	/* uCode wakes up after power-down sleep */
-	if (inta_hw & MSIX_HW_INT_CAUSES_REG_WAKEUP) {
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560 &&
+	    inta_hw & MSIX_HW_INT_CAUSES_REG_IPC) {
+		/* Reflect IML transfer status */
+		int res = iwl_read32(trans, CSR_IML_RESP_ADDR);
+
+		IWL_DEBUG_ISR(trans, "IML transfer status: %d\n", res);
+		if (res == IWL_IMAGE_RESP_FAIL) {
+			isr_stats->sw++;
+			iwl_pcie_irq_handle_error(trans);
+		}
+	} else if (inta_hw & MSIX_HW_INT_CAUSES_REG_WAKEUP) {
+		/* uCode wakes up after power-down sleep */
 		IWL_DEBUG_ISR(trans, "Wakeup interrupt\n");
 		iwl_pcie_rxq_check_wrptr(trans);
 		iwl_pcie_txq_check_wrptrs(trans);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
index b8e8dac2895d..2bc67219ed3e 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
@@ -53,6 +53,7 @@
 #include "iwl-trans.h"
 #include "iwl-prph.h"
 #include "iwl-context-info.h"
+#include "iwl-context-info-gen3.h"
 #include "internal.h"
 
 /*
@@ -188,7 +189,10 @@ void _iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans, bool low_power)
 	}
 
 	iwl_pcie_ctxt_info_free_paging(trans);
-	iwl_pcie_ctxt_info_free(trans);
+	if (trans->cfg->device_family == IWL_DEVICE_FAMILY_22560)
+		iwl_pcie_ctxt_info_gen3_free(trans);
+	else
+		iwl_pcie_ctxt_info_free(trans);
 
 	/* Make sure (redundant) we've released our request to stay awake */
 	iwl_clear_bit(trans, CSR_GP_CNTRL,
@@ -346,7 +350,10 @@ int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans,
 		goto out;
 	}
 
-	ret = iwl_pcie_ctxt_info_init(trans, fw);
+	if (trans->cfg->device_family == IWL_DEVICE_FAMILY_22560)
+		ret = iwl_pcie_ctxt_info_gen3_init(trans, fw);
+	else
+		ret = iwl_pcie_ctxt_info_init(trans, fw);
 	if (ret)
 		goto out;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 7229991ae70d..7d319b6863fe 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -84,6 +84,7 @@
 #include "iwl-scd.h"
 #include "iwl-agn-hw.h"
 #include "fw/error-dump.h"
+#include "fw/dbg.h"
 #include "internal.h"
 #include "iwl-fh.h"
 
@@ -203,7 +204,7 @@ static void iwl_pcie_free_fw_monitor(struct iwl_trans *trans)
 	trans_pcie->fw_mon_size = 0;
 }
 
-static void iwl_pcie_alloc_fw_monitor(struct iwl_trans *trans, u8 max_power)
+void iwl_pcie_alloc_fw_monitor(struct iwl_trans *trans, u8 max_power)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct page *page = NULL;
@@ -1132,21 +1133,44 @@ static struct iwl_causes_list causes_list[] = {
 	{MSIX_HW_INT_CAUSES_REG_HAP,		CSR_MSIX_HW_INT_MASK_AD, 0x2E},
 };
 
+static struct iwl_causes_list causes_list_v2[] = {
+	{MSIX_FH_INT_CAUSES_D2S_CH0_NUM,	CSR_MSIX_FH_INT_MASK_AD, 0},
+	{MSIX_FH_INT_CAUSES_D2S_CH1_NUM,	CSR_MSIX_FH_INT_MASK_AD, 0x1},
+	{MSIX_FH_INT_CAUSES_S2D,		CSR_MSIX_FH_INT_MASK_AD, 0x3},
+	{MSIX_FH_INT_CAUSES_FH_ERR,		CSR_MSIX_FH_INT_MASK_AD, 0x5},
+	{MSIX_HW_INT_CAUSES_REG_ALIVE,		CSR_MSIX_HW_INT_MASK_AD, 0x10},
+	{MSIX_HW_INT_CAUSES_REG_IPC,		CSR_MSIX_HW_INT_MASK_AD, 0x11},
+	{MSIX_HW_INT_CAUSES_REG_SW_ERR_V2,	CSR_MSIX_HW_INT_MASK_AD, 0x15},
+	{MSIX_HW_INT_CAUSES_REG_CT_KILL,	CSR_MSIX_HW_INT_MASK_AD, 0x16},
+	{MSIX_HW_INT_CAUSES_REG_RF_KILL,	CSR_MSIX_HW_INT_MASK_AD, 0x17},
+	{MSIX_HW_INT_CAUSES_REG_PERIODIC,	CSR_MSIX_HW_INT_MASK_AD, 0x18},
+	{MSIX_HW_INT_CAUSES_REG_SCD,		CSR_MSIX_HW_INT_MASK_AD, 0x2A},
+	{MSIX_HW_INT_CAUSES_REG_FH_TX,		CSR_MSIX_HW_INT_MASK_AD, 0x2B},
+	{MSIX_HW_INT_CAUSES_REG_HW_ERR,		CSR_MSIX_HW_INT_MASK_AD, 0x2D},
+	{MSIX_HW_INT_CAUSES_REG_HAP,		CSR_MSIX_HW_INT_MASK_AD, 0x2E},
+};
+
 static void iwl_pcie_map_non_rx_causes(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie =  IWL_TRANS_GET_PCIE_TRANS(trans);
 	int val = trans_pcie->def_irq | MSIX_NON_AUTO_CLEAR_CAUSE;
-	int i;
+	int i, arr_size =
+		(trans->cfg->device_family < IWL_DEVICE_FAMILY_22560) ?
+		ARRAY_SIZE(causes_list) : ARRAY_SIZE(causes_list_v2);
 
 	/*
 	 * Access all non RX causes and map them to the default irq.
 	 * In case we are missing at least one interrupt vector,
 	 * the first interrupt vector will serve non-RX and FBQ causes.
 	 */
-	for (i = 0; i < ARRAY_SIZE(causes_list); i++) {
-		iwl_write8(trans, CSR_MSIX_IVAR(causes_list[i].addr), val);
-		iwl_clear_bit(trans, causes_list[i].mask_reg,
-			      causes_list[i].cause_num);
+	for (i = 0; i < arr_size; i++) {
+		struct iwl_causes_list *causes =
+			(trans->cfg->device_family < IWL_DEVICE_FAMILY_22560) ?
+			causes_list : causes_list_v2;
+
+		iwl_write8(trans, CSR_MSIX_IVAR(causes[i].addr), val);
+		iwl_clear_bit(trans, causes[i].mask_reg,
+			      causes[i].cause_num);
 	}
 }
 
@@ -1539,18 +1563,6 @@ static int iwl_trans_pcie_d3_resume(struct iwl_trans *trans,
 
 	iwl_pcie_enable_rx_wake(trans, true);
 
-	/*
-	 * Reconfigure IVAR table in case of MSIX or reset ict table in
-	 * MSI mode since HW reset erased it.
-	 * Also enables interrupts - none will happen as
-	 * the device doesn't know we're waking it up, only when
-	 * the opmode actually tells it after this call.
-	 */
-	iwl_pcie_conf_msix_hw(trans_pcie);
-	if (!trans_pcie->msix_enabled)
-		iwl_pcie_reset_ict(trans);
-	iwl_enable_interrupts(trans);
-
 	iwl_set_bit(trans, CSR_GP_CNTRL,
 		    BIT(trans->cfg->csr->flag_mac_access_req));
 	iwl_set_bit(trans, CSR_GP_CNTRL,
@@ -1568,6 +1580,18 @@ static int iwl_trans_pcie_d3_resume(struct iwl_trans *trans,
 		return ret;
 	}
 
+	/*
+	 * Reconfigure IVAR table in case of MSIX or reset ict table in
+	 * MSI mode since HW reset erased it.
+	 * Also enables interrupts - none will happen as
+	 * the device doesn't know we're waking it up, only when
+	 * the opmode actually tells it after this call.
+	 */
+	iwl_pcie_conf_msix_hw(trans_pcie);
+	if (!trans_pcie->msix_enabled)
+		iwl_pcie_reset_ict(trans);
+	iwl_enable_interrupts(trans);
+
 	iwl_pcie_set_pwr(trans, false);
 
 	if (!reset) {
@@ -1685,29 +1709,6 @@ static void iwl_pcie_irq_set_affinity(struct iwl_trans *trans)
 	}
 }
 
-static const char *queue_name(struct device *dev,
-			      struct iwl_trans_pcie *trans_p, int i)
-{
-	if (trans_p->shared_vec_mask) {
-		int vec = trans_p->shared_vec_mask &
-			  IWL_SHARED_IRQ_FIRST_RSS ? 1 : 0;
-
-		if (i == 0)
-			return DRV_NAME ": shared IRQ";
-
-		return devm_kasprintf(dev, GFP_KERNEL,
-				      DRV_NAME ": queue %d", i + vec);
-	}
-	if (i == 0)
-		return DRV_NAME ": default queue";
-
-	if (i == trans_p->alloc_vecs - 1)
-		return DRV_NAME ": exception";
-
-	return devm_kasprintf(dev, GFP_KERNEL,
-			      DRV_NAME  ": queue %d", i);
-}
-
 static int iwl_pcie_init_msix_handler(struct pci_dev *pdev,
 				      struct iwl_trans_pcie *trans_pcie)
 {
@@ -2236,12 +2237,28 @@ void iwl_trans_pcie_log_scd_error(struct iwl_trans *trans, struct iwl_txq *txq)
 		jiffies_to_msecs(txq->wd_timeout),
 		txq->read_ptr, txq->write_ptr,
 		iwl_read_prph(trans, SCD_QUEUE_RDPTR(txq_id)) &
-			(TFD_QUEUE_SIZE_MAX - 1),
+			(trans->cfg->base_params->max_tfd_queue_size - 1),
 		iwl_read_prph(trans, SCD_QUEUE_WRPTR(txq_id)) &
-			(TFD_QUEUE_SIZE_MAX - 1),
+			(trans->cfg->base_params->max_tfd_queue_size - 1),
 		iwl_read_direct32(trans, FH_TX_TRB_REG(fifo)));
 }
 
+static int iwl_trans_pcie_rxq_dma_data(struct iwl_trans *trans, int queue,
+				       struct iwl_trans_rxq_dma_data *data)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+
+	if (queue >= trans->num_rx_queues || !trans_pcie->rxq)
+		return -EINVAL;
+
+	data->fr_bd_cb = trans_pcie->rxq[queue].bd_dma;
+	data->urbd_stts_wrptr = trans_pcie->rxq[queue].rb_stts_dma;
+	data->ur_bd_cb = trans_pcie->rxq[queue].used_bd_dma;
+	data->fr_bd_wid = 0;
+
+	return 0;
+}
+
 static int iwl_trans_pcie_wait_txq_empty(struct iwl_trans *trans, int txq_idx)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -2522,10 +2539,11 @@ static ssize_t iwl_dbgfs_rx_queue_read(struct file *file,
 		pos += scnprintf(buf + pos, bufsz - pos, "\tfree_count: %u\n",
 				 rxq->free_count);
 		if (rxq->rb_stts) {
+			u32 r =	__le16_to_cpu(iwl_get_closed_rb_stts(trans,
+								     rxq));
 			pos += scnprintf(buf + pos, bufsz - pos,
 					 "\tclosed_rb_num: %u\n",
-					 le16_to_cpu(rxq->rb_stts->closed_rb_num) &
-					 0x0FFF);
+					 r & 0x0FFF);
 		} else {
 			pos += scnprintf(buf + pos, bufsz - pos,
 					 "\tclosed_rb_num: Not Allocated\n");
@@ -2731,7 +2749,7 @@ static u32 iwl_trans_pcie_dump_rbs(struct iwl_trans *trans,
 
 	spin_lock(&rxq->lock);
 
-	r = le16_to_cpu(READ_ONCE(rxq->rb_stts->closed_rb_num)) & 0x0FFF;
+	r = le16_to_cpu(iwl_get_closed_rb_stts(trans, rxq)) & 0x0FFF;
 
 	for (i = rxq->read, j = 0;
 	     i != r && j < allocated_rb_nums;
@@ -2934,11 +2952,12 @@ static struct iwl_trans_dump_data
 	struct iwl_txq *cmdq = trans_pcie->txq[trans_pcie->cmd_queue];
 	struct iwl_fw_error_dump_txcmd *txcmd;
 	struct iwl_trans_dump_data *dump_data;
-	u32 len, num_rbs;
+	u32 len, num_rbs = 0;
 	u32 monitor_len;
 	int i, ptr;
 	bool dump_rbs = test_bit(STATUS_FW_ERROR, &trans->status) &&
-			!trans->cfg->mq_rx_supported;
+			!trans->cfg->mq_rx_supported &&
+			trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_RB);
 
 	/* transport dump header */
 	len = sizeof(*dump_data);
@@ -2990,6 +3009,10 @@ static struct iwl_trans_dump_data
 	}
 
 	if (trigger && (trigger->mode & IWL_FW_DBG_TRIGGER_MONITOR_ONLY)) {
+		if (!(trans->dbg_dump_mask &
+		      BIT(IWL_FW_ERROR_DUMP_FW_MONITOR)))
+			return NULL;
+
 		dump_data = vzalloc(len);
 		if (!dump_data)
 			return NULL;
@@ -3002,22 +3025,28 @@ static struct iwl_trans_dump_data
 	}
 
 	/* CSR registers */
-	len += sizeof(*data) + IWL_CSR_TO_DUMP;
+	if (trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_CSR))
+		len += sizeof(*data) + IWL_CSR_TO_DUMP;
 
 	/* FH registers */
-	if (trans->cfg->gen2)
-		len += sizeof(*data) +
-		       (FH_MEM_UPPER_BOUND_GEN2 - FH_MEM_LOWER_BOUND_GEN2);
-	else
-		len += sizeof(*data) +
-		       (FH_MEM_UPPER_BOUND - FH_MEM_LOWER_BOUND);
+	if (trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_FH_REGS)) {
+		if (trans->cfg->gen2)
+			len += sizeof(*data) +
+			       (FH_MEM_UPPER_BOUND_GEN2 -
+				FH_MEM_LOWER_BOUND_GEN2);
+		else
+			len += sizeof(*data) +
+			       (FH_MEM_UPPER_BOUND -
+				FH_MEM_LOWER_BOUND);
+	}
 
 	if (dump_rbs) {
 		/* Dump RBs is supported only for pre-9000 devices (1 queue) */
 		struct iwl_rxq *rxq = &trans_pcie->rxq[0];
 		/* RBs */
-		num_rbs = le16_to_cpu(READ_ONCE(rxq->rb_stts->closed_rb_num))
-				      & 0x0FFF;
+		num_rbs =
+			le16_to_cpu(iwl_get_closed_rb_stts(trans, rxq))
+			& 0x0FFF;
 		num_rbs = (num_rbs - rxq->read) & RX_QUEUE_MASK;
 		len += num_rbs * (sizeof(*data) +
 				  sizeof(struct iwl_fw_error_dump_rb) +
@@ -3025,7 +3054,8 @@ static struct iwl_trans_dump_data
 	}
 
 	/* Paged memory for gen2 HW */
-	if (trans->cfg->gen2)
+	if (trans->cfg->gen2 &&
+	    trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_PAGING))
 		for (i = 0; i < trans_pcie->init_dram.paging_cnt; i++)
 			len += sizeof(*data) +
 			       sizeof(struct iwl_fw_error_dump_paging) +
@@ -3037,41 +3067,51 @@ static struct iwl_trans_dump_data
 
 	len = 0;
 	data = (void *)dump_data->data;
-	data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_TXCMD);
-	txcmd = (void *)data->data;
-	spin_lock_bh(&cmdq->lock);
-	ptr = cmdq->write_ptr;
-	for (i = 0; i < cmdq->n_window; i++) {
-		u8 idx = iwl_pcie_get_cmd_index(cmdq, ptr);
-		u32 caplen, cmdlen;
-
-		cmdlen = iwl_trans_pcie_get_cmdlen(trans, cmdq->tfds +
-						   trans_pcie->tfd_size * ptr);
-		caplen = min_t(u32, TFD_MAX_PAYLOAD_SIZE, cmdlen);
-
-		if (cmdlen) {
-			len += sizeof(*txcmd) + caplen;
-			txcmd->cmdlen = cpu_to_le32(cmdlen);
-			txcmd->caplen = cpu_to_le32(caplen);
-			memcpy(txcmd->data, cmdq->entries[idx].cmd, caplen);
-			txcmd = (void *)((u8 *)txcmd->data + caplen);
+
+	if (trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_TXCMD)) {
+		u16 tfd_size = trans_pcie->tfd_size;
+
+		data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_TXCMD);
+		txcmd = (void *)data->data;
+		spin_lock_bh(&cmdq->lock);
+		ptr = cmdq->write_ptr;
+		for (i = 0; i < cmdq->n_window; i++) {
+			u8 idx = iwl_pcie_get_cmd_index(cmdq, ptr);
+			u32 caplen, cmdlen;
+
+			cmdlen = iwl_trans_pcie_get_cmdlen(trans,
+							   cmdq->tfds +
+							   tfd_size * ptr);
+			caplen = min_t(u32, TFD_MAX_PAYLOAD_SIZE, cmdlen);
+
+			if (cmdlen) {
+				len += sizeof(*txcmd) + caplen;
+				txcmd->cmdlen = cpu_to_le32(cmdlen);
+				txcmd->caplen = cpu_to_le32(caplen);
+				memcpy(txcmd->data, cmdq->entries[idx].cmd,
+				       caplen);
+				txcmd = (void *)((u8 *)txcmd->data + caplen);
+			}
+
+			ptr = iwl_queue_dec_wrap(trans, ptr);
 		}
+		spin_unlock_bh(&cmdq->lock);
 
-		ptr = iwl_queue_dec_wrap(ptr);
+		data->len = cpu_to_le32(len);
+		len += sizeof(*data);
+		data = iwl_fw_error_next_data(data);
 	}
-	spin_unlock_bh(&cmdq->lock);
 
-	data->len = cpu_to_le32(len);
-	len += sizeof(*data);
-	data = iwl_fw_error_next_data(data);
-
-	len += iwl_trans_pcie_dump_csr(trans, &data);
-	len += iwl_trans_pcie_fh_regs_dump(trans, &data);
+	if (trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_CSR))
+		len += iwl_trans_pcie_dump_csr(trans, &data);
+	if (trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_FH_REGS))
+		len += iwl_trans_pcie_fh_regs_dump(trans, &data);
 	if (dump_rbs)
 		len += iwl_trans_pcie_dump_rbs(trans, &data, num_rbs);
 
 	/* Paged memory for gen2 HW */
-	if (trans->cfg->gen2) {
+	if (trans->cfg->gen2 &&
+	    trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_PAGING)) {
 		for (i = 0; i < trans_pcie->init_dram.paging_cnt; i++) {
 			struct iwl_fw_error_dump_paging *paging;
 			dma_addr_t addr =
@@ -3091,8 +3131,8 @@ static struct iwl_trans_dump_data
 			len += sizeof(*data) + sizeof(*paging) + page_len;
 		}
 	}
-
-	len += iwl_trans_pcie_dump_monitor(trans, &data, monitor_len);
+	if (trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_FW_MONITOR))
+		len += iwl_trans_pcie_dump_monitor(trans, &data, monitor_len);
 
 	dump_data->len = len;
 
@@ -3187,6 +3227,7 @@ static const struct iwl_trans_ops trans_ops_pcie_gen2 = {
 	.txq_alloc = iwl_trans_pcie_dyn_txq_alloc,
 	.txq_free = iwl_trans_pcie_dyn_txq_free,
 	.wait_txq_empty = iwl_trans_pcie_wait_txq_empty,
+	.rxq_dma_data = iwl_trans_pcie_rxq_dma_data,
 };
 
 struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
@@ -3349,14 +3390,26 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 
 #if IS_ENABLED(CONFIG_IWLMVM)
 	trans->hw_rf_id = iwl_read32(trans, CSR_HW_RF_ID);
-	if (trans->hw_rf_id == CSR_HW_RF_ID_TYPE_HR) {
+
+	if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
+	    CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR)) {
 		u32 hw_status;
 
 		hw_status = iwl_read_prph(trans, UMAG_GEN_HW_STATUS);
-		if (hw_status & UMAG_GEN_HW_IS_FPGA)
-			trans->cfg = &iwl22000_2ax_cfg_qnj_hr_f0;
-		else
+		if (CSR_HW_RF_STEP(trans->hw_rf_id) == SILICON_B_STEP)
+			/*
+			* b step fw is the same for physical card and fpga
+			*/
+			trans->cfg = &iwl22000_2ax_cfg_qnj_hr_b0;
+		else if ((hw_status & UMAG_GEN_HW_IS_FPGA) &&
+			 CSR_HW_RF_STEP(trans->hw_rf_id) == SILICON_A_STEP) {
+			trans->cfg = &iwl22000_2ax_cfg_qnj_hr_a0_f0;
+		} else {
+			/*
+			* a step no FPGA
+			*/
 			trans->cfg = &iwl22000_2ac_cfg_hr;
+		}
 	}
 #endif
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 48890a1c825f..b99f33ff9123 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -6,6 +6,7 @@
  * GPL LICENSE SUMMARY
  *
  * Copyright(c) 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018        Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -19,6 +20,7 @@
  * BSD LICENSE
  *
  * Copyright(c) 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018        Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -50,6 +52,7 @@
  *****************************************************************************/
 #include <linux/pm_runtime.h>
 #include <net/tso.h>
+#include <linux/tcp.h>
 
 #include "iwl-debug.h"
 #include "iwl-csr.h"
@@ -84,16 +87,20 @@ void iwl_pcie_gen2_tx_stop(struct iwl_trans *trans)
 /*
  * iwl_pcie_txq_update_byte_tbl - Set up entry in Tx byte-count array
  */
-static void iwl_pcie_gen2_update_byte_tbl(struct iwl_txq *txq, u16 byte_cnt,
+static void iwl_pcie_gen2_update_byte_tbl(struct iwl_trans_pcie *trans_pcie,
+					  struct iwl_txq *txq, u16 byte_cnt,
 					  int num_tbs)
 {
 	struct iwlagn_scd_bc_tbl *scd_bc_tbl = txq->bc_tbl.addr;
+	struct iwl_trans *trans = iwl_trans_pcie_get_trans(trans_pcie);
+	struct iwl_gen3_bc_tbl *scd_bc_tbl_gen3 = txq->bc_tbl.addr;
 	int idx = iwl_pcie_get_cmd_index(txq, txq->write_ptr);
 	u8 filled_tfd_size, num_fetch_chunks;
 	u16 len = byte_cnt;
 	__le16 bc_ent;
 
-	len = DIV_ROUND_UP(len, 4);
+	if (trans_pcie->bc_table_dword)
+		len = DIV_ROUND_UP(len, 4);
 
 	if (WARN_ON(len > 0xFFF || idx >= txq->n_window))
 		return;
@@ -111,7 +118,10 @@ static void iwl_pcie_gen2_update_byte_tbl(struct iwl_txq *txq, u16 byte_cnt,
 	num_fetch_chunks = DIV_ROUND_UP(filled_tfd_size, 64) - 1;
 
 	bc_ent = cpu_to_le16(len | (num_fetch_chunks << 12));
-	scd_bc_tbl->tfd_offset[idx] = bc_ent;
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+		scd_bc_tbl_gen3->tfd_offset[idx] = bc_ent;
+	else
+		scd_bc_tbl->tfd_offset[idx] = bc_ent;
 }
 
 /*
@@ -355,52 +365,89 @@ out_err:
 	return -EINVAL;
 }
 
-static
-struct iwl_tfh_tfd *iwl_pcie_gen2_build_tfd(struct iwl_trans *trans,
-					    struct iwl_txq *txq,
-					    struct iwl_device_cmd *dev_cmd,
-					    struct sk_buff *skb,
-					    struct iwl_cmd_meta *out_meta)
+static struct
+iwl_tfh_tfd *iwl_pcie_gen2_build_tx_amsdu(struct iwl_trans *trans,
+					  struct iwl_txq *txq,
+					  struct iwl_device_cmd *dev_cmd,
+					  struct sk_buff *skb,
+					  struct iwl_cmd_meta *out_meta,
+					  int hdr_len,
+					  int tx_cmd_len)
 {
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	int idx = iwl_pcie_get_cmd_index(txq, txq->write_ptr);
 	struct iwl_tfh_tfd *tfd = iwl_pcie_get_tfd(trans, txq, idx);
 	dma_addr_t tb_phys;
-	bool amsdu;
-	int i, len, tb1_len, tb2_len, hdr_len;
+	int len;
 	void *tb1_addr;
 
-	memset(tfd, 0, sizeof(*tfd));
+	tb_phys = iwl_pcie_get_first_tb_dma(txq, idx);
 
-	amsdu = ieee80211_is_data_qos(hdr->frame_control) &&
-		(*ieee80211_get_qos_ctl(hdr) &
-		 IEEE80211_QOS_CTL_A_MSDU_PRESENT);
+	iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, IWL_FIRST_TB_SIZE);
+
+	/*
+	 * The second TB (tb1) points to the remainder of the TX command
+	 * and the 802.11 header - dword aligned size
+	 * (This calculation modifies the TX command, so do it before the
+	 * setup of the first TB)
+	 */
+	len = tx_cmd_len + sizeof(struct iwl_cmd_header) + hdr_len -
+	      IWL_FIRST_TB_SIZE;
+
+	/* do not align A-MSDU to dword as the subframe header aligns it */
+
+	/* map the data for TB1 */
+	tb1_addr = ((u8 *)&dev_cmd->hdr) + IWL_FIRST_TB_SIZE;
+	tb_phys = dma_map_single(trans->dev, tb1_addr, len, DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
+		goto out_err;
+	iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, len);
+
+	if (iwl_pcie_gen2_build_amsdu(trans, skb, tfd,
+				      len + IWL_FIRST_TB_SIZE,
+				      hdr_len, dev_cmd))
+		goto out_err;
+
+	/* building the A-MSDU might have changed this data, memcpy it now */
+	memcpy(&txq->first_tb_bufs[idx], &dev_cmd->hdr, IWL_FIRST_TB_SIZE);
+	return tfd;
+
+out_err:
+	iwl_pcie_gen2_tfd_unmap(trans, out_meta, tfd);
+	return NULL;
+}
+
+static struct
+iwl_tfh_tfd *iwl_pcie_gen2_build_tx(struct iwl_trans *trans,
+				    struct iwl_txq *txq,
+				    struct iwl_device_cmd *dev_cmd,
+				    struct sk_buff *skb,
+				    struct iwl_cmd_meta *out_meta,
+				    int hdr_len,
+				    int tx_cmd_len)
+{
+	int idx = iwl_pcie_get_cmd_index(txq, txq->write_ptr);
+	struct iwl_tfh_tfd *tfd = iwl_pcie_get_tfd(trans, txq, idx);
+	dma_addr_t tb_phys;
+	int i, len, tb1_len, tb2_len;
+	void *tb1_addr;
 
 	tb_phys = iwl_pcie_get_first_tb_dma(txq, idx);
+
 	/* The first TB points to bi-directional DMA data */
-	if (!amsdu)
-		memcpy(&txq->first_tb_bufs[idx], &dev_cmd->hdr,
-		       IWL_FIRST_TB_SIZE);
+	memcpy(&txq->first_tb_bufs[idx], &dev_cmd->hdr, IWL_FIRST_TB_SIZE);
 
 	iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, IWL_FIRST_TB_SIZE);
 
-	/* there must be data left over for TB1 or this code must be changed */
-	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen2) < IWL_FIRST_TB_SIZE);
-
 	/*
 	 * The second TB (tb1) points to the remainder of the TX command
 	 * and the 802.11 header - dword aligned size
 	 * (This calculation modifies the TX command, so do it before the
 	 * setup of the first TB)
 	 */
-	len = sizeof(struct iwl_tx_cmd_gen2) + sizeof(struct iwl_cmd_header) +
-	      ieee80211_hdrlen(hdr->frame_control) - IWL_FIRST_TB_SIZE;
+	len = tx_cmd_len + sizeof(struct iwl_cmd_header) + hdr_len -
+	      IWL_FIRST_TB_SIZE;
 
-	/* do not align A-MSDU to dword as the subframe header aligns it */
-	if (amsdu)
-		tb1_len = len;
-	else
-		tb1_len = ALIGN(len, 4);
+	tb1_len = ALIGN(len, 4);
 
 	/* map the data for TB1 */
 	tb1_addr = ((u8 *)&dev_cmd->hdr) + IWL_FIRST_TB_SIZE;
@@ -409,23 +456,6 @@ struct iwl_tfh_tfd *iwl_pcie_gen2_build_tfd(struct iwl_trans *trans,
 		goto out_err;
 	iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, tb1_len);
 
-	hdr_len = ieee80211_hdrlen(hdr->frame_control);
-
-	if (amsdu) {
-		if (iwl_pcie_gen2_build_amsdu(trans, skb, tfd,
-					      tb1_len + IWL_FIRST_TB_SIZE,
-					      hdr_len, dev_cmd))
-			goto out_err;
-
-		/*
-		 * building the A-MSDU might have changed this data, so memcpy
-		 * it now
-		 */
-		memcpy(&txq->first_tb_bufs[idx], &dev_cmd->hdr,
-		       IWL_FIRST_TB_SIZE);
-		return tfd;
-	}
-
 	/* set up TFD's third entry to point to remainder of skb's head */
 	tb2_len = skb_headlen(skb) - hdr_len;
 
@@ -467,13 +497,50 @@ out_err:
 	return NULL;
 }
 
+static
+struct iwl_tfh_tfd *iwl_pcie_gen2_build_tfd(struct iwl_trans *trans,
+					    struct iwl_txq *txq,
+					    struct iwl_device_cmd *dev_cmd,
+					    struct sk_buff *skb,
+					    struct iwl_cmd_meta *out_meta)
+{
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+	int idx = iwl_pcie_get_cmd_index(txq, txq->write_ptr);
+	struct iwl_tfh_tfd *tfd = iwl_pcie_get_tfd(trans, txq, idx);
+	int len, hdr_len;
+	bool amsdu;
+
+	/* There must be data left over for TB1 or this code must be changed */
+	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen2) < IWL_FIRST_TB_SIZE);
+
+	memset(tfd, 0, sizeof(*tfd));
+
+	if (trans->cfg->device_family < IWL_DEVICE_FAMILY_22560)
+		len = sizeof(struct iwl_tx_cmd_gen2);
+	else
+		len = sizeof(struct iwl_tx_cmd_gen3);
+
+	amsdu = ieee80211_is_data_qos(hdr->frame_control) &&
+			(*ieee80211_get_qos_ctl(hdr) &
+			 IEEE80211_QOS_CTL_A_MSDU_PRESENT);
+
+	hdr_len = ieee80211_hdrlen(hdr->frame_control);
+
+	if (amsdu)
+		return iwl_pcie_gen2_build_tx_amsdu(trans, txq, dev_cmd, skb,
+						    out_meta, hdr_len, len);
+
+	return iwl_pcie_gen2_build_tx(trans, txq, dev_cmd, skb, out_meta,
+				      hdr_len, len);
+}
+
 int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
 			   struct iwl_device_cmd *dev_cmd, int txq_id)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_tx_cmd_gen2 *tx_cmd = (void *)dev_cmd->payload;
 	struct iwl_cmd_meta *out_meta;
 	struct iwl_txq *txq = trans_pcie->txq[txq_id];
+	u16 cmd_len;
 	int idx;
 	void *tfd;
 
@@ -488,11 +555,23 @@ int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
 
 	spin_lock(&txq->lock);
 
-	if (iwl_queue_space(txq) < txq->high_mark) {
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
+		struct iwl_tx_cmd_gen3 *tx_cmd_gen3 =
+			(void *)dev_cmd->payload;
+
+		cmd_len = le16_to_cpu(tx_cmd_gen3->len);
+	} else {
+		struct iwl_tx_cmd_gen2 *tx_cmd_gen2 =
+			(void *)dev_cmd->payload;
+
+		cmd_len = le16_to_cpu(tx_cmd_gen2->len);
+	}
+
+	if (iwl_queue_space(trans, txq) < txq->high_mark) {
 		iwl_stop_queue(trans, txq);
 
 		/* don't put the packet on the ring, if there is no room */
-		if (unlikely(iwl_queue_space(txq) < 3)) {
+		if (unlikely(iwl_queue_space(trans, txq) < 3)) {
 			struct iwl_device_cmd **dev_cmd_ptr;
 
 			dev_cmd_ptr = (void *)((u8 *)skb->cb +
@@ -526,7 +605,7 @@ int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
 	}
 
 	/* Set up entry for this TFD in Tx byte-count array */
-	iwl_pcie_gen2_update_byte_tbl(txq, le16_to_cpu(tx_cmd->len),
+	iwl_pcie_gen2_update_byte_tbl(trans_pcie, txq, cmd_len,
 				      iwl_pcie_gen2_get_num_tbs(trans, tfd));
 
 	/* start timer if queue currently empty */
@@ -538,7 +617,7 @@ int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
 	}
 
 	/* Tell device the write index *just past* this latest filled TFD */
-	txq->write_ptr = iwl_queue_inc_wrap(txq->write_ptr);
+	txq->write_ptr = iwl_queue_inc_wrap(trans, txq->write_ptr);
 	iwl_pcie_gen2_txq_inc_wr_ptr(trans, txq);
 	/*
 	 * At this point the frame is "transmitted" successfully
@@ -650,7 +729,7 @@ static int iwl_pcie_gen2_enqueue_hcmd(struct iwl_trans *trans,
 	tfd = iwl_pcie_get_tfd(trans, txq, txq->write_ptr);
 	memset(tfd, 0, sizeof(*tfd));
 
-	if (iwl_queue_space(txq) < ((cmd->flags & CMD_ASYNC) ? 2 : 1)) {
+	if (iwl_queue_space(trans, txq) < ((cmd->flags & CMD_ASYNC) ? 2 : 1)) {
 		spin_unlock_bh(&txq->lock);
 
 		IWL_ERR(trans, "No space in command queue\n");
@@ -787,7 +866,7 @@ static int iwl_pcie_gen2_enqueue_hcmd(struct iwl_trans *trans,
 		iwl_trans_ref(trans);
 	}
 	/* Increment and update queue's write index */
-	txq->write_ptr = iwl_queue_inc_wrap(txq->write_ptr);
+	txq->write_ptr = iwl_queue_inc_wrap(trans, txq->write_ptr);
 	iwl_pcie_gen2_txq_inc_wr_ptr(trans, txq);
 	spin_unlock_irqrestore(&trans_pcie->reg_lock, flags);
 
@@ -954,7 +1033,7 @@ void iwl_pcie_gen2_txq_unmap(struct iwl_trans *trans, int txq_id)
 			iwl_pcie_free_tso_page(trans_pcie, skb);
 		}
 		iwl_pcie_gen2_free_tfd(trans, txq);
-		txq->read_ptr = iwl_queue_inc_wrap(txq->read_ptr);
+		txq->read_ptr = iwl_queue_inc_wrap(trans, txq->read_ptr);
 
 		if (txq->read_ptr == txq->write_ptr) {
 			unsigned long flags;
@@ -1062,6 +1141,9 @@ int iwl_trans_pcie_dyn_txq_alloc(struct iwl_trans *trans,
 	if (!txq)
 		return -ENOMEM;
 	ret = iwl_pcie_alloc_dma_ptr(trans, &txq->bc_tbl,
+				     (trans->cfg->device_family >=
+				      IWL_DEVICE_FAMILY_22560) ?
+				     sizeof(struct iwl_gen3_bc_tbl) :
 				     sizeof(struct iwlagn_scd_bc_tbl));
 	if (ret) {
 		IWL_ERR(trans, "Scheduler BC Table allocation failed\n");
@@ -1113,7 +1195,7 @@ int iwl_trans_pcie_dyn_txq_alloc(struct iwl_trans *trans,
 
 	txq->id = qid;
 	trans_pcie->txq[qid] = txq;
-	wr_ptr &= (TFD_QUEUE_SIZE_MAX - 1);
+	wr_ptr &= (trans->cfg->base_params->max_tfd_queue_size - 1);
 
 	/* Place first TFD at index corresponding to start sequence number */
 	txq->read_ptr = wr_ptr;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 473fe7ccb07c..93f0d387688a 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -71,27 +71,28 @@
  *
  ***************************************************/
 
-int iwl_queue_space(const struct iwl_txq *q)
+int iwl_queue_space(struct iwl_trans *trans, const struct iwl_txq *q)
 {
 	unsigned int max;
 	unsigned int used;
 
 	/*
 	 * To avoid ambiguity between empty and completely full queues, there
-	 * should always be less than TFD_QUEUE_SIZE_MAX elements in the queue.
-	 * If q->n_window is smaller than TFD_QUEUE_SIZE_MAX, there is no need
+	 * should always be less than max_tfd_queue_size elements in the queue.
+	 * If q->n_window is smaller than max_tfd_queue_size, there is no need
 	 * to reserve any queue entries for this purpose.
 	 */
-	if (q->n_window < TFD_QUEUE_SIZE_MAX)
+	if (q->n_window < trans->cfg->base_params->max_tfd_queue_size)
 		max = q->n_window;
 	else
-		max = TFD_QUEUE_SIZE_MAX - 1;
+		max = trans->cfg->base_params->max_tfd_queue_size - 1;
 
 	/*
-	 * TFD_QUEUE_SIZE_MAX is a power of 2, so the following is equivalent to
-	 * modulo by TFD_QUEUE_SIZE_MAX and is well defined.
+	 * max_tfd_queue_size is a power of 2, so the following is equivalent to
+	 * modulo by max_tfd_queue_size and is well defined.
 	 */
-	used = (q->write_ptr - q->read_ptr) & (TFD_QUEUE_SIZE_MAX - 1);
+	used = (q->write_ptr - q->read_ptr) &
+		(trans->cfg->base_params->max_tfd_queue_size - 1);
 
 	if (WARN_ON(used > max))
 		return 0;
@@ -489,7 +490,8 @@ int iwl_pcie_txq_alloc(struct iwl_trans *trans, struct iwl_txq *txq,
 		       int slots_num, bool cmd_queue)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	size_t tfd_sz = trans_pcie->tfd_size * TFD_QUEUE_SIZE_MAX;
+	size_t tfd_sz = trans_pcie->tfd_size *
+		trans->cfg->base_params->max_tfd_queue_size;
 	size_t tb0_buf_sz;
 	int i;
 
@@ -555,12 +557,16 @@ int iwl_pcie_txq_init(struct iwl_trans *trans, struct iwl_txq *txq,
 		      int slots_num, bool cmd_queue)
 {
 	int ret;
+	u32 tfd_queue_max_size = trans->cfg->base_params->max_tfd_queue_size;
 
 	txq->need_update = false;
 
-	/* TFD_QUEUE_SIZE_MAX must be power-of-two size, otherwise
+	/* max_tfd_queue_size must be power-of-two size, otherwise
 	 * iwl_queue_inc_wrap and iwl_queue_dec_wrap are broken. */
-	BUILD_BUG_ON(TFD_QUEUE_SIZE_MAX & (TFD_QUEUE_SIZE_MAX - 1));
+	if (WARN_ONCE(tfd_queue_max_size & (tfd_queue_max_size - 1),
+		      "Max tfd queue size must be a power of two, but is %d",
+		      tfd_queue_max_size))
+		return -EINVAL;
 
 	/* Initialize queue's high/low-water marks, and head/tail indexes */
 	ret = iwl_queue_init(txq, slots_num);
@@ -637,7 +643,7 @@ static void iwl_pcie_txq_unmap(struct iwl_trans *trans, int txq_id)
 			iwl_pcie_free_tso_page(trans_pcie, skb);
 		}
 		iwl_pcie_txq_free_tfd(trans, txq);
-		txq->read_ptr = iwl_queue_inc_wrap(txq->read_ptr);
+		txq->read_ptr = iwl_queue_inc_wrap(trans, txq->read_ptr);
 
 		if (txq->read_ptr == txq->write_ptr) {
 			unsigned long flags;
@@ -696,7 +702,8 @@ static void iwl_pcie_txq_free(struct iwl_trans *trans, int txq_id)
 	/* De-alloc circular buffer of TFDs */
 	if (txq->tfds) {
 		dma_free_coherent(dev,
-				  trans_pcie->tfd_size * TFD_QUEUE_SIZE_MAX,
+				  trans_pcie->tfd_size *
+				  trans->cfg->base_params->max_tfd_queue_size,
 				  txq->tfds, txq->dma_addr);
 		txq->dma_addr = 0;
 		txq->tfds = NULL;
@@ -916,9 +923,11 @@ static int iwl_pcie_tx_alloc(struct iwl_trans *trans)
 	int ret;
 	int txq_id, slots_num;
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	u16 bc_tbls_size = trans->cfg->base_params->num_of_queues;
 
-	u16 scd_bc_tbls_size = trans->cfg->base_params->num_of_queues *
-			sizeof(struct iwlagn_scd_bc_tbl);
+	bc_tbls_size *= (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) ?
+		sizeof(struct iwl_gen3_bc_tbl) :
+		sizeof(struct iwlagn_scd_bc_tbl);
 
 	/*It is not allowed to alloc twice, so warn when this happens.
 	 * We cannot rely on the previous allocation, so free and fail */
@@ -928,7 +937,7 @@ static int iwl_pcie_tx_alloc(struct iwl_trans *trans)
 	}
 
 	ret = iwl_pcie_alloc_dma_ptr(trans, &trans_pcie->scd_bc_tbls,
-				   scd_bc_tbls_size);
+				     bc_tbls_size);
 	if (ret) {
 		IWL_ERR(trans, "Scheduler BC Table allocation failed\n");
 		goto error;
@@ -1064,7 +1073,8 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_txq *txq = trans_pcie->txq[txq_id];
-	int tfd_num = ssn & (TFD_QUEUE_SIZE_MAX - 1);
+	int tfd_num = iwl_pcie_get_cmd_index(txq, ssn);
+	int read_ptr = iwl_pcie_get_cmd_index(txq, txq->read_ptr);
 	int last_to_free;
 
 	/* This function is not meant to release cmd queue*/
@@ -1079,7 +1089,7 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 		goto out;
 	}
 
-	if (txq->read_ptr == tfd_num)
+	if (read_ptr == tfd_num)
 		goto out;
 
 	IWL_DEBUG_TX_REPLY(trans, "[Q %d] %d -> %d (%d)\n",
@@ -1087,12 +1097,13 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 
 	/*Since we free until index _not_ inclusive, the one before index is
 	 * the last we will free. This one must be used */
-	last_to_free = iwl_queue_dec_wrap(tfd_num);
+	last_to_free = iwl_queue_dec_wrap(trans, tfd_num);
 
 	if (!iwl_queue_used(txq, last_to_free)) {
 		IWL_ERR(trans,
 			"%s: Read index for DMA queue txq id (%d), last_to_free %d is out of range [0-%d] %d %d.\n",
-			__func__, txq_id, last_to_free, TFD_QUEUE_SIZE_MAX,
+			__func__, txq_id, last_to_free,
+			trans->cfg->base_params->max_tfd_queue_size,
 			txq->write_ptr, txq->read_ptr);
 		goto out;
 	}
@@ -1101,10 +1112,10 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 		goto out;
 
 	for (;
-	     txq->read_ptr != tfd_num;
-	     txq->read_ptr = iwl_queue_inc_wrap(txq->read_ptr)) {
-		int idx = iwl_pcie_get_cmd_index(txq, txq->read_ptr);
-		struct sk_buff *skb = txq->entries[idx].skb;
+	     read_ptr != tfd_num;
+	     txq->read_ptr = iwl_queue_inc_wrap(trans, txq->read_ptr),
+	     read_ptr = iwl_pcie_get_cmd_index(txq, txq->read_ptr)) {
+		struct sk_buff *skb = txq->entries[read_ptr].skb;
 
 		if (WARN_ON_ONCE(!skb))
 			continue;
@@ -1113,7 +1124,7 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 
 		__skb_queue_tail(skbs, skb);
 
-		txq->entries[idx].skb = NULL;
+		txq->entries[read_ptr].skb = NULL;
 
 		if (!trans->cfg->use_tfh)
 			iwl_pcie_txq_inval_byte_cnt_tbl(trans, txq);
@@ -1123,7 +1134,7 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 
 	iwl_pcie_txq_progress(txq);
 
-	if (iwl_queue_space(txq) > txq->low_mark &&
+	if (iwl_queue_space(trans, txq) > txq->low_mark &&
 	    test_bit(txq_id, trans_pcie->queue_stopped)) {
 		struct sk_buff_head overflow_skbs;
 
@@ -1155,7 +1166,7 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 		}
 		spin_lock_bh(&txq->lock);
 
-		if (iwl_queue_space(txq) > txq->low_mark)
+		if (iwl_queue_space(trans, txq) > txq->low_mark)
 			iwl_wake_queue(trans, txq);
 	}
 
@@ -1225,23 +1236,30 @@ static void iwl_pcie_cmdq_reclaim(struct iwl_trans *trans, int txq_id, int idx)
 	struct iwl_txq *txq = trans_pcie->txq[txq_id];
 	unsigned long flags;
 	int nfreed = 0;
+	u16 r;
 
 	lockdep_assert_held(&txq->lock);
 
-	if ((idx >= TFD_QUEUE_SIZE_MAX) || (!iwl_queue_used(txq, idx))) {
+	idx = iwl_pcie_get_cmd_index(txq, idx);
+	r = iwl_pcie_get_cmd_index(txq, txq->read_ptr);
+
+	if (idx >= trans->cfg->base_params->max_tfd_queue_size ||
+	    (!iwl_queue_used(txq, idx))) {
 		IWL_ERR(trans,
 			"%s: Read index for DMA queue txq id (%d), index %d is out of range [0-%d] %d %d.\n",
-			__func__, txq_id, idx, TFD_QUEUE_SIZE_MAX,
+			__func__, txq_id, idx,
+			trans->cfg->base_params->max_tfd_queue_size,
 			txq->write_ptr, txq->read_ptr);
 		return;
 	}
 
-	for (idx = iwl_queue_inc_wrap(idx); txq->read_ptr != idx;
-	     txq->read_ptr = iwl_queue_inc_wrap(txq->read_ptr)) {
+	for (idx = iwl_queue_inc_wrap(trans, idx); r != idx;
+	     r = iwl_queue_inc_wrap(trans, r)) {
+		txq->read_ptr = iwl_queue_inc_wrap(trans, txq->read_ptr);
 
 		if (nfreed++ > 0) {
 			IWL_ERR(trans, "HCMD skipped: index (%d) %d %d\n",
-				idx, txq->write_ptr, txq->read_ptr);
+				idx, txq->write_ptr, r);
 			iwl_force_nmi(trans);
 		}
 	}
@@ -1555,7 +1573,7 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 
 	spin_lock_bh(&txq->lock);
 
-	if (iwl_queue_space(txq) < ((cmd->flags & CMD_ASYNC) ? 2 : 1)) {
+	if (iwl_queue_space(trans, txq) < ((cmd->flags & CMD_ASYNC) ? 2 : 1)) {
 		spin_unlock_bh(&txq->lock);
 
 		IWL_ERR(trans, "No space in command queue\n");
@@ -1711,7 +1729,7 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 	}
 
 	/* Increment and update queue's write index */
-	txq->write_ptr = iwl_queue_inc_wrap(txq->write_ptr);
+	txq->write_ptr = iwl_queue_inc_wrap(trans, txq->write_ptr);
 	iwl_pcie_txq_inc_wr_ptr(trans, txq);
 
 	spin_unlock_irqrestore(&trans_pcie->reg_lock, flags);
@@ -2311,11 +2329,11 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 
 	spin_lock(&txq->lock);
 
-	if (iwl_queue_space(txq) < txq->high_mark) {
+	if (iwl_queue_space(trans, txq) < txq->high_mark) {
 		iwl_stop_queue(trans, txq);
 
 		/* don't put the packet on the ring, if there is no room */
-		if (unlikely(iwl_queue_space(txq) < 3)) {
+		if (unlikely(iwl_queue_space(trans, txq) < 3)) {
 			struct iwl_device_cmd **dev_cmd_ptr;
 
 			dev_cmd_ptr = (void *)((u8 *)skb->cb +
@@ -2444,7 +2462,7 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 	}
 
 	/* Tell device the write index *just past* this latest filled TFD */
-	txq->write_ptr = iwl_queue_inc_wrap(txq->write_ptr);
+	txq->write_ptr = iwl_queue_inc_wrap(trans, txq->write_ptr);
 	if (!wait_write_ptr)
 		iwl_pcie_txq_inc_wr_ptr(trans, txq);
 
diff --git a/drivers/net/wireless/intersil/hostap/hostap_ap.c b/drivers/net/wireless/intersil/hostap/hostap_ap.c
index d1884b8913e7..0094b1d2b577 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_ap.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_ap.c
@@ -66,7 +66,7 @@ static void prism2_send_mgmt(struct net_device *dev,
 #endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
 
 
-#ifndef PRISM2_NO_PROCFS_DEBUG
+#if !defined(PRISM2_NO_PROCFS_DEBUG) && defined(CONFIG_PROC_FS)
 static int ap_debug_proc_show(struct seq_file *m, void *v)
 {
 	struct ap_data *ap = PDE_DATA(file_inode(m->file));
@@ -81,8 +81,7 @@ static int ap_debug_proc_show(struct seq_file *m, void *v)
 	seq_printf(m, "tx_drop_nonassoc=%u\n", ap->tx_drop_nonassoc);
 	return 0;
 }
-#endif /* PRISM2_NO_PROCFS_DEBUG */
-
+#endif
 
 static void ap_sta_hash_add(struct ap_data *ap, struct sta_info *sta)
 {
@@ -990,7 +989,7 @@ static void prism2_send_mgmt(struct net_device *dev,
 }
 #endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
 
-
+#ifdef CONFIG_PROC_FS
 static int prism2_sta_proc_show(struct seq_file *m, void *v)
 {
 	struct sta_info *sta = m->private;
@@ -1059,6 +1058,7 @@ static int prism2_sta_proc_show(struct seq_file *m, void *v)
 
 	return 0;
 }
+#endif
 
 static void handle_add_proc_queue(struct work_struct *work)
 {
diff --git a/drivers/net/wireless/intersil/hostap/hostap_hw.c b/drivers/net/wireless/intersil/hostap/hostap_hw.c
index 2720aa39f530..ad1aa65fee7f 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_hw.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_hw.c
@@ -151,13 +151,6 @@ static int prism2_get_ram_size(local_info_t *local);
 #define HFA384X_MAGIC 0x8A32
 #endif
 
-
-static u16 hfa384x_read_reg(struct net_device *dev, u16 reg)
-{
-	return HFA384X_INW(reg);
-}
-
-
 static void hfa384x_read_regs(struct net_device *dev,
 			      struct hfa384x_regs *regs)
 {
@@ -2897,7 +2890,12 @@ static void hostap_tick_timer(struct timer_list *t)
 }
 
 
-#ifndef PRISM2_NO_PROCFS_DEBUG
+#if !defined(PRISM2_NO_PROCFS_DEBUG) && defined(CONFIG_PROC_FS)
+static u16 hfa384x_read_reg(struct net_device *dev, u16 reg)
+{
+	return HFA384X_INW(reg);
+}
+
 static int prism2_registers_proc_show(struct seq_file *m, void *v)
 {
 	local_info_t *local = m->private;
@@ -2951,8 +2949,7 @@ static int prism2_registers_proc_show(struct seq_file *m, void *v)
 
 	return 0;
 }
-#endif /* PRISM2_NO_PROCFS_DEBUG */
-
+#endif
 
 struct set_tim_data {
 	struct list_head list;
diff --git a/drivers/net/wireless/intersil/hostap/hostap_proc.c b/drivers/net/wireless/intersil/hostap/hostap_proc.c
index 5b33ccab9188..703d74cea3c2 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_proc.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_proc.c
@@ -11,8 +11,7 @@
 
 #define PROC_LIMIT (PAGE_SIZE - 80)
 
-
-#ifndef PRISM2_NO_PROCFS_DEBUG
+#if !defined(PRISM2_NO_PROCFS_DEBUG) && defined(CONFIG_PROC_FS)
 static int prism2_debug_proc_show(struct seq_file *m, void *v)
 {
 	local_info_t *local = m->private;
@@ -43,9 +42,9 @@ static int prism2_debug_proc_show(struct seq_file *m, void *v)
 
 	return 0;
 }
-#endif /* PRISM2_NO_PROCFS_DEBUG */
-
+#endif
 
+#ifdef CONFIG_PROC_FS
 static int prism2_stats_proc_show(struct seq_file *m, void *v)
 {
 	local_info_t *local = m->private;
@@ -82,6 +81,7 @@ static int prism2_stats_proc_show(struct seq_file *m, void *v)
 
 	return 0;
 }
+#endif
 
 static int prism2_wds_proc_show(struct seq_file *m, void *v)
 {
@@ -174,6 +174,7 @@ static const struct seq_operations prism2_bss_list_proc_seqops = {
 	.show	= prism2_bss_list_proc_show,
 };
 
+#ifdef CONFIG_PROC_FS
 static int prism2_crypt_proc_show(struct seq_file *m, void *v)
 {
 	local_info_t *local = m->private;
@@ -190,6 +191,7 @@ static int prism2_crypt_proc_show(struct seq_file *m, void *v)
 	}
 	return 0;
 }
+#endif
 
 static ssize_t prism2_pda_proc_read(struct file *file, char __user *buf,
 				    size_t count, loff_t *_pos)
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 18e819d964f1..998dfac0fcff 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -2,6 +2,7 @@
  * mac80211_hwsim - software simulator of 802.11 radio(s) for mac80211
  * Copyright (c) 2008, Jouni Malinen <j@w1.fi>
  * Copyright (c) 2011, Javier Lopez <jlopex@gmail.com>
+ * Copyright (c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -2517,6 +2518,123 @@ out_err:
 	nlmsg_free(mcast_skb);
 }
 
+static const struct ieee80211_sband_iftype_data he_capa_2ghz = {
+	/* TODO: should we support other types, e.g., P2P?*/
+	.types_mask = BIT(NL80211_IFTYPE_STATION) | BIT(NL80211_IFTYPE_AP),
+	.he_cap = {
+		.has_he = true,
+		.he_cap_elem = {
+			.mac_cap_info[0] =
+				IEEE80211_HE_MAC_CAP0_HTC_HE,
+			.mac_cap_info[1] =
+				IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US |
+				IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8,
+			.mac_cap_info[2] =
+				IEEE80211_HE_MAC_CAP2_BSR |
+				IEEE80211_HE_MAC_CAP2_MU_CASCADING |
+				IEEE80211_HE_MAC_CAP2_ACK_EN,
+			.mac_cap_info[3] =
+				IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU |
+				IEEE80211_HE_MAC_CAP3_OMI_CONTROL |
+				IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2,
+			.mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU,
+			.phy_cap_info[0] =
+				IEEE80211_HE_PHY_CAP0_DUAL_BAND,
+			.phy_cap_info[1] =
+				IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK |
+				IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A |
+				IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD |
+				IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS,
+			.phy_cap_info[2] =
+				IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US |
+				IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ |
+				IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ |
+				IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO |
+				IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO,
+
+			/* Leave all the other PHY capability bytes unset, as
+			 * DCM, beam forming, RU and PPE threshold information
+			 * are not supported
+			 */
+		},
+		.he_mcs_nss_supp = {
+			.rx_mcs_80 = cpu_to_le16(0xfffa),
+			.tx_mcs_80 = cpu_to_le16(0xfffa),
+			.rx_mcs_160 = cpu_to_le16(0xffff),
+			.tx_mcs_160 = cpu_to_le16(0xffff),
+			.rx_mcs_80p80 = cpu_to_le16(0xffff),
+			.tx_mcs_80p80 = cpu_to_le16(0xffff),
+		},
+	},
+};
+
+static const struct ieee80211_sband_iftype_data he_capa_5ghz = {
+	/* TODO: should we support other types, e.g., P2P?*/
+	.types_mask = BIT(NL80211_IFTYPE_STATION) | BIT(NL80211_IFTYPE_AP),
+	.he_cap = {
+		.has_he = true,
+		.he_cap_elem = {
+			.mac_cap_info[0] =
+				IEEE80211_HE_MAC_CAP0_HTC_HE,
+			.mac_cap_info[1] =
+				IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US |
+				IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8,
+			.mac_cap_info[2] =
+				IEEE80211_HE_MAC_CAP2_BSR |
+				IEEE80211_HE_MAC_CAP2_MU_CASCADING |
+				IEEE80211_HE_MAC_CAP2_ACK_EN,
+			.mac_cap_info[3] =
+				IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU |
+				IEEE80211_HE_MAC_CAP3_OMI_CONTROL |
+				IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2,
+			.mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU,
+			.phy_cap_info[0] =
+				IEEE80211_HE_PHY_CAP0_DUAL_BAND |
+				IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G |
+				IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G |
+				IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G,
+			.phy_cap_info[1] =
+				IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK |
+				IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A |
+				IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD |
+				IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS,
+			.phy_cap_info[2] =
+				IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US |
+				IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ |
+				IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ |
+				IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO |
+				IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO,
+
+			/* Leave all the other PHY capability bytes unset, as
+			 * DCM, beam forming, RU and PPE threshold information
+			 * are not supported
+			 */
+		},
+		.he_mcs_nss_supp = {
+			.rx_mcs_80 = cpu_to_le16(0xfffa),
+			.tx_mcs_80 = cpu_to_le16(0xfffa),
+			.rx_mcs_160 = cpu_to_le16(0xfffa),
+			.tx_mcs_160 = cpu_to_le16(0xfffa),
+			.rx_mcs_80p80 = cpu_to_le16(0xfffa),
+			.tx_mcs_80p80 = cpu_to_le16(0xfffa),
+		},
+	},
+};
+
+static void mac80211_hswim_he_capab(struct ieee80211_supported_band *sband)
+{
+	if (sband->band == NL80211_BAND_2GHZ)
+		sband->iftype_data =
+			(struct ieee80211_sband_iftype_data *)&he_capa_2ghz;
+	else if (sband->band == NL80211_BAND_5GHZ)
+		sband->iftype_data =
+			(struct ieee80211_sband_iftype_data *)&he_capa_5ghz;
+	else
+		return;
+
+	sband->n_iftype_data = 1;
+}
+
 static int mac80211_hwsim_new_radio(struct genl_info *info,
 				    struct hwsim_new_radio_params *param)
 {
@@ -2678,6 +2796,9 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 
 	for (band = NL80211_BAND_2GHZ; band < NUM_NL80211_BANDS; band++) {
 		struct ieee80211_supported_band *sband = &data->bands[band];
+
+		sband->band = band;
+
 		switch (band) {
 		case NL80211_BAND_2GHZ:
 			sband->channels = data->channels_2ghz;
@@ -2734,6 +2855,8 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 		sband->ht_cap.mcs.rx_mask[1] = 0xff;
 		sband->ht_cap.mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED;
 
+		mac80211_hswim_he_capab(sband);
+
 		hw->wiphy->bands[band] = sband;
 	}
 
diff --git a/drivers/net/wireless/marvell/libertas/cfg.c b/drivers/net/wireless/marvell/libertas/cfg.c
index f99031cfdf86..57edfada0665 100644
--- a/drivers/net/wireless/marvell/libertas/cfg.c
+++ b/drivers/net/wireless/marvell/libertas/cfg.c
@@ -1559,10 +1559,10 @@ static int lbs_cfg_get_station(struct wiphy *wiphy, struct net_device *dev,
 	int ret;
 	size_t i;
 
-	sinfo->filled |= BIT(NL80211_STA_INFO_TX_BYTES) |
-			 BIT(NL80211_STA_INFO_TX_PACKETS) |
-			 BIT(NL80211_STA_INFO_RX_BYTES) |
-			 BIT(NL80211_STA_INFO_RX_PACKETS);
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BYTES) |
+			 BIT_ULL(NL80211_STA_INFO_TX_PACKETS) |
+			 BIT_ULL(NL80211_STA_INFO_RX_BYTES) |
+			 BIT_ULL(NL80211_STA_INFO_RX_PACKETS);
 	sinfo->tx_bytes = priv->dev->stats.tx_bytes;
 	sinfo->tx_packets = priv->dev->stats.tx_packets;
 	sinfo->rx_bytes = priv->dev->stats.rx_bytes;
@@ -1572,14 +1572,14 @@ static int lbs_cfg_get_station(struct wiphy *wiphy, struct net_device *dev,
 	ret = lbs_get_rssi(priv, &signal, &noise);
 	if (ret == 0) {
 		sinfo->signal = signal;
-		sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 	}
 
 	/* Convert priv->cur_rate from hw_value to NL80211 value */
 	for (i = 0; i < ARRAY_SIZE(lbs_rates); i++) {
 		if (priv->cur_rate == lbs_rates[i].hw_value) {
 			sinfo->txrate.legacy = lbs_rates[i].bitrate;
-			sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 			break;
 		}
 	}
diff --git a/drivers/net/wireless/marvell/libertas/dev.h b/drivers/net/wireless/marvell/libertas/dev.h
index dd1ee1f0af48..469134930026 100644
--- a/drivers/net/wireless/marvell/libertas/dev.h
+++ b/drivers/net/wireless/marvell/libertas/dev.h
@@ -104,6 +104,7 @@ struct lbs_private {
 	u8 fw_ready;
 	u8 surpriseremoved;
 	u8 setup_fw_on_resume;
+	u8 power_up_on_resume;
 	int (*hw_host_to_card) (struct lbs_private *priv, u8 type, u8 *payload, u16 nb);
 	void (*reset_card) (struct lbs_private *priv);
 	int (*power_save) (struct lbs_private *priv);
diff --git a/drivers/net/wireless/marvell/libertas/if_sdio.c b/drivers/net/wireless/marvell/libertas/if_sdio.c
index 2300e796c6ab..43743c26c071 100644
--- a/drivers/net/wireless/marvell/libertas/if_sdio.c
+++ b/drivers/net/wireless/marvell/libertas/if_sdio.c
@@ -1290,15 +1290,23 @@ static void if_sdio_remove(struct sdio_func *func)
 static int if_sdio_suspend(struct device *dev)
 {
 	struct sdio_func *func = dev_to_sdio_func(dev);
-	int ret;
 	struct if_sdio_card *card = sdio_get_drvdata(func);
+	struct lbs_private *priv = card->priv;
+	int ret;
 
 	mmc_pm_flag_t flags = sdio_get_host_pm_caps(func);
+	priv->power_up_on_resume = false;
 
 	/* If we're powered off anyway, just let the mmc layer remove the
 	 * card. */
-	if (!lbs_iface_active(card->priv))
-		return -ENOSYS;
+	if (!lbs_iface_active(priv)) {
+		if (priv->fw_ready) {
+			priv->power_up_on_resume = true;
+			if_sdio_power_off(card);
+		}
+
+		return 0;
+	}
 
 	dev_info(dev, "%s: suspend: PM flags = 0x%x\n",
 		 sdio_func_id(func), flags);
@@ -1306,9 +1314,14 @@ static int if_sdio_suspend(struct device *dev)
 	/* If we aren't being asked to wake on anything, we should bail out
 	 * and let the SD stack power down the card.
 	 */
-	if (card->priv->wol_criteria == EHS_REMOVE_WAKEUP) {
+	if (priv->wol_criteria == EHS_REMOVE_WAKEUP) {
 		dev_info(dev, "Suspend without wake params -- powering down card\n");
-		return -ENOSYS;
+		if (priv->fw_ready) {
+			priv->power_up_on_resume = true;
+			if_sdio_power_off(card);
+		}
+
+		return 0;
 	}
 
 	if (!(flags & MMC_PM_KEEP_POWER)) {
@@ -1321,7 +1334,7 @@ static int if_sdio_suspend(struct device *dev)
 	if (ret)
 		return ret;
 
-	ret = lbs_suspend(card->priv);
+	ret = lbs_suspend(priv);
 	if (ret)
 		return ret;
 
@@ -1336,6 +1349,11 @@ static int if_sdio_resume(struct device *dev)
 
 	dev_info(dev, "%s: resume: we're back\n", sdio_func_id(func));
 
+	if (card->priv->power_up_on_resume) {
+		if_sdio_power_on(card);
+		wait_event(card->pwron_waitq, card->priv->fw_ready);
+	}
+
 	ret = lbs_resume(card->priv);
 
 	return ret;
diff --git a/drivers/net/wireless/marvell/libertas/if_usb.c b/drivers/net/wireless/marvell/libertas/if_usb.c
index ffea610f67e2..c67a8e7be310 100644
--- a/drivers/net/wireless/marvell/libertas/if_usb.c
+++ b/drivers/net/wireless/marvell/libertas/if_usb.c
@@ -614,6 +614,7 @@ static inline void process_cmdrequest(int recvlength, uint8_t *recvbuff,
 				      struct if_usb_card *cardp,
 				      struct lbs_private *priv)
 {
+	unsigned long flags;
 	u8 i;
 
 	if (recvlength > LBS_CMD_BUFFER_SIZE) {
@@ -623,9 +624,7 @@ static inline void process_cmdrequest(int recvlength, uint8_t *recvbuff,
 		return;
 	}
 
-	BUG_ON(!in_interrupt());
-
-	spin_lock(&priv->driver_lock);
+	spin_lock_irqsave(&priv->driver_lock, flags);
 
 	i = (priv->resp_idx == 0) ? 1 : 0;
 	BUG_ON(priv->resp_len[i]);
@@ -635,7 +634,7 @@ static inline void process_cmdrequest(int recvlength, uint8_t *recvbuff,
 	kfree_skb(skb);
 	lbs_notify_command_response(priv, i);
 
-	spin_unlock(&priv->driver_lock);
+	spin_unlock_irqrestore(&priv->driver_lock, flags);
 
 	lbs_deb_usbd(&cardp->udev->dev,
 		    "Wake up main thread to handle cmd response\n");
diff --git a/drivers/net/wireless/marvell/libertas_tf/if_usb.c b/drivers/net/wireless/marvell/libertas_tf/if_usb.c
index 5153922e7ce1..e92fc5001171 100644
--- a/drivers/net/wireless/marvell/libertas_tf/if_usb.c
+++ b/drivers/net/wireless/marvell/libertas_tf/if_usb.c
@@ -603,6 +603,8 @@ static inline void process_cmdrequest(int recvlength, uint8_t *recvbuff,
 				      struct if_usb_card *cardp,
 				      struct lbtf_private *priv)
 {
+	unsigned long flags;
+
 	if (recvlength > LBS_CMD_BUFFER_SIZE) {
 		lbtf_deb_usbd(&cardp->udev->dev,
 			     "The receive buffer is too large\n");
@@ -610,14 +612,12 @@ static inline void process_cmdrequest(int recvlength, uint8_t *recvbuff,
 		return;
 	}
 
-	BUG_ON(!in_interrupt());
-
-	spin_lock(&priv->driver_lock);
+	spin_lock_irqsave(&priv->driver_lock, flags);
 	memcpy(priv->cmd_resp_buff, recvbuff + MESSAGE_HEADER_LEN,
 	       recvlength - MESSAGE_HEADER_LEN);
 	kfree_skb(skb);
 	lbtf_cmd_response_rx(priv);
-	spin_unlock(&priv->driver_lock);
+	spin_unlock_irqrestore(&priv->driver_lock, flags);
 }
 
 /**
diff --git a/drivers/net/wireless/marvell/mwifiex/11n.c b/drivers/net/wireless/marvell/mwifiex/11n.c
index 5d75c971004b..e2addd8b878b 100644
--- a/drivers/net/wireless/marvell/mwifiex/11n.c
+++ b/drivers/net/wireless/marvell/mwifiex/11n.c
@@ -696,10 +696,11 @@ void mwifiex_11n_delba(struct mwifiex_private *priv, int tid)
 				"Send delba to tid=%d, %pM\n",
 				tid, rx_reor_tbl_ptr->ta);
 			mwifiex_send_delba(priv, tid, rx_reor_tbl_ptr->ta, 0);
-			goto exit;
+			spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock,
+					       flags);
+			return;
 		}
 	}
-exit:
 	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 }
 
diff --git a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
index 7ab44cd32a9d..8e63d14c1e1c 100644
--- a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
+++ b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
@@ -103,6 +103,8 @@ static int mwifiex_11n_dispatch_pkt(struct mwifiex_private *priv, void *payload)
  * There could be holes in the buffer, which are skipped by the function.
  * Since the buffer is linear, the function uses rotation to simulate
  * circular buffer.
+ *
+ * The caller must hold rx_reorder_tbl_lock spinlock.
  */
 static void
 mwifiex_11n_dispatch_pkt_until_start_win(struct mwifiex_private *priv,
@@ -111,25 +113,21 @@ mwifiex_11n_dispatch_pkt_until_start_win(struct mwifiex_private *priv,
 {
 	int pkt_to_send, i;
 	void *rx_tmp_ptr;
-	unsigned long flags;
 
 	pkt_to_send = (start_win > tbl->start_win) ?
 		      min((start_win - tbl->start_win), tbl->win_size) :
 		      tbl->win_size;
 
 	for (i = 0; i < pkt_to_send; ++i) {
-		spin_lock_irqsave(&priv->rx_pkt_lock, flags);
 		rx_tmp_ptr = NULL;
 		if (tbl->rx_reorder_ptr[i]) {
 			rx_tmp_ptr = tbl->rx_reorder_ptr[i];
 			tbl->rx_reorder_ptr[i] = NULL;
 		}
-		spin_unlock_irqrestore(&priv->rx_pkt_lock, flags);
 		if (rx_tmp_ptr)
 			mwifiex_11n_dispatch_pkt(priv, rx_tmp_ptr);
 	}
 
-	spin_lock_irqsave(&priv->rx_pkt_lock, flags);
 	/*
 	 * We don't have a circular buffer, hence use rotation to simulate
 	 * circular buffer
@@ -140,7 +138,6 @@ mwifiex_11n_dispatch_pkt_until_start_win(struct mwifiex_private *priv,
 	}
 
 	tbl->start_win = start_win;
-	spin_unlock_irqrestore(&priv->rx_pkt_lock, flags);
 }
 
 /*
@@ -150,6 +147,8 @@ mwifiex_11n_dispatch_pkt_until_start_win(struct mwifiex_private *priv,
  * The start window is adjusted automatically when a hole is located.
  * Since the buffer is linear, the function uses rotation to simulate
  * circular buffer.
+ *
+ * The caller must hold rx_reorder_tbl_lock spinlock.
  */
 static void
 mwifiex_11n_scan_and_dispatch(struct mwifiex_private *priv,
@@ -157,21 +156,15 @@ mwifiex_11n_scan_and_dispatch(struct mwifiex_private *priv,
 {
 	int i, j, xchg;
 	void *rx_tmp_ptr;
-	unsigned long flags;
 
 	for (i = 0; i < tbl->win_size; ++i) {
-		spin_lock_irqsave(&priv->rx_pkt_lock, flags);
-		if (!tbl->rx_reorder_ptr[i]) {
-			spin_unlock_irqrestore(&priv->rx_pkt_lock, flags);
+		if (!tbl->rx_reorder_ptr[i])
 			break;
-		}
 		rx_tmp_ptr = tbl->rx_reorder_ptr[i];
 		tbl->rx_reorder_ptr[i] = NULL;
-		spin_unlock_irqrestore(&priv->rx_pkt_lock, flags);
 		mwifiex_11n_dispatch_pkt(priv, rx_tmp_ptr);
 	}
 
-	spin_lock_irqsave(&priv->rx_pkt_lock, flags);
 	/*
 	 * We don't have a circular buffer, hence use rotation to simulate
 	 * circular buffer
@@ -184,7 +177,6 @@ mwifiex_11n_scan_and_dispatch(struct mwifiex_private *priv,
 		}
 	}
 	tbl->start_win = (tbl->start_win + i) & (MAX_TID_VALUE - 1);
-	spin_unlock_irqrestore(&priv->rx_pkt_lock, flags);
 }
 
 /*
@@ -192,6 +184,8 @@ mwifiex_11n_scan_and_dispatch(struct mwifiex_private *priv,
  *
  * The function stops the associated timer and dispatches all the
  * pending packets in the Rx reorder table before deletion.
+ *
+ * The caller must hold rx_reorder_tbl_lock spinlock.
  */
 static void
 mwifiex_del_rx_reorder_entry(struct mwifiex_private *priv,
@@ -217,11 +211,7 @@ mwifiex_del_rx_reorder_entry(struct mwifiex_private *priv,
 
 	del_timer_sync(&tbl->timer_context.timer);
 	tbl->timer_context.timer_is_set = false;
-
-	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 	list_del(&tbl->list);
-	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
-
 	kfree(tbl->rx_reorder_ptr);
 	kfree(tbl);
 
@@ -234,22 +224,17 @@ mwifiex_del_rx_reorder_entry(struct mwifiex_private *priv,
 /*
  * This function returns the pointer to an entry in Rx reordering
  * table which matches the given TA/TID pair.
+ *
+ * The caller must hold rx_reorder_tbl_lock spinlock.
  */
 struct mwifiex_rx_reorder_tbl *
 mwifiex_11n_get_rx_reorder_tbl(struct mwifiex_private *priv, int tid, u8 *ta)
 {
 	struct mwifiex_rx_reorder_tbl *tbl;
-	unsigned long flags;
 
-	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
-	list_for_each_entry(tbl, &priv->rx_reorder_tbl_ptr, list) {
-		if (!memcmp(tbl->ta, ta, ETH_ALEN) && tbl->tid == tid) {
-			spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock,
-					       flags);
+	list_for_each_entry(tbl, &priv->rx_reorder_tbl_ptr, list)
+		if (!memcmp(tbl->ta, ta, ETH_ALEN) && tbl->tid == tid)
 			return tbl;
-		}
-	}
-	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 
 	return NULL;
 }
@@ -266,14 +251,9 @@ void mwifiex_11n_del_rx_reorder_tbl_by_ta(struct mwifiex_private *priv, u8 *ta)
 		return;
 
 	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
-	list_for_each_entry_safe(tbl, tmp, &priv->rx_reorder_tbl_ptr, list) {
-		if (!memcmp(tbl->ta, ta, ETH_ALEN)) {
-			spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock,
-					       flags);
+	list_for_each_entry_safe(tbl, tmp, &priv->rx_reorder_tbl_ptr, list)
+		if (!memcmp(tbl->ta, ta, ETH_ALEN))
 			mwifiex_del_rx_reorder_entry(priv, tbl);
-			spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
-		}
-	}
 	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 
 	return;
@@ -282,24 +262,18 @@ void mwifiex_11n_del_rx_reorder_tbl_by_ta(struct mwifiex_private *priv, u8 *ta)
 /*
  * This function finds the last sequence number used in the packets
  * buffered in Rx reordering table.
+ *
+ * The caller must hold rx_reorder_tbl_lock spinlock.
  */
 static int
 mwifiex_11n_find_last_seq_num(struct reorder_tmr_cnxt *ctx)
 {
 	struct mwifiex_rx_reorder_tbl *rx_reorder_tbl_ptr = ctx->ptr;
-	struct mwifiex_private *priv = ctx->priv;
-	unsigned long flags;
 	int i;
 
-	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
-	for (i = rx_reorder_tbl_ptr->win_size - 1; i >= 0; --i) {
-		if (rx_reorder_tbl_ptr->rx_reorder_ptr[i]) {
-			spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock,
-					       flags);
+	for (i = rx_reorder_tbl_ptr->win_size - 1; i >= 0; --i)
+		if (rx_reorder_tbl_ptr->rx_reorder_ptr[i])
 			return i;
-		}
-	}
-	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 
 	return -1;
 }
@@ -317,17 +291,22 @@ mwifiex_flush_data(struct timer_list *t)
 	struct reorder_tmr_cnxt *ctx =
 		from_timer(ctx, t, timer);
 	int start_win, seq_num;
+	unsigned long flags;
 
 	ctx->timer_is_set = false;
+	spin_lock_irqsave(&ctx->priv->rx_reorder_tbl_lock, flags);
 	seq_num = mwifiex_11n_find_last_seq_num(ctx);
 
-	if (seq_num < 0)
+	if (seq_num < 0) {
+		spin_unlock_irqrestore(&ctx->priv->rx_reorder_tbl_lock, flags);
 		return;
+	}
 
 	mwifiex_dbg(ctx->priv->adapter, INFO, "info: flush data %d\n", seq_num);
 	start_win = (ctx->ptr->start_win + seq_num + 1) & (MAX_TID_VALUE - 1);
 	mwifiex_11n_dispatch_pkt_until_start_win(ctx->priv, ctx->ptr,
 						 start_win);
+	spin_unlock_irqrestore(&ctx->priv->rx_reorder_tbl_lock, flags);
 }
 
 /*
@@ -354,11 +333,14 @@ mwifiex_11n_create_rx_reorder_tbl(struct mwifiex_private *priv, u8 *ta,
 	 * If we get a TID, ta pair which is already present dispatch all the
 	 * the packets and move the window size until the ssn
 	 */
+	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 	tbl = mwifiex_11n_get_rx_reorder_tbl(priv, tid, ta);
 	if (tbl) {
 		mwifiex_11n_dispatch_pkt_until_start_win(priv, tbl, seq_num);
+		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 		return;
 	}
+	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 	/* if !tbl then create one */
 	new_node = kzalloc(sizeof(struct mwifiex_rx_reorder_tbl), GFP_KERNEL);
 	if (!new_node)
@@ -569,16 +551,20 @@ int mwifiex_11n_rx_reorder_pkt(struct mwifiex_private *priv,
 	int prev_start_win, start_win, end_win, win_size;
 	u16 pkt_index;
 	bool init_window_shift = false;
+	unsigned long flags;
 	int ret = 0;
 
+	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 	tbl = mwifiex_11n_get_rx_reorder_tbl(priv, tid, ta);
 	if (!tbl) {
+		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 		if (pkt_type != PKT_TYPE_BAR)
 			mwifiex_11n_dispatch_pkt(priv, payload);
 		return ret;
 	}
 
 	if ((pkt_type == PKT_TYPE_AMSDU) && !tbl->amsdu) {
+		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 		mwifiex_11n_dispatch_pkt(priv, payload);
 		return ret;
 	}
@@ -665,6 +651,8 @@ done:
 	if (!tbl->timer_context.timer_is_set ||
 	    prev_start_win != tbl->start_win)
 		mwifiex_11n_rxreorder_timer_restart(tbl);
+
+	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 	return ret;
 }
 
@@ -693,14 +681,18 @@ mwifiex_del_ba_tbl(struct mwifiex_private *priv, int tid, u8 *peer_mac,
 		    peer_mac, tid, initiator);
 
 	if (cleanup_rx_reorder_tbl) {
+		spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 		tbl = mwifiex_11n_get_rx_reorder_tbl(priv, tid,
 								 peer_mac);
 		if (!tbl) {
+			spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock,
+					       flags);
 			mwifiex_dbg(priv->adapter, EVENT,
 				    "event: TID, TA not found in table\n");
 			return;
 		}
 		mwifiex_del_rx_reorder_entry(priv, tbl);
+		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 	} else {
 		ptx_tbl = mwifiex_get_ba_tbl(priv, tid, peer_mac);
 		if (!ptx_tbl) {
@@ -734,6 +726,7 @@ int mwifiex_ret_11n_addba_resp(struct mwifiex_private *priv,
 	int tid, win_size;
 	struct mwifiex_rx_reorder_tbl *tbl;
 	uint16_t block_ack_param_set;
+	unsigned long flags;
 
 	block_ack_param_set = le16_to_cpu(add_ba_rsp->block_ack_param_set);
 
@@ -747,17 +740,20 @@ int mwifiex_ret_11n_addba_resp(struct mwifiex_private *priv,
 		mwifiex_dbg(priv->adapter, ERROR, "ADDBA RSP: failed %pM tid=%d)\n",
 			    add_ba_rsp->peer_mac_addr, tid);
 
+		spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 		tbl = mwifiex_11n_get_rx_reorder_tbl(priv, tid,
 						     add_ba_rsp->peer_mac_addr);
 		if (tbl)
 			mwifiex_del_rx_reorder_entry(priv, tbl);
 
+		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 		return 0;
 	}
 
 	win_size = (block_ack_param_set & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK)
 		    >> BLOCKACKPARAM_WINSIZE_POS;
 
+	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 	tbl = mwifiex_11n_get_rx_reorder_tbl(priv, tid,
 					     add_ba_rsp->peer_mac_addr);
 	if (tbl) {
@@ -768,6 +764,7 @@ int mwifiex_ret_11n_addba_resp(struct mwifiex_private *priv,
 		else
 			tbl->amsdu = false;
 	}
+	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 
 	mwifiex_dbg(priv->adapter, CMD,
 		    "cmd: ADDBA RSP: %pM tid=%d ssn=%d win_size=%d\n",
@@ -807,11 +804,8 @@ void mwifiex_11n_cleanup_reorder_tbl(struct mwifiex_private *priv)
 
 	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 	list_for_each_entry_safe(del_tbl_ptr, tmp_node,
-				 &priv->rx_reorder_tbl_ptr, list) {
-		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
+				 &priv->rx_reorder_tbl_ptr, list)
 		mwifiex_del_rx_reorder_entry(priv, del_tbl_ptr);
-		spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
-	}
 	INIT_LIST_HEAD(&priv->rx_reorder_tbl_ptr);
 	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 
@@ -935,6 +929,7 @@ void mwifiex_11n_rxba_sync_event(struct mwifiex_private *priv,
 	int tlv_buf_left = len;
 	int ret;
 	u8 *tmp;
+	unsigned long flags;
 
 	mwifiex_dbg_dump(priv->adapter, EVT_D, "RXBA_SYNC event:",
 			 event_buf, len);
@@ -954,14 +949,18 @@ void mwifiex_11n_rxba_sync_event(struct mwifiex_private *priv,
 			    tlv_rxba->mac, tlv_rxba->tid, tlv_seq_num,
 			    tlv_bitmap_len);
 
+		spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 		rx_reor_tbl_ptr =
 			mwifiex_11n_get_rx_reorder_tbl(priv, tlv_rxba->tid,
 						       tlv_rxba->mac);
 		if (!rx_reor_tbl_ptr) {
+			spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock,
+					       flags);
 			mwifiex_dbg(priv->adapter, ERROR,
 				    "Can not find rx_reorder_tbl!");
 			return;
 		}
+		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 
 		for (i = 0; i < tlv_bitmap_len; i++) {
 			for (j = 0 ; j < 8; j++) {
diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index 4b5ae9098504..adc88433faa8 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -1353,17 +1353,17 @@ mwifiex_dump_station_info(struct mwifiex_private *priv,
 {
 	u32 rate;
 
-	sinfo->filled = BIT(NL80211_STA_INFO_RX_BYTES) | BIT(NL80211_STA_INFO_TX_BYTES) |
-			BIT(NL80211_STA_INFO_RX_PACKETS) | BIT(NL80211_STA_INFO_TX_PACKETS) |
-			BIT(NL80211_STA_INFO_TX_BITRATE) |
-			BIT(NL80211_STA_INFO_SIGNAL) | BIT(NL80211_STA_INFO_SIGNAL_AVG);
+	sinfo->filled = BIT_ULL(NL80211_STA_INFO_RX_BYTES) | BIT_ULL(NL80211_STA_INFO_TX_BYTES) |
+			BIT_ULL(NL80211_STA_INFO_RX_PACKETS) | BIT_ULL(NL80211_STA_INFO_TX_PACKETS) |
+			BIT_ULL(NL80211_STA_INFO_TX_BITRATE) |
+			BIT_ULL(NL80211_STA_INFO_SIGNAL) | BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG);
 
 	if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_UAP) {
 		if (!node)
 			return -ENOENT;
 
-		sinfo->filled |= BIT(NL80211_STA_INFO_INACTIVE_TIME) |
-				BIT(NL80211_STA_INFO_TX_FAILED);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_INACTIVE_TIME) |
+				BIT_ULL(NL80211_STA_INFO_TX_FAILED);
 		sinfo->inactive_time =
 			jiffies_to_msecs(jiffies - node->stats.last_rx);
 
@@ -1413,7 +1413,7 @@ mwifiex_dump_station_info(struct mwifiex_private *priv,
 	sinfo->txrate.legacy = rate * 5;
 
 	if (priv->bss_mode == NL80211_IFTYPE_STATION) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_BSS_PARAM);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BSS_PARAM);
 		sinfo->bss_param.flags = 0;
 		if (priv->curr_bss_params.bss_descriptor.cap_info_bitmap &
 						WLAN_CAPABILITY_SHORT_PREAMBLE)
@@ -2322,7 +2322,8 @@ mwifiex_cfg80211_connect(struct wiphy *wiphy, struct net_device *dev,
 	if (priv->scan_block)
 		priv->scan_block = false;
 
-	if (adapter->surprise_removed || adapter->is_cmd_timedout) {
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags) ||
+	    test_bit(MWIFIEX_IS_CMD_TIMEDOUT, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "%s: Ignore connection.\t"
 			    "Card removed or FW in bad state\n",
diff --git a/drivers/net/wireless/marvell/mwifiex/cmdevt.c b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
index 9cfcdf6bec52..60db2b969e20 100644
--- a/drivers/net/wireless/marvell/mwifiex/cmdevt.c
+++ b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
@@ -372,7 +372,7 @@ static int mwifiex_dnld_sleep_confirm_cmd(struct mwifiex_adapter *adapter)
 		adapter->ps_state = PS_STATE_SLEEP_CFM;
 
 	if (!le16_to_cpu(sleep_cfm_buf->resp_ctrl) &&
-	    (adapter->is_hs_configured &&
+	    (test_bit(MWIFIEX_IS_HS_CONFIGURED, &adapter->work_flags) &&
 	     !adapter->sleep_period.period)) {
 		adapter->pm_wakeup_card_req = true;
 		mwifiex_hs_activated_event(mwifiex_get_priv
@@ -564,25 +564,26 @@ int mwifiex_send_cmd(struct mwifiex_private *priv, u16 cmd_no,
 		return -1;
 	}
 
-	if (adapter->is_suspended) {
+	if (test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "PREP_CMD: device in suspended state\n");
 		return -1;
 	}
 
-	if (adapter->hs_enabling && cmd_no != HostCmd_CMD_802_11_HS_CFG_ENH) {
+	if (test_bit(MWIFIEX_IS_HS_ENABLING, &adapter->work_flags) &&
+	    cmd_no != HostCmd_CMD_802_11_HS_CFG_ENH) {
 		mwifiex_dbg(adapter, ERROR,
 			    "PREP_CMD: host entering sleep state\n");
 		return -1;
 	}
 
-	if (adapter->surprise_removed) {
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "PREP_CMD: card is removed\n");
 		return -1;
 	}
 
-	if (adapter->is_cmd_timedout) {
+	if (test_bit(MWIFIEX_IS_CMD_TIMEDOUT, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "PREP_CMD: FW is in bad state\n");
 		return -1;
@@ -789,7 +790,8 @@ int mwifiex_exec_next_cmd(struct mwifiex_adapter *adapter)
 	if (priv && (host_cmd->command !=
 	     cpu_to_le16(HostCmd_CMD_802_11_HS_CFG_ENH))) {
 		if (adapter->hs_activated) {
-			adapter->is_hs_configured = false;
+			clear_bit(MWIFIEX_IS_HS_CONFIGURED,
+				  &adapter->work_flags);
 			mwifiex_hs_activated_event(priv, false);
 		}
 	}
@@ -825,7 +827,7 @@ int mwifiex_process_cmdresp(struct mwifiex_adapter *adapter)
 		return -1;
 	}
 
-	adapter->is_cmd_timedout = 0;
+	clear_bit(MWIFIEX_IS_CMD_TIMEDOUT, &adapter->work_flags);
 
 	resp = (struct host_cmd_ds_command *) adapter->curr_cmd->resp_skb->data;
 	if (adapter->curr_cmd->cmd_flag & CMD_F_HOSTCMD) {
@@ -927,7 +929,7 @@ mwifiex_cmd_timeout_func(struct timer_list *t)
 	struct mwifiex_adapter *adapter = from_timer(adapter, t, cmd_timer);
 	struct cmd_ctrl_node *cmd_node;
 
-	adapter->is_cmd_timedout = 1;
+	set_bit(MWIFIEX_IS_CMD_TIMEDOUT, &adapter->work_flags);
 	if (!adapter->curr_cmd) {
 		mwifiex_dbg(adapter, ERROR,
 			    "cmd: empty curr_cmd\n");
@@ -953,7 +955,8 @@ mwifiex_cmd_timeout_func(struct timer_list *t)
 
 		mwifiex_dbg(adapter, MSG,
 			    "is_cmd_timedout = %d\n",
-			    adapter->is_cmd_timedout);
+			    test_bit(MWIFIEX_IS_CMD_TIMEDOUT,
+				     &adapter->work_flags));
 		mwifiex_dbg(adapter, MSG,
 			    "num_tx_timeout = %d\n",
 			    adapter->dbg.num_tx_timeout);
@@ -1135,7 +1138,8 @@ void
 mwifiex_hs_activated_event(struct mwifiex_private *priv, u8 activated)
 {
 	if (activated) {
-		if (priv->adapter->is_hs_configured) {
+		if (test_bit(MWIFIEX_IS_HS_CONFIGURED,
+			     &priv->adapter->work_flags)) {
 			priv->adapter->hs_activated = true;
 			mwifiex_update_rxreor_flags(priv->adapter,
 						    RXREOR_FORCE_NO_DROP);
@@ -1186,11 +1190,11 @@ int mwifiex_ret_802_11_hs_cfg(struct mwifiex_private *priv,
 			    phs_cfg->params.hs_config.gap);
 	}
 	if (conditions != HS_CFG_CANCEL) {
-		adapter->is_hs_configured = true;
+		set_bit(MWIFIEX_IS_HS_CONFIGURED, &adapter->work_flags);
 		if (adapter->iface_type == MWIFIEX_USB)
 			mwifiex_hs_activated_event(priv, true);
 	} else {
-		adapter->is_hs_configured = false;
+		clear_bit(MWIFIEX_IS_HS_CONFIGURED, &adapter->work_flags);
 		if (adapter->hs_activated)
 			mwifiex_hs_activated_event(priv, false);
 	}
@@ -1212,8 +1216,8 @@ mwifiex_process_hs_config(struct mwifiex_adapter *adapter)
 
 	adapter->if_ops.wakeup(adapter);
 	adapter->hs_activated = false;
-	adapter->is_hs_configured = false;
-	adapter->is_suspended = false;
+	clear_bit(MWIFIEX_IS_HS_CONFIGURED, &adapter->work_flags);
+	clear_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
 	mwifiex_hs_activated_event(mwifiex_get_priv(adapter,
 						    MWIFIEX_BSS_ROLE_ANY),
 				   false);
@@ -1273,7 +1277,7 @@ mwifiex_process_sleep_confirm_resp(struct mwifiex_adapter *adapter,
 		return;
 	}
 	adapter->pm_wakeup_card_req = true;
-	if (adapter->is_hs_configured)
+	if (test_bit(MWIFIEX_IS_HS_CONFIGURED, &adapter->work_flags))
 		mwifiex_hs_activated_event(mwifiex_get_priv
 						(adapter, MWIFIEX_BSS_ROLE_ANY),
 					   true);
diff --git a/drivers/net/wireless/marvell/mwifiex/debugfs.c b/drivers/net/wireless/marvell/mwifiex/debugfs.c
index 07453932f703..cce70252fd96 100644
--- a/drivers/net/wireless/marvell/mwifiex/debugfs.c
+++ b/drivers/net/wireless/marvell/mwifiex/debugfs.c
@@ -813,7 +813,7 @@ mwifiex_hscfg_write(struct file *file, const char __user *ubuf,
 			      MWIFIEX_SYNC_CMD, &hscfg);
 
 	mwifiex_enable_hs(priv->adapter);
-	priv->adapter->hs_enabling = false;
+	clear_bit(MWIFIEX_IS_HS_ENABLING, &priv->adapter->work_flags);
 	ret = count;
 done:
 	kfree(buf);
diff --git a/drivers/net/wireless/marvell/mwifiex/ie.c b/drivers/net/wireless/marvell/mwifiex/ie.c
index b10baacb51c9..75cbd609d606 100644
--- a/drivers/net/wireless/marvell/mwifiex/ie.c
+++ b/drivers/net/wireless/marvell/mwifiex/ie.c
@@ -355,8 +355,14 @@ static int mwifiex_uap_parse_tail_ies(struct mwifiex_private *priv,
 		case WLAN_EID_HT_OPERATION:
 		case WLAN_EID_VHT_CAPABILITY:
 		case WLAN_EID_VHT_OPERATION:
-		case WLAN_EID_VENDOR_SPECIFIC:
 			break;
+		case WLAN_EID_VENDOR_SPECIFIC:
+			/* Skip only Microsoft WMM IE */
+			if (cfg80211_find_vendor_ie(WLAN_OUI_MICROSOFT,
+						    WLAN_OUI_TYPE_MICROSOFT_WMM,
+						    (const u8 *)hdr,
+						    hdr->len + sizeof(struct ieee_types_header)))
+				break;
 		default:
 			memcpy(gen_ie->ie_buffer + ie_len, hdr,
 			       hdr->len + sizeof(struct ieee_types_header));
diff --git a/drivers/net/wireless/marvell/mwifiex/init.c b/drivers/net/wireless/marvell/mwifiex/init.c
index d239e9248c05..673e89dff0b5 100644
--- a/drivers/net/wireless/marvell/mwifiex/init.c
+++ b/drivers/net/wireless/marvell/mwifiex/init.c
@@ -233,7 +233,7 @@ static void mwifiex_init_adapter(struct mwifiex_adapter *adapter)
 	adapter->event_received = false;
 	adapter->data_received = false;
 
-	adapter->surprise_removed = false;
+	clear_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags);
 
 	adapter->hw_status = MWIFIEX_HW_STATUS_INITIALIZING;
 
@@ -270,7 +270,7 @@ static void mwifiex_init_adapter(struct mwifiex_adapter *adapter)
 
 	adapter->curr_tx_buf_size = MWIFIEX_TX_DATA_BUF_SIZE_2K;
 
-	adapter->is_hs_configured = false;
+	clear_bit(MWIFIEX_IS_HS_CONFIGURED, &adapter->work_flags);
 	adapter->hs_cfg.conditions = cpu_to_le32(HS_CFG_COND_DEF);
 	adapter->hs_cfg.gpio = HS_CFG_GPIO_DEF;
 	adapter->hs_cfg.gap = HS_CFG_GAP_DEF;
@@ -439,7 +439,6 @@ int mwifiex_init_lock_list(struct mwifiex_adapter *adapter)
 	for (i = 0; i < adapter->priv_num; i++) {
 		if (adapter->priv[i]) {
 			priv = adapter->priv[i];
-			spin_lock_init(&priv->rx_pkt_lock);
 			spin_lock_init(&priv->wmm.ra_list_spinlock);
 			spin_lock_init(&priv->curr_bcn_buf_lock);
 			spin_lock_init(&priv->sta_list_spinlock);
diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c
index 510f6b8e717d..20cee5c397fb 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.c
+++ b/drivers/net/wireless/marvell/mwifiex/main.c
@@ -404,7 +404,8 @@ process_start:
 		    !skb_queue_empty(&adapter->tx_data_q)) {
 			mwifiex_process_tx_queue(adapter);
 			if (adapter->hs_activated) {
-				adapter->is_hs_configured = false;
+				clear_bit(MWIFIEX_IS_HS_CONFIGURED,
+					  &adapter->work_flags);
 				mwifiex_hs_activated_event
 					(mwifiex_get_priv
 					(adapter, MWIFIEX_BSS_ROLE_ANY),
@@ -420,7 +421,8 @@ process_start:
 			(mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_STA))) {
 			mwifiex_process_bypass_tx(adapter);
 			if (adapter->hs_activated) {
-				adapter->is_hs_configured = false;
+				clear_bit(MWIFIEX_IS_HS_CONFIGURED,
+					  &adapter->work_flags);
 				mwifiex_hs_activated_event
 					(mwifiex_get_priv
 					 (adapter, MWIFIEX_BSS_ROLE_ANY),
@@ -435,7 +437,8 @@ process_start:
 			(mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_STA))) {
 			mwifiex_wmm_process_tx(adapter);
 			if (adapter->hs_activated) {
-				adapter->is_hs_configured = false;
+				clear_bit(MWIFIEX_IS_HS_CONFIGURED,
+					  &adapter->work_flags);
 				mwifiex_hs_activated_event
 					(mwifiex_get_priv
 					 (adapter, MWIFIEX_BSS_ROLE_ANY),
@@ -647,7 +650,7 @@ err_dnld_fw:
 	if (adapter->if_ops.unregister_dev)
 		adapter->if_ops.unregister_dev(adapter);
 
-	adapter->surprise_removed = true;
+	set_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags);
 	mwifiex_terminate_workqueue(adapter);
 
 	if (adapter->hw_status == MWIFIEX_HW_STATUS_READY) {
@@ -870,7 +873,7 @@ mwifiex_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		    "data: %lu BSS(%d-%d): Data <= kernel\n",
 		    jiffies, priv->bss_type, priv->bss_num);
 
-	if (priv->adapter->surprise_removed) {
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &priv->adapter->work_flags)) {
 		kfree_skb(skb);
 		priv->stats.tx_dropped++;
 		return 0;
@@ -1279,7 +1282,8 @@ static struct net_device_stats *mwifiex_get_stats(struct net_device *dev)
 
 static u16
 mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb,
-				void *accel_priv, select_queue_fallback_t fallback)
+				struct net_device *sb_dev,
+				select_queue_fallback_t fallback)
 {
 	skb->priority = cfg80211_classify8021d(skb, NULL);
 	return mwifiex_1d_to_wmm_queue[skb->priority];
@@ -1371,7 +1375,7 @@ static void mwifiex_rx_work_queue(struct work_struct *work)
 	struct mwifiex_adapter *adapter =
 		container_of(work, struct mwifiex_adapter, rx_work);
 
-	if (adapter->surprise_removed)
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags))
 		return;
 	mwifiex_process_rx(adapter);
 }
@@ -1387,7 +1391,7 @@ static void mwifiex_main_work_queue(struct work_struct *work)
 	struct mwifiex_adapter *adapter =
 		container_of(work, struct mwifiex_adapter, main_work);
 
-	if (adapter->surprise_removed)
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags))
 		return;
 	mwifiex_main_process(adapter);
 }
@@ -1404,7 +1408,7 @@ static void mwifiex_uninit_sw(struct mwifiex_adapter *adapter)
 	if (adapter->if_ops.disable_int)
 		adapter->if_ops.disable_int(adapter);
 
-	adapter->surprise_removed = true;
+	set_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags);
 	mwifiex_terminate_workqueue(adapter);
 	adapter->int_status = 0;
 
@@ -1492,11 +1496,11 @@ mwifiex_reinit_sw(struct mwifiex_adapter *adapter)
 		adapter->if_ops.up_dev(adapter);
 
 	adapter->hw_status = MWIFIEX_HW_STATUS_INITIALIZING;
-	adapter->surprise_removed = false;
+	clear_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags);
 	init_waitqueue_head(&adapter->init_wait_q);
-	adapter->is_suspended = false;
+	clear_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
 	adapter->hs_activated = false;
-	adapter->is_cmd_timedout = 0;
+	clear_bit(MWIFIEX_IS_CMD_TIMEDOUT, &adapter->work_flags);
 	init_waitqueue_head(&adapter->hs_activate_wait_q);
 	init_waitqueue_head(&adapter->cmd_wait_q.wait);
 	adapter->cmd_wait_q.status = 0;
@@ -1551,7 +1555,7 @@ err_init_fw:
 		adapter->if_ops.unregister_dev(adapter);
 
 err_kmalloc:
-	adapter->surprise_removed = true;
+	set_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags);
 	mwifiex_terminate_workqueue(adapter);
 	if (adapter->hw_status == MWIFIEX_HW_STATUS_READY) {
 		mwifiex_dbg(adapter, ERROR,
@@ -1648,9 +1652,9 @@ mwifiex_add_card(void *card, struct completion *fw_done,
 	adapter->fw_done = fw_done;
 
 	adapter->hw_status = MWIFIEX_HW_STATUS_INITIALIZING;
-	adapter->surprise_removed = false;
+	clear_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags);
 	init_waitqueue_head(&adapter->init_wait_q);
-	adapter->is_suspended = false;
+	clear_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
 	adapter->hs_activated = false;
 	init_waitqueue_head(&adapter->hs_activate_wait_q);
 	init_waitqueue_head(&adapter->cmd_wait_q.wait);
@@ -1698,7 +1702,7 @@ err_init_fw:
 	if (adapter->if_ops.unregister_dev)
 		adapter->if_ops.unregister_dev(adapter);
 err_registerdev:
-	adapter->surprise_removed = true;
+	set_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags);
 	mwifiex_terminate_workqueue(adapter);
 	if (adapter->hw_status == MWIFIEX_HW_STATUS_READY) {
 		pr_debug("info: %s: shutdown mwifiex\n", __func__);
diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
index 69ac0a22c28c..b025ba164412 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.h
+++ b/drivers/net/wireless/marvell/mwifiex/main.h
@@ -517,6 +517,14 @@ enum mwifiex_iface_work_flags {
 	MWIFIEX_IFACE_WORK_CARD_RESET,
 };
 
+enum mwifiex_adapter_work_flags {
+	MWIFIEX_SURPRISE_REMOVED,
+	MWIFIEX_IS_CMD_TIMEDOUT,
+	MWIFIEX_IS_SUSPENDED,
+	MWIFIEX_IS_HS_CONFIGURED,
+	MWIFIEX_IS_HS_ENABLING,
+};
+
 struct mwifiex_band_config {
 	u8 chan_band:2;
 	u8 chan_width:2;
@@ -616,9 +624,6 @@ struct mwifiex_private {
 	struct list_head rx_reorder_tbl_ptr;
 	/* spin lock for rx_reorder_tbl_ptr queue */
 	spinlock_t rx_reorder_tbl_lock;
-	/* spin lock for Rx packets */
-	spinlock_t rx_pkt_lock;
-
 #define MWIFIEX_ASSOC_RSP_BUF_SIZE  500
 	u8 assoc_rsp_buf[MWIFIEX_ASSOC_RSP_BUF_SIZE];
 	u32 assoc_rsp_size;
@@ -875,7 +880,7 @@ struct mwifiex_adapter {
 	struct device *dev;
 	struct wiphy *wiphy;
 	u8 perm_addr[ETH_ALEN];
-	bool surprise_removed;
+	unsigned long work_flags;
 	u32 fw_release_number;
 	u8 intf_hdr_len;
 	u16 init_wait_q_woken;
@@ -929,7 +934,6 @@ struct mwifiex_adapter {
 	struct cmd_ctrl_node *curr_cmd;
 	/* spin lock for command */
 	spinlock_t mwifiex_cmd_lock;
-	u8 is_cmd_timedout;
 	u16 last_init_cmd;
 	struct timer_list cmd_timer;
 	struct list_head cmd_free_q;
@@ -979,13 +983,10 @@ struct mwifiex_adapter {
 	u16 pps_uapsd_mode;
 	u32 pm_wakeup_fw_try;
 	struct timer_list wakeup_timer;
-	u8 is_hs_configured;
 	struct mwifiex_hs_config_param hs_cfg;
 	u8 hs_activated;
 	u16 hs_activate_wait_q_woken;
 	wait_queue_head_t hs_activate_wait_q;
-	bool is_suspended;
-	bool hs_enabling;
 	u8 event_body[MAX_EVENT_SIZE];
 	u32 hw_dot_11n_dev_cap;
 	u8 hw_dev_mcs_support;
diff --git a/drivers/net/wireless/marvell/mwifiex/pcie.c b/drivers/net/wireless/marvell/mwifiex/pcie.c
index 0c42b7296ddd..3fe81b2a929a 100644
--- a/drivers/net/wireless/marvell/mwifiex/pcie.c
+++ b/drivers/net/wireless/marvell/mwifiex/pcie.c
@@ -170,7 +170,7 @@ static int mwifiex_pcie_suspend(struct device *dev)
 	if (!mwifiex_enable_hs(adapter)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "cmd: failed to suspend\n");
-		adapter->hs_enabling = false;
+		clear_bit(MWIFIEX_IS_HS_ENABLING, &adapter->work_flags);
 		mwifiex_disable_wake(adapter);
 		return -EFAULT;
 	}
@@ -178,8 +178,8 @@ static int mwifiex_pcie_suspend(struct device *dev)
 	flush_workqueue(adapter->workqueue);
 
 	/* Indicate device suspended */
-	adapter->is_suspended = true;
-	adapter->hs_enabling = false;
+	set_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
+	clear_bit(MWIFIEX_IS_HS_ENABLING, &adapter->work_flags);
 
 	return 0;
 }
@@ -207,13 +207,13 @@ static int mwifiex_pcie_resume(struct device *dev)
 
 	adapter = card->adapter;
 
-	if (!adapter->is_suspended) {
+	if (!test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, WARN,
 			    "Device already resumed\n");
 		return 0;
 	}
 
-	adapter->is_suspended = false;
+	clear_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
 
 	mwifiex_cancel_hs(mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_STA),
 			  MWIFIEX_ASYNC_CMD);
@@ -2430,7 +2430,7 @@ static irqreturn_t mwifiex_pcie_interrupt(int irq, void *context)
 	}
 	adapter = card->adapter;
 
-	if (adapter->surprise_removed)
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags))
 		goto exit;
 
 	if (card->msix_enable)
diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c
index 895b806cdb03..8e483b0bc3b1 100644
--- a/drivers/net/wireless/marvell/mwifiex/scan.c
+++ b/drivers/net/wireless/marvell/mwifiex/scan.c
@@ -1495,7 +1495,8 @@ int mwifiex_scan_networks(struct mwifiex_private *priv,
 		return -EBUSY;
 	}
 
-	if (adapter->surprise_removed || adapter->is_cmd_timedout) {
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags) ||
+	    test_bit(MWIFIEX_IS_CMD_TIMEDOUT, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "Ignore scan. Card removed or firmware in bad state\n");
 		return -EFAULT;
diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c
index dfdcbc4f141a..d49fbd58afa7 100644
--- a/drivers/net/wireless/marvell/mwifiex/sdio.c
+++ b/drivers/net/wireless/marvell/mwifiex/sdio.c
@@ -181,13 +181,13 @@ static int mwifiex_sdio_resume(struct device *dev)
 
 	adapter = card->adapter;
 
-	if (!adapter->is_suspended) {
+	if (test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, WARN,
 			    "device already resumed\n");
 		return 0;
 	}
 
-	adapter->is_suspended = false;
+	clear_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
 
 	/* Disable Host Sleep */
 	mwifiex_cancel_hs(mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_STA),
@@ -260,7 +260,7 @@ mwifiex_write_data_sync(struct mwifiex_adapter *adapter,
 				MWIFIEX_SDIO_BLOCK_SIZE) : pkt_len;
 	u32 ioport = (port & MWIFIEX_SDIO_IO_PORT_MASK);
 
-	if (adapter->is_suspended) {
+	if (test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "%s: not allowed while suspended\n", __func__);
 		return -1;
@@ -450,7 +450,7 @@ static int mwifiex_sdio_suspend(struct device *dev)
 	if (!mwifiex_enable_hs(adapter)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "cmd: failed to suspend\n");
-		adapter->hs_enabling = false;
+		clear_bit(MWIFIEX_IS_HS_ENABLING, &adapter->work_flags);
 		mwifiex_disable_wake(adapter);
 		return -EFAULT;
 	}
@@ -460,8 +460,8 @@ static int mwifiex_sdio_suspend(struct device *dev)
 	ret = sdio_set_host_pm_flags(func, MMC_PM_KEEP_POWER);
 
 	/* Indicate device suspended */
-	adapter->is_suspended = true;
-	adapter->hs_enabling = false;
+	set_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
+	clear_bit(MWIFIEX_IS_HS_ENABLING, &adapter->work_flags);
 
 	return ret;
 }
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_event.c b/drivers/net/wireless/marvell/mwifiex/sta_event.c
index 03a6492662ca..a327fc5b36e3 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_event.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_event.c
@@ -224,7 +224,8 @@ void mwifiex_reset_connect_state(struct mwifiex_private *priv, u16 reason_code,
 	adapter->tx_lock_flag = false;
 	adapter->pps_uapsd_mode = false;
 
-	if (adapter->is_cmd_timedout && adapter->curr_cmd)
+	if (test_bit(MWIFIEX_IS_CMD_TIMEDOUT, &adapter->work_flags) &&
+	    adapter->curr_cmd)
 		return;
 	priv->media_connected = false;
 	mwifiex_dbg(adapter, MSG,
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
index 5414b755cf82..b454b5f85503 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
@@ -419,7 +419,8 @@ int mwifiex_set_hs_params(struct mwifiex_private *priv, u16 action,
 		}
 		if (hs_cfg->is_invoke_hostcmd) {
 			if (hs_cfg->conditions == HS_CFG_CANCEL) {
-				if (!adapter->is_hs_configured)
+				if (!test_bit(MWIFIEX_IS_HS_CONFIGURED,
+					      &adapter->work_flags))
 					/* Already cancelled */
 					break;
 				/* Save previous condition */
@@ -535,7 +536,7 @@ int mwifiex_enable_hs(struct mwifiex_adapter *adapter)
 	memset(&hscfg, 0, sizeof(hscfg));
 	hscfg.is_invoke_hostcmd = true;
 
-	adapter->hs_enabling = true;
+	set_bit(MWIFIEX_IS_HS_ENABLING, &adapter->work_flags);
 	mwifiex_cancel_all_pending_cmd(adapter);
 
 	if (mwifiex_set_hs_params(mwifiex_get_priv(adapter,
@@ -601,7 +602,8 @@ int mwifiex_get_bss_info(struct mwifiex_private *priv,
 	else
 		info->wep_status = false;
 
-	info->is_hs_configured = adapter->is_hs_configured;
+	info->is_hs_configured = test_bit(MWIFIEX_IS_HS_CONFIGURED,
+					  &adapter->work_flags);
 	info->is_deep_sleep = adapter->is_deep_sleep;
 
 	return 0;
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_tx.c b/drivers/net/wireless/marvell/mwifiex/sta_tx.c
index 620f8650a742..37c24b95e642 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_tx.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_tx.c
@@ -143,7 +143,7 @@ int mwifiex_send_null_packet(struct mwifiex_private *priv, u8 flags)
 	int ret;
 	struct mwifiex_txinfo *tx_info = NULL;
 
-	if (adapter->surprise_removed)
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags))
 		return -1;
 
 	if (!priv->media_connected)
diff --git a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
index 1e6a62c69ac5..a83c5afc256a 100644
--- a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
+++ b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
@@ -289,32 +289,6 @@ int mwifiex_uap_recv_packet(struct mwifiex_private *priv,
 		src_node->stats.rx_packets++;
 	}
 
-	skb->dev = priv->netdev;
-	skb->protocol = eth_type_trans(skb, priv->netdev);
-	skb->ip_summed = CHECKSUM_NONE;
-
-	/* This is required only in case of 11n and USB/PCIE as we alloc
-	 * a buffer of 4K only if its 11N (to be able to receive 4K
-	 * AMSDU packets). In case of SD we allocate buffers based
-	 * on the size of packet and hence this is not needed.
-	 *
-	 * Modifying the truesize here as our allocation for each
-	 * skb is 4K but we only receive 2K packets and this cause
-	 * the kernel to start dropping packets in case where
-	 * application has allocated buffer based on 2K size i.e.
-	 * if there a 64K packet received (in IP fragments and
-	 * application allocates 64K to receive this packet but
-	 * this packet would almost double up because we allocate
-	 * each 1.5K fragment in 4K and pass it up. As soon as the
-	 * 64K limit hits kernel will start to drop rest of the
-	 * fragments. Currently we fail the Filesndl-ht.scr script
-	 * for UDP, hence this fix
-	 */
-	if ((adapter->iface_type == MWIFIEX_USB ||
-	     adapter->iface_type == MWIFIEX_PCIE) &&
-	    (skb->truesize > MWIFIEX_RX_DATA_BUF_SIZE))
-		skb->truesize += (skb->len - MWIFIEX_RX_DATA_BUF_SIZE);
-
 	if (is_multicast_ether_addr(p_ethhdr->h_dest) ||
 	    mwifiex_get_sta_entry(priv, p_ethhdr->h_dest)) {
 		if (skb_headroom(skb) < MWIFIEX_MIN_DATA_HEADER_LEN)
@@ -350,6 +324,32 @@ int mwifiex_uap_recv_packet(struct mwifiex_private *priv,
 			return 0;
 	}
 
+	skb->dev = priv->netdev;
+	skb->protocol = eth_type_trans(skb, priv->netdev);
+	skb->ip_summed = CHECKSUM_NONE;
+
+	/* This is required only in case of 11n and USB/PCIE as we alloc
+	 * a buffer of 4K only if its 11N (to be able to receive 4K
+	 * AMSDU packets). In case of SD we allocate buffers based
+	 * on the size of packet and hence this is not needed.
+	 *
+	 * Modifying the truesize here as our allocation for each
+	 * skb is 4K but we only receive 2K packets and this cause
+	 * the kernel to start dropping packets in case where
+	 * application has allocated buffer based on 2K size i.e.
+	 * if there a 64K packet received (in IP fragments and
+	 * application allocates 64K to receive this packet but
+	 * this packet would almost double up because we allocate
+	 * each 1.5K fragment in 4K and pass it up. As soon as the
+	 * 64K limit hits kernel will start to drop rest of the
+	 * fragments. Currently we fail the Filesndl-ht.scr script
+	 * for UDP, hence this fix
+	 */
+	if ((adapter->iface_type == MWIFIEX_USB ||
+	     adapter->iface_type == MWIFIEX_PCIE) &&
+	    skb->truesize > MWIFIEX_RX_DATA_BUF_SIZE)
+		skb->truesize += (skb->len - MWIFIEX_RX_DATA_BUF_SIZE);
+
 	/* Forward multicast/broadcast packet to upper layer*/
 	if (in_interrupt())
 		netif_rx(skb);
@@ -421,12 +421,15 @@ int mwifiex_process_uap_rx_packet(struct mwifiex_private *priv,
 		spin_unlock_irqrestore(&priv->sta_list_spinlock, flags);
 	}
 
+	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 	if (!priv->ap_11n_enabled ||
 	    (!mwifiex_11n_get_rx_reorder_tbl(priv, uap_rx_pd->priority, ta) &&
 	    (le16_to_cpu(uap_rx_pd->rx_pkt_type) != PKT_TYPE_AMSDU))) {
 		ret = mwifiex_handle_uap_rx_forward(priv, skb);
+		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 		return ret;
 	}
+	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 
 	/* Reorder and send to kernel */
 	pkt_type = (u8)le16_to_cpu(uap_rx_pd->rx_pkt_type);
diff --git a/drivers/net/wireless/marvell/mwifiex/usb.c b/drivers/net/wireless/marvell/mwifiex/usb.c
index 88f4c89f89ba..433c6a16870b 100644
--- a/drivers/net/wireless/marvell/mwifiex/usb.c
+++ b/drivers/net/wireless/marvell/mwifiex/usb.c
@@ -181,7 +181,8 @@ static void mwifiex_usb_rx_complete(struct urb *urb)
 		atomic_dec(&card->rx_data_urb_pending);
 
 	if (recv_length) {
-		if (urb->status || (adapter->surprise_removed)) {
+		if (urb->status ||
+		    test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags)) {
 			mwifiex_dbg(adapter, ERROR,
 				    "URB status is failed: %d\n", urb->status);
 			/* Do not free skb in case of command ep */
@@ -218,10 +219,10 @@ static void mwifiex_usb_rx_complete(struct urb *urb)
 				dev_kfree_skb_any(skb);
 		}
 	} else if (urb->status) {
-		if (!adapter->is_suspended) {
+		if (!test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) {
 			mwifiex_dbg(adapter, FATAL,
 				    "Card is removed: %d\n", urb->status);
-			adapter->surprise_removed = true;
+			set_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags);
 		}
 		dev_kfree_skb_any(skb);
 		return;
@@ -529,7 +530,7 @@ static int mwifiex_usb_suspend(struct usb_interface *intf, pm_message_t message)
 		return 0;
 	}
 
-	if (unlikely(adapter->is_suspended))
+	if (unlikely(test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)))
 		mwifiex_dbg(adapter, WARN,
 			    "Device already suspended\n");
 
@@ -537,19 +538,19 @@ static int mwifiex_usb_suspend(struct usb_interface *intf, pm_message_t message)
 	if (!mwifiex_enable_hs(adapter)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "cmd: failed to suspend\n");
-		adapter->hs_enabling = false;
+		clear_bit(MWIFIEX_IS_HS_ENABLING, &adapter->work_flags);
 		return -EFAULT;
 	}
 
 
-	/* 'is_suspended' flag indicates device is suspended.
+	/* 'MWIFIEX_IS_SUSPENDED' bit indicates device is suspended.
 	 * It must be set here before the usb_kill_urb() calls. Reason
 	 * is in the complete handlers, urb->status(= -ENOENT) and
 	 * this flag is used in combination to distinguish between a
 	 * 'suspended' state and a 'disconnect' one.
 	 */
-	adapter->is_suspended = true;
-	adapter->hs_enabling = false;
+	set_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
+	clear_bit(MWIFIEX_IS_HS_ENABLING, &adapter->work_flags);
 
 	if (atomic_read(&card->rx_cmd_urb_pending) && card->rx_cmd.urb)
 		usb_kill_urb(card->rx_cmd.urb);
@@ -593,7 +594,7 @@ static int mwifiex_usb_resume(struct usb_interface *intf)
 	}
 	adapter = card->adapter;
 
-	if (unlikely(!adapter->is_suspended)) {
+	if (unlikely(!test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags))) {
 		mwifiex_dbg(adapter, WARN,
 			    "Device already resumed\n");
 		return 0;
@@ -602,7 +603,7 @@ static int mwifiex_usb_resume(struct usb_interface *intf)
 	/* Indicate device resumed. The netdev queue will be resumed only
 	 * after the urbs have been re-submitted
 	 */
-	adapter->is_suspended = false;
+	clear_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
 
 	if (!atomic_read(&card->rx_data_urb_pending))
 		for (i = 0; i < MWIFIEX_RX_DATA_URB; i++)
@@ -1158,13 +1159,13 @@ static int mwifiex_usb_host_to_card(struct mwifiex_adapter *adapter, u8 ep,
 	unsigned long flags;
 	int idx, ret;
 
-	if (adapter->is_suspended) {
+	if (test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "%s: not allowed while suspended\n", __func__);
 		return -1;
 	}
 
-	if (adapter->surprise_removed) {
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, ERROR, "%s: device removed\n", __func__);
 		return -1;
 	}
diff --git a/drivers/net/wireless/marvell/mwifiex/util.c b/drivers/net/wireless/marvell/mwifiex/util.c
index 6dd212898117..f9b71539d33e 100644
--- a/drivers/net/wireless/marvell/mwifiex/util.c
+++ b/drivers/net/wireless/marvell/mwifiex/util.c
@@ -197,9 +197,11 @@ int mwifiex_get_debug_info(struct mwifiex_private *priv,
 		info->is_deep_sleep = adapter->is_deep_sleep;
 		info->pm_wakeup_card_req = adapter->pm_wakeup_card_req;
 		info->pm_wakeup_fw_try = adapter->pm_wakeup_fw_try;
-		info->is_hs_configured = adapter->is_hs_configured;
+		info->is_hs_configured = test_bit(MWIFIEX_IS_HS_CONFIGURED,
+						  &adapter->work_flags);
 		info->hs_activated = adapter->hs_activated;
-		info->is_cmd_timedout = adapter->is_cmd_timedout;
+		info->is_cmd_timedout = test_bit(MWIFIEX_IS_CMD_TIMEDOUT,
+						 &adapter->work_flags);
 		info->num_cmd_host_to_card_failure
 				= adapter->dbg.num_cmd_host_to_card_failure;
 		info->num_cmd_sleep_cfm_host_to_card_failure
diff --git a/drivers/net/wireless/marvell/mwifiex/wmm.c b/drivers/net/wireless/marvell/mwifiex/wmm.c
index 936a0a841af8..407b9932ca4d 100644
--- a/drivers/net/wireless/marvell/mwifiex/wmm.c
+++ b/drivers/net/wireless/marvell/mwifiex/wmm.c
@@ -599,7 +599,7 @@ mwifiex_clean_txrx(struct mwifiex_private *priv)
 	memcpy(tos_to_tid, ac_to_tid, sizeof(tos_to_tid));
 
 	if (priv->adapter->if_ops.clean_pcie_ring &&
-	    !priv->adapter->surprise_removed)
+	    !test_bit(MWIFIEX_SURPRISE_REMOVED, &priv->adapter->work_flags))
 		priv->adapter->if_ops.clean_pcie_ring(priv->adapter);
 	spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, flags);
 
diff --git a/drivers/net/wireless/mediatek/mt76/Kconfig b/drivers/net/wireless/mediatek/mt76/Kconfig
index fc05d79c80d0..b6c5f17dca30 100644
--- a/drivers/net/wireless/mediatek/mt76/Kconfig
+++ b/drivers/net/wireless/mediatek/mt76/Kconfig
@@ -1,10 +1,37 @@
 config MT76_CORE
 	tristate
 
+config MT76_USB
+	tristate
+	depends on MT76_CORE
+
+config MT76x2_COMMON
+	tristate
+	depends on MT76_CORE
+
+config MT76x0U
+	tristate "MediaTek MT76x0U (USB) support"
+	select MT76_CORE
+	depends on MAC80211
+	depends on USB
+	help
+	  This adds support for MT7610U-based wireless USB dongles.
+
 config MT76x2E
 	tristate "MediaTek MT76x2E (PCIe) support"
 	select MT76_CORE
+	select MT76x2_COMMON
 	depends on MAC80211
 	depends on PCI
 	---help---
 	  This adds support for MT7612/MT7602/MT7662-based wireless PCIe devices.
+
+config MT76x2U
+	tristate "MediaTek MT76x2U (USB) support"
+	select MT76_CORE
+	select MT76_USB
+	select MT76x2_COMMON
+	depends on MAC80211
+	depends on USB
+	help
+	  This adds support for MT7612U-based wireless USB dongles.
diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index a0156bc01dea..158d10d2716c 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -1,15 +1,31 @@
 obj-$(CONFIG_MT76_CORE) += mt76.o
+obj-$(CONFIG_MT76_USB) += mt76-usb.o
+obj-$(CONFIG_MT76x0U) += mt76x0/
+obj-$(CONFIG_MT76x2_COMMON) += mt76x2-common.o
 obj-$(CONFIG_MT76x2E) += mt76x2e.o
+obj-$(CONFIG_MT76x2U) += mt76x2u.o
 
 mt76-y := \
 	mmio.o util.o trace.o dma.o mac80211.o debugfs.o eeprom.o tx.o agg-rx.o
 
+mt76-usb-y := usb.o usb_trace.o usb_mcu.o
+
 CFLAGS_trace.o := -I$(src)
+CFLAGS_usb_trace.o := -I$(src)
+
+mt76x2-common-y := \
+	mt76x2_eeprom.o mt76x2_tx_common.o mt76x2_mac_common.o \
+	mt76x2_init_common.o mt76x2_common.o mt76x2_phy_common.o \
+	mt76x2_debugfs.o
 
 mt76x2e-y := \
 	mt76x2_pci.o mt76x2_dma.o \
-	mt76x2_main.o mt76x2_init.o mt76x2_debugfs.o mt76x2_tx.o \
-	mt76x2_core.o mt76x2_mac.o mt76x2_eeprom.o mt76x2_mcu.o mt76x2_phy.o \
+	mt76x2_main.o mt76x2_init.o mt76x2_tx.o \
+	mt76x2_core.o mt76x2_mac.o mt76x2_mcu.o mt76x2_phy.o \
 	mt76x2_dfs.o mt76x2_trace.o
 
+mt76x2u-y := \
+	mt76x2_usb.o mt76x2u_init.o mt76x2u_main.o mt76x2u_mac.o \
+	mt76x2u_mcu.o mt76x2u_phy.o mt76x2u_core.o
+
 CFLAGS_mt76x2_trace.o := -I$(src)
diff --git a/drivers/net/wireless/mediatek/mt76/agg-rx.c b/drivers/net/wireless/mediatek/mt76/agg-rx.c
index 1e8cdce919d9..73c8b2805c97 100644
--- a/drivers/net/wireless/mediatek/mt76/agg-rx.c
+++ b/drivers/net/wireless/mediatek/mt76/agg-rx.c
@@ -113,7 +113,7 @@ mt76_rx_aggr_reorder_work(struct work_struct *work)
 	if (nframes)
 		ieee80211_queue_delayed_work(tid->dev->hw, &tid->reorder_work,
 					     REORDER_TIMEOUT);
-	mt76_rx_complete(dev, &frames, -1);
+	mt76_rx_complete(dev, &frames, NULL);
 
 	rcu_read_unlock();
 	local_bh_enable();
diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index 3dbedcedc2c4..c51da2205b93 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -239,6 +239,80 @@ mt76_dma_kick_queue(struct mt76_dev *dev, struct mt76_queue *q)
 	iowrite32(q->head, &q->regs->cpu_idx);
 }
 
+int mt76_dma_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q,
+			  struct sk_buff *skb, struct mt76_wcid *wcid,
+			  struct ieee80211_sta *sta)
+{
+	struct mt76_queue_entry e;
+	struct mt76_txwi_cache *t;
+	struct mt76_queue_buf buf[32];
+	struct sk_buff *iter;
+	dma_addr_t addr;
+	int len;
+	u32 tx_info = 0;
+	int n, ret;
+
+	t = mt76_get_txwi(dev);
+	if (!t) {
+		ieee80211_free_txskb(dev->hw, skb);
+		return -ENOMEM;
+	}
+
+	dma_sync_single_for_cpu(dev->dev, t->dma_addr, sizeof(t->txwi),
+				DMA_TO_DEVICE);
+	ret = dev->drv->tx_prepare_skb(dev, &t->txwi, skb, q, wcid, sta,
+				       &tx_info);
+	dma_sync_single_for_device(dev->dev, t->dma_addr, sizeof(t->txwi),
+				   DMA_TO_DEVICE);
+	if (ret < 0)
+		goto free;
+
+	len = skb->len - skb->data_len;
+	addr = dma_map_single(dev->dev, skb->data, len, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev->dev, addr)) {
+		ret = -ENOMEM;
+		goto free;
+	}
+
+	n = 0;
+	buf[n].addr = t->dma_addr;
+	buf[n++].len = dev->drv->txwi_size;
+	buf[n].addr = addr;
+	buf[n++].len = len;
+
+	skb_walk_frags(skb, iter) {
+		if (n == ARRAY_SIZE(buf))
+			goto unmap;
+
+		addr = dma_map_single(dev->dev, iter->data, iter->len,
+				      DMA_TO_DEVICE);
+		if (dma_mapping_error(dev->dev, addr))
+			goto unmap;
+
+		buf[n].addr = addr;
+		buf[n++].len = iter->len;
+	}
+
+	if (q->queued + (n + 1) / 2 >= q->ndesc - 1)
+		goto unmap;
+
+	return dev->queue_ops->add_buf(dev, q, buf, n, tx_info, skb, t);
+
+unmap:
+	ret = -ENOMEM;
+	for (n--; n > 0; n--)
+		dma_unmap_single(dev->dev, buf[n].addr, buf[n].len,
+				 DMA_TO_DEVICE);
+
+free:
+	e.skb = skb;
+	e.txwi = t;
+	dev->drv->tx_complete_skb(dev, q, &e, true);
+	mt76_put_txwi(dev, t);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mt76_dma_tx_queue_skb);
+
 static int
 mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q, bool napi)
 {
@@ -400,7 +474,7 @@ mt76_dma_rx_poll(struct napi_struct *napi, int budget)
 
 	do {
 		cur = mt76_dma_rx_process(dev, &dev->q_rx[qid], budget - done);
-		mt76_rx_poll_complete(dev, qid);
+		mt76_rx_poll_complete(dev, qid, napi);
 		done += cur;
 	} while (cur && done < budget);
 
@@ -436,6 +510,7 @@ static const struct mt76_queue_ops mt76_dma_ops = {
 	.init = mt76_dma_init,
 	.alloc = mt76_dma_alloc_queue,
 	.add_buf = mt76_dma_add_buf,
+	.tx_queue_skb = mt76_dma_tx_queue_skb,
 	.tx_cleanup = mt76_dma_tx_cleanup,
 	.rx_reset = mt76_dma_rx_reset,
 	.kick = mt76_dma_kick_queue,
diff --git a/drivers/net/wireless/mediatek/mt76/dma.h b/drivers/net/wireless/mediatek/mt76/dma.h
index 1dad39697929..27248e24a19b 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.h
+++ b/drivers/net/wireless/mediatek/mt76/dma.h
@@ -25,6 +25,39 @@
 #define MT_DMA_CTL_LAST_SEC0		BIT(30)
 #define MT_DMA_CTL_DMA_DONE		BIT(31)
 
+#define MT_TXD_INFO_LEN			GENMASK(15, 0)
+#define MT_TXD_INFO_NEXT_VLD		BIT(16)
+#define MT_TXD_INFO_TX_BURST		BIT(17)
+#define MT_TXD_INFO_80211		BIT(19)
+#define MT_TXD_INFO_TSO			BIT(20)
+#define MT_TXD_INFO_CSO			BIT(21)
+#define MT_TXD_INFO_WIV			BIT(24)
+#define MT_TXD_INFO_QSEL		GENMASK(26, 25)
+#define MT_TXD_INFO_DPORT		GENMASK(29, 27)
+#define MT_TXD_INFO_TYPE		GENMASK(31, 30)
+
+#define MT_RX_FCE_INFO_LEN		GENMASK(13, 0)
+#define MT_RX_FCE_INFO_SELF_GEN		BIT(15)
+#define MT_RX_FCE_INFO_CMD_SEQ		GENMASK(19, 16)
+#define MT_RX_FCE_INFO_EVT_TYPE		GENMASK(23, 20)
+#define MT_RX_FCE_INFO_PCIE_INTR	BIT(24)
+#define MT_RX_FCE_INFO_QSEL		GENMASK(26, 25)
+#define MT_RX_FCE_INFO_D_PORT		GENMASK(29, 27)
+#define MT_RX_FCE_INFO_TYPE		GENMASK(31, 30)
+
+/* MCU request message header  */
+#define MT_MCU_MSG_LEN			GENMASK(15, 0)
+#define MT_MCU_MSG_CMD_SEQ		GENMASK(19, 16)
+#define MT_MCU_MSG_CMD_TYPE		GENMASK(26, 20)
+#define MT_MCU_MSG_PORT			GENMASK(29, 27)
+#define MT_MCU_MSG_TYPE			GENMASK(31, 30)
+#define MT_MCU_MSG_TYPE_CMD		BIT(30)
+
+#define MT_DMA_HDR_LEN			4
+#define MT_RX_INFO_LEN			4
+#define MT_FCE_INFO_LEN			4
+#define MT_RX_RXWI_LEN			32
+
 struct mt76_desc {
 	__le32 buf0;
 	__le32 ctrl;
@@ -32,6 +65,16 @@ struct mt76_desc {
 	__le32 info;
 } __packed __aligned(4);
 
+enum dma_msg_port {
+	WLAN_PORT,
+	CPU_RX_PORT,
+	CPU_TX_PORT,
+	HOST_PORT,
+	VIRTUAL_CPU_RX_PORT,
+	VIRTUAL_CPU_TX_PORT,
+	DISCARD,
+};
+
 int mt76_dma_attach(struct mt76_dev *dev);
 void mt76_dma_cleanup(struct mt76_dev *dev);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index d62e34e7eadf..029d54bce9e8 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -303,14 +303,6 @@ int mt76_register_device(struct mt76_dev *dev, bool vht,
 	SET_IEEE80211_DEV(hw, dev->dev);
 	SET_IEEE80211_PERM_ADDR(hw, dev->macaddr);
 
-	wiphy->interface_modes =
-		BIT(NL80211_IFTYPE_STATION) |
-		BIT(NL80211_IFTYPE_AP) |
-#ifdef CONFIG_MAC80211_MESH
-		BIT(NL80211_IFTYPE_MESH_POINT) |
-#endif
-		BIT(NL80211_IFTYPE_ADHOC);
-
 	wiphy->features |= NL80211_FEATURE_ACTIVE_MONITOR;
 
 	wiphy->available_antennas_tx = dev->antenna_mask;
@@ -591,15 +583,11 @@ mt76_check_ps(struct mt76_dev *dev, struct sk_buff *skb)
 }
 
 void mt76_rx_complete(struct mt76_dev *dev, struct sk_buff_head *frames,
-		      int queue)
+		      struct napi_struct *napi)
 {
-	struct napi_struct *napi = NULL;
 	struct ieee80211_sta *sta;
 	struct sk_buff *skb;
 
-	if (queue >= 0)
-	    napi = &dev->napi[queue];
-
 	spin_lock(&dev->rx_lock);
 	while ((skb = __skb_dequeue(frames)) != NULL) {
 		if (mt76_check_ccmp_pn(skb)) {
@@ -613,7 +601,8 @@ void mt76_rx_complete(struct mt76_dev *dev, struct sk_buff_head *frames,
 	spin_unlock(&dev->rx_lock);
 }
 
-void mt76_rx_poll_complete(struct mt76_dev *dev, enum mt76_rxq_id q)
+void mt76_rx_poll_complete(struct mt76_dev *dev, enum mt76_rxq_id q,
+			   struct napi_struct *napi)
 {
 	struct sk_buff_head frames;
 	struct sk_buff *skb;
@@ -625,5 +614,6 @@ void mt76_rx_poll_complete(struct mt76_dev *dev, enum mt76_rxq_id q)
 		mt76_rx_aggr_reorder(skb, &frames);
 	}
 
-	mt76_rx_complete(dev, &frames, q);
+	mt76_rx_complete(dev, &frames, napi);
 }
+EXPORT_SYMBOL_GPL(mt76_rx_poll_complete);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index d2166fbf50ff..2eab35879163 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -22,6 +22,7 @@
 #include <linux/spinlock.h>
 #include <linux/skbuff.h>
 #include <linux/leds.h>
+#include <linux/usb.h>
 #include <net/mac80211.h>
 #include "util.h"
 
@@ -30,6 +31,7 @@
 #define MT_RX_BUF_SIZE      2048
 
 struct mt76_dev;
+struct mt76_wcid;
 
 struct mt76_bus_ops {
 	u32 (*rr)(struct mt76_dev *dev, u32 offset);
@@ -62,12 +64,22 @@ struct mt76_queue_buf {
 	int len;
 };
 
+struct mt76u_buf {
+	struct mt76_dev *dev;
+	struct urb *urb;
+	size_t len;
+	bool done;
+};
+
 struct mt76_queue_entry {
 	union {
 		void *buf;
 		struct sk_buff *skb;
 	};
-	struct mt76_txwi_cache *txwi;
+	union {
+		struct mt76_txwi_cache *txwi;
+		struct mt76u_buf ubuf;
+	};
 	bool schedule;
 };
 
@@ -88,6 +100,7 @@ struct mt76_queue {
 	struct list_head swq;
 	int swq_queued;
 
+	u16 first;
 	u16 head;
 	u16 tail;
 	int ndesc;
@@ -110,6 +123,10 @@ struct mt76_queue_ops {
 		       struct mt76_queue_buf *buf, int nbufs, u32 info,
 		       struct sk_buff *skb, void *txwi);
 
+	int (*tx_queue_skb)(struct mt76_dev *dev, struct mt76_queue *q,
+			    struct sk_buff *skb, struct mt76_wcid *wcid,
+			    struct ieee80211_sta *sta);
+
 	void *(*dequeue)(struct mt76_dev *dev, struct mt76_queue *q, bool flush,
 			 int *len, u32 *info, bool *more);
 
@@ -187,9 +204,13 @@ struct mt76_rx_tid {
 enum {
 	MT76_STATE_INITIALIZED,
 	MT76_STATE_RUNNING,
+	MT76_STATE_MCU_RUNNING,
 	MT76_SCANNING,
 	MT76_RESET,
 	MT76_OFFCHANNEL,
+	MT76_REMOVED,
+	MT76_READING_STATS,
+	MT76_MORE_STATS,
 };
 
 struct mt76_hw_cap {
@@ -210,6 +231,8 @@ struct mt76_driver_ops {
 	void (*tx_complete_skb)(struct mt76_dev *dev, struct mt76_queue *q,
 				struct mt76_queue_entry *e, bool flush);
 
+	bool (*tx_status_data)(struct mt76_dev *dev, u8 *update);
+
 	void (*rx_skb)(struct mt76_dev *dev, enum mt76_rxq_id q,
 		       struct sk_buff *skb);
 
@@ -229,6 +252,64 @@ struct mt76_sband {
 	struct mt76_channel_state *chan;
 };
 
+/* addr req mask */
+#define MT_VEND_TYPE_EEPROM	BIT(31)
+#define MT_VEND_TYPE_CFG	BIT(30)
+#define MT_VEND_TYPE_MASK	(MT_VEND_TYPE_EEPROM | MT_VEND_TYPE_CFG)
+
+#define MT_VEND_ADDR(type, n)	(MT_VEND_TYPE_##type | (n))
+enum mt_vendor_req {
+	MT_VEND_DEV_MODE =	0x1,
+	MT_VEND_WRITE =		0x2,
+	MT_VEND_MULTI_WRITE =	0x6,
+	MT_VEND_MULTI_READ =	0x7,
+	MT_VEND_READ_EEPROM =	0x9,
+	MT_VEND_WRITE_FCE =	0x42,
+	MT_VEND_WRITE_CFG =	0x46,
+	MT_VEND_READ_CFG =	0x47,
+};
+
+enum mt76u_in_ep {
+	MT_EP_IN_PKT_RX,
+	MT_EP_IN_CMD_RESP,
+	__MT_EP_IN_MAX,
+};
+
+enum mt76u_out_ep {
+	MT_EP_OUT_INBAND_CMD,
+	MT_EP_OUT_AC_BK,
+	MT_EP_OUT_AC_BE,
+	MT_EP_OUT_AC_VI,
+	MT_EP_OUT_AC_VO,
+	MT_EP_OUT_HCCA,
+	__MT_EP_OUT_MAX,
+};
+
+#define MT_SG_MAX_SIZE		8
+#define MT_NUM_TX_ENTRIES	256
+#define MT_NUM_RX_ENTRIES	128
+#define MCU_RESP_URB_SIZE	1024
+struct mt76_usb {
+	struct mutex usb_ctrl_mtx;
+	u8 data[32];
+
+	struct tasklet_struct rx_tasklet;
+	struct tasklet_struct tx_tasklet;
+	struct delayed_work stat_work;
+
+	u8 out_ep[__MT_EP_OUT_MAX];
+	u16 out_max_packet;
+	u8 in_ep[__MT_EP_IN_MAX];
+	u16 in_max_packet;
+
+	struct mt76u_mcu {
+		struct mutex mutex;
+		struct completion cmpl;
+		struct mt76u_buf res;
+		u32 msg_seq;
+	} mcu;
+};
+
 struct mt76_dev {
 	struct ieee80211_hw *hw;
 	struct cfg80211_chan_def chandef;
@@ -271,6 +352,8 @@ struct mt76_dev {
 	char led_name[32];
 	bool led_al;
 	u8 led_pin;
+
+	struct mt76_usb usb;
 };
 
 enum mt76_phy_type {
@@ -390,6 +473,26 @@ struct dentry *mt76_register_debugfs(struct mt76_dev *dev);
 int mt76_eeprom_init(struct mt76_dev *dev, int len);
 void mt76_eeprom_override(struct mt76_dev *dev);
 
+/* increment with wrap-around */
+static inline int mt76_incr(int val, int size)
+{
+	return (val + 1) & (size - 1);
+}
+
+/* decrement with wrap-around */
+static inline int mt76_decr(int val, int size)
+{
+	return (val - 1) & (size - 1);
+}
+
+/* Hardware uses mirrored order of queues with Q3
+ * having the highest priority
+ */
+static inline u8 q2hwq(u8 q)
+{
+	return q ^ 0x3;
+}
+
 static inline struct ieee80211_txq *
 mtxq_to_txq(struct mt76_txq *mtxq)
 {
@@ -409,9 +512,9 @@ wcid_to_sta(struct mt76_wcid *wcid)
 	return container_of(ptr, struct ieee80211_sta, drv_priv);
 }
 
-int mt76_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q,
-		      struct sk_buff *skb, struct mt76_wcid *wcid,
-		      struct ieee80211_sta *sta);
+int mt76_dma_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q,
+			  struct sk_buff *skb, struct mt76_wcid *wcid,
+			  struct ieee80211_sta *sta);
 
 void mt76_rx(struct mt76_dev *dev, enum mt76_rxq_id q, struct sk_buff *skb);
 void mt76_tx(struct mt76_dev *dev, struct ieee80211_sta *sta,
@@ -442,10 +545,69 @@ void mt76_wcid_key_setup(struct mt76_dev *dev, struct mt76_wcid *wcid,
 
 /* internal */
 void mt76_tx_free(struct mt76_dev *dev);
+struct mt76_txwi_cache *mt76_get_txwi(struct mt76_dev *dev);
 void mt76_put_txwi(struct mt76_dev *dev, struct mt76_txwi_cache *t);
 void mt76_rx_complete(struct mt76_dev *dev, struct sk_buff_head *frames,
-		      int queue);
-void mt76_rx_poll_complete(struct mt76_dev *dev, enum mt76_rxq_id q);
+		      struct napi_struct *napi);
+void mt76_rx_poll_complete(struct mt76_dev *dev, enum mt76_rxq_id q,
+			   struct napi_struct *napi);
 void mt76_rx_aggr_reorder(struct sk_buff *skb, struct sk_buff_head *frames);
 
+/* usb */
+static inline bool mt76u_urb_error(struct urb *urb)
+{
+	return urb->status &&
+	       urb->status != -ECONNRESET &&
+	       urb->status != -ESHUTDOWN &&
+	       urb->status != -ENOENT;
+}
+
+/* Map hardware queues to usb endpoints */
+static inline u8 q2ep(u8 qid)
+{
+	/* TODO: take management packets to queue 5 */
+	return qid + 1;
+}
+
+static inline bool mt76u_check_sg(struct mt76_dev *dev)
+{
+	struct usb_interface *intf = to_usb_interface(dev->dev);
+	struct usb_device *udev = interface_to_usbdev(intf);
+
+	return (udev->bus->sg_tablesize > 0 &&
+		(udev->bus->no_sg_constraint ||
+		 udev->speed == USB_SPEED_WIRELESS));
+}
+
+int mt76u_vendor_request(struct mt76_dev *dev, u8 req,
+			 u8 req_type, u16 val, u16 offset,
+			 void *buf, size_t len);
+void mt76u_single_wr(struct mt76_dev *dev, const u8 req,
+		     const u16 offset, const u32 val);
+u32 mt76u_rr(struct mt76_dev *dev, u32 addr);
+void mt76u_wr(struct mt76_dev *dev, u32 addr, u32 val);
+int mt76u_init(struct mt76_dev *dev, struct usb_interface *intf);
+void mt76u_deinit(struct mt76_dev *dev);
+int mt76u_buf_alloc(struct mt76_dev *dev, struct mt76u_buf *buf,
+		    int nsgs, int len, int sglen, gfp_t gfp);
+void mt76u_buf_free(struct mt76u_buf *buf);
+int mt76u_submit_buf(struct mt76_dev *dev, int dir, int index,
+		     struct mt76u_buf *buf, gfp_t gfp,
+		     usb_complete_t complete_fn, void *context);
+int mt76u_submit_rx_buffers(struct mt76_dev *dev);
+int mt76u_alloc_queues(struct mt76_dev *dev);
+void mt76u_stop_queues(struct mt76_dev *dev);
+void mt76u_stop_stat_wk(struct mt76_dev *dev);
+void mt76u_queues_deinit(struct mt76_dev *dev);
+int mt76u_skb_dma_info(struct sk_buff *skb, int port, u32 flags);
+
+int mt76u_mcu_fw_send_data(struct mt76_dev *dev, const void *data,
+			   int data_len, u32 max_payload, u32 offset);
+void mt76u_mcu_complete_urb(struct urb *urb);
+struct sk_buff *mt76u_mcu_msg_alloc(const void *data, int len);
+int mt76u_mcu_send_msg(struct mt76_dev *dev, struct sk_buff *skb,
+		       int cmd, bool wait_resp);
+void mt76u_mcu_fw_reset(struct mt76_dev *dev);
+int mt76u_mcu_init_rx(struct mt76_dev *dev);
+
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/Makefile b/drivers/net/wireless/mediatek/mt76/mt76x0/Makefile
new file mode 100644
index 000000000000..7843908261ba
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/Makefile
@@ -0,0 +1,7 @@
+obj-$(CONFIG_MT76x0U)    += mt76x0.o
+
+mt76x0-objs	= \
+	usb.o init.o main.o mcu.o trace.o dma.o eeprom.o phy.o \
+	mac.o util.o debugfs.o tx.o core.o
+# ccflags-y := -DDEBUG
+CFLAGS_trace.o := -I$(src)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/core.c b/drivers/net/wireless/mediatek/mt76/mt76x0/core.c
new file mode 100644
index 000000000000..892803fce842
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/core.c
@@ -0,0 +1,34 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "mt76x0.h"
+
+int mt76x0_wait_asic_ready(struct mt76x0_dev *dev)
+{
+	int i = 100;
+	u32 val;
+
+	do {
+		if (test_bit(MT76_REMOVED, &dev->mt76.state))
+			return -EIO;
+
+		val = mt76_rr(dev, MT_MAC_CSR0);
+		if (val && ~val)
+			return 0;
+
+		udelay(10);
+	} while (i--);
+
+	return -EIO;
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt76x0/debugfs.c
new file mode 100644
index 000000000000..e7a77a886068
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/debugfs.c
@@ -0,0 +1,166 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/debugfs.h>
+
+#include "mt76x0.h"
+#include "eeprom.h"
+
+static int
+mt76_reg_set(void *data, u64 val)
+{
+	struct mt76x0_dev *dev = data;
+
+	mt76_wr(dev, dev->debugfs_reg, val);
+	return 0;
+}
+
+static int
+mt76_reg_get(void *data, u64 *val)
+{
+	struct mt76x0_dev *dev = data;
+
+	*val = mt76_rr(dev, dev->debugfs_reg);
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_regval, mt76_reg_get, mt76_reg_set, "0x%08llx\n");
+
+static int
+mt76x0_ampdu_stat_read(struct seq_file *file, void *data)
+{
+	struct mt76x0_dev *dev = file->private;
+	int i, j;
+
+#define stat_printf(grp, off, name)					\
+	seq_printf(file, #name ":\t%llu\n", dev->stats.grp[off])
+
+	stat_printf(rx_stat, 0, rx_crc_err);
+	stat_printf(rx_stat, 1, rx_phy_err);
+	stat_printf(rx_stat, 2, rx_false_cca);
+	stat_printf(rx_stat, 3, rx_plcp_err);
+	stat_printf(rx_stat, 4, rx_fifo_overflow);
+	stat_printf(rx_stat, 5, rx_duplicate);
+
+	stat_printf(tx_stat, 0, tx_fail_cnt);
+	stat_printf(tx_stat, 1, tx_bcn_cnt);
+	stat_printf(tx_stat, 2, tx_success);
+	stat_printf(tx_stat, 3, tx_retransmit);
+	stat_printf(tx_stat, 4, tx_zero_len);
+	stat_printf(tx_stat, 5, tx_underflow);
+
+	stat_printf(aggr_stat, 0, non_aggr_tx);
+	stat_printf(aggr_stat, 1, aggr_tx);
+
+	stat_printf(zero_len_del, 0, tx_zero_len_del);
+	stat_printf(zero_len_del, 1, rx_zero_len_del);
+#undef stat_printf
+
+	seq_puts(file, "Aggregations stats:\n");
+	for (i = 0; i < 4; i++) {
+		for (j = 0; j < 8; j++)
+			seq_printf(file, "%08llx ",
+				   dev->stats.aggr_n[i * 8 + j]);
+		seq_putc(file, '\n');
+	}
+
+	seq_printf(file, "recent average AMPDU len: %d\n",
+		   atomic_read(&dev->avg_ampdu_len));
+
+	return 0;
+}
+
+static int
+mt76x0_ampdu_stat_open(struct inode *inode, struct file *f)
+{
+	return single_open(f, mt76x0_ampdu_stat_read, inode->i_private);
+}
+
+static const struct file_operations fops_ampdu_stat = {
+	.open = mt76x0_ampdu_stat_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int
+mt76x0_eeprom_param_read(struct seq_file *file, void *data)
+{
+	struct mt76x0_dev *dev = file->private;
+	int i;
+
+	seq_printf(file, "RF freq offset: %hhx\n", dev->ee->rf_freq_off);
+	seq_printf(file, "RSSI offset 2GHz: %hhx %hhx\n",
+		   dev->ee->rssi_offset_2ghz[0], dev->ee->rssi_offset_2ghz[1]);
+	seq_printf(file, "RSSI offset 5GHz: %hhx %hhx %hhx\n",
+		   dev->ee->rssi_offset_5ghz[0], dev->ee->rssi_offset_5ghz[1],
+		   dev->ee->rssi_offset_5ghz[2]);
+	seq_printf(file, "Temperature offset: %hhx\n", dev->ee->temp_off);
+	seq_printf(file, "LNA gain 2Ghz: %hhx\n", dev->ee->lna_gain_2ghz);
+	seq_printf(file, "LNA gain 5Ghz: %hhx %hhx %hhx\n",
+		   dev->ee->lna_gain_5ghz[0], dev->ee->lna_gain_5ghz[1],
+		   dev->ee->lna_gain_5ghz[2]);
+	seq_printf(file, "Power Amplifier type %hhx\n", dev->ee->pa_type);
+	seq_printf(file, "Reg channels: %hhu-%hhu\n", dev->ee->reg.start,
+		   dev->ee->reg.start + dev->ee->reg.num - 1);
+
+	seq_puts(file, "Per channel power:\n");
+	for (i = 0; i < 58; i++)
+		seq_printf(file, "\t%d chan:%d pwr:%d\n", i, i,
+			   dev->ee->tx_pwr_per_chan[i]);
+
+	seq_puts(file, "Per rate power 2GHz:\n");
+	for (i = 0; i < 5; i++)
+		seq_printf(file, "\t %d bw20:%d bw40:%d\n",
+			   i, dev->ee->tx_pwr_cfg_2g[i][0],
+			      dev->ee->tx_pwr_cfg_5g[i][1]);
+
+	seq_puts(file, "Per rate power 5GHz:\n");
+	for (i = 0; i < 5; i++)
+		seq_printf(file, "\t %d bw20:%d bw40:%d\n",
+			   i, dev->ee->tx_pwr_cfg_5g[i][0],
+			      dev->ee->tx_pwr_cfg_5g[i][1]);
+
+	return 0;
+}
+
+static int
+mt76x0_eeprom_param_open(struct inode *inode, struct file *f)
+{
+	return single_open(f, mt76x0_eeprom_param_read, inode->i_private);
+}
+
+static const struct file_operations fops_eeprom_param = {
+	.open = mt76x0_eeprom_param_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+void mt76x0_init_debugfs(struct mt76x0_dev *dev)
+{
+	struct dentry *dir;
+
+	dir = debugfs_create_dir("mt76x0", dev->mt76.hw->wiphy->debugfsdir);
+	if (!dir)
+		return;
+
+	debugfs_create_u32("regidx", S_IRUSR | S_IWUSR, dir, &dev->debugfs_reg);
+	debugfs_create_file("regval", S_IRUSR | S_IWUSR, dir, dev,
+			    &fops_regval);
+	debugfs_create_file("ampdu_stat", S_IRUSR, dir, dev, &fops_ampdu_stat);
+	debugfs_create_file("eeprom_param", S_IRUSR, dir, dev,
+			    &fops_eeprom_param);
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/dma.c b/drivers/net/wireless/mediatek/mt76/mt76x0/dma.c
new file mode 100644
index 000000000000..e2efb430419b
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/dma.c
@@ -0,0 +1,522 @@
+/*
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include "mt76x0.h"
+#include "dma.h"
+#include "usb.h"
+#include "trace.h"
+
+static int mt76x0_submit_rx_buf(struct mt76x0_dev *dev,
+				 struct mt76x0_dma_buf_rx *e, gfp_t gfp);
+
+static unsigned int ieee80211_get_hdrlen_from_buf(const u8 *data, unsigned len)
+{
+	const struct ieee80211_hdr *hdr = (const struct ieee80211_hdr *)data;
+	unsigned int hdrlen;
+
+	if (unlikely(len < 10))
+		return 0;
+	hdrlen = ieee80211_hdrlen(hdr->frame_control);
+	if (unlikely(hdrlen > len))
+		return 0;
+	return hdrlen;
+}
+
+static struct sk_buff *
+mt76x0_rx_skb_from_seg(struct mt76x0_dev *dev, struct mt76x0_rxwi *rxwi,
+			void *data, u32 seg_len, u32 truesize, struct page *p)
+{
+	struct sk_buff *skb;
+	u32 true_len, hdr_len = 0, copy, frag;
+
+	skb = alloc_skb(p ? 128 : seg_len, GFP_ATOMIC);
+	if (!skb)
+		return NULL;
+
+	true_len = mt76x0_mac_process_rx(dev, skb, data, rxwi);
+	if (!true_len || true_len > seg_len)
+		goto bad_frame;
+
+	hdr_len = ieee80211_get_hdrlen_from_buf(data, true_len);
+	if (!hdr_len)
+		goto bad_frame;
+
+	if (rxwi->rxinfo & cpu_to_le32(MT_RXINFO_L2PAD)) {
+		memcpy(skb_put(skb, hdr_len), data, hdr_len);
+
+		data += hdr_len + 2;
+		true_len -= hdr_len;
+		hdr_len = 0;
+	}
+
+	/* If not doing paged RX allocated skb will always have enough space */
+	copy = (true_len <= skb_tailroom(skb)) ? true_len : hdr_len + 8;
+	frag = true_len - copy;
+
+	memcpy(skb_put(skb, copy), data, copy);
+	data += copy;
+
+	if (frag) {
+		skb_add_rx_frag(skb, 0, p, data - page_address(p),
+				frag, truesize);
+		get_page(p);
+	}
+
+	return skb;
+
+bad_frame:
+	dev_err_ratelimited(dev->mt76.dev, "Error: incorrect frame len:%u hdr:%u\n",
+			    true_len, hdr_len);
+	dev_kfree_skb(skb);
+	return NULL;
+}
+
+static void mt76x0_rx_process_seg(struct mt76x0_dev *dev, u8 *data,
+				   u32 seg_len, struct page *p)
+{
+	struct sk_buff *skb;
+	struct mt76x0_rxwi *rxwi;
+	u32 fce_info, truesize = seg_len;
+
+	/* DMA_INFO field at the beginning of the segment contains only some of
+	 * the information, we need to read the FCE descriptor from the end.
+	 */
+	fce_info = get_unaligned_le32(data + seg_len - MT_FCE_INFO_LEN);
+	seg_len -= MT_FCE_INFO_LEN;
+
+	data += MT_DMA_HDR_LEN;
+	seg_len -= MT_DMA_HDR_LEN;
+
+	rxwi = (struct mt76x0_rxwi *) data;
+	data += sizeof(struct mt76x0_rxwi);
+	seg_len -= sizeof(struct mt76x0_rxwi);
+
+	if (unlikely(FIELD_GET(MT_RXD_INFO_TYPE, fce_info)))
+		dev_err_once(dev->mt76.dev, "Error: RX path seen a non-pkt urb\n");
+
+	trace_mt76x0_rx(&dev->mt76, rxwi, fce_info);
+
+	skb = mt76x0_rx_skb_from_seg(dev, rxwi, data, seg_len, truesize, p);
+	if (!skb)
+		return;
+
+	spin_lock(&dev->mac_lock);
+	ieee80211_rx(dev->mt76.hw, skb);
+	spin_unlock(&dev->mac_lock);
+}
+
+static u16 mt76x0_rx_next_seg_len(u8 *data, u32 data_len)
+{
+	u32 min_seg_len = MT_DMA_HDR_LEN + MT_RX_INFO_LEN +
+		sizeof(struct mt76x0_rxwi) + MT_FCE_INFO_LEN;
+	u16 dma_len = get_unaligned_le16(data);
+
+	if (data_len < min_seg_len ||
+	    WARN_ON(!dma_len) ||
+	    WARN_ON(dma_len + MT_DMA_HDRS > data_len) ||
+	    WARN_ON(dma_len & 0x3))
+		return 0;
+
+	return MT_DMA_HDRS + dma_len;
+}
+
+static void
+mt76x0_rx_process_entry(struct mt76x0_dev *dev, struct mt76x0_dma_buf_rx *e)
+{
+	u32 seg_len, data_len = e->urb->actual_length;
+	u8 *data = page_address(e->p);
+	struct page *new_p = NULL;
+	int cnt = 0;
+
+	if (!test_bit(MT76_STATE_INITIALIZED, &dev->mt76.state))
+		return;
+
+	/* Copy if there is very little data in the buffer. */
+	if (data_len > 512)
+		new_p = dev_alloc_pages(MT_RX_ORDER);
+
+	while ((seg_len = mt76x0_rx_next_seg_len(data, data_len))) {
+		mt76x0_rx_process_seg(dev, data, seg_len, new_p ? e->p : NULL);
+
+		data_len -= seg_len;
+		data += seg_len;
+		cnt++;
+	}
+
+	if (cnt > 1)
+		trace_mt76x0_rx_dma_aggr(&dev->mt76, cnt, !!new_p);
+
+	if (new_p) {
+		/* we have one extra ref from the allocator */
+		__free_pages(e->p, MT_RX_ORDER);
+
+		e->p = new_p;
+	}
+}
+
+static struct mt76x0_dma_buf_rx *
+mt76x0_rx_get_pending_entry(struct mt76x0_dev *dev)
+{
+	struct mt76x0_rx_queue *q = &dev->rx_q;
+	struct mt76x0_dma_buf_rx *buf = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->rx_lock, flags);
+
+	if (!q->pending)
+		goto out;
+
+	buf = &q->e[q->start];
+	q->pending--;
+	q->start = (q->start + 1) % q->entries;
+out:
+	spin_unlock_irqrestore(&dev->rx_lock, flags);
+
+	return buf;
+}
+
+static void mt76x0_complete_rx(struct urb *urb)
+{
+	struct mt76x0_dev *dev = urb->context;
+	struct mt76x0_rx_queue *q = &dev->rx_q;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->rx_lock, flags);
+
+	if (mt76x0_urb_has_error(urb))
+		dev_err(dev->mt76.dev, "Error: RX urb failed:%d\n", urb->status);
+	if (WARN_ONCE(q->e[q->end].urb != urb, "RX urb mismatch"))
+		goto out;
+
+	q->end = (q->end + 1) % q->entries;
+	q->pending++;
+	tasklet_schedule(&dev->rx_tasklet);
+out:
+	spin_unlock_irqrestore(&dev->rx_lock, flags);
+}
+
+static void mt76x0_rx_tasklet(unsigned long data)
+{
+	struct mt76x0_dev *dev = (struct mt76x0_dev *) data;
+	struct mt76x0_dma_buf_rx *e;
+
+	while ((e = mt76x0_rx_get_pending_entry(dev))) {
+		if (e->urb->status)
+			continue;
+
+		mt76x0_rx_process_entry(dev, e);
+		mt76x0_submit_rx_buf(dev, e, GFP_ATOMIC);
+	}
+}
+
+static void mt76x0_complete_tx(struct urb *urb)
+{
+	struct mt76x0_tx_queue *q = urb->context;
+	struct mt76x0_dev *dev = q->dev;
+	struct sk_buff *skb;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->tx_lock, flags);
+
+	if (mt76x0_urb_has_error(urb))
+		dev_err(dev->mt76.dev, "Error: TX urb failed:%d\n", urb->status);
+	if (WARN_ONCE(q->e[q->start].urb != urb, "TX urb mismatch"))
+		goto out;
+
+	skb = q->e[q->start].skb;
+	trace_mt76x0_tx_dma_done(&dev->mt76, skb);
+
+	__skb_queue_tail(&dev->tx_skb_done, skb);
+	tasklet_schedule(&dev->tx_tasklet);
+
+	if (q->used == q->entries - q->entries / 8)
+		ieee80211_wake_queue(dev->mt76.hw, skb_get_queue_mapping(skb));
+
+	q->start = (q->start + 1) % q->entries;
+	q->used--;
+out:
+	spin_unlock_irqrestore(&dev->tx_lock, flags);
+}
+
+static void mt76x0_tx_tasklet(unsigned long data)
+{
+	struct mt76x0_dev *dev = (struct mt76x0_dev *) data;
+	struct sk_buff_head skbs;
+	unsigned long flags;
+
+	__skb_queue_head_init(&skbs);
+
+	spin_lock_irqsave(&dev->tx_lock, flags);
+
+	set_bit(MT76_MORE_STATS, &dev->mt76.state);
+	if (!test_and_set_bit(MT76_READING_STATS, &dev->mt76.state))
+		queue_delayed_work(dev->stat_wq, &dev->stat_work,
+				   msecs_to_jiffies(10));
+
+	skb_queue_splice_init(&dev->tx_skb_done, &skbs);
+
+	spin_unlock_irqrestore(&dev->tx_lock, flags);
+
+	while (!skb_queue_empty(&skbs)) {
+		struct sk_buff *skb = __skb_dequeue(&skbs);
+
+		mt76x0_tx_status(dev, skb);
+	}
+}
+
+static int mt76x0_dma_submit_tx(struct mt76x0_dev *dev,
+				 struct sk_buff *skb, u8 ep)
+{
+	struct usb_device *usb_dev = mt76x0_to_usb_dev(dev);
+	unsigned snd_pipe = usb_sndbulkpipe(usb_dev, dev->out_ep[ep]);
+	struct mt76x0_dma_buf_tx *e;
+	struct mt76x0_tx_queue *q = &dev->tx_q[ep];
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&dev->tx_lock, flags);
+
+	if (WARN_ON_ONCE(q->entries <= q->used)) {
+		ret = -ENOSPC;
+		goto out;
+	}
+
+	e = &q->e[q->end];
+	e->skb = skb;
+	usb_fill_bulk_urb(e->urb, usb_dev, snd_pipe, skb->data, skb->len,
+			  mt76x0_complete_tx, q);
+	ret = usb_submit_urb(e->urb, GFP_ATOMIC);
+	if (ret) {
+		/* Special-handle ENODEV from TX urb submission because it will
+		 * often be the first ENODEV we see after device is removed.
+		 */
+		if (ret == -ENODEV)
+			set_bit(MT76_REMOVED, &dev->mt76.state);
+		else
+			dev_err(dev->mt76.dev, "Error: TX urb submit failed:%d\n",
+				ret);
+		goto out;
+	}
+
+	q->end = (q->end + 1) % q->entries;
+	q->used++;
+
+	if (q->used >= q->entries)
+		ieee80211_stop_queue(dev->mt76.hw, skb_get_queue_mapping(skb));
+out:
+	spin_unlock_irqrestore(&dev->tx_lock, flags);
+
+	return ret;
+}
+
+/* Map USB endpoint number to Q id in the DMA engine */
+static enum mt76_qsel ep2dmaq(u8 ep)
+{
+	if (ep == 5)
+		return MT_QSEL_MGMT;
+	return MT_QSEL_EDCA;
+}
+
+int mt76x0_dma_enqueue_tx(struct mt76x0_dev *dev, struct sk_buff *skb,
+			   struct mt76_wcid *wcid, int hw_q)
+{
+	u8 ep = q2ep(hw_q);
+	u32 dma_flags;
+	int ret;
+
+	dma_flags = MT_TXD_PKT_INFO_80211;
+	if (wcid->hw_key_idx == 0xff)
+		dma_flags |= MT_TXD_PKT_INFO_WIV;
+
+	ret = mt76x0_dma_skb_wrap_pkt(skb, ep2dmaq(ep), dma_flags);
+	if (ret)
+		return ret;
+
+	ret = mt76x0_dma_submit_tx(dev, skb, ep);
+
+	if (ret) {
+		ieee80211_free_txskb(dev->mt76.hw, skb);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void mt76x0_kill_rx(struct mt76x0_dev *dev)
+{
+	int i;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->rx_lock, flags);
+
+	for (i = 0; i < dev->rx_q.entries; i++) {
+		int next = dev->rx_q.end;
+
+		spin_unlock_irqrestore(&dev->rx_lock, flags);
+		usb_poison_urb(dev->rx_q.e[next].urb);
+		spin_lock_irqsave(&dev->rx_lock, flags);
+	}
+
+	spin_unlock_irqrestore(&dev->rx_lock, flags);
+}
+
+static int mt76x0_submit_rx_buf(struct mt76x0_dev *dev,
+				 struct mt76x0_dma_buf_rx *e, gfp_t gfp)
+{
+	struct usb_device *usb_dev = mt76x0_to_usb_dev(dev);
+	u8 *buf = page_address(e->p);
+	unsigned pipe;
+	int ret;
+
+	pipe = usb_rcvbulkpipe(usb_dev, dev->in_ep[MT_EP_IN_PKT_RX]);
+
+	usb_fill_bulk_urb(e->urb, usb_dev, pipe, buf, MT_RX_URB_SIZE,
+			  mt76x0_complete_rx, dev);
+
+	trace_mt76x0_submit_urb(&dev->mt76, e->urb);
+	ret = usb_submit_urb(e->urb, gfp);
+	if (ret)
+		dev_err(dev->mt76.dev, "Error: submit RX URB failed:%d\n", ret);
+
+	return ret;
+}
+
+static int mt76x0_submit_rx(struct mt76x0_dev *dev)
+{
+	int i, ret;
+
+	for (i = 0; i < dev->rx_q.entries; i++) {
+		ret = mt76x0_submit_rx_buf(dev, &dev->rx_q.e[i], GFP_KERNEL);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void mt76x0_free_rx(struct mt76x0_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < dev->rx_q.entries; i++) {
+		__free_pages(dev->rx_q.e[i].p, MT_RX_ORDER);
+		usb_free_urb(dev->rx_q.e[i].urb);
+	}
+}
+
+static int mt76x0_alloc_rx(struct mt76x0_dev *dev)
+{
+	int i;
+
+	memset(&dev->rx_q, 0, sizeof(dev->rx_q));
+	dev->rx_q.dev = dev;
+	dev->rx_q.entries = N_RX_ENTRIES;
+
+	for (i = 0; i < N_RX_ENTRIES; i++) {
+		dev->rx_q.e[i].urb = usb_alloc_urb(0, GFP_KERNEL);
+		dev->rx_q.e[i].p = dev_alloc_pages(MT_RX_ORDER);
+
+		if (!dev->rx_q.e[i].urb || !dev->rx_q.e[i].p)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void mt76x0_free_tx_queue(struct mt76x0_tx_queue *q)
+{
+	int i;
+
+	WARN_ON(q->used);
+
+	for (i = 0; i < q->entries; i++)  {
+		usb_poison_urb(q->e[i].urb);
+		usb_free_urb(q->e[i].urb);
+	}
+}
+
+static void mt76x0_free_tx(struct mt76x0_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < __MT_EP_OUT_MAX; i++)
+		mt76x0_free_tx_queue(&dev->tx_q[i]);
+}
+
+static int mt76x0_alloc_tx_queue(struct mt76x0_dev *dev,
+				  struct mt76x0_tx_queue *q)
+{
+	int i;
+
+	q->dev = dev;
+	q->entries = N_TX_ENTRIES;
+
+	for (i = 0; i < N_TX_ENTRIES; i++) {
+		q->e[i].urb = usb_alloc_urb(0, GFP_KERNEL);
+		if (!q->e[i].urb)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int mt76x0_alloc_tx(struct mt76x0_dev *dev)
+{
+	int i;
+
+	dev->tx_q = devm_kcalloc(dev->mt76.dev, __MT_EP_OUT_MAX,
+				 sizeof(*dev->tx_q), GFP_KERNEL);
+
+	for (i = 0; i < __MT_EP_OUT_MAX; i++)
+		if (mt76x0_alloc_tx_queue(dev, &dev->tx_q[i]))
+			return -ENOMEM;
+
+	return 0;
+}
+
+int mt76x0_dma_init(struct mt76x0_dev *dev)
+{
+	int ret = -ENOMEM;
+
+	tasklet_init(&dev->tx_tasklet, mt76x0_tx_tasklet, (unsigned long) dev);
+	tasklet_init(&dev->rx_tasklet, mt76x0_rx_tasklet, (unsigned long) dev);
+
+	ret = mt76x0_alloc_tx(dev);
+	if (ret)
+		goto err;
+	ret = mt76x0_alloc_rx(dev);
+	if (ret)
+		goto err;
+
+	ret = mt76x0_submit_rx(dev);
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	mt76x0_dma_cleanup(dev);
+	return ret;
+}
+
+void mt76x0_dma_cleanup(struct mt76x0_dev *dev)
+{
+	mt76x0_kill_rx(dev);
+
+	tasklet_kill(&dev->rx_tasklet);
+
+	mt76x0_free_rx(dev);
+	mt76x0_free_tx(dev);
+
+	tasklet_kill(&dev->tx_tasklet);
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/dma.h b/drivers/net/wireless/mediatek/mt76/mt76x0/dma.h
new file mode 100644
index 000000000000..891ce1c3461f
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/dma.h
@@ -0,0 +1,126 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __MT76X0U_DMA_H
+#define __MT76X0U_DMA_H
+
+#include <asm/unaligned.h>
+#include <linux/skbuff.h>
+
+#define MT_DMA_HDR_LEN			4
+#define MT_RX_INFO_LEN			4
+#define MT_FCE_INFO_LEN			4
+#define MT_DMA_HDRS			(MT_DMA_HDR_LEN + MT_RX_INFO_LEN)
+
+/* Common Tx DMA descriptor fields */
+#define MT_TXD_INFO_LEN		GENMASK(15, 0)
+#define MT_TXD_INFO_D_PORT	GENMASK(29, 27)
+#define MT_TXD_INFO_TYPE	GENMASK(31, 30)
+
+/* Tx DMA MCU command specific flags */
+#define MT_TXD_CMD_SEQ		GENMASK(19, 16)
+#define MT_TXD_CMD_TYPE		GENMASK(26, 20)
+
+enum mt76_msg_port {
+	WLAN_PORT,
+	CPU_RX_PORT,
+	CPU_TX_PORT,
+	HOST_PORT,
+	VIRTUAL_CPU_RX_PORT,
+	VIRTUAL_CPU_TX_PORT,
+	DISCARD,
+};
+
+enum mt76_info_type {
+	DMA_PACKET,
+	DMA_COMMAND,
+};
+
+/* Tx DMA packet specific flags */
+#define MT_TXD_PKT_INFO_NEXT_VLD	BIT(16)
+#define MT_TXD_PKT_INFO_TX_BURST	BIT(17)
+#define MT_TXD_PKT_INFO_80211		BIT(19)
+#define MT_TXD_PKT_INFO_TSO		BIT(20)
+#define MT_TXD_PKT_INFO_CSO		BIT(21)
+#define MT_TXD_PKT_INFO_WIV		BIT(24)
+#define MT_TXD_PKT_INFO_QSEL		GENMASK(26, 25)
+
+enum mt76_qsel {
+	MT_QSEL_MGMT,
+	MT_QSEL_HCCA,
+	MT_QSEL_EDCA,
+	MT_QSEL_EDCA_2,
+};
+
+
+static inline int mt76x0_dma_skb_wrap(struct sk_buff *skb,
+				       enum mt76_msg_port d_port,
+				       enum mt76_info_type type, u32 flags)
+{
+	u32 info;
+
+	/* Buffer layout:
+	 *	|   4B   | xfer len |      pad       |  4B  |
+	 *	| TXINFO | pkt/cmd  | zero pad to 4B | zero |
+	 *
+	 * length field of TXINFO should be set to 'xfer len'.
+	 */
+
+	info = flags |
+		FIELD_PREP(MT_TXD_INFO_LEN, round_up(skb->len, 4)) |
+		FIELD_PREP(MT_TXD_INFO_D_PORT, d_port) |
+		FIELD_PREP(MT_TXD_INFO_TYPE, type);
+
+	put_unaligned_le32(info, skb_push(skb, sizeof(info)));
+	return skb_put_padto(skb, round_up(skb->len, 4) + 4);
+}
+
+static inline int
+mt76x0_dma_skb_wrap_pkt(struct sk_buff *skb, enum mt76_qsel qsel, u32 flags)
+{
+	flags |= FIELD_PREP(MT_TXD_PKT_INFO_QSEL, qsel);
+	return mt76x0_dma_skb_wrap(skb, WLAN_PORT, DMA_PACKET, flags);
+}
+
+/* Common Rx DMA descriptor fields */
+#define MT_RXD_INFO_LEN			GENMASK(13, 0)
+#define MT_RXD_INFO_PCIE_INTR		BIT(24)
+#define MT_RXD_INFO_QSEL		GENMASK(26, 25)
+#define MT_RXD_INFO_PORT		GENMASK(29, 27)
+#define MT_RXD_INFO_TYPE		GENMASK(31, 30)
+
+/* Rx DMA packet specific flags */
+#define MT_RXD_PKT_INFO_UDP_ERR		BIT(16)
+#define MT_RXD_PKT_INFO_TCP_ERR		BIT(17)
+#define MT_RXD_PKT_INFO_IP_ERR		BIT(18)
+#define MT_RXD_PKT_INFO_PKT_80211	BIT(19)
+#define MT_RXD_PKT_INFO_L3L4_DONE	BIT(20)
+#define MT_RXD_PKT_INFO_MAC_LEN		GENMASK(23, 21)
+
+/* Rx DMA MCU command specific flags */
+#define MT_RXD_CMD_INFO_SELF_GEN	BIT(15)
+#define MT_RXD_CMD_INFO_CMD_SEQ		GENMASK(19, 16)
+#define MT_RXD_CMD_INFO_EVT_TYPE	GENMASK(23, 20)
+
+enum mt76_evt_type {
+	CMD_DONE,
+	CMD_ERROR,
+	CMD_RETRY,
+	EVENT_PWR_RSP,
+	EVENT_WOW_RSP,
+	EVENT_CARRIER_DETECT_RSP,
+	EVENT_DFS_DETECT_RSP,
+};
+
+#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
new file mode 100644
index 000000000000..36da1e6bc21a
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
@@ -0,0 +1,445 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/of.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/etherdevice.h>
+#include <asm/unaligned.h>
+#include "mt76x0.h"
+#include "eeprom.h"
+
+static bool
+field_valid(u8 val)
+{
+	return val != 0xff;
+}
+
+static s8
+field_validate(u8 val)
+{
+	if (!field_valid(val))
+		return 0;
+
+	return val;
+}
+
+static inline int
+sign_extend(u32 val, unsigned int size)
+{
+	bool sign = val & BIT(size - 1);
+
+	val &= BIT(size - 1) - 1;
+
+	return sign ? val : -val;
+}
+
+static int
+mt76x0_efuse_read(struct mt76x0_dev *dev, u16 addr, u8 *data,
+		   enum mt76x0_eeprom_access_modes mode)
+{
+	u32 val;
+	int i;
+
+	val = mt76_rr(dev, MT_EFUSE_CTRL);
+	val &= ~(MT_EFUSE_CTRL_AIN |
+		 MT_EFUSE_CTRL_MODE);
+	val |= FIELD_PREP(MT_EFUSE_CTRL_AIN, addr & ~0xf) |
+	       FIELD_PREP(MT_EFUSE_CTRL_MODE, mode) |
+	       MT_EFUSE_CTRL_KICK;
+	mt76_wr(dev, MT_EFUSE_CTRL, val);
+
+	if (!mt76_poll(dev, MT_EFUSE_CTRL, MT_EFUSE_CTRL_KICK, 0, 1000))
+		return -ETIMEDOUT;
+
+	val = mt76_rr(dev, MT_EFUSE_CTRL);
+	if ((val & MT_EFUSE_CTRL_AOUT) == MT_EFUSE_CTRL_AOUT) {
+		/* Parts of eeprom not in the usage map (0x80-0xc0,0xf0)
+		 * will not return valid data but it's ok.
+		 */
+		memset(data, 0xff, 16);
+		return 0;
+	}
+
+	for (i = 0; i < 4; i++) {
+		val = mt76_rr(dev, MT_EFUSE_DATA(i));
+		put_unaligned_le32(val, data + 4 * i);
+	}
+
+	return 0;
+}
+
+#define MT_MAP_READS	DIV_ROUND_UP(MT_EFUSE_USAGE_MAP_SIZE, 16)
+static int
+mt76x0_efuse_physical_size_check(struct mt76x0_dev *dev)
+{
+	u8 data[MT_MAP_READS * 16];
+	int ret, i;
+	u32 start = 0, end = 0, cnt_free;
+
+	for (i = 0; i < MT_MAP_READS; i++) {
+		ret = mt76x0_efuse_read(dev, MT_EE_USAGE_MAP_START + i * 16,
+					 data + i * 16, MT_EE_PHYSICAL_READ);
+		if (ret)
+			return ret;
+	}
+
+	for (i = 0; i < MT_EFUSE_USAGE_MAP_SIZE; i++)
+		if (!data[i]) {
+			if (!start)
+				start = MT_EE_USAGE_MAP_START + i;
+			end = MT_EE_USAGE_MAP_START + i;
+		}
+	cnt_free = end - start + 1;
+
+	if (MT_EFUSE_USAGE_MAP_SIZE - cnt_free < 5) {
+		dev_err(dev->mt76.dev, "Error: your device needs default EEPROM file and this driver doesn't support it!\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void
+mt76x0_set_chip_cap(struct mt76x0_dev *dev, u8 *eeprom)
+{
+	enum mt76x2_board_type { BOARD_TYPE_2GHZ = 1, BOARD_TYPE_5GHZ = 2 };
+	u16 nic_conf0 = get_unaligned_le16(eeprom + MT_EE_NIC_CONF_0);
+	u16 nic_conf1 = get_unaligned_le16(eeprom + MT_EE_NIC_CONF_1);
+
+	dev_dbg(dev->mt76.dev, "NIC_CONF0: %04x NIC_CONF1: %04x\n", nic_conf0, nic_conf1);
+
+	switch (FIELD_GET(MT_EE_NIC_CONF_0_BOARD_TYPE, nic_conf0)) {
+	case BOARD_TYPE_5GHZ:
+		dev->ee->has_5ghz = true;
+		break;
+	case BOARD_TYPE_2GHZ:
+		dev->ee->has_2ghz = true;
+		break;
+	default:
+		dev->ee->has_2ghz = true;
+		dev->ee->has_5ghz = true;
+		break;
+	}
+
+	dev_dbg(dev->mt76.dev, "Has 2GHZ %d 5GHZ %d\n", dev->ee->has_2ghz, dev->ee->has_5ghz);
+
+	if (!field_valid(nic_conf1 & 0xff))
+		nic_conf1 &= 0xff00;
+
+	if (nic_conf1 & MT_EE_NIC_CONF_1_HW_RF_CTRL)
+		dev_err(dev->mt76.dev,
+			"Error: this driver does not support HW RF ctrl\n");
+
+	if (!field_valid(nic_conf0 >> 8))
+		return;
+
+	if (FIELD_GET(MT_EE_NIC_CONF_0_RX_PATH, nic_conf0) > 1 ||
+	    FIELD_GET(MT_EE_NIC_CONF_0_TX_PATH, nic_conf0) > 1)
+		dev_err(dev->mt76.dev,
+			"Error: device has more than 1 RX/TX stream!\n");
+
+	dev->ee->pa_type = FIELD_GET(MT_EE_NIC_CONF_0_PA_TYPE, nic_conf0);
+	dev_dbg(dev->mt76.dev, "PA Type %d\n", dev->ee->pa_type);
+}
+
+static int
+mt76x0_set_macaddr(struct mt76x0_dev *dev, const u8 *eeprom)
+{
+	const void *src = eeprom + MT_EE_MAC_ADDR;
+
+	ether_addr_copy(dev->macaddr, src);
+
+	if (!is_valid_ether_addr(dev->macaddr)) {
+		eth_random_addr(dev->macaddr);
+		dev_info(dev->mt76.dev,
+			 "Invalid MAC address, using random address %pM\n",
+			 dev->macaddr);
+	}
+
+	mt76_wr(dev, MT_MAC_ADDR_DW0, get_unaligned_le32(dev->macaddr));
+	mt76_wr(dev, MT_MAC_ADDR_DW1, get_unaligned_le16(dev->macaddr + 4) |
+		FIELD_PREP(MT_MAC_ADDR_DW1_U2ME_MASK, 0xff));
+
+	return 0;
+}
+
+static void
+mt76x0_set_temp_offset(struct mt76x0_dev *dev, u8 *eeprom)
+{
+	u8 temp = eeprom[MT_EE_TEMP_OFFSET];
+
+	if (field_valid(temp))
+		dev->ee->temp_off = sign_extend(temp, 8);
+	else
+		dev->ee->temp_off = -10;
+}
+
+static void
+mt76x0_set_country_reg(struct mt76x0_dev *dev, u8 *eeprom)
+{
+	/* Note: - region 31 is not valid for mt76x0 (see rtmp_init.c)
+	 *	 - comments in rtmp_def.h are incorrect (see rt_channel.c)
+	 */
+	static const struct reg_channel_bounds chan_bounds[] = {
+		/* EEPROM country regions 0 - 7 */
+		{  1, 11 },	{  1, 13 },	{ 10,  2 },	{ 10,  4 },
+		{ 14,  1 },	{  1, 14 },	{  3,  7 },	{  5,  9 },
+		/* EEPROM country regions 32 - 33 */
+		{  1, 11 },	{  1, 14 }
+	};
+	u8 val = eeprom[MT_EE_COUNTRY_REGION_2GHZ];
+	int idx = -1;
+
+	dev_dbg(dev->mt76.dev, "REG 2GHZ %u REG 5GHZ %u\n", val, eeprom[MT_EE_COUNTRY_REGION_5GHZ]);
+	if (val < 8)
+		idx = val;
+	if (val > 31 && val < 33)
+		idx = val - 32 + 8;
+
+	if (idx != -1)
+		dev_info(dev->mt76.dev,
+			 "EEPROM country region %02hhx (channels %hhd-%hhd)\n",
+			 val, chan_bounds[idx].start,
+			 chan_bounds[idx].start + chan_bounds[idx].num - 1);
+	else
+		idx = 5; /* channels 1 - 14 */
+
+	dev->ee->reg = chan_bounds[idx];
+
+	/* TODO: country region 33 is special - phy should be set to B-mode
+	 *	 before entering channel 14 (see sta/connect.c)
+	 */
+}
+
+static void
+mt76x0_set_rf_freq_off(struct mt76x0_dev *dev, u8 *eeprom)
+{
+	u8 comp;
+
+	dev->ee->rf_freq_off = field_validate(eeprom[MT_EE_FREQ_OFFSET]);
+	comp = field_validate(eeprom[MT_EE_FREQ_OFFSET_COMPENSATION]);
+
+	if (comp & BIT(7))
+		dev->ee->rf_freq_off -= comp & 0x7f;
+	else
+		dev->ee->rf_freq_off += comp;
+}
+
+static void
+mt76x0_set_lna_gain(struct mt76x0_dev *dev, u8 *eeprom)
+{
+	u8 gain;
+
+	dev->ee->lna_gain_2ghz = eeprom[MT_EE_LNA_GAIN_2GHZ];
+	dev->ee->lna_gain_5ghz[0] = eeprom[MT_EE_LNA_GAIN_5GHZ_0];
+
+	gain = eeprom[MT_EE_LNA_GAIN_5GHZ_1];
+	if (gain == 0xff || gain == 0)
+		dev->ee->lna_gain_5ghz[1] = dev->ee->lna_gain_5ghz[0];
+	else
+		dev->ee->lna_gain_5ghz[1] = gain;
+
+	gain = eeprom[MT_EE_LNA_GAIN_5GHZ_2];
+	if (gain == 0xff || gain == 0)
+		dev->ee->lna_gain_5ghz[2] = dev->ee->lna_gain_5ghz[0];
+	else
+		dev->ee->lna_gain_5ghz[2] = gain;
+}
+
+static void
+mt76x0_set_rssi_offset(struct mt76x0_dev *dev, u8 *eeprom)
+{
+	int i;
+	s8 *rssi_offset = dev->ee->rssi_offset_2ghz;
+
+	for (i = 0; i < 2; i++) {
+		rssi_offset[i] = eeprom[MT_EE_RSSI_OFFSET + i];
+
+		if (rssi_offset[i] < -10 || rssi_offset[i] > 10) {
+			dev_warn(dev->mt76.dev,
+				 "Warning: EEPROM RSSI is invalid %02hhx\n",
+				 rssi_offset[i]);
+			rssi_offset[i] = 0;
+		}
+	}
+
+	rssi_offset = dev->ee->rssi_offset_5ghz;
+
+	for (i = 0; i < 3; i++) {
+		rssi_offset[i] = eeprom[MT_EE_RSSI_OFFSET_5GHZ + i];
+
+		if (rssi_offset[i] < -10 || rssi_offset[i] > 10) {
+			dev_warn(dev->mt76.dev,
+				 "Warning: EEPROM RSSI is invalid %02hhx\n",
+				 rssi_offset[i]);
+			rssi_offset[i] = 0;
+		}
+	}
+}
+
+static u32
+calc_bw40_power_rate(u32 value, int delta)
+{
+	u32 ret = 0;
+	int i, tmp;
+
+	for (i = 0; i < 4; i++) {
+		tmp = s6_to_int((value >> i*8) & 0xff) + delta;
+		ret |= (u32)(int_to_s6(tmp)) << i*8;
+	}
+
+	return ret;
+}
+
+static s8
+get_delta(u8 val)
+{
+	s8 ret;
+
+	if (!field_valid(val) || !(val & BIT(7)))
+		return 0;
+
+	ret = val & 0x1f;
+	if (ret > 8)
+		ret = 8;
+	if (val & BIT(6))
+		ret = -ret;
+
+	return ret;
+}
+
+static void
+mt76x0_set_tx_power_per_rate(struct mt76x0_dev *dev, u8 *eeprom)
+{
+	s8 bw40_delta_2g, bw40_delta_5g;
+	u32 val;
+	int i;
+
+	bw40_delta_2g = get_delta(eeprom[MT_EE_TX_POWER_DELTA_BW40]);
+	bw40_delta_5g = get_delta(eeprom[MT_EE_TX_POWER_DELTA_BW40 + 1]);
+
+	for (i = 0; i < 5; i++) {
+		val = get_unaligned_le32(eeprom + MT_EE_TX_POWER_BYRATE(i));
+
+		/* Skip last 16 bits. */
+		if (i == 4)
+			val &= 0x0000ffff;
+
+		dev->ee->tx_pwr_cfg_2g[i][0] = val;
+		dev->ee->tx_pwr_cfg_2g[i][1] = calc_bw40_power_rate(val, bw40_delta_2g);
+	}
+
+	/* Reading per rate tx power for 5 GHz band is a bit more complex. Note
+	 * we mix 16 bit and 32 bit reads and sometimes do shifts.
+	 */
+	val = get_unaligned_le16(eeprom + 0x120);
+	val <<= 16;
+	dev->ee->tx_pwr_cfg_5g[0][0] = val;
+	dev->ee->tx_pwr_cfg_5g[0][1] = calc_bw40_power_rate(val, bw40_delta_5g);
+
+	val = get_unaligned_le32(eeprom + 0x122);
+	dev->ee->tx_pwr_cfg_5g[1][0] = val;
+	dev->ee->tx_pwr_cfg_5g[1][1] = calc_bw40_power_rate(val, bw40_delta_5g);
+
+	val = get_unaligned_le16(eeprom + 0x126);
+	dev->ee->tx_pwr_cfg_5g[2][0] = val;
+	dev->ee->tx_pwr_cfg_5g[2][1] = calc_bw40_power_rate(val, bw40_delta_5g);
+
+	val = get_unaligned_le16(eeprom + 0xec);
+	val <<= 16;
+	dev->ee->tx_pwr_cfg_5g[3][0] = val;
+	dev->ee->tx_pwr_cfg_5g[3][1] = calc_bw40_power_rate(val, bw40_delta_5g);
+
+	val = get_unaligned_le16(eeprom + 0xee);
+	dev->ee->tx_pwr_cfg_5g[4][0] = val;
+	dev->ee->tx_pwr_cfg_5g[4][1] = calc_bw40_power_rate(val, bw40_delta_5g);
+}
+
+static void
+mt76x0_set_tx_power_per_chan(struct mt76x0_dev *dev, u8 *eeprom)
+{
+	int i;
+	u8 tx_pwr;
+
+	for (i = 0; i < 14; i++) {
+		tx_pwr = eeprom[MT_EE_TX_POWER_OFFSET_2GHZ + i];
+		if (tx_pwr <= 0x3f && tx_pwr > 0)
+			dev->ee->tx_pwr_per_chan[i] = tx_pwr;
+		else
+			dev->ee->tx_pwr_per_chan[i] = 5;
+	}
+
+	for (i = 0; i < 40; i++) {
+		tx_pwr = eeprom[MT_EE_TX_POWER_OFFSET_5GHZ + i];
+		if (tx_pwr <= 0x3f && tx_pwr > 0)
+			dev->ee->tx_pwr_per_chan[14 + i] = tx_pwr;
+		else
+			dev->ee->tx_pwr_per_chan[14 + i] = 5;
+	}
+
+	dev->ee->tx_pwr_per_chan[54] = dev->ee->tx_pwr_per_chan[22];
+	dev->ee->tx_pwr_per_chan[55] = dev->ee->tx_pwr_per_chan[28];
+	dev->ee->tx_pwr_per_chan[56] = dev->ee->tx_pwr_per_chan[34];
+	dev->ee->tx_pwr_per_chan[57] = dev->ee->tx_pwr_per_chan[44];
+}
+
+int
+mt76x0_eeprom_init(struct mt76x0_dev *dev)
+{
+	u8 *eeprom;
+	int i, ret;
+
+	ret = mt76x0_efuse_physical_size_check(dev);
+	if (ret)
+		return ret;
+
+	dev->ee = devm_kzalloc(dev->mt76.dev, sizeof(*dev->ee), GFP_KERNEL);
+	if (!dev->ee)
+		return -ENOMEM;
+
+	eeprom = kmalloc(MT76X0_EEPROM_SIZE, GFP_KERNEL);
+	if (!eeprom)
+		return -ENOMEM;
+
+	for (i = 0; i + 16 <= MT76X0_EEPROM_SIZE; i += 16) {
+		ret = mt76x0_efuse_read(dev, i, eeprom + i, MT_EE_READ);
+		if (ret)
+			goto out;
+	}
+
+	if (eeprom[MT_EE_VERSION_EE] > MT76X0U_EE_MAX_VER)
+		dev_warn(dev->mt76.dev,
+			 "Warning: unsupported EEPROM version %02hhx\n",
+			 eeprom[MT_EE_VERSION_EE]);
+	dev_info(dev->mt76.dev, "EEPROM ver:%02hhx fae:%02hhx\n",
+		 eeprom[MT_EE_VERSION_EE], eeprom[MT_EE_VERSION_FAE]);
+
+	mt76x0_set_macaddr(dev, eeprom);
+	mt76x0_set_chip_cap(dev, eeprom);
+	mt76x0_set_country_reg(dev, eeprom);
+	mt76x0_set_rf_freq_off(dev, eeprom);
+	mt76x0_set_temp_offset(dev, eeprom);
+	mt76x0_set_lna_gain(dev, eeprom);
+	mt76x0_set_rssi_offset(dev, eeprom);
+	dev->chainmask = 0x0101;
+
+	mt76x0_set_tx_power_per_rate(dev, eeprom);
+	mt76x0_set_tx_power_per_chan(dev, eeprom);
+
+out:
+	kfree(eeprom);
+	return ret;
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h
new file mode 100644
index 000000000000..e37b573aed7b
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h
@@ -0,0 +1,149 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __MT76X0U_EEPROM_H
+#define __MT76X0U_EEPROM_H
+
+struct mt76x0_dev;
+
+#define MT76X0U_EE_MAX_VER			0x0c
+#define MT76X0_EEPROM_SIZE			512
+
+#define MT76X0U_DEFAULT_TX_POWER		6
+
+enum mt76_eeprom_field {
+	MT_EE_CHIP_ID =				0x00,
+	MT_EE_VERSION_FAE =			0x02,
+	MT_EE_VERSION_EE =			0x03,
+	MT_EE_MAC_ADDR =			0x04,
+	MT_EE_NIC_CONF_0 =			0x34,
+	MT_EE_NIC_CONF_1 =			0x36,
+	MT_EE_COUNTRY_REGION_5GHZ =		0x38,
+	MT_EE_COUNTRY_REGION_2GHZ =		0x39,
+	MT_EE_FREQ_OFFSET =			0x3a,
+	MT_EE_NIC_CONF_2 =			0x42,
+
+	MT_EE_LNA_GAIN_2GHZ =			0x44,
+	MT_EE_LNA_GAIN_5GHZ_0 =			0x45,
+	MT_EE_RSSI_OFFSET =			0x46,
+	MT_EE_RSSI_OFFSET_5GHZ =		0x4a,
+	MT_EE_LNA_GAIN_5GHZ_1 =			0x49,
+	MT_EE_LNA_GAIN_5GHZ_2 =			0x4d,
+
+	MT_EE_TX_POWER_DELTA_BW40 =		0x50,
+
+	MT_EE_TX_POWER_OFFSET_2GHZ =		0x52,
+
+	MT_EE_TX_TSSI_SLOPE =			0x6e,
+	MT_EE_TX_TSSI_OFFSET_GROUP =		0x6f,
+	MT_EE_TX_TSSI_OFFSET =			0x76,
+
+	MT_EE_TX_POWER_OFFSET_5GHZ =		0x78,
+
+	MT_EE_TEMP_OFFSET =			0xd1,
+	MT_EE_FREQ_OFFSET_COMPENSATION =	0xdb,
+	MT_EE_TX_POWER_BYRATE_BASE =		0xde,
+
+	MT_EE_TX_POWER_BYRATE_BASE_5GHZ =	0x120,
+
+	MT_EE_USAGE_MAP_START =			0x1e0,
+	MT_EE_USAGE_MAP_END =			0x1fc,
+};
+
+#define MT_EE_NIC_CONF_0_RX_PATH		GENMASK(3, 0)
+#define MT_EE_NIC_CONF_0_TX_PATH		GENMASK(7, 4)
+#define MT_EE_NIC_CONF_0_PA_TYPE		GENMASK(9, 8)
+#define MT_EE_NIC_CONF_0_BOARD_TYPE		GENMASK(13, 12)
+
+#define MT_EE_NIC_CONF_1_HW_RF_CTRL		BIT(0)
+#define MT_EE_NIC_CONF_1_TEMP_TX_ALC		BIT(1)
+#define MT_EE_NIC_CONF_1_LNA_EXT_2G		BIT(2)
+#define MT_EE_NIC_CONF_1_LNA_EXT_5G		BIT(3)
+#define MT_EE_NIC_CONF_1_TX_ALC_EN		BIT(13)
+
+#define MT_EE_NIC_CONF_2_RX_STREAM		GENMASK(3, 0)
+#define MT_EE_NIC_CONF_2_TX_STREAM		GENMASK(7, 4)
+#define MT_EE_NIC_CONF_2_HW_ANTDIV		BIT(8)
+#define MT_EE_NIC_CONF_2_XTAL_OPTION		GENMASK(10, 9)
+#define MT_EE_NIC_CONF_2_TEMP_DISABLE		BIT(11)
+#define MT_EE_NIC_CONF_2_COEX_METHOD		GENMASK(15, 13)
+
+#define MT_EE_TX_POWER_BYRATE(i)		(MT_EE_TX_POWER_BYRATE_BASE + \
+						 (i) * 4)
+
+#define MT_EFUSE_USAGE_MAP_SIZE			(MT_EE_USAGE_MAP_END -	\
+						 MT_EE_USAGE_MAP_START + 1)
+
+enum mt76x0_eeprom_access_modes {
+	MT_EE_READ = 0,
+	MT_EE_PHYSICAL_READ = 1,
+};
+
+struct reg_channel_bounds {
+	u8 start;
+	u8 num;
+};
+
+struct mt76x0_eeprom_params {
+	u8 rf_freq_off;
+	s16 temp_off;
+	s8 rssi_offset_2ghz[2];
+	s8 rssi_offset_5ghz[3];
+	s8 lna_gain_2ghz;
+	s8 lna_gain_5ghz[3];
+	u8 pa_type;
+
+	/* TX_PWR_CFG_* values from EEPROM for 20 and 40 Mhz bandwidths. */
+	u32 tx_pwr_cfg_2g[5][2];
+	u32 tx_pwr_cfg_5g[5][2];
+
+	u8 tx_pwr_per_chan[58];
+
+	struct reg_channel_bounds reg;
+
+	bool has_2ghz;
+	bool has_5ghz;
+};
+
+int mt76x0_eeprom_init(struct mt76x0_dev *dev);
+
+static inline u32 s6_validate(u32 reg)
+{
+	WARN_ON(reg & ~GENMASK(5, 0));
+	return reg & GENMASK(5, 0);
+}
+
+static inline int s6_to_int(u32 reg)
+{
+	int s6;
+
+	s6 = s6_validate(reg);
+	if (s6 & BIT(5))
+		s6 -= BIT(6);
+
+	return s6;
+}
+
+static inline u32 int_to_s6(int val)
+{
+	if (val < -0x20)
+		return 0x20;
+	if (val > 0x1f)
+		return 0x1f;
+
+	return val & 0x3f;
+}
+
+#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
new file mode 100644
index 000000000000..7cdb3e740522
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
@@ -0,0 +1,720 @@
+/*
+ * (c) Copyright 2002-2010, Ralink Technology, Inc.
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "mt76x0.h"
+#include "eeprom.h"
+#include "trace.h"
+#include "mcu.h"
+#include "usb.h"
+
+#include "initvals.h"
+
+static void
+mt76x0_set_wlan_state(struct mt76x0_dev *dev, u32 val, bool enable)
+{
+	int i;
+
+	/* Note: we don't turn off WLAN_CLK because that makes the device
+	 *	 not respond properly on the probe path.
+	 *	 In case anyone (PSM?) wants to use this function we can
+	 *	 bring the clock stuff back and fixup the probe path.
+	 */
+
+	if (enable)
+		val |= (MT_WLAN_FUN_CTRL_WLAN_EN |
+			MT_WLAN_FUN_CTRL_WLAN_CLK_EN);
+	else
+		val &= ~(MT_WLAN_FUN_CTRL_WLAN_EN);
+
+	mt76_wr(dev, MT_WLAN_FUN_CTRL, val);
+	udelay(20);
+
+	if (!enable)
+		return;
+
+	for (i = 200; i; i--) {
+		val = mt76_rr(dev, MT_CMB_CTRL);
+
+		if (val & MT_CMB_CTRL_XTAL_RDY && val & MT_CMB_CTRL_PLL_LD)
+			break;
+
+		udelay(20);
+	}
+
+	/* Note: vendor driver tries to disable/enable wlan here and retry
+	 *       but the code which does it is so buggy it must have never
+	 *       triggered, so don't bother.
+	 */
+	if (!i)
+		dev_err(dev->mt76.dev, "Error: PLL and XTAL check failed!\n");
+}
+
+void mt76x0_chip_onoff(struct mt76x0_dev *dev, bool enable, bool reset)
+{
+	u32 val;
+
+	mutex_lock(&dev->hw_atomic_mutex);
+
+	val = mt76_rr(dev, MT_WLAN_FUN_CTRL);
+
+	if (reset) {
+		val |= MT_WLAN_FUN_CTRL_GPIO_OUT_EN;
+		val &= ~MT_WLAN_FUN_CTRL_FRC_WL_ANT_SEL;
+
+		if (val & MT_WLAN_FUN_CTRL_WLAN_EN) {
+			val |= (MT_WLAN_FUN_CTRL_WLAN_RESET |
+				MT_WLAN_FUN_CTRL_WLAN_RESET_RF);
+			mt76_wr(dev, MT_WLAN_FUN_CTRL, val);
+			udelay(20);
+
+			val &= ~(MT_WLAN_FUN_CTRL_WLAN_RESET |
+				 MT_WLAN_FUN_CTRL_WLAN_RESET_RF);
+		}
+	}
+
+	mt76_wr(dev, MT_WLAN_FUN_CTRL, val);
+	udelay(20);
+
+	mt76x0_set_wlan_state(dev, val, enable);
+
+	mutex_unlock(&dev->hw_atomic_mutex);
+}
+
+static void mt76x0_reset_csr_bbp(struct mt76x0_dev *dev)
+{
+	u32 val;
+
+	val = mt76_rr(dev, MT_PBF_SYS_CTRL);
+	val &= ~0x2000;
+	mt76_wr(dev, MT_PBF_SYS_CTRL, val);
+
+	mt76_wr(dev, MT_MAC_SYS_CTRL, MT_MAC_SYS_CTRL_RESET_CSR |
+					 MT_MAC_SYS_CTRL_RESET_BBP);
+
+	msleep(200);
+}
+
+static void mt76x0_init_usb_dma(struct mt76x0_dev *dev)
+{
+	u32 val;
+
+	val = mt76_rr(dev, MT_USB_DMA_CFG);
+
+	val |= FIELD_PREP(MT_USB_DMA_CFG_RX_BULK_AGG_TOUT, MT_USB_AGGR_TIMEOUT) |
+	       FIELD_PREP(MT_USB_DMA_CFG_RX_BULK_AGG_LMT, MT_USB_AGGR_SIZE_LIMIT) |
+	       MT_USB_DMA_CFG_RX_BULK_EN |
+	       MT_USB_DMA_CFG_TX_BULK_EN;
+	if (dev->in_max_packet == 512)
+		val |= MT_USB_DMA_CFG_RX_BULK_AGG_EN;
+	mt76_wr(dev, MT_USB_DMA_CFG, val);
+
+	val = mt76_rr(dev, MT_COM_REG0);
+	if (val & 1)
+		dev_dbg(dev->mt76.dev, "MCU not ready\n");
+
+	val = mt76_rr(dev, MT_USB_DMA_CFG);
+
+	val |= MT_USB_DMA_CFG_RX_DROP_OR_PADDING;
+	mt76_wr(dev, MT_USB_DMA_CFG, val);
+	val &= ~MT_USB_DMA_CFG_RX_DROP_OR_PADDING;
+	mt76_wr(dev, MT_USB_DMA_CFG, val);
+}
+
+#define RANDOM_WRITE(dev, tab) \
+	mt76x0_write_reg_pairs(dev, MT_MCU_MEMMAP_WLAN, tab, ARRAY_SIZE(tab));
+
+static int mt76x0_init_bbp(struct mt76x0_dev *dev)
+{
+	int ret, i;
+
+	ret = mt76x0_wait_bbp_ready(dev);
+	if (ret)
+		return ret;
+
+	RANDOM_WRITE(dev, mt76x0_bbp_init_tab);
+
+	for (i = 0; i < ARRAY_SIZE(mt76x0_bbp_switch_tab); i++) {
+		const struct mt76x0_bbp_switch_item *item = &mt76x0_bbp_switch_tab[i];
+		const struct mt76_reg_pair *pair = &item->reg_pair;
+
+		if (((RF_G_BAND | RF_BW_20) & item->bw_band) == (RF_G_BAND | RF_BW_20))
+			mt76_wr(dev, pair->reg, pair->value);
+	}
+
+	RANDOM_WRITE(dev, mt76x0_dcoc_tab);
+
+	return 0;
+}
+
+static void
+mt76_init_beacon_offsets(struct mt76x0_dev *dev)
+{
+	u16 base = MT_BEACON_BASE;
+	u32 regs[4] = {};
+	int i;
+
+	for (i = 0; i < 16; i++) {
+		u16 addr = dev->beacon_offsets[i];
+
+		regs[i / 4] |= ((addr - base) / 64) << (8 * (i % 4));
+	}
+
+	for (i = 0; i < 4; i++)
+		mt76_wr(dev, MT_BCN_OFFSET(i), regs[i]);
+}
+
+static void mt76x0_init_mac_registers(struct mt76x0_dev *dev)
+{
+	u32 reg;
+
+	RANDOM_WRITE(dev, common_mac_reg_table);
+
+	mt76_init_beacon_offsets(dev);
+
+	/* Enable PBF and MAC clock SYS_CTRL[11:10] = 0x3 */
+	RANDOM_WRITE(dev, mt76x0_mac_reg_table);
+
+	/* Release BBP and MAC reset MAC_SYS_CTRL[1:0] = 0x0 */
+	reg = mt76_rr(dev, MT_MAC_SYS_CTRL);
+	reg &= ~0x3;
+	mt76_wr(dev, MT_MAC_SYS_CTRL, reg);
+
+	if (is_mt7610e(dev)) {
+		/* Disable COEX_EN */
+		reg = mt76_rr(dev, MT_COEXCFG0);
+		reg &= 0xFFFFFFFE;
+		mt76_wr(dev, MT_COEXCFG0, reg);
+	}
+
+	/* Set 0x141C[15:12]=0xF */
+	reg = mt76_rr(dev, MT_EXT_CCA_CFG);
+	reg |= 0x0000F000;
+	mt76_wr(dev, MT_EXT_CCA_CFG, reg);
+
+	mt76_clear(dev, MT_FCE_L2_STUFF, MT_FCE_L2_STUFF_WR_MPDU_LEN_EN);
+
+	/*
+		TxRing 9 is for Mgmt frame.
+		TxRing 8 is for In-band command frame.
+		WMM_RG0_TXQMA: This register setting is for FCE to define the rule of TxRing 9.
+		WMM_RG1_TXQMA: This register setting is for FCE to define the rule of TxRing 8.
+	*/
+	reg = mt76_rr(dev, MT_WMM_CTRL);
+	reg &= ~0x000003FF;
+	reg |= 0x00000201;
+	mt76_wr(dev, MT_WMM_CTRL, reg);
+
+	/* TODO: Probably not needed */
+	mt76_wr(dev, 0x7028, 0);
+	mt76_wr(dev, 0x7010, 0);
+	mt76_wr(dev, 0x7024, 0);
+	msleep(10);
+}
+
+static int mt76x0_init_wcid_mem(struct mt76x0_dev *dev)
+{
+	u32 *vals;
+	int i, ret;
+
+	vals = kmalloc(sizeof(*vals) * N_WCIDS * 2, GFP_KERNEL);
+	if (!vals)
+		return -ENOMEM;
+
+	for (i = 0; i < N_WCIDS; i++)  {
+		vals[i * 2] = 0xffffffff;
+		vals[i * 2 + 1] = 0x00ffffff;
+	}
+
+	ret = mt76x0_burst_write_regs(dev, MT_WCID_ADDR_BASE,
+				      vals, N_WCIDS * 2);
+	kfree(vals);
+
+	return ret;
+}
+
+static int mt76x0_init_key_mem(struct mt76x0_dev *dev)
+{
+	u32 vals[4] = {};
+
+	return mt76x0_burst_write_regs(dev, MT_SKEY_MODE_BASE_0,
+					vals, ARRAY_SIZE(vals));
+}
+
+static int mt76x0_init_wcid_attr_mem(struct mt76x0_dev *dev)
+{
+	u32 *vals;
+	int i, ret;
+
+	vals = kmalloc(sizeof(*vals) * N_WCIDS * 2, GFP_KERNEL);
+	if (!vals)
+		return -ENOMEM;
+
+	for (i = 0; i < N_WCIDS * 2; i++)
+		vals[i] = 1;
+
+	ret = mt76x0_burst_write_regs(dev, MT_WCID_ATTR_BASE,
+				      vals, N_WCIDS * 2);
+	kfree(vals);
+
+	return ret;
+}
+
+static void mt76x0_reset_counters(struct mt76x0_dev *dev)
+{
+	mt76_rr(dev, MT_RX_STA_CNT0);
+	mt76_rr(dev, MT_RX_STA_CNT1);
+	mt76_rr(dev, MT_RX_STA_CNT2);
+	mt76_rr(dev, MT_TX_STA_CNT0);
+	mt76_rr(dev, MT_TX_STA_CNT1);
+	mt76_rr(dev, MT_TX_STA_CNT2);
+}
+
+int mt76x0_mac_start(struct mt76x0_dev *dev)
+{
+	mt76_wr(dev, MT_MAC_SYS_CTRL, MT_MAC_SYS_CTRL_ENABLE_TX);
+
+	if (!mt76_poll(dev, MT_WPDMA_GLO_CFG, MT_WPDMA_GLO_CFG_TX_DMA_BUSY |
+		       MT_WPDMA_GLO_CFG_RX_DMA_BUSY, 0, 200000))
+		return -ETIMEDOUT;
+
+	dev->rxfilter = MT_RX_FILTR_CFG_CRC_ERR |
+		MT_RX_FILTR_CFG_PHY_ERR | MT_RX_FILTR_CFG_PROMISC |
+		MT_RX_FILTR_CFG_VER_ERR | MT_RX_FILTR_CFG_DUP |
+		MT_RX_FILTR_CFG_CFACK | MT_RX_FILTR_CFG_CFEND |
+		MT_RX_FILTR_CFG_ACK | MT_RX_FILTR_CFG_CTS |
+		MT_RX_FILTR_CFG_RTS | MT_RX_FILTR_CFG_PSPOLL |
+		MT_RX_FILTR_CFG_BA | MT_RX_FILTR_CFG_CTRL_RSV;
+	mt76_wr(dev, MT_RX_FILTR_CFG, dev->rxfilter);
+
+	mt76_wr(dev, MT_MAC_SYS_CTRL,
+		   MT_MAC_SYS_CTRL_ENABLE_TX | MT_MAC_SYS_CTRL_ENABLE_RX);
+
+	if (!mt76_poll(dev, MT_WPDMA_GLO_CFG, MT_WPDMA_GLO_CFG_TX_DMA_BUSY |
+		       MT_WPDMA_GLO_CFG_RX_DMA_BUSY, 0, 50))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static void mt76x0_mac_stop_hw(struct mt76x0_dev *dev)
+{
+	int i, ok;
+
+	if (test_bit(MT76_REMOVED, &dev->mt76.state))
+		return;
+
+	mt76_clear(dev, MT_BEACON_TIME_CFG, MT_BEACON_TIME_CFG_TIMER_EN |
+		   MT_BEACON_TIME_CFG_SYNC_MODE | MT_BEACON_TIME_CFG_TBTT_EN |
+		   MT_BEACON_TIME_CFG_BEACON_TX);
+
+	if (!mt76_poll(dev, MT_USB_DMA_CFG, MT_USB_DMA_CFG_TX_BUSY, 0, 1000))
+		dev_warn(dev->mt76.dev, "Warning: TX DMA did not stop!\n");
+
+	/* Page count on TxQ */
+	i = 200;
+	while (i-- && ((mt76_rr(dev, 0x0438) & 0xffffffff) ||
+		       (mt76_rr(dev, 0x0a30) & 0x000000ff) ||
+		       (mt76_rr(dev, 0x0a34) & 0x00ff00ff)))
+		msleep(10);
+
+	if (!mt76_poll(dev, MT_MAC_STATUS, MT_MAC_STATUS_TX, 0, 1000))
+		dev_warn(dev->mt76.dev, "Warning: MAC TX did not stop!\n");
+
+	mt76_clear(dev, MT_MAC_SYS_CTRL, MT_MAC_SYS_CTRL_ENABLE_RX |
+					 MT_MAC_SYS_CTRL_ENABLE_TX);
+
+	/* Page count on RxQ */
+	ok = 0;
+	i = 200;
+	while (i--) {
+		if (!(mt76_rr(dev, MT_RXQ_STA) & 0x00ff0000) &&
+		    !mt76_rr(dev, 0x0a30) &&
+		    !mt76_rr(dev, 0x0a34)) {
+			if (ok++ > 5)
+				break;
+			continue;
+		}
+		msleep(1);
+	}
+
+	if (!mt76_poll(dev, MT_MAC_STATUS, MT_MAC_STATUS_RX, 0, 1000))
+		dev_warn(dev->mt76.dev, "Warning: MAC RX did not stop!\n");
+
+	if (!mt76_poll(dev, MT_USB_DMA_CFG, MT_USB_DMA_CFG_RX_BUSY, 0, 1000))
+		dev_warn(dev->mt76.dev, "Warning: RX DMA did not stop!\n");
+}
+
+void mt76x0_mac_stop(struct mt76x0_dev *dev)
+{
+	mt76x0_mac_stop_hw(dev);
+	flush_delayed_work(&dev->stat_work);
+	cancel_delayed_work_sync(&dev->stat_work);
+}
+
+static void mt76x0_stop_hardware(struct mt76x0_dev *dev)
+{
+	mt76x0_chip_onoff(dev, false, false);
+}
+
+int mt76x0_init_hardware(struct mt76x0_dev *dev)
+{
+	static const u16 beacon_offsets[16] = {
+		/* 512 byte per beacon */
+		0xc000,	0xc200,	0xc400,	0xc600,
+		0xc800,	0xca00,	0xcc00,	0xce00,
+		0xd000,	0xd200,	0xd400,	0xd600,
+		0xd800,	0xda00,	0xdc00,	0xde00
+	};
+	int ret;
+
+	dev->beacon_offsets = beacon_offsets;
+
+	mt76x0_chip_onoff(dev, true, true);
+
+	ret = mt76x0_wait_asic_ready(dev);
+	if (ret)
+		goto err;
+	ret = mt76x0_mcu_init(dev);
+	if (ret)
+		goto err;
+
+	if (!mt76_poll_msec(dev, MT_WPDMA_GLO_CFG,
+			    MT_WPDMA_GLO_CFG_TX_DMA_BUSY |
+			    MT_WPDMA_GLO_CFG_RX_DMA_BUSY, 0, 100)) {
+		ret = -EIO;
+		goto err;
+	}
+
+	/* Wait for ASIC ready after FW load. */
+	ret = mt76x0_wait_asic_ready(dev);
+	if (ret)
+		goto err;
+
+	mt76x0_reset_csr_bbp(dev);
+	mt76x0_init_usb_dma(dev);
+
+	mt76_wr(dev, MT_HEADER_TRANS_CTRL_REG, 0x0);
+	mt76_wr(dev, MT_TSO_CTRL, 0x0);
+
+	ret = mt76x0_mcu_cmd_init(dev);
+	if (ret)
+		goto err;
+	ret = mt76x0_dma_init(dev);
+	if (ret)
+		goto err_mcu;
+
+	mt76x0_init_mac_registers(dev);
+
+	if (!mt76_poll_msec(dev, MT_MAC_STATUS,
+			    MT_MAC_STATUS_TX | MT_MAC_STATUS_RX, 0, 1000)) {
+		ret = -EIO;
+		goto err_rx;
+	}
+
+	ret = mt76x0_init_bbp(dev);
+	if (ret)
+		goto err_rx;
+
+	ret = mt76x0_init_wcid_mem(dev);
+	if (ret)
+		goto err_rx;
+	ret = mt76x0_init_key_mem(dev);
+	if (ret)
+		goto err_rx;
+	ret = mt76x0_init_wcid_attr_mem(dev);
+	if (ret)
+		goto err_rx;
+
+	mt76_clear(dev, MT_BEACON_TIME_CFG, (MT_BEACON_TIME_CFG_TIMER_EN |
+					     MT_BEACON_TIME_CFG_SYNC_MODE |
+					     MT_BEACON_TIME_CFG_TBTT_EN |
+					     MT_BEACON_TIME_CFG_BEACON_TX));
+
+	mt76x0_reset_counters(dev);
+
+	mt76_rmw(dev, MT_US_CYC_CFG, MT_US_CYC_CNT, 0x1e);
+
+	mt76_wr(dev, MT_TXOP_CTRL_CFG,
+		   FIELD_PREP(MT_TXOP_TRUN_EN, 0x3f) |
+		   FIELD_PREP(MT_TXOP_EXT_CCA_DLY, 0x58));
+
+	ret = mt76x0_eeprom_init(dev);
+	if (ret)
+		goto err_rx;
+
+	mt76x0_phy_init(dev);
+	return 0;
+
+err_rx:
+	mt76x0_dma_cleanup(dev);
+err_mcu:
+	mt76x0_mcu_cmd_deinit(dev);
+err:
+	mt76x0_chip_onoff(dev, false, false);
+	return ret;
+}
+
+void mt76x0_cleanup(struct mt76x0_dev *dev)
+{
+	if (!test_and_clear_bit(MT76_STATE_INITIALIZED, &dev->mt76.state))
+		return;
+
+	mt76x0_stop_hardware(dev);
+	mt76x0_dma_cleanup(dev);
+	mt76x0_mcu_cmd_deinit(dev);
+}
+
+struct mt76x0_dev *mt76x0_alloc_device(struct device *pdev)
+{
+	struct ieee80211_hw *hw;
+	struct mt76x0_dev *dev;
+
+	hw = ieee80211_alloc_hw(sizeof(*dev), &mt76x0_ops);
+	if (!hw)
+		return NULL;
+
+	dev = hw->priv;
+	dev->mt76.dev = pdev;
+	dev->mt76.hw = hw;
+	mutex_init(&dev->usb_ctrl_mtx);
+	mutex_init(&dev->reg_atomic_mutex);
+	mutex_init(&dev->hw_atomic_mutex);
+	mutex_init(&dev->mutex);
+	spin_lock_init(&dev->tx_lock);
+	spin_lock_init(&dev->rx_lock);
+	spin_lock_init(&dev->mt76.lock);
+	spin_lock_init(&dev->mac_lock);
+	spin_lock_init(&dev->con_mon_lock);
+	atomic_set(&dev->avg_ampdu_len, 1);
+	skb_queue_head_init(&dev->tx_skb_done);
+
+	dev->stat_wq = alloc_workqueue("mt76x0", WQ_UNBOUND, 0);
+	if (!dev->stat_wq) {
+		ieee80211_free_hw(hw);
+		return NULL;
+	}
+
+	return dev;
+}
+
+#define CHAN2G(_idx, _freq) {			\
+	.band = NL80211_BAND_2GHZ,		\
+	.center_freq = (_freq),			\
+	.hw_value = (_idx),			\
+	.max_power = 30,			\
+}
+
+static const struct ieee80211_channel mt76_channels_2ghz[] = {
+	CHAN2G(1, 2412),
+	CHAN2G(2, 2417),
+	CHAN2G(3, 2422),
+	CHAN2G(4, 2427),
+	CHAN2G(5, 2432),
+	CHAN2G(6, 2437),
+	CHAN2G(7, 2442),
+	CHAN2G(8, 2447),
+	CHAN2G(9, 2452),
+	CHAN2G(10, 2457),
+	CHAN2G(11, 2462),
+	CHAN2G(12, 2467),
+	CHAN2G(13, 2472),
+	CHAN2G(14, 2484),
+};
+
+#define CHAN5G(_idx, _freq) {			\
+	.band = NL80211_BAND_5GHZ,		\
+	.center_freq = (_freq),			\
+	.hw_value = (_idx),			\
+	.max_power = 30,			\
+}
+
+static const struct ieee80211_channel mt76_channels_5ghz[] = {
+	CHAN5G(36, 5180),
+	CHAN5G(40, 5200),
+	CHAN5G(44, 5220),
+	CHAN5G(46, 5230),
+	CHAN5G(48, 5240),
+	CHAN5G(52, 5260),
+	CHAN5G(56, 5280),
+	CHAN5G(60, 5300),
+	CHAN5G(64, 5320),
+
+	CHAN5G(100, 5500),
+	CHAN5G(104, 5520),
+	CHAN5G(108, 5540),
+	CHAN5G(112, 5560),
+	CHAN5G(116, 5580),
+	CHAN5G(120, 5600),
+	CHAN5G(124, 5620),
+	CHAN5G(128, 5640),
+	CHAN5G(132, 5660),
+	CHAN5G(136, 5680),
+	CHAN5G(140, 5700),
+};
+
+#define CCK_RATE(_idx, _rate) {					\
+	.bitrate = _rate,					\
+	.flags = IEEE80211_RATE_SHORT_PREAMBLE,			\
+	.hw_value = (MT_PHY_TYPE_CCK << 8) | _idx,		\
+	.hw_value_short = (MT_PHY_TYPE_CCK << 8) | (8 + _idx),	\
+}
+
+#define OFDM_RATE(_idx, _rate) {				\
+	.bitrate = _rate,					\
+	.hw_value = (MT_PHY_TYPE_OFDM << 8) | _idx,		\
+	.hw_value_short = (MT_PHY_TYPE_OFDM << 8) | _idx,	\
+}
+
+static struct ieee80211_rate mt76_rates[] = {
+	CCK_RATE(0, 10),
+	CCK_RATE(1, 20),
+	CCK_RATE(2, 55),
+	CCK_RATE(3, 110),
+	OFDM_RATE(0, 60),
+	OFDM_RATE(1, 90),
+	OFDM_RATE(2, 120),
+	OFDM_RATE(3, 180),
+	OFDM_RATE(4, 240),
+	OFDM_RATE(5, 360),
+	OFDM_RATE(6, 480),
+	OFDM_RATE(7, 540),
+};
+
+static int
+mt76_init_sband(struct mt76x0_dev *dev, struct ieee80211_supported_band *sband,
+		const struct ieee80211_channel *chan, int n_chan,
+		struct ieee80211_rate *rates, int n_rates)
+{
+	struct ieee80211_sta_ht_cap *ht_cap;
+	void *chanlist;
+	int size;
+
+	size = n_chan * sizeof(*chan);
+	chanlist = devm_kmemdup(dev->mt76.dev, chan, size, GFP_KERNEL);
+	if (!chanlist)
+		return -ENOMEM;
+
+	sband->channels = chanlist;
+	sband->n_channels = n_chan;
+	sband->bitrates = rates;
+	sband->n_bitrates = n_rates;
+
+	ht_cap = &sband->ht_cap;
+	ht_cap->ht_supported = true;
+	ht_cap->cap = IEEE80211_HT_CAP_SUP_WIDTH_20_40 |
+		      IEEE80211_HT_CAP_GRN_FLD |
+		      IEEE80211_HT_CAP_SGI_20 |
+		      IEEE80211_HT_CAP_SGI_40 |
+		      (1 << IEEE80211_HT_CAP_RX_STBC_SHIFT);
+
+	ht_cap->mcs.rx_mask[0] = 0xff;
+	ht_cap->mcs.rx_mask[4] = 0x1;
+	ht_cap->mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED;
+	ht_cap->ampdu_factor = IEEE80211_HT_MAX_AMPDU_64K;
+	ht_cap->ampdu_density = IEEE80211_HT_MPDU_DENSITY_2;
+
+	return 0;
+}
+
+static int
+mt76_init_sband_2g(struct mt76x0_dev *dev)
+{
+	dev->mt76.hw->wiphy->bands[NL80211_BAND_2GHZ] = &dev->mt76.sband_2g.sband;
+
+	WARN_ON(dev->ee->reg.start - 1 + dev->ee->reg.num >
+		ARRAY_SIZE(mt76_channels_2ghz));
+
+
+	return mt76_init_sband(dev, &dev->mt76.sband_2g.sband,
+			       mt76_channels_2ghz, ARRAY_SIZE(mt76_channels_2ghz),
+			       mt76_rates, ARRAY_SIZE(mt76_rates));
+}
+
+static int
+mt76_init_sband_5g(struct mt76x0_dev *dev)
+{
+	dev->mt76.hw->wiphy->bands[NL80211_BAND_5GHZ] = &dev->mt76.sband_5g.sband;
+
+	return mt76_init_sband(dev, &dev->mt76.sband_5g.sband,
+			       mt76_channels_5ghz, ARRAY_SIZE(mt76_channels_5ghz),
+			       mt76_rates + 4, ARRAY_SIZE(mt76_rates) - 4);
+}
+
+
+int mt76x0_register_device(struct mt76x0_dev *dev)
+{
+	struct ieee80211_hw *hw = dev->mt76.hw;
+	struct wiphy *wiphy = hw->wiphy;
+	int ret;
+
+	/* Reserve WCID 0 for mcast - thanks to this APs WCID will go to
+	 * entry no. 1 like it does in the vendor driver.
+	 */
+	dev->wcid_mask[0] |= 1;
+
+	/* init fake wcid for monitor interfaces */
+	dev->mon_wcid = devm_kmalloc(dev->mt76.dev, sizeof(*dev->mon_wcid),
+				     GFP_KERNEL);
+	if (!dev->mon_wcid)
+		return -ENOMEM;
+	dev->mon_wcid->idx = 0xff;
+	dev->mon_wcid->hw_key_idx = -1;
+
+	SET_IEEE80211_DEV(hw, dev->mt76.dev);
+
+	hw->queues = 4;
+	ieee80211_hw_set(hw, SIGNAL_DBM);
+	ieee80211_hw_set(hw, PS_NULLFUNC_STACK);
+	ieee80211_hw_set(hw, SUPPORTS_HT_CCK_RATES);
+	ieee80211_hw_set(hw, AMPDU_AGGREGATION);
+	ieee80211_hw_set(hw, SUPPORTS_RC_TABLE);
+	hw->max_rates = 1;
+	hw->max_report_rates = 7;
+	hw->max_rate_tries = 1;
+
+	hw->sta_data_size = sizeof(struct mt76_sta);
+	hw->vif_data_size = sizeof(struct mt76_vif);
+
+	SET_IEEE80211_PERM_ADDR(hw, dev->macaddr);
+
+	wiphy->features |= NL80211_FEATURE_ACTIVE_MONITOR;
+	wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION);
+
+	if (dev->ee->has_2ghz) {
+		ret = mt76_init_sband_2g(dev);
+		if (ret)
+			return ret;
+	}
+
+	if (dev->ee->has_5ghz) {
+		ret = mt76_init_sband_5g(dev);
+		if (ret)
+			return ret;
+	}
+
+	dev->mt76.chandef.chan = &dev->mt76.sband_2g.sband.channels[0];
+
+	INIT_DELAYED_WORK(&dev->mac_work, mt76x0_mac_work);
+	INIT_DELAYED_WORK(&dev->stat_work, mt76x0_tx_stat);
+
+	ret = ieee80211_register_hw(hw);
+	if (ret)
+		return ret;
+
+	mt76x0_init_debugfs(dev);
+
+	return 0;
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h
new file mode 100644
index 000000000000..24afcfd94b4e
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h
@@ -0,0 +1,282 @@
+/*
+ * (c) Copyright 2002-2010, Ralink Technology, Inc.
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __MT76X0U_INITVALS_H
+#define __MT76X0U_INITVALS_H
+
+#include "phy.h"
+
+static const struct mt76_reg_pair common_mac_reg_table[] = {
+#if 1
+	{MT_BCN_OFFSET(0),			0xf8f0e8e0}, /* 0x3800(e0), 0x3A00(e8), 0x3C00(f0), 0x3E00(f8), 512B for each beacon */
+	{MT_BCN_OFFSET(1),			0x6f77d0c8}, /* 0x3200(c8), 0x3400(d0), 0x1DC0(77), 0x1BC0(6f), 512B for each beacon */
+#endif
+
+	{MT_LEGACY_BASIC_RATE,		0x0000013f}, /*  Basic rate set bitmap*/
+	{MT_HT_BASIC_RATE,		0x00008003}, /* Basic HT rate set , 20M, MCS=3, MM. Format is the same as in TXWI.*/
+	{MT_MAC_SYS_CTRL,		0x00}, /* 0x1004, , default Disable RX*/
+	{MT_RX_FILTR_CFG,		0x17f97}, /*0x1400  , RX filter control,  */
+	{MT_BKOFF_SLOT_CFG,	0x209}, /* default set short slot time, CC_DELAY_TIME should be 2	 */
+	/*{TX_SW_CFG0,		0x40a06},  Gary,2006-08-23 */
+	{MT_TX_SW_CFG0,		0x0}, 		/* Gary,2008-05-21 for CWC test */
+	{MT_TX_SW_CFG1,		0x80606}, /* Gary,2006-08-23 */
+	{MT_TX_LINK_CFG,		0x1020},		/* Gary,2006-08-23 */
+	/*{TX_TIMEOUT_CFG,	0x00182090},	 CCK has some problem. So increase timieout value. 2006-10-09 MArvek RT*/
+	{MT_TX_TIMEOUT_CFG,	0x000a2090},	/* CCK has some problem. So increase timieout value. 2006-10-09 MArvek RT , Modify for 2860E ,2007-08-01*/
+	{MT_MAX_LEN_CFG,		0xa0fff | 0x00001000},	/* 0x3018, MAX frame length. Max PSDU = 16kbytes.*/
+	{MT_LED_CFG,		0x7f031e46}, /* Gary, 2006-08-23*/
+
+	{MT_PBF_TX_MAX_PCNT,		0x1fbf1f1f /*0xbfbf3f1f*/},
+	{MT_PBF_RX_MAX_PCNT,		0x9f},
+
+	/*{TX_RTY_CFG,			0x6bb80408},	 Jan, 2006/11/16*/
+/* WMM_ACM_SUPPORT */
+/*	{TX_RTY_CFG,			0x6bb80101},	 sample*/
+	{MT_TX_RETRY_CFG,			0x47d01f0f},	/* Jan, 2006/11/16, Set TxWI->ACK =0 in Probe Rsp Modify for 2860E ,2007-08-03*/
+
+	{MT_AUTO_RSP_CFG,			0x00000013},	/* Initial Auto_Responder, because QA will turn off Auto-Responder*/
+	{MT_CCK_PROT_CFG,			0x05740003 /*0x01740003*/},	/* Initial Auto_Responder, because QA will turn off Auto-Responder. And RTS threshold is enabled. */
+	{MT_OFDM_PROT_CFG,			0x05740003 /*0x01740003*/},	/* Initial Auto_Responder, because QA will turn off Auto-Responder. And RTS threshold is enabled. */
+	{MT_PBF_CFG, 				0xf40006}, 		/* Only enable Queue 2*/
+	{MT_MM40_PROT_CFG,			0x3F44084},		/* Initial Auto_Responder, because QA will turn off Auto-Responder*/
+	{MT_WPDMA_GLO_CFG,			0x00000030},
+	{MT_GF20_PROT_CFG,			0x01744004},    /* set 19:18 --> Short NAV for MIMO PS*/
+	{MT_GF40_PROT_CFG,			0x03F44084},
+	{MT_MM20_PROT_CFG,			0x01744004},
+	{MT_TXOP_CTRL_CFG,			0x0000583f, /*0x0000243f*/ /*0x000024bf*/},	/*Extension channel backoff.*/
+	{MT_TX_RTS_CFG,			0x00092b20},
+
+	{MT_EXP_ACK_TIME,			0x002400ca},	/* default value */
+	{MT_TXOP_HLDR_ET, 			0x00000002},
+
+	/* Jerry comments 2008/01/16: we use SIFS = 10us in CCK defaultly, but it seems that 10us
+		is too small for INTEL 2200bg card, so in MBSS mode, the delta time between beacon0
+		and beacon1 is SIFS (10us), so if INTEL 2200bg card connects to BSS0, the ping
+		will always lost. So we change the SIFS of CCK from 10us to 16us. */
+	{MT_XIFS_TIME_CFG,			0x33a41010},
+	{MT_PWR_PIN_CFG,			0x00000000},
+};
+
+static const struct mt76_reg_pair mt76x0_mac_reg_table[] = {
+	/* {MT_IOCFG_6,		0xA0040080 }, */
+	{MT_PBF_SYS_CTRL,	0x00080c00 },
+	{MT_PBF_CFG,		0x77723c1f },
+	{MT_FCE_PSE_CTRL,	0x00000001 },
+
+	{MT_AMPDU_MAX_LEN_20M1S,	0xBAA99887 },
+
+	/* Delay bb_tx_pe for proper tx_mcs_pwr update */
+	{MT_TX_SW_CFG0,		0x00000601 },
+
+	/* Set rf_tx_pe deassert time to 1us by Chee's comment @MT7650_CR_setting_1018.xlsx */
+	{MT_TX_SW_CFG1,		0x00040000 },
+	{MT_TX_SW_CFG2,		0x00000000 },
+
+	/* disable Tx info report */
+	{0xa44,		0x0000000 },
+
+	{MT_HEADER_TRANS_CTRL_REG, 0x0},
+	{MT_TSO_CTRL,		0x0},
+
+	/* BB_PA_MODE_CFG0(0x1214) Keep default value @20120903 */
+	{MT_BB_PA_MODE_CFG1,	0x00500055},
+
+	/* RF_PA_MODE_CFG0(0x121C) Keep default value @20120903 */
+	{MT_RF_PA_MODE_CFG1,	0x00500055},
+
+	{MT_TX_ALC_CFG_0,	0x2F2F000C},
+	{MT_TX0_BB_GAIN_ATTEN,  0x00000000}, /* set BBP atten gain = 0 */
+
+	{MT_TX_PWR_CFG_0, 0x3A3A3A3A},
+	{MT_TX_PWR_CFG_1, 0x3A3A3A3A},
+	{MT_TX_PWR_CFG_2, 0x3A3A3A3A},
+	{MT_TX_PWR_CFG_3, 0x3A3A3A3A},
+	{MT_TX_PWR_CFG_4, 0x3A3A3A3A},
+	{MT_TX_PWR_CFG_7, 0x3A3A3A3A},
+	{MT_TX_PWR_CFG_8, 0x3A},
+	{MT_TX_PWR_CFG_9, 0x3A},
+	/* Enable Tx length > 4095 byte */
+	{0x150C,		0x00000002},
+
+	/* Disable bt_abort_tx_en(0x1238[21] = 0) which is not used at MT7650 */
+	{0x1238, 		0x001700C8},
+	/* PMU_OCLEVEL<5:1> from default <5'b10010> to <5'b11011> for normal driver */
+	/* {MT_LDO_CTRL_0,		0x00A647B6}, */
+
+	/* Default LDO_DIG supply 1.26V, change to 1.2V */
+	{MT_LDO_CTRL_1,		0x6B006464 },
+/*
+	{MT_HT_BASIC_RATE,	0x00004003 },
+	{MT_HT_CTRL_CFG,	0x000001FF },
+*/
+};
+
+
+static const struct mt76_reg_pair mt76x0_bbp_init_tab[] = {
+	{MT_BBP(CORE, 1), 0x00000002},
+	{MT_BBP(CORE, 4), 0x00000000},
+	{MT_BBP(CORE, 24), 0x00000000},
+	{MT_BBP(CORE, 32), 0x4003000a},
+	{MT_BBP(CORE, 42), 0x00000000},
+	{MT_BBP(CORE, 44), 0x00000000},
+
+	{MT_BBP(IBI, 11), 0x00000080},
+
+	/*
+		0x2300[5] Default Antenna:
+		0 for WIFI main antenna
+		1 for WIFI aux  antenna
+
+	*/
+	{MT_BBP(AGC, 0), 0x00021400},
+	{MT_BBP(AGC, 1), 0x00000003},
+	{MT_BBP(AGC, 2), 0x003A6464},
+	{MT_BBP(AGC, 15), 0x88A28CB8},
+	{MT_BBP(AGC, 22), 0x00001E21},
+	{MT_BBP(AGC, 23), 0x0000272C},
+	{MT_BBP(AGC, 24), 0x00002F3A},
+	{MT_BBP(AGC, 25), 0x8000005A},
+	{MT_BBP(AGC, 26), 0x007C2005},
+	{MT_BBP(AGC, 34), 0x000A0C0C},
+	{MT_BBP(AGC, 37), 0x2121262C},
+	{MT_BBP(AGC, 41), 0x38383E45},
+	{MT_BBP(AGC, 57), 0x00001010},
+	{MT_BBP(AGC, 59), 0xBAA20E96},
+	{MT_BBP(AGC, 63), 0x00000001},
+
+	{MT_BBP(TXC, 0), 0x00280403},
+	{MT_BBP(TXC, 1), 0x00000000},
+
+	{MT_BBP(RXC, 1), 0x00000012},
+	{MT_BBP(RXC, 2), 0x00000011},
+	{MT_BBP(RXC, 3), 0x00000005},
+	{MT_BBP(RXC, 4), 0x00000000},
+	{MT_BBP(RXC, 5), 0xF977C4EC},
+	{MT_BBP(RXC, 7), 0x00000090},
+
+	{MT_BBP(TXO, 8), 0x00000000},
+
+	{MT_BBP(TXBE, 0), 0x00000000},
+	{MT_BBP(TXBE, 4), 0x00000004},
+	{MT_BBP(TXBE, 6), 0x00000000},
+	{MT_BBP(TXBE, 8), 0x00000014},
+	{MT_BBP(TXBE, 9), 0x20000000},
+	{MT_BBP(TXBE, 10), 0x00000000},
+	{MT_BBP(TXBE, 12), 0x00000000},
+	{MT_BBP(TXBE, 13), 0x00000000},
+	{MT_BBP(TXBE, 14), 0x00000000},
+	{MT_BBP(TXBE, 15), 0x00000000},
+	{MT_BBP(TXBE, 16), 0x00000000},
+	{MT_BBP(TXBE, 17), 0x00000000},
+
+	{MT_BBP(RXFE, 1), 0x00008800}, /* Add for E3 */
+	{MT_BBP(RXFE, 3), 0x00000000},
+	{MT_BBP(RXFE, 4), 0x00000000},
+
+	{MT_BBP(RXO, 13), 0x00000092},
+	{MT_BBP(RXO, 14), 0x00060612},
+	{MT_BBP(RXO, 15), 0xC8321B18},
+	{MT_BBP(RXO, 16), 0x0000001E},
+	{MT_BBP(RXO, 17), 0x00000000},
+	{MT_BBP(RXO, 18), 0xCC00A993},
+	{MT_BBP(RXO, 19), 0xB9CB9CB9},
+	{MT_BBP(RXO, 20), 0x26c00057},
+	{MT_BBP(RXO, 21), 0x00000001},
+	{MT_BBP(RXO, 24), 0x00000006},
+};
+
+static const struct mt76x0_bbp_switch_item mt76x0_bbp_switch_tab[] = {
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 8), 0x0E344EF0}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 8), 0x122C54F2}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 14), 0x310F2E39}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 14), 0x310F2A3F}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 32), 0x00003230}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 32), 0x0000181C}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 33), 0x00003240}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 33), 0x00003218}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 35), 0x11112016}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 35), 0x11112016}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(RXO, 28), 0x0000008A}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(RXO, 28), 0x0000008A}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 4), 0x1FEDA049}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 4), 0x1FECA054}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 6), 0x00000045}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 6), 0x0000000A}},
+
+	{RF_G_BAND | RF_BW_20,				{MT_BBP(AGC, 12), 0x05052879}},
+	{RF_G_BAND | RF_BW_40,				{MT_BBP(AGC, 12), 0x050528F9}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 12), 0x050528F9}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 13), 0x35050004}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 13), 0x2C3A0406}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 27), 0x000000E1}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 27), 0x000000EC}},
+
+	{RF_G_BAND | RF_BW_20,				{MT_BBP(AGC, 28), 0x00060806}},
+	{RF_G_BAND | RF_BW_40,				{MT_BBP(AGC, 28), 0x00050806}},
+	{RF_A_BAND | RF_BW_40,				{MT_BBP(AGC, 28), 0x00060801}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_80,		{MT_BBP(AGC, 28), 0x00060806}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 31), 0x00000F23}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 31), 0x00000F13}},
+
+	{RF_G_BAND | RF_BW_20,				{MT_BBP(AGC, 39), 0x2A2A3036}},
+	{RF_G_BAND | RF_BW_40,				{MT_BBP(AGC, 39), 0x2A2A2C36}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 39), 0x2A2A3036}},
+	{RF_A_BAND | RF_BW_80,				{MT_BBP(AGC, 39), 0x2A2A2A36}},
+
+	{RF_G_BAND | RF_BW_20,				{MT_BBP(AGC, 43), 0x27273438}},
+	{RF_G_BAND | RF_BW_40,				{MT_BBP(AGC, 43), 0x27272D38}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 43), 0x27272B30}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 51), 0x17171C1C}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 51), 0xFFFFFFFF}},
+
+	{RF_G_BAND | RF_BW_20,				{MT_BBP(AGC, 53), 0x26262A2F}},
+	{RF_G_BAND | RF_BW_40,				{MT_BBP(AGC, 53), 0x2626322F}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 53), 0xFFFFFFFF}},
+
+	{RF_G_BAND | RF_BW_20,				{MT_BBP(AGC, 55), 0x40404E58}},
+	{RF_G_BAND | RF_BW_40,				{MT_BBP(AGC, 55), 0x40405858}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 55), 0xFFFFFFFF}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 58), 0x00001010}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 58), 0x00000000}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(RXFE, 0), 0x3D5000E0}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(RXFE, 0), 0x895000E0}},
+};
+
+static const struct mt76_reg_pair mt76x0_dcoc_tab[] = {
+	{MT_BBP(CAL, 47), 0x000010F0 },
+	{MT_BBP(CAL, 48), 0x00008080 },
+	{MT_BBP(CAL, 49), 0x00000F07 },
+	{MT_BBP(CAL, 50), 0x00000040 },
+	{MT_BBP(CAL, 51), 0x00000404 },
+	{MT_BBP(CAL, 52), 0x00080803 },
+	{MT_BBP(CAL, 53), 0x00000704 },
+	{MT_BBP(CAL, 54), 0x00002828 },
+	{MT_BBP(CAL, 55), 0x00005050 },
+};
+
+#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/initvals_phy.h b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals_phy.h
new file mode 100644
index 000000000000..95d43efc1f3d
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals_phy.h
@@ -0,0 +1,772 @@
+/*
+ * (c) Copyright 2002-2010, Ralink Technology, Inc.
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __MT76X0U_PHY_INITVALS_H
+#define __MT76X0U_PHY_INITVALS_H
+
+#define RF_REG_PAIR(bank, reg, value)				\
+	{ (bank) << 16 | (reg), value }
+
+
+static const struct mt76_reg_pair mt76x0_rf_central_tab[] = {
+/*
+	Bank 0 - For central blocks: BG, PLL, XTAL, LO, ADC/DAC
+*/
+	{ MT_RF(0, 1), 0x01},
+	{ MT_RF(0, 2), 0x11},
+
+	/*
+		R3 ~ R7: VCO Cal.
+	*/
+	{ MT_RF(0, 3), 0x73}, /* VCO Freq Cal - No Bypass, VCO Amp Cal - No Bypass */
+	{ MT_RF(0, 4), 0x30}, /* R4 b<7>=1, VCO cal */
+	{ MT_RF(0, 5), 0x00},
+	{ MT_RF(0, 6), 0x41}, /* Set the open loop amplitude to middle since bypassing amplitude calibration */
+	{ MT_RF(0, 7), 0x00},
+
+	/*
+		XO
+	*/
+	{ MT_RF(0,  8), 0x00},
+	{ MT_RF(0,  9), 0x00},
+	{ MT_RF(0, 10), 0x0C},
+	{ MT_RF(0, 11), 0x00},
+	{ MT_RF(0, 12), 0x00},
+
+	/*
+		BG
+	*/
+	{ MT_RF(0, 13), 0x00},
+	{ MT_RF(0, 14), 0x00},
+	{ MT_RF(0, 15), 0x00},
+
+	/*
+		LDO
+	*/
+	{ MT_RF(0, 19), 0x20},
+	/*
+		XO
+	*/
+	{ MT_RF(0, 20), 0x22},
+	{ MT_RF(0, 21), 0x12},
+	{ MT_RF(0, 23), 0x00},
+	{ MT_RF(0, 24), 0x33}, /* See band selection for R24<1:0> */
+	{ MT_RF(0, 25), 0x00},
+
+	/*
+		PLL, See Freq Selection
+	*/
+	{ MT_RF(0, 26), 0x00},
+	{ MT_RF(0, 27), 0x00},
+	{ MT_RF(0, 28), 0x00},
+	{ MT_RF(0, 29), 0x00},
+	{ MT_RF(0, 30), 0x00},
+	{ MT_RF(0, 31), 0x00},
+	{ MT_RF(0, 32), 0x00},
+	{ MT_RF(0, 33), 0x00},
+	{ MT_RF(0, 34), 0x00},
+	{ MT_RF(0, 35), 0x00},
+	{ MT_RF(0, 36), 0x00},
+	{ MT_RF(0, 37), 0x00},
+
+	/*
+		LO Buffer
+	*/
+	{ MT_RF(0, 38), 0x2F},
+
+	/*
+		Test Ports
+	*/
+	{ MT_RF(0, 64), 0x00},
+	{ MT_RF(0, 65), 0x80},
+	{ MT_RF(0, 66), 0x01},
+	{ MT_RF(0, 67), 0x04},
+
+	/*
+		ADC/DAC
+	*/
+	{ MT_RF(0, 68), 0x00},
+	{ MT_RF(0, 69), 0x08},
+	{ MT_RF(0, 70), 0x08},
+	{ MT_RF(0, 71), 0x40},
+	{ MT_RF(0, 72), 0xD0},
+	{ MT_RF(0, 73), 0x93},
+};
+
+static const struct mt76_reg_pair mt76x0_rf_2g_channel_0_tab[] = {
+/*
+	Bank 5 - Channel 0 2G RF registers
+*/
+	/*
+		RX logic operation
+	*/
+	/* RF_R00 Change in SelectBand6590 */
+
+	{ MT_RF(5, 2), 0x0C}, /* 5G+2G (MT7610U) */
+	{ MT_RF(5, 3), 0x00},
+
+	/*
+		TX logic operation
+	*/
+	{ MT_RF(5, 4), 0x00},
+	{ MT_RF(5, 5), 0x84},
+	{ MT_RF(5, 6), 0x02},
+
+	/*
+		LDO
+	*/
+	{ MT_RF(5, 7), 0x00},
+	{ MT_RF(5, 8), 0x00},
+	{ MT_RF(5, 9), 0x00},
+
+	/*
+		RX
+	*/
+	{ MT_RF(5, 10), 0x51},
+	{ MT_RF(5, 11), 0x22},
+	{ MT_RF(5, 12), 0x22},
+	{ MT_RF(5, 13), 0x0F},
+	{ MT_RF(5, 14), 0x47}, /* Increase mixer current for more gain */
+	{ MT_RF(5, 15), 0x25},
+	{ MT_RF(5, 16), 0xC7}, /* Tune LNA2 tank */
+	{ MT_RF(5, 17), 0x00},
+	{ MT_RF(5, 18), 0x00},
+	{ MT_RF(5, 19), 0x30}, /* Improve max Pin */
+	{ MT_RF(5, 20), 0x33},
+	{ MT_RF(5, 21), 0x02},
+	{ MT_RF(5, 22), 0x32}, /* Tune LNA1 tank */
+	{ MT_RF(5, 23), 0x00},
+	{ MT_RF(5, 24), 0x25},
+	{ MT_RF(5, 26), 0x00},
+	{ MT_RF(5, 27), 0x12},
+	{ MT_RF(5, 28), 0x0F},
+	{ MT_RF(5, 29), 0x00},
+
+	/*
+		LOGEN
+	*/
+	{ MT_RF(5, 30), 0x51}, /* Tune LOGEN tank */
+	{ MT_RF(5, 31), 0x35},
+	{ MT_RF(5, 32), 0x31},
+	{ MT_RF(5, 33), 0x31},
+	{ MT_RF(5, 34), 0x34},
+	{ MT_RF(5, 35), 0x03},
+	{ MT_RF(5, 36), 0x00},
+
+	/*
+		TX
+	*/
+	{ MT_RF(5, 37), 0xDD}, /* Improve 3.2GHz spur */
+	{ MT_RF(5, 38), 0xB3},
+	{ MT_RF(5, 39), 0x33},
+	{ MT_RF(5, 40), 0xB1},
+	{ MT_RF(5, 41), 0x71},
+	{ MT_RF(5, 42), 0xF2},
+	{ MT_RF(5, 43), 0x47},
+	{ MT_RF(5, 44), 0x77},
+	{ MT_RF(5, 45), 0x0E},
+	{ MT_RF(5, 46), 0x10},
+	{ MT_RF(5, 47), 0x00},
+	{ MT_RF(5, 48), 0x53},
+	{ MT_RF(5, 49), 0x03},
+	{ MT_RF(5, 50), 0xEF},
+	{ MT_RF(5, 51), 0xC7},
+	{ MT_RF(5, 52), 0x62},
+	{ MT_RF(5, 53), 0x62},
+	{ MT_RF(5, 54), 0x00},
+	{ MT_RF(5, 55), 0x00},
+	{ MT_RF(5, 56), 0x0F},
+	{ MT_RF(5, 57), 0x0F},
+	{ MT_RF(5, 58), 0x16},
+	{ MT_RF(5, 59), 0x16},
+	{ MT_RF(5, 60), 0x10},
+	{ MT_RF(5, 61), 0x10},
+	{ MT_RF(5, 62), 0xD0},
+	{ MT_RF(5, 63), 0x6C},
+	{ MT_RF(5, 64), 0x58},
+	{ MT_RF(5, 65), 0x58},
+	{ MT_RF(5, 66), 0xF2},
+	{ MT_RF(5, 67), 0xE8},
+	{ MT_RF(5, 68), 0xF0},
+	{ MT_RF(5, 69), 0xF0},
+	{ MT_RF(5, 127), 0x04},
+};
+
+static const struct mt76_reg_pair mt76x0_rf_5g_channel_0_tab[] = {
+/*
+	Bank 6 - Channel 0 5G RF registers
+*/
+	/*
+		RX logic operation
+	*/
+	/* RF_R00 Change in SelectBandmt76x0 */
+
+	{ MT_RF(6, 2), 0x0C},
+	{ MT_RF(6, 3), 0x00},
+
+	/*
+		TX logic operation
+	*/
+	{ MT_RF(6, 4), 0x00},
+	{ MT_RF(6, 5), 0x84},
+	{ MT_RF(6, 6), 0x02},
+
+	/*
+		LDO
+	*/
+	{ MT_RF(6, 7), 0x00},
+	{ MT_RF(6, 8), 0x00},
+	{ MT_RF(6, 9), 0x00},
+
+	/*
+		RX
+	*/
+	{ MT_RF(6, 10), 0x00},
+	{ MT_RF(6, 11), 0x01},
+
+	{ MT_RF(6, 13), 0x23},
+	{ MT_RF(6, 14), 0x00},
+	{ MT_RF(6, 15), 0x04},
+	{ MT_RF(6, 16), 0x22},
+
+	{ MT_RF(6, 18), 0x08},
+	{ MT_RF(6, 19), 0x00},
+	{ MT_RF(6, 20), 0x00},
+	{ MT_RF(6, 21), 0x00},
+	{ MT_RF(6, 22), 0xFB},
+
+	/*
+		LOGEN5G
+	*/
+	{ MT_RF(6, 25), 0x76},
+	{ MT_RF(6, 26), 0x24},
+	{ MT_RF(6, 27), 0x04},
+	{ MT_RF(6, 28), 0x00},
+	{ MT_RF(6, 29), 0x00},
+
+	/*
+		TX
+	*/
+	{ MT_RF(6, 37), 0xBB},
+	{ MT_RF(6, 38), 0xB3},
+
+	{ MT_RF(6, 40), 0x33},
+	{ MT_RF(6, 41), 0x33},
+
+	{ MT_RF(6, 43), 0x03},
+	{ MT_RF(6, 44), 0xB3},
+
+	{ MT_RF(6, 46), 0x17},
+	{ MT_RF(6, 47), 0x0E},
+	{ MT_RF(6, 48), 0x10},
+	{ MT_RF(6, 49), 0x07},
+
+	{ MT_RF(6, 62), 0x00},
+	{ MT_RF(6, 63), 0x00},
+	{ MT_RF(6, 64), 0xF1},
+	{ MT_RF(6, 65), 0x0F},
+};
+
+static const struct mt76_reg_pair mt76x0_rf_vga_channel_0_tab[] = {
+/*
+	Bank 7 - Channel 0 VGA RF registers
+*/
+	/* E3 CR */
+	{ MT_RF(7, 0), 0x47}, /* Allow BBP/MAC to do calibration */
+	{ MT_RF(7, 1), 0x00},
+	{ MT_RF(7, 2), 0x00},
+	{ MT_RF(7, 3), 0x00},
+	{ MT_RF(7, 4), 0x00},
+
+	{ MT_RF(7, 10), 0x13},
+	{ MT_RF(7, 11), 0x0F},
+	{ MT_RF(7, 12), 0x13}, /* For dcoc */
+	{ MT_RF(7, 13), 0x13}, /* For dcoc */
+	{ MT_RF(7, 14), 0x13}, /* For dcoc */
+	{ MT_RF(7, 15), 0x20}, /* For dcoc */
+	{ MT_RF(7, 16), 0x22}, /* For dcoc */
+
+	{ MT_RF(7, 17), 0x7C},
+
+	{ MT_RF(7, 18), 0x00},
+	{ MT_RF(7, 19), 0x00},
+	{ MT_RF(7, 20), 0x00},
+	{ MT_RF(7, 21), 0xF1},
+	{ MT_RF(7, 22), 0x11},
+	{ MT_RF(7, 23), 0xC2},
+	{ MT_RF(7, 24), 0x41},
+	{ MT_RF(7, 25), 0x20},
+	{ MT_RF(7, 26), 0x40},
+	{ MT_RF(7, 27), 0xD7},
+	{ MT_RF(7, 28), 0xA2},
+	{ MT_RF(7, 29), 0x60},
+	{ MT_RF(7, 30), 0x49},
+	{ MT_RF(7, 31), 0x20},
+	{ MT_RF(7, 32), 0x44},
+	{ MT_RF(7, 33), 0xC1},
+	{ MT_RF(7, 34), 0x60},
+	{ MT_RF(7, 35), 0xC0},
+
+	{ MT_RF(7, 61), 0x01},
+
+	{ MT_RF(7, 72), 0x3C},
+	{ MT_RF(7, 73), 0x34},
+	{ MT_RF(7, 74), 0x00},
+};
+
+static const struct mt76x0_rf_switch_item mt76x0_rf_bw_switch_tab[] = {
+	/*   Bank, 		Register,	Bw/Band, 	Value */
+	{ MT_RF(0, 17),		RF_G_BAND | RF_BW_20,	0x00},
+	{ MT_RF(0, 17),		RF_G_BAND | RF_BW_40,	0x00},
+	{ MT_RF(0, 17),		RF_A_BAND | RF_BW_20,	0x00},
+	{ MT_RF(0, 17),		RF_A_BAND | RF_BW_40,	0x00},
+	{ MT_RF(0, 17),		RF_A_BAND | RF_BW_80,	0x00},
+
+	/* TODO: need to check B7.R6 & B7.R7 setting for 2.4G again @20121112 */
+	{ MT_RF(7,  6),		RF_G_BAND | RF_BW_20,	0x40},
+	{ MT_RF(7,  6),		RF_G_BAND | RF_BW_40,	0x1C},
+	{ MT_RF(7,  6),		RF_A_BAND | RF_BW_20,	0x40},
+	{ MT_RF(7,  6),		RF_A_BAND | RF_BW_40,	0x20},
+	{ MT_RF(7,  6),		RF_A_BAND | RF_BW_80,	0x10},
+
+	{ MT_RF(7,  7),		RF_G_BAND | RF_BW_20,	0x40},
+	{ MT_RF(7,  7),		RF_G_BAND | RF_BW_40,	0x20},
+	{ MT_RF(7,  7),		RF_A_BAND | RF_BW_20,	0x40},
+	{ MT_RF(7,  7),		RF_A_BAND | RF_BW_40,	0x20},
+	{ MT_RF(7,  7),		RF_A_BAND | RF_BW_80,	0x10},
+
+	{ MT_RF(7,  8),		RF_G_BAND | RF_BW_20,	0x03},
+	{ MT_RF(7,  8),		RF_G_BAND | RF_BW_40,	0x01},
+	{ MT_RF(7,  8),		RF_A_BAND | RF_BW_20,	0x03},
+	{ MT_RF(7,  8),		RF_A_BAND | RF_BW_40,	0x01},
+	{ MT_RF(7,  8),		RF_A_BAND | RF_BW_80,	0x00},
+
+	/* TODO: need to check B7.R58 & B7.R59 setting for 2.4G again @20121112 */
+	{ MT_RF(7, 58),		RF_G_BAND | RF_BW_20,	0x40},
+	{ MT_RF(7, 58),		RF_G_BAND | RF_BW_40,	0x40},
+	{ MT_RF(7, 58),		RF_A_BAND | RF_BW_20,	0x40},
+	{ MT_RF(7, 58),		RF_A_BAND | RF_BW_40,	0x40},
+	{ MT_RF(7, 58),		RF_A_BAND | RF_BW_80,	0x10},
+
+	{ MT_RF(7, 59),		RF_G_BAND | RF_BW_20,	0x40},
+	{ MT_RF(7, 59),		RF_G_BAND | RF_BW_40,	0x40},
+	{ MT_RF(7, 59),		RF_A_BAND | RF_BW_20,	0x40},
+	{ MT_RF(7, 59),		RF_A_BAND | RF_BW_40,	0x40},
+	{ MT_RF(7, 59),		RF_A_BAND | RF_BW_80,	0x10},
+
+	{ MT_RF(7, 60),		RF_G_BAND | RF_BW_20,	0xAA},
+	{ MT_RF(7, 60),		RF_G_BAND | RF_BW_40,	0xAA},
+	{ MT_RF(7, 60),		RF_A_BAND | RF_BW_20,	0xAA},
+	{ MT_RF(7, 60),		RF_A_BAND | RF_BW_40,	0xAA},
+	{ MT_RF(7, 60),		RF_A_BAND | RF_BW_80,	0xAA},
+
+	{ MT_RF(7, 76),		RF_BW_20,	0x40},
+	{ MT_RF(7, 76),		RF_BW_40,	0x40},
+	{ MT_RF(7, 76),		RF_BW_80,	0x10},
+
+	{ MT_RF(7, 77),		RF_BW_20,	0x40},
+	{ MT_RF(7, 77),		RF_BW_40,	0x40},
+	{ MT_RF(7, 77),		RF_BW_80,	0x10},
+};
+
+static const struct mt76x0_rf_switch_item mt76x0_rf_band_switch_tab[] = {
+	/*   Bank, 		Register,	Bw/Band, 		Value */
+	{ MT_RF(0, 16),		RF_G_BAND,		0x20},
+	{ MT_RF(0, 16),		RF_A_BAND,		0x20},
+
+	{ MT_RF(0, 18),		RF_G_BAND,		0x00},
+	{ MT_RF(0, 18),		RF_A_BAND,		0x00},
+
+	{ MT_RF(0, 39),		RF_G_BAND,		0x36},
+	{ MT_RF(0, 39),		RF_A_BAND_LB,	0x34},
+	{ MT_RF(0, 39),		RF_A_BAND_MB,	0x33},
+	{ MT_RF(0, 39),		RF_A_BAND_HB,	0x31},
+	{ MT_RF(0, 39),		RF_A_BAND_11J,	0x36},
+
+	{ MT_RF(6, 12),		RF_A_BAND_LB,	0x44},
+	{ MT_RF(6, 12),		RF_A_BAND_MB,	0x44},
+	{ MT_RF(6, 12),		RF_A_BAND_HB,	0x55},
+	{ MT_RF(6, 12),		RF_A_BAND_11J,	0x44},
+
+	{ MT_RF(6, 17),		RF_A_BAND_LB,	0x02},
+	{ MT_RF(6, 17),		RF_A_BAND_MB,	0x00},
+	{ MT_RF(6, 17),		RF_A_BAND_HB,	0x00},
+	{ MT_RF(6, 17),		RF_A_BAND_11J,	0x05},
+
+	{ MT_RF(6, 24),		RF_A_BAND_LB,	0xA1},
+	{ MT_RF(6, 24),		RF_A_BAND_MB,	0x41},
+	{ MT_RF(6, 24),		RF_A_BAND_HB,	0x21},
+	{ MT_RF(6, 24),		RF_A_BAND_11J,	0xE1},
+
+	{ MT_RF(6, 39),		RF_A_BAND_LB,	0x36},
+	{ MT_RF(6, 39),		RF_A_BAND_MB,	0x34},
+	{ MT_RF(6, 39),		RF_A_BAND_HB,	0x32},
+	{ MT_RF(6, 39),		RF_A_BAND_11J,	0x37},
+
+	{ MT_RF(6, 42),		RF_A_BAND_LB,	0xFB},
+	{ MT_RF(6, 42),		RF_A_BAND_MB,	0xF3},
+	{ MT_RF(6, 42),		RF_A_BAND_HB,	0xEB},
+	{ MT_RF(6, 42),		RF_A_BAND_11J,	0xEB},
+
+	/* Move R6-R45, R50~R59 to mt76x0_RF_INT_PA_5G_Channel_0_RegTb/mt76x0_RF_EXT_PA_5G_Channel_0_RegTb */
+
+	{ MT_RF(6, 127),	RF_G_BAND,		0x84},
+	{ MT_RF(6, 127),	RF_A_BAND,		0x04},
+
+	{ MT_RF(7, 5),		RF_G_BAND,		0x40},
+	{ MT_RF(7, 5),		RF_A_BAND,		0x00},
+
+	{ MT_RF(7, 9),		RF_G_BAND,		0x00},
+	{ MT_RF(7, 9),		RF_A_BAND,		0x00},
+
+	{ MT_RF(7, 70),		RF_G_BAND,		0x00},
+	{ MT_RF(7, 70),		RF_A_BAND,		0x6D},
+
+	{ MT_RF(7, 71),		RF_G_BAND,		0x00},
+	{ MT_RF(7, 71),		RF_A_BAND,		0xB0},
+
+	{ MT_RF(7, 78),		RF_G_BAND,		0x00},
+	{ MT_RF(7, 78),		RF_A_BAND,		0x55},
+
+	{ MT_RF(7, 79),		RF_G_BAND,		0x00},
+	{ MT_RF(7, 79),		RF_A_BAND,		0x55},
+};
+
+static const struct mt76x0_freq_item mt76x0_frequency_plan[] = {
+	{1,	RF_G_BAND,	0x02, 0x3F, 0x28, 0xDD, 0xE2, 0x40, 0x02, 0x40, 0x02, 0, 0, 1, 0x28, 0, 0x30, 0, 0, 0x3}, /* Freq 2412 */
+	{2, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xE4, 0x40, 0x07, 0x40, 0x02, 0, 0, 1, 0xA1, 0, 0x30, 0, 0, 0x1}, /* Freq 2417 */
+	{3, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xE2, 0x40, 0x07, 0x40, 0x0B, 0, 0, 1, 0x50, 0, 0x30, 0, 0, 0x0}, /* Freq 2422 */
+	{4, 	RF_G_BAND,	0x02, 0x3F, 0x28, 0xDD, 0xD4, 0x40, 0x02, 0x40, 0x09, 0, 0, 1, 0x50, 0, 0x30, 0, 0, 0x0}, /* Freq 2427 */
+	{5, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x02, 0, 0, 1, 0xA2, 0, 0x30, 0, 0, 0x1}, /* Freq 2432 */
+	{6, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x07, 0, 0, 1, 0xA2, 0, 0x30, 0, 0, 0x1}, /* Freq 2437 */
+	{7, 	RF_G_BAND,	0x02, 0x3F, 0x28, 0xDD, 0xE2, 0x40, 0x02, 0x40, 0x07, 0, 0, 1, 0x28, 0, 0x30, 0, 0, 0x3}, /* Freq 2442 */
+	{8, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x02, 0, 0, 1, 0xA3, 0, 0x30, 0, 0, 0x1}, /* Freq 2447 */
+	{9, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xF2, 0x40, 0x07, 0x40, 0x0D, 0, 0, 1, 0x28, 0, 0x30, 0, 0, 0x3}, /* Freq 2452 */
+	{10, 	RF_G_BAND,	0x02, 0x3F, 0x28, 0xDD, 0xD4, 0x40, 0x02, 0x40, 0x09, 0, 0, 1, 0x51, 0, 0x30, 0, 0, 0x0}, /* Freq 2457 */
+	{11, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x02, 0, 0, 1, 0xA4, 0, 0x30, 0, 0, 0x1}, /* Freq 2462 */
+	{12, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x07, 0, 0, 1, 0xA4, 0, 0x30, 0, 0, 0x1}, /* Freq 2467 */
+	{13, 	RF_G_BAND,	0x02, 0x3F, 0x28, 0xDD, 0xF2, 0x40, 0x02, 0x40, 0x02, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 2472 */
+	{14, 	RF_G_BAND,	0x02, 0x3F, 0x28, 0xDD, 0xF2, 0x40, 0x02, 0x40, 0x04, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 2484 */
+
+	{183, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x28, 0, 0x30, 0, 0, 0x3}, /* Freq 4915 */
+	{184, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x00, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4920 */
+	{185, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4925 */
+	{187, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4935 */
+	{188, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4940 */
+	{189, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4945 */
+	{192, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4960 */
+	{196, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4980 */
+
+	{36, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5180 */
+	{37, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5185 */
+	{38, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5190 */
+	{39, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5195 */
+	{40, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5200 */
+	{41, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x09, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5205 */
+	{42, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x05, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5210 */
+	{43, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0B, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5215 */
+	{44, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5220 */
+	{45, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0D, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5225 */
+	{46, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x07, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5230 */
+	{47, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0F, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5235 */
+	{48, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x08, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5240 */
+	{49, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x11, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5245 */
+	{50, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x09, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5250 */
+	{51, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x13, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5255 */
+	{52, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5260 */
+	{53, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5265 */
+	{54, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x0B, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5270 */
+	{55, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5275 */
+	{56, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x00, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5280 */
+	{57, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5285 */
+	{58, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x01, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5290 */
+	{59, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5295 */
+	{60, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5300 */
+	{61, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5305 */
+	{62, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5310 */
+	{63, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5315 */
+	{64, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5320 */
+
+	{100, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x2D, 0, 0x30, 0, 0, 0x3}, /* Freq 5500 */
+	{101, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x2D, 0, 0x30, 0, 0, 0x3}, /* Freq 5505 */
+	{102, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x0B, 0, 0, 1, 0x2D, 0, 0x30, 0, 0, 0x3}, /* Freq 5510 */
+	{103, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x2D, 0, 0x30, 0, 0, 0x3}, /* Freq 5515 */
+	{104, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x00, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5520 */
+	{105, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5525 */
+	{106, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x01, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5530 */
+	{107, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5535 */
+	{108, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5540 */
+	{109, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5545 */
+	{110, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5550 */
+	{111, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5555 */
+	{112, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5560 */
+	{113, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x09, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5565 */
+	{114, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x05, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5570 */
+	{115, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0B, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5575 */
+	{116, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5580 */
+	{117, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0D, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5585 */
+	{118, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x07, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5590 */
+	{119, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0F, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5595 */
+	{120, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x08, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5600 */
+	{121, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x11, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5605 */
+	{122, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x09, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5610 */
+	{123, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x13, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5615 */
+	{124, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5620 */
+	{125, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5625 */
+	{126, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x0B, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5630 */
+	{127, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5635 */
+	{128, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x00, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5640 */
+	{129, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5645 */
+	{130, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x01, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5650 */
+	{131, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5655 */
+	{132, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5660 */
+	{133, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5665 */
+	{134, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5670 */
+	{135, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5675 */
+	{136, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5680 */
+
+	{137, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x09, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5685 */
+	{138, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x05, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5690 */
+	{139, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0B, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5695 */
+	{140, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5700 */
+	{141, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0D, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5705 */
+	{142, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x07, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5710 */
+	{143, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0F, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5715 */
+	{144, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x08, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5720 */
+	{145, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x11, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5725 */
+	{146, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x09, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5730 */
+	{147, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x13, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5735 */
+	{148, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5740 */
+	{149, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5745 */
+	{150, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x0B, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5750 */
+	{151, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5755 */
+	{152, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x00, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5760 */
+	{153, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5765 */
+	{154, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x01, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5770 */
+	{155, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5775 */
+	{156, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5780 */
+	{157, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5785 */
+	{158, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5790 */
+	{159, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5795 */
+	{160, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5800 */
+	{161, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x09, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5805 */
+	{162, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x05, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5810 */
+	{163, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0B, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5815 */
+	{164, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5820 */
+	{165, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0D, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5825 */
+	{166, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x07, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5830 */
+	{167, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0F, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5835 */
+	{168, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x08, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5840 */
+	{169, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x11, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5845 */
+	{170, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x09, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5850 */
+	{171, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x13, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5855 */
+	{172, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5860 */
+	{173, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5865 */
+};
+
+static const struct mt76x0_freq_item mt76x0_sdm_frequency_plan[] = {
+	{1,	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0xCCCC,  0x3}, /* Freq 2412 */
+	{2, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x12222, 0x3}, /* Freq 2417 */
+	{3, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x17777, 0x3}, /* Freq 2422 */
+	{4, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x1CCCC, 0x3}, /* Freq 2427 */
+	{5, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x22222, 0x3}, /* Freq 2432 */
+	{6, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x27777, 0x3}, /* Freq 2437 */
+	{7, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x2CCCC, 0x3}, /* Freq 2442 */
+	{8, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x32222, 0x3}, /* Freq 2447 */
+	{9, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x37777, 0x3}, /* Freq 2452 */
+	{10, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x3CCCC, 0x3}, /* Freq 2457 */
+	{11, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x2222, 0x3}, /* Freq 2462 */
+	{12, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x7777, 0x3}, /* Freq 2467 */
+	{13, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0xCCCC, 0x3}, /* Freq 2472 */
+	{14, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x19999, 0x3}, /* Freq 2484 */
+
+	{183, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x3D555, 0x3}, /* Freq 4915 */
+	{184, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x0,     0x3}, /* Freq 4920 */
+	{185, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x2AAA,  0x3}, /* Freq 4925 */
+	{187, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x8000,  0x3}, /* Freq 4935 */
+	{188, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0xAAAA,  0x3}, /* Freq 4940 */
+	{189, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0xD555,  0x3}, /* Freq 4945 */
+	{192, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x15555, 0x3}, /* Freq 4960 */
+	{196, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x20000, 0x3}, /* Freq 4980 */
+
+	{36, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0xAAAA,  0x3}, /* Freq 5180 */
+	{37, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0xD555,  0x3}, /* Freq 5185 */
+	{38, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x10000, 0x3}, /* Freq 5190 */
+	{39, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x12AAA, 0x3}, /* Freq 5195 */
+	{40, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x15555, 0x3}, /* Freq 5200 */
+	{41, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x18000, 0x3}, /* Freq 5205 */
+	{42, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x1AAAA, 0x3}, /* Freq 5210 */
+	{43, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x1D555, 0x3}, /* Freq 5215 */
+	{44, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x20000, 0x3}, /* Freq 5220 */
+	{45, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x22AAA, 0x3}, /* Freq 5225 */
+	{46, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x25555, 0x3}, /* Freq 5230 */
+	{47, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x28000, 0x3}, /* Freq 5235 */
+	{48, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x2AAAA, 0x3}, /* Freq 5240 */
+	{49, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x2D555, 0x3}, /* Freq 5245 */
+	{50, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x30000, 0x3}, /* Freq 5250 */
+	{51, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x32AAA, 0x3}, /* Freq 5255 */
+	{52, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x35555, 0x3}, /* Freq 5260 */
+	{53, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x38000, 0x3}, /* Freq 5265 */
+	{54, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x3AAAA, 0x3}, /* Freq 5270 */
+	{55, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x3D555, 0x3}, /* Freq 5275 */
+	{56, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x00000, 0x3}, /* Freq 5280 */
+	{57, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x02AAA, 0x3}, /* Freq 5285 */
+	{58, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x05555, 0x3}, /* Freq 5290 */
+	{59, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x08000, 0x3}, /* Freq 5295 */
+	{60, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x0AAAA, 0x3}, /* Freq 5300 */
+	{61, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x0D555, 0x3}, /* Freq 5305 */
+	{62, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x10000, 0x3}, /* Freq 5310 */
+	{63, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x12AAA, 0x3}, /* Freq 5315 */
+	{64, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x15555, 0x3}, /* Freq 5320 */
+
+	{100, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2D, 0, 0x0, 0x8, 0x35555, 0x3}, /* Freq 5500 */
+	{101, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2D, 0, 0x0, 0x8, 0x38000, 0x3}, /* Freq 5505 */
+	{102, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2D, 0, 0x0, 0x8, 0x3AAAA, 0x3}, /* Freq 5510 */
+	{103, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2D, 0, 0x0, 0x8, 0x3D555, 0x3}, /* Freq 5515 */
+	{104, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x00000, 0x3}, /* Freq 5520 */
+	{105, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x02AAA, 0x3}, /* Freq 5525 */
+	{106, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x05555, 0x3}, /* Freq 5530 */
+	{107, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x08000, 0x3}, /* Freq 5535 */
+	{108, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x0AAAA, 0x3}, /* Freq 5540 */
+	{109, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x0D555, 0x3}, /* Freq 5545 */
+	{110, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x10000, 0x3}, /* Freq 5550 */
+	{111, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x12AAA, 0x3}, /* Freq 5555 */
+	{112, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x15555, 0x3}, /* Freq 5560 */
+	{113, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x18000, 0x3}, /* Freq 5565 */
+	{114, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x1AAAA, 0x3}, /* Freq 5570 */
+	{115, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x1D555, 0x3}, /* Freq 5575 */
+	{116, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x20000, 0x3}, /* Freq 5580 */
+	{117, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x22AAA, 0x3}, /* Freq 5585 */
+	{118, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x25555, 0x3}, /* Freq 5590 */
+	{119, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x28000, 0x3}, /* Freq 5595 */
+	{120, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x2AAAA, 0x3}, /* Freq 5600 */
+	{121, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x2D555, 0x3}, /* Freq 5605 */
+	{122, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x30000, 0x3}, /* Freq 5610 */
+	{123, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x32AAA, 0x3}, /* Freq 5615 */
+	{124, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x35555, 0x3}, /* Freq 5620 */
+	{125, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x38000, 0x3}, /* Freq 5625 */
+	{126, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x3AAAA, 0x3}, /* Freq 5630 */
+	{127, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x3D555, 0x3}, /* Freq 5635 */
+	{128, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x00000, 0x3}, /* Freq 5640 */
+	{129, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x02AAA, 0x3}, /* Freq 5645 */
+	{130, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x05555, 0x3}, /* Freq 5650 */
+	{131, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x08000, 0x3}, /* Freq 5655 */
+	{132, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x0AAAA, 0x3}, /* Freq 5660 */
+	{133, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x0D555, 0x3}, /* Freq 5665 */
+	{134, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x10000, 0x3}, /* Freq 5670 */
+	{135, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x12AAA, 0x3}, /* Freq 5675 */
+	{136, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x15555, 0x3}, /* Freq 5680 */
+
+	{137, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x18000, 0x3}, /* Freq 5685 */
+	{138, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x1AAAA, 0x3}, /* Freq 5690 */
+	{139, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x1D555, 0x3}, /* Freq 5695 */
+	{140, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x20000, 0x3}, /* Freq 5700 */
+	{141, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x22AAA, 0x3}, /* Freq 5705 */
+	{142, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x25555, 0x3}, /* Freq 5710 */
+	{143, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x28000, 0x3}, /* Freq 5715 */
+	{144, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x2AAAA, 0x3}, /* Freq 5720 */
+	{145, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x2D555, 0x3}, /* Freq 5725 */
+	{146, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x30000, 0x3}, /* Freq 5730 */
+	{147, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x32AAA, 0x3}, /* Freq 5735 */
+	{148, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x35555, 0x3}, /* Freq 5740 */
+	{149, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x38000, 0x3}, /* Freq 5745 */
+	{150, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x3AAAA, 0x3}, /* Freq 5750 */
+	{151, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x3D555, 0x3}, /* Freq 5755 */
+	{152, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x00000, 0x3}, /* Freq 5760 */
+	{153, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x02AAA, 0x3}, /* Freq 5765 */
+	{154, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x05555, 0x3}, /* Freq 5770 */
+	{155, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x08000, 0x3}, /* Freq 5775 */
+	{156, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x0AAAA, 0x3}, /* Freq 5780 */
+	{157, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x0D555, 0x3}, /* Freq 5785 */
+	{158, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x10000, 0x3}, /* Freq 5790 */
+	{159, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x12AAA, 0x3}, /* Freq 5795 */
+	{160, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x15555, 0x3}, /* Freq 5800 */
+	{161, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x18000, 0x3}, /* Freq 5805 */
+	{162, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x1AAAA, 0x3}, /* Freq 5810 */
+	{163, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x1D555, 0x3}, /* Freq 5815 */
+	{164, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x20000, 0x3}, /* Freq 5820 */
+	{165, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x22AAA, 0x3}, /* Freq 5825 */
+	{166, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x25555, 0x3}, /* Freq 5830 */
+	{167, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x28000, 0x3}, /* Freq 5835 */
+	{168, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x2AAAA, 0x3}, /* Freq 5840 */
+	{169, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x2D555, 0x3}, /* Freq 5845 */
+	{170, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x30000, 0x3}, /* Freq 5850 */
+	{171, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x32AAA, 0x3}, /* Freq 5855 */
+	{172, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x35555, 0x3}, /* Freq 5860 */
+	{173, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x38000, 0x3}, /* Freq 5865 */
+};
+
+static const u8 mt76x0_sdm_channel[] = {
+	183, 185, 43, 45, 54, 55, 57, 58, 102, 103, 105, 106, 115, 117, 126, 127, 129, 130, 139, 141, 150, 151, 153, 154, 163, 165
+};
+
+static const struct mt76x0_rf_switch_item mt76x0_rf_ext_pa_tab[] = {
+	{ MT_RF(6, 45),		RF_A_BAND_LB,	0x63},
+	{ MT_RF(6, 45),		RF_A_BAND_MB,	0x43},
+	{ MT_RF(6, 45),		RF_A_BAND_HB,	0x33},
+	{ MT_RF(6, 45),		RF_A_BAND_11J,	0x73},
+
+	{ MT_RF(6, 50),		RF_A_BAND_LB,	0x02},
+	{ MT_RF(6, 50),		RF_A_BAND_MB,	0x02},
+	{ MT_RF(6, 50),		RF_A_BAND_HB,	0x02},
+	{ MT_RF(6, 50),		RF_A_BAND_11J,	0x02},
+
+	{ MT_RF(6, 51),		RF_A_BAND_LB,	0x02},
+	{ MT_RF(6, 51),		RF_A_BAND_MB,	0x02},
+	{ MT_RF(6, 51),		RF_A_BAND_HB,	0x02},
+	{ MT_RF(6, 51),		RF_A_BAND_11J,	0x02},
+
+	{ MT_RF(6, 52),		RF_A_BAND_LB,	0x08},
+	{ MT_RF(6, 52),		RF_A_BAND_MB,	0x08},
+	{ MT_RF(6, 52),		RF_A_BAND_HB,	0x08},
+	{ MT_RF(6, 52),		RF_A_BAND_11J,	0x08},
+
+	{ MT_RF(6, 53),		RF_A_BAND_LB,	0x08},
+	{ MT_RF(6, 53),		RF_A_BAND_MB,	0x08},
+	{ MT_RF(6, 53),		RF_A_BAND_HB,	0x08},
+	{ MT_RF(6, 53),		RF_A_BAND_11J,	0x08},
+
+	{ MT_RF(6, 54),		RF_A_BAND_LB,	0x0A},
+	{ MT_RF(6, 54),		RF_A_BAND_MB,	0x0A},
+	{ MT_RF(6, 54),		RF_A_BAND_HB,	0x0A},
+	{ MT_RF(6, 54),		RF_A_BAND_11J,	0x0A},
+
+	{ MT_RF(6, 55),		RF_A_BAND_LB,	0x0A},
+	{ MT_RF(6, 55),		RF_A_BAND_MB,	0x0A},
+	{ MT_RF(6, 55),		RF_A_BAND_HB,	0x0A},
+	{ MT_RF(6, 55),		RF_A_BAND_11J,	0x0A},
+
+	{ MT_RF(6, 56),		RF_A_BAND_LB,	0x05},
+	{ MT_RF(6, 56),		RF_A_BAND_MB,	0x05},
+	{ MT_RF(6, 56),		RF_A_BAND_HB,	0x05},
+	{ MT_RF(6, 56),		RF_A_BAND_11J,	0x05},
+
+	{ MT_RF(6, 57),		RF_A_BAND_LB,	0x05},
+	{ MT_RF(6, 57),		RF_A_BAND_MB,	0x05},
+	{ MT_RF(6, 57),		RF_A_BAND_HB,	0x05},
+	{ MT_RF(6, 57),		RF_A_BAND_11J,	0x05},
+
+	{ MT_RF(6, 58),		RF_A_BAND_LB,	0x05},
+	{ MT_RF(6, 58),		RF_A_BAND_MB,	0x03},
+	{ MT_RF(6, 58),		RF_A_BAND_HB,	0x02},
+	{ MT_RF(6, 58),		RF_A_BAND_11J,	0x07},
+
+	{ MT_RF(6, 59),		RF_A_BAND_LB,	0x05},
+	{ MT_RF(6, 59),		RF_A_BAND_MB,	0x03},
+	{ MT_RF(6, 59),		RF_A_BAND_HB,	0x02},
+	{ MT_RF(6, 59),		RF_A_BAND_11J,	0x07},
+};
+
+#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
new file mode 100644
index 000000000000..91a84be36d3b
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
@@ -0,0 +1,658 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "mt76x0.h"
+#include "trace.h"
+#include <linux/etherdevice.h>
+
+static void
+mt76_mac_process_tx_rate(struct ieee80211_tx_rate *txrate, u16 rate,
+			 enum nl80211_band band)
+{
+	u8 idx = FIELD_GET(MT_RXWI_RATE_INDEX, rate);
+
+	txrate->idx = 0;
+	txrate->flags = 0;
+	txrate->count = 1;
+
+	switch (FIELD_GET(MT_RXWI_RATE_PHY, rate)) {
+	case MT_PHY_TYPE_OFDM:
+		if (band == NL80211_BAND_2GHZ)
+			idx += 4;
+
+		txrate->idx = idx;
+		return;
+	case MT_PHY_TYPE_CCK:
+		if (idx >= 8)
+			idx -= 8;
+
+		txrate->idx = idx;
+		return;
+	case MT_PHY_TYPE_HT_GF:
+		txrate->flags |= IEEE80211_TX_RC_GREEN_FIELD;
+		/* fall through */
+	case MT_PHY_TYPE_HT:
+		txrate->flags |= IEEE80211_TX_RC_MCS;
+		txrate->idx = idx;
+		break;
+	case MT_PHY_TYPE_VHT:
+		txrate->flags |= IEEE80211_TX_RC_VHT_MCS;
+		txrate->idx = idx;
+		break;
+	default:
+		WARN_ON(1);
+		return;
+	}
+
+	switch (FIELD_GET(MT_RXWI_RATE_BW, rate)) {
+	case MT_PHY_BW_20:
+		break;
+	case MT_PHY_BW_40:
+		txrate->flags |= IEEE80211_TX_RC_40_MHZ_WIDTH;
+		break;
+	case MT_PHY_BW_80:
+		txrate->flags |= IEEE80211_TX_RC_80_MHZ_WIDTH;
+		break;
+	default:
+		WARN_ON(1);
+		return;
+	}
+
+	if (rate & MT_RXWI_RATE_SGI)
+		txrate->flags |= IEEE80211_TX_RC_SHORT_GI;
+}
+
+static void
+mt76_mac_fill_tx_status(struct mt76x0_dev *dev, struct ieee80211_tx_info *info,
+			struct mt76_tx_status *st, int n_frames)
+{
+	struct ieee80211_tx_rate *rate = info->status.rates;
+	int cur_idx, last_rate;
+	int i;
+
+	if (!n_frames)
+		return;
+
+	last_rate = min_t(int, st->retry, IEEE80211_TX_MAX_RATES - 1);
+	mt76_mac_process_tx_rate(&rate[last_rate], st->rate,
+				 dev->mt76.chandef.chan->band);
+	if (last_rate < IEEE80211_TX_MAX_RATES - 1)
+		rate[last_rate + 1].idx = -1;
+
+	cur_idx = rate[last_rate].idx + last_rate;
+	for (i = 0; i <= last_rate; i++) {
+		rate[i].flags = rate[last_rate].flags;
+		rate[i].idx = max_t(int, 0, cur_idx - i);
+		rate[i].count = 1;
+	}
+
+	rate[last_rate - 1].count = st->retry + 1 - last_rate;
+
+	info->status.ampdu_len = n_frames;
+	info->status.ampdu_ack_len = st->success ? n_frames : 0;
+
+	if (st->pktid & MT_TXWI_PKTID_PROBE)
+		info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE;
+
+	if (st->aggr)
+		info->flags |= IEEE80211_TX_CTL_AMPDU |
+			       IEEE80211_TX_STAT_AMPDU;
+
+	if (!st->ack_req)
+		info->flags |= IEEE80211_TX_CTL_NO_ACK;
+	else if (st->success)
+		info->flags |= IEEE80211_TX_STAT_ACK;
+}
+
+u16 mt76x0_mac_tx_rate_val(struct mt76x0_dev *dev,
+			 const struct ieee80211_tx_rate *rate, u8 *nss_val)
+{
+	u16 rateval;
+	u8 phy, rate_idx;
+	u8 nss = 1;
+	u8 bw = 0;
+
+	if (rate->flags & IEEE80211_TX_RC_VHT_MCS) {
+		rate_idx = rate->idx;
+		nss = 1 + (rate->idx >> 4);
+		phy = MT_PHY_TYPE_VHT;
+		if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
+			bw = 2;
+		else if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
+			bw = 1;
+	} else if (rate->flags & IEEE80211_TX_RC_MCS) {
+		rate_idx = rate->idx;
+		nss = 1 + (rate->idx >> 3);
+		phy = MT_PHY_TYPE_HT;
+		if (rate->flags & IEEE80211_TX_RC_GREEN_FIELD)
+			phy = MT_PHY_TYPE_HT_GF;
+		if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
+			bw = 1;
+	} else {
+		const struct ieee80211_rate *r;
+		int band = dev->mt76.chandef.chan->band;
+		u16 val;
+
+		r = &dev->mt76.hw->wiphy->bands[band]->bitrates[rate->idx];
+		if (rate->flags & IEEE80211_TX_RC_USE_SHORT_PREAMBLE)
+			val = r->hw_value_short;
+		else
+			val = r->hw_value;
+
+		phy = val >> 8;
+		rate_idx = val & 0xff;
+		bw = 0;
+	}
+
+	rateval = FIELD_PREP(MT_RXWI_RATE_INDEX, rate_idx);
+	rateval |= FIELD_PREP(MT_RXWI_RATE_PHY, phy);
+	rateval |= FIELD_PREP(MT_RXWI_RATE_BW, bw);
+	if (rate->flags & IEEE80211_TX_RC_SHORT_GI)
+		rateval |= MT_RXWI_RATE_SGI;
+
+	*nss_val = nss;
+	return cpu_to_le16(rateval);
+}
+
+void mt76x0_mac_wcid_set_rate(struct mt76x0_dev *dev, struct mt76_wcid *wcid,
+			    const struct ieee80211_tx_rate *rate)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->mt76.lock, flags);
+	wcid->tx_rate = mt76x0_mac_tx_rate_val(dev, rate, &wcid->tx_rate_nss);
+	wcid->tx_rate_set = true;
+	spin_unlock_irqrestore(&dev->mt76.lock, flags);
+}
+
+struct mt76_tx_status mt76x0_mac_fetch_tx_status(struct mt76x0_dev *dev)
+{
+	struct mt76_tx_status stat = {};
+	u32 stat2, stat1;
+
+	stat2 = mt76_rr(dev, MT_TX_STAT_FIFO_EXT);
+	stat1 = mt76_rr(dev, MT_TX_STAT_FIFO);
+
+	stat.valid = !!(stat1 & MT_TX_STAT_FIFO_VALID);
+	stat.success = !!(stat1 & MT_TX_STAT_FIFO_SUCCESS);
+	stat.aggr = !!(stat1 & MT_TX_STAT_FIFO_AGGR);
+	stat.ack_req = !!(stat1 & MT_TX_STAT_FIFO_ACKREQ);
+	stat.wcid = FIELD_GET(MT_TX_STAT_FIFO_WCID, stat1);
+	stat.rate = FIELD_GET(MT_TX_STAT_FIFO_RATE, stat1);
+
+	stat.retry = FIELD_GET(MT_TX_STAT_FIFO_EXT_RETRY, stat2);
+	stat.pktid = FIELD_GET(MT_TX_STAT_FIFO_EXT_PKTID, stat2);
+
+	return stat;
+}
+
+void mt76x0_send_tx_status(struct mt76x0_dev *dev, struct mt76_tx_status *stat, u8 *update)
+{
+	struct ieee80211_tx_info info = {};
+	struct ieee80211_sta *sta = NULL;
+	struct mt76_wcid *wcid = NULL;
+	struct mt76_sta *msta = NULL;
+
+	rcu_read_lock();
+	if (stat->wcid < ARRAY_SIZE(dev->wcid))
+		wcid = rcu_dereference(dev->wcid[stat->wcid]);
+
+	if (wcid) {
+		void *priv;
+		priv = msta = container_of(wcid, struct mt76_sta, wcid);
+		sta = container_of(priv, struct ieee80211_sta, drv_priv);
+	}
+
+	if (msta && stat->aggr) {
+		u32 stat_val, stat_cache;
+
+		stat_val = stat->rate;
+		stat_val |= ((u32) stat->retry) << 16;
+		stat_cache = msta->status.rate;
+		stat_cache |= ((u32) msta->status.retry) << 16;
+
+		if (*update == 0 && stat_val == stat_cache &&
+		    stat->wcid == msta->status.wcid && msta->n_frames < 32) {
+			msta->n_frames++;
+			goto out;
+		}
+
+		mt76_mac_fill_tx_status(dev, &info, &msta->status,
+					msta->n_frames);
+		msta->status = *stat;
+		msta->n_frames = 1;
+		*update = 0;
+	} else {
+		mt76_mac_fill_tx_status(dev, &info, stat, 1);
+		*update = 1;
+	}
+
+	spin_lock_bh(&dev->mac_lock);
+	ieee80211_tx_status_noskb(dev->mt76.hw, sta, &info);
+	spin_unlock_bh(&dev->mac_lock);
+out:
+	rcu_read_unlock();
+}
+
+void mt76x0_mac_set_protection(struct mt76x0_dev *dev, bool legacy_prot,
+				int ht_mode)
+{
+	int mode = ht_mode & IEEE80211_HT_OP_MODE_PROTECTION;
+	bool non_gf = !!(ht_mode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT);
+	u32 prot[6];
+	bool ht_rts[4] = {};
+	int i;
+
+	prot[0] = MT_PROT_NAV_SHORT |
+		  MT_PROT_TXOP_ALLOW_ALL |
+		  MT_PROT_RTS_THR_EN;
+	prot[1] = prot[0];
+	if (legacy_prot)
+		prot[1] |= MT_PROT_CTRL_CTS2SELF;
+
+	prot[2] = prot[4] = MT_PROT_NAV_SHORT | MT_PROT_TXOP_ALLOW_BW20;
+	prot[3] = prot[5] = MT_PROT_NAV_SHORT | MT_PROT_TXOP_ALLOW_ALL;
+
+	if (legacy_prot) {
+		prot[2] |= MT_PROT_RATE_CCK_11;
+		prot[3] |= MT_PROT_RATE_CCK_11;
+		prot[4] |= MT_PROT_RATE_CCK_11;
+		prot[5] |= MT_PROT_RATE_CCK_11;
+	} else {
+		prot[2] |= MT_PROT_RATE_OFDM_24;
+		prot[3] |= MT_PROT_RATE_DUP_OFDM_24;
+		prot[4] |= MT_PROT_RATE_OFDM_24;
+		prot[5] |= MT_PROT_RATE_DUP_OFDM_24;
+	}
+
+	switch (mode) {
+	case IEEE80211_HT_OP_MODE_PROTECTION_NONE:
+		break;
+
+	case IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER:
+		ht_rts[0] = ht_rts[1] = ht_rts[2] = ht_rts[3] = true;
+		break;
+
+	case IEEE80211_HT_OP_MODE_PROTECTION_20MHZ:
+		ht_rts[1] = ht_rts[3] = true;
+		break;
+
+	case IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED:
+		ht_rts[0] = ht_rts[1] = ht_rts[2] = ht_rts[3] = true;
+		break;
+	}
+
+	if (non_gf)
+		ht_rts[2] = ht_rts[3] = true;
+
+	for (i = 0; i < 4; i++)
+		if (ht_rts[i])
+			prot[i + 2] |= MT_PROT_CTRL_RTS_CTS;
+
+	for (i = 0; i < 6; i++)
+		mt76_wr(dev, MT_CCK_PROT_CFG + i * 4, prot[i]);
+}
+
+void mt76x0_mac_set_short_preamble(struct mt76x0_dev *dev, bool short_preamb)
+{
+	if (short_preamb)
+		mt76_set(dev, MT_AUTO_RSP_CFG, MT_AUTO_RSP_PREAMB_SHORT);
+	else
+		mt76_clear(dev, MT_AUTO_RSP_CFG, MT_AUTO_RSP_PREAMB_SHORT);
+}
+
+void mt76x0_mac_config_tsf(struct mt76x0_dev *dev, bool enable, int interval)
+{
+	u32 val = mt76_rr(dev, MT_BEACON_TIME_CFG);
+
+	val &= ~(MT_BEACON_TIME_CFG_TIMER_EN |
+		 MT_BEACON_TIME_CFG_SYNC_MODE |
+		 MT_BEACON_TIME_CFG_TBTT_EN);
+
+	if (!enable) {
+		mt76_wr(dev, MT_BEACON_TIME_CFG, val);
+		return;
+	}
+
+	val &= ~MT_BEACON_TIME_CFG_INTVAL;
+	val |= FIELD_PREP(MT_BEACON_TIME_CFG_INTVAL, interval << 4) |
+		MT_BEACON_TIME_CFG_TIMER_EN |
+		MT_BEACON_TIME_CFG_SYNC_MODE |
+		MT_BEACON_TIME_CFG_TBTT_EN;
+}
+
+static void mt76x0_check_mac_err(struct mt76x0_dev *dev)
+{
+	u32 val = mt76_rr(dev, 0x10f4);
+
+	if (!(val & BIT(29)) || !(val & (BIT(7) | BIT(5))))
+		return;
+
+	dev_err(dev->mt76.dev, "Error: MAC specific condition occurred\n");
+
+	mt76_set(dev, MT_MAC_SYS_CTRL, MT_MAC_SYS_CTRL_RESET_CSR);
+	udelay(10);
+	mt76_clear(dev, MT_MAC_SYS_CTRL, MT_MAC_SYS_CTRL_RESET_CSR);
+}
+void mt76x0_mac_work(struct work_struct *work)
+{
+	struct mt76x0_dev *dev = container_of(work, struct mt76x0_dev,
+					       mac_work.work);
+	struct {
+		u32 addr_base;
+		u32 span;
+		u64 *stat_base;
+	} spans[] = {
+		{ MT_RX_STA_CNT0,	3,	dev->stats.rx_stat },
+		{ MT_TX_STA_CNT0,	3,	dev->stats.tx_stat },
+		{ MT_TX_AGG_STAT,	1,	dev->stats.aggr_stat },
+		{ MT_MPDU_DENSITY_CNT,	1,	dev->stats.zero_len_del },
+		{ MT_TX_AGG_CNT_BASE0,	8,	&dev->stats.aggr_n[0] },
+		{ MT_TX_AGG_CNT_BASE1,	8,	&dev->stats.aggr_n[16] },
+	};
+	u32 sum, n;
+	int i, j, k;
+
+	/* Note: using MCU_RANDOM_READ is actually slower then reading all the
+	 *	 registers by hand.  MCU takes ca. 20ms to complete read of 24
+	 *	 registers while reading them one by one will takes roughly
+	 *	 24*200us =~ 5ms.
+	 */
+
+	k = 0;
+	n = 0;
+	sum = 0;
+	for (i = 0; i < ARRAY_SIZE(spans); i++)
+		for (j = 0; j < spans[i].span; j++) {
+			u32 val = mt76_rr(dev, spans[i].addr_base + j * 4);
+
+			spans[i].stat_base[j * 2] += val & 0xffff;
+			spans[i].stat_base[j * 2 + 1] += val >> 16;
+
+			/* Calculate average AMPDU length */
+			if (spans[i].addr_base != MT_TX_AGG_CNT_BASE0 &&
+			    spans[i].addr_base != MT_TX_AGG_CNT_BASE1)
+				continue;
+
+			n += (val >> 16) + (val & 0xffff);
+			sum += (val & 0xffff) * (1 + k * 2) +
+				(val >> 16) * (2 + k * 2);
+			k++;
+		}
+
+	atomic_set(&dev->avg_ampdu_len, n ? DIV_ROUND_CLOSEST(sum, n) : 1);
+
+	mt76x0_check_mac_err(dev);
+
+	ieee80211_queue_delayed_work(dev->mt76.hw, &dev->mac_work, 10 * HZ);
+}
+
+void
+mt76x0_mac_wcid_setup(struct mt76x0_dev *dev, u8 idx, u8 vif_idx, u8 *mac)
+{
+	u8 zmac[ETH_ALEN] = {};
+	u32 attr;
+
+	attr = FIELD_PREP(MT_WCID_ATTR_BSS_IDX, vif_idx & 7) |
+	       FIELD_PREP(MT_WCID_ATTR_BSS_IDX_EXT, !!(vif_idx & 8));
+
+	mt76_wr(dev, MT_WCID_ATTR(idx), attr);
+
+	if (mac)
+		memcpy(zmac, mac, sizeof(zmac));
+
+	mt76x0_addr_wr(dev, MT_WCID_ADDR(idx), zmac);
+}
+
+void mt76x0_mac_set_ampdu_factor(struct mt76x0_dev *dev)
+{
+	struct ieee80211_sta *sta;
+	struct mt76_wcid *wcid;
+	void *msta;
+	u8 min_factor = 3;
+	int i;
+
+	rcu_read_lock();
+	for (i = 0; i < ARRAY_SIZE(dev->wcid); i++) {
+		wcid = rcu_dereference(dev->wcid[i]);
+		if (!wcid)
+			continue;
+
+		msta = container_of(wcid, struct mt76_sta, wcid);
+		sta = container_of(msta, struct ieee80211_sta, drv_priv);
+
+		min_factor = min(min_factor, sta->ht_cap.ampdu_factor);
+	}
+	rcu_read_unlock();
+
+	mt76_wr(dev, MT_MAX_LEN_CFG, 0xa0fff |
+		   FIELD_PREP(MT_MAX_LEN_CFG_AMPDU, min_factor));
+}
+
+static void
+mt76_mac_process_rate(struct ieee80211_rx_status *status, u16 rate)
+{
+	u8 idx = FIELD_GET(MT_RXWI_RATE_INDEX, rate);
+
+	switch (FIELD_GET(MT_RXWI_RATE_PHY, rate)) {
+	case MT_PHY_TYPE_OFDM:
+		if (idx >= 8)
+			idx = 0;
+
+		if (status->band == NL80211_BAND_2GHZ)
+			idx += 4;
+
+		status->rate_idx = idx;
+		return;
+	case MT_PHY_TYPE_CCK:
+		if (idx >= 8) {
+			idx -= 8;
+			status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
+		}
+
+		if (idx >= 4)
+			idx = 0;
+
+		status->rate_idx = idx;
+		return;
+	case MT_PHY_TYPE_HT_GF:
+		status->enc_flags |= RX_ENC_FLAG_HT_GF;
+		/* fall through */
+	case MT_PHY_TYPE_HT:
+		status->encoding = RX_ENC_HT;
+		status->rate_idx = idx;
+		break;
+	case MT_PHY_TYPE_VHT:
+		status->encoding = RX_ENC_VHT;
+		status->rate_idx = FIELD_GET(MT_RATE_INDEX_VHT_IDX, idx);
+		status->nss = FIELD_GET(MT_RATE_INDEX_VHT_NSS, idx) + 1;
+		break;
+	default:
+		WARN_ON(1);
+		return;
+	}
+
+	if (rate & MT_RXWI_RATE_LDPC)
+		status->enc_flags |= RX_ENC_FLAG_LDPC;
+
+	if (rate & MT_RXWI_RATE_SGI)
+		status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
+
+	if (rate & MT_RXWI_RATE_STBC)
+		status->enc_flags |= 1 << RX_ENC_FLAG_STBC_SHIFT;
+
+	switch (FIELD_GET(MT_RXWI_RATE_BW, rate)) {
+	case MT_PHY_BW_20:
+		break;
+	case MT_PHY_BW_40:
+		status->bw = RATE_INFO_BW_40;
+		break;
+	case MT_PHY_BW_80:
+		status->bw = RATE_INFO_BW_80;
+		break;
+	default:
+		WARN_ON(1);
+		break;
+	}
+}
+
+static void
+mt76x0_rx_monitor_beacon(struct mt76x0_dev *dev, struct mt76x0_rxwi *rxwi,
+			  u16 rate, int rssi)
+{
+	dev->bcn_phy_mode = FIELD_GET(MT_RXWI_RATE_PHY, rate);
+	dev->avg_rssi = ((dev->avg_rssi * 15) / 16 + (rssi << 8)) / 256;
+}
+
+static int
+mt76x0_rx_is_our_beacon(struct mt76x0_dev *dev, u8 *data)
+{
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)data;
+
+	return ieee80211_is_beacon(hdr->frame_control) &&
+		ether_addr_equal(hdr->addr2, dev->ap_bssid);
+}
+
+u32 mt76x0_mac_process_rx(struct mt76x0_dev *dev, struct sk_buff *skb,
+			u8 *data, void *rxi)
+{
+	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
+	struct mt76x0_rxwi *rxwi = rxi;
+	u32 len, ctl = le32_to_cpu(rxwi->ctl);
+	u16 rate = le16_to_cpu(rxwi->rate);
+	int rssi;
+
+	len = FIELD_GET(MT_RXWI_CTL_MPDU_LEN, ctl);
+	if (WARN_ON(len < 10))
+		return 0;
+
+	if (rxwi->rxinfo & cpu_to_le32(MT_RXINFO_DECRYPT)) {
+		status->flag |= RX_FLAG_DECRYPTED;
+		status->flag |= RX_FLAG_IV_STRIPPED | RX_FLAG_MMIC_STRIPPED;
+	}
+
+	status->chains = BIT(0);
+	rssi = mt76x0_phy_get_rssi(dev, rxwi);
+	status->chain_signal[0] = status->signal = rssi;
+	status->freq = dev->mt76.chandef.chan->center_freq;
+	status->band = dev->mt76.chandef.chan->band;
+
+	mt76_mac_process_rate(status, rate);
+
+	spin_lock_bh(&dev->con_mon_lock);
+	if (mt76x0_rx_is_our_beacon(dev, data)) {
+		mt76x0_rx_monitor_beacon(dev, rxwi, rate, rssi);
+	} else if (rxwi->rxinfo & cpu_to_le32(MT_RXINFO_U2M)) {
+		if (dev->avg_rssi == 0)
+			dev->avg_rssi = rssi;
+		else
+			dev->avg_rssi = (dev->avg_rssi * 15) / 16 + rssi / 16;
+
+	}
+	spin_unlock_bh(&dev->con_mon_lock);
+
+	return len;
+}
+
+static enum mt76_cipher_type
+mt76_mac_get_key_info(struct ieee80211_key_conf *key, u8 *key_data)
+{
+	memset(key_data, 0, 32);
+	if (!key)
+		return MT_CIPHER_NONE;
+
+	if (key->keylen > 32)
+		return MT_CIPHER_NONE;
+
+	memcpy(key_data, key->key, key->keylen);
+
+	switch (key->cipher) {
+	case WLAN_CIPHER_SUITE_WEP40:
+		return MT_CIPHER_WEP40;
+	case WLAN_CIPHER_SUITE_WEP104:
+		return MT_CIPHER_WEP104;
+	case WLAN_CIPHER_SUITE_TKIP:
+		return MT_CIPHER_TKIP;
+	case WLAN_CIPHER_SUITE_CCMP:
+		return MT_CIPHER_AES_CCMP;
+	default:
+		return MT_CIPHER_NONE;
+	}
+}
+
+int mt76x0_mac_wcid_set_key(struct mt76x0_dev *dev, u8 idx,
+			  struct ieee80211_key_conf *key)
+{
+	enum mt76_cipher_type cipher;
+	u8 key_data[32];
+	u8 iv_data[8];
+	u32 val;
+
+	cipher = mt76_mac_get_key_info(key, key_data);
+	if (cipher == MT_CIPHER_NONE && key)
+		return -EINVAL;
+
+	trace_mt76x0_set_key(&dev->mt76, idx);
+
+	mt76_wr_copy(dev, MT_WCID_KEY(idx), key_data, sizeof(key_data));
+
+	memset(iv_data, 0, sizeof(iv_data));
+	if (key) {
+		iv_data[3] = key->keyidx << 6;
+		if (cipher >= MT_CIPHER_TKIP) {
+			/* Note: start with 1 to comply with spec,
+			 *	 (see comment on common/cmm_wpa.c:4291).
+			 */
+			iv_data[0] |= 1;
+			iv_data[3] |= 0x20;
+		}
+	}
+	mt76_wr_copy(dev, MT_WCID_IV(idx), iv_data, sizeof(iv_data));
+
+	val = mt76_rr(dev, MT_WCID_ATTR(idx));
+	val &= ~MT_WCID_ATTR_PKEY_MODE & ~MT_WCID_ATTR_PKEY_MODE_EXT;
+	val |= FIELD_PREP(MT_WCID_ATTR_PKEY_MODE, cipher & 7) |
+	       FIELD_PREP(MT_WCID_ATTR_PKEY_MODE_EXT, cipher >> 3);
+	val &= ~MT_WCID_ATTR_PAIRWISE;
+	val |= MT_WCID_ATTR_PAIRWISE *
+		!!(key && key->flags & IEEE80211_KEY_FLAG_PAIRWISE);
+	mt76_wr(dev, MT_WCID_ATTR(idx), val);
+
+	return 0;
+}
+
+int mt76x0_mac_shared_key_setup(struct mt76x0_dev *dev, u8 vif_idx, u8 key_idx,
+			      struct ieee80211_key_conf *key)
+{
+	enum mt76_cipher_type cipher;
+	u8 key_data[32];
+	u32 val;
+
+	cipher = mt76_mac_get_key_info(key, key_data);
+	if (cipher == MT_CIPHER_NONE && key)
+		return -EINVAL;
+
+	trace_mt76x0_set_shared_key(&dev->mt76, vif_idx, key_idx);
+
+	mt76_wr_copy(dev, MT_SKEY(vif_idx, key_idx),
+			key_data, sizeof(key_data));
+
+	val = mt76_rr(dev, MT_SKEY_MODE(vif_idx));
+	val &= ~(MT_SKEY_MODE_MASK << MT_SKEY_MODE_SHIFT(vif_idx, key_idx));
+	val |= cipher << MT_SKEY_MODE_SHIFT(vif_idx, key_idx);
+	mt76_wr(dev, MT_SKEY_MODE(vif_idx), val);
+
+	return 0;
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.h
new file mode 100644
index 000000000000..bea067b71c13
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.h
@@ -0,0 +1,154 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __MT76_MAC_H
+#define __MT76_MAC_H
+
+/* Note: values in original "RSSI" and "SNR" fields are not actually what they
+ *	 are called for MT76X0U, names used by this driver are educated guesses
+ *	 (see vendor mac/ral_omac.c).
+ */
+struct mt76x0_rxwi {
+	__le32 rxinfo;
+
+	__le32 ctl;
+
+	__le16 tid_sn;
+	__le16 rate;
+
+	s8 rssi[4];
+
+	__le32 bbp_rxinfo[4];
+} __packed __aligned(4);
+
+#define MT_RXINFO_BA			BIT(0)
+#define MT_RXINFO_DATA			BIT(1)
+#define MT_RXINFO_NULL			BIT(2)
+#define MT_RXINFO_FRAG			BIT(3)
+#define MT_RXINFO_U2M			BIT(4)
+#define MT_RXINFO_MULTICAST		BIT(5)
+#define MT_RXINFO_BROADCAST		BIT(6)
+#define MT_RXINFO_MYBSS			BIT(7)
+#define MT_RXINFO_CRCERR		BIT(8)
+#define MT_RXINFO_ICVERR		BIT(9)
+#define MT_RXINFO_MICERR		BIT(10)
+#define MT_RXINFO_AMSDU			BIT(11)
+#define MT_RXINFO_HTC			BIT(12)
+#define MT_RXINFO_RSSI			BIT(13)
+#define MT_RXINFO_L2PAD			BIT(14)
+#define MT_RXINFO_AMPDU			BIT(15)
+#define MT_RXINFO_DECRYPT		BIT(16)
+#define MT_RXINFO_BSSIDX3		BIT(17)
+#define MT_RXINFO_WAPI_KEY		BIT(18)
+#define MT_RXINFO_PN_LEN		GENMASK(21, 19)
+#define MT_RXINFO_SW_PKT_80211		BIT(22)
+#define MT_RXINFO_TCP_SUM_BYPASS	BIT(28)
+#define MT_RXINFO_IP_SUM_BYPASS		BIT(29)
+#define MT_RXINFO_TCP_SUM_ERR		BIT(30)
+#define MT_RXINFO_IP_SUM_ERR		BIT(31)
+
+#define MT_RXWI_CTL_WCID		GENMASK(7, 0)
+#define MT_RXWI_CTL_KEY_IDX		GENMASK(9, 8)
+#define MT_RXWI_CTL_BSS_IDX		GENMASK(12, 10)
+#define MT_RXWI_CTL_UDF			GENMASK(15, 13)
+#define MT_RXWI_CTL_MPDU_LEN		GENMASK(27, 16)
+#define MT_RXWI_CTL_TID			GENMASK(31, 28)
+
+#define MT_RXWI_FRAG			GENMASK(3, 0)
+#define MT_RXWI_SN			GENMASK(15, 4)
+
+#define MT_RXWI_RATE_INDEX		GENMASK(5, 0)
+#define MT_RXWI_RATE_LDPC		BIT(6)
+#define MT_RXWI_RATE_BW			GENMASK(8, 7)
+#define MT_RXWI_RATE_SGI		BIT(9)
+#define MT_RXWI_RATE_STBC		BIT(10)
+#define MT_RXWI_RATE_LDPC_ETXBF		BIT(11)
+#define MT_RXWI_RATE_SND		BIT(12)
+#define MT_RXWI_RATE_PHY		GENMASK(15, 13)
+
+#define MT_RATE_INDEX_VHT_IDX		GENMASK(3, 0)
+#define MT_RATE_INDEX_VHT_NSS		GENMASK(5, 4)
+
+#define MT_RXWI_GAIN_RSSI_VAL		GENMASK(5, 0)
+#define MT_RXWI_GAIN_RSSI_LNA_ID	GENMASK(7, 6)
+#define MT_RXWI_ANT_AUX_LNA		BIT(7)
+
+#define MT_RXWI_EANT_ENC_ANT_ID		GENMASK(7, 0)
+
+enum mt76_phy_bandwidth {
+	MT_PHY_BW_20,
+	MT_PHY_BW_40,
+	MT_PHY_BW_80,
+};
+
+struct mt76_txwi {
+	__le16 flags;
+	__le16 rate_ctl;
+	u8 ack_ctl;
+	u8 wcid;
+	__le16 len_ctl;
+	__le32 iv;
+	__le32 eiv;
+	u8 aid;
+	u8 txstream;
+	u8 ctl2;
+	u8 pktid;
+} __packed __aligned(4);
+
+#define MT_TXWI_FLAGS_FRAG		BIT(0)
+#define MT_TXWI_FLAGS_MMPS		BIT(1)
+#define MT_TXWI_FLAGS_CFACK		BIT(2)
+#define MT_TXWI_FLAGS_TS		BIT(3)
+#define MT_TXWI_FLAGS_AMPDU		BIT(4)
+#define MT_TXWI_FLAGS_MPDU_DENSITY	GENMASK(7, 5)
+#define MT_TXWI_FLAGS_TXOP		GENMASK(9, 8)
+#define MT_TXWI_FLAGS_CWMIN		GENMASK(12, 10)
+#define MT_TXWI_FLAGS_NO_RATE_FALLBACK	BIT(13)
+#define MT_TXWI_FLAGS_TX_RPT		BIT(14)
+#define MT_TXWI_FLAGS_TX_RATE_LUT	BIT(15)
+
+#define MT_TXWI_RATE_MCS		GENMASK(6, 0)
+#define MT_TXWI_RATE_BW			BIT(7)
+#define MT_TXWI_RATE_SGI		BIT(8)
+#define MT_TXWI_RATE_STBC		GENMASK(10, 9)
+#define MT_TXWI_RATE_PHY_MODE		GENMASK(15, 14)
+
+#define MT_TXWI_ACK_CTL_REQ		BIT(0)
+#define MT_TXWI_ACK_CTL_NSEQ		BIT(1)
+#define MT_TXWI_ACK_CTL_BA_WINDOW	GENMASK(7, 2)
+
+#define MT_TXWI_LEN_BYTE_CNT		GENMASK(11, 0)
+
+#define MT_TXWI_CTL_TX_POWER_ADJ	GENMASK(3, 0)
+#define MT_TXWI_CTL_CHAN_CHECK_PKT	BIT(4)
+#define MT_TXWI_CTL_PIFS_REV		BIT(6)
+
+#define MT_TXWI_PKTID_PROBE             BIT(7)
+
+u32 mt76x0_mac_process_rx(struct mt76x0_dev *dev, struct sk_buff *skb,
+			u8 *data, void *rxi);
+int mt76x0_mac_wcid_set_key(struct mt76x0_dev *dev, u8 idx,
+			  struct ieee80211_key_conf *key);
+void mt76x0_mac_wcid_set_rate(struct mt76x0_dev *dev, struct mt76_wcid *wcid,
+			    const struct ieee80211_tx_rate *rate);
+
+int mt76x0_mac_shared_key_setup(struct mt76x0_dev *dev, u8 vif_idx, u8 key_idx,
+			      struct ieee80211_key_conf *key);
+u16 mt76x0_mac_tx_rate_val(struct mt76x0_dev *dev,
+			 const struct ieee80211_tx_rate *rate, u8 *nss_val);
+struct mt76_tx_status
+mt76x0_mac_fetch_tx_status(struct mt76x0_dev *dev);
+void mt76x0_send_tx_status(struct mt76x0_dev *dev, struct mt76_tx_status *stat, u8 *update);
+
+#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
new file mode 100644
index 000000000000..cf6ffb1ba4a2
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
@@ -0,0 +1,403 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include "mt76x0.h"
+#include "mac.h"
+#include <linux/etherdevice.h>
+
+static int mt76x0_start(struct ieee80211_hw *hw)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	int ret;
+
+	mutex_lock(&dev->mutex);
+
+	ret = mt76x0_mac_start(dev);
+	if (ret)
+		goto out;
+
+	ieee80211_queue_delayed_work(dev->mt76.hw, &dev->mac_work,
+				     MT_CALIBRATE_INTERVAL);
+	ieee80211_queue_delayed_work(dev->mt76.hw, &dev->cal_work,
+				     MT_CALIBRATE_INTERVAL);
+out:
+	mutex_unlock(&dev->mutex);
+	return ret;
+}
+
+static void mt76x0_stop(struct ieee80211_hw *hw)
+{
+	struct mt76x0_dev *dev = hw->priv;
+
+	mutex_lock(&dev->mutex);
+
+	cancel_delayed_work_sync(&dev->cal_work);
+	cancel_delayed_work_sync(&dev->mac_work);
+	mt76x0_mac_stop(dev);
+
+	mutex_unlock(&dev->mutex);
+}
+
+
+static int mt76x0_add_interface(struct ieee80211_hw *hw,
+				 struct ieee80211_vif *vif)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	struct mt76_vif *mvif = (struct mt76_vif *) vif->drv_priv;
+	unsigned int idx;
+
+	idx = ffs(~dev->vif_mask);
+	if (!idx || idx > 8)
+		return -ENOSPC;
+
+	idx--;
+	dev->vif_mask |= BIT(idx);
+
+	mvif->idx = idx;
+	mvif->group_wcid.idx = GROUP_WCID(idx);
+	mvif->group_wcid.hw_key_idx = -1;
+
+	return 0;
+}
+
+static void mt76x0_remove_interface(struct ieee80211_hw *hw,
+				     struct ieee80211_vif *vif)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	struct mt76_vif *mvif = (struct mt76_vif *) vif->drv_priv;
+	unsigned int wcid = mvif->group_wcid.idx;
+
+	dev->wcid_mask[wcid / BITS_PER_LONG] &= ~BIT(wcid % BITS_PER_LONG);
+}
+
+static int mt76x0_config(struct ieee80211_hw *hw, u32 changed)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	int ret = 0;
+
+	mutex_lock(&dev->mutex);
+
+	if (changed & IEEE80211_CONF_CHANGE_MONITOR) {
+		if (!(hw->conf.flags & IEEE80211_CONF_MONITOR))
+			dev->rxfilter |= MT_RX_FILTR_CFG_PROMISC;
+		else
+			dev->rxfilter &= ~MT_RX_FILTR_CFG_PROMISC;
+
+		mt76_wr(dev, MT_RX_FILTR_CFG, dev->rxfilter);
+	}
+
+	if (changed & IEEE80211_CONF_CHANGE_CHANNEL) {
+		ieee80211_stop_queues(hw);
+		ret = mt76x0_phy_set_channel(dev, &hw->conf.chandef);
+		ieee80211_wake_queues(hw);
+	}
+
+	mutex_unlock(&dev->mutex);
+
+	return ret;
+}
+
+static void
+mt76_configure_filter(struct ieee80211_hw *hw, unsigned int changed_flags,
+		      unsigned int *total_flags, u64 multicast)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	u32 flags = 0;
+
+#define MT76_FILTER(_flag, _hw) do { \
+		flags |= *total_flags & FIF_##_flag;			\
+		dev->rxfilter &= ~(_hw);				\
+		dev->rxfilter |= !(flags & FIF_##_flag) * (_hw);	\
+	} while (0)
+
+	mutex_lock(&dev->mutex);
+
+	dev->rxfilter &= ~MT_RX_FILTR_CFG_OTHER_BSS;
+
+	MT76_FILTER(FCSFAIL, MT_RX_FILTR_CFG_CRC_ERR);
+	MT76_FILTER(PLCPFAIL, MT_RX_FILTR_CFG_PHY_ERR);
+	MT76_FILTER(CONTROL, MT_RX_FILTR_CFG_ACK |
+			     MT_RX_FILTR_CFG_CTS |
+			     MT_RX_FILTR_CFG_CFEND |
+			     MT_RX_FILTR_CFG_CFACK |
+			     MT_RX_FILTR_CFG_BA |
+			     MT_RX_FILTR_CFG_CTRL_RSV);
+	MT76_FILTER(PSPOLL, MT_RX_FILTR_CFG_PSPOLL);
+
+	*total_flags = flags;
+	mt76_wr(dev, MT_RX_FILTR_CFG, dev->rxfilter);
+
+	mutex_unlock(&dev->mutex);
+}
+
+static void
+mt76x0_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			 struct ieee80211_bss_conf *info, u32 changed)
+{
+	struct mt76x0_dev *dev = hw->priv;
+
+	mutex_lock(&dev->mutex);
+
+	if (changed & BSS_CHANGED_ASSOC)
+		mt76x0_phy_con_cal_onoff(dev, info);
+
+	if (changed & BSS_CHANGED_BSSID) {
+		mt76x0_addr_wr(dev, MT_MAC_BSSID_DW0, info->bssid);
+
+		/* Note: this is a hack because beacon_int is not changed
+		 *	 on leave nor is any more appropriate event generated.
+		 *	 rt2x00 doesn't seem to be bothered though.
+		 */
+		if (is_zero_ether_addr(info->bssid))
+			mt76x0_mac_config_tsf(dev, false, 0);
+	}
+
+	if (changed & BSS_CHANGED_BASIC_RATES) {
+		mt76_wr(dev, MT_LEGACY_BASIC_RATE, info->basic_rates);
+		mt76_wr(dev, MT_HT_FBK_CFG0, 0x65432100);
+		mt76_wr(dev, MT_HT_FBK_CFG1, 0xedcba980);
+		mt76_wr(dev, MT_LG_FBK_CFG0, 0xedcba988);
+		mt76_wr(dev, MT_LG_FBK_CFG1, 0x00002100);
+	}
+
+	if (changed & BSS_CHANGED_BEACON_INT)
+		mt76x0_mac_config_tsf(dev, true, info->beacon_int);
+
+	if (changed & BSS_CHANGED_HT || changed & BSS_CHANGED_ERP_CTS_PROT)
+		mt76x0_mac_set_protection(dev, info->use_cts_prot,
+					   info->ht_operation_mode);
+
+	if (changed & BSS_CHANGED_ERP_PREAMBLE)
+		mt76x0_mac_set_short_preamble(dev, info->use_short_preamble);
+
+	if (changed & BSS_CHANGED_ERP_SLOT) {
+		int slottime = info->use_short_slot ? 9 : 20;
+
+		mt76_rmw_field(dev, MT_BKOFF_SLOT_CFG,
+			       MT_BKOFF_SLOT_CFG_SLOTTIME, slottime);
+	}
+
+	if (changed & BSS_CHANGED_ASSOC)
+		mt76x0_phy_recalibrate_after_assoc(dev);
+
+	mutex_unlock(&dev->mutex);
+}
+
+static int
+mt76x0_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		struct ieee80211_sta *sta)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	struct mt76_sta *msta = (struct mt76_sta *) sta->drv_priv;
+	struct mt76_vif *mvif = (struct mt76_vif *) vif->drv_priv;
+	int ret = 0;
+	int idx = 0;
+
+	mutex_lock(&dev->mutex);
+
+	idx = mt76_wcid_alloc(dev->wcid_mask, ARRAY_SIZE(dev->wcid));
+	if (idx < 0) {
+		ret = -ENOSPC;
+		goto out;
+	}
+
+	msta->wcid.idx = idx;
+	msta->wcid.hw_key_idx = -1;
+	mt76x0_mac_wcid_setup(dev, idx, mvif->idx, sta->addr);
+	mt76_clear(dev, MT_WCID_DROP(idx), MT_WCID_DROP_MASK(idx));
+	rcu_assign_pointer(dev->wcid[idx], &msta->wcid);
+	mt76x0_mac_set_ampdu_factor(dev);
+
+out:
+	mutex_unlock(&dev->mutex);
+
+	return ret;
+}
+
+static int
+mt76x0_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		   struct ieee80211_sta *sta)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	struct mt76_sta *msta = (struct mt76_sta *) sta->drv_priv;
+	int idx = msta->wcid.idx;
+
+	mutex_lock(&dev->mutex);
+	rcu_assign_pointer(dev->wcid[idx], NULL);
+	mt76_set(dev, MT_WCID_DROP(idx), MT_WCID_DROP_MASK(idx));
+	dev->wcid_mask[idx / BITS_PER_LONG] &= ~BIT(idx % BITS_PER_LONG);
+	mt76x0_mac_wcid_setup(dev, idx, 0, NULL);
+	mt76x0_mac_set_ampdu_factor(dev);
+	mutex_unlock(&dev->mutex);
+
+	return 0;
+}
+
+static void
+mt76x0_sta_notify(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		   enum sta_notify_cmd cmd, struct ieee80211_sta *sta)
+{
+}
+
+static void
+mt76x0_sw_scan(struct ieee80211_hw *hw,
+		struct ieee80211_vif *vif,
+		const u8 *mac_addr)
+{
+	struct mt76x0_dev *dev = hw->priv;
+
+	cancel_delayed_work_sync(&dev->cal_work);
+	mt76x0_agc_save(dev);
+	set_bit(MT76_SCANNING, &dev->mt76.state);
+}
+
+static void
+mt76x0_sw_scan_complete(struct ieee80211_hw *hw,
+			 struct ieee80211_vif *vif)
+{
+	struct mt76x0_dev *dev = hw->priv;
+
+	mt76x0_agc_restore(dev);
+	clear_bit(MT76_SCANNING, &dev->mt76.state);
+
+	ieee80211_queue_delayed_work(dev->mt76.hw, &dev->cal_work,
+				     MT_CALIBRATE_INTERVAL);
+}
+
+static int
+mt76x0_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
+		struct ieee80211_vif *vif, struct ieee80211_sta *sta,
+		struct ieee80211_key_conf *key)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	struct mt76_vif *mvif = (struct mt76_vif *) vif->drv_priv;
+	struct mt76_sta *msta = sta ? (struct mt76_sta *) sta->drv_priv : NULL;
+	struct mt76_wcid *wcid = msta ? &msta->wcid : &mvif->group_wcid;
+	int idx = key->keyidx;
+	int ret;
+
+	if (cmd == SET_KEY) {
+		key->hw_key_idx = wcid->idx;
+		wcid->hw_key_idx = idx;
+	} else {
+		if (idx == wcid->hw_key_idx)
+			wcid->hw_key_idx = -1;
+
+		key = NULL;
+	}
+
+	if (!msta) {
+		if (key || wcid->hw_key_idx == idx) {
+			ret = mt76x0_mac_wcid_set_key(dev, wcid->idx, key);
+			if (ret)
+				return ret;
+		}
+
+		return mt76x0_mac_shared_key_setup(dev, mvif->idx, idx, key);
+	}
+
+	return mt76x0_mac_wcid_set_key(dev, msta->wcid.idx, key);
+}
+
+static int mt76x0_set_rts_threshold(struct ieee80211_hw *hw, u32 value)
+{
+	struct mt76x0_dev *dev = hw->priv;
+
+	mt76_rmw_field(dev, MT_TX_RTS_CFG, MT_TX_RTS_CFG_THRESH, value);
+
+	return 0;
+}
+
+static int
+mt76_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		  struct ieee80211_ampdu_params *params)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	u16 tid = params->tid;
+	u16 *ssn = &params->ssn;
+	struct mt76_sta *msta = (struct mt76_sta *) sta->drv_priv;
+
+	WARN_ON(msta->wcid.idx > N_WCIDS);
+
+	switch (action) {
+	case IEEE80211_AMPDU_RX_START:
+		mt76_set(dev, MT_WCID_ADDR(msta->wcid.idx) + 4, BIT(16 + tid));
+		break;
+	case IEEE80211_AMPDU_RX_STOP:
+		mt76_clear(dev, MT_WCID_ADDR(msta->wcid.idx) + 4, BIT(16 + tid));
+		break;
+	case IEEE80211_AMPDU_TX_OPERATIONAL:
+		ieee80211_send_bar(vif, sta->addr, tid, msta->agg_ssn[tid]);
+		break;
+	case IEEE80211_AMPDU_TX_STOP_FLUSH:
+	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
+		break;
+	case IEEE80211_AMPDU_TX_START:
+		msta->agg_ssn[tid] = *ssn << 4;
+		ieee80211_start_tx_ba_cb_irqsafe(vif, sta->addr, tid);
+		break;
+	case IEEE80211_AMPDU_TX_STOP_CONT:
+		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
+		break;
+	}
+
+	return 0;
+}
+
+static void
+mt76_sta_rate_tbl_update(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			 struct ieee80211_sta *sta)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	struct mt76_sta *msta = (struct mt76_sta *) sta->drv_priv;
+	struct ieee80211_sta_rates *rates;
+	struct ieee80211_tx_rate rate = {};
+
+	rcu_read_lock();
+	rates = rcu_dereference(sta->rates);
+
+	if (!rates)
+		goto out;
+
+	rate.idx = rates->rate[0].idx;
+	rate.flags = rates->rate[0].flags;
+	mt76x0_mac_wcid_set_rate(dev, &msta->wcid, &rate);
+
+out:
+	rcu_read_unlock();
+}
+
+const struct ieee80211_ops mt76x0_ops = {
+	.tx = mt76x0_tx,
+	.start = mt76x0_start,
+	.stop = mt76x0_stop,
+	.add_interface = mt76x0_add_interface,
+	.remove_interface = mt76x0_remove_interface,
+	.config = mt76x0_config,
+	.configure_filter = mt76_configure_filter,
+	.bss_info_changed = mt76x0_bss_info_changed,
+	.sta_add = mt76x0_sta_add,
+	.sta_remove = mt76x0_sta_remove,
+	.sta_notify = mt76x0_sta_notify,
+	.set_key = mt76x0_set_key,
+	.conf_tx = mt76x0_conf_tx,
+	.sw_scan_start = mt76x0_sw_scan,
+	.sw_scan_complete = mt76x0_sw_scan_complete,
+	.ampdu_action = mt76_ampdu_action,
+	.sta_rate_tbl_update = mt76_sta_rate_tbl_update,
+	.set_rts_threshold = mt76x0_set_rts_threshold,
+};
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x0/mcu.c
new file mode 100644
index 000000000000..8affacbab90a
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mcu.c
@@ -0,0 +1,656 @@
+/*
+ * (c) Copyright 2002-2010, Ralink Technology, Inc.
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/firmware.h>
+#include <linux/delay.h>
+#include <linux/usb.h>
+#include <linux/skbuff.h>
+
+#include "mt76x0.h"
+#include "dma.h"
+#include "mcu.h"
+#include "usb.h"
+#include "trace.h"
+
+#define MCU_FW_URB_MAX_PAYLOAD		0x38f8
+#define MCU_FW_URB_SIZE			(MCU_FW_URB_MAX_PAYLOAD + 12)
+#define MCU_RESP_URB_SIZE		1024
+
+static inline int firmware_running(struct mt76x0_dev *dev)
+{
+	return mt76_rr(dev, MT_MCU_COM_REG0) == 1;
+}
+
+static inline void skb_put_le32(struct sk_buff *skb, u32 val)
+{
+	put_unaligned_le32(val, skb_put(skb, 4));
+}
+
+static inline void mt76x0_dma_skb_wrap_cmd(struct sk_buff *skb,
+					    u8 seq, enum mcu_cmd cmd)
+{
+	WARN_ON(mt76x0_dma_skb_wrap(skb, CPU_TX_PORT, DMA_COMMAND,
+				     FIELD_PREP(MT_TXD_CMD_SEQ, seq) |
+				     FIELD_PREP(MT_TXD_CMD_TYPE, cmd)));
+}
+
+static inline void trace_mt76x0_mcu_msg_send_cs(struct mt76_dev *dev,
+					    struct sk_buff *skb, bool need_resp)
+{
+	u32 i, csum = 0;
+
+	for (i = 0; i < skb->len / 4; i++)
+		csum ^= get_unaligned_le32(skb->data + i * 4);
+
+	trace_mt76x0_mcu_msg_send(dev, skb, csum, need_resp);
+}
+
+static struct sk_buff *
+mt76x0_mcu_msg_alloc(struct mt76x0_dev *dev, const void *data, int len)
+{
+	struct sk_buff *skb;
+
+	WARN_ON(len % 4); /* if length is not divisible by 4 we need to pad */
+
+	skb = alloc_skb(len + MT_DMA_HDR_LEN + 4, GFP_KERNEL);
+	if (skb) {
+		skb_reserve(skb, MT_DMA_HDR_LEN);
+		memcpy(skb_put(skb, len), data, len);
+	}
+	return skb;
+}
+
+static void mt76x0_read_resp_regs(struct mt76x0_dev *dev, int len)
+{
+	int i;
+	int n = dev->mcu.reg_pairs_len;
+	u8 *buf = dev->mcu.resp.buf;
+
+	buf += 4;
+	len -= 8;
+
+	if (dev->mcu.burst_read) {
+		u32 reg = dev->mcu.reg_pairs[0].reg - dev->mcu.reg_base;
+
+		WARN_ON_ONCE(len/4 != n);
+		for (i = 0; i < n; i++) {
+			u32 val = get_unaligned_le32(buf + 4*i);
+
+			dev->mcu.reg_pairs[i].reg = reg++;
+			dev->mcu.reg_pairs[i].value = val;
+		}
+	} else {
+		WARN_ON_ONCE(len/8 != n);
+		for (i = 0; i < n; i++) {
+			u32 reg = get_unaligned_le32(buf + 8*i) - dev->mcu.reg_base;
+			u32 val = get_unaligned_le32(buf + 8*i + 4);
+
+			WARN_ON_ONCE(dev->mcu.reg_pairs[i].reg != reg);
+			dev->mcu.reg_pairs[i].value = val;
+		}
+	}
+}
+
+static int mt76x0_mcu_wait_resp(struct mt76x0_dev *dev, u8 seq)
+{
+	struct urb *urb = dev->mcu.resp.urb;
+	u32 rxfce;
+	int urb_status, ret, try = 5;
+
+	while (try--) {
+		if (!wait_for_completion_timeout(&dev->mcu.resp_cmpl,
+						 msecs_to_jiffies(300))) {
+			dev_warn(dev->mt76.dev, "Warning: %s retrying\n", __func__);
+			continue;
+		}
+
+		/* Make copies of important data before reusing the urb */
+		rxfce = get_unaligned_le32(dev->mcu.resp.buf);
+		urb_status = urb->status * mt76x0_urb_has_error(urb);
+
+		if (urb_status == 0 && dev->mcu.reg_pairs)
+			mt76x0_read_resp_regs(dev, urb->actual_length);
+
+		ret = mt76x0_usb_submit_buf(dev, USB_DIR_IN, MT_EP_IN_CMD_RESP,
+					     &dev->mcu.resp, GFP_KERNEL,
+					     mt76x0_complete_urb,
+					     &dev->mcu.resp_cmpl);
+		if (ret)
+			return ret;
+
+		if (urb_status)
+			dev_err(dev->mt76.dev, "Error: MCU resp urb failed:%d\n",
+				urb_status);
+
+		if (FIELD_GET(MT_RXD_CMD_INFO_CMD_SEQ, rxfce) == seq &&
+		    FIELD_GET(MT_RXD_CMD_INFO_EVT_TYPE, rxfce) == CMD_DONE)
+			return 0;
+
+		dev_err(dev->mt76.dev, "Error: MCU resp evt:%lx seq:%hhx-%lx!\n",
+			FIELD_GET(MT_RXD_CMD_INFO_EVT_TYPE, rxfce),
+			seq, FIELD_GET(MT_RXD_CMD_INFO_CMD_SEQ, rxfce));
+	}
+
+	dev_err(dev->mt76.dev, "Error: %s timed out\n", __func__);
+	return -ETIMEDOUT;
+}
+
+static int
+__mt76x0_mcu_msg_send(struct mt76x0_dev *dev, struct sk_buff *skb,
+		      enum mcu_cmd cmd, bool wait_resp)
+{
+	struct usb_device *usb_dev = mt76x0_to_usb_dev(dev);
+	unsigned cmd_pipe = usb_sndbulkpipe(usb_dev,
+					    dev->out_ep[MT_EP_OUT_INBAND_CMD]);
+	int sent, ret;
+	u8 seq = 0;
+
+	if (wait_resp)
+		while (!seq)
+			seq = ++dev->mcu.msg_seq & 0xf;
+
+	mt76x0_dma_skb_wrap_cmd(skb, seq, cmd);
+
+	if (dev->mcu.resp_cmpl.done)
+		dev_err(dev->mt76.dev, "Error: MCU response pre-completed!\n");
+
+	trace_mt76x0_mcu_msg_send_cs(&dev->mt76, skb, wait_resp);
+	trace_mt76x0_submit_urb_sync(&dev->mt76, cmd_pipe, skb->len);
+
+	ret = usb_bulk_msg(usb_dev, cmd_pipe, skb->data, skb->len, &sent, 500);
+	if (ret) {
+		dev_err(dev->mt76.dev, "Error: send MCU cmd failed:%d\n", ret);
+		goto out;
+	}
+	if (sent != skb->len)
+		dev_err(dev->mt76.dev, "Error: %s sent != skb->len\n", __func__);
+
+	if (wait_resp)
+		ret = mt76x0_mcu_wait_resp(dev, seq);
+
+out:
+	return ret;
+}
+
+static int
+mt76x0_mcu_msg_send(struct mt76x0_dev *dev, struct sk_buff *skb,
+		     enum mcu_cmd cmd, bool wait_resp)
+{
+	int ret;
+
+	if (test_bit(MT76_REMOVED, &dev->mt76.state))
+		return 0;
+
+	mutex_lock(&dev->mcu.mutex);
+	ret = __mt76x0_mcu_msg_send(dev, skb, cmd, wait_resp);
+	mutex_unlock(&dev->mcu.mutex);
+
+	consume_skb(skb);
+
+	return ret;
+}
+
+int mt76x0_mcu_function_select(struct mt76x0_dev *dev,
+			       enum mcu_function func, u32 val)
+{
+	struct sk_buff *skb;
+	struct {
+		__le32 id;
+		__le32 value;
+	} __packed __aligned(4) msg = {
+		.id = cpu_to_le32(func),
+		.value = cpu_to_le32(val),
+	};
+
+	skb = mt76x0_mcu_msg_alloc(dev, &msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+	return mt76x0_mcu_msg_send(dev, skb, CMD_FUN_SET_OP, func == 5);
+}
+
+int
+mt76x0_mcu_calibrate(struct mt76x0_dev *dev, enum mcu_calibrate cal, u32 val)
+{
+	struct sk_buff *skb;
+	struct {
+		__le32 id;
+		__le32 value;
+	} __packed __aligned(4) msg = {
+		.id = cpu_to_le32(cal),
+		.value = cpu_to_le32(val),
+	};
+
+	skb = mt76x0_mcu_msg_alloc(dev, &msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+	return mt76x0_mcu_msg_send(dev, skb, CMD_CALIBRATION_OP, true);
+}
+
+int mt76x0_write_reg_pairs(struct mt76x0_dev *dev, u32 base,
+			   const struct mt76_reg_pair *data, int n)
+{
+	const int max_vals_per_cmd = INBAND_PACKET_MAX_LEN / 8;
+	struct sk_buff *skb;
+	int cnt, i, ret;
+
+	if (!n)
+		return 0;
+
+	cnt = min(max_vals_per_cmd, n);
+
+	skb = alloc_skb(cnt * 8 + MT_DMA_HDR_LEN + 4, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+	skb_reserve(skb, MT_DMA_HDR_LEN);
+
+	for (i = 0; i < cnt; i++) {
+		skb_put_le32(skb, base + data[i].reg);
+		skb_put_le32(skb, data[i].value);
+	}
+
+	ret = mt76x0_mcu_msg_send(dev, skb, CMD_RANDOM_WRITE, cnt == n);
+	if (ret)
+		return ret;
+
+	return mt76x0_write_reg_pairs(dev, base, data + cnt, n - cnt);
+}
+
+int mt76x0_read_reg_pairs(struct mt76x0_dev *dev, u32 base,
+			  struct mt76_reg_pair *data, int n)
+{
+	const int max_vals_per_cmd = INBAND_PACKET_MAX_LEN / 8;
+	struct sk_buff *skb;
+	int cnt, i, ret;
+
+	if (!n)
+		return 0;
+
+	cnt = min(max_vals_per_cmd, n);
+	if (cnt != n)
+		return -EINVAL;
+
+	skb = alloc_skb(cnt * 8 + MT_DMA_HDR_LEN + 4, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+	skb_reserve(skb, MT_DMA_HDR_LEN);
+
+	for (i = 0; i < cnt; i++) {
+		skb_put_le32(skb, base + data[i].reg);
+		skb_put_le32(skb, data[i].value);
+	}
+
+	mutex_lock(&dev->mcu.mutex);
+
+	dev->mcu.reg_pairs = data;
+	dev->mcu.reg_pairs_len = n;
+	dev->mcu.reg_base = base;
+	dev->mcu.burst_read = false;
+
+	ret = __mt76x0_mcu_msg_send(dev, skb, CMD_RANDOM_READ, true);
+
+	dev->mcu.reg_pairs = NULL;
+
+	mutex_unlock(&dev->mcu.mutex);
+
+	consume_skb(skb);
+
+	return ret;
+
+}
+
+int mt76x0_burst_write_regs(struct mt76x0_dev *dev, u32 offset,
+			     const u32 *data, int n)
+{
+	const int max_regs_per_cmd = INBAND_PACKET_MAX_LEN / 4 - 1;
+	struct sk_buff *skb;
+	int cnt, i, ret;
+
+	if (!n)
+		return 0;
+
+	cnt = min(max_regs_per_cmd, n);
+
+	skb = alloc_skb(cnt * 4 + MT_DMA_HDR_LEN + 4, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+	skb_reserve(skb, MT_DMA_HDR_LEN);
+
+	skb_put_le32(skb, MT_MCU_MEMMAP_WLAN + offset);
+	for (i = 0; i < cnt; i++)
+		skb_put_le32(skb, data[i]);
+
+	ret = mt76x0_mcu_msg_send(dev, skb, CMD_BURST_WRITE, cnt == n);
+	if (ret)
+		return ret;
+
+	return mt76x0_burst_write_regs(dev, offset + cnt * 4,
+					data + cnt, n - cnt);
+}
+
+#if 0
+static int mt76x0_burst_read_regs(struct mt76x0_dev *dev, u32 base,
+				  struct mt76_reg_pair *data, int n)
+{
+	const int max_vals_per_cmd = INBAND_PACKET_MAX_LEN / 4 - 1;
+	struct sk_buff *skb;
+	int cnt, ret;
+
+	if (!n)
+		return 0;
+
+	cnt = min(max_vals_per_cmd, n);
+	if (cnt != n)
+		return -EINVAL;
+
+	skb = alloc_skb(cnt * 4 + MT_DMA_HDR_LEN + 4, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+	skb_reserve(skb, MT_DMA_HDR_LEN);
+
+	skb_put_le32(skb, base + data[0].reg);
+	skb_put_le32(skb, n);
+
+	mutex_lock(&dev->mcu.mutex);
+
+	dev->mcu.reg_pairs = data;
+	dev->mcu.reg_pairs_len = n;
+	dev->mcu.reg_base = base;
+	dev->mcu.burst_read = true;
+
+	ret = __mt76x0_mcu_msg_send(dev, skb, CMD_BURST_READ, true);
+
+	dev->mcu.reg_pairs = NULL;
+
+	mutex_unlock(&dev->mcu.mutex);
+
+	consume_skb(skb);
+
+	return ret;
+}
+#endif
+
+struct mt76_fw_header {
+	__le32 ilm_len;
+	__le32 dlm_len;
+	__le16 build_ver;
+	__le16 fw_ver;
+	u8 pad[4];
+	char build_time[16];
+};
+
+struct mt76_fw {
+	struct mt76_fw_header hdr;
+	u8 ivb[MT_MCU_IVB_SIZE];
+	u8 ilm[];
+};
+
+static int __mt76x0_dma_fw(struct mt76x0_dev *dev,
+			    const struct mt76x0_dma_buf *dma_buf,
+			    const void *data, u32 len, u32 dst_addr)
+{
+	DECLARE_COMPLETION_ONSTACK(cmpl);
+	struct mt76x0_dma_buf buf = *dma_buf; /* we need to fake length */
+	__le32 reg;
+	u32 val;
+	int ret;
+
+	reg = cpu_to_le32(FIELD_PREP(MT_TXD_INFO_TYPE, DMA_COMMAND) |
+			  FIELD_PREP(MT_TXD_INFO_D_PORT, CPU_TX_PORT) |
+			  FIELD_PREP(MT_TXD_INFO_LEN, len));
+	memcpy(buf.buf, &reg, sizeof(reg));
+	memcpy(buf.buf + sizeof(reg), data, len);
+	memset(buf.buf + sizeof(reg) + len, 0, 8);
+
+	ret = mt76x0_vendor_single_wr(dev, MT_VEND_WRITE_FCE,
+				       MT_FCE_DMA_ADDR, dst_addr);
+	if (ret)
+		return ret;
+	len = roundup(len, 4);
+	ret = mt76x0_vendor_single_wr(dev, MT_VEND_WRITE_FCE,
+				       MT_FCE_DMA_LEN, len << 16);
+	if (ret)
+		return ret;
+
+	buf.len = MT_DMA_HDR_LEN + len + 4;
+	ret = mt76x0_usb_submit_buf(dev, USB_DIR_OUT, MT_EP_OUT_INBAND_CMD,
+				     &buf, GFP_KERNEL,
+				     mt76x0_complete_urb, &cmpl);
+	if (ret)
+		return ret;
+
+	if (!wait_for_completion_timeout(&cmpl, msecs_to_jiffies(1000))) {
+		dev_err(dev->mt76.dev, "Error: firmware upload timed out\n");
+		usb_kill_urb(buf.urb);
+		return -ETIMEDOUT;
+	}
+	if (mt76x0_urb_has_error(buf.urb)) {
+		dev_err(dev->mt76.dev, "Error: firmware upload urb failed:%d\n",
+			buf.urb->status);
+		return buf.urb->status;
+	}
+
+	val = mt76_rr(dev, MT_TX_CPU_FROM_FCE_CPU_DESC_IDX);
+	val++;
+	mt76_wr(dev, MT_TX_CPU_FROM_FCE_CPU_DESC_IDX, val);
+
+	msleep(5);
+
+	return 0;
+}
+
+static int
+mt76x0_dma_fw(struct mt76x0_dev *dev, struct mt76x0_dma_buf *dma_buf,
+	       const void *data, int len, u32 dst_addr)
+{
+	int n, ret;
+
+	if (len == 0)
+		return 0;
+
+	n = min(MCU_FW_URB_MAX_PAYLOAD, len);
+	ret = __mt76x0_dma_fw(dev, dma_buf, data, n, dst_addr);
+	if (ret)
+		return ret;
+
+#if 0
+	if (!mt76_poll_msec(dev, MT_MCU_COM_REG1, BIT(31), BIT(31), 500))
+		return -ETIMEDOUT;
+#endif
+
+	return mt76x0_dma_fw(dev, dma_buf, data + n, len - n, dst_addr + n);
+}
+
+static int
+mt76x0_upload_firmware(struct mt76x0_dev *dev, const struct mt76_fw *fw)
+{
+	struct mt76x0_dma_buf dma_buf;
+	void *ivb;
+	u32 ilm_len, dlm_len;
+	int i, ret;
+
+	ivb = kmemdup(fw->ivb, sizeof(fw->ivb), GFP_KERNEL);
+	if (!ivb)
+		return -ENOMEM;
+	if (mt76x0_usb_alloc_buf(dev, MCU_FW_URB_SIZE, &dma_buf)) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	ilm_len = le32_to_cpu(fw->hdr.ilm_len) - sizeof(fw->ivb);
+	dev_dbg(dev->mt76.dev, "loading FW - ILM %u + IVB %zu\n",
+		ilm_len, sizeof(fw->ivb));
+	ret = mt76x0_dma_fw(dev, &dma_buf, fw->ilm, ilm_len, sizeof(fw->ivb));
+	if (ret)
+		goto error;
+
+	dlm_len = le32_to_cpu(fw->hdr.dlm_len);
+	dev_dbg(dev->mt76.dev, "loading FW - DLM %u\n", dlm_len);
+	ret = mt76x0_dma_fw(dev, &dma_buf, fw->ilm + ilm_len,
+			     dlm_len, MT_MCU_DLM_OFFSET);
+	if (ret)
+		goto error;
+
+	ret = mt76x0_vendor_request(dev, MT_VEND_DEV_MODE, USB_DIR_OUT,
+				     0x12, 0, ivb, sizeof(fw->ivb));
+	if (ret < 0)
+		goto error;
+	ret = 0;
+
+	for (i = 100; i && !firmware_running(dev); i--)
+		msleep(10);
+	if (!i) {
+		ret = -ETIMEDOUT;
+		goto error;
+	}
+
+	dev_dbg(dev->mt76.dev, "Firmware running!\n");
+error:
+	kfree(ivb);
+	mt76x0_usb_free_buf(dev, &dma_buf);
+
+	return ret;
+}
+
+static int mt76x0_load_firmware(struct mt76x0_dev *dev)
+{
+	const struct firmware *fw;
+	const struct mt76_fw_header *hdr;
+	int len, ret;
+	u32 val;
+
+	mt76_wr(dev, MT_USB_DMA_CFG, (MT_USB_DMA_CFG_RX_BULK_EN |
+					 MT_USB_DMA_CFG_TX_BULK_EN));
+
+	if (firmware_running(dev))
+		return 0;
+
+	ret = request_firmware(&fw, MT7610_FIRMWARE, dev->mt76.dev);
+	if (ret)
+		return ret;
+
+	if (!fw || !fw->data || fw->size < sizeof(*hdr))
+		goto err_inv_fw;
+
+	hdr = (const struct mt76_fw_header *) fw->data;
+
+	if (le32_to_cpu(hdr->ilm_len) <= MT_MCU_IVB_SIZE)
+		goto err_inv_fw;
+
+	len = sizeof(*hdr);
+	len += le32_to_cpu(hdr->ilm_len);
+	len += le32_to_cpu(hdr->dlm_len);
+
+	if (fw->size != len)
+		goto err_inv_fw;
+
+	val = le16_to_cpu(hdr->fw_ver);
+	dev_dbg(dev->mt76.dev,
+		 "Firmware Version: %d.%d.%02d Build: %x Build time: %.16s\n",
+		 (val >> 12) & 0xf, (val >> 8) & 0xf, val & 0xf,
+		 le16_to_cpu(hdr->build_ver), hdr->build_time);
+
+	len = le32_to_cpu(hdr->ilm_len);
+
+	mt76_wr(dev, 0x1004, 0x2c);
+
+	mt76_set(dev, MT_USB_DMA_CFG, (MT_USB_DMA_CFG_RX_BULK_EN |
+				       MT_USB_DMA_CFG_TX_BULK_EN) |
+				       FIELD_PREP(MT_USB_DMA_CFG_RX_BULK_AGG_TOUT, 0x20));
+	mt76x0_vendor_reset(dev);
+	msleep(5);
+/*
+	mt76x0_rmw(dev, MT_PBF_CFG, 0, (MT_PBF_CFG_TX0Q_EN |
+					 MT_PBF_CFG_TX1Q_EN |
+					 MT_PBF_CFG_TX2Q_EN |
+					 MT_PBF_CFG_TX3Q_EN));
+*/
+
+	mt76_wr(dev, MT_FCE_PSE_CTRL, 1);
+
+	/* FCE tx_fs_base_ptr */
+	mt76_wr(dev, MT_TX_CPU_FROM_FCE_BASE_PTR, 0x400230);
+	/* FCE tx_fs_max_cnt */
+	mt76_wr(dev, MT_TX_CPU_FROM_FCE_MAX_COUNT, 1);
+	/* FCE pdma enable */
+	mt76_wr(dev, MT_FCE_PDMA_GLOBAL_CONF, 0x44);
+	/* FCE skip_fs_en */
+	mt76_wr(dev, MT_FCE_SKIP_FS, 3);
+
+	val = mt76_rr(dev, MT_USB_DMA_CFG);
+	val |= MT_USB_DMA_CFG_TX_WL_DROP;
+	mt76_wr(dev, MT_USB_DMA_CFG, val);
+	val &= ~MT_USB_DMA_CFG_TX_WL_DROP;
+	mt76_wr(dev, MT_USB_DMA_CFG, val);
+
+	ret = mt76x0_upload_firmware(dev, (const struct mt76_fw *)fw->data);
+	release_firmware(fw);
+
+	mt76_wr(dev, MT_FCE_PSE_CTRL, 1);
+
+	return ret;
+
+err_inv_fw:
+	dev_err(dev->mt76.dev, "Invalid firmware image\n");
+	release_firmware(fw);
+	return -ENOENT;
+}
+
+int mt76x0_mcu_init(struct mt76x0_dev *dev)
+{
+	int ret;
+
+	mutex_init(&dev->mcu.mutex);
+
+	ret = mt76x0_load_firmware(dev);
+	if (ret)
+		return ret;
+
+	set_bit(MT76_STATE_MCU_RUNNING, &dev->mt76.state);
+
+	return 0;
+}
+
+int mt76x0_mcu_cmd_init(struct mt76x0_dev *dev)
+{
+	int ret;
+
+	ret = mt76x0_mcu_function_select(dev, Q_SELECT, 1);
+	if (ret)
+		return ret;
+
+	init_completion(&dev->mcu.resp_cmpl);
+	if (mt76x0_usb_alloc_buf(dev, MCU_RESP_URB_SIZE, &dev->mcu.resp)) {
+		mt76x0_usb_free_buf(dev, &dev->mcu.resp);
+		return -ENOMEM;
+	}
+
+	ret = mt76x0_usb_submit_buf(dev, USB_DIR_IN, MT_EP_IN_CMD_RESP,
+				     &dev->mcu.resp, GFP_KERNEL,
+				     mt76x0_complete_urb, &dev->mcu.resp_cmpl);
+	if (ret) {
+		mt76x0_usb_free_buf(dev, &dev->mcu.resp);
+		return ret;
+	}
+
+	return 0;
+}
+
+void mt76x0_mcu_cmd_deinit(struct mt76x0_dev *dev)
+{
+	usb_kill_urb(dev->mcu.resp.urb);
+	mt76x0_usb_free_buf(dev, &dev->mcu.resp);
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mcu.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mcu.h
new file mode 100644
index 000000000000..8c2f77f4c3f5
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mcu.h
@@ -0,0 +1,101 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __MT76X0U_MCU_H
+#define __MT76X0U_MCU_H
+
+struct mt76x0_dev;
+
+/* Register definitions */
+#define MT_MCU_RESET_CTL		0x070C
+#define MT_MCU_INT_LEVEL		0x0718
+#define MT_MCU_COM_REG0			0x0730
+#define MT_MCU_COM_REG1			0x0734
+#define MT_MCU_COM_REG2			0x0738
+#define MT_MCU_COM_REG3			0x073C
+
+#define MT_MCU_IVB_SIZE			0x40
+#define MT_MCU_DLM_OFFSET		0x80000
+
+#define MT_MCU_MEMMAP_WLAN		0x00410000
+/* We use same space for BBP as for MAC regs
+ * #define MT_MCU_MEMMAP_BBP		0x40000000
+ */
+#define MT_MCU_MEMMAP_RF		0x80000000
+
+#define INBAND_PACKET_MAX_LEN		192
+
+enum mcu_cmd {
+	CMD_FUN_SET_OP = 1,
+	CMD_LOAD_CR = 2,
+	CMD_INIT_GAIN_OP = 3,
+	CMD_DYNC_VGA_OP = 6,
+	CMD_TDLS_CH_SW = 7,
+	CMD_BURST_WRITE = 8,
+	CMD_READ_MODIFY_WRITE = 9,
+	CMD_RANDOM_READ = 10,
+	CMD_BURST_READ = 11,
+	CMD_RANDOM_WRITE = 12,
+	CMD_LED_MODE_OP = 16,
+	CMD_POWER_SAVING_OP = 20,
+	CMD_WOW_CONFIG = 21,
+	CMD_WOW_QUERY = 22,
+	CMD_WOW_FEATURE = 24,
+	CMD_CARRIER_DETECT_OP = 28,
+	CMD_RADOR_DETECT_OP = 29,
+	CMD_SWITCH_CHANNEL_OP = 30,
+	CMD_CALIBRATION_OP = 31,
+	CMD_BEACON_OP = 32,
+	CMD_ANTENNA_OP = 33,
+};
+
+enum mcu_function {
+	Q_SELECT = 1,
+	BW_SETTING = 2,
+	ATOMIC_TSSI_SETTING = 5,
+};
+
+enum mcu_power_mode {
+	RADIO_OFF = 0x30,
+	RADIO_ON = 0x31,
+	RADIO_OFF_AUTO_WAKEUP = 0x32,
+	RADIO_OFF_ADVANCE = 0x33,
+	RADIO_ON_ADVANCE = 0x34,
+};
+
+enum mcu_calibrate {
+	MCU_CAL_R = 1,
+	MCU_CAL_RXDCOC,
+	MCU_CAL_LC,
+	MCU_CAL_LOFT,
+	MCU_CAL_TXIQ,
+	MCU_CAL_BW,
+	MCU_CAL_DPD,
+	MCU_CAL_RXIQ,
+	MCU_CAL_TXDCOC,
+	MCU_CAL_RX_GROUP_DELAY,
+	MCU_CAL_TX_GROUP_DELAY,
+};
+
+int mt76x0_mcu_init(struct mt76x0_dev *dev);
+int mt76x0_mcu_cmd_init(struct mt76x0_dev *dev);
+void mt76x0_mcu_cmd_deinit(struct mt76x0_dev *dev);
+
+int
+mt76x0_mcu_calibrate(struct mt76x0_dev *dev, enum mcu_calibrate cal, u32 val);
+
+int
+mt76x0_mcu_function_select(struct mt76x0_dev *dev, enum mcu_function func, u32 val);
+
+#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
new file mode 100644
index 000000000000..fc9857f61771
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -0,0 +1,330 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef MT76X0U_H
+#define MT76X0U_H
+
+#include <linux/bitfield.h>
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/mutex.h>
+#include <linux/usb.h>
+#include <linux/completion.h>
+#include <net/mac80211.h>
+#include <linux/debugfs.h>
+
+#include "../mt76.h"
+#include "regs.h"
+
+#define MT_CALIBRATE_INTERVAL		(4 * HZ)
+
+#define MT_FREQ_CAL_INIT_DELAY		(30 * HZ)
+#define MT_FREQ_CAL_CHECK_INTERVAL	(10 * HZ)
+#define MT_FREQ_CAL_ADJ_INTERVAL	(HZ / 2)
+
+#define MT_BBP_REG_VERSION		0x00
+
+#define MT_USB_AGGR_SIZE_LIMIT		21 /* * 1024B */
+#define MT_USB_AGGR_TIMEOUT		0x80 /* * 33ns */
+#define MT_RX_ORDER			3
+#define MT_RX_URB_SIZE			(PAGE_SIZE << MT_RX_ORDER)
+
+struct mt76x0_dma_buf {
+	struct urb *urb;
+	void *buf;
+	dma_addr_t dma;
+	size_t len;
+};
+
+struct mt76x0_mcu {
+	struct mutex mutex;
+
+	u8 msg_seq;
+
+	struct mt76x0_dma_buf resp;
+	struct completion resp_cmpl;
+
+	struct mt76_reg_pair *reg_pairs;
+	unsigned int reg_pairs_len;
+	u32 reg_base;
+	bool burst_read;
+};
+
+struct mac_stats {
+	u64 rx_stat[6];
+	u64 tx_stat[6];
+	u64 aggr_stat[2];
+	u64 aggr_n[32];
+	u64 zero_len_del[2];
+};
+
+#define N_RX_ENTRIES	16
+struct mt76x0_rx_queue {
+	struct mt76x0_dev *dev;
+
+	struct mt76x0_dma_buf_rx {
+		struct urb *urb;
+		struct page *p;
+	} e[N_RX_ENTRIES];
+
+	unsigned int start;
+	unsigned int end;
+	unsigned int entries;
+	unsigned int pending;
+};
+
+#define N_TX_ENTRIES	64
+
+struct mt76x0_tx_queue {
+	struct mt76x0_dev *dev;
+
+	struct mt76x0_dma_buf_tx {
+		struct urb *urb;
+		struct sk_buff *skb;
+	} e[N_TX_ENTRIES];
+
+	unsigned int start;
+	unsigned int end;
+	unsigned int entries;
+	unsigned int used;
+	unsigned int fifo_seq;
+};
+
+/* WCID allocation:
+ *     0: mcast wcid
+ *     1: bssid wcid
+ *  1...: STAs
+ * ...7e: group wcids
+ *    7f: reserved
+ */
+#define N_WCIDS		128
+#define GROUP_WCID(idx)	(254 - idx)
+
+struct mt76x0_eeprom_params;
+
+#define MT_EE_TEMPERATURE_SLOPE		39
+#define MT_FREQ_OFFSET_INVALID		-128
+
+/* addr req mask */
+#define MT_VEND_TYPE_EEPROM	BIT(31)
+#define MT_VEND_TYPE_CFG	BIT(30)
+#define MT_VEND_TYPE_MASK	(MT_VEND_TYPE_EEPROM | MT_VEND_TYPE_CFG)
+
+#define MT_VEND_ADDR(type, n)	(MT_VEND_TYPE_##type | (n))
+
+enum mt_bw {
+	MT_BW_20,
+	MT_BW_40,
+};
+
+/**
+ * struct mt76x0_dev - adapter structure
+ * @lock:		protects @wcid->tx_rate.
+ * @mac_lock:		locks out mac80211's tx status and rx paths.
+ * @tx_lock:		protects @tx_q and changes of MT76_STATE_*_STATS
+ *			flags in @state.
+ * @rx_lock:		protects @rx_q.
+ * @con_mon_lock:	protects @ap_bssid, @bcn_*, @avg_rssi.
+ * @mutex:		ensures exclusive access from mac80211 callbacks.
+ * @reg_atomic_mutex:	ensures atomicity of indirect register accesses
+ *			(accesses to RF and BBP).
+ * @hw_atomic_mutex:	ensures exclusive access to HW during critical
+ *			operations (power management, channel switch).
+ */
+struct mt76x0_dev {
+	struct mt76_dev mt76; /* must be first */
+
+	struct mutex mutex;
+
+	struct mutex usb_ctrl_mtx;
+	u8 data[32];
+
+	struct tasklet_struct rx_tasklet;
+	struct tasklet_struct tx_tasklet;
+
+	u8 out_ep[__MT_EP_OUT_MAX];
+	u16 out_max_packet;
+	u8 in_ep[__MT_EP_IN_MAX];
+	u16 in_max_packet;
+
+	unsigned long wcid_mask[DIV_ROUND_UP(N_WCIDS, BITS_PER_LONG)];
+	unsigned long vif_mask;
+
+	struct mt76x0_mcu mcu;
+
+	struct delayed_work cal_work;
+	struct delayed_work mac_work;
+
+	struct workqueue_struct *stat_wq;
+	struct delayed_work stat_work;
+
+	struct mt76_wcid *mon_wcid;
+	struct mt76_wcid __rcu *wcid[N_WCIDS];
+
+	spinlock_t mac_lock;
+
+	const u16 *beacon_offsets;
+
+	u8 macaddr[ETH_ALEN];
+	struct mt76x0_eeprom_params *ee;
+
+	struct mutex reg_atomic_mutex;
+	struct mutex hw_atomic_mutex;
+
+	u32 rxfilter;
+	u32 debugfs_reg;
+
+	/* TX */
+	spinlock_t tx_lock;
+	struct mt76x0_tx_queue *tx_q;
+	struct sk_buff_head tx_skb_done;
+
+	atomic_t avg_ampdu_len;
+
+	/* RX */
+	spinlock_t rx_lock;
+	struct mt76x0_rx_queue rx_q;
+
+	/* Connection monitoring things */
+	spinlock_t con_mon_lock;
+	u8 ap_bssid[ETH_ALEN];
+
+	s8 bcn_freq_off;
+	u8 bcn_phy_mode;
+
+	int avg_rssi; /* starts at 0 and converges */
+
+	u8 agc_save;
+	u16 chainmask;
+
+	struct mac_stats stats;
+};
+
+struct mt76x0_wcid {
+	u8 idx;
+	u8 hw_key_idx;
+
+	u16 tx_rate;
+	bool tx_rate_set;
+	u8 tx_rate_nss;
+};
+
+struct mt76_vif {
+	u8 idx;
+
+	struct mt76_wcid group_wcid;
+};
+
+struct mt76_tx_status {
+	u8 valid:1;
+	u8 success:1;
+	u8 aggr:1;
+	u8 ack_req:1;
+	u8 is_probe:1;
+	u8 wcid;
+	u8 pktid;
+	u8 retry;
+	u16 rate;
+} __packed __aligned(2);
+
+struct mt76_sta {
+	struct mt76_wcid wcid;
+	struct mt76_tx_status status;
+	int n_frames;
+	u16 agg_ssn[IEEE80211_NUM_TIDS];
+};
+
+struct mt76_reg_pair {
+	u32 reg;
+	u32 value;
+};
+
+struct mt76x0_rxwi;
+
+extern const struct ieee80211_ops mt76x0_ops;
+
+static inline bool is_mt7610e(struct mt76x0_dev *dev)
+{
+	/* TODO */
+	return false;
+}
+
+void mt76x0_init_debugfs(struct mt76x0_dev *dev);
+
+int mt76x0_wait_asic_ready(struct mt76x0_dev *dev);
+
+/* Compatibility with mt76 */
+#define mt76_rmw_field(_dev, _reg, _field, _val)	\
+	mt76_rmw(_dev, _reg, _field, FIELD_PREP(_field, _val))
+
+int mt76x0_write_reg_pairs(struct mt76x0_dev *dev, u32 base,
+			    const struct mt76_reg_pair *data, int len);
+int mt76x0_read_reg_pairs(struct mt76x0_dev *dev, u32 base,
+			  struct mt76_reg_pair *data, int len);
+int mt76x0_burst_write_regs(struct mt76x0_dev *dev, u32 offset,
+			     const u32 *data, int n);
+void mt76x0_addr_wr(struct mt76x0_dev *dev, const u32 offset, const u8 *addr);
+
+/* Init */
+struct mt76x0_dev *mt76x0_alloc_device(struct device *dev);
+int mt76x0_init_hardware(struct mt76x0_dev *dev);
+int mt76x0_register_device(struct mt76x0_dev *dev);
+void mt76x0_cleanup(struct mt76x0_dev *dev);
+void mt76x0_chip_onoff(struct mt76x0_dev *dev, bool enable, bool reset);
+
+int mt76x0_mac_start(struct mt76x0_dev *dev);
+void mt76x0_mac_stop(struct mt76x0_dev *dev);
+
+/* PHY */
+void mt76x0_phy_init(struct mt76x0_dev *dev);
+int mt76x0_wait_bbp_ready(struct mt76x0_dev *dev);
+void mt76x0_agc_save(struct mt76x0_dev *dev);
+void mt76x0_agc_restore(struct mt76x0_dev *dev);
+int mt76x0_phy_set_channel(struct mt76x0_dev *dev,
+			    struct cfg80211_chan_def *chandef);
+void mt76x0_phy_recalibrate_after_assoc(struct mt76x0_dev *dev);
+int mt76x0_phy_get_rssi(struct mt76x0_dev *dev, struct mt76x0_rxwi *rxwi);
+void mt76x0_phy_con_cal_onoff(struct mt76x0_dev *dev,
+			       struct ieee80211_bss_conf *info);
+
+/* MAC */
+void mt76x0_mac_work(struct work_struct *work);
+void mt76x0_mac_set_protection(struct mt76x0_dev *dev, bool legacy_prot,
+				int ht_mode);
+void mt76x0_mac_set_short_preamble(struct mt76x0_dev *dev, bool short_preamb);
+void mt76x0_mac_config_tsf(struct mt76x0_dev *dev, bool enable, int interval);
+void
+mt76x0_mac_wcid_setup(struct mt76x0_dev *dev, u8 idx, u8 vif_idx, u8 *mac);
+void mt76x0_mac_set_ampdu_factor(struct mt76x0_dev *dev);
+
+/* TX */
+void mt76x0_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control,
+		struct sk_buff *skb);
+int mt76x0_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		    u16 queue, const struct ieee80211_tx_queue_params *params);
+void mt76x0_tx_status(struct mt76x0_dev *dev, struct sk_buff *skb);
+void mt76x0_tx_stat(struct work_struct *work);
+
+/* util */
+void mt76x0_remove_hdr_pad(struct sk_buff *skb);
+int mt76x0_insert_hdr_pad(struct sk_buff *skb);
+
+int mt76x0_dma_init(struct mt76x0_dev *dev);
+void mt76x0_dma_cleanup(struct mt76x0_dev *dev);
+
+int mt76x0_dma_enqueue_tx(struct mt76x0_dev *dev, struct sk_buff *skb,
+			   struct mt76_wcid *wcid, int hw_q);
+
+#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
new file mode 100644
index 000000000000..5da7bfbe907f
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -0,0 +1,1008 @@
+/*
+ * (c) Copyright 2002-2010, Ralink Technology, Inc.
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "mt76x0.h"
+#include "mcu.h"
+#include "eeprom.h"
+#include "trace.h"
+#include "phy.h"
+#include "initvals.h"
+#include "initvals_phy.h"
+
+#include <linux/etherdevice.h>
+
+static int
+mt76x0_rf_csr_wr(struct mt76x0_dev *dev, u32 offset, u8 value)
+{
+	int ret = 0;
+	u8 bank, reg;
+
+	if (test_bit(MT76_REMOVED, &dev->mt76.state))
+		return -ENODEV;
+
+	bank = MT_RF_BANK(offset);
+	reg = MT_RF_REG(offset);
+
+	if (WARN_ON_ONCE(reg > 64) || WARN_ON_ONCE(bank) > 8)
+		return -EINVAL;
+
+	mutex_lock(&dev->reg_atomic_mutex);
+
+	if (!mt76_poll(dev, MT_RF_CSR_CFG, MT_RF_CSR_CFG_KICK, 0, 100)) {
+		ret = -ETIMEDOUT;
+		goto out;
+	}
+
+	mt76_wr(dev, MT_RF_CSR_CFG,
+		   FIELD_PREP(MT_RF_CSR_CFG_DATA, value) |
+		   FIELD_PREP(MT_RF_CSR_CFG_REG_BANK, bank) |
+		   FIELD_PREP(MT_RF_CSR_CFG_REG_ID, reg) |
+		   MT_RF_CSR_CFG_WR |
+		   MT_RF_CSR_CFG_KICK);
+	trace_mt76x0_rf_write(&dev->mt76, bank, offset, value);
+out:
+	mutex_unlock(&dev->reg_atomic_mutex);
+
+	if (ret < 0)
+		dev_err(dev->mt76.dev, "Error: RF write %d:%d failed:%d!!\n",
+			bank, reg, ret);
+
+	return ret;
+}
+
+static int
+mt76x0_rf_csr_rr(struct mt76x0_dev *dev, u32 offset)
+{
+	int ret = -ETIMEDOUT;
+	u32 val;
+	u8 bank, reg;
+
+	if (test_bit(MT76_REMOVED, &dev->mt76.state))
+		return -ENODEV;
+
+	bank = MT_RF_BANK(offset);
+	reg = MT_RF_REG(offset);
+
+	if (WARN_ON_ONCE(reg > 64) || WARN_ON_ONCE(bank) > 8)
+		return -EINVAL;
+
+	mutex_lock(&dev->reg_atomic_mutex);
+
+	if (!mt76_poll(dev, MT_RF_CSR_CFG, MT_RF_CSR_CFG_KICK, 0, 100))
+		goto out;
+
+	mt76_wr(dev, MT_RF_CSR_CFG,
+		   FIELD_PREP(MT_RF_CSR_CFG_REG_BANK, bank) |
+		   FIELD_PREP(MT_RF_CSR_CFG_REG_ID, reg) |
+		   MT_RF_CSR_CFG_KICK);
+
+	if (!mt76_poll(dev, MT_RF_CSR_CFG, MT_RF_CSR_CFG_KICK, 0, 100))
+		goto out;
+
+	val = mt76_rr(dev, MT_RF_CSR_CFG);
+	if (FIELD_GET(MT_RF_CSR_CFG_REG_ID, val) == reg &&
+	    FIELD_GET(MT_RF_CSR_CFG_REG_BANK, val) == bank) {
+		ret = FIELD_GET(MT_RF_CSR_CFG_DATA, val);
+		trace_mt76x0_rf_read(&dev->mt76, bank, offset, ret);
+	}
+out:
+	mutex_unlock(&dev->reg_atomic_mutex);
+
+	if (ret < 0)
+		dev_err(dev->mt76.dev, "Error: RF read %d:%d failed:%d!!\n",
+			bank, reg, ret);
+
+	return ret;
+}
+
+static int
+rf_wr(struct mt76x0_dev *dev, u32 offset, u8 val)
+{
+	if (test_bit(MT76_STATE_MCU_RUNNING, &dev->mt76.state)) {
+		struct mt76_reg_pair pair = {
+			.reg = offset,
+			.value = val,
+		};
+
+		return mt76x0_write_reg_pairs(dev, MT_MCU_MEMMAP_RF, &pair, 1);
+	} else {
+		WARN_ON_ONCE(1);
+		return mt76x0_rf_csr_wr(dev, offset, val);
+	}
+}
+
+static int
+rf_rr(struct mt76x0_dev *dev, u32 offset)
+{
+	int ret;
+	u32 val;
+
+	if (test_bit(MT76_STATE_MCU_RUNNING, &dev->mt76.state)) {
+		struct mt76_reg_pair pair = {
+			.reg = offset,
+		};
+
+		ret = mt76x0_read_reg_pairs(dev, MT_MCU_MEMMAP_RF, &pair, 1);
+		val = pair.value;
+	} else {
+		WARN_ON_ONCE(1);
+		ret = val = mt76x0_rf_csr_rr(dev, offset);
+	}
+
+	return (ret < 0) ? ret : val;
+}
+
+static int
+rf_rmw(struct mt76x0_dev *dev, u32 offset, u8 mask, u8 val)
+{
+	int ret;
+
+	ret = rf_rr(dev, offset);
+	if (ret < 0)
+		return ret;
+	val |= ret & ~mask;
+	ret = rf_wr(dev, offset, val);
+	if (ret)
+		return ret;
+
+	return val;
+}
+
+static int
+rf_set(struct mt76x0_dev *dev, u32 offset, u8 val)
+{
+	return rf_rmw(dev, offset, 0, val);
+}
+
+#if 0
+static int
+rf_clear(struct mt76x0_dev *dev, u32 offset, u8 mask)
+{
+	return rf_rmw(dev, offset, mask, 0);
+}
+#endif
+
+#define RF_RANDOM_WRITE(dev, tab) \
+	mt76x0_write_reg_pairs(dev, MT_MCU_MEMMAP_RF, tab, ARRAY_SIZE(tab));
+
+int mt76x0_wait_bbp_ready(struct mt76x0_dev *dev)
+{
+	int i = 20;
+	u32 val;
+
+	do {
+		val = mt76_rr(dev, MT_BBP(CORE, 0));
+		printk("BBP version %08x\n", val);
+		if (val && ~val)
+			break;
+	} while (--i);
+
+	if (!i) {
+		dev_err(dev->mt76.dev, "Error: BBP is not ready\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static void
+mt76x0_bbp_set_ctrlch(struct mt76x0_dev *dev, enum nl80211_chan_width width,
+		      u8 ctrl)
+{
+	int core_val, agc_val;
+
+	switch (width) {
+	case NL80211_CHAN_WIDTH_80:
+		core_val = 3;
+		agc_val = 7;
+		break;
+	case NL80211_CHAN_WIDTH_40:
+		core_val = 2;
+		agc_val = 3;
+		break;
+	default:
+		core_val = 0;
+		agc_val = 1;
+		break;
+	}
+
+	mt76_rmw_field(dev, MT_BBP(CORE, 1), MT_BBP_CORE_R1_BW, core_val);
+	mt76_rmw_field(dev, MT_BBP(AGC, 0), MT_BBP_AGC_R0_BW, agc_val);
+	mt76_rmw_field(dev, MT_BBP(AGC, 0), MT_BBP_AGC_R0_CTRL_CHAN, ctrl);
+	mt76_rmw_field(dev, MT_BBP(TXBE, 0), MT_BBP_TXBE_R0_CTRL_CHAN, ctrl);
+}
+
+int mt76x0_phy_get_rssi(struct mt76x0_dev *dev, struct mt76x0_rxwi *rxwi)
+{
+	s8 lna_gain, rssi_offset;
+	int val;
+
+	if (dev->mt76.chandef.chan->band == NL80211_BAND_2GHZ) {
+		lna_gain = dev->ee->lna_gain_2ghz;
+		rssi_offset = dev->ee->rssi_offset_2ghz[0];
+	} else {
+		lna_gain = dev->ee->lna_gain_5ghz[0];
+		rssi_offset = dev->ee->rssi_offset_5ghz[0];
+	}
+
+	val = rxwi->rssi[0] + rssi_offset - lna_gain;
+
+	return val;
+}
+
+static void mt76x0_vco_cal(struct mt76x0_dev *dev, u8 channel)
+{
+	u8 val;
+
+	val = rf_rr(dev, MT_RF(0, 4));
+	if ((val & 0x70) != 0x30)
+		return;
+
+	/*
+	 * Calibration Mode - Open loop, closed loop, and amplitude:
+	 * B0.R06.[0]: 1
+	 * B0.R06.[3:1] bp_close_code: 100
+	 * B0.R05.[7:0] bp_open_code: 0x0
+	 * B0.R04.[2:0] cal_bits: 000
+	 * B0.R03.[2:0] startup_time: 011
+	 * B0.R03.[6:4] settle_time:
+	 *  80MHz channel: 110
+	 *  40MHz channel: 101
+	 *  20MHz channel: 100
+	 */
+	val = rf_rr(dev, MT_RF(0, 6));
+	val &= ~0xf;
+	val |= 0x09;
+	rf_wr(dev, MT_RF(0, 6), val);
+
+	val = rf_rr(dev, MT_RF(0, 5));
+	if (val != 0)
+		rf_wr(dev, MT_RF(0, 5), 0x0);
+
+	val = rf_rr(dev, MT_RF(0, 4));
+	val &= ~0x07;
+	rf_wr(dev, MT_RF(0, 4), val);
+
+	val = rf_rr(dev, MT_RF(0, 3));
+	val &= ~0x77;
+	if (channel == 1 || channel == 7 || channel == 9 || channel >= 13) {
+		val |= 0x63;
+	} else if (channel == 3 || channel == 4 || channel == 10) {
+		val |= 0x53;
+	} else if (channel == 2 || channel == 5 || channel == 6 ||
+		   channel == 8 || channel == 11 || channel == 12) {
+		val |= 0x43;
+	} else {
+		WARN(1, "Unknown channel %u\n", channel);
+		return;
+	}
+	rf_wr(dev, MT_RF(0, 3), val);
+
+	/* TODO replace by mt76x0_rf_set(dev, MT_RF(0, 4), BIT(7)); */
+	val = rf_rr(dev, MT_RF(0, 4));
+	val = ((val & ~(0x80)) | 0x80);
+	rf_wr(dev, MT_RF(0, 4), val);
+
+	msleep(2);
+}
+
+static void
+mt76x0_mac_set_ctrlch(struct mt76x0_dev *dev, bool primary_upper)
+{
+	mt76_rmw_field(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_UPPER_40M,
+		       primary_upper);
+}
+
+static void
+mt76x0_phy_set_band(struct mt76x0_dev *dev, enum nl80211_band band)
+{
+	switch (band) {
+	case NL80211_BAND_2GHZ:
+		RF_RANDOM_WRITE(dev, mt76x0_rf_2g_channel_0_tab);
+
+		rf_wr(dev, MT_RF(5, 0), 0x45);
+		rf_wr(dev, MT_RF(6, 0), 0x44);
+
+		mt76_set(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_2G);
+		mt76_clear(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_5G);
+
+		mt76_wr(dev, MT_TX_ALC_VGA3, 0x00050007);
+		mt76_wr(dev, MT_TX0_RF_GAIN_CORR, 0x003E0002);
+		break;
+	case NL80211_BAND_5GHZ:
+		RF_RANDOM_WRITE(dev, mt76x0_rf_5g_channel_0_tab);
+
+		rf_wr(dev, MT_RF(5, 0), 0x44);
+		rf_wr(dev, MT_RF(6, 0), 0x45);
+
+		mt76_clear(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_2G);
+		mt76_set(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_5G);
+
+		mt76_wr(dev, MT_TX_ALC_VGA3, 0x00000005);
+		mt76_wr(dev, MT_TX0_RF_GAIN_CORR, 0x01010102);
+		break;
+	default:
+		break;
+	}
+}
+
+#define EXT_PA_2G_5G            0x0
+#define EXT_PA_5G_ONLY          0x1
+#define EXT_PA_2G_ONLY          0x2
+#define INT_PA_2G_5G            0x3
+
+static void
+mt76x0_phy_set_chan_rf_params(struct mt76x0_dev *dev, u8 channel, u16 rf_bw_band)
+{
+	u16 rf_band = rf_bw_band & 0xff00;
+	u16 rf_bw = rf_bw_band & 0x00ff;
+	u32 mac_reg;
+	u8 rf_val;
+	int i;
+	bool bSDM = false;
+	const struct mt76x0_freq_item *freq_item;
+
+	for (i = 0; i < ARRAY_SIZE(mt76x0_sdm_channel); i++) {
+		if (channel == mt76x0_sdm_channel[i]) {
+			bSDM = true;
+			break;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(mt76x0_frequency_plan); i++) {
+		if (channel == mt76x0_frequency_plan[i].channel) {
+			rf_band = mt76x0_frequency_plan[i].band;
+
+			if (bSDM)
+				freq_item = &(mt76x0_sdm_frequency_plan[i]);
+			else
+				freq_item = &(mt76x0_frequency_plan[i]);
+
+			rf_wr(dev, MT_RF(0, 37), freq_item->pllR37);
+			rf_wr(dev, MT_RF(0, 36), freq_item->pllR36);
+			rf_wr(dev, MT_RF(0, 35), freq_item->pllR35);
+			rf_wr(dev, MT_RF(0, 34), freq_item->pllR34);
+			rf_wr(dev, MT_RF(0, 33), freq_item->pllR33);
+
+			rf_val = rf_rr(dev, MT_RF(0, 32));
+			rf_val &= ~0xE0;
+			rf_val |= freq_item->pllR32_b7b5;
+			rf_wr(dev, MT_RF(0, 32), rf_val);
+
+			/* R32<4:0> pll_den: (Denomina - 8) */
+			rf_val = rf_rr(dev, MT_RF(0, 32));
+			rf_val &= ~0x1F;
+			rf_val |= freq_item->pllR32_b4b0;
+			rf_wr(dev, MT_RF(0, 32), rf_val);
+
+			/* R31<7:5> */
+			rf_val = rf_rr(dev, MT_RF(0, 31));
+			rf_val &= ~0xE0;
+			rf_val |= freq_item->pllR31_b7b5;
+			rf_wr(dev, MT_RF(0, 31), rf_val);
+
+			/* R31<4:0> pll_k(Nominator) */
+			rf_val = rf_rr(dev, MT_RF(0, 31));
+			rf_val &= ~0x1F;
+			rf_val |= freq_item->pllR31_b4b0;
+			rf_wr(dev, MT_RF(0, 31), rf_val);
+
+			/* R30<7> sdm_reset_n */
+			rf_val = rf_rr(dev, MT_RF(0, 30));
+			rf_val &= ~0x80;
+			if (bSDM) {
+				rf_wr(dev, MT_RF(0, 30), rf_val);
+				rf_val |= 0x80;
+				rf_wr(dev, MT_RF(0, 30), rf_val);
+			} else {
+				rf_val |= freq_item->pllR30_b7;
+				rf_wr(dev, MT_RF(0, 30), rf_val);
+			}
+
+			/* R30<6:2> sdmmash_prbs,sin */
+			rf_val = rf_rr(dev, MT_RF(0, 30));
+			rf_val &= ~0x7C;
+			rf_val |= freq_item->pllR30_b6b2;
+			rf_wr(dev, MT_RF(0, 30), rf_val);
+
+			/* R30<1> sdm_bp */
+			rf_val = rf_rr(dev, MT_RF(0, 30));
+			rf_val &= ~0x02;
+			rf_val |= (freq_item->pllR30_b1 << 1);
+			rf_wr(dev, MT_RF(0, 30), rf_val);
+
+			/* R30<0> R29<7:0> (hex) pll_n */
+			rf_val = freq_item->pll_n & 0x00FF;
+			rf_wr(dev, MT_RF(0, 29), rf_val);
+
+			rf_val = rf_rr(dev, MT_RF(0, 30));
+			rf_val &= ~0x1;
+			rf_val |= ((freq_item->pll_n >> 8) & 0x0001);
+			rf_wr(dev, MT_RF(0, 30), rf_val);
+
+			/* R28<7:6> isi_iso */
+			rf_val = rf_rr(dev, MT_RF(0, 28));
+			rf_val &= ~0xC0;
+			rf_val |= freq_item->pllR28_b7b6;
+			rf_wr(dev, MT_RF(0, 28), rf_val);
+
+			/* R28<5:4> pfd_dly */
+			rf_val = rf_rr(dev, MT_RF(0, 28));
+			rf_val &= ~0x30;
+			rf_val |= freq_item->pllR28_b5b4;
+			rf_wr(dev, MT_RF(0, 28), rf_val);
+
+			/* R28<3:2> clksel option */
+			rf_val = rf_rr(dev, MT_RF(0, 28));
+			rf_val &= ~0x0C;
+			rf_val |= freq_item->pllR28_b3b2;
+			rf_wr(dev, MT_RF(0, 28), rf_val);
+
+			/* R28<1:0> R27<7:0> R26<7:0> (hex) sdm_k */
+			rf_val = freq_item->pll_sdm_k & 0x000000FF;
+			rf_wr(dev, MT_RF(0, 26), rf_val);
+
+			rf_val = ((freq_item->pll_sdm_k >> 8) & 0x000000FF);
+			rf_wr(dev, MT_RF(0, 27), rf_val);
+
+			rf_val = rf_rr(dev, MT_RF(0, 28));
+			rf_val &= ~0x3;
+			rf_val |= ((freq_item->pll_sdm_k >> 16) & 0x0003);
+			rf_wr(dev, MT_RF(0, 28), rf_val);
+
+			/* R24<1:0> xo_div */
+			rf_val = rf_rr(dev, MT_RF(0, 24));
+			rf_val &= ~0x3;
+			rf_val |= freq_item->pllR24_b1b0;
+			rf_wr(dev, MT_RF(0, 24), rf_val);
+
+			break;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(mt76x0_rf_bw_switch_tab); i++) {
+		if (rf_bw == mt76x0_rf_bw_switch_tab[i].bw_band) {
+			rf_wr(dev, mt76x0_rf_bw_switch_tab[i].rf_bank_reg,
+				   mt76x0_rf_bw_switch_tab[i].value);
+		} else if ((rf_bw == (mt76x0_rf_bw_switch_tab[i].bw_band & 0xFF)) &&
+			   (rf_band & mt76x0_rf_bw_switch_tab[i].bw_band)) {
+			rf_wr(dev, mt76x0_rf_bw_switch_tab[i].rf_bank_reg,
+				   mt76x0_rf_bw_switch_tab[i].value);
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(mt76x0_rf_band_switch_tab); i++) {
+		if (mt76x0_rf_band_switch_tab[i].bw_band & rf_band) {
+			rf_wr(dev, mt76x0_rf_band_switch_tab[i].rf_bank_reg,
+				   mt76x0_rf_band_switch_tab[i].value);
+		}
+	}
+
+	mac_reg = mt76_rr(dev, MT_RF_MISC);
+	mac_reg &= ~0xC; /* Clear 0x518[3:2] */
+	mt76_wr(dev, MT_RF_MISC, mac_reg);
+
+	if (dev->ee->pa_type == INT_PA_2G_5G ||
+	    (dev->ee->pa_type == EXT_PA_5G_ONLY && (rf_band & RF_G_BAND)) ||
+	    (dev->ee->pa_type == EXT_PA_2G_ONLY && (rf_band & RF_A_BAND))) {
+		; /* Internal PA - nothing to do. */
+	} else {
+		/*
+			MT_RF_MISC (offset: 0x0518)
+			[2]1'b1: enable external A band PA, 1'b0: disable external A band PA
+			[3]1'b1: enable external G band PA, 1'b0: disable external G band PA
+		*/
+		if (rf_band & RF_A_BAND) {
+			mac_reg = mt76_rr(dev, MT_RF_MISC);
+			mac_reg |= 0x4;
+			mt76_wr(dev, MT_RF_MISC, mac_reg);
+		} else {
+			mac_reg = mt76_rr(dev, MT_RF_MISC);
+			mac_reg |= 0x8;
+			mt76_wr(dev, MT_RF_MISC, mac_reg);
+		}
+
+		/* External PA */
+		for (i = 0; i < ARRAY_SIZE(mt76x0_rf_ext_pa_tab); i++)
+			if (mt76x0_rf_ext_pa_tab[i].bw_band & rf_band)
+				rf_wr(dev, mt76x0_rf_ext_pa_tab[i].rf_bank_reg,
+					   mt76x0_rf_ext_pa_tab[i].value);
+	}
+
+	if (rf_band & RF_G_BAND) {
+		mt76_wr(dev, MT_TX0_RF_GAIN_ATTEN, 0x63707400);
+		/* Set Atten mode = 2 For G band, Disable Tx Inc dcoc. */
+		mac_reg = mt76_rr(dev, MT_TX_ALC_CFG_1);
+		mac_reg &= 0x896400FF;
+		mt76_wr(dev, MT_TX_ALC_CFG_1, mac_reg);
+	} else {
+		mt76_wr(dev, MT_TX0_RF_GAIN_ATTEN, 0x686A7800);
+		/* Set Atten mode = 0 For Ext A band, Disable Tx Inc dcoc Cal. */
+		mac_reg = mt76_rr(dev, MT_TX_ALC_CFG_1);
+		mac_reg &= 0x890400FF;
+		mt76_wr(dev, MT_TX_ALC_CFG_1, mac_reg);
+	}
+}
+
+static void
+mt76x0_phy_set_chan_bbp_params(struct mt76x0_dev *dev, u8 channel, u16 rf_bw_band)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(mt76x0_bbp_switch_tab); i++) {
+		const struct mt76x0_bbp_switch_item *item = &mt76x0_bbp_switch_tab[i];
+		const struct mt76_reg_pair *pair = &item->reg_pair;
+
+		if ((rf_bw_band & item->bw_band) != rf_bw_band)
+			continue;
+
+		if (pair->reg == MT_BBP(AGC, 8)) {
+			u32 val = pair->value;
+			u8 gain = FIELD_GET(MT_BBP_AGC_GAIN, val);
+
+			if (channel > 14) {
+				if (channel < 100)
+					gain -= dev->ee->lna_gain_5ghz[0]*2;
+				else if (channel < 137)
+					gain -= dev->ee->lna_gain_5ghz[1]*2;
+				else
+					gain -= dev->ee->lna_gain_5ghz[2]*2;
+
+			} else {
+				gain -= dev->ee->lna_gain_2ghz*2;
+			}
+
+			val &= ~MT_BBP_AGC_GAIN;
+			val |= FIELD_PREP(MT_BBP_AGC_GAIN, gain);
+			mt76_wr(dev, pair->reg, val);
+		} else {
+			mt76_wr(dev, pair->reg, pair->value);
+		}
+	}
+}
+
+#if 0
+static void
+mt76x0_extra_power_over_mac(struct mt76x0_dev *dev)
+{
+	u32 val;
+
+	val = ((mt76_rr(dev, MT_TX_PWR_CFG_1) & 0x00003f00) >> 8);
+	val |= ((mt76_rr(dev, MT_TX_PWR_CFG_2) & 0x00003f00) << 8);
+	mt76_wr(dev, MT_TX_PWR_CFG_7, val);
+
+	/* TODO: fix VHT */
+	val = ((mt76_rr(dev, MT_TX_PWR_CFG_3) & 0x0000ff00) >> 8);
+	mt76_wr(dev, MT_TX_PWR_CFG_8, val);
+
+	val = ((mt76_rr(dev, MT_TX_PWR_CFG_4) & 0x0000ff00) >> 8);
+	mt76_wr(dev, MT_TX_PWR_CFG_9, val);
+}
+
+static void
+mt76x0_phy_set_tx_power(struct mt76x0_dev *dev, u8 channel, u8 rf_bw_band)
+{
+	u32 val;
+	int i;
+	int bw = (rf_bw_band & RF_BW_20) ? 0 : 1;
+
+	for (i = 0; i < 4; i++) {
+		if (channel <= 14)
+			val = dev->ee->tx_pwr_cfg_2g[i][bw];
+		else
+			val = dev->ee->tx_pwr_cfg_5g[i][bw];
+
+		mt76_wr(dev, MT_TX_PWR_CFG_0 + 4*i, val);
+	}
+
+	mt76x0_extra_power_over_mac(dev);
+}
+#endif
+
+static void
+mt76x0_bbp_set_bw(struct mt76x0_dev *dev, enum nl80211_chan_width width)
+{
+	enum { BW_20 = 0, BW_40 = 1, BW_80 = 2, BW_10 = 4};
+	int bw;
+
+	switch (width) {
+	default:
+	case NL80211_CHAN_WIDTH_20_NOHT:
+	case NL80211_CHAN_WIDTH_20:
+		bw = BW_20;
+		break;
+	case NL80211_CHAN_WIDTH_40:
+		bw = BW_40;
+		break;
+	case NL80211_CHAN_WIDTH_80:
+		bw = BW_80;
+		break;
+	case NL80211_CHAN_WIDTH_10:
+		bw = BW_10;
+		break;
+	case NL80211_CHAN_WIDTH_80P80:
+	case NL80211_CHAN_WIDTH_160:
+	case NL80211_CHAN_WIDTH_5:
+		/* TODO error */
+		return ;
+	}
+
+	mt76x0_mcu_function_select(dev, BW_SETTING, bw);
+}
+
+static void
+mt76x0_phy_set_chan_pwr(struct mt76x0_dev *dev, u8 channel)
+{
+	static const int mt76x0_tx_pwr_ch_list[] = {
+		1,2,3,4,5,6,7,8,9,10,11,12,13,14,
+		36,38,40,44,46,48,52,54,56,60,62,64,
+		100,102,104,108,110,112,116,118,120,124,126,128,132,134,136,140,
+		149,151,153,157,159,161,165,167,169,171,173,
+		42,58,106,122,155
+	};
+	int i;
+	u32 val;
+
+	for (i = 0; i < ARRAY_SIZE(mt76x0_tx_pwr_ch_list); i++)
+		if (mt76x0_tx_pwr_ch_list[i] == channel)
+			break;
+
+	if (WARN_ON(i == ARRAY_SIZE(mt76x0_tx_pwr_ch_list)))
+		return;
+
+	val = mt76_rr(dev, MT_TX_ALC_CFG_0);
+	val &= ~0x3f3f;
+	val |= dev->ee->tx_pwr_per_chan[i];
+	val |= 0x2f2f << 16;
+	mt76_wr(dev, MT_TX_ALC_CFG_0, val);
+}
+
+static int
+__mt76x0_phy_set_channel(struct mt76x0_dev *dev,
+		       struct cfg80211_chan_def *chandef)
+{
+	u32 ext_cca_chan[4] = {
+		[0] = FIELD_PREP(MT_EXT_CCA_CFG_CCA0, 0) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA1, 1) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA2, 2) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA3, 3) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA_MASK, BIT(0)),
+		[1] = FIELD_PREP(MT_EXT_CCA_CFG_CCA0, 1) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA1, 0) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA2, 2) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA3, 3) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA_MASK, BIT(1)),
+		[2] = FIELD_PREP(MT_EXT_CCA_CFG_CCA0, 2) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA1, 3) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA2, 1) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA3, 0) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA_MASK, BIT(2)),
+		[3] = FIELD_PREP(MT_EXT_CCA_CFG_CCA0, 3) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA1, 2) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA2, 1) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA3, 0) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA_MASK, BIT(3)),
+	};
+	bool scan = test_bit(MT76_SCANNING, &dev->mt76.state);
+	int ch_group_index, freq, freq1;
+	u8 channel;
+	u32 val;
+	u16 rf_bw_band;
+
+	freq = chandef->chan->center_freq;
+	freq1 = chandef->center_freq1;
+	channel = chandef->chan->hw_value;
+	rf_bw_band = (channel <= 14) ? RF_G_BAND : RF_A_BAND;
+
+	switch (chandef->width) {
+	case NL80211_CHAN_WIDTH_40:
+		if (freq1 > freq)
+			ch_group_index = 0;
+		else
+			ch_group_index = 1;
+		channel += 2 - ch_group_index * 4;
+		rf_bw_band |= RF_BW_40;
+		break;
+	case NL80211_CHAN_WIDTH_80:
+		ch_group_index = (freq - freq1 + 30) / 20;
+		if (WARN_ON(ch_group_index < 0 || ch_group_index > 3))
+			ch_group_index = 0;
+		channel += 6 - ch_group_index * 4;
+		rf_bw_band |= RF_BW_80;
+		break;
+	default:
+		ch_group_index = 0;
+		rf_bw_band |= RF_BW_20;
+		break;
+	}
+
+	mt76x0_bbp_set_bw(dev, chandef->width);
+	mt76x0_bbp_set_ctrlch(dev, chandef->width, ch_group_index);
+	mt76x0_mac_set_ctrlch(dev, ch_group_index & 1);
+
+	mt76_rmw(dev, MT_EXT_CCA_CFG,
+		 (MT_EXT_CCA_CFG_CCA0 |
+		  MT_EXT_CCA_CFG_CCA1 |
+		  MT_EXT_CCA_CFG_CCA2 |
+		  MT_EXT_CCA_CFG_CCA3 |
+		  MT_EXT_CCA_CFG_CCA_MASK),
+		 ext_cca_chan[ch_group_index]);
+
+	mt76x0_phy_set_band(dev, chandef->chan->band);
+	mt76x0_phy_set_chan_rf_params(dev, channel, rf_bw_band);
+
+	/* set Japan Tx filter at channel 14 */
+	val = mt76_rr(dev, MT_BBP(CORE, 1));
+	if (channel == 14)
+		val |= 0x20;
+	else
+		val &= ~0x20;
+	mt76_wr(dev, MT_BBP(CORE, 1), val);
+
+	mt76x0_phy_set_chan_bbp_params(dev, channel, rf_bw_band);
+
+	/* Vendor driver don't do it */
+	/* mt76x0_phy_set_tx_power(dev, channel, rf_bw_band); */
+
+	if (scan)
+		mt76x0_vco_cal(dev, channel);
+
+	mt76x0_mcu_calibrate(dev, MCU_CAL_RXDCOC, 1);
+	mt76x0_phy_set_chan_pwr(dev, channel);
+
+	dev->mt76.chandef = *chandef;
+	return 0;
+}
+
+int mt76x0_phy_set_channel(struct mt76x0_dev *dev,
+			   struct cfg80211_chan_def *chandef)
+{
+	int ret;
+
+	mutex_lock(&dev->hw_atomic_mutex);
+	ret = __mt76x0_phy_set_channel(dev, chandef);
+	mutex_unlock(&dev->hw_atomic_mutex);
+
+	return ret;
+}
+
+void mt76x0_phy_recalibrate_after_assoc(struct mt76x0_dev *dev)
+{
+	u32 tx_alc, reg_val;
+	u8 channel = dev->mt76.chandef.chan->hw_value;
+	int is_5ghz = (dev->mt76.chandef.chan->band == NL80211_BAND_5GHZ) ? 1 : 0;
+
+	mt76x0_mcu_calibrate(dev, MCU_CAL_R, 0);
+
+	mt76x0_vco_cal(dev, channel);
+
+	tx_alc = mt76_rr(dev, MT_TX_ALC_CFG_0);
+	mt76_wr(dev, MT_TX_ALC_CFG_0, 0);
+	usleep_range(500, 700);
+
+	reg_val = mt76_rr(dev, 0x2124);
+	reg_val &= 0xffffff7e;
+	mt76_wr(dev, 0x2124, reg_val);
+
+	mt76x0_mcu_calibrate(dev, MCU_CAL_RXDCOC, 0);
+
+	mt76x0_mcu_calibrate(dev, MCU_CAL_LC, is_5ghz);
+	mt76x0_mcu_calibrate(dev, MCU_CAL_LOFT, is_5ghz);
+	mt76x0_mcu_calibrate(dev, MCU_CAL_TXIQ, is_5ghz);
+	mt76x0_mcu_calibrate(dev, MCU_CAL_TX_GROUP_DELAY, is_5ghz);
+	mt76x0_mcu_calibrate(dev, MCU_CAL_RXIQ, is_5ghz);
+	mt76x0_mcu_calibrate(dev, MCU_CAL_RX_GROUP_DELAY, is_5ghz);
+
+	mt76_wr(dev, 0x2124, reg_val);
+	mt76_wr(dev, MT_TX_ALC_CFG_0, tx_alc);
+	msleep(100);
+
+	mt76x0_mcu_calibrate(dev, MCU_CAL_RXDCOC, 1);
+}
+
+void mt76x0_agc_save(struct mt76x0_dev *dev)
+{
+	/* Only one RX path */
+	dev->agc_save = FIELD_GET(MT_BBP_AGC_GAIN, mt76_rr(dev, MT_BBP(AGC, 8)));
+}
+
+void mt76x0_agc_restore(struct mt76x0_dev *dev)
+{
+	mt76_rmw_field(dev, MT_BBP(AGC, 8), MT_BBP_AGC_GAIN, dev->agc_save);
+}
+
+static void mt76x0_temp_sensor(struct mt76x0_dev *dev)
+{
+	u8 rf_b7_73, rf_b0_66, rf_b0_67;
+	int cycle, temp;
+	u32 val;
+	s32 sval;
+
+	rf_b7_73 = rf_rr(dev, MT_RF(7, 73));
+	rf_b0_66 = rf_rr(dev, MT_RF(0, 66));
+	rf_b0_67 = rf_rr(dev, MT_RF(0, 73));
+
+	rf_wr(dev, MT_RF(7, 73), 0x02);
+	rf_wr(dev, MT_RF(0, 66), 0x23);
+	rf_wr(dev, MT_RF(0, 73), 0x01);
+
+	mt76_wr(dev, MT_BBP(CORE, 34), 0x00080055);
+
+	for (cycle = 0; cycle < 2000; cycle++) {
+		val = mt76_rr(dev, MT_BBP(CORE, 34));
+		if (!(val & 0x10))
+			break;
+		udelay(3);
+	}
+
+	if (cycle >= 2000) {
+		val &= 0x10;
+		mt76_wr(dev, MT_BBP(CORE, 34), val);
+		goto done;
+	}
+
+	sval = mt76_rr(dev, MT_BBP(CORE, 35)) & 0xff;
+	if (!(sval & 0x80))
+		sval &= 0x7f; /* Positive */
+	else
+		sval |= 0xffffff00; /* Negative */
+
+	temp = (35 * (sval - dev->ee->temp_off))/ 10 + 25;
+
+done:
+	rf_wr(dev, MT_RF(7, 73), rf_b7_73);
+	rf_wr(dev, MT_RF(0, 66), rf_b0_66);
+	rf_wr(dev, MT_RF(0, 73), rf_b0_67);
+}
+
+static void mt76x0_dynamic_vga_tuning(struct mt76x0_dev *dev)
+{
+	u32 val, init_vga;
+
+	init_vga = (dev->mt76.chandef.chan->band == NL80211_BAND_5GHZ) ? 0x54 : 0x4E;
+	if (dev->avg_rssi > -60)
+		init_vga -= 0x20;
+	else if (dev->avg_rssi > -70)
+		init_vga -= 0x10;
+
+	val = mt76_rr(dev, MT_BBP(AGC, 8));
+	val &= 0xFFFF80FF;
+	val |= init_vga << 8;
+	mt76_wr(dev, MT_BBP(AGC,8), val);
+}
+
+static void mt76x0_phy_calibrate(struct work_struct *work)
+{
+	struct mt76x0_dev *dev = container_of(work, struct mt76x0_dev,
+					    cal_work.work);
+
+	mt76x0_dynamic_vga_tuning(dev);
+	mt76x0_temp_sensor(dev);
+
+	ieee80211_queue_delayed_work(dev->mt76.hw, &dev->cal_work,
+				     MT_CALIBRATE_INTERVAL);
+}
+
+void mt76x0_phy_con_cal_onoff(struct mt76x0_dev *dev,
+			       struct ieee80211_bss_conf *info)
+{
+	/* Start/stop collecting beacon data */
+	spin_lock_bh(&dev->con_mon_lock);
+	ether_addr_copy(dev->ap_bssid, info->bssid);
+	dev->avg_rssi = 0;
+	dev->bcn_freq_off = MT_FREQ_OFFSET_INVALID;
+	spin_unlock_bh(&dev->con_mon_lock);
+}
+
+static void
+mt76x0_set_rx_chains(struct mt76x0_dev *dev)
+{
+	u32 val;
+
+	val = mt76_rr(dev, MT_BBP(AGC, 0));
+	val &= ~(BIT(3) | BIT(4));
+
+	if (dev->chainmask & BIT(1))
+		val |= BIT(3);
+
+	mt76_wr(dev, MT_BBP(AGC, 0), val);
+
+	mb();
+	val = mt76_rr(dev, MT_BBP(AGC, 0));
+}
+
+static void
+mt76x0_set_tx_dac(struct mt76x0_dev *dev)
+{
+	if (dev->chainmask & BIT(1))
+		mt76_set(dev, MT_BBP(TXBE, 5), 3);
+	else
+		mt76_clear(dev, MT_BBP(TXBE, 5), 3);
+}
+
+static void
+mt76x0_rf_init(struct mt76x0_dev *dev)
+{
+	int i;
+	u8 val;
+
+	RF_RANDOM_WRITE(dev, mt76x0_rf_central_tab);
+	RF_RANDOM_WRITE(dev, mt76x0_rf_2g_channel_0_tab);
+	RF_RANDOM_WRITE(dev, mt76x0_rf_5g_channel_0_tab);
+	RF_RANDOM_WRITE(dev, mt76x0_rf_vga_channel_0_tab);
+
+	for (i = 0; i < ARRAY_SIZE(mt76x0_rf_bw_switch_tab); i++) {
+		const struct mt76x0_rf_switch_item *item = &mt76x0_rf_bw_switch_tab[i];
+
+		if (item->bw_band == RF_BW_20)
+			rf_wr(dev, item->rf_bank_reg, item->value);
+		else if (((RF_G_BAND | RF_BW_20) & item->bw_band) == (RF_G_BAND | RF_BW_20))
+			rf_wr(dev, item->rf_bank_reg, item->value);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(mt76x0_rf_band_switch_tab); i++) {
+		if (mt76x0_rf_band_switch_tab[i].bw_band & RF_G_BAND) {
+			rf_wr(dev,
+			      mt76x0_rf_band_switch_tab[i].rf_bank_reg,
+			      mt76x0_rf_band_switch_tab[i].value);
+		}
+	}
+
+	/*
+	   Frequency calibration
+	   E1: B0.R22<6:0>: xo_cxo<6:0>
+	   E2: B0.R21<0>: xo_cxo<0>, B0.R22<7:0>: xo_cxo<8:1>
+	 */
+	rf_wr(dev, MT_RF(0, 22), min_t(u8, dev->ee->rf_freq_off, 0xBF));
+	val = rf_rr(dev, MT_RF(0, 22));
+
+	/*
+	   Reset the DAC (Set B0.R73<7>=1, then set B0.R73<7>=0, and then set B0.R73<7>) during power up.
+	 */
+	val = rf_rr(dev, MT_RF(0, 73));
+	val |= 0x80;
+	rf_wr(dev, MT_RF(0, 73), val);
+	val &= ~0x80;
+	rf_wr(dev, MT_RF(0, 73), val);
+	val |= 0x80;
+	rf_wr(dev, MT_RF(0, 73), val);
+
+	/*
+	   vcocal_en (initiate VCO calibration (reset after completion)) - It should be at the end of RF configuration.
+	 */
+	rf_set(dev, MT_RF(0, 4), 0x80);
+}
+
+static void mt76x0_ant_select(struct mt76x0_dev *dev)
+{
+	/* Single antenna mode. */
+	mt76_rmw(dev, MT_WLAN_FUN_CTRL, BIT(5), BIT(6));
+	mt76_clear(dev, MT_CMB_CTRL, BIT(14) | BIT(12));
+	mt76_clear(dev, MT_COEXCFG0, BIT(2));
+	mt76_rmw(dev, MT_COEXCFG3, BIT(5) | BIT(4) | BIT(3) | BIT(2), BIT(1));
+}
+
+void mt76x0_phy_init(struct mt76x0_dev *dev)
+{
+	INIT_DELAYED_WORK(&dev->cal_work, mt76x0_phy_calibrate);
+
+	mt76x0_ant_select(dev);
+
+	mt76x0_rf_init(dev);
+
+	mt76x0_set_rx_chains(dev);
+	mt76x0_set_tx_dac(dev);
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.h b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.h
new file mode 100644
index 000000000000..2880a43c3cb0
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.h
@@ -0,0 +1,81 @@
+/*
+ * (c) Copyright 2002-2010, Ralink Technology, Inc.
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#ifndef _MT76X0_PHY_H_
+#define _MT76X0_PHY_H_
+
+#define RF_G_BAND 	0x0100
+#define RF_A_BAND 	0x0200
+#define RF_A_BAND_LB	0x0400
+#define RF_A_BAND_MB	0x0800
+#define RF_A_BAND_HB	0x1000
+#define RF_A_BAND_11J	0x2000
+
+#define RF_BW_20        1
+#define RF_BW_40        2
+#define RF_BW_10        4
+#define RF_BW_80        8
+
+#define MT_RF(bank, reg) ((bank) << 16 | (reg))
+#define MT_RF_BANK(offset) (offset >> 16)
+#define MT_RF_REG(offset) (offset & 0xff)
+
+struct mt76x0_bbp_switch_item {
+	u16 bw_band;
+	struct mt76_reg_pair reg_pair;
+};
+
+struct mt76x0_rf_switch_item {
+	u32 rf_bank_reg;
+	u16 bw_band;
+	u8 value;
+};
+
+struct mt76x0_freq_item {
+	u8 channel;
+	u32 band;
+	u8 pllR37;
+	u8 pllR36;
+	u8 pllR35;
+	u8 pllR34;
+	u8 pllR33;
+	u8 pllR32_b7b5;
+	u8 pllR32_b4b0; /* PLL_DEN (Denomina - 8) */
+	u8 pllR31_b7b5;
+	u8 pllR31_b4b0; /* PLL_K (Nominator *)*/
+	u8 pllR30_b7;	/* sdm_reset_n */
+	u8 pllR30_b6b2; /* sdmmash_prbs,sin */
+	u8 pllR30_b1;	/* sdm_bp */
+	u16 pll_n;	/* R30<0>, R29<7:0> (hex) */
+	u8 pllR28_b7b6; /* isi,iso */
+	u8 pllR28_b5b4;	/* pfd_dly */
+	u8 pllR28_b3b2;	/* clksel option */
+	u32 pll_sdm_k;	/* R28<1:0>, R27<7:0>, R26<7:0> (hex) SDM_k */
+	u8 pllR24_b1b0;	/* xo_div */
+};
+
+struct mt76x0_rate_pwr_item {
+	s8 mcs_power;
+	u8 rf_pa_mode;
+};
+
+struct mt76x0_rate_pwr_tab {
+	struct mt76x0_rate_pwr_item cck[4];
+	struct mt76x0_rate_pwr_item ofdm[8];
+	struct mt76x0_rate_pwr_item ht[8];
+	struct mt76x0_rate_pwr_item vht[10];
+	struct mt76x0_rate_pwr_item stbc[8];
+	struct mt76x0_rate_pwr_item mcs32;
+};
+
+#endif /* _MT76X0_PHY_H_ */
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/regs.h b/drivers/net/wireless/mediatek/mt76/mt76x0/regs.h
new file mode 100644
index 000000000000..16bed4aaa242
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/regs.h
@@ -0,0 +1,651 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __MT76_REGS_H
+#define __MT76_REGS_H
+
+#include <linux/bitops.h>
+
+#define MT_ASIC_VERSION			0x0000
+
+#define MT76XX_REV_E3		0x22
+#define MT76XX_REV_E4		0x33
+
+#define MT_CMB_CTRL			0x0020
+#define MT_CMB_CTRL_XTAL_RDY		BIT(22)
+#define MT_CMB_CTRL_PLL_LD		BIT(23)
+
+#define MT_EFUSE_CTRL			0x0024
+#define MT_EFUSE_CTRL_AOUT		GENMASK(5, 0)
+#define MT_EFUSE_CTRL_MODE		GENMASK(7, 6)
+#define MT_EFUSE_CTRL_LDO_OFF_TIME	GENMASK(13, 8)
+#define MT_EFUSE_CTRL_LDO_ON_TIME	GENMASK(15, 14)
+#define MT_EFUSE_CTRL_AIN		GENMASK(25, 16)
+#define MT_EFUSE_CTRL_KICK		BIT(30)
+#define MT_EFUSE_CTRL_SEL		BIT(31)
+
+#define MT_EFUSE_DATA_BASE		0x0028
+#define MT_EFUSE_DATA(_n)		(MT_EFUSE_DATA_BASE + ((_n) << 2))
+
+#define MT_COEXCFG0			0x0040
+#define MT_COEXCFG0_COEX_EN		BIT(0)
+
+#define MT_COEXCFG3			0x004c
+
+#define MT_LDO_CTRL_0			0x006c
+#define MT_LDO_CTRL_1			0x0070
+
+#define MT_WLAN_FUN_CTRL		0x0080
+#define MT_WLAN_FUN_CTRL_WLAN_EN	BIT(0)
+#define MT_WLAN_FUN_CTRL_WLAN_CLK_EN	BIT(1)
+#define MT_WLAN_FUN_CTRL_WLAN_RESET_RF	BIT(2)
+
+#define MT_WLAN_FUN_CTRL_WLAN_RESET	BIT(3) /* MT76x0 */
+#define MT_WLAN_FUN_CTRL_CSR_F20M_CKEN	BIT(3) /* MT76x2 */
+
+#define MT_WLAN_FUN_CTRL_PCIE_CLK_REQ	BIT(4)
+#define MT_WLAN_FUN_CTRL_FRC_WL_ANT_SEL	BIT(5)
+#define MT_WLAN_FUN_CTRL_INV_ANT_SEL	BIT(6)
+#define MT_WLAN_FUN_CTRL_WAKE_HOST	BIT(7)
+
+#define MT_WLAN_FUN_CTRL_THERM_RST	BIT(8) /* MT76x2 */
+#define MT_WLAN_FUN_CTRL_THERM_CKEN	BIT(9) /* MT76x2 */
+
+#define MT_WLAN_FUN_CTRL_GPIO_IN	GENMASK(15, 8) /* MT76x0 */
+#define MT_WLAN_FUN_CTRL_GPIO_OUT	GENMASK(23, 16) /* MT76x0 */
+#define MT_WLAN_FUN_CTRL_GPIO_OUT_EN	GENMASK(31, 24) /* MT76x0 */
+
+#define MT_XO_CTRL0			0x0100
+#define MT_XO_CTRL1			0x0104
+#define MT_XO_CTRL2			0x0108
+#define MT_XO_CTRL3			0x010c
+#define MT_XO_CTRL4			0x0110
+
+#define MT_XO_CTRL5			0x0114
+#define MT_XO_CTRL5_C2_VAL		GENMASK(14, 8)
+
+#define MT_XO_CTRL6			0x0118
+#define MT_XO_CTRL6_C2_CTRL		GENMASK(14, 8)
+
+#define MT_XO_CTRL7			0x011c
+
+#define MT_IOCFG_6			0x0124
+#define MT_WLAN_MTC_CTRL		0x10148
+#define MT_WLAN_MTC_CTRL_MTCMOS_PWR_UP	BIT(0)
+#define MT_WLAN_MTC_CTRL_PWR_ACK	BIT(12)
+#define MT_WLAN_MTC_CTRL_PWR_ACK_S	BIT(13)
+#define MT_WLAN_MTC_CTRL_BBP_MEM_PD	GENMASK(19, 16)
+#define MT_WLAN_MTC_CTRL_PBF_MEM_PD	BIT(20)
+#define MT_WLAN_MTC_CTRL_FCE_MEM_PD	BIT(21)
+#define MT_WLAN_MTC_CTRL_TSO_MEM_PD	BIT(22)
+#define MT_WLAN_MTC_CTRL_BBP_MEM_RB	BIT(24)
+#define MT_WLAN_MTC_CTRL_PBF_MEM_RB	BIT(25)
+#define MT_WLAN_MTC_CTRL_FCE_MEM_RB	BIT(26)
+#define MT_WLAN_MTC_CTRL_TSO_MEM_RB	BIT(27)
+#define MT_WLAN_MTC_CTRL_STATE_UP	BIT(28)
+
+#define MT_INT_SOURCE_CSR		0x0200
+#define MT_INT_MASK_CSR			0x0204
+
+#define MT_INT_RX_DONE(_n)		BIT(_n)
+#define MT_INT_RX_DONE_ALL		GENMASK(1, 0)
+#define MT_INT_TX_DONE_ALL		GENMASK(13, 4)
+#define MT_INT_TX_DONE(_n)		BIT(_n + 4)
+#define MT_INT_RX_COHERENT		BIT(16)
+#define MT_INT_TX_COHERENT		BIT(17)
+#define MT_INT_ANY_COHERENT		BIT(18)
+#define MT_INT_MCU_CMD			BIT(19)
+#define MT_INT_TBTT			BIT(20)
+#define MT_INT_PRE_TBTT			BIT(21)
+#define MT_INT_TX_STAT			BIT(22)
+#define MT_INT_AUTO_WAKEUP		BIT(23)
+#define MT_INT_GPTIMER			BIT(24)
+#define MT_INT_RXDELAYINT		BIT(26)
+#define MT_INT_TXDELAYINT		BIT(27)
+
+#define MT_WPDMA_GLO_CFG		0x0208
+#define MT_WPDMA_GLO_CFG_TX_DMA_EN	BIT(0)
+#define MT_WPDMA_GLO_CFG_TX_DMA_BUSY	BIT(1)
+#define MT_WPDMA_GLO_CFG_RX_DMA_EN	BIT(2)
+#define MT_WPDMA_GLO_CFG_RX_DMA_BUSY	BIT(3)
+#define MT_WPDMA_GLO_CFG_DMA_BURST_SIZE	GENMASK(5, 4)
+#define MT_WPDMA_GLO_CFG_TX_WRITEBACK_DONE	BIT(6)
+#define MT_WPDMA_GLO_CFG_BIG_ENDIAN	BIT(7)
+#define MT_WPDMA_GLO_CFG_HDR_SEG_LEN	GENMASK(15, 8)
+#define MT_WPDMA_GLO_CFG_CLK_GATE_DIS	BIT(30)
+#define MT_WPDMA_GLO_CFG_RX_2B_OFFSET	BIT(31)
+
+#define MT_WPDMA_RST_IDX		0x020c
+
+#define MT_WPDMA_DELAY_INT_CFG		0x0210
+
+#define MT_WMM_AIFSN		0x0214
+#define MT_WMM_AIFSN_MASK		GENMASK(3, 0)
+#define MT_WMM_AIFSN_SHIFT(_n)		((_n) * 4)
+
+#define MT_WMM_CWMIN		0x0218
+#define MT_WMM_CWMIN_MASK		GENMASK(3, 0)
+#define MT_WMM_CWMIN_SHIFT(_n)		((_n) * 4)
+
+#define MT_WMM_CWMAX		0x021c
+#define MT_WMM_CWMAX_MASK		GENMASK(3, 0)
+#define MT_WMM_CWMAX_SHIFT(_n)		((_n) * 4)
+
+#define MT_WMM_TXOP_BASE		0x0220
+#define MT_WMM_TXOP(_n)			(MT_WMM_TXOP_BASE + (((_n) / 2) << 2))
+#define MT_WMM_TXOP_SHIFT(_n)		((_n & 1) * 16)
+#define MT_WMM_TXOP_MASK		GENMASK(15, 0)
+
+#define MT_WMM_CTRL			0x0230 /* MT76x0 */
+
+#define MT_FCE_DMA_ADDR			0x0230
+#define MT_FCE_DMA_LEN			0x0234
+
+#define MT_USB_DMA_CFG			0x238
+#define MT_USB_DMA_CFG_RX_BULK_AGG_TOUT	GENMASK(7, 0)
+#define MT_USB_DMA_CFG_RX_BULK_AGG_LMT	GENMASK(15, 8)
+#define MT_USB_DMA_CFG_TX_WL_DROP	BIT(16)
+#define MT_USB_DMA_CFG_WAKEUP_EN	BIT(17)
+#define MT_USB_DMA_CFG_RX_DROP_OR_PADDING	BIT(18)
+#define MT_USB_DMA_CFG_TX_CLR		BIT(19)
+#define MT_USB_DMA_CFG_WL_LPK_EN	BIT(20)
+#define MT_USB_DMA_CFG_RX_BULK_AGG_EN	BIT(21)
+#define MT_USB_DMA_CFG_RX_BULK_EN	BIT(22)
+#define MT_USB_DMA_CFG_TX_BULK_EN	BIT(23)
+#define MT_USB_DMA_CFG_EP_OUT_VALID	GENMASK(29, 24)
+#define MT_USB_DMA_CFG_RX_BUSY		BIT(30)
+#define MT_USB_DMA_CFG_TX_BUSY		BIT(31)
+#if 0
+#define MT_USB_DMA_CFG_TX_CLR		BIT(19)
+#define MT_USB_DMA_CFG_TXOP_HALT	BIT(20)
+#define MT_USB_DMA_CFG_RX_BULK_AGG_EN	BIT(21)
+#define MT_USB_DMA_CFG_RX_BULK_EN	BIT(22)
+#define MT_USB_DMA_CFG_TX_BULK_EN	BIT(23)
+#define MT_USB_DMA_CFG_UDMA_RX_WL_DROP	BIT(25)
+#endif
+
+#define MT_TSO_CTRL			0x0250
+#define MT_HEADER_TRANS_CTRL_REG	0x0260
+
+#define MT_US_CYC_CFG			0x02a4
+#define MT_US_CYC_CNT			GENMASK(7, 0)
+
+#define MT_TX_RING_BASE			0x0300
+#define MT_RX_RING_BASE			0x03c0
+#define MT_RING_SIZE			0x10
+
+#define MT_TX_HW_QUEUE_MCU		8
+#define MT_TX_HW_QUEUE_MGMT		9
+
+#define MT_PBF_SYS_CTRL			0x0400
+#define MT_PBF_SYS_CTRL_MCU_RESET	BIT(0)
+#define MT_PBF_SYS_CTRL_DMA_RESET	BIT(1)
+#define MT_PBF_SYS_CTRL_MAC_RESET	BIT(2)
+#define MT_PBF_SYS_CTRL_PBF_RESET	BIT(3)
+#define MT_PBF_SYS_CTRL_ASY_RESET	BIT(4)
+
+#define MT_PBF_CFG			0x0404
+#define MT_PBF_CFG_TX0Q_EN		BIT(0)
+#define MT_PBF_CFG_TX1Q_EN		BIT(1)
+#define MT_PBF_CFG_TX2Q_EN		BIT(2)
+#define MT_PBF_CFG_TX3Q_EN		BIT(3)
+#define MT_PBF_CFG_RX0Q_EN		BIT(4)
+#define MT_PBF_CFG_RX_DROP_EN		BIT(8)
+
+#define MT_PBF_TX_MAX_PCNT		0x0408
+#define MT_PBF_RX_MAX_PCNT		0x040c
+
+#define MT_BCN_OFFSET_BASE		0x041c
+#define MT_BCN_OFFSET(_n)		(MT_BCN_OFFSET_BASE + ((_n) << 2))
+
+#define MT_RXQ_STA			0x0430
+#define MT_TXQ_STA			0x0434
+#define	MT_RF_CSR_CFG			0x0500
+#define MT_RF_CSR_CFG_DATA		GENMASK(7, 0)
+#define MT_RF_CSR_CFG_REG_ID		GENMASK(13, 8)
+#define MT_RF_CSR_CFG_REG_BANK		GENMASK(17, 14)
+#define MT_RF_CSR_CFG_WR		BIT(30)
+#define MT_RF_CSR_CFG_KICK		BIT(31)
+
+#define MT_RF_BYPASS_0			0x0504
+#define MT_RF_BYPASS_1			0x0508
+#define MT_RF_SETTING_0			0x050c
+
+#define MT_RF_MISC			0x0518
+#define MT_RF_DATA_WRITE		0x0524
+
+#define MT_RF_CTRL			0x0528
+#define MT_RF_CTRL_ADDR			GENMASK(11, 0)
+#define MT_RF_CTRL_WRITE		BIT(12)
+#define MT_RF_CTRL_BUSY			BIT(13)
+#define MT_RF_CTRL_IDX			BIT(16)
+
+#define MT_RF_DATA_READ			0x052c
+
+#define MT_COM_REG0			0x0730
+#define MT_COM_REG1			0x0734
+#define MT_COM_REG2			0x0738
+#define MT_COM_REG3			0x073C
+
+#define MT_FCE_PSE_CTRL			0x0800
+#define MT_FCE_PARAMETERS		0x0804
+#define MT_FCE_CSO			0x0808
+
+#define MT_FCE_L2_STUFF			0x080c
+#define MT_FCE_L2_STUFF_HT_L2_EN	BIT(0)
+#define MT_FCE_L2_STUFF_QOS_L2_EN	BIT(1)
+#define MT_FCE_L2_STUFF_RX_STUFF_EN	BIT(2)
+#define MT_FCE_L2_STUFF_TX_STUFF_EN	BIT(3)
+#define MT_FCE_L2_STUFF_WR_MPDU_LEN_EN	BIT(4)
+#define MT_FCE_L2_STUFF_MVINV_BSWAP	BIT(5)
+#define MT_FCE_L2_STUFF_TS_CMD_QSEL_EN	GENMASK(15, 8)
+#define MT_FCE_L2_STUFF_TS_LEN_EN	GENMASK(23, 16)
+#define MT_FCE_L2_STUFF_OTHER_PORT	GENMASK(25, 24)
+
+#define MT_FCE_WLAN_FLOW_CONTROL1	0x0824
+
+#define MT_TX_CPU_FROM_FCE_BASE_PTR	0x09a0
+#define MT_TX_CPU_FROM_FCE_MAX_COUNT	0x09a4
+#define MT_TX_CPU_FROM_FCE_CPU_DESC_IDX	0x09a8
+
+#define MT_FCE_PDMA_GLOBAL_CONF		0x09c4
+
+#define MT_PAUSE_ENABLE_CONTROL1	0x0a38
+
+#define MT_FCE_SKIP_FS			0x0a6c
+
+#define MT_MAC_CSR0			0x1000
+#define MT_MAC_SYS_CTRL			0x1004
+#define MT_MAC_SYS_CTRL_RESET_CSR	BIT(0)
+#define MT_MAC_SYS_CTRL_RESET_BBP	BIT(1)
+#define MT_MAC_SYS_CTRL_ENABLE_TX	BIT(2)
+#define MT_MAC_SYS_CTRL_ENABLE_RX	BIT(3)
+
+#define MT_MAC_ADDR_DW0			0x1008
+#define MT_MAC_ADDR_DW1			0x100c
+#define MT_MAC_ADDR_DW1_U2ME_MASK	GENMASK(23, 16)
+
+#define MT_MAC_BSSID_DW0		0x1010
+#define MT_MAC_BSSID_DW1		0x1014
+#define MT_MAC_BSSID_DW1_ADDR		GENMASK(15, 0)
+#define MT_MAC_BSSID_DW1_MBSS_MODE	GENMASK(17, 16)
+#define MT_MAC_BSSID_DW1_MBEACON_N	GENMASK(20, 18)
+#define MT_MAC_BSSID_DW1_MBSS_LOCAL_BIT	BIT(21)
+#define MT_MAC_BSSID_DW1_MBSS_MODE_B2	BIT(22)
+#define MT_MAC_BSSID_DW1_MBEACON_N_B3	BIT(23)
+#define MT_MAC_BSSID_DW1_MBSS_IDX_BYTE	GENMASK(26, 24)
+
+#define MT_MAX_LEN_CFG			0x1018
+#define MT_MAX_LEN_CFG_AMPDU		GENMASK(13, 12)
+
+#define MT_LED_CFG			0x102c
+
+#define MT_AMPDU_MAX_LEN_20M1S		0x1030
+#define MT_AMPDU_MAX_LEN_20M2S		0x1034
+#define MT_AMPDU_MAX_LEN_40M1S		0x1038
+#define MT_AMPDU_MAX_LEN_40M2S		0x103c
+#define MT_AMPDU_MAX_LEN		0x1040
+
+#define MT_WCID_DROP_BASE		0x106c
+#define MT_WCID_DROP(_n)		(MT_WCID_DROP_BASE + ((_n) >> 5) * 4)
+#define MT_WCID_DROP_MASK(_n)		BIT((_n) % 32)
+
+#define MT_BCN_BYPASS_MASK		0x108c
+
+#define MT_MAC_APC_BSSID_BASE		0x1090
+#define MT_MAC_APC_BSSID_L(_n)		(MT_MAC_APC_BSSID_BASE + ((_n) * 8))
+#define MT_MAC_APC_BSSID_H(_n)		(MT_MAC_APC_BSSID_BASE + ((_n) * 8 + 4))
+#define MT_MAC_APC_BSSID_H_ADDR		GENMASK(15, 0)
+#define MT_MAC_APC_BSSID0_H_EN		BIT(16)
+
+#define MT_XIFS_TIME_CFG		0x1100
+#define MT_XIFS_TIME_CFG_CCK_SIFS	GENMASK(7, 0)
+#define MT_XIFS_TIME_CFG_OFDM_SIFS	GENMASK(15, 8)
+#define MT_XIFS_TIME_CFG_OFDM_XIFS	GENMASK(19, 16)
+#define MT_XIFS_TIME_CFG_EIFS		GENMASK(28, 20)
+#define MT_XIFS_TIME_CFG_BB_RXEND_EN	BIT(29)
+
+#define MT_BKOFF_SLOT_CFG		0x1104
+#define MT_BKOFF_SLOT_CFG_SLOTTIME	GENMASK(7, 0)
+#define MT_BKOFF_SLOT_CFG_CC_DELAY	GENMASK(11, 8)
+
+#define MT_BEACON_TIME_CFG		0x1114
+#define MT_BEACON_TIME_CFG_INTVAL	GENMASK(15, 0)
+#define MT_BEACON_TIME_CFG_TIMER_EN	BIT(16)
+#define MT_BEACON_TIME_CFG_SYNC_MODE	GENMASK(18, 17)
+#define MT_BEACON_TIME_CFG_TBTT_EN	BIT(19)
+#define MT_BEACON_TIME_CFG_BEACON_TX	BIT(20)
+#define MT_BEACON_TIME_CFG_TSF_COMP	GENMASK(31, 24)
+
+#define MT_TBTT_SYNC_CFG		0x1118
+#define MT_TBTT_TIMER_CFG		0x1124
+
+#define MT_INT_TIMER_CFG		0x1128
+#define MT_INT_TIMER_CFG_PRE_TBTT	GENMASK(15, 0)
+#define MT_INT_TIMER_CFG_GP_TIMER	GENMASK(31, 16)
+
+#define MT_INT_TIMER_EN			0x112c
+#define MT_INT_TIMER_EN_PRE_TBTT_EN	BIT(0)
+#define MT_INT_TIMER_EN_GP_TIMER_EN	BIT(1)
+
+#define MT_MAC_STATUS			0x1200
+#define MT_MAC_STATUS_TX		BIT(0)
+#define MT_MAC_STATUS_RX		BIT(1)
+
+#define MT_PWR_PIN_CFG			0x1204
+#define MT_AUX_CLK_CFG			0x120c
+
+#define MT_BB_PA_MODE_CFG0		0x1214
+#define MT_BB_PA_MODE_CFG1		0x1218
+#define MT_RF_PA_MODE_CFG0		0x121c
+#define MT_RF_PA_MODE_CFG1		0x1220
+
+#define MT_RF_PA_MODE_ADJ0		0x1228
+#define MT_RF_PA_MODE_ADJ1		0x122c
+
+#define MT_DACCLK_EN_DLY_CFG		0x1264
+
+#define MT_EDCA_CFG_BASE		0x1300
+#define MT_EDCA_CFG_AC(_n)		(MT_EDCA_CFG_BASE + ((_n) << 2))
+#define MT_EDCA_CFG_TXOP		GENMASK(7, 0)
+#define MT_EDCA_CFG_AIFSN		GENMASK(11, 8)
+#define MT_EDCA_CFG_CWMIN		GENMASK(15, 12)
+#define MT_EDCA_CFG_CWMAX		GENMASK(19, 16)
+
+#define MT_TX_PWR_CFG_0			0x1314
+#define MT_TX_PWR_CFG_1			0x1318
+#define MT_TX_PWR_CFG_2			0x131c
+#define MT_TX_PWR_CFG_3			0x1320
+#define MT_TX_PWR_CFG_4			0x1324
+
+#define MT_TX_BAND_CFG			0x132c
+#define MT_TX_BAND_CFG_UPPER_40M	BIT(0)
+#define MT_TX_BAND_CFG_5G		BIT(1)
+#define MT_TX_BAND_CFG_2G		BIT(2)
+
+#define MT_HT_FBK_TO_LEGACY		0x1384
+#define MT_TX_MPDU_ADJ_INT		0x1388
+
+#define MT_TX_PWR_CFG_7			0x13d4
+#define MT_TX_PWR_CFG_8			0x13d8
+#define MT_TX_PWR_CFG_9			0x13dc
+
+#define MT_TX_SW_CFG0			0x1330
+#define MT_TX_SW_CFG1			0x1334
+#define MT_TX_SW_CFG2			0x1338
+
+#define MT_TXOP_CTRL_CFG		0x1340
+#define MT_TXOP_TRUN_EN			GENMASK(5, 0)
+#define MT_TXOP_EXT_CCA_DLY		GENMASK(15, 8)
+#define MT_TXOP_CTRL
+
+#define MT_TX_RTS_CFG			0x1344
+#define MT_TX_RTS_CFG_RETRY_LIMIT	GENMASK(7, 0)
+#define MT_TX_RTS_CFG_THRESH		GENMASK(23, 8)
+#define MT_TX_RTS_FALLBACK		BIT(24)
+
+#define MT_TX_TIMEOUT_CFG		0x1348
+#define MT_TX_RETRY_CFG			0x134c
+#define MT_TX_LINK_CFG			0x1350
+#define MT_HT_FBK_CFG0			0x1354
+#define MT_HT_FBK_CFG1			0x1358
+#define MT_LG_FBK_CFG0			0x135c
+#define MT_LG_FBK_CFG1			0x1360
+
+#define MT_CCK_PROT_CFG			0x1364
+#define MT_OFDM_PROT_CFG		0x1368
+#define MT_MM20_PROT_CFG		0x136c
+#define MT_MM40_PROT_CFG		0x1370
+#define MT_GF20_PROT_CFG		0x1374
+#define MT_GF40_PROT_CFG		0x1378
+
+#define MT_PROT_RATE			GENMASK(15, 0)
+#define MT_PROT_CTRL_RTS_CTS		BIT(16)
+#define MT_PROT_CTRL_CTS2SELF		BIT(17)
+#define MT_PROT_NAV_SHORT		BIT(18)
+#define MT_PROT_NAV_LONG		BIT(19)
+#define MT_PROT_TXOP_ALLOW_CCK		BIT(20)
+#define MT_PROT_TXOP_ALLOW_OFDM		BIT(21)
+#define MT_PROT_TXOP_ALLOW_MM20		BIT(22)
+#define MT_PROT_TXOP_ALLOW_MM40		BIT(23)
+#define MT_PROT_TXOP_ALLOW_GF20		BIT(24)
+#define MT_PROT_TXOP_ALLOW_GF40		BIT(25)
+#define MT_PROT_RTS_THR_EN		BIT(26)
+#define MT_PROT_RATE_CCK_11		0x0003
+#define MT_PROT_RATE_OFDM_6		0x4000
+#define MT_PROT_RATE_OFDM_24		0x4004
+#define MT_PROT_RATE_DUP_OFDM_24	0x4084
+#define MT_PROT_TXOP_ALLOW_ALL		GENMASK(25, 20)
+#define MT_PROT_TXOP_ALLOW_BW20		(MT_PROT_TXOP_ALLOW_ALL &	\
+					 ~MT_PROT_TXOP_ALLOW_MM40 &	\
+					 ~MT_PROT_TXOP_ALLOW_GF40)
+
+#define MT_EXP_ACK_TIME			0x1380
+
+#define MT_TX_PWR_CFG_0_EXT		0x1390
+#define MT_TX_PWR_CFG_1_EXT		0x1394
+
+#define MT_TX_FBK_LIMIT			0x1398
+#define MT_TX_FBK_LIMIT_MPDU_FBK	GENMASK(7, 0)
+#define MT_TX_FBK_LIMIT_AMPDU_FBK	GENMASK(15, 8)
+#define MT_TX_FBK_LIMIT_MPDU_UP_CLEAR	BIT(16)
+#define MT_TX_FBK_LIMIT_AMPDU_UP_CLEAR	BIT(17)
+#define MT_TX_FBK_LIMIT_RATE_LUT	BIT(18)
+
+#define MT_TX0_RF_GAIN_CORR		0x13a0
+#define MT_TX1_RF_GAIN_CORR		0x13a4
+#define MT_TX0_RF_GAIN_ATTEN		0x13a8
+
+#define MT_TX_ALC_CFG_0			0x13b0
+#define MT_TX_ALC_CFG_0_CH_INIT_0	GENMASK(5, 0)
+#define MT_TX_ALC_CFG_0_CH_INIT_1	GENMASK(13, 8)
+#define MT_TX_ALC_CFG_0_LIMIT_0		GENMASK(21, 16)
+#define MT_TX_ALC_CFG_0_LIMIT_1		GENMASK(29, 24)
+
+#define MT_TX_ALC_CFG_1			0x13b4
+#define MT_TX_ALC_CFG_1_TEMP_COMP	GENMASK(5, 0)
+
+#define MT_TX_ALC_CFG_2			0x13a8
+#define MT_TX_ALC_CFG_2_TEMP_COMP	GENMASK(5, 0)
+
+#define MT_TX0_BB_GAIN_ATTEN		0x13c0
+
+#define MT_TX_ALC_VGA3			0x13c8
+
+#define MT_TX_PROT_CFG6			0x13e0
+#define MT_TX_PROT_CFG7			0x13e4
+#define MT_TX_PROT_CFG8			0x13e8
+
+#define MT_PIFS_TX_CFG			0x13ec
+
+#define MT_RX_FILTR_CFG			0x1400
+
+#define MT_RX_FILTR_CFG_CRC_ERR		BIT(0)
+#define MT_RX_FILTR_CFG_PHY_ERR		BIT(1)
+#define MT_RX_FILTR_CFG_PROMISC		BIT(2)
+#define MT_RX_FILTR_CFG_OTHER_BSS	BIT(3)
+#define MT_RX_FILTR_CFG_VER_ERR		BIT(4)
+#define MT_RX_FILTR_CFG_MCAST		BIT(5)
+#define MT_RX_FILTR_CFG_BCAST		BIT(6)
+#define MT_RX_FILTR_CFG_DUP		BIT(7)
+#define MT_RX_FILTR_CFG_CFACK		BIT(8)
+#define MT_RX_FILTR_CFG_CFEND		BIT(9)
+#define MT_RX_FILTR_CFG_ACK		BIT(10)
+#define MT_RX_FILTR_CFG_CTS		BIT(11)
+#define MT_RX_FILTR_CFG_RTS		BIT(12)
+#define MT_RX_FILTR_CFG_PSPOLL		BIT(13)
+#define MT_RX_FILTR_CFG_BA		BIT(14)
+#define MT_RX_FILTR_CFG_BAR		BIT(15)
+#define MT_RX_FILTR_CFG_CTRL_RSV	BIT(16)
+
+#define MT_AUTO_RSP_CFG			0x1404
+
+#define MT_AUTO_RSP_PREAMB_SHORT	BIT(4)
+
+#define MT_LEGACY_BASIC_RATE		0x1408
+#define MT_HT_BASIC_RATE		0x140c
+#define MT_HT_CTRL_CFG			0x1410
+#define MT_RX_PARSER_CFG		0x1418
+#define MT_RX_PARSER_RX_SET_NAV_ALL	BIT(0)
+
+#define MT_EXT_CCA_CFG			0x141c
+#define MT_EXT_CCA_CFG_CCA0		GENMASK(1, 0)
+#define MT_EXT_CCA_CFG_CCA1		GENMASK(3, 2)
+#define MT_EXT_CCA_CFG_CCA2		GENMASK(5, 4)
+#define MT_EXT_CCA_CFG_CCA3		GENMASK(7, 6)
+#define MT_EXT_CCA_CFG_CCA_MASK		GENMASK(11, 8)
+#define MT_EXT_CCA_CFG_ED_CCA_MASK	GENMASK(15, 12)
+
+#define MT_TX_SW_CFG3			0x1478
+
+#define MT_PN_PAD_MODE			0x150c
+
+#define MT_TXOP_HLDR_ET			0x1608
+
+#define MT_PROT_AUTO_TX_CFG		0x1648
+
+#define MT_RX_STA_CNT0			0x1700
+#define MT_RX_STA_CNT1			0x1704
+#define MT_RX_STA_CNT2			0x1708
+#define MT_TX_STA_CNT0			0x170c
+#define MT_TX_STA_CNT1			0x1710
+#define MT_TX_STA_CNT2			0x1714
+
+/* Vendor driver defines content of the second word of STAT_FIFO as follows:
+ *	MT_TX_STAT_FIFO_RATE		GENMASK(26, 16)
+ *	MT_TX_STAT_FIFO_ETXBF		BIT(27)
+ *	MT_TX_STAT_FIFO_SND		BIT(28)
+ *	MT_TX_STAT_FIFO_ITXBF		BIT(29)
+ * However, tests show that b16-31 have the same layout as TXWI rate_ctl
+ * with rate set to rate at which frame was acked.
+ */
+#define MT_TX_STAT_FIFO			0x1718
+#define MT_TX_STAT_FIFO_VALID		BIT(0)
+#define MT_TX_STAT_FIFO_SUCCESS		BIT(5)
+#define MT_TX_STAT_FIFO_AGGR		BIT(6)
+#define MT_TX_STAT_FIFO_ACKREQ		BIT(7)
+#define MT_TX_STAT_FIFO_WCID		GENMASK(15, 8)
+#define MT_TX_STAT_FIFO_RATE		GENMASK(31, 16)
+
+#define MT_TX_AGG_STAT			0x171c
+
+#define MT_TX_AGG_CNT_BASE0		0x1720
+
+#define MT_MPDU_DENSITY_CNT		0x1740
+
+#define MT_TX_AGG_CNT_BASE1		0x174c
+
+#define MT_TX_AGG_CNT(_id)		((_id) < 8 ?			\
+					 MT_TX_AGG_CNT_BASE0 + ((_id) << 2) : \
+					 MT_TX_AGG_CNT_BASE1 + ((_id - 8) << 2))
+
+#define MT_TX_STAT_FIFO_EXT		0x1798
+#define MT_TX_STAT_FIFO_EXT_RETRY	GENMASK(7, 0)
+#define MT_TX_STAT_FIFO_EXT_PKTID	GENMASK(15, 8)
+
+#define MT_BBP_CORE_BASE		0x2000
+#define MT_BBP_IBI_BASE			0x2100
+#define MT_BBP_AGC_BASE			0x2300
+#define MT_BBP_TXC_BASE			0x2400
+#define MT_BBP_RXC_BASE			0x2500
+#define MT_BBP_TXO_BASE			0x2600
+#define MT_BBP_TXBE_BASE		0x2700
+#define MT_BBP_RXFE_BASE		0x2800
+#define MT_BBP_RXO_BASE			0x2900
+#define MT_BBP_DFS_BASE			0x2a00
+#define MT_BBP_TR_BASE			0x2b00
+#define MT_BBP_CAL_BASE			0x2c00
+#define MT_BBP_DSC_BASE			0x2e00
+#define MT_BBP_PFMU_BASE		0x2f00
+
+#define MT_BBP(_type, _n)		(MT_BBP_##_type##_BASE + ((_n) << 2))
+
+#define MT_BBP_CORE_R1_BW		GENMASK(4, 3)
+
+#define MT_BBP_AGC_R0_CTRL_CHAN		GENMASK(9, 8)
+#define MT_BBP_AGC_R0_BW		GENMASK(14, 12)
+
+/* AGC, R4/R5 */
+#define MT_BBP_AGC_LNA_GAIN		GENMASK(21, 16)
+
+/* AGC, R8/R9 */
+#define MT_BBP_AGC_GAIN			GENMASK(14, 8)
+
+#define MT_BBP_AGC20_RSSI0		GENMASK(7, 0)
+#define MT_BBP_AGC20_RSSI1		GENMASK(15, 8)
+
+#define MT_BBP_TXBE_R0_CTRL_CHAN	GENMASK(1, 0)
+
+#define MT_WCID_ADDR_BASE		0x1800
+#define MT_WCID_ADDR(_n)		(MT_WCID_ADDR_BASE + (_n) * 8)
+
+#define MT_SRAM_BASE			0x4000
+
+#define MT_WCID_KEY_BASE		0x8000
+#define MT_WCID_KEY(_n)			(MT_WCID_KEY_BASE + (_n) * 32)
+
+#define MT_WCID_IV_BASE			0xa000
+#define MT_WCID_IV(_n)			(MT_WCID_IV_BASE + (_n) * 8)
+
+#define MT_WCID_ATTR_BASE		0xa800
+#define MT_WCID_ATTR(_n)		(MT_WCID_ATTR_BASE + (_n) * 4)
+
+#define MT_WCID_ATTR_PAIRWISE		BIT(0)
+#define MT_WCID_ATTR_PKEY_MODE		GENMASK(3, 1)
+#define MT_WCID_ATTR_BSS_IDX		GENMASK(6, 4)
+#define MT_WCID_ATTR_RXWI_UDF		GENMASK(9, 7)
+#define MT_WCID_ATTR_PKEY_MODE_EXT	BIT(10)
+#define MT_WCID_ATTR_BSS_IDX_EXT	BIT(11)
+#define MT_WCID_ATTR_WAPI_MCBC		BIT(15)
+#define MT_WCID_ATTR_WAPI_KEYID		GENMASK(31, 24)
+
+#define MT_SKEY_BASE_0			0xac00
+#define MT_SKEY_BASE_1			0xb400
+#define MT_SKEY_0(_bss, _idx)		\
+	(MT_SKEY_BASE_0 + (4 * (_bss) + _idx) * 32)
+#define MT_SKEY_1(_bss, _idx)		\
+	(MT_SKEY_BASE_1 + (4 * ((_bss) & 7) + _idx) * 32)
+#define MT_SKEY(_bss, _idx)		\
+	((_bss & 8) ? MT_SKEY_1(_bss, _idx) : MT_SKEY_0(_bss, _idx))
+
+#define MT_SKEY_MODE_BASE_0		0xb000
+#define MT_SKEY_MODE_BASE_1		0xb3f0
+#define MT_SKEY_MODE_0(_bss)		\
+	(MT_SKEY_MODE_BASE_0 + ((_bss / 2) << 2))
+#define MT_SKEY_MODE_1(_bss)		\
+	(MT_SKEY_MODE_BASE_1 + ((((_bss) & 7) / 2) << 2))
+#define MT_SKEY_MODE(_bss)		\
+	((_bss & 8) ? MT_SKEY_MODE_1(_bss) : MT_SKEY_MODE_0(_bss))
+#define MT_SKEY_MODE_MASK		GENMASK(3, 0)
+#define MT_SKEY_MODE_SHIFT(_bss, _idx)	(4 * ((_idx) + 4 * (_bss & 1)))
+
+#define MT_BEACON_BASE			0xc000
+
+#define MT_TEMP_SENSOR			0x1d000
+#define MT_TEMP_SENSOR_VAL		GENMASK(6, 0)
+
+enum mt76_cipher_type {
+	MT_CIPHER_NONE,
+	MT_CIPHER_WEP40,
+	MT_CIPHER_WEP104,
+	MT_CIPHER_TKIP,
+	MT_CIPHER_AES_CCMP,
+	MT_CIPHER_CKIP40,
+	MT_CIPHER_CKIP104,
+	MT_CIPHER_CKIP128,
+	MT_CIPHER_WAPI,
+};
+
+#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/trace.c b/drivers/net/wireless/mediatek/mt76/mt76x0/trace.c
new file mode 100644
index 000000000000..8abdd3cd546d
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/trace.c
@@ -0,0 +1,21 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+
+#ifndef __CHECKER__
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
+#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/trace.h b/drivers/net/wireless/mediatek/mt76/mt76x0/trace.h
new file mode 100644
index 000000000000..8a752a09f2dc
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/trace.h
@@ -0,0 +1,313 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#if !defined(__MT76X0U_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __MT76X0U_TRACE_H
+
+#include <linux/tracepoint.h>
+#include "mt76x0.h"
+#include "mac.h"
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mt76x0
+
+#define MAXNAME		32
+#define DEV_ENTRY	__array(char, wiphy_name, 32)
+#define DEV_ASSIGN	strlcpy(__entry->wiphy_name,			\
+				wiphy_name(dev->hw->wiphy), MAXNAME)
+#define DEV_PR_FMT	"%s "
+#define DEV_PR_ARG	__entry->wiphy_name
+
+#define REG_ENTRY	__field(u32, reg) __field(u32, val)
+#define REG_ASSIGN	__entry->reg = reg; __entry->val = val
+#define REG_PR_FMT	"%04x=%08x"
+#define REG_PR_ARG	__entry->reg, __entry->val
+
+DECLARE_EVENT_CLASS(dev_reg_evt,
+	TP_PROTO(struct mt76_dev *dev, u32 reg, u32 val),
+	TP_ARGS(dev, reg, val),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		REG_ENTRY
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		REG_ASSIGN;
+	),
+	TP_printk(
+		DEV_PR_FMT REG_PR_FMT,
+		DEV_PR_ARG, REG_PR_ARG
+	)
+);
+
+DEFINE_EVENT(dev_reg_evt, mt76x0_reg_read,
+	TP_PROTO(struct mt76_dev *dev, u32 reg, u32 val),
+	TP_ARGS(dev, reg, val)
+);
+
+DEFINE_EVENT(dev_reg_evt, mt76x0_reg_write,
+	TP_PROTO(struct mt76_dev *dev, u32 reg, u32 val),
+	TP_ARGS(dev, reg, val)
+);
+
+TRACE_EVENT(mt76x0_submit_urb,
+	TP_PROTO(struct mt76_dev *dev, struct urb *u),
+	TP_ARGS(dev, u),
+	TP_STRUCT__entry(
+		DEV_ENTRY __field(unsigned, pipe) __field(u32, len)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->pipe = u->pipe;
+		__entry->len = u->transfer_buffer_length;
+	),
+	TP_printk(DEV_PR_FMT "p:%08x len:%u",
+		  DEV_PR_ARG, __entry->pipe, __entry->len)
+);
+
+#define trace_mt76x0_submit_urb_sync(__dev, __pipe, __len) ({	\
+	struct urb u;					\
+	u.pipe = __pipe;				\
+	u.transfer_buffer_length = __len;		\
+	trace_mt76x0_submit_urb(__dev, &u);			\
+})
+
+TRACE_EVENT(mt76x0_mcu_msg_send,
+	TP_PROTO(struct mt76_dev *dev,
+		 struct sk_buff *skb, u32 csum, bool resp),
+	TP_ARGS(dev, skb, csum, resp),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(u32, info)
+		__field(u32, csum)
+		__field(bool, resp)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->info = *(u32 *)skb->data;
+		__entry->csum = csum;
+		__entry->resp = resp;
+	),
+	TP_printk(DEV_PR_FMT "i:%08x c:%08x r:%d",
+		  DEV_PR_ARG, __entry->info, __entry->csum, __entry->resp)
+);
+
+TRACE_EVENT(mt76x0_vend_req,
+	TP_PROTO(struct mt76_dev *dev, unsigned pipe, u8 req, u8 req_type,
+		 u16 val, u16 offset, void *buf, size_t buflen, int ret),
+	TP_ARGS(dev, pipe, req, req_type, val, offset, buf, buflen, ret),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(unsigned, pipe) __field(u8, req) __field(u8, req_type)
+		__field(u16, val) __field(u16, offset) __field(void*, buf)
+		__field(int, buflen) __field(int, ret)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->pipe = pipe;
+		__entry->req = req;
+		__entry->req_type = req_type;
+		__entry->val = val;
+		__entry->offset = offset;
+		__entry->buf = buf;
+		__entry->buflen = buflen;
+		__entry->ret = ret;
+	),
+	TP_printk(DEV_PR_FMT
+		  "%d p:%08x req:%02hhx %02hhx val:%04hx %04hx buf:%d %d",
+		  DEV_PR_ARG, __entry->ret, __entry->pipe, __entry->req,
+		  __entry->req_type, __entry->val, __entry->offset,
+		  !!__entry->buf, __entry->buflen)
+);
+
+DECLARE_EVENT_CLASS(dev_rf_reg_evt,
+	TP_PROTO(struct mt76_dev *dev, u8 bank, u8 reg, u8 val),
+	TP_ARGS(dev, bank, reg, val),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(u8, bank)
+		__field(u8, reg)
+		__field(u8, val)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		REG_ASSIGN;
+		__entry->bank = bank;
+	),
+	TP_printk(
+		DEV_PR_FMT "%02hhx:%02hhx=%02hhx",
+		DEV_PR_ARG, __entry->bank, __entry->reg, __entry->val
+	)
+);
+
+DEFINE_EVENT(dev_rf_reg_evt, mt76x0_rf_read,
+	TP_PROTO(struct mt76_dev *dev, u8 bank, u8 reg, u8 val),
+	TP_ARGS(dev, bank, reg, val)
+);
+
+DEFINE_EVENT(dev_rf_reg_evt, mt76x0_rf_write,
+	TP_PROTO(struct mt76_dev *dev, u8 bank, u8 reg, u8 val),
+	TP_ARGS(dev, bank, reg, val)
+);
+
+DECLARE_EVENT_CLASS(dev_simple_evt,
+	TP_PROTO(struct mt76_dev *dev, u8 val),
+	TP_ARGS(dev, val),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(u8, val)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->val = val;
+	),
+	TP_printk(
+		DEV_PR_FMT "%02hhx", DEV_PR_ARG, __entry->val
+	)
+);
+
+TRACE_EVENT(mt76x0_rx,
+	TP_PROTO(struct mt76_dev *dev, struct mt76x0_rxwi *rxwi, u32 f),
+	TP_ARGS(dev, rxwi, f),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field_struct(struct mt76x0_rxwi, rxwi)
+		__field(u32, fce_info)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->rxwi = *rxwi;
+		__entry->fce_info = f;
+	),
+	TP_printk(DEV_PR_FMT "rxi:%08x ctl:%08x", DEV_PR_ARG,
+		  le32_to_cpu(__entry->rxwi.rxinfo),
+		  le32_to_cpu(__entry->rxwi.ctl))
+);
+
+TRACE_EVENT(mt76x0_tx,
+	TP_PROTO(struct mt76_dev *dev, struct sk_buff *skb,
+		 struct mt76_sta *sta, struct mt76_txwi *h),
+	TP_ARGS(dev, skb, sta, h),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field_struct(struct mt76_txwi, h)
+		__field(struct sk_buff *, skb)
+		__field(struct mt76_sta *, sta)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->h = *h;
+		__entry->skb = skb;
+		__entry->sta = sta;
+	),
+	TP_printk(DEV_PR_FMT "skb:%p sta:%p  flg:%04hx rate_ctl:%04hx "
+		  "ack:%02hhx wcid:%02hhx len_ctl:%05hx", DEV_PR_ARG,
+		  __entry->skb, __entry->sta,
+		  le16_to_cpu(__entry->h.flags),
+		  le16_to_cpu(__entry->h.rate_ctl),
+		  __entry->h.ack_ctl, __entry->h.wcid,
+		  le16_to_cpu(__entry->h.len_ctl))
+);
+
+TRACE_EVENT(mt76x0_tx_dma_done,
+	TP_PROTO(struct mt76_dev *dev, struct sk_buff *skb),
+	TP_ARGS(dev, skb),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(struct sk_buff *, skb)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->skb = skb;
+	),
+	TP_printk(DEV_PR_FMT "%p", DEV_PR_ARG, __entry->skb)
+);
+
+TRACE_EVENT(mt76x0_tx_status_cleaned,
+	TP_PROTO(struct mt76_dev *dev, int cleaned),
+	TP_ARGS(dev, cleaned),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(int, cleaned)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->cleaned = cleaned;
+	),
+	TP_printk(DEV_PR_FMT "%d", DEV_PR_ARG, __entry->cleaned)
+);
+
+TRACE_EVENT(mt76x0_tx_status,
+	TP_PROTO(struct mt76_dev *dev, u32 stat1, u32 stat2),
+	TP_ARGS(dev, stat1, stat2),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(u32, stat1)	__field(u32, stat2)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->stat1 = stat1;
+		__entry->stat2 = stat2;
+	),
+	TP_printk(DEV_PR_FMT "%08x %08x",
+		  DEV_PR_ARG, __entry->stat1, __entry->stat2)
+);
+
+TRACE_EVENT(mt76x0_rx_dma_aggr,
+	TP_PROTO(struct mt76_dev *dev, int cnt, bool paged),
+	TP_ARGS(dev, cnt, paged),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(u8, cnt)
+		__field(bool, paged)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->cnt = cnt;
+		__entry->paged = paged;
+	),
+	TP_printk(DEV_PR_FMT "cnt:%d paged:%d",
+		  DEV_PR_ARG, __entry->cnt, __entry->paged)
+);
+
+DEFINE_EVENT(dev_simple_evt, mt76x0_set_key,
+	TP_PROTO(struct mt76_dev *dev, u8 val),
+	TP_ARGS(dev, val)
+);
+
+TRACE_EVENT(mt76x0_set_shared_key,
+	TP_PROTO(struct mt76_dev *dev, u8 vid, u8 key),
+	TP_ARGS(dev, vid, key),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(u8, vid)
+		__field(u8, key)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->vid = vid;
+		__entry->key = key;
+	),
+	TP_printk(DEV_PR_FMT "phy:%02hhx off:%02hhx",
+		  DEV_PR_ARG, __entry->vid, __entry->key)
+);
+
+#endif
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+
+#include <trace/define_trace.h>
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/tx.c b/drivers/net/wireless/mediatek/mt76/mt76x0/tx.c
new file mode 100644
index 000000000000..751b49c28ae5
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/tx.c
@@ -0,0 +1,270 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include "mt76x0.h"
+#include "trace.h"
+
+/* Take mac80211 Q id from the skb and translate it to hardware Q id */
+static u8 skb2q(struct sk_buff *skb)
+{
+	int qid = skb_get_queue_mapping(skb);
+
+	if (WARN_ON(qid >= MT_TXQ_PSD)) {
+		qid = MT_TXQ_BE;
+		skb_set_queue_mapping(skb, qid);
+	}
+
+	return q2hwq(qid);
+}
+
+static void mt76x0_tx_skb_remove_dma_overhead(struct sk_buff *skb,
+					       struct ieee80211_tx_info *info)
+{
+	int pkt_len = (unsigned long)info->status.status_driver_data[0];
+
+	skb_pull(skb, sizeof(struct mt76_txwi) + 4);
+	if (ieee80211_get_hdrlen_from_skb(skb) % 4)
+		mt76x0_remove_hdr_pad(skb);
+
+	skb_trim(skb, pkt_len);
+}
+
+void mt76x0_tx_status(struct mt76x0_dev *dev, struct sk_buff *skb)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+
+	mt76x0_tx_skb_remove_dma_overhead(skb, info);
+
+	ieee80211_tx_info_clear_status(info);
+	info->status.rates[0].idx = -1;
+	info->flags |= IEEE80211_TX_STAT_ACK;
+
+	spin_lock(&dev->mac_lock);
+	ieee80211_tx_status(dev->mt76.hw, skb);
+	spin_unlock(&dev->mac_lock);
+}
+
+static int mt76x0_skb_rooms(struct mt76x0_dev *dev, struct sk_buff *skb)
+{
+	int hdr_len = ieee80211_get_hdrlen_from_skb(skb);
+	u32 need_head;
+
+	need_head = sizeof(struct mt76_txwi) + 4;
+	if (hdr_len % 4)
+		need_head += 2;
+
+	return skb_cow(skb, need_head);
+}
+
+static struct mt76_txwi *
+mt76x0_push_txwi(struct mt76x0_dev *dev, struct sk_buff *skb,
+		  struct ieee80211_sta *sta, struct mt76_wcid *wcid,
+		  int pkt_len)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ieee80211_tx_rate *rate = &info->control.rates[0];
+	struct mt76_txwi *txwi;
+	unsigned long flags;
+	u16 txwi_flags = 0;
+	u32 pkt_id;
+	u16 rate_ctl;
+	u8 nss;
+
+	txwi = (struct mt76_txwi *)skb_push(skb, sizeof(struct mt76_txwi));
+	memset(txwi, 0, sizeof(*txwi));
+
+	if (!wcid->tx_rate_set)
+		ieee80211_get_tx_rates(info->control.vif, sta, skb,
+				       info->control.rates, 1);
+
+	spin_lock_irqsave(&dev->mt76.lock, flags);
+	if (rate->idx < 0 || !rate->count) {
+		rate_ctl = wcid->tx_rate;
+		nss = wcid->tx_rate_nss;
+	} else {
+		rate_ctl = mt76x0_mac_tx_rate_val(dev, rate, &nss);
+	}
+	spin_unlock_irqrestore(&dev->mt76.lock, flags);
+
+	txwi->rate_ctl = cpu_to_le16(rate_ctl);
+
+	if (info->flags & IEEE80211_TX_CTL_LDPC)
+		txwi->rate_ctl |= cpu_to_le16(MT_RXWI_RATE_LDPC);
+	if ((info->flags & IEEE80211_TX_CTL_STBC) && nss == 1)
+		txwi->rate_ctl |= cpu_to_le16(MT_RXWI_RATE_STBC);
+	if (nss > 1 && sta && sta->smps_mode == IEEE80211_SMPS_DYNAMIC)
+		txwi_flags |= MT_TXWI_FLAGS_MMPS;
+
+	if (!(info->flags & IEEE80211_TX_CTL_NO_ACK)) {
+		txwi->ack_ctl |= MT_TXWI_ACK_CTL_REQ;
+		pkt_id = 1;
+	} else {
+		pkt_id = 0;
+	}
+
+	if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE)
+		pkt_id |= MT_TXWI_PKTID_PROBE;
+
+	if (info->flags & IEEE80211_TX_CTL_ASSIGN_SEQ)
+		txwi->ack_ctl |= MT_TXWI_ACK_CTL_NSEQ;
+
+	if ((info->flags & IEEE80211_TX_CTL_AMPDU) && sta) {
+		u8 ba_size = IEEE80211_MIN_AMPDU_BUF;
+
+		ba_size <<= sta->ht_cap.ampdu_factor;
+		ba_size = min_t(int, 7, ba_size - 1);
+		if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) {
+			ba_size = 0;
+		} else {
+			txwi_flags |= MT_TXWI_FLAGS_AMPDU;
+			txwi_flags |= FIELD_PREP(MT_TXWI_FLAGS_MPDU_DENSITY,
+						 sta->ht_cap.ampdu_density);
+		}
+		txwi->ack_ctl |= FIELD_PREP(MT_TXWI_ACK_CTL_BA_WINDOW, ba_size);
+	}
+
+	txwi->wcid = wcid->idx;
+	txwi->flags |= cpu_to_le16(txwi_flags);
+	txwi->len_ctl = cpu_to_le16(pkt_len);
+	txwi->pktid = pkt_id;
+
+	return txwi;
+}
+
+void mt76x0_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control,
+		struct sk_buff *skb)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct mt76x0_dev *dev = hw->priv;
+	struct ieee80211_vif *vif = info->control.vif;
+	struct ieee80211_sta *sta = control->sta;
+	struct mt76_sta *msta = NULL;
+	struct mt76_wcid *wcid = dev->mon_wcid;
+	struct mt76_txwi *txwi;
+	int pkt_len = skb->len;
+	int hw_q = skb2q(skb);
+
+	BUILD_BUG_ON(ARRAY_SIZE(info->status.status_driver_data) < 1);
+	info->status.status_driver_data[0] = (void *)(unsigned long)pkt_len;
+
+	if (mt76x0_skb_rooms(dev, skb) || mt76x0_insert_hdr_pad(skb)) {
+		ieee80211_free_txskb(dev->mt76.hw, skb);
+		return;
+	}
+
+	if (sta) {
+		msta = (struct mt76_sta *) sta->drv_priv;
+		wcid = &msta->wcid;
+	} else if (vif && (!info->control.hw_key && wcid->hw_key_idx != -1)) {
+		struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv;
+
+		wcid = &mvif->group_wcid;
+	}
+
+	txwi = mt76x0_push_txwi(dev, skb, sta, wcid, pkt_len);
+
+	if (mt76x0_dma_enqueue_tx(dev, skb, wcid, hw_q))
+		return;
+
+	trace_mt76x0_tx(&dev->mt76, skb, msta, txwi);
+}
+
+void mt76x0_tx_stat(struct work_struct *work)
+{
+	struct mt76x0_dev *dev = container_of(work, struct mt76x0_dev,
+					       stat_work.work);
+	struct mt76_tx_status stat;
+	unsigned long flags;
+	int cleaned = 0;
+	u8 update = 1;
+
+	while (!test_bit(MT76_REMOVED, &dev->mt76.state)) {
+		stat = mt76x0_mac_fetch_tx_status(dev);
+		if (!stat.valid)
+			break;
+
+		mt76x0_send_tx_status(dev, &stat, &update);
+
+		cleaned++;
+	}
+	trace_mt76x0_tx_status_cleaned(&dev->mt76, cleaned);
+
+	spin_lock_irqsave(&dev->tx_lock, flags);
+	if (cleaned)
+		queue_delayed_work(dev->stat_wq, &dev->stat_work,
+				   msecs_to_jiffies(10));
+	else if (test_and_clear_bit(MT76_MORE_STATS, &dev->mt76.state))
+		queue_delayed_work(dev->stat_wq, &dev->stat_work,
+				   msecs_to_jiffies(20));
+	else
+		clear_bit(MT76_READING_STATS, &dev->mt76.state);
+	spin_unlock_irqrestore(&dev->tx_lock, flags);
+}
+
+int mt76x0_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		    u16 queue, const struct ieee80211_tx_queue_params *params)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	u8 cw_min = 5, cw_max = 10, hw_q = q2hwq(queue);
+	u32 val;
+
+	/* TODO: should we do funny things with the parameters?
+	 *	 See what mt76x0_set_default_edca() used to do in init.c.
+	 */
+
+	if (params->cw_min)
+		cw_min = fls(params->cw_min);
+	if (params->cw_max)
+		cw_max = fls(params->cw_max);
+
+	WARN_ON(params->txop > 0xff);
+	WARN_ON(params->aifs > 0xf);
+	WARN_ON(cw_min > 0xf);
+	WARN_ON(cw_max > 0xf);
+
+	val = FIELD_PREP(MT_EDCA_CFG_AIFSN, params->aifs) |
+	      FIELD_PREP(MT_EDCA_CFG_CWMIN, cw_min) |
+	      FIELD_PREP(MT_EDCA_CFG_CWMAX, cw_max);
+	/* TODO: based on user-controlled EnableTxBurst var vendor drv sets
+	 *	 a really long txop on AC0 (see connect.c:2009) but only on
+	 *	 connect? When not connected should be 0.
+	 */
+	if (!hw_q)
+		val |= 0x60;
+	else
+		val |= FIELD_PREP(MT_EDCA_CFG_TXOP, params->txop);
+	mt76_wr(dev, MT_EDCA_CFG_AC(hw_q), val);
+
+	val = mt76_rr(dev, MT_WMM_TXOP(hw_q));
+	val &= ~(MT_WMM_TXOP_MASK << MT_WMM_TXOP_SHIFT(hw_q));
+	val |= params->txop << MT_WMM_TXOP_SHIFT(hw_q);
+	mt76_wr(dev, MT_WMM_TXOP(hw_q), val);
+
+	val = mt76_rr(dev, MT_WMM_AIFSN);
+	val &= ~(MT_WMM_AIFSN_MASK << MT_WMM_AIFSN_SHIFT(hw_q));
+	val |= params->aifs << MT_WMM_AIFSN_SHIFT(hw_q);
+	mt76_wr(dev, MT_WMM_AIFSN, val);
+
+	val = mt76_rr(dev, MT_WMM_CWMIN);
+	val &= ~(MT_WMM_CWMIN_MASK << MT_WMM_CWMIN_SHIFT(hw_q));
+	val |= cw_min << MT_WMM_CWMIN_SHIFT(hw_q);
+	mt76_wr(dev, MT_WMM_CWMIN, val);
+
+	val = mt76_rr(dev, MT_WMM_CWMAX);
+	val &= ~(MT_WMM_CWMAX_MASK << MT_WMM_CWMAX_SHIFT(hw_q));
+	val |= cw_max << MT_WMM_CWMAX_SHIFT(hw_q);
+	mt76_wr(dev, MT_WMM_CWMAX, val);
+
+	return 0;
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
new file mode 100644
index 000000000000..54ae1f113be2
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -0,0 +1,381 @@
+/*
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/usb.h>
+
+#include "mt76x0.h"
+#include "usb.h"
+#include "trace.h"
+
+static struct usb_device_id mt76x0_device_table[] = {
+	{ USB_DEVICE(0x148F, 0x7610) },	/* MT7610U */
+	{ USB_DEVICE(0x13B1, 0x003E) },	/* Linksys AE6000 */
+	{ USB_DEVICE(0x0E8D, 0x7610) },	/* Sabrent NTWLAC */
+	{ USB_DEVICE(0x7392, 0xa711) },	/* Edimax 7711mac */
+	{ USB_DEVICE(0x7392, 0xb711) },	/* Edimax / Elecom  */
+	{ USB_DEVICE(0x148f, 0x761a) },	/* TP-Link TL-WDN5200 */
+	{ USB_DEVICE(0x148f, 0x760a) },	/* TP-Link unknown */
+	{ USB_DEVICE(0x0b05, 0x17d1) },	/* Asus USB-AC51 */
+	{ USB_DEVICE(0x0b05, 0x17db) },	/* Asus USB-AC50 */
+	{ USB_DEVICE(0x0df6, 0x0075) },	/* Sitecom WLA-3100 */
+	{ USB_DEVICE(0x2019, 0xab31) },	/* Planex GW-450D */
+	{ USB_DEVICE(0x2001, 0x3d02) },	/* D-LINK DWA-171 rev B1 */
+	{ USB_DEVICE(0x0586, 0x3425) },	/* Zyxel NWD6505 */
+	{ USB_DEVICE(0x07b8, 0x7610) },	/* AboCom AU7212 */
+	{ USB_DEVICE(0x04bb, 0x0951) },	/* I-O DATA WN-AC433UK */
+	{ USB_DEVICE(0x057c, 0x8502) },	/* AVM FRITZ!WLAN USB Stick AC 430 */
+	{ USB_DEVICE(0x293c, 0x5702) },	/* Comcast Xfinity KXW02AAA  */
+	{ USB_DEVICE(0x20f4, 0x806b) },	/* TRENDnet TEW-806UBH  */
+	{ USB_DEVICE(0x7392, 0xc711) }, /* Devolo Wifi ac Stick */
+	{ USB_DEVICE(0x0df6, 0x0079) }, /* Sitecom Europe B.V. ac  Stick */
+	{ USB_DEVICE(0x2357, 0x0105) }, /* TP-LINK Archer T1U */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x0E8D, 0x7630, 0xff, 0x2, 0xff)}, /* MT7630U */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x0E8D, 0x7650, 0xff, 0x2, 0xff)}, /* MT7650U */
+	{ 0, }
+};
+
+bool mt76x0_usb_alloc_buf(struct mt76x0_dev *dev, size_t len,
+			   struct mt76x0_dma_buf *buf)
+{
+	struct usb_device *usb_dev = mt76x0_to_usb_dev(dev);
+
+	buf->len = len;
+	buf->urb = usb_alloc_urb(0, GFP_KERNEL);
+	buf->buf = usb_alloc_coherent(usb_dev, buf->len, GFP_KERNEL, &buf->dma);
+
+	return !buf->urb || !buf->buf;
+}
+
+void mt76x0_usb_free_buf(struct mt76x0_dev *dev, struct mt76x0_dma_buf *buf)
+{
+	struct usb_device *usb_dev = mt76x0_to_usb_dev(dev);
+
+	usb_free_coherent(usb_dev, buf->len, buf->buf, buf->dma);
+	usb_free_urb(buf->urb);
+}
+
+int mt76x0_usb_submit_buf(struct mt76x0_dev *dev, int dir, int ep_idx,
+			   struct mt76x0_dma_buf *buf, gfp_t gfp,
+			   usb_complete_t complete_fn, void *context)
+{
+	struct usb_device *usb_dev = mt76x0_to_usb_dev(dev);
+	unsigned pipe;
+	int ret;
+
+	if (dir == USB_DIR_IN)
+		pipe = usb_rcvbulkpipe(usb_dev, dev->in_ep[ep_idx]);
+	else
+		pipe = usb_sndbulkpipe(usb_dev, dev->out_ep[ep_idx]);
+
+	usb_fill_bulk_urb(buf->urb, usb_dev, pipe, buf->buf, buf->len,
+			  complete_fn, context);
+	buf->urb->transfer_dma = buf->dma;
+	buf->urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
+
+	trace_mt76x0_submit_urb(&dev->mt76, buf->urb);
+	ret = usb_submit_urb(buf->urb, gfp);
+	if (ret)
+		dev_err(dev->mt76.dev, "Error: submit URB dir:%d ep:%d failed:%d\n",
+			dir, ep_idx, ret);
+	return ret;
+}
+
+void mt76x0_complete_urb(struct urb *urb)
+{
+	struct completion *cmpl = urb->context;
+
+	complete(cmpl);
+}
+
+int mt76x0_vendor_request(struct mt76x0_dev *dev, const u8 req,
+			   const u8 direction, const u16 val, const u16 offset,
+			   void *buf, const size_t buflen)
+{
+	int i, ret;
+	struct usb_device *usb_dev = mt76x0_to_usb_dev(dev);
+	const u8 req_type = direction | USB_TYPE_VENDOR | USB_RECIP_DEVICE;
+	const unsigned int pipe = (direction == USB_DIR_IN) ?
+		usb_rcvctrlpipe(usb_dev, 0) : usb_sndctrlpipe(usb_dev, 0);
+
+	for (i = 0; i < MT_VEND_REQ_MAX_RETRY; i++) {
+		ret = usb_control_msg(usb_dev, pipe, req, req_type,
+				      val, offset, buf, buflen,
+				      MT_VEND_REQ_TOUT_MS);
+		trace_mt76x0_vend_req(&dev->mt76, pipe, req, req_type, val, offset,
+				  buf, buflen, ret);
+
+		if (ret == -ENODEV)
+			set_bit(MT76_REMOVED, &dev->mt76.state);
+		if (ret >= 0 || ret == -ENODEV)
+			return ret;
+
+		msleep(5);
+	}
+
+	dev_err(dev->mt76.dev, "Vendor request req:%02x off:%04x failed:%d\n",
+		req, offset, ret);
+
+	return ret;
+}
+
+void mt76x0_vendor_reset(struct mt76x0_dev *dev)
+{
+	mt76x0_vendor_request(dev, MT_VEND_DEV_MODE, USB_DIR_OUT,
+			      MT_VEND_DEV_MODE_RESET, 0, NULL, 0);
+}
+
+static u32 mt76x0_rr(struct mt76_dev *dev, u32 offset)
+{
+	struct mt76x0_dev *mdev = (struct mt76x0_dev *) dev;
+	int ret;
+	u32 val = ~0;
+
+	WARN_ONCE(offset > USHRT_MAX, "read high off:%08x", offset);
+
+	mutex_lock(&mdev->usb_ctrl_mtx);
+
+	ret = mt76x0_vendor_request((struct mt76x0_dev *)dev, MT_VEND_MULTI_READ, USB_DIR_IN,
+				    0, offset, mdev->data, MT_VEND_BUF);
+	if (ret == MT_VEND_BUF)
+		val = get_unaligned_le32(mdev->data);
+	else if (ret > 0)
+		dev_err(dev->dev, "Error: wrong size read:%d off:%08x\n",
+			ret, offset);
+
+	mutex_unlock(&mdev->usb_ctrl_mtx);
+
+	trace_mt76x0_reg_read(dev, offset, val);
+	return val;
+}
+
+int mt76x0_vendor_single_wr(struct mt76x0_dev *dev, const u8 req,
+			     const u16 offset, const u32 val)
+{
+	struct mt76x0_dev *mdev = dev;
+	int ret;
+
+	mutex_lock(&mdev->usb_ctrl_mtx);
+
+	ret = mt76x0_vendor_request(dev, req, USB_DIR_OUT,
+				    val & 0xffff, offset, NULL, 0);
+	if (!ret)
+		ret = mt76x0_vendor_request(dev, req, USB_DIR_OUT,
+					    val >> 16, offset + 2, NULL, 0);
+
+	mutex_unlock(&mdev->usb_ctrl_mtx);
+
+	return ret;
+}
+
+static void mt76x0_wr(struct mt76_dev *dev, u32 offset, u32 val)
+{
+	struct mt76x0_dev *mdev = (struct mt76x0_dev *) dev;
+	int ret;
+
+	WARN_ONCE(offset > USHRT_MAX, "write high off:%08x", offset);
+
+	mutex_lock(&mdev->usb_ctrl_mtx);
+
+	put_unaligned_le32(val, mdev->data);
+	ret = mt76x0_vendor_request(mdev, MT_VEND_MULTI_WRITE, USB_DIR_OUT,
+				    0, offset, mdev->data, MT_VEND_BUF);
+	trace_mt76x0_reg_write(dev, offset, val);
+
+	mutex_unlock(&mdev->usb_ctrl_mtx);
+}
+
+static u32 mt76x0_rmw(struct mt76_dev *dev, u32 offset, u32 mask, u32 val)
+{
+	val |= mt76x0_rr(dev, offset) & ~mask;
+	mt76x0_wr(dev, offset, val);
+	return val;
+}
+
+static void mt76x0_wr_copy(struct mt76_dev *dev, u32 offset,
+			   const void *data, int len)
+{
+	WARN_ONCE(offset & 3, "unaligned write copy off:%08x", offset);
+	WARN_ONCE(len & 3, "short write copy off:%08x", offset);
+
+	mt76x0_burst_write_regs((struct mt76x0_dev *) dev, offset, data, len / 4);
+}
+
+void mt76x0_addr_wr(struct mt76x0_dev *dev, const u32 offset, const u8 *addr)
+{
+	mt76_wr(dev, offset, get_unaligned_le32(addr));
+	mt76_wr(dev, offset + 4, addr[4] | addr[5] << 8);
+}
+
+static int mt76x0_assign_pipes(struct usb_interface *usb_intf,
+				struct mt76x0_dev *dev)
+{
+	struct usb_endpoint_descriptor *ep_desc;
+	struct usb_host_interface *intf_desc = usb_intf->cur_altsetting;
+	unsigned i, ep_i = 0, ep_o = 0;
+
+	BUILD_BUG_ON(sizeof(dev->in_ep) < __MT_EP_IN_MAX);
+	BUILD_BUG_ON(sizeof(dev->out_ep) < __MT_EP_OUT_MAX);
+
+	for (i = 0; i < intf_desc->desc.bNumEndpoints; i++) {
+		ep_desc = &intf_desc->endpoint[i].desc;
+
+		if (usb_endpoint_is_bulk_in(ep_desc) &&
+		    ep_i++ < __MT_EP_IN_MAX) {
+			dev->in_ep[ep_i - 1] = usb_endpoint_num(ep_desc);
+			dev->in_max_packet = usb_endpoint_maxp(ep_desc);
+			/* Note: this is ignored by usb sub-system but vendor
+			 *	 code does it. We can drop this at some point.
+			 */
+			dev->in_ep[ep_i - 1] |= USB_DIR_IN;
+		} else if (usb_endpoint_is_bulk_out(ep_desc) &&
+			   ep_o++ < __MT_EP_OUT_MAX) {
+			dev->out_ep[ep_o - 1] = usb_endpoint_num(ep_desc);
+			dev->out_max_packet = usb_endpoint_maxp(ep_desc);
+		}
+	}
+
+	if (ep_i != __MT_EP_IN_MAX || ep_o != __MT_EP_OUT_MAX) {
+		dev_err(dev->mt76.dev, "Error: wrong pipe number in:%d out:%d\n",
+			ep_i, ep_o);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int mt76x0_probe(struct usb_interface *usb_intf,
+			 const struct usb_device_id *id)
+{
+	struct usb_device *usb_dev = interface_to_usbdev(usb_intf);
+	struct mt76x0_dev *dev;
+	u32 asic_rev, mac_rev;
+	int ret;
+	static const struct mt76_bus_ops usb_ops = {
+		.rr = mt76x0_rr,
+		.wr = mt76x0_wr,
+		.rmw = mt76x0_rmw,
+		.copy = mt76x0_wr_copy,
+	};
+
+	dev = mt76x0_alloc_device(&usb_intf->dev);
+	if (!dev)
+		return -ENOMEM;
+
+	usb_dev = usb_get_dev(usb_dev);
+	usb_reset_device(usb_dev);
+
+	usb_set_intfdata(usb_intf, dev);
+
+	dev->mt76.bus = &usb_ops;
+
+	ret = mt76x0_assign_pipes(usb_intf, dev);
+	if (ret)
+		goto err;
+
+	/* Disable the HW, otherwise MCU fail to initalize on hot reboot */
+	mt76x0_chip_onoff(dev, false, false);
+
+	ret = mt76x0_wait_asic_ready(dev);
+	if (ret)
+		goto err;
+
+	asic_rev = mt76_rr(dev, MT_ASIC_VERSION);
+	mac_rev = mt76_rr(dev, MT_MAC_CSR0);
+	dev_info(dev->mt76.dev, "ASIC revision: %08x MAC revision: %08x\n",
+		 asic_rev, mac_rev);
+
+	/* Note: vendor driver skips this check for MT76X0U */
+	if (!(mt76_rr(dev, MT_EFUSE_CTRL) & MT_EFUSE_CTRL_SEL))
+		dev_warn(dev->mt76.dev, "Warning: eFUSE not present\n");
+
+	ret = mt76x0_init_hardware(dev);
+	if (ret)
+		goto err;
+
+	ret = mt76x0_register_device(dev);
+	if (ret)
+		goto err_hw;
+
+	set_bit(MT76_STATE_INITIALIZED, &dev->mt76.state);
+
+	return 0;
+err_hw:
+	mt76x0_cleanup(dev);
+err:
+	usb_set_intfdata(usb_intf, NULL);
+	usb_put_dev(interface_to_usbdev(usb_intf));
+
+	destroy_workqueue(dev->stat_wq);
+	ieee80211_free_hw(dev->mt76.hw);
+	return ret;
+}
+
+static void mt76x0_disconnect(struct usb_interface *usb_intf)
+{
+	struct mt76x0_dev *dev = usb_get_intfdata(usb_intf);
+	bool initalized = test_bit(MT76_STATE_INITIALIZED, &dev->mt76.state);
+
+	if (!initalized)
+		return;
+
+	ieee80211_unregister_hw(dev->mt76.hw);
+	mt76x0_cleanup(dev);
+
+	usb_set_intfdata(usb_intf, NULL);
+	usb_put_dev(interface_to_usbdev(usb_intf));
+
+	destroy_workqueue(dev->stat_wq);
+	ieee80211_free_hw(dev->mt76.hw);
+}
+
+static int mt76x0_suspend(struct usb_interface *usb_intf, pm_message_t state)
+{
+	struct mt76x0_dev *dev = usb_get_intfdata(usb_intf);
+
+	mt76x0_cleanup(dev);
+
+	return 0;
+}
+
+static int mt76x0_resume(struct usb_interface *usb_intf)
+{
+	struct mt76x0_dev *dev = usb_get_intfdata(usb_intf);
+	int ret;
+
+	ret = mt76x0_init_hardware(dev);
+	if (ret)
+		return ret;
+
+	set_bit(MT76_STATE_INITIALIZED, &dev->mt76.state);
+
+	return 0;
+}
+
+MODULE_DEVICE_TABLE(usb, mt76x0_device_table);
+MODULE_FIRMWARE(MT7610_FIRMWARE);
+MODULE_LICENSE("GPL");
+
+static struct usb_driver mt76x0_driver = {
+	.name		= KBUILD_MODNAME,
+	.id_table	= mt76x0_device_table,
+	.probe		= mt76x0_probe,
+	.disconnect	= mt76x0_disconnect,
+	.suspend	= mt76x0_suspend,
+	.resume		= mt76x0_resume,
+	.reset_resume	= mt76x0_resume,
+	.soft_unbind	= 1,
+	.disable_hub_initiated_lpm = 1,
+};
+module_usb_driver(mt76x0_driver);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.h b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.h
new file mode 100644
index 000000000000..492e431390a8
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.h
@@ -0,0 +1,61 @@
+/*
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __MT76X0U_USB_H
+#define __MT76X0U_USB_H
+
+#include "mt76x0.h"
+
+#define MT7610_FIRMWARE	"mediatek/mt7610u.bin"
+
+#define MT_VEND_REQ_MAX_RETRY	10
+#define MT_VEND_REQ_TOUT_MS	300
+
+#define MT_VEND_DEV_MODE_RESET	1
+
+#define MT_VEND_BUF		sizeof(__le32)
+
+static inline struct usb_device *mt76x0_to_usb_dev(struct mt76x0_dev *mt76x0)
+{
+	return interface_to_usbdev(to_usb_interface(mt76x0->mt76.dev));
+}
+
+static inline struct usb_device *mt76_to_usb_dev(struct mt76_dev *mt76)
+{
+	return interface_to_usbdev(to_usb_interface(mt76->dev));
+}
+
+static inline bool mt76x0_urb_has_error(struct urb *urb)
+{
+	return urb->status &&
+		urb->status != -ENOENT &&
+		urb->status != -ECONNRESET &&
+		urb->status != -ESHUTDOWN;
+}
+
+bool mt76x0_usb_alloc_buf(struct mt76x0_dev *dev, size_t len,
+			   struct mt76x0_dma_buf *buf);
+void mt76x0_usb_free_buf(struct mt76x0_dev *dev, struct mt76x0_dma_buf *buf);
+int mt76x0_usb_submit_buf(struct mt76x0_dev *dev, int dir, int ep_idx,
+			   struct mt76x0_dma_buf *buf, gfp_t gfp,
+			   usb_complete_t complete_fn, void *context);
+void mt76x0_complete_urb(struct urb *urb);
+
+int mt76x0_vendor_request(struct mt76x0_dev *dev, const u8 req,
+			   const u8 direction, const u16 val, const u16 offset,
+			   void *buf, const size_t buflen);
+void mt76x0_vendor_reset(struct mt76x0_dev *dev);
+int mt76x0_vendor_single_wr(struct mt76x0_dev *dev, const u8 req,
+			     const u16 offset, const u32 val);
+
+#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/util.c b/drivers/net/wireless/mediatek/mt76/mt76x0/util.c
new file mode 100644
index 000000000000..7856dd760419
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/util.c
@@ -0,0 +1,42 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "mt76x0.h"
+
+void mt76x0_remove_hdr_pad(struct sk_buff *skb)
+{
+	int len = ieee80211_get_hdrlen_from_skb(skb);
+
+	memmove(skb->data + 2, skb->data, len);
+	skb_pull(skb, 2);
+}
+
+int mt76x0_insert_hdr_pad(struct sk_buff *skb)
+{
+	int len = ieee80211_get_hdrlen_from_skb(skb);
+	int ret;
+
+	if (len % 4 == 0)
+		return 0;
+
+	ret = skb_cow(skb, 2);
+	if (ret)
+		return ret;
+
+	skb_push(skb, 2);
+	memmove(skb->data, skb->data + 2, len);
+
+	skb->data[len] = 0;
+	skb->data[len + 1] = 0;
+	return 0;
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2.h
index dc12bbdbb2ee..dca3209bf5f1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2.h
@@ -27,11 +27,15 @@
 #include <linux/mutex.h>
 #include <linux/bitops.h>
 #include <linux/kfifo.h>
+#include <linux/average.h>
 
 #define MT7662_FIRMWARE		"mt7662.bin"
 #define MT7662_ROM_PATCH	"mt7662_rom_patch.bin"
 #define MT7662_EEPROM_SIZE	512
 
+#define MT7662U_FIRMWARE	"mediatek/mt7662u.bin"
+#define MT7662U_ROM_PATCH	"mediatek/mt7662u_rom_patch.bin"
+
 #define MT76x2_RX_RING_SIZE	256
 #define MT_RX_HEADROOM		32
 
@@ -47,11 +51,14 @@
 #include "mt76x2_mac.h"
 #include "mt76x2_dfs.h"
 
+DECLARE_EWMA(signal, 10, 8)
+
 struct mt76x2_mcu {
 	struct mutex mutex;
 
 	wait_queue_head_t wait;
 	struct sk_buff_head res_q;
+	struct mt76u_buf res_u;
 
 	u32 msg_seq;
 };
@@ -69,9 +76,8 @@ struct mt76x2_calibration {
 	u8 agc_gain_init[MT_MAX_CHAINS];
 	u8 agc_gain_cur[MT_MAX_CHAINS];
 
-	int avg_rssi[MT_MAX_CHAINS];
-	int avg_rssi_all;
-
+	u16 false_cca;
+	s8 avg_rssi_all;
 	s8 agc_gain_adjust;
 	s8 low_gain;
 
@@ -120,10 +126,13 @@ struct mt76x2_dev {
 	u8 beacon_mask;
 	u8 beacon_data_mask;
 
-	u32 rxfilter;
+	u8 tbtt_count;
+	u16 beacon_int;
 
 	u16 chainmask;
 
+	u32 rxfilter;
+
 	struct mt76x2_calibration cal;
 
 	s8 target_power;
@@ -149,8 +158,28 @@ struct mt76x2_sta {
 	struct mt76x2_vif *vif;
 	struct mt76x2_tx_status status;
 	int n_frames;
+
+	struct ewma_signal rssi;
+	int inactive_count;
 };
 
+static inline bool mt76x2_wait_for_mac(struct mt76x2_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < 500; i++) {
+		switch (mt76_rr(dev, MT_MAC_CSR0)) {
+		case 0:
+		case ~0:
+			break;
+		default:
+			return true;
+		}
+		usleep_range(5000, 10000);
+	}
+	return false;
+}
+
 static inline bool is_mt7612(struct mt76x2_dev *dev)
 {
 	return mt76_chip(&dev->mt76) == 0x7612;
@@ -158,6 +187,14 @@ static inline bool is_mt7612(struct mt76x2_dev *dev)
 
 void mt76x2_set_irq_mask(struct mt76x2_dev *dev, u32 clear, u32 set);
 
+static inline bool mt76x2_channel_silent(struct mt76x2_dev *dev)
+{
+	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
+
+	return ((chan->flags & IEEE80211_CHAN_RADAR) &&
+		chan->dfs_state != NL80211_DFS_AVAILABLE);
+}
+
 static inline void mt76x2_irq_enable(struct mt76x2_dev *dev, u32 mask)
 {
 	mt76x2_set_irq_mask(dev, 0, mask);
@@ -168,11 +205,29 @@ static inline void mt76x2_irq_disable(struct mt76x2_dev *dev, u32 mask)
 	mt76x2_set_irq_mask(dev, mask, 0);
 }
 
+static inline bool mt76x2_wait_for_bbp(struct mt76x2_dev *dev)
+{
+	return mt76_poll_msec(dev, MT_MAC_STATUS,
+			      MT_MAC_STATUS_TX | MT_MAC_STATUS_RX,
+			      0, 100);
+}
+
+static inline bool wait_for_wpdma(struct mt76x2_dev *dev)
+{
+	return mt76_poll(dev, MT_WPDMA_GLO_CFG,
+			 MT_WPDMA_GLO_CFG_TX_DMA_BUSY |
+			 MT_WPDMA_GLO_CFG_RX_DMA_BUSY,
+			 0, 1000);
+}
+
 extern const struct ieee80211_ops mt76x2_ops;
 
+extern struct ieee80211_rate mt76x2_rates[12];
+
 struct mt76x2_dev *mt76x2_alloc_device(struct device *pdev);
 int mt76x2_register_device(struct mt76x2_dev *dev);
 void mt76x2_init_debugfs(struct mt76x2_dev *dev);
+void mt76x2_init_device(struct mt76x2_dev *dev);
 
 irqreturn_t mt76x2_irq_handler(int irq, void *dev_instance);
 void mt76x2_phy_power_on(struct mt76x2_dev *dev);
@@ -186,7 +241,7 @@ void mt76x2_phy_set_antenna(struct mt76x2_dev *dev);
 int mt76x2_phy_start(struct mt76x2_dev *dev);
 int mt76x2_phy_set_channel(struct mt76x2_dev *dev,
 			 struct cfg80211_chan_def *chandef);
-int mt76x2_phy_get_rssi(struct mt76x2_dev *dev, s8 rssi, int chain);
+int mt76x2_mac_get_rssi(struct mt76x2_dev *dev, s8 rssi, int chain);
 void mt76x2_phy_calibrate(struct work_struct *work);
 void mt76x2_phy_set_txpower(struct mt76x2_dev *dev);
 
@@ -214,6 +269,7 @@ int mt76x2_tx_prepare_skb(struct mt76_dev *mdev, void *txwi,
 			  u32 *tx_info);
 void mt76x2_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue *q,
 			    struct mt76_queue_entry *e, bool flush);
+void mt76x2_mac_set_tx_protection(struct mt76x2_dev *dev, u32 val);
 
 void mt76x2_pre_tbtt_tasklet(unsigned long arg);
 
@@ -230,4 +286,45 @@ s8 mt76x2_tx_get_max_txpwr_adj(struct mt76x2_dev *dev,
 s8 mt76x2_tx_get_txpwr_adj(struct mt76x2_dev *dev, s8 txpwr, s8 max_txpwr_adj);
 void mt76x2_tx_set_txpwr_auto(struct mt76x2_dev *dev, s8 txpwr);
 
+int mt76x2_insert_hdr_pad(struct sk_buff *skb);
+
+bool mt76x2_mac_load_tx_status(struct mt76x2_dev *dev,
+			       struct mt76x2_tx_status *stat);
+void mt76x2_send_tx_status(struct mt76x2_dev *dev,
+			   struct mt76x2_tx_status *stat, u8 *update);
+void mt76x2_reset_wlan(struct mt76x2_dev *dev, bool enable);
+void mt76x2_init_txpower(struct mt76x2_dev *dev,
+			 struct ieee80211_supported_band *sband);
+void mt76_write_mac_initvals(struct mt76x2_dev *dev);
+
+int mt76x2_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			struct ieee80211_ampdu_params *params);
+int mt76x2_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		   struct ieee80211_sta *sta);
+int mt76x2_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		      struct ieee80211_sta *sta);
+void mt76x2_remove_interface(struct ieee80211_hw *hw,
+			     struct ieee80211_vif *vif);
+int mt76x2_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
+		   struct ieee80211_vif *vif, struct ieee80211_sta *sta,
+		   struct ieee80211_key_conf *key);
+int mt76x2_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		   u16 queue, const struct ieee80211_tx_queue_params *params);
+void mt76x2_configure_filter(struct ieee80211_hw *hw,
+			     unsigned int changed_flags,
+			     unsigned int *total_flags, u64 multicast);
+void mt76x2_txq_init(struct mt76x2_dev *dev, struct ieee80211_txq *txq);
+void mt76x2_sta_rate_tbl_update(struct ieee80211_hw *hw,
+				struct ieee80211_vif *vif,
+				struct ieee80211_sta *sta);
+
+void mt76x2_phy_set_txpower_regs(struct mt76x2_dev *dev,
+				 enum nl80211_band band);
+void mt76x2_configure_tx_delay(struct mt76x2_dev *dev,
+			       enum nl80211_band band, u8 bw);
+void mt76x2_phy_set_bw(struct mt76x2_dev *dev, int width, u8 ctrl);
+void mt76x2_phy_set_band(struct mt76x2_dev *dev, int band, bool primary_upper);
+int mt76x2_phy_get_min_avg_rssi(struct mt76x2_dev *dev);
+void mt76x2_apply_gain_adj(struct mt76x2_dev *dev);
+
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_common.c b/drivers/net/wireless/mediatek/mt76/mt76x2_common.c
new file mode 100644
index 000000000000..a2338ba139b4
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_common.c
@@ -0,0 +1,350 @@
+/*
+ * Copyright (C) 2016 Felix Fietkau <nbd@nbd.name>
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76x2.h"
+
+void mt76x2_txq_init(struct mt76x2_dev *dev, struct ieee80211_txq *txq)
+{
+	struct mt76_txq *mtxq;
+
+	if (!txq)
+		return;
+
+	mtxq = (struct mt76_txq *) txq->drv_priv;
+	if (txq->sta) {
+		struct mt76x2_sta *sta;
+
+		sta = (struct mt76x2_sta *) txq->sta->drv_priv;
+		mtxq->wcid = &sta->wcid;
+	} else {
+		struct mt76x2_vif *mvif;
+
+		mvif = (struct mt76x2_vif *) txq->vif->drv_priv;
+		mtxq->wcid = &mvif->group_wcid;
+	}
+
+	mt76_txq_init(&dev->mt76, txq);
+}
+EXPORT_SYMBOL_GPL(mt76x2_txq_init);
+
+int mt76x2_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			struct ieee80211_ampdu_params *params)
+{
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	struct ieee80211_sta *sta = params->sta;
+	struct mt76x2_dev *dev = hw->priv;
+	struct mt76x2_sta *msta = (struct mt76x2_sta *) sta->drv_priv;
+	struct ieee80211_txq *txq = sta->txq[params->tid];
+	u16 tid = params->tid;
+	u16 *ssn = &params->ssn;
+	struct mt76_txq *mtxq;
+
+	if (!txq)
+		return -EINVAL;
+
+	mtxq = (struct mt76_txq *)txq->drv_priv;
+
+	switch (action) {
+	case IEEE80211_AMPDU_RX_START:
+		mt76_rx_aggr_start(&dev->mt76, &msta->wcid, tid, *ssn, params->buf_size);
+		mt76_set(dev, MT_WCID_ADDR(msta->wcid.idx) + 4, BIT(16 + tid));
+		break;
+	case IEEE80211_AMPDU_RX_STOP:
+		mt76_rx_aggr_stop(&dev->mt76, &msta->wcid, tid);
+		mt76_clear(dev, MT_WCID_ADDR(msta->wcid.idx) + 4,
+			   BIT(16 + tid));
+		break;
+	case IEEE80211_AMPDU_TX_OPERATIONAL:
+		mtxq->aggr = true;
+		mtxq->send_bar = false;
+		ieee80211_send_bar(vif, sta->addr, tid, mtxq->agg_ssn);
+		break;
+	case IEEE80211_AMPDU_TX_STOP_FLUSH:
+	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
+		mtxq->aggr = false;
+		ieee80211_send_bar(vif, sta->addr, tid, mtxq->agg_ssn);
+		break;
+	case IEEE80211_AMPDU_TX_START:
+		mtxq->agg_ssn = *ssn << 4;
+		ieee80211_start_tx_ba_cb_irqsafe(vif, sta->addr, tid);
+		break;
+	case IEEE80211_AMPDU_TX_STOP_CONT:
+		mtxq->aggr = false;
+		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
+		break;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt76x2_ampdu_action);
+
+int mt76x2_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		   struct ieee80211_sta *sta)
+{
+	struct mt76x2_dev *dev = hw->priv;
+	struct mt76x2_sta *msta = (struct mt76x2_sta *) sta->drv_priv;
+	struct mt76x2_vif *mvif = (struct mt76x2_vif *) vif->drv_priv;
+	int ret = 0;
+	int idx = 0;
+	int i;
+
+	mutex_lock(&dev->mutex);
+
+	idx = mt76_wcid_alloc(dev->wcid_mask, ARRAY_SIZE(dev->wcid));
+	if (idx < 0) {
+		ret = -ENOSPC;
+		goto out;
+	}
+
+	msta->vif = mvif;
+	msta->wcid.sta = 1;
+	msta->wcid.idx = idx;
+	msta->wcid.hw_key_idx = -1;
+	mt76x2_mac_wcid_setup(dev, idx, mvif->idx, sta->addr);
+	mt76x2_mac_wcid_set_drop(dev, idx, false);
+	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
+		mt76x2_txq_init(dev, sta->txq[i]);
+
+	if (vif->type == NL80211_IFTYPE_AP)
+		set_bit(MT_WCID_FLAG_CHECK_PS, &msta->wcid.flags);
+
+	ewma_signal_init(&msta->rssi);
+
+	rcu_assign_pointer(dev->wcid[idx], &msta->wcid);
+
+out:
+	mutex_unlock(&dev->mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mt76x2_sta_add);
+
+int mt76x2_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		      struct ieee80211_sta *sta)
+{
+	struct mt76x2_dev *dev = hw->priv;
+	struct mt76x2_sta *msta = (struct mt76x2_sta *) sta->drv_priv;
+	int idx = msta->wcid.idx;
+	int i;
+
+	mutex_lock(&dev->mutex);
+	rcu_assign_pointer(dev->wcid[idx], NULL);
+	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
+		mt76_txq_remove(&dev->mt76, sta->txq[i]);
+	mt76x2_mac_wcid_set_drop(dev, idx, true);
+	mt76_wcid_free(dev->wcid_mask, idx);
+	mt76x2_mac_wcid_setup(dev, idx, 0, NULL);
+	mutex_unlock(&dev->mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt76x2_sta_remove);
+
+void mt76x2_remove_interface(struct ieee80211_hw *hw,
+			     struct ieee80211_vif *vif)
+{
+	struct mt76x2_dev *dev = hw->priv;
+
+	mt76_txq_remove(&dev->mt76, vif->txq);
+}
+EXPORT_SYMBOL_GPL(mt76x2_remove_interface);
+
+int mt76x2_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
+		   struct ieee80211_vif *vif, struct ieee80211_sta *sta,
+		   struct ieee80211_key_conf *key)
+{
+	struct mt76x2_dev *dev = hw->priv;
+	struct mt76x2_vif *mvif = (struct mt76x2_vif *) vif->drv_priv;
+	struct mt76x2_sta *msta;
+	struct mt76_wcid *wcid;
+	int idx = key->keyidx;
+	int ret;
+
+	/* fall back to sw encryption for unsupported ciphers */
+	switch (key->cipher) {
+	case WLAN_CIPHER_SUITE_WEP40:
+	case WLAN_CIPHER_SUITE_WEP104:
+	case WLAN_CIPHER_SUITE_TKIP:
+	case WLAN_CIPHER_SUITE_CCMP:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	/*
+	 * The hardware does not support per-STA RX GTK, fall back
+	 * to software mode for these.
+	 */
+	if ((vif->type == NL80211_IFTYPE_ADHOC ||
+	     vif->type == NL80211_IFTYPE_MESH_POINT) &&
+	    (key->cipher == WLAN_CIPHER_SUITE_TKIP ||
+	     key->cipher == WLAN_CIPHER_SUITE_CCMP) &&
+	    !(key->flags & IEEE80211_KEY_FLAG_PAIRWISE))
+		return -EOPNOTSUPP;
+
+	msta = sta ? (struct mt76x2_sta *) sta->drv_priv : NULL;
+	wcid = msta ? &msta->wcid : &mvif->group_wcid;
+
+	if (cmd == SET_KEY) {
+		key->hw_key_idx = wcid->idx;
+		wcid->hw_key_idx = idx;
+		if (key->flags & IEEE80211_KEY_FLAG_RX_MGMT) {
+			key->flags |= IEEE80211_KEY_FLAG_SW_MGMT_TX;
+			wcid->sw_iv = true;
+		}
+	} else {
+		if (idx == wcid->hw_key_idx) {
+			wcid->hw_key_idx = -1;
+			wcid->sw_iv = true;
+		}
+
+		key = NULL;
+	}
+	mt76_wcid_key_setup(&dev->mt76, wcid, key);
+
+	if (!msta) {
+		if (key || wcid->hw_key_idx == idx) {
+			ret = mt76x2_mac_wcid_set_key(dev, wcid->idx, key);
+			if (ret)
+				return ret;
+		}
+
+		return mt76x2_mac_shared_key_setup(dev, mvif->idx, idx, key);
+	}
+
+	return mt76x2_mac_wcid_set_key(dev, msta->wcid.idx, key);
+}
+EXPORT_SYMBOL_GPL(mt76x2_set_key);
+
+int mt76x2_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		   u16 queue, const struct ieee80211_tx_queue_params *params)
+{
+	struct mt76x2_dev *dev = hw->priv;
+	u8 cw_min = 5, cw_max = 10, qid;
+	u32 val;
+
+	qid = dev->mt76.q_tx[queue].hw_idx;
+
+	if (params->cw_min)
+		cw_min = fls(params->cw_min);
+	if (params->cw_max)
+		cw_max = fls(params->cw_max);
+
+	val = FIELD_PREP(MT_EDCA_CFG_TXOP, params->txop) |
+	      FIELD_PREP(MT_EDCA_CFG_AIFSN, params->aifs) |
+	      FIELD_PREP(MT_EDCA_CFG_CWMIN, cw_min) |
+	      FIELD_PREP(MT_EDCA_CFG_CWMAX, cw_max);
+	mt76_wr(dev, MT_EDCA_CFG_AC(qid), val);
+
+	val = mt76_rr(dev, MT_WMM_TXOP(qid));
+	val &= ~(MT_WMM_TXOP_MASK << MT_WMM_TXOP_SHIFT(qid));
+	val |= params->txop << MT_WMM_TXOP_SHIFT(qid);
+	mt76_wr(dev, MT_WMM_TXOP(qid), val);
+
+	val = mt76_rr(dev, MT_WMM_AIFSN);
+	val &= ~(MT_WMM_AIFSN_MASK << MT_WMM_AIFSN_SHIFT(qid));
+	val |= params->aifs << MT_WMM_AIFSN_SHIFT(qid);
+	mt76_wr(dev, MT_WMM_AIFSN, val);
+
+	val = mt76_rr(dev, MT_WMM_CWMIN);
+	val &= ~(MT_WMM_CWMIN_MASK << MT_WMM_CWMIN_SHIFT(qid));
+	val |= cw_min << MT_WMM_CWMIN_SHIFT(qid);
+	mt76_wr(dev, MT_WMM_CWMIN, val);
+
+	val = mt76_rr(dev, MT_WMM_CWMAX);
+	val &= ~(MT_WMM_CWMAX_MASK << MT_WMM_CWMAX_SHIFT(qid));
+	val |= cw_max << MT_WMM_CWMAX_SHIFT(qid);
+	mt76_wr(dev, MT_WMM_CWMAX, val);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt76x2_conf_tx);
+
+void mt76x2_configure_filter(struct ieee80211_hw *hw,
+			     unsigned int changed_flags,
+			     unsigned int *total_flags, u64 multicast)
+{
+	struct mt76x2_dev *dev = hw->priv;
+	u32 flags = 0;
+
+#define MT76_FILTER(_flag, _hw) do { \
+		flags |= *total_flags & FIF_##_flag;			\
+		dev->rxfilter &= ~(_hw);				\
+		dev->rxfilter |= !(flags & FIF_##_flag) * (_hw);	\
+	} while (0)
+
+	mutex_lock(&dev->mutex);
+
+	dev->rxfilter &= ~MT_RX_FILTR_CFG_OTHER_BSS;
+
+	MT76_FILTER(FCSFAIL, MT_RX_FILTR_CFG_CRC_ERR);
+	MT76_FILTER(PLCPFAIL, MT_RX_FILTR_CFG_PHY_ERR);
+	MT76_FILTER(CONTROL, MT_RX_FILTR_CFG_ACK |
+			     MT_RX_FILTR_CFG_CTS |
+			     MT_RX_FILTR_CFG_CFEND |
+			     MT_RX_FILTR_CFG_CFACK |
+			     MT_RX_FILTR_CFG_BA |
+			     MT_RX_FILTR_CFG_CTRL_RSV);
+	MT76_FILTER(PSPOLL, MT_RX_FILTR_CFG_PSPOLL);
+
+	*total_flags = flags;
+	mt76_wr(dev, MT_RX_FILTR_CFG, dev->rxfilter);
+
+	mutex_unlock(&dev->mutex);
+}
+EXPORT_SYMBOL_GPL(mt76x2_configure_filter);
+
+void mt76x2_sta_rate_tbl_update(struct ieee80211_hw *hw,
+				struct ieee80211_vif *vif,
+				struct ieee80211_sta *sta)
+{
+	struct mt76x2_dev *dev = hw->priv;
+	struct mt76x2_sta *msta = (struct mt76x2_sta *) sta->drv_priv;
+	struct ieee80211_sta_rates *rates = rcu_dereference(sta->rates);
+	struct ieee80211_tx_rate rate = {};
+
+	if (!rates)
+		return;
+
+	rate.idx = rates->rate[0].idx;
+	rate.flags = rates->rate[0].flags;
+	mt76x2_mac_wcid_set_rate(dev, &msta->wcid, &rate);
+	msta->wcid.max_txpwr_adj = mt76x2_tx_get_max_txpwr_adj(dev, &rate);
+}
+EXPORT_SYMBOL_GPL(mt76x2_sta_rate_tbl_update);
+
+void mt76x2_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
+			 struct sk_buff *skb)
+{
+	struct mt76x2_dev *dev = container_of(mdev, struct mt76x2_dev, mt76);
+	void *rxwi = skb->data;
+
+	if (q == MT_RXQ_MCU) {
+		skb_queue_tail(&dev->mcu.res_q, skb);
+		wake_up(&dev->mcu.wait);
+		return;
+	}
+
+	skb_pull(skb, sizeof(struct mt76x2_rxwi));
+	if (mt76x2_mac_process_rx(dev, skb, rxwi)) {
+		dev_kfree_skb(skb);
+		return;
+	}
+
+	mt76_rx(&dev->mt76, q, skb);
+}
+EXPORT_SYMBOL_GPL(mt76x2_queue_rx_skb);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_debugfs.c b/drivers/net/wireless/mediatek/mt76/mt76x2_debugfs.c
index 955ea3e692dd..77b5ff1be05f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_debugfs.c
@@ -91,12 +91,20 @@ mt76x2_dfs_stat_read(struct seq_file *file, void *data)
 	struct mt76x2_dev *dev = file->private;
 	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
 
+	seq_printf(file, "allocated sequences:\t%d\n",
+		   dfs_pd->seq_stats.seq_pool_len);
+	seq_printf(file, "used sequences:\t\t%d\n",
+		   dfs_pd->seq_stats.seq_len);
+	seq_puts(file, "\n");
+
 	for (i = 0; i < MT_DFS_NUM_ENGINES; i++) {
 		seq_printf(file, "engine: %d\n", i);
 		seq_printf(file, "  hw pattern detected:\t%d\n",
 			   dfs_pd->stats[i].hw_pattern);
 		seq_printf(file, "  hw pulse discarded:\t%d\n",
 			   dfs_pd->stats[i].hw_pulse_discarded);
+		seq_printf(file, "  sw pattern detected:\t%d\n",
+			   dfs_pd->stats[i].sw_pattern);
 	}
 
 	return 0;
@@ -115,6 +123,18 @@ static const struct file_operations fops_dfs_stat = {
 	.release = single_release,
 };
 
+static int read_agc(struct seq_file *file, void *data)
+{
+	struct mt76x2_dev *dev = dev_get_drvdata(file->private);
+
+	seq_printf(file, "avg_rssi: %d\n", dev->cal.avg_rssi_all);
+	seq_printf(file, "low_gain: %d\n", dev->cal.low_gain);
+	seq_printf(file, "false_cca: %d\n", dev->cal.false_cca);
+	seq_printf(file, "agc_gain_adjust: %d\n", dev->cal.agc_gain_adjust);
+
+	return 0;
+}
+
 void mt76x2_init_debugfs(struct mt76x2_dev *dev)
 {
 	struct dentry *dir;
@@ -130,4 +150,7 @@ void mt76x2_init_debugfs(struct mt76x2_dev *dev)
 	debugfs_create_file("dfs_stats", 0400, dir, dev, &fops_dfs_stat);
 	debugfs_create_devm_seqfile(dev->mt76.dev, "txpower", dir,
 				    read_txpower);
+
+	debugfs_create_devm_seqfile(dev->mt76.dev, "agc", dir, read_agc);
 }
+EXPORT_SYMBOL_GPL(mt76x2_init_debugfs);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.c b/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.c
index f936dc9a5476..374cc655c11d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.c
@@ -159,6 +159,81 @@ static void mt76x2_dfs_set_capture_mode_ctrl(struct mt76x2_dev *dev,
 	mt76_wr(dev, MT_BBP(DFS, 36), data);
 }
 
+static void mt76x2_dfs_seq_pool_put(struct mt76x2_dev *dev,
+				    struct mt76x2_dfs_sequence *seq)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+
+	list_add(&seq->head, &dfs_pd->seq_pool);
+
+	dfs_pd->seq_stats.seq_pool_len++;
+	dfs_pd->seq_stats.seq_len--;
+}
+
+static
+struct mt76x2_dfs_sequence *mt76x2_dfs_seq_pool_get(struct mt76x2_dev *dev)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x2_dfs_sequence *seq;
+
+	if (list_empty(&dfs_pd->seq_pool)) {
+		seq = devm_kzalloc(dev->mt76.dev, sizeof(*seq), GFP_ATOMIC);
+	} else {
+		seq = list_first_entry(&dfs_pd->seq_pool,
+				       struct mt76x2_dfs_sequence,
+				       head);
+		list_del(&seq->head);
+		dfs_pd->seq_stats.seq_pool_len--;
+	}
+	if (seq)
+		dfs_pd->seq_stats.seq_len++;
+
+	return seq;
+}
+
+static int mt76x2_dfs_get_multiple(int val, int frac, int margin)
+{
+	int remainder, factor;
+
+	if (!frac)
+		return 0;
+
+	if (abs(val - frac) <= margin)
+		return 1;
+
+	factor = val / frac;
+	remainder = val % frac;
+
+	if (remainder > margin) {
+		if ((frac - remainder) <= margin)
+			factor++;
+		else
+			factor = 0;
+	}
+	return factor;
+}
+
+static void mt76x2_dfs_detector_reset(struct mt76x2_dev *dev)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x2_dfs_sequence *seq, *tmp_seq;
+	int i;
+
+	/* reset hw detector */
+	mt76_wr(dev, MT_BBP(DFS, 1), 0xf);
+
+	/* reset sw detector */
+	for (i = 0; i < ARRAY_SIZE(dfs_pd->event_rb); i++) {
+		dfs_pd->event_rb[i].h_rb = 0;
+		dfs_pd->event_rb[i].t_rb = 0;
+	}
+
+	list_for_each_entry_safe(seq, tmp_seq, &dfs_pd->sequences, head) {
+		list_del_init(&seq->head);
+		mt76x2_dfs_seq_pool_put(dev, seq);
+	}
+}
+
 static bool mt76x2_dfs_check_chirp(struct mt76x2_dev *dev)
 {
 	bool ret = false;
@@ -295,6 +370,256 @@ static bool mt76x2_dfs_check_hw_pulse(struct mt76x2_dev *dev,
 	return ret;
 }
 
+static bool mt76x2_dfs_fetch_event(struct mt76x2_dev *dev,
+				   struct mt76x2_dfs_event *event)
+{
+	u32 data;
+
+	/* 1st: DFS_R37[31]: 0 (engine 0) - 1 (engine 2)
+	 * 2nd: DFS_R37[21:0]: pulse time
+	 * 3rd: DFS_R37[11:0]: pulse width
+	 * 3rd: DFS_R37[25:16]: phase
+	 * 4th: DFS_R37[12:0]: current pwr
+	 * 4th: DFS_R37[21:16]: pwr stable counter
+	 *
+	 * 1st: DFS_R37[31:0] set to 0xffffffff means no event detected
+	 */
+	data = mt76_rr(dev, MT_BBP(DFS, 37));
+	if (!MT_DFS_CHECK_EVENT(data))
+		return false;
+
+	event->engine = MT_DFS_EVENT_ENGINE(data);
+	data = mt76_rr(dev, MT_BBP(DFS, 37));
+	event->ts = MT_DFS_EVENT_TIMESTAMP(data);
+	data = mt76_rr(dev, MT_BBP(DFS, 37));
+	event->width = MT_DFS_EVENT_WIDTH(data);
+
+	return true;
+}
+
+static bool mt76x2_dfs_check_event(struct mt76x2_dev *dev,
+				   struct mt76x2_dfs_event *event)
+{
+	if (event->engine == 2) {
+		struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+		struct mt76x2_dfs_event_rb *event_buff = &dfs_pd->event_rb[1];
+		u16 last_event_idx;
+		u32 delta_ts;
+
+		last_event_idx = mt76_decr(event_buff->t_rb,
+					   MT_DFS_EVENT_BUFLEN);
+		delta_ts = event->ts - event_buff->data[last_event_idx].ts;
+		if (delta_ts < MT_DFS_EVENT_TIME_MARGIN &&
+		    event_buff->data[last_event_idx].width >= 200)
+			return false;
+	}
+	return true;
+}
+
+static void mt76x2_dfs_queue_event(struct mt76x2_dev *dev,
+				   struct mt76x2_dfs_event *event)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x2_dfs_event_rb *event_buff;
+
+	/* add radar event to ring buffer */
+	event_buff = event->engine == 2 ? &dfs_pd->event_rb[1]
+					: &dfs_pd->event_rb[0];
+	event_buff->data[event_buff->t_rb] = *event;
+	event_buff->data[event_buff->t_rb].fetch_ts = jiffies;
+
+	event_buff->t_rb = mt76_incr(event_buff->t_rb, MT_DFS_EVENT_BUFLEN);
+	if (event_buff->t_rb == event_buff->h_rb)
+		event_buff->h_rb = mt76_incr(event_buff->h_rb,
+					     MT_DFS_EVENT_BUFLEN);
+}
+
+static int mt76x2_dfs_create_sequence(struct mt76x2_dev *dev,
+				      struct mt76x2_dfs_event *event,
+				      u16 cur_len)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x2_dfs_sw_detector_params *sw_params;
+	u32 width_delta, with_sum, factor, cur_pri;
+	struct mt76x2_dfs_sequence seq, *seq_p;
+	struct mt76x2_dfs_event_rb *event_rb;
+	struct mt76x2_dfs_event *cur_event;
+	int i, j, end, pri;
+
+	event_rb = event->engine == 2 ? &dfs_pd->event_rb[1]
+				      : &dfs_pd->event_rb[0];
+
+	i = mt76_decr(event_rb->t_rb, MT_DFS_EVENT_BUFLEN);
+	end = mt76_decr(event_rb->h_rb, MT_DFS_EVENT_BUFLEN);
+
+	while (i != end) {
+		cur_event = &event_rb->data[i];
+		with_sum = event->width + cur_event->width;
+
+		sw_params = &dfs_pd->sw_dpd_params;
+		switch (dev->dfs_pd.region) {
+		case NL80211_DFS_FCC:
+		case NL80211_DFS_JP:
+			if (with_sum < 600)
+				width_delta = 8;
+			else
+				width_delta = with_sum >> 3;
+			break;
+		case NL80211_DFS_ETSI:
+			if (event->engine == 2)
+				width_delta = with_sum >> 6;
+			else if (with_sum < 620)
+				width_delta = 24;
+			else
+				width_delta = 8;
+			break;
+		case NL80211_DFS_UNSET:
+		default:
+			return -EINVAL;
+		}
+
+		pri = event->ts - cur_event->ts;
+		if (abs(event->width - cur_event->width) > width_delta ||
+		    pri < sw_params->min_pri)
+			goto next;
+
+		if (pri > sw_params->max_pri)
+			break;
+
+		seq.pri = event->ts - cur_event->ts;
+		seq.first_ts = cur_event->ts;
+		seq.last_ts = event->ts;
+		seq.engine = event->engine;
+		seq.count = 2;
+
+		j = mt76_decr(i, MT_DFS_EVENT_BUFLEN);
+		while (j != end) {
+			cur_event = &event_rb->data[j];
+			cur_pri = event->ts - cur_event->ts;
+			factor = mt76x2_dfs_get_multiple(cur_pri, seq.pri,
+						sw_params->pri_margin);
+			if (factor > 0) {
+				seq.first_ts = cur_event->ts;
+				seq.count++;
+			}
+
+			j = mt76_decr(j, MT_DFS_EVENT_BUFLEN);
+		}
+		if (seq.count <= cur_len)
+			goto next;
+
+		seq_p = mt76x2_dfs_seq_pool_get(dev);
+		if (!seq_p)
+			return -ENOMEM;
+
+		*seq_p = seq;
+		INIT_LIST_HEAD(&seq_p->head);
+		list_add(&seq_p->head, &dfs_pd->sequences);
+next:
+		i = mt76_decr(i, MT_DFS_EVENT_BUFLEN);
+	}
+	return 0;
+}
+
+static u16 mt76x2_dfs_add_event_to_sequence(struct mt76x2_dev *dev,
+					    struct mt76x2_dfs_event *event)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x2_dfs_sw_detector_params *sw_params;
+	struct mt76x2_dfs_sequence *seq, *tmp_seq;
+	u16 max_seq_len = 0;
+	u32 factor, pri;
+
+	sw_params = &dfs_pd->sw_dpd_params;
+	list_for_each_entry_safe(seq, tmp_seq, &dfs_pd->sequences, head) {
+		if (event->ts > seq->first_ts + MT_DFS_SEQUENCE_WINDOW) {
+			list_del_init(&seq->head);
+			mt76x2_dfs_seq_pool_put(dev, seq);
+			continue;
+		}
+
+		if (event->engine != seq->engine)
+			continue;
+
+		pri = event->ts - seq->last_ts;
+		factor = mt76x2_dfs_get_multiple(pri, seq->pri,
+						 sw_params->pri_margin);
+		if (factor > 0) {
+			seq->last_ts = event->ts;
+			seq->count++;
+			max_seq_len = max_t(u16, max_seq_len, seq->count);
+		}
+	}
+	return max_seq_len;
+}
+
+static bool mt76x2_dfs_check_detection(struct mt76x2_dev *dev)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x2_dfs_sequence *seq;
+
+	if (list_empty(&dfs_pd->sequences))
+		return false;
+
+	list_for_each_entry(seq, &dfs_pd->sequences, head) {
+		if (seq->count > MT_DFS_SEQUENCE_TH) {
+			dfs_pd->stats[seq->engine].sw_pattern++;
+			return true;
+		}
+	}
+	return false;
+}
+
+static void mt76x2_dfs_add_events(struct mt76x2_dev *dev)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x2_dfs_event event;
+	int i, seq_len;
+
+	/* disable debug mode */
+	mt76x2_dfs_set_capture_mode_ctrl(dev, false);
+	for (i = 0; i < MT_DFS_EVENT_LOOP; i++) {
+		if (!mt76x2_dfs_fetch_event(dev, &event))
+			break;
+
+		if (dfs_pd->last_event_ts > event.ts)
+			mt76x2_dfs_detector_reset(dev);
+		dfs_pd->last_event_ts = event.ts;
+
+		if (!mt76x2_dfs_check_event(dev, &event))
+			continue;
+
+		seq_len = mt76x2_dfs_add_event_to_sequence(dev, &event);
+		mt76x2_dfs_create_sequence(dev, &event, seq_len);
+
+		mt76x2_dfs_queue_event(dev, &event);
+	}
+	mt76x2_dfs_set_capture_mode_ctrl(dev, true);
+}
+
+static void mt76x2_dfs_check_event_window(struct mt76x2_dev *dev)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x2_dfs_event_rb *event_buff;
+	struct mt76x2_dfs_event *event;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dfs_pd->event_rb); i++) {
+		event_buff = &dfs_pd->event_rb[i];
+
+		while (event_buff->h_rb != event_buff->t_rb) {
+			event = &event_buff->data[event_buff->h_rb];
+
+			/* sorted list */
+			if (time_is_after_jiffies(event->fetch_ts +
+						  MT_DFS_EVENT_WINDOW))
+				break;
+			event_buff->h_rb = mt76_incr(event_buff->h_rb,
+						     MT_DFS_EVENT_BUFLEN);
+		}
+	}
+}
+
 static void mt76x2_dfs_tasklet(unsigned long arg)
 {
 	struct mt76x2_dev *dev = (struct mt76x2_dev *)arg;
@@ -305,6 +630,24 @@ static void mt76x2_dfs_tasklet(unsigned long arg)
 	if (test_bit(MT76_SCANNING, &dev->mt76.state))
 		goto out;
 
+	if (time_is_before_jiffies(dfs_pd->last_sw_check +
+				   MT_DFS_SW_TIMEOUT)) {
+		bool radar_detected;
+
+		dfs_pd->last_sw_check = jiffies;
+
+		mt76x2_dfs_add_events(dev);
+		radar_detected = mt76x2_dfs_check_detection(dev);
+		if (radar_detected) {
+			/* sw detector rx radar pattern */
+			ieee80211_radar_detected(dev->mt76.hw);
+			mt76x2_dfs_detector_reset(dev);
+
+			return;
+		}
+		mt76x2_dfs_check_event_window(dev);
+	}
+
 	engine_mask = mt76_rr(dev, MT_BBP(DFS, 1));
 	if (!(engine_mask & 0xf))
 		goto out;
@@ -326,9 +669,7 @@ static void mt76x2_dfs_tasklet(unsigned long arg)
 		/* hw detector rx radar pattern */
 		dfs_pd->stats[i].hw_pattern++;
 		ieee80211_radar_detected(dev->mt76.hw);
-
-		/* reset hw detector */
-		mt76_wr(dev, MT_BBP(DFS, 1), 0xf);
+		mt76x2_dfs_detector_reset(dev);
 
 		return;
 	}
@@ -340,6 +681,32 @@ out:
 	mt76x2_irq_enable(dev, MT_INT_GPTIMER);
 }
 
+static void mt76x2_dfs_init_sw_detector(struct mt76x2_dev *dev)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+
+	switch (dev->dfs_pd.region) {
+	case NL80211_DFS_FCC:
+		dfs_pd->sw_dpd_params.max_pri = MT_DFS_FCC_MAX_PRI;
+		dfs_pd->sw_dpd_params.min_pri = MT_DFS_FCC_MIN_PRI;
+		dfs_pd->sw_dpd_params.pri_margin = MT_DFS_PRI_MARGIN;
+		break;
+	case NL80211_DFS_ETSI:
+		dfs_pd->sw_dpd_params.max_pri = MT_DFS_ETSI_MAX_PRI;
+		dfs_pd->sw_dpd_params.min_pri = MT_DFS_ETSI_MIN_PRI;
+		dfs_pd->sw_dpd_params.pri_margin = MT_DFS_PRI_MARGIN << 2;
+		break;
+	case NL80211_DFS_JP:
+		dfs_pd->sw_dpd_params.max_pri = MT_DFS_JP_MAX_PRI;
+		dfs_pd->sw_dpd_params.min_pri = MT_DFS_JP_MIN_PRI;
+		dfs_pd->sw_dpd_params.pri_margin = MT_DFS_PRI_MARGIN;
+		break;
+	case NL80211_DFS_UNSET:
+	default:
+		break;
+	}
+}
+
 static void mt76x2_dfs_set_bbp_params(struct mt76x2_dev *dev)
 {
 	u32 data;
@@ -462,6 +829,7 @@ void mt76x2_dfs_init_params(struct mt76x2_dev *dev)
 
 	if ((chandef->chan->flags & IEEE80211_CHAN_RADAR) &&
 	    dev->dfs_pd.region != NL80211_DFS_UNSET) {
+		mt76x2_dfs_init_sw_detector(dev);
 		mt76x2_dfs_set_bbp_params(dev);
 		/* enable debug mode */
 		mt76x2_dfs_set_capture_mode_ctrl(dev, true);
@@ -486,7 +854,10 @@ void mt76x2_dfs_init_detector(struct mt76x2_dev *dev)
 {
 	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
 
+	INIT_LIST_HEAD(&dfs_pd->sequences);
+	INIT_LIST_HEAD(&dfs_pd->seq_pool);
 	dfs_pd->region = NL80211_DFS_UNSET;
+	dfs_pd->last_sw_check = jiffies;
 	tasklet_init(&dfs_pd->dfs_tasklet, mt76x2_dfs_tasklet,
 		     (unsigned long)dev);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.h b/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.h
index 8dbc783cc6bc..693f421bf096 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.h
@@ -33,6 +33,22 @@
 #define MT_DFS_PKT_END_MASK		0
 #define MT_DFS_CH_EN			0xf
 
+/* sw detector params */
+#define MT_DFS_EVENT_LOOP		64
+#define MT_DFS_SW_TIMEOUT		(HZ / 20)
+#define MT_DFS_EVENT_WINDOW		(HZ / 5)
+#define MT_DFS_SEQUENCE_WINDOW		(200 * (1 << 20))
+#define MT_DFS_EVENT_TIME_MARGIN	2000
+#define MT_DFS_PRI_MARGIN		4
+#define MT_DFS_SEQUENCE_TH		6
+
+#define MT_DFS_FCC_MAX_PRI		((28570 << 1) + 1000)
+#define MT_DFS_FCC_MIN_PRI		(3000 - 2)
+#define MT_DFS_JP_MAX_PRI		((80000 << 1) + 1000)
+#define MT_DFS_JP_MIN_PRI		(28500 - 2)
+#define MT_DFS_ETSI_MAX_PRI		(133333 + 125000 + 117647 + 1000)
+#define MT_DFS_ETSI_MIN_PRI		(4500 - 20)
+
 struct mt76x2_radar_specs {
 	u8 mode;
 	u16 avg_len;
@@ -50,6 +66,32 @@ struct mt76x2_radar_specs {
 	u16 pwr_jmp;
 };
 
+#define MT_DFS_CHECK_EVENT(x)		((x) != GENMASK(31, 0))
+#define MT_DFS_EVENT_ENGINE(x)		(((x) & BIT(31)) ? 2 : 0)
+#define MT_DFS_EVENT_TIMESTAMP(x)	((x) & GENMASK(21, 0))
+#define MT_DFS_EVENT_WIDTH(x)		((x) & GENMASK(11, 0))
+struct mt76x2_dfs_event {
+	unsigned long fetch_ts;
+	u32 ts;
+	u16 width;
+	u8 engine;
+};
+
+#define MT_DFS_EVENT_BUFLEN		256
+struct mt76x2_dfs_event_rb {
+	struct mt76x2_dfs_event data[MT_DFS_EVENT_BUFLEN];
+	int h_rb, t_rb;
+};
+
+struct mt76x2_dfs_sequence {
+	struct list_head head;
+	u32 first_ts;
+	u32 last_ts;
+	u32 pri;
+	u16 count;
+	u8 engine;
+};
+
 struct mt76x2_dfs_hw_pulse {
 	u8 engine;
 	u32 period;
@@ -58,9 +100,21 @@ struct mt76x2_dfs_hw_pulse {
 	u32 burst;
 };
 
+struct mt76x2_dfs_sw_detector_params {
+	u32 min_pri;
+	u32 max_pri;
+	u32 pri_margin;
+};
+
 struct mt76x2_dfs_engine_stats {
 	u32 hw_pattern;
 	u32 hw_pulse_discarded;
+	u32 sw_pattern;
+};
+
+struct mt76x2_dfs_seq_stats {
+	u32 seq_pool_len;
+	u32 seq_len;
 };
 
 struct mt76x2_dfs_pattern_detector {
@@ -69,6 +123,16 @@ struct mt76x2_dfs_pattern_detector {
 	u8 chirp_pulse_cnt;
 	u32 chirp_pulse_ts;
 
+	struct mt76x2_dfs_sw_detector_params sw_dpd_params;
+	struct mt76x2_dfs_event_rb event_rb[2];
+
+	struct list_head sequences;
+	struct list_head seq_pool;
+	struct mt76x2_dfs_seq_stats seq_stats;
+
+	unsigned long last_sw_check;
+	u32 last_event_ts;
+
 	struct mt76x2_dfs_engine_stats stats[MT_DFS_NUM_ENGINES];
 	struct tasklet_struct dfs_tasklet;
 };
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_dma.c b/drivers/net/wireless/mediatek/mt76/mt76x2_dma.c
index fd1ec4743e0b..6720a6a1313f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_dma.c
@@ -66,27 +66,6 @@ mt76x2_init_tx_queue(struct mt76x2_dev *dev, struct mt76_queue *q,
 	return 0;
 }
 
-void mt76x2_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
-			 struct sk_buff *skb)
-{
-	struct mt76x2_dev *dev = container_of(mdev, struct mt76x2_dev, mt76);
-	void *rxwi = skb->data;
-
-	if (q == MT_RXQ_MCU) {
-		skb_queue_tail(&dev->mcu.res_q, skb);
-		wake_up(&dev->mcu.wait);
-		return;
-	}
-
-	skb_pull(skb, sizeof(struct mt76x2_rxwi));
-	if (mt76x2_mac_process_rx(dev, skb, rxwi)) {
-		dev_kfree_skb(skb);
-		return;
-	}
-
-	mt76_rx(&dev->mt76, q, skb);
-}
-
 static int
 mt76x2_init_rx_queue(struct mt76x2_dev *dev, struct mt76_queue *q,
 		     int idx, int n_desc, int bufsize)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_dma.h b/drivers/net/wireless/mediatek/mt76/mt76x2_dma.h
index e9d426bbf91a..da294558c268 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_dma.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_dma.h
@@ -19,34 +19,6 @@
 
 #include "dma.h"
 
-#define MT_TXD_INFO_LEN			GENMASK(15, 0)
-#define MT_TXD_INFO_NEXT_VLD		BIT(16)
-#define MT_TXD_INFO_TX_BURST		BIT(17)
-#define MT_TXD_INFO_80211		BIT(19)
-#define MT_TXD_INFO_TSO			BIT(20)
-#define MT_TXD_INFO_CSO			BIT(21)
-#define MT_TXD_INFO_WIV			BIT(24)
-#define MT_TXD_INFO_QSEL		GENMASK(26, 25)
-#define MT_TXD_INFO_DPORT		GENMASK(29, 27)
-#define MT_TXD_INFO_TYPE		GENMASK(31, 30)
-
-#define MT_RX_FCE_INFO_LEN		GENMASK(13, 0)
-#define MT_RX_FCE_INFO_SELF_GEN		BIT(15)
-#define MT_RX_FCE_INFO_CMD_SEQ		GENMASK(19, 16)
-#define MT_RX_FCE_INFO_EVT_TYPE		GENMASK(23, 20)
-#define MT_RX_FCE_INFO_PCIE_INTR	BIT(24)
-#define MT_RX_FCE_INFO_QSEL		GENMASK(26, 25)
-#define MT_RX_FCE_INFO_D_PORT		GENMASK(29, 27)
-#define MT_RX_FCE_INFO_TYPE		GENMASK(31, 30)
-
-/* MCU request message header  */
-#define MT_MCU_MSG_LEN			GENMASK(15, 0)
-#define MT_MCU_MSG_CMD_SEQ		GENMASK(19, 16)
-#define MT_MCU_MSG_CMD_TYPE		GENMASK(26, 20)
-#define MT_MCU_MSG_PORT			GENMASK(29, 27)
-#define MT_MCU_MSG_TYPE			GENMASK(31, 30)
-#define MT_MCU_MSG_TYPE_CMD		BIT(30)
-
 enum mt76x2_qsel {
 	MT_QSEL_MGMT,
 	MT_QSEL_HCCA,
@@ -54,14 +26,4 @@ enum mt76x2_qsel {
 	MT_QSEL_EDCA_2,
 };
 
-enum dma_msg_port {
-	WLAN_PORT,
-	CPU_RX_PORT,
-	CPU_TX_PORT,
-	HOST_PORT,
-	VIRTUAL_CPU_RX_PORT,
-	VIRTUAL_CPU_TX_PORT,
-	DISCARD,
-};
-
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x2_eeprom.c
index 95d5f7d888f0..1753bcb36356 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_eeprom.c
@@ -40,8 +40,7 @@ mt76x2_eeprom_get_macaddr(struct mt76x2_dev *dev)
 	return 0;
 }
 
-static void
-mt76x2_eeprom_parse_hw_cap(struct mt76x2_dev *dev)
+void mt76x2_eeprom_parse_hw_cap(struct mt76x2_dev *dev)
 {
 	u16 val = mt76x2_eeprom_get(dev, MT_EE_NIC_CONF_0);
 
@@ -58,6 +57,7 @@ mt76x2_eeprom_parse_hw_cap(struct mt76x2_dev *dev)
 		break;
 	}
 }
+EXPORT_SYMBOL_GPL(mt76x2_eeprom_parse_hw_cap);
 
 static int
 mt76x2_efuse_read(struct mt76x2_dev *dev, u16 addr, u8 *data)
@@ -415,6 +415,7 @@ void mt76x2_read_rx_gain(struct mt76x2_dev *dev)
 
 	dev->cal.rx.lna_gain = mt76x2_sign_extend(lna, 8);
 }
+EXPORT_SYMBOL_GPL(mt76x2_read_rx_gain);
 
 static s8
 mt76x2_rate_power_val(u8 val)
@@ -482,6 +483,7 @@ void mt76x2_get_rate_power(struct mt76x2_dev *dev, struct mt76_rate_power *t,
 		val >>= 8;
 	t->vht[8] = t->vht[9] = mt76x2_rate_power_val(val >> 8);
 }
+EXPORT_SYMBOL_GPL(mt76x2_get_rate_power);
 
 int mt76x2_get_max_rate_power(struct mt76_rate_power *r)
 {
@@ -493,6 +495,7 @@ int mt76x2_get_max_rate_power(struct mt76_rate_power *r)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(mt76x2_get_max_rate_power);
 
 static void
 mt76x2_get_power_info_2g(struct mt76x2_dev *dev, struct mt76x2_tx_power_info *t,
@@ -600,6 +603,7 @@ void mt76x2_get_power_info(struct mt76x2_dev *dev,
 	t->delta_bw40 = mt76x2_rate_power_val(bw40);
 	t->delta_bw80 = mt76x2_rate_power_val(bw80);
 }
+EXPORT_SYMBOL_GPL(mt76x2_get_power_info);
 
 int mt76x2_get_temp_comp(struct mt76x2_dev *dev, struct mt76x2_temp_comp *t)
 {
@@ -632,6 +636,7 @@ int mt76x2_get_temp_comp(struct mt76x2_dev *dev, struct mt76x2_temp_comp *t)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(mt76x2_get_temp_comp);
 
 bool mt76x2_ext_pa_enabled(struct mt76x2_dev *dev, enum nl80211_band band)
 {
@@ -642,6 +647,7 @@ bool mt76x2_ext_pa_enabled(struct mt76x2_dev *dev, enum nl80211_band band)
 	else
 		return !(conf0 & MT_EE_NIC_CONF_0_PA_INT_2G);
 }
+EXPORT_SYMBOL_GPL(mt76x2_ext_pa_enabled);
 
 int mt76x2_eeprom_init(struct mt76x2_dev *dev)
 {
@@ -658,3 +664,6 @@ int mt76x2_eeprom_init(struct mt76x2_dev *dev)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(mt76x2_eeprom_init);
+
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_eeprom.h b/drivers/net/wireless/mediatek/mt76/mt76x2_eeprom.h
index aa0b0c040375..0f3e4d2f4fee 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_eeprom.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_eeprom.h
@@ -155,6 +155,7 @@ void mt76x2_get_power_info(struct mt76x2_dev *dev,
 int mt76x2_get_temp_comp(struct mt76x2_dev *dev, struct mt76x2_temp_comp *t);
 bool mt76x2_ext_pa_enabled(struct mt76x2_dev *dev, enum nl80211_band band);
 void mt76x2_read_rx_gain(struct mt76x2_dev *dev);
+void mt76x2_eeprom_parse_hw_cap(struct mt76x2_dev *dev);
 
 static inline bool
 mt76x2_temp_tx_alc_enabled(struct mt76x2_dev *dev)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
index 79ab93613e06..b814391f79ac 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
@@ -19,39 +19,6 @@
 #include "mt76x2_eeprom.h"
 #include "mt76x2_mcu.h"
 
-struct mt76x2_reg_pair {
-	u32 reg;
-	u32 value;
-};
-
-static bool
-mt76x2_wait_for_mac(struct mt76x2_dev *dev)
-{
-	int i;
-
-	for (i = 0; i < 500; i++) {
-		switch (mt76_rr(dev, MT_MAC_CSR0)) {
-		case 0:
-		case ~0:
-			break;
-		default:
-			return true;
-		}
-		usleep_range(5000, 10000);
-	}
-
-	return false;
-}
-
-static bool
-wait_for_wpdma(struct mt76x2_dev *dev)
-{
-	return mt76_poll(dev, MT_WPDMA_GLO_CFG,
-			 MT_WPDMA_GLO_CFG_TX_DMA_BUSY |
-			 MT_WPDMA_GLO_CFG_RX_DMA_BUSY,
-			 0, 1000);
-}
-
 static void
 mt76x2_mac_pbf_init(struct mt76x2_dev *dev)
 {
@@ -71,107 +38,6 @@ mt76x2_mac_pbf_init(struct mt76x2_dev *dev)
 }
 
 static void
-mt76x2_write_reg_pairs(struct mt76x2_dev *dev,
-		       const struct mt76x2_reg_pair *data, int len)
-{
-	while (len > 0) {
-		mt76_wr(dev, data->reg, data->value);
-		len--;
-		data++;
-	}
-}
-
-static void
-mt76_write_mac_initvals(struct mt76x2_dev *dev)
-{
-#define DEFAULT_PROT_CFG				\
-	(FIELD_PREP(MT_PROT_CFG_RATE, 0x2004) |		\
-	 FIELD_PREP(MT_PROT_CFG_NAV, 1) |			\
-	 FIELD_PREP(MT_PROT_CFG_TXOP_ALLOW, 0x3f) |	\
-	 MT_PROT_CFG_RTS_THRESH)
-
-#define DEFAULT_PROT_CFG_20				\
-	(FIELD_PREP(MT_PROT_CFG_RATE, 0x2004) |		\
-	 FIELD_PREP(MT_PROT_CFG_CTRL, 1) |		\
-	 FIELD_PREP(MT_PROT_CFG_NAV, 1) |			\
-	 FIELD_PREP(MT_PROT_CFG_TXOP_ALLOW, 0x17))
-
-#define DEFAULT_PROT_CFG_40				\
-	(FIELD_PREP(MT_PROT_CFG_RATE, 0x2084) |		\
-	 FIELD_PREP(MT_PROT_CFG_CTRL, 1) |		\
-	 FIELD_PREP(MT_PROT_CFG_NAV, 1) |			\
-	 FIELD_PREP(MT_PROT_CFG_TXOP_ALLOW, 0x3f))
-
-	static const struct mt76x2_reg_pair vals[] = {
-		/* Copied from MediaTek reference source */
-		{ MT_PBF_SYS_CTRL,		0x00080c00 },
-		{ MT_PBF_CFG,			0x1efebcff },
-		{ MT_FCE_PSE_CTRL,		0x00000001 },
-		{ MT_MAC_SYS_CTRL,		0x0000000c },
-		{ MT_MAX_LEN_CFG,		0x003e3f00 },
-		{ MT_AMPDU_MAX_LEN_20M1S,	0xaaa99887 },
-		{ MT_AMPDU_MAX_LEN_20M2S,	0x000000aa },
-		{ MT_XIFS_TIME_CFG,		0x33a40d0a },
-		{ MT_BKOFF_SLOT_CFG,		0x00000209 },
-		{ MT_TBTT_SYNC_CFG,		0x00422010 },
-		{ MT_PWR_PIN_CFG,		0x00000000 },
-		{ 0x1238,			0x001700c8 },
-		{ MT_TX_SW_CFG0,		0x00101001 },
-		{ MT_TX_SW_CFG1,		0x00010000 },
-		{ MT_TX_SW_CFG2,		0x00000000 },
-		{ MT_TXOP_CTRL_CFG,		0x0400583f },
-		{ MT_TX_RTS_CFG,		0x00100020 },
-		{ MT_TX_TIMEOUT_CFG,		0x000a2290 },
-		{ MT_TX_RETRY_CFG,		0x47f01f0f },
-		{ MT_EXP_ACK_TIME,		0x002c00dc },
-		{ MT_TX_PROT_CFG6,		0xe3f42004 },
-		{ MT_TX_PROT_CFG7,		0xe3f42084 },
-		{ MT_TX_PROT_CFG8,		0xe3f42104 },
-		{ MT_PIFS_TX_CFG,		0x00060fff },
-		{ MT_RX_FILTR_CFG,		0x00015f97 },
-		{ MT_LEGACY_BASIC_RATE,		0x0000017f },
-		{ MT_HT_BASIC_RATE,		0x00004003 },
-		{ MT_PN_PAD_MODE,		0x00000003 },
-		{ MT_TXOP_HLDR_ET,		0x00000002 },
-		{ 0xa44,			0x00000000 },
-		{ MT_HEADER_TRANS_CTRL_REG,	0x00000000 },
-		{ MT_TSO_CTRL,			0x00000000 },
-		{ MT_AUX_CLK_CFG,		0x00000000 },
-		{ MT_DACCLK_EN_DLY_CFG,		0x00000000 },
-		{ MT_TX_ALC_CFG_4,		0x00000000 },
-		{ MT_TX_ALC_VGA3,		0x00000000 },
-		{ MT_TX_PWR_CFG_0,		0x3a3a3a3a },
-		{ MT_TX_PWR_CFG_1,		0x3a3a3a3a },
-		{ MT_TX_PWR_CFG_2,		0x3a3a3a3a },
-		{ MT_TX_PWR_CFG_3,		0x3a3a3a3a },
-		{ MT_TX_PWR_CFG_4,		0x3a3a3a3a },
-		{ MT_TX_PWR_CFG_7,		0x3a3a3a3a },
-		{ MT_TX_PWR_CFG_8,		0x0000003a },
-		{ MT_TX_PWR_CFG_9,		0x0000003a },
-		{ MT_EFUSE_CTRL,		0x0000d000 },
-		{ MT_PAUSE_ENABLE_CONTROL1,	0x0000000a },
-		{ MT_FCE_WLAN_FLOW_CONTROL1,	0x60401c18 },
-		{ MT_WPDMA_DELAY_INT_CFG,	0x94ff0000 },
-		{ MT_TX_SW_CFG3,		0x00000004 },
-		{ MT_HT_FBK_TO_LEGACY,		0x00001818 },
-		{ MT_VHT_HT_FBK_CFG1,		0xedcba980 },
-		{ MT_PROT_AUTO_TX_CFG,		0x00830083 },
-		{ MT_HT_CTRL_CFG,		0x000001ff },
-	};
-	struct mt76x2_reg_pair prot_vals[] = {
-		{ MT_CCK_PROT_CFG,		DEFAULT_PROT_CFG },
-		{ MT_OFDM_PROT_CFG,		DEFAULT_PROT_CFG },
-		{ MT_MM20_PROT_CFG,		DEFAULT_PROT_CFG_20 },
-		{ MT_MM40_PROT_CFG,		DEFAULT_PROT_CFG_40 },
-		{ MT_GF20_PROT_CFG,		DEFAULT_PROT_CFG_20 },
-		{ MT_GF40_PROT_CFG,		DEFAULT_PROT_CFG_40 },
-	};
-
-	mt76x2_write_reg_pairs(dev, vals, ARRAY_SIZE(vals));
-	mt76x2_write_reg_pairs(dev, prot_vals, ARRAY_SIZE(prot_vals));
-}
-
-static void
 mt76x2_fixup_xtal(struct mt76x2_dev *dev)
 {
 	u16 eep_val;
@@ -360,41 +226,6 @@ int mt76x2_mac_start(struct mt76x2_dev *dev)
 	return 0;
 }
 
-void mt76x2_mac_stop(struct mt76x2_dev *dev, bool force)
-{
-	bool stopped = false;
-	u32 rts_cfg;
-	int i;
-
-	mt76_wr(dev, MT_MAC_SYS_CTRL, 0);
-
-	rts_cfg = mt76_rr(dev, MT_TX_RTS_CFG);
-	mt76_wr(dev, MT_TX_RTS_CFG, rts_cfg & ~MT_TX_RTS_CFG_RETRY_LIMIT);
-
-	/* Wait for MAC to become idle */
-	for (i = 0; i < 300; i++) {
-		if ((mt76_rr(dev, MT_MAC_STATUS) &
-		     (MT_MAC_STATUS_RX | MT_MAC_STATUS_TX)) ||
-		    mt76_rr(dev, MT_BBP(IBI, 12))) {
-			udelay(1);
-			continue;
-		}
-
-		stopped = true;
-		break;
-	}
-
-	if (force && !stopped) {
-		mt76_set(dev, MT_BBP(CORE, 4), BIT(1));
-		mt76_clear(dev, MT_BBP(CORE, 4), BIT(1));
-
-		mt76_set(dev, MT_BBP(CORE, 4), BIT(0));
-		mt76_clear(dev, MT_BBP(CORE, 4), BIT(0));
-	}
-
-	mt76_wr(dev, MT_TX_RTS_CFG, rts_cfg);
-}
-
 void mt76x2_mac_resume(struct mt76x2_dev *dev)
 {
 	mt76_wr(dev, MT_MAC_SYS_CTRL,
@@ -498,45 +329,6 @@ void mt76x2_set_tx_ackto(struct mt76x2_dev *dev)
 		       MT_TX_TIMEOUT_CFG_ACKTO, ackto);
 }
 
-static void
-mt76x2_set_wlan_state(struct mt76x2_dev *dev, bool enable)
-{
-	u32 val = mt76_rr(dev, MT_WLAN_FUN_CTRL);
-
-	if (enable)
-		val |= (MT_WLAN_FUN_CTRL_WLAN_EN |
-			MT_WLAN_FUN_CTRL_WLAN_CLK_EN);
-	else
-		val &= ~(MT_WLAN_FUN_CTRL_WLAN_EN |
-			 MT_WLAN_FUN_CTRL_WLAN_CLK_EN);
-
-	mt76_wr(dev, MT_WLAN_FUN_CTRL, val);
-	udelay(20);
-}
-
-static void
-mt76x2_reset_wlan(struct mt76x2_dev *dev, bool enable)
-{
-	u32 val;
-
-	val = mt76_rr(dev, MT_WLAN_FUN_CTRL);
-
-	val &= ~MT_WLAN_FUN_CTRL_FRC_WL_ANT_SEL;
-
-	if (val & MT_WLAN_FUN_CTRL_WLAN_EN) {
-		val |= MT_WLAN_FUN_CTRL_WLAN_RESET_RF;
-		mt76_wr(dev, MT_WLAN_FUN_CTRL, val);
-		udelay(20);
-
-		val &= ~MT_WLAN_FUN_CTRL_WLAN_RESET_RF;
-	}
-
-	mt76_wr(dev, MT_WLAN_FUN_CTRL, val);
-	udelay(20);
-
-	mt76x2_set_wlan_state(dev, enable);
-}
-
 int mt76x2_init_hardware(struct mt76x2_dev *dev)
 {
 	static const u16 beacon_offsets[16] = {
@@ -567,11 +359,6 @@ int mt76x2_init_hardware(struct mt76x2_dev *dev)
 	tasklet_init(&dev->pre_tbtt_tasklet, mt76x2_pre_tbtt_tasklet,
 		     (unsigned long) dev);
 
-	dev->chainmask = 0x202;
-	dev->global_wcid.idx = 255;
-	dev->global_wcid.hw_key_idx = -1;
-	dev->slottime = 9;
-
 	val = mt76_rr(dev, MT_WPDMA_GLO_CFG);
 	val &= MT_WPDMA_GLO_CFG_DMA_BURST_SIZE |
 	       MT_WPDMA_GLO_CFG_BIG_ENDIAN |
@@ -663,34 +450,6 @@ static void mt76x2_regd_notifier(struct wiphy *wiphy,
 	mt76x2_dfs_set_domain(dev, request->dfs_region);
 }
 
-#define CCK_RATE(_idx, _rate) {					\
-	.bitrate = _rate,					\
-	.flags = IEEE80211_RATE_SHORT_PREAMBLE,			\
-	.hw_value = (MT_PHY_TYPE_CCK << 8) | _idx,		\
-	.hw_value_short = (MT_PHY_TYPE_CCK << 8) | (8 + _idx),	\
-}
-
-#define OFDM_RATE(_idx, _rate) {				\
-	.bitrate = _rate,					\
-	.hw_value = (MT_PHY_TYPE_OFDM << 8) | _idx,		\
-	.hw_value_short = (MT_PHY_TYPE_OFDM << 8) | _idx,	\
-}
-
-static struct ieee80211_rate mt76x2_rates[] = {
-	CCK_RATE(0, 10),
-	CCK_RATE(1, 20),
-	CCK_RATE(2, 55),
-	CCK_RATE(3, 110),
-	OFDM_RATE(0, 60),
-	OFDM_RATE(1, 90),
-	OFDM_RATE(2, 120),
-	OFDM_RATE(3, 180),
-	OFDM_RATE(4, 240),
-	OFDM_RATE(5, 360),
-	OFDM_RATE(6, 480),
-	OFDM_RATE(7, 540),
-};
-
 static const struct ieee80211_iface_limit if_limits[] = {
 	{
 		.max = 1,
@@ -767,37 +526,6 @@ static void mt76x2_led_set_brightness(struct led_classdev *led_cdev,
 		mt76x2_led_set_config(mt76, 0xff, 0);
 }
 
-static void
-mt76x2_init_txpower(struct mt76x2_dev *dev,
-		    struct ieee80211_supported_band *sband)
-{
-	struct ieee80211_channel *chan;
-	struct mt76x2_tx_power_info txp;
-	struct mt76_rate_power t = {};
-	int target_power;
-	int i;
-
-	for (i = 0; i < sband->n_channels; i++) {
-		chan = &sband->channels[i];
-
-		mt76x2_get_power_info(dev, &txp, chan);
-
-		target_power = max_t(int, (txp.chain[0].target_power +
-					   txp.chain[0].delta),
-					  (txp.chain[1].target_power +
-					   txp.chain[1].delta));
-
-		mt76x2_get_rate_power(dev, &t, chan);
-
-		chan->max_power = mt76x2_get_max_rate_power(&t) +
-				  target_power;
-		chan->max_power /= 2;
-
-		/* convert to combined output power on 2x2 devices */
-		chan->max_power += 3;
-	}
-}
-
 int mt76x2_register_device(struct mt76x2_dev *dev)
 {
 	struct ieee80211_hw *hw = mt76_hw(dev);
@@ -812,20 +540,15 @@ int mt76x2_register_device(struct mt76x2_dev *dev)
 		return -ENOMEM;
 
 	kfifo_init(&dev->txstatus_fifo, status_fifo, fifo_size);
+	INIT_DELAYED_WORK(&dev->cal_work, mt76x2_phy_calibrate);
+	INIT_DELAYED_WORK(&dev->mac_work, mt76x2_mac_work);
+
+	mt76x2_init_device(dev);
 
 	ret = mt76x2_init_hardware(dev);
 	if (ret)
 		return ret;
 
-	hw->queues = 4;
-	hw->max_rates = 1;
-	hw->max_report_rates = 7;
-	hw->max_rate_tries = 1;
-	hw->extra_tx_headroom = 2;
-
-	hw->sta_data_size = sizeof(struct mt76x2_sta);
-	hw->vif_data_size = sizeof(struct mt76x2_vif);
-
 	for (i = 0; i < ARRAY_SIZE(dev->macaddr_list); i++) {
 		u8 *addr = dev->macaddr_list[i].addr;
 
@@ -845,16 +568,15 @@ int mt76x2_register_device(struct mt76x2_dev *dev)
 
 	wiphy->reg_notifier = mt76x2_regd_notifier;
 
-	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_VHT_IBSS);
-
-	ieee80211_hw_set(hw, SUPPORTS_HT_CCK_RATES);
-	ieee80211_hw_set(hw, SUPPORTS_REORDERING_BUFFER);
-
-	INIT_DELAYED_WORK(&dev->cal_work, mt76x2_phy_calibrate);
-	INIT_DELAYED_WORK(&dev->mac_work, mt76x2_mac_work);
+	wiphy->interface_modes =
+		BIT(NL80211_IFTYPE_STATION) |
+		BIT(NL80211_IFTYPE_AP) |
+#ifdef CONFIG_MAC80211_MESH
+		BIT(NL80211_IFTYPE_MESH_POINT) |
+#endif
+		BIT(NL80211_IFTYPE_ADHOC);
 
-	dev->mt76.sband_2g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING;
-	dev->mt76.sband_5g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING;
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_VHT_IBSS);
 
 	mt76x2_dfs_init_detector(dev);
 
@@ -862,9 +584,6 @@ int mt76x2_register_device(struct mt76x2_dev *dev)
 	dev->mt76.led_cdev.brightness_set = mt76x2_led_set_brightness;
 	dev->mt76.led_cdev.blink_set = mt76x2_led_set_blink;
 
-	/* init antenna configuration */
-	dev->mt76.antenna_mask = 3;
-
 	ret = mt76_register_device(&dev->mt76, true, mt76x2_rates,
 				   ARRAY_SIZE(mt76x2_rates));
 	if (ret)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_init_common.c b/drivers/net/wireless/mediatek/mt76/mt76x2_init_common.c
new file mode 100644
index 000000000000..324b2a4b8b67
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_init_common.c
@@ -0,0 +1,259 @@
+/*
+ * Copyright (C) 2016 Felix Fietkau <nbd@nbd.name>
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76x2.h"
+#include "mt76x2_eeprom.h"
+
+#define CCK_RATE(_idx, _rate) {					\
+	.bitrate = _rate,					\
+	.flags = IEEE80211_RATE_SHORT_PREAMBLE,			\
+	.hw_value = (MT_PHY_TYPE_CCK << 8) | _idx,		\
+	.hw_value_short = (MT_PHY_TYPE_CCK << 8) | (8 + _idx),	\
+}
+
+#define OFDM_RATE(_idx, _rate) {				\
+	.bitrate = _rate,					\
+	.hw_value = (MT_PHY_TYPE_OFDM << 8) | _idx,		\
+	.hw_value_short = (MT_PHY_TYPE_OFDM << 8) | _idx,	\
+}
+
+struct ieee80211_rate mt76x2_rates[] = {
+	CCK_RATE(0, 10),
+	CCK_RATE(1, 20),
+	CCK_RATE(2, 55),
+	CCK_RATE(3, 110),
+	OFDM_RATE(0, 60),
+	OFDM_RATE(1, 90),
+	OFDM_RATE(2, 120),
+	OFDM_RATE(3, 180),
+	OFDM_RATE(4, 240),
+	OFDM_RATE(5, 360),
+	OFDM_RATE(6, 480),
+	OFDM_RATE(7, 540),
+};
+EXPORT_SYMBOL_GPL(mt76x2_rates);
+
+struct mt76x2_reg_pair {
+	u32 reg;
+	u32 value;
+};
+
+static void
+mt76x2_set_wlan_state(struct mt76x2_dev *dev, bool enable)
+{
+	u32 val = mt76_rr(dev, MT_WLAN_FUN_CTRL);
+
+	if (enable)
+		val |= (MT_WLAN_FUN_CTRL_WLAN_EN |
+			MT_WLAN_FUN_CTRL_WLAN_CLK_EN);
+	else
+		val &= ~(MT_WLAN_FUN_CTRL_WLAN_EN |
+			 MT_WLAN_FUN_CTRL_WLAN_CLK_EN);
+
+	mt76_wr(dev, MT_WLAN_FUN_CTRL, val);
+	udelay(20);
+}
+
+void mt76x2_reset_wlan(struct mt76x2_dev *dev, bool enable)
+{
+	u32 val;
+
+	val = mt76_rr(dev, MT_WLAN_FUN_CTRL);
+
+	val &= ~MT_WLAN_FUN_CTRL_FRC_WL_ANT_SEL;
+
+	if (val & MT_WLAN_FUN_CTRL_WLAN_EN) {
+		val |= MT_WLAN_FUN_CTRL_WLAN_RESET_RF;
+		mt76_wr(dev, MT_WLAN_FUN_CTRL, val);
+		udelay(20);
+
+		val &= ~MT_WLAN_FUN_CTRL_WLAN_RESET_RF;
+	}
+
+	mt76_wr(dev, MT_WLAN_FUN_CTRL, val);
+	udelay(20);
+
+	mt76x2_set_wlan_state(dev, enable);
+}
+EXPORT_SYMBOL_GPL(mt76x2_reset_wlan);
+
+static void
+mt76x2_write_reg_pairs(struct mt76x2_dev *dev,
+		       const struct mt76x2_reg_pair *data, int len)
+{
+	while (len > 0) {
+		mt76_wr(dev, data->reg, data->value);
+		len--;
+		data++;
+	}
+}
+
+void mt76_write_mac_initvals(struct mt76x2_dev *dev)
+{
+#define DEFAULT_PROT_CFG_CCK				\
+	(FIELD_PREP(MT_PROT_CFG_RATE, 0x3) |		\
+	 FIELD_PREP(MT_PROT_CFG_NAV, 1) |		\
+	 FIELD_PREP(MT_PROT_CFG_TXOP_ALLOW, 0x3f) |	\
+	 MT_PROT_CFG_RTS_THRESH)
+
+#define DEFAULT_PROT_CFG_OFDM				\
+	(FIELD_PREP(MT_PROT_CFG_RATE, 0x2004) |		\
+	 FIELD_PREP(MT_PROT_CFG_NAV, 1) |			\
+	 FIELD_PREP(MT_PROT_CFG_TXOP_ALLOW, 0x3f) |	\
+	 MT_PROT_CFG_RTS_THRESH)
+
+#define DEFAULT_PROT_CFG_20				\
+	(FIELD_PREP(MT_PROT_CFG_RATE, 0x2004) |		\
+	 FIELD_PREP(MT_PROT_CFG_CTRL, 1) |		\
+	 FIELD_PREP(MT_PROT_CFG_NAV, 1) |			\
+	 FIELD_PREP(MT_PROT_CFG_TXOP_ALLOW, 0x17))
+
+#define DEFAULT_PROT_CFG_40				\
+	(FIELD_PREP(MT_PROT_CFG_RATE, 0x2084) |		\
+	 FIELD_PREP(MT_PROT_CFG_CTRL, 1) |		\
+	 FIELD_PREP(MT_PROT_CFG_NAV, 1) |			\
+	 FIELD_PREP(MT_PROT_CFG_TXOP_ALLOW, 0x3f))
+
+	static const struct mt76x2_reg_pair vals[] = {
+		/* Copied from MediaTek reference source */
+		{ MT_PBF_SYS_CTRL,		0x00080c00 },
+		{ MT_PBF_CFG,			0x1efebcff },
+		{ MT_FCE_PSE_CTRL,		0x00000001 },
+		{ MT_MAC_SYS_CTRL,		0x0000000c },
+		{ MT_MAX_LEN_CFG,		0x003e3f00 },
+		{ MT_AMPDU_MAX_LEN_20M1S,	0xaaa99887 },
+		{ MT_AMPDU_MAX_LEN_20M2S,	0x000000aa },
+		{ MT_XIFS_TIME_CFG,		0x33a40d0a },
+		{ MT_BKOFF_SLOT_CFG,		0x00000209 },
+		{ MT_TBTT_SYNC_CFG,		0x00422010 },
+		{ MT_PWR_PIN_CFG,		0x00000000 },
+		{ 0x1238,			0x001700c8 },
+		{ MT_TX_SW_CFG0,		0x00101001 },
+		{ MT_TX_SW_CFG1,		0x00010000 },
+		{ MT_TX_SW_CFG2,		0x00000000 },
+		{ MT_TXOP_CTRL_CFG,		0x0400583f },
+		{ MT_TX_RTS_CFG,		0x00100020 },
+		{ MT_TX_TIMEOUT_CFG,		0x000a2290 },
+		{ MT_TX_RETRY_CFG,		0x47f01f0f },
+		{ MT_EXP_ACK_TIME,		0x002c00dc },
+		{ MT_TX_PROT_CFG6,		0xe3f42004 },
+		{ MT_TX_PROT_CFG7,		0xe3f42084 },
+		{ MT_TX_PROT_CFG8,		0xe3f42104 },
+		{ MT_PIFS_TX_CFG,		0x00060fff },
+		{ MT_RX_FILTR_CFG,		0x00015f97 },
+		{ MT_LEGACY_BASIC_RATE,		0x0000017f },
+		{ MT_HT_BASIC_RATE,		0x00004003 },
+		{ MT_PN_PAD_MODE,		0x00000003 },
+		{ MT_TXOP_HLDR_ET,		0x00000002 },
+		{ 0xa44,			0x00000000 },
+		{ MT_HEADER_TRANS_CTRL_REG,	0x00000000 },
+		{ MT_TSO_CTRL,			0x00000000 },
+		{ MT_AUX_CLK_CFG,		0x00000000 },
+		{ MT_DACCLK_EN_DLY_CFG,		0x00000000 },
+		{ MT_TX_ALC_CFG_4,		0x00000000 },
+		{ MT_TX_ALC_VGA3,		0x00000000 },
+		{ MT_TX_PWR_CFG_0,		0x3a3a3a3a },
+		{ MT_TX_PWR_CFG_1,		0x3a3a3a3a },
+		{ MT_TX_PWR_CFG_2,		0x3a3a3a3a },
+		{ MT_TX_PWR_CFG_3,		0x3a3a3a3a },
+		{ MT_TX_PWR_CFG_4,		0x3a3a3a3a },
+		{ MT_TX_PWR_CFG_7,		0x3a3a3a3a },
+		{ MT_TX_PWR_CFG_8,		0x0000003a },
+		{ MT_TX_PWR_CFG_9,		0x0000003a },
+		{ MT_EFUSE_CTRL,		0x0000d000 },
+		{ MT_PAUSE_ENABLE_CONTROL1,	0x0000000a },
+		{ MT_FCE_WLAN_FLOW_CONTROL1,	0x60401c18 },
+		{ MT_WPDMA_DELAY_INT_CFG,	0x94ff0000 },
+		{ MT_TX_SW_CFG3,		0x00000004 },
+		{ MT_HT_FBK_TO_LEGACY,		0x00001818 },
+		{ MT_VHT_HT_FBK_CFG1,		0xedcba980 },
+		{ MT_PROT_AUTO_TX_CFG,		0x00830083 },
+		{ MT_HT_CTRL_CFG,		0x000001ff },
+	};
+	struct mt76x2_reg_pair prot_vals[] = {
+		{ MT_CCK_PROT_CFG,		DEFAULT_PROT_CFG_CCK },
+		{ MT_OFDM_PROT_CFG,		DEFAULT_PROT_CFG_OFDM },
+		{ MT_MM20_PROT_CFG,		DEFAULT_PROT_CFG_20 },
+		{ MT_MM40_PROT_CFG,		DEFAULT_PROT_CFG_40 },
+		{ MT_GF20_PROT_CFG,		DEFAULT_PROT_CFG_20 },
+		{ MT_GF40_PROT_CFG,		DEFAULT_PROT_CFG_40 },
+	};
+
+	mt76x2_write_reg_pairs(dev, vals, ARRAY_SIZE(vals));
+	mt76x2_write_reg_pairs(dev, prot_vals, ARRAY_SIZE(prot_vals));
+}
+EXPORT_SYMBOL_GPL(mt76_write_mac_initvals);
+
+void mt76x2_init_device(struct mt76x2_dev *dev)
+{
+	struct ieee80211_hw *hw = mt76_hw(dev);
+
+	hw->queues = 4;
+	hw->max_rates = 1;
+	hw->max_report_rates = 7;
+	hw->max_rate_tries = 1;
+	hw->extra_tx_headroom = 2;
+
+	hw->sta_data_size = sizeof(struct mt76x2_sta);
+	hw->vif_data_size = sizeof(struct mt76x2_vif);
+
+	ieee80211_hw_set(hw, SUPPORTS_HT_CCK_RATES);
+	ieee80211_hw_set(hw, SUPPORTS_REORDERING_BUFFER);
+
+	dev->mt76.sband_2g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING;
+	dev->mt76.sband_5g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING;
+
+	dev->chainmask = 0x202;
+	dev->global_wcid.idx = 255;
+	dev->global_wcid.hw_key_idx = -1;
+	dev->slottime = 9;
+
+	/* init antenna configuration */
+	dev->mt76.antenna_mask = 3;
+}
+EXPORT_SYMBOL_GPL(mt76x2_init_device);
+
+void mt76x2_init_txpower(struct mt76x2_dev *dev,
+			 struct ieee80211_supported_band *sband)
+{
+	struct ieee80211_channel *chan;
+	struct mt76x2_tx_power_info txp;
+	struct mt76_rate_power t = {};
+	int target_power;
+	int i;
+
+	for (i = 0; i < sband->n_channels; i++) {
+		chan = &sband->channels[i];
+
+		mt76x2_get_power_info(dev, &txp, chan);
+
+		target_power = max_t(int, (txp.chain[0].target_power +
+					   txp.chain[0].delta),
+					  (txp.chain[1].target_power +
+					   txp.chain[1].delta));
+
+		mt76x2_get_rate_power(dev, &t, chan);
+
+		chan->max_power = mt76x2_get_max_rate_power(&t) +
+				  target_power;
+		chan->max_power /= 2;
+
+		/* convert to combined output power on 2x2 devices */
+		chan->max_power += 3;
+	}
+}
+EXPORT_SYMBOL_GPL(mt76x2_init_txpower);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
index b49aea4da2d6..23cf437d14f9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
@@ -28,500 +28,12 @@ void mt76x2_mac_set_bssid(struct mt76x2_dev *dev, u8 idx, const u8 *addr)
 		       get_unaligned_le16(addr + 4));
 }
 
-static int
-mt76x2_mac_process_rate(struct mt76_rx_status *status, u16 rate)
-{
-	u8 idx = FIELD_GET(MT_RXWI_RATE_INDEX, rate);
-
-	switch (FIELD_GET(MT_RXWI_RATE_PHY, rate)) {
-	case MT_PHY_TYPE_OFDM:
-		if (idx >= 8)
-			idx = 0;
-
-		if (status->band == NL80211_BAND_2GHZ)
-			idx += 4;
-
-		status->rate_idx = idx;
-		return 0;
-	case MT_PHY_TYPE_CCK:
-		if (idx >= 8) {
-			idx -= 8;
-			status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
-		}
-
-		if (idx >= 4)
-			idx = 0;
-
-		status->rate_idx = idx;
-		return 0;
-	case MT_PHY_TYPE_HT_GF:
-		status->enc_flags |= RX_ENC_FLAG_HT_GF;
-		/* fall through */
-	case MT_PHY_TYPE_HT:
-		status->encoding = RX_ENC_HT;
-		status->rate_idx = idx;
-		break;
-	case MT_PHY_TYPE_VHT:
-		status->encoding = RX_ENC_VHT;
-		status->rate_idx = FIELD_GET(MT_RATE_INDEX_VHT_IDX, idx);
-		status->nss = FIELD_GET(MT_RATE_INDEX_VHT_NSS, idx) + 1;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if (rate & MT_RXWI_RATE_LDPC)
-		status->enc_flags |= RX_ENC_FLAG_LDPC;
-
-	if (rate & MT_RXWI_RATE_SGI)
-		status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
-
-	if (rate & MT_RXWI_RATE_STBC)
-		status->enc_flags |= 1 << RX_ENC_FLAG_STBC_SHIFT;
-
-	switch (FIELD_GET(MT_RXWI_RATE_BW, rate)) {
-	case MT_PHY_BW_20:
-		break;
-	case MT_PHY_BW_40:
-		status->bw = RATE_INFO_BW_40;
-		break;
-	case MT_PHY_BW_80:
-		status->bw = RATE_INFO_BW_80;
-		break;
-	default:
-		break;
-	}
-
-	return 0;
-}
-
-static __le16
-mt76x2_mac_tx_rate_val(struct mt76x2_dev *dev,
-		       const struct ieee80211_tx_rate *rate, u8 *nss_val)
-{
-	u16 rateval;
-	u8 phy, rate_idx;
-	u8 nss = 1;
-	u8 bw = 0;
-
-	if (rate->flags & IEEE80211_TX_RC_VHT_MCS) {
-		rate_idx = rate->idx;
-		nss = 1 + (rate->idx >> 4);
-		phy = MT_PHY_TYPE_VHT;
-		if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
-			bw = 2;
-		else if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
-			bw = 1;
-	} else if (rate->flags & IEEE80211_TX_RC_MCS) {
-		rate_idx = rate->idx;
-		nss = 1 + (rate->idx >> 3);
-		phy = MT_PHY_TYPE_HT;
-		if (rate->flags & IEEE80211_TX_RC_GREEN_FIELD)
-			phy = MT_PHY_TYPE_HT_GF;
-		if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
-			bw = 1;
-	} else {
-		const struct ieee80211_rate *r;
-		int band = dev->mt76.chandef.chan->band;
-		u16 val;
-
-		r = &mt76_hw(dev)->wiphy->bands[band]->bitrates[rate->idx];
-		if (rate->flags & IEEE80211_TX_RC_USE_SHORT_PREAMBLE)
-			val = r->hw_value_short;
-		else
-			val = r->hw_value;
-
-		phy = val >> 8;
-		rate_idx = val & 0xff;
-		bw = 0;
-	}
-
-	rateval = FIELD_PREP(MT_RXWI_RATE_INDEX, rate_idx);
-	rateval |= FIELD_PREP(MT_RXWI_RATE_PHY, phy);
-	rateval |= FIELD_PREP(MT_RXWI_RATE_BW, bw);
-	if (rate->flags & IEEE80211_TX_RC_SHORT_GI)
-		rateval |= MT_RXWI_RATE_SGI;
-
-	*nss_val = nss;
-	return cpu_to_le16(rateval);
-}
-
-void mt76x2_mac_wcid_set_drop(struct mt76x2_dev *dev, u8 idx, bool drop)
-{
-	u32 val = mt76_rr(dev, MT_WCID_DROP(idx));
-	u32 bit = MT_WCID_DROP_MASK(idx);
-
-	/* prevent unnecessary writes */
-	if ((val & bit) != (bit * drop))
-		mt76_wr(dev, MT_WCID_DROP(idx), (val & ~bit) | (bit * drop));
-}
-
-void mt76x2_mac_wcid_set_rate(struct mt76x2_dev *dev, struct mt76_wcid *wcid,
-			      const struct ieee80211_tx_rate *rate)
-{
-	spin_lock_bh(&dev->mt76.lock);
-	wcid->tx_rate = mt76x2_mac_tx_rate_val(dev, rate, &wcid->tx_rate_nss);
-	wcid->tx_rate_set = true;
-	spin_unlock_bh(&dev->mt76.lock);
-}
-
-void mt76x2_mac_write_txwi(struct mt76x2_dev *dev, struct mt76x2_txwi *txwi,
-			   struct sk_buff *skb, struct mt76_wcid *wcid,
-			   struct ieee80211_sta *sta)
-{
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-	struct ieee80211_tx_rate *rate = &info->control.rates[0];
-	struct ieee80211_key_conf *key = info->control.hw_key;
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
-	u16 rate_ht_mask = FIELD_PREP(MT_RXWI_RATE_PHY, BIT(1) | BIT(2));
-	u16 txwi_flags = 0;
-	u8 nss;
-	s8 txpwr_adj, max_txpwr_adj;
-	u8 ccmp_pn[8];
-
-	memset(txwi, 0, sizeof(*txwi));
-
-	if (wcid)
-		txwi->wcid = wcid->idx;
-	else
-		txwi->wcid = 0xff;
-
-	txwi->pktid = 1;
-
-	if (wcid && wcid->sw_iv && key) {
-		u64 pn = atomic64_inc_return(&key->tx_pn);
-		ccmp_pn[0] = pn;
-		ccmp_pn[1] = pn >> 8;
-		ccmp_pn[2] = 0;
-		ccmp_pn[3] = 0x20 | (key->keyidx << 6);
-		ccmp_pn[4] = pn >> 16;
-		ccmp_pn[5] = pn >> 24;
-		ccmp_pn[6] = pn >> 32;
-		ccmp_pn[7] = pn >> 40;
-		txwi->iv = *((__le32 *)&ccmp_pn[0]);
-		txwi->eiv = *((__le32 *)&ccmp_pn[1]);
-	}
-
-	spin_lock_bh(&dev->mt76.lock);
-	if (wcid && (rate->idx < 0 || !rate->count)) {
-		txwi->rate = wcid->tx_rate;
-		max_txpwr_adj = wcid->max_txpwr_adj;
-		nss = wcid->tx_rate_nss;
-	} else {
-		txwi->rate = mt76x2_mac_tx_rate_val(dev, rate, &nss);
-		max_txpwr_adj = mt76x2_tx_get_max_txpwr_adj(dev, rate);
-	}
-	spin_unlock_bh(&dev->mt76.lock);
-
-	txpwr_adj = mt76x2_tx_get_txpwr_adj(dev, dev->txpower_conf,
-					    max_txpwr_adj);
-	txwi->ctl2 = FIELD_PREP(MT_TX_PWR_ADJ, txpwr_adj);
-
-	if (mt76xx_rev(dev) >= MT76XX_REV_E4)
-		txwi->txstream = 0x13;
-	else if (mt76xx_rev(dev) >= MT76XX_REV_E3 &&
-		 !(txwi->rate & cpu_to_le16(rate_ht_mask)))
-		txwi->txstream = 0x93;
-
-	if (info->flags & IEEE80211_TX_CTL_LDPC)
-		txwi->rate |= cpu_to_le16(MT_RXWI_RATE_LDPC);
-	if ((info->flags & IEEE80211_TX_CTL_STBC) && nss == 1)
-		txwi->rate |= cpu_to_le16(MT_RXWI_RATE_STBC);
-	if (nss > 1 && sta && sta->smps_mode == IEEE80211_SMPS_DYNAMIC)
-		txwi_flags |= MT_TXWI_FLAGS_MMPS;
-	if (!(info->flags & IEEE80211_TX_CTL_NO_ACK))
-		txwi->ack_ctl |= MT_TXWI_ACK_CTL_REQ;
-	if (info->flags & IEEE80211_TX_CTL_ASSIGN_SEQ)
-		txwi->ack_ctl |= MT_TXWI_ACK_CTL_NSEQ;
-	if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE)
-		txwi->pktid |= MT_TXWI_PKTID_PROBE;
-	if ((info->flags & IEEE80211_TX_CTL_AMPDU) && sta) {
-		u8 ba_size = IEEE80211_MIN_AMPDU_BUF;
-
-		ba_size <<= sta->ht_cap.ampdu_factor;
-		ba_size = min_t(int, 63, ba_size - 1);
-		if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE)
-			ba_size = 0;
-		txwi->ack_ctl |= FIELD_PREP(MT_TXWI_ACK_CTL_BA_WINDOW, ba_size);
-
-		txwi_flags |= MT_TXWI_FLAGS_AMPDU |
-			 FIELD_PREP(MT_TXWI_FLAGS_MPDU_DENSITY,
-				    sta->ht_cap.ampdu_density);
-	}
-
-	if (ieee80211_is_probe_resp(hdr->frame_control) ||
-	    ieee80211_is_beacon(hdr->frame_control))
-		txwi_flags |= MT_TXWI_FLAGS_TS;
-
-	txwi->flags |= cpu_to_le16(txwi_flags);
-	txwi->len_ctl = cpu_to_le16(skb->len);
-}
-
-static void mt76x2_remove_hdr_pad(struct sk_buff *skb, int len)
-{
-	int hdrlen;
-
-	if (!len)
-		return;
-
-	hdrlen = ieee80211_get_hdrlen_from_skb(skb);
-	memmove(skb->data + len, skb->data, hdrlen);
-	skb_pull(skb, len);
-}
-
-static struct mt76_wcid *
-mt76x2_rx_get_sta_wcid(struct mt76x2_dev *dev, u8 idx, bool unicast)
-{
-	struct mt76x2_sta *sta;
-	struct mt76_wcid *wcid;
-
-	if (idx >= ARRAY_SIZE(dev->wcid))
-		return NULL;
-
-	wcid = rcu_dereference(dev->wcid[idx]);
-	if (unicast || !wcid)
-		return wcid;
-
-	sta = container_of(wcid, struct mt76x2_sta, wcid);
-	return &sta->vif->group_wcid;
-}
-
-int mt76x2_mac_process_rx(struct mt76x2_dev *dev, struct sk_buff *skb,
-			  void *rxi)
-{
-	struct mt76_rx_status *status = (struct mt76_rx_status *) skb->cb;
-	struct mt76x2_rxwi *rxwi = rxi;
-	u32 rxinfo = le32_to_cpu(rxwi->rxinfo);
-	u32 ctl = le32_to_cpu(rxwi->ctl);
-	u16 rate = le16_to_cpu(rxwi->rate);
-	u16 tid_sn = le16_to_cpu(rxwi->tid_sn);
-	bool unicast = rxwi->rxinfo & cpu_to_le32(MT_RXINFO_UNICAST);
-	int pad_len = 0;
-	u8 pn_len;
-	u8 wcid;
-	int len;
-
-	if (!test_bit(MT76_STATE_RUNNING, &dev->mt76.state))
-		return -EINVAL;
-
-	if (rxinfo & MT_RXINFO_L2PAD)
-		pad_len += 2;
-
-	if (rxinfo & MT_RXINFO_DECRYPT) {
-		status->flag |= RX_FLAG_DECRYPTED;
-		status->flag |= RX_FLAG_MMIC_STRIPPED;
-		status->flag |= RX_FLAG_MIC_STRIPPED;
-		status->flag |= RX_FLAG_IV_STRIPPED;
-	}
-
-	wcid = FIELD_GET(MT_RXWI_CTL_WCID, ctl);
-	status->wcid = mt76x2_rx_get_sta_wcid(dev, wcid, unicast);
-
-	len = FIELD_GET(MT_RXWI_CTL_MPDU_LEN, ctl);
-	pn_len = FIELD_GET(MT_RXINFO_PN_LEN, rxinfo);
-	if (pn_len) {
-		int offset = ieee80211_get_hdrlen_from_skb(skb) + pad_len;
-		u8 *data = skb->data + offset;
-
-		status->iv[0] = data[7];
-		status->iv[1] = data[6];
-		status->iv[2] = data[5];
-		status->iv[3] = data[4];
-		status->iv[4] = data[1];
-		status->iv[5] = data[0];
-
-		/*
-		 * Driver CCMP validation can't deal with fragments.
-		 * Let mac80211 take care of it.
-		 */
-		if (rxinfo & MT_RXINFO_FRAG) {
-			status->flag &= ~RX_FLAG_IV_STRIPPED;
-		} else {
-			pad_len += pn_len << 2;
-			len -= pn_len << 2;
-		}
-	}
-
-	mt76x2_remove_hdr_pad(skb, pad_len);
-
-	if ((rxinfo & MT_RXINFO_BA) && !(rxinfo & MT_RXINFO_NULL))
-		status->aggr = true;
-
-	if (WARN_ON_ONCE(len > skb->len))
-		return -EINVAL;
-
-	pskb_trim(skb, len);
-	status->chains = BIT(0) | BIT(1);
-	status->chain_signal[0] = mt76x2_phy_get_rssi(dev, rxwi->rssi[0], 0);
-	status->chain_signal[1] = mt76x2_phy_get_rssi(dev, rxwi->rssi[1], 1);
-	status->signal = max(status->chain_signal[0], status->chain_signal[1]);
-	status->freq = dev->mt76.chandef.chan->center_freq;
-	status->band = dev->mt76.chandef.chan->band;
-
-	status->tid = FIELD_GET(MT_RXWI_TID, tid_sn);
-	status->seqno = FIELD_GET(MT_RXWI_SN, tid_sn);
-
-	return mt76x2_mac_process_rate(status, rate);
-}
-
-static int
-mt76x2_mac_process_tx_rate(struct ieee80211_tx_rate *txrate, u16 rate,
-			   enum nl80211_band band)
-{
-	u8 idx = FIELD_GET(MT_RXWI_RATE_INDEX, rate);
-
-	txrate->idx = 0;
-	txrate->flags = 0;
-	txrate->count = 1;
-
-	switch (FIELD_GET(MT_RXWI_RATE_PHY, rate)) {
-	case MT_PHY_TYPE_OFDM:
-		if (band == NL80211_BAND_2GHZ)
-			idx += 4;
-
-		txrate->idx = idx;
-		return 0;
-	case MT_PHY_TYPE_CCK:
-		if (idx >= 8)
-			idx -= 8;
-
-		txrate->idx = idx;
-		return 0;
-	case MT_PHY_TYPE_HT_GF:
-		txrate->flags |= IEEE80211_TX_RC_GREEN_FIELD;
-		/* fall through */
-	case MT_PHY_TYPE_HT:
-		txrate->flags |= IEEE80211_TX_RC_MCS;
-		txrate->idx = idx;
-		break;
-	case MT_PHY_TYPE_VHT:
-		txrate->flags |= IEEE80211_TX_RC_VHT_MCS;
-		txrate->idx = idx;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	switch (FIELD_GET(MT_RXWI_RATE_BW, rate)) {
-	case MT_PHY_BW_20:
-		break;
-	case MT_PHY_BW_40:
-		txrate->flags |= IEEE80211_TX_RC_40_MHZ_WIDTH;
-		break;
-	case MT_PHY_BW_80:
-		txrate->flags |= IEEE80211_TX_RC_80_MHZ_WIDTH;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if (rate & MT_RXWI_RATE_SGI)
-		txrate->flags |= IEEE80211_TX_RC_SHORT_GI;
-
-	return 0;
-}
-
-static void
-mt76x2_mac_fill_tx_status(struct mt76x2_dev *dev,
-			  struct ieee80211_tx_info *info,
-			  struct mt76x2_tx_status *st, int n_frames)
-{
-	struct ieee80211_tx_rate *rate = info->status.rates;
-	int cur_idx, last_rate;
-	int i;
-
-	if (!n_frames)
-		return;
-
-	last_rate = min_t(int, st->retry, IEEE80211_TX_MAX_RATES - 1);
-	mt76x2_mac_process_tx_rate(&rate[last_rate], st->rate,
-				 dev->mt76.chandef.chan->band);
-	if (last_rate < IEEE80211_TX_MAX_RATES - 1)
-		rate[last_rate + 1].idx = -1;
-
-	cur_idx = rate[last_rate].idx + st->retry;
-	for (i = 0; i <= last_rate; i++) {
-		rate[i].flags = rate[last_rate].flags;
-		rate[i].idx = max_t(int, 0, cur_idx - i);
-		rate[i].count = 1;
-	}
-
-	if (last_rate > 0)
-		rate[last_rate - 1].count = st->retry + 1 - last_rate;
-
-	info->status.ampdu_len = n_frames;
-	info->status.ampdu_ack_len = st->success ? n_frames : 0;
-
-	if (st->pktid & MT_TXWI_PKTID_PROBE)
-		info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE;
-
-	if (st->aggr)
-		info->flags |= IEEE80211_TX_CTL_AMPDU |
-			       IEEE80211_TX_STAT_AMPDU;
-
-	if (!st->ack_req)
-		info->flags |= IEEE80211_TX_CTL_NO_ACK;
-	else if (st->success)
-		info->flags |= IEEE80211_TX_STAT_ACK;
-}
-
-static void
-mt76x2_send_tx_status(struct mt76x2_dev *dev, struct mt76x2_tx_status *stat,
-		      u8 *update)
-{
-	struct ieee80211_tx_info info = {};
-	struct ieee80211_sta *sta = NULL;
-	struct mt76_wcid *wcid = NULL;
-	struct mt76x2_sta *msta = NULL;
-
-	rcu_read_lock();
-	if (stat->wcid < ARRAY_SIZE(dev->wcid))
-		wcid = rcu_dereference(dev->wcid[stat->wcid]);
-
-	if (wcid) {
-		void *priv;
-
-		priv = msta = container_of(wcid, struct mt76x2_sta, wcid);
-		sta = container_of(priv, struct ieee80211_sta,
-				   drv_priv);
-	}
-
-	if (msta && stat->aggr) {
-		u32 stat_val, stat_cache;
-
-		stat_val = stat->rate;
-		stat_val |= ((u32) stat->retry) << 16;
-		stat_cache = msta->status.rate;
-		stat_cache |= ((u32) msta->status.retry) << 16;
-
-		if (*update == 0 && stat_val == stat_cache &&
-		    stat->wcid == msta->status.wcid && msta->n_frames < 32) {
-			msta->n_frames++;
-			goto out;
-		}
-
-		mt76x2_mac_fill_tx_status(dev, &info, &msta->status,
-					  msta->n_frames);
-
-		msta->status = *stat;
-		msta->n_frames = 1;
-		*update = 0;
-	} else {
-		mt76x2_mac_fill_tx_status(dev, &info, stat, 1);
-		*update = 1;
-	}
-
-	ieee80211_tx_status_noskb(mt76_hw(dev), sta, &info);
-
-out:
-	rcu_read_unlock();
-}
-
 void mt76x2_mac_poll_tx_status(struct mt76x2_dev *dev, bool irq)
 {
 	struct mt76x2_tx_status stat = {};
 	unsigned long flags;
 	u8 update = 1;
+	bool ret;
 
 	if (!test_bit(MT76_STATE_RUNNING, &dev->mt76.state))
 		return;
@@ -529,26 +41,13 @@ void mt76x2_mac_poll_tx_status(struct mt76x2_dev *dev, bool irq)
 	trace_mac_txstat_poll(dev);
 
 	while (!irq || !kfifo_is_full(&dev->txstatus_fifo)) {
-		u32 stat1, stat2;
-
 		spin_lock_irqsave(&dev->irq_lock, flags);
-		stat2 = mt76_rr(dev, MT_TX_STAT_FIFO_EXT);
-		stat1 = mt76_rr(dev, MT_TX_STAT_FIFO);
-		if (!(stat1 & MT_TX_STAT_FIFO_VALID)) {
-			spin_unlock_irqrestore(&dev->irq_lock, flags);
-			break;
-		}
-
+		ret = mt76x2_mac_load_tx_status(dev, &stat);
 		spin_unlock_irqrestore(&dev->irq_lock, flags);
 
-		stat.valid = 1;
-		stat.success = !!(stat1 & MT_TX_STAT_FIFO_SUCCESS);
-		stat.aggr = !!(stat1 & MT_TX_STAT_FIFO_AGGR);
-		stat.ack_req = !!(stat1 & MT_TX_STAT_FIFO_ACKREQ);
-		stat.wcid = FIELD_GET(MT_TX_STAT_FIFO_WCID, stat1);
-		stat.rate = FIELD_GET(MT_TX_STAT_FIFO_RATE, stat1);
-		stat.retry = FIELD_GET(MT_TX_STAT_FIFO_EXT_RETRY, stat2);
-		stat.pktid = FIELD_GET(MT_TX_STAT_FIFO_EXT_PKTID, stat2);
+		if (!ret)
+			break;
+
 		trace_mac_txstat_fetch(dev, &stat);
 
 		if (!irq) {
@@ -597,104 +96,6 @@ void mt76x2_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue *q,
 		dev_kfree_skb_any(e->skb);
 }
 
-static enum mt76x2_cipher_type
-mt76x2_mac_get_key_info(struct ieee80211_key_conf *key, u8 *key_data)
-{
-	memset(key_data, 0, 32);
-	if (!key)
-		return MT_CIPHER_NONE;
-
-	if (key->keylen > 32)
-		return MT_CIPHER_NONE;
-
-	memcpy(key_data, key->key, key->keylen);
-
-	switch (key->cipher) {
-	case WLAN_CIPHER_SUITE_WEP40:
-		return MT_CIPHER_WEP40;
-	case WLAN_CIPHER_SUITE_WEP104:
-		return MT_CIPHER_WEP104;
-	case WLAN_CIPHER_SUITE_TKIP:
-		return MT_CIPHER_TKIP;
-	case WLAN_CIPHER_SUITE_CCMP:
-		return MT_CIPHER_AES_CCMP;
-	default:
-		return MT_CIPHER_NONE;
-	}
-}
-
-void mt76x2_mac_wcid_setup(struct mt76x2_dev *dev, u8 idx, u8 vif_idx, u8 *mac)
-{
-	struct mt76_wcid_addr addr = {};
-	u32 attr;
-
-	attr = FIELD_PREP(MT_WCID_ATTR_BSS_IDX, vif_idx & 7) |
-	       FIELD_PREP(MT_WCID_ATTR_BSS_IDX_EXT, !!(vif_idx & 8));
-
-	mt76_wr(dev, MT_WCID_ATTR(idx), attr);
-
-	mt76_wr(dev, MT_WCID_TX_RATE(idx), 0);
-	mt76_wr(dev, MT_WCID_TX_RATE(idx) + 4, 0);
-
-	if (idx >= 128)
-		return;
-
-	if (mac)
-		memcpy(addr.macaddr, mac, ETH_ALEN);
-
-	mt76_wr_copy(dev, MT_WCID_ADDR(idx), &addr, sizeof(addr));
-}
-
-int mt76x2_mac_wcid_set_key(struct mt76x2_dev *dev, u8 idx,
-			    struct ieee80211_key_conf *key)
-{
-	enum mt76x2_cipher_type cipher;
-	u8 key_data[32];
-	u8 iv_data[8];
-
-	cipher = mt76x2_mac_get_key_info(key, key_data);
-	if (cipher == MT_CIPHER_NONE && key)
-		return -EOPNOTSUPP;
-
-	mt76_rmw_field(dev, MT_WCID_ATTR(idx), MT_WCID_ATTR_PKEY_MODE, cipher);
-	mt76_wr_copy(dev, MT_WCID_KEY(idx), key_data, sizeof(key_data));
-
-	memset(iv_data, 0, sizeof(iv_data));
-	if (key) {
-		mt76_rmw_field(dev, MT_WCID_ATTR(idx), MT_WCID_ATTR_PAIRWISE,
-			       !!(key->flags & IEEE80211_KEY_FLAG_PAIRWISE));
-		iv_data[3] = key->keyidx << 6;
-		if (cipher >= MT_CIPHER_TKIP)
-			iv_data[3] |= 0x20;
-	}
-
-	mt76_wr_copy(dev, MT_WCID_IV(idx), iv_data, sizeof(iv_data));
-
-	return 0;
-}
-
-int mt76x2_mac_shared_key_setup(struct mt76x2_dev *dev, u8 vif_idx, u8 key_idx,
-			      struct ieee80211_key_conf *key)
-{
-	enum mt76x2_cipher_type cipher;
-	u8 key_data[32];
-	u32 val;
-
-	cipher = mt76x2_mac_get_key_info(key, key_data);
-	if (cipher == MT_CIPHER_NONE && key)
-		return -EOPNOTSUPP;
-
-	val = mt76_rr(dev, MT_SKEY_MODE(vif_idx));
-	val &= ~(MT_SKEY_MODE_MASK << MT_SKEY_MODE_SHIFT(vif_idx, key_idx));
-	val |= cipher << MT_SKEY_MODE_SHIFT(vif_idx, key_idx);
-	mt76_wr(dev, MT_SKEY_MODE(vif_idx), val);
-
-	mt76_wr_copy(dev, MT_SKEY(vif_idx, key_idx), key_data,
-		     sizeof(key_data));
-
-	return 0;
-}
-
 static int
 mt76_write_beacon(struct mt76x2_dev *dev, int offset, struct sk_buff *skb)
 {
@@ -704,7 +105,7 @@ mt76_write_beacon(struct mt76x2_dev *dev, int offset, struct sk_buff *skb)
 	if (WARN_ON_ONCE(beacon_len < skb->len + sizeof(struct mt76x2_txwi)))
 		return -ENOSPC;
 
-	mt76x2_mac_write_txwi(dev, &txwi, skb, NULL, NULL);
+	mt76x2_mac_write_txwi(dev, &txwi, skb, NULL, NULL, skb->len);
 
 	mt76_wr_copy(dev, offset, &txwi, sizeof(txwi));
 	offset += sizeof(txwi);
@@ -839,3 +240,33 @@ void mt76x2_mac_work(struct work_struct *work)
 	ieee80211_queue_delayed_work(mt76_hw(dev), &dev->mac_work,
 				     MT_CALIBRATE_INTERVAL);
 }
+
+void mt76x2_mac_set_tx_protection(struct mt76x2_dev *dev, u32 val)
+{
+	u32 data = 0;
+
+	if (val != ~0)
+		data = FIELD_PREP(MT_PROT_CFG_CTRL, 1) |
+		       MT_PROT_CFG_RTS_THRESH;
+
+	mt76_rmw_field(dev, MT_TX_RTS_CFG, MT_TX_RTS_CFG_THRESH, val);
+
+	mt76_rmw(dev, MT_CCK_PROT_CFG,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_OFDM_PROT_CFG,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_MM20_PROT_CFG,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_MM40_PROT_CFG,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_GF20_PROT_CFG,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_GF40_PROT_CFG,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_TX_PROT_CFG6,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_TX_PROT_CFG7,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_TX_PROT_CFG8,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.h b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.h
index c048cd06df6b..5af0107ba748 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.h
@@ -166,7 +166,7 @@ int mt76x2_mac_process_rx(struct mt76x2_dev *dev, struct sk_buff *skb,
 			  void *rxi);
 void mt76x2_mac_write_txwi(struct mt76x2_dev *dev, struct mt76x2_txwi *txwi,
 			   struct sk_buff *skb, struct mt76_wcid *wcid,
-			   struct ieee80211_sta *sta);
+			   struct ieee80211_sta *sta, int len);
 void mt76x2_mac_wcid_setup(struct mt76x2_dev *dev, u8 idx, u8 vif_idx, u8 *mac);
 int mt76x2_mac_wcid_set_key(struct mt76x2_dev *dev, u8 idx,
 			    struct ieee80211_key_conf *key);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_mac_common.c b/drivers/net/wireless/mediatek/mt76/mt76x2_mac_common.c
new file mode 100644
index 000000000000..6542644bc325
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_mac_common.c
@@ -0,0 +1,699 @@
+/*
+ * Copyright (C) 2016 Felix Fietkau <nbd@nbd.name>
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76x2.h"
+
+void mt76x2_mac_stop(struct mt76x2_dev *dev, bool force)
+{
+	bool stopped = false;
+	u32 rts_cfg;
+	int i;
+
+	mt76_wr(dev, MT_MAC_SYS_CTRL, 0);
+
+	rts_cfg = mt76_rr(dev, MT_TX_RTS_CFG);
+	mt76_wr(dev, MT_TX_RTS_CFG, rts_cfg & ~MT_TX_RTS_CFG_RETRY_LIMIT);
+
+	/* Wait for MAC to become idle */
+	for (i = 0; i < 300; i++) {
+		if ((mt76_rr(dev, MT_MAC_STATUS) &
+		     (MT_MAC_STATUS_RX | MT_MAC_STATUS_TX)) ||
+		    mt76_rr(dev, MT_BBP(IBI, 12))) {
+			udelay(1);
+			continue;
+		}
+
+		stopped = true;
+		break;
+	}
+
+	if (force && !stopped) {
+		mt76_set(dev, MT_BBP(CORE, 4), BIT(1));
+		mt76_clear(dev, MT_BBP(CORE, 4), BIT(1));
+
+		mt76_set(dev, MT_BBP(CORE, 4), BIT(0));
+		mt76_clear(dev, MT_BBP(CORE, 4), BIT(0));
+	}
+
+	mt76_wr(dev, MT_TX_RTS_CFG, rts_cfg);
+}
+EXPORT_SYMBOL_GPL(mt76x2_mac_stop);
+
+bool mt76x2_mac_load_tx_status(struct mt76x2_dev *dev,
+			       struct mt76x2_tx_status *stat)
+{
+	u32 stat1, stat2;
+
+	stat2 = mt76_rr(dev, MT_TX_STAT_FIFO_EXT);
+	stat1 = mt76_rr(dev, MT_TX_STAT_FIFO);
+
+	stat->valid = !!(stat1 & MT_TX_STAT_FIFO_VALID);
+	if (!stat->valid)
+		return false;
+
+	stat->success = !!(stat1 & MT_TX_STAT_FIFO_SUCCESS);
+	stat->aggr = !!(stat1 & MT_TX_STAT_FIFO_AGGR);
+	stat->ack_req = !!(stat1 & MT_TX_STAT_FIFO_ACKREQ);
+	stat->wcid = FIELD_GET(MT_TX_STAT_FIFO_WCID, stat1);
+	stat->rate = FIELD_GET(MT_TX_STAT_FIFO_RATE, stat1);
+
+	stat->retry = FIELD_GET(MT_TX_STAT_FIFO_EXT_RETRY, stat2);
+	stat->pktid = FIELD_GET(MT_TX_STAT_FIFO_EXT_PKTID, stat2);
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(mt76x2_mac_load_tx_status);
+
+static int
+mt76x2_mac_process_tx_rate(struct ieee80211_tx_rate *txrate, u16 rate,
+			   enum nl80211_band band)
+{
+	u8 idx = FIELD_GET(MT_RXWI_RATE_INDEX, rate);
+
+	txrate->idx = 0;
+	txrate->flags = 0;
+	txrate->count = 1;
+
+	switch (FIELD_GET(MT_RXWI_RATE_PHY, rate)) {
+	case MT_PHY_TYPE_OFDM:
+		if (band == NL80211_BAND_2GHZ)
+			idx += 4;
+
+		txrate->idx = idx;
+		return 0;
+	case MT_PHY_TYPE_CCK:
+		if (idx >= 8)
+			idx -= 8;
+
+		txrate->idx = idx;
+		return 0;
+	case MT_PHY_TYPE_HT_GF:
+		txrate->flags |= IEEE80211_TX_RC_GREEN_FIELD;
+		/* fall through */
+	case MT_PHY_TYPE_HT:
+		txrate->flags |= IEEE80211_TX_RC_MCS;
+		txrate->idx = idx;
+		break;
+	case MT_PHY_TYPE_VHT:
+		txrate->flags |= IEEE80211_TX_RC_VHT_MCS;
+		txrate->idx = idx;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (FIELD_GET(MT_RXWI_RATE_BW, rate)) {
+	case MT_PHY_BW_20:
+		break;
+	case MT_PHY_BW_40:
+		txrate->flags |= IEEE80211_TX_RC_40_MHZ_WIDTH;
+		break;
+	case MT_PHY_BW_80:
+		txrate->flags |= IEEE80211_TX_RC_80_MHZ_WIDTH;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (rate & MT_RXWI_RATE_SGI)
+		txrate->flags |= IEEE80211_TX_RC_SHORT_GI;
+
+	return 0;
+}
+
+static void
+mt76x2_mac_fill_tx_status(struct mt76x2_dev *dev,
+			  struct ieee80211_tx_info *info,
+			  struct mt76x2_tx_status *st, int n_frames)
+{
+	struct ieee80211_tx_rate *rate = info->status.rates;
+	int cur_idx, last_rate;
+	int i;
+
+	if (!n_frames)
+		return;
+
+	last_rate = min_t(int, st->retry, IEEE80211_TX_MAX_RATES - 1);
+	mt76x2_mac_process_tx_rate(&rate[last_rate], st->rate,
+				 dev->mt76.chandef.chan->band);
+	if (last_rate < IEEE80211_TX_MAX_RATES - 1)
+		rate[last_rate + 1].idx = -1;
+
+	cur_idx = rate[last_rate].idx + last_rate;
+	for (i = 0; i <= last_rate; i++) {
+		rate[i].flags = rate[last_rate].flags;
+		rate[i].idx = max_t(int, 0, cur_idx - i);
+		rate[i].count = 1;
+	}
+	rate[last_rate].count = st->retry + 1 - last_rate;
+
+	info->status.ampdu_len = n_frames;
+	info->status.ampdu_ack_len = st->success ? n_frames : 0;
+
+	if (st->pktid & MT_TXWI_PKTID_PROBE)
+		info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE;
+
+	if (st->aggr)
+		info->flags |= IEEE80211_TX_CTL_AMPDU |
+			       IEEE80211_TX_STAT_AMPDU;
+
+	if (!st->ack_req)
+		info->flags |= IEEE80211_TX_CTL_NO_ACK;
+	else if (st->success)
+		info->flags |= IEEE80211_TX_STAT_ACK;
+}
+
+void mt76x2_send_tx_status(struct mt76x2_dev *dev,
+			   struct mt76x2_tx_status *stat, u8 *update)
+{
+	struct ieee80211_tx_info info = {};
+	struct ieee80211_sta *sta = NULL;
+	struct mt76_wcid *wcid = NULL;
+	struct mt76x2_sta *msta = NULL;
+
+	rcu_read_lock();
+	if (stat->wcid < ARRAY_SIZE(dev->wcid))
+		wcid = rcu_dereference(dev->wcid[stat->wcid]);
+
+	if (wcid) {
+		void *priv;
+
+		priv = msta = container_of(wcid, struct mt76x2_sta, wcid);
+		sta = container_of(priv, struct ieee80211_sta,
+				   drv_priv);
+	}
+
+	if (msta && stat->aggr) {
+		u32 stat_val, stat_cache;
+
+		stat_val = stat->rate;
+		stat_val |= ((u32) stat->retry) << 16;
+		stat_cache = msta->status.rate;
+		stat_cache |= ((u32) msta->status.retry) << 16;
+
+		if (*update == 0 && stat_val == stat_cache &&
+		    stat->wcid == msta->status.wcid && msta->n_frames < 32) {
+			msta->n_frames++;
+			goto out;
+		}
+
+		mt76x2_mac_fill_tx_status(dev, &info, &msta->status,
+					  msta->n_frames);
+
+		msta->status = *stat;
+		msta->n_frames = 1;
+		*update = 0;
+	} else {
+		mt76x2_mac_fill_tx_status(dev, &info, stat, 1);
+		*update = 1;
+	}
+
+	ieee80211_tx_status_noskb(mt76_hw(dev), sta, &info);
+
+out:
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(mt76x2_send_tx_status);
+
+static enum mt76x2_cipher_type
+mt76x2_mac_get_key_info(struct ieee80211_key_conf *key, u8 *key_data)
+{
+	memset(key_data, 0, 32);
+	if (!key)
+		return MT_CIPHER_NONE;
+
+	if (key->keylen > 32)
+		return MT_CIPHER_NONE;
+
+	memcpy(key_data, key->key, key->keylen);
+
+	switch (key->cipher) {
+	case WLAN_CIPHER_SUITE_WEP40:
+		return MT_CIPHER_WEP40;
+	case WLAN_CIPHER_SUITE_WEP104:
+		return MT_CIPHER_WEP104;
+	case WLAN_CIPHER_SUITE_TKIP:
+		return MT_CIPHER_TKIP;
+	case WLAN_CIPHER_SUITE_CCMP:
+		return MT_CIPHER_AES_CCMP;
+	default:
+		return MT_CIPHER_NONE;
+	}
+}
+
+int mt76x2_mac_shared_key_setup(struct mt76x2_dev *dev, u8 vif_idx, u8 key_idx,
+				struct ieee80211_key_conf *key)
+{
+	enum mt76x2_cipher_type cipher;
+	u8 key_data[32];
+	u32 val;
+
+	cipher = mt76x2_mac_get_key_info(key, key_data);
+	if (cipher == MT_CIPHER_NONE && key)
+		return -EOPNOTSUPP;
+
+	val = mt76_rr(dev, MT_SKEY_MODE(vif_idx));
+	val &= ~(MT_SKEY_MODE_MASK << MT_SKEY_MODE_SHIFT(vif_idx, key_idx));
+	val |= cipher << MT_SKEY_MODE_SHIFT(vif_idx, key_idx);
+	mt76_wr(dev, MT_SKEY_MODE(vif_idx), val);
+
+	mt76_wr_copy(dev, MT_SKEY(vif_idx, key_idx), key_data,
+		     sizeof(key_data));
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt76x2_mac_shared_key_setup);
+
+int mt76x2_mac_wcid_set_key(struct mt76x2_dev *dev, u8 idx,
+			    struct ieee80211_key_conf *key)
+{
+	enum mt76x2_cipher_type cipher;
+	u8 key_data[32];
+	u8 iv_data[8];
+
+	cipher = mt76x2_mac_get_key_info(key, key_data);
+	if (cipher == MT_CIPHER_NONE && key)
+		return -EOPNOTSUPP;
+
+	mt76_rmw_field(dev, MT_WCID_ATTR(idx), MT_WCID_ATTR_PKEY_MODE, cipher);
+	mt76_wr_copy(dev, MT_WCID_KEY(idx), key_data, sizeof(key_data));
+
+	memset(iv_data, 0, sizeof(iv_data));
+	if (key) {
+		mt76_rmw_field(dev, MT_WCID_ATTR(idx), MT_WCID_ATTR_PAIRWISE,
+			       !!(key->flags & IEEE80211_KEY_FLAG_PAIRWISE));
+		iv_data[3] = key->keyidx << 6;
+		if (cipher >= MT_CIPHER_TKIP)
+			iv_data[3] |= 0x20;
+	}
+
+	mt76_wr_copy(dev, MT_WCID_IV(idx), iv_data, sizeof(iv_data));
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt76x2_mac_wcid_set_key);
+
+static __le16
+mt76x2_mac_tx_rate_val(struct mt76x2_dev *dev,
+		       const struct ieee80211_tx_rate *rate, u8 *nss_val)
+{
+	u16 rateval;
+	u8 phy, rate_idx;
+	u8 nss = 1;
+	u8 bw = 0;
+
+	if (rate->flags & IEEE80211_TX_RC_VHT_MCS) {
+		rate_idx = rate->idx;
+		nss = 1 + (rate->idx >> 4);
+		phy = MT_PHY_TYPE_VHT;
+		if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
+			bw = 2;
+		else if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
+			bw = 1;
+	} else if (rate->flags & IEEE80211_TX_RC_MCS) {
+		rate_idx = rate->idx;
+		nss = 1 + (rate->idx >> 3);
+		phy = MT_PHY_TYPE_HT;
+		if (rate->flags & IEEE80211_TX_RC_GREEN_FIELD)
+			phy = MT_PHY_TYPE_HT_GF;
+		if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
+			bw = 1;
+	} else {
+		const struct ieee80211_rate *r;
+		int band = dev->mt76.chandef.chan->band;
+		u16 val;
+
+		r = &mt76_hw(dev)->wiphy->bands[band]->bitrates[rate->idx];
+		if (rate->flags & IEEE80211_TX_RC_USE_SHORT_PREAMBLE)
+			val = r->hw_value_short;
+		else
+			val = r->hw_value;
+
+		phy = val >> 8;
+		rate_idx = val & 0xff;
+		bw = 0;
+	}
+
+	rateval = FIELD_PREP(MT_RXWI_RATE_INDEX, rate_idx);
+	rateval |= FIELD_PREP(MT_RXWI_RATE_PHY, phy);
+	rateval |= FIELD_PREP(MT_RXWI_RATE_BW, bw);
+	if (rate->flags & IEEE80211_TX_RC_SHORT_GI)
+		rateval |= MT_RXWI_RATE_SGI;
+
+	*nss_val = nss;
+	return cpu_to_le16(rateval);
+}
+
+void mt76x2_mac_wcid_set_rate(struct mt76x2_dev *dev, struct mt76_wcid *wcid,
+			      const struct ieee80211_tx_rate *rate)
+{
+	spin_lock_bh(&dev->mt76.lock);
+	wcid->tx_rate = mt76x2_mac_tx_rate_val(dev, rate, &wcid->tx_rate_nss);
+	wcid->tx_rate_set = true;
+	spin_unlock_bh(&dev->mt76.lock);
+}
+EXPORT_SYMBOL_GPL(mt76x2_mac_wcid_set_rate);
+
+void mt76x2_mac_write_txwi(struct mt76x2_dev *dev, struct mt76x2_txwi *txwi,
+			   struct sk_buff *skb, struct mt76_wcid *wcid,
+			   struct ieee80211_sta *sta, int len)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ieee80211_tx_rate *rate = &info->control.rates[0];
+	struct ieee80211_key_conf *key = info->control.hw_key;
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
+	u16 rate_ht_mask = FIELD_PREP(MT_RXWI_RATE_PHY, BIT(1) | BIT(2));
+	u16 txwi_flags = 0;
+	u8 nss;
+	s8 txpwr_adj, max_txpwr_adj;
+	u8 ccmp_pn[8];
+
+	memset(txwi, 0, sizeof(*txwi));
+
+	if (wcid)
+		txwi->wcid = wcid->idx;
+	else
+		txwi->wcid = 0xff;
+
+	txwi->pktid = 1;
+
+	if (wcid && wcid->sw_iv && key) {
+		u64 pn = atomic64_inc_return(&key->tx_pn);
+		ccmp_pn[0] = pn;
+		ccmp_pn[1] = pn >> 8;
+		ccmp_pn[2] = 0;
+		ccmp_pn[3] = 0x20 | (key->keyidx << 6);
+		ccmp_pn[4] = pn >> 16;
+		ccmp_pn[5] = pn >> 24;
+		ccmp_pn[6] = pn >> 32;
+		ccmp_pn[7] = pn >> 40;
+		txwi->iv = *((__le32 *)&ccmp_pn[0]);
+		txwi->eiv = *((__le32 *)&ccmp_pn[1]);
+	}
+
+	spin_lock_bh(&dev->mt76.lock);
+	if (wcid && (rate->idx < 0 || !rate->count)) {
+		txwi->rate = wcid->tx_rate;
+		max_txpwr_adj = wcid->max_txpwr_adj;
+		nss = wcid->tx_rate_nss;
+	} else {
+		txwi->rate = mt76x2_mac_tx_rate_val(dev, rate, &nss);
+		max_txpwr_adj = mt76x2_tx_get_max_txpwr_adj(dev, rate);
+	}
+	spin_unlock_bh(&dev->mt76.lock);
+
+	txpwr_adj = mt76x2_tx_get_txpwr_adj(dev, dev->txpower_conf,
+					    max_txpwr_adj);
+	txwi->ctl2 = FIELD_PREP(MT_TX_PWR_ADJ, txpwr_adj);
+
+	if (mt76xx_rev(dev) >= MT76XX_REV_E4)
+		txwi->txstream = 0x13;
+	else if (mt76xx_rev(dev) >= MT76XX_REV_E3 &&
+		 !(txwi->rate & cpu_to_le16(rate_ht_mask)))
+		txwi->txstream = 0x93;
+
+	if (info->flags & IEEE80211_TX_CTL_LDPC)
+		txwi->rate |= cpu_to_le16(MT_RXWI_RATE_LDPC);
+	if ((info->flags & IEEE80211_TX_CTL_STBC) && nss == 1)
+		txwi->rate |= cpu_to_le16(MT_RXWI_RATE_STBC);
+	if (nss > 1 && sta && sta->smps_mode == IEEE80211_SMPS_DYNAMIC)
+		txwi_flags |= MT_TXWI_FLAGS_MMPS;
+	if (!(info->flags & IEEE80211_TX_CTL_NO_ACK))
+		txwi->ack_ctl |= MT_TXWI_ACK_CTL_REQ;
+	if (info->flags & IEEE80211_TX_CTL_ASSIGN_SEQ)
+		txwi->ack_ctl |= MT_TXWI_ACK_CTL_NSEQ;
+	if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE)
+		txwi->pktid |= MT_TXWI_PKTID_PROBE;
+	if ((info->flags & IEEE80211_TX_CTL_AMPDU) && sta) {
+		u8 ba_size = IEEE80211_MIN_AMPDU_BUF;
+
+		ba_size <<= sta->ht_cap.ampdu_factor;
+		ba_size = min_t(int, 63, ba_size - 1);
+		if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE)
+			ba_size = 0;
+		txwi->ack_ctl |= FIELD_PREP(MT_TXWI_ACK_CTL_BA_WINDOW, ba_size);
+
+		txwi_flags |= MT_TXWI_FLAGS_AMPDU |
+			 FIELD_PREP(MT_TXWI_FLAGS_MPDU_DENSITY,
+				    sta->ht_cap.ampdu_density);
+	}
+
+	if (ieee80211_is_probe_resp(hdr->frame_control) ||
+	    ieee80211_is_beacon(hdr->frame_control))
+		txwi_flags |= MT_TXWI_FLAGS_TS;
+
+	txwi->flags |= cpu_to_le16(txwi_flags);
+	txwi->len_ctl = cpu_to_le16(len);
+}
+EXPORT_SYMBOL_GPL(mt76x2_mac_write_txwi);
+
+void mt76x2_mac_wcid_set_drop(struct mt76x2_dev *dev, u8 idx, bool drop)
+{
+	u32 val = mt76_rr(dev, MT_WCID_DROP(idx));
+	u32 bit = MT_WCID_DROP_MASK(idx);
+
+	/* prevent unnecessary writes */
+	if ((val & bit) != (bit * drop))
+		mt76_wr(dev, MT_WCID_DROP(idx), (val & ~bit) | (bit * drop));
+}
+EXPORT_SYMBOL_GPL(mt76x2_mac_wcid_set_drop);
+
+void mt76x2_mac_wcid_setup(struct mt76x2_dev *dev, u8 idx, u8 vif_idx, u8 *mac)
+{
+	struct mt76_wcid_addr addr = {};
+	u32 attr;
+
+	attr = FIELD_PREP(MT_WCID_ATTR_BSS_IDX, vif_idx & 7) |
+	       FIELD_PREP(MT_WCID_ATTR_BSS_IDX_EXT, !!(vif_idx & 8));
+
+	mt76_wr(dev, MT_WCID_ATTR(idx), attr);
+
+	mt76_wr(dev, MT_WCID_TX_RATE(idx), 0);
+	mt76_wr(dev, MT_WCID_TX_RATE(idx) + 4, 0);
+
+	if (idx >= 128)
+		return;
+
+	if (mac)
+		memcpy(addr.macaddr, mac, ETH_ALEN);
+
+	mt76_wr_copy(dev, MT_WCID_ADDR(idx), &addr, sizeof(addr));
+}
+EXPORT_SYMBOL_GPL(mt76x2_mac_wcid_setup);
+
+static int
+mt76x2_mac_process_rate(struct mt76_rx_status *status, u16 rate)
+{
+	u8 idx = FIELD_GET(MT_RXWI_RATE_INDEX, rate);
+
+	switch (FIELD_GET(MT_RXWI_RATE_PHY, rate)) {
+	case MT_PHY_TYPE_OFDM:
+		if (idx >= 8)
+			idx = 0;
+
+		if (status->band == NL80211_BAND_2GHZ)
+			idx += 4;
+
+		status->rate_idx = idx;
+		return 0;
+	case MT_PHY_TYPE_CCK:
+		if (idx >= 8) {
+			idx -= 8;
+			status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
+		}
+
+		if (idx >= 4)
+			idx = 0;
+
+		status->rate_idx = idx;
+		return 0;
+	case MT_PHY_TYPE_HT_GF:
+		status->enc_flags |= RX_ENC_FLAG_HT_GF;
+		/* fall through */
+	case MT_PHY_TYPE_HT:
+		status->encoding = RX_ENC_HT;
+		status->rate_idx = idx;
+		break;
+	case MT_PHY_TYPE_VHT:
+		status->encoding = RX_ENC_VHT;
+		status->rate_idx = FIELD_GET(MT_RATE_INDEX_VHT_IDX, idx);
+		status->nss = FIELD_GET(MT_RATE_INDEX_VHT_NSS, idx) + 1;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (rate & MT_RXWI_RATE_LDPC)
+		status->enc_flags |= RX_ENC_FLAG_LDPC;
+
+	if (rate & MT_RXWI_RATE_SGI)
+		status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
+
+	if (rate & MT_RXWI_RATE_STBC)
+		status->enc_flags |= 1 << RX_ENC_FLAG_STBC_SHIFT;
+
+	switch (FIELD_GET(MT_RXWI_RATE_BW, rate)) {
+	case MT_PHY_BW_20:
+		break;
+	case MT_PHY_BW_40:
+		status->bw = RATE_INFO_BW_40;
+		break;
+	case MT_PHY_BW_80:
+		status->bw = RATE_INFO_BW_80;
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static void mt76x2_remove_hdr_pad(struct sk_buff *skb, int len)
+{
+	int hdrlen;
+
+	if (!len)
+		return;
+
+	hdrlen = ieee80211_get_hdrlen_from_skb(skb);
+	memmove(skb->data + len, skb->data, hdrlen);
+	skb_pull(skb, len);
+}
+
+int mt76x2_mac_get_rssi(struct mt76x2_dev *dev, s8 rssi, int chain)
+{
+	struct mt76x2_rx_freq_cal *cal = &dev->cal.rx;
+
+	rssi += cal->rssi_offset[chain];
+	rssi -= cal->lna_gain;
+
+	return rssi;
+}
+
+static struct mt76x2_sta *
+mt76x2_rx_get_sta(struct mt76x2_dev *dev, u8 idx)
+{
+	struct mt76_wcid *wcid;
+
+	if (idx >= ARRAY_SIZE(dev->wcid))
+		return NULL;
+
+	wcid = rcu_dereference(dev->wcid[idx]);
+	if (!wcid)
+		return NULL;
+
+	return container_of(wcid, struct mt76x2_sta, wcid);
+}
+
+static struct mt76_wcid *
+mt76x2_rx_get_sta_wcid(struct mt76x2_dev *dev, struct mt76x2_sta *sta,
+		       bool unicast)
+{
+	if (!sta)
+		return NULL;
+
+	if (unicast)
+		return &sta->wcid;
+	else
+		return &sta->vif->group_wcid;
+}
+
+int mt76x2_mac_process_rx(struct mt76x2_dev *dev, struct sk_buff *skb,
+			  void *rxi)
+{
+	struct mt76_rx_status *status = (struct mt76_rx_status *) skb->cb;
+	struct mt76x2_rxwi *rxwi = rxi;
+	struct mt76x2_sta *sta;
+	u32 rxinfo = le32_to_cpu(rxwi->rxinfo);
+	u32 ctl = le32_to_cpu(rxwi->ctl);
+	u16 rate = le16_to_cpu(rxwi->rate);
+	u16 tid_sn = le16_to_cpu(rxwi->tid_sn);
+	bool unicast = rxwi->rxinfo & cpu_to_le32(MT_RXINFO_UNICAST);
+	int pad_len = 0;
+	u8 pn_len;
+	u8 wcid;
+	int len;
+
+	if (!test_bit(MT76_STATE_RUNNING, &dev->mt76.state))
+		return -EINVAL;
+
+	if (rxinfo & MT_RXINFO_L2PAD)
+		pad_len += 2;
+
+	if (rxinfo & MT_RXINFO_DECRYPT) {
+		status->flag |= RX_FLAG_DECRYPTED;
+		status->flag |= RX_FLAG_MMIC_STRIPPED;
+		status->flag |= RX_FLAG_MIC_STRIPPED;
+		status->flag |= RX_FLAG_IV_STRIPPED;
+	}
+
+	wcid = FIELD_GET(MT_RXWI_CTL_WCID, ctl);
+	sta = mt76x2_rx_get_sta(dev, wcid);
+	status->wcid = mt76x2_rx_get_sta_wcid(dev, sta, unicast);
+
+	len = FIELD_GET(MT_RXWI_CTL_MPDU_LEN, ctl);
+	pn_len = FIELD_GET(MT_RXINFO_PN_LEN, rxinfo);
+	if (pn_len) {
+		int offset = ieee80211_get_hdrlen_from_skb(skb) + pad_len;
+		u8 *data = skb->data + offset;
+
+		status->iv[0] = data[7];
+		status->iv[1] = data[6];
+		status->iv[2] = data[5];
+		status->iv[3] = data[4];
+		status->iv[4] = data[1];
+		status->iv[5] = data[0];
+
+		/*
+		 * Driver CCMP validation can't deal with fragments.
+		 * Let mac80211 take care of it.
+		 */
+		if (rxinfo & MT_RXINFO_FRAG) {
+			status->flag &= ~RX_FLAG_IV_STRIPPED;
+		} else {
+			pad_len += pn_len << 2;
+			len -= pn_len << 2;
+		}
+	}
+
+	mt76x2_remove_hdr_pad(skb, pad_len);
+
+	if ((rxinfo & MT_RXINFO_BA) && !(rxinfo & MT_RXINFO_NULL))
+		status->aggr = true;
+
+	if (WARN_ON_ONCE(len > skb->len))
+		return -EINVAL;
+
+	pskb_trim(skb, len);
+	status->chains = BIT(0) | BIT(1);
+	status->chain_signal[0] = mt76x2_mac_get_rssi(dev, rxwi->rssi[0], 0);
+	status->chain_signal[1] = mt76x2_mac_get_rssi(dev, rxwi->rssi[1], 1);
+	status->signal = max(status->chain_signal[0], status->chain_signal[1]);
+	status->freq = dev->mt76.chandef.chan->center_freq;
+	status->band = dev->mt76.chandef.chan->band;
+
+	status->tid = FIELD_GET(MT_RXWI_TID, tid_sn);
+	status->seqno = FIELD_GET(MT_RXWI_SN, tid_sn);
+
+	if (sta) {
+		ewma_signal_add(&sta->rssi, status->signal);
+		sta->inactive_count = 0;
+	}
+
+	return mt76x2_mac_process_rate(status, rate);
+}
+EXPORT_SYMBOL_GPL(mt76x2_mac_process_rx);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2_main.c
index ce90ff999b49..680a89f8aa87 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_main.c
@@ -53,30 +53,6 @@ mt76x2_stop(struct ieee80211_hw *hw)
 	mutex_unlock(&dev->mutex);
 }
 
-static void
-mt76x2_txq_init(struct mt76x2_dev *dev, struct ieee80211_txq *txq)
-{
-	struct mt76_txq *mtxq;
-
-	if (!txq)
-		return;
-
-	mtxq = (struct mt76_txq *) txq->drv_priv;
-	if (txq->sta) {
-		struct mt76x2_sta *sta;
-
-		sta = (struct mt76x2_sta *) txq->sta->drv_priv;
-		mtxq->wcid = &sta->wcid;
-	} else {
-		struct mt76x2_vif *mvif;
-
-		mvif = (struct mt76x2_vif *) txq->vif->drv_priv;
-		mtxq->wcid = &mvif->group_wcid;
-	}
-
-	mt76_txq_init(&dev->mt76, txq);
-}
-
 static int
 mt76x2_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 {
@@ -111,14 +87,6 @@ mt76x2_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	return 0;
 }
 
-static void
-mt76x2_remove_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
-{
-	struct mt76x2_dev *dev = hw->priv;
-
-	mt76_txq_remove(&dev->mt76, vif->txq);
-}
-
 static int
 mt76x2_set_channel(struct mt76x2_dev *dev, struct cfg80211_chan_def *chandef)
 {
@@ -194,39 +162,6 @@ mt76x2_config(struct ieee80211_hw *hw, u32 changed)
 }
 
 static void
-mt76x2_configure_filter(struct ieee80211_hw *hw, unsigned int changed_flags,
-			unsigned int *total_flags, u64 multicast)
-{
-	struct mt76x2_dev *dev = hw->priv;
-	u32 flags = 0;
-
-#define MT76_FILTER(_flag, _hw) do { \
-		flags |= *total_flags & FIF_##_flag;			\
-		dev->rxfilter &= ~(_hw);				\
-		dev->rxfilter |= !(flags & FIF_##_flag) * (_hw);	\
-	} while (0)
-
-	mutex_lock(&dev->mutex);
-
-	dev->rxfilter &= ~MT_RX_FILTR_CFG_OTHER_BSS;
-
-	MT76_FILTER(FCSFAIL, MT_RX_FILTR_CFG_CRC_ERR);
-	MT76_FILTER(PLCPFAIL, MT_RX_FILTR_CFG_PHY_ERR);
-	MT76_FILTER(CONTROL, MT_RX_FILTR_CFG_ACK |
-			     MT_RX_FILTR_CFG_CTS |
-			     MT_RX_FILTR_CFG_CFEND |
-			     MT_RX_FILTR_CFG_CFACK |
-			     MT_RX_FILTR_CFG_BA |
-			     MT_RX_FILTR_CFG_CTRL_RSV);
-	MT76_FILTER(PSPOLL, MT_RX_FILTR_CFG_PSPOLL);
-
-	*total_flags = flags;
-	mt76_wr(dev, MT_RX_FILTR_CFG, dev->rxfilter);
-
-	mutex_unlock(&dev->mutex);
-}
-
-static void
 mt76x2_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			struct ieee80211_bss_conf *info, u32 changed)
 {
@@ -238,10 +173,13 @@ mt76x2_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	if (changed & BSS_CHANGED_BSSID)
 		mt76x2_mac_set_bssid(dev, mvif->idx, info->bssid);
 
-	if (changed & BSS_CHANGED_BEACON_INT)
+	if (changed & BSS_CHANGED_BEACON_INT) {
 		mt76_rmw_field(dev, MT_BEACON_TIME_CFG,
 			       MT_BEACON_TIME_CFG_INTVAL,
 			       info->beacon_int << 4);
+		dev->beacon_int = info->beacon_int;
+		dev->tbtt_count = 0;
+	}
 
 	if (changed & BSS_CHANGED_BEACON_ENABLED) {
 		tasklet_disable(&dev->pre_tbtt_tasklet);
@@ -260,66 +198,6 @@ mt76x2_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	mutex_unlock(&dev->mutex);
 }
 
-static int
-mt76x2_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-	       struct ieee80211_sta *sta)
-{
-	struct mt76x2_dev *dev = hw->priv;
-	struct mt76x2_sta *msta = (struct mt76x2_sta *) sta->drv_priv;
-	struct mt76x2_vif *mvif = (struct mt76x2_vif *) vif->drv_priv;
-	int ret = 0;
-	int idx = 0;
-	int i;
-
-	mutex_lock(&dev->mutex);
-
-	idx = mt76_wcid_alloc(dev->wcid_mask, ARRAY_SIZE(dev->wcid));
-	if (idx < 0) {
-		ret = -ENOSPC;
-		goto out;
-	}
-
-	msta->vif = mvif;
-	msta->wcid.sta = 1;
-	msta->wcid.idx = idx;
-	msta->wcid.hw_key_idx = -1;
-	mt76x2_mac_wcid_setup(dev, idx, mvif->idx, sta->addr);
-	mt76x2_mac_wcid_set_drop(dev, idx, false);
-	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
-		mt76x2_txq_init(dev, sta->txq[i]);
-
-	if (vif->type == NL80211_IFTYPE_AP)
-		set_bit(MT_WCID_FLAG_CHECK_PS, &msta->wcid.flags);
-
-	rcu_assign_pointer(dev->wcid[idx], &msta->wcid);
-
-out:
-	mutex_unlock(&dev->mutex);
-
-	return ret;
-}
-
-static int
-mt76x2_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-		  struct ieee80211_sta *sta)
-{
-	struct mt76x2_dev *dev = hw->priv;
-	struct mt76x2_sta *msta = (struct mt76x2_sta *) sta->drv_priv;
-	int idx = msta->wcid.idx;
-	int i;
-
-	mutex_lock(&dev->mutex);
-	rcu_assign_pointer(dev->wcid[idx], NULL);
-	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
-		mt76_txq_remove(&dev->mt76, sta->txq[i]);
-	mt76x2_mac_wcid_set_drop(dev, idx, true);
-	mt76_wcid_free(dev->wcid_mask, idx);
-	mt76x2_mac_wcid_setup(dev, idx, 0, NULL);
-	mutex_unlock(&dev->mutex);
-
-	return 0;
-}
-
 void
 mt76x2_sta_ps(struct mt76_dev *mdev, struct ieee80211_sta *sta, bool ps)
 {
@@ -331,117 +209,6 @@ mt76x2_sta_ps(struct mt76_dev *mdev, struct ieee80211_sta *sta, bool ps)
 	mt76x2_mac_wcid_set_drop(dev, idx, ps);
 }
 
-static int
-mt76x2_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
-	       struct ieee80211_vif *vif, struct ieee80211_sta *sta,
-	       struct ieee80211_key_conf *key)
-{
-	struct mt76x2_dev *dev = hw->priv;
-	struct mt76x2_vif *mvif = (struct mt76x2_vif *) vif->drv_priv;
-	struct mt76x2_sta *msta;
-	struct mt76_wcid *wcid;
-	int idx = key->keyidx;
-	int ret;
-
-	/* fall back to sw encryption for unsupported ciphers */
-	switch (key->cipher) {
-	case WLAN_CIPHER_SUITE_WEP40:
-	case WLAN_CIPHER_SUITE_WEP104:
-	case WLAN_CIPHER_SUITE_TKIP:
-	case WLAN_CIPHER_SUITE_CCMP:
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
-	/*
-	 * The hardware does not support per-STA RX GTK, fall back
-	 * to software mode for these.
-	 */
-	if ((vif->type == NL80211_IFTYPE_ADHOC ||
-	     vif->type == NL80211_IFTYPE_MESH_POINT) &&
-	    (key->cipher == WLAN_CIPHER_SUITE_TKIP ||
-	     key->cipher == WLAN_CIPHER_SUITE_CCMP) &&
-	    !(key->flags & IEEE80211_KEY_FLAG_PAIRWISE))
-		return -EOPNOTSUPP;
-
-	msta = sta ? (struct mt76x2_sta *) sta->drv_priv : NULL;
-	wcid = msta ? &msta->wcid : &mvif->group_wcid;
-
-	if (cmd == SET_KEY) {
-		key->hw_key_idx = wcid->idx;
-		wcid->hw_key_idx = idx;
-		if (key->flags & IEEE80211_KEY_FLAG_RX_MGMT) {
-			key->flags |= IEEE80211_KEY_FLAG_SW_MGMT_TX;
-			wcid->sw_iv = true;
-		}
-	} else {
-		if (idx == wcid->hw_key_idx) {
-			wcid->hw_key_idx = -1;
-			wcid->sw_iv = true;
-		}
-
-		key = NULL;
-	}
-	mt76_wcid_key_setup(&dev->mt76, wcid, key);
-
-	if (!msta) {
-		if (key || wcid->hw_key_idx == idx) {
-			ret = mt76x2_mac_wcid_set_key(dev, wcid->idx, key);
-			if (ret)
-				return ret;
-		}
-
-		return mt76x2_mac_shared_key_setup(dev, mvif->idx, idx, key);
-	}
-
-	return mt76x2_mac_wcid_set_key(dev, msta->wcid.idx, key);
-}
-
-static int
-mt76x2_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u16 queue,
-	       const struct ieee80211_tx_queue_params *params)
-{
-	struct mt76x2_dev *dev = hw->priv;
-	u8 cw_min = 5, cw_max = 10, qid;
-	u32 val;
-
-	qid = dev->mt76.q_tx[queue].hw_idx;
-
-	if (params->cw_min)
-		cw_min = fls(params->cw_min);
-	if (params->cw_max)
-		cw_max = fls(params->cw_max);
-
-	val = FIELD_PREP(MT_EDCA_CFG_TXOP, params->txop) |
-	      FIELD_PREP(MT_EDCA_CFG_AIFSN, params->aifs) |
-	      FIELD_PREP(MT_EDCA_CFG_CWMIN, cw_min) |
-	      FIELD_PREP(MT_EDCA_CFG_CWMAX, cw_max);
-	mt76_wr(dev, MT_EDCA_CFG_AC(qid), val);
-
-	val = mt76_rr(dev, MT_WMM_TXOP(qid));
-	val &= ~(MT_WMM_TXOP_MASK << MT_WMM_TXOP_SHIFT(qid));
-	val |= params->txop << MT_WMM_TXOP_SHIFT(qid);
-	mt76_wr(dev, MT_WMM_TXOP(qid), val);
-
-	val = mt76_rr(dev, MT_WMM_AIFSN);
-	val &= ~(MT_WMM_AIFSN_MASK << MT_WMM_AIFSN_SHIFT(qid));
-	val |= params->aifs << MT_WMM_AIFSN_SHIFT(qid);
-	mt76_wr(dev, MT_WMM_AIFSN, val);
-
-	val = mt76_rr(dev, MT_WMM_CWMIN);
-	val &= ~(MT_WMM_CWMIN_MASK << MT_WMM_CWMIN_SHIFT(qid));
-	val |= cw_min << MT_WMM_CWMIN_SHIFT(qid);
-	mt76_wr(dev, MT_WMM_CWMIN, val);
-
-	val = mt76_rr(dev, MT_WMM_CWMAX);
-	val &= ~(MT_WMM_CWMAX_MASK << MT_WMM_CWMAX_SHIFT(qid));
-	val |= cw_max << MT_WMM_CWMAX_SHIFT(qid);
-	mt76_wr(dev, MT_WMM_CWMAX, val);
-
-	return 0;
-}
-
 static void
 mt76x2_sw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	       const u8 *mac)
@@ -480,75 +247,6 @@ mt76x2_get_txpower(struct ieee80211_hw *hw, struct ieee80211_vif *vif, int *dbm)
 	return 0;
 }
 
-static int
-mt76x2_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-		    struct ieee80211_ampdu_params *params)
-{
-	enum ieee80211_ampdu_mlme_action action = params->action;
-	struct ieee80211_sta *sta = params->sta;
-	struct mt76x2_dev *dev = hw->priv;
-	struct mt76x2_sta *msta = (struct mt76x2_sta *) sta->drv_priv;
-	struct ieee80211_txq *txq = sta->txq[params->tid];
-	u16 tid = params->tid;
-	u16 *ssn = &params->ssn;
-	struct mt76_txq *mtxq;
-
-	if (!txq)
-		return -EINVAL;
-
-	mtxq = (struct mt76_txq *)txq->drv_priv;
-
-	switch (action) {
-	case IEEE80211_AMPDU_RX_START:
-		mt76_rx_aggr_start(&dev->mt76, &msta->wcid, tid, *ssn, params->buf_size);
-		mt76_set(dev, MT_WCID_ADDR(msta->wcid.idx) + 4, BIT(16 + tid));
-		break;
-	case IEEE80211_AMPDU_RX_STOP:
-		mt76_rx_aggr_stop(&dev->mt76, &msta->wcid, tid);
-		mt76_clear(dev, MT_WCID_ADDR(msta->wcid.idx) + 4,
-			   BIT(16 + tid));
-		break;
-	case IEEE80211_AMPDU_TX_OPERATIONAL:
-		mtxq->aggr = true;
-		mtxq->send_bar = false;
-		ieee80211_send_bar(vif, sta->addr, tid, mtxq->agg_ssn);
-		break;
-	case IEEE80211_AMPDU_TX_STOP_FLUSH:
-	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
-		mtxq->aggr = false;
-		ieee80211_send_bar(vif, sta->addr, tid, mtxq->agg_ssn);
-		break;
-	case IEEE80211_AMPDU_TX_START:
-		mtxq->agg_ssn = *ssn << 4;
-		ieee80211_start_tx_ba_cb_irqsafe(vif, sta->addr, tid);
-		break;
-	case IEEE80211_AMPDU_TX_STOP_CONT:
-		mtxq->aggr = false;
-		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
-		break;
-	}
-
-	return 0;
-}
-
-static void
-mt76x2_sta_rate_tbl_update(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-			   struct ieee80211_sta *sta)
-{
-	struct mt76x2_dev *dev = hw->priv;
-	struct mt76x2_sta *msta = (struct mt76x2_sta *) sta->drv_priv;
-	struct ieee80211_sta_rates *rates = rcu_dereference(sta->rates);
-	struct ieee80211_tx_rate rate = {};
-
-	if (!rates)
-		return;
-
-	rate.idx = rates->rate[0].idx;
-	rate.flags = rates->rate[0].flags;
-	mt76x2_mac_wcid_set_rate(dev, &msta->wcid, &rate);
-	msta->wcid.max_txpwr_adj = mt76x2_tx_get_max_txpwr_adj(dev, &rate);
-}
-
 static void mt76x2_set_coverage_class(struct ieee80211_hw *hw,
 				      s16 coverage_class)
 {
@@ -600,6 +298,21 @@ static int mt76x2_get_antenna(struct ieee80211_hw *hw, u32 *tx_ant,
 	return 0;
 }
 
+static int
+mt76x2_set_rts_threshold(struct ieee80211_hw *hw, u32 val)
+{
+	struct mt76x2_dev *dev = hw->priv;
+
+	if (val != ~0 && val > 0xffff)
+		return -EINVAL;
+
+	mutex_lock(&dev->mutex);
+	mt76x2_mac_set_tx_protection(dev, val);
+	mutex_unlock(&dev->mutex);
+
+	return 0;
+}
+
 const struct ieee80211_ops mt76x2_ops = {
 	.tx = mt76x2_tx,
 	.start = mt76x2_start,
@@ -626,5 +339,6 @@ const struct ieee80211_ops mt76x2_ops = {
 	.set_tim = mt76x2_set_tim,
 	.set_antenna = mt76x2_set_antenna,
 	.get_antenna = mt76x2_get_antenna,
+	.set_rts_threshold = mt76x2_set_rts_threshold,
 };
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x2_mcu.c
index dfd36d736b06..743da57760dc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_mcu.c
@@ -23,23 +23,6 @@
 #include "mt76x2_dma.h"
 #include "mt76x2_eeprom.h"
 
-struct mt76x2_fw_header {
-	__le32 ilm_len;
-	__le32 dlm_len;
-	__le16 build_ver;
-	__le16 fw_ver;
-	u8 pad[4];
-	char build_time[16];
-};
-
-struct mt76x2_patch_header {
-	char build_time[16];
-	char platform[4];
-	char hw_version[4];
-	char patch_version[4];
-	u8 pad[2];
-};
-
 static struct sk_buff *mt76x2_mcu_msg_alloc(const void *data, int len)
 {
 	struct sk_buff *skb;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76x2_mcu.h
index d7a7e83262ce..e40293f21417 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_mcu.h
@@ -146,6 +146,23 @@ struct mt76x2_tssi_comp {
 	u8 offset1;
 } __packed __aligned(4);
 
+struct mt76x2_fw_header {
+	__le32 ilm_len;
+	__le32 dlm_len;
+	__le16 build_ver;
+	__le16 fw_ver;
+	u8 pad[4];
+	char build_time[16];
+};
+
+struct mt76x2_patch_header {
+	char build_time[16];
+	char platform[4];
+	char hw_version[4];
+	char patch_version[4];
+	u8 pad[2];
+};
+
 int mt76x2_mcu_calibrate(struct mt76x2_dev *dev, enum mcu_calibration type,
 			 u32 param);
 int mt76x2_mcu_tssi_comp(struct mt76x2_dev *dev, struct mt76x2_tssi_comp *tssi_data);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
index c1c38ca3330a..84c96c0415b6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
@@ -19,172 +19,6 @@
 #include "mt76x2_mcu.h"
 #include "mt76x2_eeprom.h"
 
-static void
-mt76x2_adjust_high_lna_gain(struct mt76x2_dev *dev, int reg, s8 offset)
-{
-	s8 gain;
-
-	gain = FIELD_GET(MT_BBP_AGC_LNA_HIGH_GAIN, mt76_rr(dev, MT_BBP(AGC, reg)));
-	gain -= offset / 2;
-	mt76_rmw_field(dev, MT_BBP(AGC, reg), MT_BBP_AGC_LNA_HIGH_GAIN, gain);
-}
-
-static void
-mt76x2_adjust_agc_gain(struct mt76x2_dev *dev, int reg, s8 offset)
-{
-	s8 gain;
-
-	gain = FIELD_GET(MT_BBP_AGC_GAIN, mt76_rr(dev, MT_BBP(AGC, reg)));
-	gain += offset;
-	mt76_rmw_field(dev, MT_BBP(AGC, reg), MT_BBP_AGC_GAIN, gain);
-}
-
-static void
-mt76x2_apply_gain_adj(struct mt76x2_dev *dev)
-{
-	s8 *gain_adj = dev->cal.rx.high_gain;
-
-	mt76x2_adjust_high_lna_gain(dev, 4, gain_adj[0]);
-	mt76x2_adjust_high_lna_gain(dev, 5, gain_adj[1]);
-
-	mt76x2_adjust_agc_gain(dev, 8, gain_adj[0]);
-	mt76x2_adjust_agc_gain(dev, 9, gain_adj[1]);
-}
-
-static u32
-mt76x2_tx_power_mask(u8 v1, u8 v2, u8 v3, u8 v4)
-{
-	u32 val = 0;
-
-	val |= (v1 & (BIT(6) - 1)) << 0;
-	val |= (v2 & (BIT(6) - 1)) << 8;
-	val |= (v3 & (BIT(6) - 1)) << 16;
-	val |= (v4 & (BIT(6) - 1)) << 24;
-	return val;
-}
-
-int mt76x2_phy_get_rssi(struct mt76x2_dev *dev, s8 rssi, int chain)
-{
-	struct mt76x2_rx_freq_cal *cal = &dev->cal.rx;
-
-	rssi += cal->rssi_offset[chain];
-	rssi -= cal->lna_gain;
-
-	return rssi;
-}
-
-static void
-mt76x2_add_rate_power_offset(struct mt76_rate_power *r, int offset)
-{
-	int i;
-
-	for (i = 0; i < sizeof(r->all); i++)
-		r->all[i] += offset;
-}
-
-static void
-mt76x2_limit_rate_power(struct mt76_rate_power *r, int limit)
-{
-	int i;
-
-	for (i = 0; i < sizeof(r->all); i++)
-		if (r->all[i] > limit)
-			r->all[i] = limit;
-}
-
-static int
-mt76x2_get_min_rate_power(struct mt76_rate_power *r)
-{
-	int i;
-	s8 ret = 0;
-
-	for (i = 0; i < sizeof(r->all); i++) {
-		if (!r->all[i])
-			continue;
-
-		if (ret)
-			ret = min(ret, r->all[i]);
-		else
-			ret = r->all[i];
-	}
-
-	return ret;
-}
-
-
-void mt76x2_phy_set_txpower(struct mt76x2_dev *dev)
-{
-	enum nl80211_chan_width width = dev->mt76.chandef.width;
-	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
-	struct mt76x2_tx_power_info txp;
-	int txp_0, txp_1, delta = 0;
-	struct mt76_rate_power t = {};
-	int base_power, gain;
-
-	mt76x2_get_power_info(dev, &txp, chan);
-
-	if (width == NL80211_CHAN_WIDTH_40)
-		delta = txp.delta_bw40;
-	else if (width == NL80211_CHAN_WIDTH_80)
-		delta = txp.delta_bw80;
-
-	mt76x2_get_rate_power(dev, &t, chan);
-	mt76x2_add_rate_power_offset(&t, txp.chain[0].target_power);
-	mt76x2_limit_rate_power(&t, dev->txpower_conf);
-	dev->txpower_cur = mt76x2_get_max_rate_power(&t);
-
-	base_power = mt76x2_get_min_rate_power(&t);
-	delta += base_power - txp.chain[0].target_power;
-	txp_0 = txp.chain[0].target_power + txp.chain[0].delta + delta;
-	txp_1 = txp.chain[1].target_power + txp.chain[1].delta + delta;
-
-	gain = min(txp_0, txp_1);
-	if (gain < 0) {
-		base_power -= gain;
-		txp_0 -= gain;
-		txp_1 -= gain;
-	} else if (gain > 0x2f) {
-		base_power -= gain - 0x2f;
-		txp_0 = 0x2f;
-		txp_1 = 0x2f;
-	}
-
-	mt76x2_add_rate_power_offset(&t, -base_power);
-	dev->target_power = txp.chain[0].target_power;
-	dev->target_power_delta[0] = txp_0 - txp.chain[0].target_power;
-	dev->target_power_delta[1] = txp_1 - txp.chain[0].target_power;
-	dev->rate_power = t;
-
-	mt76_rmw_field(dev, MT_TX_ALC_CFG_0, MT_TX_ALC_CFG_0_CH_INIT_0, txp_0);
-	mt76_rmw_field(dev, MT_TX_ALC_CFG_0, MT_TX_ALC_CFG_0_CH_INIT_1, txp_1);
-
-	mt76_wr(dev, MT_TX_PWR_CFG_0,
-		mt76x2_tx_power_mask(t.cck[0], t.cck[2], t.ofdm[0], t.ofdm[2]));
-	mt76_wr(dev, MT_TX_PWR_CFG_1,
-		mt76x2_tx_power_mask(t.ofdm[4], t.ofdm[6], t.ht[0], t.ht[2]));
-	mt76_wr(dev, MT_TX_PWR_CFG_2,
-		mt76x2_tx_power_mask(t.ht[4], t.ht[6], t.ht[8], t.ht[10]));
-	mt76_wr(dev, MT_TX_PWR_CFG_3,
-		mt76x2_tx_power_mask(t.ht[12], t.ht[14], t.ht[0], t.ht[2]));
-	mt76_wr(dev, MT_TX_PWR_CFG_4,
-		mt76x2_tx_power_mask(t.ht[4], t.ht[6], 0, 0));
-	mt76_wr(dev, MT_TX_PWR_CFG_7,
-		mt76x2_tx_power_mask(t.ofdm[6], t.vht[8], t.ht[6], t.vht[8]));
-	mt76_wr(dev, MT_TX_PWR_CFG_8,
-		mt76x2_tx_power_mask(t.ht[14], t.vht[8], t.vht[8], 0));
-	mt76_wr(dev, MT_TX_PWR_CFG_9,
-		mt76x2_tx_power_mask(t.ht[6], t.vht[8], t.vht[8], 0));
-}
-
-static bool
-mt76x2_channel_silent(struct mt76x2_dev *dev)
-{
-	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
-
-	return ((chan->flags & IEEE80211_CHAN_RADAR) &&
-		chan->dfs_state != NL80211_DFS_AVAILABLE);
-}
-
 static bool
 mt76x2_phy_tssi_init_cal(struct mt76x2_dev *dev)
 {
@@ -243,140 +77,6 @@ mt76x2_phy_channel_calibrate(struct mt76x2_dev *dev, bool mac_stopped)
 	dev->cal.channel_cal_done = true;
 }
 
-static void
-mt76x2_phy_set_txpower_regs(struct mt76x2_dev *dev, enum nl80211_band band)
-{
-	u32 pa_mode[2];
-	u32 pa_mode_adj;
-
-	if (band == NL80211_BAND_2GHZ) {
-		pa_mode[0] = 0x010055ff;
-		pa_mode[1] = 0x00550055;
-
-		mt76_wr(dev, MT_TX_ALC_CFG_2, 0x35160a00);
-		mt76_wr(dev, MT_TX_ALC_CFG_3, 0x35160a06);
-
-		if (mt76x2_ext_pa_enabled(dev, band)) {
-			mt76_wr(dev, MT_RF_PA_MODE_ADJ0, 0x0000ec00);
-			mt76_wr(dev, MT_RF_PA_MODE_ADJ1, 0x0000ec00);
-		} else {
-			mt76_wr(dev, MT_RF_PA_MODE_ADJ0, 0xf4000200);
-			mt76_wr(dev, MT_RF_PA_MODE_ADJ1, 0xfa000200);
-		}
-	} else {
-		pa_mode[0] = 0x0000ffff;
-		pa_mode[1] = 0x00ff00ff;
-
-		if (mt76x2_ext_pa_enabled(dev, band)) {
-			mt76_wr(dev, MT_TX_ALC_CFG_2, 0x2f0f0400);
-			mt76_wr(dev, MT_TX_ALC_CFG_3, 0x2f0f0476);
-		} else {
-			mt76_wr(dev, MT_TX_ALC_CFG_2, 0x1b0f0400);
-			mt76_wr(dev, MT_TX_ALC_CFG_3, 0x1b0f0476);
-		}
-
-		if (mt76x2_ext_pa_enabled(dev, band))
-			pa_mode_adj = 0x04000000;
-		else
-			pa_mode_adj = 0;
-
-		mt76_wr(dev, MT_RF_PA_MODE_ADJ0, pa_mode_adj);
-		mt76_wr(dev, MT_RF_PA_MODE_ADJ1, pa_mode_adj);
-	}
-
-	mt76_wr(dev, MT_BB_PA_MODE_CFG0, pa_mode[0]);
-	mt76_wr(dev, MT_BB_PA_MODE_CFG1, pa_mode[1]);
-	mt76_wr(dev, MT_RF_PA_MODE_CFG0, pa_mode[0]);
-	mt76_wr(dev, MT_RF_PA_MODE_CFG1, pa_mode[1]);
-
-	if (mt76x2_ext_pa_enabled(dev, band)) {
-		u32 val;
-
-		if (band == NL80211_BAND_2GHZ)
-			val = 0x3c3c023c;
-		else
-			val = 0x363c023c;
-
-		mt76_wr(dev, MT_TX0_RF_GAIN_CORR, val);
-		mt76_wr(dev, MT_TX1_RF_GAIN_CORR, val);
-		mt76_wr(dev, MT_TX_ALC_CFG_4, 0x00001818);
-	} else {
-		if (band == NL80211_BAND_2GHZ) {
-			u32 val = 0x0f3c3c3c;
-
-			mt76_wr(dev, MT_TX0_RF_GAIN_CORR, val);
-			mt76_wr(dev, MT_TX1_RF_GAIN_CORR, val);
-			mt76_wr(dev, MT_TX_ALC_CFG_4, 0x00000606);
-		} else {
-			mt76_wr(dev, MT_TX0_RF_GAIN_CORR, 0x383c023c);
-			mt76_wr(dev, MT_TX1_RF_GAIN_CORR, 0x24282e28);
-			mt76_wr(dev, MT_TX_ALC_CFG_4, 0);
-		}
-	}
-}
-
-static void
-mt76x2_configure_tx_delay(struct mt76x2_dev *dev, enum nl80211_band band, u8 bw)
-{
-	u32 cfg0, cfg1;
-
-	if (mt76x2_ext_pa_enabled(dev, band)) {
-		cfg0 = bw ? 0x000b0c01 : 0x00101101;
-		cfg1 = 0x00011414;
-	} else {
-		cfg0 = bw ? 0x000b0b01 : 0x00101001;
-		cfg1 = 0x00021414;
-	}
-	mt76_wr(dev, MT_TX_SW_CFG0, cfg0);
-	mt76_wr(dev, MT_TX_SW_CFG1, cfg1);
-
-	mt76_rmw_field(dev, MT_XIFS_TIME_CFG, MT_XIFS_TIME_CFG_OFDM_SIFS, 15);
-}
-
-static void
-mt76x2_phy_set_bw(struct mt76x2_dev *dev, int width, u8 ctrl)
-{
-	int core_val, agc_val;
-
-	switch (width) {
-	case NL80211_CHAN_WIDTH_80:
-		core_val = 3;
-		agc_val = 7;
-		break;
-	case NL80211_CHAN_WIDTH_40:
-		core_val = 2;
-		agc_val = 3;
-		break;
-	default:
-		core_val = 0;
-		agc_val = 1;
-		break;
-	}
-
-	mt76_rmw_field(dev, MT_BBP(CORE, 1), MT_BBP_CORE_R1_BW, core_val);
-	mt76_rmw_field(dev, MT_BBP(AGC, 0), MT_BBP_AGC_R0_BW, agc_val);
-	mt76_rmw_field(dev, MT_BBP(AGC, 0), MT_BBP_AGC_R0_CTRL_CHAN, ctrl);
-	mt76_rmw_field(dev, MT_BBP(TXBE, 0), MT_BBP_TXBE_R0_CTRL_CHAN, ctrl);
-}
-
-static void
-mt76x2_phy_set_band(struct mt76x2_dev *dev, int band, bool primary_upper)
-{
-	switch (band) {
-	case NL80211_BAND_2GHZ:
-		mt76_set(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_2G);
-		mt76_clear(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_5G);
-		break;
-	case NL80211_BAND_5GHZ:
-		mt76_clear(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_2G);
-		mt76_set(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_5G);
-		break;
-	}
-
-	mt76_rmw_field(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_UPPER_40M,
-		       primary_upper);
-}
-
 void mt76x2_phy_set_antenna(struct mt76x2_dev *dev)
 {
 	u32 val;
@@ -485,12 +185,14 @@ static void
 mt76x2_phy_adjust_vga_gain(struct mt76x2_dev *dev)
 {
 	u32 false_cca;
-	u8 limit = dev->cal.low_gain > 1 ? 4 : 16;
+	u8 limit = dev->cal.low_gain > 0 ? 16 : 4;
 
 	false_cca = FIELD_GET(MT_RX_STAT_1_CCA_ERRORS, mt76_rr(dev, MT_RX_STAT_1));
+	dev->cal.false_cca = false_cca;
 	if (false_cca > 800 && dev->cal.agc_gain_adjust < limit)
 		dev->cal.agc_gain_adjust += 2;
-	else if (false_cca < 10 && dev->cal.agc_gain_adjust > 0)
+	else if ((false_cca < 10 && dev->cal.agc_gain_adjust > 0) ||
+		 (dev->cal.agc_gain_adjust >= limit && false_cca < 500))
 		dev->cal.agc_gain_adjust -= 2;
 	else
 		return;
@@ -501,57 +203,65 @@ mt76x2_phy_adjust_vga_gain(struct mt76x2_dev *dev)
 static void
 mt76x2_phy_update_channel_gain(struct mt76x2_dev *dev)
 {
-	u32 val = mt76_rr(dev, MT_BBP(AGC, 20));
-	int rssi0 = (s8) FIELD_GET(MT_BBP_AGC20_RSSI0, val);
-	int rssi1 = (s8) FIELD_GET(MT_BBP_AGC20_RSSI1, val);
 	u8 *gain = dev->cal.agc_gain_init;
-	u8 gain_delta;
+	u8 low_gain_delta, gain_delta;
+	bool gain_change;
 	int low_gain;
+	u32 val;
 
-	dev->cal.avg_rssi[0] = (dev->cal.avg_rssi[0] * 15) / 16 +
-			       (rssi0 << 8) / 16;
-	dev->cal.avg_rssi[1] = (dev->cal.avg_rssi[1] * 15) / 16 +
-			       (rssi1 << 8) / 16;
-	dev->cal.avg_rssi_all = (dev->cal.avg_rssi[0] +
-				 dev->cal.avg_rssi[1]) / 512;
+	dev->cal.avg_rssi_all = mt76x2_phy_get_min_avg_rssi(dev);
 
 	low_gain = (dev->cal.avg_rssi_all > mt76x2_get_rssi_gain_thresh(dev)) +
 		   (dev->cal.avg_rssi_all > mt76x2_get_low_rssi_gain_thresh(dev));
 
-	if (dev->cal.low_gain == low_gain) {
+	gain_change = (dev->cal.low_gain & 2) ^ (low_gain & 2);
+	dev->cal.low_gain = low_gain;
+
+	if (!gain_change) {
 		mt76x2_phy_adjust_vga_gain(dev);
 		return;
 	}
 
-	dev->cal.low_gain = low_gain;
-
-	if (dev->mt76.chandef.width == NL80211_CHAN_WIDTH_80)
+	if (dev->mt76.chandef.width == NL80211_CHAN_WIDTH_80) {
 		mt76_wr(dev, MT_BBP(RXO, 14), 0x00560211);
-	else
+		val = mt76_rr(dev, MT_BBP(AGC, 26)) & ~0xf;
+		if (low_gain == 2)
+			val |= 0x3;
+		else
+			val |= 0x5;
+		mt76_wr(dev, MT_BBP(AGC, 26), val);
+	} else {
 		mt76_wr(dev, MT_BBP(RXO, 14), 0x00560423);
+	}
 
-	if (low_gain) {
-		mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a991);
+	if (mt76x2_has_ext_lna(dev))
+		low_gain_delta = 10;
+	else
+		low_gain_delta = 14;
+
+	if (low_gain == 2) {
+		mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a990);
 		mt76_wr(dev, MT_BBP(AGC, 35), 0x08080808);
 		mt76_wr(dev, MT_BBP(AGC, 37), 0x08080808);
-		if (mt76x2_has_ext_lna(dev))
-			gain_delta = 10;
-		else
-			gain_delta = 14;
+		gain_delta = low_gain_delta;
+		dev->cal.agc_gain_adjust = 0;
 	} else {
-		mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a990);
+		mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a991);
 		if (dev->mt76.chandef.width == NL80211_CHAN_WIDTH_80)
 			mt76_wr(dev, MT_BBP(AGC, 35), 0x10101014);
 		else
 			mt76_wr(dev, MT_BBP(AGC, 35), 0x11111116);
 		mt76_wr(dev, MT_BBP(AGC, 37), 0x2121262C);
 		gain_delta = 0;
+		dev->cal.agc_gain_adjust = low_gain_delta;
 	}
 
 	dev->cal.agc_gain_cur[0] = gain[0] - gain_delta;
 	dev->cal.agc_gain_cur[1] = gain[1] - gain_delta;
-	dev->cal.agc_gain_adjust = 0;
 	mt76x2_phy_set_gain_val(dev);
+
+	/* clear false CCA counters */
+	mt76_rr(dev, MT_RX_STAT_1);
 }
 
 int mt76x2_phy_set_channel(struct mt76x2_dev *dev,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_phy_common.c b/drivers/net/wireless/mediatek/mt76/mt76x2_phy_common.c
new file mode 100644
index 000000000000..9fd6ab4cbb94
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_phy_common.c
@@ -0,0 +1,349 @@
+/*
+ * Copyright (C) 2016 Felix Fietkau <nbd@nbd.name>
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76x2.h"
+#include "mt76x2_eeprom.h"
+
+static void
+mt76x2_adjust_high_lna_gain(struct mt76x2_dev *dev, int reg, s8 offset)
+{
+	s8 gain;
+
+	gain = FIELD_GET(MT_BBP_AGC_LNA_HIGH_GAIN, mt76_rr(dev, MT_BBP(AGC, reg)));
+	gain -= offset / 2;
+	mt76_rmw_field(dev, MT_BBP(AGC, reg), MT_BBP_AGC_LNA_HIGH_GAIN, gain);
+}
+
+static void
+mt76x2_adjust_agc_gain(struct mt76x2_dev *dev, int reg, s8 offset)
+{
+	s8 gain;
+
+	gain = FIELD_GET(MT_BBP_AGC_GAIN, mt76_rr(dev, MT_BBP(AGC, reg)));
+	gain += offset;
+	mt76_rmw_field(dev, MT_BBP(AGC, reg), MT_BBP_AGC_GAIN, gain);
+}
+
+void mt76x2_apply_gain_adj(struct mt76x2_dev *dev)
+{
+	s8 *gain_adj = dev->cal.rx.high_gain;
+
+	mt76x2_adjust_high_lna_gain(dev, 4, gain_adj[0]);
+	mt76x2_adjust_high_lna_gain(dev, 5, gain_adj[1]);
+
+	mt76x2_adjust_agc_gain(dev, 8, gain_adj[0]);
+	mt76x2_adjust_agc_gain(dev, 9, gain_adj[1]);
+}
+EXPORT_SYMBOL_GPL(mt76x2_apply_gain_adj);
+
+void mt76x2_phy_set_txpower_regs(struct mt76x2_dev *dev,
+				 enum nl80211_band band)
+{
+	u32 pa_mode[2];
+	u32 pa_mode_adj;
+
+	if (band == NL80211_BAND_2GHZ) {
+		pa_mode[0] = 0x010055ff;
+		pa_mode[1] = 0x00550055;
+
+		mt76_wr(dev, MT_TX_ALC_CFG_2, 0x35160a00);
+		mt76_wr(dev, MT_TX_ALC_CFG_3, 0x35160a06);
+
+		if (mt76x2_ext_pa_enabled(dev, band)) {
+			mt76_wr(dev, MT_RF_PA_MODE_ADJ0, 0x0000ec00);
+			mt76_wr(dev, MT_RF_PA_MODE_ADJ1, 0x0000ec00);
+		} else {
+			mt76_wr(dev, MT_RF_PA_MODE_ADJ0, 0xf4000200);
+			mt76_wr(dev, MT_RF_PA_MODE_ADJ1, 0xfa000200);
+		}
+	} else {
+		pa_mode[0] = 0x0000ffff;
+		pa_mode[1] = 0x00ff00ff;
+
+		if (mt76x2_ext_pa_enabled(dev, band)) {
+			mt76_wr(dev, MT_TX_ALC_CFG_2, 0x2f0f0400);
+			mt76_wr(dev, MT_TX_ALC_CFG_3, 0x2f0f0476);
+		} else {
+			mt76_wr(dev, MT_TX_ALC_CFG_2, 0x1b0f0400);
+			mt76_wr(dev, MT_TX_ALC_CFG_3, 0x1b0f0476);
+		}
+
+		if (mt76x2_ext_pa_enabled(dev, band))
+			pa_mode_adj = 0x04000000;
+		else
+			pa_mode_adj = 0;
+
+		mt76_wr(dev, MT_RF_PA_MODE_ADJ0, pa_mode_adj);
+		mt76_wr(dev, MT_RF_PA_MODE_ADJ1, pa_mode_adj);
+	}
+
+	mt76_wr(dev, MT_BB_PA_MODE_CFG0, pa_mode[0]);
+	mt76_wr(dev, MT_BB_PA_MODE_CFG1, pa_mode[1]);
+	mt76_wr(dev, MT_RF_PA_MODE_CFG0, pa_mode[0]);
+	mt76_wr(dev, MT_RF_PA_MODE_CFG1, pa_mode[1]);
+
+	if (mt76x2_ext_pa_enabled(dev, band)) {
+		u32 val;
+
+		if (band == NL80211_BAND_2GHZ)
+			val = 0x3c3c023c;
+		else
+			val = 0x363c023c;
+
+		mt76_wr(dev, MT_TX0_RF_GAIN_CORR, val);
+		mt76_wr(dev, MT_TX1_RF_GAIN_CORR, val);
+		mt76_wr(dev, MT_TX_ALC_CFG_4, 0x00001818);
+	} else {
+		if (band == NL80211_BAND_2GHZ) {
+			u32 val = 0x0f3c3c3c;
+
+			mt76_wr(dev, MT_TX0_RF_GAIN_CORR, val);
+			mt76_wr(dev, MT_TX1_RF_GAIN_CORR, val);
+			mt76_wr(dev, MT_TX_ALC_CFG_4, 0x00000606);
+		} else {
+			mt76_wr(dev, MT_TX0_RF_GAIN_CORR, 0x383c023c);
+			mt76_wr(dev, MT_TX1_RF_GAIN_CORR, 0x24282e28);
+			mt76_wr(dev, MT_TX_ALC_CFG_4, 0);
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(mt76x2_phy_set_txpower_regs);
+
+static void
+mt76x2_limit_rate_power(struct mt76_rate_power *r, int limit)
+{
+	int i;
+
+	for (i = 0; i < sizeof(r->all); i++)
+		if (r->all[i] > limit)
+			r->all[i] = limit;
+}
+
+static u32
+mt76x2_tx_power_mask(u8 v1, u8 v2, u8 v3, u8 v4)
+{
+	u32 val = 0;
+
+	val |= (v1 & (BIT(6) - 1)) << 0;
+	val |= (v2 & (BIT(6) - 1)) << 8;
+	val |= (v3 & (BIT(6) - 1)) << 16;
+	val |= (v4 & (BIT(6) - 1)) << 24;
+	return val;
+}
+
+static void
+mt76x2_add_rate_power_offset(struct mt76_rate_power *r, int offset)
+{
+	int i;
+
+	for (i = 0; i < sizeof(r->all); i++)
+		r->all[i] += offset;
+}
+
+static int
+mt76x2_get_min_rate_power(struct mt76_rate_power *r)
+{
+	int i;
+	s8 ret = 0;
+
+	for (i = 0; i < sizeof(r->all); i++) {
+		if (!r->all[i])
+			continue;
+
+		if (ret)
+			ret = min(ret, r->all[i]);
+		else
+			ret = r->all[i];
+	}
+
+	return ret;
+}
+
+void mt76x2_phy_set_txpower(struct mt76x2_dev *dev)
+{
+	enum nl80211_chan_width width = dev->mt76.chandef.width;
+	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
+	struct mt76x2_tx_power_info txp;
+	int txp_0, txp_1, delta = 0;
+	struct mt76_rate_power t = {};
+	int base_power, gain;
+
+	mt76x2_get_power_info(dev, &txp, chan);
+
+	if (width == NL80211_CHAN_WIDTH_40)
+		delta = txp.delta_bw40;
+	else if (width == NL80211_CHAN_WIDTH_80)
+		delta = txp.delta_bw80;
+
+	mt76x2_get_rate_power(dev, &t, chan);
+	mt76x2_add_rate_power_offset(&t, txp.chain[0].target_power);
+	mt76x2_limit_rate_power(&t, dev->txpower_conf);
+	dev->txpower_cur = mt76x2_get_max_rate_power(&t);
+
+	base_power = mt76x2_get_min_rate_power(&t);
+	delta += base_power - txp.chain[0].target_power;
+	txp_0 = txp.chain[0].target_power + txp.chain[0].delta + delta;
+	txp_1 = txp.chain[1].target_power + txp.chain[1].delta + delta;
+
+	gain = min(txp_0, txp_1);
+	if (gain < 0) {
+		base_power -= gain;
+		txp_0 -= gain;
+		txp_1 -= gain;
+	} else if (gain > 0x2f) {
+		base_power -= gain - 0x2f;
+		txp_0 = 0x2f;
+		txp_1 = 0x2f;
+	}
+
+	mt76x2_add_rate_power_offset(&t, -base_power);
+	dev->target_power = txp.chain[0].target_power;
+	dev->target_power_delta[0] = txp_0 - txp.chain[0].target_power;
+	dev->target_power_delta[1] = txp_1 - txp.chain[0].target_power;
+	dev->rate_power = t;
+
+	mt76_rmw_field(dev, MT_TX_ALC_CFG_0, MT_TX_ALC_CFG_0_CH_INIT_0, txp_0);
+	mt76_rmw_field(dev, MT_TX_ALC_CFG_0, MT_TX_ALC_CFG_0_CH_INIT_1, txp_1);
+
+	mt76_wr(dev, MT_TX_PWR_CFG_0,
+		mt76x2_tx_power_mask(t.cck[0], t.cck[2], t.ofdm[0], t.ofdm[2]));
+	mt76_wr(dev, MT_TX_PWR_CFG_1,
+		mt76x2_tx_power_mask(t.ofdm[4], t.ofdm[6], t.ht[0], t.ht[2]));
+	mt76_wr(dev, MT_TX_PWR_CFG_2,
+		mt76x2_tx_power_mask(t.ht[4], t.ht[6], t.ht[8], t.ht[10]));
+	mt76_wr(dev, MT_TX_PWR_CFG_3,
+		mt76x2_tx_power_mask(t.ht[12], t.ht[14], t.ht[0], t.ht[2]));
+	mt76_wr(dev, MT_TX_PWR_CFG_4,
+		mt76x2_tx_power_mask(t.ht[4], t.ht[6], 0, 0));
+	mt76_wr(dev, MT_TX_PWR_CFG_7,
+		mt76x2_tx_power_mask(t.ofdm[6], t.vht[8], t.ht[6], t.vht[8]));
+	mt76_wr(dev, MT_TX_PWR_CFG_8,
+		mt76x2_tx_power_mask(t.ht[14], t.vht[8], t.vht[8], 0));
+	mt76_wr(dev, MT_TX_PWR_CFG_9,
+		mt76x2_tx_power_mask(t.ht[6], t.vht[8], t.vht[8], 0));
+}
+EXPORT_SYMBOL_GPL(mt76x2_phy_set_txpower);
+
+void mt76x2_configure_tx_delay(struct mt76x2_dev *dev,
+			       enum nl80211_band band, u8 bw)
+{
+	u32 cfg0, cfg1;
+
+	if (mt76x2_ext_pa_enabled(dev, band)) {
+		cfg0 = bw ? 0x000b0c01 : 0x00101101;
+		cfg1 = 0x00011414;
+	} else {
+		cfg0 = bw ? 0x000b0b01 : 0x00101001;
+		cfg1 = 0x00021414;
+	}
+	mt76_wr(dev, MT_TX_SW_CFG0, cfg0);
+	mt76_wr(dev, MT_TX_SW_CFG1, cfg1);
+
+	mt76_rmw_field(dev, MT_XIFS_TIME_CFG, MT_XIFS_TIME_CFG_OFDM_SIFS, 15);
+}
+EXPORT_SYMBOL_GPL(mt76x2_configure_tx_delay);
+
+void mt76x2_phy_set_bw(struct mt76x2_dev *dev, int width, u8 ctrl)
+{
+	int core_val, agc_val;
+
+	switch (width) {
+	case NL80211_CHAN_WIDTH_80:
+		core_val = 3;
+		agc_val = 7;
+		break;
+	case NL80211_CHAN_WIDTH_40:
+		core_val = 2;
+		agc_val = 3;
+		break;
+	default:
+		core_val = 0;
+		agc_val = 1;
+		break;
+	}
+
+	mt76_rmw_field(dev, MT_BBP(CORE, 1), MT_BBP_CORE_R1_BW, core_val);
+	mt76_rmw_field(dev, MT_BBP(AGC, 0), MT_BBP_AGC_R0_BW, agc_val);
+	mt76_rmw_field(dev, MT_BBP(AGC, 0), MT_BBP_AGC_R0_CTRL_CHAN, ctrl);
+	mt76_rmw_field(dev, MT_BBP(TXBE, 0), MT_BBP_TXBE_R0_CTRL_CHAN, ctrl);
+}
+EXPORT_SYMBOL_GPL(mt76x2_phy_set_bw);
+
+void mt76x2_phy_set_band(struct mt76x2_dev *dev, int band, bool primary_upper)
+{
+	switch (band) {
+	case NL80211_BAND_2GHZ:
+		mt76_set(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_2G);
+		mt76_clear(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_5G);
+		break;
+	case NL80211_BAND_5GHZ:
+		mt76_clear(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_2G);
+		mt76_set(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_5G);
+		break;
+	}
+
+	mt76_rmw_field(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_UPPER_40M,
+		       primary_upper);
+}
+EXPORT_SYMBOL_GPL(mt76x2_phy_set_band);
+
+int mt76x2_phy_get_min_avg_rssi(struct mt76x2_dev *dev)
+{
+	struct mt76x2_sta *sta;
+	struct mt76_wcid *wcid;
+	int i, j, min_rssi = 0;
+	s8 cur_rssi;
+
+	local_bh_disable();
+	rcu_read_lock();
+
+	for (i = 0; i < ARRAY_SIZE(dev->wcid_mask); i++) {
+		unsigned long mask = dev->wcid_mask[i];
+
+		if (!mask)
+			continue;
+
+		for (j = i * BITS_PER_LONG; mask; j++, mask >>= 1) {
+			if (!(mask & 1))
+				continue;
+
+			wcid = rcu_dereference(dev->wcid[j]);
+			if (!wcid)
+				continue;
+
+			sta = container_of(wcid, struct mt76x2_sta, wcid);
+			spin_lock(&dev->mt76.rx_lock);
+			if (sta->inactive_count++ < 5)
+				cur_rssi = ewma_signal_read(&sta->rssi);
+			else
+				cur_rssi = 0;
+			spin_unlock(&dev->mt76.rx_lock);
+
+			if (cur_rssi < min_rssi)
+				min_rssi = cur_rssi;
+		}
+	}
+
+	rcu_read_unlock();
+	local_bh_enable();
+
+	if (!min_rssi)
+		return -75;
+
+	return min_rssi;
+}
+EXPORT_SYMBOL_GPL(mt76x2_phy_get_min_avg_rssi);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_regs.h b/drivers/net/wireless/mediatek/mt76/mt76x2_regs.h
index b9c334d9e5b8..1551ea453180 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_regs.h
@@ -75,6 +75,21 @@
 
 #define MT_XO_CTRL7			0x011c
 
+#define MT_USB_U3DMA_CFG		0x9018
+#define MT_USB_DMA_CFG_RX_BULK_AGG_TOUT	GENMASK(7, 0)
+#define MT_USB_DMA_CFG_RX_BULK_AGG_LMT	GENMASK(15, 8)
+#define MT_USB_DMA_CFG_UDMA_TX_WL_DROP	BIT(16)
+#define MT_USB_DMA_CFG_WAKE_UP_EN	BIT(17)
+#define MT_USB_DMA_CFG_RX_DROP_OR_PAD	BIT(18)
+#define MT_USB_DMA_CFG_TX_CLR		BIT(19)
+#define MT_USB_DMA_CFG_TXOP_HALT	BIT(20)
+#define MT_USB_DMA_CFG_RX_BULK_AGG_EN	BIT(21)
+#define MT_USB_DMA_CFG_RX_BULK_EN	BIT(22)
+#define MT_USB_DMA_CFG_TX_BULK_EN	BIT(23)
+#define MT_USB_DMA_CFG_EP_OUT_VALID	GENMASK(29, 24)
+#define MT_USB_DMA_CFG_RX_BUSY		BIT(30)
+#define MT_USB_DMA_CFG_TX_BUSY		BIT(31)
+
 #define MT_WLAN_MTC_CTRL		0x10148
 #define MT_WLAN_MTC_CTRL_MTCMOS_PWR_UP	BIT(0)
 #define MT_WLAN_MTC_CTRL_PWR_ACK	BIT(12)
@@ -150,6 +165,9 @@
 #define MT_TX_HW_QUEUE_MCU		8
 #define MT_TX_HW_QUEUE_MGMT		9
 
+#define MT_US_CYC_CFG			0x02a4
+#define MT_US_CYC_CNT			GENMASK(7, 0)
+
 #define MT_PBF_SYS_CTRL			0x0400
 #define MT_PBF_SYS_CTRL_MCU_RESET	BIT(0)
 #define MT_PBF_SYS_CTRL_DMA_RESET	BIT(1)
@@ -202,6 +220,11 @@
 
 #define MT_FCE_WLAN_FLOW_CONTROL1	0x0824
 
+#define MT_TX_CPU_FROM_FCE_BASE_PTR	0x09a0
+#define MT_TX_CPU_FROM_FCE_MAX_COUNT	0x09a4
+#define MT_FCE_PDMA_GLOBAL_CONF		0x09c4
+#define MT_FCE_SKIP_FS			0x0a6c
+
 #define MT_PAUSE_ENABLE_CONTROL1	0x0a38
 
 #define MT_MAC_CSR0			0x1000
@@ -214,6 +237,7 @@
 
 #define MT_MAC_ADDR_DW0			0x1008
 #define MT_MAC_ADDR_DW1			0x100c
+#define MT_MAC_ADDR_DW1_U2ME_MASK	GENMASK(23, 16)
 
 #define MT_MAC_BSSID_DW0		0x1010
 #define MT_MAC_BSSID_DW1		0x1014
@@ -351,6 +375,7 @@
 #define MT_TX_TIMEOUT_CFG_ACKTO		GENMASK(15, 8)
 
 #define MT_TX_RETRY_CFG			0x134c
+#define MT_TX_LINK_CFG			0x1350
 #define MT_VHT_HT_FBK_CFG1		0x1358
 
 #define MT_PROT_CFG_RATE		GENMASK(15, 0)
@@ -425,6 +450,7 @@
 #define MT_RX_FILTR_CFG_BAR		BIT(15)
 #define MT_RX_FILTR_CFG_CTRL_RSV	BIT(16)
 
+#define MT_AUTO_RSP_CFG			0x1404
 #define MT_LEGACY_BASIC_RATE		0x1408
 #define MT_HT_BASIC_RATE		0x140c
 
@@ -460,6 +486,10 @@
 #define MT_RX_STAT_2_DUP_ERRORS		GENMASK(15, 0)
 #define MT_RX_STAT_2_OVERFLOW_ERRORS	GENMASK(31, 16)
 
+#define MT_TX_STA_0			0x170c
+#define MT_TX_STA_1			0x1710
+#define MT_TX_STA_2			0x1714
+
 #define MT_TX_STAT_FIFO			0x1718
 #define MT_TX_STAT_FIFO_VALID		BIT(0)
 #define MT_TX_STAT_FIFO_SUCCESS		BIT(5)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c b/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c
index e46eafc4c436..4c907882e8b0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c
@@ -23,129 +23,6 @@ struct beacon_bc_data {
 	struct sk_buff *tail[8];
 };
 
-void mt76x2_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control,
-	     struct sk_buff *skb)
-{
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-	struct mt76x2_dev *dev = hw->priv;
-	struct ieee80211_vif *vif = info->control.vif;
-	struct mt76_wcid *wcid = &dev->global_wcid;
-
-	if (control->sta) {
-		struct mt76x2_sta *msta;
-
-		msta = (struct mt76x2_sta *) control->sta->drv_priv;
-		wcid = &msta->wcid;
-		/* sw encrypted frames */
-		if (!info->control.hw_key && wcid->hw_key_idx != -1)
-			control->sta = NULL;
-	}
-
-	if (vif && !control->sta) {
-		struct mt76x2_vif *mvif;
-
-		mvif = (struct mt76x2_vif *) vif->drv_priv;
-		wcid = &mvif->group_wcid;
-	}
-
-	mt76_tx(&dev->mt76, control->sta, wcid, skb);
-}
-
-void mt76x2_tx_complete(struct mt76x2_dev *dev, struct sk_buff *skb)
-{
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-
-	if (info->flags & IEEE80211_TX_CTL_AMPDU) {
-		ieee80211_free_txskb(mt76_hw(dev), skb);
-	} else {
-		ieee80211_tx_info_clear_status(info);
-		info->status.rates[0].idx = -1;
-		info->flags |= IEEE80211_TX_STAT_ACK;
-		ieee80211_tx_status(mt76_hw(dev), skb);
-	}
-}
-
-s8 mt76x2_tx_get_max_txpwr_adj(struct mt76x2_dev *dev,
-			       const struct ieee80211_tx_rate *rate)
-{
-	s8 max_txpwr;
-
-	if (rate->flags & IEEE80211_TX_RC_VHT_MCS) {
-		u8 mcs = ieee80211_rate_get_vht_mcs(rate);
-
-		if (mcs == 8 || mcs == 9) {
-			max_txpwr = dev->rate_power.vht[8];
-		} else {
-			u8 nss, idx;
-
-			nss = ieee80211_rate_get_vht_nss(rate);
-			idx = ((nss - 1) << 3) + mcs;
-			max_txpwr = dev->rate_power.ht[idx & 0xf];
-		}
-	} else if (rate->flags & IEEE80211_TX_RC_MCS) {
-		max_txpwr = dev->rate_power.ht[rate->idx & 0xf];
-	} else {
-		enum nl80211_band band = dev->mt76.chandef.chan->band;
-
-		if (band == NL80211_BAND_2GHZ) {
-			const struct ieee80211_rate *r;
-			struct wiphy *wiphy = mt76_hw(dev)->wiphy;
-			struct mt76_rate_power *rp = &dev->rate_power;
-
-			r = &wiphy->bands[band]->bitrates[rate->idx];
-			if (r->flags & IEEE80211_RATE_SHORT_PREAMBLE)
-				max_txpwr = rp->cck[r->hw_value & 0x3];
-			else
-				max_txpwr = rp->ofdm[r->hw_value & 0x7];
-		} else {
-			max_txpwr = dev->rate_power.ofdm[rate->idx & 0x7];
-		}
-	}
-
-	return max_txpwr;
-}
-
-s8 mt76x2_tx_get_txpwr_adj(struct mt76x2_dev *dev, s8 txpwr, s8 max_txpwr_adj)
-{
-	txpwr = min_t(s8, txpwr, dev->txpower_conf);
-	txpwr -= (dev->target_power + dev->target_power_delta[0]);
-	txpwr = min_t(s8, txpwr, max_txpwr_adj);
-
-	if (!dev->enable_tpc)
-		return 0;
-	else if (txpwr >= 0)
-		return min_t(s8, txpwr, 7);
-	else
-		return (txpwr < -16) ? 8 : (txpwr + 32) / 2;
-}
-
-void mt76x2_tx_set_txpwr_auto(struct mt76x2_dev *dev, s8 txpwr)
-{
-	s8 txpwr_adj;
-
-	txpwr_adj = mt76x2_tx_get_txpwr_adj(dev, txpwr,
-					    dev->rate_power.ofdm[4]);
-	mt76_rmw_field(dev, MT_PROT_AUTO_TX_CFG,
-		       MT_PROT_AUTO_TX_CFG_PROT_PADJ, txpwr_adj);
-	mt76_rmw_field(dev, MT_PROT_AUTO_TX_CFG,
-		       MT_PROT_AUTO_TX_CFG_AUTO_PADJ, txpwr_adj);
-}
-
-static int mt76x2_insert_hdr_pad(struct sk_buff *skb)
-{
-	int len = ieee80211_get_hdrlen_from_skb(skb);
-
-	if (len % 4 == 0)
-		return 0;
-
-	skb_push(skb, 2);
-	memmove(skb->data, skb->data + 2, len);
-
-	skb->data[len] = 0;
-	skb->data[len + 1] = 0;
-	return 2;
-}
-
 int mt76x2_tx_prepare_skb(struct mt76_dev *mdev, void *txwi,
 			  struct sk_buff *skb, struct mt76_queue *q,
 			  struct mt76_wcid *wcid, struct ieee80211_sta *sta,
@@ -159,7 +36,7 @@ int mt76x2_tx_prepare_skb(struct mt76_dev *mdev, void *txwi,
 	if (q == &dev->mt76.q_tx[MT_TXQ_PSD] && wcid && wcid->idx < 128)
 		mt76x2_mac_wcid_set_drop(dev, wcid->idx, false);
 
-	mt76x2_mac_write_txwi(dev, txwi, skb, wcid, sta);
+	mt76x2_mac_write_txwi(dev, txwi, skb, wcid, sta, skb->len);
 
 	ret = mt76x2_insert_hdr_pad(skb);
 	if (ret < 0)
@@ -218,6 +95,37 @@ mt76x2_add_buffered_bc(void *priv, u8 *mac, struct ieee80211_vif *vif)
 	data->tail[mvif->idx] = skb;
 }
 
+static void
+mt76x2_resync_beacon_timer(struct mt76x2_dev *dev)
+{
+	u32 timer_val = dev->beacon_int << 4;
+
+	dev->tbtt_count++;
+
+	/*
+	 * Beacon timer drifts by 1us every tick, the timer is configured
+	 * in 1/16 TU (64us) units.
+	 */
+	if (dev->tbtt_count < 62)
+		return;
+
+	if (dev->tbtt_count >= 64) {
+		dev->tbtt_count = 0;
+		return;
+	}
+
+	/*
+	 * The updated beacon interval takes effect after two TBTT, because
+	 * at this point the original interval has already been loaded into
+	 * the next TBTT_TIMER value
+	 */
+	if (dev->tbtt_count == 62)
+		timer_val -= 1;
+
+	mt76_rmw_field(dev, MT_BEACON_TIME_CFG,
+		       MT_BEACON_TIME_CFG_INTVAL, timer_val);
+}
+
 void mt76x2_pre_tbtt_tasklet(unsigned long arg)
 {
 	struct mt76x2_dev *dev = (struct mt76x2_dev *) arg;
@@ -226,6 +134,8 @@ void mt76x2_pre_tbtt_tasklet(unsigned long arg)
 	struct sk_buff *skb;
 	int i, nframes;
 
+	mt76x2_resync_beacon_timer(dev);
+
 	data.dev = dev;
 	__skb_queue_head_init(&data.q);
 
@@ -256,7 +166,8 @@ void mt76x2_pre_tbtt_tasklet(unsigned long arg)
 		struct ieee80211_vif *vif = info->control.vif;
 		struct mt76x2_vif *mvif = (struct mt76x2_vif *) vif->drv_priv;
 
-		mt76_tx_queue_skb(&dev->mt76, q, skb, &mvif->group_wcid, NULL);
+		mt76_dma_tx_queue_skb(&dev->mt76, q, skb, &mvif->group_wcid,
+				      NULL);
 	}
 	spin_unlock_bh(&q->lock);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_tx_common.c b/drivers/net/wireless/mediatek/mt76/mt76x2_tx_common.c
new file mode 100644
index 000000000000..36afb166fa3f
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_tx_common.c
@@ -0,0 +1,149 @@
+/*
+ * Copyright (C) 2016 Felix Fietkau <nbd@nbd.name>
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76x2.h"
+#include "mt76x2_dma.h"
+
+void mt76x2_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control,
+	       struct sk_buff *skb)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct mt76x2_dev *dev = hw->priv;
+	struct ieee80211_vif *vif = info->control.vif;
+	struct mt76_wcid *wcid = &dev->global_wcid;
+
+	if (control->sta) {
+		struct mt76x2_sta *msta;
+
+		msta = (struct mt76x2_sta *)control->sta->drv_priv;
+		wcid = &msta->wcid;
+		/* sw encrypted frames */
+		if (!info->control.hw_key && wcid->hw_key_idx != -1)
+			control->sta = NULL;
+	}
+
+	if (vif && !control->sta) {
+		struct mt76x2_vif *mvif;
+
+		mvif = (struct mt76x2_vif *)vif->drv_priv;
+		wcid = &mvif->group_wcid;
+	}
+
+	mt76_tx(&dev->mt76, control->sta, wcid, skb);
+}
+EXPORT_SYMBOL_GPL(mt76x2_tx);
+
+int mt76x2_insert_hdr_pad(struct sk_buff *skb)
+{
+	int len = ieee80211_get_hdrlen_from_skb(skb);
+
+	if (len % 4 == 0)
+		return 0;
+
+	skb_push(skb, 2);
+	memmove(skb->data, skb->data + 2, len);
+
+	skb->data[len] = 0;
+	skb->data[len + 1] = 0;
+	return 2;
+}
+EXPORT_SYMBOL_GPL(mt76x2_insert_hdr_pad);
+
+s8 mt76x2_tx_get_max_txpwr_adj(struct mt76x2_dev *dev,
+			       const struct ieee80211_tx_rate *rate)
+{
+	s8 max_txpwr;
+
+	if (rate->flags & IEEE80211_TX_RC_VHT_MCS) {
+		u8 mcs = ieee80211_rate_get_vht_mcs(rate);
+
+		if (mcs == 8 || mcs == 9) {
+			max_txpwr = dev->rate_power.vht[8];
+		} else {
+			u8 nss, idx;
+
+			nss = ieee80211_rate_get_vht_nss(rate);
+			idx = ((nss - 1) << 3) + mcs;
+			max_txpwr = dev->rate_power.ht[idx & 0xf];
+		}
+	} else if (rate->flags & IEEE80211_TX_RC_MCS) {
+		max_txpwr = dev->rate_power.ht[rate->idx & 0xf];
+	} else {
+		enum nl80211_band band = dev->mt76.chandef.chan->band;
+
+		if (band == NL80211_BAND_2GHZ) {
+			const struct ieee80211_rate *r;
+			struct wiphy *wiphy = mt76_hw(dev)->wiphy;
+			struct mt76_rate_power *rp = &dev->rate_power;
+
+			r = &wiphy->bands[band]->bitrates[rate->idx];
+			if (r->flags & IEEE80211_RATE_SHORT_PREAMBLE)
+				max_txpwr = rp->cck[r->hw_value & 0x3];
+			else
+				max_txpwr = rp->ofdm[r->hw_value & 0x7];
+		} else {
+			max_txpwr = dev->rate_power.ofdm[rate->idx & 0x7];
+		}
+	}
+
+	return max_txpwr;
+}
+EXPORT_SYMBOL_GPL(mt76x2_tx_get_max_txpwr_adj);
+
+s8 mt76x2_tx_get_txpwr_adj(struct mt76x2_dev *dev, s8 txpwr, s8 max_txpwr_adj)
+{
+	txpwr = min_t(s8, txpwr, dev->txpower_conf);
+	txpwr -= (dev->target_power + dev->target_power_delta[0]);
+	txpwr = min_t(s8, txpwr, max_txpwr_adj);
+
+	if (!dev->enable_tpc)
+		return 0;
+	else if (txpwr >= 0)
+		return min_t(s8, txpwr, 7);
+	else
+		return (txpwr < -16) ? 8 : (txpwr + 32) / 2;
+}
+EXPORT_SYMBOL_GPL(mt76x2_tx_get_txpwr_adj);
+
+void mt76x2_tx_set_txpwr_auto(struct mt76x2_dev *dev, s8 txpwr)
+{
+	s8 txpwr_adj;
+
+	txpwr_adj = mt76x2_tx_get_txpwr_adj(dev, txpwr,
+					    dev->rate_power.ofdm[4]);
+	mt76_rmw_field(dev, MT_PROT_AUTO_TX_CFG,
+		       MT_PROT_AUTO_TX_CFG_PROT_PADJ, txpwr_adj);
+	mt76_rmw_field(dev, MT_PROT_AUTO_TX_CFG,
+		       MT_PROT_AUTO_TX_CFG_AUTO_PADJ, txpwr_adj);
+}
+EXPORT_SYMBOL_GPL(mt76x2_tx_set_txpwr_auto);
+
+void mt76x2_tx_complete(struct mt76x2_dev *dev, struct sk_buff *skb)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+
+	if (info->flags & IEEE80211_TX_CTL_AMPDU) {
+		ieee80211_free_txskb(mt76_hw(dev), skb);
+	} else {
+		ieee80211_tx_info_clear_status(info);
+		info->status.rates[0].idx = -1;
+		info->flags |= IEEE80211_TX_STAT_ACK;
+		ieee80211_tx_status(mt76_hw(dev), skb);
+	}
+}
+EXPORT_SYMBOL_GPL(mt76x2_tx_complete);
+
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_usb.c b/drivers/net/wireless/mediatek/mt76/mt76x2_usb.c
new file mode 100644
index 000000000000..1428cfdee579
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_usb.c
@@ -0,0 +1,142 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include "mt76x2u.h"
+
+static const struct usb_device_id mt76x2u_device_table[] = {
+	{ USB_DEVICE(0x0b05, 0x1833) },	/* Asus USB-AC54 */
+	{ USB_DEVICE(0x0b05, 0x17eb) },	/* Asus USB-AC55 */
+	{ USB_DEVICE(0x0b05, 0x180b) },	/* Asus USB-N53 B1 */
+	{ USB_DEVICE(0x0e8d, 0x7612) },	/* Aukey USB-AC1200 */
+	{ USB_DEVICE(0x057c, 0x8503) },	/* Avm FRITZ!WLAN AC860 */
+	{ USB_DEVICE(0x7392, 0xb711) },	/* Edimax EW 7722 UAC */
+	{ USB_DEVICE(0x0846, 0x9053) },	/* Netgear A6210 */
+	{ USB_DEVICE(0x045e, 0x02e6) },	/* XBox One Wireless Adapter */
+	{ },
+};
+
+static int mt76x2u_probe(struct usb_interface *intf,
+			 const struct usb_device_id *id)
+{
+	struct usb_device *udev = interface_to_usbdev(intf);
+	struct mt76x2_dev *dev;
+	int err;
+
+	dev = mt76x2u_alloc_device(&intf->dev);
+	if (!dev)
+		return -ENOMEM;
+
+	udev = usb_get_dev(udev);
+	usb_reset_device(udev);
+
+	err = mt76u_init(&dev->mt76, intf);
+	if (err < 0)
+		goto err;
+
+	dev->mt76.rev = mt76_rr(dev, MT_ASIC_VERSION);
+	dev_info(dev->mt76.dev, "ASIC revision: %08x\n", dev->mt76.rev);
+
+	err = mt76x2u_register_device(dev);
+	if (err < 0)
+		goto err;
+
+	return 0;
+
+err:
+	ieee80211_free_hw(mt76_hw(dev));
+	usb_set_intfdata(intf, NULL);
+	usb_put_dev(udev);
+
+	return err;
+}
+
+static void mt76x2u_disconnect(struct usb_interface *intf)
+{
+	struct usb_device *udev = interface_to_usbdev(intf);
+	struct mt76x2_dev *dev = usb_get_intfdata(intf);
+	struct ieee80211_hw *hw = mt76_hw(dev);
+
+	set_bit(MT76_REMOVED, &dev->mt76.state);
+	ieee80211_unregister_hw(hw);
+	mt76x2u_cleanup(dev);
+
+	ieee80211_free_hw(hw);
+	usb_set_intfdata(intf, NULL);
+	usb_put_dev(udev);
+}
+
+static int __maybe_unused mt76x2u_suspend(struct usb_interface *intf,
+					  pm_message_t state)
+{
+	struct mt76x2_dev *dev = usb_get_intfdata(intf);
+	struct mt76_usb *usb = &dev->mt76.usb;
+
+	mt76u_stop_queues(&dev->mt76);
+	mt76x2u_stop_hw(dev);
+	usb_kill_urb(usb->mcu.res.urb);
+
+	return 0;
+}
+
+static int __maybe_unused mt76x2u_resume(struct usb_interface *intf)
+{
+	struct mt76x2_dev *dev = usb_get_intfdata(intf);
+	struct mt76_usb *usb = &dev->mt76.usb;
+	int err;
+
+	reinit_completion(&usb->mcu.cmpl);
+	err = mt76u_submit_buf(&dev->mt76, USB_DIR_IN,
+			       MT_EP_IN_CMD_RESP,
+			       &usb->mcu.res, GFP_KERNEL,
+			       mt76u_mcu_complete_urb,
+			       &usb->mcu.cmpl);
+	if (err < 0)
+		return err;
+
+	err = mt76u_submit_rx_buffers(&dev->mt76);
+	if (err < 0)
+		return err;
+
+	tasklet_enable(&usb->rx_tasklet);
+	tasklet_enable(&usb->tx_tasklet);
+
+	return mt76x2u_init_hardware(dev);
+}
+
+MODULE_DEVICE_TABLE(usb, mt76x2u_device_table);
+MODULE_FIRMWARE(MT7662U_FIRMWARE);
+MODULE_FIRMWARE(MT7662U_ROM_PATCH);
+
+static struct usb_driver mt76x2u_driver = {
+	.name		= KBUILD_MODNAME,
+	.id_table	= mt76x2u_device_table,
+	.probe		= mt76x2u_probe,
+	.disconnect	= mt76x2u_disconnect,
+#ifdef CONFIG_PM
+	.suspend	= mt76x2u_suspend,
+	.resume		= mt76x2u_resume,
+	.reset_resume	= mt76x2u_resume,
+#endif /* CONFIG_PM */
+	.soft_unbind	= 1,
+	.disable_hub_initiated_lpm = 1,
+};
+module_usb_driver(mt76x2u_driver);
+
+MODULE_AUTHOR("Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2u.h b/drivers/net/wireless/mediatek/mt76/mt76x2u.h
new file mode 100644
index 000000000000..008092f0cd8a
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2u.h
@@ -0,0 +1,83 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#ifndef __MT76x2U_H
+#define __MT76x2U_H
+
+#include <linux/device.h>
+
+#include "mt76x2.h"
+#include "mt76x2_dma.h"
+#include "mt76x2_mcu.h"
+
+#define MT7612U_EEPROM_SIZE		512
+
+#define MT_USB_AGGR_SIZE_LIMIT		21 /* 1024B unit */
+#define MT_USB_AGGR_TIMEOUT		0x80 /* 33ns unit */
+
+extern const struct ieee80211_ops mt76x2u_ops;
+
+struct mt76x2_dev *mt76x2u_alloc_device(struct device *pdev);
+int mt76x2u_register_device(struct mt76x2_dev *dev);
+int mt76x2u_init_hardware(struct mt76x2_dev *dev);
+void mt76x2u_cleanup(struct mt76x2_dev *dev);
+void mt76x2u_stop_hw(struct mt76x2_dev *dev);
+
+void mt76x2u_mac_setaddr(struct mt76x2_dev *dev, u8 *addr);
+int mt76x2u_mac_reset(struct mt76x2_dev *dev);
+void mt76x2u_mac_resume(struct mt76x2_dev *dev);
+int mt76x2u_mac_start(struct mt76x2_dev *dev);
+int mt76x2u_mac_stop(struct mt76x2_dev *dev);
+
+int mt76x2u_phy_set_channel(struct mt76x2_dev *dev,
+			    struct cfg80211_chan_def *chandef);
+void mt76x2u_phy_calibrate(struct work_struct *work);
+void mt76x2u_phy_channel_calibrate(struct mt76x2_dev *dev);
+void mt76x2u_phy_set_txdac(struct mt76x2_dev *dev);
+void mt76x2u_phy_set_rxpath(struct mt76x2_dev *dev);
+
+void mt76x2u_mcu_complete_urb(struct urb *urb);
+int mt76x2u_mcu_set_channel(struct mt76x2_dev *dev, u8 channel, u8 bw,
+			    u8 bw_index, bool scan);
+int mt76x2u_mcu_calibrate(struct mt76x2_dev *dev, enum mcu_calibration type,
+			  u32 val);
+int mt76x2u_mcu_tssi_comp(struct mt76x2_dev *dev,
+			  struct mt76x2_tssi_comp *tssi_data);
+int mt76x2u_mcu_init_gain(struct mt76x2_dev *dev, u8 channel, u32 gain,
+			  bool force);
+int mt76x2u_mcu_set_dynamic_vga(struct mt76x2_dev *dev, u8 channel, bool ap,
+				bool ext, int rssi, u32 false_cca);
+int mt76x2u_mcu_set_radio_state(struct mt76x2_dev *dev, bool val);
+int mt76x2u_mcu_load_cr(struct mt76x2_dev *dev, u8 type,
+			u8 temp_level, u8 channel);
+int mt76x2u_mcu_init(struct mt76x2_dev *dev);
+int mt76x2u_mcu_fw_init(struct mt76x2_dev *dev);
+void mt76x2u_mcu_deinit(struct mt76x2_dev *dev);
+
+int mt76x2u_alloc_queues(struct mt76x2_dev *dev);
+void mt76x2u_queues_deinit(struct mt76x2_dev *dev);
+void mt76x2u_stop_queues(struct mt76x2_dev *dev);
+bool mt76x2u_tx_status_data(struct mt76_dev *mdev, u8 *update);
+int mt76x2u_tx_prepare_skb(struct mt76_dev *mdev, void *data,
+			   struct sk_buff *skb, struct mt76_queue *q,
+			   struct mt76_wcid *wcid, struct ieee80211_sta *sta,
+			   u32 *tx_info);
+void mt76x2u_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue *q,
+			     struct mt76_queue_entry *e, bool flush);
+int mt76x2u_skb_dma_info(struct sk_buff *skb, enum dma_msg_port port,
+			 u32 flags);
+
+#endif /* __MT76x2U_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2u_core.c b/drivers/net/wireless/mediatek/mt76/mt76x2u_core.c
new file mode 100644
index 000000000000..1ca5dd05b265
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2u_core.c
@@ -0,0 +1,108 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76x2u.h"
+#include "dma.h"
+
+static void mt76x2u_remove_dma_hdr(struct sk_buff *skb)
+{
+	int hdr_len;
+
+	skb_pull(skb, sizeof(struct mt76x2_txwi) + MT_DMA_HDR_LEN);
+	hdr_len = ieee80211_get_hdrlen_from_skb(skb);
+	if (hdr_len % 4) {
+		memmove(skb->data + 2, skb->data, hdr_len);
+		skb_pull(skb, 2);
+	}
+}
+
+static int
+mt76x2u_check_skb_rooms(struct sk_buff *skb)
+{
+	int hdr_len = ieee80211_get_hdrlen_from_skb(skb);
+	u32 need_head;
+
+	need_head = sizeof(struct mt76x2_txwi) + MT_DMA_HDR_LEN;
+	if (hdr_len % 4)
+		need_head += 2;
+	return skb_cow(skb, need_head);
+}
+
+static int
+mt76x2u_set_txinfo(struct sk_buff *skb,
+		   struct mt76_wcid *wcid, u8 ep)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	enum mt76x2_qsel qsel;
+	u32 flags;
+
+	if ((info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) ||
+	    ep == MT_EP_OUT_HCCA)
+		qsel = MT_QSEL_MGMT;
+	else
+		qsel = MT_QSEL_EDCA;
+
+	flags = FIELD_PREP(MT_TXD_INFO_QSEL, qsel) |
+		MT_TXD_INFO_80211;
+	if (!wcid || wcid->hw_key_idx == 0xff || wcid->sw_iv)
+		flags |= MT_TXD_INFO_WIV;
+
+	return mt76u_skb_dma_info(skb, WLAN_PORT, flags);
+}
+
+bool mt76x2u_tx_status_data(struct mt76_dev *mdev, u8 *update)
+{
+	struct mt76x2_dev *dev = container_of(mdev, struct mt76x2_dev, mt76);
+	struct mt76x2_tx_status stat;
+
+	if (!mt76x2_mac_load_tx_status(dev, &stat))
+		return false;
+
+	mt76x2_send_tx_status(dev, &stat, update);
+
+	return true;
+}
+
+int mt76x2u_tx_prepare_skb(struct mt76_dev *mdev, void *data,
+			   struct sk_buff *skb, struct mt76_queue *q,
+			   struct mt76_wcid *wcid, struct ieee80211_sta *sta,
+			   u32 *tx_info)
+{
+	struct mt76x2_dev *dev = container_of(mdev, struct mt76x2_dev, mt76);
+	struct mt76x2_txwi *txwi;
+	int err, len = skb->len;
+
+	err = mt76x2u_check_skb_rooms(skb);
+	if (err < 0)
+		return -ENOMEM;
+
+	mt76x2_insert_hdr_pad(skb);
+
+	txwi = skb_push(skb, sizeof(struct mt76x2_txwi));
+	mt76x2_mac_write_txwi(dev, txwi, skb, wcid, sta, len);
+
+	return mt76x2u_set_txinfo(skb, wcid, q2ep(q->hw_idx));
+}
+
+void mt76x2u_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue *q,
+			     struct mt76_queue_entry *e, bool flush)
+{
+	struct mt76x2_dev *dev = container_of(mdev, struct mt76x2_dev, mt76);
+
+	mt76x2u_remove_dma_hdr(e->skb);
+	mt76x2_tx_complete(dev, e->skb);
+}
+
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2u_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2u_init.c
new file mode 100644
index 000000000000..9b81e7641c06
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2u_init.c
@@ -0,0 +1,318 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/delay.h>
+
+#include "mt76x2u.h"
+#include "mt76x2_eeprom.h"
+
+static void mt76x2u_init_dma(struct mt76x2_dev *dev)
+{
+	u32 val = mt76_rr(dev, MT_VEND_ADDR(CFG, MT_USB_U3DMA_CFG));
+
+	val |= MT_USB_DMA_CFG_RX_DROP_OR_PAD |
+	       MT_USB_DMA_CFG_RX_BULK_EN |
+	       MT_USB_DMA_CFG_TX_BULK_EN;
+
+	/* disable AGGR_BULK_RX in order to receive one
+	 * frame in each rx urb and avoid copies
+	 */
+	val &= ~MT_USB_DMA_CFG_RX_BULK_AGG_EN;
+	mt76_wr(dev, MT_VEND_ADDR(CFG, MT_USB_U3DMA_CFG), val);
+}
+
+static void mt76x2u_power_on_rf_patch(struct mt76x2_dev *dev)
+{
+	mt76_set(dev, MT_VEND_ADDR(CFG, 0x130), BIT(0) | BIT(16));
+	udelay(1);
+
+	mt76_clear(dev, MT_VEND_ADDR(CFG, 0x1c), 0xff);
+	mt76_set(dev, MT_VEND_ADDR(CFG, 0x1c), 0x30);
+
+	mt76_wr(dev, MT_VEND_ADDR(CFG, 0x14), 0x484f);
+	udelay(1);
+
+	mt76_set(dev, MT_VEND_ADDR(CFG, 0x130), BIT(17));
+	usleep_range(150, 200);
+
+	mt76_clear(dev, MT_VEND_ADDR(CFG, 0x130), BIT(16));
+	usleep_range(50, 100);
+
+	mt76_set(dev, MT_VEND_ADDR(CFG, 0x14c), BIT(19) | BIT(20));
+}
+
+static void mt76x2u_power_on_rf(struct mt76x2_dev *dev, int unit)
+{
+	int shift = unit ? 8 : 0;
+	u32 val = (BIT(1) | BIT(3) | BIT(4) | BIT(5)) << shift;
+
+	/* Enable RF BG */
+	mt76_set(dev, MT_VEND_ADDR(CFG, 0x130), BIT(0) << shift);
+	usleep_range(10, 20);
+
+	/* Enable RFDIG LDO/AFE/ABB/ADDA */
+	mt76_set(dev, MT_VEND_ADDR(CFG, 0x130), val);
+	usleep_range(10, 20);
+
+	/* Switch RFDIG power to internal LDO */
+	mt76_clear(dev, MT_VEND_ADDR(CFG, 0x130), BIT(2) << shift);
+	usleep_range(10, 20);
+
+	mt76x2u_power_on_rf_patch(dev);
+
+	mt76_set(dev, 0x530, 0xf);
+}
+
+static void mt76x2u_power_on(struct mt76x2_dev *dev)
+{
+	u32 val;
+
+	/* Turn on WL MTCMOS */
+	mt76_set(dev, MT_VEND_ADDR(CFG, 0x148),
+		 MT_WLAN_MTC_CTRL_MTCMOS_PWR_UP);
+
+	val = MT_WLAN_MTC_CTRL_STATE_UP |
+	      MT_WLAN_MTC_CTRL_PWR_ACK |
+	      MT_WLAN_MTC_CTRL_PWR_ACK_S;
+
+	mt76_poll(dev, MT_VEND_ADDR(CFG, 0x148), val, val, 1000);
+
+	mt76_clear(dev, MT_VEND_ADDR(CFG, 0x148), 0x7f << 16);
+	usleep_range(10, 20);
+
+	mt76_clear(dev, MT_VEND_ADDR(CFG, 0x148), 0xf << 24);
+	usleep_range(10, 20);
+
+	mt76_set(dev, MT_VEND_ADDR(CFG, 0x148), 0xf << 24);
+	mt76_clear(dev, MT_VEND_ADDR(CFG, 0x148), 0xfff);
+
+	/* Turn on AD/DA power down */
+	mt76_clear(dev, MT_VEND_ADDR(CFG, 0x1204), BIT(3));
+
+	/* WLAN function enable */
+	mt76_set(dev, MT_VEND_ADDR(CFG, 0x80), BIT(0));
+
+	/* Release BBP software reset */
+	mt76_clear(dev, MT_VEND_ADDR(CFG, 0x64), BIT(18));
+
+	mt76x2u_power_on_rf(dev, 0);
+	mt76x2u_power_on_rf(dev, 1);
+}
+
+static int mt76x2u_init_eeprom(struct mt76x2_dev *dev)
+{
+	u32 val, i;
+
+	dev->mt76.eeprom.data = devm_kzalloc(dev->mt76.dev,
+					     MT7612U_EEPROM_SIZE,
+					     GFP_KERNEL);
+	dev->mt76.eeprom.size = MT7612U_EEPROM_SIZE;
+	if (!dev->mt76.eeprom.data)
+		return -ENOMEM;
+
+	for (i = 0; i + 4 <= MT7612U_EEPROM_SIZE; i += 4) {
+		val = mt76_rr(dev, MT_VEND_ADDR(EEPROM, i));
+		put_unaligned_le32(val, dev->mt76.eeprom.data + i);
+	}
+
+	mt76x2_eeprom_parse_hw_cap(dev);
+	return 0;
+}
+
+struct mt76x2_dev *mt76x2u_alloc_device(struct device *pdev)
+{
+	static const struct mt76_driver_ops drv_ops = {
+		.tx_prepare_skb = mt76x2u_tx_prepare_skb,
+		.tx_complete_skb = mt76x2u_tx_complete_skb,
+		.tx_status_data = mt76x2u_tx_status_data,
+		.rx_skb = mt76x2_queue_rx_skb,
+	};
+	struct mt76x2_dev *dev;
+	struct mt76_dev *mdev;
+
+	mdev = mt76_alloc_device(sizeof(*dev), &mt76x2u_ops);
+	if (!mdev)
+		return NULL;
+
+	dev = container_of(mdev, struct mt76x2_dev, mt76);
+	mdev->dev = pdev;
+	mdev->drv = &drv_ops;
+
+	mutex_init(&dev->mutex);
+
+	return dev;
+}
+
+static void mt76x2u_init_beacon_offsets(struct mt76x2_dev *dev)
+{
+	mt76_wr(dev, MT_BCN_OFFSET(0), 0x18100800);
+	mt76_wr(dev, MT_BCN_OFFSET(1), 0x38302820);
+	mt76_wr(dev, MT_BCN_OFFSET(2), 0x58504840);
+	mt76_wr(dev, MT_BCN_OFFSET(3), 0x78706860);
+}
+
+int mt76x2u_init_hardware(struct mt76x2_dev *dev)
+{
+	static const u16 beacon_offsets[] = {
+		/* 512 byte per beacon */
+		0xc000, 0xc200, 0xc400, 0xc600,
+		0xc800, 0xca00, 0xcc00, 0xce00,
+		0xd000, 0xd200, 0xd400, 0xd600,
+		0xd800, 0xda00, 0xdc00, 0xde00
+	};
+	const struct mt76_wcid_addr addr = {
+		.macaddr = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff},
+		.ba_mask = 0,
+	};
+	int i, err;
+
+	dev->beacon_offsets = beacon_offsets;
+
+	mt76x2_reset_wlan(dev, true);
+	mt76x2u_power_on(dev);
+
+	if (!mt76x2_wait_for_mac(dev))
+		return -ETIMEDOUT;
+
+	err = mt76x2u_mcu_fw_init(dev);
+	if (err < 0)
+		return err;
+
+	if (!mt76_poll_msec(dev, MT_WPDMA_GLO_CFG,
+			    MT_WPDMA_GLO_CFG_TX_DMA_BUSY |
+			    MT_WPDMA_GLO_CFG_RX_DMA_BUSY, 0, 100))
+		return -EIO;
+
+	/* wait for asic ready after fw load. */
+	if (!mt76x2_wait_for_mac(dev))
+		return -ETIMEDOUT;
+
+	mt76_wr(dev, MT_HEADER_TRANS_CTRL_REG, 0);
+	mt76_wr(dev, MT_TSO_CTRL, 0);
+
+	mt76x2u_init_dma(dev);
+
+	err = mt76x2u_mcu_init(dev);
+	if (err < 0)
+		return err;
+
+	err = mt76x2u_mac_reset(dev);
+	if (err < 0)
+		return err;
+
+	mt76x2u_mac_setaddr(dev, dev->mt76.eeprom.data + MT_EE_MAC_ADDR);
+	dev->rxfilter = mt76_rr(dev, MT_RX_FILTR_CFG);
+
+	mt76x2u_init_beacon_offsets(dev);
+
+	if (!mt76x2_wait_for_bbp(dev))
+		return -ETIMEDOUT;
+
+	/* reset wcid table */
+	for (i = 0; i < 254; i++)
+		mt76_wr_copy(dev, MT_WCID_ADDR(i), &addr,
+			     sizeof(struct mt76_wcid_addr));
+
+	/* reset shared key table and pairwise key table */
+	for (i = 0; i < 4; i++)
+		mt76_wr(dev, MT_SKEY_MODE_BASE_0 + 4 * i, 0);
+	for (i = 0; i < 256; i++)
+		mt76_wr(dev, MT_WCID_ATTR(i), 1);
+
+	mt76_clear(dev, MT_BEACON_TIME_CFG,
+		   MT_BEACON_TIME_CFG_TIMER_EN |
+		   MT_BEACON_TIME_CFG_SYNC_MODE |
+		   MT_BEACON_TIME_CFG_TBTT_EN |
+		   MT_BEACON_TIME_CFG_BEACON_TX);
+
+	mt76_rmw(dev, MT_US_CYC_CFG, MT_US_CYC_CNT, 0x1e);
+	mt76_wr(dev, MT_TXOP_CTRL_CFG, 0x583f);
+
+	err = mt76x2u_mcu_load_cr(dev, MT_RF_BBP_CR, 0, 0);
+	if (err < 0)
+		return err;
+
+	mt76x2u_phy_set_rxpath(dev);
+	mt76x2u_phy_set_txdac(dev);
+
+	return mt76x2u_mac_stop(dev);
+}
+
+int mt76x2u_register_device(struct mt76x2_dev *dev)
+{
+	struct ieee80211_hw *hw = mt76_hw(dev);
+	struct wiphy *wiphy = hw->wiphy;
+	int err;
+
+	INIT_DELAYED_WORK(&dev->cal_work, mt76x2u_phy_calibrate);
+	mt76x2_init_device(dev);
+
+	err = mt76x2u_init_eeprom(dev);
+	if (err < 0)
+		return err;
+
+	err = mt76u_mcu_init_rx(&dev->mt76);
+	if (err < 0)
+		return err;
+
+	err = mt76u_alloc_queues(&dev->mt76);
+	if (err < 0)
+		goto fail;
+
+	err = mt76x2u_init_hardware(dev);
+	if (err < 0)
+		goto fail;
+
+	wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION);
+
+	err = mt76_register_device(&dev->mt76, true, mt76x2_rates,
+				   ARRAY_SIZE(mt76x2_rates));
+	if (err)
+		goto fail;
+
+	/* check hw sg support in order to enable AMSDU */
+	if (mt76u_check_sg(&dev->mt76))
+		hw->max_tx_fragments = MT_SG_MAX_SIZE;
+	else
+		hw->max_tx_fragments = 1;
+
+	set_bit(MT76_STATE_INITIALIZED, &dev->mt76.state);
+
+	mt76x2_init_debugfs(dev);
+	mt76x2_init_txpower(dev, &dev->mt76.sband_2g.sband);
+	mt76x2_init_txpower(dev, &dev->mt76.sband_5g.sband);
+
+	return 0;
+
+fail:
+	mt76x2u_cleanup(dev);
+	return err;
+}
+
+void mt76x2u_stop_hw(struct mt76x2_dev *dev)
+{
+	mt76u_stop_stat_wk(&dev->mt76);
+	cancel_delayed_work_sync(&dev->cal_work);
+	mt76x2u_mac_stop(dev);
+}
+
+void mt76x2u_cleanup(struct mt76x2_dev *dev)
+{
+	mt76x2u_mcu_set_radio_state(dev, false);
+	mt76x2u_stop_hw(dev);
+	mt76u_queues_deinit(&dev->mt76);
+	mt76x2u_mcu_deinit(dev);
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2u_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x2u_mac.c
new file mode 100644
index 000000000000..eab7ab297aa6
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2u_mac.c
@@ -0,0 +1,240 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76x2u.h"
+#include "mt76x2_eeprom.h"
+
+static void mt76x2u_mac_reset_counters(struct mt76x2_dev *dev)
+{
+	mt76_rr(dev, MT_RX_STAT_0);
+	mt76_rr(dev, MT_RX_STAT_1);
+	mt76_rr(dev, MT_RX_STAT_2);
+	mt76_rr(dev, MT_TX_STA_0);
+	mt76_rr(dev, MT_TX_STA_1);
+	mt76_rr(dev, MT_TX_STA_2);
+}
+
+static void mt76x2u_mac_fixup_xtal(struct mt76x2_dev *dev)
+{
+	s8 offset = 0;
+	u16 eep_val;
+
+	eep_val = mt76x2_eeprom_get(dev, MT_EE_XTAL_TRIM_2);
+
+	offset = eep_val & 0x7f;
+	if ((eep_val & 0xff) == 0xff)
+		offset = 0;
+	else if (eep_val & 0x80)
+		offset = 0 - offset;
+
+	eep_val >>= 8;
+	if (eep_val == 0x00 || eep_val == 0xff) {
+		eep_val = mt76x2_eeprom_get(dev, MT_EE_XTAL_TRIM_1);
+		eep_val &= 0xff;
+
+		if (eep_val == 0x00 || eep_val == 0xff)
+			eep_val = 0x14;
+	}
+
+	eep_val &= 0x7f;
+	mt76_rmw_field(dev, MT_VEND_ADDR(CFG, MT_XO_CTRL5),
+		       MT_XO_CTRL5_C2_VAL, eep_val + offset);
+	mt76_set(dev, MT_VEND_ADDR(CFG, MT_XO_CTRL6), MT_XO_CTRL6_C2_CTRL);
+
+	mt76_wr(dev, 0x504, 0x06000000);
+	mt76_wr(dev, 0x50c, 0x08800000);
+	mdelay(5);
+	mt76_wr(dev, 0x504, 0x0);
+
+	/* decrease SIFS from 16us to 13us */
+	mt76_rmw_field(dev, MT_XIFS_TIME_CFG,
+		       MT_XIFS_TIME_CFG_OFDM_SIFS, 0xd);
+	mt76_rmw_field(dev, MT_BKOFF_SLOT_CFG, MT_BKOFF_SLOT_CFG_CC_DELAY, 1);
+
+	/* init fce */
+	mt76_clear(dev, MT_FCE_L2_STUFF, MT_FCE_L2_STUFF_WR_MPDU_LEN_EN);
+
+	eep_val = mt76x2_eeprom_get(dev, MT_EE_NIC_CONF_2);
+	switch (FIELD_GET(MT_EE_NIC_CONF_2_XTAL_OPTION, eep_val)) {
+	case 0:
+		mt76_wr(dev, MT_XO_CTRL7, 0x5c1fee80);
+		break;
+	case 1:
+		mt76_wr(dev, MT_XO_CTRL7, 0x5c1feed0);
+		break;
+	default:
+		break;
+	}
+}
+
+int mt76x2u_mac_reset(struct mt76x2_dev *dev)
+{
+	mt76_wr(dev, MT_WPDMA_GLO_CFG, BIT(4) | BIT(5));
+
+	/* init pbf regs */
+	mt76_wr(dev, MT_PBF_TX_MAX_PCNT, 0xefef3f1f);
+	mt76_wr(dev, MT_PBF_RX_MAX_PCNT, 0xfebf);
+
+	mt76_write_mac_initvals(dev);
+
+	mt76_wr(dev, MT_TX_LINK_CFG, 0x1020);
+	mt76_wr(dev, MT_AUTO_RSP_CFG, 0x13);
+	mt76_wr(dev, MT_MAX_LEN_CFG, 0x2f00);
+	mt76_wr(dev, MT_TX_RTS_CFG, 0x92b20);
+
+	mt76_wr(dev, MT_WMM_AIFSN, 0x2273);
+	mt76_wr(dev, MT_WMM_CWMIN, 0x2344);
+	mt76_wr(dev, MT_WMM_CWMAX, 0x34aa);
+
+	mt76_clear(dev, MT_MAC_SYS_CTRL,
+		   MT_MAC_SYS_CTRL_RESET_CSR |
+		   MT_MAC_SYS_CTRL_RESET_BBP);
+
+	if (is_mt7612(dev))
+		mt76_clear(dev, MT_COEXCFG0, MT_COEXCFG0_COEX_EN);
+
+	mt76_set(dev, MT_EXT_CCA_CFG, 0xf000);
+	mt76_clear(dev, MT_TX_ALC_CFG_4, BIT(31));
+
+	mt76x2u_mac_fixup_xtal(dev);
+
+	return 0;
+}
+
+int mt76x2u_mac_start(struct mt76x2_dev *dev)
+{
+	mt76x2u_mac_reset_counters(dev);
+
+	mt76_wr(dev, MT_MAC_SYS_CTRL, MT_MAC_SYS_CTRL_ENABLE_TX);
+	wait_for_wpdma(dev);
+	usleep_range(50, 100);
+
+	mt76_wr(dev, MT_RX_FILTR_CFG, dev->rxfilter);
+
+	mt76_wr(dev, MT_MAC_SYS_CTRL,
+		MT_MAC_SYS_CTRL_ENABLE_TX |
+		MT_MAC_SYS_CTRL_ENABLE_RX);
+
+	return 0;
+}
+
+int mt76x2u_mac_stop(struct mt76x2_dev *dev)
+{
+	int i, count = 0, val;
+	bool stopped = false;
+	u32 rts_cfg;
+
+	if (test_bit(MT76_REMOVED, &dev->mt76.state))
+		return -EIO;
+
+	rts_cfg = mt76_rr(dev, MT_TX_RTS_CFG);
+	mt76_wr(dev, MT_TX_RTS_CFG, rts_cfg & ~MT_TX_RTS_CFG_RETRY_LIMIT);
+
+	mt76_clear(dev, MT_TXOP_CTRL_CFG, BIT(20));
+	mt76_clear(dev, MT_TXOP_HLDR_ET, BIT(1));
+
+	/* wait tx dma to stop */
+	for (i = 0; i < 2000; i++) {
+		val = mt76_rr(dev, MT_VEND_ADDR(CFG, MT_USB_U3DMA_CFG));
+		if (!(val & MT_USB_DMA_CFG_TX_BUSY) && i > 10)
+			break;
+		usleep_range(50, 100);
+	}
+
+	/* page count on TxQ */
+	for (i = 0; i < 200; i++) {
+		if (!(mt76_rr(dev, 0x0438) & 0xffffffff) &&
+		    !(mt76_rr(dev, 0x0a30) & 0x000000ff) &&
+		    !(mt76_rr(dev, 0x0a34) & 0xff00ff00))
+			break;
+		usleep_range(10, 20);
+	}
+
+	/* disable tx-rx */
+	mt76_clear(dev, MT_MAC_SYS_CTRL,
+		   MT_MAC_SYS_CTRL_ENABLE_RX |
+		   MT_MAC_SYS_CTRL_ENABLE_TX);
+
+	/* Wait for MAC to become idle */
+	for (i = 0; i < 1000; i++) {
+		if (!(mt76_rr(dev, MT_MAC_STATUS) & MT_MAC_STATUS_TX) &&
+		    !mt76_rr(dev, MT_BBP(IBI, 12))) {
+			stopped = true;
+			break;
+		}
+		usleep_range(10, 20);
+	}
+
+	if (!stopped) {
+		mt76_set(dev, MT_BBP(CORE, 4), BIT(1));
+		mt76_clear(dev, MT_BBP(CORE, 4), BIT(1));
+
+		mt76_set(dev, MT_BBP(CORE, 4), BIT(0));
+		mt76_clear(dev, MT_BBP(CORE, 4), BIT(0));
+	}
+
+	/* page count on RxQ */
+	for (i = 0; i < 200; i++) {
+		if (!(mt76_rr(dev, 0x0430) & 0x00ff0000) &&
+		    !(mt76_rr(dev, 0x0a30) & 0xffffffff) &&
+		    !(mt76_rr(dev, 0x0a34) & 0xffffffff) &&
+		    ++count > 10)
+			break;
+		msleep(50);
+	}
+
+	if (!mt76_poll(dev, MT_MAC_STATUS, MT_MAC_STATUS_RX, 0, 2000))
+		dev_warn(dev->mt76.dev, "MAC RX failed to stop\n");
+
+	/* wait rx dma to stop */
+	for (i = 0; i < 2000; i++) {
+		val = mt76_rr(dev, MT_VEND_ADDR(CFG, MT_USB_U3DMA_CFG));
+		if (!(val & MT_USB_DMA_CFG_RX_BUSY) && i > 10)
+			break;
+		usleep_range(50, 100);
+	}
+
+	mt76_wr(dev, MT_TX_RTS_CFG, rts_cfg);
+
+	return 0;
+}
+
+void mt76x2u_mac_resume(struct mt76x2_dev *dev)
+{
+	mt76_wr(dev, MT_MAC_SYS_CTRL,
+		MT_MAC_SYS_CTRL_ENABLE_TX |
+		MT_MAC_SYS_CTRL_ENABLE_RX);
+	mt76_set(dev, MT_TXOP_CTRL_CFG, BIT(20));
+	mt76_set(dev, MT_TXOP_HLDR_ET, BIT(1));
+}
+
+void mt76x2u_mac_setaddr(struct mt76x2_dev *dev, u8 *addr)
+{
+	ether_addr_copy(dev->mt76.macaddr, addr);
+
+	if (!is_valid_ether_addr(dev->mt76.macaddr)) {
+		eth_random_addr(dev->mt76.macaddr);
+		dev_info(dev->mt76.dev,
+			 "Invalid MAC address, using random address %pM\n",
+			 dev->mt76.macaddr);
+	}
+
+	mt76_wr(dev, MT_MAC_ADDR_DW0, get_unaligned_le32(dev->mt76.macaddr));
+	mt76_wr(dev, MT_MAC_ADDR_DW1,
+		get_unaligned_le16(dev->mt76.macaddr + 4) |
+		FIELD_PREP(MT_MAC_ADDR_DW1_U2ME_MASK, 0xff));
+}
+
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2u_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2u_main.c
new file mode 100644
index 000000000000..7367ba111119
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2u_main.c
@@ -0,0 +1,185 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76x2u.h"
+
+static int mt76x2u_start(struct ieee80211_hw *hw)
+{
+	struct mt76x2_dev *dev = hw->priv;
+	int ret;
+
+	mutex_lock(&dev->mutex);
+
+	ret = mt76x2u_mac_start(dev);
+	if (ret)
+		goto out;
+
+	set_bit(MT76_STATE_RUNNING, &dev->mt76.state);
+
+out:
+	mutex_unlock(&dev->mutex);
+	return ret;
+}
+
+static void mt76x2u_stop(struct ieee80211_hw *hw)
+{
+	struct mt76x2_dev *dev = hw->priv;
+
+	mutex_lock(&dev->mutex);
+	clear_bit(MT76_STATE_RUNNING, &dev->mt76.state);
+	mt76x2u_stop_hw(dev);
+	mutex_unlock(&dev->mutex);
+}
+
+static int mt76x2u_add_interface(struct ieee80211_hw *hw,
+				 struct ieee80211_vif *vif)
+{
+	struct mt76x2_dev *dev = hw->priv;
+	struct mt76x2_vif *mvif = (struct mt76x2_vif *)vif->drv_priv;
+	unsigned int idx = 0;
+
+	if (!ether_addr_equal(dev->mt76.macaddr, vif->addr))
+		mt76x2u_mac_setaddr(dev, vif->addr);
+
+	mvif->idx = idx;
+	mvif->group_wcid.idx = MT_VIF_WCID(idx);
+	mvif->group_wcid.hw_key_idx = -1;
+	mt76x2_txq_init(dev, vif->txq);
+
+	return 0;
+}
+
+static int
+mt76x2u_set_channel(struct mt76x2_dev *dev,
+		    struct cfg80211_chan_def *chandef)
+{
+	int err;
+
+	cancel_delayed_work_sync(&dev->cal_work);
+	set_bit(MT76_RESET, &dev->mt76.state);
+
+	mt76_set_channel(&dev->mt76);
+
+	mt76_clear(dev, MT_TXOP_CTRL_CFG, BIT(20));
+	mt76_clear(dev, MT_TXOP_HLDR_ET, BIT(1));
+	mt76x2_mac_stop(dev, false);
+
+	err = mt76x2u_phy_set_channel(dev, chandef);
+
+	mt76x2u_mac_resume(dev);
+
+	clear_bit(MT76_RESET, &dev->mt76.state);
+	mt76_txq_schedule_all(&dev->mt76);
+
+	return err;
+}
+
+static void
+mt76x2u_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			 struct ieee80211_bss_conf *info, u32 changed)
+{
+	struct mt76x2_dev *dev = hw->priv;
+
+	mutex_lock(&dev->mutex);
+
+	if (changed & BSS_CHANGED_ASSOC) {
+		mt76x2u_phy_channel_calibrate(dev);
+		mt76x2_apply_gain_adj(dev);
+	}
+
+	if (changed & BSS_CHANGED_BSSID) {
+		mt76_wr(dev, MT_MAC_BSSID_DW0,
+			get_unaligned_le32(info->bssid));
+		mt76_wr(dev, MT_MAC_BSSID_DW1,
+			get_unaligned_le16(info->bssid + 4));
+	}
+
+	mutex_unlock(&dev->mutex);
+}
+
+static int
+mt76x2u_config(struct ieee80211_hw *hw, u32 changed)
+{
+	struct mt76x2_dev *dev = hw->priv;
+	int err = 0;
+
+	mutex_lock(&dev->mutex);
+
+	if (changed & IEEE80211_CONF_CHANGE_MONITOR) {
+		if (!(hw->conf.flags & IEEE80211_CONF_MONITOR))
+			dev->rxfilter |= MT_RX_FILTR_CFG_PROMISC;
+		else
+			dev->rxfilter &= ~MT_RX_FILTR_CFG_PROMISC;
+		mt76_wr(dev, MT_RX_FILTR_CFG, dev->rxfilter);
+	}
+
+	if (changed & IEEE80211_CONF_CHANGE_CHANNEL) {
+		ieee80211_stop_queues(hw);
+		err = mt76x2u_set_channel(dev, &hw->conf.chandef);
+		ieee80211_wake_queues(hw);
+	}
+
+	if (changed & IEEE80211_CONF_CHANGE_POWER) {
+		dev->txpower_conf = hw->conf.power_level * 2;
+
+		/* convert to per-chain power for 2x2 devices */
+		dev->txpower_conf -= 6;
+
+		if (test_bit(MT76_STATE_RUNNING, &dev->mt76.state))
+			mt76x2_phy_set_txpower(dev);
+	}
+
+	mutex_unlock(&dev->mutex);
+
+	return err;
+}
+
+static void
+mt76x2u_sw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		const u8 *mac)
+{
+	struct mt76x2_dev *dev = hw->priv;
+
+	set_bit(MT76_SCANNING, &dev->mt76.state);
+}
+
+static void
+mt76x2u_sw_scan_complete(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
+{
+	struct mt76x2_dev *dev = hw->priv;
+
+	clear_bit(MT76_SCANNING, &dev->mt76.state);
+}
+
+const struct ieee80211_ops mt76x2u_ops = {
+	.tx = mt76x2_tx,
+	.start = mt76x2u_start,
+	.stop = mt76x2u_stop,
+	.add_interface = mt76x2u_add_interface,
+	.remove_interface = mt76x2_remove_interface,
+	.sta_add = mt76x2_sta_add,
+	.sta_remove = mt76x2_sta_remove,
+	.set_key = mt76x2_set_key,
+	.ampdu_action = mt76x2_ampdu_action,
+	.config = mt76x2u_config,
+	.wake_tx_queue = mt76_wake_tx_queue,
+	.bss_info_changed = mt76x2u_bss_info_changed,
+	.configure_filter = mt76x2_configure_filter,
+	.conf_tx = mt76x2_conf_tx,
+	.sw_scan_start = mt76x2u_sw_scan,
+	.sw_scan_complete = mt76x2u_sw_scan_complete,
+	.sta_rate_tbl_update = mt76x2_sta_rate_tbl_update,
+};
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2u_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x2u_mcu.c
new file mode 100644
index 000000000000..22c16d638baa
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2u_mcu.c
@@ -0,0 +1,463 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/firmware.h>
+
+#include "mt76x2u.h"
+#include "mt76x2_eeprom.h"
+
+#define MT_CMD_HDR_LEN			4
+#define MT_INBAND_PACKET_MAX_LEN	192
+#define MT_MCU_MEMMAP_WLAN		0x410000
+
+#define MCU_FW_URB_MAX_PAYLOAD		0x3900
+#define MCU_ROM_PATCH_MAX_PAYLOAD	2048
+
+#define MT76U_MCU_ILM_OFFSET		0x80000
+#define MT76U_MCU_DLM_OFFSET		0x110000
+#define MT76U_MCU_ROM_PATCH_OFFSET	0x90000
+
+static int
+mt76x2u_mcu_function_select(struct mt76x2_dev *dev, enum mcu_function func,
+			    u32 val)
+{
+	struct {
+		__le32 id;
+		__le32 value;
+	} __packed __aligned(4) msg = {
+		.id = cpu_to_le32(func),
+		.value = cpu_to_le32(val),
+	};
+	struct sk_buff *skb;
+
+	skb = mt76u_mcu_msg_alloc(&msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+	return mt76u_mcu_send_msg(&dev->mt76, skb, CMD_FUN_SET_OP,
+				  func != Q_SELECT);
+}
+
+int mt76x2u_mcu_set_radio_state(struct mt76x2_dev *dev, bool val)
+{
+	struct {
+		__le32 mode;
+		__le32 level;
+	} __packed __aligned(4) msg = {
+		.mode = cpu_to_le32(val ? RADIO_ON : RADIO_OFF),
+		.level = cpu_to_le32(0),
+	};
+	struct sk_buff *skb;
+
+	skb = mt76u_mcu_msg_alloc(&msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+	return mt76u_mcu_send_msg(&dev->mt76, skb, CMD_POWER_SAVING_OP,
+				  false);
+}
+
+int mt76x2u_mcu_load_cr(struct mt76x2_dev *dev, u8 type, u8 temp_level,
+			u8 channel)
+{
+	struct {
+		u8 cr_mode;
+		u8 temp;
+		u8 ch;
+		u8 _pad0;
+		__le32 cfg;
+	} __packed __aligned(4) msg = {
+		.cr_mode = type,
+		.temp = temp_level,
+		.ch = channel,
+	};
+	struct sk_buff *skb;
+	u32 val;
+
+	val = BIT(31);
+	val |= (mt76x2_eeprom_get(dev, MT_EE_NIC_CONF_0) >> 8) & 0x00ff;
+	val |= (mt76x2_eeprom_get(dev, MT_EE_NIC_CONF_1) << 8) & 0xff00;
+	msg.cfg = cpu_to_le32(val);
+
+	/* first set the channel without the extension channel info */
+	skb = mt76u_mcu_msg_alloc(&msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+	return mt76u_mcu_send_msg(&dev->mt76, skb, CMD_LOAD_CR, true);
+}
+
+int mt76x2u_mcu_set_channel(struct mt76x2_dev *dev, u8 channel, u8 bw,
+			    u8 bw_index, bool scan)
+{
+	struct {
+		u8 idx;
+		u8 scan;
+		u8 bw;
+		u8 _pad0;
+
+		__le16 chainmask;
+		u8 ext_chan;
+		u8 _pad1;
+
+	} __packed __aligned(4) msg = {
+		.idx = channel,
+		.scan = scan,
+		.bw = bw,
+		.chainmask = cpu_to_le16(dev->chainmask),
+	};
+	struct sk_buff *skb;
+
+	/* first set the channel without the extension channel info */
+	skb = mt76u_mcu_msg_alloc(&msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+
+	mt76u_mcu_send_msg(&dev->mt76, skb, CMD_SWITCH_CHANNEL_OP, true);
+
+	usleep_range(5000, 10000);
+
+	msg.ext_chan = 0xe0 + bw_index;
+	skb = mt76u_mcu_msg_alloc(&msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+
+	return mt76u_mcu_send_msg(&dev->mt76, skb, CMD_SWITCH_CHANNEL_OP, true);
+}
+
+int mt76x2u_mcu_calibrate(struct mt76x2_dev *dev, enum mcu_calibration type,
+			  u32 val)
+{
+	struct {
+		__le32 id;
+		__le32 value;
+	} __packed __aligned(4) msg = {
+		.id = cpu_to_le32(type),
+		.value = cpu_to_le32(val),
+	};
+	struct sk_buff *skb;
+
+	skb = mt76u_mcu_msg_alloc(&msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+	return mt76u_mcu_send_msg(&dev->mt76, skb, CMD_CALIBRATION_OP, true);
+}
+
+int mt76x2u_mcu_init_gain(struct mt76x2_dev *dev, u8 channel, u32 gain,
+			  bool force)
+{
+	struct {
+		__le32 channel;
+		__le32 gain_val;
+	} __packed __aligned(4) msg = {
+		.channel = cpu_to_le32(channel),
+		.gain_val = cpu_to_le32(gain),
+	};
+	struct sk_buff *skb;
+
+	if (force)
+		msg.channel |= cpu_to_le32(BIT(31));
+
+	skb = mt76u_mcu_msg_alloc(&msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+	return mt76u_mcu_send_msg(&dev->mt76, skb, CMD_INIT_GAIN_OP, true);
+}
+
+int mt76x2u_mcu_set_dynamic_vga(struct mt76x2_dev *dev, u8 channel, bool ap,
+				bool ext, int rssi, u32 false_cca)
+{
+	struct {
+		__le32 channel;
+		__le32 rssi_val;
+		__le32 false_cca_val;
+	} __packed __aligned(4) msg = {
+		.rssi_val = cpu_to_le32(rssi),
+		.false_cca_val = cpu_to_le32(false_cca),
+	};
+	struct sk_buff *skb;
+	u32 val = channel;
+
+	if (ap)
+		val |= BIT(31);
+	if (ext)
+		val |= BIT(30);
+	msg.channel = cpu_to_le32(val);
+
+	skb = mt76u_mcu_msg_alloc(&msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+	return mt76u_mcu_send_msg(&dev->mt76, skb, CMD_DYNC_VGA_OP, true);
+}
+
+int mt76x2u_mcu_tssi_comp(struct mt76x2_dev *dev,
+			  struct mt76x2_tssi_comp *tssi_data)
+{
+	struct {
+		__le32 id;
+		struct mt76x2_tssi_comp data;
+	} __packed __aligned(4) msg = {
+		.id = cpu_to_le32(MCU_CAL_TSSI_COMP),
+		.data = *tssi_data,
+	};
+	struct sk_buff *skb;
+
+	skb = mt76u_mcu_msg_alloc(&msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+	return mt76u_mcu_send_msg(&dev->mt76, skb, CMD_CALIBRATION_OP, true);
+}
+
+static void mt76x2u_mcu_load_ivb(struct mt76x2_dev *dev)
+{
+	mt76u_vendor_request(&dev->mt76, MT_VEND_DEV_MODE,
+			     USB_DIR_OUT | USB_TYPE_VENDOR,
+			     0x12, 0, NULL, 0);
+}
+
+static void mt76x2u_mcu_enable_patch(struct mt76x2_dev *dev)
+{
+	struct mt76_usb *usb = &dev->mt76.usb;
+	const u8 data[] = {
+		0x6f, 0xfc, 0x08, 0x01,
+		0x20, 0x04, 0x00, 0x00,
+		0x00, 0x09, 0x00,
+	};
+
+	memcpy(usb->data, data, sizeof(data));
+	mt76u_vendor_request(&dev->mt76, MT_VEND_DEV_MODE,
+			     USB_DIR_OUT | USB_TYPE_CLASS,
+			     0x12, 0, usb->data, sizeof(data));
+}
+
+static void mt76x2u_mcu_reset_wmt(struct mt76x2_dev *dev)
+{
+	struct mt76_usb *usb = &dev->mt76.usb;
+	u8 data[] = {
+		0x6f, 0xfc, 0x05, 0x01,
+		0x07, 0x01, 0x00, 0x04
+	};
+
+	memcpy(usb->data, data, sizeof(data));
+	mt76u_vendor_request(&dev->mt76, MT_VEND_DEV_MODE,
+			     USB_DIR_OUT | USB_TYPE_CLASS,
+			     0x12, 0, usb->data, sizeof(data));
+}
+
+static int mt76x2u_mcu_load_rom_patch(struct mt76x2_dev *dev)
+{
+	bool rom_protect = !is_mt7612(dev);
+	struct mt76x2_patch_header *hdr;
+	u32 val, patch_mask, patch_reg;
+	const struct firmware *fw;
+	int err;
+
+	if (rom_protect &&
+	    !mt76_poll_msec(dev, MT_MCU_SEMAPHORE_03, 1, 1, 600)) {
+		dev_err(dev->mt76.dev,
+			"could not get hardware semaphore for ROM PATCH\n");
+		return -ETIMEDOUT;
+	}
+
+	if (mt76xx_rev(dev) >= MT76XX_REV_E3) {
+		patch_mask = BIT(0);
+		patch_reg = MT_MCU_CLOCK_CTL;
+	} else {
+		patch_mask = BIT(1);
+		patch_reg = MT_MCU_COM_REG0;
+	}
+
+	if (rom_protect && (mt76_rr(dev, patch_reg) & patch_mask)) {
+		dev_info(dev->mt76.dev, "ROM patch already applied\n");
+		return 0;
+	}
+
+	err = request_firmware(&fw, MT7662U_ROM_PATCH, dev->mt76.dev);
+	if (err < 0)
+		return err;
+
+	if (!fw || !fw->data || fw->size <= sizeof(*hdr)) {
+		dev_err(dev->mt76.dev, "failed to load firmware\n");
+		err = -EIO;
+		goto out;
+	}
+
+	hdr = (struct mt76x2_patch_header *)fw->data;
+	dev_info(dev->mt76.dev, "ROM patch build: %.15s\n", hdr->build_time);
+
+	/* enable USB_DMA_CFG */
+	val = MT_USB_DMA_CFG_RX_BULK_EN |
+	      MT_USB_DMA_CFG_TX_BULK_EN |
+	      FIELD_PREP(MT_USB_DMA_CFG_RX_BULK_AGG_TOUT, 0x20);
+	mt76_wr(dev, MT_VEND_ADDR(CFG, MT_USB_U3DMA_CFG), val);
+
+	/* vendor reset */
+	mt76u_mcu_fw_reset(&dev->mt76);
+	usleep_range(5000, 10000);
+
+	/* enable FCE to send in-band cmd */
+	mt76_wr(dev, MT_FCE_PSE_CTRL, 0x1);
+	/* FCE tx_fs_base_ptr */
+	mt76_wr(dev, MT_TX_CPU_FROM_FCE_BASE_PTR, 0x400230);
+	/* FCE tx_fs_max_cnt */
+	mt76_wr(dev, MT_TX_CPU_FROM_FCE_MAX_COUNT, 0x1);
+	/* FCE pdma enable */
+	mt76_wr(dev, MT_FCE_PDMA_GLOBAL_CONF, 0x44);
+	/* FCE skip_fs_en */
+	mt76_wr(dev, MT_FCE_SKIP_FS, 0x3);
+
+	err = mt76u_mcu_fw_send_data(&dev->mt76, fw->data + sizeof(*hdr),
+				     fw->size - sizeof(*hdr),
+				     MCU_ROM_PATCH_MAX_PAYLOAD,
+				     MT76U_MCU_ROM_PATCH_OFFSET);
+	if (err < 0) {
+		err = -EIO;
+		goto out;
+	}
+
+	mt76x2u_mcu_enable_patch(dev);
+	mt76x2u_mcu_reset_wmt(dev);
+	mdelay(20);
+
+	if (!mt76_poll_msec(dev, patch_reg, patch_mask, patch_mask, 100)) {
+		dev_err(dev->mt76.dev, "failed to load ROM patch\n");
+		err = -ETIMEDOUT;
+	}
+
+out:
+	if (rom_protect)
+		mt76_wr(dev, MT_MCU_SEMAPHORE_03, 1);
+	release_firmware(fw);
+	return err;
+}
+
+static int mt76x2u_mcu_load_firmware(struct mt76x2_dev *dev)
+{
+	u32 val, dlm_offset = MT76U_MCU_DLM_OFFSET;
+	const struct mt76x2_fw_header *hdr;
+	int err, len, ilm_len, dlm_len;
+	const struct firmware *fw;
+
+	err = request_firmware(&fw, MT7662U_FIRMWARE, dev->mt76.dev);
+	if (err < 0)
+		return err;
+
+	if (!fw || !fw->data || fw->size < sizeof(*hdr)) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	hdr = (const struct mt76x2_fw_header *)fw->data;
+	ilm_len = le32_to_cpu(hdr->ilm_len);
+	dlm_len = le32_to_cpu(hdr->dlm_len);
+	len = sizeof(*hdr) + ilm_len + dlm_len;
+	if (fw->size != len) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	val = le16_to_cpu(hdr->fw_ver);
+	dev_info(dev->mt76.dev, "Firmware Version: %d.%d.%02d\n",
+		 (val >> 12) & 0xf, (val >> 8) & 0xf, val & 0xf);
+
+	val = le16_to_cpu(hdr->build_ver);
+	dev_info(dev->mt76.dev, "Build: %x\n", val);
+	dev_info(dev->mt76.dev, "Build Time: %.16s\n", hdr->build_time);
+
+	/* vendor reset */
+	mt76u_mcu_fw_reset(&dev->mt76);
+	usleep_range(5000, 10000);
+
+	/* enable USB_DMA_CFG */
+	val = MT_USB_DMA_CFG_RX_BULK_EN |
+	      MT_USB_DMA_CFG_TX_BULK_EN |
+	      FIELD_PREP(MT_USB_DMA_CFG_RX_BULK_AGG_TOUT, 0x20);
+	mt76_wr(dev, MT_VEND_ADDR(CFG, MT_USB_U3DMA_CFG), val);
+	/* enable FCE to send in-band cmd */
+	mt76_wr(dev, MT_FCE_PSE_CTRL, 0x1);
+	/* FCE tx_fs_base_ptr */
+	mt76_wr(dev, MT_TX_CPU_FROM_FCE_BASE_PTR, 0x400230);
+	/* FCE tx_fs_max_cnt */
+	mt76_wr(dev, MT_TX_CPU_FROM_FCE_MAX_COUNT, 0x1);
+	/* FCE pdma enable */
+	mt76_wr(dev, MT_FCE_PDMA_GLOBAL_CONF, 0x44);
+	/* FCE skip_fs_en */
+	mt76_wr(dev, MT_FCE_SKIP_FS, 0x3);
+
+	/* load ILM */
+	err = mt76u_mcu_fw_send_data(&dev->mt76, fw->data + sizeof(*hdr),
+				     ilm_len, MCU_FW_URB_MAX_PAYLOAD,
+				     MT76U_MCU_ILM_OFFSET);
+	if (err < 0) {
+		err = -EIO;
+		goto out;
+	}
+
+	/* load DLM */
+	if (mt76xx_rev(dev) >= MT76XX_REV_E3)
+		dlm_offset += 0x800;
+	err = mt76u_mcu_fw_send_data(&dev->mt76,
+				     fw->data + sizeof(*hdr) + ilm_len,
+				     dlm_len, MCU_FW_URB_MAX_PAYLOAD,
+				     dlm_offset);
+	if (err < 0) {
+		err = -EIO;
+		goto out;
+	}
+
+	mt76x2u_mcu_load_ivb(dev);
+	if (!mt76_poll_msec(dev, MT_MCU_COM_REG0, 1, 1, 100)) {
+		dev_err(dev->mt76.dev, "firmware failed to start\n");
+		err = -ETIMEDOUT;
+		goto out;
+	}
+
+	mt76_set(dev, MT_MCU_COM_REG0, BIT(1));
+	/* enable FCE to send in-band cmd */
+	mt76_wr(dev, MT_FCE_PSE_CTRL, 0x1);
+	dev_dbg(dev->mt76.dev, "firmware running\n");
+
+out:
+	release_firmware(fw);
+	return err;
+}
+
+int mt76x2u_mcu_fw_init(struct mt76x2_dev *dev)
+{
+	int err;
+
+	err = mt76x2u_mcu_load_rom_patch(dev);
+	if (err < 0)
+		return err;
+
+	return mt76x2u_mcu_load_firmware(dev);
+}
+
+int mt76x2u_mcu_init(struct mt76x2_dev *dev)
+{
+	int err;
+
+	err = mt76x2u_mcu_function_select(dev, Q_SELECT, 1);
+	if (err < 0)
+		return err;
+
+	return mt76x2u_mcu_set_radio_state(dev, true);
+}
+
+void mt76x2u_mcu_deinit(struct mt76x2_dev *dev)
+{
+	struct mt76_usb *usb = &dev->mt76.usb;
+
+	usb_kill_urb(usb->mcu.res.urb);
+	mt76u_buf_free(&usb->mcu.res);
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2u_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2u_phy.c
new file mode 100644
index 000000000000..5158063d0c2e
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2u_phy.c
@@ -0,0 +1,303 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76x2u.h"
+#include "mt76x2_eeprom.h"
+
+void mt76x2u_phy_set_rxpath(struct mt76x2_dev *dev)
+{
+	u32 val;
+
+	val = mt76_rr(dev, MT_BBP(AGC, 0));
+	val &= ~BIT(4);
+
+	switch (dev->chainmask & 0xf) {
+	case 2:
+		val |= BIT(3);
+		break;
+	default:
+		val &= ~BIT(3);
+		break;
+	}
+	mt76_wr(dev, MT_BBP(AGC, 0), val);
+}
+
+void mt76x2u_phy_set_txdac(struct mt76x2_dev *dev)
+{
+	int txpath;
+
+	txpath = (dev->chainmask >> 8) & 0xf;
+	switch (txpath) {
+	case 2:
+		mt76_set(dev, MT_BBP(TXBE, 5), 0x3);
+		break;
+	default:
+		mt76_clear(dev, MT_BBP(TXBE, 5), 0x3);
+		break;
+	}
+}
+
+void mt76x2u_phy_channel_calibrate(struct mt76x2_dev *dev)
+{
+	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
+	bool is_5ghz = chan->band == NL80211_BAND_5GHZ;
+
+	if (mt76x2_channel_silent(dev))
+		return;
+
+	mt76x2u_mac_stop(dev);
+
+	if (is_5ghz)
+		mt76x2u_mcu_calibrate(dev, MCU_CAL_LC, 0);
+
+	mt76x2u_mcu_calibrate(dev, MCU_CAL_TX_LOFT, is_5ghz);
+	mt76x2u_mcu_calibrate(dev, MCU_CAL_TXIQ, is_5ghz);
+	mt76x2u_mcu_calibrate(dev, MCU_CAL_RXIQC_FI, is_5ghz);
+	mt76x2u_mcu_calibrate(dev, MCU_CAL_TEMP_SENSOR, 0);
+
+	mt76x2u_mac_resume(dev);
+}
+
+static void
+mt76x2u_phy_tssi_compensate(struct mt76x2_dev *dev)
+{
+	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
+	struct mt76x2_tx_power_info txp;
+	struct mt76x2_tssi_comp t = {};
+
+	if (!dev->cal.tssi_cal_done)
+		return;
+
+	if (!dev->cal.tssi_comp_pending) {
+		/* TSSI trigger */
+		t.cal_mode = BIT(0);
+		mt76x2u_mcu_tssi_comp(dev, &t);
+		dev->cal.tssi_comp_pending = true;
+	} else {
+		if (mt76_rr(dev, MT_BBP(CORE, 34)) & BIT(4))
+			return;
+
+		dev->cal.tssi_comp_pending = false;
+		mt76x2_get_power_info(dev, &txp, chan);
+
+		if (mt76x2_ext_pa_enabled(dev, chan->band))
+			t.pa_mode = 1;
+
+		t.cal_mode = BIT(1);
+		t.slope0 = txp.chain[0].tssi_slope;
+		t.offset0 = txp.chain[0].tssi_offset;
+		t.slope1 = txp.chain[1].tssi_slope;
+		t.offset1 = txp.chain[1].tssi_offset;
+		mt76x2u_mcu_tssi_comp(dev, &t);
+
+		if (t.pa_mode || dev->cal.dpd_cal_done)
+			return;
+
+		usleep_range(10000, 20000);
+		mt76x2u_mcu_calibrate(dev, MCU_CAL_DPD, chan->hw_value);
+		dev->cal.dpd_cal_done = true;
+	}
+}
+
+static void
+mt76x2u_phy_update_channel_gain(struct mt76x2_dev *dev)
+{
+	u8 channel = dev->mt76.chandef.chan->hw_value;
+	int freq, freq1;
+	u32 false_cca;
+
+	freq = dev->mt76.chandef.chan->center_freq;
+	freq1 = dev->mt76.chandef.center_freq1;
+
+	switch (dev->mt76.chandef.width) {
+	case NL80211_CHAN_WIDTH_80: {
+		int ch_group_index;
+
+		ch_group_index = (freq - freq1 + 30) / 20;
+		if (WARN_ON(ch_group_index < 0 || ch_group_index > 3))
+			ch_group_index = 0;
+		channel += 6 - ch_group_index * 4;
+		break;
+	}
+	case NL80211_CHAN_WIDTH_40:
+		if (freq1 > freq)
+			channel += 2;
+		else
+			channel -= 2;
+		break;
+	default:
+		break;
+	}
+
+	dev->cal.avg_rssi_all = mt76x2_phy_get_min_avg_rssi(dev);
+	false_cca = FIELD_GET(MT_RX_STAT_1_CCA_ERRORS,
+			      mt76_rr(dev, MT_RX_STAT_1));
+
+	mt76x2u_mcu_set_dynamic_vga(dev, channel, false, false,
+				    dev->cal.avg_rssi_all, false_cca);
+}
+
+void mt76x2u_phy_calibrate(struct work_struct *work)
+{
+	struct mt76x2_dev *dev;
+
+	dev = container_of(work, struct mt76x2_dev, cal_work.work);
+	mt76x2u_phy_tssi_compensate(dev);
+	mt76x2u_phy_update_channel_gain(dev);
+
+	ieee80211_queue_delayed_work(mt76_hw(dev), &dev->cal_work,
+				     MT_CALIBRATE_INTERVAL);
+}
+
+int mt76x2u_phy_set_channel(struct mt76x2_dev *dev,
+			    struct cfg80211_chan_def *chandef)
+{
+	u32 ext_cca_chan[4] = {
+		[0] = FIELD_PREP(MT_EXT_CCA_CFG_CCA0, 0) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA1, 1) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA2, 2) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA3, 3) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA_MASK, BIT(0)),
+		[1] = FIELD_PREP(MT_EXT_CCA_CFG_CCA0, 1) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA1, 0) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA2, 2) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA3, 3) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA_MASK, BIT(1)),
+		[2] = FIELD_PREP(MT_EXT_CCA_CFG_CCA0, 2) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA1, 3) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA2, 1) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA3, 0) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA_MASK, BIT(2)),
+		[3] = FIELD_PREP(MT_EXT_CCA_CFG_CCA0, 3) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA1, 2) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA2, 1) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA3, 0) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA_MASK, BIT(3)),
+	};
+	bool scan = test_bit(MT76_SCANNING, &dev->mt76.state);
+	struct ieee80211_channel *chan = chandef->chan;
+	u8 channel = chan->hw_value, bw, bw_index;
+	int ch_group_index, freq, freq1, ret;
+
+	dev->cal.channel_cal_done = false;
+	freq = chandef->chan->center_freq;
+	freq1 = chandef->center_freq1;
+
+	switch (chandef->width) {
+	case NL80211_CHAN_WIDTH_40:
+		bw = 1;
+		if (freq1 > freq) {
+			bw_index = 1;
+			ch_group_index = 0;
+		} else {
+			bw_index = 3;
+			ch_group_index = 1;
+		}
+		channel += 2 - ch_group_index * 4;
+		break;
+	case NL80211_CHAN_WIDTH_80:
+		ch_group_index = (freq - freq1 + 30) / 20;
+		if (WARN_ON(ch_group_index < 0 || ch_group_index > 3))
+			ch_group_index = 0;
+		bw = 2;
+		bw_index = ch_group_index;
+		channel += 6 - ch_group_index * 4;
+		break;
+	default:
+		bw = 0;
+		bw_index = 0;
+		ch_group_index = 0;
+		break;
+	}
+
+	mt76x2_read_rx_gain(dev);
+	mt76x2_phy_set_txpower_regs(dev, chan->band);
+	mt76x2_configure_tx_delay(dev, chan->band, bw);
+	mt76x2_phy_set_txpower(dev);
+
+	mt76x2_phy_set_band(dev, chan->band, ch_group_index & 1);
+	mt76x2_phy_set_bw(dev, chandef->width, ch_group_index);
+
+	mt76_rmw(dev, MT_EXT_CCA_CFG,
+		 (MT_EXT_CCA_CFG_CCA0 |
+		  MT_EXT_CCA_CFG_CCA1 |
+		  MT_EXT_CCA_CFG_CCA2 |
+		  MT_EXT_CCA_CFG_CCA3 |
+		  MT_EXT_CCA_CFG_CCA_MASK),
+		 ext_cca_chan[ch_group_index]);
+
+	ret = mt76x2u_mcu_set_channel(dev, channel, bw, bw_index, scan);
+	if (ret)
+		return ret;
+
+	mt76x2u_mcu_init_gain(dev, channel, dev->cal.rx.mcu_gain, true);
+
+	/* Enable LDPC Rx */
+	if (mt76xx_rev(dev) >= MT76XX_REV_E3)
+		mt76_set(dev, MT_BBP(RXO, 13), BIT(10));
+
+	if (!dev->cal.init_cal_done) {
+		u8 val = mt76x2_eeprom_get(dev, MT_EE_BT_RCAL_RESULT);
+
+		if (val != 0xff)
+			mt76x2u_mcu_calibrate(dev, MCU_CAL_R, 0);
+	}
+
+	mt76x2u_mcu_calibrate(dev, MCU_CAL_RXDCOC, channel);
+
+	/* Rx LPF calibration */
+	if (!dev->cal.init_cal_done)
+		mt76x2u_mcu_calibrate(dev, MCU_CAL_RC, 0);
+	dev->cal.init_cal_done = true;
+
+	mt76_wr(dev, MT_BBP(AGC, 61), 0xff64a4e2);
+	mt76_wr(dev, MT_BBP(AGC, 7), 0x08081010);
+	mt76_wr(dev, MT_BBP(AGC, 11), 0x00000404);
+	mt76_wr(dev, MT_BBP(AGC, 2), 0x00007070);
+	mt76_wr(dev, MT_TXOP_CTRL_CFG, 0X04101b3f);
+
+	mt76_set(dev, MT_BBP(TXO, 4), BIT(25));
+	mt76_set(dev, MT_BBP(RXO, 13), BIT(8));
+
+	if (scan)
+		return 0;
+
+	if (mt76x2_tssi_enabled(dev)) {
+		/* init default values for temp compensation */
+		mt76_rmw_field(dev, MT_TX_ALC_CFG_1, MT_TX_ALC_CFG_1_TEMP_COMP,
+			       0x38);
+		mt76_rmw_field(dev, MT_TX_ALC_CFG_2, MT_TX_ALC_CFG_2_TEMP_COMP,
+			       0x38);
+
+		/* init tssi calibration */
+		if (!mt76x2_channel_silent(dev)) {
+			struct ieee80211_channel *chan;
+			u32 flag = 0;
+
+			chan = dev->mt76.chandef.chan;
+			if (chan->band == NL80211_BAND_5GHZ)
+				flag |= BIT(0);
+			if (mt76x2_ext_pa_enabled(dev, chan->band))
+				flag |= BIT(8);
+			mt76x2u_mcu_calibrate(dev, MCU_CAL_TSSI, flag);
+			dev->cal.tssi_cal_done = true;
+		}
+	}
+
+	ieee80211_queue_delayed_work(mt76_hw(dev), &dev->cal_work,
+				     MT_CALIBRATE_INTERVAL);
+	return 0;
+}
diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index e96956710fb2..af48d43bb7dc 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -51,7 +51,7 @@ __mt76_get_txwi(struct mt76_dev *dev)
 	return t;
 }
 
-static struct mt76_txwi_cache *
+struct mt76_txwi_cache *
 mt76_get_txwi(struct mt76_dev *dev)
 {
 	struct mt76_txwi_cache *t = __mt76_get_txwi(dev);
@@ -91,80 +91,6 @@ mt76_txq_get_qid(struct ieee80211_txq *txq)
 	return txq->ac;
 }
 
-int mt76_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q,
-		      struct sk_buff *skb, struct mt76_wcid *wcid,
-		      struct ieee80211_sta *sta)
-{
-	struct mt76_queue_entry e;
-	struct mt76_txwi_cache *t;
-	struct mt76_queue_buf buf[32];
-	struct sk_buff *iter;
-	dma_addr_t addr;
-	int len;
-	u32 tx_info = 0;
-	int n, ret;
-
-	t = mt76_get_txwi(dev);
-	if (!t) {
-		ieee80211_free_txskb(dev->hw, skb);
-		return -ENOMEM;
-	}
-
-	dma_sync_single_for_cpu(dev->dev, t->dma_addr, sizeof(t->txwi),
-				DMA_TO_DEVICE);
-	ret = dev->drv->tx_prepare_skb(dev, &t->txwi, skb, q, wcid, sta,
-				       &tx_info);
-	dma_sync_single_for_device(dev->dev, t->dma_addr, sizeof(t->txwi),
-				   DMA_TO_DEVICE);
-	if (ret < 0)
-		goto free;
-
-	len = skb->len - skb->data_len;
-	addr = dma_map_single(dev->dev, skb->data, len, DMA_TO_DEVICE);
-	if (dma_mapping_error(dev->dev, addr)) {
-		ret = -ENOMEM;
-		goto free;
-	}
-
-	n = 0;
-	buf[n].addr = t->dma_addr;
-	buf[n++].len = dev->drv->txwi_size;
-	buf[n].addr = addr;
-	buf[n++].len = len;
-
-	skb_walk_frags(skb, iter) {
-		if (n == ARRAY_SIZE(buf))
-			goto unmap;
-
-		addr = dma_map_single(dev->dev, iter->data, iter->len,
-				      DMA_TO_DEVICE);
-		if (dma_mapping_error(dev->dev, addr))
-			goto unmap;
-
-		buf[n].addr = addr;
-		buf[n++].len = iter->len;
-	}
-
-	if (q->queued + (n + 1) / 2 >= q->ndesc - 1)
-		goto unmap;
-
-	return dev->queue_ops->add_buf(dev, q, buf, n, tx_info, skb, t);
-
-unmap:
-	ret = -ENOMEM;
-	for (n--; n > 0; n--)
-		dma_unmap_single(dev->dev, buf[n].addr, buf[n].len,
-				 DMA_TO_DEVICE);
-
-free:
-	e.skb = skb;
-	e.txwi = t;
-	dev->drv->tx_complete_skb(dev, q, &e, true);
-	mt76_put_txwi(dev, t);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(mt76_tx_queue_skb);
-
 void
 mt76_tx(struct mt76_dev *dev, struct ieee80211_sta *sta,
 	struct mt76_wcid *wcid, struct sk_buff *skb)
@@ -185,7 +111,7 @@ mt76_tx(struct mt76_dev *dev, struct ieee80211_sta *sta,
 	q = &dev->q_tx[qid];
 
 	spin_lock_bh(&q->lock);
-	mt76_tx_queue_skb(dev, q, skb, wcid, sta);
+	dev->queue_ops->tx_queue_skb(dev, q, skb, wcid, sta);
 	dev->queue_ops->kick(dev, q);
 
 	if (q->queued > q->ndesc - 8)
@@ -241,7 +167,7 @@ mt76_queue_ps_skb(struct mt76_dev *dev, struct ieee80211_sta *sta,
 		info->flags |= IEEE80211_TX_STATUS_EOSP;
 
 	mt76_skb_set_moredata(skb, !last);
-	mt76_tx_queue_skb(dev, hwq, skb, wcid, sta);
+	dev->queue_ops->tx_queue_skb(dev, hwq, skb, wcid, sta);
 }
 
 void
@@ -321,7 +247,7 @@ mt76_txq_send_burst(struct mt76_dev *dev, struct mt76_queue *hwq,
 	if (ampdu)
 		mt76_check_agg_ssn(mtxq, skb);
 
-	idx = mt76_tx_queue_skb(dev, hwq, skb, wcid, txq->sta);
+	idx = dev->queue_ops->tx_queue_skb(dev, hwq, skb, wcid, txq->sta);
 
 	if (idx < 0)
 		return idx;
@@ -356,7 +282,8 @@ mt76_txq_send_burst(struct mt76_dev *dev, struct mt76_queue *hwq,
 		if (cur_ampdu)
 			mt76_check_agg_ssn(mtxq, skb);
 
-		idx = mt76_tx_queue_skb(dev, hwq, skb, wcid, txq->sta);
+		idx = dev->queue_ops->tx_queue_skb(dev, hwq, skb, wcid,
+						   txq->sta);
 		if (idx < 0)
 			return idx;
 
diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c
new file mode 100644
index 000000000000..7780b07543bb
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/usb.c
@@ -0,0 +1,845 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76.h"
+#include "usb_trace.h"
+#include "dma.h"
+
+#define MT_VEND_REQ_MAX_RETRY	10
+#define MT_VEND_REQ_TOUT_MS	300
+
+/* should be called with usb_ctrl_mtx locked */
+static int __mt76u_vendor_request(struct mt76_dev *dev, u8 req,
+				  u8 req_type, u16 val, u16 offset,
+				  void *buf, size_t len)
+{
+	struct usb_interface *intf = to_usb_interface(dev->dev);
+	struct usb_device *udev = interface_to_usbdev(intf);
+	unsigned int pipe;
+	int i, ret;
+
+	pipe = (req_type & USB_DIR_IN) ? usb_rcvctrlpipe(udev, 0)
+				       : usb_sndctrlpipe(udev, 0);
+	for (i = 0; i < MT_VEND_REQ_MAX_RETRY; i++) {
+		if (test_bit(MT76_REMOVED, &dev->state))
+			return -EIO;
+
+		ret = usb_control_msg(udev, pipe, req, req_type, val,
+				      offset, buf, len, MT_VEND_REQ_TOUT_MS);
+		if (ret == -ENODEV)
+			set_bit(MT76_REMOVED, &dev->state);
+		if (ret >= 0 || ret == -ENODEV)
+			return ret;
+		usleep_range(5000, 10000);
+	}
+
+	dev_err(dev->dev, "vendor request req:%02x off:%04x failed:%d\n",
+		req, offset, ret);
+	return ret;
+}
+
+int mt76u_vendor_request(struct mt76_dev *dev, u8 req,
+			 u8 req_type, u16 val, u16 offset,
+			 void *buf, size_t len)
+{
+	int ret;
+
+	mutex_lock(&dev->usb.usb_ctrl_mtx);
+	ret = __mt76u_vendor_request(dev, req, req_type,
+				     val, offset, buf, len);
+	trace_usb_reg_wr(dev, offset, val);
+	mutex_unlock(&dev->usb.usb_ctrl_mtx);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mt76u_vendor_request);
+
+/* should be called with usb_ctrl_mtx locked */
+static u32 __mt76u_rr(struct mt76_dev *dev, u32 addr)
+{
+	struct mt76_usb *usb = &dev->usb;
+	u32 data = ~0;
+	u16 offset;
+	int ret;
+	u8 req;
+
+	switch (addr & MT_VEND_TYPE_MASK) {
+	case MT_VEND_TYPE_EEPROM:
+		req = MT_VEND_READ_EEPROM;
+		break;
+	case MT_VEND_TYPE_CFG:
+		req = MT_VEND_READ_CFG;
+		break;
+	default:
+		req = MT_VEND_MULTI_READ;
+		break;
+	}
+	offset = addr & ~MT_VEND_TYPE_MASK;
+
+	ret = __mt76u_vendor_request(dev, req,
+				     USB_DIR_IN | USB_TYPE_VENDOR,
+				     0, offset, usb->data, sizeof(__le32));
+	if (ret == sizeof(__le32))
+		data = get_unaligned_le32(usb->data);
+	trace_usb_reg_rr(dev, addr, data);
+
+	return data;
+}
+
+u32 mt76u_rr(struct mt76_dev *dev, u32 addr)
+{
+	u32 ret;
+
+	mutex_lock(&dev->usb.usb_ctrl_mtx);
+	ret = __mt76u_rr(dev, addr);
+	mutex_unlock(&dev->usb.usb_ctrl_mtx);
+
+	return ret;
+}
+
+/* should be called with usb_ctrl_mtx locked */
+static void __mt76u_wr(struct mt76_dev *dev, u32 addr, u32 val)
+{
+	struct mt76_usb *usb = &dev->usb;
+	u16 offset;
+	u8 req;
+
+	switch (addr & MT_VEND_TYPE_MASK) {
+	case MT_VEND_TYPE_CFG:
+		req = MT_VEND_WRITE_CFG;
+		break;
+	default:
+		req = MT_VEND_MULTI_WRITE;
+		break;
+	}
+	offset = addr & ~MT_VEND_TYPE_MASK;
+
+	put_unaligned_le32(val, usb->data);
+	__mt76u_vendor_request(dev, req,
+			       USB_DIR_OUT | USB_TYPE_VENDOR, 0,
+			       offset, usb->data, sizeof(__le32));
+	trace_usb_reg_wr(dev, addr, val);
+}
+
+void mt76u_wr(struct mt76_dev *dev, u32 addr, u32 val)
+{
+	mutex_lock(&dev->usb.usb_ctrl_mtx);
+	__mt76u_wr(dev, addr, val);
+	mutex_unlock(&dev->usb.usb_ctrl_mtx);
+}
+
+static u32 mt76u_rmw(struct mt76_dev *dev, u32 addr,
+		     u32 mask, u32 val)
+{
+	mutex_lock(&dev->usb.usb_ctrl_mtx);
+	val |= __mt76u_rr(dev, addr) & ~mask;
+	__mt76u_wr(dev, addr, val);
+	mutex_unlock(&dev->usb.usb_ctrl_mtx);
+
+	return val;
+}
+
+static void mt76u_copy(struct mt76_dev *dev, u32 offset,
+		       const void *data, int len)
+{
+	struct mt76_usb *usb = &dev->usb;
+	const u32 *val = data;
+	int i, ret;
+
+	mutex_lock(&usb->usb_ctrl_mtx);
+	for (i = 0; i < (len / 4); i++) {
+		put_unaligned_le32(val[i], usb->data);
+		ret = __mt76u_vendor_request(dev, MT_VEND_MULTI_WRITE,
+					     USB_DIR_OUT | USB_TYPE_VENDOR,
+					     0, offset + i * 4, usb->data,
+					     sizeof(__le32));
+		if (ret < 0)
+			break;
+	}
+	mutex_unlock(&usb->usb_ctrl_mtx);
+}
+
+void mt76u_single_wr(struct mt76_dev *dev, const u8 req,
+		     const u16 offset, const u32 val)
+{
+	mutex_lock(&dev->usb.usb_ctrl_mtx);
+	__mt76u_vendor_request(dev, req,
+			       USB_DIR_OUT | USB_TYPE_VENDOR,
+			       val & 0xffff, offset, NULL, 0);
+	__mt76u_vendor_request(dev, req,
+			       USB_DIR_OUT | USB_TYPE_VENDOR,
+			       val >> 16, offset + 2, NULL, 0);
+	mutex_unlock(&dev->usb.usb_ctrl_mtx);
+}
+EXPORT_SYMBOL_GPL(mt76u_single_wr);
+
+static int
+mt76u_set_endpoints(struct usb_interface *intf,
+		    struct mt76_usb *usb)
+{
+	struct usb_host_interface *intf_desc = intf->cur_altsetting;
+	struct usb_endpoint_descriptor *ep_desc;
+	int i, in_ep = 0, out_ep = 0;
+
+	for (i = 0; i < intf_desc->desc.bNumEndpoints; i++) {
+		ep_desc = &intf_desc->endpoint[i].desc;
+
+		if (usb_endpoint_is_bulk_in(ep_desc) &&
+		    in_ep < __MT_EP_IN_MAX) {
+			usb->in_ep[in_ep] = usb_endpoint_num(ep_desc);
+			usb->in_max_packet = usb_endpoint_maxp(ep_desc);
+			in_ep++;
+		} else if (usb_endpoint_is_bulk_out(ep_desc) &&
+			   out_ep < __MT_EP_OUT_MAX) {
+			usb->out_ep[out_ep] = usb_endpoint_num(ep_desc);
+			usb->out_max_packet = usb_endpoint_maxp(ep_desc);
+			out_ep++;
+		}
+	}
+
+	if (in_ep != __MT_EP_IN_MAX || out_ep != __MT_EP_OUT_MAX)
+		return -EINVAL;
+	return 0;
+}
+
+static int
+mt76u_fill_rx_sg(struct mt76_dev *dev, struct mt76u_buf *buf,
+		 int nsgs, int len, int sglen)
+{
+	struct urb *urb = buf->urb;
+	int i;
+
+	for (i = 0; i < nsgs; i++) {
+		struct page *page;
+		void *data;
+		int offset;
+
+		data = netdev_alloc_frag(len);
+		if (!data)
+			break;
+
+		page = virt_to_head_page(data);
+		offset = data - page_address(page);
+		sg_set_page(&urb->sg[i], page, sglen, offset);
+	}
+
+	if (i < nsgs) {
+		int j;
+
+		for (j = nsgs; j < urb->num_sgs; j++)
+			skb_free_frag(sg_virt(&urb->sg[j]));
+		urb->num_sgs = i;
+	}
+
+	urb->num_sgs = max_t(int, i, urb->num_sgs);
+	buf->len = urb->num_sgs * sglen,
+	sg_init_marker(urb->sg, urb->num_sgs);
+
+	return i ? : -ENOMEM;
+}
+
+int mt76u_buf_alloc(struct mt76_dev *dev, struct mt76u_buf *buf,
+		    int nsgs, int len, int sglen, gfp_t gfp)
+{
+	buf->urb = usb_alloc_urb(0, gfp);
+	if (!buf->urb)
+		return -ENOMEM;
+
+	buf->urb->sg = devm_kzalloc(dev->dev, nsgs * sizeof(*buf->urb->sg),
+				    gfp);
+	if (!buf->urb->sg)
+		return -ENOMEM;
+
+	sg_init_table(buf->urb->sg, nsgs);
+	buf->dev = dev;
+
+	return mt76u_fill_rx_sg(dev, buf, nsgs, len, sglen);
+}
+EXPORT_SYMBOL_GPL(mt76u_buf_alloc);
+
+void mt76u_buf_free(struct mt76u_buf *buf)
+{
+	struct urb *urb = buf->urb;
+	int i;
+
+	for (i = 0; i < urb->num_sgs; i++)
+		skb_free_frag(sg_virt(&urb->sg[i]));
+	usb_free_urb(buf->urb);
+}
+EXPORT_SYMBOL_GPL(mt76u_buf_free);
+
+int mt76u_submit_buf(struct mt76_dev *dev, int dir, int index,
+		     struct mt76u_buf *buf, gfp_t gfp,
+		     usb_complete_t complete_fn, void *context)
+{
+	struct usb_interface *intf = to_usb_interface(dev->dev);
+	struct usb_device *udev = interface_to_usbdev(intf);
+	unsigned int pipe;
+
+	if (dir == USB_DIR_IN)
+		pipe = usb_rcvbulkpipe(udev, dev->usb.in_ep[index]);
+	else
+		pipe = usb_sndbulkpipe(udev, dev->usb.out_ep[index]);
+
+	usb_fill_bulk_urb(buf->urb, udev, pipe, NULL, buf->len,
+			  complete_fn, context);
+
+	return usb_submit_urb(buf->urb, gfp);
+}
+EXPORT_SYMBOL_GPL(mt76u_submit_buf);
+
+static inline struct mt76u_buf
+*mt76u_get_next_rx_entry(struct mt76_queue *q)
+{
+	struct mt76u_buf *buf = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->lock, flags);
+	if (q->queued > 0) {
+		buf = &q->entry[q->head].ubuf;
+		q->head = (q->head + 1) % q->ndesc;
+		q->queued--;
+	}
+	spin_unlock_irqrestore(&q->lock, flags);
+
+	return buf;
+}
+
+static int mt76u_get_rx_entry_len(u8 *data, u32 data_len)
+{
+	u16 dma_len, min_len;
+
+	dma_len = get_unaligned_le16(data);
+	min_len = MT_DMA_HDR_LEN + MT_RX_RXWI_LEN +
+		  MT_FCE_INFO_LEN;
+
+	if (data_len < min_len || WARN_ON(!dma_len) ||
+	    WARN_ON(dma_len + MT_DMA_HDR_LEN > data_len) ||
+	    WARN_ON(dma_len & 0x3))
+		return -EINVAL;
+	return dma_len;
+}
+
+static int
+mt76u_process_rx_entry(struct mt76_dev *dev, struct urb *urb)
+{
+	struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN];
+	u8 *data = sg_virt(&urb->sg[0]);
+	int data_len, len, nsgs = 1;
+	struct sk_buff *skb;
+
+	if (!test_bit(MT76_STATE_INITIALIZED, &dev->state))
+		return 0;
+
+	len = mt76u_get_rx_entry_len(data, urb->actual_length);
+	if (len < 0)
+		return 0;
+
+	skb = build_skb(data, q->buf_size);
+	if (!skb)
+		return 0;
+
+	data_len = min_t(int, len, urb->sg[0].length - MT_DMA_HDR_LEN);
+	skb_reserve(skb, MT_DMA_HDR_LEN);
+	if (skb->tail + data_len > skb->end) {
+		dev_kfree_skb(skb);
+		return 1;
+	}
+
+	__skb_put(skb, data_len);
+	len -= data_len;
+
+	while (len > 0) {
+		data_len = min_t(int, len, urb->sg[nsgs].length);
+		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+				sg_page(&urb->sg[nsgs]),
+				urb->sg[nsgs].offset,
+				data_len, q->buf_size);
+		len -= data_len;
+		nsgs++;
+	}
+	dev->drv->rx_skb(dev, MT_RXQ_MAIN, skb);
+
+	return nsgs;
+}
+
+static void mt76u_complete_rx(struct urb *urb)
+{
+	struct mt76_dev *dev = urb->context;
+	struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN];
+	unsigned long flags;
+
+	switch (urb->status) {
+	case -ECONNRESET:
+	case -ESHUTDOWN:
+	case -ENOENT:
+		return;
+	default:
+		dev_err(dev->dev, "rx urb failed: %d\n", urb->status);
+		/* fall through */
+	case 0:
+		break;
+	}
+
+	spin_lock_irqsave(&q->lock, flags);
+	if (WARN_ONCE(q->entry[q->tail].ubuf.urb != urb, "rx urb mismatch"))
+		goto out;
+
+	q->tail = (q->tail + 1) % q->ndesc;
+	q->queued++;
+	tasklet_schedule(&dev->usb.rx_tasklet);
+out:
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+
+static void mt76u_rx_tasklet(unsigned long data)
+{
+	struct mt76_dev *dev = (struct mt76_dev *)data;
+	struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN];
+	int err, nsgs, buf_len = q->buf_size;
+	struct mt76u_buf *buf;
+
+	rcu_read_lock();
+
+	while (true) {
+		buf = mt76u_get_next_rx_entry(q);
+		if (!buf)
+			break;
+
+		nsgs = mt76u_process_rx_entry(dev, buf->urb);
+		if (nsgs > 0) {
+			err = mt76u_fill_rx_sg(dev, buf, nsgs,
+					       buf_len,
+					       SKB_WITH_OVERHEAD(buf_len));
+			if (err < 0)
+				break;
+		}
+		mt76u_submit_buf(dev, USB_DIR_IN, MT_EP_IN_PKT_RX,
+				 buf, GFP_ATOMIC,
+				 mt76u_complete_rx, dev);
+	}
+	mt76_rx_poll_complete(dev, MT_RXQ_MAIN, NULL);
+
+	rcu_read_unlock();
+}
+
+int mt76u_submit_rx_buffers(struct mt76_dev *dev)
+{
+	struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN];
+	unsigned long flags;
+	int i, err = 0;
+
+	spin_lock_irqsave(&q->lock, flags);
+	for (i = 0; i < q->ndesc; i++) {
+		err = mt76u_submit_buf(dev, USB_DIR_IN, MT_EP_IN_PKT_RX,
+				       &q->entry[i].ubuf, GFP_ATOMIC,
+				       mt76u_complete_rx, dev);
+		if (err < 0)
+			break;
+	}
+	q->head = q->tail = 0;
+	q->queued = 0;
+	spin_unlock_irqrestore(&q->lock, flags);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(mt76u_submit_rx_buffers);
+
+static int mt76u_alloc_rx(struct mt76_dev *dev)
+{
+	struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN];
+	int i, err, nsgs;
+
+	spin_lock_init(&q->lock);
+	q->entry = devm_kzalloc(dev->dev,
+				MT_NUM_RX_ENTRIES * sizeof(*q->entry),
+				GFP_KERNEL);
+	if (!q->entry)
+		return -ENOMEM;
+
+	if (mt76u_check_sg(dev)) {
+		q->buf_size = MT_RX_BUF_SIZE;
+		nsgs = MT_SG_MAX_SIZE;
+	} else {
+		q->buf_size = PAGE_SIZE;
+		nsgs = 1;
+	}
+
+	for (i = 0; i < MT_NUM_RX_ENTRIES; i++) {
+		err = mt76u_buf_alloc(dev, &q->entry[i].ubuf,
+				      nsgs, q->buf_size,
+				      SKB_WITH_OVERHEAD(q->buf_size),
+				      GFP_KERNEL);
+		if (err < 0)
+			return err;
+	}
+	q->ndesc = MT_NUM_RX_ENTRIES;
+
+	return mt76u_submit_rx_buffers(dev);
+}
+
+static void mt76u_free_rx(struct mt76_dev *dev)
+{
+	struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN];
+	int i;
+
+	for (i = 0; i < q->ndesc; i++)
+		mt76u_buf_free(&q->entry[i].ubuf);
+}
+
+static void mt76u_stop_rx(struct mt76_dev *dev)
+{
+	struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN];
+	int i;
+
+	for (i = 0; i < q->ndesc; i++)
+		usb_kill_urb(q->entry[i].ubuf.urb);
+}
+
+int mt76u_skb_dma_info(struct sk_buff *skb, int port, u32 flags)
+{
+	struct sk_buff *iter, *last = skb;
+	u32 info, pad;
+
+	/* Buffer layout:
+	 *	|   4B   | xfer len |      pad       |  4B  |
+	 *	| TXINFO | pkt/cmd  | zero pad to 4B | zero |
+	 *
+	 * length field of TXINFO should be set to 'xfer len'.
+	 */
+	info = FIELD_PREP(MT_TXD_INFO_LEN, round_up(skb->len, 4)) |
+	       FIELD_PREP(MT_TXD_INFO_DPORT, port) | flags;
+	put_unaligned_le32(info, skb_push(skb, sizeof(info)));
+
+	pad = round_up(skb->len, 4) + 4 - skb->len;
+	skb_walk_frags(skb, iter) {
+		last = iter;
+		if (!iter->next) {
+			skb->data_len += pad;
+			skb->len += pad;
+			break;
+		}
+	}
+
+	if (unlikely(pad)) {
+		if (__skb_pad(last, pad, true))
+			return -ENOMEM;
+		__skb_put(last, pad);
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt76u_skb_dma_info);
+
+static void mt76u_tx_tasklet(unsigned long data)
+{
+	struct mt76_dev *dev = (struct mt76_dev *)data;
+	struct mt76u_buf *buf;
+	struct mt76_queue *q;
+	bool wake;
+	int i;
+
+	for (i = 0; i < IEEE80211_NUM_ACS; i++) {
+		q = &dev->q_tx[i];
+
+		spin_lock_bh(&q->lock);
+		while (true) {
+			buf = &q->entry[q->head].ubuf;
+			if (!buf->done || !q->queued)
+				break;
+
+			dev->drv->tx_complete_skb(dev, q,
+						  &q->entry[q->head],
+						  false);
+
+			if (q->entry[q->head].schedule) {
+				q->entry[q->head].schedule = false;
+				q->swq_queued--;
+			}
+
+			q->head = (q->head + 1) % q->ndesc;
+			q->queued--;
+		}
+		mt76_txq_schedule(dev, q);
+		wake = i < IEEE80211_NUM_ACS && q->queued < q->ndesc - 8;
+		if (!q->queued)
+			wake_up(&dev->tx_wait);
+
+		spin_unlock_bh(&q->lock);
+
+		if (!test_and_set_bit(MT76_READING_STATS, &dev->state))
+			ieee80211_queue_delayed_work(dev->hw,
+						     &dev->usb.stat_work,
+						     msecs_to_jiffies(10));
+
+		if (wake)
+			ieee80211_wake_queue(dev->hw, i);
+	}
+}
+
+static void mt76u_tx_status_data(struct work_struct *work)
+{
+	struct mt76_usb *usb;
+	struct mt76_dev *dev;
+	u8 update = 1;
+	u16 count = 0;
+
+	usb = container_of(work, struct mt76_usb, stat_work.work);
+	dev = container_of(usb, struct mt76_dev, usb);
+
+	while (true) {
+		if (test_bit(MT76_REMOVED, &dev->state))
+			break;
+
+		if (!dev->drv->tx_status_data(dev, &update))
+			break;
+		count++;
+	}
+
+	if (count && test_bit(MT76_STATE_RUNNING, &dev->state))
+		ieee80211_queue_delayed_work(dev->hw, &usb->stat_work,
+					     msecs_to_jiffies(10));
+	else
+		clear_bit(MT76_READING_STATS, &dev->state);
+}
+
+static void mt76u_complete_tx(struct urb *urb)
+{
+	struct mt76u_buf *buf = urb->context;
+	struct mt76_dev *dev = buf->dev;
+
+	if (mt76u_urb_error(urb))
+		dev_err(dev->dev, "tx urb failed: %d\n", urb->status);
+	buf->done = true;
+
+	tasklet_schedule(&dev->usb.tx_tasklet);
+}
+
+static int
+mt76u_tx_build_sg(struct sk_buff *skb, struct urb *urb)
+{
+	int nsgs = 1 + skb_shinfo(skb)->nr_frags;
+	struct sk_buff *iter;
+
+	skb_walk_frags(skb, iter)
+		nsgs += 1 + skb_shinfo(iter)->nr_frags;
+
+	memset(urb->sg, 0, sizeof(*urb->sg) * MT_SG_MAX_SIZE);
+
+	nsgs = min_t(int, MT_SG_MAX_SIZE, nsgs);
+	sg_init_marker(urb->sg, nsgs);
+	urb->num_sgs = nsgs;
+
+	return skb_to_sgvec_nomark(skb, urb->sg, 0, skb->len);
+}
+
+static int
+mt76u_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q,
+		   struct sk_buff *skb, struct mt76_wcid *wcid,
+		   struct ieee80211_sta *sta)
+{
+	struct usb_interface *intf = to_usb_interface(dev->dev);
+	struct usb_device *udev = interface_to_usbdev(intf);
+	u8 ep = q2ep(q->hw_idx);
+	struct mt76u_buf *buf;
+	u16 idx = q->tail;
+	unsigned int pipe;
+	int err;
+
+	if (q->queued == q->ndesc)
+		return -ENOSPC;
+
+	err = dev->drv->tx_prepare_skb(dev, NULL, skb, q, wcid, sta, NULL);
+	if (err < 0)
+		return err;
+
+	buf = &q->entry[idx].ubuf;
+	buf->done = false;
+
+	err = mt76u_tx_build_sg(skb, buf->urb);
+	if (err < 0)
+		return err;
+
+	pipe = usb_sndbulkpipe(udev, dev->usb.out_ep[ep]);
+	usb_fill_bulk_urb(buf->urb, udev, pipe, NULL, skb->len,
+			  mt76u_complete_tx, buf);
+
+	q->tail = (q->tail + 1) % q->ndesc;
+	q->entry[idx].skb = skb;
+	q->queued++;
+
+	return idx;
+}
+
+static void mt76u_tx_kick(struct mt76_dev *dev, struct mt76_queue *q)
+{
+	struct mt76u_buf *buf;
+	int err;
+
+	while (q->first != q->tail) {
+		buf = &q->entry[q->first].ubuf;
+		err = usb_submit_urb(buf->urb, GFP_ATOMIC);
+		if (err < 0) {
+			if (err == -ENODEV)
+				set_bit(MT76_REMOVED, &dev->state);
+			else
+				dev_err(dev->dev, "tx urb submit failed:%d\n",
+					err);
+			break;
+		}
+		q->first = (q->first + 1) % q->ndesc;
+	}
+}
+
+static int mt76u_alloc_tx(struct mt76_dev *dev)
+{
+	struct mt76u_buf *buf;
+	struct mt76_queue *q;
+	size_t size;
+	int i, j;
+
+	size = MT_SG_MAX_SIZE * sizeof(struct scatterlist);
+	for (i = 0; i < IEEE80211_NUM_ACS; i++) {
+		q = &dev->q_tx[i];
+		spin_lock_init(&q->lock);
+		INIT_LIST_HEAD(&q->swq);
+		q->hw_idx = q2hwq(i);
+
+		q->entry = devm_kzalloc(dev->dev,
+					MT_NUM_TX_ENTRIES * sizeof(*q->entry),
+					GFP_KERNEL);
+		if (!q->entry)
+			return -ENOMEM;
+
+		q->ndesc = MT_NUM_TX_ENTRIES;
+		for (j = 0; j < q->ndesc; j++) {
+			buf = &q->entry[j].ubuf;
+			buf->dev = dev;
+
+			buf->urb = usb_alloc_urb(0, GFP_KERNEL);
+			if (!buf->urb)
+				return -ENOMEM;
+
+			buf->urb->sg = devm_kzalloc(dev->dev, size, GFP_KERNEL);
+			if (!buf->urb->sg)
+				return -ENOMEM;
+		}
+	}
+	return 0;
+}
+
+static void mt76u_free_tx(struct mt76_dev *dev)
+{
+	struct mt76_queue *q;
+	int i, j;
+
+	for (i = 0; i < IEEE80211_NUM_ACS; i++) {
+		q = &dev->q_tx[i];
+		for (j = 0; j < q->ndesc; j++)
+			usb_free_urb(q->entry[j].ubuf.urb);
+	}
+}
+
+static void mt76u_stop_tx(struct mt76_dev *dev)
+{
+	struct mt76_queue *q;
+	int i, j;
+
+	for (i = 0; i < IEEE80211_NUM_ACS; i++) {
+		q = &dev->q_tx[i];
+		for (j = 0; j < q->ndesc; j++)
+			usb_kill_urb(q->entry[j].ubuf.urb);
+	}
+}
+
+void mt76u_stop_queues(struct mt76_dev *dev)
+{
+	tasklet_disable(&dev->usb.rx_tasklet);
+	tasklet_disable(&dev->usb.tx_tasklet);
+
+	mt76u_stop_rx(dev);
+	mt76u_stop_tx(dev);
+}
+EXPORT_SYMBOL_GPL(mt76u_stop_queues);
+
+void mt76u_stop_stat_wk(struct mt76_dev *dev)
+{
+	cancel_delayed_work_sync(&dev->usb.stat_work);
+	clear_bit(MT76_READING_STATS, &dev->state);
+}
+EXPORT_SYMBOL_GPL(mt76u_stop_stat_wk);
+
+void mt76u_queues_deinit(struct mt76_dev *dev)
+{
+	mt76u_stop_queues(dev);
+
+	mt76u_free_rx(dev);
+	mt76u_free_tx(dev);
+}
+EXPORT_SYMBOL_GPL(mt76u_queues_deinit);
+
+int mt76u_alloc_queues(struct mt76_dev *dev)
+{
+	int err;
+
+	err = mt76u_alloc_rx(dev);
+	if (err < 0)
+		goto err;
+
+	err = mt76u_alloc_tx(dev);
+	if (err < 0)
+		goto err;
+
+	return 0;
+err:
+	mt76u_queues_deinit(dev);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mt76u_alloc_queues);
+
+static const struct mt76_queue_ops usb_queue_ops = {
+	.tx_queue_skb = mt76u_tx_queue_skb,
+	.kick = mt76u_tx_kick,
+};
+
+int mt76u_init(struct mt76_dev *dev,
+	       struct usb_interface *intf)
+{
+	static const struct mt76_bus_ops mt76u_ops = {
+		.rr = mt76u_rr,
+		.wr = mt76u_wr,
+		.rmw = mt76u_rmw,
+		.copy = mt76u_copy,
+	};
+	struct mt76_usb *usb = &dev->usb;
+
+	tasklet_init(&usb->rx_tasklet, mt76u_rx_tasklet, (unsigned long)dev);
+	tasklet_init(&usb->tx_tasklet, mt76u_tx_tasklet, (unsigned long)dev);
+	INIT_DELAYED_WORK(&usb->stat_work, mt76u_tx_status_data);
+	skb_queue_head_init(&dev->rx_skb[MT_RXQ_MAIN]);
+
+	init_completion(&usb->mcu.cmpl);
+	mutex_init(&usb->mcu.mutex);
+
+	mutex_init(&usb->usb_ctrl_mtx);
+	dev->bus = &mt76u_ops;
+	dev->queue_ops = &usb_queue_ops;
+
+	return mt76u_set_endpoints(intf, usb);
+}
+EXPORT_SYMBOL_GPL(mt76u_init);
+
+MODULE_AUTHOR("Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/usb_mcu.c b/drivers/net/wireless/mediatek/mt76/usb_mcu.c
new file mode 100644
index 000000000000..070be803d463
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/usb_mcu.c
@@ -0,0 +1,242 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/firmware.h>
+
+#include "mt76.h"
+#include "dma.h"
+
+#define MT_CMD_HDR_LEN			4
+
+#define MT_FCE_DMA_ADDR			0x0230
+#define MT_FCE_DMA_LEN			0x0234
+
+#define MT_TX_CPU_FROM_FCE_CPU_DESC_IDX	0x09a8
+
+struct sk_buff *mt76u_mcu_msg_alloc(const void *data, int len)
+{
+	struct sk_buff *skb;
+
+	skb = alloc_skb(MT_CMD_HDR_LEN + len + 8, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	skb_reserve(skb, MT_CMD_HDR_LEN);
+	skb_put_data(skb, data, len);
+
+	return skb;
+}
+EXPORT_SYMBOL_GPL(mt76u_mcu_msg_alloc);
+
+void mt76u_mcu_complete_urb(struct urb *urb)
+{
+	struct completion *cmpl = urb->context;
+
+	complete(cmpl);
+}
+EXPORT_SYMBOL_GPL(mt76u_mcu_complete_urb);
+
+static int mt76u_mcu_wait_resp(struct mt76_dev *dev, u8 seq)
+{
+	struct mt76_usb *usb = &dev->usb;
+	struct mt76u_buf *buf = &usb->mcu.res;
+	int i, ret;
+	u32 rxfce;
+
+	for (i = 0; i < 5; i++) {
+		if (!wait_for_completion_timeout(&usb->mcu.cmpl,
+						 msecs_to_jiffies(300)))
+			continue;
+
+		if (buf->urb->status)
+			return -EIO;
+
+		rxfce = get_unaligned_le32(sg_virt(&buf->urb->sg[0]));
+		ret = mt76u_submit_buf(dev, USB_DIR_IN,
+				       MT_EP_IN_CMD_RESP,
+				       buf, GFP_KERNEL,
+				       mt76u_mcu_complete_urb,
+				       &usb->mcu.cmpl);
+		if (ret)
+			return ret;
+
+		if (seq == FIELD_GET(MT_RX_FCE_INFO_CMD_SEQ, rxfce))
+			return 0;
+
+		dev_err(dev->dev, "error: MCU resp evt:%lx seq:%hhx-%lx\n",
+			FIELD_GET(MT_RX_FCE_INFO_EVT_TYPE, rxfce),
+			seq, FIELD_GET(MT_RX_FCE_INFO_CMD_SEQ, rxfce));
+	}
+
+	dev_err(dev->dev, "error: %s timed out\n", __func__);
+	return -ETIMEDOUT;
+}
+
+int mt76u_mcu_send_msg(struct mt76_dev *dev, struct sk_buff *skb,
+		       int cmd, bool wait_resp)
+{
+	struct usb_interface *intf = to_usb_interface(dev->dev);
+	struct usb_device *udev = interface_to_usbdev(intf);
+	struct mt76_usb *usb = &dev->usb;
+	unsigned int pipe;
+	int ret, sent;
+	u8 seq = 0;
+	u32 info;
+
+	if (test_bit(MT76_REMOVED, &dev->state))
+		return 0;
+
+	mutex_lock(&usb->mcu.mutex);
+
+	pipe = usb_sndbulkpipe(udev, usb->out_ep[MT_EP_OUT_INBAND_CMD]);
+	if (wait_resp) {
+		seq = ++usb->mcu.msg_seq & 0xf;
+		if (!seq)
+			seq = ++usb->mcu.msg_seq & 0xf;
+	}
+
+	info = FIELD_PREP(MT_MCU_MSG_CMD_SEQ, seq) |
+	       FIELD_PREP(MT_MCU_MSG_CMD_TYPE, cmd) |
+	       MT_MCU_MSG_TYPE_CMD;
+	ret = mt76u_skb_dma_info(skb, CPU_TX_PORT, info);
+	if (ret)
+		goto out;
+
+	ret = usb_bulk_msg(udev, pipe, skb->data, skb->len, &sent, 500);
+	if (ret)
+		goto out;
+
+	if (wait_resp)
+		ret = mt76u_mcu_wait_resp(dev, seq);
+
+out:
+	mutex_unlock(&usb->mcu.mutex);
+
+	consume_skb(skb);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mt76u_mcu_send_msg);
+
+void mt76u_mcu_fw_reset(struct mt76_dev *dev)
+{
+	mt76u_vendor_request(dev, MT_VEND_DEV_MODE,
+			     USB_DIR_OUT | USB_TYPE_VENDOR,
+			     0x1, 0, NULL, 0);
+}
+EXPORT_SYMBOL_GPL(mt76u_mcu_fw_reset);
+
+static int
+__mt76u_mcu_fw_send_data(struct mt76_dev *dev, struct mt76u_buf *buf,
+			 const void *fw_data, int len, u32 dst_addr)
+{
+	u8 *data = sg_virt(&buf->urb->sg[0]);
+	DECLARE_COMPLETION_ONSTACK(cmpl);
+	__le32 info;
+	u32 val;
+	int err;
+
+	info = cpu_to_le32(FIELD_PREP(MT_MCU_MSG_PORT, CPU_TX_PORT) |
+			   FIELD_PREP(MT_MCU_MSG_LEN, len) |
+			   MT_MCU_MSG_TYPE_CMD);
+
+	memcpy(data, &info, sizeof(info));
+	memcpy(data + sizeof(info), fw_data, len);
+	memset(data + sizeof(info) + len, 0, 4);
+
+	mt76u_single_wr(dev, MT_VEND_WRITE_FCE,
+			MT_FCE_DMA_ADDR, dst_addr);
+	len = roundup(len, 4);
+	mt76u_single_wr(dev, MT_VEND_WRITE_FCE,
+			MT_FCE_DMA_LEN, len << 16);
+
+	buf->len = MT_CMD_HDR_LEN + len + sizeof(info);
+	err = mt76u_submit_buf(dev, USB_DIR_OUT,
+			       MT_EP_OUT_INBAND_CMD,
+			       buf, GFP_KERNEL,
+			       mt76u_mcu_complete_urb, &cmpl);
+	if (err < 0)
+		return err;
+
+	if (!wait_for_completion_timeout(&cmpl,
+					 msecs_to_jiffies(1000))) {
+		dev_err(dev->dev, "firmware upload timed out\n");
+		usb_kill_urb(buf->urb);
+		return -ETIMEDOUT;
+	}
+
+	if (mt76u_urb_error(buf->urb)) {
+		dev_err(dev->dev, "firmware upload failed: %d\n",
+			buf->urb->status);
+		return buf->urb->status;
+	}
+
+	val = mt76u_rr(dev, MT_TX_CPU_FROM_FCE_CPU_DESC_IDX);
+	val++;
+	mt76u_wr(dev, MT_TX_CPU_FROM_FCE_CPU_DESC_IDX, val);
+
+	return 0;
+}
+
+int mt76u_mcu_fw_send_data(struct mt76_dev *dev, const void *data,
+			   int data_len, u32 max_payload, u32 offset)
+{
+	int err, len, pos = 0, max_len = max_payload - 8;
+	struct mt76u_buf buf;
+
+	err = mt76u_buf_alloc(dev, &buf, 1, max_payload, max_payload,
+			      GFP_KERNEL);
+	if (err < 0)
+		return err;
+
+	while (data_len > 0) {
+		len = min_t(int, data_len, max_len);
+		err = __mt76u_mcu_fw_send_data(dev, &buf, data + pos,
+					       len, offset + pos);
+		if (err < 0)
+			break;
+
+		data_len -= len;
+		pos += len;
+		usleep_range(5000, 10000);
+	}
+	mt76u_buf_free(&buf);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(mt76u_mcu_fw_send_data);
+
+int mt76u_mcu_init_rx(struct mt76_dev *dev)
+{
+	struct mt76_usb *usb = &dev->usb;
+	int err;
+
+	err = mt76u_buf_alloc(dev, &usb->mcu.res, 1,
+			      MCU_RESP_URB_SIZE, MCU_RESP_URB_SIZE,
+			      GFP_KERNEL);
+	if (err < 0)
+		return err;
+
+	err = mt76u_submit_buf(dev, USB_DIR_IN, MT_EP_IN_CMD_RESP,
+			       &usb->mcu.res, GFP_KERNEL,
+			       mt76u_mcu_complete_urb,
+			       &usb->mcu.cmpl);
+	if (err < 0)
+		mt76u_buf_free(&usb->mcu.res);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(mt76u_mcu_init_rx);
diff --git a/drivers/net/wireless/mediatek/mt76/usb_trace.c b/drivers/net/wireless/mediatek/mt76/usb_trace.c
new file mode 100644
index 000000000000..7e1f540f0b7a
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/usb_trace.c
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/module.h>
+
+#ifndef __CHECKER__
+#define CREATE_TRACE_POINTS
+#include "usb_trace.h"
+
+#endif
diff --git a/drivers/net/wireless/mediatek/mt76/usb_trace.h b/drivers/net/wireless/mediatek/mt76/usb_trace.h
new file mode 100644
index 000000000000..52db7012304a
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/usb_trace.h
@@ -0,0 +1,71 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#if !defined(__MT76_USB_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __MT76_USB_TRACE_H
+
+#include <linux/tracepoint.h>
+#include "mt76.h"
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mt76_usb
+
+#define MAXNAME		32
+#define DEV_ENTRY   __array(char, wiphy_name, 32)
+#define DEV_ASSIGN  strlcpy(__entry->wiphy_name, wiphy_name(dev->hw->wiphy), MAXNAME)
+#define DEV_PR_FMT  "%s"
+#define DEV_PR_ARG  __entry->wiphy_name
+
+#define REG_ENTRY	__field(u32, reg) __field(u32, val)
+#define REG_ASSIGN	__entry->reg = reg; __entry->val = val
+#define REG_PR_FMT	" %04x=%08x"
+#define REG_PR_ARG	__entry->reg, __entry->val
+
+DECLARE_EVENT_CLASS(dev_reg_evt,
+	TP_PROTO(struct mt76_dev *dev, u32 reg, u32 val),
+	TP_ARGS(dev, reg, val),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		REG_ENTRY
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		REG_ASSIGN;
+	),
+	TP_printk(
+		DEV_PR_FMT REG_PR_FMT,
+		DEV_PR_ARG, REG_PR_ARG
+	)
+);
+
+DEFINE_EVENT(dev_reg_evt, usb_reg_rr,
+	TP_PROTO(struct mt76_dev *dev, u32 reg, u32 val),
+	TP_ARGS(dev, reg, val)
+);
+
+DEFINE_EVENT(dev_reg_evt, usb_reg_wr,
+	TP_PROTO(struct mt76_dev *dev, u32 reg, u32 val),
+	TP_ARGS(dev, reg, val)
+);
+
+#endif
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE usb_trace
+
+#include <trace/define_trace.h>
diff --git a/drivers/net/wireless/mediatek/mt7601u/init.c b/drivers/net/wireless/mediatek/mt7601u/init.c
index d3b611aaf061..faea99b7a445 100644
--- a/drivers/net/wireless/mediatek/mt7601u/init.c
+++ b/drivers/net/wireless/mediatek/mt7601u/init.c
@@ -603,6 +603,7 @@ int mt7601u_register_device(struct mt7601u_dev *dev)
 	ieee80211_hw_set(hw, SUPPORTS_HT_CCK_RATES);
 	ieee80211_hw_set(hw, AMPDU_AGGREGATION);
 	ieee80211_hw_set(hw, SUPPORTS_RC_TABLE);
+	ieee80211_hw_set(hw, MFP_CAPABLE);
 	hw->max_rates = 1;
 	hw->max_report_rates = 7;
 	hw->max_rate_tries = 1;
diff --git a/drivers/net/wireless/mediatek/mt7601u/main.c b/drivers/net/wireless/mediatek/mt7601u/main.c
index 7b21016012c3..0f1789020960 100644
--- a/drivers/net/wireless/mediatek/mt7601u/main.c
+++ b/drivers/net/wireless/mediatek/mt7601u/main.c
@@ -308,6 +308,17 @@ mt7601u_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	int idx = key->keyidx;
 	int ret;
 
+	/* fall back to sw encryption for unsupported ciphers */
+	switch (key->cipher) {
+	case WLAN_CIPHER_SUITE_WEP40:
+	case WLAN_CIPHER_SUITE_WEP104:
+	case WLAN_CIPHER_SUITE_TKIP:
+	case WLAN_CIPHER_SUITE_CCMP:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
 	if (cmd == SET_KEY) {
 		key->hw_key_idx = wcid->idx;
 		wcid->hw_key_idx = idx;
diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
index ae0ca8006849..4aa332f4646b 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
@@ -843,6 +843,88 @@ static int qtnf_set_mac_acl(struct wiphy *wiphy,
 	return ret;
 }
 
+static int qtnf_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev,
+			       bool enabled, int timeout)
+{
+	struct qtnf_vif *vif = qtnf_netdev_get_priv(dev);
+	int ret;
+
+	ret = qtnf_cmd_send_pm_set(vif, enabled ? QLINK_PM_AUTO_STANDBY :
+				   QLINK_PM_OFF, timeout);
+	if (ret) {
+		pr_err("%s: failed to set PM mode ret=%d\n", dev->name, ret);
+		return ret;
+	}
+
+	return ret;
+}
+
+#ifdef CONFIG_PM
+static int qtnf_suspend(struct wiphy *wiphy, struct cfg80211_wowlan *wowlan)
+{
+	struct qtnf_wmac *mac = wiphy_priv(wiphy);
+	struct qtnf_vif *vif;
+	int ret = 0;
+
+	vif = qtnf_mac_get_base_vif(mac);
+	if (!vif) {
+		pr_err("MAC%u: primary VIF is not configured\n", mac->macid);
+		ret = -EFAULT;
+		goto exit;
+	}
+
+	if (!wowlan) {
+		pr_debug("WoWLAN triggers are not enabled\n");
+		qtnf_virtual_intf_cleanup(vif->netdev);
+		goto exit;
+	}
+
+	qtnf_scan_done(vif->mac, true);
+
+	ret = qtnf_cmd_send_wowlan_set(vif, wowlan);
+	if (ret) {
+		pr_err("MAC%u: failed to set WoWLAN triggers\n",
+		       mac->macid);
+		goto exit;
+	}
+
+exit:
+	return ret;
+}
+
+static int qtnf_resume(struct wiphy *wiphy)
+{
+	struct qtnf_wmac *mac = wiphy_priv(wiphy);
+	struct qtnf_vif *vif;
+	int ret = 0;
+
+	vif = qtnf_mac_get_base_vif(mac);
+	if (!vif) {
+		pr_err("MAC%u: primary VIF is not configured\n", mac->macid);
+		ret = -EFAULT;
+		goto exit;
+	}
+
+	ret = qtnf_cmd_send_wowlan_set(vif, NULL);
+	if (ret) {
+		pr_err("MAC%u: failed to reset WoWLAN triggers\n",
+		       mac->macid);
+		goto exit;
+	}
+
+exit:
+	return ret;
+}
+
+static void qtnf_set_wakeup(struct wiphy *wiphy, bool enabled)
+{
+	struct qtnf_wmac *mac = wiphy_priv(wiphy);
+	struct qtnf_bus *bus = mac->bus;
+
+	device_set_wakeup_enable(bus->dev, enabled);
+}
+#endif
+
 static struct cfg80211_ops qtn_cfg80211_ops = {
 	.add_virtual_intf	= qtnf_add_virtual_intf,
 	.change_virtual_intf	= qtnf_change_virtual_intf,
@@ -869,6 +951,12 @@ static struct cfg80211_ops qtn_cfg80211_ops = {
 	.channel_switch		= qtnf_channel_switch,
 	.start_radar_detection	= qtnf_start_radar_detection,
 	.set_mac_acl		= qtnf_set_mac_acl,
+	.set_power_mgmt		= qtnf_set_power_mgmt,
+#ifdef CONFIG_PM
+	.suspend		= qtnf_suspend,
+	.resume			= qtnf_resume,
+	.set_wakeup		= qtnf_set_wakeup,
+#endif
 };
 
 static void qtnf_cfg80211_reg_notifier(struct wiphy *wiphy_in,
@@ -921,6 +1009,9 @@ struct wiphy *qtnf_wiphy_allocate(struct qtnf_bus *bus)
 	if (bus->hw_info.hw_capab & QLINK_HW_CAPAB_DFS_OFFLOAD)
 		qtn_cfg80211_ops.start_radar_detection = NULL;
 
+	if (!(bus->hw_info.hw_capab & QLINK_HW_CAPAB_PWR_MGMT))
+		qtn_cfg80211_ops.set_power_mgmt	= NULL;
+
 	wiphy = wiphy_new(&qtn_cfg80211_ops, sizeof(struct qtnf_wmac));
 	if (!wiphy)
 		return NULL;
@@ -975,7 +1066,8 @@ int qtnf_wiphy_register(struct qtnf_hw_info *hw_info, struct qtnf_wmac *mac)
 	wiphy->retry_long = macinfo->lretry_limit;
 	wiphy->coverage_class = macinfo->coverage_class;
 
-	wiphy->max_scan_ssids = QTNF_MAX_SSID_LIST_LENGTH;
+	wiphy->max_scan_ssids =
+		(hw_info->max_scan_ssids) ? hw_info->max_scan_ssids : 1;
 	wiphy->max_scan_ie_len = QTNF_MAX_VSIE_LEN;
 	wiphy->mgmt_stypes = qtnf_mgmt_stypes;
 	wiphy->max_remain_on_channel_duration = 5000;
@@ -994,6 +1086,7 @@ int qtnf_wiphy_register(struct qtnf_hw_info *hw_info, struct qtnf_wmac *mac)
 			WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD |
 			WIPHY_FLAG_AP_UAPSD |
 			WIPHY_FLAG_HAS_CHANNEL_SWITCH;
+	wiphy->flags &= ~WIPHY_FLAG_PS_ON_BY_DEFAULT;
 
 	if (hw_info->hw_capab & QLINK_HW_CAPAB_DFS_OFFLOAD)
 		wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_DFS_OFFLOAD);
@@ -1013,6 +1106,14 @@ int qtnf_wiphy_register(struct qtnf_hw_info *hw_info, struct qtnf_wmac *mac)
 	if (hw_info->hw_capab & QLINK_HW_CAPAB_STA_INACT_TIMEOUT)
 		wiphy->features |= NL80211_FEATURE_INACTIVITY_TIMER;
 
+	if (hw_info->hw_capab & QLINK_HW_CAPAB_SCAN_RANDOM_MAC_ADDR)
+		wiphy->features |= NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR;
+
+#ifdef CONFIG_PM
+	if (macinfo->wowlan)
+		wiphy->wowlan = macinfo->wowlan;
+#endif
+
 	if (hw_info->hw_capab & QLINK_HW_CAPAB_REG_UPDATE) {
 		wiphy->regulatory_flags |= REGULATORY_STRICT_REG |
 			REGULATORY_CUSTOM_REG;
diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.c b/drivers/net/wireless/quantenna/qtnfmac/commands.c
index c5d94a95e21a..ae9e77300533 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/commands.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/commands.c
@@ -640,83 +640,83 @@ qtnf_cmd_sta_info_parse(struct station_info *sinfo,
 		return;
 
 	if (qtnf_sta_stat_avail(inactive_time, QLINK_STA_INFO_INACTIVE_TIME)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_INACTIVE_TIME);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_INACTIVE_TIME);
 		sinfo->inactive_time = le32_to_cpu(stats->inactive_time);
 	}
 
 	if (qtnf_sta_stat_avail(connected_time,
 				QLINK_STA_INFO_CONNECTED_TIME)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_CONNECTED_TIME);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CONNECTED_TIME);
 		sinfo->connected_time = le32_to_cpu(stats->connected_time);
 	}
 
 	if (qtnf_sta_stat_avail(signal, QLINK_STA_INFO_SIGNAL)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 		sinfo->signal = stats->signal - QLINK_RSSI_OFFSET;
 	}
 
 	if (qtnf_sta_stat_avail(signal_avg, QLINK_STA_INFO_SIGNAL_AVG)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL_AVG);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG);
 		sinfo->signal_avg = stats->signal_avg - QLINK_RSSI_OFFSET;
 	}
 
 	if (qtnf_sta_stat_avail(rxrate, QLINK_STA_INFO_RX_BITRATE)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_RX_BITRATE);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BITRATE);
 		qtnf_sta_info_parse_rate(&sinfo->rxrate, &stats->rxrate);
 	}
 
 	if (qtnf_sta_stat_avail(txrate, QLINK_STA_INFO_TX_BITRATE)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 		qtnf_sta_info_parse_rate(&sinfo->txrate, &stats->txrate);
 	}
 
 	if (qtnf_sta_stat_avail(sta_flags, QLINK_STA_INFO_STA_FLAGS)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_STA_FLAGS);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_STA_FLAGS);
 		qtnf_sta_info_parse_flags(&sinfo->sta_flags, &stats->sta_flags);
 	}
 
 	if (qtnf_sta_stat_avail(rx_bytes, QLINK_STA_INFO_RX_BYTES)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_RX_BYTES);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BYTES);
 		sinfo->rx_bytes = le64_to_cpu(stats->rx_bytes);
 	}
 
 	if (qtnf_sta_stat_avail(tx_bytes, QLINK_STA_INFO_TX_BYTES)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BYTES);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BYTES);
 		sinfo->tx_bytes = le64_to_cpu(stats->tx_bytes);
 	}
 
 	if (qtnf_sta_stat_avail(rx_bytes, QLINK_STA_INFO_RX_BYTES64)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_RX_BYTES64);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BYTES64);
 		sinfo->rx_bytes = le64_to_cpu(stats->rx_bytes);
 	}
 
 	if (qtnf_sta_stat_avail(tx_bytes, QLINK_STA_INFO_TX_BYTES64)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BYTES64);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BYTES64);
 		sinfo->tx_bytes = le64_to_cpu(stats->tx_bytes);
 	}
 
 	if (qtnf_sta_stat_avail(rx_packets, QLINK_STA_INFO_RX_PACKETS)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_RX_PACKETS);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_PACKETS);
 		sinfo->rx_packets = le32_to_cpu(stats->rx_packets);
 	}
 
 	if (qtnf_sta_stat_avail(tx_packets, QLINK_STA_INFO_TX_PACKETS)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_PACKETS);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_PACKETS);
 		sinfo->tx_packets = le32_to_cpu(stats->tx_packets);
 	}
 
 	if (qtnf_sta_stat_avail(rx_beacon, QLINK_STA_INFO_BEACON_RX)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_BEACON_RX);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BEACON_RX);
 		sinfo->rx_beacon = le64_to_cpu(stats->rx_beacon);
 	}
 
 	if (qtnf_sta_stat_avail(rx_dropped_misc, QLINK_STA_INFO_RX_DROP_MISC)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_RX_DROP_MISC);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_DROP_MISC);
 		sinfo->rx_dropped_misc = le32_to_cpu(stats->rx_dropped_misc);
 	}
 
 	if (qtnf_sta_stat_avail(tx_failed, QLINK_STA_INFO_TX_FAILED)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_FAILED);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_FAILED);
 		sinfo->tx_failed = le32_to_cpu(stats->tx_failed);
 	}
 
@@ -1092,6 +1092,9 @@ qtnf_cmd_resp_proc_hw_info(struct qtnf_bus *bus,
 		case QTN_TLV_ID_UBOOT_VER:
 			uboot_ver = (const void *)tlv->val;
 			break;
+		case QTN_TLV_ID_MAX_SCAN_SSIDS:
+			hwinfo->max_scan_ssids = *tlv->val;
+			break;
 		default:
 			break;
 		}
@@ -1135,6 +1138,37 @@ qtnf_cmd_resp_proc_hw_info(struct qtnf_bus *bus,
 	return 0;
 }
 
+static void
+qtnf_parse_wowlan_info(struct qtnf_wmac *mac,
+		       const struct qlink_wowlan_capab_data *wowlan)
+{
+	struct qtnf_mac_info *mac_info = &mac->macinfo;
+	const struct qlink_wowlan_support *data1;
+	struct wiphy_wowlan_support *supp;
+
+	supp = kzalloc(sizeof(*supp), GFP_KERNEL);
+	if (!supp)
+		return;
+
+	switch (le16_to_cpu(wowlan->version)) {
+	case 0x1:
+		data1 = (struct qlink_wowlan_support *)wowlan->data;
+
+		supp->flags = WIPHY_WOWLAN_MAGIC_PKT | WIPHY_WOWLAN_DISCONNECT;
+		supp->n_patterns = le32_to_cpu(data1->n_patterns);
+		supp->pattern_max_len = le32_to_cpu(data1->pattern_max_len);
+		supp->pattern_min_len = le32_to_cpu(data1->pattern_min_len);
+
+		mac_info->wowlan = supp;
+		break;
+	default:
+		pr_warn("MAC%u: unsupported WoWLAN version 0x%x\n",
+			mac->macid, le16_to_cpu(wowlan->version));
+		kfree(supp);
+		break;
+	}
+}
+
 static int qtnf_parse_variable_mac_info(struct qtnf_wmac *mac,
 					const u8 *tlv_buf, size_t tlv_buf_size)
 {
@@ -1144,6 +1178,7 @@ static int qtnf_parse_variable_mac_info(struct qtnf_wmac *mac,
 	const struct qlink_iface_comb_num *comb_num;
 	const struct qlink_iface_limit_record *rec;
 	const struct qlink_iface_limit *lim;
+	const struct qlink_wowlan_capab_data *wowlan;
 	u16 rec_len;
 	u16 tlv_type;
 	u16 tlv_value_len;
@@ -1252,7 +1287,31 @@ static int qtnf_parse_variable_mac_info(struct qtnf_wmac *mac,
 			ext_capa_mask = (u8 *)tlv->val;
 			ext_capa_mask_len = tlv_value_len;
 			break;
+		case QTN_TLV_ID_WOWLAN_CAPAB:
+			if (tlv_value_len < sizeof(*wowlan))
+				return -EINVAL;
+
+			wowlan = (void *)tlv->val;
+			if (!le16_to_cpu(wowlan->len)) {
+				pr_warn("MAC%u: skip empty WoWLAN data\n",
+					mac->macid);
+				break;
+			}
+
+			rec_len = sizeof(*wowlan) + le16_to_cpu(wowlan->len);
+			if (unlikely(tlv_value_len != rec_len)) {
+				pr_warn("MAC%u: WoWLAN data size mismatch\n",
+					mac->macid);
+				return -EINVAL;
+			}
+
+			kfree(mac->macinfo.wowlan);
+			mac->macinfo.wowlan = NULL;
+			qtnf_parse_wowlan_info(mac, wowlan);
+			break;
 		default:
+			pr_warn("MAC%u: unknown TLV type %u\n",
+				mac->macid, tlv_type);
 			break;
 		}
 
@@ -2234,6 +2293,22 @@ static void qtnf_cmd_channel_tlv_add(struct sk_buff *cmd_skb,
 	qchan->chan.flags = cpu_to_le32(flags);
 }
 
+static void qtnf_cmd_randmac_tlv_add(struct sk_buff *cmd_skb,
+				     const u8 *mac_addr,
+				     const u8 *mac_addr_mask)
+{
+	struct qlink_random_mac_addr *randmac;
+	struct qlink_tlv_hdr *hdr =
+		skb_put(cmd_skb, sizeof(*hdr) + sizeof(*randmac));
+
+	hdr->type = cpu_to_le16(QTN_TLV_ID_RANDOM_MAC_ADDR);
+	hdr->len = cpu_to_le16(sizeof(*randmac));
+	randmac = (struct qlink_random_mac_addr *)hdr->val;
+
+	memcpy(randmac->mac_addr, mac_addr, ETH_ALEN);
+	memcpy(randmac->mac_addr_mask, mac_addr_mask, ETH_ALEN);
+}
+
 int qtnf_cmd_send_scan(struct qtnf_wmac *mac)
 {
 	struct sk_buff *cmd_skb;
@@ -2244,11 +2319,6 @@ int qtnf_cmd_send_scan(struct qtnf_wmac *mac)
 	int count = 0;
 	int ret;
 
-	if (scan_req->n_ssids > QTNF_MAX_SSID_LIST_LENGTH) {
-		pr_err("MAC%u: too many SSIDs in scan request\n", mac->macid);
-		return -EINVAL;
-	}
-
 	cmd_skb = qtnf_cmd_alloc_new_cmdskb(mac->macid, QLINK_VIFID_RSVD,
 					    QLINK_CMD_SCAN,
 					    sizeof(struct qlink_cmd));
@@ -2291,6 +2361,15 @@ int qtnf_cmd_send_scan(struct qtnf_wmac *mac)
 		}
 	}
 
+	if (scan_req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) {
+		pr_debug("MAC%u: scan with random addr=%pM, mask=%pM\n",
+			 mac->macid,
+			 scan_req->mac_addr, scan_req->mac_addr_mask);
+
+		qtnf_cmd_randmac_tlv_add(cmd_skb, scan_req->mac_addr,
+					 scan_req->mac_addr_mask);
+	}
+
 	ret = qtnf_cmd_send(mac->bus, cmd_skb, &res_code);
 
 	if (unlikely(ret))
@@ -2774,3 +2853,93 @@ int qtnf_cmd_set_mac_acl(const struct qtnf_vif *vif,
 
 	return ret;
 }
+
+int qtnf_cmd_send_pm_set(const struct qtnf_vif *vif, u8 pm_mode, int timeout)
+{
+	struct qtnf_bus *bus = vif->mac->bus;
+	struct sk_buff *cmd_skb;
+	u16 res_code = QLINK_CMD_RESULT_OK;
+	struct qlink_cmd_pm_set *cmd;
+	int ret = 0;
+
+	cmd_skb = qtnf_cmd_alloc_new_cmdskb(vif->mac->macid, vif->vifid,
+					    QLINK_CMD_PM_SET, sizeof(*cmd));
+	if (!cmd_skb)
+		return -ENOMEM;
+
+	cmd = (struct qlink_cmd_pm_set *)cmd_skb->data;
+	cmd->pm_mode = pm_mode;
+	cmd->pm_standby_timer = cpu_to_le32(timeout);
+
+	qtnf_bus_lock(bus);
+
+	ret = qtnf_cmd_send(bus, cmd_skb, &res_code);
+
+	if (unlikely(ret))
+		goto out;
+
+	if (unlikely(res_code != QLINK_CMD_RESULT_OK)) {
+		pr_err("cmd exec failed: 0x%.4X\n", res_code);
+		ret = -EFAULT;
+	}
+
+out:
+	qtnf_bus_unlock(bus);
+	return ret;
+}
+
+int qtnf_cmd_send_wowlan_set(const struct qtnf_vif *vif,
+			     const struct cfg80211_wowlan *wowl)
+{
+	struct qtnf_bus *bus = vif->mac->bus;
+	struct sk_buff *cmd_skb;
+	u16 res_code = QLINK_CMD_RESULT_OK;
+	struct qlink_cmd_wowlan_set *cmd;
+	u32 triggers = 0;
+	int count = 0;
+	int ret = 0;
+
+	cmd_skb = qtnf_cmd_alloc_new_cmdskb(vif->mac->macid, vif->vifid,
+					    QLINK_CMD_WOWLAN_SET, sizeof(*cmd));
+	if (!cmd_skb)
+		return -ENOMEM;
+
+	qtnf_bus_lock(bus);
+
+	cmd = (struct qlink_cmd_wowlan_set *)cmd_skb->data;
+
+	if (wowl) {
+		if (wowl->disconnect)
+			triggers |=  QLINK_WOWLAN_TRIG_DISCONNECT;
+
+		if (wowl->magic_pkt)
+			triggers |= QLINK_WOWLAN_TRIG_MAGIC_PKT;
+
+		if (wowl->n_patterns && wowl->patterns) {
+			triggers |= QLINK_WOWLAN_TRIG_PATTERN_PKT;
+			while (count < wowl->n_patterns) {
+				qtnf_cmd_skb_put_tlv_arr(cmd_skb,
+					QTN_TLV_ID_WOWLAN_PATTERN,
+					wowl->patterns[count].pattern,
+					wowl->patterns[count].pattern_len);
+				count++;
+			}
+		}
+	}
+
+	cmd->triggers = cpu_to_le32(triggers);
+
+	ret = qtnf_cmd_send(bus, cmd_skb, &res_code);
+
+	if (unlikely(ret))
+		goto out;
+
+	if (unlikely(res_code != QLINK_CMD_RESULT_OK)) {
+		pr_err("cmd exec failed: 0x%.4X\n", res_code);
+		ret = -EFAULT;
+	}
+
+out:
+	qtnf_bus_unlock(bus);
+	return ret;
+}
diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.h b/drivers/net/wireless/quantenna/qtnfmac/commands.h
index cf9274add26d..1ac41156c192 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/commands.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/commands.h
@@ -76,5 +76,8 @@ int qtnf_cmd_start_cac(const struct qtnf_vif *vif,
 		       u32 cac_time_ms);
 int qtnf_cmd_set_mac_acl(const struct qtnf_vif *vif,
 			 const struct cfg80211_acl_data *params);
+int qtnf_cmd_send_pm_set(const struct qtnf_vif *vif, u8 pm_mode, int timeout);
+int qtnf_cmd_send_wowlan_set(const struct qtnf_vif *vif,
+			     const struct cfg80211_wowlan *wowl);
 
 #endif /* QLINK_COMMANDS_H_ */
diff --git a/drivers/net/wireless/quantenna/qtnfmac/core.c b/drivers/net/wireless/quantenna/qtnfmac/core.c
index a6a450984f9a..19abbc4e23e0 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/core.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/core.c
@@ -179,6 +179,30 @@ static void qtnf_netdev_tx_timeout(struct net_device *ndev)
 	}
 }
 
+static int qtnf_netdev_set_mac_address(struct net_device *ndev, void *addr)
+{
+	struct qtnf_vif *vif = qtnf_netdev_get_priv(ndev);
+	struct sockaddr *sa = addr;
+	int ret;
+	unsigned char old_addr[ETH_ALEN];
+
+	memcpy(old_addr, sa->sa_data, sizeof(old_addr));
+
+	ret = eth_mac_addr(ndev, sa);
+	if (ret)
+		return ret;
+
+	qtnf_scan_done(vif->mac, true);
+
+	ret = qtnf_cmd_send_change_intf_type(vif, vif->wdev.iftype,
+					     sa->sa_data);
+
+	if (ret)
+		memcpy(ndev->dev_addr, old_addr, ETH_ALEN);
+
+	return ret;
+}
+
 /* Network device ops handlers */
 const struct net_device_ops qtnf_netdev_ops = {
 	.ndo_open = qtnf_netdev_open,
@@ -186,6 +210,7 @@ const struct net_device_ops qtnf_netdev_ops = {
 	.ndo_start_xmit = qtnf_netdev_hard_start_xmit,
 	.ndo_tx_timeout = qtnf_netdev_tx_timeout,
 	.ndo_get_stats64 = qtnf_netdev_get_stats64,
+	.ndo_set_mac_address = qtnf_netdev_set_mac_address,
 };
 
 static int qtnf_mac_init_single_band(struct wiphy *wiphy,
@@ -470,6 +495,7 @@ static void qtnf_core_mac_detach(struct qtnf_bus *bus, unsigned int macid)
 	qtnf_mac_iface_comb_free(mac);
 	kfree(mac->macinfo.extended_capabilities);
 	kfree(mac->macinfo.extended_capabilities_mask);
+	kfree(mac->macinfo.wowlan);
 	wiphy_free(wiphy);
 	bus->mac[macid] = NULL;
 }
diff --git a/drivers/net/wireless/quantenna/qtnfmac/core.h b/drivers/net/wireless/quantenna/qtnfmac/core.h
index 214435448335..a1e338a1f055 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/core.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/core.h
@@ -40,7 +40,6 @@
 #undef pr_fmt
 #define pr_fmt(fmt)	KBUILD_MODNAME ": %s: " fmt, __func__
 
-#define QTNF_MAX_SSID_LIST_LENGTH	2
 #define QTNF_MAX_VSIE_LEN		255
 #define QTNF_MAX_INTF			8
 #define QTNF_MAX_EVENT_QUEUE_LEN	255
@@ -111,6 +110,7 @@ struct qtnf_mac_info {
 	u8 *extended_capabilities;
 	u8 *extended_capabilities_mask;
 	u8 extended_capabilities_len;
+	struct wiphy_wowlan_support *wowlan;
 };
 
 struct qtnf_chan_stats {
@@ -145,6 +145,7 @@ struct qtnf_hw_info {
 	u8 total_rx_chain;
 	char fw_version[ETHTOOL_FWVERS_LEN];
 	u32 hw_version;
+	u8 max_scan_ssids;
 };
 
 struct qtnf_vif *qtnf_mac_get_free_vif(struct qtnf_wmac *mac);
diff --git a/drivers/net/wireless/quantenna/qtnfmac/qlink.h b/drivers/net/wireless/quantenna/qtnfmac/qlink.h
index f85deda703fb..99d37e3efba6 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/qlink.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/qlink.h
@@ -69,11 +69,15 @@ struct qlink_msg_header {
  *	associated STAs due to inactivity. Inactivity timeout period is taken
  *	from QLINK_CMD_START_AP parameters.
  * @QLINK_HW_CAPAB_DFS_OFFLOAD: device implements DFS offload functionality
+ * @QLINK_HW_CAPAB_SCAN_RANDOM_MAC_ADDR: device supports MAC Address
+ *	Randomization in probe requests.
  */
 enum qlink_hw_capab {
 	QLINK_HW_CAPAB_REG_UPDATE		= BIT(0),
 	QLINK_HW_CAPAB_STA_INACT_TIMEOUT	= BIT(1),
 	QLINK_HW_CAPAB_DFS_OFFLOAD		= BIT(2),
+	QLINK_HW_CAPAB_SCAN_RANDOM_MAC_ADDR	= BIT(3),
+	QLINK_HW_CAPAB_PWR_MGMT			= BIT(4),
 };
 
 enum qlink_iface_type {
@@ -253,6 +257,8 @@ enum qlink_cmd_type {
 	QLINK_CMD_CHAN_STATS		= 0x0054,
 	QLINK_CMD_CONNECT		= 0x0060,
 	QLINK_CMD_DISCONNECT		= 0x0061,
+	QLINK_CMD_PM_SET		= 0x0062,
+	QLINK_CMD_WOWLAN_SET		= 0x0063,
 };
 
 /**
@@ -665,6 +671,54 @@ struct qlink_acl_data {
 	struct qlink_mac_address mac_addrs[0];
 } __packed;
 
+/**
+ * enum qlink_pm_mode - Power Management mode
+ *
+ * @QLINK_PM_OFF: normal mode, no power saving enabled
+ * @QLINK_PM_AUTO_STANDBY: enable auto power save mode
+ */
+enum qlink_pm_mode {
+	QLINK_PM_OFF		= 0,
+	QLINK_PM_AUTO_STANDBY	= 1,
+};
+
+/**
+ * struct qlink_cmd_pm_set - data for QLINK_CMD_PM_SET command
+ *
+ * @pm_standby timer: period of network inactivity in seconds before
+ *	putting a radio in power save mode
+ * @pm_mode: power management mode
+ */
+struct qlink_cmd_pm_set {
+	struct qlink_cmd chdr;
+	__le32 pm_standby_timer;
+	u8 pm_mode;
+} __packed;
+
+/**
+ * enum qlink_wowlan_trigger
+ *
+ * @QLINK_WOWLAN_TRIG_DISCONNECT: wakeup on disconnect
+ * @QLINK_WOWLAN_TRIG_MAGIC_PKT: wakeup on magic packet
+ * @QLINK_WOWLAN_TRIG_PATTERN_PKT: wakeup on user-defined packet
+ */
+enum qlink_wowlan_trigger {
+	QLINK_WOWLAN_TRIG_DISCONNECT	= BIT(0),
+	QLINK_WOWLAN_TRIG_MAGIC_PKT	= BIT(1),
+	QLINK_WOWLAN_TRIG_PATTERN_PKT	= BIT(2),
+};
+
+/**
+ * struct qlink_cmd_wowlan_set - data for QLINK_CMD_WOWLAN_SET command
+ *
+ * @triggers: requested bitmask of WoWLAN triggers
+ */
+struct qlink_cmd_wowlan_set {
+	struct qlink_cmd chdr;
+	__le32 triggers;
+	u8 data[0];
+} __packed;
+
 /* QLINK Command Responses messages related definitions
  */
 
@@ -1062,6 +1116,8 @@ struct qlink_event_radar {
  * @QTN_TLV_ID_STA_STATS: per-STA statistics as defined by
  *	&struct qlink_sta_stats. Valid values are marked as such in a bitmap
  *	carried by QTN_TLV_ID_STA_STATS_MAP.
+ * @QTN_TLV_ID_MAX_SCAN_SSIDS: maximum number of SSIDs the device can scan
+ *	for in any given scan.
  */
 enum qlink_tlv_id {
 	QTN_TLV_ID_FRAG_THRESH		= 0x0201,
@@ -1089,6 +1145,10 @@ enum qlink_tlv_id {
 	QTN_TLV_ID_HW_ID		= 0x0405,
 	QTN_TLV_ID_CALIBRATION_VER	= 0x0406,
 	QTN_TLV_ID_UBOOT_VER		= 0x0407,
+	QTN_TLV_ID_RANDOM_MAC_ADDR	= 0x0408,
+	QTN_TLV_ID_MAX_SCAN_SSIDS	= 0x0409,
+	QTN_TLV_ID_WOWLAN_CAPAB		= 0x0410,
+	QTN_TLV_ID_WOWLAN_PATTERN	= 0x0411,
 };
 
 struct qlink_tlv_hdr {
@@ -1360,4 +1420,49 @@ struct qlink_sta_stats {
 	u8 rsvd[1];
 };
 
+/**
+ * struct qlink_random_mac_addr - data for QTN_TLV_ID_RANDOM_MAC_ADDR TLV
+ *
+ * Specifies MAC address mask/value for generation random MAC address
+ * during scan.
+ *
+ * @mac_addr: MAC address used with randomisation
+ * @mac_addr_mask: MAC address mask used with randomisation, bits that
+ *	are 0 in the mask should be randomised, bits that are 1 should
+ *	be taken from the @mac_addr
+ */
+struct qlink_random_mac_addr {
+	u8 mac_addr[ETH_ALEN];
+	u8 mac_addr_mask[ETH_ALEN];
+} __packed;
+
+/**
+ * struct qlink_wowlan_capab_data - data for QTN_TLV_ID_WOWLAN_CAPAB TLV
+ *
+ * WoWLAN capabilities supported by cards.
+ *
+ * @version: version of WoWLAN data structure, to ensure backward
+ *	compatibility for firmwares with limited WoWLAN support
+ * @len: Total length of WoWLAN data
+ * @data: supported WoWLAN features
+ */
+struct qlink_wowlan_capab_data {
+	__le16 version;
+	__le16 len;
+	u8 data[0];
+} __packed;
+
+/**
+ * struct qlink_wowlan_support - supported WoWLAN capabilities
+ *
+ * @n_patterns: number of supported wakeup patterns
+ * @pattern_max_len: maximum length of each pattern
+ * @pattern_min_len: minimum length of each pattern
+ */
+struct qlink_wowlan_support {
+	__le32 n_patterns;
+	__le32 pattern_max_len;
+	__le32 pattern_min_len;
+} __packed;
+
 #endif /* _QTN_QLINK_H_ */
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
index c380c1f56ba6..fa2fd64084ac 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
@@ -527,24 +527,6 @@ int rt2x00mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 EXPORT_SYMBOL_GPL(rt2x00mac_set_key);
 #endif /* CONFIG_RT2X00_LIB_CRYPTO */
 
-int rt2x00mac_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-		      struct ieee80211_sta *sta)
-{
-	struct rt2x00_dev *rt2x00dev = hw->priv;
-
-	return rt2x00dev->ops->lib->sta_add(rt2x00dev, vif, sta);
-}
-EXPORT_SYMBOL_GPL(rt2x00mac_sta_add);
-
-int rt2x00mac_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-			 struct ieee80211_sta *sta)
-{
-	struct rt2x00_dev *rt2x00dev = hw->priv;
-
-	return rt2x00dev->ops->lib->sta_remove(rt2x00dev, sta);
-}
-EXPORT_SYMBOL_GPL(rt2x00mac_sta_remove);
-
 void rt2x00mac_sw_scan_start(struct ieee80211_hw *hw,
 			     struct ieee80211_vif *vif,
 			     const u8 *mac_addr)
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00pci.h b/drivers/net/wireless/ralink/rt2x00/rt2x00pci.h
index bc0ca5f58f38..283e2e607bba 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00pci.h
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00pci.h
@@ -28,12 +28,6 @@
 #include <linux/pci.h>
 
 /*
- * This variable should be used with the
- * pci_driver structure initialization.
- */
-#define PCI_DEVICE_DATA(__ops)	.driver_data = (kernel_ulong_t)(__ops)
-
-/*
  * PCI driver handlers.
  */
 int rt2x00pci_probe(struct pci_dev *pci_dev, const struct rt2x00_ops *ops);
diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c
index a7e0a17aa7e8..08c607c031bc 100644
--- a/drivers/net/wireless/ray_cs.c
+++ b/drivers/net/wireless/ray_cs.c
@@ -470,7 +470,6 @@ static inline struct rcs __iomem *rcs_base(ray_dev_t *dev)
 static int ray_init(struct net_device *dev)
 {
 	int i;
-	UCHAR *p;
 	struct ccs __iomem *pccs;
 	ray_dev_t *local = netdev_priv(dev);
 	struct pcmcia_device *link = local->finder;
@@ -513,12 +512,9 @@ static int ray_init(struct net_device *dev)
 	init_startup_params(local);
 
 	/* copy mac address to startup parameters */
-	if (parse_addr(phy_addr, local->sparm.b4.a_mac_addr)) {
-		p = local->sparm.b4.a_mac_addr;
-	} else {
+	if (!parse_addr(phy_addr, local->sparm.b4.a_mac_addr)) {
 		memcpy(&local->sparm.b4.a_mac_addr,
 		       &local->startup_res.station_addr, ADDRLEN);
-		p = local->sparm.b4.a_mac_addr;
 	}
 
 	clear_interrupt(local);	/* Clear any interrupt from the card */
diff --git a/drivers/net/wireless/realtek/rtl818x/rtl8180/rtl8225se.c b/drivers/net/wireless/realtek/rtl818x/rtl8180/rtl8225se.c
index fde89866fa8d..51e32df6120b 100644
--- a/drivers/net/wireless/realtek/rtl818x/rtl8180/rtl8225se.c
+++ b/drivers/net/wireless/realtek/rtl818x/rtl8180/rtl8225se.c
@@ -363,7 +363,7 @@ void rtl8225se_rf_init(struct ieee80211_hw *dev)
 	rtl8187se_rf_writereg(dev, 0x00, 0x0037); mdelay(11);
 	rtl8187se_rf_writereg(dev, 0x04, 0x0160); mdelay(11);
 	rtl8187se_rf_writereg(dev, 0x07, 0x0080); mdelay(11);
-	rtl8187se_rf_writereg(dev, 0x02, 0x088D); mdelay(221);
+	rtl8187se_rf_writereg(dev, 0x02, 0x088D); msleep(221);
 	rtl8187se_rf_writereg(dev, 0x00, 0x0137); mdelay(11);
 	rtl8187se_rf_writereg(dev, 0x07, 0x0000); mdelay(1);
 	rtl8187se_rf_writereg(dev, 0x07, 0x0180); mdelay(1);
@@ -386,7 +386,7 @@ void rtl8225se_rf_init(struct ieee80211_hw *dev)
 	rtl8187se_rf_writereg(dev, 0x00, 0x00BF); mdelay(1);
 	rtl8187se_rf_writereg(dev, 0x0D, 0x08DF); mdelay(1);
 	rtl8187se_rf_writereg(dev, 0x02, 0x004D); mdelay(1);
-	rtl8187se_rf_writereg(dev, 0x04, 0x0975); mdelay(31);
+	rtl8187se_rf_writereg(dev, 0x04, 0x0975); msleep(31);
 	rtl8187se_rf_writereg(dev, 0x00, 0x0197); mdelay(1);
 	rtl8187se_rf_writereg(dev, 0x05, 0x05AB); mdelay(1);
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c
index 54c9f6ab0c8c..f4122c8fdd97 100644
--- a/drivers/net/wireless/realtek/rtlwifi/base.c
+++ b/drivers/net/wireless/realtek/rtlwifi/base.c
@@ -1907,7 +1907,7 @@ void rtl_rx_ampdu_apply(struct rtl_priv *rtlpriv)
 		 reject_agg, ctrl_agg_size, agg_size);
 
 	rtlpriv->hw->max_rx_aggregation_subframes =
-		(ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF);
+		(ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF_HT);
 }
 EXPORT_SYMBOL(rtl_rx_ampdu_apply);
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c
index df3facc8e5a4..6597f7cb3411 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c
@@ -2818,23 +2818,11 @@ static void btc8723b2ant_action_sco(struct btc_coexist *btcoexist)
 
 	/* sw mechanism */
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, true, true,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, true, true,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, true, true,
+					  false, false);
 	} else {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, false, true,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, false, true,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, false, true,
+					  false, false);
 	}
 }
 
@@ -2949,23 +2937,11 @@ static void btc8723b2ant_action_a2dp(struct btc_coexist *btcoexist)
 	/* sw mechanism */
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, true, false,
+					  false, false);
 	} else {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, false, false,
+					  false, false);
 	}
 }
 
@@ -3008,23 +2984,11 @@ static void btc8723b2ant_action_a2dp_pan_hs(struct btc_coexist *btcoexist)
 	/* sw mechanism */
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, true, false,
+					  false, false);
 	} else {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, false, false,
+					  false, false);
 	}
 }
 
@@ -3071,23 +3035,11 @@ static void btc8723b2ant_action_pan_edr(struct btc_coexist *btcoexist)
 	/* sw mechanism */
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, true, false,
+					  false, false);
 	} else {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, false, false,
+					  false, false);
 	}
 }
 
@@ -3121,23 +3073,11 @@ static void btc8723b2ant_action_pan_hs(struct btc_coexist *btcoexist)
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, true, false,
+					  false, false);
 	} else {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, false, false,
+					  false, false);
 	}
 }
 
@@ -3189,23 +3129,11 @@ static void btc8723b2ant_action_pan_edr_a2dp(struct btc_coexist *btcoexist)
 
 	/* sw mechanism	*/
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, true, false,
+					  false, false);
 	} else {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, false, false,
+					  false, false);
 	}
 }
 
@@ -3264,23 +3192,11 @@ static void btc8723b2ant_action_pan_edr_hid(struct btc_coexist *btcoexist)
 
 	/* sw mechanism */
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, true, true,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, true, true,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, true, true,
+					  false, false);
 	} else {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, false, true,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, false, true,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, false, true,
+					  false, false);
 	}
 }
 
@@ -3336,23 +3252,11 @@ static void btc8723b2ant_action_hid_a2dp_pan_edr(struct btc_coexist *btcoexist)
 
 	/* sw mechanism */
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, true, true,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, true, true,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, true, true,
+					  false, false);
 	} else {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, false, true,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, false, true,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, false, true,
+					  false, false);
 	}
 }
 
@@ -3436,23 +3340,11 @@ static void btc8723b2ant_action_hid_a2dp(struct btc_coexist *btcoexist)
 
 	/* sw mechanism */
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, true, true,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, true, true,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, true, true,
+					  false, false);
 	} else {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, false, true,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, false, true,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, false, true,
+					  false, false);
 	}
 }
 
diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c
index 9935bd09db1f..51e4e92d95a0 100644
--- a/drivers/net/wireless/rndis_wlan.c
+++ b/drivers/net/wireless/rndis_wlan.c
@@ -2480,7 +2480,7 @@ static void rndis_fill_station_info(struct usbnet *usbdev,
 	ret = rndis_query_oid(usbdev, RNDIS_OID_GEN_LINK_SPEED, &linkspeed, &len);
 	if (ret == 0) {
 		sinfo->txrate.legacy = le32_to_cpu(linkspeed) / 1000;
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 	}
 
 	len = sizeof(rssi);
@@ -2488,7 +2488,7 @@ static void rndis_fill_station_info(struct usbnet *usbdev,
 			      &rssi, &len);
 	if (ret == 0) {
 		sinfo->signal = level_to_qual(le32_to_cpu(rssi));
-		sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 	}
 }
 
@@ -2928,6 +2928,8 @@ static void rndis_wlan_auth_indication(struct usbnet *usbdev,
 
 	while (buflen >= sizeof(*auth_req)) {
 		auth_req = (void *)buf;
+		if (buflen < le32_to_cpu(auth_req->length))
+			return;
 		type = "unknown";
 		flags = le32_to_cpu(auth_req->flags);
 		pairwise_error = false;
diff --git a/drivers/net/wireless/rsi/rsi_91x_hal.c b/drivers/net/wireless/rsi/rsi_91x_hal.c
index 0761e61591bd..01edf960ff3c 100644
--- a/drivers/net/wireless/rsi/rsi_91x_hal.c
+++ b/drivers/net/wireless/rsi/rsi_91x_hal.c
@@ -26,6 +26,9 @@ static struct ta_metadata metadata_flash_content[] = {
 	{"flash_content", 0x00010000},
 	{"rsi/rs9113_wlan_qspi.rps", 0x00010000},
 	{"rsi/rs9113_wlan_bt_dual_mode.rps", 0x00010000},
+	{"flash_content", 0x00010000},
+	{"rsi/rs9113_ap_bt_dual_mode.rps", 0x00010000},
+
 };
 
 int rsi_send_pkt_to_bus(struct rsi_common *common, struct sk_buff *skb)
@@ -54,7 +57,6 @@ int rsi_prepare_mgmt_desc(struct rsi_common *common, struct sk_buff *skb)
 	struct ieee80211_vif *vif;
 	struct rsi_mgmt_desc *mgmt_desc;
 	struct skb_info *tx_params;
-	struct ieee80211_bss_conf *bss = NULL;
 	struct rsi_xtended_desc *xtend_desc = NULL;
 	u8 header_size;
 	u32 dword_align_bytes = 0;
@@ -88,7 +90,6 @@ int rsi_prepare_mgmt_desc(struct rsi_common *common, struct sk_buff *skb)
 
 	tx_params->internal_hdr_size = header_size;
 	memset(&skb->data[0], 0, header_size);
-	bss = &vif->bss_conf;
 	wh = (struct ieee80211_hdr *)&skb->data[header_size];
 
 	mgmt_desc = (struct rsi_mgmt_desc *)skb->data;
@@ -145,7 +146,6 @@ int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb)
 	struct ieee80211_hdr *wh = NULL;
 	struct ieee80211_tx_info *info;
 	struct skb_info *tx_params;
-	struct ieee80211_bss_conf *bss;
 	struct rsi_data_desc *data_desc;
 	struct rsi_xtended_desc *xtend_desc;
 	u8 ieee80211_size = MIN_802_11_HDR_LEN;
@@ -156,7 +156,6 @@ int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb)
 
 	info = IEEE80211_SKB_CB(skb);
 	vif = info->control.vif;
-	bss = &vif->bss_conf;
 	tx_params = (struct skb_info *)info->driver_data;
 
 	header_size = FRAME_DESC_SZ + sizeof(struct rsi_xtended_desc);
@@ -246,7 +245,7 @@ int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb)
 		}
 	}
 
-	data_desc->mac_flags = cpu_to_le16(seq_num & 0xfff);
+	data_desc->mac_flags |= cpu_to_le16(seq_num & 0xfff);
 	data_desc->qid_tid = ((skb->priority & 0xf) |
 			      ((tx_params->tid & 0xf) << 4));
 	data_desc->sta_id = tx_params->sta_id;
@@ -285,7 +284,6 @@ int rsi_send_data_pkt(struct rsi_common *common, struct sk_buff *skb)
 	struct ieee80211_tx_info *info;
 	struct skb_info *tx_params;
 	struct ieee80211_bss_conf *bss;
-	struct ieee80211_hdr *wh;
 	int status = -EINVAL;
 	u8 header_size;
 
@@ -301,7 +299,6 @@ int rsi_send_data_pkt(struct rsi_common *common, struct sk_buff *skb)
 	bss = &vif->bss_conf;
 	tx_params = (struct skb_info *)info->driver_data;
 	header_size = tx_params->internal_hdr_size;
-	wh = (struct ieee80211_hdr *)&skb->data[header_size];
 
 	if (((vif->type == NL80211_IFTYPE_STATION) ||
 	     (vif->type == NL80211_IFTYPE_P2P_CLIENT)) &&
@@ -744,13 +741,11 @@ static int ping_pong_write(struct rsi_hw *adapter, u8 cmd, u8 *addr, u32 size)
 static int auto_fw_upgrade(struct rsi_hw *adapter, u8 *flash_content,
 			   u32 content_size)
 {
-	u8 cmd, *temp_flash_content;
+	u8 cmd;
 	u32 temp_content_size, num_flash, index;
 	u32 flash_start_address;
 	int status;
 
-	temp_flash_content = flash_content;
-
 	if (content_size > MAX_FLASH_FILE_SIZE) {
 		rsi_dbg(ERR_ZONE,
 			"%s: Flash Content size is more than 400K %u\n",
@@ -842,7 +837,6 @@ static int rsi_load_firmware(struct rsi_hw *adapter)
 	const struct firmware *fw_entry = NULL;
 	u32 regout_val = 0, content_size;
 	u16 tmp_regout_val = 0;
-	u8 *flash_content = NULL;
 	struct ta_metadata *metadata_p;
 	int status;
 
@@ -904,28 +898,22 @@ static int rsi_load_firmware(struct rsi_hw *adapter)
 			__func__, metadata_p->name);
 		return status;
 	}
-	flash_content = kmemdup(fw_entry->data, fw_entry->size, GFP_KERNEL);
-	if (!flash_content) {
-		rsi_dbg(ERR_ZONE, "%s: Failed to copy firmware\n", __func__);
-		status = -EIO;
-		goto fail;
-	}
 	content_size = fw_entry->size;
 	rsi_dbg(INFO_ZONE, "FW Length = %d bytes\n", content_size);
 
 	/* Get the firmware version */
 	common->lmac_ver.ver.info.fw_ver[0] =
-		flash_content[LMAC_VER_OFFSET] & 0xFF;
+		fw_entry->data[LMAC_VER_OFFSET] & 0xFF;
 	common->lmac_ver.ver.info.fw_ver[1] =
-		flash_content[LMAC_VER_OFFSET + 1] & 0xFF;
-	common->lmac_ver.major = flash_content[LMAC_VER_OFFSET + 2] & 0xFF;
+		fw_entry->data[LMAC_VER_OFFSET + 1] & 0xFF;
+	common->lmac_ver.major = fw_entry->data[LMAC_VER_OFFSET + 2] & 0xFF;
 	common->lmac_ver.release_num =
-		flash_content[LMAC_VER_OFFSET + 3] & 0xFF;
-	common->lmac_ver.minor = flash_content[LMAC_VER_OFFSET + 4] & 0xFF;
+		fw_entry->data[LMAC_VER_OFFSET + 3] & 0xFF;
+	common->lmac_ver.minor = fw_entry->data[LMAC_VER_OFFSET + 4] & 0xFF;
 	common->lmac_ver.patch_num = 0;
 	rsi_print_version(common);
 
-	status = bl_write_header(adapter, flash_content, content_size);
+	status = bl_write_header(adapter, (u8 *)fw_entry->data, content_size);
 	if (status) {
 		rsi_dbg(ERR_ZONE,
 			"%s: RPS Image header loading failed\n",
@@ -967,7 +955,7 @@ fw_upgrade:
 
 	rsi_dbg(INFO_ZONE, "Burn Command Pass.. Upgrading the firmware\n");
 
-	status = auto_fw_upgrade(adapter, flash_content, content_size);
+	status = auto_fw_upgrade(adapter, (u8 *)fw_entry->data, content_size);
 	if (status == 0) {
 		rsi_dbg(ERR_ZONE, "Firmware upgradation Done\n");
 		goto load_image_cmd;
@@ -981,13 +969,11 @@ fw_upgrade:
 
 success:
 	rsi_dbg(ERR_ZONE, "***** Firmware Loading successful *****\n");
-	kfree(flash_content);
 	release_firmware(fw_entry);
 	return 0;
 
 fail:
 	rsi_dbg(ERR_ZONE, "##### Firmware loading failed #####\n");
-	kfree(flash_content);
 	release_firmware(fw_entry);
 	return status;
 }
diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
index 2ca7464b7fa3..4e510cbe0a89 100644
--- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c
+++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
@@ -416,7 +416,8 @@ static int rsi_mac80211_add_interface(struct ieee80211_hw *hw,
 
 	/* Get free vap index */
 	for (i = 0; i < RSI_MAX_VIFS; i++) {
-		if (!adapter->vifs[i]) {
+		if (!adapter->vifs[i] ||
+		    !memcmp(vif->addr, adapter->vifs[i]->addr, ETH_ALEN)) {
 			vap_idx = i;
 			break;
 		}
diff --git a/drivers/net/wireless/rsi/rsi_91x_main.c b/drivers/net/wireless/rsi/rsi_91x_main.c
index 1485a0c89df2..01d99ed985ee 100644
--- a/drivers/net/wireless/rsi/rsi_91x_main.c
+++ b/drivers/net/wireless/rsi/rsi_91x_main.c
@@ -122,7 +122,6 @@ static struct sk_buff *rsi_prepare_skb(struct rsi_common *common,
 				       u8 extended_desc)
 {
 	struct ieee80211_tx_info *info;
-	struct skb_info *rx_params;
 	struct sk_buff *skb = NULL;
 	u8 payload_offset;
 	struct ieee80211_vif *vif;
@@ -149,10 +148,6 @@ static struct sk_buff *rsi_prepare_skb(struct rsi_common *common,
 	vif = rsi_get_vif(common->priv, wh->addr1);
 
 	info = IEEE80211_SKB_CB(skb);
-	rx_params = (struct skb_info *)info->driver_data;
-	rx_params->rssi = rsi_get_rssi(buffer);
-	rx_params->channel = rsi_get_connected_channel(vif);
-
 	return skb;
 }
 
@@ -336,7 +331,6 @@ struct rsi_hw *rsi_91x_init(u16 oper_mode)
 	spin_lock_init(&adapter->ps_lock);
 	timer_setup(&common->roc_timer, rsi_roc_timeout, 0);
 	init_completion(&common->wlan_init_completion);
-	common->init_done = true;
 	adapter->device_model = RSI_DEV_9113;
 	common->oper_mode = oper_mode;
 
@@ -374,6 +368,7 @@ struct rsi_hw *rsi_91x_init(u16 oper_mode)
 	}
 #endif
 
+	common->init_done = true;
 	return adapter;
 
 err:
diff --git a/drivers/net/wireless/rsi/rsi_91x_mgmt.c b/drivers/net/wireless/rsi/rsi_91x_mgmt.c
index d0e5937cad6d..1095df7d9573 100644
--- a/drivers/net/wireless/rsi/rsi_91x_mgmt.c
+++ b/drivers/net/wireless/rsi/rsi_91x_mgmt.c
@@ -334,20 +334,17 @@ static int rsi_load_radio_caps(struct rsi_common *common)
 			struct ieee80211_conf *conf = &hw->conf;
 
 			if (conf_is_ht40_plus(conf)) {
-				radio_caps->radio_cfg_info =
-					RSI_CMDDESC_LOWER_20_ENABLE;
-				radio_caps->radio_info =
-					RSI_CMDDESC_LOWER_20_ENABLE;
+				radio_caps->ppe_ack_rate =
+					cpu_to_le16(LOWER_20_ENABLE |
+						    (LOWER_20_ENABLE >> 12));
 			} else if (conf_is_ht40_minus(conf)) {
-				radio_caps->radio_cfg_info =
-					RSI_CMDDESC_UPPER_20_ENABLE;
-				radio_caps->radio_info =
-					RSI_CMDDESC_UPPER_20_ENABLE;
+				radio_caps->ppe_ack_rate =
+					cpu_to_le16(UPPER_20_ENABLE |
+						    (UPPER_20_ENABLE >> 12));
 			} else {
-				radio_caps->radio_cfg_info =
-					RSI_CMDDESC_40MHZ;
-				radio_caps->radio_info =
-					RSI_CMDDESC_FULL_40_ENABLE;
+				radio_caps->ppe_ack_rate =
+					cpu_to_le16((BW_40MHZ << 12) |
+						    FULL40M_ENABLE);
 			}
 		}
 	}
@@ -749,7 +746,7 @@ int rsi_hal_load_key(struct rsi_common *common,
 			key_descriptor |= RSI_CIPHER_TKIP;
 	}
 	key_descriptor |= RSI_PROTECT_DATA_FRAMES;
-	key_descriptor |= ((key_id << RSI_KEY_ID_OFFSET) & RSI_KEY_ID_MASK);
+	key_descriptor |= (key_id << RSI_KEY_ID_OFFSET);
 
 	rsi_set_len_qno(&set_key->desc_dword0.len_qno,
 			(frame_len - FRAME_DESC_SZ), RSI_WIFI_MGMT_Q);
diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio.c b/drivers/net/wireless/rsi/rsi_91x_sdio.c
index 416981d99229..5733e440ecaf 100644
--- a/drivers/net/wireless/rsi/rsi_91x_sdio.c
+++ b/drivers/net/wireless/rsi/rsi_91x_sdio.c
@@ -1394,10 +1394,7 @@ static const struct dev_pm_ops rsi_pm_ops = {
 #endif
 
 static const struct sdio_device_id rsi_dev_table[] =  {
-	{ SDIO_DEVICE(0x303, 0x100) },
-	{ SDIO_DEVICE(0x041B, 0x0301) },
-	{ SDIO_DEVICE(0x041B, 0x0201) },
-	{ SDIO_DEVICE(0x041B, 0x9330) },
+	{ SDIO_DEVICE(RSI_SDIO_VID_9113, RSI_SDIO_PID_9113) },
 	{ /* Blank */},
 };
 
diff --git a/drivers/net/wireless/rsi/rsi_91x_usb.c b/drivers/net/wireless/rsi/rsi_91x_usb.c
index 6ce6b754df12..c0a163e40402 100644
--- a/drivers/net/wireless/rsi/rsi_91x_usb.c
+++ b/drivers/net/wireless/rsi/rsi_91x_usb.c
@@ -835,11 +835,7 @@ static int rsi_resume(struct usb_interface *intf)
 #endif
 
 static const struct usb_device_id rsi_dev_table[] = {
-	{ USB_DEVICE(0x0303, 0x0100) },
-	{ USB_DEVICE(0x041B, 0x0301) },
-	{ USB_DEVICE(0x041B, 0x0201) },
-	{ USB_DEVICE(0x041B, 0x9330) },
-	{ USB_DEVICE(0x1618, 0x9113) },
+	{ USB_DEVICE(RSI_USB_VID_9113, RSI_USB_PID_9113) },
 	{ /* Blank */},
 };
 
diff --git a/drivers/net/wireless/rsi/rsi_mgmt.h b/drivers/net/wireless/rsi/rsi_mgmt.h
index 14620935c925..359fbdf85739 100644
--- a/drivers/net/wireless/rsi/rsi_mgmt.h
+++ b/drivers/net/wireless/rsi/rsi_mgmt.h
@@ -22,7 +22,7 @@
 #include "rsi_main.h"
 
 #define MAX_MGMT_PKT_SIZE               512
-#define RSI_NEEDED_HEADROOM             80
+#define RSI_NEEDED_HEADROOM             84
 #define RSI_RCV_BUFFER_LEN              2000
 
 #define RSI_11B_MODE                    0
diff --git a/drivers/net/wireless/rsi/rsi_sdio.h b/drivers/net/wireless/rsi/rsi_sdio.h
index 353dbdf31e75..66dcd2ec9051 100644
--- a/drivers/net/wireless/rsi/rsi_sdio.h
+++ b/drivers/net/wireless/rsi/rsi_sdio.h
@@ -28,6 +28,9 @@
 #include <linux/mmc/sdio_ids.h>
 #include "rsi_main.h"
 
+#define RSI_SDIO_VID_9113    0x041B
+#define RSI_SDIO_PID_9113    0x9330
+
 enum sdio_interrupt_type {
 	BUFFER_FULL         = 0x0,
 	BUFFER_AVAILABLE    = 0x2,
diff --git a/drivers/net/wireless/rsi/rsi_usb.h b/drivers/net/wireless/rsi/rsi_usb.h
index b6fe79f0a513..5b2eddd1a2ee 100644
--- a/drivers/net/wireless/rsi/rsi_usb.h
+++ b/drivers/net/wireless/rsi/rsi_usb.h
@@ -22,6 +22,9 @@
 #include "rsi_main.h"
 #include "rsi_common.h"
 
+#define RSI_USB_VID_9113	0x1618
+#define RSI_USB_PID_9113	0x9113
+
 #define USB_INTERNAL_REG_1           0x25000
 #define RSI_USB_READY_MAGIC_NUM      0xab
 #define FW_STATUS_REG                0x41050012
diff --git a/drivers/net/wireless/ti/wl18xx/debugfs.c b/drivers/net/wireless/ti/wl18xx/debugfs.c
index 86ccf84ea0c6..597e934c4630 100644
--- a/drivers/net/wireless/ti/wl18xx/debugfs.c
+++ b/drivers/net/wireless/ti/wl18xx/debugfs.c
@@ -20,6 +20,8 @@
  *
  */
 
+#include <linux/pm_runtime.h>
+
 #include "../wlcore/debugfs.h"
 #include "../wlcore/wlcore.h"
 #include "../wlcore/debug.h"
@@ -276,15 +278,18 @@ static ssize_t radar_detection_write(struct file *file,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl18xx_cmd_radar_detection_debug(wl, channel);
 	if (ret < 0)
 		count = ret;
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
@@ -315,15 +320,18 @@ static ssize_t dynamic_fw_traces_write(struct file *file,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl18xx_acx_dynamic_fw_traces(wl);
 	if (ret < 0)
 		count = ret;
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
@@ -374,9 +382,11 @@ static ssize_t radar_debug_mode_write(struct file *file,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl12xx_for_each_wlvif_ap(wl, wlvif) {
 		wlcore_cmd_generic_cfg(wl, wlvif,
@@ -384,7 +394,8 @@ static ssize_t radar_debug_mode_write(struct file *file,
 				       wl->radar_debug_mode, 0);
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
diff --git a/drivers/net/wireless/ti/wlcore/acx.c b/drivers/net/wireless/ti/wlcore/acx.c
index 3ca9167d6146..7c83915a7c5e 100644
--- a/drivers/net/wireless/ti/wlcore/acx.c
+++ b/drivers/net/wireless/ti/wlcore/acx.c
@@ -31,7 +31,6 @@
 #include "wlcore.h"
 #include "debug.h"
 #include "wl12xx_80211.h"
-#include "ps.h"
 #include "hw_ops.h"
 
 int wl1271_acx_wake_up_conditions(struct wl1271 *wl, struct wl12xx_vif *wlvif,
diff --git a/drivers/net/wireless/ti/wlcore/cmd.c b/drivers/net/wireless/ti/wlcore/cmd.c
index 761cf8573a80..903968735a74 100644
--- a/drivers/net/wireless/ti/wlcore/cmd.c
+++ b/drivers/net/wireless/ti/wlcore/cmd.c
@@ -23,6 +23,7 @@
 
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/spi/spi.h>
 #include <linux/etherdevice.h>
 #include <linux/ieee80211.h>
@@ -191,6 +192,12 @@ int wlcore_cmd_wait_for_event_or_timeout(struct wl1271 *wl,
 
 	timeout_time = jiffies + msecs_to_jiffies(WL1271_EVENT_TIMEOUT);
 
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
+		goto free_vector;
+	}
+
 	do {
 		if (time_after(jiffies, timeout_time)) {
 			wl1271_debug(DEBUG_CMD, "timeout waiting for event %d",
@@ -222,6 +229,9 @@ int wlcore_cmd_wait_for_event_or_timeout(struct wl1271 *wl,
 	} while (!event);
 
 out:
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
+free_vector:
 	kfree(events_vector);
 	return ret;
 }
diff --git a/drivers/net/wireless/ti/wlcore/debugfs.c b/drivers/net/wireless/ti/wlcore/debugfs.c
index a2cb408be8aa..aeb74e74698e 100644
--- a/drivers/net/wireless/ti/wlcore/debugfs.c
+++ b/drivers/net/wireless/ti/wlcore/debugfs.c
@@ -26,6 +26,7 @@
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/pm_runtime.h>
 
 #include "wlcore.h"
 #include "debug.h"
@@ -65,9 +66,11 @@ void wl1271_debugfs_update_stats(struct wl1271 *wl)
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	if (!wl->plt &&
 	    time_after(jiffies, wl->stats.fw_stats_update +
@@ -76,7 +79,8 @@ void wl1271_debugfs_update_stats(struct wl1271 *wl)
 		wl->stats.fw_stats_update = jiffies;
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -118,14 +122,18 @@ static void chip_op_handler(struct wl1271 *wl, unsigned long value,
 		return;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
+
 		return;
+	}
 
 	chip_op = arg;
 	chip_op(wl);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 }
 
 
@@ -292,9 +300,11 @@ static ssize_t dynamic_ps_timeout_write(struct file *file,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	/* In case we're already in PSM, trigger it again to set new timeout
 	 * immediately without waiting for re-association
@@ -305,7 +315,8 @@ static ssize_t dynamic_ps_timeout_write(struct file *file,
 			wl1271_ps_set_mode(wl, wlvif, STATION_AUTO_PS_MODE);
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -359,9 +370,11 @@ static ssize_t forced_ps_write(struct file *file,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	/* In case we're already in PSM, trigger it again to switch mode
 	 * immediately without waiting for re-association
@@ -374,7 +387,8 @@ static ssize_t forced_ps_write(struct file *file,
 			wl1271_ps_set_mode(wl, wlvif, ps_mode);
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -838,15 +852,18 @@ static ssize_t rx_streaming_interval_write(struct file *file,
 
 	wl->conf.rx_streaming.interval = value;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl12xx_for_each_wlvif_sta(wl, wlvif) {
 		wl1271_recalc_rx_streaming(wl, wlvif);
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
@@ -893,15 +910,18 @@ static ssize_t rx_streaming_always_write(struct file *file,
 
 	wl->conf.rx_streaming.always = value;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl12xx_for_each_wlvif_sta(wl, wlvif) {
 		wl1271_recalc_rx_streaming(wl, wlvif);
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
@@ -940,15 +960,18 @@ static ssize_t beacon_filtering_write(struct file *file,
 
 	mutex_lock(&wl->mutex);
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl12xx_for_each_wlvif(wl, wlvif) {
 		ret = wl1271_acx_beacon_filter_opt(wl, wlvif, !!value);
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
@@ -1019,16 +1042,19 @@ static ssize_t sleep_auth_write(struct file *file,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl1271_acx_sleep_auth(wl, value);
 	if (ret < 0)
 		goto out_sleep;
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
@@ -1083,7 +1109,7 @@ static ssize_t dev_mem_read(struct file *file,
 	 * Don't fail if elp_wakeup returns an error, so the device's memory
 	 * could be read even if the FW crashed
 	 */
-	wl1271_ps_elp_wakeup(wl);
+	pm_runtime_get_sync(wl->dev);
 
 	/* store current partition and switch partition */
 	memcpy(&old_part, &wl->curr_part, sizeof(old_part));
@@ -1102,7 +1128,8 @@ read_err:
 		goto part_err;
 
 part_err:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 skip_read:
 	mutex_unlock(&wl->mutex);
@@ -1164,7 +1191,7 @@ static ssize_t dev_mem_write(struct file *file, const char __user *user_buf,
 	 * Don't fail if elp_wakeup returns an error, so the device's memory
 	 * could be read even if the FW crashed
 	 */
-	wl1271_ps_elp_wakeup(wl);
+	pm_runtime_get_sync(wl->dev);
 
 	/* store current partition and switch partition */
 	memcpy(&old_part, &wl->curr_part, sizeof(old_part));
@@ -1183,7 +1210,8 @@ write_err:
 		goto part_err;
 
 part_err:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 skip_write:
 	mutex_unlock(&wl->mutex);
@@ -1247,8 +1275,9 @@ static ssize_t fw_logger_write(struct file *file,
 	}
 
 	mutex_lock(&wl->mutex);
-	ret = wl1271_ps_elp_wakeup(wl);
+	ret = pm_runtime_get_sync(wl->dev);
 	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		count = ret;
 		goto out;
 	}
@@ -1257,7 +1286,8 @@ static ssize_t fw_logger_write(struct file *file,
 
 	ret = wl12xx_cmd_config_fwlog(wl);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 3a51ab116e79..89b0d0fade9f 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -26,6 +26,7 @@
 #include <linux/vmalloc.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
+#include <linux/pm_runtime.h>
 
 #include "wlcore.h"
 #include "debug.h"
@@ -43,6 +44,7 @@
 
 #define WL1271_BOOT_RETRIES 3
 #define WL1271_SUSPEND_SLEEP 100
+#define WL1271_WAKEUP_TIMEOUT 500
 
 static char *fwlog_param;
 static int fwlog_mem_blocks = -1;
@@ -153,9 +155,11 @@ static void wl1271_rx_streaming_enable_work(struct work_struct *work)
 	if (!wl->conf.rx_streaming.interval)
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl1271_set_rx_streaming(wl, wlvif, true);
 	if (ret < 0)
@@ -166,7 +170,8 @@ static void wl1271_rx_streaming_enable_work(struct work_struct *work)
 		  jiffies + msecs_to_jiffies(wl->conf.rx_streaming.duration));
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -183,16 +188,19 @@ static void wl1271_rx_streaming_disable_work(struct work_struct *work)
 	if (!test_bit(WLVIF_FLAG_RX_STREAMING_STARTED, &wlvif->flags))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl1271_set_rx_streaming(wl, wlvif, false);
 	if (ret)
 		goto out_sleep;
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -229,9 +237,11 @@ static void wlcore_rc_update_work(struct work_struct *work)
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	if (ieee80211_vif_is_mesh(vif)) {
 		ret = wl1271_acx_set_ht_capabilities(wl, &wlvif->rc_ht_cap,
@@ -243,7 +253,8 @@ static void wlcore_rc_update_work(struct work_struct *work)
 	}
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -539,15 +550,16 @@ static int wlcore_irq_locked(struct wl1271 *wl)
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	while (!done && loopcount--) {
 		/*
 		 * In order to avoid a race with the hardirq, clear the flag
-		 * before acknowledging the chip. Since the mutex is held,
-		 * wl1271_ps_elp_wakeup cannot be called concurrently.
+		 * before acknowledging the chip.
 		 */
 		clear_bit(WL1271_FLAG_IRQ_RUNNING, &wl->flags);
 		smp_mb__after_atomic();
@@ -641,7 +653,8 @@ static int wlcore_irq_locked(struct wl1271 *wl)
 			wl1271_debug(DEBUG_IRQ, "WL1271_ACX_INTR_HW_AVAILABLE");
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	return ret;
@@ -796,8 +809,6 @@ void wl12xx_queue_recovery_work(struct wl1271 *wl)
 
 		wl->state = WLCORE_STATE_RESTARTING;
 		set_bit(WL1271_FLAG_RECOVERY_IN_PROGRESS, &wl->flags);
-		wl1271_ps_elp_wakeup(wl);
-		wlcore_disable_interrupts_nosync(wl);
 		ieee80211_queue_work(wl->hw, &wl->recovery_work);
 	}
 }
@@ -819,6 +830,7 @@ size_t wl12xx_copy_fwlog(struct wl1271 *wl, u8 *memblock, size_t maxlen)
 static void wl12xx_read_fwlog_panic(struct wl1271 *wl)
 {
 	u32 end_of_log = 0;
+	int error;
 
 	if (wl->quirks & WLCORE_QUIRK_FWLOG_NOT_IMPLEMENTED)
 		return;
@@ -830,8 +842,11 @@ static void wl12xx_read_fwlog_panic(struct wl1271 *wl)
 	 * Do not send a stop fwlog command if the fw is hanged or if
 	 * dbgpins are used (due to some fw bug).
 	 */
-	if (wl1271_ps_elp_wakeup(wl))
+	error = pm_runtime_get_sync(wl->dev);
+	if (error < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		return;
+	}
 	if (!wl->watchdog_recovery &&
 	    wl->conf.fwlog.output != WL12XX_FWLOG_OUTPUT_DBG_PINS)
 		wl12xx_cmd_stop_fwlog(wl);
@@ -919,12 +934,20 @@ static void wl1271_recovery_work(struct work_struct *work)
 		container_of(work, struct wl1271, recovery_work);
 	struct wl12xx_vif *wlvif;
 	struct ieee80211_vif *vif;
+	int error;
 
 	mutex_lock(&wl->mutex);
 
 	if (wl->state == WLCORE_STATE_OFF || wl->plt)
 		goto out_unlock;
 
+	error = pm_runtime_get_sync(wl->dev);
+	if (error < 0) {
+		wl1271_warning("Enable for recovery failed");
+		pm_runtime_put_noidle(wl->dev);
+	}
+	wlcore_disable_interrupts_nosync(wl);
+
 	if (!test_bit(WL1271_FLAG_INTENDED_FW_RECOVERY, &wl->flags)) {
 		if (wl->conf.fwlog.output == WL12XX_FWLOG_OUTPUT_HOST)
 			wl12xx_read_fwlog_panic(wl);
@@ -958,6 +981,8 @@ static void wl1271_recovery_work(struct work_struct *work)
 	}
 
 	wlcore_op_stop_locked(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 	ieee80211_restart_hw(wl->hw);
 
@@ -978,24 +1003,6 @@ static int wlcore_fw_wakeup(struct wl1271 *wl)
 	return wlcore_raw_write32(wl, HW_ACCESS_ELP_CTRL_REG, ELPCTRL_WAKE_UP);
 }
 
-static int wlcore_fw_sleep(struct wl1271 *wl)
-{
-	int ret;
-
-	mutex_lock(&wl->mutex);
-	ret = wlcore_raw_write32(wl, HW_ACCESS_ELP_CTRL_REG, ELPCTRL_SLEEP);
-	if (ret < 0) {
-		wl12xx_queue_recovery_work(wl);
-		goto out;
-	}
-	set_bit(WL1271_FLAG_IN_ELP, &wl->flags);
-out:
-	mutex_unlock(&wl->mutex);
-	mdelay(WL1271_SUSPEND_SLEEP);
-
-	return 0;
-}
-
 static int wl1271_setup(struct wl1271 *wl)
 {
 	wl->raw_fw_status = kzalloc(wl->fw_status_len, GFP_KERNEL);
@@ -1184,7 +1191,6 @@ int wl1271_plt_stop(struct wl1271 *wl)
 	wl1271_flush_deferred_work(wl);
 	cancel_work_sync(&wl->netstack_work);
 	cancel_work_sync(&wl->recovery_work);
-	cancel_delayed_work_sync(&wl->elp_work);
 	cancel_delayed_work_sync(&wl->tx_watchdog_work);
 
 	mutex_lock(&wl->mutex);
@@ -1719,6 +1725,7 @@ static int __maybe_unused wl1271_op_suspend(struct ieee80211_hw *hw,
 {
 	struct wl1271 *wl = hw->priv;
 	struct wl12xx_vif *wlvif;
+	unsigned long flags;
 	int ret;
 
 	wl1271_debug(DEBUG_MAC80211, "mac80211 suspend wow=%d", !!wow);
@@ -1734,8 +1741,9 @@ static int __maybe_unused wl1271_op_suspend(struct ieee80211_hw *hw,
 
 	mutex_lock(&wl->mutex);
 
-	ret = wl1271_ps_elp_wakeup(wl);
+	ret = pm_runtime_get_sync(wl->dev);
 	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		mutex_unlock(&wl->mutex);
 		return ret;
 	}
@@ -1765,6 +1773,7 @@ static int __maybe_unused wl1271_op_suspend(struct ieee80211_hw *hw,
 		goto out_sleep;
 
 out_sleep:
+	pm_runtime_put_noidle(wl->dev);
 	mutex_unlock(&wl->mutex);
 
 	if (ret < 0) {
@@ -1775,21 +1784,7 @@ out_sleep:
 	/* flush any remaining work */
 	wl1271_debug(DEBUG_MAC80211, "flushing remaining works");
 
-	/*
-	 * disable and re-enable interrupts in order to flush
-	 * the threaded_irq
-	 */
-	wlcore_disable_interrupts(wl);
-
-	/*
-	 * set suspended flag to avoid triggering a new threaded_irq
-	 * work. no need for spinlock as interrupts are disabled.
-	 */
-	set_bit(WL1271_FLAG_SUSPENDED, &wl->flags);
-
-	wlcore_enable_interrupts(wl);
 	flush_work(&wl->tx_work);
-	flush_delayed_work(&wl->elp_work);
 
 	/*
 	 * Cancel the watchdog even if above tx_flush failed. We will detect
@@ -1798,15 +1793,14 @@ out_sleep:
 	cancel_delayed_work(&wl->tx_watchdog_work);
 
 	/*
-	 * Use an immediate call for allowing the firmware to go into power
-	 * save during suspend.
-	 * Using a workque for this last write was only hapenning on resume
-	 * leaving the firmware with power save disabled during suspend,
-	 * while consuming full power during wowlan suspend.
+	 * set suspended flag to avoid triggering a new threaded_irq
+	 * work.
 	 */
-	wlcore_fw_sleep(wl);
+	spin_lock_irqsave(&wl->wl_lock, flags);
+	set_bit(WL1271_FLAG_SUSPENDED, &wl->flags);
+	spin_unlock_irqrestore(&wl->wl_lock, flags);
 
-	return 0;
+	return pm_runtime_force_suspend(wl->dev);
 }
 
 static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw)
@@ -1821,6 +1815,12 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw)
 		     wl->wow_enabled);
 	WARN_ON(!wl->wow_enabled);
 
+	ret = pm_runtime_force_resume(wl->dev);
+	if (ret < 0) {
+		wl1271_error("ELP wakeup failure!");
+		goto out_sleep;
+	}
+
 	/*
 	 * re-enable irq_work enqueuing, and call irq_work directly if
 	 * there is a pending work.
@@ -1857,9 +1857,11 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw)
 		goto out_sleep;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl12xx_for_each_wlvif(wl, wlvif) {
 		if (wlcore_is_p2p_mgmt(wlvif))
@@ -1878,7 +1880,8 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw)
 		goto out_sleep;
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	wl->wow_enabled = false;
@@ -1945,7 +1948,6 @@ static void wlcore_op_stop_locked(struct wl1271 *wl)
 	cancel_delayed_work_sync(&wl->scan_complete_work);
 	cancel_work_sync(&wl->netstack_work);
 	cancel_work_sync(&wl->tx_work);
-	cancel_delayed_work_sync(&wl->elp_work);
 	cancel_delayed_work_sync(&wl->tx_watchdog_work);
 
 	/* let's notify MAC80211 about the remaining pending TX frames */
@@ -2060,13 +2062,16 @@ static void wlcore_channel_switch_work(struct work_struct *work)
 	vif = wl12xx_wlvif_to_vif(wlvif);
 	ieee80211_chswitch_done(vif, false);
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl12xx_cmd_stop_channel_switch(wl, wlvif);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -2128,14 +2133,17 @@ static void wlcore_pending_auth_complete_work(struct work_struct *work)
 	if (!time_after(time_spare, wlvif->pending_auth_reply_time))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	/* cancel the ROC if active */
 	wlcore_update_inconn_sta(wl, wlvif, NULL, false);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -2537,9 +2545,6 @@ static int wl1271_op_add_interface(struct ieee80211_hw *hw,
 	wl12xx_get_vif_count(hw, vif, &vif_count);
 
 	mutex_lock(&wl->mutex);
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
-		goto out_unlock;
 
 	/*
 	 * in some very corner case HW recovery scenarios its possible to
@@ -2568,14 +2573,6 @@ static int wl1271_op_add_interface(struct ieee80211_hw *hw,
 	if (ret < 0)
 		goto out;
 
-	if (wl12xx_need_fw_change(wl, vif_count, true)) {
-		wl12xx_force_active_psm(wl);
-		set_bit(WL1271_FLAG_INTENDED_FW_RECOVERY, &wl->flags);
-		mutex_unlock(&wl->mutex);
-		wl1271_recovery_work(&wl->recovery_work);
-		return 0;
-	}
-
 	/*
 	 * TODO: after the nvs issue will be solved, move this block
 	 * to start(), and make sure here the driver is ON.
@@ -2592,6 +2589,24 @@ static int wl1271_op_add_interface(struct ieee80211_hw *hw,
 			goto out;
 	}
 
+	/*
+	 * Call runtime PM only after possible wl12xx_init_fw() above
+	 * is done. Otherwise we do not have interrupts enabled.
+	 */
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
+		goto out_unlock;
+	}
+
+	if (wl12xx_need_fw_change(wl, vif_count, true)) {
+		wl12xx_force_active_psm(wl);
+		set_bit(WL1271_FLAG_INTENDED_FW_RECOVERY, &wl->flags);
+		mutex_unlock(&wl->mutex);
+		wl1271_recovery_work(&wl->recovery_work);
+		return 0;
+	}
+
 	if (!wlcore_is_p2p_mgmt(wlvif)) {
 		ret = wl12xx_cmd_role_enable(wl, vif->addr,
 					     role_type, &wlvif->role_id);
@@ -2622,7 +2637,8 @@ static int wl1271_op_add_interface(struct ieee80211_hw *hw,
 	else
 		wl->sta_count++;
 out:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out_unlock:
 	mutex_unlock(&wl->mutex);
 
@@ -2677,9 +2693,11 @@ static void __wl1271_op_remove_interface(struct wl1271 *wl,
 
 	if (!test_bit(WL1271_FLAG_RECOVERY_IN_PROGRESS, &wl->flags)) {
 		/* disable active roles */
-		ret = wl1271_ps_elp_wakeup(wl);
-		if (ret < 0)
+		ret = pm_runtime_get_sync(wl->dev);
+		if (ret < 0) {
+			pm_runtime_put_noidle(wl->dev);
 			goto deinit;
+		}
 
 		if (wlvif->bss_type == BSS_TYPE_STA_BSS ||
 		    wlvif->bss_type == BSS_TYPE_IBSS) {
@@ -2697,7 +2715,8 @@ static void __wl1271_op_remove_interface(struct wl1271 *wl,
 				goto deinit;
 		}
 
-		wl1271_ps_elp_sleep(wl);
+		pm_runtime_mark_last_busy(wl->dev);
+		pm_runtime_put_autosuspend(wl->dev);
 	}
 deinit:
 	wl12xx_tx_reset_wlvif(wl, wlvif);
@@ -3121,9 +3140,11 @@ static int wl1271_op_config(struct ieee80211_hw *hw, u32 changed)
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	/* configure each interface */
 	wl12xx_for_each_wlvif(wl, wlvif) {
@@ -3133,7 +3154,8 @@ static int wl1271_op_config(struct ieee80211_hw *hw, u32 changed)
 	}
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -3202,9 +3224,11 @@ static void wl1271_op_configure_filter(struct ieee80211_hw *hw,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl12xx_for_each_wlvif(wl, wlvif) {
 		if (wlcore_is_p2p_mgmt(wlvif))
@@ -3247,7 +3271,8 @@ static void wl1271_op_configure_filter(struct ieee80211_hw *hw,
 	 */
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -3454,13 +3479,16 @@ static int wlcore_op_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 		goto out_wake_queues;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out_wake_queues;
+	}
 
 	ret = wlcore_hw_set_key(wl, cmd, vif, sta, key_conf);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out_wake_queues:
 	if (might_change_spare)
@@ -3600,9 +3628,11 @@ static void wl1271_op_set_default_key_idx(struct ieee80211_hw *hw,
 		goto out_unlock;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out_unlock;
+	}
 
 	wlvif->default_key = key_idx;
 
@@ -3616,7 +3646,8 @@ static void wl1271_op_set_default_key_idx(struct ieee80211_hw *hw,
 	}
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out_unlock:
 	mutex_unlock(&wl->mutex);
@@ -3634,7 +3665,7 @@ void wlcore_regdomain_config(struct wl1271 *wl)
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
+	ret = pm_runtime_get_sync(wl->dev);
 	if (ret < 0)
 		goto out;
 
@@ -3644,7 +3675,8 @@ void wlcore_regdomain_config(struct wl1271 *wl)
 		goto out;
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -3678,9 +3710,11 @@ static int wl1271_op_hw_scan(struct ieee80211_hw *hw,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	/* fail if there is any role in ROC */
 	if (find_first_bit(wl->roc_map, WL12XX_MAX_ROLES) < WL12XX_MAX_ROLES) {
@@ -3691,7 +3725,8 @@ static int wl1271_op_hw_scan(struct ieee80211_hw *hw,
 
 	ret = wlcore_scan(hw->priv, vif, ssid, len, req);
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -3718,9 +3753,11 @@ static void wl1271_op_cancel_hw_scan(struct ieee80211_hw *hw,
 	if (wl->scan.state == WL1271_SCAN_STATE_IDLE)
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	if (wl->scan.state != WL1271_SCAN_STATE_DONE) {
 		ret = wl->ops->scan_stop(wl, wlvif);
@@ -3741,7 +3778,8 @@ static void wl1271_op_cancel_hw_scan(struct ieee80211_hw *hw,
 	ieee80211_scan_completed(wl->hw, &info);
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -3766,9 +3804,11 @@ static int wl1271_op_sched_scan_start(struct ieee80211_hw *hw,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl->ops->sched_scan_start(wl, wlvif, req, ies);
 	if (ret < 0)
@@ -3777,7 +3817,8 @@ static int wl1271_op_sched_scan_start(struct ieee80211_hw *hw,
 	wl->sched_vif = wlvif;
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return ret;
@@ -3797,13 +3838,16 @@ static int wl1271_op_sched_scan_stop(struct ieee80211_hw *hw,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl->ops->sched_scan_stop(wl, wlvif);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -3822,15 +3866,18 @@ static int wl1271_op_set_frag_threshold(struct ieee80211_hw *hw, u32 value)
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl1271_acx_frag_threshold(wl, value);
 	if (ret < 0)
 		wl1271_warning("wl1271_op_set_frag_threshold failed: %d", ret);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -3851,16 +3898,19 @@ static int wl1271_op_set_rts_threshold(struct ieee80211_hw *hw, u32 value)
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl12xx_for_each_wlvif(wl, wlvif) {
 		ret = wl1271_acx_rts_threshold(wl, wlvif, value);
 		if (ret < 0)
 			wl1271_warning("set rts threshold failed: %d", ret);
 	}
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -4607,9 +4657,11 @@ static void wl1271_op_bss_info_changed(struct ieee80211_hw *hw,
 	if (unlikely(!test_bit(WLVIF_FLAG_INITIALIZED, &wlvif->flags)))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	if ((changed & BSS_CHANGED_TXPOWER) &&
 	    bss_conf->txpower != wlvif->power_level) {
@@ -4626,7 +4678,8 @@ static void wl1271_op_bss_info_changed(struct ieee80211_hw *hw,
 	else
 		wl1271_bss_info_changed_sta(wl, vif, bss_conf, changed);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -4665,9 +4718,11 @@ static void wlcore_op_change_chanctx(struct ieee80211_hw *hw,
 
 	mutex_lock(&wl->mutex);
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl12xx_for_each_wlvif(wl, wlvif) {
 		struct ieee80211_vif *vif = wl12xx_wlvif_to_vif(wlvif);
@@ -4690,7 +4745,8 @@ static void wlcore_op_change_chanctx(struct ieee80211_hw *hw,
 		}
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -4719,9 +4775,11 @@ static int wlcore_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 	if (unlikely(!test_bit(WLVIF_FLAG_INITIALIZED, &wlvif->flags)))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wlvif->band = ctx->def.chan->band;
 	wlvif->channel = channel;
@@ -4737,7 +4795,8 @@ static int wlcore_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 		wlvif->radar_enabled = true;
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -4768,9 +4827,11 @@ static void wlcore_op_unassign_vif_chanctx(struct ieee80211_hw *hw,
 	if (unlikely(!test_bit(WLVIF_FLAG_INITIALIZED, &wlvif->flags)))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	if (wlvif->radar_enabled) {
 		wl1271_debug(DEBUG_MAC80211, "Stop radar detection");
@@ -4778,7 +4839,8 @@ static void wlcore_op_unassign_vif_chanctx(struct ieee80211_hw *hw,
 		wlvif->radar_enabled = false;
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -4835,9 +4897,11 @@ wlcore_op_switch_vif_chanctx(struct ieee80211_hw *hw,
 
 	mutex_lock(&wl->mutex);
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	for (i = 0; i < n_vifs; i++) {
 		struct wl12xx_vif *wlvif = wl12xx_vif_to_data(vifs[i].vif);
@@ -4847,7 +4911,8 @@ wlcore_op_switch_vif_chanctx(struct ieee80211_hw *hw,
 			goto out_sleep;
 	}
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -4878,9 +4943,11 @@ static int wl1271_op_conf_tx(struct ieee80211_hw *hw,
 	if (!test_bit(WLVIF_FLAG_INITIALIZED, &wlvif->flags))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	/*
 	 * the txop is confed in units of 32us by the mac80211,
@@ -4899,7 +4966,8 @@ static int wl1271_op_conf_tx(struct ieee80211_hw *hw,
 				 0, 0);
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -4923,16 +4991,19 @@ static u64 wl1271_op_get_tsf(struct ieee80211_hw *hw,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl12xx_acx_tsf_info(wl, wlvif, &mactime);
 	if (ret < 0)
 		goto out_sleep;
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -5238,13 +5309,16 @@ static int wl12xx_op_sta_state(struct ieee80211_hw *hw,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl12xx_update_sta_state(wl, wlvif, sta, old_state, new_state);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	if (new_state < old_state)
@@ -5293,9 +5367,11 @@ static int wl1271_op_ampdu_action(struct ieee80211_hw *hw,
 
 	ba_bitmap = &wl->links[hlid].ba_bitmap;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl1271_debug(DEBUG_MAC80211, "mac80211 ampdu: Rx tid %d action %d",
 		     tid, action);
@@ -5368,7 +5444,8 @@ static int wl1271_op_ampdu_action(struct ieee80211_hw *hw,
 		ret = -EINVAL;
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -5402,16 +5479,19 @@ static int wl12xx_set_bitrate_mask(struct ieee80211_hw *hw,
 	if (wlvif->bss_type == BSS_TYPE_STA_BSS &&
 	    !test_bit(WLVIF_FLAG_STA_ASSOCIATED, &wlvif->flags)) {
 
-		ret = wl1271_ps_elp_wakeup(wl);
-		if (ret < 0)
+		ret = pm_runtime_get_sync(wl->dev);
+		if (ret < 0) {
+			pm_runtime_put_noidle(wl->dev);
 			goto out;
+		}
 
 		wl1271_set_band_rate(wl, wlvif);
 		wlvif->basic_rate =
 			wl1271_tx_min_rate_get(wl, wlvif->basic_rate_set);
 		ret = wl1271_acx_sta_rate_policies(wl, wlvif);
 
-		wl1271_ps_elp_sleep(wl);
+		pm_runtime_mark_last_busy(wl->dev);
+		pm_runtime_put_autosuspend(wl->dev);
 	}
 out:
 	mutex_unlock(&wl->mutex);
@@ -5441,9 +5521,11 @@ static void wl12xx_op_channel_switch(struct ieee80211_hw *hw,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	/* TODO: change mac80211 to pass vif as param */
 
@@ -5465,7 +5547,8 @@ static void wl12xx_op_channel_switch(struct ieee80211_hw *hw,
 	}
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -5532,9 +5615,11 @@ static void wlcore_op_channel_switch_beacon(struct ieee80211_hw *hw,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl->ops->channel_switch(wl, wlvif, &ch_switch);
 	if (ret)
@@ -5543,7 +5628,8 @@ static void wlcore_op_channel_switch_beacon(struct ieee80211_hw *hw,
 	set_bit(WLVIF_FLAG_CS_PROGRESS, &wlvif->flags);
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -5584,9 +5670,11 @@ static int wlcore_op_remain_on_channel(struct ieee80211_hw *hw,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl12xx_start_dev(wl, wlvif, chan->band, channel);
 	if (ret < 0)
@@ -5596,7 +5684,8 @@ static int wlcore_op_remain_on_channel(struct ieee80211_hw *hw,
 	ieee80211_queue_delayed_work(hw, &wl->roc_complete_work,
 				     msecs_to_jiffies(duration));
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return ret;
@@ -5638,13 +5727,16 @@ static int wlcore_roc_completed(struct wl1271 *wl)
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = __wlcore_roc_completed(wl);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -5719,19 +5811,22 @@ static void wlcore_op_sta_statistics(struct ieee80211_hw *hw,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out_sleep;
+	}
 
 	ret = wlcore_acx_average_rssi(wl, wlvif, &rssi_dbm);
 	if (ret < 0)
 		goto out_sleep;
 
-	sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 	sinfo->signal = rssi_dbm;
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -6065,16 +6160,16 @@ static int wl1271_register_hw(struct wl1271 *wl)
 	}
 
 	if (oui_addr == 0xdeadbe && nic_addr == 0xef0000) {
-		wl1271_warning("Detected unconfigured mac address in nvs, derive from fuse instead.\n");
+		wl1271_warning("Detected unconfigured mac address in nvs, derive from fuse instead.");
 		if (!strcmp(pdev_data->family->name, "wl18xx")) {
-			wl1271_warning("This default nvs file can be removed from the file system\n");
+			wl1271_warning("This default nvs file can be removed from the file system");
 		} else {
-			wl1271_warning("Your device performance is not optimized.\n");
-			wl1271_warning("Please use the calibrator tool to configure your device.\n");
+			wl1271_warning("Your device performance is not optimized.");
+			wl1271_warning("Please use the calibrator tool to configure your device.");
 		}
 
 		if (wl->fuse_oui_addr == 0 && wl->fuse_nic_addr == 0) {
-			wl1271_warning("Fuse mac address is zero. using random mac\n");
+			wl1271_warning("Fuse mac address is zero. using random mac");
 			/* Use TI oui and a random nic */
 			oui_addr = WLCORE_TI_OUI_ADDRESS;
 			nic_addr = get_random_int();
@@ -6300,7 +6395,6 @@ struct ieee80211_hw *wlcore_alloc_hw(size_t priv_size, u32 aggr_buf_size,
 	skb_queue_head_init(&wl->deferred_rx_queue);
 	skb_queue_head_init(&wl->deferred_tx_queue);
 
-	INIT_DELAYED_WORK(&wl->elp_work, wl1271_elp_work);
 	INIT_WORK(&wl->netstack_work, wl1271_netstack_work);
 	INIT_WORK(&wl->tx_work, wl1271_tx_work);
 	INIT_WORK(&wl->recovery_work, wl1271_recovery_work);
@@ -6575,6 +6669,99 @@ out:
 	complete_all(&wl->nvs_loading_complete);
 }
 
+static int __maybe_unused wlcore_runtime_suspend(struct device *dev)
+{
+	struct wl1271 *wl = dev_get_drvdata(dev);
+	struct wl12xx_vif *wlvif;
+	int error;
+
+	/* We do not enter elp sleep in PLT mode */
+	if (wl->plt)
+		return 0;
+
+	/* Nothing to do if no ELP mode requested */
+	if (wl->sleep_auth != WL1271_PSM_ELP)
+		return 0;
+
+	wl12xx_for_each_wlvif(wl, wlvif) {
+		if (!test_bit(WLVIF_FLAG_IN_PS, &wlvif->flags) &&
+		    test_bit(WLVIF_FLAG_IN_USE, &wlvif->flags))
+			return -EBUSY;
+	}
+
+	wl1271_debug(DEBUG_PSM, "chip to elp");
+	error = wlcore_raw_write32(wl, HW_ACCESS_ELP_CTRL_REG, ELPCTRL_SLEEP);
+	if (error < 0) {
+		wl12xx_queue_recovery_work(wl);
+
+		return error;
+	}
+
+	set_bit(WL1271_FLAG_IN_ELP, &wl->flags);
+
+	return 0;
+}
+
+static int __maybe_unused wlcore_runtime_resume(struct device *dev)
+{
+	struct wl1271 *wl = dev_get_drvdata(dev);
+	DECLARE_COMPLETION_ONSTACK(compl);
+	unsigned long flags;
+	int ret;
+	unsigned long start_time = jiffies;
+	bool pending = false;
+
+	/* Nothing to do if no ELP mode requested */
+	if (!test_bit(WL1271_FLAG_IN_ELP, &wl->flags))
+		return 0;
+
+	wl1271_debug(DEBUG_PSM, "waking up chip from elp");
+
+	spin_lock_irqsave(&wl->wl_lock, flags);
+	if (test_bit(WL1271_FLAG_IRQ_RUNNING, &wl->flags))
+		pending = true;
+	else
+		wl->elp_compl = &compl;
+	spin_unlock_irqrestore(&wl->wl_lock, flags);
+
+	ret = wlcore_raw_write32(wl, HW_ACCESS_ELP_CTRL_REG, ELPCTRL_WAKE_UP);
+	if (ret < 0) {
+		wl12xx_queue_recovery_work(wl);
+		goto err;
+	}
+
+	if (!pending) {
+		ret = wait_for_completion_timeout(&compl,
+			msecs_to_jiffies(WL1271_WAKEUP_TIMEOUT));
+		if (ret == 0) {
+			wl1271_error("ELP wakeup timeout!");
+			wl12xx_queue_recovery_work(wl);
+
+			/* Return no error for runtime PM for recovery */
+			return 0;
+		}
+	}
+
+	clear_bit(WL1271_FLAG_IN_ELP, &wl->flags);
+
+	wl1271_debug(DEBUG_PSM, "wakeup time: %u ms",
+		     jiffies_to_msecs(jiffies - start_time));
+
+	return 0;
+
+err:
+	spin_lock_irqsave(&wl->wl_lock, flags);
+	wl->elp_compl = NULL;
+	spin_unlock_irqrestore(&wl->wl_lock, flags);
+	return ret;
+}
+
+static const struct dev_pm_ops wlcore_pm_ops = {
+	SET_RUNTIME_PM_OPS(wlcore_runtime_suspend,
+			   wlcore_runtime_resume,
+			   NULL)
+};
+
 int wlcore_probe(struct wl1271 *wl, struct platform_device *pdev)
 {
 	struct wlcore_platdev_data *pdev_data = dev_get_platdata(&pdev->dev);
@@ -6602,6 +6789,11 @@ int wlcore_probe(struct wl1271 *wl, struct platform_device *pdev)
 		wlcore_nvs_cb(NULL, wl);
 	}
 
+	wl->dev->driver->pm = &wlcore_pm_ops;
+	pm_runtime_set_autosuspend_delay(wl->dev, 50);
+	pm_runtime_use_autosuspend(wl->dev);
+	pm_runtime_enable(wl->dev);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(wlcore_probe);
@@ -6610,6 +6802,13 @@ int wlcore_remove(struct platform_device *pdev)
 {
 	struct wlcore_platdev_data *pdev_data = dev_get_platdata(&pdev->dev);
 	struct wl1271 *wl = platform_get_drvdata(pdev);
+	int error;
+
+	error = pm_runtime_get_sync(wl->dev);
+	if (error < 0)
+		dev_warn(wl->dev, "PM runtime failed: %i\n", error);
+
+	wl->dev->driver->pm = NULL;
 
 	if (pdev_data->family && pdev_data->family->nvs_name)
 		wait_for_completion(&wl->nvs_loading_complete);
@@ -6621,6 +6820,11 @@ int wlcore_remove(struct platform_device *pdev)
 		disable_irq_wake(wl->irq);
 	}
 	wl1271_unregister_hw(wl);
+
+	pm_runtime_put_sync(wl->dev);
+	pm_runtime_dont_use_autosuspend(wl->dev);
+	pm_runtime_disable(wl->dev);
+
 	free_irq(wl->irq, wl);
 	wlcore_free_hw(wl);
 
diff --git a/drivers/net/wireless/ti/wlcore/ps.c b/drivers/net/wireless/ti/wlcore/ps.c
index b36133b739cb..9de843d1984b 100644
--- a/drivers/net/wireless/ti/wlcore/ps.c
+++ b/drivers/net/wireless/ti/wlcore/ps.c
@@ -26,152 +26,6 @@
 #include "tx.h"
 #include "debug.h"
 
-#define WL1271_WAKEUP_TIMEOUT 500
-
-#define ELP_ENTRY_DELAY  30
-#define ELP_ENTRY_DELAY_FORCE_PS  5
-
-void wl1271_elp_work(struct work_struct *work)
-{
-	struct delayed_work *dwork;
-	struct wl1271 *wl;
-	struct wl12xx_vif *wlvif;
-	int ret;
-
-	dwork = to_delayed_work(work);
-	wl = container_of(dwork, struct wl1271, elp_work);
-
-	wl1271_debug(DEBUG_PSM, "elp work");
-
-	mutex_lock(&wl->mutex);
-
-	if (unlikely(wl->state != WLCORE_STATE_ON))
-		goto out;
-
-	/* our work might have been already cancelled */
-	if (unlikely(!test_bit(WL1271_FLAG_ELP_REQUESTED, &wl->flags)))
-		goto out;
-
-	if (test_bit(WL1271_FLAG_IN_ELP, &wl->flags))
-		goto out;
-
-	wl12xx_for_each_wlvif(wl, wlvif) {
-		if (!test_bit(WLVIF_FLAG_IN_PS, &wlvif->flags) &&
-		    test_bit(WLVIF_FLAG_IN_USE, &wlvif->flags))
-			goto out;
-	}
-
-	wl1271_debug(DEBUG_PSM, "chip to elp");
-	ret = wlcore_raw_write32(wl, HW_ACCESS_ELP_CTRL_REG, ELPCTRL_SLEEP);
-	if (ret < 0) {
-		wl12xx_queue_recovery_work(wl);
-		goto out;
-	}
-
-	set_bit(WL1271_FLAG_IN_ELP, &wl->flags);
-
-out:
-	mutex_unlock(&wl->mutex);
-}
-
-/* Routines to toggle sleep mode while in ELP */
-void wl1271_ps_elp_sleep(struct wl1271 *wl)
-{
-	struct wl12xx_vif *wlvif;
-	u32 timeout;
-
-	/* We do not enter elp sleep in PLT mode */
-	if (wl->plt)
-		return;
-
-	if (wl->sleep_auth != WL1271_PSM_ELP)
-		return;
-
-	/* we shouldn't get consecutive sleep requests */
-	if (WARN_ON(test_and_set_bit(WL1271_FLAG_ELP_REQUESTED, &wl->flags)))
-		return;
-
-	wl12xx_for_each_wlvif(wl, wlvif) {
-		if (!test_bit(WLVIF_FLAG_IN_PS, &wlvif->flags) &&
-		    test_bit(WLVIF_FLAG_IN_USE, &wlvif->flags))
-			return;
-	}
-
-	timeout = wl->conf.conn.forced_ps ?
-			ELP_ENTRY_DELAY_FORCE_PS : ELP_ENTRY_DELAY;
-	ieee80211_queue_delayed_work(wl->hw, &wl->elp_work,
-				     msecs_to_jiffies(timeout));
-}
-EXPORT_SYMBOL_GPL(wl1271_ps_elp_sleep);
-
-int wl1271_ps_elp_wakeup(struct wl1271 *wl)
-{
-	DECLARE_COMPLETION_ONSTACK(compl);
-	unsigned long flags;
-	int ret;
-	unsigned long start_time = jiffies;
-	bool pending = false;
-
-	/*
-	 * we might try to wake up even if we didn't go to sleep
-	 * before (e.g. on boot)
-	 */
-	if (!test_and_clear_bit(WL1271_FLAG_ELP_REQUESTED, &wl->flags))
-		return 0;
-
-	/* don't cancel_sync as it might contend for a mutex and deadlock */
-	cancel_delayed_work(&wl->elp_work);
-
-	if (!test_bit(WL1271_FLAG_IN_ELP, &wl->flags))
-		return 0;
-
-	wl1271_debug(DEBUG_PSM, "waking up chip from elp");
-
-	/*
-	 * The spinlock is required here to synchronize both the work and
-	 * the completion variable in one entity.
-	 */
-	spin_lock_irqsave(&wl->wl_lock, flags);
-	if (test_bit(WL1271_FLAG_IRQ_RUNNING, &wl->flags))
-		pending = true;
-	else
-		wl->elp_compl = &compl;
-	spin_unlock_irqrestore(&wl->wl_lock, flags);
-
-	ret = wlcore_raw_write32(wl, HW_ACCESS_ELP_CTRL_REG, ELPCTRL_WAKE_UP);
-	if (ret < 0) {
-		wl12xx_queue_recovery_work(wl);
-		goto err;
-	}
-
-	if (!pending) {
-		ret = wait_for_completion_timeout(
-			&compl, msecs_to_jiffies(WL1271_WAKEUP_TIMEOUT));
-		if (ret == 0) {
-			wl1271_error("ELP wakeup timeout!");
-			wl12xx_queue_recovery_work(wl);
-			ret = -ETIMEDOUT;
-			goto err;
-		}
-	}
-
-	clear_bit(WL1271_FLAG_IN_ELP, &wl->flags);
-
-	wl1271_debug(DEBUG_PSM, "wakeup time: %u ms",
-		     jiffies_to_msecs(jiffies - start_time));
-	goto out;
-
-err:
-	spin_lock_irqsave(&wl->wl_lock, flags);
-	wl->elp_compl = NULL;
-	spin_unlock_irqrestore(&wl->wl_lock, flags);
-	return ret;
-
-out:
-	return 0;
-}
-EXPORT_SYMBOL_GPL(wl1271_ps_elp_wakeup);
-
 int wl1271_ps_set_mode(struct wl1271 *wl, struct wl12xx_vif *wlvif,
 		       enum wl1271_cmd_ps_mode mode)
 {
diff --git a/drivers/net/wireless/ti/wlcore/ps.h b/drivers/net/wireless/ti/wlcore/ps.h
index de4f9da8ed26..411727587f95 100644
--- a/drivers/net/wireless/ti/wlcore/ps.h
+++ b/drivers/net/wireless/ti/wlcore/ps.h
@@ -29,9 +29,6 @@
 
 int wl1271_ps_set_mode(struct wl1271 *wl, struct wl12xx_vif *wlvif,
 		       enum wl1271_cmd_ps_mode mode);
-void wl1271_ps_elp_sleep(struct wl1271 *wl);
-int wl1271_ps_elp_wakeup(struct wl1271 *wl);
-void wl1271_elp_work(struct work_struct *work);
 void wl12xx_ps_link_start(struct wl1271 *wl, struct wl12xx_vif *wlvif,
 			  u8 hlid, bool clean_queues);
 void wl12xx_ps_link_end(struct wl1271 *wl, struct wl12xx_vif *wlvif, u8 hlid);
diff --git a/drivers/net/wireless/ti/wlcore/rx.c b/drivers/net/wireless/ti/wlcore/rx.c
index 0f15696195f8..078a4940bc5c 100644
--- a/drivers/net/wireless/ti/wlcore/rx.c
+++ b/drivers/net/wireless/ti/wlcore/rx.c
@@ -59,7 +59,7 @@ static u32 wlcore_rx_get_align_buf_size(struct wl1271 *wl, u32 pkt_len)
 static void wl1271_rx_status(struct wl1271 *wl,
 			     struct wl1271_rx_descriptor *desc,
 			     struct ieee80211_rx_status *status,
-			     u8 beacon)
+			     u8 beacon, u8 probe_rsp)
 {
 	memset(status, 0, sizeof(struct ieee80211_rx_status));
 
@@ -106,6 +106,9 @@ static void wl1271_rx_status(struct wl1271 *wl,
 		}
 	}
 
+	if (beacon || probe_rsp)
+		status->boottime_ns = ktime_get_boot_ns();
+
 	if (beacon)
 		wlcore_set_pending_regdomain_ch(wl, (u16)desc->channel,
 						status->band);
@@ -191,7 +194,8 @@ static int wl1271_rx_handle_data(struct wl1271 *wl, u8 *data, u32 length,
 	if (ieee80211_is_data_present(hdr->frame_control))
 		is_data = 1;
 
-	wl1271_rx_status(wl, desc, IEEE80211_SKB_RXCB(skb), beacon);
+	wl1271_rx_status(wl, desc, IEEE80211_SKB_RXCB(skb), beacon,
+			 ieee80211_is_probe_resp(hdr->frame_control));
 	wlcore_hw_set_rx_csum(wl, desc, skb);
 
 	seq_num = (le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_SEQ) >> 4;
diff --git a/drivers/net/wireless/ti/wlcore/scan.c b/drivers/net/wireless/ti/wlcore/scan.c
index 5612f5916b4e..764e723e4ef9 100644
--- a/drivers/net/wireless/ti/wlcore/scan.c
+++ b/drivers/net/wireless/ti/wlcore/scan.c
@@ -22,13 +22,13 @@
  */
 
 #include <linux/ieee80211.h>
+#include <linux/pm_runtime.h>
 
 #include "wlcore.h"
 #include "debug.h"
 #include "cmd.h"
 #include "scan.h"
 #include "acx.h"
-#include "ps.h"
 #include "tx.h"
 
 void wl1271_scan_complete_work(struct work_struct *work)
@@ -67,17 +67,17 @@ void wl1271_scan_complete_work(struct work_struct *work)
 	wl->scan.req = NULL;
 	wl->scan_wlvif = NULL;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	if (test_bit(WLVIF_FLAG_STA_ASSOCIATED, &wlvif->flags)) {
 		/* restore hardware connection monitoring template */
 		wl1271_cmd_build_ap_probe_req(wl, wlvif, wlvif->probereq);
 	}
 
-	wl1271_ps_elp_sleep(wl);
-
 	if (wl->scan.failed) {
 		wl1271_info("Scan completed due to error.");
 		wl12xx_queue_recovery_work(wl);
@@ -85,6 +85,9 @@ void wl1271_scan_complete_work(struct work_struct *work)
 
 	wlcore_cmd_regdomain_config_locked(wl);
 
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
+
 	ieee80211_scan_completed(wl->hw, &info);
 
 out:
diff --git a/drivers/net/wireless/ti/wlcore/sysfs.c b/drivers/net/wireless/ti/wlcore/sysfs.c
index d31eb775e023..7425ba9471d0 100644
--- a/drivers/net/wireless/ti/wlcore/sysfs.c
+++ b/drivers/net/wireless/ti/wlcore/sysfs.c
@@ -19,9 +19,11 @@
  *
  */
 
+#include <linux/pm_runtime.h>
+
+#include "acx.h"
 #include "wlcore.h"
 #include "debug.h"
-#include "ps.h"
 #include "sysfs.h"
 
 static ssize_t wl1271_sysfs_show_bt_coex_state(struct device *dev,
@@ -68,12 +70,15 @@ static ssize_t wl1271_sysfs_store_bt_coex_state(struct device *dev,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl1271_acx_sg_enable(wl, wl->sg_enabled);
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
  out:
 	mutex_unlock(&wl->mutex);
diff --git a/drivers/net/wireless/ti/wlcore/testmode.c b/drivers/net/wireless/ti/wlcore/testmode.c
index 009ec07c4cec..dcb2c8b0feb6 100644
--- a/drivers/net/wireless/ti/wlcore/testmode.c
+++ b/drivers/net/wireless/ti/wlcore/testmode.c
@@ -22,13 +22,13 @@
  */
 #include "testmode.h"
 
+#include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <net/genetlink.h>
 
 #include "wlcore.h"
 #include "debug.h"
 #include "acx.h"
-#include "ps.h"
 #include "io.h"
 
 #define WL1271_TM_MAX_DATA_LENGTH 1024
@@ -97,9 +97,11 @@ static int wl1271_tm_cmd_test(struct wl1271 *wl, struct nlattr *tb[])
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl1271_cmd_test(wl, buf, buf_len, answer);
 	if (ret < 0) {
@@ -141,7 +143,8 @@ static int wl1271_tm_cmd_test(struct wl1271 *wl, struct nlattr *tb[])
 	}
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -169,9 +172,11 @@ static int wl1271_tm_cmd_interrogate(struct wl1271 *wl, struct nlattr *tb[])
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
 	if (!cmd) {
@@ -205,7 +210,8 @@ static int wl1271_tm_cmd_interrogate(struct wl1271 *wl, struct nlattr *tb[])
 out_free:
 	kfree(cmd);
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
diff --git a/drivers/net/wireless/ti/wlcore/tx.c b/drivers/net/wireless/ti/wlcore/tx.c
index 00e9b4624dcf..b6e19c2d66b0 100644
--- a/drivers/net/wireless/ti/wlcore/tx.c
+++ b/drivers/net/wireless/ti/wlcore/tx.c
@@ -24,6 +24,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/etherdevice.h>
+#include <linux/pm_runtime.h>
 #include <linux/spinlock.h>
 
 #include "wlcore.h"
@@ -868,9 +869,11 @@ void wl1271_tx_work(struct work_struct *work)
 	int ret;
 
 	mutex_lock(&wl->mutex);
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wlcore_tx_work_locked(wl);
 	if (ret < 0) {
@@ -878,7 +881,8 @@ void wl1271_tx_work(struct work_struct *work)
 		goto out;
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
diff --git a/drivers/net/wireless/ti/wlcore/vendor_cmd.c b/drivers/net/wireless/ti/wlcore/vendor_cmd.c
index 5c0bcb1fe1a1..dbe78d8491ef 100644
--- a/drivers/net/wireless/ti/wlcore/vendor_cmd.c
+++ b/drivers/net/wireless/ti/wlcore/vendor_cmd.c
@@ -8,12 +8,13 @@
  * version 2 as published by the Free Software Foundation.
  */
 
+#include <linux/pm_runtime.h>
+
 #include <net/mac80211.h>
 #include <net/netlink.h>
 
 #include "wlcore.h"
 #include "debug.h"
-#include "ps.h"
 #include "hw_ops.h"
 #include "vendor_cmd.h"
 
@@ -55,14 +56,17 @@ wlcore_vendor_cmd_smart_config_start(struct wiphy *wiphy,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wlcore_smart_config_start(wl,
 			nla_get_u32(tb[WLCORE_VENDOR_ATTR_GROUP_ID]));
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -87,13 +91,16 @@ wlcore_vendor_cmd_smart_config_stop(struct wiphy *wiphy,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wlcore_smart_config_stop(wl);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -131,16 +138,19 @@ wlcore_vendor_cmd_smart_config_set_group_key(struct wiphy *wiphy,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wlcore_smart_config_set_group_key(wl,
 			nla_get_u32(tb[WLCORE_VENDOR_ATTR_GROUP_ID]),
 			nla_len(tb[WLCORE_VENDOR_ATTR_GROUP_KEY]),
 			nla_data(tb[WLCORE_VENDOR_ATTR_GROUP_KEY]));
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
diff --git a/drivers/net/wireless/ti/wlcore/wlcore.h b/drivers/net/wireless/ti/wlcore/wlcore.h
index 95fbedc8ea34..d4b1f66ef457 100644
--- a/drivers/net/wireless/ti/wlcore/wlcore.h
+++ b/drivers/net/wireless/ti/wlcore/wlcore.h
@@ -348,7 +348,6 @@ struct wl1271 {
 	enum nl80211_band band;
 
 	struct completion *elp_compl;
-	struct delayed_work elp_work;
 
 	/* in dBm */
 	int power_level;
diff --git a/drivers/net/wireless/ti/wlcore/wlcore_i.h b/drivers/net/wireless/ti/wlcore/wlcore_i.h
index e840985385fc..32ec121ccac2 100644
--- a/drivers/net/wireless/ti/wlcore/wlcore_i.h
+++ b/drivers/net/wireless/ti/wlcore/wlcore_i.h
@@ -233,7 +233,6 @@ enum wl12xx_flags {
 	WL1271_FLAG_TX_QUEUE_STOPPED,
 	WL1271_FLAG_TX_PENDING,
 	WL1271_FLAG_IN_ELP,
-	WL1271_FLAG_ELP_REQUESTED,
 	WL1271_FLAG_IRQ_RUNNING,
 	WL1271_FLAG_FW_TX_BUSY,
 	WL1271_FLAG_DUMMY_PACKET_PENDING,
diff --git a/drivers/net/wireless/zydas/zd1211rw/zd_chip.c b/drivers/net/wireless/zydas/zd1211rw/zd_chip.c
index 07b94eda9604..dd6a86b899eb 100644
--- a/drivers/net/wireless/zydas/zd1211rw/zd_chip.c
+++ b/drivers/net/wireless/zydas/zd1211rw/zd_chip.c
@@ -1341,7 +1341,7 @@ int zd_chip_control_leds(struct zd_chip *chip, enum led_status status)
 	case ZD_LED_SCANNING:
 		ioreqs[0].value = FW_LINK_OFF;
 		ioreqs[1].value = v[1] & ~other_led;
-		if (get_seconds() % 3 == 0) {
+		if ((u32)ktime_get_seconds() % 3 == 0) {
 			ioreqs[1].value &= ~chip->link_led;
 		} else {
 			ioreqs[1].value |= chip->link_led;
diff --git a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
index c30bf118c67d..c2cda3acd4af 100644
--- a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
+++ b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
@@ -371,25 +371,27 @@ static inline void handle_regs_int_override(struct urb *urb)
 {
 	struct zd_usb *usb = urb->context;
 	struct zd_usb_interrupt *intr = &usb->intr;
+	unsigned long flags;
 
-	spin_lock(&intr->lock);
+	spin_lock_irqsave(&intr->lock, flags);
 	if (atomic_read(&intr->read_regs_enabled)) {
 		atomic_set(&intr->read_regs_enabled, 0);
 		intr->read_regs_int_overridden = 1;
 		complete(&intr->read_regs.completion);
 	}
-	spin_unlock(&intr->lock);
+	spin_unlock_irqrestore(&intr->lock, flags);
 }
 
 static inline void handle_regs_int(struct urb *urb)
 {
 	struct zd_usb *usb = urb->context;
 	struct zd_usb_interrupt *intr = &usb->intr;
+	unsigned long flags;
 	int len;
 	u16 int_num;
 
 	ZD_ASSERT(in_interrupt());
-	spin_lock(&intr->lock);
+	spin_lock_irqsave(&intr->lock, flags);
 
 	int_num = le16_to_cpu(*(__le16 *)(urb->transfer_buffer+2));
 	if (int_num == CR_INTERRUPT) {
@@ -425,7 +427,7 @@ static inline void handle_regs_int(struct urb *urb)
 	}
 
 out:
-	spin_unlock(&intr->lock);
+	spin_unlock_irqrestore(&intr->lock, flags);
 
 	/* CR_INTERRUPT might override read_reg too. */
 	if (int_num == CR_INTERRUPT && atomic_read(&intr->read_regs_enabled))
@@ -665,6 +667,7 @@ static void rx_urb_complete(struct urb *urb)
 	struct zd_usb_rx *rx;
 	const u8 *buffer;
 	unsigned int length;
+	unsigned long flags;
 
 	switch (urb->status) {
 	case 0:
@@ -693,14 +696,14 @@ static void rx_urb_complete(struct urb *urb)
 		/* If there is an old first fragment, we don't care. */
 		dev_dbg_f(urb_dev(urb), "*** first fragment ***\n");
 		ZD_ASSERT(length <= ARRAY_SIZE(rx->fragment));
-		spin_lock(&rx->lock);
+		spin_lock_irqsave(&rx->lock, flags);
 		memcpy(rx->fragment, buffer, length);
 		rx->fragment_length = length;
-		spin_unlock(&rx->lock);
+		spin_unlock_irqrestore(&rx->lock, flags);
 		goto resubmit;
 	}
 
-	spin_lock(&rx->lock);
+	spin_lock_irqsave(&rx->lock, flags);
 	if (rx->fragment_length > 0) {
 		/* We are on a second fragment, we believe */
 		ZD_ASSERT(length + rx->fragment_length <=
@@ -710,9 +713,9 @@ static void rx_urb_complete(struct urb *urb)
 		handle_rx_packet(usb, rx->fragment,
 			         rx->fragment_length + length);
 		rx->fragment_length = 0;
-		spin_unlock(&rx->lock);
+		spin_unlock_irqrestore(&rx->lock, flags);
 	} else {
-		spin_unlock(&rx->lock);
+		spin_unlock_irqrestore(&rx->lock, flags);
 		handle_rx_packet(usb, buffer, length);
 	}
 
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 78ebe494fef0..92274c237200 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -148,14 +148,14 @@ void xenvif_wake_queue(struct xenvif_queue *queue)
 }
 
 static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb,
-			       void *accel_priv,
+			       struct net_device *sb_dev,
 			       select_queue_fallback_t fallback)
 {
 	struct xenvif *vif = netdev_priv(dev);
 	unsigned int size = vif->hash.size;
 
 	if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE)
-		return fallback(dev, skb) % dev->real_num_tx_queues;
+		return fallback(dev, skb, NULL) % dev->real_num_tx_queues;
 
 	xenvif_set_skb_hash(vif, skb);
 
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index a27daa23c9dc..3621e05a7494 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -1603,9 +1603,9 @@ static void xenvif_ctrl_action(struct xenvif *vif)
 static bool xenvif_ctrl_work_todo(struct xenvif *vif)
 {
 	if (likely(RING_HAS_UNCONSUMED_REQUESTS(&vif->ctrl)))
-		return 1;
+		return true;
 
-	return 0;
+	return false;
 }
 
 irqreturn_t xenvif_ctrl_irq_fn(int irq, void *data)
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 9dd2ca62d84a..73f596a90c69 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -546,7 +546,8 @@ static int xennet_count_skb_slots(struct sk_buff *skb)
 }
 
 static u16 xennet_select_queue(struct net_device *dev, struct sk_buff *skb,
-			       void *accel_priv, select_queue_fallback_t fallback)
+			       struct net_device *sb_dev,
+			       select_queue_fallback_t fallback)
 {
 	unsigned int num_queues = dev->real_num_tx_queues;
 	u32 hash;
@@ -1603,14 +1604,16 @@ static int xennet_init_queue(struct netfront_queue *queue)
 {
 	unsigned short i;
 	int err = 0;
+	char *devid;
 
 	spin_lock_init(&queue->tx_lock);
 	spin_lock_init(&queue->rx_lock);
 
 	timer_setup(&queue->rx_refill_timer, rx_refill_timeout, 0);
 
-	snprintf(queue->name, sizeof(queue->name), "%s-q%u",
-		 queue->info->netdev->name, queue->id);
+	devid = strrchr(queue->info->xbdev->nodename, '/') + 1;
+	snprintf(queue->name, sizeof(queue->name), "vif%s-q%u",
+		 devid, queue->id);
 
 	/* Initialise tx_skbs as a free chain containing every entry. */
 	queue->tx_skb_freelist = 0;
diff --git a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c
index f624ae27eabe..5ee5f40b4dfc 100644
--- a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c
+++ b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c
@@ -19,6 +19,7 @@
 #include <linux/kthread.h>
 #include <linux/interrupt.h>
 #include <linux/ntb.h>
+#include <linux/pci.h>
 
 MODULE_DESCRIPTION("Microsemi Switchtec(tm) NTB Driver");
 MODULE_VERSION("0.1");
@@ -1487,7 +1488,7 @@ static int switchtec_ntb_add(struct device *dev,
 
 	stdev->sndev = NULL;
 
-	if (stdev->pdev->class != MICROSEMI_NTB_CLASSCODE)
+	if (stdev->pdev->class != (PCI_CLASS_BRIDGE_OTHER << 8))
 		return -ENODEV;
 
 	sndev = kzalloc_node(sizeof(*sndev), GFP_KERNEL, dev_to_node(dev));
diff --git a/drivers/nubus/bus.c b/drivers/nubus/bus.c
index a59b6c4bb5b8..ad3d17c42e23 100644
--- a/drivers/nubus/bus.c
+++ b/drivers/nubus/bus.c
@@ -5,6 +5,7 @@
 // Copyright (C) 2017 Finn Thain
 
 #include <linux/device.h>
+#include <linux/dma-mapping.h>
 #include <linux/list.h>
 #include <linux/nubus.h>
 #include <linux/seq_file.h>
@@ -93,6 +94,8 @@ int nubus_device_register(struct nubus_board *board)
 	board->dev.release = nubus_device_release;
 	board->dev.bus = &nubus_bus_type;
 	dev_set_name(&board->dev, "slot.%X", board->slot);
+	board->dev.dma_mask = &board->dev.coherent_dma_mask;
+	dma_set_mask(&board->dev, DMA_BIT_MASK(32));
 	return device_register(&board->dev);
 }
 
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 85de8053aa34..0360c015f658 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1423,11 +1423,11 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,
 
 static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip,
 			struct page *page, unsigned int len, unsigned int off,
-			bool is_write, sector_t sector)
+			unsigned int op, sector_t sector)
 {
 	int ret;
 
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		ret = btt_read_pg(btt, bip, page, off, sector, len);
 		flush_dcache_page(page);
 	} else {
@@ -1464,7 +1464,7 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
 		}
 
 		err = btt_do_bvec(btt, bip, bvec.bv_page, len, bvec.bv_offset,
-				  op_is_write(bio_op(bio)), iter.bi_sector);
+				  bio_op(bio), iter.bi_sector);
 		if (err) {
 			dev_err(&btt->nd_btt->dev,
 					"io error in %s sector %lld, len %d,\n",
@@ -1483,16 +1483,16 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
 }
 
 static int btt_rw_page(struct block_device *bdev, sector_t sector,
-		struct page *page, bool is_write)
+		struct page *page, unsigned int op)
 {
 	struct btt *btt = bdev->bd_disk->private_data;
 	int rc;
 	unsigned int len;
 
 	len = hpage_nr_pages(page) * PAGE_SIZE;
-	rc = btt_do_bvec(btt, NULL, page, len, 0, is_write, sector);
+	rc = btt_do_bvec(btt, NULL, page, len, 0, op, sector);
 	if (rc == 0)
-		page_endio(page, is_write, 0);
+		page_endio(page, op_is_write(op), 0);
 
 	return rc;
 }
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 32e0364b48b9..6ee7fd7e4bbd 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -396,16 +396,15 @@ static inline bool nd_iostat_start(struct bio *bio, unsigned long *start)
 		return false;
 
 	*start = jiffies;
-	generic_start_io_acct(disk->queue, bio_data_dir(bio),
-			      bio_sectors(bio), &disk->part0);
+	generic_start_io_acct(disk->queue, bio_op(bio), bio_sectors(bio),
+			      &disk->part0);
 	return true;
 }
 static inline void nd_iostat_end(struct bio *bio, unsigned long start)
 {
 	struct gendisk *disk = bio->bi_disk;
 
-	generic_end_io_acct(disk->queue, bio_data_dir(bio), &disk->part0,
-				start);
+	generic_end_io_acct(disk->queue, bio_op(bio), &disk->part0, start);
 }
 static inline bool is_bad_pmem(struct badblocks *bb, sector_t sector,
 		unsigned int len)
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 8b1fd7f1a224..dd17acd8fe68 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -120,7 +120,7 @@ static blk_status_t read_pmem(struct page *page, unsigned int off,
 }
 
 static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
-			unsigned int len, unsigned int off, bool is_write,
+			unsigned int len, unsigned int off, unsigned int op,
 			sector_t sector)
 {
 	blk_status_t rc = BLK_STS_OK;
@@ -131,7 +131,7 @@ static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 	if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
 		bad_pmem = true;
 
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		if (unlikely(bad_pmem))
 			rc = BLK_STS_IOERR;
 		else {
@@ -180,8 +180,7 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 	do_acct = nd_iostat_start(bio, &start);
 	bio_for_each_segment(bvec, bio, iter) {
 		rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len,
-				bvec.bv_offset, op_is_write(bio_op(bio)),
-				iter.bi_sector);
+				bvec.bv_offset, bio_op(bio), iter.bi_sector);
 		if (rc) {
 			bio->bi_status = rc;
 			break;
@@ -198,13 +197,13 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 }
 
 static int pmem_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, bool is_write)
+		       struct page *page, unsigned int op)
 {
 	struct pmem_device *pmem = bdev->bd_queue->queuedata;
 	blk_status_t rc;
 
 	rc = pmem_do_bvec(pmem, page, hpage_nr_pages(page) * PAGE_SIZE,
-			  0, is_write, sector);
+			  0, op, sector);
 
 	/*
 	 * The ->rw_page interface is subtle and tricky.  The core
@@ -213,7 +212,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 	 * caused by double completion.
 	 */
 	if (rc == 0)
-		page_endio(page, is_write, 0);
+		page_endio(page, op_is_write(op), 0);
 
 	return blk_status_to_errno(rc);
 }
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index bf65501e6ed6..dd8ec1dd9219 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -252,7 +252,8 @@ void nvme_complete_rq(struct request *req)
 	trace_nvme_complete_rq(req);
 
 	if (unlikely(status != BLK_STS_OK && nvme_req_needs_retry(req))) {
-		if (nvme_req_needs_failover(req, status)) {
+		if ((req->cmd_flags & REQ_NVME_MPATH) &&
+		    blk_path_error(status)) {
 			nvme_failover_req(req);
 			return;
 		}
@@ -617,6 +618,8 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 			if (WARN_ON_ONCE(!nvme_ns_has_pi(ns)))
 				return BLK_STS_NOTSUPP;
 			control |= NVME_RW_PRINFO_PRACT;
+		} else if (req_op(req) == REQ_OP_WRITE) {
+			t10_pi_prepare(req, ns->pi_type);
 		}
 
 		switch (ns->pi_type) {
@@ -627,8 +630,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 		case NVME_NS_DPS_PI_TYPE2:
 			control |= NVME_RW_PRINFO_PRCHK_GUARD |
 					NVME_RW_PRINFO_PRCHK_REF;
-			cmnd->rw.reftag = cpu_to_le32(
-					nvme_block_nr(ns, blk_rq_pos(req)));
+			cmnd->rw.reftag = cpu_to_le32(t10_pi_ref_tag(req));
 			break;
 		}
 	}
@@ -638,6 +640,22 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 	return 0;
 }
 
+void nvme_cleanup_cmd(struct request *req)
+{
+	if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ &&
+	    nvme_req(req)->status == 0) {
+		struct nvme_ns *ns = req->rq_disk->private_data;
+
+		t10_pi_complete(req, ns->pi_type,
+				blk_rq_bytes(req) >> ns->lba_shift);
+	}
+	if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
+		kfree(page_address(req->special_vec.bv_page) +
+		      req->special_vec.bv_offset);
+	}
+}
+EXPORT_SYMBOL_GPL(nvme_cleanup_cmd);
+
 blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 		struct nvme_command *cmd)
 {
@@ -668,10 +686,7 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 	}
 
 	cmd->common.command_id = req->tag;
-	if (ns)
-		trace_nvme_setup_nvm_cmd(req->q->id, cmd);
-	else
-		trace_nvme_setup_admin_cmd(cmd);
+	trace_nvme_setup_cmd(req, cmd);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nvme_setup_cmd);
@@ -864,9 +879,6 @@ static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
 	if (unlikely(ctrl->kato == 0))
 		return;
 
-	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
-	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
-	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
 	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
 }
 
@@ -1056,7 +1068,7 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
 EXPORT_SYMBOL_GPL(nvme_set_queue_count);
 
 #define NVME_AEN_SUPPORTED \
-	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT)
+	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT | NVME_AEN_CFG_ANA_CHANGE)
 
 static void nvme_enable_aen(struct nvme_ctrl *ctrl)
 {
@@ -1472,6 +1484,12 @@ static void nvme_update_disk_info(struct gendisk *disk,
 
 	set_capacity(disk, capacity);
 	nvme_config_discard(ns);
+
+	if (id->nsattr & (1 << 0))
+		set_disk_ro(disk, true);
+	else
+		set_disk_ro(disk, false);
+
 	blk_mq_unfreeze_queue(disk->queue);
 }
 
@@ -2270,21 +2288,16 @@ out_unlock:
 	return ret;
 }
 
-int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
-		     u8 log_page, void *log,
-		     size_t size, u64 offset)
+int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
+		void *log, size_t size, u64 offset)
 {
 	struct nvme_command c = { };
 	unsigned long dwlen = size / 4 - 1;
 
 	c.get_log_page.opcode = nvme_admin_get_log_page;
-
-	if (ns)
-		c.get_log_page.nsid = cpu_to_le32(ns->head->ns_id);
-	else
-		c.get_log_page.nsid = cpu_to_le32(NVME_NSID_ALL);
-
+	c.get_log_page.nsid = cpu_to_le32(nsid);
 	c.get_log_page.lid = log_page;
+	c.get_log_page.lsp = lsp;
 	c.get_log_page.numdl = cpu_to_le16(dwlen & ((1 << 16) - 1));
 	c.get_log_page.numdu = cpu_to_le16(dwlen >> 16);
 	c.get_log_page.lpol = cpu_to_le32(lower_32_bits(offset));
@@ -2293,12 +2306,6 @@ int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	return nvme_submit_sync_cmd(ctrl->admin_q, &c, log, size);
 }
 
-static int nvme_get_log(struct nvme_ctrl *ctrl, u8 log_page, void *log,
-			size_t size)
-{
-	return nvme_get_log_ext(ctrl, NULL, log_page, log, size, 0);
-}
-
 static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
 {
 	int ret;
@@ -2309,8 +2316,8 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
 	if (!ctrl->effects)
 		return 0;
 
-	ret = nvme_get_log(ctrl, NVME_LOG_CMD_EFFECTS, ctrl->effects,
-					sizeof(*ctrl->effects));
+	ret = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CMD_EFFECTS, 0,
+			ctrl->effects, sizeof(*ctrl->effects), 0);
 	if (ret) {
 		kfree(ctrl->effects);
 		ctrl->effects = NULL;
@@ -2401,6 +2408,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	nvme_set_queue_limits(ctrl, ctrl->admin_q);
 	ctrl->sgls = le32_to_cpu(id->sgls);
 	ctrl->kas = le16_to_cpu(id->kas);
+	ctrl->max_namespaces = le32_to_cpu(id->mnan);
 
 	if (id->rtd3e) {
 		/* us -> s */
@@ -2460,8 +2468,12 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 		ctrl->hmmaxd = le16_to_cpu(id->hmmaxd);
 	}
 
+	ret = nvme_mpath_init(ctrl, id);
 	kfree(id);
 
+	if (ret < 0)
+		return ret;
+
 	if (ctrl->apst_enabled && !prev_apst_enabled)
 		dev_pm_qos_expose_latency_tolerance(ctrl->device);
 	else if (!ctrl->apst_enabled && prev_apst_enabled)
@@ -2680,6 +2692,10 @@ static struct attribute *nvme_ns_id_attrs[] = {
 	&dev_attr_nguid.attr,
 	&dev_attr_eui.attr,
 	&dev_attr_nsid.attr,
+#ifdef CONFIG_NVME_MULTIPATH
+	&dev_attr_ana_grpid.attr,
+	&dev_attr_ana_state.attr,
+#endif
 	NULL,
 };
 
@@ -2702,6 +2718,14 @@ static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj,
 		if (!memchr_inv(ids->eui64, 0, sizeof(ids->eui64)))
 			return 0;
 	}
+#ifdef CONFIG_NVME_MULTIPATH
+	if (a == &dev_attr_ana_grpid.attr || a == &dev_attr_ana_state.attr) {
+		if (dev_to_disk(dev)->fops != &nvme_fops) /* per-path attr */
+			return 0;
+		if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl))
+			return 0;
+	}
+#endif
 	return a->mode;
 }
 
@@ -3075,8 +3099,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 
 	nvme_get_ctrl(ctrl);
 
-	kfree(id);
-
 	device_add_disk(ctrl->device, ns->disk);
 	if (sysfs_create_group(&disk_to_dev(ns->disk)->kobj,
 					&nvme_ns_id_attr_group))
@@ -3086,8 +3108,10 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 		pr_warn("%s: failed to register lightnvm sysfs group for identification\n",
 			ns->disk->disk_name);
 
-	nvme_mpath_add_disk(ns->head);
+	nvme_mpath_add_disk(ns, id);
 	nvme_fault_inject_init(ns);
+	kfree(id);
+
 	return;
  out_unlink_ns:
 	mutex_lock(&ctrl->subsys->lock);
@@ -3229,7 +3253,8 @@ static void nvme_clear_changed_ns_log(struct nvme_ctrl *ctrl)
 	 * raced with us in reading the log page, which could cause us to miss
 	 * updates.
 	 */
-	error = nvme_get_log(ctrl, NVME_LOG_CHANGED_NS, log, log_size);
+	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CHANGED_NS, 0, log,
+			log_size, 0);
 	if (error)
 		dev_warn(ctrl->device,
 			"reading changed ns log failed: %d\n", error);
@@ -3346,9 +3371,9 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 	if (!log)
 		return;
 
-	if (nvme_get_log(ctrl, NVME_LOG_FW_SLOT, log, sizeof(*log)))
-		dev_warn(ctrl->device,
-				"Get FW SLOT INFO log error\n");
+	if (nvme_get_log(ctrl, NVME_NSID_ALL, 0, NVME_LOG_FW_SLOT, log,
+			sizeof(*log), 0))
+		dev_warn(ctrl->device, "Get FW SLOT INFO log error\n");
 	kfree(log);
 }
 
@@ -3394,6 +3419,13 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
 	case NVME_AER_NOTICE_FW_ACT_STARTING:
 		queue_work(nvme_wq, &ctrl->fw_act_work);
 		break;
+#ifdef CONFIG_NVME_MULTIPATH
+	case NVME_AER_NOTICE_ANA:
+		if (!ctrl->ana_log_buf)
+			break;
+		queue_work(nvme_wq, &ctrl->ana_work);
+		break;
+#endif
 	default:
 		dev_warn(ctrl->device, "async event result %08x\n", result);
 	}
@@ -3426,6 +3458,7 @@ EXPORT_SYMBOL_GPL(nvme_complete_async_event);
 
 void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
 {
+	nvme_mpath_stop(ctrl);
 	nvme_stop_keep_alive(ctrl);
 	flush_work(&ctrl->async_event_work);
 	flush_work(&ctrl->scan_work);
@@ -3463,6 +3496,7 @@ static void nvme_free_ctrl(struct device *dev)
 
 	ida_simple_remove(&nvme_instance_ida, ctrl->instance);
 	kfree(ctrl->effects);
+	nvme_mpath_uninit(ctrl);
 
 	if (subsys) {
 		mutex_lock(&subsys->lock);
@@ -3499,6 +3533,10 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work);
 	INIT_WORK(&ctrl->delete_work, nvme_delete_ctrl_work);
 
+	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
+	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
+	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
+
 	ret = ida_simple_get(&nvme_instance_ida, 0, 0, GFP_KERNEL);
 	if (ret < 0)
 		goto out;
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index f7efe5a58cc7..206d63cb1afc 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -474,7 +474,7 @@ EXPORT_SYMBOL_GPL(nvmf_connect_io_queue);
 
 bool nvmf_should_reconnect(struct nvme_ctrl *ctrl)
 {
-	if (ctrl->opts->max_reconnects != -1 &&
+	if (ctrl->opts->max_reconnects == -1 ||
 	    ctrl->nr_reconnects < ctrl->opts->max_reconnects)
 		return true;
 
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 9bac912173ba..611e70cae754 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1737,6 +1737,7 @@ nvme_fc_init_request(struct blk_mq_tag_set *set, struct request *rq,
 	int queue_idx = (set == &ctrl->tag_set) ? hctx_idx + 1 : 0;
 	struct nvme_fc_queue *queue = &ctrl->queues[queue_idx];
 
+	nvme_req(rq)->ctrl = &ctrl->ctrl;
 	return __nvme_fc_init_request(ctrl, queue, op, rq, queue->rqcnt++);
 }
 
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 41279da799ed..6fe5923c95d4 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -414,12 +414,6 @@ static int nvme_nvm_setup_20(struct nvme_nvm_id20 *id,
 	/* Set compacted version for upper layers */
 	geo->version = NVM_OCSSD_SPEC_20;
 
-	if (!(geo->major_ver_id == 2 && geo->minor_ver_id == 0)) {
-		pr_err("nvm: OCSSD version not supported (v%d.%d)\n",
-				geo->major_ver_id, geo->minor_ver_id);
-		return -EINVAL;
-	}
-
 	geo->num_ch = le16_to_cpu(id->num_grp);
 	geo->num_lun = le16_to_cpu(id->num_pu);
 	geo->all_luns = geo->num_ch * geo->num_lun;
@@ -583,7 +577,13 @@ static int nvme_nvm_get_chk_meta(struct nvm_dev *ndev,
 	struct ppa_addr ppa;
 	size_t left = nchks * sizeof(struct nvme_nvm_chk_meta);
 	size_t log_pos, offset, len;
-	int ret, i;
+	int ret, i, max_len;
+
+	/*
+	 * limit requests to maximum 256K to avoid issuing arbitrary large
+	 * requests when the device does not specific a maximum transfer size.
+	 */
+	max_len = min_t(unsigned int, ctrl->max_hw_sectors << 9, 256 * 1024);
 
 	/* Normalize lba address space to obtain log offset */
 	ppa.ppa = slba;
@@ -596,10 +596,11 @@ static int nvme_nvm_get_chk_meta(struct nvm_dev *ndev,
 	offset = log_pos * sizeof(struct nvme_nvm_chk_meta);
 
 	while (left) {
-		len = min_t(unsigned int, left, ctrl->max_hw_sectors << 9);
+		len = min_t(unsigned int, left, max_len);
 
-		ret = nvme_get_log_ext(ctrl, ns, NVME_NVM_LOG_REPORT_CHUNK,
-				dev_meta, len, offset);
+		ret = nvme_get_log(ctrl, ns->head->ns_id,
+				NVME_NVM_LOG_REPORT_CHUNK, 0, dev_meta, len,
+				offset);
 		if (ret) {
 			dev_err(ctrl->device, "Get REPORT CHUNK log error\n");
 			break;
@@ -662,12 +663,10 @@ static struct request *nvme_nvm_alloc_request(struct request_queue *q,
 
 	rq->cmd_flags &= ~REQ_FAILFAST_DRIVER;
 
-	if (rqd->bio) {
+	if (rqd->bio)
 		blk_init_request_from_bio(rq, rqd->bio);
-	} else {
+	else
 		rq->ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
-		rq->__data_len = 0;
-	}
 
 	return rq;
 }
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 1ffd3e8b13a1..5a9562881d4e 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017 Christoph Hellwig.
+ * Copyright (c) 2017-2018 Christoph Hellwig.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -20,6 +20,11 @@ module_param(multipath, bool, 0444);
 MODULE_PARM_DESC(multipath,
 	"turn on native support for multiple controllers per subsystem");
 
+inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
+{
+	return multipath && ctrl->subsys && (ctrl->subsys->cmic & (1 << 3));
+}
+
 /*
  * If multipathing is enabled we need to always use the subsystem instance
  * number for numbering our devices to avoid conflicts between subsystems that
@@ -45,6 +50,7 @@ void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 void nvme_failover_req(struct request *req)
 {
 	struct nvme_ns *ns = req->q->queuedata;
+	u16 status = nvme_req(req)->status;
 	unsigned long flags;
 
 	spin_lock_irqsave(&ns->head->requeue_lock, flags);
@@ -52,15 +58,35 @@ void nvme_failover_req(struct request *req)
 	spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
 	blk_mq_end_request(req, 0);
 
-	nvme_reset_ctrl(ns->ctrl);
-	kblockd_schedule_work(&ns->head->requeue_work);
-}
+	switch (status & 0x7ff) {
+	case NVME_SC_ANA_TRANSITION:
+	case NVME_SC_ANA_INACCESSIBLE:
+	case NVME_SC_ANA_PERSISTENT_LOSS:
+		/*
+		 * If we got back an ANA error we know the controller is alive,
+		 * but not ready to serve this namespaces.  The spec suggests
+		 * we should update our general state here, but due to the fact
+		 * that the admin and I/O queues are not serialized that is
+		 * fundamentally racy.  So instead just clear the current path,
+		 * mark the the path as pending and kick of a re-read of the ANA
+		 * log page ASAP.
+		 */
+		nvme_mpath_clear_current_path(ns);
+		if (ns->ctrl->ana_log_buf) {
+			set_bit(NVME_NS_ANA_PENDING, &ns->flags);
+			queue_work(nvme_wq, &ns->ctrl->ana_work);
+		}
+		break;
+	default:
+		/*
+		 * Reset the controller for any non-ANA error as we don't know
+		 * what caused the error.
+		 */
+		nvme_reset_ctrl(ns->ctrl);
+		break;
+	}
 
-bool nvme_req_needs_failover(struct request *req, blk_status_t error)
-{
-	if (!(req->cmd_flags & REQ_NVME_MPATH))
-		return false;
-	return blk_path_error(error);
+	kblockd_schedule_work(&ns->head->requeue_work);
 }
 
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
@@ -75,25 +101,51 @@ void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 	up_read(&ctrl->namespaces_rwsem);
 }
 
+static const char *nvme_ana_state_names[] = {
+	[0]				= "invalid state",
+	[NVME_ANA_OPTIMIZED]		= "optimized",
+	[NVME_ANA_NONOPTIMIZED]		= "non-optimized",
+	[NVME_ANA_INACCESSIBLE]		= "inaccessible",
+	[NVME_ANA_PERSISTENT_LOSS]	= "persistent-loss",
+	[NVME_ANA_CHANGE]		= "change",
+};
+
 static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head)
 {
-	struct nvme_ns *ns;
+	struct nvme_ns *ns, *fallback = NULL;
 
 	list_for_each_entry_rcu(ns, &head->list, siblings) {
-		if (ns->ctrl->state == NVME_CTRL_LIVE) {
+		if (ns->ctrl->state != NVME_CTRL_LIVE ||
+		    test_bit(NVME_NS_ANA_PENDING, &ns->flags))
+			continue;
+		switch (ns->ana_state) {
+		case NVME_ANA_OPTIMIZED:
 			rcu_assign_pointer(head->current_path, ns);
 			return ns;
+		case NVME_ANA_NONOPTIMIZED:
+			fallback = ns;
+			break;
+		default:
+			break;
 		}
 	}
 
-	return NULL;
+	if (fallback)
+		rcu_assign_pointer(head->current_path, fallback);
+	return fallback;
+}
+
+static inline bool nvme_path_is_optimized(struct nvme_ns *ns)
+{
+	return ns->ctrl->state == NVME_CTRL_LIVE &&
+		ns->ana_state == NVME_ANA_OPTIMIZED;
 }
 
 inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
 {
 	struct nvme_ns *ns = srcu_dereference(head->current_path, &head->srcu);
 
-	if (unlikely(!ns || ns->ctrl->state != NVME_CTRL_LIVE))
+	if (unlikely(!ns || !nvme_path_is_optimized(ns)))
 		ns = __nvme_find_path(head);
 	return ns;
 }
@@ -142,7 +194,7 @@ static bool nvme_ns_head_poll(struct request_queue *q, blk_qc_t qc)
 
 	srcu_idx = srcu_read_lock(&head->srcu);
 	ns = srcu_dereference(head->current_path, &head->srcu);
-	if (likely(ns && ns->ctrl->state == NVME_CTRL_LIVE))
+	if (likely(ns && nvme_path_is_optimized(ns)))
 		found = ns->queue->poll_fn(q, qc);
 	srcu_read_unlock(&head->srcu, srcu_idx);
 	return found;
@@ -176,6 +228,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	struct request_queue *q;
 	bool vwc = false;
 
+	mutex_init(&head->lock);
 	bio_list_init(&head->requeue_list);
 	spin_lock_init(&head->requeue_lock);
 	INIT_WORK(&head->requeue_work, nvme_requeue_work);
@@ -220,29 +273,232 @@ out:
 	return -ENOMEM;
 }
 
-void nvme_mpath_add_disk(struct nvme_ns_head *head)
+static void nvme_mpath_set_live(struct nvme_ns *ns)
 {
+	struct nvme_ns_head *head = ns->head;
+
+	lockdep_assert_held(&ns->head->lock);
+
 	if (!head->disk)
 		return;
 
-	mutex_lock(&head->subsys->lock);
 	if (!(head->disk->flags & GENHD_FL_UP)) {
 		device_add_disk(&head->subsys->dev, head->disk);
 		if (sysfs_create_group(&disk_to_dev(head->disk)->kobj,
 				&nvme_ns_id_attr_group))
-			pr_warn("%s: failed to create sysfs group for identification\n",
-				head->disk->disk_name);
+			dev_warn(&head->subsys->dev,
+				 "failed to create id group.\n");
+	}
+
+	kblockd_schedule_work(&ns->head->requeue_work);
+}
+
+static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
+		int (*cb)(struct nvme_ctrl *ctrl, struct nvme_ana_group_desc *,
+			void *))
+{
+	void *base = ctrl->ana_log_buf;
+	size_t offset = sizeof(struct nvme_ana_rsp_hdr);
+	int error, i;
+
+	lockdep_assert_held(&ctrl->ana_lock);
+
+	for (i = 0; i < le16_to_cpu(ctrl->ana_log_buf->ngrps); i++) {
+		struct nvme_ana_group_desc *desc = base + offset;
+		u32 nr_nsids = le32_to_cpu(desc->nnsids);
+		size_t nsid_buf_size = nr_nsids * sizeof(__le32);
+
+		if (WARN_ON_ONCE(desc->grpid == 0))
+			return -EINVAL;
+		if (WARN_ON_ONCE(le32_to_cpu(desc->grpid) > ctrl->anagrpmax))
+			return -EINVAL;
+		if (WARN_ON_ONCE(desc->state == 0))
+			return -EINVAL;
+		if (WARN_ON_ONCE(desc->state > NVME_ANA_CHANGE))
+			return -EINVAL;
+
+		offset += sizeof(*desc);
+		if (WARN_ON_ONCE(offset > ctrl->ana_log_size - nsid_buf_size))
+			return -EINVAL;
+
+		error = cb(ctrl, desc, data);
+		if (error)
+			return error;
+
+		offset += nsid_buf_size;
+		if (WARN_ON_ONCE(offset > ctrl->ana_log_size - sizeof(*desc)))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static inline bool nvme_state_is_live(enum nvme_ana_state state)
+{
+	return state == NVME_ANA_OPTIMIZED || state == NVME_ANA_NONOPTIMIZED;
+}
+
+static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
+		struct nvme_ns *ns)
+{
+	enum nvme_ana_state old;
+
+	mutex_lock(&ns->head->lock);
+	old = ns->ana_state;
+	ns->ana_grpid = le32_to_cpu(desc->grpid);
+	ns->ana_state = desc->state;
+	clear_bit(NVME_NS_ANA_PENDING, &ns->flags);
+
+	if (nvme_state_is_live(ns->ana_state) && !nvme_state_is_live(old))
+		nvme_mpath_set_live(ns);
+	mutex_unlock(&ns->head->lock);
+}
+
+static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
+		struct nvme_ana_group_desc *desc, void *data)
+{
+	u32 nr_nsids = le32_to_cpu(desc->nnsids), n = 0;
+	unsigned *nr_change_groups = data;
+	struct nvme_ns *ns;
+
+	dev_info(ctrl->device, "ANA group %d: %s.\n",
+			le32_to_cpu(desc->grpid),
+			nvme_ana_state_names[desc->state]);
+
+	if (desc->state == NVME_ANA_CHANGE)
+		(*nr_change_groups)++;
+
+	if (!nr_nsids)
+		return 0;
+
+	down_write(&ctrl->namespaces_rwsem);
+	list_for_each_entry(ns, &ctrl->namespaces, list) {
+		if (ns->head->ns_id != le32_to_cpu(desc->nsids[n]))
+			continue;
+		nvme_update_ns_ana_state(desc, ns);
+		if (++n == nr_nsids)
+			break;
+	}
+	up_write(&ctrl->namespaces_rwsem);
+	WARN_ON_ONCE(n < nr_nsids);
+	return 0;
+}
+
+static int nvme_read_ana_log(struct nvme_ctrl *ctrl, bool groups_only)
+{
+	u32 nr_change_groups = 0;
+	int error;
+
+	mutex_lock(&ctrl->ana_lock);
+	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA,
+			groups_only ? NVME_ANA_LOG_RGO : 0,
+			ctrl->ana_log_buf, ctrl->ana_log_size, 0);
+	if (error) {
+		dev_warn(ctrl->device, "Failed to get ANA log: %d\n", error);
+		goto out_unlock;
+	}
+
+	error = nvme_parse_ana_log(ctrl, &nr_change_groups,
+			nvme_update_ana_state);
+	if (error)
+		goto out_unlock;
+
+	/*
+	 * In theory we should have an ANATT timer per group as they might enter
+	 * the change state at different times.  But that is a lot of overhead
+	 * just to protect against a target that keeps entering new changes
+	 * states while never finishing previous ones.  But we'll still
+	 * eventually time out once all groups are in change state, so this
+	 * isn't a big deal.
+	 *
+	 * We also double the ANATT value to provide some slack for transports
+	 * or AEN processing overhead.
+	 */
+	if (nr_change_groups)
+		mod_timer(&ctrl->anatt_timer, ctrl->anatt * HZ * 2 + jiffies);
+	else
+		del_timer_sync(&ctrl->anatt_timer);
+out_unlock:
+	mutex_unlock(&ctrl->ana_lock);
+	return error;
+}
+
+static void nvme_ana_work(struct work_struct *work)
+{
+	struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, ana_work);
+
+	nvme_read_ana_log(ctrl, false);
+}
+
+static void nvme_anatt_timeout(struct timer_list *t)
+{
+	struct nvme_ctrl *ctrl = from_timer(ctrl, t, anatt_timer);
+
+	dev_info(ctrl->device, "ANATT timeout, resetting controller.\n");
+	nvme_reset_ctrl(ctrl);
+}
+
+void nvme_mpath_stop(struct nvme_ctrl *ctrl)
+{
+	if (!nvme_ctrl_use_ana(ctrl))
+		return;
+	del_timer_sync(&ctrl->anatt_timer);
+	cancel_work_sync(&ctrl->ana_work);
+}
+
+static ssize_t ana_grpid_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	return sprintf(buf, "%d\n", nvme_get_ns_from_dev(dev)->ana_grpid);
+}
+DEVICE_ATTR_RO(ana_grpid);
+
+static ssize_t ana_state_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
+
+	return sprintf(buf, "%s\n", nvme_ana_state_names[ns->ana_state]);
+}
+DEVICE_ATTR_RO(ana_state);
+
+static int nvme_set_ns_ana_state(struct nvme_ctrl *ctrl,
+		struct nvme_ana_group_desc *desc, void *data)
+{
+	struct nvme_ns *ns = data;
+
+	if (ns->ana_grpid == le32_to_cpu(desc->grpid)) {
+		nvme_update_ns_ana_state(desc, ns);
+		return -ENXIO; /* just break out of the loop */
+	}
+
+	return 0;
+}
+
+void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)
+{
+	if (nvme_ctrl_use_ana(ns->ctrl)) {
+		mutex_lock(&ns->ctrl->ana_lock);
+		ns->ana_grpid = le32_to_cpu(id->anagrpid);
+		nvme_parse_ana_log(ns->ctrl, ns, nvme_set_ns_ana_state);
+		mutex_unlock(&ns->ctrl->ana_lock);
+	} else {
+		mutex_lock(&ns->head->lock);
+		ns->ana_state = NVME_ANA_OPTIMIZED; 
+		nvme_mpath_set_live(ns);
+		mutex_unlock(&ns->head->lock);
 	}
-	mutex_unlock(&head->subsys->lock);
 }
 
 void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 {
 	if (!head->disk)
 		return;
-	sysfs_remove_group(&disk_to_dev(head->disk)->kobj,
-			   &nvme_ns_id_attr_group);
-	del_gendisk(head->disk);
+	if (head->disk->flags & GENHD_FL_UP) {
+		sysfs_remove_group(&disk_to_dev(head->disk)->kobj,
+				   &nvme_ns_id_attr_group);
+		del_gendisk(head->disk);
+	}
 	blk_set_queue_dying(head->disk->queue);
 	/* make sure all pending bios are cleaned up */
 	kblockd_schedule_work(&head->requeue_work);
@@ -250,3 +506,52 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 	blk_cleanup_queue(head->disk->queue);
 	put_disk(head->disk);
 }
+
+int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
+{
+	int error;
+
+	if (!nvme_ctrl_use_ana(ctrl))
+		return 0;
+
+	ctrl->anacap = id->anacap;
+	ctrl->anatt = id->anatt;
+	ctrl->nanagrpid = le32_to_cpu(id->nanagrpid);
+	ctrl->anagrpmax = le32_to_cpu(id->anagrpmax);
+
+	mutex_init(&ctrl->ana_lock);
+	timer_setup(&ctrl->anatt_timer, nvme_anatt_timeout, 0);
+	ctrl->ana_log_size = sizeof(struct nvme_ana_rsp_hdr) +
+		ctrl->nanagrpid * sizeof(struct nvme_ana_group_desc);
+	if (!(ctrl->anacap & (1 << 6)))
+		ctrl->ana_log_size += ctrl->max_namespaces * sizeof(__le32);
+
+	if (ctrl->ana_log_size > ctrl->max_hw_sectors << SECTOR_SHIFT) {
+		dev_err(ctrl->device,
+			"ANA log page size (%zd) larger than MDTS (%d).\n",
+			ctrl->ana_log_size,
+			ctrl->max_hw_sectors << SECTOR_SHIFT);
+		dev_err(ctrl->device, "disabling ANA support.\n");
+		return 0;
+	}
+
+	INIT_WORK(&ctrl->ana_work, nvme_ana_work);
+	ctrl->ana_log_buf = kmalloc(ctrl->ana_log_size, GFP_KERNEL);
+	if (!ctrl->ana_log_buf)
+		goto out;
+
+	error = nvme_read_ana_log(ctrl, true);
+	if (error)
+		goto out_free_ana_log_buf;
+	return 0;
+out_free_ana_log_buf:
+	kfree(ctrl->ana_log_buf);
+out:
+	return -ENOMEM;
+}
+
+void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
+{
+	kfree(ctrl->ana_log_buf);
+}
+
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 0c4a33df3b2f..bb4a2003c097 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -102,6 +102,7 @@ struct nvme_request {
 	u8			retries;
 	u8			flags;
 	u16			status;
+	struct nvme_ctrl	*ctrl;
 };
 
 /*
@@ -119,6 +120,13 @@ static inline struct nvme_request *nvme_req(struct request *req)
 	return blk_mq_rq_to_pdu(req);
 }
 
+static inline u16 nvme_req_qid(struct request *req)
+{
+	if (!req->rq_disk)
+		return 0;
+	return blk_mq_unique_tag_to_hwq(blk_mq_unique_tag(req)) + 1;
+}
+
 /* The below value is the specific amount of delay needed before checking
  * readiness in case of the PCI_DEVICE(0x1c58, 0x0003), which needs the
  * NVME_QUIRK_DELAY_BEFORE_CHK_RDY quirk enabled. The value (in ms) was
@@ -175,6 +183,7 @@ struct nvme_ctrl {
 	u16 oacs;
 	u16 nssa;
 	u16 nr_streams;
+	u32 max_namespaces;
 	atomic_t abort_limit;
 	u8 vwc;
 	u32 vs;
@@ -197,6 +206,19 @@ struct nvme_ctrl {
 	struct work_struct fw_act_work;
 	unsigned long events;
 
+#ifdef CONFIG_NVME_MULTIPATH
+	/* asymmetric namespace access: */
+	u8 anacap;
+	u8 anatt;
+	u32 anagrpmax;
+	u32 nanagrpid;
+	struct mutex ana_lock;
+	struct nvme_ana_rsp_hdr *ana_log_buf;
+	size_t ana_log_size;
+	struct timer_list anatt_timer;
+	struct work_struct ana_work;
+#endif
+
 	/* Power saving configuration */
 	u64 ps_max_latency_us;
 	bool apst_enabled;
@@ -261,6 +283,7 @@ struct nvme_ns_head {
 	struct bio_list		requeue_list;
 	spinlock_t		requeue_lock;
 	struct work_struct	requeue_work;
+	struct mutex		lock;
 #endif
 	struct list_head	list;
 	struct srcu_struct      srcu;
@@ -287,6 +310,10 @@ struct nvme_ns {
 	struct nvme_ctrl *ctrl;
 	struct request_queue *queue;
 	struct gendisk *disk;
+#ifdef CONFIG_NVME_MULTIPATH
+	enum nvme_ana_state ana_state;
+	u32 ana_grpid;
+#endif
 	struct list_head siblings;
 	struct nvm_dev *ndev;
 	struct kref kref;
@@ -299,8 +326,9 @@ struct nvme_ns {
 	bool ext;
 	u8 pi_type;
 	unsigned long flags;
-#define NVME_NS_REMOVING 0
-#define NVME_NS_DEAD     1
+#define NVME_NS_REMOVING	0
+#define NVME_NS_DEAD     	1
+#define NVME_NS_ANA_PENDING	2
 	u16 noiob;
 
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
@@ -356,14 +384,6 @@ static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector)
 	return (sector >> (ns->lba_shift - 9));
 }
 
-static inline void nvme_cleanup_cmd(struct request *req)
-{
-	if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
-		kfree(page_address(req->special_vec.bv_page) +
-		      req->special_vec.bv_offset);
-	}
-}
-
 static inline void nvme_end_request(struct request *req, __le16 status,
 		union nvme_result result)
 {
@@ -420,6 +440,7 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl);
 #define NVME_QID_ANY -1
 struct request *nvme_alloc_request(struct request_queue *q,
 		struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid);
+void nvme_cleanup_cmd(struct request *req);
 blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 		struct nvme_command *cmd);
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
@@ -435,21 +456,24 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl);
 int nvme_delete_ctrl(struct nvme_ctrl *ctrl);
 int nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl);
 
-int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
-		u8 log_page, void *log, size_t size, u64 offset);
+int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
+		void *log, size_t size, u64 offset);
 
 extern const struct attribute_group nvme_ns_id_attr_group;
 extern const struct block_device_operations nvme_ns_head_ops;
 
 #ifdef CONFIG_NVME_MULTIPATH
+bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl);
 void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 			struct nvme_ctrl *ctrl, int *flags);
 void nvme_failover_req(struct request *req);
-bool nvme_req_needs_failover(struct request *req, blk_status_t error);
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
 int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head);
-void nvme_mpath_add_disk(struct nvme_ns_head *head);
+void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id);
 void nvme_mpath_remove_disk(struct nvme_ns_head *head);
+int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id);
+void nvme_mpath_uninit(struct nvme_ctrl *ctrl);
+void nvme_mpath_stop(struct nvme_ctrl *ctrl);
 
 static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
 {
@@ -468,7 +492,14 @@ static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
 		kblockd_schedule_work(&head->requeue_work);
 }
 
+extern struct device_attribute dev_attr_ana_grpid;
+extern struct device_attribute dev_attr_ana_state;
+
 #else
+static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
+{
+	return false;
+}
 /*
  * Without the multipath code enabled, multiple controller per subsystems are
  * visible as devices and thus we cannot use the subsystem instance.
@@ -482,11 +513,6 @@ static inline void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 static inline void nvme_failover_req(struct request *req)
 {
 }
-static inline bool nvme_req_needs_failover(struct request *req,
-					   blk_status_t error)
-{
-	return false;
-}
 static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 {
 }
@@ -495,7 +521,8 @@ static inline int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,
 {
 	return 0;
 }
-static inline void nvme_mpath_add_disk(struct nvme_ns_head *head)
+static inline void nvme_mpath_add_disk(struct nvme_ns *ns,
+		struct nvme_id_ns *id)
 {
 }
 static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head)
@@ -507,6 +534,17 @@ static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
 static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
 {
 }
+static inline int nvme_mpath_init(struct nvme_ctrl *ctrl,
+		struct nvme_id_ctrl *id)
+{
+	return 0;
+}
+static inline void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
+{
+}
+static inline void nvme_mpath_stop(struct nvme_ctrl *ctrl)
+{
+}
 #endif /* CONFIG_NVME_MULTIPATH */
 
 #ifdef CONFIG_NVM
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index ddd441b1516a..1b9951d2067e 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -418,6 +418,8 @@ static int nvme_init_request(struct blk_mq_tag_set *set, struct request *req,
 
 	BUG_ON(!nvmeq);
 	iod->nvmeq = nvmeq;
+
+	nvme_req(req)->ctrl = &dev->ctrl;
 	return 0;
 }
 
@@ -535,73 +537,6 @@ static void nvme_free_iod(struct nvme_dev *dev, struct request *req)
 		mempool_free(iod->sg, dev->iod_mempool);
 }
 
-#ifdef CONFIG_BLK_DEV_INTEGRITY
-static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-	if (be32_to_cpu(pi->ref_tag) == v)
-		pi->ref_tag = cpu_to_be32(p);
-}
-
-static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-	if (be32_to_cpu(pi->ref_tag) == p)
-		pi->ref_tag = cpu_to_be32(v);
-}
-
-/**
- * nvme_dif_remap - remaps ref tags to bip seed and physical lba
- *
- * The virtual start sector is the one that was originally submitted by the
- * block layer.	Due to partitioning, MD/DM cloning, etc. the actual physical
- * start sector may be different. Remap protection information to match the
- * physical LBA on writes, and back to the original seed on reads.
- *
- * Type 0 and 3 do not have a ref tag, so no remapping required.
- */
-static void nvme_dif_remap(struct request *req,
-			void (*dif_swap)(u32 p, u32 v, struct t10_pi_tuple *pi))
-{
-	struct nvme_ns *ns = req->rq_disk->private_data;
-	struct bio_integrity_payload *bip;
-	struct t10_pi_tuple *pi;
-	void *p, *pmap;
-	u32 i, nlb, ts, phys, virt;
-
-	if (!ns->pi_type || ns->pi_type == NVME_NS_DPS_PI_TYPE3)
-		return;
-
-	bip = bio_integrity(req->bio);
-	if (!bip)
-		return;
-
-	pmap = kmap_atomic(bip->bip_vec->bv_page) + bip->bip_vec->bv_offset;
-
-	p = pmap;
-	virt = bip_get_seed(bip);
-	phys = nvme_block_nr(ns, blk_rq_pos(req));
-	nlb = (blk_rq_bytes(req) >> ns->lba_shift);
-	ts = ns->disk->queue->integrity.tuple_size;
-
-	for (i = 0; i < nlb; i++, virt++, phys++) {
-		pi = (struct t10_pi_tuple *)p;
-		dif_swap(phys, virt, pi);
-		p += ts;
-	}
-	kunmap_atomic(pmap);
-}
-#else /* CONFIG_BLK_DEV_INTEGRITY */
-static void nvme_dif_remap(struct request *req,
-			void (*dif_swap)(u32 p, u32 v, struct t10_pi_tuple *pi))
-{
-}
-static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-}
-static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-}
-#endif
-
 static void nvme_print_sgl(struct scatterlist *sgl, int nents)
 {
 	int i;
@@ -827,9 +762,6 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 		if (blk_rq_map_integrity_sg(q, req->bio, &iod->meta_sg) != 1)
 			goto out_unmap;
 
-		if (req_op(req) == REQ_OP_WRITE)
-			nvme_dif_remap(req, nvme_dif_prep);
-
 		if (!dma_map_sg(dev->dev, &iod->meta_sg, 1, dma_dir))
 			goto out_unmap;
 	}
@@ -852,11 +784,8 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
 
 	if (iod->nents) {
 		dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir);
-		if (blk_integrity_rq(req)) {
-			if (req_op(req) == REQ_OP_READ)
-				nvme_dif_remap(req, nvme_dif_complete);
+		if (blk_integrity_rq(req))
 			dma_unmap_sg(dev->dev, &iod->meta_sg, 1, dma_dir);
-		}
 	}
 
 	nvme_cleanup_cmd(req);
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 72e8e8e7d2d7..dc042017c293 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -40,13 +40,14 @@
 
 #define NVME_RDMA_MAX_SEGMENTS		256
 
-#define NVME_RDMA_MAX_INLINE_SEGMENTS	1
+#define NVME_RDMA_MAX_INLINE_SEGMENTS	4
 
 struct nvme_rdma_device {
 	struct ib_device	*dev;
 	struct ib_pd		*pd;
 	struct kref		ref;
 	struct list_head	entry;
+	unsigned int		num_inline_segments;
 };
 
 struct nvme_rdma_qe {
@@ -117,6 +118,7 @@ struct nvme_rdma_ctrl {
 	struct sockaddr_storage src_addr;
 
 	struct nvme_ctrl	ctrl;
+	bool			use_inline_data;
 };
 
 static inline struct nvme_rdma_ctrl *to_rdma_ctrl(struct nvme_ctrl *ctrl)
@@ -249,7 +251,7 @@ static int nvme_rdma_create_qp(struct nvme_rdma_queue *queue, const int factor)
 	/* +1 for drain */
 	init_attr.cap.max_recv_wr = queue->queue_size + 1;
 	init_attr.cap.max_recv_sge = 1;
-	init_attr.cap.max_send_sge = 1 + NVME_RDMA_MAX_INLINE_SEGMENTS;
+	init_attr.cap.max_send_sge = 1 + dev->num_inline_segments;
 	init_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
 	init_attr.qp_type = IB_QPT_RC;
 	init_attr.send_cq = queue->ib_cq;
@@ -286,6 +288,7 @@ static int nvme_rdma_init_request(struct blk_mq_tag_set *set,
 	struct ib_device *ibdev = dev->dev;
 	int ret;
 
+	nvme_req(rq)->ctrl = &ctrl->ctrl;
 	ret = nvme_rdma_alloc_qe(ibdev, &req->sqe, sizeof(struct nvme_command),
 			DMA_TO_DEVICE);
 	if (ret)
@@ -374,6 +377,8 @@ nvme_rdma_find_get_device(struct rdma_cm_id *cm_id)
 		goto out_free_pd;
 	}
 
+	ndev->num_inline_segments = min(NVME_RDMA_MAX_INLINE_SEGMENTS,
+					ndev->dev->attrs.max_send_sge - 1);
 	list_add(&ndev->entry, &device_list);
 out_unlock:
 	mutex_unlock(&device_list_mutex);
@@ -868,6 +873,31 @@ out_free_io_queues:
 	return ret;
 }
 
+static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
+		bool remove)
+{
+	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+	nvme_rdma_stop_queue(&ctrl->queues[0]);
+	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set, nvme_cancel_request,
+			&ctrl->ctrl);
+	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+	nvme_rdma_destroy_admin_queue(ctrl, remove);
+}
+
+static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
+		bool remove)
+{
+	if (ctrl->ctrl.queue_count > 1) {
+		nvme_stop_queues(&ctrl->ctrl);
+		nvme_rdma_stop_io_queues(ctrl);
+		blk_mq_tagset_busy_iter(&ctrl->tag_set, nvme_cancel_request,
+				&ctrl->ctrl);
+		if (remove)
+			nvme_start_queues(&ctrl->ctrl);
+		nvme_rdma_destroy_io_queues(ctrl, remove);
+	}
+}
+
 static void nvme_rdma_stop_ctrl(struct nvme_ctrl *nctrl)
 {
 	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
@@ -912,21 +942,44 @@ static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
 	}
 }
 
-static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
+static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
 {
-	struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work),
-			struct nvme_rdma_ctrl, reconnect_work);
+	int ret = -EINVAL;
 	bool changed;
-	int ret;
 
-	++ctrl->ctrl.nr_reconnects;
-
-	ret = nvme_rdma_configure_admin_queue(ctrl, false);
+	ret = nvme_rdma_configure_admin_queue(ctrl, new);
 	if (ret)
-		goto requeue;
+		return ret;
+
+	if (ctrl->ctrl.icdoff) {
+		dev_err(ctrl->ctrl.device, "icdoff is not supported!\n");
+		goto destroy_admin;
+	}
+
+	if (!(ctrl->ctrl.sgls & (1 << 2))) {
+		dev_err(ctrl->ctrl.device,
+			"Mandatory keyed sgls are not supported!\n");
+		goto destroy_admin;
+	}
+
+	if (ctrl->ctrl.opts->queue_size > ctrl->ctrl.sqsize + 1) {
+		dev_warn(ctrl->ctrl.device,
+			"queue_size %zu > ctrl sqsize %u, clamping down\n",
+			ctrl->ctrl.opts->queue_size, ctrl->ctrl.sqsize + 1);
+	}
+
+	if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
+		dev_warn(ctrl->ctrl.device,
+			"sqsize %u > ctrl maxcmd %u, clamping down\n",
+			ctrl->ctrl.sqsize + 1, ctrl->ctrl.maxcmd);
+		ctrl->ctrl.sqsize = ctrl->ctrl.maxcmd - 1;
+	}
+
+	if (ctrl->ctrl.sgls & (1 << 20))
+		ctrl->use_inline_data = true;
 
 	if (ctrl->ctrl.queue_count > 1) {
-		ret = nvme_rdma_configure_io_queues(ctrl, false);
+		ret = nvme_rdma_configure_io_queues(ctrl, new);
 		if (ret)
 			goto destroy_admin;
 	}
@@ -935,10 +988,31 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 	if (!changed) {
 		/* state change failure is ok if we're in DELETING state */
 		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);
-		return;
+		ret = -EINVAL;
+		goto destroy_io;
 	}
 
 	nvme_start_ctrl(&ctrl->ctrl);
+	return 0;
+
+destroy_io:
+	if (ctrl->ctrl.queue_count > 1)
+		nvme_rdma_destroy_io_queues(ctrl, new);
+destroy_admin:
+	nvme_rdma_stop_queue(&ctrl->queues[0]);
+	nvme_rdma_destroy_admin_queue(ctrl, new);
+	return ret;
+}
+
+static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
+{
+	struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work),
+			struct nvme_rdma_ctrl, reconnect_work);
+
+	++ctrl->ctrl.nr_reconnects;
+
+	if (nvme_rdma_setup_ctrl(ctrl, false))
+		goto requeue;
 
 	dev_info(ctrl->ctrl.device, "Successfully reconnected (%d attempts)\n",
 			ctrl->ctrl.nr_reconnects);
@@ -947,9 +1021,6 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 
 	return;
 
-destroy_admin:
-	nvme_rdma_stop_queue(&ctrl->queues[0]);
-	nvme_rdma_destroy_admin_queue(ctrl, false);
 requeue:
 	dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
 			ctrl->ctrl.nr_reconnects);
@@ -962,27 +1033,9 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
 			struct nvme_rdma_ctrl, err_work);
 
 	nvme_stop_keep_alive(&ctrl->ctrl);
-
-	if (ctrl->ctrl.queue_count > 1) {
-		nvme_stop_queues(&ctrl->ctrl);
-		nvme_rdma_stop_io_queues(ctrl);
-		blk_mq_tagset_busy_iter(&ctrl->tag_set,
-					nvme_cancel_request, &ctrl->ctrl);
-		nvme_rdma_destroy_io_queues(ctrl, false);
-	}
-
-	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
-	nvme_rdma_stop_queue(&ctrl->queues[0]);
-	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
-				nvme_cancel_request, &ctrl->ctrl);
-	nvme_rdma_destroy_admin_queue(ctrl, false);
-
-	/*
-	 * queues are not a live anymore, so restart the queues to fail fast
-	 * new IO
-	 */
-	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+	nvme_rdma_teardown_io_queues(ctrl, false);
 	nvme_start_queues(&ctrl->ctrl);
+	nvme_rdma_teardown_admin_queue(ctrl, false);
 
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
 		/* state change failure is ok if we're in DELETING state */
@@ -1089,19 +1142,27 @@ static int nvme_rdma_set_sg_null(struct nvme_command *c)
 }
 
 static int nvme_rdma_map_sg_inline(struct nvme_rdma_queue *queue,
-		struct nvme_rdma_request *req, struct nvme_command *c)
+		struct nvme_rdma_request *req, struct nvme_command *c,
+		int count)
 {
 	struct nvme_sgl_desc *sg = &c->common.dptr.sgl;
+	struct scatterlist *sgl = req->sg_table.sgl;
+	struct ib_sge *sge = &req->sge[1];
+	u32 len = 0;
+	int i;
 
-	req->sge[1].addr = sg_dma_address(req->sg_table.sgl);
-	req->sge[1].length = sg_dma_len(req->sg_table.sgl);
-	req->sge[1].lkey = queue->device->pd->local_dma_lkey;
+	for (i = 0; i < count; i++, sgl++, sge++) {
+		sge->addr = sg_dma_address(sgl);
+		sge->length = sg_dma_len(sgl);
+		sge->lkey = queue->device->pd->local_dma_lkey;
+		len += sge->length;
+	}
 
 	sg->addr = cpu_to_le64(queue->ctrl->ctrl.icdoff);
-	sg->length = cpu_to_le32(sg_dma_len(req->sg_table.sgl));
+	sg->length = cpu_to_le32(len);
 	sg->type = (NVME_SGL_FMT_DATA_DESC << 4) | NVME_SGL_FMT_OFFSET;
 
-	req->num_sge++;
+	req->num_sge += count;
 	return 0;
 }
 
@@ -1194,15 +1255,16 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
 		goto out_free_table;
 	}
 
-	if (count == 1) {
+	if (count <= dev->num_inline_segments) {
 		if (rq_data_dir(rq) == WRITE && nvme_rdma_queue_idx(queue) &&
+		    queue->ctrl->use_inline_data &&
 		    blk_rq_payload_bytes(rq) <=
 				nvme_rdma_inline_data_size(queue)) {
-			ret = nvme_rdma_map_sg_inline(queue, req, c);
+			ret = nvme_rdma_map_sg_inline(queue, req, c, count);
 			goto out;
 		}
 
-		if (dev->pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY) {
+		if (count == 1 && dev->pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY) {
 			ret = nvme_rdma_map_sg_single(queue, req, c);
 			goto out;
 		}
@@ -1573,6 +1635,7 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
 	case RDMA_CM_EVENT_CONNECT_ERROR:
 	case RDMA_CM_EVENT_UNREACHABLE:
 		nvme_rdma_destroy_queue_ib(queue);
+		/* fall through */
 	case RDMA_CM_EVENT_ADDR_ERROR:
 		dev_dbg(queue->ctrl->ctrl.device,
 			"CM error event %d\n", ev->event);
@@ -1735,25 +1798,12 @@ static const struct blk_mq_ops nvme_rdma_admin_mq_ops = {
 
 static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)
 {
-	if (ctrl->ctrl.queue_count > 1) {
-		nvme_stop_queues(&ctrl->ctrl);
-		nvme_rdma_stop_io_queues(ctrl);
-		blk_mq_tagset_busy_iter(&ctrl->tag_set,
-					nvme_cancel_request, &ctrl->ctrl);
-		nvme_rdma_destroy_io_queues(ctrl, shutdown);
-	}
-
+	nvme_rdma_teardown_io_queues(ctrl, shutdown);
 	if (shutdown)
 		nvme_shutdown_ctrl(&ctrl->ctrl);
 	else
 		nvme_disable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
-
-	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
-	nvme_rdma_stop_queue(&ctrl->queues[0]);
-	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
-				nvme_cancel_request, &ctrl->ctrl);
-	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
-	nvme_rdma_destroy_admin_queue(ctrl, shutdown);
+	nvme_rdma_teardown_admin_queue(ctrl, shutdown);
 }
 
 static void nvme_rdma_delete_ctrl(struct nvme_ctrl *ctrl)
@@ -1765,8 +1815,6 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
 {
 	struct nvme_rdma_ctrl *ctrl =
 		container_of(work, struct nvme_rdma_ctrl, ctrl.reset_work);
-	int ret;
-	bool changed;
 
 	nvme_stop_ctrl(&ctrl->ctrl);
 	nvme_rdma_shutdown_ctrl(ctrl, false);
@@ -1777,25 +1825,9 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
 		return;
 	}
 
-	ret = nvme_rdma_configure_admin_queue(ctrl, false);
-	if (ret)
+	if (nvme_rdma_setup_ctrl(ctrl, false))
 		goto out_fail;
 
-	if (ctrl->ctrl.queue_count > 1) {
-		ret = nvme_rdma_configure_io_queues(ctrl, false);
-		if (ret)
-			goto out_fail;
-	}
-
-	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
-	if (!changed) {
-		/* state change failure is ok if we're in DELETING state */
-		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);
-		return;
-	}
-
-	nvme_start_ctrl(&ctrl->ctrl);
-
 	return;
 
 out_fail:
@@ -1958,49 +1990,10 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING);
 	WARN_ON_ONCE(!changed);
 
-	ret = nvme_rdma_configure_admin_queue(ctrl, true);
+	ret = nvme_rdma_setup_ctrl(ctrl, true);
 	if (ret)
 		goto out_uninit_ctrl;
 
-	/* sanity check icdoff */
-	if (ctrl->ctrl.icdoff) {
-		dev_err(ctrl->ctrl.device, "icdoff is not supported!\n");
-		ret = -EINVAL;
-		goto out_remove_admin_queue;
-	}
-
-	/* sanity check keyed sgls */
-	if (!(ctrl->ctrl.sgls & (1 << 2))) {
-		dev_err(ctrl->ctrl.device,
-			"Mandatory keyed sgls are not supported!\n");
-		ret = -EINVAL;
-		goto out_remove_admin_queue;
-	}
-
-	/* only warn if argument is too large here, will clamp later */
-	if (opts->queue_size > ctrl->ctrl.sqsize + 1) {
-		dev_warn(ctrl->ctrl.device,
-			"queue_size %zu > ctrl sqsize %u, clamping down\n",
-			opts->queue_size, ctrl->ctrl.sqsize + 1);
-	}
-
-	/* warn if maxcmd is lower than sqsize+1 */
-	if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
-		dev_warn(ctrl->ctrl.device,
-			"sqsize %u > ctrl maxcmd %u, clamping down\n",
-			ctrl->ctrl.sqsize + 1, ctrl->ctrl.maxcmd);
-		ctrl->ctrl.sqsize = ctrl->ctrl.maxcmd - 1;
-	}
-
-	if (opts->nr_io_queues) {
-		ret = nvme_rdma_configure_io_queues(ctrl, true);
-		if (ret)
-			goto out_remove_admin_queue;
-	}
-
-	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
-	WARN_ON_ONCE(!changed);
-
 	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n",
 		ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
 
@@ -2010,13 +2003,8 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list);
 	mutex_unlock(&nvme_rdma_ctrl_mutex);
 
-	nvme_start_ctrl(&ctrl->ctrl);
-
 	return &ctrl->ctrl;
 
-out_remove_admin_queue:
-	nvme_rdma_stop_queue(&ctrl->queues[0]);
-	nvme_rdma_destroy_admin_queue(ctrl, true);
 out_uninit_ctrl:
 	nvme_uninit_ctrl(&ctrl->ctrl);
 	nvme_put_ctrl(&ctrl->ctrl);
diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c
index 41944bbef835..25b0e310f4a8 100644
--- a/drivers/nvme/host/trace.c
+++ b/drivers/nvme/host/trace.c
@@ -128,3 +128,14 @@ const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p,
 		return nvme_trace_common(p, cdw10);
 	}
 }
+
+const char *nvme_trace_disk_name(struct trace_seq *p, char *name)
+{
+	const char *ret = trace_seq_buffer_ptr(p);
+
+	if (*name)
+		trace_seq_printf(p, "disk=%s, ", name);
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h
index 01390f0e1671..a490790d6691 100644
--- a/drivers/nvme/host/trace.h
+++ b/drivers/nvme/host/trace.h
@@ -50,13 +50,8 @@
 		nvme_admin_opcode_name(nvme_admin_security_recv),	\
 		nvme_admin_opcode_name(nvme_admin_sanitize_nvm))
 
-const char *nvme_trace_parse_admin_cmd(struct trace_seq *p, u8 opcode,
-				       u8 *cdw10);
-#define __parse_nvme_admin_cmd(opcode, cdw10) \
-	nvme_trace_parse_admin_cmd(p, opcode, cdw10)
-
 #define nvme_opcode_name(opcode)	{ opcode, #opcode }
-#define show_opcode_name(val)					\
+#define show_nvm_opcode_name(val)				\
 	__print_symbolic(val,					\
 		nvme_opcode_name(nvme_cmd_flush),		\
 		nvme_opcode_name(nvme_cmd_write),		\
@@ -70,85 +65,92 @@ const char *nvme_trace_parse_admin_cmd(struct trace_seq *p, u8 opcode,
 		nvme_opcode_name(nvme_cmd_resv_acquire),	\
 		nvme_opcode_name(nvme_cmd_resv_release))
 
-const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p, u8 opcode,
-				     u8 *cdw10);
-#define __parse_nvme_cmd(opcode, cdw10) \
-	nvme_trace_parse_nvm_cmd(p, opcode, cdw10)
-
-TRACE_EVENT(nvme_setup_admin_cmd,
-	    TP_PROTO(struct nvme_command *cmd),
-	    TP_ARGS(cmd),
-	    TP_STRUCT__entry(
-		    __field(u8, opcode)
-		    __field(u8, flags)
-		    __field(u16, cid)
-		    __field(u64, metadata)
-		    __array(u8, cdw10, 24)
-	    ),
-	    TP_fast_assign(
-		    __entry->opcode = cmd->common.opcode;
-		    __entry->flags = cmd->common.flags;
-		    __entry->cid = cmd->common.command_id;
-		    __entry->metadata = le64_to_cpu(cmd->common.metadata);
-		    memcpy(__entry->cdw10, cmd->common.cdw10,
-			   sizeof(__entry->cdw10));
-	    ),
-	    TP_printk(" cmdid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
-		      __entry->cid, __entry->flags, __entry->metadata,
-		      show_admin_opcode_name(__entry->opcode),
-		      __parse_nvme_admin_cmd(__entry->opcode, __entry->cdw10))
-);
-
+#define show_opcode_name(qid, opcode)					\
+	(qid ? show_nvm_opcode_name(opcode) : show_admin_opcode_name(opcode))
 
-TRACE_EVENT(nvme_setup_nvm_cmd,
-	    TP_PROTO(int qid, struct nvme_command *cmd),
-	    TP_ARGS(qid, cmd),
+const char *nvme_trace_parse_admin_cmd(struct trace_seq *p, u8 opcode,
+		u8 *cdw10);
+const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p, u8 opcode,
+		u8 *cdw10);
+
+#define parse_nvme_cmd(qid, opcode, cdw10) 			\
+	(qid ?							\
+	 nvme_trace_parse_nvm_cmd(p, opcode, cdw10) : 		\
+	 nvme_trace_parse_admin_cmd(p, opcode, cdw10))
+
+const char *nvme_trace_disk_name(struct trace_seq *p, char *name);
+#define __print_disk_name(name)				\
+	nvme_trace_disk_name(p, name)
+
+#ifndef TRACE_HEADER_MULTI_READ
+static inline void __assign_disk_name(char *name, struct gendisk *disk)
+{
+	if (disk)
+		memcpy(name, disk->disk_name, DISK_NAME_LEN);
+	else
+		memset(name, 0, DISK_NAME_LEN);
+}
+#endif
+
+TRACE_EVENT(nvme_setup_cmd,
+	    TP_PROTO(struct request *req, struct nvme_command *cmd),
+	    TP_ARGS(req, cmd),
 	    TP_STRUCT__entry(
-		    __field(int, qid)
-		    __field(u8, opcode)
-		    __field(u8, flags)
-		    __field(u16, cid)
-		    __field(u32, nsid)
-		    __field(u64, metadata)
-		    __array(u8, cdw10, 24)
+		__array(char, disk, DISK_NAME_LEN)
+		__field(int, ctrl_id)
+		__field(int, qid)
+		__field(u8, opcode)
+		__field(u8, flags)
+		__field(u16, cid)
+		__field(u32, nsid)
+		__field(u64, metadata)
+		__array(u8, cdw10, 24)
 	    ),
 	    TP_fast_assign(
-		    __entry->qid = qid;
-		    __entry->opcode = cmd->common.opcode;
-		    __entry->flags = cmd->common.flags;
-		    __entry->cid = cmd->common.command_id;
-		    __entry->nsid = le32_to_cpu(cmd->common.nsid);
-		    __entry->metadata = le64_to_cpu(cmd->common.metadata);
-		    memcpy(__entry->cdw10, cmd->common.cdw10,
-			   sizeof(__entry->cdw10));
+		__entry->ctrl_id = nvme_req(req)->ctrl->instance;
+		__entry->qid = nvme_req_qid(req);
+		__entry->opcode = cmd->common.opcode;
+		__entry->flags = cmd->common.flags;
+		__entry->cid = cmd->common.command_id;
+		__entry->nsid = le32_to_cpu(cmd->common.nsid);
+		__entry->metadata = le64_to_cpu(cmd->common.metadata);
+		__assign_disk_name(__entry->disk, req->rq_disk);
+		memcpy(__entry->cdw10, cmd->common.cdw10,
+		       sizeof(__entry->cdw10));
 	    ),
-	    TP_printk("qid=%d, nsid=%u, cmdid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
-		      __entry->qid, __entry->nsid, __entry->cid,
+	    TP_printk("nvme%d: %sqid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
+		      __entry->ctrl_id, __print_disk_name(__entry->disk),
+		      __entry->qid, __entry->cid, __entry->nsid,
 		      __entry->flags, __entry->metadata,
-		      show_opcode_name(__entry->opcode),
-		      __parse_nvme_cmd(__entry->opcode, __entry->cdw10))
+		      show_opcode_name(__entry->qid, __entry->opcode),
+		      parse_nvme_cmd(__entry->qid, __entry->opcode, __entry->cdw10))
 );
 
 TRACE_EVENT(nvme_complete_rq,
 	    TP_PROTO(struct request *req),
 	    TP_ARGS(req),
 	    TP_STRUCT__entry(
-		    __field(int, qid)
-		    __field(int, cid)
-		    __field(u64, result)
-		    __field(u8, retries)
-		    __field(u8, flags)
-		    __field(u16, status)
+		__array(char, disk, DISK_NAME_LEN)
+		__field(int, ctrl_id)
+		__field(int, qid)
+		__field(int, cid)
+		__field(u64, result)
+		__field(u8, retries)
+		__field(u8, flags)
+		__field(u16, status)
 	    ),
 	    TP_fast_assign(
-		    __entry->qid = req->q->id;
-		    __entry->cid = req->tag;
-		    __entry->result = le64_to_cpu(nvme_req(req)->result.u64);
-		    __entry->retries = nvme_req(req)->retries;
-		    __entry->flags = nvme_req(req)->flags;
-		    __entry->status = nvme_req(req)->status;
+		__entry->ctrl_id = nvme_req(req)->ctrl->instance;
+		__entry->qid = nvme_req_qid(req);
+		__entry->cid = req->tag;
+		__entry->result = le64_to_cpu(nvme_req(req)->result.u64);
+		__entry->retries = nvme_req(req)->retries;
+		__entry->flags = nvme_req(req)->flags;
+		__entry->status = nvme_req(req)->status;
+		__assign_disk_name(__entry->disk, req->rq_disk);
 	    ),
-	    TP_printk("qid=%d, cmdid=%u, res=%llu, retries=%u, flags=0x%x, status=%u",
+	    TP_printk("nvme%d: %sqid=%d, cmdid=%u, res=%llu, retries=%u, flags=0x%x, status=%u",
+		      __entry->ctrl_id, __print_disk_name(__entry->disk),
 		      __entry->qid, __entry->cid, __entry->result,
 		      __entry->retries, __entry->flags, __entry->status)
 
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 38803576d5e1..a21caea1e080 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -19,6 +19,19 @@
 #include <asm/unaligned.h>
 #include "nvmet.h"
 
+/*
+ * This helper allows us to clear the AEN based on the RAE bit,
+ * Please use this helper when processing the log pages which are
+ * associated with the AEN.
+ */
+static inline void nvmet_clear_aen(struct nvmet_req *req, u32 aen_bit)
+{
+	int rae = le32_to_cpu(req->cmd->common.cdw10[0]) & 1 << 15;
+
+	if (!rae)
+		clear_bit(aen_bit, &req->sq->ctrl->aen_masked);
+}
+
 u32 nvmet_get_log_page_len(struct nvme_command *cmd)
 {
 	u32 len = le16_to_cpu(cmd->get_log_page.numdu);
@@ -128,6 +141,36 @@ out:
 	nvmet_req_complete(req, status);
 }
 
+static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req)
+{
+	u16 status = NVME_SC_INTERNAL;
+	struct nvme_effects_log *log;
+
+	log = kzalloc(sizeof(*log), GFP_KERNEL);
+	if (!log)
+		goto out;
+
+	log->acs[nvme_admin_get_log_page]	= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_identify]		= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_abort_cmd]		= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_set_features]	= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_get_features]	= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_async_event]	= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_keep_alive]		= cpu_to_le32(1 << 0);
+
+	log->iocs[nvme_cmd_read]		= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_write]		= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_flush]		= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_dsm]			= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_write_zeroes]	= cpu_to_le32(1 << 0);
+
+	status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log));
+
+	kfree(log);
+out:
+	nvmet_req_complete(req, status);
+}
+
 static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req)
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
@@ -146,12 +189,76 @@ static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req)
 	if (!status)
 		status = nvmet_zero_sgl(req, len, req->data_len - len);
 	ctrl->nr_changed_ns = 0;
-	clear_bit(NVME_AEN_CFG_NS_ATTR, &ctrl->aen_masked);
+	nvmet_clear_aen(req, NVME_AEN_CFG_NS_ATTR);
 	mutex_unlock(&ctrl->lock);
 out:
 	nvmet_req_complete(req, status);
 }
 
+static u32 nvmet_format_ana_group(struct nvmet_req *req, u32 grpid,
+		struct nvme_ana_group_desc *desc)
+{
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+	struct nvmet_ns *ns;
+	u32 count = 0;
+
+	if (!(req->cmd->get_log_page.lsp & NVME_ANA_LOG_RGO)) {
+		rcu_read_lock();
+		list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link)
+			if (ns->anagrpid == grpid)
+				desc->nsids[count++] = cpu_to_le32(ns->nsid);
+		rcu_read_unlock();
+	}
+
+	desc->grpid = cpu_to_le32(grpid);
+	desc->nnsids = cpu_to_le32(count);
+	desc->chgcnt = cpu_to_le64(nvmet_ana_chgcnt);
+	desc->state = req->port->ana_state[grpid];
+	memset(desc->rsvd17, 0, sizeof(desc->rsvd17));
+	return sizeof(struct nvme_ana_group_desc) + count * sizeof(__le32);
+}
+
+static void nvmet_execute_get_log_page_ana(struct nvmet_req *req)
+{
+	struct nvme_ana_rsp_hdr hdr = { 0, };
+	struct nvme_ana_group_desc *desc;
+	size_t offset = sizeof(struct nvme_ana_rsp_hdr); /* start beyond hdr */
+	size_t len;
+	u32 grpid;
+	u16 ngrps = 0;
+	u16 status;
+
+	status = NVME_SC_INTERNAL;
+	desc = kmalloc(sizeof(struct nvme_ana_group_desc) +
+			NVMET_MAX_NAMESPACES * sizeof(__le32), GFP_KERNEL);
+	if (!desc)
+		goto out;
+
+	down_read(&nvmet_ana_sem);
+	for (grpid = 1; grpid <= NVMET_MAX_ANAGRPS; grpid++) {
+		if (!nvmet_ana_group_enabled[grpid])
+			continue;
+		len = nvmet_format_ana_group(req, grpid, desc);
+		status = nvmet_copy_to_sgl(req, offset, desc, len);
+		if (status)
+			break;
+		offset += len;
+		ngrps++;
+	}
+
+	hdr.chgcnt = cpu_to_le64(nvmet_ana_chgcnt);
+	hdr.ngrps = cpu_to_le16(ngrps);
+	nvmet_clear_aen(req, NVME_AEN_CFG_ANA_CHANGE);
+	up_read(&nvmet_ana_sem);
+
+	kfree(desc);
+
+	/* copy the header last once we know the number of groups */
+	status = nvmet_copy_to_sgl(req, 0, &hdr, sizeof(hdr));
+out:
+	nvmet_req_complete(req, status);
+}
+
 static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
@@ -183,8 +290,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	 * the safest is to leave it as zeroes.
 	 */
 
-	/* we support multiple ports and multiples hosts: */
-	id->cmic = (1 << 0) | (1 << 1);
+	/* we support multiple ports, multiples hosts and ANA: */
+	id->cmic = (1 << 0) | (1 << 1) | (1 << 3);
 
 	/* no limit on data transfer sizes for now */
 	id->mdts = 0;
@@ -208,7 +315,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 
 	/* first slot is read-only, only one slot supported */
 	id->frmw = (1 << 0) | (1 << 1);
-	id->lpa = (1 << 0) | (1 << 2);
+	id->lpa = (1 << 0) | (1 << 1) | (1 << 2);
 	id->elpe = NVMET_ERROR_LOG_SLOTS - 1;
 	id->npss = 0;
 
@@ -222,6 +329,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
 
 	id->nn = cpu_to_le32(ctrl->subsys->max_nsid);
+	id->mnan = cpu_to_le32(NVMET_MAX_NAMESPACES);
 	id->oncs = cpu_to_le16(NVME_CTRL_ONCS_DSM |
 			NVME_CTRL_ONCS_WRITE_ZEROES);
 
@@ -238,19 +346,24 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->sgls = cpu_to_le32(1 << 0);	/* we always support SGLs */
 	if (ctrl->ops->has_keyed_sgls)
 		id->sgls |= cpu_to_le32(1 << 2);
-	if (ctrl->ops->sqe_inline_size)
+	if (req->port->inline_data_size)
 		id->sgls |= cpu_to_le32(1 << 20);
 
 	strcpy(id->subnqn, ctrl->subsys->subsysnqn);
 
 	/* Max command capsule size is sqe + single page of in-capsule data */
 	id->ioccsz = cpu_to_le32((sizeof(struct nvme_command) +
-				  ctrl->ops->sqe_inline_size) / 16);
+				  req->port->inline_data_size) / 16);
 	/* Max response capsule size is cqe */
 	id->iorcsz = cpu_to_le32(sizeof(struct nvme_completion) / 16);
 
 	id->msdbd = ctrl->ops->msdbd;
 
+	id->anacap = (1 << 0) | (1 << 1) | (1 << 2) | (1 << 3) | (1 << 4);
+	id->anatt = 10; /* random value */
+	id->anagrpmax = cpu_to_le32(NVMET_MAX_ANAGRPS);
+	id->nanagrpid = cpu_to_le32(NVMET_MAX_ANAGRPS);
+
 	/*
 	 * Meh, we don't really support any power state.  Fake up the same
 	 * values that qemu does.
@@ -259,6 +372,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->psd[0].entry_lat = cpu_to_le32(0x10);
 	id->psd[0].exit_lat = cpu_to_le32(0x4);
 
+	id->nwpc = 1 << 0; /* write protect and no write protect */
+
 	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
 
 	kfree(id);
@@ -292,8 +407,15 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 	 * nuse = ncap = nsze isn't always true, but we have no way to find
 	 * that out from the underlying device.
 	 */
-	id->ncap = id->nuse = id->nsze =
-		cpu_to_le64(ns->size >> ns->blksize_shift);
+	id->ncap = id->nsze = cpu_to_le64(ns->size >> ns->blksize_shift);
+	switch (req->port->ana_state[ns->anagrpid]) {
+	case NVME_ANA_INACCESSIBLE:
+	case NVME_ANA_PERSISTENT_LOSS:
+		break;
+	default:
+		id->nuse = id->nsze;
+		break;
+        }
 
 	/*
 	 * We just provide a single LBA format that matches what the
@@ -307,11 +429,14 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 	 * controllers, but also with any other user of the block device.
 	 */
 	id->nmic = (1 << 0);
+	id->anagrpid = cpu_to_le32(ns->anagrpid);
 
-	memcpy(&id->nguid, &ns->nguid, sizeof(uuid_le));
+	memcpy(&id->nguid, &ns->nguid, sizeof(id->nguid));
 
 	id->lbaf[0].ds = ns->blksize_shift;
 
+	if (ns->readonly)
+		id->nsattr |= (1 << 0);
 	nvmet_put_namespace(ns);
 done:
 	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
@@ -424,6 +549,52 @@ static void nvmet_execute_abort(struct nvmet_req *req)
 	nvmet_req_complete(req, 0);
 }
 
+static u16 nvmet_write_protect_flush_sync(struct nvmet_req *req)
+{
+	u16 status;
+
+	if (req->ns->file)
+		status = nvmet_file_flush(req);
+	else
+		status = nvmet_bdev_flush(req);
+
+	if (status)
+		pr_err("write protect flush failed nsid: %u\n", req->ns->nsid);
+	return status;
+}
+
+static u16 nvmet_set_feat_write_protect(struct nvmet_req *req)
+{
+	u32 write_protect = le32_to_cpu(req->cmd->common.cdw10[1]);
+	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
+	u16 status = NVME_SC_FEATURE_NOT_CHANGEABLE;
+
+	req->ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->rw.nsid);
+	if (unlikely(!req->ns))
+		return status;
+
+	mutex_lock(&subsys->lock);
+	switch (write_protect) {
+	case NVME_NS_WRITE_PROTECT:
+		req->ns->readonly = true;
+		status = nvmet_write_protect_flush_sync(req);
+		if (status)
+			req->ns->readonly = false;
+		break;
+	case NVME_NS_NO_WRITE_PROTECT:
+		req->ns->readonly = false;
+		status = 0;
+		break;
+	default:
+		break;
+	}
+
+	if (!status)
+		nvmet_ns_changed(subsys, req->ns->nsid);
+	mutex_unlock(&subsys->lock);
+	return status;
+}
+
 static void nvmet_execute_set_features(struct nvmet_req *req)
 {
 	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
@@ -454,6 +625,9 @@ static void nvmet_execute_set_features(struct nvmet_req *req)
 	case NVME_FEAT_HOST_ID:
 		status = NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
 		break;
+	case NVME_FEAT_WRITE_PROTECT:
+		status = nvmet_set_feat_write_protect(req);
+		break;
 	default:
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		break;
@@ -462,6 +636,26 @@ static void nvmet_execute_set_features(struct nvmet_req *req)
 	nvmet_req_complete(req, status);
 }
 
+static u16 nvmet_get_feat_write_protect(struct nvmet_req *req)
+{
+	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
+	u32 result;
+
+	req->ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->common.nsid);
+	if (!req->ns)
+		return NVME_SC_INVALID_NS | NVME_SC_DNR;
+
+	mutex_lock(&subsys->lock);
+	if (req->ns->readonly == true)
+		result = NVME_NS_WRITE_PROTECT;
+	else
+		result = NVME_NS_NO_WRITE_PROTECT;
+	nvmet_set_result(req, result);
+	mutex_unlock(&subsys->lock);
+
+	return 0;
+}
+
 static void nvmet_execute_get_features(struct nvmet_req *req)
 {
 	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
@@ -513,6 +707,9 @@ static void nvmet_execute_get_features(struct nvmet_req *req)
 		status = nvmet_copy_to_sgl(req, 0, &req->sq->ctrl->hostid,
 				sizeof(req->sq->ctrl->hostid));
 		break;
+	case NVME_FEAT_WRITE_PROTECT:
+		status = nvmet_get_feat_write_protect(req);
+		break;
 	default:
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		break;
@@ -586,6 +783,12 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 		case NVME_LOG_CHANGED_NS:
 			req->execute = nvmet_execute_get_log_changed_ns;
 			return 0;
+		case NVME_LOG_CMD_EFFECTS:
+			req->execute = nvmet_execute_get_log_cmd_effects_ns;
+			return 0;
+		case NVME_LOG_ANA:
+			req->execute = nvmet_execute_get_log_page_ana;
+			return 0;
 		}
 		break;
 	case nvme_admin_identify:
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index ebea1373d1b7..b37a8e3e3f80 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -218,6 +218,35 @@ static ssize_t nvmet_addr_trsvcid_store(struct config_item *item,
 
 CONFIGFS_ATTR(nvmet_, addr_trsvcid);
 
+static ssize_t nvmet_param_inline_data_size_show(struct config_item *item,
+		char *page)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	return snprintf(page, PAGE_SIZE, "%d\n", port->inline_data_size);
+}
+
+static ssize_t nvmet_param_inline_data_size_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+	int ret;
+
+	if (port->enabled) {
+		pr_err("Cannot modify inline_data_size while port enabled\n");
+		pr_err("Disable the port before modifying\n");
+		return -EACCES;
+	}
+	ret = kstrtoint(page, 0, &port->inline_data_size);
+	if (ret) {
+		pr_err("Invalid value '%s' for inline_data_size\n", page);
+		return -EINVAL;
+	}
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_, param_inline_data_size);
+
 static ssize_t nvmet_addr_trtype_show(struct config_item *item,
 		char *page)
 {
@@ -387,6 +416,39 @@ out_unlock:
 
 CONFIGFS_ATTR(nvmet_ns_, device_nguid);
 
+static ssize_t nvmet_ns_ana_grpid_show(struct config_item *item, char *page)
+{
+	return sprintf(page, "%u\n", to_nvmet_ns(item)->anagrpid);
+}
+
+static ssize_t nvmet_ns_ana_grpid_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_ns *ns = to_nvmet_ns(item);
+	u32 oldgrpid, newgrpid;
+	int ret;
+
+	ret = kstrtou32(page, 0, &newgrpid);
+	if (ret)
+		return ret;
+
+	if (newgrpid < 1 || newgrpid > NVMET_MAX_ANAGRPS)
+		return -EINVAL;
+
+	down_write(&nvmet_ana_sem);
+	oldgrpid = ns->anagrpid;
+	nvmet_ana_group_enabled[newgrpid]++;
+	ns->anagrpid = newgrpid;
+	nvmet_ana_group_enabled[oldgrpid]--;
+	nvmet_ana_chgcnt++;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_send_ana_event(ns->subsys, NULL);
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_ns_, ana_grpid);
+
 static ssize_t nvmet_ns_enable_show(struct config_item *item, char *page)
 {
 	return sprintf(page, "%d\n", to_nvmet_ns(item)->enabled);
@@ -412,11 +474,41 @@ static ssize_t nvmet_ns_enable_store(struct config_item *item,
 
 CONFIGFS_ATTR(nvmet_ns_, enable);
 
+static ssize_t nvmet_ns_buffered_io_show(struct config_item *item, char *page)
+{
+	return sprintf(page, "%d\n", to_nvmet_ns(item)->buffered_io);
+}
+
+static ssize_t nvmet_ns_buffered_io_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_ns *ns = to_nvmet_ns(item);
+	bool val;
+
+	if (strtobool(page, &val))
+		return -EINVAL;
+
+	mutex_lock(&ns->subsys->lock);
+	if (ns->enabled) {
+		pr_err("disable ns before setting buffered_io value.\n");
+		mutex_unlock(&ns->subsys->lock);
+		return -EINVAL;
+	}
+
+	ns->buffered_io = val;
+	mutex_unlock(&ns->subsys->lock);
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_ns_, buffered_io);
+
 static struct configfs_attribute *nvmet_ns_attrs[] = {
 	&nvmet_ns_attr_device_path,
 	&nvmet_ns_attr_device_nguid,
 	&nvmet_ns_attr_device_uuid,
+	&nvmet_ns_attr_ana_grpid,
 	&nvmet_ns_attr_enable,
+	&nvmet_ns_attr_buffered_io,
 	NULL,
 };
 
@@ -863,6 +955,134 @@ static const struct config_item_type nvmet_referrals_type = {
 	.ct_group_ops	= &nvmet_referral_group_ops,
 };
 
+static struct {
+	enum nvme_ana_state	state;
+	const char		*name;
+} nvmet_ana_state_names[] = {
+	{ NVME_ANA_OPTIMIZED,		"optimized" },
+	{ NVME_ANA_NONOPTIMIZED,	"non-optimized" },
+	{ NVME_ANA_INACCESSIBLE,	"inaccessible" },
+	{ NVME_ANA_PERSISTENT_LOSS,	"persistent-loss" },
+	{ NVME_ANA_CHANGE,		"change" },
+};
+
+static ssize_t nvmet_ana_group_ana_state_show(struct config_item *item,
+		char *page)
+{
+	struct nvmet_ana_group *grp = to_ana_group(item);
+	enum nvme_ana_state state = grp->port->ana_state[grp->grpid];
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(nvmet_ana_state_names); i++) {
+		if (state != nvmet_ana_state_names[i].state)
+			continue;
+		return sprintf(page, "%s\n", nvmet_ana_state_names[i].name);
+	}
+
+	return sprintf(page, "\n");
+}
+
+static ssize_t nvmet_ana_group_ana_state_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_ana_group *grp = to_ana_group(item);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(nvmet_ana_state_names); i++) {
+		if (sysfs_streq(page, nvmet_ana_state_names[i].name))
+			goto found;
+	}
+
+	pr_err("Invalid value '%s' for ana_state\n", page);
+	return -EINVAL;
+
+found:
+	down_write(&nvmet_ana_sem);
+	grp->port->ana_state[grp->grpid] = nvmet_ana_state_names[i].state;
+	nvmet_ana_chgcnt++;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_port_send_ana_event(grp->port);
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_ana_group_, ana_state);
+
+static struct configfs_attribute *nvmet_ana_group_attrs[] = {
+	&nvmet_ana_group_attr_ana_state,
+	NULL,
+};
+
+static void nvmet_ana_group_release(struct config_item *item)
+{
+	struct nvmet_ana_group *grp = to_ana_group(item);
+
+	if (grp == &grp->port->ana_default_group)
+		return;
+
+	down_write(&nvmet_ana_sem);
+	grp->port->ana_state[grp->grpid] = NVME_ANA_INACCESSIBLE;
+	nvmet_ana_group_enabled[grp->grpid]--;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_port_send_ana_event(grp->port);
+	kfree(grp);
+}
+
+static struct configfs_item_operations nvmet_ana_group_item_ops = {
+	.release		= nvmet_ana_group_release,
+};
+
+static const struct config_item_type nvmet_ana_group_type = {
+	.ct_item_ops		= &nvmet_ana_group_item_ops,
+	.ct_attrs		= nvmet_ana_group_attrs,
+	.ct_owner		= THIS_MODULE,
+};
+
+static struct config_group *nvmet_ana_groups_make_group(
+		struct config_group *group, const char *name)
+{
+	struct nvmet_port *port = ana_groups_to_port(&group->cg_item);
+	struct nvmet_ana_group *grp;
+	u32 grpid;
+	int ret;
+
+	ret = kstrtou32(name, 0, &grpid);
+	if (ret)
+		goto out;
+
+	ret = -EINVAL;
+	if (grpid <= 1 || grpid > NVMET_MAX_ANAGRPS)
+		goto out;
+
+	ret = -ENOMEM;
+	grp = kzalloc(sizeof(*grp), GFP_KERNEL);
+	if (!grp)
+		goto out;
+	grp->port = port;
+	grp->grpid = grpid;
+
+	down_write(&nvmet_ana_sem);
+	nvmet_ana_group_enabled[grpid]++;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_port_send_ana_event(grp->port);
+
+	config_group_init_type_name(&grp->group, name, &nvmet_ana_group_type);
+	return &grp->group;
+out:
+	return ERR_PTR(ret);
+}
+
+static struct configfs_group_operations nvmet_ana_groups_group_ops = {
+	.make_group		= nvmet_ana_groups_make_group,
+};
+
+static const struct config_item_type nvmet_ana_groups_type = {
+	.ct_group_ops		= &nvmet_ana_groups_group_ops,
+	.ct_owner		= THIS_MODULE,
+};
+
 /*
  * Ports definitions.
  */
@@ -870,6 +1090,7 @@ static void nvmet_port_release(struct config_item *item)
 {
 	struct nvmet_port *port = to_nvmet_port(item);
 
+	kfree(port->ana_state);
 	kfree(port);
 }
 
@@ -879,6 +1100,7 @@ static struct configfs_attribute *nvmet_port_attrs[] = {
 	&nvmet_attr_addr_traddr,
 	&nvmet_attr_addr_trsvcid,
 	&nvmet_attr_addr_trtype,
+	&nvmet_attr_param_inline_data_size,
 	NULL,
 };
 
@@ -897,6 +1119,7 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 {
 	struct nvmet_port *port;
 	u16 portid;
+	u32 i;
 
 	if (kstrtou16(name, 0, &portid))
 		return ERR_PTR(-EINVAL);
@@ -905,9 +1128,24 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 	if (!port)
 		return ERR_PTR(-ENOMEM);
 
+	port->ana_state = kcalloc(NVMET_MAX_ANAGRPS + 1,
+			sizeof(*port->ana_state), GFP_KERNEL);
+	if (!port->ana_state) {
+		kfree(port);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	for (i = 1; i <= NVMET_MAX_ANAGRPS; i++) {
+		if (i == NVMET_DEFAULT_ANA_GRPID)
+			port->ana_state[1] = NVME_ANA_OPTIMIZED;
+		else
+			port->ana_state[i] = NVME_ANA_INACCESSIBLE;
+	}
+
 	INIT_LIST_HEAD(&port->entry);
 	INIT_LIST_HEAD(&port->subsystems);
 	INIT_LIST_HEAD(&port->referrals);
+	port->inline_data_size = -1;	/* < 0 == let the transport choose */
 
 	port->disc_addr.portid = cpu_to_le16(portid);
 	config_group_init_type_name(&port->group, name, &nvmet_port_type);
@@ -920,6 +1158,18 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 			"referrals", &nvmet_referrals_type);
 	configfs_add_default_group(&port->referrals_group, &port->group);
 
+	config_group_init_type_name(&port->ana_groups_group,
+			"ana_groups", &nvmet_ana_groups_type);
+	configfs_add_default_group(&port->ana_groups_group, &port->group);
+
+	port->ana_default_group.port = port;
+	port->ana_default_group.grpid = NVMET_DEFAULT_ANA_GRPID;
+	config_group_init_type_name(&port->ana_default_group.group,
+			__stringify(NVMET_DEFAULT_ANA_GRPID),
+			&nvmet_ana_group_type);
+	configfs_add_default_group(&port->ana_default_group.group,
+			&port->ana_groups_group);
+
 	return &port->group;
 }
 
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 9838103f2d62..ebf3e7a6c49e 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -18,6 +18,7 @@
 
 #include "nvmet.h"
 
+struct workqueue_struct *buffered_io_wq;
 static const struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX];
 static DEFINE_IDA(cntlid_ida);
 
@@ -39,6 +40,10 @@ static DEFINE_IDA(cntlid_ida);
  */
 DECLARE_RWSEM(nvmet_config_sem);
 
+u32 nvmet_ana_group_enabled[NVMET_MAX_ANAGRPS + 1];
+u64 nvmet_ana_chgcnt;
+DECLARE_RWSEM(nvmet_ana_sem);
+
 static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
 		const char *subsysnqn);
 
@@ -175,7 +180,7 @@ out_unlock:
 	mutex_unlock(&ctrl->lock);
 }
 
-static void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
+void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
 {
 	struct nvmet_ctrl *ctrl;
 
@@ -189,6 +194,33 @@ static void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
 	}
 }
 
+void nvmet_send_ana_event(struct nvmet_subsys *subsys,
+		struct nvmet_port *port)
+{
+	struct nvmet_ctrl *ctrl;
+
+	mutex_lock(&subsys->lock);
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
+		if (port && ctrl->port != port)
+			continue;
+		if (nvmet_aen_disabled(ctrl, NVME_AEN_CFG_ANA_CHANGE))
+			continue;
+		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
+				NVME_AER_NOTICE_ANA, NVME_LOG_ANA);
+	}
+	mutex_unlock(&subsys->lock);
+}
+
+void nvmet_port_send_ana_event(struct nvmet_port *port)
+{
+	struct nvmet_subsys_link *p;
+
+	down_read(&nvmet_config_sem);
+	list_for_each_entry(p, &port->subsystems, entry)
+		nvmet_send_ana_event(p->subsys, port);
+	up_read(&nvmet_config_sem);
+}
+
 int nvmet_register_transport(const struct nvmet_fabrics_ops *ops)
 {
 	int ret = 0;
@@ -241,6 +273,10 @@ int nvmet_enable_port(struct nvmet_port *port)
 		return ret;
 	}
 
+	/* If the transport didn't set inline_data_size, then disable it. */
+	if (port->inline_data_size < 0)
+		port->inline_data_size = 0;
+
 	port->enabled = true;
 	return 0;
 }
@@ -332,9 +368,13 @@ static void nvmet_ns_dev_disable(struct nvmet_ns *ns)
 int nvmet_ns_enable(struct nvmet_ns *ns)
 {
 	struct nvmet_subsys *subsys = ns->subsys;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&subsys->lock);
+	ret = -EMFILE;
+	if (subsys->nr_namespaces == NVMET_MAX_NAMESPACES)
+		goto out_unlock;
+	ret = 0;
 	if (ns->enabled)
 		goto out_unlock;
 
@@ -369,6 +409,7 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 
 		list_add_tail_rcu(&ns->dev_link, &old->dev_link);
 	}
+	subsys->nr_namespaces++;
 
 	nvmet_ns_changed(subsys, ns->nsid);
 	ns->enabled = true;
@@ -409,6 +450,7 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
 	percpu_ref_exit(&ns->ref);
 
 	mutex_lock(&subsys->lock);
+	subsys->nr_namespaces--;
 	nvmet_ns_changed(subsys, ns->nsid);
 	nvmet_ns_dev_disable(ns);
 out_unlock:
@@ -419,6 +461,10 @@ void nvmet_ns_free(struct nvmet_ns *ns)
 {
 	nvmet_ns_disable(ns);
 
+	down_write(&nvmet_ana_sem);
+	nvmet_ana_group_enabled[ns->anagrpid]--;
+	up_write(&nvmet_ana_sem);
+
 	kfree(ns->device_path);
 	kfree(ns);
 }
@@ -436,7 +482,14 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
 
 	ns->nsid = nsid;
 	ns->subsys = subsys;
+
+	down_write(&nvmet_ana_sem);
+	ns->anagrpid = NVMET_DEFAULT_ANA_GRPID;
+	nvmet_ana_group_enabled[ns->anagrpid]++;
+	up_write(&nvmet_ana_sem);
+
 	uuid_gen(&ns->uuid);
+	ns->buffered_io = false;
 
 	return ns;
 }
@@ -542,6 +595,35 @@ int nvmet_sq_init(struct nvmet_sq *sq)
 }
 EXPORT_SYMBOL_GPL(nvmet_sq_init);
 
+static inline u16 nvmet_check_ana_state(struct nvmet_port *port,
+		struct nvmet_ns *ns)
+{
+	enum nvme_ana_state state = port->ana_state[ns->anagrpid];
+
+	if (unlikely(state == NVME_ANA_INACCESSIBLE))
+		return NVME_SC_ANA_INACCESSIBLE;
+	if (unlikely(state == NVME_ANA_PERSISTENT_LOSS))
+		return NVME_SC_ANA_PERSISTENT_LOSS;
+	if (unlikely(state == NVME_ANA_CHANGE))
+		return NVME_SC_ANA_TRANSITION;
+	return 0;
+}
+
+static inline u16 nvmet_io_cmd_check_access(struct nvmet_req *req)
+{
+	if (unlikely(req->ns->readonly)) {
+		switch (req->cmd->common.opcode) {
+		case nvme_cmd_read:
+		case nvme_cmd_flush:
+			break;
+		default:
+			return NVME_SC_NS_WRITE_PROTECTED;
+		}
+	}
+
+	return 0;
+}
+
 static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
 {
 	struct nvme_command *cmd = req->cmd;
@@ -554,6 +636,12 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
 	req->ns = nvmet_find_namespace(req->sq->ctrl, cmd->rw.nsid);
 	if (unlikely(!req->ns))
 		return NVME_SC_INVALID_NS | NVME_SC_DNR;
+	ret = nvmet_check_ana_state(req->port, req->ns);
+	if (unlikely(ret))
+		return ret;
+	ret = nvmet_io_cmd_check_access(req);
+	if (unlikely(ret))
+		return ret;
 
 	if (req->ns->file)
 		return nvmet_file_parse_io_cmd(req);
@@ -870,6 +958,8 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 
 	nvmet_init_cap(ctrl);
 
+	ctrl->port = req->port;
+
 	INIT_WORK(&ctrl->async_event_work, nvmet_async_event_work);
 	INIT_LIST_HEAD(&ctrl->async_events);
 
@@ -1109,6 +1199,15 @@ static int __init nvmet_init(void)
 {
 	int error;
 
+	nvmet_ana_group_enabled[NVMET_DEFAULT_ANA_GRPID] = 1;
+
+	buffered_io_wq = alloc_workqueue("nvmet-buffered-io-wq",
+			WQ_MEM_RECLAIM, 0);
+	if (!buffered_io_wq) {
+		error = -ENOMEM;
+		goto out;
+	}
+
 	error = nvmet_init_discovery();
 	if (error)
 		goto out;
@@ -1129,6 +1228,7 @@ static void __exit nvmet_exit(void)
 	nvmet_exit_configfs();
 	nvmet_exit_discovery();
 	ida_destroy(&cntlid_ida);
+	destroy_workqueue(buffered_io_wq);
 
 	BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_entry) != 1024);
 	BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_hdr) != 1024);
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 08656b849bd6..eae29f493a07 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -171,7 +171,7 @@ static void nvmet_execute_identify_disc_ctrl(struct nvmet_req *req)
 	id->sgls = cpu_to_le32(1 << 0);	/* we always support SGLs */
 	if (ctrl->ops->has_keyed_sgls)
 		id->sgls |= cpu_to_le32(1 << 2);
-	if (ctrl->ops->sqe_inline_size)
+	if (req->port->inline_data_size)
 		id->sgls |= cpu_to_le32(1 << 20);
 
 	strcpy(id->subnqn, ctrl->subsys->subsysnqn);
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index e0b0f7df70c2..7bc9f6240432 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -124,6 +124,13 @@ static void nvmet_bdev_execute_flush(struct nvmet_req *req)
 	submit_bio(bio);
 }
 
+u16 nvmet_bdev_flush(struct nvmet_req *req)
+{
+	if (blkdev_issue_flush(req->ns->bdev, GFP_KERNEL, NULL))
+		return NVME_SC_INTERNAL | NVME_SC_DNR;
+	return 0;
+}
+
 static u16 nvmet_bdev_discard_range(struct nvmet_ns *ns,
 		struct nvme_dsm_range *range, struct bio **bio)
 {
diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c
index 8c42b3a8c420..81a9dc5290a8 100644
--- a/drivers/nvme/target/io-cmd-file.c
+++ b/drivers/nvme/target/io-cmd-file.c
@@ -16,6 +16,8 @@
 void nvmet_file_ns_disable(struct nvmet_ns *ns)
 {
 	if (ns->file) {
+		if (ns->buffered_io)
+			flush_workqueue(buffered_io_wq);
 		mempool_destroy(ns->bvec_pool);
 		ns->bvec_pool = NULL;
 		kmem_cache_destroy(ns->bvec_cache);
@@ -27,11 +29,14 @@ void nvmet_file_ns_disable(struct nvmet_ns *ns)
 
 int nvmet_file_ns_enable(struct nvmet_ns *ns)
 {
-	int ret;
+	int flags = O_RDWR | O_LARGEFILE;
 	struct kstat stat;
+	int ret;
+
+	if (!ns->buffered_io)
+		flags |= O_DIRECT;
 
-	ns->file = filp_open(ns->device_path,
-			O_RDWR | O_LARGEFILE | O_DIRECT, 0);
+	ns->file = filp_open(ns->device_path, flags, 0);
 	if (IS_ERR(ns->file)) {
 		pr_err("failed to open file %s: (%ld)\n",
 				ns->device_path, PTR_ERR(ns->file));
@@ -100,7 +105,7 @@ static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos,
 
 	iocb->ki_pos = pos;
 	iocb->ki_filp = req->ns->file;
-	iocb->ki_flags = IOCB_DIRECT | ki_flags;
+	iocb->ki_flags = ki_flags | iocb_flags(req->ns->file);
 
 	ret = call_iter(iocb, &iter);
 
@@ -140,6 +145,12 @@ static void nvmet_file_execute_rw(struct nvmet_req *req)
 		return;
 	}
 
+	pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift;
+	if (unlikely(pos + req->data_len > req->ns->size)) {
+		nvmet_req_complete(req, NVME_SC_LBA_RANGE | NVME_SC_DNR);
+		return;
+	}
+
 	if (nr_bvec > NVMET_MAX_INLINE_BIOVEC)
 		req->f.bvec = kmalloc_array(nr_bvec, sizeof(struct bio_vec),
 				GFP_KERNEL);
@@ -155,8 +166,6 @@ static void nvmet_file_execute_rw(struct nvmet_req *req)
 			is_sync = true;
 	}
 
-	pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift;
-
 	memset(&req->f.iocb, 0, sizeof(struct kiocb));
 	for_each_sg_page(req->sg, &sg_pg_iter, req->sg_cnt, 0) {
 		nvmet_file_init_bvec(&req->f.bvec[bv_cnt], &sg_pg_iter);
@@ -189,14 +198,31 @@ out:
 	nvmet_file_submit_bvec(req, pos, bv_cnt, total_len);
 }
 
-static void nvmet_file_flush_work(struct work_struct *w)
+static void nvmet_file_buffered_io_work(struct work_struct *w)
 {
 	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
-	int ret;
 
-	ret = vfs_fsync(req->ns->file, 1);
+	nvmet_file_execute_rw(req);
+}
 
-	nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+static void nvmet_file_execute_rw_buffered_io(struct nvmet_req *req)
+{
+	INIT_WORK(&req->f.work, nvmet_file_buffered_io_work);
+	queue_work(buffered_io_wq, &req->f.work);
+}
+
+u16 nvmet_file_flush(struct nvmet_req *req)
+{
+	if (vfs_fsync(req->ns->file, 1) < 0)
+		return NVME_SC_INTERNAL | NVME_SC_DNR;
+	return 0;
+}
+
+static void nvmet_file_flush_work(struct work_struct *w)
+{
+	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
+
+	nvmet_req_complete(req, nvmet_file_flush(req));
 }
 
 static void nvmet_file_execute_flush(struct nvmet_req *req)
@@ -209,22 +235,30 @@ static void nvmet_file_execute_discard(struct nvmet_req *req)
 {
 	int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
 	struct nvme_dsm_range range;
-	loff_t offset;
-	loff_t len;
-	int i, ret;
+	loff_t offset, len;
+	u16 ret;
+	int i;
 
 	for (i = 0; i <= le32_to_cpu(req->cmd->dsm.nr); i++) {
-		if (nvmet_copy_from_sgl(req, i * sizeof(range), &range,
-					sizeof(range)))
+		ret = nvmet_copy_from_sgl(req, i * sizeof(range), &range,
+					sizeof(range));
+		if (ret)
 			break;
+
 		offset = le64_to_cpu(range.slba) << req->ns->blksize_shift;
 		len = le32_to_cpu(range.nlb) << req->ns->blksize_shift;
-		ret = vfs_fallocate(req->ns->file, mode, offset, len);
-		if (ret)
+		if (offset + len > req->ns->size) {
+			ret = NVME_SC_LBA_RANGE | NVME_SC_DNR;
 			break;
+		}
+
+		if (vfs_fallocate(req->ns->file, mode, offset, len)) {
+			ret = NVME_SC_INTERNAL | NVME_SC_DNR;
+			break;
+		}
 	}
 
-	nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+	nvmet_req_complete(req, ret);
 }
 
 static void nvmet_file_dsm_work(struct work_struct *w)
@@ -263,6 +297,11 @@ static void nvmet_file_write_zeroes_work(struct work_struct *w)
 	len = (((sector_t)le16_to_cpu(write_zeroes->length) + 1) <<
 			req->ns->blksize_shift);
 
+	if (unlikely(offset + len > req->ns->size)) {
+		nvmet_req_complete(req, NVME_SC_LBA_RANGE | NVME_SC_DNR);
+		return;
+	}
+
 	ret = vfs_fallocate(req->ns->file, mode, offset, len);
 	nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
 }
@@ -280,7 +319,10 @@ u16 nvmet_file_parse_io_cmd(struct nvmet_req *req)
 	switch (cmd->common.opcode) {
 	case nvme_cmd_read:
 	case nvme_cmd_write:
-		req->execute = nvmet_file_execute_rw;
+		if (req->ns->buffered_io)
+			req->execute = nvmet_file_execute_rw_buffered_io;
+		else
+			req->execute = nvmet_file_execute_rw;
 		req->data_len = nvmet_rw_len(req);
 		return 0;
 	case nvme_cmd_flush:
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index ae7586b8be07..9908082b32c4 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -227,6 +227,7 @@ static int nvme_loop_init_request(struct blk_mq_tag_set *set,
 {
 	struct nvme_loop_ctrl *ctrl = set->driver_data;
 
+	nvme_req(req)->ctrl = &ctrl->ctrl;
 	return nvme_loop_init_iod(ctrl, blk_mq_rq_to_pdu(req),
 			(set == &ctrl->tag_set) ? hctx_idx + 1 : 0);
 }
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 480dfe10fad9..ec9af4ee03b6 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -30,12 +30,11 @@
 #define NVMET_ASYNC_EVENTS		4
 #define NVMET_ERROR_LOG_SLOTS		128
 
-
 /*
  * Supported optional AENs:
  */
 #define NVMET_AEN_CFG_OPTIONAL \
-	NVME_AEN_CFG_NS_ATTR
+	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_ANA_CHANGE)
 
 /*
  * Plus mandatory SMART AENs (we'll never send them, but allow enabling them):
@@ -59,12 +58,15 @@ struct nvmet_ns {
 	struct percpu_ref	ref;
 	struct block_device	*bdev;
 	struct file		*file;
+	bool			readonly;
 	u32			nsid;
 	u32			blksize_shift;
 	loff_t			size;
 	u8			nguid[16];
 	uuid_t			uuid;
+	u32			anagrpid;
 
+	bool			buffered_io;
 	bool			enabled;
 	struct nvmet_subsys	*subsys;
 	const char		*device_path;
@@ -97,6 +99,18 @@ struct nvmet_sq {
 	struct completion	confirm_done;
 };
 
+struct nvmet_ana_group {
+	struct config_group	group;
+	struct nvmet_port	*port;
+	u32			grpid;
+};
+
+static inline struct nvmet_ana_group *to_ana_group(struct config_item *item)
+{
+	return container_of(to_config_group(item), struct nvmet_ana_group,
+			group);
+}
+
 /**
  * struct nvmet_port -	Common structure to keep port
  *				information for the target.
@@ -114,8 +128,12 @@ struct nvmet_port {
 	struct list_head		subsystems;
 	struct config_group		referrals_group;
 	struct list_head		referrals;
+	struct config_group		ana_groups_group;
+	struct nvmet_ana_group		ana_default_group;
+	enum nvme_ana_state		*ana_state;
 	void				*priv;
 	bool				enabled;
+	int				inline_data_size;
 };
 
 static inline struct nvmet_port *to_nvmet_port(struct config_item *item)
@@ -124,6 +142,13 @@ static inline struct nvmet_port *to_nvmet_port(struct config_item *item)
 			group);
 }
 
+static inline struct nvmet_port *ana_groups_to_port(
+		struct config_item *item)
+{
+	return container_of(to_config_group(item), struct nvmet_port,
+			ana_groups_group);
+}
+
 struct nvmet_ctrl {
 	struct nvmet_subsys	*subsys;
 	struct nvmet_cq		**cqs;
@@ -138,6 +163,8 @@ struct nvmet_ctrl {
 	u16			cntlid;
 	u32			kato;
 
+	struct nvmet_port	*port;
+
 	u32			aen_enabled;
 	unsigned long		aen_masked;
 	struct nvmet_req	*async_event_cmds[NVMET_ASYNC_EVENTS];
@@ -166,6 +193,7 @@ struct nvmet_subsys {
 	struct kref		ref;
 
 	struct list_head	namespaces;
+	unsigned int		nr_namespaces;
 	unsigned int		max_nsid;
 
 	struct list_head	ctrls;
@@ -225,7 +253,6 @@ struct nvmet_req;
 struct nvmet_fabrics_ops {
 	struct module *owner;
 	unsigned int type;
-	unsigned int sqe_inline_size;
 	unsigned int msdbd;
 	bool has_keyed_sgls : 1;
 	void (*queue_response)(struct nvmet_req *req);
@@ -269,6 +296,8 @@ struct nvmet_req {
 	const struct nvmet_fabrics_ops *ops;
 };
 
+extern struct workqueue_struct *buffered_io_wq;
+
 static inline void nvmet_set_status(struct nvmet_req *req, u16 status)
 {
 	req->rsp->status = cpu_to_le16(status << 1);
@@ -337,6 +366,10 @@ void nvmet_ns_disable(struct nvmet_ns *ns);
 struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid);
 void nvmet_ns_free(struct nvmet_ns *ns);
 
+void nvmet_send_ana_event(struct nvmet_subsys *subsys,
+		struct nvmet_port *port);
+void nvmet_port_send_ana_event(struct nvmet_port *port);
+
 int nvmet_register_transport(const struct nvmet_fabrics_ops *ops);
 void nvmet_unregister_transport(const struct nvmet_fabrics_ops *ops);
 
@@ -357,6 +390,22 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd);
 #define NVMET_QUEUE_SIZE	1024
 #define NVMET_NR_QUEUES		128
 #define NVMET_MAX_CMD		NVMET_QUEUE_SIZE
+
+/*
+ * Nice round number that makes a list of nsids fit into a page.
+ * Should become tunable at some point in the future.
+ */
+#define NVMET_MAX_NAMESPACES	1024
+
+/*
+ * 0 is not a valid ANA group ID, so we start numbering at 1.
+ *
+ * ANA Group 1 exists without manual intervention, has namespaces assigned to it
+ * by default, and is available in an optimized state through all ports.
+ */
+#define NVMET_MAX_ANAGRPS	128
+#define NVMET_DEFAULT_ANA_GRPID	1
+
 #define NVMET_KAS		10
 #define NVMET_DISC_KATO		120
 
@@ -370,6 +419,10 @@ extern struct nvmet_subsys *nvmet_disc_subsys;
 extern u64 nvmet_genctr;
 extern struct rw_semaphore nvmet_config_sem;
 
+extern u32 nvmet_ana_group_enabled[NVMET_MAX_ANAGRPS + 1];
+extern u64 nvmet_ana_chgcnt;
+extern struct rw_semaphore nvmet_ana_sem;
+
 bool nvmet_host_allowed(struct nvmet_req *req, struct nvmet_subsys *subsys,
 		const char *hostnqn);
 
@@ -377,6 +430,9 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns);
 int nvmet_file_ns_enable(struct nvmet_ns *ns);
 void nvmet_bdev_ns_disable(struct nvmet_ns *ns);
 void nvmet_file_ns_disable(struct nvmet_ns *ns);
+u16 nvmet_bdev_flush(struct nvmet_req *req);
+u16 nvmet_file_flush(struct nvmet_req *req);
+void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid);
 
 static inline u32 nvmet_rw_len(struct nvmet_req *req)
 {
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 1a642e214a4c..3533e918ea37 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -33,16 +33,17 @@
 #include "nvmet.h"
 
 /*
- * We allow up to a page of inline data to go with the SQE
+ * We allow at least 1 page, up to 4 SGEs, and up to 16KB of inline data
  */
-#define NVMET_RDMA_INLINE_DATA_SIZE	PAGE_SIZE
+#define NVMET_RDMA_DEFAULT_INLINE_DATA_SIZE	PAGE_SIZE
+#define NVMET_RDMA_MAX_INLINE_SGE		4
+#define NVMET_RDMA_MAX_INLINE_DATA_SIZE		max_t(int, SZ_16K, PAGE_SIZE)
 
 struct nvmet_rdma_cmd {
-	struct ib_sge		sge[2];
+	struct ib_sge		sge[NVMET_RDMA_MAX_INLINE_SGE + 1];
 	struct ib_cqe		cqe;
 	struct ib_recv_wr	wr;
-	struct scatterlist	inline_sg;
-	struct page		*inline_page;
+	struct scatterlist	inline_sg[NVMET_RDMA_MAX_INLINE_SGE];
 	struct nvme_command     *nvme_cmd;
 	struct nvmet_rdma_queue	*queue;
 };
@@ -116,6 +117,8 @@ struct nvmet_rdma_device {
 	size_t			srq_size;
 	struct kref		ref;
 	struct list_head	entry;
+	int			inline_data_size;
+	int			inline_page_count;
 };
 
 static bool nvmet_rdma_use_srq;
@@ -138,6 +141,11 @@ static void nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue);
 
 static const struct nvmet_fabrics_ops nvmet_rdma_ops;
 
+static int num_pages(int len)
+{
+	return 1 + (((len - 1) & PAGE_MASK) >> PAGE_SHIFT);
+}
+
 /* XXX: really should move to a generic header sooner or later.. */
 static inline u32 get_unaligned_le24(const u8 *p)
 {
@@ -184,6 +192,71 @@ nvmet_rdma_put_rsp(struct nvmet_rdma_rsp *rsp)
 	spin_unlock_irqrestore(&rsp->queue->rsps_lock, flags);
 }
 
+static void nvmet_rdma_free_inline_pages(struct nvmet_rdma_device *ndev,
+				struct nvmet_rdma_cmd *c)
+{
+	struct scatterlist *sg;
+	struct ib_sge *sge;
+	int i;
+
+	if (!ndev->inline_data_size)
+		return;
+
+	sg = c->inline_sg;
+	sge = &c->sge[1];
+
+	for (i = 0; i < ndev->inline_page_count; i++, sg++, sge++) {
+		if (sge->length)
+			ib_dma_unmap_page(ndev->device, sge->addr,
+					sge->length, DMA_FROM_DEVICE);
+		if (sg_page(sg))
+			__free_page(sg_page(sg));
+	}
+}
+
+static int nvmet_rdma_alloc_inline_pages(struct nvmet_rdma_device *ndev,
+				struct nvmet_rdma_cmd *c)
+{
+	struct scatterlist *sg;
+	struct ib_sge *sge;
+	struct page *pg;
+	int len;
+	int i;
+
+	if (!ndev->inline_data_size)
+		return 0;
+
+	sg = c->inline_sg;
+	sg_init_table(sg, ndev->inline_page_count);
+	sge = &c->sge[1];
+	len = ndev->inline_data_size;
+
+	for (i = 0; i < ndev->inline_page_count; i++, sg++, sge++) {
+		pg = alloc_page(GFP_KERNEL);
+		if (!pg)
+			goto out_err;
+		sg_assign_page(sg, pg);
+		sge->addr = ib_dma_map_page(ndev->device,
+			pg, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+		if (ib_dma_mapping_error(ndev->device, sge->addr))
+			goto out_err;
+		sge->length = min_t(int, len, PAGE_SIZE);
+		sge->lkey = ndev->pd->local_dma_lkey;
+		len -= sge->length;
+	}
+
+	return 0;
+out_err:
+	for (; i >= 0; i--, sg--, sge--) {
+		if (sge->length)
+			ib_dma_unmap_page(ndev->device, sge->addr,
+					sge->length, DMA_FROM_DEVICE);
+		if (sg_page(sg))
+			__free_page(sg_page(sg));
+	}
+	return -ENOMEM;
+}
+
 static int nvmet_rdma_alloc_cmd(struct nvmet_rdma_device *ndev,
 			struct nvmet_rdma_cmd *c, bool admin)
 {
@@ -200,33 +273,17 @@ static int nvmet_rdma_alloc_cmd(struct nvmet_rdma_device *ndev,
 	c->sge[0].length = sizeof(*c->nvme_cmd);
 	c->sge[0].lkey = ndev->pd->local_dma_lkey;
 
-	if (!admin) {
-		c->inline_page = alloc_pages(GFP_KERNEL,
-				get_order(NVMET_RDMA_INLINE_DATA_SIZE));
-		if (!c->inline_page)
-			goto out_unmap_cmd;
-		c->sge[1].addr = ib_dma_map_page(ndev->device,
-				c->inline_page, 0, NVMET_RDMA_INLINE_DATA_SIZE,
-				DMA_FROM_DEVICE);
-		if (ib_dma_mapping_error(ndev->device, c->sge[1].addr))
-			goto out_free_inline_page;
-		c->sge[1].length = NVMET_RDMA_INLINE_DATA_SIZE;
-		c->sge[1].lkey = ndev->pd->local_dma_lkey;
-	}
+	if (!admin && nvmet_rdma_alloc_inline_pages(ndev, c))
+		goto out_unmap_cmd;
 
 	c->cqe.done = nvmet_rdma_recv_done;
 
 	c->wr.wr_cqe = &c->cqe;
 	c->wr.sg_list = c->sge;
-	c->wr.num_sge = admin ? 1 : 2;
+	c->wr.num_sge = admin ? 1 : ndev->inline_page_count + 1;
 
 	return 0;
 
-out_free_inline_page:
-	if (!admin) {
-		__free_pages(c->inline_page,
-				get_order(NVMET_RDMA_INLINE_DATA_SIZE));
-	}
 out_unmap_cmd:
 	ib_dma_unmap_single(ndev->device, c->sge[0].addr,
 			sizeof(*c->nvme_cmd), DMA_FROM_DEVICE);
@@ -240,12 +297,8 @@ out:
 static void nvmet_rdma_free_cmd(struct nvmet_rdma_device *ndev,
 		struct nvmet_rdma_cmd *c, bool admin)
 {
-	if (!admin) {
-		ib_dma_unmap_page(ndev->device, c->sge[1].addr,
-				NVMET_RDMA_INLINE_DATA_SIZE, DMA_FROM_DEVICE);
-		__free_pages(c->inline_page,
-				get_order(NVMET_RDMA_INLINE_DATA_SIZE));
-	}
+	if (!admin)
+		nvmet_rdma_free_inline_pages(ndev, c);
 	ib_dma_unmap_single(ndev->device, c->sge[0].addr,
 				sizeof(*c->nvme_cmd), DMA_FROM_DEVICE);
 	kfree(c->nvme_cmd);
@@ -382,13 +435,21 @@ static void nvmet_rdma_free_rsps(struct nvmet_rdma_queue *queue)
 static int nvmet_rdma_post_recv(struct nvmet_rdma_device *ndev,
 		struct nvmet_rdma_cmd *cmd)
 {
+	int ret;
+
 	ib_dma_sync_single_for_device(ndev->device,
 		cmd->sge[0].addr, cmd->sge[0].length,
 		DMA_FROM_DEVICE);
 
 	if (ndev->srq)
-		return ib_post_srq_recv(ndev->srq, &cmd->wr, NULL);
-	return ib_post_recv(cmd->queue->cm_id->qp, &cmd->wr, NULL);
+		ret = ib_post_srq_recv(ndev->srq, &cmd->wr, NULL);
+	else
+		ret = ib_post_recv(cmd->queue->cm_id->qp, &cmd->wr, NULL);
+
+	if (unlikely(ret))
+		pr_err("post_recv cmd failed\n");
+
+	return ret;
 }
 
 static void nvmet_rdma_process_wr_wait_list(struct nvmet_rdma_queue *queue)
@@ -427,7 +488,7 @@ static void nvmet_rdma_release_rsp(struct nvmet_rdma_rsp *rsp)
 				rsp->req.sg_cnt, nvmet_data_dir(&rsp->req));
 	}
 
-	if (rsp->req.sg != &rsp->cmd->inline_sg)
+	if (rsp->req.sg != rsp->cmd->inline_sg)
 		sgl_free(rsp->req.sg);
 
 	if (unlikely(!list_empty_careful(&queue->rsp_wr_wait_list)))
@@ -491,7 +552,7 @@ static void nvmet_rdma_queue_response(struct nvmet_req *req)
 		rsp->send_sge.addr, rsp->send_sge.length,
 		DMA_TO_DEVICE);
 
-	if (ib_post_send(cm_id->qp, first_wr, NULL)) {
+	if (unlikely(ib_post_send(cm_id->qp, first_wr, NULL))) {
 		pr_err("sending cmd response failed\n");
 		nvmet_rdma_release_rsp(rsp);
 	}
@@ -527,10 +588,25 @@ static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc)
 static void nvmet_rdma_use_inline_sg(struct nvmet_rdma_rsp *rsp, u32 len,
 		u64 off)
 {
-	sg_init_table(&rsp->cmd->inline_sg, 1);
-	sg_set_page(&rsp->cmd->inline_sg, rsp->cmd->inline_page, len, off);
-	rsp->req.sg = &rsp->cmd->inline_sg;
-	rsp->req.sg_cnt = 1;
+	int sg_count = num_pages(len);
+	struct scatterlist *sg;
+	int i;
+
+	sg = rsp->cmd->inline_sg;
+	for (i = 0; i < sg_count; i++, sg++) {
+		if (i < sg_count - 1)
+			sg_unmark_end(sg);
+		else
+			sg_mark_end(sg);
+		sg->offset = off;
+		sg->length = min_t(int, len, PAGE_SIZE - off);
+		len -= sg->length;
+		if (!i)
+			off = 0;
+	}
+
+	rsp->req.sg = rsp->cmd->inline_sg;
+	rsp->req.sg_cnt = sg_count;
 }
 
 static u16 nvmet_rdma_map_sgl_inline(struct nvmet_rdma_rsp *rsp)
@@ -542,7 +618,7 @@ static u16 nvmet_rdma_map_sgl_inline(struct nvmet_rdma_rsp *rsp)
 	if (!nvme_is_write(rsp->req.cmd))
 		return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 
-	if (off + len > NVMET_RDMA_INLINE_DATA_SIZE) {
+	if (off + len > rsp->queue->dev->inline_data_size) {
 		pr_err("invalid inline data offset!\n");
 		return NVME_SC_SGL_INVALID_OFFSET | NVME_SC_DNR;
 	}
@@ -741,7 +817,7 @@ static int nvmet_rdma_init_srq(struct nvmet_rdma_device *ndev)
 	srq_size = 4095;	/* XXX: tune */
 
 	srq_attr.attr.max_wr = srq_size;
-	srq_attr.attr.max_sge = 2;
+	srq_attr.attr.max_sge = 1 + ndev->inline_page_count;
 	srq_attr.attr.srq_limit = 0;
 	srq_attr.srq_type = IB_SRQT_BASIC;
 	srq = ib_create_srq(ndev->pd, &srq_attr);
@@ -763,11 +839,16 @@ static int nvmet_rdma_init_srq(struct nvmet_rdma_device *ndev)
 	ndev->srq = srq;
 	ndev->srq_size = srq_size;
 
-	for (i = 0; i < srq_size; i++)
-		nvmet_rdma_post_recv(ndev, &ndev->srq_cmds[i]);
+	for (i = 0; i < srq_size; i++) {
+		ret = nvmet_rdma_post_recv(ndev, &ndev->srq_cmds[i]);
+		if (ret)
+			goto out_free_cmds;
+	}
 
 	return 0;
 
+out_free_cmds:
+	nvmet_rdma_free_cmds(ndev, ndev->srq_cmds, ndev->srq_size, false);
 out_destroy_srq:
 	ib_destroy_srq(srq);
 	return ret;
@@ -791,7 +872,10 @@ static void nvmet_rdma_free_dev(struct kref *ref)
 static struct nvmet_rdma_device *
 nvmet_rdma_find_get_device(struct rdma_cm_id *cm_id)
 {
+	struct nvmet_port *port = cm_id->context;
 	struct nvmet_rdma_device *ndev;
+	int inline_page_count;
+	int inline_sge_count;
 	int ret;
 
 	mutex_lock(&device_list_mutex);
@@ -805,6 +889,18 @@ nvmet_rdma_find_get_device(struct rdma_cm_id *cm_id)
 	if (!ndev)
 		goto out_err;
 
+	inline_page_count = num_pages(port->inline_data_size);
+	inline_sge_count = max(cm_id->device->attrs.max_sge_rd,
+				cm_id->device->attrs.max_recv_sge) - 1;
+	if (inline_page_count > inline_sge_count) {
+		pr_warn("inline_data_size %d cannot be supported by device %s. Reducing to %lu.\n",
+			port->inline_data_size, cm_id->device->name,
+			inline_sge_count * PAGE_SIZE);
+		port->inline_data_size = inline_sge_count * PAGE_SIZE;
+		inline_page_count = inline_sge_count;
+	}
+	ndev->inline_data_size = port->inline_data_size;
+	ndev->inline_page_count = inline_page_count;
 	ndev->device = cm_id->device;
 	kref_init(&ndev->ref);
 
@@ -879,7 +975,7 @@ static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)
 	} else {
 		/* +1 for drain */
 		qp_attr.cap.max_recv_wr = 1 + queue->recv_queue_size;
-		qp_attr.cap.max_recv_sge = 2;
+		qp_attr.cap.max_recv_sge = 1 + ndev->inline_page_count;
 	}
 
 	ret = rdma_create_qp(queue->cm_id, ndev->pd, &qp_attr);
@@ -897,13 +993,17 @@ static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)
 	if (!ndev->srq) {
 		for (i = 0; i < queue->recv_queue_size; i++) {
 			queue->cmds[i].queue = queue;
-			nvmet_rdma_post_recv(ndev, &queue->cmds[i]);
+			ret = nvmet_rdma_post_recv(ndev, &queue->cmds[i]);
+			if (ret)
+				goto err_destroy_qp;
 		}
 	}
 
 out:
 	return ret;
 
+err_destroy_qp:
+	rdma_destroy_qp(queue->cm_id);
 err_destroy_cq:
 	ib_free_cq(queue->cq);
 	goto out;
@@ -1377,6 +1477,15 @@ static int nvmet_rdma_add_port(struct nvmet_port *port)
 		return -EINVAL;
 	}
 
+	if (port->inline_data_size < 0) {
+		port->inline_data_size = NVMET_RDMA_DEFAULT_INLINE_DATA_SIZE;
+	} else if (port->inline_data_size > NVMET_RDMA_MAX_INLINE_DATA_SIZE) {
+		pr_warn("inline_data_size %u is too large, reducing to %u\n",
+			port->inline_data_size,
+			NVMET_RDMA_MAX_INLINE_DATA_SIZE);
+		port->inline_data_size = NVMET_RDMA_MAX_INLINE_DATA_SIZE;
+	}
+
 	ret = inet_pton_with_scope(&init_net, af, port->disc_addr.traddr,
 			port->disc_addr.trsvcid, &addr);
 	if (ret) {
@@ -1454,7 +1563,6 @@ static void nvmet_rdma_disc_port_addr(struct nvmet_req *req,
 static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
 	.owner			= THIS_MODULE,
 	.type			= NVMF_TRTYPE_RDMA,
-	.sqe_inline_size	= NVMET_RDMA_INLINE_DATA_SIZE,
 	.msdbd			= 1,
 	.has_keyed_sgls		= 1,
 	.add_port		= nvmet_rdma_add_port,
diff --git a/drivers/of/address.c b/drivers/of/address.c
index 53349912ac75..7ddbf0a1ab86 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -846,7 +846,7 @@ EXPORT_SYMBOL(of_iomap);
  *			   for a given device_node
  * @device:	the device whose io range will be mapped
  * @index:	index of the io range
- * @name:	name of the resource
+ * @name:	name "override" for the memory region request or NULL
  *
  * Returns a pointer to the requested and mapped memory or an ERR_PTR() encoded
  * error code on failure. Usage example:
@@ -856,7 +856,7 @@ EXPORT_SYMBOL(of_iomap);
  *		return PTR_ERR(base);
  */
 void __iomem *of_io_request_and_map(struct device_node *np, int index,
-					const char *name)
+				    const char *name)
 {
 	struct resource res;
 	void __iomem *mem;
@@ -864,6 +864,8 @@ void __iomem *of_io_request_and_map(struct device_node *np, int index,
 	if (of_address_to_resource(np, index, &res))
 		return IOMEM_ERR_PTR(-EINVAL);
 
+	if (!name)
+		name = res.name;
 	if (!request_mem_region(res.start, resource_size(&res), name))
 		return IOMEM_ERR_PTR(-EBUSY);
 
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 33d85511d790..5957cd4fa262 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -127,20 +127,20 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
 	}
 
 	/*
-	 * Set default coherent_dma_mask to 32 bit.  Drivers are expected to
-	 * setup the correct supported mask.
+	 * If @dev is expected to be DMA-capable then the bus code that created
+	 * it should have initialised its dma_mask pointer by this point. For
+	 * now, we'll continue the legacy behaviour of coercing it to the
+	 * coherent mask if not, but we'll no longer do so quietly.
 	 */
-	if (!dev->coherent_dma_mask)
-		dev->coherent_dma_mask = DMA_BIT_MASK(32);
-	/*
-	 * Set it to coherent_dma_mask by default if the architecture
-	 * code has not set it.
-	 */
-	if (!dev->dma_mask)
+	if (!dev->dma_mask) {
+		dev_warn(dev, "DMA mask not set\n");
 		dev->dma_mask = &dev->coherent_dma_mask;
+	}
 
-	if (!size)
+	if (!size && dev->coherent_dma_mask)
 		size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
+	else if (!size)
+		size = 1ULL << 32;
 
 	dev->dma_pfn_offset = offset;
 
@@ -149,6 +149,7 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
 	 * set by the driver.
 	 */
 	mask = DMA_BIT_MASK(ilog2(dma_addr + size - 1) + 1);
+	dev->bus_dma_mask = mask;
 	dev->coherent_dma_mask &= mask;
 	*dev->dma_mask &= mask;
 
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 6da20b9688f7..800ad252cf9c 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -1034,14 +1034,7 @@ int __init early_init_dt_scan_memory(unsigned long node, const char *uname,
 	bool hotpluggable;
 
 	/* We are scanning "memory" nodes only */
-	if (type == NULL) {
-		/*
-		 * The longtrail doesn't have a device_type on the
-		 * /memory node, so look for the node called /memory@0.
-		 */
-		if (!IS_ENABLED(CONFIG_PPC32) || depth != 1 || strcmp(uname, "memory@0") != 0)
-			return 0;
-	} else if (strcmp(type, "memory") != 0)
+	if (type == NULL || strcmp(type, "memory") != 0)
 		return 0;
 
 	reg = of_get_flat_dt_prop(node, "linux,usable-memory", &l);
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index d963baf8e53a..e92391d6d1bd 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -367,14 +367,23 @@ struct phy_device *of_phy_get_and_connect(struct net_device *dev,
 	phy_interface_t iface;
 	struct device_node *phy_np;
 	struct phy_device *phy;
+	int ret;
 
 	iface = of_get_phy_mode(np);
 	if (iface < 0)
 		return NULL;
-
-	phy_np = of_parse_phandle(np, "phy-handle", 0);
-	if (!phy_np)
-		return NULL;
+	if (of_phy_is_fixed_link(np)) {
+		ret = of_phy_register_fixed_link(np);
+		if (ret < 0) {
+			netdev_err(dev, "broken fixed-link specification\n");
+			return NULL;
+		}
+		phy_np = of_node_get(np);
+	} else {
+		phy_np = of_parse_phandle(np, "phy-handle", 0);
+		if (!phy_np)
+			return NULL;
+	}
 
 	phy = of_phy_connect(dev, phy_np, hndlr, 0, iface);
 
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 6925d993e1f0..7ba90c290a42 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -185,6 +185,9 @@ static struct platform_device *of_platform_device_create_pdata(
 	if (!dev)
 		goto err_clear_flag;
 
+	dev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
+	if (!dev->dev.dma_mask)
+		dev->dev.dma_mask = &dev->dev.coherent_dma_mask;
 	dev->dev.bus = &platform_bus_type;
 	dev->dev.platform_data = platform_data;
 	of_msi_configure(&dev->dev, dev->dev.of_node);
diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c
index 4923a2a8e14b..5b78f3b1b918 100644
--- a/drivers/pci/ats.c
+++ b/drivers/pci/ats.c
@@ -273,6 +273,9 @@ int pci_enable_pasid(struct pci_dev *pdev, int features)
 	if (WARN_ON(pdev->pasid_enabled))
 		return -EBUSY;
 
+	if (!pdev->eetlp_prefix_path)
+		return -EINVAL;
+
 	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID);
 	if (!pos)
 		return -EINVAL;
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index cc9fa02d32a0..028b287466fb 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -102,7 +102,7 @@ config PCI_HOST_GENERIC
 
 config PCIE_XILINX
 	bool "Xilinx AXI PCIe host bridge support"
-	depends on ARCH_ZYNQ || MICROBLAZE || (MIPS && PCI_DRIVERS_GENERIC) || COMPILE_TEST
+	depends on OF || COMPILE_TEST
 	help
 	  Say 'Y' here if you want kernel to support the Xilinx AXI PCIe
 	  Host Bridge driver.
@@ -239,6 +239,16 @@ config PCIE_MEDIATEK
 	  Say Y here if you want to enable PCIe controller support on
 	  MediaTek SoCs.
 
+config PCIE_MOBIVEIL
+	bool "Mobiveil AXI PCIe controller"
+	depends on ARCH_ZYNQMP || COMPILE_TEST
+	depends on OF
+	depends on PCI_MSI_IRQ_DOMAIN
+	help
+	  Say Y here if you want to enable support for the Mobiveil AXI PCIe
+	  Soft IP. It has up to 8 outbound and inbound windows
+	  for address translation and it is a PCIe Gen4 IP.
+
 config PCIE_TANGO_SMP8759
 	bool "Tango SMP8759 PCIe controller (DANGEROUS)"
 	depends on ARCH_TANGO && PCI_MSI && OF
diff --git a/drivers/pci/controller/Makefile b/drivers/pci/controller/Makefile
index 24322b92f200..d56a507495c5 100644
--- a/drivers/pci/controller/Makefile
+++ b/drivers/pci/controller/Makefile
@@ -26,6 +26,7 @@ obj-$(CONFIG_PCIE_ROCKCHIP) += pcie-rockchip.o
 obj-$(CONFIG_PCIE_ROCKCHIP_EP) += pcie-rockchip-ep.o
 obj-$(CONFIG_PCIE_ROCKCHIP_HOST) += pcie-rockchip-host.o
 obj-$(CONFIG_PCIE_MEDIATEK) += pcie-mediatek.o
+obj-$(CONFIG_PCIE_MOBIVEIL) += pcie-mobiveil.o
 obj-$(CONFIG_PCIE_TANGO_SMP8759) += pcie-tango.o
 obj-$(CONFIG_VMD) += vmd.o
 # pcie-hisi.o quirks are needed even without CONFIG_PCIE_DW
diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c
index 345aab56ce8b..ce9224a36f62 100644
--- a/drivers/pci/controller/dwc/pci-dra7xx.c
+++ b/drivers/pci/controller/dwc/pci-dra7xx.c
@@ -370,7 +370,7 @@ static void dra7xx_pcie_raise_msi_irq(struct dra7xx_pcie *dra7xx,
 }
 
 static int dra7xx_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				 enum pci_epc_irq_type type, u8 interrupt_num)
+				 enum pci_epc_irq_type type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci);
diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c
index 4cc1e5df8c79..cee5f2f590e2 100644
--- a/drivers/pci/controller/dwc/pci-exynos.c
+++ b/drivers/pci/controller/dwc/pci-exynos.c
@@ -421,7 +421,6 @@ static int __init exynos_add_pcie_port(struct exynos_pcie *ep,
 		}
 	}
 
-	pp->root_bus_nr = -1;
 	pp->ops = &exynos_pcie_host_ops;
 
 	ret = dw_pcie_host_init(pp);
diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index 80f604602783..4a9a673b4777 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -667,7 +667,6 @@ static int imx6_add_pcie_port(struct imx6_pcie *imx6_pcie,
 		}
 	}
 
-	pp->root_bus_nr = -1;
 	pp->ops = &imx6_pcie_host_ops;
 
 	ret = dw_pcie_host_init(pp);
diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index 3722a5f31e5e..e88bd221fffe 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -347,7 +347,6 @@ static int __init ks_add_pcie_port(struct keystone_pcie *ks_pcie,
 		}
 	}
 
-	pp->root_bus_nr = -1;
 	pp->ops = &keystone_pcie_host_ops;
 	ret = ks_dw_pcie_host_init(ks_pcie, ks_pcie->msi_intc_np);
 	if (ret) {
diff --git a/drivers/pci/controller/dwc/pcie-armada8k.c b/drivers/pci/controller/dwc/pcie-armada8k.c
index 072fd7ecc29f..0c389a30ef5d 100644
--- a/drivers/pci/controller/dwc/pcie-armada8k.c
+++ b/drivers/pci/controller/dwc/pcie-armada8k.c
@@ -172,7 +172,6 @@ static int armada8k_add_pcie_port(struct armada8k_pcie *pcie,
 	struct device *dev = &pdev->dev;
 	int ret;
 
-	pp->root_bus_nr = -1;
 	pp->ops = &armada8k_pcie_host_ops;
 
 	pp->irq = platform_get_irq(pdev, 0);
diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c
index 321b56cfd5d0..dba83abfe764 100644
--- a/drivers/pci/controller/dwc/pcie-artpec6.c
+++ b/drivers/pci/controller/dwc/pcie-artpec6.c
@@ -399,7 +399,6 @@ static int artpec6_add_pcie_port(struct artpec6_pcie *artpec6_pcie,
 		}
 	}
 
-	pp->root_bus_nr = -1;
 	pp->ops = &artpec6_pcie_host_ops;
 
 	ret = dw_pcie_host_init(pp);
@@ -428,7 +427,7 @@ static void artpec6_pcie_ep_init(struct dw_pcie_ep *ep)
 }
 
 static int artpec6_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				  enum pci_epc_irq_type type, u8 interrupt_num)
+				  enum pci_epc_irq_type type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 8650416f6f9e..1e7b02221eac 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -40,6 +40,39 @@ void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar)
 	__dw_pcie_ep_reset_bar(pci, bar, 0);
 }
 
+static u8 __dw_pcie_ep_find_next_cap(struct dw_pcie *pci, u8 cap_ptr,
+			      u8 cap)
+{
+	u8 cap_id, next_cap_ptr;
+	u16 reg;
+
+	reg = dw_pcie_readw_dbi(pci, cap_ptr);
+	next_cap_ptr = (reg & 0xff00) >> 8;
+	cap_id = (reg & 0x00ff);
+
+	if (!next_cap_ptr || cap_id > PCI_CAP_ID_MAX)
+		return 0;
+
+	if (cap_id == cap)
+		return cap_ptr;
+
+	return __dw_pcie_ep_find_next_cap(pci, next_cap_ptr, cap);
+}
+
+static u8 dw_pcie_ep_find_capability(struct dw_pcie *pci, u8 cap)
+{
+	u8 next_cap_ptr;
+	u16 reg;
+
+	reg = dw_pcie_readw_dbi(pci, PCI_CAPABILITY_LIST);
+	next_cap_ptr = (reg & 0x00ff);
+
+	if (!next_cap_ptr)
+		return 0;
+
+	return __dw_pcie_ep_find_next_cap(pci, next_cap_ptr, cap);
+}
+
 static int dw_pcie_ep_write_header(struct pci_epc *epc, u8 func_no,
 				   struct pci_epf_header *hdr)
 {
@@ -213,36 +246,84 @@ static int dw_pcie_ep_map_addr(struct pci_epc *epc, u8 func_no,
 
 static int dw_pcie_ep_get_msi(struct pci_epc *epc, u8 func_no)
 {
-	int val;
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	u32 val, reg;
+
+	if (!ep->msi_cap)
+		return -EINVAL;
+
+	reg = ep->msi_cap + PCI_MSI_FLAGS;
+	val = dw_pcie_readw_dbi(pci, reg);
+	if (!(val & PCI_MSI_FLAGS_ENABLE))
+		return -EINVAL;
+
+	val = (val & PCI_MSI_FLAGS_QSIZE) >> 4;
+
+	return val;
+}
+
+static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts)
+{
+	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
+	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	u32 val, reg;
+
+	if (!ep->msi_cap)
+		return -EINVAL;
+
+	reg = ep->msi_cap + PCI_MSI_FLAGS;
+	val = dw_pcie_readw_dbi(pci, reg);
+	val &= ~PCI_MSI_FLAGS_QMASK;
+	val |= (interrupts << 1) & PCI_MSI_FLAGS_QMASK;
+	dw_pcie_dbi_ro_wr_en(pci);
+	dw_pcie_writew_dbi(pci, reg, val);
+	dw_pcie_dbi_ro_wr_dis(pci);
+
+	return 0;
+}
+
+static int dw_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no)
+{
+	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
+	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	u32 val, reg;
 
-	val = dw_pcie_readw_dbi(pci, MSI_MESSAGE_CONTROL);
-	if (!(val & MSI_CAP_MSI_EN_MASK))
+	if (!ep->msix_cap)
 		return -EINVAL;
 
-	val = (val & MSI_CAP_MME_MASK) >> MSI_CAP_MME_SHIFT;
+	reg = ep->msix_cap + PCI_MSIX_FLAGS;
+	val = dw_pcie_readw_dbi(pci, reg);
+	if (!(val & PCI_MSIX_FLAGS_ENABLE))
+		return -EINVAL;
+
+	val &= PCI_MSIX_FLAGS_QSIZE;
+
 	return val;
 }
 
-static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 encode_int)
+static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts)
 {
-	int val;
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	u32 val, reg;
+
+	if (!ep->msix_cap)
+		return -EINVAL;
 
-	val = dw_pcie_readw_dbi(pci, MSI_MESSAGE_CONTROL);
-	val &= ~MSI_CAP_MMC_MASK;
-	val |= (encode_int << MSI_CAP_MMC_SHIFT) & MSI_CAP_MMC_MASK;
+	reg = ep->msix_cap + PCI_MSIX_FLAGS;
+	val = dw_pcie_readw_dbi(pci, reg);
+	val &= ~PCI_MSIX_FLAGS_QSIZE;
+	val |= interrupts;
 	dw_pcie_dbi_ro_wr_en(pci);
-	dw_pcie_writew_dbi(pci, MSI_MESSAGE_CONTROL, val);
+	dw_pcie_writew_dbi(pci, reg, val);
 	dw_pcie_dbi_ro_wr_dis(pci);
 
 	return 0;
 }
 
 static int dw_pcie_ep_raise_irq(struct pci_epc *epc, u8 func_no,
-				enum pci_epc_irq_type type, u8 interrupt_num)
+				enum pci_epc_irq_type type, u16 interrupt_num)
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 
@@ -282,32 +363,52 @@ static const struct pci_epc_ops epc_ops = {
 	.unmap_addr		= dw_pcie_ep_unmap_addr,
 	.set_msi		= dw_pcie_ep_set_msi,
 	.get_msi		= dw_pcie_ep_get_msi,
+	.set_msix		= dw_pcie_ep_set_msix,
+	.get_msix		= dw_pcie_ep_get_msix,
 	.raise_irq		= dw_pcie_ep_raise_irq,
 	.start			= dw_pcie_ep_start,
 	.stop			= dw_pcie_ep_stop,
 };
 
+int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	struct device *dev = pci->dev;
+
+	dev_err(dev, "EP cannot trigger legacy IRQs\n");
+
+	return -EINVAL;
+}
+
 int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 			     u8 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct pci_epc *epc = ep->epc;
 	u16 msg_ctrl, msg_data;
-	u32 msg_addr_lower, msg_addr_upper;
+	u32 msg_addr_lower, msg_addr_upper, reg;
 	u64 msg_addr;
 	bool has_upper;
 	int ret;
 
+	if (!ep->msi_cap)
+		return -EINVAL;
+
 	/* Raise MSI per the PCI Local Bus Specification Revision 3.0, 6.8.1. */
-	msg_ctrl = dw_pcie_readw_dbi(pci, MSI_MESSAGE_CONTROL);
+	reg = ep->msi_cap + PCI_MSI_FLAGS;
+	msg_ctrl = dw_pcie_readw_dbi(pci, reg);
 	has_upper = !!(msg_ctrl & PCI_MSI_FLAGS_64BIT);
-	msg_addr_lower = dw_pcie_readl_dbi(pci, MSI_MESSAGE_ADDR_L32);
+	reg = ep->msi_cap + PCI_MSI_ADDRESS_LO;
+	msg_addr_lower = dw_pcie_readl_dbi(pci, reg);
 	if (has_upper) {
-		msg_addr_upper = dw_pcie_readl_dbi(pci, MSI_MESSAGE_ADDR_U32);
-		msg_data = dw_pcie_readw_dbi(pci, MSI_MESSAGE_DATA_64);
+		reg = ep->msi_cap + PCI_MSI_ADDRESS_HI;
+		msg_addr_upper = dw_pcie_readl_dbi(pci, reg);
+		reg = ep->msi_cap + PCI_MSI_DATA_64;
+		msg_data = dw_pcie_readw_dbi(pci, reg);
 	} else {
 		msg_addr_upper = 0;
-		msg_data = dw_pcie_readw_dbi(pci, MSI_MESSAGE_DATA_32);
+		reg = ep->msi_cap + PCI_MSI_DATA_32;
+		msg_data = dw_pcie_readw_dbi(pci, reg);
 	}
 	msg_addr = ((u64) msg_addr_upper) << 32 | msg_addr_lower;
 	ret = dw_pcie_ep_map_addr(epc, func_no, ep->msi_mem_phys, msg_addr,
@@ -322,6 +423,64 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 	return 0;
 }
 
+int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
+			     u16 interrupt_num)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	struct pci_epc *epc = ep->epc;
+	u16 tbl_offset, bir;
+	u32 bar_addr_upper, bar_addr_lower;
+	u32 msg_addr_upper, msg_addr_lower;
+	u32 reg, msg_data, vec_ctrl;
+	u64 tbl_addr, msg_addr, reg_u64;
+	void __iomem *msix_tbl;
+	int ret;
+
+	reg = ep->msix_cap + PCI_MSIX_TABLE;
+	tbl_offset = dw_pcie_readl_dbi(pci, reg);
+	bir = (tbl_offset & PCI_MSIX_TABLE_BIR);
+	tbl_offset &= PCI_MSIX_TABLE_OFFSET;
+	tbl_offset >>= 3;
+
+	reg = PCI_BASE_ADDRESS_0 + (4 * bir);
+	bar_addr_upper = 0;
+	bar_addr_lower = dw_pcie_readl_dbi(pci, reg);
+	reg_u64 = (bar_addr_lower & PCI_BASE_ADDRESS_MEM_TYPE_MASK);
+	if (reg_u64 == PCI_BASE_ADDRESS_MEM_TYPE_64)
+		bar_addr_upper = dw_pcie_readl_dbi(pci, reg + 4);
+
+	tbl_addr = ((u64) bar_addr_upper) << 32 | bar_addr_lower;
+	tbl_addr += (tbl_offset + ((interrupt_num - 1) * PCI_MSIX_ENTRY_SIZE));
+	tbl_addr &= PCI_BASE_ADDRESS_MEM_MASK;
+
+	msix_tbl = ioremap_nocache(ep->phys_base + tbl_addr,
+				   PCI_MSIX_ENTRY_SIZE);
+	if (!msix_tbl)
+		return -EINVAL;
+
+	msg_addr_lower = readl(msix_tbl + PCI_MSIX_ENTRY_LOWER_ADDR);
+	msg_addr_upper = readl(msix_tbl + PCI_MSIX_ENTRY_UPPER_ADDR);
+	msg_addr = ((u64) msg_addr_upper) << 32 | msg_addr_lower;
+	msg_data = readl(msix_tbl + PCI_MSIX_ENTRY_DATA);
+	vec_ctrl = readl(msix_tbl + PCI_MSIX_ENTRY_VECTOR_CTRL);
+
+	iounmap(msix_tbl);
+
+	if (vec_ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT)
+		return -EPERM;
+
+	ret = dw_pcie_ep_map_addr(epc, func_no, ep->msi_mem_phys, msg_addr,
+				  epc->mem->page_size);
+	if (ret)
+		return ret;
+
+	writel(msg_data, ep->msi_mem);
+
+	dw_pcie_ep_unmap_addr(epc, func_no, ep->msi_mem_phys);
+
+	return 0;
+}
+
 void dw_pcie_ep_exit(struct dw_pcie_ep *ep)
 {
 	struct pci_epc *epc = ep->epc;
@@ -386,15 +545,18 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep)
 		return -ENOMEM;
 	ep->outbound_addr = addr;
 
-	if (ep->ops->ep_init)
-		ep->ops->ep_init(ep);
-
 	epc = devm_pci_epc_create(dev, &epc_ops);
 	if (IS_ERR(epc)) {
 		dev_err(dev, "Failed to create epc device\n");
 		return PTR_ERR(epc);
 	}
 
+	ep->epc = epc;
+	epc_set_drvdata(epc, ep);
+
+	if (ep->ops->ep_init)
+		ep->ops->ep_init(ep);
+
 	ret = of_property_read_u8(np, "max-functions", &epc->max_functions);
 	if (ret < 0)
 		epc->max_functions = 1;
@@ -409,15 +571,13 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep)
 	ep->msi_mem = pci_epc_mem_alloc_addr(epc, &ep->msi_mem_phys,
 					     epc->mem->page_size);
 	if (!ep->msi_mem) {
-		dev_err(dev, "Failed to reserve memory for MSI\n");
+		dev_err(dev, "Failed to reserve memory for MSI/MSI-X\n");
 		return -ENOMEM;
 	}
+	ep->msi_cap = dw_pcie_ep_find_capability(pci, PCI_CAP_ID_MSI);
 
-	epc->features = EPC_FEATURE_NO_LINKUP_NOTIFIER;
-	EPC_FEATURE_SET_BAR(epc->features, BAR_0);
+	ep->msix_cap = dw_pcie_ep_find_capability(pci, PCI_CAP_ID_MSIX);
 
-	ep->epc = epc;
-	epc_set_drvdata(epc, ep);
 	dw_pcie_setup(pci);
 
 	return 0;
diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c
index 5937fed4c938..c12bf794d69c 100644
--- a/drivers/pci/controller/dwc/pcie-designware-plat.c
+++ b/drivers/pci/controller/dwc/pcie-designware-plat.c
@@ -70,24 +70,29 @@ static const struct dw_pcie_ops dw_pcie_ops = {
 static void dw_plat_pcie_ep_init(struct dw_pcie_ep *ep)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	struct pci_epc *epc = ep->epc;
 	enum pci_barno bar;
 
 	for (bar = BAR_0; bar <= BAR_5; bar++)
 		dw_pcie_ep_reset_bar(pci, bar);
+
+	epc->features |= EPC_FEATURE_NO_LINKUP_NOTIFIER;
+	epc->features |= EPC_FEATURE_MSIX_AVAILABLE;
 }
 
 static int dw_plat_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
 				     enum pci_epc_irq_type type,
-				     u8 interrupt_num)
+				     u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
 	case PCI_EPC_IRQ_LEGACY:
-		dev_err(pci->dev, "EP cannot trigger legacy IRQs\n");
-		return -EINVAL;
+		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
 	case PCI_EPC_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
+	case PCI_EPC_IRQ_MSIX:
+		return dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(pci->dev, "UNKNOWN IRQ type\n");
 	}
@@ -118,7 +123,6 @@ static int dw_plat_add_pcie_port(struct dw_plat_pcie *dw_plat_pcie,
 			return pp->msi_irq;
 	}
 
-	pp->root_bus_nr = -1;
 	pp->ops = &dw_plat_pcie_host_ops;
 
 	ret = dw_pcie_host_init(pp);
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index bee4e2535a61..96126fd8403c 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -96,17 +96,6 @@
 #define PCIE_GET_ATU_INB_UNR_REG_OFFSET(region)				\
 			((0x3 << 20) | ((region) << 9) | (0x1 << 8))
 
-#define MSI_MESSAGE_CONTROL		0x52
-#define MSI_CAP_MMC_SHIFT		1
-#define MSI_CAP_MMC_MASK		(7 << MSI_CAP_MMC_SHIFT)
-#define MSI_CAP_MME_SHIFT		4
-#define MSI_CAP_MSI_EN_MASK		0x1
-#define MSI_CAP_MME_MASK		(7 << MSI_CAP_MME_SHIFT)
-#define MSI_MESSAGE_ADDR_L32		0x54
-#define MSI_MESSAGE_ADDR_U32		0x58
-#define MSI_MESSAGE_DATA_32		0x58
-#define MSI_MESSAGE_DATA_64		0x5C
-
 #define MAX_MSI_IRQS			256
 #define MAX_MSI_IRQS_PER_CTRL		32
 #define MAX_MSI_CTRLS			(MAX_MSI_IRQS / MAX_MSI_IRQS_PER_CTRL)
@@ -191,7 +180,7 @@ enum dw_pcie_as_type {
 struct dw_pcie_ep_ops {
 	void	(*ep_init)(struct dw_pcie_ep *ep);
 	int	(*raise_irq)(struct dw_pcie_ep *ep, u8 func_no,
-			     enum pci_epc_irq_type type, u8 interrupt_num);
+			     enum pci_epc_irq_type type, u16 interrupt_num);
 };
 
 struct dw_pcie_ep {
@@ -208,6 +197,8 @@ struct dw_pcie_ep {
 	u32			num_ob_windows;
 	void __iomem		*msi_mem;
 	phys_addr_t		msi_mem_phys;
+	u8			msi_cap;	/* MSI capability offset */
+	u8			msix_cap;	/* MSI-X capability offset */
 };
 
 struct dw_pcie_ops {
@@ -357,8 +348,11 @@ static inline int dw_pcie_allocate_domains(struct pcie_port *pp)
 void dw_pcie_ep_linkup(struct dw_pcie_ep *ep);
 int dw_pcie_ep_init(struct dw_pcie_ep *ep);
 void dw_pcie_ep_exit(struct dw_pcie_ep *ep);
+int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no);
 int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 			     u8 interrupt_num);
+int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
+			     u16 interrupt_num);
 void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar);
 #else
 static inline void dw_pcie_ep_linkup(struct dw_pcie_ep *ep)
@@ -374,12 +368,23 @@ static inline void dw_pcie_ep_exit(struct dw_pcie_ep *ep)
 {
 }
 
+static inline int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no)
+{
+	return 0;
+}
+
 static inline int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 					   u8 interrupt_num)
 {
 	return 0;
 }
 
+static inline int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
+					   u16 interrupt_num)
+{
+	return 0;
+}
+
 static inline void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar)
 {
 }
diff --git a/drivers/pci/controller/dwc/pcie-histb.c b/drivers/pci/controller/dwc/pcie-histb.c
index 3611d6ce9a92..7b32e619b959 100644
--- a/drivers/pci/controller/dwc/pcie-histb.c
+++ b/drivers/pci/controller/dwc/pcie-histb.c
@@ -420,7 +420,6 @@ static int histb_pcie_probe(struct platform_device *pdev)
 		phy_init(hipcie->phy);
 	}
 
-	pp->root_bus_nr = -1;
 	pp->ops = &histb_pcie_host_ops;
 
 	platform_set_drvdata(pdev, hipcie);
diff --git a/drivers/pci/controller/dwc/pcie-kirin.c b/drivers/pci/controller/dwc/pcie-kirin.c
index d2970a009eb5..5352e0c3be82 100644
--- a/drivers/pci/controller/dwc/pcie-kirin.c
+++ b/drivers/pci/controller/dwc/pcie-kirin.c
@@ -430,6 +430,9 @@ static int kirin_pcie_host_init(struct pcie_port *pp)
 {
 	kirin_pcie_establish_link(pp);
 
+	if (IS_ENABLED(CONFIG_PCI_MSI))
+		dw_pcie_msi_init(pp);
+
 	return 0;
 }
 
@@ -445,9 +448,34 @@ static const struct dw_pcie_host_ops kirin_pcie_host_ops = {
 	.host_init = kirin_pcie_host_init,
 };
 
+static int kirin_pcie_add_msi(struct dw_pcie *pci,
+				struct platform_device *pdev)
+{
+	int irq;
+
+	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+		irq = platform_get_irq(pdev, 0);
+		if (irq < 0) {
+			dev_err(&pdev->dev,
+				"failed to get MSI IRQ (%d)\n", irq);
+			return irq;
+		}
+
+		pci->pp.msi_irq = irq;
+	}
+
+	return 0;
+}
+
 static int __init kirin_add_pcie_port(struct dw_pcie *pci,
 				      struct platform_device *pdev)
 {
+	int ret;
+
+	ret = kirin_pcie_add_msi(pci, pdev);
+	if (ret)
+		return ret;
+
 	pci->pp.ops = &kirin_pcie_host_ops;
 
 	return dw_pcie_host_init(&pci->pp);
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index a1d0198081a6..4352c1cb926d 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -1251,7 +1251,6 @@ static int qcom_pcie_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	pp->root_bus_nr = -1;
 	pp->ops = &qcom_pcie_dw_ops;
 
 	if (IS_ENABLED(CONFIG_PCI_MSI)) {
diff --git a/drivers/pci/controller/dwc/pcie-spear13xx.c b/drivers/pci/controller/dwc/pcie-spear13xx.c
index ecb58f7b7566..7d0cdfd8138b 100644
--- a/drivers/pci/controller/dwc/pcie-spear13xx.c
+++ b/drivers/pci/controller/dwc/pcie-spear13xx.c
@@ -210,7 +210,6 @@ static int spear13xx_add_pcie_port(struct spear13xx_pcie *spear13xx_pcie,
 		return ret;
 	}
 
-	pp->root_bus_nr = -1;
 	pp->ops = &spear13xx_pcie_host_ops;
 
 	ret = dw_pcie_host_init(pp);
diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index 0fae816fba39..6b4555ff2548 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -111,24 +111,6 @@
 #define PCIE_MSI_MASK_REG			(CONTROL_BASE_ADDR + 0x5C)
 #define PCIE_MSI_PAYLOAD_REG			(CONTROL_BASE_ADDR + 0x9C)
 
-/* PCIe window configuration */
-#define OB_WIN_BASE_ADDR			0x4c00
-#define OB_WIN_BLOCK_SIZE			0x20
-#define OB_WIN_REG_ADDR(win, offset)		(OB_WIN_BASE_ADDR + \
-						 OB_WIN_BLOCK_SIZE * (win) + \
-						 (offset))
-#define OB_WIN_MATCH_LS(win)			OB_WIN_REG_ADDR(win, 0x00)
-#define OB_WIN_MATCH_MS(win)			OB_WIN_REG_ADDR(win, 0x04)
-#define OB_WIN_REMAP_LS(win)			OB_WIN_REG_ADDR(win, 0x08)
-#define OB_WIN_REMAP_MS(win)			OB_WIN_REG_ADDR(win, 0x0c)
-#define OB_WIN_MASK_LS(win)			OB_WIN_REG_ADDR(win, 0x10)
-#define OB_WIN_MASK_MS(win)			OB_WIN_REG_ADDR(win, 0x14)
-#define OB_WIN_ACTIONS(win)			OB_WIN_REG_ADDR(win, 0x18)
-
-/* PCIe window types */
-#define OB_PCIE_MEM				0x0
-#define OB_PCIE_IO				0x4
-
 /* LMI registers base address and register offsets */
 #define LMI_BASE_ADDR				0x6000
 #define CFG_REG					(LMI_BASE_ADDR + 0x0)
@@ -247,34 +229,9 @@ static int advk_pcie_wait_for_link(struct advk_pcie *pcie)
 	return -ETIMEDOUT;
 }
 
-/*
- * Set PCIe address window register which could be used for memory
- * mapping.
- */
-static void advk_pcie_set_ob_win(struct advk_pcie *pcie,
-				 u32 win_num, u32 match_ms,
-				 u32 match_ls, u32 mask_ms,
-				 u32 mask_ls, u32 remap_ms,
-				 u32 remap_ls, u32 action)
-{
-	advk_writel(pcie, match_ls, OB_WIN_MATCH_LS(win_num));
-	advk_writel(pcie, match_ms, OB_WIN_MATCH_MS(win_num));
-	advk_writel(pcie, mask_ms, OB_WIN_MASK_MS(win_num));
-	advk_writel(pcie, mask_ls, OB_WIN_MASK_LS(win_num));
-	advk_writel(pcie, remap_ms, OB_WIN_REMAP_MS(win_num));
-	advk_writel(pcie, remap_ls, OB_WIN_REMAP_LS(win_num));
-	advk_writel(pcie, action, OB_WIN_ACTIONS(win_num));
-	advk_writel(pcie, match_ls | BIT(0), OB_WIN_MATCH_LS(win_num));
-}
-
 static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 {
 	u32 reg;
-	int i;
-
-	/* Point PCIe unit MBUS decode windows to DRAM space */
-	for (i = 0; i < 8; i++)
-		advk_pcie_set_ob_win(pcie, i, 0, 0, 0, 0, 0, 0, 0);
 
 	/* Set to Direct mode */
 	reg = advk_readl(pcie, CTRL_CONFIG_REG);
@@ -433,6 +390,15 @@ static int advk_pcie_wait_pio(struct advk_pcie *pcie)
 	return -ETIMEDOUT;
 }
 
+static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus,
+				  int devfn)
+{
+	if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0)
+		return false;
+
+	return true;
+}
+
 static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 			     int where, int size, u32 *val)
 {
@@ -440,7 +406,7 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 	u32 reg;
 	int ret;
 
-	if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0) {
+	if (!advk_pcie_valid_device(pcie, bus, devfn)) {
 		*val = 0xffffffff;
 		return PCIBIOS_DEVICE_NOT_FOUND;
 	}
@@ -494,7 +460,7 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 	int offset;
 	int ret;
 
-	if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0)
+	if (!advk_pcie_valid_device(pcie, bus, devfn))
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
 	if (where % size)
@@ -843,12 +809,6 @@ static int advk_pcie_parse_request_of_pci_ranges(struct advk_pcie *pcie)
 
 		switch (resource_type(res)) {
 		case IORESOURCE_IO:
-			advk_pcie_set_ob_win(pcie, 1,
-					     upper_32_bits(res->start),
-					     lower_32_bits(res->start),
-					     0,	0xF8000000, 0,
-					     lower_32_bits(res->start),
-					     OB_PCIE_IO);
 			err = devm_pci_remap_iospace(dev, res, iobase);
 			if (err) {
 				dev_warn(dev, "error %d: failed to map resource %pR\n",
@@ -857,12 +817,6 @@ static int advk_pcie_parse_request_of_pci_ranges(struct advk_pcie *pcie)
 			}
 			break;
 		case IORESOURCE_MEM:
-			advk_pcie_set_ob_win(pcie, 0,
-					     upper_32_bits(res->start),
-					     lower_32_bits(res->start),
-					     0x0, 0xF8000000, 0,
-					     lower_32_bits(res->start),
-					     (2 << 20) | OB_PCIE_MEM);
 			res_valid |= !(res->flags & IORESOURCE_PREFETCH);
 			break;
 		case IORESOURCE_BUS:
@@ -889,7 +843,6 @@ static int advk_pcie_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct advk_pcie *pcie;
 	struct resource *res;
-	struct pci_bus *bus, *child;
 	struct pci_host_bridge *bridge;
 	int ret, irq;
 
@@ -943,21 +896,13 @@ static int advk_pcie_probe(struct platform_device *pdev)
 	bridge->map_irq = of_irq_parse_and_map_pci;
 	bridge->swizzle_irq = pci_common_swizzle;
 
-	ret = pci_scan_root_bus_bridge(bridge);
+	ret = pci_host_probe(bridge);
 	if (ret < 0) {
 		advk_pcie_remove_msi_irq_domain(pcie);
 		advk_pcie_remove_irq_domain(pcie);
 		return ret;
 	}
 
-	bus = bridge->bus;
-
-	pci_bus_assign_resources(bus);
-
-	list_for_each_entry(child, &bus->children, node)
-		pcie_bus_configure_settings(child);
-
-	pci_bus_add_devices(bus);
 	return 0;
 }
 
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index f6325f1a89e8..c00f82cc54aa 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -45,6 +45,7 @@
 #include <linux/irqdomain.h>
 #include <asm/irqdomain.h>
 #include <asm/apic.h>
+#include <linux/irq.h>
 #include <linux/msi.h>
 #include <linux/hyperv.h>
 #include <linux/refcount.h>
@@ -1545,7 +1546,7 @@ static struct hv_pci_dev *new_pcichild_device(struct hv_pcibus_device *hbus,
 	unsigned long flags;
 	int ret;
 
-	hpdev = kzalloc(sizeof(*hpdev), GFP_ATOMIC);
+	hpdev = kzalloc(sizeof(*hpdev), GFP_KERNEL);
 	if (!hpdev)
 		return NULL;
 
diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c
index 23e270839e6a..50eb0729385b 100644
--- a/drivers/pci/controller/pci-mvebu.c
+++ b/drivers/pci/controller/pci-mvebu.c
@@ -125,6 +125,7 @@ struct mvebu_pcie {
 	struct platform_device *pdev;
 	struct mvebu_pcie_port *ports;
 	struct msi_controller *msi;
+	struct list_head resources;
 	struct resource io;
 	struct resource realio;
 	struct resource mem;
@@ -800,7 +801,7 @@ static struct mvebu_pcie_port *mvebu_pcie_find_port(struct mvebu_pcie *pcie,
 static int mvebu_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 			      int where, int size, u32 val)
 {
-	struct mvebu_pcie *pcie = sys_to_pcie(bus->sysdata);
+	struct mvebu_pcie *pcie = bus->sysdata;
 	struct mvebu_pcie_port *port;
 	int ret;
 
@@ -826,7 +827,7 @@ static int mvebu_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 static int mvebu_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where,
 			      int size, u32 *val)
 {
-	struct mvebu_pcie *pcie = sys_to_pcie(bus->sysdata);
+	struct mvebu_pcie *pcie = bus->sysdata;
 	struct mvebu_pcie_port *port;
 	int ret;
 
@@ -857,36 +858,6 @@ static struct pci_ops mvebu_pcie_ops = {
 	.write = mvebu_pcie_wr_conf,
 };
 
-static int mvebu_pcie_setup(int nr, struct pci_sys_data *sys)
-{
-	struct mvebu_pcie *pcie = sys_to_pcie(sys);
-	int err, i;
-
-	pcie->mem.name = "PCI MEM";
-	pcie->realio.name = "PCI I/O";
-
-	if (resource_size(&pcie->realio) != 0)
-		pci_add_resource_offset(&sys->resources, &pcie->realio,
-					sys->io_offset);
-
-	pci_add_resource_offset(&sys->resources, &pcie->mem, sys->mem_offset);
-	pci_add_resource(&sys->resources, &pcie->busn);
-
-	err = devm_request_pci_bus_resources(&pcie->pdev->dev, &sys->resources);
-	if (err)
-		return 0;
-
-	for (i = 0; i < pcie->nports; i++) {
-		struct mvebu_pcie_port *port = &pcie->ports[i];
-
-		if (!port->base)
-			continue;
-		mvebu_pcie_setup_hw(port);
-	}
-
-	return 1;
-}
-
 static resource_size_t mvebu_pcie_align_resource(struct pci_dev *dev,
 						 const struct resource *res,
 						 resource_size_t start,
@@ -917,31 +888,6 @@ static resource_size_t mvebu_pcie_align_resource(struct pci_dev *dev,
 		return start;
 }
 
-static void mvebu_pcie_enable(struct mvebu_pcie *pcie)
-{
-	struct hw_pci hw;
-
-	memset(&hw, 0, sizeof(hw));
-
-#ifdef CONFIG_PCI_MSI
-	hw.msi_ctrl = pcie->msi;
-#endif
-
-	hw.nr_controllers = 1;
-	hw.private_data   = (void **)&pcie;
-	hw.setup          = mvebu_pcie_setup;
-	hw.map_irq        = of_irq_parse_and_map_pci;
-	hw.ops            = &mvebu_pcie_ops;
-	hw.align_resource = mvebu_pcie_align_resource;
-
-	pci_common_init_dev(&pcie->pdev->dev, &hw);
-}
-
-/*
- * Looks up the list of register addresses encoded into the reg =
- * <...> property for one that matches the given port/lane. Once
- * found, maps it.
- */
 static void __iomem *mvebu_pcie_map_registers(struct platform_device *pdev,
 					      struct device_node *np,
 					      struct mvebu_pcie_port *port)
@@ -1190,46 +1136,79 @@ static void mvebu_pcie_powerdown(struct mvebu_pcie_port *port)
 	clk_disable_unprepare(port->clk);
 }
 
-static int mvebu_pcie_probe(struct platform_device *pdev)
+/*
+ * We can't use devm_of_pci_get_host_bridge_resources() because we
+ * need to parse our special DT properties encoding the MEM and IO
+ * apertures.
+ */
+static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie)
 {
-	struct device *dev = &pdev->dev;
-	struct mvebu_pcie *pcie;
+	struct device *dev = &pcie->pdev->dev;
 	struct device_node *np = dev->of_node;
-	struct device_node *child;
-	int num, i, ret;
+	unsigned int i;
+	int ret;
 
-	pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL);
-	if (!pcie)
-		return -ENOMEM;
+	INIT_LIST_HEAD(&pcie->resources);
 
-	pcie->pdev = pdev;
-	platform_set_drvdata(pdev, pcie);
+	/* Get the bus range */
+	ret = of_pci_parse_bus_range(np, &pcie->busn);
+	if (ret) {
+		dev_err(dev, "failed to parse bus-range property: %d\n", ret);
+		return ret;
+	}
+	pci_add_resource(&pcie->resources, &pcie->busn);
 
-	/* Get the PCIe memory and I/O aperture */
+	/* Get the PCIe memory aperture */
 	mvebu_mbus_get_pcie_mem_aperture(&pcie->mem);
 	if (resource_size(&pcie->mem) == 0) {
 		dev_err(dev, "invalid memory aperture size\n");
 		return -EINVAL;
 	}
 
+	pcie->mem.name = "PCI MEM";
+	pci_add_resource(&pcie->resources, &pcie->mem);
+
+	/* Get the PCIe IO aperture */
 	mvebu_mbus_get_pcie_io_aperture(&pcie->io);
 
 	if (resource_size(&pcie->io) != 0) {
 		pcie->realio.flags = pcie->io.flags;
 		pcie->realio.start = PCIBIOS_MIN_IO;
 		pcie->realio.end = min_t(resource_size_t,
-					 IO_SPACE_LIMIT,
-					 resource_size(&pcie->io));
-	} else
-		pcie->realio = pcie->io;
+					 IO_SPACE_LIMIT - SZ_64K,
+					 resource_size(&pcie->io) - 1);
+		pcie->realio.name = "PCI I/O";
 
-	/* Get the bus range */
-	ret = of_pci_parse_bus_range(np, &pcie->busn);
-	if (ret) {
-		dev_err(dev, "failed to parse bus-range property: %d\n", ret);
-		return ret;
+		for (i = 0; i < resource_size(&pcie->realio); i += SZ_64K)
+			pci_ioremap_io(i, pcie->io.start + i);
+
+		pci_add_resource(&pcie->resources, &pcie->realio);
 	}
 
+	return devm_request_pci_bus_resources(dev, &pcie->resources);
+}
+
+static int mvebu_pcie_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct mvebu_pcie *pcie;
+	struct pci_host_bridge *bridge;
+	struct device_node *np = dev->of_node;
+	struct device_node *child;
+	int num, i, ret;
+
+	bridge = devm_pci_alloc_host_bridge(dev, sizeof(struct mvebu_pcie));
+	if (!bridge)
+		return -ENOMEM;
+
+	pcie = pci_host_bridge_priv(bridge);
+	pcie->pdev = pdev;
+	platform_set_drvdata(pdev, pcie);
+
+	ret = mvebu_pcie_parse_request_resources(pcie);
+	if (ret)
+		return ret;
+
 	num = of_get_available_child_count(np);
 
 	pcie->ports = devm_kcalloc(dev, num, sizeof(*pcie->ports), GFP_KERNEL);
@@ -1272,20 +1251,24 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
 			continue;
 		}
 
+		mvebu_pcie_setup_hw(port);
 		mvebu_pcie_set_local_dev_nr(port, 1);
 		mvebu_sw_pci_bridge_init(port);
 	}
 
 	pcie->nports = i;
 
-	for (i = 0; i < (IO_SPACE_LIMIT - SZ_64K); i += SZ_64K)
-		pci_ioremap_io(i, pcie->io.start + i);
-
-	mvebu_pcie_enable(pcie);
-
-	platform_set_drvdata(pdev, pcie);
-
-	return 0;
+	list_splice_init(&pcie->resources, &bridge->windows);
+	bridge->dev.parent = dev;
+	bridge->sysdata = pcie;
+	bridge->busnr = 0;
+	bridge->ops = &mvebu_pcie_ops;
+	bridge->map_irq = of_irq_parse_and_map_pci;
+	bridge->swizzle_irq = pci_common_swizzle;
+	bridge->align_resource = mvebu_pcie_align_resource;
+	bridge->msi = pcie->msi;
+
+	return pci_host_probe(bridge);
 }
 
 static const struct of_device_id mvebu_pcie_of_match_table[] = {
diff --git a/drivers/pci/controller/pcie-cadence-ep.c b/drivers/pci/controller/pcie-cadence-ep.c
index e3fe4124e3af..9e87dd7f9ac3 100644
--- a/drivers/pci/controller/pcie-cadence-ep.c
+++ b/drivers/pci/controller/pcie-cadence-ep.c
@@ -238,7 +238,7 @@ static int cdns_pcie_ep_get_msi(struct pci_epc *epc, u8 fn)
 	struct cdns_pcie_ep *ep = epc_get_drvdata(epc);
 	struct cdns_pcie *pcie = &ep->pcie;
 	u32 cap = CDNS_PCIE_EP_FUNC_MSI_CAP_OFFSET;
-	u16 flags, mmc, mme;
+	u16 flags, mme;
 
 	/* Validate that the MSI feature is actually enabled. */
 	flags = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSI_FLAGS);
@@ -249,7 +249,6 @@ static int cdns_pcie_ep_get_msi(struct pci_epc *epc, u8 fn)
 	 * Get the Multiple Message Enable bitfield from the Message Control
 	 * register.
 	 */
-	mmc = (flags & PCI_MSI_FLAGS_QMASK) >> 1;
 	mme = (flags & PCI_MSI_FLAGS_QSIZE) >> 4;
 
 	return mme;
@@ -363,7 +362,8 @@ static int cdns_pcie_ep_send_msi_irq(struct cdns_pcie_ep *ep, u8 fn,
 }
 
 static int cdns_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn,
-				  enum pci_epc_irq_type type, u8 interrupt_num)
+				  enum pci_epc_irq_type type,
+				  u16 interrupt_num)
 {
 	struct cdns_pcie_ep *ep = epc_get_drvdata(epc);
 
@@ -439,6 +439,7 @@ static int cdns_pcie_ep_probe(struct platform_device *pdev)
 	struct pci_epc *epc;
 	struct resource *res;
 	int ret;
+	int phy_count;
 
 	ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL);
 	if (!ep)
@@ -473,6 +474,12 @@ static int cdns_pcie_ep_probe(struct platform_device *pdev)
 	if (!ep->ob_addr)
 		return -ENOMEM;
 
+	ret = cdns_pcie_init_phy(dev, pcie);
+	if (ret) {
+		dev_err(dev, "failed to init phy\n");
+		return ret;
+	}
+	platform_set_drvdata(pdev, pcie);
 	pm_runtime_enable(dev);
 	ret = pm_runtime_get_sync(dev);
 	if (ret < 0) {
@@ -521,6 +528,10 @@ static int cdns_pcie_ep_probe(struct platform_device *pdev)
 
  err_get_sync:
 	pm_runtime_disable(dev);
+	cdns_pcie_disable_phy(pcie);
+	phy_count = pcie->phy_count;
+	while (phy_count--)
+		device_link_del(pcie->link[phy_count]);
 
 	return ret;
 }
@@ -528,6 +539,7 @@ static int cdns_pcie_ep_probe(struct platform_device *pdev)
 static void cdns_pcie_ep_shutdown(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
+	struct cdns_pcie *pcie = dev_get_drvdata(dev);
 	int ret;
 
 	ret = pm_runtime_put_sync(dev);
@@ -536,13 +548,14 @@ static void cdns_pcie_ep_shutdown(struct platform_device *pdev)
 
 	pm_runtime_disable(dev);
 
-	/* The PCIe controller can't be disabled. */
+	cdns_pcie_disable_phy(pcie);
 }
 
 static struct platform_driver cdns_pcie_ep_driver = {
 	.driver = {
 		.name = "cdns-pcie-ep",
 		.of_match_table = cdns_pcie_ep_of_match,
+		.pm	= &cdns_pcie_pm_ops,
 	},
 	.probe = cdns_pcie_ep_probe,
 	.shutdown = cdns_pcie_ep_shutdown,
diff --git a/drivers/pci/controller/pcie-cadence-host.c b/drivers/pci/controller/pcie-cadence-host.c
index a4ebbd37b553..ec394f6a19c8 100644
--- a/drivers/pci/controller/pcie-cadence-host.c
+++ b/drivers/pci/controller/pcie-cadence-host.c
@@ -58,6 +58,11 @@ static void __iomem *cdns_pci_map_bus(struct pci_bus *bus, unsigned int devfn,
 
 		return pcie->reg_base + (where & 0xfff);
 	}
+	/* Check that the link is up */
+	if (!(cdns_pcie_readl(pcie, CDNS_PCIE_LM_BASE) & 0x1))
+		return NULL;
+	/* Clear AXI link-down status */
+	cdns_pcie_writel(pcie, CDNS_PCIE_AT_LINKDOWN, 0x0);
 
 	/* Update Output registers for AXI region 0. */
 	addr0 = CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_NBITS(12) |
@@ -239,6 +244,7 @@ static int cdns_pcie_host_probe(struct platform_device *pdev)
 	struct cdns_pcie *pcie;
 	struct resource *res;
 	int ret;
+	int phy_count;
 
 	bridge = devm_pci_alloc_host_bridge(dev, sizeof(*rc));
 	if (!bridge)
@@ -290,6 +296,13 @@ static int cdns_pcie_host_probe(struct platform_device *pdev)
 	}
 	pcie->mem_res = res;
 
+	ret = cdns_pcie_init_phy(dev, pcie);
+	if (ret) {
+		dev_err(dev, "failed to init phy\n");
+		return ret;
+	}
+	platform_set_drvdata(pdev, pcie);
+
 	pm_runtime_enable(dev);
 	ret = pm_runtime_get_sync(dev);
 	if (ret < 0) {
@@ -322,15 +335,35 @@ static int cdns_pcie_host_probe(struct platform_device *pdev)
 
  err_get_sync:
 	pm_runtime_disable(dev);
+	cdns_pcie_disable_phy(pcie);
+	phy_count = pcie->phy_count;
+	while (phy_count--)
+		device_link_del(pcie->link[phy_count]);
 
 	return ret;
 }
 
+static void cdns_pcie_shutdown(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct cdns_pcie *pcie = dev_get_drvdata(dev);
+	int ret;
+
+	ret = pm_runtime_put_sync(dev);
+	if (ret < 0)
+		dev_dbg(dev, "pm_runtime_put_sync failed\n");
+
+	pm_runtime_disable(dev);
+	cdns_pcie_disable_phy(pcie);
+}
+
 static struct platform_driver cdns_pcie_host_driver = {
 	.driver = {
 		.name = "cdns-pcie-host",
 		.of_match_table = cdns_pcie_host_of_match,
+		.pm	= &cdns_pcie_pm_ops,
 	},
 	.probe = cdns_pcie_host_probe,
+	.shutdown = cdns_pcie_shutdown,
 };
 builtin_platform_driver(cdns_pcie_host_driver);
diff --git a/drivers/pci/controller/pcie-cadence.c b/drivers/pci/controller/pcie-cadence.c
index 138d113eb45d..86f1b002c846 100644
--- a/drivers/pci/controller/pcie-cadence.c
+++ b/drivers/pci/controller/pcie-cadence.c
@@ -124,3 +124,126 @@ void cdns_pcie_reset_outbound_region(struct cdns_pcie *pcie, u32 r)
 	cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR0(r), 0);
 	cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR1(r), 0);
 }
+
+void cdns_pcie_disable_phy(struct cdns_pcie *pcie)
+{
+	int i = pcie->phy_count;
+
+	while (i--) {
+		phy_power_off(pcie->phy[i]);
+		phy_exit(pcie->phy[i]);
+	}
+}
+
+int cdns_pcie_enable_phy(struct cdns_pcie *pcie)
+{
+	int ret;
+	int i;
+
+	for (i = 0; i < pcie->phy_count; i++) {
+		ret = phy_init(pcie->phy[i]);
+		if (ret < 0)
+			goto err_phy;
+
+		ret = phy_power_on(pcie->phy[i]);
+		if (ret < 0) {
+			phy_exit(pcie->phy[i]);
+			goto err_phy;
+		}
+	}
+
+	return 0;
+
+err_phy:
+	while (--i >= 0) {
+		phy_power_off(pcie->phy[i]);
+		phy_exit(pcie->phy[i]);
+	}
+
+	return ret;
+}
+
+int cdns_pcie_init_phy(struct device *dev, struct cdns_pcie *pcie)
+{
+	struct device_node *np = dev->of_node;
+	int phy_count;
+	struct phy **phy;
+	struct device_link **link;
+	int i;
+	int ret;
+	const char *name;
+
+	phy_count = of_property_count_strings(np, "phy-names");
+	if (phy_count < 1) {
+		dev_err(dev, "no phy-names.  PHY will not be initialized\n");
+		pcie->phy_count = 0;
+		return 0;
+	}
+
+	phy = devm_kzalloc(dev, sizeof(*phy) * phy_count, GFP_KERNEL);
+	if (!phy)
+		return -ENOMEM;
+
+	link = devm_kzalloc(dev, sizeof(*link) * phy_count, GFP_KERNEL);
+	if (!link)
+		return -ENOMEM;
+
+	for (i = 0; i < phy_count; i++) {
+		of_property_read_string_index(np, "phy-names", i, &name);
+		phy[i] = devm_phy_optional_get(dev, name);
+		if (IS_ERR(phy))
+			return PTR_ERR(phy);
+
+		link[i] = device_link_add(dev, &phy[i]->dev, DL_FLAG_STATELESS);
+		if (!link[i]) {
+			ret = -EINVAL;
+			goto err_link;
+		}
+	}
+
+	pcie->phy_count = phy_count;
+	pcie->phy = phy;
+	pcie->link = link;
+
+	ret =  cdns_pcie_enable_phy(pcie);
+	if (ret)
+		goto err_link;
+
+	return 0;
+
+err_link:
+	while (--i >= 0)
+		device_link_del(link[i]);
+
+	return ret;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int cdns_pcie_suspend_noirq(struct device *dev)
+{
+	struct cdns_pcie *pcie = dev_get_drvdata(dev);
+
+	cdns_pcie_disable_phy(pcie);
+
+	return 0;
+}
+
+static int cdns_pcie_resume_noirq(struct device *dev)
+{
+	struct cdns_pcie *pcie = dev_get_drvdata(dev);
+	int ret;
+
+	ret = cdns_pcie_enable_phy(pcie);
+	if (ret) {
+		dev_err(dev, "failed to enable phy\n");
+		return ret;
+	}
+
+	return 0;
+}
+#endif
+
+const struct dev_pm_ops cdns_pcie_pm_ops = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(cdns_pcie_suspend_noirq,
+				      cdns_pcie_resume_noirq)
+};
diff --git a/drivers/pci/controller/pcie-cadence.h b/drivers/pci/controller/pcie-cadence.h
index 4bb27333b05c..ae6bf2a2b3d3 100644
--- a/drivers/pci/controller/pcie-cadence.h
+++ b/drivers/pci/controller/pcie-cadence.h
@@ -8,6 +8,7 @@
 
 #include <linux/kernel.h>
 #include <linux/pci.h>
+#include <linux/phy/phy.h>
 
 /*
  * Local Management Registers
@@ -165,6 +166,9 @@
 #define CDNS_PCIE_AT_IB_RP_BAR_ADDR1(bar) \
 	(CDNS_PCIE_AT_BASE + 0x0804 + (bar) * 0x0008)
 
+/* AXI link down register */
+#define CDNS_PCIE_AT_LINKDOWN (CDNS_PCIE_AT_BASE + 0x0824)
+
 enum cdns_pcie_rp_bar {
 	RP_BAR0,
 	RP_BAR1,
@@ -229,6 +233,9 @@ struct cdns_pcie {
 	struct resource		*mem_res;
 	bool			is_rc;
 	u8			bus;
+	int			phy_count;
+	struct phy		**phy;
+	struct device_link	**link;
 };
 
 /* Register access */
@@ -279,7 +286,7 @@ static inline void cdns_pcie_ep_fn_writew(struct cdns_pcie *pcie, u8 fn,
 }
 
 static inline void cdns_pcie_ep_fn_writel(struct cdns_pcie *pcie, u8 fn,
-					  u32 reg, u16 value)
+					  u32 reg, u32 value)
 {
 	writel(value, pcie->reg_base + CDNS_PCIE_EP_FUNC_BASE(fn) + reg);
 }
@@ -307,5 +314,9 @@ void cdns_pcie_set_outbound_region_for_normal_msg(struct cdns_pcie *pcie, u8 fn,
 						  u32 r, u64 cpu_addr);
 
 void cdns_pcie_reset_outbound_region(struct cdns_pcie *pcie, u32 r);
+void cdns_pcie_disable_phy(struct cdns_pcie *pcie);
+int cdns_pcie_enable_phy(struct cdns_pcie *pcie);
+int cdns_pcie_init_phy(struct device *dev, struct cdns_pcie *pcie);
+extern const struct dev_pm_ops cdns_pcie_pm_ops;
 
 #endif /* _PCIE_CADENCE_H */
diff --git a/drivers/pci/controller/pcie-iproc.c b/drivers/pci/controller/pcie-iproc.c
index 3c76c5fa4f32..3160e9342a2f 100644
--- a/drivers/pci/controller/pcie-iproc.c
+++ b/drivers/pci/controller/pcie-iproc.c
@@ -85,6 +85,8 @@
 #define IMAP_VALID_SHIFT		0
 #define IMAP_VALID			BIT(IMAP_VALID_SHIFT)
 
+#define IPROC_PCI_PM_CAP		0x48
+#define IPROC_PCI_PM_CAP_MASK		0xffff
 #define IPROC_PCI_EXP_CAP		0xac
 
 #define IPROC_PCIE_REG_INVALID		0xffff
@@ -375,6 +377,17 @@ static const u16 iproc_pcie_reg_paxc_v2[] = {
 	[IPROC_PCIE_CFG_DATA]		= 0x1fc,
 };
 
+/*
+ * List of device IDs of controllers that have corrupted capability list that
+ * require SW fixup
+ */
+static const u16 iproc_pcie_corrupt_cap_did[] = {
+	0x16cd,
+	0x16f0,
+	0xd802,
+	0xd804
+};
+
 static inline struct iproc_pcie *iproc_data(struct pci_bus *bus)
 {
 	struct iproc_pcie *pcie = bus->sysdata;
@@ -495,6 +508,49 @@ static unsigned int iproc_pcie_cfg_retry(void __iomem *cfg_data_p)
 	return data;
 }
 
+static void iproc_pcie_fix_cap(struct iproc_pcie *pcie, int where, u32 *val)
+{
+	u32 i, dev_id;
+
+	switch (where & ~0x3) {
+	case PCI_VENDOR_ID:
+		dev_id = *val >> 16;
+
+		/*
+		 * Activate fixup for those controllers that have corrupted
+		 * capability list registers
+		 */
+		for (i = 0; i < ARRAY_SIZE(iproc_pcie_corrupt_cap_did); i++)
+			if (dev_id == iproc_pcie_corrupt_cap_did[i])
+				pcie->fix_paxc_cap = true;
+		break;
+
+	case IPROC_PCI_PM_CAP:
+		if (pcie->fix_paxc_cap) {
+			/* advertise PM, force next capability to PCIe */
+			*val &= ~IPROC_PCI_PM_CAP_MASK;
+			*val |= IPROC_PCI_EXP_CAP << 8 | PCI_CAP_ID_PM;
+		}
+		break;
+
+	case IPROC_PCI_EXP_CAP:
+		if (pcie->fix_paxc_cap) {
+			/* advertise root port, version 2, terminate here */
+			*val = (PCI_EXP_TYPE_ROOT_PORT << 4 | 2) << 16 |
+				PCI_CAP_ID_EXP;
+		}
+		break;
+
+	case IPROC_PCI_EXP_CAP + PCI_EXP_RTCTL:
+		/* Don't advertise CRS SV support */
+		*val &= ~(PCI_EXP_RTCAP_CRSVIS << 16);
+		break;
+
+	default:
+		break;
+	}
+}
+
 static int iproc_pcie_config_read(struct pci_bus *bus, unsigned int devfn,
 				  int where, int size, u32 *val)
 {
@@ -509,13 +565,10 @@ static int iproc_pcie_config_read(struct pci_bus *bus, unsigned int devfn,
 	/* root complex access */
 	if (busno == 0) {
 		ret = pci_generic_config_read32(bus, devfn, where, size, val);
-		if (ret != PCIBIOS_SUCCESSFUL)
-			return ret;
+		if (ret == PCIBIOS_SUCCESSFUL)
+			iproc_pcie_fix_cap(pcie, where, val);
 
-		/* Don't advertise CRS SV support */
-		if ((where & ~0x3) == IPROC_PCI_EXP_CAP + PCI_EXP_RTCTL)
-			*val &= ~(PCI_EXP_RTCAP_CRSVIS << 16);
-		return PCIBIOS_SUCCESSFUL;
+		return ret;
 	}
 
 	cfg_data_p = iproc_pcie_map_ep_cfg_reg(pcie, busno, slot, fn, where);
@@ -529,6 +582,25 @@ static int iproc_pcie_config_read(struct pci_bus *bus, unsigned int devfn,
 	if (size <= 2)
 		*val = (data >> (8 * (where & 3))) & ((1 << (size * 8)) - 1);
 
+	/*
+	 * For PAXC and PAXCv2, the total number of PFs that one can enumerate
+	 * depends on the firmware configuration. Unfortunately, due to an ASIC
+	 * bug, unconfigured PFs cannot be properly hidden from the root
+	 * complex. As a result, write access to these PFs will cause bus lock
+	 * up on the embedded processor
+	 *
+	 * Since all unconfigured PFs are left with an incorrect, staled device
+	 * ID of 0x168e (PCI_DEVICE_ID_NX2_57810), we try to catch those access
+	 * early here and reject them all
+	 */
+#define DEVICE_ID_MASK     0xffff0000
+#define DEVICE_ID_SHIFT    16
+	if (pcie->rej_unconfig_pf &&
+	    (where & CFG_ADDR_REG_NUM_MASK) == PCI_VENDOR_ID)
+		if ((*val & DEVICE_ID_MASK) ==
+		    (PCI_DEVICE_ID_NX2_57810 << DEVICE_ID_SHIFT))
+			return PCIBIOS_FUNC_NOT_SUPPORTED;
+
 	return PCIBIOS_SUCCESSFUL;
 }
 
@@ -628,7 +700,7 @@ static int iproc_pcie_config_read32(struct pci_bus *bus, unsigned int devfn,
 	struct iproc_pcie *pcie = iproc_data(bus);
 
 	iproc_pcie_apb_err_disable(bus, true);
-	if (pcie->type == IPROC_PCIE_PAXB_V2)
+	if (pcie->iproc_cfg_read)
 		ret = iproc_pcie_config_read(bus, devfn, where, size, val);
 	else
 		ret = pci_generic_config_read32(bus, devfn, where, size, val);
@@ -808,14 +880,14 @@ static inline int iproc_pcie_ob_write(struct iproc_pcie *pcie, int window_idx,
 	writel(lower_32_bits(pci_addr), pcie->base + omap_offset);
 	writel(upper_32_bits(pci_addr), pcie->base + omap_offset + 4);
 
-	dev_info(dev, "ob window [%d]: offset 0x%x axi %pap pci %pap\n",
-		 window_idx, oarr_offset, &axi_addr, &pci_addr);
-	dev_info(dev, "oarr lo 0x%x oarr hi 0x%x\n",
-		 readl(pcie->base + oarr_offset),
-		 readl(pcie->base + oarr_offset + 4));
-	dev_info(dev, "omap lo 0x%x omap hi 0x%x\n",
-		 readl(pcie->base + omap_offset),
-		 readl(pcie->base + omap_offset + 4));
+	dev_dbg(dev, "ob window [%d]: offset 0x%x axi %pap pci %pap\n",
+		window_idx, oarr_offset, &axi_addr, &pci_addr);
+	dev_dbg(dev, "oarr lo 0x%x oarr hi 0x%x\n",
+		readl(pcie->base + oarr_offset),
+		readl(pcie->base + oarr_offset + 4));
+	dev_dbg(dev, "omap lo 0x%x omap hi 0x%x\n",
+		readl(pcie->base + omap_offset),
+		readl(pcie->base + omap_offset + 4));
 
 	return 0;
 }
@@ -982,8 +1054,8 @@ static int iproc_pcie_ib_write(struct iproc_pcie *pcie, int region_idx,
 	    iproc_pcie_reg_is_invalid(imap_offset))
 		return -EINVAL;
 
-	dev_info(dev, "ib region [%d]: offset 0x%x axi %pap pci %pap\n",
-		 region_idx, iarr_offset, &axi_addr, &pci_addr);
+	dev_dbg(dev, "ib region [%d]: offset 0x%x axi %pap pci %pap\n",
+		region_idx, iarr_offset, &axi_addr, &pci_addr);
 
 	/*
 	 * Program the IARR registers.  The upper 32-bit IARR register is
@@ -993,9 +1065,9 @@ static int iproc_pcie_ib_write(struct iproc_pcie *pcie, int region_idx,
 	       pcie->base + iarr_offset);
 	writel(upper_32_bits(pci_addr), pcie->base + iarr_offset + 4);
 
-	dev_info(dev, "iarr lo 0x%x iarr hi 0x%x\n",
-		 readl(pcie->base + iarr_offset),
-		 readl(pcie->base + iarr_offset + 4));
+	dev_dbg(dev, "iarr lo 0x%x iarr hi 0x%x\n",
+		readl(pcie->base + iarr_offset),
+		readl(pcie->base + iarr_offset + 4));
 
 	/*
 	 * Now program the IMAP registers.  Each IARR region may have one or
@@ -1009,10 +1081,10 @@ static int iproc_pcie_ib_write(struct iproc_pcie *pcie, int region_idx,
 		writel(upper_32_bits(axi_addr),
 		       pcie->base + imap_offset + ib_map->imap_addr_offset);
 
-		dev_info(dev, "imap window [%d] lo 0x%x hi 0x%x\n",
-			 window_idx, readl(pcie->base + imap_offset),
-			 readl(pcie->base + imap_offset +
-			       ib_map->imap_addr_offset));
+		dev_dbg(dev, "imap window [%d] lo 0x%x hi 0x%x\n",
+			window_idx, readl(pcie->base + imap_offset),
+			readl(pcie->base + imap_offset +
+			      ib_map->imap_addr_offset));
 
 		imap_offset += ib_map->imap_window_offset;
 		axi_addr += size;
@@ -1144,10 +1216,22 @@ static int iproc_pcie_paxb_v2_msi_steer(struct iproc_pcie *pcie, u64 msi_addr)
 	return ret;
 }
 
-static void iproc_pcie_paxc_v2_msi_steer(struct iproc_pcie *pcie, u64 msi_addr)
+static void iproc_pcie_paxc_v2_msi_steer(struct iproc_pcie *pcie, u64 msi_addr,
+					 bool enable)
 {
 	u32 val;
 
+	if (!enable) {
+		/*
+		 * Disable PAXC MSI steering. All write transfers will be
+		 * treated as non-MSI transfers
+		 */
+		val = iproc_pcie_read_reg(pcie, IPROC_PCIE_MSI_EN_CFG);
+		val &= ~MSI_ENABLE_CFG;
+		iproc_pcie_write_reg(pcie, IPROC_PCIE_MSI_EN_CFG, val);
+		return;
+	}
+
 	/*
 	 * Program bits [43:13] of address of GITS_TRANSLATER register into
 	 * bits [30:0] of the MSI base address register.  In fact, in all iProc
@@ -1201,7 +1285,7 @@ static int iproc_pcie_msi_steer(struct iproc_pcie *pcie,
 			return ret;
 		break;
 	case IPROC_PCIE_PAXC_V2:
-		iproc_pcie_paxc_v2_msi_steer(pcie, msi_addr);
+		iproc_pcie_paxc_v2_msi_steer(pcie, msi_addr, true);
 		break;
 	default:
 		return -EINVAL;
@@ -1271,6 +1355,7 @@ static int iproc_pcie_rev_init(struct iproc_pcie *pcie)
 		break;
 	case IPROC_PCIE_PAXB:
 		regs = iproc_pcie_reg_paxb;
+		pcie->iproc_cfg_read = true;
 		pcie->has_apb_err_disable = true;
 		if (pcie->need_ob_cfg) {
 			pcie->ob_map = paxb_ob_map;
@@ -1293,10 +1378,14 @@ static int iproc_pcie_rev_init(struct iproc_pcie *pcie)
 	case IPROC_PCIE_PAXC:
 		regs = iproc_pcie_reg_paxc;
 		pcie->ep_is_internal = true;
+		pcie->iproc_cfg_read = true;
+		pcie->rej_unconfig_pf = true;
 		break;
 	case IPROC_PCIE_PAXC_V2:
 		regs = iproc_pcie_reg_paxc_v2;
 		pcie->ep_is_internal = true;
+		pcie->iproc_cfg_read = true;
+		pcie->rej_unconfig_pf = true;
 		pcie->need_msi_steer = true;
 		break;
 	default:
@@ -1427,6 +1516,24 @@ int iproc_pcie_remove(struct iproc_pcie *pcie)
 }
 EXPORT_SYMBOL(iproc_pcie_remove);
 
+/*
+ * The MSI parsing logic in certain revisions of Broadcom PAXC based root
+ * complex does not work and needs to be disabled
+ */
+static void quirk_paxc_disable_msi_parsing(struct pci_dev *pdev)
+{
+	struct iproc_pcie *pcie = iproc_data(pdev->bus);
+
+	if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
+		iproc_pcie_paxc_v2_msi_steer(pcie, 0, false);
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16f0,
+			quirk_paxc_disable_msi_parsing);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd802,
+			quirk_paxc_disable_msi_parsing);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd804,
+			quirk_paxc_disable_msi_parsing);
+
 MODULE_AUTHOR("Ray Jui <rjui@broadcom.com>");
 MODULE_DESCRIPTION("Broadcom iPROC PCIe common driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/controller/pcie-iproc.h b/drivers/pci/controller/pcie-iproc.h
index 814b600b383a..4f03ea539805 100644
--- a/drivers/pci/controller/pcie-iproc.h
+++ b/drivers/pci/controller/pcie-iproc.h
@@ -58,8 +58,13 @@ struct iproc_msi;
  * @phy: optional PHY device that controls the Serdes
  * @map_irq: function callback to map interrupts
  * @ep_is_internal: indicates an internal emulated endpoint device is connected
+ * @iproc_cfg_read: indicates the iProc config read function should be used
+ * @rej_unconfig_pf: indicates the root complex needs to detect and reject
+ * enumeration against unconfigured physical functions emulated in the ASIC
  * @has_apb_err_disable: indicates the controller can be configured to prevent
  * unsupported request from being forwarded as an APB bus error
+ * @fix_paxc_cap: indicates the controller has corrupted capability list in its
+ * config space registers and requires SW based fixup
  *
  * @need_ob_cfg: indicates SW needs to configure the outbound mapping window
  * @ob: outbound mapping related parameters
@@ -84,7 +89,10 @@ struct iproc_pcie {
 	struct phy *phy;
 	int (*map_irq)(const struct pci_dev *, u8, u8);
 	bool ep_is_internal;
+	bool iproc_cfg_read;
+	bool rej_unconfig_pf;
 	bool has_apb_err_disable;
+	bool fix_paxc_cap;
 
 	bool need_ob_cfg;
 	struct iproc_pcie_ob ob;
diff --git a/drivers/pci/controller/pcie-mobiveil.c b/drivers/pci/controller/pcie-mobiveil.c
index cf0aa7cee5b0..a939e8d31735 100644
--- a/drivers/pci/controller/pcie-mobiveil.c
+++ b/drivers/pci/controller/pcie-mobiveil.c
@@ -23,6 +23,8 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 
+#include "../pci.h"
+
 /* register offsets and bit positions */
 
 /*
@@ -130,7 +132,7 @@ struct mobiveil_pcie {
 	void __iomem *config_axi_slave_base;	/* endpoint config base */
 	void __iomem *csr_axi_slave_base;	/* root port config base */
 	void __iomem *apb_csr_base;	/* MSI register base */
-	void __iomem *pcie_reg_base;	/* Physical PCIe Controller Base */
+	phys_addr_t pcie_reg_base;	/* Physical PCIe Controller Base */
 	struct irq_domain *intx_domain;
 	raw_spinlock_t intx_mask_lock;
 	int irq;
diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index 6beba8ed7b84..b8163c56a142 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -472,7 +472,7 @@ static int rockchip_pcie_ep_send_msi_irq(struct rockchip_pcie_ep *ep, u8 fn,
 
 static int rockchip_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn,
 				      enum pci_epc_irq_type type,
-				      u8 interrupt_num)
+				      u16 interrupt_num)
 {
 	struct rockchip_pcie_ep *ep = epc_get_drvdata(epc);
 
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 942b64fc7f1f..fd2dbd7eed7b 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -197,9 +197,20 @@ static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd, struct msi_desc *d
 	int i, best = 1;
 	unsigned long flags;
 
-	if (pci_is_bridge(msi_desc_to_pci_dev(desc)) || vmd->msix_count == 1)
+	if (vmd->msix_count == 1)
 		return &vmd->irqs[0];
 
+	/*
+	 * White list for fast-interrupt handlers. All others will share the
+	 * "slow" interrupt vector.
+	 */
+	switch (msi_desc_to_pci_dev(desc)->class) {
+	case PCI_CLASS_STORAGE_EXPRESS:
+		break;
+	default:
+		return &vmd->irqs[0];
+	}
+
 	raw_spin_lock_irqsave(&list_lock, flags);
 	for (i = 1; i < vmd->msix_count; i++)
 		if (vmd->irqs[i].count < vmd->irqs[best].count)
diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index 63ed706445b9..3e86fa3c7da3 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -18,13 +18,16 @@
 #include <linux/pci-epf.h>
 #include <linux/pci_regs.h>
 
+#define IRQ_TYPE_LEGACY			0
+#define IRQ_TYPE_MSI			1
+#define IRQ_TYPE_MSIX			2
+
 #define COMMAND_RAISE_LEGACY_IRQ	BIT(0)
 #define COMMAND_RAISE_MSI_IRQ		BIT(1)
-#define MSI_NUMBER_SHIFT		2
-#define MSI_NUMBER_MASK			(0x3f << MSI_NUMBER_SHIFT)
-#define COMMAND_READ			BIT(8)
-#define COMMAND_WRITE			BIT(9)
-#define COMMAND_COPY			BIT(10)
+#define COMMAND_RAISE_MSIX_IRQ		BIT(2)
+#define COMMAND_READ			BIT(3)
+#define COMMAND_WRITE			BIT(4)
+#define COMMAND_COPY			BIT(5)
 
 #define STATUS_READ_SUCCESS		BIT(0)
 #define STATUS_READ_FAIL		BIT(1)
@@ -45,6 +48,7 @@ struct pci_epf_test {
 	struct pci_epf		*epf;
 	enum pci_barno		test_reg_bar;
 	bool			linkup_notifier;
+	bool			msix_available;
 	struct delayed_work	cmd_handler;
 };
 
@@ -56,6 +60,8 @@ struct pci_epf_test_reg {
 	u64	dst_addr;
 	u32	size;
 	u32	checksum;
+	u32	irq_type;
+	u32	irq_number;
 } __packed;
 
 static struct pci_epf_header test_header = {
@@ -244,31 +250,42 @@ err:
 	return ret;
 }
 
-static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test, u8 irq)
+static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test, u8 irq_type,
+				   u16 irq)
 {
-	u8 msi_count;
 	struct pci_epf *epf = epf_test->epf;
+	struct device *dev = &epf->dev;
 	struct pci_epc *epc = epf->epc;
 	enum pci_barno test_reg_bar = epf_test->test_reg_bar;
 	struct pci_epf_test_reg *reg = epf_test->reg[test_reg_bar];
 
 	reg->status |= STATUS_IRQ_RAISED;
-	msi_count = pci_epc_get_msi(epc, epf->func_no);
-	if (irq > msi_count || msi_count <= 0)
+
+	switch (irq_type) {
+	case IRQ_TYPE_LEGACY:
 		pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_LEGACY, 0);
-	else
+		break;
+	case IRQ_TYPE_MSI:
 		pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSI, irq);
+		break;
+	case IRQ_TYPE_MSIX:
+		pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSIX, irq);
+		break;
+	default:
+		dev_err(dev, "Failed to raise IRQ, unknown type\n");
+		break;
+	}
 }
 
 static void pci_epf_test_cmd_handler(struct work_struct *work)
 {
 	int ret;
-	u8 irq;
-	u8 msi_count;
+	int count;
 	u32 command;
 	struct pci_epf_test *epf_test = container_of(work, struct pci_epf_test,
 						     cmd_handler.work);
 	struct pci_epf *epf = epf_test->epf;
+	struct device *dev = &epf->dev;
 	struct pci_epc *epc = epf->epc;
 	enum pci_barno test_reg_bar = epf_test->test_reg_bar;
 	struct pci_epf_test_reg *reg = epf_test->reg[test_reg_bar];
@@ -280,7 +297,10 @@ static void pci_epf_test_cmd_handler(struct work_struct *work)
 	reg->command = 0;
 	reg->status = 0;
 
-	irq = (command & MSI_NUMBER_MASK) >> MSI_NUMBER_SHIFT;
+	if (reg->irq_type > IRQ_TYPE_MSIX) {
+		dev_err(dev, "Failed to detect IRQ type\n");
+		goto reset_handler;
+	}
 
 	if (command & COMMAND_RAISE_LEGACY_IRQ) {
 		reg->status = STATUS_IRQ_RAISED;
@@ -294,7 +314,8 @@ static void pci_epf_test_cmd_handler(struct work_struct *work)
 			reg->status |= STATUS_WRITE_FAIL;
 		else
 			reg->status |= STATUS_WRITE_SUCCESS;
-		pci_epf_test_raise_irq(epf_test, irq);
+		pci_epf_test_raise_irq(epf_test, reg->irq_type,
+				       reg->irq_number);
 		goto reset_handler;
 	}
 
@@ -304,7 +325,8 @@ static void pci_epf_test_cmd_handler(struct work_struct *work)
 			reg->status |= STATUS_READ_SUCCESS;
 		else
 			reg->status |= STATUS_READ_FAIL;
-		pci_epf_test_raise_irq(epf_test, irq);
+		pci_epf_test_raise_irq(epf_test, reg->irq_type,
+				       reg->irq_number);
 		goto reset_handler;
 	}
 
@@ -314,16 +336,28 @@ static void pci_epf_test_cmd_handler(struct work_struct *work)
 			reg->status |= STATUS_COPY_SUCCESS;
 		else
 			reg->status |= STATUS_COPY_FAIL;
-		pci_epf_test_raise_irq(epf_test, irq);
+		pci_epf_test_raise_irq(epf_test, reg->irq_type,
+				       reg->irq_number);
 		goto reset_handler;
 	}
 
 	if (command & COMMAND_RAISE_MSI_IRQ) {
-		msi_count = pci_epc_get_msi(epc, epf->func_no);
-		if (irq > msi_count || msi_count <= 0)
+		count = pci_epc_get_msi(epc, epf->func_no);
+		if (reg->irq_number > count || count <= 0)
 			goto reset_handler;
 		reg->status = STATUS_IRQ_RAISED;
-		pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSI, irq);
+		pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSI,
+				  reg->irq_number);
+		goto reset_handler;
+	}
+
+	if (command & COMMAND_RAISE_MSIX_IRQ) {
+		count = pci_epc_get_msix(epc, epf->func_no);
+		if (reg->irq_number > count || count <= 0)
+			goto reset_handler;
+		reg->status = STATUS_IRQ_RAISED;
+		pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSIX,
+				  reg->irq_number);
 		goto reset_handler;
 	}
 
@@ -440,6 +474,8 @@ static int pci_epf_test_bind(struct pci_epf *epf)
 	else
 		epf_test->linkup_notifier = true;
 
+	epf_test->msix_available = epc->features & EPC_FEATURE_MSIX_AVAILABLE;
+
 	epf_test->test_reg_bar = EPC_FEATURE_GET_BAR(epc->features);
 
 	ret = pci_epc_write_header(epc, epf->func_no, header);
@@ -457,8 +493,18 @@ static int pci_epf_test_bind(struct pci_epf *epf)
 		return ret;
 
 	ret = pci_epc_set_msi(epc, epf->func_no, epf->msi_interrupts);
-	if (ret)
+	if (ret) {
+		dev_err(dev, "MSI configuration failed\n");
 		return ret;
+	}
+
+	if (epf_test->msix_available) {
+		ret = pci_epc_set_msix(epc, epf->func_no, epf->msix_interrupts);
+		if (ret) {
+			dev_err(dev, "MSI-X configuration failed\n");
+			return ret;
+		}
+	}
 
 	if (!epf_test->linkup_notifier)
 		queue_work(kpcitest_workqueue, &epf_test->cmd_handler.work);
diff --git a/drivers/pci/endpoint/pci-ep-cfs.c b/drivers/pci/endpoint/pci-ep-cfs.c
index 018ea3433cb5..d1288a0bd530 100644
--- a/drivers/pci/endpoint/pci-ep-cfs.c
+++ b/drivers/pci/endpoint/pci-ep-cfs.c
@@ -286,6 +286,28 @@ static ssize_t pci_epf_msi_interrupts_show(struct config_item *item,
 		       to_pci_epf_group(item)->epf->msi_interrupts);
 }
 
+static ssize_t pci_epf_msix_interrupts_store(struct config_item *item,
+					     const char *page, size_t len)
+{
+	u16 val;
+	int ret;
+
+	ret = kstrtou16(page, 0, &val);
+	if (ret)
+		return ret;
+
+	to_pci_epf_group(item)->epf->msix_interrupts = val;
+
+	return len;
+}
+
+static ssize_t pci_epf_msix_interrupts_show(struct config_item *item,
+					    char *page)
+{
+	return sprintf(page, "%d\n",
+		       to_pci_epf_group(item)->epf->msix_interrupts);
+}
+
 PCI_EPF_HEADER_R(vendorid)
 PCI_EPF_HEADER_W_u16(vendorid)
 
@@ -327,6 +349,7 @@ CONFIGFS_ATTR(pci_epf_, subsys_vendor_id);
 CONFIGFS_ATTR(pci_epf_, subsys_id);
 CONFIGFS_ATTR(pci_epf_, interrupt_pin);
 CONFIGFS_ATTR(pci_epf_, msi_interrupts);
+CONFIGFS_ATTR(pci_epf_, msix_interrupts);
 
 static struct configfs_attribute *pci_epf_attrs[] = {
 	&pci_epf_attr_vendorid,
@@ -340,6 +363,7 @@ static struct configfs_attribute *pci_epf_attrs[] = {
 	&pci_epf_attr_subsys_id,
 	&pci_epf_attr_interrupt_pin,
 	&pci_epf_attr_msi_interrupts,
+	&pci_epf_attr_msix_interrupts,
 	NULL,
 };
 
diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c
index b0ee42739c3c..094dcc3203b8 100644
--- a/drivers/pci/endpoint/pci-epc-core.c
+++ b/drivers/pci/endpoint/pci-epc-core.c
@@ -131,13 +131,13 @@ EXPORT_SYMBOL_GPL(pci_epc_start);
  * pci_epc_raise_irq() - interrupt the host system
  * @epc: the EPC device which has to interrupt the host
  * @func_no: the endpoint function number in the EPC device
- * @type: specify the type of interrupt; legacy or MSI
- * @interrupt_num: the MSI interrupt number
+ * @type: specify the type of interrupt; legacy, MSI or MSI-X
+ * @interrupt_num: the MSI or MSI-X interrupt number
  *
- * Invoke to raise an MSI or legacy interrupt
+ * Invoke to raise an legacy, MSI or MSI-X interrupt
  */
 int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no,
-		      enum pci_epc_irq_type type, u8 interrupt_num)
+		      enum pci_epc_irq_type type, u16 interrupt_num)
 {
 	int ret;
 	unsigned long flags;
@@ -201,7 +201,8 @@ int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts)
 	u8 encode_int;
 	unsigned long flags;
 
-	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions)
+	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions ||
+	    interrupts > 32)
 		return -EINVAL;
 
 	if (!epc->ops->set_msi)
@@ -218,6 +219,63 @@ int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts)
 EXPORT_SYMBOL_GPL(pci_epc_set_msi);
 
 /**
+ * pci_epc_get_msix() - get the number of MSI-X interrupt numbers allocated
+ * @epc: the EPC device to which MSI-X interrupts was requested
+ * @func_no: the endpoint function number in the EPC device
+ *
+ * Invoke to get the number of MSI-X interrupts allocated by the RC
+ */
+int pci_epc_get_msix(struct pci_epc *epc, u8 func_no)
+{
+	int interrupt;
+	unsigned long flags;
+
+	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions)
+		return 0;
+
+	if (!epc->ops->get_msix)
+		return 0;
+
+	spin_lock_irqsave(&epc->lock, flags);
+	interrupt = epc->ops->get_msix(epc, func_no);
+	spin_unlock_irqrestore(&epc->lock, flags);
+
+	if (interrupt < 0)
+		return 0;
+
+	return interrupt + 1;
+}
+EXPORT_SYMBOL_GPL(pci_epc_get_msix);
+
+/**
+ * pci_epc_set_msix() - set the number of MSI-X interrupt numbers required
+ * @epc: the EPC device on which MSI-X has to be configured
+ * @func_no: the endpoint function number in the EPC device
+ * @interrupts: number of MSI-X interrupts required by the EPF
+ *
+ * Invoke to set the required number of MSI-X interrupts.
+ */
+int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts)
+{
+	int ret;
+	unsigned long flags;
+
+	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions ||
+	    interrupts < 1 || interrupts > 2048)
+		return -EINVAL;
+
+	if (!epc->ops->set_msix)
+		return 0;
+
+	spin_lock_irqsave(&epc->lock, flags);
+	ret = epc->ops->set_msix(epc, func_no, interrupts - 1);
+	spin_unlock_irqrestore(&epc->lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pci_epc_set_msix);
+
+/**
  * pci_epc_unmap_addr() - unmap CPU address from PCI address
  * @epc: the EPC device on which address is allocated
  * @func_no: the endpoint function number in the EPC device
diff --git a/drivers/pci/hotplug/acpi_pcihp.c b/drivers/pci/hotplug/acpi_pcihp.c
index 5bd6c1573295..6b7c1ed58e7e 100644
--- a/drivers/pci/hotplug/acpi_pcihp.c
+++ b/drivers/pci/hotplug/acpi_pcihp.c
@@ -74,20 +74,6 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev)
 	struct acpi_buffer string = { ACPI_ALLOCATE_BUFFER, NULL };
 
 	/*
-	 * Per PCI firmware specification, we should run the ACPI _OSC
-	 * method to get control of hotplug hardware before using it. If
-	 * an _OSC is missing, we look for an OSHP to do the same thing.
-	 * To handle different BIOS behavior, we look for _OSC on a root
-	 * bridge preferentially (according to PCI fw spec). Later for
-	 * OSHP within the scope of the hotplug controller and its parents,
-	 * up to the host bridge under which this controller exists.
-	 */
-	if (shpchp_is_native(pdev))
-		return 0;
-
-	/* If _OSC exists, we should not evaluate OSHP */
-
-	/*
 	 * If there's no ACPI host bridge (i.e., ACPI support is compiled
 	 * into the kernel but the hardware platform doesn't support ACPI),
 	 * there's nothing to do here.
@@ -97,9 +83,25 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev)
 	if (!root)
 		return 0;
 
-	if (root->osc_support_set)
-		goto no_control;
+	/*
+	 * If _OSC exists, it determines whether we're allowed to manage
+	 * the SHPC.  We executed it while enumerating the host bridge.
+	 */
+	if (root->osc_support_set) {
+		if (host->native_shpc_hotplug)
+			return 0;
+		return -ENODEV;
+	}
 
+	/*
+	 * In the absence of _OSC, we're always allowed to manage the SHPC.
+	 * However, if an OSHP method is present, we must execute it so the
+	 * firmware can transfer control to the OS, e.g., direct interrupts
+	 * to the OS instead of to the firmware.
+	 *
+	 * N.B. The PCI Firmware Spec (r3.2, sec 4.8) does not endorse
+	 * searching up the ACPI hierarchy, so the loops below are suspect.
+	 */
 	handle = ACPI_HANDLE(&pdev->dev);
 	if (!handle) {
 		/*
@@ -128,7 +130,7 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev)
 		if (ACPI_FAILURE(status))
 			break;
 	}
-no_control:
+
 	pci_info(pdev, "Cannot get control of SHPC hotplug\n");
 	kfree(string.pointer);
 	return -ENODEV;
diff --git a/drivers/pci/hotplug/acpiphp_core.c b/drivers/pci/hotplug/acpiphp_core.c
index 12b5655fd390..ad32ffbc4b91 100644
--- a/drivers/pci/hotplug/acpiphp_core.c
+++ b/drivers/pci/hotplug/acpiphp_core.c
@@ -254,20 +254,6 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
 	return 0;
 }
 
-/**
- * release_slot - free up the memory used by a slot
- * @hotplug_slot: slot to free
- */
-static void release_slot(struct hotplug_slot *hotplug_slot)
-{
-	struct slot *slot = hotplug_slot->private;
-
-	pr_debug("%s - physical_slot = %s\n", __func__, slot_name(slot));
-
-	kfree(slot->hotplug_slot);
-	kfree(slot);
-}
-
 /* callback routine to initialize 'struct slot' for each slot */
 int acpiphp_register_hotplug_slot(struct acpiphp_slot *acpiphp_slot,
 				  unsigned int sun)
@@ -287,7 +273,6 @@ int acpiphp_register_hotplug_slot(struct acpiphp_slot *acpiphp_slot,
 	slot->hotplug_slot->info = &slot->info;
 
 	slot->hotplug_slot->private = slot;
-	slot->hotplug_slot->release = &release_slot;
 	slot->hotplug_slot->ops = &acpi_hotplug_slot_ops;
 
 	slot->acpi_slot = acpiphp_slot;
@@ -324,13 +309,12 @@ error:
 void acpiphp_unregister_hotplug_slot(struct acpiphp_slot *acpiphp_slot)
 {
 	struct slot *slot = acpiphp_slot->slot;
-	int retval = 0;
 
 	pr_info("Slot [%s] unregistered\n", slot_name(slot));
 
-	retval = pci_hp_deregister(slot->hotplug_slot);
-	if (retval)
-		pr_err("pci_hp_deregister failed with error %d\n", retval);
+	pci_hp_deregister(slot->hotplug_slot);
+	kfree(slot->hotplug_slot);
+	kfree(slot);
 }
 
 
diff --git a/drivers/pci/hotplug/cpci_hotplug_core.c b/drivers/pci/hotplug/cpci_hotplug_core.c
index 07b533adc9df..52a339baf06c 100644
--- a/drivers/pci/hotplug/cpci_hotplug_core.c
+++ b/drivers/pci/hotplug/cpci_hotplug_core.c
@@ -195,10 +195,8 @@ get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value)
 	return 0;
 }
 
-static void release_slot(struct hotplug_slot *hotplug_slot)
+static void release_slot(struct slot *slot)
 {
-	struct slot *slot = hotplug_slot->private;
-
 	kfree(slot->hotplug_slot->info);
 	kfree(slot->hotplug_slot);
 	pci_dev_put(slot->dev);
@@ -253,7 +251,6 @@ cpci_hp_register_bus(struct pci_bus *bus, u8 first, u8 last)
 		snprintf(name, SLOT_NAME_SIZE, "%02x:%02x", bus->number, i);
 
 		hotplug_slot->private = slot;
-		hotplug_slot->release = &release_slot;
 		hotplug_slot->ops = &cpci_hotplug_slot_ops;
 
 		/*
@@ -308,12 +305,8 @@ cpci_hp_unregister_bus(struct pci_bus *bus)
 			slots--;
 
 			dbg("deregistering slot %s", slot_name(slot));
-			status = pci_hp_deregister(slot->hotplug_slot);
-			if (status) {
-				err("pci_hp_deregister failed with error %d",
-				    status);
-				break;
-			}
+			pci_hp_deregister(slot->hotplug_slot);
+			release_slot(slot);
 		}
 	}
 	up_write(&list_rwsem);
@@ -623,6 +616,7 @@ cleanup_slots(void)
 	list_for_each_entry_safe(slot, tmp, &slot_list, slot_list) {
 		list_del(&slot->slot_list);
 		pci_hp_deregister(slot->hotplug_slot);
+		release_slot(slot);
 	}
 cleanup_null:
 	up_write(&list_rwsem);
diff --git a/drivers/pci/hotplug/cpqphp_core.c b/drivers/pci/hotplug/cpqphp_core.c
index 1797e36ec586..5a06636e910a 100644
--- a/drivers/pci/hotplug/cpqphp_core.c
+++ b/drivers/pci/hotplug/cpqphp_core.c
@@ -266,17 +266,6 @@ static void __iomem *get_SMBIOS_entry(void __iomem *smbios_start,
 	return previous;
 }
 
-static void release_slot(struct hotplug_slot *hotplug_slot)
-{
-	struct slot *slot = hotplug_slot->private;
-
-	dbg("%s - physical_slot = %s\n", __func__, slot_name(slot));
-
-	kfree(slot->hotplug_slot->info);
-	kfree(slot->hotplug_slot);
-	kfree(slot);
-}
-
 static int ctrl_slot_cleanup(struct controller *ctrl)
 {
 	struct slot *old_slot, *next_slot;
@@ -285,9 +274,11 @@ static int ctrl_slot_cleanup(struct controller *ctrl)
 	ctrl->slot = NULL;
 
 	while (old_slot) {
-		/* memory will be freed by the release_slot callback */
 		next_slot = old_slot->next;
 		pci_hp_deregister(old_slot->hotplug_slot);
+		kfree(old_slot->hotplug_slot->info);
+		kfree(old_slot->hotplug_slot);
+		kfree(old_slot);
 		old_slot = next_slot;
 	}
 
@@ -678,7 +669,6 @@ static int ctrl_slot_setup(struct controller *ctrl,
 			((read_slot_enable(ctrl) << 2) >> ctrl_slot) & 0x04;
 
 		/* register this slot with the hotplug pci core */
-		hotplug_slot->release = &release_slot;
 		hotplug_slot->private = slot;
 		snprintf(name, SLOT_NAME_SIZE, "%u", slot->number);
 		hotplug_slot->ops = &cpqphp_hotplug_slot_ops;
diff --git a/drivers/pci/hotplug/ibmphp_core.c b/drivers/pci/hotplug/ibmphp_core.c
index 1869b0411ce0..4ea57e9019f1 100644
--- a/drivers/pci/hotplug/ibmphp_core.c
+++ b/drivers/pci/hotplug/ibmphp_core.c
@@ -673,7 +673,20 @@ static void free_slots(void)
 
 	list_for_each_entry_safe(slot_cur, next, &ibmphp_slot_head,
 				 ibm_slot_list) {
-		pci_hp_deregister(slot_cur->hotplug_slot);
+		pci_hp_del(slot_cur->hotplug_slot);
+		slot_cur->ctrl = NULL;
+		slot_cur->bus_on = NULL;
+
+		/*
+		 * We don't want to actually remove the resources,
+		 * since ibmphp_free_resources() will do just that.
+		 */
+		ibmphp_unconfigure_card(&slot_cur, -1);
+
+		pci_hp_destroy(slot_cur->hotplug_slot);
+		kfree(slot_cur->hotplug_slot->info);
+		kfree(slot_cur->hotplug_slot);
+		kfree(slot_cur);
 	}
 	debug("%s -- exit\n", __func__);
 }
diff --git a/drivers/pci/hotplug/ibmphp_ebda.c b/drivers/pci/hotplug/ibmphp_ebda.c
index 64549aa24c0f..6f8e90e3ec08 100644
--- a/drivers/pci/hotplug/ibmphp_ebda.c
+++ b/drivers/pci/hotplug/ibmphp_ebda.c
@@ -699,25 +699,6 @@ static int fillslotinfo(struct hotplug_slot *hotplug_slot)
 	return rc;
 }
 
-static void release_slot(struct hotplug_slot *hotplug_slot)
-{
-	struct slot *slot;
-
-	if (!hotplug_slot || !hotplug_slot->private)
-		return;
-
-	slot = hotplug_slot->private;
-	kfree(slot->hotplug_slot->info);
-	kfree(slot->hotplug_slot);
-	slot->ctrl = NULL;
-	slot->bus_on = NULL;
-
-	/* we don't want to actually remove the resources, since free_resources will do just that */
-	ibmphp_unconfigure_card(&slot, -1);
-
-	kfree(slot);
-}
-
 static struct pci_driver ibmphp_driver;
 
 /*
@@ -941,7 +922,6 @@ static int __init ebda_rsrc_controller(void)
 			tmp_slot->hotplug_slot = hp_slot_ptr;
 
 			hp_slot_ptr->private = tmp_slot;
-			hp_slot_ptr->release = release_slot;
 
 			rc = fillslotinfo(hp_slot_ptr);
 			if (rc)
diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c
index af92fed46ab7..90fde5f106d8 100644
--- a/drivers/pci/hotplug/pci_hotplug_core.c
+++ b/drivers/pci/hotplug/pci_hotplug_core.c
@@ -396,8 +396,9 @@ static struct hotplug_slot *get_slot_from_name(const char *name)
  * @owner: caller module owner
  * @mod_name: caller module name
  *
- * Registers a hotplug slot with the pci hotplug subsystem, which will allow
- * userspace interaction to the slot.
+ * Prepares a hotplug slot for in-kernel use and immediately publishes it to
+ * user space in one go.  Drivers may alternatively carry out the two steps
+ * separately by invoking pci_hp_initialize() and pci_hp_add().
  *
  * Returns 0 if successful, anything else for an error.
  */
@@ -406,45 +407,91 @@ int __pci_hp_register(struct hotplug_slot *slot, struct pci_bus *bus,
 		      struct module *owner, const char *mod_name)
 {
 	int result;
+
+	result = __pci_hp_initialize(slot, bus, devnr, name, owner, mod_name);
+	if (result)
+		return result;
+
+	result = pci_hp_add(slot);
+	if (result)
+		pci_hp_destroy(slot);
+
+	return result;
+}
+EXPORT_SYMBOL_GPL(__pci_hp_register);
+
+/**
+ * __pci_hp_initialize - prepare hotplug slot for in-kernel use
+ * @slot: pointer to the &struct hotplug_slot to initialize
+ * @bus: bus this slot is on
+ * @devnr: slot number
+ * @name: name registered with kobject core
+ * @owner: caller module owner
+ * @mod_name: caller module name
+ *
+ * Allocate and fill in a PCI slot for use by a hotplug driver.  Once this has
+ * been called, the driver may invoke hotplug_slot_name() to get the slot's
+ * unique name.  The driver must be prepared to handle a ->reset_slot callback
+ * from this point on.
+ *
+ * Returns 0 on success or a negative int on error.
+ */
+int __pci_hp_initialize(struct hotplug_slot *slot, struct pci_bus *bus,
+			int devnr, const char *name, struct module *owner,
+			const char *mod_name)
+{
 	struct pci_slot *pci_slot;
 
 	if (slot == NULL)
 		return -ENODEV;
 	if ((slot->info == NULL) || (slot->ops == NULL))
 		return -EINVAL;
-	if (slot->release == NULL) {
-		dbg("Why are you trying to register a hotplug slot without a proper release function?\n");
-		return -EINVAL;
-	}
 
 	slot->ops->owner = owner;
 	slot->ops->mod_name = mod_name;
 
-	mutex_lock(&pci_hp_mutex);
 	/*
 	 * No problems if we call this interface from both ACPI_PCI_SLOT
 	 * driver and call it here again. If we've already created the
 	 * pci_slot, the interface will simply bump the refcount.
 	 */
 	pci_slot = pci_create_slot(bus, devnr, name, slot);
-	if (IS_ERR(pci_slot)) {
-		result = PTR_ERR(pci_slot);
-		goto out;
-	}
+	if (IS_ERR(pci_slot))
+		return PTR_ERR(pci_slot);
 
 	slot->pci_slot = pci_slot;
 	pci_slot->hotplug = slot;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__pci_hp_initialize);
 
-	list_add(&slot->slot_list, &pci_hotplug_slot_list);
+/**
+ * pci_hp_add - publish hotplug slot to user space
+ * @slot: pointer to the &struct hotplug_slot to publish
+ *
+ * Make a hotplug slot's sysfs interface available and inform user space of its
+ * addition by sending a uevent.  The hotplug driver must be prepared to handle
+ * all &struct hotplug_slot_ops callbacks from this point on.
+ *
+ * Returns 0 on success or a negative int on error.
+ */
+int pci_hp_add(struct hotplug_slot *slot)
+{
+	struct pci_slot *pci_slot = slot->pci_slot;
+	int result;
 
 	result = fs_add_slot(pci_slot);
+	if (result)
+		return result;
+
 	kobject_uevent(&pci_slot->kobj, KOBJ_ADD);
-	dbg("Added slot %s to the list\n", name);
-out:
+	mutex_lock(&pci_hp_mutex);
+	list_add(&slot->slot_list, &pci_hotplug_slot_list);
 	mutex_unlock(&pci_hp_mutex);
-	return result;
+	dbg("Added slot %s to the list\n", hotplug_slot_name(slot));
+	return 0;
 }
-EXPORT_SYMBOL_GPL(__pci_hp_register);
+EXPORT_SYMBOL_GPL(pci_hp_add);
 
 /**
  * pci_hp_deregister - deregister a hotplug_slot with the PCI hotplug subsystem
@@ -455,35 +502,62 @@ EXPORT_SYMBOL_GPL(__pci_hp_register);
  *
  * Returns 0 if successful, anything else for an error.
  */
-int pci_hp_deregister(struct hotplug_slot *slot)
+void pci_hp_deregister(struct hotplug_slot *slot)
+{
+	pci_hp_del(slot);
+	pci_hp_destroy(slot);
+}
+EXPORT_SYMBOL_GPL(pci_hp_deregister);
+
+/**
+ * pci_hp_del - unpublish hotplug slot from user space
+ * @slot: pointer to the &struct hotplug_slot to unpublish
+ *
+ * Remove a hotplug slot's sysfs interface.
+ *
+ * Returns 0 on success or a negative int on error.
+ */
+void pci_hp_del(struct hotplug_slot *slot)
 {
 	struct hotplug_slot *temp;
-	struct pci_slot *pci_slot;
 
-	if (!slot)
-		return -ENODEV;
+	if (WARN_ON(!slot))
+		return;
 
 	mutex_lock(&pci_hp_mutex);
 	temp = get_slot_from_name(hotplug_slot_name(slot));
-	if (temp != slot) {
+	if (WARN_ON(temp != slot)) {
 		mutex_unlock(&pci_hp_mutex);
-		return -ENODEV;
+		return;
 	}
 
 	list_del(&slot->slot_list);
-
-	pci_slot = slot->pci_slot;
-	fs_remove_slot(pci_slot);
+	mutex_unlock(&pci_hp_mutex);
 	dbg("Removed slot %s from the list\n", hotplug_slot_name(slot));
+	fs_remove_slot(slot->pci_slot);
+}
+EXPORT_SYMBOL_GPL(pci_hp_del);
 
-	slot->release(slot);
+/**
+ * pci_hp_destroy - remove hotplug slot from in-kernel use
+ * @slot: pointer to the &struct hotplug_slot to destroy
+ *
+ * Destroy a PCI slot used by a hotplug driver.  Once this has been called,
+ * the driver may no longer invoke hotplug_slot_name() to get the slot's
+ * unique name.  The driver no longer needs to handle a ->reset_slot callback
+ * from this point on.
+ *
+ * Returns 0 on success or a negative int on error.
+ */
+void pci_hp_destroy(struct hotplug_slot *slot)
+{
+	struct pci_slot *pci_slot = slot->pci_slot;
+
+	slot->pci_slot = NULL;
 	pci_slot->hotplug = NULL;
 	pci_destroy_slot(pci_slot);
-	mutex_unlock(&pci_hp_mutex);
-
-	return 0;
 }
-EXPORT_SYMBOL_GPL(pci_hp_deregister);
+EXPORT_SYMBOL_GPL(pci_hp_destroy);
 
 /**
  * pci_hp_change_slot_info - changes the slot's information structure in the core
diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 5f892065585e..811cf83f956d 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -21,6 +21,7 @@
 #include <linux/delay.h>
 #include <linux/sched/signal.h>		/* signal_pending() */
 #include <linux/mutex.h>
+#include <linux/rwsem.h>
 #include <linux/workqueue.h>
 
 #include "../pcie/portdrv.h"
@@ -57,49 +58,111 @@ do {									\
 	dev_warn(&ctrl->pcie->device, format, ## arg)
 
 #define SLOT_NAME_SIZE 10
+
+/**
+ * struct slot - PCIe hotplug slot
+ * @state: current state machine position
+ * @ctrl: pointer to the slot's controller structure
+ * @hotplug_slot: pointer to the structure registered with the PCI hotplug core
+ * @work: work item to turn the slot on or off after 5 seconds in response to
+ *	an Attention Button press
+ * @lock: protects reads and writes of @state;
+ *	protects scheduling, execution and cancellation of @work
+ */
 struct slot {
 	u8 state;
 	struct controller *ctrl;
 	struct hotplug_slot *hotplug_slot;
-	struct delayed_work work;	/* work for button event */
+	struct delayed_work work;
 	struct mutex lock;
-	struct mutex hotplug_lock;
-	struct workqueue_struct *wq;
-};
-
-struct event_info {
-	u32 event_type;
-	struct slot *p_slot;
-	struct work_struct work;
 };
 
+/**
+ * struct controller - PCIe hotplug controller
+ * @ctrl_lock: serializes writes to the Slot Control register
+ * @pcie: pointer to the controller's PCIe port service device
+ * @reset_lock: prevents access to the Data Link Layer Link Active bit in the
+ *	Link Status register and to the Presence Detect State bit in the Slot
+ *	Status register during a slot reset which may cause them to flap
+ * @slot: pointer to the controller's slot structure
+ * @queue: wait queue to wake up on reception of a Command Completed event,
+ *	used for synchronous writes to the Slot Control register
+ * @slot_cap: cached copy of the Slot Capabilities register
+ * @slot_ctrl: cached copy of the Slot Control register
+ * @poll_thread: thread to poll for slot events if no IRQ is available,
+ *	enabled with pciehp_poll_mode module parameter
+ * @cmd_started: jiffies when the Slot Control register was last written;
+ *	the next write is allowed 1 second later, absent a Command Completed
+ *	interrupt (PCIe r4.0, sec 6.7.3.2)
+ * @cmd_busy: flag set on Slot Control register write, cleared by IRQ handler
+ *	on reception of a Command Completed event
+ * @link_active_reporting: cached copy of Data Link Layer Link Active Reporting
+ *	Capable bit in Link Capabilities register; if this bit is zero, the
+ *	Data Link Layer Link Active bit in the Link Status register will never
+ *	be set and the driver is thus confined to wait 1 second before assuming
+ *	the link to a hotplugged device is up and accessing it
+ * @notification_enabled: whether the IRQ was requested successfully
+ * @power_fault_detected: whether a power fault was detected by the hardware
+ *	that has not yet been cleared by the user
+ * @pending_events: used by the IRQ handler to save events retrieved from the
+ *	Slot Status register for later consumption by the IRQ thread
+ * @request_result: result of last user request submitted to the IRQ thread
+ * @requester: wait queue to wake up on completion of user request,
+ *	used for synchronous slot enable/disable request via sysfs
+ */
 struct controller {
-	struct mutex ctrl_lock;		/* controller lock */
-	struct pcie_device *pcie;	/* PCI Express port service */
+	struct mutex ctrl_lock;
+	struct pcie_device *pcie;
+	struct rw_semaphore reset_lock;
 	struct slot *slot;
-	wait_queue_head_t queue;	/* sleep & wake process */
+	wait_queue_head_t queue;
 	u32 slot_cap;
 	u16 slot_ctrl;
-	struct timer_list poll_timer;
+	struct task_struct *poll_thread;
 	unsigned long cmd_started;	/* jiffies */
 	unsigned int cmd_busy:1;
 	unsigned int link_active_reporting:1;
 	unsigned int notification_enabled:1;
 	unsigned int power_fault_detected;
+	atomic_t pending_events;
+	int request_result;
+	wait_queue_head_t requester;
 };
 
-#define INT_PRESENCE_ON			1
-#define INT_PRESENCE_OFF		2
-#define INT_POWER_FAULT			3
-#define INT_BUTTON_PRESS		4
-#define INT_LINK_UP			5
-#define INT_LINK_DOWN			6
-
-#define STATIC_STATE			0
+/**
+ * DOC: Slot state
+ *
+ * @OFF_STATE: slot is powered off, no subordinate devices are enumerated
+ * @BLINKINGON_STATE: slot will be powered on after the 5 second delay,
+ *	green led is blinking
+ * @BLINKINGOFF_STATE: slot will be powered off after the 5 second delay,
+ *	green led is blinking
+ * @POWERON_STATE: slot is currently powering on
+ * @POWEROFF_STATE: slot is currently powering off
+ * @ON_STATE: slot is powered on, subordinate devices have been enumerated
+ */
+#define OFF_STATE			0
 #define BLINKINGON_STATE		1
 #define BLINKINGOFF_STATE		2
 #define POWERON_STATE			3
 #define POWEROFF_STATE			4
+#define ON_STATE			5
+
+/**
+ * DOC: Flags to request an action from the IRQ thread
+ *
+ * These are stored together with events read from the Slot Status register,
+ * hence must be greater than its 16-bit width.
+ *
+ * %DISABLE_SLOT: Disable the slot in response to a user request via sysfs or
+ *	an Attention Button press after the 5 second delay
+ * %RERUN_ISR: Used by the IRQ handler to inform the IRQ thread that the
+ *	hotplug port was inaccessible when the interrupt occurred, requiring
+ *	that the IRQ handler is rerun by the IRQ thread after it has made the
+ *	hotplug port accessible by runtime resuming its parents to D0
+ */
+#define DISABLE_SLOT		(1 << 16)
+#define RERUN_ISR		(1 << 17)
 
 #define ATTN_BUTTN(ctrl)	((ctrl)->slot_cap & PCI_EXP_SLTCAP_ABP)
 #define POWER_CTRL(ctrl)	((ctrl)->slot_cap & PCI_EXP_SLTCAP_PCP)
@@ -113,15 +176,17 @@ struct controller {
 
 int pciehp_sysfs_enable_slot(struct slot *slot);
 int pciehp_sysfs_disable_slot(struct slot *slot);
-void pciehp_queue_interrupt_event(struct slot *slot, u32 event_type);
+void pciehp_request(struct controller *ctrl, int action);
+void pciehp_handle_button_press(struct slot *slot);
+void pciehp_handle_disable_request(struct slot *slot);
+void pciehp_handle_presence_or_link_change(struct slot *slot, u32 events);
 int pciehp_configure_device(struct slot *p_slot);
-int pciehp_unconfigure_device(struct slot *p_slot);
+void pciehp_unconfigure_device(struct slot *p_slot);
 void pciehp_queue_pushbutton_work(struct work_struct *work);
 struct controller *pcie_init(struct pcie_device *dev);
 int pcie_init_notification(struct controller *ctrl);
-int pciehp_enable_slot(struct slot *p_slot);
-int pciehp_disable_slot(struct slot *p_slot);
-void pcie_reenable_notification(struct controller *ctrl);
+void pcie_shutdown_notification(struct controller *ctrl);
+void pcie_clear_hotplug_events(struct controller *ctrl);
 int pciehp_power_on_slot(struct slot *slot);
 void pciehp_power_off_slot(struct slot *slot);
 void pciehp_get_power_status(struct slot *slot, u8 *status);
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index 44a6a63802d5..ec48c9433ae5 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -26,11 +26,12 @@
 #include <linux/interrupt.h>
 #include <linux/time.h>
 
+#include "../pci.h"
+
 /* Global variables */
 bool pciehp_debug;
 bool pciehp_poll_mode;
 int pciehp_poll_time;
-static bool pciehp_force;
 
 /*
  * not really modular, but the easiest way to keep compat with existing
@@ -39,11 +40,9 @@ static bool pciehp_force;
 module_param(pciehp_debug, bool, 0644);
 module_param(pciehp_poll_mode, bool, 0644);
 module_param(pciehp_poll_time, int, 0644);
-module_param(pciehp_force, bool, 0644);
 MODULE_PARM_DESC(pciehp_debug, "Debugging mode enabled or not");
 MODULE_PARM_DESC(pciehp_poll_mode, "Using polling mechanism for hot-plug events or not");
 MODULE_PARM_DESC(pciehp_poll_time, "Polling mechanism frequency, in seconds");
-MODULE_PARM_DESC(pciehp_force, "Force pciehp, even if OSHP is missing");
 
 #define PCIE_MODULE_NAME "pciehp"
 
@@ -56,17 +55,6 @@ static int get_latch_status(struct hotplug_slot *slot, u8 *value);
 static int get_adapter_status(struct hotplug_slot *slot, u8 *value);
 static int reset_slot(struct hotplug_slot *slot, int probe);
 
-/**
- * release_slot - free up the memory used by a slot
- * @hotplug_slot: slot to free
- */
-static void release_slot(struct hotplug_slot *hotplug_slot)
-{
-	kfree(hotplug_slot->ops);
-	kfree(hotplug_slot->info);
-	kfree(hotplug_slot);
-}
-
 static int init_slot(struct controller *ctrl)
 {
 	struct slot *slot = ctrl->slot;
@@ -107,15 +95,14 @@ static int init_slot(struct controller *ctrl)
 	/* register this slot with the hotplug pci core */
 	hotplug->info = info;
 	hotplug->private = slot;
-	hotplug->release = &release_slot;
 	hotplug->ops = ops;
 	slot->hotplug_slot = hotplug;
 	snprintf(name, SLOT_NAME_SIZE, "%u", PSN(ctrl));
 
-	retval = pci_hp_register(hotplug,
-				 ctrl->pcie->port->subordinate, 0, name);
+	retval = pci_hp_initialize(hotplug,
+				   ctrl->pcie->port->subordinate, 0, name);
 	if (retval)
-		ctrl_err(ctrl, "pci_hp_register failed: error %d\n", retval);
+		ctrl_err(ctrl, "pci_hp_initialize failed: error %d\n", retval);
 out:
 	if (retval) {
 		kfree(ops);
@@ -127,7 +114,12 @@ out:
 
 static void cleanup_slot(struct controller *ctrl)
 {
-	pci_hp_deregister(ctrl->slot->hotplug_slot);
+	struct hotplug_slot *hotplug_slot = ctrl->slot->hotplug_slot;
+
+	pci_hp_destroy(hotplug_slot);
+	kfree(hotplug_slot->ops);
+	kfree(hotplug_slot->info);
+	kfree(hotplug_slot);
 }
 
 /*
@@ -136,8 +128,11 @@ static void cleanup_slot(struct controller *ctrl)
 static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status)
 {
 	struct slot *slot = hotplug_slot->private;
+	struct pci_dev *pdev = slot->ctrl->pcie->port;
 
+	pci_config_pm_runtime_get(pdev);
 	pciehp_set_attention_status(slot, status);
+	pci_config_pm_runtime_put(pdev);
 	return 0;
 }
 
@@ -160,8 +155,11 @@ static int disable_slot(struct hotplug_slot *hotplug_slot)
 static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	struct slot *slot = hotplug_slot->private;
+	struct pci_dev *pdev = slot->ctrl->pcie->port;
 
+	pci_config_pm_runtime_get(pdev);
 	pciehp_get_power_status(slot, value);
+	pci_config_pm_runtime_put(pdev);
 	return 0;
 }
 
@@ -176,16 +174,22 @@ static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value)
 static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	struct slot *slot = hotplug_slot->private;
+	struct pci_dev *pdev = slot->ctrl->pcie->port;
 
+	pci_config_pm_runtime_get(pdev);
 	pciehp_get_latch_status(slot, value);
+	pci_config_pm_runtime_put(pdev);
 	return 0;
 }
 
 static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	struct slot *slot = hotplug_slot->private;
+	struct pci_dev *pdev = slot->ctrl->pcie->port;
 
+	pci_config_pm_runtime_get(pdev);
 	pciehp_get_adapter_status(slot, value);
+	pci_config_pm_runtime_put(pdev);
 	return 0;
 }
 
@@ -196,12 +200,40 @@ static int reset_slot(struct hotplug_slot *hotplug_slot, int probe)
 	return pciehp_reset_slot(slot, probe);
 }
 
+/**
+ * pciehp_check_presence() - synthesize event if presence has changed
+ *
+ * On probe and resume, an explicit presence check is necessary to bring up an
+ * occupied slot or bring down an unoccupied slot.  This can't be triggered by
+ * events in the Slot Status register, they may be stale and are therefore
+ * cleared.  Secondly, sending an interrupt for "events that occur while
+ * interrupt generation is disabled [when] interrupt generation is subsequently
+ * enabled" is optional per PCIe r4.0, sec 6.7.3.4.
+ */
+static void pciehp_check_presence(struct controller *ctrl)
+{
+	struct slot *slot = ctrl->slot;
+	u8 occupied;
+
+	down_read(&ctrl->reset_lock);
+	mutex_lock(&slot->lock);
+
+	pciehp_get_adapter_status(slot, &occupied);
+	if ((occupied && (slot->state == OFF_STATE ||
+			  slot->state == BLINKINGON_STATE)) ||
+	    (!occupied && (slot->state == ON_STATE ||
+			   slot->state == BLINKINGOFF_STATE)))
+		pciehp_request(ctrl, PCI_EXP_SLTSTA_PDC);
+
+	mutex_unlock(&slot->lock);
+	up_read(&ctrl->reset_lock);
+}
+
 static int pciehp_probe(struct pcie_device *dev)
 {
 	int rc;
 	struct controller *ctrl;
 	struct slot *slot;
-	u8 occupied, poweron;
 
 	/* If this is not a "hotplug" service, we have no business here. */
 	if (dev->service != PCIE_PORT_SERVICE_HP)
@@ -238,21 +270,20 @@ static int pciehp_probe(struct pcie_device *dev)
 		goto err_out_free_ctrl_slot;
 	}
 
-	/* Check if slot is occupied */
+	/* Publish to user space */
 	slot = ctrl->slot;
-	pciehp_get_adapter_status(slot, &occupied);
-	pciehp_get_power_status(slot, &poweron);
-	if (occupied && pciehp_force) {
-		mutex_lock(&slot->hotplug_lock);
-		pciehp_enable_slot(slot);
-		mutex_unlock(&slot->hotplug_lock);
+	rc = pci_hp_add(slot->hotplug_slot);
+	if (rc) {
+		ctrl_err(ctrl, "Publication to user space failed (%d)\n", rc);
+		goto err_out_shutdown_notification;
 	}
-	/* If empty slot's power status is on, turn power off */
-	if (!occupied && poweron && POWER_CTRL(ctrl))
-		pciehp_power_off_slot(slot);
+
+	pciehp_check_presence(ctrl);
 
 	return 0;
 
+err_out_shutdown_notification:
+	pcie_shutdown_notification(ctrl);
 err_out_free_ctrl_slot:
 	cleanup_slot(ctrl);
 err_out_release_ctlr:
@@ -264,6 +295,8 @@ static void pciehp_remove(struct pcie_device *dev)
 {
 	struct controller *ctrl = get_service_data(dev);
 
+	pci_hp_del(ctrl->slot->hotplug_slot);
+	pcie_shutdown_notification(ctrl);
 	cleanup_slot(ctrl);
 	pciehp_release_ctrl(ctrl);
 }
@@ -274,27 +307,28 @@ static int pciehp_suspend(struct pcie_device *dev)
 	return 0;
 }
 
-static int pciehp_resume(struct pcie_device *dev)
+static int pciehp_resume_noirq(struct pcie_device *dev)
 {
-	struct controller *ctrl;
-	struct slot *slot;
-	u8 status;
+	struct controller *ctrl = get_service_data(dev);
+	struct slot *slot = ctrl->slot;
 
-	ctrl = get_service_data(dev);
+	/* pci_restore_state() just wrote to the Slot Control register */
+	ctrl->cmd_started = jiffies;
+	ctrl->cmd_busy = true;
 
-	/* reinitialize the chipset's event detection logic */
-	pcie_reenable_notification(ctrl);
+	/* clear spurious events from rediscovery of inserted card */
+	if (slot->state == ON_STATE || slot->state == BLINKINGOFF_STATE)
+		pcie_clear_hotplug_events(ctrl);
 
-	slot = ctrl->slot;
+	return 0;
+}
+
+static int pciehp_resume(struct pcie_device *dev)
+{
+	struct controller *ctrl = get_service_data(dev);
+
+	pciehp_check_presence(ctrl);
 
-	/* Check if slot is occupied */
-	pciehp_get_adapter_status(slot, &status);
-	mutex_lock(&slot->hotplug_lock);
-	if (status)
-		pciehp_enable_slot(slot);
-	else
-		pciehp_disable_slot(slot);
-	mutex_unlock(&slot->hotplug_lock);
 	return 0;
 }
 #endif /* PM */
@@ -309,6 +343,7 @@ static struct pcie_port_service_driver hpdriver_portdrv = {
 
 #ifdef	CONFIG_PM
 	.suspend	= pciehp_suspend,
+	.resume_noirq	= pciehp_resume_noirq,
 	.resume		= pciehp_resume,
 #endif	/* PM */
 };
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index c684faa43387..da7c72372ffc 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -17,28 +17,11 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/slab.h>
+#include <linux/pm_runtime.h>
 #include <linux/pci.h>
 #include "../pci.h"
 #include "pciehp.h"
 
-static void interrupt_event_handler(struct work_struct *work);
-
-void pciehp_queue_interrupt_event(struct slot *p_slot, u32 event_type)
-{
-	struct event_info *info;
-
-	info = kmalloc(sizeof(*info), GFP_ATOMIC);
-	if (!info) {
-		ctrl_err(p_slot->ctrl, "dropped event %d (ENOMEM)\n", event_type);
-		return;
-	}
-
-	INIT_WORK(&info->work, interrupt_event_handler);
-	info->event_type = event_type;
-	info->p_slot = p_slot;
-	queue_work(p_slot->wq, &info->work);
-}
-
 /* The following routines constitute the bulk of the
    hotplug controller logic
  */
@@ -119,14 +102,11 @@ err_exit:
  * remove_board - Turns off slot and LEDs
  * @p_slot: slot where board is being removed
  */
-static int remove_board(struct slot *p_slot)
+static void remove_board(struct slot *p_slot)
 {
-	int retval;
 	struct controller *ctrl = p_slot->ctrl;
 
-	retval = pciehp_unconfigure_device(p_slot);
-	if (retval)
-		return retval;
+	pciehp_unconfigure_device(p_slot);
 
 	if (POWER_CTRL(ctrl)) {
 		pciehp_power_off_slot(p_slot);
@@ -141,86 +121,30 @@ static int remove_board(struct slot *p_slot)
 
 	/* turn off Green LED */
 	pciehp_green_led_off(p_slot);
-	return 0;
 }
 
-struct power_work_info {
-	struct slot *p_slot;
-	struct work_struct work;
-	unsigned int req;
-#define DISABLE_REQ 0
-#define ENABLE_REQ  1
-};
-
-/**
- * pciehp_power_thread - handle pushbutton events
- * @work: &struct work_struct describing work to be done
- *
- * Scheduled procedure to handle blocking stuff for the pushbuttons.
- * Handles all pending events and exits.
- */
-static void pciehp_power_thread(struct work_struct *work)
-{
-	struct power_work_info *info =
-		container_of(work, struct power_work_info, work);
-	struct slot *p_slot = info->p_slot;
-	int ret;
-
-	switch (info->req) {
-	case DISABLE_REQ:
-		mutex_lock(&p_slot->hotplug_lock);
-		pciehp_disable_slot(p_slot);
-		mutex_unlock(&p_slot->hotplug_lock);
-		mutex_lock(&p_slot->lock);
-		p_slot->state = STATIC_STATE;
-		mutex_unlock(&p_slot->lock);
-		break;
-	case ENABLE_REQ:
-		mutex_lock(&p_slot->hotplug_lock);
-		ret = pciehp_enable_slot(p_slot);
-		mutex_unlock(&p_slot->hotplug_lock);
-		if (ret)
-			pciehp_green_led_off(p_slot);
-		mutex_lock(&p_slot->lock);
-		p_slot->state = STATIC_STATE;
-		mutex_unlock(&p_slot->lock);
-		break;
-	default:
-		break;
-	}
-
-	kfree(info);
-}
+static int pciehp_enable_slot(struct slot *slot);
+static int pciehp_disable_slot(struct slot *slot);
 
-static void pciehp_queue_power_work(struct slot *p_slot, int req)
+void pciehp_request(struct controller *ctrl, int action)
 {
-	struct power_work_info *info;
-
-	p_slot->state = (req == ENABLE_REQ) ? POWERON_STATE : POWEROFF_STATE;
-
-	info = kmalloc(sizeof(*info), GFP_KERNEL);
-	if (!info) {
-		ctrl_err(p_slot->ctrl, "no memory to queue %s request\n",
-			 (req == ENABLE_REQ) ? "poweron" : "poweroff");
-		return;
-	}
-	info->p_slot = p_slot;
-	INIT_WORK(&info->work, pciehp_power_thread);
-	info->req = req;
-	queue_work(p_slot->wq, &info->work);
+	atomic_or(action, &ctrl->pending_events);
+	if (!pciehp_poll_mode)
+		irq_wake_thread(ctrl->pcie->irq, ctrl);
 }
 
 void pciehp_queue_pushbutton_work(struct work_struct *work)
 {
 	struct slot *p_slot = container_of(work, struct slot, work.work);
+	struct controller *ctrl = p_slot->ctrl;
 
 	mutex_lock(&p_slot->lock);
 	switch (p_slot->state) {
 	case BLINKINGOFF_STATE:
-		pciehp_queue_power_work(p_slot, DISABLE_REQ);
+		pciehp_request(ctrl, DISABLE_SLOT);
 		break;
 	case BLINKINGON_STATE:
-		pciehp_queue_power_work(p_slot, ENABLE_REQ);
+		pciehp_request(ctrl, PCI_EXP_SLTSTA_PDC);
 		break;
 	default:
 		break;
@@ -228,18 +152,15 @@ void pciehp_queue_pushbutton_work(struct work_struct *work)
 	mutex_unlock(&p_slot->lock);
 }
 
-/*
- * Note: This function must be called with slot->lock held
- */
-static void handle_button_press_event(struct slot *p_slot)
+void pciehp_handle_button_press(struct slot *p_slot)
 {
 	struct controller *ctrl = p_slot->ctrl;
-	u8 getstatus;
 
+	mutex_lock(&p_slot->lock);
 	switch (p_slot->state) {
-	case STATIC_STATE:
-		pciehp_get_power_status(p_slot, &getstatus);
-		if (getstatus) {
+	case OFF_STATE:
+	case ON_STATE:
+		if (p_slot->state == ON_STATE) {
 			p_slot->state = BLINKINGOFF_STATE;
 			ctrl_info(ctrl, "Slot(%s): Powering off due to button press\n",
 				  slot_name(p_slot));
@@ -251,7 +172,7 @@ static void handle_button_press_event(struct slot *p_slot)
 		/* blink green LED and turn off amber */
 		pciehp_green_led_blink(p_slot);
 		pciehp_set_attention_status(p_slot, 0);
-		queue_delayed_work(p_slot->wq, &p_slot->work, 5*HZ);
+		schedule_delayed_work(&p_slot->work, 5 * HZ);
 		break;
 	case BLINKINGOFF_STATE:
 	case BLINKINGON_STATE:
@@ -262,118 +183,104 @@ static void handle_button_press_event(struct slot *p_slot)
 		 */
 		ctrl_info(ctrl, "Slot(%s): Button cancel\n", slot_name(p_slot));
 		cancel_delayed_work(&p_slot->work);
-		if (p_slot->state == BLINKINGOFF_STATE)
+		if (p_slot->state == BLINKINGOFF_STATE) {
+			p_slot->state = ON_STATE;
 			pciehp_green_led_on(p_slot);
-		else
+		} else {
+			p_slot->state = OFF_STATE;
 			pciehp_green_led_off(p_slot);
+		}
 		pciehp_set_attention_status(p_slot, 0);
 		ctrl_info(ctrl, "Slot(%s): Action canceled due to button press\n",
 			  slot_name(p_slot));
-		p_slot->state = STATIC_STATE;
-		break;
-	case POWEROFF_STATE:
-	case POWERON_STATE:
-		/*
-		 * Ignore if the slot is on power-on or power-off state;
-		 * this means that the previous attention button action
-		 * to hot-add or hot-remove is undergoing
-		 */
-		ctrl_info(ctrl, "Slot(%s): Button ignored\n",
-			  slot_name(p_slot));
 		break;
 	default:
 		ctrl_err(ctrl, "Slot(%s): Ignoring invalid state %#x\n",
 			 slot_name(p_slot), p_slot->state);
 		break;
 	}
+	mutex_unlock(&p_slot->lock);
 }
 
-/*
- * Note: This function must be called with slot->lock held
- */
-static void handle_link_event(struct slot *p_slot, u32 event)
+void pciehp_handle_disable_request(struct slot *slot)
 {
-	struct controller *ctrl = p_slot->ctrl;
+	struct controller *ctrl = slot->ctrl;
 
-	switch (p_slot->state) {
+	mutex_lock(&slot->lock);
+	switch (slot->state) {
 	case BLINKINGON_STATE:
 	case BLINKINGOFF_STATE:
-		cancel_delayed_work(&p_slot->work);
-		/* Fall through */
-	case STATIC_STATE:
-		pciehp_queue_power_work(p_slot, event == INT_LINK_UP ?
-					ENABLE_REQ : DISABLE_REQ);
-		break;
-	case POWERON_STATE:
-		if (event == INT_LINK_UP) {
-			ctrl_info(ctrl, "Slot(%s): Link Up event ignored; already powering on\n",
-				  slot_name(p_slot));
-		} else {
-			ctrl_info(ctrl, "Slot(%s): Link Down event queued; currently getting powered on\n",
-				  slot_name(p_slot));
-			pciehp_queue_power_work(p_slot, DISABLE_REQ);
-		}
-		break;
-	case POWEROFF_STATE:
-		if (event == INT_LINK_UP) {
-			ctrl_info(ctrl, "Slot(%s): Link Up event queued; currently getting powered off\n",
-				  slot_name(p_slot));
-			pciehp_queue_power_work(p_slot, ENABLE_REQ);
-		} else {
-			ctrl_info(ctrl, "Slot(%s): Link Down event ignored; already powering off\n",
-				  slot_name(p_slot));
-		}
-		break;
-	default:
-		ctrl_err(ctrl, "Slot(%s): Ignoring invalid state %#x\n",
-			 slot_name(p_slot), p_slot->state);
+		cancel_delayed_work(&slot->work);
 		break;
 	}
+	slot->state = POWEROFF_STATE;
+	mutex_unlock(&slot->lock);
+
+	ctrl->request_result = pciehp_disable_slot(slot);
 }
 
-static void interrupt_event_handler(struct work_struct *work)
+void pciehp_handle_presence_or_link_change(struct slot *slot, u32 events)
 {
-	struct event_info *info = container_of(work, struct event_info, work);
-	struct slot *p_slot = info->p_slot;
-	struct controller *ctrl = p_slot->ctrl;
-
-	mutex_lock(&p_slot->lock);
-	switch (info->event_type) {
-	case INT_BUTTON_PRESS:
-		handle_button_press_event(p_slot);
-		break;
-	case INT_POWER_FAULT:
-		if (!POWER_CTRL(ctrl))
-			break;
-		pciehp_set_attention_status(p_slot, 1);
-		pciehp_green_led_off(p_slot);
-		break;
-	case INT_PRESENCE_ON:
-		pciehp_queue_power_work(p_slot, ENABLE_REQ);
+	struct controller *ctrl = slot->ctrl;
+	bool link_active;
+	u8 present;
+
+	/*
+	 * If the slot is on and presence or link has changed, turn it off.
+	 * Even if it's occupied again, we cannot assume the card is the same.
+	 */
+	mutex_lock(&slot->lock);
+	switch (slot->state) {
+	case BLINKINGOFF_STATE:
+		cancel_delayed_work(&slot->work);
+		/* fall through */
+	case ON_STATE:
+		slot->state = POWEROFF_STATE;
+		mutex_unlock(&slot->lock);
+		if (events & PCI_EXP_SLTSTA_DLLSC)
+			ctrl_info(ctrl, "Slot(%s): Link Down\n",
+				  slot_name(slot));
+		if (events & PCI_EXP_SLTSTA_PDC)
+			ctrl_info(ctrl, "Slot(%s): Card not present\n",
+				  slot_name(slot));
+		pciehp_disable_slot(slot);
 		break;
-	case INT_PRESENCE_OFF:
-		/*
-		 * Regardless of surprise capability, we need to
-		 * definitely remove a card that has been pulled out!
-		 */
-		pciehp_queue_power_work(p_slot, DISABLE_REQ);
+	default:
+		mutex_unlock(&slot->lock);
 		break;
-	case INT_LINK_UP:
-	case INT_LINK_DOWN:
-		handle_link_event(p_slot, info->event_type);
+	}
+
+	/* Turn the slot on if it's occupied or link is up */
+	mutex_lock(&slot->lock);
+	pciehp_get_adapter_status(slot, &present);
+	link_active = pciehp_check_link_active(ctrl);
+	if (!present && !link_active) {
+		mutex_unlock(&slot->lock);
+		return;
+	}
+
+	switch (slot->state) {
+	case BLINKINGON_STATE:
+		cancel_delayed_work(&slot->work);
+		/* fall through */
+	case OFF_STATE:
+		slot->state = POWERON_STATE;
+		mutex_unlock(&slot->lock);
+		if (present)
+			ctrl_info(ctrl, "Slot(%s): Card present\n",
+				  slot_name(slot));
+		if (link_active)
+			ctrl_info(ctrl, "Slot(%s): Link Up\n",
+				  slot_name(slot));
+		ctrl->request_result = pciehp_enable_slot(slot);
 		break;
 	default:
+		mutex_unlock(&slot->lock);
 		break;
 	}
-	mutex_unlock(&p_slot->lock);
-
-	kfree(info);
 }
 
-/*
- * Note: This function must be called with slot->hotplug_lock held
- */
-int pciehp_enable_slot(struct slot *p_slot)
+static int __pciehp_enable_slot(struct slot *p_slot)
 {
 	u8 getstatus = 0;
 	struct controller *ctrl = p_slot->ctrl;
@@ -404,17 +311,29 @@ int pciehp_enable_slot(struct slot *p_slot)
 	return board_added(p_slot);
 }
 
-/*
- * Note: This function must be called with slot->hotplug_lock held
- */
-int pciehp_disable_slot(struct slot *p_slot)
+static int pciehp_enable_slot(struct slot *slot)
+{
+	struct controller *ctrl = slot->ctrl;
+	int ret;
+
+	pm_runtime_get_sync(&ctrl->pcie->port->dev);
+	ret = __pciehp_enable_slot(slot);
+	if (ret && ATTN_BUTTN(ctrl))
+		pciehp_green_led_off(slot); /* may be blinking */
+	pm_runtime_put(&ctrl->pcie->port->dev);
+
+	mutex_lock(&slot->lock);
+	slot->state = ret ? OFF_STATE : ON_STATE;
+	mutex_unlock(&slot->lock);
+
+	return ret;
+}
+
+static int __pciehp_disable_slot(struct slot *p_slot)
 {
 	u8 getstatus = 0;
 	struct controller *ctrl = p_slot->ctrl;
 
-	if (!p_slot->ctrl)
-		return 1;
-
 	if (POWER_CTRL(p_slot->ctrl)) {
 		pciehp_get_power_status(p_slot, &getstatus);
 		if (!getstatus) {
@@ -424,32 +343,50 @@ int pciehp_disable_slot(struct slot *p_slot)
 		}
 	}
 
-	return remove_board(p_slot);
+	remove_board(p_slot);
+	return 0;
+}
+
+static int pciehp_disable_slot(struct slot *slot)
+{
+	struct controller *ctrl = slot->ctrl;
+	int ret;
+
+	pm_runtime_get_sync(&ctrl->pcie->port->dev);
+	ret = __pciehp_disable_slot(slot);
+	pm_runtime_put(&ctrl->pcie->port->dev);
+
+	mutex_lock(&slot->lock);
+	slot->state = OFF_STATE;
+	mutex_unlock(&slot->lock);
+
+	return ret;
 }
 
 int pciehp_sysfs_enable_slot(struct slot *p_slot)
 {
-	int retval = -ENODEV;
 	struct controller *ctrl = p_slot->ctrl;
 
 	mutex_lock(&p_slot->lock);
 	switch (p_slot->state) {
 	case BLINKINGON_STATE:
-		cancel_delayed_work(&p_slot->work);
-	case STATIC_STATE:
-		p_slot->state = POWERON_STATE;
+	case OFF_STATE:
 		mutex_unlock(&p_slot->lock);
-		mutex_lock(&p_slot->hotplug_lock);
-		retval = pciehp_enable_slot(p_slot);
-		mutex_unlock(&p_slot->hotplug_lock);
-		mutex_lock(&p_slot->lock);
-		p_slot->state = STATIC_STATE;
-		break;
+		/*
+		 * The IRQ thread becomes a no-op if the user pulls out the
+		 * card before the thread wakes up, so initialize to -ENODEV.
+		 */
+		ctrl->request_result = -ENODEV;
+		pciehp_request(ctrl, PCI_EXP_SLTSTA_PDC);
+		wait_event(ctrl->requester,
+			   !atomic_read(&ctrl->pending_events));
+		return ctrl->request_result;
 	case POWERON_STATE:
 		ctrl_info(ctrl, "Slot(%s): Already in powering on state\n",
 			  slot_name(p_slot));
 		break;
 	case BLINKINGOFF_STATE:
+	case ON_STATE:
 	case POWEROFF_STATE:
 		ctrl_info(ctrl, "Slot(%s): Already enabled\n",
 			  slot_name(p_slot));
@@ -461,32 +398,28 @@ int pciehp_sysfs_enable_slot(struct slot *p_slot)
 	}
 	mutex_unlock(&p_slot->lock);
 
-	return retval;
+	return -ENODEV;
 }
 
 int pciehp_sysfs_disable_slot(struct slot *p_slot)
 {
-	int retval = -ENODEV;
 	struct controller *ctrl = p_slot->ctrl;
 
 	mutex_lock(&p_slot->lock);
 	switch (p_slot->state) {
 	case BLINKINGOFF_STATE:
-		cancel_delayed_work(&p_slot->work);
-	case STATIC_STATE:
-		p_slot->state = POWEROFF_STATE;
+	case ON_STATE:
 		mutex_unlock(&p_slot->lock);
-		mutex_lock(&p_slot->hotplug_lock);
-		retval = pciehp_disable_slot(p_slot);
-		mutex_unlock(&p_slot->hotplug_lock);
-		mutex_lock(&p_slot->lock);
-		p_slot->state = STATIC_STATE;
-		break;
+		pciehp_request(ctrl, DISABLE_SLOT);
+		wait_event(ctrl->requester,
+			   !atomic_read(&ctrl->pending_events));
+		return ctrl->request_result;
 	case POWEROFF_STATE:
 		ctrl_info(ctrl, "Slot(%s): Already in powering off state\n",
 			  slot_name(p_slot));
 		break;
 	case BLINKINGON_STATE:
+	case OFF_STATE:
 	case POWERON_STATE:
 		ctrl_info(ctrl, "Slot(%s): Already disabled\n",
 			  slot_name(p_slot));
@@ -498,5 +431,5 @@ int pciehp_sysfs_disable_slot(struct slot *p_slot)
 	}
 	mutex_unlock(&p_slot->lock);
 
-	return retval;
+	return -ENODEV;
 }
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 718b6073afad..7136e3430925 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -17,8 +17,9 @@
 #include <linux/types.h>
 #include <linux/signal.h>
 #include <linux/jiffies.h>
-#include <linux/timer.h>
+#include <linux/kthread.h>
 #include <linux/pci.h>
+#include <linux/pm_runtime.h>
 #include <linux/interrupt.h>
 #include <linux/time.h>
 #include <linux/slab.h>
@@ -31,47 +32,24 @@ static inline struct pci_dev *ctrl_dev(struct controller *ctrl)
 	return ctrl->pcie->port;
 }
 
-static irqreturn_t pcie_isr(int irq, void *dev_id);
-static void start_int_poll_timer(struct controller *ctrl, int sec);
-
-/* This is the interrupt polling timeout function. */
-static void int_poll_timeout(struct timer_list *t)
-{
-	struct controller *ctrl = from_timer(ctrl, t, poll_timer);
-
-	/* Poll for interrupt events.  regs == NULL => polling */
-	pcie_isr(0, ctrl);
-
-	if (!pciehp_poll_time)
-		pciehp_poll_time = 2; /* default polling interval is 2 sec */
-
-	start_int_poll_timer(ctrl, pciehp_poll_time);
-}
-
-/* This function starts the interrupt polling timer. */
-static void start_int_poll_timer(struct controller *ctrl, int sec)
-{
-	/* Clamp to sane value */
-	if ((sec <= 0) || (sec > 60))
-		sec = 2;
-
-	ctrl->poll_timer.expires = jiffies + sec * HZ;
-	add_timer(&ctrl->poll_timer);
-}
+static irqreturn_t pciehp_isr(int irq, void *dev_id);
+static irqreturn_t pciehp_ist(int irq, void *dev_id);
+static int pciehp_poll(void *data);
 
 static inline int pciehp_request_irq(struct controller *ctrl)
 {
 	int retval, irq = ctrl->pcie->irq;
 
-	/* Install interrupt polling timer. Start with 10 sec delay */
 	if (pciehp_poll_mode) {
-		timer_setup(&ctrl->poll_timer, int_poll_timeout, 0);
-		start_int_poll_timer(ctrl, 10);
-		return 0;
+		ctrl->poll_thread = kthread_run(&pciehp_poll, ctrl,
+						"pciehp_poll-%s",
+						slot_name(ctrl->slot));
+		return PTR_ERR_OR_ZERO(ctrl->poll_thread);
 	}
 
 	/* Installs the interrupt handler */
-	retval = request_irq(irq, pcie_isr, IRQF_SHARED, MY_NAME, ctrl);
+	retval = request_threaded_irq(irq, pciehp_isr, pciehp_ist,
+				      IRQF_SHARED, MY_NAME, ctrl);
 	if (retval)
 		ctrl_err(ctrl, "Cannot get irq %d for the hotplug controller\n",
 			 irq);
@@ -81,7 +59,7 @@ static inline int pciehp_request_irq(struct controller *ctrl)
 static inline void pciehp_free_irq(struct controller *ctrl)
 {
 	if (pciehp_poll_mode)
-		del_timer_sync(&ctrl->poll_timer);
+		kthread_stop(ctrl->poll_thread);
 	else
 		free_irq(ctrl->pcie->irq, ctrl);
 }
@@ -293,6 +271,11 @@ int pciehp_check_link_status(struct controller *ctrl)
 	found = pci_bus_check_dev(ctrl->pcie->port->subordinate,
 					PCI_DEVFN(0, 0));
 
+	/* ignore link or presence changes up to this point */
+	if (found)
+		atomic_and(~(PCI_EXP_SLTSTA_DLLSC | PCI_EXP_SLTSTA_PDC),
+			   &ctrl->pending_events);
+
 	pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status);
 	ctrl_dbg(ctrl, "%s: lnk_status = %x\n", __func__, lnk_status);
 	if ((lnk_status & PCI_EXP_LNKSTA_LT) ||
@@ -339,7 +322,9 @@ int pciehp_get_raw_indicator_status(struct hotplug_slot *hotplug_slot,
 	struct pci_dev *pdev = ctrl_dev(slot->ctrl);
 	u16 slot_ctrl;
 
+	pci_config_pm_runtime_get(pdev);
 	pcie_capability_read_word(pdev, PCI_EXP_SLTCTL, &slot_ctrl);
+	pci_config_pm_runtime_put(pdev);
 	*status = (slot_ctrl & (PCI_EXP_SLTCTL_AIC | PCI_EXP_SLTCTL_PIC)) >> 6;
 	return 0;
 }
@@ -350,7 +335,9 @@ void pciehp_get_attention_status(struct slot *slot, u8 *status)
 	struct pci_dev *pdev = ctrl_dev(ctrl);
 	u16 slot_ctrl;
 
+	pci_config_pm_runtime_get(pdev);
 	pcie_capability_read_word(pdev, PCI_EXP_SLTCTL, &slot_ctrl);
+	pci_config_pm_runtime_put(pdev);
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x, value read %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, slot_ctrl);
 
@@ -425,9 +412,12 @@ int pciehp_set_raw_indicator_status(struct hotplug_slot *hotplug_slot,
 {
 	struct slot *slot = hotplug_slot->private;
 	struct controller *ctrl = slot->ctrl;
+	struct pci_dev *pdev = ctrl_dev(ctrl);
 
+	pci_config_pm_runtime_get(pdev);
 	pcie_write_cmd_nowait(ctrl, status << 6,
 			      PCI_EXP_SLTCTL_AIC | PCI_EXP_SLTCTL_PIC);
+	pci_config_pm_runtime_put(pdev);
 	return 0;
 }
 
@@ -539,20 +529,35 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id)
 {
 	struct controller *ctrl = (struct controller *)dev_id;
 	struct pci_dev *pdev = ctrl_dev(ctrl);
-	struct pci_bus *subordinate = pdev->subordinate;
-	struct pci_dev *dev;
-	struct slot *slot = ctrl->slot;
+	struct device *parent = pdev->dev.parent;
 	u16 status, events;
-	u8 present;
-	bool link;
 
-	/* Interrupts cannot originate from a controller that's asleep */
+	/*
+	 * Interrupts only occur in D3hot or shallower (PCIe r4.0, sec 6.7.3.4).
+	 */
 	if (pdev->current_state == PCI_D3cold)
 		return IRQ_NONE;
 
+	/*
+	 * Keep the port accessible by holding a runtime PM ref on its parent.
+	 * Defer resume of the parent to the IRQ thread if it's suspended.
+	 * Mask the interrupt until then.
+	 */
+	if (parent) {
+		pm_runtime_get_noresume(parent);
+		if (!pm_runtime_active(parent)) {
+			pm_runtime_put(parent);
+			disable_irq_nosync(irq);
+			atomic_or(RERUN_ISR, &ctrl->pending_events);
+			return IRQ_WAKE_THREAD;
+		}
+	}
+
 	pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &status);
 	if (status == (u16) ~0) {
 		ctrl_info(ctrl, "%s: no response from device\n", __func__);
+		if (parent)
+			pm_runtime_put(parent);
 		return IRQ_NONE;
 	}
 
@@ -571,86 +576,119 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id)
 	if (ctrl->power_fault_detected)
 		events &= ~PCI_EXP_SLTSTA_PFD;
 
-	if (!events)
+	if (!events) {
+		if (parent)
+			pm_runtime_put(parent);
 		return IRQ_NONE;
-
-	/* Capture link status before clearing interrupts */
-	if (events & PCI_EXP_SLTSTA_DLLSC)
-		link = pciehp_check_link_active(ctrl);
+	}
 
 	pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, events);
 	ctrl_dbg(ctrl, "pending interrupts %#06x from Slot Status\n", events);
+	if (parent)
+		pm_runtime_put(parent);
 
-	/* Check Command Complete Interrupt Pending */
+	/*
+	 * Command Completed notifications are not deferred to the
+	 * IRQ thread because it may be waiting for their arrival.
+	 */
 	if (events & PCI_EXP_SLTSTA_CC) {
 		ctrl->cmd_busy = 0;
 		smp_mb();
 		wake_up(&ctrl->queue);
+
+		if (events == PCI_EXP_SLTSTA_CC)
+			return IRQ_HANDLED;
+
+		events &= ~PCI_EXP_SLTSTA_CC;
+	}
+
+	if (pdev->ignore_hotplug) {
+		ctrl_dbg(ctrl, "ignoring hotplug event %#06x\n", events);
+		return IRQ_HANDLED;
 	}
 
-	if (subordinate) {
-		list_for_each_entry(dev, &subordinate->devices, bus_list) {
-			if (dev->ignore_hotplug) {
-				ctrl_dbg(ctrl, "ignoring hotplug event %#06x (%s requested no hotplug)\n",
-					 events, pci_name(dev));
-				return IRQ_HANDLED;
-			}
+	/* Save pending events for consumption by IRQ thread. */
+	atomic_or(events, &ctrl->pending_events);
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t pciehp_ist(int irq, void *dev_id)
+{
+	struct controller *ctrl = (struct controller *)dev_id;
+	struct pci_dev *pdev = ctrl_dev(ctrl);
+	struct slot *slot = ctrl->slot;
+	irqreturn_t ret;
+	u32 events;
+
+	pci_config_pm_runtime_get(pdev);
+
+	/* rerun pciehp_isr() if the port was inaccessible on interrupt */
+	if (atomic_fetch_and(~RERUN_ISR, &ctrl->pending_events) & RERUN_ISR) {
+		ret = pciehp_isr(irq, dev_id);
+		enable_irq(irq);
+		if (ret != IRQ_WAKE_THREAD) {
+			pci_config_pm_runtime_put(pdev);
+			return ret;
 		}
 	}
 
+	synchronize_hardirq(irq);
+	events = atomic_xchg(&ctrl->pending_events, 0);
+	if (!events) {
+		pci_config_pm_runtime_put(pdev);
+		return IRQ_NONE;
+	}
+
 	/* Check Attention Button Pressed */
 	if (events & PCI_EXP_SLTSTA_ABP) {
 		ctrl_info(ctrl, "Slot(%s): Attention button pressed\n",
 			  slot_name(slot));
-		pciehp_queue_interrupt_event(slot, INT_BUTTON_PRESS);
+		pciehp_handle_button_press(slot);
 	}
 
 	/*
-	 * Check Link Status Changed at higher precedence than Presence
-	 * Detect Changed.  The PDS value may be set to "card present" from
-	 * out-of-band detection, which may be in conflict with a Link Down
-	 * and cause the wrong event to queue.
+	 * Disable requests have higher priority than Presence Detect Changed
+	 * or Data Link Layer State Changed events.
 	 */
-	if (events & PCI_EXP_SLTSTA_DLLSC) {
-		ctrl_info(ctrl, "Slot(%s): Link %s\n", slot_name(slot),
-			  link ? "Up" : "Down");
-		pciehp_queue_interrupt_event(slot, link ? INT_LINK_UP :
-					     INT_LINK_DOWN);
-	} else if (events & PCI_EXP_SLTSTA_PDC) {
-		present = !!(status & PCI_EXP_SLTSTA_PDS);
-		ctrl_info(ctrl, "Slot(%s): Card %spresent\n", slot_name(slot),
-			  present ? "" : "not ");
-		pciehp_queue_interrupt_event(slot, present ? INT_PRESENCE_ON :
-					     INT_PRESENCE_OFF);
-	}
+	down_read(&ctrl->reset_lock);
+	if (events & DISABLE_SLOT)
+		pciehp_handle_disable_request(slot);
+	else if (events & (PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_DLLSC))
+		pciehp_handle_presence_or_link_change(slot, events);
+	up_read(&ctrl->reset_lock);
 
 	/* Check Power Fault Detected */
 	if ((events & PCI_EXP_SLTSTA_PFD) && !ctrl->power_fault_detected) {
 		ctrl->power_fault_detected = 1;
 		ctrl_err(ctrl, "Slot(%s): Power fault\n", slot_name(slot));
-		pciehp_queue_interrupt_event(slot, INT_POWER_FAULT);
+		pciehp_set_attention_status(slot, 1);
+		pciehp_green_led_off(slot);
 	}
 
+	pci_config_pm_runtime_put(pdev);
+	wake_up(&ctrl->requester);
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t pcie_isr(int irq, void *dev_id)
+static int pciehp_poll(void *data)
 {
-	irqreturn_t rc, handled = IRQ_NONE;
+	struct controller *ctrl = data;
 
-	/*
-	 * To guarantee that all interrupt events are serviced, we need to
-	 * re-inspect Slot Status register after clearing what is presumed
-	 * to be the last pending interrupt.
-	 */
-	do {
-		rc = pciehp_isr(irq, dev_id);
-		if (rc == IRQ_HANDLED)
-			handled = IRQ_HANDLED;
-	} while (rc == IRQ_HANDLED);
+	schedule_timeout_idle(10 * HZ); /* start with 10 sec delay */
+
+	while (!kthread_should_stop()) {
+		/* poll for interrupt events or user requests */
+		while (pciehp_isr(IRQ_NOTCONNECTED, ctrl) == IRQ_WAKE_THREAD ||
+		       atomic_read(&ctrl->pending_events))
+			pciehp_ist(IRQ_NOTCONNECTED, ctrl);
 
-	/* Return IRQ_HANDLED if we handled one or more events */
-	return handled;
+		if (pciehp_poll_time <= 0 || pciehp_poll_time > 60)
+			pciehp_poll_time = 2; /* clamp to sane value */
+
+		schedule_timeout_idle(pciehp_poll_time * HZ);
+	}
+
+	return 0;
 }
 
 static void pcie_enable_notification(struct controller *ctrl)
@@ -691,17 +729,6 @@ static void pcie_enable_notification(struct controller *ctrl)
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, cmd);
 }
 
-void pcie_reenable_notification(struct controller *ctrl)
-{
-	/*
-	 * Clear both Presence and Data Link Layer Changed to make sure
-	 * those events still fire after we have re-enabled them.
-	 */
-	pcie_capability_write_word(ctrl->pcie->port, PCI_EXP_SLTSTA,
-				   PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_DLLSC);
-	pcie_enable_notification(ctrl);
-}
-
 static void pcie_disable_notification(struct controller *ctrl)
 {
 	u16 mask;
@@ -715,6 +742,12 @@ static void pcie_disable_notification(struct controller *ctrl)
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, 0);
 }
 
+void pcie_clear_hotplug_events(struct controller *ctrl)
+{
+	pcie_capability_write_word(ctrl_dev(ctrl), PCI_EXP_SLTSTA,
+				   PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_DLLSC);
+}
+
 /*
  * pciehp has a 1:1 bus:slot relationship so we ultimately want a secondary
  * bus reset of the bridge, but at the same time we want to ensure that it is
@@ -728,10 +761,13 @@ int pciehp_reset_slot(struct slot *slot, int probe)
 	struct controller *ctrl = slot->ctrl;
 	struct pci_dev *pdev = ctrl_dev(ctrl);
 	u16 stat_mask = 0, ctrl_mask = 0;
+	int rc;
 
 	if (probe)
 		return 0;
 
+	down_write(&ctrl->reset_lock);
+
 	if (!ATTN_BUTTN(ctrl)) {
 		ctrl_mask |= PCI_EXP_SLTCTL_PDCE;
 		stat_mask |= PCI_EXP_SLTSTA_PDC;
@@ -742,18 +778,16 @@ int pciehp_reset_slot(struct slot *slot, int probe)
 	pcie_write_cmd(ctrl, 0, ctrl_mask);
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, 0);
-	if (pciehp_poll_mode)
-		del_timer_sync(&ctrl->poll_timer);
 
-	pci_reset_bridge_secondary_bus(ctrl->pcie->port);
+	rc = pci_bridge_secondary_bus_reset(ctrl->pcie->port);
 
 	pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, stat_mask);
 	pcie_write_cmd_nowait(ctrl, ctrl_mask, ctrl_mask);
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, ctrl_mask);
-	if (pciehp_poll_mode)
-		int_poll_timeout(&ctrl->poll_timer);
-	return 0;
+
+	up_write(&ctrl->reset_lock);
+	return rc;
 }
 
 int pcie_init_notification(struct controller *ctrl)
@@ -765,7 +799,7 @@ int pcie_init_notification(struct controller *ctrl)
 	return 0;
 }
 
-static void pcie_shutdown_notification(struct controller *ctrl)
+void pcie_shutdown_notification(struct controller *ctrl)
 {
 	if (ctrl->notification_enabled) {
 		pcie_disable_notification(ctrl);
@@ -776,32 +810,29 @@ static void pcie_shutdown_notification(struct controller *ctrl)
 
 static int pcie_init_slot(struct controller *ctrl)
 {
+	struct pci_bus *subordinate = ctrl_dev(ctrl)->subordinate;
 	struct slot *slot;
 
 	slot = kzalloc(sizeof(*slot), GFP_KERNEL);
 	if (!slot)
 		return -ENOMEM;
 
-	slot->wq = alloc_ordered_workqueue("pciehp-%u", 0, PSN(ctrl));
-	if (!slot->wq)
-		goto abort;
+	down_read(&pci_bus_sem);
+	slot->state = list_empty(&subordinate->devices) ? OFF_STATE : ON_STATE;
+	up_read(&pci_bus_sem);
 
 	slot->ctrl = ctrl;
 	mutex_init(&slot->lock);
-	mutex_init(&slot->hotplug_lock);
 	INIT_DELAYED_WORK(&slot->work, pciehp_queue_pushbutton_work);
 	ctrl->slot = slot;
 	return 0;
-abort:
-	kfree(slot);
-	return -ENOMEM;
 }
 
 static void pcie_cleanup_slot(struct controller *ctrl)
 {
 	struct slot *slot = ctrl->slot;
-	cancel_delayed_work(&slot->work);
-	destroy_workqueue(slot->wq);
+
+	cancel_delayed_work_sync(&slot->work);
 	kfree(slot);
 }
 
@@ -826,6 +857,7 @@ struct controller *pcie_init(struct pcie_device *dev)
 {
 	struct controller *ctrl;
 	u32 slot_cap, link_cap;
+	u8 occupied, poweron;
 	struct pci_dev *pdev = dev->port;
 
 	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
@@ -847,6 +879,8 @@ struct controller *pcie_init(struct pcie_device *dev)
 
 	ctrl->slot_cap = slot_cap;
 	mutex_init(&ctrl->ctrl_lock);
+	init_rwsem(&ctrl->reset_lock);
+	init_waitqueue_head(&ctrl->requester);
 	init_waitqueue_head(&ctrl->queue);
 	dbg_ctrl(ctrl);
 
@@ -855,16 +889,11 @@ struct controller *pcie_init(struct pcie_device *dev)
 	if (link_cap & PCI_EXP_LNKCAP_DLLLARC)
 		ctrl->link_active_reporting = 1;
 
-	/*
-	 * Clear all remaining event bits in Slot Status register except
-	 * Presence Detect Changed. We want to make sure possible
-	 * hotplug event is triggered when the interrupt is unmasked so
-	 * that we don't lose that event.
-	 */
+	/* Clear all remaining event bits in Slot Status register. */
 	pcie_capability_write_word(pdev, PCI_EXP_SLTSTA,
 		PCI_EXP_SLTSTA_ABP | PCI_EXP_SLTSTA_PFD |
 		PCI_EXP_SLTSTA_MRLSC | PCI_EXP_SLTSTA_CC |
-		PCI_EXP_SLTSTA_DLLSC);
+		PCI_EXP_SLTSTA_DLLSC | PCI_EXP_SLTSTA_PDC);
 
 	ctrl_info(ctrl, "Slot #%d AttnBtn%c PwrCtrl%c MRL%c AttnInd%c PwrInd%c HotPlug%c Surprise%c Interlock%c NoCompl%c LLActRep%c%s\n",
 		(slot_cap & PCI_EXP_SLTCAP_PSN) >> 19,
@@ -883,6 +912,19 @@ struct controller *pcie_init(struct pcie_device *dev)
 	if (pcie_init_slot(ctrl))
 		goto abort_ctrl;
 
+	/*
+	 * If empty slot's power status is on, turn power off.  The IRQ isn't
+	 * requested yet, so avoid triggering a notification with this command.
+	 */
+	if (POWER_CTRL(ctrl)) {
+		pciehp_get_adapter_status(ctrl->slot, &occupied);
+		pciehp_get_power_status(ctrl->slot, &poweron);
+		if (!occupied && poweron) {
+			pcie_disable_notification(ctrl);
+			pciehp_power_off_slot(ctrl->slot);
+		}
+	}
+
 	return ctrl;
 
 abort_ctrl:
@@ -893,7 +935,6 @@ abort:
 
 void pciehp_release_ctrl(struct controller *ctrl)
 {
-	pcie_shutdown_notification(ctrl);
 	pcie_cleanup_slot(ctrl);
 	kfree(ctrl);
 }
diff --git a/drivers/pci/hotplug/pciehp_pci.c b/drivers/pci/hotplug/pciehp_pci.c
index 3f518dea856d..5c58c22e0c08 100644
--- a/drivers/pci/hotplug/pciehp_pci.c
+++ b/drivers/pci/hotplug/pciehp_pci.c
@@ -62,9 +62,8 @@ int pciehp_configure_device(struct slot *p_slot)
 	return ret;
 }
 
-int pciehp_unconfigure_device(struct slot *p_slot)
+void pciehp_unconfigure_device(struct slot *p_slot)
 {
-	int rc = 0;
 	u8 presence = 0;
 	struct pci_dev *dev, *temp;
 	struct pci_bus *parent = p_slot->ctrl->pcie->port->subordinate;
@@ -107,5 +106,4 @@ int pciehp_unconfigure_device(struct slot *p_slot)
 	}
 
 	pci_unlock_rescan_remove();
-	return rc;
 }
diff --git a/drivers/pci/hotplug/pcihp_skeleton.c b/drivers/pci/hotplug/pcihp_skeleton.c
deleted file mode 100644
index c19694a04d2c..000000000000
--- a/drivers/pci/hotplug/pcihp_skeleton.c
+++ /dev/null
@@ -1,348 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-/*
- * PCI Hot Plug Controller Skeleton Driver - 0.3
- *
- * Copyright (C) 2001,2003 Greg Kroah-Hartman (greg@kroah.com)
- * Copyright (C) 2001,2003 IBM Corp.
- *
- * All rights reserved.
- *
- * This driver is to be used as a skeleton driver to show how to interface
- * with the pci hotplug core easily.
- *
- * Send feedback to <greg@kroah.com>
- *
- */
-
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/pci.h>
-#include <linux/pci_hotplug.h>
-#include <linux/init.h>
-
-#define SLOT_NAME_SIZE	10
-struct slot {
-	u8 number;
-	struct hotplug_slot *hotplug_slot;
-	struct list_head slot_list;
-	char name[SLOT_NAME_SIZE];
-};
-
-static LIST_HEAD(slot_list);
-
-#define MY_NAME	"pcihp_skeleton"
-
-#define dbg(format, arg...)					\
-	do {							\
-		if (debug)					\
-			printk(KERN_DEBUG "%s: " format "\n",	\
-				MY_NAME, ## arg);		\
-	} while (0)
-#define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME, ## arg)
-#define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME, ## arg)
-#define warn(format, arg...) printk(KERN_WARNING "%s: " format "\n", MY_NAME, ## arg)
-
-/* local variables */
-static bool debug;
-static int num_slots;
-
-#define DRIVER_VERSION	"0.3"
-#define DRIVER_AUTHOR	"Greg Kroah-Hartman <greg@kroah.com>"
-#define DRIVER_DESC	"Hot Plug PCI Controller Skeleton Driver"
-
-MODULE_AUTHOR(DRIVER_AUTHOR);
-MODULE_DESCRIPTION(DRIVER_DESC);
-MODULE_LICENSE("GPL");
-module_param(debug, bool, 0644);
-MODULE_PARM_DESC(debug, "Debugging mode enabled or not");
-
-static int enable_slot(struct hotplug_slot *slot);
-static int disable_slot(struct hotplug_slot *slot);
-static int set_attention_status(struct hotplug_slot *slot, u8 value);
-static int hardware_test(struct hotplug_slot *slot, u32 value);
-static int get_power_status(struct hotplug_slot *slot, u8 *value);
-static int get_attention_status(struct hotplug_slot *slot, u8 *value);
-static int get_latch_status(struct hotplug_slot *slot, u8 *value);
-static int get_adapter_status(struct hotplug_slot *slot, u8 *value);
-
-static struct hotplug_slot_ops skel_hotplug_slot_ops = {
-	.enable_slot =		enable_slot,
-	.disable_slot =		disable_slot,
-	.set_attention_status =	set_attention_status,
-	.hardware_test =	hardware_test,
-	.get_power_status =	get_power_status,
-	.get_attention_status =	get_attention_status,
-	.get_latch_status =	get_latch_status,
-	.get_adapter_status =	get_adapter_status,
-};
-
-static int enable_slot(struct hotplug_slot *hotplug_slot)
-{
-	struct slot *slot = hotplug_slot->private;
-	int retval = 0;
-
-	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
-
-	/*
-	 * Fill in code here to enable the specified slot
-	 */
-
-	return retval;
-}
-
-static int disable_slot(struct hotplug_slot *hotplug_slot)
-{
-	struct slot *slot = hotplug_slot->private;
-	int retval = 0;
-
-	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
-
-	/*
-	 * Fill in code here to disable the specified slot
-	 */
-
-	return retval;
-}
-
-static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status)
-{
-	struct slot *slot = hotplug_slot->private;
-	int retval = 0;
-
-	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
-
-	switch (status) {
-	case 0:
-		/*
-		 * Fill in code here to turn light off
-		 */
-		break;
-
-	case 1:
-	default:
-		/*
-		 * Fill in code here to turn light on
-		 */
-		break;
-	}
-
-	return retval;
-}
-
-static int hardware_test(struct hotplug_slot *hotplug_slot, u32 value)
-{
-	struct slot *slot = hotplug_slot->private;
-	int retval = 0;
-
-	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
-
-	switch (value) {
-	case 0:
-		/* Specify a test here */
-		break;
-	case 1:
-		/* Specify another test here */
-		break;
-	}
-
-	return retval;
-}
-
-static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value)
-{
-	struct slot *slot = hotplug_slot->private;
-	int retval = 0;
-
-	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
-
-	/*
-	 * Fill in logic to get the current power status of the specific
-	 * slot and store it in the *value location.
-	 */
-
-	return retval;
-}
-
-static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value)
-{
-	struct slot *slot = hotplug_slot->private;
-	int retval = 0;
-
-	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
-
-	/*
-	 * Fill in logic to get the current attention status of the specific
-	 * slot and store it in the *value location.
-	 */
-
-	return retval;
-}
-
-static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value)
-{
-	struct slot *slot = hotplug_slot->private;
-	int retval = 0;
-
-	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
-
-	/*
-	 * Fill in logic to get the current latch status of the specific
-	 * slot and store it in the *value location.
-	 */
-
-	return retval;
-}
-
-static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
-{
-	struct slot *slot = hotplug_slot->private;
-	int retval = 0;
-
-	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
-
-	/*
-	 * Fill in logic to get the current adapter status of the specific
-	 * slot and store it in the *value location.
-	 */
-
-	return retval;
-}
-
-static void release_slot(struct hotplug_slot *hotplug_slot)
-{
-	struct slot *slot = hotplug_slot->private;
-
-	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
-	kfree(slot->hotplug_slot->info);
-	kfree(slot->hotplug_slot);
-	kfree(slot);
-}
-
-static void make_slot_name(struct slot *slot)
-{
-	/*
-	 * Stupid way to make a filename out of the slot name.
-	 * replace this if your hardware provides a better way to name slots.
-	 */
-	snprintf(slot->hotplug_slot->name, SLOT_NAME_SIZE, "%d", slot->number);
-}
-
-/**
- * init_slots - initialize 'struct slot' structures for each slot
- *
- */
-static int __init init_slots(void)
-{
-	struct slot *slot;
-	struct hotplug_slot *hotplug_slot;
-	struct hotplug_slot_info *info;
-	int retval;
-	int i;
-
-	/*
-	 * Create a structure for each slot, and register that slot
-	 * with the pci_hotplug subsystem.
-	 */
-	for (i = 0; i < num_slots; ++i) {
-		slot = kzalloc(sizeof(*slot), GFP_KERNEL);
-		if (!slot) {
-			retval = -ENOMEM;
-			goto error;
-		}
-
-		hotplug_slot = kzalloc(sizeof(*hotplug_slot), GFP_KERNEL);
-		if (!hotplug_slot) {
-			retval = -ENOMEM;
-			goto error_slot;
-		}
-		slot->hotplug_slot = hotplug_slot;
-
-		info = kzalloc(sizeof(*info), GFP_KERNEL);
-		if (!info) {
-			retval = -ENOMEM;
-			goto error_hpslot;
-		}
-		hotplug_slot->info = info;
-
-		slot->number = i;
-
-		hotplug_slot->name = slot->name;
-		hotplug_slot->private = slot;
-		hotplug_slot->release = &release_slot;
-		make_slot_name(slot);
-		hotplug_slot->ops = &skel_hotplug_slot_ops;
-
-		/*
-		 * Initialize the slot info structure with some known
-		 * good values.
-		 */
-		get_power_status(hotplug_slot, &info->power_status);
-		get_attention_status(hotplug_slot, &info->attention_status);
-		get_latch_status(hotplug_slot, &info->latch_status);
-		get_adapter_status(hotplug_slot, &info->adapter_status);
-
-		dbg("registering slot %d\n", i);
-		retval = pci_hp_register(slot->hotplug_slot);
-		if (retval) {
-			err("pci_hp_register failed with error %d\n", retval);
-			goto error_info;
-		}
-
-		/* add slot to our internal list */
-		list_add(&slot->slot_list, &slot_list);
-	}
-
-	return 0;
-error_info:
-	kfree(info);
-error_hpslot:
-	kfree(hotplug_slot);
-error_slot:
-	kfree(slot);
-error:
-	return retval;
-}
-
-static void __exit cleanup_slots(void)
-{
-	struct slot *slot, *next;
-
-	/*
-	 * Unregister all of our slots with the pci_hotplug subsystem.
-	 * Memory will be freed in release_slot() callback after slot's
-	 * lifespan is finished.
-	 */
-	list_for_each_entry_safe(slot, next, &slot_list, slot_list) {
-		list_del(&slot->slot_list);
-		pci_hp_deregister(slot->hotplug_slot);
-	}
-}
-
-static int __init pcihp_skel_init(void)
-{
-	int retval;
-
-	info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
-	/*
-	 * Do specific initialization stuff for your driver here
-	 * like initializing your controller hardware (if any) and
-	 * determining the number of slots you have in the system
-	 * right now.
-	 */
-	num_slots = 5;
-
-	return init_slots();
-}
-
-static void __exit pcihp_skel_exit(void)
-{
-	/*
-	 * Clean everything up.
-	 */
-	cleanup_slots();
-}
-
-module_init(pcihp_skel_init);
-module_exit(pcihp_skel_exit);
diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c
index 6c2e8d7307c6..3276a5e4c430 100644
--- a/drivers/pci/hotplug/pnv_php.c
+++ b/drivers/pci/hotplug/pnv_php.c
@@ -538,9 +538,8 @@ static struct hotplug_slot_ops php_slot_ops = {
 	.disable_slot		= pnv_php_disable_slot,
 };
 
-static void pnv_php_release(struct hotplug_slot *slot)
+static void pnv_php_release(struct pnv_php_slot *php_slot)
 {
-	struct pnv_php_slot *php_slot = slot->private;
 	unsigned long flags;
 
 	/* Remove from global or child list */
@@ -596,7 +595,6 @@ static struct pnv_php_slot *pnv_php_alloc_slot(struct device_node *dn)
 	php_slot->power_state_check     = false;
 	php_slot->slot.ops              = &php_slot_ops;
 	php_slot->slot.info             = &php_slot->slot_info;
-	php_slot->slot.release          = pnv_php_release;
 	php_slot->slot.private          = php_slot;
 
 	INIT_LIST_HEAD(&php_slot->children);
@@ -924,6 +922,7 @@ static void pnv_php_unregister_one(struct device_node *dn)
 
 	php_slot->state = PNV_PHP_STATE_OFFLINE;
 	pci_hp_deregister(&php_slot->slot);
+	pnv_php_release(php_slot);
 	pnv_php_put_slot(php_slot);
 }
 
diff --git a/drivers/pci/hotplug/rpaphp_core.c b/drivers/pci/hotplug/rpaphp_core.c
index fb5e0845429d..857c358b727b 100644
--- a/drivers/pci/hotplug/rpaphp_core.c
+++ b/drivers/pci/hotplug/rpaphp_core.c
@@ -404,13 +404,13 @@ static void __exit cleanup_slots(void)
 	/*
 	 * Unregister all of our slots with the pci_hotplug subsystem,
 	 * and free up all memory that we had allocated.
-	 * memory will be freed in release_slot callback.
 	 */
 
 	list_for_each_entry_safe(slot, next, &rpaphp_slot_head,
 				 rpaphp_slot_list) {
 		list_del(&slot->rpaphp_slot_list);
 		pci_hp_deregister(slot->hotplug_slot);
+		dealloc_slot_struct(slot);
 	}
 	return;
 }
diff --git a/drivers/pci/hotplug/rpaphp_slot.c b/drivers/pci/hotplug/rpaphp_slot.c
index 3840a2075e6a..b916c8e4372d 100644
--- a/drivers/pci/hotplug/rpaphp_slot.c
+++ b/drivers/pci/hotplug/rpaphp_slot.c
@@ -19,12 +19,6 @@
 #include "rpaphp.h"
 
 /* free up the memory used by a slot */
-static void rpaphp_release_slot(struct hotplug_slot *hotplug_slot)
-{
-	struct slot *slot = (struct slot *) hotplug_slot->private;
-	dealloc_slot_struct(slot);
-}
-
 void dealloc_slot_struct(struct slot *slot)
 {
 	kfree(slot->hotplug_slot->info);
@@ -56,7 +50,6 @@ struct slot *alloc_slot_struct(struct device_node *dn,
 	slot->power_domain = power_domain;
 	slot->hotplug_slot->private = slot;
 	slot->hotplug_slot->ops = &rpaphp_hotplug_slot_ops;
-	slot->hotplug_slot->release = &rpaphp_release_slot;
 
 	return (slot);
 
@@ -90,10 +83,8 @@ int rpaphp_deregister_slot(struct slot *slot)
 		__func__, slot->name);
 
 	list_del(&slot->rpaphp_slot_list);
-
-	retval = pci_hp_deregister(php_slot);
-	if (retval)
-		err("Problem unregistering a slot %s\n", slot->name);
+	pci_hp_deregister(php_slot);
+	dealloc_slot_struct(slot);
 
 	dbg("%s - Exit: rc[%d]\n", __func__, retval);
 	return retval;
diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c
index ffdc2977395d..93b5341d282c 100644
--- a/drivers/pci/hotplug/s390_pci_hpc.c
+++ b/drivers/pci/hotplug/s390_pci_hpc.c
@@ -130,15 +130,6 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
 	return 0;
 }
 
-static void release_slot(struct hotplug_slot *hotplug_slot)
-{
-	struct slot *slot = hotplug_slot->private;
-
-	kfree(slot->hotplug_slot->info);
-	kfree(slot->hotplug_slot);
-	kfree(slot);
-}
-
 static struct hotplug_slot_ops s390_hotplug_slot_ops = {
 	.enable_slot =		enable_slot,
 	.disable_slot =		disable_slot,
@@ -175,7 +166,6 @@ int zpci_init_slot(struct zpci_dev *zdev)
 	hotplug_slot->info = info;
 
 	hotplug_slot->ops = &s390_hotplug_slot_ops;
-	hotplug_slot->release = &release_slot;
 
 	get_power_status(hotplug_slot, &info->power_status);
 	get_adapter_status(hotplug_slot, &info->adapter_status);
@@ -209,5 +199,8 @@ void zpci_exit_slot(struct zpci_dev *zdev)
 			continue;
 		list_del(&slot->slot_list);
 		pci_hp_deregister(slot->hotplug_slot);
+		kfree(slot->hotplug_slot->info);
+		kfree(slot->hotplug_slot);
+		kfree(slot);
 	}
 }
diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c
index 78b6bdbb3a39..babd23409f61 100644
--- a/drivers/pci/hotplug/sgi_hotplug.c
+++ b/drivers/pci/hotplug/sgi_hotplug.c
@@ -628,7 +628,6 @@ static int sn_hotplug_slot_register(struct pci_bus *pci_bus)
 			goto alloc_err;
 		}
 		bss_hotplug_slot->ops = &sn_hotplug_slot_ops;
-		bss_hotplug_slot->release = &sn_release_slot;
 
 		rc = pci_hp_register(bss_hotplug_slot, pci_bus, device, name);
 		if (rc)
@@ -656,8 +655,10 @@ alloc_err:
 		sn_release_slot(bss_hotplug_slot);
 
 	/* destroy anything else on the list */
-	while ((bss_hotplug_slot = sn_hp_destroy()))
+	while ((bss_hotplug_slot = sn_hp_destroy())) {
 		pci_hp_deregister(bss_hotplug_slot);
+		sn_release_slot(bss_hotplug_slot);
+	}
 
 	return rc;
 }
@@ -703,8 +704,10 @@ static void __exit sn_pci_hotplug_exit(void)
 {
 	struct hotplug_slot *bss_hotplug_slot;
 
-	while ((bss_hotplug_slot = sn_hp_destroy()))
+	while ((bss_hotplug_slot = sn_hp_destroy())) {
 		pci_hp_deregister(bss_hotplug_slot);
+		sn_release_slot(bss_hotplug_slot);
+	}
 
 	if (!list_empty(&sn_hp_list))
 		printk(KERN_ERR "%s: internal list is not empty\n", __FILE__);
diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c
index e91be287f292..97cee23f3d51 100644
--- a/drivers/pci/hotplug/shpchp_core.c
+++ b/drivers/pci/hotplug/shpchp_core.c
@@ -61,22 +61,6 @@ static struct hotplug_slot_ops shpchp_hotplug_slot_ops = {
 	.get_adapter_status =	get_adapter_status,
 };
 
-/**
- * release_slot - free up the memory used by a slot
- * @hotplug_slot: slot to free
- */
-static void release_slot(struct hotplug_slot *hotplug_slot)
-{
-	struct slot *slot = hotplug_slot->private;
-
-	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
-		 __func__, slot_name(slot));
-
-	kfree(slot->hotplug_slot->info);
-	kfree(slot->hotplug_slot);
-	kfree(slot);
-}
-
 static int init_slots(struct controller *ctrl)
 {
 	struct slot *slot;
@@ -125,7 +109,6 @@ static int init_slots(struct controller *ctrl)
 
 		/* register this slot with the hotplug pci core */
 		hotplug_slot->private = slot;
-		hotplug_slot->release = &release_slot;
 		snprintf(name, SLOT_NAME_SIZE, "%d", slot->number);
 		hotplug_slot->ops = &shpchp_hotplug_slot_ops;
 
@@ -171,6 +154,9 @@ void cleanup_slots(struct controller *ctrl)
 		cancel_delayed_work(&slot->work);
 		destroy_workqueue(slot->wq);
 		pci_hp_deregister(slot->hotplug_slot);
+		kfree(slot->hotplug_slot->info);
+		kfree(slot->hotplug_slot);
+		kfree(slot);
 	}
 }
 
@@ -270,11 +256,30 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
 	return 0;
 }
 
+static bool shpc_capable(struct pci_dev *bridge)
+{
+	/*
+	 * It is assumed that AMD GOLAM chips support SHPC but they do not
+	 * have SHPC capability.
+	 */
+	if (bridge->vendor == PCI_VENDOR_ID_AMD &&
+	    bridge->device == PCI_DEVICE_ID_AMD_GOLAM_7450)
+		return true;
+
+	if (pci_find_capability(bridge, PCI_CAP_ID_SHPC))
+		return true;
+
+	return false;
+}
+
 static int shpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	int rc;
 	struct controller *ctrl;
 
+	if (!shpc_capable(pdev))
+		return -ENODEV;
+
 	if (acpi_get_hp_hw_control_from_firmware(pdev))
 		return -ENODEV;
 
@@ -303,6 +308,7 @@ static int shpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto err_cleanup_slots;
 
+	pdev->shpc_managed = 1;
 	return 0;
 
 err_cleanup_slots:
@@ -319,6 +325,7 @@ static void shpc_remove(struct pci_dev *dev)
 {
 	struct controller *ctrl = pci_get_drvdata(dev);
 
+	dev->shpc_managed = 0;
 	shpchp_remove_ctrl_files(ctrl);
 	ctrl->hpc_ops->release_ctlr(ctrl);
 	kfree(ctrl);
diff --git a/drivers/pci/hotplug/shpchp_ctrl.c b/drivers/pci/hotplug/shpchp_ctrl.c
index 1047b56e5730..1267dcc5a531 100644
--- a/drivers/pci/hotplug/shpchp_ctrl.c
+++ b/drivers/pci/hotplug/shpchp_ctrl.c
@@ -654,6 +654,7 @@ int shpchp_sysfs_enable_slot(struct slot *p_slot)
 	switch (p_slot->state) {
 	case BLINKINGON_STATE:
 		cancel_delayed_work(&p_slot->work);
+		/* fall through */
 	case STATIC_STATE:
 		p_slot->state = POWERON_STATE;
 		mutex_unlock(&p_slot->lock);
@@ -689,6 +690,7 @@ int shpchp_sysfs_disable_slot(struct slot *p_slot)
 	switch (p_slot->state) {
 	case BLINKINGOFF_STATE:
 		cancel_delayed_work(&p_slot->work);
+		/* fall through */
 	case STATIC_STATE:
 		p_slot->state = POWEROFF_STATE;
 		mutex_unlock(&p_slot->lock);
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 0f04ae648cf1..c5f3cd4ed766 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -818,15 +818,15 @@ int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs)
 {
 	if (!dev->is_physfn)
 		return -ENOSYS;
+
 	if (numvfs > dev->sriov->total_VFs)
 		return -EINVAL;
 
 	/* Shouldn't change if VFs already enabled */
 	if (dev->sriov->ctrl & PCI_SRIOV_CTRL_VFE)
 		return -EBUSY;
-	else
-		dev->sriov->driver_max_VFs = numvfs;
 
+	dev->sriov->driver_max_VFs = numvfs;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(pci_sriov_set_totalvfs);
diff --git a/drivers/pci/irq.c b/drivers/pci/irq.c
index 2a808e10645f..a1de501a2729 100644
--- a/drivers/pci/irq.c
+++ b/drivers/pci/irq.c
@@ -86,13 +86,17 @@ int pci_request_irq(struct pci_dev *dev, unsigned int nr, irq_handler_t handler,
 	va_list ap;
 	int ret;
 	char *devname;
+	unsigned long irqflags = IRQF_SHARED;
+
+	if (!handler)
+		irqflags |= IRQF_ONESHOT;
 
 	va_start(ap, fmt);
 	devname = kvasprintf(GFP_KERNEL, fmt, ap);
 	va_end(ap);
 
 	ret = request_threaded_irq(pci_irq_vector(dev, nr), handler, thread_fn,
-			IRQF_SHARED, devname, dev_id);
+				   irqflags, devname, dev_id);
 	if (ret)
 		kfree(devname);
 	return ret;
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 4d88afdfc843..f2ef896464b3 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1446,6 +1446,9 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
 	if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE))
 		info->flags |= MSI_FLAG_MUST_REACTIVATE;
 
+	/* PCI-MSI is oneshot-safe */
+	info->chip->flags |= IRQCHIP_ONESHOT_SAFE;
+
 	domain = msi_create_irq_domain(fwnode, info, parent);
 	if (!domain)
 		return NULL;
diff --git a/drivers/pci/of.c b/drivers/pci/of.c
index 69a60d6ebd73..1836b8ddf292 100644
--- a/drivers/pci/of.c
+++ b/drivers/pci/of.c
@@ -266,7 +266,7 @@ int devm_of_pci_get_host_bridge_resources(struct device *dev,
 			struct list_head *resources, resource_size_t *io_base)
 {
 	struct device_node *dev_node = dev->of_node;
-	struct resource *res;
+	struct resource *res, tmp_res;
 	struct resource *bus_range;
 	struct of_pci_range range;
 	struct of_pci_range_parser parser;
@@ -320,18 +320,16 @@ int devm_of_pci_get_host_bridge_resources(struct device *dev,
 		if (range.cpu_addr == OF_BAD_ADDR || range.size == 0)
 			continue;
 
-		res = devm_kzalloc(dev, sizeof(struct resource), GFP_KERNEL);
+		err = of_pci_range_to_resource(&range, dev_node, &tmp_res);
+		if (err)
+			continue;
+
+		res = devm_kmemdup(dev, &tmp_res, sizeof(tmp_res), GFP_KERNEL);
 		if (!res) {
 			err = -ENOMEM;
 			goto failed;
 		}
 
-		err = of_pci_range_to_resource(&range, dev_node, res);
-		if (err) {
-			devm_kfree(dev, res);
-			continue;
-		}
-
 		if (resource_type(res) == IORESOURCE_IO) {
 			if (!io_base) {
 				dev_err(dev, "I/O range found for %pOF. Please provide an io_base pointer to save CPU base address\n",
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 89ee6a2b6eb8..738e3546abb1 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -403,24 +403,7 @@ bool pciehp_is_native(struct pci_dev *bridge)
  */
 bool shpchp_is_native(struct pci_dev *bridge)
 {
-	const struct pci_host_bridge *host;
-
-	if (!IS_ENABLED(CONFIG_HOTPLUG_PCI_SHPC))
-		return false;
-
-	/*
-	 * It is assumed that AMD GOLAM chips support SHPC but they do not
-	 * have SHPC capability.
-	 */
-	if (bridge->vendor == PCI_VENDOR_ID_AMD &&
-	    bridge->device == PCI_DEVICE_ID_AMD_GOLAM_7450)
-		return true;
-
-	if (!pci_find_capability(bridge, PCI_CAP_ID_SHPC))
-		return false;
-
-	host = pci_find_host_bridge(bridge->bus);
-	return host->native_shpc_hotplug;
+	return bridge->shpc_managed;
 }
 
 /**
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 6792292b5fc7..bef17c3fca67 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -1668,7 +1668,7 @@ static int __init pci_driver_init(void)
 	if (ret)
 		return ret;
 #endif
-
+	dma_debug_add_bus(&pci_bus_type);
 	return 0;
 }
 postcore_initcall(pci_driver_init);
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 0c4653c1d2ce..9ecfe13157c0 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -23,7 +23,6 @@
 #include <linux/fs.h>
 #include <linux/capability.h>
 #include <linux/security.h>
-#include <linux/pci-aspm.h>
 #include <linux/slab.h>
 #include <linux/vgaarb.h>
 #include <linux/pm_runtime.h>
@@ -1449,7 +1448,9 @@ static ssize_t reset_store(struct device *dev, struct device_attribute *attr,
 	if (val != 1)
 		return -EINVAL;
 
+	pm_runtime_get_sync(dev);
 	result = pci_reset_function(pdev);
+	pm_runtime_put(dev);
 	if (result < 0)
 		return result;
 
@@ -1746,6 +1747,9 @@ static const struct attribute_group *pci_dev_attr_groups[] = {
 #endif
 	&pci_bridge_attr_group,
 	&pcie_dev_attr_group,
+#ifdef CONFIG_PCIEAER
+	&aer_stats_attr_group,
+#endif
 	NULL,
 };
 
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 316496e99da9..29ff9619b5fa 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -23,7 +23,6 @@
 #include <linux/string.h>
 #include <linux/log2.h>
 #include <linux/logic_pio.h>
-#include <linux/pci-aspm.h>
 #include <linux/pm_wakeup.h>
 #include <linux/interrupt.h>
 #include <linux/device.h>
@@ -115,6 +114,9 @@ static bool pcie_ari_disabled;
 /* If set, the PCIe ATS capability will not be used. */
 static bool pcie_ats_disabled;
 
+/* If set, the PCI config space of each device is printed during boot. */
+bool pci_early_dump;
+
 bool pci_ats_disabled(void)
 {
 	return pcie_ats_disabled;
@@ -191,6 +193,168 @@ void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar)
 EXPORT_SYMBOL_GPL(pci_ioremap_wc_bar);
 #endif
 
+/**
+ * pci_dev_str_match_path - test if a path string matches a device
+ * @dev:    the PCI device to test
+ * @p:      string to match the device against
+ * @endptr: pointer to the string after the match
+ *
+ * Test if a string (typically from a kernel parameter) formatted as a
+ * path of device/function addresses matches a PCI device. The string must
+ * be of the form:
+ *
+ *   [<domain>:]<bus>:<device>.<func>[/<device>.<func>]*
+ *
+ * A path for a device can be obtained using 'lspci -t'.  Using a path
+ * is more robust against bus renumbering than using only a single bus,
+ * device and function address.
+ *
+ * Returns 1 if the string matches the device, 0 if it does not and
+ * a negative error code if it fails to parse the string.
+ */
+static int pci_dev_str_match_path(struct pci_dev *dev, const char *path,
+				  const char **endptr)
+{
+	int ret;
+	int seg, bus, slot, func;
+	char *wpath, *p;
+	char end;
+
+	*endptr = strchrnul(path, ';');
+
+	wpath = kmemdup_nul(path, *endptr - path, GFP_KERNEL);
+	if (!wpath)
+		return -ENOMEM;
+
+	while (1) {
+		p = strrchr(wpath, '/');
+		if (!p)
+			break;
+		ret = sscanf(p, "/%x.%x%c", &slot, &func, &end);
+		if (ret != 2) {
+			ret = -EINVAL;
+			goto free_and_exit;
+		}
+
+		if (dev->devfn != PCI_DEVFN(slot, func)) {
+			ret = 0;
+			goto free_and_exit;
+		}
+
+		/*
+		 * Note: we don't need to get a reference to the upstream
+		 * bridge because we hold a reference to the top level
+		 * device which should hold a reference to the bridge,
+		 * and so on.
+		 */
+		dev = pci_upstream_bridge(dev);
+		if (!dev) {
+			ret = 0;
+			goto free_and_exit;
+		}
+
+		*p = 0;
+	}
+
+	ret = sscanf(wpath, "%x:%x:%x.%x%c", &seg, &bus, &slot,
+		     &func, &end);
+	if (ret != 4) {
+		seg = 0;
+		ret = sscanf(wpath, "%x:%x.%x%c", &bus, &slot, &func, &end);
+		if (ret != 3) {
+			ret = -EINVAL;
+			goto free_and_exit;
+		}
+	}
+
+	ret = (seg == pci_domain_nr(dev->bus) &&
+	       bus == dev->bus->number &&
+	       dev->devfn == PCI_DEVFN(slot, func));
+
+free_and_exit:
+	kfree(wpath);
+	return ret;
+}
+
+/**
+ * pci_dev_str_match - test if a string matches a device
+ * @dev:    the PCI device to test
+ * @p:      string to match the device against
+ * @endptr: pointer to the string after the match
+ *
+ * Test if a string (typically from a kernel parameter) matches a specified
+ * PCI device. The string may be of one of the following formats:
+ *
+ *   [<domain>:]<bus>:<device>.<func>[/<device>.<func>]*
+ *   pci:<vendor>:<device>[:<subvendor>:<subdevice>]
+ *
+ * The first format specifies a PCI bus/device/function address which
+ * may change if new hardware is inserted, if motherboard firmware changes,
+ * or due to changes caused in kernel parameters. If the domain is
+ * left unspecified, it is taken to be 0.  In order to be robust against
+ * bus renumbering issues, a path of PCI device/function numbers may be used
+ * to address the specific device.  The path for a device can be determined
+ * through the use of 'lspci -t'.
+ *
+ * The second format matches devices using IDs in the configuration
+ * space which may match multiple devices in the system. A value of 0
+ * for any field will match all devices. (Note: this differs from
+ * in-kernel code that uses PCI_ANY_ID which is ~0; this is for
+ * legacy reasons and convenience so users don't have to specify
+ * FFFFFFFFs on the command line.)
+ *
+ * Returns 1 if the string matches the device, 0 if it does not and
+ * a negative error code if the string cannot be parsed.
+ */
+static int pci_dev_str_match(struct pci_dev *dev, const char *p,
+			     const char **endptr)
+{
+	int ret;
+	int count;
+	unsigned short vendor, device, subsystem_vendor, subsystem_device;
+
+	if (strncmp(p, "pci:", 4) == 0) {
+		/* PCI vendor/device (subvendor/subdevice) IDs are specified */
+		p += 4;
+		ret = sscanf(p, "%hx:%hx:%hx:%hx%n", &vendor, &device,
+			     &subsystem_vendor, &subsystem_device, &count);
+		if (ret != 4) {
+			ret = sscanf(p, "%hx:%hx%n", &vendor, &device, &count);
+			if (ret != 2)
+				return -EINVAL;
+
+			subsystem_vendor = 0;
+			subsystem_device = 0;
+		}
+
+		p += count;
+
+		if ((!vendor || vendor == dev->vendor) &&
+		    (!device || device == dev->device) &&
+		    (!subsystem_vendor ||
+			    subsystem_vendor == dev->subsystem_vendor) &&
+		    (!subsystem_device ||
+			    subsystem_device == dev->subsystem_device))
+			goto found;
+	} else {
+		/*
+		 * PCI Bus, Device, Function IDs are specified
+		 *  (optionally, may include a path of devfns following it)
+		 */
+		ret = pci_dev_str_match_path(dev, p, &p);
+		if (ret < 0)
+			return ret;
+		else if (ret)
+			goto found;
+	}
+
+	*endptr = p;
+	return 0;
+
+found:
+	*endptr = p;
+	return 1;
+}
 
 static int __pci_find_next_cap_ttl(struct pci_bus *bus, unsigned int devfn,
 				   u8 pos, int cap, int *ttl)
@@ -1171,6 +1335,33 @@ static void pci_restore_config_space(struct pci_dev *pdev)
 	}
 }
 
+static void pci_restore_rebar_state(struct pci_dev *pdev)
+{
+	unsigned int pos, nbars, i;
+	u32 ctrl;
+
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_REBAR);
+	if (!pos)
+		return;
+
+	pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl);
+	nbars = (ctrl & PCI_REBAR_CTRL_NBAR_MASK) >>
+		    PCI_REBAR_CTRL_NBAR_SHIFT;
+
+	for (i = 0; i < nbars; i++, pos += 8) {
+		struct resource *res;
+		int bar_idx, size;
+
+		pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl);
+		bar_idx = ctrl & PCI_REBAR_CTRL_BAR_IDX;
+		res = pdev->resource + bar_idx;
+		size = order_base_2((resource_size(res) >> 20) | 1) - 1;
+		ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE;
+		ctrl |= size << PCI_REBAR_CTRL_BAR_SHIFT;
+		pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl);
+	}
+}
+
 /**
  * pci_restore_state - Restore the saved state of a PCI device
  * @dev: - PCI device that we're dealing with
@@ -1186,6 +1377,7 @@ void pci_restore_state(struct pci_dev *dev)
 	pci_restore_pri_state(dev);
 	pci_restore_ats_state(dev);
 	pci_restore_vc_state(dev);
+	pci_restore_rebar_state(dev);
 
 	pci_cleanup_aer_error_status_regs(dev);
 
@@ -2045,6 +2237,7 @@ static pci_power_t pci_target_state(struct pci_dev *dev, bool wakeup)
 		case PCI_D2:
 			if (pci_no_d1d2(dev))
 				break;
+			/* else: fall through */
 		default:
 			target_state = state;
 		}
@@ -2290,7 +2483,7 @@ void pci_config_pm_runtime_put(struct pci_dev *pdev)
  * @bridge: Bridge to check
  *
  * This function checks if it is possible to move the bridge to D3.
- * Currently we only allow D3 for recent enough PCIe ports.
+ * Currently we only allow D3 for recent enough PCIe ports and Thunderbolt.
  */
 bool pci_bridge_d3_possible(struct pci_dev *bridge)
 {
@@ -2305,18 +2498,27 @@ bool pci_bridge_d3_possible(struct pci_dev *bridge)
 			return false;
 
 		/*
-		 * Hotplug interrupts cannot be delivered if the link is down,
-		 * so parents of a hotplug port must stay awake. In addition,
-		 * hotplug ports handled by firmware in System Management Mode
+		 * Hotplug ports handled by firmware in System Management Mode
 		 * may not be put into D3 by the OS (Thunderbolt on non-Macs).
-		 * For simplicity, disallow in general for now.
 		 */
-		if (bridge->is_hotplug_bridge)
+		if (bridge->is_hotplug_bridge && !pciehp_is_native(bridge))
 			return false;
 
 		if (pci_bridge_d3_force)
 			return true;
 
+		/* Even the oldest 2010 Thunderbolt controller supports D3. */
+		if (bridge->is_thunderbolt)
+			return true;
+
+		/*
+		 * Hotplug ports handled natively by the OS were not validated
+		 * by vendors for runtime D3 at least until 2018 because there
+		 * was no OS support.
+		 */
+		if (bridge->is_hotplug_bridge)
+			return false;
+
 		/*
 		 * It should be safe to put PCIe ports from 2015 or newer
 		 * to D3.
@@ -2820,6 +3022,66 @@ void pci_request_acs(void)
 	pci_acs_enable = 1;
 }
 
+static const char *disable_acs_redir_param;
+
+/**
+ * pci_disable_acs_redir - disable ACS redirect capabilities
+ * @dev: the PCI device
+ *
+ * For only devices specified in the disable_acs_redir parameter.
+ */
+static void pci_disable_acs_redir(struct pci_dev *dev)
+{
+	int ret = 0;
+	const char *p;
+	int pos;
+	u16 ctrl;
+
+	if (!disable_acs_redir_param)
+		return;
+
+	p = disable_acs_redir_param;
+	while (*p) {
+		ret = pci_dev_str_match(dev, p, &p);
+		if (ret < 0) {
+			pr_info_once("PCI: Can't parse disable_acs_redir parameter: %s\n",
+				     disable_acs_redir_param);
+
+			break;
+		} else if (ret == 1) {
+			/* Found a match */
+			break;
+		}
+
+		if (*p != ';' && *p != ',') {
+			/* End of param or invalid format */
+			break;
+		}
+		p++;
+	}
+
+	if (ret != 1)
+		return;
+
+	if (!pci_dev_specific_disable_acs_redir(dev))
+		return;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
+	if (!pos) {
+		pci_warn(dev, "cannot disable ACS redirect for this hardware as it does not have ACS capabilities\n");
+		return;
+	}
+
+	pci_read_config_word(dev, pos + PCI_ACS_CTRL, &ctrl);
+
+	/* P2P Request & Completion Redirect */
+	ctrl &= ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC);
+
+	pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl);
+
+	pci_info(dev, "disabled ACS redirect\n");
+}
+
 /**
  * pci_std_enable_acs - enable ACS on devices using standard ACS capabilites
  * @dev: the PCI device
@@ -2859,12 +3121,22 @@ static void pci_std_enable_acs(struct pci_dev *dev)
 void pci_enable_acs(struct pci_dev *dev)
 {
 	if (!pci_acs_enable)
-		return;
+		goto disable_acs_redir;
 
 	if (!pci_dev_specific_enable_acs(dev))
-		return;
+		goto disable_acs_redir;
 
 	pci_std_enable_acs(dev);
+
+disable_acs_redir:
+	/*
+	 * Note: pci_disable_acs_redir() must be called even if ACS was not
+	 * enabled by the kernel because it may have been enabled by
+	 * platform firmware.  So if we are told to disable it, we should
+	 * always disable it after setting the kernel's default
+	 * preferences.
+	 */
+	pci_disable_acs_redir(dev);
 }
 
 static bool pci_acs_flags_enabled(struct pci_dev *pdev, u16 acs_flags)
@@ -3070,7 +3342,7 @@ int pci_rebar_get_current_size(struct pci_dev *pdev, int bar)
 		return pos;
 
 	pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl);
-	return (ctrl & PCI_REBAR_CTRL_BAR_SIZE) >> 8;
+	return (ctrl & PCI_REBAR_CTRL_BAR_SIZE) >> PCI_REBAR_CTRL_BAR_SHIFT;
 }
 
 /**
@@ -3093,7 +3365,7 @@ int pci_rebar_set_size(struct pci_dev *pdev, int bar, int size)
 
 	pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl);
 	ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE;
-	ctrl |= size << 8;
+	ctrl |= size << PCI_REBAR_CTRL_BAR_SHIFT;
 	pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl);
 	return 0;
 }
@@ -4077,7 +4349,7 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout)
  * Returns true if the device advertises support for PCIe function level
  * resets.
  */
-static bool pcie_has_flr(struct pci_dev *dev)
+bool pcie_has_flr(struct pci_dev *dev)
 {
 	u32 cap;
 
@@ -4087,6 +4359,7 @@ static bool pcie_has_flr(struct pci_dev *dev)
 	pcie_capability_read_dword(dev, PCI_EXP_DEVCAP, &cap);
 	return cap & PCI_EXP_DEVCAP_FLR;
 }
+EXPORT_SYMBOL_GPL(pcie_has_flr);
 
 /**
  * pcie_flr - initiate a PCIe function level reset
@@ -4262,19 +4535,18 @@ void __weak pcibios_reset_secondary_bus(struct pci_dev *dev)
 }
 
 /**
- * pci_reset_bridge_secondary_bus - Reset the secondary bus on a PCI bridge.
+ * pci_bridge_secondary_bus_reset - Reset the secondary bus on a PCI bridge.
  * @dev: Bridge device
  *
  * Use the bridge control register to assert reset on the secondary bus.
  * Devices on the secondary bus are left in power-on state.
  */
-int pci_reset_bridge_secondary_bus(struct pci_dev *dev)
+int pci_bridge_secondary_bus_reset(struct pci_dev *dev)
 {
 	pcibios_reset_secondary_bus(dev);
 
 	return pci_dev_wait(dev, "bus reset", PCIE_RESET_READY_POLL_MS);
 }
-EXPORT_SYMBOL_GPL(pci_reset_bridge_secondary_bus);
 
 static int pci_parent_bus_reset(struct pci_dev *dev, int probe)
 {
@@ -4291,9 +4563,7 @@ static int pci_parent_bus_reset(struct pci_dev *dev, int probe)
 	if (probe)
 		return 0;
 
-	pci_reset_bridge_secondary_bus(dev->bus->self);
-
-	return 0;
+	return pci_bridge_secondary_bus_reset(dev->bus->self);
 }
 
 static int pci_reset_hotplug_slot(struct hotplug_slot *hotplug, int probe)
@@ -4825,7 +5095,7 @@ int pci_probe_reset_slot(struct pci_slot *slot)
 EXPORT_SYMBOL_GPL(pci_probe_reset_slot);
 
 /**
- * pci_reset_slot - reset a PCI slot
+ * __pci_reset_slot - Try to reset a PCI slot
  * @slot: PCI slot to reset
  *
  * A PCI bus may host multiple slots, each slot may support a reset mechanism
@@ -4837,33 +5107,9 @@ EXPORT_SYMBOL_GPL(pci_probe_reset_slot);
  * through this function.  PCI config space of all devices in the slot and
  * behind the slot is saved before and restored after reset.
  *
- * Return 0 on success, non-zero on error.
- */
-int pci_reset_slot(struct pci_slot *slot)
-{
-	int rc;
-
-	rc = pci_slot_reset(slot, 1);
-	if (rc)
-		return rc;
-
-	pci_slot_save_and_disable(slot);
-
-	rc = pci_slot_reset(slot, 0);
-
-	pci_slot_restore(slot);
-
-	return rc;
-}
-EXPORT_SYMBOL_GPL(pci_reset_slot);
-
-/**
- * pci_try_reset_slot - Try to reset a PCI slot
- * @slot: PCI slot to reset
- *
  * Same as above except return -EAGAIN if the slot cannot be locked
  */
-int pci_try_reset_slot(struct pci_slot *slot)
+static int __pci_reset_slot(struct pci_slot *slot)
 {
 	int rc;
 
@@ -4884,10 +5130,11 @@ int pci_try_reset_slot(struct pci_slot *slot)
 
 	return rc;
 }
-EXPORT_SYMBOL_GPL(pci_try_reset_slot);
 
 static int pci_bus_reset(struct pci_bus *bus, int probe)
 {
+	int ret;
+
 	if (!bus->self || !pci_bus_resetable(bus))
 		return -ENOTTY;
 
@@ -4898,11 +5145,11 @@ static int pci_bus_reset(struct pci_bus *bus, int probe)
 
 	might_sleep();
 
-	pci_reset_bridge_secondary_bus(bus->self);
+	ret = pci_bridge_secondary_bus_reset(bus->self);
 
 	pci_bus_unlock(bus);
 
-	return 0;
+	return ret;
 }
 
 /**
@@ -4918,15 +5165,12 @@ int pci_probe_reset_bus(struct pci_bus *bus)
 EXPORT_SYMBOL_GPL(pci_probe_reset_bus);
 
 /**
- * pci_reset_bus - reset a PCI bus
+ * __pci_reset_bus - Try to reset a PCI bus
  * @bus: top level PCI bus to reset
  *
- * Do a bus reset on the given bus and any subordinate buses, saving
- * and restoring state of all devices.
- *
- * Return 0 on success, non-zero on error.
+ * Same as above except return -EAGAIN if the bus cannot be locked
  */
-int pci_reset_bus(struct pci_bus *bus)
+static int __pci_reset_bus(struct pci_bus *bus)
 {
 	int rc;
 
@@ -4936,42 +5180,30 @@ int pci_reset_bus(struct pci_bus *bus)
 
 	pci_bus_save_and_disable(bus);
 
-	rc = pci_bus_reset(bus, 0);
+	if (pci_bus_trylock(bus)) {
+		might_sleep();
+		rc = pci_bridge_secondary_bus_reset(bus->self);
+		pci_bus_unlock(bus);
+	} else
+		rc = -EAGAIN;
 
 	pci_bus_restore(bus);
 
 	return rc;
 }
-EXPORT_SYMBOL_GPL(pci_reset_bus);
 
 /**
- * pci_try_reset_bus - Try to reset a PCI bus
- * @bus: top level PCI bus to reset
+ * pci_reset_bus - Try to reset a PCI bus
+ * @pdev: top level PCI device to reset via slot/bus
  *
  * Same as above except return -EAGAIN if the bus cannot be locked
  */
-int pci_try_reset_bus(struct pci_bus *bus)
+int pci_reset_bus(struct pci_dev *pdev)
 {
-	int rc;
-
-	rc = pci_bus_reset(bus, 1);
-	if (rc)
-		return rc;
-
-	pci_bus_save_and_disable(bus);
-
-	if (pci_bus_trylock(bus)) {
-		might_sleep();
-		pci_reset_bridge_secondary_bus(bus->self);
-		pci_bus_unlock(bus);
-	} else
-		rc = -EAGAIN;
-
-	pci_bus_restore(bus);
-
-	return rc;
+	return pci_probe_reset_slot(pdev->slot) ?
+	    __pci_reset_slot(pdev->slot) : __pci_reset_bus(pdev->bus);
 }
-EXPORT_SYMBOL_GPL(pci_try_reset_bus);
+EXPORT_SYMBOL_GPL(pci_reset_bus);
 
 /**
  * pcix_get_max_mmrbc - get PCI-X maximum designed memory read byte count
@@ -5260,6 +5492,7 @@ enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev)
 
 	return PCI_SPEED_UNKNOWN;
 }
+EXPORT_SYMBOL(pcie_get_speed_cap);
 
 /**
  * pcie_get_width_cap - query for the PCI device's link width capability
@@ -5278,6 +5511,7 @@ enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev)
 
 	return PCIE_LNK_WIDTH_UNKNOWN;
 }
+EXPORT_SYMBOL(pcie_get_width_cap);
 
 /**
  * pcie_bandwidth_capable - calculate a PCI device's link bandwidth capability
@@ -5302,14 +5536,16 @@ u32 pcie_bandwidth_capable(struct pci_dev *dev, enum pci_bus_speed *speed,
 }
 
 /**
- * pcie_print_link_status - Report the PCI device's link speed and width
+ * __pcie_print_link_status - Report the PCI device's link speed and width
  * @dev: PCI device to query
+ * @verbose: Print info even when enough bandwidth is available
  *
- * Report the available bandwidth at the device.  If this is less than the
- * device is capable of, report the device's maximum possible bandwidth and
- * the upstream link that limits its performance to less than that.
+ * If the available bandwidth at the device is less than the device is
+ * capable of, report the device's maximum possible bandwidth and the
+ * upstream link that limits its performance.  If @verbose, always print
+ * the available bandwidth, even if the device isn't constrained.
  */
-void pcie_print_link_status(struct pci_dev *dev)
+void __pcie_print_link_status(struct pci_dev *dev, bool verbose)
 {
 	enum pcie_link_width width, width_cap;
 	enum pci_bus_speed speed, speed_cap;
@@ -5319,11 +5555,11 @@ void pcie_print_link_status(struct pci_dev *dev)
 	bw_cap = pcie_bandwidth_capable(dev, &speed_cap, &width_cap);
 	bw_avail = pcie_bandwidth_available(dev, &limiting_dev, &speed, &width);
 
-	if (bw_avail >= bw_cap)
+	if (bw_avail >= bw_cap && verbose)
 		pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth (%s x%d link)\n",
 			 bw_cap / 1000, bw_cap % 1000,
 			 PCIE_SPEED2STR(speed_cap), width_cap);
-	else
+	else if (bw_avail < bw_cap)
 		pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth, limited by %s x%d link at %s (capable of %u.%03u Gb/s with %s x%d link)\n",
 			 bw_avail / 1000, bw_avail % 1000,
 			 PCIE_SPEED2STR(speed), width,
@@ -5331,6 +5567,17 @@ void pcie_print_link_status(struct pci_dev *dev)
 			 bw_cap / 1000, bw_cap % 1000,
 			 PCIE_SPEED2STR(speed_cap), width_cap);
 }
+
+/**
+ * pcie_print_link_status - Report the PCI device's link speed and width
+ * @dev: PCI device to query
+ *
+ * Report the available bandwidth at the device.
+ */
+void pcie_print_link_status(struct pci_dev *dev)
+{
+	__pcie_print_link_status(dev, true);
+}
 EXPORT_SYMBOL(pcie_print_link_status);
 
 /**
@@ -5425,8 +5672,19 @@ int pci_set_vga_state(struct pci_dev *dev, bool decode,
  * @dev: the PCI device for which alias is added
  * @devfn: alias slot and function
  *
- * This helper encodes 8-bit devfn as bit number in dma_alias_mask.
- * It should be called early, preferably as PCI fixup header quirk.
+ * This helper encodes an 8-bit devfn as a bit number in dma_alias_mask
+ * which is used to program permissible bus-devfn source addresses for DMA
+ * requests in an IOMMU.  These aliases factor into IOMMU group creation
+ * and are useful for devices generating DMA requests beyond or different
+ * from their logical bus-devfn.  Examples include device quirks where the
+ * device simply uses the wrong devfn, as well as non-transparent bridges
+ * where the alias may be a proxy for devices in another domain.
+ *
+ * IOMMU group creation is performed during device discovery or addition,
+ * prior to any potential DMA mapping and therefore prior to driver probing
+ * (especially for userspace assigned devices where IOMMU group definition
+ * cannot be left as a userspace activity).  DMA aliases should therefore
+ * be configured via quirks, such as the PCI fixup header quirk.
  */
 void pci_add_dma_alias(struct pci_dev *dev, u8 devfn)
 {
@@ -5492,10 +5750,10 @@ static DEFINE_SPINLOCK(resource_alignment_lock);
 static resource_size_t pci_specified_resource_alignment(struct pci_dev *dev,
 							bool *resize)
 {
-	int seg, bus, slot, func, align_order, count;
-	unsigned short vendor, device, subsystem_vendor, subsystem_device;
+	int align_order, count;
 	resource_size_t align = pcibios_default_alignment();
-	char *p;
+	const char *p;
+	int ret;
 
 	spin_lock(&resource_alignment_lock);
 	p = resource_alignment_param;
@@ -5515,58 +5773,21 @@ static resource_size_t pci_specified_resource_alignment(struct pci_dev *dev,
 		} else {
 			align_order = -1;
 		}
-		if (strncmp(p, "pci:", 4) == 0) {
-			/* PCI vendor/device (subvendor/subdevice) ids are specified */
-			p += 4;
-			if (sscanf(p, "%hx:%hx:%hx:%hx%n",
-				&vendor, &device, &subsystem_vendor, &subsystem_device, &count) != 4) {
-				if (sscanf(p, "%hx:%hx%n", &vendor, &device, &count) != 2) {
-					printk(KERN_ERR "PCI: Can't parse resource_alignment parameter: pci:%s\n",
-						p);
-					break;
-				}
-				subsystem_vendor = subsystem_device = 0;
-			}
-			p += count;
-			if ((!vendor || (vendor == dev->vendor)) &&
-				(!device || (device == dev->device)) &&
-				(!subsystem_vendor || (subsystem_vendor == dev->subsystem_vendor)) &&
-				(!subsystem_device || (subsystem_device == dev->subsystem_device))) {
-				*resize = true;
-				if (align_order == -1)
-					align = PAGE_SIZE;
-				else
-					align = 1 << align_order;
-				/* Found */
-				break;
-			}
-		}
-		else {
-			if (sscanf(p, "%x:%x:%x.%x%n",
-				&seg, &bus, &slot, &func, &count) != 4) {
-				seg = 0;
-				if (sscanf(p, "%x:%x.%x%n",
-						&bus, &slot, &func, &count) != 3) {
-					/* Invalid format */
-					printk(KERN_ERR "PCI: Can't parse resource_alignment parameter: %s\n",
-						p);
-					break;
-				}
-			}
-			p += count;
-			if (seg == pci_domain_nr(dev->bus) &&
-				bus == dev->bus->number &&
-				slot == PCI_SLOT(dev->devfn) &&
-				func == PCI_FUNC(dev->devfn)) {
-				*resize = true;
-				if (align_order == -1)
-					align = PAGE_SIZE;
-				else
-					align = 1 << align_order;
-				/* Found */
-				break;
-			}
+
+		ret = pci_dev_str_match(dev, p, &p);
+		if (ret == 1) {
+			*resize = true;
+			if (align_order == -1)
+				align = PAGE_SIZE;
+			else
+				align = 1 << align_order;
+			break;
+		} else if (ret < 0) {
+			pr_err("PCI: Can't parse resource_alignment parameter: %s\n",
+			       p);
+			break;
 		}
+
 		if (*p != ';' && *p != ',') {
 			/* End of param or invalid format */
 			break;
@@ -5843,6 +6064,8 @@ static int __init pci_setup(char *str)
 				pcie_ats_disabled = true;
 			} else if (!strcmp(str, "noaer")) {
 				pci_no_aer();
+			} else if (!strcmp(str, "earlydump")) {
+				pci_early_dump = true;
 			} else if (!strncmp(str, "realloc=", 8)) {
 				pci_realloc_get_opt(str + 8);
 			} else if (!strncmp(str, "realloc", 7)) {
@@ -5879,6 +6102,8 @@ static int __init pci_setup(char *str)
 				pcie_bus_config = PCIE_BUS_PEER2PEER;
 			} else if (!strncmp(str, "pcie_scan_all", 13)) {
 				pci_add_flags(PCI_SCAN_ALL_PCIE_DEVS);
+			} else if (!strncmp(str, "disable_acs_redir=", 18)) {
+				disable_acs_redir_param = str + 18;
 			} else {
 				printk(KERN_ERR "PCI: Unknown option `%s'\n",
 						str);
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 08817253c8a2..6e0d1528d471 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -7,6 +7,7 @@
 #define PCI_VSEC_ID_INTEL_TBT	0x1234	/* Thunderbolt */
 
 extern const unsigned char pcie_link_speed[];
+extern bool pci_early_dump;
 
 bool pcie_cap_has_lnkctl(const struct pci_dev *dev);
 
@@ -33,6 +34,7 @@ int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vmai,
 		  enum pci_mmap_api mmap_api);
 
 int pci_probe_reset_function(struct pci_dev *dev);
+int pci_bridge_secondary_bus_reset(struct pci_dev *dev);
 
 /**
  * struct pci_platform_pm_ops - Firmware PM callbacks
@@ -225,6 +227,10 @@ enum pci_bar_type {
 int pci_configure_extended_tags(struct pci_dev *dev, void *ign);
 bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl,
 				int crs_timeout);
+bool pci_bus_generic_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl,
+					int crs_timeout);
+int pci_idt_bus_quirk(struct pci_bus *bus, int devfn, u32 *pl, int crs_timeout);
+
 int pci_setup_device(struct pci_dev *dev);
 int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 		    struct resource *res, unsigned int reg);
@@ -259,6 +265,7 @@ enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev);
 enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev);
 u32 pcie_bandwidth_capable(struct pci_dev *dev, enum pci_bus_speed *speed,
 			   enum pcie_link_width *width);
+void __pcie_print_link_status(struct pci_dev *dev, bool verbose);
 
 /* Single Root I/O Virtualization */
 struct pci_sriov {
@@ -311,6 +318,34 @@ static inline bool pci_dev_is_added(const struct pci_dev *dev)
 	return test_bit(PCI_DEV_ADDED, &dev->priv_flags);
 }
 
+#ifdef CONFIG_PCIEAER
+#include <linux/aer.h>
+
+#define AER_MAX_MULTI_ERR_DEVICES	5	/* Not likely to have more */
+
+struct aer_err_info {
+	struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES];
+	int error_dev_num;
+
+	unsigned int id:16;
+
+	unsigned int severity:2;	/* 0:NONFATAL | 1:FATAL | 2:COR */
+	unsigned int __pad1:5;
+	unsigned int multi_error_valid:1;
+
+	unsigned int first_error:5;
+	unsigned int __pad2:2;
+	unsigned int tlp_header_valid:1;
+
+	unsigned int status;		/* COR/UNCOR Error Status */
+	unsigned int mask;		/* COR/UNCOR Error Mask */
+	struct aer_header_log_regs tlp;	/* TLP Header */
+};
+
+int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info);
+void aer_print_error(struct pci_dev *dev, struct aer_err_info *info);
+#endif	/* CONFIG_PCIEAER */
+
 #ifdef CONFIG_PCI_ATS
 void pci_restore_ats_state(struct pci_dev *dev);
 #else
@@ -367,6 +402,25 @@ static inline resource_size_t pci_resource_alignment(struct pci_dev *dev,
 }
 
 void pci_enable_acs(struct pci_dev *dev);
+#ifdef CONFIG_PCI_QUIRKS
+int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags);
+int pci_dev_specific_enable_acs(struct pci_dev *dev);
+int pci_dev_specific_disable_acs_redir(struct pci_dev *dev);
+#else
+static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev,
+					       u16 acs_flags)
+{
+	return -ENOTTY;
+}
+static inline int pci_dev_specific_enable_acs(struct pci_dev *dev)
+{
+	return -ENOTTY;
+}
+static inline int pci_dev_specific_disable_acs_redir(struct pci_dev *dev)
+{
+	return -ENOTTY;
+}
+#endif
 
 /* PCI error reporting and recovery */
 void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service);
@@ -467,4 +521,19 @@ static inline int devm_of_pci_get_host_bridge_resources(struct device *dev,
 }
 #endif
 
+#ifdef CONFIG_PCIEAER
+void pci_no_aer(void);
+void pci_aer_init(struct pci_dev *dev);
+void pci_aer_exit(struct pci_dev *dev);
+extern const struct attribute_group aer_stats_attr_group;
+void pci_aer_clear_fatal_status(struct pci_dev *dev);
+void pci_aer_clear_device_status(struct pci_dev *dev);
+#else
+static inline void pci_no_aer(void) { }
+static inline int pci_aer_init(struct pci_dev *d) { return -ENODEV; }
+static inline void pci_aer_exit(struct pci_dev *d) { }
+static inline void pci_aer_clear_fatal_status(struct pci_dev *dev) { }
+static inline void pci_aer_clear_device_status(struct pci_dev *dev) { }
+#endif
+
 #endif /* DRIVERS_PCI_H */
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index a2e88386af28..83180edd6ed4 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -31,26 +31,9 @@
 #include "portdrv.h"
 
 #define AER_ERROR_SOURCES_MAX		100
-#define AER_MAX_MULTI_ERR_DEVICES	5	/* Not likely to have more */
 
-struct aer_err_info {
-	struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES];
-	int error_dev_num;
-
-	unsigned int id:16;
-
-	unsigned int severity:2;	/* 0:NONFATAL | 1:FATAL | 2:COR */
-	unsigned int __pad1:5;
-	unsigned int multi_error_valid:1;
-
-	unsigned int first_error:5;
-	unsigned int __pad2:2;
-	unsigned int tlp_header_valid:1;
-
-	unsigned int status;		/* COR/UNCOR Error Status */
-	unsigned int mask;		/* COR/UNCOR Error Mask */
-	struct aer_header_log_regs tlp;	/* TLP Header */
-};
+#define AER_MAX_TYPEOF_COR_ERRS		16	/* as per PCI_ERR_COR_STATUS */
+#define AER_MAX_TYPEOF_UNCOR_ERRS	26	/* as per PCI_ERR_UNCOR_STATUS*/
 
 struct aer_err_source {
 	unsigned int status;
@@ -76,6 +59,42 @@ struct aer_rpc {
 					 */
 };
 
+/* AER stats for the device */
+struct aer_stats {
+
+	/*
+	 * Fields for all AER capable devices. They indicate the errors
+	 * "as seen by this device". Note that this may mean that if an
+	 * end point is causing problems, the AER counters may increment
+	 * at its link partner (e.g. root port) because the errors will be
+	 * "seen" by the link partner and not the the problematic end point
+	 * itself (which may report all counters as 0 as it never saw any
+	 * problems).
+	 */
+	/* Counters for different type of correctable errors */
+	u64 dev_cor_errs[AER_MAX_TYPEOF_COR_ERRS];
+	/* Counters for different type of fatal uncorrectable errors */
+	u64 dev_fatal_errs[AER_MAX_TYPEOF_UNCOR_ERRS];
+	/* Counters for different type of nonfatal uncorrectable errors */
+	u64 dev_nonfatal_errs[AER_MAX_TYPEOF_UNCOR_ERRS];
+	/* Total number of ERR_COR sent by this device */
+	u64 dev_total_cor_errs;
+	/* Total number of ERR_FATAL sent by this device */
+	u64 dev_total_fatal_errs;
+	/* Total number of ERR_NONFATAL sent by this device */
+	u64 dev_total_nonfatal_errs;
+
+	/*
+	 * Fields for Root ports & root complex event collectors only, these
+	 * indicate the total number of ERR_COR, ERR_FATAL, and ERR_NONFATAL
+	 * messages received by the root port / event collector, INCLUDING the
+	 * ones that are generated internally (by the rootport itself)
+	 */
+	u64 rootport_total_cor_errs;
+	u64 rootport_total_fatal_errs;
+	u64 rootport_total_nonfatal_errs;
+};
+
 #define AER_LOG_TLP_MASKS		(PCI_ERR_UNC_POISON_TLP|	\
 					PCI_ERR_UNC_ECRC|		\
 					PCI_ERR_UNC_UNSUP|		\
@@ -303,12 +322,13 @@ int pcie_aer_get_firmware_first(struct pci_dev *dev)
 	if (!pci_is_pcie(dev))
 		return 0;
 
+	if (pcie_ports_native)
+		return 0;
+
 	if (!dev->__aer_firmware_first_valid)
 		aer_set_firmware_first(dev);
 	return dev->__aer_firmware_first;
 }
-#define	PCI_EXP_AER_FLAGS	(PCI_EXP_DEVCTL_CERE | PCI_EXP_DEVCTL_NFERE | \
-				 PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE)
 
 static bool aer_firmware_first;
 
@@ -323,6 +343,9 @@ bool aer_acpi_firmware_first(void)
 		.firmware_first	= 0,
 	};
 
+	if (pcie_ports_native)
+		return false;
+
 	if (!parsed) {
 		apei_hest_parse(aer_hest_parse, &info);
 		aer_firmware_first = info.firmware_first;
@@ -357,16 +380,30 @@ int pci_disable_pcie_error_reporting(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_GPL(pci_disable_pcie_error_reporting);
 
+void pci_aer_clear_device_status(struct pci_dev *dev)
+{
+	u16 sta;
+
+	pcie_capability_read_word(dev, PCI_EXP_DEVSTA, &sta);
+	pcie_capability_write_word(dev, PCI_EXP_DEVSTA, sta);
+}
+
 int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
 {
 	int pos;
-	u32 status;
+	u32 status, sev;
 
 	pos = dev->aer_cap;
 	if (!pos)
 		return -EIO;
 
+	if (pcie_aer_get_firmware_first(dev))
+		return -EIO;
+
+	/* Clear status bits for ERR_NONFATAL errors only */
 	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &sev);
+	status &= ~sev;
 	if (status)
 		pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);
 
@@ -374,6 +411,26 @@ int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_GPL(pci_cleanup_aer_uncorrect_error_status);
 
+void pci_aer_clear_fatal_status(struct pci_dev *dev)
+{
+	int pos;
+	u32 status, sev;
+
+	pos = dev->aer_cap;
+	if (!pos)
+		return;
+
+	if (pcie_aer_get_firmware_first(dev))
+		return;
+
+	/* Clear status bits for ERR_FATAL errors only */
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &sev);
+	status &= sev;
+	if (status)
+		pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);
+}
+
 int pci_cleanup_aer_error_status_regs(struct pci_dev *dev)
 {
 	int pos;
@@ -387,6 +444,9 @@ int pci_cleanup_aer_error_status_regs(struct pci_dev *dev)
 	if (!pos)
 		return -EIO;
 
+	if (pcie_aer_get_firmware_first(dev))
+		return -EIO;
+
 	port_type = pci_pcie_type(dev);
 	if (port_type == PCI_EXP_TYPE_ROOT_PORT) {
 		pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, &status);
@@ -402,10 +462,20 @@ int pci_cleanup_aer_error_status_regs(struct pci_dev *dev)
 	return 0;
 }
 
-int pci_aer_init(struct pci_dev *dev)
+void pci_aer_init(struct pci_dev *dev)
 {
 	dev->aer_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
-	return pci_cleanup_aer_error_status_regs(dev);
+
+	if (dev->aer_cap)
+		dev->aer_stats = kzalloc(sizeof(struct aer_stats), GFP_KERNEL);
+
+	pci_cleanup_aer_error_status_regs(dev);
+}
+
+void pci_aer_exit(struct pci_dev *dev)
+{
+	kfree(dev->aer_stats);
+	dev->aer_stats = NULL;
 }
 
 #define AER_AGENT_RECEIVER		0
@@ -458,52 +528,52 @@ static const char *aer_error_layer[] = {
 	"Transaction Layer"
 };
 
-static const char *aer_correctable_error_string[] = {
-	"Receiver Error",		/* Bit Position 0	*/
+static const char *aer_correctable_error_string[AER_MAX_TYPEOF_COR_ERRS] = {
+	"RxErr",			/* Bit Position 0	*/
 	NULL,
 	NULL,
 	NULL,
 	NULL,
 	NULL,
-	"Bad TLP",			/* Bit Position 6	*/
-	"Bad DLLP",			/* Bit Position 7	*/
-	"RELAY_NUM Rollover",		/* Bit Position 8	*/
+	"BadTLP",			/* Bit Position 6	*/
+	"BadDLLP",			/* Bit Position 7	*/
+	"Rollover",			/* Bit Position 8	*/
 	NULL,
 	NULL,
 	NULL,
-	"Replay Timer Timeout",		/* Bit Position 12	*/
-	"Advisory Non-Fatal",		/* Bit Position 13	*/
-	"Corrected Internal Error",	/* Bit Position 14	*/
-	"Header Log Overflow",		/* Bit Position 15	*/
+	"Timeout",			/* Bit Position 12	*/
+	"NonFatalErr",			/* Bit Position 13	*/
+	"CorrIntErr",			/* Bit Position 14	*/
+	"HeaderOF",			/* Bit Position 15	*/
 };
 
-static const char *aer_uncorrectable_error_string[] = {
+static const char *aer_uncorrectable_error_string[AER_MAX_TYPEOF_UNCOR_ERRS] = {
 	"Undefined",			/* Bit Position 0	*/
 	NULL,
 	NULL,
 	NULL,
-	"Data Link Protocol",		/* Bit Position 4	*/
-	"Surprise Down Error",		/* Bit Position 5	*/
+	"DLP",				/* Bit Position 4	*/
+	"SDES",				/* Bit Position 5	*/
 	NULL,
 	NULL,
 	NULL,
 	NULL,
 	NULL,
 	NULL,
-	"Poisoned TLP",			/* Bit Position 12	*/
-	"Flow Control Protocol",	/* Bit Position 13	*/
-	"Completion Timeout",		/* Bit Position 14	*/
-	"Completer Abort",		/* Bit Position 15	*/
-	"Unexpected Completion",	/* Bit Position 16	*/
-	"Receiver Overflow",		/* Bit Position 17	*/
-	"Malformed TLP",		/* Bit Position 18	*/
+	"TLP",				/* Bit Position 12	*/
+	"FCP",				/* Bit Position 13	*/
+	"CmpltTO",			/* Bit Position 14	*/
+	"CmpltAbrt",			/* Bit Position 15	*/
+	"UnxCmplt",			/* Bit Position 16	*/
+	"RxOF",				/* Bit Position 17	*/
+	"MalfTLP",			/* Bit Position 18	*/
 	"ECRC",				/* Bit Position 19	*/
-	"Unsupported Request",		/* Bit Position 20	*/
-	"ACS Violation",		/* Bit Position 21	*/
-	"Uncorrectable Internal Error",	/* Bit Position 22	*/
-	"MC Blocked TLP",		/* Bit Position 23	*/
-	"AtomicOp Egress Blocked",	/* Bit Position 24	*/
-	"TLP Prefix Blocked Error",	/* Bit Position 25	*/
+	"UnsupReq",			/* Bit Position 20	*/
+	"ACSViol",			/* Bit Position 21	*/
+	"UncorrIntErr",			/* Bit Position 22	*/
+	"BlockedTLP",			/* Bit Position 23	*/
+	"AtomicOpBlocked",		/* Bit Position 24	*/
+	"TLPBlockedErr",		/* Bit Position 25	*/
 };
 
 static const char *aer_agent_string[] = {
@@ -513,6 +583,144 @@ static const char *aer_agent_string[] = {
 	"Transmitter ID"
 };
 
+#define aer_stats_dev_attr(name, stats_array, strings_array,		\
+			   total_string, total_field)			\
+	static ssize_t							\
+	name##_show(struct device *dev, struct device_attribute *attr,	\
+		     char *buf)						\
+{									\
+	unsigned int i;							\
+	char *str = buf;						\
+	struct pci_dev *pdev = to_pci_dev(dev);				\
+	u64 *stats = pdev->aer_stats->stats_array;			\
+									\
+	for (i = 0; i < ARRAY_SIZE(strings_array); i++) {		\
+		if (strings_array[i])					\
+			str += sprintf(str, "%s %llu\n",		\
+				       strings_array[i], stats[i]);	\
+		else if (stats[i])					\
+			str += sprintf(str, #stats_array "_bit[%d] %llu\n",\
+				       i, stats[i]);			\
+	}								\
+	str += sprintf(str, "TOTAL_%s %llu\n", total_string,		\
+		       pdev->aer_stats->total_field);			\
+	return str-buf;							\
+}									\
+static DEVICE_ATTR_RO(name)
+
+aer_stats_dev_attr(aer_dev_correctable, dev_cor_errs,
+		   aer_correctable_error_string, "ERR_COR",
+		   dev_total_cor_errs);
+aer_stats_dev_attr(aer_dev_fatal, dev_fatal_errs,
+		   aer_uncorrectable_error_string, "ERR_FATAL",
+		   dev_total_fatal_errs);
+aer_stats_dev_attr(aer_dev_nonfatal, dev_nonfatal_errs,
+		   aer_uncorrectable_error_string, "ERR_NONFATAL",
+		   dev_total_nonfatal_errs);
+
+#define aer_stats_rootport_attr(name, field)				\
+	static ssize_t							\
+	name##_show(struct device *dev, struct device_attribute *attr,	\
+		     char *buf)						\
+{									\
+	struct pci_dev *pdev = to_pci_dev(dev);				\
+	return sprintf(buf, "%llu\n", pdev->aer_stats->field);		\
+}									\
+static DEVICE_ATTR_RO(name)
+
+aer_stats_rootport_attr(aer_rootport_total_err_cor,
+			 rootport_total_cor_errs);
+aer_stats_rootport_attr(aer_rootport_total_err_fatal,
+			 rootport_total_fatal_errs);
+aer_stats_rootport_attr(aer_rootport_total_err_nonfatal,
+			 rootport_total_nonfatal_errs);
+
+static struct attribute *aer_stats_attrs[] __ro_after_init = {
+	&dev_attr_aer_dev_correctable.attr,
+	&dev_attr_aer_dev_fatal.attr,
+	&dev_attr_aer_dev_nonfatal.attr,
+	&dev_attr_aer_rootport_total_err_cor.attr,
+	&dev_attr_aer_rootport_total_err_fatal.attr,
+	&dev_attr_aer_rootport_total_err_nonfatal.attr,
+	NULL
+};
+
+static umode_t aer_stats_attrs_are_visible(struct kobject *kobj,
+					   struct attribute *a, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	if (!pdev->aer_stats)
+		return 0;
+
+	if ((a == &dev_attr_aer_rootport_total_err_cor.attr ||
+	     a == &dev_attr_aer_rootport_total_err_fatal.attr ||
+	     a == &dev_attr_aer_rootport_total_err_nonfatal.attr) &&
+	    pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT)
+		return 0;
+
+	return a->mode;
+}
+
+const struct attribute_group aer_stats_attr_group = {
+	.attrs  = aer_stats_attrs,
+	.is_visible = aer_stats_attrs_are_visible,
+};
+
+static void pci_dev_aer_stats_incr(struct pci_dev *pdev,
+				   struct aer_err_info *info)
+{
+	int status, i, max = -1;
+	u64 *counter = NULL;
+	struct aer_stats *aer_stats = pdev->aer_stats;
+
+	if (!aer_stats)
+		return;
+
+	switch (info->severity) {
+	case AER_CORRECTABLE:
+		aer_stats->dev_total_cor_errs++;
+		counter = &aer_stats->dev_cor_errs[0];
+		max = AER_MAX_TYPEOF_COR_ERRS;
+		break;
+	case AER_NONFATAL:
+		aer_stats->dev_total_nonfatal_errs++;
+		counter = &aer_stats->dev_nonfatal_errs[0];
+		max = AER_MAX_TYPEOF_UNCOR_ERRS;
+		break;
+	case AER_FATAL:
+		aer_stats->dev_total_fatal_errs++;
+		counter = &aer_stats->dev_fatal_errs[0];
+		max = AER_MAX_TYPEOF_UNCOR_ERRS;
+		break;
+	}
+
+	status = (info->status & ~info->mask);
+	for (i = 0; i < max; i++)
+		if (status & (1 << i))
+			counter[i]++;
+}
+
+static void pci_rootport_aer_stats_incr(struct pci_dev *pdev,
+				 struct aer_err_source *e_src)
+{
+	struct aer_stats *aer_stats = pdev->aer_stats;
+
+	if (!aer_stats)
+		return;
+
+	if (e_src->status & PCI_ERR_ROOT_COR_RCV)
+		aer_stats->rootport_total_cor_errs++;
+
+	if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) {
+		if (e_src->status & PCI_ERR_ROOT_FATAL_RCV)
+			aer_stats->rootport_total_fatal_errs++;
+		else
+			aer_stats->rootport_total_nonfatal_errs++;
+	}
+}
+
 static void __print_tlp_header(struct pci_dev *dev,
 			       struct aer_header_log_regs *t)
 {
@@ -545,9 +753,10 @@ static void __aer_print_error(struct pci_dev *dev,
 			pci_err(dev, "   [%2d] Unknown Error Bit%s\n",
 				i, info->first_error == i ? " (First)" : "");
 	}
+	pci_dev_aer_stats_incr(dev, info);
 }
 
-static void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
+void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 {
 	int layer, agent;
 	int id = ((dev->bus->number << 8) | dev->devfn);
@@ -799,6 +1008,7 @@ static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info)
 		if (pos)
 			pci_write_config_dword(dev, pos + PCI_ERR_COR_STATUS,
 					info->status);
+		pci_aer_clear_device_status(dev);
 	} else if (info->severity == AER_NONFATAL)
 		pcie_do_nonfatal_recovery(dev);
 	else if (info->severity == AER_FATAL)
@@ -876,7 +1086,7 @@ EXPORT_SYMBOL_GPL(aer_recover_queue);
 #endif
 
 /**
- * get_device_error_info - read error status from dev and store it to info
+ * aer_get_device_error_info - read error status from dev and store it to info
  * @dev: pointer to the device expected to have a error record
  * @info: pointer to structure to store the error record
  *
@@ -884,7 +1094,7 @@ EXPORT_SYMBOL_GPL(aer_recover_queue);
  *
  * Note that @info is reused among all error devices. Clear fields properly.
  */
-static int get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
+int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
 {
 	int pos, temp;
 
@@ -942,11 +1152,11 @@ static inline void aer_process_err_devices(struct aer_err_info *e_info)
 
 	/* Report all before handle them, not to lost records by reset etc. */
 	for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
-		if (get_device_error_info(e_info->dev[i], e_info))
+		if (aer_get_device_error_info(e_info->dev[i], e_info))
 			aer_print_error(e_info->dev[i], e_info);
 	}
 	for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
-		if (get_device_error_info(e_info->dev[i], e_info))
+		if (aer_get_device_error_info(e_info->dev[i], e_info))
 			handle_error_source(e_info->dev[i], e_info);
 	}
 }
@@ -962,6 +1172,8 @@ static void aer_isr_one_error(struct aer_rpc *rpc,
 	struct pci_dev *pdev = rpc->rpd;
 	struct aer_err_info *e_info = &rpc->e_info;
 
+	pci_rootport_aer_stats_incr(pdev, e_src);
+
 	/*
 	 * There is a possibility that both correctable error and
 	 * uncorrectable error being logged. Report correctable error first.
@@ -1305,6 +1517,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
 {
 	u32 reg32;
 	int pos;
+	int rc;
 
 	pos = dev->aer_cap;
 
@@ -1313,7 +1526,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
 	reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK;
 	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32);
 
-	pci_reset_bridge_secondary_bus(dev);
+	rc = pci_bridge_secondary_bus_reset(dev);
 	pci_printk(KERN_DEBUG, dev, "Root Port link has been reset\n");
 
 	/* Clear Root Error Status */
@@ -1325,7 +1538,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
 	reg32 |= ROOT_PORT_INTR_ON_MESG_MASK;
 	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32);
 
-	return PCI_ERS_RESULT_RECOVERED;
+	return rc ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
 }
 
 /**
@@ -1336,20 +1549,8 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
  */
 static void aer_error_resume(struct pci_dev *dev)
 {
-	int pos;
-	u32 status, mask;
-	u16 reg16;
-
-	/* Clean up Root device status */
-	pcie_capability_read_word(dev, PCI_EXP_DEVSTA, &reg16);
-	pcie_capability_write_word(dev, PCI_EXP_DEVSTA, reg16);
-
-	/* Clean AER Root Error Status */
-	pos = dev->aer_cap;
-	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
-	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &mask);
-	status &= ~mask; /* Clear corresponding nonfatal bits */
-	pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);
+	pci_aer_clear_device_status(dev);
+	pci_cleanup_aer_uncorrect_error_status(dev);
 }
 
 static struct pcie_port_service_driver aerdriver = {
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index c687c817b47d..5326916715d2 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -1127,11 +1127,9 @@ static int pcie_aspm_set_policy(const char *val,
 
 	if (aspm_disabled)
 		return -EPERM;
-	for (i = 0; i < ARRAY_SIZE(policy_str); i++)
-		if (!strncmp(val, policy_str[i], strlen(policy_str[i])))
-			break;
-	if (i >= ARRAY_SIZE(policy_str))
-		return -EINVAL;
+	i = sysfs_match_string(policy_str, val);
+	if (i < 0)
+		return i;
 	if (i == aspm_policy)
 		return 0;
 
diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
index 921ed979109d..f03279fc87cd 100644
--- a/drivers/pci/pcie/dpc.c
+++ b/drivers/pci/pcie/dpc.c
@@ -6,6 +6,7 @@
  * Copyright (C) 2016 Intel Corp.
  */
 
+#include <linux/aer.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
@@ -16,10 +17,8 @@
 
 struct dpc_dev {
 	struct pcie_device	*dev;
-	struct work_struct	work;
 	u16			cap_pos;
 	bool			rp_extensions;
-	u32			rp_pio_status;
 	u8			rp_log_size;
 };
 
@@ -65,19 +64,13 @@ static int dpc_wait_rp_inactive(struct dpc_dev *dpc)
 	return 0;
 }
 
-static void dpc_wait_link_inactive(struct dpc_dev *dpc)
-{
-	struct pci_dev *pdev = dpc->dev->port;
-
-	pcie_wait_for_link(pdev, false);
-}
-
 static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev)
 {
 	struct dpc_dev *dpc;
 	struct pcie_device *pciedev;
 	struct device *devdpc;
-	u16 cap, ctl;
+
+	u16 cap;
 
 	/*
 	 * DPC disables the Link automatically in hardware, so it has
@@ -92,34 +85,17 @@ static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev)
 	 * Wait until the Link is inactive, then clear DPC Trigger Status
 	 * to allow the Port to leave DPC.
 	 */
-	dpc_wait_link_inactive(dpc);
+	pcie_wait_for_link(pdev, false);
 
 	if (dpc->rp_extensions && dpc_wait_rp_inactive(dpc))
 		return PCI_ERS_RESULT_DISCONNECT;
-	if (dpc->rp_extensions && dpc->rp_pio_status) {
-		pci_write_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_STATUS,
-				       dpc->rp_pio_status);
-		dpc->rp_pio_status = 0;
-	}
 
 	pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS,
 			      PCI_EXP_DPC_STATUS_TRIGGER);
 
-	pci_read_config_word(pdev, cap + PCI_EXP_DPC_CTL, &ctl);
-	pci_write_config_word(pdev, cap + PCI_EXP_DPC_CTL,
-			      ctl | PCI_EXP_DPC_CTL_INT_EN);
-
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
-static void dpc_work(struct work_struct *work)
-{
-	struct dpc_dev *dpc = container_of(work, struct dpc_dev, work);
-	struct pci_dev *pdev = dpc->dev->port;
-
-	/* We configure DPC so it only triggers on ERR_FATAL */
-	pcie_do_fatal_recovery(pdev, PCIE_PORT_SERVICE_DPC);
-}
 
 static void dpc_process_rp_pio_error(struct dpc_dev *dpc)
 {
@@ -134,8 +110,6 @@ static void dpc_process_rp_pio_error(struct dpc_dev *dpc)
 	dev_err(dev, "rp_pio_status: %#010x, rp_pio_mask: %#010x\n",
 		status, mask);
 
-	dpc->rp_pio_status = status;
-
 	pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_SEVERITY, &sev);
 	pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_SYSERROR, &syserr);
 	pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_EXCEPTION, &exc);
@@ -146,15 +120,14 @@ static void dpc_process_rp_pio_error(struct dpc_dev *dpc)
 	pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &dpc_status);
 	first_error = (dpc_status & 0x1f00) >> 8;
 
-	status &= ~mask;
 	for (i = 0; i < ARRAY_SIZE(rp_pio_error_string); i++) {
-		if (status & (1 << i))
+		if ((status & ~mask) & (1 << i))
 			dev_err(dev, "[%2d] %s%s\n", i, rp_pio_error_string[i],
 				first_error == i ? " (First)" : "");
 	}
 
 	if (dpc->rp_log_size < 4)
-		return;
+		goto clear_status;
 	pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_HEADER_LOG,
 			      &dw0);
 	pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_HEADER_LOG + 4,
@@ -167,7 +140,7 @@ static void dpc_process_rp_pio_error(struct dpc_dev *dpc)
 		dw0, dw1, dw2, dw3);
 
 	if (dpc->rp_log_size < 5)
-		return;
+		goto clear_status;
 	pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_IMPSPEC_LOG, &log);
 	dev_err(dev, "RP PIO ImpSpec Log %#010x\n", log);
 
@@ -176,43 +149,26 @@ static void dpc_process_rp_pio_error(struct dpc_dev *dpc)
 			cap + PCI_EXP_DPC_RP_PIO_TLPPREFIX_LOG, &prefix);
 		dev_err(dev, "TLP Prefix Header: dw%d, %#010x\n", i, prefix);
 	}
+ clear_status:
+	pci_write_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_STATUS, status);
 }
 
-static irqreturn_t dpc_irq(int irq, void *context)
+static irqreturn_t dpc_handler(int irq, void *context)
 {
-	struct dpc_dev *dpc = (struct dpc_dev *)context;
+	struct aer_err_info info;
+	struct dpc_dev *dpc = context;
 	struct pci_dev *pdev = dpc->dev->port;
 	struct device *dev = &dpc->dev->device;
-	u16 cap = dpc->cap_pos, ctl, status, source, reason, ext_reason;
-
-	pci_read_config_word(pdev, cap + PCI_EXP_DPC_CTL, &ctl);
-
-	if (!(ctl & PCI_EXP_DPC_CTL_INT_EN) || ctl == (u16)(~0))
-		return IRQ_NONE;
+	u16 cap = dpc->cap_pos, status, source, reason, ext_reason;
 
 	pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status);
-
-	if (!(status & PCI_EXP_DPC_STATUS_INTERRUPT))
-		return IRQ_NONE;
-
-	if (!(status & PCI_EXP_DPC_STATUS_TRIGGER)) {
-		pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS,
-				      PCI_EXP_DPC_STATUS_INTERRUPT);
-		return IRQ_HANDLED;
-	}
-
-	pci_write_config_word(pdev, cap + PCI_EXP_DPC_CTL,
-			      ctl & ~PCI_EXP_DPC_CTL_INT_EN);
-
-	pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID,
-			     &source);
+	pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID, &source);
 
 	dev_info(dev, "DPC containment event, status:%#06x source:%#06x\n",
-		status, source);
+		 status, source);
 
 	reason = (status & PCI_EXP_DPC_STATUS_TRIGGER_RSN) >> 1;
 	ext_reason = (status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT) >> 5;
-
 	dev_warn(dev, "DPC %s detected, remove downstream devices\n",
 		 (reason == 0) ? "unmasked uncorrectable error" :
 		 (reason == 1) ? "ERR_NONFATAL" :
@@ -220,15 +176,36 @@ static irqreturn_t dpc_irq(int irq, void *context)
 		 (ext_reason == 0) ? "RP PIO error" :
 		 (ext_reason == 1) ? "software trigger" :
 				     "reserved error");
+
 	/* show RP PIO error detail information */
 	if (dpc->rp_extensions && reason == 3 && ext_reason == 0)
 		dpc_process_rp_pio_error(dpc);
+	else if (reason == 0 && aer_get_device_error_info(pdev, &info)) {
+		aer_print_error(pdev, &info);
+		pci_cleanup_aer_uncorrect_error_status(pdev);
+	}
 
-	pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS,
-			      PCI_EXP_DPC_STATUS_INTERRUPT);
+	/* We configure DPC so it only triggers on ERR_FATAL */
+	pcie_do_fatal_recovery(pdev, PCIE_PORT_SERVICE_DPC);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t dpc_irq(int irq, void *context)
+{
+	struct dpc_dev *dpc = (struct dpc_dev *)context;
+	struct pci_dev *pdev = dpc->dev->port;
+	u16 cap = dpc->cap_pos, status;
+
+	pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status);
 
-	schedule_work(&dpc->work);
+	if (!(status & PCI_EXP_DPC_STATUS_INTERRUPT) || status == (u16)(~0))
+		return IRQ_NONE;
 
+	pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS,
+			      PCI_EXP_DPC_STATUS_INTERRUPT);
+	if (status & PCI_EXP_DPC_STATUS_TRIGGER)
+		return IRQ_WAKE_THREAD;
 	return IRQ_HANDLED;
 }
 
@@ -250,11 +227,11 @@ static int dpc_probe(struct pcie_device *dev)
 
 	dpc->cap_pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DPC);
 	dpc->dev = dev;
-	INIT_WORK(&dpc->work, dpc_work);
 	set_service_data(dev, dpc);
 
-	status = devm_request_irq(device, dev->irq, dpc_irq, IRQF_SHARED,
-				  "pcie-dpc", dpc);
+	status = devm_request_threaded_irq(device, dev->irq, dpc_irq,
+					   dpc_handler, IRQF_SHARED,
+					   "pcie-dpc", dpc);
 	if (status) {
 		dev_warn(device, "request IRQ%d failed: %d\n", dev->irq,
 			 status);
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index f02e334beb45..708fd3a0d646 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -175,9 +175,11 @@ out:
  */
 static pci_ers_result_t default_reset_link(struct pci_dev *dev)
 {
-	pci_reset_bridge_secondary_bus(dev);
+	int rc;
+
+	rc = pci_bridge_secondary_bus_reset(dev);
 	pci_printk(KERN_DEBUG, dev, "downstream link has been reset\n");
-	return PCI_ERS_RESULT_RECOVERED;
+	return rc ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
 }
 
 static pci_ers_result_t reset_link(struct pci_dev *dev, u32 service)
@@ -252,6 +254,7 @@ static pci_ers_result_t broadcast_error_message(struct pci_dev *dev,
 			dev->error_state = state;
 		pci_walk_bus(dev->subordinate, cb, &result_data);
 		if (cb == report_resume) {
+			pci_aer_clear_device_status(dev);
 			pci_cleanup_aer_uncorrect_error_status(dev);
 			dev->error_state = pci_channel_io_normal;
 		}
@@ -259,15 +262,10 @@ static pci_ers_result_t broadcast_error_message(struct pci_dev *dev,
 		/*
 		 * If the error is reported by an end point, we think this
 		 * error is related to the upstream link of the end point.
+		 * The error is non fatal so the bus is ok; just invoke
+		 * the callback for the function that logged the error.
 		 */
-		if (state == pci_channel_io_normal)
-			/*
-			 * the error is non fatal so the bus is ok, just invoke
-			 * the callback for the function that logged the error.
-			 */
-			cb(dev, &result_data);
-		else
-			pci_walk_bus(dev->bus, cb, &result_data);
+		cb(dev, &result_data);
 	}
 
 	return result_data.result;
@@ -317,7 +315,8 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service)
 		 * do error recovery on all subordinates of the bridge instead
 		 * of the bridge and clear the error status of the bridge.
 		 */
-		pci_cleanup_aer_uncorrect_error_status(dev);
+		pci_aer_clear_fatal_status(dev);
+		pci_aer_clear_device_status(dev);
 	}
 
 	if (result == PCI_ERS_RESULT_RECOVERED) {
diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h
index 6ffc797a0dc1..d59afa42fc14 100644
--- a/drivers/pci/pcie/portdrv.h
+++ b/drivers/pci/pcie/portdrv.h
@@ -50,6 +50,7 @@ struct pcie_port_service_driver {
 	int (*probe) (struct pcie_device *dev);
 	void (*remove) (struct pcie_device *dev);
 	int (*suspend) (struct pcie_device *dev);
+	int (*resume_noirq) (struct pcie_device *dev);
 	int (*resume) (struct pcie_device *dev);
 
 	/* Device driver may resume normal operations */
@@ -82,6 +83,7 @@ extern struct bus_type pcie_port_bus_type;
 int pcie_port_device_register(struct pci_dev *dev);
 #ifdef CONFIG_PM
 int pcie_port_device_suspend(struct device *dev);
+int pcie_port_device_resume_noirq(struct device *dev);
 int pcie_port_device_resume(struct device *dev);
 #endif
 void pcie_port_device_remove(struct pci_dev *dev);
diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c
index e0261ad4bcdd..7c37d815229e 100644
--- a/drivers/pci/pcie/portdrv_core.c
+++ b/drivers/pci/pcie/portdrv_core.c
@@ -353,14 +353,19 @@ error_disable:
 }
 
 #ifdef CONFIG_PM
-static int suspend_iter(struct device *dev, void *data)
+typedef int (*pcie_pm_callback_t)(struct pcie_device *);
+
+static int pm_iter(struct device *dev, void *data)
 {
 	struct pcie_port_service_driver *service_driver;
+	size_t offset = *(size_t *)data;
+	pcie_pm_callback_t cb;
 
 	if ((dev->bus == &pcie_port_bus_type) && dev->driver) {
 		service_driver = to_service_driver(dev->driver);
-		if (service_driver->suspend)
-			service_driver->suspend(to_pcie_device(dev));
+		cb = *(pcie_pm_callback_t *)((void *)service_driver + offset);
+		if (cb)
+			return cb(to_pcie_device(dev));
 	}
 	return 0;
 }
@@ -371,20 +376,14 @@ static int suspend_iter(struct device *dev, void *data)
  */
 int pcie_port_device_suspend(struct device *dev)
 {
-	return device_for_each_child(dev, NULL, suspend_iter);
+	size_t off = offsetof(struct pcie_port_service_driver, suspend);
+	return device_for_each_child(dev, &off, pm_iter);
 }
 
-static int resume_iter(struct device *dev, void *data)
+int pcie_port_device_resume_noirq(struct device *dev)
 {
-	struct pcie_port_service_driver *service_driver;
-
-	if ((dev->bus == &pcie_port_bus_type) &&
-	    (dev->driver)) {
-		service_driver = to_service_driver(dev->driver);
-		if (service_driver->resume)
-			service_driver->resume(to_pcie_device(dev));
-	}
-	return 0;
+	size_t off = offsetof(struct pcie_port_service_driver, resume_noirq);
+	return device_for_each_child(dev, &off, pm_iter);
 }
 
 /**
@@ -393,7 +392,8 @@ static int resume_iter(struct device *dev, void *data)
  */
 int pcie_port_device_resume(struct device *dev)
 {
-	return device_for_each_child(dev, NULL, resume_iter);
+	size_t off = offsetof(struct pcie_port_service_driver, resume);
+	return device_for_each_child(dev, &off, pm_iter);
 }
 #endif /* PM */
 
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index 973f1b80a038..eef22dc29140 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -42,17 +42,6 @@ __setup("pcie_ports=", pcie_port_setup);
 
 /* global data */
 
-static int pcie_portdrv_restore_config(struct pci_dev *dev)
-{
-	int retval;
-
-	retval = pci_enable_device(dev);
-	if (retval)
-		return retval;
-	pci_set_master(dev);
-	return 0;
-}
-
 #ifdef CONFIG_PM
 static int pcie_port_runtime_suspend(struct device *dev)
 {
@@ -76,10 +65,12 @@ static int pcie_port_runtime_idle(struct device *dev)
 
 static const struct dev_pm_ops pcie_portdrv_pm_ops = {
 	.suspend	= pcie_port_device_suspend,
+	.resume_noirq	= pcie_port_device_resume_noirq,
 	.resume		= pcie_port_device_resume,
 	.freeze		= pcie_port_device_suspend,
 	.thaw		= pcie_port_device_resume,
 	.poweroff	= pcie_port_device_suspend,
+	.restore_noirq	= pcie_port_device_resume_noirq,
 	.restore	= pcie_port_device_resume,
 	.runtime_suspend = pcie_port_runtime_suspend,
 	.runtime_resume	= pcie_port_runtime_resume,
@@ -160,19 +151,6 @@ static pci_ers_result_t pcie_portdrv_mmio_enabled(struct pci_dev *dev)
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
-static pci_ers_result_t pcie_portdrv_slot_reset(struct pci_dev *dev)
-{
-	/* If fatal, restore cfg space for possible link reset at upstream */
-	if (dev->error_state == pci_channel_io_frozen) {
-		dev->state_saved = true;
-		pci_restore_state(dev);
-		pcie_portdrv_restore_config(dev);
-		pci_enable_pcie_error_reporting(dev);
-	}
-
-	return PCI_ERS_RESULT_RECOVERED;
-}
-
 static int resume_iter(struct device *device, void *data)
 {
 	struct pcie_device *pcie_device;
@@ -208,7 +186,6 @@ static const struct pci_device_id port_pci_ids[] = { {
 static const struct pci_error_handlers pcie_portdrv_err_handler = {
 	.error_detected = pcie_portdrv_error_detected,
 	.mmio_enabled = pcie_portdrv_mmio_enabled,
-	.slot_reset = pcie_portdrv_slot_reset,
 	.resume = pcie_portdrv_err_resume,
 };
 
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 611adcd9c169..ec784009a36b 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -13,7 +13,6 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/cpumask.h>
-#include <linux/pci-aspm.h>
 #include <linux/aer.h>
 #include <linux/acpi.h>
 #include <linux/hypervisor.h>
@@ -1549,6 +1548,20 @@ static int pci_intx_mask_broken(struct pci_dev *dev)
 	return 0;
 }
 
+static void early_dump_pci_device(struct pci_dev *pdev)
+{
+	u32 value[256 / 4];
+	int i;
+
+	pci_info(pdev, "config space:\n");
+
+	for (i = 0; i < 256; i += 4)
+		pci_read_config_dword(pdev, i, &value[i / 4]);
+
+	print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET, 16, 1,
+		       value, 256, false);
+}
+
 /**
  * pci_setup_device - Fill in class and map information of a device
  * @dev: the device structure to fill
@@ -1598,6 +1611,9 @@ int pci_setup_device(struct pci_dev *dev)
 	pci_printk(KERN_DEBUG, dev, "[%04x:%04x] type %02x class %#08x\n",
 		   dev->vendor, dev->device, dev->hdr_type, dev->class);
 
+	if (pci_early_dump)
+		early_dump_pci_device(dev);
+
 	/* Need to have dev->class ready */
 	dev->cfg_size = pci_cfg_space_size(dev);
 
@@ -1725,11 +1741,15 @@ int pci_setup_device(struct pci_dev *dev)
 static void pci_configure_mps(struct pci_dev *dev)
 {
 	struct pci_dev *bridge = pci_upstream_bridge(dev);
-	int mps, p_mps, rc;
+	int mps, mpss, p_mps, rc;
 
 	if (!pci_is_pcie(dev) || !bridge || !pci_is_pcie(bridge))
 		return;
 
+	/* MPS and MRRS fields are of type 'RsvdP' for VFs, short-circuit out */
+	if (dev->is_virtfn)
+		return;
+
 	mps = pcie_get_mps(dev);
 	p_mps = pcie_get_mps(bridge);
 
@@ -1749,6 +1769,14 @@ static void pci_configure_mps(struct pci_dev *dev)
 	if (pcie_bus_config != PCIE_BUS_DEFAULT)
 		return;
 
+	mpss = 128 << dev->pcie_mpss;
+	if (mpss < p_mps && pci_pcie_type(bridge) == PCI_EXP_TYPE_ROOT_PORT) {
+		pcie_set_mps(bridge, mpss);
+		pci_info(dev, "Upstream bridge's Max Payload Size set to %d (was %d, max %d)\n",
+			 mpss, p_mps, 128 << bridge->pcie_mpss);
+		p_mps = pcie_get_mps(bridge);
+	}
+
 	rc = pcie_set_mps(dev, p_mps);
 	if (rc) {
 		pci_warn(dev, "can't set Max Payload Size to %d; if necessary, use \"pci=pcie_bus_safe\" and report a bug\n",
@@ -1757,7 +1785,7 @@ static void pci_configure_mps(struct pci_dev *dev)
 	}
 
 	pci_info(dev, "Max Payload Size set to %d (was %d, max %d)\n",
-		 p_mps, mps, 128 << dev->pcie_mpss);
+		 p_mps, mps, mpss);
 }
 
 static struct hpp_type0 pci_default_type0 = {
@@ -2042,6 +2070,29 @@ static void pci_configure_ltr(struct pci_dev *dev)
 #endif
 }
 
+static void pci_configure_eetlp_prefix(struct pci_dev *dev)
+{
+#ifdef CONFIG_PCI_PASID
+	struct pci_dev *bridge;
+	u32 cap;
+
+	if (!pci_is_pcie(dev))
+		return;
+
+	pcie_capability_read_dword(dev, PCI_EXP_DEVCAP2, &cap);
+	if (!(cap & PCI_EXP_DEVCAP2_EE_PREFIX))
+		return;
+
+	if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT)
+		dev->eetlp_prefix_path = 1;
+	else {
+		bridge = pci_upstream_bridge(dev);
+		if (bridge && bridge->eetlp_prefix_path)
+			dev->eetlp_prefix_path = 1;
+	}
+#endif
+}
+
 static void pci_configure_device(struct pci_dev *dev)
 {
 	struct hotplug_params hpp;
@@ -2051,6 +2102,7 @@ static void pci_configure_device(struct pci_dev *dev)
 	pci_configure_extended_tags(dev, NULL);
 	pci_configure_relaxed_ordering(dev);
 	pci_configure_ltr(dev);
+	pci_configure_eetlp_prefix(dev);
 
 	memset(&hpp, 0, sizeof(hpp));
 	ret = pci_get_hp_params(dev, &hpp);
@@ -2064,6 +2116,7 @@ static void pci_configure_device(struct pci_dev *dev)
 
 static void pci_release_capabilities(struct pci_dev *dev)
 {
+	pci_aer_exit(dev);
 	pci_vpd_release(dev);
 	pci_iov_release(dev);
 	pci_free_cap_save_buffers(dev);
@@ -2156,8 +2209,8 @@ static bool pci_bus_wait_crs(struct pci_bus *bus, int devfn, u32 *l,
 	return true;
 }
 
-bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
-				int timeout)
+bool pci_bus_generic_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
+					int timeout)
 {
 	if (pci_bus_read_config_dword(bus, devfn, PCI_VENDOR_ID, l))
 		return false;
@@ -2172,6 +2225,24 @@ bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
 
 	return true;
 }
+
+bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
+				int timeout)
+{
+#ifdef CONFIG_PCI_QUIRKS
+	struct pci_dev *bridge = bus->self;
+
+	/*
+	 * Certain IDT switches have an issue where they improperly trigger
+	 * ACS Source Validation errors on completions for config reads.
+	 */
+	if (bridge && bridge->vendor == PCI_VENDOR_ID_IDT &&
+	    bridge->device == 0x80b5)
+		return pci_idt_bus_quirk(bus, devfn, l, timeout);
+#endif
+
+	return pci_bus_generic_read_dev_vendor_id(bus, devfn, l, timeout);
+}
 EXPORT_SYMBOL(pci_bus_read_dev_vendor_id);
 
 /*
@@ -2205,6 +2276,25 @@ static struct pci_dev *pci_scan_device(struct pci_bus *bus, int devfn)
 	return dev;
 }
 
+static void pcie_report_downtraining(struct pci_dev *dev)
+{
+	if (!pci_is_pcie(dev))
+		return;
+
+	/* Look from the device up to avoid downstream ports with no devices */
+	if ((pci_pcie_type(dev) != PCI_EXP_TYPE_ENDPOINT) &&
+	    (pci_pcie_type(dev) != PCI_EXP_TYPE_LEG_END) &&
+	    (pci_pcie_type(dev) != PCI_EXP_TYPE_UPSTREAM))
+		return;
+
+	/* Multi-function PCIe devices share the same link/status */
+	if (PCI_FUNC(dev->devfn) != 0 || dev->is_virtfn)
+		return;
+
+	/* Print link status only if the device is constrained by the fabric */
+	__pcie_print_link_status(dev, false);
+}
+
 static void pci_init_capabilities(struct pci_dev *dev)
 {
 	/* Enhanced Allocation */
@@ -2240,6 +2330,8 @@ static void pci_init_capabilities(struct pci_dev *dev)
 	/* Advanced Error Reporting */
 	pci_aer_init(dev);
 
+	pcie_report_downtraining(dev);
+
 	if (pci_probe_reset_function(dev) == 0)
 		dev->reset_fn = 1;
 }
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index f439de848658..46f58a9771d7 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -25,8 +25,10 @@
 #include <linux/sched.h>
 #include <linux/ktime.h>
 #include <linux/mm.h>
+#include <linux/nvme.h>
 #include <linux/platform_data/x86/apple.h>
 #include <linux/pm_runtime.h>
+#include <linux/switchtec.h>
 #include <asm/dma.h>	/* isa_dma_bridge_buggy */
 #include "pci.h"
 
@@ -460,6 +462,7 @@ static void quirk_nfp6000(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETRONOME,	PCI_DEVICE_ID_NETRONOME_NFP4000,	quirk_nfp6000);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETRONOME,	PCI_DEVICE_ID_NETRONOME_NFP6000,	quirk_nfp6000);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETRONOME,	PCI_DEVICE_ID_NETRONOME_NFP5000,	quirk_nfp6000);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETRONOME,	PCI_DEVICE_ID_NETRONOME_NFP6000_VF,	quirk_nfp6000);
 
 /*  On IBM Crocodile ipr SAS adapters, expand BAR to system page size */
@@ -2105,6 +2108,7 @@ static void quirk_netmos(struct pci_dev *dev)
 		if (dev->subsystem_vendor == PCI_VENDOR_ID_IBM &&
 				dev->subsystem_device == 0x0299)
 			return;
+		/* else: fall through */
 	case PCI_DEVICE_ID_NETMOS_9735:
 	case PCI_DEVICE_ID_NETMOS_9745:
 	case PCI_DEVICE_ID_NETMOS_9845:
@@ -2352,6 +2356,9 @@ static void quirk_paxc_bridge(struct pci_dev *pdev)
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16cd, quirk_paxc_bridge);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16f0, quirk_paxc_bridge);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd750, quirk_paxc_bridge);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd802, quirk_paxc_bridge);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd804, quirk_paxc_bridge);
 #endif
 
 /*
@@ -3664,6 +3671,108 @@ static int reset_chelsio_generic_dev(struct pci_dev *dev, int probe)
 #define PCI_DEVICE_ID_INTEL_IVB_M_VGA      0x0156
 #define PCI_DEVICE_ID_INTEL_IVB_M2_VGA     0x0166
 
+/*
+ * The Samsung SM961/PM961 controller can sometimes enter a fatal state after
+ * FLR where config space reads from the device return -1.  We seem to be
+ * able to avoid this condition if we disable the NVMe controller prior to
+ * FLR.  This quirk is generic for any NVMe class device requiring similar
+ * assistance to quiesce the device prior to FLR.
+ *
+ * NVMe specification: https://nvmexpress.org/resources/specifications/
+ * Revision 1.0e:
+ *    Chapter 2: Required and optional PCI config registers
+ *    Chapter 3: NVMe control registers
+ *    Chapter 7.3: Reset behavior
+ */
+static int nvme_disable_and_flr(struct pci_dev *dev, int probe)
+{
+	void __iomem *bar;
+	u16 cmd;
+	u32 cfg;
+
+	if (dev->class != PCI_CLASS_STORAGE_EXPRESS ||
+	    !pcie_has_flr(dev) || !pci_resource_start(dev, 0))
+		return -ENOTTY;
+
+	if (probe)
+		return 0;
+
+	bar = pci_iomap(dev, 0, NVME_REG_CC + sizeof(cfg));
+	if (!bar)
+		return -ENOTTY;
+
+	pci_read_config_word(dev, PCI_COMMAND, &cmd);
+	pci_write_config_word(dev, PCI_COMMAND, cmd | PCI_COMMAND_MEMORY);
+
+	cfg = readl(bar + NVME_REG_CC);
+
+	/* Disable controller if enabled */
+	if (cfg & NVME_CC_ENABLE) {
+		u32 cap = readl(bar + NVME_REG_CAP);
+		unsigned long timeout;
+
+		/*
+		 * Per nvme_disable_ctrl() skip shutdown notification as it
+		 * could complete commands to the admin queue.  We only intend
+		 * to quiesce the device before reset.
+		 */
+		cfg &= ~(NVME_CC_SHN_MASK | NVME_CC_ENABLE);
+
+		writel(cfg, bar + NVME_REG_CC);
+
+		/*
+		 * Some controllers require an additional delay here, see
+		 * NVME_QUIRK_DELAY_BEFORE_CHK_RDY.  None of those are yet
+		 * supported by this quirk.
+		 */
+
+		/* Cap register provides max timeout in 500ms increments */
+		timeout = ((NVME_CAP_TIMEOUT(cap) + 1) * HZ / 2) + jiffies;
+
+		for (;;) {
+			u32 status = readl(bar + NVME_REG_CSTS);
+
+			/* Ready status becomes zero on disable complete */
+			if (!(status & NVME_CSTS_RDY))
+				break;
+
+			msleep(100);
+
+			if (time_after(jiffies, timeout)) {
+				pci_warn(dev, "Timeout waiting for NVMe ready status to clear after disable\n");
+				break;
+			}
+		}
+	}
+
+	pci_iounmap(dev, bar);
+
+	pcie_flr(dev);
+
+	return 0;
+}
+
+/*
+ * Intel DC P3700 NVMe controller will timeout waiting for ready status
+ * to change after NVMe enable if the driver starts interacting with the
+ * device too soon after FLR.  A 250ms delay after FLR has heuristically
+ * proven to produce reliably working results for device assignment cases.
+ */
+static int delay_250ms_after_flr(struct pci_dev *dev, int probe)
+{
+	if (!pcie_has_flr(dev))
+		return -ENOTTY;
+
+	if (probe)
+		return 0;
+
+	pcie_flr(dev);
+
+	msleep(250);
+
+	return 0;
+}
+
 static const struct pci_dev_reset_methods pci_dev_reset_methods[] = {
 	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82599_SFP_VF,
 		 reset_intel_82599_sfp_virtfn },
@@ -3671,6 +3780,8 @@ static const struct pci_dev_reset_methods pci_dev_reset_methods[] = {
 		reset_ivb_igd },
 	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_M2_VGA,
 		reset_ivb_igd },
+	{ PCI_VENDOR_ID_SAMSUNG, 0xa804, nvme_disable_and_flr },
+	{ PCI_VENDOR_ID_INTEL, 0x0953, delay_250ms_after_flr },
 	{ PCI_VENDOR_ID_CHELSIO, PCI_ANY_ID,
 		reset_chelsio_generic_dev },
 	{ 0 }
@@ -3740,6 +3851,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x917a,
 /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c78 */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9182,
 			 quirk_dma_func1_alias);
+/* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c134 */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9183,
+			 quirk_dma_func1_alias);
 /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c46 */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x91a0,
 			 quirk_dma_func1_alias);
@@ -4553,27 +4667,79 @@ static int pci_quirk_enable_intel_spt_pch_acs(struct pci_dev *dev)
 	return 0;
 }
 
-static const struct pci_dev_enable_acs {
+static int pci_quirk_disable_intel_spt_pch_acs_redir(struct pci_dev *dev)
+{
+	int pos;
+	u32 cap, ctrl;
+
+	if (!pci_quirk_intel_spt_pch_acs_match(dev))
+		return -ENOTTY;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
+	if (!pos)
+		return -ENOTTY;
+
+	pci_read_config_dword(dev, pos + PCI_ACS_CAP, &cap);
+	pci_read_config_dword(dev, pos + INTEL_SPT_ACS_CTRL, &ctrl);
+
+	ctrl &= ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC);
+
+	pci_write_config_dword(dev, pos + INTEL_SPT_ACS_CTRL, ctrl);
+
+	pci_info(dev, "Intel SPT PCH root port workaround: disabled ACS redirect\n");
+
+	return 0;
+}
+
+static const struct pci_dev_acs_ops {
 	u16 vendor;
 	u16 device;
 	int (*enable_acs)(struct pci_dev *dev);
-} pci_dev_enable_acs[] = {
-	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_quirk_enable_intel_pch_acs },
-	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_quirk_enable_intel_spt_pch_acs },
-	{ 0 }
+	int (*disable_acs_redir)(struct pci_dev *dev);
+} pci_dev_acs_ops[] = {
+	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID,
+	    .enable_acs = pci_quirk_enable_intel_pch_acs,
+	},
+	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID,
+	    .enable_acs = pci_quirk_enable_intel_spt_pch_acs,
+	    .disable_acs_redir = pci_quirk_disable_intel_spt_pch_acs_redir,
+	},
 };
 
 int pci_dev_specific_enable_acs(struct pci_dev *dev)
 {
-	const struct pci_dev_enable_acs *i;
-	int ret;
+	const struct pci_dev_acs_ops *p;
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(pci_dev_acs_ops); i++) {
+		p = &pci_dev_acs_ops[i];
+		if ((p->vendor == dev->vendor ||
+		     p->vendor == (u16)PCI_ANY_ID) &&
+		    (p->device == dev->device ||
+		     p->device == (u16)PCI_ANY_ID) &&
+		    p->enable_acs) {
+			ret = p->enable_acs(dev);
+			if (ret >= 0)
+				return ret;
+		}
+	}
 
-	for (i = pci_dev_enable_acs; i->enable_acs; i++) {
-		if ((i->vendor == dev->vendor ||
-		     i->vendor == (u16)PCI_ANY_ID) &&
-		    (i->device == dev->device ||
-		     i->device == (u16)PCI_ANY_ID)) {
-			ret = i->enable_acs(dev);
+	return -ENOTTY;
+}
+
+int pci_dev_specific_disable_acs_redir(struct pci_dev *dev)
+{
+	const struct pci_dev_acs_ops *p;
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(pci_dev_acs_ops); i++) {
+		p = &pci_dev_acs_ops[i];
+		if ((p->vendor == dev->vendor ||
+		     p->vendor == (u16)PCI_ANY_ID) &&
+		    (p->device == dev->device ||
+		     p->device == (u16)PCI_ANY_ID) &&
+		    p->disable_acs_redir) {
+			ret = p->disable_acs_redir(dev);
 			if (ret >= 0)
 				return ret;
 		}
@@ -4753,3 +4919,197 @@ DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_AMD, PCI_ANY_ID,
 			      PCI_CLASS_MULTIMEDIA_HD_AUDIO, 8, quirk_gpu_hda);
 DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
 			      PCI_CLASS_MULTIMEDIA_HD_AUDIO, 8, quirk_gpu_hda);
+
+/*
+ * Some IDT switches incorrectly flag an ACS Source Validation error on
+ * completions for config read requests even though PCIe r4.0, sec
+ * 6.12.1.1, says that completions are never affected by ACS Source
+ * Validation.  Here's the text of IDT 89H32H8G3-YC, erratum #36:
+ *
+ *   Item #36 - Downstream port applies ACS Source Validation to Completions
+ *   Section 6.12.1.1 of the PCI Express Base Specification 3.1 states that
+ *   completions are never affected by ACS Source Validation.  However,
+ *   completions received by a downstream port of the PCIe switch from a
+ *   device that has not yet captured a PCIe bus number are incorrectly
+ *   dropped by ACS Source Validation by the switch downstream port.
+ *
+ * The workaround suggested by IDT is to issue a config write to the
+ * downstream device before issuing the first config read.  This allows the
+ * downstream device to capture its bus and device numbers (see PCIe r4.0,
+ * sec 2.2.9), thus avoiding the ACS error on the completion.
+ *
+ * However, we don't know when the device is ready to accept the config
+ * write, so we do config reads until we receive a non-Config Request Retry
+ * Status, then do the config write.
+ *
+ * To avoid hitting the erratum when doing the config reads, we disable ACS
+ * SV around this process.
+ */
+int pci_idt_bus_quirk(struct pci_bus *bus, int devfn, u32 *l, int timeout)
+{
+	int pos;
+	u16 ctrl = 0;
+	bool found;
+	struct pci_dev *bridge = bus->self;
+
+	pos = pci_find_ext_capability(bridge, PCI_EXT_CAP_ID_ACS);
+
+	/* Disable ACS SV before initial config reads */
+	if (pos) {
+		pci_read_config_word(bridge, pos + PCI_ACS_CTRL, &ctrl);
+		if (ctrl & PCI_ACS_SV)
+			pci_write_config_word(bridge, pos + PCI_ACS_CTRL,
+					      ctrl & ~PCI_ACS_SV);
+	}
+
+	found = pci_bus_generic_read_dev_vendor_id(bus, devfn, l, timeout);
+
+	/* Write Vendor ID (read-only) so the endpoint latches its bus/dev */
+	if (found)
+		pci_bus_write_config_word(bus, devfn, PCI_VENDOR_ID, 0);
+
+	/* Re-enable ACS_SV if it was previously enabled */
+	if (ctrl & PCI_ACS_SV)
+		pci_write_config_word(bridge, pos + PCI_ACS_CTRL, ctrl);
+
+	return found;
+}
+
+/*
+ * Microsemi Switchtec NTB uses devfn proxy IDs to move TLPs between
+ * NT endpoints via the internal switch fabric. These IDs replace the
+ * originating requestor ID TLPs which access host memory on peer NTB
+ * ports. Therefore, all proxy IDs must be aliased to the NTB device
+ * to permit access when the IOMMU is turned on.
+ */
+static void quirk_switchtec_ntb_dma_alias(struct pci_dev *pdev)
+{
+	void __iomem *mmio;
+	struct ntb_info_regs __iomem *mmio_ntb;
+	struct ntb_ctrl_regs __iomem *mmio_ctrl;
+	struct sys_info_regs __iomem *mmio_sys_info;
+	u64 partition_map;
+	u8 partition;
+	int pp;
+
+	if (pci_enable_device(pdev)) {
+		pci_err(pdev, "Cannot enable Switchtec device\n");
+		return;
+	}
+
+	mmio = pci_iomap(pdev, 0, 0);
+	if (mmio == NULL) {
+		pci_disable_device(pdev);
+		pci_err(pdev, "Cannot iomap Switchtec device\n");
+		return;
+	}
+
+	pci_info(pdev, "Setting Switchtec proxy ID aliases\n");
+
+	mmio_ntb = mmio + SWITCHTEC_GAS_NTB_OFFSET;
+	mmio_ctrl = (void __iomem *) mmio_ntb + SWITCHTEC_NTB_REG_CTRL_OFFSET;
+	mmio_sys_info = mmio + SWITCHTEC_GAS_SYS_INFO_OFFSET;
+
+	partition = ioread8(&mmio_ntb->partition_id);
+
+	partition_map = ioread32(&mmio_ntb->ep_map);
+	partition_map |= ((u64) ioread32(&mmio_ntb->ep_map + 4)) << 32;
+	partition_map &= ~(1ULL << partition);
+
+	for (pp = 0; pp < (sizeof(partition_map) * 8); pp++) {
+		struct ntb_ctrl_regs __iomem *mmio_peer_ctrl;
+		u32 table_sz = 0;
+		int te;
+
+		if (!(partition_map & (1ULL << pp)))
+			continue;
+
+		pci_dbg(pdev, "Processing partition %d\n", pp);
+
+		mmio_peer_ctrl = &mmio_ctrl[pp];
+
+		table_sz = ioread16(&mmio_peer_ctrl->req_id_table_size);
+		if (!table_sz) {
+			pci_warn(pdev, "Partition %d table_sz 0\n", pp);
+			continue;
+		}
+
+		if (table_sz > 512) {
+			pci_warn(pdev,
+				 "Invalid Switchtec partition %d table_sz %d\n",
+				 pp, table_sz);
+			continue;
+		}
+
+		for (te = 0; te < table_sz; te++) {
+			u32 rid_entry;
+			u8 devfn;
+
+			rid_entry = ioread32(&mmio_peer_ctrl->req_id_table[te]);
+			devfn = (rid_entry >> 1) & 0xFF;
+			pci_dbg(pdev,
+				"Aliasing Partition %d Proxy ID %02x.%d\n",
+				pp, PCI_SLOT(devfn), PCI_FUNC(devfn));
+			pci_add_dma_alias(pdev, devfn);
+		}
+	}
+
+	pci_iounmap(pdev, mmio);
+	pci_disable_device(pdev);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8531,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8532,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8533,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8534,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8535,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8536,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8543,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8544,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8545,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8546,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8551,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8552,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8553,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8554,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8555,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8556,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8561,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8562,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8563,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8564,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8565,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8566,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8571,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8572,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8573,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8574,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8575,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8576,
+			quirk_switchtec_ntb_dma_alias);
diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c
index 5e3d0dced2b8..461e7fd2756f 100644
--- a/drivers/pci/remove.c
+++ b/drivers/pci/remove.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/pci.h>
 #include <linux/module.h>
-#include <linux/pci-aspm.h>
 #include "pci.h"
 
 static void pci_free_resources(struct pci_dev *dev)
diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c
index a7b5c37a85ec..137bf0cee897 100644
--- a/drivers/pci/rom.c
+++ b/drivers/pci/rom.c
@@ -80,7 +80,8 @@ EXPORT_SYMBOL_GPL(pci_disable_rom);
  * The PCI window size could be much larger than the
  * actual image size.
  */
-size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size)
+static size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom,
+			       size_t size)
 {
 	void __iomem *image;
 	int last_image;
@@ -106,8 +107,14 @@ size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size)
 		length = readw(pds + 16);
 		image += length * 512;
 		/* Avoid iterating through memory outside the resource window */
-		if (image > rom + size)
+		if (image >= rom + size)
 			break;
+		if (!last_image) {
+			if (readw(image) != 0xAA55) {
+				pci_info(pdev, "No more image in the PCI ROM\n");
+				break;
+			}
+		}
 	} while (length && !last_image);
 
 	/* never return a size larger than the PCI resource window */
diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c
index 47cd0c037433..9940cc70f38b 100644
--- a/drivers/pci/switch/switchtec.c
+++ b/drivers/pci/switch/switchtec.c
@@ -641,7 +641,7 @@ static int ioctl_event_summary(struct switchtec_dev *stdev,
 
 	for (i = 0; i < SWITCHTEC_MAX_PFF_CSR; i++) {
 		reg = ioread16(&stdev->mmio_pff_csr[i].vendor_id);
-		if (reg != MICROSEMI_VENDOR_ID)
+		if (reg != PCI_VENDOR_ID_MICROSEMI)
 			break;
 
 		reg = ioread32(&stdev->mmio_pff_csr[i].pff_event_summary);
@@ -1203,7 +1203,7 @@ static void init_pff(struct switchtec_dev *stdev)
 
 	for (i = 0; i < SWITCHTEC_MAX_PFF_CSR; i++) {
 		reg = ioread16(&stdev->mmio_pff_csr[i].vendor_id);
-		if (reg != MICROSEMI_VENDOR_ID)
+		if (reg != PCI_VENDOR_ID_MICROSEMI)
 			break;
 	}
 
@@ -1267,7 +1267,7 @@ static int switchtec_pci_probe(struct pci_dev *pdev,
 	struct switchtec_dev *stdev;
 	int rc;
 
-	if (pdev->class == MICROSEMI_NTB_CLASSCODE)
+	if (pdev->class == (PCI_CLASS_BRIDGE_OTHER << 8))
 		request_module_nowait("ntb_hw_switchtec");
 
 	stdev = stdev_create(pdev);
@@ -1321,19 +1321,19 @@ static void switchtec_pci_remove(struct pci_dev *pdev)
 
 #define SWITCHTEC_PCI_DEVICE(device_id) \
 	{ \
-		.vendor     = MICROSEMI_VENDOR_ID, \
+		.vendor     = PCI_VENDOR_ID_MICROSEMI, \
 		.device     = device_id, \
 		.subvendor  = PCI_ANY_ID, \
 		.subdevice  = PCI_ANY_ID, \
-		.class      = MICROSEMI_MGMT_CLASSCODE, \
+		.class      = (PCI_CLASS_MEMORY_OTHER << 8), \
 		.class_mask = 0xFFFFFFFF, \
 	}, \
 	{ \
-		.vendor     = MICROSEMI_VENDOR_ID, \
+		.vendor     = PCI_VENDOR_ID_MICROSEMI, \
 		.device     = device_id, \
 		.subvendor  = PCI_ANY_ID, \
 		.subdevice  = PCI_ANY_ID, \
-		.class      = MICROSEMI_NTB_CLASSCODE, \
+		.class      = (PCI_CLASS_BRIDGE_OTHER << 8), \
 		.class_mask = 0xFFFFFFFF, \
 	}
 
diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c
index 8617565ba561..4963c2e2bd4c 100644
--- a/drivers/pci/vpd.c
+++ b/drivers/pci/vpd.c
@@ -146,7 +146,7 @@ static int pci_vpd_wait(struct pci_dev *dev)
 	if (!vpd->busy)
 		return 0;
 
-	while (time_before(jiffies, timeout)) {
+	do {
 		ret = pci_user_read_config_word(dev, vpd->cap + PCI_VPD_ADDR,
 						&status);
 		if (ret < 0)
@@ -160,10 +160,13 @@ static int pci_vpd_wait(struct pci_dev *dev)
 		if (fatal_signal_pending(current))
 			return -EINTR;
 
+		if (time_after(jiffies, timeout))
+			break;
+
 		usleep_range(10, max_sleep);
 		if (max_sleep < 1024)
 			max_sleep *= 2;
-	}
+	} while (true);
 
 	pci_warn(dev, "VPD access failed.  This is likely a firmware bug on this device.  Contact the card vendor for a firmware update\n");
 	return -ETIMEDOUT;
diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c
index 0d09d8e669cd..1bfeb160c5b1 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -53,6 +53,16 @@ enum {
 	CCI_IF_MAX,
 };
 
+#define NUM_HW_CNTRS_CII_4XX	4
+#define NUM_HW_CNTRS_CII_5XX	8
+#define NUM_HW_CNTRS_MAX	NUM_HW_CNTRS_CII_5XX
+
+#define FIXED_HW_CNTRS_CII_4XX	1
+#define FIXED_HW_CNTRS_CII_5XX	0
+#define FIXED_HW_CNTRS_MAX	FIXED_HW_CNTRS_CII_4XX
+
+#define HW_CNTRS_MAX		(NUM_HW_CNTRS_MAX + FIXED_HW_CNTRS_MAX)
+
 struct event_range {
 	u32 min;
 	u32 max;
@@ -633,8 +643,7 @@ static void cci_pmu_sync_counters(struct cci_pmu *cci_pmu)
 {
 	int i;
 	struct cci_pmu_hw_events *cci_hw = &cci_pmu->hw_events;
-
-	DECLARE_BITMAP(mask, cci_pmu->num_cntrs);
+	DECLARE_BITMAP(mask, HW_CNTRS_MAX);
 
 	bitmap_zero(mask, cci_pmu->num_cntrs);
 	for_each_set_bit(i, cci_pmu->hw_events.used_mask, cci_pmu->num_cntrs) {
@@ -940,7 +949,7 @@ static void pmu_write_counters(struct cci_pmu *cci_pmu, unsigned long *mask)
 static void cci5xx_pmu_write_counters(struct cci_pmu *cci_pmu, unsigned long *mask)
 {
 	int i;
-	DECLARE_BITMAP(saved_mask, cci_pmu->num_cntrs);
+	DECLARE_BITMAP(saved_mask, HW_CNTRS_MAX);
 
 	bitmap_zero(saved_mask, cci_pmu->num_cntrs);
 	pmu_save_counters(cci_pmu, saved_mask);
@@ -1245,7 +1254,7 @@ static int validate_group(struct perf_event *event)
 {
 	struct perf_event *sibling, *leader = event->group_leader;
 	struct cci_pmu *cci_pmu = to_cci_pmu(event->pmu);
-	unsigned long mask[BITS_TO_LONGS(cci_pmu->num_cntrs)];
+	unsigned long mask[BITS_TO_LONGS(HW_CNTRS_MAX)];
 	struct cci_pmu_hw_events fake_pmu = {
 		/*
 		 * Initialise the fake PMU. We only need to populate the
@@ -1403,6 +1412,11 @@ static int cci_pmu_init(struct cci_pmu *cci_pmu, struct platform_device *pdev)
 	char *name = model->name;
 	u32 num_cntrs;
 
+	if (WARN_ON(model->num_hw_cntrs > NUM_HW_CNTRS_MAX))
+		return -EINVAL;
+	if (WARN_ON(model->fixed_hw_cntrs > FIXED_HW_CNTRS_MAX))
+		return -EINVAL;
+
 	pmu_event_attr_group.attrs = model->event_attrs;
 	pmu_format_attr_group.attrs = model->format_attrs;
 
@@ -1455,8 +1469,8 @@ static __maybe_unused struct cci_pmu_model cci_pmu_models[] = {
 #ifdef CONFIG_ARM_CCI400_PMU
 	[CCI400_R0] = {
 		.name = "CCI_400",
-		.fixed_hw_cntrs = 1,	/* Cycle counter */
-		.num_hw_cntrs = 4,
+		.fixed_hw_cntrs = FIXED_HW_CNTRS_CII_4XX, /* Cycle counter */
+		.num_hw_cntrs = NUM_HW_CNTRS_CII_4XX,
 		.cntr_size = SZ_4K,
 		.format_attrs = cci400_pmu_format_attrs,
 		.event_attrs = cci400_r0_pmu_event_attrs,
@@ -1475,8 +1489,8 @@ static __maybe_unused struct cci_pmu_model cci_pmu_models[] = {
 	},
 	[CCI400_R1] = {
 		.name = "CCI_400_r1",
-		.fixed_hw_cntrs = 1,	/* Cycle counter */
-		.num_hw_cntrs = 4,
+		.fixed_hw_cntrs = FIXED_HW_CNTRS_CII_4XX, /* Cycle counter */
+		.num_hw_cntrs = NUM_HW_CNTRS_CII_4XX,
 		.cntr_size = SZ_4K,
 		.format_attrs = cci400_pmu_format_attrs,
 		.event_attrs = cci400_r1_pmu_event_attrs,
@@ -1497,8 +1511,8 @@ static __maybe_unused struct cci_pmu_model cci_pmu_models[] = {
 #ifdef CONFIG_ARM_CCI5xx_PMU
 	[CCI500_R0] = {
 		.name = "CCI_500",
-		.fixed_hw_cntrs = 0,
-		.num_hw_cntrs = 8,
+		.fixed_hw_cntrs = FIXED_HW_CNTRS_CII_5XX,
+		.num_hw_cntrs = NUM_HW_CNTRS_CII_5XX,
 		.cntr_size = SZ_64K,
 		.format_attrs = cci5xx_pmu_format_attrs,
 		.event_attrs = cci5xx_pmu_event_attrs,
@@ -1521,8 +1535,8 @@ static __maybe_unused struct cci_pmu_model cci_pmu_models[] = {
 	},
 	[CCI550_R0] = {
 		.name = "CCI_550",
-		.fixed_hw_cntrs = 0,
-		.num_hw_cntrs = 8,
+		.fixed_hw_cntrs = FIXED_HW_CNTRS_CII_5XX,
+		.num_hw_cntrs = NUM_HW_CNTRS_CII_5XX,
 		.cntr_size = SZ_64K,
 		.format_attrs = cci5xx_pmu_format_attrs,
 		.event_attrs = cci5xx_pmu_event_attrs,
diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index b416ee18e6bb..4b15c36f4631 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -1485,17 +1485,9 @@ static int arm_ccn_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, ccn);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -EINVAL;
-
-	if (!devm_request_mem_region(ccn->dev, res->start,
-			resource_size(res), pdev->name))
-		return -EBUSY;
-
-	ccn->base = devm_ioremap(ccn->dev, res->start,
-				resource_size(res));
-	if (!ccn->base)
-		return -EFAULT;
+	ccn->base = devm_ioremap_resource(ccn->dev, res);
+	if (IS_ERR(ccn->base))
+		return PTR_ERR(ccn->base);
 
 	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	if (!res)
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index a6347d487635..7f01f6f60b87 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -28,6 +28,14 @@
 static DEFINE_PER_CPU(struct arm_pmu *, cpu_armpmu);
 static DEFINE_PER_CPU(int, cpu_irq);
 
+static inline u64 arm_pmu_event_max_period(struct perf_event *event)
+{
+	if (event->hw.flags & ARMPMU_EVT_64BIT)
+		return GENMASK_ULL(63, 0);
+	else
+		return GENMASK_ULL(31, 0);
+}
+
 static int
 armpmu_map_cache_event(const unsigned (*cache_map)
 				      [PERF_COUNT_HW_CACHE_MAX]
@@ -114,8 +122,10 @@ int armpmu_event_set_period(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	s64 left = local64_read(&hwc->period_left);
 	s64 period = hwc->sample_period;
+	u64 max_period;
 	int ret = 0;
 
+	max_period = arm_pmu_event_max_period(event);
 	if (unlikely(left <= -period)) {
 		left = period;
 		local64_set(&hwc->period_left, left);
@@ -136,12 +146,12 @@ int armpmu_event_set_period(struct perf_event *event)
 	 * effect we are reducing max_period to account for
 	 * interrupt latency (and we are being very conservative).
 	 */
-	if (left > (armpmu->max_period >> 1))
-		left = armpmu->max_period >> 1;
+	if (left > (max_period >> 1))
+		left = (max_period >> 1);
 
 	local64_set(&hwc->prev_count, (u64)-left);
 
-	armpmu->write_counter(event, (u64)(-left) & 0xffffffff);
+	armpmu->write_counter(event, (u64)(-left) & max_period);
 
 	perf_event_update_userpage(event);
 
@@ -153,6 +163,7 @@ u64 armpmu_event_update(struct perf_event *event)
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	u64 delta, prev_raw_count, new_raw_count;
+	u64 max_period = arm_pmu_event_max_period(event);
 
 again:
 	prev_raw_count = local64_read(&hwc->prev_count);
@@ -162,7 +173,7 @@ again:
 			     new_raw_count) != prev_raw_count)
 		goto again;
 
-	delta = (new_raw_count - prev_raw_count) & armpmu->max_period;
+	delta = (new_raw_count - prev_raw_count) & max_period;
 
 	local64_add(delta, &event->count);
 	local64_sub(delta, &hwc->period_left);
@@ -227,11 +238,10 @@ armpmu_del(struct perf_event *event, int flags)
 
 	armpmu_stop(event, PERF_EF_UPDATE);
 	hw_events->events[idx] = NULL;
-	clear_bit(idx, hw_events->used_mask);
-	if (armpmu->clear_event_idx)
-		armpmu->clear_event_idx(hw_events, event);
-
+	armpmu->clear_event_idx(hw_events, event);
 	perf_event_update_userpage(event);
+	/* Clear the allocated counter */
+	hwc->idx = -1;
 }
 
 static int
@@ -360,6 +370,7 @@ __hw_perf_event_init(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int mapping;
 
+	hwc->flags = 0;
 	mapping = armpmu->map_event(event);
 
 	if (mapping < 0) {
@@ -402,7 +413,7 @@ __hw_perf_event_init(struct perf_event *event)
 		 * is far less likely to overtake the previous one unless
 		 * you have some serious IRQ latency issues.
 		 */
-		hwc->sample_period  = armpmu->max_period >> 1;
+		hwc->sample_period  = arm_pmu_event_max_period(event) >> 1;
 		hwc->last_period    = hwc->sample_period;
 		local64_set(&hwc->period_left, hwc->sample_period);
 	}
@@ -654,14 +665,9 @@ static void cpu_pm_pmu_setup(struct arm_pmu *armpmu, unsigned long cmd)
 	int idx;
 
 	for (idx = 0; idx < armpmu->num_events; idx++) {
-		/*
-		 * If the counter is not used skip it, there is no
-		 * need of stopping/restarting it.
-		 */
-		if (!test_bit(idx, hw_events->used_mask))
-			continue;
-
 		event = hw_events->events[idx];
+		if (!event)
+			continue;
 
 		switch (cmd) {
 		case CPU_PM_ENTER:
diff --git a/drivers/perf/arm_pmu_platform.c b/drivers/perf/arm_pmu_platform.c
index 971ff336494a..96075cecb0ae 100644
--- a/drivers/perf/arm_pmu_platform.c
+++ b/drivers/perf/arm_pmu_platform.c
@@ -160,7 +160,7 @@ static int pmu_parse_irqs(struct arm_pmu *pmu)
 static int armpmu_request_irqs(struct arm_pmu *armpmu)
 {
 	struct pmu_hw_events __percpu *hw_events = armpmu->hw_events;
-	int cpu, err;
+	int cpu, err = 0;
 
 	for_each_cpu(cpu, &armpmu->supported_cpus) {
 		int irq = per_cpu(hw_events->irq, cpu);
diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c
index 44df61397a38..9efd2413240c 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_pmu.c
@@ -350,19 +350,21 @@ void hisi_uncore_pmu_disable(struct pmu *pmu)
 
 /*
  * Read Super CPU cluster and CPU cluster ID from MPIDR_EL1.
- * If multi-threading is supported, SCCL_ID is in MPIDR[aff3] and CCL_ID
- * is in MPIDR[aff2]; if not, SCCL_ID is in MPIDR[aff2] and CCL_ID is
- * in MPIDR[aff1]. If this changes in future, this shall be updated.
+ * If multi-threading is supported, CCL_ID is the low 3-bits in MPIDR[Aff2]
+ * and SCCL_ID is the upper 5-bits of Aff2 field; if not, SCCL_ID
+ * is in MPIDR[Aff2] and CCL_ID is in MPIDR[Aff1].
  */
 static void hisi_read_sccl_and_ccl_id(int *sccl_id, int *ccl_id)
 {
 	u64 mpidr = read_cpuid_mpidr();
 
 	if (mpidr & MPIDR_MT_BITMASK) {
+		int aff2 = MPIDR_AFFINITY_LEVEL(mpidr, 2);
+
 		if (sccl_id)
-			*sccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 3);
+			*sccl_id = aff2 >> 3;
 		if (ccl_id)
-			*ccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
+			*ccl_id = aff2 & 0x7;
 	} else {
 		if (sccl_id)
 			*sccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index dd50371225bc..8d4b7e999f02 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -161,10 +161,10 @@ config PINCTRL_MCP23S08
 	select REGMAP_SPI if SPI_MASTER
 	select GENERIC_PINCONF
 	help
-	  SPI/I2C driver for Microchip MCP23S08/MCP23S17/MCP23008/MCP23017
-	  I/O expanders.
-	  This provides a GPIO interface supporting inputs and outputs.
-	  The I2C versions of the chips can be used as interrupt-controller.
+	  SPI/I2C driver for Microchip MCP23S08 / MCP23S17 / MCP23S18 /
+	  MCP23008 / MCP23017 / MCP23018 I/O expanders.
+	  This provides a GPIO interface supporting inputs and outputs and a
+	  corresponding interrupt-controller.
 
 config PINCTRL_OXNAS
 	bool
@@ -332,6 +332,7 @@ config PINCTRL_OCELOT
 	depends on OF
 	depends on MSCC_OCELOT || COMPILE_TEST
 	select GPIOLIB
+	select GPIOLIB_IRQCHIP
 	select GENERIC_PINCONF
 	select GENERIC_PINCTRL_GROUPS
 	select GENERIC_PINMUX_FUNCTIONS
diff --git a/drivers/pinctrl/actions/Kconfig b/drivers/pinctrl/actions/Kconfig
index 490927b4ea76..2397cb0f6011 100644
--- a/drivers/pinctrl/actions/Kconfig
+++ b/drivers/pinctrl/actions/Kconfig
@@ -5,6 +5,7 @@ config PINCTRL_OWL
 	select PINCONF
 	select GENERIC_PINCONF
 	select GPIOLIB
+	select GPIOLIB_IRQCHIP
 	help
 	  Say Y here to enable Actions Semi OWL pinctrl driver
 
diff --git a/drivers/pinctrl/actions/pinctrl-owl.c b/drivers/pinctrl/actions/pinctrl-owl.c
index b5c880b50bb3..9d18c02f192b 100644
--- a/drivers/pinctrl/actions/pinctrl-owl.c
+++ b/drivers/pinctrl/actions/pinctrl-owl.c
@@ -13,6 +13,7 @@
 #include <linux/err.h>
 #include <linux/gpio/driver.h>
 #include <linux/io.h>
+#include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
@@ -45,6 +46,9 @@ struct owl_pinctrl {
 	struct clk *clk;
 	const struct owl_pinctrl_soc_data *soc;
 	void __iomem *base;
+	struct irq_chip irq_chip;
+	unsigned int num_irq;
+	unsigned int *irq;
 };
 
 static void owl_update_bits(void __iomem *base, u32 mask, u32 val)
@@ -701,10 +705,213 @@ static int owl_gpio_direction_output(struct gpio_chip *chip,
 	return 0;
 }
 
+static void irq_set_type(struct owl_pinctrl *pctrl, int gpio, unsigned int type)
+{
+	const struct owl_gpio_port *port;
+	void __iomem *gpio_base;
+	unsigned long flags;
+	unsigned int offset, value, irq_type = 0;
+
+	switch (type) {
+	case IRQ_TYPE_EDGE_BOTH:
+		/*
+		 * Since the hardware doesn't support interrupts on both edges,
+		 * emulate it in the software by setting the single edge
+		 * interrupt and switching to the opposite edge while ACKing
+		 * the interrupt
+		 */
+		if (owl_gpio_get(&pctrl->chip, gpio))
+			irq_type = OWL_GPIO_INT_EDGE_FALLING;
+		else
+			irq_type = OWL_GPIO_INT_EDGE_RISING;
+		break;
+
+	case IRQ_TYPE_EDGE_RISING:
+		irq_type = OWL_GPIO_INT_EDGE_RISING;
+		break;
+
+	case IRQ_TYPE_EDGE_FALLING:
+		irq_type = OWL_GPIO_INT_EDGE_FALLING;
+		break;
+
+	case IRQ_TYPE_LEVEL_HIGH:
+		irq_type = OWL_GPIO_INT_LEVEL_HIGH;
+		break;
+
+	case IRQ_TYPE_LEVEL_LOW:
+		irq_type = OWL_GPIO_INT_LEVEL_LOW;
+		break;
+
+	default:
+		break;
+	}
+
+	port = owl_gpio_get_port(pctrl, &gpio);
+	if (WARN_ON(port == NULL))
+		return;
+
+	gpio_base = pctrl->base + port->offset;
+
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
+
+	offset = (gpio < 16) ? 4 : 0;
+	value = readl_relaxed(gpio_base + port->intc_type + offset);
+	value &= ~(OWL_GPIO_INT_MASK << ((gpio % 16) * 2));
+	value |= irq_type << ((gpio % 16) * 2);
+	writel_relaxed(value, gpio_base + port->intc_type + offset);
+
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+}
+
+static void owl_gpio_irq_mask(struct irq_data *data)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(data);
+	struct owl_pinctrl *pctrl = gpiochip_get_data(gc);
+	const struct owl_gpio_port *port;
+	void __iomem *gpio_base;
+	unsigned long flags;
+	unsigned int gpio = data->hwirq;
+	u32 val;
+
+	port = owl_gpio_get_port(pctrl, &gpio);
+	if (WARN_ON(port == NULL))
+		return;
+
+	gpio_base = pctrl->base + port->offset;
+
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
+
+	owl_gpio_update_reg(gpio_base + port->intc_msk, gpio, false);
+
+	/* disable port interrupt if no interrupt pending bit is active */
+	val = readl_relaxed(gpio_base + port->intc_msk);
+	if (val == 0)
+		owl_gpio_update_reg(gpio_base + port->intc_ctl,
+					OWL_GPIO_CTLR_ENABLE, false);
+
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+}
+
+static void owl_gpio_irq_unmask(struct irq_data *data)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(data);
+	struct owl_pinctrl *pctrl = gpiochip_get_data(gc);
+	const struct owl_gpio_port *port;
+	void __iomem *gpio_base;
+	unsigned long flags;
+	unsigned int gpio = data->hwirq;
+	u32 value;
+
+	port = owl_gpio_get_port(pctrl, &gpio);
+	if (WARN_ON(port == NULL))
+		return;
+
+	gpio_base = pctrl->base + port->offset;
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
+
+	/* enable port interrupt */
+	value = readl_relaxed(gpio_base + port->intc_ctl);
+	value |= BIT(OWL_GPIO_CTLR_ENABLE) | BIT(OWL_GPIO_CTLR_SAMPLE_CLK_24M);
+	writel_relaxed(value, gpio_base + port->intc_ctl);
+
+	/* enable GPIO interrupt */
+	owl_gpio_update_reg(gpio_base + port->intc_msk, gpio, true);
+
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+}
+
+static void owl_gpio_irq_ack(struct irq_data *data)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(data);
+	struct owl_pinctrl *pctrl = gpiochip_get_data(gc);
+	const struct owl_gpio_port *port;
+	void __iomem *gpio_base;
+	unsigned long flags;
+	unsigned int gpio = data->hwirq;
+
+	/*
+	 * Switch the interrupt edge to the opposite edge of the interrupt
+	 * which got triggered for the case of emulating both edges
+	 */
+	if (irqd_get_trigger_type(data) == IRQ_TYPE_EDGE_BOTH) {
+		if (owl_gpio_get(gc, gpio))
+			irq_set_type(pctrl, gpio, IRQ_TYPE_EDGE_FALLING);
+		else
+			irq_set_type(pctrl, gpio, IRQ_TYPE_EDGE_RISING);
+	}
+
+	port = owl_gpio_get_port(pctrl, &gpio);
+	if (WARN_ON(port == NULL))
+		return;
+
+	gpio_base = pctrl->base + port->offset;
+
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
+
+	owl_gpio_update_reg(gpio_base + port->intc_ctl,
+				OWL_GPIO_CTLR_PENDING, true);
+
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+}
+
+static int owl_gpio_irq_set_type(struct irq_data *data, unsigned int type)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(data);
+	struct owl_pinctrl *pctrl = gpiochip_get_data(gc);
+
+	if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
+		irq_set_handler_locked(data, handle_level_irq);
+	else
+		irq_set_handler_locked(data, handle_edge_irq);
+
+	irq_set_type(pctrl, data->hwirq, type);
+
+	return 0;
+}
+
+static void owl_gpio_irq_handler(struct irq_desc *desc)
+{
+	struct owl_pinctrl *pctrl = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct irq_domain *domain = pctrl->chip.irq.domain;
+	unsigned int parent = irq_desc_get_irq(desc);
+	const struct owl_gpio_port *port;
+	void __iomem *base;
+	unsigned int pin, irq, offset = 0, i;
+	unsigned long pending_irq;
+
+	chained_irq_enter(chip, desc);
+
+	for (i = 0; i < pctrl->soc->nports; i++) {
+		port = &pctrl->soc->ports[i];
+		base = pctrl->base + port->offset;
+
+		/* skip ports that are not associated with this irq */
+		if (parent != pctrl->irq[i])
+			goto skip;
+
+		pending_irq = readl_relaxed(base + port->intc_pd);
+
+		for_each_set_bit(pin, &pending_irq, port->pins) {
+			irq = irq_find_mapping(domain, offset + pin);
+			generic_handle_irq(irq);
+
+			/* clear pending interrupt */
+			owl_gpio_update_reg(base + port->intc_pd, pin, true);
+		}
+
+skip:
+		offset += port->pins;
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
 static int owl_gpio_init(struct owl_pinctrl *pctrl)
 {
 	struct gpio_chip *chip;
-	int ret;
+	struct gpio_irq_chip *gpio_irq;
+	int ret, i, j, offset;
 
 	chip = &pctrl->chip;
 	chip->base = -1;
@@ -714,6 +921,35 @@ static int owl_gpio_init(struct owl_pinctrl *pctrl)
 	chip->owner = THIS_MODULE;
 	chip->of_node = pctrl->dev->of_node;
 
+	pctrl->irq_chip.name = chip->of_node->name;
+	pctrl->irq_chip.irq_ack = owl_gpio_irq_ack;
+	pctrl->irq_chip.irq_mask = owl_gpio_irq_mask;
+	pctrl->irq_chip.irq_unmask = owl_gpio_irq_unmask;
+	pctrl->irq_chip.irq_set_type = owl_gpio_irq_set_type;
+
+	gpio_irq = &chip->irq;
+	gpio_irq->chip = &pctrl->irq_chip;
+	gpio_irq->handler = handle_simple_irq;
+	gpio_irq->default_type = IRQ_TYPE_NONE;
+	gpio_irq->parent_handler = owl_gpio_irq_handler;
+	gpio_irq->parent_handler_data = pctrl;
+	gpio_irq->num_parents = pctrl->num_irq;
+	gpio_irq->parents = pctrl->irq;
+
+	gpio_irq->map = devm_kcalloc(pctrl->dev, chip->ngpio,
+				sizeof(*gpio_irq->map), GFP_KERNEL);
+	if (!gpio_irq->map)
+		return -ENOMEM;
+
+	for (i = 0, offset = 0; i < pctrl->soc->nports; i++) {
+		const struct owl_gpio_port *port = &pctrl->soc->ports[i];
+
+		for (j = 0; j < port->pins; j++)
+			gpio_irq->map[offset + j] = gpio_irq->parents[i];
+
+		offset += port->pins;
+	}
+
 	ret = gpiochip_add_data(&pctrl->chip, pctrl);
 	if (ret) {
 		dev_err(pctrl->dev, "failed to register gpiochip\n");
@@ -728,7 +964,7 @@ int owl_pinctrl_probe(struct platform_device *pdev,
 {
 	struct resource *res;
 	struct owl_pinctrl *pctrl;
-	int ret;
+	int ret, i;
 
 	pctrl = devm_kzalloc(&pdev->dev, sizeof(*pctrl), GFP_KERNEL);
 	if (!pctrl)
@@ -772,14 +1008,40 @@ int owl_pinctrl_probe(struct platform_device *pdev,
 					&owl_pinctrl_desc, pctrl);
 	if (IS_ERR(pctrl->pctrldev)) {
 		dev_err(&pdev->dev, "could not register Actions OWL pinmux driver\n");
-		return PTR_ERR(pctrl->pctrldev);
+		ret = PTR_ERR(pctrl->pctrldev);
+		goto err_exit;
+	}
+
+	ret = platform_irq_count(pdev);
+	if (ret < 0)
+		goto err_exit;
+
+	pctrl->num_irq = ret;
+
+	pctrl->irq = devm_kcalloc(&pdev->dev, pctrl->num_irq,
+					sizeof(*pctrl->irq), GFP_KERNEL);
+	if (!pctrl->irq) {
+		ret = -ENOMEM;
+		goto err_exit;
+	}
+
+	for (i = 0; i < pctrl->num_irq ; i++) {
+		ret = platform_get_irq(pdev, i);
+		if (ret < 0)
+			goto err_exit;
+		pctrl->irq[i] = ret;
 	}
 
 	ret = owl_gpio_init(pctrl);
 	if (ret)
-		return ret;
+		goto err_exit;
 
 	platform_set_drvdata(pdev, pctrl);
 
 	return 0;
+
+err_exit:
+	clk_disable_unprepare(pctrl->clk);
+
+	return ret;
 }
diff --git a/drivers/pinctrl/actions/pinctrl-owl.h b/drivers/pinctrl/actions/pinctrl-owl.h
index 74342378937c..a724d1d406d4 100644
--- a/drivers/pinctrl/actions/pinctrl-owl.h
+++ b/drivers/pinctrl/actions/pinctrl-owl.h
@@ -29,6 +29,18 @@ enum owl_pinconf_drv {
 	OWL_PINCONF_DRV_12MA,
 };
 
+/* GPIO CTRL Bit Definition */
+#define OWL_GPIO_CTLR_PENDING		0
+#define OWL_GPIO_CTLR_ENABLE		1
+#define OWL_GPIO_CTLR_SAMPLE_CLK_24M	2
+
+/* GPIO TYPE Bit Definition */
+#define OWL_GPIO_INT_LEVEL_HIGH		0
+#define OWL_GPIO_INT_LEVEL_LOW		1
+#define OWL_GPIO_INT_EDGE_RISING	2
+#define OWL_GPIO_INT_EDGE_FALLING	3
+#define OWL_GPIO_INT_MASK		3
+
 /**
  * struct owl_pullctl - Actions pad pull control register
  * @reg: offset to the pull control register
@@ -121,6 +133,10 @@ struct owl_pinmux_func {
  * @outen: offset of the output enable register.
  * @inen: offset of the input enable register.
  * @dat: offset of the data register.
+ * @intc_ctl: offset of the interrupt control register.
+ * @intc_pd: offset of the interrupt pending register.
+ * @intc_msk: offset of the interrupt mask register.
+ * @intc_type: offset of the interrupt type register.
  */
 struct owl_gpio_port {
 	unsigned int offset;
@@ -128,6 +144,10 @@ struct owl_gpio_port {
 	unsigned int outen;
 	unsigned int inen;
 	unsigned int dat;
+	unsigned int intc_ctl;
+	unsigned int intc_pd;
+	unsigned int intc_msk;
+	unsigned int intc_type;
 };
 
 /**
@@ -140,7 +160,7 @@ struct owl_gpio_port {
  * @ngroups: number of entries in @groups.
  * @padinfo: array describing the pad info of this SoC.
  * @ngpios: number of pingroups the driver should expose as GPIOs.
- * @port: array describing all GPIO ports of this SoC.
+ * @ports: array describing all GPIO ports of this SoC.
  * @nports: number of GPIO ports in this SoC.
  */
 struct owl_pinctrl_soc_data {
diff --git a/drivers/pinctrl/actions/pinctrl-s900.c b/drivers/pinctrl/actions/pinctrl-s900.c
index 5503c7945764..ea67b14ef93b 100644
--- a/drivers/pinctrl/actions/pinctrl-s900.c
+++ b/drivers/pinctrl/actions/pinctrl-s900.c
@@ -1821,22 +1821,27 @@ static struct owl_padinfo s900_padinfo[NUM_PADS] = {
 	[SGPIO3] = PAD_INFO_PULLCTL_ST(SGPIO3)
 };
 
-#define OWL_GPIO_PORT(port, base, count, _outen, _inen, _dat)	\
-	[OWL_GPIO_PORT_##port] = {				\
-		.offset = base,					\
-		.pins = count,					\
-		.outen = _outen,				\
-		.inen = _inen,					\
-		.dat = _dat,					\
+#define OWL_GPIO_PORT(port, base, count, _outen, _inen, _dat,		\
+			_intc_ctl, _intc_pd, _intc_msk, _intc_type)	\
+	[OWL_GPIO_PORT_##port] = {					\
+		.offset = base,						\
+		.pins = count,						\
+		.outen = _outen,					\
+		.inen = _inen,						\
+		.dat = _dat,						\
+		.intc_ctl = _intc_ctl,					\
+		.intc_pd = _intc_pd,					\
+		.intc_msk = _intc_msk,					\
+		.intc_type = _intc_type,				\
 	}
 
 static const struct owl_gpio_port s900_gpio_ports[] = {
-	OWL_GPIO_PORT(A, 0x0000, 32, 0x0, 0x4, 0x8),
-	OWL_GPIO_PORT(B, 0x000C, 32, 0x0, 0x4, 0x8),
-	OWL_GPIO_PORT(C, 0x0018, 12, 0x0, 0x4, 0x8),
-	OWL_GPIO_PORT(D, 0x0024, 30, 0x0, 0x4, 0x8),
-	OWL_GPIO_PORT(E, 0x0030, 32, 0x0, 0x4, 0x8),
-	OWL_GPIO_PORT(F, 0x00F0, 8, 0x0, 0x4, 0x8)
+	OWL_GPIO_PORT(A, 0x0000, 32, 0x0, 0x4, 0x8, 0x204, 0x208, 0x20C, 0x240),
+	OWL_GPIO_PORT(B, 0x000C, 32, 0x0, 0x4, 0x8, 0x534, 0x204, 0x208, 0x23C),
+	OWL_GPIO_PORT(C, 0x0018, 12, 0x0, 0x4, 0x8, 0x52C, 0x200, 0x204, 0x238),
+	OWL_GPIO_PORT(D, 0x0024, 30, 0x0, 0x4, 0x8, 0x524, 0x1FC, 0x200, 0x234),
+	OWL_GPIO_PORT(E, 0x0030, 32, 0x0, 0x4, 0x8, 0x51C, 0x1F8, 0x1FC, 0x230),
+	OWL_GPIO_PORT(F, 0x00F0, 8, 0x0, 0x4, 0x8, 0x460, 0x140, 0x144, 0x178)
 };
 
 static struct owl_pinctrl_soc_data s900_pinctrl_data = {
diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed.c b/drivers/pinctrl/aspeed/pinctrl-aspeed.c
index 7f13ce8450a3..aefe3c33dffd 100644
--- a/drivers/pinctrl/aspeed/pinctrl-aspeed.c
+++ b/drivers/pinctrl/aspeed/pinctrl-aspeed.c
@@ -95,7 +95,7 @@ static inline void aspeed_sig_desc_print_val(
  *
  * @desc: The signal descriptor of interest
  * @enabled: True to query the enabled state, false to query disabled state
- * @regmap: The IP block's regmap instance
+ * @map: The IP block's regmap instance
  *
  * Return: 1 if the descriptor's bitfield is configured to the state
  * selected by @enabled, 0 if not, and less than zero if an unrecoverable
@@ -594,7 +594,7 @@ static inline const struct aspeed_pin_config *find_pinconf_config(
 /**
  * @param: pinconf configuration parameter
  * @arg: The supported argument for @param, or -1 if any value is supported
- * @value: The register value to write to configure @arg for @param
+ * @val: The register value to write to configure @arg for @param
  *
  * The map is to be used in conjunction with the configuration array supplied
  * by the driver implementation.
diff --git a/drivers/pinctrl/berlin/Kconfig b/drivers/pinctrl/berlin/Kconfig
index 8fe6ad7795dc..0dd60278e973 100644
--- a/drivers/pinctrl/berlin/Kconfig
+++ b/drivers/pinctrl/berlin/Kconfig
@@ -5,6 +5,11 @@ config PINCTRL_BERLIN
 	select PINMUX
 	select REGMAP_MMIO
 
+config PINCTRL_AS370
+	bool "Synaptics as370 pin controller driver"
+	depends on OF
+	select PINCTRL_BERLIN
+
 config PINCTRL_BERLIN_BG2
 	def_bool MACH_BERLIN_BG2
 	depends on OF
diff --git a/drivers/pinctrl/berlin/Makefile b/drivers/pinctrl/berlin/Makefile
index 6f641ce2c830..00c53ca3676d 100644
--- a/drivers/pinctrl/berlin/Makefile
+++ b/drivers/pinctrl/berlin/Makefile
@@ -3,3 +3,4 @@ obj-$(CONFIG_PINCTRL_BERLIN_BG2)	+= berlin-bg2.o
 obj-$(CONFIG_PINCTRL_BERLIN_BG2CD)	+= berlin-bg2cd.o
 obj-$(CONFIG_PINCTRL_BERLIN_BG2Q)	+= berlin-bg2q.o
 obj-$(CONFIG_PINCTRL_BERLIN_BG4CT)	+= berlin-bg4ct.o
+obj-$(CONFIG_PINCTRL_AS370)		+= pinctrl-as370.o
diff --git a/drivers/pinctrl/berlin/berlin.c b/drivers/pinctrl/berlin/berlin.c
index d6d183e9db17..b5903fffb3d0 100644
--- a/drivers/pinctrl/berlin/berlin.c
+++ b/drivers/pinctrl/berlin/berlin.c
@@ -216,10 +216,8 @@ static int berlin_pinctrl_build_state(struct platform_device *pdev)
 	}
 
 	/* we will reallocate later */
-	pctrl->functions = devm_kcalloc(&pdev->dev,
-					max_functions,
-					sizeof(*pctrl->functions),
-					GFP_KERNEL);
+	pctrl->functions = kcalloc(max_functions,
+				   sizeof(*pctrl->functions), GFP_KERNEL);
 	if (!pctrl->functions)
 		return -ENOMEM;
 
@@ -257,8 +255,10 @@ static int berlin_pinctrl_build_state(struct platform_device *pdev)
 				function++;
 			}
 
-			if (!found)
+			if (!found) {
+				kfree(pctrl->functions);
 				return -EINVAL;
+			}
 
 			if (!function->groups) {
 				function->groups =
@@ -267,8 +267,10 @@ static int berlin_pinctrl_build_state(struct platform_device *pdev)
 						     sizeof(char *),
 						     GFP_KERNEL);
 
-				if (!function->groups)
+				if (!function->groups) {
+					kfree(pctrl->functions);
 					return -ENOMEM;
+				}
 			}
 
 			groups = function->groups;
diff --git a/drivers/pinctrl/berlin/pinctrl-as370.c b/drivers/pinctrl/berlin/pinctrl-as370.c
new file mode 100644
index 000000000000..d2bb811fc5fa
--- /dev/null
+++ b/drivers/pinctrl/berlin/pinctrl-as370.c
@@ -0,0 +1,368 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Synaptics AS370 pinctrl driver
+ *
+ * Copyright (C) 2018 Synaptics Incorporated
+ *
+ * Author: Jisheng Zhang <jszhang@kernel.org>
+ */
+
+#include <linux/init.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include "berlin.h"
+
+static const struct berlin_desc_group as370_soc_pinctrl_groups[] = {
+	BERLIN_PINCTRL_GROUP("I2S1_BCLKIO", 0x0, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO0 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* BCLKIO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG0 */
+	BERLIN_PINCTRL_GROUP("I2S1_LRCKIO", 0x0, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO1 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* LRCKIO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG1 */
+	BERLIN_PINCTRL_GROUP("I2S1_DO0", 0x0, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "por"), /* 1P8V RSTB*/
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* DO0 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio"), /* GPIO2 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG2 */
+	BERLIN_PINCTRL_GROUP("I2S1_DO1", 0x0, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "por"), /* 3P3V RSTB */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* DO1 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio"), /* GPIO3 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG3 */
+	BERLIN_PINCTRL_GROUP("I2S1_DO2", 0x0, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "por"), /* CORE RSTB */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* DO2 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm4"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio"), /* GPIO4 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG4 */
+	BERLIN_PINCTRL_GROUP("I2S1_DO3", 0x0, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO5 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* DO3 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm5"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "spififib"), /* SPDIFIB */
+			BERLIN_PINCTRL_FUNCTION(0x4, "spdifo"), /* SPDIFO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG5 */
+	BERLIN_PINCTRL_GROUP("I2S1_MCLK", 0x0, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO6 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* MCLK */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG6 */
+	BERLIN_PINCTRL_GROUP("I2S2_BCLKIO", 0x0, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO7 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s2"), /* BCLKIO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG7 */
+	BERLIN_PINCTRL_GROUP("I2S2_LRCKIO", 0x0, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO8 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s2"), /* LRCKIO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG8 */
+	BERLIN_PINCTRL_GROUP("I2S2_DI0", 0x0, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO9 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s2"), /* DI0 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm2"),
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG9 */
+	BERLIN_PINCTRL_GROUP("I2S2_DI1", 0x4, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO10 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s2"), /* DI1 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm3"),
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG10 */
+	BERLIN_PINCTRL_GROUP("I2S2_DI2", 0x4, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO11 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s2"), /* DI2 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm6"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "spdific"), /* SPDIFIC */
+			BERLIN_PINCTRL_FUNCTION(0x4, "spdifo"), /* SPDIFO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG11 */
+	BERLIN_PINCTRL_GROUP("I2S2_DI3", 0x4, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO12 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s2"), /* DI3 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm7"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "spdifia"), /* SPDIFIA */
+			BERLIN_PINCTRL_FUNCTION(0x4, "spdifo"), /* SPDIFO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG12 */
+	BERLIN_PINCTRL_GROUP("PDM_CLKO", 0x4, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO13 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pdm"), /* CLKO */
+			BERLIN_PINCTRL_FUNCTION(0x2, "i2s2"), /* MCLK */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG13 */
+	BERLIN_PINCTRL_GROUP("PDM_DI0", 0x4, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO14 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pdm"), /* DI0 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG14 */
+	BERLIN_PINCTRL_GROUP("PDM_DI1", 0x4, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO15 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pdm"), /* DI1 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG15 */
+	BERLIN_PINCTRL_GROUP("PDM_DI2", 0x4, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO16 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pdm"), /* DI2 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm4"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "spdifid"), /* SPDIFID */
+			BERLIN_PINCTRL_FUNCTION(0x4, "spdifo"), /* SPDIFO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG16 */
+	BERLIN_PINCTRL_GROUP("PDM_DI3", 0x4, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO17 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pdm"), /* DI3 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm5"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "spdifi"), /* SPDIFI */
+			BERLIN_PINCTRL_FUNCTION(0x4, "spdifo"), /* SPDIFO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG17 */
+	BERLIN_PINCTRL_GROUP("NAND_IO0", 0x4, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO0 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* DATA0 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pcie0")), /* MDIO */
+	BERLIN_PINCTRL_GROUP("NAND_IO1", 0x4, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO1 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* DATA1 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pcie0")), /* MDC */
+	BERLIN_PINCTRL_GROUP("NAND_IO2", 0x8, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO2 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* DATA2 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pcie1")), /* MDIO */
+	BERLIN_PINCTRL_GROUP("NAND_IO3", 0x8, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO3 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* DATA3 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pcie1")), /* MDC */
+	BERLIN_PINCTRL_GROUP("NAND_IO4", 0x8, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO4 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc")), /* DATA4 */
+	BERLIN_PINCTRL_GROUP("NAND_IO5", 0x8, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO5 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc")), /* DATA5 */
+	BERLIN_PINCTRL_GROUP("NAND_IO6", 0x8, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO6 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc")), /* DATA6 */
+	BERLIN_PINCTRL_GROUP("NAND_IO7", 0x8, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO7 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc")), /* DATA7 */
+	BERLIN_PINCTRL_GROUP("NAND_ALE", 0x8, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* ALE */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm6"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO18 */
+	BERLIN_PINCTRL_GROUP("NAND_CLE", 0x8, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* CLE */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm7"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO19 */
+	BERLIN_PINCTRL_GROUP("NAND_WEn", 0x8, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* WEn */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO20 */
+	BERLIN_PINCTRL_GROUP("NAND_REn", 0x8, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* REn */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO21 */
+	BERLIN_PINCTRL_GROUP("NAND_WPn", 0xc, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* WPn */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* CLK */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO22 */
+	BERLIN_PINCTRL_GROUP("NAND_CEn", 0xc, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* CEn */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* RSTn */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO23 */
+	BERLIN_PINCTRL_GROUP("NAND_RDY", 0xc, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* RDY */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* CMD */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO24 */
+	BERLIN_PINCTRL_GROUP("SPI1_SS0n", 0xc, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SS0n */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio")), /* GPIO25 */
+	BERLIN_PINCTRL_GROUP("SPI1_SS1n", 0xc, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SS1n */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio"), /* GPIO26 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "pwm2")),
+	BERLIN_PINCTRL_GROUP("SPI1_SS2n", 0xc, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "uart0"), /* RXD */
+			BERLIN_PINCTRL_FUNCTION(0x1, "spi1"), /* SS2n */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio"), /* GPIO27 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "pwm3")),
+	BERLIN_PINCTRL_GROUP("SPI1_SS3n", 0xc, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "uart0"), /* TXD */
+			BERLIN_PINCTRL_FUNCTION(0x1, "spi1"), /* SS3n */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO28 */
+	BERLIN_PINCTRL_GROUP("SPI1_SCLK", 0xc, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SCLK */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO29 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "pwm4")),
+	BERLIN_PINCTRL_GROUP("SPI1_SDO", 0xc, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SDO */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO30 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "pwm5")),
+	BERLIN_PINCTRL_GROUP("SPI1_SDI", 0xc, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SDI */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio")), /* GPIO31 */
+	BERLIN_PINCTRL_GROUP("USB0_DRV_VBUS", 0x10, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "usb0"), /* VBUS */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO32 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "refclko")), /* 25M */
+	BERLIN_PINCTRL_GROUP("TW1_SCL", 0x10, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO33 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "tw1")), /* SCL */
+	BERLIN_PINCTRL_GROUP("TW1_SDA", 0x10, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO34 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "tw1")), /* SDA */
+	BERLIN_PINCTRL_GROUP("TW0_SCL", 0x10, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO35 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "tw0")), /* SCL */
+	BERLIN_PINCTRL_GROUP("TW0_SDA", 0x10, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO36 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "tw0")), /* SDA */
+	BERLIN_PINCTRL_GROUP("TMS", 0x10, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "jtag"), /* TMS */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO37 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pwm0")),
+	BERLIN_PINCTRL_GROUP("TDI", 0x10, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "jtag"), /* TDI */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO38 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pwm1")),
+	BERLIN_PINCTRL_GROUP("TDO", 0x10, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "jtag"), /* TDO */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO39 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pwm0")),
+	BERLIN_PINCTRL_GROUP("PWM6", 0x10, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO40 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm6")),
+	BERLIN_PINCTRL_GROUP("PWM7", 0x10, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO41 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm7")),
+	BERLIN_PINCTRL_GROUP("PWM0", 0x14, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "por"), /* VDDCPUSOC RSTB */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm0"),
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO42 */
+	BERLIN_PINCTRL_GROUP("PWM1", 0x14, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO43 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm1")),
+	BERLIN_PINCTRL_GROUP("PWM2", 0x14, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO44 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm2")),
+	BERLIN_PINCTRL_GROUP("PWM3", 0x14, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO45 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm3")),
+	BERLIN_PINCTRL_GROUP("PWM4", 0x14, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO46 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm4")),
+	BERLIN_PINCTRL_GROUP("PWM5", 0x14, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO47 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm5")),
+	BERLIN_PINCTRL_GROUP("URT1_RTSn", 0x14, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO48 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "uart1"), /* RTSn */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm6"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "tw1a"), /* SCL */
+			BERLIN_PINCTRL_FUNCTION(0x4, "aio"), /* DBG0 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG18 */
+	BERLIN_PINCTRL_GROUP("URT1_CTSn", 0x14, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO49 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "uart1"), /* CTSn */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm7"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "tw1a"), /* SDA */
+			BERLIN_PINCTRL_FUNCTION(0x4, "aio"), /* DBG1 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG19 */
+	BERLIN_PINCTRL_GROUP("URT1_RXD", 0x14, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO50 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "uart1"), /* RXD */
+			BERLIN_PINCTRL_FUNCTION(0x4, "aio"), /* DBG2 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG20 */
+	BERLIN_PINCTRL_GROUP("URT1_TXD", 0x14, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO51 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "uart1"), /* TXD */
+			BERLIN_PINCTRL_FUNCTION(0x4, "aio"), /* DBG3 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG21 */
+	BERLIN_PINCTRL_GROUP("I2S3_DI", 0x18, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO52 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s3"), /* DI */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG22 */
+	BERLIN_PINCTRL_GROUP("I2S3_DO", 0x18, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO53 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s3"), /* DO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG23 */
+	BERLIN_PINCTRL_GROUP("I2S3_BCLKIO", 0x18, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO54 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s3"), /* BCLKIO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "clk")), /* DBG */
+	BERLIN_PINCTRL_GROUP("I2S3_LRCKIO", 0x18, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO55 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s3")), /* LRCKIO */
+	BERLIN_PINCTRL_GROUP("SD0_DAT0", 0x18, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "cpupll"), /* OUT */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* DAT0 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO56 */
+	BERLIN_PINCTRL_GROUP("SD0_DAT1", 0x18, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "syspll"), /* OUT */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* DAT1 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO57 */
+	BERLIN_PINCTRL_GROUP("SD0_CLK", 0x18, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO58 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0")), /* CLK */
+	BERLIN_PINCTRL_GROUP("SD0_DAT2", 0x18, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "mempll"), /* OUT */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* DAT2 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO59 */
+	BERLIN_PINCTRL_GROUP("SD0_DAT3", 0x18, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "apll0"), /* OUT */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* DAT3 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO60 */
+	BERLIN_PINCTRL_GROUP("SD0_CMD", 0x18, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "apll1"), /* OUT */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* CMD */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO61 */
+	BERLIN_PINCTRL_GROUP("SD0_CDn", 0x1c, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO62 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* CDn */
+			BERLIN_PINCTRL_FUNCTION(0x3, "pwm2")),
+	BERLIN_PINCTRL_GROUP("SD0_WP", 0x1c, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO63 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* WP */
+			BERLIN_PINCTRL_FUNCTION(0x3, "pwm3")),
+};
+
+static const struct berlin_pinctrl_desc as370_soc_pinctrl_data = {
+	.groups = as370_soc_pinctrl_groups,
+	.ngroups = ARRAY_SIZE(as370_soc_pinctrl_groups),
+};
+
+static const struct of_device_id as370_pinctrl_match[] = {
+	{
+		.compatible = "syna,as370-soc-pinctrl",
+		.data = &as370_soc_pinctrl_data,
+	},
+	{}
+};
+
+static int as370_pinctrl_probe(struct platform_device *pdev)
+{
+	const struct of_device_id *match =
+		of_match_device(as370_pinctrl_match, &pdev->dev);
+	struct regmap_config *rmconfig;
+	struct regmap *regmap;
+	struct resource *res;
+	void __iomem *base;
+
+	rmconfig = devm_kzalloc(&pdev->dev, sizeof(*rmconfig), GFP_KERNEL);
+	if (!rmconfig)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	rmconfig->reg_bits = 32,
+	rmconfig->val_bits = 32,
+	rmconfig->reg_stride = 4,
+	rmconfig->max_register = resource_size(res);
+
+	regmap = devm_regmap_init_mmio(&pdev->dev, base, rmconfig);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	return berlin_pinctrl_probe_regmap(pdev, match->data, regmap);
+}
+
+static struct platform_driver as370_pinctrl_driver = {
+	.probe	= as370_pinctrl_probe,
+	.driver	= {
+		.name = "as370-pinctrl",
+		.of_match_table = as370_pinctrl_match,
+	},
+};
+builtin_platform_driver(as370_pinctrl_driver);
diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index e5a303002021..a3dd777e3ce8 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -21,7 +21,6 @@
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/list.h>
-#include <linux/sysfs.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/pinctrl/consumer.h>
@@ -617,6 +616,26 @@ struct group_desc *pinctrl_generic_get_group(struct pinctrl_dev *pctldev,
 }
 EXPORT_SYMBOL_GPL(pinctrl_generic_get_group);
 
+static int pinctrl_generic_group_name_to_selector(struct pinctrl_dev *pctldev,
+						  const char *function)
+{
+	const struct pinctrl_ops *ops = pctldev->desc->pctlops;
+	int ngroups = ops->get_groups_count(pctldev);
+	int selector = 0;
+
+	/* See if this pctldev has this group */
+	while (selector < ngroups) {
+		const char *gname = ops->get_group_name(pctldev, selector);
+
+		if (!strcmp(function, gname))
+			return selector;
+
+		selector++;
+	}
+
+	return -EINVAL;
+}
+
 /**
  * pinctrl_generic_add_group() - adds a new pin group
  * @pctldev: pin controller device
@@ -631,6 +650,16 @@ int pinctrl_generic_add_group(struct pinctrl_dev *pctldev, const char *name,
 			      int *pins, int num_pins, void *data)
 {
 	struct group_desc *group;
+	int selector;
+
+	if (!name)
+		return -EINVAL;
+
+	selector = pinctrl_generic_group_name_to_selector(pctldev, name);
+	if (selector >= 0)
+		return selector;
+
+	selector = pctldev->num_groups;
 
 	group = devm_kzalloc(pctldev->dev, sizeof(*group), GFP_KERNEL);
 	if (!group)
@@ -641,12 +670,11 @@ int pinctrl_generic_add_group(struct pinctrl_dev *pctldev, const char *name,
 	group->num_pins = num_pins;
 	group->data = data;
 
-	radix_tree_insert(&pctldev->pin_group_tree, pctldev->num_groups,
-			  group);
+	radix_tree_insert(&pctldev->pin_group_tree, selector, group);
 
 	pctldev->num_groups++;
 
-	return 0;
+	return selector;
 }
 EXPORT_SYMBOL_GPL(pinctrl_generic_add_group);
 
diff --git a/drivers/pinctrl/core.h b/drivers/pinctrl/core.h
index 8cf2eba17c8c..4a0526e567df 100644
--- a/drivers/pinctrl/core.h
+++ b/drivers/pinctrl/core.h
@@ -218,12 +218,6 @@ int pinctrl_generic_add_group(struct pinctrl_dev *pctldev, const char *name,
 int pinctrl_generic_remove_group(struct pinctrl_dev *pctldev,
 				 unsigned int group_selector);
 
-static inline int
-pinctrl_generic_remove_last_group(struct pinctrl_dev *pctldev)
-{
-	return pinctrl_generic_remove_group(pctldev, pctldev->num_groups - 1);
-}
-
 #endif	/* CONFIG_GENERIC_PINCTRL_GROUPS */
 
 struct pinctrl_dev *get_pinctrl_dev_from_devname(const char *dev_name);
diff --git a/drivers/pinctrl/freescale/Kconfig b/drivers/pinctrl/freescale/Kconfig
index 0d8ba1ef5329..dccf64c55498 100644
--- a/drivers/pinctrl/freescale/Kconfig
+++ b/drivers/pinctrl/freescale/Kconfig
@@ -117,6 +117,13 @@ config PINCTRL_IMX7ULP
 	help
 	  Say Y here to enable the imx7ulp pinctrl driver
 
+config PINCTRL_IMX8MQ
+	bool "IMX8MQ pinctrl driver"
+	depends on SOC_IMX8MQ
+	select PINCTRL_IMX
+	help
+	  Say Y here to enable the imx8mq pinctrl driver
+
 config PINCTRL_VF610
 	bool "Freescale Vybrid VF610 pinctrl driver"
 	depends on SOC_VF610
diff --git a/drivers/pinctrl/freescale/Makefile b/drivers/pinctrl/freescale/Makefile
index 368be8cfc9b1..73175b3e7c9c 100644
--- a/drivers/pinctrl/freescale/Makefile
+++ b/drivers/pinctrl/freescale/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_PINCTRL_IMX6SX)	+= pinctrl-imx6sx.o
 obj-$(CONFIG_PINCTRL_IMX6UL)	+= pinctrl-imx6ul.o
 obj-$(CONFIG_PINCTRL_IMX7D)	+= pinctrl-imx7d.o
 obj-$(CONFIG_PINCTRL_IMX7ULP)	+= pinctrl-imx7ulp.o
+obj-$(CONFIG_PINCTRL_IMX8MQ)	+= pinctrl-imx8mq.o
 obj-$(CONFIG_PINCTRL_VF610)	+= pinctrl-vf610.o
 obj-$(CONFIG_PINCTRL_MXS)	+= pinctrl-mxs.o
 obj-$(CONFIG_PINCTRL_IMX23)	+= pinctrl-imx23.o
diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index 1c6bb15579e1..b04edc22dad7 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -383,7 +383,7 @@ static void imx_pinconf_group_dbg_show(struct pinctrl_dev *pctldev,
 	const char *name;
 	int i, ret;
 
-	if (group > pctldev->num_groups)
+	if (group >= pctldev->num_groups)
 		return;
 
 	seq_puts(s, "\n");
diff --git a/drivers/pinctrl/freescale/pinctrl-imx1-core.c b/drivers/pinctrl/freescale/pinctrl-imx1-core.c
index c3bdd90b1422..deb7870b3d1a 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx1-core.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx1-core.c
@@ -429,7 +429,7 @@ static void imx1_pinconf_group_dbg_show(struct pinctrl_dev *pctldev,
 	const char *name;
 	int i, ret;
 
-	if (group > info->ngroups)
+	if (group >= info->ngroups)
 		return;
 
 	seq_puts(s, "\n");
diff --git a/drivers/pinctrl/freescale/pinctrl-imx8mq.c b/drivers/pinctrl/freescale/pinctrl-imx8mq.c
new file mode 100644
index 000000000000..8d39af541d5f
--- /dev/null
+++ b/drivers/pinctrl/freescale/pinctrl-imx8mq.c
@@ -0,0 +1,351 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2016 Freescale Semiconductor, Inc.
+ * Copyright 2017-2018 NXP
+ * Copyright (C) 2018 Pengutronix, Lucas Stach <kernel@pengutronix.de>
+ */
+
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/pinctrl/pinctrl.h>
+
+#include "pinctrl-imx.h"
+
+enum imx8mq_pads {
+	MX8MQ_PAD_RESERVE0 = 0,
+	MX8MQ_PAD_RESERVE1 = 1,
+	MX8MQ_PAD_RESERVE2 = 2,
+	MX8MQ_PAD_RESERVE3 = 3,
+	MX8MQ_PAD_RESERVE4 = 4,
+	MX8MQ_IOMUXC_PMIC_STBY_REQ_CCMSRCGPCMIX = 5,
+	MX8MQ_IOMUXC_PMIC_ON_REQ_SNVSMIX = 6,
+	MX8MQ_IOMUXC_ONOFF_SNVSMIX = 7,
+	MX8MQ_IOMUXC_POR_B_SNVSMIX = 8,
+	MX8MQ_IOMUXC_RTC_RESET_B_SNVSMIX = 9,
+	MX8MQ_IOMUXC_GPIO1_IO00 = 10,
+	MX8MQ_IOMUXC_GPIO1_IO01 = 11,
+	MX8MQ_IOMUXC_GPIO1_IO02 = 12,
+	MX8MQ_IOMUXC_GPIO1_IO03 = 13,
+	MX8MQ_IOMUXC_GPIO1_IO04 = 14,
+	MX8MQ_IOMUXC_GPIO1_IO05 = 15,
+	MX8MQ_IOMUXC_GPIO1_IO06 = 16,
+	MX8MQ_IOMUXC_GPIO1_IO07 = 17,
+	MX8MQ_IOMUXC_GPIO1_IO08 = 18,
+	MX8MQ_IOMUXC_GPIO1_IO09 = 19,
+	MX8MQ_IOMUXC_GPIO1_IO10 = 20,
+	MX8MQ_IOMUXC_GPIO1_IO11 = 21,
+	MX8MQ_IOMUXC_GPIO1_IO12 = 22,
+	MX8MQ_IOMUXC_GPIO1_IO13 = 23,
+	MX8MQ_IOMUXC_GPIO1_IO14 = 24,
+	MX8MQ_IOMUXC_GPIO1_IO15 = 25,
+	MX8MQ_IOMUXC_ENET_MDC = 26,
+	MX8MQ_IOMUXC_ENET_MDIO = 27,
+	MX8MQ_IOMUXC_ENET_TD3 = 28,
+	MX8MQ_IOMUXC_ENET_TD2 = 29,
+	MX8MQ_IOMUXC_ENET_TD1 = 30,
+	MX8MQ_IOMUXC_ENET_TD0 = 31,
+	MX8MQ_IOMUXC_ENET_TX_CTL = 32,
+	MX8MQ_IOMUXC_ENET_TXC = 33,
+	MX8MQ_IOMUXC_ENET_RX_CTL = 34,
+	MX8MQ_IOMUXC_ENET_RXC = 35,
+	MX8MQ_IOMUXC_ENET_RD0 = 36,
+	MX8MQ_IOMUXC_ENET_RD1 = 37,
+	MX8MQ_IOMUXC_ENET_RD2 = 38,
+	MX8MQ_IOMUXC_ENET_RD3 = 39,
+	MX8MQ_IOMUXC_SD1_CLK = 40,
+	MX8MQ_IOMUXC_SD1_CMD = 41,
+	MX8MQ_IOMUXC_SD1_DATA0 = 42,
+	MX8MQ_IOMUXC_SD1_DATA1 = 43,
+	MX8MQ_IOMUXC_SD1_DATA2 = 44,
+	MX8MQ_IOMUXC_SD1_DATA3 = 45,
+	MX8MQ_IOMUXC_SD1_DATA4 = 46,
+	MX8MQ_IOMUXC_SD1_DATA5 = 47,
+	MX8MQ_IOMUXC_SD1_DATA6 = 48,
+	MX8MQ_IOMUXC_SD1_DATA7 = 49,
+	MX8MQ_IOMUXC_SD1_RESET_B = 50,
+	MX8MQ_IOMUXC_SD1_STROBE = 51,
+	MX8MQ_IOMUXC_SD2_CD_B = 52,
+	MX8MQ_IOMUXC_SD2_CLK = 53,
+	MX8MQ_IOMUXC_SD2_CMD = 54,
+	MX8MQ_IOMUXC_SD2_DATA0 = 55,
+	MX8MQ_IOMUXC_SD2_DATA1 = 56,
+	MX8MQ_IOMUXC_SD2_DATA2 = 57,
+	MX8MQ_IOMUXC_SD2_DATA3 = 58,
+	MX8MQ_IOMUXC_SD2_RESET_B = 59,
+	MX8MQ_IOMUXC_SD2_WP = 60,
+	MX8MQ_IOMUXC_NAND_ALE = 61,
+	MX8MQ_IOMUXC_NAND_CE0_B = 62,
+	MX8MQ_IOMUXC_NAND_CE1_B = 63,
+	MX8MQ_IOMUXC_NAND_CE2_B = 64,
+	MX8MQ_IOMUXC_NAND_CE3_B = 65,
+	MX8MQ_IOMUXC_NAND_CLE = 66,
+	MX8MQ_IOMUXC_NAND_DATA00 = 67,
+	MX8MQ_IOMUXC_NAND_DATA01 = 68,
+	MX8MQ_IOMUXC_NAND_DATA02 = 69,
+	MX8MQ_IOMUXC_NAND_DATA03 = 70,
+	MX8MQ_IOMUXC_NAND_DATA04 = 71,
+	MX8MQ_IOMUXC_NAND_DATA05 = 72,
+	MX8MQ_IOMUXC_NAND_DATA06 = 73,
+	MX8MQ_IOMUXC_NAND_DATA07 = 74,
+	MX8MQ_IOMUXC_NAND_DQS = 75,
+	MX8MQ_IOMUXC_NAND_RE_B = 76,
+	MX8MQ_IOMUXC_NAND_READY_B = 77,
+	MX8MQ_IOMUXC_NAND_WE_B = 78,
+	MX8MQ_IOMUXC_NAND_WP_B = 79,
+	MX8MQ_IOMUXC_SAI5_RXFS = 80,
+	MX8MQ_IOMUXC_SAI5_RXC = 81,
+	MX8MQ_IOMUXC_SAI5_RXD0 = 82,
+	MX8MQ_IOMUXC_SAI5_RXD1 = 83,
+	MX8MQ_IOMUXC_SAI5_RXD2 = 84,
+	MX8MQ_IOMUXC_SAI5_RXD3 = 85,
+	MX8MQ_IOMUXC_SAI5_MCLK = 86,
+	MX8MQ_IOMUXC_SAI1_RXFS = 87,
+	MX8MQ_IOMUXC_SAI1_RXC = 88,
+	MX8MQ_IOMUXC_SAI1_RXD0 = 89,
+	MX8MQ_IOMUXC_SAI1_RXD1 = 90,
+	MX8MQ_IOMUXC_SAI1_RXD2 = 91,
+	MX8MQ_IOMUXC_SAI1_RXD3 = 92,
+	MX8MQ_IOMUXC_SAI1_RXD4 = 93,
+	MX8MQ_IOMUXC_SAI1_RXD5 = 94,
+	MX8MQ_IOMUXC_SAI1_RXD6 = 95,
+	MX8MQ_IOMUXC_SAI1_RXD7 = 96,
+	MX8MQ_IOMUXC_SAI1_TXFS = 97,
+	MX8MQ_IOMUXC_SAI1_TXC = 98,
+	MX8MQ_IOMUXC_SAI1_TXD0 = 99,
+	MX8MQ_IOMUXC_SAI1_TXD1 = 100,
+	MX8MQ_IOMUXC_SAI1_TXD2 = 101,
+	MX8MQ_IOMUXC_SAI1_TXD3 = 102,
+	MX8MQ_IOMUXC_SAI1_TXD4 = 103,
+	MX8MQ_IOMUXC_SAI1_TXD5 = 104,
+	MX8MQ_IOMUXC_SAI1_TXD6 = 105,
+	MX8MQ_IOMUXC_SAI1_TXD7 = 106,
+	MX8MQ_IOMUXC_SAI1_MCLK = 107,
+	MX8MQ_IOMUXC_SAI2_RXFS = 108,
+	MX8MQ_IOMUXC_SAI2_RXC = 109,
+	MX8MQ_IOMUXC_SAI2_RXD0 = 110,
+	MX8MQ_IOMUXC_SAI2_TXFS = 111,
+	MX8MQ_IOMUXC_SAI2_TXC = 112,
+	MX8MQ_IOMUXC_SAI2_TXD0 = 113,
+	MX8MQ_IOMUXC_SAI2_MCLK = 114,
+	MX8MQ_IOMUXC_SAI3_RXFS = 115,
+	MX8MQ_IOMUXC_SAI3_RXC = 116,
+	MX8MQ_IOMUXC_SAI3_RXD = 117,
+	MX8MQ_IOMUXC_SAI3_TXFS = 118,
+	MX8MQ_IOMUXC_SAI3_TXC = 119,
+	MX8MQ_IOMUXC_SAI3_TXD = 120,
+	MX8MQ_IOMUXC_SAI3_MCLK = 121,
+	MX8MQ_IOMUXC_SPDIF_TX = 122,
+	MX8MQ_IOMUXC_SPDIF_RX = 123,
+	MX8MQ_IOMUXC_SPDIF_EXT_CLK = 124,
+	MX8MQ_IOMUXC_ECSPI1_SCLK = 125,
+	MX8MQ_IOMUXC_ECSPI1_MOSI = 126,
+	MX8MQ_IOMUXC_ECSPI1_MISO = 127,
+	MX8MQ_IOMUXC_ECSPI1_SS0 = 128,
+	MX8MQ_IOMUXC_ECSPI2_SCLK = 129,
+	MX8MQ_IOMUXC_ECSPI2_MOSI = 130,
+	MX8MQ_IOMUXC_ECSPI2_MISO = 131,
+	MX8MQ_IOMUXC_ECSPI2_SS0 = 132,
+	MX8MQ_IOMUXC_I2C1_SCL = 133,
+	MX8MQ_IOMUXC_I2C1_SDA = 134,
+	MX8MQ_IOMUXC_I2C2_SCL = 135,
+	MX8MQ_IOMUXC_I2C2_SDA = 136,
+	MX8MQ_IOMUXC_I2C3_SCL = 137,
+	MX8MQ_IOMUXC_I2C3_SDA = 138,
+	MX8MQ_IOMUXC_I2C4_SCL = 139,
+	MX8MQ_IOMUXC_I2C4_SDA = 140,
+	MX8MQ_IOMUXC_UART1_RXD = 141,
+	MX8MQ_IOMUXC_UART1_TXD = 142,
+	MX8MQ_IOMUXC_UART2_RXD = 143,
+	MX8MQ_IOMUXC_UART2_TXD = 144,
+	MX8MQ_IOMUXC_UART3_RXD = 145,
+	MX8MQ_IOMUXC_UART3_TXD = 146,
+	MX8MQ_IOMUXC_UART4_RXD = 147,
+	MX8MQ_IOMUXC_UART4_TXD = 148,
+};
+
+/* Pad names for the pinmux subsystem */
+static const struct pinctrl_pin_desc imx8mq_pinctrl_pads[] = {
+	IMX_PINCTRL_PIN(MX8MQ_PAD_RESERVE0),
+	IMX_PINCTRL_PIN(MX8MQ_PAD_RESERVE1),
+	IMX_PINCTRL_PIN(MX8MQ_PAD_RESERVE2),
+	IMX_PINCTRL_PIN(MX8MQ_PAD_RESERVE3),
+	IMX_PINCTRL_PIN(MX8MQ_PAD_RESERVE4),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_PMIC_STBY_REQ_CCMSRCGPCMIX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_PMIC_ON_REQ_SNVSMIX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ONOFF_SNVSMIX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_POR_B_SNVSMIX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_RTC_RESET_B_SNVSMIX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO00),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO01),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO02),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO03),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO04),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO05),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO06),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO07),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO08),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO09),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO10),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO11),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO12),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO13),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO14),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO15),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_MDC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_MDIO),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_TD3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_TD2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_TD1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_TD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_TX_CTL),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_TXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_RX_CTL),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_RXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_RD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_RD1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_RD2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_RD3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_CLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_CMD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA4),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA5),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA6),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA7),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_RESET_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_STROBE),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_CD_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_CLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_CMD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_DATA0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_DATA1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_DATA2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_DATA3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_RESET_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_WP),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_ALE),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_CE0_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_CE1_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_CE2_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_CE3_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_CLE),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA00),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA01),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA02),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA03),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA04),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA05),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA06),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA07),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DQS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_RE_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_READY_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_WE_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_WP_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_RXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_RXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_RXD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_RXD1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_RXD2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_RXD3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_MCLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD4),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD5),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD6),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD7),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD4),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD5),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD6),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD7),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_MCLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_RXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_RXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_RXD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_TXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_TXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_TXD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_MCLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_RXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_RXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_RXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_TXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_TXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_TXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_MCLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SPDIF_TX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SPDIF_RX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SPDIF_EXT_CLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI1_SCLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI1_MOSI),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI1_MISO),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI1_SS0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI2_SCLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI2_MOSI),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI2_MISO),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI2_SS0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C1_SCL),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C1_SDA),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C2_SCL),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C2_SDA),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C3_SCL),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C3_SDA),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C4_SCL),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C4_SDA),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART1_RXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART1_TXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART2_RXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART2_TXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART3_RXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART3_TXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART4_RXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART4_TXD),
+};
+
+static const struct imx_pinctrl_soc_info imx8mq_pinctrl_info = {
+	.pins = imx8mq_pinctrl_pads,
+	.npins = ARRAY_SIZE(imx8mq_pinctrl_pads),
+	.gpr_compatible = "fsl,imx8mq-iomuxc-gpr",
+};
+
+static const struct of_device_id imx8mq_pinctrl_of_match[] = {
+	{ .compatible = "fsl,imx8mq-iomuxc", .data = &imx8mq_pinctrl_info, },
+	{ /* sentinel */ }
+};
+
+static int imx8mq_pinctrl_probe(struct platform_device *pdev)
+{
+	return imx_pinctrl_probe(pdev, &imx8mq_pinctrl_info);
+}
+
+static struct platform_driver imx8mq_pinctrl_driver = {
+	.driver = {
+		.name = "imx8mq-pinctrl",
+		.of_match_table = of_match_ptr(imx8mq_pinctrl_of_match),
+		.suppress_bind_attrs = true,
+	},
+	.probe = imx8mq_pinctrl_probe,
+};
+
+static int __init imx8mq_pinctrl_init(void)
+{
+	return platform_driver_register(&imx8mq_pinctrl_driver);
+}
+arch_initcall(imx8mq_pinctrl_init);
diff --git a/drivers/pinctrl/intel/Kconfig b/drivers/pinctrl/intel/Kconfig
index 4aea1b8504f7..452a14f78707 100644
--- a/drivers/pinctrl/intel/Kconfig
+++ b/drivers/pinctrl/intel/Kconfig
@@ -1,6 +1,6 @@
-#
+# SPDX-License-Identifier: GPL-2.0
 # Intel pin control drivers
-#
+
 if (X86 || COMPILE_TEST)
 
 config PINCTRL_BAYTRAIL
@@ -90,6 +90,14 @@ config PINCTRL_GEMINILAKE
 	  This pinctrl driver provides an interface that allows configuring
 	  of Intel Gemini Lake SoC pins and using them as GPIOs.
 
+config PINCTRL_ICELAKE
+	tristate "Intel Ice Lake PCH pinctrl and GPIO driver"
+	depends on ACPI
+	select PINCTRL_INTEL
+	help
+	  This pinctrl driver provides an interface that allows configuring
+	  of Intel Ice Lake PCH pins and using them as GPIOs.
+
 config PINCTRL_LEWISBURG
 	tristate "Intel Lewisburg pinctrl and GPIO driver"
 	depends on ACPI
diff --git a/drivers/pinctrl/intel/Makefile b/drivers/pinctrl/intel/Makefile
index fadfe3ea2b04..cb491e655749 100644
--- a/drivers/pinctrl/intel/Makefile
+++ b/drivers/pinctrl/intel/Makefile
@@ -10,5 +10,6 @@ obj-$(CONFIG_PINCTRL_CANNONLAKE)	+= pinctrl-cannonlake.o
 obj-$(CONFIG_PINCTRL_CEDARFORK)		+= pinctrl-cedarfork.o
 obj-$(CONFIG_PINCTRL_DENVERTON)		+= pinctrl-denverton.o
 obj-$(CONFIG_PINCTRL_GEMINILAKE)	+= pinctrl-geminilake.o
+obj-$(CONFIG_PINCTRL_ICELAKE)		+= pinctrl-icelake.o
 obj-$(CONFIG_PINCTRL_LEWISBURG)		+= pinctrl-lewisburg.o
 obj-$(CONFIG_PINCTRL_SUNRISEPOINT)	+= pinctrl-sunrisepoint.o
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 6b52ea1440a6..f38d596efa05 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -1,17 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Pinctrl GPIO driver for Intel Baytrail
- * Copyright (c) 2012-2013, Intel Corporation.
  *
+ * Copyright (c) 2012-2013, Intel Corporation
  * Author: Mathias Nyman <mathias.nyman@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
  */
 
 #include <linux/kernel.h>
@@ -1542,11 +1534,13 @@ static void byt_irq_unmask(struct irq_data *d)
 	switch (irqd_get_trigger_type(d)) {
 	case IRQ_TYPE_LEVEL_HIGH:
 		value |= BYT_TRIG_LVL;
+		/* fall through */
 	case IRQ_TYPE_EDGE_RISING:
 		value |= BYT_TRIG_POS;
 		break;
 	case IRQ_TYPE_LEVEL_LOW:
 		value |= BYT_TRIG_LVL;
+		/* fall through */
 	case IRQ_TYPE_EDGE_FALLING:
 		value |= BYT_TRIG_NEG;
 		break;
@@ -1691,7 +1685,8 @@ static void byt_gpio_irq_init_hw(struct byt_gpio *vg)
 		value = readl(reg);
 		if (value)
 			dev_err(&vg->pdev->dev,
-				"GPIO interrupt error, pins misconfigured\n");
+				"GPIO interrupt error, pins misconfigured. INT_STAT%u: 0x%08x\n",
+				base / 32, value);
 	}
 }
 
diff --git a/drivers/pinctrl/intel/pinctrl-broxton.c b/drivers/pinctrl/intel/pinctrl-broxton.c
index e6e6fd112585..8b1c7b59ad3e 100644
--- a/drivers/pinctrl/intel/pinctrl-broxton.c
+++ b/drivers/pinctrl/intel/pinctrl-broxton.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Broxton SoC pinctrl/GPIO driver
  *
  * Copyright (C) 2015, 2016 Intel Corporation
  * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/pinctrl/intel/pinctrl-cannonlake.c b/drivers/pinctrl/intel/pinctrl-cannonlake.c
index 6243e7d95e7e..fb1afe55bf53 100644
--- a/drivers/pinctrl/intel/pinctrl-cannonlake.c
+++ b/drivers/pinctrl/intel/pinctrl-cannonlake.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Cannon Lake PCH pinctrl/GPIO driver
  *
  * Copyright (C) 2017, Intel Corporation
  * Authors: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
  *          Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
@@ -447,12 +444,8 @@ static const struct intel_function cnlh_functions[] = {
 static const struct intel_community cnlh_communities[] = {
 	CNL_COMMUNITY(0, 0, 50, cnlh_community0_gpps),
 	CNL_COMMUNITY(1, 51, 154, cnlh_community1_gpps),
-	/*
-	 * ACPI MMIO resources are returned in reverse order for
-	 * communities 3 and 4.
-	 */
-	CNL_COMMUNITY(3, 155, 248, cnlh_community3_gpps),
-	CNL_COMMUNITY(2, 249, 298, cnlh_community4_gpps),
+	CNL_COMMUNITY(2, 155, 248, cnlh_community3_gpps),
+	CNL_COMMUNITY(3, 249, 298, cnlh_community4_gpps),
 };
 
 static const struct intel_pinctrl_soc_data cnlh_soc_data = {
diff --git a/drivers/pinctrl/intel/pinctrl-cedarfork.c b/drivers/pinctrl/intel/pinctrl-cedarfork.c
index 59216b0533d9..c788e37e338e 100644
--- a/drivers/pinctrl/intel/pinctrl-cedarfork.c
+++ b/drivers/pinctrl/intel/pinctrl-cedarfork.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Cedar Fork PCH pinctrl/GPIO driver
  *
  * Copyright (C) 2017, Intel Corporation
  * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
@@ -240,51 +237,51 @@ static const struct pinctrl_pin_desc cdf_pins[] = {
 	PINCTRL_PIN(179, "GBE_GPIO10"),
 	PINCTRL_PIN(180, "GBE_GPIO11"),
 	PINCTRL_PIN(181, "GBE_GPIO12"),
-	PINCTRL_PIN(182, "SATA0_LED_N"),
-	PINCTRL_PIN(183, "SATA1_LED_N"),
-	PINCTRL_PIN(184, "SATA_PDETECT0"),
-	PINCTRL_PIN(185, "SATA_PDETECT1"),
-	PINCTRL_PIN(186, "SATA0_SDOUT"),
-	PINCTRL_PIN(187, "SATA1_SDOUT"),
-	PINCTRL_PIN(188, "SATA2_LED_N"),
-	PINCTRL_PIN(189, "SATA_PDETECT2"),
-	PINCTRL_PIN(190, "SATA2_SDOUT"),
+	PINCTRL_PIN(182, "PECI_SMB_DATA"),
+	PINCTRL_PIN(183, "SATA0_LED_N"),
+	PINCTRL_PIN(184, "SATA1_LED_N"),
+	PINCTRL_PIN(185, "SATA_PDETECT0"),
+	PINCTRL_PIN(186, "SATA_PDETECT1"),
+	PINCTRL_PIN(187, "SATA0_SDOUT"),
+	PINCTRL_PIN(188, "SATA1_SDOUT"),
+	PINCTRL_PIN(189, "SATA2_LED_N"),
+	PINCTRL_PIN(190, "SATA_PDETECT2"),
+	PINCTRL_PIN(191, "SATA2_SDOUT"),
 	/* EAST3 */
-	PINCTRL_PIN(191, "ESPI_IO0"),
-	PINCTRL_PIN(192, "ESPI_IO1"),
-	PINCTRL_PIN(193, "ESPI_IO2"),
-	PINCTRL_PIN(194, "ESPI_IO3"),
-	PINCTRL_PIN(195, "ESPI_CLK"),
-	PINCTRL_PIN(196, "ESPI_RST_N"),
-	PINCTRL_PIN(197, "ESPI_CS0_N"),
-	PINCTRL_PIN(198, "ESPI_ALRT0_N"),
-	PINCTRL_PIN(199, "ESPI_CS1_N"),
-	PINCTRL_PIN(200, "ESPI_ALRT1_N"),
-	PINCTRL_PIN(201, "ESPI_CLK_LOOPBK"),
+	PINCTRL_PIN(192, "ESPI_IO0"),
+	PINCTRL_PIN(193, "ESPI_IO1"),
+	PINCTRL_PIN(194, "ESPI_IO2"),
+	PINCTRL_PIN(195, "ESPI_IO3"),
+	PINCTRL_PIN(196, "ESPI_CLK"),
+	PINCTRL_PIN(197, "ESPI_RST_N"),
+	PINCTRL_PIN(198, "ESPI_CS0_N"),
+	PINCTRL_PIN(199, "ESPI_ALRT0_N"),
+	PINCTRL_PIN(200, "ESPI_CS1_N"),
+	PINCTRL_PIN(201, "ESPI_ALRT1_N"),
+	PINCTRL_PIN(202, "ESPI_CLK_LOOPBK"),
 	/* EAST0 */
-	PINCTRL_PIN(202, "SPI_CS0_N"),
-	PINCTRL_PIN(203, "SPI_CS1_N"),
-	PINCTRL_PIN(204, "SPI_MOSI_IO0"),
-	PINCTRL_PIN(205, "SPI_MISO_IO1"),
-	PINCTRL_PIN(206, "SPI_IO2"),
-	PINCTRL_PIN(207, "SPI_IO3"),
-	PINCTRL_PIN(208, "SPI_CLK"),
-	PINCTRL_PIN(209, "SPI_CLK_LOOPBK"),
-	PINCTRL_PIN(210, "SUSPWRDNACK"),
-	PINCTRL_PIN(211, "PMU_SUSCLK"),
-	PINCTRL_PIN(212, "ADR_COMPLETE"),
-	PINCTRL_PIN(213, "ADR_TRIGGER_N"),
-	PINCTRL_PIN(214, "PMU_SLP_S45_N"),
-	PINCTRL_PIN(215, "PMU_SLP_S3_N"),
-	PINCTRL_PIN(216, "PMU_WAKE_N"),
-	PINCTRL_PIN(217, "PMU_PWRBTN_N"),
-	PINCTRL_PIN(218, "PMU_RESETBUTTON_N"),
-	PINCTRL_PIN(219, "PMU_PLTRST_N"),
-	PINCTRL_PIN(220, "SUS_STAT_N"),
-	PINCTRL_PIN(221, "PMU_I2C_CLK"),
-	PINCTRL_PIN(222, "PMU_I2C_DATA"),
-	PINCTRL_PIN(223, "PECI_SMB_CLK"),
-	PINCTRL_PIN(224, "PECI_SMB_DATA"),
+	PINCTRL_PIN(203, "SPI_CS0_N"),
+	PINCTRL_PIN(204, "SPI_CS1_N"),
+	PINCTRL_PIN(205, "SPI_MOSI_IO0"),
+	PINCTRL_PIN(206, "SPI_MISO_IO1"),
+	PINCTRL_PIN(207, "SPI_IO2"),
+	PINCTRL_PIN(208, "SPI_IO3"),
+	PINCTRL_PIN(209, "SPI_CLK"),
+	PINCTRL_PIN(210, "SPI_CLK_LOOPBK"),
+	PINCTRL_PIN(211, "SUSPWRDNACK"),
+	PINCTRL_PIN(212, "PMU_SUSCLK"),
+	PINCTRL_PIN(213, "ADR_COMPLETE"),
+	PINCTRL_PIN(214, "ADR_TRIGGER_N"),
+	PINCTRL_PIN(215, "PMU_SLP_S45_N"),
+	PINCTRL_PIN(216, "PMU_SLP_S3_N"),
+	PINCTRL_PIN(217, "PMU_WAKE_N"),
+	PINCTRL_PIN(218, "PMU_PWRBTN_N"),
+	PINCTRL_PIN(219, "PMU_RESETBUTTON_N"),
+	PINCTRL_PIN(220, "PMU_PLTRST_N"),
+	PINCTRL_PIN(221, "SUS_STAT_N"),
+	PINCTRL_PIN(222, "PMU_I2C_CLK"),
+	PINCTRL_PIN(223, "PMU_I2C_DATA"),
+	PINCTRL_PIN(224, "PECI_SMB_CLK"),
 	PINCTRL_PIN(225, "PECI_SMB_ALRT_N"),
 	/* EMMC */
 	PINCTRL_PIN(226, "EMMC_CMD"),
@@ -315,9 +312,9 @@ static const struct intel_padgroup cdf_community0_gpps[] = {
 };
 
 static const struct intel_padgroup cdf_community1_gpps[] = {
-	CDF_GPP(0, 168, 190),	/* EAST2 */
-	CDF_GPP(1, 191, 201),	/* EAST3 */
-	CDF_GPP(2, 202, 225),	/* EAST0 */
+	CDF_GPP(0, 168, 191),	/* EAST2 */
+	CDF_GPP(1, 192, 202),	/* EAST3 */
+	CDF_GPP(2, 203, 225),	/* EAST0 */
 	CDF_GPP(3, 226, 236),	/* EMMC */
 };
 
diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index 0f1019ae3993..6d31ad799987 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Cherryview/Braswell pinctrl driver
  *
@@ -7,10 +8,6 @@
  * This driver is based on the original Cherryview GPIO driver by
  *   Ning Li <ning.li@intel.com>
  *   Alan Cox <alan@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/dmi.h>
diff --git a/drivers/pinctrl/intel/pinctrl-denverton.c b/drivers/pinctrl/intel/pinctrl-denverton.c
index 6572550cfe78..f321ab0d76e5 100644
--- a/drivers/pinctrl/intel/pinctrl-denverton.c
+++ b/drivers/pinctrl/intel/pinctrl-denverton.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Denverton SoC pinctrl/GPIO driver
  *
  * Copyright (C) 2017, Intel Corporation
  * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/pinctrl/intel/pinctrl-geminilake.c b/drivers/pinctrl/intel/pinctrl-geminilake.c
index a6b94c930007..5c4c96752fc1 100644
--- a/drivers/pinctrl/intel/pinctrl-geminilake.c
+++ b/drivers/pinctrl/intel/pinctrl-geminilake.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Gemini Lake SoC pinctrl/GPIO driver
  *
  * Copyright (C) 2017 Intel Corporation
  * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/pinctrl/intel/pinctrl-icelake.c b/drivers/pinctrl/intel/pinctrl-icelake.c
new file mode 100644
index 000000000000..630b966ce081
--- /dev/null
+++ b/drivers/pinctrl/intel/pinctrl-icelake.c
@@ -0,0 +1,436 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Ice Lake PCH pinctrl/GPIO driver
+ *
+ * Copyright (C) 2018, Intel Corporation
+ * Authors: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ *	    Mika Westerberg <mika.westerberg@linux.intel.com>
+ */
+
+#include <linux/acpi.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/pinctrl/pinctrl.h>
+
+#include "pinctrl-intel.h"
+
+#define ICL_PAD_OWN	0x020
+#define ICL_PADCFGLOCK	0x080
+#define ICL_HOSTSW_OWN	0x0b0
+#define ICL_GPI_IE	0x110
+
+#define ICL_GPP(r, s, e, g)				\
+	{						\
+		.reg_num = (r),				\
+		.base = (s),				\
+		.size = ((e) - (s) + 1),		\
+		.gpio_base = (g),			\
+	}
+
+#define ICL_NO_GPIO	-1
+
+#define ICL_COMMUNITY(b, s, e, g)			\
+	{						\
+		.barno = (b),				\
+		.padown_offset = ICL_PAD_OWN,		\
+		.padcfglock_offset = ICL_PADCFGLOCK,	\
+		.hostown_offset = ICL_HOSTSW_OWN,	\
+		.ie_offset = ICL_GPI_IE,		\
+		.pin_base = (s),			\
+		.npins = ((e) - (s) + 1),		\
+		.gpps = (g),				\
+		.ngpps = ARRAY_SIZE(g),			\
+	}
+
+/* Ice Lake-LP */
+static const struct pinctrl_pin_desc icllp_pins[] = {
+	/* GPP_G */
+	PINCTRL_PIN(0, "SD3_CMD"),
+	PINCTRL_PIN(1, "SD3_D0"),
+	PINCTRL_PIN(2, "SD3_D1"),
+	PINCTRL_PIN(3, "SD3_D2"),
+	PINCTRL_PIN(4, "SD3_D3"),
+	PINCTRL_PIN(5, "SD3_CDB"),
+	PINCTRL_PIN(6, "SD3_CLK"),
+	PINCTRL_PIN(7, "SD3_WP"),
+	/* GPP_B */
+	PINCTRL_PIN(8, "CORE_VID_0"),
+	PINCTRL_PIN(9, "CORE_VID_1"),
+	PINCTRL_PIN(10, "VRALERTB"),
+	PINCTRL_PIN(11, "CPU_GP_2"),
+	PINCTRL_PIN(12, "CPU_GP_3"),
+	PINCTRL_PIN(13, "ISH_I2C0_SDA"),
+	PINCTRL_PIN(14, "ISH_I2C0_SCL"),
+	PINCTRL_PIN(15, "ISH_I2C1_SDA"),
+	PINCTRL_PIN(16, "ISH_I2C1_SCL"),
+	PINCTRL_PIN(17, "I2C5_SDA"),
+	PINCTRL_PIN(18, "I2C5_SCL"),
+	PINCTRL_PIN(19, "PMCALERTB"),
+	PINCTRL_PIN(20, "SLP_S0B"),
+	PINCTRL_PIN(21, "PLTRSTB"),
+	PINCTRL_PIN(22, "SPKR"),
+	PINCTRL_PIN(23, "GSPI0_CS0B"),
+	PINCTRL_PIN(24, "GSPI0_CLK"),
+	PINCTRL_PIN(25, "GSPI0_MISO"),
+	PINCTRL_PIN(26, "GSPI0_MOSI"),
+	PINCTRL_PIN(27, "GSPI1_CS0B"),
+	PINCTRL_PIN(28, "GSPI1_CLK"),
+	PINCTRL_PIN(29, "GSPI1_MISO"),
+	PINCTRL_PIN(30, "GSPI1_MOSI"),
+	PINCTRL_PIN(31, "SML1ALERTB"),
+	PINCTRL_PIN(32, "GSPI0_CLK_LOOPBK"),
+	PINCTRL_PIN(33, "GSPI1_CLK_LOOPBK"),
+	/* GPP_A */
+	PINCTRL_PIN(34, "ESPI_IO_0"),
+	PINCTRL_PIN(35, "ESPI_IO_1"),
+	PINCTRL_PIN(36, "ESPI_IO_2"),
+	PINCTRL_PIN(37, "ESPI_IO_3"),
+	PINCTRL_PIN(38, "ESPI_CSB"),
+	PINCTRL_PIN(39, "ESPI_CLK"),
+	PINCTRL_PIN(40, "ESPI_RESETB"),
+	PINCTRL_PIN(41, "I2S2_SCLK"),
+	PINCTRL_PIN(42, "I2S2_SFRM"),
+	PINCTRL_PIN(43, "I2S2_TXD"),
+	PINCTRL_PIN(44, "I2S2_RXD"),
+	PINCTRL_PIN(45, "SATA_DEVSLP_2"),
+	PINCTRL_PIN(46, "SATAXPCIE_1"),
+	PINCTRL_PIN(47, "SATAXPCIE_2"),
+	PINCTRL_PIN(48, "USB2_OCB_1"),
+	PINCTRL_PIN(49, "USB2_OCB_2"),
+	PINCTRL_PIN(50, "USB2_OCB_3"),
+	PINCTRL_PIN(51, "DDSP_HPD_C"),
+	PINCTRL_PIN(52, "DDSP_HPD_B"),
+	PINCTRL_PIN(53, "DDSP_HPD_1"),
+	PINCTRL_PIN(54, "DDSP_HPD_2"),
+	PINCTRL_PIN(55, "I2S5_TXD"),
+	PINCTRL_PIN(56, "I2S5_RXD"),
+	PINCTRL_PIN(57, "I2S1_SCLK"),
+	PINCTRL_PIN(58, "ESPI_CLK_LOOPBK"),
+	/* GPP_H */
+	PINCTRL_PIN(59, "SD_1P8_SEL"),
+	PINCTRL_PIN(60, "SD_PWR_EN_B"),
+	PINCTRL_PIN(61, "GPPC_H_2"),
+	PINCTRL_PIN(62, "SX_EXIT_HOLDOFFB"),
+	PINCTRL_PIN(63, "I2C2_SDA"),
+	PINCTRL_PIN(64, "I2C2_SCL"),
+	PINCTRL_PIN(65, "I2C3_SDA"),
+	PINCTRL_PIN(66, "I2C3_SCL"),
+	PINCTRL_PIN(67, "I2C4_SDA"),
+	PINCTRL_PIN(68, "I2C4_SCL"),
+	PINCTRL_PIN(69, "SRCCLKREQB_4"),
+	PINCTRL_PIN(70, "SRCCLKREQB_5"),
+	PINCTRL_PIN(71, "M2_SKT2_CFG_0"),
+	PINCTRL_PIN(72, "M2_SKT2_CFG_1"),
+	PINCTRL_PIN(73, "M2_SKT2_CFG_2"),
+	PINCTRL_PIN(74, "M2_SKT2_CFG_3"),
+	PINCTRL_PIN(75, "DDPB_CTRLCLK"),
+	PINCTRL_PIN(76, "DDPB_CTRLDATA"),
+	PINCTRL_PIN(77, "CPU_VCCIO_PWR_GATEB"),
+	PINCTRL_PIN(78, "TIME_SYNC_0"),
+	PINCTRL_PIN(79, "IMGCLKOUT_1"),
+	PINCTRL_PIN(80, "IMGCLKOUT_2"),
+	PINCTRL_PIN(81, "IMGCLKOUT_3"),
+	PINCTRL_PIN(82, "IMGCLKOUT_4"),
+	/* GPP_D */
+	PINCTRL_PIN(83, "ISH_GP_0"),
+	PINCTRL_PIN(84, "ISH_GP_1"),
+	PINCTRL_PIN(85, "ISH_GP_2"),
+	PINCTRL_PIN(86, "ISH_GP_3"),
+	PINCTRL_PIN(87, "IMGCLKOUT_0"),
+	PINCTRL_PIN(88, "SRCCLKREQB_0"),
+	PINCTRL_PIN(89, "SRCCLKREQB_1"),
+	PINCTRL_PIN(90, "SRCCLKREQB_2"),
+	PINCTRL_PIN(91, "SRCCLKREQB_3"),
+	PINCTRL_PIN(92, "ISH_SPI_CSB"),
+	PINCTRL_PIN(93, "ISH_SPI_CLK"),
+	PINCTRL_PIN(94, "ISH_SPI_MISO"),
+	PINCTRL_PIN(95, "ISH_SPI_MOSI"),
+	PINCTRL_PIN(96, "ISH_UART0_RXD"),
+	PINCTRL_PIN(97, "ISH_UART0_TXD"),
+	PINCTRL_PIN(98, "ISH_UART0_RTSB"),
+	PINCTRL_PIN(99, "ISH_UART0_CTSB"),
+	PINCTRL_PIN(100, "ISH_GP_4"),
+	PINCTRL_PIN(101, "ISH_GP_5"),
+	PINCTRL_PIN(102, "I2S_MCLK"),
+	PINCTRL_PIN(103, "GSPI2_CLK_LOOPBK"),
+	/* GPP_F */
+	PINCTRL_PIN(104, "CNV_BRI_DT"),
+	PINCTRL_PIN(105, "CNV_BRI_RSP"),
+	PINCTRL_PIN(106, "CNV_RGI_DT"),
+	PINCTRL_PIN(107, "CNV_RGI_RSP"),
+	PINCTRL_PIN(108, "CNV_RF_RESET_B"),
+	PINCTRL_PIN(109, "EMMC_HIP_MON"),
+	PINCTRL_PIN(110, "CNV_PA_BLANKING"),
+	PINCTRL_PIN(111, "EMMC_CMD"),
+	PINCTRL_PIN(112, "EMMC_DATA0"),
+	PINCTRL_PIN(113, "EMMC_DATA1"),
+	PINCTRL_PIN(114, "EMMC_DATA2"),
+	PINCTRL_PIN(115, "EMMC_DATA3"),
+	PINCTRL_PIN(116, "EMMC_DATA4"),
+	PINCTRL_PIN(117, "EMMC_DATA5"),
+	PINCTRL_PIN(118, "EMMC_DATA6"),
+	PINCTRL_PIN(119, "EMMC_DATA7"),
+	PINCTRL_PIN(120, "EMMC_RCLK"),
+	PINCTRL_PIN(121, "EMMC_CLK"),
+	PINCTRL_PIN(122, "EMMC_RESETB"),
+	PINCTRL_PIN(123, "A4WP_PRESENT"),
+	/* vGPIO */
+	PINCTRL_PIN(124, "CNV_BTEN"),
+	PINCTRL_PIN(125, "CNV_WCEN"),
+	PINCTRL_PIN(126, "CNV_BT_HOST_WAKEB"),
+	PINCTRL_PIN(127, "CNV_BT_IF_SELECT"),
+	PINCTRL_PIN(128, "vCNV_BT_UART_TXD"),
+	PINCTRL_PIN(129, "vCNV_BT_UART_RXD"),
+	PINCTRL_PIN(130, "vCNV_BT_UART_CTS_B"),
+	PINCTRL_PIN(131, "vCNV_BT_UART_RTS_B"),
+	PINCTRL_PIN(132, "vCNV_MFUART1_TXD"),
+	PINCTRL_PIN(133, "vCNV_MFUART1_RXD"),
+	PINCTRL_PIN(134, "vCNV_MFUART1_CTS_B"),
+	PINCTRL_PIN(135, "vCNV_MFUART1_RTS_B"),
+	PINCTRL_PIN(136, "vUART0_TXD"),
+	PINCTRL_PIN(137, "vUART0_RXD"),
+	PINCTRL_PIN(138, "vUART0_CTS_B"),
+	PINCTRL_PIN(139, "vUART0_RTS_B"),
+	PINCTRL_PIN(140, "vISH_UART0_TXD"),
+	PINCTRL_PIN(141, "vISH_UART0_RXD"),
+	PINCTRL_PIN(142, "vISH_UART0_CTS_B"),
+	PINCTRL_PIN(143, "vISH_UART0_RTS_B"),
+	PINCTRL_PIN(144, "vCNV_BT_I2S_BCLK"),
+	PINCTRL_PIN(145, "vCNV_BT_I2S_WS_SYNC"),
+	PINCTRL_PIN(146, "vCNV_BT_I2S_SDO"),
+	PINCTRL_PIN(147, "vCNV_BT_I2S_SDI"),
+	PINCTRL_PIN(148, "vI2S2_SCLK"),
+	PINCTRL_PIN(149, "vI2S2_SFRM"),
+	PINCTRL_PIN(150, "vI2S2_TXD"),
+	PINCTRL_PIN(151, "vI2S2_RXD"),
+	PINCTRL_PIN(152, "vSD3_CD_B"),
+	/* GPP_C */
+	PINCTRL_PIN(153, "SMBCLK"),
+	PINCTRL_PIN(154, "SMBDATA"),
+	PINCTRL_PIN(155, "SMBALERTB"),
+	PINCTRL_PIN(156, "SML0CLK"),
+	PINCTRL_PIN(157, "SML0DATA"),
+	PINCTRL_PIN(158, "SML0ALERTB"),
+	PINCTRL_PIN(159, "SML1CLK"),
+	PINCTRL_PIN(160, "SML1DATA"),
+	PINCTRL_PIN(161, "UART0_RXD"),
+	PINCTRL_PIN(162, "UART0_TXD"),
+	PINCTRL_PIN(163, "UART0_RTSB"),
+	PINCTRL_PIN(164, "UART0_CTSB"),
+	PINCTRL_PIN(165, "UART1_RXD"),
+	PINCTRL_PIN(166, "UART1_TXD"),
+	PINCTRL_PIN(167, "UART1_RTSB"),
+	PINCTRL_PIN(168, "UART1_CTSB"),
+	PINCTRL_PIN(169, "I2C0_SDA"),
+	PINCTRL_PIN(170, "I2C0_SCL"),
+	PINCTRL_PIN(171, "I2C1_SDA"),
+	PINCTRL_PIN(172, "I2C1_SCL"),
+	PINCTRL_PIN(173, "UART2_RXD"),
+	PINCTRL_PIN(174, "UART2_TXD"),
+	PINCTRL_PIN(175, "UART2_RTSB"),
+	PINCTRL_PIN(176, "UART2_CTSB"),
+	/* HVCMOS */
+	PINCTRL_PIN(177, "L_BKLTEN"),
+	PINCTRL_PIN(178, "L_BKLTCTL"),
+	PINCTRL_PIN(179, "L_VDDEN"),
+	PINCTRL_PIN(180, "SYS_PWROK"),
+	PINCTRL_PIN(181, "SYS_RESETB"),
+	PINCTRL_PIN(182, "MLK_RSTB"),
+	/* GPP_E */
+	PINCTRL_PIN(183, "SATAXPCIE_0"),
+	PINCTRL_PIN(184, "SPI1_IO_2"),
+	PINCTRL_PIN(185, "SPI1_IO_3"),
+	PINCTRL_PIN(186, "CPU_GP_0"),
+	PINCTRL_PIN(187, "SATA_DEVSLP_0"),
+	PINCTRL_PIN(188, "SATA_DEVSLP_1"),
+	PINCTRL_PIN(189, "GPPC_E_6"),
+	PINCTRL_PIN(190, "CPU_GP_1"),
+	PINCTRL_PIN(191, "SATA_LEDB"),
+	PINCTRL_PIN(192, "USB2_OCB_0"),
+	PINCTRL_PIN(193, "SPI1_CSB"),
+	PINCTRL_PIN(194, "SPI1_CLK"),
+	PINCTRL_PIN(195, "SPI1_MISO_IO_1"),
+	PINCTRL_PIN(196, "SPI1_MOSI_IO_0"),
+	PINCTRL_PIN(197, "DDSP_HPD_A"),
+	PINCTRL_PIN(198, "ISH_GP_6"),
+	PINCTRL_PIN(199, "ISH_GP_7"),
+	PINCTRL_PIN(200, "DISP_MISC_4"),
+	PINCTRL_PIN(201, "DDP1_CTRLCLK"),
+	PINCTRL_PIN(202, "DDP1_CTRLDATA"),
+	PINCTRL_PIN(203, "DDP2_CTRLCLK"),
+	PINCTRL_PIN(204, "DDP2_CTRLDATA"),
+	PINCTRL_PIN(205, "DDPA_CTRLCLK"),
+	PINCTRL_PIN(206, "DDPA_CTRLDATA"),
+	/* JTAG */
+	PINCTRL_PIN(207, "JTAG_TDO"),
+	PINCTRL_PIN(208, "JTAGX"),
+	PINCTRL_PIN(209, "PRDYB"),
+	PINCTRL_PIN(210, "PREQB"),
+	PINCTRL_PIN(211, "CPU_TRSTB"),
+	PINCTRL_PIN(212, "JTAG_TDI"),
+	PINCTRL_PIN(213, "JTAG_TMS"),
+	PINCTRL_PIN(214, "JTAG_TCK"),
+	PINCTRL_PIN(215, "ITP_PMODE"),
+	/* GPP_R */
+	PINCTRL_PIN(216, "HDA_BCLK"),
+	PINCTRL_PIN(217, "HDA_SYNC"),
+	PINCTRL_PIN(218, "HDA_SDO"),
+	PINCTRL_PIN(219, "HDA_SDI_0"),
+	PINCTRL_PIN(220, "HDA_RSTB"),
+	PINCTRL_PIN(221, "HDA_SDI_1"),
+	PINCTRL_PIN(222, "I2S1_TXD"),
+	PINCTRL_PIN(223, "I2S1_RXD"),
+	/* GPP_S */
+	PINCTRL_PIN(224, "SNDW1_CLK"),
+	PINCTRL_PIN(225, "SNDW1_DATA"),
+	PINCTRL_PIN(226, "SNDW2_CLK"),
+	PINCTRL_PIN(227, "SNDW2_DATA"),
+	PINCTRL_PIN(228, "SNDW3_CLK"),
+	PINCTRL_PIN(229, "SNDW3_DATA"),
+	PINCTRL_PIN(230, "SNDW4_CLK"),
+	PINCTRL_PIN(231, "SNDW4_DATA"),
+	/* SPI */
+	PINCTRL_PIN(232, "SPI0_IO_2"),
+	PINCTRL_PIN(233, "SPI0_IO_3"),
+	PINCTRL_PIN(234, "SPI0_MOSI_IO_0"),
+	PINCTRL_PIN(235, "SPI0_MISO_IO_1"),
+	PINCTRL_PIN(236, "SPI0_TPM_CSB"),
+	PINCTRL_PIN(237, "SPI0_FLASH_0_CSB"),
+	PINCTRL_PIN(238, "SPI0_FLASH_1_CSB"),
+	PINCTRL_PIN(239, "SPI0_CLK"),
+	PINCTRL_PIN(240, "SPI0_CLK_LOOPBK"),
+};
+
+static const struct intel_padgroup icllp_community0_gpps[] = {
+	ICL_GPP(0, 0, 7, 0),			/* GPP_G */
+	ICL_GPP(1, 8, 33, 32),			/* GPP_B */
+	ICL_GPP(2, 34, 58, 64),			/* GPP_A */
+};
+
+static const struct intel_padgroup icllp_community1_gpps[] = {
+	ICL_GPP(0, 59, 82, 96),			/* GPP_H */
+	ICL_GPP(1, 83, 103, 128),		/* GPP_D */
+	ICL_GPP(2, 104, 123, 160),		/* GPP_F */
+	ICL_GPP(3, 124, 152, 192),		/* vGPIO */
+};
+
+static const struct intel_padgroup icllp_community4_gpps[] = {
+	ICL_GPP(0, 153, 176, 224),		/* GPP_C */
+	ICL_GPP(1, 177, 182, ICL_NO_GPIO),	/* HVCMOS */
+	ICL_GPP(2, 183, 206, 256),		/* GPP_E */
+	ICL_GPP(3, 207, 215, ICL_NO_GPIO),	/* JTAG */
+};
+
+static const struct intel_padgroup icllp_community5_gpps[] = {
+	ICL_GPP(0, 216, 223, 288),		/* GPP_R */
+	ICL_GPP(1, 224, 231, 320),		/* GPP_S */
+	ICL_GPP(2, 232, 240, ICL_NO_GPIO),	/* SPI */
+};
+
+static const struct intel_community icllp_communities[] = {
+	ICL_COMMUNITY(0, 0, 58, icllp_community0_gpps),
+	ICL_COMMUNITY(1, 59, 152, icllp_community1_gpps),
+	ICL_COMMUNITY(2, 153, 215, icllp_community4_gpps),
+	ICL_COMMUNITY(3, 216, 240, icllp_community5_gpps),
+};
+
+static const unsigned int icllp_spi0_pins[] = { 22, 23, 24, 25, 26 };
+static const unsigned int icllp_spi0_modes[] = { 3, 1, 1, 1, 1 };
+static const unsigned int icllp_spi1_pins[] = { 27, 28, 29, 30, 31 };
+static const unsigned int icllp_spi1_modes[] = { 1, 1, 1, 1, 3 };
+static const unsigned int icllp_spi2_pins[] = { 92, 93, 94, 95, 98 };
+static const unsigned int icllp_spi2_modes[] = { 3, 3, 3, 3, 2 };
+
+static const unsigned int icllp_i2c0_pins[] = { 169, 170 };
+static const unsigned int icllp_i2c1_pins[] = { 171, 172 };
+static const unsigned int icllp_i2c2_pins[] = { 63, 64 };
+static const unsigned int icllp_i2c3_pins[] = { 65, 66 };
+static const unsigned int icllp_i2c4_pins[] = { 67, 68 };
+
+static const unsigned int icllp_uart0_pins[] = { 161, 162, 163, 164 };
+static const unsigned int icllp_uart1_pins[] = { 165, 166, 167, 168 };
+static const unsigned int icllp_uart2_pins[] = { 173, 174, 175, 176 };
+
+static const struct intel_pingroup icllp_groups[] = {
+	PIN_GROUP("spi0_grp", icllp_spi0_pins, icllp_spi0_modes),
+	PIN_GROUP("spi1_grp", icllp_spi1_pins, icllp_spi1_modes),
+	PIN_GROUP("spi2_grp", icllp_spi2_pins, icllp_spi2_modes),
+	PIN_GROUP("i2c0_grp", icllp_i2c0_pins, 1),
+	PIN_GROUP("i2c1_grp", icllp_i2c1_pins, 1),
+	PIN_GROUP("i2c2_grp", icllp_i2c2_pins, 1),
+	PIN_GROUP("i2c3_grp", icllp_i2c3_pins, 1),
+	PIN_GROUP("i2c4_grp", icllp_i2c4_pins, 1),
+	PIN_GROUP("uart0_grp", icllp_uart0_pins, 1),
+	PIN_GROUP("uart1_grp", icllp_uart1_pins, 1),
+	PIN_GROUP("uart2_grp", icllp_uart2_pins, 1),
+};
+
+static const char * const icllp_spi0_groups[] = { "spi0_grp" };
+static const char * const icllp_spi1_groups[] = { "spi1_grp" };
+static const char * const icllp_spi2_groups[] = { "spi2_grp" };
+static const char * const icllp_i2c0_groups[] = { "i2c0_grp" };
+static const char * const icllp_i2c1_groups[] = { "i2c1_grp" };
+static const char * const icllp_i2c2_groups[] = { "i2c2_grp" };
+static const char * const icllp_i2c3_groups[] = { "i2c3_grp" };
+static const char * const icllp_i2c4_groups[] = { "i2c4_grp" };
+static const char * const icllp_uart0_groups[] = { "uart0_grp" };
+static const char * const icllp_uart1_groups[] = { "uart1_grp" };
+static const char * const icllp_uart2_groups[] = { "uart2_grp" };
+
+static const struct intel_function icllp_functions[] = {
+	FUNCTION("spi0", icllp_spi0_groups),
+	FUNCTION("spi1", icllp_spi1_groups),
+	FUNCTION("spi2", icllp_spi2_groups),
+	FUNCTION("i2c0", icllp_i2c0_groups),
+	FUNCTION("i2c1", icllp_i2c1_groups),
+	FUNCTION("i2c2", icllp_i2c2_groups),
+	FUNCTION("i2c3", icllp_i2c3_groups),
+	FUNCTION("i2c4", icllp_i2c4_groups),
+	FUNCTION("uart0", icllp_uart0_groups),
+	FUNCTION("uart1", icllp_uart1_groups),
+	FUNCTION("uart2", icllp_uart2_groups),
+};
+
+static const struct intel_pinctrl_soc_data icllp_soc_data = {
+	.pins = icllp_pins,
+	.npins = ARRAY_SIZE(icllp_pins),
+	.groups = icllp_groups,
+	.ngroups = ARRAY_SIZE(icllp_groups),
+	.functions = icllp_functions,
+	.nfunctions = ARRAY_SIZE(icllp_functions),
+	.communities = icllp_communities,
+	.ncommunities = ARRAY_SIZE(icllp_communities),
+};
+
+static int icl_pinctrl_probe(struct platform_device *pdev)
+{
+	return intel_pinctrl_probe(pdev, &icllp_soc_data);
+}
+
+static const struct dev_pm_ops icl_pinctrl_pm_ops = {
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(intel_pinctrl_suspend,
+				     intel_pinctrl_resume)
+};
+
+static const struct acpi_device_id icl_pinctrl_acpi_match[] = {
+	{ "INT3455" },
+	{ },
+};
+MODULE_DEVICE_TABLE(acpi, icl_pinctrl_acpi_match);
+
+static struct platform_driver icl_pinctrl_driver = {
+	.probe = icl_pinctrl_probe,
+	.driver = {
+		.name = "icelake-pinctrl",
+		.acpi_match_table = icl_pinctrl_acpi_match,
+		.pm = &icl_pinctrl_pm_ops,
+	},
+};
+
+module_platform_driver(icl_pinctrl_driver);
+
+MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>");
+MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
+MODULE_DESCRIPTION("Intel Ice Lake PCH pinctrl/GPIO driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 1e24a6b8a64e..62b009b27eda 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel pinctrl/GPIO core driver.
  *
  * Copyright (C) 2015, Intel Corporation
  * Authors: Mathias Nyman <mathias.nyman@linux.intel.com>
  *          Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/module.h>
@@ -875,6 +872,36 @@ static int intel_gpio_to_pin(struct intel_pinctrl *pctrl, unsigned offset,
 	return -EINVAL;
 }
 
+static int intel_gpio_irq_reqres(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct intel_pinctrl *pctrl = gpiochip_get_data(gc);
+	int pin;
+	int ret;
+
+	pin = intel_gpio_to_pin(pctrl, irqd_to_hwirq(d), NULL, NULL);
+	if (pin >= 0) {
+		ret = gpiochip_lock_as_irq(gc, pin);
+		if (ret) {
+			dev_err(pctrl->dev, "unable to lock HW IRQ %d for IRQ\n",
+				pin);
+			return ret;
+		}
+	}
+	return 0;
+}
+
+static void intel_gpio_irq_relres(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct intel_pinctrl *pctrl = gpiochip_get_data(gc);
+	int pin;
+
+	pin = intel_gpio_to_pin(pctrl, irqd_to_hwirq(d), NULL, NULL);
+	if (pin >= 0)
+		gpiochip_unlock_as_irq(gc, pin);
+}
+
 static void intel_gpio_irq_ack(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
@@ -1090,6 +1117,8 @@ static irqreturn_t intel_gpio_irq(int irq, void *data)
 
 static struct irq_chip intel_gpio_irqchip = {
 	.name = "intel-gpio",
+	.irq_request_resources = intel_gpio_irq_reqres,
+	.irq_release_resources = intel_gpio_irq_relres,
 	.irq_enable = intel_gpio_irq_enable,
 	.irq_ack = intel_gpio_irq_ack,
 	.irq_mask = intel_gpio_irq_mask,
diff --git a/drivers/pinctrl/intel/pinctrl-intel.h b/drivers/pinctrl/intel/pinctrl-intel.h
index 98fdf9adf623..1785abf157e4 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.h
+++ b/drivers/pinctrl/intel/pinctrl-intel.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Core pinctrl/GPIO driver for Intel GPIO controllers
  *
  * Copyright (C) 2015, Intel Corporation
  * Authors: Mathias Nyman <mathias.nyman@linux.intel.com>
  *          Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef PINCTRL_INTEL_H
diff --git a/drivers/pinctrl/intel/pinctrl-lewisburg.c b/drivers/pinctrl/intel/pinctrl-lewisburg.c
index 14d56ea6cfdc..99894647eddd 100644
--- a/drivers/pinctrl/intel/pinctrl-lewisburg.c
+++ b/drivers/pinctrl/intel/pinctrl-lewisburg.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Lewisburg pinctrl/GPIO driver
  *
  * Copyright (C) 2017, Intel Corporation
  * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/pinctrl/intel/pinctrl-merrifield.c b/drivers/pinctrl/intel/pinctrl-merrifield.c
index d9357054d41d..4a916be44f4f 100644
--- a/drivers/pinctrl/intel/pinctrl-merrifield.c
+++ b/drivers/pinctrl/intel/pinctrl-merrifield.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Merrifield SoC pinctrl driver
  *
  * Copyright (C) 2016, Intel Corporation
  * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/bitops.h>
diff --git a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
index fee3435a6f15..7984392104fe 100644
--- a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
+++ b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Sunrisepoint PCH pinctrl/GPIO driver
  *
  * Copyright (C) 2015, Intel Corporation
  * Authors: Mathias Nyman <mathias.nyman@linux.intel.com>
  *          Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/pinctrl/mediatek/mtk-eint.c b/drivers/pinctrl/mediatek/mtk-eint.c
index 30f3316747e2..a613e546717a 100644
--- a/drivers/pinctrl/mediatek/mtk-eint.c
+++ b/drivers/pinctrl/mediatek/mtk-eint.c
@@ -13,6 +13,7 @@
 #include <linux/err.h>
 #include <linux/gpio.h>
 #include <linux/io.h>
+#include <linux/irqchip/chained_irq.h>
 #include <linux/irqdomain.h>
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt7622.c b/drivers/pinctrl/mediatek/pinctrl-mt7622.c
index 4c4740ffeb9c..6f931b85701b 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt7622.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt7622.c
@@ -1263,6 +1263,7 @@ static int mtk_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin,
 					       MTK_DISABLE);
 			if (err)
 				goto err;
+			/* else: fall through */
 		case PIN_CONFIG_INPUT_ENABLE:
 		case PIN_CONFIG_SLEW_RATE:
 			reg = (param == PIN_CONFIG_SLEW_RATE) ?
@@ -1537,7 +1538,7 @@ static int mtk_build_groups(struct mtk_pinctrl *hw)
 		err = pinctrl_generic_add_group(hw->pctrl, group->name,
 						group->pins, group->num_pins,
 						group->data);
-		if (err) {
+		if (err < 0) {
 			dev_err(hw->dev, "Failed to register group %s\n",
 				group->name);
 			return err;
@@ -1558,7 +1559,7 @@ static int mtk_build_functions(struct mtk_pinctrl *hw)
 						  func->group_names,
 						  func->num_group_names,
 						  func->data);
-		if (err) {
+		if (err < 0) {
 			dev_err(hw->dev, "Failed to register function %s\n",
 				func->name);
 			return err;
diff --git a/drivers/pinctrl/meson/pinctrl-meson-axg.c b/drivers/pinctrl/meson/pinctrl-meson-axg.c
index 46a0918bd284..ad502eda4afa 100644
--- a/drivers/pinctrl/meson/pinctrl-meson-axg.c
+++ b/drivers/pinctrl/meson/pinctrl-meson-axg.c
@@ -672,6 +672,9 @@ static const unsigned int jtag_ao_tdo_pins[] = {GPIOAO_4};
 static const unsigned int jtag_ao_clk_pins[] = {GPIOAO_5};
 static const unsigned int jtag_ao_tms_pins[] = {GPIOAO_7};
 
+/* gen_clk */
+static const unsigned int gen_clk_ee_pins[] = {GPIOAO_13};
+
 static struct meson_pmx_group meson_axg_aobus_groups[] = {
 	GPIO_GROUP(GPIOAO_0),
 	GPIO_GROUP(GPIOAO_1),
@@ -718,6 +721,7 @@ static struct meson_pmx_group meson_axg_aobus_groups[] = {
 	GROUP(jtag_ao_tdo, 4),
 	GROUP(jtag_ao_clk, 4),
 	GROUP(jtag_ao_tms, 4),
+	GROUP(gen_clk_ee, 4),
 };
 
 static const char * const gpio_periphs_groups[] = {
@@ -947,6 +951,10 @@ static const char * const tdmb_groups[] = {
 	"tdmb_din2", "tdmb_dout2", "tdmb_din3",	"tdmb_dout3",
 };
 
+static const char * const gen_clk_ee_groups[] = {
+	"gen_clk_ee",
+};
+
 static struct meson_pmx_func meson_axg_periphs_functions[] = {
 	FUNCTION(gpio_periphs),
 	FUNCTION(emmc),
@@ -992,6 +1000,7 @@ static struct meson_pmx_func meson_axg_aobus_functions[] = {
 	FUNCTION(pwm_ao_c),
 	FUNCTION(pwm_ao_d),
 	FUNCTION(jtag_ao),
+	FUNCTION(gen_clk_ee),
 };
 
 static struct meson_bank meson_axg_periphs_banks[] = {
diff --git a/drivers/pinctrl/meson/pinctrl-meson-gxbb.c b/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
index 2c97a2e07a5f..4ceb06f8a33c 100644
--- a/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
+++ b/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
@@ -243,6 +243,8 @@ static const unsigned int i2s_out_ch67_y_pins[]	= { GPIOY_10 };
 
 static const unsigned int spdif_out_y_pins[]	= { GPIOY_12 };
 
+static const unsigned int gen_clk_out_pins[]	= { GPIOY_15 };
+
 static const struct pinctrl_pin_desc meson_gxbb_aobus_pins[] = {
 	MESON_PIN(GPIOAO_0),
 	MESON_PIN(GPIOAO_1),
@@ -453,6 +455,7 @@ static struct meson_pmx_group meson_gxbb_periphs_groups[] = {
 	GROUP(i2s_out_ch45_y,	1,	6),
 	GROUP(i2s_out_ch67_y,	1,	7),
 	GROUP(spdif_out_y,	1,	9),
+	GROUP(gen_clk_out,	6,	15),
 
 	/* Bank Z */
 	GROUP(eth_mdio,		6,	1),
@@ -706,6 +709,10 @@ static const char * const spdif_out_groups[] = {
 	"spdif_out_y",
 };
 
+static const char * const gen_clk_out_groups[] = {
+	"gen_clk_out",
+};
+
 static const char * const gpio_aobus_groups[] = {
 	"GPIOAO_0", "GPIOAO_1", "GPIOAO_2", "GPIOAO_3", "GPIOAO_4",
 	"GPIOAO_5", "GPIOAO_6", "GPIOAO_7", "GPIOAO_8", "GPIOAO_9",
@@ -790,6 +797,7 @@ static struct meson_pmx_func meson_gxbb_periphs_functions[] = {
 	FUNCTION(hdmi_i2c),
 	FUNCTION(i2s_out),
 	FUNCTION(spdif_out),
+	FUNCTION(gen_clk_out),
 };
 
 static struct meson_pmx_func meson_gxbb_aobus_functions[] = {
diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
index 53cf800688e9..aa48b3f23c7f 100644
--- a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
+++ b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
@@ -80,6 +80,18 @@ struct armada_37xx_pmx_func {
 	unsigned int		ngroups;
 };
 
+struct armada_37xx_pm_state {
+	u32 out_en_l;
+	u32 out_en_h;
+	u32 out_val_l;
+	u32 out_val_h;
+	u32 irq_en_l;
+	u32 irq_en_h;
+	u32 irq_pol_l;
+	u32 irq_pol_h;
+	u32 selection;
+};
+
 struct armada_37xx_pinctrl {
 	struct regmap			*regmap;
 	void __iomem			*base;
@@ -94,6 +106,7 @@ struct armada_37xx_pinctrl {
 	unsigned int			ngroups;
 	struct armada_37xx_pmx_func	*funcs;
 	unsigned int			nfuncs;
+	struct armada_37xx_pm_state	pm;
 };
 
 #define PIN_GRP(_name, _start, _nr, _mask, _func1, _func2)	\
@@ -996,6 +1009,110 @@ static int armada_37xx_pinctrl_register(struct platform_device *pdev,
 	return 0;
 }
 
+#if defined(CONFIG_PM)
+static int armada_3700_pinctrl_suspend(struct device *dev)
+{
+	struct armada_37xx_pinctrl *info = dev_get_drvdata(dev);
+
+	/* Save GPIO state */
+	regmap_read(info->regmap, OUTPUT_EN, &info->pm.out_en_l);
+	regmap_read(info->regmap, OUTPUT_EN + sizeof(u32), &info->pm.out_en_h);
+	regmap_read(info->regmap, OUTPUT_VAL, &info->pm.out_val_l);
+	regmap_read(info->regmap, OUTPUT_VAL + sizeof(u32),
+		    &info->pm.out_val_h);
+
+	info->pm.irq_en_l = readl(info->base + IRQ_EN);
+	info->pm.irq_en_h = readl(info->base + IRQ_EN + sizeof(u32));
+	info->pm.irq_pol_l = readl(info->base + IRQ_POL);
+	info->pm.irq_pol_h = readl(info->base + IRQ_POL + sizeof(u32));
+
+	/* Save pinctrl state */
+	regmap_read(info->regmap, SELECTION, &info->pm.selection);
+
+	return 0;
+}
+
+static int armada_3700_pinctrl_resume(struct device *dev)
+{
+	struct armada_37xx_pinctrl *info = dev_get_drvdata(dev);
+	struct gpio_chip *gc;
+	struct irq_domain *d;
+	int i;
+
+	/* Restore GPIO state */
+	regmap_write(info->regmap, OUTPUT_EN, info->pm.out_en_l);
+	regmap_write(info->regmap, OUTPUT_EN + sizeof(u32),
+		     info->pm.out_en_h);
+	regmap_write(info->regmap, OUTPUT_VAL, info->pm.out_val_l);
+	regmap_write(info->regmap, OUTPUT_VAL + sizeof(u32),
+		     info->pm.out_val_h);
+
+	/*
+	 * Input levels may change during suspend, which is not monitored at
+	 * that time. GPIOs used for both-edge IRQs may not be synchronized
+	 * anymore with their polarities (rising/falling edge) and must be
+	 * re-configured manually.
+	 */
+	gc = &info->gpio_chip;
+	d = gc->irq.domain;
+	for (i = 0; i < gc->ngpio; i++) {
+		u32 irq_bit = BIT(i % GPIO_PER_REG);
+		u32 mask, *irq_pol, input_reg, virq, type, level;
+
+		if (i < GPIO_PER_REG) {
+			mask = info->pm.irq_en_l;
+			irq_pol = &info->pm.irq_pol_l;
+			input_reg = INPUT_VAL;
+		} else {
+			mask = info->pm.irq_en_h;
+			irq_pol = &info->pm.irq_pol_h;
+			input_reg = INPUT_VAL + sizeof(u32);
+		}
+
+		if (!(mask & irq_bit))
+			continue;
+
+		virq = irq_find_mapping(d, i);
+		type = irq_get_trigger_type(virq);
+
+		/*
+		 * Synchronize level and polarity for both-edge irqs:
+		 *     - a high input level expects a falling edge,
+		 *     - a low input level exepects a rising edge.
+		 */
+		if ((type & IRQ_TYPE_SENSE_MASK) ==
+		    IRQ_TYPE_EDGE_BOTH) {
+			regmap_read(info->regmap, input_reg, &level);
+			if ((*irq_pol ^ level) & irq_bit)
+				*irq_pol ^= irq_bit;
+		}
+	}
+
+	writel(info->pm.irq_en_l, info->base + IRQ_EN);
+	writel(info->pm.irq_en_h, info->base + IRQ_EN + sizeof(u32));
+	writel(info->pm.irq_pol_l, info->base + IRQ_POL);
+	writel(info->pm.irq_pol_h, info->base + IRQ_POL + sizeof(u32));
+
+	/* Restore pinctrl state */
+	regmap_write(info->regmap, SELECTION, info->pm.selection);
+
+	return 0;
+}
+
+/*
+ * Since pinctrl is an infrastructure module, its resume should be issued prior
+ * to other IO drivers.
+ */
+static const struct dev_pm_ops armada_3700_pinctrl_pm_ops = {
+	.suspend_late = armada_3700_pinctrl_suspend,
+	.resume_early = armada_3700_pinctrl_resume,
+};
+
+#define PINCTRL_ARMADA_37XX_DEV_PM_OPS (&armada_3700_pinctrl_pm_ops)
+#else
+#define PINCTRL_ARMADA_37XX_DEV_PM_OPS NULL
+#endif /* CONFIG_PM */
+
 static const struct of_device_id armada_37xx_pinctrl_of_match[] = {
 	{
 		.compatible = "marvell,armada3710-sb-pinctrl",
@@ -1049,6 +1166,7 @@ static struct platform_driver armada_37xx_pinctrl_driver = {
 	.driver = {
 		.name = "armada-37xx-pinctrl",
 		.of_match_table = armada_37xx_pinctrl_of_match,
+		.pm = PINCTRL_ARMADA_37XX_DEV_PM_OPS,
 	},
 };
 
diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.c b/drivers/pinctrl/nomadik/pinctrl-abx500.c
index aa592ef23a29..e3689cc62a41 100644
--- a/drivers/pinctrl/nomadik/pinctrl-abx500.c
+++ b/drivers/pinctrl/nomadik/pinctrl-abx500.c
@@ -101,15 +101,16 @@ static int abx500_gpio_get_bit(struct gpio_chip *chip, u8 reg,
 	reg += offset / 8;
 	ret = abx500_get_register_interruptible(pct->dev,
 						AB8500_MISC, reg, &val);
-
-	*bit = !!(val & BIT(pos));
-
-	if (ret < 0)
+	if (ret < 0) {
 		dev_err(pct->dev,
 			"%s read reg =%x, offset=%x failed (%d)\n",
 			__func__, reg, offset, ret);
+		return ret;
+	}
 
-	return ret;
+	*bit = !!(val & BIT(pos));
+
+	return 0;
 }
 
 static int abx500_gpio_set_bits(struct gpio_chip *chip, u8 reg,
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 04ae139671c8..41ccc759b8b8 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -247,16 +247,16 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc)
 			raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 
 			if (pin_reg & BIT(INTERRUPT_ENABLE_OFF)) {
+				u8 level = (pin_reg >> ACTIVE_LEVEL_OFF) &
+						ACTIVE_LEVEL_MASK;
 				interrupt_enable = "interrupt is enabled|";
 
-				if (!(pin_reg & BIT(ACTIVE_LEVEL_OFF)) &&
-				    !(pin_reg & BIT(ACTIVE_LEVEL_OFF + 1)))
-					active_level = "Active low|";
-				else if (pin_reg & BIT(ACTIVE_LEVEL_OFF) &&
-					 !(pin_reg & BIT(ACTIVE_LEVEL_OFF + 1)))
+				if (level == ACTIVE_LEVEL_HIGH)
 					active_level = "Active high|";
-				else if (!(pin_reg & BIT(ACTIVE_LEVEL_OFF)) &&
-					 pin_reg & BIT(ACTIVE_LEVEL_OFF + 1))
+				else if (level == ACTIVE_LEVEL_LOW)
+					active_level = "Active low|";
+				else if (!(pin_reg & BIT(LEVEL_TRIG_OFF)) &&
+					 level == ACTIVE_LEVEL_BOTH)
 					active_level = "Active on both|";
 				else
 					active_level = "Unknown Active level|";
@@ -552,7 +552,8 @@ static irqreturn_t amd_gpio_irq_handler(int irq, void *dev_id)
 		/* Each status bit covers four pins */
 		for (i = 0; i < 4; i++) {
 			regval = readl(regs + i);
-			if (!(regval & PIN_IRQ_PENDING))
+			if (!(regval & PIN_IRQ_PENDING) ||
+			    !(regval & BIT(INTERRUPT_MASK_OFF)))
 				continue;
 			irq = irq_find_mapping(gc->irq.domain, irqnr + i);
 			generic_handle_irq(irq);
diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h
index 8fa453a59da5..22af7edfdb38 100644
--- a/drivers/pinctrl/pinctrl-amd.h
+++ b/drivers/pinctrl/pinctrl-amd.h
@@ -54,6 +54,10 @@
 #define ACTIVE_LEVEL_MASK	0x3UL
 #define DRV_STRENGTH_SEL_MASK	0x3UL
 
+#define ACTIVE_LEVEL_HIGH	0x0UL
+#define ACTIVE_LEVEL_LOW	0x1UL
+#define ACTIVE_LEVEL_BOTH	0x2UL
+
 #define DB_TYPE_NO_DEBOUNCE               0x0UL
 #define DB_TYPE_PRESERVE_LOW_GLITCH       0x1UL
 #define DB_TYPE_PRESERVE_HIGH_GLITCH      0x2UL
diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c
index 67e4d9ffa6b1..ef7ab208b951 100644
--- a/drivers/pinctrl/pinctrl-at91-pio4.c
+++ b/drivers/pinctrl/pinctrl-at91-pio4.c
@@ -14,6 +14,7 @@
  * GNU General Public License for more details.
  */
 
+#include <dt-bindings/pinctrl/at91.h>
 #include <linux/clk.h>
 #include <linux/gpio/driver.h>
 /* FIXME: needed for gpio_to_irq(), get rid of this */
@@ -49,6 +50,8 @@
 #define		ATMEL_PIO_IFSCEN_MASK		BIT(13)
 #define		ATMEL_PIO_OPD_MASK		BIT(14)
 #define		ATMEL_PIO_SCHMITT_MASK		BIT(15)
+#define		ATMEL_PIO_DRVSTR_MASK		GENMASK(17, 16)
+#define		ATMEL_PIO_DRVSTR_OFFSET		16
 #define		ATMEL_PIO_CFGR_EVTSEL_MASK	GENMASK(26, 24)
 #define		ATMEL_PIO_CFGR_EVTSEL_FALLING	(0 << 24)
 #define		ATMEL_PIO_CFGR_EVTSEL_RISING	(1 << 24)
@@ -75,6 +78,9 @@
 #define ATMEL_GET_PIN_FUNC(pinfunc)	((pinfunc >> 16) & 0xf)
 #define ATMEL_GET_PIN_IOSET(pinfunc)	((pinfunc >> 20) & 0xf)
 
+/* Custom pinconf parameters */
+#define ATMEL_PIN_CONFIG_DRIVE_STRENGTH	(PIN_CONFIG_END + 1)
+
 struct atmel_pioctrl_data {
 	unsigned nbanks;
 };
@@ -139,6 +145,10 @@ static const char * const atmel_functions[] = {
 	"GPIO", "A", "B", "C", "D", "E", "F", "G"
 };
 
+static const struct pinconf_generic_params atmel_custom_bindings[] = {
+	{"atmel,drive-strength", ATMEL_PIN_CONFIG_DRIVE_STRENGTH, 0},
+};
+
 /* --- GPIO --- */
 static unsigned int atmel_gpio_read(struct atmel_pioctrl *atmel_pioctrl,
 				    unsigned int bank, unsigned int reg)
@@ -692,6 +702,11 @@ static int atmel_conf_pin_config_group_get(struct pinctrl_dev *pctldev,
 			return -EINVAL;
 		arg = 1;
 		break;
+	case ATMEL_PIN_CONFIG_DRIVE_STRENGTH:
+		if (!(res & ATMEL_PIO_DRVSTR_MASK))
+			return -EINVAL;
+		arg = (res & ATMEL_PIO_DRVSTR_MASK) >> ATMEL_PIO_DRVSTR_OFFSET;
+		break;
 	default:
 		return -ENOTSUPP;
 	}
@@ -777,6 +792,18 @@ static int atmel_conf_pin_config_group_set(struct pinctrl_dev *pctldev,
 					ATMEL_PIO_SODR);
 			}
 			break;
+		case ATMEL_PIN_CONFIG_DRIVE_STRENGTH:
+			switch (arg) {
+			case ATMEL_PIO_DRVSTR_LO:
+			case ATMEL_PIO_DRVSTR_ME:
+			case ATMEL_PIO_DRVSTR_HI:
+				conf &= (~ATMEL_PIO_DRVSTR_MASK);
+				conf |= arg << ATMEL_PIO_DRVSTR_OFFSET;
+				break;
+			default:
+				dev_warn(pctldev->dev, "drive strength not updated (incorrect value)\n");
+			}
+			break;
 		default:
 			dev_warn(pctldev->dev,
 				 "unsupported configuration parameter: %u\n",
@@ -816,6 +843,19 @@ static void atmel_conf_pin_config_dbg_show(struct pinctrl_dev *pctldev,
 		seq_printf(s, "%s ", "open-drain");
 	if (conf & ATMEL_PIO_SCHMITT_MASK)
 		seq_printf(s, "%s ", "schmitt");
+	if (conf & ATMEL_PIO_DRVSTR_MASK) {
+		switch ((conf & ATMEL_PIO_DRVSTR_MASK) >> ATMEL_PIO_DRVSTR_OFFSET) {
+		case ATMEL_PIO_DRVSTR_ME:
+			seq_printf(s, "%s ", "medium-drive");
+			break;
+		case ATMEL_PIO_DRVSTR_HI:
+			seq_printf(s, "%s ", "high-drive");
+			break;
+		/* ATMEL_PIO_DRVSTR_LO and 0 which is the default value at reset */
+		default:
+			seq_printf(s, "%s ", "low-drive");
+		}
+	}
 }
 
 static const struct pinconf_ops atmel_confops = {
@@ -931,10 +971,6 @@ static int atmel_pinctrl_probe(struct platform_device *pdev)
 	atmel_pioctrl->npins = atmel_pioctrl->nbanks * ATMEL_PIO_NPINS_PER_BANK;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(dev, "unable to get atmel pinctrl resource\n");
-		return -EINVAL;
-	}
 	atmel_pioctrl->reg_base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(atmel_pioctrl->reg_base))
 		return -EINVAL;
@@ -958,6 +994,8 @@ static int atmel_pinctrl_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	atmel_pinctrl_desc.pins = pin_desc;
 	atmel_pinctrl_desc.npins = atmel_pioctrl->npins;
+	atmel_pinctrl_desc.num_custom_params = ARRAY_SIZE(atmel_custom_bindings);
+	atmel_pinctrl_desc.custom_params = atmel_custom_bindings;
 
 	/* One pin is one group since a pin can achieve all functions. */
 	group_names = devm_kcalloc(dev,
diff --git a/drivers/pinctrl/pinctrl-axp209.c b/drivers/pinctrl/pinctrl-axp209.c
index a52779f33ad4..afd0b533c40a 100644
--- a/drivers/pinctrl/pinctrl-axp209.c
+++ b/drivers/pinctrl/pinctrl-axp209.c
@@ -316,7 +316,7 @@ static const struct pinctrl_ops axp20x_pctrl_ops = {
 	.get_group_pins		= axp20x_group_pins,
 };
 
-static void axp20x_funcs_groups_from_mask(struct device *dev, unsigned int mask,
+static int axp20x_funcs_groups_from_mask(struct device *dev, unsigned int mask,
 					  unsigned int mask_len,
 					  struct axp20x_pinctrl_function *func,
 					  const struct pinctrl_pin_desc *pins)
@@ -331,18 +331,22 @@ static void axp20x_funcs_groups_from_mask(struct device *dev, unsigned int mask,
 		func->groups = devm_kcalloc(dev,
 					    ngroups, sizeof(const char *),
 					    GFP_KERNEL);
+		if (!func->groups)
+			return -ENOMEM;
 		group = func->groups;
 		for_each_set_bit(bit, &mask_cpy, mask_len) {
 			*group = pins[bit].name;
 			group++;
 		}
 	}
+
+	return 0;
 }
 
-static void axp20x_build_funcs_groups(struct platform_device *pdev)
+static int axp20x_build_funcs_groups(struct platform_device *pdev)
 {
 	struct axp20x_pctl *pctl = platform_get_drvdata(pdev);
-	int i, pin, npins = pctl->desc->npins;
+	int i, ret, pin, npins = pctl->desc->npins;
 
 	pctl->funcs[AXP20X_FUNC_GPIO_OUT].name = "gpio_out";
 	pctl->funcs[AXP20X_FUNC_GPIO_OUT].muxval = AXP20X_MUX_GPIO_OUT;
@@ -366,13 +370,19 @@ static void axp20x_build_funcs_groups(struct platform_device *pdev)
 			pctl->funcs[i].groups[pin] = pctl->desc->pins[pin].name;
 	}
 
-	axp20x_funcs_groups_from_mask(&pdev->dev, pctl->desc->ldo_mask,
+	ret = axp20x_funcs_groups_from_mask(&pdev->dev, pctl->desc->ldo_mask,
 				      npins, &pctl->funcs[AXP20X_FUNC_LDO],
 				      pctl->desc->pins);
+	if (ret)
+		return ret;
 
-	axp20x_funcs_groups_from_mask(&pdev->dev, pctl->desc->adc_mask,
+	ret = axp20x_funcs_groups_from_mask(&pdev->dev, pctl->desc->adc_mask,
 				      npins, &pctl->funcs[AXP20X_FUNC_ADC],
 				      pctl->desc->pins);
+	if (ret)
+		return ret;
+
+	return 0;
 }
 
 static const struct of_device_id axp20x_pctl_match[] = {
@@ -424,7 +434,11 @@ static int axp20x_pctl_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, pctl);
 
-	axp20x_build_funcs_groups(pdev);
+	ret = axp20x_build_funcs_groups(pdev);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to build groups\n");
+		return ret;
+	}
 
 	pctrl_desc = devm_kzalloc(&pdev->dev, sizeof(*pctrl_desc), GFP_KERNEL);
 	if (!pctrl_desc)
diff --git a/drivers/pinctrl/pinctrl-gemini.c b/drivers/pinctrl/pinctrl-gemini.c
index 8c9970ae8505..fa7d998e1d5a 100644
--- a/drivers/pinctrl/pinctrl-gemini.c
+++ b/drivers/pinctrl/pinctrl-gemini.c
@@ -1696,6 +1696,7 @@ static const struct gemini_pin_group gemini_3516_pin_groups[] = {
 		.name = "gmii_gmac0_grp",
 		.pins = gmii_gmac0_3516_pins,
 		.num_pins = ARRAY_SIZE(gmii_gmac0_3516_pins),
+		.mask = GEMINI_GMAC_IOSEL_MASK,
 		.driving_mask = GENMASK(17, 16),
 	},
 	{
@@ -1703,6 +1704,7 @@ static const struct gemini_pin_group gemini_3516_pin_groups[] = {
 		.pins = gmii_gmac1_3516_pins,
 		.num_pins = ARRAY_SIZE(gmii_gmac1_3516_pins),
 		/* Bring out RGMII on the GMAC1 pins */
+		.mask = GEMINI_GMAC_IOSEL_MASK,
 		.value = GEMINI_GMAC_IOSEL_GMAC0_GMAC1_RGMII,
 		.driving_mask = GENMASK(19, 18),
 	},
diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c
index 022307dd4b54..4a8a8efadefa 100644
--- a/drivers/pinctrl/pinctrl-mcp23s08.c
+++ b/drivers/pinctrl/pinctrl-mcp23s08.c
@@ -666,7 +666,7 @@ static int mcp23s08_irq_setup(struct mcp23s08 *mcp)
  * can be used to fix state for MCP23xxx, that temporary
  * lost its power supply.
  */
-#define MCP23S08_CONFIG_REGS 8
+#define MCP23S08_CONFIG_REGS 7
 static int __check_mcp23s08_reg_cache(struct mcp23s08 *mcp)
 {
 	int cached[MCP23S08_CONFIG_REGS];
diff --git a/drivers/pinctrl/pinctrl-ocelot.c b/drivers/pinctrl/pinctrl-ocelot.c
index 15bb1cb8729b..f9fc2b3a8731 100644
--- a/drivers/pinctrl/pinctrl-ocelot.c
+++ b/drivers/pinctrl/pinctrl-ocelot.c
@@ -11,6 +11,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/of_device.h>
+#include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/pinctrl/pinctrl.h>
 #include <linux/pinctrl/pinmux.h>
@@ -132,7 +133,7 @@ OCELOT_P(0,  SG0,       NONE,      NONE);
 OCELOT_P(1,  SG0,       NONE,      NONE);
 OCELOT_P(2,  SG0,       NONE,      NONE);
 OCELOT_P(3,  SG0,       NONE,      NONE);
-OCELOT_P(4,  IRQ0_IN,   IRQ0_OUT,  TWI);
+OCELOT_P(4,  IRQ0_IN,   IRQ0_OUT,  TWI_SCL_M);
 OCELOT_P(5,  IRQ1_IN,   IRQ1_OUT,  PCI_WAKE);
 OCELOT_P(6,  UART,      TWI_SCL_M, NONE);
 OCELOT_P(7,  UART,      TWI_SCL_M, NONE);
@@ -427,11 +428,98 @@ static const struct gpio_chip ocelot_gpiolib_chip = {
 	.owner = THIS_MODULE,
 };
 
+static void ocelot_irq_mask(struct irq_data *data)
+{
+	struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
+	struct ocelot_pinctrl *info = gpiochip_get_data(chip);
+	unsigned int gpio = irqd_to_hwirq(data);
+
+	regmap_update_bits(info->map, OCELOT_GPIO_INTR_ENA, BIT(gpio), 0);
+}
+
+static void ocelot_irq_unmask(struct irq_data *data)
+{
+	struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
+	struct ocelot_pinctrl *info = gpiochip_get_data(chip);
+	unsigned int gpio = irqd_to_hwirq(data);
+
+	regmap_update_bits(info->map, OCELOT_GPIO_INTR_ENA, BIT(gpio),
+			   BIT(gpio));
+}
+
+static void ocelot_irq_ack(struct irq_data *data)
+{
+	struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
+	struct ocelot_pinctrl *info = gpiochip_get_data(chip);
+	unsigned int gpio = irqd_to_hwirq(data);
+
+	regmap_write_bits(info->map, OCELOT_GPIO_INTR, BIT(gpio), BIT(gpio));
+}
+
+static int ocelot_irq_set_type(struct irq_data *data, unsigned int type);
+
+static struct irq_chip ocelot_eoi_irqchip = {
+	.name		= "gpio",
+	.irq_mask	= ocelot_irq_mask,
+	.irq_eoi	= ocelot_irq_ack,
+	.irq_unmask	= ocelot_irq_unmask,
+	.flags          = IRQCHIP_EOI_THREADED | IRQCHIP_EOI_IF_HANDLED,
+	.irq_set_type	= ocelot_irq_set_type,
+};
+
+static struct irq_chip ocelot_irqchip = {
+	.name		= "gpio",
+	.irq_mask	= ocelot_irq_mask,
+	.irq_ack	= ocelot_irq_ack,
+	.irq_unmask	= ocelot_irq_unmask,
+	.irq_set_type	= ocelot_irq_set_type,
+};
+
+static int ocelot_irq_set_type(struct irq_data *data, unsigned int type)
+{
+	type &= IRQ_TYPE_SENSE_MASK;
+
+	if (!(type & (IRQ_TYPE_EDGE_BOTH | IRQ_TYPE_LEVEL_HIGH)))
+		return -EINVAL;
+
+	if (type & IRQ_TYPE_LEVEL_HIGH)
+		irq_set_chip_handler_name_locked(data, &ocelot_eoi_irqchip,
+						 handle_fasteoi_irq, NULL);
+	if (type & IRQ_TYPE_EDGE_BOTH)
+		irq_set_chip_handler_name_locked(data, &ocelot_irqchip,
+						 handle_edge_irq, NULL);
+
+	return 0;
+}
+
+static void ocelot_irq_handler(struct irq_desc *desc)
+{
+	struct irq_chip *parent_chip = irq_desc_get_chip(desc);
+	struct gpio_chip *chip = irq_desc_get_handler_data(desc);
+	struct ocelot_pinctrl *info = gpiochip_get_data(chip);
+	unsigned int reg = 0, irq;
+	unsigned long irqs;
+
+	regmap_read(info->map, OCELOT_GPIO_INTR_IDENT, &reg);
+	if (!reg)
+		return;
+
+	chained_irq_enter(parent_chip, desc);
+
+	irqs = reg;
+
+	for_each_set_bit(irq, &irqs, OCELOT_PINS) {
+		generic_handle_irq(irq_linear_revmap(chip->irq.domain, irq));
+	}
+
+	chained_irq_exit(parent_chip, desc);
+}
+
 static int ocelot_gpiochip_register(struct platform_device *pdev,
 				    struct ocelot_pinctrl *info)
 {
 	struct gpio_chip *gc;
-	int ret;
+	int ret, irq;
 
 	info->gpio_chip = ocelot_gpiolib_chip;
 
@@ -446,7 +534,17 @@ static int ocelot_gpiochip_register(struct platform_device *pdev,
 	if (ret)
 		return ret;
 
-	/* TODO: this can be used as an irqchip but no board is using that */
+	irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
+	if (irq <= 0)
+		return irq;
+
+	ret = gpiochip_irqchip_add(gc, &ocelot_irqchip, 0, handle_edge_irq,
+				   IRQ_TYPE_NONE);
+	if (ret)
+		return ret;
+
+	gpiochip_set_chained_irqchip(gc, &ocelot_irqchip, irq,
+				     ocelot_irq_handler);
 
 	return 0;
 }
diff --git a/drivers/pinctrl/pinctrl-rza1.c b/drivers/pinctrl/pinctrl-rza1.c
index 717c0f4449a0..f76edf664539 100644
--- a/drivers/pinctrl/pinctrl-rza1.c
+++ b/drivers/pinctrl/pinctrl-rza1.c
@@ -1006,6 +1006,7 @@ static int rza1_dt_node_to_map(struct pinctrl_dev *pctldev,
 	const char *grpname;
 	const char **fngrps;
 	int ret, npins;
+	int gsel, fsel;
 
 	npins = rza1_dt_node_pin_count(np);
 	if (npins < 0) {
@@ -1055,18 +1056,19 @@ static int rza1_dt_node_to_map(struct pinctrl_dev *pctldev,
 	fngrps[0] = grpname;
 
 	mutex_lock(&rza1_pctl->mutex);
-	ret = pinctrl_generic_add_group(pctldev, grpname, grpins, npins,
-					NULL);
-	if (ret) {
+	gsel = pinctrl_generic_add_group(pctldev, grpname, grpins, npins,
+					 NULL);
+	if (gsel < 0) {
 		mutex_unlock(&rza1_pctl->mutex);
-		return ret;
+		return gsel;
 	}
 
-	ret = pinmux_generic_add_function(pctldev, grpname, fngrps, 1,
-					  mux_confs);
-	if (ret)
+	fsel = pinmux_generic_add_function(pctldev, grpname, fngrps, 1,
+					   mux_confs);
+	if (fsel < 0) {
+		ret = fsel;
 		goto remove_group;
-	mutex_unlock(&rza1_pctl->mutex);
+	}
 
 	dev_info(rza1_pctl->dev, "Parsed function and group %s with %d pins\n",
 				 grpname, npins);
@@ -1083,15 +1085,15 @@ static int rza1_dt_node_to_map(struct pinctrl_dev *pctldev,
 	(*map)->data.mux.group = np->name;
 	(*map)->data.mux.function = np->name;
 	*num_maps = 1;
+	mutex_unlock(&rza1_pctl->mutex);
 
 	return 0;
 
 remove_function:
-	mutex_lock(&rza1_pctl->mutex);
-	pinmux_generic_remove_last_function(pctldev);
+	pinmux_generic_remove_function(pctldev, fsel);
 
 remove_group:
-	pinctrl_generic_remove_last_group(pctldev);
+	pinctrl_generic_remove_group(pctldev, gsel);
 	mutex_unlock(&rza1_pctl->mutex);
 
 	dev_info(rza1_pctl->dev, "Unable to parse function and group %s\n",
diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index e5647dac0818..7ec72ff2419a 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -747,38 +747,44 @@ static int pcs_allocate_pin_table(struct pcs_device *pcs)
 /**
  * pcs_add_function() - adds a new function to the function list
  * @pcs: pcs driver instance
- * @np: device node of the mux entry
+ * @fcn: new function allocated
  * @name: name of the function
  * @vals: array of mux register value pairs used by the function
  * @nvals: number of mux register value pairs
  * @pgnames: array of pingroup names for the function
  * @npgnames: number of pingroup names
+ *
+ * Caller must take care of locking.
  */
-static struct pcs_function *pcs_add_function(struct pcs_device *pcs,
-					struct device_node *np,
-					const char *name,
-					struct pcs_func_vals *vals,
-					unsigned nvals,
-					const char **pgnames,
-					unsigned npgnames)
+static int pcs_add_function(struct pcs_device *pcs,
+			    struct pcs_function **fcn,
+			    const char *name,
+			    struct pcs_func_vals *vals,
+			    unsigned int nvals,
+			    const char **pgnames,
+			    unsigned int npgnames)
 {
 	struct pcs_function *function;
-	int res;
+	int selector;
 
 	function = devm_kzalloc(pcs->dev, sizeof(*function), GFP_KERNEL);
 	if (!function)
-		return NULL;
+		return -ENOMEM;
 
 	function->vals = vals;
 	function->nvals = nvals;
 
-	res = pinmux_generic_add_function(pcs->pctl, name,
-					  pgnames, npgnames,
-					  function);
-	if (res)
-		return NULL;
+	selector = pinmux_generic_add_function(pcs->pctl, name,
+					       pgnames, npgnames,
+					       function);
+	if (selector < 0) {
+		devm_kfree(pcs->dev, function);
+		*fcn = NULL;
+	} else {
+		*fcn = function;
+	}
 
-	return function;
+	return selector;
 }
 
 /**
@@ -979,8 +985,8 @@ static int pcs_parse_one_pinctrl_entry(struct pcs_device *pcs,
 {
 	const char *name = "pinctrl-single,pins";
 	struct pcs_func_vals *vals;
-	int rows, *pins, found = 0, res = -ENOMEM, i;
-	struct pcs_function *function;
+	int rows, *pins, found = 0, res = -ENOMEM, i, fsel, gsel;
+	struct pcs_function *function = NULL;
 
 	rows = pinctrl_count_index_with_args(np, name);
 	if (rows <= 0) {
@@ -1030,21 +1036,25 @@ static int pcs_parse_one_pinctrl_entry(struct pcs_device *pcs,
 	}
 
 	pgnames[0] = np->name;
-	function = pcs_add_function(pcs, np, np->name, vals, found, pgnames, 1);
-	if (!function) {
-		res = -ENOMEM;
+	mutex_lock(&pcs->mutex);
+	fsel = pcs_add_function(pcs, &function, np->name, vals, found,
+				pgnames, 1);
+	if (fsel < 0) {
+		res = fsel;
 		goto free_pins;
 	}
 
-	res = pinctrl_generic_add_group(pcs->pctl, np->name, pins, found, pcs);
-	if (res < 0)
+	gsel = pinctrl_generic_add_group(pcs->pctl, np->name, pins, found, pcs);
+	if (gsel < 0) {
+		res = gsel;
 		goto free_function;
+	}
 
 	(*map)->type = PIN_MAP_TYPE_MUX_GROUP;
 	(*map)->data.mux.group = np->name;
 	(*map)->data.mux.function = np->name;
 
-	if (PCS_HAS_PINCONF) {
+	if (PCS_HAS_PINCONF && function) {
 		res = pcs_parse_pinconf(pcs, np, function, map);
 		if (res)
 			goto free_pingroups;
@@ -1052,15 +1062,17 @@ static int pcs_parse_one_pinctrl_entry(struct pcs_device *pcs,
 	} else {
 		*num_maps = 1;
 	}
+	mutex_unlock(&pcs->mutex);
+
 	return 0;
 
 free_pingroups:
-	pinctrl_generic_remove_last_group(pcs->pctl);
+	pinctrl_generic_remove_group(pcs->pctl, gsel);
 	*num_maps = 1;
 free_function:
-	pinmux_generic_remove_last_function(pcs->pctl);
-
+	pinmux_generic_remove_function(pcs->pctl, fsel);
 free_pins:
+	mutex_unlock(&pcs->mutex);
 	devm_kfree(pcs->dev, pins);
 
 free_vals:
@@ -1077,9 +1089,9 @@ static int pcs_parse_bits_in_pinctrl_entry(struct pcs_device *pcs,
 {
 	const char *name = "pinctrl-single,bits";
 	struct pcs_func_vals *vals;
-	int rows, *pins, found = 0, res = -ENOMEM, i;
+	int rows, *pins, found = 0, res = -ENOMEM, i, fsel, gsel;
 	int npins_in_row;
-	struct pcs_function *function;
+	struct pcs_function *function = NULL;
 
 	rows = pinctrl_count_index_with_args(np, name);
 	if (rows <= 0) {
@@ -1166,15 +1178,19 @@ static int pcs_parse_bits_in_pinctrl_entry(struct pcs_device *pcs,
 	}
 
 	pgnames[0] = np->name;
-	function = pcs_add_function(pcs, np, np->name, vals, found, pgnames, 1);
-	if (!function) {
-		res = -ENOMEM;
+	mutex_lock(&pcs->mutex);
+	fsel = pcs_add_function(pcs, &function, np->name, vals, found,
+				pgnames, 1);
+	if (fsel < 0) {
+		res = fsel;
 		goto free_pins;
 	}
 
-	res = pinctrl_generic_add_group(pcs->pctl, np->name, pins, found, pcs);
-	if (res < 0)
+	gsel = pinctrl_generic_add_group(pcs->pctl, np->name, pins, found, pcs);
+	if (gsel < 0) {
+		res = gsel;
 		goto free_function;
+	}
 
 	(*map)->type = PIN_MAP_TYPE_MUX_GROUP;
 	(*map)->data.mux.group = np->name;
@@ -1186,14 +1202,17 @@ static int pcs_parse_bits_in_pinctrl_entry(struct pcs_device *pcs,
 	}
 
 	*num_maps = 1;
+	mutex_unlock(&pcs->mutex);
+
 	return 0;
 
 free_pingroups:
-	pinctrl_generic_remove_last_group(pcs->pctl);
+	pinctrl_generic_remove_group(pcs->pctl, gsel);
 	*num_maps = 1;
 free_function:
-	pinmux_generic_remove_last_function(pcs->pctl);
+	pinmux_generic_remove_function(pcs->pctl, fsel);
 free_pins:
+	mutex_unlock(&pcs->mutex);
 	devm_kfree(pcs->dev, pins);
 
 free_vals:
@@ -1598,19 +1617,19 @@ static int pcs_save_context(struct pcs_device *pcs)
 
 	switch (pcs->width) {
 	case 64:
-		regsl = (u64 *)pcs->saved_vals;
-		for (i = 0; i < pcs->size / mux_bytes; i++)
-			regsl[i] = pcs->read(pcs->base + i * mux_bytes);
+		regsl = pcs->saved_vals;
+		for (i = 0; i < pcs->size; i += mux_bytes)
+			*regsl++ = pcs->read(pcs->base + i);
 		break;
 	case 32:
-		regsw = (u32 *)pcs->saved_vals;
-		for (i = 0; i < pcs->size / mux_bytes; i++)
-			regsw[i] = pcs->read(pcs->base + i * mux_bytes);
+		regsw = pcs->saved_vals;
+		for (i = 0; i < pcs->size; i += mux_bytes)
+			*regsw++ = pcs->read(pcs->base + i);
 		break;
 	case 16:
-		regshw = (u16 *)pcs->saved_vals;
-		for (i = 0; i < pcs->size / mux_bytes; i++)
-			regshw[i] = pcs->read(pcs->base + i * mux_bytes);
+		regshw = pcs->saved_vals;
+		for (i = 0; i < pcs->size; i += mux_bytes)
+			*regshw++ = pcs->read(pcs->base + i);
 		break;
 	}
 
@@ -1628,19 +1647,19 @@ static void pcs_restore_context(struct pcs_device *pcs)
 
 	switch (pcs->width) {
 	case 64:
-		regsl = (u64 *)pcs->saved_vals;
-		for (i = 0; i < pcs->size / mux_bytes; i++)
-			pcs->write(regsl[i], pcs->base + i * mux_bytes);
+		regsl = pcs->saved_vals;
+		for (i = 0; i < pcs->size; i += mux_bytes)
+			pcs->write(*regsl++, pcs->base + i);
 		break;
 	case 32:
-		regsw = (u32 *)pcs->saved_vals;
-		for (i = 0; i < pcs->size / mux_bytes; i++)
-			pcs->write(regsw[i], pcs->base + i * mux_bytes);
+		regsw = pcs->saved_vals;
+		for (i = 0; i < pcs->size; i += mux_bytes)
+			pcs->write(*regsw++, pcs->base + i);
 		break;
 	case 16:
-		regshw = (u16 *)pcs->saved_vals;
-		for (i = 0; i < pcs->size / mux_bytes; i++)
-			pcs->write(regshw[i], pcs->base + i * mux_bytes);
+		regshw = pcs->saved_vals;
+		for (i = 0; i < pcs->size; i += mux_bytes)
+			pcs->write(*regshw++, pcs->base + i);
 		break;
 	}
 }
diff --git a/drivers/pinctrl/pinmux.c b/drivers/pinctrl/pinmux.c
index b8e9bda8ec98..5780442c068b 100644
--- a/drivers/pinctrl/pinmux.c
+++ b/drivers/pinctrl/pinmux.c
@@ -22,7 +22,6 @@
 #include <linux/err.h>
 #include <linux/list.h>
 #include <linux/string.h>
-#include <linux/sysfs.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/pinctrl/machine.h>
@@ -308,7 +307,6 @@ static int pinmux_func_name_to_selector(struct pinctrl_dev *pctldev,
 		selector++;
 	}
 
-	dev_err(pctldev->dev, "function '%s' not supported\n", function);
 	return -EINVAL;
 }
 
@@ -775,6 +773,16 @@ int pinmux_generic_add_function(struct pinctrl_dev *pctldev,
 				void *data)
 {
 	struct function_desc *function;
+	int selector;
+
+	if (!name)
+		return -EINVAL;
+
+	selector = pinmux_func_name_to_selector(pctldev, name);
+	if (selector >= 0)
+		return selector;
+
+	selector = pctldev->num_functions;
 
 	function = devm_kzalloc(pctldev->dev, sizeof(*function), GFP_KERNEL);
 	if (!function)
@@ -785,12 +793,11 @@ int pinmux_generic_add_function(struct pinctrl_dev *pctldev,
 	function->num_group_names = num_groups;
 	function->data = data;
 
-	radix_tree_insert(&pctldev->pin_function_tree, pctldev->num_functions,
-			  function);
+	radix_tree_insert(&pctldev->pin_function_tree, selector, function);
 
 	pctldev->num_functions++;
 
-	return 0;
+	return selector;
 }
 EXPORT_SYMBOL_GPL(pinmux_generic_add_function);
 
diff --git a/drivers/pinctrl/pinmux.h b/drivers/pinctrl/pinmux.h
index a331fcdbedd9..3319535c76cb 100644
--- a/drivers/pinctrl/pinmux.h
+++ b/drivers/pinctrl/pinmux.h
@@ -150,13 +150,6 @@ int pinmux_generic_add_function(struct pinctrl_dev *pctldev,
 int pinmux_generic_remove_function(struct pinctrl_dev *pctldev,
 				   unsigned int selector);
 
-static inline int
-pinmux_generic_remove_last_function(struct pinctrl_dev *pctldev)
-{
-	return pinmux_generic_remove_function(pctldev,
-					      pctldev->num_functions - 1);
-}
-
 void pinmux_generic_free_functions(struct pinctrl_dev *pctldev);
 
 #else
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index 0e22f52b2a19..2155a30c282b 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -250,22 +250,30 @@ static int msm_config_group_get(struct pinctrl_dev *pctldev,
 	/* Convert register value to pinconf value */
 	switch (param) {
 	case PIN_CONFIG_BIAS_DISABLE:
-		arg = arg == MSM_NO_PULL;
+		if (arg != MSM_NO_PULL)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_PULL_DOWN:
-		arg = arg == MSM_PULL_DOWN;
+		if (arg != MSM_PULL_DOWN)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_BUS_HOLD:
 		if (pctrl->soc->pull_no_keeper)
 			return -ENOTSUPP;
 
-		arg = arg == MSM_KEEPER;
+		if (arg != MSM_KEEPER)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_PULL_UP:
 		if (pctrl->soc->pull_no_keeper)
 			arg = arg == MSM_PULL_UP_NO_KEEPER;
 		else
 			arg = arg == MSM_PULL_UP;
+		if (!arg)
+			return -EINVAL;
 		break;
 	case PIN_CONFIG_DRIVE_STRENGTH:
 		arg = msm_regval_to_drive(arg);
diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
index 3e66e0d10010..cf82db78e69e 100644
--- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
+++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
@@ -390,31 +390,47 @@ static int pmic_gpio_config_get(struct pinctrl_dev *pctldev,
 
 	switch (param) {
 	case PIN_CONFIG_DRIVE_PUSH_PULL:
-		arg = pad->buffer_type == PMIC_GPIO_OUT_BUF_CMOS;
+		if (pad->buffer_type != PMIC_GPIO_OUT_BUF_CMOS)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_DRIVE_OPEN_DRAIN:
-		arg = pad->buffer_type == PMIC_GPIO_OUT_BUF_OPEN_DRAIN_NMOS;
+		if (pad->buffer_type != PMIC_GPIO_OUT_BUF_OPEN_DRAIN_NMOS)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_DRIVE_OPEN_SOURCE:
-		arg = pad->buffer_type == PMIC_GPIO_OUT_BUF_OPEN_DRAIN_PMOS;
+		if (pad->buffer_type != PMIC_GPIO_OUT_BUF_OPEN_DRAIN_PMOS)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_PULL_DOWN:
-		arg = pad->pullup == PMIC_GPIO_PULL_DOWN;
+		if (pad->pullup != PMIC_GPIO_PULL_DOWN)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_DISABLE:
-		arg = pad->pullup = PMIC_GPIO_PULL_DISABLE;
+		if (pad->pullup != PMIC_GPIO_PULL_DISABLE)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_PULL_UP:
-		arg = pad->pullup == PMIC_GPIO_PULL_UP_30;
+		if (pad->pullup != PMIC_GPIO_PULL_UP_30)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_HIGH_IMPEDANCE:
-		arg = !pad->is_enabled;
+		if (pad->is_enabled)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_POWER_SOURCE:
 		arg = pad->power_source;
 		break;
 	case PIN_CONFIG_INPUT_ENABLE:
-		arg = pad->input_enabled;
+		if (!pad->input_enabled)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_OUTPUT:
 		arg = pad->out_value;
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos-arm.c b/drivers/pinctrl/samsung/pinctrl-exynos-arm.c
index d82820fc349a..44c6b753f692 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos-arm.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos-arm.c
@@ -616,16 +616,22 @@ static const struct samsung_pin_ctrl exynos5260_pin_ctrl[] __initconst = {
 		.nr_banks	= ARRAY_SIZE(exynos5260_pin_banks0),
 		.eint_gpio_init = exynos_eint_gpio_init,
 		.eint_wkup_init = exynos_eint_wkup_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 	}, {
 		/* pin-controller instance 1 data */
 		.pin_banks	= exynos5260_pin_banks1,
 		.nr_banks	= ARRAY_SIZE(exynos5260_pin_banks1),
 		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 	}, {
 		/* pin-controller instance 2 data */
 		.pin_banks	= exynos5260_pin_banks2,
 		.nr_banks	= ARRAY_SIZE(exynos5260_pin_banks2),
 		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 	},
 };
 
@@ -842,30 +848,40 @@ static const struct samsung_pin_ctrl exynos5420_pin_ctrl[] __initconst = {
 		.nr_banks	= ARRAY_SIZE(exynos5420_pin_banks0),
 		.eint_gpio_init = exynos_eint_gpio_init,
 		.eint_wkup_init = exynos_eint_wkup_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 		.retention_data	= &exynos5420_retention_data,
 	}, {
 		/* pin-controller instance 1 data */
 		.pin_banks	= exynos5420_pin_banks1,
 		.nr_banks	= ARRAY_SIZE(exynos5420_pin_banks1),
 		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 		.retention_data	= &exynos5420_retention_data,
 	}, {
 		/* pin-controller instance 2 data */
 		.pin_banks	= exynos5420_pin_banks2,
 		.nr_banks	= ARRAY_SIZE(exynos5420_pin_banks2),
 		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 		.retention_data	= &exynos5420_retention_data,
 	}, {
 		/* pin-controller instance 3 data */
 		.pin_banks	= exynos5420_pin_banks3,
 		.nr_banks	= ARRAY_SIZE(exynos5420_pin_banks3),
 		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 		.retention_data	= &exynos5420_retention_data,
 	}, {
 		/* pin-controller instance 4 data */
 		.pin_banks	= exynos5420_pin_banks4,
 		.nr_banks	= ARRAY_SIZE(exynos5420_pin_banks4),
 		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 		.retention_data	= &exynos4_audio_retention_data,
 	},
 };
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index a263ddd94945..f49ea3d92aa1 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -25,6 +25,7 @@
 #include <linux/regmap.h>
 #include <linux/err.h>
 #include <linux/soc/samsung/exynos-pmu.h>
+#include <linux/soc/samsung/exynos-regs-pmu.h>
 
 #include <dt-bindings/pinctrl/samsung.h>
 
@@ -37,6 +38,8 @@ struct exynos_irq_chip {
 	u32 eint_con;
 	u32 eint_mask;
 	u32 eint_pend;
+	u32 eint_wake_mask_value;
+	u32 eint_wake_mask_reg;
 };
 
 static inline struct exynos_irq_chip *to_exynos_irq_chip(struct irq_chip *chip)
@@ -215,6 +218,7 @@ static struct exynos_irq_chip exynos_gpio_irq_chip = {
 	.eint_con = EXYNOS_GPIO_ECON_OFFSET,
 	.eint_mask = EXYNOS_GPIO_EMASK_OFFSET,
 	.eint_pend = EXYNOS_GPIO_EPEND_OFFSET,
+	/* eint_wake_mask_value not used */
 };
 
 static int exynos_eint_irq_map(struct irq_domain *h, unsigned int virq,
@@ -330,6 +334,8 @@ u32 exynos_get_eint_wake_mask(void)
 
 static int exynos_wkup_irq_set_wake(struct irq_data *irqd, unsigned int on)
 {
+	struct irq_chip *chip = irq_data_get_irq_chip(irqd);
+	struct exynos_irq_chip *our_chip = to_exynos_irq_chip(chip);
 	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
 	unsigned long bit = 1UL << (2 * bank->eint_offset + irqd->hwirq);
 
@@ -339,6 +345,7 @@ static int exynos_wkup_irq_set_wake(struct irq_data *irqd, unsigned int on)
 		exynos_eint_wake_mask |= bit;
 	else
 		exynos_eint_wake_mask &= ~bit;
+	our_chip->eint_wake_mask_value = exynos_eint_wake_mask;
 
 	return 0;
 }
@@ -346,6 +353,25 @@ static int exynos_wkup_irq_set_wake(struct irq_data *irqd, unsigned int on)
 /*
  * irq_chip for wakeup interrupts
  */
+static const struct exynos_irq_chip s5pv210_wkup_irq_chip __initconst = {
+	.chip = {
+		.name = "s5pv210_wkup_irq_chip",
+		.irq_unmask = exynos_irq_unmask,
+		.irq_mask = exynos_irq_mask,
+		.irq_ack = exynos_irq_ack,
+		.irq_set_type = exynos_irq_set_type,
+		.irq_set_wake = exynos_wkup_irq_set_wake,
+		.irq_request_resources = exynos_irq_request_resources,
+		.irq_release_resources = exynos_irq_release_resources,
+	},
+	.eint_con = EXYNOS_WKUP_ECON_OFFSET,
+	.eint_mask = EXYNOS_WKUP_EMASK_OFFSET,
+	.eint_pend = EXYNOS_WKUP_EPEND_OFFSET,
+	.eint_wake_mask_value = EXYNOS_EINT_WAKEUP_MASK_DISABLED,
+	/* Only difference with exynos4210_wkup_irq_chip: */
+	.eint_wake_mask_reg = S5PV210_EINT_WAKEUP_MASK,
+};
+
 static const struct exynos_irq_chip exynos4210_wkup_irq_chip __initconst = {
 	.chip = {
 		.name = "exynos4210_wkup_irq_chip",
@@ -360,6 +386,8 @@ static const struct exynos_irq_chip exynos4210_wkup_irq_chip __initconst = {
 	.eint_con = EXYNOS_WKUP_ECON_OFFSET,
 	.eint_mask = EXYNOS_WKUP_EMASK_OFFSET,
 	.eint_pend = EXYNOS_WKUP_EPEND_OFFSET,
+	.eint_wake_mask_value = EXYNOS_EINT_WAKEUP_MASK_DISABLED,
+	.eint_wake_mask_reg = EXYNOS_EINT_WAKEUP_MASK,
 };
 
 static const struct exynos_irq_chip exynos7_wkup_irq_chip __initconst = {
@@ -376,10 +404,14 @@ static const struct exynos_irq_chip exynos7_wkup_irq_chip __initconst = {
 	.eint_con = EXYNOS7_WKUP_ECON_OFFSET,
 	.eint_mask = EXYNOS7_WKUP_EMASK_OFFSET,
 	.eint_pend = EXYNOS7_WKUP_EPEND_OFFSET,
+	.eint_wake_mask_value = EXYNOS_EINT_WAKEUP_MASK_DISABLED,
+	.eint_wake_mask_reg = EXYNOS5433_EINT_WAKEUP_MASK,
 };
 
 /* list of external wakeup controllers supported */
 static const struct of_device_id exynos_wkup_irq_ids[] = {
+	{ .compatible = "samsung,s5pv210-wakeup-eint",
+			.data = &s5pv210_wkup_irq_chip },
 	{ .compatible = "samsung,exynos4210-wakeup-eint",
 			.data = &exynos4210_wkup_irq_chip },
 	{ .compatible = "samsung,exynos7-wakeup-eint",
@@ -542,6 +574,27 @@ int exynos_eint_wkup_init(struct samsung_pinctrl_drv_data *d)
 	return 0;
 }
 
+static void
+exynos_pinctrl_set_eint_wakeup_mask(struct samsung_pinctrl_drv_data *drvdata,
+				    struct exynos_irq_chip *irq_chip)
+{
+	struct regmap *pmu_regs;
+
+	if (!drvdata->retention_ctrl || !drvdata->retention_ctrl->priv) {
+		dev_warn(drvdata->dev,
+			 "No retention data configured bank with external wakeup interrupt. Wake-up mask will not be set.\n");
+		return;
+	}
+
+	pmu_regs = drvdata->retention_ctrl->priv;
+	dev_info(drvdata->dev,
+		 "Setting external wakeup interrupt mask: 0x%x\n",
+		 irq_chip->eint_wake_mask_value);
+
+	regmap_write(pmu_regs, irq_chip->eint_wake_mask_reg,
+		     irq_chip->eint_wake_mask_value);
+}
+
 static void exynos_pinctrl_suspend_bank(
 				struct samsung_pinctrl_drv_data *drvdata,
 				struct samsung_pin_bank *bank)
@@ -564,11 +617,24 @@ static void exynos_pinctrl_suspend_bank(
 void exynos_pinctrl_suspend(struct samsung_pinctrl_drv_data *drvdata)
 {
 	struct samsung_pin_bank *bank = drvdata->pin_banks;
+	struct exynos_irq_chip *irq_chip = NULL;
 	int i;
 
-	for (i = 0; i < drvdata->nr_banks; ++i, ++bank)
+	for (i = 0; i < drvdata->nr_banks; ++i, ++bank) {
 		if (bank->eint_type == EINT_TYPE_GPIO)
 			exynos_pinctrl_suspend_bank(drvdata, bank);
+		else if (bank->eint_type == EINT_TYPE_WKUP) {
+			if (!irq_chip) {
+				irq_chip = bank->irq_chip;
+				exynos_pinctrl_set_eint_wakeup_mask(drvdata,
+								    irq_chip);
+			} else if (bank->irq_chip != irq_chip) {
+				dev_warn(drvdata->dev,
+					 "More than one external wakeup interrupt chip configured (bank: %s). This is not supported by hardware nor by driver.\n",
+					 bank->name);
+			}
+		}
+	}
 }
 
 static void exynos_pinctrl_resume_bank(
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.h b/drivers/pinctrl/samsung/pinctrl-samsung.h
index f0cda9424dfe..e571bbd7139b 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.h
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.h
@@ -223,6 +223,13 @@ struct samsung_retention_data {
  *	interrupts for the controller.
  * @eint_wkup_init: platform specific callback to setup the external wakeup
  *	interrupts for the controller.
+ * @suspend: platform specific suspend callback, executed during pin controller
+ *	device suspend, see samsung_pinctrl_suspend()
+ * @resume: platform specific resume callback, executed during pin controller
+ *	device suspend, see samsung_pinctrl_resume()
+ *
+ * External wakeup interrupts must define at least eint_wkup_init,
+ * retention_data and suspend in order for proper suspend/resume to work.
  */
 struct samsung_pin_ctrl {
 	const struct samsung_pin_bank_data *pin_banks;
@@ -255,6 +262,10 @@ struct samsung_pin_ctrl {
  * @pin_base: starting system wide pin number.
  * @nr_pins: number of pins supported by the controller.
  * @retention_ctrl: retention control runtime data.
+ * @suspend: platform specific suspend callback, executed during pin controller
+ *	device suspend, see samsung_pinctrl_suspend()
+ * @resume: platform specific resume callback, executed during pin controller
+ *	device suspend, see samsung_pinctrl_resume()
  */
 struct samsung_pinctrl_drv_data {
 	struct list_head		node;
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a77965.c b/drivers/pinctrl/sh-pfc/pfc-r8a77965.c
index d2bbee656381..cfd7de67e3e3 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a77965.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a77965.c
@@ -1758,6 +1758,263 @@ static const unsigned int du_disp_mux[] = {
 	DU_DISP_MARK,
 };
 
+/* - HSCIF0 ----------------------------------------------------------------- */
+static const unsigned int hscif0_data_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 13), RCAR_GP_PIN(5, 14),
+};
+
+static const unsigned int hscif0_data_mux[] = {
+	HRX0_MARK, HTX0_MARK,
+};
+
+static const unsigned int hscif0_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 12),
+};
+
+static const unsigned int hscif0_clk_mux[] = {
+	HSCK0_MARK,
+};
+
+static const unsigned int hscif0_ctrl_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(5, 16), RCAR_GP_PIN(5, 15),
+};
+
+static const unsigned int hscif0_ctrl_mux[] = {
+	HRTS0_N_MARK, HCTS0_N_MARK,
+};
+
+/* - HSCIF1 ----------------------------------------------------------------- */
+static const unsigned int hscif1_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 5), RCAR_GP_PIN(5, 6),
+};
+
+static const unsigned int hscif1_data_a_mux[] = {
+	HRX1_A_MARK, HTX1_A_MARK,
+};
+
+static const unsigned int hscif1_clk_a_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 21),
+};
+
+static const unsigned int hscif1_clk_a_mux[] = {
+	HSCK1_A_MARK,
+};
+
+static const unsigned int hscif1_ctrl_a_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(5, 8), RCAR_GP_PIN(5, 7),
+};
+
+static const unsigned int hscif1_ctrl_a_mux[] = {
+	HRTS1_N_A_MARK, HCTS1_N_A_MARK,
+};
+
+static const unsigned int hscif1_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 1), RCAR_GP_PIN(5, 2),
+};
+
+static const unsigned int hscif1_data_b_mux[] = {
+	HRX1_B_MARK, HTX1_B_MARK,
+};
+
+static const unsigned int hscif1_clk_b_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 0),
+};
+
+static const unsigned int hscif1_clk_b_mux[] = {
+	HSCK1_B_MARK,
+};
+
+static const unsigned int hscif1_ctrl_b_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(5, 4), RCAR_GP_PIN(5, 3),
+};
+
+static const unsigned int hscif1_ctrl_b_mux[] = {
+	HRTS1_N_B_MARK, HCTS1_N_B_MARK,
+};
+
+/* - HSCIF2 ----------------------------------------------------------------- */
+static const unsigned int hscif2_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(6, 8), RCAR_GP_PIN(6, 9),
+};
+
+static const unsigned int hscif2_data_a_mux[] = {
+	HRX2_A_MARK, HTX2_A_MARK,
+};
+
+static const unsigned int hscif2_clk_a_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 10),
+};
+
+static const unsigned int hscif2_clk_a_mux[] = {
+	HSCK2_A_MARK,
+};
+
+static const unsigned int hscif2_ctrl_a_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(6, 7), RCAR_GP_PIN(6, 6),
+};
+
+static const unsigned int hscif2_ctrl_a_mux[] = {
+	HRTS2_N_A_MARK, HCTS2_N_A_MARK,
+};
+
+static const unsigned int hscif2_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 18),
+};
+
+static const unsigned int hscif2_data_b_mux[] = {
+	HRX2_B_MARK, HTX2_B_MARK,
+};
+
+static const unsigned int hscif2_clk_b_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 21),
+};
+
+static const unsigned int hscif2_clk_b_mux[] = {
+	HSCK2_B_MARK,
+};
+
+static const unsigned int hscif2_ctrl_b_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(6, 20), RCAR_GP_PIN(6, 19),
+};
+
+static const unsigned int hscif2_ctrl_b_mux[] = {
+	HRTS2_N_B_MARK, HCTS2_N_B_MARK,
+};
+
+static const unsigned int hscif2_data_c_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(6, 25), RCAR_GP_PIN(6, 26),
+};
+
+static const unsigned int hscif2_data_c_mux[] = {
+	HRX2_C_MARK, HTX2_C_MARK,
+};
+
+static const unsigned int hscif2_clk_c_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 24),
+};
+
+static const unsigned int hscif2_clk_c_mux[] = {
+	HSCK2_C_MARK,
+};
+
+static const unsigned int hscif2_ctrl_c_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(6, 28), RCAR_GP_PIN(6, 27),
+};
+
+static const unsigned int hscif2_ctrl_c_mux[] = {
+	HRTS2_N_C_MARK, HCTS2_N_C_MARK,
+};
+
+/* - HSCIF3 ----------------------------------------------------------------- */
+static const unsigned int hscif3_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(1, 23), RCAR_GP_PIN(1, 24),
+};
+
+static const unsigned int hscif3_data_a_mux[] = {
+	HRX3_A_MARK, HTX3_A_MARK,
+};
+
+static const unsigned int hscif3_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 22),
+};
+
+static const unsigned int hscif3_clk_mux[] = {
+	HSCK3_MARK,
+};
+
+static const unsigned int hscif3_ctrl_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(1, 26), RCAR_GP_PIN(1, 25),
+};
+
+static const unsigned int hscif3_ctrl_mux[] = {
+	HRTS3_N_MARK, HCTS3_N_MARK,
+};
+
+static const unsigned int hscif3_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(0, 10), RCAR_GP_PIN(0, 11),
+};
+
+static const unsigned int hscif3_data_b_mux[] = {
+	HRX3_B_MARK, HTX3_B_MARK,
+};
+
+static const unsigned int hscif3_data_c_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(0, 14), RCAR_GP_PIN(0, 15),
+};
+
+static const unsigned int hscif3_data_c_mux[] = {
+	HRX3_C_MARK, HTX3_C_MARK,
+};
+
+static const unsigned int hscif3_data_d_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(2, 7), RCAR_GP_PIN(2, 8),
+};
+
+static const unsigned int hscif3_data_d_mux[] = {
+	HRX3_D_MARK, HTX3_D_MARK,
+};
+
+/* - HSCIF4 ----------------------------------------------------------------- */
+static const unsigned int hscif4_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(1, 12), RCAR_GP_PIN(1, 13),
+};
+
+static const unsigned int hscif4_data_a_mux[] = {
+	HRX4_A_MARK, HTX4_A_MARK,
+};
+
+static const unsigned int hscif4_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 11),
+};
+
+static const unsigned int hscif4_clk_mux[] = {
+	HSCK4_MARK,
+};
+
+static const unsigned int hscif4_ctrl_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(1, 15), RCAR_GP_PIN(1, 14),
+};
+
+static const unsigned int hscif4_ctrl_mux[] = {
+	HRTS4_N_MARK, HCTS4_N_MARK,
+};
+
+static const unsigned int hscif4_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(1, 8), RCAR_GP_PIN(1, 11),
+};
+
+static const unsigned int hscif4_data_b_mux[] = {
+	HRX4_B_MARK, HTX4_B_MARK,
+};
+
 /* - I2C -------------------------------------------------------------------- */
 static const unsigned int i2c1_a_pins[] = {
 	/* SDA, SCL */
@@ -3169,6 +3426,34 @@ static const struct sh_pfc_pin_group pinmux_groups[] = {
 	SH_PFC_PIN_GROUP(du_oddf),
 	SH_PFC_PIN_GROUP(du_cde),
 	SH_PFC_PIN_GROUP(du_disp),
+	SH_PFC_PIN_GROUP(hscif0_data),
+	SH_PFC_PIN_GROUP(hscif0_clk),
+	SH_PFC_PIN_GROUP(hscif0_ctrl),
+	SH_PFC_PIN_GROUP(hscif1_data_a),
+	SH_PFC_PIN_GROUP(hscif1_clk_a),
+	SH_PFC_PIN_GROUP(hscif1_ctrl_a),
+	SH_PFC_PIN_GROUP(hscif1_data_b),
+	SH_PFC_PIN_GROUP(hscif1_clk_b),
+	SH_PFC_PIN_GROUP(hscif1_ctrl_b),
+	SH_PFC_PIN_GROUP(hscif2_data_a),
+	SH_PFC_PIN_GROUP(hscif2_clk_a),
+	SH_PFC_PIN_GROUP(hscif2_ctrl_a),
+	SH_PFC_PIN_GROUP(hscif2_data_b),
+	SH_PFC_PIN_GROUP(hscif2_clk_b),
+	SH_PFC_PIN_GROUP(hscif2_ctrl_b),
+	SH_PFC_PIN_GROUP(hscif2_data_c),
+	SH_PFC_PIN_GROUP(hscif2_clk_c),
+	SH_PFC_PIN_GROUP(hscif2_ctrl_c),
+	SH_PFC_PIN_GROUP(hscif3_data_a),
+	SH_PFC_PIN_GROUP(hscif3_clk),
+	SH_PFC_PIN_GROUP(hscif3_ctrl),
+	SH_PFC_PIN_GROUP(hscif3_data_b),
+	SH_PFC_PIN_GROUP(hscif3_data_c),
+	SH_PFC_PIN_GROUP(hscif3_data_d),
+	SH_PFC_PIN_GROUP(hscif4_data_a),
+	SH_PFC_PIN_GROUP(hscif4_clk),
+	SH_PFC_PIN_GROUP(hscif4_ctrl),
+	SH_PFC_PIN_GROUP(hscif4_data_b),
 	SH_PFC_PIN_GROUP(i2c1_a),
 	SH_PFC_PIN_GROUP(i2c1_b),
 	SH_PFC_PIN_GROUP(i2c2_a),
@@ -3379,6 +3664,49 @@ static const char * const du_groups[] = {
 	"du_disp",
 };
 
+static const char * const hscif0_groups[] = {
+	"hscif0_data",
+	"hscif0_clk",
+	"hscif0_ctrl",
+};
+
+static const char * const hscif1_groups[] = {
+	"hscif1_data_a",
+	"hscif1_clk_a",
+	"hscif1_ctrl_a",
+	"hscif1_data_b",
+	"hscif1_clk_b",
+	"hscif1_ctrl_b",
+};
+
+static const char * const hscif2_groups[] = {
+	"hscif2_data_a",
+	"hscif2_clk_a",
+	"hscif2_ctrl_a",
+	"hscif2_data_b",
+	"hscif2_clk_b",
+	"hscif2_ctrl_b",
+	"hscif2_data_c",
+	"hscif2_clk_c",
+	"hscif2_ctrl_c",
+};
+
+static const char * const hscif3_groups[] = {
+	"hscif3_data_a",
+	"hscif3_clk",
+	"hscif3_ctrl",
+	"hscif3_data_b",
+	"hscif3_data_c",
+	"hscif3_data_d",
+};
+
+static const char * const hscif4_groups[] = {
+	"hscif4_data_a",
+	"hscif4_clk",
+	"hscif4_ctrl",
+	"hscif4_data_b",
+};
+
 static const char * const i2c1_groups[] = {
 	"i2c1_a",
 	"i2c1_b",
@@ -3651,6 +3979,11 @@ static const char * const usb30_groups[] = {
 static const struct sh_pfc_function pinmux_functions[] = {
 	SH_PFC_FUNCTION(avb),
 	SH_PFC_FUNCTION(du),
+	SH_PFC_FUNCTION(hscif0),
+	SH_PFC_FUNCTION(hscif1),
+	SH_PFC_FUNCTION(hscif2),
+	SH_PFC_FUNCTION(hscif3),
+	SH_PFC_FUNCTION(hscif4),
 	SH_PFC_FUNCTION(i2c1),
 	SH_PFC_FUNCTION(i2c2),
 	SH_PFC_FUNCTION(i2c6),
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a77990.c b/drivers/pinctrl/sh-pfc/pfc-r8a77990.c
index a68fd658aada..b81c807ac54d 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a77990.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a77990.c
@@ -277,7 +277,7 @@
 #define IP11_15_12	FM(TX0_A)		FM(HTX1_A)		FM(SSI_WS2_A)		FM(RIF1_D0)		F_(0, 0)		F_(0, 0)	F_(0, 0)	FM(TS_SDAT1)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP11_19_16	FM(CTS0_N_A)		FM(NFDATA14_A)		FM(AUDIO_CLKOUT_A)	FM(RIF1_D1)		FM(SCIF_CLK_A)		FM(FMCLK_A)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP11_23_20	FM(RTS0_N_TANS_A)	FM(NFDATA15_A)		FM(AUDIO_CLKOUT1_A)	FM(RIF1_CLK)		FM(SCL2_A)		FM(FMIN_A)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP11_27_24	FM(SCK0_A)		FM(HSCK1_A)		FM(USB3HS0_ID)		FM(RTS1_N_TANS)		FM(SDA2_A)		FM(FMCLK_C)	F_(0, 0)	F_(0, 0)	FM(USB1_ID)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP11_27_24	FM(SCK0_A)		FM(HSCK1_A)		FM(USB3HS0_ID)		FM(RTS1_N_TANS)		FM(SDA2_A)		FM(FMCLK_C)	F_(0, 0)	F_(0, 0)	FM(USB0_ID)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP11_31_28	FM(RX1)			FM(HRX2_B)		FM(SSI_SCK9_B)		FM(AUDIO_CLKOUT1_B)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 
 /* IPSRx */		/* 0 */			/* 1 */			/* 2 */			/* 3 */			/* 4 */			/* 5 */		/* 6 */		/* 7 */		/* 8 */		/* 9 - F */
@@ -1082,7 +1082,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_GPSR(IP11_27_24,		RTS1_N_TANS),
 	PINMUX_IPSR_MSEL(IP11_27_24,		SDA2_A,		SEL_I2C2_0),
 	PINMUX_IPSR_MSEL(IP11_27_24,		FMCLK_C,	SEL_FM_2),
-	PINMUX_IPSR_GPSR(IP11_27_24,		USB1_ID),
+	PINMUX_IPSR_GPSR(IP11_27_24,		USB0_ID),
 
 	PINMUX_IPSR_GPSR(IP11_31_28,		RX1),
 	PINMUX_IPSR_MSEL(IP11_31_28,		HRX2_B,		SEL_HSCIF2_1),
@@ -1784,6 +1784,53 @@ static const unsigned int scif_clk_b_mux[] = {
 	SCIF_CLK_B_MARK,
 };
 
+/* - USB0 ------------------------------------------------------------------- */
+static const unsigned int usb0_a_pins[] = {
+	/* PWEN, OVC */
+	RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 9),
+};
+
+static const unsigned int usb0_a_mux[] = {
+	USB0_PWEN_A_MARK, USB0_OVC_A_MARK,
+};
+
+static const unsigned int usb0_b_pins[] = {
+	/* PWEN, OVC */
+	RCAR_GP_PIN(6, 11), RCAR_GP_PIN(6, 12),
+};
+
+static const unsigned int usb0_b_mux[] = {
+	USB0_PWEN_B_MARK, USB0_OVC_B_MARK,
+};
+
+static const unsigned int usb0_id_pins[] = {
+	/* ID */
+	RCAR_GP_PIN(5, 0)
+};
+
+static const unsigned int usb0_id_mux[] = {
+	USB0_ID_MARK,
+};
+
+/* - USB30 ------------------------------------------------------------------ */
+static const unsigned int usb30_pins[] = {
+	/* PWEN, OVC */
+	RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 9),
+};
+
+static const unsigned int usb30_mux[] = {
+	USB30_PWEN_MARK, USB30_OVC_MARK,
+};
+
+static const unsigned int usb30_id_pins[] = {
+	/* ID */
+	RCAR_GP_PIN(5, 0),
+};
+
+static const unsigned int usb30_id_mux[] = {
+	USB3HS0_ID_MARK,
+};
+
 static const struct sh_pfc_pin_group pinmux_groups[] = {
 	SH_PFC_PIN_GROUP(avb_link),
 	SH_PFC_PIN_GROUP(avb_magic),
@@ -1837,6 +1884,11 @@ static const struct sh_pfc_pin_group pinmux_groups[] = {
 	SH_PFC_PIN_GROUP(scif5_data_c),
 	SH_PFC_PIN_GROUP(scif_clk_a),
 	SH_PFC_PIN_GROUP(scif_clk_b),
+	SH_PFC_PIN_GROUP(usb0_a),
+	SH_PFC_PIN_GROUP(usb0_b),
+	SH_PFC_PIN_GROUP(usb0_id),
+	SH_PFC_PIN_GROUP(usb30),
+	SH_PFC_PIN_GROUP(usb30_id),
 };
 
 static const char * const avb_groups[] = {
@@ -1933,6 +1985,17 @@ static const char * const scif_clk_groups[] = {
 	"scif_clk_b",
 };
 
+static const char * const usb0_groups[] = {
+	"usb0_a",
+	"usb0_b",
+	"usb0_id",
+};
+
+static const char * const usb30_groups[] = {
+	"usb30",
+	"usb30_id",
+};
+
 static const struct sh_pfc_function pinmux_functions[] = {
 	SH_PFC_FUNCTION(avb),
 	SH_PFC_FUNCTION(i2c1),
@@ -1948,6 +2011,8 @@ static const struct sh_pfc_function pinmux_functions[] = {
 	SH_PFC_FUNCTION(scif4),
 	SH_PFC_FUNCTION(scif5),
 	SH_PFC_FUNCTION(scif_clk),
+	SH_PFC_FUNCTION(usb0),
+	SH_PFC_FUNCTION(usb30),
 };
 
 static const struct pinmux_cfg_reg pinmux_config_regs[] = {
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c
index dfed60982a8a..a9bec6e6fdd1 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.c
@@ -46,6 +46,8 @@
 #define STM32_GPIO_PINS_PER_BANK 16
 #define STM32_GPIO_IRQ_LINE	 16
 
+#define SYSCFG_IRQMUX_MASK GENMASK(3, 0)
+
 #define gpio_range_to_bank(chip) \
 		container_of(chip, struct stm32_gpio_bank, range)
 
@@ -73,6 +75,7 @@ struct stm32_gpio_bank {
 	struct fwnode_handle *fwnode;
 	struct irq_domain *domain;
 	u32 bank_nr;
+	u32 bank_ioport_nr;
 };
 
 struct stm32_pinctrl {
@@ -298,7 +301,7 @@ static int stm32_gpio_domain_activate(struct irq_domain *d,
 	struct stm32_gpio_bank *bank = d->host_data;
 	struct stm32_pinctrl *pctl = dev_get_drvdata(bank->gpio_chip.parent);
 
-	regmap_field_write(pctl->irqmux[irq_data->hwirq], bank->bank_nr);
+	regmap_field_write(pctl->irqmux[irq_data->hwirq], bank->bank_ioport_nr);
 	return 0;
 }
 
@@ -638,6 +641,11 @@ static int stm32_pmx_set_mux(struct pinctrl_dev *pctldev,
 	}
 
 	range = pinctrl_find_gpio_range_from_pin(pctldev, g->pin);
+	if (!range) {
+		dev_err(pctl->dev, "No gpio range defined.\n");
+		return -EINVAL;
+	}
+
 	bank = gpiochip_get_data(range->gc);
 	pin = stm32_gpio_pin(g->pin);
 
@@ -806,11 +814,17 @@ static int stm32_pconf_parse_conf(struct pinctrl_dev *pctldev,
 		unsigned int pin, enum pin_config_param param,
 		enum pin_config_param arg)
 {
+	struct stm32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
 	struct pinctrl_gpio_range *range;
 	struct stm32_gpio_bank *bank;
 	int offset, ret = 0;
 
 	range = pinctrl_find_gpio_range_from_pin(pctldev, pin);
+	if (!range) {
+		dev_err(pctl->dev, "No gpio range defined.\n");
+		return -EINVAL;
+	}
+
 	bank = gpiochip_get_data(range->gc);
 	offset = stm32_gpio_pin(pin);
 
@@ -892,6 +906,9 @@ static void stm32_pconf_dbg_show(struct pinctrl_dev *pctldev,
 	bool val;
 
 	range = pinctrl_find_gpio_range_from_pin_nolock(pctldev, pin);
+	if (!range)
+		return;
+
 	bank = gpiochip_get_data(range->gc);
 	offset = stm32_gpio_pin(pin);
 
@@ -948,6 +965,7 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl,
 	struct device_node *np)
 {
 	struct stm32_gpio_bank *bank = &pctl->banks[pctl->nbanks];
+	int bank_ioport_nr;
 	struct pinctrl_gpio_range *range = &bank->range;
 	struct of_phandle_args args;
 	struct device *dev = pctl->dev;
@@ -998,12 +1016,17 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl,
 		pinctrl_add_gpio_range(pctl->pctl_dev,
 				       &pctl->banks[bank_nr].range);
 	}
+
+	if (of_property_read_u32(np, "st,bank-ioport", &bank_ioport_nr))
+		bank_ioport_nr = bank_nr;
+
 	bank->gpio_chip.base = bank_nr * STM32_GPIO_PINS_PER_BANK;
 
 	bank->gpio_chip.ngpio = npins;
 	bank->gpio_chip.of_node = np;
 	bank->gpio_chip.parent = dev;
 	bank->bank_nr = bank_nr;
+	bank->bank_ioport_nr = bank_ioport_nr;
 	spin_lock_init(&bank->lock);
 
 	/* create irq hierarchical domain */
@@ -1033,6 +1056,7 @@ static int stm32_pctrl_dt_setup_irq(struct platform_device *pdev,
 	struct device *dev = &pdev->dev;
 	struct regmap *rm;
 	int offset, ret, i;
+	int mask, mask_width;
 
 	parent = of_irq_find_parent(np);
 	if (!parent)
@@ -1052,12 +1076,21 @@ static int stm32_pctrl_dt_setup_irq(struct platform_device *pdev,
 	if (ret)
 		return ret;
 
+	ret = of_property_read_u32_index(np, "st,syscfg", 2, &mask);
+	if (ret)
+		mask = SYSCFG_IRQMUX_MASK;
+
+	mask_width = fls(mask);
+
 	for (i = 0; i < STM32_GPIO_PINS_PER_BANK; i++) {
 		struct reg_field mux;
 
 		mux.reg = offset + (i / 4) * 4;
-		mux.lsb = (i % 4) * 4;
-		mux.msb = mux.lsb + 3;
+		mux.lsb = (i % 4) * mask_width;
+		mux.msb = mux.lsb + mask_width - 1;
+
+		dev_dbg(dev, "irqmux%d: reg:%#x, lsb:%d, msb:%d\n",
+			i, mux.reg, mux.lsb, mux.msb);
 
 		pctl->irqmux[i] = devm_regmap_field_alloc(dev, rm, mux);
 		if (IS_ERR(pctl->irqmux[i]))
@@ -1166,7 +1199,7 @@ int stm32_pctl_probe(struct platform_device *pdev)
 		return PTR_ERR(pctl->pctl_dev);
 	}
 
-	for_each_child_of_node(np, child)
+	for_each_available_child_of_node(np, child)
 		if (of_property_read_bool(child, "gpio-controller"))
 			banks++;
 
@@ -1179,7 +1212,7 @@ int stm32_pctl_probe(struct platform_device *pdev)
 	if (!pctl->banks)
 		return -ENOMEM;
 
-	for_each_child_of_node(np, child) {
+	for_each_available_child_of_node(np, child) {
 		if (of_property_read_bool(child, "gpio-controller")) {
 			ret = stm32_gpiolib_register_bank(pctl, child);
 			if (ret)
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra.c b/drivers/pinctrl/tegra/pinctrl-tegra.c
index f974eee29a19..1aba75897d14 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra.c
@@ -629,12 +629,12 @@ static void tegra_pinctrl_clear_parked_bits(struct tegra_pmx *pmx)
 	}
 }
 
-static bool gpio_node_has_range(void)
+static bool gpio_node_has_range(const char *compatible)
 {
 	struct device_node *np;
 	bool has_prop = false;
 
-	np = of_find_compatible_node(NULL, NULL, "nvidia,tegra30-gpio");
+	np = of_find_compatible_node(NULL, NULL, compatible);
 	if (!np)
 		return has_prop;
 
@@ -728,7 +728,7 @@ int tegra_pinctrl_probe(struct platform_device *pdev,
 
 	tegra_pinctrl_clear_parked_bits(pmx);
 
-	if (!gpio_node_has_range())
+	if (!gpio_node_has_range(pmx->soc->gpio_compatible))
 		pinctrl_add_gpio_range(pmx->pctl, &tegra_pinctrl_gpio_range);
 
 	platform_set_drvdata(pdev, pmx);
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra.h b/drivers/pinctrl/tegra/pinctrl-tegra.h
index aa33c20766c4..44c71941b5f8 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra.h
+++ b/drivers/pinctrl/tegra/pinctrl-tegra.h
@@ -189,6 +189,7 @@ struct tegra_pingroup {
  */
 struct tegra_pinctrl_soc_data {
 	unsigned ngpios;
+	const char *gpio_compatible;
 	const struct pinctrl_pin_desc *pins;
 	unsigned npins;
 	struct tegra_function *functions;
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra114.c b/drivers/pinctrl/tegra/pinctrl-tegra114.c
index 56b33fca1bfc..d43c209e9c30 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra114.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra114.c
@@ -1839,6 +1839,7 @@ static const struct tegra_pingroup tegra114_groups[] = {
 
 static const struct tegra_pinctrl_soc_data tegra114_pinctrl = {
 	.ngpios = NUM_GPIOS,
+	.gpio_compatible = "nvidia,tegra30-gpio",
 	.pins = tegra114_pins,
 	.npins = ARRAY_SIZE(tegra114_pins),
 	.functions = tegra114_functions,
@@ -1867,4 +1868,9 @@ static struct platform_driver tegra114_pinctrl_driver = {
 	},
 	.probe = tegra114_pinctrl_probe,
 };
-builtin_platform_driver(tegra114_pinctrl_driver);
+
+static int __init tegra114_pinctrl_init(void)
+{
+	return platform_driver_register(&tegra114_pinctrl_driver);
+}
+arch_initcall(tegra114_pinctrl_init);
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra124.c b/drivers/pinctrl/tegra/pinctrl-tegra124.c
index 7bc998ace0d5..5b07a5834d15 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra124.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra124.c
@@ -2051,6 +2051,7 @@ static const struct tegra_pingroup tegra124_groups[] = {
 
 static const struct tegra_pinctrl_soc_data tegra124_pinctrl = {
 	.ngpios = NUM_GPIOS,
+	.gpio_compatible = "nvidia,tegra30-gpio",
 	.pins = tegra124_pins,
 	.npins = ARRAY_SIZE(tegra124_pins),
 	.functions = tegra124_functions,
@@ -2079,4 +2080,9 @@ static struct platform_driver tegra124_pinctrl_driver = {
 	},
 	.probe = tegra124_pinctrl_probe,
 };
-builtin_platform_driver(tegra124_pinctrl_driver);
+
+static int __init tegra124_pinctrl_init(void)
+{
+	return platform_driver_register(&tegra124_pinctrl_driver);
+}
+arch_initcall(tegra124_pinctrl_init);
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra20.c b/drivers/pinctrl/tegra/pinctrl-tegra20.c
index b6dd939d32cc..1fc82a9576e0 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra20.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra20.c
@@ -2221,6 +2221,7 @@ static const struct tegra_pingroup tegra20_groups[] = {
 
 static const struct tegra_pinctrl_soc_data tegra20_pinctrl = {
 	.ngpios = NUM_GPIOS,
+	.gpio_compatible = "nvidia,tegra20-gpio",
 	.pins = tegra20_pins,
 	.npins = ARRAY_SIZE(tegra20_pins),
 	.functions = tegra20_functions,
@@ -2276,4 +2277,9 @@ static struct platform_driver tegra20_pinctrl_driver = {
 	},
 	.probe = tegra20_pinctrl_probe,
 };
-builtin_platform_driver(tegra20_pinctrl_driver);
+
+static int __init tegra20_pinctrl_init(void)
+{
+	return platform_driver_register(&tegra20_pinctrl_driver);
+}
+arch_initcall(tegra20_pinctrl_init);
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra210.c b/drivers/pinctrl/tegra/pinctrl-tegra210.c
index c244e5b17bd6..3e77f5474dd8 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra210.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra210.c
@@ -1553,6 +1553,7 @@ static const struct tegra_pingroup tegra210_groups[] = {
 
 static const struct tegra_pinctrl_soc_data tegra210_pinctrl = {
 	.ngpios = NUM_GPIOS,
+	.gpio_compatible = "nvidia,tegra30-gpio",
 	.pins = tegra210_pins,
 	.npins = ARRAY_SIZE(tegra210_pins),
 	.functions = tegra210_functions,
@@ -1581,4 +1582,9 @@ static struct platform_driver tegra210_pinctrl_driver = {
 	},
 	.probe = tegra210_pinctrl_probe,
 };
-builtin_platform_driver(tegra210_pinctrl_driver);
+
+static int __init tegra210_pinctrl_init(void)
+{
+	return platform_driver_register(&tegra210_pinctrl_driver);
+}
+arch_initcall(tegra210_pinctrl_init);
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra30.c b/drivers/pinctrl/tegra/pinctrl-tegra30.c
index 1f180a20f2ab..10e617003e9c 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra30.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra30.c
@@ -2474,6 +2474,7 @@ static const struct tegra_pingroup tegra30_groups[] = {
 
 static const struct tegra_pinctrl_soc_data tegra30_pinctrl = {
 	.ngpios = NUM_GPIOS,
+	.gpio_compatible = "nvidia,tegra30-gpio",
 	.pins = tegra30_pins,
 	.npins = ARRAY_SIZE(tegra30_pins),
 	.functions = tegra30_functions,
@@ -2502,4 +2503,9 @@ static struct platform_driver tegra30_pinctrl_driver = {
 	},
 	.probe = tegra30_pinctrl_probe,
 };
-builtin_platform_driver(tegra30_pinctrl_driver);
+
+static int __init tegra30_pinctrl_init(void)
+{
+	return platform_driver_register(&tegra30_pinctrl_driver);
+}
+arch_initcall(tegra30_pinctrl_init);
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c
index 58825f68b58b..bce533f85420 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c
@@ -517,6 +517,10 @@ static const int i2c4_muxvals[] = {1, 1};
 static const unsigned nand_pins[] = {3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14,
 				     15, 16, 17};
 static const int nand_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {56, 57, 58, 59};
+static const int spi0_muxvals[] = {0, 0, 0, 0};
+static const unsigned spi1_pins[] = {169, 170, 171, 172};
+static const int spi1_muxvals[] = {1, 1, 1, 1};
 static const unsigned system_bus_pins[] = {1, 2, 6, 7, 8, 9, 10, 11, 12, 13,
 					   14, 15, 16, 17};
 static const int system_bus_muxvals[] = {0, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
@@ -596,6 +600,8 @@ static const struct uniphier_pinctrl_group uniphier_ld11_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(i2c3),
 	UNIPHIER_PINCTRL_GROUP(i2c4),
 	UNIPHIER_PINCTRL_GROUP(nand),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
 	UNIPHIER_PINCTRL_GROUP(uart0),
@@ -632,6 +638,8 @@ static const char * const i2c1_groups[] = {"i2c1"};
 static const char * const i2c3_groups[] = {"i2c3"};
 static const char * const i2c4_groups[] = {"i2c4"};
 static const char * const nand_groups[] = {"nand"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs1"};
 static const char * const uart0_groups[] = {"uart0"};
@@ -657,6 +665,8 @@ static const struct uniphier_pinmux_function uniphier_ld11_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c3),
 	UNIPHIER_PINMUX_FUNCTION(i2c4),
 	UNIPHIER_PINMUX_FUNCTION(nand),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c
index 9f449b35e300..99f06fe8e1cb 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c
@@ -606,6 +606,14 @@ static const unsigned nand_pins[] = {3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14,
 static const int nand_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
 static const unsigned sd_pins[] = {10, 11, 12, 13, 14, 15, 16, 17};
 static const int sd_muxvals[] = {3, 3, 3, 3, 3, 3, 3, 3};  /* No SDVOLC */
+static const unsigned spi0_pins[] = {56, 57, 58, 59};
+static const int spi0_muxvals[] = {0, 0, 0, 0};
+static const unsigned spi1_pins[] = {169, 170, 171, 172};
+static const int spi1_muxvals[] = {1, 1, 1, 1};
+static const unsigned spi2_pins[] = {86, 87, 88, 89};
+static const int spi2_muxvals[] = {1, 1, 1, 1};
+static const unsigned spi3_pins[] = {74, 75, 76, 77};
+static const int spi3_muxvals[] = {1, 1, 1, 1};
 static const unsigned system_bus_pins[] = {1, 2, 6, 7, 8, 9, 10, 11, 12, 13,
 					   14, 15, 16, 17};
 static const int system_bus_muxvals[] = {0, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
@@ -685,6 +693,10 @@ static const struct uniphier_pinctrl_group uniphier_ld20_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(i2c4),
 	UNIPHIER_PINCTRL_GROUP(nand),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
+	UNIPHIER_PINCTRL_GROUP(spi2),
+	UNIPHIER_PINCTRL_GROUP(spi3),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
 	UNIPHIER_PINCTRL_GROUP(uart0),
@@ -722,6 +734,10 @@ static const char * const i2c3_groups[] = {"i2c3"};
 static const char * const i2c4_groups[] = {"i2c4"};
 static const char * const nand_groups[] = {"nand"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
+static const char * const spi2_groups[] = {"spi2"};
+static const char * const spi3_groups[] = {"spi3"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs1"};
 static const char * const uart0_groups[] = {"uart0"};
@@ -751,6 +767,10 @@ static const struct uniphier_pinmux_function uniphier_ld20_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c4),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
+	UNIPHIER_PINMUX_FUNCTION(spi2),
+	UNIPHIER_PINMUX_FUNCTION(spi3),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld4.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld4.c
index 0b10ebc07eb8..b247011524bf 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld4.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld4.c
@@ -576,6 +576,8 @@ static const unsigned nand_cs1_pins[] = {22, 23};
 static const int nand_cs1_muxvals[] = {0, 0};
 static const unsigned sd_pins[] = {44, 45, 46, 47, 48, 49, 50, 51, 52};
 static const int sd_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {135, 136, 137, 138};
+static const int spi0_muxvals[] = {12, 12, 12, 12};
 static const unsigned system_bus_pins[] = {16, 17, 18, 19, 20, 165, 166, 167,
 					   168, 169, 170, 171, 172, 173};
 static const int system_bus_muxvals[] = {0, 0, 0, 0, 0, -1, -1, -1, -1, -1, -1,
@@ -640,6 +642,7 @@ static const struct uniphier_pinctrl_group uniphier_ld4_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(nand),
 	UNIPHIER_PINCTRL_GROUP(nand_cs1),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs0),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
@@ -667,6 +670,7 @@ static const char * const i2c2_groups[] = {"i2c2"};
 static const char * const i2c3_groups[] = {"i2c3"};
 static const char * const nand_groups[] = {"nand", "nand_cs1"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs0",
 						 "system_bus_cs1",
@@ -690,6 +694,7 @@ static const struct uniphier_pinmux_function uniphier_ld4_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c3),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld6b.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld6b.c
index 8e4d45fea885..cb58797adaee 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld6b.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld6b.c
@@ -769,6 +769,10 @@ static const unsigned nand_cs1_pins[] = {37, 38};
 static const int nand_cs1_muxvals[] = {0, 0};
 static const unsigned sd_pins[] = {47, 48, 49, 50, 51, 52, 53, 54, 55};
 static const int sd_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {199, 200, 201, 202};
+static const int spi0_muxvals[] = {8, 8, 8, 8};
+static const unsigned spi1_pins[] = {93, 94, 95, 96};
+static const int spi1_muxvals[] = {1, 1, 1, 1};
 static const unsigned system_bus_pins[] = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10,
 					   11, 12, 13};
 static const int system_bus_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
@@ -851,6 +855,8 @@ static const struct uniphier_pinctrl_group uniphier_ld6b_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(nand),
 	UNIPHIER_PINCTRL_GROUP(nand_cs1),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs2),
@@ -882,6 +888,8 @@ static const char * const i2c2_groups[] = {"i2c2"};
 static const char * const i2c3_groups[] = {"i2c3"};
 static const char * const nand_groups[] = {"nand", "nand_cs1"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs1",
 						 "system_bus_cs2",
@@ -907,6 +915,8 @@ static const struct uniphier_pinmux_function uniphier_ld6b_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c3),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c
index 24788a74c254..89148f81d5e0 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c
@@ -1050,6 +1050,10 @@ static const int sd_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
 static const unsigned sd1_pins[] = {319, 320, 321, 322, 323, 324, 325, 326,
 				    327};
 static const int sd1_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {199, 200, 201, 202};
+static const int spi0_muxvals[] = {11, 11, 11, 11};
+static const unsigned spi1_pins[] = {195, 196, 197, 198, 235, 238, 239};
+static const int spi1_muxvals[] = {11, 11, 11, 11, 11, 11, 11};
 static const unsigned system_bus_pins[] = {25, 26, 27, 28, 29, 30, 31, 32, 33,
 					   34, 35, 36, 37, 38};
 static const int system_bus_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
@@ -1138,6 +1142,8 @@ static const struct uniphier_pinctrl_group uniphier_pro4_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(nand_cs1),
 	UNIPHIER_PINCTRL_GROUP(sd),
 	UNIPHIER_PINCTRL_GROUP(sd1),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs0),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
@@ -1171,6 +1177,8 @@ static const char * const i2c6_groups[] = {"i2c6"};
 static const char * const nand_groups[] = {"nand", "nand_cs1"};
 static const char * const sd_groups[] = {"sd"};
 static const char * const sd1_groups[] = {"sd1"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs0",
 						 "system_bus_cs1",
@@ -1202,6 +1210,8 @@ static const struct uniphier_pinmux_function uniphier_pro4_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
 	UNIPHIER_PINMUX_FUNCTION(sd1),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-pro5.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro5.c
index d5d5e579cb08..d77d6b37aabe 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-pro5.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro5.c
@@ -818,6 +818,12 @@ static const unsigned nand_cs1_pins[] = {26, 27};
 static const int nand_cs1_muxvals[] = {0, 0};
 static const unsigned sd_pins[] = {250, 251, 252, 253, 254, 255, 256, 257, 258};
 static const int sd_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {120, 121, 122, 123};
+static const int spi0_muxvals[] = {0, 0, 0, 0};
+static const unsigned spi1_pins[] = {134, 139, 85, 86};
+static const int spi1_muxvals[] = {1, 1, 1, 1};
+static const unsigned spi2_pins[] = {55, 56, 57, 58, 82, 83, 84};
+static const int spi2_muxvals[] = {0, 0, 0, 0, 1, 1, 1};
 static const unsigned system_bus_pins[] = {4, 5, 6, 7, 8, 9, 10, 11, 12, 13,
 					   14, 15, 16, 17};
 static const int system_bus_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
@@ -904,6 +910,9 @@ static const struct uniphier_pinctrl_group uniphier_pro5_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(i2c5c),
 	UNIPHIER_PINCTRL_GROUP(i2c6),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
+	UNIPHIER_PINCTRL_GROUP(spi2),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs0),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
@@ -934,6 +943,9 @@ static const char * const i2c5_groups[] = {"i2c5", "i2c5b", "i2c5c"};
 static const char * const i2c6_groups[] = {"i2c6"};
 static const char * const nand_groups[] = {"nand", "nand_cs1"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
+static const char * const spi2_groups[] = {"spi2"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs0",
 						 "system_bus_cs1",
@@ -961,6 +973,9 @@ static const struct uniphier_pinmux_function uniphier_pro5_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c6),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
+	UNIPHIER_PINMUX_FUNCTION(spi2),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs2.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs2.c
index 032619ad0e73..90199da87eb9 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs2.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs2.c
@@ -778,6 +778,10 @@ static const unsigned nand_cs1_pins[] = {37, 38};
 static const int nand_cs1_muxvals[] = {8, 8};
 static const unsigned sd_pins[] = {47, 48, 49, 50, 51, 52, 53, 54, 55};
 static const int sd_muxvals[] = {8, 8, 8, 8, 8, 8, 8, 8, 8};
+static const unsigned spi0_pins[] = {199, 200, 201, 202};
+static const int spi0_muxvals[] = {8, 8, 8, 8};
+static const unsigned spi1_pins[] = {93, 94, 95, 96};
+static const int spi1_muxvals[] = {1, 1, 1, 1};
 static const unsigned system_bus_pins[] = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10,
 					   11, 12, 13};
 static const int system_bus_muxvals[] = {8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,
@@ -861,6 +865,8 @@ static const struct uniphier_pinctrl_group uniphier_pxs2_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(nand),
 	UNIPHIER_PINCTRL_GROUP(nand_cs1),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
 	UNIPHIER_PINCTRL_GROUP(uart0),
@@ -897,6 +903,8 @@ static const char * const i2c5_groups[] = {"i2c5"};
 static const char * const i2c6_groups[] = {"i2c6"};
 static const char * const nand_groups[] = {"nand", "nand_cs1"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs1"};
 static const char * const uart0_groups[] = {"uart0", "uart0b", "uart0b_ctsrts"};
@@ -928,6 +936,8 @@ static const struct uniphier_pinmux_function uniphier_pxs2_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c6),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs3.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs3.c
index 535bb2e935e4..3b860da47733 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs3.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs3.c
@@ -808,6 +808,10 @@ static const unsigned int nand_pins[] = {16, 17, 18, 19, 20, 21, 22, 23, 24, 25,
 static const int nand_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
 static const unsigned int sd_pins[] = {43, 44, 45, 46, 47, 48, 49, 50, 51};
 static const int sd_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {100, 101, 102, 103};
+static const int spi0_muxvals[] = {0, 0, 0, 0};
+static const unsigned spi1_pins[] = {112, 113, 114, 115};
+static const int spi1_muxvals[] = {2, 2, 2, 2};
 static const unsigned int system_bus_pins[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10,
 					       11, 12, 13, 14};
 static const int system_bus_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
@@ -886,6 +890,8 @@ static const struct uniphier_pinctrl_group uniphier_pxs3_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(i2c3),
 	UNIPHIER_PINCTRL_GROUP(nand),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
 	UNIPHIER_PINCTRL_GROUP(uart0),
@@ -913,6 +919,8 @@ static const char * const i2c2_groups[] = {"i2c2"};
 static const char * const i2c3_groups[] = {"i2c3"};
 static const char * const nand_groups[] = {"nand"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs1"};
 static const char * const uart0_groups[] = {"uart0", "uart0_ctsrts"};
@@ -936,6 +944,8 @@ static const struct uniphier_pinmux_function uniphier_pxs3_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c3),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-sld8.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-sld8.c
index 0f921a653164..f086083368a7 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-sld8.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-sld8.c
@@ -504,6 +504,8 @@ static const unsigned nand_cs1_pins[] = {22, 23};
 static const int nand_cs1_muxvals[] = {0, 0};
 static const unsigned sd_pins[] = {32, 33, 34, 35, 36, 37, 38, 39, 40};
 static const int sd_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {118, 119, 120, 121};
+static const int spi0_muxvals[] = {3, 3, 3, 3};
 static const unsigned system_bus_pins[] = {136, 137, 138, 139, 140, 141, 142,
 					   143, 144, 145, 146, 147, 148, 149};
 static const int system_bus_muxvals[] = {-1, -1, -1, -1, -1, -1, -1, -1, -1,
@@ -570,6 +572,7 @@ static const struct uniphier_pinctrl_group uniphier_sld8_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(nand),
 	UNIPHIER_PINCTRL_GROUP(nand_cs1),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs2),
@@ -598,6 +601,7 @@ static const char * const i2c2_groups[] = {"i2c2"};
 static const char * const i2c3_groups[] = {"i2c3"};
 static const char * const nand_groups[] = {"nand", "nand_cs1"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs1",
 						 "system_bus_cs2",
@@ -622,6 +626,7 @@ static const struct uniphier_pinmux_function uniphier_sld8_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c3),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/platform/mips/cpu_hwmon.c b/drivers/platform/mips/cpu_hwmon.c
index 322de58eebaf..f66521c7f846 100644
--- a/drivers/platform/mips/cpu_hwmon.c
+++ b/drivers/platform/mips/cpu_hwmon.c
@@ -30,7 +30,8 @@ int loongson3_cpu_temp(int cpu)
 	case PRID_REV_LOONGSON3B_R2:
 		reg = ((reg >> 8) & 0xff) - 100;
 		break;
-	case PRID_REV_LOONGSON3A_R3:
+	case PRID_REV_LOONGSON3A_R3_0:
+	case PRID_REV_LOONGSON3A_R3_1:
 		reg = (reg & 0xffff)*731/0x4000 - 273;
 		break;
 	}
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index ac4d48830415..107d336453b2 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -1218,6 +1218,17 @@ config INTEL_CHTDC_TI_PWRBTN
 	  To compile this driver as a module, choose M here: the module
 	  will be called intel_chtdc_ti_pwrbtn.
 
+config I2C_MULTI_INSTANTIATE
+	tristate "I2C multi instantiate pseudo device driver"
+	depends on I2C && ACPI
+	help
+	  Some ACPI-based systems list multiple i2c-devices in a single ACPI
+	  firmware-node. This driver will instantiate separate i2c-clients
+	  for each device in the firmware-node.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called i2c-multi-instantiate.
+
 endif # X86_PLATFORM_DEVICES
 
 config PMC_ATOM
diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile
index 2ba6cb795338..50dc8f280914 100644
--- a/drivers/platform/x86/Makefile
+++ b/drivers/platform/x86/Makefile
@@ -91,3 +91,4 @@ obj-$(CONFIG_PMC_ATOM)		+= pmc_atom.o
 obj-$(CONFIG_MLX_PLATFORM)	+= mlx-platform.o
 obj-$(CONFIG_INTEL_TURBO_MAX_3) += intel_turbo_max_3.o
 obj-$(CONFIG_INTEL_CHTDC_TI_PWRBTN)	+= intel_chtdc_ti_pwrbtn.o
+obj-$(CONFIG_I2C_MULTI_INSTANTIATE)	+= i2c-multi-instantiate.o
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 3d523ca64694..d67f32a29bb4 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -858,12 +858,6 @@ static int asus_get_adapter_status(struct hotplug_slot *hotplug_slot,
 	return 0;
 }
 
-static void asus_cleanup_pci_hotplug(struct hotplug_slot *hotplug_slot)
-{
-	kfree(hotplug_slot->info);
-	kfree(hotplug_slot);
-}
-
 static struct hotplug_slot_ops asus_hotplug_slot_ops = {
 	.owner = THIS_MODULE,
 	.get_adapter_status = asus_get_adapter_status,
@@ -905,7 +899,6 @@ static int asus_setup_pci_hotplug(struct asus_wmi *asus)
 		goto error_info;
 
 	asus->hotplug_slot->private = asus;
-	asus->hotplug_slot->release = &asus_cleanup_pci_hotplug;
 	asus->hotplug_slot->ops = &asus_hotplug_slot_ops;
 	asus_get_adapter_status(asus->hotplug_slot,
 				&asus->hotplug_slot->info->adapter_status);
@@ -1051,8 +1044,11 @@ static void asus_wmi_rfkill_exit(struct asus_wmi *asus)
 	 * asus_unregister_rfkill_notifier()
 	 */
 	asus_rfkill_hotplug(asus);
-	if (asus->hotplug_slot)
+	if (asus->hotplug_slot) {
 		pci_hp_deregister(asus->hotplug_slot);
+		kfree(asus->hotplug_slot->info);
+		kfree(asus->hotplug_slot);
+	}
 	if (asus->hotplug_workqueue)
 		destroy_workqueue(asus->hotplug_workqueue);
 
diff --git a/drivers/platform/x86/eeepc-laptop.c b/drivers/platform/x86/eeepc-laptop.c
index 4c38904a8a32..a4bbf6ecd1f0 100644
--- a/drivers/platform/x86/eeepc-laptop.c
+++ b/drivers/platform/x86/eeepc-laptop.c
@@ -726,12 +726,6 @@ static int eeepc_get_adapter_status(struct hotplug_slot *hotplug_slot,
 	return 0;
 }
 
-static void eeepc_cleanup_pci_hotplug(struct hotplug_slot *hotplug_slot)
-{
-	kfree(hotplug_slot->info);
-	kfree(hotplug_slot);
-}
-
 static struct hotplug_slot_ops eeepc_hotplug_slot_ops = {
 	.owner = THIS_MODULE,
 	.get_adapter_status = eeepc_get_adapter_status,
@@ -758,7 +752,6 @@ static int eeepc_setup_pci_hotplug(struct eeepc_laptop *eeepc)
 		goto error_info;
 
 	eeepc->hotplug_slot->private = eeepc;
-	eeepc->hotplug_slot->release = &eeepc_cleanup_pci_hotplug;
 	eeepc->hotplug_slot->ops = &eeepc_hotplug_slot_ops;
 	eeepc_get_adapter_status(eeepc->hotplug_slot,
 				 &eeepc->hotplug_slot->info->adapter_status);
@@ -837,8 +830,11 @@ static void eeepc_rfkill_exit(struct eeepc_laptop *eeepc)
 		eeepc->wlan_rfkill = NULL;
 	}
 
-	if (eeepc->hotplug_slot)
+	if (eeepc->hotplug_slot) {
 		pci_hp_deregister(eeepc->hotplug_slot);
+		kfree(eeepc->hotplug_slot->info);
+		kfree(eeepc->hotplug_slot);
+	}
 
 	if (eeepc->bluetooth_rfkill) {
 		rfkill_unregister(eeepc->bluetooth_rfkill);
diff --git a/drivers/platform/x86/i2c-multi-instantiate.c b/drivers/platform/x86/i2c-multi-instantiate.c
new file mode 100644
index 000000000000..5456581b473c
--- /dev/null
+++ b/drivers/platform/x86/i2c-multi-instantiate.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * I2C multi-instantiate driver, pseudo driver to instantiate multiple
+ * i2c-clients from a single fwnode.
+ *
+ * Copyright 2018 Hans de Goede <hdegoede@redhat.com>
+ */
+
+#include <linux/acpi.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+struct i2c_inst_data {
+	const char *type;
+	int gpio_irq_idx;
+};
+
+struct i2c_multi_inst_data {
+	int num_clients;
+	struct i2c_client *clients[0];
+};
+
+static int i2c_multi_inst_probe(struct platform_device *pdev)
+{
+	struct i2c_multi_inst_data *multi;
+	const struct acpi_device_id *match;
+	const struct i2c_inst_data *inst_data;
+	struct i2c_board_info board_info = {};
+	struct device *dev = &pdev->dev;
+	struct acpi_device *adev;
+	char name[32];
+	int i, ret;
+
+	match = acpi_match_device(dev->driver->acpi_match_table, dev);
+	if (!match) {
+		dev_err(dev, "Error ACPI match data is missing\n");
+		return -ENODEV;
+	}
+	inst_data = (const struct i2c_inst_data *)match->driver_data;
+
+	adev = ACPI_COMPANION(dev);
+
+	/* Count number of clients to instantiate */
+	for (i = 0; inst_data[i].type; i++) {}
+
+	multi = devm_kmalloc(dev,
+			offsetof(struct i2c_multi_inst_data, clients[i]),
+			GFP_KERNEL);
+	if (!multi)
+		return -ENOMEM;
+
+	multi->num_clients = i;
+
+	for (i = 0; i < multi->num_clients; i++) {
+		memset(&board_info, 0, sizeof(board_info));
+		strlcpy(board_info.type, inst_data[i].type, I2C_NAME_SIZE);
+		snprintf(name, sizeof(name), "%s-%s", match->id,
+			 inst_data[i].type);
+		board_info.dev_name = name;
+		board_info.irq = 0;
+		if (inst_data[i].gpio_irq_idx != -1) {
+			ret = acpi_dev_gpio_irq_get(adev,
+						    inst_data[i].gpio_irq_idx);
+			if (ret < 0) {
+				dev_err(dev, "Error requesting irq at index %d: %d\n",
+					inst_data[i].gpio_irq_idx, ret);
+				goto error;
+			}
+			board_info.irq = ret;
+		}
+		multi->clients[i] = i2c_acpi_new_device(dev, i, &board_info);
+		if (!multi->clients[i]) {
+			dev_err(dev, "Error creating i2c-client, idx %d\n", i);
+			ret = -ENODEV;
+			goto error;
+		}
+	}
+
+	platform_set_drvdata(pdev, multi);
+	return 0;
+
+error:
+	while (--i >= 0)
+		i2c_unregister_device(multi->clients[i]);
+
+	return ret;
+}
+
+static int i2c_multi_inst_remove(struct platform_device *pdev)
+{
+	struct i2c_multi_inst_data *multi = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < multi->num_clients; i++)
+		i2c_unregister_device(multi->clients[i]);
+
+	return 0;
+}
+
+static const struct i2c_inst_data bsg1160_data[]  = {
+	{ "bmc150_accel", 0 },
+	{ "bmc150_magn", -1 },
+	{ "bmg160", -1 },
+	{}
+};
+
+/*
+ * Note new device-ids must also be added to i2c_multi_instantiate_ids in
+ * drivers/acpi/scan.c: acpi_device_enumeration_by_parent().
+ */
+static const struct acpi_device_id i2c_multi_inst_acpi_ids[] = {
+	{ "BSG1160", (unsigned long)bsg1160_data },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, i2c_multi_inst_acpi_ids);
+
+static struct platform_driver i2c_multi_inst_driver = {
+	.driver	= {
+		.name = "I2C multi instantiate pseudo device driver",
+		.acpi_match_table = ACPI_PTR(i2c_multi_inst_acpi_ids),
+	},
+	.probe = i2c_multi_inst_probe,
+	.remove = i2c_multi_inst_remove,
+};
+module_platform_driver(i2c_multi_inst_driver);
+
+MODULE_DESCRIPTION("I2C multi instantiate pseudo device driver");
+MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/platform/x86/intel_punit_ipc.c b/drivers/platform/x86/intel_punit_ipc.c
index b5b890127479..f1afc0ebbc68 100644
--- a/drivers/platform/x86/intel_punit_ipc.c
+++ b/drivers/platform/x86/intel_punit_ipc.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/mod_devicetable.h>
 #include <linux/acpi.h>
 #include <linux/delay.h>
 #include <linux/bitops.h>
diff --git a/drivers/powercap/Kconfig b/drivers/powercap/Kconfig
index 85727ef6ce8e..6ac27e5908f5 100644
--- a/drivers/powercap/Kconfig
+++ b/drivers/powercap/Kconfig
@@ -29,4 +29,14 @@ config INTEL_RAPL
 	  controller, CPU core (Power Plance 0), graphics uncore (Power Plane
 	  1), etc.
 
+config IDLE_INJECT
+	bool "Idle injection framework"
+	depends on CPU_IDLE
+	default n
+	help
+	  This enables support for the idle injection framework. It
+	  provides a way to force idle periods on a set of specified
+	  CPUs for power capping. Idle period can be injected
+	  synchronously on a set of specified CPUs or alternatively
+	  on a per CPU basis.
 endif
diff --git a/drivers/powercap/Makefile b/drivers/powercap/Makefile
index 0a21ef31372b..1b328854b36e 100644
--- a/drivers/powercap/Makefile
+++ b/drivers/powercap/Makefile
@@ -1,2 +1,3 @@
 obj-$(CONFIG_POWERCAP)	+= powercap_sys.o
 obj-$(CONFIG_INTEL_RAPL) += intel_rapl.o
+obj-$(CONFIG_IDLE_INJECT) += idle_inject.o
diff --git a/drivers/powercap/idle_inject.c b/drivers/powercap/idle_inject.c
new file mode 100644
index 000000000000..24ff2a068978
--- /dev/null
+++ b/drivers/powercap/idle_inject.c
@@ -0,0 +1,356 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2018 Linaro Limited
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ * The idle injection framework provides a way to force CPUs to enter idle
+ * states for a specified fraction of time over a specified period.
+ *
+ * It relies on the smpboot kthreads feature providing common code for CPU
+ * hotplug and thread [un]parking.
+ *
+ * All of the kthreads used for idle injection are created at init time.
+ *
+ * Next, the users of the the idle injection framework provide a cpumask via
+ * its register function. The kthreads will be synchronized with respect to
+ * this cpumask.
+ *
+ * The idle + run duration is specified via separate helpers and that allows
+ * idle injection to be started.
+ *
+ * The idle injection kthreads will call play_idle() with the idle duration
+ * specified as per the above.
+ *
+ * After all of them have been woken up, a timer is set to start the next idle
+ * injection cycle.
+ *
+ * The timer interrupt handler will wake up the idle injection kthreads for
+ * all of the CPUs in the cpumask provided by the user.
+ *
+ * Idle injection is stopped synchronously and no leftover idle injection
+ * kthread activity after its completion is guaranteed.
+ *
+ * It is up to the user of this framework to provide a lock for higher-level
+ * synchronization to prevent race conditions like starting idle injection
+ * while unregistering from the framework.
+ */
+#define pr_fmt(fmt) "ii_dev: " fmt
+
+#include <linux/cpu.h>
+#include <linux/hrtimer.h>
+#include <linux/kthread.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/smpboot.h>
+
+#include <uapi/linux/sched/types.h>
+
+/**
+ * struct idle_inject_thread - task on/off switch structure
+ * @tsk: task injecting the idle cycles
+ * @should_run: whether or not to run the task (for the smpboot kthread API)
+ */
+struct idle_inject_thread {
+	struct task_struct *tsk;
+	int should_run;
+};
+
+/**
+ * struct idle_inject_device - idle injection data
+ * @timer: idle injection period timer
+ * @idle_duration_ms: duration of CPU idle time to inject
+ * @run_duration_ms: duration of CPU run time to allow
+ * @cpumask: mask of CPUs affected by idle injection
+ */
+struct idle_inject_device {
+	struct hrtimer timer;
+	unsigned int idle_duration_ms;
+	unsigned int run_duration_ms;
+	unsigned long int cpumask[0];
+};
+
+static DEFINE_PER_CPU(struct idle_inject_thread, idle_inject_thread);
+static DEFINE_PER_CPU(struct idle_inject_device *, idle_inject_device);
+
+/**
+ * idle_inject_wakeup - Wake up idle injection threads
+ * @ii_dev: target idle injection device
+ *
+ * Every idle injection task associated with the given idle injection device
+ * and running on an online CPU will be woken up.
+ */
+static void idle_inject_wakeup(struct idle_inject_device *ii_dev)
+{
+	struct idle_inject_thread *iit;
+	unsigned int cpu;
+
+	for_each_cpu_and(cpu, to_cpumask(ii_dev->cpumask), cpu_online_mask) {
+		iit = per_cpu_ptr(&idle_inject_thread, cpu);
+		iit->should_run = 1;
+		wake_up_process(iit->tsk);
+	}
+}
+
+/**
+ * idle_inject_timer_fn - idle injection timer function
+ * @timer: idle injection hrtimer
+ *
+ * This function is called when the idle injection timer expires.  It wakes up
+ * idle injection tasks associated with the timer and they, in turn, invoke
+ * play_idle() to inject a specified amount of CPU idle time.
+ *
+ * Return: HRTIMER_RESTART.
+ */
+static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer)
+{
+	unsigned int duration_ms;
+	struct idle_inject_device *ii_dev =
+		container_of(timer, struct idle_inject_device, timer);
+
+	duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+	duration_ms += READ_ONCE(ii_dev->idle_duration_ms);
+
+	idle_inject_wakeup(ii_dev);
+
+	hrtimer_forward_now(timer, ms_to_ktime(duration_ms));
+
+	return HRTIMER_RESTART;
+}
+
+/**
+ * idle_inject_fn - idle injection work function
+ * @cpu: the CPU owning the task
+ *
+ * This function calls play_idle() to inject a specified amount of CPU idle
+ * time.
+ */
+static void idle_inject_fn(unsigned int cpu)
+{
+	struct idle_inject_device *ii_dev;
+	struct idle_inject_thread *iit;
+
+	ii_dev = per_cpu(idle_inject_device, cpu);
+	iit = per_cpu_ptr(&idle_inject_thread, cpu);
+
+	/*
+	 * Let the smpboot main loop know that the task should not run again.
+	 */
+	iit->should_run = 0;
+
+	play_idle(READ_ONCE(ii_dev->idle_duration_ms));
+}
+
+/**
+ * idle_inject_set_duration - idle and run duration update helper
+ * @run_duration_ms: CPU run time to allow in milliseconds
+ * @idle_duration_ms: CPU idle time to inject in milliseconds
+ */
+void idle_inject_set_duration(struct idle_inject_device *ii_dev,
+			      unsigned int run_duration_ms,
+			      unsigned int idle_duration_ms)
+{
+	if (run_duration_ms && idle_duration_ms) {
+		WRITE_ONCE(ii_dev->run_duration_ms, run_duration_ms);
+		WRITE_ONCE(ii_dev->idle_duration_ms, idle_duration_ms);
+	}
+}
+
+/**
+ * idle_inject_get_duration - idle and run duration retrieval helper
+ * @run_duration_ms: memory location to store the current CPU run time
+ * @idle_duration_ms: memory location to store the current CPU idle time
+ */
+void idle_inject_get_duration(struct idle_inject_device *ii_dev,
+			      unsigned int *run_duration_ms,
+			      unsigned int *idle_duration_ms)
+{
+	*run_duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+	*idle_duration_ms = READ_ONCE(ii_dev->idle_duration_ms);
+}
+
+/**
+ * idle_inject_start - start idle injections
+ * @ii_dev: idle injection control device structure
+ *
+ * The function starts idle injection by first waking up all of the idle
+ * injection kthreads associated with @ii_dev to let them inject CPU idle time
+ * sets up a timer to start the next idle injection period.
+ *
+ * Return: -EINVAL if the CPU idle or CPU run time is not set or 0 on success.
+ */
+int idle_inject_start(struct idle_inject_device *ii_dev)
+{
+	unsigned int idle_duration_ms = READ_ONCE(ii_dev->idle_duration_ms);
+	unsigned int run_duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+
+	if (!idle_duration_ms || !run_duration_ms)
+		return -EINVAL;
+
+	pr_debug("Starting injecting idle cycles on CPUs '%*pbl'\n",
+		 cpumask_pr_args(to_cpumask(ii_dev->cpumask)));
+
+	idle_inject_wakeup(ii_dev);
+
+	hrtimer_start(&ii_dev->timer,
+		      ms_to_ktime(idle_duration_ms + run_duration_ms),
+		      HRTIMER_MODE_REL);
+
+	return 0;
+}
+
+/**
+ * idle_inject_stop - stops idle injections
+ * @ii_dev: idle injection control device structure
+ *
+ * The function stops idle injection and waits for the threads to finish work.
+ * If CPU idle time is being injected when this function runs, then it will
+ * wait until the end of the cycle.
+ *
+ * When it returns, there is no more idle injection kthread activity.  The
+ * kthreads are scheduled out and the periodic timer is off.
+ */
+void idle_inject_stop(struct idle_inject_device *ii_dev)
+{
+	struct idle_inject_thread *iit;
+	unsigned int cpu;
+
+	pr_debug("Stopping idle injection on CPUs '%*pbl'\n",
+		 cpumask_pr_args(to_cpumask(ii_dev->cpumask)));
+
+	hrtimer_cancel(&ii_dev->timer);
+
+	/*
+	 * Stopping idle injection requires all of the idle injection kthreads
+	 * associated with the given cpumask to be parked and stay that way, so
+	 * prevent CPUs from going online at this point.  Any CPUs going online
+	 * after the loop below will be covered by clearing the should_run flag
+	 * that will cause the smpboot main loop to schedule them out.
+	 */
+	cpu_hotplug_disable();
+
+	/*
+	 * Iterate over all (online + offline) CPUs here in case one of them
+	 * goes offline with the should_run flag set so as to prevent its idle
+	 * injection kthread from running when the CPU goes online again after
+	 * the ii_dev has been freed.
+	 */
+	for_each_cpu(cpu, to_cpumask(ii_dev->cpumask)) {
+		iit = per_cpu_ptr(&idle_inject_thread, cpu);
+		iit->should_run = 0;
+
+		wait_task_inactive(iit->tsk, 0);
+	}
+
+	cpu_hotplug_enable();
+}
+
+/**
+ * idle_inject_setup - prepare the current task for idle injection
+ * @cpu: not used
+ *
+ * Called once, this function is in charge of setting the current task's
+ * scheduler parameters to make it an RT task.
+ */
+static void idle_inject_setup(unsigned int cpu)
+{
+	struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO / 2 };
+
+	sched_setscheduler(current, SCHED_FIFO, &param);
+}
+
+/**
+ * idle_inject_should_run - function helper for the smpboot API
+ * @cpu: CPU the kthread is running on
+ *
+ * Return: whether or not the thread can run.
+ */
+static int idle_inject_should_run(unsigned int cpu)
+{
+	struct idle_inject_thread *iit =
+		per_cpu_ptr(&idle_inject_thread, cpu);
+
+	return iit->should_run;
+}
+
+/**
+ * idle_inject_register - initialize idle injection on a set of CPUs
+ * @cpumask: CPUs to be affected by idle injection
+ *
+ * This function creates an idle injection control device structure for the
+ * given set of CPUs and initializes the timer associated with it.  It does not
+ * start any injection cycles.
+ *
+ * Return: NULL if memory allocation fails, idle injection control device
+ * pointer on success.
+ */
+struct idle_inject_device *idle_inject_register(struct cpumask *cpumask)
+{
+	struct idle_inject_device *ii_dev;
+	int cpu, cpu_rb;
+
+	ii_dev = kzalloc(sizeof(*ii_dev) + cpumask_size(), GFP_KERNEL);
+	if (!ii_dev)
+		return NULL;
+
+	cpumask_copy(to_cpumask(ii_dev->cpumask), cpumask);
+	hrtimer_init(&ii_dev->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	ii_dev->timer.function = idle_inject_timer_fn;
+
+	for_each_cpu(cpu, to_cpumask(ii_dev->cpumask)) {
+
+		if (per_cpu(idle_inject_device, cpu)) {
+			pr_err("cpu%d is already registered\n", cpu);
+			goto out_rollback;
+		}
+
+		per_cpu(idle_inject_device, cpu) = ii_dev;
+	}
+
+	return ii_dev;
+
+out_rollback:
+	for_each_cpu(cpu_rb, to_cpumask(ii_dev->cpumask)) {
+		if (cpu == cpu_rb)
+			break;
+		per_cpu(idle_inject_device, cpu_rb) = NULL;
+	}
+
+	kfree(ii_dev);
+
+	return NULL;
+}
+
+/**
+ * idle_inject_unregister - unregister idle injection control device
+ * @ii_dev: idle injection control device to unregister
+ *
+ * The function stops idle injection for the given control device,
+ * unregisters its kthreads and frees memory allocated when that device was
+ * created.
+ */
+void idle_inject_unregister(struct idle_inject_device *ii_dev)
+{
+	unsigned int cpu;
+
+	idle_inject_stop(ii_dev);
+
+	for_each_cpu(cpu, to_cpumask(ii_dev->cpumask))
+		per_cpu(idle_inject_device, cpu) = NULL;
+
+	kfree(ii_dev);
+}
+
+static struct smp_hotplug_thread idle_inject_threads = {
+	.store = &idle_inject_thread.tsk,
+	.setup = idle_inject_setup,
+	.thread_fn = idle_inject_fn,
+	.thread_comm = "idle_inject/%u",
+	.thread_should_run = idle_inject_should_run,
+};
+
+static int __init idle_inject_init(void)
+{
+	return smpboot_register_percpu_thread(&idle_inject_threads);
+}
+early_initcall(idle_inject_init);
diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig
index 474c988d2e95..d137c480db46 100644
--- a/drivers/ptp/Kconfig
+++ b/drivers/ptp/Kconfig
@@ -43,7 +43,7 @@ config PTP_1588_CLOCK_DTE
 
 config PTP_1588_CLOCK_QORIQ
 	tristate "Freescale QorIQ 1588 timer as PTP clock"
-	depends on GIANFAR
+	depends on GIANFAR || FSL_DPAA_ETH
 	depends on PTP_1588_CLOCK
 	default y
 	help
diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c
index e8652c148c52..fdd49c26bbcc 100644
--- a/drivers/ptp/ptp_qoriq.c
+++ b/drivers/ptp/ptp_qoriq.c
@@ -29,6 +29,7 @@
 #include <linux/of_platform.h>
 #include <linux/timex.h>
 #include <linux/slab.h>
+#include <linux/clk.h>
 
 #include <linux/fsl/ptp_qoriq.h>
 
@@ -39,11 +40,12 @@
 /* Caller must hold qoriq_ptp->lock. */
 static u64 tmr_cnt_read(struct qoriq_ptp *qoriq_ptp)
 {
+	struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
 	u64 ns;
 	u32 lo, hi;
 
-	lo = qoriq_read(&qoriq_ptp->regs->tmr_cnt_l);
-	hi = qoriq_read(&qoriq_ptp->regs->tmr_cnt_h);
+	lo = qoriq_read(&regs->ctrl_regs->tmr_cnt_l);
+	hi = qoriq_read(&regs->ctrl_regs->tmr_cnt_h);
 	ns = ((u64) hi) << 32;
 	ns |= lo;
 	return ns;
@@ -52,16 +54,18 @@ static u64 tmr_cnt_read(struct qoriq_ptp *qoriq_ptp)
 /* Caller must hold qoriq_ptp->lock. */
 static void tmr_cnt_write(struct qoriq_ptp *qoriq_ptp, u64 ns)
 {
+	struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
 	u32 hi = ns >> 32;
 	u32 lo = ns & 0xffffffff;
 
-	qoriq_write(&qoriq_ptp->regs->tmr_cnt_l, lo);
-	qoriq_write(&qoriq_ptp->regs->tmr_cnt_h, hi);
+	qoriq_write(&regs->ctrl_regs->tmr_cnt_l, lo);
+	qoriq_write(&regs->ctrl_regs->tmr_cnt_h, hi);
 }
 
 /* Caller must hold qoriq_ptp->lock. */
 static void set_alarm(struct qoriq_ptp *qoriq_ptp)
 {
+	struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
 	u64 ns;
 	u32 lo, hi;
 
@@ -70,16 +74,18 @@ static void set_alarm(struct qoriq_ptp *qoriq_ptp)
 	ns -= qoriq_ptp->tclk_period;
 	hi = ns >> 32;
 	lo = ns & 0xffffffff;
-	qoriq_write(&qoriq_ptp->regs->tmr_alarm1_l, lo);
-	qoriq_write(&qoriq_ptp->regs->tmr_alarm1_h, hi);
+	qoriq_write(&regs->alarm_regs->tmr_alarm1_l, lo);
+	qoriq_write(&regs->alarm_regs->tmr_alarm1_h, hi);
 }
 
 /* Caller must hold qoriq_ptp->lock. */
 static void set_fipers(struct qoriq_ptp *qoriq_ptp)
 {
+	struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
+
 	set_alarm(qoriq_ptp);
-	qoriq_write(&qoriq_ptp->regs->tmr_fiper1, qoriq_ptp->tmr_fiper1);
-	qoriq_write(&qoriq_ptp->regs->tmr_fiper2, qoriq_ptp->tmr_fiper2);
+	qoriq_write(&regs->fiper_regs->tmr_fiper1, qoriq_ptp->tmr_fiper1);
+	qoriq_write(&regs->fiper_regs->tmr_fiper2, qoriq_ptp->tmr_fiper2);
 }
 
 /*
@@ -89,16 +95,17 @@ static void set_fipers(struct qoriq_ptp *qoriq_ptp)
 static irqreturn_t isr(int irq, void *priv)
 {
 	struct qoriq_ptp *qoriq_ptp = priv;
+	struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
 	struct ptp_clock_event event;
 	u64 ns;
 	u32 ack = 0, lo, hi, mask, val;
 
-	val = qoriq_read(&qoriq_ptp->regs->tmr_tevent);
+	val = qoriq_read(&regs->ctrl_regs->tmr_tevent);
 
 	if (val & ETS1) {
 		ack |= ETS1;
-		hi = qoriq_read(&qoriq_ptp->regs->tmr_etts1_h);
-		lo = qoriq_read(&qoriq_ptp->regs->tmr_etts1_l);
+		hi = qoriq_read(&regs->etts_regs->tmr_etts1_h);
+		lo = qoriq_read(&regs->etts_regs->tmr_etts1_l);
 		event.type = PTP_CLOCK_EXTTS;
 		event.index = 0;
 		event.timestamp = ((u64) hi) << 32;
@@ -108,8 +115,8 @@ static irqreturn_t isr(int irq, void *priv)
 
 	if (val & ETS2) {
 		ack |= ETS2;
-		hi = qoriq_read(&qoriq_ptp->regs->tmr_etts2_h);
-		lo = qoriq_read(&qoriq_ptp->regs->tmr_etts2_l);
+		hi = qoriq_read(&regs->etts_regs->tmr_etts2_h);
+		lo = qoriq_read(&regs->etts_regs->tmr_etts2_l);
 		event.type = PTP_CLOCK_EXTTS;
 		event.index = 1;
 		event.timestamp = ((u64) hi) << 32;
@@ -130,16 +137,16 @@ static irqreturn_t isr(int irq, void *priv)
 			hi = ns >> 32;
 			lo = ns & 0xffffffff;
 			spin_lock(&qoriq_ptp->lock);
-			qoriq_write(&qoriq_ptp->regs->tmr_alarm2_l, lo);
-			qoriq_write(&qoriq_ptp->regs->tmr_alarm2_h, hi);
+			qoriq_write(&regs->alarm_regs->tmr_alarm2_l, lo);
+			qoriq_write(&regs->alarm_regs->tmr_alarm2_h, hi);
 			spin_unlock(&qoriq_ptp->lock);
 			qoriq_ptp->alarm_value = ns;
 		} else {
-			qoriq_write(&qoriq_ptp->regs->tmr_tevent, ALM2);
+			qoriq_write(&regs->ctrl_regs->tmr_tevent, ALM2);
 			spin_lock(&qoriq_ptp->lock);
-			mask = qoriq_read(&qoriq_ptp->regs->tmr_temask);
+			mask = qoriq_read(&regs->ctrl_regs->tmr_temask);
 			mask &= ~ALM2EN;
-			qoriq_write(&qoriq_ptp->regs->tmr_temask, mask);
+			qoriq_write(&regs->ctrl_regs->tmr_temask, mask);
 			spin_unlock(&qoriq_ptp->lock);
 			qoriq_ptp->alarm_value = 0;
 			qoriq_ptp->alarm_interval = 0;
@@ -153,7 +160,7 @@ static irqreturn_t isr(int irq, void *priv)
 	}
 
 	if (ack) {
-		qoriq_write(&qoriq_ptp->regs->tmr_tevent, ack);
+		qoriq_write(&regs->ctrl_regs->tmr_tevent, ack);
 		return IRQ_HANDLED;
 	} else
 		return IRQ_NONE;
@@ -169,6 +176,7 @@ static int ptp_qoriq_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 	u32 tmr_add;
 	int neg_adj = 0;
 	struct qoriq_ptp *qoriq_ptp = container_of(ptp, struct qoriq_ptp, caps);
+	struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
 
 	if (scaled_ppm < 0) {
 		neg_adj = 1;
@@ -186,7 +194,7 @@ static int ptp_qoriq_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 
 	tmr_add = neg_adj ? tmr_add - diff : tmr_add + diff;
 
-	qoriq_write(&qoriq_ptp->regs->tmr_add, tmr_add);
+	qoriq_write(&regs->ctrl_regs->tmr_add, tmr_add);
 
 	return 0;
 }
@@ -250,6 +258,7 @@ static int ptp_qoriq_enable(struct ptp_clock_info *ptp,
 			      struct ptp_clock_request *rq, int on)
 {
 	struct qoriq_ptp *qoriq_ptp = container_of(ptp, struct qoriq_ptp, caps);
+	struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
 	unsigned long flags;
 	u32 bit, mask;
 
@@ -266,23 +275,23 @@ static int ptp_qoriq_enable(struct ptp_clock_info *ptp,
 			return -EINVAL;
 		}
 		spin_lock_irqsave(&qoriq_ptp->lock, flags);
-		mask = qoriq_read(&qoriq_ptp->regs->tmr_temask);
+		mask = qoriq_read(&regs->ctrl_regs->tmr_temask);
 		if (on)
 			mask |= bit;
 		else
 			mask &= ~bit;
-		qoriq_write(&qoriq_ptp->regs->tmr_temask, mask);
+		qoriq_write(&regs->ctrl_regs->tmr_temask, mask);
 		spin_unlock_irqrestore(&qoriq_ptp->lock, flags);
 		return 0;
 
 	case PTP_CLK_REQ_PPS:
 		spin_lock_irqsave(&qoriq_ptp->lock, flags);
-		mask = qoriq_read(&qoriq_ptp->regs->tmr_temask);
+		mask = qoriq_read(&regs->ctrl_regs->tmr_temask);
 		if (on)
 			mask |= PP1EN;
 		else
 			mask &= ~PP1EN;
-		qoriq_write(&qoriq_ptp->regs->tmr_temask, mask);
+		qoriq_write(&regs->ctrl_regs->tmr_temask, mask);
 		spin_unlock_irqrestore(&qoriq_ptp->lock, flags);
 		return 0;
 
@@ -309,20 +318,123 @@ static const struct ptp_clock_info ptp_qoriq_caps = {
 	.enable		= ptp_qoriq_enable,
 };
 
+/**
+ * qoriq_ptp_nominal_freq - calculate nominal frequency according to
+ *			    reference clock frequency
+ *
+ * @clk_src: reference clock frequency
+ *
+ * The nominal frequency is the desired clock frequency.
+ * It should be less than the reference clock frequency.
+ * It should be a factor of 1000MHz.
+ *
+ * Return the nominal frequency
+ */
+static u32 qoriq_ptp_nominal_freq(u32 clk_src)
+{
+	u32 remainder = 0;
+
+	clk_src /= 1000000;
+	remainder = clk_src % 100;
+	if (remainder) {
+		clk_src -= remainder;
+		clk_src += 100;
+	}
+
+	do {
+		clk_src -= 100;
+
+	} while (1000 % clk_src);
+
+	return clk_src * 1000000;
+}
+
+/**
+ * qoriq_ptp_auto_config - calculate a set of default configurations
+ *
+ * @qoriq_ptp: pointer to qoriq_ptp
+ * @node: pointer to device_node
+ *
+ * If below dts properties are not provided, this function will be
+ * called to calculate a set of default configurations for them.
+ *   "fsl,tclk-period"
+ *   "fsl,tmr-prsc"
+ *   "fsl,tmr-add"
+ *   "fsl,tmr-fiper1"
+ *   "fsl,tmr-fiper2"
+ *   "fsl,max-adj"
+ *
+ * Return 0 if success
+ */
+static int qoriq_ptp_auto_config(struct qoriq_ptp *qoriq_ptp,
+				 struct device_node *node)
+{
+	struct clk *clk;
+	u64 freq_comp;
+	u64 max_adj;
+	u32 nominal_freq;
+	u32 remainder = 0;
+	u32 clk_src = 0;
+
+	qoriq_ptp->cksel = DEFAULT_CKSEL;
+
+	clk = of_clk_get(node, 0);
+	if (!IS_ERR(clk)) {
+		clk_src = clk_get_rate(clk);
+		clk_put(clk);
+	}
+
+	if (clk_src <= 100000000UL) {
+		pr_err("error reference clock value, or lower than 100MHz\n");
+		return -EINVAL;
+	}
+
+	nominal_freq = qoriq_ptp_nominal_freq(clk_src);
+	if (!nominal_freq)
+		return -EINVAL;
+
+	qoriq_ptp->tclk_period = 1000000000UL / nominal_freq;
+	qoriq_ptp->tmr_prsc = DEFAULT_TMR_PRSC;
+
+	/* Calculate initial frequency compensation value for TMR_ADD register.
+	 * freq_comp = ceil(2^32 / freq_ratio)
+	 * freq_ratio = reference_clock_freq / nominal_freq
+	 */
+	freq_comp = ((u64)1 << 32) * nominal_freq;
+	freq_comp = div_u64_rem(freq_comp, clk_src, &remainder);
+	if (remainder)
+		freq_comp++;
+
+	qoriq_ptp->tmr_add = freq_comp;
+	qoriq_ptp->tmr_fiper1 = DEFAULT_FIPER1_PERIOD - qoriq_ptp->tclk_period;
+	qoriq_ptp->tmr_fiper2 = DEFAULT_FIPER2_PERIOD - qoriq_ptp->tclk_period;
+
+	/* max_adj = 1000000000 * (freq_ratio - 1.0) - 1
+	 * freq_ratio = reference_clock_freq / nominal_freq
+	 */
+	max_adj = 1000000000ULL * (clk_src - nominal_freq);
+	max_adj = div_u64(max_adj, nominal_freq) - 1;
+	qoriq_ptp->caps.max_adj = max_adj;
+
+	return 0;
+}
+
 static int qoriq_ptp_probe(struct platform_device *dev)
 {
 	struct device_node *node = dev->dev.of_node;
 	struct qoriq_ptp *qoriq_ptp;
+	struct qoriq_ptp_registers *regs;
 	struct timespec64 now;
 	int err = -ENOMEM;
 	u32 tmr_ctrl;
 	unsigned long flags;
+	void __iomem *base;
 
 	qoriq_ptp = kzalloc(sizeof(*qoriq_ptp), GFP_KERNEL);
 	if (!qoriq_ptp)
 		goto no_memory;
 
-	err = -ENODEV;
+	err = -EINVAL;
 
 	qoriq_ptp->caps = ptp_qoriq_caps;
 
@@ -341,17 +453,21 @@ static int qoriq_ptp_probe(struct platform_device *dev)
 				 "fsl,tmr-fiper2", &qoriq_ptp->tmr_fiper2) ||
 	    of_property_read_u32(node,
 				 "fsl,max-adj", &qoriq_ptp->caps.max_adj)) {
-		pr_err("device tree node missing required elements\n");
-		goto no_node;
+		pr_warn("device tree node missing required elements, try automatic configuration\n");
+
+		if (qoriq_ptp_auto_config(qoriq_ptp, node))
+			goto no_config;
 	}
 
+	err = -ENODEV;
+
 	qoriq_ptp->irq = platform_get_irq(dev, 0);
 
 	if (qoriq_ptp->irq < 0) {
 		pr_err("irq not in device tree\n");
 		goto no_node;
 	}
-	if (request_irq(qoriq_ptp->irq, isr, 0, DRIVER, qoriq_ptp)) {
+	if (request_irq(qoriq_ptp->irq, isr, IRQF_SHARED, DRIVER, qoriq_ptp)) {
 		pr_err("request_irq failed\n");
 		goto no_node;
 	}
@@ -368,12 +484,27 @@ static int qoriq_ptp_probe(struct platform_device *dev)
 
 	spin_lock_init(&qoriq_ptp->lock);
 
-	qoriq_ptp->regs = ioremap(qoriq_ptp->rsrc->start,
-				resource_size(qoriq_ptp->rsrc));
-	if (!qoriq_ptp->regs) {
+	base = ioremap(qoriq_ptp->rsrc->start,
+		       resource_size(qoriq_ptp->rsrc));
+	if (!base) {
 		pr_err("ioremap ptp registers failed\n");
 		goto no_ioremap;
 	}
+
+	qoriq_ptp->base = base;
+
+	if (of_device_is_compatible(node, "fsl,fman-ptp-timer")) {
+		qoriq_ptp->regs.ctrl_regs = base + FMAN_CTRL_REGS_OFFSET;
+		qoriq_ptp->regs.alarm_regs = base + FMAN_ALARM_REGS_OFFSET;
+		qoriq_ptp->regs.fiper_regs = base + FMAN_FIPER_REGS_OFFSET;
+		qoriq_ptp->regs.etts_regs = base + FMAN_ETTS_REGS_OFFSET;
+	} else {
+		qoriq_ptp->regs.ctrl_regs = base + CTRL_REGS_OFFSET;
+		qoriq_ptp->regs.alarm_regs = base + ALARM_REGS_OFFSET;
+		qoriq_ptp->regs.fiper_regs = base + FIPER_REGS_OFFSET;
+		qoriq_ptp->regs.etts_regs = base + ETTS_REGS_OFFSET;
+	}
+
 	ktime_get_real_ts64(&now);
 	ptp_qoriq_settime(&qoriq_ptp->caps, &now);
 
@@ -383,13 +514,14 @@ static int qoriq_ptp_probe(struct platform_device *dev)
 
 	spin_lock_irqsave(&qoriq_ptp->lock, flags);
 
-	qoriq_write(&qoriq_ptp->regs->tmr_ctrl,   tmr_ctrl);
-	qoriq_write(&qoriq_ptp->regs->tmr_add,    qoriq_ptp->tmr_add);
-	qoriq_write(&qoriq_ptp->regs->tmr_prsc,   qoriq_ptp->tmr_prsc);
-	qoriq_write(&qoriq_ptp->regs->tmr_fiper1, qoriq_ptp->tmr_fiper1);
-	qoriq_write(&qoriq_ptp->regs->tmr_fiper2, qoriq_ptp->tmr_fiper2);
+	regs = &qoriq_ptp->regs;
+	qoriq_write(&regs->ctrl_regs->tmr_ctrl,   tmr_ctrl);
+	qoriq_write(&regs->ctrl_regs->tmr_add,    qoriq_ptp->tmr_add);
+	qoriq_write(&regs->ctrl_regs->tmr_prsc,   qoriq_ptp->tmr_prsc);
+	qoriq_write(&regs->fiper_regs->tmr_fiper1, qoriq_ptp->tmr_fiper1);
+	qoriq_write(&regs->fiper_regs->tmr_fiper2, qoriq_ptp->tmr_fiper2);
 	set_alarm(qoriq_ptp);
-	qoriq_write(&qoriq_ptp->regs->tmr_ctrl,   tmr_ctrl|FIPERST|RTPE|TE|FRD);
+	qoriq_write(&regs->ctrl_regs->tmr_ctrl,   tmr_ctrl|FIPERST|RTPE|TE|FRD);
 
 	spin_unlock_irqrestore(&qoriq_ptp->lock, flags);
 
@@ -405,11 +537,12 @@ static int qoriq_ptp_probe(struct platform_device *dev)
 	return 0;
 
 no_clock:
-	iounmap(qoriq_ptp->regs);
+	iounmap(qoriq_ptp->base);
 no_ioremap:
 	release_resource(qoriq_ptp->rsrc);
 no_resource:
 	free_irq(qoriq_ptp->irq, qoriq_ptp);
+no_config:
 no_node:
 	kfree(qoriq_ptp);
 no_memory:
@@ -419,12 +552,13 @@ no_memory:
 static int qoriq_ptp_remove(struct platform_device *dev)
 {
 	struct qoriq_ptp *qoriq_ptp = platform_get_drvdata(dev);
+	struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
 
-	qoriq_write(&qoriq_ptp->regs->tmr_temask, 0);
-	qoriq_write(&qoriq_ptp->regs->tmr_ctrl,   0);
+	qoriq_write(&regs->ctrl_regs->tmr_temask, 0);
+	qoriq_write(&regs->ctrl_regs->tmr_ctrl,   0);
 
 	ptp_clock_unregister(qoriq_ptp->clock);
-	iounmap(qoriq_ptp->regs);
+	iounmap(qoriq_ptp->base);
 	release_resource(qoriq_ptp->rsrc);
 	free_irq(qoriq_ptp->irq, qoriq_ptp);
 	kfree(qoriq_ptp);
@@ -434,6 +568,7 @@ static int qoriq_ptp_remove(struct platform_device *dev)
 
 static const struct of_device_id match_table[] = {
 	{ .compatible = "fsl,etsec-ptp" },
+	{ .compatible = "fsl,fman-ptp-timer" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, match_table);
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 5dbccf5f3037..329cdd33ed62 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -180,9 +180,9 @@ config REGULATOR_BCM590XX
 	  BCM590xx PMUs. This will enable support for the software
 	  controllable LDO/Switching regulators.
 
-config REGULATOR_BD71837
+config REGULATOR_BD718XX
 	tristate "ROHM BD71837 Power Regulator"
-	depends on MFD_BD71837
+	depends on MFD_ROHM_BD718XX
 	help
 	  This driver supports voltage regulators on ROHM BD71837 PMIC.
 	  This will enable support for the software controllable buck
@@ -633,12 +633,12 @@ config REGULATOR_PCF50633
 	 on PCF50633
 
 config REGULATOR_PFUZE100
-	tristate "Freescale PFUZE100/200/3000 regulator driver"
+	tristate "Freescale PFUZE100/200/3000/3001 regulator driver"
 	depends on I2C
 	select REGMAP_I2C
 	help
 	  Say y here to support the regulators found on the Freescale
-	  PFUZE100/200/3000 PMIC.
+	  PFUZE100/200/3000/3001 PMIC.
 
 config REGULATOR_PV88060
 	tristate "Powerventure Semiconductor PV88060 regulator"
@@ -682,6 +682,15 @@ config REGULATOR_QCOM_RPM
 	  Qualcomm RPM as a module. The module will be named
 	  "qcom_rpm-regulator".
 
+config REGULATOR_QCOM_RPMH
+	tristate "Qualcomm Technologies, Inc. RPMh regulator driver"
+	depends on QCOM_RPMH || COMPILE_TEST
+	help
+	  This driver supports control of PMIC regulators via the RPMh hardware
+	  block found on Qualcomm Technologies Inc. SoCs.  RPMh regulator
+	  control allows for voting on regulator state between multiple
+	  processors within the SoC.
+
 config REGULATOR_QCOM_SMD_RPM
 	tristate "Qualcomm SMD based RPM regulator driver"
 	depends on QCOM_SMD_RPM
@@ -950,6 +959,14 @@ config REGULATOR_TWL4030
 	  This driver supports the voltage regulators provided by
 	  this family of companion chips.
 
+config REGULATOR_UNIPHIER
+	tristate "UniPhier regulator driver"
+	depends on ARCH_UNIPHIER || COMPILE_TEST
+	depends on OF && MFD_SYSCON
+	default ARCH_UNIPHIER
+	help
+	  Support for regulators implemented on Socionext UniPhier SoCs.
+
 config REGULATOR_VCTRL
 	tristate "Voltage controlled regulators"
 	depends on OF
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index bd818ceb7c72..801d9a34a203 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -27,7 +27,7 @@ obj-$(CONFIG_REGULATOR_AS3711) += as3711-regulator.o
 obj-$(CONFIG_REGULATOR_AS3722) += as3722-regulator.o
 obj-$(CONFIG_REGULATOR_AXP20X) += axp20x-regulator.o
 obj-$(CONFIG_REGULATOR_BCM590XX) += bcm590xx-regulator.o
-obj-$(CONFIG_REGULATOR_BD71837) += bd71837-regulator.o
+obj-$(CONFIG_REGULATOR_BD718XX) += bd71837-regulator.o
 obj-$(CONFIG_REGULATOR_BD9571MWV) += bd9571mwv-regulator.o
 obj-$(CONFIG_REGULATOR_DA903X)	+= da903x.o
 obj-$(CONFIG_REGULATOR_DA9052)	+= da9052-regulator.o
@@ -78,6 +78,7 @@ obj-$(CONFIG_REGULATOR_MT6323)	+= mt6323-regulator.o
 obj-$(CONFIG_REGULATOR_MT6380)	+= mt6380-regulator.o
 obj-$(CONFIG_REGULATOR_MT6397)	+= mt6397-regulator.o
 obj-$(CONFIG_REGULATOR_QCOM_RPM) += qcom_rpm-regulator.o
+obj-$(CONFIG_REGULATOR_QCOM_RPMH) += qcom-rpmh-regulator.o
 obj-$(CONFIG_REGULATOR_QCOM_SMD_RPM) += qcom_smd-regulator.o
 obj-$(CONFIG_REGULATOR_QCOM_SPMI) += qcom_spmi-regulator.o
 obj-$(CONFIG_REGULATOR_PALMAS) += palmas-regulator.o
@@ -118,6 +119,7 @@ obj-$(CONFIG_REGULATOR_TPS65912) += tps65912-regulator.o
 obj-$(CONFIG_REGULATOR_TPS80031) += tps80031-regulator.o
 obj-$(CONFIG_REGULATOR_TPS65132) += tps65132-regulator.o
 obj-$(CONFIG_REGULATOR_TWL4030) += twl-regulator.o twl6030-regulator.o
+obj-$(CONFIG_REGULATOR_UNIPHIER) += uniphier-regulator.o
 obj-$(CONFIG_REGULATOR_VCTRL) += vctrl-regulator.o
 obj-$(CONFIG_REGULATOR_VEXPRESS) += vexpress-regulator.o
 obj-$(CONFIG_REGULATOR_WM831X) += wm831x-dcdc.o
diff --git a/drivers/regulator/arizona-ldo1.c b/drivers/regulator/arizona-ldo1.c
index f6d6a4ad9e8a..e976d073f28d 100644
--- a/drivers/regulator/arizona-ldo1.c
+++ b/drivers/regulator/arizona-ldo1.c
@@ -36,6 +36,8 @@ struct arizona_ldo1 {
 
 	struct regulator_consumer_supply supply;
 	struct regulator_init_data init_data;
+
+	struct gpio_desc *ena_gpiod;
 };
 
 static int arizona_ldo1_hc_list_voltage(struct regulator_dev *rdev,
@@ -253,12 +255,17 @@ static int arizona_ldo1_common_init(struct platform_device *pdev,
 		}
 	}
 
-	/* We assume that high output = regulator off */
-	config.ena_gpiod = devm_gpiod_get_optional(&pdev->dev, "wlf,ldoena",
-						   GPIOD_OUT_HIGH);
+	/* We assume that high output = regulator off
+	 * Don't use devm, since we need to get against the parent device
+	 * so clean up would happen at the wrong time
+	 */
+	config.ena_gpiod = gpiod_get_optional(parent_dev, "wlf,ldoena",
+					      GPIOD_OUT_LOW);
 	if (IS_ERR(config.ena_gpiod))
 		return PTR_ERR(config.ena_gpiod);
 
+	ldo1->ena_gpiod = config.ena_gpiod;
+
 	if (pdata->init_data)
 		config.init_data = pdata->init_data;
 	else
@@ -276,6 +283,9 @@ static int arizona_ldo1_common_init(struct platform_device *pdev,
 	of_node_put(config.of_node);
 
 	if (IS_ERR(ldo1->regulator)) {
+		if (config.ena_gpiod)
+			gpiod_put(config.ena_gpiod);
+
 		ret = PTR_ERR(ldo1->regulator);
 		dev_err(&pdev->dev, "Failed to register LDO1 supply: %d\n",
 			ret);
@@ -334,8 +344,19 @@ static int arizona_ldo1_probe(struct platform_device *pdev)
 	return ret;
 }
 
+static int arizona_ldo1_remove(struct platform_device *pdev)
+{
+	struct arizona_ldo1 *ldo1 = platform_get_drvdata(pdev);
+
+	if (ldo1->ena_gpiod)
+		gpiod_put(ldo1->ena_gpiod);
+
+	return 0;
+}
+
 static struct platform_driver arizona_ldo1_driver = {
 	.probe = arizona_ldo1_probe,
+	.remove = arizona_ldo1_remove,
 	.driver		= {
 		.name	= "arizona-ldo1",
 	},
diff --git a/drivers/regulator/bd71837-regulator.c b/drivers/regulator/bd71837-regulator.c
index 6eae4d0432a2..0f8ac8dec3e1 100644
--- a/drivers/regulator/bd71837-regulator.c
+++ b/drivers/regulator/bd71837-regulator.c
@@ -2,19 +2,18 @@
 // Copyright (C) 2018 ROHM Semiconductors
 // bd71837-regulator.c ROHM BD71837MWV regulator driver
 
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
+#include <linux/delay.h>
 #include <linux/err.h>
+#include <linux/gpio.h>
 #include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/mfd/rohm-bd718x7.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/driver.h>
 #include <linux/regulator/machine.h>
-#include <linux/delay.h>
-#include <linux/slab.h>
-#include <linux/gpio.h>
-#include <linux/mfd/bd71837.h>
 #include <linux/regulator/of_regulator.h>
+#include <linux/slab.h>
 
 struct bd71837_pmic {
 	struct regulator_desc descs[BD71837_REGULATOR_CNT];
@@ -39,7 +38,7 @@ static int bd71837_buck1234_set_ramp_delay(struct regulator_dev *rdev,
 	int id = rdev->desc->id;
 	unsigned int ramp_value = BUCK_RAMPRATE_10P00MV;
 
-	dev_dbg(&(pmic->pdev->dev), "Buck[%d] Set Ramp = %d\n", id + 1,
+	dev_dbg(&pmic->pdev->dev, "Buck[%d] Set Ramp = %d\n", id + 1,
 		ramp_delay);
 	switch (ramp_delay) {
 	case 1 ... 1250:
@@ -73,14 +72,10 @@ static int bd71837_buck1234_set_ramp_delay(struct regulator_dev *rdev,
 static int bd71837_set_voltage_sel_restricted(struct regulator_dev *rdev,
 						    unsigned int sel)
 {
-	int ret;
-
-	ret = regulator_is_enabled_regmap(rdev);
-	if (!ret)
-		ret = regulator_set_voltage_sel_regmap(rdev, sel);
-	else if (ret == 1)
-		ret = -EBUSY;
-	return ret;
+	if (regulator_is_enabled_regmap(rdev))
+		return -EBUSY;
+
+	return regulator_set_voltage_sel_regmap(rdev, sel);
 }
 
 static struct regulator_ops bd71837_ldo_regulator_ops = {
@@ -195,7 +190,7 @@ static const struct regulator_linear_range bd71837_ldo1_voltage_ranges[] = {
  * LDO2
  * 0.8 or 0.9V
  */
-const unsigned int ldo_2_volts[] = {
+static const unsigned int ldo_2_volts[] = {
 	900000, 800000
 };
 
@@ -495,7 +490,6 @@ struct reg_init {
 static int bd71837_probe(struct platform_device *pdev)
 {
 	struct bd71837_pmic *pmic;
-	struct bd71837_board *pdata;
 	struct regulator_config config = { 0 };
 	struct reg_init pmic_regulator_inits[] = {
 		{
@@ -548,8 +542,7 @@ static int bd71837_probe(struct platform_device *pdev)
 
 	int i, err;
 
-	pmic = devm_kzalloc(&pdev->dev, sizeof(struct bd71837_pmic),
-			    GFP_KERNEL);
+	pmic = devm_kzalloc(&pdev->dev, sizeof(*pmic), GFP_KERNEL);
 	if (!pmic)
 		return -ENOMEM;
 
@@ -564,7 +557,6 @@ static int bd71837_probe(struct platform_device *pdev)
 		goto err;
 	}
 	platform_set_drvdata(pdev, pmic);
-	pdata = dev_get_platdata(pmic->mfd->dev);
 
 	/* Register LOCK release */
 	err = regmap_update_bits(pmic->mfd->regmap, BD71837_REG_REGLOCK,
@@ -573,8 +565,8 @@ static int bd71837_probe(struct platform_device *pdev)
 		dev_err(&pmic->pdev->dev, "Failed to unlock PMIC (%d)\n", err);
 		goto err;
 	} else {
-		dev_dbg(&pmic->pdev->dev, "%s: Unlocked lock register 0x%x\n",
-			__func__, BD71837_REG_REGLOCK);
+		dev_dbg(&pmic->pdev->dev, "Unlocked lock register 0x%x\n",
+			BD71837_REG_REGLOCK);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(pmic_regulator_inits); i++) {
@@ -584,9 +576,6 @@ static int bd71837_probe(struct platform_device *pdev)
 
 		desc = &pmic->descs[i];
 
-		if (pdata)
-			config.init_data = pdata->init_data[i];
-
 		config.dev = pdev->dev.parent;
 		config.driver_data = pmic;
 		config.regmap = pmic->mfd->regmap;
@@ -619,8 +608,6 @@ static int bd71837_probe(struct platform_device *pdev)
 		pmic->rdev[i] = rdev;
 	}
 
-	return 0;
-
 err:
 	return err;
 }
@@ -628,7 +615,6 @@ err:
 static struct platform_driver bd71837_regulator = {
 	.driver = {
 		.name = "bd71837-pmic",
-		.owner = THIS_MODULE,
 	},
 	.probe = bd71837_probe,
 };
diff --git a/drivers/regulator/bd9571mwv-regulator.c b/drivers/regulator/bd9571mwv-regulator.c
index be574eb444eb..274c5ed7cd73 100644
--- a/drivers/regulator/bd9571mwv-regulator.c
+++ b/drivers/regulator/bd9571mwv-regulator.c
@@ -30,6 +30,7 @@ struct bd9571mwv_reg {
 	/* DDR Backup Power */
 	u8 bkup_mode_cnt_keepon;	/* from "rohm,ddr-backup-power" */
 	u8 bkup_mode_cnt_saved;
+	bool bkup_mode_enabled;
 
 	/* Power switch type */
 	bool rstbmode_level;
@@ -171,13 +172,60 @@ static int bd9571mwv_bkup_mode_write(struct bd9571mwv *bd, unsigned int mode)
 	return 0;
 }
 
+static ssize_t backup_mode_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct bd9571mwv_reg *bdreg = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%s\n", bdreg->bkup_mode_enabled ? "on" : "off");
+}
+
+static ssize_t backup_mode_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
+{
+	struct bd9571mwv_reg *bdreg = dev_get_drvdata(dev);
+	unsigned int mode;
+	int ret;
+
+	if (!count)
+		return 0;
+
+	ret = kstrtobool(buf, &bdreg->bkup_mode_enabled);
+	if (ret)
+		return ret;
+
+	if (!bdreg->rstbmode_level)
+		return count;
+
+	/*
+	 * Configure DDR Backup Mode, to change the role of the accessory power
+	 * switch from a power switch to a wake-up switch, or vice versa
+	 */
+	ret = bd9571mwv_bkup_mode_read(bdreg->bd, &mode);
+	if (ret)
+		return ret;
+
+	mode &= ~BD9571MWV_BKUP_MODE_CNT_KEEPON_MASK;
+	if (bdreg->bkup_mode_enabled)
+		mode |= bdreg->bkup_mode_cnt_keepon;
+
+	ret = bd9571mwv_bkup_mode_write(bdreg->bd, mode);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(backup_mode);
+
 static int bd9571mwv_suspend(struct device *dev)
 {
 	struct bd9571mwv_reg *bdreg = dev_get_drvdata(dev);
 	unsigned int mode;
 	int ret;
 
-	if (!device_may_wakeup(dev))
+	if (!bdreg->bkup_mode_enabled)
 		return 0;
 
 	/* Save DDR Backup Mode */
@@ -204,7 +252,7 @@ static int bd9571mwv_resume(struct device *dev)
 {
 	struct bd9571mwv_reg *bdreg = dev_get_drvdata(dev);
 
-	if (!device_may_wakeup(dev))
+	if (!bdreg->bkup_mode_enabled)
 		return 0;
 
 	/* Restore DDR Backup Mode */
@@ -215,9 +263,15 @@ static const struct dev_pm_ops bd9571mwv_pm  = {
 	SET_SYSTEM_SLEEP_PM_OPS(bd9571mwv_suspend, bd9571mwv_resume)
 };
 
+static int bd9571mwv_regulator_remove(struct platform_device *pdev)
+{
+	device_remove_file(&pdev->dev, &dev_attr_backup_mode);
+	return 0;
+}
 #define DEV_PM_OPS	&bd9571mwv_pm
 #else
 #define DEV_PM_OPS	NULL
+#define bd9571mwv_regulator_remove	NULL
 #endif /* CONFIG_PM_SLEEP */
 
 static int bd9571mwv_regulator_probe(struct platform_device *pdev)
@@ -270,14 +324,21 @@ static int bd9571mwv_regulator_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+#ifdef CONFIG_PM_SLEEP
 	if (bdreg->bkup_mode_cnt_keepon) {
-		device_set_wakeup_capable(&pdev->dev, true);
+		int ret;
+
 		/*
-		 * Wakeup is enabled by default in pulse mode, but needs
+		 * Backup mode is enabled by default in pulse mode, but needs
 		 * explicit user setup in level mode.
 		 */
-		device_set_wakeup_enable(&pdev->dev, bdreg->rstbmode_pulse);
+		bdreg->bkup_mode_enabled = bdreg->rstbmode_pulse;
+
+		ret = device_create_file(&pdev->dev, &dev_attr_backup_mode);
+		if (ret)
+			return ret;
 	}
+#endif /* CONFIG_PM_SLEEP */
 
 	return 0;
 }
@@ -294,6 +355,7 @@ static struct platform_driver bd9571mwv_regulator_driver = {
 		.pm = DEV_PM_OPS,
 	},
 	.probe = bd9571mwv_regulator_probe,
+	.remove = bd9571mwv_regulator_remove,
 	.id_table = bd9571mwv_regulator_id_table,
 };
 module_platform_driver(bd9571mwv_regulator_driver);
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 6ed568b96c0e..bb1324f93143 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1740,6 +1740,8 @@ struct regulator *_regulator_get(struct device *dev, const char *id,
 			rdev->use_count = 0;
 	}
 
+	device_link_add(dev, &rdev->dev, DL_FLAG_STATELESS);
+
 	return regulator;
 }
 
@@ -1829,9 +1831,21 @@ static void _regulator_put(struct regulator *regulator)
 
 	debugfs_remove_recursive(regulator->debugfs);
 
-	/* remove any sysfs entries */
-	if (regulator->dev)
+	if (regulator->dev) {
+		int count = 0;
+		struct regulator *r;
+
+		list_for_each_entry(r, &rdev->consumer_list, list)
+			if (r->dev == regulator->dev)
+				count++;
+
+		if (count == 1)
+			device_link_remove(regulator->dev, &rdev->dev);
+
+		/* remove any sysfs entries */
 		sysfs_remove_link(&rdev->dev.kobj, regulator->supply_name);
+	}
+
 	regulator_lock(rdev);
 	list_del(&regulator->list);
 
@@ -4441,7 +4455,7 @@ void regulator_unregister(struct regulator_dev *rdev)
 EXPORT_SYMBOL_GPL(regulator_unregister);
 
 #ifdef CONFIG_SUSPEND
-static int _regulator_suspend_late(struct device *dev, void *data)
+static int _regulator_suspend(struct device *dev, void *data)
 {
 	struct regulator_dev *rdev = dev_to_rdev(dev);
 	suspend_state_t *state = data;
@@ -4455,20 +4469,20 @@ static int _regulator_suspend_late(struct device *dev, void *data)
 }
 
 /**
- * regulator_suspend_late - prepare regulators for system wide suspend
+ * regulator_suspend - prepare regulators for system wide suspend
  * @state: system suspend state
  *
  * Configure each regulator with it's suspend operating parameters for state.
  */
-static int regulator_suspend_late(struct device *dev)
+static int regulator_suspend(struct device *dev)
 {
 	suspend_state_t state = pm_suspend_target_state;
 
 	return class_for_each_device(&regulator_class, NULL, &state,
-				     _regulator_suspend_late);
+				     _regulator_suspend);
 }
 
-static int _regulator_resume_early(struct device *dev, void *data)
+static int _regulator_resume(struct device *dev, void *data)
 {
 	int ret = 0;
 	struct regulator_dev *rdev = dev_to_rdev(dev);
@@ -4481,35 +4495,35 @@ static int _regulator_resume_early(struct device *dev, void *data)
 
 	regulator_lock(rdev);
 
-	if (rdev->desc->ops->resume_early &&
+	if (rdev->desc->ops->resume &&
 	    (rstate->enabled == ENABLE_IN_SUSPEND ||
 	     rstate->enabled == DISABLE_IN_SUSPEND))
-		ret = rdev->desc->ops->resume_early(rdev);
+		ret = rdev->desc->ops->resume(rdev);
 
 	regulator_unlock(rdev);
 
 	return ret;
 }
 
-static int regulator_resume_early(struct device *dev)
+static int regulator_resume(struct device *dev)
 {
 	suspend_state_t state = pm_suspend_target_state;
 
 	return class_for_each_device(&regulator_class, NULL, &state,
-				     _regulator_resume_early);
+				     _regulator_resume);
 }
 
 #else /* !CONFIG_SUSPEND */
 
-#define regulator_suspend_late	NULL
-#define regulator_resume_early	NULL
+#define regulator_suspend	NULL
+#define regulator_resume	NULL
 
 #endif /* !CONFIG_SUSPEND */
 
 #ifdef CONFIG_PM
 static const struct dev_pm_ops __maybe_unused regulator_pm_ops = {
-	.suspend_late	= regulator_suspend_late,
-	.resume_early	= regulator_resume_early,
+	.suspend	= regulator_suspend,
+	.resume		= regulator_resume,
 };
 #endif
 
diff --git a/drivers/regulator/cpcap-regulator.c b/drivers/regulator/cpcap-regulator.c
index bd910fe123d9..2131457937b7 100644
--- a/drivers/regulator/cpcap-regulator.c
+++ b/drivers/regulator/cpcap-regulator.c
@@ -271,6 +271,29 @@ static struct regulator_ops cpcap_regulator_ops = {
 };
 
 static const unsigned int unknown_val_tbl[] = { 0, };
+static const unsigned int sw2_sw4_val_tbl[] = { 612500, 625000, 637500,
+						650000, 662500, 675000,
+						687500, 700000, 712500,
+						725000, 737500, 750000,
+						762500, 775000, 787500,
+						800000, 812500, 825000,
+						837500, 850000, 862500,
+						875000, 887500, 900000,
+						912500, 925000, 937500,
+						950000, 962500, 975000,
+						987500, 1000000, 1012500,
+						1025000, 1037500, 1050000,
+						1062500, 1075000, 1087500,
+						1100000, 1112500, 1125000,
+						1137500, 1150000, 1162500,
+						1175000, 1187500, 1200000,
+						1212500, 1225000, 1237500,
+						1250000, 1262500, 1275000,
+						1287500, 1300000, 1312500,
+						1325000, 1337500, 1350000,
+						1362500, 1375000, 1387500,
+						1400000, 1412500, 1425000,
+						1437500, 1450000, 1462500, };
 static const unsigned int sw5_val_tbl[] = { 0, 5050000, };
 static const unsigned int vcam_val_tbl[] = { 2600000, 2700000, 2800000,
 					     2900000, };
@@ -389,6 +412,82 @@ static struct cpcap_regulator omap4_regulators[] = {
 	{ /* sentinel */ },
 };
 
+static struct cpcap_regulator xoom_regulators[] = {
+	CPCAP_REG(SW1, CPCAP_REG_S1C1, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW1_SEL, unknown_val_tbl,
+		  0, 0, 0, 0, 0, 0),
+	CPCAP_REG(SW2, CPCAP_REG_S2C1, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW2_SEL, sw2_sw4_val_tbl,
+		  0xf00, 0x7f, 0, 0x800, 0, 120),
+	CPCAP_REG(SW3, CPCAP_REG_S3C, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW3_SEL, unknown_val_tbl,
+		  0, 0, 0, 0, 0, 0),
+	CPCAP_REG(SW4, CPCAP_REG_S4C1, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW4_SEL, sw2_sw4_val_tbl,
+		  0xf00, 0x7f, 0, 0x900, 0, 100),
+	CPCAP_REG(SW5, CPCAP_REG_S5C, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW5_SEL, sw5_val_tbl,
+		  0x2a, 0, 0, 0x22, 0, 0),
+	CPCAP_REG(SW6, CPCAP_REG_S6C, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW6_SEL, unknown_val_tbl,
+		  0, 0, 0, 0, 0, 0),
+	CPCAP_REG(VCAM, CPCAP_REG_VCAMC, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_VCAM_SEL, vcam_val_tbl,
+		  0x87, 0x30, 4, 0x7, 0, 420),
+	CPCAP_REG(VCSI, CPCAP_REG_VCSIC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VCSI_SEL, vcsi_val_tbl,
+		  0x47, 0x10, 4, 0x7, 0, 350),
+	CPCAP_REG(VDAC, CPCAP_REG_VDACC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VDAC_SEL, vdac_val_tbl,
+		  0x87, 0x30, 4, 0x3, 0, 420),
+	CPCAP_REG(VDIG, CPCAP_REG_VDIGC, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_VDIG_SEL, vdig_val_tbl,
+		  0x87, 0x30, 4, 0x5, 0, 420),
+	CPCAP_REG(VFUSE, CPCAP_REG_VFUSEC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VFUSE_SEL, vfuse_val_tbl,
+		  0x80, 0xf, 0, 0x80, 0, 420),
+	CPCAP_REG(VHVIO, CPCAP_REG_VHVIOC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VHVIO_SEL, vhvio_val_tbl,
+		  0x17, 0, 0, 0x2, 0, 0),
+	CPCAP_REG(VSDIO, CPCAP_REG_VSDIOC, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_VSDIO_SEL, vsdio_val_tbl,
+		  0x87, 0x38, 3, 0x2, 0, 420),
+	CPCAP_REG(VPLL, CPCAP_REG_VPLLC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VPLL_SEL, vpll_val_tbl,
+		  0x43, 0x18, 3, 0x1, 0, 420),
+	CPCAP_REG(VRF1, CPCAP_REG_VRF1C, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VRF1_SEL, vrf1_val_tbl,
+		  0xac, 0x2, 1, 0xc, 0, 10),
+	CPCAP_REG(VRF2, CPCAP_REG_VRF2C, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VRF2_SEL, vrf2_val_tbl,
+		  0x23, 0x8, 3, 0x3, 0, 10),
+	CPCAP_REG(VRFREF, CPCAP_REG_VRFREFC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VRFREF_SEL, vrfref_val_tbl,
+		  0x23, 0x8, 3, 0x3, 0, 420),
+	CPCAP_REG(VWLAN1, CPCAP_REG_VWLAN1C, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VWLAN1_SEL, vwlan1_val_tbl,
+		  0x47, 0x10, 4, 0x5, 0, 420),
+	CPCAP_REG(VWLAN2, CPCAP_REG_VWLAN2C, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VWLAN2_SEL, vwlan2_val_tbl,
+		  0x20c, 0xc0, 6, 0x8, 0, 420),
+	CPCAP_REG(VSIM, CPCAP_REG_VSIMC, CPCAP_REG_ASSIGN3,
+		  0xffff, vsim_val_tbl,
+		  0x23, 0x8, 3, 0x3, 0, 420),
+	CPCAP_REG(VSIMCARD, CPCAP_REG_VSIMC, CPCAP_REG_ASSIGN3,
+		  0xffff, vsimcard_val_tbl,
+		  0x1e80, 0x8, 3, 0x1e00, 0, 420),
+	CPCAP_REG(VVIB, CPCAP_REG_VVIBC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VVIB_SEL, vvib_val_tbl,
+		  0x1, 0xc, 2, 0, 0x1, 500),
+	CPCAP_REG(VUSB, CPCAP_REG_VUSBC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VUSB_SEL, vusb_val_tbl,
+		  0x11c, 0x40, 6, 0xc, 0, 0),
+	CPCAP_REG(VAUDIO, CPCAP_REG_VAUDIOC, CPCAP_REG_ASSIGN4,
+		  CPCAP_BIT_VAUDIO_SEL, vaudio_val_tbl,
+		  0x16, 0x1, 0, 0x4, 0, 0),
+	{ /* sentinel */ },
+};
+
 static const struct of_device_id cpcap_regulator_id_table[] = {
 	{
 		.compatible = "motorola,cpcap-regulator",
@@ -397,6 +496,10 @@ static const struct of_device_id cpcap_regulator_id_table[] = {
 		.compatible = "motorola,mapphone-cpcap-regulator",
 		.data = omap4_regulators,
 	},
+	{
+		.compatible = "motorola,xoom-cpcap-regulator",
+		.data = xoom_regulators,
+	},
 	{},
 };
 MODULE_DEVICE_TABLE(of, cpcap_regulator_id_table);
diff --git a/drivers/regulator/max14577-regulator.c b/drivers/regulator/max14577-regulator.c
index 0db288ce319c..bc7f4751bf9c 100644
--- a/drivers/regulator/max14577-regulator.c
+++ b/drivers/regulator/max14577-regulator.c
@@ -1,19 +1,9 @@
-/*
- * max14577.c - Regulator driver for the Maxim 14577/77836
- *
- * Copyright (C) 2013,2014 Samsung Electronics
- * Krzysztof Kozlowski <krzk@kernel.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// max14577.c - Regulator driver for the Maxim 14577/77836
+//
+// Copyright (C) 2013,2014 Samsung Electronics
+// Krzysztof Kozlowski <krzk@kernel.org>
 
 #include <linux/module.h>
 #include <linux/platform_device.h>
diff --git a/drivers/regulator/max77686-regulator.c b/drivers/regulator/max77686-regulator.c
index c301f3733475..bee060937f56 100644
--- a/drivers/regulator/max77686-regulator.c
+++ b/drivers/regulator/max77686-regulator.c
@@ -1,26 +1,12 @@
-/*
- * max77686.c - Regulator driver for the Maxim 77686
- *
- * Copyright (C) 2012 Samsung Electronics
- * Chiwoong Byun <woong.byun@samsung.com>
- * Jonghwa Lee <jonghwa3.lee@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- * This driver is based on max8997.c
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// max77686.c - Regulator driver for the Maxim 77686
+//
+// Copyright (C) 2012 Samsung Electronics
+// Chiwoong Byun <woong.byun@samsung.com>
+// Jonghwa Lee <jonghwa3.lee@samsung.com>
+//
+// This driver is based on max8997.c
 
 #include <linux/kernel.h>
 #include <linux/bug.h>
diff --git a/drivers/regulator/max77693-regulator.c b/drivers/regulator/max77693-regulator.c
index e7000e777292..077ecbbfdf76 100644
--- a/drivers/regulator/max77693-regulator.c
+++ b/drivers/regulator/max77693-regulator.c
@@ -1,26 +1,12 @@
-/*
- * max77693.c - Regulator driver for the Maxim 77693 and 77843
- *
- * Copyright (C) 2013-2015 Samsung Electronics
- * Jonghwa Lee <jonghwa3.lee@samsung.com>
- * Krzysztof Kozlowski <krzk@kernel.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- * This driver is based on max77686.c
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// max77693.c - Regulator driver for the Maxim 77693 and 77843
+//
+// Copyright (C) 2013-2015 Samsung Electronics
+// Jonghwa Lee <jonghwa3.lee@samsung.com>
+// Krzysztof Kozlowski <krzk@kernel.org>
+//
+// This driver is based on max77686.c
 
 #include <linux/err.h>
 #include <linux/slab.h>
diff --git a/drivers/regulator/max77802-regulator.c b/drivers/regulator/max77802-regulator.c
index b6261903818c..c30cf5c9f2de 100644
--- a/drivers/regulator/max77802-regulator.c
+++ b/drivers/regulator/max77802-regulator.c
@@ -1,25 +1,15 @@
-/*
- * max77802.c - Regulator driver for the Maxim 77802
- *
- * Copyright (C) 2013-2014 Google, Inc
- * Simon Glass <sjg@chromium.org>
- *
- * Copyright (C) 2012 Samsung Electronics
- * Chiwoong Byun <woong.byun@samsung.com>
- * Jonghwa Lee <jonghwa3.lee@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * This driver is based on max8997.c
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// max77802.c - Regulator driver for the Maxim 77802
+//
+// Copyright (C) 2013-2014 Google, Inc
+// Simon Glass <sjg@chromium.org>
+//
+// Copyright (C) 2012 Samsung Electronics
+// Chiwoong Byun <woong.byun@samsung.com>
+// Jonghwa Lee <jonghwa3.lee@samsung.com>
+//
+// This driver is based on max8997.c
 
 #include <linux/kernel.h>
 #include <linux/bug.h>
diff --git a/drivers/regulator/max8997-regulator.c b/drivers/regulator/max8997-regulator.c
index a8ea30ee18a6..ad0c806b0737 100644
--- a/drivers/regulator/max8997-regulator.c
+++ b/drivers/regulator/max8997-regulator.c
@@ -1,25 +1,11 @@
-/*
- * max8997.c - Regulator driver for the Maxim 8997/8966
- *
- * Copyright (C) 2011 Samsung Electronics
- * MyungJoo Ham <myungjoo.ham@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- * This driver is based on max8998.c
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// max8997.c - Regulator driver for the Maxim 8997/8966
+//
+// Copyright (C) 2011 Samsung Electronics
+// MyungJoo Ham <myungjoo.ham@samsung.com>
+//
+// This driver is based on max8998.c
 
 #include <linux/bug.h>
 #include <linux/err.h>
@@ -165,8 +151,7 @@ static int max8997_list_voltage(struct regulator_dev *rdev,
 	int rid = rdev_get_id(rdev);
 	int val;
 
-	if (rid >= ARRAY_SIZE(reg_voltage_map) ||
-			rid < 0)
+	if (rid < 0 || rid >= ARRAY_SIZE(reg_voltage_map))
 		return -EINVAL;
 
 	desc = reg_voltage_map[rid];
diff --git a/drivers/regulator/max8998.c b/drivers/regulator/max8998.c
index 6b9f262ebbb0..271bb736f3f5 100644
--- a/drivers/regulator/max8998.c
+++ b/drivers/regulator/max8998.c
@@ -1,24 +1,10 @@
-/*
- * max8998.c - Voltage regulator driver for the Maxim 8998
- *
- *  Copyright (C) 2009-2010 Samsung Electronics
- *  Kyungmin Park <kyungmin.park@samsung.com>
- *  Marek Szyprowski <m.szyprowski@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// max8998.c - Voltage regulator driver for the Maxim 8998
+//
+//  Copyright (C) 2009-2010 Samsung Electronics
+//  Kyungmin Park <kyungmin.park@samsung.com>
+//  Marek Szyprowski <m.szyprowski@samsung.com>
 
 #include <linux/module.h>
 #include <linux/init.h>
diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index 8d9dbcc775ea..31c3a236120a 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -17,6 +17,8 @@
 #include <linux/slab.h>
 #include <linux/regmap.h>
 
+#define PFUZE_FLAG_DISABLE_SW	BIT(1)
+
 #define PFUZE_NUMREGS		128
 #define PFUZE100_VOL_OFFSET	0
 #define PFUZE100_STANDBY_OFFSET	1
@@ -44,16 +46,18 @@
 #define PFUZE100_VGEN5VOL	0x70
 #define PFUZE100_VGEN6VOL	0x71
 
-enum chips { PFUZE100, PFUZE200, PFUZE3000 = 3 };
+enum chips { PFUZE100, PFUZE200, PFUZE3000 = 3, PFUZE3001 = 0x31, };
 
 struct pfuze_regulator {
 	struct regulator_desc desc;
 	unsigned char stby_reg;
 	unsigned char stby_mask;
+	bool sw_reg;
 };
 
 struct pfuze_chip {
 	int	chip_id;
+	int     flags;
 	struct regmap *regmap;
 	struct device *dev;
 	struct pfuze_regulator regulator_descs[PFUZE100_MAX_REGULATOR];
@@ -92,6 +96,7 @@ static const struct i2c_device_id pfuze_device_id[] = {
 	{.name = "pfuze100", .driver_data = PFUZE100},
 	{.name = "pfuze200", .driver_data = PFUZE200},
 	{.name = "pfuze3000", .driver_data = PFUZE3000},
+	{.name = "pfuze3001", .driver_data = PFUZE3001},
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, pfuze_device_id);
@@ -100,6 +105,7 @@ static const struct of_device_id pfuze_dt_ids[] = {
 	{ .compatible = "fsl,pfuze100", .data = (void *)PFUZE100},
 	{ .compatible = "fsl,pfuze200", .data = (void *)PFUZE200},
 	{ .compatible = "fsl,pfuze3000", .data = (void *)PFUZE3000},
+	{ .compatible = "fsl,pfuze3001", .data = (void *)PFUZE3001},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, pfuze_dt_ids);
@@ -108,10 +114,28 @@ static int pfuze100_set_ramp_delay(struct regulator_dev *rdev, int ramp_delay)
 {
 	struct pfuze_chip *pfuze100 = rdev_get_drvdata(rdev);
 	int id = rdev_get_id(rdev);
+	bool reg_has_ramp_delay;
 	unsigned int ramp_bits;
 	int ret;
 
-	if (id < PFUZE100_SWBST) {
+	switch (pfuze100->chip_id) {
+	case PFUZE3001:
+		/* no dynamic voltage scaling for PF3001 */
+		reg_has_ramp_delay = false;
+		break;
+	case PFUZE3000:
+		reg_has_ramp_delay = (id < PFUZE3000_SWBST);
+		break;
+	case PFUZE200:
+		reg_has_ramp_delay = (id < PFUZE200_SWBST);
+		break;
+	case PFUZE100:
+	default:
+		reg_has_ramp_delay = (id < PFUZE100_SWBST);
+		break;
+	}
+
+	if (reg_has_ramp_delay) {
 		ramp_delay = 12500 / ramp_delay;
 		ramp_bits = (ramp_delay >> 1) - (ramp_delay >> 3);
 		ret = regmap_update_bits(pfuze100->regmap,
@@ -119,8 +143,9 @@ static int pfuze100_set_ramp_delay(struct regulator_dev *rdev, int ramp_delay)
 					 0xc0, ramp_bits << 6);
 		if (ret < 0)
 			dev_err(pfuze100->dev, "ramp failed, err %d\n", ret);
-	} else
+	} else {
 		ret = -EACCES;
+	}
 
 	return ret;
 }
@@ -142,6 +167,14 @@ static const struct regulator_ops pfuze100_fixed_regulator_ops = {
 };
 
 static const struct regulator_ops pfuze100_sw_regulator_ops = {
+	.list_voltage = regulator_list_voltage_linear,
+	.set_voltage_sel = regulator_set_voltage_sel_regmap,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+	.set_voltage_time_sel = regulator_set_voltage_time_sel,
+	.set_ramp_delay = pfuze100_set_ramp_delay,
+};
+
+static const struct regulator_ops pfuze100_sw_disable_regulator_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
 	.is_enabled = regulator_is_enabled_regmap,
@@ -192,13 +225,11 @@ static const struct regulator_ops pfuze100_swb_regulator_ops = {
 			.vsel_reg = (base) + PFUZE100_VOL_OFFSET,	\
 			.vsel_mask = 0x3f,	\
 			.enable_reg = (base) + PFUZE100_MODE_OFFSET,	\
-			.enable_val = 0xc,	\
-			.disable_val = 0x0,	\
 			.enable_mask = 0xf,	\
-			.enable_time = 500,	\
 		},	\
 		.stby_reg = (base) + PFUZE100_STANDBY_OFFSET,	\
 		.stby_mask = 0x3f,	\
+		.sw_reg = true,		\
 	}
 
 #define PFUZE100_SWB_REG(_chip, _name, base, mask, voltages)	\
@@ -361,6 +392,19 @@ static struct pfuze_regulator pfuze3000_regulators[] = {
 	PFUZE100_VGEN_REG(PFUZE3000, VLDO4, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000),
 };
 
+static struct pfuze_regulator pfuze3001_regulators[] = {
+	PFUZE100_SWB_REG(PFUZE3001, SW1, PFUZE100_SW1ABVOL, 0x1f, pfuze3000_sw1a),
+	PFUZE100_SWB_REG(PFUZE3001, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo),
+	PFUZE3000_SW3_REG(PFUZE3001, SW3, PFUZE100_SW3AVOL, 900000, 1650000, 50000),
+	PFUZE100_SWB_REG(PFUZE3001, VSNVS, PFUZE100_VSNVSVOL, 0x7, pfuze100_vsnvs),
+	PFUZE100_VGEN_REG(PFUZE3001, VLDO1, PFUZE100_VGEN1VOL, 1800000, 3300000, 100000),
+	PFUZE100_VGEN_REG(PFUZE3001, VLDO2, PFUZE100_VGEN2VOL, 800000, 1550000, 50000),
+	PFUZE3000_VCC_REG(PFUZE3001, VCCSD, PFUZE100_VGEN3VOL, 2850000, 3300000, 150000),
+	PFUZE3000_VCC_REG(PFUZE3001, V33, PFUZE100_VGEN4VOL, 2850000, 3300000, 150000),
+	PFUZE100_VGEN_REG(PFUZE3001, VLDO3, PFUZE100_VGEN5VOL, 1800000, 3300000, 100000),
+	PFUZE100_VGEN_REG(PFUZE3001, VLDO4, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000),
+};
+
 #ifdef CONFIG_OF
 /* PFUZE100 */
 static struct of_regulator_match pfuze100_matches[] = {
@@ -418,6 +462,21 @@ static struct of_regulator_match pfuze3000_matches[] = {
 	{ .name = "vldo4",	},
 };
 
+/* PFUZE3001 */
+static struct of_regulator_match pfuze3001_matches[] = {
+
+	{ .name = "sw1",	},
+	{ .name = "sw2",	},
+	{ .name = "sw3",	},
+	{ .name = "vsnvs",	},
+	{ .name = "vldo1",	},
+	{ .name = "vldo2",	},
+	{ .name = "vccsd",	},
+	{ .name = "v33",	},
+	{ .name = "vldo3",	},
+	{ .name = "vldo4",	},
+};
+
 static struct of_regulator_match *pfuze_matches;
 
 static int pfuze_parse_regulators_dt(struct pfuze_chip *chip)
@@ -430,6 +489,9 @@ static int pfuze_parse_regulators_dt(struct pfuze_chip *chip)
 	if (!np)
 		return -EINVAL;
 
+	if (of_property_read_bool(np, "fsl,pfuze-support-disable-sw"))
+		chip->flags |= PFUZE_FLAG_DISABLE_SW;
+
 	parent = of_get_child_by_name(np, "regulators");
 	if (!parent) {
 		dev_err(dev, "regulators node not found\n");
@@ -437,6 +499,11 @@ static int pfuze_parse_regulators_dt(struct pfuze_chip *chip)
 	}
 
 	switch (chip->chip_id) {
+	case PFUZE3001:
+		pfuze_matches = pfuze3001_matches;
+		ret = of_regulator_match(dev, parent, pfuze3001_matches,
+					 ARRAY_SIZE(pfuze3001_matches));
+		break;
 	case PFUZE3000:
 		pfuze_matches = pfuze3000_matches;
 		ret = of_regulator_match(dev, parent, pfuze3000_matches,
@@ -508,7 +575,8 @@ static int pfuze_identify(struct pfuze_chip *pfuze_chip)
 		 */
 		dev_info(pfuze_chip->dev, "Assuming misprogrammed ID=0x8");
 	} else if ((value & 0x0f) != pfuze_chip->chip_id &&
-		   (value & 0xf0) >> 4 != pfuze_chip->chip_id) {
+		   (value & 0xf0) >> 4 != pfuze_chip->chip_id &&
+		   (value != pfuze_chip->chip_id)) {
 		/* device id NOT match with your setting */
 		dev_warn(pfuze_chip->dev, "Illegal ID: %x\n", value);
 		return -ENODEV;
@@ -588,6 +656,13 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 
 	/* use the right regulators after identify the right device */
 	switch (pfuze_chip->chip_id) {
+	case PFUZE3001:
+		pfuze_chip->pfuze_regulators = pfuze3001_regulators;
+		regulator_num = ARRAY_SIZE(pfuze3001_regulators);
+		sw_check_start = PFUZE3001_SW2;
+		sw_check_end = PFUZE3001_SW2;
+		sw_hi = 1 << 3;
+		break;
 	case PFUZE3000:
 		pfuze_chip->pfuze_regulators = pfuze3000_regulators;
 		regulator_num = ARRAY_SIZE(pfuze3000_regulators);
@@ -611,7 +686,8 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 	}
 	dev_info(&client->dev, "pfuze%s found.\n",
 		(pfuze_chip->chip_id == PFUZE100) ? "100" :
-		((pfuze_chip->chip_id == PFUZE200) ? "200" : "3000"));
+		(((pfuze_chip->chip_id == PFUZE200) ? "200" :
+		((pfuze_chip->chip_id == PFUZE3000) ? "3000" : "3001"))));
 
 	memcpy(pfuze_chip->regulator_descs, pfuze_chip->pfuze_regulators,
 		sizeof(pfuze_chip->regulator_descs));
@@ -636,7 +712,8 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 		if (i >= sw_check_start && i <= sw_check_end) {
 			regmap_read(pfuze_chip->regmap, desc->vsel_reg, &val);
 			if (val & sw_hi) {
-				if (pfuze_chip->chip_id == PFUZE3000) {
+				if (pfuze_chip->chip_id == PFUZE3000 ||
+					pfuze_chip->chip_id == PFUZE3001) {
 					desc->volt_table = pfuze3000_sw2hi;
 					desc->n_voltages = ARRAY_SIZE(pfuze3000_sw2hi);
 				} else {
@@ -647,6 +724,21 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 			}
 		}
 
+		/*
+		 * Allow SW regulators to turn off. Checking it trough a flag is
+		 * a workaround to keep the backward compatibility with existing
+		 * old dtb's which may relay on the fact that we didn't disable
+		 * the switched regulator till yet.
+		 */
+		if (pfuze_chip->flags & PFUZE_FLAG_DISABLE_SW) {
+			if (pfuze_chip->regulator_descs[i].sw_reg) {
+				desc->ops = &pfuze100_sw_disable_regulator_ops;
+				desc->enable_val = 0x8;
+				desc->disable_val = 0x0;
+				desc->enable_time = 500;
+			}
+		}
+
 		config.dev = &client->dev;
 		config.init_data = init_data;
 		config.driver_data = pfuze_chip;
@@ -675,5 +767,5 @@ static struct i2c_driver pfuze_driver = {
 module_i2c_driver(pfuze_driver);
 
 MODULE_AUTHOR("Robin Gong <b38343@freescale.com>");
-MODULE_DESCRIPTION("Regulator Driver for Freescale PFUZE100/200/3000 PMIC");
+MODULE_DESCRIPTION("Regulator Driver for Freescale PFUZE100/200/3000/3001 PMIC");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c
new file mode 100644
index 000000000000..9f27daebd8c8
--- /dev/null
+++ b/drivers/regulator/qcom-rpmh-regulator.c
@@ -0,0 +1,769 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018, The Linux Foundation. All rights reserved.
+
+#define pr_fmt(fmt) "%s: " fmt, __func__
+
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/of_regulator.h>
+
+#include <soc/qcom/cmd-db.h>
+#include <soc/qcom/rpmh.h>
+
+#include <dt-bindings/regulator/qcom,rpmh-regulator.h>
+
+/**
+ * enum rpmh_regulator_type - supported RPMh accelerator types
+ * %VRM:	RPMh VRM accelerator which supports voting on enable, voltage,
+ *		and mode of LDO, SMPS, and BOB type PMIC regulators.
+ * %XOB:	RPMh XOB accelerator which supports voting on the enable state
+ *		of PMIC regulators.
+ */
+enum rpmh_regulator_type {
+	VRM,
+	XOB,
+};
+
+#define RPMH_REGULATOR_REG_VRM_VOLTAGE		0x0
+#define RPMH_REGULATOR_REG_ENABLE		0x4
+#define RPMH_REGULATOR_REG_VRM_MODE		0x8
+
+#define PMIC4_LDO_MODE_RETENTION		4
+#define PMIC4_LDO_MODE_LPM			5
+#define PMIC4_LDO_MODE_HPM			7
+
+#define PMIC4_SMPS_MODE_RETENTION		4
+#define PMIC4_SMPS_MODE_PFM			5
+#define PMIC4_SMPS_MODE_AUTO			6
+#define PMIC4_SMPS_MODE_PWM			7
+
+#define PMIC4_BOB_MODE_PASS			0
+#define PMIC4_BOB_MODE_PFM			1
+#define PMIC4_BOB_MODE_AUTO			2
+#define PMIC4_BOB_MODE_PWM			3
+
+/**
+ * struct rpmh_vreg_hw_data - RPMh regulator hardware configurations
+ * @regulator_type:		RPMh accelerator type used to manage this
+ *				regulator
+ * @ops:			Pointer to regulator ops callback structure
+ * @voltage_range:		The single range of voltages supported by this
+ *				PMIC regulator type
+ * @n_voltages:			The number of unique voltage set points defined
+ *				by voltage_range
+ * @hpm_min_load_uA:		Minimum load current in microamps that requires
+ *				high power mode (HPM) operation.  This is used
+ *				for LDO hardware type regulators only.
+ * @pmic_mode_map:		Array indexed by regulator framework mode
+ *				containing PMIC hardware modes.  Must be large
+ *				enough to index all framework modes supported
+ *				by this regulator hardware type.
+ * @of_map_mode:		Maps an RPMH_REGULATOR_MODE_* mode value defined
+ *				in device tree to a regulator framework mode
+ */
+struct rpmh_vreg_hw_data {
+	enum rpmh_regulator_type		regulator_type;
+	const struct regulator_ops		*ops;
+	const struct regulator_linear_range	voltage_range;
+	int					n_voltages;
+	int					hpm_min_load_uA;
+	const int				*pmic_mode_map;
+	unsigned int			      (*of_map_mode)(unsigned int mode);
+};
+
+/**
+ * struct rpmh_vreg - individual RPMh regulator data structure encapsulating a
+ *		single regulator device
+ * @dev:			Device pointer for the top-level PMIC RPMh
+ *				regulator parent device.  This is used as a
+ *				handle in RPMh write requests.
+ * @addr:			Base address of the regulator resource within
+ *				an RPMh accelerator
+ * @rdesc:			Regulator descriptor
+ * @hw_data:			PMIC regulator configuration data for this RPMh
+ *				regulator
+ * @always_wait_for_ack:	Boolean flag indicating if a request must always
+ *				wait for an ACK from RPMh before continuing even
+ *				if it corresponds to a strictly lower power
+ *				state (e.g. enabled --> disabled).
+ * @enabled:			Flag indicating if the regulator is enabled or
+ *				not
+ * @bypassed:			Boolean indicating if the regulator is in
+ *				bypass (pass-through) mode or not.  This is
+ *				only used by BOB rpmh-regulator resources.
+ * @voltage_selector:		Selector used for get_voltage_sel() and
+ *				set_voltage_sel() callbacks
+ * @mode:			RPMh VRM regulator current framework mode
+ */
+struct rpmh_vreg {
+	struct device			*dev;
+	u32				addr;
+	struct regulator_desc		rdesc;
+	const struct rpmh_vreg_hw_data	*hw_data;
+	bool				always_wait_for_ack;
+
+	int				enabled;
+	bool				bypassed;
+	int				voltage_selector;
+	unsigned int			mode;
+};
+
+/**
+ * struct rpmh_vreg_init_data - initialization data for an RPMh regulator
+ * @name:			Name for the regulator which also corresponds
+ *				to the device tree subnode name of the regulator
+ * @resource_name:		RPMh regulator resource name format string.
+ *				This must include exactly one field: '%s' which
+ *				is filled at run-time with the PMIC ID provided
+ *				by device tree property qcom,pmic-id.  Example:
+ *				"ldo%s1" for RPMh resource "ldoa1".
+ * @supply_name:		Parent supply regulator name
+ * @hw_data:			Configuration data for this PMIC regulator type
+ */
+struct rpmh_vreg_init_data {
+	const char			*name;
+	const char			*resource_name;
+	const char			*supply_name;
+	const struct rpmh_vreg_hw_data	*hw_data;
+};
+
+/**
+ * rpmh_regulator_send_request() - send the request to RPMh
+ * @vreg:		Pointer to the RPMh regulator
+ * @cmd:		Pointer to the RPMh command to send
+ * @wait_for_ack:	Boolean indicating if execution must wait until the
+ *			request has been acknowledged as complete
+ *
+ * Return: 0 on success, errno on failure
+ */
+static int rpmh_regulator_send_request(struct rpmh_vreg *vreg,
+			struct tcs_cmd *cmd, bool wait_for_ack)
+{
+	int ret;
+
+	if (wait_for_ack || vreg->always_wait_for_ack)
+		ret = rpmh_write(vreg->dev, RPMH_ACTIVE_ONLY_STATE, cmd, 1);
+	else
+		ret = rpmh_write_async(vreg->dev, RPMH_ACTIVE_ONLY_STATE, cmd,
+					1);
+
+	return ret;
+}
+
+static int _rpmh_regulator_vrm_set_voltage_sel(struct regulator_dev *rdev,
+				unsigned int selector, bool wait_for_ack)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+	struct tcs_cmd cmd = {
+		.addr = vreg->addr + RPMH_REGULATOR_REG_VRM_VOLTAGE,
+	};
+	int ret;
+
+	/* VRM voltage control register is set with voltage in millivolts. */
+	cmd.data = DIV_ROUND_UP(regulator_list_voltage_linear_range(rdev,
+							selector), 1000);
+
+	ret = rpmh_regulator_send_request(vreg, &cmd, wait_for_ack);
+	if (!ret)
+		vreg->voltage_selector = selector;
+
+	return ret;
+}
+
+static int rpmh_regulator_vrm_set_voltage_sel(struct regulator_dev *rdev,
+					unsigned int selector)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+
+	if (vreg->enabled == -EINVAL) {
+		/*
+		 * Cache the voltage and send it later when the regulator is
+		 * enabled or disabled.
+		 */
+		vreg->voltage_selector = selector;
+		return 0;
+	}
+
+	return _rpmh_regulator_vrm_set_voltage_sel(rdev, selector,
+					selector > vreg->voltage_selector);
+}
+
+static int rpmh_regulator_vrm_get_voltage_sel(struct regulator_dev *rdev)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+
+	return vreg->voltage_selector;
+}
+
+static int rpmh_regulator_is_enabled(struct regulator_dev *rdev)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+
+	return vreg->enabled;
+}
+
+static int rpmh_regulator_set_enable_state(struct regulator_dev *rdev,
+					bool enable)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+	struct tcs_cmd cmd = {
+		.addr = vreg->addr + RPMH_REGULATOR_REG_ENABLE,
+		.data = enable,
+	};
+	int ret;
+
+	if (vreg->enabled == -EINVAL &&
+	    vreg->voltage_selector != -ENOTRECOVERABLE) {
+		ret = _rpmh_regulator_vrm_set_voltage_sel(rdev,
+						vreg->voltage_selector, true);
+		if (ret < 0)
+			return ret;
+	}
+
+	ret = rpmh_regulator_send_request(vreg, &cmd, enable);
+	if (!ret)
+		vreg->enabled = enable;
+
+	return ret;
+}
+
+static int rpmh_regulator_enable(struct regulator_dev *rdev)
+{
+	return rpmh_regulator_set_enable_state(rdev, true);
+}
+
+static int rpmh_regulator_disable(struct regulator_dev *rdev)
+{
+	return rpmh_regulator_set_enable_state(rdev, false);
+}
+
+static int rpmh_regulator_vrm_set_mode_bypass(struct rpmh_vreg *vreg,
+					unsigned int mode, bool bypassed)
+{
+	struct tcs_cmd cmd = {
+		.addr = vreg->addr + RPMH_REGULATOR_REG_VRM_MODE,
+	};
+	int pmic_mode;
+
+	if (mode > REGULATOR_MODE_STANDBY)
+		return -EINVAL;
+
+	pmic_mode = vreg->hw_data->pmic_mode_map[mode];
+	if (pmic_mode < 0)
+		return pmic_mode;
+
+	if (bypassed)
+		cmd.data = PMIC4_BOB_MODE_PASS;
+	else
+		cmd.data = pmic_mode;
+
+	return rpmh_regulator_send_request(vreg, &cmd, true);
+}
+
+static int rpmh_regulator_vrm_set_mode(struct regulator_dev *rdev,
+					unsigned int mode)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+	int ret;
+
+	if (mode == vreg->mode)
+		return 0;
+
+	ret = rpmh_regulator_vrm_set_mode_bypass(vreg, mode, vreg->bypassed);
+	if (!ret)
+		vreg->mode = mode;
+
+	return ret;
+}
+
+static unsigned int rpmh_regulator_vrm_get_mode(struct regulator_dev *rdev)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+
+	return vreg->mode;
+}
+
+/**
+ * rpmh_regulator_vrm_set_load() - set the regulator mode based upon the load
+ *		current requested
+ * @rdev:		Regulator device pointer for the rpmh-regulator
+ * @load_uA:		Aggregated load current in microamps
+ *
+ * This function is used in the regulator_ops for VRM type RPMh regulator
+ * devices.
+ *
+ * Return: 0 on success, errno on failure
+ */
+static int rpmh_regulator_vrm_set_load(struct regulator_dev *rdev, int load_uA)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+	unsigned int mode;
+
+	if (load_uA >= vreg->hw_data->hpm_min_load_uA)
+		mode = REGULATOR_MODE_NORMAL;
+	else
+		mode = REGULATOR_MODE_IDLE;
+
+	return rpmh_regulator_vrm_set_mode(rdev, mode);
+}
+
+static int rpmh_regulator_vrm_set_bypass(struct regulator_dev *rdev,
+				bool enable)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+	int ret;
+
+	if (vreg->bypassed == enable)
+		return 0;
+
+	ret = rpmh_regulator_vrm_set_mode_bypass(vreg, vreg->mode, enable);
+	if (!ret)
+		vreg->bypassed = enable;
+
+	return ret;
+}
+
+static int rpmh_regulator_vrm_get_bypass(struct regulator_dev *rdev,
+				bool *enable)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+
+	*enable = vreg->bypassed;
+
+	return 0;
+}
+
+static const struct regulator_ops rpmh_regulator_vrm_ops = {
+	.enable			= rpmh_regulator_enable,
+	.disable		= rpmh_regulator_disable,
+	.is_enabled		= rpmh_regulator_is_enabled,
+	.set_voltage_sel	= rpmh_regulator_vrm_set_voltage_sel,
+	.get_voltage_sel	= rpmh_regulator_vrm_get_voltage_sel,
+	.list_voltage		= regulator_list_voltage_linear_range,
+	.set_mode		= rpmh_regulator_vrm_set_mode,
+	.get_mode		= rpmh_regulator_vrm_get_mode,
+};
+
+static const struct regulator_ops rpmh_regulator_vrm_drms_ops = {
+	.enable			= rpmh_regulator_enable,
+	.disable		= rpmh_regulator_disable,
+	.is_enabled		= rpmh_regulator_is_enabled,
+	.set_voltage_sel	= rpmh_regulator_vrm_set_voltage_sel,
+	.get_voltage_sel	= rpmh_regulator_vrm_get_voltage_sel,
+	.list_voltage		= regulator_list_voltage_linear_range,
+	.set_mode		= rpmh_regulator_vrm_set_mode,
+	.get_mode		= rpmh_regulator_vrm_get_mode,
+	.set_load		= rpmh_regulator_vrm_set_load,
+};
+
+static const struct regulator_ops rpmh_regulator_vrm_bypass_ops = {
+	.enable			= rpmh_regulator_enable,
+	.disable		= rpmh_regulator_disable,
+	.is_enabled		= rpmh_regulator_is_enabled,
+	.set_voltage_sel	= rpmh_regulator_vrm_set_voltage_sel,
+	.get_voltage_sel	= rpmh_regulator_vrm_get_voltage_sel,
+	.list_voltage		= regulator_list_voltage_linear_range,
+	.set_mode		= rpmh_regulator_vrm_set_mode,
+	.get_mode		= rpmh_regulator_vrm_get_mode,
+	.set_bypass		= rpmh_regulator_vrm_set_bypass,
+	.get_bypass		= rpmh_regulator_vrm_get_bypass,
+};
+
+static const struct regulator_ops rpmh_regulator_xob_ops = {
+	.enable			= rpmh_regulator_enable,
+	.disable		= rpmh_regulator_disable,
+	.is_enabled		= rpmh_regulator_is_enabled,
+};
+
+/**
+ * rpmh_regulator_init_vreg() - initialize all attributes of an rpmh-regulator
+ * vreg:		Pointer to the individual rpmh-regulator resource
+ * dev:			Pointer to the top level rpmh-regulator PMIC device
+ * node:		Pointer to the individual rpmh-regulator resource
+ *			device node
+ * pmic_id:		String used to identify the top level rpmh-regulator
+ *			PMIC device on the board
+ * pmic_rpmh_data:	Pointer to a null-terminated array of rpmh-regulator
+ *			resources defined for the top level PMIC device
+ *
+ * Return: 0 on success, errno on failure
+ */
+static int rpmh_regulator_init_vreg(struct rpmh_vreg *vreg, struct device *dev,
+			struct device_node *node, const char *pmic_id,
+			const struct rpmh_vreg_init_data *pmic_rpmh_data)
+{
+	struct regulator_config reg_config = {};
+	char rpmh_resource_name[20] = "";
+	const struct rpmh_vreg_init_data *rpmh_data;
+	struct regulator_init_data *init_data;
+	struct regulator_dev *rdev;
+	int ret;
+
+	vreg->dev = dev;
+
+	for (rpmh_data = pmic_rpmh_data; rpmh_data->name; rpmh_data++)
+		if (!strcmp(rpmh_data->name, node->name))
+			break;
+
+	if (!rpmh_data->name) {
+		dev_err(dev, "Unknown regulator %s\n", node->name);
+		return -EINVAL;
+	}
+
+	scnprintf(rpmh_resource_name, sizeof(rpmh_resource_name),
+		rpmh_data->resource_name, pmic_id);
+
+	vreg->addr = cmd_db_read_addr(rpmh_resource_name);
+	if (!vreg->addr) {
+		dev_err(dev, "%s: could not find RPMh address for resource %s\n",
+			node->name, rpmh_resource_name);
+		return -ENODEV;
+	}
+
+	vreg->rdesc.name = rpmh_data->name;
+	vreg->rdesc.supply_name = rpmh_data->supply_name;
+	vreg->hw_data = rpmh_data->hw_data;
+
+	vreg->enabled = -EINVAL;
+	vreg->voltage_selector = -ENOTRECOVERABLE;
+	vreg->mode = REGULATOR_MODE_INVALID;
+
+	if (rpmh_data->hw_data->n_voltages) {
+		vreg->rdesc.linear_ranges = &rpmh_data->hw_data->voltage_range;
+		vreg->rdesc.n_linear_ranges = 1;
+		vreg->rdesc.n_voltages = rpmh_data->hw_data->n_voltages;
+	}
+
+	vreg->always_wait_for_ack = of_property_read_bool(node,
+						"qcom,always-wait-for-ack");
+
+	vreg->rdesc.owner	= THIS_MODULE;
+	vreg->rdesc.type	= REGULATOR_VOLTAGE;
+	vreg->rdesc.ops		= vreg->hw_data->ops;
+	vreg->rdesc.of_map_mode	= vreg->hw_data->of_map_mode;
+
+	init_data = of_get_regulator_init_data(dev, node, &vreg->rdesc);
+	if (!init_data)
+		return -ENOMEM;
+
+	if (rpmh_data->hw_data->regulator_type == XOB &&
+	    init_data->constraints.min_uV &&
+	    init_data->constraints.min_uV == init_data->constraints.max_uV) {
+		vreg->rdesc.fixed_uV = init_data->constraints.min_uV;
+		vreg->rdesc.n_voltages = 1;
+	}
+
+	reg_config.dev		= dev;
+	reg_config.init_data	= init_data;
+	reg_config.of_node	= node;
+	reg_config.driver_data	= vreg;
+
+	rdev = devm_regulator_register(dev, &vreg->rdesc, &reg_config);
+	if (IS_ERR(rdev)) {
+		ret = PTR_ERR(rdev);
+		dev_err(dev, "%s: devm_regulator_register() failed, ret=%d\n",
+			node->name, ret);
+		return ret;
+	}
+
+	dev_dbg(dev, "%s regulator registered for RPMh resource %s @ 0x%05X\n",
+		node->name, rpmh_resource_name, vreg->addr);
+
+	return 0;
+}
+
+static const int pmic_mode_map_pmic4_ldo[REGULATOR_MODE_STANDBY + 1] = {
+	[REGULATOR_MODE_INVALID] = -EINVAL,
+	[REGULATOR_MODE_STANDBY] = PMIC4_LDO_MODE_RETENTION,
+	[REGULATOR_MODE_IDLE]    = PMIC4_LDO_MODE_LPM,
+	[REGULATOR_MODE_NORMAL]  = PMIC4_LDO_MODE_HPM,
+	[REGULATOR_MODE_FAST]    = -EINVAL,
+};
+
+static unsigned int rpmh_regulator_pmic4_ldo_of_map_mode(unsigned int rpmh_mode)
+{
+	unsigned int mode;
+
+	switch (rpmh_mode) {
+	case RPMH_REGULATOR_MODE_HPM:
+		mode = REGULATOR_MODE_NORMAL;
+		break;
+	case RPMH_REGULATOR_MODE_LPM:
+		mode = REGULATOR_MODE_IDLE;
+		break;
+	case RPMH_REGULATOR_MODE_RET:
+		mode = REGULATOR_MODE_STANDBY;
+		break;
+	default:
+		mode = REGULATOR_MODE_INVALID;
+	}
+
+	return mode;
+}
+
+static const int pmic_mode_map_pmic4_smps[REGULATOR_MODE_STANDBY + 1] = {
+	[REGULATOR_MODE_INVALID] = -EINVAL,
+	[REGULATOR_MODE_STANDBY] = PMIC4_SMPS_MODE_RETENTION,
+	[REGULATOR_MODE_IDLE]    = PMIC4_SMPS_MODE_PFM,
+	[REGULATOR_MODE_NORMAL]  = PMIC4_SMPS_MODE_AUTO,
+	[REGULATOR_MODE_FAST]    = PMIC4_SMPS_MODE_PWM,
+};
+
+static unsigned int
+rpmh_regulator_pmic4_smps_of_map_mode(unsigned int rpmh_mode)
+{
+	unsigned int mode;
+
+	switch (rpmh_mode) {
+	case RPMH_REGULATOR_MODE_HPM:
+		mode = REGULATOR_MODE_FAST;
+		break;
+	case RPMH_REGULATOR_MODE_AUTO:
+		mode = REGULATOR_MODE_NORMAL;
+		break;
+	case RPMH_REGULATOR_MODE_LPM:
+		mode = REGULATOR_MODE_IDLE;
+		break;
+	case RPMH_REGULATOR_MODE_RET:
+		mode = REGULATOR_MODE_STANDBY;
+		break;
+	default:
+		mode = REGULATOR_MODE_INVALID;
+	}
+
+	return mode;
+}
+
+static const int pmic_mode_map_pmic4_bob[REGULATOR_MODE_STANDBY + 1] = {
+	[REGULATOR_MODE_INVALID] = -EINVAL,
+	[REGULATOR_MODE_STANDBY] = -EINVAL,
+	[REGULATOR_MODE_IDLE]    = PMIC4_BOB_MODE_PFM,
+	[REGULATOR_MODE_NORMAL]  = PMIC4_BOB_MODE_AUTO,
+	[REGULATOR_MODE_FAST]    = PMIC4_BOB_MODE_PWM,
+};
+
+static unsigned int rpmh_regulator_pmic4_bob_of_map_mode(unsigned int rpmh_mode)
+{
+	unsigned int mode;
+
+	switch (rpmh_mode) {
+	case RPMH_REGULATOR_MODE_HPM:
+		mode = REGULATOR_MODE_FAST;
+		break;
+	case RPMH_REGULATOR_MODE_AUTO:
+		mode = REGULATOR_MODE_NORMAL;
+		break;
+	case RPMH_REGULATOR_MODE_LPM:
+		mode = REGULATOR_MODE_IDLE;
+		break;
+	default:
+		mode = REGULATOR_MODE_INVALID;
+	}
+
+	return mode;
+}
+
+static const struct rpmh_vreg_hw_data pmic4_pldo = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_drms_ops,
+	.voltage_range = REGULATOR_LINEAR_RANGE(1664000, 0, 255, 8000),
+	.n_voltages = 256,
+	.hpm_min_load_uA = 10000,
+	.pmic_mode_map = pmic_mode_map_pmic4_ldo,
+	.of_map_mode = rpmh_regulator_pmic4_ldo_of_map_mode,
+};
+
+static const struct rpmh_vreg_hw_data pmic4_pldo_lv = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_drms_ops,
+	.voltage_range = REGULATOR_LINEAR_RANGE(1256000, 0, 127, 8000),
+	.n_voltages = 128,
+	.hpm_min_load_uA = 10000,
+	.pmic_mode_map = pmic_mode_map_pmic4_ldo,
+	.of_map_mode = rpmh_regulator_pmic4_ldo_of_map_mode,
+};
+
+static const struct rpmh_vreg_hw_data pmic4_nldo = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_drms_ops,
+	.voltage_range = REGULATOR_LINEAR_RANGE(312000, 0, 127, 8000),
+	.n_voltages = 128,
+	.hpm_min_load_uA = 30000,
+	.pmic_mode_map = pmic_mode_map_pmic4_ldo,
+	.of_map_mode = rpmh_regulator_pmic4_ldo_of_map_mode,
+};
+
+static const struct rpmh_vreg_hw_data pmic4_hfsmps3 = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_ops,
+	.voltage_range = REGULATOR_LINEAR_RANGE(320000, 0, 215, 8000),
+	.n_voltages = 216,
+	.pmic_mode_map = pmic_mode_map_pmic4_smps,
+	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
+};
+
+static const struct rpmh_vreg_hw_data pmic4_ftsmps426 = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_ops,
+	.voltage_range = REGULATOR_LINEAR_RANGE(320000, 0, 258, 4000),
+	.n_voltages = 259,
+	.pmic_mode_map = pmic_mode_map_pmic4_smps,
+	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
+};
+
+static const struct rpmh_vreg_hw_data pmic4_bob = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_bypass_ops,
+	.voltage_range = REGULATOR_LINEAR_RANGE(1824000, 0, 83, 32000),
+	.n_voltages = 84,
+	.pmic_mode_map = pmic_mode_map_pmic4_bob,
+	.of_map_mode = rpmh_regulator_pmic4_bob_of_map_mode,
+};
+
+static const struct rpmh_vreg_hw_data pmic4_lvs = {
+	.regulator_type = XOB,
+	.ops = &rpmh_regulator_xob_ops,
+	/* LVS hardware does not support voltage or mode configuration. */
+};
+
+#define RPMH_VREG(_name, _resource_name, _hw_data, _supply_name) \
+{ \
+	.name		= _name, \
+	.resource_name	= _resource_name, \
+	.hw_data	= _hw_data, \
+	.supply_name	= _supply_name, \
+}
+
+static const struct rpmh_vreg_init_data pm8998_vreg_data[] = {
+	RPMH_VREG("smps1",  "smp%s1",  &pmic4_ftsmps426, "vdd-s1"),
+	RPMH_VREG("smps2",  "smp%s2",  &pmic4_ftsmps426, "vdd-s2"),
+	RPMH_VREG("smps3",  "smp%s3",  &pmic4_hfsmps3,   "vdd-s3"),
+	RPMH_VREG("smps4",  "smp%s4",  &pmic4_hfsmps3,   "vdd-s4"),
+	RPMH_VREG("smps5",  "smp%s5",  &pmic4_hfsmps3,   "vdd-s5"),
+	RPMH_VREG("smps6",  "smp%s6",  &pmic4_ftsmps426, "vdd-s6"),
+	RPMH_VREG("smps7",  "smp%s7",  &pmic4_ftsmps426, "vdd-s7"),
+	RPMH_VREG("smps8",  "smp%s8",  &pmic4_ftsmps426, "vdd-s8"),
+	RPMH_VREG("smps9",  "smp%s9",  &pmic4_ftsmps426, "vdd-s9"),
+	RPMH_VREG("smps10", "smp%s10", &pmic4_ftsmps426, "vdd-s10"),
+	RPMH_VREG("smps11", "smp%s11", &pmic4_ftsmps426, "vdd-s11"),
+	RPMH_VREG("smps12", "smp%s12", &pmic4_ftsmps426, "vdd-s12"),
+	RPMH_VREG("smps13", "smp%s13", &pmic4_ftsmps426, "vdd-s13"),
+	RPMH_VREG("ldo1",   "ldo%s1",  &pmic4_nldo,      "vdd-l1-l27"),
+	RPMH_VREG("ldo2",   "ldo%s2",  &pmic4_nldo,      "vdd-l2-l8-l17"),
+	RPMH_VREG("ldo3",   "ldo%s3",  &pmic4_nldo,      "vdd-l3-l11"),
+	RPMH_VREG("ldo4",   "ldo%s4",  &pmic4_nldo,      "vdd-l4-l5"),
+	RPMH_VREG("ldo5",   "ldo%s5",  &pmic4_nldo,      "vdd-l4-l5"),
+	RPMH_VREG("ldo6",   "ldo%s6",  &pmic4_pldo,      "vdd-l6"),
+	RPMH_VREG("ldo7",   "ldo%s7",  &pmic4_pldo_lv,   "vdd-l7-l12-l14-l15"),
+	RPMH_VREG("ldo8",   "ldo%s8",  &pmic4_nldo,      "vdd-l2-l8-l17"),
+	RPMH_VREG("ldo9",   "ldo%s9",  &pmic4_pldo,      "vdd-l9"),
+	RPMH_VREG("ldo10",  "ldo%s10", &pmic4_pldo,      "vdd-l10-l23-l25"),
+	RPMH_VREG("ldo11",  "ldo%s11", &pmic4_nldo,      "vdd-l3-l11"),
+	RPMH_VREG("ldo12",  "ldo%s12", &pmic4_pldo_lv,   "vdd-l7-l12-l14-l15"),
+	RPMH_VREG("ldo13",  "ldo%s13", &pmic4_pldo,      "vdd-l13-l19-l21"),
+	RPMH_VREG("ldo14",  "ldo%s14", &pmic4_pldo_lv,   "vdd-l7-l12-l14-l15"),
+	RPMH_VREG("ldo15",  "ldo%s15", &pmic4_pldo_lv,   "vdd-l7-l12-l14-l15"),
+	RPMH_VREG("ldo16",  "ldo%s16", &pmic4_pldo,      "vdd-l16-l28"),
+	RPMH_VREG("ldo17",  "ldo%s17", &pmic4_nldo,      "vdd-l2-l8-l17"),
+	RPMH_VREG("ldo18",  "ldo%s18", &pmic4_pldo,      "vdd-l18-l22"),
+	RPMH_VREG("ldo19",  "ldo%s19", &pmic4_pldo,      "vdd-l13-l19-l21"),
+	RPMH_VREG("ldo20",  "ldo%s20", &pmic4_pldo,      "vdd-l20-l24"),
+	RPMH_VREG("ldo21",  "ldo%s21", &pmic4_pldo,      "vdd-l13-l19-l21"),
+	RPMH_VREG("ldo22",  "ldo%s22", &pmic4_pldo,      "vdd-l18-l22"),
+	RPMH_VREG("ldo23",  "ldo%s23", &pmic4_pldo,      "vdd-l10-l23-l25"),
+	RPMH_VREG("ldo24",  "ldo%s24", &pmic4_pldo,      "vdd-l20-l24"),
+	RPMH_VREG("ldo25",  "ldo%s25", &pmic4_pldo,      "vdd-l10-l23-l25"),
+	RPMH_VREG("ldo26",  "ldo%s26", &pmic4_nldo,      "vdd-l26"),
+	RPMH_VREG("ldo27",  "ldo%s27", &pmic4_nldo,      "vdd-l1-l27"),
+	RPMH_VREG("ldo28",  "ldo%s28", &pmic4_pldo,      "vdd-l16-l28"),
+	RPMH_VREG("lvs1",   "vs%s1",   &pmic4_lvs,       "vin-lvs-1-2"),
+	RPMH_VREG("lvs2",   "vs%s2",   &pmic4_lvs,       "vin-lvs-1-2"),
+	{},
+};
+
+static const struct rpmh_vreg_init_data pmi8998_vreg_data[] = {
+	RPMH_VREG("bob",    "bob%s1",  &pmic4_bob,       "vdd-bob"),
+	{},
+};
+
+static const struct rpmh_vreg_init_data pm8005_vreg_data[] = {
+	RPMH_VREG("smps1",  "smp%s1",  &pmic4_ftsmps426, "vdd-s1"),
+	RPMH_VREG("smps2",  "smp%s2",  &pmic4_ftsmps426, "vdd-s2"),
+	RPMH_VREG("smps3",  "smp%s3",  &pmic4_ftsmps426, "vdd-s3"),
+	RPMH_VREG("smps4",  "smp%s4",  &pmic4_ftsmps426, "vdd-s4"),
+	{},
+};
+
+static int rpmh_regulator_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	const struct rpmh_vreg_init_data *vreg_data;
+	struct device_node *node;
+	struct rpmh_vreg *vreg;
+	const char *pmic_id;
+	int ret;
+
+	vreg_data = of_device_get_match_data(dev);
+	if (!vreg_data)
+		return -ENODEV;
+
+	ret = of_property_read_string(dev->of_node, "qcom,pmic-id", &pmic_id);
+	if (ret < 0) {
+		dev_err(dev, "qcom,pmic-id missing in DT node\n");
+		return ret;
+	}
+
+	for_each_available_child_of_node(dev->of_node, node) {
+		vreg = devm_kzalloc(dev, sizeof(*vreg), GFP_KERNEL);
+		if (!vreg) {
+			of_node_put(node);
+			return -ENOMEM;
+		}
+
+		ret = rpmh_regulator_init_vreg(vreg, dev, node, pmic_id,
+						vreg_data);
+		if (ret < 0) {
+			of_node_put(node);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static const struct of_device_id rpmh_regulator_match_table[] = {
+	{
+		.compatible = "qcom,pm8998-rpmh-regulators",
+		.data = pm8998_vreg_data,
+	},
+	{
+		.compatible = "qcom,pmi8998-rpmh-regulators",
+		.data = pmi8998_vreg_data,
+	},
+	{
+		.compatible = "qcom,pm8005-rpmh-regulators",
+		.data = pm8005_vreg_data,
+	},
+	{}
+};
+MODULE_DEVICE_TABLE(of, rpmh_regulator_match_table);
+
+static struct platform_driver rpmh_regulator_driver = {
+	.driver = {
+		.name = "qcom-rpmh-regulator",
+		.of_match_table	= of_match_ptr(rpmh_regulator_match_table),
+	},
+	.probe = rpmh_regulator_probe,
+};
+module_platform_driver(rpmh_regulator_driver);
+
+MODULE_DESCRIPTION("Qualcomm RPMh regulator driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/regulator/qcom_spmi-regulator.c b/drivers/regulator/qcom_spmi-regulator.c
index 9817f1a75342..53a61fb65642 100644
--- a/drivers/regulator/qcom_spmi-regulator.c
+++ b/drivers/regulator/qcom_spmi-regulator.c
@@ -1060,7 +1060,7 @@ static irqreturn_t spmi_regulator_vs_ocp_isr(int irq, void *data)
 #define SAW3_AVS_CTL_TGGL_MASK	0x8000000
 #define SAW3_AVS_CTL_CLEAR_MASK	0x7efc00
 
-static struct regmap *saw_regmap = NULL;
+static struct regmap *saw_regmap;
 
 static void spmi_saw_set_vdd(void *data)
 {
@@ -1728,7 +1728,7 @@ static const struct spmi_regulator_data pmi8994_regulators[] = {
 	{ "s2", 0x1700, "vdd_s2", },
 	{ "s3", 0x1a00, "vdd_s3", },
 	{ "l1", 0x4000, "vdd_l1", },
-        { }
+	{ }
 };
 
 static const struct of_device_id qcom_spmi_regulator_match[] = {
@@ -1752,7 +1752,8 @@ static int qcom_spmi_regulator_probe(struct platform_device *pdev)
 	const char *name;
 	struct device *dev = &pdev->dev;
 	struct device_node *node = pdev->dev.of_node;
-	struct device_node *syscon;
+	struct device_node *syscon, *reg_node;
+	struct property *reg_prop;
 	int ret, lenp;
 	struct list_head *vreg_list;
 
@@ -1774,16 +1775,19 @@ static int qcom_spmi_regulator_probe(struct platform_device *pdev)
 		syscon = of_parse_phandle(node, "qcom,saw-reg", 0);
 		saw_regmap = syscon_node_to_regmap(syscon);
 		of_node_put(syscon);
-		if (IS_ERR(regmap))
+		if (IS_ERR(saw_regmap))
 			dev_err(dev, "ERROR reading SAW regmap\n");
 	}
 
 	for (reg = match->data; reg->name; reg++) {
 
-		if (saw_regmap && \
-		    of_find_property(of_find_node_by_name(node, reg->name), \
-				     "qcom,saw-slave", &lenp)) {
-			continue;
+		if (saw_regmap) {
+			reg_node = of_get_child_by_name(node, reg->name);
+			reg_prop = of_find_property(reg_node, "qcom,saw-slave",
+						    &lenp);
+			of_node_put(reg_node);
+			if (reg_prop)
+				continue;
 		}
 
 		vreg = devm_kzalloc(dev, sizeof(*vreg), GFP_KERNEL);
@@ -1816,13 +1820,17 @@ static int qcom_spmi_regulator_probe(struct platform_device *pdev)
 		if (ret)
 			continue;
 
-		if (saw_regmap && \
-		    of_find_property(of_find_node_by_name(node, reg->name), \
-				     "qcom,saw-leader", &lenp)) {
-			spmi_saw_ops = *(vreg->desc.ops);
-			spmi_saw_ops.set_voltage_sel = \
-				spmi_regulator_saw_set_voltage;
-			vreg->desc.ops = &spmi_saw_ops;
+		if (saw_regmap) {
+			reg_node = of_get_child_by_name(node, reg->name);
+			reg_prop = of_find_property(reg_node, "qcom,saw-leader",
+						    &lenp);
+			of_node_put(reg_node);
+			if (reg_prop) {
+				spmi_saw_ops = *(vreg->desc.ops);
+				spmi_saw_ops.set_voltage_sel =
+					spmi_regulator_saw_set_voltage;
+				vreg->desc.ops = &spmi_saw_ops;
+			}
 		}
 
 		config.dev = dev;
diff --git a/drivers/regulator/s2mpa01.c b/drivers/regulator/s2mpa01.c
index 48f0ca90743c..095d25f3d2ea 100644
--- a/drivers/regulator/s2mpa01.c
+++ b/drivers/regulator/s2mpa01.c
@@ -1,13 +1,7 @@
-/*
- * Copyright (c) 2013 Samsung Electronics Co., Ltd
- *		http://www.samsung.com
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2013 Samsung Electronics Co., Ltd
+//		http://www.samsung.com
 
 #include <linux/bug.h>
 #include <linux/err.h>
diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c
index d1207ec683db..5bb6f4ca48db 100644
--- a/drivers/regulator/s2mps11.c
+++ b/drivers/regulator/s2mps11.c
@@ -1,20 +1,7 @@
-/*
- * s2mps11.c
- *
- * Copyright (c) 2012-2014 Samsung Electronics Co., Ltd
- *              http://www.samsung.com
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2012-2014 Samsung Electronics Co., Ltd
+//              http://www.samsung.com
 
 #include <linux/bug.h>
 #include <linux/err.h>
diff --git a/drivers/regulator/s5m8767.c b/drivers/regulator/s5m8767.c
index 0cbc980753c2..667d16dc83ce 100644
--- a/drivers/regulator/s5m8767.c
+++ b/drivers/regulator/s5m8767.c
@@ -1,15 +1,7 @@
-/*
- * s5m8767.c
- *
- * Copyright (c) 2011 Samsung Electronics Co., Ltd
- *              http://www.samsung.com
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2011 Samsung Electronics Co., Ltd
+//              http://www.samsung.com
 
 #include <linux/err.h>
 #include <linux/of_gpio.h>
diff --git a/drivers/regulator/tps65217-regulator.c b/drivers/regulator/tps65217-regulator.c
index fc12badf3805..d84fab616abf 100644
--- a/drivers/regulator/tps65217-regulator.c
+++ b/drivers/regulator/tps65217-regulator.c
@@ -232,6 +232,8 @@ static int tps65217_regulator_probe(struct platform_device *pdev)
 	tps->strobes = devm_kcalloc(&pdev->dev,
 				    TPS65217_NUM_REGULATOR, sizeof(u8),
 				    GFP_KERNEL);
+	if (!tps->strobes)
+		return -ENOMEM;
 
 	platform_set_drvdata(pdev, tps);
 
diff --git a/drivers/regulator/uniphier-regulator.c b/drivers/regulator/uniphier-regulator.c
new file mode 100644
index 000000000000..abf22acbd13e
--- /dev/null
+++ b/drivers/regulator/uniphier-regulator.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Regulator controller driver for UniPhier SoC
+// Copyright 2018 Socionext Inc.
+// Author: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
+
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/of_regulator.h>
+#include <linux/reset.h>
+
+#define MAX_CLKS	2
+#define MAX_RSTS	2
+
+struct uniphier_regulator_soc_data {
+	int nclks;
+	const char * const *clock_names;
+	int nrsts;
+	const char * const *reset_names;
+	const struct regulator_desc *desc;
+	const struct regmap_config *regconf;
+};
+
+struct uniphier_regulator_priv {
+	struct clk_bulk_data clk[MAX_CLKS];
+	struct reset_control *rst[MAX_RSTS];
+	const struct uniphier_regulator_soc_data *data;
+};
+
+static struct regulator_ops uniphier_regulator_ops = {
+	.enable     = regulator_enable_regmap,
+	.disable    = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+};
+
+static int uniphier_regulator_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct uniphier_regulator_priv *priv;
+	struct regulator_config config = { };
+	struct regulator_dev *rdev;
+	struct regmap *regmap;
+	struct resource *res;
+	void __iomem *base;
+	const char *name;
+	int i, ret, nr;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->data = of_device_get_match_data(dev);
+	if (WARN_ON(!priv->data))
+		return -EINVAL;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	for (i = 0; i < priv->data->nclks; i++)
+		priv->clk[i].id = priv->data->clock_names[i];
+	ret = devm_clk_bulk_get(dev, priv->data->nclks, priv->clk);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < priv->data->nrsts; i++) {
+		name = priv->data->reset_names[i];
+		priv->rst[i] = devm_reset_control_get_shared(dev, name);
+		if (IS_ERR(priv->rst[i]))
+			return PTR_ERR(priv->rst[i]);
+	}
+
+	ret = clk_bulk_prepare_enable(priv->data->nclks, priv->clk);
+	if (ret)
+		return ret;
+
+	for (nr = 0; nr < priv->data->nrsts; nr++) {
+		ret = reset_control_deassert(priv->rst[nr]);
+		if (ret)
+			goto out_rst_assert;
+	}
+
+	regmap = devm_regmap_init_mmio(dev, base, priv->data->regconf);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	config.dev = dev;
+	config.driver_data = priv;
+	config.of_node = dev->of_node;
+	config.regmap = regmap;
+	config.init_data = of_get_regulator_init_data(dev, dev->of_node,
+						      priv->data->desc);
+	rdev = devm_regulator_register(dev, priv->data->desc, &config);
+	if (IS_ERR(rdev)) {
+		ret = PTR_ERR(rdev);
+		goto out_rst_assert;
+	}
+
+	platform_set_drvdata(pdev, priv);
+
+	return 0;
+
+out_rst_assert:
+	while (nr--)
+		reset_control_assert(priv->rst[nr]);
+
+	clk_bulk_disable_unprepare(priv->data->nclks, priv->clk);
+
+	return ret;
+}
+
+static int uniphier_regulator_remove(struct platform_device *pdev)
+{
+	struct uniphier_regulator_priv *priv = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < priv->data->nrsts; i++)
+		reset_control_assert(priv->rst[i]);
+
+	clk_bulk_disable_unprepare(priv->data->nclks, priv->clk);
+
+	return 0;
+}
+
+/* USB3 controller data */
+#define USB3VBUS_OFFSET		0x0
+#define USB3VBUS_REG		BIT(4)
+#define USB3VBUS_REG_EN		BIT(3)
+static const struct regulator_desc uniphier_usb3_regulator_desc = {
+	.name = "vbus",
+	.of_match = of_match_ptr("vbus"),
+	.ops = &uniphier_regulator_ops,
+	.type = REGULATOR_VOLTAGE,
+	.owner = THIS_MODULE,
+	.enable_reg  = USB3VBUS_OFFSET,
+	.enable_mask = USB3VBUS_REG_EN | USB3VBUS_REG,
+	.enable_val  = USB3VBUS_REG_EN | USB3VBUS_REG,
+	.disable_val = USB3VBUS_REG_EN,
+};
+
+static const struct regmap_config uniphier_usb3_regulator_regconf = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+	.max_register = 1,
+};
+
+static const char * const uniphier_pro4_clock_reset_names[] = {
+	"gio", "link",
+};
+
+static const struct uniphier_regulator_soc_data uniphier_pro4_usb3_data = {
+	.nclks = ARRAY_SIZE(uniphier_pro4_clock_reset_names),
+	.clock_names = uniphier_pro4_clock_reset_names,
+	.nrsts = ARRAY_SIZE(uniphier_pro4_clock_reset_names),
+	.reset_names = uniphier_pro4_clock_reset_names,
+	.desc = &uniphier_usb3_regulator_desc,
+	.regconf = &uniphier_usb3_regulator_regconf,
+};
+
+static const char * const uniphier_pxs2_clock_reset_names[] = {
+	"link",
+};
+
+static const struct uniphier_regulator_soc_data uniphier_pxs2_usb3_data = {
+	.nclks = ARRAY_SIZE(uniphier_pxs2_clock_reset_names),
+	.clock_names = uniphier_pxs2_clock_reset_names,
+	.nrsts = ARRAY_SIZE(uniphier_pxs2_clock_reset_names),
+	.reset_names = uniphier_pxs2_clock_reset_names,
+	.desc = &uniphier_usb3_regulator_desc,
+	.regconf = &uniphier_usb3_regulator_regconf,
+};
+
+static const struct of_device_id uniphier_regulator_match[] = {
+	/* USB VBUS */
+	{
+		.compatible = "socionext,uniphier-pro4-usb3-regulator",
+		.data = &uniphier_pro4_usb3_data,
+	},
+	{
+		.compatible = "socionext,uniphier-pxs2-usb3-regulator",
+		.data = &uniphier_pxs2_usb3_data,
+	},
+	{
+		.compatible = "socionext,uniphier-ld20-usb3-regulator",
+		.data = &uniphier_pxs2_usb3_data,
+	},
+	{
+		.compatible = "socionext,uniphier-pxs3-usb3-regulator",
+		.data = &uniphier_pxs2_usb3_data,
+	},
+	{ /* Sentinel */ },
+};
+
+static struct platform_driver uniphier_regulator_driver = {
+	.probe = uniphier_regulator_probe,
+	.remove = uniphier_regulator_remove,
+	.driver = {
+		.name  = "uniphier-regulator",
+		.of_match_table = uniphier_regulator_match,
+	},
+};
+module_platform_driver(uniphier_regulator_driver);
+
+MODULE_AUTHOR("Kunihiko Hayashi <hayashi.kunihiko@socionext.com>");
+MODULE_DESCRIPTION("UniPhier Regulator Controller Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index a9f60d0ee02e..a23e7d394a0a 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -73,8 +73,8 @@ static int  dasd_alloc_queue(struct dasd_block *);
 static void dasd_setup_queue(struct dasd_block *);
 static void dasd_free_queue(struct dasd_block *);
 static int dasd_flush_block_queue(struct dasd_block *);
-static void dasd_device_tasklet(struct dasd_device *);
-static void dasd_block_tasklet(struct dasd_block *);
+static void dasd_device_tasklet(unsigned long);
+static void dasd_block_tasklet(unsigned long);
 static void do_kick_device(struct work_struct *);
 static void do_restore_device(struct work_struct *);
 static void do_reload_device(struct work_struct *);
@@ -125,8 +125,7 @@ struct dasd_device *dasd_alloc_device(void)
 	dasd_init_chunklist(&device->erp_chunks, device->erp_mem, PAGE_SIZE);
 	spin_lock_init(&device->mem_lock);
 	atomic_set(&device->tasklet_scheduled, 0);
-	tasklet_init(&device->tasklet,
-		     (void (*)(unsigned long)) dasd_device_tasklet,
+	tasklet_init(&device->tasklet, dasd_device_tasklet,
 		     (unsigned long) device);
 	INIT_LIST_HEAD(&device->ccw_queue);
 	timer_setup(&device->timer, dasd_device_timeout, 0);
@@ -166,8 +165,7 @@ struct dasd_block *dasd_alloc_block(void)
 	atomic_set(&block->open_count, -1);
 
 	atomic_set(&block->tasklet_scheduled, 0);
-	tasklet_init(&block->tasklet,
-		     (void (*)(unsigned long)) dasd_block_tasklet,
+	tasklet_init(&block->tasklet, dasd_block_tasklet,
 		     (unsigned long) block);
 	INIT_LIST_HEAD(&block->ccw_queue);
 	spin_lock_init(&block->queue_lock);
@@ -2064,8 +2062,9 @@ EXPORT_SYMBOL_GPL(dasd_flush_device_queue);
 /*
  * Acquire the device lock and process queues for the device.
  */
-static void dasd_device_tasklet(struct dasd_device *device)
+static void dasd_device_tasklet(unsigned long data)
 {
+	struct dasd_device *device = (struct dasd_device *) data;
 	struct list_head final_queue;
 
 	atomic_set (&device->tasklet_scheduled, 0);
@@ -2783,8 +2782,9 @@ static void __dasd_block_start_head(struct dasd_block *block)
  * block layer request queue, creates ccw requests, enqueues them on
  * a dasd_device and processes ccw requests that have been returned.
  */
-static void dasd_block_tasklet(struct dasd_block *block)
+static void dasd_block_tasklet(unsigned long data)
 {
+	struct dasd_block *block = (struct dasd_block *) data;
 	struct list_head final_queue;
 	struct list_head *l, *n;
 	struct dasd_ccw_req *cqr;
@@ -3127,6 +3127,7 @@ static int dasd_alloc_queue(struct dasd_block *block)
 	block->tag_set.nr_hw_queues = nr_hw_queues;
 	block->tag_set.queue_depth = queue_depth;
 	block->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	block->tag_set.numa_node = NUMA_NO_NODE;
 
 	rc = blk_mq_alloc_tag_set(&block->tag_set);
 	if (rc)
diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c
index e36a114354fc..b9ce93e9df89 100644
--- a/drivers/s390/block/dasd_alias.c
+++ b/drivers/s390/block/dasd_alias.c
@@ -708,7 +708,7 @@ static int reset_summary_unit_check(struct alias_lcu *lcu,
 	struct ccw1 *ccw;
 
 	cqr = lcu->rsu_cqr;
-	strncpy((char *) &cqr->magic, "ECKD", 4);
+	memcpy((char *) &cqr->magic, "ECKD", 4);
 	ASCEBC((char *) &cqr->magic, 4);
 	ccw = cqr->cpaddr;
 	ccw->cmd_code = DASD_ECKD_CCW_RSCK;
diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
index b9ebb565ee2c..fab35c6170cc 100644
--- a/drivers/s390/block/dasd_devmap.c
+++ b/drivers/s390/block/dasd_devmap.c
@@ -426,7 +426,7 @@ dasd_add_busid(const char *bus_id, int features)
 	if (!devmap) {
 		/* This bus_id is new. */
 		new->devindex = dasd_max_devindex++;
-		strncpy(new->bus_id, bus_id, DASD_BUS_ID_SIZE);
+		strlcpy(new->bus_id, bus_id, DASD_BUS_ID_SIZE);
 		new->features = features;
 		new->device = NULL;
 		list_add(&new->list, &dasd_hashlists[hash]);
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index bbf95b78ef5d..4e7b55a14b1a 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -1780,6 +1780,9 @@ static void dasd_eckd_uncheck_device(struct dasd_device *device)
 	struct dasd_eckd_private *private = device->private;
 	int i;
 
+	if (!private)
+		return;
+
 	dasd_alias_disconnect_device_from_lcu(device);
 	private->ned = NULL;
 	private->sneq = NULL;
@@ -2035,8 +2038,11 @@ static int dasd_eckd_basic_to_ready(struct dasd_device *device)
 
 static int dasd_eckd_online_to_ready(struct dasd_device *device)
 {
-	cancel_work_sync(&device->reload_device);
-	cancel_work_sync(&device->kick_validate);
+	if (cancel_work_sync(&device->reload_device))
+		dasd_put_device(device);
+	if (cancel_work_sync(&device->kick_validate))
+		dasd_put_device(device);
+
 	return 0;
 };
 
@@ -3535,7 +3541,7 @@ static int prepare_itcw(struct itcw *itcw,
 
 	dcw = itcw_add_dcw(itcw, pfx_cmd, 0,
 		     &pfxdata, sizeof(pfxdata), total_data_size);
-	return PTR_RET(dcw);
+	return PTR_ERR_OR_ZERO(dcw);
 }
 
 static struct dasd_ccw_req *dasd_eckd_build_cp_tpm_track(
diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c
index 6ef8714dc693..93bb09da7fdc 100644
--- a/drivers/s390/block/dasd_eer.c
+++ b/drivers/s390/block/dasd_eer.c
@@ -313,7 +313,7 @@ static void dasd_eer_write_standard_trigger(struct dasd_device *device,
 	ktime_get_real_ts64(&ts);
 	header.tv_sec = ts.tv_sec;
 	header.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
-	strncpy(header.busid, dev_name(&device->cdev->dev),
+	strlcpy(header.busid, dev_name(&device->cdev->dev),
 		DASD_EER_BUSID_SIZE);
 
 	spin_lock_irqsave(&bufferlock, flags);
@@ -356,7 +356,7 @@ static void dasd_eer_write_snss_trigger(struct dasd_device *device,
 	ktime_get_real_ts64(&ts);
 	header.tv_sec = ts.tv_sec;
 	header.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
-	strncpy(header.busid, dev_name(&device->cdev->dev),
+	strlcpy(header.busid, dev_name(&device->cdev->dev),
 		DASD_EER_BUSID_SIZE);
 
 	spin_lock_irqsave(&bufferlock, flags);
diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c
index b1fcb76dd272..98f66b7b6794 100644
--- a/drivers/s390/block/scm_blk.c
+++ b/drivers/s390/block/scm_blk.c
@@ -455,6 +455,7 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev)
 	bdev->tag_set.nr_hw_queues = nr_requests;
 	bdev->tag_set.queue_depth = nr_requests_per_io * nr_requests;
 	bdev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	bdev->tag_set.numa_node = NUMA_NO_NODE;
 
 	ret = blk_mq_alloc_tag_set(&bdev->tag_set);
 	if (ret)
diff --git a/drivers/s390/char/Makefile b/drivers/s390/char/Makefile
index 0a4c13e1e76e..c6ab34f94b1b 100644
--- a/drivers/s390/char/Makefile
+++ b/drivers/s390/char/Makefile
@@ -12,11 +12,6 @@ GCOV_PROFILE_sclp_early_core.o		:= n
 KCOV_INSTRUMENT_sclp_early_core.o	:= n
 UBSAN_SANITIZE_sclp_early_core.o	:= n
 
-ifneq ($(CC_FLAGS_MARCH),-march=z900)
-CFLAGS_REMOVE_sclp_early_core.o	+= $(CC_FLAGS_MARCH)
-CFLAGS_sclp_early_core.o		+= -march=z900
-endif
-
 CFLAGS_sclp_early_core.o		+= -D__NO_FORTIFY
 
 CFLAGS_REMOVE_sclp_early_core.o	+= $(CC_FLAGS_EXPOLINE)
diff --git a/drivers/s390/char/keyboard.c b/drivers/s390/char/keyboard.c
index 79eb60958015..bbb3001b0961 100644
--- a/drivers/s390/char/keyboard.c
+++ b/drivers/s390/char/keyboard.c
@@ -334,37 +334,41 @@ do_kdsk_ioctl(struct kbd_data *kbd, struct kbentry __user *user_kbe,
 	      int cmd, int perm)
 {
 	struct kbentry tmp;
+	unsigned long kb_index, kb_table;
 	ushort *key_map, val, ov;
 
 	if (copy_from_user(&tmp, user_kbe, sizeof(struct kbentry)))
 		return -EFAULT;
+	kb_index = (unsigned long) tmp.kb_index;
 #if NR_KEYS < 256
-	if (tmp.kb_index >= NR_KEYS)
+	if (kb_index >= NR_KEYS)
 		return -EINVAL;
 #endif
+	kb_table = (unsigned long) tmp.kb_table;
 #if MAX_NR_KEYMAPS < 256
-	if (tmp.kb_table >= MAX_NR_KEYMAPS)
+	if (kb_table >= MAX_NR_KEYMAPS)
 		return -EINVAL;	
+	kb_table = array_index_nospec(kb_table , MAX_NR_KEYMAPS);
 #endif
 
 	switch (cmd) {
 	case KDGKBENT:
-		key_map = kbd->key_maps[tmp.kb_table];
+		key_map = kbd->key_maps[kb_table];
 		if (key_map) {
-		    val = U(key_map[tmp.kb_index]);
+		    val = U(key_map[kb_index]);
 		    if (KTYP(val) >= KBD_NR_TYPES)
 			val = K_HOLE;
 		} else
-		    val = (tmp.kb_index ? K_HOLE : K_NOSUCHMAP);
+		    val = (kb_index ? K_HOLE : K_NOSUCHMAP);
 		return put_user(val, &user_kbe->kb_value);
 	case KDSKBENT:
 		if (!perm)
 			return -EPERM;
-		if (!tmp.kb_index && tmp.kb_value == K_NOSUCHMAP) {
+		if (!kb_index && tmp.kb_value == K_NOSUCHMAP) {
 			/* disallocate map */
-			key_map = kbd->key_maps[tmp.kb_table];
+			key_map = kbd->key_maps[kb_table];
 			if (key_map) {
-			    kbd->key_maps[tmp.kb_table] = NULL;
+			    kbd->key_maps[kb_table] = NULL;
 			    kfree(key_map);
 			}
 			break;
@@ -375,18 +379,18 @@ do_kdsk_ioctl(struct kbd_data *kbd, struct kbentry __user *user_kbe,
 		if (KVAL(tmp.kb_value) > kbd_max_vals[KTYP(tmp.kb_value)])
 			return -EINVAL;
 
-		if (!(key_map = kbd->key_maps[tmp.kb_table])) {
+		if (!(key_map = kbd->key_maps[kb_table])) {
 			int j;
 
 			key_map = kmalloc(sizeof(plain_map),
 						     GFP_KERNEL);
 			if (!key_map)
 				return -ENOMEM;
-			kbd->key_maps[tmp.kb_table] = key_map;
+			kbd->key_maps[kb_table] = key_map;
 			for (j = 0; j < NR_KEYS; j++)
 				key_map[j] = U(K_HOLE);
 		}
-		ov = U(key_map[tmp.kb_index]);
+		ov = U(key_map[kb_index]);
 		if (tmp.kb_value == ov)
 			break;	/* nothing to do */
 		/*
@@ -395,7 +399,7 @@ do_kdsk_ioctl(struct kbd_data *kbd, struct kbentry __user *user_kbe,
 		if (((ov == K_SAK) || (tmp.kb_value == K_SAK)) &&
 		    !capable(CAP_SYS_ADMIN))
 			return -EPERM;
-		key_map[tmp.kb_index] = U(tmp.kb_value);
+		key_map[kb_index] = U(tmp.kb_value);
 		break;
 	}
 	return 0;
diff --git a/drivers/s390/char/monwriter.c b/drivers/s390/char/monwriter.c
index 76c158c41510..4f1a69c9d81d 100644
--- a/drivers/s390/char/monwriter.c
+++ b/drivers/s390/char/monwriter.c
@@ -61,7 +61,7 @@ static int monwrite_diag(struct monwrite_hdr *myhdr, char *buffer, int fcn)
 	struct appldata_product_id id;
 	int rc;
 
-	strncpy(id.prod_nr, "LNXAPPL", 7);
+	memcpy(id.prod_nr, "LNXAPPL", 7);
 	id.prod_fn = myhdr->applid;
 	id.record_nr = myhdr->record_num;
 	id.version_nr = myhdr->version;
diff --git a/drivers/s390/char/sclp_async.c b/drivers/s390/char/sclp_async.c
index ee6f3b563728..e69b12a40636 100644
--- a/drivers/s390/char/sclp_async.c
+++ b/drivers/s390/char/sclp_async.c
@@ -64,42 +64,18 @@ static struct notifier_block call_home_panic_nb = {
 	.priority = INT_MAX,
 };
 
-static int proc_handler_callhome(struct ctl_table *ctl, int write,
-				 void __user *buffer, size_t *count,
-				 loff_t *ppos)
-{
-	unsigned long val;
-	int len, rc;
-	char buf[3];
-
-	if (!*count || (*ppos && !write)) {
-		*count = 0;
-		return 0;
-	}
-	if (!write) {
-		len = snprintf(buf, sizeof(buf), "%d\n", callhome_enabled);
-		rc = copy_to_user(buffer, buf, sizeof(buf));
-		if (rc != 0)
-			return -EFAULT;
-	} else {
-		len = *count;
-		rc = kstrtoul_from_user(buffer, len, 0, &val);
-		if (rc)
-			return rc;
-		if (val != 0 && val != 1)
-			return -EINVAL;
-		callhome_enabled = val;
-	}
-	*count = len;
-	*ppos += len;
-	return 0;
-}
+static int zero;
+static int one = 1;
 
 static struct ctl_table callhome_table[] = {
 	{
 		.procname	= "callhome",
+		.data		= &callhome_enabled,
+		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_handler_callhome,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
 	},
 	{}
 };
diff --git a/drivers/s390/char/tape_3590.c b/drivers/s390/char/tape_3590.c
index 37e65a05517f..cdcde18e7220 100644
--- a/drivers/s390/char/tape_3590.c
+++ b/drivers/s390/char/tape_3590.c
@@ -113,16 +113,16 @@ static int crypt_enabled(struct tape_device *device)
 static void ext_to_int_kekl(struct tape390_kekl *in,
 			    struct tape3592_kekl *out)
 {
-	int i;
+	int len;
 
 	memset(out, 0, sizeof(*out));
 	if (in->type == TAPE390_KEKL_TYPE_HASH)
 		out->flags |= 0x40;
 	if (in->type_on_tape == TAPE390_KEKL_TYPE_HASH)
 		out->flags |= 0x80;
-	strncpy(out->label, in->label, 64);
-	for (i = strlen(in->label); i < sizeof(out->label); i++)
-		out->label[i] = ' ';
+	len = min(sizeof(out->label), strlen(in->label));
+	memcpy(out->label, in->label, len);
+	memset(out->label + len, ' ', sizeof(out->label) - len);
 	ASCEBC(out->label, sizeof(out->label));
 }
 
diff --git a/drivers/s390/char/tape_class.c b/drivers/s390/char/tape_class.c
index a07102472ce9..b58df0dd0039 100644
--- a/drivers/s390/char/tape_class.c
+++ b/drivers/s390/char/tape_class.c
@@ -54,10 +54,10 @@ struct tape_class_device *register_tape_dev(
 	if (!tcd)
 		return ERR_PTR(-ENOMEM);
 
-	strncpy(tcd->device_name, device_name, TAPECLASS_NAME_LEN);
+	strlcpy(tcd->device_name, device_name, TAPECLASS_NAME_LEN);
 	for (s = strchr(tcd->device_name, '/'); s; s = strchr(s, '/'))
 		*s = '!';
-	strncpy(tcd->mode_name, mode_name, TAPECLASS_NAME_LEN);
+	strlcpy(tcd->mode_name, mode_name, TAPECLASS_NAME_LEN);
 	for (s = strchr(tcd->mode_name, '/'); s; s = strchr(s, '/'))
 		*s = '!';
 
@@ -77,7 +77,7 @@ struct tape_class_device *register_tape_dev(
 	tcd->class_device = device_create(tape_class, device,
 					  tcd->char_device->dev, NULL,
 					  "%s", tcd->device_name);
-	rc = PTR_RET(tcd->class_device);
+	rc = PTR_ERR_OR_ZERO(tcd->class_device);
 	if (rc)
 		goto fail_with_cdev;
 	rc = sysfs_create_link(
diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c
index afbdee74147d..51038ec309c1 100644
--- a/drivers/s390/cio/chp.c
+++ b/drivers/s390/cio/chp.c
@@ -471,14 +471,17 @@ int chp_new(struct chp_id chpid)
 {
 	struct channel_subsystem *css = css_by_id(chpid.cssid);
 	struct channel_path *chp;
-	int ret;
+	int ret = 0;
 
+	mutex_lock(&css->mutex);
 	if (chp_is_registered(chpid))
-		return 0;
-	chp = kzalloc(sizeof(struct channel_path), GFP_KERNEL);
-	if (!chp)
-		return -ENOMEM;
+		goto out;
 
+	chp = kzalloc(sizeof(struct channel_path), GFP_KERNEL);
+	if (!chp) {
+		ret = -ENOMEM;
+		goto out;
+	}
 	/* fill in status, etc. */
 	chp->chpid = chpid;
 	chp->state = 1;
@@ -505,21 +508,20 @@ int chp_new(struct chp_id chpid)
 		put_device(&chp->dev);
 		goto out;
 	}
-	mutex_lock(&css->mutex);
+
 	if (css->cm_enabled) {
 		ret = chp_add_cmg_attr(chp);
 		if (ret) {
 			device_unregister(&chp->dev);
-			mutex_unlock(&css->mutex);
 			goto out;
 		}
 	}
 	css->chps[chpid.id] = chp;
-	mutex_unlock(&css->mutex);
 	goto out;
 out_free:
 	kfree(chp);
 out:
+	mutex_unlock(&css->mutex);
 	return ret;
 }
 
@@ -585,8 +587,7 @@ static void chp_process_crw(struct crw *crw0, struct crw *crw1,
 	switch (crw0->erc) {
 	case CRW_ERC_IPARM: /* Path has come. */
 	case CRW_ERC_INIT:
-		if (!chp_is_registered(chpid))
-			chp_new(chpid);
+		chp_new(chpid);
 		chsc_chp_online(chpid);
 		break;
 	case CRW_ERC_PERRI: /* Path has gone. */
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index 9029804dcd22..a0baee25134c 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -91,7 +91,7 @@ struct chsc_ssd_area {
 	u16 sch;	  /* subchannel */
 	u8 chpid[8];	  /* chpids 0-7 */
 	u16 fla[8];	  /* full link addresses 0-7 */
-} __attribute__ ((packed));
+} __packed __aligned(PAGE_SIZE);
 
 int chsc_get_ssd_info(struct subchannel_id schid, struct chsc_ssd_info *ssd)
 {
@@ -319,7 +319,7 @@ struct chsc_sei {
 		struct chsc_sei_nt2_area nt2_area;
 		u8 nt_area[PAGE_SIZE - 24];
 	} u;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 /*
  * Node Descriptor as defined in SA22-7204, "Common I/O-Device Commands"
@@ -841,7 +841,7 @@ int __chsc_do_secm(struct channel_subsystem *css, int enable)
 		u32 : 4;
 		u32 fmt : 4;
 		u32 : 16;
-	} __attribute__ ((packed)) *secm_area;
+	} *secm_area;
 	unsigned long flags;
 	int ret, ccode;
 
@@ -1014,7 +1014,7 @@ int chsc_get_channel_measurement_chars(struct channel_path *chp)
 		u32 cmg : 8;
 		u32 zeroes3;
 		u32 data[NR_MEASUREMENT_CHARS];
-	} __attribute__ ((packed)) *scmc_area;
+	} *scmc_area;
 
 	chp->shared = -1;
 	chp->cmg = -1;
@@ -1142,7 +1142,7 @@ int __init chsc_get_cssid(int idx)
 			u8 cssid;
 			u32 : 24;
 		} list[0];
-	} __packed *sdcal_area;
+	} *sdcal_area;
 	int ret;
 
 	spin_lock_irq(&chsc_page_lock);
@@ -1192,7 +1192,7 @@ chsc_determine_css_characteristics(void)
 		u32 reserved4;
 		u32 general_char[510];
 		u32 chsc_char[508];
-	} __attribute__ ((packed)) *scsc_area;
+	} *scsc_area;
 
 	spin_lock_irqsave(&chsc_page_lock, flags);
 	memset(chsc_page, 0, PAGE_SIZE);
@@ -1236,7 +1236,7 @@ int chsc_sstpc(void *page, unsigned int op, u16 ctrl, u64 *clock_delta)
 		unsigned int rsvd3[3];
 		u64 clock_delta;
 		unsigned int rsvd4[2];
-	} __attribute__ ((packed)) *rr;
+	} *rr;
 	int rc;
 
 	memset(page, 0, PAGE_SIZE);
@@ -1261,7 +1261,7 @@ int chsc_sstpi(void *page, void *result, size_t size)
 		unsigned int rsvd0[3];
 		struct chsc_header response;
 		char data[];
-	} __attribute__ ((packed)) *rr;
+	} *rr;
 	int rc;
 
 	memset(page, 0, PAGE_SIZE);
@@ -1284,7 +1284,7 @@ int chsc_siosl(struct subchannel_id schid)
 		u32 word3;
 		struct chsc_header response;
 		u32 word[11];
-	} __attribute__ ((packed)) *siosl_area;
+	} *siosl_area;
 	unsigned long flags;
 	int ccode;
 	int rc;
diff --git a/drivers/s390/cio/chsc.h b/drivers/s390/cio/chsc.h
index 5c9f0dd33f4e..78aba8d94eec 100644
--- a/drivers/s390/cio/chsc.h
+++ b/drivers/s390/cio/chsc.h
@@ -15,12 +15,12 @@
 #define NR_MEASUREMENT_CHARS 5
 struct cmg_chars {
 	u32 values[NR_MEASUREMENT_CHARS];
-} __attribute__ ((packed));
+};
 
 #define NR_MEASUREMENT_ENTRIES 8
 struct cmg_entry {
 	u32 values[NR_MEASUREMENT_ENTRIES];
-} __attribute__ ((packed));
+};
 
 struct channel_path_desc_fmt1 {
 	u8 flags;
@@ -38,7 +38,7 @@ struct channel_path_desc_fmt1 {
 	u8 s:1;
 	u8 f:1;
 	u32 zeros[2];
-} __attribute__ ((packed));
+};
 
 struct channel_path_desc_fmt3 {
 	struct channel_path_desc_fmt1 fmt1_desc;
@@ -59,7 +59,7 @@ struct css_chsc_char {
 	u32:7;
 	u32 pnso:1; /* bit 116 */
 	u32:11;
-}__attribute__((packed));
+} __packed;
 
 extern struct css_chsc_char css_chsc_characteristics;
 
@@ -82,7 +82,7 @@ struct chsc_ssqd_area {
 	struct chsc_header response;
 	u32:32;
 	struct qdio_ssqd_desc qdio_ssqd;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 struct chsc_scssc_area {
 	struct chsc_header request;
@@ -102,7 +102,7 @@ struct chsc_scssc_area {
 	u32 reserved[1004];
 	struct chsc_header response;
 	u32:32;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 struct chsc_scpd {
 	struct chsc_header request;
@@ -120,7 +120,7 @@ struct chsc_scpd {
 	struct chsc_header response;
 	u32:32;
 	u8 data[0];
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 struct chsc_sda_area {
 	struct chsc_header request;
@@ -199,7 +199,7 @@ struct chsc_scm_info {
 	u32 reserved2[10];
 	u64 restok;
 	struct sale scmal[248];
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 int chsc_scm_info(struct chsc_scm_info *scm_area, u64 token);
 
@@ -243,7 +243,7 @@ struct chsc_pnso_area {
 		struct qdio_brinfo_entry_l3_ipv4 l3_ipv4[0];
 		struct qdio_brinfo_entry_l2	 l2[0];
 	} entries;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 int chsc_pnso_brinfo(struct subchannel_id schid,
 		struct chsc_pnso_area *brinfo_area,
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index 5130d7c67239..de744ca158fd 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -526,76 +526,6 @@ int cio_disable_subchannel(struct subchannel *sch)
 }
 EXPORT_SYMBOL_GPL(cio_disable_subchannel);
 
-static int cio_check_devno_blacklisted(struct subchannel *sch)
-{
-	if (is_blacklisted(sch->schid.ssid, sch->schib.pmcw.dev)) {
-		/*
-		 * This device must not be known to Linux. So we simply
-		 * say that there is no device and return ENODEV.
-		 */
-		CIO_MSG_EVENT(6, "Blacklisted device detected "
-			      "at devno %04X, subchannel set %x\n",
-			      sch->schib.pmcw.dev, sch->schid.ssid);
-		return -ENODEV;
-	}
-	return 0;
-}
-
-/**
- * cio_validate_subchannel - basic validation of subchannel
- * @sch: subchannel structure to be filled out
- * @schid: subchannel id
- *
- * Find out subchannel type and initialize struct subchannel.
- * Return codes:
- *   0 on success
- *   -ENXIO for non-defined subchannels
- *   -ENODEV for invalid subchannels or blacklisted devices
- *   -EIO for subchannels in an invalid subchannel set
- */
-int cio_validate_subchannel(struct subchannel *sch, struct subchannel_id schid)
-{
-	char dbf_txt[15];
-	int ccode;
-	int err;
-
-	sprintf(dbf_txt, "valsch%x", schid.sch_no);
-	CIO_TRACE_EVENT(4, dbf_txt);
-
-	/*
-	 * The first subchannel that is not-operational (ccode==3)
-	 * indicates that there aren't any more devices available.
-	 * If stsch gets an exception, it means the current subchannel set
-	 * is not valid.
-	 */
-	ccode = stsch(schid, &sch->schib);
-	if (ccode) {
-		err = (ccode == 3) ? -ENXIO : ccode;
-		goto out;
-	}
-	sch->st = sch->schib.pmcw.st;
-	sch->schid = schid;
-
-	switch (sch->st) {
-	case SUBCHANNEL_TYPE_IO:
-	case SUBCHANNEL_TYPE_MSG:
-		if (!css_sch_is_valid(&sch->schib))
-			err = -ENODEV;
-		else
-			err = cio_check_devno_blacklisted(sch);
-		break;
-	default:
-		err = 0;
-	}
-	if (err)
-		goto out;
-
-	CIO_MSG_EVENT(4, "Subchannel 0.%x.%04x reports subchannel type %04X\n",
-		      sch->schid.ssid, sch->schid.sch_no, sch->st);
-out:
-	return err;
-}
-
 /*
  * do_cio_interrupt() handles all normal I/O device IRQ's
  */
@@ -719,6 +649,7 @@ struct subchannel *cio_probe_console(void)
 {
 	struct subchannel_id schid;
 	struct subchannel *sch;
+	struct schib schib;
 	int sch_no, ret;
 
 	sch_no = cio_get_console_sch_no();
@@ -728,7 +659,11 @@ struct subchannel *cio_probe_console(void)
 	}
 	init_subchannel_id(&schid);
 	schid.sch_no = sch_no;
-	sch = css_alloc_subchannel(schid);
+	ret = stsch(schid, &schib);
+	if (ret)
+		return ERR_PTR(-ENODEV);
+
+	sch = css_alloc_subchannel(schid, &schib);
 	if (IS_ERR(sch))
 		return sch;
 
diff --git a/drivers/s390/cio/cio.h b/drivers/s390/cio/cio.h
index 94cd813bdcfe..9811fd8a0c73 100644
--- a/drivers/s390/cio/cio.h
+++ b/drivers/s390/cio/cio.h
@@ -119,7 +119,6 @@ DECLARE_PER_CPU(struct irb, cio_irb);
 
 #define to_subchannel(n) container_of(n, struct subchannel, dev)
 
-extern int cio_validate_subchannel (struct subchannel *, struct subchannel_id);
 extern int cio_enable_subchannel(struct subchannel *, u32);
 extern int cio_disable_subchannel (struct subchannel *);
 extern int cio_cancel (struct subchannel *);
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index 9263a0fb3858..aea502922646 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -25,6 +25,7 @@
 
 #include "css.h"
 #include "cio.h"
+#include "blacklist.h"
 #include "cio_debug.h"
 #include "ioasm.h"
 #include "chsc.h"
@@ -168,18 +169,53 @@ static void css_subchannel_release(struct device *dev)
 	kfree(sch);
 }
 
-struct subchannel *css_alloc_subchannel(struct subchannel_id schid)
+static int css_validate_subchannel(struct subchannel_id schid,
+				   struct schib *schib)
+{
+	int err;
+
+	switch (schib->pmcw.st) {
+	case SUBCHANNEL_TYPE_IO:
+	case SUBCHANNEL_TYPE_MSG:
+		if (!css_sch_is_valid(schib))
+			err = -ENODEV;
+		else if (is_blacklisted(schid.ssid, schib->pmcw.dev)) {
+			CIO_MSG_EVENT(6, "Blacklisted device detected "
+				      "at devno %04X, subchannel set %x\n",
+				      schib->pmcw.dev, schid.ssid);
+			err = -ENODEV;
+		} else
+			err = 0;
+		break;
+	default:
+		err = 0;
+	}
+	if (err)
+		goto out;
+
+	CIO_MSG_EVENT(4, "Subchannel 0.%x.%04x reports subchannel type %04X\n",
+		      schid.ssid, schid.sch_no, schib->pmcw.st);
+out:
+	return err;
+}
+
+struct subchannel *css_alloc_subchannel(struct subchannel_id schid,
+					struct schib *schib)
 {
 	struct subchannel *sch;
 	int ret;
 
+	ret = css_validate_subchannel(schid, schib);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
 	sch = kzalloc(sizeof(*sch), GFP_KERNEL | GFP_DMA);
 	if (!sch)
 		return ERR_PTR(-ENOMEM);
 
-	ret = cio_validate_subchannel(sch, schid);
-	if (ret < 0)
-		goto err;
+	sch->schid = schid;
+	sch->schib = *schib;
+	sch->st = schib->pmcw.st;
 
 	ret = css_sch_create_locks(sch);
 	if (ret)
@@ -244,8 +280,7 @@ static void ssd_register_chpids(struct chsc_ssd_info *ssd)
 	for (i = 0; i < 8; i++) {
 		mask = 0x80 >> i;
 		if (ssd->path_mask & mask)
-			if (!chp_is_registered(ssd->chpid[i]))
-				chp_new(ssd->chpid[i]);
+			chp_new(ssd->chpid[i]);
 	}
 }
 
@@ -382,12 +417,12 @@ int css_register_subchannel(struct subchannel *sch)
 	return ret;
 }
 
-static int css_probe_device(struct subchannel_id schid)
+static int css_probe_device(struct subchannel_id schid, struct schib *schib)
 {
 	struct subchannel *sch;
 	int ret;
 
-	sch = css_alloc_subchannel(schid);
+	sch = css_alloc_subchannel(schid, schib);
 	if (IS_ERR(sch))
 		return PTR_ERR(sch);
 
@@ -436,23 +471,23 @@ EXPORT_SYMBOL_GPL(css_sch_is_valid);
 static int css_evaluate_new_subchannel(struct subchannel_id schid, int slow)
 {
 	struct schib schib;
+	int ccode;
 
 	if (!slow) {
 		/* Will be done on the slow path. */
 		return -EAGAIN;
 	}
-	if (stsch(schid, &schib)) {
-		/* Subchannel is not provided. */
-		return -ENXIO;
-	}
-	if (!css_sch_is_valid(&schib)) {
-		/* Unusable - ignore. */
-		return 0;
-	}
-	CIO_MSG_EVENT(4, "event: sch 0.%x.%04x, new\n", schid.ssid,
-		      schid.sch_no);
+	/*
+	 * The first subchannel that is not-operational (ccode==3)
+	 * indicates that there aren't any more devices available.
+	 * If stsch gets an exception, it means the current subchannel set
+	 * is not valid.
+	 */
+	ccode = stsch(schid, &schib);
+	if (ccode)
+		return (ccode == 3) ? -ENXIO : ccode;
 
-	return css_probe_device(schid);
+	return css_probe_device(schid, &schib);
 }
 
 static int css_evaluate_known_subchannel(struct subchannel *sch, int slow)
@@ -1081,6 +1116,11 @@ static int __init channel_subsystem_init(void)
 	if (ret)
 		goto out_wq;
 
+	/* Register subchannels which are already in use. */
+	cio_register_early_subchannels();
+	/* Start initial subchannel evaluation. */
+	css_schedule_eval_all();
+
 	return ret;
 out_wq:
 	destroy_workqueue(cio_work_q);
@@ -1120,10 +1160,6 @@ int css_complete_work(void)
  */
 static int __init channel_subsystem_init_sync(void)
 {
-	/* Register subchannels which are already in use. */
-	cio_register_early_subchannels();
-	/* Start initial subchannel evaluation. */
-	css_schedule_eval_all();
 	css_complete_work();
 	return 0;
 }
diff --git a/drivers/s390/cio/css.h b/drivers/s390/cio/css.h
index 30357cbf350a..8d832900a63d 100644
--- a/drivers/s390/cio/css.h
+++ b/drivers/s390/cio/css.h
@@ -103,7 +103,8 @@ extern void css_driver_unregister(struct css_driver *);
 
 extern void css_sch_device_unregister(struct subchannel *);
 extern int css_register_subchannel(struct subchannel *);
-extern struct subchannel *css_alloc_subchannel(struct subchannel_id);
+extern struct subchannel *css_alloc_subchannel(struct subchannel_id,
+					       struct schib *schib);
 extern struct subchannel *get_subchannel_by_schid(struct subchannel_id);
 extern int css_init_done;
 extern int max_ssid;
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index f4ca72dd862f..9c7d9da42ba0 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -631,21 +631,20 @@ static inline unsigned long qdio_aob_for_buffer(struct qdio_output_q *q,
 	unsigned long phys_aob = 0;
 
 	if (!q->use_cq)
-		goto out;
+		return 0;
 
 	if (!q->aobs[bufnr]) {
 		struct qaob *aob = qdio_allocate_aob();
 		q->aobs[bufnr] = aob;
 	}
 	if (q->aobs[bufnr]) {
-		q->sbal_state[bufnr].flags = QDIO_OUTBUF_STATE_FLAG_NONE;
 		q->sbal_state[bufnr].aob = q->aobs[bufnr];
 		q->aobs[bufnr]->user1 = (u64) q->sbal_state[bufnr].user;
 		phys_aob = virt_to_phys(q->aobs[bufnr]);
 		WARN_ON_ONCE(phys_aob & 0xFF);
 	}
 
-out:
+	q->sbal_state[bufnr].flags = 0;
 	return phys_aob;
 }
 
diff --git a/drivers/s390/cio/trace.h b/drivers/s390/cio/trace.h
index 1f8d1c1e566d..0ebb29b6fd6d 100644
--- a/drivers/s390/cio/trace.h
+++ b/drivers/s390/cio/trace.h
@@ -30,6 +30,17 @@ DECLARE_EVENT_CLASS(s390_class_schib,
 		__field(u16, schno)
 		__field(u16, devno)
 		__field_struct(struct schib, schib)
+		__field(u8, pmcw_ena)
+		__field(u8, pmcw_st)
+		__field(u8, pmcw_dnv)
+		__field(u16, pmcw_dev)
+		__field(u8, pmcw_lpm)
+		__field(u8, pmcw_pnom)
+		__field(u8, pmcw_lpum)
+		__field(u8, pmcw_pim)
+		__field(u8, pmcw_pam)
+		__field(u8, pmcw_pom)
+		__field(u64, pmcw_chpid)
 		__field(int, cc)
 	),
 	TP_fast_assign(
@@ -38,18 +49,29 @@ DECLARE_EVENT_CLASS(s390_class_schib,
 		__entry->schno = schid.sch_no;
 		__entry->devno = schib->pmcw.dev;
 		__entry->schib = *schib;
+		__entry->pmcw_ena = schib->pmcw.ena;
+		__entry->pmcw_st = schib->pmcw.ena;
+		__entry->pmcw_dnv = schib->pmcw.dnv;
+		__entry->pmcw_dev = schib->pmcw.dev;
+		__entry->pmcw_lpm = schib->pmcw.lpm;
+		__entry->pmcw_pnom = schib->pmcw.pnom;
+		__entry->pmcw_lpum = schib->pmcw.lpum;
+		__entry->pmcw_pim = schib->pmcw.pim;
+		__entry->pmcw_pam = schib->pmcw.pam;
+		__entry->pmcw_pom = schib->pmcw.pom;
+		memcpy(&__entry->pmcw_chpid, &schib->pmcw.chpid, 8);
 		__entry->cc = cc;
 	),
 	TP_printk("schid=%x.%x.%04x cc=%d ena=%d st=%d dnv=%d dev=%04x "
 		  "lpm=0x%02x pnom=0x%02x lpum=0x%02x pim=0x%02x pam=0x%02x "
 		  "pom=0x%02x chpids=%016llx",
 		  __entry->cssid, __entry->ssid, __entry->schno, __entry->cc,
-		  __entry->schib.pmcw.ena, __entry->schib.pmcw.st,
-		  __entry->schib.pmcw.dnv, __entry->schib.pmcw.dev,
-		  __entry->schib.pmcw.lpm, __entry->schib.pmcw.pnom,
-		  __entry->schib.pmcw.lpum, __entry->schib.pmcw.pim,
-		  __entry->schib.pmcw.pam, __entry->schib.pmcw.pom,
-		  *((u64 *) __entry->schib.pmcw.chpid)
+		  __entry->pmcw_ena, __entry->pmcw_st,
+		  __entry->pmcw_dnv, __entry->pmcw_dev,
+		  __entry->pmcw_lpm, __entry->pmcw_pnom,
+		  __entry->pmcw_lpum, __entry->pmcw_pim,
+		  __entry->pmcw_pam, __entry->pmcw_pom,
+		  __entry->pmcw_chpid
 	)
 );
 
@@ -89,6 +111,13 @@ TRACE_EVENT(s390_cio_tsch,
 		__field(u8, ssid)
 		__field(u16, schno)
 		__field_struct(struct irb, irb)
+		__field(u8, scsw_dcc)
+		__field(u8, scsw_pno)
+		__field(u8, scsw_fctl)
+		__field(u8, scsw_actl)
+		__field(u8, scsw_stctl)
+		__field(u8, scsw_dstat)
+		__field(u8, scsw_cstat)
 		__field(int, cc)
 	),
 	TP_fast_assign(
@@ -96,15 +125,22 @@ TRACE_EVENT(s390_cio_tsch,
 		__entry->ssid = schid.ssid;
 		__entry->schno = schid.sch_no;
 		__entry->irb = *irb;
+		__entry->scsw_dcc = scsw_cc(&irb->scsw);
+		__entry->scsw_pno = scsw_pno(&irb->scsw);
+		__entry->scsw_fctl = scsw_fctl(&irb->scsw);
+		__entry->scsw_actl = scsw_actl(&irb->scsw);
+		__entry->scsw_stctl = scsw_stctl(&irb->scsw);
+		__entry->scsw_dstat = scsw_dstat(&irb->scsw);
+		__entry->scsw_cstat = scsw_cstat(&irb->scsw);
 		__entry->cc = cc;
 	),
 	TP_printk("schid=%x.%x.%04x cc=%d dcc=%d pno=%d fctl=0x%x actl=0x%x "
 		  "stctl=0x%x dstat=0x%x cstat=0x%x",
 		  __entry->cssid, __entry->ssid, __entry->schno, __entry->cc,
-		  scsw_cc(&__entry->irb.scsw), scsw_pno(&__entry->irb.scsw),
-		  scsw_fctl(&__entry->irb.scsw), scsw_actl(&__entry->irb.scsw),
-		  scsw_stctl(&__entry->irb.scsw),
-		  scsw_dstat(&__entry->irb.scsw), scsw_cstat(&__entry->irb.scsw)
+		  __entry->scsw_dcc, __entry->scsw_pno,
+		  __entry->scsw_fctl, __entry->scsw_actl,
+		  __entry->scsw_stctl,
+		  __entry->scsw_dstat, __entry->scsw_cstat
 	)
 );
 
@@ -122,6 +158,9 @@ TRACE_EVENT(s390_cio_tpi,
 		__field(u8, cssid)
 		__field(u8, ssid)
 		__field(u16, schno)
+		__field(u8, adapter_IO)
+		__field(u8, isc)
+		__field(u8, type)
 	),
 	TP_fast_assign(
 		__entry->cc = cc;
@@ -136,11 +175,14 @@ TRACE_EVENT(s390_cio_tpi,
 		__entry->cssid = __entry->tpi_info.schid.cssid;
 		__entry->ssid = __entry->tpi_info.schid.ssid;
 		__entry->schno = __entry->tpi_info.schid.sch_no;
+		__entry->adapter_IO = __entry->tpi_info.adapter_IO;
+		__entry->isc = __entry->tpi_info.isc;
+		__entry->type = __entry->tpi_info.type;
 	),
 	TP_printk("schid=%x.%x.%04x cc=%d a=%d isc=%d type=%d",
 		  __entry->cssid, __entry->ssid, __entry->schno, __entry->cc,
-		  __entry->tpi_info.adapter_IO, __entry->tpi_info.isc,
-		  __entry->tpi_info.type
+		  __entry->adapter_IO, __entry->isc,
+		  __entry->type
 	)
 );
 
@@ -299,16 +341,20 @@ TRACE_EVENT(s390_cio_interrupt,
 		__field(u8, cssid)
 		__field(u8, ssid)
 		__field(u16, schno)
+		__field(u8, isc)
+		__field(u8, type)
 	),
 	TP_fast_assign(
 		__entry->tpi_info = *tpi_info;
-		__entry->cssid = __entry->tpi_info.schid.cssid;
-		__entry->ssid = __entry->tpi_info.schid.ssid;
-		__entry->schno = __entry->tpi_info.schid.sch_no;
+		__entry->cssid = tpi_info->schid.cssid;
+		__entry->ssid = tpi_info->schid.ssid;
+		__entry->schno = tpi_info->schid.sch_no;
+		__entry->isc = tpi_info->isc;
+		__entry->type = tpi_info->type;
 	),
 	TP_printk("schid=%x.%x.%04x isc=%d type=%d",
 		  __entry->cssid, __entry->ssid, __entry->schno,
-		  __entry->tpi_info.isc, __entry->tpi_info.type
+		  __entry->isc, __entry->type
 	)
 );
 
@@ -321,11 +367,13 @@ TRACE_EVENT(s390_cio_adapter_int,
 	TP_ARGS(tpi_info),
 	TP_STRUCT__entry(
 		__field_struct(struct tpi_info, tpi_info)
+		__field(u8, isc)
 	),
 	TP_fast_assign(
 		__entry->tpi_info = *tpi_info;
+		__entry->isc = tpi_info->isc;
 	),
-	TP_printk("isc=%d", __entry->tpi_info.isc)
+	TP_printk("isc=%d", __entry->isc)
 );
 
 /**
@@ -339,16 +387,30 @@ TRACE_EVENT(s390_cio_stcrw,
 	TP_STRUCT__entry(
 		__field_struct(struct crw, crw)
 		__field(int, cc)
+		__field(u8, slct)
+		__field(u8, oflw)
+		__field(u8, chn)
+		__field(u8, rsc)
+		__field(u8, anc)
+		__field(u8, erc)
+		__field(u16, rsid)
 	),
 	TP_fast_assign(
 		__entry->crw = *crw;
 		__entry->cc = cc;
+		__entry->slct = crw->slct;
+		__entry->oflw = crw->oflw;
+		__entry->chn = crw->chn;
+		__entry->rsc = crw->rsc;
+		__entry->anc = crw->anc;
+		__entry->erc = crw->erc;
+		__entry->rsid = crw->rsid;
 	),
 	TP_printk("cc=%d slct=%d oflw=%d chn=%d rsc=%d anc=%d erc=0x%x "
 		  "rsid=0x%x",
-		  __entry->cc, __entry->crw.slct, __entry->crw.oflw,
-		  __entry->crw.chn, __entry->crw.rsc,  __entry->crw.anc,
-		  __entry->crw.erc, __entry->crw.rsid
+		  __entry->cc, __entry->slct, __entry->oflw,
+		  __entry->chn, __entry->rsc,  __entry->anc,
+		  __entry->erc, __entry->rsid
 	)
 );
 
diff --git a/drivers/s390/crypto/ap_asm.h b/drivers/s390/crypto/ap_asm.h
deleted file mode 100644
index 16b59ce5e01d..000000000000
--- a/drivers/s390/crypto/ap_asm.h
+++ /dev/null
@@ -1,236 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright IBM Corp. 2016
- * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- *
- * Adjunct processor bus inline assemblies.
- */
-
-#ifndef _AP_ASM_H_
-#define _AP_ASM_H_
-
-#include <asm/isc.h>
-
-/**
- * ap_intructions_available() - Test if AP instructions are available.
- *
- * Returns 0 if the AP instructions are installed.
- */
-static inline int ap_instructions_available(void)
-{
-	register unsigned long reg0 asm ("0") = AP_MKQID(0, 0);
-	register unsigned long reg1 asm ("1") = -ENODEV;
-	register unsigned long reg2 asm ("2") = 0UL;
-
-	asm volatile(
-		"   .long 0xb2af0000\n"		/* PQAP(TAPQ) */
-		"0: la    %1,0\n"
-		"1:\n"
-		EX_TABLE(0b, 1b)
-		: "+d" (reg0), "+d" (reg1), "+d" (reg2) : : "cc");
-	return reg1;
-}
-
-/**
- * ap_tapq(): Test adjunct processor queue.
- * @qid: The AP queue number
- * @info: Pointer to queue descriptor
- *
- * Returns AP queue status structure.
- */
-static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info)
-{
-	register unsigned long reg0 asm ("0") = qid;
-	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm ("2") = 0UL;
-
-	asm volatile(".long 0xb2af0000"		/* PQAP(TAPQ) */
-		     : "+d" (reg0), "=d" (reg1), "+d" (reg2) : : "cc");
-	if (info)
-		*info = reg2;
-	return reg1;
-}
-
-/**
- * ap_pqap_rapq(): Reset adjunct processor queue.
- * @qid: The AP queue number
- *
- * Returns AP queue status structure.
- */
-static inline struct ap_queue_status ap_rapq(ap_qid_t qid)
-{
-	register unsigned long reg0 asm ("0") = qid | 0x01000000UL;
-	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm ("2") = 0UL;
-
-	asm volatile(
-		".long 0xb2af0000"		/* PQAP(RAPQ) */
-		: "+d" (reg0), "=d" (reg1), "+d" (reg2) : : "cc");
-	return reg1;
-}
-
-/**
- * ap_aqic(): Control interruption for a specific AP.
- * @qid: The AP queue number
- * @qirqctrl: struct ap_qirq_ctrl (64 bit value)
- * @ind: The notification indicator byte
- *
- * Returns AP queue status.
- */
-static inline struct ap_queue_status ap_aqic(ap_qid_t qid,
-					     struct ap_qirq_ctrl qirqctrl,
-					     void *ind)
-{
-	register unsigned long reg0 asm ("0") = qid | (3UL << 24);
-	register struct ap_qirq_ctrl reg1_in asm ("1") = qirqctrl;
-	register struct ap_queue_status reg1_out asm ("1");
-	register void *reg2 asm ("2") = ind;
-
-	asm volatile(
-		".long 0xb2af0000"		/* PQAP(AQIC) */
-		: "+d" (reg0), "+d" (reg1_in), "=d" (reg1_out), "+d" (reg2)
-		:
-		: "cc");
-	return reg1_out;
-}
-
-/**
- * ap_qci(): Get AP configuration data
- *
- * Returns 0 on success, or -EOPNOTSUPP.
- */
-static inline int ap_qci(void *config)
-{
-	register unsigned long reg0 asm ("0") = 0x04000000UL;
-	register unsigned long reg1 asm ("1") = -EINVAL;
-	register void *reg2 asm ("2") = (void *) config;
-
-	asm volatile(
-		".long 0xb2af0000\n"		/* PQAP(QCI) */
-		"0: la    %1,0\n"
-		"1:\n"
-		EX_TABLE(0b, 1b)
-		: "+d" (reg0), "+d" (reg1), "+d" (reg2)
-		:
-		: "cc", "memory");
-
-	return reg1;
-}
-
-/*
- * union ap_qact_ap_info - used together with the
- * ap_aqic() function to provide a convenient way
- * to handle the ap info needed by the qact function.
- */
-union ap_qact_ap_info {
-	unsigned long val;
-	struct {
-		unsigned int	  : 3;
-		unsigned int mode : 3;
-		unsigned int	  : 26;
-		unsigned int cat  : 8;
-		unsigned int	  : 8;
-		unsigned char ver[2];
-	};
-};
-
-/**
- * ap_qact(): Query AP combatibility type.
- * @qid: The AP queue number
- * @apinfo: On input the info about the AP queue. On output the
- *	    alternate AP queue info provided by the qact function
- *	    in GR2 is stored in.
- *
- * Returns AP queue status. Check response_code field for failures.
- */
-static inline struct ap_queue_status ap_qact(ap_qid_t qid, int ifbit,
-					     union ap_qact_ap_info *apinfo)
-{
-	register unsigned long reg0 asm ("0") = qid | (5UL << 24)
-		| ((ifbit & 0x01) << 22);
-	register unsigned long reg1_in asm ("1") = apinfo->val;
-	register struct ap_queue_status reg1_out asm ("1");
-	register unsigned long reg2 asm ("2") = 0;
-
-	asm volatile(
-		".long 0xb2af0000"		/* PQAP(QACT) */
-		: "+d" (reg0), "+d" (reg1_in), "=d" (reg1_out), "+d" (reg2)
-		: : "cc");
-	apinfo->val = reg2;
-	return reg1_out;
-}
-
-/**
- * ap_nqap(): Send message to adjunct processor queue.
- * @qid: The AP queue number
- * @psmid: The program supplied message identifier
- * @msg: The message text
- * @length: The message length
- *
- * Returns AP queue status structure.
- * Condition code 1 on NQAP can't happen because the L bit is 1.
- * Condition code 2 on NQAP also means the send is incomplete,
- * because a segment boundary was reached. The NQAP is repeated.
- */
-static inline struct ap_queue_status ap_nqap(ap_qid_t qid,
-					     unsigned long long psmid,
-					     void *msg, size_t length)
-{
-	register unsigned long reg0 asm ("0") = qid | 0x40000000UL;
-	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm ("2") = (unsigned long) msg;
-	register unsigned long reg3 asm ("3") = (unsigned long) length;
-	register unsigned long reg4 asm ("4") = (unsigned int) (psmid >> 32);
-	register unsigned long reg5 asm ("5") = psmid & 0xffffffff;
-
-	asm volatile (
-		"0: .long 0xb2ad0042\n"		/* NQAP */
-		"   brc   2,0b"
-		: "+d" (reg0), "=d" (reg1), "+d" (reg2), "+d" (reg3)
-		: "d" (reg4), "d" (reg5)
-		: "cc", "memory");
-	return reg1;
-}
-
-/**
- * ap_dqap(): Receive message from adjunct processor queue.
- * @qid: The AP queue number
- * @psmid: Pointer to program supplied message identifier
- * @msg: The message text
- * @length: The message length
- *
- * Returns AP queue status structure.
- * Condition code 1 on DQAP means the receive has taken place
- * but only partially.	The response is incomplete, hence the
- * DQAP is repeated.
- * Condition code 2 on DQAP also means the receive is incomplete,
- * this time because a segment boundary was reached. Again, the
- * DQAP is repeated.
- * Note that gpr2 is used by the DQAP instruction to keep track of
- * any 'residual' length, in case the instruction gets interrupted.
- * Hence it gets zeroed before the instruction.
- */
-static inline struct ap_queue_status ap_dqap(ap_qid_t qid,
-					     unsigned long long *psmid,
-					     void *msg, size_t length)
-{
-	register unsigned long reg0 asm("0") = qid | 0x80000000UL;
-	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm("2") = 0UL;
-	register unsigned long reg4 asm("4") = (unsigned long) msg;
-	register unsigned long reg5 asm("5") = (unsigned long) length;
-	register unsigned long reg6 asm("6") = 0UL;
-	register unsigned long reg7 asm("7") = 0UL;
-
-
-	asm volatile(
-		"0: .long 0xb2ae0064\n"		/* DQAP */
-		"   brc   6,0b\n"
-		: "+d" (reg0), "=d" (reg1), "+d" (reg2),
-		  "+d" (reg4), "+d" (reg5), "+d" (reg6), "+d" (reg7)
-		: : "cc", "memory");
-	*psmid = (((unsigned long long) reg6) << 32) + reg7;
-	return reg1;
-}
-
-#endif /* _AP_ASM_H_ */
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 35a0c2b52f82..bf27fc4d1335 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -36,7 +36,6 @@
 #include <linux/debugfs.h>
 
 #include "ap_bus.h"
-#include "ap_asm.h"
 #include "ap_debug.h"
 
 /*
@@ -174,24 +173,6 @@ static inline int ap_qact_available(void)
 	return 0;
 }
 
-/**
- * ap_test_queue(): Test adjunct processor queue.
- * @qid: The AP queue number
- * @tbit: Test facilities bit
- * @info: Pointer to queue descriptor
- *
- * Returns AP queue status structure.
- */
-struct ap_queue_status ap_test_queue(ap_qid_t qid,
-				     int tbit,
-				     unsigned long *info)
-{
-	if (tbit)
-		qid |= 1UL << 23; /* set T bit*/
-	return ap_tapq(qid, info);
-}
-EXPORT_SYMBOL(ap_test_queue);
-
 /*
  * ap_query_configuration(): Fetch cryptographic config info
  *
@@ -200,7 +181,7 @@ EXPORT_SYMBOL(ap_test_queue);
  * is returned, e.g. if the PQAP(QCI) instruction is not
  * available, the return value will be -EOPNOTSUPP.
  */
-int ap_query_configuration(struct ap_config_info *info)
+static inline int ap_query_configuration(struct ap_config_info *info)
 {
 	if (!ap_configuration_available())
 		return -EOPNOTSUPP;
@@ -493,7 +474,7 @@ static int ap_poll_thread_start(void)
 		return 0;
 	mutex_lock(&ap_poll_thread_mutex);
 	ap_poll_kthread = kthread_run(ap_poll_thread, NULL, "appoll");
-	rc = PTR_RET(ap_poll_kthread);
+	rc = PTR_ERR_OR_ZERO(ap_poll_kthread);
 	if (rc)
 		ap_poll_kthread = NULL;
 	mutex_unlock(&ap_poll_thread_mutex);
@@ -1261,7 +1242,7 @@ static int __init ap_module_init(void)
 
 	/* Create /sys/devices/ap. */
 	ap_root_device = root_device_register("ap");
-	rc = PTR_RET(ap_root_device);
+	rc = PTR_ERR_OR_ZERO(ap_root_device);
 	if (rc)
 		goto out_bus;
 
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index 6a273c5ebca5..936541937e15 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -15,6 +15,7 @@
 
 #include <linux/device.h>
 #include <linux/types.h>
+#include <asm/isc.h>
 #include <asm/ap.h>
 
 #define AP_DEVICES 256		/* Number of AP devices. */
diff --git a/drivers/s390/crypto/ap_card.c b/drivers/s390/crypto/ap_card.c
index 2c726df210f6..c13e43292cb7 100644
--- a/drivers/s390/crypto/ap_card.c
+++ b/drivers/s390/crypto/ap_card.c
@@ -14,7 +14,6 @@
 #include <asm/facility.h>
 
 #include "ap_bus.h"
-#include "ap_asm.h"
 
 /*
  * AP card related attributes.
diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c
index ba3a2e13b0eb..e365171fe28f 100644
--- a/drivers/s390/crypto/ap_queue.c
+++ b/drivers/s390/crypto/ap_queue.c
@@ -14,26 +14,6 @@
 #include <asm/facility.h>
 
 #include "ap_bus.h"
-#include "ap_asm.h"
-
-/**
- * ap_queue_irq_ctrl(): Control interruption on a AP queue.
- * @qirqctrl: struct ap_qirq_ctrl (64 bit value)
- * @ind: The notification indicator byte
- *
- * Returns AP queue status.
- *
- * Control interruption on the given AP queue.
- * Just a simple wrapper function for the low level PQAP(AQIC)
- * instruction available for other kernel modules.
- */
-struct ap_queue_status ap_queue_irq_ctrl(ap_qid_t qid,
-					 struct ap_qirq_ctrl qirqctrl,
-					 void *ind)
-{
-	return ap_aqic(qid, qirqctrl, ind);
-}
-EXPORT_SYMBOL(ap_queue_irq_ctrl);
 
 /**
  * ap_queue_enable_interruption(): Enable interruption on an AP queue.
diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c
index 3929c8be8098..e663432395c1 100644
--- a/drivers/s390/crypto/pkey_api.c
+++ b/drivers/s390/crypto/pkey_api.c
@@ -699,7 +699,7 @@ static int query_crypto_facility(u16 cardnr, u16 domain,
 	/* fill request cprb param block with FQ request */
 	preqparm = (struct fqreqparm *) preqcblk->req_parmb;
 	memcpy(preqparm->subfunc_code, "FQ", 2);
-	strncpy(preqparm->rule_array, keyword, sizeof(preqparm->rule_array));
+	memcpy(preqparm->rule_array, keyword, sizeof(preqparm->rule_array));
 	preqparm->rule_array_len =
 		sizeof(preqparm->rule_array_len) + sizeof(preqparm->rule_array);
 	preqparm->lv1.len = sizeof(preqparm->lv1);
diff --git a/drivers/s390/crypto/zcrypt_card.c b/drivers/s390/crypto/zcrypt_card.c
index 233e1e695208..da2c8dfd4d74 100644
--- a/drivers/s390/crypto/zcrypt_card.c
+++ b/drivers/s390/crypto/zcrypt_card.c
@@ -83,9 +83,21 @@ static ssize_t zcrypt_card_online_store(struct device *dev,
 static DEVICE_ATTR(online, 0644, zcrypt_card_online_show,
 		   zcrypt_card_online_store);
 
+static ssize_t zcrypt_card_load_show(struct device *dev,
+				     struct device_attribute *attr,
+				     char *buf)
+{
+	struct zcrypt_card *zc = to_ap_card(dev)->private;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&zc->load));
+}
+
+static DEVICE_ATTR(load, 0444, zcrypt_card_load_show, NULL);
+
 static struct attribute *zcrypt_card_attrs[] = {
 	&dev_attr_type.attr,
 	&dev_attr_online.attr,
+	&dev_attr_load.attr,
 	NULL,
 };
 
diff --git a/drivers/s390/crypto/zcrypt_cca_key.h b/drivers/s390/crypto/zcrypt_cca_key.h
index 011d61d8a4ae..1752622b95f7 100644
--- a/drivers/s390/crypto/zcrypt_cca_key.h
+++ b/drivers/s390/crypto/zcrypt_cca_key.h
@@ -99,7 +99,7 @@ struct cca_pvt_ext_CRT_sec {
  * @mex: pointer to user input data
  * @p: pointer to memory area for the key
  *
- * Returns the size of the key area or -EFAULT
+ * Returns the size of the key area or negative errno value.
  */
 static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex, void *p)
 {
@@ -118,6 +118,15 @@ static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex, void *p)
 	unsigned char *temp;
 	int i;
 
+	/*
+	 * The inputdatalength was a selection criteria in the dispatching
+	 * function zcrypt_rsa_modexpo(). However, do a plausibility check
+	 * here to make sure the following copy_from_user() can't be utilized
+	 * to compromise the system.
+	 */
+	if (WARN_ON_ONCE(mex->inputdatalength > 512))
+		return -EINVAL;
+
 	memset(key, 0, sizeof(*key));
 
 	key->pubHdr = static_pub_hdr;
@@ -178,6 +187,15 @@ static inline int zcrypt_type6_crt_key(struct ica_rsa_modexpo_crt *crt, void *p)
 	struct cca_public_sec *pub;
 	int short_len, long_len, pad_len, key_len, size;
 
+	/*
+	 * The inputdatalength was a selection criteria in the dispatching
+	 * function zcrypt_rsa_crt(). However, do a plausibility check
+	 * here to make sure the following copy_from_user() can't be utilized
+	 * to compromise the system.
+	 */
+	if (WARN_ON_ONCE(crt->inputdatalength > 512))
+		return -EINVAL;
+
 	memset(key, 0, sizeof(*key));
 
 	short_len = (crt->inputdatalength + 1) / 2;
diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c
index 97d4bacbc442..e70ae078c86b 100644
--- a/drivers/s390/crypto/zcrypt_msgtype6.c
+++ b/drivers/s390/crypto/zcrypt_msgtype6.c
@@ -246,7 +246,7 @@ int speed_idx_ep11(int req_type)
  * @ap_msg: pointer to AP message
  * @mex: pointer to user input data
  *
- * Returns 0 on success or -EFAULT.
+ * Returns 0 on success or negative errno value.
  */
 static int ICAMEX_msg_to_type6MEX_msgX(struct zcrypt_queue *zq,
 				       struct ap_message *ap_msg,
@@ -272,6 +272,14 @@ static int ICAMEX_msg_to_type6MEX_msgX(struct zcrypt_queue *zq,
 	} __packed * msg = ap_msg->message;
 	int size;
 
+	/*
+	 * The inputdatalength was a selection criteria in the dispatching
+	 * function zcrypt_rsa_modexpo(). However, make sure the following
+	 * copy_from_user() never exceeds the allocated buffer space.
+	 */
+	if (WARN_ON_ONCE(mex->inputdatalength > PAGE_SIZE))
+		return -EINVAL;
+
 	/* VUD.ciphertext */
 	msg->length = mex->inputdatalength + 2;
 	if (copy_from_user(msg->text, mex->inputdata, mex->inputdatalength))
@@ -307,7 +315,7 @@ static int ICAMEX_msg_to_type6MEX_msgX(struct zcrypt_queue *zq,
  * @ap_msg: pointer to AP message
  * @crt: pointer to user input data
  *
- * Returns 0 on success or -EFAULT.
+ * Returns 0 on success or negative errno value.
  */
 static int ICACRT_msg_to_type6CRT_msgX(struct zcrypt_queue *zq,
 				       struct ap_message *ap_msg,
@@ -334,6 +342,14 @@ static int ICACRT_msg_to_type6CRT_msgX(struct zcrypt_queue *zq,
 	} __packed * msg = ap_msg->message;
 	int size;
 
+	/*
+	 * The inputdatalength was a selection criteria in the dispatching
+	 * function zcrypt_rsa_crt(). However, make sure the following
+	 * copy_from_user() never exceeds the allocated buffer space.
+	 */
+	if (WARN_ON_ONCE(crt->inputdatalength > PAGE_SIZE))
+		return -EINVAL;
+
 	/* VUD.ciphertext */
 	msg->length = crt->inputdatalength + 2;
 	if (copy_from_user(msg->text, crt->inputdata, crt->inputdatalength))
diff --git a/drivers/s390/crypto/zcrypt_queue.c b/drivers/s390/crypto/zcrypt_queue.c
index 720434e18007..91a52f268353 100644
--- a/drivers/s390/crypto/zcrypt_queue.c
+++ b/drivers/s390/crypto/zcrypt_queue.c
@@ -75,8 +75,20 @@ static ssize_t zcrypt_queue_online_store(struct device *dev,
 static DEVICE_ATTR(online, 0644, zcrypt_queue_online_show,
 		   zcrypt_queue_online_store);
 
+static ssize_t zcrypt_queue_load_show(struct device *dev,
+				      struct device_attribute *attr,
+				      char *buf)
+{
+	struct zcrypt_queue *zq = to_ap_queue(dev)->private;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&zq->load));
+}
+
+static DEVICE_ATTR(load, 0444, zcrypt_queue_load_show, NULL);
+
 static struct attribute *zcrypt_queue_attrs[] = {
 	&dev_attr_online.attr,
+	&dev_attr_load.attr,
 	NULL,
 };
 
diff --git a/drivers/s390/net/Kconfig b/drivers/s390/net/Kconfig
index c7e484f70654..7c5a25ddf832 100644
--- a/drivers/s390/net/Kconfig
+++ b/drivers/s390/net/Kconfig
@@ -95,4 +95,14 @@ config CCWGROUP
 	tristate
 	default (LCS || CTCM || QETH)
 
+config ISM
+	tristate "Support for ISM vPCI Adapter"
+	depends on PCI && SMC
+	default n
+	help
+	  Select this option if you want to use the Internal Shared Memory
+	  vPCI Adapter.
+
+	  To compile as a module choose M. The module name is ism.
+	  If unsure, choose N.
 endmenu
diff --git a/drivers/s390/net/Makefile b/drivers/s390/net/Makefile
index 513b7ae64980..f2d6bbe57a6f 100644
--- a/drivers/s390/net/Makefile
+++ b/drivers/s390/net/Makefile
@@ -15,3 +15,6 @@ qeth_l2-y += qeth_l2_main.o qeth_l2_sys.o
 obj-$(CONFIG_QETH_L2) += qeth_l2.o
 qeth_l3-y += qeth_l3_main.o qeth_l3_sys.o
 obj-$(CONFIG_QETH_L3) += qeth_l3.o
+
+ism-y := ism_drv.o
+obj-$(CONFIG_ISM) += ism.o
diff --git a/drivers/s390/net/ism.h b/drivers/s390/net/ism.h
new file mode 100644
index 000000000000..0aab90817326
--- /dev/null
+++ b/drivers/s390/net/ism.h
@@ -0,0 +1,221 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef S390_ISM_H
+#define S390_ISM_H
+
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <net/smc.h>
+
+#define UTIL_STR_LEN	16
+
+/*
+ * Do not use the first word of the DMB bits to ensure 8 byte aligned access.
+ */
+#define ISM_DMB_WORD_OFFSET	1
+#define ISM_DMB_BIT_OFFSET	(ISM_DMB_WORD_OFFSET * 32)
+#define ISM_NR_DMBS		1920
+
+#define ISM_REG_SBA	0x1
+#define ISM_REG_IEQ	0x2
+#define ISM_READ_GID	0x3
+#define ISM_ADD_VLAN_ID	0x4
+#define ISM_DEL_VLAN_ID	0x5
+#define ISM_SET_VLAN	0x6
+#define ISM_RESET_VLAN	0x7
+#define ISM_QUERY_INFO	0x8
+#define ISM_QUERY_RGID	0x9
+#define ISM_REG_DMB	0xA
+#define ISM_UNREG_DMB	0xB
+#define ISM_SIGNAL_IEQ	0xE
+#define ISM_UNREG_SBA	0x11
+#define ISM_UNREG_IEQ	0x12
+
+#define ISM_ERROR	0xFFFF
+
+struct ism_req_hdr {
+	u32 cmd;
+	u16 : 16;
+	u16 len;
+};
+
+struct ism_resp_hdr {
+	u32 cmd;
+	u16 ret;
+	u16 len;
+};
+
+union ism_reg_sba {
+	struct {
+		struct ism_req_hdr hdr;
+		u64 sba;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+	} response;
+} __aligned(16);
+
+union ism_reg_ieq {
+	struct {
+		struct ism_req_hdr hdr;
+		u64 ieq;
+		u64 len;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+	} response;
+} __aligned(16);
+
+union ism_read_gid {
+	struct {
+		struct ism_req_hdr hdr;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+		u64 gid;
+	} response;
+} __aligned(16);
+
+union ism_qi {
+	struct {
+		struct ism_req_hdr hdr;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+		u32 version;
+		u32 max_len;
+		u64 ism_state;
+		u64 my_gid;
+		u64 sba;
+		u64 ieq;
+		u32 ieq_len;
+		u32 : 32;
+		u32 dmbs_owned;
+		u32 dmbs_used;
+		u32 vlan_required;
+		u32 vlan_nr_ids;
+		u16 vlan_id[64];
+	} response;
+} __aligned(64);
+
+union ism_query_rgid {
+	struct {
+		struct ism_req_hdr hdr;
+		u64 rgid;
+		u32 vlan_valid;
+		u32 vlan_id;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+	} response;
+} __aligned(16);
+
+union ism_reg_dmb {
+	struct {
+		struct ism_req_hdr hdr;
+		u64 dmb;
+		u32 dmb_len;
+		u32 sba_idx;
+		u32 vlan_valid;
+		u32 vlan_id;
+		u64 rgid;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+		u64 dmb_tok;
+	} response;
+} __aligned(32);
+
+union ism_sig_ieq {
+	struct {
+		struct ism_req_hdr hdr;
+		u64 rgid;
+		u32 trigger_irq;
+		u32 event_code;
+		u64 info;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+	} response;
+} __aligned(32);
+
+union ism_unreg_dmb {
+	struct {
+		struct ism_req_hdr hdr;
+		u64 dmb_tok;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+	} response;
+} __aligned(16);
+
+union ism_cmd_simple {
+	struct {
+		struct ism_req_hdr hdr;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+	} response;
+} __aligned(8);
+
+union ism_set_vlan_id {
+	struct {
+		struct ism_req_hdr hdr;
+		u64 vlan_id;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+	} response;
+} __aligned(16);
+
+struct ism_eq_header {
+	u64 idx;
+	u64 ieq_len;
+	u64 entry_len;
+	u64 : 64;
+};
+
+struct ism_eq {
+	struct ism_eq_header header;
+	struct smcd_event entry[15];
+};
+
+struct ism_sba {
+	u32 s : 1;	/* summary bit */
+	u32 e : 1;	/* event bit */
+	u32 : 30;
+	u32 dmb_bits[ISM_NR_DMBS / 32];
+	u32 reserved[3];
+	u16 dmbe_mask[ISM_NR_DMBS];
+};
+
+struct ism_dev {
+	spinlock_t lock;
+	struct pci_dev *pdev;
+	struct smcd_dev *smcd;
+
+	void __iomem *ctl;
+
+	struct ism_sba *sba;
+	dma_addr_t sba_dma_addr;
+	DECLARE_BITMAP(sba_bitmap, ISM_NR_DMBS);
+
+	struct ism_eq *ieq;
+	dma_addr_t ieq_dma_addr;
+
+	int ieq_idx;
+};
+
+#define ISM_CREATE_REQ(dmb, idx, sf, offset)		\
+	((dmb) | (idx) << 24 | (sf) << 23 | (offset))
+
+static inline int __ism_move(struct ism_dev *ism, u64 dmb_req, void *data,
+			     unsigned int size)
+{
+	struct zpci_dev *zdev = to_zpci(ism->pdev);
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, size);
+
+	return zpci_write_block(req, data, dmb_req);
+}
+
+#endif /* S390_ISM_H */
diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
new file mode 100644
index 000000000000..c0631895154e
--- /dev/null
+++ b/drivers/s390/net/ism_drv.c
@@ -0,0 +1,623 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ISM driver for s390.
+ *
+ * Copyright IBM Corp. 2018
+ */
+#define KMSG_COMPONENT "ism"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/device.h>
+#include <linux/pci.h>
+#include <linux/err.h>
+#include <net/smc.h>
+
+#include <asm/debug.h>
+
+#include "ism.h"
+
+MODULE_DESCRIPTION("ISM driver for s390");
+MODULE_LICENSE("GPL");
+
+#define PCI_DEVICE_ID_IBM_ISM 0x04ED
+#define DRV_NAME "ism"
+
+static const struct pci_device_id ism_device_table[] = {
+	{ PCI_VDEVICE(IBM, PCI_DEVICE_ID_IBM_ISM), 0 },
+	{ 0, }
+};
+MODULE_DEVICE_TABLE(pci, ism_device_table);
+
+static debug_info_t *ism_debug_info;
+
+static int ism_cmd(struct ism_dev *ism, void *cmd)
+{
+	struct ism_req_hdr *req = cmd;
+	struct ism_resp_hdr *resp = cmd;
+
+	memcpy_toio(ism->ctl + sizeof(*req), req + 1, req->len - sizeof(*req));
+	memcpy_toio(ism->ctl, req, sizeof(*req));
+
+	WRITE_ONCE(resp->ret, ISM_ERROR);
+
+	memcpy_fromio(resp, ism->ctl, sizeof(*resp));
+	if (resp->ret) {
+		debug_text_event(ism_debug_info, 0, "cmd failure");
+		debug_event(ism_debug_info, 0, resp, sizeof(*resp));
+		goto out;
+	}
+	memcpy_fromio(resp + 1, ism->ctl + sizeof(*resp),
+		      resp->len - sizeof(*resp));
+out:
+	return resp->ret;
+}
+
+static int ism_cmd_simple(struct ism_dev *ism, u32 cmd_code)
+{
+	union ism_cmd_simple cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = cmd_code;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	return ism_cmd(ism, &cmd);
+}
+
+static int query_info(struct ism_dev *ism)
+{
+	union ism_qi cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_QUERY_INFO;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	if (ism_cmd(ism, &cmd))
+		goto out;
+
+	debug_text_event(ism_debug_info, 3, "query info");
+	debug_event(ism_debug_info, 3, &cmd.response, sizeof(cmd.response));
+out:
+	return 0;
+}
+
+static int register_sba(struct ism_dev *ism)
+{
+	union ism_reg_sba cmd;
+	dma_addr_t dma_handle;
+	struct ism_sba *sba;
+
+	sba = dma_zalloc_coherent(&ism->pdev->dev, PAGE_SIZE,
+				  &dma_handle, GFP_KERNEL);
+	if (!sba)
+		return -ENOMEM;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_REG_SBA;
+	cmd.request.hdr.len = sizeof(cmd.request);
+	cmd.request.sba = dma_handle;
+
+	if (ism_cmd(ism, &cmd)) {
+		dma_free_coherent(&ism->pdev->dev, PAGE_SIZE, sba, dma_handle);
+		return -EIO;
+	}
+
+	ism->sba = sba;
+	ism->sba_dma_addr = dma_handle;
+
+	return 0;
+}
+
+static int register_ieq(struct ism_dev *ism)
+{
+	union ism_reg_ieq cmd;
+	dma_addr_t dma_handle;
+	struct ism_eq *ieq;
+
+	ieq = dma_zalloc_coherent(&ism->pdev->dev, PAGE_SIZE,
+				  &dma_handle, GFP_KERNEL);
+	if (!ieq)
+		return -ENOMEM;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_REG_IEQ;
+	cmd.request.hdr.len = sizeof(cmd.request);
+	cmd.request.ieq = dma_handle;
+	cmd.request.len = sizeof(*ieq);
+
+	if (ism_cmd(ism, &cmd)) {
+		dma_free_coherent(&ism->pdev->dev, PAGE_SIZE, ieq, dma_handle);
+		return -EIO;
+	}
+
+	ism->ieq = ieq;
+	ism->ieq_idx = -1;
+	ism->ieq_dma_addr = dma_handle;
+
+	return 0;
+}
+
+static int unregister_sba(struct ism_dev *ism)
+{
+	if (!ism->sba)
+		return 0;
+
+	if (ism_cmd_simple(ism, ISM_UNREG_SBA))
+		return -EIO;
+
+	dma_free_coherent(&ism->pdev->dev, PAGE_SIZE,
+			  ism->sba, ism->sba_dma_addr);
+
+	ism->sba = NULL;
+	ism->sba_dma_addr = 0;
+
+	return 0;
+}
+
+static int unregister_ieq(struct ism_dev *ism)
+{
+	if (!ism->ieq)
+		return 0;
+
+	if (ism_cmd_simple(ism, ISM_UNREG_IEQ))
+		return -EIO;
+
+	dma_free_coherent(&ism->pdev->dev, PAGE_SIZE,
+			  ism->ieq, ism->ieq_dma_addr);
+
+	ism->ieq = NULL;
+	ism->ieq_dma_addr = 0;
+
+	return 0;
+}
+
+static int ism_read_local_gid(struct ism_dev *ism)
+{
+	union ism_read_gid cmd;
+	int ret;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_READ_GID;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	ret = ism_cmd(ism, &cmd);
+	if (ret)
+		goto out;
+
+	ism->smcd->local_gid = cmd.response.gid;
+out:
+	return ret;
+}
+
+static int ism_query_rgid(struct smcd_dev *smcd, u64 rgid, u32 vid_valid,
+			  u32 vid)
+{
+	struct ism_dev *ism = smcd->priv;
+	union ism_query_rgid cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_QUERY_RGID;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	cmd.request.rgid = rgid;
+	cmd.request.vlan_valid = vid_valid;
+	cmd.request.vlan_id = vid;
+
+	return ism_cmd(ism, &cmd);
+}
+
+static void ism_free_dmb(struct ism_dev *ism, struct smcd_dmb *dmb)
+{
+	clear_bit(dmb->sba_idx, ism->sba_bitmap);
+	dma_free_coherent(&ism->pdev->dev, dmb->dmb_len,
+			  dmb->cpu_addr, dmb->dma_addr);
+}
+
+static int ism_alloc_dmb(struct ism_dev *ism, struct smcd_dmb *dmb)
+{
+	unsigned long bit;
+
+	if (PAGE_ALIGN(dmb->dmb_len) > dma_get_max_seg_size(&ism->pdev->dev))
+		return -EINVAL;
+
+	if (!dmb->sba_idx) {
+		bit = find_next_zero_bit(ism->sba_bitmap, ISM_NR_DMBS,
+					 ISM_DMB_BIT_OFFSET);
+		if (bit == ISM_NR_DMBS)
+			return -ENOMEM;
+
+		dmb->sba_idx = bit;
+	}
+	if (dmb->sba_idx < ISM_DMB_BIT_OFFSET ||
+	    test_and_set_bit(dmb->sba_idx, ism->sba_bitmap))
+		return -EINVAL;
+
+	dmb->cpu_addr = dma_zalloc_coherent(&ism->pdev->dev, dmb->dmb_len,
+					    &dmb->dma_addr, GFP_KERNEL |
+					    __GFP_NOWARN | __GFP_NOMEMALLOC |
+					    __GFP_COMP | __GFP_NORETRY);
+	if (!dmb->cpu_addr)
+		clear_bit(dmb->sba_idx, ism->sba_bitmap);
+
+	return dmb->cpu_addr ? 0 : -ENOMEM;
+}
+
+static int ism_register_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb)
+{
+	struct ism_dev *ism = smcd->priv;
+	union ism_reg_dmb cmd;
+	int ret;
+
+	ret = ism_alloc_dmb(ism, dmb);
+	if (ret)
+		goto out;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_REG_DMB;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	cmd.request.dmb = dmb->dma_addr;
+	cmd.request.dmb_len = dmb->dmb_len;
+	cmd.request.sba_idx = dmb->sba_idx;
+	cmd.request.vlan_valid = dmb->vlan_valid;
+	cmd.request.vlan_id = dmb->vlan_id;
+	cmd.request.rgid = dmb->rgid;
+
+	ret = ism_cmd(ism, &cmd);
+	if (ret) {
+		ism_free_dmb(ism, dmb);
+		goto out;
+	}
+	dmb->dmb_tok = cmd.response.dmb_tok;
+out:
+	return ret;
+}
+
+static int ism_unregister_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb)
+{
+	struct ism_dev *ism = smcd->priv;
+	union ism_unreg_dmb cmd;
+	int ret;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_UNREG_DMB;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	cmd.request.dmb_tok = dmb->dmb_tok;
+
+	ret = ism_cmd(ism, &cmd);
+	if (ret)
+		goto out;
+
+	ism_free_dmb(ism, dmb);
+out:
+	return ret;
+}
+
+static int ism_add_vlan_id(struct smcd_dev *smcd, u64 vlan_id)
+{
+	struct ism_dev *ism = smcd->priv;
+	union ism_set_vlan_id cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_ADD_VLAN_ID;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	cmd.request.vlan_id = vlan_id;
+
+	return ism_cmd(ism, &cmd);
+}
+
+static int ism_del_vlan_id(struct smcd_dev *smcd, u64 vlan_id)
+{
+	struct ism_dev *ism = smcd->priv;
+	union ism_set_vlan_id cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_DEL_VLAN_ID;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	cmd.request.vlan_id = vlan_id;
+
+	return ism_cmd(ism, &cmd);
+}
+
+static int ism_set_vlan_required(struct smcd_dev *smcd)
+{
+	return ism_cmd_simple(smcd->priv, ISM_SET_VLAN);
+}
+
+static int ism_reset_vlan_required(struct smcd_dev *smcd)
+{
+	return ism_cmd_simple(smcd->priv, ISM_RESET_VLAN);
+}
+
+static int ism_signal_ieq(struct smcd_dev *smcd, u64 rgid, u32 trigger_irq,
+			  u32 event_code, u64 info)
+{
+	struct ism_dev *ism = smcd->priv;
+	union ism_sig_ieq cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_SIGNAL_IEQ;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	cmd.request.rgid = rgid;
+	cmd.request.trigger_irq = trigger_irq;
+	cmd.request.event_code = event_code;
+	cmd.request.info = info;
+
+	return ism_cmd(ism, &cmd);
+}
+
+static unsigned int max_bytes(unsigned int start, unsigned int len,
+			      unsigned int boundary)
+{
+	return min(boundary - (start & (boundary - 1)), len);
+}
+
+static int ism_move(struct smcd_dev *smcd, u64 dmb_tok, unsigned int idx,
+		    bool sf, unsigned int offset, void *data, unsigned int size)
+{
+	struct ism_dev *ism = smcd->priv;
+	unsigned int bytes;
+	u64 dmb_req;
+	int ret;
+
+	while (size) {
+		bytes = max_bytes(offset, size, PAGE_SIZE);
+		dmb_req = ISM_CREATE_REQ(dmb_tok, idx, size == bytes ? sf : 0,
+					 offset);
+
+		ret = __ism_move(ism, dmb_req, data, bytes);
+		if (ret)
+			return ret;
+
+		size -= bytes;
+		data += bytes;
+		offset += bytes;
+	}
+
+	return 0;
+}
+
+static void ism_handle_event(struct ism_dev *ism)
+{
+	struct smcd_event *entry;
+
+	while ((ism->ieq_idx + 1) != READ_ONCE(ism->ieq->header.idx)) {
+		if (++(ism->ieq_idx) == ARRAY_SIZE(ism->ieq->entry))
+			ism->ieq_idx = 0;
+
+		entry = &ism->ieq->entry[ism->ieq_idx];
+		debug_event(ism_debug_info, 2, entry, sizeof(*entry));
+		smcd_handle_event(ism->smcd, entry);
+	}
+}
+
+static irqreturn_t ism_handle_irq(int irq, void *data)
+{
+	struct ism_dev *ism = data;
+	unsigned long bit, end;
+	unsigned long *bv;
+
+	bv = (void *) &ism->sba->dmb_bits[ISM_DMB_WORD_OFFSET];
+	end = sizeof(ism->sba->dmb_bits) * BITS_PER_BYTE - ISM_DMB_BIT_OFFSET;
+
+	spin_lock(&ism->lock);
+	ism->sba->s = 0;
+	barrier();
+	for (bit = 0;;) {
+		bit = find_next_bit_inv(bv, end, bit);
+		if (bit >= end)
+			break;
+
+		clear_bit_inv(bit, bv);
+		barrier();
+		smcd_handle_irq(ism->smcd, bit + ISM_DMB_BIT_OFFSET);
+		ism->sba->dmbe_mask[bit + ISM_DMB_BIT_OFFSET] = 0;
+	}
+
+	if (ism->sba->e) {
+		ism->sba->e = 0;
+		barrier();
+		ism_handle_event(ism);
+	}
+	spin_unlock(&ism->lock);
+	return IRQ_HANDLED;
+}
+
+static const struct smcd_ops ism_ops = {
+	.query_remote_gid = ism_query_rgid,
+	.register_dmb = ism_register_dmb,
+	.unregister_dmb = ism_unregister_dmb,
+	.add_vlan_id = ism_add_vlan_id,
+	.del_vlan_id = ism_del_vlan_id,
+	.set_vlan_required = ism_set_vlan_required,
+	.reset_vlan_required = ism_reset_vlan_required,
+	.signal_event = ism_signal_ieq,
+	.move_data = ism_move,
+};
+
+static int ism_dev_init(struct ism_dev *ism)
+{
+	struct pci_dev *pdev = ism->pdev;
+	int ret;
+
+	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI);
+	if (ret <= 0)
+		goto out;
+
+	ret = request_irq(pci_irq_vector(pdev, 0), ism_handle_irq, 0,
+			  pci_name(pdev), ism);
+	if (ret)
+		goto free_vectors;
+
+	ret = register_sba(ism);
+	if (ret)
+		goto free_irq;
+
+	ret = register_ieq(ism);
+	if (ret)
+		goto unreg_sba;
+
+	ret = ism_read_local_gid(ism);
+	if (ret)
+		goto unreg_ieq;
+
+	ret = smcd_register_dev(ism->smcd);
+	if (ret)
+		goto unreg_ieq;
+
+	query_info(ism);
+	return 0;
+
+unreg_ieq:
+	unregister_ieq(ism);
+unreg_sba:
+	unregister_sba(ism);
+free_irq:
+	free_irq(pci_irq_vector(pdev, 0), ism);
+free_vectors:
+	pci_free_irq_vectors(pdev);
+out:
+	return ret;
+}
+
+static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct ism_dev *ism;
+	int ret;
+
+	ism = kzalloc(sizeof(*ism), GFP_KERNEL);
+	if (!ism)
+		return -ENOMEM;
+
+	spin_lock_init(&ism->lock);
+	dev_set_drvdata(&pdev->dev, ism);
+	ism->pdev = pdev;
+
+	ret = pci_enable_device_mem(pdev);
+	if (ret)
+		goto err;
+
+	ret = pci_request_mem_regions(pdev, DRV_NAME);
+	if (ret)
+		goto err_disable;
+
+	ism->ctl = pci_iomap(pdev, 2, 0);
+	if (!ism->ctl)
+		goto err_resource;
+
+	ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	if (ret)
+		goto err_unmap;
+
+	pci_set_dma_seg_boundary(pdev, SZ_1M - 1);
+	pci_set_dma_max_seg_size(pdev, SZ_1M);
+	pci_set_master(pdev);
+
+	ism->smcd = smcd_alloc_dev(&pdev->dev, dev_name(&pdev->dev), &ism_ops,
+				   ISM_NR_DMBS);
+	if (!ism->smcd)
+		goto err_unmap;
+
+	ism->smcd->priv = ism;
+	ret = ism_dev_init(ism);
+	if (ret)
+		goto err_free;
+
+	return 0;
+
+err_free:
+	smcd_free_dev(ism->smcd);
+err_unmap:
+	pci_iounmap(pdev, ism->ctl);
+err_resource:
+	pci_release_mem_regions(pdev);
+err_disable:
+	pci_disable_device(pdev);
+err:
+	kfree(ism);
+	dev_set_drvdata(&pdev->dev, NULL);
+	return ret;
+}
+
+static void ism_dev_exit(struct ism_dev *ism)
+{
+	struct pci_dev *pdev = ism->pdev;
+
+	smcd_unregister_dev(ism->smcd);
+	unregister_ieq(ism);
+	unregister_sba(ism);
+	free_irq(pci_irq_vector(pdev, 0), ism);
+	pci_free_irq_vectors(pdev);
+}
+
+static void ism_remove(struct pci_dev *pdev)
+{
+	struct ism_dev *ism = dev_get_drvdata(&pdev->dev);
+
+	ism_dev_exit(ism);
+
+	smcd_free_dev(ism->smcd);
+	pci_iounmap(pdev, ism->ctl);
+	pci_release_mem_regions(pdev);
+	pci_disable_device(pdev);
+	dev_set_drvdata(&pdev->dev, NULL);
+	kfree(ism);
+}
+
+static int ism_suspend(struct device *dev)
+{
+	struct ism_dev *ism = dev_get_drvdata(dev);
+
+	ism_dev_exit(ism);
+	return 0;
+}
+
+static int ism_resume(struct device *dev)
+{
+	struct ism_dev *ism = dev_get_drvdata(dev);
+
+	return ism_dev_init(ism);
+}
+
+static SIMPLE_DEV_PM_OPS(ism_pm_ops, ism_suspend, ism_resume);
+
+static struct pci_driver ism_driver = {
+	.name	  = DRV_NAME,
+	.id_table = ism_device_table,
+	.probe	  = ism_probe,
+	.remove	  = ism_remove,
+	.driver	  = {
+		.pm = &ism_pm_ops,
+	},
+};
+
+static int __init ism_init(void)
+{
+	int ret;
+
+	ism_debug_info = debug_register("ism", 2, 1, 16);
+	if (!ism_debug_info)
+		return -ENODEV;
+
+	debug_register_view(ism_debug_info, &debug_hex_ascii_view);
+	ret = pci_register_driver(&ism_driver);
+	if (ret)
+		debug_unregister(ism_debug_info);
+
+	return ret;
+}
+
+static void __exit ism_exit(void)
+{
+	pci_unregister_driver(&ism_driver);
+	debug_unregister(ism_debug_info);
+}
+
+module_init(ism_init);
+module_exit(ism_exit);
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index a246a618f9a4..34e0d476c5c6 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -104,6 +104,7 @@ struct qeth_dbf_info {
 struct qeth_perf_stats {
 	unsigned int bufs_rec;
 	unsigned int bufs_sent;
+	unsigned int buf_elements_sent;
 
 	unsigned int skbs_sent_pack;
 	unsigned int bufs_sent_pack;
@@ -137,7 +138,6 @@ struct qeth_perf_stats {
 	unsigned int large_send_bytes;
 	unsigned int large_send_cnt;
 	unsigned int sg_skbs_sent;
-	unsigned int sg_frags_sent;
 	/* initial values when measuring starts */
 	unsigned long initial_rx_packets;
 	unsigned long initial_tx_packets;
@@ -235,6 +235,8 @@ static inline int qeth_is_ipa_enabled(struct qeth_ipa_info *ipa,
 #define QETH_IDX_FUNC_LEVEL_IQD		 0x4108
 
 #define QETH_BUFSIZE		4096
+#define CCW_CMD_WRITE		0x01
+#define CCW_CMD_READ		0x02
 
 /**
  * some more defs
@@ -465,7 +467,6 @@ struct qeth_qdio_out_buffer {
 	struct sk_buff_head skb_list;
 	int is_header[QDIO_MAX_ELEMENTS_PER_BUFFER];
 
-	struct qaob *aob;
 	struct qeth_qdio_out_q *q;
 	struct qeth_qdio_out_buffer *next_pending;
 };
@@ -593,7 +594,7 @@ static inline struct qeth_ipa_cmd *__ipa_cmd(struct qeth_cmd_buffer *iob)
  */
 struct qeth_channel {
 	enum qeth_channel_states state;
-	struct ccw1 ccw;
+	struct ccw1 *ccw;
 	spinlock_t iob_lock;
 	wait_queue_head_t wait_q;
 	struct ccw_device *ccwdev;
@@ -659,12 +660,8 @@ struct qeth_card_info {
 	char mcl_level[QETH_MCL_LENGTH + 1];
 	int guestlan;
 	int mac_bits;
-	int portno;
 	enum qeth_card_types type;
 	enum qeth_link_types link_type;
-	int is_multicast_different;
-	int initial_mtu;
-	int max_mtu;
 	int broadcast_capable;
 	int unique_id;
 	bool layer_enforced;
@@ -935,6 +932,19 @@ static inline int qeth_send_simple_setassparms_v6(struct qeth_card *card,
 						 data, QETH_PROT_IPV6);
 }
 
+int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb,
+			    int ipv);
+static inline struct qeth_qdio_out_q *qeth_get_tx_queue(struct qeth_card *card,
+							struct sk_buff *skb,
+							int ipv, int cast_type)
+{
+	if (IS_IQD(card) && cast_type != RTN_UNICAST)
+		return card->qdio.out_qs[card->qdio.no_out_queues - 1];
+	if (!card->qdio.do_prio_queueing)
+		return card->qdio.out_qs[card->qdio.default_out_queue];
+	return card->qdio.out_qs[qeth_get_priority_queue(card, skb, ipv)];
+}
+
 extern struct qeth_discipline qeth_l2_discipline;
 extern struct qeth_discipline qeth_l3_discipline;
 extern const struct attribute_group *qeth_generic_attr_groups[];
@@ -955,6 +965,7 @@ extern struct qeth_card_list_struct qeth_core_card_list;
 extern struct kmem_cache *qeth_core_header_cache;
 extern struct qeth_dbf_info qeth_dbf[QETH_DBF_INFOS];
 
+struct net_device *qeth_clone_netdev(struct net_device *orig);
 void qeth_set_recovery_task(struct qeth_card *);
 void qeth_clear_recovery_task(struct qeth_card *);
 void qeth_set_allowed_threads(struct qeth_card *, unsigned long , int);
@@ -972,7 +983,6 @@ int qeth_send_ipa_cmd(struct qeth_card *, struct qeth_cmd_buffer *,
 		  void *);
 struct qeth_cmd_buffer *qeth_get_ipacmd_buffer(struct qeth_card *,
 			enum qeth_ipa_cmds, enum qeth_prot_versions);
-int qeth_query_setadapterparms(struct qeth_card *);
 struct sk_buff *qeth_core_get_next_skb(struct qeth_card *,
 		struct qeth_qdio_buffer *, struct qdio_buffer_element **, int *,
 		struct qeth_hdr **);
@@ -985,24 +995,18 @@ void qeth_clear_cmd_buffers(struct qeth_channel *);
 void qeth_clear_qdio_buffers(struct qeth_card *);
 void qeth_setadp_promisc_mode(struct qeth_card *);
 struct net_device_stats *qeth_get_stats(struct net_device *);
-int qeth_change_mtu(struct net_device *, int);
 int qeth_setadpparms_change_macaddr(struct qeth_card *);
 void qeth_tx_timeout(struct net_device *);
 void qeth_prepare_control_data(struct qeth_card *, int,
 				struct qeth_cmd_buffer *);
 void qeth_release_buffer(struct qeth_channel *, struct qeth_cmd_buffer *);
-void qeth_prepare_ipa_cmd(struct qeth_card *, struct qeth_cmd_buffer *, char);
+void qeth_prepare_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob);
 struct qeth_cmd_buffer *qeth_wait_for_buffer(struct qeth_channel *);
 int qeth_query_switch_attributes(struct qeth_card *card,
 				  struct qeth_switch_info *sw_info);
 int qeth_send_control_data(struct qeth_card *, int, struct qeth_cmd_buffer *,
 	int (*reply_cb)(struct qeth_card *, struct qeth_reply*, unsigned long),
 	void *reply_param);
-int qeth_bridgeport_query_ports(struct qeth_card *card,
-	enum qeth_sbp_roles *role, enum qeth_sbp_states *state);
-int qeth_bridgeport_setrole(struct qeth_card *card, enum qeth_sbp_roles role);
-int qeth_bridgeport_an_set(struct qeth_card *card, int enable);
-int qeth_get_priority_queue(struct qeth_card *, struct sk_buff *, int, int);
 int qeth_get_elements_no(struct qeth_card *card, struct sk_buff *skb,
 			 int extra_elems, int data_offset);
 int qeth_get_elements_for_frags(struct sk_buff *);
@@ -1026,7 +1030,6 @@ int qeth_set_access_ctrl_online(struct qeth_card *card, int fallback);
 int qeth_hdr_chk_and_bounce(struct sk_buff *, struct qeth_hdr **, int);
 int qeth_configure_cq(struct qeth_card *, enum qeth_cq);
 int qeth_hw_trap(struct qeth_card *, enum qeth_diags_trap_action);
-int qeth_query_ipassists(struct qeth_card *, enum qeth_prot_versions prot);
 void qeth_trace_features(struct qeth_card *);
 void qeth_close_dev(struct qeth_card *);
 int qeth_send_setassparms(struct qeth_card *, struct qeth_cmd_buffer *, __u16,
@@ -1046,7 +1049,9 @@ netdev_features_t qeth_features_check(struct sk_buff *skb,
 				      struct net_device *dev,
 				      netdev_features_t features);
 int qeth_vm_request_mac(struct qeth_card *card);
-int qeth_push_hdr(struct sk_buff *skb, struct qeth_hdr **hdr, unsigned int len);
+int qeth_add_hw_header(struct qeth_card *card, struct sk_buff *skb,
+		       struct qeth_hdr **hdr, unsigned int hdr_len,
+		       unsigned int proto_len, unsigned int *elements);
 
 /* exports for OSN */
 int qeth_osn_assist(struct net_device *, void *, int);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index d01ac29fd986..49f64eb3eab0 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -65,7 +65,6 @@ static struct mutex qeth_mod_mutex;
 static void qeth_send_control_data_cb(struct qeth_channel *,
 			struct qeth_cmd_buffer *);
 static struct qeth_cmd_buffer *qeth_get_buffer(struct qeth_channel *);
-static void qeth_setup_ccw(struct qeth_channel *, unsigned char *, __u32);
 static void qeth_free_buffer_pool(struct qeth_card *);
 static int qeth_qdio_establish(struct qeth_card *);
 static void qeth_free_qdio_buffers(struct qeth_card *);
@@ -473,7 +472,6 @@ static void qeth_cleanup_handled_pending(struct qeth_qdio_out_q *q, int bidx,
 	if (forced_cleanup && (atomic_read(&(q->bufs[bidx]->state)) ==
 					QETH_QDIO_BUF_HANDLED_DELAYED)) {
 		/* for recovery situations */
-		q->bufs[bidx]->aob = q->bufstates[bidx].aob;
 		qeth_init_qdio_out_buf(q, bidx);
 		QETH_CARD_TEXT(q->card, 2, "clprecov");
 	}
@@ -510,7 +508,6 @@ static void qeth_qdio_handle_aob(struct qeth_card *card,
 	}
 	qeth_notify_skbs(buffer->q, buffer, notification);
 
-	buffer->aob = NULL;
 	/* Free dangling allocations. The attached skbs are handled by
 	 * qeth_cleanup_handled_pending().
 	 */
@@ -534,15 +531,24 @@ static inline int qeth_is_cq(struct qeth_card *card, unsigned int queue)
 	    queue == card->qdio.no_in_queues - 1;
 }
 
+static void qeth_setup_ccw(struct ccw1 *ccw, u8 cmd_code, u32 len, void *data)
+{
+	ccw->cmd_code = cmd_code;
+	ccw->flags = CCW_FLAG_SLI;
+	ccw->count = len;
+	ccw->cda = (__u32) __pa(data);
+}
+
 static int __qeth_issue_next_read(struct qeth_card *card)
 {
-	int rc;
+	struct qeth_channel *channel = &card->read;
 	struct qeth_cmd_buffer *iob;
+	int rc;
 
 	QETH_CARD_TEXT(card, 5, "issnxrd");
-	if (card->read.state != CH_STATE_UP)
+	if (channel->state != CH_STATE_UP)
 		return -EIO;
-	iob = qeth_get_buffer(&card->read);
+	iob = qeth_get_buffer(channel);
 	if (!iob) {
 		dev_warn(&card->gdev->dev, "The qeth device driver "
 			"failed to recover an error on the device\n");
@@ -550,14 +556,14 @@ static int __qeth_issue_next_read(struct qeth_card *card)
 			"available\n", dev_name(&card->gdev->dev));
 		return -ENOMEM;
 	}
-	qeth_setup_ccw(&card->read, iob->data, QETH_BUFSIZE);
+	qeth_setup_ccw(channel->ccw, CCW_CMD_READ, QETH_BUFSIZE, iob->data);
 	QETH_CARD_TEXT(card, 6, "noirqpnd");
-	rc = ccw_device_start(card->read.ccwdev, &card->read.ccw,
+	rc = ccw_device_start(channel->ccwdev, channel->ccw,
 			      (addr_t) iob, 0, 0);
 	if (rc) {
 		QETH_DBF_MESSAGE(2, "%s error in starting next read ccw! "
 			"rc=%i\n", dev_name(&card->gdev->dev), rc);
-		atomic_set(&card->read.irq_pending, 0);
+		atomic_set(&channel->irq_pending, 0);
 		card->read_or_write_problem = 1;
 		qeth_schedule_recovery(card);
 		wake_up(&card->wait_q);
@@ -655,8 +661,7 @@ static struct qeth_ipa_cmd *qeth_check_ipa_data(struct qeth_card *card,
 						cmd->hdr.return_code, card);
 				}
 				card->lan_online = 0;
-				if (card->dev && netif_carrier_ok(card->dev))
-					netif_carrier_off(card->dev);
+				netif_carrier_off(card->dev);
 				return NULL;
 			case IPA_CMD_STARTLAN:
 				dev_info(&card->gdev->dev,
@@ -747,21 +752,6 @@ static struct qeth_card *CARD_FROM_CDEV(struct ccw_device *cdev)
 	return card;
 }
 
-static void qeth_setup_ccw(struct qeth_channel *channel, unsigned char *iob,
-		__u32 len)
-{
-	struct qeth_card *card;
-
-	card = CARD_FROM_CDEV(channel->ccwdev);
-	QETH_CARD_TEXT(card, 4, "setupccw");
-	if (channel == &card->read)
-		memcpy(&channel->ccw, READ_CCW, sizeof(struct ccw1));
-	else
-		memcpy(&channel->ccw, WRITE_CCW, sizeof(struct ccw1));
-	channel->ccw.count = len;
-	channel->ccw.cda = (__u32) __pa(iob);
-}
-
 static struct qeth_cmd_buffer *__qeth_get_buffer(struct qeth_channel *channel)
 {
 	__u8 index;
@@ -909,11 +899,22 @@ out:
 	qeth_release_buffer(channel, iob);
 }
 
-static int qeth_setup_channel(struct qeth_channel *channel)
+static int qeth_setup_channel(struct qeth_channel *channel, bool alloc_buffers)
 {
 	int cnt;
 
 	QETH_DBF_TEXT(SETUP, 2, "setupch");
+
+	channel->ccw = kmalloc(sizeof(struct ccw1), GFP_KERNEL | GFP_DMA);
+	if (!channel->ccw)
+		return -ENOMEM;
+	channel->state = CH_STATE_DOWN;
+	atomic_set(&channel->irq_pending, 0);
+	init_waitqueue_head(&channel->wait_q);
+
+	if (!alloc_buffers)
+		return 0;
+
 	for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++) {
 		channel->iob[cnt].data =
 			kzalloc(QETH_BUFSIZE, GFP_DMA|GFP_KERNEL);
@@ -925,15 +926,14 @@ static int qeth_setup_channel(struct qeth_channel *channel)
 		channel->iob[cnt].rc = 0;
 	}
 	if (cnt < QETH_CMD_BUFFER_NO) {
+		kfree(channel->ccw);
 		while (cnt-- > 0)
 			kfree(channel->iob[cnt].data);
 		return -ENOMEM;
 	}
 	channel->io_buf_no = 0;
-	atomic_set(&channel->irq_pending, 0);
 	spin_lock_init(&channel->iob_lock);
 
-	init_waitqueue_head(&channel->wait_q);
 	return 0;
 }
 
@@ -1267,8 +1267,7 @@ static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf)
 }
 
 static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
-		struct qeth_qdio_out_buffer *buf,
-		enum qeth_qdio_buffer_states newbufstate)
+				     struct qeth_qdio_out_buffer *buf)
 {
 	int i;
 
@@ -1276,23 +1275,19 @@ static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
 	if (buf->buffer->element[0].sflags & SBAL_SFLAGS0_PCI_REQ)
 		atomic_dec(&queue->set_pci_flags_count);
 
-	if (newbufstate == QETH_QDIO_BUF_EMPTY) {
-		qeth_release_skbs(buf);
-	}
+	qeth_release_skbs(buf);
+
 	for (i = 0; i < QETH_MAX_BUFFER_ELEMENTS(queue->card); ++i) {
 		if (buf->buffer->element[i].addr && buf->is_header[i])
 			kmem_cache_free(qeth_core_header_cache,
 				buf->buffer->element[i].addr);
 		buf->is_header[i] = 0;
-		buf->buffer->element[i].length = 0;
-		buf->buffer->element[i].addr = NULL;
-		buf->buffer->element[i].eflags = 0;
-		buf->buffer->element[i].sflags = 0;
 	}
-	buf->buffer->element[15].eflags = 0;
-	buf->buffer->element[15].sflags = 0;
+
+	qeth_scrub_qdio_buffer(buf->buffer,
+			       QETH_MAX_BUFFER_ELEMENTS(queue->card));
 	buf->next_element_to_fill = 0;
-	atomic_set(&buf->state, newbufstate);
+	atomic_set(&buf->state, QETH_QDIO_BUF_EMPTY);
 }
 
 static void qeth_clear_outq_buffers(struct qeth_qdio_out_q *q, int free)
@@ -1303,7 +1298,7 @@ static void qeth_clear_outq_buffers(struct qeth_qdio_out_q *q, int free)
 		if (!q->bufs[j])
 			continue;
 		qeth_cleanup_handled_pending(q, j, 1);
-		qeth_clear_output_buffer(q, q->bufs[j], QETH_QDIO_BUF_EMPTY);
+		qeth_clear_output_buffer(q, q->bufs[j]);
 		if (free) {
 			kmem_cache_free(qeth_qdio_outbuf_cache, q->bufs[j]);
 			q->bufs[j] = NULL;
@@ -1345,6 +1340,7 @@ static void qeth_clean_channel(struct qeth_channel *channel)
 	QETH_DBF_TEXT(SETUP, 2, "freech");
 	for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++)
 		kfree(channel->iob[cnt].data);
+	kfree(channel->ccw);
 }
 
 static void qeth_set_single_write_queues(struct qeth_card *card)
@@ -1401,6 +1397,10 @@ static void qeth_init_qdio_info(struct qeth_card *card)
 {
 	QETH_DBF_TEXT(SETUP, 4, "intqdinf");
 	atomic_set(&card->qdio.state, QETH_QDIO_UNINITIALIZED);
+	card->qdio.do_prio_queueing = QETH_PRIOQ_DEFAULT;
+	card->qdio.default_out_queue = QETH_DEFAULT_QUEUE;
+	card->qdio.no_out_queues = QETH_MAX_QUEUES;
+
 	/* inbound */
 	card->qdio.no_in_queues = 1;
 	card->qdio.in_buf_size = QETH_IN_BUF_SIZE_DEFAULT;
@@ -1413,12 +1413,10 @@ static void qeth_init_qdio_info(struct qeth_card *card)
 	INIT_LIST_HEAD(&card->qdio.init_pool.entry_list);
 }
 
-static void qeth_set_intial_options(struct qeth_card *card)
+static void qeth_set_initial_options(struct qeth_card *card)
 {
 	card->options.route4.type = NO_ROUTER;
 	card->options.route6.type = NO_ROUTER;
-	card->options.fake_broadcast = 0;
-	card->options.performance_stats = 0;
 	card->options.rx_sg_cb = QETH_RX_SG_CB;
 	card->options.isolation = ISOLATION_MODE_NONE;
 	card->options.cq = QETH_CQ_DISABLED;
@@ -1461,19 +1459,13 @@ static void qeth_start_kernel_thread(struct work_struct *work)
 }
 
 static void qeth_buffer_reclaim_work(struct work_struct *);
-static int qeth_setup_card(struct qeth_card *card)
+static void qeth_setup_card(struct qeth_card *card)
 {
-
 	QETH_DBF_TEXT(SETUP, 2, "setupcrd");
 	QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *));
 
-	card->read.state  = CH_STATE_DOWN;
-	card->write.state = CH_STATE_DOWN;
-	card->data.state  = CH_STATE_DOWN;
+	card->info.type = CARD_RDEV(card)->id.driver_info;
 	card->state = CARD_STATE_DOWN;
-	card->lan_online = 0;
-	card->read_or_write_problem = 0;
-	card->dev = NULL;
 	spin_lock_init(&card->mclock);
 	spin_lock_init(&card->lock);
 	spin_lock_init(&card->ip_lock);
@@ -1481,24 +1473,15 @@ static int qeth_setup_card(struct qeth_card *card)
 	mutex_init(&card->conf_mutex);
 	mutex_init(&card->discipline_mutex);
 	mutex_init(&card->vid_list_mutex);
-	card->thread_start_mask = 0;
-	card->thread_allowed_mask = 0;
-	card->thread_running_mask = 0;
 	INIT_WORK(&card->kernel_thread_starter, qeth_start_kernel_thread);
 	INIT_LIST_HEAD(&card->cmd_waiter_list);
 	init_waitqueue_head(&card->wait_q);
-	/* initial options */
-	qeth_set_intial_options(card);
+	qeth_set_initial_options(card);
 	/* IP address takeover */
 	INIT_LIST_HEAD(&card->ipato.entries);
-	card->ipato.enabled = false;
-	card->ipato.invert4 = false;
-	card->ipato.invert6 = false;
-	/* init QDIO stuff */
 	qeth_init_qdio_info(card);
 	INIT_DELAYED_WORK(&card->buffer_reclaim_work, qeth_buffer_reclaim_work);
 	INIT_WORK(&card->close_dev_work, qeth_close_dev_handler);
-	return 0;
 }
 
 static void qeth_core_sl_print(struct seq_file *m, struct service_level *slr)
@@ -1515,19 +1498,23 @@ static struct qeth_card *qeth_alloc_card(void)
 	struct qeth_card *card;
 
 	QETH_DBF_TEXT(SETUP, 2, "alloccrd");
-	card = kzalloc(sizeof(struct qeth_card), GFP_DMA|GFP_KERNEL);
+	card = kzalloc(sizeof(*card), GFP_KERNEL);
 	if (!card)
 		goto out;
 	QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *));
-	if (qeth_setup_channel(&card->read))
+	if (qeth_setup_channel(&card->read, true))
 		goto out_ip;
-	if (qeth_setup_channel(&card->write))
+	if (qeth_setup_channel(&card->write, true))
 		goto out_channel;
+	if (qeth_setup_channel(&card->data, false))
+		goto out_data;
 	card->options.layer2 = -1;
 	card->qeth_service_level.seq_print = qeth_core_sl_print;
 	register_service_level(&card->qeth_service_level);
 	return card;
 
+out_data:
+	qeth_clean_channel(&card->write);
 out_channel:
 	qeth_clean_channel(&card->read);
 out_ip:
@@ -1536,19 +1523,6 @@ out:
 	return NULL;
 }
 
-static void qeth_determine_card_type(struct qeth_card *card)
-{
-	QETH_DBF_TEXT(SETUP, 2, "detcdtyp");
-
-	card->qdio.do_prio_queueing = QETH_PRIOQ_DEFAULT;
-	card->qdio.default_out_queue = QETH_DEFAULT_QUEUE;
-	card->info.type = CARD_RDEV(card)->id.driver_info;
-	card->qdio.no_out_queues = QETH_MAX_QUEUES;
-	if (card->info.type == QETH_CARD_TYPE_IQD)
-		card->info.is_multicast_different = 0x0103;
-	qeth_update_from_chp_desc(card);
-}
-
 static int qeth_clear_channel(struct qeth_channel *channel)
 {
 	unsigned long flags;
@@ -1689,13 +1663,10 @@ static int qeth_read_conf_data(struct qeth_card *card, void **buffer,
 	if (!rcd_buf)
 		return -ENOMEM;
 
-	channel->ccw.cmd_code = ciw->cmd;
-	channel->ccw.cda = (__u32) __pa(rcd_buf);
-	channel->ccw.count = ciw->count;
-	channel->ccw.flags = CCW_FLAG_SLI;
+	qeth_setup_ccw(channel->ccw, ciw->cmd, ciw->count, rcd_buf);
 	channel->state = CH_STATE_RCD;
 	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	ret = ccw_device_start_timeout(channel->ccwdev, &channel->ccw,
+	ret = ccw_device_start_timeout(channel->ccwdev, channel->ccw,
 				       QETH_RCD_PARM, LPM_ANYPATH, 0,
 				       QETH_RCD_TIMEOUT);
 	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
@@ -1866,15 +1837,13 @@ static int qeth_idx_activate_get_answer(struct qeth_channel *channel,
 	if (!iob)
 		return -ENOMEM;
 	iob->callback = idx_reply_cb;
-	memcpy(&channel->ccw, READ_CCW, sizeof(struct ccw1));
-	channel->ccw.count = QETH_BUFSIZE;
-	channel->ccw.cda = (__u32) __pa(iob->data);
+	qeth_setup_ccw(channel->ccw, CCW_CMD_READ, QETH_BUFSIZE, iob->data);
 
 	wait_event(card->wait_q,
 		   atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0);
 	QETH_DBF_TEXT(SETUP, 6, "noirqpnd");
 	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	rc = ccw_device_start_timeout(channel->ccwdev, &channel->ccw,
+	rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw,
 				      (addr_t) iob, 0, 0, QETH_TIMEOUT);
 	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
 
@@ -1917,9 +1886,8 @@ static int qeth_idx_activate_channel(struct qeth_channel *channel,
 	if (!iob)
 		return -ENOMEM;
 	iob->callback = idx_reply_cb;
-	memcpy(&channel->ccw, WRITE_CCW, sizeof(struct ccw1));
-	channel->ccw.count = IDX_ACTIVATE_SIZE;
-	channel->ccw.cda = (__u32) __pa(iob->data);
+	qeth_setup_ccw(channel->ccw, CCW_CMD_WRITE, IDX_ACTIVATE_SIZE,
+		       iob->data);
 	if (channel == &card->write) {
 		memcpy(iob->data, IDX_ACTIVATE_WRITE, IDX_ACTIVATE_SIZE);
 		memcpy(QETH_TRANSPORT_HEADER_SEQ_NO(iob->data),
@@ -1930,7 +1898,7 @@ static int qeth_idx_activate_channel(struct qeth_channel *channel,
 		memcpy(QETH_TRANSPORT_HEADER_SEQ_NO(iob->data),
 		       &card->seqno.trans_hdr, QETH_SEQ_NO_LENGTH);
 	}
-	tmp = ((__u8)card->info.portno) | 0x80;
+	tmp = ((u8)card->dev->dev_port) | 0x80;
 	memcpy(QETH_IDX_ACT_PNO(iob->data), &tmp, 1);
 	memcpy(QETH_IDX_ACT_ISSUER_RM_TOKEN(iob->data),
 	       &card->token.issuer_rm_w, QETH_MPC_TOKEN_LENGTH);
@@ -1945,7 +1913,7 @@ static int qeth_idx_activate_channel(struct qeth_channel *channel,
 		   atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0);
 	QETH_DBF_TEXT(SETUP, 6, "noirqpnd");
 	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	rc = ccw_device_start_timeout(channel->ccwdev, &channel->ccw,
+	rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw,
 				      (addr_t) iob, 0, 0, QETH_TIMEOUT);
 	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
 
@@ -1997,20 +1965,20 @@ static void qeth_idx_write_cb(struct qeth_channel *channel,
 
 	if (!(QETH_IS_IDX_ACT_POS_REPLY(iob->data))) {
 		if (QETH_IDX_ACT_CAUSE_CODE(iob->data) == QETH_IDX_ACT_ERR_EXCL)
-			dev_err(&card->write.ccwdev->dev,
+			dev_err(&channel->ccwdev->dev,
 				"The adapter is used exclusively by another "
 				"host\n");
 		else
 			QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on write channel:"
 				" negative reply\n",
-				dev_name(&card->write.ccwdev->dev));
+				dev_name(&channel->ccwdev->dev));
 		goto out;
 	}
 	memcpy(&temp, QETH_IDX_ACT_FUNC_LEVEL(iob->data), 2);
 	if ((temp & ~0x0100) != qeth_peer_func_level(card->info.func_level)) {
 		QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on write channel: "
 			"function level mismatch (sent: 0x%x, received: "
-			"0x%x)\n", dev_name(&card->write.ccwdev->dev),
+			"0x%x)\n", dev_name(&channel->ccwdev->dev),
 			card->info.func_level, temp);
 		goto out;
 	}
@@ -2038,20 +2006,20 @@ static void qeth_idx_read_cb(struct qeth_channel *channel,
 	if (!(QETH_IS_IDX_ACT_POS_REPLY(iob->data))) {
 		switch (QETH_IDX_ACT_CAUSE_CODE(iob->data)) {
 		case QETH_IDX_ACT_ERR_EXCL:
-			dev_err(&card->write.ccwdev->dev,
+			dev_err(&channel->ccwdev->dev,
 				"The adapter is used exclusively by another "
 				"host\n");
 			break;
 		case QETH_IDX_ACT_ERR_AUTH:
 		case QETH_IDX_ACT_ERR_AUTH_USER:
-			dev_err(&card->read.ccwdev->dev,
+			dev_err(&channel->ccwdev->dev,
 				"Setting the device online failed because of "
 				"insufficient authorization\n");
 			break;
 		default:
 			QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on read channel:"
 				" negative reply\n",
-				dev_name(&card->read.ccwdev->dev));
+				dev_name(&channel->ccwdev->dev));
 		}
 		QETH_CARD_TEXT_(card, 2, "idxread%c",
 			QETH_IDX_ACT_CAUSE_CODE(iob->data));
@@ -2062,7 +2030,7 @@ static void qeth_idx_read_cb(struct qeth_channel *channel,
 	if (temp != qeth_peer_func_level(card->info.func_level)) {
 		QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on read channel: function "
 			"level mismatch (sent: 0x%x, received: 0x%x)\n",
-			dev_name(&card->read.ccwdev->dev),
+			dev_name(&channel->ccwdev->dev),
 			card->info.func_level, temp);
 		goto out;
 	}
@@ -2079,7 +2047,7 @@ out:
 void qeth_prepare_control_data(struct qeth_card *card, int len,
 		struct qeth_cmd_buffer *iob)
 {
-	qeth_setup_ccw(&card->write, iob->data, len);
+	qeth_setup_ccw(iob->channel->ccw, CCW_CMD_WRITE, len, iob->data);
 	iob->callback = qeth_release_buffer;
 
 	memcpy(QETH_TRANSPORT_HEADER_SEQ_NO(iob->data),
@@ -2126,6 +2094,7 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 				unsigned long cb_cmd),
 		void *reply_param)
 {
+	struct qeth_channel *channel = iob->channel;
 	int rc;
 	unsigned long flags;
 	struct qeth_reply *reply = NULL;
@@ -2135,7 +2104,7 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 	QETH_CARD_TEXT(card, 2, "sendctl");
 
 	if (card->read_or_write_problem) {
-		qeth_release_buffer(iob->channel, iob);
+		qeth_release_buffer(channel, iob);
 		return -EIO;
 	}
 	reply = qeth_alloc_reply(card);
@@ -2147,7 +2116,7 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 
 	init_waitqueue_head(&reply->wait_q);
 
-	while (atomic_cmpxchg(&card->write.irq_pending, 0, 1)) ;
+	while (atomic_cmpxchg(&channel->irq_pending, 0, 1)) ;
 
 	if (IS_IPA(iob->data)) {
 		cmd = __ipa_cmd(iob);
@@ -2167,21 +2136,21 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 	timeout = jiffies + event_timeout;
 
 	QETH_CARD_TEXT(card, 6, "noirqpnd");
-	spin_lock_irqsave(get_ccwdev_lock(card->write.ccwdev), flags);
-	rc = ccw_device_start_timeout(CARD_WDEV(card), &card->write.ccw,
+	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
+	rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw,
 				      (addr_t) iob, 0, 0, event_timeout);
-	spin_unlock_irqrestore(get_ccwdev_lock(card->write.ccwdev), flags);
+	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
 	if (rc) {
 		QETH_DBF_MESSAGE(2, "%s qeth_send_control_data: "
 			"ccw_device_start rc = %i\n",
-			dev_name(&card->write.ccwdev->dev), rc);
+			dev_name(&channel->ccwdev->dev), rc);
 		QETH_CARD_TEXT_(card, 2, " err%d", rc);
 		spin_lock_irqsave(&card->lock, flags);
 		list_del_init(&reply->list);
 		qeth_put_reply(reply);
 		spin_unlock_irqrestore(&card->lock, flags);
-		qeth_release_buffer(iob->channel, iob);
-		atomic_set(&card->write.irq_pending, 0);
+		qeth_release_buffer(channel, iob);
+		atomic_set(&channel->irq_pending, 0);
 		wake_up(&card->wait_q);
 		return rc;
 	}
@@ -2288,19 +2257,42 @@ static int qeth_cm_setup(struct qeth_card *card)
 
 }
 
-static int qeth_get_initial_mtu_for_card(struct qeth_card *card)
+static int qeth_update_max_mtu(struct qeth_card *card, unsigned int max_mtu)
 {
-	switch (card->info.type) {
-	case QETH_CARD_TYPE_IQD:
-		return card->info.max_mtu;
-	case QETH_CARD_TYPE_OSD:
-	case QETH_CARD_TYPE_OSX:
-		if (!card->options.layer2)
-			return ETH_DATA_LEN - 8; /* L3: allow for LLC + SNAP */
-		/* fall through */
-	default:
-		return ETH_DATA_LEN;
+	struct net_device *dev = card->dev;
+	unsigned int new_mtu;
+
+	if (!max_mtu) {
+		/* IQD needs accurate max MTU to set up its RX buffers: */
+		if (IS_IQD(card))
+			return -EINVAL;
+		/* tolerate quirky HW: */
+		max_mtu = ETH_MAX_MTU;
+	}
+
+	rtnl_lock();
+	if (IS_IQD(card)) {
+		/* move any device with default MTU to new max MTU: */
+		new_mtu = (dev->mtu == dev->max_mtu) ? max_mtu : dev->mtu;
+
+		/* adjust RX buffer size to new max MTU: */
+		card->qdio.in_buf_size = max_mtu + 2 * PAGE_SIZE;
+		if (dev->max_mtu && dev->max_mtu != max_mtu)
+			qeth_free_qdio_buffers(card);
+	} else {
+		if (dev->mtu)
+			new_mtu = dev->mtu;
+		/* default MTUs for first setup: */
+		else if (card->options.layer2)
+			new_mtu = ETH_DATA_LEN;
+		else
+			new_mtu = ETH_DATA_LEN - 8; /* allow for LLC + SNAP */
 	}
+
+	dev->max_mtu = max_mtu;
+	dev->mtu = min(new_mtu, max_mtu);
+	rtnl_unlock();
+	return 0;
 }
 
 static int qeth_get_mtu_outof_framesize(int framesize)
@@ -2319,21 +2311,6 @@ static int qeth_get_mtu_outof_framesize(int framesize)
 	}
 }
 
-static int qeth_mtu_is_valid(struct qeth_card *card, int mtu)
-{
-	switch (card->info.type) {
-	case QETH_CARD_TYPE_OSD:
-	case QETH_CARD_TYPE_OSM:
-	case QETH_CARD_TYPE_OSX:
-	case QETH_CARD_TYPE_IQD:
-		return ((mtu >= 576) &&
-			(mtu <= card->info.max_mtu));
-	case QETH_CARD_TYPE_OSN:
-	default:
-		return 1;
-	}
-}
-
 static int qeth_ulp_enable_cb(struct qeth_card *card, struct qeth_reply *reply,
 		unsigned long data)
 {
@@ -2352,29 +2329,10 @@ static int qeth_ulp_enable_cb(struct qeth_card *card, struct qeth_reply *reply,
 	if (card->info.type == QETH_CARD_TYPE_IQD) {
 		memcpy(&framesize, QETH_ULP_ENABLE_RESP_MAX_MTU(iob->data), 2);
 		mtu = qeth_get_mtu_outof_framesize(framesize);
-		if (!mtu) {
-			iob->rc = -EINVAL;
-			QETH_DBF_TEXT_(SETUP, 2, "  rc%d", iob->rc);
-			return 0;
-		}
-		if (card->info.initial_mtu && (card->info.initial_mtu != mtu)) {
-			/* frame size has changed */
-			if (card->dev &&
-			    ((card->dev->mtu == card->info.initial_mtu) ||
-			     (card->dev->mtu > mtu)))
-				card->dev->mtu = mtu;
-			qeth_free_qdio_buffers(card);
-		}
-		card->info.initial_mtu = mtu;
-		card->info.max_mtu = mtu;
-		card->qdio.in_buf_size = mtu + 2 * PAGE_SIZE;
 	} else {
-		card->info.max_mtu = *(__u16 *)QETH_ULP_ENABLE_RESP_MAX_MTU(
-			iob->data);
-		card->info.initial_mtu = min(card->info.max_mtu,
-					qeth_get_initial_mtu_for_card(card));
-		card->qdio.in_buf_size = QETH_IN_BUF_SIZE_DEFAULT;
+		mtu = *(__u16 *)QETH_ULP_ENABLE_RESP_MAX_MTU(iob->data);
 	}
+	*(u16 *)reply->param = mtu;
 
 	memcpy(&len, QETH_ULP_ENABLE_RESP_DIFINFO_LEN(iob->data), 2);
 	if (len >= QETH_MPC_DIFINFO_LEN_INDICATES_LINK_TYPE) {
@@ -2388,11 +2346,19 @@ static int qeth_ulp_enable_cb(struct qeth_card *card, struct qeth_reply *reply,
 	return 0;
 }
 
+static u8 qeth_mpc_select_prot_type(struct qeth_card *card)
+{
+	if (IS_OSN(card))
+		return QETH_PROT_OSN2;
+	return (card->options.layer2 == 1) ? QETH_PROT_LAYER2 : QETH_PROT_TCPIP;
+}
+
 static int qeth_ulp_enable(struct qeth_card *card)
 {
-	int rc;
-	char prot_type;
+	u8 prot_type = qeth_mpc_select_prot_type(card);
 	struct qeth_cmd_buffer *iob;
+	u16 max_mtu;
+	int rc;
 
 	/*FIXME: trace view callbacks*/
 	QETH_DBF_TEXT(SETUP, 2, "ulpenabl");
@@ -2400,25 +2366,17 @@ static int qeth_ulp_enable(struct qeth_card *card)
 	iob = qeth_wait_for_buffer(&card->write);
 	memcpy(iob->data, ULP_ENABLE, ULP_ENABLE_SIZE);
 
-	*(QETH_ULP_ENABLE_LINKNUM(iob->data)) =
-		(__u8) card->info.portno;
-	if (card->options.layer2)
-		if (card->info.type == QETH_CARD_TYPE_OSN)
-			prot_type = QETH_PROT_OSN2;
-		else
-			prot_type = QETH_PROT_LAYER2;
-	else
-		prot_type = QETH_PROT_TCPIP;
-
+	*(QETH_ULP_ENABLE_LINKNUM(iob->data)) = (u8) card->dev->dev_port;
 	memcpy(QETH_ULP_ENABLE_PROT_TYPE(iob->data), &prot_type, 1);
 	memcpy(QETH_ULP_ENABLE_DEST_ADDR(iob->data),
 	       &card->token.cm_connection_r, QETH_MPC_TOKEN_LENGTH);
 	memcpy(QETH_ULP_ENABLE_FILTER_TOKEN(iob->data),
 	       &card->token.ulp_filter_w, QETH_MPC_TOKEN_LENGTH);
 	rc = qeth_send_control_data(card, ULP_ENABLE_SIZE, iob,
-				    qeth_ulp_enable_cb, NULL);
-	return rc;
-
+				    qeth_ulp_enable_cb, &max_mtu);
+	if (rc)
+		return rc;
+	return qeth_update_max_mtu(card, max_mtu);
 }
 
 static int qeth_ulp_setup_cb(struct qeth_card *card, struct qeth_reply *reply,
@@ -2473,32 +2431,20 @@ static int qeth_ulp_setup(struct qeth_card *card)
 
 static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *q, int bidx)
 {
-	int rc;
 	struct qeth_qdio_out_buffer *newbuf;
 
-	rc = 0;
 	newbuf = kmem_cache_zalloc(qeth_qdio_outbuf_cache, GFP_ATOMIC);
-	if (!newbuf) {
-		rc = -ENOMEM;
-		goto out;
-	}
+	if (!newbuf)
+		return -ENOMEM;
+
 	newbuf->buffer = q->qdio_bufs[bidx];
 	skb_queue_head_init(&newbuf->skb_list);
 	lockdep_set_class(&newbuf->skb_list.lock, &qdio_out_skb_queue_key);
 	newbuf->q = q;
-	newbuf->aob = NULL;
 	newbuf->next_pending = q->bufs[bidx];
 	atomic_set(&newbuf->state, QETH_QDIO_BUF_EMPTY);
 	q->bufs[bidx] = newbuf;
-	if (q->bufstates) {
-		q->bufstates[bidx].user = newbuf;
-		QETH_CARD_TEXT_(q->card, 2, "nbs%d", bidx);
-		QETH_CARD_TEXT_(q->card, 2, "%lx", (long) newbuf);
-		QETH_CARD_TEXT_(q->card, 2, "%lx",
-				(long) newbuf->next_pending);
-	}
-out:
-	return rc;
+	return 0;
 }
 
 static void qeth_free_qdio_out_buf(struct qeth_qdio_out_q *q)
@@ -2908,8 +2854,7 @@ int qeth_init_qdio_queues(struct qeth_card *card)
 				   QDIO_MAX_BUFFERS_PER_Q);
 		for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j) {
 			qeth_clear_output_buffer(card->qdio.out_qs[i],
-					card->qdio.out_qs[i]->bufs[j],
-					QETH_QDIO_BUF_EMPTY);
+						 card->qdio.out_qs[i]->bufs[j]);
 		}
 		card->qdio.out_qs[i]->card = card;
 		card->qdio.out_qs[i]->next_buf_to_fill = 0;
@@ -2942,7 +2887,7 @@ static void qeth_fill_ipacmd_header(struct qeth_card *card,
 	cmd->hdr.initiator = IPA_CMD_INITIATOR_HOST;
 	/* cmd->hdr.seqno is set by qeth_send_control_data() */
 	cmd->hdr.adapter_type = qeth_get_ipa_adp_type(card->info.link_type);
-	cmd->hdr.rel_adapter_no = (__u8) card->info.portno;
+	cmd->hdr.rel_adapter_no = (u8) card->dev->dev_port;
 	if (card->options.layer2)
 		cmd->hdr.prim_version_no = 2;
 	else
@@ -2972,9 +2917,10 @@ struct qeth_cmd_buffer *qeth_get_ipacmd_buffer(struct qeth_card *card,
 }
 EXPORT_SYMBOL_GPL(qeth_get_ipacmd_buffer);
 
-void qeth_prepare_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob,
-		char prot_type)
+void qeth_prepare_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob)
 {
+	u8 prot_type = qeth_mpc_select_prot_type(card);
+
 	memcpy(iob->data, IPA_PDU_HEADER, IPA_PDU_HEADER_SIZE);
 	memcpy(QETH_IPA_CMD_PROT_TYPE(iob->data), &prot_type, 1);
 	memcpy(QETH_IPA_CMD_DEST_ADDR(iob->data),
@@ -2994,18 +2940,9 @@ int qeth_send_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob,
 		void *reply_param)
 {
 	int rc;
-	char prot_type;
 
 	QETH_CARD_TEXT(card, 4, "sendipa");
-
-	if (card->options.layer2)
-		if (card->info.type == QETH_CARD_TYPE_OSN)
-			prot_type = QETH_PROT_OSN2;
-		else
-			prot_type = QETH_PROT_LAYER2;
-	else
-		prot_type = QETH_PROT_TCPIP;
-	qeth_prepare_ipa_cmd(card, iob, prot_type);
+	qeth_prepare_ipa_cmd(card, iob);
 	rc = qeth_send_control_data(card, IPA_CMD_LENGTH,
 						iob, reply_cb, reply_param);
 	if (rc == -ETIME) {
@@ -3076,7 +3013,7 @@ static struct qeth_cmd_buffer *qeth_get_adapter_cmd(struct qeth_card *card,
 	return iob;
 }
 
-int qeth_query_setadapterparms(struct qeth_card *card)
+static int qeth_query_setadapterparms(struct qeth_card *card)
 {
 	int rc;
 	struct qeth_cmd_buffer *iob;
@@ -3089,7 +3026,6 @@ int qeth_query_setadapterparms(struct qeth_card *card)
 	rc = qeth_send_ipa_cmd(card, iob, qeth_query_setadapterparms_cb, NULL);
 	return rc;
 }
-EXPORT_SYMBOL_GPL(qeth_query_setadapterparms);
 
 static int qeth_query_ipassists_cb(struct qeth_card *card,
 		struct qeth_reply *reply, unsigned long data)
@@ -3129,7 +3065,8 @@ static int qeth_query_ipassists_cb(struct qeth_card *card,
 	return 0;
 }
 
-int qeth_query_ipassists(struct qeth_card *card, enum qeth_prot_versions prot)
+static int qeth_query_ipassists(struct qeth_card *card,
+				enum qeth_prot_versions prot)
 {
 	int rc;
 	struct qeth_cmd_buffer *iob;
@@ -3141,7 +3078,6 @@ int qeth_query_ipassists(struct qeth_card *card, enum qeth_prot_versions prot)
 	rc = qeth_send_ipa_cmd(card, iob, qeth_query_ipassists_cb, NULL);
 	return rc;
 }
-EXPORT_SYMBOL_GPL(qeth_query_ipassists);
 
 static int qeth_query_switch_attributes_cb(struct qeth_card *card,
 				struct qeth_reply *reply, unsigned long data)
@@ -3180,7 +3116,6 @@ int qeth_query_switch_attributes(struct qeth_card *card,
 	return qeth_send_ipa_cmd(card, iob,
 				qeth_query_switch_attributes_cb, sw_info);
 }
-EXPORT_SYMBOL_GPL(qeth_query_switch_attributes);
 
 static int qeth_query_setdiagass_cb(struct qeth_card *card,
 		struct qeth_reply *reply, unsigned long data)
@@ -3530,13 +3465,14 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index,
 	qdio_flags = QDIO_FLAG_SYNC_OUTPUT;
 	if (atomic_read(&queue->set_pci_flags_count))
 		qdio_flags |= QDIO_FLAG_PCI_OUT;
+	atomic_add(count, &queue->used_buffers);
+
 	rc = do_QDIO(CARD_DDEV(queue->card), qdio_flags,
 		     queue->queue_no, index, count);
 	if (queue->card->options.performance_stats)
 		queue->card->perf_stats.outbound_do_qdio_time +=
 			qeth_get_micros() -
 			queue->card->perf_stats.outbound_do_qdio_start_time;
-	atomic_add(count, &queue->used_buffers);
 	if (rc) {
 		queue->card->stats.tx_errors += count;
 		/* ignore temporary SIGA errors without busy condition */
@@ -3601,7 +3537,7 @@ static void qeth_qdio_start_poll(struct ccw_device *ccwdev, int queue,
 {
 	struct qeth_card *card = (struct qeth_card *)card_ptr;
 
-	if (card->dev && (card->dev->flags & IFF_UP))
+	if (card->dev->flags & IFF_UP)
 		napi_schedule(&card->napi);
 }
 
@@ -3634,10 +3570,10 @@ out:
 }
 EXPORT_SYMBOL_GPL(qeth_configure_cq);
 
-
-static void qeth_qdio_cq_handler(struct qeth_card *card,
-		unsigned int qdio_err,
-		unsigned int queue, int first_element, int count) {
+static void qeth_qdio_cq_handler(struct qeth_card *card, unsigned int qdio_err,
+				 unsigned int queue, int first_element,
+				 int count)
+{
 	struct qeth_qdio_q *cq = card->qdio.c_q;
 	int i;
 	int rc;
@@ -3663,25 +3599,17 @@ static void qeth_qdio_cq_handler(struct qeth_card *card,
 	for (i = first_element; i < first_element + count; ++i) {
 		int bidx = i % QDIO_MAX_BUFFERS_PER_Q;
 		struct qdio_buffer *buffer = cq->qdio_bufs[bidx];
-		int e;
+		int e = 0;
 
-		e = 0;
 		while ((e < QDIO_MAX_ELEMENTS_PER_BUFFER) &&
 		       buffer->element[e].addr) {
 			unsigned long phys_aob_addr;
 
 			phys_aob_addr = (unsigned long) buffer->element[e].addr;
 			qeth_qdio_handle_aob(card, phys_aob_addr);
-			buffer->element[e].addr = NULL;
-			buffer->element[e].eflags = 0;
-			buffer->element[e].sflags = 0;
-			buffer->element[e].length = 0;
-
 			++e;
 		}
-
-		buffer->element[15].eflags = 0;
-		buffer->element[15].sflags = 0;
+		qeth_scrub_qdio_buffer(buffer, QDIO_MAX_ELEMENTS_PER_BUFFER);
 	}
 	rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_INPUT, queue,
 		    card->qdio.c_q->next_buf_to_init,
@@ -3760,11 +3688,7 @@ static void qeth_qdio_output_handler(struct ccw_device *ccwdev,
 				qeth_notify_skbs(queue, buffer,
 						 TX_NOTIFY_PENDING);
 			}
-			buffer->aob = queue->bufstates[bidx].aob;
 			QETH_CARD_TEXT_(queue->card, 5, "pel%d", bidx);
-			QETH_CARD_TEXT(queue->card, 5, "aob");
-			QETH_CARD_TEXT_(queue->card, 5, "%lx",
-					virt_to_phys(buffer->aob));
 
 			/* prepare the queue slot for re-use: */
 			qeth_scrub_qdio_buffer(buffer->buffer,
@@ -3782,8 +3706,7 @@ static void qeth_qdio_output_handler(struct ccw_device *ccwdev,
 				qeth_notify_skbs(queue, buffer, n);
 			}
 
-			qeth_clear_output_buffer(queue, buffer,
-						QETH_QDIO_BUF_EMPTY);
+			qeth_clear_output_buffer(queue, buffer);
 		}
 		qeth_cleanup_handled_pending(queue, bidx, 0);
 	}
@@ -3810,15 +3733,11 @@ static inline int qeth_cut_iqd_prio(struct qeth_card *card, int queue_num)
  * Note: Function assumes that we have 4 outbound queues.
  */
 int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb,
-			int ipv, int cast_type)
+			    int ipv)
 {
 	__be16 *tci;
 	u8 tos;
 
-	if (cast_type && card->info.is_multicast_different)
-		return card->info.is_multicast_different &
-			(card->qdio.no_out_queues - 1);
-
 	switch (card->qdio.do_prio_queueing) {
 	case QETH_PRIO_Q_ING_TOS:
 	case QETH_PRIO_Q_ING_PREC:
@@ -3882,6 +3801,17 @@ int qeth_get_elements_for_frags(struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags);
 
+static unsigned int qeth_count_elements(struct sk_buff *skb, int data_offset)
+{
+	unsigned int elements = qeth_get_elements_for_frags(skb);
+	addr_t end = (addr_t)skb->data + skb_headlen(skb);
+	addr_t start = (addr_t)skb->data + data_offset;
+
+	if (start != end)
+		elements += qeth_get_elements_for_range(start, end);
+	return elements;
+}
+
 /**
  * qeth_get_elements_no() -	find number of SBALEs for skb data, inc. frags.
  * @card:			qeth card structure, to check max. elems.
@@ -3897,12 +3827,7 @@ EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags);
 int qeth_get_elements_no(struct qeth_card *card,
 		     struct sk_buff *skb, int extra_elems, int data_offset)
 {
-	addr_t end = (addr_t)skb->data + skb_headlen(skb);
-	int elements = qeth_get_elements_for_frags(skb);
-	addr_t start = (addr_t)skb->data + data_offset;
-
-	if (start != end)
-		elements += qeth_get_elements_for_range(start, end);
+	int elements = qeth_count_elements(skb, data_offset);
 
 	if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) {
 		QETH_DBF_MESSAGE(2, "Invalid size of IP packet "
@@ -3936,32 +3861,87 @@ int qeth_hdr_chk_and_bounce(struct sk_buff *skb, struct qeth_hdr **hdr, int len)
 EXPORT_SYMBOL_GPL(qeth_hdr_chk_and_bounce);
 
 /**
- * qeth_push_hdr() - push a qeth_hdr onto an skb.
- * @skb: skb that the qeth_hdr should be pushed onto.
+ * qeth_add_hw_header() - add a HW header to an skb.
+ * @skb: skb that the HW header should be added to.
  * @hdr: double pointer to a qeth_hdr. When returning with >= 0,
  *	 it contains a valid pointer to a qeth_hdr.
- * @len: length of the hdr that needs to be pushed on.
+ * @hdr_len: length of the HW header.
+ * @proto_len: length of protocol headers that need to be in same page as the
+ *	       HW header.
  *
  * Returns the pushed length. If the header can't be pushed on
  * (eg. because it would cross a page boundary), it is allocated from
  * the cache instead and 0 is returned.
+ * The number of needed buffer elements is returned in @elements.
  * Error to create the hdr is indicated by returning with < 0.
  */
-int qeth_push_hdr(struct sk_buff *skb, struct qeth_hdr **hdr, unsigned int len)
-{
-	if (skb_headroom(skb) >= len &&
-	    qeth_get_elements_for_range((addr_t)skb->data - len,
-					(addr_t)skb->data) == 1) {
-		*hdr = skb_push(skb, len);
-		return len;
+int qeth_add_hw_header(struct qeth_card *card, struct sk_buff *skb,
+		       struct qeth_hdr **hdr, unsigned int hdr_len,
+		       unsigned int proto_len, unsigned int *elements)
+{
+	const unsigned int max_elements = QETH_MAX_BUFFER_ELEMENTS(card);
+	const unsigned int contiguous = proto_len ? proto_len : 1;
+	unsigned int __elements;
+	addr_t start, end;
+	bool push_ok;
+	int rc;
+
+check_layout:
+	start = (addr_t)skb->data - hdr_len;
+	end = (addr_t)skb->data;
+
+	if (qeth_get_elements_for_range(start, end + contiguous) == 1) {
+		/* Push HW header into same page as first protocol header. */
+		push_ok = true;
+		__elements = qeth_count_elements(skb, 0);
+	} else if (!proto_len && qeth_get_elements_for_range(start, end) == 1) {
+		/* Push HW header into a new page. */
+		push_ok = true;
+		__elements = 1 + qeth_count_elements(skb, 0);
+	} else {
+		/* Use header cache, copy protocol headers up. */
+		push_ok = false;
+		__elements = 1 + qeth_count_elements(skb, proto_len);
+	}
+
+	/* Compress skb to fit into one IO buffer: */
+	if (__elements > max_elements) {
+		if (!skb_is_nonlinear(skb)) {
+			/* Drop it, no easy way of shrinking it further. */
+			QETH_DBF_MESSAGE(2, "Dropped an oversized skb (Max Elements=%u / Actual=%u / Length=%u).\n",
+					 max_elements, __elements, skb->len);
+			return -E2BIG;
+		}
+
+		rc = skb_linearize(skb);
+		if (card->options.performance_stats) {
+			if (rc)
+				card->perf_stats.tx_linfail++;
+			else
+				card->perf_stats.tx_lin++;
+		}
+		if (rc)
+			return rc;
+
+		/* Linearization changed the layout, re-evaluate: */
+		goto check_layout;
+	}
+
+	*elements = __elements;
+	/* Add the header: */
+	if (push_ok) {
+		*hdr = skb_push(skb, hdr_len);
+		return hdr_len;
 	}
 	/* fall back */
 	*hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC);
 	if (!*hdr)
 		return -ENOMEM;
+	/* Copy protocol headers behind HW header: */
+	skb_copy_from_linear_data(skb, ((char *)*hdr) + hdr_len, proto_len);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(qeth_push_hdr);
+EXPORT_SYMBOL_GPL(qeth_add_hw_header);
 
 static void __qeth_fill_buffer(struct sk_buff *skb,
 			       struct qeth_qdio_out_buffer *buf,
@@ -4241,24 +4221,6 @@ void qeth_setadp_promisc_mode(struct qeth_card *card)
 }
 EXPORT_SYMBOL_GPL(qeth_setadp_promisc_mode);
 
-int qeth_change_mtu(struct net_device *dev, int new_mtu)
-{
-	struct qeth_card *card;
-	char dbf_text[15];
-
-	card = dev->ml_priv;
-
-	QETH_CARD_TEXT(card, 4, "chgmtu");
-	sprintf(dbf_text, "%8x", new_mtu);
-	QETH_CARD_TEXT(card, 4, dbf_text);
-
-	if (!qeth_mtu_is_valid(card, new_mtu))
-		return -EINVAL;
-	dev->mtu = new_mtu;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(qeth_change_mtu);
-
 struct net_device_stats *qeth_get_stats(struct net_device *dev)
 {
 	struct qeth_card *card;
@@ -4834,9 +4796,6 @@ int qeth_vm_request_mac(struct qeth_card *card)
 
 	QETH_DBF_TEXT(SETUP, 2, "vmreqmac");
 
-	if (!card->dev)
-		return -ENODEV;
-
 	request = kzalloc(sizeof(*request), GFP_KERNEL | GFP_DMA);
 	response = kzalloc(sizeof(*response), GFP_KERNEL | GFP_DMA);
 	if (!request || !response) {
@@ -5077,11 +5036,11 @@ out_free_nothing:
 
 static void qeth_core_free_card(struct qeth_card *card)
 {
-
 	QETH_DBF_TEXT(SETUP, 2, "freecrd");
 	QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *));
 	qeth_clean_channel(&card->read);
 	qeth_clean_channel(&card->write);
+	qeth_clean_channel(&card->data);
 	qeth_free_qdio_buffers(card);
 	unregister_service_level(&card->qeth_service_level);
 	kfree(card);
@@ -5716,6 +5675,53 @@ static void qeth_clear_dbf_list(void)
 	mutex_unlock(&qeth_dbf_list_mutex);
 }
 
+static struct net_device *qeth_alloc_netdev(struct qeth_card *card)
+{
+	struct net_device *dev;
+
+	switch (card->info.type) {
+	case QETH_CARD_TYPE_IQD:
+		dev = alloc_netdev(0, "hsi%d", NET_NAME_UNKNOWN, ether_setup);
+		break;
+	case QETH_CARD_TYPE_OSN:
+		dev = alloc_netdev(0, "osn%d", NET_NAME_UNKNOWN, ether_setup);
+		break;
+	default:
+		dev = alloc_etherdev(0);
+	}
+
+	if (!dev)
+		return NULL;
+
+	dev->ml_priv = card;
+	dev->watchdog_timeo = QETH_TX_TIMEOUT;
+	dev->min_mtu = IS_OSN(card) ? 64 : 576;
+	 /* initialized when device first goes online: */
+	dev->max_mtu = 0;
+	dev->mtu = 0;
+	SET_NETDEV_DEV(dev, &card->gdev->dev);
+	netif_carrier_off(dev);
+
+	if (!IS_OSN(card)) {
+		dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+		dev->hw_features |= NETIF_F_SG;
+		dev->vlan_features |= NETIF_F_SG;
+	}
+
+	return dev;
+}
+
+struct net_device *qeth_clone_netdev(struct net_device *orig)
+{
+	struct net_device *clone = qeth_alloc_netdev(orig->ml_priv);
+
+	if (!clone)
+		return NULL;
+
+	clone->dev_port = orig->dev_port;
+	return clone;
+}
+
 static int qeth_core_probe_device(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card;
@@ -5758,12 +5764,12 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev)
 	gdev->cdev[1]->handler = qeth_irq;
 	gdev->cdev[2]->handler = qeth_irq;
 
-	qeth_determine_card_type(card);
-	rc = qeth_setup_card(card);
-	if (rc) {
-		QETH_DBF_TEXT_(SETUP, 2, "2err%d", rc);
+	qeth_setup_card(card);
+	qeth_update_from_chp_desc(card);
+
+	card->dev = qeth_alloc_netdev(card);
+	if (!card->dev)
 		goto err_card;
-	}
 
 	qeth_determine_capabilities(card);
 	enforced_disc = qeth_enforce_discipline(card);
@@ -5775,7 +5781,7 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev)
 		card->info.layer_enforced = true;
 		rc = qeth_core_load_discipline(card, enforced_disc);
 		if (rc)
-			goto err_card;
+			goto err_load;
 
 		gdev->dev.type = (card->info.type != QETH_CARD_TYPE_OSN)
 					? card->discipline->devtype
@@ -5793,6 +5799,8 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev)
 
 err_disc:
 	qeth_core_free_discipline(card);
+err_load:
+	free_netdev(card->dev);
 err_card:
 	qeth_core_free_card(card);
 err_dev:
@@ -5815,10 +5823,10 @@ static void qeth_core_remove_device(struct ccwgroup_device *gdev)
 	write_lock_irqsave(&qeth_core_card_list.rwlock, flags);
 	list_del(&card->list);
 	write_unlock_irqrestore(&qeth_core_card_list.rwlock, flags);
+	free_netdev(card->dev);
 	qeth_core_free_card(card);
 	dev_set_drvdata(&gdev->dev, NULL);
 	put_device(&gdev->dev);
-	return;
 }
 
 static int qeth_core_set_online(struct ccwgroup_device *gdev)
@@ -5887,31 +5895,13 @@ static int qeth_core_restore(struct ccwgroup_device *gdev)
 	return 0;
 }
 
-static struct ccwgroup_driver qeth_core_ccwgroup_driver = {
-	.driver = {
-		.owner = THIS_MODULE,
-		.name = "qeth",
-	},
-	.ccw_driver = &qeth_ccw_driver,
-	.setup = qeth_core_probe_device,
-	.remove = qeth_core_remove_device,
-	.set_online = qeth_core_set_online,
-	.set_offline = qeth_core_set_offline,
-	.shutdown = qeth_core_shutdown,
-	.prepare = NULL,
-	.complete = NULL,
-	.freeze = qeth_core_freeze,
-	.thaw = qeth_core_thaw,
-	.restore = qeth_core_restore,
-};
-
 static ssize_t group_store(struct device_driver *ddrv, const char *buf,
 			   size_t count)
 {
 	int err;
 
-	err = ccwgroup_create_dev(qeth_core_root_dev,
-				  &qeth_core_ccwgroup_driver, 3, buf);
+	err = ccwgroup_create_dev(qeth_core_root_dev, to_ccwgroupdrv(ddrv), 3,
+				  buf);
 
 	return err ? err : count;
 }
@@ -5929,6 +5919,25 @@ static const struct attribute_group *qeth_drv_attr_groups[] = {
 	NULL,
 };
 
+static struct ccwgroup_driver qeth_core_ccwgroup_driver = {
+	.driver = {
+		.groups = qeth_drv_attr_groups,
+		.owner = THIS_MODULE,
+		.name = "qeth",
+	},
+	.ccw_driver = &qeth_ccw_driver,
+	.setup = qeth_core_probe_device,
+	.remove = qeth_core_remove_device,
+	.set_online = qeth_core_set_online,
+	.set_offline = qeth_core_set_offline,
+	.shutdown = qeth_core_shutdown,
+	.prepare = NULL,
+	.complete = NULL,
+	.freeze = qeth_core_freeze,
+	.thaw = qeth_core_thaw,
+	.restore = qeth_core_restore,
+};
+
 int qeth_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
 	struct qeth_card *card = dev->ml_priv;
@@ -5995,7 +6004,7 @@ static struct {
 	{"tx skbs packing"},
 	{"tx buffers packing"},
 	{"tx sg skbs"},
-	{"tx sg frags"},
+	{"tx buffer elements"},
 /* 10 */{"rx sg skbs"},
 	{"rx sg frags"},
 	{"rx sg page allocs"},
@@ -6054,7 +6063,7 @@ void qeth_core_get_ethtool_stats(struct net_device *dev,
 	data[6] = card->perf_stats.skbs_sent_pack;
 	data[7] = card->perf_stats.bufs_sent_pack;
 	data[8] = card->perf_stats.sg_skbs_sent;
-	data[9] = card->perf_stats.sg_frags_sent;
+	data[9] = card->perf_stats.buf_elements_sent;
 	data[10] = card->perf_stats.sg_skbs_rx;
 	data[11] = card->perf_stats.sg_frags_rx;
 	data[12] = card->perf_stats.sg_alloc_page_rx;
@@ -6620,7 +6629,6 @@ static int __init qeth_core_init(void)
 	rc = ccw_driver_register(&qeth_ccw_driver);
 	if (rc)
 		goto ccw_err;
-	qeth_core_ccwgroup_driver.driver.groups = qeth_drv_attr_groups;
 	rc = ccwgroup_driver_register(&qeth_core_ccwgroup_driver);
 	if (rc)
 		goto ccwgroup_err;
diff --git a/drivers/s390/net/qeth_core_mpc.c b/drivers/s390/net/qeth_core_mpc.c
index 22428b769f9b..5bcb8dafc3ee 100644
--- a/drivers/s390/net/qeth_core_mpc.c
+++ b/drivers/s390/net/qeth_core_mpc.c
@@ -146,17 +146,6 @@ unsigned char IPA_PDU_HEADER[] = {
 };
 EXPORT_SYMBOL_GPL(IPA_PDU_HEADER);
 
-unsigned char WRITE_CCW[] = {
-	0x01, CCW_FLAG_SLI, 0, 0,
-	0, 0, 0, 0
-};
-
-unsigned char READ_CCW[] = {
-	0x02, CCW_FLAG_SLI, 0, 0,
-	0, 0, 0, 0
-};
-
-
 struct ipa_rc_msg {
 	enum qeth_ipa_return_codes rc;
 	char *msg;
diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h
index 878e62f35169..aa8b9196b089 100644
--- a/drivers/s390/net/qeth_core_mpc.h
+++ b/drivers/s390/net/qeth_core_mpc.h
@@ -64,6 +64,9 @@ enum qeth_card_types {
 	QETH_CARD_TYPE_OSX     = 2,
 };
 
+#define IS_IQD(card)	((card)->info.type == QETH_CARD_TYPE_IQD)
+#define IS_OSN(card)	((card)->info.type == QETH_CARD_TYPE_OSN)
+
 #define QETH_MPC_DIFINFO_LEN_INDICATES_LINK_TYPE 0x18
 /* only the first two bytes are looked at in qeth_get_cardname_short */
 enum qeth_link_types {
@@ -815,10 +818,6 @@ extern char *qeth_get_ipa_cmd_name(enum qeth_ipa_cmds cmd);
 /* END OF   IP Assist related definitions                                    */
 /*****************************************************************************/
 
-
-extern unsigned char WRITE_CCW[];
-extern unsigned char READ_CCW[];
-
 extern unsigned char CM_ENABLE[];
 #define CM_ENABLE_SIZE 0x63
 #define QETH_CM_ENABLE_ISSUER_RM_TOKEN(buffer) (buffer + 0x2c)
diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c
index c3f18afb368b..25d0be25bcb3 100644
--- a/drivers/s390/net/qeth_core_sys.c
+++ b/drivers/s390/net/qeth_core_sys.c
@@ -112,7 +112,7 @@ static ssize_t qeth_dev_portno_show(struct device *dev,
 	if (!card)
 		return -EINVAL;
 
-	return sprintf(buf, "%i\n", card->info.portno);
+	return sprintf(buf, "%i\n", card->dev->dev_port);
 }
 
 static ssize_t qeth_dev_portno_store(struct device *dev,
@@ -143,9 +143,7 @@ static ssize_t qeth_dev_portno_store(struct device *dev,
 		rc = -EINVAL;
 		goto out;
 	}
-	card->info.portno = portno;
-	if (card->dev)
-		card->dev->dev_port = portno;
+	card->dev->dev_port = portno;
 out:
 	mutex_unlock(&card->conf_mutex);
 	return rc ? rc : count;
@@ -388,6 +386,7 @@ static ssize_t qeth_dev_layer2_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
 	struct qeth_card *card = dev_get_drvdata(dev);
+	struct net_device *ndev;
 	char *tmp;
 	int i, rc = 0;
 	enum qeth_discipline_id newdis;
@@ -424,8 +423,19 @@ static ssize_t qeth_dev_layer2_store(struct device *dev,
 
 	card->info.mac_bits = 0;
 	if (card->discipline) {
+		/* start with a new, pristine netdevice: */
+		ndev = qeth_clone_netdev(card->dev);
+		if (!ndev) {
+			rc = -ENOMEM;
+			goto out;
+		}
+
 		card->discipline->remove(card->gdev);
 		qeth_core_free_discipline(card);
+		card->options.layer2 = -1;
+
+		free_netdev(card->dev);
+		card->dev = ndev;
 	}
 
 	rc = qeth_core_load_discipline(card, newdis);
diff --git a/drivers/s390/net/qeth_l2.h b/drivers/s390/net/qeth_l2.h
index f2130051ca11..ddc615b431a8 100644
--- a/drivers/s390/net/qeth_l2.h
+++ b/drivers/s390/net/qeth_l2.h
@@ -14,6 +14,11 @@ extern const struct attribute_group *qeth_l2_attr_groups[];
 int qeth_l2_create_device_attributes(struct device *);
 void qeth_l2_remove_device_attributes(struct device *);
 void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card);
+int qeth_bridgeport_query_ports(struct qeth_card *card,
+				enum qeth_sbp_roles *role,
+				enum qeth_sbp_states *state);
+int qeth_bridgeport_setrole(struct qeth_card *card, enum qeth_sbp_roles role);
+int qeth_bridgeport_an_set(struct qeth_card *card, int enable);
 
 int qeth_l2_vnicc_set_state(struct qeth_card *card, u32 vnicc, bool state);
 int qeth_l2_vnicc_get_state(struct qeth_card *card, u32 vnicc, bool *state);
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 2487f0aeb165..710fa74892ae 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -26,7 +26,6 @@
 
 static int qeth_l2_set_offline(struct ccwgroup_device *);
 static int qeth_l2_stop(struct net_device *);
-static void qeth_l2_set_rx_mode(struct net_device *);
 static void qeth_bridgeport_query_support(struct qeth_card *card);
 static void qeth_bridge_state_change(struct qeth_card *card,
 					struct qeth_ipa_cmd *cmd);
@@ -186,12 +185,12 @@ static void qeth_l2_del_all_macs(struct qeth_card *card)
 static int qeth_l2_get_cast_type(struct qeth_card *card, struct sk_buff *skb)
 {
 	if (card->info.type == QETH_CARD_TYPE_OSN)
-		return RTN_UNSPEC;
+		return RTN_UNICAST;
 	if (is_broadcast_ether_addr(skb->data))
 		return RTN_BROADCAST;
 	if (is_multicast_ether_addr(skb->data))
 		return RTN_MULTICAST;
-	return RTN_UNSPEC;
+	return RTN_UNICAST;
 }
 
 static void qeth_l2_fill_header(struct qeth_hdr *hdr, struct sk_buff *skb,
@@ -344,7 +343,6 @@ static int qeth_l2_vlan_rx_kill_vid(struct net_device *dev,
 		rc = qeth_l2_send_setdelvlan(card, vid, IPA_CMD_DELVLAN);
 		kfree(tmpid);
 	}
-	qeth_l2_set_rx_mode(card->dev);
 	return rc;
 }
 
@@ -643,97 +641,58 @@ static void qeth_l2_set_rx_mode(struct net_device *dev)
 		qeth_promisc_to_bridge(card);
 }
 
-static int qeth_l2_xmit_iqd(struct qeth_card *card, struct sk_buff *skb,
-			    struct qeth_qdio_out_q *queue, int cast_type)
+static int qeth_l2_xmit(struct qeth_card *card, struct sk_buff *skb,
+			struct qeth_qdio_out_q *queue, int cast_type, int ipv)
 {
-	unsigned int data_offset = ETH_HLEN;
-	struct qeth_hdr *hdr;
-	int rc;
-
-	hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC);
-	if (!hdr)
-		return -ENOMEM;
-	qeth_l2_fill_header(hdr, skb, cast_type, skb->len);
-	skb_copy_from_linear_data(skb, ((char *)hdr) + sizeof(*hdr),
-				  data_offset);
-
-	if (!qeth_get_elements_no(card, skb, 1, data_offset)) {
-		rc = -E2BIG;
-		goto out;
-	}
-	rc = qeth_do_send_packet_fast(queue, skb, hdr, data_offset,
-				      sizeof(*hdr) + data_offset);
-out:
-	if (rc)
-		kmem_cache_free(qeth_core_header_cache, hdr);
-	return rc;
-}
-
-static int qeth_l2_xmit_osa(struct qeth_card *card, struct sk_buff *skb,
-			    struct qeth_qdio_out_q *queue, int cast_type,
-			    int ipv)
-{
-	int push_len = sizeof(struct qeth_hdr);
-	unsigned int elements, nr_frags;
-	unsigned int hdr_elements = 0;
+	const unsigned int proto_len = IS_IQD(card) ? ETH_HLEN : 0;
+	const unsigned int hw_hdr_len = sizeof(struct qeth_hdr);
+	unsigned int frame_len = skb->len;
+	unsigned int data_offset = 0;
 	struct qeth_hdr *hdr = NULL;
 	unsigned int hd_len = 0;
-	int rc;
-
-	/* fix hardware limitation: as long as we do not have sbal
-	 * chaining we can not send long frag lists
-	 */
-	if (!qeth_get_elements_no(card, skb, 0, 0)) {
-		rc = skb_linearize(skb);
-
-		if (card->options.performance_stats) {
-			if (rc)
-				card->perf_stats.tx_linfail++;
-			else
-				card->perf_stats.tx_lin++;
-		}
-		if (rc)
-			return rc;
-	}
-	nr_frags = skb_shinfo(skb)->nr_frags;
+	unsigned int elements;
+	int push_len, rc;
+	bool is_sg;
 
-	rc = skb_cow_head(skb, push_len);
+	rc = skb_cow_head(skb, hw_hdr_len);
 	if (rc)
 		return rc;
-	push_len = qeth_push_hdr(skb, &hdr, push_len);
+
+	push_len = qeth_add_hw_header(card, skb, &hdr, hw_hdr_len, proto_len,
+				      &elements);
 	if (push_len < 0)
 		return push_len;
 	if (!push_len) {
-		/* hdr was allocated from cache */
-		hd_len = sizeof(*hdr);
-		hdr_elements = 1;
+		/* HW header needs its own buffer element. */
+		hd_len = hw_hdr_len + proto_len;
+		data_offset = proto_len;
 	}
-	qeth_l2_fill_header(hdr, skb, cast_type, skb->len - push_len);
+	qeth_l2_fill_header(hdr, skb, cast_type, frame_len);
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		qeth_tx_csum(skb, &hdr->hdr.l2.flags[1], ipv);
 		if (card->options.performance_stats)
 			card->perf_stats.tx_csum++;
 	}
 
-	elements = qeth_get_elements_no(card, skb, hdr_elements, 0);
-	if (!elements) {
-		rc = -E2BIG;
-		goto out;
+	is_sg = skb_is_nonlinear(skb);
+	if (IS_IQD(card)) {
+		rc = qeth_do_send_packet_fast(queue, skb, hdr, data_offset,
+					      hd_len);
+	} else {
+		/* TODO: drop skb_orphan() once TX completion is fast enough */
+		skb_orphan(skb);
+		rc = qeth_do_send_packet(card, queue, skb, hdr, data_offset,
+					 hd_len, elements);
 	}
-	elements += hdr_elements;
 
-	/* TODO: remove the skb_orphan() once TX completion is fast enough */
-	skb_orphan(skb);
-	rc = qeth_do_send_packet(card, queue, skb, hdr, 0, hd_len, elements);
-out:
 	if (!rc) {
-		if (card->options.performance_stats && nr_frags) {
-			card->perf_stats.sg_skbs_sent++;
-			/* nr_frags + skb->data */
-			card->perf_stats.sg_frags_sent += nr_frags + 1;
+		if (card->options.performance_stats) {
+			card->perf_stats.buf_elements_sent += elements;
+			if (is_sg)
+				card->perf_stats.sg_skbs_sent++;
 		}
 	} else {
-		if (hd_len)
+		if (!push_len)
 			kmem_cache_free(qeth_core_header_cache, hdr);
 		if (rc == -EBUSY)
 			/* roll back to ETH header */
@@ -770,34 +729,23 @@ static netdev_tx_t qeth_l2_hard_start_xmit(struct sk_buff *skb,
 	int tx_bytes = skb->len;
 	int rc;
 
-	if (card->qdio.do_prio_queueing || (cast_type &&
-					card->info.is_multicast_different))
-		queue = card->qdio.out_qs[qeth_get_priority_queue(card, skb,
-					ipv, cast_type)];
-	else
-		queue = card->qdio.out_qs[card->qdio.default_out_queue];
-
 	if ((card->state != CARD_STATE_UP) || !card->lan_online) {
 		card->stats.tx_carrier_errors++;
 		goto tx_drop;
 	}
 
+	queue = qeth_get_tx_queue(card, skb, ipv, cast_type);
+
 	if (card->options.performance_stats) {
 		card->perf_stats.outbound_cnt++;
 		card->perf_stats.outbound_start_time = qeth_get_micros();
 	}
 	netif_stop_queue(dev);
 
-	switch (card->info.type) {
-	case QETH_CARD_TYPE_OSN:
+	if (IS_OSN(card))
 		rc = qeth_l2_xmit_osn(card, skb, queue);
-		break;
-	case QETH_CARD_TYPE_IQD:
-		rc = qeth_l2_xmit_iqd(card, skb, queue, cast_type);
-		break;
-	default:
-		rc = qeth_l2_xmit_osa(card, skb, queue, cast_type, ipv);
-	}
+	else
+		rc = qeth_l2_xmit(card, skb, queue, cast_type, ipv);
 
 	if (!rc) {
 		card->stats.tx_packets++;
@@ -906,13 +854,7 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev)
 
 	if (cgdev->state == CCWGROUP_ONLINE)
 		qeth_l2_set_offline(cgdev);
-
-	if (card->dev) {
-		unregister_netdev(card->dev);
-		free_netdev(card->dev);
-		card->dev = NULL;
-	}
-	return;
+	unregister_netdev(card->dev);
 }
 
 static const struct ethtool_ops qeth_l2_ethtool_ops = {
@@ -941,7 +883,6 @@ static const struct net_device_ops qeth_l2_netdev_ops = {
 	.ndo_set_rx_mode	= qeth_l2_set_rx_mode,
 	.ndo_do_ioctl		= qeth_do_ioctl,
 	.ndo_set_mac_address    = qeth_l2_set_mac_address,
-	.ndo_change_mtu	   	= qeth_change_mtu,
 	.ndo_vlan_rx_add_vid	= qeth_l2_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid   = qeth_l2_vlan_rx_kill_vid,
 	.ndo_tx_timeout	   	= qeth_tx_timeout,
@@ -951,35 +892,19 @@ static const struct net_device_ops qeth_l2_netdev_ops = {
 
 static int qeth_l2_setup_netdev(struct qeth_card *card)
 {
-	switch (card->info.type) {
-	case QETH_CARD_TYPE_IQD:
-		card->dev = alloc_netdev(0, "hsi%d", NET_NAME_UNKNOWN,
-					 ether_setup);
-		break;
-	case QETH_CARD_TYPE_OSN:
-		card->dev = alloc_netdev(0, "osn%d", NET_NAME_UNKNOWN,
-					 ether_setup);
-		break;
-	default:
-		card->dev = alloc_etherdev(0);
-	}
+	int rc;
 
-	if (!card->dev)
-		return -ENODEV;
+	if (card->dev->netdev_ops)
+		return 0;
 
-	card->dev->ml_priv = card;
 	card->dev->priv_flags |= IFF_UNICAST_FLT;
-	card->dev->watchdog_timeo = QETH_TX_TIMEOUT;
-	card->dev->mtu = card->info.initial_mtu;
-	card->dev->min_mtu = 64;
-	card->dev->max_mtu = ETH_MAX_MTU;
-	card->dev->dev_port = card->info.portno;
 	card->dev->netdev_ops = &qeth_l2_netdev_ops;
 	if (card->info.type == QETH_CARD_TYPE_OSN) {
 		card->dev->ethtool_ops = &qeth_l2_osn_ops;
 		card->dev->flags |= IFF_NOARP;
 	} else {
 		card->dev->ethtool_ops = &qeth_l2_ethtool_ops;
+		card->dev->needed_headroom = sizeof(struct qeth_hdr);
 	}
 
 	if (card->info.type == QETH_CARD_TYPE_OSM)
@@ -987,14 +912,6 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 	else
 		card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 
-	if (card->info.type != QETH_CARD_TYPE_OSN &&
-	    card->info.type != QETH_CARD_TYPE_IQD) {
-		card->dev->priv_flags &= ~IFF_TX_SKB_SHARING;
-		card->dev->needed_headroom = sizeof(struct qeth_hdr);
-		card->dev->hw_features |= NETIF_F_SG;
-		card->dev->vlan_features |= NETIF_F_SG;
-	}
-
 	if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) {
 		card->dev->features |= NETIF_F_SG;
 		/* OSA 3S and earlier has no RX/TX support */
@@ -1013,12 +930,12 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 		card->dev->vlan_features |= NETIF_F_RXCSUM;
 	}
 
-	card->info.broadcast_capable = 1;
 	qeth_l2_request_initial_mac(card);
-	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
 	netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT);
-	netif_carrier_off(card->dev);
-	return register_netdev(card->dev);
+	rc = register_netdev(card->dev);
+	if (rc)
+		card->dev->netdev_ops = NULL;
+	return rc;
 }
 
 static int qeth_l2_start_ipassists(struct qeth_card *card)
@@ -1064,10 +981,9 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 		dev_info(&card->gdev->dev,
 		"The device represents a Bridge Capable Port\n");
 
-	if (!card->dev && qeth_l2_setup_netdev(card)) {
-		rc = -ENODEV;
+	rc = qeth_l2_setup_netdev(card);
+	if (rc)
 		goto out_remove;
-	}
 
 	if (card->info.type != QETH_CARD_TYPE_OSN &&
 	    !qeth_l2_send_setmac(card, card->dev->dev_addr))
@@ -1125,13 +1041,12 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 		if (recovery_mode &&
 		    card->info.type != QETH_CARD_TYPE_OSN) {
 			__qeth_l2_open(card->dev);
+			qeth_l2_set_rx_mode(card->dev);
 		} else {
 			rtnl_lock();
 			dev_open(card->dev);
 			rtnl_unlock();
 		}
-		/* this also sets saved unicast addresses */
-		qeth_l2_set_rx_mode(card->dev);
 	}
 	/* let user_space know that device is online */
 	kobject_uevent(&gdev->dev.kobj, KOBJ_CHANGE);
@@ -1171,8 +1086,7 @@ static int __qeth_l2_set_offline(struct ccwgroup_device *cgdev,
 	QETH_DBF_TEXT(SETUP, 3, "setoffl");
 	QETH_DBF_HEX(SETUP, 3, &card, sizeof(void *));
 
-	if (card->dev && netif_carrier_ok(card->dev))
-		netif_carrier_off(card->dev);
+	netif_carrier_off(card->dev);
 	recover_flag = card->state;
 	if ((!recovery_mode && card->info.hwtrap) || card->info.hwtrap == 2) {
 		qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
@@ -1245,8 +1159,7 @@ static int qeth_l2_pm_suspend(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
 
-	if (card->dev)
-		netif_device_detach(card->dev);
+	netif_device_detach(card->dev);
 	qeth_set_allowed_threads(card, 0, 1);
 	wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
 	if (gdev->state == CCWGROUP_OFFLINE)
@@ -1279,8 +1192,7 @@ static int qeth_l2_pm_resume(struct ccwgroup_device *gdev)
 		rc = __qeth_l2_set_online(card->gdev, 0);
 out:
 	qeth_set_allowed_threads(card, 0xffffffff, 0);
-	if (card->dev)
-		netif_device_attach(card->dev);
+	netif_device_attach(card->dev);
 	if (rc)
 		dev_warn(&card->gdev->dev, "The qeth device driver "
 			"failed to recover an error on the device\n");
@@ -1327,25 +1239,26 @@ EXPORT_SYMBOL_GPL(qeth_l2_discipline);
 static int qeth_osn_send_control_data(struct qeth_card *card, int len,
 			   struct qeth_cmd_buffer *iob)
 {
+	struct qeth_channel *channel = iob->channel;
 	unsigned long flags;
 	int rc = 0;
 
 	QETH_CARD_TEXT(card, 5, "osndctrd");
 
 	wait_event(card->wait_q,
-		   atomic_cmpxchg(&card->write.irq_pending, 0, 1) == 0);
+		   atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0);
 	qeth_prepare_control_data(card, len, iob);
 	QETH_CARD_TEXT(card, 6, "osnoirqp");
-	spin_lock_irqsave(get_ccwdev_lock(card->write.ccwdev), flags);
-	rc = ccw_device_start_timeout(CARD_WDEV(card), &card->write.ccw,
+	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
+	rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw,
 				      (addr_t) iob, 0, 0, QETH_IPA_TIMEOUT);
-	spin_unlock_irqrestore(get_ccwdev_lock(card->write.ccwdev), flags);
+	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
 	if (rc) {
 		QETH_DBF_MESSAGE(2, "qeth_osn_send_control_data: "
 			   "ccw_device_start rc = %i\n", rc);
 		QETH_CARD_TEXT_(card, 2, " err%d", rc);
-		qeth_release_buffer(iob->channel, iob);
-		atomic_set(&card->write.irq_pending, 0);
+		qeth_release_buffer(channel, iob);
+		atomic_set(&channel->irq_pending, 0);
 		wake_up(&card->wait_q);
 	}
 	return rc;
@@ -1358,7 +1271,7 @@ static int qeth_osn_send_ipa_cmd(struct qeth_card *card,
 
 	QETH_CARD_TEXT(card, 4, "osndipa");
 
-	qeth_prepare_ipa_cmd(card, iob, QETH_PROT_OSN2);
+	qeth_prepare_ipa_cmd(card, iob);
 	s1 = (u16)(IPA_PDU_HEADER_SIZE + data_len);
 	s2 = (u16)data_len;
 	memcpy(QETH_IPA_PDU_LEN_TOTAL(iob->data), &s1, 2);
@@ -1877,7 +1790,6 @@ int qeth_bridgeport_query_ports(struct qeth_card *card,
 		return rc;
 	return qeth_bridgeport_makerc(card, &cbctl, IPA_SBP_QUERY_BRIDGE_PORTS);
 }
-EXPORT_SYMBOL_GPL(qeth_bridgeport_query_ports);
 
 static int qeth_bridgeport_set_cb(struct qeth_card *card,
 	struct qeth_reply *reply, unsigned long data)
@@ -2025,7 +1937,6 @@ int qeth_bridgeport_an_set(struct qeth_card *card, int enable)
 		rc = qdio_pnso_brinfo(schid, 0, &response, NULL, NULL);
 	return qeth_anset_makerc(card, rc, response);
 }
-EXPORT_SYMBOL_GPL(qeth_bridgeport_an_set);
 
 static bool qeth_bridgeport_is_in_use(struct qeth_card *card)
 {
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 5905dc63e256..7175086677fb 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -117,9 +117,9 @@ static bool qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
 	int rc = 0;
 
 	if (!card->ipato.enabled)
-		return 0;
+		return false;
 	if (addr->type != QETH_IP_TYPE_NORMAL)
-		return 0;
+		return false;
 
 	qeth_l3_convert_addr_to_bits((u8 *) &addr->u, addr_bits,
 				  (addr->proto == QETH_PROT_IPV4)? 4:16);
@@ -1978,17 +1978,17 @@ static int qeth_l3_get_cast_type(struct sk_buff *skb)
 		    (cast_type == RTN_MULTICAST) ||
 		    (cast_type == RTN_ANYCAST))
 			return cast_type;
-		return RTN_UNSPEC;
+		return RTN_UNICAST;
 	}
 	rcu_read_unlock();
 
 	/* no neighbour (eg AF_PACKET), fall back to target's IP address ... */
 	if (be16_to_cpu(skb->protocol) == ETH_P_IPV6)
 		return ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) ?
-				RTN_MULTICAST : RTN_UNSPEC;
+				RTN_MULTICAST : RTN_UNICAST;
 	else if (be16_to_cpu(skb->protocol) == ETH_P_IP)
 		return ipv4_is_multicast(ip_hdr(skb)->daddr) ?
-				RTN_MULTICAST : RTN_UNSPEC;
+				RTN_MULTICAST : RTN_UNICAST;
 
 	/* ... and MAC address */
 	if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, skb->dev->broadcast))
@@ -1997,22 +1997,21 @@ static int qeth_l3_get_cast_type(struct sk_buff *skb)
 		return RTN_MULTICAST;
 
 	/* default to unicast */
-	return RTN_UNSPEC;
+	return RTN_UNICAST;
 }
 
-static void qeth_l3_fill_af_iucv_hdr(struct qeth_card *card,
-		struct qeth_hdr *hdr, struct sk_buff *skb)
+static void qeth_l3_fill_af_iucv_hdr(struct qeth_hdr *hdr, struct sk_buff *skb,
+				     unsigned int data_len)
 {
 	char daddr[16];
 	struct af_iucv_trans_hdr *iucv_hdr;
 
 	memset(hdr, 0, sizeof(struct qeth_hdr));
 	hdr->hdr.l3.id = QETH_HEADER_TYPE_LAYER3;
-	hdr->hdr.l3.ext_flags = 0;
-	hdr->hdr.l3.length = skb->len - ETH_HLEN;
+	hdr->hdr.l3.length = data_len;
 	hdr->hdr.l3.flags = QETH_HDR_IPV6 | QETH_CAST_UNICAST;
 
-	iucv_hdr = (struct af_iucv_trans_hdr *) (skb->data + ETH_HLEN);
+	iucv_hdr = (struct af_iucv_trans_hdr *)(skb_mac_header(skb) + ETH_HLEN);
 	memset(daddr, 0, sizeof(daddr));
 	daddr[0] = 0xfe;
 	daddr[1] = 0x80;
@@ -2051,6 +2050,12 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr,
 		hdr->hdr.l3.vlan_id = skb_vlan_tag_get(skb);
 	}
 
+	if (!skb_is_gso(skb) && skb->ip_summed == CHECKSUM_PARTIAL) {
+		qeth_tx_csum(skb, &hdr->hdr.l3.ext_flags, ipv);
+		if (card->options.performance_stats)
+			card->perf_stats.tx_csum++;
+	}
+
 	/* OSA only: */
 	if (!ipv) {
 		hdr->hdr.l3.flags = QETH_HDR_PASSTHRU;
@@ -2156,106 +2161,121 @@ static int qeth_l3_get_elements_no_tso(struct qeth_card *card,
 	return elements;
 }
 
-static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
-					   struct net_device *dev)
+static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb,
+				struct qeth_qdio_out_q *queue, int ipv,
+				int cast_type)
 {
-	int rc;
-	__be16 *tag;
+	const unsigned int hw_hdr_len = sizeof(struct qeth_hdr);
+	unsigned int frame_len, elements;
+	unsigned char eth_hdr[ETH_HLEN];
 	struct qeth_hdr *hdr = NULL;
-	int hdr_elements = 0;
-	int elements;
-	struct qeth_card *card = dev->ml_priv;
-	struct sk_buff *new_skb = NULL;
-	int ipv = qeth_get_ip_version(skb);
-	int cast_type = qeth_l3_get_cast_type(skb);
-	struct qeth_qdio_out_q *queue =
-		card->qdio.out_qs[card->qdio.do_prio_queueing
-			|| (cast_type && card->info.is_multicast_different) ?
-			qeth_get_priority_queue(card, skb, ipv, cast_type) :
-			card->qdio.default_out_queue];
-	int tx_bytes = skb->len;
 	unsigned int hd_len = 0;
-	bool use_tso;
-	int data_offset = -1;
-	unsigned int nr_frags;
-
-	if (((card->info.type == QETH_CARD_TYPE_IQD) &&
-	     (((card->options.cq != QETH_CQ_ENABLED) && !ipv) ||
-	      ((card->options.cq == QETH_CQ_ENABLED) &&
-	       (be16_to_cpu(skb->protocol) != ETH_P_AF_IUCV)))) ||
-	    card->options.sniffer)
-			goto tx_drop;
+	int push_len, rc;
+	bool is_sg;
 
-	if ((card->state != CARD_STATE_UP) || !card->lan_online) {
-		card->stats.tx_carrier_errors++;
-		goto tx_drop;
+	/* re-use the L2 header area for the HW header: */
+	rc = skb_cow_head(skb, hw_hdr_len - ETH_HLEN);
+	if (rc)
+		return rc;
+	skb_copy_from_linear_data(skb, eth_hdr, ETH_HLEN);
+	skb_pull(skb, ETH_HLEN);
+	frame_len = skb->len;
+
+	push_len = qeth_add_hw_header(card, skb, &hdr, hw_hdr_len, 0,
+				      &elements);
+	if (push_len < 0)
+		return push_len;
+	if (!push_len) {
+		/* hdr was added discontiguous from skb->data */
+		hd_len = hw_hdr_len;
 	}
 
-	if ((cast_type == RTN_BROADCAST) &&
-	    (card->info.broadcast_capable == 0))
-		goto tx_drop;
+	if (skb->protocol == htons(ETH_P_AF_IUCV))
+		qeth_l3_fill_af_iucv_hdr(hdr, skb, frame_len);
+	else
+		qeth_l3_fill_header(card, hdr, skb, ipv, cast_type, frame_len);
 
-	if (card->options.performance_stats) {
-		card->perf_stats.outbound_cnt++;
-		card->perf_stats.outbound_start_time = qeth_get_micros();
+	is_sg = skb_is_nonlinear(skb);
+	if (IS_IQD(card)) {
+		rc = qeth_do_send_packet_fast(queue, skb, hdr, 0, hd_len);
+	} else {
+		/* TODO: drop skb_orphan() once TX completion is fast enough */
+		skb_orphan(skb);
+		rc = qeth_do_send_packet(card, queue, skb, hdr, 0, hd_len,
+					 elements);
 	}
 
+	if (!rc) {
+		if (card->options.performance_stats) {
+			card->perf_stats.buf_elements_sent += elements;
+			if (is_sg)
+				card->perf_stats.sg_skbs_sent++;
+		}
+	} else {
+		if (!push_len)
+			kmem_cache_free(qeth_core_header_cache, hdr);
+		if (rc == -EBUSY) {
+			/* roll back to ETH header */
+			skb_pull(skb, push_len);
+			skb_push(skb, ETH_HLEN);
+			skb_copy_to_linear_data(skb, eth_hdr, ETH_HLEN);
+		}
+	}
+	return rc;
+}
+
+static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb,
+			struct qeth_qdio_out_q *queue, int ipv, int cast_type)
+{
+	int elements, len, rc;
+	__be16 *tag;
+	struct qeth_hdr *hdr = NULL;
+	int hdr_elements = 0;
+	struct sk_buff *new_skb = NULL;
+	int tx_bytes = skb->len;
+	unsigned int hd_len;
+	bool use_tso, is_sg;
+
 	/* Ignore segment size from skb_is_gso(), 1 page is always used. */
 	use_tso = skb_is_gso(skb) &&
 		  (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4);
 
-	if (card->info.type == QETH_CARD_TYPE_IQD) {
-		new_skb = skb;
-		data_offset = ETH_HLEN;
-		hd_len = sizeof(*hdr);
-		hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC);
-		if (!hdr)
-			goto tx_drop;
-		hdr_elements++;
-	} else {
-		/* create a clone with writeable headroom */
-		new_skb = skb_realloc_headroom(skb, sizeof(struct qeth_hdr_tso)
-					+ VLAN_HLEN);
-		if (!new_skb)
-			goto tx_drop;
-
-		if (ipv == 4) {
-			skb_pull(new_skb, ETH_HLEN);
-		}
+	/* create a clone with writeable headroom */
+	new_skb = skb_realloc_headroom(skb, sizeof(struct qeth_hdr_tso) +
+					    VLAN_HLEN);
+	if (!new_skb)
+		return -ENOMEM;
 
-		if (ipv != 4 && skb_vlan_tag_present(new_skb)) {
-			skb_push(new_skb, VLAN_HLEN);
-			skb_copy_to_linear_data(new_skb, new_skb->data + 4, 4);
-			skb_copy_to_linear_data_offset(new_skb, 4,
-				new_skb->data + 8, 4);
-			skb_copy_to_linear_data_offset(new_skb, 8,
-				new_skb->data + 12, 4);
-			tag = (__be16 *)(new_skb->data + 12);
-			*tag = cpu_to_be16(ETH_P_8021Q);
-			*(tag + 1) = cpu_to_be16(skb_vlan_tag_get(new_skb));
-		}
+	if (ipv == 4) {
+		skb_pull(new_skb, ETH_HLEN);
+	} else if (skb_vlan_tag_present(new_skb)) {
+		skb_push(new_skb, VLAN_HLEN);
+		skb_copy_to_linear_data(new_skb, new_skb->data + 4, 4);
+		skb_copy_to_linear_data_offset(new_skb, 4,
+					       new_skb->data + 8, 4);
+		skb_copy_to_linear_data_offset(new_skb, 8,
+					       new_skb->data + 12, 4);
+		tag = (__be16 *)(new_skb->data + 12);
+		*tag = cpu_to_be16(ETH_P_8021Q);
+		*(tag + 1) = cpu_to_be16(skb_vlan_tag_get(new_skb));
 	}
 
-	netif_stop_queue(dev);
-
 	/* fix hardware limitation: as long as we do not have sbal
 	 * chaining we can not send long frag lists
 	 */
-	if ((card->info.type != QETH_CARD_TYPE_IQD) &&
-	    ((use_tso && !qeth_l3_get_elements_no_tso(card, new_skb, 1)) ||
-	     (!use_tso && !qeth_get_elements_no(card, new_skb, 0, 0)))) {
-		int lin_rc = skb_linearize(new_skb);
+	if ((use_tso && !qeth_l3_get_elements_no_tso(card, new_skb, 1)) ||
+	    (!use_tso && !qeth_get_elements_no(card, new_skb, 0, 0))) {
+		rc = skb_linearize(new_skb);
 
 		if (card->options.performance_stats) {
-			if (lin_rc)
+			if (rc)
 				card->perf_stats.tx_linfail++;
 			else
 				card->perf_stats.tx_lin++;
 		}
-		if (lin_rc)
-			goto tx_drop;
+		if (rc)
+			goto out;
 	}
-	nr_frags = skb_shinfo(new_skb)->nr_frags;
 
 	if (use_tso) {
 		hdr = skb_push(new_skb, sizeof(struct qeth_hdr_tso));
@@ -2265,97 +2285,112 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
 		qeth_tso_fill_header(card, hdr, new_skb);
 		hdr_elements++;
 	} else {
-		if (data_offset < 0) {
-			hdr = skb_push(new_skb, sizeof(struct qeth_hdr));
-			qeth_l3_fill_header(card, hdr, new_skb, ipv, cast_type,
-					    new_skb->len -
-					    sizeof(struct qeth_hdr));
-		} else {
-			if (be16_to_cpu(new_skb->protocol) == ETH_P_AF_IUCV)
-				qeth_l3_fill_af_iucv_hdr(card, hdr, new_skb);
-			else {
-				qeth_l3_fill_header(card, hdr, new_skb, ipv,
-						    cast_type,
-						    new_skb->len - data_offset);
-			}
-		}
-
-		if (new_skb->ip_summed == CHECKSUM_PARTIAL) {
-			qeth_tx_csum(new_skb, &hdr->hdr.l3.ext_flags, ipv);
-			if (card->options.performance_stats)
-				card->perf_stats.tx_csum++;
-		}
+		hdr = skb_push(new_skb, sizeof(struct qeth_hdr));
+		qeth_l3_fill_header(card, hdr, new_skb, ipv, cast_type,
+				    new_skb->len - sizeof(struct qeth_hdr));
 	}
 
 	elements = use_tso ?
 		   qeth_l3_get_elements_no_tso(card, new_skb, hdr_elements) :
-		   qeth_get_elements_no(card, new_skb, hdr_elements,
-					(data_offset > 0) ? data_offset : 0);
+		   qeth_get_elements_no(card, new_skb, hdr_elements, 0);
 	if (!elements) {
-		if (data_offset >= 0)
-			kmem_cache_free(qeth_core_header_cache, hdr);
-		goto tx_drop;
+		rc = -E2BIG;
+		goto out;
 	}
 	elements += hdr_elements;
 
-	if (card->info.type != QETH_CARD_TYPE_IQD) {
-		int len;
-		if (use_tso) {
-			hd_len = sizeof(struct qeth_hdr_tso) +
-				 ip_hdrlen(new_skb) + tcp_hdrlen(new_skb);
-			len = hd_len;
-		} else {
-			len = sizeof(struct qeth_hdr_layer3);
-		}
+	if (use_tso) {
+		hd_len = sizeof(struct qeth_hdr_tso) +
+			 ip_hdrlen(new_skb) + tcp_hdrlen(new_skb);
+		len = hd_len;
+	} else {
+		hd_len = 0;
+		len = sizeof(struct qeth_hdr_layer3);
+	}
 
-		if (qeth_hdr_chk_and_bounce(new_skb, &hdr, len))
-			goto tx_drop;
-		rc = qeth_do_send_packet(card, queue, new_skb, hdr, hd_len,
-					 hd_len, elements);
-	} else
-		rc = qeth_do_send_packet_fast(queue, new_skb, hdr, data_offset,
-					      hd_len);
+	if (qeth_hdr_chk_and_bounce(new_skb, &hdr, len)) {
+		rc = -EINVAL;
+		goto out;
+	}
 
+	is_sg = skb_is_nonlinear(new_skb);
+	rc = qeth_do_send_packet(card, queue, new_skb, hdr, hd_len, hd_len,
+				 elements);
+out:
 	if (!rc) {
-		card->stats.tx_packets++;
-		card->stats.tx_bytes += tx_bytes;
 		if (new_skb != skb)
 			dev_kfree_skb_any(skb);
 		if (card->options.performance_stats) {
+			card->perf_stats.buf_elements_sent += elements;
+			if (is_sg)
+				card->perf_stats.sg_skbs_sent++;
 			if (use_tso) {
 				card->perf_stats.large_send_bytes += tx_bytes;
 				card->perf_stats.large_send_cnt++;
 			}
-			if (nr_frags) {
-				card->perf_stats.sg_skbs_sent++;
-				/* nr_frags + skb->data */
-				card->perf_stats.sg_frags_sent += nr_frags + 1;
-			}
 		}
-		rc = NETDEV_TX_OK;
 	} else {
-		if (data_offset >= 0)
-			kmem_cache_free(qeth_core_header_cache, hdr);
+		if (new_skb != skb)
+			dev_kfree_skb_any(new_skb);
+	}
+	return rc;
+}
 
-		if (rc == -EBUSY) {
-			if (new_skb != skb)
-				dev_kfree_skb_any(new_skb);
-			return NETDEV_TX_BUSY;
-		} else
+static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
+					   struct net_device *dev)
+{
+	int cast_type = qeth_l3_get_cast_type(skb);
+	struct qeth_card *card = dev->ml_priv;
+	int ipv = qeth_get_ip_version(skb);
+	struct qeth_qdio_out_q *queue;
+	int tx_bytes = skb->len;
+	int rc;
+
+	if (IS_IQD(card)) {
+		if (card->options.sniffer)
+			goto tx_drop;
+		if ((card->options.cq != QETH_CQ_ENABLED && !ipv) ||
+		    (card->options.cq == QETH_CQ_ENABLED &&
+		     skb->protocol != htons(ETH_P_AF_IUCV)))
 			goto tx_drop;
 	}
 
-	netif_wake_queue(dev);
-	if (card->options.performance_stats)
-		card->perf_stats.outbound_time += qeth_get_micros() -
-			card->perf_stats.outbound_start_time;
-	return rc;
+	if (card->state != CARD_STATE_UP || !card->lan_online) {
+		card->stats.tx_carrier_errors++;
+		goto tx_drop;
+	}
+
+	if (cast_type == RTN_BROADCAST && !card->info.broadcast_capable)
+		goto tx_drop;
+
+	queue = qeth_get_tx_queue(card, skb, ipv, cast_type);
+
+	if (card->options.performance_stats) {
+		card->perf_stats.outbound_cnt++;
+		card->perf_stats.outbound_start_time = qeth_get_micros();
+	}
+	netif_stop_queue(dev);
+
+	if (IS_IQD(card) || (!skb_is_gso(skb) && ipv == 4))
+		rc = qeth_l3_xmit_offload(card, skb, queue, ipv, cast_type);
+	else
+		rc = qeth_l3_xmit(card, skb, queue, ipv, cast_type);
+
+	if (!rc) {
+		card->stats.tx_packets++;
+		card->stats.tx_bytes += tx_bytes;
+		if (card->options.performance_stats)
+			card->perf_stats.outbound_time += qeth_get_micros() -
+				card->perf_stats.outbound_start_time;
+		netif_wake_queue(dev);
+		return NETDEV_TX_OK;
+	} else if (rc == -EBUSY) {
+		return NETDEV_TX_BUSY;
+	} /* else fall through */
 
 tx_drop:
 	card->stats.tx_dropped++;
 	card->stats.tx_errors++;
-	if ((new_skb != skb) && new_skb)
-		dev_kfree_skb_any(new_skb);
 	dev_kfree_skb_any(skb);
 	netif_wake_queue(dev);
 	return NETDEV_TX_OK;
@@ -2449,7 +2484,6 @@ static const struct net_device_ops qeth_l3_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= qeth_l3_set_rx_mode,
 	.ndo_do_ioctl		= qeth_do_ioctl,
-	.ndo_change_mtu		= qeth_change_mtu,
 	.ndo_fix_features	= qeth_fix_features,
 	.ndo_set_features	= qeth_set_features,
 	.ndo_vlan_rx_add_vid	= qeth_l3_vlan_rx_add_vid,
@@ -2466,7 +2500,6 @@ static const struct net_device_ops qeth_l3_osa_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= qeth_l3_set_rx_mode,
 	.ndo_do_ioctl		= qeth_do_ioctl,
-	.ndo_change_mtu		= qeth_change_mtu,
 	.ndo_fix_features	= qeth_fix_features,
 	.ndo_set_features	= qeth_set_features,
 	.ndo_vlan_rx_add_vid	= qeth_l3_vlan_rx_add_vid,
@@ -2479,6 +2512,9 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 {
 	int rc;
 
+	if (card->dev->netdev_ops)
+		return 0;
+
 	if (card->info.type == QETH_CARD_TYPE_OSD ||
 	    card->info.type == QETH_CARD_TYPE_OSX) {
 		if ((card->info.link_type == QETH_LINK_TYPE_LANE_TR) ||
@@ -2487,9 +2523,6 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 			return -ENODEV;
 		}
 
-		card->dev = alloc_etherdev(0);
-		if (!card->dev)
-			return -ENODEV;
 		card->dev->netdev_ops = &qeth_l3_osa_netdev_ops;
 
 		/*IPv6 address autoconfiguration stuff*/
@@ -2497,9 +2530,6 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 		if (!(card->info.unique_id & UNIQUE_ID_NOT_BY_CARD))
 			card->dev->dev_id = card->info.unique_id & 0xffff;
 
-		card->dev->hw_features |= NETIF_F_SG;
-		card->dev->vlan_features |= NETIF_F_SG;
-
 		if (!card->info.guestlan) {
 			card->dev->features |= NETIF_F_SG;
 			card->dev->hw_features |= NETIF_F_TSO |
@@ -2513,38 +2543,35 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 			card->dev->vlan_features |= NETIF_F_IPV6_CSUM;
 		}
 	} else if (card->info.type == QETH_CARD_TYPE_IQD) {
-		card->dev = alloc_netdev(0, "hsi%d", NET_NAME_UNKNOWN,
-					 ether_setup);
-		if (!card->dev)
-			return -ENODEV;
 		card->dev->flags |= IFF_NOARP;
 		card->dev->netdev_ops = &qeth_l3_netdev_ops;
+
 		rc = qeth_l3_iqd_read_initial_mac(card);
 		if (rc)
-			return rc;
+			goto out;
+
 		if (card->options.hsuid[0])
 			memcpy(card->dev->perm_addr, card->options.hsuid, 9);
 	} else
 		return -ENODEV;
 
-	card->dev->ml_priv = card;
-	card->dev->watchdog_timeo = QETH_TX_TIMEOUT;
-	card->dev->mtu = card->info.initial_mtu;
-	card->dev->min_mtu = 64;
-	card->dev->max_mtu = ETH_MAX_MTU;
-	card->dev->dev_port = card->info.portno;
 	card->dev->ethtool_ops = &qeth_l3_ethtool_ops;
+	card->dev->needed_headroom = sizeof(struct qeth_hdr) - ETH_HLEN;
 	card->dev->features |=	NETIF_F_HW_VLAN_CTAG_TX |
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER;
+
 	netif_keep_dst(card->dev);
-	netif_set_gso_max_size(card->dev, (QETH_MAX_BUFFER_ELEMENTS(card) - 1) *
-					  PAGE_SIZE);
+	if (card->dev->hw_features & NETIF_F_TSO)
+		netif_set_gso_max_size(card->dev,
+				       PAGE_SIZE * (QETH_MAX_BUFFER_ELEMENTS(card) - 1));
 
-	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
 	netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT);
-	netif_carrier_off(card->dev);
-	return register_netdev(card->dev);
+	rc = register_netdev(card->dev);
+out:
+	if (rc)
+		card->dev->netdev_ops = NULL;
+	return rc;
 }
 
 static const struct device_type qeth_l3_devtype = {
@@ -2582,15 +2609,9 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev)
 	if (cgdev->state == CCWGROUP_ONLINE)
 		qeth_l3_set_offline(cgdev);
 
-	if (card->dev) {
-		unregister_netdev(card->dev);
-		free_netdev(card->dev);
-		card->dev = NULL;
-	}
-
+	unregister_netdev(card->dev);
 	qeth_l3_clear_ip_htable(card, 0);
 	qeth_l3_clear_ipato_list(card);
-	return;
 }
 
 static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode)
@@ -2612,10 +2633,9 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 		goto out_remove;
 	}
 
-	if (!card->dev && qeth_l3_setup_netdev(card)) {
-		rc = -ENODEV;
+	rc = qeth_l3_setup_netdev(card);
+	if (rc)
 		goto out_remove;
-	}
 
 	if (qeth_is_diagass_supported(card, QETH_DIAGS_CMD_TRAP)) {
 		if (card->info.hwtrap &&
@@ -2666,11 +2686,12 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 	qeth_enable_hw_features(card->dev);
 	if (recover_flag == CARD_STATE_RECOVER) {
 		rtnl_lock();
-		if (recovery_mode)
+		if (recovery_mode) {
 			__qeth_l3_open(card->dev);
-		else
+			qeth_l3_set_rx_mode(card->dev);
+		} else {
 			dev_open(card->dev);
-		qeth_l3_set_rx_mode(card->dev);
+		}
 		rtnl_unlock();
 	}
 	qeth_trace_features(card);
@@ -2711,8 +2732,7 @@ static int __qeth_l3_set_offline(struct ccwgroup_device *cgdev,
 	QETH_DBF_TEXT(SETUP, 3, "setoffl");
 	QETH_DBF_HEX(SETUP, 3, &card, sizeof(void *));
 
-	if (card->dev && netif_carrier_ok(card->dev))
-		netif_carrier_off(card->dev);
+	netif_carrier_off(card->dev);
 	recover_flag = card->state;
 	if ((!recovery_mode && card->info.hwtrap) || card->info.hwtrap == 2) {
 		qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
@@ -2780,8 +2800,7 @@ static int qeth_l3_pm_suspend(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
 
-	if (card->dev)
-		netif_device_detach(card->dev);
+	netif_device_detach(card->dev);
 	qeth_set_allowed_threads(card, 0, 1);
 	wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
 	if (gdev->state == CCWGROUP_OFFLINE)
@@ -2814,8 +2833,7 @@ static int qeth_l3_pm_resume(struct ccwgroup_device *gdev)
 		rc = __qeth_l3_set_online(card->gdev, 0);
 out:
 	qeth_set_allowed_threads(card, 0xffffffff, 0);
-	if (card->dev)
-		netif_device_attach(card->dev);
+	netif_device_attach(card->dev);
 	if (rc)
 		dev_warn(&card->gdev->dev, "The qeth device driver "
 			"failed to recover an error on the device\n");
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index f61192a048f4..45ac6d8705c6 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -299,8 +299,7 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev,
 	if (strlen(tmp) == 0) {
 		/* delete ip address only */
 		card->options.hsuid[0] = '\0';
-		if (card->dev)
-			memcpy(card->dev->perm_addr, card->options.hsuid, 9);
+		memcpy(card->dev->perm_addr, card->options.hsuid, 9);
 		qeth_configure_cq(card, QETH_CQ_DISABLED);
 		return count;
 	}
@@ -311,8 +310,7 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev,
 	snprintf(card->options.hsuid, sizeof(card->options.hsuid),
 		 "%-8s", tmp);
 	ASCEBC(card->options.hsuid, 8);
-	if (card->dev)
-		memcpy(card->dev->perm_addr, card->options.hsuid, 9);
+	memcpy(card->dev->perm_addr, card->options.hsuid, 9);
 
 	rc = qeth_l3_modify_hsuid(card, true);
 
diff --git a/drivers/s390/scsi/zfcp_aux.c b/drivers/s390/scsi/zfcp_aux.c
index a3a8c8d9d717..94f4d8fe85e0 100644
--- a/drivers/s390/scsi/zfcp_aux.c
+++ b/drivers/s390/scsi/zfcp_aux.c
@@ -101,7 +101,7 @@ static void __init zfcp_init_device_setup(char *devstr)
 	token = strsep(&str, ",");
 	if (!token || strlen(token) >= ZFCP_BUS_ID_SIZE)
 		goto err_out;
-	strncpy(busid, token, ZFCP_BUS_ID_SIZE);
+	strlcpy(busid, token, ZFCP_BUS_ID_SIZE);
 
 	token = strsep(&str, ",");
 	if (!token || kstrtoull(token, 0, (unsigned long long *) &wwpn))
diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c
index 99ba4a770406..27521fc3ef5a 100644
--- a/drivers/scsi/3w-9xxx.c
+++ b/drivers/scsi/3w-9xxx.c
@@ -2038,6 +2038,7 @@ static int twa_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id)
 
 	if (twa_initialize_device_extension(tw_dev)) {
 		TW_PRINTK(tw_dev->host, TW_DRIVER, 0x25, "Failed to initialize device extension");
+		retval = -ENOMEM;
 		goto out_free_device_extension;
 	}
 
@@ -2060,6 +2061,7 @@ static int twa_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id)
 	tw_dev->base_addr = ioremap(mem_addr, mem_len);
 	if (!tw_dev->base_addr) {
 		TW_PRINTK(tw_dev->host, TW_DRIVER, 0x35, "Failed to ioremap");
+		retval = -ENOMEM;
 		goto out_release_mem_region;
 	}
 
@@ -2067,8 +2069,10 @@ static int twa_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id)
 	TW_DISABLE_INTERRUPTS(tw_dev);
 
 	/* Initialize the card */
-	if (twa_reset_sequence(tw_dev, 0))
+	if (twa_reset_sequence(tw_dev, 0)) {
+		retval = -ENOMEM;
 		goto out_iounmap;
+	}
 
 	/* Set host specific parameters */
 	if ((pdev->device == PCI_DEVICE_ID_3WARE_9650SE) ||
diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c
index cf9f2a09b47d..40c1e6e64f58 100644
--- a/drivers/scsi/3w-sas.c
+++ b/drivers/scsi/3w-sas.c
@@ -1594,6 +1594,7 @@ static int twl_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id)
 
 	if (twl_initialize_device_extension(tw_dev)) {
 		TW_PRINTK(tw_dev->host, TW_DRIVER, 0x1a, "Failed to initialize device extension");
+		retval = -ENOMEM;
 		goto out_free_device_extension;
 	}
 
@@ -1608,6 +1609,7 @@ static int twl_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id)
 	tw_dev->base_addr = pci_iomap(pdev, 1, 0);
 	if (!tw_dev->base_addr) {
 		TW_PRINTK(tw_dev->host, TW_DRIVER, 0x1c, "Failed to ioremap");
+		retval = -ENOMEM;
 		goto out_release_mem_region;
 	}
 
@@ -1617,6 +1619,7 @@ static int twl_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id)
 	/* Initialize the card */
 	if (twl_reset_sequence(tw_dev, 0)) {
 		TW_PRINTK(tw_dev->host, TW_DRIVER, 0x1d, "Controller reset failed during probe");
+		retval = -ENOMEM;
 		goto out_iounmap;
 	}
 
diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c
index f6179e3d6953..471366945bd4 100644
--- a/drivers/scsi/3w-xxxx.c
+++ b/drivers/scsi/3w-xxxx.c
@@ -1925,7 +1925,7 @@ static int tw_scsi_queue_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_c
 	if (test_bit(TW_IN_RESET, &tw_dev->flags))
 		return SCSI_MLQUEUE_HOST_BUSY;
 
-	/* Save done function into Scsi_Cmnd struct */
+	/* Save done function into struct scsi_cmnd */
 	SCpnt->scsi_done = done;
 		 
 	/* Queue the command and get a request id */
@@ -2280,6 +2280,7 @@ static int tw_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id)
 
 	if (tw_initialize_device_extension(tw_dev)) {
 		printk(KERN_WARNING "3w-xxxx: Failed to initialize device extension.");
+		retval = -ENOMEM;
 		goto out_free_device_extension;
 	}
 
@@ -2294,6 +2295,7 @@ static int tw_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id)
 	tw_dev->base_addr = pci_resource_start(pdev, 0);
 	if (!tw_dev->base_addr) {
 		printk(KERN_WARNING "3w-xxxx: Failed to get io address.");
+		retval = -ENOMEM;
 		goto out_release_mem_region;
 	}
 
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 35c909bbf8ba..8fc851a9e116 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -49,6 +49,7 @@ config SCSI_NETLINK
 
 config SCSI_MQ_DEFAULT
 	bool "SCSI: use blk-mq I/O path by default"
+	default y
 	depends on SCSI
 	---help---
 	  This option enables the new blk-mq based I/O path for SCSI
@@ -841,18 +842,6 @@ config SCSI_IZIP_SLOW_CTR
 
 	  Generally, saying N is fine.
 
-config SCSI_NCR_D700
-	tristate "NCR Dual 700 MCA SCSI support"
-	depends on MCA && SCSI
-	select SCSI_SPI_ATTRS
-	help
-	  This is a driver for the MicroChannel Dual 700 card produced by
-	  NCR and commonly used in 345x/35xx/4100 class machines.  It always
-	  tries to negotiate sync and uses tag command queueing.
-
-	  Unless you have an NCR manufactured machine, the chances are that
-	  you do not have this SCSI card, so say N.
-
 config SCSI_LASI700
 	tristate "HP Lasi SCSI support for 53c700/710"
 	depends on GSC && SCSI
@@ -1000,21 +989,9 @@ config SCSI_ZALON
 	  used on the add-in Bluefish, Barracuda & Shrike SCSI cards.
 	  Say Y here if you have one of these machines or cards.
 
-config SCSI_NCR_Q720
-	tristate "NCR Quad 720 MCA SCSI support"
-	depends on MCA && SCSI
-	select SCSI_SPI_ATTRS
-	help
-	  This is a driver for the MicroChannel Quad 720 card produced by
-	  NCR and commonly used in 345x/35xx/4100 class machines.  It always
-	  tries to negotiate sync and uses tag command queueing.
-
-	  Unless you have an NCR manufactured machine, the chances are that
-	  you do not have this SCSI card, so say N.
-
 config SCSI_NCR53C8XX_DEFAULT_TAGS
 	int "default tagged command queue depth"
-	depends on SCSI_ZALON || SCSI_NCR_Q720
+	depends on SCSI_ZALON
 	default "8"
 	---help---
 	  "Tagged command queuing" is a feature of SCSI-2 which improves
@@ -1040,7 +1017,7 @@ config SCSI_NCR53C8XX_DEFAULT_TAGS
 
 config SCSI_NCR53C8XX_MAX_TAGS
 	int "maximum number of queued commands"
-	depends on SCSI_ZALON || SCSI_NCR_Q720
+	depends on SCSI_ZALON
 	default "32"
 	---help---
 	  This option allows you to specify the maximum number of commands
@@ -1057,7 +1034,7 @@ config SCSI_NCR53C8XX_MAX_TAGS
 
 config SCSI_NCR53C8XX_SYNC
 	int "synchronous transfers frequency in MHz"
-	depends on SCSI_ZALON || SCSI_NCR_Q720
+	depends on SCSI_ZALON
 	default "20"
 	---help---
 	  The SCSI Parallel Interface-2 Standard defines 5 classes of transfer
@@ -1091,7 +1068,7 @@ config SCSI_NCR53C8XX_SYNC
 
 config SCSI_NCR53C8XX_NO_DISCONNECT
 	bool "not allow targets to disconnect"
-	depends on (SCSI_ZALON || SCSI_NCR_Q720) && SCSI_NCR53C8XX_DEFAULT_TAGS=0
+	depends on SCSI_ZALON && SCSI_NCR53C8XX_DEFAULT_TAGS=0
 	help
 	  This option is only provided for safety if you suspect some SCSI
 	  device of yours to not support properly the target-disconnect
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index 80aca2456353..6d71b2a9592b 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -21,6 +21,7 @@ CFLAGS_gdth.o    = # -DDEBUG_GDTH=2 -D__SERIAL__ -D__COM2__ -DGDTH_STATISTICS
 obj-$(CONFIG_PCMCIA)		+= pcmcia/
 
 obj-$(CONFIG_SCSI)		+= scsi_mod.o
+obj-$(CONFIG_BLK_SCSI_REQUEST)	+= scsi_common.o
 
 obj-$(CONFIG_RAID_ATTRS)	+= raid_class.o
 
@@ -76,8 +77,6 @@ obj-$(CONFIG_SCSI_PM8001)	+= pm8001/
 obj-$(CONFIG_SCSI_ISCI)		+= isci/
 obj-$(CONFIG_SCSI_IPS)		+= ips.o
 obj-$(CONFIG_SCSI_GENERIC_NCR5380) += g_NCR5380.o
-obj-$(CONFIG_SCSI_NCR_D700)	+= 53c700.o NCR_D700.o
-obj-$(CONFIG_SCSI_NCR_Q720)	+= NCR_Q720_mod.o
 obj-$(CONFIG_SCSI_QLOGIC_FAS)	+= qlogicfas408.o	qlogicfas.o
 obj-$(CONFIG_PCMCIA_QLOGIC)	+= qlogicfas408.o
 obj-$(CONFIG_SCSI_QLOGIC_1280)	+= qla1280.o 
@@ -156,7 +155,6 @@ obj-$(CONFIG_SCSI_HISI_SAS) += hisi_sas/
 obj-$(CONFIG_SCSI_DEBUG)	+= scsi_debug.o
 scsi_mod-y			+= scsi.o hosts.o scsi_ioctl.o \
 				   scsicam.o scsi_error.o scsi_lib.o
-scsi_mod-y			+= scsi_common.o
 scsi_mod-$(CONFIG_SCSI_CONSTANTS) += constants.o
 scsi_mod-$(CONFIG_SCSI_DMA)	+= scsi_lib_dma.o
 scsi_mod-y			+= scsi_scan.o scsi_sysfs.o scsi_devinfo.o
@@ -180,7 +178,6 @@ ncr53c8xx-flags-$(CONFIG_SCSI_ZALON) \
 			-DCONFIG_SCSI_NCR53C8XX_NO_WORD_TRANSFERS
 CFLAGS_ncr53c8xx.o	:= $(ncr53c8xx-flags-y) $(ncr53c8xx-flags-m)
 zalon7xx-objs	:= zalon.o ncr53c8xx.o
-NCR_Q720_mod-objs	:= NCR_Q720.o ncr53c8xx.o
 
 # Files generated that shall be removed upon make clean
 clean-files :=	53c700_d.h 53c700_u.h scsi_devinfo_tbl.c
diff --git a/drivers/scsi/NCR_D700.c b/drivers/scsi/NCR_D700.c
deleted file mode 100644
index b39a2409a507..000000000000
--- a/drivers/scsi/NCR_D700.c
+++ /dev/null
@@ -1,405 +0,0 @@
-/* -*- mode: c; c-basic-offset: 8 -*- */
-
-/* NCR Dual 700 MCA SCSI Driver
- *
- * Copyright (C) 2001 by James.Bottomley@HansenPartnership.com
-**-----------------------------------------------------------------------------
-**  
-**  This program is free software; you can redistribute it and/or modify
-**  it under the terms of the GNU General Public License as published by
-**  the Free Software Foundation; either version 2 of the License, or
-**  (at your option) any later version.
-**
-**  This program is distributed in the hope that it will be useful,
-**  but WITHOUT ANY WARRANTY; without even the implied warranty of
-**  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-**  GNU General Public License for more details.
-**
-**  You should have received a copy of the GNU General Public License
-**  along with this program; if not, write to the Free Software
-**  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
-**
-**-----------------------------------------------------------------------------
- */
-
-/* Notes:
- *
- * Most of the work is done in the chip specific module, 53c700.o
- *
- * TODO List:
- *
- * 1. Extract the SCSI ID from the voyager CMOS table (necessary to
- *    support multi-host environments.
- *
- * */
-
-
-/* CHANGELOG 
- *
- * Version 2.2
- *
- * Added mca_set_adapter_name().
- *
- * Version 2.1
- *
- * Modularise the driver into a Board piece (this file) and a chip
- * piece 53c700.[ch] and 53c700.scr, added module options.  You can
- * now specify the scsi id by the parameters
- *
- * NCR_D700=slot:<n> [siop:<n>] id:<n> ....
- *
- * They need to be comma separated if compiled into the kernel
- *
- * Version 2.0
- *
- * Initial implementation of TCQ (Tag Command Queueing).  TCQ is full
- * featured and uses the clock algorithm to keep track of outstanding
- * tags and guard against individual tag starvation.  Also fixed a bug
- * in all of the 1.x versions where the D700_data_residue() function
- * was returning results off by 32 bytes (and thus causing the same 32
- * bytes to be written twice corrupting the data block).  It turns out
- * the 53c700 only has a 6 bit DBC and DFIFO registers not 7 bit ones
- * like the 53c710 (The 710 is the only data manual still available,
- * which I'd been using to program the 700).
- *
- * Version 1.2
- *
- * Much improved message handling engine
- *
- * Version 1.1
- *
- * Add code to handle selection reasonably correctly.  By the time we
- * get the selection interrupt, we've already responded, but drop off the
- * bus and hope the selector will go away.
- *
- * Version 1.0:
- *
- *   Initial release.  Fully functional except for procfs and tag
- * command queueing.  Has only been tested on cards with 53c700-66
- * chips and only single ended. Features are
- *
- * 1. Synchronous data transfers to offset 8 (limit of 700-66) and
- *    100ns (10MHz) limit of SCSI-2
- *
- * 2. Disconnection and reselection
- *
- * Testing:
- * 
- *  I've only really tested this with the 700-66 chip, but have done
- * soak tests in multi-device environments to verify that
- * disconnections and reselections are being processed correctly.
- * */
-
-#define NCR_D700_VERSION "2.2"
-
-#include <linux/blkdev.h>
-#include <linux/interrupt.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mca.h>
-#include <linux/slab.h>
-#include <asm/io.h>
-#include <scsi/scsi_host.h>
-#include <scsi/scsi_device.h>
-#include <scsi/scsi_transport.h>
-#include <scsi/scsi_transport_spi.h>
-
-#include "53c700.h"
-#include "NCR_D700.h"
-
-static char *NCR_D700;		/* command line from insmod */
-
-MODULE_AUTHOR("James Bottomley");
-MODULE_DESCRIPTION("NCR Dual700 SCSI Driver");
-MODULE_LICENSE("GPL");
-module_param(NCR_D700, charp, 0);
-
-static __u8 id_array[2*(MCA_MAX_SLOT_NR + 1)] =
-	{ [0 ... 2*(MCA_MAX_SLOT_NR + 1)-1] = 7 };
-
-#ifdef MODULE
-#define ARG_SEP ' '
-#else
-#define ARG_SEP ','
-#endif
-
-static int __init
-param_setup(char *string)
-{
-	char *pos = string, *next;
-	int slot = -1, siop = -1;
-
-	while(pos != NULL && (next = strchr(pos, ':')) != NULL) {
-		int val = (int)simple_strtoul(++next, NULL, 0);
-
-		if(!strncmp(pos, "slot:", 5))
-			slot = val;
-		else if(!strncmp(pos, "siop:", 5))
-			siop = val;
-		else if(!strncmp(pos, "id:", 3)) {
-			if(slot == -1) {
-				printk(KERN_WARNING "NCR D700: Must specify slot for id parameter\n");
-			} else if(slot > MCA_MAX_SLOT_NR) {
-				printk(KERN_WARNING "NCR D700: Illegal slot %d for id %d\n", slot, val);
-			} else {
-				if(siop != 0 && siop != 1) {
-					id_array[slot*2] = val;
-					id_array[slot*2 + 1] =val;
-				} else {
-					id_array[slot*2 + siop] = val;
-				}
-			}
-		}
-		if((pos = strchr(pos, ARG_SEP)) != NULL)
-			pos++;
-	}
-	return 1;
-}
-
-/* Host template.  The 53c700 routine NCR_700_detect will
- * fill in all of the missing routines */
-static struct scsi_host_template NCR_D700_driver_template = {
-	.module			= THIS_MODULE,
-	.name			= "NCR Dual 700 MCA",
-	.proc_name		= "NCR_D700",
-	.this_id		= 7,
-};
-
-/* We needs this helper because we have two hosts per struct device */
-struct NCR_D700_private {
-	struct device		*dev;
-	struct Scsi_Host	*hosts[2];
-	char			name[30];
-	char			pad;
-};
-
-static int
-NCR_D700_probe_one(struct NCR_D700_private *p, int siop, int irq,
-		   int slot, u32 region, int differential)
-{
-	struct NCR_700_Host_Parameters *hostdata;
-	struct Scsi_Host *host;
-	int ret;
-
-	hostdata = kzalloc(sizeof(*hostdata), GFP_KERNEL);
-	if (!hostdata) {
-		printk(KERN_ERR "NCR D700: SIOP%d: Failed to allocate host"
-		       "data, detatching\n", siop);
-		return -ENOMEM;
-	}
-
-	if (!request_region(region, 64, "NCR_D700")) {
-		printk(KERN_ERR "NCR D700: Failed to reserve IO region 0x%x\n",
-				region);
-		ret = -ENODEV;
-		goto region_failed;
-	}
-		
-	/* Fill in the three required pieces of hostdata */
-	hostdata->base = ioport_map(region, 64);
-	hostdata->differential = (((1<<siop) & differential) != 0);
-	hostdata->clock = NCR_D700_CLOCK_MHZ;
-	hostdata->burst_length = 8;
-
-	/* and register the siop */
-	host = NCR_700_detect(&NCR_D700_driver_template, hostdata, p->dev);
-	if (!host) {
-		ret = -ENOMEM;
-		goto detect_failed;
-	}
-
-	p->hosts[siop] = host;
-	/* FIXME: read this from SUS */
-	host->this_id = id_array[slot * 2 + siop];
-	host->irq = irq;
-	host->base = region;
-	scsi_scan_host(host);
-
-	return 0;
-
- detect_failed:
-	release_region(region, 64);
- region_failed:
-	kfree(hostdata);
-
-	return ret;
-}
-
-static irqreturn_t
-NCR_D700_intr(int irq, void *data)
-{
-	struct NCR_D700_private *p = (struct NCR_D700_private *)data;
-	int i, found = 0;
-
-	for (i = 0; i < 2; i++)
-		if (p->hosts[i] &&
-		    NCR_700_intr(irq, p->hosts[i]) == IRQ_HANDLED)
-			found++;
-
-	return found ? IRQ_HANDLED : IRQ_NONE;
-}
-
-/* Detect a D700 card.  Note, because of the setup --- the chips are
- * essentially connectecd to the MCA bus independently, it is easier
- * to set them up as two separate host adapters, rather than one
- * adapter with two channels */
-static int
-NCR_D700_probe(struct device *dev)
-{
-	struct NCR_D700_private *p;
-	int differential;
-	static int banner = 1;
-	struct mca_device *mca_dev = to_mca_device(dev);
-	int slot = mca_dev->slot;
-	int found = 0;
-	int irq, i;
-	int pos3j, pos3k, pos3a, pos3b, pos4;
-	__u32 base_addr, offset_addr;
-
-	/* enable board interrupt */
-	pos4 = mca_device_read_pos(mca_dev, 4);
-	pos4 |= 0x4;
-	mca_device_write_pos(mca_dev, 4, pos4);
-
-	mca_device_write_pos(mca_dev, 6, 9);
-	pos3j = mca_device_read_pos(mca_dev, 3);
-	mca_device_write_pos(mca_dev, 6, 10);
-	pos3k = mca_device_read_pos(mca_dev, 3);
-	mca_device_write_pos(mca_dev, 6, 0);
-	pos3a = mca_device_read_pos(mca_dev, 3);
-	mca_device_write_pos(mca_dev, 6, 1);
-	pos3b = mca_device_read_pos(mca_dev, 3);
-
-	base_addr = ((pos3j << 8) | pos3k) & 0xfffffff0;
-	offset_addr = ((pos3a << 8) | pos3b) & 0xffffff70;
-
-	irq = (pos4 & 0x3) + 11;
-	if(irq >= 13)
-		irq++;
-	if(banner) {
-		printk(KERN_NOTICE "NCR D700: Driver Version " NCR_D700_VERSION "\n"
-		       "NCR D700:  Copyright (c) 2001 by James.Bottomley@HansenPartnership.com\n"
-		       "NCR D700:\n");
-		banner = 0;
-	}
-	/* now do the bus related transforms */
-	irq = mca_device_transform_irq(mca_dev, irq);
-	base_addr = mca_device_transform_ioport(mca_dev, base_addr);
-	offset_addr = mca_device_transform_ioport(mca_dev, offset_addr);
-
-	printk(KERN_NOTICE "NCR D700: found in slot %d  irq = %d  I/O base = 0x%x\n", slot, irq, offset_addr);
-
-	/*outb(BOARD_RESET, base_addr);*/
-
-	/* clear any pending interrupts */
-	(void)inb(base_addr + 0x08);
-	/* get modctl, used later for setting diff bits */
-	switch(differential = (inb(base_addr + 0x08) >> 6)) {
-	case 0x00:
-		/* only SIOP1 differential */
-		differential = 0x02;
-		break;
-	case 0x01:
-		/* Both SIOPs differential */
-		differential = 0x03;
-		break;
-	case 0x03:
-		/* No SIOPs differential */
-		differential = 0x00;
-		break;
-	default:
-		printk(KERN_ERR "D700: UNEXPECTED DIFFERENTIAL RESULT 0x%02x\n",
-		       differential);
-		differential = 0x00;
-		break;
-	}
-
-	p = kzalloc(sizeof(*p), GFP_KERNEL);
-	if (!p)
-		return -ENOMEM;
-
-	p->dev = dev;
-	snprintf(p->name, sizeof(p->name), "D700(%s)", dev_name(dev));
-	if (request_irq(irq, NCR_D700_intr, IRQF_SHARED, p->name, p)) {
-		printk(KERN_ERR "D700: request_irq failed\n");
-		kfree(p);
-		return -EBUSY;
-	}
-	/* plumb in both 700 chips */
-	for (i = 0; i < 2; i++) {
-		int err;
-
-		if ((err = NCR_D700_probe_one(p, i, irq, slot,
-					      offset_addr + (0x80 * i),
-					      differential)) != 0)
-			printk("D700: SIOP%d: probe failed, error = %d\n",
-			       i, err);
-		else
-			found++;
-	}
-
-	if (!found) {
-		kfree(p);
-		return -ENODEV;
-	}
-
-	mca_device_set_claim(mca_dev, 1);
-	mca_device_set_name(mca_dev, "NCR_D700");
-	dev_set_drvdata(dev, p);
-	return 0;
-}
-
-static void
-NCR_D700_remove_one(struct Scsi_Host *host)
-{
-	scsi_remove_host(host);
-	NCR_700_release(host);
-	kfree((struct NCR_700_Host_Parameters *)host->hostdata[0]);
-	free_irq(host->irq, host);
-	release_region(host->base, 64);
-}
-
-static int
-NCR_D700_remove(struct device *dev)
-{
-	struct NCR_D700_private *p = dev_get_drvdata(dev);
-	int i;
-
-	for (i = 0; i < 2; i++)
-		NCR_D700_remove_one(p->hosts[i]);
-
-	kfree(p);
-	return 0;
-}
-
-static short NCR_D700_id_table[] = { NCR_D700_MCA_ID, 0 };
-
-static struct mca_driver NCR_D700_driver = {
-	.id_table = NCR_D700_id_table,
-	.driver = {
-		.name		= "NCR_D700",
-		.bus		= &mca_bus_type,
-		.probe		= NCR_D700_probe,
-		.remove		= NCR_D700_remove,
-	},
-};
-
-static int __init NCR_D700_init(void)
-{
-#ifdef MODULE
-	if (NCR_D700)
-		param_setup(NCR_D700);
-#endif
-
-	return mca_register_driver(&NCR_D700_driver);
-}
-
-static void __exit NCR_D700_exit(void)
-{
-	mca_unregister_driver(&NCR_D700_driver);
-}
-
-module_init(NCR_D700_init);
-module_exit(NCR_D700_exit);
-
-__setup("NCR_D700=", param_setup);
diff --git a/drivers/scsi/NCR_D700.h b/drivers/scsi/NCR_D700.h
deleted file mode 100644
index eb675d782ef6..000000000000
--- a/drivers/scsi/NCR_D700.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* -*- mode: c; c-basic-offset: 8 -*- */
-
-/* NCR Dual 700 MCA SCSI Driver
- *
- * Copyright (C) 2001 by James.Bottomley@HansenPartnership.com
- */
-
-#ifndef _NCR_D700_H
-#define _NCR_D700_H
-
-/* Don't turn on debugging messages */
-#undef NCR_D700_DEBUG
-
-/* The MCA identifier */
-#define NCR_D700_MCA_ID		0x0092
-
-/* Defines for the Board registers */
-#define	BOARD_RESET		0x80	/* board level reset */
-#define ADD_PARENB		0x04	/* Address Parity Enabled */
-#define DAT_PARENB		0x01	/* Data Parity Enabled */
-#define SFBK_ENB		0x10	/* SFDBK Interrupt Enabled */
-#define LED0GREEN		0x20	/* Led 0 (red 0; green 1) */
-#define LED1GREEN		0x40	/* Led 1 (red 0; green 1) */
-#define LED0RED			0xDF	/* Led 0 (red 0; green 1) */
-#define LED1RED			0xBF	/* Led 1 (red 0; green 1) */
-
-#define NCR_D700_CLOCK_MHZ	50
-
-#endif
diff --git a/drivers/scsi/NCR_Q720.c b/drivers/scsi/NCR_Q720.c
deleted file mode 100644
index 54e7d26908ee..000000000000
--- a/drivers/scsi/NCR_Q720.c
+++ /dev/null
@@ -1,376 +0,0 @@
-/* -*- mode: c; c-basic-offset: 8 -*- */
-
-/* NCR Quad 720 MCA SCSI Driver
- *
- * Copyright (C) 2003 by James.Bottomley@HansenPartnership.com
- */
-
-#include <linux/blkdev.h>
-#include <linux/interrupt.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mca.h>
-#include <linux/slab.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <asm/io.h>
-
-#include "scsi.h"
-#include <scsi/scsi_host.h>
-
-#include "ncr53c8xx.h"
-
-#include "NCR_Q720.h"
-
-static struct ncr_chip q720_chip __initdata = {
-	.revision_id =	0x0f,
-	.burst_max =	3,
-	.offset_max =	8,
-	.nr_divisor =	4,
-	.features =	FE_WIDE | FE_DIFF | FE_VARCLK,
-};
-
-MODULE_AUTHOR("James Bottomley");
-MODULE_DESCRIPTION("NCR Quad 720 SCSI Driver");
-MODULE_LICENSE("GPL");
-
-#define NCR_Q720_VERSION		"0.9"
-
-/* We needs this helper because we have up to four hosts per struct device */
-struct NCR_Q720_private {
-	struct device		*dev;
-	void __iomem *		mem_base;
-	__u32			phys_mem_base;
-	__u32			mem_size;
-	__u8			irq;
-	__u8			siops;
-	__u8			irq_enable;
-	struct Scsi_Host	*hosts[4];
-};
-
-static struct scsi_host_template NCR_Q720_tpnt = {
-	.module			= THIS_MODULE,
-	.proc_name		= "NCR_Q720",
-};
-
-static irqreturn_t
-NCR_Q720_intr(int irq, void *data)
-{
-	struct NCR_Q720_private *p = (struct NCR_Q720_private *)data;
-	__u8 sir = (readb(p->mem_base + 0x0d) & 0xf0) >> 4;
-	__u8 siop;
-
-	sir |= ~p->irq_enable;
-
-	if(sir == 0xff)
-		return IRQ_NONE;
-
-
-	while((siop = ffz(sir)) < p->siops) {
-		sir |= 1<<siop;
-		ncr53c8xx_intr(irq, p->hosts[siop]);
-	}
-	return IRQ_HANDLED;
-}
-
-static int __init
-NCR_Q720_probe_one(struct NCR_Q720_private *p, int siop,
-		int irq, int slot, __u32 paddr, void __iomem *vaddr)
-{
-	struct ncr_device device;
-	__u8 scsi_id;
-	static int unit = 0;
-	__u8 scsr1 = readb(vaddr + NCR_Q720_SCSR_OFFSET + 1);
-	__u8 differential = readb(vaddr + NCR_Q720_SCSR_OFFSET) & 0x20;
-	__u8 version;
-	int error;
-
-	scsi_id = scsr1 >> 4;
-	/* enable burst length 16 (FIXME: should allow this) */
-	scsr1 |= 0x02;
-	/* force a siop reset */
-	scsr1 |= 0x04;
-	writeb(scsr1, vaddr + NCR_Q720_SCSR_OFFSET + 1);
-	udelay(10);
-	version = readb(vaddr + 0x18) >> 4;
-
-	memset(&device, 0, sizeof(struct ncr_device));
-		/* Initialise ncr_device structure with items required by ncr_attach. */
-	device.chip		= q720_chip;
-	device.chip.revision_id	= version;
-	device.host_id		= scsi_id;
-	device.dev		= p->dev;
-	device.slot.base	= paddr;
-	device.slot.base_c	= paddr;
-	device.slot.base_v	= vaddr;
-	device.slot.irq		= irq;
-	device.differential	= differential ? 2 : 0;
-	printk("Q720 probe unit %d (siop%d) at 0x%lx, diff = %d, vers = %d\n", unit, siop,
-	       (unsigned long)paddr, differential, version);
-
-	p->hosts[siop] = ncr_attach(&NCR_Q720_tpnt, unit++, &device);
-	
-	if (!p->hosts[siop]) 
-		goto fail;
-
-	p->irq_enable |= (1<<siop);
-	scsr1 = readb(vaddr + NCR_Q720_SCSR_OFFSET + 1);
-	/* clear the disable interrupt bit */
-	scsr1 &= ~0x01;
-	writeb(scsr1, vaddr + NCR_Q720_SCSR_OFFSET + 1);
-
-	error = scsi_add_host(p->hosts[siop], p->dev);
-	if (error)
-		ncr53c8xx_release(p->hosts[siop]);
-	else
-		scsi_scan_host(p->hosts[siop]);
-	return error;
-
- fail:
-	return -ENODEV;
-}
-
-/* Detect a Q720 card.  Note, because of the setup --- the chips are
- * essentially connectecd to the MCA bus independently, it is easier
- * to set them up as two separate host adapters, rather than one
- * adapter with two channels */
-static int __init
-NCR_Q720_probe(struct device *dev)
-{
-	struct NCR_Q720_private *p;
-	static int banner = 1;
-	struct mca_device *mca_dev = to_mca_device(dev);
-	int slot = mca_dev->slot;
-	int found = 0;
-	int irq, i, siops;
-	__u8 pos2, pos4, asr2, asr9, asr10;
-	__u16 io_base;
-	__u32 base_addr, mem_size;
-	void __iomem *mem_base;
-
-	p = kzalloc(sizeof(*p), GFP_KERNEL);
-	if (!p)
-		return -ENOMEM;
-
-	pos2 = mca_device_read_pos(mca_dev, 2);
-	/* enable device */
-	pos2 |=  NCR_Q720_POS2_BOARD_ENABLE | NCR_Q720_POS2_INTERRUPT_ENABLE;
-	mca_device_write_pos(mca_dev, 2, pos2);
-
-	io_base = (pos2 & NCR_Q720_POS2_IO_MASK) << NCR_Q720_POS2_IO_SHIFT;
-
-
-	if(banner) {
-		printk(KERN_NOTICE "NCR Q720: Driver Version " NCR_Q720_VERSION "\n"
-		       "NCR Q720:  Copyright (c) 2003 by James.Bottomley@HansenPartnership.com\n"
-		       "NCR Q720:\n");
-		banner = 0;
-	}
-	io_base = mca_device_transform_ioport(mca_dev, io_base);
-
-	/* OK, this is phase one of the bootstrap, we now know the
-	 * I/O space base address.  All the configuration registers
-	 * are mapped here (including pos) */
-
-	/* sanity check I/O mapping */
-	i = inb(io_base) | (inb(io_base+1)<<8);
-	if(i != NCR_Q720_MCA_ID) {
-		printk(KERN_ERR "NCR_Q720, adapter failed to I/O map registers correctly at 0x%x(0x%x)\n", io_base, i);
-		kfree(p);
-		return -ENODEV;
-	}
-
-	/* Phase II, find the ram base and memory map the board register */
-	pos4 = inb(io_base + 4);
-	/* enable streaming data */
-	pos4 |= 0x01;
-	outb(pos4, io_base + 4);
-	base_addr = (pos4 & 0x7e) << 20;
-	base_addr += (pos4 & 0x80) << 23;
-	asr10 = inb(io_base + 0x12);
-	base_addr += (asr10 & 0x80) << 24;
-	base_addr += (asr10 & 0x70) << 23;
-
-	/* OK, got the base addr, now we need to find the ram size,
-	 * enable and map it */
-	asr9 = inb(io_base + 0x11);
-	i = (asr9 & 0xc0) >> 6;
-	if(i == 0)
-		mem_size = 1024;
-	else
-		mem_size = 1 << (19 + i);
-
-	/* enable the sram mapping */
-	asr9 |= 0x20;
-
-	/* disable the rom mapping */
-	asr9 &= ~0x10;
-
-	outb(asr9, io_base + 0x11);
-
-	if(!request_mem_region(base_addr, mem_size, "NCR_Q720")) {
-		printk(KERN_ERR "NCR_Q720: Failed to claim memory region 0x%lx\n-0x%lx",
-		       (unsigned long)base_addr,
-		       (unsigned long)(base_addr + mem_size));
-		goto out_free;
-	}
-	
-	if (dma_declare_coherent_memory(dev, base_addr, base_addr,
-					mem_size, 0)) {
-		printk(KERN_ERR "NCR_Q720: DMA declare memory failed\n");
-		goto out_release_region;
-	}
-
-	/* The first 1k of the memory buffer is a memory map of the registers
-	 */
-	mem_base = dma_mark_declared_memory_occupied(dev, base_addr,
-							    1024);
-	if (IS_ERR(mem_base)) {
-		printk("NCR_Q720 failed to reserve memory mapped region\n");
-		goto out_release;
-	}
-
-	/* now also enable accesses in asr 2 */
-	asr2 = inb(io_base + 0x0a);
-
-	asr2 |= 0x01;
-
-	outb(asr2, io_base + 0x0a);
-
-	/* get the number of SIOPs (this should be 2 or 4) */
-	siops = ((asr2 & 0xe0) >> 5) + 1;
-
-	/* sanity check mapping (again) */
-	i = readw(mem_base);
-	if(i != NCR_Q720_MCA_ID) {
-		printk(KERN_ERR "NCR_Q720, adapter failed to memory map registers correctly at 0x%lx(0x%x)\n", (unsigned long)base_addr, i);
-		goto out_release;
-	}
-
-	irq = readb(mem_base + 5) & 0x0f;
-	
-	
-	/* now do the bus related transforms */
-	irq = mca_device_transform_irq(mca_dev, irq);
-
-	printk(KERN_NOTICE "NCR Q720: found in slot %d  irq = %d  mem base = 0x%lx siops = %d\n", slot, irq, (unsigned long)base_addr, siops);
-	printk(KERN_NOTICE "NCR Q720: On board ram %dk\n", mem_size/1024);
-
-	p->dev = dev;
-	p->mem_base = mem_base;
-	p->phys_mem_base = base_addr;
-	p->mem_size = mem_size;
-	p->irq = irq;
-	p->siops = siops;
-
-	if (request_irq(irq, NCR_Q720_intr, IRQF_SHARED, "NCR_Q720", p)) {
-		printk(KERN_ERR "NCR_Q720: request irq %d failed\n", irq);
-		goto out_release;
-	}
-	/* disable all the siop interrupts */
-	for(i = 0; i < siops; i++) {
-		void __iomem *reg_scsr1 = mem_base + NCR_Q720_CHIP_REGISTER_OFFSET
-			+ i*NCR_Q720_SIOP_SHIFT + NCR_Q720_SCSR_OFFSET + 1;
-		__u8 scsr1 = readb(reg_scsr1);
-		scsr1 |= 0x01;
-		writeb(scsr1, reg_scsr1);
-	}
-
-	/* plumb in all 720 chips */
-	for (i = 0; i < siops; i++) {
-		void __iomem *siop_v_base = mem_base + NCR_Q720_CHIP_REGISTER_OFFSET
-			+ i*NCR_Q720_SIOP_SHIFT;
-		__u32 siop_p_base = base_addr + NCR_Q720_CHIP_REGISTER_OFFSET
-			+ i*NCR_Q720_SIOP_SHIFT;
-		__u16 port = io_base + NCR_Q720_CHIP_REGISTER_OFFSET
-			+ i*NCR_Q720_SIOP_SHIFT;
-		int err;
-
-		outb(0xff, port + 0x40);
-		outb(0x07, port + 0x41);
-		if ((err = NCR_Q720_probe_one(p, i, irq, slot,
-					      siop_p_base, siop_v_base)) != 0)
-			printk("Q720: SIOP%d: probe failed, error = %d\n",
-			       i, err);
-		else
-			found++;
-	}
-
-	if (!found) {
-		kfree(p);
-		return -ENODEV;
-	}
-
-	mca_device_set_claim(mca_dev, 1);
-	mca_device_set_name(mca_dev, "NCR_Q720");
-	dev_set_drvdata(dev, p);
-
-	return 0;
-
- out_release:
-	dma_release_declared_memory(dev);
- out_release_region:
-	release_mem_region(base_addr, mem_size);
- out_free:
-	kfree(p);
-
-	return -ENODEV;
-}
-
-static void __exit
-NCR_Q720_remove_one(struct Scsi_Host *host)
-{
-	scsi_remove_host(host);
-	ncr53c8xx_release(host);
-}
-
-static int __exit
-NCR_Q720_remove(struct device *dev)
-{
-	struct NCR_Q720_private *p = dev_get_drvdata(dev);
-	int i;
-
-	for (i = 0; i < p->siops; i++)
-		if(p->hosts[i])
-			NCR_Q720_remove_one(p->hosts[i]);
-
-	dma_release_declared_memory(dev);
-	release_mem_region(p->phys_mem_base, p->mem_size);
-	free_irq(p->irq, p);
-	kfree(p);
-	return 0;
-}
-
-static short NCR_Q720_id_table[] = { NCR_Q720_MCA_ID, 0 };
-
-static struct mca_driver NCR_Q720_driver = {
-	.id_table = NCR_Q720_id_table,
-	.driver = {
-		.name		= "NCR_Q720",
-		.bus		= &mca_bus_type,
-		.probe		= NCR_Q720_probe,
-		.remove		= NCR_Q720_remove,
-	},
-};
-
-static int __init
-NCR_Q720_init(void)
-{
-	int ret = ncr53c8xx_init();
-	if (!ret)
-		ret = mca_register_driver(&NCR_Q720_driver);
-	if (ret)
-		ncr53c8xx_exit();
-	return ret;
-}
-
-static void __exit
-NCR_Q720_exit(void)
-{
-	mca_unregister_driver(&NCR_Q720_driver);
-	ncr53c8xx_exit();
-}
-
-module_init(NCR_Q720_init);
-module_exit(NCR_Q720_exit);
diff --git a/drivers/scsi/NCR_Q720.h b/drivers/scsi/NCR_Q720.h
deleted file mode 100644
index d5f46cdb736e..000000000000
--- a/drivers/scsi/NCR_Q720.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* -*- mode: c; c-basic-offset: 8 -*- */
-
-/* NCR Quad 720 MCA SCSI Driver
- *
- * Copyright (C) 2003 by James.Bottomley@HansenPartnership.com
- */
-
-#ifndef _NCR_Q720_H
-#define _NCR_Q720_H
-
-/* The MCA identifier */
-#define NCR_Q720_MCA_ID		0x0720
-
-#define NCR_Q720_CLOCK_MHZ	30
-
-#define NCR_Q720_POS2_BOARD_ENABLE	0x01
-#define NCR_Q720_POS2_INTERRUPT_ENABLE	0x02
-#define NCR_Q720_POS2_PARITY_DISABLE	0x04
-#define NCR_Q720_POS2_IO_MASK		0xf8
-#define NCR_Q720_POS2_IO_SHIFT		8
-
-#define NCR_Q720_CHIP_REGISTER_OFFSET	0x200
-#define NCR_Q720_SCSR_OFFSET		0x070
-#define NCR_Q720_SIOP_SHIFT		0x080
-
-#endif
-
-
diff --git a/drivers/scsi/a100u2w.c b/drivers/scsi/a100u2w.c
index b2942ec3d455..23b17621b6d2 100644
--- a/drivers/scsi/a100u2w.c
+++ b/drivers/scsi/a100u2w.c
@@ -143,7 +143,7 @@ static u8 wait_chip_ready(struct orc_host * host)
 	for (i = 0; i < 10; i++) {	/* Wait 1 second for report timeout     */
 		if (inb(host->base + ORC_HCTRL) & HOSTSTOP)	/* Wait HOSTSTOP set */
 			return 1;
-		mdelay(100);
+		msleep(100);
 	}
 	return 0;
 }
@@ -155,7 +155,7 @@ static u8 wait_firmware_ready(struct orc_host * host)
 	for (i = 0; i < 10; i++) {	/* Wait 1 second for report timeout     */
 		if (inb(host->base + ORC_HSTUS) & RREADY)		/* Wait READY set */
 			return 1;
-		mdelay(100);	/* wait 100ms before try again  */
+		msleep(100);	/* wait 100ms before try again  */
 	}
 	return 0;
 }
diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c
index a57f3a7d4748..6e356325d8d9 100644
--- a/drivers/scsi/aacraid/aachba.c
+++ b/drivers/scsi/aacraid/aachba.c
@@ -115,8 +115,6 @@
 #define ASENCODE_LUN_FAILED_SELF_CONFIG		0x00
 #define ASENCODE_OVERLAPPED_COMMAND		0x00
 
-#define AAC_STAT_GOOD (DID_OK << 16 | COMMAND_COMPLETE << 8 | SAM_STAT_GOOD)
-
 #define BYTE0(x) (unsigned char)(x)
 #define BYTE1(x) (unsigned char)((x) >> 8)
 #define BYTE2(x) (unsigned char)((x) >> 16)
@@ -2961,7 +2959,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 
 	case SYNCHRONIZE_CACHE:
 		if (((aac_cache & 6) == 6) && dev->cache_protected) {
-			scsicmd->result = AAC_STAT_GOOD;
+			scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+					  SAM_STAT_GOOD;
 			break;
 		}
 		/* Issue FIB to tell Firmware to flush it's cache */
@@ -2989,7 +2988,9 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 				arr[1] = scsicmd->cmnd[2];
 				scsi_sg_copy_from_buffer(scsicmd, &inq_data,
 							 sizeof(inq_data));
-				scsicmd->result = AAC_STAT_GOOD;
+				scsicmd->result = DID_OK << 16 |
+						  COMMAND_COMPLETE << 8 |
+						  SAM_STAT_GOOD;
 			} else if (scsicmd->cmnd[2] == 0x80) {
 				/* unit serial number page */
 				arr[3] = setinqserial(dev, &arr[4],
@@ -3000,7 +3001,9 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 				if (aac_wwn != 2)
 					return aac_get_container_serial(
 						scsicmd);
-				scsicmd->result = AAC_STAT_GOOD;
+				scsicmd->result = DID_OK << 16 |
+						  COMMAND_COMPLETE << 8 |
+						  SAM_STAT_GOOD;
 			} else if (scsicmd->cmnd[2] == 0x83) {
 				/* vpd page 0x83 - Device Identification Page */
 				char *sno = (char *)&inq_data;
@@ -3009,7 +3012,9 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 				if (aac_wwn != 2)
 					return aac_get_container_serial(
 						scsicmd);
-				scsicmd->result = AAC_STAT_GOOD;
+				scsicmd->result = DID_OK << 16 |
+						  COMMAND_COMPLETE << 8 |
+						  SAM_STAT_GOOD;
 			} else {
 				/* vpd page not implemented */
 				scsicmd->result = DID_OK << 16 |
@@ -3040,7 +3045,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 			inq_data.inqd_pdt = INQD_PDT_PROC;	/* Processor device */
 			scsi_sg_copy_from_buffer(scsicmd, &inq_data,
 						 sizeof(inq_data));
-			scsicmd->result = AAC_STAT_GOOD;
+			scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+					  SAM_STAT_GOOD;
 			break;
 		}
 		if (dev->in_reset)
@@ -3089,7 +3095,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 		/* Do not cache partition table for arrays */
 		scsicmd->device->removable = 1;
 
-		scsicmd->result = AAC_STAT_GOOD;
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+				  SAM_STAT_GOOD;
 		break;
 	}
 
@@ -3115,7 +3122,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 		scsi_sg_copy_from_buffer(scsicmd, cp, sizeof(cp));
 		/* Do not cache partition table for arrays */
 		scsicmd->device->removable = 1;
-		scsicmd->result = AAC_STAT_GOOD;
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+				  SAM_STAT_GOOD;
 		break;
 	}
 
@@ -3194,7 +3202,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 		scsi_sg_copy_from_buffer(scsicmd,
 					 (char *)&mpd,
 					 mode_buf_length);
-		scsicmd->result = AAC_STAT_GOOD;
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+				  SAM_STAT_GOOD;
 		break;
 	}
 	case MODE_SENSE_10:
@@ -3271,7 +3280,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 					 (char *)&mpd10,
 					 mode_buf_length);
 
-		scsicmd->result = AAC_STAT_GOOD;
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+				  SAM_STAT_GOOD;
 		break;
 	}
 	case REQUEST_SENSE:
@@ -3280,7 +3290,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 				sizeof(struct sense_data));
 		memset(&dev->fsa_dev[cid].sense_data, 0,
 				sizeof(struct sense_data));
-		scsicmd->result = AAC_STAT_GOOD;
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+				  SAM_STAT_GOOD;
 		break;
 
 	case ALLOW_MEDIUM_REMOVAL:
@@ -3290,7 +3301,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 		else
 			fsa_dev_ptr[cid].locked = 0;
 
-		scsicmd->result = AAC_STAT_GOOD;
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+				  SAM_STAT_GOOD;
 		break;
 	/*
 	 *	These commands are all No-Ops
@@ -3314,7 +3326,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 	case REZERO_UNIT:
 	case REASSIGN_BLOCKS:
 	case SEEK_10:
-		scsicmd->result = AAC_STAT_GOOD;
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+				  SAM_STAT_GOOD;
 		break;
 
 	case START_STOP:
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index d62ddd63f4fe..6e1b022a823d 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -514,7 +514,7 @@ int aac_fib_send(u16 command, struct fib *fibptr, unsigned long size,
 	 *	The only invalid cases are if the caller requests to wait and
 	 *	does not request a response and if the caller does not want a
 	 *	response and the Fib is not allocated from pool. If a response
-	 *	is not requesed the Fib will just be deallocaed by the DPC
+	 *	is not requested the Fib will just be deallocaed by the DPC
 	 *	routine when the response comes back from the adapter. No
 	 *	further processing will be done besides deleting the Fib. We
 	 *	will have a debug mode where the adapter can notify the host
diff --git a/drivers/scsi/aacraid/dpcsup.c b/drivers/scsi/aacraid/dpcsup.c
index 417ba349e10e..ddc69738375f 100644
--- a/drivers/scsi/aacraid/dpcsup.c
+++ b/drivers/scsi/aacraid/dpcsup.c
@@ -65,7 +65,7 @@ unsigned int aac_response_normal(struct aac_queue * q)
 	/*
 	 *	Keep pulling response QEs off the response queue and waking
 	 *	up the waiters until there are no more QEs. We then return
-	 *	back to the system. If no response was requesed we just
+	 *	back to the system. If no response was requested we just
 	 *	deallocate the Fib here and continue.
 	 */
 	while(aac_consumer_get(dev, q, &entry))
diff --git a/drivers/scsi/aacraid/rx.c b/drivers/scsi/aacraid/rx.c
index 620166694171..576cdf9cc120 100644
--- a/drivers/scsi/aacraid/rx.c
+++ b/drivers/scsi/aacraid/rx.c
@@ -319,7 +319,7 @@ static void aac_rx_start_adapter(struct aac_dev *dev)
 	union aac_init *init;
 
 	init = dev->init;
-	init->r7.host_elapsed_seconds = cpu_to_le32(get_seconds());
+	init->r7.host_elapsed_seconds = cpu_to_le32(ktime_get_real_seconds());
 	// We can only use a 32 bit address here
 	rx_sync_cmd(dev, INIT_STRUCT_BASE_ADDRESS, (u32)(ulong)dev->init_pa,
 	  0, 0, 0, 0, 0, NULL, NULL, NULL, NULL, NULL);
diff --git a/drivers/scsi/aacraid/sa.c b/drivers/scsi/aacraid/sa.c
index 882f40353b96..efa96c1c6aa3 100644
--- a/drivers/scsi/aacraid/sa.c
+++ b/drivers/scsi/aacraid/sa.c
@@ -251,7 +251,7 @@ static void aac_sa_start_adapter(struct aac_dev *dev)
 	 * Fill in the remaining pieces of the init.
 	 */
 	init = dev->init;
-	init->r7.host_elapsed_seconds = cpu_to_le32(get_seconds());
+	init->r7.host_elapsed_seconds = cpu_to_le32(ktime_get_real_seconds());
 	/* We can only use a 32 bit address here */
 	sa_sync_cmd(dev, INIT_STRUCT_BASE_ADDRESS, 
 			(u32)(ulong)dev->init_pa, 0, 0, 0, 0, 0,
diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c
index 4ebb35a29caa..7a51ccfa8662 100644
--- a/drivers/scsi/aacraid/src.c
+++ b/drivers/scsi/aacraid/src.c
@@ -409,7 +409,8 @@ static void aac_src_start_adapter(struct aac_dev *dev)
 
 	init = dev->init;
 	if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE3) {
-		init->r8.host_elapsed_seconds = cpu_to_le32(get_seconds());
+		init->r8.host_elapsed_seconds =
+			cpu_to_le32(ktime_get_real_seconds());
 		src_sync_cmd(dev, INIT_STRUCT_BASE_ADDRESS,
 			lower_32_bits(dev->init_pa),
 			upper_32_bits(dev->init_pa),
@@ -417,7 +418,8 @@ static void aac_src_start_adapter(struct aac_dev *dev)
 			(AAC_MAX_HRRQ - 1) * sizeof(struct _rrq),
 			0, 0, 0, NULL, NULL, NULL, NULL, NULL);
 	} else {
-		init->r7.host_elapsed_seconds = cpu_to_le32(get_seconds());
+		init->r7.host_elapsed_seconds =
+			cpu_to_le32(ktime_get_real_seconds());
 		// We can only use a 32 bit address here
 		src_sync_cmd(dev, INIT_STRUCT_BASE_ADDRESS,
 			(u32)(ulong)dev->init_pa, 0, 0, 0, 0, 0,
diff --git a/drivers/scsi/advansys.c b/drivers/scsi/advansys.c
index 24e57e770432..713f69033f20 100644
--- a/drivers/scsi/advansys.c
+++ b/drivers/scsi/advansys.c
@@ -2416,8 +2416,8 @@ static void asc_prt_scsi_host(struct Scsi_Host *s)
 	struct asc_board *boardp = shost_priv(s);
 
 	printk("Scsi_Host at addr 0x%p, device %s\n", s, dev_name(boardp->dev));
-	printk(" host_busy %u, host_no %d,\n",
-	       atomic_read(&s->host_busy), s->host_no);
+	printk(" host_busy %d, host_no %d,\n",
+	       scsi_host_busy(s), s->host_no);
 
 	printk(" base 0x%lx, io_port 0x%lx, irq %d,\n",
 	       (ulong)s->base, (ulong)s->io_port, boardp->irq);
@@ -3182,8 +3182,8 @@ static void asc_prt_driver_conf(struct seq_file *m, struct Scsi_Host *shost)
 		shost->host_no);
 
 	seq_printf(m,
-		   " host_busy %u, max_id %u, max_lun %llu, max_channel %u\n",
-		   atomic_read(&shost->host_busy), shost->max_id,
+		   " host_busy %d, max_id %u, max_lun %llu, max_channel %u\n",
+		   scsi_host_busy(shost), shost->max_id,
 		   shost->max_lun, shost->max_channel);
 
 	seq_printf(m,
@@ -8466,7 +8466,7 @@ static int AdvExeScsiQueue(ADV_DVC_VAR *asc_dvc, adv_req_t *reqp)
 }
 
 /*
- * Execute a single 'Scsi_Cmnd'.
+ * Execute a single 'struct scsi_cmnd'.
  */
 static int asc_execute_scsi_cmnd(struct scsi_cmnd *scp)
 {
diff --git a/drivers/scsi/aha152x.c b/drivers/scsi/aha152x.c
index bc0058df31c6..4d7b0e0adbf7 100644
--- a/drivers/scsi/aha152x.c
+++ b/drivers/scsi/aha152x.c
@@ -422,16 +422,16 @@ enum aha152x_state {
  *
  */
 struct aha152x_hostdata {
-	Scsi_Cmnd *issue_SC;
+	struct scsi_cmnd *issue_SC;
 		/* pending commands to issue */
 
-	Scsi_Cmnd *current_SC;
+	struct scsi_cmnd *current_SC;
 		/* current command on the bus */
 
-	Scsi_Cmnd *disconnected_SC;
+	struct scsi_cmnd *disconnected_SC;
 		/* commands that disconnected */
 
-	Scsi_Cmnd *done_SC;
+	struct scsi_cmnd *done_SC;
 		/* command that was completed */
 
 	spinlock_t lock;
@@ -510,7 +510,7 @@ struct aha152x_hostdata {
  *
  */
 struct aha152x_scdata {
-	Scsi_Cmnd *next;	/* next sc in queue */
+	struct scsi_cmnd *next;	/* next sc in queue */
 	struct completion *done;/* semaphore to block on */
 	struct scsi_eh_save ses;
 };
@@ -633,7 +633,7 @@ static void aha152x_error(struct Scsi_Host *shpnt, char *msg);
 static void done(struct Scsi_Host *shpnt, int error);
 
 /* diagnostics */
-static void show_command(Scsi_Cmnd * ptr);
+static void show_command(struct scsi_cmnd * ptr);
 static void show_queues(struct Scsi_Host *shpnt);
 static void disp_enintr(struct Scsi_Host *shpnt);
 
@@ -642,9 +642,9 @@ static void disp_enintr(struct Scsi_Host *shpnt);
  *  queue services:
  *
  */
-static inline void append_SC(Scsi_Cmnd **SC, Scsi_Cmnd *new_SC)
+static inline void append_SC(struct scsi_cmnd **SC, struct scsi_cmnd *new_SC)
 {
-	Scsi_Cmnd *end;
+	struct scsi_cmnd *end;
 
 	SCNEXT(new_SC) = NULL;
 	if (!*SC)
@@ -656,9 +656,9 @@ static inline void append_SC(Scsi_Cmnd **SC, Scsi_Cmnd *new_SC)
 	}
 }
 
-static inline Scsi_Cmnd *remove_first_SC(Scsi_Cmnd ** SC)
+static inline struct scsi_cmnd *remove_first_SC(struct scsi_cmnd ** SC)
 {
-	Scsi_Cmnd *ptr;
+	struct scsi_cmnd *ptr;
 
 	ptr = *SC;
 	if (ptr) {
@@ -668,9 +668,10 @@ static inline Scsi_Cmnd *remove_first_SC(Scsi_Cmnd ** SC)
 	return ptr;
 }
 
-static inline Scsi_Cmnd *remove_lun_SC(Scsi_Cmnd ** SC, int target, int lun)
+static inline struct scsi_cmnd *remove_lun_SC(struct scsi_cmnd ** SC,
+					      int target, int lun)
 {
-	Scsi_Cmnd *ptr, *prev;
+	struct scsi_cmnd *ptr, *prev;
 
 	for (ptr = *SC, prev = NULL;
 	     ptr && ((ptr->device->id != target) || (ptr->device->lun != lun));
@@ -689,9 +690,10 @@ static inline Scsi_Cmnd *remove_lun_SC(Scsi_Cmnd ** SC, int target, int lun)
 	return ptr;
 }
 
-static inline Scsi_Cmnd *remove_SC(Scsi_Cmnd **SC, Scsi_Cmnd *SCp)
+static inline struct scsi_cmnd *remove_SC(struct scsi_cmnd **SC,
+					  struct scsi_cmnd *SCp)
 {
-	Scsi_Cmnd *ptr, *prev;
+	struct scsi_cmnd *ptr, *prev;
 
 	for (ptr = *SC, prev = NULL;
 	     ptr && SCp!=ptr;
@@ -912,8 +914,9 @@ static int setup_expected_interrupts(struct Scsi_Host *shpnt)
 /*
  *  Queue a command and setup interrupts for a free bus.
  */
-static int aha152x_internal_queue(Scsi_Cmnd *SCpnt, struct completion *complete,
-		int phase, void (*done)(Scsi_Cmnd *))
+static int aha152x_internal_queue(struct scsi_cmnd *SCpnt,
+				  struct completion *complete,
+				  int phase, void (*done)(struct scsi_cmnd *))
 {
 	struct Scsi_Host *shpnt = SCpnt->device->host;
 	unsigned long flags;
@@ -987,7 +990,8 @@ static int aha152x_internal_queue(Scsi_Cmnd *SCpnt, struct completion *complete,
  *  queue a command
  *
  */
-static int aha152x_queue_lck(Scsi_Cmnd *SCpnt, void (*done)(Scsi_Cmnd *))
+static int aha152x_queue_lck(struct scsi_cmnd *SCpnt,
+			     void (*done)(struct scsi_cmnd *))
 {
 	return aha152x_internal_queue(SCpnt, NULL, 0, done);
 }
@@ -998,7 +1002,7 @@ static DEF_SCSI_QCMD(aha152x_queue)
 /*
  *
  */
-static void reset_done(Scsi_Cmnd *SCpnt)
+static void reset_done(struct scsi_cmnd *SCpnt)
 {
 	if(SCSEM(SCpnt)) {
 		complete(SCSEM(SCpnt));
@@ -1011,10 +1015,10 @@ static void reset_done(Scsi_Cmnd *SCpnt)
  *  Abort a command
  *
  */
-static int aha152x_abort(Scsi_Cmnd *SCpnt)
+static int aha152x_abort(struct scsi_cmnd *SCpnt)
 {
 	struct Scsi_Host *shpnt = SCpnt->device->host;
-	Scsi_Cmnd *ptr;
+	struct scsi_cmnd *ptr;
 	unsigned long flags;
 
 	DO_LOCK(flags);
@@ -1052,7 +1056,7 @@ static int aha152x_abort(Scsi_Cmnd *SCpnt)
  * Reset a device
  *
  */
-static int aha152x_device_reset(Scsi_Cmnd * SCpnt)
+static int aha152x_device_reset(struct scsi_cmnd * SCpnt)
 {
 	struct Scsi_Host *shpnt = SCpnt->device->host;
 	DECLARE_COMPLETION(done);
@@ -1110,13 +1114,14 @@ static int aha152x_device_reset(Scsi_Cmnd * SCpnt)
 	return ret;
 }
 
-static void free_hard_reset_SCs(struct Scsi_Host *shpnt, Scsi_Cmnd **SCs)
+static void free_hard_reset_SCs(struct Scsi_Host *shpnt,
+				struct scsi_cmnd **SCs)
 {
-	Scsi_Cmnd *ptr;
+	struct scsi_cmnd *ptr;
 
 	ptr=*SCs;
 	while(ptr) {
-		Scsi_Cmnd *next;
+		struct scsi_cmnd *next;
 
 		if(SCDATA(ptr)) {
 			next = SCNEXT(ptr);
@@ -1171,7 +1176,7 @@ static int aha152x_bus_reset_host(struct Scsi_Host *shpnt)
  * Reset the bus
  *
  */
-static int aha152x_bus_reset(Scsi_Cmnd *SCpnt)
+static int aha152x_bus_reset(struct scsi_cmnd *SCpnt)
 {
 	return aha152x_bus_reset_host(SCpnt->device->host);
 }
@@ -1436,7 +1441,7 @@ static void busfree_run(struct Scsi_Host *shpnt)
 
 			if(!(DONE_SC->SCp.phase & not_issued)) {
 				struct aha152x_scdata *sc;
-				Scsi_Cmnd *ptr = DONE_SC;
+				struct scsi_cmnd *ptr = DONE_SC;
 				DONE_SC=NULL;
 
 				sc = SCDATA(ptr);
@@ -1451,7 +1456,7 @@ static void busfree_run(struct Scsi_Host *shpnt)
 		}
 
 		if(DONE_SC && DONE_SC->scsi_done) {
-			Scsi_Cmnd *ptr = DONE_SC;
+			struct scsi_cmnd *ptr = DONE_SC;
 			DONE_SC=NULL;
 
 			/* turn led off, when no commands are in the driver */
@@ -2247,13 +2252,13 @@ static void parerr_run(struct Scsi_Host *shpnt)
  */
 static void rsti_run(struct Scsi_Host *shpnt)
 {
-	Scsi_Cmnd *ptr;
+	struct scsi_cmnd *ptr;
 
 	shost_printk(KERN_NOTICE, shpnt, "scsi reset in\n");
 
 	ptr=DISCONNECTED_SC;
 	while(ptr) {
-		Scsi_Cmnd *next = SCNEXT(ptr);
+		struct scsi_cmnd *next = SCNEXT(ptr);
 
 		if (!ptr->device->soft_reset) {
 			remove_SC(&DISCONNECTED_SC, ptr);
@@ -2438,7 +2443,7 @@ static void disp_enintr(struct Scsi_Host *shpnt)
 /*
  * Show the command data of a command
  */
-static void show_command(Scsi_Cmnd *ptr)
+static void show_command(struct scsi_cmnd *ptr)
 {
 	scsi_print_command(ptr);
 	scmd_printk(KERN_DEBUG, ptr,
@@ -2462,7 +2467,7 @@ static void show_command(Scsi_Cmnd *ptr)
  */
 static void show_queues(struct Scsi_Host *shpnt)
 {
-	Scsi_Cmnd *ptr;
+	struct scsi_cmnd *ptr;
 	unsigned long flags;
 
 	DO_LOCK(flags);
@@ -2484,7 +2489,7 @@ static void show_queues(struct Scsi_Host *shpnt)
 	disp_enintr(shpnt);
 }
 
-static void get_command(struct seq_file *m, Scsi_Cmnd * ptr)
+static void get_command(struct seq_file *m, struct scsi_cmnd * ptr)
 {
 	int i;
 
@@ -2813,7 +2818,7 @@ static int aha152x_set_info(struct Scsi_Host *shpnt, char *buffer, int length)
 static int aha152x_show_info(struct seq_file *m, struct Scsi_Host *shpnt)
 {
 	int i;
-	Scsi_Cmnd *ptr;
+	struct scsi_cmnd *ptr;
 	unsigned long flags;
 
 	seq_puts(m, AHA152X_REVID "\n");
diff --git a/drivers/scsi/aha1740.c b/drivers/scsi/aha1740.c
index b48d5436f094..786bf7f32c64 100644
--- a/drivers/scsi/aha1740.c
+++ b/drivers/scsi/aha1740.c
@@ -207,11 +207,11 @@ static int aha1740_test_port(unsigned int base)
 static irqreturn_t aha1740_intr_handle(int irq, void *dev_id)
 {
 	struct Scsi_Host *host = (struct Scsi_Host *) dev_id;
-        void (*my_done)(Scsi_Cmnd *);
+        void (*my_done)(struct scsi_cmnd *);
 	int errstatus, adapstat;
 	int number_serviced;
 	struct ecb *ecbptr;
-	Scsi_Cmnd *SCtmp;
+	struct scsi_cmnd *SCtmp;
 	unsigned int base;
 	unsigned long flags;
 	int handled = 0;
@@ -311,7 +311,8 @@ static irqreturn_t aha1740_intr_handle(int irq, void *dev_id)
 	return IRQ_RETVAL(handled);
 }
 
-static int aha1740_queuecommand_lck(Scsi_Cmnd * SCpnt, void (*done)(Scsi_Cmnd *))
+static int aha1740_queuecommand_lck(struct scsi_cmnd * SCpnt,
+				    void (*done)(struct scsi_cmnd *))
 {
 	unchar direction;
 	unchar *cmd = (unchar *) SCpnt->cmnd;
@@ -520,7 +521,7 @@ static int aha1740_biosparam(struct scsi_device *sdev,
 	return 0;
 }
 
-static int aha1740_eh_abort_handler (Scsi_Cmnd *dummy)
+static int aha1740_eh_abort_handler (struct scsi_cmnd *dummy)
 {
 /*
  * From Alan Cox :
diff --git a/drivers/scsi/aha1740.h b/drivers/scsi/aha1740.h
index dfdaa4d3ea4e..6eeed6da0b54 100644
--- a/drivers/scsi/aha1740.h
+++ b/drivers/scsi/aha1740.h
@@ -135,8 +135,8 @@ struct ecb {			/* Enhanced Control Block 6.1 */
 /* Hardware defined portion ends here, rest is driver defined */
 	u8 sense[MAX_SENSE];	/* Sense area */
 	u8 status[MAX_STATUS];	/* Status area */
-	Scsi_Cmnd *SCpnt;	/* Link to the SCSI Command Block */
-	void (*done) (Scsi_Cmnd *);	/* Completion Function */
+	struct scsi_cmnd *SCpnt;	/* Link to the SCSI Command Block */
+	void (*done) (struct scsi_cmnd *);	/* Completion Function */
 };
 
 #define	AHA1740CMD_NOP	 0x00	/* No OP */
diff --git a/drivers/scsi/aic94xx/aic94xx_init.c b/drivers/scsi/aic94xx/aic94xx_init.c
index 80e5b283fd81..1391e5f35918 100644
--- a/drivers/scsi/aic94xx/aic94xx_init.c
+++ b/drivers/scsi/aic94xx/aic94xx_init.c
@@ -1030,8 +1030,10 @@ static int __init aic94xx_init(void)
 
 	aic94xx_transport_template =
 		sas_domain_attach_transport(&aic94xx_transport_functions);
-	if (!aic94xx_transport_template)
+	if (!aic94xx_transport_template) {
+		err = -ENOMEM;
 		goto out_destroy_caches;
+	}
 
 	err = pci_register_driver(&aic94xx_pci_driver);
 	if (err)
diff --git a/drivers/scsi/arcmsr/arcmsr.h b/drivers/scsi/arcmsr/arcmsr.h
index 2e51ccc510e8..9c397a2794d6 100644
--- a/drivers/scsi/arcmsr/arcmsr.h
+++ b/drivers/scsi/arcmsr/arcmsr.h
@@ -49,7 +49,7 @@ struct device_attribute;
 #define ARCMSR_MAX_OUTSTANDING_CMD	1024
 #define ARCMSR_DEFAULT_OUTSTANDING_CMD	128
 #define ARCMSR_MIN_OUTSTANDING_CMD	32
-#define ARCMSR_DRIVER_VERSION		"v1.40.00.05-20180309"
+#define ARCMSR_DRIVER_VERSION		"v1.40.00.09-20180709"
 #define ARCMSR_SCSI_INITIATOR_ID	255
 #define ARCMSR_MAX_XFER_SECTORS		512
 #define ARCMSR_MAX_XFER_SECTORS_B	4096
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index 732b5d9242f1..12316ef4c893 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -1061,6 +1061,13 @@ static int arcmsr_resume(struct pci_dev *pdev)
 	pci_set_master(pdev);
 	if (arcmsr_request_irq(pdev, acb) == FAILED)
 		goto controller_stop;
+	if (acb->adapter_type == ACB_ADAPTER_TYPE_E) {
+		writel(0, &acb->pmuE->host_int_status);
+		writel(ARCMSR_HBEMU_DOORBELL_SYNC, &acb->pmuE->iobound_doorbell);
+		acb->in_doorbell = 0;
+		acb->out_doorbell = 0;
+		acb->doneq_index = 0;
+	}
 	arcmsr_iop_init(acb);
 	arcmsr_init_get_devmap_timer(acb);
 	if (set_date_time)
diff --git a/drivers/scsi/atp870u.c b/drivers/scsi/atp870u.c
index b46997cf77e2..8996d2329e11 100644
--- a/drivers/scsi/atp870u.c
+++ b/drivers/scsi/atp870u.c
@@ -1055,7 +1055,7 @@ static void tscam(struct Scsi_Host *host, bool wide_chip, u8 scam_on)
 	udelay(2);		/* 2 deskew delay(45ns*2=90ns) */
 	val &= 0x007f;		/* no bsy  */
 	atp_writew_io(dev, 0, 0x1c, val);
-	mdelay(128);
+	msleep(128);
 	val &= 0x00fb;		/* after 1ms no msg */
 	atp_writew_io(dev, 0, 0x1c, val);
 	while ((atp_readb_io(dev, 0, 0x1c) & 0x04) != 0)
@@ -1286,9 +1286,9 @@ static void atp870_init(struct Scsi_Host *shpnt)
 	k = (atp_readb_base(atpdev, 0x3a) & 0xf3) | 0x10;
 	atp_writeb_base(atpdev, 0x3a, k);
 	atp_writeb_base(atpdev, 0x3a, k & 0xdf);
-	mdelay(32);
+	msleep(32);
 	atp_writeb_base(atpdev, 0x3a, k);
-	mdelay(32);
+	msleep(32);
 	atp_set_host_id(atpdev, 0, host_id);
 
 	tscam(shpnt, wide_chip, scam_on);
@@ -1370,9 +1370,9 @@ static void atp880_init(struct Scsi_Host *shpnt)
 	k = atp_readb_base(atpdev, 0x38) & 0x80;
 	atp_writeb_base(atpdev, 0x38, k);
 	atp_writeb_base(atpdev, 0x3b, 0x20);
-	mdelay(32);
+	msleep(32);
 	atp_writeb_base(atpdev, 0x3b, 0);
-	mdelay(32);
+	msleep(32);
 	atp_readb_io(atpdev, 0, 0x1b);
 	atp_readb_io(atpdev, 0, 0x17);
 
@@ -1454,10 +1454,10 @@ static void atp885_init(struct Scsi_Host *shpnt)
 	atp_writeb_base(atpdev, 0x28, k);
 	atp_writeb_pci(atpdev, 0, 1, 0x80);
 	atp_writeb_pci(atpdev, 1, 1, 0x80);
-	mdelay(100);
+	msleep(100);
 	atp_writeb_pci(atpdev, 0, 1, 0);
 	atp_writeb_pci(atpdev, 1, 1, 0);
-	mdelay(1000);
+	msleep(1000);
 	atp_readb_io(atpdev, 0, 0x1b);
 	atp_readb_io(atpdev, 0, 0x17);
 	atp_readb_io(atpdev, 1, 0x1b);
@@ -1473,7 +1473,7 @@ static void atp885_init(struct Scsi_Host *shpnt)
 		k = (k & 0x07) | 0x40;
 	atp_set_host_id(atpdev, 1, k);
 
-	mdelay(600); /* this delay used to be called tscam_885() */
+	msleep(600); /* this delay used to be called tscam_885() */
 	dev_info(&pdev->dev, "Scanning Channel A SCSI Device ...\n");
 	atp_is(atpdev, 0, true, atp_readb_io(atpdev, 0, 0x1b) >> 7);
 	atp_writeb_io(atpdev, 0, 0x16, 0x80);
diff --git a/drivers/scsi/be2iscsi/be_cmds.c b/drivers/scsi/be2iscsi/be_cmds.c
index 2eb66df3e3d6..c10aac4dbc5e 100644
--- a/drivers/scsi/be2iscsi/be_cmds.c
+++ b/drivers/scsi/be2iscsi/be_cmds.c
@@ -1545,7 +1545,7 @@ int beiscsi_set_host_data(struct beiscsi_hba *phba)
 		snprintf((char *)ioctl->param.req.param_data,
 			 sizeof(ioctl->param.req.param_data),
 			 "Linux iSCSI v%s", BUILD_STR);
-	ioctl->param.req.param_len = ALIGN(ioctl->param.req.param_len, 4);
+	ioctl->param.req.param_len = ALIGN(ioctl->param.req.param_len + 1, 4);
 	if (ioctl->param.req.param_len > BE_CMD_MAX_DRV_VERSION)
 		ioctl->param.req.param_len = BE_CMD_MAX_DRV_VERSION;
 	ret = be_mbox_notify(ctrl);
diff --git a/drivers/scsi/be2iscsi/be_iscsi.c b/drivers/scsi/be2iscsi/be_iscsi.c
index a398c54139aa..c8f0a2144b44 100644
--- a/drivers/scsi/be2iscsi/be_iscsi.c
+++ b/drivers/scsi/be2iscsi/be_iscsi.c
@@ -1,11 +1,14 @@
 /*
- * Copyright 2017 Broadcom. All Rights Reserved.
- * The term "Broadcom" refers to Broadcom Limited and/or its subsidiaries.
+ * This file is part of the Emulex Linux Device Driver for Enterprise iSCSI
+ * Host Bus Adapters. Refer to the README file included with this package
+ * for driver version and adapter compatibility.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation. The full GNU General
- * Public License is included in this distribution in the file called COPYING.
+ * Copyright (c) 2018 Broadcom. All Rights Reserved.
+ * The term "Broadcom" refers to Broadcom Inc. and/or its subsidiaries.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License as published
+ * by the Free Software Foundation.
  *
  * Contact Information:
  * linux-drivers@broadcom.com
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index 818d185d63f0..3660059784f7 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -1,11 +1,22 @@
 /*
- * Copyright 2017 Broadcom. All Rights Reserved.
- * The term "Broadcom" refers to Broadcom Limited and/or its subsidiaries.
+ * This file is part of the Emulex Linux Device Driver for Enterprise iSCSI
+ * Host Bus Adapters. Refer to the README file included with this package
+ * for driver version and adapter compatibility.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation. The full GNU General
- * Public License is included in this distribution in the file called COPYING.
+ * Copyright (c) 2018 Broadcom. All Rights Reserved.
+ * The term “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful. ALL EXPRESS
+ * OR IMPLIED CONDITIONS, REPRESENTATIONS AND WARRANTIES, INCLUDING ANY
+ * IMPLIED WARRANTY OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE,
+ * OR NON-INFRINGEMENT, ARE DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH
+ * DISCLAIMERS ARE HELD TO BE LEGALLY INVALID.
+ * See the GNU General Public License for more details, a copy of which
+ * can be found in the file COPYING included with this package.
  *
  * Contact Information:
  * linux-drivers@broadcom.com
diff --git a/drivers/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c
index 66ca967f2850..8fdc07b6c686 100644
--- a/drivers/scsi/be2iscsi/be_mgmt.c
+++ b/drivers/scsi/be2iscsi/be_mgmt.c
@@ -1,11 +1,22 @@
 /*
- * Copyright 2017 Broadcom. All Rights Reserved.
- * The term "Broadcom" refers to Broadcom Limited and/or its subsidiaries.
+ * This file is part of the Emulex Linux Device Driver for Enterprise iSCSI
+ * Host Bus Adapters. Refer to the README file included with this package
+ * for driver version and adapter compatibility.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation. The full GNU General
- * Public License is included in this distribution in the file called COPYING.
+ * Copyright (c) 2018 Broadcom. All Rights Reserved.
+ * The term “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful. ALL EXPRESS
+ * OR IMPLIED CONDITIONS, REPRESENTATIONS AND WARRANTIES, INCLUDING ANY
+ * IMPLIED WARRANTY OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE,
+ * OR NON-INFRINGEMENT, ARE DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH
+ * DISCLAIMERS ARE HELD TO BE LEGALLY INVALID.
+ * See the GNU General Public License for more details, a copy of which
+ * can be found in the file COPYING included with this package.
  *
  * Contact Information:
  * linux-drivers@broadcom.com
diff --git a/drivers/scsi/bfa/bfad_im.c b/drivers/scsi/bfa/bfad_im.c
index c05d6e91e4bd..c4a33317d344 100644
--- a/drivers/scsi/bfa/bfad_im.c
+++ b/drivers/scsi/bfa/bfad_im.c
@@ -70,21 +70,18 @@ bfa_cb_ioim_done(void *drv, struct bfad_ioim_s *dio,
 				host_status = DID_ERROR;
 			}
 		}
-		cmnd->result = ScsiResult(host_status, scsi_status);
+		cmnd->result = host_status << 16 | scsi_status;
 
 		break;
 
 	case BFI_IOIM_STS_TIMEDOUT:
-		host_status = DID_TIME_OUT;
-		cmnd->result = ScsiResult(host_status, 0);
+		cmnd->result = DID_TIME_OUT << 16;
 		break;
 	case BFI_IOIM_STS_PATHTOV:
-		host_status = DID_TRANSPORT_DISRUPTED;
-		cmnd->result = ScsiResult(host_status, 0);
+		cmnd->result = DID_TRANSPORT_DISRUPTED << 16;
 		break;
 	default:
-		host_status = DID_ERROR;
-		cmnd->result = ScsiResult(host_status, 0);
+		cmnd->result = DID_ERROR << 16;
 	}
 
 	/* Unmap DMA, if host is NULL, it means a scsi passthru cmd */
@@ -117,7 +114,7 @@ bfa_cb_ioim_good_comp(void *drv, struct bfad_ioim_s *dio)
 	struct bfad_itnim_data_s *itnim_data;
 	struct bfad_itnim_s *itnim;
 
-	cmnd->result = ScsiResult(DID_OK, SCSI_STATUS_GOOD);
+	cmnd->result = DID_OK << 16 | SCSI_STATUS_GOOD;
 
 	/* Unmap DMA, if host is NULL, it means a scsi passthru cmd */
 	if (cmnd->device->host != NULL)
@@ -144,7 +141,7 @@ bfa_cb_ioim_abort(void *drv, struct bfad_ioim_s *dio)
 	struct scsi_cmnd *cmnd = (struct scsi_cmnd *)dio;
 	struct bfad_s         *bfad = drv;
 
-	cmnd->result = ScsiResult(DID_ERROR, 0);
+	cmnd->result = DID_ERROR << 16;
 
 	/* Unmap DMA, if host is NULL, it means a scsi passthru cmd */
 	if (cmnd->device->host != NULL)
@@ -1253,14 +1250,14 @@ bfad_im_queuecommand_lck(struct scsi_cmnd *cmnd, void (*done) (struct scsi_cmnd
 		printk(KERN_WARNING
 			"bfad%d, queuecommand %p %x failed, BFA stopped\n",
 		       bfad->inst_no, cmnd, cmnd->cmnd[0]);
-		cmnd->result = ScsiResult(DID_NO_CONNECT, 0);
+		cmnd->result = DID_NO_CONNECT << 16;
 		goto out_fail_cmd;
 	}
 
 
 	itnim = itnim_data->itnim;
 	if (!itnim) {
-		cmnd->result = ScsiResult(DID_IMM_RETRY, 0);
+		cmnd->result = DID_IMM_RETRY << 16;
 		goto out_fail_cmd;
 	}
 
diff --git a/drivers/scsi/bfa/bfad_im.h b/drivers/scsi/bfa/bfad_im.h
index af66275570c3..e61ed8dad0b4 100644
--- a/drivers/scsi/bfa/bfad_im.h
+++ b/drivers/scsi/bfa/bfad_im.h
@@ -44,7 +44,6 @@ u32 bfad_im_supported_speeds(struct bfa_s *bfa);
 #define MAX_FCP_LUN 16384
 #define BFAD_TARGET_RESET_TMO 60
 #define BFAD_LUN_RESET_TMO 60
-#define ScsiResult(host_code, scsi_code) (((host_code) << 16) | scsi_code)
 #define BFA_QUEUE_FULL_RAMP_UP_TIME 120
 
 /*
diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c
index 8f03a869ac98..e9e669a6c2bc 100644
--- a/drivers/scsi/bnx2i/bnx2i_hwi.c
+++ b/drivers/scsi/bnx2i/bnx2i_hwi.c
@@ -2727,6 +2727,8 @@ int bnx2i_map_ep_dbell_regs(struct bnx2i_endpoint *ep)
 					      BNX2X_DOORBELL_PCI_BAR);
 		reg_off = (1 << BNX2X_DB_SHIFT) * (cid_num & 0x1FFFF);
 		ep->qp.ctx_base = ioremap_nocache(reg_base + reg_off, 4);
+		if (!ep->qp.ctx_base)
+			return -ENOMEM;
 		goto arm_cq;
 	}
 
diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c
index c535c52e72e5..1c5051b1c125 100644
--- a/drivers/scsi/ch.c
+++ b/drivers/scsi/ch.c
@@ -199,7 +199,7 @@ ch_do_scsi(scsi_changer *ch, unsigned char *cmd, int cmd_len,
 				  buflength, &sshdr, timeout * HZ,
 				  MAX_RETRIES, NULL);
 
-	if (driver_byte(result) & DRIVER_SENSE) {
+	if (driver_byte(result) == DRIVER_SENSE) {
 		if (debug)
 			scsi_print_sense_hdr(ch->device, ch->name, &sshdr);
 		errno = ch_find_errno(&sshdr);
diff --git a/drivers/scsi/csiostor/csio_hw.c b/drivers/scsi/csiostor/csio_hw.c
index a10cf25ee7f9..23d07e9f87d0 100644
--- a/drivers/scsi/csiostor/csio_hw.c
+++ b/drivers/scsi/csiostor/csio_hw.c
@@ -761,27 +761,116 @@ out:
 static int
 csio_hw_get_flash_params(struct csio_hw *hw)
 {
+	/* Table for non-Numonix supported flash parts.  Numonix parts are left
+	 * to the preexisting code.  All flash parts have 64KB sectors.
+	 */
+	static struct flash_desc {
+		u32 vendor_and_model_id;
+		u32 size_mb;
+	} supported_flash[] = {
+		{ 0x150201, 4 << 20 },       /* Spansion 4MB S25FL032P */
+	};
+
+	u32 part, manufacturer;
+	u32 density, size = 0;
+	u32 flashid = 0;
 	int ret;
-	uint32_t info = 0;
 
 	ret = csio_hw_sf1_write(hw, 1, 1, 0, SF_RD_ID);
 	if (!ret)
-		ret = csio_hw_sf1_read(hw, 3, 0, 1, &info);
+		ret = csio_hw_sf1_read(hw, 3, 0, 1, &flashid);
 	csio_wr_reg32(hw, 0, SF_OP_A);    /* unlock SF */
-	if (ret != 0)
+	if (ret)
 		return ret;
 
-	if ((info & 0xff) != 0x20)		/* not a Numonix flash */
-		return -EINVAL;
-	info >>= 16;				/* log2 of size */
-	if (info >= 0x14 && info < 0x18)
-		hw->params.sf_nsec = 1 << (info - 16);
-	else if (info == 0x18)
-		hw->params.sf_nsec = 64;
-	else
-		return -EINVAL;
-	hw->params.sf_size = 1 << info;
+	/* Check to see if it's one of our non-standard supported Flash parts.
+	 */
+	for (part = 0; part < ARRAY_SIZE(supported_flash); part++)
+		if (supported_flash[part].vendor_and_model_id == flashid) {
+			hw->params.sf_size = supported_flash[part].size_mb;
+			hw->params.sf_nsec =
+				hw->params.sf_size / SF_SEC_SIZE;
+			goto found;
+		}
+
+	/* Decode Flash part size.  The code below looks repetative with
+	 * common encodings, but that's not guaranteed in the JEDEC
+	 * specification for the Read JADEC ID command.  The only thing that
+	 * we're guaranteed by the JADEC specification is where the
+	 * Manufacturer ID is in the returned result.  After that each
+	 * Manufacturer ~could~ encode things completely differently.
+	 * Note, all Flash parts must have 64KB sectors.
+	 */
+	manufacturer = flashid & 0xff;
+	switch (manufacturer) {
+	case 0x20: { /* Micron/Numonix */
+		/* This Density -> Size decoding table is taken from Micron
+		 * Data Sheets.
+		 */
+		density = (flashid >> 16) & 0xff;
+		switch (density) {
+		case 0x14 ... 0x19: /* 1MB - 32MB */
+			size = 1 << density;
+			break;
+		case 0x20: /* 64MB */
+			size = 1 << 26;
+			break;
+		case 0x21: /* 128MB */
+			size = 1 << 27;
+			break;
+		case 0x22: /* 256MB */
+			size = 1 << 28;
+		}
+		break;
+	}
+	case 0x9d: { /* ISSI -- Integrated Silicon Solution, Inc. */
+		/* This Density -> Size decoding table is taken from ISSI
+		 * Data Sheets.
+		 */
+		density = (flashid >> 16) & 0xff;
+		switch (density) {
+		case 0x16: /* 32 MB */
+			size = 1 << 25;
+			break;
+		case 0x17: /* 64MB */
+			size = 1 << 26;
+		}
+		break;
+	}
+	case 0xc2: /* Macronix */
+	case 0xef: /* Winbond */ {
+		/* This Density -> Size decoding table is taken from
+		 * Macronix and Winbond Data Sheets.
+		 */
+		density = (flashid >> 16) & 0xff;
+		switch (density) {
+		case 0x17: /* 8MB */
+		case 0x18: /* 16MB */
+			size = 1 << density;
+		}
+	}
+	}
+
+	/* If we didn't recognize the FLASH part, that's no real issue: the
+	 * Hardware/Software contract says that Hardware will _*ALWAYS*_
+	 * use a FLASH part which is at least 4MB in size and has 64KB
+	 * sectors.  The unrecognized FLASH part is likely to be much larger
+	 * than 4MB, but that's all we really need.
+	 */
+	if (size == 0) {
+		csio_warn(hw, "Unknown Flash Part, ID = %#x, assuming 4MB\n",
+			  flashid);
+		size = 1 << 22;
+	}
+
+	/* Store decoded Flash size */
+	hw->params.sf_size = size;
+	hw->params.sf_nsec = size / SF_SEC_SIZE;
 
+found:
+	if (hw->params.sf_size < FLASH_MIN_SIZE)
+		csio_warn(hw, "WARNING: Flash Part ID %#x, size %#x < %#x\n",
+			  flashid, hw->params.sf_size, FLASH_MIN_SIZE);
 	return 0;
 }
 
diff --git a/drivers/scsi/csiostor/csio_wr.c b/drivers/scsi/csiostor/csio_wr.c
index faa357b62c61..5022e82ccc4f 100644
--- a/drivers/scsi/csiostor/csio_wr.c
+++ b/drivers/scsi/csiostor/csio_wr.c
@@ -39,6 +39,7 @@
 #include <asm/page.h>
 #include <linux/cache.h>
 
+#include "t4_values.h"
 #include "csio_hw.h"
 #include "csio_wr.h"
 #include "csio_mb.h"
@@ -1309,8 +1310,11 @@ csio_wr_fixup_host_params(struct csio_hw *hw)
 	struct csio_sge *sge = &wrm->sge;
 	uint32_t clsz = L1_CACHE_BYTES;
 	uint32_t s_hps = PAGE_SHIFT - 10;
-	uint32_t ingpad = 0;
 	uint32_t stat_len = clsz > 64 ? 128 : 64;
+	u32 fl_align = clsz < 32 ? 32 : clsz;
+	u32 pack_align;
+	u32 ingpad, ingpack;
+	int pcie_cap;
 
 	csio_wr_reg32(hw, HOSTPAGESIZEPF0_V(s_hps) | HOSTPAGESIZEPF1_V(s_hps) |
 		      HOSTPAGESIZEPF2_V(s_hps) | HOSTPAGESIZEPF3_V(s_hps) |
@@ -1318,14 +1322,82 @@ csio_wr_fixup_host_params(struct csio_hw *hw)
 		      HOSTPAGESIZEPF6_V(s_hps) | HOSTPAGESIZEPF7_V(s_hps),
 		      SGE_HOST_PAGE_SIZE_A);
 
-	sge->csio_fl_align = clsz < 32 ? 32 : clsz;
-	ingpad = ilog2(sge->csio_fl_align) - 5;
+	/* T5 introduced the separation of the Free List Padding and
+	 * Packing Boundaries.  Thus, we can select a smaller Padding
+	 * Boundary to avoid uselessly chewing up PCIe Link and Memory
+	 * Bandwidth, and use a Packing Boundary which is large enough
+	 * to avoid false sharing between CPUs, etc.
+	 *
+	 * For the PCI Link, the smaller the Padding Boundary the
+	 * better.  For the Memory Controller, a smaller Padding
+	 * Boundary is better until we cross under the Memory Line
+	 * Size (the minimum unit of transfer to/from Memory).  If we
+	 * have a Padding Boundary which is smaller than the Memory
+	 * Line Size, that'll involve a Read-Modify-Write cycle on the
+	 * Memory Controller which is never good.
+	 */
+
+	/* We want the Packing Boundary to be based on the Cache Line
+	 * Size in order to help avoid False Sharing performance
+	 * issues between CPUs, etc.  We also want the Packing
+	 * Boundary to incorporate the PCI-E Maximum Payload Size.  We
+	 * get best performance when the Packing Boundary is a
+	 * multiple of the Maximum Payload Size.
+	 */
+	pack_align = fl_align;
+	pcie_cap = pci_find_capability(hw->pdev, PCI_CAP_ID_EXP);
+	if (pcie_cap) {
+		u32 mps, mps_log;
+		u16 devctl;
+
+		/* The PCIe Device Control Maximum Payload Size field
+		 * [bits 7:5] encodes sizes as powers of 2 starting at
+		 * 128 bytes.
+		 */
+		pci_read_config_word(hw->pdev,
+				     pcie_cap + PCI_EXP_DEVCTL,
+				     &devctl);
+		mps_log = ((devctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5) + 7;
+		mps = 1 << mps_log;
+		if (mps > pack_align)
+			pack_align = mps;
+	}
+
+	/* T5/T6 have a special interpretation of the "0"
+	 * value for the Packing Boundary.  This corresponds to 16
+	 * bytes instead of the expected 32 bytes.
+	 */
+	if (pack_align <= 16) {
+		ingpack = INGPACKBOUNDARY_16B_X;
+		fl_align = 16;
+	} else if (pack_align == 32) {
+		ingpack = INGPACKBOUNDARY_64B_X;
+		fl_align = 64;
+	} else {
+		u32 pack_align_log = fls(pack_align) - 1;
+
+		ingpack = pack_align_log - INGPACKBOUNDARY_SHIFT_X;
+		fl_align = pack_align;
+	}
+
+	/* Use the smallest Ingress Padding which isn't smaller than
+	 * the Memory Controller Read/Write Size.  We'll take that as
+	 * being 8 bytes since we don't know of any system with a
+	 * wider Memory Controller Bus Width.
+	 */
+	if (csio_is_t5(hw->pdev->device & CSIO_HW_CHIP_MASK))
+		ingpad = INGPADBOUNDARY_32B_X;
+	else
+		ingpad = T6_INGPADBOUNDARY_8B_X;
 
 	csio_set_reg_field(hw, SGE_CONTROL_A,
 			   INGPADBOUNDARY_V(INGPADBOUNDARY_M) |
 			   EGRSTATUSPAGESIZE_F,
 			   INGPADBOUNDARY_V(ingpad) |
 			   EGRSTATUSPAGESIZE_V(stat_len != 64));
+	csio_set_reg_field(hw, SGE_CONTROL2_A,
+			   INGPACKBOUNDARY_V(INGPACKBOUNDARY_M),
+			   INGPACKBOUNDARY_V(ingpack));
 
 	/* FL BUFFER SIZE#0 is Page size i,e already aligned to cache line */
 	csio_wr_reg32(hw, PAGE_SIZE, SGE_FL_BUFFER_SIZE0_A);
@@ -1337,14 +1409,16 @@ csio_wr_fixup_host_params(struct csio_hw *hw)
 	if (hw->flags & CSIO_HWF_USING_SOFT_PARAMS) {
 		csio_wr_reg32(hw,
 			(csio_rd_reg32(hw, SGE_FL_BUFFER_SIZE2_A) +
-			sge->csio_fl_align - 1) & ~(sge->csio_fl_align - 1),
+			fl_align - 1) & ~(fl_align - 1),
 			SGE_FL_BUFFER_SIZE2_A);
 		csio_wr_reg32(hw,
 			(csio_rd_reg32(hw, SGE_FL_BUFFER_SIZE3_A) +
-			sge->csio_fl_align - 1) & ~(sge->csio_fl_align - 1),
+			fl_align - 1) & ~(fl_align - 1),
 			SGE_FL_BUFFER_SIZE3_A);
 	}
 
+	sge->csio_fl_align = fl_align;
+
 	csio_wr_reg32(hw, HPZ0_V(PAGE_SHIFT - 12), ULP_RX_TDDP_PSZ_A);
 
 	/* default value of rx_dma_offset of the NIC driver */
diff --git a/drivers/scsi/cxlflash/ocxl_hw.c b/drivers/scsi/cxlflash/ocxl_hw.c
index 497a68389461..37b8dc60f5f6 100644
--- a/drivers/scsi/cxlflash/ocxl_hw.c
+++ b/drivers/scsi/cxlflash/ocxl_hw.c
@@ -88,10 +88,8 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name,
 				      const struct file_operations *fops,
 				      void *priv, int flags)
 {
-	struct qstr this;
-	struct path path;
 	struct file *file;
-	struct inode *inode = NULL;
+	struct inode *inode;
 	int rc;
 
 	if (fops->owner && !try_module_get(fops->owner)) {
@@ -116,29 +114,15 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name,
 		goto err3;
 	}
 
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0;
-	path.dentry = d_alloc_pseudo(ocxlflash_vfs_mount->mnt_sb, &this);
-	if (!path.dentry) {
-		dev_err(dev, "%s: d_alloc_pseudo failed\n", __func__);
-		rc = -ENOMEM;
-		goto err4;
-	}
-
-	path.mnt = mntget(ocxlflash_vfs_mount);
-	d_instantiate(path.dentry, inode);
-
-	file = alloc_file(&path, OPEN_FMODE(flags), fops);
+	file = alloc_file_pseudo(inode, ocxlflash_vfs_mount, name,
+				 flags & (O_ACCMODE | O_NONBLOCK), fops);
 	if (IS_ERR(file)) {
 		rc = PTR_ERR(file);
 		dev_err(dev, "%s: alloc_file failed rc=%d\n",
 			__func__, rc);
-		path_put(&path);
-		goto err3;
+		goto err4;
 	}
 
-	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
 	file->private_data = priv;
 out:
 	return file;
@@ -1157,7 +1141,7 @@ static int afu_release(struct inode *inode, struct file *file)
  *
  * Return: 0 on success, -errno on failure
  */
-static int ocxlflash_mmap_fault(struct vm_fault *vmf)
+static vm_fault_t ocxlflash_mmap_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct ocxlflash_context *ctx = vma->vm_file->private_data;
@@ -1180,8 +1164,7 @@ static int ocxlflash_mmap_fault(struct vm_fault *vmf)
 	mmio_area = ctx->psn_phys;
 	mmio_area += offset;
 
-	vm_insert_pfn(vma, vmf->address, mmio_area >> PAGE_SHIFT);
-	return VM_FAULT_NOPAGE;
+	return vmf_insert_pfn(vma, vmf->address, mmio_area >> PAGE_SHIFT);
 }
 
 static const struct vm_operations_struct ocxlflash_vmops = {
diff --git a/drivers/scsi/cxlflash/superpipe.c b/drivers/scsi/cxlflash/superpipe.c
index e489d89cbb45..acac6152f50b 100644
--- a/drivers/scsi/cxlflash/superpipe.c
+++ b/drivers/scsi/cxlflash/superpipe.c
@@ -339,7 +339,6 @@ static int read_cap16(struct scsi_device *sdev, struct llun_info *lli)
 	struct scsi_sense_hdr sshdr;
 	u8 *cmd_buf = NULL;
 	u8 *scsi_cmd = NULL;
-	u8 *sense_buf = NULL;
 	int rc = 0;
 	int result = 0;
 	int retry_cnt = 0;
@@ -348,8 +347,7 @@ static int read_cap16(struct scsi_device *sdev, struct llun_info *lli)
 retry:
 	cmd_buf = kzalloc(CMD_BUFSIZE, GFP_KERNEL);
 	scsi_cmd = kzalloc(MAX_COMMAND_SIZE, GFP_KERNEL);
-	sense_buf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL);
-	if (unlikely(!cmd_buf || !scsi_cmd || !sense_buf)) {
+	if (unlikely(!cmd_buf || !scsi_cmd)) {
 		rc = -ENOMEM;
 		goto out;
 	}
@@ -364,7 +362,7 @@ retry:
 	/* Drop the ioctl read semahpore across lengthy call */
 	up_read(&cfg->ioctl_rwsem);
 	result = scsi_execute(sdev, scsi_cmd, DMA_FROM_DEVICE, cmd_buf,
-			      CMD_BUFSIZE, sense_buf, &sshdr, to, CMD_RETRIES,
+			      CMD_BUFSIZE, NULL, &sshdr, to, CMD_RETRIES,
 			      0, 0, NULL);
 	down_read(&cfg->ioctl_rwsem);
 	rc = check_state(cfg);
@@ -395,7 +393,6 @@ retry:
 					if (retry_cnt++ < 1) {
 						kfree(cmd_buf);
 						kfree(scsi_cmd);
-						kfree(sense_buf);
 						goto retry;
 					}
 				}
@@ -426,7 +423,6 @@ retry:
 out:
 	kfree(cmd_buf);
 	kfree(scsi_cmd);
-	kfree(sense_buf);
 
 	dev_dbg(dev, "%s: maxlba=%lld blklen=%d rc=%d\n",
 		__func__, gli->max_lba, gli->blk_len, rc);
@@ -1108,7 +1104,7 @@ out:
  *
  * Return: 0 on success, VM_FAULT_SIGBUS on failure
  */
-static int cxlflash_mmap_fault(struct vm_fault *vmf)
+static vm_fault_t cxlflash_mmap_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct file *file = vma->vm_file;
@@ -1119,7 +1115,7 @@ static int cxlflash_mmap_fault(struct vm_fault *vmf)
 	struct ctx_info *ctxi = NULL;
 	struct page *err_page = NULL;
 	enum ctx_ctrl ctrl = CTX_CTRL_ERR_FALLBACK | CTX_CTRL_FILE;
-	int rc = 0;
+	vm_fault_t rc = 0;
 	int ctxid;
 
 	ctxid = cfg->ops->process_element(ctx);
@@ -1159,7 +1155,7 @@ static int cxlflash_mmap_fault(struct vm_fault *vmf)
 out:
 	if (likely(ctxi))
 		put_context(ctxi);
-	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%x\n", __func__, rc);
 	return rc;
 
 err:
diff --git a/drivers/scsi/cxlflash/vlun.c b/drivers/scsi/cxlflash/vlun.c
index 66e445a17d6c..2c904bf16b65 100644
--- a/drivers/scsi/cxlflash/vlun.c
+++ b/drivers/scsi/cxlflash/vlun.c
@@ -426,7 +426,6 @@ static int write_same16(struct scsi_device *sdev,
 {
 	u8 *cmd_buf = NULL;
 	u8 *scsi_cmd = NULL;
-	u8 *sense_buf = NULL;
 	int rc = 0;
 	int result = 0;
 	u64 offset = lba;
@@ -440,8 +439,7 @@ static int write_same16(struct scsi_device *sdev,
 
 	cmd_buf = kzalloc(CMD_BUFSIZE, GFP_KERNEL);
 	scsi_cmd = kzalloc(MAX_COMMAND_SIZE, GFP_KERNEL);
-	sense_buf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL);
-	if (unlikely(!cmd_buf || !scsi_cmd || !sense_buf)) {
+	if (unlikely(!cmd_buf || !scsi_cmd)) {
 		rc = -ENOMEM;
 		goto out;
 	}
@@ -457,7 +455,7 @@ static int write_same16(struct scsi_device *sdev,
 		/* Drop the ioctl read semahpore across lengthy call */
 		up_read(&cfg->ioctl_rwsem);
 		result = scsi_execute(sdev, scsi_cmd, DMA_TO_DEVICE, cmd_buf,
-				      CMD_BUFSIZE, sense_buf, NULL, to,
+				      CMD_BUFSIZE, NULL, NULL, to,
 				      CMD_RETRIES, 0, 0, NULL);
 		down_read(&cfg->ioctl_rwsem);
 		rc = check_state(cfg);
@@ -482,7 +480,6 @@ static int write_same16(struct scsi_device *sdev,
 out:
 	kfree(cmd_buf);
 	kfree(scsi_cmd);
-	kfree(sense_buf);
 	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
diff --git a/drivers/scsi/dc395x.c b/drivers/scsi/dc395x.c
index 60ef8df42b95..1ed2cd82129d 100644
--- a/drivers/scsi/dc395x.c
+++ b/drivers/scsi/dc395x.c
@@ -3473,9 +3473,8 @@ static void srb_done(struct AdapterCtlBlk *acb, struct DeviceCtlBlk *dcb,
 
 	/*if( srb->cmd->cmnd[0] == INQUIRY && */
 	/*  (host_byte(cmd->result) == DID_OK || status_byte(cmd->result) & CHECK_CONDITION) ) */
-		if ((cmd->result == (DID_OK << 16)
-		     || status_byte(cmd->result) &
-		     CHECK_CONDITION)) {
+		if ((cmd->result == (DID_OK << 16) ||
+		     status_byte(cmd->result) == CHECK_CONDITION)) {
 			if (!dcb->init_tcq_flag) {
 				add_dev(acb, dcb, ptr);
 				dcb->init_tcq_flag = 1;
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index ffec695e0bfb..54da3166da8d 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -2175,15 +2175,13 @@ static void fcoe_ctlr_disc_stop_locked(struct fc_lport *lport)
 {
 	struct fc_rport_priv *rdata;
 
-	rcu_read_lock();
+	mutex_lock(&lport->disc.disc_mutex);
 	list_for_each_entry_rcu(rdata, &lport->disc.rports, peers) {
 		if (kref_get_unless_zero(&rdata->kref)) {
 			fc_rport_logoff(rdata);
 			kref_put(&rdata->kref, fc_rport_destroy);
 		}
 	}
-	rcu_read_unlock();
-	mutex_lock(&lport->disc.disc_mutex);
 	lport->disc.disc_callback = NULL;
 	mutex_unlock(&lport->disc.disc_mutex);
 }
@@ -2712,7 +2710,7 @@ static unsigned long fcoe_ctlr_vn_age(struct fcoe_ctlr *fip)
 	unsigned long deadline;
 
 	next_time = jiffies + msecs_to_jiffies(FIP_VN_BEACON_INT * 10);
-	rcu_read_lock();
+	mutex_lock(&lport->disc.disc_mutex);
 	list_for_each_entry_rcu(rdata, &lport->disc.rports, peers) {
 		if (!kref_get_unless_zero(&rdata->kref))
 			continue;
@@ -2733,7 +2731,7 @@ static unsigned long fcoe_ctlr_vn_age(struct fcoe_ctlr *fip)
 			next_time = deadline;
 		kref_put(&rdata->kref, fc_rport_destroy);
 	}
-	rcu_read_unlock();
+	mutex_unlock(&lport->disc.disc_mutex);
 	return next_time;
 }
 
@@ -3080,8 +3078,6 @@ static void fcoe_ctlr_vn_disc(struct fcoe_ctlr *fip)
 	mutex_lock(&disc->disc_mutex);
 	callback = disc->pending ? disc->disc_callback : NULL;
 	disc->pending = 0;
-	mutex_unlock(&disc->disc_mutex);
-	rcu_read_lock();
 	list_for_each_entry_rcu(rdata, &disc->rports, peers) {
 		if (!kref_get_unless_zero(&rdata->kref))
 			continue;
@@ -3090,7 +3086,7 @@ static void fcoe_ctlr_vn_disc(struct fcoe_ctlr *fip)
 			fc_rport_login(rdata);
 		kref_put(&rdata->kref, fc_rport_destroy);
 	}
-	rcu_read_unlock();
+	mutex_unlock(&disc->disc_mutex);
 	if (callback)
 		callback(lport, DISC_EV_SUCCESS);
 }
diff --git a/drivers/scsi/gdth.c b/drivers/scsi/gdth.c
index 85604795d8ee..16709735b546 100644
--- a/drivers/scsi/gdth.c
+++ b/drivers/scsi/gdth.c
@@ -146,14 +146,14 @@ static irqreturn_t gdth_interrupt(int irq, void *dev_id);
 static irqreturn_t __gdth_interrupt(gdth_ha_str *ha,
                                     int gdth_from_wait, int* pIndex);
 static int gdth_sync_event(gdth_ha_str *ha, int service, u8 index,
-                                                               Scsi_Cmnd *scp);
+                                                               struct scsi_cmnd *scp);
 static int gdth_async_event(gdth_ha_str *ha);
 static void gdth_log_event(gdth_evt_data *dvr, char *buffer);
 
-static void gdth_putq(gdth_ha_str *ha, Scsi_Cmnd *scp, u8 priority);
+static void gdth_putq(gdth_ha_str *ha, struct scsi_cmnd *scp, u8 priority);
 static void gdth_next(gdth_ha_str *ha);
-static int gdth_fill_raw_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp, u8 b);
-static int gdth_special_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp);
+static int gdth_fill_raw_cmd(gdth_ha_str *ha, struct scsi_cmnd *scp, u8 b);
+static int gdth_special_cmd(gdth_ha_str *ha, struct scsi_cmnd *scp);
 static gdth_evt_str *gdth_store_event(gdth_ha_str *ha, u16 source,
                                       u16 idx, gdth_evt_data *evt);
 static int gdth_read_event(gdth_ha_str *ha, int handle, gdth_evt_str *estr);
@@ -161,10 +161,11 @@ static void gdth_readapp_event(gdth_ha_str *ha, u8 application,
                                gdth_evt_str *estr);
 static void gdth_clear_events(void);
 
-static void gdth_copy_internal_data(gdth_ha_str *ha, Scsi_Cmnd *scp,
+static void gdth_copy_internal_data(gdth_ha_str *ha, struct scsi_cmnd *scp,
                                     char *buffer, u16 count);
-static int gdth_internal_cache_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp);
-static int gdth_fill_cache_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp, u16 hdrive);
+static int gdth_internal_cache_cmd(gdth_ha_str *ha, struct scsi_cmnd *scp);
+static int gdth_fill_cache_cmd(gdth_ha_str *ha, struct scsi_cmnd *scp,
+			       u16 hdrive);
 
 static void gdth_enable_int(gdth_ha_str *ha);
 static int gdth_test_busy(gdth_ha_str *ha);
@@ -446,7 +447,7 @@ int __gdth_execute(struct scsi_device *sdev, gdth_cmd_str *gdtcmd, char *cmnd,
                    int timeout, u32 *info)
 {
     gdth_ha_str *ha = shost_priv(sdev->host);
-    Scsi_Cmnd *scp;
+    struct scsi_cmnd *scp;
     struct gdth_cmndinfo cmndinfo;
     DECLARE_COMPLETION_ONSTACK(wait);
     int rval;
@@ -1982,11 +1983,11 @@ static int gdth_analyse_hdrive(gdth_ha_str *ha, u16 hdrive)
 
 /* command queueing/sending functions */
 
-static void gdth_putq(gdth_ha_str *ha, Scsi_Cmnd *scp, u8 priority)
+static void gdth_putq(gdth_ha_str *ha, struct scsi_cmnd *scp, u8 priority)
 {
     struct gdth_cmndinfo *cmndinfo = gdth_cmnd_priv(scp);
-    register Scsi_Cmnd *pscp;
-    register Scsi_Cmnd *nscp;
+    register struct scsi_cmnd *pscp;
+    register struct scsi_cmnd *nscp;
     unsigned long flags;
 
     TRACE(("gdth_putq() priority %d\n",priority));
@@ -2000,11 +2001,11 @@ static void gdth_putq(gdth_ha_str *ha, Scsi_Cmnd *scp, u8 priority)
         scp->SCp.ptr = NULL;
     } else {                                    /* queue not empty */
         pscp = ha->req_first;
-        nscp = (Scsi_Cmnd *)pscp->SCp.ptr;
+        nscp = (struct scsi_cmnd *)pscp->SCp.ptr;
         /* priority: 0-highest,..,0xff-lowest */
         while (nscp && gdth_cmnd_priv(nscp)->priority <= priority) {
             pscp = nscp;
-            nscp = (Scsi_Cmnd *)pscp->SCp.ptr;
+            nscp = (struct scsi_cmnd *)pscp->SCp.ptr;
         }
         pscp->SCp.ptr = (char *)scp;
         scp->SCp.ptr  = (char *)nscp;
@@ -2013,7 +2014,7 @@ static void gdth_putq(gdth_ha_str *ha, Scsi_Cmnd *scp, u8 priority)
 
 #ifdef GDTH_STATISTICS
     flags = 0;
-    for (nscp=ha->req_first; nscp; nscp=(Scsi_Cmnd*)nscp->SCp.ptr)
+    for (nscp=ha->req_first; nscp; nscp=(struct scsi_cmnd*)nscp->SCp.ptr)
         ++flags;
     if (max_rq < flags) {
         max_rq = flags;
@@ -2024,8 +2025,8 @@ static void gdth_putq(gdth_ha_str *ha, Scsi_Cmnd *scp, u8 priority)
 
 static void gdth_next(gdth_ha_str *ha)
 {
-    register Scsi_Cmnd *pscp;
-    register Scsi_Cmnd *nscp;
+    register struct scsi_cmnd *pscp;
+    register struct scsi_cmnd *nscp;
     u8 b, t, l, firsttime;
     u8 this_cmd, next_cmd;
     unsigned long flags = 0;
@@ -2040,10 +2041,10 @@ static void gdth_next(gdth_ha_str *ha)
     next_cmd = gdth_polling ? FALSE:TRUE;
     cmd_index = 0;
 
-    for (nscp = pscp = ha->req_first; nscp; nscp = (Scsi_Cmnd *)nscp->SCp.ptr) {
+    for (nscp = pscp = ha->req_first; nscp; nscp = (struct scsi_cmnd *)nscp->SCp.ptr) {
         struct gdth_cmndinfo *nscp_cmndinfo = gdth_cmnd_priv(nscp);
-        if (nscp != pscp && nscp != (Scsi_Cmnd *)pscp->SCp.ptr)
-            pscp = (Scsi_Cmnd *)pscp->SCp.ptr;
+        if (nscp != pscp && nscp != (struct scsi_cmnd *)pscp->SCp.ptr)
+            pscp = (struct scsi_cmnd *)pscp->SCp.ptr;
         if (!nscp_cmndinfo->internal_command) {
             b = nscp->device->channel;
             t = nscp->device->id;
@@ -2250,7 +2251,7 @@ static void gdth_next(gdth_ha_str *ha)
         if (!this_cmd)
             break;
         if (nscp == ha->req_first)
-            ha->req_first = pscp = (Scsi_Cmnd *)nscp->SCp.ptr;
+            ha->req_first = pscp = (struct scsi_cmnd *)nscp->SCp.ptr;
         else
             pscp->SCp.ptr = nscp->SCp.ptr;
         if (!next_cmd)
@@ -2275,7 +2276,7 @@ static void gdth_next(gdth_ha_str *ha)
  * gdth_copy_internal_data() - copy to/from a buffer onto a scsi_cmnd's
  * buffers, kmap_atomic() as needed.
  */
-static void gdth_copy_internal_data(gdth_ha_str *ha, Scsi_Cmnd *scp,
+static void gdth_copy_internal_data(gdth_ha_str *ha, struct scsi_cmnd *scp,
                                     char *buffer, u16 count)
 {
     u16 cpcount,i, max_sg = scsi_sg_count(scp);
@@ -2317,7 +2318,7 @@ static void gdth_copy_internal_data(gdth_ha_str *ha, Scsi_Cmnd *scp,
     }
 }
 
-static int gdth_internal_cache_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp)
+static int gdth_internal_cache_cmd(gdth_ha_str *ha, struct scsi_cmnd *scp)
 {
     u8 t;
     gdth_inq_data inq;
@@ -2419,7 +2420,8 @@ static int gdth_internal_cache_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp)
     return 0;
 }
 
-static int gdth_fill_cache_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp, u16 hdrive)
+static int gdth_fill_cache_cmd(gdth_ha_str *ha, struct scsi_cmnd *scp,
+                               u16 hdrive)
 {
     register gdth_cmd_str *cmdp;
     struct gdth_cmndinfo *cmndinfo = gdth_cmnd_priv(scp);
@@ -2594,7 +2596,7 @@ static int gdth_fill_cache_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp, u16 hdrive)
     return cmd_index;
 }
 
-static int gdth_fill_raw_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp, u8 b)
+static int gdth_fill_raw_cmd(gdth_ha_str *ha, struct scsi_cmnd *scp, u8 b)
 {
     register gdth_cmd_str *cmdp;
     u16 i;
@@ -2767,7 +2769,7 @@ static int gdth_fill_raw_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp, u8 b)
     return cmd_index;
 }
 
-static int gdth_special_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp)
+static int gdth_special_cmd(gdth_ha_str *ha, struct scsi_cmnd *scp)
 {
     register gdth_cmd_str *cmdp;
     struct gdth_cmndinfo *cmndinfo = gdth_cmnd_priv(scp);
@@ -2958,7 +2960,7 @@ static irqreturn_t __gdth_interrupt(gdth_ha_str *ha,
     gdt6m_dpram_str __iomem *dp6m_ptr = NULL;
     gdt6_dpram_str __iomem *dp6_ptr;
     gdt2_dpram_str __iomem *dp2_ptr;
-    Scsi_Cmnd *scp;
+    struct scsi_cmnd *scp;
     int rval, i;
     u8 IStatus;
     u16 Service;
@@ -3217,7 +3219,7 @@ static irqreturn_t gdth_interrupt(int irq, void *dev_id)
 }
 
 static int gdth_sync_event(gdth_ha_str *ha, int service, u8 index,
-                                                              Scsi_Cmnd *scp)
+                                                              struct scsi_cmnd *scp)
 {
     gdth_msg_str *msg;
     gdth_cmd_str *cmdp;
@@ -3708,7 +3710,7 @@ static u8	gdth_timer_running;
 static void gdth_timeout(struct timer_list *unused)
 {
     u32 i;
-    Scsi_Cmnd *nscp;
+    struct scsi_cmnd *nscp;
     gdth_ha_str *ha;
     unsigned long flags;
 
@@ -3724,7 +3726,8 @@ static void gdth_timeout(struct timer_list *unused)
         if (ha->cmd_tab[i].cmnd != UNUSED_CMND)
             ++act_stats;
 
-    for (act_rq=0,nscp=ha->req_first; nscp; nscp=(Scsi_Cmnd*)nscp->SCp.ptr)
+    for (act_rq=0,
+         nscp=ha->req_first; nscp; nscp=(struct scsi_cmnd*)nscp->SCp.ptr)
         ++act_rq;
 
     TRACE2(("gdth_to(): ints %d, ios %d, act_stats %d, act_rq %d\n",
@@ -3909,12 +3912,12 @@ static enum blk_eh_timer_return gdth_timed_out(struct scsi_cmnd *scp)
 }
 
 
-static int gdth_eh_bus_reset(Scsi_Cmnd *scp)
+static int gdth_eh_bus_reset(struct scsi_cmnd *scp)
 {
     gdth_ha_str *ha = shost_priv(scp->device->host);
     int i;
     unsigned long flags;
-    Scsi_Cmnd *cmnd;
+    struct scsi_cmnd *cmnd;
     u8 b;
 
     TRACE2(("gdth_eh_bus_reset()\n"));
@@ -4465,7 +4468,7 @@ free_fail:
 static int gdth_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 {
     gdth_ha_str *ha; 
-    Scsi_Cmnd *scp;
+    struct scsi_cmnd *scp;
     unsigned long flags;
     char cmnd[MAX_COMMAND_SIZE];   
     void __user *argp = (void __user *)arg;
diff --git a/drivers/scsi/gdth.h b/drivers/scsi/gdth.h
index e6e5ccb1e0f3..ee6ffcf388e8 100644
--- a/drivers/scsi/gdth.h
+++ b/drivers/scsi/gdth.h
@@ -162,9 +162,9 @@
 #define BIGSECS         63                      /* mapping 255*63 */
 
 /* special command ptr. */
-#define UNUSED_CMND     ((Scsi_Cmnd *)-1)
-#define INTERNAL_CMND   ((Scsi_Cmnd *)-2)
-#define SCREEN_CMND     ((Scsi_Cmnd *)-3)
+#define UNUSED_CMND     ((struct scsi_cmnd *)-1)
+#define INTERNAL_CMND   ((struct scsi_cmnd *)-2)
+#define SCREEN_CMND     ((struct scsi_cmnd *)-3)
 #define SPECIAL_SCP(p)  (p==UNUSED_CMND || p==INTERNAL_CMND || p==SCREEN_CMND)
 
 /* controller services */
@@ -867,7 +867,7 @@ typedef struct {
     u16              service;                /* service/firmware ver./.. */
     u32             info;
     u32             info2;                  /* additional info */
-    Scsi_Cmnd           *req_first;             /* top of request queue */
+    struct scsi_cmnd           *req_first;             /* top of request queue */
     struct {
         u8          present;                /* Flag: host drive present? */
         u8          is_logdrv;              /* Flag: log. drive (master)? */
@@ -896,7 +896,7 @@ typedef struct {
         u32         id_list[MAXID];         /* IDs of the phys. devices */
     } raw[MAXBUS];                              /* SCSI channels */
     struct {
-        Scsi_Cmnd       *cmnd;                  /* pending request */
+        struct scsi_cmnd       *cmnd;                  /* pending request */
         u16          service;                /* service */
     } cmd_tab[GDTH_MAXCMDS];                    /* table of pend. requests */
     struct gdth_cmndinfo {                      /* per-command private info */
diff --git a/drivers/scsi/gdth_proc.c b/drivers/scsi/gdth_proc.c
index 20add49cdd32..3a9751a80225 100644
--- a/drivers/scsi/gdth_proc.c
+++ b/drivers/scsi/gdth_proc.c
@@ -626,7 +626,7 @@ static void gdth_wait_completion(gdth_ha_str *ha, int busnum, int id)
 {
     unsigned long flags;
     int i;
-    Scsi_Cmnd *scp;
+    struct scsi_cmnd *scp;
     struct gdth_cmndinfo *cmndinfo;
     u8 b, t;
 
diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index 7052a5d45f7f..6c7d2e201abe 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -16,6 +16,7 @@
 #include <linux/clk.h>
 #include <linux/dmapool.h>
 #include <linux/iopoll.h>
+#include <linux/lcm.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of_address.h>
@@ -199,17 +200,17 @@ struct hisi_sas_slot {
 	int	dlvry_queue_slot;
 	int	cmplt_queue;
 	int	cmplt_queue_slot;
-	int	idx;
 	int	abort;
 	int	ready;
-	void	*buf;
-	dma_addr_t buf_dma;
 	void	*cmd_hdr;
 	dma_addr_t cmd_hdr_dma;
-	struct work_struct abort_slot;
 	struct timer_list internal_abort_timer;
 	bool is_internal;
 	struct hisi_sas_tmf_task *tmf;
+	/* Do not reorder/change members after here */
+	void	*buf;
+	dma_addr_t buf_dma;
+	int	idx;
 };
 
 struct hisi_sas_hw {
@@ -277,6 +278,7 @@ struct hisi_hba {
 
 	int n_phy;
 	spinlock_t lock;
+	struct semaphore sem;
 
 	struct timer_list timer;
 	struct workqueue_struct *wq;
@@ -298,7 +300,6 @@ struct hisi_hba {
 
 	int	queue_count;
 
-	struct dma_pool *buffer_pool;
 	struct hisi_sas_device	devices[HISI_SAS_MAX_DEVICES];
 	struct hisi_sas_cmd_hdr	*cmd_hdr[HISI_SAS_MAX_QUEUES];
 	dma_addr_t cmd_hdr_dma[HISI_SAS_MAX_QUEUES];
@@ -319,6 +320,7 @@ struct hisi_hba {
 	const struct hisi_sas_hw *hw;	/* Low level hw interface */
 	unsigned long sata_dev_bitmap[BITS_TO_LONGS(HISI_SAS_MAX_DEVICES)];
 	struct work_struct rst_work;
+	u32 phy_state;
 };
 
 /* Generic HW DMA host memory structures */
@@ -479,4 +481,6 @@ extern bool hisi_sas_notify_phy_event(struct hisi_sas_phy *phy,
 				enum hisi_sas_phy_event event);
 extern void hisi_sas_release_tasks(struct hisi_hba *hisi_hba);
 extern u8 hisi_sas_get_prog_phy_linkrate_mask(enum sas_linkrate max);
+extern void hisi_sas_controller_reset_prepare(struct hisi_hba *hisi_hba);
+extern void hisi_sas_controller_reset_done(struct hisi_hba *hisi_hba);
 #endif
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 6f562974f8f6..a4e2e6aa9a6b 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -242,20 +242,16 @@ void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task,
 					     task->data_dir);
 	}
 
-	if (slot->buf)
-		dma_pool_free(hisi_hba->buffer_pool, slot->buf, slot->buf_dma);
 
 	spin_lock_irqsave(&dq->lock, flags);
 	list_del_init(&slot->entry);
 	spin_unlock_irqrestore(&dq->lock, flags);
-	slot->buf = NULL;
-	slot->task = NULL;
-	slot->port = NULL;
+
+	memset(slot, 0, offsetof(struct hisi_sas_slot, buf));
+
 	spin_lock_irqsave(&hisi_hba->lock, flags);
 	hisi_sas_slot_index_free(hisi_hba, slot->idx);
 	spin_unlock_irqrestore(&hisi_hba->lock, flags);
-
-	/* slot memory is fully zeroed when it is reused */
 }
 EXPORT_SYMBOL_GPL(hisi_sas_slot_task_free);
 
@@ -285,40 +281,6 @@ static void hisi_sas_task_prep_abort(struct hisi_hba *hisi_hba,
 			device_id, abort_flag, tag_to_abort);
 }
 
-/*
- * This function will issue an abort TMF regardless of whether the
- * task is in the sdev or not. Then it will do the task complete
- * cleanup and callbacks.
- */
-static void hisi_sas_slot_abort(struct work_struct *work)
-{
-	struct hisi_sas_slot *abort_slot =
-		container_of(work, struct hisi_sas_slot, abort_slot);
-	struct sas_task *task = abort_slot->task;
-	struct hisi_hba *hisi_hba = dev_to_hisi_hba(task->dev);
-	struct scsi_cmnd *cmnd = task->uldd_task;
-	struct hisi_sas_tmf_task tmf_task;
-	struct scsi_lun lun;
-	struct device *dev = hisi_hba->dev;
-	int tag = abort_slot->idx;
-
-	if (!(task->task_proto & SAS_PROTOCOL_SSP)) {
-		dev_err(dev, "cannot abort slot for non-ssp task\n");
-		goto out;
-	}
-
-	int_to_scsilun(cmnd->device->lun, &lun);
-	tmf_task.tmf = TMF_ABORT_TASK;
-	tmf_task.tag_of_task_to_be_managed = cpu_to_le16(tag);
-
-	hisi_sas_debug_issue_ssp_tmf(task->dev, lun.scsi_lun, &tmf_task);
-out:
-	/* Do cleanup for this task */
-	hisi_sas_slot_task_free(hisi_hba, task, abort_slot);
-	if (task->task_done)
-		task->task_done(task);
-}
-
 static int hisi_sas_task_prep(struct sas_task *task,
 			      struct hisi_sas_dq **dq_pointer,
 			      bool is_tmf, struct hisi_sas_tmf_task *tmf,
@@ -334,8 +296,8 @@ static int hisi_sas_task_prep(struct sas_task *task,
 	struct device *dev = hisi_hba->dev;
 	int dlvry_queue_slot, dlvry_queue, rc, slot_idx;
 	int n_elem = 0, n_elem_req = 0, n_elem_resp = 0;
-	unsigned long flags, flags_dq;
 	struct hisi_sas_dq *dq;
+	unsigned long flags;
 	int wr_q_index;
 
 	if (!sas_port) {
@@ -430,30 +392,22 @@ static int hisi_sas_task_prep(struct sas_task *task,
 		goto err_out_dma_unmap;
 
 	slot = &hisi_hba->slot_info[slot_idx];
-	memset(slot, 0, sizeof(struct hisi_sas_slot));
-
-	slot->buf = dma_pool_alloc(hisi_hba->buffer_pool,
-				   GFP_ATOMIC, &slot->buf_dma);
-	if (!slot->buf) {
-		rc = -ENOMEM;
-		goto err_out_tag;
-	}
 
-	spin_lock_irqsave(&dq->lock, flags_dq);
+	spin_lock_irqsave(&dq->lock, flags);
 	wr_q_index = hisi_hba->hw->get_free_slot(hisi_hba, dq);
 	if (wr_q_index < 0) {
-		spin_unlock_irqrestore(&dq->lock, flags_dq);
+		spin_unlock_irqrestore(&dq->lock, flags);
 		rc = -EAGAIN;
-		goto err_out_buf;
+		goto err_out_tag;
 	}
 
 	list_add_tail(&slot->delivery, &dq->list);
-	spin_unlock_irqrestore(&dq->lock, flags_dq);
+	list_add_tail(&slot->entry, &sas_dev->list);
+	spin_unlock_irqrestore(&dq->lock, flags);
 
 	dlvry_queue = dq->id;
 	dlvry_queue_slot = wr_q_index;
 
-	slot->idx = slot_idx;
 	slot->n_elem = n_elem;
 	slot->dlvry_queue = dlvry_queue;
 	slot->dlvry_queue_slot = dlvry_queue_slot;
@@ -464,7 +418,6 @@ static int hisi_sas_task_prep(struct sas_task *task,
 	slot->tmf = tmf;
 	slot->is_internal = is_tmf;
 	task->lldd_task = slot;
-	INIT_WORK(&slot->abort_slot, hisi_sas_slot_abort);
 
 	memset(slot->cmd_hdr, 0, sizeof(struct hisi_sas_cmd_hdr));
 	memset(hisi_sas_cmd_hdr_addr_mem(slot), 0, HISI_SAS_COMMAND_TABLE_SZ);
@@ -488,21 +441,15 @@ static int hisi_sas_task_prep(struct sas_task *task,
 		break;
 	}
 
-	spin_lock_irqsave(&dq->lock, flags);
-	list_add_tail(&slot->entry, &sas_dev->list);
-	spin_unlock_irqrestore(&dq->lock, flags);
 	spin_lock_irqsave(&task->task_state_lock, flags);
 	task->task_state_flags |= SAS_TASK_AT_INITIATOR;
 	spin_unlock_irqrestore(&task->task_state_lock, flags);
 
 	++(*pass);
-	slot->ready = 1;
+	WRITE_ONCE(slot->ready, 1);
 
 	return 0;
 
-err_out_buf:
-	dma_pool_free(hisi_hba->buffer_pool, slot->buf,
-		      slot->buf_dma);
 err_out_tag:
 	spin_lock_irqsave(&hisi_hba->lock, flags);
 	hisi_sas_slot_index_free(hisi_hba, slot_idx);
@@ -536,8 +483,13 @@ static int hisi_sas_task_exec(struct sas_task *task, gfp_t gfp_flags,
 	struct device *dev = hisi_hba->dev;
 	struct hisi_sas_dq *dq = NULL;
 
-	if (unlikely(test_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags)))
-		return -EINVAL;
+	if (unlikely(test_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags))) {
+		if (in_softirq())
+			return -EINVAL;
+
+		down(&hisi_hba->sem);
+		up(&hisi_hba->sem);
+	}
 
 	/* protect task_prep and start_delivery sequence */
 	rc = hisi_sas_task_prep(task, &dq, is_tmf, tmf, &pass);
@@ -819,6 +771,8 @@ static void hisi_sas_phy_init(struct hisi_hba *hisi_hba, int phy_no)
 
 	for (i = 0; i < HISI_PHYES_NUM; i++)
 		INIT_WORK(&phy->works[i], hisi_sas_phye_fns[i]);
+
+	spin_lock_init(&phy->lock);
 }
 
 static void hisi_sas_port_notify_formed(struct asd_sas_phy *sas_phy)
@@ -862,7 +816,6 @@ static void hisi_sas_do_release_task(struct hisi_hba *hisi_hba, struct sas_task
 	hisi_sas_slot_task_free(hisi_hba, task, slot);
 }
 
-/* hisi_hba.lock should be locked */
 static void hisi_sas_release_task(struct hisi_hba *hisi_hba,
 			struct domain_device *device)
 {
@@ -914,7 +867,9 @@ static void hisi_sas_dev_gone(struct domain_device *device)
 
 		hisi_sas_dereg_device(hisi_hba, device);
 
+		down(&hisi_hba->sem);
 		hisi_hba->hw->clear_itct(hisi_hba, sas_dev);
+		up(&hisi_hba->sem);
 		device->lldd_dev = NULL;
 	}
 
@@ -1351,21 +1306,12 @@ static void hisi_sas_terminate_stp_reject(struct hisi_hba *hisi_hba)
 	}
 }
 
-static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
+void hisi_sas_controller_reset_prepare(struct hisi_hba *hisi_hba)
 {
-	struct device *dev = hisi_hba->dev;
 	struct Scsi_Host *shost = hisi_hba->shost;
-	u32 old_state, state;
-	int rc;
-
-	if (!hisi_hba->hw->soft_reset)
-		return -1;
 
-	if (test_and_set_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
-		return -1;
-
-	dev_info(dev, "controller resetting...\n");
-	old_state = hisi_hba->hw->get_phys_state(hisi_hba);
+	down(&hisi_hba->sem);
+	hisi_hba->phy_state = hisi_hba->hw->get_phys_state(hisi_hba);
 
 	scsi_block_requests(shost);
 	hisi_hba->hw->wait_cmds_complete_timeout(hisi_hba, 100, 5000);
@@ -1374,34 +1320,61 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
 		del_timer_sync(&hisi_hba->timer);
 
 	set_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
-	rc = hisi_hba->hw->soft_reset(hisi_hba);
-	if (rc) {
-		dev_warn(dev, "controller reset failed (%d)\n", rc);
-		clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
-		scsi_unblock_requests(shost);
-		goto out;
-	}
+}
+EXPORT_SYMBOL_GPL(hisi_sas_controller_reset_prepare);
 
-	clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
+void hisi_sas_controller_reset_done(struct hisi_hba *hisi_hba)
+{
+	struct Scsi_Host *shost = hisi_hba->shost;
+	u32 state;
 
 	/* Init and wait for PHYs to come up and all libsas event finished. */
 	hisi_hba->hw->phys_init(hisi_hba);
 	msleep(1000);
 	hisi_sas_refresh_port_id(hisi_hba);
+	clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
+	up(&hisi_hba->sem);
 
 	if (hisi_hba->reject_stp_links_msk)
 		hisi_sas_terminate_stp_reject(hisi_hba);
 	hisi_sas_reset_init_all_devices(hisi_hba);
 	scsi_unblock_requests(shost);
+	clear_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
 
 	state = hisi_hba->hw->get_phys_state(hisi_hba);
-	hisi_sas_rescan_topology(hisi_hba, old_state, state);
-	dev_info(dev, "controller reset complete\n");
+	hisi_sas_rescan_topology(hisi_hba, hisi_hba->phy_state, state);
+}
+EXPORT_SYMBOL_GPL(hisi_sas_controller_reset_done);
 
-out:
-	clear_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
+static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
+{
+	struct device *dev = hisi_hba->dev;
+	struct Scsi_Host *shost = hisi_hba->shost;
+	int rc;
 
-	return rc;
+	if (!hisi_hba->hw->soft_reset)
+		return -1;
+
+	if (test_and_set_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
+		return -1;
+
+	dev_info(dev, "controller resetting...\n");
+	hisi_sas_controller_reset_prepare(hisi_hba);
+
+	rc = hisi_hba->hw->soft_reset(hisi_hba);
+	if (rc) {
+		dev_warn(dev, "controller reset failed (%d)\n", rc);
+		clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
+		up(&hisi_hba->sem);
+		scsi_unblock_requests(shost);
+		clear_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
+		return rc;
+	}
+
+	hisi_sas_controller_reset_done(hisi_hba);
+	dev_info(dev, "controller reset complete\n");
+
+	return 0;
 }
 
 static int hisi_sas_abort_task(struct sas_task *task)
@@ -1644,14 +1617,32 @@ out:
 static int hisi_sas_clear_nexus_ha(struct sas_ha_struct *sas_ha)
 {
 	struct hisi_hba *hisi_hba = sas_ha->lldd_ha;
+	struct device *dev = hisi_hba->dev;
 	HISI_SAS_DECLARE_RST_WORK_ON_STACK(r);
+	int rc, i;
 
 	queue_work(hisi_hba->wq, &r.work);
 	wait_for_completion(r.completion);
-	if (r.done)
-		return TMF_RESP_FUNC_COMPLETE;
+	if (!r.done)
+		return TMF_RESP_FUNC_FAILED;
+
+	for (i = 0; i < HISI_SAS_MAX_DEVICES; i++) {
+		struct hisi_sas_device *sas_dev = &hisi_hba->devices[i];
+		struct domain_device *device = sas_dev->sas_device;
 
-	return TMF_RESP_FUNC_FAILED;
+		if ((sas_dev->dev_type == SAS_PHY_UNUSED) || !device ||
+		    DEV_IS_EXPANDER(device->dev_type))
+			continue;
+
+		rc = hisi_sas_debug_I_T_nexus_reset(device);
+		if (rc != TMF_RESP_FUNC_COMPLETE)
+			dev_info(dev, "clear nexus ha: for device[%d] rc=%d\n",
+				 sas_dev->device_id, rc);
+	}
+
+	hisi_sas_release_tasks(hisi_hba);
+
+	return TMF_RESP_FUNC_COMPLETE;
 }
 
 static int hisi_sas_query_task(struct sas_task *task)
@@ -1723,21 +1714,13 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, int device_id,
 	spin_unlock_irqrestore(&hisi_hba->lock, flags);
 
 	slot = &hisi_hba->slot_info[slot_idx];
-	memset(slot, 0, sizeof(struct hisi_sas_slot));
-
-	slot->buf = dma_pool_alloc(hisi_hba->buffer_pool,
-			GFP_ATOMIC, &slot->buf_dma);
-	if (!slot->buf) {
-		rc = -ENOMEM;
-		goto err_out_tag;
-	}
 
 	spin_lock_irqsave(&dq->lock, flags_dq);
 	wr_q_index = hisi_hba->hw->get_free_slot(hisi_hba, dq);
 	if (wr_q_index < 0) {
 		spin_unlock_irqrestore(&dq->lock, flags_dq);
 		rc = -EAGAIN;
-		goto err_out_buf;
+		goto err_out_tag;
 	}
 	list_add_tail(&slot->delivery, &dq->list);
 	spin_unlock_irqrestore(&dq->lock, flags_dq);
@@ -1745,7 +1728,6 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, int device_id,
 	dlvry_queue = dq->id;
 	dlvry_queue_slot = wr_q_index;
 
-	slot->idx = slot_idx;
 	slot->n_elem = n_elem;
 	slot->dlvry_queue = dlvry_queue;
 	slot->dlvry_queue_slot = dlvry_queue_slot;
@@ -1767,7 +1749,7 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, int device_id,
 	task->task_state_flags |= SAS_TASK_AT_INITIATOR;
 	spin_unlock_irqrestore(&task->task_state_lock, flags);
 
-	slot->ready = 1;
+	WRITE_ONCE(slot->ready, 1);
 	/* send abort command to the chip */
 	spin_lock_irqsave(&dq->lock, flags);
 	list_add_tail(&slot->entry, &sas_dev->list);
@@ -1776,9 +1758,6 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, int device_id,
 
 	return 0;
 
-err_out_buf:
-	dma_pool_free(hisi_hba->buffer_pool, slot->buf,
-		      slot->buf_dma);
 err_out_tag:
 	spin_lock_irqsave(&hisi_hba->lock, flags);
 	hisi_sas_slot_index_free(hisi_hba, slot_idx);
@@ -1919,7 +1898,8 @@ void hisi_sas_phy_down(struct hisi_hba *hisi_hba, int phy_no, int rdy)
 	} else {
 		struct hisi_sas_port *port  = phy->port;
 
-		if (phy->in_reset) {
+		if (test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags) ||
+		    phy->in_reset) {
 			dev_info(dev, "ignore flutter phy%d down\n", phy_no);
 			return;
 		}
@@ -2014,8 +1994,11 @@ EXPORT_SYMBOL_GPL(hisi_sas_init_mem);
 int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 {
 	struct device *dev = hisi_hba->dev;
-	int i, s, max_command_entries = hisi_hba->hw->max_command_entries;
+	int i, j, s, max_command_entries = hisi_hba->hw->max_command_entries;
+	int max_command_entries_ru, sz_slot_buf_ru;
+	int blk_cnt, slots_per_blk;
 
+	sema_init(&hisi_hba->sem, 1);
 	spin_lock_init(&hisi_hba->lock);
 	for (i = 0; i < hisi_hba->n_phy; i++) {
 		hisi_sas_phy_init(hisi_hba, i);
@@ -2045,29 +2028,27 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 
 		/* Delivery queue */
 		s = sizeof(struct hisi_sas_cmd_hdr) * HISI_SAS_QUEUE_SLOTS;
-		hisi_hba->cmd_hdr[i] = dma_alloc_coherent(dev, s,
-					&hisi_hba->cmd_hdr_dma[i], GFP_KERNEL);
+		hisi_hba->cmd_hdr[i] = dmam_alloc_coherent(dev, s,
+						&hisi_hba->cmd_hdr_dma[i],
+						GFP_KERNEL);
 		if (!hisi_hba->cmd_hdr[i])
 			goto err_out;
 
 		/* Completion queue */
 		s = hisi_hba->hw->complete_hdr_size * HISI_SAS_QUEUE_SLOTS;
-		hisi_hba->complete_hdr[i] = dma_alloc_coherent(dev, s,
-				&hisi_hba->complete_hdr_dma[i], GFP_KERNEL);
+		hisi_hba->complete_hdr[i] = dmam_alloc_coherent(dev, s,
+						&hisi_hba->complete_hdr_dma[i],
+						GFP_KERNEL);
 		if (!hisi_hba->complete_hdr[i])
 			goto err_out;
 	}
 
-	s = sizeof(struct hisi_sas_slot_buf_table);
-	hisi_hba->buffer_pool = dma_pool_create("dma_buffer", dev, s, 16, 0);
-	if (!hisi_hba->buffer_pool)
-		goto err_out;
-
 	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_itct);
-	hisi_hba->itct = dma_zalloc_coherent(dev, s, &hisi_hba->itct_dma,
-					    GFP_KERNEL);
+	hisi_hba->itct = dmam_alloc_coherent(dev, s, &hisi_hba->itct_dma,
+					     GFP_KERNEL);
 	if (!hisi_hba->itct)
 		goto err_out;
+	memset(hisi_hba->itct, 0, s);
 
 	hisi_hba->slot_info = devm_kcalloc(dev, max_command_entries,
 					   sizeof(struct hisi_sas_slot),
@@ -2075,15 +2056,45 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 	if (!hisi_hba->slot_info)
 		goto err_out;
 
+	/* roundup to avoid overly large block size */
+	max_command_entries_ru = roundup(max_command_entries, 64);
+	sz_slot_buf_ru = roundup(sizeof(struct hisi_sas_slot_buf_table), 64);
+	s = lcm(max_command_entries_ru, sz_slot_buf_ru);
+	blk_cnt = (max_command_entries_ru * sz_slot_buf_ru) / s;
+	slots_per_blk = s / sz_slot_buf_ru;
+	for (i = 0; i < blk_cnt; i++) {
+		struct hisi_sas_slot_buf_table *buf;
+		dma_addr_t buf_dma;
+		int slot_index = i * slots_per_blk;
+
+		buf = dmam_alloc_coherent(dev, s, &buf_dma, GFP_KERNEL);
+		if (!buf)
+			goto err_out;
+		memset(buf, 0, s);
+
+		for (j = 0; j < slots_per_blk; j++, slot_index++) {
+			struct hisi_sas_slot *slot;
+
+			slot = &hisi_hba->slot_info[slot_index];
+			slot->buf = buf;
+			slot->buf_dma = buf_dma;
+			slot->idx = slot_index;
+
+			buf++;
+			buf_dma += sizeof(*buf);
+		}
+	}
+
 	s = max_command_entries * sizeof(struct hisi_sas_iost);
-	hisi_hba->iost = dma_alloc_coherent(dev, s, &hisi_hba->iost_dma,
-					    GFP_KERNEL);
+	hisi_hba->iost = dmam_alloc_coherent(dev, s, &hisi_hba->iost_dma,
+					     GFP_KERNEL);
 	if (!hisi_hba->iost)
 		goto err_out;
 
 	s = max_command_entries * sizeof(struct hisi_sas_breakpoint);
-	hisi_hba->breakpoint = dma_alloc_coherent(dev, s,
-				&hisi_hba->breakpoint_dma, GFP_KERNEL);
+	hisi_hba->breakpoint = dmam_alloc_coherent(dev, s,
+						   &hisi_hba->breakpoint_dma,
+						   GFP_KERNEL);
 	if (!hisi_hba->breakpoint)
 		goto err_out;
 
@@ -2094,14 +2105,16 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 		goto err_out;
 
 	s = sizeof(struct hisi_sas_initial_fis) * HISI_SAS_MAX_PHYS;
-	hisi_hba->initial_fis = dma_alloc_coherent(dev, s,
-				&hisi_hba->initial_fis_dma, GFP_KERNEL);
+	hisi_hba->initial_fis = dmam_alloc_coherent(dev, s,
+						    &hisi_hba->initial_fis_dma,
+						    GFP_KERNEL);
 	if (!hisi_hba->initial_fis)
 		goto err_out;
 
 	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_sata_breakpoint);
-	hisi_hba->sata_breakpoint = dma_alloc_coherent(dev, s,
-				&hisi_hba->sata_breakpoint_dma, GFP_KERNEL);
+	hisi_hba->sata_breakpoint = dmam_alloc_coherent(dev, s,
+					&hisi_hba->sata_breakpoint_dma,
+					GFP_KERNEL);
 	if (!hisi_hba->sata_breakpoint)
 		goto err_out;
 	hisi_sas_init_mem(hisi_hba);
@@ -2122,54 +2135,6 @@ EXPORT_SYMBOL_GPL(hisi_sas_alloc);
 
 void hisi_sas_free(struct hisi_hba *hisi_hba)
 {
-	struct device *dev = hisi_hba->dev;
-	int i, s, max_command_entries = hisi_hba->hw->max_command_entries;
-
-	for (i = 0; i < hisi_hba->queue_count; i++) {
-		s = sizeof(struct hisi_sas_cmd_hdr) * HISI_SAS_QUEUE_SLOTS;
-		if (hisi_hba->cmd_hdr[i])
-			dma_free_coherent(dev, s,
-					  hisi_hba->cmd_hdr[i],
-					  hisi_hba->cmd_hdr_dma[i]);
-
-		s = hisi_hba->hw->complete_hdr_size * HISI_SAS_QUEUE_SLOTS;
-		if (hisi_hba->complete_hdr[i])
-			dma_free_coherent(dev, s,
-					  hisi_hba->complete_hdr[i],
-					  hisi_hba->complete_hdr_dma[i]);
-	}
-
-	dma_pool_destroy(hisi_hba->buffer_pool);
-
-	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_itct);
-	if (hisi_hba->itct)
-		dma_free_coherent(dev, s,
-				  hisi_hba->itct, hisi_hba->itct_dma);
-
-	s = max_command_entries * sizeof(struct hisi_sas_iost);
-	if (hisi_hba->iost)
-		dma_free_coherent(dev, s,
-				  hisi_hba->iost, hisi_hba->iost_dma);
-
-	s = max_command_entries * sizeof(struct hisi_sas_breakpoint);
-	if (hisi_hba->breakpoint)
-		dma_free_coherent(dev, s,
-				  hisi_hba->breakpoint,
-				  hisi_hba->breakpoint_dma);
-
-
-	s = sizeof(struct hisi_sas_initial_fis) * HISI_SAS_MAX_PHYS;
-	if (hisi_hba->initial_fis)
-		dma_free_coherent(dev, s,
-				  hisi_hba->initial_fis,
-				  hisi_hba->initial_fis_dma);
-
-	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_sata_breakpoint);
-	if (hisi_hba->sata_breakpoint)
-		dma_free_coherent(dev, s,
-				  hisi_hba->sata_breakpoint,
-				  hisi_hba->sata_breakpoint_dma);
-
 	if (hisi_hba->wq)
 		destroy_workqueue(hisi_hba->wq);
 }
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
index 89ab18c1959c..8f60f0e04599 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
@@ -903,23 +903,28 @@ get_free_slot_v1_hw(struct hisi_hba *hisi_hba, struct hisi_sas_dq *dq)
 static void start_delivery_v1_hw(struct hisi_sas_dq *dq)
 {
 	struct hisi_hba *hisi_hba = dq->hisi_hba;
-	struct hisi_sas_slot *s, *s1;
+	struct hisi_sas_slot *s, *s1, *s2 = NULL;
 	struct list_head *dq_list;
 	int dlvry_queue = dq->id;
-	int wp, count = 0;
+	int wp;
 
 	dq_list = &dq->list;
 	list_for_each_entry_safe(s, s1, &dq->list, delivery) {
 		if (!s->ready)
 			break;
-		count++;
-		wp = (s->dlvry_queue_slot + 1) % HISI_SAS_QUEUE_SLOTS;
+		s2 = s;
 		list_del(&s->delivery);
 	}
 
-	if (!count)
+	if (!s2)
 		return;
 
+	/*
+	 * Ensure that memories for slots built on other CPUs is observed.
+	 */
+	smp_rmb();
+	wp = (s2->dlvry_queue_slot + 1) % HISI_SAS_QUEUE_SLOTS;
+
 	hisi_sas_write32(hisi_hba, DLVRY_Q_0_WR_PTR + (dlvry_queue * 0x14), wp);
 }
 
@@ -1296,11 +1301,8 @@ static int slot_complete_v1_hw(struct hisi_hba *hisi_hba,
 		!(cmplt_hdr_data & CMPLT_HDR_RSPNS_XFRD_MSK)) {
 
 		slot_err_v1_hw(hisi_hba, task, slot);
-		if (unlikely(slot->abort)) {
-			queue_work(hisi_hba->wq, &slot->abort_slot);
-			/* immediately return and do not complete */
+		if (unlikely(slot->abort))
 			return ts->stat;
-		}
 		goto out;
 	}
 
@@ -1469,7 +1471,8 @@ static irqreturn_t int_bcast_v1_hw(int irq, void *p)
 		goto end;
 	}
 
-	sha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
+	if (!test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
+		sha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
 
 end:
 	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT2,
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index 213c530e63f2..9c5c5a601332 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -1665,23 +1665,28 @@ get_free_slot_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_dq *dq)
 static void start_delivery_v2_hw(struct hisi_sas_dq *dq)
 {
 	struct hisi_hba *hisi_hba = dq->hisi_hba;
-	struct hisi_sas_slot *s, *s1;
+	struct hisi_sas_slot *s, *s1, *s2 = NULL;
 	struct list_head *dq_list;
 	int dlvry_queue = dq->id;
-	int wp, count = 0;
+	int wp;
 
 	dq_list = &dq->list;
 	list_for_each_entry_safe(s, s1, &dq->list, delivery) {
 		if (!s->ready)
 			break;
-		count++;
-		wp = (s->dlvry_queue_slot + 1) % HISI_SAS_QUEUE_SLOTS;
+		s2 = s;
 		list_del(&s->delivery);
 	}
 
-	if (!count)
+	if (!s2)
 		return;
 
+	/*
+	 * Ensure that memories for slots built on other CPUs is observed.
+	 */
+	smp_rmb();
+	wp = (s2->dlvry_queue_slot + 1) % HISI_SAS_QUEUE_SLOTS;
+
 	hisi_sas_write32(hisi_hba, DLVRY_Q_0_WR_PTR + (dlvry_queue * 0x14), wp);
 }
 
@@ -2840,7 +2845,8 @@ static void phy_bcast_v2_hw(int phy_no, struct hisi_hba *hisi_hba)
 
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 1);
 	bcast_status = hisi_sas_phy_read32(hisi_hba, phy_no, RX_PRIMS_STATUS);
-	if (bcast_status & RX_BCAST_CHG_MSK)
+	if ((bcast_status & RX_BCAST_CHG_MSK) &&
+	    !test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
 		sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
 	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0,
 			     CHL_INT0_SL_RX_BCST_ACK_MSK);
@@ -3234,8 +3240,7 @@ static irqreturn_t sata_int_v2_hw(int irq_no, void *p)
 	if (fis->status & ATA_ERR) {
 		dev_warn(dev, "sata int: phy%d FIS status: 0x%x\n", phy_no,
 				fis->status);
-		disable_phy_v2_hw(hisi_hba, phy_no);
-		enable_phy_v2_hw(hisi_hba, phy_no);
+		hisi_sas_notify_phy_event(phy, HISI_PHYE_LINK_RESET);
 		res = IRQ_NONE;
 		goto end;
 	}
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 9f1e2d03f914..08b503e274b8 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -51,7 +51,6 @@
 #define CFG_ABT_SET_IPTT_DONE	0xd8
 #define CFG_ABT_SET_IPTT_DONE_OFF	0
 #define HGC_IOMB_PROC1_STATUS	0x104
-#define CFG_1US_TIMER_TRSH		0xcc
 #define CHNL_INT_STATUS			0x148
 #define HGC_AXI_FIFO_ERR_INFO  0x154
 #define AXI_ERR_INFO_OFF               0
@@ -121,6 +120,8 @@
 #define PHY_CFG_ENA_MSK			(0x1 << PHY_CFG_ENA_OFF)
 #define PHY_CFG_DC_OPT_OFF		2
 #define PHY_CFG_DC_OPT_MSK		(0x1 << PHY_CFG_DC_OPT_OFF)
+#define PHY_CFG_PHY_RST_OFF		3
+#define PHY_CFG_PHY_RST_MSK		(0x1 << PHY_CFG_PHY_RST_OFF)
 #define PROG_PHY_LINK_RATE		(PORT_BASE + 0x8)
 #define PHY_CTRL			(PORT_BASE + 0x14)
 #define PHY_CTRL_RESET_OFF		0
@@ -131,6 +132,9 @@
 #define SL_CONTROL_NOTIFY_EN_MSK	(0x1 << SL_CONTROL_NOTIFY_EN_OFF)
 #define SL_CTA_OFF		17
 #define SL_CTA_MSK		(0x1 << SL_CTA_OFF)
+#define RX_PRIMS_STATUS			(PORT_BASE + 0x98)
+#define RX_BCAST_CHG_OFF		1
+#define RX_BCAST_CHG_MSK		(0x1 << RX_BCAST_CHG_OFF)
 #define TX_ID_DWORD0			(PORT_BASE + 0x9c)
 #define TX_ID_DWORD1			(PORT_BASE + 0xa0)
 #define TX_ID_DWORD2			(PORT_BASE + 0xa4)
@@ -206,6 +210,8 @@
 
 #define AXI_MASTER_CFG_BASE		(0x5000)
 #define AM_CTRL_GLOBAL			(0x0)
+#define AM_CTRL_SHUTDOWN_REQ_OFF	0
+#define AM_CTRL_SHUTDOWN_REQ_MSK	(0x1 << AM_CTRL_SHUTDOWN_REQ_OFF)
 #define AM_CURR_TRANS_RETURN	(0x150)
 
 #define AM_CFG_MAX_TRANS		(0x5010)
@@ -425,7 +431,6 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba)
 			 (u32)((1ULL << hisi_hba->queue_count) - 1));
 	hisi_sas_write32(hisi_hba, CFG_MAX_TAG, 0xfff0400);
 	hisi_sas_write32(hisi_hba, HGC_SAS_TXFAIL_RETRY_CTRL, 0x108);
-	hisi_sas_write32(hisi_hba, CFG_1US_TIMER_TRSH, 0xd);
 	hisi_sas_write32(hisi_hba, INT_COAL_EN, 0x1);
 	hisi_sas_write32(hisi_hba, OQ_INT_COAL_TIME, 0x1);
 	hisi_sas_write32(hisi_hba, OQ_INT_COAL_CNT, 0x1);
@@ -486,6 +491,7 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba)
 		hisi_sas_phy_write32(hisi_hba, i, SL_RX_BCAST_CHK_MSK, 0x0);
 		hisi_sas_phy_write32(hisi_hba, i, PHYCTRL_OOB_RESTART_MSK, 0x1);
 		hisi_sas_phy_write32(hisi_hba, i, STP_LINK_TIMER, 0x7f7a120);
+		hisi_sas_phy_write32(hisi_hba, i, CON_CFG_DRIVER, 0x2a0a01);
 
 		/* used for 12G negotiate */
 		hisi_sas_phy_write32(hisi_hba, i, COARSETUNE_TIME, 0x1e);
@@ -758,15 +764,25 @@ static void enable_phy_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
 	u32 cfg = hisi_sas_phy_read32(hisi_hba, phy_no, PHY_CFG);
 
 	cfg |= PHY_CFG_ENA_MSK;
+	cfg &= ~PHY_CFG_PHY_RST_MSK;
 	hisi_sas_phy_write32(hisi_hba, phy_no, PHY_CFG, cfg);
 }
 
 static void disable_phy_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
 {
 	u32 cfg = hisi_sas_phy_read32(hisi_hba, phy_no, PHY_CFG);
+	u32 state;
 
 	cfg &= ~PHY_CFG_ENA_MSK;
 	hisi_sas_phy_write32(hisi_hba, phy_no, PHY_CFG, cfg);
+
+	mdelay(50);
+
+	state = hisi_sas_read32(hisi_hba, PHY_STATE);
+	if (state & BIT(phy_no)) {
+		cfg |= PHY_CFG_PHY_RST_MSK;
+		hisi_sas_phy_write32(hisi_hba, phy_no, PHY_CFG, cfg);
+	}
 }
 
 static void start_phy_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
@@ -866,23 +882,28 @@ get_free_slot_v3_hw(struct hisi_hba *hisi_hba, struct hisi_sas_dq *dq)
 static void start_delivery_v3_hw(struct hisi_sas_dq *dq)
 {
 	struct hisi_hba *hisi_hba = dq->hisi_hba;
-	struct hisi_sas_slot *s, *s1;
+	struct hisi_sas_slot *s, *s1, *s2 = NULL;
 	struct list_head *dq_list;
 	int dlvry_queue = dq->id;
-	int wp, count = 0;
+	int wp;
 
 	dq_list = &dq->list;
 	list_for_each_entry_safe(s, s1, &dq->list, delivery) {
 		if (!s->ready)
 			break;
-		count++;
-		wp = (s->dlvry_queue_slot + 1) % HISI_SAS_QUEUE_SLOTS;
+		s2 = s;
 		list_del(&s->delivery);
 	}
 
-	if (!count)
+	if (!s2)
 		return;
 
+	/*
+	 * Ensure that memories for slots built on other CPUs is observed.
+	 */
+	smp_rmb();
+	wp = (s2->dlvry_queue_slot + 1) % HISI_SAS_QUEUE_SLOTS;
+
 	hisi_sas_write32(hisi_hba, DLVRY_Q_0_WR_PTR + (dlvry_queue * 0x14), wp);
 }
 
@@ -1170,6 +1191,16 @@ static irqreturn_t phy_up_v3_hw(int phy_no, struct hisi_hba *hisi_hba)
 		dev_info(dev, "phyup: phy%d link_rate=%d(sata)\n", phy_no, link_rate);
 		initial_fis = &hisi_hba->initial_fis[phy_no];
 		fis = &initial_fis->fis;
+
+		/* check ERR bit of Status Register */
+		if (fis->status & ATA_ERR) {
+			dev_warn(dev, "sata int: phy%d FIS status: 0x%x\n",
+				 phy_no, fis->status);
+			hisi_sas_notify_phy_event(phy, HISI_PHYE_LINK_RESET);
+			res = IRQ_NONE;
+			goto end;
+		}
+
 		sas_phy->oob_mode = SATA_OOB_MODE;
 		attached_sas_addr[0] = 0x50;
 		attached_sas_addr[7] = phy_no;
@@ -1256,9 +1287,13 @@ static irqreturn_t phy_bcast_v3_hw(int phy_no, struct hisi_hba *hisi_hba)
 	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
 	struct asd_sas_phy *sas_phy = &phy->sas_phy;
 	struct sas_ha_struct *sas_ha = &hisi_hba->sha;
+	u32 bcast_status;
 
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 1);
-	sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
+	bcast_status = hisi_sas_phy_read32(hisi_hba, phy_no, RX_PRIMS_STATUS);
+	if ((bcast_status & RX_BCAST_CHG_MSK) &&
+	    !test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
+		sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
 	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0,
 			     CHL_INT0_SL_RX_BCST_ACK_MSK);
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 0);
@@ -1327,11 +1362,77 @@ static const struct hisi_sas_hw_error port_axi_error[] = {
 	},
 };
 
-static irqreturn_t int_chnl_int_v3_hw(int irq_no, void *p)
+static void handle_chl_int1_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
 {
-	struct hisi_hba *hisi_hba = p;
+	u32 irq_value = hisi_sas_phy_read32(hisi_hba, phy_no, CHL_INT1);
+	u32 irq_msk = hisi_sas_phy_read32(hisi_hba, phy_no, CHL_INT1_MSK);
 	struct device *dev = hisi_hba->dev;
+	int i;
+
+	irq_value &= ~irq_msk;
+	if (!irq_value)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(port_axi_error); i++) {
+		const struct hisi_sas_hw_error *error = &port_axi_error[i];
+
+		if (!(irq_value & error->irq_msk))
+			continue;
+
+		dev_err(dev, "%s error (phy%d 0x%x) found!\n",
+			error->msg, phy_no, irq_value);
+		queue_work(hisi_hba->wq, &hisi_hba->rst_work);
+	}
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT1, irq_value);
+}
+
+static void handle_chl_int2_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
+{
+	u32 irq_msk = hisi_sas_phy_read32(hisi_hba, phy_no, CHL_INT2_MSK);
+	u32 irq_value = hisi_sas_phy_read32(hisi_hba, phy_no, CHL_INT2);
+	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
 	struct pci_dev *pci_dev = hisi_hba->pci_dev;
+	struct device *dev = hisi_hba->dev;
+
+	irq_value &= ~irq_msk;
+	if (!irq_value)
+		return;
+
+	if (irq_value & BIT(CHL_INT2_SL_IDAF_TOUT_CONF_OFF)) {
+		dev_warn(dev, "phy%d identify timeout\n", phy_no);
+		hisi_sas_notify_phy_event(phy, HISI_PHYE_LINK_RESET);
+	}
+
+	if (irq_value & BIT(CHL_INT2_STP_LINK_TIMEOUT_OFF)) {
+		u32 reg_value = hisi_sas_phy_read32(hisi_hba, phy_no,
+				STP_LINK_TIMEOUT_STATE);
+
+		dev_warn(dev, "phy%d stp link timeout (0x%x)\n",
+			 phy_no, reg_value);
+		if (reg_value & BIT(4))
+			hisi_sas_notify_phy_event(phy, HISI_PHYE_LINK_RESET);
+	}
+
+	if ((irq_value & BIT(CHL_INT2_RX_INVLD_DW_OFF)) &&
+	    (pci_dev->revision == 0x20)) {
+		u32 reg_value;
+		int rc;
+
+		rc = hisi_sas_read32_poll_timeout_atomic(
+				HILINK_ERR_DFX, reg_value,
+				!((reg_value >> 8) & BIT(phy_no)),
+				1000, 10000);
+		if (rc)
+			hisi_sas_notify_phy_event(phy, HISI_PHYE_LINK_RESET);
+	}
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT2, irq_value);
+}
+
+static irqreturn_t int_chnl_int_v3_hw(int irq_no, void *p)
+{
+	struct hisi_hba *hisi_hba = p;
 	u32 irq_msk;
 	int phy_no = 0;
 
@@ -1341,84 +1442,12 @@ static irqreturn_t int_chnl_int_v3_hw(int irq_no, void *p)
 	while (irq_msk) {
 		u32 irq_value0 = hisi_sas_phy_read32(hisi_hba, phy_no,
 						     CHL_INT0);
-		u32 irq_value1 = hisi_sas_phy_read32(hisi_hba, phy_no,
-						     CHL_INT1);
-		u32 irq_value2 = hisi_sas_phy_read32(hisi_hba, phy_no,
-						     CHL_INT2);
-		u32 irq_msk1 = hisi_sas_phy_read32(hisi_hba, phy_no,
-							CHL_INT1_MSK);
-		u32 irq_msk2 = hisi_sas_phy_read32(hisi_hba, phy_no,
-							CHL_INT2_MSK);
-
-		irq_value1 &= ~irq_msk1;
-		irq_value2 &= ~irq_msk2;
-
-		if ((irq_msk & (4 << (phy_no * 4))) &&
-						irq_value1) {
-			int i;
-
-			for (i = 0; i < ARRAY_SIZE(port_axi_error); i++) {
-				const struct hisi_sas_hw_error *error =
-						&port_axi_error[i];
-
-				if (!(irq_value1 & error->irq_msk))
-					continue;
-
-				dev_err(dev, "%s error (phy%d 0x%x) found!\n",
-					error->msg, phy_no, irq_value1);
-				queue_work(hisi_hba->wq, &hisi_hba->rst_work);
-			}
-
-			hisi_sas_phy_write32(hisi_hba, phy_no,
-					     CHL_INT1, irq_value1);
-		}
 
-		if (irq_msk & (8 << (phy_no * 4)) && irq_value2) {
-			struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
+		if (irq_msk & (4 << (phy_no * 4)))
+			handle_chl_int1_v3_hw(hisi_hba, phy_no);
 
-			if (irq_value2 & BIT(CHL_INT2_SL_IDAF_TOUT_CONF_OFF)) {
-				dev_warn(dev, "phy%d identify timeout\n",
-							phy_no);
-				hisi_sas_notify_phy_event(phy,
-					HISI_PHYE_LINK_RESET);
-
-			}
-
-			if (irq_value2 & BIT(CHL_INT2_STP_LINK_TIMEOUT_OFF)) {
-				u32 reg_value = hisi_sas_phy_read32(hisi_hba,
-						phy_no, STP_LINK_TIMEOUT_STATE);
-
-				dev_warn(dev, "phy%d stp link timeout (0x%x)\n",
-							phy_no, reg_value);
-				if (reg_value & BIT(4))
-					hisi_sas_notify_phy_event(phy,
-						HISI_PHYE_LINK_RESET);
-			}
-
-			hisi_sas_phy_write32(hisi_hba, phy_no,
-					     CHL_INT2, irq_value2);
-
-			if ((irq_value2 & BIT(CHL_INT2_RX_INVLD_DW_OFF)) &&
-			    (pci_dev->revision == 0x20)) {
-				u32 reg_value;
-				int rc;
-
-				rc = hisi_sas_read32_poll_timeout_atomic(
-					HILINK_ERR_DFX, reg_value,
-					!((reg_value >> 8) & BIT(phy_no)),
-					1000, 10000);
-				if (rc) {
-					disable_phy_v3_hw(hisi_hba, phy_no);
-					hisi_sas_phy_write32(hisi_hba, phy_no,
-						CHL_INT2,
-						BIT(CHL_INT2_RX_INVLD_DW_OFF));
-					hisi_sas_phy_read32(hisi_hba, phy_no,
-						ERR_CNT_INVLD_DW);
-					mdelay(1);
-					enable_phy_v3_hw(hisi_hba, phy_no);
-				}
-			}
-		}
+		if (irq_msk & (8 << (phy_no * 4)))
+			handle_chl_int2_v3_hw(hisi_hba, phy_no);
 
 		if (irq_msk & (2 << (phy_no * 4)) && irq_value0) {
 			hisi_sas_phy_write32(hisi_hba, phy_no,
@@ -1964,11 +1993,11 @@ static void phy_get_events_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
 
 }
 
-static int soft_reset_v3_hw(struct hisi_hba *hisi_hba)
+static int disable_host_v3_hw(struct hisi_hba *hisi_hba)
 {
 	struct device *dev = hisi_hba->dev;
+	u32 status, reg_val;
 	int rc;
-	u32 status;
 
 	interrupt_disable_v3_hw(hisi_hba);
 	hisi_sas_write32(hisi_hba, DLVRY_QUEUE_ENABLE, 0x0);
@@ -1978,14 +2007,32 @@ static int soft_reset_v3_hw(struct hisi_hba *hisi_hba)
 
 	mdelay(10);
 
-	hisi_sas_write32(hisi_hba, AXI_MASTER_CFG_BASE + AM_CTRL_GLOBAL, 0x1);
+	reg_val = hisi_sas_read32(hisi_hba, AXI_MASTER_CFG_BASE +
+				  AM_CTRL_GLOBAL);
+	reg_val |= AM_CTRL_SHUTDOWN_REQ_MSK;
+	hisi_sas_write32(hisi_hba, AXI_MASTER_CFG_BASE +
+			 AM_CTRL_GLOBAL, reg_val);
 
 	/* wait until bus idle */
 	rc = hisi_sas_read32_poll_timeout(AXI_MASTER_CFG_BASE +
 					  AM_CURR_TRANS_RETURN, status,
 					  status == 0x3, 10, 100);
 	if (rc) {
-		dev_err(dev, "axi bus is not idle, rc = %d\n", rc);
+		dev_err(dev, "axi bus is not idle, rc=%d\n", rc);
+		return rc;
+	}
+
+	return 0;
+}
+
+static int soft_reset_v3_hw(struct hisi_hba *hisi_hba)
+{
+	struct device *dev = hisi_hba->dev;
+	int rc;
+
+	rc = disable_host_v3_hw(hisi_hba);
+	if (rc) {
+		dev_err(dev, "soft reset: disable host failed rc=%d\n", rc);
 		return rc;
 	}
 
@@ -2433,6 +2480,41 @@ static pci_ers_result_t hisi_sas_slot_reset_v3_hw(struct pci_dev *pdev)
 	return PCI_ERS_RESULT_DISCONNECT;
 }
 
+static void hisi_sas_reset_prepare_v3_hw(struct pci_dev *pdev)
+{
+	struct sas_ha_struct *sha = pci_get_drvdata(pdev);
+	struct hisi_hba *hisi_hba = sha->lldd_ha;
+	struct device *dev = hisi_hba->dev;
+	int rc;
+
+	dev_info(dev, "FLR prepare\n");
+	set_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
+	hisi_sas_controller_reset_prepare(hisi_hba);
+
+	rc = disable_host_v3_hw(hisi_hba);
+	if (rc)
+		dev_err(dev, "FLR: disable host failed rc=%d\n", rc);
+}
+
+static void hisi_sas_reset_done_v3_hw(struct pci_dev *pdev)
+{
+	struct sas_ha_struct *sha = pci_get_drvdata(pdev);
+	struct hisi_hba *hisi_hba = sha->lldd_ha;
+	struct device *dev = hisi_hba->dev;
+	int rc;
+
+	hisi_sas_init_mem(hisi_hba);
+
+	rc = hw_init_v3_hw(hisi_hba);
+	if (rc) {
+		dev_err(dev, "FLR: hw init failed rc=%d\n", rc);
+		return;
+	}
+
+	hisi_sas_controller_reset_done(hisi_hba);
+	dev_info(dev, "FLR done\n");
+}
+
 enum {
 	/* instances of the controller */
 	hip08,
@@ -2444,38 +2526,24 @@ static int hisi_sas_v3_suspend(struct pci_dev *pdev, pm_message_t state)
 	struct hisi_hba *hisi_hba = sha->lldd_ha;
 	struct device *dev = hisi_hba->dev;
 	struct Scsi_Host *shost = hisi_hba->shost;
-	u32 device_state, status;
+	u32 device_state;
 	int rc;
-	u32 reg_val;
 
 	if (!pdev->pm_cap) {
 		dev_err(dev, "PCI PM not supported\n");
 		return -ENODEV;
 	}
 
-	set_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
+	if (test_and_set_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
+		return -1;
+
 	scsi_block_requests(shost);
 	set_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
 	flush_workqueue(hisi_hba->wq);
-	/* disable DQ/PHY/bus */
-	interrupt_disable_v3_hw(hisi_hba);
-	hisi_sas_write32(hisi_hba, DLVRY_QUEUE_ENABLE, 0x0);
-	hisi_sas_kill_tasklets(hisi_hba);
-
-	hisi_sas_stop_phys(hisi_hba);
 
-	reg_val = hisi_sas_read32(hisi_hba, AXI_MASTER_CFG_BASE +
-		AM_CTRL_GLOBAL);
-	reg_val |= 0x1;
-	hisi_sas_write32(hisi_hba, AXI_MASTER_CFG_BASE +
-		AM_CTRL_GLOBAL, reg_val);
-
-	/* wait until bus idle */
-	rc = hisi_sas_read32_poll_timeout(AXI_MASTER_CFG_BASE +
-					  AM_CURR_TRANS_RETURN, status,
-					  status == 0x3, 10, 100);
+	rc = disable_host_v3_hw(hisi_hba);
 	if (rc) {
-		dev_err(dev, "axi bus is not idle, rc = %d\n", rc);
+		dev_err(dev, "PM suspend: disable host failed rc=%d\n", rc);
 		clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
 		clear_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
 		scsi_unblock_requests(shost);
@@ -2538,6 +2606,8 @@ static const struct pci_error_handlers hisi_sas_err_handler = {
 	.error_detected	= hisi_sas_error_detected_v3_hw,
 	.mmio_enabled	= hisi_sas_mmio_enabled_v3_hw,
 	.slot_reset	= hisi_sas_slot_reset_v3_hw,
+	.reset_prepare	= hisi_sas_reset_prepare_v3_hw,
+	.reset_done	= hisi_sas_reset_done_v3_hw,
 };
 
 static struct pci_driver sas_v3_pci_driver = {
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 3771e59a9fae..f02dcc875a09 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -563,6 +563,38 @@ struct Scsi_Host *scsi_host_get(struct Scsi_Host *shost)
 }
 EXPORT_SYMBOL(scsi_host_get);
 
+struct scsi_host_mq_in_flight {
+	int cnt;
+};
+
+static void scsi_host_check_in_flight(struct request *rq, void *data,
+		bool reserved)
+{
+	struct scsi_host_mq_in_flight *in_flight = data;
+
+	if (blk_mq_request_started(rq))
+		in_flight->cnt++;
+}
+
+/**
+ * scsi_host_busy - Return the host busy counter
+ * @shost:	Pointer to Scsi_Host to inc.
+ **/
+int scsi_host_busy(struct Scsi_Host *shost)
+{
+	struct scsi_host_mq_in_flight in_flight = {
+		.cnt = 0,
+	};
+
+	if (!shost->use_blk_mq)
+		return atomic_read(&shost->host_busy);
+
+	blk_mq_tagset_busy_iter(&shost->tag_set, scsi_host_check_in_flight,
+			&in_flight);
+	return in_flight.cnt;
+}
+EXPORT_SYMBOL(scsi_host_busy);
+
 /**
  * scsi_host_put - dec a Scsi_Host ref count
  * @shost:	Pointer to Scsi_Host to dec.
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index daefe8172b04..b64ca977825d 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -1322,7 +1322,7 @@ static void ibmvfc_map_sg_list(struct scsi_cmnd *scmd, int nseg,
 
 /**
  * ibmvfc_map_sg_data - Maps dma for a scatterlist and initializes decriptor fields
- * @scmd:		Scsi_Cmnd with the scatterlist
+ * @scmd:		struct scsi_cmnd with the scatterlist
  * @evt:		ibmvfc event struct
  * @vfc_cmd:	vfc_cmd that contains the memory descriptor
  * @dev:		device for which to map dma memory
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index 17df76f0be3c..9df8a1a2299c 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -93,7 +93,7 @@ static int max_requests = IBMVSCSI_MAX_REQUESTS_DEFAULT;
 static int max_events = IBMVSCSI_MAX_REQUESTS_DEFAULT + 2;
 static int fast_fail = 1;
 static int client_reserve = 1;
-static char partition_name[97] = "UNKNOWN";
+static char partition_name[96] = "UNKNOWN";
 static unsigned int partition_number = -1;
 static LIST_HEAD(ibmvscsi_head);
 
@@ -262,7 +262,7 @@ static void gather_partition_info(void)
 
 	ppartition_name = of_get_property(of_root, "ibm,partition-name", NULL);
 	if (ppartition_name)
-		strncpy(partition_name, ppartition_name,
+		strlcpy(partition_name, ppartition_name,
 				sizeof(partition_name));
 	p_number_ptr = of_get_property(of_root, "ibm,partition-no", NULL);
 	if (p_number_ptr)
@@ -681,7 +681,7 @@ static int map_sg_list(struct scsi_cmnd *cmd, int nseg,
 
 /**
  * map_sg_data: - Maps dma for a scatterlist and initializes decriptor fields
- * @cmd:	Scsi_Cmnd with the scatterlist
+ * @cmd:	struct scsi_cmnd with the scatterlist
  * @srp_cmd:	srp_cmd that contains the memory descriptor
  * @dev:	device for which to map dma memory
  *
@@ -1274,14 +1274,12 @@ static void send_mad_capabilities(struct ibmvscsi_host_data *hostdata)
 	if (hostdata->client_migrated)
 		hostdata->caps.flags |= cpu_to_be32(CLIENT_MIGRATED);
 
-	strncpy(hostdata->caps.name, dev_name(&hostdata->host->shost_gendev),
+	strlcpy(hostdata->caps.name, dev_name(&hostdata->host->shost_gendev),
 		sizeof(hostdata->caps.name));
-	hostdata->caps.name[sizeof(hostdata->caps.name) - 1] = '\0';
 
 	location = of_get_property(of_node, "ibm,loc-code", NULL);
 	location = location ? location : dev_name(hostdata->dev);
-	strncpy(hostdata->caps.loc, location, sizeof(hostdata->caps.loc));
-	hostdata->caps.loc[sizeof(hostdata->caps.loc) - 1] = '\0';
+	strlcpy(hostdata->caps.loc, location, sizeof(hostdata->caps.loc));
 
 	req->common.type = cpu_to_be32(VIOSRP_CAPABILITIES_TYPE);
 	req->buffer = cpu_to_be64(hostdata->caps_addr);
diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index c3a76af9f5fa..fac377320158 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -2233,7 +2233,7 @@ static int ibmvscsis_make_nexus(struct ibmvscsis_tport *tport)
 		return -ENOMEM;
 	}
 
-	nexus->se_sess = target_alloc_session(&tport->se_tpg, 0, 0,
+	nexus->se_sess = target_setup_session(&tport->se_tpg, 0, 0,
 					      TARGET_PROT_NORMAL, name, nexus,
 					      NULL);
 	if (IS_ERR(nexus->se_sess)) {
@@ -2267,8 +2267,7 @@ static int ibmvscsis_drop_nexus(struct ibmvscsis_tport *tport)
 	 * Release the SCSI I_T Nexus to the emulated ibmvscsis Target Port
 	 */
 	target_wait_for_sess_cmds(se_sess);
-	transport_deregister_session_configfs(se_sess);
-	transport_deregister_session(se_sess);
+	target_remove_session(se_sess);
 	tport->ibmv_nexus = NULL;
 	kfree(nexus);
 
@@ -3928,7 +3927,6 @@ static void ibmvscsis_drop_tport(struct se_wwn *wwn)
 }
 
 static struct se_portal_group *ibmvscsis_make_tpg(struct se_wwn *wwn,
-						  struct config_group *group,
 						  const char *name)
 {
 	struct ibmvscsis_tport *tport =
diff --git a/drivers/scsi/imm.c b/drivers/scsi/imm.c
index 87c94191033b..8c6627bc8a39 100644
--- a/drivers/scsi/imm.c
+++ b/drivers/scsi/imm.c
@@ -892,7 +892,7 @@ static int imm_engine(imm_struct *dev, struct scsi_cmnd *cmd)
 			/* Check for optional message byte */
 			if (imm_wait(dev) == (unsigned char) 0xb8)
 				imm_in(dev, &h, 1);
-			cmd->result = (DID_OK << 16) + (l & STATUS_MASK);
+			cmd->result = (DID_OK << 16) | (l & STATUS_MASK);
 		}
 		if ((dev->mode == IMM_NIBBLE) || (dev->mode == IMM_PS2)) {
 			w_ctr(ppb, 0x4);
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 02d65dce74e5..f2ec80b0ffc0 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -2412,6 +2412,28 @@ static void ipr_log_sis64_fabric_error(struct ipr_ioa_cfg *ioa_cfg,
 }
 
 /**
+ * ipr_log_sis64_service_required_error - Log a sis64 service required error.
+ * @ioa_cfg:    ioa config struct
+ * @hostrcb:    hostrcb struct
+ *
+ * Return value:
+ *      none
+ **/
+static void ipr_log_sis64_service_required_error(struct ipr_ioa_cfg *ioa_cfg,
+				       struct ipr_hostrcb *hostrcb)
+{
+	struct ipr_hostrcb_type_41_error *error;
+
+	error = &hostrcb->hcam.u.error64.u.type_41_error;
+
+	error->failure_reason[sizeof(error->failure_reason) - 1] = '\0';
+	ipr_err("Primary Failure Reason: %s\n", error->failure_reason);
+	ipr_log_hex_data(ioa_cfg, error->data,
+			 be32_to_cpu(hostrcb->hcam.length) -
+			 (offsetof(struct ipr_hostrcb_error, u) +
+			  offsetof(struct ipr_hostrcb_type_41_error, data)));
+}
+/**
  * ipr_log_generic_error - Log an adapter error.
  * @ioa_cfg:	ioa config struct
  * @hostrcb:	hostrcb struct
@@ -2586,6 +2608,9 @@ static void ipr_handle_log_data(struct ipr_ioa_cfg *ioa_cfg,
 	case IPR_HOST_RCB_OVERLAY_ID_30:
 		ipr_log_sis64_fabric_error(ioa_cfg, hostrcb);
 		break;
+	case IPR_HOST_RCB_OVERLAY_ID_41:
+		ipr_log_sis64_service_required_error(ioa_cfg, hostrcb);
+		break;
 	case IPR_HOST_RCB_OVERLAY_ID_1:
 	case IPR_HOST_RCB_OVERLAY_ID_DEFAULT:
 	default:
diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h
index 93570734cbfb..68afbbde54d3 100644
--- a/drivers/scsi/ipr.h
+++ b/drivers/scsi/ipr.h
@@ -1135,6 +1135,11 @@ struct ipr_hostrcb_type_30_error {
 	struct ipr_hostrcb64_fabric_desc desc[1];
 }__attribute__((packed, aligned (4)));
 
+struct ipr_hostrcb_type_41_error {
+	u8 failure_reason[64];
+	 __be32 data[200];
+}__attribute__((packed, aligned (4)));
+
 struct ipr_hostrcb_error {
 	__be32 fd_ioasc;
 	struct ipr_res_addr fd_res_addr;
@@ -1173,6 +1178,7 @@ struct ipr_hostrcb64_error {
 		struct ipr_hostrcb_type_23_error type_23_error;
 		struct ipr_hostrcb_type_24_error type_24_error;
 		struct ipr_hostrcb_type_30_error type_30_error;
+		struct ipr_hostrcb_type_41_error type_41_error;
 	} u;
 }__attribute__((packed, aligned (8)));
 
@@ -1218,6 +1224,7 @@ struct ipr_hcam {
 #define IPR_HOST_RCB_OVERLAY_ID_24				0x24
 #define IPR_HOST_RCB_OVERLAY_ID_26				0x26
 #define IPR_HOST_RCB_OVERLAY_ID_30				0x30
+#define IPR_HOST_RCB_OVERLAY_ID_41				0x41
 #define IPR_HOST_RCB_OVERLAY_ID_DEFAULT				0xFF
 
 	u8 reserved1[3];
diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c
index 3f3569ec5ce3..f969a71348ef 100644
--- a/drivers/scsi/libfc/fc_disc.c
+++ b/drivers/scsi/libfc/fc_disc.c
@@ -59,34 +59,25 @@ static void fc_disc_restart(struct fc_disc *);
 /**
  * fc_disc_stop_rports() - Delete all the remote ports associated with the lport
  * @disc: The discovery job to stop remote ports on
- *
- * Locking Note: This function expects that the lport mutex is locked before
- * calling it.
  */
 static void fc_disc_stop_rports(struct fc_disc *disc)
 {
-	struct fc_lport *lport;
 	struct fc_rport_priv *rdata;
 
-	lport = fc_disc_lport(disc);
+	lockdep_assert_held(&disc->disc_mutex);
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(rdata, &disc->rports, peers) {
+	list_for_each_entry(rdata, &disc->rports, peers) {
 		if (kref_get_unless_zero(&rdata->kref)) {
 			fc_rport_logoff(rdata);
 			kref_put(&rdata->kref, fc_rport_destroy);
 		}
 	}
-	rcu_read_unlock();
 }
 
 /**
  * fc_disc_recv_rscn_req() - Handle Registered State Change Notification (RSCN)
  * @disc:  The discovery object to which the RSCN applies
  * @fp:	   The RSCN frame
- *
- * Locking Note: This function expects that the disc_mutex is locked
- *		 before it is called.
  */
 static void fc_disc_recv_rscn_req(struct fc_disc *disc, struct fc_frame *fp)
 {
@@ -101,6 +92,8 @@ static void fc_disc_recv_rscn_req(struct fc_disc *disc, struct fc_frame *fp)
 	LIST_HEAD(disc_ports);
 	struct fc_disc_port *dp, *next;
 
+	lockdep_assert_held(&disc->disc_mutex);
+
 	lport = fc_disc_lport(disc);
 
 	FC_DISC_DBG(disc, "Received an RSCN event\n");
@@ -220,12 +213,11 @@ static void fc_disc_recv_req(struct fc_lport *lport, struct fc_frame *fp)
 /**
  * fc_disc_restart() - Restart discovery
  * @disc: The discovery object to be restarted
- *
- * Locking Note: This function expects that the disc mutex
- *		 is already locked.
  */
 static void fc_disc_restart(struct fc_disc *disc)
 {
+	lockdep_assert_held(&disc->disc_mutex);
+
 	if (!disc->disc_callback)
 		return;
 
@@ -271,16 +263,13 @@ static void fc_disc_start(void (*disc_callback)(struct fc_lport *,
  * fc_disc_done() - Discovery has been completed
  * @disc:  The discovery context
  * @event: The discovery completion status
- *
- * Locking Note: This function expects that the disc mutex is locked before
- * it is called. The discovery callback is then made with the lock released,
- * and the lock is re-taken before returning from this function
  */
 static void fc_disc_done(struct fc_disc *disc, enum fc_disc_event event)
 {
 	struct fc_lport *lport = fc_disc_lport(disc);
 	struct fc_rport_priv *rdata;
 
+	lockdep_assert_held(&disc->disc_mutex);
 	FC_DISC_DBG(disc, "Discovery complete\n");
 
 	disc->pending = 0;
@@ -294,9 +283,11 @@ static void fc_disc_done(struct fc_disc *disc, enum fc_disc_event event)
 	 * discovery, reverify or log them in.	Otherwise, log them out.
 	 * Skip ports which were never discovered.  These are the dNS port
 	 * and ports which were created by PLOGI.
+	 *
+	 * We don't need to use the _rcu variant here as the rport list
+	 * is protected by the disc mutex which is already held on entry.
 	 */
-	rcu_read_lock();
-	list_for_each_entry_rcu(rdata, &disc->rports, peers) {
+	list_for_each_entry(rdata, &disc->rports, peers) {
 		if (!kref_get_unless_zero(&rdata->kref))
 			continue;
 		if (rdata->disc_id) {
@@ -307,7 +298,6 @@ static void fc_disc_done(struct fc_disc *disc, enum fc_disc_event event)
 		}
 		kref_put(&rdata->kref, fc_rport_destroy);
 	}
-	rcu_read_unlock();
 	mutex_unlock(&disc->disc_mutex);
 	disc->disc_callback(lport, event);
 	mutex_lock(&disc->disc_mutex);
@@ -360,15 +350,14 @@ static void fc_disc_error(struct fc_disc *disc, struct fc_frame *fp)
 /**
  * fc_disc_gpn_ft_req() - Send Get Port Names by FC-4 type (GPN_FT) request
  * @lport: The discovery context
- *
- * Locking Note: This function expects that the disc_mutex is locked
- *		 before it is called.
  */
 static void fc_disc_gpn_ft_req(struct fc_disc *disc)
 {
 	struct fc_frame *fp;
 	struct fc_lport *lport = fc_disc_lport(disc);
 
+	lockdep_assert_held(&disc->disc_mutex);
+
 	WARN_ON(!fc_lport_test_ready(lport));
 
 	disc->pending = 1;
@@ -658,8 +647,6 @@ out:
  * @lport: The local port to initiate discovery on
  * @rdata: remote port private data
  *
- * Locking Note: This function expects that the disc_mutex is locked
- *		 before it is called.
  * On failure, an error code is returned.
  */
 static int fc_disc_gpn_id_req(struct fc_lport *lport,
@@ -667,6 +654,7 @@ static int fc_disc_gpn_id_req(struct fc_lport *lport,
 {
 	struct fc_frame *fp;
 
+	lockdep_assert_held(&lport->disc.disc_mutex);
 	fp = fc_frame_alloc(lport, sizeof(struct fc_ct_hdr) +
 			    sizeof(struct fc_ns_fid));
 	if (!fp)
@@ -683,14 +671,13 @@ static int fc_disc_gpn_id_req(struct fc_lport *lport,
  * fc_disc_single() - Discover the directory information for a single target
  * @lport: The local port the remote port is associated with
  * @dp:	   The port to rediscover
- *
- * Locking Note: This function expects that the disc_mutex is locked
- *		 before it is called.
  */
 static int fc_disc_single(struct fc_lport *lport, struct fc_disc_port *dp)
 {
 	struct fc_rport_priv *rdata;
 
+	lockdep_assert_held(&lport->disc.disc_mutex);
+
 	rdata = fc_rport_create(lport, dp->port_id);
 	if (!rdata)
 		return -ENOMEM;
@@ -708,7 +695,9 @@ static void fc_disc_stop(struct fc_lport *lport)
 
 	if (disc->pending)
 		cancel_delayed_work_sync(&disc->disc_work);
+	mutex_lock(&disc->disc_mutex);
 	fc_disc_stop_rports(disc);
+	mutex_unlock(&disc->disc_mutex);
 }
 
 /**
diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c
index 21be672679fb..be83590ed955 100644
--- a/drivers/scsi/libfc/fc_lport.c
+++ b/drivers/scsi/libfc/fc_lport.c
@@ -237,14 +237,13 @@ static const char *fc_lport_state(struct fc_lport *lport)
  * @remote_fid:	 The FID of the ptp rport
  * @remote_wwpn: The WWPN of the ptp rport
  * @remote_wwnn: The WWNN of the ptp rport
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_ptp_setup(struct fc_lport *lport,
 			       u32 remote_fid, u64 remote_wwpn,
 			       u64 remote_wwnn)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	if (lport->ptp_rdata) {
 		fc_rport_logoff(lport->ptp_rdata);
 		kref_put(&lport->ptp_rdata->kref, fc_rport_destroy);
@@ -403,12 +402,11 @@ static void fc_lport_add_fc4_type(struct fc_lport *lport, enum fc_fh_type type)
  * fc_lport_recv_rlir_req() - Handle received Registered Link Incident Report.
  * @lport: Fibre Channel local port receiving the RLIR
  * @fp:	   The RLIR request frame
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this function.
  */
 static void fc_lport_recv_rlir_req(struct fc_lport *lport, struct fc_frame *fp)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Received RLIR request while in state %s\n",
 		     fc_lport_state(lport));
 
@@ -420,9 +418,6 @@ static void fc_lport_recv_rlir_req(struct fc_lport *lport, struct fc_frame *fp)
  * fc_lport_recv_echo_req() - Handle received ECHO request
  * @lport: The local port receiving the ECHO
  * @fp:	   ECHO request frame
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this function.
  */
 static void fc_lport_recv_echo_req(struct fc_lport *lport,
 				   struct fc_frame *in_fp)
@@ -432,6 +427,8 @@ static void fc_lport_recv_echo_req(struct fc_lport *lport,
 	void *pp;
 	void *dp;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Received ECHO request while in state %s\n",
 		     fc_lport_state(lport));
 
@@ -456,9 +453,6 @@ static void fc_lport_recv_echo_req(struct fc_lport *lport,
  * fc_lport_recv_rnid_req() - Handle received Request Node ID data request
  * @lport: The local port receiving the RNID
  * @fp:	   The RNID request frame
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this function.
  */
 static void fc_lport_recv_rnid_req(struct fc_lport *lport,
 				   struct fc_frame *in_fp)
@@ -474,6 +468,8 @@ static void fc_lport_recv_rnid_req(struct fc_lport *lport,
 	u8 fmt;
 	size_t len;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Received RNID request while in state %s\n",
 		     fc_lport_state(lport));
 
@@ -515,12 +511,11 @@ static void fc_lport_recv_rnid_req(struct fc_lport *lport,
  * fc_lport_recv_logo_req() - Handle received fabric LOGO request
  * @lport: The local port receiving the LOGO
  * @fp:	   The LOGO request frame
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this function.
  */
 static void fc_lport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	fc_seq_els_rsp_send(fp, ELS_LS_ACC, NULL);
 	fc_lport_enter_reset(lport);
 	fc_frame_free(fp);
@@ -553,11 +548,11 @@ EXPORT_SYMBOL(fc_fabric_login);
 /**
  * __fc_linkup() - Handler for transport linkup events
  * @lport: The lport whose link is up
- *
- * Locking: must be called with the lp_mutex held
  */
 void __fc_linkup(struct fc_lport *lport)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	if (!lport->link_up) {
 		lport->link_up = 1;
 
@@ -584,11 +579,11 @@ EXPORT_SYMBOL(fc_linkup);
 /**
  * __fc_linkdown() - Handler for transport linkdown events
  * @lport: The lport whose link is down
- *
- * Locking: must be called with the lp_mutex held
  */
 void __fc_linkdown(struct fc_lport *lport)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	if (lport->link_up) {
 		lport->link_up = 0;
 		fc_lport_enter_reset(lport);
@@ -722,12 +717,11 @@ static void fc_lport_disc_callback(struct fc_lport *lport,
 /**
  * fc_rport_enter_ready() - Enter the ready state and start discovery
  * @lport: The local port that is ready
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_ready(struct fc_lport *lport)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered READY from state %s\n",
 		     fc_lport_state(lport));
 
@@ -745,13 +739,12 @@ static void fc_lport_enter_ready(struct fc_lport *lport)
  * @lport: The local port which will have its Port ID set.
  * @port_id: The new port ID.
  * @fp: The frame containing the incoming request, or NULL.
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this function.
  */
 static void fc_lport_set_port_id(struct fc_lport *lport, u32 port_id,
 				 struct fc_frame *fp)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	if (port_id)
 		printk(KERN_INFO "host%d: Assigned Port ID %6.6x\n",
 		       lport->host->host_no, port_id);
@@ -801,9 +794,6 @@ EXPORT_SYMBOL(fc_lport_set_local_id);
  * A received FLOGI request indicates a point-to-point connection.
  * Accept it with the common service parameters indicating our N port.
  * Set up to do a PLOGI if we have the higher-number WWPN.
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this function.
  */
 static void fc_lport_recv_flogi_req(struct fc_lport *lport,
 				    struct fc_frame *rx_fp)
@@ -816,6 +806,8 @@ static void fc_lport_recv_flogi_req(struct fc_lport *lport,
 	u32 remote_fid;
 	u32 local_fid;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Received FLOGI request while in state %s\n",
 		     fc_lport_state(lport));
 
@@ -1006,12 +998,11 @@ EXPORT_SYMBOL(fc_lport_reset);
 /**
  * fc_lport_reset_locked() - Reset the local port w/ the lport lock held
  * @lport: The local port to be reset
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_reset_locked(struct fc_lport *lport)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	if (lport->dns_rdata) {
 		fc_rport_logoff(lport->dns_rdata);
 		lport->dns_rdata = NULL;
@@ -1035,12 +1026,11 @@ static void fc_lport_reset_locked(struct fc_lport *lport)
 /**
  * fc_lport_enter_reset() - Reset the local port
  * @lport: The local port to be reset
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_reset(struct fc_lport *lport)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered RESET state from %s state\n",
 		     fc_lport_state(lport));
 
@@ -1065,12 +1055,11 @@ static void fc_lport_enter_reset(struct fc_lport *lport)
 /**
  * fc_lport_enter_disabled() - Disable the local port
  * @lport: The local port to be reset
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_disabled(struct fc_lport *lport)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered disabled state from %s state\n",
 		     fc_lport_state(lport));
 
@@ -1321,14 +1310,13 @@ err:
 /**
  * fc_lport_enter_scr() - Send a SCR (State Change Register) request
  * @lport: The local port to register for state changes
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_scr(struct fc_lport *lport)
 {
 	struct fc_frame *fp;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered SCR state from %s state\n",
 		     fc_lport_state(lport));
 
@@ -1349,9 +1337,6 @@ static void fc_lport_enter_scr(struct fc_lport *lport)
 /**
  * fc_lport_enter_ns() - register some object with the name server
  * @lport: Fibre Channel local port to register
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_ns(struct fc_lport *lport, enum fc_lport_state state)
 {
@@ -1360,6 +1345,8 @@ static void fc_lport_enter_ns(struct fc_lport *lport, enum fc_lport_state state)
 	int size = sizeof(struct fc_ct_hdr);
 	size_t len;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered %s state from %s state\n",
 		     fc_lport_state_names[state],
 		     fc_lport_state(lport));
@@ -1419,14 +1406,13 @@ static struct fc_rport_operations fc_lport_rport_ops = {
 /**
  * fc_rport_enter_dns() - Create a fc_rport for the name server
  * @lport: The local port requesting a remote port for the name server
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_dns(struct fc_lport *lport)
 {
 	struct fc_rport_priv *rdata;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered DNS state from %s state\n",
 		     fc_lport_state(lport));
 
@@ -1449,9 +1435,6 @@ err:
 /**
  * fc_lport_enter_ms() - management server commands
  * @lport: Fibre Channel local port to register
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_ms(struct fc_lport *lport, enum fc_lport_state state)
 {
@@ -1461,6 +1444,8 @@ static void fc_lport_enter_ms(struct fc_lport *lport, enum fc_lport_state state)
 	size_t len;
 	int numattrs;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered %s state from %s state\n",
 		     fc_lport_state_names[state],
 		     fc_lport_state(lport));
@@ -1536,14 +1521,13 @@ static void fc_lport_enter_ms(struct fc_lport *lport, enum fc_lport_state state)
 /**
  * fc_rport_enter_fdmi() - Create a fc_rport for the management server
  * @lport: The local port requesting a remote port for the management server
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_fdmi(struct fc_lport *lport)
 {
 	struct fc_rport_priv *rdata;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered FDMI state from %s state\n",
 		     fc_lport_state(lport));
 
@@ -1668,15 +1652,14 @@ EXPORT_SYMBOL(fc_lport_logo_resp);
 /**
  * fc_rport_enter_logo() - Logout of the fabric
  * @lport: The local port to be logged out
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_logo(struct fc_lport *lport)
 {
 	struct fc_frame *fp;
 	struct fc_els_logo *logo;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered LOGO state from %s state\n",
 		     fc_lport_state(lport));
 
@@ -1811,14 +1794,13 @@ EXPORT_SYMBOL(fc_lport_flogi_resp);
 /**
  * fc_rport_enter_flogi() - Send a FLOGI request to the fabric manager
  * @lport: Fibre Channel local port to be logged in to the fabric
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_flogi(struct fc_lport *lport)
 {
 	struct fc_frame *fp;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered FLOGI state from %s state\n",
 		     fc_lport_state(lport));
 
@@ -1962,9 +1944,6 @@ static void fc_lport_bsg_resp(struct fc_seq *sp, struct fc_frame *fp,
  * @job:   The BSG Passthrough job
  * @lport: The local port sending the request
  * @did:   The destination port id
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static int fc_lport_els_request(struct bsg_job *job,
 				struct fc_lport *lport,
@@ -1976,6 +1955,8 @@ static int fc_lport_els_request(struct bsg_job *job,
 	char *pp;
 	int len;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	fp = fc_frame_alloc(lport, job->request_payload.payload_len);
 	if (!fp)
 		return -ENOMEM;
@@ -2023,9 +2004,6 @@ static int fc_lport_els_request(struct bsg_job *job,
  * @lport: The local port sending the request
  * @did:   The destination FC-ID
  * @tov:   The timeout period to wait for the response
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static int fc_lport_ct_request(struct bsg_job *job,
 			       struct fc_lport *lport, u32 did, u32 tov)
@@ -2036,6 +2014,8 @@ static int fc_lport_ct_request(struct bsg_job *job,
 	struct fc_ct_req *ct;
 	size_t len;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	fp = fc_frame_alloc(lport, sizeof(struct fc_ct_hdr) +
 			    job->request_payload.payload_len);
 	if (!fp)
diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index 89b1f1af2fd4..372387a450df 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -136,13 +136,13 @@ EXPORT_SYMBOL(fc_rport_lookup);
  * @ids:   The identifiers for the new remote port
  *
  * The remote port will start in the INIT state.
- *
- * Locking note:  must be called with the disc_mutex held.
  */
 struct fc_rport_priv *fc_rport_create(struct fc_lport *lport, u32 port_id)
 {
 	struct fc_rport_priv *rdata;
 
+	lockdep_assert_held(&lport->disc.disc_mutex);
+
 	rdata = fc_rport_lookup(lport, port_id);
 	if (rdata)
 		return rdata;
@@ -184,6 +184,7 @@ void fc_rport_destroy(struct kref *kref)
 	struct fc_rport_priv *rdata;
 
 	rdata = container_of(kref, struct fc_rport_priv, kref);
+	WARN_ON(!list_empty(&rdata->peers));
 	kfree_rcu(rdata, rcu);
 }
 EXPORT_SYMBOL(fc_rport_destroy);
@@ -245,12 +246,12 @@ static unsigned int fc_plogi_get_maxframe(struct fc_els_flogi *flp,
  * fc_rport_state_enter() - Change the state of a remote port
  * @rdata: The remote port whose state should change
  * @new:   The new state
- *
- * Locking Note: Called with the rport lock held
  */
 static void fc_rport_state_enter(struct fc_rport_priv *rdata,
 				 enum fc_rport_state new)
 {
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	if (rdata->rp_state != new)
 		rdata->retries = 0;
 	rdata->rp_state = new;
@@ -469,8 +470,6 @@ EXPORT_SYMBOL(fc_rport_login);
  * @rdata: The remote port to be deleted
  * @event: The event to report as the reason for deletion
  *
- * Locking Note: Called with the rport lock held.
- *
  * Allow state change into DELETE only once.
  *
  * Call queue_work only if there's no event already pending.
@@ -483,6 +482,8 @@ EXPORT_SYMBOL(fc_rport_login);
 static void fc_rport_enter_delete(struct fc_rport_priv *rdata,
 				  enum fc_rport_event event)
 {
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	if (rdata->rp_state == RPORT_ST_DELETE)
 		return;
 
@@ -546,13 +547,12 @@ EXPORT_SYMBOL(fc_rport_logoff);
  * fc_rport_enter_ready() - Transition to the RPORT_ST_READY state
  * @rdata: The remote port that is ready
  *
- * Locking Note: The rport lock is expected to be held before calling
- * this routine.
- *
  * Reference counting: schedules workqueue, does not modify kref
  */
 static void fc_rport_enter_ready(struct fc_rport_priv *rdata)
 {
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	fc_rport_state_enter(rdata, RPORT_ST_READY);
 
 	FC_RPORT_DBG(rdata, "Port is Ready\n");
@@ -615,15 +615,14 @@ static void fc_rport_timeout(struct work_struct *work)
  * @rdata: The remote port the error is happened on
  * @err:   The error code
  *
- * Locking Note: The rport lock is expected to be held before
- * calling this routine
- *
  * Reference counting: does not modify kref
  */
 static void fc_rport_error(struct fc_rport_priv *rdata, int err)
 {
 	struct fc_lport *lport = rdata->local_port;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	FC_RPORT_DBG(rdata, "Error %d in state %s, retries %d\n",
 		     -err, fc_rport_state(rdata), rdata->retries);
 
@@ -662,15 +661,14 @@ static void fc_rport_error(struct fc_rport_priv *rdata, int err)
  * If the error was an exchange timeout retry immediately,
  * otherwise wait for E_D_TOV.
  *
- * Locking Note: The rport lock is expected to be held before
- * calling this routine
- *
  * Reference counting: increments kref when scheduling retry_work
  */
 static void fc_rport_error_retry(struct fc_rport_priv *rdata, int err)
 {
 	unsigned long delay = msecs_to_jiffies(rdata->e_d_tov);
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	/* make sure this isn't an FC_EX_CLOSED error, never retry those */
 	if (err == -FC_EX_CLOSED)
 		goto out;
@@ -822,9 +820,6 @@ bad:
  * fc_rport_enter_flogi() - Send a FLOGI request to the remote port for p-mp
  * @rdata: The remote port to send a FLOGI to
  *
- * Locking Note: The rport lock is expected to be held before calling
- * this routine.
- *
  * Reference counting: increments kref when sending ELS
  */
 static void fc_rport_enter_flogi(struct fc_rport_priv *rdata)
@@ -832,6 +827,8 @@ static void fc_rport_enter_flogi(struct fc_rport_priv *rdata)
 	struct fc_lport *lport = rdata->local_port;
 	struct fc_frame *fp;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	if (!lport->point_to_multipoint)
 		return fc_rport_enter_plogi(rdata);
 
@@ -1071,9 +1068,6 @@ fc_rport_compatible_roles(struct fc_lport *lport, struct fc_rport_priv *rdata)
  * fc_rport_enter_plogi() - Send Port Login (PLOGI) request
  * @rdata: The remote port to send a PLOGI to
  *
- * Locking Note: The rport lock is expected to be held before calling
- * this routine.
- *
  * Reference counting: increments kref when sending ELS
  */
 static void fc_rport_enter_plogi(struct fc_rport_priv *rdata)
@@ -1081,6 +1075,8 @@ static void fc_rport_enter_plogi(struct fc_rport_priv *rdata)
 	struct fc_lport *lport = rdata->local_port;
 	struct fc_frame *fp;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	if (!fc_rport_compatible_roles(lport, rdata)) {
 		FC_RPORT_DBG(rdata, "PLOGI suppressed for incompatible role\n");
 		fc_rport_state_enter(rdata, RPORT_ST_PLOGI_WAIT);
@@ -1232,9 +1228,6 @@ put:
  * fc_rport_enter_prli() - Send Process Login (PRLI) request
  * @rdata: The remote port to send the PRLI request to
  *
- * Locking Note: The rport lock is expected to be held before calling
- * this routine.
- *
  * Reference counting: increments kref when sending ELS
  */
 static void fc_rport_enter_prli(struct fc_rport_priv *rdata)
@@ -1247,6 +1240,8 @@ static void fc_rport_enter_prli(struct fc_rport_priv *rdata)
 	struct fc_frame *fp;
 	struct fc4_prov *prov;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	/*
 	 * If the rport is one of the well known addresses
 	 * we skip PRLI and RTV and go straight to READY.
@@ -1372,9 +1367,6 @@ put:
  * fc_rport_enter_rtv() - Send Request Timeout Value (RTV) request
  * @rdata: The remote port to send the RTV request to
  *
- * Locking Note: The rport lock is expected to be held before calling
- * this routine.
- *
  * Reference counting: increments kref when sending ELS
  */
 static void fc_rport_enter_rtv(struct fc_rport_priv *rdata)
@@ -1382,6 +1374,8 @@ static void fc_rport_enter_rtv(struct fc_rport_priv *rdata)
 	struct fc_frame *fp;
 	struct fc_lport *lport = rdata->local_port;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	FC_RPORT_DBG(rdata, "Port entered RTV state from %s state\n",
 		     fc_rport_state(rdata));
 
@@ -1406,8 +1400,6 @@ static void fc_rport_enter_rtv(struct fc_rport_priv *rdata)
  * fc_rport_recv_rtv_req() - Handler for Read Timeout Value (RTV) requests
  * @rdata: The remote port that sent the RTV request
  * @in_fp: The RTV request frame
- *
- * Locking Note:  Called with the lport and rport locks held.
  */
 static void fc_rport_recv_rtv_req(struct fc_rport_priv *rdata,
 				  struct fc_frame *in_fp)
@@ -1417,6 +1409,9 @@ static void fc_rport_recv_rtv_req(struct fc_rport_priv *rdata,
 	struct fc_els_rtv_acc *rtv;
 	struct fc_seq_els_data rjt_data;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_RPORT_DBG(rdata, "Received RTV request\n");
 
 	fp = fc_frame_alloc(lport, sizeof(*rtv));
@@ -1460,9 +1455,6 @@ static void fc_rport_logo_resp(struct fc_seq *sp, struct fc_frame *fp,
  * fc_rport_enter_logo() - Send a logout (LOGO) request
  * @rdata: The remote port to send the LOGO request to
  *
- * Locking Note: The rport lock is expected to be held before calling
- * this routine.
- *
  * Reference counting: increments kref when sending ELS
  */
 static void fc_rport_enter_logo(struct fc_rport_priv *rdata)
@@ -1470,6 +1462,8 @@ static void fc_rport_enter_logo(struct fc_rport_priv *rdata)
 	struct fc_lport *lport = rdata->local_port;
 	struct fc_frame *fp;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	FC_RPORT_DBG(rdata, "Port sending LOGO from %s state\n",
 		     fc_rport_state(rdata));
 
@@ -1548,9 +1542,6 @@ put:
  * fc_rport_enter_adisc() - Send Address Discover (ADISC) request
  * @rdata: The remote port to send the ADISC request to
  *
- * Locking Note: The rport lock is expected to be held before calling
- * this routine.
- *
  * Reference counting: increments kref when sending ELS
  */
 static void fc_rport_enter_adisc(struct fc_rport_priv *rdata)
@@ -1558,6 +1549,8 @@ static void fc_rport_enter_adisc(struct fc_rport_priv *rdata)
 	struct fc_lport *lport = rdata->local_port;
 	struct fc_frame *fp;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	FC_RPORT_DBG(rdata, "sending ADISC from %s state\n",
 		     fc_rport_state(rdata));
 
@@ -1581,8 +1574,6 @@ static void fc_rport_enter_adisc(struct fc_rport_priv *rdata)
  * fc_rport_recv_adisc_req() - Handler for Address Discovery (ADISC) requests
  * @rdata: The remote port that sent the ADISC request
  * @in_fp: The ADISC request frame
- *
- * Locking Note:  Called with the lport and rport locks held.
  */
 static void fc_rport_recv_adisc_req(struct fc_rport_priv *rdata,
 				    struct fc_frame *in_fp)
@@ -1592,6 +1583,9 @@ static void fc_rport_recv_adisc_req(struct fc_rport_priv *rdata,
 	struct fc_els_adisc *adisc;
 	struct fc_seq_els_data rjt_data;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_RPORT_DBG(rdata, "Received ADISC request\n");
 
 	adisc = fc_frame_payload_get(in_fp, sizeof(*adisc));
@@ -1618,9 +1612,6 @@ drop:
  * fc_rport_recv_rls_req() - Handle received Read Link Status request
  * @rdata: The remote port that sent the RLS request
  * @rx_fp: The PRLI request frame
- *
- * Locking Note: The rport lock is expected to be held before calling
- * this function.
  */
 static void fc_rport_recv_rls_req(struct fc_rport_priv *rdata,
 				  struct fc_frame *rx_fp)
@@ -1634,6 +1625,8 @@ static void fc_rport_recv_rls_req(struct fc_rport_priv *rdata,
 	struct fc_seq_els_data rjt_data;
 	struct fc_host_statistics *hst;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	FC_RPORT_DBG(rdata, "Received RLS request while in state %s\n",
 		     fc_rport_state(rdata));
 
@@ -1687,8 +1680,6 @@ out:
  * Handle incoming ELS requests that require port login.
  * The ELS opcode has already been validated by the caller.
  *
- * Locking Note: Called with the lport lock held.
- *
  * Reference counting: does not modify kref
  */
 static void fc_rport_recv_els_req(struct fc_lport *lport, struct fc_frame *fp)
@@ -1696,6 +1687,8 @@ static void fc_rport_recv_els_req(struct fc_lport *lport, struct fc_frame *fp)
 	struct fc_rport_priv *rdata;
 	struct fc_seq_els_data els_data;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	rdata = fc_rport_lookup(lport, fc_frame_sid(fp));
 	if (!rdata) {
 		FC_RPORT_ID_DBG(lport, fc_frame_sid(fp),
@@ -1783,14 +1776,14 @@ busy:
  * @lport: The local port that received the request
  * @fp:	   The request frame
  *
- * Locking Note: Called with the lport lock held.
- *
  * Reference counting: does not modify kref
  */
 void fc_rport_recv_req(struct fc_lport *lport, struct fc_frame *fp)
 {
 	struct fc_seq_els_data els_data;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	/*
 	 * Handle FLOGI, PLOGI and LOGO requests separately, since they
 	 * don't require prior login.
@@ -1831,8 +1824,6 @@ EXPORT_SYMBOL(fc_rport_recv_req);
  * @lport: The local port that received the PLOGI request
  * @rx_fp: The PLOGI request frame
  *
- * Locking Note: The rport lock is held before calling this function.
- *
  * Reference counting: increments kref on return
  */
 static void fc_rport_recv_plogi_req(struct fc_lport *lport,
@@ -1845,6 +1836,8 @@ static void fc_rport_recv_plogi_req(struct fc_lport *lport,
 	struct fc_seq_els_data rjt_data;
 	u32 sid;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	sid = fc_frame_sid(fp);
 
 	FC_RPORT_ID_DBG(lport, sid, "Received PLOGI request\n");
@@ -1955,9 +1948,6 @@ reject:
  * fc_rport_recv_prli_req() - Handler for process login (PRLI) requests
  * @rdata: The remote port that sent the PRLI request
  * @rx_fp: The PRLI request frame
- *
- * Locking Note: The rport lock is expected to be held before calling
- * this function.
  */
 static void fc_rport_recv_prli_req(struct fc_rport_priv *rdata,
 				   struct fc_frame *rx_fp)
@@ -1976,6 +1966,8 @@ static void fc_rport_recv_prli_req(struct fc_rport_priv *rdata,
 	struct fc_seq_els_data rjt_data;
 	struct fc4_prov *prov;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	FC_RPORT_DBG(rdata, "Received PRLI request while in state %s\n",
 		     fc_rport_state(rdata));
 
@@ -2072,9 +2064,6 @@ drop:
  * fc_rport_recv_prlo_req() - Handler for process logout (PRLO) requests
  * @rdata: The remote port that sent the PRLO request
  * @rx_fp: The PRLO request frame
- *
- * Locking Note: The rport lock is expected to be held before calling
- * this function.
  */
 static void fc_rport_recv_prlo_req(struct fc_rport_priv *rdata,
 				   struct fc_frame *rx_fp)
@@ -2091,6 +2080,8 @@ static void fc_rport_recv_prlo_req(struct fc_rport_priv *rdata,
 	unsigned int plen;
 	struct fc_seq_els_data rjt_data;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	FC_RPORT_DBG(rdata, "Received PRLO request while in state %s\n",
 		     fc_rport_state(rdata));
 
@@ -2144,9 +2135,6 @@ drop:
  * @lport: The local port that received the LOGO request
  * @fp:	   The LOGO request frame
  *
- * Locking Note: The rport lock is expected to be held before calling
- * this function.
- *
  * Reference counting: drops kref on return
  */
 static void fc_rport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp)
@@ -2154,6 +2142,8 @@ static void fc_rport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp)
 	struct fc_rport_priv *rdata;
 	u32 sid;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	fc_seq_els_rsp_send(fp, ELS_LS_ACC, NULL);
 
 	sid = fc_frame_sid(fp);
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index c972cc2b3d5b..93c66ebad907 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -1705,6 +1705,7 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc)
 				sc->result = DID_NO_CONNECT << 16;
 				break;
 			}
+			/* fall through */
 		case ISCSI_STATE_IN_RECOVERY:
 			reason = FAILURE_SESSION_IN_RECOVERY;
 			sc->result = DID_IMM_RETRY << 16;
@@ -1832,6 +1833,7 @@ static void iscsi_tmf_timedout(struct timer_list *t)
 static int iscsi_exec_task_mgmt_fn(struct iscsi_conn *conn,
 				   struct iscsi_tm *hdr, int age,
 				   int timeout)
+	__must_hold(&session->frwd_lock)
 {
 	struct iscsi_session *session = conn->session;
 	struct iscsi_task *task;
diff --git a/drivers/scsi/libiscsi_tcp.c b/drivers/scsi/libiscsi_tcp.c
index 369ef8f23b24..4fcb9e65be57 100644
--- a/drivers/scsi/libiscsi_tcp.c
+++ b/drivers/scsi/libiscsi_tcp.c
@@ -695,7 +695,7 @@ iscsi_tcp_hdr_dissect(struct iscsi_conn *conn, struct iscsi_hdr *hdr)
 			struct scsi_data_buffer *sdb = scsi_in(task->sc);
 
 			/*
-			 * Setup copy of Data-In into the Scsi_Cmnd
+			 * Setup copy of Data-In into the struct scsi_cmnd
 			 * Scatterlist case:
 			 * We set up the iscsi_segment to point to the next
 			 * scatterlist entry to copy to. As we go along,
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index ff1d612f6fb9..64a958a99f6a 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -176,7 +176,6 @@ qc_already_gone:
 
 static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 {
-	unsigned long flags;
 	struct sas_task *task;
 	struct scatterlist *sg;
 	int ret = AC_ERR_SYSTEM;
@@ -187,10 +186,7 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 	struct Scsi_Host *host = sas_ha->core.shost;
 	struct sas_internal *i = to_sas_internal(host->transportt);
 
-	/* TODO: audit callers to ensure they are ready for qc_issue to
-	 * unconditionally re-enable interrupts
-	 */
-	local_irq_save(flags);
+	/* TODO: we should try to remove that unlock */
 	spin_unlock(ap->lock);
 
 	/* If the device fell off, no sense in issuing commands */
@@ -252,7 +248,6 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 
  out:
 	spin_lock(ap->lock);
-	local_irq_restore(flags);
 	return ret;
 }
 
@@ -557,34 +552,46 @@ int sas_ata_init(struct domain_device *found_dev)
 {
 	struct sas_ha_struct *ha = found_dev->port->ha;
 	struct Scsi_Host *shost = ha->core.shost;
+	struct ata_host *ata_host;
 	struct ata_port *ap;
 	int rc;
 
-	ata_host_init(&found_dev->sata_dev.ata_host, ha->dev, &sas_sata_ops);
-	ap = ata_sas_port_alloc(&found_dev->sata_dev.ata_host,
-				&sata_port_info,
-				shost);
+	ata_host = kzalloc(sizeof(*ata_host), GFP_KERNEL);
+	if (!ata_host)	{
+		SAS_DPRINTK("ata host alloc failed.\n");
+		return -ENOMEM;
+	}
+
+	ata_host_init(ata_host, ha->dev, &sas_sata_ops);
+
+	ap = ata_sas_port_alloc(ata_host, &sata_port_info, shost);
 	if (!ap) {
 		SAS_DPRINTK("ata_sas_port_alloc failed.\n");
-		return -ENODEV;
+		rc = -ENODEV;
+		goto free_host;
 	}
 
 	ap->private_data = found_dev;
 	ap->cbl = ATA_CBL_SATA;
 	ap->scsi_host = shost;
 	rc = ata_sas_port_init(ap);
-	if (rc) {
-		ata_sas_port_destroy(ap);
-		return rc;
-	}
-	rc = ata_sas_tport_add(found_dev->sata_dev.ata_host.dev, ap);
-	if (rc) {
-		ata_sas_port_destroy(ap);
-		return rc;
-	}
+	if (rc)
+		goto destroy_port;
+
+	rc = ata_sas_tport_add(ata_host->dev, ap);
+	if (rc)
+		goto destroy_port;
+
+	found_dev->sata_dev.ata_host = ata_host;
 	found_dev->sata_dev.ap = ap;
 
 	return 0;
+
+destroy_port:
+	ata_sas_port_destroy(ap);
+free_host:
+	ata_host_put(ata_host);
+	return rc;
 }
 
 void sas_ata_task_abort(struct sas_task *task)
diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c
index 1ffca28fe6a8..0148ae62a52a 100644
--- a/drivers/scsi/libsas/sas_discover.c
+++ b/drivers/scsi/libsas/sas_discover.c
@@ -316,6 +316,8 @@ void sas_free_device(struct kref *kref)
 	if (dev_is_sata(dev) && dev->sata_dev.ap) {
 		ata_sas_tport_delete(dev->sata_dev.ap);
 		ata_sas_port_destroy(dev->sata_dev.ap);
+		ata_host_put(dev->sata_dev.ata_host);
+		dev->sata_dev.ata_host = NULL;
 		dev->sata_dev.ap = NULL;
 	}
 
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index ceab5e5c41c2..33229348dcb6 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -759,7 +759,7 @@ retry:
 	spin_unlock_irq(shost->host_lock);
 
 	SAS_DPRINTK("Enter %s busy: %d failed: %d\n",
-		    __func__, atomic_read(&shost->host_busy), shost->host_failed);
+		    __func__, scsi_host_busy(shost), shost->host_failed);
 	/*
 	 * Deal with commands that still have SAS tasks (i.e. they didn't
 	 * complete via the normal sas_task completion mechanism),
@@ -801,7 +801,7 @@ out:
 		goto retry;
 
 	SAS_DPRINTK("--- Exit %s: busy: %d failed: %d tries: %d\n",
-		    __func__, atomic_read(&shost->host_busy),
+		    __func__, scsi_host_busy(shost),
 		    shost->host_failed, tries);
 }
 
diff --git a/drivers/scsi/lpfc/Makefile b/drivers/scsi/lpfc/Makefile
index cb6aa802c48e..092a971d066b 100644
--- a/drivers/scsi/lpfc/Makefile
+++ b/drivers/scsi/lpfc/Makefile
@@ -1,8 +1,8 @@
 #/*******************************************************************
 # * This file is part of the Emulex Linux Device Driver for         *
 # * Fibre Channel Host Bus Adapters.                                *
-# * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
-# * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+# * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+# * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
 # * Copyright (C) 2004-2012 Emulex.  All rights reserved.           *
 # * EMULEX and SLI are trademarks of Emulex.                        *
 # * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 20b249a649dd..e0d0da5f43d6 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
@@ -840,8 +840,7 @@ struct lpfc_hba {
 #define LPFC_ENABLE_FCP  1
 #define LPFC_ENABLE_NVME 2
 #define LPFC_ENABLE_BOTH 3
-	uint32_t nvme_embed_pbde;
-	uint32_t fcp_embed_pbde;
+	uint32_t cfg_enable_pbde;
 	uint32_t io_channel_irqs;	/* number of irqs for io channels */
 	struct nvmet_fc_target_port *targetport;
 	lpfc_vpd_t vpd;		/* vital product data */
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 729d343861f4..5a25553415f8 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -64,6 +64,9 @@
 #define LPFC_MIN_MRQ_POST	512
 #define LPFC_MAX_MRQ_POST	2048
 
+#define LPFC_MAX_NVME_INFO_TMP_LEN	100
+#define LPFC_NVME_INFO_MORE_STR		"\nCould be more info...\n"
+
 /*
  * Write key size should be multiple of 4. If write key is changed
  * make sure that library write key is also changed.
@@ -158,14 +161,15 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 	char *statep;
 	int i;
 	int len = 0;
+	char tmp[LPFC_MAX_NVME_INFO_TMP_LEN] = {0};
 
 	if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)) {
-		len += snprintf(buf, PAGE_SIZE, "NVME Disabled\n");
+		len = scnprintf(buf, PAGE_SIZE, "NVME Disabled\n");
 		return len;
 	}
 	if (phba->nvmet_support) {
 		if (!phba->targetport) {
-			len = snprintf(buf, PAGE_SIZE,
+			len = scnprintf(buf, PAGE_SIZE,
 					"NVME Target: x%llx is not allocated\n",
 					wwn_to_u64(vport->fc_portname.u.wwn));
 			return len;
@@ -175,135 +179,169 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 			statep = "REGISTERED";
 		else
 			statep = "INIT";
-		len += snprintf(buf + len, PAGE_SIZE - len,
-				"NVME Target Enabled  State %s\n",
-				statep);
-		len += snprintf(buf + len, PAGE_SIZE - len,
-				"%s%d WWPN x%llx WWNN x%llx DID x%06x\n",
-				"NVME Target: lpfc",
-				phba->brd_no,
-				wwn_to_u64(vport->fc_portname.u.wwn),
-				wwn_to_u64(vport->fc_nodename.u.wwn),
-				phba->targetport->port_id);
-
-		len += snprintf(buf + len, PAGE_SIZE - len,
-				"\nNVME Target: Statistics\n");
+		scnprintf(tmp, sizeof(tmp),
+			  "NVME Target Enabled  State %s\n",
+			  statep);
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp),
+			  "%s%d WWPN x%llx WWNN x%llx DID x%06x\n",
+			  "NVME Target: lpfc",
+			  phba->brd_no,
+			  wwn_to_u64(vport->fc_portname.u.wwn),
+			  wwn_to_u64(vport->fc_nodename.u.wwn),
+			  phba->targetport->port_id);
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		if (strlcat(buf, "\nNVME Target: Statistics\n", PAGE_SIZE)
+		    >= PAGE_SIZE)
+			goto buffer_done;
+
 		tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
-		len += snprintf(buf+len, PAGE_SIZE-len,
-				"LS: Rcv %08x Drop %08x Abort %08x\n",
-				atomic_read(&tgtp->rcv_ls_req_in),
-				atomic_read(&tgtp->rcv_ls_req_drop),
-				atomic_read(&tgtp->xmt_ls_abort));
+		scnprintf(tmp, sizeof(tmp),
+			  "LS: Rcv %08x Drop %08x Abort %08x\n",
+			  atomic_read(&tgtp->rcv_ls_req_in),
+			  atomic_read(&tgtp->rcv_ls_req_drop),
+			  atomic_read(&tgtp->xmt_ls_abort));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
 		if (atomic_read(&tgtp->rcv_ls_req_in) !=
 		    atomic_read(&tgtp->rcv_ls_req_out)) {
-			len += snprintf(buf+len, PAGE_SIZE-len,
-					"Rcv LS: in %08x != out %08x\n",
-					atomic_read(&tgtp->rcv_ls_req_in),
-					atomic_read(&tgtp->rcv_ls_req_out));
+			scnprintf(tmp, sizeof(tmp),
+				  "Rcv LS: in %08x != out %08x\n",
+				  atomic_read(&tgtp->rcv_ls_req_in),
+				  atomic_read(&tgtp->rcv_ls_req_out));
+			if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+				goto buffer_done;
 		}
 
-		len += snprintf(buf+len, PAGE_SIZE-len,
-				"LS: Xmt %08x Drop %08x Cmpl %08x\n",
-				atomic_read(&tgtp->xmt_ls_rsp),
-				atomic_read(&tgtp->xmt_ls_drop),
-				atomic_read(&tgtp->xmt_ls_rsp_cmpl));
-
-		len += snprintf(buf + len, PAGE_SIZE - len,
-				"LS: RSP Abort %08x xb %08x Err %08x\n",
-				atomic_read(&tgtp->xmt_ls_rsp_aborted),
-				atomic_read(&tgtp->xmt_ls_rsp_xb_set),
-				atomic_read(&tgtp->xmt_ls_rsp_error));
-
-		len += snprintf(buf+len, PAGE_SIZE-len,
-				"FCP: Rcv %08x Defer %08x Release %08x "
-				"Drop %08x\n",
-				atomic_read(&tgtp->rcv_fcp_cmd_in),
-				atomic_read(&tgtp->rcv_fcp_cmd_defer),
-				atomic_read(&tgtp->xmt_fcp_release),
-				atomic_read(&tgtp->rcv_fcp_cmd_drop));
+		scnprintf(tmp, sizeof(tmp),
+			  "LS: Xmt %08x Drop %08x Cmpl %08x\n",
+			  atomic_read(&tgtp->xmt_ls_rsp),
+			  atomic_read(&tgtp->xmt_ls_drop),
+			  atomic_read(&tgtp->xmt_ls_rsp_cmpl));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp),
+			  "LS: RSP Abort %08x xb %08x Err %08x\n",
+			  atomic_read(&tgtp->xmt_ls_rsp_aborted),
+			  atomic_read(&tgtp->xmt_ls_rsp_xb_set),
+			  atomic_read(&tgtp->xmt_ls_rsp_error));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp),
+			  "FCP: Rcv %08x Defer %08x Release %08x "
+			  "Drop %08x\n",
+			  atomic_read(&tgtp->rcv_fcp_cmd_in),
+			  atomic_read(&tgtp->rcv_fcp_cmd_defer),
+			  atomic_read(&tgtp->xmt_fcp_release),
+			  atomic_read(&tgtp->rcv_fcp_cmd_drop));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
 
 		if (atomic_read(&tgtp->rcv_fcp_cmd_in) !=
 		    atomic_read(&tgtp->rcv_fcp_cmd_out)) {
-			len += snprintf(buf+len, PAGE_SIZE-len,
-					"Rcv FCP: in %08x != out %08x\n",
-					atomic_read(&tgtp->rcv_fcp_cmd_in),
-					atomic_read(&tgtp->rcv_fcp_cmd_out));
+			scnprintf(tmp, sizeof(tmp),
+				  "Rcv FCP: in %08x != out %08x\n",
+				  atomic_read(&tgtp->rcv_fcp_cmd_in),
+				  atomic_read(&tgtp->rcv_fcp_cmd_out));
+			if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+				goto buffer_done;
 		}
 
-		len += snprintf(buf+len, PAGE_SIZE-len,
-				"FCP Rsp: RD %08x rsp %08x WR %08x rsp %08x "
-				"drop %08x\n",
-				atomic_read(&tgtp->xmt_fcp_read),
-				atomic_read(&tgtp->xmt_fcp_read_rsp),
-				atomic_read(&tgtp->xmt_fcp_write),
-				atomic_read(&tgtp->xmt_fcp_rsp),
-				atomic_read(&tgtp->xmt_fcp_drop));
-
-		len += snprintf(buf+len, PAGE_SIZE-len,
-				"FCP Rsp Cmpl: %08x err %08x drop %08x\n",
-				atomic_read(&tgtp->xmt_fcp_rsp_cmpl),
-				atomic_read(&tgtp->xmt_fcp_rsp_error),
-				atomic_read(&tgtp->xmt_fcp_rsp_drop));
-
-		len += snprintf(buf+len, PAGE_SIZE-len,
-				"FCP Rsp Abort: %08x xb %08x xricqe  %08x\n",
-				atomic_read(&tgtp->xmt_fcp_rsp_aborted),
-				atomic_read(&tgtp->xmt_fcp_rsp_xb_set),
-				atomic_read(&tgtp->xmt_fcp_xri_abort_cqe));
-
-		len += snprintf(buf + len, PAGE_SIZE - len,
-				"ABORT: Xmt %08x Cmpl %08x\n",
-				atomic_read(&tgtp->xmt_fcp_abort),
-				atomic_read(&tgtp->xmt_fcp_abort_cmpl));
-
-		len += snprintf(buf + len, PAGE_SIZE - len,
-				"ABORT: Sol %08x  Usol %08x Err %08x Cmpl %08x",
-				atomic_read(&tgtp->xmt_abort_sol),
-				atomic_read(&tgtp->xmt_abort_unsol),
-				atomic_read(&tgtp->xmt_abort_rsp),
-				atomic_read(&tgtp->xmt_abort_rsp_error));
-
-		len += snprintf(buf + len, PAGE_SIZE - len,
-				"DELAY: ctx %08x  fod %08x wqfull %08x\n",
-				atomic_read(&tgtp->defer_ctx),
-				atomic_read(&tgtp->defer_fod),
-				atomic_read(&tgtp->defer_wqfull));
+		scnprintf(tmp, sizeof(tmp),
+			  "FCP Rsp: RD %08x rsp %08x WR %08x rsp %08x "
+			  "drop %08x\n",
+			  atomic_read(&tgtp->xmt_fcp_read),
+			  atomic_read(&tgtp->xmt_fcp_read_rsp),
+			  atomic_read(&tgtp->xmt_fcp_write),
+			  atomic_read(&tgtp->xmt_fcp_rsp),
+			  atomic_read(&tgtp->xmt_fcp_drop));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp),
+			  "FCP Rsp Cmpl: %08x err %08x drop %08x\n",
+			  atomic_read(&tgtp->xmt_fcp_rsp_cmpl),
+			  atomic_read(&tgtp->xmt_fcp_rsp_error),
+			  atomic_read(&tgtp->xmt_fcp_rsp_drop));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp),
+			  "FCP Rsp Abort: %08x xb %08x xricqe  %08x\n",
+			  atomic_read(&tgtp->xmt_fcp_rsp_aborted),
+			  atomic_read(&tgtp->xmt_fcp_rsp_xb_set),
+			  atomic_read(&tgtp->xmt_fcp_xri_abort_cqe));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp),
+			  "ABORT: Xmt %08x Cmpl %08x\n",
+			  atomic_read(&tgtp->xmt_fcp_abort),
+			  atomic_read(&tgtp->xmt_fcp_abort_cmpl));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp),
+			  "ABORT: Sol %08x  Usol %08x Err %08x Cmpl %08x\n",
+			  atomic_read(&tgtp->xmt_abort_sol),
+			  atomic_read(&tgtp->xmt_abort_unsol),
+			  atomic_read(&tgtp->xmt_abort_rsp),
+			  atomic_read(&tgtp->xmt_abort_rsp_error));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp),
+			  "DELAY: ctx %08x  fod %08x wqfull %08x\n",
+			  atomic_read(&tgtp->defer_ctx),
+			  atomic_read(&tgtp->defer_fod),
+			  atomic_read(&tgtp->defer_wqfull));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
 
 		/* Calculate outstanding IOs */
 		tot = atomic_read(&tgtp->rcv_fcp_cmd_drop);
 		tot += atomic_read(&tgtp->xmt_fcp_release);
 		tot = atomic_read(&tgtp->rcv_fcp_cmd_in) - tot;
 
-		len += snprintf(buf + len, PAGE_SIZE - len,
-				"IO_CTX: %08x  WAIT: cur %08x tot %08x\n"
-				"CTX Outstanding %08llx\n",
-				phba->sli4_hba.nvmet_xri_cnt,
-				phba->sli4_hba.nvmet_io_wait_cnt,
-				phba->sli4_hba.nvmet_io_wait_total,
-				tot);
-
-		len +=  snprintf(buf+len, PAGE_SIZE-len, "\n");
-		return len;
+		scnprintf(tmp, sizeof(tmp),
+			  "IO_CTX: %08x  WAIT: cur %08x tot %08x\n"
+			  "CTX Outstanding %08llx\n\n",
+			  phba->sli4_hba.nvmet_xri_cnt,
+			  phba->sli4_hba.nvmet_io_wait_cnt,
+			  phba->sli4_hba.nvmet_io_wait_total,
+			  tot);
+		strlcat(buf, tmp, PAGE_SIZE);
+		goto buffer_done;
 	}
 
 	localport = vport->localport;
 	if (!localport) {
-		len = snprintf(buf, PAGE_SIZE,
+		len = scnprintf(buf, PAGE_SIZE,
 				"NVME Initiator x%llx is not allocated\n",
 				wwn_to_u64(vport->fc_portname.u.wwn));
 		return len;
 	}
 	lport = (struct lpfc_nvme_lport *)localport->private;
-	len = snprintf(buf, PAGE_SIZE, "NVME Initiator Enabled\n");
-
-	spin_lock_irq(shost->host_lock);
-	len += snprintf(buf + len, PAGE_SIZE - len,
-			"XRI Dist lpfc%d Total %d NVME %d SCSI %d ELS %d\n",
-			phba->brd_no,
-			phba->sli4_hba.max_cfg_param.max_xri,
-			phba->sli4_hba.nvme_xri_max,
-			phba->sli4_hba.scsi_xri_max,
-			lpfc_sli4_get_els_iocb_cnt(phba));
+	if (strlcat(buf, "\nNVME Initiator Enabled\n", PAGE_SIZE) >= PAGE_SIZE)
+		goto buffer_done;
+
+	rcu_read_lock();
+	scnprintf(tmp, sizeof(tmp),
+		  "XRI Dist lpfc%d Total %d NVME %d SCSI %d ELS %d\n",
+		  phba->brd_no,
+		  phba->sli4_hba.max_cfg_param.max_xri,
+		  phba->sli4_hba.nvme_xri_max,
+		  phba->sli4_hba.scsi_xri_max,
+		  lpfc_sli4_get_els_iocb_cnt(phba));
+	if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+		goto buffer_done;
 
 	/* Port state is only one of two values for now. */
 	if (localport->port_id)
@@ -311,13 +349,15 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 	else
 		statep = "UNKNOWN ";
 
-	len += snprintf(buf + len, PAGE_SIZE - len,
-			"%s%d WWPN x%llx WWNN x%llx DID x%06x %s\n",
-			"NVME LPORT lpfc",
-			phba->brd_no,
-			wwn_to_u64(vport->fc_portname.u.wwn),
-			wwn_to_u64(vport->fc_nodename.u.wwn),
-			localport->port_id, statep);
+	scnprintf(tmp, sizeof(tmp),
+		  "%s%d WWPN x%llx WWNN x%llx DID x%06x %s\n",
+		  "NVME LPORT lpfc",
+		  phba->brd_no,
+		  wwn_to_u64(vport->fc_portname.u.wwn),
+		  wwn_to_u64(vport->fc_nodename.u.wwn),
+		  localport->port_id, statep);
+	if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+		goto buffer_done;
 
 	list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) {
 		rport = lpfc_ndlp_get_nrport(ndlp);
@@ -343,56 +383,77 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 		}
 
 		/* Tab in to show lport ownership. */
-		len += snprintf(buf + len, PAGE_SIZE - len,
-				"NVME RPORT       ");
-		if (phba->brd_no >= 10)
-			len += snprintf(buf + len, PAGE_SIZE - len, " ");
-
-		len += snprintf(buf + len, PAGE_SIZE - len, "WWPN x%llx ",
-				nrport->port_name);
-		len += snprintf(buf + len, PAGE_SIZE - len, "WWNN x%llx ",
-				nrport->node_name);
-		len += snprintf(buf + len, PAGE_SIZE - len, "DID x%06x ",
-				nrport->port_id);
+		if (strlcat(buf, "NVME RPORT       ", PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+		if (phba->brd_no >= 10) {
+			if (strlcat(buf, " ", PAGE_SIZE) >= PAGE_SIZE)
+				goto buffer_done;
+		}
+
+		scnprintf(tmp, sizeof(tmp), "WWPN x%llx ",
+			  nrport->port_name);
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp), "WWNN x%llx ",
+			  nrport->node_name);
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp), "DID x%06x ",
+			  nrport->port_id);
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
 
 		/* An NVME rport can have multiple roles. */
-		if (nrport->port_role & FC_PORT_ROLE_NVME_INITIATOR)
-			len +=  snprintf(buf + len, PAGE_SIZE - len,
-					 "INITIATOR ");
-		if (nrport->port_role & FC_PORT_ROLE_NVME_TARGET)
-			len +=  snprintf(buf + len, PAGE_SIZE - len,
-					 "TARGET ");
-		if (nrport->port_role & FC_PORT_ROLE_NVME_DISCOVERY)
-			len +=  snprintf(buf + len, PAGE_SIZE - len,
-					 "DISCSRVC ");
+		if (nrport->port_role & FC_PORT_ROLE_NVME_INITIATOR) {
+			if (strlcat(buf, "INITIATOR ", PAGE_SIZE) >= PAGE_SIZE)
+				goto buffer_done;
+		}
+		if (nrport->port_role & FC_PORT_ROLE_NVME_TARGET) {
+			if (strlcat(buf, "TARGET ", PAGE_SIZE) >= PAGE_SIZE)
+				goto buffer_done;
+		}
+		if (nrport->port_role & FC_PORT_ROLE_NVME_DISCOVERY) {
+			if (strlcat(buf, "DISCSRVC ", PAGE_SIZE) >= PAGE_SIZE)
+				goto buffer_done;
+		}
 		if (nrport->port_role & ~(FC_PORT_ROLE_NVME_INITIATOR |
 					  FC_PORT_ROLE_NVME_TARGET |
-					  FC_PORT_ROLE_NVME_DISCOVERY))
-			len +=  snprintf(buf + len, PAGE_SIZE - len,
-					 "UNKNOWN ROLE x%x",
-					 nrport->port_role);
-
-		len +=  snprintf(buf + len, PAGE_SIZE - len, "%s  ", statep);
-		/* Terminate the string. */
-		len +=  snprintf(buf + len, PAGE_SIZE - len, "\n");
+					  FC_PORT_ROLE_NVME_DISCOVERY)) {
+			scnprintf(tmp, sizeof(tmp), "UNKNOWN ROLE x%x",
+				  nrport->port_role);
+			if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+				goto buffer_done;
+		}
+
+		scnprintf(tmp, sizeof(tmp), "%s\n", statep);
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
 	}
-	spin_unlock_irq(shost->host_lock);
+	rcu_read_unlock();
 
 	if (!lport)
-		return len;
-
-	len += snprintf(buf + len, PAGE_SIZE - len, "\nNVME Statistics\n");
-	len += snprintf(buf+len, PAGE_SIZE-len,
-			"LS: Xmt %010x Cmpl %010x Abort %08x\n",
-			atomic_read(&lport->fc4NvmeLsRequests),
-			atomic_read(&lport->fc4NvmeLsCmpls),
-			atomic_read(&lport->xmt_ls_abort));
-
-	len += snprintf(buf + len, PAGE_SIZE - len,
-			"LS XMIT: Err %08x  CMPL: xb %08x Err %08x\n",
-			atomic_read(&lport->xmt_ls_err),
-			atomic_read(&lport->cmpl_ls_xb),
-			atomic_read(&lport->cmpl_ls_err));
+		goto buffer_done;
+
+	if (strlcat(buf, "\nNVME Statistics\n", PAGE_SIZE) >= PAGE_SIZE)
+		goto buffer_done;
+
+	scnprintf(tmp, sizeof(tmp),
+		  "LS: Xmt %010x Cmpl %010x Abort %08x\n",
+		  atomic_read(&lport->fc4NvmeLsRequests),
+		  atomic_read(&lport->fc4NvmeLsCmpls),
+		  atomic_read(&lport->xmt_ls_abort));
+	if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+		goto buffer_done;
+
+	scnprintf(tmp, sizeof(tmp),
+		  "LS XMIT: Err %08x  CMPL: xb %08x Err %08x\n",
+		  atomic_read(&lport->xmt_ls_err),
+		  atomic_read(&lport->cmpl_ls_xb),
+		  atomic_read(&lport->cmpl_ls_err));
+	if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+		goto buffer_done;
 
 	totin = 0;
 	totout = 0;
@@ -405,25 +466,46 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 		data3 = atomic_read(&cstat->fc4NvmeControlRequests);
 		totout += (data1 + data2 + data3);
 	}
-	len += snprintf(buf+len, PAGE_SIZE-len,
-			"Total FCP Cmpl %016llx Issue %016llx "
-			"OutIO %016llx\n",
-			totin, totout, totout - totin);
-
-	len += snprintf(buf+len, PAGE_SIZE-len,
-			"      abort %08x noxri %08x nondlp %08x qdepth %08x "
-			"wqerr %08x err %08x\n",
-			atomic_read(&lport->xmt_fcp_abort),
-			atomic_read(&lport->xmt_fcp_noxri),
-			atomic_read(&lport->xmt_fcp_bad_ndlp),
-			atomic_read(&lport->xmt_fcp_qdepth),
-			atomic_read(&lport->xmt_fcp_err),
-			atomic_read(&lport->xmt_fcp_wqerr));
-
-	len += snprintf(buf + len, PAGE_SIZE - len,
-			"FCP CMPL: xb %08x Err %08x\n",
-			atomic_read(&lport->cmpl_fcp_xb),
-			atomic_read(&lport->cmpl_fcp_err));
+	scnprintf(tmp, sizeof(tmp),
+		  "Total FCP Cmpl %016llx Issue %016llx "
+		  "OutIO %016llx\n",
+		  totin, totout, totout - totin);
+	if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+		goto buffer_done;
+
+	scnprintf(tmp, sizeof(tmp),
+		  "\tabort %08x noxri %08x nondlp %08x qdepth %08x "
+		  "wqerr %08x err %08x\n",
+		  atomic_read(&lport->xmt_fcp_abort),
+		  atomic_read(&lport->xmt_fcp_noxri),
+		  atomic_read(&lport->xmt_fcp_bad_ndlp),
+		  atomic_read(&lport->xmt_fcp_qdepth),
+		  atomic_read(&lport->xmt_fcp_err),
+		  atomic_read(&lport->xmt_fcp_wqerr));
+	if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+		goto buffer_done;
+
+	scnprintf(tmp, sizeof(tmp),
+		  "FCP CMPL: xb %08x Err %08x\n",
+		  atomic_read(&lport->cmpl_fcp_xb),
+		  atomic_read(&lport->cmpl_fcp_err));
+	strlcat(buf, tmp, PAGE_SIZE);
+
+buffer_done:
+	len = strnlen(buf, PAGE_SIZE);
+
+	if (unlikely(len >= (PAGE_SIZE - 1))) {
+		lpfc_printf_log(phba, KERN_INFO, LOG_NVME,
+				"6314 Catching potential buffer "
+				"overflow > PAGE_SIZE = %lu bytes\n",
+				PAGE_SIZE);
+		strlcpy(buf + PAGE_SIZE - 1 -
+			strnlen(LPFC_NVME_INFO_MORE_STR, PAGE_SIZE - 1),
+			LPFC_NVME_INFO_MORE_STR,
+			strnlen(LPFC_NVME_INFO_MORE_STR, PAGE_SIZE - 1)
+			+ 1);
+	}
+
 	return len;
 }
 
@@ -5836,6 +5918,24 @@ lpfc_get_host_speed(struct Scsi_Host *shost)
 			fc_host_speed(shost) = FC_PORTSPEED_UNKNOWN;
 			break;
 		}
+	} else if (lpfc_is_link_up(phba) && (phba->hba_flag & HBA_FCOE_MODE)) {
+		switch (phba->fc_linkspeed) {
+		case LPFC_ASYNC_LINK_SPEED_10GBPS:
+			fc_host_speed(shost) = FC_PORTSPEED_10GBIT;
+			break;
+		case LPFC_ASYNC_LINK_SPEED_25GBPS:
+			fc_host_speed(shost) = FC_PORTSPEED_25GBIT;
+			break;
+		case LPFC_ASYNC_LINK_SPEED_40GBPS:
+			fc_host_speed(shost) = FC_PORTSPEED_40GBIT;
+			break;
+		case LPFC_ASYNC_LINK_SPEED_100GBPS:
+			fc_host_speed(shost) = FC_PORTSPEED_100GBIT;
+			break;
+		default:
+			fc_host_speed(shost) = FC_PORTSPEED_UNKNOWN;
+			break;
+		}
 	} else
 		fc_host_speed(shost) = FC_PORTSPEED_UNKNOWN;
 
@@ -5891,7 +5991,6 @@ lpfc_get_stats(struct Scsi_Host *shost)
 	struct lpfc_lnk_stat * lso = &psli->lnk_stat_offsets;
 	LPFC_MBOXQ_t *pmboxq;
 	MAILBOX_t *pmb;
-	unsigned long seconds;
 	int rc = 0;
 
 	/*
@@ -5992,12 +6091,7 @@ lpfc_get_stats(struct Scsi_Host *shost)
 
 	hs->dumped_frames = -1;
 
-	seconds = get_seconds();
-	if (seconds < psli->stats_start)
-		hs->seconds_since_last_reset = seconds +
-				((unsigned long)-1 - psli->stats_start);
-	else
-		hs->seconds_since_last_reset = seconds - psli->stats_start;
+	hs->seconds_since_last_reset = ktime_get_seconds() - psli->stats_start;
 
 	mempool_free(pmboxq, phba->mbox_mem_pool);
 
@@ -6076,7 +6170,7 @@ lpfc_reset_stats(struct Scsi_Host *shost)
 	else
 		lso->link_events = (phba->fc_eventTag >> 1);
 
-	psli->stats_start = get_seconds();
+	psli->stats_start = ktime_get_seconds();
 
 	mempool_free(pmboxq, phba->mbox_mem_pool);
 
@@ -6454,6 +6548,8 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 		phba->cfg_auto_imax = 0;
 	phba->initial_imax = phba->cfg_fcp_imax;
 
+	phba->cfg_enable_pbde = 0;
+
 	/* A value of 0 means use the number of CPUs found in the system */
 	if (phba->cfg_fcp_io_channel == 0)
 		phba->cfg_fcp_io_channel = phba->sli4_hba.num_present_cpu;
diff --git a/drivers/scsi/lpfc/lpfc_attr.h b/drivers/scsi/lpfc/lpfc_attr.h
index 931db52692f5..9659a8fff971 100644
--- a/drivers/scsi/lpfc/lpfc_attr.h
+++ b/drivers/scsi/lpfc/lpfc_attr.h
@@ -1,8 +1,8 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index edb1a18a6414..90745feca808 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2009-2015 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_bsg.h b/drivers/scsi/lpfc/lpfc_bsg.h
index e7d95a4e8042..32347c87e3b4 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.h
+++ b/drivers/scsi/lpfc/lpfc_bsg.h
@@ -1,8 +1,8 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2010-2015 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_compat.h b/drivers/scsi/lpfc/lpfc_compat.h
index 6b32b0ae7506..43cf46a3a71f 100644
--- a/drivers/scsi/lpfc/lpfc_compat.h
+++ b/drivers/scsi/lpfc/lpfc_compat.h
@@ -1,8 +1,8 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2011 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index 4ae9ba425e78..bea24bc4410a 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
@@ -469,7 +469,6 @@ int lpfc_parse_vpd(struct lpfc_hba *, uint8_t *, int);
 void lpfc_start_fdiscs(struct lpfc_hba *phba);
 struct lpfc_vport *lpfc_find_vport_by_vpid(struct lpfc_hba *, uint16_t);
 struct lpfc_sglq *__lpfc_get_active_sglq(struct lpfc_hba *, uint16_t);
-#define ScsiResult(host_code, scsi_code) (((host_code) << 16) | scsi_code)
 #define HBA_EVENT_RSCN                   5
 #define HBA_EVENT_LINK_UP                2
 #define HBA_EVENT_LINK_DOWN              3
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index d4a200ae5a6f..1cbdc892ff95 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.h b/drivers/scsi/lpfc/lpfc_debugfs.h
index f32eaeb2225a..30efc7bf91bd 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.h
+++ b/drivers/scsi/lpfc/lpfc_debugfs.h
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2007-2011 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h
index 5a7547f9d8d8..28e2b60fc5c0 100644
--- a/drivers/scsi/lpfc/lpfc_disc.h
+++ b/drivers/scsi/lpfc/lpfc_disc.h
@@ -1,8 +1,8 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
@@ -150,6 +150,9 @@ struct lpfc_node_rrq {
 	unsigned long rrq_stop_time;
 };
 
+#define lpfc_ndlp_check_qdepth(phba, ndlp) \
+	(ndlp->cmd_qdepth < phba->sli4_hba.max_cfg_param.max_xri)
+
 /* Defines for nlp_flag (uint32) */
 #define NLP_IGNR_REG_CMPL  0x00000001 /* Rcvd rscn before we cmpl reg login */
 #define NLP_REG_LOGIN_SEND 0x00000002   /* sent reglogin to adapter */
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 6d84a10fef07..4dda969e947c 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
@@ -5640,8 +5640,9 @@ lpfc_els_lcb_rsp(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 				" mbx status x%x\n",
 				shdr_status, shdr_add_status, mb->mbxStatus);
 
-	if (mb->mbxStatus && !(shdr_status &&
-		shdr_add_status == ADD_STATUS_OPERATION_ALREADY_ACTIVE)) {
+	if ((mb->mbxStatus != MBX_SUCCESS) || shdr_status ||
+	    (shdr_add_status == ADD_STATUS_OPERATION_ALREADY_ACTIVE) ||
+	    (shdr_add_status == ADD_STATUS_INVALID_REQUEST)) {
 		mempool_free(pmb, phba->mbox_mem_pool);
 		goto error;
 	}
@@ -5661,6 +5662,7 @@ lpfc_els_lcb_rsp(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	lcb_res = (struct fc_lcb_res_frame *)
 		(((struct lpfc_dmabuf *)elsiocb->context2)->virt);
 
+	memset(lcb_res, 0, sizeof(struct fc_lcb_res_frame));
 	icmd = &elsiocb->iocb;
 	icmd->ulpContext = lcb_context->rx_id;
 	icmd->unsli3.rcvsli3.ox_id = lcb_context->ox_id;
@@ -5669,7 +5671,9 @@ lpfc_els_lcb_rsp(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	*((uint32_t *)(pcmd)) = ELS_CMD_ACC;
 	lcb_res->lcb_sub_command = lcb_context->sub_command;
 	lcb_res->lcb_type = lcb_context->type;
+	lcb_res->capability = lcb_context->capability;
 	lcb_res->lcb_frequency = lcb_context->frequency;
+	lcb_res->lcb_duration = lcb_context->duration;
 	elsiocb->iocb_cmpl = lpfc_cmpl_els_rsp;
 	phba->fc_stat.elsXmitACC++;
 	rc = lpfc_sli_issue_iocb(phba, LPFC_ELS_RING, elsiocb, 0);
@@ -5712,6 +5716,7 @@ lpfc_sli4_set_beacon(struct lpfc_vport *vport,
 		     uint32_t beacon_state)
 {
 	struct lpfc_hba *phba = vport->phba;
+	union lpfc_sli4_cfg_shdr *cfg_shdr;
 	LPFC_MBOXQ_t *mbox = NULL;
 	uint32_t len;
 	int rc;
@@ -5720,6 +5725,7 @@ lpfc_sli4_set_beacon(struct lpfc_vport *vport,
 	if (!mbox)
 		return 1;
 
+	cfg_shdr = &mbox->u.mqe.un.sli4_config.header.cfg_shdr;
 	len = sizeof(struct lpfc_mbx_set_beacon_config) -
 		sizeof(struct lpfc_sli4_cfg_mhdr);
 	lpfc_sli4_config(phba, mbox, LPFC_MBOX_SUBSYSTEM_COMMON,
@@ -5732,8 +5738,40 @@ lpfc_sli4_set_beacon(struct lpfc_vport *vport,
 	       phba->sli4_hba.physical_port);
 	bf_set(lpfc_mbx_set_beacon_state, &mbox->u.mqe.un.beacon_config,
 	       beacon_state);
-	bf_set(lpfc_mbx_set_beacon_port_type, &mbox->u.mqe.un.beacon_config, 1);
-	bf_set(lpfc_mbx_set_beacon_duration, &mbox->u.mqe.un.beacon_config, 0);
+	mbox->u.mqe.un.beacon_config.word5 = 0;		/* Reserved */
+
+	/*
+	 *	Check bv1s bit before issuing the mailbox
+	 *	if bv1s == 1, LCB V1 supported
+	 *	else, LCB V0 supported
+	 */
+
+	if (phba->sli4_hba.pc_sli4_params.bv1s) {
+		/* COMMON_SET_BEACON_CONFIG_V1 */
+		cfg_shdr->request.word9 = BEACON_VERSION_V1;
+		lcb_context->capability |= LCB_CAPABILITY_DURATION;
+		bf_set(lpfc_mbx_set_beacon_port_type,
+		       &mbox->u.mqe.un.beacon_config, 0);
+		bf_set(lpfc_mbx_set_beacon_duration_v1,
+		       &mbox->u.mqe.un.beacon_config,
+		       be16_to_cpu(lcb_context->duration));
+	} else {
+		/* COMMON_SET_BEACON_CONFIG_V0 */
+		if (be16_to_cpu(lcb_context->duration) != 0) {
+			mempool_free(mbox, phba->mbox_mem_pool);
+			return 1;
+		}
+		cfg_shdr->request.word9 = BEACON_VERSION_V0;
+		lcb_context->capability &=  ~(LCB_CAPABILITY_DURATION);
+		bf_set(lpfc_mbx_set_beacon_state,
+		       &mbox->u.mqe.un.beacon_config, beacon_state);
+		bf_set(lpfc_mbx_set_beacon_port_type,
+		       &mbox->u.mqe.un.beacon_config, 1);
+		bf_set(lpfc_mbx_set_beacon_duration,
+		       &mbox->u.mqe.un.beacon_config,
+		       be16_to_cpu(lcb_context->duration));
+	}
+
 	rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
 	if (rc == MBX_NOT_FINISHED) {
 		mempool_free(mbox, phba->mbox_mem_pool);
@@ -5784,24 +5822,16 @@ lpfc_els_rcv_lcb(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 			beacon->lcb_frequency,
 			be16_to_cpu(beacon->lcb_duration));
 
-	if (phba->sli_rev < LPFC_SLI_REV4 ||
-	    (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) !=
-	    LPFC_SLI_INTF_IF_TYPE_2)) {
-		rjt_err = LSRJT_CMD_UNSUPPORTED;
-		goto rjt;
-	}
-
-	if (phba->hba_flag & HBA_FCOE_MODE) {
-		rjt_err = LSRJT_CMD_UNSUPPORTED;
-		goto rjt;
-	}
 	if (beacon->lcb_sub_command != LPFC_LCB_ON &&
 	    beacon->lcb_sub_command != LPFC_LCB_OFF) {
 		rjt_err = LSRJT_CMD_UNSUPPORTED;
 		goto rjt;
 	}
-	if (beacon->lcb_sub_command == LPFC_LCB_ON &&
-	    be16_to_cpu(beacon->lcb_duration) != 0) {
+
+	if (phba->sli_rev < LPFC_SLI_REV4  ||
+	    phba->hba_flag & HBA_FCOE_MODE ||
+	    (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) <
+	    LPFC_SLI_INTF_IF_TYPE_2)) {
 		rjt_err = LSRJT_CMD_UNSUPPORTED;
 		goto rjt;
 	}
@@ -5814,8 +5844,10 @@ lpfc_els_rcv_lcb(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 
 	state = (beacon->lcb_sub_command == LPFC_LCB_ON) ? 1 : 0;
 	lcb_context->sub_command = beacon->lcb_sub_command;
+	lcb_context->capability	= 0;
 	lcb_context->type = beacon->lcb_type;
 	lcb_context->frequency = beacon->lcb_frequency;
+	lcb_context->duration = beacon->lcb_duration;
 	lcb_context->ox_id = cmdiocb->iocb.unsli3.rcvsli3.ox_id;
 	lcb_context->rx_id = cmdiocb->iocb.ulpContext;
 	lcb_context->ndlp = lpfc_nlp_get(ndlp);
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 2fef54fab86d..eb71877f12f8 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h
index 08a3f1520159..009aa0eee040 100644
--- a/drivers/scsi/lpfc/lpfc_hw.h
+++ b/drivers/scsi/lpfc/lpfc_hw.h
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
@@ -1065,14 +1065,17 @@ typedef struct _ELS_PKT {	/* Structure is in Big Endian format */
 struct fc_lcb_request_frame {
 	uint32_t      lcb_command;      /* ELS command opcode (0x81)     */
 	uint8_t       lcb_sub_command;/* LCB Payload Word 1, bit 24:31 */
-#define LPFC_LCB_ON    0x1
-#define LPFC_LCB_OFF   0x2
-	uint8_t       reserved[3];
-
+#define LPFC_LCB_ON		0x1
+#define LPFC_LCB_OFF		0x2
+	uint8_t       reserved[2];
+	uint8_t	      capability;	/* LCB Payload Word 1, bit 0:7 */
 	uint8_t       lcb_type; /* LCB Payload Word 2, bit 24:31 */
-#define LPFC_LCB_GREEN 0x1
-#define LPFC_LCB_AMBER 0x2
+#define LPFC_LCB_GREEN		0x1
+#define LPFC_LCB_AMBER		0x2
 	uint8_t       lcb_frequency;    /* LCB Payload Word 2, bit 16:23 */
+#define LCB_CAPABILITY_DURATION	1
+#define BEACON_VERSION_V1	1
+#define BEACON_VERSION_V0	0
 	uint16_t      lcb_duration;     /* LCB Payload Word 2, bit 15:0  */
 };
 
@@ -1082,7 +1085,8 @@ struct fc_lcb_request_frame {
 struct fc_lcb_res_frame {
 	uint32_t      lcb_ls_acc;       /* Acceptance of LCB request (0x02) */
 	uint8_t       lcb_sub_command;/* LCB Payload Word 1, bit 24:31 */
-	uint8_t       reserved[3];
+	uint8_t       reserved[2];
+	uint8_t	      capability;	/* LCB Payload Word 1, bit 0:7 */
 	uint8_t       lcb_type; /* LCB Payload Word 2, bit 24:31 */
 	uint8_t       lcb_frequency;    /* LCB Payload Word 2, bit 16:23 */
 	uint16_t      lcb_duration;     /* LCB Payload Word 2, bit 15:0  */
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index f43f0bacb77a..083f8c8706e5 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -1790,9 +1790,12 @@ struct lpfc_mbx_set_beacon_config {
 #define lpfc_mbx_set_beacon_duration_SHIFT		16
 #define lpfc_mbx_set_beacon_duration_MASK		0x000000FF
 #define lpfc_mbx_set_beacon_duration_WORD		word4
-#define lpfc_mbx_set_beacon_status_duration_SHIFT	24
-#define lpfc_mbx_set_beacon_status_duration_MASK	0x000000FF
-#define lpfc_mbx_set_beacon_status_duration_WORD	word4
+
+/* COMMON_SET_BEACON_CONFIG_V1 */
+#define lpfc_mbx_set_beacon_duration_v1_SHIFT		16
+#define lpfc_mbx_set_beacon_duration_v1_MASK		0x0000FFFF
+#define lpfc_mbx_set_beacon_duration_v1_WORD		word4
+	uint32_t word5;  /* RESERVED  */
 };
 
 struct lpfc_id_range {
@@ -2243,6 +2246,7 @@ struct lpfc_mbx_redisc_fcf_tbl {
  */
 #define ADD_STATUS_OPERATION_ALREADY_ACTIVE		0x67
 #define ADD_STATUS_FW_NOT_SUPPORTED			0xEB
+#define ADD_STATUS_INVALID_REQUEST			0x4B
 
 struct lpfc_mbx_sli4_config {
 	struct mbox_header header;
@@ -3392,7 +3396,41 @@ struct lpfc_sli4_parameters {
 #define cfg_nosr_SHIFT				9
 #define cfg_nosr_MASK				0x00000001
 #define cfg_nosr_WORD				word19
-#define LPFC_NODELAY_MAX_IO		32
+
+#define cfg_bv1s_SHIFT                          10
+#define cfg_bv1s_MASK                           0x00000001
+#define cfg_bv1s_WORD                           word19
+
+	uint32_t word20;
+#define cfg_max_tow_xri_SHIFT			0
+#define cfg_max_tow_xri_MASK			0x0000ffff
+#define cfg_max_tow_xri_WORD			word20
+
+	uint32_t word21;                        /* RESERVED */
+	uint32_t word22;                        /* RESERVED */
+	uint32_t word23;                        /* RESERVED */
+
+	uint32_t word24;
+#define cfg_frag_field_offset_SHIFT		0
+#define cfg_frag_field_offset_MASK		0x0000ffff
+#define cfg_frag_field_offset_WORD		word24
+
+#define cfg_frag_field_size_SHIFT		16
+#define cfg_frag_field_size_MASK		0x0000ffff
+#define cfg_frag_field_size_WORD		word24
+
+	uint32_t word25;
+#define cfg_sgl_field_offset_SHIFT		0
+#define cfg_sgl_field_offset_MASK		0x0000ffff
+#define cfg_sgl_field_offset_WORD		word25
+
+#define cfg_sgl_field_size_SHIFT		16
+#define cfg_sgl_field_size_MASK			0x0000ffff
+#define cfg_sgl_field_size_WORD			word25
+
+	uint32_t word26;	/* Chain SGE initial value LOW  */
+	uint32_t word27;	/* Chain SGE initial value HIGH */
+#define LPFC_NODELAY_MAX_IO			32
 };
 
 #define LPFC_SET_UE_RECOVERY		0x10
diff --git a/drivers/scsi/lpfc/lpfc_ids.h b/drivers/scsi/lpfc/lpfc_ids.h
index 07ee34017d88..d48414e295a0 100644
--- a/drivers/scsi/lpfc/lpfc_ids.h
+++ b/drivers/scsi/lpfc/lpfc_ids.h
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 52cae87da0d2..f3cae733ae2d 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -10387,6 +10387,11 @@ lpfc_sli4_xri_exchange_busy_wait(struct lpfc_hba *phba)
 	while (!fcp_xri_cmpl || !els_xri_cmpl || !nvme_xri_cmpl ||
 	       !nvmet_xri_cmpl) {
 		if (wait_time > LPFC_XRI_EXCH_BUSY_WAIT_TMO) {
+			if (!nvmet_xri_cmpl)
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+						"6424 NVMET XRI exchange busy "
+						"wait time: %d seconds.\n",
+						wait_time/1000);
 			if (!nvme_xri_cmpl)
 				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 						"6100 NVME XRI exchange busy "
@@ -10639,6 +10644,7 @@ lpfc_get_sli4_parameters(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 	sli4_params->eqav = bf_get(cfg_eqav, mbx_sli4_parameters);
 	sli4_params->cqav = bf_get(cfg_cqav, mbx_sli4_parameters);
 	sli4_params->wqsize = bf_get(cfg_wqsize, mbx_sli4_parameters);
+	sli4_params->bv1s = bf_get(cfg_bv1s, mbx_sli4_parameters);
 	sli4_params->sgl_pages_max = bf_get(cfg_sgl_page_cnt,
 					    mbx_sli4_parameters);
 	sli4_params->wqpcnt = bf_get(cfg_wqpcnt, mbx_sli4_parameters);
@@ -10668,18 +10674,10 @@ lpfc_get_sli4_parameters(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 		phba->cfg_enable_fc4_type = LPFC_ENABLE_FCP;
 	}
 
-	/* Only embed PBDE for if_type 6 */
-	if (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) ==
-	    LPFC_SLI_INTF_IF_TYPE_6) {
-		phba->fcp_embed_pbde = 1;
-		phba->nvme_embed_pbde = 1;
-	}
-
-	/* PBDE support requires xib be set */
-	if (!bf_get(cfg_xib, mbx_sli4_parameters)) {
-		phba->fcp_embed_pbde = 0;
-		phba->nvme_embed_pbde = 0;
-	}
+	/* Only embed PBDE for if_type 6, PBDE support requires xib be set */
+	if ((bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) !=
+	    LPFC_SLI_INTF_IF_TYPE_6) || (!bf_get(cfg_xib, mbx_sli4_parameters)))
+		phba->cfg_enable_pbde = 0;
 
 	/*
 	 * To support Suppress Response feature we must satisfy 3 conditions.
@@ -10713,10 +10711,10 @@ lpfc_get_sli4_parameters(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 		phba->fcp_embed_io = 0;
 
 	lpfc_printf_log(phba, KERN_INFO, LOG_INIT | LOG_NVME,
-			"6422 XIB %d: FCP %d %d NVME %d %d %d %d\n",
+			"6422 XIB %d PBDE %d: FCP %d NVME %d %d %d\n",
 			bf_get(cfg_xib, mbx_sli4_parameters),
-			phba->fcp_embed_pbde, phba->fcp_embed_io,
-			phba->nvme_support, phba->nvme_embed_pbde,
+			phba->cfg_enable_pbde,
+			phba->fcp_embed_io, phba->nvme_support,
 			phba->cfg_nvme_embed_cmd, phba->cfg_suppress_rsp);
 
 	if ((bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) ==
diff --git a/drivers/scsi/lpfc/lpfc_logmsg.h b/drivers/scsi/lpfc/lpfc_logmsg.h
index 3b654ad08d1f..ea10f03437f5 100644
--- a/drivers/scsi/lpfc/lpfc_logmsg.h
+++ b/drivers/scsi/lpfc/lpfc_logmsg.h
@@ -1,8 +1,8 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2009 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_mbox.c b/drivers/scsi/lpfc/lpfc_mbox.c
index 47c02da11f01..deb094fdbb79 100644
--- a/drivers/scsi/lpfc/lpfc_mbox.c
+++ b/drivers/scsi/lpfc/lpfc_mbox.c
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_mem.c b/drivers/scsi/lpfc/lpfc_mem.c
index 0758edb9dfe2..9c22a2c93462 100644
--- a/drivers/scsi/lpfc/lpfc_mem.c
+++ b/drivers/scsi/lpfc/lpfc_mem.c
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_nl.h b/drivers/scsi/lpfc/lpfc_nl.h
index b93e78f671fb..95d60ab5ebf9 100644
--- a/drivers/scsi/lpfc/lpfc_nl.h
+++ b/drivers/scsi/lpfc/lpfc_nl.h
@@ -1,8 +1,8 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2010 Emulex.  All rights reserved.                *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 1a803975bcbc..bd9bce9d9974 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
@@ -1062,6 +1062,9 @@ lpfc_rcv_logo_plogi_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 {
 	struct lpfc_iocbq *cmdiocb = (struct lpfc_iocbq *) arg;
 
+	/* Retrieve RPI from LOGO IOCB. RPI is used for CMD_ABORT_XRI_CN */
+	if (vport->phba->sli_rev == LPFC_SLI_REV3)
+		ndlp->nlp_rpi = cmdiocb->iocb.ulpIoTag;
 				/* software abort outstanding PLOGI */
 	lpfc_els_abort(vport->phba, ndlp);
 
@@ -1982,12 +1985,6 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			if (bf_get_be32(prli_disc, nvpr))
 				ndlp->nlp_type |= NLP_NVME_DISCOVERY;
 
-			/* This node is an NVME target.  Adjust the command
-			 * queue depth on this node to not exceed the available
-			 * xris.
-			 */
-			ndlp->cmd_qdepth = phba->sli4_hba.nvme_xri_max;
-
 			/*
 			 * If prli_fba is set, the Target supports FirstBurst.
 			 * If prli_fb_sz is 0, the FirstBurst size is unlimited,
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index 76a5a99605aa..028462e5994d 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -1135,9 +1135,6 @@ out_err:
 	else
 		lpfc_ncmd->flags &= ~LPFC_SBUF_XBUSY;
 
-	if (ndlp && NLP_CHK_NODE_ACT(ndlp))
-		atomic_dec(&ndlp->cmd_pending);
-
 	/* Update stats and complete the IO.  There is
 	 * no need for dma unprep because the nvme_transport
 	 * owns the dma address.
@@ -1279,6 +1276,8 @@ lpfc_nvme_prep_io_cmd(struct lpfc_vport *vport,
 	/* Word 9 */
 	bf_set(wqe_reqtag, &wqe->generic.wqe_com, pwqeq->iotag);
 
+	/* Words 13 14 15 are for PBDE support */
+
 	pwqeq->vport = vport;
 	return 0;
 }
@@ -1378,7 +1377,7 @@ lpfc_nvme_prep_io_dma(struct lpfc_vport *vport,
 			data_sg = sg_next(data_sg);
 			sgl++;
 		}
-		if (phba->nvme_embed_pbde) {
+		if (phba->cfg_enable_pbde) {
 			/* Use PBDE support for first SGL only, offset == 0 */
 			/* Words 13-15 */
 			bde = (struct ulp_bde64 *)
@@ -1394,10 +1393,8 @@ lpfc_nvme_prep_io_dma(struct lpfc_vport *vport,
 			memset(&wqe->words[13], 0, (sizeof(uint32_t) * 3));
 			bf_set(wqe_pbde, &wqe->generic.wqe_com, 0);
 		}
-	} else {
-		bf_set(wqe_pbde, &wqe->generic.wqe_com, 0);
-		memset(&wqe->words[13], 0, (sizeof(uint32_t) * 3));
 
+	} else {
 		/* For this clause to be valid, the payload_length
 		 * and sg_cnt must zero.
 		 */
@@ -1546,17 +1543,19 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
 	/* The node is shared with FCP IO, make sure the IO pending count does
 	 * not exceed the programmed depth.
 	 */
-	if ((atomic_read(&ndlp->cmd_pending) >= ndlp->cmd_qdepth) &&
-	    !expedite) {
-		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_IOERR,
-				 "6174 Fail IO, ndlp qdepth exceeded: "
-				 "idx %d DID %x pend %d qdepth %d\n",
-				 lpfc_queue_info->index, ndlp->nlp_DID,
-				 atomic_read(&ndlp->cmd_pending),
-				 ndlp->cmd_qdepth);
-		atomic_inc(&lport->xmt_fcp_qdepth);
-		ret = -EBUSY;
-		goto out_fail;
+	if (lpfc_ndlp_check_qdepth(phba, ndlp)) {
+		if ((atomic_read(&ndlp->cmd_pending) >= ndlp->cmd_qdepth) &&
+		    !expedite) {
+			lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_IOERR,
+					 "6174 Fail IO, ndlp qdepth exceeded: "
+					 "idx %d DID %x pend %d qdepth %d\n",
+					 lpfc_queue_info->index, ndlp->nlp_DID,
+					 atomic_read(&ndlp->cmd_pending),
+					 ndlp->cmd_qdepth);
+			atomic_inc(&lport->xmt_fcp_qdepth);
+			ret = -EBUSY;
+			goto out_fail;
+		}
 	}
 
 	lpfc_ncmd = lpfc_get_nvme_buf(phba, ndlp, expedite);
@@ -1614,8 +1613,6 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
 		goto out_free_nvme_buf;
 	}
 
-	atomic_inc(&ndlp->cmd_pending);
-
 	lpfc_nvmeio_data(phba, "NVME FCP XMIT: xri x%x idx %d to %06x\n",
 			 lpfc_ncmd->cur_iocbq.sli4_xritag,
 			 lpfc_queue_info->index, ndlp->nlp_DID);
@@ -1623,7 +1620,6 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
 	ret = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, &lpfc_ncmd->cur_iocbq);
 	if (ret) {
 		atomic_inc(&lport->xmt_fcp_wqerr);
-		atomic_dec(&ndlp->cmd_pending);
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_IOERR,
 				 "6113 Fail IO, Could not issue WQE err %x "
 				 "sid: x%x did: x%x oxid: x%x\n",
@@ -2378,6 +2374,11 @@ lpfc_get_nvme_buf(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp,
 			lpfc_ncmd = lpfc_nvme_buf(phba);
 	}
 	spin_unlock_irqrestore(&phba->nvme_buf_list_get_lock, iflag);
+
+	if (lpfc_ndlp_check_qdepth(phba, ndlp) && lpfc_ncmd) {
+		atomic_inc(&ndlp->cmd_pending);
+		lpfc_ncmd->flags |= LPFC_BUMP_QDEPTH;
+	}
 	return  lpfc_ncmd;
 }
 
@@ -2396,7 +2397,13 @@ lpfc_release_nvme_buf(struct lpfc_hba *phba, struct lpfc_nvme_buf *lpfc_ncmd)
 {
 	unsigned long iflag = 0;
 
+	if ((lpfc_ncmd->flags & LPFC_BUMP_QDEPTH) && lpfc_ncmd->ndlp)
+		atomic_dec(&lpfc_ncmd->ndlp->cmd_pending);
+
 	lpfc_ncmd->nonsg_phys = 0;
+	lpfc_ncmd->ndlp = NULL;
+	lpfc_ncmd->flags &= ~LPFC_BUMP_QDEPTH;
+
 	if (lpfc_ncmd->flags & LPFC_SBUF_XBUSY) {
 		lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
 				"6310 XB release deferred for "
@@ -2687,7 +2694,7 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	struct lpfc_nvme_rport *oldrport;
 	struct nvme_fc_remote_port *remote_port;
 	struct nvme_fc_port_info rpinfo;
-	struct lpfc_nodelist *prev_ndlp;
+	struct lpfc_nodelist *prev_ndlp = NULL;
 
 	lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NVME_DISC,
 			 "6006 Register NVME PORT. DID x%06x nlptype x%x\n",
@@ -2736,23 +2743,29 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		spin_unlock_irq(&vport->phba->hbalock);
 		rport = remote_port->private;
 		if (oldrport) {
+			/* New remoteport record does not guarantee valid
+			 * host private memory area.
+			 */
+			prev_ndlp = oldrport->ndlp;
 			if (oldrport == remote_port->private) {
-				/* Same remoteport.  Just reuse. */
+				/* Same remoteport - ndlp should match.
+				 * Just reuse.
+				 */
 				lpfc_printf_vlog(ndlp->vport, KERN_INFO,
 						 LOG_NVME_DISC,
 						 "6014 Rebinding lport to "
 						 "remoteport %p wwpn 0x%llx, "
-						 "Data: x%x x%x %p x%x x%06x\n",
+						 "Data: x%x x%x %p %p x%x x%06x\n",
 						 remote_port,
 						 remote_port->port_name,
 						 remote_port->port_id,
 						 remote_port->port_role,
+						 prev_ndlp,
 						 ndlp,
 						 ndlp->nlp_type,
 						 ndlp->nlp_DID);
 				return 0;
 			}
-			prev_ndlp = rport->ndlp;
 
 			/* Sever the ndlp<->rport association
 			 * before dropping the ndlp ref from
@@ -2786,13 +2799,13 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		lpfc_printf_vlog(vport, KERN_INFO,
 				 LOG_NVME_DISC | LOG_NODE,
 				 "6022 Binding new rport to "
-				 "lport %p Remoteport %p  WWNN 0x%llx, "
+				 "lport %p Remoteport %p rport %p WWNN 0x%llx, "
 				 "Rport WWPN 0x%llx DID "
-				 "x%06x Role x%x, ndlp %p\n",
-				 lport, remote_port,
+				 "x%06x Role x%x, ndlp %p prev_ndlp %p\n",
+				 lport, remote_port, rport,
 				 rpinfo.node_name, rpinfo.port_name,
 				 rpinfo.port_id, rpinfo.port_role,
-				 ndlp);
+				 ndlp, prev_ndlp);
 	} else {
 		lpfc_printf_vlog(vport, KERN_ERR,
 				 LOG_NVME_DISC | LOG_NODE,
@@ -2970,7 +2983,7 @@ lpfc_nvme_wait_for_io_drain(struct lpfc_hba *phba)
 	struct lpfc_sli_ring  *pring;
 	u32 i, wait_cnt = 0;
 
-	if (phba->sli_rev < LPFC_SLI_REV4)
+	if (phba->sli_rev < LPFC_SLI_REV4 || !phba->sli4_hba.nvme_wq)
 		return;
 
 	/* Cycle through all NVME rings and make sure all outstanding
@@ -2979,6 +2992,9 @@ lpfc_nvme_wait_for_io_drain(struct lpfc_hba *phba)
 	for (i = 0; i < phba->cfg_nvme_io_channel; i++) {
 		pring = phba->sli4_hba.nvme_wq[i]->pring;
 
+		if (!pring)
+			continue;
+
 		/* Retrieve everything on the txcmplq */
 		while (!list_empty(&pring->txcmplq)) {
 			msleep(LPFC_XRI_EXCH_BUSY_WAIT_T1);
diff --git a/drivers/scsi/lpfc/lpfc_nvme.h b/drivers/scsi/lpfc/lpfc_nvme.h
index 04bd463dd043..cfd4719be25c 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.h
+++ b/drivers/scsi/lpfc/lpfc_nvme.h
@@ -86,6 +86,7 @@ struct lpfc_nvme_buf {
 
 	uint16_t flags;  /* TBD convert exch_busy to flags */
 #define LPFC_SBUF_XBUSY         0x1     /* SLI4 hba reported XB on WCQE cmpl */
+#define LPFC_BUMP_QDEPTH	0x2	/* bumped queue depth counter */
 	uint16_t exch_busy;     /* SLI4 hba reported XB on complete WCQE */
 	uint16_t status;	/* From IOCB Word 7- ulpStatus */
 	uint16_t cpu;
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index 7271c9d885dd..b766afe10d3d 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channsel Host Bus Adapters.                               *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
@@ -402,6 +402,7 @@ lpfc_nvmet_ctxbuf_post(struct lpfc_hba *phba, struct lpfc_nvmet_ctxbuf *ctx_buf)
 
 		/* Process FCP command */
 		if (rc == 0) {
+			ctxp->rqb_buffer = NULL;
 			atomic_inc(&tgtp->rcv_fcp_cmd_out);
 			nvmebuf->hrq->rqbp->rqb_free_buffer(phba, nvmebuf);
 			return;
@@ -1116,8 +1117,17 @@ lpfc_nvmet_defer_rcv(struct nvmet_fc_target_port *tgtport,
 	lpfc_nvmeio_data(phba, "NVMET DEFERRCV: xri x%x sz %d CPU %02x\n",
 			 ctxp->oxid, ctxp->size, smp_processor_id());
 
+	if (!nvmebuf) {
+		lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR,
+				"6425 Defer rcv: no buffer xri x%x: "
+				"flg %x ste %x\n",
+				ctxp->oxid, ctxp->flag, ctxp->state);
+		return;
+	}
+
 	tgtp = phba->targetport->private;
-	atomic_inc(&tgtp->rcv_fcp_cmd_defer);
+	if (tgtp)
+		atomic_inc(&tgtp->rcv_fcp_cmd_defer);
 
 	/* Free the nvmebuf since a new buffer already replaced it */
 	nvmebuf->hrq->rqbp->rqb_free_buffer(phba, nvmebuf);
@@ -1732,9 +1742,12 @@ lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	uint32_t *payload;
 	uint32_t size, oxid, sid, rc;
 
-	if (!nvmebuf || !phba->targetport) {
+	fc_hdr = (struct fc_frame_header *)(nvmebuf->hbuf.virt);
+	oxid = be16_to_cpu(fc_hdr->fh_ox_id);
+
+	if (!phba->targetport) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
-				"6154 LS Drop IO\n");
+				"6154 LS Drop IO x%x\n", oxid);
 		oxid = 0;
 		size = 0;
 		sid = 0;
@@ -1744,9 +1757,7 @@ lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 
 	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
 	payload = (uint32_t *)(nvmebuf->dbuf.virt);
-	fc_hdr = (struct fc_frame_header *)(nvmebuf->hbuf.virt);
 	size = bf_get(lpfc_rcqe_length,  &nvmebuf->cq_event.cqe.rcqe_cmpl);
-	oxid = be16_to_cpu(fc_hdr->fh_ox_id);
 	sid = sli4_sid_from_fc_hdr(fc_hdr);
 
 	ctxp = kzalloc(sizeof(struct lpfc_nvmet_rcv_ctx), GFP_ATOMIC);
@@ -1759,8 +1770,7 @@ dropit:
 		lpfc_nvmeio_data(phba, "NVMET LS  DROP: "
 				 "xri x%x sz %d from %06x\n",
 				 oxid, size, sid);
-		if (nvmebuf)
-			lpfc_in_buf_free(phba, &nvmebuf->dbuf);
+		lpfc_in_buf_free(phba, &nvmebuf->dbuf);
 		return;
 	}
 	ctxp->phba = phba;
@@ -1803,8 +1813,7 @@ dropit:
 			ctxp->oxid, rc);
 
 	/* We assume a rcv'ed cmd ALWAYs fits into 1 buffer */
-	if (nvmebuf)
-		lpfc_in_buf_free(phba, &nvmebuf->dbuf);
+	lpfc_in_buf_free(phba, &nvmebuf->dbuf);
 
 	atomic_inc(&tgtp->xmt_ls_abort);
 	lpfc_nvmet_unsol_ls_issue_abort(phba, ctxp, sid, oxid);
@@ -2492,7 +2501,7 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 			bf_set(wqe_xc, &wqe->fcp_treceive.wqe_com, 0);
 
 		/* Word 11 - set pbde later */
-		if (phba->nvme_embed_pbde) {
+		if (phba->cfg_enable_pbde) {
 			do_pbde = 1;
 		} else {
 			bf_set(wqe_pbde, &wqe->fcp_treceive.wqe_com, 0);
@@ -2607,16 +2616,19 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 			bf_set(lpfc_sli4_sge_last, sgl, 1);
 		sgl->word2 = cpu_to_le32(sgl->word2);
 		sgl->sge_len = cpu_to_le32(cnt);
-		if (do_pbde && i == 0) {
+		if (i == 0) {
 			bde = (struct ulp_bde64 *)&wqe->words[13];
-			memset(bde, 0, sizeof(struct ulp_bde64));
-			/* Words 13-15  (PBDE)*/
-			bde->addrLow = sgl->addr_lo;
-			bde->addrHigh = sgl->addr_hi;
-			bde->tus.f.bdeSize =
-				le32_to_cpu(sgl->sge_len);
-			bde->tus.f.bdeFlags = BUFF_TYPE_BDE_64;
-			bde->tus.w = cpu_to_le32(bde->tus.w);
+			if (do_pbde) {
+				/* Words 13-15  (PBDE) */
+				bde->addrLow = sgl->addr_lo;
+				bde->addrHigh = sgl->addr_hi;
+				bde->tus.f.bdeSize =
+					le32_to_cpu(sgl->sge_len);
+				bde->tus.f.bdeFlags = BUFF_TYPE_BDE_64;
+				bde->tus.w = cpu_to_le32(bde->tus.w);
+			} else {
+				memset(bde, 0, sizeof(struct ulp_bde64));
+			}
 		}
 		sgl++;
 		ctxp->offset += cnt;
@@ -3105,11 +3117,17 @@ lpfc_nvmet_unsol_fcp_issue_abort(struct lpfc_hba *phba,
 	}
 
 aerr:
-	ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
+	spin_lock_irqsave(&ctxp->ctxlock, flags);
+	if (ctxp->flag & LPFC_NVMET_CTX_RLS)
+		list_del(&ctxp->list);
+	ctxp->flag &= ~(LPFC_NVMET_ABORT_OP | LPFC_NVMET_CTX_RLS);
+	spin_unlock_irqrestore(&ctxp->ctxlock, flags);
+
 	atomic_inc(&tgtp->xmt_abort_rsp_error);
 	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
 			"6135 Failed to Issue ABTS for oxid x%x. Status x%x\n",
 			ctxp->oxid, rc);
+	lpfc_nvmet_ctxbuf_post(phba, ctxp->ctxbuf);
 	return 1;
 }
 
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.h b/drivers/scsi/lpfc/lpfc_nvmet.h
index 81f520abfd64..1aaff63f1f41 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.h
+++ b/drivers/scsi/lpfc/lpfc_nvmet.h
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index a94fb9f8bb44..5c7858e735c9 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -995,6 +995,11 @@ lpfc_get_scsi_buf_s3(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
 		spin_unlock(&phba->scsi_buf_list_put_lock);
 	}
 	spin_unlock_irqrestore(&phba->scsi_buf_list_get_lock, iflag);
+
+	if (lpfc_ndlp_check_qdepth(phba, ndlp) && lpfc_cmd) {
+		atomic_inc(&ndlp->cmd_pending);
+		lpfc_cmd->flags |= LPFC_SBUF_BUMP_QDEPTH;
+	}
 	return  lpfc_cmd;
 }
 /**
@@ -1044,6 +1049,11 @@ lpfc_get_scsi_buf_s4(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
 	spin_unlock_irqrestore(&phba->scsi_buf_list_get_lock, iflag);
 	if (!found)
 		return NULL;
+
+	if (lpfc_ndlp_check_qdepth(phba, ndlp) && lpfc_cmd) {
+		atomic_inc(&ndlp->cmd_pending);
+		lpfc_cmd->flags |= LPFC_SBUF_BUMP_QDEPTH;
+	}
 	return  lpfc_cmd;
 }
 /**
@@ -1134,7 +1144,10 @@ lpfc_release_scsi_buf_s4(struct lpfc_hba *phba, struct lpfc_scsi_buf *psb)
 static void
 lpfc_release_scsi_buf(struct lpfc_hba *phba, struct lpfc_scsi_buf *psb)
 {
+	if ((psb->flags & LPFC_SBUF_BUMP_QDEPTH) && psb->ndlp)
+		atomic_dec(&psb->ndlp->cmd_pending);
 
+	psb->flags &= ~LPFC_SBUF_BUMP_QDEPTH;
 	phba->lpfc_release_scsi_buf(phba, psb);
 }
 
@@ -3017,8 +3030,8 @@ out:
 	if (err_type == BGS_GUARD_ERR_MASK) {
 		scsi_build_sense_buffer(1, cmd->sense_buffer, ILLEGAL_REQUEST,
 					0x10, 0x1);
-		cmd->result = DRIVER_SENSE << 24
-			| ScsiResult(DID_ABORT, SAM_STAT_CHECK_CONDITION);
+		cmd->result = DRIVER_SENSE << 24 | DID_ABORT << 16 |
+			      SAM_STAT_CHECK_CONDITION;
 		phba->bg_guard_err_cnt++;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
 				"9069 BLKGRD: LBA %lx grd_tag error %x != %x\n",
@@ -3028,8 +3041,8 @@ out:
 	} else if (err_type == BGS_REFTAG_ERR_MASK) {
 		scsi_build_sense_buffer(1, cmd->sense_buffer, ILLEGAL_REQUEST,
 					0x10, 0x3);
-		cmd->result = DRIVER_SENSE << 24
-			| ScsiResult(DID_ABORT, SAM_STAT_CHECK_CONDITION);
+		cmd->result = DRIVER_SENSE << 24 | DID_ABORT << 16 |
+			      SAM_STAT_CHECK_CONDITION;
 
 		phba->bg_reftag_err_cnt++;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
@@ -3040,8 +3053,8 @@ out:
 	} else if (err_type == BGS_APPTAG_ERR_MASK) {
 		scsi_build_sense_buffer(1, cmd->sense_buffer, ILLEGAL_REQUEST,
 					0x10, 0x2);
-		cmd->result = DRIVER_SENSE << 24
-			| ScsiResult(DID_ABORT, SAM_STAT_CHECK_CONDITION);
+		cmd->result = DRIVER_SENSE << 24 | DID_ABORT << 16 |
+			      SAM_STAT_CHECK_CONDITION;
 
 		phba->bg_apptag_err_cnt++;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
@@ -3096,7 +3109,7 @@ lpfc_parse_bg_err(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd,
 	spin_unlock(&_dump_buf_lock);
 
 	if (lpfc_bgs_get_invalid_prof(bgstat)) {
-		cmd->result = ScsiResult(DID_ERROR, 0);
+		cmd->result = DID_ERROR << 16;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
 				"9072 BLKGRD: Invalid BG Profile in cmd"
 				" 0x%x lba 0x%llx blk cnt 0x%x "
@@ -3108,7 +3121,7 @@ lpfc_parse_bg_err(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd,
 	}
 
 	if (lpfc_bgs_get_uninit_dif_block(bgstat)) {
-		cmd->result = ScsiResult(DID_ERROR, 0);
+		cmd->result = DID_ERROR << 16;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
 				"9073 BLKGRD: Invalid BG PDIF Block in cmd"
 				" 0x%x lba 0x%llx blk cnt 0x%x "
@@ -3124,8 +3137,8 @@ lpfc_parse_bg_err(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd,
 
 		scsi_build_sense_buffer(1, cmd->sense_buffer, ILLEGAL_REQUEST,
 				0x10, 0x1);
-		cmd->result = DRIVER_SENSE << 24
-			| ScsiResult(DID_ABORT, SAM_STAT_CHECK_CONDITION);
+		cmd->result = DRIVER_SENSE << 24 | DID_ABORT << 16 |
+			      SAM_STAT_CHECK_CONDITION;
 		phba->bg_guard_err_cnt++;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
 				"9055 BLKGRD: Guard Tag error in cmd"
@@ -3140,8 +3153,8 @@ lpfc_parse_bg_err(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd,
 
 		scsi_build_sense_buffer(1, cmd->sense_buffer, ILLEGAL_REQUEST,
 				0x10, 0x3);
-		cmd->result = DRIVER_SENSE << 24
-			| ScsiResult(DID_ABORT, SAM_STAT_CHECK_CONDITION);
+		cmd->result = DRIVER_SENSE << 24 | DID_ABORT << 16 |
+			      SAM_STAT_CHECK_CONDITION;
 
 		phba->bg_reftag_err_cnt++;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
@@ -3157,8 +3170,8 @@ lpfc_parse_bg_err(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd,
 
 		scsi_build_sense_buffer(1, cmd->sense_buffer, ILLEGAL_REQUEST,
 				0x10, 0x2);
-		cmd->result = DRIVER_SENSE << 24
-			| ScsiResult(DID_ABORT, SAM_STAT_CHECK_CONDITION);
+		cmd->result = DRIVER_SENSE << 24 | DID_ABORT << 16 |
+			      SAM_STAT_CHECK_CONDITION;
 
 		phba->bg_apptag_err_cnt++;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
@@ -3311,12 +3324,13 @@ lpfc_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd)
 		}
 		/*
 		 * Setup the first Payload BDE. For FCoE we just key off
-		 * Performance Hints, for FC we utilize fcp_embed_pbde.
+		 * Performance Hints, for FC we use lpfc_enable_pbde.
+		 * We populate words 13-15 of IOCB/WQE.
 		 */
 		if ((phba->sli3_options & LPFC_SLI4_PERFH_ENABLED) ||
-		    phba->fcp_embed_pbde) {
+		    phba->cfg_enable_pbde) {
 			bde = (struct ulp_bde64 *)
-					&(iocb_cmd->unsli3.sli3Words[5]);
+				&(iocb_cmd->unsli3.sli3Words[5]);
 			bde->addrLow = first_data_sgl->addr_lo;
 			bde->addrHigh = first_data_sgl->addr_hi;
 			bde->tus.f.bdeSize =
@@ -3330,6 +3344,13 @@ lpfc_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd)
 		sgl->word2 = le32_to_cpu(sgl->word2);
 		bf_set(lpfc_sli4_sge_last, sgl, 1);
 		sgl->word2 = cpu_to_le32(sgl->word2);
+
+		if ((phba->sli3_options & LPFC_SLI4_PERFH_ENABLED) ||
+		    phba->cfg_enable_pbde) {
+			bde = (struct ulp_bde64 *)
+				&(iocb_cmd->unsli3.sli3Words[5]);
+			memset(bde, 0, (sizeof(uint32_t) * 3));
+		}
 	}
 
 	/*
@@ -3866,7 +3887,7 @@ lpfc_handle_fcp_err(struct lpfc_vport *vport, struct lpfc_scsi_buf *lpfc_cmd,
 	}
 
  out:
-	cmnd->result = ScsiResult(host_status, scsi_status);
+	cmnd->result = host_status << 16 | scsi_status;
 	lpfc_send_scsi_error_event(vport->phba, vport, lpfc_cmd, rsp_iocb);
 }
 
@@ -4019,7 +4040,7 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 			break;
 		case IOSTAT_NPORT_BSY:
 		case IOSTAT_FABRIC_BSY:
-			cmd->result = ScsiResult(DID_TRANSPORT_DISRUPTED, 0);
+			cmd->result = DID_TRANSPORT_DISRUPTED << 16;
 			fast_path_evt = lpfc_alloc_fast_evt(phba);
 			if (!fast_path_evt)
 				break;
@@ -4053,14 +4074,14 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 			    lpfc_cmd->result == IOERR_ELXSEC_CRYPTO_ERROR ||
 			    lpfc_cmd->result ==
 					IOERR_ELXSEC_CRYPTO_COMPARE_ERROR) {
-				cmd->result = ScsiResult(DID_NO_CONNECT, 0);
+				cmd->result = DID_NO_CONNECT << 16;
 				break;
 			}
 			if (lpfc_cmd->result == IOERR_INVALID_RPI ||
 			    lpfc_cmd->result == IOERR_NO_RESOURCES ||
 			    lpfc_cmd->result == IOERR_ABORT_REQUESTED ||
 			    lpfc_cmd->result == IOERR_SLER_CMD_RCV_FAILURE) {
-				cmd->result = ScsiResult(DID_REQUEUE, 0);
+				cmd->result = DID_REQUEUE << 16;
 				break;
 			}
 			if ((lpfc_cmd->result == IOERR_RX_DMA_FAILED ||
@@ -4094,16 +4115,16 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 			}
 		/* else: fall through */
 		default:
-			cmd->result = ScsiResult(DID_ERROR, 0);
+			cmd->result = DID_ERROR << 16;
 			break;
 		}
 
 		if (!pnode || !NLP_CHK_NODE_ACT(pnode)
 		    || (pnode->nlp_state != NLP_STE_MAPPED_NODE))
-			cmd->result = ScsiResult(DID_TRANSPORT_DISRUPTED,
-						 SAM_STAT_BUSY);
+			cmd->result = DID_TRANSPORT_DISRUPTED << 16 |
+				      SAM_STAT_BUSY;
 	} else
-		cmd->result = ScsiResult(DID_OK, 0);
+		cmd->result = DID_OK << 16;
 
 	if (cmd->result || lpfc_cmd->fcp_rsp->rspSnsLen) {
 		uint32_t *lp = (uint32_t *)cmd->sense_buffer;
@@ -4122,7 +4143,6 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 		msecs_to_jiffies(vport->cfg_max_scsicmpl_time))) {
 		spin_lock_irqsave(shost->host_lock, flags);
 		if (pnode && NLP_CHK_NODE_ACT(pnode)) {
-			atomic_dec(&pnode->cmd_pending);
 			if (pnode->cmd_qdepth >
 				atomic_read(&pnode->cmd_pending) &&
 				(atomic_read(&pnode->cmd_pending) >
@@ -4135,8 +4155,6 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 			pnode->last_change_time = jiffies;
 		}
 		spin_unlock_irqrestore(shost->host_lock, flags);
-	} else if (pnode && NLP_CHK_NODE_ACT(pnode)) {
-		atomic_dec(&pnode->cmd_pending);
 	}
 	lpfc_scsi_unprep_dma_buf(phba, lpfc_cmd);
 
@@ -4530,6 +4548,11 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 	int err;
 
 	rdata = lpfc_rport_data_from_scsi_device(cmnd->device);
+
+	/* sanity check on references */
+	if (unlikely(!rdata) || unlikely(!rport))
+		goto out_fail_command;
+
 	err = fc_remote_port_chkready(rport);
 	if (err) {
 		cmnd->result = err;
@@ -4555,33 +4578,36 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 	 */
 	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp))
 		goto out_tgt_busy;
-	if (atomic_read(&ndlp->cmd_pending) >= ndlp->cmd_qdepth) {
-		lpfc_printf_vlog(vport, KERN_INFO, LOG_FCP_ERROR,
-				 "3377 Target Queue Full, scsi Id:%d Qdepth:%d"
-				 " Pending command:%d"
-				 " WWNN:%02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x, "
-				 " WWPN:%02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x",
-				 ndlp->nlp_sid, ndlp->cmd_qdepth,
-				 atomic_read(&ndlp->cmd_pending),
-				 ndlp->nlp_nodename.u.wwn[0],
-				 ndlp->nlp_nodename.u.wwn[1],
-				 ndlp->nlp_nodename.u.wwn[2],
-				 ndlp->nlp_nodename.u.wwn[3],
-				 ndlp->nlp_nodename.u.wwn[4],
-				 ndlp->nlp_nodename.u.wwn[5],
-				 ndlp->nlp_nodename.u.wwn[6],
-				 ndlp->nlp_nodename.u.wwn[7],
-				 ndlp->nlp_portname.u.wwn[0],
-				 ndlp->nlp_portname.u.wwn[1],
-				 ndlp->nlp_portname.u.wwn[2],
-				 ndlp->nlp_portname.u.wwn[3],
-				 ndlp->nlp_portname.u.wwn[4],
-				 ndlp->nlp_portname.u.wwn[5],
-				 ndlp->nlp_portname.u.wwn[6],
-				 ndlp->nlp_portname.u.wwn[7]);
-		goto out_tgt_busy;
+	if (lpfc_ndlp_check_qdepth(phba, ndlp)) {
+		if (atomic_read(&ndlp->cmd_pending) >= ndlp->cmd_qdepth) {
+			lpfc_printf_vlog(vport, KERN_INFO, LOG_FCP_ERROR,
+					 "3377 Target Queue Full, scsi Id:%d "
+					 "Qdepth:%d Pending command:%d"
+					 " WWNN:%02x:%02x:%02x:%02x:"
+					 "%02x:%02x:%02x:%02x, "
+					 " WWPN:%02x:%02x:%02x:%02x:"
+					 "%02x:%02x:%02x:%02x",
+					 ndlp->nlp_sid, ndlp->cmd_qdepth,
+					 atomic_read(&ndlp->cmd_pending),
+					 ndlp->nlp_nodename.u.wwn[0],
+					 ndlp->nlp_nodename.u.wwn[1],
+					 ndlp->nlp_nodename.u.wwn[2],
+					 ndlp->nlp_nodename.u.wwn[3],
+					 ndlp->nlp_nodename.u.wwn[4],
+					 ndlp->nlp_nodename.u.wwn[5],
+					 ndlp->nlp_nodename.u.wwn[6],
+					 ndlp->nlp_nodename.u.wwn[7],
+					 ndlp->nlp_portname.u.wwn[0],
+					 ndlp->nlp_portname.u.wwn[1],
+					 ndlp->nlp_portname.u.wwn[2],
+					 ndlp->nlp_portname.u.wwn[3],
+					 ndlp->nlp_portname.u.wwn[4],
+					 ndlp->nlp_portname.u.wwn[5],
+					 ndlp->nlp_portname.u.wwn[6],
+					 ndlp->nlp_portname.u.wwn[7]);
+			goto out_tgt_busy;
+		}
 	}
-	atomic_inc(&ndlp->cmd_pending);
 
 	lpfc_cmd = lpfc_get_scsi_buf(phba, ndlp);
 	if (lpfc_cmd == NULL) {
@@ -4599,6 +4625,7 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 	 */
 	lpfc_cmd->pCmd  = cmnd;
 	lpfc_cmd->rdata = rdata;
+	lpfc_cmd->ndlp = ndlp;
 	lpfc_cmd->timeout = 0;
 	lpfc_cmd->start_time = jiffies;
 	cmnd->host_scribble = (unsigned char *)lpfc_cmd;
@@ -4681,7 +4708,6 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 	lpfc_scsi_unprep_dma_buf(phba, lpfc_cmd);
 	lpfc_release_scsi_buf(phba, lpfc_cmd);
  out_host_busy:
-	atomic_dec(&ndlp->cmd_pending);
 	return SCSI_MLQUEUE_HOST_BUSY;
 
  out_tgt_busy:
@@ -4714,7 +4740,7 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 	struct lpfc_scsi_buf *lpfc_cmd;
 	IOCB_t *cmd, *icmd;
 	int ret = SUCCESS, status = 0;
-	struct lpfc_sli_ring *pring_s4;
+	struct lpfc_sli_ring *pring_s4 = NULL;
 	int ret_val;
 	unsigned long flags;
 	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(waitq);
@@ -4744,8 +4770,25 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 	}
 
 	iocb = &lpfc_cmd->cur_iocbq;
+	if (phba->sli_rev == LPFC_SLI_REV4) {
+		if (!(phba->cfg_fof) ||
+		    (!(iocb->iocb_flag & LPFC_IO_FOF))) {
+			pring_s4 =
+				phba->sli4_hba.fcp_wq[iocb->hba_wqidx]->pring;
+		} else {
+			iocb->hba_wqidx = 0;
+			pring_s4 = phba->sli4_hba.oas_wq->pring;
+		}
+		if (!pring_s4) {
+			ret = FAILED;
+			goto out_unlock;
+		}
+		spin_lock(&pring_s4->ring_lock);
+	}
 	/* the command is in process of being cancelled */
 	if (!(iocb->iocb_flag & LPFC_IO_ON_TXCMPLQ)) {
+		if (phba->sli_rev == LPFC_SLI_REV4)
+			spin_unlock(&pring_s4->ring_lock);
 		spin_unlock_irqrestore(&phba->hbalock, flags);
 		lpfc_printf_vlog(vport, KERN_WARNING, LOG_FCP,
 			"3169 SCSI Layer abort requested I/O has been "
@@ -4759,6 +4802,8 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 	 * see the completion before the eh fired. Just return SUCCESS.
 	 */
 	if (lpfc_cmd->pCmd != cmnd) {
+		if (phba->sli_rev == LPFC_SLI_REV4)
+			spin_unlock(&pring_s4->ring_lock);
 		lpfc_printf_vlog(vport, KERN_WARNING, LOG_FCP,
 			"3170 SCSI Layer abort requested I/O has been "
 			"completed by LLD.\n");
@@ -4771,6 +4816,8 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 	if (iocb->iocb_flag & LPFC_DRIVER_ABORTED) {
 		lpfc_printf_vlog(vport, KERN_WARNING, LOG_FCP,
 			 "3389 SCSI Layer I/O Abort Request is pending\n");
+		if (phba->sli_rev == LPFC_SLI_REV4)
+			spin_unlock(&pring_s4->ring_lock);
 		spin_unlock_irqrestore(&phba->hbalock, flags);
 		goto wait_for_cmpl;
 	}
@@ -4778,6 +4825,8 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 	abtsiocb = __lpfc_sli_get_iocbq(phba);
 	if (abtsiocb == NULL) {
 		ret = FAILED;
+		if (phba->sli_rev == LPFC_SLI_REV4)
+			spin_unlock(&pring_s4->ring_lock);
 		goto out_unlock;
 	}
 
@@ -4815,14 +4864,9 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 
 	abtsiocb->iocb_cmpl = lpfc_sli_abort_fcp_cmpl;
 	abtsiocb->vport = vport;
+	lpfc_cmd->waitq = &waitq;
 	if (phba->sli_rev == LPFC_SLI_REV4) {
-		pring_s4 = lpfc_sli4_calc_ring(phba, abtsiocb);
-		if (pring_s4 == NULL) {
-			ret = FAILED;
-			goto out_unlock;
-		}
 		/* Note: both hbalock and ring_lock must be set here */
-		spin_lock(&pring_s4->ring_lock);
 		ret_val = __lpfc_sli_issue_iocb(phba, pring_s4->ringno,
 						abtsiocb, 0);
 		spin_unlock(&pring_s4->ring_lock);
@@ -4835,6 +4879,17 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 
 
 	if (ret_val == IOCB_ERROR) {
+		if (phba->sli_rev == LPFC_SLI_REV4)
+			spin_lock_irqsave(&pring_s4->ring_lock, flags);
+		else
+			spin_lock_irqsave(&phba->hbalock, flags);
+		/* Indicate the IO is not being aborted by the driver. */
+		iocb->iocb_flag &= ~LPFC_DRIVER_ABORTED;
+		lpfc_cmd->waitq = NULL;
+		if (phba->sli_rev == LPFC_SLI_REV4)
+			spin_unlock_irqrestore(&pring_s4->ring_lock, flags);
+		else
+			spin_unlock_irqrestore(&phba->hbalock, flags);
 		lpfc_sli_release_iocbq(phba, abtsiocb);
 		ret = FAILED;
 		goto out;
@@ -4845,7 +4900,6 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 			&phba->sli.sli3_ring[LPFC_FCP_RING], HA_R0RE_REQ);
 
 wait_for_cmpl:
-	lpfc_cmd->waitq = &waitq;
 	/* Wait for abort to complete */
 	wait_event_timeout(waitq,
 			  (lpfc_cmd->pCmd != cmnd),
@@ -5006,6 +5060,7 @@ lpfc_send_taskmgmt(struct lpfc_vport *vport, struct scsi_cmnd *cmnd,
 	lpfc_cmd->timeout = phba->cfg_task_mgmt_tmo;
 	lpfc_cmd->rdata = rdata;
 	lpfc_cmd->pCmd = cmnd;
+	lpfc_cmd->ndlp = pnode;
 
 	status = lpfc_scsi_prep_task_mgmt_cmd(vport, lpfc_cmd, lun_id,
 					   task_mgmt_cmd);
diff --git a/drivers/scsi/lpfc/lpfc_scsi.h b/drivers/scsi/lpfc/lpfc_scsi.h
index c38e4da71f5f..cc99859774ff 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.h
+++ b/drivers/scsi/lpfc/lpfc_scsi.h
@@ -134,11 +134,13 @@ struct lpfc_scsi_buf {
 	struct list_head list;
 	struct scsi_cmnd *pCmd;
 	struct lpfc_rport_data *rdata;
+	struct lpfc_nodelist *ndlp;
 
 	uint32_t timeout;
 
 	uint16_t flags;  /* TBD convert exch_busy to flags */
 #define LPFC_SBUF_XBUSY         0x1     /* SLI4 hba reported XB on WCQE cmpl */
+#define LPFC_SBUF_BUMP_QDEPTH	0x8	/* bumped queue depth counter */
 	uint16_t exch_busy;     /* SLI4 hba reported XB on complete WCQE */
 	uint16_t status;	/* From IOCB Word 7- ulpStatus */
 	uint32_t result;	/* From IOCB Word 4. */
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 6f3c00a233ec..9830bdb6e072 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -145,6 +145,7 @@ lpfc_sli4_wq_put(struct lpfc_queue *q, union lpfc_wqe128 *wqe)
 	uint32_t idx;
 	uint32_t i = 0;
 	uint8_t *tmp;
+	u32 if_type;
 
 	/* sanity check on queue memory */
 	if (unlikely(!q))
@@ -199,8 +200,14 @@ lpfc_sli4_wq_put(struct lpfc_queue *q, union lpfc_wqe128 *wqe)
 			    q->queue_id);
 		} else {
 			bf_set(lpfc_wq_db_list_fm_num_posted, &doorbell, 1);
-			bf_set(lpfc_wq_db_list_fm_index, &doorbell, host_index);
 			bf_set(lpfc_wq_db_list_fm_id, &doorbell, q->queue_id);
+
+			/* Leave bits <23:16> clear for if_type 6 dpp */
+			if_type = bf_get(lpfc_sli_intf_if_type,
+					 &q->phba->sli4_hba.sli_intf);
+			if (if_type != LPFC_SLI_INTF_IF_TYPE_6)
+				bf_set(lpfc_wq_db_list_fm_index, &doorbell,
+				       host_index);
 		}
 	} else if (q->db_format == LPFC_DB_RING_FORMAT) {
 		bf_set(lpfc_wq_db_ring_fm_num_posted, &doorbell, 1);
@@ -4591,7 +4598,7 @@ lpfc_sli_brdrestart_s3(struct lpfc_hba *phba)
 	spin_unlock_irq(&phba->hbalock);
 
 	memset(&psli->lnk_stat_offsets, 0, sizeof(psli->lnk_stat_offsets));
-	psli->stats_start = get_seconds();
+	psli->stats_start = ktime_get_seconds();
 
 	/* Give the INITFF and Post time to settle. */
 	mdelay(100);
@@ -4638,7 +4645,7 @@ lpfc_sli_brdrestart_s4(struct lpfc_hba *phba)
 	spin_unlock_irq(&phba->hbalock);
 
 	memset(&psli->lnk_stat_offsets, 0, sizeof(psli->lnk_stat_offsets));
-	psli->stats_start = get_seconds();
+	psli->stats_start = ktime_get_seconds();
 
 	/* Reset HBA AER if it was enabled, note hba_flag was reset above */
 	if (hba_aer_enabled)
@@ -9110,8 +9117,8 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 		}
 		/* Note, word 10 is already initialized to 0 */
 
-		/* Don't set PBDE for Perf hints, just fcp_embed_pbde */
-		if (phba->fcp_embed_pbde)
+		/* Don't set PBDE for Perf hints, just lpfc_enable_pbde */
+		if (phba->cfg_enable_pbde)
 			bf_set(wqe_pbde, &wqe->fcp_iwrite.wqe_com, 1);
 		else
 			bf_set(wqe_pbde, &wqe->fcp_iwrite.wqe_com, 0);
@@ -9174,8 +9181,8 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 		}
 		/* Note, word 10 is already initialized to 0 */
 
-		/* Don't set PBDE for Perf hints, just fcp_embed_pbde */
-		if (phba->fcp_embed_pbde)
+		/* Don't set PBDE for Perf hints, just lpfc_enable_pbde */
+		if (phba->cfg_enable_pbde)
 			bf_set(wqe_pbde, &wqe->fcp_iread.wqe_com, 1);
 		else
 			bf_set(wqe_pbde, &wqe->fcp_iread.wqe_com, 0);
@@ -10696,6 +10703,12 @@ lpfc_sli_abort_els_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 		spin_lock_irq(&phba->hbalock);
 		if (phba->sli_rev < LPFC_SLI_REV4) {
+			if (irsp->ulpCommand == CMD_ABORT_XRI_CX &&
+			    irsp->ulpStatus == IOSTAT_LOCAL_REJECT &&
+			    irsp->un.ulpWord[4] == IOERR_ABORT_REQUESTED) {
+				spin_unlock_irq(&phba->hbalock);
+				goto release_iocb;
+			}
 			if (abort_iotag != 0 &&
 				abort_iotag <= phba->sli.last_iotag)
 				abort_iocb =
@@ -10717,6 +10730,7 @@ lpfc_sli_abort_els_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 		spin_unlock_irq(&phba->hbalock);
 	}
+release_iocb:
 	lpfc_sli_release_iocbq(phba, cmdiocb);
 	return;
 }
@@ -10773,6 +10787,7 @@ lpfc_sli_abort_iotag_issue(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	IOCB_t *iabt = NULL;
 	int retval;
 	unsigned long iflags;
+	struct lpfc_nodelist *ndlp;
 
 	lockdep_assert_held(&phba->hbalock);
 
@@ -10803,9 +10818,13 @@ lpfc_sli_abort_iotag_issue(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	if (phba->sli_rev == LPFC_SLI_REV4) {
 		iabt->un.acxri.abortIoTag = cmdiocb->sli4_xritag;
 		iabt->un.acxri.abortContextTag = cmdiocb->iotag;
-	}
-	else
+	} else {
 		iabt->un.acxri.abortIoTag = icmd->ulpIoTag;
+		if (pring->ringno == LPFC_ELS_RING) {
+			ndlp = (struct lpfc_nodelist *)(cmdiocb->context1);
+			iabt->un.acxri.abortContextTag = ndlp->nlp_rpi;
+		}
+	}
 	iabt->ulpLe = 1;
 	iabt->ulpClass = icmd->ulpClass;
 
@@ -11084,10 +11103,11 @@ lpfc_sli_validate_fcp_iocb(struct lpfc_iocbq *iocbq, struct lpfc_vport *vport,
 	struct lpfc_scsi_buf *lpfc_cmd;
 	int rc = 1;
 
-	if (!(iocbq->iocb_flag &  LPFC_IO_FCP))
+	if (iocbq->vport != vport)
 		return rc;
 
-	if (iocbq->vport != vport)
+	if (!(iocbq->iocb_flag &  LPFC_IO_FCP) ||
+	    !(iocbq->iocb_flag & LPFC_IO_ON_TXCMPLQ))
 		return rc;
 
 	lpfc_cmd = container_of(iocbq, struct lpfc_scsi_buf, cur_iocbq);
@@ -11097,13 +11117,13 @@ lpfc_sli_validate_fcp_iocb(struct lpfc_iocbq *iocbq, struct lpfc_vport *vport,
 
 	switch (ctx_cmd) {
 	case LPFC_CTX_LUN:
-		if ((lpfc_cmd->rdata->pnode) &&
+		if ((lpfc_cmd->rdata) && (lpfc_cmd->rdata->pnode) &&
 		    (lpfc_cmd->rdata->pnode->nlp_sid == tgt_id) &&
 		    (scsilun_to_int(&lpfc_cmd->fcp_cmnd->fcp_lun) == lun_id))
 			rc = 0;
 		break;
 	case LPFC_CTX_TGT:
-		if ((lpfc_cmd->rdata->pnode) &&
+		if ((lpfc_cmd->rdata) && (lpfc_cmd->rdata->pnode) &&
 		    (lpfc_cmd->rdata->pnode->nlp_sid == tgt_id))
 			rc = 0;
 		break;
@@ -11218,6 +11238,10 @@ lpfc_sli_abort_iocb(struct lpfc_vport *vport, struct lpfc_sli_ring *pring,
 	int errcnt = 0, ret_val = 0;
 	int i;
 
+	/* all I/Os are in process of being flushed */
+	if (phba->hba_flag & HBA_FCP_IOQ_FLUSH)
+		return errcnt;
+
 	for (i = 1; i <= phba->sli.last_iotag; i++) {
 		iocbq = phba->sli.iocbq_lookup[i];
 
diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h
index 431754195505..34b7ab69b9b4 100644
--- a/drivers/scsi/lpfc/lpfc_sli.h
+++ b/drivers/scsi/lpfc/lpfc_sli.h
@@ -1,8 +1,8 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
@@ -339,7 +339,7 @@ struct lpfc_sli {
 	struct lpfc_iocbq ** iocbq_lookup; /* array to lookup IOCB by IOTAG */
 	size_t iocbq_lookup_len;           /* current lengs of the array */
 	uint16_t  last_iotag;              /* last allocated IOTAG */
-	unsigned long  stats_start;        /* in seconds */
+	time64_t  stats_start;		   /* in seconds */
 	struct lpfc_lnk_stat lnk_stat_offsets;
 };
 
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index cf64aca82bd0..399c0015c546 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2009-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
@@ -490,6 +490,7 @@ struct lpfc_pc_sli4_params {
 	uint8_t eqav;
 	uint8_t cqav;
 	uint8_t wqsize;
+	uint8_t bv1s;
 #define LPFC_WQ_SZ64_SUPPORT	1
 #define LPFC_WQ_SZ128_SUPPORT	2
 	uint8_t wqpcnt;
@@ -774,7 +775,9 @@ struct lpfc_rdp_context {
 struct lpfc_lcb_context {
 	uint8_t  sub_command;
 	uint8_t  type;
+	uint8_t  capability;
 	uint8_t  frequency;
+	uint16_t  duration;
 	uint16_t ox_id;
 	uint16_t rx_id;
 	struct lpfc_nodelist *ndlp;
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index 18c23afcf46b..501249509af4 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
@@ -20,7 +20,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "12.0.0.4"
+#define LPFC_DRIVER_VERSION "12.0.0.6"
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */
@@ -33,5 +33,5 @@
 #define LPFC_MODULE_DESC "Emulex LightPulse Fibre Channel SCSI driver " \
 		LPFC_DRIVER_VERSION
 #define LPFC_COPYRIGHT "Copyright (C) 2017-2018 Broadcom. All Rights " \
-		"Reserved. The term \"Broadcom\" refers to Broadcom Limited " \
+		"Reserved. The term \"Broadcom\" refers to Broadcom Inc. " \
 		"and/or its subsidiaries."
diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c
index 81bc12dedf41..1ff0f7de9105 100644
--- a/drivers/scsi/lpfc/lpfc_vport.c
+++ b/drivers/scsi/lpfc/lpfc_vport.c
@@ -1,8 +1,8 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_vport.h b/drivers/scsi/lpfc/lpfc_vport.h
index 62295971f66c..f4b8528dd2e7 100644
--- a/drivers/scsi/lpfc/lpfc_vport.h
+++ b/drivers/scsi/lpfc/lpfc_vport.h
@@ -1,8 +1,8 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2006 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c
index 8e8cf1145d7f..8c7154143a4e 100644
--- a/drivers/scsi/megaraid.c
+++ b/drivers/scsi/megaraid.c
@@ -371,7 +371,7 @@ mega_runpendq(adapter_t *adapter)
  * The command queuing entry point for the mid-layer.
  */
 static int
-megaraid_queue_lck(Scsi_Cmnd *scmd, void (*done)(Scsi_Cmnd *))
+megaraid_queue_lck(struct scsi_cmnd *scmd, void (*done)(struct scsi_cmnd *))
 {
 	adapter_t	*adapter;
 	scb_t	*scb;
@@ -425,7 +425,7 @@ static DEF_SCSI_QCMD(megaraid_queue)
  * commands.
  */
 static inline scb_t *
-mega_allocate_scb(adapter_t *adapter, Scsi_Cmnd *cmd)
+mega_allocate_scb(adapter_t *adapter, struct scsi_cmnd *cmd)
 {
 	struct list_head *head = &adapter->free_list;
 	scb_t	*scb;
@@ -457,7 +457,7 @@ mega_allocate_scb(adapter_t *adapter, Scsi_Cmnd *cmd)
  * and the channel number.
  */
 static inline int
-mega_get_ldrv_num(adapter_t *adapter, Scsi_Cmnd *cmd, int channel)
+mega_get_ldrv_num(adapter_t *adapter, struct scsi_cmnd *cmd, int channel)
 {
 	int		tgt;
 	int		ldrv_num;
@@ -520,7 +520,7 @@ mega_get_ldrv_num(adapter_t *adapter, Scsi_Cmnd *cmd, int channel)
  * boot settings.
  */
 static scb_t *
-mega_build_cmd(adapter_t *adapter, Scsi_Cmnd *cmd, int *busy)
+mega_build_cmd(adapter_t *adapter, struct scsi_cmnd *cmd, int *busy)
 {
 	mega_ext_passthru	*epthru;
 	mega_passthru	*pthru;
@@ -951,8 +951,8 @@ mega_build_cmd(adapter_t *adapter, Scsi_Cmnd *cmd, int *busy)
  * prepare a command for the scsi physical devices.
  */
 static mega_passthru *
-mega_prepare_passthru(adapter_t *adapter, scb_t *scb, Scsi_Cmnd *cmd,
-		int channel, int target)
+mega_prepare_passthru(adapter_t *adapter, scb_t *scb, struct scsi_cmnd *cmd,
+		      int channel, int target)
 {
 	mega_passthru *pthru;
 
@@ -1015,8 +1015,9 @@ mega_prepare_passthru(adapter_t *adapter, scb_t *scb, Scsi_Cmnd *cmd,
  * commands for devices which can take extended CDBs (>10 bytes)
  */
 static mega_ext_passthru *
-mega_prepare_extpassthru(adapter_t *adapter, scb_t *scb, Scsi_Cmnd *cmd,
-		int channel, int target)
+mega_prepare_extpassthru(adapter_t *adapter, scb_t *scb,
+			 struct scsi_cmnd *cmd,
+			 int channel, int target)
 {
 	mega_ext_passthru	*epthru;
 
@@ -1417,7 +1418,7 @@ mega_cmd_done(adapter_t *adapter, u8 completed[], int nstatus, int status)
 {
 	mega_ext_passthru	*epthru = NULL;
 	struct scatterlist	*sgl;
-	Scsi_Cmnd	*cmd = NULL;
+	struct scsi_cmnd	*cmd = NULL;
 	mega_passthru	*pthru = NULL;
 	mbox_t	*mbox = NULL;
 	u8	c;
@@ -1652,14 +1653,14 @@ mega_cmd_done(adapter_t *adapter, u8 completed[], int nstatus, int status)
 static void
 mega_rundoneq (adapter_t *adapter)
 {
-	Scsi_Cmnd *cmd;
+	struct scsi_cmnd *cmd;
 	struct list_head *pos;
 
 	list_for_each(pos, &adapter->completed_list) {
 
 		struct scsi_pointer* spos = (struct scsi_pointer *)pos;
 
-		cmd = list_entry(spos, Scsi_Cmnd, SCp);
+		cmd = list_entry(spos, struct scsi_cmnd, SCp);
 		cmd->scsi_done(cmd);
 	}
 
@@ -1722,7 +1723,7 @@ static int
 mega_build_sglist(adapter_t *adapter, scb_t *scb, u32 *buf, u32 *len)
 {
 	struct scatterlist *sg;
-	Scsi_Cmnd	*cmd;
+	struct scsi_cmnd	*cmd;
 	int	sgcnt;
 	int	idx;
 
@@ -1869,7 +1870,7 @@ megaraid_info(struct Scsi_Host *host)
  * aborted. All the commands issued to the F/W must complete.
  */
 static int
-megaraid_abort(Scsi_Cmnd *cmd)
+megaraid_abort(struct scsi_cmnd *cmd)
 {
 	adapter_t	*adapter;
 	int		rval;
@@ -1933,7 +1934,7 @@ megaraid_reset(struct scsi_cmnd *cmd)
  * issued to the controller, abort/reset it. Otherwise return failure
  */
 static int
-megaraid_abort_and_reset(adapter_t *adapter, Scsi_Cmnd *cmd, int aor)
+megaraid_abort_and_reset(adapter_t *adapter, struct scsi_cmnd *cmd, int aor)
 {
 	struct list_head	*pos, *next;
 	scb_t			*scb;
diff --git a/drivers/scsi/megaraid.h b/drivers/scsi/megaraid.h
index 18e85d9267ff..cce23a086fbe 100644
--- a/drivers/scsi/megaraid.h
+++ b/drivers/scsi/megaraid.h
@@ -191,7 +191,7 @@ typedef struct {
 	u32	dma_type;
 	u32	dma_direction;
 
-	Scsi_Cmnd	*cmd;
+	struct scsi_cmnd	*cmd;
 	dma_addr_t	dma_h_bulkdata;
 	dma_addr_t	dma_h_sgdata;
 
@@ -942,7 +942,7 @@ static int issue_scb(adapter_t *, scb_t *);
 static int mega_setup_mailbox(adapter_t *);
 
 static int megaraid_queue (struct Scsi_Host *, struct scsi_cmnd *);
-static scb_t * mega_build_cmd(adapter_t *, Scsi_Cmnd *, int *);
+static scb_t * mega_build_cmd(adapter_t *, struct scsi_cmnd *, int *);
 static void __mega_runpendq(adapter_t *);
 static int issue_scb_block(adapter_t *, u_char *);
 
@@ -951,9 +951,9 @@ static irqreturn_t megaraid_isr_iomapped(int, void *);
 
 static void mega_free_scb(adapter_t *, scb_t *);
 
-static int megaraid_abort(Scsi_Cmnd *);
-static int megaraid_reset(Scsi_Cmnd *);
-static int megaraid_abort_and_reset(adapter_t *, Scsi_Cmnd *, int);
+static int megaraid_abort(struct scsi_cmnd *);
+static int megaraid_reset(struct scsi_cmnd *);
+static int megaraid_abort_and_reset(adapter_t *, struct scsi_cmnd *, int);
 static int megaraid_biosparam(struct scsi_device *, struct block_device *,
 		sector_t, int []);
 
@@ -983,9 +983,9 @@ static int mega_internal_dev_inquiry(adapter_t *, u8, u8, dma_addr_t);
 
 static int mega_support_ext_cdb(adapter_t *);
 static mega_passthru* mega_prepare_passthru(adapter_t *, scb_t *,
-		Scsi_Cmnd *, int, int);
+		struct scsi_cmnd *, int, int);
 static mega_ext_passthru* mega_prepare_extpassthru(adapter_t *,
-		scb_t *, Scsi_Cmnd *, int, int);
+		scb_t *, struct scsi_cmnd *, int, int);
 static void mega_enum_raid_scsi(adapter_t *);
 static void mega_get_boot_drv(adapter_t *);
 static int mega_support_random_del(adapter_t *);
diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index 75dc25f78336..67d356d84717 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -35,8 +35,8 @@
 /*
  * MegaRAID SAS Driver meta data
  */
-#define MEGASAS_VERSION				"07.705.02.00-rc1"
-#define MEGASAS_RELDATE				"April 4, 2018"
+#define MEGASAS_VERSION				"07.706.03.00-rc1"
+#define MEGASAS_RELDATE				"May 21, 2018"
 
 /*
  * Device IDs
@@ -709,7 +709,8 @@ struct MR_TARGET_PROPERTIES {
 	u32    max_io_size_kb;
 	u32    device_qdepth;
 	u32    sector_size;
-	u8     reserved[500];
+	u8     reset_tmo;
+	u8     reserved[499];
 } __packed;
 
  /*
@@ -1400,6 +1401,19 @@ struct megasas_ctrl_info {
 	#endif
 		} adapter_operations4;
 	u8 pad[0x800 - 0x7FE]; /* 0x7FE pad to 2K for expansion */
+
+	u32 size;
+	u32 pad1;
+
+	u8 reserved6[64];
+
+	u32 rsvdForAdptOp[64];
+
+	u8 reserved7[3];
+
+	u8 TaskAbortTO;	/* Timeout value in seconds used by Abort Task TM */
+	u8 MaxResetTO;	/* Max Supported Reset timeout in seconds. */
+	u8 reserved8[3];
 } __packed;
 
 /*
@@ -1472,6 +1486,7 @@ enum FW_BOOT_CONTEXT {
 #define MEGASAS_DEFAULT_CMD_TIMEOUT		90
 #define MEGASAS_THROTTLE_QUEUE_DEPTH		16
 #define MEGASAS_BLOCKED_CMD_TIMEOUT		60
+#define MEGASAS_DEFAULT_TM_TIMEOUT		50
 /*
  * FW reports the maximum of number of commands that it can accept (maximum
  * commands that can be outstanding) at any time. The driver must report a
@@ -1915,7 +1930,9 @@ struct MR_PRIV_DEVICE {
 	bool is_tm_capable;
 	bool tm_busy;
 	atomic_t r1_ldio_hint;
-	u8   interface_type;
+	u8 interface_type;
+	u8 task_abort_tmo;
+	u8 target_reset_tmo;
 };
 struct megasas_cmd;
 
@@ -2291,6 +2308,8 @@ struct megasas_instance {
 	u8 adapter_type;
 	bool consistent_mask_64bit;
 	bool support_nvme_passthru;
+	u8 task_abort_tmo;
+	u8 max_reset_tmo;
 };
 struct MR_LD_VF_MAP {
 	u32 size;
@@ -2512,7 +2531,11 @@ int megasas_get_ctrl_info(struct megasas_instance *instance);
 /* PD sequence */
 int
 megasas_sync_pd_seq_num(struct megasas_instance *instance, bool pend);
-void megasas_set_dynamic_target_properties(struct scsi_device *sdev);
+void megasas_set_dynamic_target_properties(struct scsi_device *sdev,
+					   bool is_target_prop);
+int megasas_get_target_prop(struct megasas_instance *instance,
+			    struct scsi_device *sdev);
+
 int megasas_set_crash_dump_params(struct megasas_instance *instance,
 	u8 crash_buf_state);
 void megasas_free_host_crash_buffer(struct megasas_instance *instance);
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 71d97573a667..9aa9590c5373 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -120,8 +120,7 @@ static int megasas_register_aen(struct megasas_instance *instance,
 				u32 seq_num, u32 class_locale_word);
 static void megasas_get_pd_info(struct megasas_instance *instance,
 				struct scsi_device *sdev);
-static int megasas_get_target_prop(struct megasas_instance *instance,
-				   struct scsi_device *sdev);
+
 /*
  * PCI ID table for all supported controllers
  */
@@ -1794,7 +1793,8 @@ static struct megasas_instance *megasas_lookup_instance(u16 host_no)
 *
 * Returns void
 */
-void megasas_set_dynamic_target_properties(struct scsi_device *sdev)
+void megasas_set_dynamic_target_properties(struct scsi_device *sdev,
+					   bool is_target_prop)
 {
 	u16 pd_index = 0, ld;
 	u32 device_id;
@@ -1834,6 +1834,22 @@ void megasas_set_dynamic_target_properties(struct scsi_device *sdev)
 		mr_device_priv_data->is_tm_capable =
 			pd_sync->seq[pd_index].capability.tmCapable;
 	}
+
+	if (is_target_prop && instance->tgt_prop->reset_tmo) {
+		/*
+		 * If FW provides a target reset timeout value, driver will use
+		 * it. If not set, fallback to default values.
+		 */
+		mr_device_priv_data->target_reset_tmo =
+			min_t(u8, instance->max_reset_tmo,
+			      instance->tgt_prop->reset_tmo);
+		mr_device_priv_data->task_abort_tmo = instance->task_abort_tmo;
+	} else {
+		mr_device_priv_data->target_reset_tmo =
+						MEGASAS_DEFAULT_TM_TIMEOUT;
+		mr_device_priv_data->task_abort_tmo =
+						MEGASAS_DEFAULT_TM_TIMEOUT;
+	}
 }
 
 /*
@@ -1967,10 +1983,10 @@ static int megasas_slave_configure(struct scsi_device *sdev)
 	is_target_prop = (ret_target_prop == DCMD_SUCCESS) ? true : false;
 	megasas_set_static_target_properties(sdev, is_target_prop);
 
-	mutex_unlock(&instance->reset_mutex);
-
 	/* This sdev property may change post OCR */
-	megasas_set_dynamic_target_properties(sdev);
+	megasas_set_dynamic_target_properties(sdev, is_target_prop);
+
+	mutex_unlock(&instance->reset_mutex);
 
 	return 0;
 }
@@ -2818,7 +2834,7 @@ static int megasas_reset_bus_host(struct scsi_cmnd *scmd)
 		"SCSI command pointer: (%p)\t SCSI host state: %d\t"
 		" SCSI host busy: %d\t FW outstanding: %d\n",
 		scmd, scmd->device->host->shost_state,
-		atomic_read((atomic_t *)&scmd->device->host->host_busy),
+		scsi_host_busy(scmd->device->host),
 		atomic_read(&instance->fw_outstanding));
 
 	/*
@@ -4720,6 +4736,8 @@ megasas_get_ctrl_info(struct megasas_instance *instance)
 			ci->adapter_operations4.support_pd_map_target_id;
 		instance->support_nvme_passthru =
 			ci->adapter_operations4.support_nvme_passthru;
+		instance->task_abort_tmo = ci->TaskAbortTO;
+		instance->max_reset_tmo = ci->MaxResetTO;
 
 		/*Check whether controller is iMR or MR */
 		instance->is_imr = (ci->memory_size ? 0 : 1);
@@ -4738,6 +4756,10 @@ megasas_get_ctrl_info(struct megasas_instance *instance)
 			instance->secure_jbod_support ? "Yes" : "No");
 		dev_info(&instance->pdev->dev, "NVMe passthru support\t: %s\n",
 			 instance->support_nvme_passthru ? "Yes" : "No");
+		dev_info(&instance->pdev->dev,
+			 "FW provided TM TaskAbort/Reset timeout\t: %d secs/%d secs\n",
+			 instance->task_abort_tmo, instance->max_reset_tmo);
+
 		break;
 
 	case DCMD_TIMEOUT:
@@ -4755,14 +4777,15 @@ megasas_get_ctrl_info(struct megasas_instance *instance)
 				__func__, __LINE__);
 			break;
 		}
+		break;
 	case DCMD_FAILED:
 		megaraid_sas_kill_hba(instance);
 		break;
 
 	}
 
-	megasas_return_cmd(instance, cmd);
-
+	if (ret != DCMD_TIMEOUT)
+		megasas_return_cmd(instance, cmd);
 
 	return ret;
 }
@@ -5831,7 +5854,7 @@ megasas_register_aen(struct megasas_instance *instance, u32 seq_num,
  *
  * Returns 0 on success non-zero on failure.
  */
-static int
+int
 megasas_get_target_prop(struct megasas_instance *instance,
 			struct scsi_device *sdev)
 {
@@ -6789,6 +6812,9 @@ megasas_resume(struct pci_dev *pdev)
 			goto fail_init_mfi;
 	}
 
+	if (megasas_get_ctrl_info(instance) != DCMD_SUCCESS)
+		goto fail_init_mfi;
+
 	tasklet_init(&instance->isr_tasklet, instance->instancet->tasklet,
 		     (unsigned long)instance);
 
@@ -6842,12 +6868,12 @@ megasas_wait_for_adapter_operational(struct megasas_instance *instance)
 {
 	int wait_time = MEGASAS_RESET_WAIT_TIME * 2;
 	int i;
-
-	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR)
-		return 1;
+	u8 adp_state;
 
 	for (i = 0; i < wait_time; i++) {
-		if (atomic_read(&instance->adprecovery)	== MEGASAS_HBA_OPERATIONAL)
+		adp_state = atomic_read(&instance->adprecovery);
+		if ((adp_state == MEGASAS_HBA_OPERATIONAL) ||
+		    (adp_state == MEGASAS_HW_CRITICAL_ERROR))
 			break;
 
 		if (!(i % MEGASAS_RESET_NOTICE_INTERVAL))
@@ -6856,9 +6882,10 @@ megasas_wait_for_adapter_operational(struct megasas_instance *instance)
 		msleep(1000);
 	}
 
-	if (atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL) {
-		dev_info(&instance->pdev->dev, "%s timed out while waiting for HBA to recover.\n",
-			__func__);
+	if (adp_state != MEGASAS_HBA_OPERATIONAL) {
+		dev_info(&instance->pdev->dev,
+			 "%s HBA failed to become operational, adp_state %d\n",
+			 __func__, adp_state);
 		return 1;
 	}
 
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 94c23ad51179..c7f95bace353 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -4108,7 +4108,8 @@ megasas_tm_response_code(struct megasas_instance *instance,
  */
 static int
 megasas_issue_tm(struct megasas_instance *instance, u16 device_handle,
-	uint channel, uint id, u16 smid_task, u8 type)
+	uint channel, uint id, u16 smid_task, u8 type,
+	struct MR_PRIV_DEVICE *mr_device_priv_data)
 {
 	struct MR_TASK_MANAGE_REQUEST *mr_request;
 	struct MPI2_SCSI_TASK_MANAGE_REQUEST *mpi_request;
@@ -4119,6 +4120,7 @@ megasas_issue_tm(struct megasas_instance *instance, u16 device_handle,
 	struct fusion_context *fusion = NULL;
 	struct megasas_cmd_fusion *scsi_lookup;
 	int rc;
+	int timeout = MEGASAS_DEFAULT_TM_TIMEOUT;
 	struct MPI2_SCSI_TASK_MANAGE_REPLY *mpi_reply;
 
 	fusion = instance->ctrl_context;
@@ -4170,7 +4172,16 @@ megasas_issue_tm(struct megasas_instance *instance, u16 device_handle,
 	init_completion(&cmd_fusion->done);
 	megasas_fire_cmd_fusion(instance, req_desc);
 
-	timeleft = wait_for_completion_timeout(&cmd_fusion->done, 50 * HZ);
+	switch (type) {
+	case MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK:
+		timeout = mr_device_priv_data->task_abort_tmo;
+		break;
+	case MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET:
+		timeout = mr_device_priv_data->target_reset_tmo;
+		break;
+	}
+
+	timeleft = wait_for_completion_timeout(&cmd_fusion->done, timeout * HZ);
 
 	if (!timeleft) {
 		dev_err(&instance->pdev->dev,
@@ -4363,7 +4374,8 @@ int megasas_task_abort_fusion(struct scsi_cmnd *scmd)
 	mr_device_priv_data->tm_busy = 1;
 	ret = megasas_issue_tm(instance, devhandle,
 			scmd->device->channel, scmd->device->id, smid,
-			MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK);
+			MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK,
+			mr_device_priv_data);
 	mr_device_priv_data->tm_busy = 0;
 
 	mutex_unlock(&instance->reset_mutex);
@@ -4435,7 +4447,8 @@ int megasas_reset_target_fusion(struct scsi_cmnd *scmd)
 	mr_device_priv_data->tm_busy = 1;
 	ret = megasas_issue_tm(instance, devhandle,
 			scmd->device->channel, scmd->device->id, 0,
-			MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET);
+			MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET,
+			mr_device_priv_data);
 	mr_device_priv_data->tm_busy = 0;
 	mutex_unlock(&instance->reset_mutex);
 out:
@@ -4490,6 +4503,8 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int reason)
 	u32 io_timeout_in_crash_mode = 0;
 	struct scsi_cmnd *scmd_local = NULL;
 	struct scsi_device *sdev;
+	int ret_target_prop = DCMD_FAILED;
+	bool is_target_prop = false;
 
 	instance = (struct megasas_instance *)shost->hostdata;
 	fusion = instance->ctrl_context;
@@ -4661,9 +4676,6 @@ transition_to_ready:
 
 			megasas_setup_jbod_map(instance);
 
-			shost_for_each_device(sdev, shost)
-				megasas_set_dynamic_target_properties(sdev);
-
 			/* reset stream detection array */
 			if (instance->adapter_type == VENTURA_SERIES) {
 				for (j = 0; j < MAX_LOGICAL_DRIVES_EXT; ++j) {
@@ -4677,6 +4689,16 @@ transition_to_ready:
 			clear_bit(MEGASAS_FUSION_IN_RESET,
 				  &instance->reset_flags);
 			instance->instancet->enable_intr(instance);
+
+			shost_for_each_device(sdev, shost) {
+				if ((instance->tgt_prop) &&
+				    (instance->nvme_page_size))
+					ret_target_prop = megasas_get_target_prop(instance, sdev);
+
+				is_target_prop = (ret_target_prop == DCMD_SUCCESS) ? true : false;
+				megasas_set_dynamic_target_properties(sdev, is_target_prop);
+			}
+
 			atomic_set(&instance->adprecovery, MEGASAS_HBA_OPERATIONAL);
 
 			dev_info(&instance->pdev->dev, "Interrupts are enabled and"
diff --git a/drivers/scsi/mesh.c b/drivers/scsi/mesh.c
index 1753e42826dd..82e01dbe90af 100644
--- a/drivers/scsi/mesh.c
+++ b/drivers/scsi/mesh.c
@@ -594,9 +594,9 @@ static void mesh_done(struct mesh_state *ms, int start_next)
 	ms->current_req = NULL;
 	tp->current_req = NULL;
 	if (cmd) {
-		cmd->result = (ms->stat << 16) + cmd->SCp.Status;
+		cmd->result = (ms->stat << 16) | cmd->SCp.Status;
 		if (ms->stat == DID_OK)
-			cmd->result += (cmd->SCp.Message << 8);
+			cmd->result |= cmd->SCp.Message << 8;
 		if (DEBUG_TARGET(cmd)) {
 			printk(KERN_DEBUG "mesh_done: result = %x, data_ptr=%d, buflen=%d\n",
 			       cmd->result, ms->data_ptr, scsi_bufflen(cmd));
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index e44c91edf92d..59d7844ee022 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -102,8 +102,39 @@ static int
 _base_get_ioc_facts(struct MPT3SAS_ADAPTER *ioc);
 
 /**
+ * mpt3sas_base_check_cmd_timeout - Function
+ *		to check timeout and command termination due
+ *		to Host reset.
+ *
+ * @ioc:	per adapter object.
+ * @status:	Status of issued command.
+ * @mpi_request:mf request pointer.
+ * @sz:		size of buffer.
+ *
+ * @Returns - 1/0 Reset to be done or Not
+ */
+u8
+mpt3sas_base_check_cmd_timeout(struct MPT3SAS_ADAPTER *ioc,
+		u8 status, void *mpi_request, int sz)
+{
+	u8 issue_reset = 0;
+
+	if (!(status & MPT3_CMD_RESET))
+		issue_reset = 1;
+
+	pr_err(MPT3SAS_FMT "Command %s\n", ioc->name,
+	    ((issue_reset == 0) ? "terminated due to Host Reset" : "Timeout"));
+	_debug_dump_mf(mpi_request, sz);
+
+	return issue_reset;
+}
+
+/**
  * _scsih_set_fwfault_debug - global setting of ioc->fwfault_debug.
+ * @val: ?
+ * @kp: ?
  *
+ * Return: ?
  */
 static int
 _scsih_set_fwfault_debug(const char *val, const struct kernel_param *kp)
@@ -132,8 +163,6 @@ module_param_call(mpt3sas_fwfault_debug, _scsih_set_fwfault_debug,
  * @ioc: per adapter object
  * @reply: reply message frame(lower 32bit addr)
  * @index: System request message index.
- *
- * @Returns - Nothing
  */
 static void
 _base_clone_reply_to_sys_mem(struct MPT3SAS_ADAPTER *ioc, u32 reply,
@@ -156,7 +185,7 @@ _base_clone_reply_to_sys_mem(struct MPT3SAS_ADAPTER *ioc, u32 reply,
  * _base_clone_mpi_to_sys_mem - Writes/copies MPI frames
  *				to system/BAR0 region.
  *
- * @dst_iomem: Pointer to the destinaltion location in BAR0 space.
+ * @dst_iomem: Pointer to the destination location in BAR0 space.
  * @src: Pointer to the Source data.
  * @size: Size of data to be copied.
  */
@@ -197,7 +226,7 @@ _base_clone_to_sys_mem(void __iomem *dst_iomem, void *src, u32 size)
  * @smid: system request message index
  * @sge_chain_count: Scatter gather chain count.
  *
- * @Return: chain address.
+ * Return: the chain address.
  */
 static inline void __iomem*
 _base_get_chain(struct MPT3SAS_ADAPTER *ioc, u16 smid,
@@ -223,7 +252,7 @@ _base_get_chain(struct MPT3SAS_ADAPTER *ioc, u16 smid,
  * @smid: system request message index
  * @sge_chain_count: Scatter gather chain count.
  *
- * @Return - Physical chain address.
+ * Return: Physical chain address.
  */
 static inline phys_addr_t
 _base_get_chain_phys(struct MPT3SAS_ADAPTER *ioc, u16 smid,
@@ -248,7 +277,7 @@ _base_get_chain_phys(struct MPT3SAS_ADAPTER *ioc, u16 smid,
  * @ioc: per adapter object
  * @smid: system request message index
  *
- * @Returns - Pointer to buffer location in BAR0.
+ * Return: Pointer to buffer location in BAR0.
  */
 
 static void __iomem *
@@ -270,7 +299,7 @@ _base_get_buffer_bar0(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * @ioc: per adapter object
  * @smid: system request message index
  *
- * @Returns - Pointer to buffer location in BAR0.
+ * Return: Pointer to buffer location in BAR0.
  */
 static phys_addr_t
 _base_get_buffer_phys_bar0(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -291,7 +320,7 @@ _base_get_buffer_phys_bar0(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * @ioc: per adapter object
  * @chain_buffer_dma: Chain buffer dma address.
  *
- * @Returns - Pointer to chain buffer. Or Null on Failure.
+ * Return: Pointer to chain buffer. Or Null on Failure.
  */
 static void *
 _base_get_chain_buffer_dma_to_chain_buffer(struct MPT3SAS_ADAPTER *ioc,
@@ -322,8 +351,6 @@ _base_get_chain_buffer_dma_to_chain_buffer(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object.
  * @mpi_request: mf request pointer.
  * @smid: system request message index.
- *
- * @Returns: Nothing.
  */
 static void _clone_sg_entries(struct MPT3SAS_ADAPTER *ioc,
 		void *mpi_request, u16 smid)
@@ -496,8 +523,9 @@ eob_clone_chain:
  *  mpt3sas_remove_dead_ioc_func - kthread context to remove dead ioc
  * @arg: input argument, used to derive ioc
  *
- * Return 0 if controller is removed from pci subsystem.
- * Return -1 for other case.
+ * Return:
+ * 0 if controller is removed from pci subsystem.
+ * -1 for other case.
  */
 static int mpt3sas_remove_dead_ioc_func(void *arg)
 {
@@ -517,9 +545,8 @@ static int mpt3sas_remove_dead_ioc_func(void *arg)
 /**
  * _base_fault_reset_work - workq handling ioc fault conditions
  * @work: input argument, used to derive ioc
- * Context: sleep.
  *
- * Return nothing.
+ * Context: sleep.
  */
 static void
 _base_fault_reset_work(struct work_struct *work)
@@ -610,9 +637,8 @@ _base_fault_reset_work(struct work_struct *work)
 /**
  * mpt3sas_base_start_watchdog - start the fault_reset_work_q
  * @ioc: per adapter object
- * Context: sleep.
  *
- * Return nothing.
+ * Context: sleep.
  */
 void
 mpt3sas_base_start_watchdog(struct MPT3SAS_ADAPTER *ioc)
@@ -633,7 +659,7 @@ mpt3sas_base_start_watchdog(struct MPT3SAS_ADAPTER *ioc)
 	if (!ioc->fault_reset_work_q) {
 		pr_err(MPT3SAS_FMT "%s: failed (line=%d)\n",
 		    ioc->name, __func__, __LINE__);
-			return;
+		return;
 	}
 	spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags);
 	if (ioc->fault_reset_work_q)
@@ -646,9 +672,8 @@ mpt3sas_base_start_watchdog(struct MPT3SAS_ADAPTER *ioc)
 /**
  * mpt3sas_base_stop_watchdog - stop the fault_reset_work_q
  * @ioc: per adapter object
- * Context: sleep.
  *
- * Return nothing.
+ * Context: sleep.
  */
 void
 mpt3sas_base_stop_watchdog(struct MPT3SAS_ADAPTER *ioc)
@@ -671,8 +696,6 @@ mpt3sas_base_stop_watchdog(struct MPT3SAS_ADAPTER *ioc)
  * mpt3sas_base_fault_info - verbose translation of firmware FAULT code
  * @ioc: per adapter object
  * @fault_code: fault code
- *
- * Return nothing.
  */
 void
 mpt3sas_base_fault_info(struct MPT3SAS_ADAPTER *ioc , u16 fault_code)
@@ -721,8 +744,6 @@ mpt3sas_halt_firmware(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: per adapter object
  * @mpi_reply: reply mf payload returned from firmware
  * @request_hdr: request mf
- *
- * Return nothing.
  */
 static void
 _base_sas_ioc_info(struct MPT3SAS_ADAPTER *ioc, MPI2DefaultReply_t *mpi_reply,
@@ -945,8 +966,6 @@ _base_sas_ioc_info(struct MPT3SAS_ADAPTER *ioc, MPI2DefaultReply_t *mpi_reply,
  * _base_display_event_data - verbose translation of firmware asyn events
  * @ioc: per adapter object
  * @mpi_reply: reply mf payload returned from firmware
- *
- * Return nothing.
  */
 static void
 _base_display_event_data(struct MPT3SAS_ADAPTER *ioc,
@@ -1065,8 +1084,6 @@ _base_display_event_data(struct MPT3SAS_ADAPTER *ioc,
  * _base_sas_log_info - verbose translation of firmware log info
  * @ioc: per adapter object
  * @log_info: log info
- *
- * Return nothing.
  */
 static void
 _base_sas_log_info(struct MPT3SAS_ADAPTER *ioc , u32 log_info)
@@ -1124,8 +1141,6 @@ _base_sas_log_info(struct MPT3SAS_ADAPTER *ioc , u32 log_info)
  * @smid: system request message index
  * @msix_index: MSIX table index supplied by the OS
  * @reply: reply message frame(lower 32bit addr)
- *
- * Return nothing.
  */
 static void
 _base_display_reply_info(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
@@ -1167,8 +1182,9 @@ _base_display_reply_info(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
  * @msix_index: MSIX table index supplied by the OS
  * @reply: reply message frame(lower 32bit addr)
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return:
+ * 1 meaning mf should be freed from _base_interrupt
+ * 0 means the mf is freed from this function.
  */
 u8
 mpt3sas_base_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
@@ -1200,8 +1216,9 @@ mpt3sas_base_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
  * @msix_index: MSIX table index supplied by the OS
  * @reply: reply message frame(lower 32bit addr)
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return:
+ * 1 meaning mf should be freed from _base_interrupt
+ * 0 means the mf is freed from this function.
  */
 static u8
 _base_async_event(struct MPT3SAS_ADAPTER *ioc, u8 msix_index, u32 reply)
@@ -1279,7 +1296,7 @@ _get_st_from_smid(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * @ioc: per adapter object
  * @smid: system request message index
  *
- * Return callback index.
+ * Return: callback index.
  */
 static u8
 _base_get_cb_idx(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -1312,8 +1329,6 @@ _base_get_cb_idx(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * @ioc: per adapter object
  *
  * Disabling ResetIRQ, Reply and Doorbell Interrupts
- *
- * Return nothing.
  */
 static void
 _base_mask_interrupts(struct MPT3SAS_ADAPTER *ioc)
@@ -1332,8 +1347,6 @@ _base_mask_interrupts(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: per adapter object
  *
  * Enabling only Reply Interrupts
- *
- * Return nothing.
  */
 static void
 _base_unmask_interrupts(struct MPT3SAS_ADAPTER *ioc)
@@ -1358,9 +1371,8 @@ union reply_descriptor {
  * _base_interrupt - MPT adapter (IOC) specific interrupt handler.
  * @irq: irq number (not used)
  * @bus_id: bus identifier cookie == pointer to MPT_ADAPTER structure
- * @r: pt_regs pointer (not used)
  *
- * Return IRQ_HANDLE if processed, else IRQ_NONE.
+ * Return: IRQ_HANDLED if processed, else IRQ_NONE.
  */
 static irqreturn_t
 _base_interrupt(int irq, void *bus_id)
@@ -1535,6 +1547,7 @@ _base_interrupt(int irq, void *bus_id)
  * _base_is_controller_msix_enabled - is controller support muli-reply queues
  * @ioc: per adapter object
  *
+ * Return: Whether or not MSI/X is enabled.
  */
 static inline int
 _base_is_controller_msix_enabled(struct MPT3SAS_ADAPTER *ioc)
@@ -1549,8 +1562,6 @@ _base_is_controller_msix_enabled(struct MPT3SAS_ADAPTER *ioc)
  * Context: non ISR conext
  *
  * Called when a Task Management request has completed.
- *
- * Return nothing.
  */
 void
 mpt3sas_base_sync_reply_irqs(struct MPT3SAS_ADAPTER *ioc)
@@ -1577,8 +1588,6 @@ mpt3sas_base_sync_reply_irqs(struct MPT3SAS_ADAPTER *ioc)
 /**
  * mpt3sas_base_release_callback_handler - clear interrupt callback handler
  * @cb_idx: callback index
- *
- * Return nothing.
  */
 void
 mpt3sas_base_release_callback_handler(u8 cb_idx)
@@ -1590,7 +1599,7 @@ mpt3sas_base_release_callback_handler(u8 cb_idx)
  * mpt3sas_base_register_callback_handler - obtain index for the interrupt callback handler
  * @cb_func: callback function
  *
- * Returns cb_func.
+ * Return: Index of @cb_func.
  */
 u8
 mpt3sas_base_register_callback_handler(MPT_CALLBACK cb_func)
@@ -1607,8 +1616,6 @@ mpt3sas_base_register_callback_handler(MPT_CALLBACK cb_func)
 
 /**
  * mpt3sas_base_initialize_callback_handler - initialize the interrupt callback handler
- *
- * Return nothing.
  */
 void
 mpt3sas_base_initialize_callback_handler(void)
@@ -1628,8 +1635,6 @@ mpt3sas_base_initialize_callback_handler(void)
  * Create a zero length scatter gather entry to insure the IOCs hardware has
  * something to use if the target device goes brain dead and tries
  * to send data even when none is asked for.
- *
- * Return nothing.
  */
 static void
 _base_build_zero_len_sge(struct MPT3SAS_ADAPTER *ioc, void *paddr)
@@ -1646,8 +1651,6 @@ _base_build_zero_len_sge(struct MPT3SAS_ADAPTER *ioc, void *paddr)
  * @paddr: virtual address for SGE
  * @flags_length: SGE flags and data transfer length
  * @dma_addr: Physical address
- *
- * Return nothing.
  */
 static void
 _base_add_sg_single_32(void *paddr, u32 flags_length, dma_addr_t dma_addr)
@@ -1666,8 +1669,6 @@ _base_add_sg_single_32(void *paddr, u32 flags_length, dma_addr_t dma_addr)
  * @paddr: virtual address for SGE
  * @flags_length: SGE flags and data transfer length
  * @dma_addr: Physical address
- *
- * Return nothing.
  */
 static void
 _base_add_sg_single_64(void *paddr, u32 flags_length, dma_addr_t dma_addr)
@@ -1685,7 +1686,7 @@ _base_add_sg_single_64(void *paddr, u32 flags_length, dma_addr_t dma_addr)
  * @ioc: per adapter object
  * @scmd: SCSI commands of the IO request
  *
- * Returns chain tracker from chain_lookup table using key as
+ * Return: chain tracker from chain_lookup table using key as
  * smid and smid's chain_offset.
  */
 static struct chain_tracker *
@@ -1715,8 +1716,6 @@ _base_get_chain_buffer_tracker(struct MPT3SAS_ADAPTER *ioc,
  * @data_out_sz: data xfer size for WRITES
  * @data_in_dma: physical address for READS
  * @data_in_sz: data xfer size for READS
- *
- * Return nothing.
  */
 static void
 _base_build_sg(struct MPT3SAS_ADAPTER *ioc, void *psge,
@@ -1777,7 +1776,7 @@ _base_build_sg(struct MPT3SAS_ADAPTER *ioc, void *psge,
  * describes the first data memory segment, and PRP2 contains a pointer to a PRP
  * list located elsewhere in memory to describe the remaining data memory
  * segments.  The PRP list will be contiguous.
-
+ *
  * The native SGL for NVMe devices is a Physical Region Page (PRP).  A PRP
  * consists of a list of PRP entries to describe a number of noncontigous
  * physical memory segments as a single memory buffer, just as a SGL does.  Note
@@ -1820,8 +1819,6 @@ _base_build_sg(struct MPT3SAS_ADAPTER *ioc, void *psge,
  * @data_out_sz: data xfer size for WRITES
  * @data_in_dma: physical address for READS
  * @data_in_sz: data xfer size for READS
- *
- * Returns nothing.
  */
 static void
 _base_build_nvme_prp(struct MPT3SAS_ADAPTER *ioc, u16 smid,
@@ -1836,6 +1833,8 @@ _base_build_nvme_prp(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 	u32		offset, entry_len;
 	u32		page_mask_result, page_mask;
 	size_t		length;
+	struct mpt3sas_nvme_cmd *nvme_cmd =
+		(void *)nvme_encap_request->NVMe_Command;
 
 	/*
 	 * Not all commands require a data transfer. If no data, just return
@@ -1843,15 +1842,8 @@ _base_build_nvme_prp(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 	 */
 	if (!data_in_sz && !data_out_sz)
 		return;
-	/*
-	 * Set pointers to PRP1 and PRP2, which are in the NVMe command.
-	 * PRP1 is located at a 24 byte offset from the start of the NVMe
-	 * command.  Then set the current PRP entry pointer to PRP1.
-	 */
-	prp1_entry = (__le64 *)(nvme_encap_request->NVMe_Command +
-	    NVME_CMD_PRP1_OFFSET);
-	prp2_entry = (__le64 *)(nvme_encap_request->NVMe_Command +
-	    NVME_CMD_PRP2_OFFSET);
+	prp1_entry = &nvme_cmd->prp1;
+	prp2_entry = &nvme_cmd->prp2;
 	prp_entry = prp1_entry;
 	/*
 	 * For the PRP entries, use the specially allocated buffer of
@@ -1992,7 +1984,7 @@ _base_build_nvme_prp(struct MPT3SAS_ADAPTER *ioc, u16 smid,
  * @smid:		msg Index
  * @sge_count:		scatter gather element count.
  *
- * Returns:		true: PRPs are built
+ * Return:		true: PRPs are built
  *			false: IEEE SGLs needs to be built
  */
 static void
@@ -2127,11 +2119,9 @@ base_is_prp_possible(struct MPT3SAS_ADAPTER *ioc,
 	struct _pcie_device *pcie_device, struct scsi_cmnd *scmd, int sge_count)
 {
 	u32 data_length = 0;
-	struct scatterlist *sg_scmd;
 	bool build_prp = true;
 
 	data_length = scsi_bufflen(scmd);
-	sg_scmd = scsi_sglist(scmd);
 
 	/* If Datalenth is <= 16K and number of SGE’s entries are <= 2
 	 * we built IEEE SGL
@@ -2155,18 +2145,16 @@ base_is_prp_possible(struct MPT3SAS_ADAPTER *ioc,
  * @scmd: scsi command
  * @pcie_device: points to the PCIe device's info
  *
- * Returns 0 if native SGL was built, 1 if no SGL was built
+ * Return: 0 if native SGL was built, 1 if no SGL was built
  */
 static int
 _base_check_pcie_native_sgl(struct MPT3SAS_ADAPTER *ioc,
 	Mpi25SCSIIORequest_t *mpi_request, u16 smid, struct scsi_cmnd *scmd,
 	struct _pcie_device *pcie_device)
 {
-	struct scatterlist *sg_scmd;
 	int sges_left;
 
 	/* Get the SG list pointer and info. */
-	sg_scmd = scsi_sglist(scmd);
 	sges_left = scsi_dma_map(scmd);
 	if (sges_left < 0) {
 		sdev_printk(KERN_ERR, scmd->device,
@@ -2201,8 +2189,6 @@ out:
  * @chain_offset: number of 128 byte elements from start of segment
  * @length: data transfer length
  * @dma_addr: Physical address
- *
- * Return nothing.
  */
 static void
 _base_add_sg_single_ieee(void *paddr, u8 flags, u8 chain_offset, u32 length,
@@ -2224,8 +2210,6 @@ _base_add_sg_single_ieee(void *paddr, u8 flags, u8 chain_offset, u32 length,
  * Create a zero length scatter gather entry to insure the IOCs hardware has
  * something to use if the target device goes brain dead and tries
  * to send data even when none is asked for.
- *
- * Return nothing.
  */
 static void
 _base_build_zero_len_sge_ieee(struct MPT3SAS_ADAPTER *ioc, void *paddr)
@@ -2249,7 +2233,7 @@ _base_build_zero_len_sge_ieee(struct MPT3SAS_ADAPTER *ioc, void *paddr)
  * The main routine that builds scatter gather table from a given
  * scsi request sent via the .queuecommand main handler.
  *
- * Returns 0 success, anything else error
+ * Return: 0 success, anything else error
  */
 static int
 _base_build_sg_scmd(struct MPT3SAS_ADAPTER *ioc,
@@ -2394,7 +2378,7 @@ _base_build_sg_scmd(struct MPT3SAS_ADAPTER *ioc,
  * The main routine that builds scatter gather table from a given
  * scsi request sent via the .queuecommand main handler.
  *
- * Returns 0 success, anything else error
+ * Return: 0 success, anything else error
  */
 static int
 _base_build_sg_scmd_ieee(struct MPT3SAS_ADAPTER *ioc,
@@ -2525,8 +2509,6 @@ _base_build_sg_scmd_ieee(struct MPT3SAS_ADAPTER *ioc,
  * @data_out_sz: data xfer size for WRITES
  * @data_in_dma: physical address for READS
  * @data_in_sz: data xfer size for READS
- *
- * Return nothing.
  */
 static void
 _base_build_sg_ieee(struct MPT3SAS_ADAPTER *ioc, void *psge,
@@ -2576,7 +2558,7 @@ _base_build_sg_ieee(struct MPT3SAS_ADAPTER *ioc, void *psge,
  * @ioc: per adapter object
  * @pdev: PCI device struct
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_config_dma_addressing(struct MPT3SAS_ADAPTER *ioc, struct pci_dev *pdev)
@@ -2924,10 +2906,9 @@ mpt3sas_base_unmap_resources(struct MPT3SAS_ADAPTER *ioc)
 	_base_free_irq(ioc);
 	_base_disable_msix(ioc);
 
-	if (ioc->combined_reply_queue) {
-		kfree(ioc->replyPostRegisterIndex);
-		ioc->replyPostRegisterIndex = NULL;
-	}
+	kfree(ioc->replyPostRegisterIndex);
+	ioc->replyPostRegisterIndex = NULL;
+
 
 	if (ioc->chip_phys) {
 		iounmap(ioc->chip);
@@ -2945,7 +2926,7 @@ mpt3sas_base_unmap_resources(struct MPT3SAS_ADAPTER *ioc)
  * mpt3sas_base_map_resources - map in controller resources (io/irq/memap)
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_base_map_resources(struct MPT3SAS_ADAPTER *ioc)
@@ -3034,7 +3015,7 @@ mpt3sas_base_map_resources(struct MPT3SAS_ADAPTER *ioc)
 	/* Use the Combined reply queue feature only for SAS3 C0 & higher
 	 * revision HBAs and also only when reply queue count is greater than 8
 	 */
-	if (ioc->combined_reply_queue && ioc->reply_queue_count > 8) {
+	if (ioc->combined_reply_queue) {
 		/* Determine the Supplemental Reply Post Host Index Registers
 		 * Addresse. Supplemental Reply Post Host Index Registers
 		 * starts at offset MPI25_SUP_REPLY_POST_HOST_INDEX_OFFSET and
@@ -3058,8 +3039,7 @@ mpt3sas_base_map_resources(struct MPT3SAS_ADAPTER *ioc)
 			     MPI25_SUP_REPLY_POST_HOST_INDEX_OFFSET +
 			     (i * MPT3_SUP_REPLY_POST_HOST_INDEX_REG_OFFSET));
 		}
-	} else
-		ioc->combined_reply_queue = 0;
+	}
 
 	if (ioc->is_warpdrive) {
 		ioc->reply_post_host_index[0] = (resource_size_t __iomem *)
@@ -3097,7 +3077,7 @@ mpt3sas_base_map_resources(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: per adapter object
  * @smid: system request message index(smid zero is invalid)
  *
- * Returns virt pointer to message frame.
+ * Return: virt pointer to message frame.
  */
 void *
 mpt3sas_base_get_msg_frame(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -3110,7 +3090,7 @@ mpt3sas_base_get_msg_frame(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * @ioc: per adapter object
  * @smid: system request message index
  *
- * Returns virt pointer to sense buffer.
+ * Return: virt pointer to sense buffer.
  */
 void *
 mpt3sas_base_get_sense_buffer(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -3123,7 +3103,7 @@ mpt3sas_base_get_sense_buffer(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * @ioc: per adapter object
  * @smid: system request message index
  *
- * Returns phys pointer to the low 32bit address of the sense buffer.
+ * Return: phys pointer to the low 32bit address of the sense buffer.
  */
 __le32
 mpt3sas_base_get_sense_buffer_dma(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -3137,7 +3117,7 @@ mpt3sas_base_get_sense_buffer_dma(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * @ioc: per adapter object
  * @smid: system request message index
  *
- * Returns virt pointer to a PCIe SGL.
+ * Return: virt pointer to a PCIe SGL.
  */
 void *
 mpt3sas_base_get_pcie_sgl(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -3150,7 +3130,7 @@ mpt3sas_base_get_pcie_sgl(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * @ioc: per adapter object
  * @smid: system request message index
  *
- * Returns phys pointer to the address of the PCIe buffer.
+ * Return: phys pointer to the address of the PCIe buffer.
  */
 dma_addr_t
 mpt3sas_base_get_pcie_sgl_dma(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -3184,7 +3164,7 @@ _base_get_msix_index(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: per adapter object
  * @cb_idx: callback index
  *
- * Returns smid (zero is invalid)
+ * Return: smid (zero is invalid)
  */
 u16
 mpt3sas_base_get_smid(struct MPT3SAS_ADAPTER *ioc, u8 cb_idx)
@@ -3216,7 +3196,7 @@ mpt3sas_base_get_smid(struct MPT3SAS_ADAPTER *ioc, u8 cb_idx)
  * @cb_idx: callback index
  * @scmd: pointer to scsi command object
  *
- * Returns smid (zero is invalid)
+ * Return: smid (zero is invalid)
  */
 u16
 mpt3sas_base_get_smid_scsiio(struct MPT3SAS_ADAPTER *ioc, u8 cb_idx,
@@ -3239,7 +3219,7 @@ mpt3sas_base_get_smid_scsiio(struct MPT3SAS_ADAPTER *ioc, u8 cb_idx,
  * @ioc: per adapter object
  * @cb_idx: callback index
  *
- * Returns smid (zero is invalid)
+ * Return: smid (zero is invalid)
  */
 u16
 mpt3sas_base_get_smid_hpr(struct MPT3SAS_ADAPTER *ioc, u8 cb_idx)
@@ -3270,7 +3250,7 @@ _base_recovery_check(struct MPT3SAS_ADAPTER *ioc)
 	 * See _wait_for_commands_to_complete() call with regards to this code.
 	 */
 	if (ioc->shost_recovery && ioc->pending_io_count) {
-		ioc->pending_io_count = atomic_read(&ioc->shost->host_busy);
+		ioc->pending_io_count = scsi_host_busy(ioc->shost);
 		if (ioc->pending_io_count == 0)
 			wake_up(&ioc->reset_wq);
 	}
@@ -3284,14 +3264,13 @@ void mpt3sas_base_clear_st(struct MPT3SAS_ADAPTER *ioc,
 	st->cb_idx = 0xFF;
 	st->direct_io = 0;
 	atomic_set(&ioc->chain_lookup[st->smid - 1].chain_offset, 0);
+	st->smid = 0;
 }
 
 /**
  * mpt3sas_base_free_smid - put smid back on free_list
  * @ioc: per adapter object
  * @smid: system request message index
- *
- * Return nothing.
  */
 void
 mpt3sas_base_free_smid(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -3353,7 +3332,6 @@ _base_mpi_ep_writeq(__u64 b, volatile void __iomem *addr,
 
 /**
  * _base_writeq - 64 bit write to MMIO
- * @ioc: per adapter object
  * @b: data payload
  * @addr: address in MMIO space
  * @writeq_lock: spin lock
@@ -3382,8 +3360,6 @@ _base_writeq(__u64 b, volatile void __iomem *addr, spinlock_t *writeq_lock)
  * @ioc: per adapter object
  * @smid: system request message index
  * @handle: device handle
- *
- * Return nothing.
  */
 static void
 _base_put_smid_mpi_ep_scsi_io(struct MPT3SAS_ADAPTER *ioc, u16 smid, u16 handle)
@@ -3412,8 +3388,6 @@ _base_put_smid_mpi_ep_scsi_io(struct MPT3SAS_ADAPTER *ioc, u16 smid, u16 handle)
  * @ioc: per adapter object
  * @smid: system request message index
  * @handle: device handle
- *
- * Return nothing.
  */
 static void
 _base_put_smid_scsi_io(struct MPT3SAS_ADAPTER *ioc, u16 smid, u16 handle)
@@ -3436,8 +3410,6 @@ _base_put_smid_scsi_io(struct MPT3SAS_ADAPTER *ioc, u16 smid, u16 handle)
  * @ioc: per adapter object
  * @smid: system request message index
  * @handle: device handle
- *
- * Return nothing.
  */
 void
 mpt3sas_base_put_smid_fast_path(struct MPT3SAS_ADAPTER *ioc, u16 smid,
@@ -3461,7 +3433,6 @@ mpt3sas_base_put_smid_fast_path(struct MPT3SAS_ADAPTER *ioc, u16 smid,
  * @ioc: per adapter object
  * @smid: system request message index
  * @msix_task: msix_task will be same as msix of IO incase of task abort else 0.
- * Return nothing.
  */
 void
 mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc, u16 smid,
@@ -3472,11 +3443,8 @@ mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 	u64 *request;
 
 	if (ioc->is_mcpu_endpoint) {
-		MPI2RequestHeader_t *request_hdr;
-
 		__le32 *mfp = (__le32 *)mpt3sas_base_get_msg_frame(ioc, smid);
 
-		request_hdr = (MPI2RequestHeader_t *)mfp;
 		/* TBD 256 is offset within sys register. */
 		mpi_req_iomem = (void __force *)ioc->chip
 					+ MPI_FRAME_START_OFFSET
@@ -3507,8 +3475,6 @@ mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc, u16 smid,
  *  firmware
  * @ioc: per adapter object
  * @smid: system request message index
- *
- * Return nothing.
  */
 void
 mpt3sas_base_put_smid_nvme_encap(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -3530,8 +3496,6 @@ mpt3sas_base_put_smid_nvme_encap(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * mpt3sas_base_put_smid_default - Default, primarily used for config pages
  * @ioc: per adapter object
  * @smid: system request message index
- *
- * Return nothing.
  */
 void
 mpt3sas_base_put_smid_default(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -3539,13 +3503,10 @@ mpt3sas_base_put_smid_default(struct MPT3SAS_ADAPTER *ioc, u16 smid)
 	Mpi2RequestDescriptorUnion_t descriptor;
 	void *mpi_req_iomem;
 	u64 *request;
-	MPI2RequestHeader_t *request_hdr;
 
 	if (ioc->is_mcpu_endpoint) {
 		__le32 *mfp = (__le32 *)mpt3sas_base_get_msg_frame(ioc, smid);
 
-		request_hdr = (MPI2RequestHeader_t *)mfp;
-
 		_clone_sg_entries(ioc, (void *) mfp, smid);
 		/* TBD 256 is offset within sys register */
 		mpi_req_iomem = (void __force *)ioc->chip +
@@ -3571,8 +3532,6 @@ mpt3sas_base_put_smid_default(struct MPT3SAS_ADAPTER *ioc, u16 smid)
 /**
  * _base_display_OEMs_branding - Display branding string
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 static void
 _base_display_OEMs_branding(struct MPT3SAS_ADAPTER *ioc)
@@ -3833,7 +3792,7 @@ _base_display_OEMs_branding(struct MPT3SAS_ADAPTER *ioc)
  *				version from FW Image Header.
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 	static int
 _base_display_fwpkg_version(struct MPT3SAS_ADAPTER *ioc)
@@ -3930,8 +3889,6 @@ out:
 /**
  * _base_display_ioc_capabilities - Disply IOC's capabilities.
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 static void
 _base_display_ioc_capabilities(struct MPT3SAS_ADAPTER *ioc)
@@ -4047,8 +4004,6 @@ _base_display_ioc_capabilities(struct MPT3SAS_ADAPTER *ioc)
  * @device_missing_delay: amount of time till device is reported missing
  * @io_missing_delay: interval IO is returned when there is a missing device
  *
- * Return nothing.
- *
  * Passed on the command line, this function will modify the device missing
  * delay, as well as the io missing delay. This should be called at driver
  * load time.
@@ -4131,11 +4086,10 @@ mpt3sas_base_update_missing_delay(struct MPT3SAS_ADAPTER *ioc,
 out:
 	kfree(sas_iounit_pg1);
 }
+
 /**
  * _base_static_config_pages - static start of day config pages
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 static void
 _base_static_config_pages(struct MPT3SAS_ADAPTER *ioc)
@@ -4207,8 +4161,6 @@ _base_static_config_pages(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: per adapter object
  *
  * Free memory allocated during encloure add.
- *
- * Return nothing.
  */
 void
 mpt3sas_free_enclosure_list(struct MPT3SAS_ADAPTER *ioc)
@@ -4228,8 +4180,6 @@ mpt3sas_free_enclosure_list(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: per adapter object
  *
  * Free memory allocated from _base_allocate_memory_pools.
- *
- * Return nothing.
  */
 static void
 _base_release_memory_pools(struct MPT3SAS_ADAPTER *ioc)
@@ -4350,9 +4300,8 @@ _base_release_memory_pools(struct MPT3SAS_ADAPTER *ioc)
  * @reply_pool_start_address: Base address of a reply queue set
  * @pool_sz: Size of single Reply Descriptor Post Queues pool size
  *
- * Returns 1 if reply queues in a set have a same upper 32bits
- * in their base memory address,
- * else 0
+ * Return: 1 if reply queues in a set have a same upper 32bits in their base
+ * memory address, else 0.
  */
 
 static int
@@ -4373,7 +4322,7 @@ is_MSB_are_same(long reply_pool_start_address, u32 pool_sz)
  * _base_allocate_memory_pools - allocate start of day memory pools
  * @ioc: per adapter object
  *
- * Returns 0 success, anything else error
+ * Return: 0 success, anything else error.
  */
 static int
 _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc)
@@ -4975,7 +4924,7 @@ _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: Pointer to MPT_ADAPTER structure
  * @cooked: Request raw or cooked IOC state
  *
- * Returns all IOC Doorbell register bits if cooked==0, else just the
+ * Return: all IOC Doorbell register bits if cooked==0, else just the
  * Doorbell bits in MPI_IOC_STATE_MASK.
  */
 u32
@@ -4990,10 +4939,11 @@ mpt3sas_base_get_iocstate(struct MPT3SAS_ADAPTER *ioc, int cooked)
 
 /**
  * _base_wait_on_iocstate - waiting on a particular ioc state
+ * @ioc: ?
  * @ioc_state: controller state { READY, OPERATIONAL, or RESET }
  * @timeout: timeout in second
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_wait_on_iocstate(struct MPT3SAS_ADAPTER *ioc, u32 ioc_state, int timeout)
@@ -5021,9 +4971,8 @@ _base_wait_on_iocstate(struct MPT3SAS_ADAPTER *ioc, u32 ioc_state, int timeout)
  * _base_wait_for_doorbell_int - waiting for controller interrupt(generated by
  * a write to the doorbell)
  * @ioc: per adapter object
- * @timeout: timeout in second
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  *
  * Notes: MPI2_HIS_IOC2SYS_DB_STATUS - set to one when IOC writes to doorbell.
  */
@@ -5090,7 +5039,7 @@ _base_spin_on_doorbell_int(struct MPT3SAS_ADAPTER *ioc, int timeout)
  * @ioc: per adapter object
  * @timeout: timeout in second
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  *
  * Notes: MPI2_HIS_SYS2IOC_DB_STATUS - set to one when host writes to
  * doorbell.
@@ -5137,8 +5086,7 @@ _base_wait_for_doorbell_ack(struct MPT3SAS_ADAPTER *ioc, int timeout)
  * @ioc: per adapter object
  * @timeout: timeout in second
  *
- * Returns 0 for success, non-zero for failure.
- *
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_wait_for_doorbell_not_used(struct MPT3SAS_ADAPTER *ioc, int timeout)
@@ -5173,7 +5121,7 @@ _base_wait_for_doorbell_not_used(struct MPT3SAS_ADAPTER *ioc, int timeout)
  * @reset_type: currently only supports: MPI2_FUNCTION_IOC_MESSAGE_UNIT_RESET
  * @timeout: timeout in second
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_send_ioc_reset(struct MPT3SAS_ADAPTER *ioc, u8 reset_type, int timeout)
@@ -5222,7 +5170,7 @@ _base_send_ioc_reset(struct MPT3SAS_ADAPTER *ioc, u8 reset_type, int timeout)
  * @reply: pointer to reply payload
  * @timeout: timeout in second
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
@@ -5346,7 +5294,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
  * identifying information about the device, in addition allows the host to
  * remove IOC resources associated with the device.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_base_sas_iounit_control(struct MPT3SAS_ADAPTER *ioc,
@@ -5355,7 +5303,7 @@ mpt3sas_base_sas_iounit_control(struct MPT3SAS_ADAPTER *ioc,
 {
 	u16 smid;
 	u32 ioc_state;
-	bool issue_reset = false;
+	u8 issue_reset = 0;
 	int rc;
 	void *request;
 	u16 wait_state_count;
@@ -5414,12 +5362,10 @@ mpt3sas_base_sas_iounit_control(struct MPT3SAS_ADAPTER *ioc,
 	    ioc->ioc_link_reset_in_progress)
 		ioc->ioc_link_reset_in_progress = 0;
 	if (!(ioc->base_cmds.status & MPT3_CMD_COMPLETE)) {
-		pr_err(MPT3SAS_FMT "%s: timeout\n",
-		    ioc->name, __func__);
-		_debug_dump_mf(mpi_request,
-		    sizeof(Mpi2SasIoUnitControlRequest_t)/4);
-		if (!(ioc->base_cmds.status & MPT3_CMD_RESET))
-			issue_reset = true;
+		issue_reset =
+			mpt3sas_base_check_cmd_timeout(ioc,
+				ioc->base_cmds.status, mpi_request,
+				sizeof(Mpi2SasIoUnitControlRequest_t)/4);
 		goto issue_host_reset;
 	}
 	if (ioc->base_cmds.status & MPT3_CMD_REPLY_VALID)
@@ -5449,7 +5395,7 @@ mpt3sas_base_sas_iounit_control(struct MPT3SAS_ADAPTER *ioc,
  * The SCSI Enclosure Processor request message causes the IOC to
  * communicate with SES devices to control LED status signals.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_base_scsi_enclosure_processor(struct MPT3SAS_ADAPTER *ioc,
@@ -5457,7 +5403,7 @@ mpt3sas_base_scsi_enclosure_processor(struct MPT3SAS_ADAPTER *ioc,
 {
 	u16 smid;
 	u32 ioc_state;
-	bool issue_reset = false;
+	u8 issue_reset = 0;
 	int rc;
 	void *request;
 	u16 wait_state_count;
@@ -5510,12 +5456,10 @@ mpt3sas_base_scsi_enclosure_processor(struct MPT3SAS_ADAPTER *ioc,
 	wait_for_completion_timeout(&ioc->base_cmds.done,
 	    msecs_to_jiffies(10000));
 	if (!(ioc->base_cmds.status & MPT3_CMD_COMPLETE)) {
-		pr_err(MPT3SAS_FMT "%s: timeout\n",
-		    ioc->name, __func__);
-		_debug_dump_mf(mpi_request,
-		    sizeof(Mpi2SepRequest_t)/4);
-		if (!(ioc->base_cmds.status & MPT3_CMD_RESET))
-			issue_reset = false;
+		issue_reset =
+			mpt3sas_base_check_cmd_timeout(ioc,
+				ioc->base_cmds.status, mpi_request,
+				sizeof(Mpi2SepRequest_t)/4);
 		goto issue_host_reset;
 	}
 	if (ioc->base_cmds.status & MPT3_CMD_REPLY_VALID)
@@ -5539,8 +5483,9 @@ mpt3sas_base_scsi_enclosure_processor(struct MPT3SAS_ADAPTER *ioc,
 /**
  * _base_get_port_facts - obtain port facts reply and save in ioc
  * @ioc: per adapter object
+ * @port: ?
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_get_port_facts(struct MPT3SAS_ADAPTER *ioc, int port)
@@ -5583,7 +5528,7 @@ _base_get_port_facts(struct MPT3SAS_ADAPTER *ioc, int port)
  * @ioc: per adapter object
  * @timeout:
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_wait_for_iocstate(struct MPT3SAS_ADAPTER *ioc, int timeout)
@@ -5637,7 +5582,7 @@ _base_wait_for_iocstate(struct MPT3SAS_ADAPTER *ioc, int timeout)
  * _base_get_ioc_facts - obtain ioc facts reply and save in ioc
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_get_ioc_facts(struct MPT3SAS_ADAPTER *ioc)
@@ -5681,6 +5626,9 @@ _base_get_ioc_facts(struct MPT3SAS_ADAPTER *ioc)
 	facts->WhoInit = mpi_reply.WhoInit;
 	facts->NumberOfPorts = mpi_reply.NumberOfPorts;
 	facts->MaxMSIxVectors = mpi_reply.MaxMSIxVectors;
+	if (ioc->msix_enable && (facts->MaxMSIxVectors <=
+	    MAX_COMBINED_MSIX_VECTORS(ioc->is_gen35_ioc)))
+		ioc->combined_reply_queue = 0;
 	facts->RequestCredit = le16_to_cpu(mpi_reply.RequestCredit);
 	facts->MaxReplyDescriptorPostQueueDepth =
 	    le16_to_cpu(mpi_reply.MaxReplyDescriptorPostQueueDepth);
@@ -5736,7 +5684,7 @@ _base_get_ioc_facts(struct MPT3SAS_ADAPTER *ioc)
  * _base_send_ioc_init - send ioc_init to firmware
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_send_ioc_init(struct MPT3SAS_ADAPTER *ioc)
@@ -5837,8 +5785,8 @@ _base_send_ioc_init(struct MPT3SAS_ADAPTER *ioc)
  * @msix_index: MSIX table index supplied by the OS
  * @reply: reply message frame(lower 32bit addr)
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *          0 means the mf is freed from this function.
  */
 u8
 mpt3sas_port_enable_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
@@ -5883,7 +5831,7 @@ mpt3sas_port_enable_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
  * _base_send_port_enable - send port_enable(discovery stuff) to firmware
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_send_port_enable(struct MPT3SAS_ADAPTER *ioc)
@@ -5950,7 +5898,7 @@ _base_send_port_enable(struct MPT3SAS_ADAPTER *ioc)
  * mpt3sas_port_enable - initiate firmware discovery (don't wait for reply)
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_port_enable(struct MPT3SAS_ADAPTER *ioc)
@@ -5990,7 +5938,7 @@ mpt3sas_port_enable(struct MPT3SAS_ADAPTER *ioc)
  * Decide whether to wait on discovery to complete. Used to either
  * locate boot device, or report volumes ahead of physical devices.
  *
- * Returns 1 for wait, 0 for don't wait
+ * Return: 1 for wait, 0 for don't wait.
  */
 static int
 _base_determine_wait_on_discovery(struct MPT3SAS_ADAPTER *ioc)
@@ -6062,7 +6010,7 @@ _base_unmask_events(struct MPT3SAS_ADAPTER *ioc, u16 event)
  * _base_event_notification - send event notification
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_event_notification(struct MPT3SAS_ADAPTER *ioc)
@@ -6119,7 +6067,7 @@ _base_event_notification(struct MPT3SAS_ADAPTER *ioc)
 /**
  * mpt3sas_base_validate_event_type - validating event types
  * @ioc: per adapter object
- * @event: firmware event
+ * @event_type: firmware event
  *
  * This will turn on firmware event notification when application
  * ask for that event. We don't mask events that are already enabled.
@@ -6157,7 +6105,7 @@ mpt3sas_base_validate_event_type(struct MPT3SAS_ADAPTER *ioc, u32 *event_type)
  * _base_diag_reset - the "big hammer" start of day reset
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_diag_reset(struct MPT3SAS_ADAPTER *ioc)
@@ -6271,7 +6219,7 @@ _base_diag_reset(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: per adapter object
  * @type: FORCE_BIG_HAMMER or SOFT_RESET
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_make_ioc_ready(struct MPT3SAS_ADAPTER *ioc, enum reset_type type)
@@ -6340,7 +6288,7 @@ _base_make_ioc_ready(struct MPT3SAS_ADAPTER *ioc, enum reset_type type)
  * _base_make_ioc_operational - put controller in OPERATIONAL state
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_make_ioc_operational(struct MPT3SAS_ADAPTER *ioc)
@@ -6513,8 +6461,6 @@ _base_make_ioc_operational(struct MPT3SAS_ADAPTER *ioc)
 /**
  * mpt3sas_base_free_resources - free resources controller resources
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 void
 mpt3sas_base_free_resources(struct MPT3SAS_ADAPTER *ioc)
@@ -6540,7 +6486,7 @@ mpt3sas_base_free_resources(struct MPT3SAS_ADAPTER *ioc)
  * mpt3sas_base_attach - attach controller instance
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
@@ -6797,8 +6743,6 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
 /**
  * mpt3sas_base_detach - remove controller instance
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 void
 mpt3sas_base_detach(struct MPT3SAS_ADAPTER *ioc)
@@ -6830,65 +6774,69 @@ mpt3sas_base_detach(struct MPT3SAS_ADAPTER *ioc)
 }
 
 /**
- * _base_reset_handler - reset callback handler (for base)
+ * _base_pre_reset_handler - pre reset handler
  * @ioc: per adapter object
- * @reset_phase: phase
- *
- * The handler for doing any required cleanup or initialization.
- *
- * The reset phase can be MPT3_IOC_PRE_RESET, MPT3_IOC_AFTER_RESET,
- * MPT3_IOC_DONE_RESET
- *
- * Return nothing.
  */
-static void
-_base_reset_handler(struct MPT3SAS_ADAPTER *ioc, int reset_phase)
+static void _base_pre_reset_handler(struct MPT3SAS_ADAPTER *ioc)
 {
-	mpt3sas_scsih_reset_handler(ioc, reset_phase);
-	mpt3sas_ctl_reset_handler(ioc, reset_phase);
-	switch (reset_phase) {
-	case MPT3_IOC_PRE_RESET:
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT
-		"%s: MPT3_IOC_PRE_RESET\n", ioc->name, __func__));
-		break;
-	case MPT3_IOC_AFTER_RESET:
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT
-		"%s: MPT3_IOC_AFTER_RESET\n", ioc->name, __func__));
-		if (ioc->transport_cmds.status & MPT3_CMD_PENDING) {
-			ioc->transport_cmds.status |= MPT3_CMD_RESET;
-			mpt3sas_base_free_smid(ioc, ioc->transport_cmds.smid);
-			complete(&ioc->transport_cmds.done);
-		}
-		if (ioc->base_cmds.status & MPT3_CMD_PENDING) {
-			ioc->base_cmds.status |= MPT3_CMD_RESET;
-			mpt3sas_base_free_smid(ioc, ioc->base_cmds.smid);
-			complete(&ioc->base_cmds.done);
-		}
-		if (ioc->port_enable_cmds.status & MPT3_CMD_PENDING) {
-			ioc->port_enable_failed = 1;
-			ioc->port_enable_cmds.status |= MPT3_CMD_RESET;
-			mpt3sas_base_free_smid(ioc, ioc->port_enable_cmds.smid);
-			if (ioc->is_driver_loading) {
-				ioc->start_scan_failed =
-				    MPI2_IOCSTATUS_INTERNAL_ERROR;
-				ioc->start_scan = 0;
-				ioc->port_enable_cmds.status =
-				    MPT3_CMD_NOT_USED;
-			} else
-				complete(&ioc->port_enable_cmds.done);
-		}
-		if (ioc->config_cmds.status & MPT3_CMD_PENDING) {
-			ioc->config_cmds.status |= MPT3_CMD_RESET;
-			mpt3sas_base_free_smid(ioc, ioc->config_cmds.smid);
-			ioc->config_cmds.smid = USHRT_MAX;
-			complete(&ioc->config_cmds.done);
+	mpt3sas_scsih_pre_reset_handler(ioc);
+	mpt3sas_ctl_pre_reset_handler(ioc);
+	dtmprintk(ioc, pr_info(MPT3SAS_FMT
+			"%s: MPT3_IOC_PRE_RESET\n", ioc->name, __func__));
+}
+
+/**
+ * _base_after_reset_handler - after reset handler
+ * @ioc: per adapter object
+ */
+static void _base_after_reset_handler(struct MPT3SAS_ADAPTER *ioc)
+{
+	mpt3sas_scsih_after_reset_handler(ioc);
+	mpt3sas_ctl_after_reset_handler(ioc);
+	dtmprintk(ioc, pr_info(MPT3SAS_FMT
+			"%s: MPT3_IOC_AFTER_RESET\n", ioc->name, __func__));
+	if (ioc->transport_cmds.status & MPT3_CMD_PENDING) {
+		ioc->transport_cmds.status |= MPT3_CMD_RESET;
+		mpt3sas_base_free_smid(ioc, ioc->transport_cmds.smid);
+		complete(&ioc->transport_cmds.done);
+	}
+	if (ioc->base_cmds.status & MPT3_CMD_PENDING) {
+		ioc->base_cmds.status |= MPT3_CMD_RESET;
+		mpt3sas_base_free_smid(ioc, ioc->base_cmds.smid);
+		complete(&ioc->base_cmds.done);
+	}
+	if (ioc->port_enable_cmds.status & MPT3_CMD_PENDING) {
+		ioc->port_enable_failed = 1;
+		ioc->port_enable_cmds.status |= MPT3_CMD_RESET;
+		mpt3sas_base_free_smid(ioc, ioc->port_enable_cmds.smid);
+		if (ioc->is_driver_loading) {
+			ioc->start_scan_failed =
+				MPI2_IOCSTATUS_INTERNAL_ERROR;
+			ioc->start_scan = 0;
+			ioc->port_enable_cmds.status =
+				MPT3_CMD_NOT_USED;
+		} else {
+			complete(&ioc->port_enable_cmds.done);
 		}
-		break;
-	case MPT3_IOC_DONE_RESET:
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT
-			"%s: MPT3_IOC_DONE_RESET\n", ioc->name, __func__));
-		break;
 	}
+	if (ioc->config_cmds.status & MPT3_CMD_PENDING) {
+		ioc->config_cmds.status |= MPT3_CMD_RESET;
+		mpt3sas_base_free_smid(ioc, ioc->config_cmds.smid);
+		ioc->config_cmds.smid = USHRT_MAX;
+		complete(&ioc->config_cmds.done);
+	}
+}
+
+/**
+ * _base_reset_done_handler - reset done handler
+ * @ioc: per adapter object
+ */
+static void _base_reset_done_handler(struct MPT3SAS_ADAPTER *ioc)
+{
+	mpt3sas_scsih_reset_done_handler(ioc);
+	mpt3sas_ctl_reset_done_handler(ioc);
+	dtmprintk(ioc, pr_info(MPT3SAS_FMT
+			"%s: MPT3_IOC_DONE_RESET\n", ioc->name, __func__));
 }
 
 /**
@@ -6910,7 +6858,7 @@ mpt3sas_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc)
 		return;
 
 	/* pending command count */
-	ioc->pending_io_count = atomic_read(&ioc->shost->host_busy);
+	ioc->pending_io_count = scsi_host_busy(ioc->shost);
 
 	if (!ioc->pending_io_count)
 		return;
@@ -6924,7 +6872,7 @@ mpt3sas_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: Pointer to MPT_ADAPTER structure
  * @type: FORCE_BIG_HAMMER or SOFT_RESET
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc,
@@ -6949,14 +6897,7 @@ mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc,
 		mpt3sas_halt_firmware(ioc);
 
 	/* wait for an active reset in progress to complete */
-	if (!mutex_trylock(&ioc->reset_in_progress_mutex)) {
-		do {
-			ssleep(1);
-		} while (ioc->shost_recovery == 1);
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT "%s: exit\n", ioc->name,
-		    __func__));
-		return ioc->ioc_reset_in_progress_status;
-	}
+	mutex_lock(&ioc->reset_in_progress_mutex);
 
 	spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags);
 	ioc->shost_recovery = 1;
@@ -6971,13 +6912,13 @@ mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc,
 		if ((ioc_state & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT)
 			is_fault = 1;
 	}
-	_base_reset_handler(ioc, MPT3_IOC_PRE_RESET);
+	_base_pre_reset_handler(ioc);
 	mpt3sas_wait_for_commands_to_complete(ioc);
 	_base_mask_interrupts(ioc);
 	r = _base_make_ioc_ready(ioc, type);
 	if (r)
 		goto out;
-	_base_reset_handler(ioc, MPT3_IOC_AFTER_RESET);
+	_base_after_reset_handler(ioc);
 
 	/* If this hard reset is called while port enable is active, then
 	 * there is no reason to call make_ioc_operational
@@ -6998,14 +6939,13 @@ mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc,
 
 	r = _base_make_ioc_operational(ioc);
 	if (!r)
-		_base_reset_handler(ioc, MPT3_IOC_DONE_RESET);
+		_base_reset_done_handler(ioc);
 
  out:
 	dtmprintk(ioc, pr_info(MPT3SAS_FMT "%s: %s\n",
 	    ioc->name, __func__, ((r == 0) ? "SUCCESS" : "FAILED")));
 
 	spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags);
-	ioc->ioc_reset_in_progress_status = r;
 	ioc->shost_recovery = 0;
 	spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags);
 	ioc->ioc_reset_count++;
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index f02974c0be4a..96dc15e90bd8 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -74,8 +74,8 @@
 #define MPT3SAS_DRIVER_NAME		"mpt3sas"
 #define MPT3SAS_AUTHOR "Avago Technologies <MPT-FusionLinux.pdl@avagotech.com>"
 #define MPT3SAS_DESCRIPTION	"LSI MPT Fusion SAS 3.0 Device Driver"
-#define MPT3SAS_DRIVER_VERSION		"25.100.00.00"
-#define MPT3SAS_MAJOR_VERSION		25
+#define MPT3SAS_DRIVER_VERSION		"26.100.00.00"
+#define MPT3SAS_MAJOR_VERSION		26
 #define MPT3SAS_MINOR_VERSION		100
 #define MPT3SAS_BUILD_VERSION		0
 #define MPT3SAS_RELEASE_VERSION	00
@@ -143,21 +143,17 @@
  * NVMe defines
  */
 #define	NVME_PRP_SIZE			8	/* PRP size */
-#define	NVME_CMD_PRP1_OFFSET		24	/* PRP1 offset in NVMe cmd */
-#define	NVME_CMD_PRP2_OFFSET		32	/* PRP2 offset in NVMe cmd */
 #define	NVME_ERROR_RESPONSE_SIZE	16	/* Max NVME Error Response */
 #define NVME_TASK_ABORT_MIN_TIMEOUT	6
 #define NVME_TASK_ABORT_MAX_TIMEOUT	60
 #define NVME_TASK_MNGT_CUSTOM_MASK	(0x0010)
 #define	NVME_PRP_PAGE_SIZE		4096	/* Page size */
 
-
-/*
- * reset phases
- */
-#define MPT3_IOC_PRE_RESET		1 /* prior to host reset */
-#define MPT3_IOC_AFTER_RESET		2 /* just after host reset */
-#define MPT3_IOC_DONE_RESET		3 /* links re-initialized */
+struct mpt3sas_nvme_cmd {
+	u8	rsvd[24];
+	__le64	prp1;
+	__le64	prp2;
+};
 
 /*
  * logging format
@@ -323,6 +319,7 @@
  * There are twelve Supplemental Reply Post Host Index Registers
  * and each register is at offset 0x10 bytes from the previous one.
  */
+#define MAX_COMBINED_MSIX_VECTORS(gen35) ((gen35 == 1) ? 16 : 8)
 #define MPT3_SUP_REPLY_POST_HOST_INDEX_REG_COUNT_G3	12
 #define MPT3_SUP_REPLY_POST_HOST_INDEX_REG_COUNT_G35	16
 #define MPT3_SUP_REPLY_POST_HOST_INDEX_REG_OFFSET	(0x10)
@@ -1162,7 +1159,6 @@ struct MPT3SAS_ADAPTER {
 	struct mutex	reset_in_progress_mutex;
 	spinlock_t	ioc_reset_in_progress_lock;
 	u8		ioc_link_reset_in_progress;
-	u8		ioc_reset_in_progress_status;
 
 	u8		ignore_loginfos;
 	u8		remove_host;
@@ -1482,13 +1478,17 @@ int mpt3sas_port_enable(struct MPT3SAS_ADAPTER *ioc);
 void
 mpt3sas_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc);
 
+u8 mpt3sas_base_check_cmd_timeout(struct MPT3SAS_ADAPTER *ioc,
+	u8 status, void *mpi_request, int sz);
 
 /* scsih shared API */
 struct scsi_cmnd *mpt3sas_scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc,
 	u16 smid);
 u8 mpt3sas_scsih_event_callback(struct MPT3SAS_ADAPTER *ioc, u8 msix_index,
 	u32 reply);
-void mpt3sas_scsih_reset_handler(struct MPT3SAS_ADAPTER *ioc, int reset_phase);
+void mpt3sas_scsih_pre_reset_handler(struct MPT3SAS_ADAPTER *ioc);
+void mpt3sas_scsih_after_reset_handler(struct MPT3SAS_ADAPTER *ioc);
+void mpt3sas_scsih_reset_done_handler(struct MPT3SAS_ADAPTER *ioc);
 
 int mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle, u64 lun,
 	u8 type, u16 smid_task, u16 msix_task, u8 timeout, u8 tr_method);
@@ -1615,7 +1615,9 @@ void mpt3sas_ctl_init(ushort hbas_to_enumerate);
 void mpt3sas_ctl_exit(ushort hbas_to_enumerate);
 u8 mpt3sas_ctl_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
 	u32 reply);
-void mpt3sas_ctl_reset_handler(struct MPT3SAS_ADAPTER *ioc, int reset_phase);
+void mpt3sas_ctl_pre_reset_handler(struct MPT3SAS_ADAPTER *ioc);
+void mpt3sas_ctl_after_reset_handler(struct MPT3SAS_ADAPTER *ioc);
+void mpt3sas_ctl_reset_done_handler(struct MPT3SAS_ADAPTER *ioc);
 u8 mpt3sas_ctl_event_callback(struct MPT3SAS_ADAPTER *ioc,
 	u8 msix_index, u32 reply);
 void mpt3sas_ctl_add_to_event_log(struct MPT3SAS_ADAPTER *ioc,
diff --git a/drivers/scsi/mpt3sas/mpt3sas_config.c b/drivers/scsi/mpt3sas/mpt3sas_config.c
index e87c76a832f6..d29a2dcc7d0e 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_config.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_config.c
@@ -198,7 +198,7 @@ _config_display_some_debug(struct MPT3SAS_ADAPTER *ioc, u16 smid,
  *
  * A wrapper for obtaining dma-able memory for config page request.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _config_alloc_config_dma_memory(struct MPT3SAS_ADAPTER *ioc,
@@ -230,7 +230,7 @@ _config_alloc_config_dma_memory(struct MPT3SAS_ADAPTER *ioc,
  *
  * A wrapper to free dma-able memory when using _config_alloc_config_dma_memory.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static void
 _config_free_config_dma_memory(struct MPT3SAS_ADAPTER *ioc,
@@ -251,8 +251,8 @@ _config_free_config_dma_memory(struct MPT3SAS_ADAPTER *ioc,
  *
  * The callback handler when using _config_request.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 u8
 mpt3sas_config_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
@@ -295,7 +295,7 @@ mpt3sas_config_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
  *
  * The callback index is set inside `ioc->config_cb_idx.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _config_request(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigRequest_t
@@ -406,10 +406,9 @@ _config_request(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigRequest_t
 	mpt3sas_base_put_smid_default(ioc, smid);
 	wait_for_completion_timeout(&ioc->config_cmds.done, timeout*HZ);
 	if (!(ioc->config_cmds.status & MPT3_CMD_COMPLETE)) {
-		pr_err(MPT3SAS_FMT "%s: timeout\n",
-		    ioc->name, __func__);
-		_debug_dump_mf(mpi_request,
-		    sizeof(Mpi2ConfigRequest_t)/4);
+		mpt3sas_base_check_cmd_timeout(ioc,
+			ioc->config_cmds.status, mpi_request,
+			sizeof(Mpi2ConfigRequest_t)/4);
 		retry_count++;
 		if (ioc->config_cmds.smid == smid)
 			mpt3sas_base_free_smid(ioc, smid);
@@ -519,7 +518,7 @@ _config_request(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigRequest_t
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_manufacturing_pg0(struct MPT3SAS_ADAPTER *ioc,
@@ -556,7 +555,7 @@ mpt3sas_config_get_manufacturing_pg0(struct MPT3SAS_ADAPTER *ioc,
  * @sz: size of buffer passed in config_page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_manufacturing_pg7(struct MPT3SAS_ADAPTER *ioc,
@@ -593,7 +592,7 @@ mpt3sas_config_get_manufacturing_pg7(struct MPT3SAS_ADAPTER *ioc,
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_manufacturing_pg10(struct MPT3SAS_ADAPTER *ioc,
@@ -630,7 +629,7 @@ mpt3sas_config_get_manufacturing_pg10(struct MPT3SAS_ADAPTER *ioc,
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_manufacturing_pg11(struct MPT3SAS_ADAPTER *ioc,
@@ -667,7 +666,7 @@ mpt3sas_config_get_manufacturing_pg11(struct MPT3SAS_ADAPTER *ioc,
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_set_manufacturing_pg11(struct MPT3SAS_ADAPTER *ioc,
@@ -708,7 +707,7 @@ mpt3sas_config_set_manufacturing_pg11(struct MPT3SAS_ADAPTER *ioc,
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_bios_pg2(struct MPT3SAS_ADAPTER *ioc,
@@ -744,7 +743,7 @@ mpt3sas_config_get_bios_pg2(struct MPT3SAS_ADAPTER *ioc,
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_bios_pg3(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
@@ -780,7 +779,7 @@ mpt3sas_config_get_bios_pg3(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_iounit_pg0(struct MPT3SAS_ADAPTER *ioc,
@@ -816,7 +815,7 @@ mpt3sas_config_get_iounit_pg0(struct MPT3SAS_ADAPTER *ioc,
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_iounit_pg1(struct MPT3SAS_ADAPTER *ioc,
@@ -852,7 +851,7 @@ mpt3sas_config_get_iounit_pg1(struct MPT3SAS_ADAPTER *ioc,
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_set_iounit_pg1(struct MPT3SAS_ADAPTER *ioc,
@@ -889,7 +888,7 @@ mpt3sas_config_set_iounit_pg1(struct MPT3SAS_ADAPTER *ioc,
  * @sz: size of buffer passed in config_page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_iounit_pg3(struct MPT3SAS_ADAPTER *ioc,
@@ -924,7 +923,7 @@ mpt3sas_config_get_iounit_pg3(struct MPT3SAS_ADAPTER *ioc,
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_iounit_pg8(struct MPT3SAS_ADAPTER *ioc,
@@ -960,7 +959,7 @@ mpt3sas_config_get_iounit_pg8(struct MPT3SAS_ADAPTER *ioc,
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_ioc_pg8(struct MPT3SAS_ADAPTER *ioc,
@@ -998,7 +997,7 @@ mpt3sas_config_get_ioc_pg8(struct MPT3SAS_ADAPTER *ioc,
  * @handle: device handle
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_sas_device_pg0(struct MPT3SAS_ADAPTER *ioc,
@@ -1039,7 +1038,7 @@ mpt3sas_config_get_sas_device_pg0(struct MPT3SAS_ADAPTER *ioc,
  * @handle: device handle
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_sas_device_pg1(struct MPT3SAS_ADAPTER *ioc,
@@ -1080,7 +1079,7 @@ mpt3sas_config_get_sas_device_pg1(struct MPT3SAS_ADAPTER *ioc,
  * @handle: device handle
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_pcie_device_pg0(struct MPT3SAS_ADAPTER *ioc,
@@ -1121,7 +1120,7 @@ out:
  * @handle: device handle
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_pcie_device_pg2(struct MPT3SAS_ADAPTER *ioc,
@@ -1159,7 +1158,7 @@ out:
  * @num_phys: pointer returned with the number of phys
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_number_hba_phys(struct MPT3SAS_ADAPTER *ioc, u8 *num_phys)
@@ -1209,7 +1208,7 @@ mpt3sas_config_get_number_hba_phys(struct MPT3SAS_ADAPTER *ioc, u8 *num_phys)
  * Calling function should call config_get_number_hba_phys prior to
  * this function, so enough memory is allocated for config_page.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_sas_iounit_pg0(struct MPT3SAS_ADAPTER *ioc,
@@ -1250,7 +1249,7 @@ mpt3sas_config_get_sas_iounit_pg0(struct MPT3SAS_ADAPTER *ioc,
  * Calling function should call config_get_number_hba_phys prior to
  * this function, so enough memory is allocated for config_page.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_sas_iounit_pg1(struct MPT3SAS_ADAPTER *ioc,
@@ -1291,7 +1290,7 @@ mpt3sas_config_get_sas_iounit_pg1(struct MPT3SAS_ADAPTER *ioc,
  * Calling function should call config_get_number_hba_phys prior to
  * this function, so enough memory is allocated for config_page.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_set_sas_iounit_pg1(struct MPT3SAS_ADAPTER *ioc,
@@ -1333,7 +1332,7 @@ mpt3sas_config_set_sas_iounit_pg1(struct MPT3SAS_ADAPTER *ioc,
  * @handle: expander handle
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_expander_pg0(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
@@ -1373,7 +1372,7 @@ mpt3sas_config_get_expander_pg0(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
  * @handle: expander handle
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_expander_pg1(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
@@ -1416,7 +1415,7 @@ mpt3sas_config_get_expander_pg1(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
  * @handle: expander handle
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_enclosure_pg0(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
@@ -1455,7 +1454,7 @@ mpt3sas_config_get_enclosure_pg0(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
  * @phy_number: phy number
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_phy_pg0(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
@@ -1495,7 +1494,7 @@ mpt3sas_config_get_phy_pg0(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
  * @phy_number: phy number
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_phy_pg1(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
@@ -1536,7 +1535,7 @@ mpt3sas_config_get_phy_pg1(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
  * @handle: volume handle
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_raid_volume_pg1(struct MPT3SAS_ADAPTER *ioc,
@@ -1574,7 +1573,7 @@ mpt3sas_config_get_raid_volume_pg1(struct MPT3SAS_ADAPTER *ioc,
  * @num_pds: returns pds count
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_number_pds(struct MPT3SAS_ADAPTER *ioc, u16 handle,
@@ -1626,7 +1625,7 @@ mpt3sas_config_get_number_pds(struct MPT3SAS_ADAPTER *ioc, u16 handle,
  * @sz: size of buffer passed in config_page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_raid_volume_pg0(struct MPT3SAS_ADAPTER *ioc,
@@ -1665,7 +1664,7 @@ mpt3sas_config_get_raid_volume_pg0(struct MPT3SAS_ADAPTER *ioc,
  * @form_specific: specific to the form
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_phys_disk_pg0(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
@@ -1704,7 +1703,7 @@ mpt3sas_config_get_phys_disk_pg0(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
  * @volume_handle: volume handle
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_volume_handle(struct MPT3SAS_ADAPTER *ioc, u16 pd_handle,
@@ -1794,7 +1793,7 @@ mpt3sas_config_get_volume_handle(struct MPT3SAS_ADAPTER *ioc, u16 pd_handle,
  * @wwid: volume wwid
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_volume_wwid(struct MPT3SAS_ADAPTER *ioc, u16 volume_handle,
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index 3269ef43f07e..5e8c059ce2c9 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -253,8 +253,8 @@ _ctl_display_some_debug(struct MPT3SAS_ADAPTER *ioc, u16 smid,
  *
  * The callback handler when using ioc->ctl_cb_idx.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 u8
 mpt3sas_ctl_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
@@ -317,7 +317,7 @@ mpt3sas_ctl_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
  * The bitmask in ioc->event_type[] indicates which events should be
  * be saved in the driver event_log.  This bitmask is set by application.
  *
- * Returns 1 when event should be captured, or zero means no match.
+ * Return: 1 when event should be captured, or zero means no match.
  */
 static int
 _ctl_check_event_type(struct MPT3SAS_ADAPTER *ioc, u16 event)
@@ -339,8 +339,6 @@ _ctl_check_event_type(struct MPT3SAS_ADAPTER *ioc, u16 event)
  * mpt3sas_ctl_add_to_event_log - add event
  * @ioc: per adapter object
  * @mpi_reply: reply message frame
- *
- * Return nothing.
  */
 void
 mpt3sas_ctl_add_to_event_log(struct MPT3SAS_ADAPTER *ioc,
@@ -395,8 +393,8 @@ mpt3sas_ctl_add_to_event_log(struct MPT3SAS_ADAPTER *ioc,
  * This function merely adds a new work task into ioc->firmware_event_thread.
  * The tasks are worked from _firmware_event_work in user context.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 u8
 mpt3sas_ctl_event_callback(struct MPT3SAS_ADAPTER *ioc, u8 msix_index,
@@ -412,12 +410,12 @@ mpt3sas_ctl_event_callback(struct MPT3SAS_ADAPTER *ioc, u8 msix_index,
 
 /**
  * _ctl_verify_adapter - validates ioc_number passed from application
- * @ioc: per adapter object
+ * @ioc_number: ?
  * @iocpp: The ioc pointer is returned in this.
  * @mpi_version: will be MPI2_VERSION for mpt2ctl ioctl device &
  * MPI25_VERSION | MPI26_VERSION for mpt3ctl ioctl device.
  *
- * Return (-1) means error, else ioc_number.
+ * Return: (-1) means error, else ioc_number.
  */
 static int
 _ctl_verify_adapter(int ioc_number, struct MPT3SAS_ADAPTER **iocpp,
@@ -460,65 +458,74 @@ out:
 /**
  * mpt3sas_ctl_reset_handler - reset callback handler (for ctl)
  * @ioc: per adapter object
- * @reset_phase: phase
  *
  * The handler for doing any required cleanup or initialization.
- *
- * The reset phase can be MPT3_IOC_PRE_RESET, MPT3_IOC_AFTER_RESET,
- * MPT3_IOC_DONE_RESET
  */
-void
-mpt3sas_ctl_reset_handler(struct MPT3SAS_ADAPTER *ioc, int reset_phase)
+void mpt3sas_ctl_pre_reset_handler(struct MPT3SAS_ADAPTER *ioc)
 {
 	int i;
 	u8 issue_reset;
 
-	switch (reset_phase) {
-	case MPT3_IOC_PRE_RESET:
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT
+	dtmprintk(ioc, pr_info(MPT3SAS_FMT
 			"%s: MPT3_IOC_PRE_RESET\n", ioc->name, __func__));
-		for (i = 0; i < MPI2_DIAG_BUF_TYPE_COUNT; i++) {
-			if (!(ioc->diag_buffer_status[i] &
-			    MPT3_DIAG_BUFFER_IS_REGISTERED))
-				continue;
-			if ((ioc->diag_buffer_status[i] &
-			    MPT3_DIAG_BUFFER_IS_RELEASED))
-				continue;
-			mpt3sas_send_diag_release(ioc, i, &issue_reset);
-		}
-		break;
-	case MPT3_IOC_AFTER_RESET:
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT
+	for (i = 0; i < MPI2_DIAG_BUF_TYPE_COUNT; i++) {
+		if (!(ioc->diag_buffer_status[i] &
+		      MPT3_DIAG_BUFFER_IS_REGISTERED))
+			continue;
+		if ((ioc->diag_buffer_status[i] &
+		     MPT3_DIAG_BUFFER_IS_RELEASED))
+			continue;
+		mpt3sas_send_diag_release(ioc, i, &issue_reset);
+	}
+}
+
+/**
+ * mpt3sas_ctl_reset_handler - reset callback handler (for ctl)
+ * @ioc: per adapter object
+ *
+ * The handler for doing any required cleanup or initialization.
+ */
+void mpt3sas_ctl_after_reset_handler(struct MPT3SAS_ADAPTER *ioc)
+{
+	dtmprintk(ioc, pr_info(MPT3SAS_FMT
 			"%s: MPT3_IOC_AFTER_RESET\n", ioc->name, __func__));
-		if (ioc->ctl_cmds.status & MPT3_CMD_PENDING) {
-			ioc->ctl_cmds.status |= MPT3_CMD_RESET;
-			mpt3sas_base_free_smid(ioc, ioc->ctl_cmds.smid);
-			complete(&ioc->ctl_cmds.done);
-		}
-		break;
-	case MPT3_IOC_DONE_RESET:
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT
+	if (ioc->ctl_cmds.status & MPT3_CMD_PENDING) {
+		ioc->ctl_cmds.status |= MPT3_CMD_RESET;
+		mpt3sas_base_free_smid(ioc, ioc->ctl_cmds.smid);
+		complete(&ioc->ctl_cmds.done);
+	}
+}
+
+/**
+ * mpt3sas_ctl_reset_handler - reset callback handler (for ctl)
+ * @ioc: per adapter object
+ *
+ * The handler for doing any required cleanup or initialization.
+ */
+void mpt3sas_ctl_reset_done_handler(struct MPT3SAS_ADAPTER *ioc)
+{
+	int i;
+
+	dtmprintk(ioc, pr_info(MPT3SAS_FMT
 			"%s: MPT3_IOC_DONE_RESET\n", ioc->name, __func__));
 
-		for (i = 0; i < MPI2_DIAG_BUF_TYPE_COUNT; i++) {
-			if (!(ioc->diag_buffer_status[i] &
-			    MPT3_DIAG_BUFFER_IS_REGISTERED))
-				continue;
-			if ((ioc->diag_buffer_status[i] &
-			    MPT3_DIAG_BUFFER_IS_RELEASED))
-				continue;
-			ioc->diag_buffer_status[i] |=
-			    MPT3_DIAG_BUFFER_IS_DIAG_RESET;
-		}
-		break;
+	for (i = 0; i < MPI2_DIAG_BUF_TYPE_COUNT; i++) {
+		if (!(ioc->diag_buffer_status[i] &
+		      MPT3_DIAG_BUFFER_IS_REGISTERED))
+			continue;
+		if ((ioc->diag_buffer_status[i] &
+		     MPT3_DIAG_BUFFER_IS_RELEASED))
+			continue;
+		ioc->diag_buffer_status[i] |=
+			MPT3_DIAG_BUFFER_IS_DIAG_RESET;
 	}
 }
 
 /**
  * _ctl_fasync -
- * @fd -
- * @filep -
- * @mode -
+ * @fd: ?
+ * @filep: ?
+ * @mode: ?
  *
  * Called when application request fasyn callback handler.
  */
@@ -530,8 +537,8 @@ _ctl_fasync(int fd, struct file *filep, int mode)
 
 /**
  * _ctl_poll -
- * @file -
- * @wait -
+ * @filep: ?
+ * @wait: ?
  *
  */
 static __poll_t
@@ -556,10 +563,10 @@ _ctl_poll(struct file *filep, poll_table *wait)
 /**
  * _ctl_set_task_mid - assign an active smid to tm request
  * @ioc: per adapter object
- * @karg - (struct mpt3_ioctl_command)
- * @tm_request - pointer to mf from user space
+ * @karg: (struct mpt3_ioctl_command)
+ * @tm_request: pointer to mf from user space
  *
- * Returns 0 when an smid if found, else fail.
+ * Return: 0 when an smid if found, else fail.
  * during failure, the reply frame is filled.
  */
 static int
@@ -634,8 +641,8 @@ _ctl_set_task_mid(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command *karg,
 /**
  * _ctl_do_mpt_command - main handler for MPT3COMMAND opcode
  * @ioc: per adapter object
- * @karg - (struct mpt3_ioctl_command)
- * @mf - pointer to mf in user space
+ * @karg: (struct mpt3_ioctl_command)
+ * @mf: pointer to mf in user space
  */
 static long
 _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
@@ -970,6 +977,7 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 		}
 		/* drop to default case for posting the request */
 	}
+		/* fall through */
 	default:
 		ioc->build_sg_mpi(ioc, psge, data_out_dma, data_out_sz,
 		    data_in_dma, data_in_sz);
@@ -995,11 +1003,10 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 		ioc->ignore_loginfos = 0;
 	}
 	if (!(ioc->ctl_cmds.status & MPT3_CMD_COMPLETE)) {
-		pr_err(MPT3SAS_FMT "%s: timeout\n", ioc->name,
-		    __func__);
-		_debug_dump_mf(mpi_request, karg.data_sge_offset);
-		if (!(ioc->ctl_cmds.status & MPT3_CMD_RESET))
-			issue_reset = 1;
+		issue_reset =
+			mpt3sas_base_check_cmd_timeout(ioc,
+				ioc->ctl_cmds.status, mpi_request,
+				karg.data_sge_offset);
 		goto issue_host_reset;
 	}
 
@@ -1114,7 +1121,7 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 /**
  * _ctl_getiocinfo - main handler for MPT3IOCINFO opcode
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  */
 static long
 _ctl_getiocinfo(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
@@ -1168,7 +1175,7 @@ _ctl_getiocinfo(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 /**
  * _ctl_eventquery - main handler for MPT3EVENTQUERY opcode
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  */
 static long
 _ctl_eventquery(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
@@ -1199,7 +1206,7 @@ _ctl_eventquery(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 /**
  * _ctl_eventenable - main handler for MPT3EVENTENABLE opcode
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  */
 static long
 _ctl_eventenable(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
@@ -1237,7 +1244,7 @@ _ctl_eventenable(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 /**
  * _ctl_eventreport - main handler for MPT3EVENTREPORT opcode
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  */
 static long
 _ctl_eventreport(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
@@ -1281,7 +1288,7 @@ _ctl_eventreport(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 /**
  * _ctl_do_reset - main handler for MPT3HARDRESET opcode
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  */
 static long
 _ctl_do_reset(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
@@ -1419,7 +1426,7 @@ _ctl_btdh_search_raid_device(struct MPT3SAS_ADAPTER *ioc,
 /**
  * _ctl_btdh_mapping - main handler for MPT3BTDHMAPPING opcode
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  */
 static long
 _ctl_btdh_mapping(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
@@ -1621,12 +1628,10 @@ _ctl_diag_register_2(struct MPT3SAS_ADAPTER *ioc,
 	    MPT3_IOCTL_DEFAULT_TIMEOUT*HZ);
 
 	if (!(ioc->ctl_cmds.status & MPT3_CMD_COMPLETE)) {
-		pr_err(MPT3SAS_FMT "%s: timeout\n", ioc->name,
-		    __func__);
-		_debug_dump_mf(mpi_request,
-		    sizeof(Mpi2DiagBufferPostRequest_t)/4);
-		if (!(ioc->ctl_cmds.status & MPT3_CMD_RESET))
-			issue_reset = 1;
+		issue_reset =
+			mpt3sas_base_check_cmd_timeout(ioc,
+				ioc->ctl_cmds.status, mpi_request,
+				sizeof(Mpi2DiagBufferPostRequest_t)/4);
 		goto issue_host_reset;
 	}
 
@@ -1719,7 +1724,7 @@ mpt3sas_enable_diag_buffer(struct MPT3SAS_ADAPTER *ioc, u8 bits_to_register)
 /**
  * _ctl_diag_register - application register with driver
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  *
  * This will allow the driver to setup any required buffers that will be
  * needed by firmware to communicate with the driver.
@@ -1743,7 +1748,7 @@ _ctl_diag_register(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 /**
  * _ctl_diag_unregister - application unregister with driver
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  *
  * This will allow the driver to cleanup any memory allocated for diag
  * messages and to free up any resources.
@@ -1816,7 +1821,7 @@ _ctl_diag_unregister(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 /**
  * _ctl_diag_query - query relevant info associated with diag buffers
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  *
  * The application will send only buffer_type and unique_id.  Driver will
  * inspect unique_id first, if valid, fill in all the info.  If unique_id is
@@ -1903,8 +1908,8 @@ _ctl_diag_query(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 /**
  * mpt3sas_send_diag_release - Diag Release Message
  * @ioc: per adapter object
- * @buffer_type - specifies either TRACE, SNAPSHOT, or EXTENDED
- * @issue_reset - specifies whether host reset is required.
+ * @buffer_type: specifies either TRACE, SNAPSHOT, or EXTENDED
+ * @issue_reset: specifies whether host reset is required.
  *
  */
 int
@@ -1968,12 +1973,9 @@ mpt3sas_send_diag_release(struct MPT3SAS_ADAPTER *ioc, u8 buffer_type,
 	    MPT3_IOCTL_DEFAULT_TIMEOUT*HZ);
 
 	if (!(ioc->ctl_cmds.status & MPT3_CMD_COMPLETE)) {
-		pr_err(MPT3SAS_FMT "%s: timeout\n", ioc->name,
-		    __func__);
-		_debug_dump_mf(mpi_request,
-		    sizeof(Mpi2DiagReleaseRequest_t)/4);
-		if (!(ioc->ctl_cmds.status & MPT3_CMD_RESET))
-			*issue_reset = 1;
+		*issue_reset = mpt3sas_base_check_cmd_timeout(ioc,
+				ioc->ctl_cmds.status, mpi_request,
+				sizeof(Mpi2DiagReleaseRequest_t)/4);
 		rc = -EFAULT;
 		goto out;
 	}
@@ -2009,7 +2011,8 @@ mpt3sas_send_diag_release(struct MPT3SAS_ADAPTER *ioc, u8 buffer_type,
 
 /**
  * _ctl_diag_release - request to send Diag Release Message to firmware
- * @arg - user space buffer containing ioctl content
+ * @ioc: ?
+ * @arg: user space buffer containing ioctl content
  *
  * This allows ownership of the specified buffer to returned to the driver,
  * allowing an application to read the buffer without fear that firmware is
@@ -2098,7 +2101,7 @@ _ctl_diag_release(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 /**
  * _ctl_diag_read_buffer - request for copy of the diag buffer
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  */
 static long
 _ctl_diag_read_buffer(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
@@ -2235,12 +2238,10 @@ _ctl_diag_read_buffer(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 	    MPT3_IOCTL_DEFAULT_TIMEOUT*HZ);
 
 	if (!(ioc->ctl_cmds.status & MPT3_CMD_COMPLETE)) {
-		pr_err(MPT3SAS_FMT "%s: timeout\n", ioc->name,
-		    __func__);
-		_debug_dump_mf(mpi_request,
-		    sizeof(Mpi2DiagBufferPostRequest_t)/4);
-		if (!(ioc->ctl_cmds.status & MPT3_CMD_RESET))
-			issue_reset = 1;
+		issue_reset =
+			mpt3sas_base_check_cmd_timeout(ioc,
+				ioc->ctl_cmds.status, mpi_request,
+				sizeof(Mpi2DiagBufferPostRequest_t)/4);
 		goto issue_host_reset;
 	}
 
@@ -2284,8 +2285,8 @@ _ctl_diag_read_buffer(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 /**
  * _ctl_compat_mpt_command - convert 32bit pointers to 64bit.
  * @ioc: per adapter object
- * @cmd - ioctl opcode
- * @arg - (struct mpt3_ioctl_command32)
+ * @cmd: ioctl opcode
+ * @arg: (struct mpt3_ioctl_command32)
  *
  * MPT3COMMAND32 - Handle 32bit applications running on 64bit os.
  */
@@ -2328,10 +2329,10 @@ _ctl_compat_mpt_command(struct MPT3SAS_ADAPTER *ioc, unsigned cmd,
 
 /**
  * _ctl_ioctl_main - main ioctl entry point
- * @file - (struct file)
- * @cmd - ioctl opcode
- * @arg - user space data buffer
- * @compat - handles 32 bit applications in 64bit os
+ * @file:  (struct file)
+ * @cmd:  ioctl opcode
+ * @arg:  user space data buffer
+ * @compat:  handles 32 bit applications in 64bit os
  * @mpi_version: will be MPI2_VERSION for mpt2ctl ioctl device &
  * MPI25_VERSION | MPI26_VERSION for mpt3ctl ioctl device.
  */
@@ -2462,9 +2463,9 @@ out_unlock_pciaccess:
 
 /**
  * _ctl_ioctl - mpt3ctl main ioctl entry point (unlocked)
- * @file - (struct file)
- * @cmd - ioctl opcode
- * @arg -
+ * @file: (struct file)
+ * @cmd: ioctl opcode
+ * @arg: ?
  */
 static long
 _ctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
@@ -2482,9 +2483,9 @@ _ctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 /**
  * _ctl_mpt2_ioctl - mpt2ctl main ioctl entry point (unlocked)
- * @file - (struct file)
- * @cmd - ioctl opcode
- * @arg -
+ * @file: (struct file)
+ * @cmd: ioctl opcode
+ * @arg: ?
  */
 static long
 _ctl_mpt2_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
@@ -2500,9 +2501,9 @@ _ctl_mpt2_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 #ifdef CONFIG_COMPAT
 /**
  *_ ctl_ioctl_compat - main ioctl entry point (compat)
- * @file -
- * @cmd -
- * @arg -
+ * @file: ?
+ * @cmd: ?
+ * @arg: ?
  *
  * This routine handles 32 bit applications in 64bit os.
  */
@@ -2518,9 +2519,9 @@ _ctl_ioctl_compat(struct file *file, unsigned cmd, unsigned long arg)
 
 /**
  *_ ctl_mpt2_ioctl_compat - main ioctl entry point (compat)
- * @file -
- * @cmd -
- * @arg -
+ * @file: ?
+ * @cmd: ?
+ * @arg: ?
  *
  * This routine handles 32 bit applications in 64bit os.
  */
@@ -2537,8 +2538,9 @@ _ctl_mpt2_ioctl_compat(struct file *file, unsigned cmd, unsigned long arg)
 /* scsi host attributes */
 /**
  * _ctl_version_fw_show - firmware version
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -2559,8 +2561,9 @@ static DEVICE_ATTR(version_fw, S_IRUGO, _ctl_version_fw_show, NULL);
 
 /**
  * _ctl_version_bios_show - bios version
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -2583,8 +2586,9 @@ static DEVICE_ATTR(version_bios, S_IRUGO, _ctl_version_bios_show, NULL);
 
 /**
  * _ctl_version_mpi_show - MPI (message passing interface) version
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -2602,8 +2606,9 @@ static DEVICE_ATTR(version_mpi, S_IRUGO, _ctl_version_mpi_show, NULL);
 
 /**
  * _ctl_version_product_show - product name
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -2620,8 +2625,9 @@ static DEVICE_ATTR(version_product, S_IRUGO, _ctl_version_product_show, NULL);
 
 /**
  * _ctl_version_nvdata_persistent_show - ndvata persistent version
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -2640,8 +2646,9 @@ static DEVICE_ATTR(version_nvdata_persistent, S_IRUGO,
 
 /**
  * _ctl_version_nvdata_default_show - nvdata default version
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -2660,8 +2667,9 @@ static DEVICE_ATTR(version_nvdata_default, S_IRUGO,
 
 /**
  * _ctl_board_name_show - board name
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -2678,8 +2686,9 @@ static DEVICE_ATTR(board_name, S_IRUGO, _ctl_board_name_show, NULL);
 
 /**
  * _ctl_board_assembly_show - board assembly name
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -2696,8 +2705,9 @@ static DEVICE_ATTR(board_assembly, S_IRUGO, _ctl_board_assembly_show, NULL);
 
 /**
  * _ctl_board_tracer_show - board tracer number
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -2714,8 +2724,9 @@ static DEVICE_ATTR(board_tracer, S_IRUGO, _ctl_board_tracer_show, NULL);
 
 /**
  * _ctl_io_delay_show - io missing delay
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * This is for firmware implemention for deboucing device
  * removal events.
@@ -2735,8 +2746,9 @@ static DEVICE_ATTR(io_delay, S_IRUGO, _ctl_io_delay_show, NULL);
 
 /**
  * _ctl_device_delay_show - device missing delay
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * This is for firmware implemention for deboucing device
  * removal events.
@@ -2756,8 +2768,9 @@ static DEVICE_ATTR(device_delay, S_IRUGO, _ctl_device_delay_show, NULL);
 
 /**
  * _ctl_fw_queue_depth_show - global credits
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * This is firmware queue depth limit
  *
@@ -2776,8 +2789,9 @@ static DEVICE_ATTR(fw_queue_depth, S_IRUGO, _ctl_fw_queue_depth_show, NULL);
 
 /**
  * _ctl_sas_address_show - sas address
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * This is the controller sas address
  *
@@ -2799,8 +2813,9 @@ static DEVICE_ATTR(host_sas_address, S_IRUGO,
 
 /**
  * _ctl_logging_level_show - logging level
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read/write' shost attribute.
  */
@@ -2834,8 +2849,9 @@ static DEVICE_ATTR(logging_level, S_IRUGO | S_IWUSR, _ctl_logging_level_show,
 
 /**
  * _ctl_fwfault_debug_show - show/store fwfault_debug
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * mpt3sas_fwfault_debug is command line option
  * A sysfs 'read/write' shost attribute.
@@ -2870,8 +2886,9 @@ static DEVICE_ATTR(fwfault_debug, S_IRUGO | S_IWUSR,
 
 /**
  * _ctl_ioc_reset_count_show - ioc reset count
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * This is firmware queue depth limit
  *
@@ -2890,8 +2907,9 @@ static DEVICE_ATTR(ioc_reset_count, S_IRUGO, _ctl_ioc_reset_count_show, NULL);
 
 /**
  * _ctl_ioc_reply_queue_count_show - number of reply queues
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * This is number of reply queues
  *
@@ -2918,8 +2936,9 @@ static DEVICE_ATTR(reply_queue_count, S_IRUGO, _ctl_ioc_reply_queue_count_show,
 
 /**
  * _ctl_BRM_status_show - Backup Rail Monitor Status
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * This is number of reply queues
  *
@@ -3004,8 +3023,9 @@ struct DIAG_BUFFER_START {
 
 /**
  * _ctl_host_trace_buffer_size_show - host buffer size (trace only)
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -3049,8 +3069,9 @@ static DEVICE_ATTR(host_trace_buffer_size, S_IRUGO,
 
 /**
  * _ctl_host_trace_buffer_show - firmware ring buffer (trace only)
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read/write' shost attribute.
  *
@@ -3114,8 +3135,9 @@ static DEVICE_ATTR(host_trace_buffer, S_IRUGO | S_IWUSR,
 
 /**
  * _ctl_host_trace_buffer_enable_show - firmware ring buffer (trace only)
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read/write' shost attribute.
  *
@@ -3200,8 +3222,9 @@ static DEVICE_ATTR(host_trace_buffer_enable, S_IRUGO | S_IWUSR,
 
 /**
  * _ctl_diag_trigger_master_show - show the diag_trigger_master attribute
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read/write' shost attribute.
  */
@@ -3224,8 +3247,10 @@ _ctl_diag_trigger_master_show(struct device *cdev,
 
 /**
  * _ctl_diag_trigger_master_store - store the diag_trigger_master attribute
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
+ * @count: ?
  *
  * A sysfs 'read/write' shost attribute.
  */
@@ -3255,8 +3280,9 @@ static DEVICE_ATTR(diag_trigger_master, S_IRUGO | S_IWUSR,
 
 /**
  * _ctl_diag_trigger_event_show - show the diag_trigger_event attribute
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read/write' shost attribute.
  */
@@ -3278,8 +3304,10 @@ _ctl_diag_trigger_event_show(struct device *cdev,
 
 /**
  * _ctl_diag_trigger_event_store - store the diag_trigger_event attribute
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
+ * @count: ?
  *
  * A sysfs 'read/write' shost attribute.
  */
@@ -3309,8 +3337,9 @@ static DEVICE_ATTR(diag_trigger_event, S_IRUGO | S_IWUSR,
 
 /**
  * _ctl_diag_trigger_scsi_show - show the diag_trigger_scsi attribute
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read/write' shost attribute.
  */
@@ -3332,8 +3361,10 @@ _ctl_diag_trigger_scsi_show(struct device *cdev,
 
 /**
  * _ctl_diag_trigger_scsi_store - store the diag_trigger_scsi attribute
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
+ * @count: ?
  *
  * A sysfs 'read/write' shost attribute.
  */
@@ -3362,8 +3393,9 @@ static DEVICE_ATTR(diag_trigger_scsi, S_IRUGO | S_IWUSR,
 
 /**
  * _ctl_diag_trigger_scsi_show - show the diag_trigger_mpi attribute
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read/write' shost attribute.
  */
@@ -3385,8 +3417,10 @@ _ctl_diag_trigger_mpi_show(struct device *cdev,
 
 /**
  * _ctl_diag_trigger_mpi_store - store the diag_trigger_mpi attribute
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
+ * @count: ?
  *
  * A sysfs 'read/write' shost attribute.
  */
@@ -3450,8 +3484,9 @@ struct device_attribute *mpt3sas_host_attrs[] = {
 
 /**
  * _ctl_device_sas_address_show - sas address
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @dev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * This is the sas address for the target
  *
@@ -3471,8 +3506,9 @@ static DEVICE_ATTR(sas_address, S_IRUGO, _ctl_device_sas_address_show, NULL);
 
 /**
  * _ctl_device_handle_show - device handle
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @dev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * This is the firmware assigned device handle
  *
@@ -3492,8 +3528,9 @@ static DEVICE_ATTR(sas_device_handle, S_IRUGO, _ctl_device_handle_show, NULL);
 
 /**
  * _ctl_device_ncq_io_prio_show - send prioritized io commands to device
- * @dev - pointer to embedded device
- * @buf - the buffer returned
+ * @dev: pointer to embedded device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read/write' sdev attribute, only works with SATA
  */
@@ -3573,7 +3610,7 @@ static struct miscdevice gen2_ctl_dev = {
 
 /**
  * mpt3sas_ctl_init - main entry point for ctl.
- *
+ * @hbas_to_enumerate: ?
  */
 void
 mpt3sas_ctl_init(ushort hbas_to_enumerate)
@@ -3601,7 +3638,7 @@ mpt3sas_ctl_init(ushort hbas_to_enumerate)
 
 /**
  * mpt3sas_ctl_exit - exit point for ctl
- *
+ * @hbas_to_enumerate: ?
  */
 void
 mpt3sas_ctl_exit(ushort hbas_to_enumerate)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index b8d131a455d0..53133cfd420f 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -284,6 +284,8 @@ struct _scsi_io_transfer {
 
 /**
  * _scsih_set_debug_level - global setting of ioc->logging_level.
+ * @val: ?
+ * @kp: ?
  *
  * Note: The logging levels are defined in mpt3sas_debug.h.
  */
@@ -311,7 +313,7 @@ module_param_call(logging_level, _scsih_set_debug_level, param_get_int,
  * @sas_address: sas address
  * @boot_device: boot device object from bios page 2
  *
- * Returns 1 when there's a match, 0 means no match.
+ * Return: 1 when there's a match, 0 means no match.
  */
 static inline int
 _scsih_srch_boot_sas_address(u64 sas_address,
@@ -325,7 +327,7 @@ _scsih_srch_boot_sas_address(u64 sas_address,
  * @device_name: device name specified in INDENTIFY fram
  * @boot_device: boot device object from bios page 2
  *
- * Returns 1 when there's a match, 0 means no match.
+ * Return: 1 when there's a match, 0 means no match.
  */
 static inline int
 _scsih_srch_boot_device_name(u64 device_name,
@@ -340,7 +342,7 @@ _scsih_srch_boot_device_name(u64 device_name,
  * @slot_number: slot number
  * @boot_device: boot device object from bios page 2
  *
- * Returns 1 when there's a match, 0 means no match.
+ * Return: 1 when there's a match, 0 means no match.
  */
 static inline int
 _scsih_srch_boot_encl_slot(u64 enclosure_logical_id, u16 slot_number,
@@ -356,11 +358,11 @@ _scsih_srch_boot_encl_slot(u64 enclosure_logical_id, u16 slot_number,
  * @sas_address: sas address
  * @device_name: device name specified in INDENTIFY fram
  * @enclosure_logical_id: enclosure logical id
- * @slot_number: slot number
+ * @slot: slot number
  * @form: specifies boot device form
  * @boot_device: boot device object from bios page 2
  *
- * Returns 1 when there's a match, 0 means no match.
+ * Return: 1 when there's a match, 0 means no match.
  */
 static int
 _scsih_is_boot_device(u64 sas_address, u64 device_name,
@@ -398,10 +400,11 @@ _scsih_is_boot_device(u64 sas_address, u64 device_name,
 
 /**
  * _scsih_get_sas_address - set the sas_address for given device handle
+ * @ioc: ?
  * @handle: device handle
  * @sas_address: sas address
  *
- * Returns 0 success, non-zero when failure
+ * Return: 0 success, non-zero when failure
  */
 static int
 _scsih_get_sas_address(struct MPT3SAS_ADAPTER *ioc, u16 handle,
@@ -710,8 +713,6 @@ mpt3sas_get_sdev_by_handle(struct MPT3SAS_ADAPTER *ioc, u16 handle)
  * @sas_device: per sas device object
  * @sdev: scsi device struct
  * @starget: scsi target struct
- *
- * Returns nothing.
  */
 static void
 _scsih_display_enclosure_chassis_info(struct MPT3SAS_ADAPTER *ioc,
@@ -806,8 +807,6 @@ _scsih_sas_device_remove(struct MPT3SAS_ADAPTER *ioc,
  * _scsih_device_remove_by_handle - removing device object by handle
  * @ioc: per adapter object
  * @handle: device handle
- *
- * Return nothing.
  */
 static void
 _scsih_device_remove_by_handle(struct MPT3SAS_ADAPTER *ioc, u16 handle)
@@ -835,8 +834,6 @@ _scsih_device_remove_by_handle(struct MPT3SAS_ADAPTER *ioc, u16 handle)
  * mpt3sas_device_remove_by_sas_address - removing device object by sas address
  * @ioc: per adapter object
  * @sas_address: device sas_address
- *
- * Return nothing.
  */
 void
 mpt3sas_device_remove_by_sas_address(struct MPT3SAS_ADAPTER *ioc,
@@ -1109,8 +1106,6 @@ _scsih_pcie_device_remove(struct MPT3SAS_ADAPTER *ioc,
  * _scsih_pcie_device_remove_by_handle - removing pcie device object by handle
  * @ioc: per adapter object
  * @handle: device handle
- *
- * Return nothing.
  */
 static void
 _scsih_pcie_device_remove_by_handle(struct MPT3SAS_ADAPTER *ioc, u16 handle)
@@ -1273,7 +1268,7 @@ mpt3sas_raid_device_find_by_handle(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 /**
  * _scsih_raid_device_find_by_wwid - raid device search
  * @ioc: per adapter object
- * @handle: sas device handle (assigned by firmware)
+ * @wwid: ?
  * Context: Calling function should acquire ioc->raid_device_lock
  *
  * This searches for raid_device based on wwid, then return raid_device
@@ -1418,8 +1413,6 @@ mpt3sas_scsih_expander_find_by_sas_address(struct MPT3SAS_ADAPTER *ioc,
  * Context: This function will acquire ioc->sas_node_lock.
  *
  * Adding new object to the ioc->sas_expander_list.
- *
- * Return nothing.
  */
 static void
 _scsih_expander_node_add(struct MPT3SAS_ADAPTER *ioc,
@@ -1437,7 +1430,7 @@ _scsih_expander_node_add(struct MPT3SAS_ADAPTER *ioc,
  * @device_info: bitfield providing information about the device.
  * Context: none
  *
- * Returns 1 if end device.
+ * Return: 1 if end device.
  */
 static int
 _scsih_is_end_device(u32 device_info)
@@ -1456,7 +1449,7 @@ _scsih_is_end_device(u32 device_info)
  * @device_info: bitfield providing information about the device.
  * Context: none
  *
- * Returns 1 if nvme device.
+ * Return: 1 if nvme device.
  */
 static int
 _scsih_is_nvme_device(u32 device_info)
@@ -1473,7 +1466,7 @@ _scsih_is_nvme_device(u32 device_info)
  * @ioc: per adapter object
  * @smid: system request message index
  *
- * Returns the smid stored scmd pointer.
+ * Return: the smid stored scmd pointer.
  * Then will dereference the stored scmd pointer.
  */
 struct scsi_cmnd *
@@ -1489,7 +1482,7 @@ mpt3sas_scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc, u16 smid)
 		scmd = scsi_host_find_tag(ioc->shost, unique_tag);
 		if (scmd) {
 			st = scsi_cmd_priv(scmd);
-			if (st->cb_idx == 0xFF)
+			if (st->cb_idx == 0xFF || st->smid == 0)
 				scmd = NULL;
 		}
 	}
@@ -1501,7 +1494,7 @@ mpt3sas_scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * @sdev: scsi device struct
  * @qdepth: requested queue depth
  *
- * Returns queue depth.
+ * Return: queue depth.
  */
 static int
 scsih_change_queue_depth(struct scsi_device *sdev, int qdepth)
@@ -1549,7 +1542,7 @@ scsih_change_queue_depth(struct scsi_device *sdev, int qdepth)
  * scsih_target_alloc - target add routine
  * @starget: scsi target struct
  *
- * Returns 0 if ok. Any other return is assumed to be an error and
+ * Return: 0 if ok. Any other return is assumed to be an error and
  * the device is ignored.
  */
 static int
@@ -1640,8 +1633,6 @@ scsih_target_alloc(struct scsi_target *starget)
 /**
  * scsih_target_destroy - target destroy routine
  * @starget: scsi target struct
- *
- * Returns nothing.
  */
 static void
 scsih_target_destroy(struct scsi_target *starget)
@@ -1653,7 +1644,6 @@ scsih_target_destroy(struct scsi_target *starget)
 	struct _raid_device *raid_device;
 	struct _pcie_device *pcie_device;
 	unsigned long flags;
-	struct sas_rphy *rphy;
 
 	sas_target_priv_data = starget->hostdata;
 	if (!sas_target_priv_data)
@@ -1693,7 +1683,6 @@ scsih_target_destroy(struct scsi_target *starget)
 	}
 
 	spin_lock_irqsave(&ioc->sas_device_lock, flags);
-	rphy = dev_to_rphy(starget->dev.parent);
 	sas_device = __mpt3sas_get_sdev_from_target(ioc, sas_target_priv_data);
 	if (sas_device && (sas_device->starget == starget) &&
 	    (sas_device->id == starget->id) &&
@@ -1720,7 +1709,7 @@ scsih_target_destroy(struct scsi_target *starget)
  * scsih_slave_alloc - device add routine
  * @sdev: scsi device struct
  *
- * Returns 0 if ok. Any other return is assumed to be an error and
+ * Return: 0 if ok. Any other return is assumed to be an error and
  * the device is ignored.
  */
 static int
@@ -1800,8 +1789,6 @@ scsih_slave_alloc(struct scsi_device *sdev)
 /**
  * scsih_slave_destroy - device destroy routine
  * @sdev: scsi device struct
- *
- * Returns nothing.
  */
 static void
 scsih_slave_destroy(struct scsi_device *sdev)
@@ -1907,7 +1894,7 @@ _scsih_display_sata_capabilities(struct MPT3SAS_ADAPTER *ioc,
 
 /**
  * scsih_is_raid - return boolean indicating device is raid volume
- * @dev the device struct object
+ * @dev: the device struct object
  */
 static int
 scsih_is_raid(struct device *dev)
@@ -1930,7 +1917,7 @@ scsih_is_nvme(struct device *dev)
 
 /**
  * scsih_get_resync - get raid volume resync percent complete
- * @dev the device struct object
+ * @dev: the device struct object
  */
 static void
 scsih_get_resync(struct device *dev)
@@ -1991,7 +1978,7 @@ scsih_get_resync(struct device *dev)
 
 /**
  * scsih_get_state - get raid volume level
- * @dev the device struct object
+ * @dev: the device struct object
  */
 static void
 scsih_get_state(struct device *dev)
@@ -2057,6 +2044,7 @@ scsih_get_state(struct device *dev)
 
 /**
  * _scsih_set_level - set raid level
+ * @ioc: ?
  * @sdev: scsi device struct
  * @volume_type: volume type
  */
@@ -2098,9 +2086,9 @@ _scsih_set_level(struct MPT3SAS_ADAPTER *ioc,
 /**
  * _scsih_get_volume_capabilities - volume capabilities
  * @ioc: per adapter object
- * @sas_device: the raid_device object
+ * @raid_device: the raid_device object
  *
- * Returns 0 for success, else 1
+ * Return: 0 for success, else 1
  */
 static int
 _scsih_get_volume_capabilities(struct MPT3SAS_ADAPTER *ioc,
@@ -2192,7 +2180,7 @@ _scsih_enable_tlr(struct MPT3SAS_ADAPTER *ioc, struct scsi_device *sdev)
  * scsih_slave_configure - device configure routine.
  * @sdev: scsi device struct
  *
- * Returns 0 if ok. Any other return is assumed to be an error and
+ * Return: 0 if ok. Any other return is assumed to be an error and
  * the device is ignored.
  */
 static int
@@ -2256,7 +2244,7 @@ scsih_slave_configure(struct scsi_device *sdev)
 			ds = "SSP";
 		} else {
 			qdepth = MPT3SAS_SATA_QUEUE_DEPTH;
-			 if (raid_device->device_info &
+			if (raid_device->device_info &
 			    MPI2_SAS_DEVICE_INFO_SATA_DEVICE)
 				ds = "SATA";
 			else
@@ -2365,13 +2353,14 @@ scsih_slave_configure(struct scsi_device *sdev)
 				"connector name( %s)\n", ds,
 				pcie_device->enclosure_level,
 				pcie_device->connector_name);
-		pcie_device_put(pcie_device);
-		spin_unlock_irqrestore(&ioc->pcie_device_lock, flags);
-		scsih_change_queue_depth(sdev, qdepth);
 
 		if (pcie_device->nvme_mdts)
 			blk_queue_max_hw_sectors(sdev->request_queue,
 					pcie_device->nvme_mdts/512);
+
+		pcie_device_put(pcie_device);
+		spin_unlock_irqrestore(&ioc->pcie_device_lock, flags);
+		scsih_change_queue_depth(sdev, qdepth);
 		/* Enable QUEUE_FLAG_NOMERGES flag, so that IOs won't be
 		 ** merged and can eliminate holes created during merging
 		 ** operation.
@@ -2450,8 +2439,6 @@ scsih_slave_configure(struct scsi_device *sdev)
  *              params[0] number of heads (max 255)
  *              params[1] number of sectors (max 63)
  *              params[2] number of cylinders
- *
- * Return nothing.
  */
 static int
 scsih_bios_param(struct scsi_device *sdev, struct block_device *bdev,
@@ -2493,8 +2480,6 @@ scsih_bios_param(struct scsi_device *sdev, struct block_device *bdev,
  * _scsih_response_code - translation of device response code
  * @ioc: per adapter object
  * @response_code: response code returned by the device
- *
- * Return nothing.
  */
 static void
 _scsih_response_code(struct MPT3SAS_ADAPTER *ioc, u8 response_code)
@@ -2544,8 +2529,8 @@ _scsih_response_code(struct MPT3SAS_ADAPTER *ioc, u8 response_code)
  *
  * The callback handler when using scsih_issue_tm.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 static u8
 _scsih_tm_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
@@ -2640,7 +2625,7 @@ mpt3sas_scsih_clear_tm_flag(struct MPT3SAS_ADAPTER *ioc, u16 handle)
  * The callback index is set inside `ioc->tm_cb_idx`.
  * The caller is responsible to check for outstanding commands.
  *
- * Return SUCCESS or FAILED.
+ * Return: SUCCESS or FAILED.
  */
 int
 mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle, u64 lun,
@@ -2708,11 +2693,9 @@ mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle, u64 lun,
 	mpt3sas_base_put_smid_hi_priority(ioc, smid, msix_task);
 	wait_for_completion_timeout(&ioc->tm_cmds.done, timeout*HZ);
 	if (!(ioc->tm_cmds.status & MPT3_CMD_COMPLETE)) {
-		pr_err(MPT3SAS_FMT "%s: timeout\n",
-		    ioc->name, __func__);
-		_debug_dump_mf(mpi_request,
-		    sizeof(Mpi2SCSITaskManagementRequest_t)/4);
-		if (!(ioc->tm_cmds.status & MPT3_CMD_RESET)) {
+		if (mpt3sas_base_check_cmd_timeout(ioc,
+			ioc->tm_cmds.status, mpi_request,
+			sizeof(Mpi2SCSITaskManagementRequest_t)/4)) {
 			rc = mpt3sas_base_hard_reset_handler(ioc,
 					FORCE_BIG_HAMMER);
 			rc = (!rc) ? SUCCESS : FAILED;
@@ -2846,7 +2829,7 @@ _scsih_tm_display_info(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd)
  * scsih_abort - eh threads main abort routine
  * @scmd: pointer to scsi command object
  *
- * Returns SUCCESS if command aborted else FAILED
+ * Return: SUCCESS if command aborted else FAILED
  */
 static int
 scsih_abort(struct scsi_cmnd *scmd)
@@ -2914,7 +2897,7 @@ scsih_abort(struct scsi_cmnd *scmd)
  * scsih_dev_reset - eh threads main device reset routine
  * @scmd: pointer to scsi command object
  *
- * Returns SUCCESS if command aborted else FAILED
+ * Return: SUCCESS if command aborted else FAILED
  */
 static int
 scsih_dev_reset(struct scsi_cmnd *scmd)
@@ -2992,7 +2975,7 @@ scsih_dev_reset(struct scsi_cmnd *scmd)
  * scsih_target_reset - eh threads main target reset routine
  * @scmd: pointer to scsi command object
  *
- * Returns SUCCESS if command aborted else FAILED
+ * Return: SUCCESS if command aborted else FAILED
  */
 static int
 scsih_target_reset(struct scsi_cmnd *scmd)
@@ -3069,7 +3052,7 @@ scsih_target_reset(struct scsi_cmnd *scmd)
  * scsih_host_reset - eh threads main host reset routine
  * @scmd: pointer to scsi command object
  *
- * Returns SUCCESS if command aborted else FAILED
+ * Return: SUCCESS if command aborted else FAILED
  */
 static int
 scsih_host_reset(struct scsi_cmnd *scmd)
@@ -3105,8 +3088,6 @@ out:
  *
  * This adds the firmware event object into link list, then queues it up to
  * be processed from user context.
- *
- * Return nothing.
  */
 static void
 _scsih_fw_event_add(struct MPT3SAS_ADAPTER *ioc, struct fw_event_work *fw_event)
@@ -3133,8 +3114,6 @@ _scsih_fw_event_add(struct MPT3SAS_ADAPTER *ioc, struct fw_event_work *fw_event)
  * Context: This function will acquire ioc->fw_event_lock.
  *
  * If the fw_event is on the fw_event_list, remove it and do a put.
- *
- * Return nothing.
  */
 static void
 _scsih_fw_event_del_from_list(struct MPT3SAS_ADAPTER *ioc, struct fw_event_work
@@ -3155,8 +3134,6 @@ _scsih_fw_event_del_from_list(struct MPT3SAS_ADAPTER *ioc, struct fw_event_work
  * mpt3sas_send_trigger_data_event - send event for processing trigger data
  * @ioc: per adapter object
  * @event_data: trigger event data
- *
- * Return nothing.
  */
 void
 mpt3sas_send_trigger_data_event(struct MPT3SAS_ADAPTER *ioc,
@@ -3181,8 +3158,6 @@ mpt3sas_send_trigger_data_event(struct MPT3SAS_ADAPTER *ioc,
 /**
  * _scsih_error_recovery_delete_devices - remove devices not responding
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 static void
 _scsih_error_recovery_delete_devices(struct MPT3SAS_ADAPTER *ioc)
@@ -3203,8 +3178,6 @@ _scsih_error_recovery_delete_devices(struct MPT3SAS_ADAPTER *ioc)
 /**
  * mpt3sas_port_enable_complete - port enable completed (fake event)
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 void
 mpt3sas_port_enable_complete(struct MPT3SAS_ADAPTER *ioc)
@@ -3242,8 +3215,6 @@ static struct fw_event_work *dequeue_next_fw_event(struct MPT3SAS_ADAPTER *ioc)
  *
  * Walk the firmware event queue, either killing timers, or waiting
  * for outstanding events to complete
- *
- * Return nothing.
  */
 static void
 _scsih_fw_event_cleanup_queue(struct MPT3SAS_ADAPTER *ioc)
@@ -3369,7 +3340,7 @@ _scsih_ublock_io_all_device(struct MPT3SAS_ADAPTER *ioc)
 /**
  * _scsih_ublock_io_device - prepare device to be deleted
  * @ioc: per adapter object
- * @sas_addr: sas address
+ * @sas_address: sas address
  *
  * unblock then put device in offline state
  */
@@ -3395,7 +3366,6 @@ _scsih_ublock_io_device(struct MPT3SAS_ADAPTER *ioc, u64 sas_address)
 /**
  * _scsih_block_io_all_device - set the device state to SDEV_BLOCK
  * @ioc: per adapter object
- * @handle: device handle
  *
  * During device pull we need to appropriately set the sdev state.
  */
@@ -3730,8 +3700,8 @@ out:
  * handshake protocol with controller firmware.
  * It will send a sas iounit control request (MPI2_SAS_OP_REMOVE_DEVICE)
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 static u8
 _scsih_tm_tr_complete(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
@@ -3822,8 +3792,8 @@ _scsih_tm_tr_complete(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
  * This code is part of the code to initiate the device removal
  * handshake protocol with controller firmware.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 static u8
 _scsih_sas_control_complete(struct MPT3SAS_ADAPTER *ioc, u16 smid,
@@ -3909,8 +3879,8 @@ _scsih_tm_tr_volume_send(struct MPT3SAS_ADAPTER *ioc, u16 handle)
  * @reply: reply message frame(lower 32bit addr)
  * Context: interrupt time.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 static u8
 _scsih_tm_volume_tr_complete(struct MPT3SAS_ADAPTER *ioc, u16 smid,
@@ -4004,19 +3974,19 @@ _scsih_issue_delayed_event_ack(struct MPT3SAS_ADAPTER *ioc, u16 smid, U16 event,
 static void
 _scsih_issue_delayed_sas_io_unit_ctrl(struct MPT3SAS_ADAPTER *ioc,
 					u16 smid, u16 handle)
-	{
-		Mpi2SasIoUnitControlRequest_t *mpi_request;
-		u32 ioc_state;
-		int i = smid - ioc->internal_smid;
-		unsigned long flags;
+{
+	Mpi2SasIoUnitControlRequest_t *mpi_request;
+	u32 ioc_state;
+	int i = smid - ioc->internal_smid;
+	unsigned long flags;
 
-		if (ioc->remove_host) {
-			dewtprintk(ioc, pr_info(MPT3SAS_FMT
+	if (ioc->remove_host) {
+		dewtprintk(ioc, pr_info(MPT3SAS_FMT
 			    "%s: host has been removed\n",
 			     __func__, ioc->name));
-			return;
-		} else if (ioc->pci_error_recovery) {
-			dewtprintk(ioc, pr_info(MPT3SAS_FMT
+		return;
+	} else if (ioc->pci_error_recovery) {
+		dewtprintk(ioc, pr_info(MPT3SAS_FMT
 			    "%s: host in pci error recovery\n",
 			    __func__, ioc->name));
 		return;
@@ -4059,8 +4029,8 @@ _scsih_issue_delayed_sas_io_unit_ctrl(struct MPT3SAS_ADAPTER *ioc,
  * This will check delayed internal messages list, and process the
  * next request.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 u8
 mpt3sas_check_for_pending_internal_cmds(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -4098,8 +4068,8 @@ mpt3sas_check_for_pending_internal_cmds(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * This will check delayed target reset list, and feed the
  * next reqeust.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 static u8
 _scsih_check_for_pending_tm(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -4139,8 +4109,6 @@ _scsih_check_for_pending_tm(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * This handles the case where driver receives multiple expander
  * add and delete events in a single shot.  When there is a delete event
  * the routine will void any pending add events waiting in the event queue.
- *
- * Return nothing.
  */
 static void
 _scsih_check_topo_delete_events(struct MPT3SAS_ADAPTER *ioc,
@@ -4222,8 +4190,6 @@ _scsih_check_topo_delete_events(struct MPT3SAS_ADAPTER *ioc,
  * or device add and delete events in a single shot.  When there
  * is a delete event the routine will void any pending add
  * events waiting in the event queue.
- *
- * Return nothing.
  */
 static void
 _scsih_check_pcie_topo_remove_events(struct MPT3SAS_ADAPTER *ioc,
@@ -4348,8 +4314,6 @@ _scsih_set_volume_handle_for_tr(u16 handle, u16 *a, u16 *b)
  * volume has been deleted or removed. When the target reset is sent
  * to volume, the PD target resets need to be queued to start upon
  * completion of the volume target reset.
- *
- * Return nothing.
  */
 static void
 _scsih_check_ir_config_unhide_events(struct MPT3SAS_ADAPTER *ioc,
@@ -4433,8 +4397,6 @@ _scsih_check_ir_config_unhide_events(struct MPT3SAS_ADAPTER *ioc,
  * This will handle the case when the cable connected to entire volume is
  * pulled. We will take care of setting the deleted flag so normal IO will
  * not be sent.
- *
- * Return nothing.
  */
 static void
 _scsih_check_volume_delete_events(struct MPT3SAS_ADAPTER *ioc,
@@ -4456,8 +4418,6 @@ _scsih_check_volume_delete_events(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @event_data: the temp threshold event data
  * Context: interrupt time.
- *
- * Return nothing.
  */
 static void
 _scsih_temp_threshold_events(struct MPT3SAS_ADAPTER *ioc,
@@ -4496,8 +4456,6 @@ static int _scsih_set_satl_pending(struct scsi_cmnd *scmd, bool pending)
  *
  * The flushing out of all pending scmd commands following host reset,
  * where all IO is dropped to the floor.
- *
- * Return nothing.
  */
 static void
 _scsih_flush_running_cmds(struct MPT3SAS_ADAPTER *ioc)
@@ -4533,8 +4491,6 @@ _scsih_flush_running_cmds(struct MPT3SAS_ADAPTER *ioc)
  * @mpi_request: pointer to the SCSI_IO request message frame
  *
  * Supporting protection 1 and 3.
- *
- * Returns nothing
  */
 static void
 _scsih_setup_eedp(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
@@ -4568,7 +4524,7 @@ _scsih_setup_eedp(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
 		    MPI2_SCSIIO_EEDPFLAGS_CHECK_REFTAG |
 		    MPI2_SCSIIO_EEDPFLAGS_CHECK_GUARD;
 		mpi_request->CDB.EEDP32.PrimaryReferenceTag =
-		    cpu_to_be32(scsi_prot_ref_tag(scmd));
+		    cpu_to_be32(t10_pi_ref_tag(scmd->request));
 		break;
 
 	case SCSI_PROT_DIF_TYPE3:
@@ -4593,8 +4549,6 @@ _scsih_setup_eedp(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
  * _scsih_eedp_error_handling - return sense code for EEDP errors
  * @scmd: pointer to scsi command object
  * @ioc_status: ioc status
- *
- * Returns nothing
  */
 static void
 _scsih_eedp_error_handling(struct scsi_cmnd *scmd, u16 ioc_status)
@@ -4623,12 +4577,12 @@ _scsih_eedp_error_handling(struct scsi_cmnd *scmd, u16 ioc_status)
 
 /**
  * scsih_qcmd - main scsi request entry point
+ * @shost: SCSI host pointer
  * @scmd: pointer to scsi command object
- * @done: function pointer to be invoked on completion
  *
  * The callback index is set inside `ioc->scsi_io_cb_idx`.
  *
- * Returns 0 on success.  If there's a failure, return either:
+ * Return: 0 on success.  If there's a failure, return either:
  * SCSI_MLQUEUE_DEVICE_BUSY if the device queue is full, or
  * SCSI_MLQUEUE_HOST_BUSY if the entire host queue is full
  */
@@ -4674,19 +4628,19 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 	}
 
 
-	/* host recovery or link resets sent via IOCTLs */
-	if (ioc->shost_recovery || ioc->ioc_link_reset_in_progress)
+	if (ioc->shost_recovery || ioc->ioc_link_reset_in_progress) {
+		/* host recovery or link resets sent via IOCTLs */
 		return SCSI_MLQUEUE_HOST_BUSY;
-
-	/* device has been deleted */
-	else if (sas_target_priv_data->deleted) {
+	} else if (sas_target_priv_data->deleted) {
+		/* device has been deleted */
 		scmd->result = DID_NO_CONNECT << 16;
 		scmd->scsi_done(scmd);
 		return 0;
-	/* device busy with task management */
 	} else if (sas_target_priv_data->tm_busy ||
-	    sas_device_priv_data->block)
+		   sas_device_priv_data->block) {
+		/* device busy with task management */
 		return SCSI_MLQUEUE_DEVICE_BUSY;
+	}
 
 	/*
 	 * Bug work around for firmware SATL handling.  The loop
@@ -4791,8 +4745,6 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
  * _scsih_normalize_sense - normalize descriptor and fixed format sense data
  * @sense_buffer: sense data returned by target
  * @data: normalized skey/asc/ascq
- *
- * Return nothing.
  */
 static void
 _scsih_normalize_sense(char *sense_buffer, struct sense_info *data)
@@ -4815,12 +4767,11 @@ _scsih_normalize_sense(char *sense_buffer, struct sense_info *data)
  * @ioc: per adapter object
  * @scmd: pointer to scsi command object
  * @mpi_reply: reply mf payload returned from firmware
+ * @smid: ?
  *
  * scsi_status - SCSI Status code returned from target device
  * scsi_state - state info associated with SCSI_IO determined by ioc
  * ioc_status - ioc supplied status info
- *
- * Return nothing.
  */
 static void
 _scsih_scsi_ioc_info(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
@@ -5044,8 +4995,6 @@ _scsih_scsi_ioc_info(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
  * @ioc: per adapter object
  * @handle: device handle
  * Context: process
- *
- * Return nothing.
  */
 static void
 _scsih_turn_on_pfa_led(struct MPT3SAS_ADAPTER *ioc, u16 handle)
@@ -5089,8 +5038,6 @@ out:
  * @ioc: per adapter object
  * @sas_device: sas device whose PFA LED has to turned off
  * Context: process
- *
- * Return nothing.
  */
 static void
 _scsih_turn_off_pfa_led(struct MPT3SAS_ADAPTER *ioc,
@@ -5128,8 +5075,6 @@ _scsih_turn_off_pfa_led(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @handle: device handle
  * Context: interrupt.
- *
- * Return nothing.
  */
 static void
 _scsih_send_event_to_turn_on_pfa_led(struct MPT3SAS_ADAPTER *ioc, u16 handle)
@@ -5151,8 +5096,6 @@ _scsih_send_event_to_turn_on_pfa_led(struct MPT3SAS_ADAPTER *ioc, u16 handle)
  * @ioc: per adapter object
  * @handle: device handle
  * Context: interrupt.
- *
- * Return nothing.
  */
 static void
 _scsih_smart_predicted_fault(struct MPT3SAS_ADAPTER *ioc, u16 handle)
@@ -5228,8 +5171,8 @@ out_unlock:
  *
  * Callback handler when using _scsih_qcmd.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 static u8
 _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
@@ -5416,6 +5359,7 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 
 	case MPI2_IOCSTATUS_SCSI_DATA_OVERRUN:
 		scsi_set_resid(scmd, 0);
+		/* fall through */
 	case MPI2_IOCSTATUS_SCSI_RECOVERED_ERROR:
 	case MPI2_IOCSTATUS_SUCCESS:
 		scmd->result = (DID_OK << 16) | scsi_status;
@@ -5468,8 +5412,6 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
  * During port enable, fw will send topology events for every device. Its
  * possible that the handles may change from the previous setting, so this
  * code keeping handles updating if changed.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_host_refresh(struct MPT3SAS_ADAPTER *ioc)
@@ -5523,8 +5465,6 @@ _scsih_sas_host_refresh(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: per adapter object
  *
  * Creating host side data object, stored in ioc->sas_hba
- *
- * Return nothing.
  */
 static void
 _scsih_sas_host_add(struct MPT3SAS_ADAPTER *ioc)
@@ -5672,7 +5612,7 @@ _scsih_sas_host_add(struct MPT3SAS_ADAPTER *ioc)
  *
  * Creating expander object, stored in ioc->sas_expander_list.
  *
- * Return 0 for success, else error.
+ * Return: 0 for success, else error.
  */
 static int
 _scsih_expander_add(struct MPT3SAS_ADAPTER *ioc, u16 handle)
@@ -5812,7 +5752,7 @@ _scsih_expander_add(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 	}
 
 	_scsih_expander_node_add(ioc, sas_expander);
-	 return 0;
+	return 0;
 
  out_fail:
 
@@ -5827,8 +5767,6 @@ _scsih_expander_add(struct MPT3SAS_ADAPTER *ioc, u16 handle)
  * mpt3sas_expander_remove - removing expander object
  * @ioc: per adapter object
  * @sas_address: expander sas_address
- *
- * Return nothing.
  */
 void
 mpt3sas_expander_remove(struct MPT3SAS_ADAPTER *ioc, u64 sas_address)
@@ -5857,8 +5795,8 @@ mpt3sas_expander_remove(struct MPT3SAS_ADAPTER *ioc, u64 sas_address)
  * Callback handler when sending internal generated SCSI_IO.
  * The callback index passed is `ioc->scsih_cb_idx`
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 static u8
 _scsih_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
@@ -5892,9 +5830,9 @@ _scsih_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
  * @ioc: per adapter object
  * @sas_address: sas address
  * @handle: sas device handle
- * @access_flags: errors returned during discovery of the device
+ * @access_status: errors returned during discovery of the device
  *
- * Return 0 for success, else failure
+ * Return: 0 for success, else failure
  */
 static u8
 _scsih_check_access_status(struct MPT3SAS_ADAPTER *ioc, u64 sas_address,
@@ -5956,10 +5894,8 @@ _scsih_check_access_status(struct MPT3SAS_ADAPTER *ioc, u64 sas_address,
  * @ioc: per adapter object
  * @parent_sas_address: sas address of parent expander or sas host
  * @handle: attached device handle
- * @phy_numberv: phy number
+ * @phy_number: phy number
  * @link_rate: new link rate
- *
- * Returns nothing.
  */
 static void
 _scsih_check_device(struct MPT3SAS_ADAPTER *ioc,
@@ -6076,7 +6012,7 @@ out_unlock:
  *
  * Creating end device object, stored in ioc->sas_device_list.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _scsih_add_device(struct MPT3SAS_ADAPTER *ioc, u16 handle, u8 phy_num,
@@ -6208,9 +6144,7 @@ _scsih_add_device(struct MPT3SAS_ADAPTER *ioc, u16 handle, u8 phy_num,
 /**
  * _scsih_remove_device -  removing sas device object
  * @ioc: per adapter object
- * @sas_device_delete: the sas_device object
- *
- * Return nothing.
+ * @sas_device: the sas_device object
  */
 static void
 _scsih_remove_device(struct MPT3SAS_ADAPTER *ioc,
@@ -6446,6 +6380,7 @@ _scsih_sas_topology_change_event(struct MPT3SAS_ADAPTER *ioc,
 			if (!test_bit(handle, ioc->pend_os_device_add))
 				break;
 
+			/* fall through */
 
 		case MPI2_EVENT_SAS_TOPO_RC_TARG_ADDED:
 
@@ -6475,10 +6410,9 @@ _scsih_sas_topology_change_event(struct MPT3SAS_ADAPTER *ioc,
 
 /**
  * _scsih_sas_device_status_change_event_debug - debug for device event
+ * @ioc: ?
  * @event_data: event data payload
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_device_status_change_event_debug(struct MPT3SAS_ADAPTER *ioc,
@@ -6546,8 +6480,6 @@ _scsih_sas_device_status_change_event_debug(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_device_status_change_event(struct MPT3SAS_ADAPTER *ioc,
@@ -6608,9 +6540,9 @@ out:
  * @ioc: per adapter object
  * @wwid: wwid
  * @handle: sas device handle
- * @access_flags: errors returned during discovery of the device
+ * @access_status: errors returned during discovery of the device
  *
- * Return 0 for success, else failure
+ * Return: 0 for success, else failure
  */
 static u8
 _scsih_check_pcie_access_status(struct MPT3SAS_ADAPTER *ioc, u64 wwid,
@@ -6695,8 +6627,6 @@ _scsih_check_pcie_access_status(struct MPT3SAS_ADAPTER *ioc, u64 wwid,
  * from SML and free up associated memory
  * @ioc: per adapter object
  * @pcie_device: the pcie_device object
- *
- * Return nothing.
  */
 static void
 _scsih_pcie_device_remove_from_sml(struct MPT3SAS_ADAPTER *ioc,
@@ -6770,8 +6700,6 @@ _scsih_pcie_device_remove_from_sml(struct MPT3SAS_ADAPTER *ioc,
  * _scsih_pcie_check_device - checking device responsiveness
  * @ioc: per adapter object
  * @handle: attached device handle
- *
- * Returns nothing.
  */
 static void
 _scsih_pcie_check_device(struct MPT3SAS_ADAPTER *ioc, u16 handle)
@@ -6863,7 +6791,7 @@ _scsih_pcie_check_device(struct MPT3SAS_ADAPTER *ioc, u16 handle)
  *
  * Creating end device object, stored in ioc->pcie_device_list.
  *
- * Return 1 means queue the event later, 0 means complete the event
+ * Return: 1 means queue the event later, 0 means complete the event
  */
 static int
 _scsih_pcie_add_device(struct MPT3SAS_ADAPTER *ioc, u16 handle)
@@ -6873,7 +6801,6 @@ _scsih_pcie_add_device(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 	Mpi2ConfigReply_t mpi_reply;
 	struct _pcie_device *pcie_device;
 	struct _enclosure_node *enclosure_dev;
-	u32 pcie_device_type;
 	u32 ioc_status;
 	u64 wwid;
 
@@ -6935,8 +6862,6 @@ _scsih_pcie_add_device(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 	pcie_device->port_num = pcie_device_pg0.PortNum;
 	pcie_device->fast_path = (le32_to_cpu(pcie_device_pg0.Flags) &
 	    MPI26_PCIEDEV0_FLAGS_FAST_PATH_CAPABLE) ? 1 : 0;
-	pcie_device_type = pcie_device->device_info &
-	    MPI26_PCIE_DEVINFO_MASK_DEVICE_TYPE;
 
 	pcie_device->enclosure_handle =
 	    le16_to_cpu(pcie_device_pg0.EnclosureHandle);
@@ -7165,6 +7090,7 @@ _scsih_pcie_topology_change_event(struct MPT3SAS_ADAPTER *ioc,
 			event_data->PortEntry[i].PortStatus &= 0xF0;
 			event_data->PortEntry[i].PortStatus |=
 				MPI26_EVENT_PCIE_TOPO_PS_DEV_ADDED;
+			/* fall through */
 		case MPI26_EVENT_PCIE_TOPO_PS_DEV_ADDED:
 			if (ioc->shost_recovery)
 				break;
@@ -7190,12 +7116,10 @@ _scsih_pcie_topology_change_event(struct MPT3SAS_ADAPTER *ioc,
 }
 
 /**
- * _scsih_pcie_device_status_change_event_debug - debug for
- * device event
+ * _scsih_pcie_device_status_change_event_debug - debug for device event
+ * @ioc: ?
  * @event_data: event data payload
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_pcie_device_status_change_event_debug(struct MPT3SAS_ADAPTER *ioc,
@@ -7262,8 +7186,6 @@ _scsih_pcie_device_status_change_event_debug(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_pcie_device_status_change_event(struct MPT3SAS_ADAPTER *ioc,
@@ -7314,8 +7236,6 @@ out:
  * @ioc: per adapter object
  * @event_data: event data payload
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_enclosure_dev_status_change_event_debug(struct MPT3SAS_ADAPTER *ioc,
@@ -7348,8 +7268,6 @@ _scsih_sas_enclosure_dev_status_change_event_debug(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_enclosure_dev_status_change_event(struct MPT3SAS_ADAPTER *ioc,
@@ -7416,8 +7334,6 @@ _scsih_sas_enclosure_dev_status_change_event(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_broadcast_primitive_event(struct MPT3SAS_ADAPTER *ioc,
@@ -7483,6 +7399,10 @@ _scsih_sas_broadcast_primitive_event(struct MPT3SAS_ADAPTER *ioc,
 		if (sas_device_priv_data->sas_target->flags &
 		    MPT_TARGET_FLAGS_VOLUME)
 			continue;
+		 /* skip PCIe devices */
+		if (sas_device_priv_data->sas_target->flags &
+		    MPT_TARGET_FLAGS_PCIE_DEVICE)
+			continue;
 
 		handle = sas_device_priv_data->sas_target->handle;
 		lun = sas_device_priv_data->lun;
@@ -7580,8 +7500,6 @@ _scsih_sas_broadcast_primitive_event(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_discovery_event(struct MPT3SAS_ADAPTER *ioc,
@@ -7617,8 +7535,6 @@ _scsih_sas_discovery_event(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_device_discovery_error_event(struct MPT3SAS_ADAPTER *ioc,
@@ -7654,8 +7570,6 @@ _scsih_sas_device_discovery_error_event(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_pcie_enumeration_event(struct MPT3SAS_ADAPTER *ioc,
@@ -7684,7 +7598,7 @@ _scsih_pcie_enumeration_event(struct MPT3SAS_ADAPTER *ioc,
  * @handle: device handle for physical disk
  * @phys_disk_num: physical disk number
  *
- * Return 0 for success, else failure.
+ * Return: 0 for success, else failure.
  */
 static int
 _scsih_ir_fastpath(struct MPT3SAS_ADAPTER *ioc, u16 handle, u8 phys_disk_num)
@@ -7736,10 +7650,10 @@ _scsih_ir_fastpath(struct MPT3SAS_ADAPTER *ioc, u16 handle, u8 phys_disk_num)
 	wait_for_completion_timeout(&ioc->scsih_cmds.done, 10*HZ);
 
 	if (!(ioc->scsih_cmds.status & MPT3_CMD_COMPLETE)) {
-		pr_err(MPT3SAS_FMT "%s: timeout\n",
-		    ioc->name, __func__);
-		if (!(ioc->scsih_cmds.status & MPT3_CMD_RESET))
-			issue_reset = 1;
+		issue_reset =
+			mpt3sas_base_check_cmd_timeout(ioc,
+				ioc->scsih_cmds.status, mpi_request,
+				sizeof(Mpi2RaidActionRequest_t)/4);
 		rc = -EFAULT;
 		goto out;
 	}
@@ -7794,8 +7708,6 @@ _scsih_reprobe_lun(struct scsi_device *sdev, void *no_uld_attach)
  * @ioc: per adapter object
  * @element: IR config element data
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_volume_add(struct MPT3SAS_ADAPTER *ioc,
@@ -7852,8 +7764,6 @@ _scsih_sas_volume_add(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @handle: volume device handle
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_volume_delete(struct MPT3SAS_ADAPTER *ioc, u16 handle)
@@ -7887,8 +7797,6 @@ _scsih_sas_volume_delete(struct MPT3SAS_ADAPTER *ioc, u16 handle)
  * @ioc: per adapter object
  * @element: IR config element data
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_pd_expose(struct MPT3SAS_ADAPTER *ioc,
@@ -7929,8 +7837,6 @@ _scsih_sas_pd_expose(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @element: IR config element data
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_pd_hide(struct MPT3SAS_ADAPTER *ioc,
@@ -7980,8 +7886,6 @@ _scsih_sas_pd_hide(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @element: IR config element data
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_pd_delete(struct MPT3SAS_ADAPTER *ioc,
@@ -7997,8 +7901,6 @@ _scsih_sas_pd_delete(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @element: IR config element data
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_pd_add(struct MPT3SAS_ADAPTER *ioc,
@@ -8050,8 +7952,6 @@ _scsih_sas_pd_add(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @event_data: event data payload
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_ir_config_change_event_debug(struct MPT3SAS_ADAPTER *ioc,
@@ -8130,8 +8030,6 @@ _scsih_sas_ir_config_change_event_debug(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_ir_config_change_event(struct MPT3SAS_ADAPTER *ioc,
@@ -8202,8 +8100,6 @@ _scsih_sas_ir_config_change_event(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_ir_volume_event(struct MPT3SAS_ADAPTER *ioc,
@@ -8286,8 +8182,6 @@ _scsih_sas_ir_volume_event(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_ir_physical_disk_event(struct MPT3SAS_ADAPTER *ioc,
@@ -8372,8 +8266,6 @@ _scsih_sas_ir_physical_disk_event(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @event_data: event data payload
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_ir_operation_status_event_debug(struct MPT3SAS_ADAPTER *ioc,
@@ -8414,8 +8306,6 @@ _scsih_sas_ir_operation_status_event_debug(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_ir_operation_status_event(struct MPT3SAS_ADAPTER *ioc,
@@ -8473,8 +8363,6 @@ _scsih_prep_device_scan(struct MPT3SAS_ADAPTER *ioc)
  *
  * After host reset, find out whether devices are still responding.
  * Used in _scsih_remove_unresponsive_sas_devices.
- *
- * Return nothing.
  */
 static void
 _scsih_mark_responding_sas_device(struct MPT3SAS_ADAPTER *ioc,
@@ -8569,8 +8457,6 @@ Mpi2SasDevicePage0_t *sas_device_pg0)
  * _scsih_create_enclosure_list_after_reset - Free Existing list,
  *	And create enclosure list by scanning all Enclosure Page(0)s
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 static void
 _scsih_create_enclosure_list_after_reset(struct MPT3SAS_ADAPTER *ioc)
@@ -8617,8 +8503,6 @@ _scsih_create_enclosure_list_after_reset(struct MPT3SAS_ADAPTER *ioc)
  *
  * After host reset, find out whether devices are still responding.
  * If not remove.
- *
- * Return nothing.
  */
 static void
 _scsih_search_responding_sas_devices(struct MPT3SAS_ADAPTER *ioc)
@@ -8661,8 +8545,6 @@ _scsih_search_responding_sas_devices(struct MPT3SAS_ADAPTER *ioc)
  *
  * After host reset, find out whether devices are still responding.
  * Used in _scsih_remove_unresponding_devices.
- *
- * Return nothing.
  */
 static void
 _scsih_mark_responding_pcie_device(struct MPT3SAS_ADAPTER *ioc,
@@ -8736,8 +8618,6 @@ _scsih_mark_responding_pcie_device(struct MPT3SAS_ADAPTER *ioc,
  *
  * After host reset, find out whether devices are still responding.
  * If not remove.
- *
- * Return nothing.
  */
 static void
 _scsih_search_responding_pcie_devices(struct MPT3SAS_ADAPTER *ioc)
@@ -8785,8 +8665,6 @@ out:
  *
  * After host reset, find out whether devices are still responding.
  * Used in _scsih_remove_unresponsive_raid_devices.
- *
- * Return nothing.
  */
 static void
 _scsih_mark_responding_raid_device(struct MPT3SAS_ADAPTER *ioc, u64 wwid,
@@ -8842,8 +8720,6 @@ _scsih_mark_responding_raid_device(struct MPT3SAS_ADAPTER *ioc, u64 wwid,
  *
  * After host reset, find out whether devices are still responding.
  * If not remove.
- *
- * Return nothing.
  */
 static void
 _scsih_search_responding_raid_devices(struct MPT3SAS_ADAPTER *ioc)
@@ -8914,8 +8790,6 @@ _scsih_search_responding_raid_devices(struct MPT3SAS_ADAPTER *ioc)
  *
  * After host reset, find out whether devices are still responding.
  * Used in _scsih_remove_unresponsive_expanders.
- *
- * Return nothing.
  */
 static void
 _scsih_mark_responding_expander(struct MPT3SAS_ADAPTER *ioc,
@@ -8968,8 +8842,6 @@ _scsih_mark_responding_expander(struct MPT3SAS_ADAPTER *ioc,
  *
  * After host reset, find out whether devices are still responding.
  * If not remove.
- *
- * Return nothing.
  */
 static void
 _scsih_search_responding_expanders(struct MPT3SAS_ADAPTER *ioc)
@@ -9009,8 +8881,6 @@ _scsih_search_responding_expanders(struct MPT3SAS_ADAPTER *ioc)
 /**
  * _scsih_remove_unresponding_devices - removing unresponding devices
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 static void
 _scsih_remove_unresponding_devices(struct MPT3SAS_ADAPTER *ioc)
@@ -9136,8 +9006,6 @@ _scsih_refresh_expander_links(struct MPT3SAS_ADAPTER *ioc,
 /**
  * _scsih_scan_for_devices_after_reset - scan for devices after host reset
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 static void
 _scsih_scan_for_devices_after_reset(struct MPT3SAS_ADAPTER *ioc)
@@ -9421,60 +9289,68 @@ _scsih_scan_for_devices_after_reset(struct MPT3SAS_ADAPTER *ioc)
 		ioc->name);
 	pr_info(MPT3SAS_FMT "scan devices: complete\n", ioc->name);
 }
+
 /**
  * mpt3sas_scsih_reset_handler - reset callback handler (for scsih)
  * @ioc: per adapter object
- * @reset_phase: phase
  *
  * The handler for doing any required cleanup or initialization.
+ */
+void mpt3sas_scsih_pre_reset_handler(struct MPT3SAS_ADAPTER *ioc)
+{
+	dtmprintk(ioc, pr_info(MPT3SAS_FMT
+			"%s: MPT3_IOC_PRE_RESET\n", ioc->name, __func__));
+}
+
+/**
+ * mpt3sas_scsih_after_reset_handler - reset callback handler (for scsih)
+ * @ioc: per adapter object
  *
- * The reset phase can be MPT3_IOC_PRE_RESET, MPT3_IOC_AFTER_RESET,
- * MPT3_IOC_DONE_RESET
- *
- * Return nothing.
+ * The handler for doing any required cleanup or initialization.
  */
 void
-mpt3sas_scsih_reset_handler(struct MPT3SAS_ADAPTER *ioc, int reset_phase)
+mpt3sas_scsih_after_reset_handler(struct MPT3SAS_ADAPTER *ioc)
 {
-	switch (reset_phase) {
-	case MPT3_IOC_PRE_RESET:
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT
-			"%s: MPT3_IOC_PRE_RESET\n", ioc->name, __func__));
-		break;
-	case MPT3_IOC_AFTER_RESET:
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT
+	dtmprintk(ioc, pr_info(MPT3SAS_FMT
 			"%s: MPT3_IOC_AFTER_RESET\n", ioc->name, __func__));
-		if (ioc->scsih_cmds.status & MPT3_CMD_PENDING) {
-			ioc->scsih_cmds.status |= MPT3_CMD_RESET;
-			mpt3sas_base_free_smid(ioc, ioc->scsih_cmds.smid);
-			complete(&ioc->scsih_cmds.done);
-		}
-		if (ioc->tm_cmds.status & MPT3_CMD_PENDING) {
-			ioc->tm_cmds.status |= MPT3_CMD_RESET;
-			mpt3sas_base_free_smid(ioc, ioc->tm_cmds.smid);
-			complete(&ioc->tm_cmds.done);
-		}
+	if (ioc->scsih_cmds.status & MPT3_CMD_PENDING) {
+		ioc->scsih_cmds.status |= MPT3_CMD_RESET;
+		mpt3sas_base_free_smid(ioc, ioc->scsih_cmds.smid);
+		complete(&ioc->scsih_cmds.done);
+	}
+	if (ioc->tm_cmds.status & MPT3_CMD_PENDING) {
+		ioc->tm_cmds.status |= MPT3_CMD_RESET;
+		mpt3sas_base_free_smid(ioc, ioc->tm_cmds.smid);
+		complete(&ioc->tm_cmds.done);
+	}
 
-		memset(ioc->pend_os_device_add, 0, ioc->pend_os_device_add_sz);
-		memset(ioc->device_remove_in_progress, 0,
-		       ioc->device_remove_in_progress_sz);
-		_scsih_fw_event_cleanup_queue(ioc);
-		_scsih_flush_running_cmds(ioc);
-		break;
-	case MPT3_IOC_DONE_RESET:
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT
+	memset(ioc->pend_os_device_add, 0, ioc->pend_os_device_add_sz);
+	memset(ioc->device_remove_in_progress, 0,
+	       ioc->device_remove_in_progress_sz);
+	_scsih_fw_event_cleanup_queue(ioc);
+	_scsih_flush_running_cmds(ioc);
+}
+
+/**
+ * mpt3sas_scsih_reset_handler - reset callback handler (for scsih)
+ * @ioc: per adapter object
+ *
+ * The handler for doing any required cleanup or initialization.
+ */
+void
+mpt3sas_scsih_reset_done_handler(struct MPT3SAS_ADAPTER *ioc)
+{
+	dtmprintk(ioc, pr_info(MPT3SAS_FMT
 			"%s: MPT3_IOC_DONE_RESET\n", ioc->name, __func__));
-		if ((!ioc->is_driver_loading) && !(disable_discovery > 0 &&
-		    !ioc->sas_hba.num_phys)) {
-			_scsih_prep_device_scan(ioc);
-			_scsih_create_enclosure_list_after_reset(ioc);
-			_scsih_search_responding_sas_devices(ioc);
-			_scsih_search_responding_pcie_devices(ioc);
-			_scsih_search_responding_raid_devices(ioc);
-			_scsih_search_responding_expanders(ioc);
-			_scsih_error_recovery_delete_devices(ioc);
-		}
-		break;
+	if ((!ioc->is_driver_loading) && !(disable_discovery > 0 &&
+					   !ioc->sas_hba.num_phys)) {
+		_scsih_prep_device_scan(ioc);
+		_scsih_create_enclosure_list_after_reset(ioc);
+		_scsih_search_responding_sas_devices(ioc);
+		_scsih_search_responding_pcie_devices(ioc);
+		_scsih_search_responding_raid_devices(ioc);
+		_scsih_search_responding_expanders(ioc);
+		_scsih_error_recovery_delete_devices(ioc);
 	}
 }
 
@@ -9483,8 +9359,6 @@ mpt3sas_scsih_reset_handler(struct MPT3SAS_ADAPTER *ioc, int reset_phase)
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _mpt3sas_fw_work(struct MPT3SAS_ADAPTER *ioc, struct fw_event_work *fw_event)
@@ -9519,7 +9393,7 @@ _mpt3sas_fw_work(struct MPT3SAS_ADAPTER *ioc, struct fw_event_work *fw_event)
 		break;
 	case MPT3SAS_PORT_ENABLE_COMPLETE:
 		ioc->start_scan = 0;
-	if (missing_delay[0] != -1 && missing_delay[1] != -1)
+		if (missing_delay[0] != -1 && missing_delay[1] != -1)
 			mpt3sas_base_update_missing_delay(ioc, missing_delay[0],
 			    missing_delay[1]);
 		dewtprintk(ioc, pr_info(MPT3SAS_FMT
@@ -9577,13 +9451,10 @@ out:
 
 /**
  * _firmware_event_work
- * @ioc: per adapter object
  * @work: The fw_event_work object
  * Context: user.
  *
  * wrappers for the work thread handling firmware events
- *
- * Return nothing.
  */
 
 static void
@@ -9605,8 +9476,8 @@ _firmware_event_work(struct work_struct *work)
  * This function merely adds a new work task into ioc->firmware_event_thread.
  * The tasks are worked from _firmware_event_work in user context.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 u8
 mpt3sas_scsih_event_callback(struct MPT3SAS_ADAPTER *ioc, u8 msix_index,
@@ -9791,8 +9662,6 @@ mpt3sas_scsih_event_callback(struct MPT3SAS_ADAPTER *ioc, u8 msix_index,
  *
  * Removing object and freeing associated memory from the
  * ioc->sas_expander_list.
- *
- * Return nothing.
  */
 static void
 _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc,
@@ -9841,8 +9710,6 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc,
  *
  * Sending RAID Action to alert the Integrated RAID subsystem of the IOC that
  * the host system is shutting down.
- *
- * Return nothing.
  */
 static void
 _scsih_ir_shutdown(struct MPT3SAS_ADAPTER *ioc)
@@ -9914,7 +9781,6 @@ _scsih_ir_shutdown(struct MPT3SAS_ADAPTER *ioc)
  * @pdev: PCI device struct
  *
  * Routine called when unloading the driver.
- * Return nothing.
  */
 static void scsih_remove(struct pci_dev *pdev)
 {
@@ -9996,8 +9862,6 @@ static void scsih_remove(struct pci_dev *pdev)
 /**
  * scsih_shutdown - routine call during system shutdown
  * @pdev: PCI device struct
- *
- * Return nothing.
  */
 static void
 scsih_shutdown(struct pci_dev *pdev)
@@ -10220,7 +10084,7 @@ _scsih_probe_sas(struct MPT3SAS_ADAPTER *ioc)
  *
  * Get the next pcie device from pcie_device_init_list list.
  *
- * Returns pcie device structure if pcie_device_init_list list is not empty
+ * Return: pcie device structure if pcie_device_init_list list is not empty
  * otherwise returns NULL
  */
 static struct _pcie_device *get_next_pcie_device(struct MPT3SAS_ADAPTER *ioc)
@@ -10390,7 +10254,7 @@ scsih_scan_finished(struct Scsi_Host *shost, unsigned long time)
 	}
 
 	if (time >= (300 * HZ)) {
-		ioc->base_cmds.status = MPT3_CMD_NOT_USED;
+		ioc->port_enable_cmds.status = MPT3_CMD_NOT_USED;
 		pr_info(MPT3SAS_FMT
 			"port enable: FAILED with timeout (timeout=300s)\n",
 			ioc->name);
@@ -10412,7 +10276,7 @@ scsih_scan_finished(struct Scsi_Host *shost, unsigned long time)
 	}
 
 	pr_info(MPT3SAS_FMT "port enable: SUCCESS\n", ioc->name);
-	ioc->base_cmds.status = MPT3_CMD_NOT_USED;
+	ioc->port_enable_cmds.status = MPT3_CMD_NOT_USED;
 
 	if (ioc->wait_for_discovery_to_complete) {
 		ioc->wait_for_discovery_to_complete = 0;
@@ -10568,7 +10432,7 @@ _scsih_determine_hba_mpi_version(struct pci_dev *pdev)
  * @pdev: PCI device struct
  * @id: pci device id
  *
- * Returns 0 success, anything else error.
+ * Return: 0 success, anything else error.
  */
 static int
 _scsih_probe(struct pci_dev *pdev, const struct pci_device_id *id)
@@ -10818,7 +10682,7 @@ out_add_shost_fail:
  * @pdev: PCI device struct
  * @state: PM state change to (usually PCI_D3)
  *
- * Returns 0 success, anything else error.
+ * Return: 0 success, anything else error.
  */
 static int
 scsih_suspend(struct pci_dev *pdev, pm_message_t state)
@@ -10845,7 +10709,7 @@ scsih_suspend(struct pci_dev *pdev, pm_message_t state)
  * scsih_resume - power management resume main entry point
  * @pdev: PCI device struct
  *
- * Returns 0 success, anything else error.
+ * Return: 0 success, anything else error.
  */
 static int
 scsih_resume(struct pci_dev *pdev)
@@ -10881,8 +10745,7 @@ scsih_resume(struct pci_dev *pdev)
  *
  * Description: Called when a PCI error is detected.
  *
- * Return value:
- *      PCI_ERS_RESULT_NEED_RESET or PCI_ERS_RESULT_DISCONNECT
+ * Return: PCI_ERS_RESULT_NEED_RESET or PCI_ERS_RESULT_DISCONNECT.
  */
 static pci_ers_result_t
 scsih_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t state)
@@ -11143,7 +11006,7 @@ static struct pci_driver mpt3sas_driver = {
 /**
  * scsih_init - main entry point for this driver.
  *
- * Returns 0 success, anything else error.
+ * Return: 0 success, anything else error.
  */
 static int
 scsih_init(void)
@@ -11193,7 +11056,7 @@ scsih_init(void)
 /**
  * scsih_exit - exit point for this driver (when it is a module).
  *
- * Returns 0 success, anything else error.
+ * Return: 0 success, anything else error.
  */
 static void
 scsih_exit(void)
@@ -11223,7 +11086,7 @@ scsih_exit(void)
 /**
  * _mpt3sas_init - main entry point for this driver.
  *
- * Returns 0 success, anything else error.
+ * Return: 0 success, anything else error.
  */
 static int __init
 _mpt3sas_init(void)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_transport.c b/drivers/scsi/mpt3sas/mpt3sas_transport.c
index 3a143bb5ca72..f8cc2677c1cd 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_transport.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_transport.c
@@ -134,7 +134,7 @@ _transport_convert_phy_link_rate(u8 link_rate)
  *
  * Populates sas identify info.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _transport_set_identify(struct MPT3SAS_ADAPTER *ioc, u16 handle,
@@ -226,8 +226,8 @@ _transport_set_identify(struct MPT3SAS_ADAPTER *ioc, u16 handle,
  * Callback handler when sending internal generated transport cmds.
  * The callback index passed is `ioc->transport_cb_idx`
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 u8
 mpt3sas_transport_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
@@ -287,7 +287,7 @@ struct rep_manu_reply {
  *
  * Fills in the sas_expander_device object when SMP port is created.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _transport_expander_report_manufacture(struct MPT3SAS_ADAPTER *ioc,
@@ -460,8 +460,6 @@ _transport_expander_report_manufacture(struct MPT3SAS_ADAPTER *ioc,
  * _transport_delete_port - helper function to removing a port
  * @ioc: per adapter object
  * @mpt3sas_port: mpt3sas per port object
- *
- * Returns nothing.
  */
 static void
 _transport_delete_port(struct MPT3SAS_ADAPTER *ioc,
@@ -489,8 +487,6 @@ _transport_delete_port(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @mpt3sas_port: mpt3sas per port object
  * @mpt3sas_phy: mpt3sas per phy object
- *
- * Returns nothing.
  */
 static void
 _transport_delete_phy(struct MPT3SAS_ADAPTER *ioc,
@@ -513,8 +509,6 @@ _transport_delete_phy(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @mpt3sas_port: mpt3sas per port object
  * @mpt3sas_phy: mpt3sas per phy object
- *
- * Returns nothing.
  */
 static void
 _transport_add_phy(struct MPT3SAS_ADAPTER *ioc, struct _sas_port *mpt3sas_port,
@@ -538,8 +532,6 @@ _transport_add_phy(struct MPT3SAS_ADAPTER *ioc, struct _sas_port *mpt3sas_port,
  * @sas_node: sas node object (either expander or sas host)
  * @mpt3sas_phy: mpt3sas per phy object
  * @sas_address: sas address of device/expander were phy needs to be added to
- *
- * Returns nothing.
  */
 static void
 _transport_add_phy_to_an_existing_port(struct MPT3SAS_ADAPTER *ioc,
@@ -563,7 +555,7 @@ _transport_add_phy_to_an_existing_port(struct MPT3SAS_ADAPTER *ioc,
 				return;
 		}
 		_transport_add_phy(ioc, mpt3sas_port, mpt3sas_phy);
-			return;
+		return;
 	}
 
 }
@@ -573,8 +565,6 @@ _transport_add_phy_to_an_existing_port(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @sas_node: sas node object (either expander or sas host)
  * @mpt3sas_phy: mpt3sas per phy object
- *
- * Returns nothing.
  */
 static void
 _transport_del_phy_from_an_existing_port(struct MPT3SAS_ADAPTER *ioc,
@@ -635,7 +625,7 @@ _transport_sanity_check(struct MPT3SAS_ADAPTER *ioc, struct _sas_node *sas_node,
  *
  * Adding new port object to the sas_node->sas_port_list.
  *
- * Returns mpt3sas_port.
+ * Return: mpt3sas_port.
  */
 struct _sas_port *
 mpt3sas_transport_port_add(struct MPT3SAS_ADAPTER *ioc, u16 handle,
@@ -794,8 +784,6 @@ mpt3sas_transport_port_add(struct MPT3SAS_ADAPTER *ioc, u16 handle,
  *
  * Removing object and freeing associated memory from the
  * ioc->sas_port_list.
- *
- * Return nothing.
  */
 void
 mpt3sas_transport_port_remove(struct MPT3SAS_ADAPTER *ioc, u64 sas_address,
@@ -860,7 +848,7 @@ mpt3sas_transport_port_remove(struct MPT3SAS_ADAPTER *ioc, u64 sas_address,
  * @phy_pg0: sas phy page 0
  * @parent_dev: parent device class object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_transport_add_host_phy(struct MPT3SAS_ADAPTER *ioc, struct _sas_phy
@@ -928,7 +916,7 @@ mpt3sas_transport_add_host_phy(struct MPT3SAS_ADAPTER *ioc, struct _sas_phy
  * @expander_pg1: expander page 1
  * @parent_dev: parent device class object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_transport_add_expander_phy(struct MPT3SAS_ADAPTER *ioc, struct _sas_phy
@@ -995,10 +983,8 @@ mpt3sas_transport_add_expander_phy(struct MPT3SAS_ADAPTER *ioc, struct _sas_phy
  * @ioc: per adapter object
  * @sas_address: sas address of parent expander or sas host
  * @handle: attached device handle
- * @phy_numberv: phy number
+ * @phy_number: phy number
  * @link_rate: new link rate
- *
- * Returns nothing.
  */
 void
 mpt3sas_transport_update_links(struct MPT3SAS_ADAPTER *ioc,
@@ -1090,7 +1076,7 @@ struct phy_error_log_reply {
  * @ioc: per adapter object
  * @phy: The sas phy object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  *
  */
 static int
@@ -1262,7 +1248,7 @@ _transport_get_expander_phy_error_log(struct MPT3SAS_ADAPTER *ioc,
  * _transport_get_linkerrors - return phy counters for both hba and expanders
  * @phy: The sas phy object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  *
  */
 static int
@@ -1311,10 +1297,11 @@ _transport_get_linkerrors(struct sas_phy *phy)
 
 /**
  * _transport_get_enclosure_identifier -
- * @phy: The sas phy object
+ * @rphy: The sas phy object
+ * @identifier: ?
  *
  * Obtain the enclosure logical id for an expander.
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _transport_get_enclosure_identifier(struct sas_rphy *rphy, u64 *identifier)
@@ -1342,9 +1329,9 @@ _transport_get_enclosure_identifier(struct sas_rphy *rphy, u64 *identifier)
 
 /**
  * _transport_get_bay_identifier -
- * @phy: The sas phy object
+ * @rphy: The sas phy object
  *
- * Returns the slot id for a device that resides inside an enclosure.
+ * Return: the slot id for a device that resides inside an enclosure.
  */
 static int
 _transport_get_bay_identifier(struct sas_rphy *rphy)
@@ -1400,8 +1387,9 @@ struct phy_control_reply {
  * _transport_expander_phy_control - expander phy control
  * @ioc: per adapter object
  * @phy: The sas phy object
+ * @phy_operation: ?
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  *
  */
 static int
@@ -1571,7 +1559,7 @@ _transport_expander_phy_control(struct MPT3SAS_ADAPTER *ioc,
  * @phy: The sas phy object
  * @hard_reset:
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _transport_phy_reset(struct sas_phy *phy, int hard_reset)
@@ -1623,7 +1611,7 @@ _transport_phy_reset(struct sas_phy *phy, int hard_reset)
  * @enable: enable phy when true
  *
  * Only support sas_host direct attached phys.
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _transport_phy_enable(struct sas_phy *phy, int enable)
@@ -1761,7 +1749,8 @@ _transport_phy_enable(struct sas_phy *phy, int enable)
  * @rates: rates defined in sas_phy_linkrates
  *
  * Only support sas_host direct attached phys.
- * Returns 0 for success, non-zero for failure.
+ *
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _transport_phy_speed(struct sas_phy *phy, struct sas_phy_linkrates *rates)
@@ -1904,9 +1893,9 @@ _transport_unmap_smp_buffer(struct device *dev, struct bsg_buffer *buf,
 
 /**
  * _transport_smp_handler - transport portal for smp passthru
+ * @job: ?
  * @shost: shost object
  * @rphy: sas transport rphy object
- * @req:
  *
  * This used primarily for smp_utils.
  * Example:
@@ -1936,12 +1925,12 @@ _transport_smp_handler(struct bsg_job *job, struct Scsi_Host *shost,
 		pr_info(MPT3SAS_FMT "%s: host reset in progress!\n",
 		    __func__, ioc->name);
 		rc = -EFAULT;
-		goto out;
+		goto job_done;
 	}
 
 	rc = mutex_lock_interruptible(&ioc->transport_cmds.mutex);
 	if (rc)
-		goto out;
+		goto job_done;
 
 	if (ioc->transport_cmds.status != MPT3_CMD_NOT_USED) {
 		pr_err(MPT3SAS_FMT "%s: transport_cmds in use\n", ioc->name,
@@ -2066,6 +2055,7 @@ _transport_smp_handler(struct bsg_job *job, struct Scsi_Host *shost,
  out:
 	ioc->transport_cmds.status = MPT3_CMD_NOT_USED;
 	mutex_unlock(&ioc->transport_cmds.mutex);
+job_done:
 	bsg_job_done(job, rc, reslen);
 }
 
diff --git a/drivers/scsi/mpt3sas/mpt3sas_trigger_diag.c b/drivers/scsi/mpt3sas/mpt3sas_trigger_diag.c
index b60fd7a3b571..cae7c1eaef34 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_trigger_diag.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_trigger_diag.c
@@ -62,7 +62,7 @@
 /**
  * _mpt3sas_raise_sigio - notifiy app
  * @ioc: per adapter object
- * @event_data:
+ * @event_data: ?
  */
 static void
 _mpt3sas_raise_sigio(struct MPT3SAS_ADAPTER *ioc,
@@ -107,7 +107,7 @@ _mpt3sas_raise_sigio(struct MPT3SAS_ADAPTER *ioc,
 /**
  * mpt3sas_process_trigger_data - process the event data for the trigger
  * @ioc: per adapter object
- * @event_data:
+ * @event_data: ?
  */
 void
 mpt3sas_process_trigger_data(struct MPT3SAS_ADAPTER *ioc,
@@ -209,8 +209,8 @@ mpt3sas_trigger_master(struct MPT3SAS_ADAPTER *ioc, u32 trigger_bitmask)
 /**
  * mpt3sas_trigger_event - Event trigger handler
  * @ioc: per adapter object
- * @event:
- * @log_entry_qualifier:
+ * @event: ?
+ * @log_entry_qualifier: ?
  *
  */
 void
@@ -288,9 +288,9 @@ mpt3sas_trigger_event(struct MPT3SAS_ADAPTER *ioc, u16 event,
 /**
  * mpt3sas_trigger_scsi - SCSI trigger handler
  * @ioc: per adapter object
- * @sense_key:
- * @asc:
- * @ascq:
+ * @sense_key: ?
+ * @asc: ?
+ * @ascq: ?
  *
  */
 void
@@ -364,8 +364,8 @@ mpt3sas_trigger_scsi(struct MPT3SAS_ADAPTER *ioc, u8 sense_key, u8 asc,
 /**
  * mpt3sas_trigger_mpi - MPI trigger handler
  * @ioc: per adapter object
- * @ioc_status:
- * @loginfo:
+ * @ioc_status: ?
+ * @loginfo: ?
  *
  */
 void
diff --git a/drivers/scsi/mpt3sas/mpt3sas_warpdrive.c b/drivers/scsi/mpt3sas/mpt3sas_warpdrive.c
index 45aa94915cbf..b4927f2b7677 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_warpdrive.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_warpdrive.c
@@ -267,9 +267,6 @@ out_error:
  * @scmd: pointer to scsi command object
  * @raid_device: pointer to raid device data structure
  * @mpi_request: pointer to the SCSI_IO reqest message frame
- * @smid: system request message index
- *
- * Returns nothing
  */
 void
 mpt3sas_setup_direct_io(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
diff --git a/drivers/scsi/ncr53c8xx.c b/drivers/scsi/ncr53c8xx.c
index dc4e801b2cef..6cd3e289ef99 100644
--- a/drivers/scsi/ncr53c8xx.c
+++ b/drivers/scsi/ncr53c8xx.c
@@ -4611,7 +4611,7 @@ static int ncr_reset_bus (struct ncb *np, struct scsi_cmnd *cmd, int sync_reset)
  * in order to keep it alive.
  */
 	if (!found && sync_reset && !retrieve_from_waiting_list(0, np, cmd)) {
-		cmd->result = ScsiResult(DID_RESET, 0);
+		cmd->result = DID_RESET << 16;
 		ncr_queue_done_cmd(np, cmd);
 	}
 
@@ -4957,7 +4957,7 @@ void ncr_complete (struct ncb *np, struct ccb *cp)
 		/*
 		**   Check condition code
 		*/
-		cmd->result = ScsiResult(DID_OK, S_CHECK_COND);
+		cmd->result = DID_OK << 16 | S_CHECK_COND;
 
 		/*
 		**	Copy back sense data to caller's buffer.
@@ -4978,7 +4978,7 @@ void ncr_complete (struct ncb *np, struct ccb *cp)
 		/*
 		**   Reservation Conflict condition code
 		*/
-		cmd->result = ScsiResult(DID_OK, S_CONFLICT);
+		cmd->result = DID_OK << 16 | S_CONFLICT;
 	
 	} else if ((cp->host_status == HS_COMPLETE)
 		&& (cp->scsi_status == S_BUSY ||
@@ -8043,7 +8043,7 @@ printk("ncr53c8xx_queue_command\n");
      spin_lock_irqsave(&np->smp_lock, flags);
 
      if ((sts = ncr_queue_command(np, cmd)) != DID_OK) {
-	  cmd->result = ScsiResult(sts, 0);
+	  cmd->result = sts << 16;
 #ifdef DEBUG_NCR53C8XX
 printk("ncr53c8xx : command not queued - result=%d\n", sts);
 #endif
@@ -8234,7 +8234,7 @@ static void process_waiting_list(struct ncb *np, int sts)
 #ifdef DEBUG_WAITING_LIST
 	printk("%s: cmd %lx done forced sts=%d\n", ncr_name(np), (u_long) wcmd, sts);
 #endif
-			wcmd->result = ScsiResult(sts, 0);
+			wcmd->result = sts << 16;
 			ncr_queue_done_cmd(np, wcmd);
 		}
 	}
diff --git a/drivers/scsi/nsp32_debug.c b/drivers/scsi/nsp32_debug.c
index 58806f432a16..4f1d4bf9c775 100644
--- a/drivers/scsi/nsp32_debug.c
+++ b/drivers/scsi/nsp32_debug.c
@@ -137,7 +137,7 @@ static void print_commandk (unsigned char *command)
 	printk("\n");
 }
 
-static void show_command(Scsi_Cmnd *SCpnt)
+static void show_command(struct scsi_cmnd *SCpnt)
 {
 	print_commandk(SCpnt->cmnd);
 }
diff --git a/drivers/scsi/qedi/qedi_fw_api.c b/drivers/scsi/qedi/qedi_fw_api.c
index a269da1a6c75..387dc87e4d22 100644
--- a/drivers/scsi/qedi/qedi_fw_api.c
+++ b/drivers/scsi/qedi/qedi_fw_api.c
@@ -126,22 +126,24 @@ static void init_sqe(struct iscsi_task_params *task_params,
 						     sgl_task_params,
 						     dif_task_params);
 
-		if (scsi_is_slow_sgl(sgl_task_params->num_sges,
-				     sgl_task_params->small_mid_sge))
-			num_sges = ISCSI_WQE_NUM_SGES_SLOWIO;
-		else
-			num_sges = min(sgl_task_params->num_sges,
-				       (u16)SCSI_NUM_SGES_SLOW_SGL_THR);
-	}
+			if (scsi_is_slow_sgl(sgl_task_params->num_sges,
+					     sgl_task_params->small_mid_sge))
+				num_sges = ISCSI_WQE_NUM_SGES_SLOWIO;
+			else
+				num_sges = min(sgl_task_params->num_sges,
+					       (u16)SCSI_NUM_SGES_SLOW_SGL_THR);
+		}
 
-	SET_FIELD(task_params->sqe->flags, ISCSI_WQE_NUM_SGES, num_sges);
-	SET_FIELD(task_params->sqe->contlen_cdbsize, ISCSI_WQE_CONT_LEN,
-		  buf_size);
+		SET_FIELD(task_params->sqe->flags, ISCSI_WQE_NUM_SGES,
+			  num_sges);
+		SET_FIELD(task_params->sqe->contlen_cdbsize, ISCSI_WQE_CONT_LEN,
+			  buf_size);
 
-	if (GET_FIELD(pdu_header->hdr_second_dword,
-		      ISCSI_CMD_HDR_TOTAL_AHS_LEN))
-		SET_FIELD(task_params->sqe->contlen_cdbsize, ISCSI_WQE_CDB_SIZE,
-			  cmd_params->extended_cdb_sge.sge_len);
+		if (GET_FIELD(pdu_header->hdr_second_dword,
+			      ISCSI_CMD_HDR_TOTAL_AHS_LEN))
+			SET_FIELD(task_params->sqe->contlen_cdbsize,
+				  ISCSI_WQE_CDB_SIZE,
+				  cmd_params->extended_cdb_sge.sge_len);
 	}
 		break;
 	case ISCSI_TASK_TYPE_INITIATOR_READ:
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index cff83b9457f7..aa96bccb5a96 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -524,7 +524,7 @@ static int qedi_init_id_tbl(struct qedi_portid_tbl *id_tbl, u16 size,
 	id_tbl->max = size;
 	id_tbl->next = next;
 	spin_lock_init(&id_tbl->lock);
-	id_tbl->table = kcalloc(DIV_ROUND_UP(size, 32), 4, GFP_KERNEL);
+	id_tbl->table = kcalloc(BITS_TO_LONGS(size), sizeof(long), GFP_KERNEL);
 	if (!id_tbl->table)
 		return -ENOMEM;
 
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index c8731568f9c4..4888b999e82f 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -518,6 +518,9 @@ qla2x00_sysfs_write_vpd(struct file *filp, struct kobject *kobj,
 	if (unlikely(pci_channel_offline(ha->pdev)))
 		return 0;
 
+	if (qla2x00_chip_is_down(vha))
+		return 0;
+
 	if (!capable(CAP_SYS_ADMIN) || off != 0 || count != ha->vpd_size ||
 	    !ha->isp_ops->write_nvram)
 		return 0;
@@ -570,7 +573,7 @@ qla2x00_sysfs_read_sfp(struct file *filp, struct kobject *kobj,
 	if (!capable(CAP_SYS_ADMIN) || off != 0 || count < SFP_DEV_SIZE)
 		return 0;
 
-	if (qla2x00_reset_active(vha))
+	if (qla2x00_chip_is_down(vha))
 		return 0;
 
 	rval = qla2x00_read_sfp_dev(vha, buf, count);
@@ -733,6 +736,15 @@ qla2x00_issue_logo(struct file *filp, struct kobject *kobj,
 	int type;
 	port_id_t did;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return 0;
+
+	if (unlikely(pci_channel_offline(vha->hw->pdev)))
+		return 0;
+
+	if (qla2x00_chip_is_down(vha))
+		return 0;
+
 	type = simple_strtol(buf, NULL, 10);
 
 	did.b.domain = (type & 0x00ff0000) >> 16;
@@ -771,6 +783,12 @@ qla2x00_sysfs_read_xgmac_stats(struct file *filp, struct kobject *kobj,
 	if (!capable(CAP_SYS_ADMIN) || off != 0 || count > XGMAC_DATA_SIZE)
 		return 0;
 
+	if (unlikely(pci_channel_offline(ha->pdev)))
+		return 0;
+
+	if (qla2x00_chip_is_down(vha))
+		return 0;
+
 	if (ha->xgmac_data)
 		goto do_read;
 
@@ -825,6 +843,9 @@ qla2x00_sysfs_read_dcbx_tlv(struct file *filp, struct kobject *kobj,
 	if (ha->dcbx_tlv)
 		goto do_read;
 
+	if (qla2x00_chip_is_down(vha))
+		return 0;
+
 	ha->dcbx_tlv = dma_alloc_coherent(&ha->pdev->dev, DCBX_TLV_DATA_SIZE,
 	    &ha->dcbx_tlv_dma, GFP_KERNEL);
 	if (!ha->dcbx_tlv) {
@@ -1036,7 +1057,7 @@ qla2x00_link_state_show(struct device *dev, struct device_attribute *attr,
 	    vha->device_flags & DFLG_NO_CABLE)
 		len = scnprintf(buf, PAGE_SIZE, "Link Down\n");
 	else if (atomic_read(&vha->loop_state) != LOOP_READY ||
-	    qla2x00_reset_active(vha))
+	    qla2x00_chip_is_down(vha))
 		len = scnprintf(buf, PAGE_SIZE, "Unknown Link State\n");
 	else {
 		len = scnprintf(buf, PAGE_SIZE, "Link Up - ");
@@ -1163,7 +1184,7 @@ qla2x00_beacon_store(struct device *dev, struct device_attribute *attr,
 	if (IS_QLA2100(ha) || IS_QLA2200(ha))
 		return -EPERM;
 
-	if (test_bit(ABORT_ISP_ACTIVE, &vha->dpc_flags)) {
+	if (qla2x00_chip_is_down(vha)) {
 		ql_log(ql_log_warn, vha, 0x707a,
 		    "Abort ISP active -- ignoring beacon request.\n");
 		return -EBUSY;
@@ -1350,7 +1371,7 @@ qla2x00_thermal_temp_show(struct device *dev,
 	scsi_qla_host_t *vha = shost_priv(class_to_shost(dev));
 	uint16_t temp = 0;
 
-	if (qla2x00_reset_active(vha)) {
+	if (qla2x00_chip_is_down(vha)) {
 		ql_log(ql_log_warn, vha, 0x70dc, "ISP reset active.\n");
 		goto done;
 	}
@@ -1381,7 +1402,7 @@ qla2x00_fw_state_show(struct device *dev, struct device_attribute *attr,
 		return scnprintf(buf, PAGE_SIZE, "0x%x\n", pstate);
 	}
 
-	if (qla2x00_reset_active(vha))
+	if (qla2x00_chip_is_down(vha))
 		ql_log(ql_log_warn, vha, 0x707c,
 		    "ISP reset active.\n");
 	else if (!vha->hw->flags.eeh_busy)
@@ -1840,7 +1861,7 @@ qla2x00_get_fc_host_stats(struct Scsi_Host *shost)
 	if (unlikely(pci_channel_offline(ha->pdev)))
 		goto done;
 
-	if (qla2x00_reset_active(vha))
+	if (qla2x00_chip_is_down(vha))
 		goto done;
 
 	stats = dma_zalloc_coherent(&ha->pdev->dev, sizeof(*stats),
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index 5fd44c50bbac..c7533fa7f46e 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -1130,6 +1130,7 @@ qla24xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 		    ha->fw_dump);
 		goto qla24xx_fw_dump_failed;
 	}
+	QLA_FW_STOPPED(ha);
 	fw = &ha->fw_dump->isp.isp24;
 	qla2xxx_prep_dump(ha, ha->fw_dump);
 
@@ -1384,6 +1385,7 @@ qla25xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 		    ha->fw_dump);
 		goto qla25xx_fw_dump_failed;
 	}
+	QLA_FW_STOPPED(ha);
 	fw = &ha->fw_dump->isp.isp25;
 	qla2xxx_prep_dump(ha, ha->fw_dump);
 	ha->fw_dump->version = htonl(2);
@@ -2036,6 +2038,7 @@ qla83xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 		    "request...\n", ha->fw_dump);
 		goto qla83xx_fw_dump_failed;
 	}
+	QLA_FW_STOPPED(ha);
 	fw = &ha->fw_dump->isp.isp83;
 	qla2xxx_prep_dump(ha, ha->fw_dump);
 
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 0f94b1d62d3f..a9dc9c4a6382 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -313,6 +313,7 @@ struct srb_cmd {
 #define SRB_CRC_CTX_DMA_VALID		BIT_2	/* DIF: context DMA valid */
 #define SRB_CRC_PROT_DMA_VALID		BIT_4	/* DIF: prot DMA valid */
 #define SRB_CRC_CTX_DSD_VALID		BIT_5	/* DIF: dsd_list valid */
+#define SRB_WAKEUP_ON_COMP		BIT_6
 
 /* To identify if a srb is of T10-CRC type. @sp => srb_t pointer */
 #define IS_PROT_IO(sp)	(sp->flags & SRB_CRC_CTX_DSD_VALID)
@@ -379,6 +380,7 @@ struct srb_iocb {
 #define SRB_LOGIN_COND_PLOGI	BIT_1
 #define SRB_LOGIN_SKIP_PRLI	BIT_2
 #define SRB_LOGIN_NVME_PRLI	BIT_3
+#define SRB_LOGIN_PRLI_ONLY	BIT_4
 			uint16_t data[2];
 			u32 iop[2];
 		} logio;
@@ -398,6 +400,8 @@ struct srb_iocb {
 			struct completion comp;
 			struct els_plogi_payload *els_plogi_pyld;
 			struct els_plogi_payload *els_resp_pyld;
+			u32 tx_size;
+			u32 rx_size;
 			dma_addr_t els_plogi_pyld_dma;
 			dma_addr_t els_resp_pyld_dma;
 			uint32_t	fw_status[3];
@@ -2312,6 +2316,7 @@ enum fcport_mgt_event {
 	FCME_ADISC_DONE,
 	FCME_GNNID_DONE,
 	FCME_GFPNID_DONE,
+	FCME_ELS_PLOGI_DONE,
 };
 
 enum rscn_addr_format {
@@ -2408,6 +2413,7 @@ typedef struct fc_port {
 	struct ct_sns_desc ct_desc;
 	enum discovery_state disc_state;
 	enum login_state fw_login_state;
+	unsigned long dm_login_expire;
 	unsigned long plogi_nack_done_deadline;
 
 	u32 login_gen, last_login_gen;
@@ -2418,7 +2424,8 @@ typedef struct fc_port {
 	u8 iocb[IOCB_SIZE];
 	u8 current_login_state;
 	u8 last_login_state;
-	struct completion n2n_done;
+	u16 n2n_link_reset_cnt;
+	u16 n2n_chip_reset;
 } fc_port_t;
 
 #define QLA_FCPORT_SCAN		1
@@ -3228,6 +3235,7 @@ enum qla_work_type {
 	QLA_EVT_GFPNID,
 	QLA_EVT_SP_RETRY,
 	QLA_EVT_IIDMA,
+	QLA_EVT_ELS_PLOGI,
 };
 
 
@@ -3599,6 +3607,8 @@ struct qla_hw_data {
 		uint32_t	detected_lr_sfp:1;
 		uint32_t	using_lr_setting:1;
 		uint32_t	rida_fmt2:1;
+		uint32_t	purge_mbox:1;
+		uint32_t        n2n_bigger:1;
 	} flags;
 
 	uint16_t max_exchg;
@@ -3844,6 +3854,10 @@ struct qla_hw_data {
 	int		port_down_retry_count;
 	uint8_t		mbx_count;
 	uint8_t		aen_mbx_count;
+	atomic_t	num_pend_mbx_stage1;
+	atomic_t	num_pend_mbx_stage2;
+	atomic_t	num_pend_mbx_stage3;
+	uint16_t	frame_payload_size;
 
 	uint32_t	login_retry_count;
 	/* SNS command interfaces. */
@@ -3903,6 +3917,9 @@ struct qla_hw_data {
 	int		exchoffld_size;
 	int 		exchoffld_count;
 
+	/* n2n */
+	struct els_plogi_payload plogi_els_payld;
+
 	void            *swl;
 
 	/* These are used by mailbox operations. */
@@ -4157,6 +4174,7 @@ struct qla_hw_data {
 	struct work_struct board_disable;
 
 	struct mr_data_fx00 mr;
+	uint32_t chip_reset;
 
 	struct qlt_hw_data tgt;
 	int	allow_cna_fw_dump;
@@ -4238,7 +4256,7 @@ typedef struct scsi_qla_host {
 #define FCOE_CTX_RESET_NEEDED	18	/* Initiate FCoE context reset */
 #define MPI_RESET_NEEDED	19	/* Initiate MPI FW reset */
 #define ISP_QUIESCE_NEEDED	20	/* Driver need some quiescence */
-#define FREE_BIT 21
+#define N2N_LINK_RESET		21
 #define PORT_UPDATE_NEEDED	22
 #define FX00_RESET_RECOVERY	23
 #define FX00_TARGET_SCAN	24
diff --git a/drivers/scsi/qla2xxx/qla_fw.h b/drivers/scsi/qla2xxx/qla_fw.h
index 5d8688e5bc7c..50c1e6c62e31 100644
--- a/drivers/scsi/qla2xxx/qla_fw.h
+++ b/drivers/scsi/qla2xxx/qla_fw.h
@@ -1366,6 +1366,11 @@ struct vp_rpt_id_entry_24xx {
 			/* format 1 fabric */
 			uint8_t vpstat1_subcode; /* vp_status=1 subcode */
 			uint8_t flags;
+#define TOPO_MASK  0xE
+#define TOPO_FL    0x2
+#define TOPO_N2N   0x4
+#define TOPO_F     0x6
+
 			uint16_t fip_flags;
 			uint8_t rsv2[12];
 
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index 2660a48d918a..178974896b5c 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -45,8 +45,7 @@ extern int qla2x00_fabric_login(scsi_qla_host_t *, fc_port_t *, uint16_t *);
 extern int qla2x00_local_device_login(scsi_qla_host_t *, fc_port_t *);
 
 extern int qla24xx_els_dcmd_iocb(scsi_qla_host_t *, int, port_id_t);
-extern int qla24xx_els_dcmd2_iocb(scsi_qla_host_t *, int, fc_port_t *,
-				  port_id_t);
+extern int qla24xx_els_dcmd2_iocb(scsi_qla_host_t *, int, fc_port_t *, bool);
 
 extern void qla2x00_update_fcports(scsi_qla_host_t *);
 
@@ -118,6 +117,7 @@ extern int qla2x00_post_async_prlo_done_work(struct scsi_qla_host *,
     fc_port_t *, uint16_t *);
 int qla_post_iidma_work(struct scsi_qla_host *vha, fc_port_t *fcport);
 void qla_do_iidma_work(struct scsi_qla_host *vha, fc_port_t *fcport);
+int qla2x00_reserve_mgmt_server_loop_id(scsi_qla_host_t *);
 /*
  * Global Data in qla_os.c source file.
  */
@@ -212,7 +212,7 @@ extern int qla24xx_post_upd_fcport_work(struct scsi_qla_host *, fc_port_t *);
 void qla2x00_handle_login_done_event(struct scsi_qla_host *, fc_port_t *,
 	uint16_t *);
 int qla24xx_post_gnl_work(struct scsi_qla_host *, fc_port_t *);
-int qla24xx_async_abort_cmd(srb_t *);
+int qla24xx_async_abort_cmd(srb_t *, bool);
 int qla24xx_post_relogin_work(struct scsi_qla_host *vha);
 void qla2x00_wait_for_sess_deletion(scsi_qla_host_t *);
 
diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
index 7a3744006419..a0038d879b9d 100644
--- a/drivers/scsi/qla2xxx/qla_gs.c
+++ b/drivers/scsi/qla2xxx/qla_gs.c
@@ -1962,7 +1962,6 @@ qla2x00_fdmiv2_rhba(scsi_qla_host_t *vha)
 	void *entries;
 	struct ct_fdmiv2_hba_attr *eiter;
 	struct qla_hw_data *ha = vha->hw;
-	struct init_cb_24xx *icb24 = (struct init_cb_24xx *)ha->init_cb;
 	struct new_utsname *p_sysid = NULL;
 
 	/* Issue RHBA */
@@ -2142,9 +2141,7 @@ qla2x00_fdmiv2_rhba(scsi_qla_host_t *vha)
 	/* MAX CT Payload Length */
 	eiter = entries + size;
 	eiter->type = cpu_to_be16(FDMI_HBA_MAXIMUM_CT_PAYLOAD_LENGTH);
-	eiter->a.max_ct_len = IS_FWI2_CAPABLE(ha) ?
-	    le16_to_cpu(icb24->frame_payload_size) :
-	    le16_to_cpu(ha->init_cb->frame_payload_size);
+	eiter->a.max_ct_len = cpu_to_be32(ha->frame_payload_size);
 	eiter->a.max_ct_len = cpu_to_be32(eiter->a.max_ct_len);
 	eiter->len = cpu_to_be16(4 + 4);
 	size += 4 + 4;
@@ -3394,19 +3391,40 @@ int qla24xx_post_gpnid_work(struct scsi_qla_host *vha, port_id_t *id)
 
 void qla24xx_sp_unmap(scsi_qla_host_t *vha, srb_t *sp)
 {
-	if (sp->u.iocb_cmd.u.ctarg.req) {
-		dma_free_coherent(&vha->hw->pdev->dev,
-			sp->u.iocb_cmd.u.ctarg.req_allocated_size,
-			sp->u.iocb_cmd.u.ctarg.req,
-			sp->u.iocb_cmd.u.ctarg.req_dma);
-		sp->u.iocb_cmd.u.ctarg.req = NULL;
-	}
-	if (sp->u.iocb_cmd.u.ctarg.rsp) {
-		dma_free_coherent(&vha->hw->pdev->dev,
-			sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
-			sp->u.iocb_cmd.u.ctarg.rsp,
-			sp->u.iocb_cmd.u.ctarg.rsp_dma);
-		sp->u.iocb_cmd.u.ctarg.rsp = NULL;
+	struct srb_iocb *c = &sp->u.iocb_cmd;
+
+	switch (sp->type) {
+	case SRB_ELS_DCMD:
+		if (c->u.els_plogi.els_plogi_pyld)
+			dma_free_coherent(&vha->hw->pdev->dev,
+			    c->u.els_plogi.tx_size,
+			    c->u.els_plogi.els_plogi_pyld,
+			    c->u.els_plogi.els_plogi_pyld_dma);
+
+		if (c->u.els_plogi.els_resp_pyld)
+			dma_free_coherent(&vha->hw->pdev->dev,
+			    c->u.els_plogi.rx_size,
+			    c->u.els_plogi.els_resp_pyld,
+			    c->u.els_plogi.els_resp_pyld_dma);
+		break;
+	case SRB_CT_PTHRU_CMD:
+	default:
+		if (sp->u.iocb_cmd.u.ctarg.req) {
+			dma_free_coherent(&vha->hw->pdev->dev,
+			    sp->u.iocb_cmd.u.ctarg.req_allocated_size,
+			    sp->u.iocb_cmd.u.ctarg.req,
+			    sp->u.iocb_cmd.u.ctarg.req_dma);
+			sp->u.iocb_cmd.u.ctarg.req = NULL;
+		}
+
+		if (sp->u.iocb_cmd.u.ctarg.rsp) {
+			dma_free_coherent(&vha->hw->pdev->dev,
+			    sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
+			    sp->u.iocb_cmd.u.ctarg.rsp,
+			    sp->u.iocb_cmd.u.ctarg.rsp_dma);
+			sp->u.iocb_cmd.u.ctarg.rsp = NULL;
+		}
+		break;
 	}
 
 	sp->free(sp);
@@ -3483,6 +3501,14 @@ void qla24xx_handle_gpnid_event(scsi_qla_host_t *vha, struct event_arg *ea)
 			fcport->rscn_gen++;
 			fcport->scan_state = QLA_FCPORT_FOUND;
 			fcport->flags |= FCF_FABRIC_DEVICE;
+			if (fcport->login_retry == 0) {
+				fcport->login_retry =
+					vha->hw->login_retry_count;
+				ql_dbg(ql_dbg_disc, vha, 0xffff,
+				    "Port login retry %8phN, lid 0x%04x cnt=%d.\n",
+				    fcport->port_name, fcport->loop_id,
+				    fcport->login_retry);
+			}
 			switch (fcport->disc_state) {
 			case DSC_LOGIN_COMPLETE:
 				/* recheck session is still intact. */
@@ -3981,6 +4007,14 @@ void qla24xx_async_gnnft_done(scsi_qla_host_t *vha, srb_t *sp)
 		} else {
 			if (fcport->rscn_rcvd ||
 			    fcport->disc_state != DSC_LOGIN_COMPLETE) {
+				if (fcport->login_retry == 0) {
+					fcport->login_retry =
+						vha->hw->login_retry_count;
+					ql_dbg(ql_dbg_disc, vha, 0x20a3,
+					    "Port login retry %8phN, lid 0x%04x retry cnt=%d.\n",
+					    fcport->port_name, fcport->loop_id,
+					    fcport->login_retry);
+				}
 				fcport->rscn_rcvd = 0;
 				qla24xx_fcport_handle_login(vha, fcport);
 			}
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 1b19b954bbae..b934977c5c26 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -50,16 +50,15 @@ qla2x00_sp_timeout(struct timer_list *t)
 {
 	srb_t *sp = from_timer(sp, t, u.iocb_cmd.timer);
 	struct srb_iocb *iocb;
-	scsi_qla_host_t *vha = sp->vha;
 	struct req_que *req;
 	unsigned long flags;
 
-	spin_lock_irqsave(&vha->hw->hardware_lock, flags);
-	req = vha->hw->req_q_map[0];
+	spin_lock_irqsave(sp->qpair->qp_lock_ptr, flags);
+	req = sp->qpair->req;
 	req->outstanding_cmds[sp->handle] = NULL;
 	iocb = &sp->u.iocb_cmd;
+	spin_unlock_irqrestore(sp->qpair->qp_lock_ptr, flags);
 	iocb->timeout(sp);
-	spin_unlock_irqrestore(&vha->hw->hardware_lock, flags);
 }
 
 void
@@ -100,6 +99,8 @@ qla2x00_async_iocb_timeout(void *data)
 	srb_t *sp = data;
 	fc_port_t *fcport = sp->fcport;
 	struct srb_iocb *lio = &sp->u.iocb_cmd;
+	int rc, h;
+	unsigned long flags;
 
 	if (fcport) {
 		ql_dbg(ql_dbg_disc, fcport->vha, 0x2071,
@@ -114,11 +115,26 @@ qla2x00_async_iocb_timeout(void *data)
 
 	switch (sp->type) {
 	case SRB_LOGIN_CMD:
-		/* Retry as needed. */
-		lio->u.logio.data[0] = MBS_COMMAND_ERROR;
-		lio->u.logio.data[1] = lio->u.logio.flags & SRB_LOGIN_RETRIED ?
-			QLA_LOGIO_LOGIN_RETRIED : 0;
-		sp->done(sp, QLA_FUNCTION_TIMEOUT);
+		rc = qla24xx_async_abort_cmd(sp, false);
+		if (rc) {
+			/* Retry as needed. */
+			lio->u.logio.data[0] = MBS_COMMAND_ERROR;
+			lio->u.logio.data[1] =
+				lio->u.logio.flags & SRB_LOGIN_RETRIED ?
+				QLA_LOGIO_LOGIN_RETRIED : 0;
+			spin_lock_irqsave(sp->qpair->qp_lock_ptr, flags);
+			for (h = 1; h < sp->qpair->req->num_outstanding_cmds;
+			    h++) {
+				if (sp->qpair->req->outstanding_cmds[h] ==
+				    sp) {
+					sp->qpair->req->outstanding_cmds[h] =
+					    NULL;
+					break;
+				}
+			}
+			spin_unlock_irqrestore(sp->qpair->qp_lock_ptr, flags);
+			sp->done(sp, QLA_FUNCTION_TIMEOUT);
+		}
 		break;
 	case SRB_LOGOUT_CMD:
 	case SRB_CT_PTHRU_CMD:
@@ -127,7 +143,21 @@ qla2x00_async_iocb_timeout(void *data)
 	case SRB_NACK_PRLI:
 	case SRB_NACK_LOGO:
 	case SRB_CTRL_VP:
-		sp->done(sp, QLA_FUNCTION_TIMEOUT);
+		rc = qla24xx_async_abort_cmd(sp, false);
+		if (rc) {
+			spin_lock_irqsave(sp->qpair->qp_lock_ptr, flags);
+			for (h = 1; h < sp->qpair->req->num_outstanding_cmds;
+			    h++) {
+				if (sp->qpair->req->outstanding_cmds[h] ==
+				    sp) {
+					sp->qpair->req->outstanding_cmds[h] =
+					    NULL;
+					break;
+				}
+			}
+			spin_unlock_irqrestore(sp->qpair->qp_lock_ptr, flags);
+			sp->done(sp, QLA_FUNCTION_TIMEOUT);
+		}
 		break;
 	}
 }
@@ -160,6 +190,22 @@ qla2x00_async_login_sp_done(void *ptr, int res)
 	sp->free(sp);
 }
 
+static inline bool
+fcport_is_smaller(fc_port_t *fcport)
+{
+	if (wwn_to_u64(fcport->port_name) <
+	    wwn_to_u64(fcport->vha->port_name))
+		return true;
+	else
+		return false;
+}
+
+static inline bool
+fcport_is_bigger(fc_port_t *fcport)
+{
+	return !fcport_is_smaller(fcport);
+}
+
 int
 qla2x00_async_login(struct scsi_qla_host *vha, fc_port_t *fcport,
     uint16_t *data)
@@ -189,13 +235,16 @@ qla2x00_async_login(struct scsi_qla_host *vha, fc_port_t *fcport,
 	qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha) + 2);
 
 	sp->done = qla2x00_async_login_sp_done;
-	lio->u.logio.flags |= SRB_LOGIN_COND_PLOGI;
+	if (N2N_TOPO(fcport->vha->hw) && fcport_is_bigger(fcport)) {
+		lio->u.logio.flags |= SRB_LOGIN_PRLI_ONLY;
+	} else {
+		lio->u.logio.flags |= SRB_LOGIN_COND_PLOGI;
 
-	if (fcport->fc4f_nvme)
-		lio->u.logio.flags |= SRB_LOGIN_SKIP_PRLI;
+		if (fcport->fc4f_nvme)
+			lio->u.logio.flags |= SRB_LOGIN_SKIP_PRLI;
+
+	}
 
-	if (data[1] & QLA_LOGIO_LOGIN_RETRIED)
-		lio->u.logio.flags |= SRB_LOGIN_RETRIED;
 	rval = qla2x00_start_sp(sp);
 	if (rval != QLA_SUCCESS) {
 		fcport->flags |= FCF_LOGIN_NEEDED;
@@ -370,6 +419,19 @@ void qla24xx_handle_adisc_event(scsi_qla_host_t *vha, struct event_arg *ea)
 	__qla24xx_handle_gpdb_event(vha, ea);
 }
 
+int qla_post_els_plogi_work(struct scsi_qla_host *vha, fc_port_t *fcport)
+{
+	struct qla_work_evt *e;
+
+	e = qla2x00_alloc_work(vha, QLA_EVT_ELS_PLOGI);
+	if (!e)
+		return QLA_FUNCTION_FAILED;
+
+	e->u.fcport.fcport = fcport;
+	fcport->flags |= FCF_ASYNC_ACTIVE;
+	return qla2x00_post_work(vha, e);
+}
+
 static void
 qla2x00_async_adisc_sp_done(void *ptr, int res)
 {
@@ -382,7 +444,7 @@ qla2x00_async_adisc_sp_done(void *ptr, int res)
 	    "Async done-%s res %x %8phC\n",
 	    sp->name, res, sp->fcport->port_name);
 
-	sp->fcport->flags &= ~FCF_ASYNC_SENT;
+	sp->fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE);
 
 	memset(&ea, 0, sizeof(ea));
 	ea.event = FCME_ADISC_DONE;
@@ -418,6 +480,8 @@ qla2x00_async_adisc(struct scsi_qla_host *vha, fc_port_t *fcport,
 
 	lio = &sp->u.iocb_cmd;
 	lio->timeout = qla2x00_async_iocb_timeout;
+	sp->gen1 = fcport->rscn_gen;
+	sp->gen2 = fcport->login_gen;
 	qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha) + 2);
 
 	sp->done = qla2x00_async_adisc_sp_done;
@@ -464,7 +528,6 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 
 	if (ea->rc) { /* rval */
 		if (fcport->login_retry == 0) {
-			fcport->login_retry = vha->hw->login_retry_count;
 			ql_dbg(ql_dbg_disc, vha, 0x20de,
 			    "GNL failed Port login retry %8phN, retry cnt=%d.\n",
 			    fcport->port_name, fcport->login_retry);
@@ -497,35 +560,51 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 	for (i = 0; i < n; i++) {
 		e = &vha->gnl.l[i];
 		wwn = wwn_to_u64(e->port_name);
+		id.b.domain = e->port_id[2];
+		id.b.area = e->port_id[1];
+		id.b.al_pa = e->port_id[0];
+		id.b.rsvd_1 = 0;
 
 		if (memcmp((u8 *)&wwn, fcport->port_name, WWN_SIZE))
 			continue;
 
+		if (IS_SW_RESV_ADDR(id))
+			continue;
+
 		found = 1;
-		id.b.domain = e->port_id[2];
-		id.b.area = e->port_id[1];
-		id.b.al_pa = e->port_id[0];
-		id.b.rsvd_1 = 0;
 
 		loop_id = le16_to_cpu(e->nport_handle);
 		loop_id = (loop_id & 0x7fff);
+		if  (fcport->fc4f_nvme)
+			current_login_state = e->current_login_state >> 4;
+		else
+			current_login_state = e->current_login_state & 0xf;
+
 
 		ql_dbg(ql_dbg_disc, vha, 0x20e2,
-		    "%s found %8phC CLS [%d|%d] ID[%02x%02x%02x|%02x%02x%02x] lid[%d|%d]\n",
+		    "%s found %8phC CLS [%x|%x] nvme %d ID[%02x%02x%02x|%02x%02x%02x] lid[%d|%d]\n",
 		    __func__, fcport->port_name,
 		    e->current_login_state, fcport->fw_login_state,
-		    id.b.domain, id.b.area, id.b.al_pa,
+		    fcport->fc4f_nvme, id.b.domain, id.b.area, id.b.al_pa,
 		    fcport->d_id.b.domain, fcport->d_id.b.area,
 		    fcport->d_id.b.al_pa, loop_id, fcport->loop_id);
 
-		if ((id.b24 != fcport->d_id.b24) ||
-		    ((fcport->loop_id != FC_NO_LOOP_ID) &&
-			(fcport->loop_id != loop_id))) {
-			ql_dbg(ql_dbg_disc, vha, 0x20e3,
-			    "%s %d %8phC post del sess\n",
-			    __func__, __LINE__, fcport->port_name);
-			qlt_schedule_sess_for_deletion(fcport);
-			return;
+		switch (fcport->disc_state) {
+		case DSC_DELETE_PEND:
+		case DSC_DELETED:
+			break;
+		default:
+			if ((id.b24 != fcport->d_id.b24 &&
+			    fcport->d_id.b24) ||
+			    (fcport->loop_id != FC_NO_LOOP_ID &&
+				fcport->loop_id != loop_id)) {
+				ql_dbg(ql_dbg_disc, vha, 0x20e3,
+				    "%s %d %8phC post del sess\n",
+				    __func__, __LINE__, fcport->port_name);
+				qlt_schedule_sess_for_deletion(fcport);
+				return;
+			}
+			break;
 		}
 
 		fcport->loop_id = loop_id;
@@ -544,68 +623,148 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 			fcport->login_pause = 1;
 		}
 
-		if  (fcport->fc4f_nvme)
-			current_login_state = e->current_login_state >> 4;
-		else
-			current_login_state = e->current_login_state & 0xf;
-
-		switch (current_login_state) {
-		case DSC_LS_PRLI_COMP:
-			ql_dbg(ql_dbg_disc, vha, 0x20e4,
-			    "%s %d %8phC post gpdb\n",
-			    __func__, __LINE__, fcport->port_name);
+		switch (vha->hw->current_topology) {
+		default:
+			switch (current_login_state) {
+			case DSC_LS_PRLI_COMP:
+				ql_dbg(ql_dbg_disc + ql_dbg_verbose,
+				    vha, 0x20e4, "%s %d %8phC post gpdb\n",
+				    __func__, __LINE__, fcport->port_name);
 
-			if ((e->prli_svc_param_word_3[0] & BIT_4) == 0)
-				fcport->port_type = FCT_INITIATOR;
-			else
-				fcport->port_type = FCT_TARGET;
+				if ((e->prli_svc_param_word_3[0] & BIT_4) == 0)
+					fcport->port_type = FCT_INITIATOR;
+				else
+					fcport->port_type = FCT_TARGET;
+				data[0] = data[1] = 0;
+				qla2x00_post_async_adisc_work(vha, fcport,
+				    data);
+				break;
+			case DSC_LS_PORT_UNAVAIL:
+			default:
+				if (fcport->loop_id != FC_NO_LOOP_ID)
+					qla2x00_clear_loop_id(fcport);
 
-			data[0] = data[1] = 0;
-			qla2x00_post_async_adisc_work(vha, fcport, data);
-			break;
-		case DSC_LS_PORT_UNAVAIL:
-		default:
-			if (fcport->loop_id == FC_NO_LOOP_ID) {
-				qla2x00_find_new_loop_id(vha, fcport);
+				fcport->loop_id = loop_id;
 				fcport->fw_login_state = DSC_LS_PORT_UNAVAIL;
+				qla24xx_fcport_handle_login(vha, fcport);
+				break;
 			}
-			ql_dbg(ql_dbg_disc, vha, 0x20e5,
-			    "%s %d %8phC\n",
-			    __func__, __LINE__, fcport->port_name);
-			qla24xx_fcport_handle_login(vha, fcport);
 			break;
-		}
+		case ISP_CFG_N:
+			fcport->fw_login_state = current_login_state;
+			fcport->d_id = id;
+			switch (current_login_state) {
+			case DSC_LS_PRLI_COMP:
+				if ((e->prli_svc_param_word_3[0] & BIT_4) == 0)
+					fcport->port_type = FCT_INITIATOR;
+				else
+					fcport->port_type = FCT_TARGET;
+
+				data[0] = data[1] = 0;
+				qla2x00_post_async_adisc_work(vha, fcport,
+				    data);
+				break;
+			case DSC_LS_PLOGI_COMP:
+				if (fcport_is_bigger(fcport)) {
+					/* local adapter is smaller */
+					if (fcport->loop_id != FC_NO_LOOP_ID)
+						qla2x00_clear_loop_id(fcport);
+
+					fcport->loop_id = loop_id;
+					qla24xx_fcport_handle_login(vha,
+					    fcport);
+					break;
+				}
+				/* drop through */
+			default:
+				if (fcport_is_smaller(fcport)) {
+					/* local adapter is bigger */
+					if (fcport->loop_id != FC_NO_LOOP_ID)
+						qla2x00_clear_loop_id(fcport);
+
+					fcport->loop_id = loop_id;
+					qla24xx_fcport_handle_login(vha,
+					    fcport);
+				}
+				break;
+			}
+			break;
+		} /* switch (ha->current_topology) */
 	}
 
 	if (!found) {
-		/* fw has no record of this port */
-		for (i = 0; i < n; i++) {
-			e = &vha->gnl.l[i];
-			id.b.domain = e->port_id[0];
-			id.b.area = e->port_id[1];
-			id.b.al_pa = e->port_id[2];
-			id.b.rsvd_1 = 0;
-			loop_id = le16_to_cpu(e->nport_handle);
-
-			if (fcport->d_id.b24 == id.b24) {
-				conflict_fcport =
-					qla2x00_find_fcport_by_wwpn(vha,
-					    e->port_name, 0);
-				if (conflict_fcport) {
-					qlt_schedule_sess_for_deletion
-						(conflict_fcport);
-					ql_dbg(ql_dbg_disc, vha, 0x20e6,
-					    "%s %d %8phC post del sess\n",
-					    __func__, __LINE__,
-					    conflict_fcport->port_name);
+		switch (vha->hw->current_topology) {
+		case ISP_CFG_F:
+		case ISP_CFG_FL:
+			for (i = 0; i < n; i++) {
+				e = &vha->gnl.l[i];
+				id.b.domain = e->port_id[0];
+				id.b.area = e->port_id[1];
+				id.b.al_pa = e->port_id[2];
+				id.b.rsvd_1 = 0;
+				loop_id = le16_to_cpu(e->nport_handle);
+
+				if (fcport->d_id.b24 == id.b24) {
+					conflict_fcport =
+					    qla2x00_find_fcport_by_wwpn(vha,
+						e->port_name, 0);
+					if (conflict_fcport) {
+						ql_dbg(ql_dbg_disc + ql_dbg_verbose,
+						    vha, 0x20e5,
+						    "%s %d %8phC post del sess\n",
+						    __func__, __LINE__,
+						    conflict_fcport->port_name);
+						qlt_schedule_sess_for_deletion
+							(conflict_fcport);
+					}
 				}
+				/*
+				 * FW already picked this loop id for
+				 * another fcport
+				 */
+				if (fcport->loop_id == loop_id)
+					fcport->loop_id = FC_NO_LOOP_ID;
 			}
-
-			/* FW already picked this loop id for another fcport */
-			if (fcport->loop_id == loop_id)
-				fcport->loop_id = FC_NO_LOOP_ID;
+			qla24xx_fcport_handle_login(vha, fcport);
+			break;
+		case ISP_CFG_N:
+			fcport->disc_state = DSC_DELETED;
+			if (time_after_eq(jiffies, fcport->dm_login_expire)) {
+				if (fcport->n2n_link_reset_cnt < 2) {
+					fcport->n2n_link_reset_cnt++;
+					/*
+					 * remote port is not sending PLOGI.
+					 * Reset link to kick start his state
+					 * machine
+					 */
+					set_bit(N2N_LINK_RESET,
+					    &vha->dpc_flags);
+				} else {
+					if (fcport->n2n_chip_reset < 1) {
+						ql_log(ql_log_info, vha, 0x705d,
+						    "Chip reset to bring laser down");
+						set_bit(ISP_ABORT_NEEDED,
+						    &vha->dpc_flags);
+						fcport->n2n_chip_reset++;
+					} else {
+						ql_log(ql_log_info, vha, 0x705d,
+						    "Remote port %8ph is not coming back\n",
+						    fcport->port_name);
+						fcport->scan_state = 0;
+					}
+				}
+				qla2xxx_wake_dpc(vha);
+			} else {
+				/*
+				 * report port suppose to do PLOGI. Give him
+				 * more time. FW will catch it.
+				 */
+				set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+			}
+			break;
+		default:
+			break;
 		}
-		qla24xx_fcport_handle_login(vha, fcport);
 	}
 } /* gnl_event */
 
@@ -911,9 +1070,9 @@ qla24xx_async_prli(struct scsi_qla_host *vha, fc_port_t *fcport)
 	}
 
 	ql_dbg(ql_dbg_disc, vha, 0x211b,
-	    "Async-prli - %8phC hdl=%x, loopid=%x portid=%06x retries=%d.\n",
-	    fcport->port_name, sp->handle, fcport->loop_id,
-	    fcport->d_id.b24, fcport->login_retry);
+	    "Async-prli - %8phC hdl=%x, loopid=%x portid=%06x retries=%d %s.\n",
+	    fcport->port_name, sp->handle, fcport->loop_id, fcport->d_id.b24,
+	    fcport->login_retry, fcport->fc4f_nvme ? "nvme" : "fc");
 
 	return rval;
 
@@ -1055,8 +1214,9 @@ void qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea)
 	fcport->flags &= ~FCF_ASYNC_SENT;
 
 	ql_dbg(ql_dbg_disc, vha, 0x20d2,
-	    "%s %8phC DS %d LS %d rc %d\n", __func__, fcport->port_name,
-	    fcport->disc_state, pd->current_login_state, ea->rc);
+	    "%s %8phC DS %d LS %d nvme %x rc %d\n", __func__, fcport->port_name,
+	    fcport->disc_state, pd->current_login_state, fcport->fc4f_nvme,
+	    ea->rc);
 
 	if (fcport->disc_state == DSC_DELETE_PEND)
 		return;
@@ -1074,9 +1234,12 @@ void qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea)
 	case PDS_PLOGI_COMPLETE:
 	case PDS_PRLI_PENDING:
 	case PDS_PRLI2_PENDING:
-		ql_dbg(ql_dbg_disc, vha, 0x20d5, "%s %d %8phC relogin needed\n",
-		    __func__, __LINE__, fcport->port_name);
-		set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+		/* Set discovery state back to GNL to Relogin attempt */
+		if (qla_dual_mode_enabled(vha) ||
+		    qla_ini_mode_enabled(vha)) {
+			fcport->disc_state = DSC_GNL;
+			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+		}
 		return;
 	case PDS_LOGO_PENDING:
 	case PDS_PORT_UNAVAILABLE:
@@ -1174,39 +1337,80 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport)
 		return 0;
 	}
 
-	if (fcport->login_retry > 0)
-		fcport->login_retry--;
-
 	switch (fcport->disc_state) {
 	case DSC_DELETED:
 		wwn = wwn_to_u64(fcport->node_name);
-		if (wwn == 0) {
-			ql_dbg(ql_dbg_disc, vha, 0xffff,
-			    "%s %d %8phC post GNNID\n",
-			    __func__, __LINE__, fcport->port_name);
-			qla24xx_post_gnnid_work(vha, fcport);
-		} else if (fcport->loop_id == FC_NO_LOOP_ID) {
-			ql_dbg(ql_dbg_disc, vha, 0x20bd,
-			    "%s %d %8phC post gnl\n",
-			    __func__, __LINE__, fcport->port_name);
-			qla24xx_post_gnl_work(vha, fcport);
-		} else {
-			qla_chk_n2n_b4_login(vha, fcport);
+		switch (vha->hw->current_topology) {
+		case ISP_CFG_N:
+			if (fcport_is_smaller(fcport)) {
+				/* this adapter is bigger */
+				if (fcport->login_retry) {
+					if (fcport->loop_id == FC_NO_LOOP_ID) {
+						qla2x00_find_new_loop_id(vha,
+						    fcport);
+						fcport->fw_login_state =
+						    DSC_LS_PORT_UNAVAIL;
+					}
+					fcport->login_retry--;
+					qla_post_els_plogi_work(vha, fcport);
+				} else {
+					ql_log(ql_log_info, vha, 0x705d,
+					    "Unable to reach remote port %8phC",
+					    fcport->port_name);
+				}
+			} else {
+				qla24xx_post_gnl_work(vha, fcport);
+			}
+			break;
+		default:
+			if (wwn == 0)    {
+				ql_dbg(ql_dbg_disc, vha, 0xffff,
+				    "%s %d %8phC post GNNID\n",
+				    __func__, __LINE__, fcport->port_name);
+				qla24xx_post_gnnid_work(vha, fcport);
+			} else if (fcport->loop_id == FC_NO_LOOP_ID) {
+				ql_dbg(ql_dbg_disc, vha, 0x20bd,
+				    "%s %d %8phC post gnl\n",
+				    __func__, __LINE__, fcport->port_name);
+				qla24xx_post_gnl_work(vha, fcport);
+			} else {
+				qla_chk_n2n_b4_login(vha, fcport);
+			}
+			break;
 		}
 		break;
 
 	case DSC_GNL:
-		if (fcport->login_pause) {
-			fcport->last_rscn_gen = fcport->rscn_gen;
-			fcport->last_login_gen = fcport->login_gen;
-			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+		switch (vha->hw->current_topology) {
+		case ISP_CFG_N:
+			if ((fcport->current_login_state & 0xf) == 0x6) {
+				ql_dbg(ql_dbg_disc, vha, 0x2118,
+				    "%s %d %8phC post GPDB work\n",
+				    __func__, __LINE__, fcport->port_name);
+				fcport->chip_reset =
+					vha->hw->base_qpair->chip_reset;
+				qla24xx_post_gpdb_work(vha, fcport, 0);
+			}  else {
+				ql_dbg(ql_dbg_disc, vha, 0x2118,
+				    "%s %d %8phC post NVMe PRLI\n",
+				    __func__, __LINE__, fcport->port_name);
+				qla24xx_post_prli_work(vha, fcport);
+			}
+			break;
+		default:
+			if (fcport->login_pause) {
+				fcport->last_rscn_gen = fcport->rscn_gen;
+				fcport->last_login_gen = fcport->login_gen;
+				set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+				break;
+			}
+			qla_chk_n2n_b4_login(vha, fcport);
 			break;
 		}
-
-		qla_chk_n2n_b4_login(vha, fcport);
 		break;
 
 	case DSC_LOGIN_FAILED:
+		fcport->login_retry--;
 		ql_dbg(ql_dbg_disc, vha, 0x20d0,
 		    "%s %d %8phC post gidpn\n",
 		    __func__, __LINE__, fcport->port_name);
@@ -1221,6 +1425,7 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport)
 		ql_dbg(ql_dbg_disc, vha, 0x20d1,
 		    "%s %d %8phC post adisc\n",
 		    __func__, __LINE__, fcport->port_name);
+		fcport->login_retry--;
 		data[0] = data[1] = 0;
 		qla2x00_post_async_adisc_work(vha, fcport, data);
 		break;
@@ -1304,17 +1509,6 @@ void qla24xx_handle_relogin_event(scsi_qla_host_t *vha,
 		}
 	}
 
-	if (fcport->flags & FCF_ASYNC_SENT) {
-		fcport->login_retry++;
-		set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
-		return;
-	}
-
-	if (fcport->disc_state == DSC_DELETE_PEND) {
-		fcport->login_retry++;
-		return;
-	}
-
 	if (fcport->last_rscn_gen != fcport->rscn_gen) {
 		ql_dbg(ql_dbg_disc, vha, 0x20e9, "%s %d %8phC post gidpn\n",
 		    __func__, __LINE__, fcport->port_name);
@@ -1326,6 +1520,15 @@ void qla24xx_handle_relogin_event(scsi_qla_host_t *vha,
 	qla24xx_fcport_handle_login(vha, fcport);
 }
 
+
+void qla_handle_els_plogi_done(scsi_qla_host_t *vha, struct event_arg *ea)
+{
+	ql_dbg(ql_dbg_disc, vha, 0x2118,
+	    "%s %d %8phC post PRLI\n",
+	    __func__, __LINE__, ea->fcport->port_name);
+	qla24xx_post_prli_work(vha, ea->fcport);
+}
+
 void qla2x00_fcport_event_handler(scsi_qla_host_t *vha, struct event_arg *ea)
 {
 	fc_port_t *f, *tf;
@@ -1427,6 +1630,9 @@ void qla2x00_fcport_event_handler(scsi_qla_host_t *vha, struct event_arg *ea)
 	case FCME_GFPNID_DONE:
 		qla24xx_handle_gfpnid_event(vha, ea);
 		break;
+	case FCME_ELS_PLOGI_DONE:
+		qla_handle_els_plogi_done(vha, ea);
+		break;
 	default:
 		BUG_ON(1);
 		break;
@@ -1520,7 +1726,7 @@ qla24xx_abort_iocb_timeout(void *data)
 	struct srb_iocb *abt = &sp->u.iocb_cmd;
 
 	abt->u.abt.comp_status = CS_TIMEOUT;
-	complete(&abt->u.abt.comp);
+	sp->done(sp, QLA_FUNCTION_TIMEOUT);
 }
 
 static void
@@ -1529,12 +1735,16 @@ qla24xx_abort_sp_done(void *ptr, int res)
 	srb_t *sp = ptr;
 	struct srb_iocb *abt = &sp->u.iocb_cmd;
 
-	if (del_timer(&sp->u.iocb_cmd.timer))
-		complete(&abt->u.abt.comp);
+	if (del_timer(&sp->u.iocb_cmd.timer)) {
+		if (sp->flags & SRB_WAKEUP_ON_COMP)
+			complete(&abt->u.abt.comp);
+		else
+			sp->free(sp);
+	}
 }
 
 int
-qla24xx_async_abort_cmd(srb_t *cmd_sp)
+qla24xx_async_abort_cmd(srb_t *cmd_sp, bool wait)
 {
 	scsi_qla_host_t *vha = cmd_sp->vha;
 	fc_port_t *fcport = cmd_sp->fcport;
@@ -1549,6 +1759,8 @@ qla24xx_async_abort_cmd(srb_t *cmd_sp)
 	abt_iocb = &sp->u.iocb_cmd;
 	sp->type = SRB_ABT_CMD;
 	sp->name = "abort";
+	if (wait)
+		sp->flags = SRB_WAKEUP_ON_COMP;
 
 	abt_iocb->timeout = qla24xx_abort_iocb_timeout;
 	init_completion(&abt_iocb->u.abt.comp);
@@ -1572,10 +1784,11 @@ qla24xx_async_abort_cmd(srb_t *cmd_sp)
 	    "Abort command issued - hdl=%x, target_id=%x\n",
 	    cmd_sp->handle, fcport->tgt_id);
 
-	wait_for_completion(&abt_iocb->u.abt.comp);
-
-	rval = abt_iocb->u.abt.comp_status == CS_COMPLETE ?
-	    QLA_SUCCESS : QLA_FUNCTION_FAILED;
+	if (wait) {
+		wait_for_completion(&abt_iocb->u.abt.comp);
+		rval = abt_iocb->u.abt.comp_status == CS_COMPLETE ?
+			QLA_SUCCESS : QLA_FUNCTION_FAILED;
+	}
 
 done_free_sp:
 	sp->free(sp);
@@ -1611,7 +1824,7 @@ qla24xx_async_abort_command(srb_t *sp)
 		return qlafx00_fx_disc(vha, &vha->hw->mr.fcport,
 		    FXDISC_ABORT_IOCTL);
 
-	return qla24xx_async_abort_cmd(sp);
+	return qla24xx_async_abort_cmd(sp, true);
 }
 
 static void
@@ -1799,7 +2012,6 @@ void
 qla2x00_async_logout_done(struct scsi_qla_host *vha, fc_port_t *fcport,
     uint16_t *data)
 {
-	qla2x00_mark_device_lost(vha, fcport, 1, 0);
 	qlt_logo_completion_handler(fcport, data[0]);
 	fcport->login_gen++;
 	fcport->flags &= ~FCF_ASYNC_ACTIVE;
@@ -4050,7 +4262,8 @@ qla2x00_configure_hba(scsi_qla_host_t *vha)
 	id.b.al_pa = al_pa;
 	id.b.rsvd_1 = 0;
 	spin_lock_irqsave(&ha->hardware_lock, flags);
-	qlt_update_host_map(vha, id);
+	if (!(topo == 2 && ha->flags.n2n_bigger))
+		qlt_update_host_map(vha, id);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 	if (!vha->flags.init_done)
@@ -4308,7 +4521,7 @@ qla2x00_nvram_config(scsi_qla_host_t *vha)
 	cnt = (uint8_t *)icb->reserved_3 - (uint8_t *)icb->add_firmware_options;
 	while (cnt--)
 		*dptr1++ = *dptr2++;
-
+	ha->frame_payload_size = le16_to_cpu(icb->frame_payload_size);
 	/* Use alternate WWN? */
 	if (nv->host_p[1] & BIT_7) {
 		memcpy(icb->node_name, nv->alternate_node_name, WWN_SIZE);
@@ -4591,20 +4804,10 @@ qla2x00_configure_loop(scsi_qla_host_t *vha)
 
 	} else if (ha->current_topology == ISP_CFG_N) {
 		clear_bit(RSCN_UPDATE, &flags);
-		if (ha->flags.rida_fmt2) {
-			/* With Rida Format 2, the login is already triggered.
-			 * We know who is on the other side of the wire.
-			 * No need to login to do login to find out or drop into
-			 * qla2x00_configure_local_loop().
-			 */
+		if (qla_tgt_mode_enabled(vha)) {
+			/* allow the other side to start the login */
 			clear_bit(LOCAL_LOOP_UPDATE, &flags);
 			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
-		} else {
-			if (qla_tgt_mode_enabled(vha)) {
-				/* allow the other side to start the login */
-				clear_bit(LOCAL_LOOP_UPDATE, &flags);
-				set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
-			}
 		}
 	} else if (ha->current_topology == ISP_CFG_NL) {
 		clear_bit(RSCN_UPDATE, &flags);
@@ -4688,110 +4891,6 @@ qla2x00_configure_loop(scsi_qla_host_t *vha)
 }
 
 /*
- * N2N Login
- *	Updates Fibre Channel Device Database with local loop devices.
- *
- * Input:
- *	ha = adapter block pointer.
- *
- * Returns:
- */
-static int qla24xx_n2n_handle_login(struct scsi_qla_host *vha,
-				    fc_port_t *fcport)
-{
-	struct qla_hw_data *ha = vha->hw;
-	int	res = QLA_SUCCESS, rval;
-	int	greater_wwpn = 0;
-	int	logged_in = 0;
-
-	if (ha->current_topology != ISP_CFG_N)
-		return res;
-
-	if (wwn_to_u64(vha->port_name) >
-	    wwn_to_u64(vha->n2n_port_name)) {
-		ql_dbg(ql_dbg_disc, vha, 0x2002,
-		    "HBA WWPN is greater %llx > target %llx\n",
-		    wwn_to_u64(vha->port_name),
-		    wwn_to_u64(vha->n2n_port_name));
-		greater_wwpn = 1;
-		fcport->d_id.b24 = vha->n2n_id;
-	}
-
-	fcport->loop_id = vha->loop_id;
-	fcport->fc4f_nvme = 0;
-	fcport->query = 1;
-
-	ql_dbg(ql_dbg_disc, vha, 0x4001,
-	    "Initiate N2N login handler: HBA port_id=%06x loopid=%d\n",
-	    fcport->d_id.b24, vha->loop_id);
-
-	/* Fill in member data. */
-	if (!greater_wwpn) {
-		rval = qla2x00_get_port_database(vha, fcport, 0);
-		ql_dbg(ql_dbg_disc, vha, 0x1051,
-		    "Remote login-state (%x/%x) port_id=%06x loop_id=%x, rval=%d\n",
-		    fcport->current_login_state, fcport->last_login_state,
-		    fcport->d_id.b24, fcport->loop_id, rval);
-
-		if (((fcport->current_login_state & 0xf) == 0x4) ||
-		    ((fcport->current_login_state & 0xf) == 0x6))
-			logged_in = 1;
-	}
-
-	if (logged_in || greater_wwpn) {
-		if (!vha->nvme_local_port && vha->flags.nvme_enabled)
-			qla_nvme_register_hba(vha);
-
-		/* Set connected N_Port d_id */
-		if (vha->flags.nvme_enabled)
-			fcport->fc4f_nvme = 1;
-
-		fcport->scan_state = QLA_FCPORT_FOUND;
-		fcport->fw_login_state = DSC_LS_PORT_UNAVAIL;
-		fcport->disc_state = DSC_GNL;
-		fcport->n2n_flag = 1;
-		fcport->flags = 3;
-		vha->hw->flags.gpsc_supported = 0;
-
-		if (greater_wwpn) {
-			ql_dbg(ql_dbg_disc, vha, 0x20e5,
-			    "%s %d PLOGI ELS %8phC\n",
-			    __func__, __LINE__, fcport->port_name);
-
-			res = qla24xx_els_dcmd2_iocb(vha, ELS_DCMD_PLOGI,
-			    fcport, fcport->d_id);
-		}
-
-		if (res != QLA_SUCCESS) {
-			ql_log(ql_log_info, vha, 0xd04d,
-			    "PLOGI Failed: portid=%06x - retrying\n",
-			    fcport->d_id.b24);
-			res = QLA_SUCCESS;
-		} else {
-			/* State 0x6 means FCP PRLI complete */
-			if ((fcport->current_login_state & 0xf) == 0x6) {
-				ql_dbg(ql_dbg_disc, vha, 0x2118,
-				    "%s %d %8phC post GPDB work\n",
-				    __func__, __LINE__, fcport->port_name);
-				fcport->chip_reset =
-				    vha->hw->base_qpair->chip_reset;
-				qla24xx_post_gpdb_work(vha, fcport, 0);
-			} else {
-				ql_dbg(ql_dbg_disc, vha, 0x2118,
-				    "%s %d %8phC post NVMe PRLI\n",
-				    __func__, __LINE__, fcport->port_name);
-				qla24xx_post_prli_work(vha, fcport);
-			}
-		}
-	} else {
-		/* Wait for next database change */
-		set_bit(N2N_LOGIN_NEEDED, &vha->dpc_flags);
-	}
-
-	return res;
-}
-
-/*
  * qla2x00_configure_local_loop
  *	Updates Fibre Channel Device Database with local loop devices.
  *
@@ -4817,6 +4916,31 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha)
 	struct qla_hw_data *ha = vha->hw;
 	unsigned long flags;
 
+	/* Inititae N2N login. */
+	if (test_and_clear_bit(N2N_LOGIN_NEEDED, &vha->dpc_flags)) {
+		/* borrowing */
+		u32 *bp, i, sz;
+
+		memset(ha->init_cb, 0, ha->init_cb_size);
+		sz = min_t(int, sizeof(struct els_plogi_payload),
+		    ha->init_cb_size);
+		rval = qla24xx_get_port_login_templ(vha, ha->init_cb_dma,
+		    (void *)ha->init_cb, sz);
+		if (rval == QLA_SUCCESS) {
+			bp = (uint32_t *)ha->init_cb;
+			for (i = 0; i < sz/4 ; i++, bp++)
+				*bp = cpu_to_be32(*bp);
+
+			memcpy(&ha->plogi_els_payld.data, (void *)ha->init_cb,
+			    sizeof(ha->plogi_els_payld.data));
+			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+		} else {
+			ql_dbg(ql_dbg_init, vha, 0x00d1,
+			    "PLOGI ELS param read fail.\n");
+		}
+		return QLA_SUCCESS;
+	}
+
 	found_devs = 0;
 	new_fcport = NULL;
 	entries = MAX_FIBRE_DEVICES_LOOP;
@@ -4848,14 +4972,6 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha)
 	}
 	new_fcport->flags &= ~FCF_FABRIC_DEVICE;
 
-	/* Inititae N2N login. */
-	if (test_and_clear_bit(N2N_LOGIN_NEEDED, &vha->dpc_flags)) {
-		rval = qla24xx_n2n_handle_login(vha, new_fcport);
-		if (rval != QLA_SUCCESS)
-			goto cleanup_allocation;
-		return QLA_SUCCESS;
-	}
-
 	/* Add devices to port list. */
 	id_iter = (char *)ha->gid_list;
 	for (index = 0; index < entries; index++) {
@@ -5054,6 +5170,9 @@ qla2x00_reg_remote_port(scsi_qla_host_t *vha, fc_port_t *fcport)
 	struct fc_rport *rport;
 	unsigned long flags;
 
+	if (atomic_read(&fcport->state) == FCS_ONLINE)
+		return;
+
 	rport_ids.node_name = wwn_to_u64(fcport->node_name);
 	rport_ids.port_name = wwn_to_u64(fcport->port_name);
 	rport_ids.port_id = fcport->d_id.b.domain << 16 |
@@ -5109,25 +5228,28 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
 	if (IS_SW_RESV_ADDR(fcport->d_id))
 		return;
 
-	ql_dbg(ql_dbg_disc, vha, 0x20ef, "%s %8phC\n",
-	    __func__, fcport->port_name);
-
-	if (IS_QLAFX00(vha->hw)) {
-		qla2x00_set_fcport_state(fcport, FCS_ONLINE);
-	} else {
-		fcport->login_retry = 0;
-		fcport->flags &= ~(FCF_LOGIN_NEEDED | FCF_ASYNC_SENT);
-		fcport->disc_state = DSC_LOGIN_COMPLETE;
-		fcport->deleted = 0;
-		fcport->logout_on_delete = 1;
-		qla2x00_set_fcport_state(fcport, FCS_ONLINE);
-	}
+	fcport->flags &= ~(FCF_LOGIN_NEEDED | FCF_ASYNC_SENT);
+	fcport->disc_state = DSC_LOGIN_COMPLETE;
+	fcport->deleted = 0;
+	fcport->logout_on_delete = 1;
+	fcport->login_retry = vha->hw->login_retry_count;
+	fcport->n2n_chip_reset = fcport->n2n_link_reset_cnt = 0;
 
-	qla2x00_set_fcport_state(fcport, FCS_ONLINE);
 	qla2x00_iidma_fcport(vha, fcport);
 
+	switch (vha->hw->current_topology) {
+	case ISP_CFG_N:
+	case ISP_CFG_NL:
+		fcport->keep_nport_handle = 1;
+		break;
+	default:
+		break;
+	}
+
 	if (fcport->fc4f_nvme) {
 		qla_nvme_register_remote(vha, fcport);
+		fcport->disc_state = DSC_LOGIN_COMPLETE;
+		qla2x00_set_fcport_state(fcport, FCS_ONLINE);
 		return;
 	}
 
@@ -5168,6 +5290,7 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
 			qla24xx_post_gpsc_work(vha, fcport);
 		}
 	}
+	qla2x00_set_fcport_state(fcport, FCS_ONLINE);
 }
 
 /*
@@ -5668,6 +5791,34 @@ qla2x00_find_new_loop_id(scsi_qla_host_t *vha, fc_port_t *dev)
 }
 
 
+/* FW does not set aside Loop id for MGMT Server/FFFFFAh */
+int
+qla2x00_reserve_mgmt_server_loop_id(scsi_qla_host_t *vha)
+{
+	int loop_id = FC_NO_LOOP_ID;
+	int lid = NPH_MGMT_SERVER - vha->vp_idx;
+	unsigned long flags;
+	struct qla_hw_data *ha = vha->hw;
+
+	if (vha->vp_idx == 0) {
+		set_bit(NPH_MGMT_SERVER, ha->loop_id_map);
+		return NPH_MGMT_SERVER;
+	}
+
+	/* pick id from high and work down to low */
+	spin_lock_irqsave(&ha->vport_slock, flags);
+	for (; lid > 0; lid--) {
+		if (!test_bit(lid, vha->hw->loop_id_map)) {
+			set_bit(lid, vha->hw->loop_id_map);
+			loop_id = lid;
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&ha->vport_slock, flags);
+
+	return loop_id;
+}
+
 /*
  * qla2x00_fabric_login
  *	Issue fabric login command.
@@ -6335,6 +6486,7 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha)
 	ql_log(ql_log_info, vha, 0x00af,
 	    "Performing ISP error recovery - ha=%p.\n", ha);
 
+	ha->flags.purge_mbox = 1;
 	/* For ISP82XX, reset_chip is just disabling interrupts.
 	 * Driver waits for the completion of the commands.
 	 * the interrupts need to be enabled.
@@ -6349,13 +6501,31 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha)
 	ha->current_topology = 0;
 	ha->flags.fw_started = 0;
 	ha->flags.fw_init_done = 0;
-	ha->base_qpair->chip_reset++;
+	ha->chip_reset++;
+	ha->base_qpair->chip_reset = ha->chip_reset;
 	for (i = 0; i < ha->max_qpairs; i++) {
 		if (ha->queue_pair_map[i])
 			ha->queue_pair_map[i]->chip_reset =
 				ha->base_qpair->chip_reset;
 	}
 
+	/* purge MBox commands */
+	if (atomic_read(&ha->num_pend_mbx_stage3)) {
+		clear_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags);
+		complete(&ha->mbx_intr_comp);
+	}
+
+	i = 0;
+	while (atomic_read(&ha->num_pend_mbx_stage3) ||
+	    atomic_read(&ha->num_pend_mbx_stage2) ||
+	    atomic_read(&ha->num_pend_mbx_stage1)) {
+		msleep(20);
+		i++;
+		if (i > 50)
+			break;
+	}
+	ha->flags.purge_mbox = 0;
+
 	atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME);
 	if (atomic_read(&vha->loop_state) != LOOP_DOWN) {
 		atomic_set(&vha->loop_state, LOOP_DOWN);
@@ -6861,7 +7031,7 @@ qla24xx_nvram_config(scsi_qla_host_t *vha)
 	    (uint8_t *)&icb->interrupt_delay_timer;
 	while (cnt--)
 		*dptr1++ = *dptr2++;
-
+	ha->frame_payload_size = le16_to_cpu(icb->frame_payload_size);
 	/*
 	 * Setup driver NVRAM options.
 	 */
@@ -6960,6 +7130,9 @@ qla24xx_nvram_config(scsi_qla_host_t *vha)
 	if (ql2xloginretrycount)
 		ha->login_retry_count = ql2xloginretrycount;
 
+	/* N2N: driver will initiate Login instead of FW */
+	icb->firmware_options_3 |= BIT_8;
+
 	/* Enable ZIO. */
 	if (!vha->flags.init_done) {
 		ha->zio_mode = le32_to_cpu(icb->firmware_options_2) &
@@ -7069,7 +7242,7 @@ check_valid_image:
 			ha->active_image = QLA27XX_SECONDARY_IMAGE;
 	}
 
-	ql_dbg(ql_dbg_init, vha, 0x018f, "%s image\n",
+	ql_dbg(ql_dbg_init + ql_dbg_verbose, vha, 0x018f, "%s image\n",
 	    ha->active_image == 0 ? "default bootld and fw" :
 	    ha->active_image == 1 ? "primary" :
 	    ha->active_image == 2 ? "secondary" :
@@ -7917,7 +8090,7 @@ qla81xx_nvram_config(scsi_qla_host_t *vha)
 
 	/* Use extended-initialization control block. */
 	memcpy(ha->ex_init_cb, &nv->ex_version, sizeof(*ha->ex_init_cb));
-
+	ha->frame_payload_size = le16_to_cpu(icb->frame_payload_size);
 	/*
 	 * Setup driver NVRAM options.
 	 */
@@ -8042,8 +8215,10 @@ qla81xx_nvram_config(scsi_qla_host_t *vha)
 	}
 
 	 /* enable RIDA Format2 */
-	if (qla_tgt_mode_enabled(vha) || qla_dual_mode_enabled(vha))
-		icb->firmware_options_3 |= BIT_0;
+	icb->firmware_options_3 |= BIT_0;
+
+	/* N2N: driver will initiate Login instead of FW */
+	icb->firmware_options_3 |= BIT_8;
 
 	if (IS_QLA27XX(ha)) {
 		icb->firmware_options_3 |= BIT_8;
diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index 59fd5a9dfeb8..4351736b2426 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -58,14 +58,12 @@ qla2x00_debounce_register(volatile uint16_t __iomem *addr)
 static inline void
 qla2x00_poll(struct rsp_que *rsp)
 {
-	unsigned long flags;
 	struct qla_hw_data *ha = rsp->hw;
-	local_irq_save(flags);
+
 	if (IS_P3P_TYPE(ha))
 		qla82xx_poll(0, rsp);
 	else
 		ha->isp_ops->intr_handler(0, rsp);
-	local_irq_restore(flags);
 }
 
 static inline uint8_t *
@@ -204,6 +202,12 @@ qla2x00_reset_active(scsi_qla_host_t *vha)
 	    test_bit(ABORT_ISP_ACTIVE, &vha->dpc_flags);
 }
 
+static inline int
+qla2x00_chip_is_down(scsi_qla_host_t *vha)
+{
+	return (qla2x00_reset_active(vha) || !vha->hw->flags.fw_started);
+}
+
 static inline srb_t *
 qla2xxx_get_qpair_sp(struct qla_qpair *qpair, fc_port_t *fcport, gfp_t flag)
 {
@@ -278,8 +282,6 @@ qla2x00_init_timer(srb_t *sp, unsigned long tmo)
 	init_completion(&sp->comp);
 	if (IS_QLAFX00(sp->vha->hw) && (sp->type == SRB_FXIOCB_DCMD))
 		init_completion(&sp->u.iocb_cmd.u.fxiocb.fxiocb_comp);
-	if (sp->type == SRB_ELS_DCMD)
-		init_completion(&sp->u.iocb_cmd.u.els_logo.comp);
 	add_timer(&sp->u.iocb_cmd.timer);
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index dd93a22fe843..42ac8e097419 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2241,12 +2241,15 @@ qla24xx_login_iocb(srb_t *sp, struct logio_entry_24xx *logio)
 	struct srb_iocb *lio = &sp->u.iocb_cmd;
 
 	logio->entry_type = LOGINOUT_PORT_IOCB_TYPE;
-	logio->control_flags = cpu_to_le16(LCF_COMMAND_PLOGI);
-
-	if (lio->u.logio.flags & SRB_LOGIN_COND_PLOGI)
-		logio->control_flags |= cpu_to_le16(LCF_COND_PLOGI);
-	if (lio->u.logio.flags & SRB_LOGIN_SKIP_PRLI)
-		logio->control_flags |= cpu_to_le16(LCF_SKIP_PRLI);
+	if (lio->u.logio.flags & SRB_LOGIN_PRLI_ONLY) {
+		logio->control_flags = cpu_to_le16(LCF_COMMAND_PRLI);
+	} else {
+		logio->control_flags = cpu_to_le16(LCF_COMMAND_PLOGI);
+		if (lio->u.logio.flags & SRB_LOGIN_COND_PLOGI)
+			logio->control_flags |= cpu_to_le16(LCF_COND_PLOGI);
+		if (lio->u.logio.flags & SRB_LOGIN_SKIP_PRLI)
+			logio->control_flags |= cpu_to_le16(LCF_SKIP_PRLI);
+	}
 	logio->nport_handle = cpu_to_le16(sp->fcport->loop_id);
 	logio->port_id[0] = sp->fcport->d_id.b.al_pa;
 	logio->port_id[1] = sp->fcport->d_id.b.area;
@@ -2463,6 +2466,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode,
 	sp->fcport = fcport;
 	elsio->timeout = qla2x00_els_dcmd_iocb_timeout;
 	qla2x00_init_timer(sp, ELS_DCMD_TIMEOUT);
+	init_completion(&sp->u.iocb_cmd.u.els_logo.comp);
 	sp->done = qla2x00_els_dcmd_sp_done;
 	sp->free = qla2x00_els_dcmd_sp_free;
 
@@ -2510,7 +2514,6 @@ qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb)
 {
 	scsi_qla_host_t *vha = sp->vha;
 	struct srb_iocb *elsio = &sp->u.iocb_cmd;
-	uint32_t	dsd_len = 24;
 
 	els_iocb->entry_type = ELS_IOCB_TYPE;
 	els_iocb->entry_count = 1;
@@ -2533,20 +2536,21 @@ qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb)
 	els_iocb->control_flags = 0;
 
 	if (elsio->u.els_logo.els_cmd == ELS_DCMD_PLOGI) {
-		els_iocb->tx_byte_count = sizeof(struct els_plogi_payload);
+		els_iocb->tx_byte_count = els_iocb->tx_len =
+			sizeof(struct els_plogi_payload);
 		els_iocb->tx_address[0] =
 			cpu_to_le32(LSD(elsio->u.els_plogi.els_plogi_pyld_dma));
 		els_iocb->tx_address[1] =
 			cpu_to_le32(MSD(elsio->u.els_plogi.els_plogi_pyld_dma));
-		els_iocb->tx_len = dsd_len;
 
 		els_iocb->rx_dsd_count = 1;
-		els_iocb->rx_byte_count = sizeof(struct els_plogi_payload);
+		els_iocb->rx_byte_count = els_iocb->rx_len =
+			sizeof(struct els_plogi_payload);
 		els_iocb->rx_address[0] =
 			cpu_to_le32(LSD(elsio->u.els_plogi.els_resp_pyld_dma));
 		els_iocb->rx_address[1] =
 			cpu_to_le32(MSD(elsio->u.els_plogi.els_resp_pyld_dma));
-		els_iocb->rx_len = dsd_len;
+
 		ql_dbg(ql_dbg_io + ql_dbg_buffer, vha, 0x3073,
 		    "PLOGI ELS IOCB:\n");
 		ql_dump_buffer(ql_log_info, vha, 0x0109,
@@ -2569,33 +2573,12 @@ qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb)
 }
 
 static void
-qla2x00_els_dcmd2_sp_free(void *data)
-{
-	srb_t *sp = data;
-	struct srb_iocb *elsio = &sp->u.iocb_cmd;
-
-	if (elsio->u.els_plogi.els_plogi_pyld)
-		dma_free_coherent(&sp->vha->hw->pdev->dev, DMA_POOL_SIZE,
-		    elsio->u.els_plogi.els_plogi_pyld,
-		    elsio->u.els_plogi.els_plogi_pyld_dma);
-
-	if (elsio->u.els_plogi.els_resp_pyld)
-		dma_free_coherent(&sp->vha->hw->pdev->dev, DMA_POOL_SIZE,
-		    elsio->u.els_plogi.els_resp_pyld,
-		    elsio->u.els_plogi.els_resp_pyld_dma);
-
-	del_timer(&elsio->timer);
-	qla2x00_rel_sp(sp);
-}
-
-static void
 qla2x00_els_dcmd2_iocb_timeout(void *data)
 {
 	srb_t *sp = data;
 	fc_port_t *fcport = sp->fcport;
 	struct scsi_qla_host *vha = sp->vha;
 	struct qla_hw_data *ha = vha->hw;
-	struct srb_iocb *lio = &sp->u.iocb_cmd;
 	unsigned long flags = 0;
 	int res;
 
@@ -2611,7 +2594,7 @@ qla2x00_els_dcmd2_iocb_timeout(void *data)
 	    (res == QLA_SUCCESS) ? "successful" : "failed");
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
-	complete(&lio->u.els_plogi.comp);
+	sp->done(sp, QLA_FUNCTION_TIMEOUT);
 }
 
 static void
@@ -2621,17 +2604,55 @@ qla2x00_els_dcmd2_sp_done(void *ptr, int res)
 	fc_port_t *fcport = sp->fcport;
 	struct srb_iocb *lio = &sp->u.iocb_cmd;
 	struct scsi_qla_host *vha = sp->vha;
+	struct event_arg ea;
+	struct qla_work_evt *e;
+
+	ql_dbg(ql_dbg_disc, vha, 0x3072,
+	    "%s ELS done rc %d hdl=%x, portid=%06x %8phC\n",
+	    sp->name, res, sp->handle, fcport->d_id.b24, fcport->port_name);
 
-	ql_dbg(ql_dbg_io + ql_dbg_disc, vha, 0x3072,
-	    "%s ELS hdl=%x, portid=%06x done %8phC\n",
-	    sp->name, sp->handle, fcport->d_id.b24, fcport->port_name);
+	fcport->flags &= ~(FCF_ASYNC_SENT|FCF_ASYNC_ACTIVE);
+	del_timer(&sp->u.iocb_cmd.timer);
 
-	complete(&lio->u.els_plogi.comp);
+	if (sp->flags & SRB_WAKEUP_ON_COMP)
+		complete(&lio->u.els_plogi.comp);
+	else {
+		if (res) {
+			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+		} else {
+			memset(&ea, 0, sizeof(ea));
+			ea.fcport = fcport;
+			ea.rc = res;
+			ea.event = FCME_ELS_PLOGI_DONE;
+			qla2x00_fcport_event_handler(vha, &ea);
+		}
+
+		e = qla2x00_alloc_work(vha, QLA_EVT_UNMAP);
+		if (!e) {
+			struct srb_iocb *elsio = &sp->u.iocb_cmd;
+
+			if (elsio->u.els_plogi.els_plogi_pyld)
+				dma_free_coherent(&sp->vha->hw->pdev->dev,
+				    elsio->u.els_plogi.tx_size,
+				    elsio->u.els_plogi.els_plogi_pyld,
+				    elsio->u.els_plogi.els_plogi_pyld_dma);
+
+			if (elsio->u.els_plogi.els_resp_pyld)
+				dma_free_coherent(&sp->vha->hw->pdev->dev,
+				    elsio->u.els_plogi.rx_size,
+				    elsio->u.els_plogi.els_resp_pyld,
+				    elsio->u.els_plogi.els_resp_pyld_dma);
+			sp->free(sp);
+			return;
+		}
+		e->u.iosb.sp = sp;
+		qla2x00_post_work(vha, e);
+	}
 }
 
 int
 qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,
-		       fc_port_t *fcport, port_id_t remote_did)
+    fc_port_t *fcport, bool wait)
 {
 	srb_t *sp;
 	struct srb_iocb *elsio = NULL;
@@ -2649,23 +2670,23 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,
 	}
 
 	elsio = &sp->u.iocb_cmd;
-	fcport->d_id.b.domain = remote_did.b.domain;
-	fcport->d_id.b.area = remote_did.b.area;
-	fcport->d_id.b.al_pa = remote_did.b.al_pa;
-
 	ql_dbg(ql_dbg_io, vha, 0x3073,
 	    "Enter: PLOGI portid=%06x\n", fcport->d_id.b24);
 
+	fcport->flags |= FCF_ASYNC_SENT;
 	sp->type = SRB_ELS_DCMD;
 	sp->name = "ELS_DCMD";
 	sp->fcport = fcport;
 
 	elsio->timeout = qla2x00_els_dcmd2_iocb_timeout;
 	init_completion(&elsio->u.els_plogi.comp);
-	qla2x00_init_timer(sp, ELS_DCMD_TIMEOUT);
+	if (wait)
+		sp->flags = SRB_WAKEUP_ON_COMP;
+
+	qla2x00_init_timer(sp, ELS_DCMD_TIMEOUT + 2);
 
 	sp->done = qla2x00_els_dcmd2_sp_done;
-	sp->free = qla2x00_els_dcmd2_sp_free;
+	elsio->u.els_plogi.tx_size = elsio->u.els_plogi.rx_size = DMA_POOL_SIZE;
 
 	ptr = elsio->u.els_plogi.els_plogi_pyld =
 	    dma_alloc_coherent(&ha->pdev->dev, DMA_POOL_SIZE,
@@ -2690,33 +2711,52 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,
 
 	memset(ptr, 0, sizeof(struct els_plogi_payload));
 	memset(resp_ptr, 0, sizeof(struct els_plogi_payload));
+	memcpy(elsio->u.els_plogi.els_plogi_pyld->data,
+	    &ha->plogi_els_payld.data,
+	    sizeof(elsio->u.els_plogi.els_plogi_pyld->data));
+
 	elsio->u.els_plogi.els_cmd = els_opcode;
 	elsio->u.els_plogi.els_plogi_pyld->opcode = els_opcode;
-	qla24xx_get_port_login_templ(vha, ptr_dma + 4,
-		&elsio->u.els_plogi.els_plogi_pyld->data[0],
-		sizeof(struct els_plogi_payload));
 
-	ql_dbg(ql_dbg_io + ql_dbg_buffer, vha, 0x3073, "PLOGI buffer:\n");
-	ql_dump_buffer(ql_dbg_io + ql_dbg_buffer, vha, 0x0109,
+	ql_dbg(ql_dbg_disc + ql_dbg_buffer, vha, 0x3073, "PLOGI buffer:\n");
+	ql_dump_buffer(ql_dbg_disc + ql_dbg_buffer, vha, 0x0109,
 	    (uint8_t *)elsio->u.els_plogi.els_plogi_pyld, 0x70);
 
 	rval = qla2x00_start_sp(sp);
 	if (rval != QLA_SUCCESS) {
 		rval = QLA_FUNCTION_FAILED;
-		goto out;
+	} else {
+		ql_dbg(ql_dbg_disc, vha, 0x3074,
+		    "%s PLOGI sent, hdl=%x, loopid=%x, to port_id %06x from port_id %06x\n",
+		    sp->name, sp->handle, fcport->loop_id,
+		    fcport->d_id.b24, vha->d_id.b24);
 	}
 
-	ql_dbg(ql_dbg_io, vha, 0x3074,
-	    "%s PLOGI sent, hdl=%x, loopid=%x, portid=%06x\n",
-	    sp->name, sp->handle, fcport->loop_id, fcport->d_id.b24);
-
-	wait_for_completion(&elsio->u.els_plogi.comp);
+	if (wait) {
+		wait_for_completion(&elsio->u.els_plogi.comp);
 
-	if (elsio->u.els_plogi.comp_status != CS_COMPLETE)
-		rval = QLA_FUNCTION_FAILED;
+		if (elsio->u.els_plogi.comp_status != CS_COMPLETE)
+			rval = QLA_FUNCTION_FAILED;
+	} else {
+		goto done;
+	}
 
 out:
+	fcport->flags &= ~(FCF_ASYNC_SENT);
+	if (elsio->u.els_plogi.els_plogi_pyld)
+		dma_free_coherent(&sp->vha->hw->pdev->dev,
+		    elsio->u.els_plogi.tx_size,
+		    elsio->u.els_plogi.els_plogi_pyld,
+		    elsio->u.els_plogi.els_plogi_pyld_dma);
+
+	if (elsio->u.els_plogi.els_resp_pyld)
+		dma_free_coherent(&sp->vha->hw->pdev->dev,
+		    elsio->u.els_plogi.rx_size,
+		    elsio->u.els_plogi.els_resp_pyld,
+		    elsio->u.els_plogi.els_resp_pyld_dma);
+
 	sp->free(sp);
+done:
 	return rval;
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 7756106d4555..36cbb29c84f6 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -911,7 +911,8 @@ skip_rio:
 			if (!atomic_read(&vha->loop_down_timer))
 				atomic_set(&vha->loop_down_timer,
 				    LOOP_DOWN_TIME);
-			qla2x00_mark_all_devices_lost(vha, 1);
+			if (!N2N_TOPO(ha))
+				qla2x00_mark_all_devices_lost(vha, 1);
 		}
 
 		if (vha->vp_idx) {
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index f0ec13d48bf3..2c6c2cd5a0d0 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -59,6 +59,7 @@ static struct rom_cmd {
 	{ MBC_IOCB_COMMAND_A64 },
 	{ MBC_GET_ADAPTER_LOOP_ID },
 	{ MBC_READ_SFP },
+	{ MBC_GET_RNID_PARAMS },
 };
 
 static int is_rom_cmd(uint16_t cmd)
@@ -110,6 +111,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 	unsigned long	wait_time;
 	struct qla_hw_data *ha = vha->hw;
 	scsi_qla_host_t *base_vha = pci_get_drvdata(ha->pdev);
+	u32 chip_reset;
 
 
 	ql_dbg(ql_dbg_mbx, vha, 0x1000, "Entered %s.\n", __func__);
@@ -140,7 +142,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 
 	rval = QLA_SUCCESS;
 	abort_active = test_bit(ABORT_ISP_ACTIVE, &base_vha->dpc_flags);
-
+	chip_reset = ha->chip_reset;
 
 	if (ha->flags.pci_channel_io_perm_failure) {
 		ql_log(ql_log_warn, vha, 0x1003,
@@ -167,6 +169,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 		return QLA_FUNCTION_TIMEOUT;
 	}
 
+	atomic_inc(&ha->num_pend_mbx_stage1);
 	/*
 	 * Wait for active mailbox commands to finish by waiting at most tov
 	 * seconds. This is to serialize actual issuing of mailbox cmds during
@@ -177,8 +180,14 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 		ql_log(ql_log_warn, vha, 0xd035,
 		    "Cmd access timeout, cmd=0x%x, Exiting.\n",
 		    mcp->mb[0]);
+		atomic_dec(&ha->num_pend_mbx_stage1);
 		return QLA_FUNCTION_TIMEOUT;
 	}
+	atomic_dec(&ha->num_pend_mbx_stage1);
+	if (ha->flags.purge_mbox || chip_reset != ha->chip_reset) {
+		rval = QLA_ABORTED;
+		goto premature_exit;
+	}
 
 	ha->flags.mbox_busy = 1;
 	/* Save mailbox command for debug */
@@ -189,6 +198,13 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 
+	if (ha->flags.purge_mbox || chip_reset != ha->chip_reset) {
+		rval = QLA_ABORTED;
+		ha->flags.mbox_busy = 0;
+		spin_unlock_irqrestore(&ha->hardware_lock, flags);
+		goto premature_exit;
+	}
+
 	/* Load mailbox registers. */
 	if (IS_P3P_TYPE(ha))
 		optr = (uint16_t __iomem *)&reg->isp82.mailbox_in[0];
@@ -231,7 +247,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 	    "jiffies=%lx.\n", jiffies);
 
 	/* Wait for mbx cmd completion until timeout */
-
+	atomic_inc(&ha->num_pend_mbx_stage2);
 	if ((!abort_active && io_lock_on) || IS_NOPOLLING_TYPE(ha)) {
 		set_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags);
 
@@ -241,6 +257,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 				spin_unlock_irqrestore(&ha->hardware_lock,
 					flags);
 				ha->flags.mbox_busy = 0;
+				atomic_dec(&ha->num_pend_mbx_stage2);
 				ql_dbg(ql_dbg_mbx, vha, 0x1010,
 				    "Pending mailbox timeout, exiting.\n");
 				rval = QLA_FUNCTION_TIMEOUT;
@@ -254,6 +271,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 		wait_time = jiffies;
+		atomic_inc(&ha->num_pend_mbx_stage3);
 		if (!wait_for_completion_timeout(&ha->mbx_intr_comp,
 		    mcp->tov * HZ)) {
 			ql_dbg(ql_dbg_mbx, vha, 0x117a,
@@ -261,7 +279,17 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 			spin_lock_irqsave(&ha->hardware_lock, flags);
 			clear_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags);
 			spin_unlock_irqrestore(&ha->hardware_lock, flags);
+
+		} else if (ha->flags.purge_mbox ||
+		    chip_reset != ha->chip_reset) {
+			ha->flags.mbox_busy = 0;
+			atomic_dec(&ha->num_pend_mbx_stage2);
+			atomic_dec(&ha->num_pend_mbx_stage3);
+			rval = QLA_ABORTED;
+			goto premature_exit;
 		}
+		atomic_dec(&ha->num_pend_mbx_stage3);
+
 		if (time_after(jiffies, wait_time + 5 * HZ))
 			ql_log(ql_log_warn, vha, 0x1015, "cmd=0x%x, waited %d msecs\n",
 			    command, jiffies_to_msecs(jiffies - wait_time));
@@ -275,6 +303,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 				spin_unlock_irqrestore(&ha->hardware_lock,
 					flags);
 				ha->flags.mbox_busy = 0;
+				atomic_dec(&ha->num_pend_mbx_stage2);
 				ql_dbg(ql_dbg_mbx, vha, 0x1012,
 				    "Pending mailbox timeout, exiting.\n");
 				rval = QLA_FUNCTION_TIMEOUT;
@@ -289,6 +318,14 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 
 		wait_time = jiffies + mcp->tov * HZ; /* wait at most tov secs */
 		while (!ha->flags.mbox_int) {
+			if (ha->flags.purge_mbox ||
+			    chip_reset != ha->chip_reset) {
+				ha->flags.mbox_busy = 0;
+				atomic_dec(&ha->num_pend_mbx_stage2);
+				rval = QLA_ABORTED;
+				goto premature_exit;
+			}
+
 			if (time_after(jiffies, wait_time))
 				break;
 
@@ -312,6 +349,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 		    "Waited %d sec.\n",
 		    (uint)((jiffies - (wait_time - (mcp->tov * HZ)))/HZ));
 	}
+	atomic_dec(&ha->num_pend_mbx_stage2);
 
 	/* Check whether we timed out */
 	if (ha->flags.mbox_int) {
@@ -390,7 +428,8 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 		/* Capture FW dump only, if PCI device active */
 		if (!pci_channel_offline(vha->hw->pdev)) {
 			pci_read_config_word(ha->pdev, PCI_VENDOR_ID, &w);
-			if (w == 0xffff || ictrl == 0xffffffff) {
+			if (w == 0xffff || ictrl == 0xffffffff ||
+			    (chip_reset != ha->chip_reset)) {
 				/* This is special case if there is unload
 				 * of driver happening and if PCI device go
 				 * into bad state due to PCI error condition
@@ -497,7 +536,11 @@ premature_exit:
 	complete(&ha->mbx_cmd_comp);
 
 mbx_done:
-	if (rval) {
+	if (rval == QLA_ABORTED) {
+		ql_log(ql_log_info, vha, 0xd035,
+		    "Chip Reset in progress. Purging Mbox cmd=0x%x.\n",
+		    mcp->mb[0]);
+	} else if (rval) {
 		if (ql2xextended_error_logging & (ql_dbg_disc|ql_dbg_mbx)) {
 			pr_warn("%s [%s]-%04x:%ld: **** Failed", QL_MSGHDR,
 			    dev_name(&ha->pdev->dev), 0x1020+0x800,
@@ -2177,7 +2220,10 @@ qla2x00_lip_reset(scsi_qla_host_t *vha)
 		mcp->out_mb = MBX_2|MBX_1|MBX_0;
 	} else if (IS_FWI2_CAPABLE(vha->hw)) {
 		mcp->mb[0] = MBC_LIP_FULL_LOGIN;
-		mcp->mb[1] = BIT_6;
+		if (N2N_TOPO(vha->hw))
+			mcp->mb[1] = BIT_4; /* re-init */
+		else
+			mcp->mb[1] = BIT_6; /* LIP */
 		mcp->mb[2] = 0;
 		mcp->mb[3] = vha->hw->loop_reset_delay;
 		mcp->out_mb = MBX_3|MBX_2|MBX_1|MBX_0;
@@ -3797,30 +3843,68 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 		   "Format 1: WWPN %8phC.\n",
 		   vha->port_name);
 
-		/* N2N.  direct connect */
-		if (IS_QLA27XX(ha) &&
-		    ((rptid_entry->u.f1.flags>>1) & 0x7) == 2) {
-			/* if our portname is higher then initiate N2N login */
-			if (wwn_to_u64(vha->port_name) >
-			    wwn_to_u64(rptid_entry->u.f1.port_name)) {
-				// ??? qlt_update_host_map(vha, id);
-				vha->n2n_id = 0x1;
-				ql_dbg(ql_dbg_async, vha, 0x5075,
-				    "Format 1: Setting n2n_update_needed for id %d\n",
-				    vha->n2n_id);
+		switch (rptid_entry->u.f1.flags & TOPO_MASK) {
+		case TOPO_N2N:
+			ha->current_topology = ISP_CFG_N;
+			spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
+			fcport = qla2x00_find_fcport_by_wwpn(vha,
+			    rptid_entry->u.f1.port_name, 1);
+			spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
+
+			if (fcport) {
+				fcport->plogi_nack_done_deadline = jiffies + HZ;
+				fcport->dm_login_expire = jiffies + 3*HZ;
+				fcport->scan_state = QLA_FCPORT_FOUND;
+				switch (fcport->disc_state) {
+				case DSC_DELETED:
+					set_bit(RELOGIN_NEEDED,
+					    &vha->dpc_flags);
+					break;
+				case DSC_DELETE_PEND:
+					break;
+				default:
+					qlt_schedule_sess_for_deletion(fcport);
+					break;
+				}
 			} else {
-				ql_dbg(ql_dbg_async, vha, 0x5075,
-				    "Format 1: Remote login - Waiting for WWPN %8phC.\n",
-				    rptid_entry->u.f1.port_name);
+				id.b24 = 0;
+				if (wwn_to_u64(vha->port_name) >
+				    wwn_to_u64(rptid_entry->u.f1.port_name)) {
+					vha->d_id.b24 = 0;
+					vha->d_id.b.al_pa = 1;
+					ha->flags.n2n_bigger = 1;
+
+					id.b.al_pa = 2;
+					ql_dbg(ql_dbg_async, vha, 0x5075,
+					    "Format 1: assign local id %x remote id %x\n",
+					    vha->d_id.b24, id.b24);
+				} else {
+					ql_dbg(ql_dbg_async, vha, 0x5075,
+					    "Format 1: Remote login - Waiting for WWPN %8phC.\n",
+					    rptid_entry->u.f1.port_name);
+					ha->flags.n2n_bigger = 0;
+				}
+				qla24xx_post_newsess_work(vha, &id,
+				    rptid_entry->u.f1.port_name,
+				    rptid_entry->u.f1.node_name,
+				    NULL,
+				    FC4_TYPE_UNKNOWN);
 			}
 
-			memcpy(vha->n2n_port_name, rptid_entry->u.f1.port_name,
-			    WWN_SIZE);
+			/* if our portname is higher then initiate N2N login */
+
 			set_bit(N2N_LOGIN_NEEDED, &vha->dpc_flags);
-			set_bit(REGISTER_FC4_NEEDED, &vha->dpc_flags);
-			set_bit(REGISTER_FDMI_NEEDED, &vha->dpc_flags);
 			ha->flags.n2n_ae = 1;
 			return;
+			break;
+		case TOPO_FL:
+			ha->current_topology = ISP_CFG_FL;
+			break;
+		case TOPO_F:
+			ha->current_topology = ISP_CFG_F;
+			break;
+		default:
+			break;
 		}
 
 		ha->flags.gpsc_supported = 1;
@@ -3909,30 +3993,9 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 		    rptid_entry->u.f2.port_name, 1);
 
 		if (fcport) {
+			fcport->login_retry = vha->hw->login_retry_count;
 			fcport->plogi_nack_done_deadline = jiffies + HZ;
 			fcport->scan_state = QLA_FCPORT_FOUND;
-			switch (fcport->disc_state) {
-			case DSC_DELETED:
-				ql_dbg(ql_dbg_disc, vha, 0x210d,
-				    "%s %d %8phC login\n",
-				    __func__, __LINE__, fcport->port_name);
-				qla24xx_fcport_handle_login(vha, fcport);
-				break;
-			case DSC_DELETE_PEND:
-				break;
-			default:
-				qlt_schedule_sess_for_deletion(fcport);
-				break;
-			}
-		} else {
-			id.b.al_pa  = rptid_entry->u.f2.remote_nport_id[0];
-			id.b.area   = rptid_entry->u.f2.remote_nport_id[1];
-			id.b.domain = rptid_entry->u.f2.remote_nport_id[2];
-			qla24xx_post_newsess_work(vha, &id,
-			    rptid_entry->u.f2.port_name,
-			    rptid_entry->u.f2.node_name,
-			    NULL,
-			    FC4_TYPE_UNKNOWN);
 		}
 	}
 }
@@ -4663,7 +4726,7 @@ qla24xx_get_port_login_templ(scsi_qla_host_t *vha, dma_addr_t buf_dma,
 		    "Done %s.\n", __func__);
 		bp = (uint32_t *) buf;
 		for (i = 0; i < (bufsiz-4)/4; i++, bp++)
-			*bp = cpu_to_be32(*bp);
+			*bp = le32_to_cpu(*bp);
 	}
 
 	return rval;
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index aa727d07b702..d620f4bebcd0 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -492,7 +492,7 @@ qla24xx_create_vhost(struct fc_vport *fc_vport)
 		    "Couldn't allocate vp_id.\n");
 		goto create_vhost_failed;
 	}
-	vha->mgmt_svr_loop_id = NPH_MGMT_SERVER;
+	vha->mgmt_svr_loop_id = qla2x00_reserve_mgmt_server_loop_id(vha);
 
 	vha->dpc_flags = 0L;
 
diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index c5a963c2c86e..20d9dc39f0fb 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -30,6 +30,9 @@ int qla_nvme_register_remote(struct scsi_qla_host *vha, struct fc_port *fcport)
 		return 0;
 	}
 
+	if (!vha->nvme_local_port && qla_nvme_register_hba(vha))
+		return 0;
+
 	if (!(fcport->nvme_prli_service_param &
 	    (NVME_PRLI_SP_TARGET | NVME_PRLI_SP_DISCOVERY)) ||
 		(fcport->nvme_flag & NVME_FLAG_REGISTERED))
@@ -676,15 +679,15 @@ void qla_nvme_delete(struct scsi_qla_host *vha)
 	}
 }
 
-void qla_nvme_register_hba(struct scsi_qla_host *vha)
+int qla_nvme_register_hba(struct scsi_qla_host *vha)
 {
 	struct nvme_fc_port_template *tmpl;
 	struct qla_hw_data *ha;
 	struct nvme_fc_port_info pinfo;
-	int ret;
+	int ret = EINVAL;
 
 	if (!IS_ENABLED(CONFIG_NVME_FC))
-		return;
+		return ret;
 
 	ha = vha->hw;
 	tmpl = &qla_nvme_fc_transport;
@@ -711,7 +714,9 @@ void qla_nvme_register_hba(struct scsi_qla_host *vha)
 	if (ret) {
 		ql_log(ql_log_warn, vha, 0xffff,
 		    "register_localport failed: ret=%x\n", ret);
-		return;
+	} else {
+		vha->nvme_local_port->private = vha;
 	}
-	vha->nvme_local_port->private = vha;
+
+	return ret;
 }
diff --git a/drivers/scsi/qla2xxx/qla_nvme.h b/drivers/scsi/qla2xxx/qla_nvme.h
index 816854ada654..4941d107fb1c 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.h
+++ b/drivers/scsi/qla2xxx/qla_nvme.h
@@ -142,7 +142,7 @@ struct pt_ls4_rx_unsol {
 /*
  * Global functions prototype in qla_nvme.c source file.
  */
-void qla_nvme_register_hba(struct scsi_qla_host *);
+int qla_nvme_register_hba(struct scsi_qla_host *);
 int  qla_nvme_register_remote(struct scsi_qla_host *, struct fc_port *);
 void qla_nvme_delete(struct scsi_qla_host *);
 void qla_nvme_abort(struct qla_hw_data *, struct srb *sp, int res);
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 1fbd16c8c9a7..42b8f0d3e580 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -2816,6 +2816,9 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	ha->link_data_rate = PORT_SPEED_UNKNOWN;
 	ha->optrom_size = OPTROM_SIZE_2300;
 	ha->max_exchg = FW_MAX_EXCHANGES_CNT;
+	atomic_set(&ha->num_pend_mbx_stage1, 0);
+	atomic_set(&ha->num_pend_mbx_stage2, 0);
+	atomic_set(&ha->num_pend_mbx_stage3, 0);
 
 	/* Assign ISP specific operations. */
 	if (IS_QLA2100(ha)) {
@@ -3046,7 +3049,8 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	host = base_vha->host;
 	base_vha->req = req;
 	if (IS_QLA2XXX_MIDTYPE(ha))
-		base_vha->mgmt_svr_loop_id = NPH_MGMT_SERVER;
+		base_vha->mgmt_svr_loop_id =
+			qla2x00_reserve_mgmt_server_loop_id(base_vha);
 	else
 		base_vha->mgmt_svr_loop_id = MANAGEMENT_SERVER +
 						base_vha->vp_idx;
@@ -3830,14 +3834,6 @@ void qla2x00_mark_device_lost(scsi_qla_host_t *vha, fc_port_t *fcport,
 		return;
 
 	set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
-
-	if (fcport->login_retry == 0) {
-		fcport->login_retry = vha->hw->login_retry_count;
-
-		ql_dbg(ql_dbg_disc, vha, 0x20a3,
-		    "Port login retry %8phN, lid 0x%04x retry cnt=%d.\n",
-		    fcport->port_name, fcport->loop_id, fcport->login_retry);
-	}
 }
 
 /*
@@ -4785,7 +4781,6 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e)
 	struct qlt_plogi_ack_t *pla =
 	    (struct qlt_plogi_ack_t *)e->u.new_sess.pla;
 	uint8_t free_fcport = 0;
-	u64 wwn;
 
 	ql_dbg(ql_dbg_disc, vha, 0xffff,
 	    "%s %d %8phC enter\n",
@@ -4813,10 +4808,10 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e)
 			fcport->d_id = e->u.new_sess.id;
 			fcport->flags |= FCF_FABRIC_DEVICE;
 			fcport->fw_login_state = DSC_LS_PLOGI_PEND;
-			if (e->u.new_sess.fc4_type & FS_FC4TYPE_FCP)
+			if (e->u.new_sess.fc4_type == FS_FC4TYPE_FCP)
 				fcport->fc4_type = FC4_TYPE_FCP_SCSI;
 
-			if (e->u.new_sess.fc4_type & FS_FC4TYPE_NVME) {
+			if (e->u.new_sess.fc4_type == FS_FC4TYPE_NVME) {
 				fcport->fc4_type = FC4_TYPE_OTHER;
 				fcport->fc4f_nvme = FC4_TYPE_NVME;
 			}
@@ -4858,9 +4853,6 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e)
 	spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
 
 	if (fcport) {
-		if (N2N_TOPO(vha->hw))
-			fcport->flags &= ~FCF_FABRIC_DEVICE;
-
 		fcport->id_changed = 1;
 		fcport->scan_state = QLA_FCPORT_FOUND;
 		memcpy(fcport->node_name, e->u.new_sess.node_name, WWN_SIZE);
@@ -4921,12 +4913,22 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e)
 			if (dfcp)
 				qlt_schedule_sess_for_deletion(tfcp);
 
-			wwn = wwn_to_u64(fcport->node_name);
 
-			if (!wwn)
-				qla24xx_async_gnnid(vha, fcport);
-			else
-				qla24xx_async_gnl(vha, fcport);
+			if (N2N_TOPO(vha->hw))
+				fcport->flags &= ~FCF_FABRIC_DEVICE;
+
+			if (N2N_TOPO(vha->hw)) {
+				if (vha->flags.nvme_enabled) {
+					fcport->fc4f_nvme = 1;
+					fcport->n2n_flag = 1;
+				}
+				fcport->fw_login_state = 0;
+				/*
+				 * wait link init done before sending login
+				 */
+			} else {
+				qla24xx_fcport_handle_login(vha, fcport);
+			}
 		}
 	}
 
@@ -5061,6 +5063,10 @@ qla2x00_do_work(struct scsi_qla_host *vha)
 		case QLA_EVT_IIDMA:
 			qla_do_iidma_work(vha, e->u.fcport.fcport);
 			break;
+		case QLA_EVT_ELS_PLOGI:
+			qla24xx_els_dcmd2_iocb(vha, ELS_DCMD_PLOGI,
+			    e->u.fcport.fcport, false);
+			break;
 		}
 		if (e->flags & QLA_EVT_FLAG_FREE)
 			kfree(e);
@@ -5090,7 +5096,7 @@ int qla24xx_post_relogin_work(struct scsi_qla_host *vha)
 void qla2x00_relogin(struct scsi_qla_host *vha)
 {
 	fc_port_t       *fcport;
-	int status;
+	int status, relogin_needed = 0;
 	struct event_arg ea;
 
 	list_for_each_entry(fcport, &vha->vp_fcports, list) {
@@ -5099,47 +5105,59 @@ void qla2x00_relogin(struct scsi_qla_host *vha)
 		 * to it if we haven't run out of retries.
 		 */
 		if (atomic_read(&fcport->state) != FCS_ONLINE &&
-		    fcport->login_retry &&
-		    !(fcport->flags & (FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE))) {
-			if (vha->hw->current_topology != ISP_CFG_NL) {
-				ql_dbg(ql_dbg_disc, fcport->vha, 0x2108,
-				    "%s %8phC DS %d LS %d\n", __func__,
-				    fcport->port_name, fcport->disc_state,
-				    fcport->fw_login_state);
-				memset(&ea, 0, sizeof(ea));
-				ea.event = FCME_RELOGIN;
-				ea.fcport = fcport;
-				qla2x00_fcport_event_handler(vha, &ea);
-			} else if (vha->hw->current_topology == ISP_CFG_NL) {
-				fcport->login_retry--;
-				status = qla2x00_local_device_login(vha,
-								fcport);
-				if (status == QLA_SUCCESS) {
-					fcport->old_loop_id = fcport->loop_id;
-					ql_dbg(ql_dbg_disc, vha, 0x2003,
-					    "Port login OK: logged in ID 0x%x.\n",
-					    fcport->loop_id);
-					qla2x00_update_fcport(vha, fcport);
-				} else if (status == 1) {
-					set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
-					/* retry the login again */
-					ql_dbg(ql_dbg_disc, vha, 0x2007,
-					    "Retrying %d login again loop_id 0x%x.\n",
-					    fcport->login_retry,
-					    fcport->loop_id);
-				} else {
-					fcport->login_retry = 0;
-				}
+		    fcport->login_retry) {
+			if (fcport->scan_state != QLA_FCPORT_FOUND ||
+			    fcport->disc_state == DSC_LOGIN_COMPLETE)
+				continue;
+
+			if (fcport->flags & (FCF_ASYNC_SENT|FCF_ASYNC_ACTIVE) ||
+				fcport->disc_state == DSC_DELETE_PEND) {
+				relogin_needed = 1;
+			} else {
+				if (vha->hw->current_topology != ISP_CFG_NL) {
+					memset(&ea, 0, sizeof(ea));
+					ea.event = FCME_RELOGIN;
+					ea.fcport = fcport;
+					qla2x00_fcport_event_handler(vha, &ea);
+				} else if (vha->hw->current_topology ==
+				    ISP_CFG_NL) {
+					fcport->login_retry--;
+					status =
+					    qla2x00_local_device_login(vha,
+						fcport);
+					if (status == QLA_SUCCESS) {
+						fcport->old_loop_id =
+						    fcport->loop_id;
+						ql_dbg(ql_dbg_disc, vha, 0x2003,
+						    "Port login OK: logged in ID 0x%x.\n",
+						    fcport->loop_id);
+						qla2x00_update_fcport
+							(vha, fcport);
+					} else if (status == 1) {
+						set_bit(RELOGIN_NEEDED,
+						    &vha->dpc_flags);
+						/* retry the login again */
+						ql_dbg(ql_dbg_disc, vha, 0x2007,
+						    "Retrying %d login again loop_id 0x%x.\n",
+						    fcport->login_retry,
+						    fcport->loop_id);
+					} else {
+						fcport->login_retry = 0;
+					}
 
-				if (fcport->login_retry == 0 &&
-				    status != QLA_SUCCESS)
-					qla2x00_clear_loop_id(fcport);
+					if (fcport->login_retry == 0 &&
+					    status != QLA_SUCCESS)
+						qla2x00_clear_loop_id(fcport);
+				}
 			}
 		}
 		if (test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags))
 			break;
 	}
 
+	if (relogin_needed)
+		set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+
 	ql_dbg(ql_dbg_disc, vha, 0x400e,
 	    "Relogin end.\n");
 }
@@ -6179,6 +6197,11 @@ intr_on_check:
 		if (!IS_QLAFX00(ha))
 			qla2x00_do_dpc_all_vps(base_vha);
 
+		if (test_and_clear_bit(N2N_LINK_RESET,
+			&base_vha->dpc_flags)) {
+			qla2x00_lip_reset(base_vha);
+		}
+
 		ha->dpc_active = 0;
 end_loop:
 		set_current_state(TASK_INTERRUPTIBLE);
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 1027b0cb7fa3..8c811b251d42 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -805,6 +805,10 @@ qlt_plogi_ack_find_add(struct scsi_qla_host *vha, port_id_t *id,
 
 	list_for_each_entry(pla, &vha->plogi_ack_list, list) {
 		if (pla->id.b24 == id->b24) {
+			ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0x210d,
+			    "%s %d %8phC Term INOT due to new INOT",
+			    __func__, __LINE__,
+			    pla->iocb.u.isp24.port_name);
 			qlt_send_term_imm_notif(vha, &pla->iocb, 1);
 			memcpy(&pla->iocb, iocb, sizeof(pla->iocb));
 			return pla;
@@ -982,8 +986,9 @@ void qlt_free_session_done(struct work_struct *work)
 
 			logo.id = sess->d_id;
 			logo.cmd_count = 0;
+			if (!own)
+				qlt_send_first_logo(vha, &logo);
 			sess->send_els_logo = 0;
-			qlt_send_first_logo(vha, &logo);
 		}
 
 		if (sess->logout_on_delete && sess->loop_id != FC_NO_LOOP_ID) {
@@ -1053,7 +1058,6 @@ void qlt_free_session_done(struct work_struct *work)
 	sess->disc_state = DSC_DELETED;
 	sess->fw_login_state = DSC_LS_PORT_UNAVAIL;
 	sess->deleted = QLA_SESS_DELETED;
-	sess->login_retry = vha->hw->login_retry_count;
 
 	if (sess->login_succ && !IS_SW_RESV_ADDR(sess->d_id)) {
 		vha->fcport_count--;
@@ -1073,6 +1077,7 @@ void qlt_free_session_done(struct work_struct *work)
 		struct qlt_plogi_ack_t *con =
 		    sess->plogi_link[QLT_PLOGI_LINK_CONFLICT];
 		struct imm_ntfy_from_isp *iocb;
+		own = sess->plogi_link[QLT_PLOGI_LINK_SAME_WWN];
 
 		if (con) {
 			iocb = &con->iocb;
@@ -1156,7 +1161,7 @@ void qlt_unreg_sess(struct fc_port *sess)
 	if (sess->se_sess)
 		vha->hw->tgt.tgt_ops->clear_nacl_from_fcport_map(sess);
 
-	qla2x00_mark_device_lost(vha, sess, 1, 1);
+	qla2x00_mark_device_lost(vha, sess, 0, 0);
 
 	sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
 	sess->disc_state = DSC_DELETE_PEND;
@@ -3782,7 +3787,7 @@ void qlt_free_cmd(struct qla_tgt_cmd *cmd)
 		return;
 	}
 	cmd->jiffies_at_free = get_jiffies_64();
-	percpu_ida_free(&sess->se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
+	target_free_tag(sess->se_sess, &cmd->se_cmd);
 }
 EXPORT_SYMBOL(qlt_free_cmd);
 
@@ -4145,7 +4150,7 @@ out_term:
 	qlt_send_term_exchange(qpair, NULL, &cmd->atio, 1, 0);
 
 	qlt_decr_num_pend_cmds(vha);
-	percpu_ida_free(&sess->se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
+	target_free_tag(sess->se_sess, &cmd->se_cmd);
 	spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
 
 	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
@@ -4276,9 +4281,9 @@ static struct qla_tgt_cmd *qlt_get_tag(scsi_qla_host_t *vha,
 {
 	struct se_session *se_sess = sess->se_sess;
 	struct qla_tgt_cmd *cmd;
-	int tag;
+	int tag, cpu;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
+	tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
 	if (tag < 0)
 		return NULL;
 
@@ -4291,6 +4296,7 @@ static struct qla_tgt_cmd *qlt_get_tag(scsi_qla_host_t *vha,
 	qlt_incr_num_pend_cmds(vha);
 	cmd->vha = vha;
 	cmd->se_cmd.map_tag = tag;
+	cmd->se_cmd.map_cpu = cpu;
 	cmd->sess = sess;
 	cmd->loop_id = sess->loop_id;
 	cmd->conf_compl_supported = sess->conf_compl_supported;
@@ -4714,6 +4720,10 @@ static int qlt_handle_login(struct scsi_qla_host *vha,
 
 	pla = qlt_plogi_ack_find_add(vha, &port_id, iocb);
 	if (!pla) {
+		ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0xffff,
+		    "%s %d %8phC Term INOT due to mem alloc fail",
+		    __func__, __LINE__,
+		    iocb->u.isp24.port_name);
 		qlt_send_term_imm_notif(vha, iocb, 1);
 		goto out;
 	}
@@ -5293,7 +5303,7 @@ qlt_alloc_qfull_cmd(struct scsi_qla_host *vha,
 	struct fc_port *sess;
 	struct se_session *se_sess;
 	struct qla_tgt_cmd *cmd;
-	int tag;
+	int tag, cpu;
 	unsigned long flags;
 
 	if (unlikely(tgt->tgt_stop)) {
@@ -5325,7 +5335,7 @@ qlt_alloc_qfull_cmd(struct scsi_qla_host *vha,
 
 	se_sess = sess->se_sess;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
+	tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
 	if (tag < 0)
 		return;
 
@@ -5356,6 +5366,7 @@ qlt_alloc_qfull_cmd(struct scsi_qla_host *vha,
 	cmd->reset_count = ha->base_qpair->chip_reset;
 	cmd->q_full = 1;
 	cmd->qpair = ha->base_qpair;
+	cmd->se_cmd.map_cpu = cpu;
 
 	if (qfull) {
 		cmd->q_full = 1;
diff --git a/drivers/scsi/qla2xxx/qla_tmpl.c b/drivers/scsi/qla2xxx/qla_tmpl.c
index 731ca0d8520a..0ccd06f11f12 100644
--- a/drivers/scsi/qla2xxx/qla_tmpl.c
+++ b/drivers/scsi/qla2xxx/qla_tmpl.c
@@ -571,6 +571,15 @@ qla27xx_fwdt_entry_t268(struct scsi_qla_host *vha,
 		}
 		break;
 
+	case T268_BUF_TYPE_REQ_MIRROR:
+	case T268_BUF_TYPE_RSP_MIRROR:
+		/*
+		 * Mirror pointers are not implemented in the
+		 * driver, instead shadow pointers are used by
+		 * the drier. Skip these entries.
+		 */
+		qla27xx_skip_entry(ent, buf);
+		break;
 	default:
 		ql_dbg(ql_dbg_async, vha, 0xd02b,
 		    "%s: unknown buffer %x\n", __func__, ent->t268.buf_type);
@@ -1028,8 +1037,10 @@ qla27xx_fwdump(scsi_qla_host_t *vha, int hardware_locked)
 		ql_log(ql_log_warn, vha, 0xd300,
 		    "Firmware has been previously dumped (%p),"
 		    " -- ignoring request\n", vha->hw->fw_dump);
-	else
+	else {
+		QLA_FW_STOPPED(vha->hw);
 		qla27xx_execute_fwdt_template(vha);
+	}
 
 #ifndef __CHECKER__
 	if (!hardware_locked)
diff --git a/drivers/scsi/qla2xxx/qla_version.h b/drivers/scsi/qla2xxx/qla_version.h
index 1ad7582220c3..3850b28518e5 100644
--- a/drivers/scsi/qla2xxx/qla_version.h
+++ b/drivers/scsi/qla2xxx/qla_version.h
@@ -7,7 +7,7 @@
 /*
  * Driver version
  */
-#define QLA2XXX_VERSION      "10.00.00.07-k"
+#define QLA2XXX_VERSION      "10.00.00.08-k"
 
 #define QLA_DRIVER_MAJOR_VER	10
 #define QLA_DRIVER_MINOR_VER	0
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 7732e9336d43..e03d12a5f986 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -1049,10 +1049,8 @@ static struct configfs_attribute *tcm_qla2xxx_tpg_attrs[] = {
 	NULL,
 };
 
-static struct se_portal_group *tcm_qla2xxx_make_tpg(
-	struct se_wwn *wwn,
-	struct config_group *group,
-	const char *name)
+static struct se_portal_group *tcm_qla2xxx_make_tpg(struct se_wwn *wwn,
+						    const char *name)
 {
 	struct tcm_qla2xxx_lport *lport = container_of(wwn,
 			struct tcm_qla2xxx_lport, lport_wwn);
@@ -1171,10 +1169,8 @@ static struct configfs_attribute *tcm_qla2xxx_npiv_tpg_attrs[] = {
         NULL,
 };
 
-static struct se_portal_group *tcm_qla2xxx_npiv_make_tpg(
-	struct se_wwn *wwn,
-	struct config_group *group,
-	const char *name)
+static struct se_portal_group *tcm_qla2xxx_npiv_make_tpg(struct se_wwn *wwn,
+							 const char *name)
 {
 	struct tcm_qla2xxx_lport *lport = container_of(wwn,
 			struct tcm_qla2xxx_lport, lport_wwn);
@@ -1465,8 +1461,7 @@ static void tcm_qla2xxx_free_session(struct fc_port *sess)
 	}
 	target_wait_for_sess_cmds(se_sess);
 
-	transport_deregister_session_configfs(sess->se_sess);
-	transport_deregister_session(sess->se_sess);
+	target_remove_session(se_sess);
 }
 
 static int tcm_qla2xxx_session_cb(struct se_portal_group *se_tpg,
@@ -1543,7 +1538,7 @@ static int tcm_qla2xxx_check_initiator_node_acl(
 	 * Locate our struct se_node_acl either from an explict NodeACL created
 	 * via ConfigFS, or via running in TPG demo mode.
 	 */
-	se_sess = target_alloc_session(&tpg->se_tpg, num_tags,
+	se_sess = target_setup_session(&tpg->se_tpg, num_tags,
 				       sizeof(struct qla_tgt_cmd),
 				       TARGET_PROT_ALL, port_name,
 				       qlat_sess, tcm_qla2xxx_session_cb);
@@ -1624,9 +1619,6 @@ static void tcm_qla2xxx_update_sess(struct fc_port *sess, port_id_t s_id,
 
 	sess->conf_compl_supported = conf_compl_supported;
 
-	/* Reset logout parameters to default */
-	sess->logout_on_delete = 1;
-	sess->keep_nport_handle = 0;
 }
 
 /*
diff --git a/drivers/scsi/qlogicpti.c b/drivers/scsi/qlogicpti.c
index 8578e566ab41..9d09228eee28 100644
--- a/drivers/scsi/qlogicpti.c
+++ b/drivers/scsi/qlogicpti.c
@@ -959,7 +959,7 @@ static inline void update_can_queue(struct Scsi_Host *host, u_int in_ptr, u_int
 	/* Temporary workaround until bug is found and fixed (one bug has been found
 	   already, but fixing it makes things even worse) -jj */
 	int num_free = QLOGICPTI_REQ_QUEUE_LEN - REQ_QUEUE_DEPTH(in_ptr, out_ptr) - 64;
-	host->can_queue = atomic_read(&host->host_busy) + num_free;
+	host->can_queue = scsi_host_busy(host) + num_free;
 	host->sg_tablesize = QLOGICPTI_MAX_SG(num_free);
 }
 
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 4c60c260c5da..fc1356d101b0 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -162,12 +162,12 @@ void scsi_log_completion(struct scsi_cmnd *cmd, int disposition)
 		    (level > 1)) {
 			scsi_print_result(cmd, "Done", disposition);
 			scsi_print_command(cmd);
-			if (status_byte(cmd->result) & CHECK_CONDITION)
+			if (status_byte(cmd->result) == CHECK_CONDITION)
 				scsi_print_sense(cmd);
 			if (level > 3)
 				scmd_printk(KERN_INFO, cmd,
 					    "scsi host busy %d failed %d\n",
-					    atomic_read(&cmd->device->host->host_busy),
+					    scsi_host_busy(cmd->device->host),
 					    cmd->device->host->host_failed);
 		}
 	}
diff --git a/drivers/scsi/scsi.h b/drivers/scsi/scsi.h
index 6dcc4c685d1d..4fd75a3aff66 100644
--- a/drivers/scsi/scsi.h
+++ b/drivers/scsi/scsi.h
@@ -43,7 +43,4 @@ struct scsi_device;
 struct scsi_target;
 struct scatterlist;
 
-/* obsolete typedef junk. */
-#include "scsi_typedefs.h"
-
 #endif /* _SCSI_H */
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 364e71861bfd..60bcc6df97a9 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -164,29 +164,29 @@ static const char *sdebug_version_date = "20180128";
 #define SDEBUG_OPT_RESET_NOISE		0x2000
 #define SDEBUG_OPT_NO_CDB_NOISE		0x4000
 #define SDEBUG_OPT_HOST_BUSY		0x8000
+#define SDEBUG_OPT_CMD_ABORT		0x10000
 #define SDEBUG_OPT_ALL_NOISE (SDEBUG_OPT_NOISE | SDEBUG_OPT_Q_NOISE | \
 			      SDEBUG_OPT_RESET_NOISE)
 #define SDEBUG_OPT_ALL_INJECTING (SDEBUG_OPT_RECOVERED_ERR | \
 				  SDEBUG_OPT_TRANSPORT_ERR | \
 				  SDEBUG_OPT_DIF_ERR | SDEBUG_OPT_DIX_ERR | \
 				  SDEBUG_OPT_SHORT_TRANSFER | \
-				  SDEBUG_OPT_HOST_BUSY)
+				  SDEBUG_OPT_HOST_BUSY | \
+				  SDEBUG_OPT_CMD_ABORT)
 /* When "every_nth" > 0 then modulo "every_nth" commands:
  *   - a missing response is simulated if SDEBUG_OPT_TIMEOUT is set
  *   - a RECOVERED_ERROR is simulated on successful read and write
  *     commands if SDEBUG_OPT_RECOVERED_ERR is set.
  *   - a TRANSPORT_ERROR is simulated on successful read and write
  *     commands if SDEBUG_OPT_TRANSPORT_ERR is set.
+ *   - similarly for DIF_ERR, DIX_ERR, SHORT_TRANSFER, HOST_BUSY and
+ *     CMD_ABORT
  *
- * When "every_nth" < 0 then after "- every_nth" commands:
- *   - a missing response is simulated if SDEBUG_OPT_TIMEOUT is set
- *   - a RECOVERED_ERROR is simulated on successful read and write
- *     commands if SDEBUG_OPT_RECOVERED_ERR is set.
- *   - a TRANSPORT_ERROR is simulated on successful read and write
- *     commands if _DEBUG_OPT_TRANSPORT_ERR is set.
- * This will continue on every subsequent command until some other action
- * occurs (e.g. the user * writing a new value (other than -1 or 1) to
- * every_nth via sysfs).
+ * When "every_nth" < 0 then after "- every_nth" commands the selected
+ * error will be injected. The error will be injected on every subsequent
+ * command until some other action occurs; for example, the user writing
+ * a new value (other than -1 or 1) to every_nth:
+ *      echo 0 > /sys/bus/pseudo/drivers/scsi_debug/every_nth
  */
 
 /* As indicated in SAM-5 and SPC-4 Unit Attentions (UAs) are returned in
@@ -281,6 +281,7 @@ struct sdebug_defer {
 	int issuing_cpu;
 	bool init_hrt;
 	bool init_wq;
+	bool aborted;	/* true when blk_abort_request() already called */
 	enum sdeb_defer_type defer_t;
 };
 
@@ -296,6 +297,7 @@ struct sdebug_queued_cmd {
 	unsigned int inj_dix:1;
 	unsigned int inj_short:1;
 	unsigned int inj_host_busy:1;
+	unsigned int inj_cmd_abort:1;
 };
 
 struct sdebug_queue {
@@ -3792,6 +3794,7 @@ static struct sdebug_queue *get_queue(struct scsi_cmnd *cmnd)
 /* Queued (deferred) command completions converge here. */
 static void sdebug_q_cmd_complete(struct sdebug_defer *sd_dp)
 {
+	bool aborted = sd_dp->aborted;
 	int qc_idx;
 	int retiring = 0;
 	unsigned long iflags;
@@ -3801,6 +3804,8 @@ static void sdebug_q_cmd_complete(struct sdebug_defer *sd_dp)
 	struct sdebug_dev_info *devip;
 
 	sd_dp->defer_t = SDEB_DEFER_NONE;
+	if (unlikely(aborted))
+		sd_dp->aborted = false;
 	qc_idx = sd_dp->qc_idx;
 	sqp = sdebug_q_arr + sd_dp->sqa_idx;
 	if (sdebug_statistics) {
@@ -3852,6 +3857,11 @@ static void sdebug_q_cmd_complete(struct sdebug_defer *sd_dp)
 			atomic_set(&retired_max_queue, k + 1);
 	}
 	spin_unlock_irqrestore(&sqp->qc_lock, iflags);
+	if (unlikely(aborted)) {
+		if (sdebug_verbose)
+			pr_info("bypassing scsi_done() due to aborted cmd\n");
+		return;
+	}
 	scp->scsi_done(scp); /* callback to mid level */
 }
 
@@ -4312,7 +4322,8 @@ static void setup_inject(struct sdebug_queue *sqp,
 		if (sdebug_every_nth > 0)
 			sqcp->inj_recovered = sqcp->inj_transport
 				= sqcp->inj_dif
-				= sqcp->inj_dix = sqcp->inj_short = 0;
+				= sqcp->inj_dix = sqcp->inj_short
+				= sqcp->inj_host_busy = sqcp->inj_cmd_abort = 0;
 		return;
 	}
 	sqcp->inj_recovered = !!(SDEBUG_OPT_RECOVERED_ERR & sdebug_opts);
@@ -4321,6 +4332,7 @@ static void setup_inject(struct sdebug_queue *sqp,
 	sqcp->inj_dix = !!(SDEBUG_OPT_DIX_ERR & sdebug_opts);
 	sqcp->inj_short = !!(SDEBUG_OPT_SHORT_TRANSFER & sdebug_opts);
 	sqcp->inj_host_busy = !!(SDEBUG_OPT_HOST_BUSY & sdebug_opts);
+	sqcp->inj_cmd_abort = !!(SDEBUG_OPT_CMD_ABORT & sdebug_opts);
 }
 
 /* Complete the processing of the thread that queued a SCSI command to this
@@ -4458,7 +4470,14 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip,
 		if (sdebug_statistics)
 			sd_dp->issuing_cpu = raw_smp_processor_id();
 		sd_dp->defer_t = SDEB_DEFER_WQ;
+		if (unlikely(sqcp->inj_cmd_abort))
+			sd_dp->aborted = true;
 		schedule_work(&sd_dp->ew.work);
+		if (unlikely(sqcp->inj_cmd_abort)) {
+			sdev_printk(KERN_INFO, sdp, "abort request tag %d\n",
+				    cmnd->request->tag);
+			blk_abort_request(cmnd->request);
+		}
 	}
 	if (unlikely((SDEBUG_OPT_Q_NOISE & sdebug_opts) &&
 		     (scsi_result == device_qfull_result)))
@@ -4844,12 +4863,11 @@ static ssize_t fake_rw_store(struct device_driver *ddp, const char *buf,
 					(unsigned long)sdebug_dev_size_mb *
 					1048576;
 
-				fake_storep = vmalloc(sz);
+				fake_storep = vzalloc(sz);
 				if (NULL == fake_storep) {
 					pr_err("out of memory, 9\n");
 					return -ENOMEM;
 				}
-				memset(fake_storep, 0, sz);
 			}
 			sdebug_fake_rw = n;
 		}
@@ -5391,13 +5409,12 @@ static int __init scsi_debug_init(void)
 	}
 
 	if (sdebug_fake_rw == 0) {
-		fake_storep = vmalloc(sz);
+		fake_storep = vzalloc(sz);
 		if (NULL == fake_storep) {
 			pr_err("out of memory, 1\n");
 			ret = -ENOMEM;
 			goto free_q_arr;
 		}
-		memset(fake_storep, 0, sz);
 		if (sdebug_num_parts > 0)
 			sdebug_build_parts(fake_storep, sz);
 	}
@@ -5790,11 +5807,13 @@ static int scsi_debug_queuecommand(struct Scsi_Host *shost,
 fini:
 	if (F_DELAY_OVERR & flags)
 		return schedule_resp(scp, devip, errsts, pfp, 0, 0);
-	else if ((sdebug_jdelay || sdebug_ndelay) && (flags & F_LONG_DELAY)) {
+	else if ((flags & F_LONG_DELAY) && (sdebug_jdelay > 0 ||
+					    sdebug_ndelay > 10000)) {
 		/*
-		 * If any delay is active, for F_SSU_DELAY want at least 1
-		 * second and if sdebug_jdelay>0 want a long delay of that
-		 * many seconds; for F_SYNC_DELAY want 1/20 of that.
+		 * Skip long delays if ndelay <= 10 microseconds. Otherwise
+		 * for Start Stop Unit (SSU) want at least 1 second delay and
+		 * if sdebug_jdelay>1 want a long delay of that many seconds.
+		 * For Synchronize Cache want 1/20 of SSU's delay.
 		 */
 		int jdelay = (sdebug_jdelay < 2) ? 1 : sdebug_jdelay;
 		int denom = (flags & F_SYNC_DELAY) ? 20 : 1;
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 2715cdaa669c..b7a8fdfeb2f4 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -66,7 +66,7 @@ void scsi_eh_wakeup(struct Scsi_Host *shost)
 {
 	lockdep_assert_held(shost->host_lock);
 
-	if (atomic_read(&shost->host_busy) == shost->host_failed) {
+	if (scsi_host_busy(shost) == shost->host_failed) {
 		trace_scsi_eh_wakeup(shost);
 		wake_up_process(shost->ehandler);
 		SCSI_LOG_ERROR_RECOVERY(5, shost_printk(KERN_INFO, shost,
@@ -2169,7 +2169,7 @@ int scsi_error_handler(void *data)
 			break;
 
 		if ((shost->host_failed == 0 && shost->host_eh_scheduled == 0) ||
-		    shost->host_failed != atomic_read(&shost->host_busy)) {
+		    shost->host_failed != scsi_host_busy(shost)) {
 			SCSI_LOG_ERROR_RECOVERY(1,
 				shost_printk(KERN_INFO, shost,
 					     "scsi_eh_%d: sleeping\n",
@@ -2184,7 +2184,7 @@ int scsi_error_handler(void *data)
 				     "scsi_eh_%d: waking up %d/%d/%d\n",
 				     shost->host_no, shost->host_eh_scheduled,
 				     shost->host_failed,
-				     atomic_read(&shost->host_busy)));
+				     scsi_host_busy(shost)));
 
 		/*
 		 * We have a host that is failing for some reason.  Figure out
diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index 0a875491f5a7..cc30fccc1a2e 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -100,8 +100,8 @@ static int ioctl_internal_command(struct scsi_device *sdev, char *cmd,
 	SCSI_LOG_IOCTL(2, sdev_printk(KERN_INFO, sdev,
 				      "Ioctl returned  0x%x\n", result));
 
-	if ((driver_byte(result) & DRIVER_SENSE) &&
-	    (scsi_sense_valid(&sshdr))) {
+	if (driver_byte(result) == DRIVER_SENSE &&
+	    scsi_sense_valid(&sshdr)) {
 		switch (sshdr.sense_key) {
 		case ILLEGAL_REQUEST:
 			if (cmd[0] == ALLOW_MEDIUM_REMOVAL)
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 41e9ac9fc138..0adfb3bce0fd 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -238,7 +238,7 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
 
 
 /**
- * scsi_execute - insert request and wait for the result
+ * __scsi_execute - insert request and wait for the result
  * @sdev:	scsi device
  * @cmd:	scsi command
  * @data_direction: data direction
@@ -255,7 +255,7 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
  * Returns the scsi_cmnd result field if a command was executed, or a negative
  * Linux error code if we didn't get that far.
  */
-int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
+int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 		 int data_direction, void *buffer, unsigned bufflen,
 		 unsigned char *sense, struct scsi_sense_hdr *sshdr,
 		 int timeout, int retries, u64 flags, req_flags_t rq_flags,
@@ -309,7 +309,7 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 
 	return ret;
 }
-EXPORT_SYMBOL(scsi_execute);
+EXPORT_SYMBOL(__scsi_execute);
 
 /*
  * Function:    scsi_init_cmd_errh()
@@ -345,7 +345,8 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost)
 	unsigned long flags;
 
 	rcu_read_lock();
-	atomic_dec(&shost->host_busy);
+	if (!shost->use_blk_mq)
+		atomic_dec(&shost->host_busy);
 	if (unlikely(scsi_host_in_recovery(shost))) {
 		spin_lock_irqsave(shost->host_lock, flags);
 		if (shost->host_failed || shost->host_eh_scheduled)
@@ -371,7 +372,7 @@ void scsi_device_unbusy(struct scsi_device *sdev)
 static void scsi_kick_queue(struct request_queue *q)
 {
 	if (q->mq_ops)
-		blk_mq_start_hw_queues(q);
+		blk_mq_run_hw_queues(q, false);
 	else
 		blk_run_queue(q);
 }
@@ -444,7 +445,12 @@ static inline bool scsi_target_is_busy(struct scsi_target *starget)
 
 static inline bool scsi_host_is_busy(struct Scsi_Host *shost)
 {
-	if (shost->can_queue > 0 &&
+	/*
+	 * blk-mq can handle host queue busy efficiently via host-wide driver
+	 * tag allocation
+	 */
+
+	if (!shost->use_blk_mq && shost->can_queue > 0 &&
 	    atomic_read(&shost->host_busy) >= shost->can_queue)
 		return true;
 	if (atomic_read(&shost->host_blocked) > 0)
@@ -662,6 +668,7 @@ static void scsi_release_bidi_buffers(struct scsi_cmnd *cmd)
 	cmd->request->next_rq->special = NULL;
 }
 
+/* Returns false when no more bytes to process, true if there are more */
 static bool scsi_end_request(struct request *req, blk_status_t error,
 		unsigned int bytes, unsigned int bidi_bytes)
 {
@@ -760,161 +767,39 @@ static blk_status_t scsi_result_to_blk_status(struct scsi_cmnd *cmd, int result)
 	}
 }
 
-/*
- * Function:    scsi_io_completion()
- *
- * Purpose:     Completion processing for block device I/O requests.
- *
- * Arguments:   cmd   - command that is finished.
- *
- * Lock status: Assumed that no lock is held upon entry.
- *
- * Returns:     Nothing
- *
- * Notes:       We will finish off the specified number of sectors.  If we
- *		are done, the command block will be released and the queue
- *		function will be goosed.  If we are not done then we have to
- *		figure out what to do next:
- *
- *		a) We can call scsi_requeue_command().  The request
- *		   will be unprepared and put back on the queue.  Then
- *		   a new command will be created for it.  This should
- *		   be used if we made forward progress, or if we want
- *		   to switch from READ(10) to READ(6) for example.
- *
- *		b) We can call __scsi_queue_insert().  The request will
- *		   be put back on the queue and retried using the same
- *		   command as before, possibly after a delay.
- *
- *		c) We can call scsi_end_request() with -EIO to fail
- *		   the remainder of the request.
- */
-void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
+/* Helper for scsi_io_completion() when "reprep" action required. */
+static void scsi_io_completion_reprep(struct scsi_cmnd *cmd,
+				      struct request_queue *q)
+{
+	/* A new command will be prepared and issued. */
+	if (q->mq_ops) {
+		scsi_mq_requeue_cmd(cmd);
+	} else {
+		/* Unprep request and put it back at head of the queue. */
+		scsi_release_buffers(cmd);
+		scsi_requeue_command(q, cmd);
+	}
+}
+
+/* Helper for scsi_io_completion() when special action required. */
+static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
 {
-	int result = cmd->result;
 	struct request_queue *q = cmd->device->request_queue;
 	struct request *req = cmd->request;
-	blk_status_t error = BLK_STS_OK;
-	struct scsi_sense_hdr sshdr;
-	bool sense_valid = false;
-	int sense_deferred = 0, level = 0;
+	int level = 0;
 	enum {ACTION_FAIL, ACTION_REPREP, ACTION_RETRY,
 	      ACTION_DELAYED_RETRY} action;
 	unsigned long wait_for = (cmd->allowed + 1) * req->timeout;
+	struct scsi_sense_hdr sshdr;
+	bool sense_valid;
+	bool sense_current = true;      /* false implies "deferred sense" */
+	blk_status_t blk_stat;
 
-	if (result) {
-		sense_valid = scsi_command_normalize_sense(cmd, &sshdr);
-		if (sense_valid)
-			sense_deferred = scsi_sense_is_deferred(&sshdr);
-	}
-
-	if (blk_rq_is_passthrough(req)) {
-		if (result) {
-			if (sense_valid) {
-				/*
-				 * SG_IO wants current and deferred errors
-				 */
-				scsi_req(req)->sense_len =
-					min(8 + cmd->sense_buffer[7],
-					    SCSI_SENSE_BUFFERSIZE);
-			}
-			if (!sense_deferred)
-				error = scsi_result_to_blk_status(cmd, result);
-		}
-		/*
-		 * scsi_result_to_blk_status may have reset the host_byte
-		 */
-		scsi_req(req)->result = cmd->result;
-		scsi_req(req)->resid_len = scsi_get_resid(cmd);
-
-		if (scsi_bidi_cmnd(cmd)) {
-			/*
-			 * Bidi commands Must be complete as a whole,
-			 * both sides at once.
-			 */
-			scsi_req(req->next_rq)->resid_len = scsi_in(cmd)->resid;
-			if (scsi_end_request(req, BLK_STS_OK, blk_rq_bytes(req),
-					blk_rq_bytes(req->next_rq)))
-				BUG();
-			return;
-		}
-	} else if (blk_rq_bytes(req) == 0 && result && !sense_deferred) {
-		/*
-		 * Flush commands do not transfers any data, and thus cannot use
-		 * good_bytes != blk_rq_bytes(req) as the signal for an error.
-		 * This sets the error explicitly for the problem case.
-		 */
-		error = scsi_result_to_blk_status(cmd, result);
-	}
-
-	/* no bidi support for !blk_rq_is_passthrough yet */
-	BUG_ON(blk_bidi_rq(req));
-
-	/*
-	 * Next deal with any sectors which we were able to correctly
-	 * handle.
-	 */
-	SCSI_LOG_HLCOMPLETE(1, scmd_printk(KERN_INFO, cmd,
-		"%u sectors total, %d bytes done.\n",
-		blk_rq_sectors(req), good_bytes));
-
-	/*
-	 * Recovered errors need reporting, but they're always treated as
-	 * success, so fiddle the result code here.  For passthrough requests
-	 * we already took a copy of the original into sreq->result which
-	 * is what gets returned to the user
-	 */
-	if (sense_valid && (sshdr.sense_key == RECOVERED_ERROR)) {
-		/* if ATA PASS-THROUGH INFORMATION AVAILABLE skip
-		 * print since caller wants ATA registers. Only occurs on
-		 * SCSI ATA PASS_THROUGH commands when CK_COND=1
-		 */
-		if ((sshdr.asc == 0x0) && (sshdr.ascq == 0x1d))
-			;
-		else if (!(req->rq_flags & RQF_QUIET))
-			scsi_print_sense(cmd);
-		result = 0;
-		/* for passthrough error may be set */
-		error = BLK_STS_OK;
-	}
-	/*
-	 * Another corner case: the SCSI status byte is non-zero but 'good'.
-	 * Example: PRE-FETCH command returns SAM_STAT_CONDITION_MET when
-	 * it is able to fit nominated LBs in its cache (and SAM_STAT_GOOD
-	 * if it can't fit). Treat SAM_STAT_CONDITION_MET and the related
-	 * intermediate statuses (both obsolete in SAM-4) as good.
-	 */
-	if (status_byte(result) && scsi_status_is_good(result)) {
-		result = 0;
-		error = BLK_STS_OK;
-	}
-
-	/*
-	 * special case: failed zero length commands always need to
-	 * drop down into the retry code. Otherwise, if we finished
-	 * all bytes in the request we are done now.
-	 */
-	if (!(blk_rq_bytes(req) == 0 && error) &&
-	    !scsi_end_request(req, error, good_bytes, 0))
-		return;
-
-	/*
-	 * Kill remainder if no retrys.
-	 */
-	if (error && scsi_noretry_cmd(cmd)) {
-		if (scsi_end_request(req, error, blk_rq_bytes(req), 0))
-			BUG();
-		return;
-	}
-
-	/*
-	 * If there had been no error, but we have leftover bytes in the
-	 * requeues just queue the command up again.
-	 */
-	if (result == 0)
-		goto requeue;
+	sense_valid = scsi_command_normalize_sense(cmd, &sshdr);
+	if (sense_valid)
+		sense_current = !scsi_sense_is_deferred(&sshdr);
 
-	error = scsi_result_to_blk_status(cmd, result);
+	blk_stat = scsi_result_to_blk_status(cmd, result);
 
 	if (host_byte(result) == DID_RESET) {
 		/* Third party bus reset or reset for error recovery
@@ -922,7 +807,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 		 * happens.
 		 */
 		action = ACTION_RETRY;
-	} else if (sense_valid && !sense_deferred) {
+	} else if (sense_valid && sense_current) {
 		switch (sshdr.sense_key) {
 		case UNIT_ATTENTION:
 			if (cmd->device->removable) {
@@ -958,18 +843,18 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 				action = ACTION_REPREP;
 			} else if (sshdr.asc == 0x10) /* DIX */ {
 				action = ACTION_FAIL;
-				error = BLK_STS_PROTECTION;
+				blk_stat = BLK_STS_PROTECTION;
 			/* INVALID COMMAND OPCODE or INVALID FIELD IN CDB */
 			} else if (sshdr.asc == 0x20 || sshdr.asc == 0x24) {
 				action = ACTION_FAIL;
-				error = BLK_STS_TARGET;
+				blk_stat = BLK_STS_TARGET;
 			} else
 				action = ACTION_FAIL;
 			break;
 		case ABORTED_COMMAND:
 			action = ACTION_FAIL;
 			if (sshdr.asc == 0x10) /* DIF */
-				error = BLK_STS_PROTECTION;
+				blk_stat = BLK_STS_PROTECTION;
 			break;
 		case NOT_READY:
 			/* If the device is in the process of becoming
@@ -1022,8 +907,9 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 					DEFAULT_RATELIMIT_BURST);
 
 			if (unlikely(scsi_logging_level))
-				level = SCSI_LOG_LEVEL(SCSI_LOG_MLCOMPLETE_SHIFT,
-						       SCSI_LOG_MLCOMPLETE_BITS);
+				level =
+				     SCSI_LOG_LEVEL(SCSI_LOG_MLCOMPLETE_SHIFT,
+						    SCSI_LOG_MLCOMPLETE_BITS);
 
 			/*
 			 * if logging is enabled the failure will be printed
@@ -1031,25 +917,16 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 			 */
 			if (!level && __ratelimit(&_rs)) {
 				scsi_print_result(cmd, NULL, FAILED);
-				if (driver_byte(result) & DRIVER_SENSE)
+				if (driver_byte(result) == DRIVER_SENSE)
 					scsi_print_sense(cmd);
 				scsi_print_command(cmd);
 			}
 		}
-		if (!scsi_end_request(req, error, blk_rq_err_bytes(req), 0))
+		if (!scsi_end_request(req, blk_stat, blk_rq_err_bytes(req), 0))
 			return;
 		/*FALLTHRU*/
 	case ACTION_REPREP:
-	requeue:
-		/* Unprep the request and put it back at the head of the queue.
-		 * A new command will be prepared and issued.
-		 */
-		if (q->mq_ops) {
-			scsi_mq_requeue_cmd(cmd);
-		} else {
-			scsi_release_buffers(cmd);
-			scsi_requeue_command(q, cmd);
-		}
+		scsi_io_completion_reprep(cmd, q);
 		break;
 	case ACTION_RETRY:
 		/* Retry the same command immediately */
@@ -1062,6 +939,185 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	}
 }
 
+/*
+ * Helper for scsi_io_completion() when cmd->result is non-zero. Returns a
+ * new result that may suppress further error checking. Also modifies
+ * *blk_statp in some cases.
+ */
+static int scsi_io_completion_nz_result(struct scsi_cmnd *cmd, int result,
+					blk_status_t *blk_statp)
+{
+	bool sense_valid;
+	bool sense_current = true;	/* false implies "deferred sense" */
+	struct request *req = cmd->request;
+	struct scsi_sense_hdr sshdr;
+
+	sense_valid = scsi_command_normalize_sense(cmd, &sshdr);
+	if (sense_valid)
+		sense_current = !scsi_sense_is_deferred(&sshdr);
+
+	if (blk_rq_is_passthrough(req)) {
+		if (sense_valid) {
+			/*
+			 * SG_IO wants current and deferred errors
+			 */
+			scsi_req(req)->sense_len =
+				min(8 + cmd->sense_buffer[7],
+				    SCSI_SENSE_BUFFERSIZE);
+		}
+		if (sense_current)
+			*blk_statp = scsi_result_to_blk_status(cmd, result);
+	} else if (blk_rq_bytes(req) == 0 && sense_current) {
+		/*
+		 * Flush commands do not transfers any data, and thus cannot use
+		 * good_bytes != blk_rq_bytes(req) as the signal for an error.
+		 * This sets *blk_statp explicitly for the problem case.
+		 */
+		*blk_statp = scsi_result_to_blk_status(cmd, result);
+	}
+	/*
+	 * Recovered errors need reporting, but they're always treated as
+	 * success, so fiddle the result code here.  For passthrough requests
+	 * we already took a copy of the original into sreq->result which
+	 * is what gets returned to the user
+	 */
+	if (sense_valid && (sshdr.sense_key == RECOVERED_ERROR)) {
+		bool do_print = true;
+		/*
+		 * if ATA PASS-THROUGH INFORMATION AVAILABLE [0x0, 0x1d]
+		 * skip print since caller wants ATA registers. Only occurs
+		 * on SCSI ATA PASS_THROUGH commands when CK_COND=1
+		 */
+		if ((sshdr.asc == 0x0) && (sshdr.ascq == 0x1d))
+			do_print = false;
+		else if (req->rq_flags & RQF_QUIET)
+			do_print = false;
+		if (do_print)
+			scsi_print_sense(cmd);
+		result = 0;
+		/* for passthrough, *blk_statp may be set */
+		*blk_statp = BLK_STS_OK;
+	}
+	/*
+	 * Another corner case: the SCSI status byte is non-zero but 'good'.
+	 * Example: PRE-FETCH command returns SAM_STAT_CONDITION_MET when
+	 * it is able to fit nominated LBs in its cache (and SAM_STAT_GOOD
+	 * if it can't fit). Treat SAM_STAT_CONDITION_MET and the related
+	 * intermediate statuses (both obsolete in SAM-4) as good.
+	 */
+	if (status_byte(result) && scsi_status_is_good(result)) {
+		result = 0;
+		*blk_statp = BLK_STS_OK;
+	}
+	return result;
+}
+
+/*
+ * Function:    scsi_io_completion()
+ *
+ * Purpose:     Completion processing for block device I/O requests.
+ *
+ * Arguments:   cmd   - command that is finished.
+ *
+ * Lock status: Assumed that no lock is held upon entry.
+ *
+ * Returns:     Nothing
+ *
+ * Notes:       We will finish off the specified number of sectors.  If we
+ *		are done, the command block will be released and the queue
+ *		function will be goosed.  If we are not done then we have to
+ *		figure out what to do next:
+ *
+ *		a) We can call scsi_requeue_command().  The request
+ *		   will be unprepared and put back on the queue.  Then
+ *		   a new command will be created for it.  This should
+ *		   be used if we made forward progress, or if we want
+ *		   to switch from READ(10) to READ(6) for example.
+ *
+ *		b) We can call __scsi_queue_insert().  The request will
+ *		   be put back on the queue and retried using the same
+ *		   command as before, possibly after a delay.
+ *
+ *		c) We can call scsi_end_request() with blk_stat other than
+ *		   BLK_STS_OK, to fail the remainder of the request.
+ */
+void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
+{
+	int result = cmd->result;
+	struct request_queue *q = cmd->device->request_queue;
+	struct request *req = cmd->request;
+	blk_status_t blk_stat = BLK_STS_OK;
+
+	if (unlikely(result))	/* a nz result may or may not be an error */
+		result = scsi_io_completion_nz_result(cmd, result, &blk_stat);
+
+	if (unlikely(blk_rq_is_passthrough(req))) {
+		/*
+		 * scsi_result_to_blk_status may have reset the host_byte
+		 */
+		scsi_req(req)->result = cmd->result;
+		scsi_req(req)->resid_len = scsi_get_resid(cmd);
+
+		if (unlikely(scsi_bidi_cmnd(cmd))) {
+			/*
+			 * Bidi commands Must be complete as a whole,
+			 * both sides at once.
+			 */
+			scsi_req(req->next_rq)->resid_len = scsi_in(cmd)->resid;
+			if (scsi_end_request(req, BLK_STS_OK, blk_rq_bytes(req),
+					blk_rq_bytes(req->next_rq)))
+				WARN_ONCE(true,
+					  "Bidi command with remaining bytes");
+			return;
+		}
+	}
+
+	/* no bidi support yet, other than in pass-through */
+	if (unlikely(blk_bidi_rq(req))) {
+		WARN_ONCE(true, "Only support bidi command in passthrough");
+		scmd_printk(KERN_ERR, cmd, "Killing bidi command\n");
+		if (scsi_end_request(req, BLK_STS_IOERR, blk_rq_bytes(req),
+				     blk_rq_bytes(req->next_rq)))
+			WARN_ONCE(true, "Bidi command with remaining bytes");
+		return;
+	}
+
+	/*
+	 * Next deal with any sectors which we were able to correctly
+	 * handle.
+	 */
+	SCSI_LOG_HLCOMPLETE(1, scmd_printk(KERN_INFO, cmd,
+		"%u sectors total, %d bytes done.\n",
+		blk_rq_sectors(req), good_bytes));
+
+	/*
+	 * Next deal with any sectors which we were able to correctly
+	 * handle. Failed, zero length commands always need to drop down
+	 * to retry code. Fast path should return in this block.
+	 */
+	if (likely(blk_rq_bytes(req) > 0 || blk_stat == BLK_STS_OK)) {
+		if (likely(!scsi_end_request(req, blk_stat, good_bytes, 0)))
+			return; /* no bytes remaining */
+	}
+
+	/* Kill remainder if no retries. */
+	if (unlikely(blk_stat && scsi_noretry_cmd(cmd))) {
+		if (scsi_end_request(req, blk_stat, blk_rq_bytes(req), 0))
+			WARN_ONCE(true,
+			    "Bytes remaining after failed, no-retry command");
+		return;
+	}
+
+	/*
+	 * If there had been no error, but we have leftover bytes in the
+	 * requeues just queue the command up again.
+	 */
+	if (likely(result == 0))
+		scsi_io_completion_reprep(cmd, q);
+	else
+		scsi_io_completion_action(cmd, result);
+}
+
 static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb)
 {
 	int count;
@@ -1550,7 +1606,10 @@ static inline int scsi_host_queue_ready(struct request_queue *q,
 	if (scsi_host_in_recovery(shost))
 		return 0;
 
-	busy = atomic_inc_return(&shost->host_busy) - 1;
+	if (!shost->use_blk_mq)
+		busy = atomic_inc_return(&shost->host_busy) - 1;
+	else
+		busy = 0;
 	if (atomic_read(&shost->host_blocked) > 0) {
 		if (busy)
 			goto starved;
@@ -1566,7 +1625,7 @@ static inline int scsi_host_queue_ready(struct request_queue *q,
 				     "unblocking host at zero depth\n"));
 	}
 
-	if (shost->can_queue > 0 && busy >= shost->can_queue)
+	if (!shost->use_blk_mq && shost->can_queue > 0 && busy >= shost->can_queue)
 		goto starved;
 	if (shost->host_self_blocked)
 		goto starved;
@@ -1652,7 +1711,9 @@ static void scsi_kill_request(struct request *req, struct request_queue *q)
 	 * with the locks as normal issue path does.
 	 */
 	atomic_inc(&sdev->device_busy);
-	atomic_inc(&shost->host_busy);
+
+	if (!shost->use_blk_mq)
+		atomic_inc(&shost->host_busy);
 	if (starget->can_queue > 0)
 		atomic_inc(&starget->target_busy);
 
@@ -2555,7 +2616,7 @@ scsi_mode_sense(struct scsi_device *sdev, int dbd, int modepage,
 	 * ILLEGAL REQUEST if the code page isn't supported */
 
 	if (use_10_for_ms && !scsi_status_is_good(result) &&
-	    (driver_byte(result) & DRIVER_SENSE)) {
+	    driver_byte(result) == DRIVER_SENSE) {
 		if (scsi_sense_valid(sshdr)) {
 			if ((sshdr->sense_key == ILLEGAL_REQUEST) &&
 			    (sshdr->asc == 0x20) && (sshdr->ascq == 0)) {
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 0880d975eed3..78ca63dfba4a 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -614,7 +614,7 @@ static int scsi_probe_lun(struct scsi_device *sdev, unsigned char *inq_result,
 			 * INQUIRY should not yield UNIT_ATTENTION
 			 * but many buggy devices do so anyway. 
 			 */
-			if ((driver_byte(result) & DRIVER_SENSE) &&
+			if (driver_byte(result) == DRIVER_SENSE &&
 			    scsi_sense_valid(&sshdr)) {
 				if ((sshdr.sense_key == UNIT_ATTENTION) &&
 				    ((sshdr.asc == 0x28) ||
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 7943b762c12d..3aee9464a7bf 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -382,7 +382,7 @@ static ssize_t
 show_host_busy(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct Scsi_Host *shost = class_to_shost(dev);
-	return snprintf(buf, 20, "%d\n", atomic_read(&shost->host_busy));
+	return snprintf(buf, 20, "%d\n", scsi_host_busy(shost));
 }
 static DEVICE_ATTR(host_busy, S_IRUGO, show_host_busy, NULL);
 
@@ -722,8 +722,24 @@ static ssize_t
 sdev_store_delete(struct device *dev, struct device_attribute *attr,
 		  const char *buf, size_t count)
 {
-	if (device_remove_file_self(dev, attr))
-		scsi_remove_device(to_scsi_device(dev));
+	struct kernfs_node *kn;
+
+	kn = sysfs_break_active_protection(&dev->kobj, &attr->attr);
+	WARN_ON_ONCE(!kn);
+	/*
+	 * Concurrent writes into the "delete" sysfs attribute may trigger
+	 * concurrent calls to device_remove_file() and scsi_remove_device().
+	 * device_remove_file() handles concurrent removal calls by
+	 * serializing these and by ignoring the second and later removal
+	 * attempts.  Concurrent calls of scsi_remove_device() are
+	 * serialized. The second and later calls of scsi_remove_device() are
+	 * ignored because the first call of that function changes the device
+	 * state into SDEV_DEL.
+	 */
+	device_remove_file(dev, attr);
+	scsi_remove_device(to_scsi_device(dev));
+	if (kn)
+		sysfs_unbreak_active_protection(kn);
 	return count;
 };
 static DEVICE_ATTR(delete, S_IWUSR, NULL, sdev_store_delete);
diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c
index 13948102ca29..381668fa135d 100644
--- a/drivers/scsi/scsi_transport_fc.c
+++ b/drivers/scsi/scsi_transport_fc.c
@@ -567,7 +567,7 @@ fc_host_post_event(struct Scsi_Host *shost, u32 event_number,
 
 	INIT_SCSI_NL_HDR(&event->snlh, SCSI_NL_TRANSPORT_FC,
 				FC_NL_ASYNC_EVENT, len);
-	event->seconds = get_seconds();
+	event->seconds = ktime_get_real_seconds();
 	event->vendor_id = 0;
 	event->host_no = shost->host_no;
 	event->event_datalen = sizeof(u32);	/* bytes */
@@ -635,7 +635,7 @@ fc_host_post_vendor_event(struct Scsi_Host *shost, u32 event_number,
 
 	INIT_SCSI_NL_HDR(&event->snlh, SCSI_NL_TRANSPORT_FC,
 				FC_NL_ASYNC_EVENT, len);
-	event->seconds = get_seconds();
+	event->seconds = ktime_get_real_seconds();
 	event->vendor_id = vendor_id;
 	event->host_no = shost->host_no;
 	event->event_datalen = data_len;	/* bytes */
diff --git a/drivers/scsi/scsi_transport_spi.c b/drivers/scsi/scsi_transport_spi.c
index 2ca150b16764..40b85b752b79 100644
--- a/drivers/scsi/scsi_transport_spi.c
+++ b/drivers/scsi/scsi_transport_spi.c
@@ -136,7 +136,7 @@ static int spi_execute(struct scsi_device *sdev, const void *cmd,
 				      REQ_FAILFAST_TRANSPORT |
 				      REQ_FAILFAST_DRIVER,
 				      0, NULL);
-		if (!(driver_byte(result) & DRIVER_SENSE) ||
+		if (driver_byte(result) != DRIVER_SENSE ||
 		    sshdr->sense_key != UNIT_ATTENTION)
 			break;
 	}
diff --git a/drivers/scsi/scsi_typedefs.h b/drivers/scsi/scsi_typedefs.h
deleted file mode 100644
index 2ed4c5cb7088..000000000000
--- a/drivers/scsi/scsi_typedefs.h
+++ /dev/null
@@ -1,2 +0,0 @@
-
-typedef struct scsi_cmnd Scsi_Cmnd;
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 9421d9877730..a58cee7a85f2 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1119,7 +1119,7 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 		SCpnt->cmnd[0] = WRITE_6;
 
 		if (blk_integrity_rq(rq))
-			sd_dif_prepare(SCpnt);
+			t10_pi_prepare(SCpnt->request, sdkp->protection_type);
 
 	} else if (rq_data_dir(rq) == READ) {
 		SCpnt->cmnd[0] = READ_6;
@@ -1635,7 +1635,7 @@ static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr)
 	if (res) {
 		sd_print_result(sdkp, "Synchronize Cache(10) failed", res);
 
-		if (driver_byte(res) & DRIVER_SENSE)
+		if (driver_byte(res) == DRIVER_SENSE)
 			sd_print_sense_hdr(sdkp, sshdr);
 
 		/* we need to evaluate the error return  */
@@ -1737,8 +1737,8 @@ static int sd_pr_command(struct block_device *bdev, u8 sa,
 	result = scsi_execute_req(sdev, cmd, DMA_TO_DEVICE, &data, sizeof(data),
 			&sshdr, SD_TIMEOUT, SD_MAX_RETRIES, NULL);
 
-	if ((driver_byte(result) & DRIVER_SENSE) &&
-	    (scsi_sense_valid(&sshdr))) {
+	if (driver_byte(result) == DRIVER_SENSE &&
+	    scsi_sense_valid(&sshdr)) {
 		sdev_printk(KERN_INFO, sdev, "PR command failed: %d\n", result);
 		scsi_print_sense_hdr(sdev, NULL, &sshdr);
 	}
@@ -2028,7 +2028,6 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 				} else {
 					sdkp->device->no_write_same = 1;
 					sd_config_write_same(sdkp);
-					req->__data_len = blk_rq_bytes(req);
 					req->rq_flags |= RQF_QUIET;
 				}
 				break;
@@ -2047,8 +2046,10 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 					   "sd_done: completed %d of %d bytes\n",
 					   good_bytes, scsi_bufflen(SCpnt)));
 
-	if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt))
-		sd_dif_complete(SCpnt, good_bytes);
+	if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt) &&
+	    good_bytes)
+		t10_pi_complete(SCpnt->request, sdkp->protection_type,
+				good_bytes / scsi_prot_interval(SCpnt));
 
 	return good_bytes;
 }
@@ -2095,10 +2096,10 @@ sd_spinup_disk(struct scsi_disk *sdkp)
 			retries++;
 		} while (retries < 3 && 
 			 (!scsi_status_is_good(the_result) ||
-			  ((driver_byte(the_result) & DRIVER_SENSE) &&
+			  ((driver_byte(the_result) == DRIVER_SENSE) &&
 			  sense_valid && sshdr.sense_key == UNIT_ATTENTION)));
 
-		if ((driver_byte(the_result) & DRIVER_SENSE) == 0) {
+		if (driver_byte(the_result) != DRIVER_SENSE) {
 			/* no sense, TUR either succeeded or failed
 			 * with a status error */
 			if(!spintime && !scsi_status_is_good(the_result)) {
@@ -2224,7 +2225,7 @@ static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp,
 			struct scsi_sense_hdr *sshdr, int sense_valid,
 			int the_result)
 {
-	if (driver_byte(the_result) & DRIVER_SENSE)
+	if (driver_byte(the_result) == DRIVER_SENSE)
 		sd_print_sense_hdr(sdkp, sshdr);
 	else
 		sd_printk(KERN_NOTICE, sdkp, "Sense not available.\n");
@@ -3490,7 +3491,7 @@ static int sd_start_stop_device(struct scsi_disk *sdkp, int start)
 			SD_TIMEOUT, SD_MAX_RETRIES, 0, RQF_PM, NULL);
 	if (res) {
 		sd_print_result(sdkp, "Start/Stop Unit failed", res);
-		if (driver_byte(res) & DRIVER_SENSE)
+		if (driver_byte(res) == DRIVER_SENSE)
 			sd_print_sense_hdr(sdkp, &sshdr);
 		if (scsi_sense_valid(&sshdr) &&
 			/* 0x3a is medium not present */
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 392c7d078ae3..a7d4f50b67d4 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -254,21 +254,12 @@ static inline unsigned int sd_prot_flag_mask(unsigned int prot_op)
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 
 extern void sd_dif_config_host(struct scsi_disk *);
-extern void sd_dif_prepare(struct scsi_cmnd *scmd);
-extern void sd_dif_complete(struct scsi_cmnd *, unsigned int);
 
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 
 static inline void sd_dif_config_host(struct scsi_disk *disk)
 {
 }
-static inline int sd_dif_prepare(struct scsi_cmnd *scmd)
-{
-	return 0;
-}
-static inline void sd_dif_complete(struct scsi_cmnd *cmd, unsigned int a)
-{
-}
 
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index 9035380c0dda..db72c82486e3 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -95,116 +95,3 @@ out:
 	blk_integrity_register(disk, &bi);
 }
 
-/*
- * The virtual start sector is the one that was originally submitted
- * by the block layer.	Due to partitioning, MD/DM cloning, etc. the
- * actual physical start sector is likely to be different.  Remap
- * protection information to match the physical LBA.
- *
- * From a protocol perspective there's a slight difference between
- * Type 1 and 2.  The latter uses 32-byte CDBs exclusively, and the
- * reference tag is seeded in the CDB.  This gives us the potential to
- * avoid virt->phys remapping during write.  However, at read time we
- * don't know whether the virt sector is the same as when we wrote it
- * (we could be reading from real disk as opposed to MD/DM device.  So
- * we always remap Type 2 making it identical to Type 1.
- *
- * Type 3 does not have a reference tag so no remapping is required.
- */
-void sd_dif_prepare(struct scsi_cmnd *scmd)
-{
-	const int tuple_sz = sizeof(struct t10_pi_tuple);
-	struct bio *bio;
-	struct scsi_disk *sdkp;
-	struct t10_pi_tuple *pi;
-	u32 phys, virt;
-
-	sdkp = scsi_disk(scmd->request->rq_disk);
-
-	if (sdkp->protection_type == T10_PI_TYPE3_PROTECTION)
-		return;
-
-	phys = scsi_prot_ref_tag(scmd);
-
-	__rq_for_each_bio(bio, scmd->request) {
-		struct bio_integrity_payload *bip = bio_integrity(bio);
-		struct bio_vec iv;
-		struct bvec_iter iter;
-		unsigned int j;
-
-		/* Already remapped? */
-		if (bip->bip_flags & BIP_MAPPED_INTEGRITY)
-			break;
-
-		virt = bip_get_seed(bip) & 0xffffffff;
-
-		bip_for_each_vec(iv, bip, iter) {
-			pi = kmap_atomic(iv.bv_page) + iv.bv_offset;
-
-			for (j = 0; j < iv.bv_len; j += tuple_sz, pi++) {
-
-				if (be32_to_cpu(pi->ref_tag) == virt)
-					pi->ref_tag = cpu_to_be32(phys);
-
-				virt++;
-				phys++;
-			}
-
-			kunmap_atomic(pi);
-		}
-
-		bip->bip_flags |= BIP_MAPPED_INTEGRITY;
-	}
-}
-
-/*
- * Remap physical sector values in the reference tag to the virtual
- * values expected by the block layer.
- */
-void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes)
-{
-	const int tuple_sz = sizeof(struct t10_pi_tuple);
-	struct scsi_disk *sdkp;
-	struct bio *bio;
-	struct t10_pi_tuple *pi;
-	unsigned int j, intervals;
-	u32 phys, virt;
-
-	sdkp = scsi_disk(scmd->request->rq_disk);
-
-	if (sdkp->protection_type == T10_PI_TYPE3_PROTECTION || good_bytes == 0)
-		return;
-
-	intervals = good_bytes / scsi_prot_interval(scmd);
-	phys = scsi_prot_ref_tag(scmd);
-
-	__rq_for_each_bio(bio, scmd->request) {
-		struct bio_integrity_payload *bip = bio_integrity(bio);
-		struct bio_vec iv;
-		struct bvec_iter iter;
-
-		virt = bip_get_seed(bip) & 0xffffffff;
-
-		bip_for_each_vec(iv, bip, iter) {
-			pi = kmap_atomic(iv.bv_page) + iv.bv_offset;
-
-			for (j = 0; j < iv.bv_len; j += tuple_sz, pi++) {
-
-				if (intervals == 0) {
-					kunmap_atomic(pi);
-					return;
-				}
-
-				if (be32_to_cpu(pi->ref_tag) == phys)
-					pi->ref_tag = cpu_to_be32(virt);
-
-				virt++;
-				phys++;
-				intervals--;
-			}
-
-			kunmap_atomic(pi);
-		}
-	}
-}
-
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index 2bf3bf73886e..412c1787dcd9 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -148,12 +148,6 @@ int sd_zbc_setup_report_cmnd(struct scsi_cmnd *cmd)
 	cmd->transfersize = sdkp->device->sector_size;
 	cmd->allowed = 0;
 
-	/*
-	 * Report may return less bytes than requested. Make sure
-	 * to report completion on the entire initial request.
-	 */
-	rq->__data_len = nr_bytes;
-
 	return BLKPREP_OK;
 }
 
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index ba9ba0e04f42..8a254bb46a9b 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1103,15 +1103,6 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 	case SCSI_IOCTL_SEND_COMMAND:
 		if (atomic_read(&sdp->detaching))
 			return -ENODEV;
-		if (read_only) {
-			unsigned char opcode = WRITE_6;
-			Scsi_Ioctl_Command __user *siocp = p;
-
-			if (copy_from_user(&opcode, siocp->data, 1))
-				return -EFAULT;
-			if (sg_allow_access(filp, &opcode))
-				return -EPERM;
-		}
 		return sg_scsi_ioctl(sdp->device->request_queue, NULL, filp->f_mode, p);
 	case SG_SET_DEBUG:
 		result = get_user(val, ip);
@@ -1884,7 +1875,7 @@ sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size)
 	int ret_sz = 0, i, k, rem_sz, num, mx_sc_elems;
 	int sg_tablesize = sfp->parentdp->sg_tablesize;
 	int blk_size = buff_size, order;
-	gfp_t gfp_mask = GFP_ATOMIC | __GFP_COMP | __GFP_NOWARN;
+	gfp_t gfp_mask = GFP_ATOMIC | __GFP_COMP | __GFP_NOWARN | __GFP_ZERO;
 	struct sg_device *sdp = sfp->parentdp;
 
 	if (blk_size < 0)
@@ -1914,9 +1905,6 @@ sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size)
 	if (sdp->device->host->unchecked_isa_dma)
 		gfp_mask |= GFP_DMA;
 
-	if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO))
-		gfp_mask |= __GFP_ZERO;
-
 	order = get_order(num);
 retry:
 	ret_sz = 1 << (PAGE_SHIFT + order);
@@ -1927,7 +1915,7 @@ retry:
 		num = (rem_sz > scatter_elem_sz_prev) ?
 			scatter_elem_sz_prev : rem_sz;
 
-		schp->pages[k] = alloc_pages(gfp_mask | __GFP_ZERO, order);
+		schp->pages[k] = alloc_pages(gfp_mask, order);
 		if (!schp->pages[k])
 			goto out;
 
diff --git a/drivers/scsi/smartpqi/smartpqi.h b/drivers/scsi/smartpqi/smartpqi.h
index dc3a0542a2e8..e97bf2670315 100644
--- a/drivers/scsi/smartpqi/smartpqi.h
+++ b/drivers/scsi/smartpqi/smartpqi.h
@@ -483,6 +483,8 @@ struct pqi_raid_error_info {
 #define CISS_CMD_STATUS_TMF			0xd
 #define CISS_CMD_STATUS_AIO_DISABLED		0xe
 
+#define PQI_CMD_STATUS_ABORTED	CISS_CMD_STATUS_ABORTED
+
 #define PQI_NUM_EVENT_QUEUE_ELEMENTS	32
 #define PQI_EVENT_OQ_ELEMENT_LENGTH	sizeof(struct pqi_event_response)
 
@@ -581,8 +583,8 @@ struct pqi_admin_queues_aligned {
 struct pqi_admin_queues {
 	void		*iq_element_array;
 	void		*oq_element_array;
-	volatile pqi_index_t *iq_ci;
-	volatile pqi_index_t *oq_pi;
+	pqi_index_t	*iq_ci;
+	pqi_index_t __iomem *oq_pi;
 	dma_addr_t	iq_element_array_bus_addr;
 	dma_addr_t	oq_element_array_bus_addr;
 	dma_addr_t	iq_ci_bus_addr;
@@ -606,8 +608,8 @@ struct pqi_queue_group {
 	dma_addr_t	oq_element_array_bus_addr;
 	__le32 __iomem	*iq_pi[2];
 	pqi_index_t	iq_pi_copy[2];
-	volatile pqi_index_t *iq_ci[2];
-	volatile pqi_index_t *oq_pi;
+	pqi_index_t __iomem	*iq_ci[2];
+	pqi_index_t __iomem	*oq_pi;
 	dma_addr_t	iq_ci_bus_addr[2];
 	dma_addr_t	oq_pi_bus_addr;
 	__le32 __iomem	*oq_ci;
@@ -620,7 +622,7 @@ struct pqi_event_queue {
 	u16		oq_id;
 	u16		int_msg_num;
 	void		*oq_element_array;
-	volatile pqi_index_t *oq_pi;
+	pqi_index_t __iomem	*oq_pi;
 	dma_addr_t	oq_element_array_bus_addr;
 	dma_addr_t	oq_pi_bus_addr;
 	__le32 __iomem	*oq_ci;
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index b78d20b74ed8..2112ea6723c6 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -40,11 +40,11 @@
 #define BUILD_TIMESTAMP
 #endif
 
-#define DRIVER_VERSION		"1.1.4-115"
+#define DRIVER_VERSION		"1.1.4-130"
 #define DRIVER_MAJOR		1
 #define DRIVER_MINOR		1
 #define DRIVER_RELEASE		4
-#define DRIVER_REVISION		115
+#define DRIVER_REVISION		130
 
 #define DRIVER_NAME		"Microsemi PQI Driver (v" \
 				DRIVER_VERSION BUILD_TIMESTAMP ")"
@@ -1197,20 +1197,30 @@ no_buffer:
 	device->volume_offline = volume_offline;
 }
 
+#define PQI_INQUIRY_PAGE0_RETRIES	3
+
 static int pqi_get_device_info(struct pqi_ctrl_info *ctrl_info,
 	struct pqi_scsi_dev *device)
 {
 	int rc;
 	u8 *buffer;
+	unsigned int retries;
 
 	buffer = kmalloc(64, GFP_KERNEL);
 	if (!buffer)
 		return -ENOMEM;
 
 	/* Send an inquiry to the device to see what it is. */
-	rc = pqi_scsi_inquiry(ctrl_info, device->scsi3addr, 0, buffer, 64);
-	if (rc)
-		goto out;
+	for (retries = 0;;) {
+		rc = pqi_scsi_inquiry(ctrl_info, device->scsi3addr, 0,
+			buffer, 64);
+		if (rc == 0)
+			break;
+		if (pqi_is_logical_device(device) ||
+			rc != PQI_CMD_STATUS_ABORTED ||
+			++retries > PQI_INQUIRY_PAGE0_RETRIES)
+			goto out;
+	}
 
 	scsi_sanitize_inquiry_string(&buffer[8], 8);
 	scsi_sanitize_inquiry_string(&buffer[16], 16);
@@ -2693,7 +2703,7 @@ static unsigned int pqi_process_io_intr(struct pqi_ctrl_info *ctrl_info,
 	oq_ci = queue_group->oq_ci_copy;
 
 	while (1) {
-		oq_pi = *queue_group->oq_pi;
+		oq_pi = readl(queue_group->oq_pi);
 		if (oq_pi == oq_ci)
 			break;
 
@@ -2784,7 +2794,7 @@ static void pqi_send_event_ack(struct pqi_ctrl_info *ctrl_info,
 		spin_lock_irqsave(&queue_group->submit_lock[RAID_PATH], flags);
 
 		iq_pi = queue_group->iq_pi_copy[RAID_PATH];
-		iq_ci = *queue_group->iq_ci[RAID_PATH];
+		iq_ci = readl(queue_group->iq_ci[RAID_PATH]);
 
 		if (pqi_num_elements_free(iq_pi, iq_ci,
 			ctrl_info->num_elements_per_iq))
@@ -2943,7 +2953,7 @@ static unsigned int pqi_process_event_intr(struct pqi_ctrl_info *ctrl_info)
 	oq_ci = event_queue->oq_ci_copy;
 
 	while (1) {
-		oq_pi = *event_queue->oq_pi;
+		oq_pi = readl(event_queue->oq_pi);
 		if (oq_pi == oq_ci)
 			break;
 
@@ -3167,7 +3177,7 @@ static int pqi_alloc_operational_queues(struct pqi_ctrl_info *ctrl_info)
 	size_t element_array_length_per_iq;
 	size_t element_array_length_per_oq;
 	void *element_array;
-	void *next_queue_index;
+	void __iomem *next_queue_index;
 	void *aligned_pointer;
 	unsigned int num_inbound_queues;
 	unsigned int num_outbound_queues;
@@ -3263,7 +3273,7 @@ static int pqi_alloc_operational_queues(struct pqi_ctrl_info *ctrl_info)
 	element_array += PQI_NUM_EVENT_QUEUE_ELEMENTS *
 		PQI_EVENT_OQ_ELEMENT_LENGTH;
 
-	next_queue_index = PTR_ALIGN(element_array,
+	next_queue_index = (void __iomem *)PTR_ALIGN(element_array,
 		PQI_OPERATIONAL_INDEX_ALIGNMENT);
 
 	for (i = 0; i < ctrl_info->num_queue_groups; i++) {
@@ -3271,21 +3281,24 @@ static int pqi_alloc_operational_queues(struct pqi_ctrl_info *ctrl_info)
 		queue_group->iq_ci[RAID_PATH] = next_queue_index;
 		queue_group->iq_ci_bus_addr[RAID_PATH] =
 			ctrl_info->queue_memory_base_dma_handle +
-			(next_queue_index - ctrl_info->queue_memory_base);
+			(next_queue_index -
+			(void __iomem *)ctrl_info->queue_memory_base);
 		next_queue_index += sizeof(pqi_index_t);
 		next_queue_index = PTR_ALIGN(next_queue_index,
 			PQI_OPERATIONAL_INDEX_ALIGNMENT);
 		queue_group->iq_ci[AIO_PATH] = next_queue_index;
 		queue_group->iq_ci_bus_addr[AIO_PATH] =
 			ctrl_info->queue_memory_base_dma_handle +
-			(next_queue_index - ctrl_info->queue_memory_base);
+			(next_queue_index -
+			(void __iomem *)ctrl_info->queue_memory_base);
 		next_queue_index += sizeof(pqi_index_t);
 		next_queue_index = PTR_ALIGN(next_queue_index,
 			PQI_OPERATIONAL_INDEX_ALIGNMENT);
 		queue_group->oq_pi = next_queue_index;
 		queue_group->oq_pi_bus_addr =
 			ctrl_info->queue_memory_base_dma_handle +
-			(next_queue_index - ctrl_info->queue_memory_base);
+			(next_queue_index -
+			(void __iomem *)ctrl_info->queue_memory_base);
 		next_queue_index += sizeof(pqi_index_t);
 		next_queue_index = PTR_ALIGN(next_queue_index,
 			PQI_OPERATIONAL_INDEX_ALIGNMENT);
@@ -3294,7 +3307,8 @@ static int pqi_alloc_operational_queues(struct pqi_ctrl_info *ctrl_info)
 	ctrl_info->event_queue.oq_pi = next_queue_index;
 	ctrl_info->event_queue.oq_pi_bus_addr =
 		ctrl_info->queue_memory_base_dma_handle +
-		(next_queue_index - ctrl_info->queue_memory_base);
+		(next_queue_index -
+		(void __iomem *)ctrl_info->queue_memory_base);
 
 	return 0;
 }
@@ -3368,7 +3382,8 @@ static int pqi_alloc_admin_queues(struct pqi_ctrl_info *ctrl_info)
 	admin_queues->oq_element_array =
 		&admin_queues_aligned->oq_element_array;
 	admin_queues->iq_ci = &admin_queues_aligned->iq_ci;
-	admin_queues->oq_pi = &admin_queues_aligned->oq_pi;
+	admin_queues->oq_pi =
+		(pqi_index_t __iomem *)&admin_queues_aligned->oq_pi;
 
 	admin_queues->iq_element_array_bus_addr =
 		ctrl_info->admin_queue_memory_base_dma_handle +
@@ -3384,8 +3399,8 @@ static int pqi_alloc_admin_queues(struct pqi_ctrl_info *ctrl_info)
 		ctrl_info->admin_queue_memory_base);
 	admin_queues->oq_pi_bus_addr =
 		ctrl_info->admin_queue_memory_base_dma_handle +
-		((void *)admin_queues->oq_pi -
-		ctrl_info->admin_queue_memory_base);
+		((void __iomem *)admin_queues->oq_pi -
+		(void __iomem *)ctrl_info->admin_queue_memory_base);
 
 	return 0;
 }
@@ -3486,7 +3501,7 @@ static int pqi_poll_for_admin_response(struct pqi_ctrl_info *ctrl_info,
 	timeout = (PQI_ADMIN_REQUEST_TIMEOUT_SECS * HZ) + jiffies;
 
 	while (1) {
-		oq_pi = *admin_queues->oq_pi;
+		oq_pi = readl(admin_queues->oq_pi);
 		if (oq_pi != oq_ci)
 			break;
 		if (time_after(jiffies, timeout)) {
@@ -3545,7 +3560,7 @@ static void pqi_start_io(struct pqi_ctrl_info *ctrl_info,
 			DIV_ROUND_UP(iu_length,
 				PQI_OPERATIONAL_IQ_ELEMENT_LENGTH);
 
-		iq_ci = *queue_group->iq_ci[path];
+		iq_ci = readl(queue_group->iq_ci[path]);
 
 		if (num_elements_needed > pqi_num_elements_free(iq_pi, iq_ci,
 			ctrl_info->num_elements_per_iq))
@@ -3621,29 +3636,24 @@ static void pqi_raid_synchronous_complete(struct pqi_io_request *io_request,
 	complete(waiting);
 }
 
-static int pqi_submit_raid_request_synchronous_with_io_request(
-	struct pqi_ctrl_info *ctrl_info, struct pqi_io_request *io_request,
-	unsigned long timeout_msecs)
+static int pqi_process_raid_io_error_synchronous(struct pqi_raid_error_info
+						*error_info)
 {
-	int rc = 0;
-	DECLARE_COMPLETION_ONSTACK(wait);
+	int rc = -EIO;
 
-	io_request->io_complete_callback = pqi_raid_synchronous_complete;
-	io_request->context = &wait;
-
-	pqi_start_io(ctrl_info,
-		&ctrl_info->queue_groups[PQI_DEFAULT_QUEUE_GROUP], RAID_PATH,
-		io_request);
-
-	if (timeout_msecs == NO_TIMEOUT) {
-		pqi_wait_for_completion_io(ctrl_info, &wait);
-	} else {
-		if (!wait_for_completion_io_timeout(&wait,
-			msecs_to_jiffies(timeout_msecs))) {
-			dev_warn(&ctrl_info->pci_dev->dev,
-				"command timed out\n");
-			rc = -ETIMEDOUT;
-		}
+	switch (error_info->data_out_result) {
+	case PQI_DATA_IN_OUT_GOOD:
+		if (error_info->status == SAM_STAT_GOOD)
+			rc = 0;
+		break;
+	case PQI_DATA_IN_OUT_UNDERFLOW:
+		if (error_info->status == SAM_STAT_GOOD ||
+			error_info->status == SAM_STAT_CHECK_CONDITION)
+			rc = 0;
+		break;
+	case PQI_DATA_IN_OUT_ABORTED:
+		rc = PQI_CMD_STATUS_ABORTED;
+		break;
 	}
 
 	return rc;
@@ -3653,11 +3663,12 @@ static int pqi_submit_raid_request_synchronous(struct pqi_ctrl_info *ctrl_info,
 	struct pqi_iu_header *request, unsigned int flags,
 	struct pqi_raid_error_info *error_info, unsigned long timeout_msecs)
 {
-	int rc;
+	int rc = 0;
 	struct pqi_io_request *io_request;
 	unsigned long start_jiffies;
 	unsigned long msecs_blocked;
 	size_t iu_length;
+	DECLARE_COMPLETION_ONSTACK(wait);
 
 	/*
 	 * Note that specifying PQI_SYNC_FLAGS_INTERRUPTABLE and a timeout value
@@ -3686,11 +3697,13 @@ static int pqi_submit_raid_request_synchronous(struct pqi_ctrl_info *ctrl_info,
 	pqi_ctrl_busy(ctrl_info);
 	timeout_msecs = pqi_wait_if_ctrl_blocked(ctrl_info, timeout_msecs);
 	if (timeout_msecs == 0) {
+		pqi_ctrl_unbusy(ctrl_info);
 		rc = -ETIMEDOUT;
 		goto out;
 	}
 
 	if (pqi_ctrl_offline(ctrl_info)) {
+		pqi_ctrl_unbusy(ctrl_info);
 		rc = -ENXIO;
 		goto out;
 	}
@@ -3708,8 +3721,25 @@ static int pqi_submit_raid_request_synchronous(struct pqi_ctrl_info *ctrl_info,
 		PQI_REQUEST_HEADER_LENGTH;
 	memcpy(io_request->iu, request, iu_length);
 
-	rc = pqi_submit_raid_request_synchronous_with_io_request(ctrl_info,
-		io_request, timeout_msecs);
+	io_request->io_complete_callback = pqi_raid_synchronous_complete;
+	io_request->context = &wait;
+
+	pqi_start_io(ctrl_info,
+		&ctrl_info->queue_groups[PQI_DEFAULT_QUEUE_GROUP], RAID_PATH,
+		io_request);
+
+	pqi_ctrl_unbusy(ctrl_info);
+
+	if (timeout_msecs == NO_TIMEOUT) {
+		pqi_wait_for_completion_io(ctrl_info, &wait);
+	} else {
+		if (!wait_for_completion_io_timeout(&wait,
+			msecs_to_jiffies(timeout_msecs))) {
+			dev_warn(&ctrl_info->pci_dev->dev,
+				"command timed out\n");
+			rc = -ETIMEDOUT;
+		}
+	}
 
 	if (error_info) {
 		if (io_request->error_info)
@@ -3718,25 +3748,13 @@ static int pqi_submit_raid_request_synchronous(struct pqi_ctrl_info *ctrl_info,
 		else
 			memset(error_info, 0, sizeof(*error_info));
 	} else if (rc == 0 && io_request->error_info) {
-		u8 scsi_status;
-		struct pqi_raid_error_info *raid_error_info;
-
-		raid_error_info = io_request->error_info;
-		scsi_status = raid_error_info->status;
-
-		if (scsi_status == SAM_STAT_CHECK_CONDITION &&
-			raid_error_info->data_out_result ==
-			PQI_DATA_IN_OUT_UNDERFLOW)
-			scsi_status = SAM_STAT_GOOD;
-
-		if (scsi_status != SAM_STAT_GOOD)
-			rc = -EIO;
+		rc = pqi_process_raid_io_error_synchronous(
+			io_request->error_info);
 	}
 
 	pqi_free_io_request(io_request);
 
 out:
-	pqi_ctrl_unbusy(ctrl_info);
 	up(&ctrl_info->sync_request_sem);
 
 	return rc;
@@ -5041,7 +5059,7 @@ static int pqi_wait_until_inbound_queues_empty(struct pqi_ctrl_info *ctrl_info)
 			iq_pi = queue_group->iq_pi_copy[path];
 
 			while (1) {
-				iq_ci = *queue_group->iq_ci[path];
+				iq_ci = readl(queue_group->iq_ci[path]);
 				if (iq_ci == iq_pi)
 					break;
 				pqi_check_ctrl_health(ctrl_info);
@@ -6230,20 +6248,20 @@ static void pqi_reinit_queues(struct pqi_ctrl_info *ctrl_info)
 	admin_queues = &ctrl_info->admin_queues;
 	admin_queues->iq_pi_copy = 0;
 	admin_queues->oq_ci_copy = 0;
-	*admin_queues->oq_pi = 0;
+	writel(0, admin_queues->oq_pi);
 
 	for (i = 0; i < ctrl_info->num_queue_groups; i++) {
 		ctrl_info->queue_groups[i].iq_pi_copy[RAID_PATH] = 0;
 		ctrl_info->queue_groups[i].iq_pi_copy[AIO_PATH] = 0;
 		ctrl_info->queue_groups[i].oq_ci_copy = 0;
 
-		*ctrl_info->queue_groups[i].iq_ci[RAID_PATH] = 0;
-		*ctrl_info->queue_groups[i].iq_ci[AIO_PATH] = 0;
-		*ctrl_info->queue_groups[i].oq_pi = 0;
+		writel(0, ctrl_info->queue_groups[i].iq_ci[RAID_PATH]);
+		writel(0, ctrl_info->queue_groups[i].iq_ci[AIO_PATH]);
+		writel(0, ctrl_info->queue_groups[i].oq_pi);
 	}
 
 	event_queue = &ctrl_info->event_queue;
-	*event_queue->oq_pi = 0;
+	writel(0, event_queue->oq_pi);
 	event_queue->oq_ci_copy = 0;
 }
 
@@ -6826,6 +6844,18 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1bd4, 0x004a)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1bd4, 0x004b)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1bd4, 0x004c)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       PCI_VENDOR_ID_ADAPTEC2, 0x0110)
 	},
 	{
@@ -6950,6 +6980,10 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       PCI_VENDOR_ID_ADVANTECH, 0x8312)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       PCI_VENDOR_ID_DELL, 0x1fe0)
 	},
 	{
diff --git a/drivers/scsi/snic/snic_debugfs.c b/drivers/scsi/snic/snic_debugfs.c
index 269ddf791a73..0abe17c1a73b 100644
--- a/drivers/scsi/snic/snic_debugfs.c
+++ b/drivers/scsi/snic/snic_debugfs.c
@@ -200,7 +200,7 @@ snic_stats_show(struct seq_file *sfp, void *data)
 {
 	struct snic *snic = (struct snic *) sfp->private;
 	struct snic_stats *stats = &snic->s_stats;
-	struct timespec last_isr_tms, last_ack_tms;
+	struct timespec64 last_isr_tms, last_ack_tms;
 	u64 maxio_tm;
 	int i;
 
@@ -312,12 +312,12 @@ snic_stats_show(struct seq_file *sfp, void *data)
 		   "\t\t Other Statistics\n"
 		   "\n---------------------------------------------\n");
 
-	jiffies_to_timespec(stats->misc.last_isr_time, &last_isr_tms);
-	jiffies_to_timespec(stats->misc.last_ack_time, &last_ack_tms);
+	jiffies_to_timespec64(stats->misc.last_isr_time, &last_isr_tms);
+	jiffies_to_timespec64(stats->misc.last_ack_time, &last_ack_tms);
 
 	seq_printf(sfp,
-		   "Last ISR Time               : %llu (%8lu.%8lu)\n"
-		   "Last Ack Time               : %llu (%8lu.%8lu)\n"
+		   "Last ISR Time               : %llu (%8llu.%09lu)\n"
+		   "Last Ack Time               : %llu (%8llu.%09lu)\n"
 		   "Ack ISRs                    : %llu\n"
 		   "IO Cmpl ISRs                : %llu\n"
 		   "Err Notify ISRs             : %llu\n"
diff --git a/drivers/scsi/snic/snic_trc.c b/drivers/scsi/snic/snic_trc.c
index f00ebf4717e0..fc60c933d6c0 100644
--- a/drivers/scsi/snic/snic_trc.c
+++ b/drivers/scsi/snic/snic_trc.c
@@ -65,12 +65,12 @@ static int
 snic_fmt_trc_data(struct snic_trc_data *td, char *buf, int buf_sz)
 {
 	int len = 0;
-	struct timespec tmspec;
+	struct timespec64 tmspec;
 
-	jiffies_to_timespec(td->ts, &tmspec);
+	jiffies_to_timespec64(td->ts, &tmspec);
 
 	len += snprintf(buf, buf_sz,
-			"%lu.%10lu %-25s %3d %4x %16llx %16llx %16llx %16llx %16llx\n",
+			"%llu.%09lu %-25s %3d %4x %16llx %16llx %16llx %16llx %16llx\n",
 			tmspec.tv_sec,
 			tmspec.tv_nsec,
 			td->fn,
diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c
index 35fab1e18adc..ffcf902da390 100644
--- a/drivers/scsi/sr_ioctl.c
+++ b/drivers/scsi/sr_ioctl.c
@@ -186,14 +186,13 @@ static int sr_play_trkind(struct cdrom_device_info *cdi,
 int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 {
 	struct scsi_device *SDev;
-	struct scsi_sense_hdr sshdr;
+	struct scsi_sense_hdr local_sshdr, *sshdr = &local_sshdr;
 	int result, err = 0, retries = 0;
-	unsigned char sense_buffer[SCSI_SENSE_BUFFERSIZE], *senseptr = NULL;
 
 	SDev = cd->device;
 
-	if (cgc->sense)
-		senseptr = sense_buffer;
+	if (cgc->sshdr)
+		sshdr = cgc->sshdr;
 
       retry:
 	if (!scsi_block_when_processing_errors(SDev)) {
@@ -202,15 +201,12 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 	}
 
 	result = scsi_execute(SDev, cgc->cmd, cgc->data_direction,
-			      cgc->buffer, cgc->buflen, senseptr, &sshdr,
+			      cgc->buffer, cgc->buflen, NULL, sshdr,
 			      cgc->timeout, IOCTL_RETRIES, 0, 0, NULL);
 
-	if (cgc->sense)
-		memcpy(cgc->sense, sense_buffer, sizeof(*cgc->sense));
-
 	/* Minimal error checking.  Ignore cases we know about, and report the rest. */
 	if (driver_byte(result) != 0) {
-		switch (sshdr.sense_key) {
+		switch (sshdr->sense_key) {
 		case UNIT_ATTENTION:
 			SDev->changed = 1;
 			if (!cgc->quiet)
@@ -221,8 +217,8 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 			err = -ENOMEDIUM;
 			break;
 		case NOT_READY:	/* This happens if there is no disc in drive */
-			if (sshdr.asc == 0x04 &&
-			    sshdr.ascq == 0x01) {
+			if (sshdr->asc == 0x04 &&
+			    sshdr->ascq == 0x01) {
 				/* sense: Logical unit is in process of becoming ready */
 				if (!cgc->quiet)
 					sr_printk(KERN_INFO, cd,
@@ -245,8 +241,8 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 			break;
 		case ILLEGAL_REQUEST:
 			err = -EIO;
-			if (sshdr.asc == 0x20 &&
-			    sshdr.ascq == 0x00)
+			if (sshdr->asc == 0x20 &&
+			    sshdr->ascq == 0x00)
 				/* sense: Invalid command operation code */
 				err = -EDRIVE_CANT_DO_THIS;
 			break;
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 50c66ccc4b41..307df2fa39a3 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -828,11 +828,8 @@ static int st_flush_write_buffer(struct scsi_tape * STp)
 static int flush_buffer(struct scsi_tape *STp, int seek_next)
 {
 	int backspace, result;
-	struct st_buffer *STbuffer;
 	struct st_partstat *STps;
 
-	STbuffer = STp->buffer;
-
 	/*
 	 * If there was a bus reset, block further access
 	 * to this device.
diff --git a/drivers/scsi/sym53c8xx_2/sym_fw.c b/drivers/scsi/sym53c8xx_2/sym_fw.c
index 190770bdc194..91db17727963 100644
--- a/drivers/scsi/sym53c8xx_2/sym_fw.c
+++ b/drivers/scsi/sym53c8xx_2/sym_fw.c
@@ -295,10 +295,8 @@ static void
 sym_fw1_setup(struct sym_hcb *np, struct sym_fw *fw)
 {
 	struct sym_fw1a_scr *scripta0;
-	struct sym_fw1b_scr *scriptb0;
 
 	scripta0 = (struct sym_fw1a_scr *) np->scripta0;
-	scriptb0 = (struct sym_fw1b_scr *) np->scriptb0;
 
 	/*
 	 *  Fill variable parts in scripts.
@@ -319,10 +317,8 @@ static void
 sym_fw2_setup(struct sym_hcb *np, struct sym_fw *fw)
 {
 	struct sym_fw2a_scr *scripta0;
-	struct sym_fw2b_scr *scriptb0;
 
 	scripta0 = (struct sym_fw2a_scr *) np->scripta0;
-	scriptb0 = (struct sym_fw2b_scr *) np->scriptb0;
 
 	/*
 	 *  Fill variable parts in scripts.
diff --git a/drivers/scsi/sym53c8xx_2/sym_glue.c b/drivers/scsi/sym53c8xx_2/sym_glue.c
index 7320d5fe4cbc..5f10aa9bad9b 100644
--- a/drivers/scsi/sym53c8xx_2/sym_glue.c
+++ b/drivers/scsi/sym53c8xx_2/sym_glue.c
@@ -252,7 +252,7 @@ void sym_set_cam_result_error(struct sym_hcb *np, struct sym_ccb *cp, int resid)
 		cam_status = sym_xerr_cam_status(DID_ERROR, cp->xerr_status);
 	}
 	scsi_set_resid(cmd, resid);
-	cmd->result = (drv_status << 24) + (cam_status << 16) + scsi_status;
+	cmd->result = (drv_status << 24) | (cam_status << 16) | scsi_status;
 }
 
 static int sym_scatter(struct sym_hcb *np, struct sym_ccb *cp, struct scsi_cmnd *cmd)
diff --git a/drivers/scsi/sym53c8xx_2/sym_glue.h b/drivers/scsi/sym53c8xx_2/sym_glue.h
index 805369521df8..e34801ae5d69 100644
--- a/drivers/scsi/sym53c8xx_2/sym_glue.h
+++ b/drivers/scsi/sym53c8xx_2/sym_glue.h
@@ -256,7 +256,7 @@ sym_get_cam_status(struct scsi_cmnd *cmd)
 static inline void sym_set_cam_result_ok(struct sym_ccb *cp, struct scsi_cmnd *cmd, int resid)
 {
 	scsi_set_resid(cmd, resid);
-	cmd->result = (((DID_OK) << 16) + ((cp->ssss_status) & 0x7f));
+	cmd->result = (DID_OK << 16) | (cp->ssss_status & 0x7f);
 }
 void sym_set_cam_result_error(struct sym_hcb *np, struct sym_ccb *cp, int resid);
 
diff --git a/drivers/scsi/sym53c8xx_2/sym_hipd.c b/drivers/scsi/sym53c8xx_2/sym_hipd.c
index 378af306fda1..bd3f6e2d6834 100644
--- a/drivers/scsi/sym53c8xx_2/sym_hipd.c
+++ b/drivers/scsi/sym53c8xx_2/sym_hipd.c
@@ -3855,7 +3855,7 @@ out_reject:
 
 int sym_compute_residual(struct sym_hcb *np, struct sym_ccb *cp)
 {
-	int dp_sg, dp_sgmin, resid = 0;
+	int dp_sg, resid = 0;
 	int dp_ofs = 0;
 
 	/*
@@ -3902,7 +3902,6 @@ int sym_compute_residual(struct sym_hcb *np, struct sym_ccb *cp)
 	 *  We are now full comfortable in the computation 
 	 *  of the data residual (2's complement).
 	 */
-	dp_sgmin = SYM_CONF_MAX_SG - cp->segments;
 	resid = -cp->ext_ofs;
 	for (dp_sg = cp->ext_sg; dp_sg < SYM_CONF_MAX_SG; ++dp_sg) {
 		u_int tmp = scr_to_cpu(cp->phys.data[dp_sg].size);
diff --git a/drivers/scsi/ufs/Kconfig b/drivers/scsi/ufs/Kconfig
index e27b4d4e6ae2..e09fe6ab3572 100644
--- a/drivers/scsi/ufs/Kconfig
+++ b/drivers/scsi/ufs/Kconfig
@@ -100,3 +100,12 @@ config SCSI_UFS_QCOM
 
 	  Select this if you have UFS controller on QCOM chipset.
 	  If unsure, say N.
+
+config SCSI_UFS_HISI
+	tristate "Hisilicon specific hooks to UFS controller platform driver"
+	depends on (ARCH_HISI || COMPILE_TEST) && SCSI_UFSHCD_PLATFORM
+	---help---
+	  This selects the Hisilicon specific additions to UFSHCD platform driver.
+
+	  Select this if you have UFS controller on Hisilicon chipset.
+	  If unsure, say N.
diff --git a/drivers/scsi/ufs/Makefile b/drivers/scsi/ufs/Makefile
index 918f5791202d..2c50f03d8c4a 100644
--- a/drivers/scsi/ufs/Makefile
+++ b/drivers/scsi/ufs/Makefile
@@ -7,3 +7,4 @@ obj-$(CONFIG_SCSI_UFSHCD) += ufshcd-core.o
 ufshcd-core-objs := ufshcd.o ufs-sysfs.o
 obj-$(CONFIG_SCSI_UFSHCD_PCI) += ufshcd-pci.o
 obj-$(CONFIG_SCSI_UFSHCD_PLATFORM) += ufshcd-pltfrm.o
+obj-$(CONFIG_SCSI_UFS_HISI) += ufs-hisi.o
diff --git a/drivers/scsi/ufs/ufs-hisi.c b/drivers/scsi/ufs/ufs-hisi.c
new file mode 100644
index 000000000000..46df707e6f2c
--- /dev/null
+++ b/drivers/scsi/ufs/ufs-hisi.c
@@ -0,0 +1,619 @@
+/*
+ * HiSilicon Hixxxx UFS Driver
+ *
+ * Copyright (c) 2016-2017 Linaro Ltd.
+ * Copyright (c) 2016-2017 HiSilicon Technologies Co., Ltd.
+ *
+ * Released under the GPLv2 only.
+ * SPDX-License-Identifier: GPL-2.0
+ */
+
+#include <linux/time.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+
+#include "ufshcd.h"
+#include "ufshcd-pltfrm.h"
+#include "unipro.h"
+#include "ufs-hisi.h"
+#include "ufshci.h"
+
+static int ufs_hisi_check_hibern8(struct ufs_hba *hba)
+{
+	int err = 0;
+	u32 tx_fsm_val_0 = 0;
+	u32 tx_fsm_val_1 = 0;
+	unsigned long timeout = jiffies + msecs_to_jiffies(HBRN8_POLL_TOUT_MS);
+
+	do {
+		err = ufshcd_dme_get(hba, UIC_ARG_MIB_SEL(MPHY_TX_FSM_STATE, 0),
+				      &tx_fsm_val_0);
+		err |= ufshcd_dme_get(hba,
+		    UIC_ARG_MIB_SEL(MPHY_TX_FSM_STATE, 1), &tx_fsm_val_1);
+		if (err || (tx_fsm_val_0 == TX_FSM_HIBERN8 &&
+			tx_fsm_val_1 == TX_FSM_HIBERN8))
+			break;
+
+		/* sleep for max. 200us */
+		usleep_range(100, 200);
+	} while (time_before(jiffies, timeout));
+
+	/*
+	 * we might have scheduled out for long during polling so
+	 * check the state again.
+	 */
+	if (time_after(jiffies, timeout)) {
+		err = ufshcd_dme_get(hba, UIC_ARG_MIB_SEL(MPHY_TX_FSM_STATE, 0),
+				     &tx_fsm_val_0);
+		err |= ufshcd_dme_get(hba,
+		 UIC_ARG_MIB_SEL(MPHY_TX_FSM_STATE, 1), &tx_fsm_val_1);
+	}
+
+	if (err) {
+		dev_err(hba->dev, "%s: unable to get TX_FSM_STATE, err %d\n",
+			__func__, err);
+	} else if (tx_fsm_val_0 != TX_FSM_HIBERN8 ||
+			 tx_fsm_val_1 != TX_FSM_HIBERN8) {
+		err = -1;
+		dev_err(hba->dev, "%s: invalid TX_FSM_STATE, lane0 = %d, lane1 = %d\n",
+			__func__, tx_fsm_val_0, tx_fsm_val_1);
+	}
+
+	return err;
+}
+
+static void ufs_hi3660_clk_init(struct ufs_hba *hba)
+{
+	struct ufs_hisi_host *host = ufshcd_get_variant(hba);
+
+	ufs_sys_ctrl_clr_bits(host, BIT_SYSCTRL_REF_CLOCK_EN, PHY_CLK_CTRL);
+	if (ufs_sys_ctrl_readl(host, PHY_CLK_CTRL) & BIT_SYSCTRL_REF_CLOCK_EN)
+		mdelay(1);
+	/* use abb clk */
+	ufs_sys_ctrl_clr_bits(host, BIT_UFS_REFCLK_SRC_SEl, UFS_SYSCTRL);
+	ufs_sys_ctrl_clr_bits(host, BIT_UFS_REFCLK_ISO_EN, PHY_ISO_EN);
+	/* open mphy ref clk */
+	ufs_sys_ctrl_set_bits(host, BIT_SYSCTRL_REF_CLOCK_EN, PHY_CLK_CTRL);
+}
+
+static void ufs_hi3660_soc_init(struct ufs_hba *hba)
+{
+	struct ufs_hisi_host *host = ufshcd_get_variant(hba);
+	u32 reg;
+
+	if (!IS_ERR(host->rst))
+		reset_control_assert(host->rst);
+
+	/* HC_PSW powerup */
+	ufs_sys_ctrl_set_bits(host, BIT_UFS_PSW_MTCMOS_EN, PSW_POWER_CTRL);
+	udelay(10);
+	/* notify PWR ready */
+	ufs_sys_ctrl_set_bits(host, BIT_SYSCTRL_PWR_READY, HC_LP_CTRL);
+	ufs_sys_ctrl_writel(host, MASK_UFS_DEVICE_RESET | 0,
+		UFS_DEVICE_RESET_CTRL);
+
+	reg = ufs_sys_ctrl_readl(host, PHY_CLK_CTRL);
+	reg = (reg & ~MASK_SYSCTRL_CFG_CLOCK_FREQ) | UFS_FREQ_CFG_CLK;
+	/* set cfg clk freq */
+	ufs_sys_ctrl_writel(host, reg, PHY_CLK_CTRL);
+	/* set ref clk freq */
+	ufs_sys_ctrl_clr_bits(host, MASK_SYSCTRL_REF_CLOCK_SEL, PHY_CLK_CTRL);
+	/* bypass ufs clk gate */
+	ufs_sys_ctrl_set_bits(host, MASK_UFS_CLK_GATE_BYPASS,
+						 CLOCK_GATE_BYPASS);
+	ufs_sys_ctrl_set_bits(host, MASK_UFS_SYSCRTL_BYPASS, UFS_SYSCTRL);
+
+	/* open psw clk */
+	ufs_sys_ctrl_set_bits(host, BIT_SYSCTRL_PSW_CLK_EN, PSW_CLK_CTRL);
+	/* disable ufshc iso */
+	ufs_sys_ctrl_clr_bits(host, BIT_UFS_PSW_ISO_CTRL, PSW_POWER_CTRL);
+	/* disable phy iso */
+	ufs_sys_ctrl_clr_bits(host, BIT_UFS_PHY_ISO_CTRL, PHY_ISO_EN);
+	/* notice iso disable */
+	ufs_sys_ctrl_clr_bits(host, BIT_SYSCTRL_LP_ISOL_EN, HC_LP_CTRL);
+
+	/* disable lp_reset_n */
+	ufs_sys_ctrl_set_bits(host, BIT_SYSCTRL_LP_RESET_N, RESET_CTRL_EN);
+	mdelay(1);
+
+	ufs_sys_ctrl_writel(host, MASK_UFS_DEVICE_RESET | BIT_UFS_DEVICE_RESET,
+		UFS_DEVICE_RESET_CTRL);
+
+	msleep(20);
+
+	/*
+	 * enable the fix of linereset recovery,
+	 * and enable rx_reset/tx_rest beat
+	 * enable ref_clk_en override(bit5) &
+	 * override value = 1(bit4), with mask
+	 */
+	ufs_sys_ctrl_writel(host, 0x03300330, UFS_DEVICE_RESET_CTRL);
+
+	if (!IS_ERR(host->rst))
+		reset_control_deassert(host->rst);
+}
+
+static int ufs_hisi_link_startup_pre_change(struct ufs_hba *hba)
+{
+	int err;
+	uint32_t value;
+	uint32_t reg;
+
+	/* Unipro VS_mphy_disable */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0xD0C1, 0x0), 0x1);
+	/* PA_HSSeries */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x156A, 0x0), 0x2);
+	/* MPHY CBRATESEL */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x8114, 0x0), 0x1);
+	/* MPHY CBOVRCTRL2 */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x8121, 0x0), 0x2D);
+	/* MPHY CBOVRCTRL3 */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x8122, 0x0), 0x1);
+	/* Unipro VS_MphyCfgUpdt */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0xD085, 0x0), 0x1);
+	/* MPHY RXOVRCTRL4 rx0 */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x800D, 0x4), 0x58);
+	/* MPHY RXOVRCTRL4 rx1 */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x800D, 0x5), 0x58);
+	/* MPHY RXOVRCTRL5 rx0 */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x800E, 0x4), 0xB);
+	/* MPHY RXOVRCTRL5 rx1 */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x800E, 0x5), 0xB);
+	/* MPHY RXSQCONTROL rx0 */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x8009, 0x4), 0x1);
+	/* MPHY RXSQCONTROL rx1 */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x8009, 0x5), 0x1);
+	/* Unipro VS_MphyCfgUpdt */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0xD085, 0x0), 0x1);
+
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x8113, 0x0), 0x1);
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0xD085, 0x0), 0x1);
+
+	/* Tactive RX */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x008F, 0x4), 0x7);
+	/* Tactive RX */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x008F, 0x5), 0x7);
+
+	/* Gear3 Synclength */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x0095, 0x4), 0x4F);
+	/* Gear3 Synclength */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x0095, 0x5), 0x4F);
+	/* Gear2 Synclength */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x0094, 0x4), 0x4F);
+	/* Gear2 Synclength */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x0094, 0x5), 0x4F);
+	/* Gear1 Synclength */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x008B, 0x4), 0x4F);
+	/* Gear1 Synclength */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x008B, 0x5), 0x4F);
+	/* Thibernate Tx */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x000F, 0x0), 0x5);
+	/* Thibernate Tx */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x000F, 0x1), 0x5);
+
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0xD085, 0x0), 0x1);
+	/* Unipro VS_mphy_disable */
+	ufshcd_dme_get(hba, UIC_ARG_MIB_SEL(0xD0C1, 0x0), &value);
+	if (value != 0x1)
+		dev_info(hba->dev,
+		    "Warring!!! Unipro VS_mphy_disable is 0x%x\n", value);
+
+	/* Unipro VS_mphy_disable */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0xD0C1, 0x0), 0x0);
+	err = ufs_hisi_check_hibern8(hba);
+	if (err)
+		dev_err(hba->dev, "ufs_hisi_check_hibern8 error\n");
+
+	ufshcd_writel(hba, UFS_HCLKDIV_NORMAL_VALUE, UFS_REG_HCLKDIV);
+
+	/* disable auto H8 */
+	reg = ufshcd_readl(hba, REG_AUTO_HIBERNATE_IDLE_TIMER);
+	reg = reg & (~UFS_AHIT_AH8ITV_MASK);
+	ufshcd_writel(hba, reg, REG_AUTO_HIBERNATE_IDLE_TIMER);
+
+	/* Unipro PA_Local_TX_LCC_Enable */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x155E, 0x0), 0x0);
+	/* close Unipro VS_Mk2ExtnSupport */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0xD0AB, 0x0), 0x0);
+	ufshcd_dme_get(hba, UIC_ARG_MIB_SEL(0xD0AB, 0x0), &value);
+	if (value != 0) {
+		/* Ensure close success */
+		dev_info(hba->dev, "WARN: close VS_Mk2ExtnSupport failed\n");
+	}
+
+	return err;
+}
+
+static int ufs_hisi_link_startup_post_change(struct ufs_hba *hba)
+{
+	struct ufs_hisi_host *host = ufshcd_get_variant(hba);
+
+	/* Unipro DL_AFC0CreditThreshold */
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x2044), 0x0);
+	/* Unipro DL_TC0OutAckThreshold */
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x2045), 0x0);
+	/* Unipro DL_TC0TXFCThreshold */
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x2040), 0x9);
+
+	/* not bypass ufs clk gate */
+	ufs_sys_ctrl_clr_bits(host, MASK_UFS_CLK_GATE_BYPASS,
+						CLOCK_GATE_BYPASS);
+	ufs_sys_ctrl_clr_bits(host, MASK_UFS_SYSCRTL_BYPASS,
+						UFS_SYSCTRL);
+
+	/* select received symbol cnt */
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0xd09a), 0x80000000);
+	 /* reset counter0 and enable */
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0xd09c), 0x00000005);
+
+	return 0;
+}
+
+static int ufs_hi3660_link_startup_notify(struct ufs_hba *hba,
+					  enum ufs_notify_change_status status)
+{
+	int err = 0;
+
+	switch (status) {
+	case PRE_CHANGE:
+		err = ufs_hisi_link_startup_pre_change(hba);
+		break;
+	case POST_CHANGE:
+		err = ufs_hisi_link_startup_post_change(hba);
+		break;
+	default:
+		break;
+	}
+
+	return err;
+}
+
+struct ufs_hisi_dev_params {
+	u32 pwm_rx_gear; /* pwm rx gear to work in */
+	u32 pwm_tx_gear; /* pwm tx gear to work in */
+	u32 hs_rx_gear;  /* hs rx gear to work in */
+	u32 hs_tx_gear;  /* hs tx gear to work in */
+	u32 rx_lanes;    /* number of rx lanes */
+	u32 tx_lanes;    /* number of tx lanes */
+	u32 rx_pwr_pwm;  /* rx pwm working pwr */
+	u32 tx_pwr_pwm;  /* tx pwm working pwr */
+	u32 rx_pwr_hs;   /* rx hs working pwr */
+	u32 tx_pwr_hs;   /* tx hs working pwr */
+	u32 hs_rate;     /* rate A/B to work in HS */
+	u32 desired_working_mode;
+};
+
+static int ufs_hisi_get_pwr_dev_param(
+				    struct ufs_hisi_dev_params *hisi_param,
+				    struct ufs_pa_layer_attr *dev_max,
+				    struct ufs_pa_layer_attr *agreed_pwr)
+{
+	int min_hisi_gear;
+	int min_dev_gear;
+	bool is_dev_sup_hs = false;
+	bool is_hisi_max_hs = false;
+
+	if (dev_max->pwr_rx == FASTAUTO_MODE || dev_max->pwr_rx == FAST_MODE)
+		is_dev_sup_hs = true;
+
+	if (hisi_param->desired_working_mode == FAST) {
+		is_hisi_max_hs = true;
+		min_hisi_gear = min_t(u32, hisi_param->hs_rx_gear,
+				       hisi_param->hs_tx_gear);
+	} else {
+		min_hisi_gear = min_t(u32, hisi_param->pwm_rx_gear,
+				       hisi_param->pwm_tx_gear);
+	}
+
+	/*
+	 * device doesn't support HS but
+	 * hisi_param->desired_working_mode is HS,
+	 * thus device and hisi_param don't agree
+	 */
+	if (!is_dev_sup_hs && is_hisi_max_hs) {
+		pr_err("%s: device not support HS\n", __func__);
+		return -ENOTSUPP;
+	} else if (is_dev_sup_hs && is_hisi_max_hs) {
+		/*
+		 * since device supports HS, it supports FAST_MODE.
+		 * since hisi_param->desired_working_mode is also HS
+		 * then final decision (FAST/FASTAUTO) is done according
+		 * to hisi_params as it is the restricting factor
+		 */
+		agreed_pwr->pwr_rx = agreed_pwr->pwr_tx =
+			hisi_param->rx_pwr_hs;
+	} else {
+		/*
+		 * here hisi_param->desired_working_mode is PWM.
+		 * it doesn't matter whether device supports HS or PWM,
+		 * in both cases hisi_param->desired_working_mode will
+		 * determine the mode
+		 */
+		agreed_pwr->pwr_rx = agreed_pwr->pwr_tx =
+			hisi_param->rx_pwr_pwm;
+	}
+
+	/*
+	 * we would like tx to work in the minimum number of lanes
+	 * between device capability and vendor preferences.
+	 * the same decision will be made for rx
+	 */
+	agreed_pwr->lane_tx =
+		min_t(u32, dev_max->lane_tx, hisi_param->tx_lanes);
+	agreed_pwr->lane_rx =
+		min_t(u32, dev_max->lane_rx, hisi_param->rx_lanes);
+
+	/* device maximum gear is the minimum between device rx and tx gears */
+	min_dev_gear = min_t(u32, dev_max->gear_rx, dev_max->gear_tx);
+
+	/*
+	 * if both device capabilities and vendor pre-defined preferences are
+	 * both HS or both PWM then set the minimum gear to be the chosen
+	 * working gear.
+	 * if one is PWM and one is HS then the one that is PWM get to decide
+	 * what is the gear, as it is the one that also decided previously what
+	 * pwr the device will be configured to.
+	 */
+	if ((is_dev_sup_hs && is_hisi_max_hs) ||
+	    (!is_dev_sup_hs && !is_hisi_max_hs))
+		agreed_pwr->gear_rx = agreed_pwr->gear_tx =
+			min_t(u32, min_dev_gear, min_hisi_gear);
+	else
+		agreed_pwr->gear_rx = agreed_pwr->gear_tx = min_hisi_gear;
+
+	agreed_pwr->hs_rate = hisi_param->hs_rate;
+
+	pr_info("ufs final power mode: gear = %d, lane = %d, pwr = %d, rate = %d\n",
+		agreed_pwr->gear_rx, agreed_pwr->lane_rx, agreed_pwr->pwr_rx,
+		agreed_pwr->hs_rate);
+	return 0;
+}
+
+static void ufs_hisi_set_dev_cap(struct ufs_hisi_dev_params *hisi_param)
+{
+	hisi_param->rx_lanes = UFS_HISI_LIMIT_NUM_LANES_RX;
+	hisi_param->tx_lanes = UFS_HISI_LIMIT_NUM_LANES_TX;
+	hisi_param->hs_rx_gear = UFS_HISI_LIMIT_HSGEAR_RX;
+	hisi_param->hs_tx_gear = UFS_HISI_LIMIT_HSGEAR_TX;
+	hisi_param->pwm_rx_gear = UFS_HISI_LIMIT_PWMGEAR_RX;
+	hisi_param->pwm_tx_gear = UFS_HISI_LIMIT_PWMGEAR_TX;
+	hisi_param->rx_pwr_pwm = UFS_HISI_LIMIT_RX_PWR_PWM;
+	hisi_param->tx_pwr_pwm = UFS_HISI_LIMIT_TX_PWR_PWM;
+	hisi_param->rx_pwr_hs = UFS_HISI_LIMIT_RX_PWR_HS;
+	hisi_param->tx_pwr_hs = UFS_HISI_LIMIT_TX_PWR_HS;
+	hisi_param->hs_rate = UFS_HISI_LIMIT_HS_RATE;
+	hisi_param->desired_working_mode = UFS_HISI_LIMIT_DESIRED_MODE;
+}
+
+static void ufs_hisi_pwr_change_pre_change(struct ufs_hba *hba)
+{
+	/* update */
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x15A8), 0x1);
+	/* PA_TxSkip */
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x155c), 0x0);
+	/*PA_PWRModeUserData0 = 8191, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b0), 8191);
+	/*PA_PWRModeUserData1 = 65535, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b1), 65535);
+	/*PA_PWRModeUserData2 = 32767, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b2), 32767);
+	/*DME_FC0ProtectionTimeOutVal = 8191, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0xd041), 8191);
+	/*DME_TC0ReplayTimeOutVal = 65535, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0xd042), 65535);
+	/*DME_AFC0ReqTimeOutVal = 32767, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0xd043), 32767);
+	/*PA_PWRModeUserData3 = 8191, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b3), 8191);
+	/*PA_PWRModeUserData4 = 65535, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b4), 65535);
+	/*PA_PWRModeUserData5 = 32767, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b5), 32767);
+	/*DME_FC1ProtectionTimeOutVal = 8191, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0xd044), 8191);
+	/*DME_TC1ReplayTimeOutVal = 65535, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0xd045), 65535);
+	/*DME_AFC1ReqTimeOutVal = 32767, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0xd046), 32767);
+}
+
+static int ufs_hi3660_pwr_change_notify(struct ufs_hba *hba,
+				       enum ufs_notify_change_status status,
+				       struct ufs_pa_layer_attr *dev_max_params,
+				       struct ufs_pa_layer_attr *dev_req_params)
+{
+	struct ufs_hisi_dev_params ufs_hisi_cap;
+	int ret = 0;
+
+	if (!dev_req_params) {
+		dev_err(hba->dev,
+			    "%s: incoming dev_req_params is NULL\n", __func__);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	switch (status) {
+	case PRE_CHANGE:
+		ufs_hisi_set_dev_cap(&ufs_hisi_cap);
+		ret = ufs_hisi_get_pwr_dev_param(
+			&ufs_hisi_cap, dev_max_params, dev_req_params);
+		if (ret) {
+			dev_err(hba->dev,
+			    "%s: failed to determine capabilities\n", __func__);
+			goto out;
+		}
+
+		ufs_hisi_pwr_change_pre_change(hba);
+		break;
+	case POST_CHANGE:
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+out:
+	return ret;
+}
+
+static int ufs_hisi_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
+{
+	struct ufs_hisi_host *host = ufshcd_get_variant(hba);
+
+	if (ufshcd_is_runtime_pm(pm_op))
+		return 0;
+
+	if (host->in_suspend) {
+		WARN_ON(1);
+		return 0;
+	}
+
+	ufs_sys_ctrl_clr_bits(host, BIT_SYSCTRL_REF_CLOCK_EN, PHY_CLK_CTRL);
+	udelay(10);
+	/* set ref_dig_clk override of PHY PCS to 0 */
+	ufs_sys_ctrl_writel(host, 0x00100000, UFS_DEVICE_RESET_CTRL);
+
+	host->in_suspend = true;
+
+	return 0;
+}
+
+static int ufs_hisi_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)
+{
+	struct ufs_hisi_host *host = ufshcd_get_variant(hba);
+
+	if (!host->in_suspend)
+		return 0;
+
+	/* set ref_dig_clk override of PHY PCS to 1 */
+	ufs_sys_ctrl_writel(host, 0x00100010, UFS_DEVICE_RESET_CTRL);
+	udelay(10);
+	ufs_sys_ctrl_set_bits(host, BIT_SYSCTRL_REF_CLOCK_EN, PHY_CLK_CTRL);
+
+	host->in_suspend = false;
+	return 0;
+}
+
+static int ufs_hisi_get_resource(struct ufs_hisi_host *host)
+{
+	struct resource *mem_res;
+	struct device *dev = host->hba->dev;
+	struct platform_device *pdev = to_platform_device(dev);
+
+	/* get resource of ufs sys ctrl */
+	mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	host->ufs_sys_ctrl = devm_ioremap_resource(dev, mem_res);
+	if (IS_ERR(host->ufs_sys_ctrl))
+		return PTR_ERR(host->ufs_sys_ctrl);
+
+	return 0;
+}
+
+static void ufs_hisi_set_pm_lvl(struct ufs_hba *hba)
+{
+	hba->rpm_lvl = UFS_PM_LVL_1;
+	hba->spm_lvl = UFS_PM_LVL_3;
+}
+
+/**
+ * ufs_hisi_init_common
+ * @hba: host controller instance
+ */
+static int ufs_hisi_init_common(struct ufs_hba *hba)
+{
+	int err = 0;
+	struct device *dev = hba->dev;
+	struct ufs_hisi_host *host;
+
+	host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL);
+	if (!host)
+		return -ENOMEM;
+
+	host->hba = hba;
+	ufshcd_set_variant(hba, host);
+
+	host->rst  = devm_reset_control_get(dev, "rst");
+
+	ufs_hisi_set_pm_lvl(hba);
+
+	err = ufs_hisi_get_resource(host);
+	if (err) {
+		ufshcd_set_variant(hba, NULL);
+		return err;
+	}
+
+	return 0;
+}
+
+static int ufs_hi3660_init(struct ufs_hba *hba)
+{
+	int ret = 0;
+	struct device *dev = hba->dev;
+
+	ret = ufs_hisi_init_common(hba);
+	if (ret) {
+		dev_err(dev, "%s: ufs common init fail\n", __func__);
+		return ret;
+	}
+
+	ufs_hi3660_clk_init(hba);
+
+	ufs_hi3660_soc_init(hba);
+
+	return 0;
+}
+
+static struct ufs_hba_variant_ops ufs_hba_hisi_vops = {
+	.name = "hi3660",
+	.init = ufs_hi3660_init,
+	.link_startup_notify = ufs_hi3660_link_startup_notify,
+	.pwr_change_notify = ufs_hi3660_pwr_change_notify,
+	.suspend = ufs_hisi_suspend,
+	.resume = ufs_hisi_resume,
+};
+
+static int ufs_hisi_probe(struct platform_device *pdev)
+{
+	return ufshcd_pltfrm_init(pdev, &ufs_hba_hisi_vops);
+}
+
+static int ufs_hisi_remove(struct platform_device *pdev)
+{
+	struct ufs_hba *hba =  platform_get_drvdata(pdev);
+
+	ufshcd_remove(hba);
+	return 0;
+}
+
+static const struct of_device_id ufs_hisi_of_match[] = {
+	{ .compatible = "hisilicon,hi3660-ufs" },
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, ufs_hisi_of_match);
+
+static const struct dev_pm_ops ufs_hisi_pm_ops = {
+	.suspend	= ufshcd_pltfrm_suspend,
+	.resume		= ufshcd_pltfrm_resume,
+	.runtime_suspend = ufshcd_pltfrm_runtime_suspend,
+	.runtime_resume  = ufshcd_pltfrm_runtime_resume,
+	.runtime_idle    = ufshcd_pltfrm_runtime_idle,
+};
+
+static struct platform_driver ufs_hisi_pltform = {
+	.probe	= ufs_hisi_probe,
+	.remove	= ufs_hisi_remove,
+	.shutdown = ufshcd_pltfrm_shutdown,
+	.driver	= {
+		.name	= "ufshcd-hisi",
+		.pm	= &ufs_hisi_pm_ops,
+		.of_match_table = of_match_ptr(ufs_hisi_of_match),
+	},
+};
+module_platform_driver(ufs_hisi_pltform);
+
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:ufshcd-hisi");
+MODULE_DESCRIPTION("HiSilicon Hixxxx UFS Driver");
diff --git a/drivers/scsi/ufs/ufs-hisi.h b/drivers/scsi/ufs/ufs-hisi.h
new file mode 100644
index 000000000000..3df9cd7acc29
--- /dev/null
+++ b/drivers/scsi/ufs/ufs-hisi.h
@@ -0,0 +1,115 @@
+/*
+ * Copyright (c) 2017, HiSilicon. All rights reserved.
+ *
+ * Released under the GPLv2 only.
+ * SPDX-License-Identifier: GPL-2.0
+ */
+
+#ifndef UFS_HISI_H_
+#define UFS_HISI_H_
+
+#define HBRN8_POLL_TOUT_MS	1000
+
+/*
+ * ufs sysctrl specific define
+ */
+#define PSW_POWER_CTRL	(0x04)
+#define PHY_ISO_EN	(0x08)
+#define HC_LP_CTRL	(0x0C)
+#define PHY_CLK_CTRL	(0x10)
+#define PSW_CLK_CTRL	(0x14)
+#define CLOCK_GATE_BYPASS	(0x18)
+#define RESET_CTRL_EN	(0x1C)
+#define UFS_SYSCTRL	(0x5C)
+#define UFS_DEVICE_RESET_CTRL	(0x60)
+
+#define BIT_UFS_PSW_ISO_CTRL		(1 << 16)
+#define BIT_UFS_PSW_MTCMOS_EN		(1 << 0)
+#define BIT_UFS_REFCLK_ISO_EN		(1 << 16)
+#define BIT_UFS_PHY_ISO_CTRL		(1 << 0)
+#define BIT_SYSCTRL_LP_ISOL_EN		(1 << 16)
+#define BIT_SYSCTRL_PWR_READY		(1 << 8)
+#define BIT_SYSCTRL_REF_CLOCK_EN	(1 << 24)
+#define MASK_SYSCTRL_REF_CLOCK_SEL	(0x3 << 8)
+#define MASK_SYSCTRL_CFG_CLOCK_FREQ	(0xFF)
+#define UFS_FREQ_CFG_CLK                (0x39)
+#define BIT_SYSCTRL_PSW_CLK_EN		(1 << 4)
+#define MASK_UFS_CLK_GATE_BYPASS	(0x3F)
+#define BIT_SYSCTRL_LP_RESET_N		(1 << 0)
+#define BIT_UFS_REFCLK_SRC_SEl		(1 << 0)
+#define MASK_UFS_SYSCRTL_BYPASS		(0x3F << 16)
+#define MASK_UFS_DEVICE_RESET		(0x1 << 16)
+#define BIT_UFS_DEVICE_RESET		(0x1)
+
+/*
+ * M-TX Configuration Attributes for Hixxxx
+ */
+#define MPHY_TX_FSM_STATE	0x41
+#define TX_FSM_HIBERN8	0x1
+
+/*
+ * Hixxxx UFS HC specific Registers
+ */
+enum {
+	UFS_REG_OCPTHRTL = 0xc0,
+	UFS_REG_OOCPR    = 0xc4,
+
+	UFS_REG_CDACFG   = 0xd0,
+	UFS_REG_CDATX1   = 0xd4,
+	UFS_REG_CDATX2   = 0xd8,
+	UFS_REG_CDARX1   = 0xdc,
+	UFS_REG_CDARX2   = 0xe0,
+	UFS_REG_CDASTA   = 0xe4,
+
+	UFS_REG_LBMCFG   = 0xf0,
+	UFS_REG_LBMSTA   = 0xf4,
+	UFS_REG_UFSMODE  = 0xf8,
+
+	UFS_REG_HCLKDIV  = 0xfc,
+};
+
+/* AHIT - Auto-Hibernate Idle Timer */
+#define UFS_AHIT_AH8ITV_MASK	0x3FF
+
+/* REG UFS_REG_OCPTHRTL definition */
+#define UFS_HCLKDIV_NORMAL_VALUE	0xE4
+
+/* vendor specific pre-defined parameters */
+#define SLOW	1
+#define FAST	2
+
+#define UFS_HISI_LIMIT_NUM_LANES_RX	2
+#define UFS_HISI_LIMIT_NUM_LANES_TX	2
+#define UFS_HISI_LIMIT_HSGEAR_RX	UFS_HS_G3
+#define UFS_HISI_LIMIT_HSGEAR_TX	UFS_HS_G3
+#define UFS_HISI_LIMIT_PWMGEAR_RX	UFS_PWM_G4
+#define UFS_HISI_LIMIT_PWMGEAR_TX	UFS_PWM_G4
+#define UFS_HISI_LIMIT_RX_PWR_PWM	SLOW_MODE
+#define UFS_HISI_LIMIT_TX_PWR_PWM	SLOW_MODE
+#define UFS_HISI_LIMIT_RX_PWR_HS	FAST_MODE
+#define UFS_HISI_LIMIT_TX_PWR_HS	FAST_MODE
+#define UFS_HISI_LIMIT_HS_RATE	PA_HS_MODE_B
+#define UFS_HISI_LIMIT_DESIRED_MODE	FAST
+
+struct ufs_hisi_host {
+	struct ufs_hba *hba;
+	void __iomem *ufs_sys_ctrl;
+
+	struct reset_control	*rst;
+
+	uint64_t caps;
+
+	bool in_suspend;
+};
+
+#define ufs_sys_ctrl_writel(host, val, reg)                                    \
+	writel((val), (host)->ufs_sys_ctrl + (reg))
+#define ufs_sys_ctrl_readl(host, reg) readl((host)->ufs_sys_ctrl + (reg))
+#define ufs_sys_ctrl_set_bits(host, mask, reg)                                 \
+	ufs_sys_ctrl_writel(                                                   \
+		(host), ((mask) | (ufs_sys_ctrl_readl((host), (reg)))), (reg))
+#define ufs_sys_ctrl_clr_bits(host, mask, reg)                                 \
+	ufs_sys_ctrl_writel((host),                                            \
+			    ((~(mask)) & (ufs_sys_ctrl_readl((host), (reg)))), \
+			    (reg))
+#endif /* UFS_HISI_H_ */
diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c
index 221820a7c78b..75ee5906b966 100644
--- a/drivers/scsi/ufs/ufs-qcom.c
+++ b/drivers/scsi/ufs/ufs-qcom.c
@@ -50,19 +50,10 @@ static void ufs_qcom_get_default_testbus_cfg(struct ufs_qcom_host *host);
 static int ufs_qcom_set_dme_vs_core_clk_ctrl_clear_div(struct ufs_hba *hba,
 						       u32 clk_cycles);
 
-static void ufs_qcom_dump_regs(struct ufs_hba *hba, int offset, int len,
-		char *prefix)
-{
-	print_hex_dump(KERN_ERR, prefix,
-			len > 4 ? DUMP_PREFIX_OFFSET : DUMP_PREFIX_NONE,
-			16, 4, (void __force *)hba->mmio_base + offset,
-			len * 4, false);
-}
-
 static void ufs_qcom_dump_regs_wrapper(struct ufs_hba *hba, int offset, int len,
-		char *prefix, void *priv)
+				       const char *prefix, void *priv)
 {
-	ufs_qcom_dump_regs(hba, offset, len, prefix);
+	ufshcd_dump_regs(hba, offset, len * 4, prefix);
 }
 
 static int ufs_qcom_get_connected_tx_lanes(struct ufs_hba *hba, u32 *tx_lanes)
@@ -1431,7 +1422,7 @@ out:
 
 static void ufs_qcom_print_hw_debug_reg_all(struct ufs_hba *hba,
 		void *priv, void (*print_fn)(struct ufs_hba *hba,
-		int offset, int num_regs, char *str, void *priv))
+		int offset, int num_regs, const char *str, void *priv))
 {
 	u32 reg;
 	struct ufs_qcom_host *host;
@@ -1613,7 +1604,7 @@ int ufs_qcom_testbus_config(struct ufs_qcom_host *host)
 
 static void ufs_qcom_testbus_read(struct ufs_hba *hba)
 {
-	ufs_qcom_dump_regs(hba, UFS_TEST_BUS, 1, "UFS_TEST_BUS ");
+	ufshcd_dump_regs(hba, UFS_TEST_BUS, 4, "UFS_TEST_BUS ");
 }
 
 static void ufs_qcom_print_unipro_testbus(struct ufs_hba *hba)
@@ -1639,8 +1630,8 @@ static void ufs_qcom_print_unipro_testbus(struct ufs_hba *hba)
 
 static void ufs_qcom_dump_dbg_regs(struct ufs_hba *hba)
 {
-	ufs_qcom_dump_regs(hba, REG_UFS_SYS1CLK_1US, 16,
-			"HCI Vendor Specific Registers ");
+	ufshcd_dump_regs(hba, REG_UFS_SYS1CLK_1US, 16 * 4,
+			 "HCI Vendor Specific Registers ");
 
 	/* sleep a bit intermittently as we are dumping too much data */
 	ufs_qcom_print_hw_debug_reg_all(hba, NULL, ufs_qcom_dump_regs_wrapper);
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 397081d320b1..9d5d2ca7fc4f 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -99,8 +99,29 @@
 		_ret;                                                   \
 	})
 
-#define ufshcd_hex_dump(prefix_str, buf, len) \
-print_hex_dump(KERN_ERR, prefix_str, DUMP_PREFIX_OFFSET, 16, 4, buf, len, false)
+#define ufshcd_hex_dump(prefix_str, buf, len) do {                       \
+	size_t __len = (len);                                            \
+	print_hex_dump(KERN_ERR, prefix_str,                             \
+		       __len > 4 ? DUMP_PREFIX_OFFSET : DUMP_PREFIX_NONE,\
+		       16, 4, buf, __len, false);                        \
+} while (0)
+
+int ufshcd_dump_regs(struct ufs_hba *hba, size_t offset, size_t len,
+		     const char *prefix)
+{
+	u8 *regs;
+
+	regs = kzalloc(len, GFP_KERNEL);
+	if (!regs)
+		return -ENOMEM;
+
+	memcpy_fromio(regs, hba->mmio_base + offset, len);
+	ufshcd_hex_dump(prefix, regs, len);
+	kfree(regs);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ufshcd_dump_regs);
 
 enum {
 	UFSHCD_MAX_CHANNEL	= 0,
@@ -321,18 +342,19 @@ static void ufshcd_add_command_trace(struct ufs_hba *hba,
 	sector_t lba = -1;
 	u8 opcode = 0;
 	u32 intr, doorbell;
-	struct ufshcd_lrb *lrbp;
+	struct ufshcd_lrb *lrbp = &hba->lrb[tag];
 	int transfer_len = -1;
 
-	/* trace UPIU also */
-	ufshcd_add_cmd_upiu_trace(hba, tag, str);
-
-	if (!trace_ufshcd_command_enabled())
+	if (!trace_ufshcd_command_enabled()) {
+		/* trace UPIU W/O tracing command */
+		if (lrbp->cmd)
+			ufshcd_add_cmd_upiu_trace(hba, tag, str);
 		return;
-
-	lrbp = &hba->lrb[tag];
+	}
 
 	if (lrbp->cmd) { /* data phase exists */
+		/* trace UPIU also */
+		ufshcd_add_cmd_upiu_trace(hba, tag, str);
 		opcode = (u8)(*lrbp->cmd->cmnd);
 		if ((opcode == READ_10) || (opcode == WRITE_10)) {
 			/*
@@ -386,15 +408,7 @@ static void ufshcd_print_uic_err_hist(struct ufs_hba *hba,
 
 static void ufshcd_print_host_regs(struct ufs_hba *hba)
 {
-	/*
-	 * hex_dump reads its data without the readl macro. This might
-	 * cause inconsistency issues on some platform, as the printed
-	 * values may be from cache and not the most recent value.
-	 * To know whether you are looking at an un-cached version verify
-	 * that IORESOURCE_MEM flag is on when xxx_get_resource() is invoked
-	 * during platform/pci probe function.
-	 */
-	ufshcd_hex_dump("host regs: ", hba->mmio_base, UFSHCI_REG_SPACE_SIZE);
+	ufshcd_dump_regs(hba, 0, UFSHCI_REG_SPACE_SIZE, "host_regs: ");
 	dev_err(hba->dev, "hba->ufs_version = 0x%x, hba->capabilities = 0x%x\n",
 		hba->ufs_version, hba->capabilities);
 	dev_err(hba->dev,
@@ -7290,7 +7304,7 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
 		sdev_printk(KERN_WARNING, sdp,
 			    "START_STOP failed for power mode: %d, result %x\n",
 			    pwr_mode, ret);
-		if (driver_byte(ret) & DRIVER_SENSE)
+		if (driver_byte(ret) == DRIVER_SENSE)
 			scsi_print_sense_hdr(sdp, NULL, &sshdr);
 	}
 
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index f51758f1e5cc..33fdd3f281ae 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -1043,4 +1043,7 @@ static inline u8 ufshcd_scsi_to_upiu_lun(unsigned int scsi_lun)
 		return scsi_lun & UFS_UPIU_MAX_UNIT_NUM_ID;
 }
 
+int ufshcd_dump_regs(struct ufs_hba *hba, size_t offset, size_t len,
+		     const char *prefix);
+
 #endif /* End of Header */
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 6dc8891ccb74..1c72db94270e 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -513,12 +513,12 @@ static void virtio_scsi_init_hdr_pi(struct virtio_device *vdev,
 
 	if (sc->sc_data_direction == DMA_TO_DEVICE)
 		cmd_pi->pi_bytesout = cpu_to_virtio32(vdev,
-							blk_rq_sectors(rq) *
-							bi->tuple_size);
+						      bio_integrity_bytes(bi,
+							blk_rq_sectors(rq)));
 	else if (sc->sc_data_direction == DMA_FROM_DEVICE)
 		cmd_pi->pi_bytesin = cpu_to_virtio32(vdev,
-						       blk_rq_sectors(rq) *
-						       bi->tuple_size);
+						     bio_integrity_bytes(bi,
+							blk_rq_sectors(rq)));
 }
 #endif
 
diff --git a/drivers/sh/maple/maple.c b/drivers/sh/maple/maple.c
index 2e45988d1259..e5d7fb81ad66 100644
--- a/drivers/sh/maple/maple.c
+++ b/drivers/sh/maple/maple.c
@@ -300,8 +300,8 @@ static void maple_send(void)
 	mutex_unlock(&maple_wlist_lock);
 	if (maple_packets > 0) {
 		for (i = 0; i < (1 << MAPLE_DMA_PAGES); i++)
-			sh_sync_dma_for_device(maple_sendbuf + i * PAGE_SIZE,
-				       PAGE_SIZE, DMA_BIDIRECTIONAL);
+			__flush_purge_region(maple_sendbuf + i * PAGE_SIZE,
+					PAGE_SIZE);
 	}
 
 finish:
@@ -642,7 +642,8 @@ static void maple_dma_handler(struct work_struct *work)
 		list_for_each_entry_safe(mq, nmq, &maple_sentq, list) {
 			mdev = mq->dev;
 			recvbuf = mq->recvbuf->buf;
-			sh_sync_dma_for_device(recvbuf, 0x400, DMA_FROM_DEVICE);
+			__flush_invalidate_region(sh_cacheop_vaddr(recvbuf),
+					0x400);
 			code = recvbuf[0];
 			kfree(mq->sendbuf);
 			list_del_init(&mq->list);
diff --git a/drivers/soc/imx/gpc.c b/drivers/soc/imx/gpc.c
index 0097a939487f..546960a18d60 100644
--- a/drivers/soc/imx/gpc.c
+++ b/drivers/soc/imx/gpc.c
@@ -209,7 +209,7 @@ static int imx_pgc_power_domain_probe(struct platform_device *pdev)
 			goto genpd_err;
 	}
 
-	device_link_add(dev, dev->parent, DL_FLAG_AUTOREMOVE);
+	device_link_add(dev, dev->parent, DL_FLAG_AUTOREMOVE_CONSUMER);
 
 	return 0;
 
diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
index 5856e792d09c..ba79b609aca2 100644
--- a/drivers/soc/qcom/Kconfig
+++ b/drivers/soc/qcom/Kconfig
@@ -40,6 +40,23 @@ config QCOM_GSBI
           functions for connecting the underlying serial UART, SPI, and I2C
           devices to the output pins.
 
+config QCOM_LLCC
+	tristate "Qualcomm Technologies, Inc. LLCC driver"
+	depends on ARCH_QCOM
+	help
+	  Qualcomm Technologies, Inc. platform specific
+	  Last Level Cache Controller(LLCC) driver. This provides interfaces
+	  to clients that use the LLCC. Say yes here to enable LLCC slice
+	  driver.
+
+config QCOM_SDM845_LLCC
+	tristate "Qualcomm Technologies, Inc. SDM845 LLCC driver"
+	depends on QCOM_LLCC
+	help
+	  Say yes here to enable the LLCC driver for SDM845. This provides
+	  data required to configure LLCC so that clients can start using the
+	  LLCC slices.
+
 config QCOM_MDT_LOADER
 	tristate
 	select QCOM_SCM
@@ -75,6 +92,16 @@ config QCOM_RMTFS_MEM
 
 	  Say y here if you intend to boot the modem remoteproc.
 
+config QCOM_RPMH
+	bool "Qualcomm RPM-Hardened (RPMH) Communication"
+	depends on ARCH_QCOM && ARM64 && OF || COMPILE_TEST
+	help
+	  Support for communication with the hardened-RPM blocks in
+	  Qualcomm Technologies Inc (QTI) SoCs. RPMH communication uses an
+	  internal bus to transmit state requests for shared resources. A set
+	  of hardware components aggregate requests for these resources and
+	  help apply the aggregated state on the resource.
+
 config QCOM_SMEM
 	tristate "Qualcomm Shared Memory Manager (SMEM)"
 	depends on ARCH_QCOM
diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile
index 19dcf957cb3a..f25b54cd6cf8 100644
--- a/drivers/soc/qcom/Makefile
+++ b/drivers/soc/qcom/Makefile
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
+CFLAGS_rpmh-rsc.o := -I$(src)
 obj-$(CONFIG_QCOM_GENI_SE) +=	qcom-geni-se.o
 obj-$(CONFIG_QCOM_COMMAND_DB) += cmd-db.o
 obj-$(CONFIG_QCOM_GLINK_SSR) +=	glink_ssr.o
@@ -8,6 +9,9 @@ obj-$(CONFIG_QCOM_PM)	+=	spm.o
 obj-$(CONFIG_QCOM_QMI_HELPERS)	+= qmi_helpers.o
 qmi_helpers-y	+= qmi_encdec.o qmi_interface.o
 obj-$(CONFIG_QCOM_RMTFS_MEM)	+= rmtfs_mem.o
+obj-$(CONFIG_QCOM_RPMH)		+= qcom_rpmh.o
+qcom_rpmh-y			+= rpmh-rsc.o
+qcom_rpmh-y			+= rpmh.o
 obj-$(CONFIG_QCOM_SMD_RPM)	+= smd-rpm.o
 obj-$(CONFIG_QCOM_SMEM) +=	smem.o
 obj-$(CONFIG_QCOM_SMEM_STATE) += smem_state.o
@@ -15,3 +19,5 @@ obj-$(CONFIG_QCOM_SMP2P)	+= smp2p.o
 obj-$(CONFIG_QCOM_SMSM)	+= smsm.o
 obj-$(CONFIG_QCOM_WCNSS_CTRL) += wcnss_ctrl.o
 obj-$(CONFIG_QCOM_APR) += apr.o
+obj-$(CONFIG_QCOM_LLCC) += llcc-slice.o
+obj-$(CONFIG_QCOM_SDM845_LLCC) += llcc-sdm845.o
diff --git a/drivers/soc/qcom/llcc-sdm845.c b/drivers/soc/qcom/llcc-sdm845.c
new file mode 100644
index 000000000000..2e1e4f0a5db8
--- /dev/null
+++ b/drivers/soc/qcom/llcc-sdm845.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/soc/qcom/llcc-qcom.h>
+
+/*
+ * SCT(System Cache Table) entry contains of the following members:
+ * usecase_id: Unique id for the client's use case
+ * slice_id: llcc slice id for each client
+ * max_cap: The maximum capacity of the cache slice provided in KB
+ * priority: Priority of the client used to select victim line for replacement
+ * fixed_size: Boolean indicating if the slice has a fixed capacity
+ * bonus_ways: Bonus ways are additional ways to be used for any slice,
+ *		if client ends up using more than reserved cache ways. Bonus
+ *		ways are allocated only if they are not reserved for some
+ *		other client.
+ * res_ways: Reserved ways for the cache slice, the reserved ways cannot
+ *		be used by any other client than the one its assigned to.
+ * cache_mode: Each slice operates as a cache, this controls the mode of the
+ *             slice: normal or TCM(Tightly Coupled Memory)
+ * probe_target_ways: Determines what ways to probe for access hit. When
+ *                    configured to 1 only bonus and reserved ways are probed.
+ *                    When configured to 0 all ways in llcc are probed.
+ * dis_cap_alloc: Disable capacity based allocation for a client
+ * retain_on_pc: If this bit is set and client has maintained active vote
+ *               then the ways assigned to this client are not flushed on power
+ *               collapse.
+ * activate_on_init: Activate the slice immediately after the SCT is programmed
+ */
+#define SCT_ENTRY(uid, sid, mc, p, fs, bway, rway, cmod, ptw, dca, rp, a) \
+	{					\
+		.usecase_id = uid,		\
+		.slice_id = sid,		\
+		.max_cap = mc,			\
+		.priority = p,			\
+		.fixed_size = fs,		\
+		.bonus_ways = bway,		\
+		.res_ways = rway,		\
+		.cache_mode = cmod,		\
+		.probe_target_ways = ptw,	\
+		.dis_cap_alloc = dca,		\
+		.retain_on_pc = rp,		\
+		.activate_on_init = a,		\
+	}
+
+static struct llcc_slice_config sdm845_data[] =  {
+	SCT_ENTRY(LLCC_CPUSS,    1,  2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 1),
+	SCT_ENTRY(LLCC_VIDSC0,   2,  512,  2, 1, 0x0,   0x0f0, 0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_VIDSC1,   3,  512,  2, 1, 0x0,   0x0f0, 0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_ROTATOR,  4,  563,  2, 1, 0x0,   0x00e, 2, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_VOICE,    5,  2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_AUDIO,    6,  2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_MDMHPGRW, 7,  1024, 2, 0, 0xfc,  0xf00, 0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_MDM,      8,  2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_CMPT,     10, 2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_GPUHTW,   11, 512,  1, 1, 0xc,   0x0,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_GPU,      12, 2304, 1, 0, 0xff0, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_MMUHWT,   13, 256,  2, 0, 0x0,   0x1,   0, 0, 1, 0, 1),
+	SCT_ENTRY(LLCC_CMPTDMA,  15, 2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_DISP,     16, 2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_VIDFW,    17, 2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_MDMHPFX,  20, 1024, 2, 1, 0x0,   0xf00, 0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_MDMPNG,   21, 1024, 0, 1, 0x1e,  0x0,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_AUDHW,    22, 1024, 1, 1, 0xffc, 0x2,   0, 0, 1, 1, 0),
+};
+
+static int sdm845_qcom_llcc_probe(struct platform_device *pdev)
+{
+	return qcom_llcc_probe(pdev, sdm845_data, ARRAY_SIZE(sdm845_data));
+}
+
+static const struct of_device_id sdm845_qcom_llcc_of_match[] = {
+	{ .compatible = "qcom,sdm845-llcc", },
+	{ }
+};
+
+static struct platform_driver sdm845_qcom_llcc_driver = {
+	.driver = {
+		.name = "sdm845-llcc",
+		.of_match_table = sdm845_qcom_llcc_of_match,
+	},
+	.probe = sdm845_qcom_llcc_probe,
+};
+module_platform_driver(sdm845_qcom_llcc_driver);
+
+MODULE_DESCRIPTION("QCOM sdm845 LLCC driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/soc/qcom/llcc-slice.c b/drivers/soc/qcom/llcc-slice.c
new file mode 100644
index 000000000000..54063a31132f
--- /dev/null
+++ b/drivers/soc/qcom/llcc-slice.c
@@ -0,0 +1,338 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved.
+ *
+ */
+
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/soc/qcom/llcc-qcom.h>
+
+#define ACTIVATE                      BIT(0)
+#define DEACTIVATE                    BIT(1)
+#define ACT_CTRL_OPCODE_ACTIVATE      BIT(0)
+#define ACT_CTRL_OPCODE_DEACTIVATE    BIT(1)
+#define ACT_CTRL_ACT_TRIG             BIT(0)
+#define ACT_CTRL_OPCODE_SHIFT         0x01
+#define ATTR1_PROBE_TARGET_WAYS_SHIFT 0x02
+#define ATTR1_FIXED_SIZE_SHIFT        0x03
+#define ATTR1_PRIORITY_SHIFT          0x04
+#define ATTR1_MAX_CAP_SHIFT           0x10
+#define ATTR0_RES_WAYS_MASK           GENMASK(11, 0)
+#define ATTR0_BONUS_WAYS_MASK         GENMASK(27, 16)
+#define ATTR0_BONUS_WAYS_SHIFT        0x10
+#define LLCC_STATUS_READ_DELAY        100
+
+#define CACHE_LINE_SIZE_SHIFT         6
+
+#define LLCC_COMMON_STATUS0           0x0003000c
+#define LLCC_LB_CNT_MASK              GENMASK(31, 28)
+#define LLCC_LB_CNT_SHIFT             28
+
+#define MAX_CAP_TO_BYTES(n)           (n * SZ_1K)
+#define LLCC_TRP_ACT_CTRLn(n)         (n * SZ_4K)
+#define LLCC_TRP_STATUSn(n)           (4 + n * SZ_4K)
+#define LLCC_TRP_ATTR0_CFGn(n)        (0x21000 + SZ_8 * n)
+#define LLCC_TRP_ATTR1_CFGn(n)        (0x21004 + SZ_8 * n)
+
+#define BANK_OFFSET_STRIDE	      0x80000
+
+static struct llcc_drv_data *drv_data;
+
+static const struct regmap_config llcc_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.fast_io = true,
+};
+
+/**
+ * llcc_slice_getd - get llcc slice descriptor
+ * @uid: usecase_id for the client
+ *
+ * A pointer to llcc slice descriptor will be returned on success and
+ * and error pointer is returned on failure
+ */
+struct llcc_slice_desc *llcc_slice_getd(u32 uid)
+{
+	const struct llcc_slice_config *cfg;
+	struct llcc_slice_desc *desc;
+	u32 sz, count;
+
+	cfg = drv_data->cfg;
+	sz = drv_data->cfg_size;
+
+	for (count = 0; cfg && count < sz; count++, cfg++)
+		if (cfg->usecase_id == uid)
+			break;
+
+	if (count == sz || !cfg)
+		return ERR_PTR(-ENODEV);
+
+	desc = kzalloc(sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return ERR_PTR(-ENOMEM);
+
+	desc->slice_id = cfg->slice_id;
+	desc->slice_size = cfg->max_cap;
+
+	return desc;
+}
+EXPORT_SYMBOL_GPL(llcc_slice_getd);
+
+/**
+ * llcc_slice_putd - llcc slice descritpor
+ * @desc: Pointer to llcc slice descriptor
+ */
+void llcc_slice_putd(struct llcc_slice_desc *desc)
+{
+	kfree(desc);
+}
+EXPORT_SYMBOL_GPL(llcc_slice_putd);
+
+static int llcc_update_act_ctrl(u32 sid,
+				u32 act_ctrl_reg_val, u32 status)
+{
+	u32 act_ctrl_reg;
+	u32 status_reg;
+	u32 slice_status;
+	int ret;
+
+	act_ctrl_reg = drv_data->bcast_off + LLCC_TRP_ACT_CTRLn(sid);
+	status_reg = drv_data->bcast_off + LLCC_TRP_STATUSn(sid);
+
+	/* Set the ACTIVE trigger */
+	act_ctrl_reg_val |= ACT_CTRL_ACT_TRIG;
+	ret = regmap_write(drv_data->regmap, act_ctrl_reg, act_ctrl_reg_val);
+	if (ret)
+		return ret;
+
+	/* Clear the ACTIVE trigger */
+	act_ctrl_reg_val &= ~ACT_CTRL_ACT_TRIG;
+	ret = regmap_write(drv_data->regmap, act_ctrl_reg, act_ctrl_reg_val);
+	if (ret)
+		return ret;
+
+	ret = regmap_read_poll_timeout(drv_data->regmap, status_reg,
+				      slice_status, !(slice_status & status),
+				      0, LLCC_STATUS_READ_DELAY);
+	return ret;
+}
+
+/**
+ * llcc_slice_activate - Activate the llcc slice
+ * @desc: Pointer to llcc slice descriptor
+ *
+ * A value of zero will be returned on success and a negative errno will
+ * be returned in error cases
+ */
+int llcc_slice_activate(struct llcc_slice_desc *desc)
+{
+	int ret;
+	u32 act_ctrl_val;
+
+	mutex_lock(&drv_data->lock);
+	if (test_bit(desc->slice_id, drv_data->bitmap)) {
+		mutex_unlock(&drv_data->lock);
+		return 0;
+	}
+
+	act_ctrl_val = ACT_CTRL_OPCODE_ACTIVATE << ACT_CTRL_OPCODE_SHIFT;
+
+	ret = llcc_update_act_ctrl(desc->slice_id, act_ctrl_val,
+				  DEACTIVATE);
+	if (ret) {
+		mutex_unlock(&drv_data->lock);
+		return ret;
+	}
+
+	__set_bit(desc->slice_id, drv_data->bitmap);
+	mutex_unlock(&drv_data->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(llcc_slice_activate);
+
+/**
+ * llcc_slice_deactivate - Deactivate the llcc slice
+ * @desc: Pointer to llcc slice descriptor
+ *
+ * A value of zero will be returned on success and a negative errno will
+ * be returned in error cases
+ */
+int llcc_slice_deactivate(struct llcc_slice_desc *desc)
+{
+	u32 act_ctrl_val;
+	int ret;
+
+	mutex_lock(&drv_data->lock);
+	if (!test_bit(desc->slice_id, drv_data->bitmap)) {
+		mutex_unlock(&drv_data->lock);
+		return 0;
+	}
+	act_ctrl_val = ACT_CTRL_OPCODE_DEACTIVATE << ACT_CTRL_OPCODE_SHIFT;
+
+	ret = llcc_update_act_ctrl(desc->slice_id, act_ctrl_val,
+				  ACTIVATE);
+	if (ret) {
+		mutex_unlock(&drv_data->lock);
+		return ret;
+	}
+
+	__clear_bit(desc->slice_id, drv_data->bitmap);
+	mutex_unlock(&drv_data->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(llcc_slice_deactivate);
+
+/**
+ * llcc_get_slice_id - return the slice id
+ * @desc: Pointer to llcc slice descriptor
+ */
+int llcc_get_slice_id(struct llcc_slice_desc *desc)
+{
+	return desc->slice_id;
+}
+EXPORT_SYMBOL_GPL(llcc_get_slice_id);
+
+/**
+ * llcc_get_slice_size - return the slice id
+ * @desc: Pointer to llcc slice descriptor
+ */
+size_t llcc_get_slice_size(struct llcc_slice_desc *desc)
+{
+	return desc->slice_size;
+}
+EXPORT_SYMBOL_GPL(llcc_get_slice_size);
+
+static int qcom_llcc_cfg_program(struct platform_device *pdev)
+{
+	int i;
+	u32 attr1_cfg;
+	u32 attr0_cfg;
+	u32 attr1_val;
+	u32 attr0_val;
+	u32 max_cap_cacheline;
+	u32 sz;
+	int ret;
+	const struct llcc_slice_config *llcc_table;
+	struct llcc_slice_desc desc;
+	u32 bcast_off = drv_data->bcast_off;
+
+	sz = drv_data->cfg_size;
+	llcc_table = drv_data->cfg;
+
+	for (i = 0; i < sz; i++) {
+		attr1_cfg = bcast_off +
+				LLCC_TRP_ATTR1_CFGn(llcc_table[i].slice_id);
+		attr0_cfg = bcast_off +
+				LLCC_TRP_ATTR0_CFGn(llcc_table[i].slice_id);
+
+		attr1_val = llcc_table[i].cache_mode;
+		attr1_val |= llcc_table[i].probe_target_ways <<
+				ATTR1_PROBE_TARGET_WAYS_SHIFT;
+		attr1_val |= llcc_table[i].fixed_size <<
+				ATTR1_FIXED_SIZE_SHIFT;
+		attr1_val |= llcc_table[i].priority <<
+				ATTR1_PRIORITY_SHIFT;
+
+		max_cap_cacheline = MAX_CAP_TO_BYTES(llcc_table[i].max_cap);
+
+		/* LLCC instances can vary for each target.
+		 * The SW writes to broadcast register which gets propagated
+		 * to each llcc instace (llcc0,.. llccN).
+		 * Since the size of the memory is divided equally amongst the
+		 * llcc instances, we need to configure the max cap accordingly.
+		 */
+		max_cap_cacheline = max_cap_cacheline / drv_data->num_banks;
+		max_cap_cacheline >>= CACHE_LINE_SIZE_SHIFT;
+		attr1_val |= max_cap_cacheline << ATTR1_MAX_CAP_SHIFT;
+
+		attr0_val = llcc_table[i].res_ways & ATTR0_RES_WAYS_MASK;
+		attr0_val |= llcc_table[i].bonus_ways << ATTR0_BONUS_WAYS_SHIFT;
+
+		ret = regmap_write(drv_data->regmap, attr1_cfg, attr1_val);
+		if (ret)
+			return ret;
+		ret = regmap_write(drv_data->regmap, attr0_cfg, attr0_val);
+		if (ret)
+			return ret;
+		if (llcc_table[i].activate_on_init) {
+			desc.slice_id = llcc_table[i].slice_id;
+			ret = llcc_slice_activate(&desc);
+		}
+	}
+	return ret;
+}
+
+int qcom_llcc_probe(struct platform_device *pdev,
+		      const struct llcc_slice_config *llcc_cfg, u32 sz)
+{
+	u32 num_banks;
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	void __iomem *base;
+	int ret, i;
+
+	drv_data = devm_kzalloc(dev, sizeof(*drv_data), GFP_KERNEL);
+	if (!drv_data)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	drv_data->regmap = devm_regmap_init_mmio(dev, base,
+					&llcc_regmap_config);
+	if (IS_ERR(drv_data->regmap))
+		return PTR_ERR(drv_data->regmap);
+
+	ret = regmap_read(drv_data->regmap, LLCC_COMMON_STATUS0,
+						&num_banks);
+	if (ret)
+		return ret;
+
+	num_banks &= LLCC_LB_CNT_MASK;
+	num_banks >>= LLCC_LB_CNT_SHIFT;
+	drv_data->num_banks = num_banks;
+
+	for (i = 0; i < sz; i++)
+		if (llcc_cfg[i].slice_id > drv_data->max_slices)
+			drv_data->max_slices = llcc_cfg[i].slice_id;
+
+	drv_data->offsets = devm_kcalloc(dev, num_banks, sizeof(u32),
+							GFP_KERNEL);
+	if (!drv_data->offsets)
+		return -ENOMEM;
+
+	for (i = 0; i < num_banks; i++)
+		drv_data->offsets[i] = i * BANK_OFFSET_STRIDE;
+
+	drv_data->bcast_off = num_banks * BANK_OFFSET_STRIDE;
+
+	drv_data->bitmap = devm_kcalloc(dev,
+	BITS_TO_LONGS(drv_data->max_slices), sizeof(unsigned long),
+						GFP_KERNEL);
+	if (!drv_data->bitmap)
+		return -ENOMEM;
+
+	drv_data->cfg = llcc_cfg;
+	drv_data->cfg_size = sz;
+	mutex_init(&drv_data->lock);
+	platform_set_drvdata(pdev, drv_data);
+
+	return qcom_llcc_cfg_program(pdev);
+}
+EXPORT_SYMBOL_GPL(qcom_llcc_probe);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/soc/qcom/rmtfs_mem.c b/drivers/soc/qcom/rmtfs_mem.c
index c8999e38b005..8a3678c2e83c 100644
--- a/drivers/soc/qcom/rmtfs_mem.c
+++ b/drivers/soc/qcom/rmtfs_mem.c
@@ -184,6 +184,7 @@ static int qcom_rmtfs_mem_probe(struct platform_device *pdev)
 	device_initialize(&rmtfs_mem->dev);
 	rmtfs_mem->dev.parent = &pdev->dev;
 	rmtfs_mem->dev.groups = qcom_rmtfs_mem_groups;
+	rmtfs_mem->dev.release = qcom_rmtfs_mem_release_device;
 
 	rmtfs_mem->base = devm_memremap(&rmtfs_mem->dev, rmtfs_mem->addr,
 					rmtfs_mem->size, MEMREMAP_WC);
@@ -206,8 +207,6 @@ static int qcom_rmtfs_mem_probe(struct platform_device *pdev)
 		goto put_device;
 	}
 
-	rmtfs_mem->dev.release = qcom_rmtfs_mem_release_device;
-
 	ret = of_property_read_u32(node, "qcom,vmid", &vmid);
 	if (ret < 0 && ret != -EINVAL) {
 		dev_err(&pdev->dev, "failed to parse qcom,vmid\n");
diff --git a/drivers/soc/qcom/rpmh-internal.h b/drivers/soc/qcom/rpmh-internal.h
new file mode 100644
index 000000000000..a7bbbb67991c
--- /dev/null
+++ b/drivers/soc/qcom/rpmh-internal.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+
+#ifndef __RPM_INTERNAL_H__
+#define __RPM_INTERNAL_H__
+
+#include <linux/bitmap.h>
+#include <soc/qcom/tcs.h>
+
+#define TCS_TYPE_NR			4
+#define MAX_CMDS_PER_TCS		16
+#define MAX_TCS_PER_TYPE		3
+#define MAX_TCS_NR			(MAX_TCS_PER_TYPE * TCS_TYPE_NR)
+#define MAX_TCS_SLOTS			(MAX_CMDS_PER_TCS * MAX_TCS_PER_TYPE)
+
+struct rsc_drv;
+
+/**
+ * struct tcs_group: group of Trigger Command Sets (TCS) to send state requests
+ * to the controller
+ *
+ * @drv:       the controller
+ * @type:      type of the TCS in this group - active, sleep, wake
+ * @mask:      mask of the TCSes relative to all the TCSes in the RSC
+ * @offset:    start of the TCS group relative to the TCSes in the RSC
+ * @num_tcs:   number of TCSes in this type
+ * @ncpt:      number of commands in each TCS
+ * @lock:      lock for synchronizing this TCS writes
+ * @req:       requests that are sent from the TCS
+ * @cmd_cache: flattened cache of cmds in sleep/wake TCS
+ * @slots:     indicates which of @cmd_addr are occupied
+ */
+struct tcs_group {
+	struct rsc_drv *drv;
+	int type;
+	u32 mask;
+	u32 offset;
+	int num_tcs;
+	int ncpt;
+	spinlock_t lock;
+	const struct tcs_request *req[MAX_TCS_PER_TYPE];
+	u32 *cmd_cache;
+	DECLARE_BITMAP(slots, MAX_TCS_SLOTS);
+};
+
+/**
+ * struct rpmh_request: the message to be sent to rpmh-rsc
+ *
+ * @msg: the request
+ * @cmd: the payload that will be part of the @msg
+ * @completion: triggered when request is done
+ * @dev: the device making the request
+ * @err: err return from the controller
+ * @needs_free: check to free dynamically allocated request object
+ */
+struct rpmh_request {
+	struct tcs_request msg;
+	struct tcs_cmd cmd[MAX_RPMH_PAYLOAD];
+	struct completion *completion;
+	const struct device *dev;
+	int err;
+	bool needs_free;
+};
+
+/**
+ * struct rpmh_ctrlr: our representation of the controller
+ *
+ * @cache: the list of cached requests
+ * @cache_lock: synchronize access to the cache data
+ * @dirty: was the cache updated since flush
+ * @batch_cache: Cache sleep and wake requests sent as batch
+ */
+struct rpmh_ctrlr {
+	struct list_head cache;
+	spinlock_t cache_lock;
+	bool dirty;
+	struct list_head batch_cache;
+};
+
+/**
+ * struct rsc_drv: the Direct Resource Voter (DRV) of the
+ * Resource State Coordinator controller (RSC)
+ *
+ * @name:       controller identifier
+ * @tcs_base:   start address of the TCS registers in this controller
+ * @id:         instance id in the controller (Direct Resource Voter)
+ * @num_tcs:    number of TCSes in this DRV
+ * @tcs:        TCS groups
+ * @tcs_in_use: s/w state of the TCS
+ * @lock:       synchronize state of the controller
+ * @client:     handle to the DRV's client.
+ */
+struct rsc_drv {
+	const char *name;
+	void __iomem *tcs_base;
+	int id;
+	int num_tcs;
+	struct tcs_group tcs[TCS_TYPE_NR];
+	DECLARE_BITMAP(tcs_in_use, MAX_TCS_NR);
+	spinlock_t lock;
+	struct rpmh_ctrlr client;
+};
+
+int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg);
+int rpmh_rsc_write_ctrl_data(struct rsc_drv *drv,
+			     const struct tcs_request *msg);
+int rpmh_rsc_invalidate(struct rsc_drv *drv);
+
+void rpmh_tx_done(const struct tcs_request *msg, int r);
+
+#endif /* __RPM_INTERNAL_H__ */
diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c
new file mode 100644
index 000000000000..ee75da66d64b
--- /dev/null
+++ b/drivers/soc/qcom/rpmh-rsc.c
@@ -0,0 +1,693 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#define pr_fmt(fmt) "%s " fmt, KBUILD_MODNAME
+
+#include <linux/atomic.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include <soc/qcom/cmd-db.h>
+#include <soc/qcom/tcs.h>
+#include <dt-bindings/soc/qcom,rpmh-rsc.h>
+
+#include "rpmh-internal.h"
+
+#define CREATE_TRACE_POINTS
+#include "trace-rpmh.h"
+
+#define RSC_DRV_TCS_OFFSET		672
+#define RSC_DRV_CMD_OFFSET		20
+
+/* DRV Configuration Information Register */
+#define DRV_PRNT_CHLD_CONFIG		0x0C
+#define DRV_NUM_TCS_MASK		0x3F
+#define DRV_NUM_TCS_SHIFT		6
+#define DRV_NCPT_MASK			0x1F
+#define DRV_NCPT_SHIFT			27
+
+/* Register offsets */
+#define RSC_DRV_IRQ_ENABLE		0x00
+#define RSC_DRV_IRQ_STATUS		0x04
+#define RSC_DRV_IRQ_CLEAR		0x08
+#define RSC_DRV_CMD_WAIT_FOR_CMPL	0x10
+#define RSC_DRV_CONTROL			0x14
+#define RSC_DRV_STATUS			0x18
+#define RSC_DRV_CMD_ENABLE		0x1C
+#define RSC_DRV_CMD_MSGID		0x30
+#define RSC_DRV_CMD_ADDR		0x34
+#define RSC_DRV_CMD_DATA		0x38
+#define RSC_DRV_CMD_STATUS		0x3C
+#define RSC_DRV_CMD_RESP_DATA		0x40
+
+#define TCS_AMC_MODE_ENABLE		BIT(16)
+#define TCS_AMC_MODE_TRIGGER		BIT(24)
+
+/* TCS CMD register bit mask */
+#define CMD_MSGID_LEN			8
+#define CMD_MSGID_RESP_REQ		BIT(8)
+#define CMD_MSGID_WRITE			BIT(16)
+#define CMD_STATUS_ISSUED		BIT(8)
+#define CMD_STATUS_COMPL		BIT(16)
+
+static u32 read_tcs_reg(struct rsc_drv *drv, int reg, int tcs_id, int cmd_id)
+{
+	return readl_relaxed(drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id +
+			     RSC_DRV_CMD_OFFSET * cmd_id);
+}
+
+static void write_tcs_cmd(struct rsc_drv *drv, int reg, int tcs_id, int cmd_id,
+			  u32 data)
+{
+	writel_relaxed(data, drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id +
+		       RSC_DRV_CMD_OFFSET * cmd_id);
+}
+
+static void write_tcs_reg(struct rsc_drv *drv, int reg, int tcs_id, u32 data)
+{
+	writel_relaxed(data, drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id);
+}
+
+static void write_tcs_reg_sync(struct rsc_drv *drv, int reg, int tcs_id,
+			       u32 data)
+{
+	writel(data, drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id);
+	for (;;) {
+		if (data == readl(drv->tcs_base + reg +
+				  RSC_DRV_TCS_OFFSET * tcs_id))
+			break;
+		udelay(1);
+	}
+}
+
+static bool tcs_is_free(struct rsc_drv *drv, int tcs_id)
+{
+	return !test_bit(tcs_id, drv->tcs_in_use) &&
+	       read_tcs_reg(drv, RSC_DRV_STATUS, tcs_id, 0);
+}
+
+static struct tcs_group *get_tcs_of_type(struct rsc_drv *drv, int type)
+{
+	return &drv->tcs[type];
+}
+
+static int tcs_invalidate(struct rsc_drv *drv, int type)
+{
+	int m;
+	struct tcs_group *tcs;
+
+	tcs = get_tcs_of_type(drv, type);
+
+	spin_lock(&tcs->lock);
+	if (bitmap_empty(tcs->slots, MAX_TCS_SLOTS)) {
+		spin_unlock(&tcs->lock);
+		return 0;
+	}
+
+	for (m = tcs->offset; m < tcs->offset + tcs->num_tcs; m++) {
+		if (!tcs_is_free(drv, m)) {
+			spin_unlock(&tcs->lock);
+			return -EAGAIN;
+		}
+		write_tcs_reg_sync(drv, RSC_DRV_CMD_ENABLE, m, 0);
+	}
+	bitmap_zero(tcs->slots, MAX_TCS_SLOTS);
+	spin_unlock(&tcs->lock);
+
+	return 0;
+}
+
+/**
+ * rpmh_rsc_invalidate - Invalidate sleep and wake TCSes
+ *
+ * @drv: the RSC controller
+ */
+int rpmh_rsc_invalidate(struct rsc_drv *drv)
+{
+	int ret;
+
+	ret = tcs_invalidate(drv, SLEEP_TCS);
+	if (!ret)
+		ret = tcs_invalidate(drv, WAKE_TCS);
+
+	return ret;
+}
+
+static struct tcs_group *get_tcs_for_msg(struct rsc_drv *drv,
+					 const struct tcs_request *msg)
+{
+	int type, ret;
+	struct tcs_group *tcs;
+
+	switch (msg->state) {
+	case RPMH_ACTIVE_ONLY_STATE:
+		type = ACTIVE_TCS;
+		break;
+	case RPMH_WAKE_ONLY_STATE:
+		type = WAKE_TCS;
+		break;
+	case RPMH_SLEEP_STATE:
+		type = SLEEP_TCS;
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+
+	/*
+	 * If we are making an active request on a RSC that does not have a
+	 * dedicated TCS for active state use, then re-purpose a wake TCS to
+	 * send active votes.
+	 * NOTE: The driver must be aware that this RSC does not have a
+	 * dedicated AMC, and therefore would invalidate the sleep and wake
+	 * TCSes before making an active state request.
+	 */
+	tcs = get_tcs_of_type(drv, type);
+	if (msg->state == RPMH_ACTIVE_ONLY_STATE && !tcs->num_tcs) {
+		tcs = get_tcs_of_type(drv, WAKE_TCS);
+		if (tcs->num_tcs) {
+			ret = rpmh_rsc_invalidate(drv);
+			if (ret)
+				return ERR_PTR(ret);
+		}
+	}
+
+	return tcs;
+}
+
+static const struct tcs_request *get_req_from_tcs(struct rsc_drv *drv,
+						  int tcs_id)
+{
+	struct tcs_group *tcs;
+	int i;
+
+	for (i = 0; i < TCS_TYPE_NR; i++) {
+		tcs = &drv->tcs[i];
+		if (tcs->mask & BIT(tcs_id))
+			return tcs->req[tcs_id - tcs->offset];
+	}
+
+	return NULL;
+}
+
+/**
+ * tcs_tx_done: TX Done interrupt handler
+ */
+static irqreturn_t tcs_tx_done(int irq, void *p)
+{
+	struct rsc_drv *drv = p;
+	int i, j, err = 0;
+	unsigned long irq_status;
+	const struct tcs_request *req;
+	struct tcs_cmd *cmd;
+
+	irq_status = read_tcs_reg(drv, RSC_DRV_IRQ_STATUS, 0, 0);
+
+	for_each_set_bit(i, &irq_status, BITS_PER_LONG) {
+		req = get_req_from_tcs(drv, i);
+		if (!req) {
+			WARN_ON(1);
+			goto skip;
+		}
+
+		err = 0;
+		for (j = 0; j < req->num_cmds; j++) {
+			u32 sts;
+
+			cmd = &req->cmds[j];
+			sts = read_tcs_reg(drv, RSC_DRV_CMD_STATUS, i, j);
+			if (!(sts & CMD_STATUS_ISSUED) ||
+			   ((req->wait_for_compl || cmd->wait) &&
+			   !(sts & CMD_STATUS_COMPL))) {
+				pr_err("Incomplete request: %s: addr=%#x data=%#x",
+				       drv->name, cmd->addr, cmd->data);
+				err = -EIO;
+			}
+		}
+
+		trace_rpmh_tx_done(drv, i, req, err);
+skip:
+		/* Reclaim the TCS */
+		write_tcs_reg(drv, RSC_DRV_CMD_ENABLE, i, 0);
+		write_tcs_reg(drv, RSC_DRV_IRQ_CLEAR, 0, BIT(i));
+		spin_lock(&drv->lock);
+		clear_bit(i, drv->tcs_in_use);
+		spin_unlock(&drv->lock);
+		if (req)
+			rpmh_tx_done(req, err);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void __tcs_buffer_write(struct rsc_drv *drv, int tcs_id, int cmd_id,
+			       const struct tcs_request *msg)
+{
+	u32 msgid, cmd_msgid;
+	u32 cmd_enable = 0;
+	u32 cmd_complete;
+	struct tcs_cmd *cmd;
+	int i, j;
+
+	cmd_msgid = CMD_MSGID_LEN;
+	cmd_msgid |= msg->wait_for_compl ? CMD_MSGID_RESP_REQ : 0;
+	cmd_msgid |= CMD_MSGID_WRITE;
+
+	cmd_complete = read_tcs_reg(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, tcs_id, 0);
+
+	for (i = 0, j = cmd_id; i < msg->num_cmds; i++, j++) {
+		cmd = &msg->cmds[i];
+		cmd_enable |= BIT(j);
+		cmd_complete |= cmd->wait << j;
+		msgid = cmd_msgid;
+		msgid |= cmd->wait ? CMD_MSGID_RESP_REQ : 0;
+
+		write_tcs_cmd(drv, RSC_DRV_CMD_MSGID, tcs_id, j, msgid);
+		write_tcs_cmd(drv, RSC_DRV_CMD_ADDR, tcs_id, j, cmd->addr);
+		write_tcs_cmd(drv, RSC_DRV_CMD_DATA, tcs_id, j, cmd->data);
+		trace_rpmh_send_msg(drv, tcs_id, j, msgid, cmd);
+	}
+
+	write_tcs_reg(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, tcs_id, cmd_complete);
+	cmd_enable |= read_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id, 0);
+	write_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id, cmd_enable);
+}
+
+static void __tcs_trigger(struct rsc_drv *drv, int tcs_id)
+{
+	u32 enable;
+
+	/*
+	 * HW req: Clear the DRV_CONTROL and enable TCS again
+	 * While clearing ensure that the AMC mode trigger is cleared
+	 * and then the mode enable is cleared.
+	 */
+	enable = read_tcs_reg(drv, RSC_DRV_CONTROL, tcs_id, 0);
+	enable &= ~TCS_AMC_MODE_TRIGGER;
+	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+	enable &= ~TCS_AMC_MODE_ENABLE;
+	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+
+	/* Enable the AMC mode on the TCS and then trigger the TCS */
+	enable = TCS_AMC_MODE_ENABLE;
+	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+	enable |= TCS_AMC_MODE_TRIGGER;
+	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+}
+
+static int check_for_req_inflight(struct rsc_drv *drv, struct tcs_group *tcs,
+				  const struct tcs_request *msg)
+{
+	unsigned long curr_enabled;
+	u32 addr;
+	int i, j, k;
+	int tcs_id = tcs->offset;
+
+	for (i = 0; i < tcs->num_tcs; i++, tcs_id++) {
+		if (tcs_is_free(drv, tcs_id))
+			continue;
+
+		curr_enabled = read_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id, 0);
+
+		for_each_set_bit(j, &curr_enabled, MAX_CMDS_PER_TCS) {
+			addr = read_tcs_reg(drv, RSC_DRV_CMD_ADDR, tcs_id, j);
+			for (k = 0; k < msg->num_cmds; k++) {
+				if (addr == msg->cmds[k].addr)
+					return -EBUSY;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int find_free_tcs(struct tcs_group *tcs)
+{
+	int i;
+
+	for (i = 0; i < tcs->num_tcs; i++) {
+		if (tcs_is_free(tcs->drv, tcs->offset + i))
+			return tcs->offset + i;
+	}
+
+	return -EBUSY;
+}
+
+static int tcs_write(struct rsc_drv *drv, const struct tcs_request *msg)
+{
+	struct tcs_group *tcs;
+	int tcs_id;
+	unsigned long flags;
+	int ret;
+
+	tcs = get_tcs_for_msg(drv, msg);
+	if (IS_ERR(tcs))
+		return PTR_ERR(tcs);
+
+	spin_lock_irqsave(&tcs->lock, flags);
+	spin_lock(&drv->lock);
+	/*
+	 * The h/w does not like if we send a request to the same address,
+	 * when one is already in-flight or being processed.
+	 */
+	ret = check_for_req_inflight(drv, tcs, msg);
+	if (ret) {
+		spin_unlock(&drv->lock);
+		goto done_write;
+	}
+
+	tcs_id = find_free_tcs(tcs);
+	if (tcs_id < 0) {
+		ret = tcs_id;
+		spin_unlock(&drv->lock);
+		goto done_write;
+	}
+
+	tcs->req[tcs_id - tcs->offset] = msg;
+	set_bit(tcs_id, drv->tcs_in_use);
+	spin_unlock(&drv->lock);
+
+	__tcs_buffer_write(drv, tcs_id, 0, msg);
+	__tcs_trigger(drv, tcs_id);
+
+done_write:
+	spin_unlock_irqrestore(&tcs->lock, flags);
+	return ret;
+}
+
+/**
+ * rpmh_rsc_send_data: Validate the incoming message and write to the
+ * appropriate TCS block.
+ *
+ * @drv: the controller
+ * @msg: the data to be sent
+ *
+ * Return: 0 on success, -EINVAL on error.
+ * Note: This call blocks until a valid data is written to the TCS.
+ */
+int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg)
+{
+	int ret;
+
+	if (!msg || !msg->cmds || !msg->num_cmds ||
+	    msg->num_cmds > MAX_RPMH_PAYLOAD) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	do {
+		ret = tcs_write(drv, msg);
+		if (ret == -EBUSY) {
+			pr_info_ratelimited("TCS Busy, retrying RPMH message send: addr=%#x\n",
+					    msg->cmds[0].addr);
+			udelay(10);
+		}
+	} while (ret == -EBUSY);
+
+	return ret;
+}
+
+static int find_match(const struct tcs_group *tcs, const struct tcs_cmd *cmd,
+		      int len)
+{
+	int i, j;
+
+	/* Check for already cached commands */
+	for_each_set_bit(i, tcs->slots, MAX_TCS_SLOTS) {
+		if (tcs->cmd_cache[i] != cmd[0].addr)
+			continue;
+		if (i + len >= tcs->num_tcs * tcs->ncpt)
+			goto seq_err;
+		for (j = 0; j < len; j++) {
+			if (tcs->cmd_cache[i + j] != cmd[j].addr)
+				goto seq_err;
+		}
+		return i;
+	}
+
+	return -ENODATA;
+
+seq_err:
+	WARN(1, "Message does not match previous sequence.\n");
+	return -EINVAL;
+}
+
+static int find_slots(struct tcs_group *tcs, const struct tcs_request *msg,
+		      int *tcs_id, int *cmd_id)
+{
+	int slot, offset;
+	int i = 0;
+
+	/* Find if we already have the msg in our TCS */
+	slot = find_match(tcs, msg->cmds, msg->num_cmds);
+	if (slot >= 0)
+		goto copy_data;
+
+	/* Do over, until we can fit the full payload in a TCS */
+	do {
+		slot = bitmap_find_next_zero_area(tcs->slots, MAX_TCS_SLOTS,
+						  i, msg->num_cmds, 0);
+		if (slot == tcs->num_tcs * tcs->ncpt)
+			return -ENOMEM;
+		i += tcs->ncpt;
+	} while (slot + msg->num_cmds - 1 >= i);
+
+copy_data:
+	bitmap_set(tcs->slots, slot, msg->num_cmds);
+	/* Copy the addresses of the resources over to the slots */
+	for (i = 0; i < msg->num_cmds; i++)
+		tcs->cmd_cache[slot + i] = msg->cmds[i].addr;
+
+	offset = slot / tcs->ncpt;
+	*tcs_id = offset + tcs->offset;
+	*cmd_id = slot % tcs->ncpt;
+
+	return 0;
+}
+
+static int tcs_ctrl_write(struct rsc_drv *drv, const struct tcs_request *msg)
+{
+	struct tcs_group *tcs;
+	int tcs_id = 0, cmd_id = 0;
+	unsigned long flags;
+	int ret;
+
+	tcs = get_tcs_for_msg(drv, msg);
+	if (IS_ERR(tcs))
+		return PTR_ERR(tcs);
+
+	spin_lock_irqsave(&tcs->lock, flags);
+	/* find the TCS id and the command in the TCS to write to */
+	ret = find_slots(tcs, msg, &tcs_id, &cmd_id);
+	if (!ret)
+		__tcs_buffer_write(drv, tcs_id, cmd_id, msg);
+	spin_unlock_irqrestore(&tcs->lock, flags);
+
+	return ret;
+}
+
+/**
+ * rpmh_rsc_write_ctrl_data: Write request to the controller
+ *
+ * @drv: the controller
+ * @msg: the data to be written to the controller
+ *
+ * There is no response returned for writing the request to the controller.
+ */
+int rpmh_rsc_write_ctrl_data(struct rsc_drv *drv, const struct tcs_request *msg)
+{
+	if (!msg || !msg->cmds || !msg->num_cmds ||
+	    msg->num_cmds > MAX_RPMH_PAYLOAD) {
+		pr_err("Payload error\n");
+		return -EINVAL;
+	}
+
+	/* Data sent to this API will not be sent immediately */
+	if (msg->state == RPMH_ACTIVE_ONLY_STATE)
+		return -EINVAL;
+
+	return tcs_ctrl_write(drv, msg);
+}
+
+static int rpmh_probe_tcs_config(struct platform_device *pdev,
+				 struct rsc_drv *drv)
+{
+	struct tcs_type_config {
+		u32 type;
+		u32 n;
+	} tcs_cfg[TCS_TYPE_NR] = { { 0 } };
+	struct device_node *dn = pdev->dev.of_node;
+	u32 config, max_tcs, ncpt, offset;
+	int i, ret, n, st = 0;
+	struct tcs_group *tcs;
+	struct resource *res;
+	void __iomem *base;
+	char drv_id[10] = {0};
+
+	snprintf(drv_id, ARRAY_SIZE(drv_id), "drv-%d", drv->id);
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, drv_id);
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	ret = of_property_read_u32(dn, "qcom,tcs-offset", &offset);
+	if (ret)
+		return ret;
+	drv->tcs_base = base + offset;
+
+	config = readl_relaxed(base + DRV_PRNT_CHLD_CONFIG);
+
+	max_tcs = config;
+	max_tcs &= DRV_NUM_TCS_MASK << (DRV_NUM_TCS_SHIFT * drv->id);
+	max_tcs = max_tcs >> (DRV_NUM_TCS_SHIFT * drv->id);
+
+	ncpt = config & (DRV_NCPT_MASK << DRV_NCPT_SHIFT);
+	ncpt = ncpt >> DRV_NCPT_SHIFT;
+
+	n = of_property_count_u32_elems(dn, "qcom,tcs-config");
+	if (n != 2 * TCS_TYPE_NR)
+		return -EINVAL;
+
+	for (i = 0; i < TCS_TYPE_NR; i++) {
+		ret = of_property_read_u32_index(dn, "qcom,tcs-config",
+						 i * 2, &tcs_cfg[i].type);
+		if (ret)
+			return ret;
+		if (tcs_cfg[i].type >= TCS_TYPE_NR)
+			return -EINVAL;
+
+		ret = of_property_read_u32_index(dn, "qcom,tcs-config",
+						 i * 2 + 1, &tcs_cfg[i].n);
+		if (ret)
+			return ret;
+		if (tcs_cfg[i].n > MAX_TCS_PER_TYPE)
+			return -EINVAL;
+	}
+
+	for (i = 0; i < TCS_TYPE_NR; i++) {
+		tcs = &drv->tcs[tcs_cfg[i].type];
+		if (tcs->drv)
+			return -EINVAL;
+		tcs->drv = drv;
+		tcs->type = tcs_cfg[i].type;
+		tcs->num_tcs = tcs_cfg[i].n;
+		tcs->ncpt = ncpt;
+		spin_lock_init(&tcs->lock);
+
+		if (!tcs->num_tcs || tcs->type == CONTROL_TCS)
+			continue;
+
+		if (st + tcs->num_tcs > max_tcs ||
+		    st + tcs->num_tcs >= BITS_PER_BYTE * sizeof(tcs->mask))
+			return -EINVAL;
+
+		tcs->mask = ((1 << tcs->num_tcs) - 1) << st;
+		tcs->offset = st;
+		st += tcs->num_tcs;
+
+		/*
+		 * Allocate memory to cache sleep and wake requests to
+		 * avoid reading TCS register memory.
+		 */
+		if (tcs->type == ACTIVE_TCS)
+			continue;
+
+		tcs->cmd_cache = devm_kcalloc(&pdev->dev,
+					      tcs->num_tcs * ncpt, sizeof(u32),
+					      GFP_KERNEL);
+		if (!tcs->cmd_cache)
+			return -ENOMEM;
+	}
+
+	drv->num_tcs = st;
+
+	return 0;
+}
+
+static int rpmh_rsc_probe(struct platform_device *pdev)
+{
+	struct device_node *dn = pdev->dev.of_node;
+	struct rsc_drv *drv;
+	int ret, irq;
+
+	/*
+	 * Even though RPMh doesn't directly use cmd-db, all of its children
+	 * do. To avoid adding this check to our children we'll do it now.
+	 */
+	ret = cmd_db_ready();
+	if (ret) {
+		if (ret != -EPROBE_DEFER)
+			dev_err(&pdev->dev, "Command DB not available (%d)\n",
+									ret);
+		return ret;
+	}
+
+	drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_KERNEL);
+	if (!drv)
+		return -ENOMEM;
+
+	ret = of_property_read_u32(dn, "qcom,drv-id", &drv->id);
+	if (ret)
+		return ret;
+
+	drv->name = of_get_property(dn, "label", NULL);
+	if (!drv->name)
+		drv->name = dev_name(&pdev->dev);
+
+	ret = rpmh_probe_tcs_config(pdev, drv);
+	if (ret)
+		return ret;
+
+	spin_lock_init(&drv->lock);
+	bitmap_zero(drv->tcs_in_use, MAX_TCS_NR);
+
+	irq = platform_get_irq(pdev, drv->id);
+	if (irq < 0)
+		return irq;
+
+	ret = devm_request_irq(&pdev->dev, irq, tcs_tx_done,
+			       IRQF_TRIGGER_HIGH | IRQF_NO_SUSPEND,
+			       drv->name, drv);
+	if (ret)
+		return ret;
+
+	/* Enable the active TCS to send requests immediately */
+	write_tcs_reg(drv, RSC_DRV_IRQ_ENABLE, 0, drv->tcs[ACTIVE_TCS].mask);
+
+	spin_lock_init(&drv->client.cache_lock);
+	INIT_LIST_HEAD(&drv->client.cache);
+	INIT_LIST_HEAD(&drv->client.batch_cache);
+
+	dev_set_drvdata(&pdev->dev, drv);
+
+	return devm_of_platform_populate(&pdev->dev);
+}
+
+static const struct of_device_id rpmh_drv_match[] = {
+	{ .compatible = "qcom,rpmh-rsc", },
+	{ }
+};
+
+static struct platform_driver rpmh_driver = {
+	.probe = rpmh_rsc_probe,
+	.driver = {
+		  .name = "rpmh",
+		  .of_match_table = rpmh_drv_match,
+	},
+};
+
+static int __init rpmh_driver_init(void)
+{
+	return platform_driver_register(&rpmh_driver);
+}
+arch_initcall(rpmh_driver_init);
diff --git a/drivers/soc/qcom/rpmh.c b/drivers/soc/qcom/rpmh.c
new file mode 100644
index 000000000000..c7beb6841289
--- /dev/null
+++ b/drivers/soc/qcom/rpmh.c
@@ -0,0 +1,513 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/atomic.h>
+#include <linux/bug.h>
+#include <linux/interrupt.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/wait.h>
+
+#include <soc/qcom/rpmh.h>
+
+#include "rpmh-internal.h"
+
+#define RPMH_TIMEOUT_MS			msecs_to_jiffies(10000)
+
+#define DEFINE_RPMH_MSG_ONSTACK(dev, s, q, name)	\
+	struct rpmh_request name = {			\
+		.msg = {				\
+			.state = s,			\
+			.cmds = name.cmd,		\
+			.num_cmds = 0,			\
+			.wait_for_compl = true,		\
+		},					\
+		.cmd = { { 0 } },			\
+		.completion = q,			\
+		.dev = dev,				\
+		.needs_free = false,				\
+	}
+
+#define ctrlr_to_drv(ctrlr) container_of(ctrlr, struct rsc_drv, client)
+
+/**
+ * struct cache_req: the request object for caching
+ *
+ * @addr: the address of the resource
+ * @sleep_val: the sleep vote
+ * @wake_val: the wake vote
+ * @list: linked list obj
+ */
+struct cache_req {
+	u32 addr;
+	u32 sleep_val;
+	u32 wake_val;
+	struct list_head list;
+};
+
+/**
+ * struct batch_cache_req - An entry in our batch catch
+ *
+ * @list: linked list obj
+ * @count: number of messages
+ * @rpm_msgs: the messages
+ */
+
+struct batch_cache_req {
+	struct list_head list;
+	int count;
+	struct rpmh_request rpm_msgs[];
+};
+
+static struct rpmh_ctrlr *get_rpmh_ctrlr(const struct device *dev)
+{
+	struct rsc_drv *drv = dev_get_drvdata(dev->parent);
+
+	return &drv->client;
+}
+
+void rpmh_tx_done(const struct tcs_request *msg, int r)
+{
+	struct rpmh_request *rpm_msg = container_of(msg, struct rpmh_request,
+						    msg);
+	struct completion *compl = rpm_msg->completion;
+
+	rpm_msg->err = r;
+
+	if (r)
+		dev_err(rpm_msg->dev, "RPMH TX fail in msg addr=%#x, err=%d\n",
+			rpm_msg->msg.cmds[0].addr, r);
+
+	if (!compl)
+		goto exit;
+
+	/* Signal the blocking thread we are done */
+	complete(compl);
+
+exit:
+	if (rpm_msg->needs_free)
+		kfree(rpm_msg);
+}
+
+static struct cache_req *__find_req(struct rpmh_ctrlr *ctrlr, u32 addr)
+{
+	struct cache_req *p, *req = NULL;
+
+	list_for_each_entry(p, &ctrlr->cache, list) {
+		if (p->addr == addr) {
+			req = p;
+			break;
+		}
+	}
+
+	return req;
+}
+
+static struct cache_req *cache_rpm_request(struct rpmh_ctrlr *ctrlr,
+					   enum rpmh_state state,
+					   struct tcs_cmd *cmd)
+{
+	struct cache_req *req;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctrlr->cache_lock, flags);
+	req = __find_req(ctrlr, cmd->addr);
+	if (req)
+		goto existing;
+
+	req = kzalloc(sizeof(*req), GFP_ATOMIC);
+	if (!req) {
+		req = ERR_PTR(-ENOMEM);
+		goto unlock;
+	}
+
+	req->addr = cmd->addr;
+	req->sleep_val = req->wake_val = UINT_MAX;
+	INIT_LIST_HEAD(&req->list);
+	list_add_tail(&req->list, &ctrlr->cache);
+
+existing:
+	switch (state) {
+	case RPMH_ACTIVE_ONLY_STATE:
+		if (req->sleep_val != UINT_MAX)
+			req->wake_val = cmd->data;
+		break;
+	case RPMH_WAKE_ONLY_STATE:
+		req->wake_val = cmd->data;
+		break;
+	case RPMH_SLEEP_STATE:
+		req->sleep_val = cmd->data;
+		break;
+	default:
+		break;
+	}
+
+	ctrlr->dirty = true;
+unlock:
+	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
+
+	return req;
+}
+
+/**
+ * __rpmh_write: Cache and send the RPMH request
+ *
+ * @dev: The device making the request
+ * @state: Active/Sleep request type
+ * @rpm_msg: The data that needs to be sent (cmds).
+ *
+ * Cache the RPMH request and send if the state is ACTIVE_ONLY.
+ * SLEEP/WAKE_ONLY requests are not sent to the controller at
+ * this time. Use rpmh_flush() to send them to the controller.
+ */
+static int __rpmh_write(const struct device *dev, enum rpmh_state state,
+			struct rpmh_request *rpm_msg)
+{
+	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
+	int ret = -EINVAL;
+	struct cache_req *req;
+	int i;
+
+	rpm_msg->msg.state = state;
+
+	/* Cache the request in our store and link the payload */
+	for (i = 0; i < rpm_msg->msg.num_cmds; i++) {
+		req = cache_rpm_request(ctrlr, state, &rpm_msg->msg.cmds[i]);
+		if (IS_ERR(req))
+			return PTR_ERR(req);
+	}
+
+	rpm_msg->msg.state = state;
+
+	if (state == RPMH_ACTIVE_ONLY_STATE) {
+		WARN_ON(irqs_disabled());
+		ret = rpmh_rsc_send_data(ctrlr_to_drv(ctrlr), &rpm_msg->msg);
+	} else {
+		ret = rpmh_rsc_write_ctrl_data(ctrlr_to_drv(ctrlr),
+				&rpm_msg->msg);
+		/* Clean up our call by spoofing tx_done */
+		rpmh_tx_done(&rpm_msg->msg, ret);
+	}
+
+	return ret;
+}
+
+static int __fill_rpmh_msg(struct rpmh_request *req, enum rpmh_state state,
+		const struct tcs_cmd *cmd, u32 n)
+{
+	if (!cmd || !n || n > MAX_RPMH_PAYLOAD)
+		return -EINVAL;
+
+	memcpy(req->cmd, cmd, n * sizeof(*cmd));
+
+	req->msg.state = state;
+	req->msg.cmds = req->cmd;
+	req->msg.num_cmds = n;
+
+	return 0;
+}
+
+/**
+ * rpmh_write_async: Write a set of RPMH commands
+ *
+ * @dev: The device making the request
+ * @state: Active/sleep set
+ * @cmd: The payload data
+ * @n: The number of elements in payload
+ *
+ * Write a set of RPMH commands, the order of commands is maintained
+ * and will be sent as a single shot.
+ */
+int rpmh_write_async(const struct device *dev, enum rpmh_state state,
+		     const struct tcs_cmd *cmd, u32 n)
+{
+	struct rpmh_request *rpm_msg;
+	int ret;
+
+	rpm_msg = kzalloc(sizeof(*rpm_msg), GFP_ATOMIC);
+	if (!rpm_msg)
+		return -ENOMEM;
+	rpm_msg->needs_free = true;
+
+	ret = __fill_rpmh_msg(rpm_msg, state, cmd, n);
+	if (ret) {
+		kfree(rpm_msg);
+		return ret;
+	}
+
+	return __rpmh_write(dev, state, rpm_msg);
+}
+EXPORT_SYMBOL(rpmh_write_async);
+
+/**
+ * rpmh_write: Write a set of RPMH commands and block until response
+ *
+ * @rc: The RPMH handle got from rpmh_get_client
+ * @state: Active/sleep set
+ * @cmd: The payload data
+ * @n: The number of elements in @cmd
+ *
+ * May sleep. Do not call from atomic contexts.
+ */
+int rpmh_write(const struct device *dev, enum rpmh_state state,
+	       const struct tcs_cmd *cmd, u32 n)
+{
+	DECLARE_COMPLETION_ONSTACK(compl);
+	DEFINE_RPMH_MSG_ONSTACK(dev, state, &compl, rpm_msg);
+	int ret;
+
+	if (!cmd || !n || n > MAX_RPMH_PAYLOAD)
+		return -EINVAL;
+
+	memcpy(rpm_msg.cmd, cmd, n * sizeof(*cmd));
+	rpm_msg.msg.num_cmds = n;
+
+	ret = __rpmh_write(dev, state, &rpm_msg);
+	if (ret)
+		return ret;
+
+	ret = wait_for_completion_timeout(&compl, RPMH_TIMEOUT_MS);
+	WARN_ON(!ret);
+	return (ret > 0) ? 0 : -ETIMEDOUT;
+}
+EXPORT_SYMBOL(rpmh_write);
+
+static void cache_batch(struct rpmh_ctrlr *ctrlr, struct batch_cache_req *req)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctrlr->cache_lock, flags);
+	list_add_tail(&req->list, &ctrlr->batch_cache);
+	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
+}
+
+static int flush_batch(struct rpmh_ctrlr *ctrlr)
+{
+	struct batch_cache_req *req;
+	const struct rpmh_request *rpm_msg;
+	unsigned long flags;
+	int ret = 0;
+	int i;
+
+	/* Send Sleep/Wake requests to the controller, expect no response */
+	spin_lock_irqsave(&ctrlr->cache_lock, flags);
+	list_for_each_entry(req, &ctrlr->batch_cache, list) {
+		for (i = 0; i < req->count; i++) {
+			rpm_msg = req->rpm_msgs + i;
+			ret = rpmh_rsc_write_ctrl_data(ctrlr_to_drv(ctrlr),
+						       &rpm_msg->msg);
+			if (ret)
+				break;
+		}
+	}
+	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
+
+	return ret;
+}
+
+static void invalidate_batch(struct rpmh_ctrlr *ctrlr)
+{
+	struct batch_cache_req *req, *tmp;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctrlr->cache_lock, flags);
+	list_for_each_entry_safe(req, tmp, &ctrlr->batch_cache, list)
+		kfree(req);
+	INIT_LIST_HEAD(&ctrlr->batch_cache);
+	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
+}
+
+/**
+ * rpmh_write_batch: Write multiple sets of RPMH commands and wait for the
+ * batch to finish.
+ *
+ * @dev: the device making the request
+ * @state: Active/sleep set
+ * @cmd: The payload data
+ * @n: The array of count of elements in each batch, 0 terminated.
+ *
+ * Write a request to the RSC controller without caching. If the request
+ * state is ACTIVE, then the requests are treated as completion request
+ * and sent to the controller immediately. The function waits until all the
+ * commands are complete. If the request was to SLEEP or WAKE_ONLY, then the
+ * request is sent as fire-n-forget and no ack is expected.
+ *
+ * May sleep. Do not call from atomic contexts for ACTIVE_ONLY requests.
+ */
+int rpmh_write_batch(const struct device *dev, enum rpmh_state state,
+		     const struct tcs_cmd *cmd, u32 *n)
+{
+	struct batch_cache_req *req;
+	struct rpmh_request *rpm_msgs;
+	DECLARE_COMPLETION_ONSTACK(compl);
+	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
+	unsigned long time_left;
+	int count = 0;
+	int ret, i, j;
+
+	if (!cmd || !n)
+		return -EINVAL;
+
+	while (n[count] > 0)
+		count++;
+	if (!count)
+		return -EINVAL;
+
+	req = kzalloc(sizeof(*req) + count * sizeof(req->rpm_msgs[0]),
+		      GFP_ATOMIC);
+	if (!req)
+		return -ENOMEM;
+	req->count = count;
+	rpm_msgs = req->rpm_msgs;
+
+	for (i = 0; i < count; i++) {
+		__fill_rpmh_msg(rpm_msgs + i, state, cmd, n[i]);
+		cmd += n[i];
+	}
+
+	if (state != RPMH_ACTIVE_ONLY_STATE) {
+		cache_batch(ctrlr, req);
+		return 0;
+	}
+
+	for (i = 0; i < count; i++) {
+		rpm_msgs[i].completion = &compl;
+		ret = rpmh_rsc_send_data(ctrlr_to_drv(ctrlr), &rpm_msgs[i].msg);
+		if (ret) {
+			pr_err("Error(%d) sending RPMH message addr=%#x\n",
+			       ret, rpm_msgs[i].msg.cmds[0].addr);
+			for (j = i; j < count; j++)
+				rpmh_tx_done(&rpm_msgs[j].msg, ret);
+			break;
+		}
+	}
+
+	time_left = RPMH_TIMEOUT_MS;
+	for (i = 0; i < count; i++) {
+		time_left = wait_for_completion_timeout(&compl, time_left);
+		if (!time_left) {
+			/*
+			 * Better hope they never finish because they'll signal
+			 * the completion on our stack and that's bad once
+			 * we've returned from the function.
+			 */
+			WARN_ON(1);
+			ret = -ETIMEDOUT;
+			goto exit;
+		}
+	}
+
+exit:
+	kfree(req);
+
+	return ret;
+}
+EXPORT_SYMBOL(rpmh_write_batch);
+
+static int is_req_valid(struct cache_req *req)
+{
+	return (req->sleep_val != UINT_MAX &&
+		req->wake_val != UINT_MAX &&
+		req->sleep_val != req->wake_val);
+}
+
+static int send_single(const struct device *dev, enum rpmh_state state,
+		       u32 addr, u32 data)
+{
+	DEFINE_RPMH_MSG_ONSTACK(dev, state, NULL, rpm_msg);
+	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
+
+	/* Wake sets are always complete and sleep sets are not */
+	rpm_msg.msg.wait_for_compl = (state == RPMH_WAKE_ONLY_STATE);
+	rpm_msg.cmd[0].addr = addr;
+	rpm_msg.cmd[0].data = data;
+	rpm_msg.msg.num_cmds = 1;
+
+	return rpmh_rsc_write_ctrl_data(ctrlr_to_drv(ctrlr), &rpm_msg.msg);
+}
+
+/**
+ * rpmh_flush: Flushes the buffered active and sleep sets to TCS
+ *
+ * @dev: The device making the request
+ *
+ * Return: -EBUSY if the controller is busy, probably waiting on a response
+ * to a RPMH request sent earlier.
+ *
+ * This function is always called from the sleep code from the last CPU
+ * that is powering down the entire system. Since no other RPMH API would be
+ * executing at this time, it is safe to run lockless.
+ */
+int rpmh_flush(const struct device *dev)
+{
+	struct cache_req *p;
+	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
+	int ret;
+
+	if (!ctrlr->dirty) {
+		pr_debug("Skipping flush, TCS has latest data.\n");
+		return 0;
+	}
+
+	/* First flush the cached batch requests */
+	ret = flush_batch(ctrlr);
+	if (ret)
+		return ret;
+
+	/*
+	 * Nobody else should be calling this function other than system PM,
+	 * hence we can run without locks.
+	 */
+	list_for_each_entry(p, &ctrlr->cache, list) {
+		if (!is_req_valid(p)) {
+			pr_debug("%s: skipping RPMH req: a:%#x s:%#x w:%#x",
+				 __func__, p->addr, p->sleep_val, p->wake_val);
+			continue;
+		}
+		ret = send_single(dev, RPMH_SLEEP_STATE, p->addr, p->sleep_val);
+		if (ret)
+			return ret;
+		ret = send_single(dev, RPMH_WAKE_ONLY_STATE,
+				  p->addr, p->wake_val);
+		if (ret)
+			return ret;
+	}
+
+	ctrlr->dirty = false;
+
+	return 0;
+}
+EXPORT_SYMBOL(rpmh_flush);
+
+/**
+ * rpmh_invalidate: Invalidate all sleep and active sets
+ * sets.
+ *
+ * @dev: The device making the request
+ *
+ * Invalidate the sleep and active values in the TCS blocks.
+ */
+int rpmh_invalidate(const struct device *dev)
+{
+	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
+	int ret;
+
+	invalidate_batch(ctrlr);
+	ctrlr->dirty = true;
+
+	do {
+		ret = rpmh_rsc_invalidate(ctrlr_to_drv(ctrlr));
+	} while (ret == -EAGAIN);
+
+	return ret;
+}
+EXPORT_SYMBOL(rpmh_invalidate);
diff --git a/drivers/soc/qcom/smem.c b/drivers/soc/qcom/smem.c
index 70b2ee80d6bd..bf4bd71ab53f 100644
--- a/drivers/soc/qcom/smem.c
+++ b/drivers/soc/qcom/smem.c
@@ -364,11 +364,6 @@ static int qcom_smem_alloc_private(struct qcom_smem *smem,
 	end = phdr_to_last_uncached_entry(phdr);
 	cached = phdr_to_last_cached_entry(phdr);
 
-	if (smem->global_partition) {
-		dev_err(smem->dev, "Already found the global partition\n");
-		return -EINVAL;
-	}
-
 	while (hdr < end) {
 		if (hdr->canary != SMEM_PRIVATE_CANARY)
 			goto bad_canary;
@@ -736,6 +731,11 @@ static int qcom_smem_set_global_partition(struct qcom_smem *smem)
 	bool found = false;
 	int i;
 
+	if (smem->global_partition) {
+		dev_err(smem->dev, "Already found the global partition\n");
+		return -EINVAL;
+	}
+
 	ptable = qcom_smem_get_ptable(smem);
 	if (IS_ERR(ptable))
 		return PTR_ERR(ptable);
diff --git a/drivers/soc/qcom/trace-rpmh.h b/drivers/soc/qcom/trace-rpmh.h
new file mode 100644
index 000000000000..feb0cb455e37
--- /dev/null
+++ b/drivers/soc/qcom/trace-rpmh.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#if !defined(_TRACE_RPMH_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_RPMH_H
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM rpmh
+
+#include <linux/tracepoint.h>
+#include "rpmh-internal.h"
+
+TRACE_EVENT(rpmh_tx_done,
+
+	TP_PROTO(struct rsc_drv *d, int m, const struct tcs_request *r, int e),
+
+	TP_ARGS(d, m, r, e),
+
+	TP_STRUCT__entry(
+			 __string(name, d->name)
+			 __field(int, m)
+			 __field(u32, addr)
+			 __field(u32, data)
+			 __field(int, err)
+	),
+
+	TP_fast_assign(
+		       __assign_str(name, d->name);
+		       __entry->m = m;
+		       __entry->addr = r->cmds[0].addr;
+		       __entry->data = r->cmds[0].data;
+		       __entry->err = e;
+	),
+
+	TP_printk("%s: ack: tcs-m: %d addr: %#x data: %#x errno: %d",
+		  __get_str(name), __entry->m, __entry->addr, __entry->data,
+		  __entry->err)
+);
+
+TRACE_EVENT(rpmh_send_msg,
+
+	TP_PROTO(struct rsc_drv *d, int m, int n, u32 h,
+		 const struct tcs_cmd *c),
+
+	TP_ARGS(d, m, n, h, c),
+
+	TP_STRUCT__entry(
+			 __string(name, d->name)
+			 __field(int, m)
+			 __field(int, n)
+			 __field(u32, hdr)
+			 __field(u32, addr)
+			 __field(u32, data)
+			 __field(bool, wait)
+	),
+
+	TP_fast_assign(
+		       __assign_str(name, d->name);
+		       __entry->m = m;
+		       __entry->n = n;
+		       __entry->hdr = h;
+		       __entry->addr = c->addr;
+		       __entry->data = c->data;
+		       __entry->wait = c->wait;
+	),
+
+	TP_printk("%s: send-msg: tcs(m): %d cmd(n): %d msgid: %#x addr: %#x data: %#x complete: %d",
+		  __get_str(name), __entry->m, __entry->n, __entry->hdr,
+		  __entry->addr, __entry->data, __entry->wait)
+);
+
+#endif /* _TRACE_RPMH_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace-rpmh
+
+#include <trace/define_trace.h>
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index ad5d68e1dab7..671d078349cc 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -688,6 +688,19 @@ config SPI_TXX9
 	help
 	  SPI driver for Toshiba TXx9 MIPS SoCs
 
+config SPI_UNIPHIER
+	tristate "Socionext UniPhier SPI Controller"
+	depends on (ARCH_UNIPHIER || COMPILE_TEST) && OF
+	help
+	  This enables a driver for the Socionext UniPhier SoC SCSSI SPI controller.
+
+	  UniPhier SoCs have SCSSI and MCSSI SPI controllers.
+	  Every UniPhier SoC has SCSSI which supports single channel.
+	  Older UniPhier Pro4/Pro5 also has MCSSI which support multiple channels.
+	  This driver supports SCSSI only.
+
+	  If your SoC supports SCSSI, say Y here.
+
 config SPI_XCOMM
 	tristate "Analog Devices AD-FMCOMMS1-EBZ SPI-I2C-bridge driver"
 	depends on I2C
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index cb1f4378b87c..a90d55970036 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -101,6 +101,7 @@ spi-thunderx-objs			:= spi-cavium.o spi-cavium-thunderx.o
 obj-$(CONFIG_SPI_THUNDERX)		+= spi-thunderx.o
 obj-$(CONFIG_SPI_TOPCLIFF_PCH)		+= spi-topcliff-pch.o
 obj-$(CONFIG_SPI_TXX9)			+= spi-txx9.o
+obj-$(CONFIG_SPI_UNIPHIER)		+= spi-uniphier.o
 obj-$(CONFIG_SPI_XCOMM)		+= spi-xcomm.o
 obj-$(CONFIG_SPI_XILINX)		+= spi-xilinx.o
 obj-$(CONFIG_SPI_XLP)			+= spi-xlp.o
diff --git a/drivers/spi/spi-ath79.c b/drivers/spi/spi-ath79.c
index 0719bd484891..3f6b657394de 100644
--- a/drivers/spi/spi-ath79.c
+++ b/drivers/spi/spi-ath79.c
@@ -176,7 +176,7 @@ static void ath79_spi_cleanup(struct spi_device *spi)
 }
 
 static u32 ath79_spi_txrx_mode0(struct spi_device *spi, unsigned int nsecs,
-			       u32 word, u8 bits)
+			       u32 word, u8 bits, unsigned flags)
 {
 	struct ath79_spi *sp = ath79_spidev_to_sp(spi);
 	u32 ioc = sp->ioc_base;
diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c
index 3aa9e6e3dac8..f29176000b8d 100644
--- a/drivers/spi/spi-bitbang.c
+++ b/drivers/spi/spi-bitbang.c
@@ -49,22 +49,26 @@
 struct spi_bitbang_cs {
 	unsigned	nsecs;	/* (clock cycle time)/2 */
 	u32		(*txrx_word)(struct spi_device *spi, unsigned nsecs,
-					u32 word, u8 bits);
+					u32 word, u8 bits, unsigned flags);
 	unsigned	(*txrx_bufs)(struct spi_device *,
 					u32 (*txrx_word)(
 						struct spi_device *spi,
 						unsigned nsecs,
-						u32 word, u8 bits),
-					unsigned, struct spi_transfer *);
+						u32 word, u8 bits,
+						unsigned flags),
+					unsigned, struct spi_transfer *,
+					unsigned);
 };
 
 static unsigned bitbang_txrx_8(
 	struct spi_device	*spi,
 	u32			(*txrx_word)(struct spi_device *spi,
 					unsigned nsecs,
-					u32 word, u8 bits),
+					u32 word, u8 bits,
+					unsigned flags),
 	unsigned		ns,
-	struct spi_transfer	*t
+	struct spi_transfer	*t,
+	unsigned flags
 ) {
 	unsigned		bits = t->bits_per_word;
 	unsigned		count = t->len;
@@ -76,7 +80,7 @@ static unsigned bitbang_txrx_8(
 
 		if (tx)
 			word = *tx++;
-		word = txrx_word(spi, ns, word, bits);
+		word = txrx_word(spi, ns, word, bits, flags);
 		if (rx)
 			*rx++ = word;
 		count -= 1;
@@ -88,9 +92,11 @@ static unsigned bitbang_txrx_16(
 	struct spi_device	*spi,
 	u32			(*txrx_word)(struct spi_device *spi,
 					unsigned nsecs,
-					u32 word, u8 bits),
+					u32 word, u8 bits,
+					unsigned flags),
 	unsigned		ns,
-	struct spi_transfer	*t
+	struct spi_transfer	*t,
+	unsigned flags
 ) {
 	unsigned		bits = t->bits_per_word;
 	unsigned		count = t->len;
@@ -102,7 +108,7 @@ static unsigned bitbang_txrx_16(
 
 		if (tx)
 			word = *tx++;
-		word = txrx_word(spi, ns, word, bits);
+		word = txrx_word(spi, ns, word, bits, flags);
 		if (rx)
 			*rx++ = word;
 		count -= 2;
@@ -114,9 +120,11 @@ static unsigned bitbang_txrx_32(
 	struct spi_device	*spi,
 	u32			(*txrx_word)(struct spi_device *spi,
 					unsigned nsecs,
-					u32 word, u8 bits),
+					u32 word, u8 bits,
+					unsigned flags),
 	unsigned		ns,
-	struct spi_transfer	*t
+	struct spi_transfer	*t,
+	unsigned flags
 ) {
 	unsigned		bits = t->bits_per_word;
 	unsigned		count = t->len;
@@ -128,7 +136,7 @@ static unsigned bitbang_txrx_32(
 
 		if (tx)
 			word = *tx++;
-		word = txrx_word(spi, ns, word, bits);
+		word = txrx_word(spi, ns, word, bits, flags);
 		if (rx)
 			*rx++ = word;
 		count -= 4;
@@ -235,8 +243,24 @@ static int spi_bitbang_bufs(struct spi_device *spi, struct spi_transfer *t)
 {
 	struct spi_bitbang_cs	*cs = spi->controller_state;
 	unsigned		nsecs = cs->nsecs;
+	struct spi_bitbang	*bitbang;
+
+	bitbang = spi_master_get_devdata(spi->master);
+	if (bitbang->set_line_direction) {
+		int err;
 
-	return cs->txrx_bufs(spi, cs->txrx_word, nsecs, t);
+		err = bitbang->set_line_direction(spi, !!(t->tx_buf));
+		if (err < 0)
+			return err;
+	}
+
+	if (spi->mode & SPI_3WIRE) {
+		unsigned flags;
+
+		flags = t->tx_buf ? SPI_MASTER_NO_RX : SPI_MASTER_NO_TX;
+		return cs->txrx_bufs(spi, cs->txrx_word, nsecs, t, flags);
+	}
+	return cs->txrx_bufs(spi, cs->txrx_word, nsecs, t, 0);
 }
 
 /*----------------------------------------------------------------------*/
diff --git a/drivers/spi/spi-butterfly.c b/drivers/spi/spi-butterfly.c
index 22a31e4a1a11..1a3510215841 100644
--- a/drivers/spi/spi-butterfly.c
+++ b/drivers/spi/spi-butterfly.c
@@ -144,9 +144,9 @@ static void butterfly_chipselect(struct spi_device *spi, int value)
 
 static u32
 butterfly_txrx_word_mode0(struct spi_device *spi, unsigned nsecs, u32 word,
-			  u8 bits)
+			  u8 bits, unsigned flags)
 {
-	return bitbang_txrx_be_cpha0(spi, nsecs, 0, 0, word, bits);
+	return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits);
 }
 
 /*----------------------------------------------------------------------*/
diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c
index f3dad6fcdc35..7c88f74f7f47 100644
--- a/drivers/spi/spi-cadence.c
+++ b/drivers/spi/spi-cadence.c
@@ -319,7 +319,7 @@ static void cdns_spi_fill_tx_fifo(struct cdns_spi *xspi)
 		 */
 		if (cdns_spi_read(xspi, CDNS_SPI_ISR) &
 		    CDNS_SPI_IXR_TXFULL)
-			usleep_range(10, 20);
+			udelay(10);
 
 		if (xspi->txbuf)
 			cdns_spi_write(xspi, CDNS_SPI_TXD, *xspi->txbuf++);
@@ -739,7 +739,7 @@ static int __maybe_unused cnds_runtime_resume(struct device *dev)
 	ret = clk_prepare_enable(xspi->ref_clk);
 	if (ret) {
 		dev_err(dev, "Cannot enable device clock.\n");
-		clk_disable(xspi->pclk);
+		clk_disable_unprepare(xspi->pclk);
 		return ret;
 	}
 	return 0;
diff --git a/drivers/spi/spi-davinci.c b/drivers/spi/spi-davinci.c
index 577084bb911b..a02099c90c5c 100644
--- a/drivers/spi/spi-davinci.c
+++ b/drivers/spi/spi-davinci.c
@@ -217,7 +217,7 @@ static void davinci_spi_chipselect(struct spi_device *spi, int value)
 	pdata = &dspi->pdata;
 
 	/* program delay transfers if tx_delay is non zero */
-	if (spicfg->wdelay)
+	if (spicfg && spicfg->wdelay)
 		spidat1 |= SPIDAT1_WDEL;
 
 	/*
diff --git a/drivers/spi/spi-dw-mmio.c b/drivers/spi/spi-dw-mmio.c
index d25cc4037e23..e80f60ed6fdf 100644
--- a/drivers/spi/spi-dw-mmio.c
+++ b/drivers/spi/spi-dw-mmio.c
@@ -15,11 +15,13 @@
 #include <linux/slab.h>
 #include <linux/spi/spi.h>
 #include <linux/scatterlist.h>
+#include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_gpio.h>
 #include <linux/of_platform.h>
 #include <linux/property.h>
+#include <linux/regmap.h>
 
 #include "spi-dw.h"
 
@@ -28,10 +30,90 @@
 struct dw_spi_mmio {
 	struct dw_spi  dws;
 	struct clk     *clk;
+	void           *priv;
 };
 
+#define MSCC_CPU_SYSTEM_CTRL_GENERAL_CTRL	0x24
+#define OCELOT_IF_SI_OWNER_MASK			GENMASK(5, 4)
+#define OCELOT_IF_SI_OWNER_OFFSET		4
+#define MSCC_IF_SI_OWNER_SISL			0
+#define MSCC_IF_SI_OWNER_SIBM			1
+#define MSCC_IF_SI_OWNER_SIMC			2
+
+#define MSCC_SPI_MST_SW_MODE			0x14
+#define MSCC_SPI_MST_SW_MODE_SW_PIN_CTRL_MODE	BIT(13)
+#define MSCC_SPI_MST_SW_MODE_SW_SPI_CS(x)	(x << 5)
+
+struct dw_spi_mscc {
+	struct regmap       *syscon;
+	void __iomem        *spi_mst;
+};
+
+/*
+ * The Designware SPI controller (referred to as master in the documentation)
+ * automatically deasserts chip select when the tx fifo is empty. The chip
+ * selects then needs to be either driven as GPIOs or, for the first 4 using the
+ * the SPI boot controller registers. the final chip select is an OR gate
+ * between the Designware SPI controller and the SPI boot controller.
+ */
+static void dw_spi_mscc_set_cs(struct spi_device *spi, bool enable)
+{
+	struct dw_spi *dws = spi_master_get_devdata(spi->master);
+	struct dw_spi_mmio *dwsmmio = container_of(dws, struct dw_spi_mmio, dws);
+	struct dw_spi_mscc *dwsmscc = dwsmmio->priv;
+	u32 cs = spi->chip_select;
+
+	if (cs < 4) {
+		u32 sw_mode = MSCC_SPI_MST_SW_MODE_SW_PIN_CTRL_MODE;
+
+		if (!enable)
+			sw_mode |= MSCC_SPI_MST_SW_MODE_SW_SPI_CS(BIT(cs));
+
+		writel(sw_mode, dwsmscc->spi_mst + MSCC_SPI_MST_SW_MODE);
+	}
+
+	dw_spi_set_cs(spi, enable);
+}
+
+static int dw_spi_mscc_init(struct platform_device *pdev,
+			    struct dw_spi_mmio *dwsmmio)
+{
+	struct dw_spi_mscc *dwsmscc;
+	struct resource *res;
+
+	dwsmscc = devm_kzalloc(&pdev->dev, sizeof(*dwsmscc), GFP_KERNEL);
+	if (!dwsmscc)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	dwsmscc->spi_mst = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(dwsmscc->spi_mst)) {
+		dev_err(&pdev->dev, "SPI_MST region map failed\n");
+		return PTR_ERR(dwsmscc->spi_mst);
+	}
+
+	dwsmscc->syscon = syscon_regmap_lookup_by_compatible("mscc,ocelot-cpu-syscon");
+	if (IS_ERR(dwsmscc->syscon))
+		return PTR_ERR(dwsmscc->syscon);
+
+	/* Deassert all CS */
+	writel(0, dwsmscc->spi_mst + MSCC_SPI_MST_SW_MODE);
+
+	/* Select the owner of the SI interface */
+	regmap_update_bits(dwsmscc->syscon, MSCC_CPU_SYSTEM_CTRL_GENERAL_CTRL,
+			   OCELOT_IF_SI_OWNER_MASK,
+			   MSCC_IF_SI_OWNER_SIMC << OCELOT_IF_SI_OWNER_OFFSET);
+
+	dwsmmio->dws.set_cs = dw_spi_mscc_set_cs;
+	dwsmmio->priv = dwsmscc;
+
+	return 0;
+}
+
 static int dw_spi_mmio_probe(struct platform_device *pdev)
 {
+	int (*init_func)(struct platform_device *pdev,
+			 struct dw_spi_mmio *dwsmmio);
 	struct dw_spi_mmio *dwsmmio;
 	struct dw_spi *dws;
 	struct resource *mem;
@@ -99,6 +181,13 @@ static int dw_spi_mmio_probe(struct platform_device *pdev)
 		}
 	}
 
+	init_func = device_get_match_data(&pdev->dev);
+	if (init_func) {
+		ret = init_func(pdev, dwsmmio);
+		if (ret)
+			goto out;
+	}
+
 	ret = dw_spi_add_host(&pdev->dev, dws);
 	if (ret)
 		goto out;
@@ -123,6 +212,7 @@ static int dw_spi_mmio_remove(struct platform_device *pdev)
 
 static const struct of_device_id dw_spi_mmio_of_match[] = {
 	{ .compatible = "snps,dw-apb-ssi", },
+	{ .compatible = "mscc,ocelot-spi", .data = dw_spi_mscc_init},
 	{ /* end of table */}
 };
 MODULE_DEVICE_TABLE(of, dw_spi_mmio_of_match);
diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c
index f693bfe95ab9..ac2eb89ef7a5 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw.c
@@ -133,7 +133,7 @@ static inline void dw_spi_debugfs_remove(struct dw_spi *dws)
 }
 #endif /* CONFIG_DEBUG_FS */
 
-static void dw_spi_set_cs(struct spi_device *spi, bool enable)
+void dw_spi_set_cs(struct spi_device *spi, bool enable)
 {
 	struct dw_spi *dws = spi_controller_get_devdata(spi->controller);
 	struct chip_data *chip = spi_get_ctldata(spi);
@@ -145,6 +145,7 @@ static void dw_spi_set_cs(struct spi_device *spi, bool enable)
 	if (!enable)
 		dw_writel(dws, DW_SPI_SER, BIT(spi->chip_select));
 }
+EXPORT_SYMBOL_GPL(dw_spi_set_cs);
 
 /* Return the max entries we can fill into tx fifo */
 static inline u32 tx_max(struct dw_spi *dws)
@@ -485,6 +486,8 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
 	dws->dma_inited = 0;
 	dws->dma_addr = (dma_addr_t)(dws->paddr + DW_SPI_DR);
 
+	spi_controller_set_devdata(master, dws);
+
 	ret = request_irq(dws->irq, dw_spi_irq, IRQF_SHARED, dev_name(dev),
 			  master);
 	if (ret < 0) {
@@ -505,6 +508,9 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
 	master->dev.of_node = dev->of_node;
 	master->flags = SPI_MASTER_GPIO_SS;
 
+	if (dws->set_cs)
+		master->set_cs = dws->set_cs;
+
 	/* Basic HW init */
 	spi_hw_init(dev, dws);
 
@@ -518,7 +524,6 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
 		}
 	}
 
-	spi_controller_set_devdata(master, dws);
 	ret = devm_spi_register_controller(dev, master);
 	if (ret) {
 		dev_err(&master->dev, "problem registering spi master\n");
diff --git a/drivers/spi/spi-dw.h b/drivers/spi/spi-dw.h
index 2cde2473b3e9..0168b08364d5 100644
--- a/drivers/spi/spi-dw.h
+++ b/drivers/spi/spi-dw.h
@@ -112,6 +112,7 @@ struct dw_spi {
 	u32			reg_io_width;	/* DR I/O width in bytes */
 	u16			bus_num;
 	u16			num_cs;		/* supported slave numbers */
+	void (*set_cs)(struct spi_device *spi, bool enable);
 
 	/* Current message transfer state info */
 	size_t			len;
@@ -244,6 +245,7 @@ struct dw_spi_chip {
 	void (*cs_control)(u32 command);
 };
 
+extern void dw_spi_set_cs(struct spi_device *spi, bool enable);
 extern int dw_spi_add_host(struct device *dev, struct dw_spi *dws);
 extern void dw_spi_remove_host(struct dw_spi *dws);
 extern int dw_spi_suspend_host(struct dw_spi *dws);
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 0630962ce442..7cb3ab0a35a0 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -1,17 +1,9 @@
-/*
- * drivers/spi/spi-fsl-dspi.c
- *
- * Copyright 2013 Freescale Semiconductor, Inc.
- *
- * Freescale DSPI driver
- * This file contains a driver for the Freescale DSPI
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright 2013 Freescale Semiconductor, Inc.
+//
+// Freescale DSPI driver
+// This file contains a driver for the Freescale DSPI
 
 #include <linux/clk.h>
 #include <linux/delay.h>
@@ -38,10 +30,6 @@
 
 #define DRIVER_NAME "fsl-dspi"
 
-#define TRAN_STATE_RX_VOID		0x01
-#define TRAN_STATE_TX_VOID		0x02
-#define TRAN_STATE_WORD_ODD_NUM	0x04
-
 #define DSPI_FIFO_SIZE			4
 #define DSPI_DMA_BUFSIZE		(DSPI_FIFO_SIZE * 1024)
 
@@ -50,6 +38,7 @@
 #define SPI_MCR_PCSIS		(0x3F << 16)
 #define SPI_MCR_CLR_TXF	(1 << 11)
 #define SPI_MCR_CLR_RXF	(1 << 10)
+#define SPI_MCR_XSPI		(1 << 3)
 
 #define SPI_TCR			0x08
 #define SPI_TCR_GET_TCNT(x)	(((x) & 0xffff0000) >> 16)
@@ -86,11 +75,16 @@
 #define SPI_RSER_TCFQE		0x80000000
 
 #define SPI_PUSHR		0x34
-#define SPI_PUSHR_CONT		(1 << 31)
-#define SPI_PUSHR_CTAS(x)	(((x) & 0x00000003) << 28)
-#define SPI_PUSHR_EOQ		(1 << 27)
-#define SPI_PUSHR_CTCNT	(1 << 26)
-#define SPI_PUSHR_PCS(x)	(((1 << x) & 0x0000003f) << 16)
+#define SPI_PUSHR_CMD_CONT	(1 << 15)
+#define SPI_PUSHR_CONT		(SPI_PUSHR_CMD_CONT << 16)
+#define SPI_PUSHR_CMD_CTAS(x)	(((x) & 0x0003) << 12)
+#define SPI_PUSHR_CTAS(x)	(SPI_PUSHR_CMD_CTAS(x) << 16)
+#define SPI_PUSHR_CMD_EOQ	(1 << 11)
+#define SPI_PUSHR_EOQ		(SPI_PUSHR_CMD_EOQ << 16)
+#define SPI_PUSHR_CMD_CTCNT	(1 << 10)
+#define SPI_PUSHR_CTCNT		(SPI_PUSHR_CMD_CTCNT << 16)
+#define SPI_PUSHR_CMD_PCS(x)	((1 << x) & 0x003f)
+#define SPI_PUSHR_PCS(x)	(SPI_PUSHR_CMD_PCS(x) << 16)
 #define SPI_PUSHR_TXDATA(x)	((x) & 0x0000ffff)
 
 #define SPI_PUSHR_SLAVE	0x34
@@ -107,21 +101,31 @@
 #define SPI_RXFR2		0x84
 #define SPI_RXFR3		0x88
 
+#define SPI_CTARE(x)		(0x11c + (((x) & 0x3) * 4))
+#define SPI_CTARE_FMSZE(x)	(((x) & 0x1) << 16)
+#define SPI_CTARE_DTCP(x)	((x) & 0x7ff)
+
+#define SPI_SREX		0x13c
+
 #define SPI_FRAME_BITS(bits)	SPI_CTAR_FMSZ((bits) - 1)
 #define SPI_FRAME_BITS_MASK	SPI_CTAR_FMSZ(0xf)
 #define SPI_FRAME_BITS_16	SPI_CTAR_FMSZ(0xf)
 #define SPI_FRAME_BITS_8	SPI_CTAR_FMSZ(0x7)
 
+#define SPI_FRAME_EBITS(bits)	SPI_CTARE_FMSZE(((bits) - 1) >> 4)
+#define SPI_FRAME_EBITS_MASK	SPI_CTARE_FMSZE(1)
+
+/* Register offsets for regmap_pushr */
+#define PUSHR_CMD		0x0
+#define PUSHR_TX		0x2
+
 #define SPI_CS_INIT		0x01
 #define SPI_CS_ASSERT		0x02
 #define SPI_CS_DROP		0x04
 
-#define SPI_TCR_TCNT_MAX	0x10000
-
 #define DMA_COMPLETION_TIMEOUT	msecs_to_jiffies(3000)
 
 struct chip_data {
-	u32 mcr_val;
 	u32 ctar_val;
 	u16 void_write_data;
 };
@@ -135,6 +139,7 @@ enum dspi_trans_mode {
 struct fsl_dspi_devtype_data {
 	enum dspi_trans_mode trans_mode;
 	u8 max_clock_factor;
+	bool xspi_mode;
 };
 
 static const struct fsl_dspi_devtype_data vf610_data = {
@@ -145,6 +150,7 @@ static const struct fsl_dspi_devtype_data vf610_data = {
 static const struct fsl_dspi_devtype_data ls1021a_v1_data = {
 	.trans_mode = DSPI_TCFQ_MODE,
 	.max_clock_factor = 8,
+	.xspi_mode = true,
 };
 
 static const struct fsl_dspi_devtype_data ls2085a_data = {
@@ -179,6 +185,7 @@ struct fsl_dspi {
 	struct platform_device	*pdev;
 
 	struct regmap		*regmap;
+	struct regmap		*regmap_pushr;
 	int			irq;
 	struct clk		*clk;
 
@@ -186,32 +193,62 @@ struct fsl_dspi {
 	struct spi_message	*cur_msg;
 	struct chip_data	*cur_chip;
 	size_t			len;
-	void			*tx;
-	void			*tx_end;
+	const void		*tx;
 	void			*rx;
 	void			*rx_end;
-	char			dataflags;
-	u8			cs;
 	u16			void_write_data;
-	u32			cs_change;
+	u16			tx_cmd;
+	u8			bits_per_word;
+	u8			bytes_per_word;
 	const struct fsl_dspi_devtype_data *devtype_data;
 
 	wait_queue_head_t	waitq;
 	u32			waitflags;
 
-	u32			spi_tcnt;
 	struct fsl_dspi_dma	*dma;
 };
 
-static u32 dspi_data_to_pushr(struct fsl_dspi *dspi, int tx_word);
+static u32 dspi_pop_tx(struct fsl_dspi *dspi)
+{
+	u32 txdata = 0;
+
+	if (dspi->tx) {
+		if (dspi->bytes_per_word == 1)
+			txdata = *(u8 *)dspi->tx;
+		else if (dspi->bytes_per_word == 2)
+			txdata = *(u16 *)dspi->tx;
+		else  /* dspi->bytes_per_word == 4 */
+			txdata = *(u32 *)dspi->tx;
+		dspi->tx += dspi->bytes_per_word;
+	}
+	dspi->len -= dspi->bytes_per_word;
+	return txdata;
+}
 
-static inline int is_double_byte_mode(struct fsl_dspi *dspi)
+static u32 dspi_pop_tx_pushr(struct fsl_dspi *dspi)
 {
-	unsigned int val;
+	u16 cmd = dspi->tx_cmd, data = dspi_pop_tx(dspi);
 
-	regmap_read(dspi->regmap, SPI_CTAR(0), &val);
+	if (dspi->len > 0)
+		cmd |= SPI_PUSHR_CMD_CONT;
+	return cmd << 16 | data;
+}
 
-	return ((val & SPI_FRAME_BITS_MASK) == SPI_FRAME_BITS(8)) ? 0 : 1;
+static void dspi_push_rx(struct fsl_dspi *dspi, u32 rxdata)
+{
+	if (!dspi->rx)
+		return;
+
+	/* Mask of undefined bits */
+	rxdata &= (1 << dspi->bits_per_word) - 1;
+
+	if (dspi->bytes_per_word == 1)
+		*(u8 *)dspi->rx = rxdata;
+	else if (dspi->bytes_per_word == 2)
+		*(u16 *)dspi->rx = rxdata;
+	else /* dspi->bytes_per_word == 4 */
+		*(u32 *)dspi->rx = rxdata;
+	dspi->rx += dspi->bytes_per_word;
 }
 
 static void dspi_tx_dma_callback(void *arg)
@@ -226,19 +263,11 @@ static void dspi_rx_dma_callback(void *arg)
 {
 	struct fsl_dspi *dspi = arg;
 	struct fsl_dspi_dma *dma = dspi->dma;
-	int rx_word;
 	int i;
-	u16 d;
-
-	rx_word = is_double_byte_mode(dspi);
 
-	if (!(dspi->dataflags & TRAN_STATE_RX_VOID)) {
-		for (i = 0; i < dma->curr_xfer_len; i++) {
-			d = dspi->dma->rx_dma_buf[i];
-			rx_word ? (*(u16 *)dspi->rx = d) :
-						(*(u8 *)dspi->rx = d);
-			dspi->rx += rx_word + 1;
-		}
+	if (dspi->rx) {
+		for (i = 0; i < dma->curr_xfer_len; i++)
+			dspi_push_rx(dspi, dspi->dma->rx_dma_buf[i]);
 	}
 
 	complete(&dma->cmd_rx_complete);
@@ -249,16 +278,10 @@ static int dspi_next_xfer_dma_submit(struct fsl_dspi *dspi)
 	struct fsl_dspi_dma *dma = dspi->dma;
 	struct device *dev = &dspi->pdev->dev;
 	int time_left;
-	int tx_word;
 	int i;
 
-	tx_word = is_double_byte_mode(dspi);
-
-	for (i = 0; i < dma->curr_xfer_len; i++) {
-		dspi->dma->tx_dma_buf[i] = dspi_data_to_pushr(dspi, tx_word);
-		if ((dspi->cs_change) && (!dspi->len))
-			dspi->dma->tx_dma_buf[i] &= ~SPI_PUSHR_CONT;
-	}
+	for (i = 0; i < dma->curr_xfer_len; i++)
+		dspi->dma->tx_dma_buf[i] = dspi_pop_tx_pushr(dspi);
 
 	dma->tx_desc = dmaengine_prep_slave_single(dma->chan_tx,
 					dma->tx_dma_phys,
@@ -327,18 +350,17 @@ static int dspi_dma_xfer(struct fsl_dspi *dspi)
 {
 	struct fsl_dspi_dma *dma = dspi->dma;
 	struct device *dev = &dspi->pdev->dev;
+	struct spi_message *message = dspi->cur_msg;
 	int curr_remaining_bytes;
 	int bytes_per_buffer;
-	int word = 1;
 	int ret = 0;
 
-	if (is_double_byte_mode(dspi))
-		word = 2;
 	curr_remaining_bytes = dspi->len;
 	bytes_per_buffer = DSPI_DMA_BUFSIZE / DSPI_FIFO_SIZE;
 	while (curr_remaining_bytes) {
 		/* Check if current transfer fits the DMA buffer */
-		dma->curr_xfer_len = curr_remaining_bytes / word;
+		dma->curr_xfer_len = curr_remaining_bytes
+			/ dspi->bytes_per_word;
 		if (dma->curr_xfer_len > bytes_per_buffer)
 			dma->curr_xfer_len = bytes_per_buffer;
 
@@ -348,7 +370,10 @@ static int dspi_dma_xfer(struct fsl_dspi *dspi)
 			goto exit;
 
 		} else {
-			curr_remaining_bytes -= dma->curr_xfer_len * word;
+			const int len =
+				dma->curr_xfer_len * dspi->bytes_per_word;
+			curr_remaining_bytes -= len;
+			message->actual_length += len;
 			if (curr_remaining_bytes < 0)
 				curr_remaining_bytes = 0;
 		}
@@ -534,125 +559,91 @@ static void ns_delay_scale(char *psc, char *sc, int delay_ns,
 	}
 }
 
-static u32 dspi_data_to_pushr(struct fsl_dspi *dspi, int tx_word)
+static void fifo_write(struct fsl_dspi *dspi)
 {
-	u16 d16;
-
-	if (!(dspi->dataflags & TRAN_STATE_TX_VOID))
-		d16 = tx_word ? *(u16 *)dspi->tx : *(u8 *)dspi->tx;
-	else
-		d16 = dspi->void_write_data;
-
-	dspi->tx += tx_word + 1;
-	dspi->len -= tx_word + 1;
-
-	return	SPI_PUSHR_TXDATA(d16) |
-		SPI_PUSHR_PCS(dspi->cs) |
-		SPI_PUSHR_CTAS(0) |
-		SPI_PUSHR_CONT;
+	regmap_write(dspi->regmap, SPI_PUSHR, dspi_pop_tx_pushr(dspi));
 }
 
-static void dspi_data_from_popr(struct fsl_dspi *dspi, int rx_word)
+static void cmd_fifo_write(struct fsl_dspi *dspi)
 {
-	u16 d;
-	unsigned int val;
-
-	regmap_read(dspi->regmap, SPI_POPR, &val);
-	d = SPI_POPR_RXDATA(val);
+	u16 cmd = dspi->tx_cmd;
 
-	if (!(dspi->dataflags & TRAN_STATE_RX_VOID))
-		rx_word ? (*(u16 *)dspi->rx = d) : (*(u8 *)dspi->rx = d);
-
-	dspi->rx += rx_word + 1;
+	if (dspi->len > 0)
+		cmd |= SPI_PUSHR_CMD_CONT;
+	regmap_write(dspi->regmap_pushr, PUSHR_CMD, cmd);
 }
 
-static int dspi_eoq_write(struct fsl_dspi *dspi)
+static void tx_fifo_write(struct fsl_dspi *dspi, u16 txdata)
 {
-	int tx_count = 0;
-	int tx_word;
-	u32 dspi_pushr = 0;
+	regmap_write(dspi->regmap_pushr, PUSHR_TX, txdata);
+}
 
-	tx_word = is_double_byte_mode(dspi);
+static void dspi_tcfq_write(struct fsl_dspi *dspi)
+{
+	/* Clear transfer count */
+	dspi->tx_cmd |= SPI_PUSHR_CMD_CTCNT;
 
-	while (dspi->len && (tx_count < DSPI_FIFO_SIZE)) {
-		/* If we are in word mode, only have a single byte to transfer
-		 * switch to byte mode temporarily.  Will switch back at the
-		 * end of the transfer.
+	if (dspi->devtype_data->xspi_mode && dspi->bits_per_word > 16) {
+		/* Write two TX FIFO entries first, and then the corresponding
+		 * CMD FIFO entry.
 		 */
-		if (tx_word && (dspi->len == 1)) {
-			dspi->dataflags |= TRAN_STATE_WORD_ODD_NUM;
-			regmap_update_bits(dspi->regmap, SPI_CTAR(0),
-					SPI_FRAME_BITS_MASK, SPI_FRAME_BITS(8));
-			tx_word = 0;
-		}
-
-		dspi_pushr = dspi_data_to_pushr(dspi, tx_word);
-
-		if (dspi->len == 0 || tx_count == DSPI_FIFO_SIZE - 1) {
-			/* last transfer in the transfer */
-			dspi_pushr |= SPI_PUSHR_EOQ;
-			if ((dspi->cs_change) && (!dspi->len))
-				dspi_pushr &= ~SPI_PUSHR_CONT;
-		} else if (tx_word && (dspi->len == 1))
-			dspi_pushr |= SPI_PUSHR_EOQ;
+		u32 data = dspi_pop_tx(dspi);
 
-		regmap_write(dspi->regmap, SPI_PUSHR, dspi_pushr);
-
-		tx_count++;
+		if (dspi->cur_chip->ctar_val & SPI_CTAR_LSBFE(1)) {
+			/* LSB */
+			tx_fifo_write(dspi, data & 0xFFFF);
+			tx_fifo_write(dspi, data >> 16);
+		} else {
+			/* MSB */
+			tx_fifo_write(dspi, data >> 16);
+			tx_fifo_write(dspi, data & 0xFFFF);
+		}
+		cmd_fifo_write(dspi);
+	} else {
+		/* Write one entry to both TX FIFO and CMD FIFO
+		 * simultaneously.
+		 */
+		fifo_write(dspi);
 	}
-
-	return tx_count * (tx_word + 1);
 }
 
-static int dspi_eoq_read(struct fsl_dspi *dspi)
+static u32 fifo_read(struct fsl_dspi *dspi)
 {
-	int rx_count = 0;
-	int rx_word = is_double_byte_mode(dspi);
-
-	while ((dspi->rx < dspi->rx_end)
-			&& (rx_count < DSPI_FIFO_SIZE)) {
-		if (rx_word && (dspi->rx_end - dspi->rx) == 1)
-			rx_word = 0;
+	u32 rxdata = 0;
 
-		dspi_data_from_popr(dspi, rx_word);
-		rx_count++;
-	}
-
-	return rx_count;
+	regmap_read(dspi->regmap, SPI_POPR, &rxdata);
+	return rxdata;
 }
 
-static int dspi_tcfq_write(struct fsl_dspi *dspi)
+static void dspi_tcfq_read(struct fsl_dspi *dspi)
 {
-	int tx_word;
-	u32 dspi_pushr = 0;
-
-	tx_word = is_double_byte_mode(dspi);
+	dspi_push_rx(dspi, fifo_read(dspi));
+}
 
-	if (tx_word && (dspi->len == 1)) {
-		dspi->dataflags |= TRAN_STATE_WORD_ODD_NUM;
-		regmap_update_bits(dspi->regmap, SPI_CTAR(0),
-				SPI_FRAME_BITS_MASK, SPI_FRAME_BITS(8));
-		tx_word = 0;
+static void dspi_eoq_write(struct fsl_dspi *dspi)
+{
+	int fifo_size = DSPI_FIFO_SIZE;
+
+	/* Fill TX FIFO with as many transfers as possible */
+	while (dspi->len && fifo_size--) {
+		/* Request EOQF for last transfer in FIFO */
+		if (dspi->len == dspi->bytes_per_word || fifo_size == 0)
+			dspi->tx_cmd |= SPI_PUSHR_CMD_EOQ;
+		/* Clear transfer count for first transfer in FIFO */
+		if (fifo_size == (DSPI_FIFO_SIZE - 1))
+			dspi->tx_cmd |= SPI_PUSHR_CMD_CTCNT;
+		/* Write combined TX FIFO and CMD FIFO entry */
+		fifo_write(dspi);
 	}
-
-	dspi_pushr = dspi_data_to_pushr(dspi, tx_word);
-
-	if ((dspi->cs_change) && (!dspi->len))
-		dspi_pushr &= ~SPI_PUSHR_CONT;
-
-	regmap_write(dspi->regmap, SPI_PUSHR, dspi_pushr);
-
-	return tx_word + 1;
 }
 
-static void dspi_tcfq_read(struct fsl_dspi *dspi)
+static void dspi_eoq_read(struct fsl_dspi *dspi)
 {
-	int rx_word = is_double_byte_mode(dspi);
-
-	if (rx_word && (dspi->rx_end - dspi->rx) == 1)
-		rx_word = 0;
+	int fifo_size = DSPI_FIFO_SIZE;
 
-	dspi_data_from_popr(dspi, rx_word);
+	/* Read one FIFO entry at and push to rx buffer */
+	while ((dspi->rx < dspi->rx_end) && fifo_size--)
+		dspi_push_rx(dspi, fifo_read(dspi));
 }
 
 static int dspi_transfer_one_message(struct spi_master *master,
@@ -663,10 +654,6 @@ static int dspi_transfer_one_message(struct spi_master *master,
 	struct spi_transfer *transfer;
 	int status = 0;
 	enum dspi_trans_mode trans_mode;
-	u32 spi_tcr;
-
-	regmap_read(dspi->regmap, SPI_TCR, &spi_tcr);
-	dspi->spi_tcnt = SPI_TCR_GET_TCNT(spi_tcr);
 
 	message->actual_length = 0;
 
@@ -674,32 +661,51 @@ static int dspi_transfer_one_message(struct spi_master *master,
 		dspi->cur_transfer = transfer;
 		dspi->cur_msg = message;
 		dspi->cur_chip = spi_get_ctldata(spi);
-		dspi->cs = spi->chip_select;
-		dspi->cs_change = 0;
+		/* Prepare command word for CMD FIFO */
+		dspi->tx_cmd = SPI_PUSHR_CMD_CTAS(0) |
+			SPI_PUSHR_CMD_PCS(spi->chip_select);
 		if (list_is_last(&dspi->cur_transfer->transfer_list,
-				 &dspi->cur_msg->transfers) || transfer->cs_change)
-			dspi->cs_change = 1;
+				 &dspi->cur_msg->transfers)) {
+			/* Leave PCS activated after last transfer when
+			 * cs_change is set.
+			 */
+			if (transfer->cs_change)
+				dspi->tx_cmd |= SPI_PUSHR_CMD_CONT;
+		} else {
+			/* Keep PCS active between transfers in same message
+			 * when cs_change is not set, and de-activate PCS
+			 * between transfers in the same message when
+			 * cs_change is set.
+			 */
+			if (!transfer->cs_change)
+				dspi->tx_cmd |= SPI_PUSHR_CMD_CONT;
+		}
+
 		dspi->void_write_data = dspi->cur_chip->void_write_data;
 
-		dspi->dataflags = 0;
-		dspi->tx = (void *)transfer->tx_buf;
-		dspi->tx_end = dspi->tx + transfer->len;
+		dspi->tx = transfer->tx_buf;
 		dspi->rx = transfer->rx_buf;
 		dspi->rx_end = dspi->rx + transfer->len;
 		dspi->len = transfer->len;
+		/* Validated transfer specific frame size (defaults applied) */
+		dspi->bits_per_word = transfer->bits_per_word;
+		if (transfer->bits_per_word <= 8)
+			dspi->bytes_per_word = 1;
+		else if (transfer->bits_per_word <= 16)
+			dspi->bytes_per_word = 2;
+		else
+			dspi->bytes_per_word = 4;
 
-		if (!dspi->rx)
-			dspi->dataflags |= TRAN_STATE_RX_VOID;
-
-		if (!dspi->tx)
-			dspi->dataflags |= TRAN_STATE_TX_VOID;
-
-		regmap_write(dspi->regmap, SPI_MCR, dspi->cur_chip->mcr_val);
 		regmap_update_bits(dspi->regmap, SPI_MCR,
-				SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF,
-				SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF);
+				   SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF,
+				   SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF);
 		regmap_write(dspi->regmap, SPI_CTAR(0),
-				dspi->cur_chip->ctar_val);
+			     dspi->cur_chip->ctar_val |
+			     SPI_FRAME_BITS(transfer->bits_per_word));
+		if (dspi->devtype_data->xspi_mode)
+			regmap_write(dspi->regmap, SPI_CTARE(0),
+				     SPI_FRAME_EBITS(transfer->bits_per_word)
+				     | SPI_CTARE_DTCP(1));
 
 		trans_mode = dspi->devtype_data->trans_mode;
 		switch (trans_mode) {
@@ -750,16 +756,9 @@ static int dspi_setup(struct spi_device *spi)
 	struct fsl_dspi_platform_data *pdata;
 	u32 cs_sck_delay = 0, sck_cs_delay = 0;
 	unsigned char br = 0, pbr = 0, pcssck = 0, cssck = 0;
-	unsigned char pasc = 0, asc = 0, fmsz = 0;
+	unsigned char pasc = 0, asc = 0;
 	unsigned long clkrate;
 
-	if ((spi->bits_per_word >= 4) && (spi->bits_per_word <= 16)) {
-		fmsz = spi->bits_per_word - 1;
-	} else {
-		pr_err("Invalid wordsize\n");
-		return -ENODEV;
-	}
-
 	/* Only alloc on first setup */
 	chip = spi_get_ctldata(spi);
 	if (chip == NULL) {
@@ -781,9 +780,6 @@ static int dspi_setup(struct spi_device *spi)
 		sck_cs_delay = pdata->sck_cs_delay;
 	}
 
-	chip->mcr_val = SPI_MCR_MASTER | SPI_MCR_PCSIS |
-		SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF;
-
 	chip->void_write_data = 0;
 
 	clkrate = clk_get_rate(dspi->clk);
@@ -795,8 +791,7 @@ static int dspi_setup(struct spi_device *spi)
 	/* Set After SCK delay scale values */
 	ns_delay_scale(&pasc, &asc, sck_cs_delay, clkrate);
 
-	chip->ctar_val =  SPI_CTAR_FMSZ(fmsz)
-		| SPI_CTAR_CPOL(spi->mode & SPI_CPOL ? 1 : 0)
+	chip->ctar_val = SPI_CTAR_CPOL(spi->mode & SPI_CPOL ? 1 : 0)
 		| SPI_CTAR_CPHA(spi->mode & SPI_CPHA ? 1 : 0)
 		| SPI_CTAR_LSBFE(spi->mode & SPI_LSB_FIRST ? 1 : 0)
 		| SPI_CTAR_PCSSCK(pcssck)
@@ -827,36 +822,20 @@ static irqreturn_t dspi_interrupt(int irq, void *dev_id)
 	struct spi_message *msg = dspi->cur_msg;
 	enum dspi_trans_mode trans_mode;
 	u32 spi_sr, spi_tcr;
-	u32 spi_tcnt, tcnt_diff;
-	int tx_word;
+	u16 spi_tcnt;
 
 	regmap_read(dspi->regmap, SPI_SR, &spi_sr);
 	regmap_write(dspi->regmap, SPI_SR, spi_sr);
 
 
 	if (spi_sr & (SPI_SR_EOQF | SPI_SR_TCFQF)) {
-		tx_word = is_double_byte_mode(dspi);
-
+		/* Get transfer counter (in number of SPI transfers). It was
+		 * reset to 0 when transfer(s) were started.
+		 */
 		regmap_read(dspi->regmap, SPI_TCR, &spi_tcr);
 		spi_tcnt = SPI_TCR_GET_TCNT(spi_tcr);
-		/*
-		 * The width of SPI Transfer Counter in SPI_TCR is 16bits,
-		 * so the max couner is 65535. When the counter reach 65535,
-		 * it will wrap around, counter reset to zero.
-		 * spi_tcnt my be less than dspi->spi_tcnt, it means the
-		 * counter already wrapped around.
-		 * SPI Transfer Counter is a counter of transmitted frames.
-		 * The size of frame maybe two bytes.
-		 */
-		tcnt_diff = ((spi_tcnt + SPI_TCR_TCNT_MAX) - dspi->spi_tcnt)
-			% SPI_TCR_TCNT_MAX;
-		tcnt_diff *= (tx_word + 1);
-		if (dspi->dataflags & TRAN_STATE_WORD_ODD_NUM)
-			tcnt_diff--;
-
-		msg->actual_length += tcnt_diff;
-
-		dspi->spi_tcnt = spi_tcnt;
+		/* Update total number of bytes that were transferred */
+		msg->actual_length += spi_tcnt * dspi->bytes_per_word;
 
 		trans_mode = dspi->devtype_data->trans_mode;
 		switch (trans_mode) {
@@ -873,14 +852,6 @@ static irqreturn_t dspi_interrupt(int irq, void *dev_id)
 		}
 
 		if (!dspi->len) {
-			if (dspi->dataflags & TRAN_STATE_WORD_ODD_NUM) {
-				regmap_update_bits(dspi->regmap,
-						   SPI_CTAR(0),
-						   SPI_FRAME_BITS_MASK,
-						   SPI_FRAME_BITS(16));
-				dspi->dataflags &= ~TRAN_STATE_WORD_ODD_NUM;
-			}
-
 			dspi->waitflags = 1;
 			wake_up_interruptible(&dspi->waitq);
 		} else {
@@ -943,16 +914,62 @@ static int dspi_resume(struct device *dev)
 
 static SIMPLE_DEV_PM_OPS(dspi_pm, dspi_suspend, dspi_resume);
 
+static const struct regmap_range dspi_volatile_ranges[] = {
+	regmap_reg_range(SPI_MCR, SPI_TCR),
+	regmap_reg_range(SPI_SR, SPI_SR),
+	regmap_reg_range(SPI_PUSHR, SPI_RXFR3),
+};
+
+static const struct regmap_access_table dspi_volatile_table = {
+	.yes_ranges     = dspi_volatile_ranges,
+	.n_yes_ranges   = ARRAY_SIZE(dspi_volatile_ranges),
+};
+
 static const struct regmap_config dspi_regmap_config = {
 	.reg_bits = 32,
 	.val_bits = 32,
 	.reg_stride = 4,
 	.max_register = 0x88,
+	.volatile_table = &dspi_volatile_table,
+};
+
+static const struct regmap_range dspi_xspi_volatile_ranges[] = {
+	regmap_reg_range(SPI_MCR, SPI_TCR),
+	regmap_reg_range(SPI_SR, SPI_SR),
+	regmap_reg_range(SPI_PUSHR, SPI_RXFR3),
+	regmap_reg_range(SPI_SREX, SPI_SREX),
+};
+
+static const struct regmap_access_table dspi_xspi_volatile_table = {
+	.yes_ranges     = dspi_xspi_volatile_ranges,
+	.n_yes_ranges   = ARRAY_SIZE(dspi_xspi_volatile_ranges),
+};
+
+static const struct regmap_config dspi_xspi_regmap_config[] = {
+	{
+		.reg_bits = 32,
+		.val_bits = 32,
+		.reg_stride = 4,
+		.max_register = 0x13c,
+		.volatile_table = &dspi_xspi_volatile_table,
+	},
+	{
+		.name = "pushr",
+		.reg_bits = 16,
+		.val_bits = 16,
+		.reg_stride = 2,
+		.max_register = 0x2,
+	},
 };
 
 static void dspi_init(struct fsl_dspi *dspi)
 {
+	regmap_write(dspi->regmap, SPI_MCR, SPI_MCR_MASTER | SPI_MCR_PCSIS |
+		     (dspi->devtype_data->xspi_mode ? SPI_MCR_XSPI : 0));
 	regmap_write(dspi->regmap, SPI_SR, SPI_SR_CLEAR);
+	if (dspi->devtype_data->xspi_mode)
+		regmap_write(dspi->regmap, SPI_CTARE(0),
+			     SPI_CTARE_FMSZE(0) | SPI_CTARE_DTCP(1));
 }
 
 static int dspi_probe(struct platform_device *pdev)
@@ -961,6 +978,7 @@ static int dspi_probe(struct platform_device *pdev)
 	struct spi_master *master;
 	struct fsl_dspi *dspi;
 	struct resource *res;
+	const struct regmap_config *regmap_config;
 	void __iomem *base;
 	struct fsl_dspi_platform_data *pdata;
 	int ret = 0, cs_num, bus_num;
@@ -980,8 +998,6 @@ static int dspi_probe(struct platform_device *pdev)
 
 	master->cleanup = dspi_cleanup;
 	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST;
-	master->bits_per_word_mask = SPI_BPW_MASK(4) | SPI_BPW_MASK(8) |
-					SPI_BPW_MASK(16);
 
 	pdata = dev_get_platdata(&pdev->dev);
 	if (pdata) {
@@ -1013,6 +1029,11 @@ static int dspi_probe(struct platform_device *pdev)
 		}
 	}
 
+	if (dspi->devtype_data->xspi_mode)
+		master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
+	else
+		master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16);
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(base)) {
@@ -1020,8 +1041,11 @@ static int dspi_probe(struct platform_device *pdev)
 		goto out_master_put;
 	}
 
-	dspi->regmap = devm_regmap_init_mmio_clk(&pdev->dev, NULL, base,
-						&dspi_regmap_config);
+	if (dspi->devtype_data->xspi_mode)
+		regmap_config = &dspi_xspi_regmap_config[0];
+	else
+		regmap_config = &dspi_regmap_config;
+	dspi->regmap = devm_regmap_init_mmio(&pdev->dev, base, regmap_config);
 	if (IS_ERR(dspi->regmap)) {
 		dev_err(&pdev->dev, "failed to init regmap: %ld\n",
 				PTR_ERR(dspi->regmap));
@@ -1029,30 +1053,43 @@ static int dspi_probe(struct platform_device *pdev)
 		goto out_master_put;
 	}
 
+	if (dspi->devtype_data->xspi_mode) {
+		dspi->regmap_pushr = devm_regmap_init_mmio(
+			&pdev->dev, base + SPI_PUSHR,
+			&dspi_xspi_regmap_config[1]);
+		if (IS_ERR(dspi->regmap_pushr)) {
+			dev_err(&pdev->dev,
+				"failed to init pushr regmap: %ld\n",
+				PTR_ERR(dspi->regmap_pushr));
+			ret = PTR_ERR(dspi->regmap_pushr);
+			goto out_master_put;
+		}
+	}
+
+	dspi->clk = devm_clk_get(&pdev->dev, "dspi");
+	if (IS_ERR(dspi->clk)) {
+		ret = PTR_ERR(dspi->clk);
+		dev_err(&pdev->dev, "unable to get clock\n");
+		goto out_master_put;
+	}
+	ret = clk_prepare_enable(dspi->clk);
+	if (ret)
+		goto out_master_put;
+
 	dspi_init(dspi);
 	dspi->irq = platform_get_irq(pdev, 0);
 	if (dspi->irq < 0) {
 		dev_err(&pdev->dev, "can't get platform irq\n");
 		ret = dspi->irq;
-		goto out_master_put;
+		goto out_clk_put;
 	}
 
 	ret = devm_request_irq(&pdev->dev, dspi->irq, dspi_interrupt, 0,
 			pdev->name, dspi);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Unable to attach DSPI interrupt\n");
-		goto out_master_put;
-	}
-
-	dspi->clk = devm_clk_get(&pdev->dev, "dspi");
-	if (IS_ERR(dspi->clk)) {
-		ret = PTR_ERR(dspi->clk);
-		dev_err(&pdev->dev, "unable to get clock\n");
-		goto out_master_put;
+		goto out_clk_put;
 	}
-	ret = clk_prepare_enable(dspi->clk);
-	if (ret)
-		goto out_master_put;
 
 	if (dspi->devtype_data->trans_mode == DSPI_DMA_MODE) {
 		ret = dspi_request_dma(dspi, res->start);
diff --git a/drivers/spi/spi-fsl-espi.c b/drivers/spi/spi-fsl-espi.c
index 1d332e23f6ed..1e8ff6256079 100644
--- a/drivers/spi/spi-fsl-espi.c
+++ b/drivers/spi/spi-fsl-espi.c
@@ -547,8 +547,11 @@ static void fsl_espi_cpu_irq(struct fsl_espi *espi, u32 events)
 		dev_err(espi->dev,
 			"Transfer done but SPIE_DON isn't set!\n");
 
-	if (SPIE_RXCNT(events) || SPIE_TXCNT(events) != FSL_ESPI_FIFO_SIZE)
+	if (SPIE_RXCNT(events) || SPIE_TXCNT(events) != FSL_ESPI_FIFO_SIZE) {
 		dev_err(espi->dev, "Transfer done but rx/tx fifo's aren't empty!\n");
+		dev_err(espi->dev, "SPIE_RXCNT = %d, SPIE_TXCNT = %d\n",
+			SPIE_RXCNT(events), SPIE_TXCNT(events));
+	}
 
 	complete(&espi->done);
 }
diff --git a/drivers/spi/spi-gpio.c b/drivers/spi/spi-gpio.c
index 6ae92d4dca19..0626e6e3ea0c 100644
--- a/drivers/spi/spi-gpio.c
+++ b/drivers/spi/spi-gpio.c
@@ -121,7 +121,10 @@ static inline int getmiso(const struct spi_device *spi)
 {
 	struct spi_gpio *spi_gpio = spi_to_spi_gpio(spi);
 
-	return !!gpiod_get_value_cansleep(spi_gpio->miso);
+	if (spi->mode & SPI_3WIRE)
+		return !!gpiod_get_value_cansleep(spi_gpio->mosi);
+	else
+		return !!gpiod_get_value_cansleep(spi_gpio->miso);
 }
 
 /*
@@ -149,27 +152,27 @@ static inline int getmiso(const struct spi_device *spi)
  */
 
 static u32 spi_gpio_txrx_word_mode0(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	return bitbang_txrx_be_cpha0(spi, nsecs, 0, 0, word, bits);
+	return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits);
 }
 
 static u32 spi_gpio_txrx_word_mode1(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	return bitbang_txrx_be_cpha1(spi, nsecs, 0, 0, word, bits);
+	return bitbang_txrx_be_cpha1(spi, nsecs, 0, flags, word, bits);
 }
 
 static u32 spi_gpio_txrx_word_mode2(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	return bitbang_txrx_be_cpha0(spi, nsecs, 1, 0, word, bits);
+	return bitbang_txrx_be_cpha0(spi, nsecs, 1, flags, word, bits);
 }
 
 static u32 spi_gpio_txrx_word_mode3(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	return bitbang_txrx_be_cpha1(spi, nsecs, 1, 0, word, bits);
+	return bitbang_txrx_be_cpha1(spi, nsecs, 1, flags, word, bits);
 }
 
 /*
@@ -183,30 +186,30 @@ static u32 spi_gpio_txrx_word_mode3(struct spi_device *spi,
  */
 
 static u32 spi_gpio_spec_txrx_word_mode0(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	unsigned flags = spi->master->flags;
+	flags = spi->master->flags;
 	return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits);
 }
 
 static u32 spi_gpio_spec_txrx_word_mode1(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	unsigned flags = spi->master->flags;
+	flags = spi->master->flags;
 	return bitbang_txrx_be_cpha1(spi, nsecs, 0, flags, word, bits);
 }
 
 static u32 spi_gpio_spec_txrx_word_mode2(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	unsigned flags = spi->master->flags;
+	flags = spi->master->flags;
 	return bitbang_txrx_be_cpha0(spi, nsecs, 1, flags, word, bits);
 }
 
 static u32 spi_gpio_spec_txrx_word_mode3(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	unsigned flags = spi->master->flags;
+	flags = spi->master->flags;
 	return bitbang_txrx_be_cpha1(spi, nsecs, 1, flags, word, bits);
 }
 
@@ -250,6 +253,16 @@ static int spi_gpio_setup(struct spi_device *spi)
 	return status;
 }
 
+static int spi_gpio_set_direction(struct spi_device *spi, bool output)
+{
+	struct spi_gpio *spi_gpio = spi_to_spi_gpio(spi);
+
+	if (output)
+		return gpiod_direction_output(spi_gpio->mosi, 1);
+	else
+		return gpiod_direction_input(spi_gpio->mosi);
+}
+
 static void spi_gpio_cleanup(struct spi_device *spi)
 {
 	spi_bitbang_cleanup(spi);
@@ -395,6 +408,7 @@ static int spi_gpio_probe(struct platform_device *pdev)
 		return status;
 
 	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 32);
+	master->mode_bits = SPI_3WIRE | SPI_CPHA | SPI_CPOL;
 	master->flags = master_flags;
 	master->bus_num = pdev->id;
 	/* The master needs to think there is a chipselect even if not connected */
@@ -407,6 +421,7 @@ static int spi_gpio_probe(struct platform_device *pdev)
 
 	spi_gpio->bitbang.master = master;
 	spi_gpio->bitbang.chipselect = spi_gpio_chipselect;
+	spi_gpio->bitbang.set_line_direction = spi_gpio_set_direction;
 
 	if ((master_flags & (SPI_MASTER_NO_TX | SPI_MASTER_NO_RX)) == 0) {
 		spi_gpio->bitbang.txrx_word[SPI_MODE_0] = spi_gpio_txrx_word_mode0;
diff --git a/drivers/spi/spi-img-spfi.c b/drivers/spi/spi-img-spfi.c
index 7a37090dabbe..e6eb979f1b8a 100644
--- a/drivers/spi/spi-img-spfi.c
+++ b/drivers/spi/spi-img-spfi.c
@@ -419,6 +419,9 @@ static int img_spfi_prepare(struct spi_master *master, struct spi_message *msg)
 	u32 val;
 
 	val = spfi_readl(spfi, SPFI_PORT_STATE);
+	val &= ~(SPFI_PORT_STATE_DEV_SEL_MASK <<
+		 SPFI_PORT_STATE_DEV_SEL_SHIFT);
+	val |= msg->spi->chip_select << SPFI_PORT_STATE_DEV_SEL_SHIFT;
 	if (msg->spi->mode & SPI_CPHA)
 		val |= SPFI_PORT_STATE_CK_PHASE(msg->spi->chip_select);
 	else
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index d3b21faf6b1f..08dd3a31a3e5 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -94,8 +94,7 @@ struct spi_imx_data {
 	void *rx_buf;
 	const void *tx_buf;
 	unsigned int txfifo; /* number of words pushed in tx FIFO */
-	unsigned int dynamic_burst, read_u32;
-	unsigned int word_mask;
+	unsigned int dynamic_burst;
 
 	/* Slave mode */
 	bool slave_mode;
@@ -140,6 +139,8 @@ static void spi_imx_buf_rx_##type(struct spi_imx_data *spi_imx)		\
 		*(type *)spi_imx->rx_buf = val;				\
 		spi_imx->rx_buf += sizeof(type);			\
 	}								\
+									\
+	spi_imx->remainder -= sizeof(type);				\
 }
 
 #define MXC_SPI_BUF_TX(type)						\
@@ -203,7 +204,12 @@ out:
 
 static int spi_imx_bytes_per_word(const int bits_per_word)
 {
-	return DIV_ROUND_UP(bits_per_word, BITS_PER_BYTE);
+	if (bits_per_word <= 8)
+		return 1;
+	else if (bits_per_word <= 16)
+		return 2;
+	else
+		return 4;
 }
 
 static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi,
@@ -220,17 +226,11 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi,
 
 	bytes_per_word = spi_imx_bytes_per_word(transfer->bits_per_word);
 
-	if (bytes_per_word != 1 && bytes_per_word != 2 && bytes_per_word != 4)
-		return false;
-
 	for (i = spi_imx->devtype_data->fifo_size / 2; i > 0; i--) {
 		if (!(transfer->len % (i * bytes_per_word)))
 			break;
 	}
 
-	if (i == 0)
-		return false;
-
 	spi_imx->wml = i;
 	spi_imx->dynamic_burst = 0;
 
@@ -291,26 +291,39 @@ static void spi_imx_buf_rx_swap_u32(struct spi_imx_data *spi_imx)
 		else if (bytes_per_word == 2)
 			val = (val << 16) | (val >> 16);
 #endif
-		val &= spi_imx->word_mask;
 		*(u32 *)spi_imx->rx_buf = val;
 		spi_imx->rx_buf += sizeof(u32);
 	}
+
+	spi_imx->remainder -= sizeof(u32);
 }
 
 static void spi_imx_buf_rx_swap(struct spi_imx_data *spi_imx)
 {
-	unsigned int bytes_per_word;
+	int unaligned;
+	u32 val;
 
-	bytes_per_word = spi_imx_bytes_per_word(spi_imx->bits_per_word);
-	if (spi_imx->read_u32) {
+	unaligned = spi_imx->remainder % 4;
+
+	if (!unaligned) {
 		spi_imx_buf_rx_swap_u32(spi_imx);
 		return;
 	}
 
-	if (bytes_per_word == 1)
-		spi_imx_buf_rx_u8(spi_imx);
-	else if (bytes_per_word == 2)
+	if (spi_imx_bytes_per_word(spi_imx->bits_per_word) == 2) {
 		spi_imx_buf_rx_u16(spi_imx);
+		return;
+	}
+
+	val = readl(spi_imx->base + MXC_CSPIRXDATA);
+
+	while (unaligned--) {
+		if (spi_imx->rx_buf) {
+			*(u8 *)spi_imx->rx_buf = (val >> (8 * unaligned)) & 0xff;
+			spi_imx->rx_buf++;
+		}
+		spi_imx->remainder--;
+	}
 }
 
 static void spi_imx_buf_tx_swap_u32(struct spi_imx_data *spi_imx)
@@ -322,7 +335,6 @@ static void spi_imx_buf_tx_swap_u32(struct spi_imx_data *spi_imx)
 
 	if (spi_imx->tx_buf) {
 		val = *(u32 *)spi_imx->tx_buf;
-		val &= spi_imx->word_mask;
 		spi_imx->tx_buf += sizeof(u32);
 	}
 
@@ -340,40 +352,30 @@ static void spi_imx_buf_tx_swap_u32(struct spi_imx_data *spi_imx)
 
 static void spi_imx_buf_tx_swap(struct spi_imx_data *spi_imx)
 {
-	u32 ctrl, val;
-	unsigned int bytes_per_word;
+	int unaligned;
+	u32 val = 0;
 
-	if (spi_imx->count == spi_imx->remainder) {
-		ctrl = readl(spi_imx->base + MX51_ECSPI_CTRL);
-		ctrl &= ~MX51_ECSPI_CTRL_BL_MASK;
-		if (spi_imx->count > MX51_ECSPI_CTRL_MAX_BURST) {
-			spi_imx->remainder = spi_imx->count %
-					     MX51_ECSPI_CTRL_MAX_BURST;
-			val = MX51_ECSPI_CTRL_MAX_BURST * 8 - 1;
-		} else if (spi_imx->count >= sizeof(u32)) {
-			spi_imx->remainder = spi_imx->count % sizeof(u32);
-			val = (spi_imx->count - spi_imx->remainder) * 8 - 1;
-		} else {
-			spi_imx->remainder = 0;
-			val = spi_imx->bits_per_word - 1;
-			spi_imx->read_u32 = 0;
-		}
+	unaligned = spi_imx->count % 4;
 
-		ctrl |= (val << MX51_ECSPI_CTRL_BL_OFFSET);
-		writel(ctrl, spi_imx->base + MX51_ECSPI_CTRL);
+	if (!unaligned) {
+		spi_imx_buf_tx_swap_u32(spi_imx);
+		return;
 	}
 
-	if (spi_imx->count >= sizeof(u32)) {
-		spi_imx_buf_tx_swap_u32(spi_imx);
+	if (spi_imx_bytes_per_word(spi_imx->bits_per_word) == 2) {
+		spi_imx_buf_tx_u16(spi_imx);
 		return;
 	}
 
-	bytes_per_word = spi_imx_bytes_per_word(spi_imx->bits_per_word);
+	while (unaligned--) {
+		if (spi_imx->tx_buf) {
+			val |= *(u8 *)spi_imx->tx_buf << (8 * unaligned);
+			spi_imx->tx_buf++;
+		}
+		spi_imx->count--;
+	}
 
-	if (bytes_per_word == 1)
-		spi_imx_buf_tx_u8(spi_imx);
-	else if (bytes_per_word == 2)
-		spi_imx_buf_tx_u16(spi_imx);
+	writel(val, spi_imx->base + MXC_CSPITXDATA);
 }
 
 static void mx53_ecspi_rx_slave(struct spi_imx_data *spi_imx)
@@ -392,6 +394,8 @@ static void mx53_ecspi_rx_slave(struct spi_imx_data *spi_imx)
 		spi_imx->rx_buf += n_bytes;
 		spi_imx->slave_burst -= n_bytes;
 	}
+
+	spi_imx->remainder -= sizeof(u32);
 }
 
 static void mx53_ecspi_tx_slave(struct spi_imx_data *spi_imx)
@@ -1001,12 +1005,52 @@ static void spi_imx_chipselect(struct spi_device *spi, int is_active)
 	gpio_set_value(spi->cs_gpio, dev_is_lowactive ^ active);
 }
 
+static void spi_imx_set_burst_len(struct spi_imx_data *spi_imx, int n_bits)
+{
+	u32 ctrl;
+
+	ctrl = readl(spi_imx->base + MX51_ECSPI_CTRL);
+	ctrl &= ~MX51_ECSPI_CTRL_BL_MASK;
+	ctrl |= ((n_bits - 1) << MX51_ECSPI_CTRL_BL_OFFSET);
+	writel(ctrl, spi_imx->base + MX51_ECSPI_CTRL);
+}
+
 static void spi_imx_push(struct spi_imx_data *spi_imx)
 {
+	unsigned int burst_len, fifo_words;
+
+	if (spi_imx->dynamic_burst)
+		fifo_words = 4;
+	else
+		fifo_words = spi_imx_bytes_per_word(spi_imx->bits_per_word);
+	/*
+	 * Reload the FIFO when the remaining bytes to be transferred in the
+	 * current burst is 0. This only applies when bits_per_word is a
+	 * multiple of 8.
+	 */
+	if (!spi_imx->remainder) {
+		if (spi_imx->dynamic_burst) {
+
+			/* We need to deal unaligned data first */
+			burst_len = spi_imx->count % MX51_ECSPI_CTRL_MAX_BURST;
+
+			if (!burst_len)
+				burst_len = MX51_ECSPI_CTRL_MAX_BURST;
+
+			spi_imx_set_burst_len(spi_imx, burst_len * 8);
+
+			spi_imx->remainder = burst_len;
+		} else {
+			spi_imx->remainder = fifo_words;
+		}
+	}
+
 	while (spi_imx->txfifo < spi_imx->devtype_data->fifo_size) {
 		if (!spi_imx->count)
 			break;
-		if (spi_imx->txfifo && (spi_imx->count == spi_imx->remainder))
+		if (spi_imx->dynamic_burst &&
+		    spi_imx->txfifo >=  DIV_ROUND_UP(spi_imx->remainder,
+						     fifo_words))
 			break;
 		spi_imx->tx(spi_imx);
 		spi_imx->txfifo++;
@@ -1102,27 +1146,20 @@ static int spi_imx_setupxfer(struct spi_device *spi,
 	spi_imx->bits_per_word = t->bits_per_word;
 	spi_imx->speed_hz  = t->speed_hz;
 
-	/* Initialize the functions for transfer */
-	if (spi_imx->devtype_data->dynamic_burst && !spi_imx->slave_mode) {
-		u32 mask;
-
-		spi_imx->dynamic_burst = 0;
-		spi_imx->remainder = 0;
-		spi_imx->read_u32  = 1;
+	/*
+	 * Initialize the functions for transfer. To transfer non byte-aligned
+	 * words, we have to use multiple word-size bursts, we can't use
+	 * dynamic_burst in that case.
+	 */
+	if (spi_imx->devtype_data->dynamic_burst && !spi_imx->slave_mode &&
+	    (spi_imx->bits_per_word == 8 ||
+	    spi_imx->bits_per_word == 16 ||
+	    spi_imx->bits_per_word == 32)) {
 
-		mask = (1 << spi_imx->bits_per_word) - 1;
 		spi_imx->rx = spi_imx_buf_rx_swap;
 		spi_imx->tx = spi_imx_buf_tx_swap;
 		spi_imx->dynamic_burst = 1;
-		spi_imx->remainder = t->len;
-
-		if (spi_imx->bits_per_word <= 8)
-			spi_imx->word_mask = mask << 24 | mask << 16
-					     | mask << 8 | mask;
-		else if (spi_imx->bits_per_word <= 16)
-			spi_imx->word_mask = mask << 16 | mask;
-		else
-			spi_imx->word_mask = mask;
+
 	} else {
 		if (spi_imx->bits_per_word <= 8) {
 			spi_imx->rx = spi_imx_buf_rx_u8;
@@ -1134,6 +1171,7 @@ static int spi_imx_setupxfer(struct spi_device *spi,
 			spi_imx->rx = spi_imx_buf_rx_u32;
 			spi_imx->tx = spi_imx_buf_tx_u32;
 		}
+		spi_imx->dynamic_burst = 0;
 	}
 
 	if (spi_imx_can_dma(spi_imx->bitbang.master, spi, t))
@@ -1317,6 +1355,7 @@ static int spi_imx_pio_transfer(struct spi_device *spi,
 	spi_imx->rx_buf = transfer->rx_buf;
 	spi_imx->count = transfer->len;
 	spi_imx->txfifo = 0;
+	spi_imx->remainder = 0;
 
 	reinit_completion(&spi_imx->xfer_done);
 
@@ -1354,6 +1393,7 @@ static int spi_imx_pio_transfer_slave(struct spi_device *spi,
 	spi_imx->rx_buf = transfer->rx_buf;
 	spi_imx->count = transfer->len;
 	spi_imx->txfifo = 0;
+	spi_imx->remainder = 0;
 
 	reinit_completion(&spi_imx->xfer_done);
 	spi_imx->slave_aborted = false;
diff --git a/drivers/spi/spi-lm70llp.c b/drivers/spi/spi-lm70llp.c
index 61ee0f4269ae..4549efd792da 100644
--- a/drivers/spi/spi-lm70llp.c
+++ b/drivers/spi/spi-lm70llp.c
@@ -188,9 +188,10 @@ static void lm70_chipselect(struct spi_device *spi, int value)
 /*
  * Our actual bitbanger routine.
  */
-static u32 lm70_txrx(struct spi_device *spi, unsigned nsecs, u32 word, u8 bits)
+static u32 lm70_txrx(struct spi_device *spi, unsigned nsecs, u32 word, u8 bits,
+		     unsigned flags)
 {
-	return bitbang_txrx_be_cpha0(spi, nsecs, 0, 0, word, bits);
+	return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits);
 }
 
 static void spi_lm70llp_attach(struct parport *p)
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index 990770dfa5cf..e43842c7a31a 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -311,6 +311,24 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 EXPORT_SYMBOL_GPL(spi_mem_exec_op);
 
 /**
+ * spi_mem_get_name() - Return the SPI mem device name to be used by the
+ *			upper layer if necessary
+ * @mem: the SPI memory
+ *
+ * This function allows SPI mem users to retrieve the SPI mem device name.
+ * It is useful if the upper layer needs to expose a custom name for
+ * compatibility reasons.
+ *
+ * Return: a string containing the name of the memory device to be used
+ *	   by the SPI mem user
+ */
+const char *spi_mem_get_name(struct spi_mem *mem)
+{
+	return mem->name;
+}
+EXPORT_SYMBOL_GPL(spi_mem_get_name);
+
+/**
  * spi_mem_adjust_op_size() - Adjust the data size of a SPI mem operation to
  *			      match controller limitations
  * @mem: the SPI memory
@@ -344,6 +362,7 @@ static inline struct spi_mem_driver *to_spi_mem_drv(struct device_driver *drv)
 static int spi_mem_probe(struct spi_device *spi)
 {
 	struct spi_mem_driver *memdrv = to_spi_mem_drv(spi->dev.driver);
+	struct spi_controller *ctlr = spi->controller;
 	struct spi_mem *mem;
 
 	mem = devm_kzalloc(&spi->dev, sizeof(*mem), GFP_KERNEL);
@@ -351,6 +370,15 @@ static int spi_mem_probe(struct spi_device *spi)
 		return -ENOMEM;
 
 	mem->spi = spi;
+
+	if (ctlr->mem_ops && ctlr->mem_ops->get_name)
+		mem->name = ctlr->mem_ops->get_name(mem);
+	else
+		mem->name = dev_name(&spi->dev);
+
+	if (IS_ERR_OR_NULL(mem->name))
+		return PTR_ERR(mem->name);
+
 	spi_set_drvdata(spi, mem);
 
 	return memdrv->probe(mem);
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 6c628a54e946..508c61c669e7 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -398,11 +398,9 @@ static void omap2_mcspi_tx_dma(struct spi_device *spi,
 {
 	struct omap2_mcspi	*mcspi;
 	struct omap2_mcspi_dma  *mcspi_dma;
-	unsigned int		count;
 
 	mcspi = spi_master_get_devdata(spi->master);
 	mcspi_dma = &mcspi->dma_channels[spi->chip_select];
-	count = xfer->len;
 
 	if (mcspi_dma->dma_tx) {
 		struct dma_async_tx_descriptor *tx;
@@ -582,7 +580,6 @@ omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer)
 	struct omap2_mcspi_cs	*cs = spi->controller_state;
 	struct omap2_mcspi_dma  *mcspi_dma;
 	unsigned int		count;
-	u32			l;
 	u8			*rx;
 	const u8		*tx;
 	struct dma_slave_config	cfg;
@@ -595,8 +592,6 @@ omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer)
 
 	mcspi = spi_master_get_devdata(spi->master);
 	mcspi_dma = &mcspi->dma_channels[spi->chip_select];
-	l = mcspi_cached_chconf0(spi);
-
 
 	if (cs->word_len <= 8) {
 		width = DMA_SLAVE_BUSWIDTH_1_BYTE;
@@ -676,7 +671,6 @@ omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer)
 static unsigned
 omap2_mcspi_txrx_pio(struct spi_device *spi, struct spi_transfer *xfer)
 {
-	struct omap2_mcspi	*mcspi;
 	struct omap2_mcspi_cs	*cs = spi->controller_state;
 	unsigned int		count, c;
 	u32			l;
@@ -686,7 +680,6 @@ omap2_mcspi_txrx_pio(struct spi_device *spi, struct spi_transfer *xfer)
 	void __iomem		*chstat_reg;
 	int			word_len;
 
-	mcspi = spi_master_get_devdata(spi->master);
 	count = xfer->len;
 	c = count;
 	word_len = cs->word_len;
@@ -883,13 +876,11 @@ static int omap2_mcspi_setup_transfer(struct spi_device *spi,
 {
 	struct omap2_mcspi_cs *cs = spi->controller_state;
 	struct omap2_mcspi *mcspi;
-	struct spi_master *spi_cntrl;
 	u32 l = 0, clkd = 0, div, extclk = 0, clkg = 0;
 	u8 word_len = spi->bits_per_word;
 	u32 speed_hz = spi->max_speed_hz;
 
 	mcspi = spi_master_get_devdata(spi->master);
-	spi_cntrl = mcspi->master;
 
 	if (t != NULL && t->bits_per_word)
 		word_len = t->bits_per_word;
diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c
index d01a6adc726e..47ef6b1a2e76 100644
--- a/drivers/spi/spi-orion.c
+++ b/drivers/spi/spi-orion.c
@@ -20,6 +20,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
+#include <linux/of_gpio.h>
 #include <linux/clk.h>
 #include <linux/sizes.h>
 #include <linux/gpio.h>
@@ -681,9 +682,9 @@ static int orion_spi_probe(struct platform_device *pdev)
 		goto out_rel_axi_clk;
 	}
 
-	/* Scan all SPI devices of this controller for direct mapped devices */
 	for_each_available_child_of_node(pdev->dev.of_node, np) {
 		u32 cs;
+		int cs_gpio;
 
 		/* Get chip-select number from the "reg" property */
 		status = of_property_read_u32(np, "reg", &cs);
@@ -695,6 +696,44 @@ static int orion_spi_probe(struct platform_device *pdev)
 		}
 
 		/*
+		 * Initialize the CS GPIO:
+		 * - properly request the actual GPIO signal
+		 * - de-assert the logical signal so that all GPIO CS lines
+		 *   are inactive when probing for slaves
+		 * - find an unused physical CS which will be driven for any
+		 *   slave which uses a CS GPIO
+		 */
+		cs_gpio = of_get_named_gpio(pdev->dev.of_node, "cs-gpios", cs);
+		if (cs_gpio > 0) {
+			char *gpio_name;
+			int cs_flags;
+
+			if (spi->unused_hw_gpio == -1) {
+				dev_info(&pdev->dev,
+					"Selected unused HW CS#%d for any GPIO CSes\n",
+					cs);
+				spi->unused_hw_gpio = cs;
+			}
+
+			gpio_name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+					"%s-CS%d", dev_name(&pdev->dev), cs);
+			if (!gpio_name) {
+				status = -ENOMEM;
+				goto out_rel_axi_clk;
+			}
+
+			cs_flags = of_property_read_bool(np, "spi-cs-high") ?
+				GPIOF_OUT_INIT_LOW : GPIOF_OUT_INIT_HIGH;
+			status = devm_gpio_request_one(&pdev->dev, cs_gpio,
+					cs_flags, gpio_name);
+			if (status) {
+				dev_err(&pdev->dev,
+					"Can't request GPIO for CS %d\n", cs);
+				goto out_rel_axi_clk;
+			}
+		}
+
+		/*
 		 * Check if an address is configured for this SPI device. If
 		 * not, the MBus mapping via the 'ranges' property in the 'soc'
 		 * node is not configured and this device should not use the
@@ -740,44 +779,8 @@ static int orion_spi_probe(struct platform_device *pdev)
 	if (status < 0)
 		goto out_rel_pm;
 
-	if (master->cs_gpios) {
-		int i;
-		for (i = 0; i < master->num_chipselect; ++i) {
-			char *gpio_name;
-
-			if (!gpio_is_valid(master->cs_gpios[i])) {
-				continue;
-			}
-
-			gpio_name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
-					"%s-CS%d", dev_name(&pdev->dev), i);
-			if (!gpio_name) {
-				status = -ENOMEM;
-				goto out_rel_master;
-			}
-
-			status = devm_gpio_request(&pdev->dev,
-					master->cs_gpios[i], gpio_name);
-			if (status) {
-				dev_err(&pdev->dev,
-					"Can't request GPIO for CS %d\n",
-					master->cs_gpios[i]);
-				goto out_rel_master;
-			}
-			if (spi->unused_hw_gpio == -1) {
-				dev_info(&pdev->dev,
-					"Selected unused HW CS#%d for any GPIO CSes\n",
-					i);
-				spi->unused_hw_gpio = i;
-			}
-		}
-	}
-
-
 	return status;
 
-out_rel_master:
-	spi_unregister_master(master);
 out_rel_pm:
 	pm_runtime_disable(&pdev->dev);
 out_rel_axi_clk:
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 0b2d60d30f69..14f4ea59caff 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -1391,6 +1391,10 @@ static const struct pci_device_id pxa2xx_spi_pci_compound_match[] = {
 	{ PCI_VDEVICE(INTEL, 0x31c2), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x31c4), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x31c6), LPSS_BXT_SSP },
+	/* ICL-LP */
+	{ PCI_VDEVICE(INTEL, 0x34aa), LPSS_CNL_SSP },
+	{ PCI_VDEVICE(INTEL, 0x34ab), LPSS_CNL_SSP },
+	{ PCI_VDEVICE(INTEL, 0x34fb), LPSS_CNL_SSP },
 	/* APL */
 	{ PCI_VDEVICE(INTEL, 0x5ac2), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x5ac4), LPSS_BXT_SSP },
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index 0e74cbf9929d..539d6d1a277a 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -49,6 +49,7 @@ struct sh_msiof_spi_priv {
 	struct platform_device *pdev;
 	struct sh_msiof_spi_info *info;
 	struct completion done;
+	struct completion done_txdma;
 	unsigned int tx_fifo_size;
 	unsigned int rx_fifo_size;
 	unsigned int min_div_pow;
@@ -649,19 +650,21 @@ static int sh_msiof_slave_abort(struct spi_master *master)
 
 	p->slave_aborted = true;
 	complete(&p->done);
+	complete(&p->done_txdma);
 	return 0;
 }
 
-static int sh_msiof_wait_for_completion(struct sh_msiof_spi_priv *p)
+static int sh_msiof_wait_for_completion(struct sh_msiof_spi_priv *p,
+					struct completion *x)
 {
 	if (spi_controller_is_slave(p->master)) {
-		if (wait_for_completion_interruptible(&p->done) ||
+		if (wait_for_completion_interruptible(x) ||
 		    p->slave_aborted) {
 			dev_dbg(&p->pdev->dev, "interrupted\n");
 			return -EINTR;
 		}
 	} else {
-		if (!wait_for_completion_timeout(&p->done, HZ)) {
+		if (!wait_for_completion_timeout(x, HZ)) {
 			dev_err(&p->pdev->dev, "timeout\n");
 			return -ETIMEDOUT;
 		}
@@ -711,7 +714,7 @@ static int sh_msiof_spi_txrx_once(struct sh_msiof_spi_priv *p,
 	}
 
 	/* wait for tx fifo to be emptied / rx fifo to be filled */
-	ret = sh_msiof_wait_for_completion(p);
+	ret = sh_msiof_wait_for_completion(p, &p->done);
 	if (ret)
 		goto stop_reset;
 
@@ -740,10 +743,7 @@ stop_ier:
 
 static void sh_msiof_dma_complete(void *arg)
 {
-	struct sh_msiof_spi_priv *p = arg;
-
-	sh_msiof_write(p, IER, 0);
-	complete(&p->done);
+	complete(arg);
 }
 
 static int sh_msiof_dma_once(struct sh_msiof_spi_priv *p, const void *tx,
@@ -764,7 +764,7 @@ static int sh_msiof_dma_once(struct sh_msiof_spi_priv *p, const void *tx,
 			return -EAGAIN;
 
 		desc_rx->callback = sh_msiof_dma_complete;
-		desc_rx->callback_param = p;
+		desc_rx->callback_param = &p->done;
 		cookie = dmaengine_submit(desc_rx);
 		if (dma_submit_error(cookie))
 			return cookie;
@@ -782,13 +782,8 @@ static int sh_msiof_dma_once(struct sh_msiof_spi_priv *p, const void *tx,
 			goto no_dma_tx;
 		}
 
-		if (rx) {
-			/* No callback */
-			desc_tx->callback = NULL;
-		} else {
-			desc_tx->callback = sh_msiof_dma_complete;
-			desc_tx->callback_param = p;
-		}
+		desc_tx->callback = sh_msiof_dma_complete;
+		desc_tx->callback_param = &p->done_txdma;
 		cookie = dmaengine_submit(desc_tx);
 		if (dma_submit_error(cookie)) {
 			ret = cookie;
@@ -805,6 +800,8 @@ static int sh_msiof_dma_once(struct sh_msiof_spi_priv *p, const void *tx,
 	sh_msiof_write(p, IER, ier_bits);
 
 	reinit_completion(&p->done);
+	if (tx)
+		reinit_completion(&p->done_txdma);
 	p->slave_aborted = false;
 
 	/* Now start DMA */
@@ -819,17 +816,24 @@ static int sh_msiof_dma_once(struct sh_msiof_spi_priv *p, const void *tx,
 		goto stop_dma;
 	}
 
-	/* wait for tx/rx DMA completion */
-	ret = sh_msiof_wait_for_completion(p);
-	if (ret)
-		goto stop_reset;
+	if (tx) {
+		/* wait for tx DMA completion */
+		ret = sh_msiof_wait_for_completion(p, &p->done_txdma);
+		if (ret)
+			goto stop_reset;
+	}
 
-	if (!rx) {
-		reinit_completion(&p->done);
-		sh_msiof_write(p, IER, IER_TEOFE);
+	if (rx) {
+		/* wait for rx DMA completion */
+		ret = sh_msiof_wait_for_completion(p, &p->done);
+		if (ret)
+			goto stop_reset;
 
+		sh_msiof_write(p, IER, 0);
+	} else {
 		/* wait for tx fifo to be emptied */
-		ret = sh_msiof_wait_for_completion(p);
+		sh_msiof_write(p, IER, IER_TEOFE);
+		ret = sh_msiof_wait_for_completion(p, &p->done);
 		if (ret)
 			goto stop_reset;
 	}
@@ -1327,6 +1331,7 @@ static int sh_msiof_spi_probe(struct platform_device *pdev)
 	p->min_div_pow = chipdata->min_div_pow;
 
 	init_completion(&p->done);
+	init_completion(&p->done_txdma);
 
 	p->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(p->clk)) {
diff --git a/drivers/spi/spi-sh-sci.c b/drivers/spi/spi-sh-sci.c
index a9beeeed812c..393701cfca3c 100644
--- a/drivers/spi/spi-sh-sci.c
+++ b/drivers/spi/spi-sh-sci.c
@@ -80,27 +80,31 @@ static inline u32 getmiso(struct spi_device *dev)
 #include "spi-bitbang-txrx.h"
 
 static u32 sh_sci_spi_txrx_mode0(struct spi_device *spi,
-				      unsigned nsecs, u32 word, u8 bits)
+				 unsigned nsecs, u32 word, u8 bits,
+				 unsigned flags)
 {
-	return bitbang_txrx_be_cpha0(spi, nsecs, 0, 0, word, bits);
+	return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits);
 }
 
 static u32 sh_sci_spi_txrx_mode1(struct spi_device *spi,
-				      unsigned nsecs, u32 word, u8 bits)
+				 unsigned nsecs, u32 word, u8 bits,
+				 unsigned flags)
 {
-	return bitbang_txrx_be_cpha1(spi, nsecs, 0, 0, word, bits);
+	return bitbang_txrx_be_cpha1(spi, nsecs, 0, flags, word, bits);
 }
 
 static u32 sh_sci_spi_txrx_mode2(struct spi_device *spi,
-				      unsigned nsecs, u32 word, u8 bits)
+				 unsigned nsecs, u32 word, u8 bits,
+				 unsigned flags)
 {
-	return bitbang_txrx_be_cpha0(spi, nsecs, 1, 0, word, bits);
+	return bitbang_txrx_be_cpha0(spi, nsecs, 1, flags, word, bits);
 }
 
 static u32 sh_sci_spi_txrx_mode3(struct spi_device *spi,
-				      unsigned nsecs, u32 word, u8 bits)
+				 unsigned nsecs, u32 word, u8 bits,
+				 unsigned flags)
 {
-	return bitbang_txrx_be_cpha1(spi, nsecs, 1, 0, word, bits);
+	return bitbang_txrx_be_cpha1(spi, nsecs, 1, flags, word, bits);
 }
 
 static void sh_sci_spi_chipselect(struct spi_device *dev, int value)
diff --git a/drivers/spi/spi-uniphier.c b/drivers/spi/spi-uniphier.c
new file mode 100644
index 000000000000..5a6137fe172d
--- /dev/null
+++ b/drivers/spi/spi-uniphier.c
@@ -0,0 +1,523 @@
+// SPDX-License-Identifier: GPL-2.0
+// spi-uniphier.c - Socionext UniPhier SPI controller driver
+// Copyright 2012      Panasonic Corporation
+// Copyright 2016-2018 Socionext Inc.
+
+#include <linux/kernel.h>
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+
+#include <asm/unaligned.h>
+
+#define SSI_TIMEOUT_MS		2000
+#define SSI_MAX_CLK_DIVIDER	254
+#define SSI_MIN_CLK_DIVIDER	4
+
+struct uniphier_spi_priv {
+	void __iomem *base;
+	struct clk *clk;
+	struct spi_master *master;
+	struct completion xfer_done;
+
+	int error;
+	unsigned int tx_bytes;
+	unsigned int rx_bytes;
+	const u8 *tx_buf;
+	u8 *rx_buf;
+
+	bool is_save_param;
+	u8 bits_per_word;
+	u16 mode;
+	u32 speed_hz;
+};
+
+#define SSI_CTL			0x00
+#define   SSI_CTL_EN		BIT(0)
+
+#define SSI_CKS			0x04
+#define   SSI_CKS_CKRAT_MASK	GENMASK(7, 0)
+#define   SSI_CKS_CKPHS		BIT(14)
+#define   SSI_CKS_CKINIT	BIT(13)
+#define   SSI_CKS_CKDLY		BIT(12)
+
+#define SSI_TXWDS		0x08
+#define   SSI_TXWDS_WDLEN_MASK	GENMASK(13, 8)
+#define   SSI_TXWDS_TDTF_MASK	GENMASK(7, 6)
+#define   SSI_TXWDS_DTLEN_MASK	GENMASK(5, 0)
+
+#define SSI_RXWDS		0x0c
+#define   SSI_RXWDS_DTLEN_MASK	GENMASK(5, 0)
+
+#define SSI_FPS			0x10
+#define   SSI_FPS_FSPOL		BIT(15)
+#define   SSI_FPS_FSTRT		BIT(14)
+
+#define SSI_SR			0x14
+#define   SSI_SR_RNE		BIT(0)
+
+#define SSI_IE			0x18
+#define   SSI_IE_RCIE		BIT(3)
+#define   SSI_IE_RORIE		BIT(0)
+
+#define SSI_IS			0x1c
+#define   SSI_IS_RXRS		BIT(9)
+#define   SSI_IS_RCID		BIT(3)
+#define   SSI_IS_RORID		BIT(0)
+
+#define SSI_IC			0x1c
+#define   SSI_IC_TCIC		BIT(4)
+#define   SSI_IC_RCIC		BIT(3)
+#define   SSI_IC_RORIC		BIT(0)
+
+#define SSI_FC			0x20
+#define   SSI_FC_TXFFL		BIT(12)
+#define   SSI_FC_TXFTH_MASK	GENMASK(11, 8)
+#define   SSI_FC_RXFFL		BIT(4)
+#define   SSI_FC_RXFTH_MASK	GENMASK(3, 0)
+
+#define SSI_TXDR		0x24
+#define SSI_RXDR		0x24
+
+#define SSI_FIFO_DEPTH		8U
+
+static inline unsigned int bytes_per_word(unsigned int bits)
+{
+	return bits <= 8 ? 1 : (bits <= 16 ? 2 : 4);
+}
+
+static inline void uniphier_spi_irq_enable(struct spi_device *spi, u32 mask)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val;
+
+	val = readl(priv->base + SSI_IE);
+	val |= mask;
+	writel(val, priv->base + SSI_IE);
+}
+
+static inline void uniphier_spi_irq_disable(struct spi_device *spi, u32 mask)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val;
+
+	val = readl(priv->base + SSI_IE);
+	val &= ~mask;
+	writel(val, priv->base + SSI_IE);
+}
+
+static void uniphier_spi_set_mode(struct spi_device *spi)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val1, val2;
+
+	/*
+	 * clock setting
+	 * CKPHS    capture timing. 0:rising edge, 1:falling edge
+	 * CKINIT   clock initial level. 0:low, 1:high
+	 * CKDLY    clock delay. 0:no delay, 1:delay depending on FSTRT
+	 *          (FSTRT=0: 1 clock, FSTRT=1: 0.5 clock)
+	 *
+	 * frame setting
+	 * FSPOL    frame signal porarity. 0: low, 1: high
+	 * FSTRT    start frame timing
+	 *          0: rising edge of clock, 1: falling edge of clock
+	 */
+	switch (spi->mode & (SPI_CPOL | SPI_CPHA)) {
+	case SPI_MODE_0:
+		/* CKPHS=1, CKINIT=0, CKDLY=1, FSTRT=0 */
+		val1 = SSI_CKS_CKPHS | SSI_CKS_CKDLY;
+		val2 = 0;
+		break;
+	case SPI_MODE_1:
+		/* CKPHS=0, CKINIT=0, CKDLY=0, FSTRT=1 */
+		val1 = 0;
+		val2 = SSI_FPS_FSTRT;
+		break;
+	case SPI_MODE_2:
+		/* CKPHS=0, CKINIT=1, CKDLY=1, FSTRT=1 */
+		val1 = SSI_CKS_CKINIT | SSI_CKS_CKDLY;
+		val2 = SSI_FPS_FSTRT;
+		break;
+	case SPI_MODE_3:
+		/* CKPHS=1, CKINIT=1, CKDLY=0, FSTRT=0 */
+		val1 = SSI_CKS_CKPHS | SSI_CKS_CKINIT;
+		val2 = 0;
+		break;
+	}
+
+	if (!(spi->mode & SPI_CS_HIGH))
+		val2 |= SSI_FPS_FSPOL;
+
+	writel(val1, priv->base + SSI_CKS);
+	writel(val2, priv->base + SSI_FPS);
+
+	val1 = 0;
+	if (spi->mode & SPI_LSB_FIRST)
+		val1 |= FIELD_PREP(SSI_TXWDS_TDTF_MASK, 1);
+	writel(val1, priv->base + SSI_TXWDS);
+	writel(val1, priv->base + SSI_RXWDS);
+}
+
+static void uniphier_spi_set_transfer_size(struct spi_device *spi, int size)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val;
+
+	val = readl(priv->base + SSI_TXWDS);
+	val &= ~(SSI_TXWDS_WDLEN_MASK | SSI_TXWDS_DTLEN_MASK);
+	val |= FIELD_PREP(SSI_TXWDS_WDLEN_MASK, size);
+	val |= FIELD_PREP(SSI_TXWDS_DTLEN_MASK, size);
+	writel(val, priv->base + SSI_TXWDS);
+
+	val = readl(priv->base + SSI_RXWDS);
+	val &= ~SSI_RXWDS_DTLEN_MASK;
+	val |= FIELD_PREP(SSI_RXWDS_DTLEN_MASK, size);
+	writel(val, priv->base + SSI_RXWDS);
+}
+
+static void uniphier_spi_set_baudrate(struct spi_device *spi,
+				      unsigned int speed)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val, ckdiv;
+
+	/*
+	 * the supported rates are even numbers from 4 to 254. (4,6,8...254)
+	 * round up as we look for equal or less speed
+	 */
+	ckdiv = DIV_ROUND_UP(clk_get_rate(priv->clk), speed);
+	ckdiv = round_up(ckdiv, 2);
+
+	val = readl(priv->base + SSI_CKS);
+	val &= ~SSI_CKS_CKRAT_MASK;
+	val |= ckdiv & SSI_CKS_CKRAT_MASK;
+	writel(val, priv->base + SSI_CKS);
+}
+
+static void uniphier_spi_setup_transfer(struct spi_device *spi,
+				       struct spi_transfer *t)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val;
+
+	priv->error = 0;
+	priv->tx_buf = t->tx_buf;
+	priv->rx_buf = t->rx_buf;
+	priv->tx_bytes = priv->rx_bytes = t->len;
+
+	if (!priv->is_save_param || priv->mode != spi->mode) {
+		uniphier_spi_set_mode(spi);
+		priv->mode = spi->mode;
+	}
+
+	if (!priv->is_save_param || priv->bits_per_word != t->bits_per_word) {
+		uniphier_spi_set_transfer_size(spi, t->bits_per_word);
+		priv->bits_per_word = t->bits_per_word;
+	}
+
+	if (!priv->is_save_param || priv->speed_hz != t->speed_hz) {
+		uniphier_spi_set_baudrate(spi, t->speed_hz);
+		priv->speed_hz = t->speed_hz;
+	}
+
+	if (!priv->is_save_param)
+		priv->is_save_param = true;
+
+	/* reset FIFOs */
+	val = SSI_FC_TXFFL | SSI_FC_RXFFL;
+	writel(val, priv->base + SSI_FC);
+}
+
+static void uniphier_spi_send(struct uniphier_spi_priv *priv)
+{
+	int wsize;
+	u32 val = 0;
+
+	wsize = min(bytes_per_word(priv->bits_per_word), priv->tx_bytes);
+	priv->tx_bytes -= wsize;
+
+	if (priv->tx_buf) {
+		switch (wsize) {
+		case 1:
+			val = *priv->tx_buf;
+			break;
+		case 2:
+			val = get_unaligned_le16(priv->tx_buf);
+			break;
+		case 4:
+			val = get_unaligned_le32(priv->tx_buf);
+			break;
+		}
+
+		priv->tx_buf += wsize;
+	}
+
+	writel(val, priv->base + SSI_TXDR);
+}
+
+static void uniphier_spi_recv(struct uniphier_spi_priv *priv)
+{
+	int rsize;
+	u32 val;
+
+	rsize = min(bytes_per_word(priv->bits_per_word), priv->rx_bytes);
+	priv->rx_bytes -= rsize;
+
+	val = readl(priv->base + SSI_RXDR);
+
+	if (priv->rx_buf) {
+		switch (rsize) {
+		case 1:
+			*priv->rx_buf = val;
+			break;
+		case 2:
+			put_unaligned_le16(val, priv->rx_buf);
+			break;
+		case 4:
+			put_unaligned_le32(val, priv->rx_buf);
+			break;
+		}
+
+		priv->rx_buf += rsize;
+	}
+}
+
+static void uniphier_spi_fill_tx_fifo(struct uniphier_spi_priv *priv)
+{
+	unsigned int tx_count;
+	u32 val;
+
+	tx_count = DIV_ROUND_UP(priv->tx_bytes,
+				bytes_per_word(priv->bits_per_word));
+	tx_count = min(tx_count, SSI_FIFO_DEPTH);
+
+	/* set fifo threshold */
+	val = readl(priv->base + SSI_FC);
+	val &= ~(SSI_FC_TXFTH_MASK | SSI_FC_RXFTH_MASK);
+	val |= FIELD_PREP(SSI_FC_TXFTH_MASK, tx_count);
+	val |= FIELD_PREP(SSI_FC_RXFTH_MASK, tx_count);
+	writel(val, priv->base + SSI_FC);
+
+	while (tx_count--)
+		uniphier_spi_send(priv);
+}
+
+static void uniphier_spi_set_cs(struct spi_device *spi, bool enable)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val;
+
+	val = readl(priv->base + SSI_FPS);
+
+	if (enable)
+		val |= SSI_FPS_FSPOL;
+	else
+		val &= ~SSI_FPS_FSPOL;
+
+	writel(val, priv->base + SSI_FPS);
+}
+
+static int uniphier_spi_transfer_one(struct spi_master *master,
+				     struct spi_device *spi,
+				     struct spi_transfer *t)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
+	int status;
+
+	uniphier_spi_setup_transfer(spi, t);
+
+	reinit_completion(&priv->xfer_done);
+
+	uniphier_spi_fill_tx_fifo(priv);
+
+	uniphier_spi_irq_enable(spi, SSI_IE_RCIE | SSI_IE_RORIE);
+
+	status = wait_for_completion_timeout(&priv->xfer_done,
+					     msecs_to_jiffies(SSI_TIMEOUT_MS));
+
+	uniphier_spi_irq_disable(spi, SSI_IE_RCIE | SSI_IE_RORIE);
+
+	if (status < 0)
+		return status;
+
+	return priv->error;
+}
+
+static int uniphier_spi_prepare_transfer_hardware(struct spi_master *master)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
+
+	writel(SSI_CTL_EN, priv->base + SSI_CTL);
+
+	return 0;
+}
+
+static int uniphier_spi_unprepare_transfer_hardware(struct spi_master *master)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
+
+	writel(0, priv->base + SSI_CTL);
+
+	return 0;
+}
+
+static irqreturn_t uniphier_spi_handler(int irq, void *dev_id)
+{
+	struct uniphier_spi_priv *priv = dev_id;
+	u32 val, stat;
+
+	stat = readl(priv->base + SSI_IS);
+	val = SSI_IC_TCIC | SSI_IC_RCIC | SSI_IC_RORIC;
+	writel(val, priv->base + SSI_IC);
+
+	/* rx fifo overrun */
+	if (stat & SSI_IS_RORID) {
+		priv->error = -EIO;
+		goto done;
+	}
+
+	/* rx complete */
+	if ((stat & SSI_IS_RCID) && (stat & SSI_IS_RXRS)) {
+		while ((readl(priv->base + SSI_SR) & SSI_SR_RNE) &&
+				(priv->rx_bytes - priv->tx_bytes) > 0)
+			uniphier_spi_recv(priv);
+
+		if ((readl(priv->base + SSI_SR) & SSI_SR_RNE) ||
+				(priv->rx_bytes != priv->tx_bytes)) {
+			priv->error = -EIO;
+			goto done;
+		} else if (priv->rx_bytes == 0)
+			goto done;
+
+		/* next tx transfer */
+		uniphier_spi_fill_tx_fifo(priv);
+
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+
+done:
+	complete(&priv->xfer_done);
+	return IRQ_HANDLED;
+}
+
+static int uniphier_spi_probe(struct platform_device *pdev)
+{
+	struct uniphier_spi_priv *priv;
+	struct spi_master *master;
+	struct resource *res;
+	unsigned long clk_rate;
+	int irq;
+	int ret;
+
+	master = spi_alloc_master(&pdev->dev, sizeof(*priv));
+	if (!master)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, master);
+
+	priv = spi_master_get_devdata(master);
+	priv->master = master;
+	priv->is_save_param = false;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	priv->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(priv->base)) {
+		ret = PTR_ERR(priv->base);
+		goto out_master_put;
+	}
+
+	priv->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(priv->clk)) {
+		dev_err(&pdev->dev, "failed to get clock\n");
+		ret = PTR_ERR(priv->clk);
+		goto out_master_put;
+	}
+
+	ret = clk_prepare_enable(priv->clk);
+	if (ret)
+		goto out_master_put;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "failed to get IRQ\n");
+		ret = irq;
+		goto out_disable_clk;
+	}
+
+	ret = devm_request_irq(&pdev->dev, irq, uniphier_spi_handler,
+			       0, "uniphier-spi", priv);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to request IRQ\n");
+		goto out_disable_clk;
+	}
+
+	init_completion(&priv->xfer_done);
+
+	clk_rate = clk_get_rate(priv->clk);
+
+	master->max_speed_hz = DIV_ROUND_UP(clk_rate, SSI_MIN_CLK_DIVIDER);
+	master->min_speed_hz = DIV_ROUND_UP(clk_rate, SSI_MAX_CLK_DIVIDER);
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LSB_FIRST;
+	master->dev.of_node = pdev->dev.of_node;
+	master->bus_num = pdev->id;
+	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 32);
+
+	master->set_cs = uniphier_spi_set_cs;
+	master->transfer_one = uniphier_spi_transfer_one;
+	master->prepare_transfer_hardware
+				= uniphier_spi_prepare_transfer_hardware;
+	master->unprepare_transfer_hardware
+				= uniphier_spi_unprepare_transfer_hardware;
+	master->num_chipselect = 1;
+
+	ret = devm_spi_register_master(&pdev->dev, master);
+	if (ret)
+		goto out_disable_clk;
+
+	return 0;
+
+out_disable_clk:
+	clk_disable_unprepare(priv->clk);
+
+out_master_put:
+	spi_master_put(master);
+	return ret;
+}
+
+static int uniphier_spi_remove(struct platform_device *pdev)
+{
+	struct uniphier_spi_priv *priv = platform_get_drvdata(pdev);
+
+	clk_disable_unprepare(priv->clk);
+
+	return 0;
+}
+
+static const struct of_device_id uniphier_spi_match[] = {
+	{ .compatible = "socionext,uniphier-scssi" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, uniphier_spi_match);
+
+static struct platform_driver uniphier_spi_driver = {
+	.probe = uniphier_spi_probe,
+	.remove = uniphier_spi_remove,
+	.driver = {
+		.name = "uniphier-spi",
+		.of_match_table = uniphier_spi_match,
+	},
+};
+module_platform_driver(uniphier_spi_driver);
+
+MODULE_AUTHOR("Kunihiko Hayashi <hayashi.kunihiko@socionext.com>");
+MODULE_AUTHOR("Keiji Hayashibara <hayashibara.keiji@socionext.com>");
+MODULE_DESCRIPTION("Socionext UniPhier SPI controller driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/spi/spi-xtensa-xtfpga.c b/drivers/spi/spi-xtensa-xtfpga.c
index be6155cba9de..8ce04f829a80 100644
--- a/drivers/spi/spi-xtensa-xtfpga.c
+++ b/drivers/spi/spi-xtensa-xtfpga.c
@@ -54,7 +54,7 @@ static inline void xtfpga_spi_wait_busy(struct xtfpga_spi *xspi)
 }
 
 static u32 xtfpga_spi_txrx_word(struct spi_device *spi, unsigned nsecs,
-				u32 v, u8 bits)
+				u32 v, u8 bits, unsigned flags)
 {
 	struct xtfpga_spi *xspi = spi_master_get_devdata(spi->master);
 
diff --git a/drivers/ssb/Kconfig b/drivers/ssb/Kconfig
index c574dd210500..df30e1323252 100644
--- a/drivers/ssb/Kconfig
+++ b/drivers/ssb/Kconfig
@@ -89,27 +89,6 @@ config SSB_HOST_SOC
 
 	  If unsure, say N
 
-config SSB_SILENT
-	bool "No SSB kernel messages"
-	depends on SSB && EXPERT
-	help
-	  This option turns off all Sonics Silicon Backplane printks.
-	  Note that you won't be able to identify problems, once
-	  messages are turned off.
-	  This might only be desired for production kernels on
-	  embedded devices to reduce the kernel size.
-
-	  Say N
-
-config SSB_DEBUG
-	bool "SSB debugging"
-	depends on SSB && !SSB_SILENT
-	help
-	  This turns on additional runtime checks and debugging
-	  messages. Turn this on for SSB troubleshooting.
-
-	  If unsure, say N
-
 config SSB_SERIAL
 	bool
 	depends on SSB
diff --git a/drivers/ssb/b43_pci_bridge.c b/drivers/ssb/b43_pci_bridge.c
index bed2fedeb057..9c7316b5685f 100644
--- a/drivers/ssb/b43_pci_bridge.c
+++ b/drivers/ssb/b43_pci_bridge.c
@@ -10,12 +10,12 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/pci.h>
 #include <linux/module.h>
 #include <linux/ssb/ssb.h>
 
-#include "ssb_private.h"
-
 
 static const struct pci_device_id b43_pci_bridge_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, 0x4301) },
diff --git a/drivers/ssb/bridge_pcmcia_80211.c b/drivers/ssb/bridge_pcmcia_80211.c
index d70568ea02d5..f51f150307df 100644
--- a/drivers/ssb/bridge_pcmcia_80211.c
+++ b/drivers/ssb/bridge_pcmcia_80211.c
@@ -6,6 +6,8 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/ssb/ssb.h>
 #include <linux/slab.h>
 #include <linux/module.h>
@@ -15,8 +17,6 @@
 #include <pcmcia/ds.h>
 #include <pcmcia/cisreg.h>
 
-#include "ssb_private.h"
-
 static const struct pcmcia_device_id ssb_host_pcmcia_tbl[] = {
 	PCMCIA_DEVICE_MANF_CARD(0x2D0, 0x448),
 	PCMCIA_DEVICE_MANF_CARD(0x2D0, 0x476),
@@ -70,7 +70,7 @@ err_disable:
 err_kfree_ssb:
 	kfree(ssb);
 out_error:
-	ssb_err("Initialization failed (%d, %d)\n", res, err);
+	dev_err(&dev->dev, "Initialization failed (%d, %d)\n", res, err);
 	return err;
 }
 
diff --git a/drivers/ssb/driver_chipcommon.c b/drivers/ssb/driver_chipcommon.c
index 7cb7d2c8fd86..99a4656d113d 100644
--- a/drivers/ssb/driver_chipcommon.c
+++ b/drivers/ssb/driver_chipcommon.c
@@ -9,14 +9,14 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/ssb/ssb.h>
 #include <linux/ssb/ssb_regs.h>
 #include <linux/export.h>
 #include <linux/pci.h>
 #include <linux/bcm47xx_wdt.h>
 
-#include "ssb_private.h"
-
 
 /* Clock sources */
 enum ssb_clksrc {
@@ -56,7 +56,7 @@ void ssb_chipco_set_clockmode(struct ssb_chipcommon *cc,
 
 	if (cc->capabilities & SSB_CHIPCO_CAP_PMU)
 		return; /* PMU controls clockmode, separated function needed */
-	SSB_WARN_ON(ccdev->id.revision >= 20);
+	WARN_ON(ccdev->id.revision >= 20);
 
 	/* chipcommon cores prior to rev6 don't support dynamic clock control */
 	if (ccdev->id.revision < 6)
@@ -111,7 +111,7 @@ void ssb_chipco_set_clockmode(struct ssb_chipcommon *cc,
 		}
 		break;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 }
 
@@ -164,7 +164,7 @@ static int chipco_pctl_clockfreqlimit(struct ssb_chipcommon *cc, int get_max)
 			divisor = 32;
 			break;
 		default:
-			SSB_WARN_ON(1);
+			WARN_ON(1);
 		}
 	} else if (cc->dev->id.revision < 10) {
 		switch (clocksrc) {
@@ -277,7 +277,7 @@ static void calc_fast_powerup_delay(struct ssb_chipcommon *cc)
 	minfreq = chipco_pctl_clockfreqlimit(cc, 0);
 	pll_on_delay = chipco_read32(cc, SSB_CHIPCO_PLLONDELAY);
 	tmp = (((pll_on_delay + 2) * 1000000) + (minfreq - 1)) / minfreq;
-	SSB_WARN_ON(tmp & ~0xFFFF);
+	WARN_ON(tmp & ~0xFFFF);
 
 	cc->fast_pwrup_delay = tmp;
 }
@@ -354,7 +354,7 @@ void ssb_chipcommon_init(struct ssb_chipcommon *cc)
 
 	if (cc->dev->id.revision >= 11)
 		cc->status = chipco_read32(cc, SSB_CHIPCO_CHIPSTAT);
-	ssb_dbg("chipcommon status is 0x%x\n", cc->status);
+	dev_dbg(cc->dev->dev, "chipcommon status is 0x%x\n", cc->status);
 
 	if (cc->dev->id.revision >= 20) {
 		chipco_write32(cc, SSB_CHIPCO_GPIOPULLUP, 0);
diff --git a/drivers/ssb/driver_chipcommon_pmu.c b/drivers/ssb/driver_chipcommon_pmu.c
index c5352ea4821e..0f60e90ded26 100644
--- a/drivers/ssb/driver_chipcommon_pmu.c
+++ b/drivers/ssb/driver_chipcommon_pmu.c
@@ -8,6 +8,8 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/ssb/ssb.h>
 #include <linux/ssb/ssb_regs.h>
 #include <linux/ssb/ssb_driver_chipcommon.h>
@@ -17,8 +19,6 @@
 #include <linux/bcm47xx_nvram.h>
 #endif
 
-#include "ssb_private.h"
-
 static u32 ssb_chipco_pll_read(struct ssb_chipcommon *cc, u32 offset)
 {
 	chipco_write32(cc, SSB_CHIPCO_PLLCTL_ADDR, offset);
@@ -110,7 +110,7 @@ static void ssb_pmu0_pllinit_r0(struct ssb_chipcommon *cc,
 		return;
 	}
 
-	ssb_info("Programming PLL to %u.%03u MHz\n",
+	dev_info(cc->dev->dev, "Programming PLL to %u.%03u MHz\n",
 		 crystalfreq / 1000, crystalfreq % 1000);
 
 	/* First turn the PLL off. */
@@ -128,7 +128,7 @@ static void ssb_pmu0_pllinit_r0(struct ssb_chipcommon *cc,
 			      ~(1 << SSB_PMURES_5354_BB_PLL_PU));
 		break;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 	for (i = 1500; i; i--) {
 		tmp = chipco_read32(cc, SSB_CHIPCO_CLKCTLST);
@@ -138,7 +138,7 @@ static void ssb_pmu0_pllinit_r0(struct ssb_chipcommon *cc,
 	}
 	tmp = chipco_read32(cc, SSB_CHIPCO_CLKCTLST);
 	if (tmp & SSB_CHIPCO_CLKCTLST_HAVEHT)
-		ssb_emerg("Failed to turn the PLL off!\n");
+		dev_emerg(cc->dev->dev, "Failed to turn the PLL off!\n");
 
 	/* Set PDIV in PLL control 0. */
 	pllctl = ssb_chipco_pll_read(cc, SSB_PMU0_PLLCTL0);
@@ -249,7 +249,7 @@ static void ssb_pmu1_pllinit_r0(struct ssb_chipcommon *cc,
 		return;
 	}
 
-	ssb_info("Programming PLL to %u.%03u MHz\n",
+	dev_info(cc->dev->dev, "Programming PLL to %u.%03u MHz\n",
 		 crystalfreq / 1000, crystalfreq % 1000);
 
 	/* First turn the PLL off. */
@@ -265,7 +265,7 @@ static void ssb_pmu1_pllinit_r0(struct ssb_chipcommon *cc,
 		buffer_strength = 0x222222;
 		break;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 	for (i = 1500; i; i--) {
 		tmp = chipco_read32(cc, SSB_CHIPCO_CLKCTLST);
@@ -275,7 +275,7 @@ static void ssb_pmu1_pllinit_r0(struct ssb_chipcommon *cc,
 	}
 	tmp = chipco_read32(cc, SSB_CHIPCO_CLKCTLST);
 	if (tmp & SSB_CHIPCO_CLKCTLST_HAVEHT)
-		ssb_emerg("Failed to turn the PLL off!\n");
+		dev_emerg(cc->dev->dev, "Failed to turn the PLL off!\n");
 
 	/* Set p1div and p2div. */
 	pllctl = ssb_chipco_pll_read(cc, SSB_PMU1_PLLCTL0);
@@ -349,7 +349,7 @@ static void ssb_pmu_pll_init(struct ssb_chipcommon *cc)
 	case 43222:
 		break;
 	default:
-		ssb_err("ERROR: PLL init unknown for device %04X\n",
+		dev_err(cc->dev->dev, "ERROR: PLL init unknown for device %04X\n",
 			bus->chip_id);
 	}
 }
@@ -471,7 +471,7 @@ static void ssb_pmu_resources_init(struct ssb_chipcommon *cc)
 		max_msk = 0xFFFFF;
 		break;
 	default:
-		ssb_err("ERROR: PMU resource config unknown for device %04X\n",
+		dev_err(cc->dev->dev, "ERROR: PMU resource config unknown for device %04X\n",
 			bus->chip_id);
 	}
 
@@ -501,7 +501,7 @@ static void ssb_pmu_resources_init(struct ssb_chipcommon *cc)
 					      ~(depend_tab[i].depend));
 				break;
 			default:
-				SSB_WARN_ON(1);
+				WARN_ON(1);
 			}
 		}
 	}
@@ -524,7 +524,7 @@ void ssb_pmu_init(struct ssb_chipcommon *cc)
 	pmucap = chipco_read32(cc, SSB_CHIPCO_PMU_CAP);
 	cc->pmu.rev = (pmucap & SSB_CHIPCO_PMU_CAP_REVISION);
 
-	ssb_dbg("Found rev %u PMU (capabilities 0x%08X)\n",
+	dev_dbg(cc->dev->dev, "Found rev %u PMU (capabilities 0x%08X)\n",
 		cc->pmu.rev, pmucap);
 
 	if (cc->pmu.rev == 1)
@@ -568,12 +568,12 @@ void ssb_pmu_set_ldo_voltage(struct ssb_chipcommon *cc,
 			mask = 0x3F;
 			break;
 		default:
-			SSB_WARN_ON(1);
+			WARN_ON(1);
 			return;
 		}
 		break;
 	case 0x4312:
-		if (SSB_WARN_ON(id != LDO_PAREF))
+		if (WARN_ON(id != LDO_PAREF))
 			return;
 		addr = 0;
 		shift = 21;
@@ -636,7 +636,7 @@ u32 ssb_pmu_get_alp_clock(struct ssb_chipcommon *cc)
 	case 0x5354:
 		return ssb_pmu_get_alp_clock_clk0(cc);
 	default:
-		ssb_err("ERROR: PMU alp clock unknown for device %04X\n",
+		dev_err(cc->dev->dev, "ERROR: PMU alp clock unknown for device %04X\n",
 			bus->chip_id);
 		return 0;
 	}
@@ -651,7 +651,7 @@ u32 ssb_pmu_get_cpu_clock(struct ssb_chipcommon *cc)
 		/* 5354 chip uses a non programmable PLL of frequency 240MHz */
 		return 240000000;
 	default:
-		ssb_err("ERROR: PMU cpu clock unknown for device %04X\n",
+		dev_err(cc->dev->dev, "ERROR: PMU cpu clock unknown for device %04X\n",
 			bus->chip_id);
 		return 0;
 	}
@@ -665,7 +665,7 @@ u32 ssb_pmu_get_controlclock(struct ssb_chipcommon *cc)
 	case 0x5354:
 		return 120000000;
 	default:
-		ssb_err("ERROR: PMU controlclock unknown for device %04X\n",
+		dev_err(cc->dev->dev, "ERROR: PMU controlclock unknown for device %04X\n",
 			bus->chip_id);
 		return 0;
 	}
@@ -705,9 +705,9 @@ void ssb_pmu_spuravoid_pllupdate(struct ssb_chipcommon *cc, int spuravoid)
 		pmu_ctl = SSB_CHIPCO_PMU_CTL_PLL_UPD;
 		break;
 	default:
-		ssb_printk(KERN_ERR PFX
-			   "Unknown spuravoidance settings for chip 0x%04X, not changing PLL\n",
-			   cc->dev->bus->chip_id);
+		dev_err(cc->dev->dev,
+			"Unknown spuravoidance settings for chip 0x%04X, not changing PLL\n",
+			cc->dev->bus->chip_id);
 		return;
 	}
 
diff --git a/drivers/ssb/driver_chipcommon_sflash.c b/drivers/ssb/driver_chipcommon_sflash.c
index 937fc31971a7..fac0e6828288 100644
--- a/drivers/ssb/driver_chipcommon_sflash.c
+++ b/drivers/ssb/driver_chipcommon_sflash.c
@@ -5,10 +5,10 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
-#include <linux/ssb/ssb.h>
-
 #include "ssb_private.h"
 
+#include <linux/ssb/ssb.h>
+
 static struct resource ssb_sflash_resource = {
 	.name	= "ssb_sflash",
 	.start	= SSB_FLASH2,
@@ -80,7 +80,7 @@ static void ssb_sflash_cmd(struct ssb_chipcommon *cc, u32 opcode)
 			return;
 		cpu_relax();
 	}
-	pr_err("SFLASH control command failed (timeout)!\n");
+	dev_err(cc->dev->dev, "SFLASH control command failed (timeout)!\n");
 }
 
 /* Initialize serial flash access */
diff --git a/drivers/ssb/driver_extif.c b/drivers/ssb/driver_extif.c
index 59385fdab5b0..06b68dd6e022 100644
--- a/drivers/ssb/driver_extif.c
+++ b/drivers/ssb/driver_extif.c
@@ -10,12 +10,12 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/serial.h>
 #include <linux/serial_core.h>
 #include <linux/serial_reg.h>
 
-#include "ssb_private.h"
-
 
 static inline u32 extif_read32(struct ssb_extif *extif, u16 offset)
 {
diff --git a/drivers/ssb/driver_gige.c b/drivers/ssb/driver_gige.c
index e9734051e3c4..ebee6b0e3c34 100644
--- a/drivers/ssb/driver_gige.c
+++ b/drivers/ssb/driver_gige.c
@@ -242,7 +242,7 @@ static int ssb_gige_probe(struct ssb_device *sdev,
 bool pdev_is_ssb_gige_core(struct pci_dev *pdev)
 {
 	if (!pdev->resource[0].name)
-		return 0;
+		return false;
 	return (strcmp(pdev->resource[0].name, SSB_GIGE_MEM_RES_NAME) == 0);
 }
 EXPORT_SYMBOL(pdev_is_ssb_gige_core);
diff --git a/drivers/ssb/driver_gpio.c b/drivers/ssb/driver_gpio.c
index 796e22037bc4..e809dae4c470 100644
--- a/drivers/ssb/driver_gpio.c
+++ b/drivers/ssb/driver_gpio.c
@@ -8,6 +8,8 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/gpio/driver.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
@@ -15,8 +17,6 @@
 #include <linux/export.h>
 #include <linux/ssb/ssb.h>
 
-#include "ssb_private.h"
-
 
 /**************************************************
  * Shared
@@ -461,7 +461,7 @@ int ssb_gpio_init(struct ssb_bus *bus)
 	else if (ssb_extif_available(&bus->extif))
 		return ssb_gpio_extif_init(bus);
 	else
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 
 	return -1;
 }
@@ -473,7 +473,7 @@ int ssb_gpio_unregister(struct ssb_bus *bus)
 		gpiochip_remove(&bus->gpio);
 		return 0;
 	} else {
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 
 	return -1;
diff --git a/drivers/ssb/driver_mipscore.c b/drivers/ssb/driver_mipscore.c
index f87efef42252..1ca2ac5ef2b8 100644
--- a/drivers/ssb/driver_mipscore.c
+++ b/drivers/ssb/driver_mipscore.c
@@ -8,6 +8,8 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/ssb/ssb.h>
 
 #include <linux/mtd/physmap.h>
@@ -19,8 +21,6 @@
 #include <linux/bcm47xx_nvram.h>
 #endif
 
-#include "ssb_private.h"
-
 static const char * const part_probes[] = { "bcm47xxpart", NULL };
 
 static struct physmap_flash_data ssb_pflash_data = {
@@ -170,14 +170,15 @@ static void set_irq(struct ssb_device *dev, unsigned int irq)
 		irqflag |= (ipsflag & ~ipsflag_irq_mask[irq]);
 		ssb_write32(mdev, SSB_IPSFLAG, irqflag);
 	}
-	ssb_dbg("set_irq: core 0x%04x, irq %d => %d\n",
+	dev_dbg(dev->dev, "set_irq: core 0x%04x, irq %d => %d\n",
 		dev->id.coreid, oldirq+2, irq+2);
 }
 
 static void print_irq(struct ssb_device *dev, unsigned int irq)
 {
 	static const char *irq_name[] = {"2(S)", "3", "4", "5", "6", "D", "I"};
-	ssb_dbg("core 0x%04x, irq : %s%s %s%s %s%s %s%s %s%s %s%s %s%s\n",
+	dev_dbg(dev->dev,
+		"core 0x%04x, irq : %s%s %s%s %s%s %s%s %s%s %s%s %s%s\n",
 		dev->id.coreid,
 		irq_name[0], irq == 0 ? "*" : " ",
 		irq_name[1], irq == 1 ? "*" : " ",
@@ -229,11 +230,11 @@ static void ssb_mips_flash_detect(struct ssb_mipscore *mcore)
 	switch (bus->chipco.capabilities & SSB_CHIPCO_CAP_FLASHT) {
 	case SSB_CHIPCO_FLASHT_STSER:
 	case SSB_CHIPCO_FLASHT_ATSER:
-		pr_debug("Found serial flash\n");
+		dev_dbg(mcore->dev->dev, "Found serial flash\n");
 		ssb_sflash_init(&bus->chipco);
 		break;
 	case SSB_CHIPCO_FLASHT_PARA:
-		pr_debug("Found parallel flash\n");
+		dev_dbg(mcore->dev->dev, "Found parallel flash\n");
 		pflash->present = true;
 		pflash->window = SSB_FLASH2;
 		pflash->window_size = SSB_FLASH2_SZ;
@@ -299,7 +300,7 @@ void ssb_mipscore_init(struct ssb_mipscore *mcore)
 	if (!mcore->dev)
 		return; /* We don't have a MIPS core */
 
-	ssb_dbg("Initializing MIPS core...\n");
+	dev_dbg(mcore->dev->dev, "Initializing MIPS core...\n");
 
 	bus = mcore->dev->bus;
 	hz = ssb_clockspeed(bus);
@@ -347,7 +348,7 @@ void ssb_mipscore_init(struct ssb_mipscore *mcore)
 			break;
 		}
 	}
-	ssb_dbg("after irq reconfiguration\n");
+	dev_dbg(mcore->dev->dev, "after irq reconfiguration\n");
 	dump_irq(bus);
 
 	ssb_mips_serial_init(mcore);
diff --git a/drivers/ssb/driver_pcicore.c b/drivers/ssb/driver_pcicore.c
index 5fe1c22e289b..6a5622e0ded5 100644
--- a/drivers/ssb/driver_pcicore.c
+++ b/drivers/ssb/driver_pcicore.c
@@ -8,14 +8,14 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/ssb/ssb.h>
 #include <linux/pci.h>
 #include <linux/export.h>
 #include <linux/delay.h>
 #include <linux/ssb/ssb_embedded.h>
 
-#include "ssb_private.h"
-
 static u32 ssb_pcie_read(struct ssb_pcicore *pc, u32 address);
 static void ssb_pcie_write(struct ssb_pcicore *pc, u32 address, u32 data);
 static u16 ssb_pcie_mdio_read(struct ssb_pcicore *pc, u8 device, u8 address);
@@ -115,7 +115,7 @@ static int ssb_extpci_read_config(struct ssb_pcicore *pc,
 	u32 addr, val;
 	void __iomem *mmio;
 
-	SSB_WARN_ON(!pc->hostmode);
+	WARN_ON(!pc->hostmode);
 	if (unlikely(len != 1 && len != 2 && len != 4))
 		goto out;
 	addr = get_cfgspace_addr(pc, bus, dev, func, off);
@@ -161,7 +161,7 @@ static int ssb_extpci_write_config(struct ssb_pcicore *pc,
 	u32 addr, val = 0;
 	void __iomem *mmio;
 
-	SSB_WARN_ON(!pc->hostmode);
+	WARN_ON(!pc->hostmode);
 	if (unlikely(len != 1 && len != 2 && len != 4))
 		goto out;
 	addr = get_cfgspace_addr(pc, bus, dev, func, off);
@@ -263,7 +263,7 @@ int ssb_pcicore_plat_dev_init(struct pci_dev *d)
 		return -ENODEV;
 	}
 
-	ssb_info("PCI: Fixing up device %s\n", pci_name(d));
+	dev_info(&d->dev, "PCI: Fixing up device %s\n", pci_name(d));
 
 	/* Fix up interrupt lines */
 	d->irq = ssb_mips_irq(extpci_core->dev) + 2;
@@ -284,12 +284,12 @@ static void ssb_pcicore_fixup_pcibridge(struct pci_dev *dev)
 	if (dev->bus->number != 0 || PCI_SLOT(dev->devfn) != 0)
 		return;
 
-	ssb_info("PCI: Fixing up bridge %s\n", pci_name(dev));
+	dev_info(&dev->dev, "PCI: Fixing up bridge %s\n", pci_name(dev));
 
 	/* Enable PCI bridge bus mastering and memory space */
 	pci_set_master(dev);
 	if (pcibios_enable_device(dev, ~0) < 0) {
-		ssb_err("PCI: SSB bridge enable failed\n");
+		dev_err(&dev->dev, "PCI: SSB bridge enable failed\n");
 		return;
 	}
 
@@ -298,7 +298,8 @@ static void ssb_pcicore_fixup_pcibridge(struct pci_dev *dev)
 
 	/* Make sure our latency is high enough to handle the devices behind us */
 	lat = 168;
-	ssb_info("PCI: Fixing latency timer of device %s to %u\n",
+	dev_info(&dev->dev,
+		 "PCI: Fixing latency timer of device %s to %u\n",
 		 pci_name(dev), lat);
 	pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat);
 }
@@ -322,7 +323,7 @@ static void ssb_pcicore_init_hostmode(struct ssb_pcicore *pc)
 		return;
 	extpci_core = pc;
 
-	ssb_dbg("PCIcore in host mode found\n");
+	dev_dbg(pc->dev->dev, "PCIcore in host mode found\n");
 	/* Reset devices on the external PCI bus */
 	val = SSB_PCICORE_CTL_RST_OE;
 	val |= SSB_PCICORE_CTL_CLK_OE;
@@ -337,7 +338,7 @@ static void ssb_pcicore_init_hostmode(struct ssb_pcicore *pc)
 	udelay(1); /* Assertion time demanded by the PCI standard */
 
 	if (pc->dev->bus->has_cardbus_slot) {
-		ssb_dbg("CardBus slot detected\n");
+		dev_dbg(pc->dev->dev, "CardBus slot detected\n");
 		pc->cardbusmode = 1;
 		/* GPIO 1 resets the bridge */
 		ssb_gpio_out(pc->dev->bus, 1, 1);
@@ -701,7 +702,7 @@ int ssb_pcicore_dev_irqvecs_enable(struct ssb_pcicore *pc,
 		/* Calculate the "coremask" for the device. */
 		coremask = (1 << dev->core_index);
 
-		SSB_WARN_ON(bus->bustype != SSB_BUSTYPE_PCI);
+		WARN_ON(bus->bustype != SSB_BUSTYPE_PCI);
 		err = pci_read_config_dword(bus->host_pci, SSB_PCI_IRQMASK, &tmp);
 		if (err)
 			goto out;
diff --git a/drivers/ssb/embedded.c b/drivers/ssb/embedded.c
index 55e101115038..8254ed25e063 100644
--- a/drivers/ssb/embedded.c
+++ b/drivers/ssb/embedded.c
@@ -9,6 +9,8 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/export.h>
 #include <linux/platform_device.h>
 #include <linux/ssb/ssb.h>
@@ -17,8 +19,6 @@
 #include <linux/ssb/ssb_driver_gige.h>
 #include <linux/pci.h>
 
-#include "ssb_private.h"
-
 
 int ssb_watchdog_timer_set(struct ssb_bus *bus, u32 ticks)
 {
@@ -57,8 +57,8 @@ int ssb_watchdog_register(struct ssb_bus *bus)
 					     bus->busnumber, &wdt,
 					     sizeof(wdt));
 	if (IS_ERR(pdev)) {
-		ssb_dbg("can not register watchdog device, err: %li\n",
-			PTR_ERR(pdev));
+		pr_debug("can not register watchdog device, err: %li\n",
+			 PTR_ERR(pdev));
 		return PTR_ERR(pdev);
 	}
 
@@ -77,7 +77,7 @@ u32 ssb_gpio_in(struct ssb_bus *bus, u32 mask)
 	else if (ssb_extif_available(&bus->extif))
 		res = ssb_extif_gpio_in(&bus->extif, mask);
 	else
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	spin_unlock_irqrestore(&bus->gpio_lock, flags);
 
 	return res;
@@ -95,7 +95,7 @@ u32 ssb_gpio_out(struct ssb_bus *bus, u32 mask, u32 value)
 	else if (ssb_extif_available(&bus->extif))
 		res = ssb_extif_gpio_out(&bus->extif, mask, value);
 	else
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	spin_unlock_irqrestore(&bus->gpio_lock, flags);
 
 	return res;
@@ -113,7 +113,7 @@ u32 ssb_gpio_outen(struct ssb_bus *bus, u32 mask, u32 value)
 	else if (ssb_extif_available(&bus->extif))
 		res = ssb_extif_gpio_outen(&bus->extif, mask, value);
 	else
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	spin_unlock_irqrestore(&bus->gpio_lock, flags);
 
 	return res;
@@ -145,7 +145,7 @@ u32 ssb_gpio_intmask(struct ssb_bus *bus, u32 mask, u32 value)
 	else if (ssb_extif_available(&bus->extif))
 		res = ssb_extif_gpio_intmask(&bus->extif, mask, value);
 	else
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	spin_unlock_irqrestore(&bus->gpio_lock, flags);
 
 	return res;
@@ -163,7 +163,7 @@ u32 ssb_gpio_polarity(struct ssb_bus *bus, u32 mask, u32 value)
 	else if (ssb_extif_available(&bus->extif))
 		res = ssb_extif_gpio_polarity(&bus->extif, mask, value);
 	else
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	spin_unlock_irqrestore(&bus->gpio_lock, flags);
 
 	return res;
diff --git a/drivers/ssb/host_soc.c b/drivers/ssb/host_soc.c
index d62992dc08b2..3b438480515c 100644
--- a/drivers/ssb/host_soc.c
+++ b/drivers/ssb/host_soc.c
@@ -8,11 +8,11 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/bcm47xx_nvram.h>
 #include <linux/ssb/ssb.h>
 
-#include "ssb_private.h"
-
 static u8 ssb_host_soc_read8(struct ssb_device *dev, u16 offset)
 {
 	struct ssb_bus *bus = dev->bus;
@@ -61,7 +61,7 @@ static void ssb_host_soc_block_read(struct ssb_device *dev, void *buffer,
 	case sizeof(u16): {
 		__le16 *buf = buffer;
 
-		SSB_WARN_ON(count & 1);
+		WARN_ON(count & 1);
 		while (count) {
 			*buf = (__force __le16)__raw_readw(addr);
 			buf++;
@@ -72,7 +72,7 @@ static void ssb_host_soc_block_read(struct ssb_device *dev, void *buffer,
 	case sizeof(u32): {
 		__le32 *buf = buffer;
 
-		SSB_WARN_ON(count & 3);
+		WARN_ON(count & 3);
 		while (count) {
 			*buf = (__force __le32)__raw_readl(addr);
 			buf++;
@@ -81,7 +81,7 @@ static void ssb_host_soc_block_read(struct ssb_device *dev, void *buffer,
 		break;
 	}
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 }
 #endif /* CONFIG_SSB_BLOCKIO */
@@ -134,7 +134,7 @@ static void ssb_host_soc_block_write(struct ssb_device *dev, const void *buffer,
 	case sizeof(u16): {
 		const __le16 *buf = buffer;
 
-		SSB_WARN_ON(count & 1);
+		WARN_ON(count & 1);
 		while (count) {
 			__raw_writew((__force u16)(*buf), addr);
 			buf++;
@@ -145,7 +145,7 @@ static void ssb_host_soc_block_write(struct ssb_device *dev, const void *buffer,
 	case sizeof(u32): {
 		const __le32 *buf = buffer;
 
-		SSB_WARN_ON(count & 3);
+		WARN_ON(count & 3);
 		while (count) {
 			__raw_writel((__force u32)(*buf), addr);
 			buf++;
@@ -154,7 +154,7 @@ static void ssb_host_soc_block_write(struct ssb_device *dev, const void *buffer,
 		break;
 	}
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 }
 #endif /* CONFIG_SSB_BLOCKIO */
diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c
index 116594413f66..0a26984acb2c 100644
--- a/drivers/ssb/main.c
+++ b/drivers/ssb/main.c
@@ -209,7 +209,7 @@ int ssb_devices_freeze(struct ssb_bus *bus, struct ssb_freeze_context *ctx)
 
 	memset(ctx, 0, sizeof(*ctx));
 	ctx->bus = bus;
-	SSB_WARN_ON(bus->nr_devices > ARRAY_SIZE(ctx->device_frozen));
+	WARN_ON(bus->nr_devices > ARRAY_SIZE(ctx->device_frozen));
 
 	for (i = 0; i < bus->nr_devices; i++) {
 		sdev = ssb_device_get(&bus->devices[i]);
@@ -220,7 +220,7 @@ int ssb_devices_freeze(struct ssb_bus *bus, struct ssb_freeze_context *ctx)
 			continue;
 		}
 		sdrv = drv_to_ssb_drv(sdev->dev->driver);
-		if (SSB_WARN_ON(!sdrv->remove))
+		if (WARN_ON(!sdrv->remove))
 			continue;
 		sdrv->remove(sdev);
 		ctx->device_frozen[i] = 1;
@@ -248,15 +248,16 @@ int ssb_devices_thaw(struct ssb_freeze_context *ctx)
 			continue;
 		sdev = &bus->devices[i];
 
-		if (SSB_WARN_ON(!sdev->dev || !sdev->dev->driver))
+		if (WARN_ON(!sdev->dev || !sdev->dev->driver))
 			continue;
 		sdrv = drv_to_ssb_drv(sdev->dev->driver);
-		if (SSB_WARN_ON(!sdrv || !sdrv->probe))
+		if (WARN_ON(!sdrv || !sdrv->probe))
 			continue;
 
 		err = sdrv->probe(sdev, &sdev->id);
 		if (err) {
-			ssb_err("Failed to thaw device %s\n",
+			dev_err(sdev->dev,
+				"Failed to thaw device %s\n",
 				dev_name(sdev->dev));
 			result = err;
 		}
@@ -431,9 +432,9 @@ void ssb_bus_unregister(struct ssb_bus *bus)
 
 	err = ssb_gpio_unregister(bus);
 	if (err == -EBUSY)
-		ssb_dbg("Some GPIOs are still in use\n");
+		pr_debug("Some GPIOs are still in use\n");
 	else if (err)
-		ssb_dbg("Can not unregister GPIO driver: %i\n", err);
+		pr_debug("Can not unregister GPIO driver: %i\n", err);
 
 	ssb_buses_lock();
 	ssb_devices_unregister(bus);
@@ -518,7 +519,7 @@ static int ssb_devices_register(struct ssb_bus *bus)
 		sdev->dev = dev;
 		err = device_register(dev);
 		if (err) {
-			ssb_err("Could not register %s\n", dev_name(dev));
+			pr_err("Could not register %s\n", dev_name(dev));
 			/* Set dev to NULL to not unregister
 			 * dev on error unwinding. */
 			sdev->dev = NULL;
@@ -576,9 +577,9 @@ static int ssb_attach_queued_buses(void)
 
 		err = ssb_gpio_init(bus);
 		if (err == -ENOTSUPP)
-			ssb_dbg("GPIO driver not activated\n");
+			pr_debug("GPIO driver not activated\n");
 		else if (err)
-			ssb_dbg("Error registering GPIO driver: %i\n", err);
+			pr_debug("Error registering GPIO driver: %i\n", err);
 
 		ssb_bus_may_powerdown(bus);
 
@@ -707,10 +708,12 @@ int ssb_bus_pcibus_register(struct ssb_bus *bus, struct pci_dev *host_pci)
 
 	err = ssb_bus_register(bus, ssb_pci_get_invariants, 0);
 	if (!err) {
-		ssb_info("Sonics Silicon Backplane found on PCI device %s\n",
+		dev_info(&host_pci->dev,
+			 "Sonics Silicon Backplane found on PCI device %s\n",
 			 dev_name(&host_pci->dev));
 	} else {
-		ssb_err("Failed to register PCI version of SSB with error %d\n",
+		dev_err(&host_pci->dev,
+			"Failed to register PCI version of SSB with error %d\n",
 			err);
 	}
 
@@ -731,7 +734,8 @@ int ssb_bus_pcmciabus_register(struct ssb_bus *bus,
 
 	err = ssb_bus_register(bus, ssb_pcmcia_get_invariants, baseaddr);
 	if (!err) {
-		ssb_info("Sonics Silicon Backplane found on PCMCIA device %s\n",
+		dev_info(&pcmcia_dev->dev,
+			 "Sonics Silicon Backplane found on PCMCIA device %s\n",
 			 pcmcia_dev->devname);
 	}
 
@@ -752,7 +756,8 @@ int ssb_bus_sdiobus_register(struct ssb_bus *bus, struct sdio_func *func,
 
 	err = ssb_bus_register(bus, ssb_sdio_get_invariants, ~0);
 	if (!err) {
-		ssb_info("Sonics Silicon Backplane found on SDIO device %s\n",
+		dev_info(&func->dev,
+			 "Sonics Silicon Backplane found on SDIO device %s\n",
 			 sdio_func_id(func));
 	}
 
@@ -771,8 +776,8 @@ int ssb_bus_host_soc_register(struct ssb_bus *bus, unsigned long baseaddr)
 
 	err = ssb_bus_register(bus, ssb_host_soc_get_invariants, baseaddr);
 	if (!err) {
-		ssb_info("Sonics Silicon Backplane found at address 0x%08lX\n",
-			 baseaddr);
+		pr_info("Sonics Silicon Backplane found at address 0x%08lX\n",
+			baseaddr);
 	}
 
 	return err;
@@ -856,13 +861,13 @@ u32 ssb_calc_clock_rate(u32 plltype, u32 n, u32 m)
 	case SSB_PLLTYPE_2: /* 48Mhz, 4 dividers */
 		n1 += SSB_CHIPCO_CLK_T2_BIAS;
 		n2 += SSB_CHIPCO_CLK_T2_BIAS;
-		SSB_WARN_ON(!((n1 >= 2) && (n1 <= 7)));
-		SSB_WARN_ON(!((n2 >= 5) && (n2 <= 23)));
+		WARN_ON(!((n1 >= 2) && (n1 <= 7)));
+		WARN_ON(!((n2 >= 5) && (n2 <= 23)));
 		break;
 	case SSB_PLLTYPE_5: /* 25Mhz, 4 dividers */
 		return 100000000;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 
 	switch (plltype) {
@@ -911,9 +916,9 @@ u32 ssb_calc_clock_rate(u32 plltype, u32 n, u32 m)
 		m1 += SSB_CHIPCO_CLK_T2_BIAS;
 		m2 += SSB_CHIPCO_CLK_T2M2_BIAS;
 		m3 += SSB_CHIPCO_CLK_T2_BIAS;
-		SSB_WARN_ON(!((m1 >= 2) && (m1 <= 7)));
-		SSB_WARN_ON(!((m2 >= 3) && (m2 <= 10)));
-		SSB_WARN_ON(!((m3 >= 2) && (m3 <= 7)));
+		WARN_ON(!((m1 >= 2) && (m1 <= 7)));
+		WARN_ON(!((m2 >= 3) && (m2 <= 10)));
+		WARN_ON(!((m3 >= 2) && (m3 <= 7)));
 
 		if (!(mc & SSB_CHIPCO_CLK_T2MC_M1BYP))
 			clock /= m1;
@@ -923,7 +928,7 @@ u32 ssb_calc_clock_rate(u32 plltype, u32 n, u32 m)
 			clock /= m3;
 		return clock;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 	return 0;
 }
@@ -1057,9 +1062,9 @@ static int ssb_wait_bits(struct ssb_device *dev, u16 reg, u32 bitmask,
 		}
 		udelay(10);
 	}
-	printk(KERN_ERR PFX "Timeout waiting for bitmask %08X on "
-			    "register %04X to %s.\n",
-	       bitmask, reg, (set ? "set" : "clear"));
+	dev_err(dev->dev,
+		"Timeout waiting for bitmask %08X on register %04X to %s\n",
+		bitmask, reg, set ? "set" : "clear");
 
 	return -ETIMEDOUT;
 }
@@ -1164,12 +1169,10 @@ int ssb_bus_may_powerdown(struct ssb_bus *bus)
 	if (err)
 		goto error;
 out:
-#ifdef CONFIG_SSB_DEBUG
 	bus->powered_up = 0;
-#endif
 	return err;
 error:
-	ssb_err("Bus powerdown failed\n");
+	pr_err("Bus powerdown failed\n");
 	goto out;
 }
 EXPORT_SYMBOL(ssb_bus_may_powerdown);
@@ -1183,16 +1186,14 @@ int ssb_bus_powerup(struct ssb_bus *bus, bool dynamic_pctl)
 	if (err)
 		goto error;
 
-#ifdef CONFIG_SSB_DEBUG
 	bus->powered_up = 1;
-#endif
 
 	mode = dynamic_pctl ? SSB_CLKMODE_DYNAMIC : SSB_CLKMODE_FAST;
 	ssb_chipco_set_clockmode(&bus->chipco, mode);
 
 	return 0;
 error:
-	ssb_err("Bus powerup failed\n");
+	pr_err("Bus powerup failed\n");
 	return err;
 }
 EXPORT_SYMBOL(ssb_bus_powerup);
@@ -1237,15 +1238,15 @@ u32 ssb_admatch_base(u32 adm)
 		base = (adm & SSB_ADM_BASE0);
 		break;
 	case SSB_ADM_TYPE1:
-		SSB_WARN_ON(adm & SSB_ADM_NEG); /* unsupported */
+		WARN_ON(adm & SSB_ADM_NEG); /* unsupported */
 		base = (adm & SSB_ADM_BASE1);
 		break;
 	case SSB_ADM_TYPE2:
-		SSB_WARN_ON(adm & SSB_ADM_NEG); /* unsupported */
+		WARN_ON(adm & SSB_ADM_NEG); /* unsupported */
 		base = (adm & SSB_ADM_BASE2);
 		break;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 
 	return base;
@@ -1261,15 +1262,15 @@ u32 ssb_admatch_size(u32 adm)
 		size = ((adm & SSB_ADM_SZ0) >> SSB_ADM_SZ0_SHIFT);
 		break;
 	case SSB_ADM_TYPE1:
-		SSB_WARN_ON(adm & SSB_ADM_NEG); /* unsupported */
+		WARN_ON(adm & SSB_ADM_NEG); /* unsupported */
 		size = ((adm & SSB_ADM_SZ1) >> SSB_ADM_SZ1_SHIFT);
 		break;
 	case SSB_ADM_TYPE2:
-		SSB_WARN_ON(adm & SSB_ADM_NEG); /* unsupported */
+		WARN_ON(adm & SSB_ADM_NEG); /* unsupported */
 		size = ((adm & SSB_ADM_SZ2) >> SSB_ADM_SZ2_SHIFT);
 		break;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 	size = (1 << (size + 1));
 
@@ -1300,19 +1301,19 @@ static int __init ssb_modinit(void)
 
 	err = b43_pci_ssb_bridge_init();
 	if (err) {
-		ssb_err("Broadcom 43xx PCI-SSB-bridge initialization failed\n");
+		pr_err("Broadcom 43xx PCI-SSB-bridge initialization failed\n");
 		/* don't fail SSB init because of this */
 		err = 0;
 	}
 	err = ssb_host_pcmcia_init();
 	if (err) {
-		ssb_err("PCMCIA host initialization failed\n");
+		pr_err("PCMCIA host initialization failed\n");
 		/* don't fail SSB init because of this */
 		err = 0;
 	}
 	err = ssb_gige_init();
 	if (err) {
-		ssb_err("SSB Broadcom Gigabit Ethernet driver initialization failed\n");
+		pr_err("SSB Broadcom Gigabit Ethernet driver initialization failed\n");
 		/* don't fail SSB init because of this */
 		err = 0;
 	}
diff --git a/drivers/ssb/pci.c b/drivers/ssb/pci.c
index 77b551da5728..84807a9b4b13 100644
--- a/drivers/ssb/pci.c
+++ b/drivers/ssb/pci.c
@@ -15,14 +15,14 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/ssb/ssb.h>
 #include <linux/ssb/ssb_regs.h>
 #include <linux/slab.h>
 #include <linux/pci.h>
 #include <linux/delay.h>
 
-#include "ssb_private.h"
-
 
 /* Define the following to 1 to enable a printk on each coreswitch. */
 #define SSB_VERBOSE_PCICORESWITCH_DEBUG		0
@@ -56,7 +56,7 @@ int ssb_pci_switch_coreidx(struct ssb_bus *bus, u8 coreidx)
 	}
 	return 0;
 error:
-	ssb_err("Failed to switch to core %u\n", coreidx);
+	pr_err("Failed to switch to core %u\n", coreidx);
 	return -ENODEV;
 }
 
@@ -67,9 +67,8 @@ int ssb_pci_switch_core(struct ssb_bus *bus,
 	unsigned long flags;
 
 #if SSB_VERBOSE_PCICORESWITCH_DEBUG
-	ssb_info("Switching to %s core, index %d\n",
-		 ssb_core_name(dev->id.coreid),
-		 dev->core_index);
+	pr_info("Switching to %s core, index %d\n",
+		ssb_core_name(dev->id.coreid), dev->core_index);
 #endif
 
 	spin_lock_irqsave(&bus->bar_lock, flags);
@@ -161,7 +160,7 @@ out:
 	return err;
 
 err_pci:
-	printk(KERN_ERR PFX "Error: ssb_pci_xtal() could not access PCI config space!\n");
+	pr_err("Error: ssb_pci_xtal() could not access PCI config space!\n");
 	err = -EBUSY;
 	goto out;
 }
@@ -286,7 +285,7 @@ static int sprom_do_write(struct ssb_bus *bus, const u16 *sprom)
 	u32 spromctl;
 	u16 size = bus->sprom_size;
 
-	ssb_notice("Writing SPROM. Do NOT turn off the power! Please stand by...\n");
+	pr_notice("Writing SPROM. Do NOT turn off the power! Please stand by...\n");
 	err = pci_read_config_dword(pdev, SSB_SPROMCTL, &spromctl);
 	if (err)
 		goto err_ctlreg;
@@ -294,17 +293,17 @@ static int sprom_do_write(struct ssb_bus *bus, const u16 *sprom)
 	err = pci_write_config_dword(pdev, SSB_SPROMCTL, spromctl);
 	if (err)
 		goto err_ctlreg;
-	ssb_notice("[ 0%%");
+	pr_notice("[ 0%%");
 	msleep(500);
 	for (i = 0; i < size; i++) {
 		if (i == size / 4)
-			ssb_cont("25%%");
+			pr_cont("25%%");
 		else if (i == size / 2)
-			ssb_cont("50%%");
+			pr_cont("50%%");
 		else if (i == (size * 3) / 4)
-			ssb_cont("75%%");
+			pr_cont("75%%");
 		else if (i % 2)
-			ssb_cont(".");
+			pr_cont(".");
 		writew(sprom[i], bus->mmio + bus->sprom_offset + (i * 2));
 		mmiowb();
 		msleep(20);
@@ -317,12 +316,12 @@ static int sprom_do_write(struct ssb_bus *bus, const u16 *sprom)
 	if (err)
 		goto err_ctlreg;
 	msleep(500);
-	ssb_cont("100%% ]\n");
-	ssb_notice("SPROM written\n");
+	pr_cont("100%% ]\n");
+	pr_notice("SPROM written\n");
 
 	return 0;
 err_ctlreg:
-	ssb_err("Could not access SPROM control register.\n");
+	pr_err("Could not access SPROM control register.\n");
 	return err;
 }
 
@@ -816,7 +815,7 @@ static int sprom_extract(struct ssb_bus *bus, struct ssb_sprom *out,
 	memset(out, 0, sizeof(*out));
 
 	out->revision = in[size - 1] & 0x00FF;
-	ssb_dbg("SPROM revision %d detected\n", out->revision);
+	pr_debug("SPROM revision %d detected\n", out->revision);
 	memset(out->et0mac, 0xFF, 6);		/* preset et0 and et1 mac */
 	memset(out->et1mac, 0xFF, 6);
 
@@ -825,7 +824,7 @@ static int sprom_extract(struct ssb_bus *bus, struct ssb_sprom *out,
 		 * number stored in the SPROM.
 		 * Always extract r1. */
 		out->revision = 1;
-		ssb_dbg("SPROM treated as revision %d\n", out->revision);
+		pr_debug("SPROM treated as revision %d\n", out->revision);
 	}
 
 	switch (out->revision) {
@@ -842,8 +841,8 @@ static int sprom_extract(struct ssb_bus *bus, struct ssb_sprom *out,
 		sprom_extract_r8(out, in);
 		break;
 	default:
-		ssb_warn("Unsupported SPROM revision %d detected. Will extract v1\n",
-			 out->revision);
+		pr_warn("Unsupported SPROM revision %d detected. Will extract v1\n",
+			out->revision);
 		out->revision = 1;
 		sprom_extract_r123(out, in);
 	}
@@ -863,7 +862,7 @@ static int ssb_pci_sprom_get(struct ssb_bus *bus,
 	u16 *buf;
 
 	if (!ssb_is_sprom_available(bus)) {
-		ssb_err("No SPROM available!\n");
+		pr_err("No SPROM available!\n");
 		return -ENODEV;
 	}
 	if (bus->chipco.dev) {	/* can be unavailable! */
@@ -882,7 +881,7 @@ static int ssb_pci_sprom_get(struct ssb_bus *bus,
 	} else {
 		bus->sprom_offset = SSB_SPROM_BASE1;
 	}
-	ssb_dbg("SPROM offset is 0x%x\n", bus->sprom_offset);
+	pr_debug("SPROM offset is 0x%x\n", bus->sprom_offset);
 
 	buf = kcalloc(SSB_SPROMSIZE_WORDS_R123, sizeof(u16), GFP_KERNEL);
 	if (!buf)
@@ -907,16 +906,16 @@ static int ssb_pci_sprom_get(struct ssb_bus *bus,
 			 * available for this device in some other storage */
 			err = ssb_fill_sprom_with_fallback(bus, sprom);
 			if (err) {
-				ssb_warn("WARNING: Using fallback SPROM failed (err %d)\n",
-					 err);
+				pr_warn("WARNING: Using fallback SPROM failed (err %d)\n",
+					err);
 				goto out_free;
 			} else {
-				ssb_dbg("Using SPROM revision %d provided by platform\n",
-					sprom->revision);
+				pr_debug("Using SPROM revision %d provided by platform\n",
+					 sprom->revision);
 				err = 0;
 				goto out_free;
 			}
-			ssb_warn("WARNING: Invalid SPROM CRC (corrupt SPROM)\n");
+			pr_warn("WARNING: Invalid SPROM CRC (corrupt SPROM)\n");
 		}
 	}
 	err = sprom_extract(bus, sprom, buf, bus->sprom_size);
@@ -947,14 +946,12 @@ out:
 	return err;
 }
 
-#ifdef CONFIG_SSB_DEBUG
 static int ssb_pci_assert_buspower(struct ssb_bus *bus)
 {
 	if (likely(bus->powered_up))
 		return 0;
 
-	printk(KERN_ERR PFX "FATAL ERROR: Bus powered down "
-	       "while accessing PCI MMIO space\n");
+	pr_err("FATAL ERROR: Bus powered down while accessing PCI MMIO space\n");
 	if (bus->power_warn_count <= 10) {
 		bus->power_warn_count++;
 		dump_stack();
@@ -962,12 +959,6 @@ static int ssb_pci_assert_buspower(struct ssb_bus *bus)
 
 	return -ENODEV;
 }
-#else /* DEBUG */
-static inline int ssb_pci_assert_buspower(struct ssb_bus *bus)
-{
-	return 0;
-}
-#endif /* DEBUG */
 
 static u8 ssb_pci_read8(struct ssb_device *dev, u16 offset)
 {
@@ -1026,15 +1017,15 @@ static void ssb_pci_block_read(struct ssb_device *dev, void *buffer,
 		ioread8_rep(addr, buffer, count);
 		break;
 	case sizeof(u16):
-		SSB_WARN_ON(count & 1);
+		WARN_ON(count & 1);
 		ioread16_rep(addr, buffer, count >> 1);
 		break;
 	case sizeof(u32):
-		SSB_WARN_ON(count & 3);
+		WARN_ON(count & 3);
 		ioread32_rep(addr, buffer, count >> 2);
 		break;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 
 	return;
@@ -1100,15 +1091,15 @@ static void ssb_pci_block_write(struct ssb_device *dev, const void *buffer,
 		iowrite8_rep(addr, buffer, count);
 		break;
 	case sizeof(u16):
-		SSB_WARN_ON(count & 1);
+		WARN_ON(count & 1);
 		iowrite16_rep(addr, buffer, count >> 1);
 		break;
 	case sizeof(u32):
-		SSB_WARN_ON(count & 3);
+		WARN_ON(count & 3);
 		iowrite32_rep(addr, buffer, count >> 2);
 		break;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 }
 #endif /* CONFIG_SSB_BLOCKIO */
diff --git a/drivers/ssb/pcmcia.c b/drivers/ssb/pcmcia.c
index f03422bbf087..567013f8a8be 100644
--- a/drivers/ssb/pcmcia.c
+++ b/drivers/ssb/pcmcia.c
@@ -8,6 +8,8 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/ssb/ssb.h>
 #include <linux/delay.h>
 #include <linux/io.h>
@@ -18,8 +20,6 @@
 #include <pcmcia/ds.h>
 #include <pcmcia/cisreg.h>
 
-#include "ssb_private.h"
-
 
 /* Define the following to 1 to enable a printk on each coreswitch. */
 #define SSB_VERBOSE_PCMCIACORESWITCH_DEBUG		0
@@ -143,7 +143,7 @@ int ssb_pcmcia_switch_coreidx(struct ssb_bus *bus,
 
 	return 0;
 error:
-	ssb_err("Failed to switch to core %u\n", coreidx);
+	pr_err("Failed to switch to core %u\n", coreidx);
 	return err;
 }
 
@@ -152,9 +152,8 @@ static int ssb_pcmcia_switch_core(struct ssb_bus *bus, struct ssb_device *dev)
 	int err;
 
 #if SSB_VERBOSE_PCMCIACORESWITCH_DEBUG
-	ssb_info("Switching to %s core, index %d\n",
-		 ssb_core_name(dev->id.coreid),
-		 dev->core_index);
+	pr_info("Switching to %s core, index %d\n",
+		ssb_core_name(dev->id.coreid), dev->core_index);
 #endif
 
 	err = ssb_pcmcia_switch_coreidx(bus, dev->core_index);
@@ -170,7 +169,7 @@ int ssb_pcmcia_switch_segment(struct ssb_bus *bus, u8 seg)
 	int err;
 	u8 val;
 
-	SSB_WARN_ON((seg != 0) && (seg != 1));
+	WARN_ON((seg != 0) && (seg != 1));
 	while (1) {
 		err = ssb_pcmcia_cfg_write(bus, SSB_PCMCIA_MEMSEG, seg);
 		if (err)
@@ -190,7 +189,7 @@ int ssb_pcmcia_switch_segment(struct ssb_bus *bus, u8 seg)
 
 	return 0;
 error:
-	ssb_err("Failed to switch pcmcia segment\n");
+	pr_err("Failed to switch pcmcia segment\n");
 	return err;
 }
 
@@ -300,7 +299,7 @@ static void ssb_pcmcia_block_read(struct ssb_device *dev, void *buffer,
 	case sizeof(u16): {
 		__le16 *buf = buffer;
 
-		SSB_WARN_ON(count & 1);
+		WARN_ON(count & 1);
 		while (count) {
 			*buf = (__force __le16)__raw_readw(addr);
 			buf++;
@@ -311,7 +310,7 @@ static void ssb_pcmcia_block_read(struct ssb_device *dev, void *buffer,
 	case sizeof(u32): {
 		__le16 *buf = buffer;
 
-		SSB_WARN_ON(count & 3);
+		WARN_ON(count & 3);
 		while (count) {
 			*buf = (__force __le16)__raw_readw(addr);
 			buf++;
@@ -322,7 +321,7 @@ static void ssb_pcmcia_block_read(struct ssb_device *dev, void *buffer,
 		break;
 	}
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 unlock:
 	spin_unlock_irqrestore(&bus->bar_lock, flags);
@@ -400,7 +399,7 @@ static void ssb_pcmcia_block_write(struct ssb_device *dev, const void *buffer,
 	case sizeof(u16): {
 		const __le16 *buf = buffer;
 
-		SSB_WARN_ON(count & 1);
+		WARN_ON(count & 1);
 		while (count) {
 			__raw_writew((__force u16)(*buf), addr);
 			buf++;
@@ -411,7 +410,7 @@ static void ssb_pcmcia_block_write(struct ssb_device *dev, const void *buffer,
 	case sizeof(u32): {
 		const __le16 *buf = buffer;
 
-		SSB_WARN_ON(count & 3);
+		WARN_ON(count & 3);
 		while (count) {
 			__raw_writew((__force u16)(*buf), addr);
 			buf++;
@@ -422,7 +421,7 @@ static void ssb_pcmcia_block_write(struct ssb_device *dev, const void *buffer,
 		break;
 	}
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 unlock:
 	mmiowb();
@@ -547,39 +546,39 @@ static int ssb_pcmcia_sprom_write_all(struct ssb_bus *bus, const u16 *sprom)
 	bool failed = 0;
 	size_t size = SSB_PCMCIA_SPROM_SIZE;
 
-	ssb_notice("Writing SPROM. Do NOT turn off the power! Please stand by...\n");
+	pr_notice("Writing SPROM. Do NOT turn off the power! Please stand by...\n");
 	err = ssb_pcmcia_sprom_command(bus, SSB_PCMCIA_SPROMCTL_WRITEEN);
 	if (err) {
-		ssb_notice("Could not enable SPROM write access\n");
+		pr_notice("Could not enable SPROM write access\n");
 		return -EBUSY;
 	}
-	ssb_notice("[ 0%%");
+	pr_notice("[ 0%%");
 	msleep(500);
 	for (i = 0; i < size; i++) {
 		if (i == size / 4)
-			ssb_cont("25%%");
+			pr_cont("25%%");
 		else if (i == size / 2)
-			ssb_cont("50%%");
+			pr_cont("50%%");
 		else if (i == (size * 3) / 4)
-			ssb_cont("75%%");
+			pr_cont("75%%");
 		else if (i % 2)
-			ssb_cont(".");
+			pr_cont(".");
 		err = ssb_pcmcia_sprom_write(bus, i, sprom[i]);
 		if (err) {
-			ssb_notice("Failed to write to SPROM\n");
+			pr_notice("Failed to write to SPROM\n");
 			failed = 1;
 			break;
 		}
 	}
 	err = ssb_pcmcia_sprom_command(bus, SSB_PCMCIA_SPROMCTL_WRITEDIS);
 	if (err) {
-		ssb_notice("Could not disable SPROM write access\n");
+		pr_notice("Could not disable SPROM write access\n");
 		failed = 1;
 	}
 	msleep(500);
 	if (!failed) {
-		ssb_cont("100%% ]\n");
-		ssb_notice("SPROM written\n");
+		pr_cont("100%% ]\n");
+		pr_notice("SPROM written\n");
 	}
 
 	return failed ? -EBUSY : 0;
@@ -693,9 +692,8 @@ static int ssb_pcmcia_do_get_invariants(struct pcmcia_device *p_dev,
 	return -ENOSPC; /* continue with next entry */
 
 error:
-	ssb_err(
-		   "PCMCIA: Failed to fetch device invariants: %s\n",
-		   error_description);
+	pr_err("PCMCIA: Failed to fetch device invariants: %s\n",
+	       error_description);
 	return -ENODEV;
 }
 
@@ -715,8 +713,7 @@ int ssb_pcmcia_get_invariants(struct ssb_bus *bus,
 	res = pcmcia_loop_tuple(bus->host_pcmcia, CISTPL_FUNCE,
 				ssb_pcmcia_get_mac, sprom);
 	if (res != 0) {
-		ssb_err(
-			"PCMCIA: Failed to fetch MAC address\n");
+		pr_err("PCMCIA: Failed to fetch MAC address\n");
 		return -ENODEV;
 	}
 
@@ -726,8 +723,7 @@ int ssb_pcmcia_get_invariants(struct ssb_bus *bus,
 	if ((res == 0) || (res == -ENOSPC))
 		return 0;
 
-	ssb_err(
-			"PCMCIA: Failed to fetch device invariants\n");
+	pr_err("PCMCIA: Failed to fetch device invariants\n");
 	return -ENODEV;
 }
 
@@ -836,6 +832,6 @@ int ssb_pcmcia_init(struct ssb_bus *bus)
 
 	return 0;
 error:
-	ssb_err("Failed to initialize PCMCIA host device\n");
+	pr_err("Failed to initialize PCMCIA host device\n");
 	return err;
 }
diff --git a/drivers/ssb/scan.c b/drivers/ssb/scan.c
index b9429df583eb..6ceee98ed6ff 100644
--- a/drivers/ssb/scan.c
+++ b/drivers/ssb/scan.c
@@ -12,6 +12,8 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/ssb/ssb.h>
 #include <linux/ssb/ssb_regs.h>
 #include <linux/pci.h>
@@ -20,8 +22,6 @@
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 
-#include "ssb_private.h"
-
 
 const char *ssb_core_name(u16 coreid)
 {
@@ -125,7 +125,7 @@ static u16 pcidev_to_chipid(struct pci_dev *pci_dev)
 		chipid_fallback = 0x4401;
 		break;
 	default:
-		ssb_err("PCI-ID not in fallback list\n");
+		dev_err(&pci_dev->dev, "PCI-ID not in fallback list\n");
 	}
 
 	return chipid_fallback;
@@ -151,7 +151,7 @@ static u8 chipid_to_nrcores(u16 chipid)
 	case 0x4704:
 		return 9;
 	default:
-		ssb_err("CHIPID not in nrcores fallback list\n");
+		pr_err("CHIPID not in nrcores fallback list\n");
 	}
 
 	return 1;
@@ -210,7 +210,7 @@ void ssb_iounmap(struct ssb_bus *bus)
 #ifdef CONFIG_SSB_PCIHOST
 		pci_iounmap(bus->host_pci, bus->mmio);
 #else
-		SSB_BUG_ON(1); /* Can't reach this code. */
+		WARN_ON(1); /* Can't reach this code. */
 #endif
 		break;
 	case SSB_BUSTYPE_SDIO:
@@ -236,7 +236,7 @@ static void __iomem *ssb_ioremap(struct ssb_bus *bus,
 #ifdef CONFIG_SSB_PCIHOST
 		mmio = pci_iomap(bus->host_pci, 0, ~0UL);
 #else
-		SSB_BUG_ON(1); /* Can't reach this code. */
+		WARN_ON(1); /* Can't reach this code. */
 #endif
 		break;
 	case SSB_BUSTYPE_SDIO:
@@ -318,13 +318,13 @@ int ssb_bus_scan(struct ssb_bus *bus,
 			bus->chip_package = 0;
 		}
 	}
-	ssb_info("Found chip with id 0x%04X, rev 0x%02X and package 0x%02X\n",
-		 bus->chip_id, bus->chip_rev, bus->chip_package);
+	pr_info("Found chip with id 0x%04X, rev 0x%02X and package 0x%02X\n",
+		bus->chip_id, bus->chip_rev, bus->chip_package);
 	if (!bus->nr_devices)
 		bus->nr_devices = chipid_to_nrcores(bus->chip_id);
 	if (bus->nr_devices > ARRAY_SIZE(bus->devices)) {
-		ssb_err("More than %d ssb cores found (%d)\n",
-			SSB_MAX_NR_CORES, bus->nr_devices);
+		pr_err("More than %d ssb cores found (%d)\n",
+		       SSB_MAX_NR_CORES, bus->nr_devices);
 		goto err_unmap;
 	}
 	if (bus->bustype == SSB_BUSTYPE_SSB) {
@@ -355,18 +355,16 @@ int ssb_bus_scan(struct ssb_bus *bus,
 		dev->bus = bus;
 		dev->ops = bus->ops;
 
-		printk(KERN_DEBUG PFX
-			    "Core %d found: %s "
-			    "(cc 0x%03X, rev 0x%02X, vendor 0x%04X)\n",
-			    i, ssb_core_name(dev->id.coreid),
-			    dev->id.coreid, dev->id.revision, dev->id.vendor);
+		pr_debug("Core %d found: %s (cc 0x%03X, rev 0x%02X, vendor 0x%04X)\n",
+			 i, ssb_core_name(dev->id.coreid),
+			 dev->id.coreid, dev->id.revision, dev->id.vendor);
 
 		switch (dev->id.coreid) {
 		case SSB_DEV_80211:
 			nr_80211_cores++;
 			if (nr_80211_cores > 1) {
 				if (!we_support_multiple_80211_cores(bus)) {
-					ssb_dbg("Ignoring additional 802.11 core\n");
+					pr_debug("Ignoring additional 802.11 core\n");
 					continue;
 				}
 			}
@@ -374,7 +372,7 @@ int ssb_bus_scan(struct ssb_bus *bus,
 		case SSB_DEV_EXTIF:
 #ifdef CONFIG_SSB_DRIVER_EXTIF
 			if (bus->extif.dev) {
-				ssb_warn("WARNING: Multiple EXTIFs found\n");
+				pr_warn("WARNING: Multiple EXTIFs found\n");
 				break;
 			}
 			bus->extif.dev = dev;
@@ -382,7 +380,7 @@ int ssb_bus_scan(struct ssb_bus *bus,
 			break;
 		case SSB_DEV_CHIPCOMMON:
 			if (bus->chipco.dev) {
-				ssb_warn("WARNING: Multiple ChipCommon found\n");
+				pr_warn("WARNING: Multiple ChipCommon found\n");
 				break;
 			}
 			bus->chipco.dev = dev;
@@ -391,7 +389,7 @@ int ssb_bus_scan(struct ssb_bus *bus,
 		case SSB_DEV_MIPS_3302:
 #ifdef CONFIG_SSB_DRIVER_MIPS
 			if (bus->mipscore.dev) {
-				ssb_warn("WARNING: Multiple MIPS cores found\n");
+				pr_warn("WARNING: Multiple MIPS cores found\n");
 				break;
 			}
 			bus->mipscore.dev = dev;
@@ -412,7 +410,7 @@ int ssb_bus_scan(struct ssb_bus *bus,
 				}
 			}
 			if (bus->pcicore.dev) {
-				ssb_warn("WARNING: Multiple PCI(E) cores found\n");
+				pr_warn("WARNING: Multiple PCI(E) cores found\n");
 				break;
 			}
 			bus->pcicore.dev = dev;
diff --git a/drivers/ssb/sdio.c b/drivers/ssb/sdio.c
index 2278e43614bd..7fe0afb42234 100644
--- a/drivers/ssb/sdio.c
+++ b/drivers/ssb/sdio.c
@@ -12,14 +12,14 @@
  *
  */
 
+#include "ssb_private.h"
+
 #include <linux/ssb/ssb.h>
 #include <linux/delay.h>
 #include <linux/io.h>
 #include <linux/etherdevice.h>
 #include <linux/mmc/sdio_func.h>
 
-#include "ssb_private.h"
-
 /* Define the following to 1 to enable a printk on each coreswitch. */
 #define SSB_VERBOSE_SDIOCORESWITCH_DEBUG		0
 
@@ -316,18 +316,18 @@ static void ssb_sdio_block_read(struct ssb_device *dev, void *buffer,
 		break;
 	}
 	case sizeof(u16): {
-		SSB_WARN_ON(count & 1);
+		WARN_ON(count & 1);
 		error = sdio_readsb(bus->host_sdio, buffer, offset, count);
 		break;
 	}
 	case sizeof(u32): {
-		SSB_WARN_ON(count & 3);
+		WARN_ON(count & 3);
 		offset |= SBSDIO_SB_ACCESS_2_4B_FLAG;	/* 32 bit data access */
 		error = sdio_readsb(bus->host_sdio, buffer, offset, count);
 		break;
 	}
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 	if (!error)
 		goto out;
@@ -423,18 +423,18 @@ static void ssb_sdio_block_write(struct ssb_device *dev, const void *buffer,
 				     (void *)buffer, count);
 		break;
 	case sizeof(u16):
-		SSB_WARN_ON(count & 1);
+		WARN_ON(count & 1);
 		error = sdio_writesb(bus->host_sdio, offset,
 				     (void *)buffer, count);
 		break;
 	case sizeof(u32):
-		SSB_WARN_ON(count & 3);
+		WARN_ON(count & 3);
 		offset |= SBSDIO_SB_ACCESS_2_4B_FLAG;	/* 32 bit data access */
 		error = sdio_writesb(bus->host_sdio, offset,
 				     (void *)buffer, count);
 		break;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 	if (!error)
 		goto out;
diff --git a/drivers/ssb/sprom.c b/drivers/ssb/sprom.c
index e753fbe302a7..4f028a80d6c4 100644
--- a/drivers/ssb/sprom.c
+++ b/drivers/ssb/sprom.c
@@ -127,13 +127,13 @@ ssize_t ssb_attr_sprom_store(struct ssb_bus *bus,
 		goto out_kfree;
 	err = ssb_devices_freeze(bus, &freeze);
 	if (err) {
-		ssb_err("SPROM write: Could not freeze all devices\n");
+		pr_err("SPROM write: Could not freeze all devices\n");
 		goto out_unlock;
 	}
 	res = sprom_write(bus, sprom);
 	err = ssb_devices_thaw(&freeze);
 	if (err)
-		ssb_err("SPROM write: Could not thaw all devices\n");
+		pr_err("SPROM write: Could not thaw all devices\n");
 out_unlock:
 	mutex_unlock(&bus->sprom_mutex);
 out_kfree:
diff --git a/drivers/ssb/ssb_private.h b/drivers/ssb/ssb_private.h
index ef9ac8efcab4..5f31bdfbe77f 100644
--- a/drivers/ssb/ssb_private.h
+++ b/drivers/ssb/ssb_private.h
@@ -2,47 +2,14 @@
 #ifndef LINUX_SSB_PRIVATE_H_
 #define LINUX_SSB_PRIVATE_H_
 
+#define PFX		"ssb: "
+#define pr_fmt(fmt)	PFX fmt
+
 #include <linux/ssb/ssb.h>
 #include <linux/types.h>
 #include <linux/bcm47xx_wdt.h>
 
 
-#define PFX	"ssb: "
-
-#ifdef CONFIG_SSB_SILENT
-# define ssb_printk(fmt, ...)					\
-	do { if (0) printk(fmt, ##__VA_ARGS__); } while (0)
-#else
-# define ssb_printk(fmt, ...)					\
-	printk(fmt, ##__VA_ARGS__)
-#endif /* CONFIG_SSB_SILENT */
-
-#define ssb_emerg(fmt, ...)	ssb_printk(KERN_EMERG PFX fmt, ##__VA_ARGS__)
-#define ssb_err(fmt, ...)	ssb_printk(KERN_ERR PFX fmt, ##__VA_ARGS__)
-#define ssb_warn(fmt, ...)	ssb_printk(KERN_WARNING PFX fmt, ##__VA_ARGS__)
-#define ssb_notice(fmt, ...)	ssb_printk(KERN_NOTICE PFX fmt, ##__VA_ARGS__)
-#define ssb_info(fmt, ...)	ssb_printk(KERN_INFO PFX fmt, ##__VA_ARGS__)
-#define ssb_cont(fmt, ...)	ssb_printk(KERN_CONT fmt, ##__VA_ARGS__)
-
-/* dprintk: Debugging printk; vanishes for non-debug compilation */
-#ifdef CONFIG_SSB_DEBUG
-# define ssb_dbg(fmt, ...)					\
-	ssb_printk(KERN_DEBUG PFX fmt, ##__VA_ARGS__)
-#else
-# define ssb_dbg(fmt, ...)					\
-	do { if (0) printk(KERN_DEBUG PFX fmt, ##__VA_ARGS__); } while (0)
-#endif
-
-#ifdef CONFIG_SSB_DEBUG
-# define SSB_WARN_ON(x)		WARN_ON(x)
-# define SSB_BUG_ON(x)		BUG_ON(x)
-#else
-static inline int __ssb_do_nothing(int x) { return x; }
-# define SSB_WARN_ON(x)		__ssb_do_nothing(unlikely(!!(x)))
-# define SSB_BUG_ON(x)		__ssb_do_nothing(unlikely(!!(x)))
-#endif
-
-
 /* pci.c */
 #ifdef CONFIG_SSB_PCIHOST
 extern int ssb_pci_switch_core(struct ssb_bus *bus,
diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c
index 9d1109e43ed4..99073325b0c0 100644
--- a/drivers/staging/android/ion/ion.c
+++ b/drivers/staging/android/ion/ion.c
@@ -201,7 +201,7 @@ struct ion_dma_buf_attachment {
 	struct list_head list;
 };
 
-static int ion_dma_buf_attach(struct dma_buf *dmabuf, struct device *dev,
+static int ion_dma_buf_attach(struct dma_buf *dmabuf,
 			      struct dma_buf_attachment *attachment)
 {
 	struct ion_dma_buf_attachment *a;
@@ -219,7 +219,7 @@ static int ion_dma_buf_attach(struct dma_buf *dmabuf, struct device *dev,
 	}
 
 	a->table = table;
-	a->dev = dev;
+	a->dev = attachment->dev;
 	INIT_LIST_HEAD(&a->list);
 
 	attachment->priv = a;
@@ -375,8 +375,6 @@ static const struct dma_buf_ops dma_buf_ops = {
 	.detach = ion_dma_buf_detatch,
 	.begin_cpu_access = ion_dma_buf_begin_cpu_access,
 	.end_cpu_access = ion_dma_buf_end_cpu_access,
-	.map_atomic = ion_dma_buf_kmap,
-	.unmap_atomic = ion_dma_buf_kunmap,
 	.map = ion_dma_buf_kmap,
 	.unmap = ion_dma_buf_kunmap,
 };
diff --git a/drivers/staging/media/bcm2048/radio-bcm2048.c b/drivers/staging/media/bcm2048/radio-bcm2048.c
index 06d1920150da..a90b2eb112f9 100644
--- a/drivers/staging/media/bcm2048/radio-bcm2048.c
+++ b/drivers/staging/media/bcm2048/radio-bcm2048.c
@@ -2175,7 +2175,7 @@ static int bcm2048_fops_release(struct file *file)
 }
 
 static __poll_t bcm2048_fops_poll(struct file *file,
-				      struct poll_table_struct *pts)
+				  struct poll_table_struct *pts)
 {
 	struct bcm2048_device *bdev = video_drvdata(file);
 	__poll_t retval = 0;
diff --git a/drivers/staging/media/davinci_vpfe/vpfe_video.c b/drivers/staging/media/davinci_vpfe/vpfe_video.c
index 390fc98d07dd..1269a983455e 100644
--- a/drivers/staging/media/davinci_vpfe/vpfe_video.c
+++ b/drivers/staging/media/davinci_vpfe/vpfe_video.c
@@ -1312,6 +1312,8 @@ static const struct vb2_ops video_qops = {
 	.stop_streaming		= vpfe_stop_streaming,
 	.buf_cleanup		= vpfe_buf_cleanup,
 	.buf_queue		= vpfe_buffer_queue,
+	.wait_prepare		= vb2_ops_wait_prepare,
+	.wait_finish		= vb2_ops_wait_finish,
 };
 
 /*
@@ -1357,6 +1359,7 @@ static int vpfe_reqbufs(struct file *file, void *priv,
 	q->buf_struct_size = sizeof(struct vpfe_cap_buffer);
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->dev = vpfe_dev->pdev;
+	q->lock = &video->lock;
 
 	ret = vb2_queue_init(q);
 	if (ret) {
@@ -1598,17 +1601,18 @@ int vpfe_video_init(struct vpfe_video_device *video, const char *name)
 		return -EINVAL;
 	}
 	/* Initialize field of video device */
+	mutex_init(&video->lock);
 	video->video_dev.release = video_device_release;
 	video->video_dev.fops = &vpfe_fops;
 	video->video_dev.ioctl_ops = &vpfe_ioctl_ops;
 	video->video_dev.minor = -1;
 	video->video_dev.tvnorms = 0;
+	video->video_dev.lock = &video->lock;
 	snprintf(video->video_dev.name, sizeof(video->video_dev.name),
 		 "DAVINCI VIDEO %s %s", name, direction);
 
 	spin_lock_init(&video->irqlock);
 	spin_lock_init(&video->dma_queue_lock);
-	mutex_init(&video->lock);
 	ret = media_entity_pads_init(&video->video_dev.entity,
 				1, &video->pad);
 	if (ret < 0)
diff --git a/drivers/staging/media/davinci_vpfe/vpfe_video.h b/drivers/staging/media/davinci_vpfe/vpfe_video.h
index 22136d3dadcb..4bbd219e8329 100644
--- a/drivers/staging/media/davinci_vpfe/vpfe_video.h
+++ b/drivers/staging/media/davinci_vpfe/vpfe_video.h
@@ -128,7 +128,7 @@ struct vpfe_video_device {
 	spinlock_t				irqlock;
 	/* IRQ lock for DMA queue */
 	spinlock_t				dma_queue_lock;
-	/* lock used to access this structure */
+	/* lock used to serialize all video4linux ioctls */
 	struct mutex				lock;
 	/* number of users performing IO */
 	u32					io_usrs;
diff --git a/drivers/staging/media/imx/imx-ic-prpencvf.c b/drivers/staging/media/imx/imx-ic-prpencvf.c
index ae453fd422f0..28f41caba05d 100644
--- a/drivers/staging/media/imx/imx-ic-prpencvf.c
+++ b/drivers/staging/media/imx/imx-ic-prpencvf.c
@@ -103,6 +103,7 @@ struct prp_priv {
 	int nfb4eof_irq;
 
 	int stream_count;
+	u32 frame_sequence; /* frame sequence counter */
 	bool last_eof;  /* waiting for last EOF at stream off */
 	bool nfb4eof;    /* NFB4EOF encountered during streaming */
 	struct completion last_eof_comp;
@@ -210,12 +211,15 @@ static void prp_vb2_buf_done(struct prp_priv *priv, struct ipuv3_channel *ch)
 
 	done = priv->active_vb2_buf[priv->ipu_buf_num];
 	if (done) {
+		done->vbuf.field = vdev->fmt.fmt.pix.field;
+		done->vbuf.sequence = priv->frame_sequence;
 		vb = &done->vbuf.vb2_buf;
 		vb->timestamp = ktime_get_ns();
 		vb2_buffer_done(vb, priv->nfb4eof ?
 				VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);
 	}
 
+	priv->frame_sequence++;
 	priv->nfb4eof = false;
 
 	/* get next queued buffer */
@@ -637,6 +641,7 @@ static int prp_start(struct prp_priv *priv)
 
 	/* init EOF completion waitq */
 	init_completion(&priv->last_eof_comp);
+	priv->frame_sequence = 0;
 	priv->last_eof = false;
 	priv->nfb4eof = false;
 
diff --git a/drivers/staging/media/imx/imx-media-capture.c b/drivers/staging/media/imx/imx-media-capture.c
index 4e3fdf8aeef5..256039ce561e 100644
--- a/drivers/staging/media/imx/imx-media-capture.c
+++ b/drivers/staging/media/imx/imx-media-capture.c
@@ -170,23 +170,22 @@ static int capture_enum_fmt_vid_cap(struct file *file, void *fh,
 	}
 
 	cc_src = imx_media_find_ipu_format(fmt_src.format.code, CS_SEL_ANY);
-	if (!cc_src)
-		cc_src = imx_media_find_mbus_format(fmt_src.format.code,
-						    CS_SEL_ANY, true);
-	if (!cc_src)
-		return -EINVAL;
-
-	if (cc_src->bayer) {
-		if (f->index != 0)
-			return -EINVAL;
-		fourcc = cc_src->fourcc;
-	} else {
+	if (cc_src) {
 		u32 cs_sel = (cc_src->cs == IPUV3_COLORSPACE_YUV) ?
 			CS_SEL_YUV : CS_SEL_RGB;
 
 		ret = imx_media_enum_format(&fourcc, f->index, cs_sel);
 		if (ret)
 			return ret;
+	} else {
+		cc_src = imx_media_find_mbus_format(fmt_src.format.code,
+						    CS_SEL_ANY, true);
+		if (WARN_ON(!cc_src))
+			return -EINVAL;
+
+		if (f->index != 0)
+			return -EINVAL;
+		fourcc = cc_src->fourcc;
 	}
 
 	f->pixelformat = fourcc;
@@ -219,15 +218,7 @@ static int capture_try_fmt_vid_cap(struct file *file, void *fh,
 		return ret;
 
 	cc_src = imx_media_find_ipu_format(fmt_src.format.code, CS_SEL_ANY);
-	if (!cc_src)
-		cc_src = imx_media_find_mbus_format(fmt_src.format.code,
-						    CS_SEL_ANY, true);
-	if (!cc_src)
-		return -EINVAL;
-
-	if (cc_src->bayer) {
-		cc = cc_src;
-	} else {
+	if (cc_src) {
 		u32 fourcc, cs_sel;
 
 		cs_sel = (cc_src->cs == IPUV3_COLORSPACE_YUV) ?
@@ -239,6 +230,13 @@ static int capture_try_fmt_vid_cap(struct file *file, void *fh,
 			imx_media_enum_format(&fourcc, 0, cs_sel);
 			cc = imx_media_find_format(fourcc, cs_sel, false);
 		}
+	} else {
+		cc_src = imx_media_find_mbus_format(fmt_src.format.code,
+						    CS_SEL_ANY, true);
+		if (WARN_ON(!cc_src))
+			return -EINVAL;
+
+		cc = cc_src;
 	}
 
 	imx_media_mbus_fmt_to_pix_fmt(&f->fmt.pix, &fmt_src.format, cc);
diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c
index 95d7805f3485..cd2c291e1e94 100644
--- a/drivers/staging/media/imx/imx-media-csi.c
+++ b/drivers/staging/media/imx/imx-media-csi.c
@@ -111,6 +111,7 @@ struct csi_priv {
 	struct v4l2_ctrl_handler ctrl_hdlr;
 
 	int stream_count; /* streaming counter */
+	u32 frame_sequence; /* frame sequence counter */
 	bool last_eof;   /* waiting for last EOF at stream off */
 	bool nfb4eof;    /* NFB4EOF encountered during streaming */
 	struct completion last_eof_comp;
@@ -121,10 +122,32 @@ static inline struct csi_priv *sd_to_dev(struct v4l2_subdev *sdev)
 	return container_of(sdev, struct csi_priv, sd);
 }
 
+static inline bool is_parallel_bus(struct v4l2_fwnode_endpoint *ep)
+{
+	return ep->bus_type != V4L2_MBUS_CSI2;
+}
+
 static inline bool is_parallel_16bit_bus(struct v4l2_fwnode_endpoint *ep)
 {
-	return ep->bus_type != V4L2_MBUS_CSI2 &&
-		ep->bus.parallel.bus_width >= 16;
+	return is_parallel_bus(ep) && ep->bus.parallel.bus_width >= 16;
+}
+
+/*
+ * Check for conditions that require the IPU to handle the
+ * data internally as generic data, aka passthrough mode:
+ * - raw bayer media bus formats, or
+ * - the CSI is receiving from a 16-bit parallel bus, or
+ * - the CSI is receiving from an 8-bit parallel bus and the incoming
+ *   media bus format is other than UYVY8_2X8/YUYV8_2X8.
+ */
+static inline bool requires_passthrough(struct v4l2_fwnode_endpoint *ep,
+					struct v4l2_mbus_framefmt *infmt,
+					const struct imx_media_pixfmt *incc)
+{
+	return incc->bayer || is_parallel_16bit_bus(ep) ||
+		(is_parallel_bus(ep) &&
+		 infmt->code != MEDIA_BUS_FMT_UYVY8_2X8 &&
+		 infmt->code != MEDIA_BUS_FMT_YUYV8_2X8);
 }
 
 /*
@@ -236,12 +259,15 @@ static void csi_vb2_buf_done(struct csi_priv *priv)
 
 	done = priv->active_vb2_buf[priv->ipu_buf_num];
 	if (done) {
+		done->vbuf.field = vdev->fmt.fmt.pix.field;
+		done->vbuf.sequence = priv->frame_sequence;
 		vb = &done->vbuf.vb2_buf;
 		vb->timestamp = ktime_get_ns();
 		vb2_buffer_done(vb, priv->nfb4eof ?
 				VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);
 	}
 
+	priv->frame_sequence++;
 	priv->nfb4eof = false;
 
 	/* get next queued buffer */
@@ -367,15 +393,18 @@ static void csi_idmac_unsetup_vb2_buf(struct csi_priv *priv,
 static int csi_idmac_setup_channel(struct csi_priv *priv)
 {
 	struct imx_media_video_dev *vdev = priv->vdev;
+	const struct imx_media_pixfmt *incc;
 	struct v4l2_mbus_framefmt *infmt;
 	struct ipu_image image;
 	u32 passthrough_bits;
+	u32 passthrough_cycles;
 	dma_addr_t phys[2];
 	bool passthrough;
 	u32 burst_size;
 	int ret;
 
 	infmt = &priv->format_mbus[CSI_SINK_PAD];
+	incc = priv->cc[CSI_SINK_PAD];
 
 	ipu_cpmem_zero(priv->idmac_ch);
 
@@ -389,12 +418,9 @@ static int csi_idmac_setup_channel(struct csi_priv *priv)
 	image.phys0 = phys[0];
 	image.phys1 = phys[1];
 
-	/*
-	 * Check for conditions that require the IPU to handle the
-	 * data internally as generic data, aka passthrough mode:
-	 * - raw bayer formats
-	 * - the CSI is receiving from a 16-bit parallel bus
-	 */
+	passthrough = requires_passthrough(&priv->upstream_ep, infmt, incc);
+	passthrough_cycles = 1;
+
 	switch (image.pix.pixelformat) {
 	case V4L2_PIX_FMT_SBGGR8:
 	case V4L2_PIX_FMT_SGBRG8:
@@ -402,7 +428,6 @@ static int csi_idmac_setup_channel(struct csi_priv *priv)
 	case V4L2_PIX_FMT_SRGGB8:
 	case V4L2_PIX_FMT_GREY:
 		burst_size = 16;
-		passthrough = true;
 		passthrough_bits = 8;
 		break;
 	case V4L2_PIX_FMT_SBGGR16:
@@ -411,7 +436,6 @@ static int csi_idmac_setup_channel(struct csi_priv *priv)
 	case V4L2_PIX_FMT_SRGGB16:
 	case V4L2_PIX_FMT_Y16:
 		burst_size = 8;
-		passthrough = true;
 		passthrough_bits = 16;
 		break;
 	case V4L2_PIX_FMT_YUV420:
@@ -419,7 +443,6 @@ static int csi_idmac_setup_channel(struct csi_priv *priv)
 		burst_size = (image.pix.width & 0x3f) ?
 			     ((image.pix.width & 0x1f) ?
 			      ((image.pix.width & 0xf) ? 8 : 16) : 32) : 64;
-		passthrough = is_parallel_16bit_bus(&priv->upstream_ep);
 		passthrough_bits = 16;
 		/* Skip writing U and V components to odd rows */
 		ipu_cpmem_skip_odd_chroma_rows(priv->idmac_ch);
@@ -428,18 +451,25 @@ static int csi_idmac_setup_channel(struct csi_priv *priv)
 	case V4L2_PIX_FMT_UYVY:
 		burst_size = (image.pix.width & 0x1f) ?
 			     ((image.pix.width & 0xf) ? 8 : 16) : 32;
-		passthrough = is_parallel_16bit_bus(&priv->upstream_ep);
 		passthrough_bits = 16;
 		break;
+	case V4L2_PIX_FMT_RGB565:
+		if (passthrough) {
+			burst_size = 16;
+			passthrough_bits = 8;
+			passthrough_cycles = incc->cycles;
+			break;
+		}
+		/* fallthrough - non-passthrough RGB565 (CSI-2 bus) */
 	default:
 		burst_size = (image.pix.width & 0xf) ? 8 : 16;
-		passthrough = is_parallel_16bit_bus(&priv->upstream_ep);
 		passthrough_bits = 16;
 		break;
 	}
 
 	if (passthrough) {
-		ipu_cpmem_set_resolution(priv->idmac_ch, image.rect.width,
+		ipu_cpmem_set_resolution(priv->idmac_ch,
+					 image.rect.width * passthrough_cycles,
 					 image.rect.height);
 		ipu_cpmem_set_stride(priv->idmac_ch, image.pix.bytesperline);
 		ipu_cpmem_set_buffer(priv->idmac_ch, 0, image.phys0);
@@ -545,6 +575,7 @@ static int csi_idmac_start(struct csi_priv *priv)
 
 	/* init EOF completion waitq */
 	init_completion(&priv->last_eof_comp);
+	priv->frame_sequence = 0;
 	priv->last_eof = false;
 	priv->nfb4eof = false;
 
@@ -630,17 +661,20 @@ static void csi_idmac_stop(struct csi_priv *priv)
 static int csi_setup(struct csi_priv *priv)
 {
 	struct v4l2_mbus_framefmt *infmt, *outfmt;
+	const struct imx_media_pixfmt *incc;
 	struct v4l2_mbus_config mbus_cfg;
 	struct v4l2_mbus_framefmt if_fmt;
+	struct v4l2_rect crop;
 
 	infmt = &priv->format_mbus[CSI_SINK_PAD];
+	incc = priv->cc[CSI_SINK_PAD];
 	outfmt = &priv->format_mbus[priv->active_output_pad];
 
 	/* compose mbus_config from the upstream endpoint */
 	mbus_cfg.type = priv->upstream_ep.bus_type;
-	mbus_cfg.flags = (priv->upstream_ep.bus_type == V4L2_MBUS_CSI2) ?
-		priv->upstream_ep.bus.mipi_csi2.flags :
-		priv->upstream_ep.bus.parallel.flags;
+	mbus_cfg.flags = is_parallel_bus(&priv->upstream_ep) ?
+		priv->upstream_ep.bus.parallel.flags :
+		priv->upstream_ep.bus.mipi_csi2.flags;
 
 	/*
 	 * we need to pass input frame to CSI interface, but
@@ -648,8 +682,18 @@ static int csi_setup(struct csi_priv *priv)
 	 */
 	if_fmt = *infmt;
 	if_fmt.field = outfmt->field;
+	crop = priv->crop;
 
-	ipu_csi_set_window(priv->csi, &priv->crop);
+	/*
+	 * if cycles is set, we need to handle this over multiple cycles as
+	 * generic/bayer data
+	 */
+	if (is_parallel_bus(&priv->upstream_ep) && incc->cycles) {
+		if_fmt.width *= incc->cycles;
+		crop.width *= incc->cycles;
+	}
+
+	ipu_csi_set_window(priv->csi, &crop);
 
 	ipu_csi_set_downsize(priv->csi,
 			     priv->crop.width == 2 * priv->compose.width,
@@ -1007,7 +1051,6 @@ static int csi_link_validate(struct v4l2_subdev *sd,
 {
 	struct csi_priv *priv = v4l2_get_subdevdata(sd);
 	struct v4l2_fwnode_endpoint upstream_ep = {};
-	const struct imx_media_pixfmt *incc;
 	bool is_csi2;
 	int ret;
 
@@ -1025,17 +1068,7 @@ static int csi_link_validate(struct v4l2_subdev *sd,
 	mutex_lock(&priv->lock);
 
 	priv->upstream_ep = upstream_ep;
-	is_csi2 = (upstream_ep.bus_type == V4L2_MBUS_CSI2);
-	incc = priv->cc[CSI_SINK_PAD];
-
-	if (priv->dest != IPU_CSI_DEST_IDMAC &&
-	    (incc->bayer || is_parallel_16bit_bus(&upstream_ep))) {
-		v4l2_err(&priv->sd,
-			 "bayer/16-bit parallel buses must go to IDMAC pad\n");
-		ret = -EINVAL;
-		goto out;
-	}
-
+	is_csi2 = !is_parallel_bus(&upstream_ep);
 	if (is_csi2) {
 		int vc_num = 0;
 		/*
@@ -1059,7 +1092,7 @@ static int csi_link_validate(struct v4l2_subdev *sd,
 
 	/* select either parallel or MIPI-CSI2 as input to CSI */
 	ipu_set_csi_src_mux(priv->ipu, priv->csi_id, is_csi2);
-out:
+
 	mutex_unlock(&priv->lock);
 	return ret;
 }
@@ -1131,6 +1164,7 @@ static int csi_enum_mbus_code(struct v4l2_subdev *sd,
 			      struct v4l2_subdev_mbus_code_enum *code)
 {
 	struct csi_priv *priv = v4l2_get_subdevdata(sd);
+	struct v4l2_fwnode_endpoint upstream_ep;
 	const struct imx_media_pixfmt *incc;
 	struct v4l2_mbus_framefmt *infmt;
 	int ret = 0;
@@ -1147,7 +1181,13 @@ static int csi_enum_mbus_code(struct v4l2_subdev *sd,
 		break;
 	case CSI_SRC_PAD_DIRECT:
 	case CSI_SRC_PAD_IDMAC:
-		if (incc->bayer) {
+		ret = csi_get_upstream_endpoint(priv, &upstream_ep);
+		if (ret) {
+			v4l2_err(&priv->sd, "failed to find upstream endpoint\n");
+			goto out;
+		}
+
+		if (requires_passthrough(&upstream_ep, infmt, incc)) {
 			if (code->index != 0) {
 				ret = -EINVAL;
 				goto out;
@@ -1192,10 +1232,12 @@ static int csi_enum_frame_size(struct v4l2_subdev *sd,
 	} else {
 		crop = __csi_get_crop(priv, cfg, fse->which);
 
-		fse->min_width = fse->max_width = fse->index & 1 ?
+		fse->min_width = fse->index & 1 ?
 			crop->width / 2 : crop->width;
-		fse->min_height = fse->max_height = fse->index & 2 ?
+		fse->max_width = fse->min_width;
+		fse->min_height = fse->index & 2 ?
 			crop->height / 2 : crop->height;
+		fse->max_height = fse->min_height;
 	}
 
 	mutex_unlock(&priv->lock);
@@ -1286,7 +1328,7 @@ static void csi_try_fmt(struct csi_priv *priv,
 		sdformat->format.width = compose->width;
 		sdformat->format.height = compose->height;
 
-		if (incc->bayer) {
+		if (requires_passthrough(upstream_ep, infmt, incc)) {
 			sdformat->format.code = infmt->code;
 			*cc = incc;
 		} else {
diff --git a/drivers/staging/media/imx/imx-media-utils.c b/drivers/staging/media/imx/imx-media-utils.c
index 7ec2db84451c..8aa13403b09d 100644
--- a/drivers/staging/media/imx/imx-media-utils.c
+++ b/drivers/staging/media/imx/imx-media-utils.c
@@ -78,6 +78,7 @@ static const struct imx_media_pixfmt rgb_formats[] = {
 		.codes  = {MEDIA_BUS_FMT_RGB565_2X8_LE},
 		.cs     = IPUV3_COLORSPACE_RGB,
 		.bpp    = 16,
+		.cycles = 2,
 	}, {
 		.fourcc	= V4L2_PIX_FMT_RGB24,
 		.codes  = {
diff --git a/drivers/staging/media/imx/imx-media.h b/drivers/staging/media/imx/imx-media.h
index e945e0ed6dd6..57bd094cf765 100644
--- a/drivers/staging/media/imx/imx-media.h
+++ b/drivers/staging/media/imx/imx-media.h
@@ -62,6 +62,8 @@ struct imx_media_pixfmt {
 	u32     fourcc;
 	u32     codes[4];
 	int     bpp;     /* total bpp */
+	/* cycles per pixel for generic (bayer) formats for the parallel bus */
+	int	cycles;
 	enum ipu_color_space cs;
 	bool    planar;  /* is a planar format */
 	bool    bayer;   /* is a raw bayer format */
diff --git a/drivers/staging/most/sound/sound.c b/drivers/staging/most/sound/sound.c
index 04c18323c2ea..89b02fc305b8 100644
--- a/drivers/staging/most/sound/sound.c
+++ b/drivers/staging/most/sound/sound.c
@@ -457,7 +457,6 @@ static const struct snd_pcm_ops pcm_ops = {
 	.trigger    = pcm_trigger,
 	.pointer    = pcm_pointer,
 	.page       = snd_pcm_lib_get_vmalloc_page,
-	.mmap       = snd_pcm_lib_mmap_vmalloc,
 };
 
 static int split_arg_list(char *buf, char **card_name, u16 *ch_num,
diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c
index e461168313bf..4e6611e4c59b 100644
--- a/drivers/staging/netlogic/xlr_net.c
+++ b/drivers/staging/netlogic/xlr_net.c
@@ -290,13 +290,6 @@ static netdev_tx_t xlr_net_start_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 }
 
-static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb,
-				void *accel_priv,
-				select_queue_fallback_t fallback)
-{
-	return (u16)smp_processor_id();
-}
-
 static void xlr_hw_set_mac_addr(struct net_device *ndev)
 {
 	struct xlr_net_priv *priv = netdev_priv(ndev);
@@ -403,7 +396,7 @@ static const struct net_device_ops xlr_netdev_ops = {
 	.ndo_open = xlr_net_open,
 	.ndo_stop = xlr_net_stop,
 	.ndo_start_xmit = xlr_net_start_xmit,
-	.ndo_select_queue = xlr_net_select_queue,
+	.ndo_select_queue = dev_pick_tx_cpu_id,
 	.ndo_set_mac_address = xlr_net_set_mac_addr,
 	.ndo_set_rx_mode = xlr_set_rx_mode,
 	.ndo_get_stats64 = xlr_stats,
diff --git a/drivers/staging/rtl8188eu/include/wifi.h b/drivers/staging/rtl8188eu/include/wifi.h
index 084a246eec19..6790b7c8cfb1 100644
--- a/drivers/staging/rtl8188eu/include/wifi.h
+++ b/drivers/staging/rtl8188eu/include/wifi.h
@@ -575,7 +575,6 @@ enum ht_cap_ampdu_factor {
  * According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2)
  */
 #define IEEE80211_MIN_AMPDU_BUF 0x8
-#define IEEE80211_MAX_AMPDU_BUF 0x40
 
 
 #define OP_MODE_PURE                    0
diff --git a/drivers/staging/rtl8188eu/os_dep/os_intfs.c b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
index add1ba00f3e9..38e85c8a85c8 100644
--- a/drivers/staging/rtl8188eu/os_dep/os_intfs.c
+++ b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
@@ -253,7 +253,8 @@ static unsigned int rtw_classify8021d(struct sk_buff *skb)
 }
 
 static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    void *accel_priv, select_queue_fallback_t fallback)
+			    struct net_device *sb_dev,
+			    select_queue_fallback_t fallback)
 {
 	struct adapter	*padapter = rtw_netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
diff --git a/drivers/staging/rtl8712/rtl871x_security.c b/drivers/staging/rtl8712/rtl871x_security.c
index 7bc74d7d8a3a..1075eacdb441 100644
--- a/drivers/staging/rtl8712/rtl871x_security.c
+++ b/drivers/staging/rtl8712/rtl871x_security.c
@@ -40,6 +40,7 @@
 #include <linux/uaccess.h>
 #include <asm/byteorder.h>
 #include <linux/atomic.h>
+#include <linux/crc32poly.h>
 #include <linux/semaphore.h>
 
 #include "osdep_service.h"
@@ -49,8 +50,6 @@
 
 /* =====WEP related===== */
 
-#define CRC32_POLY 0x04c11db7
-
 struct arc4context {
 	u32 x;
 	u32 y;
@@ -135,7 +134,7 @@ static void crc32_init(void)
 	for (i = 0; i < 256; ++i) {
 		k = crc32_reverseBit((u8)i);
 		for (c = ((u32)k) << 24, j = 8; j > 0; --j)
-			c = c & 0x80000000 ? (c << 1) ^ CRC32_POLY : (c << 1);
+			c = c & 0x80000000 ? (c << 1) ^ CRC32_POLY_BE : (c << 1);
 		p1 = (u8 *)&crc32_table[i];
 		p1[0] = crc32_reverseBit(p[3]);
 		p1[1] = crc32_reverseBit(p[2]);
diff --git a/drivers/staging/rtl8712/wifi.h b/drivers/staging/rtl8712/wifi.h
index 0ed2f44ab4e9..00a4302e9983 100644
--- a/drivers/staging/rtl8712/wifi.h
+++ b/drivers/staging/rtl8712/wifi.h
@@ -574,7 +574,6 @@ struct ieee80211_ht_addt_info {
  * According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2)
  */
 #define IEEE80211_MIN_AMPDU_BUF 0x8
-#define IEEE80211_MAX_AMPDU_BUF 0x40
 
 
 /* Spatial Multiplexing Power Save Modes */
diff --git a/drivers/staging/rtl8723bs/core/rtw_security.c b/drivers/staging/rtl8723bs/core/rtw_security.c
index 612277a555d2..6c8ac9e86c9f 100644
--- a/drivers/staging/rtl8723bs/core/rtw_security.c
+++ b/drivers/staging/rtl8723bs/core/rtw_security.c
@@ -6,6 +6,7 @@
  ******************************************************************************/
 #define  _RTW_SECURITY_C_
 
+#include <linux/crc32poly.h>
 #include <drv_types.h>
 #include <rtw_debug.h>
 
@@ -87,8 +88,6 @@ const char *security_type_str(u8 value)
 
 /* WEP related ===== */
 
-#define CRC32_POLY 0x04c11db7
-
 struct arc4context {
 	u32 x;
 	u32 y;
@@ -178,7 +177,7 @@ static void crc32_init(void)
 		for (i = 0; i < 256; ++i) {
 			k = crc32_reverseBit((u8)i);
 			for (c = ((u32)k) << 24, j = 8; j > 0; --j) {
-				c = c & 0x80000000 ? (c << 1) ^ CRC32_POLY : (c << 1);
+				c = c & 0x80000000 ? (c << 1) ^ CRC32_POLY_BE : (c << 1);
 			}
 			p1 = (u8 *)&crc32_table[i];
 
diff --git a/drivers/staging/rtl8723bs/include/wifi.h b/drivers/staging/rtl8723bs/include/wifi.h
index 08bc79840b23..559bf2606fb7 100644
--- a/drivers/staging/rtl8723bs/include/wifi.h
+++ b/drivers/staging/rtl8723bs/include/wifi.h
@@ -799,7 +799,6 @@ enum HT_CAP_AMPDU_FACTOR {
  * According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2)
  */
 #define IEEE80211_MIN_AMPDU_BUF 0x8
-#define IEEE80211_MAX_AMPDU_BUF 0x40
 
 
 /* Spatial Multiplexing Power Save Modes */
diff --git a/drivers/staging/rtl8723bs/os_dep/os_intfs.c b/drivers/staging/rtl8723bs/os_dep/os_intfs.c
index ace68f023b49..181642358e3f 100644
--- a/drivers/staging/rtl8723bs/os_dep/os_intfs.c
+++ b/drivers/staging/rtl8723bs/os_dep/os_intfs.c
@@ -403,10 +403,9 @@ static unsigned int rtw_classify8021d(struct sk_buff *skb)
 }
 
 
-static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb
-				, void *accel_priv
-				, select_queue_fallback_t fallback
-)
+static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb,
+			    struct net_device *sb_dev,
+			    select_queue_fallback_t fallback)
 {
 	struct adapter	*padapter = rtw_netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
diff --git a/drivers/staging/rtlwifi/base.c b/drivers/staging/rtlwifi/base.c
index e46e47d93d7d..094827c1879a 100644
--- a/drivers/staging/rtlwifi/base.c
+++ b/drivers/staging/rtlwifi/base.c
@@ -1838,7 +1838,7 @@ void rtl_rx_ampdu_apply(struct rtl_priv *rtlpriv)
 		 reject_agg, ctrl_agg_size, agg_size);
 
 	rtlpriv->hw->max_rx_aggregation_subframes =
-		(ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF);
+		(ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF_HT);
 }
 
 /*********************************************************
diff --git a/drivers/staging/skein/skein_generic.c b/drivers/staging/skein/skein_generic.c
index 11f5e530a75f..c31fc6408383 100644
--- a/drivers/staging/skein/skein_generic.c
+++ b/drivers/staging/skein/skein_generic.c
@@ -137,7 +137,6 @@ static struct shash_alg alg256 = {
 	.base		=	{
 		.cra_name		=	"skein256",
 		.cra_driver_name	=	"skein",
-		.cra_flags		=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		=	SKEIN_256_BLOCK_BYTES,
 		.cra_module		=	THIS_MODULE,
 	}
@@ -155,7 +154,6 @@ static struct shash_alg alg512 = {
 	.base		=	{
 		.cra_name		=	"skein512",
 		.cra_driver_name	=	"skein",
-		.cra_flags		=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		=	SKEIN_512_BLOCK_BYTES,
 		.cra_module		=	THIS_MODULE,
 	}
@@ -173,7 +171,6 @@ static struct shash_alg alg1024 = {
 	.base		=	{
 		.cra_name		=	"skein1024",
 		.cra_driver_name	=	"skein",
-		.cra_flags		=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		=	SKEIN_1024_BLOCK_BYTES,
 		.cra_module		=	THIS_MODULE,
 	}
diff --git a/drivers/staging/vboxvideo/vbox_mode.c b/drivers/staging/vboxvideo/vbox_mode.c
index 5c7ea237893e..da4a93df8d75 100644
--- a/drivers/staging/vboxvideo/vbox_mode.c
+++ b/drivers/staging/vboxvideo/vbox_mode.c
@@ -504,7 +504,7 @@ static void vbox_set_edid(struct drm_connector *connector, int width,
 	for (i = 0; i < EDID_SIZE - 1; ++i)
 		sum += edid[i];
 	edid[EDID_SIZE - 1] = (0x100 - (sum & 0xFF)) & 0xFF;
-	drm_mode_connector_update_edid_property(connector, (struct edid *)edid);
+	drm_connector_update_edid_property(connector, (struct edid *)edid);
 }
 
 static int vbox_get_modes(struct drm_connector *connector)
@@ -655,7 +655,7 @@ static int vbox_connector_init(struct drm_device *dev,
 				   dev->mode_config.suggested_y_property, 0);
 	drm_connector_register(connector);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c b/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c
index ce26741ae9d9..6dd0c838db05 100644
--- a/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c
+++ b/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c
@@ -628,20 +628,6 @@ static void stop_streaming(struct vb2_queue *vq)
 		v4l2_err(&dev->v4l2_dev, "Failed to disable camera\n");
 }
 
-static void bm2835_mmal_lock(struct vb2_queue *vq)
-{
-	struct bm2835_mmal_dev *dev = vb2_get_drv_priv(vq);
-
-	mutex_lock(&dev->mutex);
-}
-
-static void bm2835_mmal_unlock(struct vb2_queue *vq)
-{
-	struct bm2835_mmal_dev *dev = vb2_get_drv_priv(vq);
-
-	mutex_unlock(&dev->mutex);
-}
-
 static const struct vb2_ops bm2835_mmal_video_qops = {
 	.queue_setup = queue_setup,
 	.buf_init = buffer_init,
@@ -650,8 +636,8 @@ static const struct vb2_ops bm2835_mmal_video_qops = {
 	.buf_queue = buffer_queue,
 	.start_streaming = start_streaming,
 	.stop_streaming = stop_streaming,
-	.wait_prepare = bm2835_mmal_unlock,
-	.wait_finish = bm2835_mmal_lock,
+	.wait_prepare = vb2_ops_wait_prepare,
+	.wait_finish = vb2_ops_wait_finish,
 };
 
 /* ------------------------------------------------------------------
@@ -1864,6 +1850,8 @@ static int bcm2835_mmal_probe(struct platform_device *pdev)
 			goto cleanup_gdev;
 		}
 
+		/* v4l2 core mutex used to protect all fops and v4l2 ioctls. */
+		mutex_init(&dev->mutex);
 		dev->camera_num = camera;
 		dev->max_width = resolutions[camera][0];
 		dev->max_height = resolutions[camera][1];
@@ -1908,13 +1896,11 @@ static int bcm2835_mmal_probe(struct platform_device *pdev)
 		q->ops = &bm2835_mmal_video_qops;
 		q->mem_ops = &vb2_vmalloc_memops;
 		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+		q->lock = &dev->mutex;
 		ret = vb2_queue_init(q);
 		if (ret < 0)
 			goto unreg_dev;
 
-		/* v4l2 core mutex used to protect all fops and v4l2 ioctls. */
-		mutex_init(&dev->mutex);
-
 		/* initialise video devices */
 		ret = bm2835_mmal_init_device(dev, &dev->vdev);
 		if (ret < 0)
diff --git a/drivers/target/Kconfig b/drivers/target/Kconfig
index 4c44d7bed01a..cb6f32ce7de8 100644
--- a/drivers/target/Kconfig
+++ b/drivers/target/Kconfig
@@ -1,10 +1,10 @@
 
 menuconfig TARGET_CORE
 	tristate "Generic Target Core Mod (TCM) and ConfigFS Infrastructure"
-	depends on SCSI && BLOCK
+	depends on BLOCK
 	select CONFIGFS_FS
 	select CRC_T10DIF
-	select BLK_SCSI_REQUEST # only for scsi_command_size_tbl..
+	select BLK_SCSI_REQUEST
 	select SGL_ALLOC
 	default n
 	help
@@ -29,6 +29,7 @@ config TCM_FILEIO
 
 config TCM_PSCSI
 	tristate "TCM/pSCSI Subsystem Plugin for Linux/SCSI"
+	depends on SCSI
 	help
 	Say Y here to enable the TCM/pSCSI subsystem plugin for non-buffered
 	passthrough access to Linux/SCSI device
diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index 0ebc4818e132..95d0a22b2ad6 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -1090,10 +1090,8 @@ static struct configfs_attribute *lio_target_tpg_attrs[] = {
 
 /* Start items for lio_target_tiqn_cit */
 
-static struct se_portal_group *lio_target_tiqn_addtpg(
-	struct se_wwn *wwn,
-	struct config_group *group,
-	const char *name)
+static struct se_portal_group *lio_target_tiqn_addtpg(struct se_wwn *wwn,
+						      const char *name)
 {
 	struct iscsi_portal_group *tpg;
 	struct iscsi_tiqn *tiqn;
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 99501785cdc1..923b1a9fc3dc 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -369,7 +369,7 @@ static int iscsi_login_zero_tsih_s1(
 		return -ENOMEM;
 	}
 
-	sess->se_sess = transport_init_session(TARGET_PROT_NORMAL);
+	sess->se_sess = transport_alloc_session(TARGET_PROT_NORMAL);
 	if (IS_ERR(sess->se_sess)) {
 		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
 				ISCSI_LOGIN_STATUS_NO_RESOURCES);
diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c
index 4b34f71547c6..101d62105c93 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.c
+++ b/drivers/target/iscsi/iscsi_target_tpg.c
@@ -636,8 +636,7 @@ int iscsit_ta_authentication(struct iscsi_portal_group *tpg, u32 authentication)
 		none = strstr(buf1, NONE);
 		if (none)
 			goto out;
-		strncat(buf1, ",", strlen(","));
-		strncat(buf1, NONE, strlen(NONE));
+		strlcat(buf1, "," NONE, sizeof(buf1));
 		if (iscsi_update_param_value(param, buf1) < 0)
 			return -EINVAL;
 	}
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 4435bf374d2d..49be1e41290c 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -17,7 +17,7 @@
  ******************************************************************************/
 
 #include <linux/list.h>
-#include <linux/percpu_ida.h>
+#include <linux/sched/signal.h>
 #include <net/ipv6.h>         /* ipv6_addr_equal() */
 #include <scsi/scsi_tcq.h>
 #include <scsi/iscsi_proto.h>
@@ -147,6 +147,30 @@ void iscsit_free_r2ts_from_list(struct iscsi_cmd *cmd)
 	spin_unlock_bh(&cmd->r2t_lock);
 }
 
+static int iscsit_wait_for_tag(struct se_session *se_sess, int state, int *cpup)
+{
+	int tag = -1;
+	DEFINE_WAIT(wait);
+	struct sbq_wait_state *ws;
+
+	if (state == TASK_RUNNING)
+		return tag;
+
+	ws = &se_sess->sess_tag_pool.ws[0];
+	for (;;) {
+		prepare_to_wait_exclusive(&ws->wait, &wait, state);
+		if (signal_pending_state(state, current))
+			break;
+		tag = sbitmap_queue_get(&se_sess->sess_tag_pool, cpup);
+		if (tag >= 0)
+			break;
+		schedule();
+	}
+
+	finish_wait(&ws->wait, &wait);
+	return tag;
+}
+
 /*
  * May be called from software interrupt (timer) context for allocating
  * iSCSI NopINs.
@@ -155,9 +179,11 @@ struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *conn, int state)
 {
 	struct iscsi_cmd *cmd;
 	struct se_session *se_sess = conn->sess->se_sess;
-	int size, tag;
+	int size, tag, cpu;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, state);
+	tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
+	if (tag < 0)
+		tag = iscsit_wait_for_tag(se_sess, state, &cpu);
 	if (tag < 0)
 		return NULL;
 
@@ -166,6 +192,7 @@ struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *conn, int state)
 	memset(cmd, 0, size);
 
 	cmd->se_cmd.map_tag = tag;
+	cmd->se_cmd.map_cpu = cpu;
 	cmd->conn = conn;
 	cmd->data_direction = DMA_NONE;
 	INIT_LIST_HEAD(&cmd->i_conn_node);
@@ -711,7 +738,7 @@ void iscsit_release_cmd(struct iscsi_cmd *cmd)
 	kfree(cmd->iov_data);
 	kfree(cmd->text_in_ptr);
 
-	percpu_ida_free(&sess->se_sess->sess_tag_pool, se_cmd->map_tag);
+	target_free_tag(sess->se_sess, se_cmd);
 }
 EXPORT_SYMBOL(iscsit_release_cmd);
 
@@ -1026,26 +1053,8 @@ void __iscsit_start_nopin_timer(struct iscsi_conn *conn)
 
 void iscsit_start_nopin_timer(struct iscsi_conn *conn)
 {
-	struct iscsi_session *sess = conn->sess;
-	struct iscsi_node_attrib *na = iscsit_tpg_get_node_attrib(sess);
-	/*
-	 * NOPIN timeout is disabled..
-	 */
-	if (!na->nopin_timeout)
-		return;
-
 	spin_lock_bh(&conn->nopin_timer_lock);
-	if (conn->nopin_timer_flags & ISCSI_TF_RUNNING) {
-		spin_unlock_bh(&conn->nopin_timer_lock);
-		return;
-	}
-
-	conn->nopin_timer_flags &= ~ISCSI_TF_STOP;
-	conn->nopin_timer_flags |= ISCSI_TF_RUNNING;
-	mod_timer(&conn->nopin_timer, jiffies + na->nopin_timeout * HZ);
-
-	pr_debug("Started NOPIN Timer on CID: %d at %u second"
-			" interval\n", conn->cid, na->nopin_timeout);
+	__iscsit_start_nopin_timer(conn);
 	spin_unlock_bh(&conn->nopin_timer_lock);
 }
 
diff --git a/drivers/target/loopback/Kconfig b/drivers/target/loopback/Kconfig
index abe8ecbcdf06..158ee9d522f7 100644
--- a/drivers/target/loopback/Kconfig
+++ b/drivers/target/loopback/Kconfig
@@ -1,5 +1,6 @@
 config LOOPBACK_TARGET
 	tristate "TCM Virtual SAS target and Linux/SCSI LDD fabric loopback module"
+	depends on SCSI
 	help
 	  Say Y here to enable the TCM Virtual SAS target and Linux/SCSI LLD
 	  fabric loopback module.
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 60d5b918c4ac..bc8918f382e4 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -239,10 +239,7 @@ out:
 	return ret;
 
 release:
-	if (se_cmd)
-		transport_generic_free_cmd(se_cmd, 0);
-	else
-		kmem_cache_free(tcm_loop_cmd_cache, tl_cmd);
+	kmem_cache_free(tcm_loop_cmd_cache, tl_cmd);
 	goto out;
 }
 
@@ -768,7 +765,7 @@ static int tcm_loop_make_nexus(
 	if (!tl_nexus)
 		return -ENOMEM;
 
-	tl_nexus->se_sess = target_alloc_session(&tl_tpg->tl_se_tpg, 0, 0,
+	tl_nexus->se_sess = target_setup_session(&tl_tpg->tl_se_tpg, 0, 0,
 					TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS,
 					name, tl_nexus, tcm_loop_alloc_sess_cb);
 	if (IS_ERR(tl_nexus->se_sess)) {
@@ -808,7 +805,7 @@ static int tcm_loop_drop_nexus(
 	/*
 	 * Release the SCSI I_T Nexus to the emulated Target Port
 	 */
-	transport_deregister_session(tl_nexus->se_sess);
+	target_remove_session(se_sess);
 	tpg->tl_nexus = NULL;
 	kfree(tl_nexus);
 	return 0;
@@ -983,10 +980,8 @@ static struct configfs_attribute *tcm_loop_tpg_attrs[] = {
 
 /* Start items for tcm_loop_naa_cit */
 
-static struct se_portal_group *tcm_loop_make_naa_tpg(
-	struct se_wwn *wwn,
-	struct config_group *group,
-	const char *name)
+static struct se_portal_group *tcm_loop_make_naa_tpg(struct se_wwn *wwn,
+						     const char *name)
 {
 	struct tcm_loop_hba *tl_hba = container_of(wwn,
 			struct tcm_loop_hba, tl_hba_wwn);
diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c
index fb1003921d85..3d10189ecedc 100644
--- a/drivers/target/sbp/sbp_target.c
+++ b/drivers/target/sbp/sbp_target.c
@@ -209,7 +209,7 @@ static struct sbp_session *sbp_session_create(
 	INIT_DELAYED_WORK(&sess->maint_work, session_maintenance_work);
 	sess->guid = guid;
 
-	sess->se_sess = target_alloc_session(&tpg->se_tpg, 128,
+	sess->se_sess = target_setup_session(&tpg->se_tpg, 128,
 					     sizeof(struct sbp_target_request),
 					     TARGET_PROT_NORMAL, guid_str,
 					     sess, NULL);
@@ -235,8 +235,7 @@ static void sbp_session_release(struct sbp_session *sess, bool cancel_work)
 	if (cancel_work)
 		cancel_delayed_work_sync(&sess->maint_work);
 
-	transport_deregister_session_configfs(sess->se_sess);
-	transport_deregister_session(sess->se_sess);
+	target_remove_session(sess->se_sess);
 
 	if (sess->card)
 		fw_card_put(sess->card);
@@ -926,15 +925,16 @@ static struct sbp_target_request *sbp_mgt_get_req(struct sbp_session *sess,
 {
 	struct se_session *se_sess = sess->se_sess;
 	struct sbp_target_request *req;
-	int tag;
+	int tag, cpu;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
+	tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
 	if (tag < 0)
 		return ERR_PTR(-ENOMEM);
 
 	req = &((struct sbp_target_request *)se_sess->sess_cmd_map)[tag];
 	memset(req, 0, sizeof(*req));
 	req->se_cmd.map_tag = tag;
+	req->se_cmd.map_cpu = cpu;
 	req->se_cmd.tag = next_orb;
 
 	return req;
@@ -1460,7 +1460,7 @@ static void sbp_free_request(struct sbp_target_request *req)
 	kfree(req->pg_tbl);
 	kfree(req->cmd_buf);
 
-	percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag);
+	target_free_tag(se_sess, se_cmd);
 }
 
 static void sbp_mgt_agent_process(struct work_struct *work)
@@ -2005,10 +2005,8 @@ static void sbp_pre_unlink_lun(
 		pr_err("unlink LUN: failed to update unit directory\n");
 }
 
-static struct se_portal_group *sbp_make_tpg(
-		struct se_wwn *wwn,
-		struct config_group *group,
-		const char *name)
+static struct se_portal_group *sbp_make_tpg(struct se_wwn *wwn,
+					    const char *name)
 {
 	struct sbp_tport *tport =
 		container_of(wwn, struct sbp_tport, tport_wwn);
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 5ccef7d597fa..f6b1549f4142 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -263,8 +263,8 @@ static struct config_group *target_core_register_fabric(
 			&tf->tf_discovery_cit);
 	configfs_add_default_group(&tf->tf_disc_group, &tf->tf_group);
 
-	pr_debug("Target_Core_ConfigFS: REGISTER -> Allocated Fabric:"
-			" %s\n", tf->tf_group.cg_item.ci_name);
+	pr_debug("Target_Core_ConfigFS: REGISTER -> Allocated Fabric: %s\n",
+		 config_item_name(&tf->tf_group.cg_item));
 	return &tf->tf_group;
 }
 
@@ -810,7 +810,7 @@ static ssize_t pi_prot_type_store(struct config_item *item,
 		       dev->transport->name);
 		return -ENOSYS;
 	}
-	if (!(dev->dev_flags & DF_CONFIGURED)) {
+	if (!target_dev_configured(dev)) {
 		pr_err("DIF protection requires device to be configured\n");
 		return -ENODEV;
 	}
@@ -859,7 +859,7 @@ static ssize_t pi_prot_format_store(struct config_item *item,
 		       dev->transport->name);
 		return -ENOSYS;
 	}
-	if (!(dev->dev_flags & DF_CONFIGURED)) {
+	if (!target_dev_configured(dev)) {
 		pr_err("DIF protection format requires device to be configured\n");
 		return -ENODEV;
 	}
@@ -1948,7 +1948,7 @@ static ssize_t target_dev_enable_show(struct config_item *item, char *page)
 {
 	struct se_device *dev = to_device(item);
 
-	return snprintf(page, PAGE_SIZE, "%d\n", !!(dev->dev_flags & DF_CONFIGURED));
+	return snprintf(page, PAGE_SIZE, "%d\n", target_dev_configured(dev));
 }
 
 static ssize_t target_dev_enable_store(struct config_item *item,
@@ -2473,7 +2473,7 @@ static ssize_t target_tg_pt_gp_alua_access_state_store(struct config_item *item,
 			" tg_pt_gp ID: %hu\n", tg_pt_gp->tg_pt_gp_valid_id);
 		return -EINVAL;
 	}
-	if (!(dev->dev_flags & DF_CONFIGURED)) {
+	if (!target_dev_configured(dev)) {
 		pr_err("Unable to set alua_access_state while device is"
 		       " not configured\n");
 		return -ENODEV;
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index e27db4d45a9d..47b5ef153135 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -336,7 +336,6 @@ int core_enable_device_list_for_node(
 		return -ENOMEM;
 	}
 
-	atomic_set(&new->ua_count, 0);
 	spin_lock_init(&new->ua_lock);
 	INIT_LIST_HEAD(&new->ua_list);
 	INIT_LIST_HEAD(&new->lun_link);
@@ -879,39 +878,21 @@ sector_t target_to_linux_sector(struct se_device *dev, sector_t lb)
 }
 EXPORT_SYMBOL(target_to_linux_sector);
 
-/**
- * target_find_device - find a se_device by its dev_index
- * @id: dev_index
- * @do_depend: true if caller needs target_depend_item to be done
- *
- * If do_depend is true, the caller must do a target_undepend_item
- * when finished using the device.
- *
- * If do_depend is false, the caller must be called in a configfs
- * callback or during removal.
- */
-struct se_device *target_find_device(int id, bool do_depend)
-{
-	struct se_device *dev;
-
-	mutex_lock(&device_mutex);
-	dev = idr_find(&devices_idr, id);
-	if (dev && do_depend && target_depend_item(&dev->dev_group.cg_item))
-		dev = NULL;
-	mutex_unlock(&device_mutex);
-	return dev;
-}
-EXPORT_SYMBOL(target_find_device);
-
 struct devices_idr_iter {
+	struct config_item *prev_item;
 	int (*fn)(struct se_device *dev, void *data);
 	void *data;
 };
 
 static int target_devices_idr_iter(int id, void *p, void *data)
+	 __must_hold(&device_mutex)
 {
 	struct devices_idr_iter *iter = data;
 	struct se_device *dev = p;
+	int ret;
+
+	config_item_put(iter->prev_item);
+	iter->prev_item = NULL;
 
 	/*
 	 * We add the device early to the idr, so it can be used
@@ -919,10 +900,18 @@ static int target_devices_idr_iter(int id, void *p, void *data)
 	 * to allow other callers to access partially setup devices,
 	 * so we skip them here.
 	 */
-	if (!(dev->dev_flags & DF_CONFIGURED))
+	if (!target_dev_configured(dev))
+		return 0;
+
+	iter->prev_item = config_item_get_unless_zero(&dev->dev_group.cg_item);
+	if (!iter->prev_item)
 		return 0;
+	mutex_unlock(&device_mutex);
+
+	ret = iter->fn(dev, iter->data);
 
-	return iter->fn(dev, iter->data);
+	mutex_lock(&device_mutex);
+	return ret;
 }
 
 /**
@@ -936,15 +925,13 @@ static int target_devices_idr_iter(int id, void *p, void *data)
 int target_for_each_device(int (*fn)(struct se_device *dev, void *data),
 			   void *data)
 {
-	struct devices_idr_iter iter;
+	struct devices_idr_iter iter = { .fn = fn, .data = data };
 	int ret;
 
-	iter.fn = fn;
-	iter.data = data;
-
 	mutex_lock(&device_mutex);
 	ret = idr_for_each(&devices_idr, target_devices_idr_iter, &iter);
 	mutex_unlock(&device_mutex);
+	config_item_put(iter.prev_item);
 	return ret;
 }
 
@@ -953,7 +940,7 @@ int target_configure_device(struct se_device *dev)
 	struct se_hba *hba = dev->se_hba;
 	int ret, id;
 
-	if (dev->dev_flags & DF_CONFIGURED) {
+	if (target_dev_configured(dev)) {
 		pr_err("se_dev->se_dev_ptr already set for storage"
 				" object\n");
 		return -EEXIST;
@@ -1058,7 +1045,7 @@ void target_free_device(struct se_device *dev)
 
 	WARN_ON(!list_empty(&dev->dev_sep_list));
 
-	if (dev->dev_flags & DF_CONFIGURED) {
+	if (target_dev_configured(dev)) {
 		destroy_workqueue(dev->tmr_wq);
 
 		dev->transport->destroy_device(dev);
diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c
index e1416b007aa4..aa2f4f632ebe 100644
--- a/drivers/target/target_core_fabric_configfs.c
+++ b/drivers/target/target_core_fabric_configfs.c
@@ -34,6 +34,7 @@
 #include <linux/configfs.h>
 
 #include <target/target_core_base.h>
+#include <target/target_core_backend.h>
 #include <target/target_core_fabric.h>
 
 #include "target_core_internal.h"
@@ -642,7 +643,7 @@ static int target_fabric_port_link(
 	}
 	dev = container_of(to_config_group(se_dev_ci), struct se_device, dev_group);
 
-	if (!(dev->dev_flags & DF_CONFIGURED)) {
+	if (!target_dev_configured(dev)) {
 		pr_err("se_device not configured yet, cannot port link\n");
 		return -ENODEV;
 	}
@@ -841,7 +842,7 @@ static struct config_group *target_fabric_make_tpg(
 		return ERR_PTR(-ENOSYS);
 	}
 
-	se_tpg = tf->tf_ops->fabric_make_tpg(wwn, group, name);
+	se_tpg = tf->tf_ops->fabric_make_tpg(wwn, name);
 	if (!se_tpg || IS_ERR(se_tpg))
 		return ERR_PTR(-EINVAL);
 
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index dead30b1d32c..0c6635587930 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -138,7 +138,7 @@ int	init_se_kmem_caches(void);
 void	release_se_kmem_caches(void);
 u32	scsi_get_new_index(scsi_index_t);
 void	transport_subsystem_check_init(void);
-int	transport_cmd_finish_abort(struct se_cmd *, int);
+int	transport_cmd_finish_abort(struct se_cmd *);
 unsigned char *transport_dump_cmd_direction(struct se_cmd *);
 void	transport_dump_dev_state(struct se_device *, char *, int *);
 void	transport_dump_dev_info(struct se_device *, struct se_lun *,
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index b054682e974f..ebac2b49b9c6 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -978,9 +978,10 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 	}
 	case COMPARE_AND_WRITE:
 		if (!dev->dev_attrib.emulate_caw) {
-			pr_err_ratelimited("se_device %s/%s (vpd_unit_serial %s) reject"
-				" COMPARE_AND_WRITE\n", dev->se_hba->backend->ops->name,
-				dev->dev_group.cg_item.ci_name, dev->t10_wwn.unit_serial);
+			pr_err_ratelimited("se_device %s/%s (vpd_unit_serial %s) reject COMPARE_AND_WRITE\n",
+					   dev->se_hba->backend->ops->name,
+					   config_item_name(&dev->dev_group.cg_item),
+					   dev->t10_wwn.unit_serial);
 			return TCM_UNSUPPORTED_SCSI_OPCODE;
 		}
 		sectors = cdb[13];
diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index 9c7bc1ca341a..6d1179a7f043 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -75,25 +75,6 @@ void core_tmr_release_req(struct se_tmr_req *tmr)
 	kfree(tmr);
 }
 
-static int core_tmr_handle_tas_abort(struct se_cmd *cmd, int tas)
-{
-	unsigned long flags;
-	bool remove = true, send_tas;
-	/*
-	 * TASK ABORTED status (TAS) bit support
-	 */
-	spin_lock_irqsave(&cmd->t_state_lock, flags);
-	send_tas = (cmd->transport_state & CMD_T_TAS);
-	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-
-	if (send_tas) {
-		remove = false;
-		transport_send_task_abort(cmd);
-	}
-
-	return transport_cmd_finish_abort(cmd, remove);
-}
-
 static int target_check_cdb_and_preempt(struct list_head *list,
 		struct se_cmd *cmd)
 {
@@ -142,7 +123,7 @@ static bool __target_check_io_state(struct se_cmd *se_cmd,
 			return false;
 		}
 	}
-	if (sess->sess_tearing_down || se_cmd->cmd_wait_set) {
+	if (sess->sess_tearing_down) {
 		pr_debug("Attempted to abort io tag: %llu already shutdown,"
 			" skipping\n", se_cmd->tag);
 		spin_unlock(&se_cmd->t_state_lock);
@@ -187,13 +168,12 @@ void core_tmr_abort_task(
 		if (!__target_check_io_state(se_cmd, se_sess, 0))
 			continue;
 
-		list_del_init(&se_cmd->se_cmd_list);
 		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 
 		cancel_work_sync(&se_cmd->work);
 		transport_wait_for_tasks(se_cmd);
 
-		if (!transport_cmd_finish_abort(se_cmd, true))
+		if (!transport_cmd_finish_abort(se_cmd))
 			target_put_sess_cmd(se_cmd);
 
 		printk("ABORT_TASK: Sending TMR_FUNCTION_COMPLETE for"
@@ -259,7 +239,7 @@ static void core_tmr_drain_tmr_list(
 			spin_unlock(&sess->sess_cmd_lock);
 			continue;
 		}
-		if (sess->sess_tearing_down || cmd->cmd_wait_set) {
+		if (sess->sess_tearing_down) {
 			spin_unlock(&cmd->t_state_lock);
 			spin_unlock(&sess->sess_cmd_lock);
 			continue;
@@ -291,7 +271,7 @@ static void core_tmr_drain_tmr_list(
 		cancel_work_sync(&cmd->work);
 		transport_wait_for_tasks(cmd);
 
-		if (!transport_cmd_finish_abort(cmd, 1))
+		if (!transport_cmd_finish_abort(cmd))
 			target_put_sess_cmd(cmd);
 	}
 }
@@ -380,7 +360,7 @@ static void core_tmr_drain_state_list(
 		cancel_work_sync(&cmd->work);
 		transport_wait_for_tasks(cmd);
 
-		if (!core_tmr_handle_tas_abort(cmd, tas))
+		if (!transport_cmd_finish_abort(cmd))
 			target_put_sess_cmd(cmd);
 	}
 }
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index ee5081ba5313..86c0156e6c88 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -64,7 +64,7 @@ struct kmem_cache *t10_alua_lba_map_cache;
 struct kmem_cache *t10_alua_lba_map_mem_cache;
 
 static void transport_complete_task_attr(struct se_cmd *cmd);
-static int translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason);
+static void translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason);
 static void transport_handle_queue_full(struct se_cmd *cmd,
 		struct se_device *dev, int err, bool write_pending);
 static void target_complete_ok_work(struct work_struct *work);
@@ -224,7 +224,27 @@ void transport_subsystem_check_init(void)
 	sub_api_initialized = 1;
 }
 
-struct se_session *transport_init_session(enum target_prot_op sup_prot_ops)
+/**
+ * transport_init_session - initialize a session object
+ * @se_sess: Session object pointer.
+ *
+ * The caller must have zero-initialized @se_sess before calling this function.
+ */
+void transport_init_session(struct se_session *se_sess)
+{
+	INIT_LIST_HEAD(&se_sess->sess_list);
+	INIT_LIST_HEAD(&se_sess->sess_acl_list);
+	INIT_LIST_HEAD(&se_sess->sess_cmd_list);
+	spin_lock_init(&se_sess->sess_cmd_lock);
+	init_waitqueue_head(&se_sess->cmd_list_wq);
+}
+EXPORT_SYMBOL(transport_init_session);
+
+/**
+ * transport_alloc_session - allocate a session object and initialize it
+ * @sup_prot_ops: bitmask that defines which T10-PI modes are supported.
+ */
+struct se_session *transport_alloc_session(enum target_prot_op sup_prot_ops)
 {
 	struct se_session *se_sess;
 
@@ -234,17 +254,20 @@ struct se_session *transport_init_session(enum target_prot_op sup_prot_ops)
 				" se_sess_cache\n");
 		return ERR_PTR(-ENOMEM);
 	}
-	INIT_LIST_HEAD(&se_sess->sess_list);
-	INIT_LIST_HEAD(&se_sess->sess_acl_list);
-	INIT_LIST_HEAD(&se_sess->sess_cmd_list);
-	INIT_LIST_HEAD(&se_sess->sess_wait_list);
-	spin_lock_init(&se_sess->sess_cmd_lock);
+	transport_init_session(se_sess);
 	se_sess->sup_prot_ops = sup_prot_ops;
 
 	return se_sess;
 }
-EXPORT_SYMBOL(transport_init_session);
+EXPORT_SYMBOL(transport_alloc_session);
 
+/**
+ * transport_alloc_session_tags - allocate target driver private data
+ * @se_sess:  Session pointer.
+ * @tag_num:  Maximum number of in-flight commands between initiator and target.
+ * @tag_size: Size in bytes of the private data a target driver associates with
+ *	      each command.
+ */
 int transport_alloc_session_tags(struct se_session *se_sess,
 			         unsigned int tag_num, unsigned int tag_size)
 {
@@ -260,7 +283,8 @@ int transport_alloc_session_tags(struct se_session *se_sess,
 		}
 	}
 
-	rc = percpu_ida_init(&se_sess->sess_tag_pool, tag_num);
+	rc = sbitmap_queue_init_node(&se_sess->sess_tag_pool, tag_num, -1,
+			false, GFP_KERNEL, NUMA_NO_NODE);
 	if (rc < 0) {
 		pr_err("Unable to init se_sess->sess_tag_pool,"
 			" tag_num: %u\n", tag_num);
@@ -273,9 +297,16 @@ int transport_alloc_session_tags(struct se_session *se_sess,
 }
 EXPORT_SYMBOL(transport_alloc_session_tags);
 
-struct se_session *transport_init_session_tags(unsigned int tag_num,
-					       unsigned int tag_size,
-					       enum target_prot_op sup_prot_ops)
+/**
+ * transport_init_session_tags - allocate a session and target driver private data
+ * @tag_num:  Maximum number of in-flight commands between initiator and target.
+ * @tag_size: Size in bytes of the private data a target driver associates with
+ *	      each command.
+ * @sup_prot_ops: bitmask that defines which T10-PI modes are supported.
+ */
+static struct se_session *
+transport_init_session_tags(unsigned int tag_num, unsigned int tag_size,
+			    enum target_prot_op sup_prot_ops)
 {
 	struct se_session *se_sess;
 	int rc;
@@ -291,7 +322,7 @@ struct se_session *transport_init_session_tags(unsigned int tag_num,
 		return ERR_PTR(-EINVAL);
 	}
 
-	se_sess = transport_init_session(sup_prot_ops);
+	se_sess = transport_alloc_session(sup_prot_ops);
 	if (IS_ERR(se_sess))
 		return se_sess;
 
@@ -303,7 +334,6 @@ struct se_session *transport_init_session_tags(unsigned int tag_num,
 
 	return se_sess;
 }
-EXPORT_SYMBOL(transport_init_session_tags);
 
 /*
  * Called with spin_lock_irqsave(&struct se_portal_group->session_lock called.
@@ -316,6 +346,7 @@ void __transport_register_session(
 {
 	const struct target_core_fabric_ops *tfo = se_tpg->se_tpg_tfo;
 	unsigned char buf[PR_REG_ISID_LEN];
+	unsigned long flags;
 
 	se_sess->se_tpg = se_tpg;
 	se_sess->fabric_sess_ptr = fabric_sess_ptr;
@@ -352,7 +383,7 @@ void __transport_register_session(
 			se_sess->sess_bin_isid = get_unaligned_be64(&buf[0]);
 		}
 
-		spin_lock_irq(&se_nacl->nacl_sess_lock);
+		spin_lock_irqsave(&se_nacl->nacl_sess_lock, flags);
 		/*
 		 * The se_nacl->nacl_sess pointer will be set to the
 		 * last active I_T Nexus for each struct se_node_acl.
@@ -361,7 +392,7 @@ void __transport_register_session(
 
 		list_add_tail(&se_sess->sess_acl_list,
 			      &se_nacl->acl_sess_list);
-		spin_unlock_irq(&se_nacl->nacl_sess_lock);
+		spin_unlock_irqrestore(&se_nacl->nacl_sess_lock, flags);
 	}
 	list_add_tail(&se_sess->sess_list, &se_tpg->tpg_sess_list);
 
@@ -385,7 +416,7 @@ void transport_register_session(
 EXPORT_SYMBOL(transport_register_session);
 
 struct se_session *
-target_alloc_session(struct se_portal_group *tpg,
+target_setup_session(struct se_portal_group *tpg,
 		     unsigned int tag_num, unsigned int tag_size,
 		     enum target_prot_op prot_op,
 		     const char *initiatorname, void *private,
@@ -401,7 +432,7 @@ target_alloc_session(struct se_portal_group *tpg,
 	if (tag_num != 0)
 		sess = transport_init_session_tags(tag_num, tag_size, prot_op);
 	else
-		sess = transport_init_session(prot_op);
+		sess = transport_alloc_session(prot_op);
 
 	if (IS_ERR(sess))
 		return sess;
@@ -427,7 +458,7 @@ target_alloc_session(struct se_portal_group *tpg,
 	transport_register_session(tpg, sess->se_node_acl, sess, private);
 	return sess;
 }
-EXPORT_SYMBOL(target_alloc_session);
+EXPORT_SYMBOL(target_setup_session);
 
 ssize_t target_show_dynamic_sessions(struct se_portal_group *se_tpg, char *page)
 {
@@ -547,7 +578,7 @@ void transport_free_session(struct se_session *se_sess)
 		target_put_nacl(se_nacl);
 	}
 	if (se_sess->sess_cmd_map) {
-		percpu_ida_destroy(&se_sess->sess_tag_pool);
+		sbitmap_queue_free(&se_sess->sess_tag_pool);
 		kvfree(se_sess->sess_cmd_map);
 	}
 	kmem_cache_free(se_sess_cache, se_sess);
@@ -585,6 +616,13 @@ void transport_deregister_session(struct se_session *se_sess)
 }
 EXPORT_SYMBOL(transport_deregister_session);
 
+void target_remove_session(struct se_session *se_sess)
+{
+	transport_deregister_session_configfs(se_sess);
+	transport_deregister_session(se_sess);
+}
+EXPORT_SYMBOL(target_remove_session);
+
 static void target_remove_from_state_list(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
@@ -601,6 +639,13 @@ static void target_remove_from_state_list(struct se_cmd *cmd)
 	spin_unlock_irqrestore(&dev->execute_task_lock, flags);
 }
 
+/*
+ * This function is called by the target core after the target core has
+ * finished processing a SCSI command or SCSI TMF. Both the regular command
+ * processing code and the code for aborting commands can call this
+ * function. CMD_T_STOP is set if and only if another thread is waiting
+ * inside transport_wait_for_tasks() for t_transport_stop_comp.
+ */
 static int transport_cmd_check_stop_to_fabric(struct se_cmd *cmd)
 {
 	unsigned long flags;
@@ -650,23 +695,27 @@ static void transport_lun_remove_cmd(struct se_cmd *cmd)
 		percpu_ref_put(&lun->lun_ref);
 }
 
-int transport_cmd_finish_abort(struct se_cmd *cmd, int remove)
+int transport_cmd_finish_abort(struct se_cmd *cmd)
 {
+	bool send_tas = cmd->transport_state & CMD_T_TAS;
 	bool ack_kref = (cmd->se_cmd_flags & SCF_ACK_KREF);
 	int ret = 0;
 
+	if (send_tas)
+		transport_send_task_abort(cmd);
+
 	if (cmd->se_cmd_flags & SCF_SE_LUN_CMD)
 		transport_lun_remove_cmd(cmd);
 	/*
 	 * Allow the fabric driver to unmap any resources before
 	 * releasing the descriptor via TFO->release_cmd()
 	 */
-	if (remove)
+	if (!send_tas)
 		cmd->se_tfo->aborted_task(cmd);
 
 	if (transport_cmd_check_stop_to_fabric(cmd))
 		return 1;
-	if (remove && ack_kref)
+	if (!send_tas && ack_kref)
 		ret = target_put_sess_cmd(cmd);
 
 	return ret;
@@ -1267,7 +1316,7 @@ void transport_init_se_cmd(
 	INIT_LIST_HEAD(&cmd->se_cmd_list);
 	INIT_LIST_HEAD(&cmd->state_list);
 	init_completion(&cmd->t_transport_stop_comp);
-	init_completion(&cmd->cmd_wait_comp);
+	cmd->compl = NULL;
 	spin_lock_init(&cmd->t_state_lock);
 	INIT_WORK(&cmd->work, NULL);
 	kref_init(&cmd->cmd_kref);
@@ -2079,9 +2128,6 @@ static void transport_complete_qf(struct se_cmd *cmd)
 		if (cmd->scsi_status)
 			goto queue_status;
 
-		cmd->se_cmd_flags |= SCF_EMULATED_TASK_SENSE;
-		cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
-		cmd->scsi_sense_length  = TRANSPORT_SENSE_BUFFER;
 		translate_sense_reason(cmd, TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE);
 		goto queue_status;
 	}
@@ -2593,20 +2639,37 @@ static void target_wait_free_cmd(struct se_cmd *cmd, bool *aborted, bool *tas)
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 }
 
+/*
+ * This function is called by frontend drivers after processing of a command
+ * has finished.
+ *
+ * The protocol for ensuring that either the regular flow or the TMF
+ * code drops one reference is as follows:
+ * - Calling .queue_data_in(), .queue_status() or queue_tm_rsp() will cause
+ *   the frontend driver to drop one reference, synchronously or asynchronously.
+ * - During regular command processing the target core sets CMD_T_COMPLETE
+ *   before invoking one of the .queue_*() functions.
+ * - The code that aborts commands skips commands and TMFs for which
+ *   CMD_T_COMPLETE has been set.
+ * - CMD_T_ABORTED is set atomically after the CMD_T_COMPLETE check for
+ *   commands that will be aborted.
+ * - If the CMD_T_ABORTED flag is set but CMD_T_TAS has not been set
+ *   transport_generic_free_cmd() skips its call to target_put_sess_cmd().
+ * - For aborted commands for which CMD_T_TAS has been set .queue_status() will
+ *   be called and will drop a reference.
+ * - For aborted commands for which CMD_T_TAS has not been set .aborted_task()
+ *   will be called. transport_cmd_finish_abort() will drop the final reference.
+ */
 int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
 {
+	DECLARE_COMPLETION_ONSTACK(compl);
 	int ret = 0;
 	bool aborted = false, tas = false;
 
-	if (!(cmd->se_cmd_flags & SCF_SE_LUN_CMD)) {
-		if (wait_for_tasks && (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB))
-			target_wait_free_cmd(cmd, &aborted, &tas);
+	if (wait_for_tasks)
+		target_wait_free_cmd(cmd, &aborted, &tas);
 
-		if (!aborted || tas)
-			ret = target_put_sess_cmd(cmd);
-	} else {
-		if (wait_for_tasks)
-			target_wait_free_cmd(cmd, &aborted, &tas);
+	if (cmd->se_cmd_flags & SCF_SE_LUN_CMD) {
 		/*
 		 * Handle WRITE failure case where transport_generic_new_cmd()
 		 * has already added se_cmd to state_list, but fabric has
@@ -2617,20 +2680,14 @@ int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
 
 		if (cmd->se_lun)
 			transport_lun_remove_cmd(cmd);
-
-		if (!aborted || tas)
-			ret = target_put_sess_cmd(cmd);
 	}
-	/*
-	 * If the task has been internally aborted due to TMR ABORT_TASK
-	 * or LUN_RESET, target_core_tmr.c is responsible for performing
-	 * the remaining calls to target_put_sess_cmd(), and not the
-	 * callers of this function.
-	 */
+	if (aborted)
+		cmd->compl = &compl;
+	if (!aborted || tas)
+		ret = target_put_sess_cmd(cmd);
 	if (aborted) {
 		pr_debug("Detected CMD_T_ABORTED for ITT: %llu\n", cmd->tag);
-		wait_for_completion(&cmd->cmd_wait_comp);
-		cmd->se_tfo->release_cmd(cmd);
+		wait_for_completion(&compl);
 		ret = 1;
 	}
 	return ret;
@@ -2691,30 +2748,21 @@ static void target_release_cmd_kref(struct kref *kref)
 {
 	struct se_cmd *se_cmd = container_of(kref, struct se_cmd, cmd_kref);
 	struct se_session *se_sess = se_cmd->se_sess;
+	struct completion *compl = se_cmd->compl;
 	unsigned long flags;
-	bool fabric_stop;
 
 	if (se_sess) {
 		spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
-
-		spin_lock(&se_cmd->t_state_lock);
-		fabric_stop = (se_cmd->transport_state & CMD_T_FABRIC_STOP) &&
-			      (se_cmd->transport_state & CMD_T_ABORTED);
-		spin_unlock(&se_cmd->t_state_lock);
-
-		if (se_cmd->cmd_wait_set || fabric_stop) {
-			list_del_init(&se_cmd->se_cmd_list);
-			spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
-			target_free_cmd_mem(se_cmd);
-			complete(&se_cmd->cmd_wait_comp);
-			return;
-		}
 		list_del_init(&se_cmd->se_cmd_list);
+		if (list_empty(&se_sess->sess_cmd_list))
+			wake_up(&se_sess->cmd_list_wq);
 		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 	}
 
 	target_free_cmd_mem(se_cmd);
 	se_cmd->se_tfo->release_cmd(se_cmd);
+	if (compl)
+		complete(compl);
 }
 
 /**
@@ -2833,78 +2881,41 @@ void target_show_cmd(const char *pfx, struct se_cmd *cmd)
 EXPORT_SYMBOL(target_show_cmd);
 
 /**
- * target_sess_cmd_list_set_waiting - Flag all commands in
- *         sess_cmd_list to complete cmd_wait_comp.  Set
- *         sess_tearing_down so no more commands are queued.
+ * target_sess_cmd_list_set_waiting - Set sess_tearing_down so no new commands are queued.
  * @se_sess:	session to flag
  */
 void target_sess_cmd_list_set_waiting(struct se_session *se_sess)
 {
-	struct se_cmd *se_cmd, *tmp_cmd;
 	unsigned long flags;
-	int rc;
 
 	spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
-	if (se_sess->sess_tearing_down) {
-		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
-		return;
-	}
 	se_sess->sess_tearing_down = 1;
-	list_splice_init(&se_sess->sess_cmd_list, &se_sess->sess_wait_list);
-
-	list_for_each_entry_safe(se_cmd, tmp_cmd,
-				 &se_sess->sess_wait_list, se_cmd_list) {
-		rc = kref_get_unless_zero(&se_cmd->cmd_kref);
-		if (rc) {
-			se_cmd->cmd_wait_set = 1;
-			spin_lock(&se_cmd->t_state_lock);
-			se_cmd->transport_state |= CMD_T_FABRIC_STOP;
-			spin_unlock(&se_cmd->t_state_lock);
-		} else
-			list_del_init(&se_cmd->se_cmd_list);
-	}
-
 	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 }
 EXPORT_SYMBOL(target_sess_cmd_list_set_waiting);
 
 /**
- * target_wait_for_sess_cmds - Wait for outstanding descriptors
+ * target_wait_for_sess_cmds - Wait for outstanding commands
  * @se_sess:    session to wait for active I/O
  */
 void target_wait_for_sess_cmds(struct se_session *se_sess)
 {
-	struct se_cmd *se_cmd, *tmp_cmd;
-	unsigned long flags;
-	bool tas;
-
-	list_for_each_entry_safe(se_cmd, tmp_cmd,
-				&se_sess->sess_wait_list, se_cmd_list) {
-		pr_debug("Waiting for se_cmd: %p t_state: %d, fabric state:"
-			" %d\n", se_cmd, se_cmd->t_state,
-			se_cmd->se_tfo->get_cmd_state(se_cmd));
-
-		spin_lock_irqsave(&se_cmd->t_state_lock, flags);
-		tas = (se_cmd->transport_state & CMD_T_TAS);
-		spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
-
-		if (!target_put_sess_cmd(se_cmd)) {
-			if (tas)
-				target_put_sess_cmd(se_cmd);
-		}
-
-		wait_for_completion(&se_cmd->cmd_wait_comp);
-		pr_debug("After cmd_wait_comp: se_cmd: %p t_state: %d"
-			" fabric state: %d\n", se_cmd, se_cmd->t_state,
-			se_cmd->se_tfo->get_cmd_state(se_cmd));
-
-		se_cmd->se_tfo->release_cmd(se_cmd);
-	}
+	struct se_cmd *cmd;
+	int ret;
 
-	spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
-	WARN_ON(!list_empty(&se_sess->sess_cmd_list));
-	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
+	WARN_ON_ONCE(!se_sess->sess_tearing_down);
 
+	spin_lock_irq(&se_sess->sess_cmd_lock);
+	do {
+		ret = wait_event_interruptible_lock_irq_timeout(
+				se_sess->cmd_list_wq,
+				list_empty(&se_sess->sess_cmd_list),
+				se_sess->sess_cmd_lock, 180 * HZ);
+		list_for_each_entry(cmd, &se_sess->sess_cmd_list, se_cmd_list)
+			target_show_cmd("session shutdown: still waiting for ",
+					cmd);
+	} while (ret <= 0);
+	spin_unlock_irq(&se_sess->sess_cmd_lock);
 }
 EXPORT_SYMBOL(target_wait_for_sess_cmds);
 
@@ -3166,12 +3177,23 @@ static const struct sense_info sense_info_table[] = {
 	},
 };
 
-static int translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason)
+/**
+ * translate_sense_reason - translate a sense reason into T10 key, asc and ascq
+ * @cmd: SCSI command in which the resulting sense buffer or SCSI status will
+ *   be stored.
+ * @reason: LIO sense reason code. If this argument has the value
+ *   TCM_CHECK_CONDITION_UNIT_ATTENTION, try to dequeue a unit attention. If
+ *   dequeuing a unit attention fails due to multiple commands being processed
+ *   concurrently, set the command status to BUSY.
+ *
+ * Return: 0 upon success or -EINVAL if the sense buffer is too small.
+ */
+static void translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason)
 {
 	const struct sense_info *si;
 	u8 *buffer = cmd->sense_buffer;
 	int r = (__force int)reason;
-	u8 asc, ascq;
+	u8 key, asc, ascq;
 	bool desc_format = target_sense_desc_format(cmd->se_dev);
 
 	if (r < ARRAY_SIZE(sense_info_table) && sense_info_table[r].key)
@@ -3180,9 +3202,13 @@ static int translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason)
 		si = &sense_info_table[(__force int)
 				       TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE];
 
+	key = si->key;
 	if (reason == TCM_CHECK_CONDITION_UNIT_ATTENTION) {
-		core_scsi3_ua_for_check_condition(cmd, &asc, &ascq);
-		WARN_ON_ONCE(asc == 0);
+		if (!core_scsi3_ua_for_check_condition(cmd, &key, &asc,
+						       &ascq)) {
+			cmd->scsi_status = SAM_STAT_BUSY;
+			return;
+		}
 	} else if (si->asc == 0) {
 		WARN_ON_ONCE(cmd->scsi_asc == 0);
 		asc = cmd->scsi_asc;
@@ -3192,13 +3218,14 @@ static int translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason)
 		ascq = si->ascq;
 	}
 
-	scsi_build_sense_buffer(desc_format, buffer, si->key, asc, ascq);
+	cmd->se_cmd_flags |= SCF_EMULATED_TASK_SENSE;
+	cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
+	cmd->scsi_sense_length  = TRANSPORT_SENSE_BUFFER;
+	scsi_build_sense_buffer(desc_format, buffer, key, asc, ascq);
 	if (si->add_sector_info)
-		return scsi_set_sense_information(buffer,
-						  cmd->scsi_sense_length,
-						  cmd->bad_sector);
-
-	return 0;
+		WARN_ON_ONCE(scsi_set_sense_information(buffer,
+							cmd->scsi_sense_length,
+							cmd->bad_sector) < 0);
 }
 
 int
@@ -3215,16 +3242,8 @@ transport_send_check_condition_and_sense(struct se_cmd *cmd,
 	cmd->se_cmd_flags |= SCF_SENT_CHECK_CONDITION;
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
-	if (!from_transport) {
-		int rc;
-
-		cmd->se_cmd_flags |= SCF_EMULATED_TASK_SENSE;
-		cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
-		cmd->scsi_sense_length  = TRANSPORT_SENSE_BUFFER;
-		rc = translate_sense_reason(cmd, reason);
-		if (rc)
-			return rc;
-	}
+	if (!from_transport)
+		translate_sense_reason(cmd, reason);
 
 	trace_target_cmd_complete(cmd);
 	return cmd->se_tfo->queue_status(cmd);
diff --git a/drivers/target/target_core_ua.c b/drivers/target/target_core_ua.c
index be25eb807a5f..c8ac242ce888 100644
--- a/drivers/target/target_core_ua.c
+++ b/drivers/target/target_core_ua.c
@@ -55,7 +55,7 @@ target_scsi3_ua_check(struct se_cmd *cmd)
 		rcu_read_unlock();
 		return 0;
 	}
-	if (!atomic_read(&deve->ua_count)) {
+	if (list_empty_careful(&deve->ua_list)) {
 		rcu_read_unlock();
 		return 0;
 	}
@@ -154,7 +154,6 @@ int core_scsi3_ua_allocate(
 				&deve->ua_list);
 		spin_unlock(&deve->ua_lock);
 
-		atomic_inc_mb(&deve->ua_count);
 		return 0;
 	}
 	list_add_tail(&ua->ua_nacl_list, &deve->ua_list);
@@ -164,7 +163,6 @@ int core_scsi3_ua_allocate(
 		" 0x%02x, ASCQ: 0x%02x\n", deve->mapped_lun,
 		asc, ascq);
 
-	atomic_inc_mb(&deve->ua_count);
 	return 0;
 }
 
@@ -196,16 +194,17 @@ void core_scsi3_ua_release_all(
 	list_for_each_entry_safe(ua, ua_p, &deve->ua_list, ua_nacl_list) {
 		list_del(&ua->ua_nacl_list);
 		kmem_cache_free(se_ua_cache, ua);
-
-		atomic_dec_mb(&deve->ua_count);
 	}
 	spin_unlock(&deve->ua_lock);
 }
 
-void core_scsi3_ua_for_check_condition(
-	struct se_cmd *cmd,
-	u8 *asc,
-	u8 *ascq)
+/*
+ * Dequeue a unit attention from the unit attention list. This function
+ * returns true if the dequeuing succeeded and if *@key, *@asc and *@ascq have
+ * been set.
+ */
+bool core_scsi3_ua_for_check_condition(struct se_cmd *cmd, u8 *key, u8 *asc,
+				       u8 *ascq)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct se_dev_entry *deve;
@@ -214,23 +213,23 @@ void core_scsi3_ua_for_check_condition(
 	struct se_ua *ua = NULL, *ua_p;
 	int head = 1;
 
-	if (!sess)
-		return;
+	if (WARN_ON_ONCE(!sess))
+		return false;
 
 	nacl = sess->se_node_acl;
-	if (!nacl)
-		return;
+	if (WARN_ON_ONCE(!nacl))
+		return false;
 
 	rcu_read_lock();
 	deve = target_nacl_find_deve(nacl, cmd->orig_fe_lun);
 	if (!deve) {
 		rcu_read_unlock();
-		return;
-	}
-	if (!atomic_read(&deve->ua_count)) {
-		rcu_read_unlock();
-		return;
+		*key = ILLEGAL_REQUEST;
+		*asc = 0x25; /* LOGICAL UNIT NOT SUPPORTED */
+		*ascq = 0;
+		return true;
 	}
+	*key = UNIT_ATTENTION;
 	/*
 	 * The highest priority Unit Attentions are placed at the head of the
 	 * struct se_dev_entry->ua_list, and will be returned in CHECK_CONDITION +
@@ -260,8 +259,6 @@ void core_scsi3_ua_for_check_condition(
 		}
 		list_del(&ua->ua_nacl_list);
 		kmem_cache_free(se_ua_cache, ua);
-
-		atomic_dec_mb(&deve->ua_count);
 	}
 	spin_unlock(&deve->ua_lock);
 	rcu_read_unlock();
@@ -273,6 +270,8 @@ void core_scsi3_ua_for_check_condition(
 		(dev->dev_attrib.emulate_ua_intlck_ctrl != 0) ? "Reporting" :
 		"Releasing", dev->dev_attrib.emulate_ua_intlck_ctrl,
 		cmd->orig_fe_lun, cmd->t_task_cdb[0], *asc, *ascq);
+
+	return head == 0;
 }
 
 int core_scsi3_ua_clear_for_request_sense(
@@ -299,7 +298,7 @@ int core_scsi3_ua_clear_for_request_sense(
 		rcu_read_unlock();
 		return -EINVAL;
 	}
-	if (!atomic_read(&deve->ua_count)) {
+	if (list_empty_careful(&deve->ua_list)) {
 		rcu_read_unlock();
 		return -EPERM;
 	}
@@ -322,8 +321,6 @@ int core_scsi3_ua_clear_for_request_sense(
 		}
 		list_del(&ua->ua_nacl_list);
 		kmem_cache_free(se_ua_cache, ua);
-
-		atomic_dec_mb(&deve->ua_count);
 	}
 	spin_unlock(&deve->ua_lock);
 	rcu_read_unlock();
diff --git a/drivers/target/target_core_ua.h b/drivers/target/target_core_ua.h
index b0f4205a96cd..76487c9be090 100644
--- a/drivers/target/target_core_ua.h
+++ b/drivers/target/target_core_ua.h
@@ -37,7 +37,8 @@ extern sense_reason_t target_scsi3_ua_check(struct se_cmd *);
 extern int core_scsi3_ua_allocate(struct se_dev_entry *, u8, u8);
 extern void target_ua_allocate_lun(struct se_node_acl *, u32, u8, u8);
 extern void core_scsi3_ua_release_all(struct se_dev_entry *);
-extern void core_scsi3_ua_for_check_condition(struct se_cmd *, u8 *, u8 *);
+extern bool core_scsi3_ua_for_check_condition(struct se_cmd *, u8 *, u8 *,
+					      u8 *);
 extern int core_scsi3_ua_clear_for_request_sense(struct se_cmd *,
 						u8 *, u8 *);
 
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index d8dc3d22051f..9cd404acdb82 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -83,14 +83,10 @@
 #define DATA_BLOCK_SIZE PAGE_SIZE
 #define DATA_BLOCK_SHIFT PAGE_SHIFT
 #define DATA_BLOCK_BITS_DEF (256 * 1024)
-#define DATA_SIZE (DATA_BLOCK_BITS * DATA_BLOCK_SIZE)
 
 #define TCMU_MBS_TO_BLOCKS(_mbs) (_mbs << (20 - DATA_BLOCK_SHIFT))
 #define TCMU_BLOCKS_TO_MBS(_blocks) (_blocks >> (20 - DATA_BLOCK_SHIFT))
 
-/* The total size of the ring is 8M + 256K * PAGE_SIZE */
-#define TCMU_RING_SIZE (CMDR_SIZE + DATA_SIZE)
-
 /*
  * Default number of global data blocks(512K * PAGE_SIZE)
  * when the unmap thread will be started.
@@ -98,6 +94,7 @@
 #define TCMU_GLOBAL_MAX_BLOCKS_DEF (512 * 1024)
 
 static u8 tcmu_kern_cmd_reply_supported;
+static u8 tcmu_netlink_blocked;
 
 static struct device *tcmu_root_device;
 
@@ -107,9 +104,16 @@ struct tcmu_hba {
 
 #define TCMU_CONFIG_LEN 256
 
+static DEFINE_MUTEX(tcmu_nl_cmd_mutex);
+static LIST_HEAD(tcmu_nl_cmd_list);
+
+struct tcmu_dev;
+
 struct tcmu_nl_cmd {
 	/* wake up thread waiting for reply */
 	struct completion complete;
+	struct list_head nl_list;
+	struct tcmu_dev *udev;
 	int cmd;
 	int status;
 };
@@ -133,7 +137,7 @@ struct tcmu_dev {
 	struct inode *inode;
 
 	struct tcmu_mailbox *mb_addr;
-	size_t dev_size;
+	uint64_t dev_size;
 	u32 cmdr_size;
 	u32 cmdr_last_cleaned;
 	/* Offset of data area from start of mb */
@@ -161,10 +165,7 @@ struct tcmu_dev {
 
 	struct list_head timedout_entry;
 
-	spinlock_t nl_cmd_lock;
 	struct tcmu_nl_cmd curr_nl_cmd;
-	/* wake up threads waiting on curr_nl_cmd */
-	wait_queue_head_t nl_cmd_wq;
 
 	char dev_config[TCMU_CONFIG_LEN];
 
@@ -255,6 +256,92 @@ MODULE_PARM_DESC(global_max_data_area_mb,
 		 "Max MBs allowed to be allocated to all the tcmu device's "
 		 "data areas.");
 
+static int tcmu_get_block_netlink(char *buffer,
+				  const struct kernel_param *kp)
+{
+	return sprintf(buffer, "%s\n", tcmu_netlink_blocked ?
+		       "blocked" : "unblocked");
+}
+
+static int tcmu_set_block_netlink(const char *str,
+				  const struct kernel_param *kp)
+{
+	int ret;
+	u8 val;
+
+	ret = kstrtou8(str, 0, &val);
+	if (ret < 0)
+		return ret;
+
+	if (val > 1) {
+		pr_err("Invalid block netlink value %u\n", val);
+		return -EINVAL;
+	}
+
+	tcmu_netlink_blocked = val;
+	return 0;
+}
+
+static const struct kernel_param_ops tcmu_block_netlink_op = {
+	.set = tcmu_set_block_netlink,
+	.get = tcmu_get_block_netlink,
+};
+
+module_param_cb(block_netlink, &tcmu_block_netlink_op, NULL, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(block_netlink, "Block new netlink commands.");
+
+static int tcmu_fail_netlink_cmd(struct tcmu_nl_cmd *nl_cmd)
+{
+	struct tcmu_dev *udev = nl_cmd->udev;
+
+	if (!tcmu_netlink_blocked) {
+		pr_err("Could not reset device's netlink interface. Netlink is not blocked.\n");
+		return -EBUSY;
+	}
+
+	if (nl_cmd->cmd != TCMU_CMD_UNSPEC) {
+		pr_debug("Aborting nl cmd %d on %s\n", nl_cmd->cmd, udev->name);
+		nl_cmd->status = -EINTR;
+		list_del(&nl_cmd->nl_list);
+		complete(&nl_cmd->complete);
+	}
+	return 0;
+}
+
+static int tcmu_set_reset_netlink(const char *str,
+				  const struct kernel_param *kp)
+{
+	struct tcmu_nl_cmd *nl_cmd, *tmp_cmd;
+	int ret;
+	u8 val;
+
+	ret = kstrtou8(str, 0, &val);
+	if (ret < 0)
+		return ret;
+
+	if (val != 1) {
+		pr_err("Invalid reset netlink value %u\n", val);
+		return -EINVAL;
+	}
+
+	mutex_lock(&tcmu_nl_cmd_mutex);
+	list_for_each_entry_safe(nl_cmd, tmp_cmd, &tcmu_nl_cmd_list, nl_list) {
+		ret = tcmu_fail_netlink_cmd(nl_cmd);
+		if (ret)
+			break;
+	}
+	mutex_unlock(&tcmu_nl_cmd_mutex);
+
+	return ret;
+}
+
+static const struct kernel_param_ops tcmu_reset_netlink_op = {
+	.set = tcmu_set_reset_netlink,
+};
+
+module_param_cb(reset_netlink, &tcmu_reset_netlink_op, NULL, S_IWUSR);
+MODULE_PARM_DESC(reset_netlink, "Reset netlink commands.");
+
 /* multicast group */
 enum tcmu_multicast_groups {
 	TCMU_MCGRP_CONFIG,
@@ -274,48 +361,50 @@ static struct nla_policy tcmu_attr_policy[TCMU_ATTR_MAX+1] = {
 
 static int tcmu_genl_cmd_done(struct genl_info *info, int completed_cmd)
 {
-	struct se_device *dev;
-	struct tcmu_dev *udev;
+	struct tcmu_dev *udev = NULL;
 	struct tcmu_nl_cmd *nl_cmd;
 	int dev_id, rc, ret = 0;
-	bool is_removed = (completed_cmd == TCMU_CMD_REMOVED_DEVICE);
 
 	if (!info->attrs[TCMU_ATTR_CMD_STATUS] ||
 	    !info->attrs[TCMU_ATTR_DEVICE_ID]) {
 		printk(KERN_ERR "TCMU_ATTR_CMD_STATUS or TCMU_ATTR_DEVICE_ID not set, doing nothing\n");
-                return -EINVAL;
+		return -EINVAL;
         }
 
 	dev_id = nla_get_u32(info->attrs[TCMU_ATTR_DEVICE_ID]);
 	rc = nla_get_s32(info->attrs[TCMU_ATTR_CMD_STATUS]);
 
-	dev = target_find_device(dev_id, !is_removed);
-	if (!dev) {
-		printk(KERN_ERR "tcmu nl cmd %u/%u completion could not find device with dev id %u.\n",
-		       completed_cmd, rc, dev_id);
-		return -ENODEV;
+	mutex_lock(&tcmu_nl_cmd_mutex);
+	list_for_each_entry(nl_cmd, &tcmu_nl_cmd_list, nl_list) {
+		if (nl_cmd->udev->se_dev.dev_index == dev_id) {
+			udev = nl_cmd->udev;
+			break;
+		}
 	}
-	udev = TCMU_DEV(dev);
 
-	spin_lock(&udev->nl_cmd_lock);
-	nl_cmd = &udev->curr_nl_cmd;
+	if (!udev) {
+		pr_err("tcmu nl cmd %u/%d completion could not find device with dev id %u.\n",
+		       completed_cmd, rc, dev_id);
+		ret = -ENODEV;
+		goto unlock;
+	}
+	list_del(&nl_cmd->nl_list);
 
-	pr_debug("genl cmd done got id %d curr %d done %d rc %d\n", dev_id,
-		 nl_cmd->cmd, completed_cmd, rc);
+	pr_debug("%s genl cmd done got id %d curr %d done %d rc %d stat %d\n",
+		 udev->name, dev_id, nl_cmd->cmd, completed_cmd, rc,
+		 nl_cmd->status);
 
 	if (nl_cmd->cmd != completed_cmd) {
-		printk(KERN_ERR "Mismatched commands (Expecting reply for %d. Current %d).\n",
-		       completed_cmd, nl_cmd->cmd);
+		pr_err("Mismatched commands on %s (Expecting reply for %d. Current %d).\n",
+		       udev->name, completed_cmd, nl_cmd->cmd);
 		ret = -EINVAL;
-	} else {
-		nl_cmd->status = rc;
+		goto unlock;
 	}
 
-	spin_unlock(&udev->nl_cmd_lock);
-	if (!is_removed)
-		 target_undepend_item(&dev->dev_group.cg_item);
-	if (!ret)
-		complete(&nl_cmd->complete);
+	nl_cmd->status = rc;
+	complete(&nl_cmd->complete);
+unlock:
+	mutex_unlock(&tcmu_nl_cmd_mutex);
 	return ret;
 }
 
@@ -982,7 +1071,6 @@ static sense_reason_t queue_cmd_ring(struct tcmu_cmd *tcmu_cmd, int *scsi_err)
 				   &udev->cmd_timer);
 	if (ret) {
 		tcmu_cmd_free_data(tcmu_cmd, tcmu_cmd->dbi_cnt);
-		mutex_unlock(&udev->cmdr_lock);
 
 		*scsi_err = TCM_OUT_OF_RESOURCES;
 		return -1;
@@ -1282,6 +1370,7 @@ static struct se_device *tcmu_alloc_device(struct se_hba *hba, const char *name)
 	udev->max_blocks = DATA_BLOCK_BITS_DEF;
 	mutex_init(&udev->cmdr_lock);
 
+	INIT_LIST_HEAD(&udev->node);
 	INIT_LIST_HEAD(&udev->timedout_entry);
 	INIT_LIST_HEAD(&udev->cmdr_queue);
 	idr_init(&udev->commands);
@@ -1289,9 +1378,6 @@ static struct se_device *tcmu_alloc_device(struct se_hba *hba, const char *name)
 	timer_setup(&udev->qfull_timer, tcmu_qfull_timedout, 0);
 	timer_setup(&udev->cmd_timer, tcmu_cmd_timedout, 0);
 
-	init_waitqueue_head(&udev->nl_cmd_wq);
-	spin_lock_init(&udev->nl_cmd_lock);
-
 	INIT_RADIX_TREE(&udev->data_blocks, GFP_KERNEL);
 
 	return &udev->se_dev;
@@ -1565,38 +1651,48 @@ static int tcmu_release(struct uio_info *info, struct inode *inode)
 	return 0;
 }
 
-static void tcmu_init_genl_cmd_reply(struct tcmu_dev *udev, int cmd)
+static int tcmu_init_genl_cmd_reply(struct tcmu_dev *udev, int cmd)
 {
 	struct tcmu_nl_cmd *nl_cmd = &udev->curr_nl_cmd;
 
 	if (!tcmu_kern_cmd_reply_supported)
-		return;
+		return 0;
 
 	if (udev->nl_reply_supported <= 0)
-		return;
+		return 0;
+
+	mutex_lock(&tcmu_nl_cmd_mutex);
 
-relock:
-	spin_lock(&udev->nl_cmd_lock);
+	if (tcmu_netlink_blocked) {
+		mutex_unlock(&tcmu_nl_cmd_mutex);
+		pr_warn("Failing nl cmd %d on %s. Interface is blocked.\n", cmd,
+			udev->name);
+		return -EAGAIN;
+	}
 
 	if (nl_cmd->cmd != TCMU_CMD_UNSPEC) {
-		spin_unlock(&udev->nl_cmd_lock);
-		pr_debug("sleeping for open nl cmd\n");
-		wait_event(udev->nl_cmd_wq, (nl_cmd->cmd == TCMU_CMD_UNSPEC));
-		goto relock;
+		mutex_unlock(&tcmu_nl_cmd_mutex);
+		pr_warn("netlink cmd %d already executing on %s\n",
+			 nl_cmd->cmd, udev->name);
+		return -EBUSY;
 	}
 
 	memset(nl_cmd, 0, sizeof(*nl_cmd));
 	nl_cmd->cmd = cmd;
+	nl_cmd->udev = udev;
 	init_completion(&nl_cmd->complete);
+	INIT_LIST_HEAD(&nl_cmd->nl_list);
+
+	list_add_tail(&nl_cmd->nl_list, &tcmu_nl_cmd_list);
 
-	spin_unlock(&udev->nl_cmd_lock);
+	mutex_unlock(&tcmu_nl_cmd_mutex);
+	return 0;
 }
 
 static int tcmu_wait_genl_cmd_reply(struct tcmu_dev *udev)
 {
 	struct tcmu_nl_cmd *nl_cmd = &udev->curr_nl_cmd;
 	int ret;
-	DEFINE_WAIT(__wait);
 
 	if (!tcmu_kern_cmd_reply_supported)
 		return 0;
@@ -1607,13 +1703,10 @@ static int tcmu_wait_genl_cmd_reply(struct tcmu_dev *udev)
 	pr_debug("sleeping for nl reply\n");
 	wait_for_completion(&nl_cmd->complete);
 
-	spin_lock(&udev->nl_cmd_lock);
+	mutex_lock(&tcmu_nl_cmd_mutex);
 	nl_cmd->cmd = TCMU_CMD_UNSPEC;
 	ret = nl_cmd->status;
-	nl_cmd->status = 0;
-	spin_unlock(&udev->nl_cmd_lock);
-
-	wake_up_all(&udev->nl_cmd_wq);
+	mutex_unlock(&tcmu_nl_cmd_mutex);
 
 	return ret;
 }
@@ -1657,19 +1750,21 @@ free_skb:
 
 static int tcmu_netlink_event_send(struct tcmu_dev *udev,
 				   enum tcmu_genl_cmd cmd,
-				   struct sk_buff **buf, void **hdr)
+				   struct sk_buff *skb, void *msg_header)
 {
-	int ret = 0;
-	struct sk_buff *skb = *buf;
-	void *msg_header = *hdr;
+	int ret;
 
 	genlmsg_end(skb, msg_header);
 
-	tcmu_init_genl_cmd_reply(udev, cmd);
+	ret = tcmu_init_genl_cmd_reply(udev, cmd);
+	if (ret) {
+		nlmsg_free(skb);
+		return ret;
+	}
 
 	ret = genlmsg_multicast_allns(&tcmu_genl_family, skb, 0,
 				      TCMU_MCGRP_CONFIG, GFP_KERNEL);
-       /* We don't care if no one is listening */
+	/* We don't care if no one is listening */
 	if (ret == -ESRCH)
 		ret = 0;
 	if (!ret)
@@ -1687,9 +1782,8 @@ static int tcmu_send_dev_add_event(struct tcmu_dev *udev)
 				      &msg_header);
 	if (ret < 0)
 		return ret;
-	return tcmu_netlink_event_send(udev, TCMU_CMD_ADDED_DEVICE, &skb,
-				       &msg_header);
-
+	return tcmu_netlink_event_send(udev, TCMU_CMD_ADDED_DEVICE, skb,
+				       msg_header);
 }
 
 static int tcmu_send_dev_remove_event(struct tcmu_dev *udev)
@@ -1703,7 +1797,7 @@ static int tcmu_send_dev_remove_event(struct tcmu_dev *udev)
 	if (ret < 0)
 		return ret;
 	return tcmu_netlink_event_send(udev, TCMU_CMD_REMOVED_DEVICE,
-				       &skb, &msg_header);
+				       skb, msg_header);
 }
 
 static int tcmu_update_uio_info(struct tcmu_dev *udev)
@@ -1745,9 +1839,11 @@ static int tcmu_configure_device(struct se_device *dev)
 
 	info = &udev->uio_info;
 
+	mutex_lock(&udev->cmdr_lock);
 	udev->data_bitmap = kcalloc(BITS_TO_LONGS(udev->max_blocks),
 				    sizeof(unsigned long),
 				    GFP_KERNEL);
+	mutex_unlock(&udev->cmdr_lock);
 	if (!udev->data_bitmap) {
 		ret = -ENOMEM;
 		goto err_bitmap_alloc;
@@ -1842,11 +1938,6 @@ err_bitmap_alloc:
 	return ret;
 }
 
-static bool tcmu_dev_configured(struct tcmu_dev *udev)
-{
-	return udev->uio_info.uio_dev ? true : false;
-}
-
 static void tcmu_free_device(struct se_device *dev)
 {
 	struct tcmu_dev *udev = TCMU_DEV(dev);
@@ -1953,45 +2044,76 @@ enum {
 
 static match_table_t tokens = {
 	{Opt_dev_config, "dev_config=%s"},
-	{Opt_dev_size, "dev_size=%u"},
-	{Opt_hw_block_size, "hw_block_size=%u"},
-	{Opt_hw_max_sectors, "hw_max_sectors=%u"},
+	{Opt_dev_size, "dev_size=%s"},
+	{Opt_hw_block_size, "hw_block_size=%d"},
+	{Opt_hw_max_sectors, "hw_max_sectors=%d"},
 	{Opt_nl_reply_supported, "nl_reply_supported=%d"},
-	{Opt_max_data_area_mb, "max_data_area_mb=%u"},
+	{Opt_max_data_area_mb, "max_data_area_mb=%d"},
 	{Opt_err, NULL}
 };
 
 static int tcmu_set_dev_attrib(substring_t *arg, u32 *dev_attrib)
 {
-	unsigned long tmp_ul;
-	char *arg_p;
-	int ret;
+	int val, ret;
 
-	arg_p = match_strdup(arg);
-	if (!arg_p)
-		return -ENOMEM;
-
-	ret = kstrtoul(arg_p, 0, &tmp_ul);
-	kfree(arg_p);
+	ret = match_int(arg, &val);
 	if (ret < 0) {
-		pr_err("kstrtoul() failed for dev attrib\n");
+		pr_err("match_int() failed for dev attrib. Error %d.\n",
+		       ret);
 		return ret;
 	}
-	if (!tmp_ul) {
-		pr_err("dev attrib must be nonzero\n");
+
+	if (val <= 0) {
+		pr_err("Invalid dev attrib value %d. Must be greater than zero.\n",
+		       val);
 		return -EINVAL;
 	}
-	*dev_attrib = tmp_ul;
+	*dev_attrib = val;
 	return 0;
 }
 
+static int tcmu_set_max_blocks_param(struct tcmu_dev *udev, substring_t *arg)
+{
+	int val, ret;
+
+	ret = match_int(arg, &val);
+	if (ret < 0) {
+		pr_err("match_int() failed for max_data_area_mb=. Error %d.\n",
+		       ret);
+		return ret;
+	}
+
+	if (val <= 0) {
+		pr_err("Invalid max_data_area %d.\n", val);
+		return -EINVAL;
+	}
+
+	mutex_lock(&udev->cmdr_lock);
+	if (udev->data_bitmap) {
+		pr_err("Cannot set max_data_area_mb after it has been enabled.\n");
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	udev->max_blocks = TCMU_MBS_TO_BLOCKS(val);
+	if (udev->max_blocks > tcmu_global_max_blocks) {
+		pr_err("%d is too large. Adjusting max_data_area_mb to global limit of %u\n",
+		       val, TCMU_BLOCKS_TO_MBS(tcmu_global_max_blocks));
+		udev->max_blocks = tcmu_global_max_blocks;
+	}
+
+unlock:
+	mutex_unlock(&udev->cmdr_lock);
+	return ret;
+}
+
 static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev,
 		const char *page, ssize_t count)
 {
 	struct tcmu_dev *udev = TCMU_DEV(dev);
-	char *orig, *ptr, *opts, *arg_p;
+	char *orig, *ptr, *opts;
 	substring_t args[MAX_OPT_ARGS];
-	int ret = 0, token, tmpval;
+	int ret = 0, token;
 
 	opts = kstrdup(page, GFP_KERNEL);
 	if (!opts)
@@ -2014,15 +2136,10 @@ static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev,
 			pr_debug("TCMU: Referencing Path: %s\n", udev->dev_config);
 			break;
 		case Opt_dev_size:
-			arg_p = match_strdup(&args[0]);
-			if (!arg_p) {
-				ret = -ENOMEM;
-				break;
-			}
-			ret = kstrtoul(arg_p, 0, (unsigned long *) &udev->dev_size);
-			kfree(arg_p);
+			ret = match_u64(&args[0], &udev->dev_size);
 			if (ret < 0)
-				pr_err("kstrtoul() failed for dev_size=\n");
+				pr_err("match_u64() failed for dev_size=. Error %d.\n",
+				       ret);
 			break;
 		case Opt_hw_block_size:
 			ret = tcmu_set_dev_attrib(&args[0],
@@ -2033,48 +2150,13 @@ static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev,
 					&(dev->dev_attrib.hw_max_sectors));
 			break;
 		case Opt_nl_reply_supported:
-			arg_p = match_strdup(&args[0]);
-			if (!arg_p) {
-				ret = -ENOMEM;
-				break;
-			}
-			ret = kstrtoint(arg_p, 0, &udev->nl_reply_supported);
-			kfree(arg_p);
+			ret = match_int(&args[0], &udev->nl_reply_supported);
 			if (ret < 0)
-				pr_err("kstrtoint() failed for nl_reply_supported=\n");
+				pr_err("match_int() failed for nl_reply_supported=. Error %d.\n",
+				       ret);
 			break;
 		case Opt_max_data_area_mb:
-			if (dev->export_count) {
-				pr_err("Unable to set max_data_area_mb while exports exist\n");
-				ret = -EINVAL;
-				break;
-			}
-
-			arg_p = match_strdup(&args[0]);
-			if (!arg_p) {
-				ret = -ENOMEM;
-				break;
-			}
-			ret = kstrtoint(arg_p, 0, &tmpval);
-			kfree(arg_p);
-			if (ret < 0) {
-				pr_err("kstrtoint() failed for max_data_area_mb=\n");
-				break;
-			}
-
-			if (tmpval <= 0) {
-				pr_err("Invalid max_data_area %d\n", tmpval);
-				ret = -EINVAL;
-				break;
-			}
-
-			udev->max_blocks = TCMU_MBS_TO_BLOCKS(tmpval);
-			if (udev->max_blocks > tcmu_global_max_blocks) {
-				pr_err("%d is too large. Adjusting max_data_area_mb to global limit of %u\n",
-				       tmpval,
-				       TCMU_BLOCKS_TO_MBS(tcmu_global_max_blocks));
-				udev->max_blocks = tcmu_global_max_blocks;
-			}
+			ret = tcmu_set_max_blocks_param(udev, &args[0]);
 			break;
 		default:
 			break;
@@ -2095,7 +2177,7 @@ static ssize_t tcmu_show_configfs_dev_params(struct se_device *dev, char *b)
 
 	bl = sprintf(b + bl, "Config: %s ",
 		     udev->dev_config[0] ? udev->dev_config : "NULL");
-	bl += sprintf(b + bl, "Size: %zu ", udev->dev_size);
+	bl += sprintf(b + bl, "Size: %llu ", udev->dev_size);
 	bl += sprintf(b + bl, "MaxDataAreaMB: %u\n",
 		      TCMU_BLOCKS_TO_MBS(udev->max_blocks));
 
@@ -2222,7 +2304,7 @@ static int tcmu_send_dev_config_event(struct tcmu_dev *udev,
 		return ret;
 	}
 	return tcmu_netlink_event_send(udev, TCMU_CMD_RECONFIG_DEVICE,
-				       &skb, &msg_header);
+				       skb, msg_header);
 }
 
 
@@ -2239,7 +2321,7 @@ static ssize_t tcmu_dev_config_store(struct config_item *item, const char *page,
 		return -EINVAL;
 
 	/* Check if device has been configured before */
-	if (tcmu_dev_configured(udev)) {
+	if (target_dev_configured(&udev->se_dev)) {
 		ret = tcmu_send_dev_config_event(udev, page);
 		if (ret) {
 			pr_err("Unable to reconfigure device\n");
@@ -2264,7 +2346,7 @@ static ssize_t tcmu_dev_size_show(struct config_item *item, char *page)
 						struct se_dev_attrib, da_group);
 	struct tcmu_dev *udev = TCMU_DEV(da->da_dev);
 
-	return snprintf(page, PAGE_SIZE, "%zu\n", udev->dev_size);
+	return snprintf(page, PAGE_SIZE, "%llu\n", udev->dev_size);
 }
 
 static int tcmu_send_dev_size_event(struct tcmu_dev *udev, u64 size)
@@ -2284,7 +2366,7 @@ static int tcmu_send_dev_size_event(struct tcmu_dev *udev, u64 size)
 		return ret;
 	}
 	return tcmu_netlink_event_send(udev, TCMU_CMD_RECONFIG_DEVICE,
-				       &skb, &msg_header);
+				       skb, msg_header);
 }
 
 static ssize_t tcmu_dev_size_store(struct config_item *item, const char *page,
@@ -2301,7 +2383,7 @@ static ssize_t tcmu_dev_size_store(struct config_item *item, const char *page,
 		return ret;
 
 	/* Check if device has been configured before */
-	if (tcmu_dev_configured(udev)) {
+	if (target_dev_configured(&udev->se_dev)) {
 		ret = tcmu_send_dev_size_event(udev, val);
 		if (ret) {
 			pr_err("Unable to reconfigure device\n");
@@ -2366,7 +2448,7 @@ static int tcmu_send_emulate_write_cache(struct tcmu_dev *udev, u8 val)
 		return ret;
 	}
 	return tcmu_netlink_event_send(udev, TCMU_CMD_RECONFIG_DEVICE,
-				       &skb, &msg_header);
+				       skb, msg_header);
 }
 
 static ssize_t tcmu_emulate_write_cache_store(struct config_item *item,
@@ -2383,7 +2465,7 @@ static ssize_t tcmu_emulate_write_cache_store(struct config_item *item,
 		return ret;
 
 	/* Check if device has been configured before */
-	if (tcmu_dev_configured(udev)) {
+	if (target_dev_configured(&udev->se_dev)) {
 		ret = tcmu_send_emulate_write_cache(udev, val);
 		if (ret) {
 			pr_err("Unable to reconfigure device\n");
@@ -2419,6 +2501,11 @@ static ssize_t tcmu_block_dev_store(struct config_item *item, const char *page,
 	u8 val;
 	int ret;
 
+	if (!target_dev_configured(&udev->se_dev)) {
+		pr_err("Device is not configured.\n");
+		return -EINVAL;
+	}
+
 	ret = kstrtou8(page, 0, &val);
 	if (ret < 0)
 		return ret;
@@ -2446,6 +2533,11 @@ static ssize_t tcmu_reset_ring_store(struct config_item *item, const char *page,
 	u8 val;
 	int ret;
 
+	if (!target_dev_configured(&udev->se_dev)) {
+		pr_err("Device is not configured.\n");
+		return -EINVAL;
+	}
+
 	ret = kstrtou8(page, 0, &val);
 	if (ret < 0)
 		return ret;
@@ -2510,6 +2602,11 @@ static void find_free_blocks(void)
 	list_for_each_entry(udev, &root_udev, node) {
 		mutex_lock(&udev->cmdr_lock);
 
+		if (!target_dev_configured(&udev->se_dev)) {
+			mutex_unlock(&udev->cmdr_lock);
+			continue;
+		}
+
 		/* Try to complete the finished commands first */
 		tcmu_handle_completions(udev);
 
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index 9ee89e00cd77..2718a933c0c6 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -497,10 +497,7 @@ int target_xcopy_setup_pt(void)
 	INIT_LIST_HEAD(&xcopy_pt_nacl.acl_list);
 	INIT_LIST_HEAD(&xcopy_pt_nacl.acl_sess_list);
 	memset(&xcopy_pt_sess, 0, sizeof(struct se_session));
-	INIT_LIST_HEAD(&xcopy_pt_sess.sess_list);
-	INIT_LIST_HEAD(&xcopy_pt_sess.sess_acl_list);
-	INIT_LIST_HEAD(&xcopy_pt_sess.sess_cmd_list);
-	spin_lock_init(&xcopy_pt_sess.sess_cmd_lock);
+	transport_init_session(&xcopy_pt_sess);
 
 	xcopy_pt_nacl.se_tpg = &xcopy_pt_tpg;
 	xcopy_pt_nacl.nacl_sess = &xcopy_pt_sess;
diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c
index ec372860106f..a183d4da7db2 100644
--- a/drivers/target/tcm_fc/tfc_cmd.c
+++ b/drivers/target/tcm_fc/tfc_cmd.c
@@ -28,7 +28,6 @@
 #include <linux/configfs.h>
 #include <linux/ctype.h>
 #include <linux/hash.h>
-#include <linux/percpu_ida.h>
 #include <asm/unaligned.h>
 #include <scsi/scsi_tcq.h>
 #include <scsi/libfc.h>
@@ -92,7 +91,7 @@ static void ft_free_cmd(struct ft_cmd *cmd)
 	if (fr_seq(fp))
 		fc_seq_release(fr_seq(fp));
 	fc_frame_free(fp);
-	percpu_ida_free(&sess->se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
+	target_free_tag(sess->se_sess, &cmd->se_cmd);
 	ft_sess_put(sess);	/* undo get from lookup at recv */
 }
 
@@ -448,9 +447,9 @@ static void ft_recv_cmd(struct ft_sess *sess, struct fc_frame *fp)
 	struct ft_cmd *cmd;
 	struct fc_lport *lport = sess->tport->lport;
 	struct se_session *se_sess = sess->se_sess;
-	int tag;
+	int tag, cpu;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
+	tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
 	if (tag < 0)
 		goto busy;
 
@@ -458,10 +457,11 @@ static void ft_recv_cmd(struct ft_sess *sess, struct fc_frame *fp)
 	memset(cmd, 0, sizeof(struct ft_cmd));
 
 	cmd->se_cmd.map_tag = tag;
+	cmd->se_cmd.map_cpu = cpu;
 	cmd->sess = sess;
 	cmd->seq = fc_seq_assign(lport, fp);
 	if (!cmd->seq) {
-		percpu_ida_free(&se_sess->sess_tag_pool, tag);
+		target_free_tag(se_sess, &cmd->se_cmd);
 		goto busy;
 	}
 	cmd->req_frame = fp;		/* hold frame during cmd */
diff --git a/drivers/target/tcm_fc/tfc_conf.c b/drivers/target/tcm_fc/tfc_conf.c
index 42ee91123dca..e55c4d537592 100644
--- a/drivers/target/tcm_fc/tfc_conf.c
+++ b/drivers/target/tcm_fc/tfc_conf.c
@@ -223,10 +223,7 @@ static int ft_init_nodeacl(struct se_node_acl *nacl, const char *name)
 /*
  * local_port port_group (tpg) ops.
  */
-static struct se_portal_group *ft_add_tpg(
-	struct se_wwn *wwn,
-	struct config_group *group,
-	const char *name)
+static struct se_portal_group *ft_add_tpg(struct se_wwn *wwn, const char *name)
 {
 	struct ft_lport_wwn *ft_wwn;
 	struct ft_tpg *tpg;
diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c
index c91979c1463d..6d4adf5ec26c 100644
--- a/drivers/target/tcm_fc/tfc_sess.c
+++ b/drivers/target/tcm_fc/tfc_sess.c
@@ -239,7 +239,7 @@ static struct ft_sess *ft_sess_create(struct ft_tport *tport, u32 port_id,
 	sess->tport = tport;
 	sess->port_id = port_id;
 
-	sess->se_sess = target_alloc_session(se_tpg, TCM_FC_DEFAULT_TAGS,
+	sess->se_sess = target_setup_session(se_tpg, TCM_FC_DEFAULT_TAGS,
 					     sizeof(struct ft_cmd),
 					     TARGET_PROT_NORMAL, &initiatorname[0],
 					     sess, ft_sess_alloc_cb);
@@ -287,7 +287,6 @@ static struct ft_sess *ft_sess_delete(struct ft_tport *tport, u32 port_id)
 
 static void ft_close_sess(struct ft_sess *sess)
 {
-	transport_deregister_session_configfs(sess->se_sess);
 	target_sess_cmd_list_set_waiting(sess->se_sess);
 	target_wait_for_sess_cmds(sess->se_sess);
 	ft_sess_put(sess);
@@ -448,7 +447,7 @@ static void ft_sess_free(struct kref *kref)
 {
 	struct ft_sess *sess = container_of(kref, struct ft_sess, kref);
 
-	transport_deregister_session(sess->se_sess);
+	target_remove_session(sess->se_sess);
 	kfree_rcu(sess, rcu);
 }
 
diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c
index 07d3be6f0780..0b9ab1d0dd45 100644
--- a/drivers/tee/tee_shm.c
+++ b/drivers/tee/tee_shm.c
@@ -80,11 +80,6 @@ static void tee_shm_op_release(struct dma_buf *dmabuf)
 	tee_shm_release(shm);
 }
 
-static void *tee_shm_op_map_atomic(struct dma_buf *dmabuf, unsigned long pgnum)
-{
-	return NULL;
-}
-
 static void *tee_shm_op_map(struct dma_buf *dmabuf, unsigned long pgnum)
 {
 	return NULL;
@@ -107,7 +102,6 @@ static const struct dma_buf_ops tee_shm_dma_buf_ops = {
 	.map_dma_buf = tee_shm_op_map_dma_buf,
 	.unmap_dma_buf = tee_shm_op_unmap_dma_buf,
 	.release = tee_shm_op_release,
-	.map_atomic = tee_shm_op_map_atomic,
 	.map = tee_shm_op_map,
 	.mmap = tee_shm_op_mmap,
 };
diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index 4c275ec10ac5..2c2f6d93034e 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -24,6 +24,8 @@
 #include <linux/of_device.h>
 #include <linux/thermal.h>
 #include <linux/iopoll.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 /* Thermal Manager Control and Status Register */
 #define PMU_TDC0_SW_RST_MASK		(0x1 << 1)
@@ -39,24 +41,24 @@
 #define A375_READOUT_INVERT		BIT(15)
 #define A375_HW_RESETn			BIT(8)
 
-/* Legacy bindings */
-#define LEGACY_CONTROL_MEM_LEN		0x4
-
-/* Current bindings with the 2 control registers under the same memory area */
-#define LEGACY_CONTROL1_OFFSET		0x0
-#define CONTROL0_OFFSET			0x0
-#define CONTROL1_OFFSET			0x4
-
 /* Errata fields */
 #define CONTROL0_TSEN_TC_TRIM_MASK	0x7
 #define CONTROL0_TSEN_TC_TRIM_VAL	0x3
 
-/* TSEN refers to the temperature sensors within the AP */
 #define CONTROL0_TSEN_START		BIT(0)
 #define CONTROL0_TSEN_RESET		BIT(1)
 #define CONTROL0_TSEN_ENABLE		BIT(2)
-
-/* EXT_TSEN refers to the external temperature sensors, out of the AP */
+#define CONTROL0_TSEN_AVG_BYPASS	BIT(6)
+#define CONTROL0_TSEN_CHAN_SHIFT	13
+#define CONTROL0_TSEN_CHAN_MASK		0xF
+#define CONTROL0_TSEN_OSR_SHIFT		24
+#define CONTROL0_TSEN_OSR_MAX		0x3
+#define CONTROL0_TSEN_MODE_SHIFT	30
+#define CONTROL0_TSEN_MODE_EXTERNAL	0x2
+#define CONTROL0_TSEN_MODE_MASK		0x3
+
+#define CONTROL1_TSEN_AVG_SHIFT		0
+#define CONTROL1_TSEN_AVG_MASK		0x7
 #define CONTROL1_EXT_TSEN_SW_RESET	BIT(7)
 #define CONTROL1_EXT_TSEN_HW_RESETn	BIT(8)
 
@@ -67,19 +69,19 @@ struct armada_thermal_data;
 
 /* Marvell EBU Thermal Sensor Dev Structure */
 struct armada_thermal_priv {
-	void __iomem *status;
-	void __iomem *control0;
-	void __iomem *control1;
+	struct device *dev;
+	struct regmap *syscon;
+	char zone_name[THERMAL_NAME_LENGTH];
+	/* serialize temperature reads/updates */
+	struct mutex update_lock;
 	struct armada_thermal_data *data;
+	int current_channel;
 };
 
 struct armada_thermal_data {
-	/* Initialize the sensor */
-	void (*init_sensor)(struct platform_device *pdev,
-			    struct armada_thermal_priv *);
-
-	/* Test for a valid sensor value (optional) */
-	bool (*is_valid)(struct armada_thermal_priv *);
+	/* Initialize the thermal IC */
+	void (*init)(struct platform_device *pdev,
+		     struct armada_thermal_priv *priv);
 
 	/* Formula coeficients: temp = (b - m * reg) / div */
 	s64 coef_b;
@@ -92,141 +94,242 @@ struct armada_thermal_data {
 	unsigned int temp_shift;
 	unsigned int temp_mask;
 	u32 is_valid_bit;
-	bool needs_control0;
+
+	/* Syscon access */
+	unsigned int syscon_control0_off;
+	unsigned int syscon_control1_off;
+	unsigned int syscon_status_off;
+
+	/* One sensor is in the thermal IC, the others are in the CPUs if any */
+	unsigned int cpu_nr;
 };
 
-static void armadaxp_init_sensor(struct platform_device *pdev,
-				 struct armada_thermal_priv *priv)
+struct armada_drvdata {
+	enum drvtype {
+		LEGACY,
+		SYSCON
+	} type;
+	union {
+		struct armada_thermal_priv *priv;
+		struct thermal_zone_device *tz;
+	} data;
+};
+
+/*
+ * struct armada_thermal_sensor - hold the information of one thermal sensor
+ * @thermal: pointer to the local private structure
+ * @tzd: pointer to the thermal zone device
+ * @id: identifier of the thermal sensor
+ */
+struct armada_thermal_sensor {
+	struct armada_thermal_priv *priv;
+	int id;
+};
+
+static void armadaxp_init(struct platform_device *pdev,
+			  struct armada_thermal_priv *priv)
 {
+	struct armada_thermal_data *data = priv->data;
 	u32 reg;
 
-	reg = readl_relaxed(priv->control1);
+	regmap_read(priv->syscon, data->syscon_control1_off, &reg);
 	reg |= PMU_TDC0_OTF_CAL_MASK;
-	writel(reg, priv->control1);
 
 	/* Reference calibration value */
 	reg &= ~PMU_TDC0_REF_CAL_CNT_MASK;
 	reg |= (0xf1 << PMU_TDC0_REF_CAL_CNT_OFFS);
-	writel(reg, priv->control1);
 
 	/* Reset the sensor */
-	reg = readl_relaxed(priv->control1);
-	writel((reg | PMU_TDC0_SW_RST_MASK), priv->control1);
+	reg |= PMU_TDC0_SW_RST_MASK;
 
-	writel(reg, priv->control1);
+	regmap_write(priv->syscon, data->syscon_control1_off, reg);
 
 	/* Enable the sensor */
-	reg = readl_relaxed(priv->status);
+	regmap_read(priv->syscon, data->syscon_status_off, &reg);
 	reg &= ~PMU_TM_DISABLE_MASK;
-	writel(reg, priv->status);
+	regmap_write(priv->syscon, data->syscon_status_off, reg);
 }
 
-static void armada370_init_sensor(struct platform_device *pdev,
-				  struct armada_thermal_priv *priv)
+static void armada370_init(struct platform_device *pdev,
+			   struct armada_thermal_priv *priv)
 {
+	struct armada_thermal_data *data = priv->data;
 	u32 reg;
 
-	reg = readl_relaxed(priv->control1);
+	regmap_read(priv->syscon, data->syscon_control1_off, &reg);
 	reg |= PMU_TDC0_OTF_CAL_MASK;
-	writel(reg, priv->control1);
 
 	/* Reference calibration value */
 	reg &= ~PMU_TDC0_REF_CAL_CNT_MASK;
 	reg |= (0xf1 << PMU_TDC0_REF_CAL_CNT_OFFS);
-	writel(reg, priv->control1);
 
+	/* Reset the sensor */
 	reg &= ~PMU_TDC0_START_CAL_MASK;
-	writel(reg, priv->control1);
+
+	regmap_write(priv->syscon, data->syscon_control1_off, reg);
 
 	msleep(10);
 }
 
-static void armada375_init_sensor(struct platform_device *pdev,
-				  struct armada_thermal_priv *priv)
+static void armada375_init(struct platform_device *pdev,
+			   struct armada_thermal_priv *priv)
 {
+	struct armada_thermal_data *data = priv->data;
 	u32 reg;
 
-	reg = readl(priv->control1);
+	regmap_read(priv->syscon, data->syscon_control1_off, &reg);
 	reg &= ~(A375_UNIT_CONTROL_MASK << A375_UNIT_CONTROL_SHIFT);
 	reg &= ~A375_READOUT_INVERT;
 	reg &= ~A375_HW_RESETn;
+	regmap_write(priv->syscon, data->syscon_control1_off, reg);
 
-	writel(reg, priv->control1);
 	msleep(20);
 
 	reg |= A375_HW_RESETn;
-	writel(reg, priv->control1);
+	regmap_write(priv->syscon, data->syscon_control1_off, reg);
+
 	msleep(50);
 }
 
-static void armada_wait_sensor_validity(struct armada_thermal_priv *priv)
+static int armada_wait_sensor_validity(struct armada_thermal_priv *priv)
 {
 	u32 reg;
 
-	readl_relaxed_poll_timeout(priv->status, reg,
-				   reg & priv->data->is_valid_bit,
-				   STATUS_POLL_PERIOD_US,
-				   STATUS_POLL_TIMEOUT_US);
+	return regmap_read_poll_timeout(priv->syscon,
+					priv->data->syscon_status_off, reg,
+					reg & priv->data->is_valid_bit,
+					STATUS_POLL_PERIOD_US,
+					STATUS_POLL_TIMEOUT_US);
 }
 
-static void armada380_init_sensor(struct platform_device *pdev,
-				  struct armada_thermal_priv *priv)
+static void armada380_init(struct platform_device *pdev,
+			   struct armada_thermal_priv *priv)
 {
-	u32 reg = readl_relaxed(priv->control1);
+	struct armada_thermal_data *data = priv->data;
+	u32 reg;
 
 	/* Disable the HW/SW reset */
+	regmap_read(priv->syscon, data->syscon_control1_off, &reg);
 	reg |= CONTROL1_EXT_TSEN_HW_RESETn;
 	reg &= ~CONTROL1_EXT_TSEN_SW_RESET;
-	writel(reg, priv->control1);
+	regmap_write(priv->syscon, data->syscon_control1_off, reg);
 
 	/* Set Tsen Tc Trim to correct default value (errata #132698) */
-	if (priv->control0) {
-		reg = readl_relaxed(priv->control0);
-		reg &= ~CONTROL0_TSEN_TC_TRIM_MASK;
-		reg |= CONTROL0_TSEN_TC_TRIM_VAL;
-		writel(reg, priv->control0);
-	}
-
-	/* Wait the sensors to be valid or the core will warn the user */
-	armada_wait_sensor_validity(priv);
+	regmap_read(priv->syscon, data->syscon_control0_off, &reg);
+	reg &= ~CONTROL0_TSEN_TC_TRIM_MASK;
+	reg |= CONTROL0_TSEN_TC_TRIM_VAL;
+	regmap_write(priv->syscon, data->syscon_control0_off, reg);
 }
 
-static void armada_ap806_init_sensor(struct platform_device *pdev,
-				     struct armada_thermal_priv *priv)
+static void armada_ap806_init(struct platform_device *pdev,
+			      struct armada_thermal_priv *priv)
 {
+	struct armada_thermal_data *data = priv->data;
 	u32 reg;
 
-	reg = readl_relaxed(priv->control0);
+	regmap_read(priv->syscon, data->syscon_control0_off, &reg);
 	reg &= ~CONTROL0_TSEN_RESET;
 	reg |= CONTROL0_TSEN_START | CONTROL0_TSEN_ENABLE;
-	writel(reg, priv->control0);
 
-	/* Wait the sensors to be valid or the core will warn the user */
-	armada_wait_sensor_validity(priv);
+	/* Sample every ~2ms */
+	reg |= CONTROL0_TSEN_OSR_MAX << CONTROL0_TSEN_OSR_SHIFT;
+
+	/* Enable average (2 samples by default) */
+	reg &= ~CONTROL0_TSEN_AVG_BYPASS;
+
+	regmap_write(priv->syscon, data->syscon_control0_off, reg);
+}
+
+static void armada_cp110_init(struct platform_device *pdev,
+			      struct armada_thermal_priv *priv)
+{
+	struct armada_thermal_data *data = priv->data;
+	u32 reg;
+
+	armada380_init(pdev, priv);
+
+	/* Sample every ~2ms */
+	regmap_read(priv->syscon, data->syscon_control0_off, &reg);
+	reg |= CONTROL0_TSEN_OSR_MAX << CONTROL0_TSEN_OSR_SHIFT;
+	regmap_write(priv->syscon, data->syscon_control0_off, reg);
+
+	/* Average the output value over 2^1 = 2 samples */
+	regmap_read(priv->syscon, data->syscon_control1_off, &reg);
+	reg &= ~CONTROL1_TSEN_AVG_MASK << CONTROL1_TSEN_AVG_SHIFT;
+	reg |= 1 << CONTROL1_TSEN_AVG_SHIFT;
+	regmap_write(priv->syscon, data->syscon_control1_off, reg);
 }
 
 static bool armada_is_valid(struct armada_thermal_priv *priv)
 {
-	u32 reg = readl_relaxed(priv->status);
+	u32 reg;
+
+	if (!priv->data->is_valid_bit)
+		return true;
+
+	regmap_read(priv->syscon, priv->data->syscon_status_off, &reg);
 
 	return reg & priv->data->is_valid_bit;
 }
 
-static int armada_get_temp(struct thermal_zone_device *thermal,
-			   int *temp)
+/* There is currently no board with more than one sensor per channel */
+static int armada_select_channel(struct armada_thermal_priv *priv, int channel)
 {
-	struct armada_thermal_priv *priv = thermal->devdata;
-	u32 reg, div;
-	s64 sample, b, m;
+	struct armada_thermal_data *data = priv->data;
+	u32 ctrl0;
+
+	if (channel < 0 || channel > priv->data->cpu_nr)
+		return -EINVAL;
+
+	if (priv->current_channel == channel)
+		return 0;
+
+	/* Stop the measurements */
+	regmap_read(priv->syscon, data->syscon_control0_off, &ctrl0);
+	ctrl0 &= ~CONTROL0_TSEN_START;
+	regmap_write(priv->syscon, data->syscon_control0_off, ctrl0);
+
+	/* Reset the mode, internal sensor will be automatically selected */
+	ctrl0 &= ~(CONTROL0_TSEN_MODE_MASK << CONTROL0_TSEN_MODE_SHIFT);
+
+	/* Other channels are external and should be selected accordingly */
+	if (channel) {
+		/* Change the mode to external */
+		ctrl0 |= CONTROL0_TSEN_MODE_EXTERNAL <<
+			 CONTROL0_TSEN_MODE_SHIFT;
+		/* Select the sensor */
+		ctrl0 &= ~(CONTROL0_TSEN_CHAN_MASK << CONTROL0_TSEN_CHAN_SHIFT);
+		ctrl0 |= (channel - 1) << CONTROL0_TSEN_CHAN_SHIFT;
+	}
 
-	/* Valid check */
-	if (priv->data->is_valid && !priv->data->is_valid(priv)) {
-		dev_err(&thermal->device,
+	/* Actually set the mode/channel */
+	regmap_write(priv->syscon, data->syscon_control0_off, ctrl0);
+	priv->current_channel = channel;
+
+	/* Re-start the measurements */
+	ctrl0 |= CONTROL0_TSEN_START;
+	regmap_write(priv->syscon, data->syscon_control0_off, ctrl0);
+
+	/*
+	 * The IP has a latency of ~15ms, so after updating the selected source,
+	 * we must absolutely wait for the sensor validity bit to ensure we read
+	 * actual data.
+	 */
+	if (armada_wait_sensor_validity(priv)) {
+		dev_err(priv->dev,
 			"Temperature sensor reading not valid\n");
 		return -EIO;
 	}
 
-	reg = readl_relaxed(priv->status);
+	return 0;
+}
+
+static int armada_read_sensor(struct armada_thermal_priv *priv, int *temp)
+{
+	u32 reg, div;
+	s64 sample, b, m;
+
+	regmap_read(priv->syscon, priv->data->syscon_status_off, &reg);
 	reg = (reg >> priv->data->temp_shift) & priv->data->temp_mask;
 	if (priv->data->signed_sample)
 		/* The most significant bit is the sign bit */
@@ -247,45 +350,93 @@ static int armada_get_temp(struct thermal_zone_device *thermal,
 	return 0;
 }
 
-static struct thermal_zone_device_ops ops = {
+static int armada_get_temp_legacy(struct thermal_zone_device *thermal,
+				  int *temp)
+{
+	struct armada_thermal_priv *priv = thermal->devdata;
+	int ret;
+
+	/* Valid check */
+	if (armada_is_valid(priv)) {
+		dev_err(priv->dev,
+			"Temperature sensor reading not valid\n");
+		return -EIO;
+	}
+
+	/* Do the actual reading */
+	ret = armada_read_sensor(priv, temp);
+
+	return ret;
+}
+
+static struct thermal_zone_device_ops legacy_ops = {
+	.get_temp = armada_get_temp_legacy,
+};
+
+static int armada_get_temp(void *_sensor, int *temp)
+{
+	struct armada_thermal_sensor *sensor = _sensor;
+	struct armada_thermal_priv *priv = sensor->priv;
+	int ret;
+
+	mutex_lock(&priv->update_lock);
+
+	/* Select the desired channel */
+	ret = armada_select_channel(priv, sensor->id);
+	if (ret)
+		goto unlock_mutex;
+
+	/* Do the actual reading */
+	ret = armada_read_sensor(priv, temp);
+
+unlock_mutex:
+	mutex_unlock(&priv->update_lock);
+
+	return ret;
+}
+
+static struct thermal_zone_of_device_ops of_ops = {
 	.get_temp = armada_get_temp,
 };
 
 static const struct armada_thermal_data armadaxp_data = {
-	.init_sensor = armadaxp_init_sensor,
+	.init = armadaxp_init,
 	.temp_shift = 10,
 	.temp_mask = 0x1ff,
 	.coef_b = 3153000000ULL,
 	.coef_m = 10000000ULL,
 	.coef_div = 13825,
+	.syscon_status_off = 0xb0,
+	.syscon_control1_off = 0xd0,
 };
 
 static const struct armada_thermal_data armada370_data = {
-	.is_valid = armada_is_valid,
-	.init_sensor = armada370_init_sensor,
+	.init = armada370_init,
 	.is_valid_bit = BIT(9),
 	.temp_shift = 10,
 	.temp_mask = 0x1ff,
 	.coef_b = 3153000000ULL,
 	.coef_m = 10000000ULL,
 	.coef_div = 13825,
+	.syscon_status_off = 0x0,
+	.syscon_control1_off = 0x4,
 };
 
 static const struct armada_thermal_data armada375_data = {
-	.is_valid = armada_is_valid,
-	.init_sensor = armada375_init_sensor,
+	.init = armada375_init,
 	.is_valid_bit = BIT(10),
 	.temp_shift = 0,
 	.temp_mask = 0x1ff,
 	.coef_b = 3171900000ULL,
 	.coef_m = 10000000ULL,
 	.coef_div = 13616,
-	.needs_control0 = true,
+	.syscon_status_off = 0x78,
+	.syscon_control0_off = 0x7c,
+	.syscon_control1_off = 0x80,
 };
 
 static const struct armada_thermal_data armada380_data = {
-	.is_valid = armada_is_valid,
-	.init_sensor = armada380_init_sensor,
+	.init = armada380_init,
 	.is_valid_bit = BIT(10),
 	.temp_shift = 0,
 	.temp_mask = 0x3ff,
@@ -293,11 +444,13 @@ static const struct armada_thermal_data armada380_data = {
 	.coef_m = 2000096ULL,
 	.coef_div = 4201,
 	.inverted = true,
+	.syscon_control0_off = 0x70,
+	.syscon_control1_off = 0x74,
+	.syscon_status_off = 0x78,
 };
 
 static const struct armada_thermal_data armada_ap806_data = {
-	.is_valid = armada_is_valid,
-	.init_sensor = armada_ap806_init_sensor,
+	.init = armada_ap806_init,
 	.is_valid_bit = BIT(16),
 	.temp_shift = 0,
 	.temp_mask = 0x3ff,
@@ -306,12 +459,14 @@ static const struct armada_thermal_data armada_ap806_data = {
 	.coef_div = 1,
 	.inverted = true,
 	.signed_sample = true,
-	.needs_control0 = true,
+	.syscon_control0_off = 0x84,
+	.syscon_control1_off = 0x88,
+	.syscon_status_off = 0x8C,
+	.cpu_nr = 4,
 };
 
 static const struct armada_thermal_data armada_cp110_data = {
-	.is_valid = armada_is_valid,
-	.init_sensor = armada380_init_sensor,
+	.init = armada_cp110_init,
 	.is_valid_bit = BIT(10),
 	.temp_shift = 0,
 	.temp_mask = 0x3ff,
@@ -319,7 +474,9 @@ static const struct armada_thermal_data armada_cp110_data = {
 	.coef_m = 2000096ULL,
 	.coef_div = 4201,
 	.inverted = true,
-	.needs_control0 = true,
+	.syscon_control0_off = 0x70,
+	.syscon_control1_off = 0x74,
+	.syscon_status_off = 0x78,
 };
 
 static const struct of_device_id armada_thermal_id_table[] = {
@@ -353,13 +510,97 @@ static const struct of_device_id armada_thermal_id_table[] = {
 };
 MODULE_DEVICE_TABLE(of, armada_thermal_id_table);
 
+static const struct regmap_config armada_thermal_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.fast_io = true,
+};
+
+static int armada_thermal_probe_legacy(struct platform_device *pdev,
+				       struct armada_thermal_priv *priv)
+{
+	struct armada_thermal_data *data = priv->data;
+	struct resource *res;
+	void __iomem *base;
+
+	/* First memory region points towards the status register */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (IS_ERR(res))
+		return PTR_ERR(res);
+
+	/*
+	 * Edit the resource start address and length to map over all the
+	 * registers, instead of pointing at them one by one.
+	 */
+	res->start -= data->syscon_status_off;
+	res->end = res->start + max(data->syscon_status_off,
+				    max(data->syscon_control0_off,
+					data->syscon_control1_off)) +
+		   sizeof(unsigned int) - 1;
+
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	priv->syscon = devm_regmap_init_mmio(&pdev->dev, base,
+					     &armada_thermal_regmap_config);
+	if (IS_ERR(priv->syscon))
+		return PTR_ERR(priv->syscon);
+
+	return 0;
+}
+
+static int armada_thermal_probe_syscon(struct platform_device *pdev,
+				       struct armada_thermal_priv *priv)
+{
+	priv->syscon = syscon_node_to_regmap(pdev->dev.parent->of_node);
+	if (IS_ERR(priv->syscon))
+		return PTR_ERR(priv->syscon);
+
+	return 0;
+}
+
+static void armada_set_sane_name(struct platform_device *pdev,
+				 struct armada_thermal_priv *priv)
+{
+	const char *name = dev_name(&pdev->dev);
+	char *insane_char;
+
+	if (strlen(name) > THERMAL_NAME_LENGTH) {
+		/*
+		 * When inside a system controller, the device name has the
+		 * form: f06f8000.system-controller:ap-thermal so stripping
+		 * after the ':' should give us a shorter but meaningful name.
+		 */
+		name = strrchr(name, ':');
+		if (!name)
+			name = "armada_thermal";
+		else
+			name++;
+	}
+
+	/* Save the name locally */
+	strncpy(priv->zone_name, name, THERMAL_NAME_LENGTH - 1);
+	priv->zone_name[THERMAL_NAME_LENGTH - 1] = '\0';
+
+	/* Then check there are no '-' or hwmon core will complain */
+	do {
+		insane_char = strpbrk(priv->zone_name, "-");
+		if (insane_char)
+			*insane_char = '_';
+	} while (insane_char);
+}
+
 static int armada_thermal_probe(struct platform_device *pdev)
 {
-	void __iomem *control = NULL;
-	struct thermal_zone_device *thermal;
+	struct thermal_zone_device *tz;
+	struct armada_thermal_sensor *sensor;
+	struct armada_drvdata *drvdata;
 	const struct of_device_id *match;
 	struct armada_thermal_priv *priv;
-	struct resource *res;
+	int sensor_id;
+	int ret;
 
 	match = of_match_device(armada_thermal_id_table, &pdev->dev);
 	if (!match)
@@ -369,58 +610,99 @@ static int armada_thermal_probe(struct platform_device *pdev)
 	if (!priv)
 		return -ENOMEM;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	priv->status = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(priv->status))
-		return PTR_ERR(priv->status);
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	control = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(control))
-		return PTR_ERR(control);
+	drvdata = devm_kzalloc(&pdev->dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
 
+	priv->dev = &pdev->dev;
 	priv->data = (struct armada_thermal_data *)match->data;
 
+	mutex_init(&priv->update_lock);
+
 	/*
 	 * Legacy DT bindings only described "control1" register (also referred
-	 * as "control MSB" on old documentation). New bindings cover
+	 * as "control MSB" on old documentation). Then, bindings moved to cover
 	 * "control0/control LSB" and "control1/control MSB" registers within
-	 * the same resource, which is then of size 8 instead of 4.
+	 * the same resource, which was then of size 8 instead of 4.
+	 *
+	 * The logic of defining sporadic registers is broken. For instance, it
+	 * blocked the addition of the overheat interrupt feature that needed
+	 * another resource somewhere else in the same memory area. One solution
+	 * is to define an overall system controller and put the thermal node
+	 * into it, which requires the use of regmaps across all the driver.
 	 */
-	if (resource_size(res) == LEGACY_CONTROL_MEM_LEN) {
-		/* ->control0 unavailable in this configuration */
-		if (priv->data->needs_control0) {
-			dev_err(&pdev->dev, "No access to control0 register\n");
-			return -EINVAL;
+	if (IS_ERR(syscon_node_to_regmap(pdev->dev.parent->of_node))) {
+		/* Ensure device name is correct for the thermal core */
+		armada_set_sane_name(pdev, priv);
+
+		ret = armada_thermal_probe_legacy(pdev, priv);
+		if (ret)
+			return ret;
+
+		priv->data->init(pdev, priv);
+
+		/* Wait the sensors to be valid */
+		armada_wait_sensor_validity(priv);
+
+		tz = thermal_zone_device_register(priv->zone_name, 0, 0, priv,
+						  &legacy_ops, NULL, 0, 0);
+		if (IS_ERR(tz)) {
+			dev_err(&pdev->dev,
+				"Failed to register thermal zone device\n");
+			return PTR_ERR(tz);
 		}
 
-		priv->control1 = control + LEGACY_CONTROL1_OFFSET;
-	} else {
-		priv->control0 = control + CONTROL0_OFFSET;
-		priv->control1 = control + CONTROL1_OFFSET;
+		drvdata->type = LEGACY;
+		drvdata->data.tz = tz;
+		platform_set_drvdata(pdev, drvdata);
+
+		return 0;
 	}
 
-	priv->data->init_sensor(pdev, priv);
+	ret = armada_thermal_probe_syscon(pdev, priv);
+	if (ret)
+		return ret;
 
-	thermal = thermal_zone_device_register(dev_name(&pdev->dev), 0, 0, priv,
-					       &ops, NULL, 0, 0);
-	if (IS_ERR(thermal)) {
-		dev_err(&pdev->dev,
-			"Failed to register thermal zone device\n");
-		return PTR_ERR(thermal);
-	}
+	priv->current_channel = -1;
+	priv->data->init(pdev, priv);
+	drvdata->type = SYSCON;
+	drvdata->data.priv = priv;
+	platform_set_drvdata(pdev, drvdata);
 
-	platform_set_drvdata(pdev, thermal);
+	/*
+	 * There is one channel for the IC and one per CPU (if any), each
+	 * channel has one sensor.
+	 */
+	for (sensor_id = 0; sensor_id <= priv->data->cpu_nr; sensor_id++) {
+		sensor = devm_kzalloc(&pdev->dev,
+				      sizeof(struct armada_thermal_sensor),
+				      GFP_KERNEL);
+		if (!sensor)
+			return -ENOMEM;
+
+		/* Register the sensor */
+		sensor->priv = priv;
+		sensor->id = sensor_id;
+		tz = devm_thermal_zone_of_sensor_register(&pdev->dev,
+							  sensor->id, sensor,
+							  &of_ops);
+		if (IS_ERR(tz)) {
+			dev_info(&pdev->dev, "Thermal sensor %d unavailable\n",
+				 sensor_id);
+			devm_kfree(&pdev->dev, sensor);
+			continue;
+		}
+	}
 
 	return 0;
 }
 
 static int armada_thermal_exit(struct platform_device *pdev)
 {
-	struct thermal_zone_device *armada_thermal =
-		platform_get_drvdata(pdev);
+	struct armada_drvdata *drvdata = platform_get_drvdata(pdev);
 
-	thermal_zone_device_unregister(armada_thermal);
+	if (drvdata->type == LEGACY)
+		thermal_zone_device_unregister(drvdata->data.tz);
 
 	return 0;
 }
diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c
index 334d98be03b9..aa452acb60b6 100644
--- a/drivers/thermal/imx_thermal.c
+++ b/drivers/thermal/imx_thermal.c
@@ -3,6 +3,7 @@
 // Copyright 2013 Freescale Semiconductor, Inc.
 
 #include <linux/clk.h>
+#include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/cpu_cooling.h>
 #include <linux/delay.h>
@@ -604,7 +605,10 @@ static int imx_init_from_nvmem_cells(struct platform_device *pdev)
 	ret = nvmem_cell_read_u32(&pdev->dev, "calib", &val);
 	if (ret)
 		return ret;
-	imx_init_calib(pdev, val);
+
+	ret = imx_init_calib(pdev, val);
+	if (ret)
+		return ret;
 
 	ret = nvmem_cell_read_u32(&pdev->dev, "temp_grade", &val);
 	if (ret)
@@ -644,6 +648,27 @@ static const struct of_device_id of_imx_thermal_match[] = {
 };
 MODULE_DEVICE_TABLE(of, of_imx_thermal_match);
 
+/*
+ * Create cooling device in case no #cooling-cells property is available in
+ * CPU node
+ */
+static int imx_thermal_register_legacy_cooling(struct imx_thermal_data *data)
+{
+	struct device_node *np = of_get_cpu_node(data->policy->cpu, NULL);
+	int ret;
+
+	if (!np || !of_find_property(np, "#cooling-cells", NULL)) {
+		data->cdev = cpufreq_cooling_register(data->policy);
+		if (IS_ERR(data->cdev)) {
+			ret = PTR_ERR(data->cdev);
+			cpufreq_cpu_put(data->policy);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
 static int imx_thermal_probe(struct platform_device *pdev)
 {
 	struct imx_thermal_data *data;
@@ -724,12 +749,10 @@ static int imx_thermal_probe(struct platform_device *pdev)
 		return -EPROBE_DEFER;
 	}
 
-	data->cdev = cpufreq_cooling_register(data->policy);
-	if (IS_ERR(data->cdev)) {
-		ret = PTR_ERR(data->cdev);
+	ret = imx_thermal_register_legacy_cooling(data);
+	if (ret) {
 		dev_err(&pdev->dev,
 			"failed to register cpufreq cooling device: %d\n", ret);
-		cpufreq_cpu_put(data->policy);
 		return ret;
 	}
 
diff --git a/drivers/thermal/qcom/Makefile b/drivers/thermal/qcom/Makefile
index 2cc2193637e7..a821929ede0b 100644
--- a/drivers/thermal/qcom/Makefile
+++ b/drivers/thermal/qcom/Makefile
@@ -1,2 +1,2 @@
 obj-$(CONFIG_QCOM_TSENS)	+= qcom_tsens.o
-qcom_tsens-y			+= tsens.o tsens-common.o tsens-8916.o tsens-8974.o tsens-8960.o tsens-8996.o
+qcom_tsens-y			+= tsens.o tsens-common.o tsens-8916.o tsens-8974.o tsens-8960.o tsens-v2.o
diff --git a/drivers/thermal/qcom/tsens-8996.c b/drivers/thermal/qcom/tsens-8996.c
deleted file mode 100644
index e1f77818d8fa..000000000000
--- a/drivers/thermal/qcom/tsens-8996.c
+++ /dev/null
@@ -1,84 +0,0 @@
-/*
- * Copyright (c) 2015, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#include <linux/platform_device.h>
-#include <linux/regmap.h>
-#include "tsens.h"
-
-#define STATUS_OFFSET	0x10a0
-#define LAST_TEMP_MASK	0xfff
-#define STATUS_VALID_BIT	BIT(21)
-#define CODE_SIGN_BIT		BIT(11)
-
-static int get_temp_8996(struct tsens_device *tmdev, int id, int *temp)
-{
-	struct tsens_sensor *s = &tmdev->sensor[id];
-	u32 code;
-	unsigned int sensor_addr;
-	int last_temp = 0, last_temp2 = 0, last_temp3 = 0, ret;
-
-	sensor_addr = STATUS_OFFSET + s->hw_id * 4;
-	ret = regmap_read(tmdev->map, sensor_addr, &code);
-	if (ret)
-		return ret;
-	last_temp = code & LAST_TEMP_MASK;
-	if (code & STATUS_VALID_BIT)
-		goto done;
-
-	/* Try a second time */
-	ret = regmap_read(tmdev->map, sensor_addr, &code);
-	if (ret)
-		return ret;
-	if (code & STATUS_VALID_BIT) {
-		last_temp = code & LAST_TEMP_MASK;
-		goto done;
-	} else {
-		last_temp2 = code & LAST_TEMP_MASK;
-	}
-
-	/* Try a third/last time */
-	ret = regmap_read(tmdev->map, sensor_addr, &code);
-	if (ret)
-		return ret;
-	if (code & STATUS_VALID_BIT) {
-		last_temp = code & LAST_TEMP_MASK;
-		goto done;
-	} else {
-		last_temp3 = code & LAST_TEMP_MASK;
-	}
-
-	if (last_temp == last_temp2)
-		last_temp = last_temp2;
-	else if (last_temp2 == last_temp3)
-		last_temp = last_temp3;
-done:
-	/* Code sign bit is the sign extension for a negative value */
-	if (last_temp & CODE_SIGN_BIT)
-		last_temp |= ~CODE_SIGN_BIT;
-
-	/* Temperatures are in deciCelicius */
-	*temp = last_temp * 100;
-
-	return 0;
-}
-
-static const struct tsens_ops ops_8996 = {
-	.init		= init_common,
-	.get_temp	= get_temp_8996,
-};
-
-const struct tsens_data data_8996 = {
-	.num_sensors	= 13,
-	.ops		= &ops_8996,
-};
diff --git a/drivers/thermal/qcom/tsens-common.c b/drivers/thermal/qcom/tsens-common.c
index b1449ad67fc0..6207d8d92351 100644
--- a/drivers/thermal/qcom/tsens-common.c
+++ b/drivers/thermal/qcom/tsens-common.c
@@ -16,6 +16,7 @@
 #include <linux/io.h>
 #include <linux/nvmem-consumer.h>
 #include <linux/of_address.h>
+#include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include "tsens.h"
@@ -103,11 +104,11 @@ int get_temp_common(struct tsens_device *tmdev, int id, int *temp)
 {
 	struct tsens_sensor *s = &tmdev->sensor[id];
 	u32 code;
-	unsigned int sensor_addr;
+	unsigned int status_reg;
 	int last_temp = 0, ret;
 
-	sensor_addr = S0_ST_ADDR + s->hw_id * SN_ADDR_OFFSET;
-	ret = regmap_read(tmdev->map, sensor_addr, &code);
+	status_reg = S0_ST_ADDR + s->hw_id * SN_ADDR_OFFSET;
+	ret = regmap_read(tmdev->map, status_reg, &code);
 	if (ret)
 		return ret;
 	last_temp = code & SN_ST_TEMP_MASK;
@@ -126,16 +127,28 @@ static const struct regmap_config tsens_config = {
 int __init init_common(struct tsens_device *tmdev)
 {
 	void __iomem *base;
+	struct resource *res;
+	struct platform_device *op = of_find_device_by_node(tmdev->dev->of_node);
 
-	base = of_iomap(tmdev->dev->of_node, 0);
-	if (!base)
+	if (!op)
 		return -EINVAL;
 
+	/* The driver only uses the TM register address space for now */
+	if (op->num_resources > 1) {
+		tmdev->tm_offset = 0;
+	} else {
+		/* old DTs where SROT and TM were in a contiguous 2K block */
+		tmdev->tm_offset = 0x1000;
+	}
+
+	res = platform_get_resource(op, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(&op->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
 	tmdev->map = devm_regmap_init_mmio(tmdev->dev, base, &tsens_config);
-	if (IS_ERR(tmdev->map)) {
-		iounmap(base);
+	if (IS_ERR(tmdev->map))
 		return PTR_ERR(tmdev->map);
-	}
 
 	return 0;
 }
diff --git a/drivers/thermal/qcom/tsens-v2.c b/drivers/thermal/qcom/tsens-v2.c
new file mode 100644
index 000000000000..44da02f594ac
--- /dev/null
+++ b/drivers/thermal/qcom/tsens-v2.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2015, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2018, Linaro Limited
+ */
+
+#include <linux/regmap.h>
+#include <linux/bitops.h>
+#include "tsens.h"
+
+#define STATUS_OFFSET		0xa0
+#define LAST_TEMP_MASK		0xfff
+#define STATUS_VALID_BIT	BIT(21)
+
+static int get_temp_tsens_v2(struct tsens_device *tmdev, int id, int *temp)
+{
+	struct tsens_sensor *s = &tmdev->sensor[id];
+	u32 code;
+	unsigned int status_reg;
+	u32 last_temp = 0, last_temp2 = 0, last_temp3 = 0;
+	int ret;
+
+	status_reg = tmdev->tm_offset + STATUS_OFFSET + s->hw_id * 4;
+	ret = regmap_read(tmdev->map, status_reg, &code);
+	if (ret)
+		return ret;
+	last_temp = code & LAST_TEMP_MASK;
+	if (code & STATUS_VALID_BIT)
+		goto done;
+
+	/* Try a second time */
+	ret = regmap_read(tmdev->map, status_reg, &code);
+	if (ret)
+		return ret;
+	if (code & STATUS_VALID_BIT) {
+		last_temp = code & LAST_TEMP_MASK;
+		goto done;
+	} else {
+		last_temp2 = code & LAST_TEMP_MASK;
+	}
+
+	/* Try a third/last time */
+	ret = regmap_read(tmdev->map, status_reg, &code);
+	if (ret)
+		return ret;
+	if (code & STATUS_VALID_BIT) {
+		last_temp = code & LAST_TEMP_MASK;
+		goto done;
+	} else {
+		last_temp3 = code & LAST_TEMP_MASK;
+	}
+
+	if (last_temp == last_temp2)
+		last_temp = last_temp2;
+	else if (last_temp2 == last_temp3)
+		last_temp = last_temp3;
+done:
+	/* Convert temperature from deciCelsius to milliCelsius */
+	*temp = sign_extend32(last_temp, fls(LAST_TEMP_MASK) - 1) * 100;
+
+	return 0;
+}
+
+static const struct tsens_ops ops_generic_v2 = {
+	.init		= init_common,
+	.get_temp	= get_temp_tsens_v2,
+};
+
+const struct tsens_data data_tsens_v2 = {
+	.ops            = &ops_generic_v2,
+};
+
+/* Kept around for backward compatibility with old msm8996.dtsi */
+const struct tsens_data data_8996 = {
+	.num_sensors	= 13,
+	.ops		= &ops_generic_v2,
+};
diff --git a/drivers/thermal/qcom/tsens.c b/drivers/thermal/qcom/tsens.c
index 3440166c2ae9..a2c9bfae3d86 100644
--- a/drivers/thermal/qcom/tsens.c
+++ b/drivers/thermal/qcom/tsens.c
@@ -72,6 +72,9 @@ static const struct of_device_id tsens_table[] = {
 	}, {
 		.compatible = "qcom,msm8996-tsens",
 		.data = &data_8996,
+	}, {
+		.compatible = "qcom,tsens-v2",
+		.data = &data_tsens_v2,
 	},
 	{}
 };
diff --git a/drivers/thermal/qcom/tsens.h b/drivers/thermal/qcom/tsens.h
index 911c1978892b..14331eb45a86 100644
--- a/drivers/thermal/qcom/tsens.h
+++ b/drivers/thermal/qcom/tsens.h
@@ -77,9 +77,8 @@ struct tsens_device {
 	struct device			*dev;
 	u32				num_sensors;
 	struct regmap			*map;
-	struct regmap_field		*status_field;
+	u32				tm_offset;
 	struct tsens_context		ctx;
-	bool				trdy;
 	const struct tsens_ops		*ops;
 	struct tsens_sensor		sensor[0];
 };
@@ -89,6 +88,9 @@ void compute_intercept_slope(struct tsens_device *, u32 *, u32 *, u32);
 int init_common(struct tsens_device *);
 int get_temp_common(struct tsens_device *, int, int *);
 
-extern const struct tsens_data data_8916, data_8974, data_8960, data_8996;
+/* TSENS v1 targets */
+extern const struct tsens_data data_8916, data_8974, data_8960;
+/* TSENS v2 targets */
+extern const struct tsens_data data_8996, data_tsens_v2;
 
 #endif /* __QCOM_TSENS_H__ */
diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c
index 45fb284d4c11..e77e63070e99 100644
--- a/drivers/thermal/rcar_thermal.c
+++ b/drivers/thermal/rcar_thermal.c
@@ -598,7 +598,7 @@ static int rcar_thermal_probe(struct platform_device *pdev)
 			enr_bits |= 3 << (i * 8);
 	}
 
-	if (enr_bits)
+	if (common->base && enr_bits)
 		rcar_thermal_common_write(common, ENR, enr_bits);
 
 	dev_info(dev, "%d sensor probed\n", i);
diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c
index a992e51ef065..48eef552cba4 100644
--- a/drivers/thermal/samsung/exynos_tmu.c
+++ b/drivers/thermal/samsung/exynos_tmu.c
@@ -789,11 +789,6 @@ static void exynos_tmu_work(struct work_struct *work)
 	struct exynos_tmu_data *data = container_of(work,
 			struct exynos_tmu_data, irq_work);
 
-	if (!IS_ERR(data->clk_sec))
-		clk_enable(data->clk_sec);
-	if (!IS_ERR(data->clk_sec))
-		clk_disable(data->clk_sec);
-
 	thermal_zone_device_update(data->tzd, THERMAL_EVENT_UNSPECIFIED);
 
 	mutex_lock(&data->lock);
diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c
index 11278836ed12..40c69a533b24 100644
--- a/drivers/thermal/thermal_hwmon.c
+++ b/drivers/thermal/thermal_hwmon.c
@@ -142,7 +142,8 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
 
 	INIT_LIST_HEAD(&hwmon->tz_list);
 	strlcpy(hwmon->type, tz->type, THERMAL_NAME_LENGTH);
-	hwmon->device = hwmon_device_register_with_info(NULL, hwmon->type,
+	strreplace(hwmon->type, '-', '_');
+	hwmon->device = hwmon_device_register_with_info(&tz->device, hwmon->type,
 							hwmon, NULL, NULL);
 	if (IS_ERR(hwmon->device)) {
 		result = PTR_ERR(hwmon->device);
diff --git a/drivers/thermal/ti-soc-thermal/dra752-bandgap.h b/drivers/thermal/ti-soc-thermal/dra752-bandgap.h
index a31e4b5e82cd..9490cd63fa6a 100644
--- a/drivers/thermal/ti-soc-thermal/dra752-bandgap.h
+++ b/drivers/thermal/ti-soc-thermal/dra752-bandgap.h
@@ -54,56 +54,36 @@
 #define DRA752_STD_FUSE_OPP_BGAP_CORE_OFFSET		0x8
 #define DRA752_TEMP_SENSOR_CORE_OFFSET			0x154
 #define DRA752_BANDGAP_THRESHOLD_CORE_OFFSET		0x1ac
-#define DRA752_BANDGAP_CUMUL_DTEMP_CORE_OFFSET		0x1c4
-#define DRA752_DTEMP_CORE_0_OFFSET			0x208
 #define DRA752_DTEMP_CORE_1_OFFSET			0x20c
 #define DRA752_DTEMP_CORE_2_OFFSET			0x210
-#define DRA752_DTEMP_CORE_3_OFFSET			0x214
-#define DRA752_DTEMP_CORE_4_OFFSET			0x218
 
 /* DRA752.iva register offsets */
 #define DRA752_STD_FUSE_OPP_BGAP_IVA_OFFSET		0x388
 #define DRA752_TEMP_SENSOR_IVA_OFFSET			0x398
 #define DRA752_BANDGAP_THRESHOLD_IVA_OFFSET		0x3a4
-#define DRA752_BANDGAP_CUMUL_DTEMP_IVA_OFFSET		0x3b4
-#define DRA752_DTEMP_IVA_0_OFFSET			0x3d0
 #define DRA752_DTEMP_IVA_1_OFFSET			0x3d4
 #define DRA752_DTEMP_IVA_2_OFFSET			0x3d8
-#define DRA752_DTEMP_IVA_3_OFFSET			0x3dc
-#define DRA752_DTEMP_IVA_4_OFFSET			0x3e0
 
 /* DRA752.mpu register offsets */
 #define DRA752_STD_FUSE_OPP_BGAP_MPU_OFFSET		0x4
 #define DRA752_TEMP_SENSOR_MPU_OFFSET			0x14c
 #define DRA752_BANDGAP_THRESHOLD_MPU_OFFSET		0x1a4
-#define DRA752_BANDGAP_CUMUL_DTEMP_MPU_OFFSET		0x1bc
-#define DRA752_DTEMP_MPU_0_OFFSET			0x1e0
 #define DRA752_DTEMP_MPU_1_OFFSET			0x1e4
 #define DRA752_DTEMP_MPU_2_OFFSET			0x1e8
-#define DRA752_DTEMP_MPU_3_OFFSET			0x1ec
-#define DRA752_DTEMP_MPU_4_OFFSET			0x1f0
 
 /* DRA752.dspeve register offsets */
 #define DRA752_STD_FUSE_OPP_BGAP_DSPEVE_OFFSET			0x384
 #define DRA752_TEMP_SENSOR_DSPEVE_OFFSET			0x394
 #define DRA752_BANDGAP_THRESHOLD_DSPEVE_OFFSET			0x3a0
-#define DRA752_BANDGAP_CUMUL_DTEMP_DSPEVE_OFFSET		0x3b0
-#define DRA752_DTEMP_DSPEVE_0_OFFSET				0x3bc
 #define DRA752_DTEMP_DSPEVE_1_OFFSET				0x3c0
 #define DRA752_DTEMP_DSPEVE_2_OFFSET				0x3c4
-#define DRA752_DTEMP_DSPEVE_3_OFFSET				0x3c8
-#define DRA752_DTEMP_DSPEVE_4_OFFSET				0x3cc
 
 /* DRA752.gpu register offsets */
 #define DRA752_STD_FUSE_OPP_BGAP_GPU_OFFSET		0x0
 #define DRA752_TEMP_SENSOR_GPU_OFFSET			0x150
 #define DRA752_BANDGAP_THRESHOLD_GPU_OFFSET		0x1a8
-#define DRA752_BANDGAP_CUMUL_DTEMP_GPU_OFFSET		0x1c0
-#define DRA752_DTEMP_GPU_0_OFFSET			0x1f4
 #define DRA752_DTEMP_GPU_1_OFFSET			0x1f8
 #define DRA752_DTEMP_GPU_2_OFFSET			0x1fc
-#define DRA752_DTEMP_GPU_3_OFFSET			0x200
-#define DRA752_DTEMP_GPU_4_OFFSET			0x204
 
 /**
  * Register bitfields for DRA752
@@ -114,7 +94,6 @@
  */
 
 /* DRA752.BANDGAP_STATUS_1 */
-#define DRA752_BANDGAP_STATUS_1_ALERT_MASK		BIT(31)
 #define DRA752_BANDGAP_STATUS_1_HOT_CORE_MASK		BIT(5)
 #define DRA752_BANDGAP_STATUS_1_COLD_CORE_MASK		BIT(4)
 #define DRA752_BANDGAP_STATUS_1_HOT_GPU_MASK		BIT(3)
@@ -125,10 +104,6 @@
 /* DRA752.BANDGAP_CTRL_2 */
 #define DRA752_BANDGAP_CTRL_2_FREEZE_IVA_MASK			BIT(22)
 #define DRA752_BANDGAP_CTRL_2_FREEZE_DSPEVE_MASK		BIT(21)
-#define DRA752_BANDGAP_CTRL_2_CLEAR_IVA_MASK			BIT(19)
-#define DRA752_BANDGAP_CTRL_2_CLEAR_DSPEVE_MASK			BIT(18)
-#define DRA752_BANDGAP_CTRL_2_CLEAR_ACCUM_IVA_MASK		BIT(16)
-#define DRA752_BANDGAP_CTRL_2_CLEAR_ACCUM_DSPEVE_MASK		BIT(15)
 #define DRA752_BANDGAP_CTRL_2_MASK_HOT_IVA_MASK			BIT(3)
 #define DRA752_BANDGAP_CTRL_2_MASK_COLD_IVA_MASK		BIT(2)
 #define DRA752_BANDGAP_CTRL_2_MASK_HOT_DSPEVE_MASK		BIT(1)
@@ -141,17 +116,10 @@
 #define DRA752_BANDGAP_STATUS_2_COLD_DSPEVE_MASK		BIT(0)
 
 /* DRA752.BANDGAP_CTRL_1 */
-#define DRA752_BANDGAP_CTRL_1_SIDLEMODE_MASK			(0x3 << 30)
 #define DRA752_BANDGAP_CTRL_1_COUNTER_DELAY_MASK		(0x7 << 27)
 #define DRA752_BANDGAP_CTRL_1_FREEZE_CORE_MASK			BIT(23)
 #define DRA752_BANDGAP_CTRL_1_FREEZE_GPU_MASK			BIT(22)
 #define DRA752_BANDGAP_CTRL_1_FREEZE_MPU_MASK			BIT(21)
-#define DRA752_BANDGAP_CTRL_1_CLEAR_CORE_MASK			BIT(20)
-#define DRA752_BANDGAP_CTRL_1_CLEAR_GPU_MASK			BIT(19)
-#define DRA752_BANDGAP_CTRL_1_CLEAR_MPU_MASK			BIT(18)
-#define DRA752_BANDGAP_CTRL_1_CLEAR_ACCUM_CORE_MASK		BIT(17)
-#define DRA752_BANDGAP_CTRL_1_CLEAR_ACCUM_GPU_MASK		BIT(16)
-#define DRA752_BANDGAP_CTRL_1_CLEAR_ACCUM_MPU_MASK		BIT(15)
 #define DRA752_BANDGAP_CTRL_1_MASK_HOT_CORE_MASK		BIT(5)
 #define DRA752_BANDGAP_CTRL_1_MASK_COLD_CORE_MASK		BIT(4)
 #define DRA752_BANDGAP_CTRL_1_MASK_HOT_GPU_MASK			BIT(3)
@@ -168,22 +136,6 @@
 #define DRA752_BANDGAP_THRESHOLD_HOT_MASK		(0x3ff << 16)
 #define DRA752_BANDGAP_THRESHOLD_COLD_MASK		(0x3ff << 0)
 
-
-/* DRA752.BANDGAP_CUMUL_DTEMP_CORE */
-#define DRA752_BANDGAP_CUMUL_DTEMP_CORE_MASK		(0xffffffff << 0)
-
-/* DRA752.BANDGAP_CUMUL_DTEMP_IVA */
-#define DRA752_BANDGAP_CUMUL_DTEMP_IVA_MASK		(0xffffffff << 0)
-
-/* DRA752.BANDGAP_CUMUL_DTEMP_MPU */
-#define DRA752_BANDGAP_CUMUL_DTEMP_MPU_MASK		(0xffffffff << 0)
-
-/* DRA752.BANDGAP_CUMUL_DTEMP_DSPEVE */
-#define DRA752_BANDGAP_CUMUL_DTEMP_DSPEVE_MASK		(0xffffffff << 0)
-
-/* DRA752.BANDGAP_CUMUL_DTEMP_GPU */
-#define DRA752_BANDGAP_CUMUL_DTEMP_GPU_MASK		(0xffffffff << 0)
-
 /**
  * Temperature limits and thresholds for DRA752
  *
@@ -202,10 +154,6 @@
 /* bandgap clock limits */
 #define DRA752_GPU_MAX_FREQ				1500000
 #define DRA752_GPU_MIN_FREQ				1000000
-/* sensor limits */
-#define DRA752_GPU_MIN_TEMP				-40000
-#define DRA752_GPU_MAX_TEMP				125000
-#define DRA752_GPU_HYST_VAL				5000
 /* interrupts thresholds */
 #define DRA752_GPU_T_HOT				800
 #define DRA752_GPU_T_COLD				795
@@ -214,10 +162,6 @@
 /* bandgap clock limits */
 #define DRA752_MPU_MAX_FREQ				1500000
 #define DRA752_MPU_MIN_FREQ				1000000
-/* sensor limits */
-#define DRA752_MPU_MIN_TEMP				-40000
-#define DRA752_MPU_MAX_TEMP				125000
-#define DRA752_MPU_HYST_VAL				5000
 /* interrupts thresholds */
 #define DRA752_MPU_T_HOT				800
 #define DRA752_MPU_T_COLD				795
@@ -226,10 +170,6 @@
 /* bandgap clock limits */
 #define DRA752_CORE_MAX_FREQ				1500000
 #define DRA752_CORE_MIN_FREQ				1000000
-/* sensor limits */
-#define DRA752_CORE_MIN_TEMP				-40000
-#define DRA752_CORE_MAX_TEMP				125000
-#define DRA752_CORE_HYST_VAL				5000
 /* interrupts thresholds */
 #define DRA752_CORE_T_HOT				800
 #define DRA752_CORE_T_COLD				795
@@ -238,10 +178,6 @@
 /* bandgap clock limits */
 #define DRA752_DSPEVE_MAX_FREQ				1500000
 #define DRA752_DSPEVE_MIN_FREQ				1000000
-/* sensor limits */
-#define DRA752_DSPEVE_MIN_TEMP				-40000
-#define DRA752_DSPEVE_MAX_TEMP				125000
-#define DRA752_DSPEVE_HYST_VAL				5000
 /* interrupts thresholds */
 #define DRA752_DSPEVE_T_HOT				800
 #define DRA752_DSPEVE_T_COLD				795
@@ -250,10 +186,6 @@
 /* bandgap clock limits */
 #define DRA752_IVA_MAX_FREQ				1500000
 #define DRA752_IVA_MIN_FREQ				1000000
-/* sensor limits */
-#define DRA752_IVA_MIN_TEMP				-40000
-#define DRA752_IVA_MAX_TEMP				125000
-#define DRA752_IVA_HYST_VAL				5000
 /* interrupts thresholds */
 #define DRA752_IVA_T_HOT				800
 #define DRA752_IVA_T_COLD				795
diff --git a/drivers/thermal/ti-soc-thermal/dra752-thermal-data.c b/drivers/thermal/ti-soc-thermal/dra752-thermal-data.c
index 4167373327d9..33a3030aa3c0 100644
--- a/drivers/thermal/ti-soc-thermal/dra752-thermal-data.c
+++ b/drivers/thermal/ti-soc-thermal/dra752-thermal-data.c
@@ -41,24 +41,16 @@ dra752_core_temp_sensor_registers = {
 	.bgap_mask_ctrl = DRA752_BANDGAP_CTRL_1_OFFSET,
 	.mask_hot_mask = DRA752_BANDGAP_CTRL_1_MASK_HOT_CORE_MASK,
 	.mask_cold_mask = DRA752_BANDGAP_CTRL_1_MASK_COLD_CORE_MASK,
-	.mask_sidlemode_mask = DRA752_BANDGAP_CTRL_1_SIDLEMODE_MASK,
 	.mask_counter_delay_mask = DRA752_BANDGAP_CTRL_1_COUNTER_DELAY_MASK,
 	.mask_freeze_mask = DRA752_BANDGAP_CTRL_1_FREEZE_CORE_MASK,
-	.mask_clear_mask = DRA752_BANDGAP_CTRL_1_CLEAR_CORE_MASK,
-	.mask_clear_accum_mask = DRA752_BANDGAP_CTRL_1_CLEAR_ACCUM_CORE_MASK,
 	.bgap_threshold = DRA752_BANDGAP_THRESHOLD_CORE_OFFSET,
 	.threshold_thot_mask = DRA752_BANDGAP_THRESHOLD_HOT_MASK,
 	.threshold_tcold_mask = DRA752_BANDGAP_THRESHOLD_COLD_MASK,
 	.bgap_status = DRA752_BANDGAP_STATUS_1_OFFSET,
-	.status_bgap_alert_mask = DRA752_BANDGAP_STATUS_1_ALERT_MASK,
 	.status_hot_mask = DRA752_BANDGAP_STATUS_1_HOT_CORE_MASK,
 	.status_cold_mask = DRA752_BANDGAP_STATUS_1_COLD_CORE_MASK,
-	.bgap_cumul_dtemp = DRA752_BANDGAP_CUMUL_DTEMP_CORE_OFFSET,
-	.ctrl_dtemp_0 = DRA752_DTEMP_CORE_0_OFFSET,
 	.ctrl_dtemp_1 = DRA752_DTEMP_CORE_1_OFFSET,
 	.ctrl_dtemp_2 = DRA752_DTEMP_CORE_2_OFFSET,
-	.ctrl_dtemp_3 = DRA752_DTEMP_CORE_3_OFFSET,
-	.ctrl_dtemp_4 = DRA752_DTEMP_CORE_4_OFFSET,
 	.bgap_efuse = DRA752_STD_FUSE_OPP_BGAP_CORE_OFFSET,
 };
 
@@ -74,24 +66,16 @@ dra752_iva_temp_sensor_registers = {
 	.bgap_mask_ctrl = DRA752_BANDGAP_CTRL_2_OFFSET,
 	.mask_hot_mask = DRA752_BANDGAP_CTRL_2_MASK_HOT_IVA_MASK,
 	.mask_cold_mask = DRA752_BANDGAP_CTRL_2_MASK_COLD_IVA_MASK,
-	.mask_sidlemode_mask = DRA752_BANDGAP_CTRL_1_SIDLEMODE_MASK,
 	.mask_counter_delay_mask = DRA752_BANDGAP_CTRL_1_COUNTER_DELAY_MASK,
 	.mask_freeze_mask = DRA752_BANDGAP_CTRL_2_FREEZE_IVA_MASK,
-	.mask_clear_mask = DRA752_BANDGAP_CTRL_2_CLEAR_IVA_MASK,
-	.mask_clear_accum_mask = DRA752_BANDGAP_CTRL_2_CLEAR_ACCUM_IVA_MASK,
 	.bgap_threshold = DRA752_BANDGAP_THRESHOLD_IVA_OFFSET,
 	.threshold_thot_mask = DRA752_BANDGAP_THRESHOLD_HOT_MASK,
 	.threshold_tcold_mask = DRA752_BANDGAP_THRESHOLD_COLD_MASK,
 	.bgap_status = DRA752_BANDGAP_STATUS_2_OFFSET,
-	.status_bgap_alert_mask = DRA752_BANDGAP_STATUS_1_ALERT_MASK,
 	.status_hot_mask = DRA752_BANDGAP_STATUS_2_HOT_IVA_MASK,
 	.status_cold_mask = DRA752_BANDGAP_STATUS_2_COLD_IVA_MASK,
-	.bgap_cumul_dtemp = DRA752_BANDGAP_CUMUL_DTEMP_IVA_OFFSET,
-	.ctrl_dtemp_0 = DRA752_DTEMP_IVA_0_OFFSET,
 	.ctrl_dtemp_1 = DRA752_DTEMP_IVA_1_OFFSET,
 	.ctrl_dtemp_2 = DRA752_DTEMP_IVA_2_OFFSET,
-	.ctrl_dtemp_3 = DRA752_DTEMP_IVA_3_OFFSET,
-	.ctrl_dtemp_4 = DRA752_DTEMP_IVA_4_OFFSET,
 	.bgap_efuse = DRA752_STD_FUSE_OPP_BGAP_IVA_OFFSET,
 };
 
@@ -107,24 +91,16 @@ dra752_mpu_temp_sensor_registers = {
 	.bgap_mask_ctrl = DRA752_BANDGAP_CTRL_1_OFFSET,
 	.mask_hot_mask = DRA752_BANDGAP_CTRL_1_MASK_HOT_MPU_MASK,
 	.mask_cold_mask = DRA752_BANDGAP_CTRL_1_MASK_COLD_MPU_MASK,
-	.mask_sidlemode_mask = DRA752_BANDGAP_CTRL_1_SIDLEMODE_MASK,
 	.mask_counter_delay_mask = DRA752_BANDGAP_CTRL_1_COUNTER_DELAY_MASK,
 	.mask_freeze_mask = DRA752_BANDGAP_CTRL_1_FREEZE_MPU_MASK,
-	.mask_clear_mask = DRA752_BANDGAP_CTRL_1_CLEAR_MPU_MASK,
-	.mask_clear_accum_mask = DRA752_BANDGAP_CTRL_1_CLEAR_ACCUM_MPU_MASK,
 	.bgap_threshold = DRA752_BANDGAP_THRESHOLD_MPU_OFFSET,
 	.threshold_thot_mask = DRA752_BANDGAP_THRESHOLD_HOT_MASK,
 	.threshold_tcold_mask = DRA752_BANDGAP_THRESHOLD_COLD_MASK,
 	.bgap_status = DRA752_BANDGAP_STATUS_1_OFFSET,
-	.status_bgap_alert_mask = DRA752_BANDGAP_STATUS_1_ALERT_MASK,
 	.status_hot_mask = DRA752_BANDGAP_STATUS_1_HOT_MPU_MASK,
 	.status_cold_mask = DRA752_BANDGAP_STATUS_1_COLD_MPU_MASK,
-	.bgap_cumul_dtemp = DRA752_BANDGAP_CUMUL_DTEMP_MPU_OFFSET,
-	.ctrl_dtemp_0 = DRA752_DTEMP_MPU_0_OFFSET,
 	.ctrl_dtemp_1 = DRA752_DTEMP_MPU_1_OFFSET,
 	.ctrl_dtemp_2 = DRA752_DTEMP_MPU_2_OFFSET,
-	.ctrl_dtemp_3 = DRA752_DTEMP_MPU_3_OFFSET,
-	.ctrl_dtemp_4 = DRA752_DTEMP_MPU_4_OFFSET,
 	.bgap_efuse = DRA752_STD_FUSE_OPP_BGAP_MPU_OFFSET,
 };
 
@@ -140,24 +116,16 @@ dra752_dspeve_temp_sensor_registers = {
 	.bgap_mask_ctrl = DRA752_BANDGAP_CTRL_2_OFFSET,
 	.mask_hot_mask = DRA752_BANDGAP_CTRL_2_MASK_HOT_DSPEVE_MASK,
 	.mask_cold_mask = DRA752_BANDGAP_CTRL_2_MASK_COLD_DSPEVE_MASK,
-	.mask_sidlemode_mask = DRA752_BANDGAP_CTRL_1_SIDLEMODE_MASK,
 	.mask_counter_delay_mask = DRA752_BANDGAP_CTRL_1_COUNTER_DELAY_MASK,
 	.mask_freeze_mask = DRA752_BANDGAP_CTRL_2_FREEZE_DSPEVE_MASK,
-	.mask_clear_mask = DRA752_BANDGAP_CTRL_2_CLEAR_DSPEVE_MASK,
-	.mask_clear_accum_mask = DRA752_BANDGAP_CTRL_2_CLEAR_ACCUM_DSPEVE_MASK,
 	.bgap_threshold = DRA752_BANDGAP_THRESHOLD_DSPEVE_OFFSET,
 	.threshold_thot_mask = DRA752_BANDGAP_THRESHOLD_HOT_MASK,
 	.threshold_tcold_mask = DRA752_BANDGAP_THRESHOLD_COLD_MASK,
 	.bgap_status = DRA752_BANDGAP_STATUS_2_OFFSET,
-	.status_bgap_alert_mask = DRA752_BANDGAP_STATUS_1_ALERT_MASK,
 	.status_hot_mask = DRA752_BANDGAP_STATUS_2_HOT_DSPEVE_MASK,
 	.status_cold_mask = DRA752_BANDGAP_STATUS_2_COLD_DSPEVE_MASK,
-	.bgap_cumul_dtemp = DRA752_BANDGAP_CUMUL_DTEMP_DSPEVE_OFFSET,
-	.ctrl_dtemp_0 = DRA752_DTEMP_DSPEVE_0_OFFSET,
 	.ctrl_dtemp_1 = DRA752_DTEMP_DSPEVE_1_OFFSET,
 	.ctrl_dtemp_2 = DRA752_DTEMP_DSPEVE_2_OFFSET,
-	.ctrl_dtemp_3 = DRA752_DTEMP_DSPEVE_3_OFFSET,
-	.ctrl_dtemp_4 = DRA752_DTEMP_DSPEVE_4_OFFSET,
 	.bgap_efuse = DRA752_STD_FUSE_OPP_BGAP_DSPEVE_OFFSET,
 };
 
@@ -173,24 +141,16 @@ dra752_gpu_temp_sensor_registers = {
 	.bgap_mask_ctrl = DRA752_BANDGAP_CTRL_1_OFFSET,
 	.mask_hot_mask = DRA752_BANDGAP_CTRL_1_MASK_HOT_GPU_MASK,
 	.mask_cold_mask = DRA752_BANDGAP_CTRL_1_MASK_COLD_GPU_MASK,
-	.mask_sidlemode_mask = DRA752_BANDGAP_CTRL_1_SIDLEMODE_MASK,
 	.mask_counter_delay_mask = DRA752_BANDGAP_CTRL_1_COUNTER_DELAY_MASK,
 	.mask_freeze_mask = DRA752_BANDGAP_CTRL_1_FREEZE_GPU_MASK,
-	.mask_clear_mask = DRA752_BANDGAP_CTRL_1_CLEAR_GPU_MASK,
-	.mask_clear_accum_mask = DRA752_BANDGAP_CTRL_1_CLEAR_ACCUM_GPU_MASK,
 	.bgap_threshold = DRA752_BANDGAP_THRESHOLD_GPU_OFFSET,
 	.threshold_thot_mask = DRA752_BANDGAP_THRESHOLD_HOT_MASK,
 	.threshold_tcold_mask = DRA752_BANDGAP_THRESHOLD_COLD_MASK,
 	.bgap_status = DRA752_BANDGAP_STATUS_1_OFFSET,
-	.status_bgap_alert_mask = DRA752_BANDGAP_STATUS_1_ALERT_MASK,
 	.status_hot_mask = DRA752_BANDGAP_STATUS_1_HOT_GPU_MASK,
 	.status_cold_mask = DRA752_BANDGAP_STATUS_1_COLD_GPU_MASK,
-	.bgap_cumul_dtemp = DRA752_BANDGAP_CUMUL_DTEMP_GPU_OFFSET,
-	.ctrl_dtemp_0 = DRA752_DTEMP_GPU_0_OFFSET,
 	.ctrl_dtemp_1 = DRA752_DTEMP_GPU_1_OFFSET,
 	.ctrl_dtemp_2 = DRA752_DTEMP_GPU_2_OFFSET,
-	.ctrl_dtemp_3 = DRA752_DTEMP_GPU_3_OFFSET,
-	.ctrl_dtemp_4 = DRA752_DTEMP_GPU_4_OFFSET,
 	.bgap_efuse = DRA752_STD_FUSE_OPP_BGAP_GPU_OFFSET,
 };
 
@@ -200,11 +160,6 @@ static struct temp_sensor_data dra752_mpu_temp_sensor_data = {
 	.t_cold = DRA752_MPU_T_COLD,
 	.min_freq = DRA752_MPU_MIN_FREQ,
 	.max_freq = DRA752_MPU_MAX_FREQ,
-	.max_temp = DRA752_MPU_MAX_TEMP,
-	.min_temp = DRA752_MPU_MIN_TEMP,
-	.hyst_val = DRA752_MPU_HYST_VAL,
-	.update_int1 = 1000,
-	.update_int2 = 2000,
 };
 
 /* Thresholds and limits for DRA752 GPU temperature sensor */
@@ -213,11 +168,6 @@ static struct temp_sensor_data dra752_gpu_temp_sensor_data = {
 	.t_cold = DRA752_GPU_T_COLD,
 	.min_freq = DRA752_GPU_MIN_FREQ,
 	.max_freq = DRA752_GPU_MAX_FREQ,
-	.max_temp = DRA752_GPU_MAX_TEMP,
-	.min_temp = DRA752_GPU_MIN_TEMP,
-	.hyst_val = DRA752_GPU_HYST_VAL,
-	.update_int1 = 1000,
-	.update_int2 = 2000,
 };
 
 /* Thresholds and limits for DRA752 CORE temperature sensor */
@@ -226,11 +176,6 @@ static struct temp_sensor_data dra752_core_temp_sensor_data = {
 	.t_cold = DRA752_CORE_T_COLD,
 	.min_freq = DRA752_CORE_MIN_FREQ,
 	.max_freq = DRA752_CORE_MAX_FREQ,
-	.max_temp = DRA752_CORE_MAX_TEMP,
-	.min_temp = DRA752_CORE_MIN_TEMP,
-	.hyst_val = DRA752_CORE_HYST_VAL,
-	.update_int1 = 1000,
-	.update_int2 = 2000,
 };
 
 /* Thresholds and limits for DRA752 DSPEVE temperature sensor */
@@ -239,11 +184,6 @@ static struct temp_sensor_data dra752_dspeve_temp_sensor_data = {
 	.t_cold = DRA752_DSPEVE_T_COLD,
 	.min_freq = DRA752_DSPEVE_MIN_FREQ,
 	.max_freq = DRA752_DSPEVE_MAX_FREQ,
-	.max_temp = DRA752_DSPEVE_MAX_TEMP,
-	.min_temp = DRA752_DSPEVE_MIN_TEMP,
-	.hyst_val = DRA752_DSPEVE_HYST_VAL,
-	.update_int1 = 1000,
-	.update_int2 = 2000,
 };
 
 /* Thresholds and limits for DRA752 IVA temperature sensor */
@@ -252,11 +192,6 @@ static struct temp_sensor_data dra752_iva_temp_sensor_data = {
 	.t_cold = DRA752_IVA_T_COLD,
 	.min_freq = DRA752_IVA_MIN_FREQ,
 	.max_freq = DRA752_IVA_MAX_FREQ,
-	.max_temp = DRA752_IVA_MAX_TEMP,
-	.min_temp = DRA752_IVA_MIN_TEMP,
-	.hyst_val = DRA752_IVA_HYST_VAL,
-	.update_int1 = 1000,
-	.update_int2 = 2000,
 };
 
 /*
diff --git a/drivers/thermal/ti-soc-thermal/omap3-thermal-data.c b/drivers/thermal/ti-soc-thermal/omap3-thermal-data.c
index c6d217913dd1..f5366807daf0 100644
--- a/drivers/thermal/ti-soc-thermal/omap3-thermal-data.c
+++ b/drivers/thermal/ti-soc-thermal/omap3-thermal-data.c
@@ -48,9 +48,6 @@ omap34xx_mpu_temp_sensor_registers = {
 static struct temp_sensor_data omap34xx_mpu_temp_sensor_data = {
 	.min_freq = 32768,
 	.max_freq = 32768,
-	.max_temp = 125000,
-	.min_temp = -40000,
-	.hyst_val = 5000,
 };
 
 /*
@@ -119,9 +116,6 @@ omap36xx_mpu_temp_sensor_registers = {
 static struct temp_sensor_data omap36xx_mpu_temp_sensor_data = {
 	.min_freq = 32768,
 	.max_freq = 32768,
-	.max_temp = 125000,
-	.min_temp = -40000,
-	.hyst_val = 5000,
 };
 
 /*
diff --git a/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c b/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c
index fd1113360603..c12211eaaac4 100644
--- a/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c
+++ b/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c
@@ -42,9 +42,6 @@ omap4430_mpu_temp_sensor_registers = {
 static struct temp_sensor_data omap4430_mpu_temp_sensor_data = {
 	.min_freq = OMAP4430_MIN_FREQ,
 	.max_freq = OMAP4430_MAX_FREQ,
-	.max_temp = OMAP4430_MAX_TEMP,
-	.min_temp = OMAP4430_MIN_TEMP,
-	.hyst_val = OMAP4430_HYST_VAL,
 };
 
 /*
@@ -121,8 +118,6 @@ omap4460_mpu_temp_sensor_registers = {
 	.tshut_cold_mask = OMAP4460_TSHUT_COLD_MASK,
 
 	.bgap_status = OMAP4460_BGAP_STATUS_OFFSET,
-	.status_clean_stop_mask = OMAP4460_CLEAN_STOP_MASK,
-	.status_bgap_alert_mask = OMAP4460_BGAP_ALERT_MASK,
 	.status_hot_mask = OMAP4460_HOT_FLAG_MASK,
 	.status_cold_mask = OMAP4460_COLD_FLAG_MASK,
 
@@ -137,11 +132,6 @@ static struct temp_sensor_data omap4460_mpu_temp_sensor_data = {
 	.t_cold = OMAP4460_T_COLD,
 	.min_freq = OMAP4460_MIN_FREQ,
 	.max_freq = OMAP4460_MAX_FREQ,
-	.max_temp = OMAP4460_MAX_TEMP,
-	.min_temp = OMAP4460_MIN_TEMP,
-	.hyst_val = OMAP4460_HYST_VAL,
-	.update_int1 = 1000,
-	.update_int2 = 2000,
 };
 
 /*
diff --git a/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h b/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h
index 6f2de3a3356d..b87c8659ec60 100644
--- a/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h
+++ b/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h
@@ -73,10 +73,6 @@
 /* bandgap clock limits (no control on 4430) */
 #define OMAP4430_MAX_FREQ				32768
 #define OMAP4430_MIN_FREQ				32768
-/* sensor limits */
-#define OMAP4430_MIN_TEMP				-40000
-#define OMAP4430_MAX_TEMP				125000
-#define OMAP4430_HYST_VAL				5000
 
 /**
  * *** OMAP4460 *** Applicable for OMAP4470
@@ -143,8 +139,6 @@
 #define OMAP4460_TSHUT_COLD_MASK			(0x3ff << 0)
 
 /* OMAP4460.BANDGAP_STATUS bits */
-#define OMAP4460_CLEAN_STOP_MASK			BIT(3)
-#define OMAP4460_BGAP_ALERT_MASK			BIT(2)
 #define OMAP4460_HOT_FLAG_MASK				BIT(1)
 #define OMAP4460_COLD_FLAG_MASK				BIT(0)
 
@@ -162,10 +156,6 @@
 /* bandgap clock limits */
 #define OMAP4460_MAX_FREQ				1500000
 #define OMAP4460_MIN_FREQ				1000000
-/* sensor limits */
-#define OMAP4460_MIN_TEMP				-40000
-#define OMAP4460_MAX_TEMP				123000
-#define OMAP4460_HYST_VAL				5000
 /* interrupts thresholds */
 #define OMAP4460_TSHUT_HOT				900	/* 122 deg C */
 #define OMAP4460_TSHUT_COLD				895	/* 100 deg C */
diff --git a/drivers/thermal/ti-soc-thermal/omap5-thermal-data.c b/drivers/thermal/ti-soc-thermal/omap5-thermal-data.c
index 6ac037098b52..8191bae834de 100644
--- a/drivers/thermal/ti-soc-thermal/omap5-thermal-data.c
+++ b/drivers/thermal/ti-soc-thermal/omap5-thermal-data.c
@@ -38,12 +38,8 @@ omap5430_mpu_temp_sensor_registers = {
 	.bgap_mask_ctrl = OMAP5430_BGAP_CTRL_OFFSET,
 	.mask_hot_mask = OMAP5430_MASK_HOT_MPU_MASK,
 	.mask_cold_mask = OMAP5430_MASK_COLD_MPU_MASK,
-	.mask_sidlemode_mask = OMAP5430_MASK_SIDLEMODE_MASK,
 	.mask_counter_delay_mask = OMAP5430_MASK_COUNTER_DELAY_MASK,
 	.mask_freeze_mask = OMAP5430_MASK_FREEZE_MPU_MASK,
-	.mask_clear_mask = OMAP5430_MASK_CLEAR_MPU_MASK,
-	.mask_clear_accum_mask = OMAP5430_MASK_CLEAR_ACCUM_MPU_MASK,
-
 
 	.bgap_counter = OMAP5430_BGAP_CTRL_OFFSET,
 	.counter_mask = OMAP5430_COUNTER_MASK,
@@ -57,17 +53,11 @@ omap5430_mpu_temp_sensor_registers = {
 	.tshut_cold_mask = OMAP5430_TSHUT_COLD_MASK,
 
 	.bgap_status = OMAP5430_BGAP_STATUS_OFFSET,
-	.status_clean_stop_mask = 0x0,
-	.status_bgap_alert_mask = OMAP5430_BGAP_ALERT_MASK,
 	.status_hot_mask = OMAP5430_HOT_MPU_FLAG_MASK,
 	.status_cold_mask = OMAP5430_COLD_MPU_FLAG_MASK,
 
-	.bgap_cumul_dtemp = OMAP5430_BGAP_CUMUL_DTEMP_MPU_OFFSET,
-	.ctrl_dtemp_0 = OMAP5430_BGAP_DTEMP_MPU_0_OFFSET,
 	.ctrl_dtemp_1 = OMAP5430_BGAP_DTEMP_MPU_1_OFFSET,
 	.ctrl_dtemp_2 = OMAP5430_BGAP_DTEMP_MPU_2_OFFSET,
-	.ctrl_dtemp_3 = OMAP5430_BGAP_DTEMP_MPU_3_OFFSET,
-	.ctrl_dtemp_4 = OMAP5430_BGAP_DTEMP_MPU_4_OFFSET,
 	.bgap_efuse = OMAP5430_FUSE_OPP_BGAP_MPU,
 };
 
@@ -84,11 +74,8 @@ omap5430_gpu_temp_sensor_registers = {
 	.bgap_mask_ctrl = OMAP5430_BGAP_CTRL_OFFSET,
 	.mask_hot_mask = OMAP5430_MASK_HOT_GPU_MASK,
 	.mask_cold_mask = OMAP5430_MASK_COLD_GPU_MASK,
-	.mask_sidlemode_mask = OMAP5430_MASK_SIDLEMODE_MASK,
 	.mask_counter_delay_mask = OMAP5430_MASK_COUNTER_DELAY_MASK,
 	.mask_freeze_mask = OMAP5430_MASK_FREEZE_GPU_MASK,
-	.mask_clear_mask = OMAP5430_MASK_CLEAR_GPU_MASK,
-	.mask_clear_accum_mask = OMAP5430_MASK_CLEAR_ACCUM_GPU_MASK,
 
 	.bgap_counter = OMAP5430_BGAP_CTRL_OFFSET,
 	.counter_mask = OMAP5430_COUNTER_MASK,
@@ -102,17 +89,11 @@ omap5430_gpu_temp_sensor_registers = {
 	.tshut_cold_mask = OMAP5430_TSHUT_COLD_MASK,
 
 	.bgap_status = OMAP5430_BGAP_STATUS_OFFSET,
-	.status_clean_stop_mask = 0x0,
-	.status_bgap_alert_mask = OMAP5430_BGAP_ALERT_MASK,
 	.status_hot_mask = OMAP5430_HOT_GPU_FLAG_MASK,
 	.status_cold_mask = OMAP5430_COLD_GPU_FLAG_MASK,
 
-	.bgap_cumul_dtemp = OMAP5430_BGAP_CUMUL_DTEMP_GPU_OFFSET,
-	.ctrl_dtemp_0 = OMAP5430_BGAP_DTEMP_GPU_0_OFFSET,
 	.ctrl_dtemp_1 = OMAP5430_BGAP_DTEMP_GPU_1_OFFSET,
 	.ctrl_dtemp_2 = OMAP5430_BGAP_DTEMP_GPU_2_OFFSET,
-	.ctrl_dtemp_3 = OMAP5430_BGAP_DTEMP_GPU_3_OFFSET,
-	.ctrl_dtemp_4 = OMAP5430_BGAP_DTEMP_GPU_4_OFFSET,
 
 	.bgap_efuse = OMAP5430_FUSE_OPP_BGAP_GPU,
 };
@@ -130,11 +111,8 @@ omap5430_core_temp_sensor_registers = {
 	.bgap_mask_ctrl = OMAP5430_BGAP_CTRL_OFFSET,
 	.mask_hot_mask = OMAP5430_MASK_HOT_CORE_MASK,
 	.mask_cold_mask = OMAP5430_MASK_COLD_CORE_MASK,
-	.mask_sidlemode_mask = OMAP5430_MASK_SIDLEMODE_MASK,
 	.mask_counter_delay_mask = OMAP5430_MASK_COUNTER_DELAY_MASK,
 	.mask_freeze_mask = OMAP5430_MASK_FREEZE_CORE_MASK,
-	.mask_clear_mask = OMAP5430_MASK_CLEAR_CORE_MASK,
-	.mask_clear_accum_mask = OMAP5430_MASK_CLEAR_ACCUM_CORE_MASK,
 
 	.bgap_counter = OMAP5430_BGAP_CTRL_OFFSET,
 	.counter_mask = OMAP5430_COUNTER_MASK,
@@ -148,17 +126,11 @@ omap5430_core_temp_sensor_registers = {
 	.tshut_cold_mask = OMAP5430_TSHUT_COLD_MASK,
 
 	.bgap_status = OMAP5430_BGAP_STATUS_OFFSET,
-	.status_clean_stop_mask = 0x0,
-	.status_bgap_alert_mask = OMAP5430_BGAP_ALERT_MASK,
 	.status_hot_mask = OMAP5430_HOT_CORE_FLAG_MASK,
 	.status_cold_mask = OMAP5430_COLD_CORE_FLAG_MASK,
 
-	.bgap_cumul_dtemp = OMAP5430_BGAP_CUMUL_DTEMP_CORE_OFFSET,
-	.ctrl_dtemp_0 = OMAP5430_BGAP_DTEMP_CORE_0_OFFSET,
 	.ctrl_dtemp_1 = OMAP5430_BGAP_DTEMP_CORE_1_OFFSET,
 	.ctrl_dtemp_2 = OMAP5430_BGAP_DTEMP_CORE_2_OFFSET,
-	.ctrl_dtemp_3 = OMAP5430_BGAP_DTEMP_CORE_3_OFFSET,
-	.ctrl_dtemp_4 = OMAP5430_BGAP_DTEMP_CORE_4_OFFSET,
 
 	.bgap_efuse = OMAP5430_FUSE_OPP_BGAP_CORE,
 };
@@ -171,11 +143,6 @@ static struct temp_sensor_data omap5430_mpu_temp_sensor_data = {
 	.t_cold = OMAP5430_MPU_T_COLD,
 	.min_freq = OMAP5430_MPU_MIN_FREQ,
 	.max_freq = OMAP5430_MPU_MAX_FREQ,
-	.max_temp = OMAP5430_MPU_MAX_TEMP,
-	.min_temp = OMAP5430_MPU_MIN_TEMP,
-	.hyst_val = OMAP5430_MPU_HYST_VAL,
-	.update_int1 = 1000,
-	.update_int2 = 2000,
 };
 
 /* Thresholds and limits for OMAP5430 GPU temperature sensor */
@@ -186,11 +153,6 @@ static struct temp_sensor_data omap5430_gpu_temp_sensor_data = {
 	.t_cold = OMAP5430_GPU_T_COLD,
 	.min_freq = OMAP5430_GPU_MIN_FREQ,
 	.max_freq = OMAP5430_GPU_MAX_FREQ,
-	.max_temp = OMAP5430_GPU_MAX_TEMP,
-	.min_temp = OMAP5430_GPU_MIN_TEMP,
-	.hyst_val = OMAP5430_GPU_HYST_VAL,
-	.update_int1 = 1000,
-	.update_int2 = 2000,
 };
 
 /* Thresholds and limits for OMAP5430 CORE temperature sensor */
@@ -201,11 +163,6 @@ static struct temp_sensor_data omap5430_core_temp_sensor_data = {
 	.t_cold = OMAP5430_CORE_T_COLD,
 	.min_freq = OMAP5430_CORE_MIN_FREQ,
 	.max_freq = OMAP5430_CORE_MAX_FREQ,
-	.max_temp = OMAP5430_CORE_MAX_TEMP,
-	.min_temp = OMAP5430_CORE_MIN_TEMP,
-	.hyst_val = OMAP5430_CORE_HYST_VAL,
-	.update_int1 = 1000,
-	.update_int2 = 2000,
 };
 
 /*
@@ -319,8 +276,7 @@ const struct ti_bandgap_data omap5430_data = {
 			TI_BANDGAP_FEATURE_FREEZE_BIT |
 			TI_BANDGAP_FEATURE_TALERT |
 			TI_BANDGAP_FEATURE_COUNTER_DELAY |
-			TI_BANDGAP_FEATURE_HISTORY_BUFFER |
-			TI_BANDGAP_FEATURE_ERRATA_813,
+			TI_BANDGAP_FEATURE_HISTORY_BUFFER,
 	.fclock_name = "l3instr_ts_gclk_div",
 	.div_ck_name = "l3instr_ts_gclk_div",
 	.conv_table = omap5430_adc_to_temp,
diff --git a/drivers/thermal/ti-soc-thermal/omap5xxx-bandgap.h b/drivers/thermal/ti-soc-thermal/omap5xxx-bandgap.h
index 400b55dffadd..9096403b74b0 100644
--- a/drivers/thermal/ti-soc-thermal/omap5xxx-bandgap.h
+++ b/drivers/thermal/ti-soc-thermal/omap5xxx-bandgap.h
@@ -44,36 +44,24 @@
 #define OMAP5430_TEMP_SENSOR_GPU_OFFSET			0x150
 #define OMAP5430_BGAP_THRESHOLD_GPU_OFFSET		0x1A8
 #define OMAP5430_BGAP_TSHUT_GPU_OFFSET			0x1B4
-#define OMAP5430_BGAP_CUMUL_DTEMP_GPU_OFFSET		0x1C0
-#define OMAP5430_BGAP_DTEMP_GPU_0_OFFSET		0x1F4
 #define OMAP5430_BGAP_DTEMP_GPU_1_OFFSET		0x1F8
 #define OMAP5430_BGAP_DTEMP_GPU_2_OFFSET		0x1FC
-#define OMAP5430_BGAP_DTEMP_GPU_3_OFFSET		0x200
-#define OMAP5430_BGAP_DTEMP_GPU_4_OFFSET		0x204
 
 /* OMAP5430.MPU register offsets */
 #define OMAP5430_FUSE_OPP_BGAP_MPU			0x4
 #define OMAP5430_TEMP_SENSOR_MPU_OFFSET			0x14C
 #define OMAP5430_BGAP_THRESHOLD_MPU_OFFSET		0x1A4
 #define OMAP5430_BGAP_TSHUT_MPU_OFFSET			0x1B0
-#define OMAP5430_BGAP_CUMUL_DTEMP_MPU_OFFSET		0x1BC
-#define OMAP5430_BGAP_DTEMP_MPU_0_OFFSET		0x1E0
 #define OMAP5430_BGAP_DTEMP_MPU_1_OFFSET		0x1E4
 #define OMAP5430_BGAP_DTEMP_MPU_2_OFFSET		0x1E8
-#define OMAP5430_BGAP_DTEMP_MPU_3_OFFSET		0x1EC
-#define OMAP5430_BGAP_DTEMP_MPU_4_OFFSET		0x1F0
 
 /* OMAP5430.MPU register offsets */
 #define OMAP5430_FUSE_OPP_BGAP_CORE			0x8
 #define OMAP5430_TEMP_SENSOR_CORE_OFFSET		0x154
 #define OMAP5430_BGAP_THRESHOLD_CORE_OFFSET		0x1AC
 #define OMAP5430_BGAP_TSHUT_CORE_OFFSET			0x1B8
-#define OMAP5430_BGAP_CUMUL_DTEMP_CORE_OFFSET		0x1C4
-#define OMAP5430_BGAP_DTEMP_CORE_0_OFFSET		0x208
 #define OMAP5430_BGAP_DTEMP_CORE_1_OFFSET		0x20C
 #define OMAP5430_BGAP_DTEMP_CORE_2_OFFSET		0x210
-#define OMAP5430_BGAP_DTEMP_CORE_3_OFFSET		0x214
-#define OMAP5430_BGAP_DTEMP_CORE_4_OFFSET		0x218
 
 /* OMAP5430.common register offsets */
 #define OMAP5430_BGAP_CTRL_OFFSET			0x1A0
@@ -94,17 +82,10 @@
 #define OMAP5430_BGAP_TEMP_SENSOR_DTEMP_MASK		(0x3ff << 0)
 
 /* OMAP5430.BANDGAP_CTRL */
-#define OMAP5430_MASK_SIDLEMODE_MASK			(0x3 << 30)
 #define OMAP5430_MASK_COUNTER_DELAY_MASK		(0x7 << 27)
 #define OMAP5430_MASK_FREEZE_CORE_MASK			BIT(23)
 #define OMAP5430_MASK_FREEZE_GPU_MASK			BIT(22)
 #define OMAP5430_MASK_FREEZE_MPU_MASK			BIT(21)
-#define OMAP5430_MASK_CLEAR_CORE_MASK			BIT(20)
-#define OMAP5430_MASK_CLEAR_GPU_MASK			BIT(19)
-#define OMAP5430_MASK_CLEAR_MPU_MASK			BIT(18)
-#define OMAP5430_MASK_CLEAR_ACCUM_CORE_MASK		BIT(17)
-#define OMAP5430_MASK_CLEAR_ACCUM_GPU_MASK		BIT(16)
-#define OMAP5430_MASK_CLEAR_ACCUM_MPU_MASK		BIT(15)
 #define OMAP5430_MASK_HOT_CORE_MASK			BIT(5)
 #define OMAP5430_MASK_COLD_CORE_MASK			BIT(4)
 #define OMAP5430_MASK_HOT_GPU_MASK			BIT(3)
@@ -123,17 +104,7 @@
 #define OMAP5430_TSHUT_HOT_MASK				(0x3ff << 16)
 #define OMAP5430_TSHUT_COLD_MASK			(0x3ff << 0)
 
-/* OMAP5430.BANDGAP_CUMUL_DTEMP_MPU */
-#define OMAP5430_CUMUL_DTEMP_MPU_MASK			(0xffffffff << 0)
-
-/* OMAP5430.BANDGAP_CUMUL_DTEMP_GPU */
-#define OMAP5430_CUMUL_DTEMP_GPU_MASK			(0xffffffff << 0)
-
-/* OMAP5430.BANDGAP_CUMUL_DTEMP_CORE */
-#define OMAP5430_CUMUL_DTEMP_CORE_MASK			(0xffffffff << 0)
-
 /* OMAP5430.BANDGAP_STATUS */
-#define OMAP5430_BGAP_ALERT_MASK			BIT(31)
 #define OMAP5430_HOT_CORE_FLAG_MASK			BIT(5)
 #define OMAP5430_COLD_CORE_FLAG_MASK			BIT(4)
 #define OMAP5430_HOT_GPU_FLAG_MASK			BIT(3)
@@ -159,10 +130,6 @@
 /* bandgap clock limits */
 #define OMAP5430_GPU_MAX_FREQ				1500000
 #define OMAP5430_GPU_MIN_FREQ				1000000
-/* sensor limits */
-#define OMAP5430_GPU_MIN_TEMP				-40000
-#define OMAP5430_GPU_MAX_TEMP				125000
-#define OMAP5430_GPU_HYST_VAL				5000
 /* interrupts thresholds */
 #define OMAP5430_GPU_TSHUT_HOT				915
 #define OMAP5430_GPU_TSHUT_COLD				900
@@ -173,10 +140,6 @@
 /* bandgap clock limits */
 #define OMAP5430_MPU_MAX_FREQ				1500000
 #define OMAP5430_MPU_MIN_FREQ				1000000
-/* sensor limits */
-#define OMAP5430_MPU_MIN_TEMP				-40000
-#define OMAP5430_MPU_MAX_TEMP				125000
-#define OMAP5430_MPU_HYST_VAL				5000
 /* interrupts thresholds */
 #define OMAP5430_MPU_TSHUT_HOT				915
 #define OMAP5430_MPU_TSHUT_COLD				900
@@ -187,10 +150,6 @@
 /* bandgap clock limits */
 #define OMAP5430_CORE_MAX_FREQ				1500000
 #define OMAP5430_CORE_MIN_FREQ				1000000
-/* sensor limits */
-#define OMAP5430_CORE_MIN_TEMP				-40000
-#define OMAP5430_CORE_MAX_TEMP				125000
-#define OMAP5430_CORE_HYST_VAL				5000
 /* interrupts thresholds */
 #define OMAP5430_CORE_TSHUT_HOT				915
 #define OMAP5430_CORE_TSHUT_COLD			900
diff --git a/drivers/thermal/ti-soc-thermal/ti-bandgap.c b/drivers/thermal/ti-soc-thermal/ti-bandgap.c
index 696ab3046b87..097328d8e943 100644
--- a/drivers/thermal/ti-soc-thermal/ti-bandgap.c
+++ b/drivers/thermal/ti-soc-thermal/ti-bandgap.c
@@ -306,217 +306,6 @@ int ti_bandgap_adc_to_mcelsius(struct ti_bandgap *bgp, int adc_val, int *t)
 }
 
 /**
- * ti_bandgap_mcelsius_to_adc() - converts a mCelsius value to ADC scale
- * @bgp: struct ti_bandgap pointer
- * @temp: value in mCelsius
- * @adc: address where to write the resulting temperature in ADC representation
- *
- * Simple conversion from mCelsius to ADC values. In case the temp value
- * is out of the ADC conv table range, it returns -ERANGE, 0 on success.
- * The conversion table is indexed by the ADC values.
- *
- * Return: 0 if conversion was successful, else -ERANGE in case the @temp
- * argument is out of the ADC conv table range.
- */
-static
-int ti_bandgap_mcelsius_to_adc(struct ti_bandgap *bgp, long temp, int *adc)
-{
-	const struct ti_bandgap_data *conf = bgp->conf;
-	const int *conv_table = bgp->conf->conv_table;
-	int high, low, mid;
-
-	low = 0;
-	high = conf->adc_end_val - conf->adc_start_val;
-	mid = (high + low) / 2;
-
-	if (temp < conv_table[low] || temp > conv_table[high])
-		return -ERANGE;
-
-	while (low < high) {
-		if (temp < conv_table[mid])
-			high = mid - 1;
-		else
-			low = mid + 1;
-		mid = (low + high) / 2;
-	}
-
-	*adc = conf->adc_start_val + low;
-	return 0;
-}
-
-/**
- * ti_bandgap_add_hyst() - add hysteresis (in mCelsius) to an ADC value
- * @bgp: struct ti_bandgap pointer
- * @adc_val: temperature value in ADC representation
- * @hyst_val: hysteresis value in mCelsius
- * @sum: address where to write the resulting temperature (in ADC scale)
- *
- * Adds an hysteresis value (in mCelsius) to a ADC temperature value.
- *
- * Return: 0 on success, -ERANGE otherwise.
- */
-static
-int ti_bandgap_add_hyst(struct ti_bandgap *bgp, int adc_val, int hyst_val,
-			u32 *sum)
-{
-	int temp, ret;
-
-	/*
-	 * Need to add in the mcelsius domain, so we have a temperature
-	 * the conv_table range
-	 */
-	ret = ti_bandgap_adc_to_mcelsius(bgp, adc_val, &temp);
-	if (ret < 0)
-		return ret;
-
-	temp += hyst_val;
-
-	ret = ti_bandgap_mcelsius_to_adc(bgp, temp, sum);
-	return ret;
-}
-
-/***   Helper functions handling device Alert/Shutdown signals   ***/
-
-/**
- * ti_bandgap_unmask_interrupts() - unmasks the events of thot & tcold
- * @bgp: struct ti_bandgap pointer
- * @id: bandgap sensor id
- * @t_hot: hot temperature value to trigger alert signal
- * @t_cold: cold temperature value to trigger alert signal
- *
- * Checks the requested t_hot and t_cold values and configures the IRQ event
- * masks accordingly. Call this function only if bandgap features HAS(TALERT).
- */
-static void ti_bandgap_unmask_interrupts(struct ti_bandgap *bgp, int id,
-					 u32 t_hot, u32 t_cold)
-{
-	struct temp_sensor_registers *tsr;
-	u32 temp, reg_val;
-
-	/* Read the current on die temperature */
-	temp = ti_bandgap_read_temp(bgp, id);
-
-	tsr = bgp->conf->sensors[id].registers;
-	reg_val = ti_bandgap_readl(bgp, tsr->bgap_mask_ctrl);
-
-	if (temp < t_hot)
-		reg_val |= tsr->mask_hot_mask;
-	else
-		reg_val &= ~tsr->mask_hot_mask;
-
-	if (t_cold < temp)
-		reg_val |= tsr->mask_cold_mask;
-	else
-		reg_val &= ~tsr->mask_cold_mask;
-	ti_bandgap_writel(bgp, reg_val, tsr->bgap_mask_ctrl);
-}
-
-/**
- * ti_bandgap_update_alert_threshold() - sequence to update thresholds
- * @bgp: struct ti_bandgap pointer
- * @id: bandgap sensor id
- * @val: value (ADC) of a new threshold
- * @hot: desired threshold to be updated. true if threshold hot, false if
- *       threshold cold
- *
- * It will program the required thresholds (hot and cold) for TALERT signal.
- * This function can be used to update t_hot or t_cold, depending on @hot value.
- * It checks the resulting t_hot and t_cold values, based on the new passed @val
- * and configures the thresholds so that t_hot is always greater than t_cold.
- * Call this function only if bandgap features HAS(TALERT).
- *
- * Return: 0 if no error, else corresponding error
- */
-static int ti_bandgap_update_alert_threshold(struct ti_bandgap *bgp, int id,
-					     int val, bool hot)
-{
-	struct temp_sensor_data *ts_data = bgp->conf->sensors[id].ts_data;
-	struct temp_sensor_registers *tsr;
-	u32 thresh_val, reg_val, t_hot, t_cold, ctrl;
-	int err = 0;
-
-	tsr = bgp->conf->sensors[id].registers;
-
-	/* obtain the current value */
-	thresh_val = ti_bandgap_readl(bgp, tsr->bgap_threshold);
-	t_cold = (thresh_val & tsr->threshold_tcold_mask) >>
-		__ffs(tsr->threshold_tcold_mask);
-	t_hot = (thresh_val & tsr->threshold_thot_mask) >>
-		__ffs(tsr->threshold_thot_mask);
-	if (hot)
-		t_hot = val;
-	else
-		t_cold = val;
-
-	if (t_cold > t_hot) {
-		if (hot)
-			err = ti_bandgap_add_hyst(bgp, t_hot,
-						  -ts_data->hyst_val,
-						  &t_cold);
-		else
-			err = ti_bandgap_add_hyst(bgp, t_cold,
-						  ts_data->hyst_val,
-						  &t_hot);
-	}
-
-	/* write the new threshold values */
-	reg_val = thresh_val &
-		  ~(tsr->threshold_thot_mask | tsr->threshold_tcold_mask);
-	reg_val |= (t_hot << __ffs(tsr->threshold_thot_mask)) |
-		   (t_cold << __ffs(tsr->threshold_tcold_mask));
-
-	/**
-	 * Errata i813:
-	 * Spurious Thermal Alert: Talert can happen randomly while the device
-	 * remains under the temperature limit defined for this event to trig.
-	 * This spurious event is caused by a incorrect re-synchronization
-	 * between clock domains. The comparison between configured threshold
-	 * and current temperature value can happen while the value is
-	 * transitioning (metastable), thus causing inappropriate event
-	 * generation. No spurious event occurs as long as the threshold value
-	 * stays unchanged. Spurious event can be generated while a thermal
-	 * alert threshold is modified in
-	 * CONTROL_BANDGAP_THRESHOLD_MPU/GPU/CORE/DSPEVE/IVA_n.
-	 */
-
-	if (TI_BANDGAP_HAS(bgp, ERRATA_813)) {
-		/* Mask t_hot and t_cold events at the IP Level */
-		ctrl = ti_bandgap_readl(bgp, tsr->bgap_mask_ctrl);
-
-		if (hot)
-			ctrl &= ~tsr->mask_hot_mask;
-		else
-			ctrl &= ~tsr->mask_cold_mask;
-
-		ti_bandgap_writel(bgp, ctrl, tsr->bgap_mask_ctrl);
-	}
-
-	/* Write the threshold value */
-	ti_bandgap_writel(bgp, reg_val, tsr->bgap_threshold);
-
-	if (TI_BANDGAP_HAS(bgp, ERRATA_813)) {
-		/* Unmask t_hot and t_cold events at the IP Level */
-		ctrl = ti_bandgap_readl(bgp, tsr->bgap_mask_ctrl);
-		if (hot)
-			ctrl |= tsr->mask_hot_mask;
-		else
-			ctrl |= tsr->mask_cold_mask;
-
-		ti_bandgap_writel(bgp, ctrl, tsr->bgap_mask_ctrl);
-	}
-
-	if (err) {
-		dev_err(bgp->dev, "failed to reprogram thot threshold\n");
-		err = -EIO;
-		goto exit;
-	}
-
-	ti_bandgap_unmask_interrupts(bgp, id, t_hot, t_cold);
-exit:
-	return err;
-}
-
-/**
  * ti_bandgap_validate() - helper to check the sanity of a struct ti_bandgap
  * @bgp: struct ti_bandgap pointer
  * @id: bandgap sensor id
@@ -544,165 +333,6 @@ static inline int ti_bandgap_validate(struct ti_bandgap *bgp, int id)
 }
 
 /**
- * _ti_bandgap_write_threshold() - helper to update TALERT t_cold or t_hot
- * @bgp: struct ti_bandgap pointer
- * @id: bandgap sensor id
- * @val: value (mCelsius) of a new threshold
- * @hot: desired threshold to be updated. true if threshold hot, false if
- *       threshold cold
- *
- * It will update the required thresholds (hot and cold) for TALERT signal.
- * This function can be used to update t_hot or t_cold, depending on @hot value.
- * Validates the mCelsius range and update the requested threshold.
- * Call this function only if bandgap features HAS(TALERT).
- *
- * Return: 0 if no error, else corresponding error value.
- */
-static int _ti_bandgap_write_threshold(struct ti_bandgap *bgp, int id, int val,
-				       bool hot)
-{
-	struct temp_sensor_data *ts_data;
-	struct temp_sensor_registers *tsr;
-	u32 adc_val;
-	int ret;
-
-	ret = ti_bandgap_validate(bgp, id);
-	if (ret)
-		return ret;
-
-	if (!TI_BANDGAP_HAS(bgp, TALERT))
-		return -ENOTSUPP;
-
-	ts_data = bgp->conf->sensors[id].ts_data;
-	tsr = bgp->conf->sensors[id].registers;
-	if (hot) {
-		if (val < ts_data->min_temp + ts_data->hyst_val)
-			ret = -EINVAL;
-	} else {
-		if (val > ts_data->max_temp + ts_data->hyst_val)
-			ret = -EINVAL;
-	}
-
-	if (ret)
-		return ret;
-
-	ret = ti_bandgap_mcelsius_to_adc(bgp, val, &adc_val);
-	if (ret < 0)
-		return ret;
-
-	spin_lock(&bgp->lock);
-	ret = ti_bandgap_update_alert_threshold(bgp, id, adc_val, hot);
-	spin_unlock(&bgp->lock);
-	return ret;
-}
-
-/**
- * _ti_bandgap_read_threshold() - helper to read TALERT t_cold or t_hot
- * @bgp: struct ti_bandgap pointer
- * @id: bandgap sensor id
- * @val: value (mCelsius) of a threshold
- * @hot: desired threshold to be read. true if threshold hot, false if
- *       threshold cold
- *
- * It will fetch the required thresholds (hot and cold) for TALERT signal.
- * This function can be used to read t_hot or t_cold, depending on @hot value.
- * Call this function only if bandgap features HAS(TALERT).
- *
- * Return: 0 if no error, -ENOTSUPP if it has no TALERT support, or the
- * corresponding error value if some operation fails.
- */
-static int _ti_bandgap_read_threshold(struct ti_bandgap *bgp, int id,
-				      int *val, bool hot)
-{
-	struct temp_sensor_registers *tsr;
-	u32 temp, mask;
-	int ret = 0;
-
-	ret = ti_bandgap_validate(bgp, id);
-	if (ret)
-		goto exit;
-
-	if (!TI_BANDGAP_HAS(bgp, TALERT)) {
-		ret = -ENOTSUPP;
-		goto exit;
-	}
-
-	tsr = bgp->conf->sensors[id].registers;
-	if (hot)
-		mask = tsr->threshold_thot_mask;
-	else
-		mask = tsr->threshold_tcold_mask;
-
-	temp = ti_bandgap_readl(bgp, tsr->bgap_threshold);
-	temp = (temp & mask) >> __ffs(mask);
-	ret = ti_bandgap_adc_to_mcelsius(bgp, temp, &temp);
-	if (ret) {
-		dev_err(bgp->dev, "failed to read thot\n");
-		ret = -EIO;
-		goto exit;
-	}
-
-	*val = temp;
-
-exit:
-	return ret;
-}
-
-/***   Exposed APIs   ***/
-
-/**
- * ti_bandgap_read_thot() - reads sensor current thot
- * @bgp: pointer to bandgap instance
- * @id: sensor id
- * @thot: resulting current thot value
- *
- * Return: 0 on success or the proper error code
- */
-int ti_bandgap_read_thot(struct ti_bandgap *bgp, int id, int *thot)
-{
-	return _ti_bandgap_read_threshold(bgp, id, thot, true);
-}
-
-/**
- * ti_bandgap_write_thot() - sets sensor current thot
- * @bgp: pointer to bandgap instance
- * @id: sensor id
- * @val: desired thot value
- *
- * Return: 0 on success or the proper error code
- */
-int ti_bandgap_write_thot(struct ti_bandgap *bgp, int id, int val)
-{
-	return _ti_bandgap_write_threshold(bgp, id, val, true);
-}
-
-/**
- * ti_bandgap_read_tcold() - reads sensor current tcold
- * @bgp: pointer to bandgap instance
- * @id: sensor id
- * @tcold: resulting current tcold value
- *
- * Return: 0 on success or the proper error code
- */
-int ti_bandgap_read_tcold(struct ti_bandgap *bgp, int id, int *tcold)
-{
-	return _ti_bandgap_read_threshold(bgp, id, tcold, false);
-}
-
-/**
- * ti_bandgap_write_tcold() - sets the sensor tcold
- * @bgp: pointer to bandgap instance
- * @id: sensor id
- * @val: desired tcold value
- *
- * Return: 0 on success or the proper error code
- */
-int ti_bandgap_write_tcold(struct ti_bandgap *bgp, int id, int val)
-{
-	return _ti_bandgap_write_threshold(bgp, id, val, false);
-}
-
-/**
  * ti_bandgap_read_counter() - read the sensor counter
  * @bgp: pointer to bandgap instance
  * @id: sensor id
diff --git a/drivers/thermal/ti-soc-thermal/ti-bandgap.h b/drivers/thermal/ti-soc-thermal/ti-bandgap.h
index 209c664c2823..68d39ad43241 100644
--- a/drivers/thermal/ti-soc-thermal/ti-bandgap.h
+++ b/drivers/thermal/ti-soc-thermal/ti-bandgap.h
@@ -78,11 +78,8 @@
  * @bgap_mask_ctrl: BANDGAP_MASK_CTRL register offset
  * @mask_hot_mask: mask to bandgap_mask_ctrl.mask_hot
  * @mask_cold_mask: mask to bandgap_mask_ctrl.mask_cold
- * @mask_sidlemode_mask: mask to bandgap_mask_ctrl.mask_sidlemode
  * @mask_counter_delay_mask: mask to bandgap_mask_ctrl.mask_counter_delay
  * @mask_freeze_mask: mask to bandgap_mask_ctrl.mask_free
- * @mask_clear_mask: mask to bandgap_mask_ctrl.mask_clear
- * @mask_clear_accum_mask: mask to bandgap_mask_ctrl.mask_clear_accum
  * @bgap_mode_ctrl: BANDGAP_MODE_CTRL register offset
  * @mode_ctrl_mask: mask to bandgap_mode_ctrl.mode_ctrl
  * @bgap_counter: BANDGAP_COUNTER register offset
@@ -91,21 +88,13 @@
  * @threshold_thot_mask: mask to bandgap_threhold.thot
  * @threshold_tcold_mask: mask to bandgap_threhold.tcold
  * @tshut_threshold: TSHUT_THRESHOLD register offset (TSHUT thresholds)
- * @tshut_efuse_mask: mask to tshut_threshold.tshut_efuse
- * @tshut_efuse_shift: shift to tshut_threshold.tshut_efuse
  * @tshut_hot_mask: mask to tshut_threhold.thot
  * @tshut_cold_mask: mask to tshut_threhold.thot
  * @bgap_status: BANDGAP_STATUS register offset
- * @status_clean_stop_mask: mask to bandgap_status.clean_stop
- * @status_bgap_alert_mask: mask to bandgap_status.bandgap_alert
  * @status_hot_mask: mask to bandgap_status.hot
  * @status_cold_mask: mask to bandgap_status.cold
- * @bgap_cumul_dtemp: BANDGAP_CUMUL_DTEMP register offset
- * @ctrl_dtemp_0: CTRL_DTEMP0 register offset
  * @ctrl_dtemp_1: CTRL_DTEMP1 register offset
  * @ctrl_dtemp_2: CTRL_DTEMP2 register offset
- * @ctrl_dtemp_3: CTRL_DTEMP3 register offset
- * @ctrl_dtemp_4: CTRL_DTEMP4 register offset
  * @bgap_efuse: BANDGAP_EFUSE register offset
  *
  * The register offsets and bitfields might change across
@@ -121,17 +110,14 @@ struct temp_sensor_registers {
 	u32	temp_sensor_ctrl;
 	u32	bgap_tempsoff_mask;
 	u32	bgap_soc_mask;
-	u32	bgap_eocz_mask; /* not used: but needs revisit */
+	u32	bgap_eocz_mask;
 	u32	bgap_dtemp_mask;
 
 	u32	bgap_mask_ctrl;
 	u32	mask_hot_mask;
 	u32	mask_cold_mask;
-	u32	mask_sidlemode_mask; /* not used: but may be needed for pm */
 	u32	mask_counter_delay_mask;
 	u32	mask_freeze_mask;
-	u32	mask_clear_mask; /* not used: but needed for trending */
-	u32	mask_clear_accum_mask; /* not used: but needed for trending */
 
 	u32	bgap_mode_ctrl;
 	u32	mode_ctrl_mask;
@@ -144,23 +130,15 @@ struct temp_sensor_registers {
 	u32	threshold_tcold_mask;
 
 	u32	tshut_threshold;
-	u32	tshut_efuse_mask; /* not used */
-	u32	tshut_efuse_shift; /* not used */
 	u32	tshut_hot_mask;
 	u32	tshut_cold_mask;
 
 	u32	bgap_status;
-	u32	status_clean_stop_mask; /* not used: but needed for trending */
-	u32	status_bgap_alert_mask; /* not used */
 	u32	status_hot_mask;
 	u32	status_cold_mask;
 
-	u32	bgap_cumul_dtemp; /* not used: but needed for trending */
-	u32	ctrl_dtemp_0; /* not used: but needed for trending */
-	u32	ctrl_dtemp_1; /* not used: but needed for trending */
-	u32	ctrl_dtemp_2; /* not used: but needed for trending */
-	u32	ctrl_dtemp_3; /* not used: but needed for trending */
-	u32	ctrl_dtemp_4; /* not used: but needed for trending */
+	u32	ctrl_dtemp_1;
+	u32	ctrl_dtemp_2;
 	u32	bgap_efuse;
 };
 
@@ -172,11 +150,6 @@ struct temp_sensor_registers {
  * @t_cold: temperature to trigger a thermal alert (low initial value)
  * @min_freq: sensor minimum clock rate
  * @max_freq: sensor maximum clock rate
- * @max_temp: sensor maximum temperature
- * @min_temp: sensor minimum temperature
- * @hyst_val: temperature hysteresis considered while converting ADC values
- * @update_int1: update interval
- * @update_int2: update interval
  *
  * This data structure will hold the required thresholds and temperature limits
  * for a specific temperature sensor, like shutdown temperature, alert
@@ -189,11 +162,6 @@ struct temp_sensor_data {
 	u32	t_cold;
 	u32	min_freq;
 	u32	max_freq;
-	int     max_temp;
-	int     min_temp;
-	int     hyst_val;
-	u32     update_int1; /* not used */
-	u32     update_int2; /* not used */
 };
 
 struct ti_bandgap_data;
@@ -316,8 +284,6 @@ struct ti_temp_sensor {
  *
  * TI_BANDGAP_FEATURE_ERRATA_814 - used to workaorund when the bandgap device
  *	has Errata 814
- * TI_BANDGAP_FEATURE_ERRATA_813 - used to workaorund when the bandgap device
- *	has Errata 813
  * TI_BANDGAP_FEATURE_UNRELIABLE - used when the sensor readings are too
  *	inaccurate.
  * TI_BANDGAP_HAS(b, f) - macro to check if a bandgap device is capable of a
@@ -334,8 +300,7 @@ struct ti_temp_sensor {
 #define TI_BANDGAP_FEATURE_COUNTER_DELAY	BIT(8)
 #define TI_BANDGAP_FEATURE_HISTORY_BUFFER	BIT(9)
 #define TI_BANDGAP_FEATURE_ERRATA_814		BIT(10)
-#define TI_BANDGAP_FEATURE_ERRATA_813		BIT(11)
-#define TI_BANDGAP_FEATURE_UNRELIABLE		BIT(12)
+#define TI_BANDGAP_FEATURE_UNRELIABLE		BIT(11)
 #define TI_BANDGAP_HAS(b, f)			\
 			((b)->conf->features & TI_BANDGAP_FEATURE_ ## f)
 
diff --git a/drivers/tty/tty_audit.c b/drivers/tty/tty_audit.c
index e30aa6bf9ff9..50f567b6a66e 100644
--- a/drivers/tty/tty_audit.c
+++ b/drivers/tty/tty_audit.c
@@ -92,7 +92,7 @@ static void tty_audit_buf_push(struct tty_audit_buf *buf)
 {
 	if (buf->valid == 0)
 		return;
-	if (audit_enabled == 0) {
+	if (audit_enabled == AUDIT_OFF) {
 		buf->valid = 0;
 		return;
 	}
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index d5b4a2b44ab8..de310621b8e7 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -959,7 +959,7 @@ struct kbd_led_trigger {
 	unsigned int mask;
 };
 
-static void kbd_led_trigger_activate(struct led_classdev *cdev)
+static int kbd_led_trigger_activate(struct led_classdev *cdev)
 {
 	struct kbd_led_trigger *trigger =
 		container_of(cdev->trigger, struct kbd_led_trigger, trigger);
@@ -970,6 +970,8 @@ static void kbd_led_trigger_activate(struct led_classdev *cdev)
 				  ledstate & trigger->mask ?
 					LED_FULL : LED_OFF);
 	tasklet_enable(&keyboard_tasklet);
+
+	return 0;
 }
 
 #define KBD_LED_TRIGGER(_led_bit, _name) {			\
diff --git a/drivers/usb/core/ledtrig-usbport.c b/drivers/usb/core/ledtrig-usbport.c
index d775ffea20c3..dc7f7fd71684 100644
--- a/drivers/usb/core/ledtrig-usbport.c
+++ b/drivers/usb/core/ledtrig-usbport.c
@@ -113,11 +113,17 @@ static ssize_t usbport_trig_port_store(struct device *dev,
 static struct attribute *ports_attrs[] = {
 	NULL,
 };
+
 static const struct attribute_group ports_group = {
 	.name = "ports",
 	.attrs = ports_attrs,
 };
 
+static const struct attribute_group *ports_groups[] = {
+	&ports_group,
+	NULL
+};
+
 /***************************************
  * Adding & removing ports
  ***************************************/
@@ -298,61 +304,47 @@ static int usbport_trig_notify(struct notifier_block *nb, unsigned long action,
 	return NOTIFY_DONE;
 }
 
-static void usbport_trig_activate(struct led_classdev *led_cdev)
+static int usbport_trig_activate(struct led_classdev *led_cdev)
 {
 	struct usbport_trig_data *usbport_data;
-	int err;
 
 	usbport_data = kzalloc(sizeof(*usbport_data), GFP_KERNEL);
 	if (!usbport_data)
-		return;
+		return -ENOMEM;
 	usbport_data->led_cdev = led_cdev;
 
 	/* List of ports */
 	INIT_LIST_HEAD(&usbport_data->ports);
-	err = sysfs_create_group(&led_cdev->dev->kobj, &ports_group);
-	if (err)
-		goto err_free;
 	usb_for_each_dev(usbport_data, usbport_trig_add_usb_dev_ports);
 	usbport_trig_update_count(usbport_data);
 
 	/* Notifications */
-	usbport_data->nb.notifier_call = usbport_trig_notify,
-	led_cdev->trigger_data = usbport_data;
+	usbport_data->nb.notifier_call = usbport_trig_notify;
+	led_set_trigger_data(led_cdev, usbport_data);
 	usb_register_notify(&usbport_data->nb);
 
-	led_cdev->activated = true;
-	return;
-
-err_free:
-	kfree(usbport_data);
+	return 0;
 }
 
 static void usbport_trig_deactivate(struct led_classdev *led_cdev)
 {
-	struct usbport_trig_data *usbport_data = led_cdev->trigger_data;
+	struct usbport_trig_data *usbport_data = led_get_trigger_data(led_cdev);
 	struct usbport_trig_port *port, *tmp;
 
-	if (!led_cdev->activated)
-		return;
-
 	list_for_each_entry_safe(port, tmp, &usbport_data->ports, list) {
 		usbport_trig_remove_port(usbport_data, port);
 	}
 
 	usb_unregister_notify(&usbport_data->nb);
 
-	sysfs_remove_group(&led_cdev->dev->kobj, &ports_group);
-
 	kfree(usbport_data);
-
-	led_cdev->activated = false;
 }
 
 static struct led_trigger usbport_led_trigger = {
 	.name     = "usbport",
 	.activate = usbport_trig_activate,
 	.deactivate = usbport_trig_deactivate,
+	.groups = ports_groups,
 };
 
 static int __init usbport_trig_init(void)
diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c
index d78dbb73bde8..106988a6661a 100644
--- a/drivers/usb/gadget/function/f_tcm.c
+++ b/drivers/usb/gadget/function/f_tcm.c
@@ -1071,15 +1071,16 @@ static struct usbg_cmd *usbg_get_cmd(struct f_uas *fu,
 {
 	struct se_session *se_sess = tv_nexus->tvn_se_sess;
 	struct usbg_cmd *cmd;
-	int tag;
+	int tag, cpu;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
+	tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
 	if (tag < 0)
 		return ERR_PTR(-ENOMEM);
 
 	cmd = &((struct usbg_cmd *)se_sess->sess_cmd_map)[tag];
 	memset(cmd, 0, sizeof(*cmd));
 	cmd->se_cmd.map_tag = tag;
+	cmd->se_cmd.map_cpu = cpu;
 	cmd->se_cmd.tag = cmd->tag = scsi_tag;
 	cmd->fu = fu;
 
@@ -1288,7 +1289,7 @@ static void usbg_release_cmd(struct se_cmd *se_cmd)
 	struct se_session *se_sess = se_cmd->se_sess;
 
 	kfree(cmd->data_buf);
-	percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag);
+	target_free_tag(se_sess, se_cmd);
 }
 
 static u32 usbg_sess_get_index(struct se_session *se_sess)
@@ -1343,10 +1344,8 @@ static int usbg_init_nodeacl(struct se_node_acl *se_nacl, const char *name)
 	return 0;
 }
 
-static struct se_portal_group *usbg_make_tpg(
-	struct se_wwn *wwn,
-	struct config_group *group,
-	const char *name)
+static struct se_portal_group *usbg_make_tpg(struct se_wwn *wwn,
+					     const char *name)
 {
 	struct usbg_tport *tport = container_of(wwn, struct usbg_tport,
 			tport_wwn);
@@ -1379,7 +1378,7 @@ static struct se_portal_group *usbg_make_tpg(
 			goto unlock_dep;
 	} else {
 		ret = configfs_depend_item_unlocked(
-			group->cg_subsys,
+			wwn->wwn_group.cg_subsys,
 			&opts->func_inst.group.cg_item);
 		if (ret)
 			goto unlock_dep;
@@ -1593,7 +1592,7 @@ static int tcm_usbg_make_nexus(struct usbg_tpg *tpg, char *name)
 		goto out_unlock;
 	}
 
-	tv_nexus->tvn_se_sess = target_alloc_session(&tpg->se_tpg,
+	tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg,
 						     USB_G_DEFAULT_SESSION_TAGS,
 						     sizeof(struct usbg_cmd),
 						     TARGET_PROT_NORMAL, name,
@@ -1639,7 +1638,7 @@ static int tcm_usbg_drop_nexus(struct usbg_tpg *tpg)
 	/*
 	 * Release the SCSI I_T Nexus to the emulated vHost Target Port
 	 */
-	transport_deregister_session(tv_nexus->tvn_se_sess);
+	target_remove_session(se_sess);
 	tpg->tpg_nexus = NULL;
 
 	kfree(tv_nexus);
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 125b58eff936..cddb453a1ba5 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -789,7 +789,7 @@ static long vfio_pci_ioctl(void *device_data,
 		case VFIO_PCI_ERR_IRQ_INDEX:
 			if (pci_is_pcie(vdev->pdev))
 				break;
-		/* pass thru to return error */
+		/* fall through */
 		default:
 			return -EINVAL;
 		}
@@ -1014,8 +1014,7 @@ reset_info_exit:
 						    &info, slot);
 		if (!ret)
 			/* User has access, do the reset */
-			ret = slot ? pci_try_reset_slot(vdev->pdev->slot) :
-				     pci_try_reset_bus(vdev->pdev->bus);
+			ret = pci_reset_bus(vdev->pdev);
 
 hot_reset_release:
 		for (i--; i >= 0; i--)
@@ -1193,6 +1192,19 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL)
 		return -EINVAL;
 
+	/*
+	 * Prevent binding to PFs with VFs enabled, this too easily allows
+	 * userspace instance with VFs and PFs from the same device, which
+	 * cannot work.  Disabling SR-IOV here would initiate removing the
+	 * VFs, which would unbind the driver, which is prone to blocking
+	 * if that VF is also in use by vfio-pci.  Just reject these PFs
+	 * and let the user sort it out.
+	 */
+	if (pci_num_vf(pdev)) {
+		pci_warn(pdev, "Cannot bind to PF with SR-IOV enabled\n");
+		return -EBUSY;
+	}
+
 	group = vfio_iommu_group_get(&pdev->dev);
 	if (!group)
 		return -EINVAL;
@@ -1377,8 +1389,7 @@ static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev)
 	}
 
 	if (needs_reset)
-		ret = slot ? pci_try_reset_slot(vdev->pdev->slot) :
-			     pci_try_reset_bus(vdev->pdev->bus);
+		ret = pci_reset_bus(vdev->pdev);
 
 put_devs:
 	for (i = 0; i < devs.cur_index; i++) {
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 3e5b17710a4f..d9fd3188615d 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -1601,6 +1601,7 @@ static void *vfio_iommu_type1_open(unsigned long arg)
 		break;
 	case VFIO_TYPE1_NESTING_IOMMU:
 		iommu->nesting = true;
+		/* fall through */
 	case VFIO_TYPE1v2_IOMMU:
 		iommu->v2 = true;
 		break;
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 29756d88799b..4e656f89cb22 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -78,6 +78,10 @@ enum {
 };
 
 enum {
+	VHOST_NET_BACKEND_FEATURES = (1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2)
+};
+
+enum {
 	VHOST_NET_VQ_RX = 0,
 	VHOST_NET_VQ_TX = 1,
 	VHOST_NET_VQ_MAX = 2,
@@ -94,7 +98,7 @@ struct vhost_net_ubuf_ref {
 	struct vhost_virtqueue *vq;
 };
 
-#define VHOST_RX_BATCH 64
+#define VHOST_NET_BATCH 64
 struct vhost_net_buf {
 	void **queue;
 	int tail;
@@ -168,7 +172,7 @@ static int vhost_net_buf_produce(struct vhost_net_virtqueue *nvq)
 
 	rxq->head = 0;
 	rxq->tail = ptr_ring_consume_batched(nvq->rx_ring, rxq->queue,
-					      VHOST_RX_BATCH);
+					      VHOST_NET_BATCH);
 	return rxq->tail;
 }
 
@@ -396,13 +400,10 @@ static inline unsigned long busy_clock(void)
 	return local_clock() >> 10;
 }
 
-static bool vhost_can_busy_poll(struct vhost_dev *dev,
-				unsigned long endtime)
+static bool vhost_can_busy_poll(unsigned long endtime)
 {
-	return likely(!need_resched()) &&
-	       likely(!time_after(busy_clock(), endtime)) &&
-	       likely(!signal_pending(current)) &&
-	       !vhost_has_work(dev);
+	return likely(!need_resched() && !time_after(busy_clock(), endtime) &&
+		      !signal_pending(current));
 }
 
 static void vhost_net_disable_vq(struct vhost_net *n,
@@ -431,21 +432,42 @@ static int vhost_net_enable_vq(struct vhost_net *n,
 	return vhost_poll_start(poll, sock->file);
 }
 
+static void vhost_net_signal_used(struct vhost_net_virtqueue *nvq)
+{
+	struct vhost_virtqueue *vq = &nvq->vq;
+	struct vhost_dev *dev = vq->dev;
+
+	if (!nvq->done_idx)
+		return;
+
+	vhost_add_used_and_signal_n(dev, vq, vq->heads, nvq->done_idx);
+	nvq->done_idx = 0;
+}
+
 static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
-				    struct vhost_virtqueue *vq,
-				    struct iovec iov[], unsigned int iov_size,
-				    unsigned int *out_num, unsigned int *in_num)
+				    struct vhost_net_virtqueue *nvq,
+				    unsigned int *out_num, unsigned int *in_num,
+				    bool *busyloop_intr)
 {
+	struct vhost_virtqueue *vq = &nvq->vq;
 	unsigned long uninitialized_var(endtime);
 	int r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
 				  out_num, in_num, NULL, NULL);
 
 	if (r == vq->num && vq->busyloop_timeout) {
+		if (!vhost_sock_zcopy(vq->private_data))
+			vhost_net_signal_used(nvq);
 		preempt_disable();
 		endtime = busy_clock() + vq->busyloop_timeout;
-		while (vhost_can_busy_poll(vq->dev, endtime) &&
-		       vhost_vq_avail_empty(vq->dev, vq))
+		while (vhost_can_busy_poll(endtime)) {
+			if (vhost_has_work(vq->dev)) {
+				*busyloop_intr = true;
+				break;
+			}
+			if (!vhost_vq_avail_empty(vq->dev, vq))
+				break;
 			cpu_relax();
+		}
 		preempt_enable();
 		r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
 				      out_num, in_num, NULL, NULL);
@@ -463,9 +485,62 @@ static bool vhost_exceeds_maxpend(struct vhost_net *net)
 	       min_t(unsigned int, VHOST_MAX_PEND, vq->num >> 2);
 }
 
-/* Expects to be always run from workqueue - which acts as
- * read-size critical section for our kind of RCU. */
-static void handle_tx(struct vhost_net *net)
+static size_t init_iov_iter(struct vhost_virtqueue *vq, struct iov_iter *iter,
+			    size_t hdr_size, int out)
+{
+	/* Skip header. TODO: support TSO. */
+	size_t len = iov_length(vq->iov, out);
+
+	iov_iter_init(iter, WRITE, vq->iov, out, len);
+	iov_iter_advance(iter, hdr_size);
+
+	return iov_iter_count(iter);
+}
+
+static bool vhost_exceeds_weight(int pkts, int total_len)
+{
+	return total_len >= VHOST_NET_WEIGHT ||
+	       pkts >= VHOST_NET_PKT_WEIGHT;
+}
+
+static int get_tx_bufs(struct vhost_net *net,
+		       struct vhost_net_virtqueue *nvq,
+		       struct msghdr *msg,
+		       unsigned int *out, unsigned int *in,
+		       size_t *len, bool *busyloop_intr)
+{
+	struct vhost_virtqueue *vq = &nvq->vq;
+	int ret;
+
+	ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, busyloop_intr);
+
+	if (ret < 0 || ret == vq->num)
+		return ret;
+
+	if (*in) {
+		vq_err(vq, "Unexpected descriptor format for TX: out %d, int %d\n",
+			*out, *in);
+		return -EFAULT;
+	}
+
+	/* Sanity check */
+	*len = init_iov_iter(vq, &msg->msg_iter, nvq->vhost_hlen, *out);
+	if (*len == 0) {
+		vq_err(vq, "Unexpected header len for TX: %zd expected %zd\n",
+			*len, nvq->vhost_hlen);
+		return -EFAULT;
+	}
+
+	return ret;
+}
+
+static bool tx_can_batch(struct vhost_virtqueue *vq, size_t total_len)
+{
+	return total_len < VHOST_NET_WEIGHT &&
+	       !vhost_vq_avail_empty(vq->dev, vq);
+}
+
+static void handle_tx_copy(struct vhost_net *net, struct socket *sock)
 {
 	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
 	struct vhost_virtqueue *vq = &nvq->vq;
@@ -480,67 +555,103 @@ static void handle_tx(struct vhost_net *net)
 	};
 	size_t len, total_len = 0;
 	int err;
-	size_t hdr_size;
-	struct socket *sock;
-	struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
-	bool zcopy, zcopy_used;
 	int sent_pkts = 0;
 
-	mutex_lock(&vq->mutex);
-	sock = vq->private_data;
-	if (!sock)
-		goto out;
+	for (;;) {
+		bool busyloop_intr = false;
 
-	if (!vq_iotlb_prefetch(vq))
-		goto out;
+		head = get_tx_bufs(net, nvq, &msg, &out, &in, &len,
+				   &busyloop_intr);
+		/* On error, stop handling until the next kick. */
+		if (unlikely(head < 0))
+			break;
+		/* Nothing new?  Wait for eventfd to tell us they refilled. */
+		if (head == vq->num) {
+			if (unlikely(busyloop_intr)) {
+				vhost_poll_queue(&vq->poll);
+			} else if (unlikely(vhost_enable_notify(&net->dev,
+								vq))) {
+				vhost_disable_notify(&net->dev, vq);
+				continue;
+			}
+			break;
+		}
 
-	vhost_disable_notify(&net->dev, vq);
-	vhost_net_disable_vq(net, vq);
+		vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head);
+		vq->heads[nvq->done_idx].len = 0;
 
-	hdr_size = nvq->vhost_hlen;
-	zcopy = nvq->ubufs;
+		total_len += len;
+		if (tx_can_batch(vq, total_len))
+			msg.msg_flags |= MSG_MORE;
+		else
+			msg.msg_flags &= ~MSG_MORE;
+
+		/* TODO: Check specific error and bomb out unless ENOBUFS? */
+		err = sock->ops->sendmsg(sock, &msg, len);
+		if (unlikely(err < 0)) {
+			vhost_discard_vq_desc(vq, 1);
+			vhost_net_enable_vq(net, vq);
+			break;
+		}
+		if (err != len)
+			pr_debug("Truncated TX packet: len %d != %zd\n",
+				 err, len);
+		if (++nvq->done_idx >= VHOST_NET_BATCH)
+			vhost_net_signal_used(nvq);
+		if (vhost_exceeds_weight(++sent_pkts, total_len)) {
+			vhost_poll_queue(&vq->poll);
+			break;
+		}
+	}
+
+	vhost_net_signal_used(nvq);
+}
+
+static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock)
+{
+	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
+	struct vhost_virtqueue *vq = &nvq->vq;
+	unsigned out, in;
+	int head;
+	struct msghdr msg = {
+		.msg_name = NULL,
+		.msg_namelen = 0,
+		.msg_control = NULL,
+		.msg_controllen = 0,
+		.msg_flags = MSG_DONTWAIT,
+	};
+	size_t len, total_len = 0;
+	int err;
+	struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
+	bool zcopy_used;
+	int sent_pkts = 0;
 
 	for (;;) {
-		/* Release DMAs done buffers first */
-		if (zcopy)
-			vhost_zerocopy_signal_used(net, vq);
+		bool busyloop_intr;
 
+		/* Release DMAs done buffers first */
+		vhost_zerocopy_signal_used(net, vq);
 
-		head = vhost_net_tx_get_vq_desc(net, vq, vq->iov,
-						ARRAY_SIZE(vq->iov),
-						&out, &in);
+		busyloop_intr = false;
+		head = get_tx_bufs(net, nvq, &msg, &out, &in, &len,
+				   &busyloop_intr);
 		/* On error, stop handling until the next kick. */
 		if (unlikely(head < 0))
 			break;
 		/* Nothing new?  Wait for eventfd to tell us they refilled. */
 		if (head == vq->num) {
-			if (unlikely(vhost_enable_notify(&net->dev, vq))) {
+			if (unlikely(busyloop_intr)) {
+				vhost_poll_queue(&vq->poll);
+			} else if (unlikely(vhost_enable_notify(&net->dev, vq))) {
 				vhost_disable_notify(&net->dev, vq);
 				continue;
 			}
 			break;
 		}
-		if (in) {
-			vq_err(vq, "Unexpected descriptor format for TX: "
-			       "out %d, int %d\n", out, in);
-			break;
-		}
-		/* Skip header. TODO: support TSO. */
-		len = iov_length(vq->iov, out);
-		iov_iter_init(&msg.msg_iter, WRITE, vq->iov, out, len);
-		iov_iter_advance(&msg.msg_iter, hdr_size);
-		/* Sanity check */
-		if (!msg_data_left(&msg)) {
-			vq_err(vq, "Unexpected header len for TX: "
-			       "%zd expected %zd\n",
-			       len, hdr_size);
-			break;
-		}
-		len = msg_data_left(&msg);
 
-		zcopy_used = zcopy && len >= VHOST_GOODCOPY_LEN
-				   && !vhost_exceeds_maxpend(net)
-				   && vhost_net_tx_select_zcopy(net);
+		zcopy_used = len >= VHOST_GOODCOPY_LEN
+			     && !vhost_exceeds_maxpend(net)
+			     && vhost_net_tx_select_zcopy(net);
 
 		/* use msg_control to pass vhost zerocopy ubuf info to skb */
 		if (zcopy_used) {
@@ -562,10 +673,8 @@ static void handle_tx(struct vhost_net *net)
 			msg.msg_control = NULL;
 			ubufs = NULL;
 		}
-
 		total_len += len;
-		if (total_len < VHOST_NET_WEIGHT &&
-		    !vhost_vq_avail_empty(&net->dev, vq) &&
+		if (tx_can_batch(vq, total_len) &&
 		    likely(!vhost_exceeds_maxpend(net))) {
 			msg.msg_flags |= MSG_MORE;
 		} else {
@@ -592,12 +701,37 @@ static void handle_tx(struct vhost_net *net)
 		else
 			vhost_zerocopy_signal_used(net, vq);
 		vhost_net_tx_packet(net);
-		if (unlikely(total_len >= VHOST_NET_WEIGHT) ||
-		    unlikely(++sent_pkts >= VHOST_NET_PKT_WEIGHT)) {
+		if (unlikely(vhost_exceeds_weight(++sent_pkts, total_len))) {
 			vhost_poll_queue(&vq->poll);
 			break;
 		}
 	}
+}
+
+/* Expects to be always run from workqueue - which acts as
+ * read-size critical section for our kind of RCU. */
+static void handle_tx(struct vhost_net *net)
+{
+	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
+	struct vhost_virtqueue *vq = &nvq->vq;
+	struct socket *sock;
+
+	mutex_lock(&vq->mutex);
+	sock = vq->private_data;
+	if (!sock)
+		goto out;
+
+	if (!vq_iotlb_prefetch(vq))
+		goto out;
+
+	vhost_disable_notify(&net->dev, vq);
+	vhost_net_disable_vq(net, vq);
+
+	if (vhost_sock_zcopy(sock))
+		handle_tx_zerocopy(net, sock);
+	else
+		handle_tx_copy(net, sock);
+
 out:
 	mutex_unlock(&vq->mutex);
 }
@@ -633,53 +767,50 @@ static int sk_has_rx_data(struct sock *sk)
 	return skb_queue_empty(&sk->sk_receive_queue);
 }
 
-static void vhost_rx_signal_used(struct vhost_net_virtqueue *nvq)
+static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk,
+				      bool *busyloop_intr)
 {
-	struct vhost_virtqueue *vq = &nvq->vq;
-	struct vhost_dev *dev = vq->dev;
-
-	if (!nvq->done_idx)
-		return;
-
-	vhost_add_used_and_signal_n(dev, vq, vq->heads, nvq->done_idx);
-	nvq->done_idx = 0;
-}
-
-static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
-{
-	struct vhost_net_virtqueue *rvq = &net->vqs[VHOST_NET_VQ_RX];
-	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
-	struct vhost_virtqueue *vq = &nvq->vq;
+	struct vhost_net_virtqueue *rnvq = &net->vqs[VHOST_NET_VQ_RX];
+	struct vhost_net_virtqueue *tnvq = &net->vqs[VHOST_NET_VQ_TX];
+	struct vhost_virtqueue *rvq = &rnvq->vq;
+	struct vhost_virtqueue *tvq = &tnvq->vq;
 	unsigned long uninitialized_var(endtime);
-	int len = peek_head_len(rvq, sk);
+	int len = peek_head_len(rnvq, sk);
 
-	if (!len && vq->busyloop_timeout) {
+	if (!len && tvq->busyloop_timeout) {
 		/* Flush batched heads first */
-		vhost_rx_signal_used(rvq);
+		vhost_net_signal_used(rnvq);
 		/* Both tx vq and rx socket were polled here */
-		mutex_lock_nested(&vq->mutex, 1);
-		vhost_disable_notify(&net->dev, vq);
+		mutex_lock_nested(&tvq->mutex, 1);
+		vhost_disable_notify(&net->dev, tvq);
 
 		preempt_disable();
-		endtime = busy_clock() + vq->busyloop_timeout;
+		endtime = busy_clock() + tvq->busyloop_timeout;
 
-		while (vhost_can_busy_poll(&net->dev, endtime) &&
-		       !sk_has_rx_data(sk) &&
-		       vhost_vq_avail_empty(&net->dev, vq))
+		while (vhost_can_busy_poll(endtime)) {
+			if (vhost_has_work(&net->dev)) {
+				*busyloop_intr = true;
+				break;
+			}
+			if ((sk_has_rx_data(sk) &&
+			     !vhost_vq_avail_empty(&net->dev, rvq)) ||
+			    !vhost_vq_avail_empty(&net->dev, tvq))
+				break;
 			cpu_relax();
+		}
 
 		preempt_enable();
 
-		if (!vhost_vq_avail_empty(&net->dev, vq))
-			vhost_poll_queue(&vq->poll);
-		else if (unlikely(vhost_enable_notify(&net->dev, vq))) {
-			vhost_disable_notify(&net->dev, vq);
-			vhost_poll_queue(&vq->poll);
+		if (!vhost_vq_avail_empty(&net->dev, tvq)) {
+			vhost_poll_queue(&tvq->poll);
+		} else if (unlikely(vhost_enable_notify(&net->dev, tvq))) {
+			vhost_disable_notify(&net->dev, tvq);
+			vhost_poll_queue(&tvq->poll);
 		}
 
-		mutex_unlock(&vq->mutex);
+		mutex_unlock(&tvq->mutex);
 
-		len = peek_head_len(rvq, sk);
+		len = peek_head_len(rnvq, sk);
 	}
 
 	return len;
@@ -786,6 +917,7 @@ static void handle_rx(struct vhost_net *net)
 	s16 headcount;
 	size_t vhost_hlen, sock_hlen;
 	size_t vhost_len, sock_len;
+	bool busyloop_intr = false;
 	struct socket *sock;
 	struct iov_iter fixup;
 	__virtio16 num_buffers;
@@ -809,7 +941,8 @@ static void handle_rx(struct vhost_net *net)
 		vq->log : NULL;
 	mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF);
 
-	while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk))) {
+	while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk,
+						      &busyloop_intr))) {
 		sock_len += sock_hlen;
 		vhost_len = sock_len + vhost_hlen;
 		headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx,
@@ -820,7 +953,9 @@ static void handle_rx(struct vhost_net *net)
 			goto out;
 		/* OK, now we need to know about added descriptors. */
 		if (!headcount) {
-			if (unlikely(vhost_enable_notify(&net->dev, vq))) {
+			if (unlikely(busyloop_intr)) {
+				vhost_poll_queue(&vq->poll);
+			} else if (unlikely(vhost_enable_notify(&net->dev, vq))) {
 				/* They have slipped one in as we were
 				 * doing that: check again. */
 				vhost_disable_notify(&net->dev, vq);
@@ -830,6 +965,7 @@ static void handle_rx(struct vhost_net *net)
 			 * they refilled. */
 			goto out;
 		}
+		busyloop_intr = false;
 		if (nvq->rx_ring)
 			msg.msg_control = vhost_net_buf_consume(&nvq->rxq);
 		/* On overrun, truncate and discard */
@@ -885,20 +1021,22 @@ static void handle_rx(struct vhost_net *net)
 			goto out;
 		}
 		nvq->done_idx += headcount;
-		if (nvq->done_idx > VHOST_RX_BATCH)
-			vhost_rx_signal_used(nvq);
+		if (nvq->done_idx > VHOST_NET_BATCH)
+			vhost_net_signal_used(nvq);
 		if (unlikely(vq_log))
 			vhost_log_write(vq, vq_log, log, vhost_len);
 		total_len += vhost_len;
-		if (unlikely(total_len >= VHOST_NET_WEIGHT) ||
-		    unlikely(++recv_pkts >= VHOST_NET_PKT_WEIGHT)) {
+		if (unlikely(vhost_exceeds_weight(++recv_pkts, total_len))) {
 			vhost_poll_queue(&vq->poll);
 			goto out;
 		}
 	}
-	vhost_net_enable_vq(net, vq);
+	if (unlikely(busyloop_intr))
+		vhost_poll_queue(&vq->poll);
+	else
+		vhost_net_enable_vq(net, vq);
 out:
-	vhost_rx_signal_used(nvq);
+	vhost_net_signal_used(nvq);
 	mutex_unlock(&vq->mutex);
 }
 
@@ -951,7 +1089,7 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 		return -ENOMEM;
 	}
 
-	queue = kmalloc_array(VHOST_RX_BATCH, sizeof(void *),
+	queue = kmalloc_array(VHOST_NET_BATCH, sizeof(void *),
 			      GFP_KERNEL);
 	if (!queue) {
 		kfree(vqs);
@@ -1265,6 +1403,21 @@ done:
 	return err;
 }
 
+static int vhost_net_set_backend_features(struct vhost_net *n, u64 features)
+{
+	int i;
+
+	mutex_lock(&n->dev.mutex);
+	for (i = 0; i < VHOST_NET_VQ_MAX; ++i) {
+		mutex_lock(&n->vqs[i].vq.mutex);
+		n->vqs[i].vq.acked_backend_features = features;
+		mutex_unlock(&n->vqs[i].vq.mutex);
+	}
+	mutex_unlock(&n->dev.mutex);
+
+	return 0;
+}
+
 static int vhost_net_set_features(struct vhost_net *n, u64 features)
 {
 	size_t vhost_hlen, sock_hlen, hdr_len;
@@ -1355,6 +1508,17 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl,
 		if (features & ~VHOST_NET_FEATURES)
 			return -EOPNOTSUPP;
 		return vhost_net_set_features(n, features);
+	case VHOST_GET_BACKEND_FEATURES:
+		features = VHOST_NET_BACKEND_FEATURES;
+		if (copy_to_user(featurep, &features, sizeof(features)))
+			return -EFAULT;
+		return 0;
+	case VHOST_SET_BACKEND_FEATURES:
+		if (copy_from_user(&features, featurep, sizeof(features)))
+			return -EFAULT;
+		if (features & ~VHOST_NET_BACKEND_FEATURES)
+			return -EOPNOTSUPP;
+		return vhost_net_set_backend_features(n, features);
 	case VHOST_RESET_OWNER:
 		return vhost_net_reset_owner(n);
 	case VHOST_SET_OWNER:
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 17fcd3b2e686..76f8d649147b 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -46,7 +46,6 @@
 #include <linux/virtio_scsi.h>
 #include <linux/llist.h>
 #include <linux/bitmap.h>
-#include <linux/percpu_ida.h>
 
 #include "vhost.h"
 
@@ -324,7 +323,7 @@ static void vhost_scsi_release_cmd(struct se_cmd *se_cmd)
 	}
 
 	vhost_scsi_put_inflight(tv_cmd->inflight);
-	percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag);
+	target_free_tag(se_sess, se_cmd);
 }
 
 static u32 vhost_scsi_sess_get_index(struct se_session *se_sess)
@@ -567,7 +566,7 @@ vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg,
 	struct se_session *se_sess;
 	struct scatterlist *sg, *prot_sg;
 	struct page **pages;
-	int tag;
+	int tag, cpu;
 
 	tv_nexus = tpg->tpg_nexus;
 	if (!tv_nexus) {
@@ -576,7 +575,7 @@ vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg,
 	}
 	se_sess = tv_nexus->tvn_se_sess;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
+	tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
 	if (tag < 0) {
 		pr_err("Unable to obtain tag for vhost_scsi_cmd\n");
 		return ERR_PTR(-ENOMEM);
@@ -591,6 +590,7 @@ vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg,
 	cmd->tvc_prot_sgl = prot_sg;
 	cmd->tvc_upages = pages;
 	cmd->tvc_se_cmd.map_tag = tag;
+	cmd->tvc_se_cmd.map_cpu = cpu;
 	cmd->tvc_tag = scsi_tag;
 	cmd->tvc_lun = lun;
 	cmd->tvc_task_attr = task_attr;
@@ -1738,7 +1738,7 @@ static int vhost_scsi_make_nexus(struct vhost_scsi_tpg *tpg,
 	 * struct se_node_acl for the vhost_scsi struct se_portal_group with
 	 * the SCSI Initiator port name of the passed configfs group 'name'.
 	 */
-	tv_nexus->tvn_se_sess = target_alloc_session(&tpg->se_tpg,
+	tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg,
 					VHOST_SCSI_DEFAULT_TAGS,
 					sizeof(struct vhost_scsi_cmd),
 					TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS,
@@ -1797,7 +1797,7 @@ static int vhost_scsi_drop_nexus(struct vhost_scsi_tpg *tpg)
 	/*
 	 * Release the SCSI I_T Nexus to the emulated vhost Target Port
 	 */
-	transport_deregister_session(tv_nexus->tvn_se_sess);
+	target_remove_session(se_sess);
 	tpg->tpg_nexus = NULL;
 	mutex_unlock(&tpg->tv_tpg_mutex);
 
@@ -1912,9 +1912,7 @@ static struct configfs_attribute *vhost_scsi_tpg_attrs[] = {
 };
 
 static struct se_portal_group *
-vhost_scsi_make_tpg(struct se_wwn *wwn,
-		   struct config_group *group,
-		   const char *name)
+vhost_scsi_make_tpg(struct se_wwn *wwn, const char *name)
 {
 	struct vhost_scsi_tport *tport = container_of(wwn,
 			struct vhost_scsi_tport, tport_wwn);
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index ed3114556fda..96c1d8400822 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -315,6 +315,7 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->log_addr = -1ull;
 	vq->private_data = NULL;
 	vq->acked_features = 0;
+	vq->acked_backend_features = 0;
 	vq->log_base = NULL;
 	vq->error_ctx = NULL;
 	vq->kick = NULL;
@@ -1027,28 +1028,40 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev,
 ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
 			     struct iov_iter *from)
 {
-	struct vhost_msg_node node;
-	unsigned size = sizeof(struct vhost_msg);
-	size_t ret;
-	int err;
+	struct vhost_iotlb_msg msg;
+	size_t offset;
+	int type, ret;
 
-	if (iov_iter_count(from) < size)
-		return 0;
-	ret = copy_from_iter(&node.msg, size, from);
-	if (ret != size)
+	ret = copy_from_iter(&type, sizeof(type), from);
+	if (ret != sizeof(type))
 		goto done;
 
-	switch (node.msg.type) {
+	switch (type) {
 	case VHOST_IOTLB_MSG:
-		err = vhost_process_iotlb_msg(dev, &node.msg.iotlb);
-		if (err)
-			ret = err;
+		/* There maybe a hole after type for V1 message type,
+		 * so skip it here.
+		 */
+		offset = offsetof(struct vhost_msg, iotlb) - sizeof(int);
+		break;
+	case VHOST_IOTLB_MSG_V2:
+		offset = sizeof(__u32);
 		break;
 	default:
 		ret = -EINVAL;
-		break;
+		goto done;
+	}
+
+	iov_iter_advance(from, offset);
+	ret = copy_from_iter(&msg, sizeof(msg), from);
+	if (ret != sizeof(msg))
+		goto done;
+	if (vhost_process_iotlb_msg(dev, &msg)) {
+		ret = -EFAULT;
+		goto done;
 	}
 
+	ret = (type == VHOST_IOTLB_MSG) ? sizeof(struct vhost_msg) :
+	      sizeof(struct vhost_msg_v2);
 done:
 	return ret;
 }
@@ -1107,13 +1120,28 @@ ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to,
 		finish_wait(&dev->wait, &wait);
 
 	if (node) {
-		ret = copy_to_iter(&node->msg, size, to);
+		struct vhost_iotlb_msg *msg;
+		void *start = &node->msg;
+
+		switch (node->msg.type) {
+		case VHOST_IOTLB_MSG:
+			size = sizeof(node->msg);
+			msg = &node->msg.iotlb;
+			break;
+		case VHOST_IOTLB_MSG_V2:
+			size = sizeof(node->msg_v2);
+			msg = &node->msg_v2.iotlb;
+			break;
+		default:
+			BUG();
+			break;
+		}
 
-		if (ret != size || node->msg.type != VHOST_IOTLB_MISS) {
+		ret = copy_to_iter(start, size, to);
+		if (ret != size || msg->type != VHOST_IOTLB_MISS) {
 			kfree(node);
 			return ret;
 		}
-
 		vhost_enqueue_msg(dev, &dev->pending_list, node);
 	}
 
@@ -1126,12 +1154,19 @@ static int vhost_iotlb_miss(struct vhost_virtqueue *vq, u64 iova, int access)
 	struct vhost_dev *dev = vq->dev;
 	struct vhost_msg_node *node;
 	struct vhost_iotlb_msg *msg;
+	bool v2 = vhost_backend_has_feature(vq, VHOST_BACKEND_F_IOTLB_MSG_V2);
 
-	node = vhost_new_msg(vq, VHOST_IOTLB_MISS);
+	node = vhost_new_msg(vq, v2 ? VHOST_IOTLB_MSG_V2 : VHOST_IOTLB_MSG);
 	if (!node)
 		return -ENOMEM;
 
-	msg = &node->msg.iotlb;
+	if (v2) {
+		node->msg_v2.type = VHOST_IOTLB_MSG_V2;
+		msg = &node->msg_v2.iotlb;
+	} else {
+		msg = &node->msg.iotlb;
+	}
+
 	msg->type = VHOST_IOTLB_MISS;
 	msg->iova = iova;
 	msg->perm = access;
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 6c844b90a168..466ef7542291 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -132,6 +132,7 @@ struct vhost_virtqueue {
 	struct vhost_umem *iotlb;
 	void *private_data;
 	u64 acked_features;
+	u64 acked_backend_features;
 	/* Log write descriptors */
 	void __user *log_base;
 	struct vhost_log *log;
@@ -147,7 +148,10 @@ struct vhost_virtqueue {
 };
 
 struct vhost_msg_node {
-  struct vhost_msg msg;
+  union {
+	  struct vhost_msg msg;
+	  struct vhost_msg_v2 msg_v2;
+  };
   struct vhost_virtqueue *vq;
   struct list_head node;
 };
@@ -238,6 +242,11 @@ static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit)
 	return vq->acked_features & (1ULL << bit);
 }
 
+static inline bool vhost_backend_has_feature(struct vhost_virtqueue *vq, int bit)
+{
+	return vq->acked_backend_features & (1ULL << bit);
+}
+
 #ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY
 static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq)
 {
diff --git a/drivers/video/console/Kconfig b/drivers/video/console/Kconfig
index 4110ba7d7ca9..e91edef98633 100644
--- a/drivers/video/console/Kconfig
+++ b/drivers/video/console/Kconfig
@@ -150,6 +150,17 @@ config FRAMEBUFFER_CONSOLE_ROTATION
          such that other users of the framebuffer will remain normally
          oriented.
 
+config FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER
+	bool "Framebuffer Console Deferred Takeover"
+	depends on FRAMEBUFFER_CONSOLE=y && DUMMY_CONSOLE=y
+	help
+	  If enabled this defers the framebuffer console taking over the
+	  console from the dummy console until the first text is displayed on
+	  the console. This is useful in combination with the "quiet" kernel
+	  commandline option to keep the framebuffer contents initially put up
+	  by the firmware in place, rather then replacing the contents with a
+	  black screen as soon as fbcon loads.
+
 config STI_CONSOLE
         bool "STI text console"
 	depends on PARISC && HAS_IOMEM
diff --git a/drivers/video/console/dummycon.c b/drivers/video/console/dummycon.c
index f2eafe2ed980..0254251fdd79 100644
--- a/drivers/video/console/dummycon.c
+++ b/drivers/video/console/dummycon.c
@@ -26,6 +26,67 @@
 #define DUMMY_ROWS	CONFIG_DUMMY_CONSOLE_ROWS
 #endif
 
+#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER
+/* These are both protected by the console_lock */
+static RAW_NOTIFIER_HEAD(dummycon_output_nh);
+static bool dummycon_putc_called;
+
+void dummycon_register_output_notifier(struct notifier_block *nb)
+{
+	raw_notifier_chain_register(&dummycon_output_nh, nb);
+
+	if (dummycon_putc_called)
+		nb->notifier_call(nb, 0, NULL);
+}
+EXPORT_SYMBOL_GPL(dummycon_register_output_notifier);
+
+void dummycon_unregister_output_notifier(struct notifier_block *nb)
+{
+	raw_notifier_chain_unregister(&dummycon_output_nh, nb);
+}
+EXPORT_SYMBOL_GPL(dummycon_unregister_output_notifier);
+
+static void dummycon_putc(struct vc_data *vc, int c, int ypos, int xpos)
+{
+	dummycon_putc_called = true;
+	raw_notifier_call_chain(&dummycon_output_nh, 0, NULL);
+}
+
+static void dummycon_putcs(struct vc_data *vc, const unsigned short *s,
+			   int count, int ypos, int xpos)
+{
+	int i;
+
+	if (!dummycon_putc_called) {
+		/* Ignore erases */
+		for (i = 0 ; i < count; i++) {
+			if (s[i] != vc->vc_video_erase_char)
+				break;
+		}
+		if (i == count)
+			return;
+
+		dummycon_putc_called = true;
+	}
+
+	raw_notifier_call_chain(&dummycon_output_nh, 0, NULL);
+}
+
+static int dummycon_blank(struct vc_data *vc, int blank, int mode_switch)
+{
+	/* Redraw, so that we get putc(s) for output done while blanked */
+	return 1;
+}
+#else
+static void dummycon_putc(struct vc_data *vc, int c, int ypos, int xpos) { }
+static void dummycon_putcs(struct vc_data *vc, const unsigned short *s,
+			   int count, int ypos, int xpos) { }
+static int dummycon_blank(struct vc_data *vc, int blank, int mode_switch)
+{
+	return 0;
+}
+#endif
+
 static const char *dummycon_startup(void)
 {
     return "dummy device";
@@ -44,9 +105,6 @@ static void dummycon_init(struct vc_data *vc, int init)
 static void dummycon_deinit(struct vc_data *vc) { }
 static void dummycon_clear(struct vc_data *vc, int sy, int sx, int height,
 			   int width) { }
-static void dummycon_putc(struct vc_data *vc, int c, int ypos, int xpos) { }
-static void dummycon_putcs(struct vc_data *vc, const unsigned short *s,
-			   int count, int ypos, int xpos) { }
 static void dummycon_cursor(struct vc_data *vc, int mode) { }
 
 static bool dummycon_scroll(struct vc_data *vc, unsigned int top,
@@ -61,11 +119,6 @@ static int dummycon_switch(struct vc_data *vc)
 	return 0;
 }
 
-static int dummycon_blank(struct vc_data *vc, int blank, int mode_switch)
-{
-	return 0;
-}
-
 static int dummycon_font_set(struct vc_data *vc, struct console_font *font,
 			     unsigned int flags)
 {
diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index c910e74d46ff..5fb156bdcf4e 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -129,6 +129,12 @@ static inline void fbcon_map_override(void)
 }
 #endif /* CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY */
 
+#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER
+static bool deferred_takeover = true;
+#else
+#define deferred_takeover false
+#endif
+
 /* font data */
 static char fontname[40];
 
@@ -499,6 +505,12 @@ static int __init fb_console_setup(char *this_opt)
 				margin_color = simple_strtoul(options, &options, 0);
 			continue;
 		}
+#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER
+		if (!strcmp(options, "nodefer")) {
+			deferred_takeover = false;
+			continue;
+		}
+#endif
 	}
 	return 1;
 }
@@ -828,6 +840,8 @@ static int set_con2fb_map(int unit, int newidx, int user)
 	struct fb_info *oldinfo = NULL;
  	int found, err = 0;
 
+	WARN_CONSOLE_UNLOCKED();
+
 	if (oldidx == newidx)
 		return 0;
 
@@ -3044,6 +3058,8 @@ static int fbcon_fb_unbind(int idx)
 {
 	int i, new_idx = -1, ret = 0;
 
+	WARN_CONSOLE_UNLOCKED();
+
 	if (!fbcon_has_console_bind)
 		return 0;
 
@@ -3094,6 +3110,11 @@ static int fbcon_fb_unregistered(struct fb_info *info)
 {
 	int i, idx;
 
+	WARN_CONSOLE_UNLOCKED();
+
+	if (deferred_takeover)
+		return 0;
+
 	idx = info->node;
 	for (i = first_fb_vc; i <= last_fb_vc; i++) {
 		if (con2fb_map[i] == idx)
@@ -3131,6 +3152,16 @@ static int fbcon_fb_unregistered(struct fb_info *info)
 static void fbcon_remap_all(int idx)
 {
 	int i;
+
+	WARN_CONSOLE_UNLOCKED();
+
+	if (deferred_takeover) {
+		for (i = first_fb_vc; i <= last_fb_vc; i++)
+			con2fb_map_boot[i] = idx;
+		fbcon_map_override();
+		return;
+	}
+
 	for (i = first_fb_vc; i <= last_fb_vc; i++)
 		set_con2fb_map(i, idx, 0);
 
@@ -3177,9 +3208,16 @@ static int fbcon_fb_registered(struct fb_info *info)
 {
 	int ret = 0, i, idx;
 
+	WARN_CONSOLE_UNLOCKED();
+
 	idx = info->node;
 	fbcon_select_primary(info);
 
+	if (deferred_takeover) {
+		pr_info("fbcon: Deferring console take-over\n");
+		return 0;
+	}
+
 	if (info_idx == -1) {
 		for (i = first_fb_vc; i <= last_fb_vc; i++) {
 			if (con2fb_map_boot[i] == idx) {
@@ -3555,8 +3593,46 @@ static int fbcon_init_device(void)
 	return 0;
 }
 
+#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER
+static struct notifier_block fbcon_output_nb;
+
+static int fbcon_output_notifier(struct notifier_block *nb,
+				 unsigned long action, void *data)
+{
+	int i;
+
+	WARN_CONSOLE_UNLOCKED();
+
+	pr_info("fbcon: Taking over console\n");
+
+	dummycon_unregister_output_notifier(&fbcon_output_nb);
+	deferred_takeover = false;
+	logo_shown = FBCON_LOGO_DONTSHOW;
+
+	for (i = 0; i < FB_MAX; i++) {
+		if (registered_fb[i])
+			fbcon_fb_registered(registered_fb[i]);
+	}
+
+	return NOTIFY_OK;
+}
+
+static void fbcon_register_output_notifier(void)
+{
+	fbcon_output_nb.notifier_call = fbcon_output_notifier;
+	dummycon_register_output_notifier(&fbcon_output_nb);
+}
+#else
+static inline void fbcon_register_output_notifier(void) {}
+#endif
+
 static void fbcon_start(void)
 {
+	if (deferred_takeover) {
+		fbcon_register_output_notifier();
+		return;
+	}
+
 	if (num_registered_fb) {
 		int i;
 
@@ -3583,6 +3659,13 @@ static void fbcon_exit(void)
 	if (fbcon_has_exited)
 		return;
 
+#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER
+	if (deferred_takeover) {
+		dummycon_unregister_output_notifier(&fbcon_output_nb);
+		deferred_takeover = false;
+	}
+#endif
+
 	kfree((void *)softback_buf);
 	softback_buf = 0UL;
 
diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c
index 46a4484e3da7..c6f78d27947b 100644
--- a/drivers/video/fbdev/efifb.c
+++ b/drivers/video/fbdev/efifb.c
@@ -20,7 +20,7 @@
 #include <drm/drm_connector.h>  /* For DRM_MODE_PANEL_ORIENTATION_* */
 
 static bool request_mem_succeeded = false;
-static bool nowc = false;
+static u64 mem_flags = EFI_MEMORY_WC | EFI_MEMORY_UC;
 
 static struct fb_var_screeninfo efifb_defined = {
 	.activate		= FB_ACTIVATE_NOW,
@@ -68,8 +68,12 @@ static int efifb_setcolreg(unsigned regno, unsigned red, unsigned green,
 
 static void efifb_destroy(struct fb_info *info)
 {
-	if (info->screen_base)
-		iounmap(info->screen_base);
+	if (info->screen_base) {
+		if (mem_flags & (EFI_MEMORY_UC | EFI_MEMORY_WC))
+			iounmap(info->screen_base);
+		else
+			memunmap(info->screen_base);
+	}
 	if (request_mem_succeeded)
 		release_mem_region(info->apertures->ranges[0].base,
 				   info->apertures->ranges[0].size);
@@ -104,7 +108,7 @@ static int efifb_setup(char *options)
 			else if (!strncmp(this_opt, "width:", 6))
 				screen_info.lfb_width = simple_strtoul(this_opt+6, NULL, 0);
 			else if (!strcmp(this_opt, "nowc"))
-				nowc = true;
+				mem_flags &= ~EFI_MEMORY_WC;
 		}
 	}
 
@@ -164,6 +168,7 @@ static int efifb_probe(struct platform_device *dev)
 	unsigned int size_remap;
 	unsigned int size_total;
 	char *option = NULL;
+	efi_memory_desc_t md;
 
 	if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || pci_dev_disabled)
 		return -ENODEV;
@@ -272,12 +277,35 @@ static int efifb_probe(struct platform_device *dev)
 	info->apertures->ranges[0].base = efifb_fix.smem_start;
 	info->apertures->ranges[0].size = size_remap;
 
-	if (nowc)
-		info->screen_base = ioremap(efifb_fix.smem_start, efifb_fix.smem_len);
-	else
-		info->screen_base = ioremap_wc(efifb_fix.smem_start, efifb_fix.smem_len);
+	if (!efi_mem_desc_lookup(efifb_fix.smem_start, &md)) {
+		if ((efifb_fix.smem_start + efifb_fix.smem_len) >
+		    (md.phys_addr + (md.num_pages << EFI_PAGE_SHIFT))) {
+			pr_err("efifb: video memory @ 0x%lx spans multiple EFI memory regions\n",
+			       efifb_fix.smem_start);
+			err = -EIO;
+			goto err_release_fb;
+		}
+		/*
+		 * If the UEFI memory map covers the efifb region, we may only
+		 * remap it using the attributes the memory map prescribes.
+		 */
+		mem_flags |= EFI_MEMORY_WT | EFI_MEMORY_WB;
+		mem_flags &= md.attribute;
+	}
+	if (mem_flags & EFI_MEMORY_WC)
+		info->screen_base = ioremap_wc(efifb_fix.smem_start,
+					       efifb_fix.smem_len);
+	else if (mem_flags & EFI_MEMORY_UC)
+		info->screen_base = ioremap(efifb_fix.smem_start,
+					    efifb_fix.smem_len);
+	else if (mem_flags & EFI_MEMORY_WT)
+		info->screen_base = memremap(efifb_fix.smem_start,
+					     efifb_fix.smem_len, MEMREMAP_WT);
+	else if (mem_flags & EFI_MEMORY_WB)
+		info->screen_base = memremap(efifb_fix.smem_start,
+					     efifb_fix.smem_len, MEMREMAP_WB);
 	if (!info->screen_base) {
-		pr_err("efifb: abort, cannot ioremap video memory 0x%x @ 0x%lx\n",
+		pr_err("efifb: abort, cannot remap video memory 0x%x @ 0x%lx\n",
 			efifb_fix.smem_len, efifb_fix.smem_start);
 		err = -EIO;
 		goto err_release_fb;
@@ -371,7 +399,10 @@ err_fb_dealoc:
 err_groups:
 	sysfs_remove_groups(&dev->dev.kobj, efifb_groups);
 err_unmap:
-	iounmap(info->screen_base);
+	if (mem_flags & (EFI_MEMORY_UC | EFI_MEMORY_WC))
+		iounmap(info->screen_base);
+	else
+		memunmap(info->screen_base);
 err_release_fb:
 	framebuffer_release(info);
 err_release_mem:
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/core.c b/drivers/video/fbdev/omap2/omapfb/dss/core.c
index 09e5bb013d28..a5e58a829ea0 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/core.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/core.c
@@ -137,8 +137,7 @@ static int dss_initialize_debugfs(void)
 
 static void dss_uninitialize_debugfs(void)
 {
-	if (dss_debugfs_dir)
-		debugfs_remove_recursive(dss_debugfs_dir);
+	debugfs_remove_recursive(dss_debugfs_dir);
 }
 
 int dss_debugfs_create_file(const char *name, void (*write)(struct seq_file *))
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dss_features.c b/drivers/video/fbdev/omap2/omapfb/dss/dss_features.c
index 8fc843b56b26..e8d428bc47e3 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dss_features.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dss_features.c
@@ -891,8 +891,7 @@ bool dss_has_feature(enum dss_feat_id id)
 
 void dss_feat_get_reg_field(enum dss_feat_reg_field id, u8 *start, u8 *end)
 {
-	if (id >= omap_current_dss_features->num_reg_fields)
-		BUG();
+	BUG_ON(id >= omap_current_dss_features->num_reg_fields);
 
 	*start = omap_current_dss_features->reg_fields[id].start;
 	*end = omap_current_dss_features->reg_fields[id].end;
diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-main.c b/drivers/video/fbdev/omap2/omapfb/omapfb-main.c
index e08e5664e330..3e7887c53d7c 100644
--- a/drivers/video/fbdev/omap2/omapfb/omapfb-main.c
+++ b/drivers/video/fbdev/omap2/omapfb/omapfb-main.c
@@ -287,7 +287,7 @@ static bool cmp_var_to_colormode(struct fb_var_screeninfo *var,
 			var->red.length == 0 ||
 			var->blue.length == 0 ||
 			var->green.length == 0)
-		return 0;
+		return false;
 
 	return var->bits_per_pixel == color->bits_per_pixel &&
 		cmp_component(&var->red, &color->red) &&
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 705aebd74e56..465a6f5142cc 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -421,7 +421,7 @@ const char *vp_bus_name(struct virtio_device *vdev)
  * - OR over all affinities for shared MSI
  * - ignore the affinity request if we're using INTX
  */
-int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
+int vp_set_vq_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask)
 {
 	struct virtio_device *vdev = vq->vdev;
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -435,11 +435,10 @@ int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
 	if (vp_dev->msix_enabled) {
 		mask = vp_dev->msix_affinity_masks[info->msix_vector];
 		irq = pci_irq_vector(vp_dev->pci_dev, info->msix_vector);
-		if (cpu == -1)
+		if (!cpu_mask)
 			irq_set_affinity_hint(irq, NULL);
 		else {
-			cpumask_clear(mask);
-			cpumask_set_cpu(cpu, mask);
+			cpumask_copy(mask, cpu_mask);
 			irq_set_affinity_hint(irq, mask);
 		}
 	}
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index 135ee3cf7175..02271002c2f3 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -141,7 +141,7 @@ const char *vp_bus_name(struct virtio_device *vdev);
  * - OR over all affinities for shared MSI
  * - ignore the affinity request if we're using INTX
  */
-int vp_set_vq_affinity(struct virtqueue *vq, int cpu);
+int vp_set_vq_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask);
 
 const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index);
 
diff --git a/drivers/w1/masters/Kconfig b/drivers/w1/masters/Kconfig
index 1708b2300c7a..00827d2897b5 100644
--- a/drivers/w1/masters/Kconfig
+++ b/drivers/w1/masters/Kconfig
@@ -49,7 +49,7 @@ config W1_MASTER_DS1WM
 
 config W1_MASTER_GPIO
 	tristate "GPIO 1-wire busmaster"
-	depends on GPIOLIB
+	depends on GPIOLIB || COMPILE_TEST
 	help
 	  Say Y here if you want to communicate with your 1-wire devices using
 	  GPIO pins. This driver uses the GPIO API to control the wire.
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index e5d0c28372ea..b459edfacff3 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -152,6 +152,16 @@ config XEN_GNTDEV
 	help
 	  Allows userspace processes to use grants.
 
+config XEN_GNTDEV_DMABUF
+	bool "Add support for dma-buf grant access device driver extension"
+	depends on XEN_GNTDEV && XEN_GRANT_DMA_ALLOC && DMA_SHARED_BUFFER
+	help
+	  Allows userspace processes and kernel modules to use Xen backed
+	  dma-buf implementation. With this extension grant references to
+	  the pages of an imported dma-buf can be exported for other domain
+	  use and grant references coming from a foreign domain can be
+	  converted into a local dma-buf for local export.
+
 config XEN_GRANT_DEV_ALLOC
 	tristate "User-space grant reference allocator driver"
 	depends on XEN
@@ -161,6 +171,20 @@ config XEN_GRANT_DEV_ALLOC
 	  to other domains. This can be used to implement frontend drivers
 	  or as part of an inter-domain shared memory channel.
 
+config XEN_GRANT_DMA_ALLOC
+	bool "Allow allocating DMA capable buffers with grant reference module"
+	depends on XEN && HAS_DMA
+	help
+	  Extends grant table module API to allow allocating DMA capable
+	  buffers and mapping foreign grant references on top of it.
+	  The resulting buffer is similar to one allocated by the balloon
+	  driver in that proper memory reservation is made by
+	  ({increase|decrease}_reservation and VA mappings are updated if
+	  needed).
+	  This is useful for sharing foreign buffers with HW drivers which
+	  cannot work with scattered buffers provided by the balloon driver,
+	  but require DMAable memory instead.
+
 config SWIOTLB_XEN
 	def_bool y
 	select SWIOTLB
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index 48b154276179..3e542f60f29f 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -2,6 +2,7 @@
 obj-$(CONFIG_HOTPLUG_CPU)		+= cpu_hotplug.o
 obj-$(CONFIG_X86)			+= fallback.o
 obj-y	+= grant-table.o features.o balloon.o manage.o preempt.o time.o
+obj-y	+= mem-reservation.o
 obj-y	+= events/
 obj-y	+= xenbus/
 
@@ -40,5 +41,6 @@ obj-$(CONFIG_XEN_PVCALLS_BACKEND)	+= pvcalls-back.o
 obj-$(CONFIG_XEN_PVCALLS_FRONTEND)	+= pvcalls-front.o
 xen-evtchn-y				:= evtchn.o
 xen-gntdev-y				:= gntdev.o
+xen-gntdev-$(CONFIG_XEN_GNTDEV_DMABUF)	+= gntdev-dmabuf.o
 xen-gntalloc-y				:= gntalloc.o
 xen-privcmd-y				:= privcmd.o privcmd-buf.o
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 065f0b607373..e12bb256036f 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -71,6 +71,7 @@
 #include <xen/balloon.h>
 #include <xen/features.h>
 #include <xen/page.h>
+#include <xen/mem-reservation.h>
 
 static int xen_hotplug_unpopulated;
 
@@ -157,13 +158,6 @@ static DECLARE_DELAYED_WORK(balloon_worker, balloon_process);
 #define GFP_BALLOON \
 	(GFP_HIGHUSER | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC)
 
-static void scrub_page(struct page *page)
-{
-#ifdef CONFIG_XEN_SCRUB_PAGES
-	clear_highpage(page);
-#endif
-}
-
 /* balloon_append: add the given page to the balloon. */
 static void __balloon_append(struct page *page)
 {
@@ -463,11 +457,6 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 	int rc;
 	unsigned long i;
 	struct page   *page;
-	struct xen_memory_reservation reservation = {
-		.address_bits = 0,
-		.extent_order = EXTENT_ORDER,
-		.domid        = DOMID_SELF
-	};
 
 	if (nr_pages > ARRAY_SIZE(frame_list))
 		nr_pages = ARRAY_SIZE(frame_list);
@@ -479,16 +468,11 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 			break;
 		}
 
-		/* XENMEM_populate_physmap requires a PFN based on Xen
-		 * granularity.
-		 */
 		frame_list[i] = page_to_xen_pfn(page);
 		page = balloon_next_page(page);
 	}
 
-	set_xen_guest_handle(reservation.extent_start, frame_list);
-	reservation.nr_extents = nr_pages;
-	rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation);
+	rc = xenmem_reservation_increase(nr_pages, frame_list);
 	if (rc <= 0)
 		return BP_EAGAIN;
 
@@ -496,29 +480,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 		page = balloon_retrieve(false);
 		BUG_ON(page == NULL);
 
-#ifdef CONFIG_XEN_HAVE_PVMMU
-		/*
-		 * We don't support PV MMU when Linux and Xen is using
-		 * different page granularity.
-		 */
-		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
-
-		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-			unsigned long pfn = page_to_pfn(page);
-
-			set_phys_to_machine(pfn, frame_list[i]);
-
-			/* Link back into the page tables if not highmem. */
-			if (!PageHighMem(page)) {
-				int ret;
-				ret = HYPERVISOR_update_va_mapping(
-						(unsigned long)__va(pfn << PAGE_SHIFT),
-						mfn_pte(frame_list[i], PAGE_KERNEL),
-						0);
-				BUG_ON(ret);
-			}
-		}
-#endif
+		xenmem_reservation_va_mapping_update(1, &page, &frame_list[i]);
 
 		/* Relinquish the page back to the allocator. */
 		free_reserved_page(page);
@@ -535,11 +497,6 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 	unsigned long i;
 	struct page *page, *tmp;
 	int ret;
-	struct xen_memory_reservation reservation = {
-		.address_bits = 0,
-		.extent_order = EXTENT_ORDER,
-		.domid        = DOMID_SELF
-	};
 	LIST_HEAD(pages);
 
 	if (nr_pages > ARRAY_SIZE(frame_list))
@@ -553,7 +510,7 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 			break;
 		}
 		adjust_managed_page_count(page, -1);
-		scrub_page(page);
+		xenmem_reservation_scrub_page(page);
 		list_add(&page->lru, &pages);
 	}
 
@@ -572,28 +529,10 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 	 */
 	i = 0;
 	list_for_each_entry_safe(page, tmp, &pages, lru) {
-		/* XENMEM_decrease_reservation requires a GFN */
 		frame_list[i++] = xen_page_to_gfn(page);
 
-#ifdef CONFIG_XEN_HAVE_PVMMU
-		/*
-		 * We don't support PV MMU when Linux and Xen is using
-		 * different page granularity.
-		 */
-		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
-
-		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-			unsigned long pfn = page_to_pfn(page);
+		xenmem_reservation_va_mapping_reset(1, &page);
 
-			if (!PageHighMem(page)) {
-				ret = HYPERVISOR_update_va_mapping(
-						(unsigned long)__va(pfn << PAGE_SHIFT),
-						__pte_ma(0), 0);
-				BUG_ON(ret);
-			}
-			__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
-		}
-#endif
 		list_del(&page->lru);
 
 		balloon_append(page);
@@ -601,9 +540,7 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 
 	flush_tlb_all();
 
-	set_xen_guest_handle(reservation.extent_start, frame_list);
-	reservation.nr_extents   = nr_pages;
-	ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
+	ret = xenmem_reservation_decrease(nr_pages, frame_list);
 	BUG_ON(ret != nr_pages);
 
 	balloon_stats.current_pages -= nr_pages;
diff --git a/drivers/xen/biomerge.c b/drivers/xen/biomerge.c
index 30d7f52eb7ca..55ed80c3a17c 100644
--- a/drivers/xen/biomerge.c
+++ b/drivers/xen/biomerge.c
@@ -17,7 +17,7 @@ bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
 	 * XXX: Add support for merging bio_vec when using different page
 	 * size in Xen and Linux.
 	 */
-	return 0;
+	return false;
 #endif
 }
 EXPORT_SYMBOL(xen_biovec_phys_mergeable);
diff --git a/drivers/xen/gntdev-common.h b/drivers/xen/gntdev-common.h
new file mode 100644
index 000000000000..2f8b949c3eeb
--- /dev/null
+++ b/drivers/xen/gntdev-common.h
@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Common functionality of grant device.
+ *
+ * Copyright (c) 2006-2007, D G Murray.
+ *           (c) 2009 Gerd Hoffmann <kraxel@redhat.com>
+ *           (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#ifndef _GNTDEV_COMMON_H
+#define _GNTDEV_COMMON_H
+
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/mmu_notifier.h>
+#include <linux/types.h>
+
+struct gntdev_dmabuf_priv;
+
+struct gntdev_priv {
+	/* Maps with visible offsets in the file descriptor. */
+	struct list_head maps;
+	/*
+	 * Maps that are not visible; will be freed on munmap.
+	 * Only populated if populate_freeable_maps == 1
+	 */
+	struct list_head freeable_maps;
+	/* lock protects maps and freeable_maps. */
+	struct mutex lock;
+	struct mm_struct *mm;
+	struct mmu_notifier mn;
+
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	/* Device for which DMA memory is allocated. */
+	struct device *dma_dev;
+#endif
+
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+	struct gntdev_dmabuf_priv *dmabuf_priv;
+#endif
+};
+
+struct gntdev_unmap_notify {
+	int flags;
+	/* Address relative to the start of the gntdev_grant_map. */
+	int addr;
+	int event;
+};
+
+struct gntdev_grant_map {
+	struct list_head next;
+	struct vm_area_struct *vma;
+	int index;
+	int count;
+	int flags;
+	refcount_t users;
+	struct gntdev_unmap_notify notify;
+	struct ioctl_gntdev_grant_ref *grants;
+	struct gnttab_map_grant_ref   *map_ops;
+	struct gnttab_unmap_grant_ref *unmap_ops;
+	struct gnttab_map_grant_ref   *kmap_ops;
+	struct gnttab_unmap_grant_ref *kunmap_ops;
+	struct page **pages;
+	unsigned long pages_vm_start;
+
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	/*
+	 * If dmabuf_vaddr is not NULL then this mapping is backed by DMA
+	 * capable memory.
+	 */
+
+	struct device *dma_dev;
+	/* Flags used to create this DMA buffer: GNTDEV_DMA_FLAG_XXX. */
+	int dma_flags;
+	void *dma_vaddr;
+	dma_addr_t dma_bus_addr;
+	/* Needed to avoid allocation in gnttab_dma_free_pages(). */
+	xen_pfn_t *frames;
+#endif
+};
+
+struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
+					  int dma_flags);
+
+void gntdev_add_map(struct gntdev_priv *priv, struct gntdev_grant_map *add);
+
+void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map);
+
+bool gntdev_account_mapped_pages(int count);
+
+int gntdev_map_grant_pages(struct gntdev_grant_map *map);
+
+#endif
diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c
new file mode 100644
index 000000000000..cba6b586bfbd
--- /dev/null
+++ b/drivers/xen/gntdev-dmabuf.c
@@ -0,0 +1,856 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Xen dma-buf functionality for gntdev.
+ *
+ * DMA buffer implementation is based on drivers/gpu/drm/drm_prime.c.
+ *
+ * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/dma-buf.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+
+#include <xen/xen.h>
+#include <xen/grant_table.h>
+
+#include "gntdev-common.h"
+#include "gntdev-dmabuf.h"
+
+#ifndef GRANT_INVALID_REF
+/*
+ * Note on usage of grant reference 0 as invalid grant reference:
+ * grant reference 0 is valid, but never exposed to a driver,
+ * because of the fact it is already in use/reserved by the PV console.
+ */
+#define GRANT_INVALID_REF	0
+#endif
+
+struct gntdev_dmabuf {
+	struct gntdev_dmabuf_priv *priv;
+	struct dma_buf *dmabuf;
+	struct list_head next;
+	int fd;
+
+	union {
+		struct {
+			/* Exported buffers are reference counted. */
+			struct kref refcount;
+
+			struct gntdev_priv *priv;
+			struct gntdev_grant_map *map;
+		} exp;
+		struct {
+			/* Granted references of the imported buffer. */
+			grant_ref_t *refs;
+			/* Scatter-gather table of the imported buffer. */
+			struct sg_table *sgt;
+			/* dma-buf attachment of the imported buffer. */
+			struct dma_buf_attachment *attach;
+		} imp;
+	} u;
+
+	/* Number of pages this buffer has. */
+	int nr_pages;
+	/* Pages of this buffer. */
+	struct page **pages;
+};
+
+struct gntdev_dmabuf_wait_obj {
+	struct list_head next;
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	struct completion completion;
+};
+
+struct gntdev_dmabuf_attachment {
+	struct sg_table *sgt;
+	enum dma_data_direction dir;
+};
+
+struct gntdev_dmabuf_priv {
+	/* List of exported DMA buffers. */
+	struct list_head exp_list;
+	/* List of wait objects. */
+	struct list_head exp_wait_list;
+	/* List of imported DMA buffers. */
+	struct list_head imp_list;
+	/* This is the lock which protects dma_buf_xxx lists. */
+	struct mutex lock;
+};
+
+/* DMA buffer export support. */
+
+/* Implementation of wait for exported DMA buffer to be released. */
+
+static void dmabuf_exp_release(struct kref *kref);
+
+static struct gntdev_dmabuf_wait_obj *
+dmabuf_exp_wait_obj_new(struct gntdev_dmabuf_priv *priv,
+			struct gntdev_dmabuf *gntdev_dmabuf)
+{
+	struct gntdev_dmabuf_wait_obj *obj;
+
+	obj = kzalloc(sizeof(*obj), GFP_KERNEL);
+	if (!obj)
+		return ERR_PTR(-ENOMEM);
+
+	init_completion(&obj->completion);
+	obj->gntdev_dmabuf = gntdev_dmabuf;
+
+	mutex_lock(&priv->lock);
+	list_add(&obj->next, &priv->exp_wait_list);
+	/* Put our reference and wait for gntdev_dmabuf's release to fire. */
+	kref_put(&gntdev_dmabuf->u.exp.refcount, dmabuf_exp_release);
+	mutex_unlock(&priv->lock);
+	return obj;
+}
+
+static void dmabuf_exp_wait_obj_free(struct gntdev_dmabuf_priv *priv,
+				     struct gntdev_dmabuf_wait_obj *obj)
+{
+	mutex_lock(&priv->lock);
+	list_del(&obj->next);
+	mutex_unlock(&priv->lock);
+	kfree(obj);
+}
+
+static int dmabuf_exp_wait_obj_wait(struct gntdev_dmabuf_wait_obj *obj,
+				    u32 wait_to_ms)
+{
+	if (wait_for_completion_timeout(&obj->completion,
+			msecs_to_jiffies(wait_to_ms)) <= 0)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static void dmabuf_exp_wait_obj_signal(struct gntdev_dmabuf_priv *priv,
+				       struct gntdev_dmabuf *gntdev_dmabuf)
+{
+	struct gntdev_dmabuf_wait_obj *obj;
+
+	list_for_each_entry(obj, &priv->exp_wait_list, next)
+		if (obj->gntdev_dmabuf == gntdev_dmabuf) {
+			pr_debug("Found gntdev_dmabuf in the wait list, wake\n");
+			complete_all(&obj->completion);
+			break;
+		}
+}
+
+static struct gntdev_dmabuf *
+dmabuf_exp_wait_obj_get_dmabuf(struct gntdev_dmabuf_priv *priv, int fd)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf, *ret = ERR_PTR(-ENOENT);
+
+	mutex_lock(&priv->lock);
+	list_for_each_entry(gntdev_dmabuf, &priv->exp_list, next)
+		if (gntdev_dmabuf->fd == fd) {
+			pr_debug("Found gntdev_dmabuf in the wait list\n");
+			kref_get(&gntdev_dmabuf->u.exp.refcount);
+			ret = gntdev_dmabuf;
+			break;
+		}
+	mutex_unlock(&priv->lock);
+	return ret;
+}
+
+static int dmabuf_exp_wait_released(struct gntdev_dmabuf_priv *priv, int fd,
+				    int wait_to_ms)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	struct gntdev_dmabuf_wait_obj *obj;
+	int ret;
+
+	pr_debug("Will wait for dma-buf with fd %d\n", fd);
+	/*
+	 * Try to find the DMA buffer: if not found means that
+	 * either the buffer has already been released or file descriptor
+	 * provided is wrong.
+	 */
+	gntdev_dmabuf = dmabuf_exp_wait_obj_get_dmabuf(priv, fd);
+	if (IS_ERR(gntdev_dmabuf))
+		return PTR_ERR(gntdev_dmabuf);
+
+	/*
+	 * gntdev_dmabuf still exists and is reference count locked by us now,
+	 * so prepare to wait: allocate wait object and add it to the wait list,
+	 * so we can find it on release.
+	 */
+	obj = dmabuf_exp_wait_obj_new(priv, gntdev_dmabuf);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	ret = dmabuf_exp_wait_obj_wait(obj, wait_to_ms);
+	dmabuf_exp_wait_obj_free(priv, obj);
+	return ret;
+}
+
+/* DMA buffer export support. */
+
+static struct sg_table *
+dmabuf_pages_to_sgt(struct page **pages, unsigned int nr_pages)
+{
+	struct sg_table *sgt;
+	int ret;
+
+	sgt = kmalloc(sizeof(*sgt), GFP_KERNEL);
+	if (!sgt) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = sg_alloc_table_from_pages(sgt, pages, nr_pages, 0,
+					nr_pages << PAGE_SHIFT,
+					GFP_KERNEL);
+	if (ret)
+		goto out;
+
+	return sgt;
+
+out:
+	kfree(sgt);
+	return ERR_PTR(ret);
+}
+
+static int dmabuf_exp_ops_attach(struct dma_buf *dma_buf,
+				 struct dma_buf_attachment *attach)
+{
+	struct gntdev_dmabuf_attachment *gntdev_dmabuf_attach;
+
+	gntdev_dmabuf_attach = kzalloc(sizeof(*gntdev_dmabuf_attach),
+				       GFP_KERNEL);
+	if (!gntdev_dmabuf_attach)
+		return -ENOMEM;
+
+	gntdev_dmabuf_attach->dir = DMA_NONE;
+	attach->priv = gntdev_dmabuf_attach;
+	return 0;
+}
+
+static void dmabuf_exp_ops_detach(struct dma_buf *dma_buf,
+				  struct dma_buf_attachment *attach)
+{
+	struct gntdev_dmabuf_attachment *gntdev_dmabuf_attach = attach->priv;
+
+	if (gntdev_dmabuf_attach) {
+		struct sg_table *sgt = gntdev_dmabuf_attach->sgt;
+
+		if (sgt) {
+			if (gntdev_dmabuf_attach->dir != DMA_NONE)
+				dma_unmap_sg_attrs(attach->dev, sgt->sgl,
+						   sgt->nents,
+						   gntdev_dmabuf_attach->dir,
+						   DMA_ATTR_SKIP_CPU_SYNC);
+			sg_free_table(sgt);
+		}
+
+		kfree(sgt);
+		kfree(gntdev_dmabuf_attach);
+		attach->priv = NULL;
+	}
+}
+
+static struct sg_table *
+dmabuf_exp_ops_map_dma_buf(struct dma_buf_attachment *attach,
+			   enum dma_data_direction dir)
+{
+	struct gntdev_dmabuf_attachment *gntdev_dmabuf_attach = attach->priv;
+	struct gntdev_dmabuf *gntdev_dmabuf = attach->dmabuf->priv;
+	struct sg_table *sgt;
+
+	pr_debug("Mapping %d pages for dev %p\n", gntdev_dmabuf->nr_pages,
+		 attach->dev);
+
+	if (dir == DMA_NONE || !gntdev_dmabuf_attach)
+		return ERR_PTR(-EINVAL);
+
+	/* Return the cached mapping when possible. */
+	if (gntdev_dmabuf_attach->dir == dir)
+		return gntdev_dmabuf_attach->sgt;
+
+	/*
+	 * Two mappings with different directions for the same attachment are
+	 * not allowed.
+	 */
+	if (gntdev_dmabuf_attach->dir != DMA_NONE)
+		return ERR_PTR(-EBUSY);
+
+	sgt = dmabuf_pages_to_sgt(gntdev_dmabuf->pages,
+				  gntdev_dmabuf->nr_pages);
+	if (!IS_ERR(sgt)) {
+		if (!dma_map_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir,
+				      DMA_ATTR_SKIP_CPU_SYNC)) {
+			sg_free_table(sgt);
+			kfree(sgt);
+			sgt = ERR_PTR(-ENOMEM);
+		} else {
+			gntdev_dmabuf_attach->sgt = sgt;
+			gntdev_dmabuf_attach->dir = dir;
+		}
+	}
+	if (IS_ERR(sgt))
+		pr_debug("Failed to map sg table for dev %p\n", attach->dev);
+	return sgt;
+}
+
+static void dmabuf_exp_ops_unmap_dma_buf(struct dma_buf_attachment *attach,
+					 struct sg_table *sgt,
+					 enum dma_data_direction dir)
+{
+	/* Not implemented. The unmap is done at dmabuf_exp_ops_detach(). */
+}
+
+static void dmabuf_exp_release(struct kref *kref)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf =
+		container_of(kref, struct gntdev_dmabuf, u.exp.refcount);
+
+	dmabuf_exp_wait_obj_signal(gntdev_dmabuf->priv, gntdev_dmabuf);
+	list_del(&gntdev_dmabuf->next);
+	kfree(gntdev_dmabuf);
+}
+
+static void dmabuf_exp_remove_map(struct gntdev_priv *priv,
+				  struct gntdev_grant_map *map)
+{
+	mutex_lock(&priv->lock);
+	list_del(&map->next);
+	gntdev_put_map(NULL /* already removed */, map);
+	mutex_unlock(&priv->lock);
+}
+
+static void dmabuf_exp_ops_release(struct dma_buf *dma_buf)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf = dma_buf->priv;
+	struct gntdev_dmabuf_priv *priv = gntdev_dmabuf->priv;
+
+	dmabuf_exp_remove_map(gntdev_dmabuf->u.exp.priv,
+			      gntdev_dmabuf->u.exp.map);
+	mutex_lock(&priv->lock);
+	kref_put(&gntdev_dmabuf->u.exp.refcount, dmabuf_exp_release);
+	mutex_unlock(&priv->lock);
+}
+
+static void *dmabuf_exp_ops_kmap(struct dma_buf *dma_buf,
+				 unsigned long page_num)
+{
+	/* Not implemented. */
+	return NULL;
+}
+
+static void dmabuf_exp_ops_kunmap(struct dma_buf *dma_buf,
+				  unsigned long page_num, void *addr)
+{
+	/* Not implemented. */
+}
+
+static int dmabuf_exp_ops_mmap(struct dma_buf *dma_buf,
+			       struct vm_area_struct *vma)
+{
+	/* Not implemented. */
+	return 0;
+}
+
+static const struct dma_buf_ops dmabuf_exp_ops =  {
+	.attach = dmabuf_exp_ops_attach,
+	.detach = dmabuf_exp_ops_detach,
+	.map_dma_buf = dmabuf_exp_ops_map_dma_buf,
+	.unmap_dma_buf = dmabuf_exp_ops_unmap_dma_buf,
+	.release = dmabuf_exp_ops_release,
+	.map = dmabuf_exp_ops_kmap,
+	.unmap = dmabuf_exp_ops_kunmap,
+	.mmap = dmabuf_exp_ops_mmap,
+};
+
+struct gntdev_dmabuf_export_args {
+	struct gntdev_priv *priv;
+	struct gntdev_grant_map *map;
+	struct gntdev_dmabuf_priv *dmabuf_priv;
+	struct device *dev;
+	int count;
+	struct page **pages;
+	u32 fd;
+};
+
+static int dmabuf_exp_from_pages(struct gntdev_dmabuf_export_args *args)
+{
+	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	int ret;
+
+	gntdev_dmabuf = kzalloc(sizeof(*gntdev_dmabuf), GFP_KERNEL);
+	if (!gntdev_dmabuf)
+		return -ENOMEM;
+
+	kref_init(&gntdev_dmabuf->u.exp.refcount);
+
+	gntdev_dmabuf->priv = args->dmabuf_priv;
+	gntdev_dmabuf->nr_pages = args->count;
+	gntdev_dmabuf->pages = args->pages;
+	gntdev_dmabuf->u.exp.priv = args->priv;
+	gntdev_dmabuf->u.exp.map = args->map;
+
+	exp_info.exp_name = KBUILD_MODNAME;
+	if (args->dev->driver && args->dev->driver->owner)
+		exp_info.owner = args->dev->driver->owner;
+	else
+		exp_info.owner = THIS_MODULE;
+	exp_info.ops = &dmabuf_exp_ops;
+	exp_info.size = args->count << PAGE_SHIFT;
+	exp_info.flags = O_RDWR;
+	exp_info.priv = gntdev_dmabuf;
+
+	gntdev_dmabuf->dmabuf = dma_buf_export(&exp_info);
+	if (IS_ERR(gntdev_dmabuf->dmabuf)) {
+		ret = PTR_ERR(gntdev_dmabuf->dmabuf);
+		gntdev_dmabuf->dmabuf = NULL;
+		goto fail;
+	}
+
+	ret = dma_buf_fd(gntdev_dmabuf->dmabuf, O_CLOEXEC);
+	if (ret < 0)
+		goto fail;
+
+	gntdev_dmabuf->fd = ret;
+	args->fd = ret;
+
+	pr_debug("Exporting DMA buffer with fd %d\n", ret);
+
+	mutex_lock(&args->dmabuf_priv->lock);
+	list_add(&gntdev_dmabuf->next, &args->dmabuf_priv->exp_list);
+	mutex_unlock(&args->dmabuf_priv->lock);
+	return 0;
+
+fail:
+	if (gntdev_dmabuf->dmabuf)
+		dma_buf_put(gntdev_dmabuf->dmabuf);
+	kfree(gntdev_dmabuf);
+	return ret;
+}
+
+static struct gntdev_grant_map *
+dmabuf_exp_alloc_backing_storage(struct gntdev_priv *priv, int dmabuf_flags,
+				 int count)
+{
+	struct gntdev_grant_map *map;
+
+	if (unlikely(count <= 0))
+		return ERR_PTR(-EINVAL);
+
+	if ((dmabuf_flags & GNTDEV_DMA_FLAG_WC) &&
+	    (dmabuf_flags & GNTDEV_DMA_FLAG_COHERENT)) {
+		pr_debug("Wrong dma-buf flags: 0x%x\n", dmabuf_flags);
+		return ERR_PTR(-EINVAL);
+	}
+
+	map = gntdev_alloc_map(priv, count, dmabuf_flags);
+	if (!map)
+		return ERR_PTR(-ENOMEM);
+
+	if (unlikely(gntdev_account_mapped_pages(count))) {
+		pr_debug("can't map %d pages: over limit\n", count);
+		gntdev_put_map(NULL, map);
+		return ERR_PTR(-ENOMEM);
+	}
+	return map;
+}
+
+static int dmabuf_exp_from_refs(struct gntdev_priv *priv, int flags,
+				int count, u32 domid, u32 *refs, u32 *fd)
+{
+	struct gntdev_grant_map *map;
+	struct gntdev_dmabuf_export_args args;
+	int i, ret;
+
+	map = dmabuf_exp_alloc_backing_storage(priv, flags, count);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	for (i = 0; i < count; i++) {
+		map->grants[i].domid = domid;
+		map->grants[i].ref = refs[i];
+	}
+
+	mutex_lock(&priv->lock);
+	gntdev_add_map(priv, map);
+	mutex_unlock(&priv->lock);
+
+	map->flags |= GNTMAP_host_map;
+#if defined(CONFIG_X86)
+	map->flags |= GNTMAP_device_map;
+#endif
+
+	ret = gntdev_map_grant_pages(map);
+	if (ret < 0)
+		goto out;
+
+	args.priv = priv;
+	args.map = map;
+	args.dev = priv->dma_dev;
+	args.dmabuf_priv = priv->dmabuf_priv;
+	args.count = map->count;
+	args.pages = map->pages;
+	args.fd = -1; /* Shut up unnecessary gcc warning for i386 */
+
+	ret = dmabuf_exp_from_pages(&args);
+	if (ret < 0)
+		goto out;
+
+	*fd = args.fd;
+	return 0;
+
+out:
+	dmabuf_exp_remove_map(priv, map);
+	return ret;
+}
+
+/* DMA buffer import support. */
+
+static int
+dmabuf_imp_grant_foreign_access(struct page **pages, u32 *refs,
+				int count, int domid)
+{
+	grant_ref_t priv_gref_head;
+	int i, ret;
+
+	ret = gnttab_alloc_grant_references(count, &priv_gref_head);
+	if (ret < 0) {
+		pr_debug("Cannot allocate grant references, ret %d\n", ret);
+		return ret;
+	}
+
+	for (i = 0; i < count; i++) {
+		int cur_ref;
+
+		cur_ref = gnttab_claim_grant_reference(&priv_gref_head);
+		if (cur_ref < 0) {
+			ret = cur_ref;
+			pr_debug("Cannot claim grant reference, ret %d\n", ret);
+			goto out;
+		}
+
+		gnttab_grant_foreign_access_ref(cur_ref, domid,
+						xen_page_to_gfn(pages[i]), 0);
+		refs[i] = cur_ref;
+	}
+
+	return 0;
+
+out:
+	gnttab_free_grant_references(priv_gref_head);
+	return ret;
+}
+
+static void dmabuf_imp_end_foreign_access(u32 *refs, int count)
+{
+	int i;
+
+	for (i = 0; i < count; i++)
+		if (refs[i] != GRANT_INVALID_REF)
+			gnttab_end_foreign_access(refs[i], 0, 0UL);
+}
+
+static void dmabuf_imp_free_storage(struct gntdev_dmabuf *gntdev_dmabuf)
+{
+	kfree(gntdev_dmabuf->pages);
+	kfree(gntdev_dmabuf->u.imp.refs);
+	kfree(gntdev_dmabuf);
+}
+
+static struct gntdev_dmabuf *dmabuf_imp_alloc_storage(int count)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	int i;
+
+	gntdev_dmabuf = kzalloc(sizeof(*gntdev_dmabuf), GFP_KERNEL);
+	if (!gntdev_dmabuf)
+		goto fail_no_free;
+
+	gntdev_dmabuf->u.imp.refs = kcalloc(count,
+					    sizeof(gntdev_dmabuf->u.imp.refs[0]),
+					    GFP_KERNEL);
+	if (!gntdev_dmabuf->u.imp.refs)
+		goto fail;
+
+	gntdev_dmabuf->pages = kcalloc(count,
+				       sizeof(gntdev_dmabuf->pages[0]),
+				       GFP_KERNEL);
+	if (!gntdev_dmabuf->pages)
+		goto fail;
+
+	gntdev_dmabuf->nr_pages = count;
+
+	for (i = 0; i < count; i++)
+		gntdev_dmabuf->u.imp.refs[i] = GRANT_INVALID_REF;
+
+	return gntdev_dmabuf;
+
+fail:
+	dmabuf_imp_free_storage(gntdev_dmabuf);
+fail_no_free:
+	return ERR_PTR(-ENOMEM);
+}
+
+static struct gntdev_dmabuf *
+dmabuf_imp_to_refs(struct gntdev_dmabuf_priv *priv, struct device *dev,
+		   int fd, int count, int domid)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf, *ret;
+	struct dma_buf *dma_buf;
+	struct dma_buf_attachment *attach;
+	struct sg_table *sgt;
+	struct sg_page_iter sg_iter;
+	int i;
+
+	dma_buf = dma_buf_get(fd);
+	if (IS_ERR(dma_buf))
+		return ERR_CAST(dma_buf);
+
+	gntdev_dmabuf = dmabuf_imp_alloc_storage(count);
+	if (IS_ERR(gntdev_dmabuf)) {
+		ret = gntdev_dmabuf;
+		goto fail_put;
+	}
+
+	gntdev_dmabuf->priv = priv;
+	gntdev_dmabuf->fd = fd;
+
+	attach = dma_buf_attach(dma_buf, dev);
+	if (IS_ERR(attach)) {
+		ret = ERR_CAST(attach);
+		goto fail_free_obj;
+	}
+
+	gntdev_dmabuf->u.imp.attach = attach;
+
+	sgt = dma_buf_map_attachment(attach, DMA_BIDIRECTIONAL);
+	if (IS_ERR(sgt)) {
+		ret = ERR_CAST(sgt);
+		goto fail_detach;
+	}
+
+	/* Check number of pages that imported buffer has. */
+	if (attach->dmabuf->size != gntdev_dmabuf->nr_pages << PAGE_SHIFT) {
+		ret = ERR_PTR(-EINVAL);
+		pr_debug("DMA buffer has %zu pages, user-space expects %d\n",
+			 attach->dmabuf->size, gntdev_dmabuf->nr_pages);
+		goto fail_unmap;
+	}
+
+	gntdev_dmabuf->u.imp.sgt = sgt;
+
+	/* Now convert sgt to array of pages and check for page validity. */
+	i = 0;
+	for_each_sg_page(sgt->sgl, &sg_iter, sgt->nents, 0) {
+		struct page *page = sg_page_iter_page(&sg_iter);
+		/*
+		 * Check if page is valid: this can happen if we are given
+		 * a page from VRAM or other resources which are not backed
+		 * by a struct page.
+		 */
+		if (!pfn_valid(page_to_pfn(page))) {
+			ret = ERR_PTR(-EINVAL);
+			goto fail_unmap;
+		}
+
+		gntdev_dmabuf->pages[i++] = page;
+	}
+
+	ret = ERR_PTR(dmabuf_imp_grant_foreign_access(gntdev_dmabuf->pages,
+						      gntdev_dmabuf->u.imp.refs,
+						      count, domid));
+	if (IS_ERR(ret))
+		goto fail_end_access;
+
+	pr_debug("Imported DMA buffer with fd %d\n", fd);
+
+	mutex_lock(&priv->lock);
+	list_add(&gntdev_dmabuf->next, &priv->imp_list);
+	mutex_unlock(&priv->lock);
+
+	return gntdev_dmabuf;
+
+fail_end_access:
+	dmabuf_imp_end_foreign_access(gntdev_dmabuf->u.imp.refs, count);
+fail_unmap:
+	dma_buf_unmap_attachment(attach, sgt, DMA_BIDIRECTIONAL);
+fail_detach:
+	dma_buf_detach(dma_buf, attach);
+fail_free_obj:
+	dmabuf_imp_free_storage(gntdev_dmabuf);
+fail_put:
+	dma_buf_put(dma_buf);
+	return ret;
+}
+
+/*
+ * Find the hyper dma-buf by its file descriptor and remove
+ * it from the buffer's list.
+ */
+static struct gntdev_dmabuf *
+dmabuf_imp_find_unlink(struct gntdev_dmabuf_priv *priv, int fd)
+{
+	struct gntdev_dmabuf *q, *gntdev_dmabuf, *ret = ERR_PTR(-ENOENT);
+
+	mutex_lock(&priv->lock);
+	list_for_each_entry_safe(gntdev_dmabuf, q, &priv->imp_list, next) {
+		if (gntdev_dmabuf->fd == fd) {
+			pr_debug("Found gntdev_dmabuf in the import list\n");
+			ret = gntdev_dmabuf;
+			list_del(&gntdev_dmabuf->next);
+			break;
+		}
+	}
+	mutex_unlock(&priv->lock);
+	return ret;
+}
+
+static int dmabuf_imp_release(struct gntdev_dmabuf_priv *priv, u32 fd)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	struct dma_buf_attachment *attach;
+	struct dma_buf *dma_buf;
+
+	gntdev_dmabuf = dmabuf_imp_find_unlink(priv, fd);
+	if (IS_ERR(gntdev_dmabuf))
+		return PTR_ERR(gntdev_dmabuf);
+
+	pr_debug("Releasing DMA buffer with fd %d\n", fd);
+
+	dmabuf_imp_end_foreign_access(gntdev_dmabuf->u.imp.refs,
+				      gntdev_dmabuf->nr_pages);
+
+	attach = gntdev_dmabuf->u.imp.attach;
+
+	if (gntdev_dmabuf->u.imp.sgt)
+		dma_buf_unmap_attachment(attach, gntdev_dmabuf->u.imp.sgt,
+					 DMA_BIDIRECTIONAL);
+	dma_buf = attach->dmabuf;
+	dma_buf_detach(attach->dmabuf, attach);
+	dma_buf_put(dma_buf);
+
+	dmabuf_imp_free_storage(gntdev_dmabuf);
+	return 0;
+}
+
+/* DMA buffer IOCTL support. */
+
+long gntdev_ioctl_dmabuf_exp_from_refs(struct gntdev_priv *priv, int use_ptemod,
+				       struct ioctl_gntdev_dmabuf_exp_from_refs __user *u)
+{
+	struct ioctl_gntdev_dmabuf_exp_from_refs op;
+	u32 *refs;
+	long ret;
+
+	if (use_ptemod) {
+		pr_debug("Cannot provide dma-buf: use_ptemode %d\n",
+			 use_ptemod);
+		return -EINVAL;
+	}
+
+	if (copy_from_user(&op, u, sizeof(op)) != 0)
+		return -EFAULT;
+
+	if (unlikely(op.count <= 0))
+		return -EINVAL;
+
+	refs = kcalloc(op.count, sizeof(*refs), GFP_KERNEL);
+	if (!refs)
+		return -ENOMEM;
+
+	if (copy_from_user(refs, u->refs, sizeof(*refs) * op.count) != 0) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	ret = dmabuf_exp_from_refs(priv, op.flags, op.count,
+				   op.domid, refs, &op.fd);
+	if (ret)
+		goto out;
+
+	if (copy_to_user(u, &op, sizeof(op)) != 0)
+		ret = -EFAULT;
+
+out:
+	kfree(refs);
+	return ret;
+}
+
+long gntdev_ioctl_dmabuf_exp_wait_released(struct gntdev_priv *priv,
+					   struct ioctl_gntdev_dmabuf_exp_wait_released __user *u)
+{
+	struct ioctl_gntdev_dmabuf_exp_wait_released op;
+
+	if (copy_from_user(&op, u, sizeof(op)) != 0)
+		return -EFAULT;
+
+	return dmabuf_exp_wait_released(priv->dmabuf_priv, op.fd,
+					op.wait_to_ms);
+}
+
+long gntdev_ioctl_dmabuf_imp_to_refs(struct gntdev_priv *priv,
+				     struct ioctl_gntdev_dmabuf_imp_to_refs __user *u)
+{
+	struct ioctl_gntdev_dmabuf_imp_to_refs op;
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	long ret;
+
+	if (copy_from_user(&op, u, sizeof(op)) != 0)
+		return -EFAULT;
+
+	if (unlikely(op.count <= 0))
+		return -EINVAL;
+
+	gntdev_dmabuf = dmabuf_imp_to_refs(priv->dmabuf_priv,
+					   priv->dma_dev, op.fd,
+					   op.count, op.domid);
+	if (IS_ERR(gntdev_dmabuf))
+		return PTR_ERR(gntdev_dmabuf);
+
+	if (copy_to_user(u->refs, gntdev_dmabuf->u.imp.refs,
+			 sizeof(*u->refs) * op.count) != 0) {
+		ret = -EFAULT;
+		goto out_release;
+	}
+	return 0;
+
+out_release:
+	dmabuf_imp_release(priv->dmabuf_priv, op.fd);
+	return ret;
+}
+
+long gntdev_ioctl_dmabuf_imp_release(struct gntdev_priv *priv,
+				     struct ioctl_gntdev_dmabuf_imp_release __user *u)
+{
+	struct ioctl_gntdev_dmabuf_imp_release op;
+
+	if (copy_from_user(&op, u, sizeof(op)) != 0)
+		return -EFAULT;
+
+	return dmabuf_imp_release(priv->dmabuf_priv, op.fd);
+}
+
+struct gntdev_dmabuf_priv *gntdev_dmabuf_init(void)
+{
+	struct gntdev_dmabuf_priv *priv;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_init(&priv->lock);
+	INIT_LIST_HEAD(&priv->exp_list);
+	INIT_LIST_HEAD(&priv->exp_wait_list);
+	INIT_LIST_HEAD(&priv->imp_list);
+
+	return priv;
+}
+
+void gntdev_dmabuf_fini(struct gntdev_dmabuf_priv *priv)
+{
+	kfree(priv);
+}
diff --git a/drivers/xen/gntdev-dmabuf.h b/drivers/xen/gntdev-dmabuf.h
new file mode 100644
index 000000000000..7220a53d0fc5
--- /dev/null
+++ b/drivers/xen/gntdev-dmabuf.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Xen dma-buf functionality for gntdev.
+ *
+ * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#ifndef _GNTDEV_DMABUF_H
+#define _GNTDEV_DMABUF_H
+
+#include <xen/gntdev.h>
+
+struct gntdev_dmabuf_priv;
+struct gntdev_priv;
+
+struct gntdev_dmabuf_priv *gntdev_dmabuf_init(void);
+
+void gntdev_dmabuf_fini(struct gntdev_dmabuf_priv *priv);
+
+long gntdev_ioctl_dmabuf_exp_from_refs(struct gntdev_priv *priv, int use_ptemod,
+				       struct ioctl_gntdev_dmabuf_exp_from_refs __user *u);
+
+long gntdev_ioctl_dmabuf_exp_wait_released(struct gntdev_priv *priv,
+					   struct ioctl_gntdev_dmabuf_exp_wait_released __user *u);
+
+long gntdev_ioctl_dmabuf_imp_to_refs(struct gntdev_priv *priv,
+				     struct ioctl_gntdev_dmabuf_imp_to_refs __user *u);
+
+long gntdev_ioctl_dmabuf_imp_release(struct gntdev_priv *priv,
+				     struct ioctl_gntdev_dmabuf_imp_release __user *u);
+
+#endif
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index bd56653b9bbc..c866a62f766d 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -6,6 +6,7 @@
  *
  * Copyright (c) 2006-2007, D G Murray.
  *           (c) 2009 Gerd Hoffmann <kraxel@redhat.com>
+ *           (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
  *
  * This program is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
@@ -26,10 +27,6 @@
 #include <linux/init.h>
 #include <linux/miscdevice.h>
 #include <linux/fs.h>
-#include <linux/mm.h>
-#include <linux/mman.h>
-#include <linux/mmu_notifier.h>
-#include <linux/types.h>
 #include <linux/uaccess.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
@@ -37,6 +34,9 @@
 #include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/refcount.h>
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+#include <linux/of_device.h>
+#endif
 
 #include <xen/xen.h>
 #include <xen/grant_table.h>
@@ -47,6 +47,11 @@
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 
+#include "gntdev-common.h"
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+#include "gntdev-dmabuf.h"
+#endif
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Derek G. Murray <Derek.Murray@cl.cam.ac.uk>, "
 	      "Gerd Hoffmann <kraxel@redhat.com>");
@@ -62,51 +67,23 @@ static atomic_t pages_mapped = ATOMIC_INIT(0);
 static int use_ptemod;
 #define populate_freeable_maps use_ptemod
 
-struct gntdev_priv {
-	/* maps with visible offsets in the file descriptor */
-	struct list_head maps;
-	/* maps that are not visible; will be freed on munmap.
-	 * Only populated if populate_freeable_maps == 1 */
-	struct list_head freeable_maps;
-	/* lock protects maps and freeable_maps */
-	struct mutex lock;
-	struct mm_struct *mm;
-	struct mmu_notifier mn;
-};
-
-struct unmap_notify {
-	int flags;
-	/* Address relative to the start of the grant_map */
-	int addr;
-	int event;
-};
-
-struct grant_map {
-	struct list_head next;
-	struct vm_area_struct *vma;
-	int index;
-	int count;
-	int flags;
-	refcount_t users;
-	struct unmap_notify notify;
-	struct ioctl_gntdev_grant_ref *grants;
-	struct gnttab_map_grant_ref   *map_ops;
-	struct gnttab_unmap_grant_ref *unmap_ops;
-	struct gnttab_map_grant_ref   *kmap_ops;
-	struct gnttab_unmap_grant_ref *kunmap_ops;
-	struct page **pages;
-	unsigned long pages_vm_start;
-};
+static int unmap_grant_pages(struct gntdev_grant_map *map,
+			     int offset, int pages);
 
-static int unmap_grant_pages(struct grant_map *map, int offset, int pages);
+static struct miscdevice gntdev_miscdev;
 
 /* ------------------------------------------------------------------ */
 
+bool gntdev_account_mapped_pages(int count)
+{
+	return atomic_add_return(count, &pages_mapped) > limit;
+}
+
 static void gntdev_print_maps(struct gntdev_priv *priv,
 			      char *text, int text_index)
 {
 #ifdef DEBUG
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	pr_debug("%s: maps list (priv %p)\n", __func__, priv);
 	list_for_each_entry(map, &priv->maps, next)
@@ -116,13 +93,32 @@ static void gntdev_print_maps(struct gntdev_priv *priv,
 #endif
 }
 
-static void gntdev_free_map(struct grant_map *map)
+static void gntdev_free_map(struct gntdev_grant_map *map)
 {
 	if (map == NULL)
 		return;
 
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	if (map->dma_vaddr) {
+		struct gnttab_dma_alloc_args args;
+
+		args.dev = map->dma_dev;
+		args.coherent = !!(map->dma_flags & GNTDEV_DMA_FLAG_COHERENT);
+		args.nr_pages = map->count;
+		args.pages = map->pages;
+		args.frames = map->frames;
+		args.vaddr = map->dma_vaddr;
+		args.dev_bus_addr = map->dma_bus_addr;
+
+		gnttab_dma_free_pages(&args);
+	} else
+#endif
 	if (map->pages)
 		gnttab_free_pages(map->count, map->pages);
+
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	kfree(map->frames);
+#endif
 	kfree(map->pages);
 	kfree(map->grants);
 	kfree(map->map_ops);
@@ -132,12 +128,13 @@ static void gntdev_free_map(struct grant_map *map)
 	kfree(map);
 }
 
-static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
+struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
+					  int dma_flags)
 {
-	struct grant_map *add;
+	struct gntdev_grant_map *add;
 	int i;
 
-	add = kzalloc(sizeof(struct grant_map), GFP_KERNEL);
+	add = kzalloc(sizeof(*add), GFP_KERNEL);
 	if (NULL == add)
 		return NULL;
 
@@ -155,6 +152,37 @@ static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
 	    NULL == add->pages)
 		goto err;
 
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	add->dma_flags = dma_flags;
+
+	/*
+	 * Check if this mapping is requested to be backed
+	 * by a DMA buffer.
+	 */
+	if (dma_flags & (GNTDEV_DMA_FLAG_WC | GNTDEV_DMA_FLAG_COHERENT)) {
+		struct gnttab_dma_alloc_args args;
+
+		add->frames = kcalloc(count, sizeof(add->frames[0]),
+				      GFP_KERNEL);
+		if (!add->frames)
+			goto err;
+
+		/* Remember the device, so we can free DMA memory. */
+		add->dma_dev = priv->dma_dev;
+
+		args.dev = priv->dma_dev;
+		args.coherent = !!(dma_flags & GNTDEV_DMA_FLAG_COHERENT);
+		args.nr_pages = count;
+		args.pages = add->pages;
+		args.frames = add->frames;
+
+		if (gnttab_dma_alloc_pages(&args))
+			goto err;
+
+		add->dma_vaddr = args.vaddr;
+		add->dma_bus_addr = args.dev_bus_addr;
+	} else
+#endif
 	if (gnttab_alloc_pages(count, add->pages))
 		goto err;
 
@@ -176,9 +204,9 @@ err:
 	return NULL;
 }
 
-static void gntdev_add_map(struct gntdev_priv *priv, struct grant_map *add)
+void gntdev_add_map(struct gntdev_priv *priv, struct gntdev_grant_map *add)
 {
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	list_for_each_entry(map, &priv->maps, next) {
 		if (add->index + add->count < map->index) {
@@ -193,10 +221,10 @@ done:
 	gntdev_print_maps(priv, "[new]", add->index);
 }
 
-static struct grant_map *gntdev_find_map_index(struct gntdev_priv *priv,
-		int index, int count)
+static struct gntdev_grant_map *gntdev_find_map_index(struct gntdev_priv *priv,
+						      int index, int count)
 {
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	list_for_each_entry(map, &priv->maps, next) {
 		if (map->index != index)
@@ -208,7 +236,7 @@ static struct grant_map *gntdev_find_map_index(struct gntdev_priv *priv,
 	return NULL;
 }
 
-static void gntdev_put_map(struct gntdev_priv *priv, struct grant_map *map)
+void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map)
 {
 	if (!map)
 		return;
@@ -239,7 +267,7 @@ static void gntdev_put_map(struct gntdev_priv *priv, struct grant_map *map)
 static int find_grant_ptes(pte_t *pte, pgtable_t token,
 		unsigned long addr, void *data)
 {
-	struct grant_map *map = data;
+	struct gntdev_grant_map *map = data;
 	unsigned int pgnr = (addr - map->vma->vm_start) >> PAGE_SHIFT;
 	int flags = map->flags | GNTMAP_application_map | GNTMAP_contains_pte;
 	u64 pte_maddr;
@@ -272,7 +300,7 @@ static int set_grant_ptes_as_special(pte_t *pte, pgtable_t token,
 }
 #endif
 
-static int map_grant_pages(struct grant_map *map)
+int gntdev_map_grant_pages(struct gntdev_grant_map *map)
 {
 	int i, err = 0;
 
@@ -325,11 +353,20 @@ static int map_grant_pages(struct grant_map *map)
 		map->unmap_ops[i].handle = map->map_ops[i].handle;
 		if (use_ptemod)
 			map->kunmap_ops[i].handle = map->kmap_ops[i].handle;
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+		else if (map->dma_vaddr) {
+			unsigned long bfn;
+
+			bfn = pfn_to_bfn(page_to_pfn(map->pages[i]));
+			map->unmap_ops[i].dev_bus_addr = __pfn_to_phys(bfn);
+		}
+#endif
 	}
 	return err;
 }
 
-static int __unmap_grant_pages(struct grant_map *map, int offset, int pages)
+static int __unmap_grant_pages(struct gntdev_grant_map *map, int offset,
+			       int pages)
 {
 	int i, err = 0;
 	struct gntab_unmap_queue_data unmap_data;
@@ -364,7 +401,8 @@ static int __unmap_grant_pages(struct grant_map *map, int offset, int pages)
 	return err;
 }
 
-static int unmap_grant_pages(struct grant_map *map, int offset, int pages)
+static int unmap_grant_pages(struct gntdev_grant_map *map, int offset,
+			     int pages)
 {
 	int range, err = 0;
 
@@ -396,7 +434,7 @@ static int unmap_grant_pages(struct grant_map *map, int offset, int pages)
 
 static void gntdev_vma_open(struct vm_area_struct *vma)
 {
-	struct grant_map *map = vma->vm_private_data;
+	struct gntdev_grant_map *map = vma->vm_private_data;
 
 	pr_debug("gntdev_vma_open %p\n", vma);
 	refcount_inc(&map->users);
@@ -404,7 +442,7 @@ static void gntdev_vma_open(struct vm_area_struct *vma)
 
 static void gntdev_vma_close(struct vm_area_struct *vma)
 {
-	struct grant_map *map = vma->vm_private_data;
+	struct gntdev_grant_map *map = vma->vm_private_data;
 	struct file *file = vma->vm_file;
 	struct gntdev_priv *priv = file->private_data;
 
@@ -428,7 +466,7 @@ static void gntdev_vma_close(struct vm_area_struct *vma)
 static struct page *gntdev_vma_find_special_page(struct vm_area_struct *vma,
 						 unsigned long addr)
 {
-	struct grant_map *map = vma->vm_private_data;
+	struct gntdev_grant_map *map = vma->vm_private_data;
 
 	return map->pages[(addr - map->pages_vm_start) >> PAGE_SHIFT];
 }
@@ -441,7 +479,7 @@ static const struct vm_operations_struct gntdev_vmops = {
 
 /* ------------------------------------------------------------------ */
 
-static void unmap_if_in_range(struct grant_map *map,
+static void unmap_if_in_range(struct gntdev_grant_map *map,
 			      unsigned long start, unsigned long end)
 {
 	unsigned long mstart, mend;
@@ -470,7 +508,7 @@ static void mn_invl_range_start(struct mmu_notifier *mn,
 				unsigned long start, unsigned long end)
 {
 	struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	mutex_lock(&priv->lock);
 	list_for_each_entry(map, &priv->maps, next) {
@@ -486,7 +524,7 @@ static void mn_release(struct mmu_notifier *mn,
 		       struct mm_struct *mm)
 {
 	struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int err;
 
 	mutex_lock(&priv->lock);
@@ -531,6 +569,15 @@ static int gntdev_open(struct inode *inode, struct file *flip)
 	INIT_LIST_HEAD(&priv->freeable_maps);
 	mutex_init(&priv->lock);
 
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+	priv->dmabuf_priv = gntdev_dmabuf_init();
+	if (IS_ERR(priv->dmabuf_priv)) {
+		ret = PTR_ERR(priv->dmabuf_priv);
+		kfree(priv);
+		return ret;
+	}
+#endif
+
 	if (use_ptemod) {
 		priv->mm = get_task_mm(current);
 		if (!priv->mm) {
@@ -548,6 +595,17 @@ static int gntdev_open(struct inode *inode, struct file *flip)
 	}
 
 	flip->private_data = priv;
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	priv->dma_dev = gntdev_miscdev.this_device;
+
+	/*
+	 * The device is not spawn from a device tree, so arch_setup_dma_ops
+	 * is not called, thus leaving the device with dummy DMA ops.
+	 * Fix this by calling of_dma_configure() with a NULL node to set
+	 * default DMA ops.
+	 */
+	of_dma_configure(priv->dma_dev, NULL, true);
+#endif
 	pr_debug("priv %p\n", priv);
 
 	return 0;
@@ -556,21 +614,27 @@ static int gntdev_open(struct inode *inode, struct file *flip)
 static int gntdev_release(struct inode *inode, struct file *flip)
 {
 	struct gntdev_priv *priv = flip->private_data;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	pr_debug("priv %p\n", priv);
 
 	mutex_lock(&priv->lock);
 	while (!list_empty(&priv->maps)) {
-		map = list_entry(priv->maps.next, struct grant_map, next);
+		map = list_entry(priv->maps.next,
+				 struct gntdev_grant_map, next);
 		list_del(&map->next);
 		gntdev_put_map(NULL /* already removed */, map);
 	}
 	WARN_ON(!list_empty(&priv->freeable_maps));
 	mutex_unlock(&priv->lock);
 
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+	gntdev_dmabuf_fini(priv->dmabuf_priv);
+#endif
+
 	if (use_ptemod)
 		mmu_notifier_unregister(&priv->mn, priv->mm);
+
 	kfree(priv);
 	return 0;
 }
@@ -579,7 +643,7 @@ static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv,
 				       struct ioctl_gntdev_map_grant_ref __user *u)
 {
 	struct ioctl_gntdev_map_grant_ref op;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int err;
 
 	if (copy_from_user(&op, u, sizeof(op)) != 0)
@@ -589,11 +653,11 @@ static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv,
 		return -EINVAL;
 
 	err = -ENOMEM;
-	map = gntdev_alloc_map(priv, op.count);
+	map = gntdev_alloc_map(priv, op.count, 0 /* This is not a dma-buf. */);
 	if (!map)
 		return err;
 
-	if (unlikely(atomic_add_return(op.count, &pages_mapped) > limit)) {
+	if (unlikely(gntdev_account_mapped_pages(op.count))) {
 		pr_debug("can't map: over limit\n");
 		gntdev_put_map(NULL, map);
 		return err;
@@ -620,7 +684,7 @@ static long gntdev_ioctl_unmap_grant_ref(struct gntdev_priv *priv,
 					 struct ioctl_gntdev_unmap_grant_ref __user *u)
 {
 	struct ioctl_gntdev_unmap_grant_ref op;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int err = -ENOENT;
 
 	if (copy_from_user(&op, u, sizeof(op)) != 0)
@@ -646,7 +710,7 @@ static long gntdev_ioctl_get_offset_for_vaddr(struct gntdev_priv *priv,
 {
 	struct ioctl_gntdev_get_offset_for_vaddr op;
 	struct vm_area_struct *vma;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int rv = -EINVAL;
 
 	if (copy_from_user(&op, u, sizeof(op)) != 0)
@@ -677,7 +741,7 @@ static long gntdev_ioctl_get_offset_for_vaddr(struct gntdev_priv *priv,
 static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u)
 {
 	struct ioctl_gntdev_unmap_notify op;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int rc;
 	int out_flags;
 	unsigned int out_event;
@@ -962,6 +1026,20 @@ static long gntdev_ioctl(struct file *flip,
 	case IOCTL_GNTDEV_GRANT_COPY:
 		return gntdev_ioctl_grant_copy(priv, ptr);
 
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+	case IOCTL_GNTDEV_DMABUF_EXP_FROM_REFS:
+		return gntdev_ioctl_dmabuf_exp_from_refs(priv, use_ptemod, ptr);
+
+	case IOCTL_GNTDEV_DMABUF_EXP_WAIT_RELEASED:
+		return gntdev_ioctl_dmabuf_exp_wait_released(priv, ptr);
+
+	case IOCTL_GNTDEV_DMABUF_IMP_TO_REFS:
+		return gntdev_ioctl_dmabuf_imp_to_refs(priv, ptr);
+
+	case IOCTL_GNTDEV_DMABUF_IMP_RELEASE:
+		return gntdev_ioctl_dmabuf_imp_release(priv, ptr);
+#endif
+
 	default:
 		pr_debug("priv %p, unknown cmd %x\n", priv, cmd);
 		return -ENOIOCTLCMD;
@@ -975,7 +1053,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 	struct gntdev_priv *priv = flip->private_data;
 	int index = vma->vm_pgoff;
 	int count = vma_pages(vma);
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int i, err = -EINVAL;
 
 	if ((vma->vm_flags & VM_WRITE) && !(vma->vm_flags & VM_SHARED))
@@ -1032,7 +1110,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 		}
 	}
 
-	err = map_grant_pages(map);
+	err = gntdev_map_grant_pages(map);
 	if (err)
 		goto out_put_map;
 
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index ba9f3eec2bd0..7bafa703a992 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -45,6 +45,9 @@
 #include <linux/workqueue.h>
 #include <linux/ratelimit.h>
 #include <linux/moduleparam.h>
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+#include <linux/dma-mapping.h>
+#endif
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
@@ -57,6 +60,7 @@
 #ifdef CONFIG_X86
 #include <asm/xen/cpuid.h>
 #endif
+#include <xen/mem-reservation.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
@@ -769,29 +773,18 @@ void gnttab_free_auto_xlat_frames(void)
 }
 EXPORT_SYMBOL_GPL(gnttab_free_auto_xlat_frames);
 
-/**
- * gnttab_alloc_pages - alloc pages suitable for grant mapping into
- * @nr_pages: number of pages to alloc
- * @pages: returns the pages
- */
-int gnttab_alloc_pages(int nr_pages, struct page **pages)
+int gnttab_pages_set_private(int nr_pages, struct page **pages)
 {
 	int i;
-	int ret;
-
-	ret = alloc_xenballooned_pages(nr_pages, pages);
-	if (ret < 0)
-		return ret;
 
 	for (i = 0; i < nr_pages; i++) {
 #if BITS_PER_LONG < 64
 		struct xen_page_foreign *foreign;
 
 		foreign = kzalloc(sizeof(*foreign), GFP_KERNEL);
-		if (!foreign) {
-			gnttab_free_pages(nr_pages, pages);
+		if (!foreign)
 			return -ENOMEM;
-		}
+
 		set_page_private(pages[i], (unsigned long)foreign);
 #endif
 		SetPagePrivate(pages[i]);
@@ -799,14 +792,30 @@ int gnttab_alloc_pages(int nr_pages, struct page **pages)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(gnttab_alloc_pages);
+EXPORT_SYMBOL_GPL(gnttab_pages_set_private);
 
 /**
- * gnttab_free_pages - free pages allocated by gnttab_alloc_pages()
- * @nr_pages; number of pages to free
- * @pages: the pages
+ * gnttab_alloc_pages - alloc pages suitable for grant mapping into
+ * @nr_pages: number of pages to alloc
+ * @pages: returns the pages
  */
-void gnttab_free_pages(int nr_pages, struct page **pages)
+int gnttab_alloc_pages(int nr_pages, struct page **pages)
+{
+	int ret;
+
+	ret = alloc_xenballooned_pages(nr_pages, pages);
+	if (ret < 0)
+		return ret;
+
+	ret = gnttab_pages_set_private(nr_pages, pages);
+	if (ret < 0)
+		gnttab_free_pages(nr_pages, pages);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(gnttab_alloc_pages);
+
+void gnttab_pages_clear_private(int nr_pages, struct page **pages)
 {
 	int i;
 
@@ -818,10 +827,114 @@ void gnttab_free_pages(int nr_pages, struct page **pages)
 			ClearPagePrivate(pages[i]);
 		}
 	}
+}
+EXPORT_SYMBOL_GPL(gnttab_pages_clear_private);
+
+/**
+ * gnttab_free_pages - free pages allocated by gnttab_alloc_pages()
+ * @nr_pages; number of pages to free
+ * @pages: the pages
+ */
+void gnttab_free_pages(int nr_pages, struct page **pages)
+{
+	gnttab_pages_clear_private(nr_pages, pages);
 	free_xenballooned_pages(nr_pages, pages);
 }
 EXPORT_SYMBOL_GPL(gnttab_free_pages);
 
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+/**
+ * gnttab_dma_alloc_pages - alloc DMAable pages suitable for grant mapping into
+ * @args: arguments to the function
+ */
+int gnttab_dma_alloc_pages(struct gnttab_dma_alloc_args *args)
+{
+	unsigned long pfn, start_pfn;
+	size_t size;
+	int i, ret;
+
+	size = args->nr_pages << PAGE_SHIFT;
+	if (args->coherent)
+		args->vaddr = dma_alloc_coherent(args->dev, size,
+						 &args->dev_bus_addr,
+						 GFP_KERNEL | __GFP_NOWARN);
+	else
+		args->vaddr = dma_alloc_wc(args->dev, size,
+					   &args->dev_bus_addr,
+					   GFP_KERNEL | __GFP_NOWARN);
+	if (!args->vaddr) {
+		pr_debug("Failed to allocate DMA buffer of size %zu\n", size);
+		return -ENOMEM;
+	}
+
+	start_pfn = __phys_to_pfn(args->dev_bus_addr);
+	for (pfn = start_pfn, i = 0; pfn < start_pfn + args->nr_pages;
+			pfn++, i++) {
+		struct page *page = pfn_to_page(pfn);
+
+		args->pages[i] = page;
+		args->frames[i] = xen_page_to_gfn(page);
+		xenmem_reservation_scrub_page(page);
+	}
+
+	xenmem_reservation_va_mapping_reset(args->nr_pages, args->pages);
+
+	ret = xenmem_reservation_decrease(args->nr_pages, args->frames);
+	if (ret != args->nr_pages) {
+		pr_debug("Failed to decrease reservation for DMA buffer\n");
+		ret = -EFAULT;
+		goto fail;
+	}
+
+	ret = gnttab_pages_set_private(args->nr_pages, args->pages);
+	if (ret < 0)
+		goto fail;
+
+	return 0;
+
+fail:
+	gnttab_dma_free_pages(args);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(gnttab_dma_alloc_pages);
+
+/**
+ * gnttab_dma_free_pages - free DMAable pages
+ * @args: arguments to the function
+ */
+int gnttab_dma_free_pages(struct gnttab_dma_alloc_args *args)
+{
+	size_t size;
+	int i, ret;
+
+	gnttab_pages_clear_private(args->nr_pages, args->pages);
+
+	for (i = 0; i < args->nr_pages; i++)
+		args->frames[i] = page_to_xen_pfn(args->pages[i]);
+
+	ret = xenmem_reservation_increase(args->nr_pages, args->frames);
+	if (ret != args->nr_pages) {
+		pr_debug("Failed to decrease reservation for DMA buffer\n");
+		ret = -EFAULT;
+	} else {
+		ret = 0;
+	}
+
+	xenmem_reservation_va_mapping_update(args->nr_pages, args->pages,
+					     args->frames);
+
+	size = args->nr_pages << PAGE_SHIFT;
+	if (args->coherent)
+		dma_free_coherent(args->dev, size,
+				  args->vaddr, args->dev_bus_addr);
+	else
+		dma_free_wc(args->dev, size,
+			    args->vaddr, args->dev_bus_addr);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(gnttab_dma_free_pages);
+#endif
+
 /* Handling of paged out grant targets (GNTST_eagain) */
 #define MAX_DELAY 256
 static inline void
diff --git a/drivers/xen/mem-reservation.c b/drivers/xen/mem-reservation.c
new file mode 100644
index 000000000000..084799c6180e
--- /dev/null
+++ b/drivers/xen/mem-reservation.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/******************************************************************************
+ * Xen memory reservation utilities.
+ *
+ * Copyright (c) 2003, B Dragovic
+ * Copyright (c) 2003-2004, M Williamson, K Fraser
+ * Copyright (c) 2005 Dan M. Smith, IBM Corporation
+ * Copyright (c) 2010 Daniel Kiper
+ * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#include <asm/xen/hypercall.h>
+
+#include <xen/interface/memory.h>
+#include <xen/mem-reservation.h>
+
+/*
+ * Use one extent per PAGE_SIZE to avoid to break down the page into
+ * multiple frame.
+ */
+#define EXTENT_ORDER (fls(XEN_PFN_PER_PAGE) - 1)
+
+#ifdef CONFIG_XEN_HAVE_PVMMU
+void __xenmem_reservation_va_mapping_update(unsigned long count,
+					    struct page **pages,
+					    xen_pfn_t *frames)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		struct page *page = pages[i];
+		unsigned long pfn = page_to_pfn(page);
+
+		BUG_ON(!page);
+
+		/*
+		 * We don't support PV MMU when Linux and Xen is using
+		 * different page granularity.
+		 */
+		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
+
+		set_phys_to_machine(pfn, frames[i]);
+
+		/* Link back into the page tables if not highmem. */
+		if (!PageHighMem(page)) {
+			int ret;
+
+			ret = HYPERVISOR_update_va_mapping(
+					(unsigned long)__va(pfn << PAGE_SHIFT),
+					mfn_pte(frames[i], PAGE_KERNEL),
+					0);
+			BUG_ON(ret);
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(__xenmem_reservation_va_mapping_update);
+
+void __xenmem_reservation_va_mapping_reset(unsigned long count,
+					   struct page **pages)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		struct page *page = pages[i];
+		unsigned long pfn = page_to_pfn(page);
+
+		/*
+		 * We don't support PV MMU when Linux and Xen are using
+		 * different page granularity.
+		 */
+		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
+
+		if (!PageHighMem(page)) {
+			int ret;
+
+			ret = HYPERVISOR_update_va_mapping(
+					(unsigned long)__va(pfn << PAGE_SHIFT),
+					__pte_ma(0), 0);
+			BUG_ON(ret);
+		}
+		__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+	}
+}
+EXPORT_SYMBOL_GPL(__xenmem_reservation_va_mapping_reset);
+#endif /* CONFIG_XEN_HAVE_PVMMU */
+
+/* @frames is an array of PFNs */
+int xenmem_reservation_increase(int count, xen_pfn_t *frames)
+{
+	struct xen_memory_reservation reservation = {
+		.address_bits = 0,
+		.extent_order = EXTENT_ORDER,
+		.domid        = DOMID_SELF
+	};
+
+	/* XENMEM_populate_physmap requires a PFN based on Xen granularity. */
+	set_xen_guest_handle(reservation.extent_start, frames);
+	reservation.nr_extents = count;
+	return HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation);
+}
+EXPORT_SYMBOL_GPL(xenmem_reservation_increase);
+
+/* @frames is an array of GFNs */
+int xenmem_reservation_decrease(int count, xen_pfn_t *frames)
+{
+	struct xen_memory_reservation reservation = {
+		.address_bits = 0,
+		.extent_order = EXTENT_ORDER,
+		.domid        = DOMID_SELF
+	};
+
+	/* XENMEM_decrease_reservation requires a GFN */
+	set_xen_guest_handle(reservation.extent_start, frames);
+	reservation.nr_extents = count;
+	return HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
+}
+EXPORT_SYMBOL_GPL(xenmem_reservation_decrease);
diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c
index b437fccd4e62..294f35ce9e46 100644
--- a/drivers/xen/xen-balloon.c
+++ b/drivers/xen/xen-balloon.c
@@ -81,7 +81,7 @@ static void watch_target(struct xenbus_watch *watch,
 			static_max = new_target;
 		else
 			static_max >>= PAGE_SHIFT - 10;
-		target_diff = xen_pv_domain() ? 0
+		target_diff = (xen_pv_domain() || xen_initial_domain()) ? 0
 				: static_max - balloon_stats.target_pages;
 	}
 
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index e2f3e8b0fba9..14a3d4cbc2a7 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -654,9 +654,9 @@ static struct vscsibk_pend *scsiback_get_pend_req(struct vscsiif_back_ring *ring
 	struct scsiback_nexus *nexus = tpg->tpg_nexus;
 	struct se_session *se_sess = nexus->tvn_se_sess;
 	struct vscsibk_pend *req;
-	int tag, i;
+	int tag, cpu, i;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
+	tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
 	if (tag < 0) {
 		pr_err("Unable to obtain tag for vscsiif_request\n");
 		return ERR_PTR(-ENOMEM);
@@ -665,6 +665,7 @@ static struct vscsibk_pend *scsiback_get_pend_req(struct vscsiif_back_ring *ring
 	req = &((struct vscsibk_pend *)se_sess->sess_cmd_map)[tag];
 	memset(req, 0, sizeof(*req));
 	req->se_cmd.map_tag = tag;
+	req->se_cmd.map_cpu = cpu;
 
 	for (i = 0; i < VSCSI_MAX_GRANTS; i++)
 		req->grant_handles[i] = SCSIBACK_INVALID_HANDLE;
@@ -1387,9 +1388,7 @@ static int scsiback_check_stop_free(struct se_cmd *se_cmd)
 
 static void scsiback_release_cmd(struct se_cmd *se_cmd)
 {
-	struct se_session *se_sess = se_cmd->se_sess;
-
-	percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag);
+	target_free_tag(se_cmd->se_sess, se_cmd);
 }
 
 static u32 scsiback_sess_get_index(struct se_session *se_sess)
@@ -1532,7 +1531,7 @@ static int scsiback_make_nexus(struct scsiback_tpg *tpg,
 		goto out_unlock;
 	}
 
-	tv_nexus->tvn_se_sess = target_alloc_session(&tpg->se_tpg,
+	tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg,
 						     VSCSI_DEFAULT_SESSION_TAGS,
 						     sizeof(struct vscsibk_pend),
 						     TARGET_PROT_NORMAL, name,
@@ -1587,7 +1586,7 @@ static int scsiback_drop_nexus(struct scsiback_tpg *tpg)
 	/*
 	 * Release the SCSI I_T Nexus to the emulated xen-pvscsi Target Port
 	 */
-	transport_deregister_session(tv_nexus->tvn_se_sess);
+	target_remove_session(se_sess);
 	tpg->tpg_nexus = NULL;
 	mutex_unlock(&tpg->tv_tpg_mutex);
 
@@ -1743,9 +1742,7 @@ static void scsiback_port_unlink(struct se_portal_group *se_tpg,
 }
 
 static struct se_portal_group *
-scsiback_make_tpg(struct se_wwn *wwn,
-		   struct config_group *group,
-		   const char *name)
+scsiback_make_tpg(struct se_wwn *wwn, const char *name)
 {
 	struct scsiback_tport *tport = container_of(wwn,
 			struct scsiback_tport, tport_wwn);